5558 files changed, 228053 insertions, 99201 deletions

diff --git a/.mailmap b/.mailmap
index 7fa9d41fbdaf..29ddeb1bf015 100644
--- a/.mailmap
+++ b/.mailmap
@@ -186,6 +186,9 @@ Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
 Uwe Kleine-König <ukl@pengutronix.de>
 Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
 Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
+Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com>
+Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com>
+Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org>
 Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 708dc4c166e4..2754fe83f0d4 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -64,8 +64,6 @@ auxdisplay/
 	- misc. LCD driver documentation (cfag12864b, ks0108).
 backlight/
 	- directory with info on controlling backlights in flat panel displays
-bcache.txt
-	- Block-layer cache on fast SSDs to improve slow (raid) I/O performance.
 block/
 	- info on the Block I/O (BIO) layer.
 blockdev/
@@ -78,18 +76,10 @@ bus-devices/
 	- directory with info on TI GPMC (General Purpose Memory Controller)
 bus-virt-phys-mapping.txt
 	- how to access I/O mapped memory from within device drivers.
-cachetlb.txt
-	- describes the cache/TLB flushing interfaces Linux uses.
 cdrom/
 	- directory with information on the CD-ROM drivers that Linux has.
 cgroup-v1/
 	- cgroups v1 features, including cpusets and memory controller.
-cgroup-v2.txt
-	- cgroups v2 features, including cpusets and memory controller.
-circular-buffers.txt
-	- how to make use of the existing circular buffer infrastructure
-clk.txt
-	- info on the common clock framework
 cma/
 	- Continuous Memory Area (CMA) debugfs interface.
 conf.py
diff --git a/Documentation/ABI/stable/sysfs-bus-vmbus b/Documentation/ABI/stable/sysfs-bus-vmbus
index 0c9d9dcd2151..3eaffbb2d468 100644
--- a/Documentation/ABI/stable/sysfs-bus-vmbus
+++ b/Documentation/ABI/stable/sysfs-bus-vmbus
@@ -1,25 +1,25 @@
-What:		/sys/bus/vmbus/devices/vmbus_*/id
+What:		/sys/bus/vmbus/devices/<UUID>/id
 Date:		Jul 2009
 KernelVersion:	2.6.31
 Contact:	K. Y. Srinivasan <kys@microsoft.com>
 Description:	The VMBus child_relid of the device's primary channel
 Users:		tools/hv/lsvmbus
 
-What:		/sys/bus/vmbus/devices/vmbus_*/class_id
+What:		/sys/bus/vmbus/devices/<UUID>/class_id
 Date:		Jul 2009
 KernelVersion:	2.6.31
 Contact:	K. Y. Srinivasan <kys@microsoft.com>
 Description:	The VMBus interface type GUID of the device
 Users:		tools/hv/lsvmbus
 
-What:		/sys/bus/vmbus/devices/vmbus_*/device_id
+What:		/sys/bus/vmbus/devices/<UUID>/device_id
 Date:		Jul 2009
 KernelVersion:	2.6.31
 Contact:	K. Y. Srinivasan <kys@microsoft.com>
 Description:	The VMBus interface instance GUID of the device
 Users:		tools/hv/lsvmbus
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channel_vp_mapping
+What:		/sys/bus/vmbus/devices/<UUID>/channel_vp_mapping
 Date:		Jul 2015
 KernelVersion:	4.2.0
 Contact:	K. Y. Srinivasan <kys@microsoft.com>
@@ -28,112 +28,112 @@ Description:	The mapping of which primary/sub channels are bound to which
 		Format: <channel's child_relid:the bound cpu's number>
 Users:		tools/hv/lsvmbus
 
-What:		/sys/bus/vmbus/devices/vmbus_*/device
+What:		/sys/bus/vmbus/devices/<UUID>/device
 Date:		Dec. 2015
 KernelVersion:	4.5
 Contact:	K. Y. Srinivasan <kys@microsoft.com>
 Description:	The 16 bit device ID of the device
 Users:		tools/hv/lsvmbus and user level RDMA libraries
 
-What:		/sys/bus/vmbus/devices/vmbus_*/vendor
+What:		/sys/bus/vmbus/devices/<UUID>/vendor
 Date:		Dec. 2015
 KernelVersion:	4.5
 Contact:	K. Y. Srinivasan <kys@microsoft.com>
 Description:	The 16 bit vendor ID of the device
 Users:		tools/hv/lsvmbus and user level RDMA libraries
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Directory for per-channel information
 		NN is the VMBUS relid associtated with the channel.
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/cpu
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/cpu
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	VCPU (sub)channel is affinitized to
 Users:		tools/hv/lsvmbus and other debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/cpu
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/cpu
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	VCPU (sub)channel is affinitized to
 Users:		tools/hv/lsvmbus and other debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/in_mask
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/in_mask
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Host to guest channel interrupt mask
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/latency
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/latency
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Channel signaling latency
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/out_mask
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/out_mask
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Guest to host channel interrupt mask
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/pending
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/pending
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Channel interrupt pending state
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/read_avail
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/read_avail
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Bytes available to read
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/write_avail
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/write_avail
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Bytes available to write
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/events
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/events
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Number of times we have signaled the host
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/interrupts
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/interrupts
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Number of times we have taken an interrupt (incoming)
 Users:		Debugging tools
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/subchannel_id
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/subchannel_id
 Date:		January. 2018
 KernelVersion:	4.16
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Subchannel ID associated with VMBUS channel
 Users:		Debugging tools and userspace drivers
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/monitor_id
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/monitor_id
 Date:		January. 2018
 KernelVersion:	4.16
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
 Description:	Monitor bit associated with channel
 Users:		Debugging tools and userspace drivers
 
-What:		/sys/bus/vmbus/devices/vmbus_*/channels/NN/ring
+What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/ring
 Date:		January. 2018
 KernelVersion:	4.16
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
index 5b2d0f08867c..3e90e1f3bf0a 100644
--- a/Documentation/ABI/stable/sysfs-devices-node
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -90,4 +90,4 @@ Date:		December 2009
 Contact:	Lee Schermerhorn <lee.schermerhorn@hp.com>
 Description:
 		The node's huge page size control/query attributes.
-		See Documentation/vm/hugetlbpage.txt
\ No newline at end of file
+		See Documentation/admin-guide/mm/hugetlbpage.rst
\ No newline at end of file
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index c702c78f24d8..08d456e07b53 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -189,6 +189,28 @@ Description:
 		The file will read "hotplug", "wired" and "not used" if the
 		information is available, and "unknown" otherwise.
 
+What:		/sys/bus/usb/devices/.../(hub interface)/portX/quirks
+Date:		May 2018
+Contact:	Nicolas Boichat <drinkcat@chromium.org>
+Description:
+		In some cases, we care about time-to-active for devices
+		connected on a specific port (e.g. non-standard USB port like
+		pogo pins), where the device to be connected is known in
+		advance, and behaves well according to the specification.
+		This attribute is a bit-field that controls the behavior of
+		a specific port:
+		 - Bit 0 of this field selects the "old" enumeration scheme,
+		   as it is considerably faster (it only causes one USB reset
+		   instead of 2).
+		   The old enumeration scheme can also be selected globally
+		   using /sys/module/usbcore/parameters/old_scheme_first, but
+		   it is often not desirable as the new scheme was introduced to
+		   increase compatibility with more devices.
+		 - Bit 1 reduces TRSTRCY to the 10 ms that are required by the
+		   USB 2.0 specification, instead of the 50 ms that are normally
+		   used to help make enumeration work better on some high speed
+		   devices.
+
 What:		/sys/bus/usb/devices/.../(hub interface)/portX/over_current_count
 Date:		February 2018
 Contact:	Richard Leitner <richard.leitner@skidata.com>
@@ -236,3 +258,21 @@ Description:
 		Supported values are 0 - 15.
 		More information on how besl values map to microseconds can be found in
 		USB 2.0 ECN Errata for Link Power Management, section 4.10)
+
+What:		/sys/bus/usb/devices/.../rx_lanes
+Date:		March 2018
+Contact:	Mathias Nyman <mathias.nyman@linux.intel.com>
+Description:
+		Number of rx lanes the device is using.
+		USB 3.2 adds Dual-lane support, 2 rx and 2 tx lanes over Type-C.
+		Inter-Chip SSIC devices support asymmetric lanes up to 4 lanes per
+		direction. Devices before USB 3.2 are single lane (rx_lanes = 1)
+
+What:		/sys/bus/usb/devices/.../tx_lanes
+Date:		March 2018
+Contact:	Mathias Nyman <mathias.nyman@linux.intel.com>
+Description:
+		Number of tx lanes the device is using.
+		USB 3.2 adds Dual-lane support, 2 rx and 2 tx -lanes over Type-C.
+		Inter-Chip SSIC devices support asymmetric lanes up to 4 lanes per
+		direction. Devices before USB 3.2 are single lane (tx_lanes = 1)
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index 640f65e79ef1..8e69345c37cc 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -244,3 +244,11 @@ Description:    read only
                 Returns 1 if the psl timebase register is synchronized
                 with the core timebase register, 0 otherwise.
 Users:          https://github.com/ibm-capi/libcxl
+
+What:           /sys/class/cxl/<card>/tunneled_ops_supported
+Date:           May 2018
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Returns 1 if tunneled operations are supported in capi mode,
+                0 otherwise.
+Users:          https://github.com/ibm-capi/libcxl
diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index f85ce9e327b9..5e23e22dce1b 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -1,3 +1,458 @@
+===== General Properties =====
+
+What:		/sys/class/power_supply/<supply_name>/manufacturer
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the name of the device manufacturer.
+
+		Access: Read
+		Valid values: Represented as string
+
+What:		/sys/class/power_supply/<supply_name>/model_name
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the name of the device model.
+
+		Access: Read
+		Valid values: Represented as string
+
+What:		/sys/class/power_supply/<supply_name>/serial_number
+Date:		January 2008
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the serial number of the device.
+
+		Access: Read
+		Valid values: Represented as string
+
+What:		/sys/class/power_supply/<supply_name>/type
+Date:		May 2010
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Describes the main type of the supply.
+
+		Access: Read
+		Valid values: "Battery", "UPS", "Mains", "USB"
+
+===== Battery Properties =====
+
+What:		/sys/class/power_supply/<supply_name>/capacity
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Fine grain representation of battery capacity.
+		Access: Read
+		Valid values: 0 - 100 (percent)
+
+What:		/sys/class/power_supply/<supply_name>/capacity_alert_max
+Date:		July 2012
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Maximum battery capacity trip-wire value where the supply will
+		notify user-space of the event. This is normally used for the
+		battery discharging scenario where user-space needs to know the
+		battery has dropped to an upper level so it can take
+		appropriate action (e.g. warning user that battery level is
+		low).
+
+		Access: Read, Write
+		Valid values: 0 - 100 (percent)
+
+What:		/sys/class/power_supply/<supply_name>/capacity_alert_min
+Date:		July 2012
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Minimum battery capacity trip-wire value where the supply will
+		notify user-space of the event. This is normally used for the
+		battery discharging scenario where user-space needs to know the
+		battery has dropped to a lower level so it can take
+		appropriate action (e.g. warning user that battery level is
+		critically low).
+
+		Access: Read, Write
+		Valid values: 0 - 100 (percent)
+
+What:		/sys/class/power_supply/<supply_name>/capacity_level
+Date:		June 2009
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Coarse representation of battery capacity.
+
+		Access: Read
+		Valid values: "Unknown", "Critical", "Low", "Normal", "High",
+			      "Full"
+
+What:		/sys/class/power_supply/<supply_name>/current_avg
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports an average IBAT current reading for the battery, over a
+		fixed period. Normally devices will provide a fixed interval in
+		which they average readings to smooth out the reported value.
+
+		Access: Read
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/current_max
+Date:		October 2010
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the maximum IBAT current allowed into the battery.
+
+		Access: Read
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/current_now
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports an instant, single IBAT current reading for the battery.
+		This value is not averaged/smoothed.
+
+		Access: Read
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/charge_type
+Date:		July 2009
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Represents the type of charging currently being applied to the
+		battery.
+
+		Access: Read
+		Valid values: "Unknown", "N/A", "Trickle", "Fast"
+
+What:		/sys/class/power_supply/<supply_name>/charge_term_current
+Date:		July 2014
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the charging current value which is used to determine
+		when the battery is considered full and charging should end.
+
+		Access: Read
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/health
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the health of the battery or battery side of charger
+		functionality.
+
+		Access: Read
+		Valid values: "Unknown", "Good", "Overheat", "Dead",
+			      "Over voltage", "Unspecified failure", "Cold",
+			      "Watchdog timer expire", "Safety timer expire"
+
+What:		/sys/class/power_supply/<supply_name>/precharge_current
+Date:		June 2017
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the charging current applied during pre-charging phase
+		for a battery charge cycle.
+
+		Access: Read
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/present
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports whether a battery is present or not in the system.
+
+		Access: Read
+		Valid values:
+			0: Absent
+			1: Present
+
+What:		/sys/class/power_supply/<supply_name>/status
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Represents the charging status of the battery. Normally this
+		is read-only reporting although for some supplies this can be
+		used to enable/disable charging to the battery.
+
+		Access: Read, Write
+		Valid values: "Unknown", "Charging", "Discharging",
+			      "Not charging", "Full"
+
+What:		/sys/class/power_supply/<supply_name>/technology
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Describes the battery technology supported by the supply.
+
+		Access: Read
+		Valid values: "Unknown", "NiMH", "Li-ion", "Li-poly", "LiFe",
+			      "NiCd", "LiMn"
+
+What:		/sys/class/power_supply/<supply_name>/temp
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the current TBAT battery temperature reading.
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/temp_alert_max
+Date:		July 2012
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Maximum TBAT temperature trip-wire value where the supply will
+		notify user-space of the event. This is normally used for the
+		battery charging scenario where user-space needs to know the
+		battery temperature has crossed an upper threshold so it can
+		take appropriate action (e.g. warning user that battery level is
+		critically high, and charging has stopped).
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/temp_alert_min
+Date:		July 2012
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Minimum TBAT temperature trip-wire value where the supply will
+		notify user-space of the event. This is normally used for the
+		battery charging scenario where user-space needs to know the
+		battery temperature has crossed a lower threshold so it can take
+		appropriate action (e.g. warning user that battery level is
+		high, and charging current has been reduced accordingly to
+		remedy the situation).
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/temp_max
+Date:		July 2014
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the maximum allowed TBAT battery temperature for
+		charging.
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/temp_min
+Date:		July 2014
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the minimum allowed TBAT battery temperature for
+		charging.
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/voltage_avg,
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports an average VBAT voltage reading for the battery, over a
+		fixed period. Normally devices will provide a fixed interval in
+		which they average readings to smooth out the reported value.
+
+		Access: Read
+		Valid values: Represented in microvolts
+
+What:		/sys/class/power_supply/<supply_name>/voltage_max,
+Date:		January 2008
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the maximum safe VBAT voltage permitted for the battery,
+		during charging.
+
+		Access: Read
+		Valid values: Represented in microvolts
+
+What:		/sys/class/power_supply/<supply_name>/voltage_min,
+Date:		January 2008
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the minimum safe VBAT voltage permitted for the battery,
+		during discharging.
+
+		Access: Read
+		Valid values: Represented in microvolts
+
+What:		/sys/class/power_supply/<supply_name>/voltage_now,
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports an instant, single VBAT voltage reading for the battery.
+		This value is not averaged/smoothed.
+
+		Access: Read
+		Valid values: Represented in microvolts
+
+===== USB Properties =====
+
+What: 		/sys/class/power_supply/<supply_name>/current_avg
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports an average IBUS current reading over a fixed period.
+		Normally devices will provide a fixed interval in which they
+		average readings to smooth out the reported value.
+
+		Access: Read
+		Valid values: Represented in microamps
+
+
+What: 		/sys/class/power_supply/<supply_name>/current_max
+Date:		October 2010
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the maximum IBUS current the supply can support.
+
+		Access: Read
+		Valid values: Represented in microamps
+
+What: 		/sys/class/power_supply/<supply_name>/current_now
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the IBUS current supplied now. This value is generally
+		read-only reporting, unless the 'online' state of the supply
+		is set to be programmable, in which case this value can be set
+		within the reported min/max range.
+
+		Access: Read, Write
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/input_current_limit
+Date:		July 2014
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Details the incoming IBUS current limit currently set in the
+		supply. Normally this is configured based on the type of
+		connection made (e.g. A configured SDP should output a maximum
+		of 500mA so the input current limit is set to the same value).
+
+		Access: Read, Write
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/online,
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Indicates if VBUS is present for the supply. When the supply is
+		online, and the supply allows it, then it's possible to switch
+		between online states (e.g. Fixed -> Programmable for a PD_PPS
+		USB supply so voltage and current can be controlled).
+
+		Access: Read, Write
+		Valid values:
+			0: Offline
+			1: Online Fixed - Fixed Voltage Supply
+			2: Online Programmable - Programmable Voltage Supply
+
+What:		/sys/class/power_supply/<supply_name>/temp
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the current supply temperature reading. This would
+		normally be the internal temperature of the device itself (e.g
+		TJUNC temperature of an IC)
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/temp_alert_max
+Date:		July 2012
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Maximum supply temperature trip-wire value where the supply will
+		notify user-space of the event. This is normally used for the
+		charging scenario where user-space needs to know the supply
+		temperature has crossed an upper threshold so it can take
+		appropriate action (e.g. warning user that the supply
+		temperature is critically high, and charging has stopped to
+		remedy the situation).
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/temp_alert_min
+Date:		July 2012
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Minimum supply temperature trip-wire value where the supply will
+		notify user-space of the event. This is normally used for the
+		charging scenario where user-space needs to know the supply
+		temperature has crossed a lower threshold so it can take
+		appropriate action (e.g. warning user that the supply
+		temperature is high, and charging current has been reduced
+		accordingly to remedy the situation).
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/temp_max
+Date:		July 2014
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the maximum allowed supply temperature for operation.
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/<supply_name>/temp_min
+Date:		July 2014
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the mainimum allowed supply temperature for operation.
+
+		Access: Read
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What: 		/sys/class/power_supply/<supply_name>/usb_type
+Date:		March 2018
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports what type of USB connection is currently active for
+		the supply, for example it can show if USB-PD capable source
+		is attached.
+
+		Access: Read-Only
+		Valid values: "Unknown", "SDP", "DCP", "CDP", "ACA", "C", "PD",
+			      "PD_DRP", "PD_PPS", "BrickID"
+
+What: 		/sys/class/power_supply/<supply_name>/voltage_max
+Date:		January 2008
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the maximum VBUS voltage the supply can support.
+
+		Access: Read
+		Valid values: Represented in microvolts
+
+What: 		/sys/class/power_supply/<supply_name>/voltage_min
+Date:		January 2008
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the minimum VBUS voltage the supply can support.
+
+		Access: Read
+		Valid values: Represented in microvolts
+
+What: 		/sys/class/power_supply/<supply_name>/voltage_now
+Date:		May 2007
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the VBUS voltage supplied now. This value is generally
+		read-only reporting, unless the 'online' state of the supply
+		is set to be programmable, in which case this value can be set
+		within the reported min/max range.
+
+		Access: Read, Write
+		Valid values: Represented in microvolts
+
+===== Device Specific Properties =====
+
 What:		/sys/class/power/ds2760-battery.*/charge_now
 Date:		May 2010
 KernelVersion:	2.6.35
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 025b7cf3768d..bd4975e132d3 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -478,6 +478,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/meltdown
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
+		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
index e21c00571cf4..fdaa2162fae1 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
@@ -12,4 +12,4 @@ Description:
 			free_hugepages
 			surplus_hugepages
 			resv_hugepages
-		See Documentation/vm/hugetlbpage.txt for details.
+		See Documentation/admin-guide/mm/hugetlbpage.rst for details.
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
index 73e653ee2481..dfc13244cda3 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-ksm
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
@@ -40,7 +40,7 @@ Description:	Kernel Samepage Merging daemon sysfs interface
 		sleep_millisecs: how many milliseconds ksm should sleep between
 		scans.
 
-		See Documentation/vm/ksm.txt for more information.
+		See Documentation/vm/ksm.rst for more information.
 
 What:		/sys/kernel/mm/ksm/merge_across_nodes
 Date:		January 2013
diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab
index 2cc0a72b64be..29601d93a1c2 100644
--- a/Documentation/ABI/testing/sysfs-kernel-slab
+++ b/Documentation/ABI/testing/sysfs-kernel-slab
@@ -37,7 +37,7 @@ Description:
 		The alloc_calls file is read-only and lists the kernel code
 		locations from which allocations for this cache were performed.
 		The alloc_calls file only contains information if debugging is
-		enabled for that cache (see Documentation/vm/slub.txt).
+		enabled for that cache (see Documentation/vm/slub.rst).
 
 What:		/sys/kernel/slab/cache/alloc_fastpath
 Date:		February 2008
@@ -219,7 +219,7 @@ Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 Description:
 		The free_calls file is read-only and lists the locations of
 		object frees if slab debugging is enabled (see
-		Documentation/vm/slub.txt).
+		Documentation/vm/slub.rst).
 
 What:		/sys/kernel/slab/cache/free_fastpath
 Date:		February 2008
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index a27fbfb0efb8..65eb856526b7 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -1,3 +1,5 @@
+What is RCU?  --  "Read, Copy, Update"
+
 Please note that the "What is RCU?" LWN series is an excellent place
 to start learning about RCU:
 
diff --git a/Documentation/acpi/cppc_sysfs.txt b/Documentation/acpi/cppc_sysfs.txt
new file mode 100644
index 000000000000..f20fb445135d
--- /dev/null
+++ b/Documentation/acpi/cppc_sysfs.txt
@@ -0,0 +1,69 @@
+
+	Collaborative Processor Performance Control (CPPC)
+
+CPPC defined in the ACPI spec describes a mechanism for the OS to manage the
+performance of a logical processor on a contigious and abstract performance
+scale. CPPC exposes a set of registers to describe abstract performance scale,
+to request performance levels and to measure per-cpu delivered performance.
+
+For more details on CPPC please refer to the ACPI specification at:
+
+http://uefi.org/specifications
+
+Some of the CPPC registers are exposed via sysfs under:
+
+/sys/devices/system/cpu/cpuX/acpi_cppc/
+
+for each cpu X
+
+--------------------------------------------------------------------------------
+
+$ ls -lR  /sys/devices/system/cpu/cpu0/acpi_cppc/
+/sys/devices/system/cpu/cpu0/acpi_cppc/:
+total 0
+-r--r--r-- 1 root root 65536 Mar  5 19:38 feedback_ctrs
+-r--r--r-- 1 root root 65536 Mar  5 19:38 highest_perf
+-r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_freq
+-r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_nonlinear_perf
+-r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_perf
+-r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_freq
+-r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_perf
+-r--r--r-- 1 root root 65536 Mar  5 19:38 reference_perf
+-r--r--r-- 1 root root 65536 Mar  5 19:38 wraparound_time
+
+--------------------------------------------------------------------------------
+
+* highest_perf : Highest performance of this processor (abstract scale).
+* nominal_perf : Highest sustained performance of this processor (abstract scale).
+* lowest_nonlinear_perf : Lowest performance of this processor with nonlinear
+  power savings (abstract scale).
+* lowest_perf : Lowest performance of this processor (abstract scale).
+
+* lowest_freq : CPU frequency corresponding to lowest_perf (in MHz).
+* nominal_freq : CPU frequency corresponding to nominal_perf (in MHz).
+  The above frequencies should only be used to report processor performance in
+  freqency instead of abstract scale. These values should not be used for any
+  functional decisions.
+
+* feedback_ctrs : Includes both Reference and delivered performance counter.
+  Reference counter ticks up proportional to processor's reference performance.
+  Delivered counter ticks up proportional to processor's delivered performance.
+* wraparound_time: Minimum time for the feedback counters to wraparound (seconds).
+* reference_perf : Performance level at which reference performance counter
+  accumulates (abstract scale).
+
+--------------------------------------------------------------------------------
+
+		Computing Average Delivered Performance
+
+Below describes the steps to compute the average performance delivered by taking
+two different snapshots of feedback counters at time T1 and T2.
+
+T1: Read feedback_ctrs as fbc_t1
+    Wait or run some workload
+T2: Read feedback_ctrs as fbc_t2
+
+delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
+reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
+
+delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
diff --git a/Documentation/bcache.txt b/Documentation/admin-guide/bcache.rst
index c0ce64d75bbf..c0ce64d75bbf 100644
--- a/Documentation/bcache.txt
+++ b/Documentation/admin-guide/bcache.rst
diff --git a/Documentation/cgroup-v2.txt b/Documentation/admin-guide/cgroup-v2.rst
index 74cdeaed9f7a..74cdeaed9f7a 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/admin-guide/cgroup-v2.rst
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 5bb9161dbe6a..48d70af11652 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -48,6 +48,7 @@ configure specific aspects of kernel behavior to your liking.
    :maxdepth: 1
 
    initrd
+   cgroup-v2
    serial-console
    braille-console
    parport
@@ -60,9 +61,11 @@ configure specific aspects of kernel behavior to your liking.
    mono
    java
    ras
+   bcache
    pm/index
    thunderbolt
    LSM/index
+   mm/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 11fc28ecdb6d..1beb30d8d7fc 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -106,11 +106,11 @@
 			use by PCI
 			Format: <irq>,<irq>...
 
-	acpi_mask_gpe=  [HW,ACPI]
+	acpi_mask_gpe=	[HW,ACPI]
 			Due to the existence of _Lxx/_Exx, some GPEs triggered
 			by unsupported hardware/firmware features can result in
-                        GPE floodings that cannot be automatically disabled by
-                        the GPE dispatcher.
+			GPE floodings that cannot be automatically disabled by
+			the GPE dispatcher.
 			This facility can be used to prevent such uncontrolled
 			GPE floodings.
 			Format: <int>
@@ -472,10 +472,10 @@
 			for platform specific values (SB1, Loongson3 and
 			others).
 
-	ccw_timeout_log [S390]
+	ccw_timeout_log	[S390]
 			See Documentation/s390/CommonIO for details.
 
-	cgroup_disable= [KNL] Disable a particular controller
+	cgroup_disable=	[KNL] Disable a particular controller
 			Format: {name of the controller(s) to disable}
 			The effects of cgroup_disable=foo are:
 			- foo isn't auto-mounted if you mount all cgroups in
@@ -518,7 +518,7 @@
 			those clocks in any way. This parameter is useful for
 			debug and development, but should not be needed on a
 			platform with proper driver support.  For more
-			information, see Documentation/clk.txt.
+			information, see Documentation/driver-api/clk.rst.
 
 	clock=		[BUGS=X86-32, HW] gettimeofday clocksource override.
 			[Deprecated]
@@ -587,11 +587,6 @@
 			Sets the size of memory pool for coherent, atomic dma
 			allocations, by default set to 256K.
 
-	code_bytes	[X86] How many bytes of object code to print
-			in an oops report.
-			Range: 0 - 8192
-			Default: 64
-
 	com20020=	[HW,NET] ARCnet - COM20020 chipset
 			Format:
 			<io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
@@ -641,8 +636,8 @@
 		hvc<n>	Use the hypervisor console device <n>. This is for
 			both Xen and PowerPC hypervisors.
 
-                If the device connected to the port is not a TTY but a braille
-                device, prepend "brl," before the device type, for instance
+		If the device connected to the port is not a TTY but a braille
+		device, prepend "brl," before the device type, for instance
 			console=brl,ttyS0
 		For now, only VisioBraille is supported.
 
@@ -662,7 +657,7 @@
 
 	consoleblank=	[KNL] The console blank (screen saver) timeout in
 			seconds. A value of 0 disables the blank timer.
-                       Defaults to 0.
+			Defaults to 0.
 
 	coredump_filter=
 			[KNL] Change the default value for
@@ -730,7 +725,7 @@
 			or memory reserved is below 4G.
 
 	cryptomgr.notests
-                        [KNL] Disable crypto self-tests
+			[KNL] Disable crypto self-tests
 
 	cs89x0_dma=	[HW,NET]
 			Format: <dma>
@@ -746,7 +741,7 @@
 			Format: <port#>,<type>
 			See also Documentation/input/devices/joystick-parport.rst
 
-	ddebug_query=   [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
+	ddebug_query=	[KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
 			time. See
 			Documentation/admin-guide/dynamic-debug-howto.rst for
 			details.  Deprecated, see dyndbg.
@@ -833,7 +828,7 @@
 			causing system reset or hang due to sending
 			INIT from AP to BSP.
 
-	disable_ddw     [PPC/PSERIES]
+	disable_ddw	[PPC/PSERIES]
 			Disable Dynamic DMA Window support. Use this if
 			to workaround buggy firmware.
 
@@ -1025,6 +1020,12 @@
 			address. The serial port must already be setup
 			and configured. Options are not yet supported.
 
+		qcom_geni,<addr>
+			Start an early, polled-mode console on a Qualcomm
+			Generic Interface (GENI) based serial port at the
+			specified address. The serial port must already be
+			setup and configured. Options are not yet supported.
+
 	earlyprintk=	[X86,SH,ARM,M68k,S390]
 			earlyprintk=vga
 			earlyprintk=efi
@@ -1188,7 +1189,7 @@
 			parameter will force ia64_sal_cache_flush to call
 			ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
 
-	forcepae [X86-32]
+	forcepae	[X86-32]
 			Forcefully enable Physical Address Extension (PAE).
 			Many Pentium M systems disable PAE but may have a
 			functionally usable PAE implementation.
@@ -1247,7 +1248,7 @@
 
 	gamma=		[HW,DRM]
 
-	gart_fix_e820=  [X86_64] disable the fix e820 for K8 GART
+	gart_fix_e820=	[X86_64] disable the fix e820 for K8 GART
 			Format: off | on
 			default: on
 
@@ -1341,23 +1342,32 @@
 			x86-64 are 2M (when the CPU supports "pse") and 1G
 			(when the CPU supports the "pdpe1gb" cpuinfo flag).
 
-	hvc_iucv=	[S390] Number of z/VM IUCV hypervisor console (HVC)
-			       terminal devices. Valid values: 0..8
-	hvc_iucv_allow=	[S390] Comma-separated list of z/VM user IDs.
-			       If specified, z/VM IUCV HVC accepts connections
-			       from listed z/VM user IDs only.
+	hung_task_panic=
+			[KNL] Should the hung task detector generate panics.
+			Format: <integer>
 
+			A nonzero value instructs the kernel to panic when a
+			hung task is detected. The default value is controlled
+			by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
+			option. The value selected by this boot parameter can
+			be changed later by the kernel.hung_task_panic sysctl.
+
+	hvc_iucv=	[S390]	Number of z/VM IUCV hypervisor console (HVC)
+				terminal devices. Valid values: 0..8
+	hvc_iucv_allow=	[S390]	Comma-separated list of z/VM user IDs.
+				If specified, z/VM IUCV HVC accepts connections
+				from listed z/VM user IDs only.
 	keep_bootcon	[KNL]
 			Do not unregister boot console at start. This is only
 			useful for debugging when something happens in the window
 			between unregistering the boot console and initializing
 			the real console.
 
-	i2c_bus=	[HW] Override the default board specific I2C bus speed
-			     or register an additional I2C bus that is not
-			     registered from board initialization code.
-			     Format:
-			     <bus_id>,<clkrate>
+	i2c_bus=	[HW]	Override the default board specific I2C bus speed
+				or register an additional I2C bus that is not
+				registered from board initialization code.
+				Format:
+				<bus_id>,<clkrate>
 
 	i8042.debug	[HW] Toggle i8042 debug mode
 	i8042.unmask_kbd_data
@@ -1386,7 +1396,7 @@
 			Default: only on s2r transitions on x86; most other
 			architectures force reset to be always executed
 	i8042.unlock	[HW] Unlock (ignore) the keylock
-	i8042.kbdreset  [HW] Reset device connected to KBD port
+	i8042.kbdreset	[HW] Reset device connected to KBD port
 
 	i810=		[HW,DRM]
 
@@ -1548,13 +1558,13 @@
 			programs exec'd, files mmap'd for exec, and all files
 			opened for read by uid=0.
 
-	ima_template=   [IMA]
+	ima_template=	[IMA]
 			Select one of defined IMA measurements template formats.
 			Formats: { "ima" | "ima-ng" | "ima-sig" }
 			Default: "ima-ng"
 
 	ima_template_fmt=
-	                [IMA] Define a custom template format.
+			[IMA] Define a custom template format.
 			Format: { "field1|...|fieldN" }
 
 	ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
@@ -1597,7 +1607,7 @@
 	inport.irq=	[HW] Inport (ATI XL and Microsoft) busmouse driver
 			Format: <irq>
 
-	int_pln_enable  [x86] Enable power limit notification interrupt
+	int_pln_enable	[x86] Enable power limit notification interrupt
 
 	integrity_audit=[IMA]
 			Format: { "0" | "1" }
@@ -1650,39 +1660,39 @@
 			0	disables intel_idle and fall back on acpi_idle.
 			1 to 9	specify maximum depth of C-state.
 
-	intel_pstate=  [X86]
-		       disable
-		         Do not enable intel_pstate as the default
-		         scaling driver for the supported processors
-		       passive
-			 Use intel_pstate as a scaling driver, but configure it
-			 to work with generic cpufreq governors (instead of
-			 enabling its internal governor).  This mode cannot be
-			 used along with the hardware-managed P-states (HWP)
-			 feature.
-		       force
-			 Enable intel_pstate on systems that prohibit it by default
-			 in favor of acpi-cpufreq. Forcing the intel_pstate driver
-			 instead of acpi-cpufreq may disable platform features, such
-			 as thermal controls and power capping, that rely on ACPI
-			 P-States information being indicated to OSPM and therefore
-			 should be used with caution. This option does not work with
-			 processors that aren't supported by the intel_pstate driver
-			 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
-		       no_hwp
-		         Do not enable hardware P state control (HWP)
-			 if available.
-		hwp_only
-			Only load intel_pstate on systems which support
-			hardware P state control (HWP) if available.
-		support_acpi_ppc
-			Enforce ACPI _PPC performance limits. If the Fixed ACPI
-			Description Table, specifies preferred power management
-			profile as "Enterprise Server" or "Performance Server",
-			then this feature is turned on by default.
-		per_cpu_perf_limits
-			Allow per-logical-CPU P-State performance control limits using
-			cpufreq sysfs interface
+	intel_pstate=	[X86]
+			disable
+			  Do not enable intel_pstate as the default
+			  scaling driver for the supported processors
+			passive
+			  Use intel_pstate as a scaling driver, but configure it
+			  to work with generic cpufreq governors (instead of
+			  enabling its internal governor).  This mode cannot be
+			  used along with the hardware-managed P-states (HWP)
+			  feature.
+			force
+			  Enable intel_pstate on systems that prohibit it by default
+			  in favor of acpi-cpufreq. Forcing the intel_pstate driver
+			  instead of acpi-cpufreq may disable platform features, such
+			  as thermal controls and power capping, that rely on ACPI
+			  P-States information being indicated to OSPM and therefore
+			  should be used with caution. This option does not work with
+			  processors that aren't supported by the intel_pstate driver
+			  or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
+			no_hwp
+			  Do not enable hardware P state control (HWP)
+			  if available.
+			hwp_only
+			  Only load intel_pstate on systems which support
+			  hardware P state control (HWP) if available.
+			support_acpi_ppc
+			  Enforce ACPI _PPC performance limits. If the Fixed ACPI
+			  Description Table, specifies preferred power management
+			  profile as "Enterprise Server" or "Performance Server",
+			  then this feature is turned on by default.
+			per_cpu_perf_limits
+			  Allow per-logical-CPU P-State performance control limits using
+			  cpufreq sysfs interface
 
 	intremap=	[X86-64, Intel-IOMMU]
 			on	enable Interrupt Remapping (default)
@@ -1705,7 +1715,6 @@
 		nopanic
 		merge
 		nomerge
-		forcesac
 		soft
 		pt		[x86, IA-64]
 		nobypass	[PPC/POWERNV]
@@ -2027,7 +2036,7 @@
 			* [no]ncqtrim: Turn off queued DSM TRIM.
 
 			* nohrst, nosrst, norst: suppress hard, soft
-                          and both resets.
+			  and both resets.
 
 			* rstonce: only attempt one reset during
 			  hot-unplug link recovery
@@ -2215,7 +2224,7 @@
 			[KNL,SH] Allow user to override the default size for
 			per-device physically contiguous DMA buffers.
 
-        memhp_default_state=online/offline
+	memhp_default_state=online/offline
 			[KNL] Set the initial state for the memory hotplug
 			onlining policy. If not specified, the default value is
 			set according to the
@@ -2600,6 +2609,9 @@
 			emulation library even if a 387 maths coprocessor
 			is present.
 
+	no5lvl		[X86-64] Disable 5-level paging mode. Forces
+			kernel to use 4-level paging instead.
+
 	no_console_suspend
 			[HW] Never suspend the console
 			Disable suspending of consoles during suspend and
@@ -2680,6 +2692,9 @@
 			allow data leaks with this option, which is equivalent
 			to spectre_v2=off.
 
+	nospec_store_bypass_disable
+			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -2762,7 +2777,7 @@
 			[X86,PV_OPS] Disable paravirtualized VMware scheduler
 			clock and use the default one.
 
-	no-steal-acc    [X86,KVM] Disable paravirtualized steal time accounting.
+	no-steal-acc	[X86,KVM] Disable paravirtualized steal time accounting.
 			steal time is computed, but won't influence scheduler
 			behaviour
 
@@ -2823,7 +2838,7 @@
 	notsc		[BUGS=X86-32] Disable Time Stamp Counter
 
 	nowatchdog	[KNL] Disable both lockup detectors, i.e.
-                        soft-lockup and NMI watchdog (hard-lockup).
+			soft-lockup and NMI watchdog (hard-lockup).
 
 	nowb		[ARM]
 
@@ -2843,7 +2858,7 @@
 			If the dependencies are under your control, you can
 			turn on cpu0_hotplug.
 
-	nps_mtm_hs_ctr= [KNL,ARC]
+	nps_mtm_hs_ctr=	[KNL,ARC]
 			This parameter sets the maximum duration, in
 			cycles, each HW thread of the CTOP can run
 			without interruptions, before HW switches it.
@@ -2984,7 +2999,7 @@
 
 	pci=option[,option...]	[PCI] various PCI subsystem options:
 		earlydump	[X86] dump PCI config space before the kernel
-			        changes anything
+				changes anything
 		off		[X86] don't probe for the PCI bus
 		bios		[X86-32] force use of PCI BIOS, don't access
 				the hardware directly. Use this if your machine
@@ -3072,7 +3087,7 @@
 				is enabled by default.  If you need to use this,
 				please report a bug.
 		nocrs		[X86] Ignore PCI host bridge windows from ACPI.
-			        If you need to use this, please report a bug.
+				If you need to use this, please report a bug.
 		routeirq	Do IRQ routing for all PCI devices.
 				This is normally done in pci_enable_device(),
 				so this option is a temporary workaround
@@ -3915,7 +3930,7 @@
 			cache (risks via metadata attacks are mostly
 			unchanged). Debug options disable merging on their
 			own.
-			For more information see Documentation/vm/slub.txt.
+			For more information see Documentation/vm/slub.rst.
 
 	slab_max_order=	[MM, SLAB]
 			Determines the maximum allowed order for slabs.
@@ -3929,7 +3944,7 @@
 			slub_debug can create guard zones around objects and
 			may poison objects when not in use. Also tracks the
 			last alloc / free. For more information see
-			Documentation/vm/slub.txt.
+			Documentation/vm/slub.rst.
 
 	slub_memcg_sysfs=	[MM, SLUB]
 			Determines whether to enable sysfs directories for
@@ -3943,7 +3958,7 @@
 			Determines the maximum allowed order for slabs.
 			A high setting may cause OOMs due to memory
 			fragmentation. For more information see
-			Documentation/vm/slub.txt.
+			Documentation/vm/slub.rst.
 
 	slub_min_objects=	[MM, SLUB]
 			The minimum number of objects per slab. SLUB will
@@ -3952,12 +3967,12 @@
 			the number of objects indicated. The higher the number
 			of objects the smaller the overhead of tracking slabs
 			and the less frequently locks need to be acquired.
-			For more information see Documentation/vm/slub.txt.
+			For more information see Documentation/vm/slub.rst.
 
 	slub_min_order=	[MM, SLUB]
 			Determines the minimum page order for slabs. Must be
 			lower than slub_max_order.
-			For more information see Documentation/vm/slub.txt.
+			For more information see Documentation/vm/slub.rst.
 
 	slub_nomerge	[MM, SLUB]
 			Same with slab_nomerge. This is supported for legacy.
@@ -4025,6 +4040,48 @@
 			Not specifying this option is equivalent to
 			spectre_v2=auto.
 
+	spec_store_bypass_disable=
+			[HW] Control Speculative Store Bypass (SSB) Disable mitigation
+			(Speculative Store Bypass vulnerability)
+
+			Certain CPUs are vulnerable to an exploit against a
+			a common industry wide performance optimization known
+			as "Speculative Store Bypass" in which recent stores
+			to the same memory location may not be observed by
+			later loads during speculative execution. The idea
+			is that such stores are unlikely and that they can
+			be detected prior to instruction retirement at the
+			end of a particular speculation execution window.
+
+			In vulnerable processors, the speculatively forwarded
+			store can be used in a cache side channel attack, for
+			example to read memory to which the attacker does not
+			directly have access (e.g. inside sandboxed code).
+
+			This parameter controls whether the Speculative Store
+			Bypass optimization is used.
+
+			on      - Unconditionally disable Speculative Store Bypass
+			off     - Unconditionally enable Speculative Store Bypass
+			auto    - Kernel detects whether the CPU model contains an
+				  implementation of Speculative Store Bypass and
+				  picks the most appropriate mitigation. If the
+				  CPU is not vulnerable, "off" is selected. If the
+				  CPU is vulnerable the default mitigation is
+				  architecture and Kconfig dependent. See below.
+			prctl   - Control Speculative Store Bypass per thread
+				  via prctl. Speculative Store Bypass is enabled
+				  for a process by default. The state of the control
+				  is inherited on fork.
+			seccomp - Same as "prctl" above, but all seccomp threads
+				  will disable SSB unless they explicitly opt out.
+
+			Not specifying this option is equivalent to
+			spec_store_bypass_disable=auto.
+
+			Default mitigations:
+			X86:	If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=
@@ -4313,7 +4370,8 @@
 			Format: [always|madvise|never]
 			Can be used to control the default behavior of the system
 			with respect to transparent hugepages.
-			See Documentation/vm/transhuge.txt for more details.
+			See Documentation/admin-guide/mm/transhuge.rst
+			for more details.
 
 	tsc=		Disable clocksource stability checks for TSC.
 			Format: <string>
@@ -4391,7 +4449,7 @@
 
 	usbcore.initial_descriptor_timeout=
 			[USB] Specifies timeout for the initial 64-byte
-                        USB_REQ_GET_DESCRIPTOR request in milliseconds
+			USB_REQ_GET_DESCRIPTOR request in milliseconds
 			(default 5000 = 5.0 seconds).
 
 	usbcore.nousb	[USB] Disable the USB subsystem
diff --git a/Documentation/admin-guide/mm/concepts.rst b/Documentation/admin-guide/mm/concepts.rst
new file mode 100644
index 000000000000..291699c810d4
--- /dev/null
+++ b/Documentation/admin-guide/mm/concepts.rst
@@ -0,0 +1,222 @@
+.. _mm_concepts:
+
+=================
+Concepts overview
+=================
+
+The memory management in Linux is complex system that evolved over the
+years and included more and more functionality to support variety of
+systems from MMU-less microcontrollers to supercomputers. The memory
+management for systems without MMU is called ``nommu`` and it
+definitely deserves a dedicated document, which hopefully will be
+eventually written. Yet, although some of the concepts are the same,
+here we assume that MMU is available and CPU can translate a virtual
+address to a physical address.
+
+.. contents:: :local:
+
+Virtual Memory Primer
+=====================
+
+The physical memory in a computer system is a limited resource and
+even for systems that support memory hotplug there is a hard limit on
+the amount of memory that can be installed. The physical memory is not
+necessary contiguous, it might be accessible as a set of distinct
+address ranges. Besides, different CPU architectures, and even
+different implementations of the same architecture have different view
+how these address ranges defined.
+
+All this makes dealing directly with physical memory quite complex and
+to avoid this complexity a concept of virtual memory was developed.
+
+The virtual memory abstracts the details of physical memory from the
+application software, allows to keep only needed information in the
+physical memory (demand paging) and provides a mechanism for the
+protection and controlled sharing of data between processes.
+
+With virtual memory, each and every memory access uses a virtual
+address. When the CPU decodes the an instruction that reads (or
+writes) from (or to) the system memory, it translates the `virtual`
+address encoded in that instruction to a `physical` address that the
+memory controller can understand.
+
+The physical system memory is divided into page frames, or pages. The
+size of each page is architecture specific. Some architectures allow
+selection of the page size from several supported values; this
+selection is performed at the kernel build time by setting an
+appropriate kernel configuration option.
+
+Each physical memory page can be mapped as one or more virtual
+pages. These mappings are described by page tables that allow
+translation from virtual address used by programs to real address in
+the physical memory. The page tables organized hierarchically.
+
+The tables at the lowest level of the hierarchy contain physical
+addresses of actual pages used by the software. The tables at higher
+levels contain physical addresses of the pages belonging to the lower
+levels. The pointer to the top level page table resides in a
+register. When the CPU performs the address translation, it uses this
+register to access the top level page table. The high bits of the
+virtual address are used to index an entry in the top level page
+table. That entry is then used to access the next level in the
+hierarchy with the next bits of the virtual address as the index to
+that level page table. The lowest bits in the virtual address define
+the offset inside the actual page.
+
+Huge Pages
+==========
+
+The address translation requires several memory accesses and memory
+accesses are slow relatively to CPU speed. To avoid spending precious
+processor cycles on the address translation, CPUs maintain a cache of
+such translations called Translation Lookaside Buffer (or
+TLB). Usually TLB is pretty scarce resource and applications with
+large memory working set will experience performance hit because of
+TLB misses.
+
+Many modern CPU architectures allow mapping of the memory pages
+directly by the higher levels in the page table. For instance, on x86,
+it is possible to map 2M and even 1G pages using entries in the second
+and the third level page tables. In Linux such pages are called
+`huge`. Usage of huge pages significantly reduces pressure on TLB,
+improves TLB hit-rate and thus improves overall system performance.
+
+There are two mechanisms in Linux that enable mapping of the physical
+memory with the huge pages. The first one is `HugeTLB filesystem`, or
+hugetlbfs. It is a pseudo filesystem that uses RAM as its backing
+store. For the files created in this filesystem the data resides in
+the memory and mapped using huge pages. The hugetlbfs is described at
+:ref:`Documentation/admin-guide/mm/hugetlbpage.rst <hugetlbpage>`.
+
+Another, more recent, mechanism that enables use of the huge pages is
+called `Transparent HugePages`, or THP. Unlike the hugetlbfs that
+requires users and/or system administrators to configure what parts of
+the system memory should and can be mapped by the huge pages, THP
+manages such mappings transparently to the user and hence the
+name. See
+:ref:`Documentation/admin-guide/mm/transhuge.rst <admin_guide_transhuge>`
+for more details about THP.
+
+Zones
+=====
+
+Often hardware poses restrictions on how different physical memory
+ranges can be accessed. In some cases, devices cannot perform DMA to
+all the addressable memory. In other cases, the size of the physical
+memory exceeds the maximal addressable size of virtual memory and
+special actions are required to access portions of the memory. Linux
+groups memory pages into `zones` according to their possible
+usage. For example, ZONE_DMA will contain memory that can be used by
+devices for DMA, ZONE_HIGHMEM will contain memory that is not
+permanently mapped into kernel's address space and ZONE_NORMAL will
+contain normally addressed pages.
+
+The actual layout of the memory zones is hardware dependent as not all
+architectures define all zones, and requirements for DMA are different
+for different platforms.
+
+Nodes
+=====
+
+Many multi-processor machines are NUMA - Non-Uniform Memory Access -
+systems. In such systems the memory is arranged into banks that have
+different access latency depending on the "distance" from the
+processor. Each bank is referred as `node` and for each node Linux
+constructs an independent memory management subsystem. A node has it's
+own set of zones, lists of free and used pages and various statistics
+counters. You can find more details about NUMA in
+:ref:`Documentation/vm/numa.rst <numa>` and in
+:ref:`Documentation/admin-guide/mm/numa_memory_policy.rst <numa_memory_policy>`.
+
+Page cache
+==========
+
+The physical memory is volatile and the common case for getting data
+into the memory is to read it from files. Whenever a file is read, the
+data is put into the `page cache` to avoid expensive disk access on
+the subsequent reads. Similarly, when one writes to a file, the data
+is placed in the page cache and eventually gets into the backing
+storage device. The written pages are marked as `dirty` and when Linux
+decides to reuse them for other purposes, it makes sure to synchronize
+the file contents on the device with the updated data.
+
+Anonymous Memory
+================
+
+The `anonymous memory` or `anonymous mappings` represent memory that
+is not backed by a filesystem. Such mappings are implicitly created
+for program's stack and heap or by explicit calls to mmap(2) system
+call. Usually, the anonymous mappings only define virtual memory areas
+that the program is allowed to access. The read accesses will result
+in creation of a page table entry that references a special physical
+page filled with zeroes. When the program performs a write, regular
+physical page will be allocated to hold the written data. The page
+will be marked dirty and if the kernel will decide to repurpose it,
+the dirty page will be swapped out.
+
+Reclaim
+=======
+
+Throughout the system lifetime, a physical page can be used for storing
+different types of data. It can be kernel internal data structures,
+DMA'able buffers for device drivers use, data read from a filesystem,
+memory allocated by user space processes etc.
+
+Depending on the page usage it is treated differently by the Linux
+memory management. The pages that can be freed at any time, either
+because they cache the data available elsewhere, for instance, on a
+hard disk, or because they can be swapped out, again, to the hard
+disk, are called `reclaimable`. The most notable categories of the
+reclaimable pages are page cache and anonymous memory.
+
+In most cases, the pages holding internal kernel data and used as DMA
+buffers cannot be repurposed, and they remain pinned until freed by
+their user. Such pages are called `unreclaimable`. However, in certain
+circumstances, even pages occupied with kernel data structures can be
+reclaimed. For instance, in-memory caches of filesystem metadata can
+be re-read from the storage device and therefore it is possible to
+discard them from the main memory when system is under memory
+pressure.
+
+The process of freeing the reclaimable physical memory pages and
+repurposing them is called (surprise!) `reclaim`. Linux can reclaim
+pages either asynchronously or synchronously, depending on the state
+of the system. When system is not loaded, most of the memory is free
+and allocation request will be satisfied immediately from the free
+pages supply. As the load increases, the amount of the free pages goes
+down and when it reaches a certain threshold (high watermark), an
+allocation request will awaken the ``kswapd`` daemon. It will
+asynchronously scan memory pages and either just free them if the data
+they contain is available elsewhere, or evict to the backing storage
+device (remember those dirty pages?). As memory usage increases even
+more and reaches another threshold - min watermark - an allocation
+will trigger the `direct reclaim`. In this case allocation is stalled
+until enough memory pages are reclaimed to satisfy the request.
+
+Compaction
+==========
+
+As the system runs, tasks allocate and free the memory and it becomes
+fragmented. Although with virtual memory it is possible to present
+scattered physical pages as virtually contiguous range, sometimes it is
+necessary to allocate large physically contiguous memory areas. Such
+need may arise, for instance, when a device driver requires large
+buffer for DMA, or when THP allocates a huge page. Memory `compaction`
+addresses the fragmentation issue. This mechanism moves occupied pages
+from the lower part of a memory zone to free pages in the upper part
+of the zone. When a compaction scan is finished free pages are grouped
+together at the beginning of the zone and allocations of large
+physically contiguous areas become possible.
+
+Like reclaim, the compaction may happen asynchronously in ``kcompactd``
+daemon or synchronously as a result of memory allocation request.
+
+OOM killer
+==========
+
+It may happen, that on a loaded machine memory will be exhausted. When
+the kernel detects that the system runs out of memory (OOM) it invokes
+`OOM killer`. Its mission is simple: all it has to do is to select a
+task to sacrifice for the sake of the overall system health. The
+selected task is killed in a hope that after it exits enough memory
+will be freed to continue normal operation.
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/admin-guide/mm/hugetlbpage.rst
index faf077d50d42..1cc0bc78d10e 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -1,3 +1,11 @@
+.. _hugetlbpage:
+
+=============
+HugeTLB Pages
+=============
+
+Overview
+========
 
 The intent of this file is to give a brief summary of hugetlbpage support in
 the Linux kernel.  This support is built on top of multiple page size support
@@ -18,53 +26,59 @@ First the Linux kernel needs to be built with the CONFIG_HUGETLBFS
 automatically when CONFIG_HUGETLBFS is selected) configuration
 options.
 
-The /proc/meminfo file provides information about the total number of
+The ``/proc/meminfo`` file provides information about the total number of
 persistent hugetlb pages in the kernel's huge page pool.  It also displays
 default huge page size and information about the number of free, reserved
 and surplus huge pages in the pool of huge pages of default size.
 The huge page size is needed for generating the proper alignment and
 size of the arguments to system calls that map huge page regions.
 
-The output of "cat /proc/meminfo" will include lines like:
+The output of ``cat /proc/meminfo`` will include lines like::
 
-.....
-HugePages_Total: uuu
-HugePages_Free:  vvv
-HugePages_Rsvd:  www
-HugePages_Surp:  xxx
-Hugepagesize:    yyy kB
-Hugetlb:         zzz kB
+	HugePages_Total: uuu
+	HugePages_Free:  vvv
+	HugePages_Rsvd:  www
+	HugePages_Surp:  xxx
+	Hugepagesize:    yyy kB
+	Hugetlb:         zzz kB
 
 where:
-HugePages_Total is the size of the pool of huge pages.
-HugePages_Free  is the number of huge pages in the pool that are not yet
-                allocated.
-HugePages_Rsvd  is short for "reserved," and is the number of huge pages for
-                which a commitment to allocate from the pool has been made,
-                but no allocation has yet been made.  Reserved huge pages
-                guarantee that an application will be able to allocate a
-                huge page from the pool of huge pages at fault time.
-HugePages_Surp  is short for "surplus," and is the number of huge pages in
-                the pool above the value in /proc/sys/vm/nr_hugepages. The
-                maximum number of surplus huge pages is controlled by
-                /proc/sys/vm/nr_overcommit_hugepages.
-Hugepagesize    is the default hugepage size (in Kb).
-Hugetlb         is the total amount of memory (in kB), consumed by huge
-                pages of all sizes.
-                If huge pages of different sizes are in use, this number
-                will exceed HugePages_Total * Hugepagesize. To get more
-                detailed information, please, refer to
-                /sys/kernel/mm/hugepages (described below).
-
-
-/proc/filesystems should also show a filesystem of type "hugetlbfs" configured
-in the kernel.
-
-/proc/sys/vm/nr_hugepages indicates the current number of "persistent" huge
+
+HugePages_Total
+	is the size of the pool of huge pages.
+HugePages_Free
+	is the number of huge pages in the pool that are not yet
+        allocated.
+HugePages_Rsvd
+	is short for "reserved," and is the number of huge pages for
+        which a commitment to allocate from the pool has been made,
+        but no allocation has yet been made.  Reserved huge pages
+        guarantee that an application will be able to allocate a
+        huge page from the pool of huge pages at fault time.
+HugePages_Surp
+	is short for "surplus," and is the number of huge pages in
+        the pool above the value in ``/proc/sys/vm/nr_hugepages``. The
+        maximum number of surplus huge pages is controlled by
+        ``/proc/sys/vm/nr_overcommit_hugepages``.
+Hugepagesize
+	is the default hugepage size (in Kb).
+Hugetlb
+        is the total amount of memory (in kB), consumed by huge
+        pages of all sizes.
+        If huge pages of different sizes are in use, this number
+        will exceed HugePages_Total \* Hugepagesize. To get more
+        detailed information, please, refer to
+        ``/sys/kernel/mm/hugepages`` (described below).
+
+
+``/proc/filesystems`` should also show a filesystem of type "hugetlbfs"
+configured in the kernel.
+
+``/proc/sys/vm/nr_hugepages`` indicates the current number of "persistent" huge
 pages in the kernel's huge page pool.  "Persistent" huge pages will be
 returned to the huge page pool when freed by a task.  A user with root
 privileges can dynamically allocate more or free some persistent huge pages
-by increasing or decreasing the value of 'nr_hugepages'.
+by increasing or decreasing the value of ``nr_hugepages``.
 
 Pages that are used as huge pages are reserved inside the kernel and cannot
 be used for other purposes.  Huge pages cannot be swapped out under
@@ -73,7 +87,7 @@ memory pressure.
 Once a number of huge pages have been pre-allocated to the kernel huge page
 pool, a user with appropriate privilege can use either the mmap system call
 or shared memory system calls to use the huge pages.  See the discussion of
-Using Huge Pages, below.
+:ref:`Using Huge Pages <using_huge_pages>`, below.
 
 The administrator can allocate persistent huge pages on the kernel boot
 command line by specifying the "hugepages=N" parameter, where 'N' = the
@@ -86,10 +100,10 @@ with a huge page size selection parameter "hugepagesz=<size>".  <size> must
 be specified in bytes with optional scale suffix [kKmMgG].  The default huge
 page size may be selected with the "default_hugepagesz=<size>" boot parameter.
 
-When multiple huge page sizes are supported, /proc/sys/vm/nr_hugepages
+When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
 indicates the current number of pre-allocated huge pages of the default size.
 Thus, one can use the following command to dynamically allocate/deallocate
-default sized persistent huge pages:
+default sized persistent huge pages::
 
 	echo 20 > /proc/sys/vm/nr_hugepages
 
@@ -98,11 +112,12 @@ huge page pool to 20, allocating or freeing huge pages, as required.
 
 On a NUMA platform, the kernel will attempt to distribute the huge page pool
 over all the set of allowed nodes specified by the NUMA memory policy of the
-task that modifies nr_hugepages.  The default for the allowed nodes--when the
+task that modifies ``nr_hugepages``. The default for the allowed nodes--when the
 task has default memory policy--is all on-line nodes with memory.  Allowed
 nodes with insufficient available, contiguous memory for a huge page will be
-silently skipped when allocating persistent huge pages.  See the discussion
-below of the interaction of task memory policy, cpusets and per node attributes
+silently skipped when allocating persistent huge pages.  See the
+:ref:`discussion below <mem_policy_and_hp_alloc>`
+of the interaction of task memory policy, cpusets and per node attributes
 with the allocation and freeing of persistent huge pages.
 
 The success or failure of huge page allocation depends on the amount of
@@ -117,51 +132,52 @@ init files.  This will enable the kernel to allocate huge pages early in
 the boot process when the possibility of getting physical contiguous pages
 is still very high.  Administrators can verify the number of huge pages
 actually allocated by checking the sysctl or meminfo.  To check the per node
-distribution of huge pages in a NUMA system, use:
+distribution of huge pages in a NUMA system, use::
 
 	cat /sys/devices/system/node/node*/meminfo | fgrep Huge
 
-/proc/sys/vm/nr_overcommit_hugepages specifies how large the pool of
-huge pages can grow, if more huge pages than /proc/sys/vm/nr_hugepages are
+``/proc/sys/vm/nr_overcommit_hugepages`` specifies how large the pool of
+huge pages can grow, if more huge pages than ``/proc/sys/vm/nr_hugepages`` are
 requested by applications.  Writing any non-zero value into this file
 indicates that the hugetlb subsystem is allowed to try to obtain that
 number of "surplus" huge pages from the kernel's normal page pool, when the
 persistent huge page pool is exhausted. As these surplus huge pages become
 unused, they are freed back to the kernel's normal page pool.
 
-When increasing the huge page pool size via nr_hugepages, any existing surplus
-pages will first be promoted to persistent huge pages.  Then, additional
+When increasing the huge page pool size via ``nr_hugepages``, any existing
+surplus pages will first be promoted to persistent huge pages.  Then, additional
 huge pages will be allocated, if necessary and if possible, to fulfill
 the new persistent huge page pool size.
 
 The administrator may shrink the pool of persistent huge pages for
-the default huge page size by setting the nr_hugepages sysctl to a
+the default huge page size by setting the ``nr_hugepages`` sysctl to a
 smaller value.  The kernel will attempt to balance the freeing of huge pages
-across all nodes in the memory policy of the task modifying nr_hugepages.
+across all nodes in the memory policy of the task modifying ``nr_hugepages``.
 Any free huge pages on the selected nodes will be freed back to the kernel's
 normal page pool.
 
-Caveat: Shrinking the persistent huge page pool via nr_hugepages such that
+Caveat: Shrinking the persistent huge page pool via ``nr_hugepages`` such that
 it becomes less than the number of huge pages in use will convert the balance
 of the in-use huge pages to surplus huge pages.  This will occur even if
-the number of surplus pages it would exceed the overcommit value.  As long as
-this condition holds--that is, until nr_hugepages+nr_overcommit_hugepages is
+the number of surplus pages would exceed the overcommit value.  As long as
+this condition holds--that is, until ``nr_hugepages+nr_overcommit_hugepages`` is
 increased sufficiently, or the surplus huge pages go out of use and are freed--
 no more surplus huge pages will be allowed to be allocated.
 
 With support for multiple huge page pools at run-time available, much of
-the huge page userspace interface in /proc/sys/vm has been duplicated in sysfs.
-The /proc interfaces discussed above have been retained for backwards
-compatibility. The root huge page control directory in sysfs is:
+the huge page userspace interface in ``/proc/sys/vm`` has been duplicated in
+sysfs.
+The ``/proc`` interfaces discussed above have been retained for backwards
+compatibility. The root huge page control directory in sysfs is::
 
 	/sys/kernel/mm/hugepages
 
 For each huge page size supported by the running kernel, a subdirectory
-will exist, of the form:
+will exist, of the form::
 
 	hugepages-${size}kB
 
-Inside each of these directories, the same set of files will exist:
+Inside each of these directories, the same set of files will exist::
 
 	nr_hugepages
 	nr_hugepages_mempolicy
@@ -172,37 +188,39 @@ Inside each of these directories, the same set of files will exist:
 
 which function as described above for the default huge page-sized case.
 
+.. _mem_policy_and_hp_alloc:
 
 Interaction of Task Memory Policy with Huge Page Allocation/Freeing
 ===================================================================
 
-Whether huge pages are allocated and freed via the /proc interface or
-the /sysfs interface using the nr_hugepages_mempolicy attribute, the NUMA
-nodes from which huge pages are allocated or freed are controlled by the
-NUMA memory policy of the task that modifies the nr_hugepages_mempolicy
-sysctl or attribute.  When the nr_hugepages attribute is used, mempolicy
+Whether huge pages are allocated and freed via the ``/proc`` interface or
+the ``/sysfs`` interface using the ``nr_hugepages_mempolicy`` attribute, the
+NUMA nodes from which huge pages are allocated or freed are controlled by the
+NUMA memory policy of the task that modifies the ``nr_hugepages_mempolicy``
+sysctl or attribute.  When the ``nr_hugepages`` attribute is used, mempolicy
 is ignored.
 
 The recommended method to allocate or free huge pages to/from the kernel
-huge page pool, using the nr_hugepages example above, is:
+huge page pool, using the ``nr_hugepages`` example above, is::
 
     numactl --interleave <node-list> echo 20 \
 				>/proc/sys/vm/nr_hugepages_mempolicy
 
-or, more succinctly:
+or, more succinctly::
 
     numactl -m <node-list> echo 20 >/proc/sys/vm/nr_hugepages_mempolicy
 
-This will allocate or free abs(20 - nr_hugepages) to or from the nodes
+This will allocate or free ``abs(20 - nr_hugepages)`` to or from the nodes
 specified in <node-list>, depending on whether number of persistent huge pages
 is initially less than or greater than 20, respectively.  No huge pages will be
 allocated nor freed on any node not included in the specified <node-list>.
 
-When adjusting the persistent hugepage count via nr_hugepages_mempolicy, any
+When adjusting the persistent hugepage count via ``nr_hugepages_mempolicy``, any
 memory policy mode--bind, preferred, local or interleave--may be used.  The
 resulting effect on persistent huge page allocation is as follows:
 
-1) Regardless of mempolicy mode [see Documentation/vm/numa_memory_policy.txt],
+#. Regardless of mempolicy mode [see
+   :ref:`Documentation/admin-guide/mm/numa_memory_policy.rst <numa_memory_policy>`],
    persistent huge pages will be distributed across the node or nodes
    specified in the mempolicy as if "interleave" had been specified.
    However, if a node in the policy does not contain sufficient contiguous
@@ -212,7 +230,7 @@ resulting effect on persistent huge page allocation is as follows:
    possibly, allocation of persistent huge pages on nodes not allowed by
    the task's memory policy.
 
-2) One or more nodes may be specified with the bind or interleave policy.
+#. One or more nodes may be specified with the bind or interleave policy.
    If more than one node is specified with the preferred policy, only the
    lowest numeric id will be used.  Local policy will select the node where
    the task is running at the time the nodes_allowed mask is constructed.
@@ -222,20 +240,20 @@ resulting effect on persistent huge page allocation is as follows:
    indeterminate.  Thus, local policy is not very useful for this purpose.
    Any of the other mempolicy modes may be used to specify a single node.
 
-3) The nodes allowed mask will be derived from any non-default task mempolicy,
+#. The nodes allowed mask will be derived from any non-default task mempolicy,
    whether this policy was set explicitly by the task itself or one of its
    ancestors, such as numactl.  This means that if the task is invoked from a
    shell with non-default policy, that policy will be used.  One can specify a
    node list of "all" with numactl --interleave or --membind [-m] to achieve
    interleaving over all nodes in the system or cpuset.
 
-4) Any task mempolicy specified--e.g., using numactl--will be constrained by
+#. Any task mempolicy specified--e.g., using numactl--will be constrained by
    the resource limits of any cpuset in which the task runs.  Thus, there will
    be no way for a task with non-default policy running in a cpuset with a
    subset of the system nodes to allocate huge pages outside the cpuset
    without first moving to a cpuset that contains all of the desired nodes.
 
-5) Boot-time huge page allocation attempts to distribute the requested number
+#. Boot-time huge page allocation attempts to distribute the requested number
    of huge pages over all on-lines nodes with memory.
 
 Per Node Hugepages Attributes
@@ -243,22 +261,22 @@ Per Node Hugepages Attributes
 
 A subset of the contents of the root huge page control directory in sysfs,
 described above, will be replicated under each the system device of each
-NUMA node with memory in:
+NUMA node with memory in::
 
 	/sys/devices/system/node/node[0-9]*/hugepages/
 
 Under this directory, the subdirectory for each supported huge page size
-contains the following attribute files:
+contains the following attribute files::
 
 	nr_hugepages
 	free_hugepages
 	surplus_hugepages
 
-The free_' and surplus_' attribute files are read-only.  They return the number
+The free\_' and surplus\_' attribute files are read-only.  They return the number
 of free and surplus [overcommitted] huge pages, respectively, on the parent
 node.
 
-The nr_hugepages attribute returns the total number of huge pages on the
+The ``nr_hugepages`` attribute returns the total number of huge pages on the
 specified node.  When this attribute is written, the number of persistent huge
 pages on the parent node will be adjusted to the specified value, if sufficient
 resources exist, regardless of the task's mempolicy or cpuset constraints.
@@ -267,43 +285,58 @@ Note that the number of overcommit and reserve pages remain global quantities,
 as we don't know until fault time, when the faulting task's mempolicy is
 applied, from which node the huge page allocation will be attempted.
 
+.. _using_huge_pages:
 
 Using Huge Pages
 ================
 
 If the user applications are going to request huge pages using mmap system
 call, then it is required that system administrator mount a file system of
-type hugetlbfs:
+type hugetlbfs::
 
   mount -t hugetlbfs \
 	-o uid=<value>,gid=<value>,mode=<value>,pagesize=<value>,size=<value>,\
 	min_size=<value>,nr_inodes=<value> none /mnt/huge
 
 This command mounts a (pseudo) filesystem of type hugetlbfs on the directory
-/mnt/huge.  Any files created on /mnt/huge uses huge pages.  The uid and gid
-options sets the owner and group of the root of the file system.  By default
-the uid and gid of the current process are taken.  The mode option sets the
-mode of root of file system to value & 01777.  This value is given in octal.
-By default the value 0755 is picked. If the platform supports multiple huge
-page sizes, the pagesize option can be used to specify the huge page size and
-associated pool.  pagesize is specified in bytes.  If pagesize is not specified
-the platform's default huge page size and associated pool will be used. The
-size option sets the maximum value of memory (huge pages) allowed for that
-filesystem (/mnt/huge).  The size option can be specified in bytes, or as a
-percentage of the specified huge page pool (nr_hugepages).  The size is
-rounded down to HPAGE_SIZE boundary.  The min_size option sets the minimum
-value of memory (huge pages) allowed for the filesystem.  min_size can be
-specified in the same way as size, either bytes or a percentage of the
-huge page pool.  At mount time, the number of huge pages specified by
-min_size are reserved for use by the filesystem.  If there are not enough
-free huge pages available, the mount will fail.  As huge pages are allocated
-to the filesystem and freed, the reserve count is adjusted so that the sum
-of allocated and reserved huge pages is always at least min_size.  The option
-nr_inodes sets the maximum number of inodes that /mnt/huge can use.  If the
-size, min_size or nr_inodes option is not provided on command line then
-no limits are set.  For pagesize, size, min_size and nr_inodes options, you
-can use [G|g]/[M|m]/[K|k] to represent giga/mega/kilo. For example, size=2K
-has the same meaning as size=2048.
+``/mnt/huge``.  Any file created on ``/mnt/huge`` uses huge pages.
+
+The ``uid`` and ``gid`` options sets the owner and group of the root of the
+file system.  By default the ``uid`` and ``gid`` of the current process
+are taken.
+
+The ``mode`` option sets the mode of root of file system to value & 01777.
+This value is given in octal. By default the value 0755 is picked.
+
+If the platform supports multiple huge page sizes, the ``pagesize`` option can
+be used to specify the huge page size and associated pool. ``pagesize``
+is specified in bytes. If ``pagesize`` is not specified the platform's
+default huge page size and associated pool will be used.
+
+The ``size`` option sets the maximum value of memory (huge pages) allowed
+for that filesystem (``/mnt/huge``). The ``size`` option can be specified
+in bytes, or as a percentage of the specified huge page pool (``nr_hugepages``).
+The size is rounded down to HPAGE_SIZE boundary.
+
+The ``min_size`` option sets the minimum value of memory (huge pages) allowed
+for the filesystem. ``min_size`` can be specified in the same way as ``size``,
+either bytes or a percentage of the huge page pool.
+At mount time, the number of huge pages specified by ``min_size`` are reserved
+for use by the filesystem.
+If there are not enough free huge pages available, the mount will fail.
+As huge pages are allocated to the filesystem and freed, the reserve count
+is adjusted so that the sum of allocated and reserved huge pages is always
+at least ``min_size``.
+
+The option ``nr_inodes`` sets the maximum number of inodes that ``/mnt/huge``
+can use.
+
+If the ``size``, ``min_size`` or ``nr_inodes`` option is not provided on
+command line then no limits are set.
+
+For ``pagesize``, ``size``, ``min_size`` and ``nr_inodes`` options, you can
+use [G|g]/[M|m]/[K|k] to represent giga/mega/kilo.
+For example, size=2K has the same meaning as size=2048.
 
 While read system calls are supported on files that reside on hugetlb
 file systems, write system calls are not.
@@ -313,12 +346,12 @@ used to change the file attributes on hugetlbfs.
 
 Also, it is important to note that no such mount command is required if
 applications are going to use only shmat/shmget system calls or mmap with
-MAP_HUGETLB.  For an example of how to use mmap with MAP_HUGETLB see map_hugetlb
-below.
+MAP_HUGETLB.  For an example of how to use mmap with MAP_HUGETLB see
+:ref:`map_hugetlb <map_hugetlb>` below.
 
-Users who wish to use hugetlb memory via shared memory segment should be a
-member of a supplementary group and system admin needs to configure that gid
-into /proc/sys/vm/hugetlb_shm_group.  It is possible for same or different
+Users who wish to use hugetlb memory via shared memory segment should be
+members of a supplementary group and system admin needs to configure that gid
+into ``/proc/sys/vm/hugetlb_shm_group``.  It is possible for same or different
 applications to use any combination of mmaps and shm* calls, though the mount of
 filesystem will be required for using mmap calls without MAP_HUGETLB.
 
@@ -332,20 +365,18 @@ a hugetlb page and the length is smaller than the hugepage size.
 Examples
 ========
 
-1) map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
+.. _map_hugetlb:
 
-2) hugepage-shm:  see tools/testing/selftests/vm/hugepage-shm.c
+``map_hugetlb``
+	see tools/testing/selftests/vm/map_hugetlb.c
 
-3) hugepage-mmap:  see tools/testing/selftests/vm/hugepage-mmap.c
+``hugepage-shm``
+	see tools/testing/selftests/vm/hugepage-shm.c
 
-4) The libhugetlbfs (https://github.com/libhugetlbfs/libhugetlbfs) library
-   provides a wide range of userspace tools to help with huge page usability,
-   environment setup, and control.
+``hugepage-mmap``
+	see tools/testing/selftests/vm/hugepage-mmap.c
 
-Kernel development regression testing
-=====================================
+The `libhugetlbfs`_  library provides a wide range of userspace tools
+to help with huge page usability, environment setup, and control.
 
-The most complete set of hugetlb tests are in the libhugetlbfs repository.
-If you modify any hugetlb related code, use the libhugetlbfs test suite
-to check for regressions.  In addition, if you add any new hugetlb
-functionality, please add appropriate tests to libhugetlbfs.
+.. _libhugetlbfs: https://github.com/libhugetlbfs/libhugetlbfs
diff --git a/Documentation/vm/idle_page_tracking.txt b/Documentation/admin-guide/mm/idle_page_tracking.rst
index 85dcc3bb85dc..6f7b7ca1add3 100644
--- a/Documentation/vm/idle_page_tracking.txt
+++ b/Documentation/admin-guide/mm/idle_page_tracking.rst
@@ -1,4 +1,11 @@
-MOTIVATION
+.. _idle_page_tracking:
+
+==================
+Idle Page Tracking
+==================
+
+Motivation
+==========
 
 The idle page tracking feature allows to track which memory pages are being
 accessed by a workload and which are idle. This information can be useful for
@@ -8,10 +15,14 @@ or deciding where to place the workload within a compute cluster.
 
 It is enabled by CONFIG_IDLE_PAGE_TRACKING=y.
 
-USER API
+.. _user_api:
 
-The idle page tracking API is located at /sys/kernel/mm/page_idle. Currently,
-it consists of the only read-write file, /sys/kernel/mm/page_idle/bitmap.
+User API
+========
+
+The idle page tracking API is located at ``/sys/kernel/mm/page_idle``.
+Currently, it consists of the only read-write file,
+``/sys/kernel/mm/page_idle/bitmap``.
 
 The file implements a bitmap where each bit corresponds to a memory page. The
 bitmap is represented by an array of 8-byte integers, and the page at PFN #i is
@@ -19,8 +30,9 @@ mapped to bit #i%64 of array element #i/64, byte order is native. When a bit is
 set, the corresponding page is idle.
 
 A page is considered idle if it has not been accessed since it was marked idle
-(for more details on what "accessed" actually means see the IMPLEMENTATION
-DETAILS section). To mark a page idle one has to set the bit corresponding to
+(for more details on what "accessed" actually means see the :ref:`Implementation
+Details <impl_details>` section).
+To mark a page idle one has to set the bit corresponding to
 the page by writing to the file. A value written to the file is OR-ed with the
 current bitmap value.
 
@@ -30,9 +42,9 @@ page types (e.g. SLAB pages) an attempt to mark a page idle is silently ignored,
 and hence such pages are never reported idle.
 
 For huge pages the idle flag is set only on the head page, so one has to read
-/proc/kpageflags in order to correctly count idle huge pages.
+``/proc/kpageflags`` in order to correctly count idle huge pages.
 
-Reading from or writing to /sys/kernel/mm/page_idle/bitmap will return
+Reading from or writing to ``/sys/kernel/mm/page_idle/bitmap`` will return
 -EINVAL if you are not starting the read/write on an 8-byte boundary, or
 if the size of the read/write is not a multiple of 8 bytes. Writing to
 this file beyond max PFN will return -ENXIO.
@@ -41,21 +53,26 @@ That said, in order to estimate the amount of pages that are not used by a
 workload one should:
 
  1. Mark all the workload's pages as idle by setting corresponding bits in
-    /sys/kernel/mm/page_idle/bitmap. The pages can be found by reading
-    /proc/pid/pagemap if the workload is represented by a process, or by
-    filtering out alien pages using /proc/kpagecgroup in case the workload is
-    placed in a memory cgroup.
+    ``/sys/kernel/mm/page_idle/bitmap``. The pages can be found by reading
+    ``/proc/pid/pagemap`` if the workload is represented by a process, or by
+    filtering out alien pages using ``/proc/kpagecgroup`` in case the workload
+    is placed in a memory cgroup.
 
  2. Wait until the workload accesses its working set.
 
- 3. Read /sys/kernel/mm/page_idle/bitmap and count the number of bits set. If
-    one wants to ignore certain types of pages, e.g. mlocked pages since they
-    are not reclaimable, he or she can filter them out using /proc/kpageflags.
+ 3. Read ``/sys/kernel/mm/page_idle/bitmap`` and count the number of bits set.
+    If one wants to ignore certain types of pages, e.g. mlocked pages since they
+    are not reclaimable, he or she can filter them out using
+    ``/proc/kpageflags``.
+
+See :ref:`Documentation/admin-guide/mm/pagemap.rst <pagemap>` for more
+information about ``/proc/pid/pagemap``, ``/proc/kpageflags``, and
+``/proc/kpagecgroup``.
 
-See Documentation/vm/pagemap.txt for more information about /proc/pid/pagemap,
-/proc/kpageflags, and /proc/kpagecgroup.
+.. _impl_details:
 
-IMPLEMENTATION DETAILS
+Implementation Details
+======================
 
 The kernel internally keeps track of accesses to user memory pages in order to
 reclaim unreferenced pages first on memory shortage conditions. A page is
@@ -77,7 +94,8 @@ When a dirty page is written to swap or disk as a result of memory reclaim or
 exceeding the dirty memory limit, it is not marked referenced.
 
 The idle memory tracking feature adds a new page flag, the Idle flag. This flag
-is set manually, by writing to /sys/kernel/mm/page_idle/bitmap (see the USER API
+is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` (see the
+:ref:`User API <user_api>`
 section), and cleared automatically whenever a page is referenced as defined
 above.
 
diff --git a/Documentation/admin-guide/mm/index.rst b/Documentation/admin-guide/mm/index.rst
new file mode 100644
index 000000000000..ceead68c2df7
--- /dev/null
+++ b/Documentation/admin-guide/mm/index.rst
@@ -0,0 +1,36 @@
+=================
+Memory Management
+=================
+
+Linux memory management subsystem is responsible, as the name implies,
+for managing the memory in the system. This includes implemnetation of
+virtual memory and demand paging, memory allocation both for kernel
+internal structures and user space programms, mapping of files into
+processes address space and many other cool things.
+
+Linux memory management is a complex system with many configurable
+settings. Most of these settings are available via ``/proc``
+filesystem and can be quired and adjusted using ``sysctl``. These APIs
+are described in Documentation/sysctl/vm.txt and in `man 5 proc`_.
+
+.. _man 5 proc: http://man7.org/linux/man-pages/man5/proc.5.html
+
+Linux memory management has its own jargon and if you are not yet
+familiar with it, consider reading
+:ref:`Documentation/admin-guide/mm/concepts.rst <mm_concepts>`.
+
+Here we document in detail how to interact with various mechanisms in
+the Linux memory management.
+
+.. toctree::
+   :maxdepth: 1
+
+   concepts
+   hugetlbpage
+   idle_page_tracking
+   ksm
+   numa_memory_policy
+   pagemap
+   soft-dirty
+   transhuge
+   userfaultfd
diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst
new file mode 100644
index 000000000000..9303786632d1
--- /dev/null
+++ b/Documentation/admin-guide/mm/ksm.rst
@@ -0,0 +1,189 @@
+.. _admin_guide_ksm:
+
+=======================
+Kernel Samepage Merging
+=======================
+
+Overview
+========
+
+KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
+added to the Linux kernel in 2.6.32.  See ``mm/ksm.c`` for its implementation,
+and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
+
+KSM was originally developed for use with KVM (where it was known as
+Kernel Shared Memory), to fit more virtual machines into physical memory,
+by sharing the data common between them.  But it can be useful to any
+application which generates many instances of the same data.
+
+The KSM daemon ksmd periodically scans those areas of user memory
+which have been registered with it, looking for pages of identical
+content which can be replaced by a single write-protected page (which
+is automatically copied if a process later wants to update its
+content). The amount of pages that KSM daemon scans in a single pass
+and the time between the passes are configured using :ref:`sysfs
+intraface <ksm_sysfs>`
+
+KSM only merges anonymous (private) pages, never pagecache (file) pages.
+KSM's merged pages were originally locked into kernel memory, but can now
+be swapped out just like other user pages (but sharing is broken when they
+are swapped back in: ksmd must rediscover their identity and merge again).
+
+Controlling KSM with madvise
+============================
+
+KSM only operates on those areas of address space which an application
+has advised to be likely candidates for merging, by using the madvise(2)
+system call::
+
+	int madvise(addr, length, MADV_MERGEABLE)
+
+The app may call
+
+::
+
+	int madvise(addr, length, MADV_UNMERGEABLE)
+
+to cancel that advice and restore unshared pages: whereupon KSM
+unmerges whatever it merged in that range.  Note: this unmerging call
+may suddenly require more memory than is available - possibly failing
+with EAGAIN, but more probably arousing the Out-Of-Memory killer.
+
+If KSM is not configured into the running kernel, madvise MADV_MERGEABLE
+and MADV_UNMERGEABLE simply fail with EINVAL.  If the running kernel was
+built with CONFIG_KSM=y, those calls will normally succeed: even if the
+the KSM daemon is not currently running, MADV_MERGEABLE still registers
+the range for whenever the KSM daemon is started; even if the range
+cannot contain any pages which KSM could actually merge; even if
+MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.
+
+If a region of memory must be split into at least one new MADV_MERGEABLE
+or MADV_UNMERGEABLE region, the madvise may return ENOMEM if the process
+will exceed ``vm.max_map_count`` (see Documentation/sysctl/vm.txt).
+
+Like other madvise calls, they are intended for use on mapped areas of
+the user address space: they will report ENOMEM if the specified range
+includes unmapped gaps (though working on the intervening mapped areas),
+and might fail with EAGAIN if not enough memory for internal structures.
+
+Applications should be considerate in their use of MADV_MERGEABLE,
+restricting its use to areas likely to benefit.  KSM's scans may use a lot
+of processing power: some installations will disable KSM for that reason.
+
+.. _ksm_sysfs:
+
+KSM daemon sysfs interface
+==========================
+
+The KSM daemon is controlled by sysfs files in ``/sys/kernel/mm/ksm/``,
+readable by all but writable only by root:
+
+pages_to_scan
+        how many pages to scan before ksmd goes to sleep
+        e.g. ``echo 100 > /sys/kernel/mm/ksm/pages_to_scan``.
+
+        Default: 100 (chosen for demonstration purposes)
+
+sleep_millisecs
+        how many milliseconds ksmd should sleep before next scan
+        e.g. ``echo 20 > /sys/kernel/mm/ksm/sleep_millisecs``
+
+        Default: 20 (chosen for demonstration purposes)
+
+merge_across_nodes
+        specifies if pages from different NUMA nodes can be merged.
+        When set to 0, ksm merges only pages which physically reside
+        in the memory area of same NUMA node. That brings lower
+        latency to access of shared pages. Systems with more nodes, at
+        significant NUMA distances, are likely to benefit from the
+        lower latency of setting 0. Smaller systems, which need to
+        minimize memory usage, are likely to benefit from the greater
+        sharing of setting 1 (default). You may wish to compare how
+        your system performs under each setting, before deciding on
+        which to use. ``merge_across_nodes`` setting can be changed only
+        when there are no ksm shared pages in the system: set run 2 to
+        unmerge pages first, then to 1 after changing
+        ``merge_across_nodes``, to remerge according to the new setting.
+
+        Default: 1 (merging across nodes as in earlier releases)
+
+run
+        * set to 0 to stop ksmd from running but keep merged pages,
+        * set to 1 to run ksmd e.g. ``echo 1 > /sys/kernel/mm/ksm/run``,
+        * set to 2 to stop ksmd and unmerge all pages currently merged, but
+	  leave mergeable areas registered for next run.
+
+        Default: 0 (must be changed to 1 to activate KSM, except if
+        CONFIG_SYSFS is disabled)
+
+use_zero_pages
+        specifies whether empty pages (i.e. allocated pages that only
+        contain zeroes) should be treated specially.  When set to 1,
+        empty pages are merged with the kernel zero page(s) instead of
+        with each other as it would happen normally. This can improve
+        the performance on architectures with coloured zero pages,
+        depending on the workload. Care should be taken when enabling
+        this setting, as it can potentially degrade the performance of
+        KSM for some workloads, for example if the checksums of pages
+        candidate for merging match the checksum of an empty
+        page. This setting can be changed at any time, it is only
+        effective for pages merged after the change.
+
+        Default: 0 (normal KSM behaviour as in earlier releases)
+
+max_page_sharing
+        Maximum sharing allowed for each KSM page. This enforces a
+        deduplication limit to avoid high latency for virtual memory
+        operations that involve traversal of the virtual mappings that
+        share the KSM page. The minimum value is 2 as a newly created
+        KSM page will have at least two sharers. The higher this value
+        the faster KSM will merge the memory and the higher the
+        deduplication factor will be, but the slower the worst case
+        virtual mappings traversal could be for any given KSM
+        page. Slowing down this traversal means there will be higher
+        latency for certain virtual memory operations happening during
+        swapping, compaction, NUMA balancing and page migration, in
+        turn decreasing responsiveness for the caller of those virtual
+        memory operations. The scheduler latency of other tasks not
+        involved with the VM operations doing the virtual mappings
+        traversal is not affected by this parameter as these
+        traversals are always schedule friendly themselves.
+
+stable_node_chains_prune_millisecs
+        specifies how frequently KSM checks the metadata of the pages
+        that hit the deduplication limit for stale information.
+        Smaller milllisecs values will free up the KSM metadata with
+        lower latency, but they will make ksmd use more CPU during the
+        scan. It's a noop if not a single KSM page hit the
+        ``max_page_sharing`` yet.
+
+The effectiveness of KSM and MADV_MERGEABLE is shown in ``/sys/kernel/mm/ksm/``:
+
+pages_shared
+        how many shared pages are being used
+pages_sharing
+        how many more sites are sharing them i.e. how much saved
+pages_unshared
+        how many pages unique but repeatedly checked for merging
+pages_volatile
+        how many pages changing too fast to be placed in a tree
+full_scans
+        how many times all mergeable areas have been scanned
+stable_node_chains
+        the number of KSM pages that hit the ``max_page_sharing`` limit
+stable_node_dups
+        number of duplicated KSM pages
+
+A high ratio of ``pages_sharing`` to ``pages_shared`` indicates good
+sharing, but a high ratio of ``pages_unshared`` to ``pages_sharing``
+indicates wasted effort.  ``pages_volatile`` embraces several
+different kinds of activity, but a high proportion there would also
+indicate poor use of madvise MADV_MERGEABLE.
+
+The maximum possible ``pages_sharing/pages_shared`` ratio is limited by the
+``max_page_sharing`` tunable. To increase the ratio ``max_page_sharing`` must
+be increased accordingly.
+
+--
+Izik Eidus,
+Hugh Dickins, 17 Nov 2009
diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
new file mode 100644
index 000000000000..d78c5b315f72
--- /dev/null
+++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -0,0 +1,495 @@
+.. _numa_memory_policy:
+
+==================
+NUMA Memory Policy
+==================
+
+What is NUMA Memory Policy?
+============================
+
+In the Linux kernel, "memory policy" determines from which node the kernel will
+allocate memory in a NUMA system or in an emulated NUMA system.  Linux has
+supported platforms with Non-Uniform Memory Access architectures since 2.4.?.
+The current memory policy support was added to Linux 2.6 around May 2004.  This
+document attempts to describe the concepts and APIs of the 2.6 memory policy
+support.
+
+Memory policies should not be confused with cpusets
+(``Documentation/cgroup-v1/cpusets.txt``)
+which is an administrative mechanism for restricting the nodes from which
+memory may be allocated by a set of processes. Memory policies are a
+programming interface that a NUMA-aware application can take advantage of.  When
+both cpusets and policies are applied to a task, the restrictions of the cpuset
+takes priority.  See :ref:`Memory Policies and cpusets <mem_pol_and_cpusets>`
+below for more details.
+
+Memory Policy Concepts
+======================
+
+Scope of Memory Policies
+------------------------
+
+The Linux kernel supports _scopes_ of memory policy, described here from
+most general to most specific:
+
+System Default Policy
+	this policy is "hard coded" into the kernel.  It is the policy
+	that governs all page allocations that aren't controlled by
+	one of the more specific policy scopes discussed below.  When
+	the system is "up and running", the system default policy will
+	use "local allocation" described below.  However, during boot
+	up, the system default policy will be set to interleave
+	allocations across all nodes with "sufficient" memory, so as
+	not to overload the initial boot node with boot-time
+	allocations.
+
+Task/Process Policy
+	this is an optional, per-task policy.  When defined for a
+	specific task, this policy controls all page allocations made
+	by or on behalf of the task that aren't controlled by a more
+	specific scope. If a task does not define a task policy, then
+	all page allocations that would have been controlled by the
+	task policy "fall back" to the System Default Policy.
+
+	The task policy applies to the entire address space of a task. Thus,
+	it is inheritable, and indeed is inherited, across both fork()
+	[clone() w/o the CLONE_VM flag] and exec*().  This allows a parent task
+	to establish the task policy for a child task exec()'d from an
+	executable image that has no awareness of memory policy.  See the
+	:ref:`Memory Policy APIs <memory_policy_apis>` section,
+	below, for an overview of the system call
+	that a task may use to set/change its task/process policy.
+
+	In a multi-threaded task, task policies apply only to the thread
+	[Linux kernel task] that installs the policy and any threads
+	subsequently created by that thread.  Any sibling threads existing
+	at the time a new task policy is installed retain their current
+	policy.
+
+	A task policy applies only to pages allocated after the policy is
+	installed.  Any pages already faulted in by the task when the task
+	changes its task policy remain where they were allocated based on
+	the policy at the time they were allocated.
+
+.. _vma_policy:
+
+VMA Policy
+	A "VMA" or "Virtual Memory Area" refers to a range of a task's
+	virtual address space.  A task may define a specific policy for a range
+	of its virtual address space.   See the
+	:ref:`Memory Policy APIs <memory_policy_apis>` section,
+	below, for an overview of the mbind() system call used to set a VMA
+	policy.
+
+	A VMA policy will govern the allocation of pages that back
+	this region of the address space.  Any regions of the task's
+	address space that don't have an explicit VMA policy will fall
+	back to the task policy, which may itself fall back to the
+	System Default Policy.
+
+	VMA policies have a few complicating details:
+
+	* VMA policy applies ONLY to anonymous pages.  These include
+	  pages allocated for anonymous segments, such as the task
+	  stack and heap, and any regions of the address space
+	  mmap()ed with the MAP_ANONYMOUS flag.  If a VMA policy is
+	  applied to a file mapping, it will be ignored if the mapping
+	  used the MAP_SHARED flag.  If the file mapping used the
+	  MAP_PRIVATE flag, the VMA policy will only be applied when
+	  an anonymous page is allocated on an attempt to write to the
+	  mapping-- i.e., at Copy-On-Write.
+
+	* VMA policies are shared between all tasks that share a
+	  virtual address space--a.k.a. threads--independent of when
+	  the policy is installed; and they are inherited across
+	  fork().  However, because VMA policies refer to a specific
+	  region of a task's address space, and because the address
+	  space is discarded and recreated on exec*(), VMA policies
+	  are NOT inheritable across exec().  Thus, only NUMA-aware
+	  applications may use VMA policies.
+
+	* A task may install a new VMA policy on a sub-range of a
+	  previously mmap()ed region.  When this happens, Linux splits
+	  the existing virtual memory area into 2 or 3 VMAs, each with
+	  it's own policy.
+
+	* By default, VMA policy applies only to pages allocated after
+	  the policy is installed.  Any pages already faulted into the
+	  VMA range remain where they were allocated based on the
+	  policy at the time they were allocated.  However, since
+	  2.6.16, Linux supports page migration via the mbind() system
+	  call, so that page contents can be moved to match a newly
+	  installed policy.
+
+Shared Policy
+	Conceptually, shared policies apply to "memory objects" mapped
+	shared into one or more tasks' distinct address spaces.  An
+	application installs shared policies the same way as VMA
+	policies--using the mbind() system call specifying a range of
+	virtual addresses that map the shared object.  However, unlike
+	VMA policies, which can be considered to be an attribute of a
+	range of a task's address space, shared policies apply
+	directly to the shared object.  Thus, all tasks that attach to
+	the object share the policy, and all pages allocated for the
+	shared object, by any task, will obey the shared policy.
+
+	As of 2.6.22, only shared memory segments, created by shmget() or
+	mmap(MAP_ANONYMOUS|MAP_SHARED), support shared policy.  When shared
+	policy support was added to Linux, the associated data structures were
+	added to hugetlbfs shmem segments.  At the time, hugetlbfs did not
+	support allocation at fault time--a.k.a lazy allocation--so hugetlbfs
+	shmem segments were never "hooked up" to the shared policy support.
+	Although hugetlbfs segments now support lazy allocation, their support
+	for shared policy has not been completed.
+
+	As mentioned above in :ref:`VMA policies <vma_policy>` section,
+	allocations of page cache pages for regular files mmap()ed
+	with MAP_SHARED ignore any VMA policy installed on the virtual
+	address range backed by the shared file mapping.  Rather,
+	shared page cache pages, including pages backing private
+	mappings that have not yet been written by the task, follow
+	task policy, if any, else System Default Policy.
+
+	The shared policy infrastructure supports different policies on subset
+	ranges of the shared object.  However, Linux still splits the VMA of
+	the task that installs the policy for each range of distinct policy.
+	Thus, different tasks that attach to a shared memory segment can have
+	different VMA configurations mapping that one shared object.  This
+	can be seen by examining the /proc/<pid>/numa_maps of tasks sharing
+	a shared memory region, when one task has installed shared policy on
+	one or more ranges of the region.
+
+Components of Memory Policies
+-----------------------------
+
+A NUMA memory policy consists of a "mode", optional mode flags, and
+an optional set of nodes.  The mode determines the behavior of the
+policy, the optional mode flags determine the behavior of the mode,
+and the optional set of nodes can be viewed as the arguments to the
+policy behavior.
+
+Internally, memory policies are implemented by a reference counted
+structure, struct mempolicy.  Details of this structure will be
+discussed in context, below, as required to explain the behavior.
+
+NUMA memory policy supports the following 4 behavioral modes:
+
+Default Mode--MPOL_DEFAULT
+	This mode is only used in the memory policy APIs.  Internally,
+	MPOL_DEFAULT is converted to the NULL memory policy in all
+	policy scopes.  Any existing non-default policy will simply be
+	removed when MPOL_DEFAULT is specified.  As a result,
+	MPOL_DEFAULT means "fall back to the next most specific policy
+	scope."
+
+	For example, a NULL or default task policy will fall back to the
+	system default policy.  A NULL or default vma policy will fall
+	back to the task policy.
+
+	When specified in one of the memory policy APIs, the Default mode
+	does not use the optional set of nodes.
+
+	It is an error for the set of nodes specified for this policy to
+	be non-empty.
+
+MPOL_BIND
+	This mode specifies that memory must come from the set of
+	nodes specified by the policy.  Memory will be allocated from
+	the node in the set with sufficient free memory that is
+	closest to the node where the allocation takes place.
+
+MPOL_PREFERRED
+	This mode specifies that the allocation should be attempted
+	from the single node specified in the policy.  If that
+	allocation fails, the kernel will search other nodes, in order
+	of increasing distance from the preferred node based on
+	information provided by the platform firmware.
+
+	Internally, the Preferred policy uses a single node--the
+	preferred_node member of struct mempolicy.  When the internal
+	mode flag MPOL_F_LOCAL is set, the preferred_node is ignored
+	and the policy is interpreted as local allocation.  "Local"
+	allocation policy can be viewed as a Preferred policy that
+	starts at the node containing the cpu where the allocation
+	takes place.
+
+	It is possible for the user to specify that local allocation
+	is always preferred by passing an empty nodemask with this
+	mode.  If an empty nodemask is passed, the policy cannot use
+	the MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags
+	described below.
+
+MPOL_INTERLEAVED
+	This mode specifies that page allocations be interleaved, on a
+	page granularity, across the nodes specified in the policy.
+	This mode also behaves slightly differently, based on the
+	context where it is used:
+
+	For allocation of anonymous pages and shared memory pages,
+	Interleave mode indexes the set of nodes specified by the
+	policy using the page offset of the faulting address into the
+	segment [VMA] containing the address modulo the number of
+	nodes specified by the policy.  It then attempts to allocate a
+	page, starting at the selected node, as if the node had been
+	specified by a Preferred policy or had been selected by a
+	local allocation.  That is, allocation will follow the per
+	node zonelist.
+
+	For allocation of page cache pages, Interleave mode indexes
+	the set of nodes specified by the policy using a node counter
+	maintained per task.  This counter wraps around to the lowest
+	specified node after it reaches the highest specified node.
+	This will tend to spread the pages out over the nodes
+	specified by the policy based on the order in which they are
+	allocated, rather than based on any page offset into an
+	address range or file.  During system boot up, the temporary
+	interleaved system default policy works in this mode.
+
+NUMA memory policy supports the following optional mode flags:
+
+MPOL_F_STATIC_NODES
+	This flag specifies that the nodemask passed by
+	the user should not be remapped if the task or VMA's set of allowed
+	nodes changes after the memory policy has been defined.
+
+	Without this flag, any time a mempolicy is rebound because of a
+	change in the set of allowed nodes, the node (Preferred) or
+	nodemask (Bind, Interleave) is remapped to the new set of
+	allowed nodes.  This may result in nodes being used that were
+	previously undesired.
+
+	With this flag, if the user-specified nodes overlap with the
+	nodes allowed by the task's cpuset, then the memory policy is
+	applied to their intersection.  If the two sets of nodes do not
+	overlap, the Default policy is used.
+
+	For example, consider a task that is attached to a cpuset with
+	mems 1-3 that sets an Interleave policy over the same set.  If
+	the cpuset's mems change to 3-5, the Interleave will now occur
+	over nodes 3, 4, and 5.  With this flag, however, since only node
+	3 is allowed from the user's nodemask, the "interleave" only
+	occurs over that node.  If no nodes from the user's nodemask are
+	now allowed, the Default behavior is used.
+
+	MPOL_F_STATIC_NODES cannot be combined with the
+	MPOL_F_RELATIVE_NODES flag.  It also cannot be used for
+	MPOL_PREFERRED policies that were created with an empty nodemask
+	(local allocation).
+
+MPOL_F_RELATIVE_NODES
+	This flag specifies that the nodemask passed
+	by the user will be mapped relative to the set of the task or VMA's
+	set of allowed nodes.  The kernel stores the user-passed nodemask,
+	and if the allowed nodes changes, then that original nodemask will
+	be remapped relative to the new set of allowed nodes.
+
+	Without this flag (and without MPOL_F_STATIC_NODES), anytime a
+	mempolicy is rebound because of a change in the set of allowed
+	nodes, the node (Preferred) or nodemask (Bind, Interleave) is
+	remapped to the new set of allowed nodes.  That remap may not
+	preserve the relative nature of the user's passed nodemask to its
+	set of allowed nodes upon successive rebinds: a nodemask of
+	1,3,5 may be remapped to 7-9 and then to 1-3 if the set of
+	allowed nodes is restored to its original state.
+
+	With this flag, the remap is done so that the node numbers from
+	the user's passed nodemask are relative to the set of allowed
+	nodes.  In other words, if nodes 0, 2, and 4 are set in the user's
+	nodemask, the policy will be effected over the first (and in the
+	Bind or Interleave case, the third and fifth) nodes in the set of
+	allowed nodes.  The nodemask passed by the user represents nodes
+	relative to task or VMA's set of allowed nodes.
+
+	If the user's nodemask includes nodes that are outside the range
+	of the new set of allowed nodes (for example, node 5 is set in
+	the user's nodemask when the set of allowed nodes is only 0-3),
+	then the remap wraps around to the beginning of the nodemask and,
+	if not already set, sets the node in the mempolicy nodemask.
+
+	For example, consider a task that is attached to a cpuset with
+	mems 2-5 that sets an Interleave policy over the same set with
+	MPOL_F_RELATIVE_NODES.  If the cpuset's mems change to 3-7, the
+	interleave now occurs over nodes 3,5-7.  If the cpuset's mems
+	then change to 0,2-3,5, then the interleave occurs over nodes
+	0,2-3,5.
+
+	Thanks to the consistent remapping, applications preparing
+	nodemasks to specify memory policies using this flag should
+	disregard their current, actual cpuset imposed memory placement
+	and prepare the nodemask as if they were always located on
+	memory nodes 0 to N-1, where N is the number of memory nodes the
+	policy is intended to manage.  Let the kernel then remap to the
+	set of memory nodes allowed by the task's cpuset, as that may
+	change over time.
+
+	MPOL_F_RELATIVE_NODES cannot be combined with the
+	MPOL_F_STATIC_NODES flag.  It also cannot be used for
+	MPOL_PREFERRED policies that were created with an empty nodemask
+	(local allocation).
+
+Memory Policy Reference Counting
+================================
+
+To resolve use/free races, struct mempolicy contains an atomic reference
+count field.  Internal interfaces, mpol_get()/mpol_put() increment and
+decrement this reference count, respectively.  mpol_put() will only free
+the structure back to the mempolicy kmem cache when the reference count
+goes to zero.
+
+When a new memory policy is allocated, its reference count is initialized
+to '1', representing the reference held by the task that is installing the
+new policy.  When a pointer to a memory policy structure is stored in another
+structure, another reference is added, as the task's reference will be dropped
+on completion of the policy installation.
+
+During run-time "usage" of the policy, we attempt to minimize atomic operations
+on the reference count, as this can lead to cache lines bouncing between cpus
+and NUMA nodes.  "Usage" here means one of the following:
+
+1) querying of the policy, either by the task itself [using the get_mempolicy()
+   API discussed below] or by another task using the /proc/<pid>/numa_maps
+   interface.
+
+2) examination of the policy to determine the policy mode and associated node
+   or node lists, if any, for page allocation.  This is considered a "hot
+   path".  Note that for MPOL_BIND, the "usage" extends across the entire
+   allocation process, which may sleep during page reclaimation, because the
+   BIND policy nodemask is used, by reference, to filter ineligible nodes.
+
+We can avoid taking an extra reference during the usages listed above as
+follows:
+
+1) we never need to get/free the system default policy as this is never
+   changed nor freed, once the system is up and running.
+
+2) for querying the policy, we do not need to take an extra reference on the
+   target task's task policy nor vma policies because we always acquire the
+   task's mm's mmap_sem for read during the query.  The set_mempolicy() and
+   mbind() APIs [see below] always acquire the mmap_sem for write when
+   installing or replacing task or vma policies.  Thus, there is no possibility
+   of a task or thread freeing a policy while another task or thread is
+   querying it.
+
+3) Page allocation usage of task or vma policy occurs in the fault path where
+   we hold them mmap_sem for read.  Again, because replacing the task or vma
+   policy requires that the mmap_sem be held for write, the policy can't be
+   freed out from under us while we're using it for page allocation.
+
+4) Shared policies require special consideration.  One task can replace a
+   shared memory policy while another task, with a distinct mmap_sem, is
+   querying or allocating a page based on the policy.  To resolve this
+   potential race, the shared policy infrastructure adds an extra reference
+   to the shared policy during lookup while holding a spin lock on the shared
+   policy management structure.  This requires that we drop this extra
+   reference when we're finished "using" the policy.  We must drop the
+   extra reference on shared policies in the same query/allocation paths
+   used for non-shared policies.  For this reason, shared policies are marked
+   as such, and the extra reference is dropped "conditionally"--i.e., only
+   for shared policies.
+
+   Because of this extra reference counting, and because we must lookup
+   shared policies in a tree structure under spinlock, shared policies are
+   more expensive to use in the page allocation path.  This is especially
+   true for shared policies on shared memory regions shared by tasks running
+   on different NUMA nodes.  This extra overhead can be avoided by always
+   falling back to task or system default policy for shared memory regions,
+   or by prefaulting the entire shared memory region into memory and locking
+   it down.  However, this might not be appropriate for all applications.
+
+.. _memory_policy_apis:
+
+Memory Policy APIs
+==================
+
+Linux supports 3 system calls for controlling memory policy.  These APIS
+always affect only the calling task, the calling task's address space, or
+some shared object mapped into the calling task's address space.
+
+.. note::
+   the headers that define these APIs and the parameter data types for
+   user space applications reside in a package that is not part of the
+   Linux kernel.  The kernel system call interfaces, with the 'sys\_'
+   prefix, are defined in <linux/syscalls.h>; the mode and flag
+   definitions are defined in <linux/mempolicy.h>.
+
+Set [Task] Memory Policy::
+
+	long set_mempolicy(int mode, const unsigned long *nmask,
+					unsigned long maxnode);
+
+Set's the calling task's "task/process memory policy" to mode
+specified by the 'mode' argument and the set of nodes defined by
+'nmask'.  'nmask' points to a bit mask of node ids containing at least
+'maxnode' ids.  Optional mode flags may be passed by combining the
+'mode' argument with the flag (for example: MPOL_INTERLEAVE |
+MPOL_F_STATIC_NODES).
+
+See the set_mempolicy(2) man page for more details
+
+
+Get [Task] Memory Policy or Related Information::
+
+	long get_mempolicy(int *mode,
+			   const unsigned long *nmask, unsigned long maxnode,
+			   void *addr, int flags);
+
+Queries the "task/process memory policy" of the calling task, or the
+policy or location of a specified virtual address, depending on the
+'flags' argument.
+
+See the get_mempolicy(2) man page for more details
+
+
+Install VMA/Shared Policy for a Range of Task's Address Space::
+
+	long mbind(void *start, unsigned long len, int mode,
+		   const unsigned long *nmask, unsigned long maxnode,
+		   unsigned flags);
+
+mbind() installs the policy specified by (mode, nmask, maxnodes) as a
+VMA policy for the range of the calling task's address space specified
+by the 'start' and 'len' arguments.  Additional actions may be
+requested via the 'flags' argument.
+
+See the mbind(2) man page for more details.
+
+Memory Policy Command Line Interface
+====================================
+
+Although not strictly part of the Linux implementation of memory policy,
+a command line tool, numactl(8), exists that allows one to:
+
++ set the task policy for a specified program via set_mempolicy(2), fork(2) and
+  exec(2)
+
++ set the shared policy for a shared memory segment via mbind(2)
+
+The numactl(8) tool is packaged with the run-time version of the library
+containing the memory policy system call wrappers.  Some distributions
+package the headers and compile-time libraries in a separate development
+package.
+
+.. _mem_pol_and_cpusets:
+
+Memory Policies and cpusets
+===========================
+
+Memory policies work within cpusets as described above.  For memory policies
+that require a node or set of nodes, the nodes are restricted to the set of
+nodes whose memories are allowed by the cpuset constraints.  If the nodemask
+specified for the policy contains nodes that are not allowed by the cpuset and
+MPOL_F_RELATIVE_NODES is not used, the intersection of the set of nodes
+specified for the policy and the set of nodes with memory is used.  If the
+result is the empty set, the policy is considered invalid and cannot be
+installed.  If MPOL_F_RELATIVE_NODES is used, the policy's nodes are mapped
+onto and folded into the task's set of allowed nodes as previously described.
+
+The interaction of memory policies and cpusets can be problematic when tasks
+in two cpusets share access to a memory region, such as shared memory segments
+created by shmget() of mmap() with the MAP_ANONYMOUS and MAP_SHARED flags, and
+any of the tasks install shared policy on the region, only nodes whose
+memories are allowed in both cpusets may be used in the policies.  Obtaining
+this information requires "stepping outside" the memory policy APIs to use the
+cpuset information and requires that one know in what cpusets other task might
+be attaching to the shared region.  Furthermore, if the cpusets' allowed
+memory sets are disjoint, "local" allocation is the only valid policy.
diff --git a/Documentation/vm/pagemap.txt b/Documentation/admin-guide/mm/pagemap.rst
index eafcefa15261..577af85beb41 100644
--- a/Documentation/vm/pagemap.txt
+++ b/Documentation/admin-guide/mm/pagemap.rst
@@ -1,21 +1,25 @@
-pagemap, from the userspace perspective
----------------------------------------
+.. _pagemap:
+
+=============================
+Examining Process Page Tables
+=============================
 
 pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
 userspace programs to examine the page tables and related information by
-reading files in /proc.
+reading files in ``/proc``.
 
 There are four components to pagemap:
 
- * /proc/pid/pagemap.  This file lets a userspace process find out which
+ * ``/proc/pid/pagemap``.  This file lets a userspace process find out which
    physical frame each virtual page is mapped to.  It contains one 64-bit
    value for each virtual page, containing the following data (from
-   fs/proc/task_mmu.c, above pagemap_read):
+   ``fs/proc/task_mmu.c``, above pagemap_read):
 
     * Bits 0-54  page frame number (PFN) if present
     * Bits 0-4   swap type if swapped
     * Bits 5-54  swap offset if swapped
-    * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
+    * Bit  55    pte is soft-dirty (see
+      :ref:`Documentation/admin-guide/mm/soft-dirty.rst <soft_dirty>`)
     * Bit  56    page exclusively mapped (since 4.2)
     * Bits 57-60 zero
     * Bit  61    page is file-page or shared-anon (since 3.5)
@@ -33,28 +37,28 @@ There are four components to pagemap:
    precisely which pages are mapped (or in swap) and comparing mapped
    pages between processes.
 
-   Efficient users of this interface will use /proc/pid/maps to
+   Efficient users of this interface will use ``/proc/pid/maps`` to
    determine which areas of memory are actually mapped and llseek to
    skip over unmapped regions.
 
- * /proc/kpagecount.  This file contains a 64-bit count of the number of
+ * ``/proc/kpagecount``.  This file contains a 64-bit count of the number of
    times each page is mapped, indexed by PFN.
 
- * /proc/kpageflags.  This file contains a 64-bit set of flags for each
+ * ``/proc/kpageflags``.  This file contains a 64-bit set of flags for each
    page, indexed by PFN.
 
-   The flags are (from fs/proc/page.c, above kpageflags_read):
-
-     0. LOCKED
-     1. ERROR
-     2. REFERENCED
-     3. UPTODATE
-     4. DIRTY
-     5. LRU
-     6. ACTIVE
-     7. SLAB
-     8. WRITEBACK
-     9. RECLAIM
+   The flags are (from ``fs/proc/page.c``, above kpageflags_read):
+
+    0. LOCKED
+    1. ERROR
+    2. REFERENCED
+    3. UPTODATE
+    4. DIRTY
+    5. LRU
+    6. ACTIVE
+    7. SLAB
+    8. WRITEBACK
+    9. RECLAIM
     10. BUDDY
     11. MMAP
     12. ANON
@@ -72,98 +76,111 @@ There are four components to pagemap:
     24. ZERO_PAGE
     25. IDLE
 
- * /proc/kpagecgroup.  This file contains a 64-bit inode number of the
+ * ``/proc/kpagecgroup``.  This file contains a 64-bit inode number of the
    memory cgroup each page is charged to, indexed by PFN. Only available when
    CONFIG_MEMCG is set.
 
-Short descriptions to the page flags:
-
- 0. LOCKED
-    page is being locked for exclusive access, eg. by undergoing read/write IO
-
- 7. SLAB
-    page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator
-    When compound page is used, SLUB/SLQB will only set this flag on the head
-    page; SLOB will not flag it at all.
+Short descriptions to the page flags
+====================================
 
-10. BUDDY
+0 - LOCKED
+   page is being locked for exclusive access, e.g. by undergoing read/write IO
+7 - SLAB
+   page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator
+   When compound page is used, SLUB/SLQB will only set this flag on the head
+   page; SLOB will not flag it at all.
+10 - BUDDY
     a free memory block managed by the buddy system allocator
     The buddy system organizes free memory in blocks of various orders.
     An order N block has 2^N physically contiguous pages, with the BUDDY flag
     set for and _only_ for the first page.
-
-15. COMPOUND_HEAD
-16. COMPOUND_TAIL
+15 - COMPOUND_HEAD
     A compound page with order N consists of 2^N physically contiguous pages.
     A compound page with order 2 takes the form of "HTTT", where H donates its
     head page and T donates its tail page(s).  The major consumers of compound
-    pages are hugeTLB pages (Documentation/vm/hugetlbpage.txt), the SLUB etc.
-    memory allocators and various device drivers. However in this interface,
-    only huge/giga pages are made visible to end users.
-17. HUGE
+    pages are hugeTLB pages
+    (:ref:`Documentation/admin-guide/mm/hugetlbpage.rst <hugetlbpage>`),
+    the SLUB etc.  memory allocators and various device drivers.
+    However in this interface, only huge/giga pages are made visible
+    to end users.
+16 - COMPOUND_TAIL
+    A compound page tail (see description above).
+17 - HUGE
     this is an integral part of a HugeTLB page
-
-19. HWPOISON
+19 - HWPOISON
     hardware detected memory corruption on this page: don't touch the data!
-
-20. NOPAGE
+20 - NOPAGE
     no page frame exists at the requested address
-
-21. KSM
+21 - KSM
     identical memory pages dynamically shared between one or more processes
-
-22. THP
+22 - THP
     contiguous pages which construct transparent hugepages
-
-23. BALLOON
+23 - BALLOON
     balloon compaction page
-
-24. ZERO_PAGE
+24 - ZERO_PAGE
     zero page for pfn_zero or huge_zero page
-
-25. IDLE
+25 - IDLE
     page has not been accessed since it was marked idle (see
-    Documentation/vm/idle_page_tracking.txt). Note that this flag may be
-    stale in case the page was accessed via a PTE. To make sure the flag
-    is up-to-date one has to read /sys/kernel/mm/page_idle/bitmap first.
-
-    [IO related page flags]
- 1. ERROR     IO error occurred
- 3. UPTODATE  page has up-to-date data
-              ie. for file backed page: (in-memory data revision >= on-disk one)
- 4. DIRTY     page has been written to, hence contains new data
-              ie. for file backed page: (in-memory data revision >  on-disk one)
- 8. WRITEBACK page is being synced to disk
-
-    [LRU related page flags]
- 5. LRU         page is in one of the LRU lists
- 6. ACTIVE      page is in the active LRU list
-18. UNEVICTABLE page is in the unevictable (non-)LRU list
-                It is somehow pinned and not a candidate for LRU page reclaims,
-		eg. ramfs pages, shmctl(SHM_LOCK) and mlock() memory segments
- 2. REFERENCED  page has been referenced since last LRU list enqueue/requeue
- 9. RECLAIM     page will be reclaimed soon after its pageout IO completed
-11. MMAP        a memory mapped page
-12. ANON        a memory mapped page that is not part of a file
-13. SWAPCACHE   page is mapped to swap space, ie. has an associated swap entry
-14. SWAPBACKED  page is backed by swap/RAM
+    :ref:`Documentation/admin-guide/mm/idle_page_tracking.rst <idle_page_tracking>`).
+    Note that this flag may be stale in case the page was accessed via
+    a PTE. To make sure the flag is up-to-date one has to read
+    ``/sys/kernel/mm/page_idle/bitmap`` first.
+
+IO related page flags
+---------------------
+
+1 - ERROR
+   IO error occurred
+3 - UPTODATE
+   page has up-to-date data
+   ie. for file backed page: (in-memory data revision >= on-disk one)
+4 - DIRTY
+   page has been written to, hence contains new data
+   i.e. for file backed page: (in-memory data revision >  on-disk one)
+8 - WRITEBACK
+   page is being synced to disk
+
+LRU related page flags
+----------------------
+
+5 - LRU
+   page is in one of the LRU lists
+6 - ACTIVE
+   page is in the active LRU list
+18 - UNEVICTABLE
+   page is in the unevictable (non-)LRU list It is somehow pinned and
+   not a candidate for LRU page reclaims, e.g. ramfs pages,
+   shmctl(SHM_LOCK) and mlock() memory segments
+2 - REFERENCED
+   page has been referenced since last LRU list enqueue/requeue
+9 - RECLAIM
+   page will be reclaimed soon after its pageout IO completed
+11 - MMAP
+   a memory mapped page
+12 - ANON
+   a memory mapped page that is not part of a file
+13 - SWAPCACHE
+   page is mapped to swap space, i.e. has an associated swap entry
+14 - SWAPBACKED
+   page is backed by swap/RAM
 
 The page-types tool in the tools/vm directory can be used to query the
 above flags.
 
-Using pagemap to do something useful:
+Using pagemap to do something useful
+====================================
 
 The general procedure for using pagemap to find out about a process' memory
 usage goes like this:
 
- 1. Read /proc/pid/maps to determine which parts of the memory space are
+ 1. Read ``/proc/pid/maps`` to determine which parts of the memory space are
     mapped to what.
  2. Select the maps you are interested in -- all of them, or a particular
     library, or the stack or the heap, etc.
- 3. Open /proc/pid/pagemap and seek to the pages you would like to examine.
+ 3. Open ``/proc/pid/pagemap`` and seek to the pages you would like to examine.
  4. Read a u64 for each page from pagemap.
- 5. Open /proc/kpagecount and/or /proc/kpageflags.  For each PFN you just
-    read, seek to that entry in the file, and read the data you want.
+ 5. Open ``/proc/kpagecount`` and/or ``/proc/kpageflags``.  For each PFN you
+    just read, seek to that entry in the file, and read the data you want.
 
 For example, to find the "unique set size" (USS), which is the amount of
 memory that a process is using that is not shared with any other process,
@@ -171,7 +188,8 @@ you can go through every map in the process, find the PFNs, look those up
 in kpagecount, and tally up the number of pages that are only referenced
 once.
 
-Other notes:
+Other notes
+===========
 
 Reading from any of the files will return -EINVAL if you are not starting
 the read on an 8-byte boundary (e.g., if you sought an odd number of bytes
diff --git a/Documentation/vm/soft-dirty.txt b/Documentation/admin-guide/mm/soft-dirty.rst
index 55684d11a1e8..cb0cfd6672fa 100644
--- a/Documentation/vm/soft-dirty.txt
+++ b/Documentation/admin-guide/mm/soft-dirty.rst
@@ -1,34 +1,38 @@
-                            SOFT-DIRTY PTEs
+.. _soft_dirty:
 
-  The soft-dirty is a bit on a PTE which helps to track which pages a task
+===============
+Soft-Dirty PTEs
+===============
+
+The soft-dirty is a bit on a PTE which helps to track which pages a task
 writes to. In order to do this tracking one should
 
   1. Clear soft-dirty bits from the task's PTEs.
 
-     This is done by writing "4" into the /proc/PID/clear_refs file of the
+     This is done by writing "4" into the ``/proc/PID/clear_refs`` file of the
      task in question.
 
   2. Wait some time.
 
   3. Read soft-dirty bits from the PTEs.
 
-     This is done by reading from the /proc/PID/pagemap. The bit 55 of the
+     This is done by reading from the ``/proc/PID/pagemap``. The bit 55 of the
      64-bit qword is the soft-dirty one. If set, the respective PTE was
      written to since step 1.
 
 
-  Internally, to do this tracking, the writable bit is cleared from PTEs
+Internally, to do this tracking, the writable bit is cleared from PTEs
 when the soft-dirty bit is cleared. So, after this, when the task tries to
 modify a page at some virtual address the #PF occurs and the kernel sets
 the soft-dirty bit on the respective PTE.
 
-  Note, that although all the task's address space is marked as r/o after the
+Note, that although all the task's address space is marked as r/o after the
 soft-dirty bits clear, the #PF-s that occur after that are processed fast.
 This is so, since the pages are still mapped to physical memory, and thus all
 the kernel does is finds this fact out and puts both writable and soft-dirty
 bits on the PTE.
 
-  While in most cases tracking memory changes by #PF-s is more than enough
+While in most cases tracking memory changes by #PF-s is more than enough
 there is still a scenario when we can lose soft dirty bits -- a task
 unmaps a previously mapped memory region and then maps a new one at exactly
 the same place. When unmap is called, the kernel internally clears PTE values
@@ -36,7 +40,7 @@ including soft dirty bits. To notify user space application about such
 memory region renewal the kernel always marks new memory regions (and
 expanded regions) as soft dirty.
 
-  This feature is actively used by the checkpoint-restore project. You
+This feature is actively used by the checkpoint-restore project. You
 can find more details about it on http://criu.org
 
 
diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
new file mode 100644
index 000000000000..7ab93a8404b9
--- /dev/null
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -0,0 +1,418 @@
+.. _admin_guide_transhuge:
+
+============================
+Transparent Hugepage Support
+============================
+
+Objective
+=========
+
+Performance critical computing applications dealing with large memory
+working sets are already running on top of libhugetlbfs and in turn
+hugetlbfs. Transparent HugePage Support (THP) is an alternative mean of
+using huge pages for the backing of virtual memory with huge pages
+that supports the automatic promotion and demotion of page sizes and
+without the shortcomings of hugetlbfs.
+
+Currently THP only works for anonymous memory mappings and tmpfs/shmem.
+But in the future it can expand to other filesystems.
+
+.. note::
+   in the examples below we presume that the basic page size is 4K and
+   the huge page size is 2M, although the actual numbers may vary
+   depending on the CPU architecture.
+
+The reason applications are running faster is because of two
+factors. The first factor is almost completely irrelevant and it's not
+of significant interest because it'll also have the downside of
+requiring larger clear-page copy-page in page faults which is a
+potentially negative effect. The first factor consists in taking a
+single page fault for each 2M virtual region touched by userland (so
+reducing the enter/exit kernel frequency by a 512 times factor). This
+only matters the first time the memory is accessed for the lifetime of
+a memory mapping. The second long lasting and much more important
+factor will affect all subsequent accesses to the memory for the whole
+runtime of the application. The second factor consist of two
+components:
+
+1) the TLB miss will run faster (especially with virtualization using
+   nested pagetables but almost always also on bare metal without
+   virtualization)
+
+2) a single TLB entry will be mapping a much larger amount of virtual
+   memory in turn reducing the number of TLB misses. With
+   virtualization and nested pagetables the TLB can be mapped of
+   larger size only if both KVM and the Linux guest are using
+   hugepages but a significant speedup already happens if only one of
+   the two is using hugepages just because of the fact the TLB miss is
+   going to run faster.
+
+THP can be enabled system wide or restricted to certain tasks or even
+memory ranges inside task's address space. Unless THP is completely
+disabled, there is ``khugepaged`` daemon that scans memory and
+collapses sequences of basic pages into huge pages.
+
+The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>`
+interface and using madivse(2) and prctl(2) system calls.
+
+Transparent Hugepage Support maximizes the usefulness of free memory
+if compared to the reservation approach of hugetlbfs by allowing all
+unused memory to be used as cache or other movable (or even unmovable
+entities). It doesn't require reservation to prevent hugepage
+allocation failures to be noticeable from userland. It allows paging
+and all other advanced VM features to be available on the
+hugepages. It requires no modifications for applications to take
+advantage of it.
+
+Applications however can be further optimized to take advantage of
+this feature, like for example they've been optimized before to avoid
+a flood of mmap system calls for every malloc(4k). Optimizing userland
+is by far not mandatory and khugepaged already can take care of long
+lived page allocations even for hugepage unaware applications that
+deals with large amounts of memory.
+
+In certain cases when hugepages are enabled system wide, application
+may end up allocating more memory resources. An application may mmap a
+large region but only touch 1 byte of it, in that case a 2M page might
+be allocated instead of a 4k page for no good. This is why it's
+possible to disable hugepages system-wide and to only have them inside
+MADV_HUGEPAGE madvise regions.
+
+Embedded systems should enable hugepages only inside madvise regions
+to eliminate any risk of wasting any precious byte of memory and to
+only run faster.
+
+Applications that gets a lot of benefit from hugepages and that don't
+risk to lose memory by using hugepages, should use
+madvise(MADV_HUGEPAGE) on their critical mmapped regions.
+
+.. _thp_sysfs:
+
+sysfs
+=====
+
+Global THP controls
+-------------------
+
+Transparent Hugepage Support for anonymous memory can be entirely disabled
+(mostly for debugging purposes) or only enabled inside MADV_HUGEPAGE
+regions (to avoid the risk of consuming more memory resources) or enabled
+system wide. This can be achieved with one of::
+
+	echo always >/sys/kernel/mm/transparent_hugepage/enabled
+	echo madvise >/sys/kernel/mm/transparent_hugepage/enabled
+	echo never >/sys/kernel/mm/transparent_hugepage/enabled
+
+It's also possible to limit defrag efforts in the VM to generate
+anonymous hugepages in case they're not immediately free to madvise
+regions or to never try to defrag memory and simply fallback to regular
+pages unless hugepages are immediately available. Clearly if we spend CPU
+time to defrag memory, we would expect to gain even more by the fact we
+use hugepages later instead of regular pages. This isn't always
+guaranteed, but it may be more likely in case the allocation is for a
+MADV_HUGEPAGE region.
+
+::
+
+	echo always >/sys/kernel/mm/transparent_hugepage/defrag
+	echo defer >/sys/kernel/mm/transparent_hugepage/defrag
+	echo defer+madvise >/sys/kernel/mm/transparent_hugepage/defrag
+	echo madvise >/sys/kernel/mm/transparent_hugepage/defrag
+	echo never >/sys/kernel/mm/transparent_hugepage/defrag
+
+always
+	means that an application requesting THP will stall on
+	allocation failure and directly reclaim pages and compact
+	memory in an effort to allocate a THP immediately. This may be
+	desirable for virtual machines that benefit heavily from THP
+	use and are willing to delay the VM start to utilise them.
+
+defer
+	means that an application will wake kswapd in the background
+	to reclaim pages and wake kcompactd to compact memory so that
+	THP is available in the near future. It's the responsibility
+	of khugepaged to then install the THP pages later.
+
+defer+madvise
+	will enter direct reclaim and compaction like ``always``, but
+	only for regions that have used madvise(MADV_HUGEPAGE); all
+	other regions will wake kswapd in the background to reclaim
+	pages and wake kcompactd to compact memory so that THP is
+	available in the near future.
+
+madvise
+	will enter direct reclaim like ``always`` but only for regions
+	that are have used madvise(MADV_HUGEPAGE). This is the default
+	behaviour.
+
+never
+	should be self-explanatory.
+
+By default kernel tries to use huge zero page on read page fault to
+anonymous mapping. It's possible to disable huge zero page by writing 0
+or enable it back by writing 1::
+
+	echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page
+	echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page
+
+Some userspace (such as a test program, or an optimized memory allocation
+library) may want to know the size (in bytes) of a transparent hugepage::
+
+	cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size
+
+khugepaged will be automatically started when
+transparent_hugepage/enabled is set to "always" or "madvise, and it'll
+be automatically shutdown if it's set to "never".
+
+Khugepaged controls
+-------------------
+
+khugepaged runs usually at low frequency so while one may not want to
+invoke defrag algorithms synchronously during the page faults, it
+should be worth invoking defrag at least in khugepaged. However it's
+also possible to disable defrag in khugepaged by writing 0 or enable
+defrag in khugepaged by writing 1::
+
+	echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
+	echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
+
+You can also control how many pages khugepaged should scan at each
+pass::
+
+	/sys/kernel/mm/transparent_hugepage/khugepaged/pages_to_scan
+
+and how many milliseconds to wait in khugepaged between each pass (you
+can set this to 0 to run khugepaged at 100% utilization of one core)::
+
+	/sys/kernel/mm/transparent_hugepage/khugepaged/scan_sleep_millisecs
+
+and how many milliseconds to wait in khugepaged if there's an hugepage
+allocation failure to throttle the next allocation attempt::
+
+	/sys/kernel/mm/transparent_hugepage/khugepaged/alloc_sleep_millisecs
+
+The khugepaged progress can be seen in the number of pages collapsed::
+
+	/sys/kernel/mm/transparent_hugepage/khugepaged/pages_collapsed
+
+for each pass::
+
+	/sys/kernel/mm/transparent_hugepage/khugepaged/full_scans
+
+``max_ptes_none`` specifies how many extra small pages (that are
+not already mapped) can be allocated when collapsing a group
+of small pages into one large page::
+
+	/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none
+
+A higher value leads to use additional memory for programs.
+A lower value leads to gain less thp performance. Value of
+max_ptes_none can waste cpu time very little, you can
+ignore it.
+
+``max_ptes_swap`` specifies how many pages can be brought in from
+swap when collapsing a group of pages into a transparent huge page::
+
+	/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap
+
+A higher value can cause excessive swap IO and waste
+memory. A lower value can prevent THPs from being
+collapsed, resulting fewer pages being collapsed into
+THPs, and lower memory access performance.
+
+Boot parameter
+==============
+
+You can change the sysfs boot time defaults of Transparent Hugepage
+Support by passing the parameter ``transparent_hugepage=always`` or
+``transparent_hugepage=madvise`` or ``transparent_hugepage=never``
+to the kernel command line.
+
+Hugepages in tmpfs/shmem
+========================
+
+You can control hugepage allocation policy in tmpfs with mount option
+``huge=``. It can have following values:
+
+always
+    Attempt to allocate huge pages every time we need a new page;
+
+never
+    Do not allocate huge pages;
+
+within_size
+    Only allocate huge page if it will be fully within i_size.
+    Also respect fadvise()/madvise() hints;
+
+advise
+    Only allocate huge pages if requested with fadvise()/madvise();
+
+The default policy is ``never``.
+
+``mount -o remount,huge= /mountpoint`` works fine after mount: remounting
+``huge=never`` will not attempt to break up huge pages at all, just stop more
+from being allocated.
+
+There's also sysfs knob to control hugepage allocation policy for internal
+shmem mount: /sys/kernel/mm/transparent_hugepage/shmem_enabled. The mount
+is used for SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or
+MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem.
+
+In addition to policies listed above, shmem_enabled allows two further
+values:
+
+deny
+    For use in emergencies, to force the huge option off from
+    all mounts;
+force
+    Force the huge option on for all - very useful for testing;
+
+Need of application restart
+===========================
+
+The transparent_hugepage/enabled values and tmpfs mount option only affect
+future behavior. So to make them effective you need to restart any
+application that could have been using hugepages. This also applies to the
+regions registered in khugepaged.
+
+Monitoring usage
+================
+
+The number of anonymous transparent huge pages currently used by the
+system is available by reading the AnonHugePages field in ``/proc/meminfo``.
+To identify what applications are using anonymous transparent huge pages,
+it is necessary to read ``/proc/PID/smaps`` and count the AnonHugePages fields
+for each mapping.
+
+The number of file transparent huge pages mapped to userspace is available
+by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``.
+To identify what applications are mapping file transparent huge pages, it
+is necessary to read ``/proc/PID/smaps`` and count the FileHugeMapped fields
+for each mapping.
+
+Note that reading the smaps file is expensive and reading it
+frequently will incur overhead.
+
+There are a number of counters in ``/proc/vmstat`` that may be used to
+monitor how successfully the system is providing huge pages for use.
+
+thp_fault_alloc
+	is incremented every time a huge page is successfully
+	allocated to handle a page fault. This applies to both the
+	first time a page is faulted and for COW faults.
+
+thp_collapse_alloc
+	is incremented by khugepaged when it has found
+	a range of pages to collapse into one huge page and has
+	successfully allocated a new huge page to store the data.
+
+thp_fault_fallback
+	is incremented if a page fault fails to allocate
+	a huge page and instead falls back to using small pages.
+
+thp_collapse_alloc_failed
+	is incremented if khugepaged found a range
+	of pages that should be collapsed into one huge page but failed
+	the allocation.
+
+thp_file_alloc
+	is incremented every time a file huge page is successfully
+	allocated.
+
+thp_file_mapped
+	is incremented every time a file huge page is mapped into
+	user address space.
+
+thp_split_page
+	is incremented every time a huge page is split into base
+	pages. This can happen for a variety of reasons but a common
+	reason is that a huge page is old and is being reclaimed.
+	This action implies splitting all PMD the page mapped with.
+
+thp_split_page_failed
+	is incremented if kernel fails to split huge
+	page. This can happen if the page was pinned by somebody.
+
+thp_deferred_split_page
+	is incremented when a huge page is put onto split
+	queue. This happens when a huge page is partially unmapped and
+	splitting it would free up some memory. Pages on split queue are
+	going to be split under memory pressure.
+
+thp_split_pmd
+	is incremented every time a PMD split into table of PTEs.
+	This can happen, for instance, when application calls mprotect() or
+	munmap() on part of huge page. It doesn't split huge page, only
+	page table entry.
+
+thp_zero_page_alloc
+	is incremented every time a huge zero page is
+	successfully allocated. It includes allocations which where
+	dropped due race with other allocation. Note, it doesn't count
+	every map of the huge zero page, only its allocation.
+
+thp_zero_page_alloc_failed
+	is incremented if kernel fails to allocate
+	huge zero page and falls back to using small pages.
+
+thp_swpout
+	is incremented every time a huge page is swapout in one
+	piece without splitting.
+
+thp_swpout_fallback
+	is incremented if a huge page has to be split before swapout.
+	Usually because failed to allocate some continuous swap space
+	for the huge page.
+
+As the system ages, allocating huge pages may be expensive as the
+system uses memory compaction to copy data around memory to free a
+huge page for use. There are some counters in ``/proc/vmstat`` to help
+monitor this overhead.
+
+compact_stall
+	is incremented every time a process stalls to run
+	memory compaction so that a huge page is free for use.
+
+compact_success
+	is incremented if the system compacted memory and
+	freed a huge page for use.
+
+compact_fail
+	is incremented if the system tries to compact memory
+	but failed.
+
+compact_pages_moved
+	is incremented each time a page is moved. If
+	this value is increasing rapidly, it implies that the system
+	is copying a lot of data to satisfy the huge page allocation.
+	It is possible that the cost of copying exceeds any savings
+	from reduced TLB misses.
+
+compact_pagemigrate_failed
+	is incremented when the underlying mechanism
+	for moving a page failed.
+
+compact_blocks_moved
+	is incremented each time memory compaction examines
+	a huge page aligned range of pages.
+
+It is possible to establish how long the stalls were using the function
+tracer to record how long was spent in __alloc_pages_nodemask and
+using the mm_page_alloc tracepoint to identify which allocations were
+for huge pages.
+
+Optimizing the applications
+===========================
+
+To be guaranteed that the kernel will map a 2M page immediately in any
+memory region, the mmap region has to be hugepage naturally
+aligned. posix_memalign() can provide that guarantee.
+
+Hugetlbfs
+=========
+
+You can use hugetlbfs on a kernel that has transparent hugepage
+support enabled just fine as always. No difference can be noted in
+hugetlbfs other than there will be less overall fragmentation. All
+usual features belonging to hugetlbfs are preserved and
+unaffected. libhugetlbfs will also work fine as usual.
diff --git a/Documentation/vm/userfaultfd.txt b/Documentation/admin-guide/mm/userfaultfd.rst
index bb2f945f87ab..5048cf661a8a 100644
--- a/Documentation/vm/userfaultfd.txt
+++ b/Documentation/admin-guide/mm/userfaultfd.rst
@@ -1,6 +1,11 @@
-= Userfaultfd =
+.. _userfaultfd:
 
-== Objective ==
+===========
+Userfaultfd
+===========
+
+Objective
+=========
 
 Userfaults allow the implementation of on-demand paging from userland
 and more generally they allow userland to take control of various
@@ -9,7 +14,8 @@ memory page faults, something otherwise only the kernel code could do.
 For example userfaults allows a proper and more optimal implementation
 of the PROT_NONE+SIGSEGV trick.
 
-== Design ==
+Design
+======
 
 Userfaults are delivered and resolved through the userfaultfd syscall.
 
@@ -41,7 +47,8 @@ different processes without them being aware about what is going on
 themselves on the same region the manager is already tracking, which
 is a corner case that would currently return -EBUSY).
 
-== API ==
+API
+===
 
 When first opened the userfaultfd must be enabled invoking the
 UFFDIO_API ioctl specifying a uffdio_api.api value set to UFFD_API (or
@@ -101,7 +108,8 @@ UFFDIO_COPY. They're atomic as in guaranteeing that nothing can see an
 half copied page since it'll keep userfaulting until the copy has
 finished.
 
-== QEMU/KVM ==
+QEMU/KVM
+========
 
 QEMU/KVM is using the userfaultfd syscall to implement postcopy live
 migration. Postcopy live migration is one form of memory
@@ -163,7 +171,8 @@ sending the same page twice (in case the userfault is read by the
 postcopy thread just before UFFDIO_COPY|ZEROPAGE runs in the migration
 thread).
 
-== Non-cooperative userfaultfd ==
+Non-cooperative userfaultfd
+===========================
 
 When the userfaultfd is monitored by an external manager, the manager
 must be able to track changes in the process virtual memory
@@ -172,27 +181,30 @@ the same read(2) protocol as for the page fault notifications. The
 manager has to explicitly enable these events by setting appropriate
 bits in uffdio_api.features passed to UFFDIO_API ioctl:
 
-UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
-this feature is enabled, the userfaultfd context of the parent process
-is duplicated into the newly created process. The manager receives
-UFFD_EVENT_FORK with file descriptor of the new userfaultfd context in
-the uffd_msg.fork.
-
-UFFD_FEATURE_EVENT_REMAP - enable notifications about mremap()
-calls. When the non-cooperative process moves a virtual memory area to
-a different location, the manager will receive UFFD_EVENT_REMAP. The
-uffd_msg.remap will contain the old and new addresses of the area and
-its original length.
-
-UFFD_FEATURE_EVENT_REMOVE - enable notifications about
-madvise(MADV_REMOVE) and madvise(MADV_DONTNEED) calls. The event
-UFFD_EVENT_REMOVE will be generated upon these calls to madvise. The
-uffd_msg.remove will contain start and end addresses of the removed
-area.
-
-UFFD_FEATURE_EVENT_UNMAP - enable notifications about memory
-unmapping. The manager will get UFFD_EVENT_UNMAP with uffd_msg.remove
-containing start and end addresses of the unmapped area.
+UFFD_FEATURE_EVENT_FORK
+	enable userfaultfd hooks for fork(). When this feature is
+	enabled, the userfaultfd context of the parent process is
+	duplicated into the newly created process. The manager
+	receives UFFD_EVENT_FORK with file descriptor of the new
+	userfaultfd context in the uffd_msg.fork.
+
+UFFD_FEATURE_EVENT_REMAP
+	enable notifications about mremap() calls. When the
+	non-cooperative process moves a virtual memory area to a
+	different location, the manager will receive
+	UFFD_EVENT_REMAP. The uffd_msg.remap will contain the old and
+	new addresses of the area and its original length.
+
+UFFD_FEATURE_EVENT_REMOVE
+	enable notifications about madvise(MADV_REMOVE) and
+	madvise(MADV_DONTNEED) calls. The event UFFD_EVENT_REMOVE will
+	be generated upon these calls to madvise. The uffd_msg.remove
+	will contain start and end addresses of the removed area.
+
+UFFD_FEATURE_EVENT_UNMAP
+	enable notifications about memory unmapping. The manager will
+	get UFFD_EVENT_UNMAP with uffd_msg.remove containing start and
+	end addresses of the unmapped area.
 
 Although the UFFD_FEATURE_EVENT_REMOVE and UFFD_FEATURE_EVENT_UNMAP
 are pretty similar, they quite differ in the action expected from the
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index d2b6fda3d67b..ab2fe0eda1d7 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -145,7 +145,7 @@ feature enabled.]
 
 In this mode ``intel_pstate`` registers utilization update callbacks with the
 CPU scheduler in order to run a P-state selection algorithm, either
-``powersave`` or ``performance``, depending on the ``scaling_cur_freq`` policy
+``powersave`` or ``performance``, depending on the ``scaling_governor`` policy
 setting in ``sysfs``.  The current CPU frequency information to be made
 available from the ``scaling_cur_freq`` policy attribute in ``sysfs`` is
 periodically updated by those utilization update callbacks too.
diff --git a/Documentation/admin-guide/pm/sleep-states.rst b/Documentation/admin-guide/pm/sleep-states.rst
index 1e5c0f00cb2f..dbf5acd49f35 100644
--- a/Documentation/admin-guide/pm/sleep-states.rst
+++ b/Documentation/admin-guide/pm/sleep-states.rst
@@ -15,7 +15,7 @@ Sleep States That Can Be Supported
 ==================================
 
 Depending on its configuration and the capabilities of the platform it runs on,
-the Linux kernel can support up to four system sleep states, includig
+the Linux kernel can support up to four system sleep states, including
 hibernation and up to three variants of system suspend.  The sleep states that
 can be supported by the kernel are listed below.
 
diff --git a/Documentation/admin-guide/ramoops.rst b/Documentation/admin-guide/ramoops.rst
index 4efd7ce77565..6dbcc5481000 100644
--- a/Documentation/admin-guide/ramoops.rst
+++ b/Documentation/admin-guide/ramoops.rst
@@ -61,7 +61,7 @@ Setting the ramoops parameters can be done in several different manners:
 	mem=128M ramoops.mem_address=0x8000000 ramoops.ecc=1
 
  B. Use Device Tree bindings, as described in
- ``Documentation/device-tree/bindings/reserved-memory/admin-guide/ramoops.rst``.
+ ``Documentation/devicetree/bindings/reserved-memory/ramoops.txt``.
  For example::
 
 	reserved-memory {
diff --git a/Documentation/arm/Marvell/README b/Documentation/arm/Marvell/README
index b5bb7f518840..56ada27c53be 100644
--- a/Documentation/arm/Marvell/README
+++ b/Documentation/arm/Marvell/README
@@ -302,19 +302,15 @@ Berlin family (Multimedia Solutions)
 	88DE3010, Armada 1000 (no Linux support)
 		Core:		Marvell PJ1 (ARMv5TE), Dual-core
 		Product Brief:	http://www.marvell.com.cn/digital-entertainment/assets/armada_1000_pb.pdf
-	88DE3005, Armada 1500-mini
 	88DE3005, Armada 1500 Mini
 		Design name:	BG2CD
 		Core:		ARM Cortex-A9, PL310 L2CC
-		Homepage:	http://www.marvell.com/multimedia-solutions/armada-1500-mini/
-        88DE3006, Armada 1500 Mini Plus
-                Design name:    BG2CDP
-                Core:           Dual Core ARM Cortex-A7
-                Homepage:       http://www.marvell.com/multimedia-solutions/armada-1500-mini-plus/
+	88DE3006, Armada 1500 Mini Plus
+		Design name:	BG2CDP
+		Core:		Dual Core ARM Cortex-A7
 	88DE3100, Armada 1500
 		Design name:	BG2
 		Core:		Marvell PJ4B-MP (ARMv7), Tauros3 L2CC
-		Product Brief:	http://www.marvell.com/digital-entertainment/armada-1500/assets/Marvell-ARMADA-1500-Product-Brief.pdf
 	88DE3114, Armada 1500 Pro
 		Design name:	BG2Q
 		Core:		Quad Core ARM Cortex-A9, PL310 L2CC
@@ -324,13 +320,16 @@ Berlin family (Multimedia Solutions)
 	88DE3218, ARMADA 1500 Ultra
 		Core:		ARM Cortex-A53
 
-  Homepage: http://www.marvell.com/multimedia-solutions/
+  Homepage: https://www.synaptics.com/products/multimedia-solutions
   Directory: arch/arm/mach-berlin
 
   Comments:
+
    * This line of SoCs is based on Marvell Sheeva or ARM Cortex CPUs
      with Synopsys DesignWare (IRQ, GPIO, Timers, ...) and PXA IP (SDHCI, USB, ETH, ...).
 
+   * The Berlin family was acquired by Synaptics from Marvell in 2017.
+
 CPU Cores
 ---------
 
diff --git a/Documentation/block/cmdline-partition.txt b/Documentation/block/cmdline-partition.txt
index 525b9f6d7fb4..760a3f7c3ed4 100644
--- a/Documentation/block/cmdline-partition.txt
+++ b/Documentation/block/cmdline-partition.txt
@@ -1,7 +1,9 @@
 Embedded device command line partition parsing
 =====================================================================
 
-Support for reading the block device partition table from the command line.
+The "blkdevparts" command line option adds support for reading the
+block device partition table from the kernel command line.
+
 It is typically used for fixed block (eMMC) embedded devices.
 It has no MBR, so saves storage space. Bootloader can be easily accessed
 by absolute address of data on the block device.
@@ -14,22 +16,27 @@ blkdevparts=<blkdev-def>[;<blkdev-def>]
     <partdef> := <size>[@<offset>](part-name)
 
 <blkdev-id>
-    block device disk name, embedded device used fixed block device,
-    it's disk name also fixed. such as: mmcblk0, mmcblk1, mmcblk0boot0.
+    block device disk name. Embedded device uses fixed block device.
+    Its disk name is also fixed, such as: mmcblk0, mmcblk1, mmcblk0boot0.
 
 <size>
     partition size, in bytes, such as: 512, 1m, 1G.
+    size may contain an optional suffix of (upper or lower case):
+      K, M, G, T, P, E.
+    "-" is used to denote all remaining space.
 
 <offset>
     partition start address, in bytes.
+    offset may contain an optional suffix of (upper or lower case):
+      K, M, G, T, P, E.
 
 (part-name)
-    partition name, kernel send uevent with "PARTNAME". application can create
-    a link to block device partition with the name "PARTNAME".
-    user space application can access partition by partition name.
+    partition name. Kernel sends uevent with "PARTNAME". Application can
+    create a link to block device partition with the name "PARTNAME".
+    User space application can access partition by partition name.
 
 Example:
-    eMMC disk name is "mmcblk0" and "mmcblk0boot0"
+    eMMC disk names are "mmcblk0" and "mmcblk0boot0".
 
   bootargs:
     'blkdevparts=mmcblk0:1G(data0),1G(data1),-;mmcblk0boot0:1m(boot),-(kernel)'
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
index 733927a7b501..07f147381f32 100644
--- a/Documentation/block/null_blk.txt
+++ b/Documentation/block/null_blk.txt
@@ -71,13 +71,16 @@ use_per_node_hctx=[0/1]: Default: 0
   1: The multi-queue block layer is instantiated with a hardware dispatch
      queue for each CPU node in the system.
 
-use_lightnvm=[0/1]: Default: 0
-  Register device with LightNVM. Requires blk-mq and CONFIG_NVM to be enabled.
-
 no_sched=[0/1]: Default: 0
   0: nullb* use default blk-mq io scheduler.
   1: nullb* doesn't use io scheduler.
 
+blocking=[0/1]: Default: 0
+  0: Register as a non-blocking blk-mq driver device.
+  1: Register as a blocking blk-mq driver device, null_blk will set
+     the BLK_MQ_F_BLOCKING flag, indicating that it sometimes/always
+     needs to block in its ->queue_rq() function.
+
 shared_tags=[0/1]: Default: 0
   0: Tag set is not shared.
   1: Tag set shared between devices for blk-mq. Only makes sense with
diff --git a/Documentation/bpf/bpf_devel_QA.txt b/Documentation/bpf/bpf_devel_QA.txt
index 1a0b704e1a38..da57601153a0 100644
--- a/Documentation/bpf/bpf_devel_QA.txt
+++ b/Documentation/bpf/bpf_devel_QA.txt
@@ -557,6 +557,14 @@ A: Although LLVM IR generation and optimization try to stay architecture
        pulls in some header files containing file scope host assembly codes.
      - You can add "-fno-jump-tables" to work around the switch table issue.
 
-   Otherwise, you can use bpf target.
+   Otherwise, you can use bpf target. Additionally, you _must_ use bpf target
+   when:
+
+     - Your program uses data structures with pointer or long / unsigned long
+       types that interface with BPF helpers or context data structures. Access
+       into these structures is verified by the BPF verifier and may result
+       in verification failures if the native architecture is not aligned with
+       the BPF architecture, e.g. 64-bit. An example of this is
+       BPF_PROG_TYPE_SK_MSG require '-target bpf'
 
 Happy BPF hacking!
diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst
index fce929144ccd..2e7165f86f55 100644
--- a/Documentation/core-api/atomic_ops.rst
+++ b/Documentation/core-api/atomic_ops.rst
@@ -111,7 +111,6 @@ If the compiler can prove that do_something() does not store to the
 variable a, then the compiler is within its rights transforming this to
 the following::
 
-	tmp = a;
 	if (a > 0)
 		for (;;)
 			do_something();
@@ -119,7 +118,7 @@ the following::
 If you don't want the compiler to do this (and you probably don't), then
 you should use something like the following::
 
-	while (READ_ONCE(a) < 0)
+	while (READ_ONCE(a) > 0)
 		do_something();
 
 Alternatively, you could place a barrier() call in the loop.
@@ -467,10 +466,12 @@ Like the above, except that these routines return a boolean which
 indicates whether the changed bit was set _BEFORE_ the atomic bit
 operation.
 
-WARNING! It is incredibly important that the value be a boolean,
-ie. "0" or "1".  Do not try to be fancy and save a few instructions by
-declaring the above to return "long" and just returning something like
-"old_val & mask" because that will not work.
+
+.. warning::
+        It is incredibly important that the value be a boolean, ie. "0" or "1".
+        Do not try to be fancy and save a few instructions by declaring the
+        above to return "long" and just returning something like "old_val &
+        mask" because that will not work.
 
 For one thing, this return value gets truncated to int in many code
 paths using these interfaces, so on 64-bit if the bit is set in the
diff --git a/Documentation/cachetlb.txt b/Documentation/core-api/cachetlb.rst
index 6eb9d3f090cd..6eb9d3f090cd 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/core-api/cachetlb.rst
diff --git a/Documentation/circular-buffers.txt b/Documentation/core-api/circular-buffers.rst
index 53e51caa3347..53e51caa3347 100644
--- a/Documentation/circular-buffers.txt
+++ b/Documentation/core-api/circular-buffers.rst
diff --git a/Documentation/core-api/gfp_mask-from-fs-io.rst b/Documentation/core-api/gfp_mask-from-fs-io.rst
new file mode 100644
index 000000000000..e0df8f416582
--- /dev/null
+++ b/Documentation/core-api/gfp_mask-from-fs-io.rst
@@ -0,0 +1,66 @@
+=================================
+GFP masks used from FS/IO context
+=================================
+
+:Date: May, 2018
+:Author: Michal Hocko <mhocko@kernel.org>
+
+Introduction
+============
+
+Code paths in the filesystem and IO stacks must be careful when
+allocating memory to prevent recursion deadlocks caused by direct
+memory reclaim calling back into the FS or IO paths and blocking on
+already held resources (e.g. locks - most commonly those used for the
+transaction context).
+
+The traditional way to avoid this deadlock problem is to clear __GFP_FS
+respectively __GFP_IO (note the latter implies clearing the first as well) in
+the gfp mask when calling an allocator. GFP_NOFS respectively GFP_NOIO can be
+used as shortcut. It turned out though that above approach has led to
+abuses when the restricted gfp mask is used "just in case" without a
+deeper consideration which leads to problems because an excessive use
+of GFP_NOFS/GFP_NOIO can lead to memory over-reclaim or other memory
+reclaim issues.
+
+New API
+========
+
+Since 4.12 we do have a generic scope API for both NOFS and NOIO context
+``memalloc_nofs_save``, ``memalloc_nofs_restore`` respectively ``memalloc_noio_save``,
+``memalloc_noio_restore`` which allow to mark a scope to be a critical
+section from a filesystem or I/O point of view. Any allocation from that
+scope will inherently drop __GFP_FS respectively __GFP_IO from the given
+mask so no memory allocation can recurse back in the FS/IO.
+
+.. kernel-doc:: include/linux/sched/mm.h
+   :functions: memalloc_nofs_save memalloc_nofs_restore
+.. kernel-doc:: include/linux/sched/mm.h
+   :functions: memalloc_noio_save memalloc_noio_restore
+
+FS/IO code then simply calls the appropriate save function before
+any critical section with respect to the reclaim is started - e.g.
+lock shared with the reclaim context or when a transaction context
+nesting would be possible via reclaim. The restore function should be
+called when the critical section ends. All that ideally along with an
+explanation what is the reclaim context for easier maintenance.
+
+Please note that the proper pairing of save/restore functions
+allows nesting so it is safe to call ``memalloc_noio_save`` or
+``memalloc_noio_restore`` respectively from an existing NOIO or NOFS
+scope.
+
+What about __vmalloc(GFP_NOFS)
+==============================
+
+vmalloc doesn't support GFP_NOFS semantic because there are hardcoded
+GFP_KERNEL allocations deep inside the allocator which are quite non-trivial
+to fix up. That means that calling ``vmalloc`` with GFP_NOFS/GFP_NOIO is
+almost always a bug. The good news is that the NOFS/NOIO semantic can be
+achieved by the scope API.
+
+In the ideal world, upper layers should already mark dangerous contexts
+and so no special care is required and vmalloc should be called without
+any problems. Sometimes if the context is not really clear or there are
+layering violations then the recommended way around that is to wrap ``vmalloc``
+by the scope API with a comment explaining the problem.
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index c670a8031786..f5a66b72f984 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -14,6 +14,7 @@ Core utilities
    kernel-api
    assoc_array
    atomic_ops
+   cachetlb
    refcount-vs-atomic
    cpu_hotplug
    idr
@@ -25,6 +26,8 @@ Core utilities
    genalloc
    errseq
    printk-formats
+   circular-buffers
+   gfp_mask-from-fs-io
 
 Interfaces for kernel debugging
 ===============================
diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index ff335f8aeb39..8e44aea366c2 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -39,17 +39,17 @@ String Manipulation
 .. kernel-doc:: lib/string.c
    :export:
 
+Basic Kernel Library Functions
+==============================
+
+The Linux kernel provides more basic utility functions.
+
 Bit Operations
 --------------
 
 .. kernel-doc:: arch/x86/include/asm/bitops.h
    :internal:
 
-Basic Kernel Library Functions
-==============================
-
-The Linux kernel provides more basic utility functions.
-
 Bitmap Operations
 -----------------
 
@@ -80,6 +80,31 @@ Command-line Parsing
 .. kernel-doc:: lib/cmdline.c
    :export:
 
+Sorting
+-------
+
+.. kernel-doc:: lib/sort.c
+   :export:
+
+.. kernel-doc:: lib/list_sort.c
+   :export:
+
+Text Searching
+--------------
+
+.. kernel-doc:: lib/textsearch.c
+   :doc: ts_intro
+
+.. kernel-doc:: lib/textsearch.c
+   :export:
+
+.. kernel-doc:: include/linux/textsearch.h
+   :functions: textsearch_find textsearch_next \
+               textsearch_get_pattern textsearch_get_pattern_len
+
+CRC and Math Functions in Linux
+===============================
+
 CRC Functions
 -------------
 
@@ -103,9 +128,6 @@ CRC Functions
 .. kernel-doc:: lib/crc-itu-t.c
    :export:
 
-Math Functions in Linux
-=======================
-
 Base 2 log and power Functions
 ------------------------------
 
@@ -127,15 +149,6 @@ Division Functions
 .. kernel-doc:: lib/gcd.c
    :export:
 
-Sorting
--------
-
-.. kernel-doc:: lib/sort.c
-   :export:
-
-.. kernel-doc:: lib/list_sort.c
-   :export:
-
 UUID/GUID
 ---------
 
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst
index eb30efdd2e78..25dc591cb110 100644
--- a/Documentation/core-api/printk-formats.rst
+++ b/Documentation/core-api/printk-formats.rst
@@ -419,11 +419,10 @@ struct clk
 
 	%pC	pll1
 	%pCn	pll1
-	%pCr	1560000000
 
 For printing struct clk structures. %pC and %pCn print the name
 (Common Clock Framework) or address (legacy clock framework) of the
-structure; %pCr prints the current clock rate.
+structure.
 
 Passed by reference.
 
diff --git a/Documentation/core-api/refcount-vs-atomic.rst b/Documentation/core-api/refcount-vs-atomic.rst
index 83351c258cdb..322851bada16 100644
--- a/Documentation/core-api/refcount-vs-atomic.rst
+++ b/Documentation/core-api/refcount-vs-atomic.rst
@@ -17,7 +17,7 @@ in order to help maintainers validate their code against the change in
 these memory ordering guarantees.
 
 The terms used through this document try to follow the formal LKMM defined in
-github.com/aparri/memory-model/blob/master/Documentation/explanation.txt
+tools/memory-model/Documentation/explanation.txt.
 
 memory-barriers.txt and atomic_t.txt provide more background to the
 memory ordering in general and for atomic operations specifically.
diff --git a/Documentation/crypto/index.rst b/Documentation/crypto/index.rst
index 94c4786f2573..c4ff5d791233 100644
--- a/Documentation/crypto/index.rst
+++ b/Documentation/crypto/index.rst
@@ -20,5 +20,6 @@ for cryptographic use cases, as well as programming examples.
    architecture
    devel-algos
    userspace-if
+   crypto_engine
    api
    api-samples
diff --git a/Documentation/dell_rbu.txt b/Documentation/dell_rbu.txt
index 0fdb6aa2704c..5d1ce7bcd04d 100644
--- a/Documentation/dell_rbu.txt
+++ b/Documentation/dell_rbu.txt
@@ -121,10 +121,7 @@ read back the image downloaded.
 
 .. note::
 
-   This driver requires a patch for firmware_class.c which has the modified
-   request_firmware_nowait function.
-
-   Also after updating the BIOS image a user mode application needs to execute
+   After updating the BIOS image a user mode application needs to execute
    code which sends the BIOS update request to the BIOS. So on the next reboot
    the BIOS knows about the new image downloaded and it updates itself.
    Also don't unload the rbu driver if the image has to be updated.
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index f7a18f274357..aabc8738b3d8 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -120,7 +120,7 @@ A typical out of bounds access report looks like this::
 
 The header of the report discribe what kind of bug happened and what kind of
 access caused it. It's followed by the description of the accessed slub object
-(see 'SLUB Debug output' section in Documentation/vm/slub.txt for details) and
+(see 'SLUB Debug output' section in Documentation/vm/slub.rst for details) and
 the description of the accessed memory page.
 
 In the last section the report shows memory state around the accessed address.
diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index e80850eefe13..3bf371a938d0 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -151,6 +151,11 @@ Contributing new tests (details)
    TEST_FILES, TEST_GEN_FILES mean it is the file which is used by
    test.
 
+ * First use the headers inside the kernel source and/or git repo, and then the
+   system headers.  Headers for the kernel release as opposed to headers
+   installed by the distro on the system should be the primary focus to be able
+   to find regressions.
+
 Test Harness
 ============
 
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 4bcd4b7f79f9..3d01948ea061 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -264,7 +264,10 @@ i) Constructor
 			   data device, but just remove the mapping.
 
       read_only: Don't allow any changes to be made to the pool
-		 metadata.
+		 metadata.  This mode is only available after the
+		 thin-pool has been created and first used in full
+		 read/write mode.  It cannot be specified on initial
+		 thin-pool creation.
 
       error_if_no_space: Error IOs, instead of queueing, if no space.
 
diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt
index f4006d3c9fdf..c760ecb81381 100644
--- a/Documentation/devicetree/bindings/ata/ahci-platform.txt
+++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt
@@ -30,7 +30,6 @@ compatible:
 Optional properties:
 - dma-coherent      : Present if dma operations are coherent
 - clocks            : a list of phandle + clock specifier pairs
-- resets            : a list of phandle + reset specifier pairs
 - target-supply     : regulator for SATA target power
 - phys              : reference to the SATA PHY node
 - phy-names         : must be "sata-phy"
diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
index 0047b1394c70..2c887536258c 100644
--- a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
+++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
@@ -14,7 +14,13 @@ Required properties:
 		"adi,adv7513"
 		"adi,adv7533"
 
-- reg: I2C slave address
+- reg: I2C slave addresses
+  The ADV7511 internal registers are split into four pages exposed through
+  different I2C addresses, creating four register maps. Each map has it own
+  I2C address and acts as a standard slave device on the I2C bus. The main
+  address is mandatory, others are optional and revert to defaults if not
+  specified.
+
 
 The ADV7511 supports a large number of input data formats that differ by their
 color depth, color format, clock mode, bit justification and random
@@ -70,6 +76,9 @@ Optional properties:
   rather than generate its own timings for HDMI output.
 - clocks: from common clock binding: reference to the CEC clock.
 - clock-names: from common clock binding: must be "cec".
+- reg-names : Names of maps with programmable addresses.
+	It can contain any map needing a non-default address.
+	Possible maps names are : "main", "edid", "cec", "packet"
 
 Required nodes:
 
@@ -88,7 +97,12 @@ Example
 
 	adv7511w: hdmi@39 {
 		compatible = "adi,adv7511w";
-		reg = <39>;
+		/*
+		 * The EDID page will be accessible on address 0x66 on the I2C
+		 * bus. All other maps continue to use their default addresses.
+		 */
+		reg = <0x39>, <0x66>;
+		reg-names = "main", "edid";
 		interrupt-parent = <&gpio3>;
 		interrupts = <29 IRQ_TYPE_EDGE_FALLING>;
 		clocks = <&cec_clock>;
diff --git a/Documentation/devicetree/bindings/display/bridge/cdns,dsi.txt b/Documentation/devicetree/bindings/display/bridge/cdns,dsi.txt
new file mode 100644
index 000000000000..f5725bb6c61c
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/bridge/cdns,dsi.txt
@@ -0,0 +1,133 @@
+Cadence DSI bridge
+==================
+
+The Cadence DSI bridge is a DPI to DSI bridge supporting up to 4 DSI lanes.
+
+Required properties:
+- compatible: should be set to "cdns,dsi".
+- reg: physical base address and length of the controller's registers.
+- interrupts: interrupt line connected to the DSI bridge.
+- clocks: DSI bridge clocks.
+- clock-names: must contain "dsi_p_clk" and "dsi_sys_clk".
+- phys: phandle link to the MIPI D-PHY controller.
+- phy-names: must contain "dphy".
+- #address-cells: must be set to 1.
+- #size-cells: must be set to 0.
+
+Optional properties:
+- resets: DSI reset lines.
+- reset-names: can contain "dsi_p_rst".
+
+Required subnodes:
+- ports: Ports as described in Documentation/devicetree/bindings/graph.txt.
+  2 ports are available:
+  * port 0: this port is only needed if some of your DSI devices are
+	    controlled through  an external bus like I2C or SPI. Can have at
+	    most 4 endpoints. The endpoint number is directly encoding the
+	    DSI virtual channel used by this device.
+  * port 1: represents the DPI input.
+  Other ports will be added later to support the new kind of inputs.
+
+- one subnode per DSI device connected on the DSI bus. Each DSI device should
+  contain a reg property encoding its virtual channel.
+
+Cadence DPHY
+============
+
+Cadence DPHY block.
+
+Required properties:
+- compatible: should be set to "cdns,dphy".
+- reg: physical base address and length of the DPHY registers.
+- clocks: DPHY reference clocks.
+- clock-names: must contain "psm" and "pll_ref".
+- #phy-cells: must be set to 0.
+
+
+Example:
+	dphy0: dphy@fd0e0000{
+		compatible = "cdns,dphy";
+		reg = <0x0 0xfd0e0000 0x0 0x1000>;
+		clocks = <&psm_clk>, <&pll_ref_clk>;
+		clock-names = "psm", "pll_ref";
+		#phy-cells = <0>;
+	};
+
+	dsi0: dsi@fd0c0000 {
+		compatible = "cdns,dsi";
+		reg = <0x0 0xfd0c0000 0x0 0x1000>;
+		clocks = <&pclk>, <&sysclk>;
+		clock-names = "dsi_p_clk", "dsi_sys_clk";
+		interrupts = <1>;
+		phys = <&dphy0>;
+		phy-names = "dphy";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@1 {
+				reg = <1>;
+				dsi0_dpi_input: endpoint {
+					remote-endpoint = <&xxx_dpi_output>;
+				};
+			};
+		};
+
+		panel: dsi-dev@0 {
+			compatible = "<vendor,panel>";
+			reg = <0>;
+		};
+	};
+
+or
+
+	dsi0: dsi@fd0c0000 {
+		compatible = "cdns,dsi";
+		reg = <0x0 0xfd0c0000 0x0 0x1000>;
+		clocks = <&pclk>, <&sysclk>;
+		clock-names = "dsi_p_clk", "dsi_sys_clk";
+		interrupts = <1>;
+		phys = <&dphy1>;
+		phy-names = "dphy";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				dsi0_output: endpoint@0 {
+					reg = <0>;
+					remote-endpoint = <&dsi_panel_input>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				dsi0_dpi_input: endpoint {
+					remote-endpoint = <&xxx_dpi_output>;
+				};
+			};
+		};
+	};
+
+	i2c@xxx {
+		panel: panel@59 {
+			compatible = "<vendor,panel>";
+			reg = <0x59>;
+
+			port {
+				dsi_panel_input: endpoint {
+					remote-endpoint = <&dsi0_output>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt b/Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt
index 3a72a103a18a..a41d280c3f9f 100644
--- a/Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt
+++ b/Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt
@@ -14,6 +14,7 @@ Required properties:
 - compatible : Shall contain one or more of
   - "renesas,r8a7795-hdmi" for R8A7795 (R-Car H3) compatible HDMI TX
   - "renesas,r8a7796-hdmi" for R8A7796 (R-Car M3-W) compatible HDMI TX
+  - "renesas,r8a77965-hdmi" for R8A77965 (R-Car M3-N) compatible HDMI TX
   - "renesas,rcar-gen3-hdmi" for the generic R-Car Gen3 compatible HDMI TX
 
     When compatible with generic versions, nodes must list the SoC-specific
diff --git a/Documentation/devicetree/bindings/display/bridge/tda998x.txt b/Documentation/devicetree/bindings/display/bridge/tda998x.txt
index 24cc2466185a..1a4eaca40d94 100644
--- a/Documentation/devicetree/bindings/display/bridge/tda998x.txt
+++ b/Documentation/devicetree/bindings/display/bridge/tda998x.txt
@@ -27,6 +27,9 @@ Optional properties:
 	in question is used. The implementation allows one or two DAIs. If two
 	DAIs are defined, they must be of different type.
 
+  - nxp,calib-gpios: calibration GPIO, which must correspond with the
+	gpio used for the TDA998x interrupt pin.
+
 [1] Documentation/sound/alsa/soc/DAI.txt
 [2] include/dt-bindings/display/tda998x.h
 
diff --git a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
new file mode 100644
index 000000000000..37f0c04d5a28
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
@@ -0,0 +1,60 @@
+Thine Electronics THC63LVD1024 LVDS decoder
+-------------------------------------------
+
+The THC63LVD1024 is a dual link LVDS receiver designed to convert LVDS streams
+to parallel data outputs. The chip supports single/dual input/output modes,
+handling up to two LVDS input streams and up to two digital CMOS/TTL outputs.
+
+Single or dual operation mode, output data mapping and DDR output modes are
+configured through input signals and the chip does not expose any control bus.
+
+Required properties:
+- compatible: Shall be "thine,thc63lvd1024"
+- vcc-supply: Power supply for TTL output, TTL CLOCKOUT signal, LVDS input,
+  PPL and digital circuitry
+
+Optional properties:
+- powerdown-gpios: Power down GPIO signal, pin name "/PDWN". Active low
+- oe-gpios: Output enable GPIO signal, pin name "OE". Active high
+
+The THC63LVD1024 video port connections are modeled according
+to OF graph bindings specified by Documentation/devicetree/bindings/graph.txt
+
+Required video port nodes:
+- port@0: First LVDS input port
+- port@2: First digital CMOS/TTL parallel output
+
+Optional video port nodes:
+- port@1: Second LVDS input port
+- port@3: Second digital CMOS/TTL parallel output
+
+Example:
+--------
+
+	thc63lvd1024: lvds-decoder {
+		compatible = "thine,thc63lvd1024";
+
+		vcc-supply = <&reg_lvds_vcc>;
+		powerdown-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lvds_dec_in_0: endpoint {
+					remote-endpoint = <&lvds_out>;
+				};
+			};
+
+			port@2{
+				reg = <2>;
+
+				lvds_dec_out_2: endpoint {
+					remote-endpoint = <&adv7511_in>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos5433-decon.txt b/Documentation/devicetree/bindings/display/exynos/exynos5433-decon.txt
index fc2588292a68..775193e1c641 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos5433-decon.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos5433-decon.txt
@@ -19,7 +19,8 @@ Required properties:
 	  clock-names property.
 - clock-names: list of clock names sorted in the same order as the clocks
 	       property. Must contain "pclk", "aclk_decon", "aclk_smmu_decon0x",
-	       "aclk_xiu_decon0x", "pclk_smmu_decon0x", clk_decon_vclk",
+	       "aclk_xiu_decon0x", "pclk_smmu_decon0x", "aclk_smmu_decon1x",
+	       "aclk_xiu_decon1x", "pclk_smmu_decon1x", clk_decon_vclk",
 	       "sclk_decon_eclk"
 - ports: contains a port which is connected to mic node. address-cells and
 	 size-cells must 1 and 0, respectively.
@@ -34,10 +35,14 @@ decon: decon@13800000 {
 	clocks = <&cmu_disp CLK_ACLK_DECON>, <&cmu_disp CLK_ACLK_SMMU_DECON0X>,
 		<&cmu_disp CLK_ACLK_XIU_DECON0X>,
 		<&cmu_disp CLK_PCLK_SMMU_DECON0X>,
+		<&cmu_disp CLK_ACLK_SMMU_DECON1X>,
+		<&cmu_disp CLK_ACLK_XIU_DECON1X>,
+		<&cmu_disp CLK_PCLK_SMMU_DECON1X>,
 		<&cmu_disp CLK_SCLK_DECON_VCLK>,
 		<&cmu_disp CLK_SCLK_DECON_ECLK>;
 	clock-names = "aclk_decon", "aclk_smmu_decon0x", "aclk_xiu_decon0x",
-		"pclk_smmu_decon0x", "sclk_decon_vclk", "sclk_decon_eclk";
+		"pclk_smmu_decon0x", "aclk_smmu_decon1x", "aclk_xiu_decon1x",
+		"pclk_smmu_decon1x", "sclk_decon_vclk", "sclk_decon_eclk";
 	interrupt-names = "vsync", "lcd_sys";
 	interrupts = <0 202 0>, <0 203 0>;
 
diff --git a/Documentation/devicetree/bindings/display/panel/panel-common.txt b/Documentation/devicetree/bindings/display/panel/panel-common.txt
index 557fa765adcb..5d2519af4bb5 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-common.txt
+++ b/Documentation/devicetree/bindings/display/panel/panel-common.txt
@@ -38,7 +38,7 @@ Display Timings
   require specific display timings. The panel-timing subnode expresses those
   timings as specified in the timing subnode section of the display timing
   bindings defined in
-  Documentation/devicetree/bindings/display/display-timing.txt.
+  Documentation/devicetree/bindings/display/panel/display-timing.txt.
 
 
 Connectivity
diff --git a/Documentation/devicetree/bindings/display/renesas,du.txt b/Documentation/devicetree/bindings/display/renesas,du.txt
index c9cd17f99702..7c6854bd0a04 100644
--- a/Documentation/devicetree/bindings/display/renesas,du.txt
+++ b/Documentation/devicetree/bindings/display/renesas,du.txt
@@ -13,6 +13,7 @@ Required Properties:
     - "renesas,du-r8a7794" for R8A7794 (R-Car E2) compatible DU
     - "renesas,du-r8a7795" for R8A7795 (R-Car H3) compatible DU
     - "renesas,du-r8a7796" for R8A7796 (R-Car M3-W) compatible DU
+    - "renesas,du-r8a77965" for R8A77965 (R-Car M3-N) compatible DU
     - "renesas,du-r8a77970" for R8A77970 (R-Car V3M) compatible DU
     - "renesas,du-r8a77995" for R8A77995 (R-Car D3) compatible DU
 
@@ -47,20 +48,21 @@ bindings specified in Documentation/devicetree/bindings/graph.txt.
 The following table lists for each supported model the port number
 corresponding to each DU output.
 
-                      Port0          Port1          Port2          Port3
+                        Port0          Port1          Port2          Port3
 -----------------------------------------------------------------------------
- R8A7743 (RZ/G1M)     DPAD 0         LVDS 0         -              -
- R8A7745 (RZ/G1E)     DPAD 0         DPAD 1         -              -
- R8A7779 (R-Car H1)   DPAD 0         DPAD 1         -              -
- R8A7790 (R-Car H2)   DPAD 0         LVDS 0         LVDS 1         -
- R8A7791 (R-Car M2-W) DPAD 0         LVDS 0         -              -
- R8A7792 (R-Car V2H)  DPAD 0         DPAD 1         -              -
- R8A7793 (R-Car M2-N) DPAD 0         LVDS 0         -              -
- R8A7794 (R-Car E2)   DPAD 0         DPAD 1         -              -
- R8A7795 (R-Car H3)   DPAD 0         HDMI 0         HDMI 1         LVDS 0
- R8A7796 (R-Car M3-W) DPAD 0         HDMI 0         LVDS 0         -
- R8A77970 (R-Car V3M) DPAD 0         LVDS 0         -              -
- R8A77995 (R-Car D3)  DPAD 0         LVDS 0         LVDS 1         -
+ R8A7743 (RZ/G1M)       DPAD 0         LVDS 0         -              -
+ R8A7745 (RZ/G1E)       DPAD 0         DPAD 1         -              -
+ R8A7779 (R-Car H1)     DPAD 0         DPAD 1         -              -
+ R8A7790 (R-Car H2)     DPAD 0         LVDS 0         LVDS 1         -
+ R8A7791 (R-Car M2-W)   DPAD 0         LVDS 0         -              -
+ R8A7792 (R-Car V2H)    DPAD 0         DPAD 1         -              -
+ R8A7793 (R-Car M2-N)   DPAD 0         LVDS 0         -              -
+ R8A7794 (R-Car E2)     DPAD 0         DPAD 1         -              -
+ R8A7795 (R-Car H3)     DPAD 0         HDMI 0         HDMI 1         LVDS 0
+ R8A7796 (R-Car M3-W)   DPAD 0         HDMI 0         LVDS 0         -
+ R8A77965 (R-Car M3-N)  DPAD 0         HDMI 0         LVDS 0         -
+ R8A77970 (R-Car V3M)   DPAD 0         LVDS 0         -              -
+ R8A77995 (R-Car D3)    DPAD 0         LVDS 0         LVDS 1         -
 
 
 Example: R8A7795 (R-Car H3) ES2.0 DU
diff --git a/Documentation/devicetree/bindings/display/sunxi/sun6i-dsi.txt b/Documentation/devicetree/bindings/display/sunxi/sun6i-dsi.txt
new file mode 100644
index 000000000000..6a6cf5de08b0
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/sunxi/sun6i-dsi.txt
@@ -0,0 +1,93 @@
+Allwinner A31 DSI Encoder
+=========================
+
+The DSI pipeline consists of two separate blocks: the DSI controller
+itself, and its associated D-PHY.
+
+DSI Encoder
+-----------
+
+The DSI Encoder generates the DSI signal from the TCON's.
+
+Required properties:
+  - compatible: value must be one of:
+    * allwinner,sun6i-a31-mipi-dsi
+  - reg: base address and size of memory-mapped region
+  - interrupts: interrupt associated to this IP
+  - clocks: phandles to the clocks feeding the DSI encoder
+    * bus: the DSI interface clock
+    * mod: the DSI module clock
+  - clock-names: the clock names mentioned above
+  - phys: phandle to the D-PHY
+  - phy-names: must be "dphy"
+  - resets: phandle to the reset controller driving the encoder
+
+  - ports: A ports node with endpoint definitions as defined in
+    Documentation/devicetree/bindings/media/video-interfaces.txt. The
+    first port should be the input endpoint, usually coming from the
+    associated TCON.
+
+Any MIPI-DSI device attached to this should be described according to
+the bindings defined in ../mipi-dsi-bus.txt
+
+D-PHY
+-----
+
+Required properties:
+  - compatible: value must be one of:
+    * allwinner,sun6i-a31-mipi-dphy
+  - reg: base address and size of memory-mapped region
+  - clocks: phandles to the clocks feeding the DSI encoder
+    * bus: the DSI interface clock
+    * mod: the DSI module clock
+  - clock-names: the clock names mentioned above
+  - resets: phandle to the reset controller driving the encoder
+
+Example:
+
+dsi0: dsi@1ca0000 {
+	compatible = "allwinner,sun6i-a31-mipi-dsi";
+	reg = <0x01ca0000 0x1000>;
+	interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&ccu CLK_BUS_MIPI_DSI>,
+		 <&ccu CLK_DSI_SCLK>;
+	clock-names = "bus", "mod";
+	resets = <&ccu RST_BUS_MIPI_DSI>;
+	phys = <&dphy0>;
+	phy-names = "dphy";
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	panel@0 {
+		compatible = "bananapi,lhr050h41", "ilitek,ili9881c";
+		reg = <0>;
+		power-gpios = <&pio 1 7 GPIO_ACTIVE_HIGH>; /* PB07 */
+		reset-gpios = <&r_pio 0 5 GPIO_ACTIVE_LOW>; /* PL05 */
+		backlight = <&pwm_bl>;
+	};
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			dsi0_in_tcon0: endpoint {
+				remote-endpoint = <&tcon0_out_dsi0>;
+			};
+		};
+	};
+};
+
+dphy0: d-phy@1ca1000 {
+	compatible = "allwinner,sun6i-a31-mipi-dphy";
+	reg = <0x01ca1000 0x1000>;
+	clocks = <&ccu CLK_BUS_MIPI_DSI>,
+		 <&ccu CLK_DSI_DPHY>;
+	clock-names = "bus", "mod";
+	resets = <&ccu RST_BUS_MIPI_DSI>;
+	#phy-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
index aadfb236d53a..61315eaa7660 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
@@ -26,6 +26,7 @@ Required Properties:
 		- "renesas,dmac-r8a7794" (R-Car E2)
 		- "renesas,dmac-r8a7795" (R-Car H3)
 		- "renesas,dmac-r8a7796" (R-Car M3-W)
+		- "renesas,dmac-r8a77965" (R-Car M3-N)
 		- "renesas,dmac-r8a77970" (R-Car V3M)
 		- "renesas,dmac-r8a77980" (R-Car V3H)
 
diff --git a/Documentation/devicetree/bindings/arm/altera/socfpga-eccmgr.txt b/Documentation/devicetree/bindings/edac/socfpga-eccmgr.txt
index 4a1714f96bab..5626560a6cfd 100644
--- a/Documentation/devicetree/bindings/arm/altera/socfpga-eccmgr.txt
+++ b/Documentation/devicetree/bindings/edac/socfpga-eccmgr.txt
@@ -231,3 +231,38 @@ Example:
 				     <48 IRQ_TYPE_LEVEL_HIGH>;
 		};
 	};
+
+Stratix10 SoCFPGA ECC Manager
+The Stratix10 SoC ECC Manager handles the IRQs for each peripheral
+in a shared register similar to the Arria10. However, ECC requires
+access to registers that can only be read from Secure Monitor with
+SMC calls. Therefore the device tree is slightly different.
+
+Required Properties:
+- compatible : Should be "altr,socfpga-s10-ecc-manager"
+- interrupts : Should be single bit error interrupt, then double bit error
+	interrupt.
+- interrupt-controller : boolean indicator that ECC Manager is an interrupt controller
+- #interrupt-cells : must be set to 2.
+
+Subcomponents:
+
+SDRAM ECC
+Required Properties:
+- compatible : Should be "altr,sdram-edac-s10"
+- interrupts : Should be single bit error interrupt, then double bit error
+	interrupt, in this order.
+
+Example:
+
+	eccmgr {
+		compatible = "altr,socfpga-s10-ecc-manager";
+		interrupts = <0 15 4>, <0 95 4>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+
+		sdramedac {
+			compatible = "altr,sdram-edac-s10";
+			interrupts = <16 4>, <48 4>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/fpga/lattice-machxo2-spi.txt b/Documentation/devicetree/bindings/fpga/lattice-machxo2-spi.txt
new file mode 100644
index 000000000000..a8c362eb160c
--- /dev/null
+++ b/Documentation/devicetree/bindings/fpga/lattice-machxo2-spi.txt
@@ -0,0 +1,29 @@
+Lattice MachXO2 Slave SPI FPGA Manager
+
+Lattice MachXO2 FPGAs support a method of loading the bitstream over
+'slave SPI' interface.
+
+See 'MachXO2ProgrammingandConfigurationUsageGuide.pdf' on www.latticesemi.com
+
+Required properties:
+- compatible: should contain "lattice,machxo2-slave-spi"
+- reg: spi chip select of the FPGA
+
+Example for full FPGA configuration:
+
+	fpga-region0 {
+		compatible = "fpga-region";
+		fpga-mgr = <&fpga_mgr_spi>;
+		#address-cells = <0x1>;
+		#size-cells = <0x1>;
+	};
+
+	spi1: spi@2000 {
+        ...
+
+		fpga_mgr_spi: fpga-mgr@0 {
+			compatible = "lattice,machxo2-slave-spi";
+			spi-max-frequency = <8000000>;
+			reg = <0>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/gpu/brcm,bcm-v3d.txt b/Documentation/devicetree/bindings/gpu/brcm,bcm-v3d.txt
new file mode 100644
index 000000000000..c907aa8dd755
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpu/brcm,bcm-v3d.txt
@@ -0,0 +1,28 @@
+Broadcom V3D GPU
+
+Only the Broadcom V3D 3.x and newer GPUs are covered by this binding.
+For V3D 2.x, see brcm,bcm-vc4.txt.
+
+Required properties:
+- compatible:	Should be "brcm,7268-v3d" or "brcm,7278-v3d"
+- reg:		Physical base addresses and lengths of the register areas
+- reg-names:	Names for the register areas.  The "hub", "bridge", and "core0"
+		  register areas are always required.  The "gca" register area
+		  is required if the GCA cache controller is present.
+- interrupts:	The interrupt numbers.  The first interrupt is for the hub,
+		  while the following interrupts are for the cores.
+		  See bindings/interrupt-controller/interrupts.txt
+
+Optional properties:
+- clocks:	The core clock the unit runs on
+
+v3d {
+	compatible = "brcm,7268-v3d";
+	reg = <0xf1204000 0x100>,
+	      <0xf1200000 0x4000>,
+	      <0xf1208000 0x4000>,
+	      <0xf1204100 0x100>;
+	reg-names = "bridge", "hub", "core0", "gca";
+	interrupts = <0 78 4>,
+		     <0 77 4>;
+};
diff --git a/Documentation/devicetree/bindings/gpu/samsung-scaler.txt b/Documentation/devicetree/bindings/gpu/samsung-scaler.txt
new file mode 100644
index 000000000000..9c3d98105dfd
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpu/samsung-scaler.txt
@@ -0,0 +1,27 @@
+* Samsung Exynos Image Scaler
+
+Required properties:
+  - compatible : value should be one of the following:
+	(a) "samsung,exynos5420-scaler" for Scaler IP in Exynos5420
+	(b) "samsung,exynos5433-scaler" for Scaler IP in Exynos5433
+
+  - reg : Physical base address of the IP registers and length of memory
+	  mapped region.
+
+  - interrupts : Interrupt specifier for scaler interrupt, according to format
+		 specific to interrupt parent.
+
+  - clocks : Clock specifier for scaler clock, according to generic clock
+	     bindings. (See Documentation/devicetree/bindings/clock/exynos*.txt)
+
+  - clock-names : Names of clocks. For exynos scaler, it should be "mscl"
+		  on 5420 and "pclk", "aclk" and "aclk_xiu" on 5433.
+
+Example:
+	scaler@12800000 {
+		compatible = "samsung,exynos5420-scaler";
+		reg = <0x12800000 0x1294>;
+		interrupts = <0 220 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&clock CLK_MSCL0>;
+		clock-names = "mscl";
+	};
diff --git a/Documentation/devicetree/bindings/hwmon/gpio-fan.txt b/Documentation/devicetree/bindings/hwmon/gpio-fan.txt
index 439a7430fc68..2becdcfdc840 100644
--- a/Documentation/devicetree/bindings/hwmon/gpio-fan.txt
+++ b/Documentation/devicetree/bindings/hwmon/gpio-fan.txt
@@ -11,7 +11,7 @@ Optional properties:
   must have the RPM values in ascending order.
 - alarm-gpios: This pin going active indicates something is wrong with
   the fan, and a udev event will be fired.
-- cooling-cells: If used as a cooling device, must be <2>
+- #cooling-cells: If used as a cooling device, must be <2>
   Also see: Documentation/devicetree/bindings/thermal/thermal.txt
   min and max states are derived from the speed-map of the fan.
 
diff --git a/Documentation/devicetree/bindings/hwmon/ltc2990.txt b/Documentation/devicetree/bindings/hwmon/ltc2990.txt
new file mode 100644
index 000000000000..f92f54029e84
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/ltc2990.txt
@@ -0,0 +1,36 @@
+ltc2990: Linear Technology LTC2990 power monitor
+
+Required properties:
+- compatible: Must be "lltc,ltc2990"
+- reg: I2C slave address
+- lltc,meas-mode:
+	An array of two integers for configuring the chip measurement mode.
+
+	The first integer defines the bits 2..0 in the control register. In all
+	cases the internal temperature and supply voltage are measured. In
+	addition the following input measurements are enabled per mode:
+
+		0: V1, V2, TR2
+		1: V1-V2, TR2
+		2: V1-V2, V3, V4
+		3: TR1, V3, V4
+		4: TR1, V3-V4
+		5: TR1, TR2
+		6: V1-V2, V3-V4
+		7: V1, V2, V3, V4
+
+	The second integer defines the bits 4..3 in the control register. This
+	allows a subset of the measurements to be enabled:
+
+		0: Internal temperature and supply voltage only
+		1: TR1, V1 or V1-V2 only per mode
+		2: TR2, V3 or V3-V4 only per mode
+		3: All measurements per mode
+
+Example:
+
+ltc2990@4c {
+	compatible = "lltc,ltc2990";
+	reg = <0x4c>;
+	lltc,meas-mode = <7 3>;	/* V1, V2, V3, V4 */
+};
diff --git a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
index 23e3abc3fdef..c88919480d37 100644
--- a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
+++ b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
@@ -4,6 +4,13 @@ Required properties:
 - compatible:
     atmel,maxtouch
 
+    The following compatibles have been used in various products but are
+    deprecated:
+	atmel,qt602240_ts
+	atmel,atmel_mxt_ts
+	atmel,atmel_mxt_tp
+	atmel,mXT224
+
 - reg: The I2C address of the device
 
 - interrupts: The sink for the touchpad's IRQ output
diff --git a/Documentation/devicetree/bindings/input/elan_i2c.txt b/Documentation/devicetree/bindings/input/elan_i2c.txt
index ee3242c4ba67..d80a83583238 100644
--- a/Documentation/devicetree/bindings/input/elan_i2c.txt
+++ b/Documentation/devicetree/bindings/input/elan_i2c.txt
@@ -14,6 +14,7 @@ Optional properties:
 - pinctrl-0: a phandle pointing to the pin settings for the device (see
   pinctrl binding [1]).
 - vcc-supply: a phandle for the regulator supplying 3.3V power.
+- elan,trackpoint: touchpad can support a trackpoint (boolean)
 
 [0]: Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 [1]: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
diff --git a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
index a83f9a5734ca..89674ad8a097 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
@@ -9,11 +9,12 @@ number of interrupt exposed depends on the SoC.
 
 Required properties:
 
-- compatible : must have "amlogic,meson8-gpio-intc� and either
-   “amlogic,meson8-gpio-intc� for meson8 SoCs (S802) or
-   “amlogic,meson8b-gpio-intc� for meson8b SoCs (S805) or
-   “amlogic,meson-gxbb-gpio-intc� for GXBB SoCs (S905) or
-   “amlogic,meson-gxl-gpio-intc� for GXL SoCs (S905X, S912)
+- compatible : must have "amlogic,meson8-gpio-intc" and either
+    "amlogic,meson8-gpio-intc" for meson8 SoCs (S802) or
+    "amlogic,meson8b-gpio-intc" for meson8b SoCs (S805) or
+    "amlogic,meson-gxbb-gpio-intc" for GXBB SoCs (S905) or
+    "amlogic,meson-gxl-gpio-intc" for GXL SoCs (S905X, S912)
+    "amlogic,meson-axg-gpio-intc" for AXG SoCs (A113D, A113X)
 - interrupt-parent : a phandle to the GIC the interrupts are routed to.
    Usually this is provided at the root level of the device tree as it is
    common to most of the SoC.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
index 0a57f2f4167d..3ea78c4ef887 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
@@ -57,6 +57,20 @@ Optional
   occupied by the redistributors. Required if more than one such
   region is present.
 
+- msi-controller: Boolean property. Identifies the node as an MSI
+  controller. Only present if the Message Based Interrupt
+  functionnality is being exposed by the HW, and the mbi-ranges
+  property present.
+
+- mbi-ranges: A list of pairs <intid span>, where "intid" is the first
+  SPI of a range that can be used an MBI, and "span" the size of that
+  range. Multiple ranges can be provided. Requires "msi-controller" to
+  be set.
+
+- mbi-alias: Address property. Base address of an alias of the GICD
+  region containing only the {SET,CLR}SPI registers to be used if
+  isolation is required, and if supported by the HW.
+
 Sub-nodes:
 
 PPI affinity can be expressed as a single "ppi-partitions" node,
@@ -99,6 +113,9 @@ Examples:
 		      <0x0 0x2c020000 0 0x2000>;	// GICV
 		interrupts = <1 9 4>;
 
+		msi-controller;
+		mbi-ranges = <256 128>;
+
 		gic-its@2c200000 {
 			compatible = "arm,gic-v3-its";
 			msi-controller;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
index edf03f09244b..136bd612bd83 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
@@ -5,11 +5,14 @@ Required properties:
 - compatible: Should be:
     "st,stm32-exti"
     "st,stm32h7-exti"
+    "st,stm32mp1-exti"
 - reg: Specifies base physical address and size of the registers
 - interrupt-controller: Indentifies the node as an interrupt controller
 - #interrupt-cells: Specifies the number of cells to encode an interrupt
   specifier, shall be 2
 - interrupts: interrupts references to primary interrupt controller
+  (only needed for exti controller with multiple exti under
+  same parent interrupt: st,stm32-exti and st,stm32h7-exti")
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/ipmi/npcm7xx-kcs-bmc.txt b/Documentation/devicetree/bindings/ipmi/npcm7xx-kcs-bmc.txt
new file mode 100644
index 000000000000..3538a214fff1
--- /dev/null
+++ b/Documentation/devicetree/bindings/ipmi/npcm7xx-kcs-bmc.txt
@@ -0,0 +1,39 @@
+* Nuvoton NPCM7xx KCS (Keyboard Controller Style) IPMI interface
+
+The Nuvoton SOCs (NPCM7xx) are commonly used as BMCs
+(Baseboard Management Controllers) and the KCS interface can be
+used to perform in-band IPMI communication with their host.
+
+Required properties:
+- compatible : should be one of
+    "nuvoton,npcm750-kcs-bmc"
+- interrupts : interrupt generated by the controller
+- kcs_chan : The KCS channel number in the controller
+
+Example:
+
+    lpc_kcs: lpc_kcs@f0007000 {
+        compatible = "nuvoton,npcm750-lpc-kcs", "simple-mfd", "syscon";
+        reg = <0xf0007000 0x40>;
+        reg-io-width = <1>;
+
+        #address-cells = <1>;
+        #size-cells = <1>;
+        ranges = <0x0 0xf0007000 0x40>;
+
+        kcs1: kcs1@0 {
+            compatible = "nuvoton,npcm750-kcs-bmc";
+            reg = <0x0 0x40>;
+            interrupts = <0 9 4>;
+            kcs_chan = <1>;
+            status = "disabled";
+        };
+
+        kcs2: kcs2@0 {
+            compatible = "nuvoton,npcm750-kcs-bmc";
+            reg = <0x0 0x40>;
+            interrupts = <0 9 4>;
+            kcs_chan = <2>;
+            status = "disabled";
+        };
+    };
\ No newline at end of file
diff --git a/Documentation/devicetree/bindings/leds/leds-cr0014114.txt b/Documentation/devicetree/bindings/leds/leds-cr0014114.txt
new file mode 100644
index 000000000000..4255b19ad25c
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-cr0014114.txt
@@ -0,0 +1,54 @@
+Crane Merchandising System - cr0014114 LED driver
+-------------------------------------------------
+
+This LED Board is widely used in vending machines produced
+by Crane Merchandising Systems.
+
+Required properties:
+- compatible: "crane,cr0014114"
+
+Property rules described in Documentation/devicetree/bindings/spi/spi-bus.txt
+apply. In particular, "reg" and "spi-max-frequency" properties must be given.
+
+LED sub-node properties:
+- label :
+	see Documentation/devicetree/bindings/leds/common.txt
+- linux,default-trigger : (optional)
+	see Documentation/devicetree/bindings/leds/common.txt
+
+Example
+-------
+
+led-controller@0 {
+	compatible = "crane,cr0014114";
+	reg = <0>;
+	spi-max-frequency = <50000>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	led@0 {
+		reg = <0>;
+		label = "red:coin";
+	};
+	led@1 {
+		reg = <1>;
+		label = "green:coin";
+	};
+	led@2 {
+		reg = <2>;
+		label = "blue:coin";
+	};
+	led@3 {
+		reg = <3>;
+		label = "red:bill";
+	};
+	led@4 {
+		reg = <4>;
+		label = "green:bill";
+	};
+	led@5 {
+		reg = <5>;
+		label = "blue:bill";
+	};
+	...
+};
diff --git a/Documentation/devicetree/bindings/leds/leds-lm3601x.txt b/Documentation/devicetree/bindings/leds/leds-lm3601x.txt
new file mode 100644
index 000000000000..a88b2c41e75b
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-lm3601x.txt
@@ -0,0 +1,45 @@
+* Texas Instruments - lm3601x Single-LED Flash Driver
+
+The LM3601X are ultra-small LED flash drivers that
+provide a high level of adjustability.
+
+Required properties:
+	- compatible : Can be one of the following
+		"ti,lm36010"
+		"ti,lm36011"
+	- reg : I2C slave address
+	- #address-cells : 1
+	- #size-cells : 0
+
+Required child properties:
+	- reg : 0 - Indicates a IR mode
+		1 - Indicates a Torch (white LED) mode
+
+Required properties for flash LED child nodes:
+	See Documentation/devicetree/bindings/leds/common.txt
+	- flash-max-microamp : Range from 11mA - 1.5A
+	- flash-max-timeout-us : Range from 40ms - 1600ms
+	- led-max-microamp : Range from 2.4mA - 376mA
+
+Optional child properties:
+	- label : see Documentation/devicetree/bindings/leds/common.txt
+
+Example:
+led-controller@64 {
+	compatible = "ti,lm36010";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	reg = <0x64>;
+
+	led@0 {
+		reg = <1>;
+		label = "white:torch";
+		led-max-microamp = <376000>;
+		flash-max-microamp = <1500000>;
+		flash-max-timeout-us = <1600000>;
+	};
+}
+
+For more product information please see the links below:
+http://www.ti.com/product/LM36010
+http://www.ti.com/product/LM36011
diff --git a/Documentation/devicetree/bindings/leds/leds-sc27xx-bltc.txt b/Documentation/devicetree/bindings/leds/leds-sc27xx-bltc.txt
new file mode 100644
index 000000000000..dddf84f9c7ea
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-sc27xx-bltc.txt
@@ -0,0 +1,41 @@
+LEDs connected to Spreadtrum SC27XX PMIC breathing light controller
+
+The SC27xx breathing light controller supports to 3 outputs:
+red LED, green LED and blue LED. Each LED can work at normal
+PWM mode or breath light mode.
+
+Required properties:
+- compatible: Should be "sprd,sc2731-bltc".
+- #address-cells: Must be 1.
+- #size-cells: Must be 0.
+- reg: Specify the controller address.
+
+Required child properties:
+- reg: Port this LED is connected to.
+
+Optional child properties:
+- label: See Documentation/devicetree/bindings/leds/common.txt.
+
+Examples:
+
+led-controller@200 {
+	compatible = "sprd,sc2731-bltc";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	reg = <0x200>;
+
+	led@0 {
+		label = "red";
+		reg = <0x0>;
+	};
+
+	led@1 {
+		label = "green";
+		reg = <0x1>;
+	};
+
+	led@2 {
+		label = "blue";
+		reg = <0x2>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/mmc/amlogic,meson-gx.txt b/Documentation/devicetree/bindings/mmc/amlogic,meson-gx.txt
index 50bf611a4d2c..13e70409e8ac 100644
--- a/Documentation/devicetree/bindings/mmc/amlogic,meson-gx.txt
+++ b/Documentation/devicetree/bindings/mmc/amlogic,meson-gx.txt
@@ -12,6 +12,7 @@ Required properties:
   - "amlogic,meson-gxbb-mmc"
   - "amlogic,meson-gxl-mmc"
   - "amlogic,meson-gxm-mmc"
+  - "amlogic,meson-axg-mmc"
 - clocks     : A list of phandle + clock-specifier pairs for the clocks listed in clock-names.
 - clock-names: Should contain the following:
 	"core" - Main peripheral bus clock
@@ -19,6 +20,7 @@ Required properties:
 	"clkin1" - Other parent clock of internal mux
   The driver has an internal mux clock which switches between clkin0 and clkin1 depending on the
   clock rate requested by the MMC core.
+- resets     : phandle of the internal reset line
 
 Example:
 
@@ -29,4 +31,5 @@ Example:
 		clocks = <&clkc CLKID_SD_EMMC_A>, <&xtal>, <&clkc CLKID_FCLK_DIV2>;
 		clock-names = "core", "clkin0", "clkin1";
 		pinctrl-0 = <&emmc_pins>;
+		resets = <&reset RESET_SD_EMMC_A>;
 	};
diff --git a/Documentation/devicetree/bindings/mmc/bluefield-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/bluefield-dw-mshc.txt
new file mode 100644
index 000000000000..b0f0999ea1a9
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/bluefield-dw-mshc.txt
@@ -0,0 +1,29 @@
+* Mellanox Bluefield SoC specific extensions to the Synopsys Designware
+  Mobile Storage Host Controller
+
+Read synopsys-dw-mshc.txt for more details
+
+The Synopsys designware mobile storage host controller is used to interface
+a SoC with storage medium such as eMMC or SD/MMC cards. This file documents
+differences between the core Synopsys dw mshc controller properties described
+by synopsys-dw-mshc.txt and the properties used by the Mellanox Bluefield SoC
+specific extensions to the Synopsys Designware Mobile Storage Host Controller.
+
+Required Properties:
+
+* compatible: should be one of the following.
+  - "mellanox,bluefield-dw-mshc": for controllers with Mellanox Bluefield SoC
+    specific extensions.
+
+Example:
+
+	/* Mellanox Bluefield SoC MMC */
+	mmc@6008000 {
+		compatible = "mellanox,bluefield-dw-mshc";
+		reg = <0x6008000 0x400>;
+		interrupts = <32>;
+		fifo-depth = <0x100>;
+		clock-frequency = <24000000>;
+		bus-width = <8>;
+		cap-mmc-highspeed;
+	};
diff --git a/Documentation/devicetree/bindings/mmc/jz4740.txt b/Documentation/devicetree/bindings/mmc/jz4740.txt
new file mode 100644
index 000000000000..7cd8c432d7c8
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/jz4740.txt
@@ -0,0 +1,38 @@
+* Ingenic JZ47xx MMC controllers
+
+This file documents the device tree properties used for the MMC controller in
+Ingenic JZ4740/JZ4780 SoCs. These are in addition to the core MMC properties
+described in mmc.txt.
+
+Required properties:
+- compatible: Should be one of the following:
+  - "ingenic,jz4740-mmc" for the JZ4740
+  - "ingenic,jz4780-mmc" for the JZ4780
+- reg: Should contain the MMC controller registers location and length.
+- interrupts: Should contain the interrupt specifier of the MMC controller.
+- clocks: Clock for the MMC controller.
+
+Optional properties:
+- dmas: List of DMA specifiers with the controller specific format
+        as described in the generic DMA client binding. A tx and rx
+        specifier is required.
+- dma-names: RX and TX  DMA request names.
+        Should be "rx" and "tx", in that order.
+
+For additional details on DMA client bindings see ../dma/dma.txt.
+
+Example:
+
+mmc0: mmc@13450000 {
+	compatible = "ingenic,jz4780-mmc";
+	reg = <0x13450000 0x1000>;
+
+	interrupt-parent = <&intc>;
+	interrupts = <37>;
+
+	clocks = <&cgu JZ4780_CLK_MSC0>;
+	clock-names = "mmc";
+
+	dmas = <&dma JZ4780_DMA_MSC0_RX 0xffffffff>, <&dma JZ4780_DMA_MSC0_TX 0xffffffff>;
+	dma-names = "rx", "tx";
+};
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 467cd7b147ce..f5a0923b34ca 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -19,6 +19,8 @@ Optional properties:
 - wp-gpios: Specify GPIOs for write protection, see gpio binding
 - cd-inverted: when present, polarity on the CD line is inverted. See the note
   below for the case, when a GPIO is used for the CD line
+- cd-debounce-delay-ms: Set delay time before detecting card after card insert interrupt.
+  It's only valid when cd-gpios is present.
 - wp-inverted: when present, polarity on the WP line is inverted. See the note
   below for the case, when a GPIO is used for the WP line
 - disable-wp: When set no physical WP line is present. This property should
@@ -56,6 +58,10 @@ Optional properties:
 - fixed-emmc-driver-type: for non-removable eMMC, enforce this driver type.
   The value <n> is the driver type as specified in the eMMC specification
   (table 206 in spec version 5.1).
+- post-power-on-delay-ms : It was invented for MMC pwrseq-simple which could
+  be referred to mmc-pwrseq-simple.txt. But now it's reused as a tunable delay
+  waiting for I/O signalling and card power supply to be stable, regardless of
+  whether pwrseq-simple is used. Default to 10ms if no available.
 
 *NOTE* on CD and WP polarity. To use common for all SD/MMC host controllers line
 polarity properties, we have to fix the meaning of the "normal" and "inverted"
diff --git a/Documentation/devicetree/bindings/mmc/sdhci-omap.txt b/Documentation/devicetree/bindings/mmc/sdhci-omap.txt
index 51775a372c06..393848c2138e 100644
--- a/Documentation/devicetree/bindings/mmc/sdhci-omap.txt
+++ b/Documentation/devicetree/bindings/mmc/sdhci-omap.txt
@@ -4,7 +4,14 @@ Refer to mmc.txt for standard MMC bindings.
 
 Required properties:
 - compatible: Should be "ti,dra7-sdhci" for DRA7 and DRA72 controllers
+	      Should be "ti,k2g-sdhci" for K2G
 - ti,hwmods: Must be "mmc<n>", <n> is controller instance starting 1
+	     (Not required for K2G).
+- pinctrl-names: Should be subset of "default", "hs", "sdr12", "sdr25", "sdr50",
+		 "ddr50-rev11", "sdr104-rev11", "ddr50", "sdr104",
+		 "ddr_1_8v-rev11", "ddr_1_8v" or "ddr_3_3v", "hs200_1_8v-rev11",
+		 "hs200_1_8v",
+- pinctrl-<n> : Pinctrl states as described in bindings/pinctrl/pinctrl-bindings.txt
 
 Example:
 	mmc1: mmc@4809c000 {
diff --git a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
index 2d5287eeed95..ee978c95189d 100644
--- a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
@@ -26,6 +26,8 @@ Required properties:
 		"renesas,sdhi-r8a7794" - SDHI IP on R8A7794 SoC
 		"renesas,sdhi-r8a7795" - SDHI IP on R8A7795 SoC
 		"renesas,sdhi-r8a7796" - SDHI IP on R8A7796 SoC
+		"renesas,sdhi-r8a77965" - SDHI IP on R8A77965 SoC
+		"renesas,sdhi-r8a77980" - SDHI IP on R8A77980 SoC
 		"renesas,sdhi-r8a77995" - SDHI IP on R8A77995 SoC
 		"renesas,sdhi-shmobile" - a generic sh-mobile SDHI controller
 		"renesas,rcar-gen1-sdhi" - a generic R-Car Gen1 SDHI controller
diff --git a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
index 93c3a6ae32f9..ac71daa46195 100644
--- a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
+++ b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
@@ -5,7 +5,9 @@ Required properties:
 - compatible: Must contain one or more of the following:
   - "renesas,rcar-gen3-canfd" for R-Car Gen3 compatible controller.
   - "renesas,r8a7795-canfd" for R8A7795 (R-Car H3) compatible controller.
-  - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3) compatible controller.
+  - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3-W) compatible controller.
+  - "renesas,r8a77970-canfd" for R8A77970 (R-Car V3M) compatible controller.
+  - "renesas,r8a77980-canfd" for R8A77980 (R-Car V3H) compatible controller.
 
   When compatible with the generic version, nodes must list the
   SoC-specific version corresponding to the platform first, followed by the
diff --git a/Documentation/devicetree/bindings/net/dsa/b53.txt b/Documentation/devicetree/bindings/net/dsa/b53.txt
index 8acf51a4dfa8..47a6a7fe0b86 100644
--- a/Documentation/devicetree/bindings/net/dsa/b53.txt
+++ b/Documentation/devicetree/bindings/net/dsa/b53.txt
@@ -10,6 +10,7 @@ Required properties:
       "brcm,bcm53128"
       "brcm,bcm5365"
       "brcm,bcm5395"
+      "brcm,bcm5389"
       "brcm,bcm5397"
       "brcm,bcm5398"
 
diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt
index 1814fa13f6ab..fc019df0d863 100644
--- a/Documentation/devicetree/bindings/net/marvell-pp2.txt
+++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt
@@ -21,9 +21,10 @@ Required properties:
 	- main controller clock (for both armada-375-pp2 and armada-7k-pp2)
 	- GOP clock (for both armada-375-pp2 and armada-7k-pp2)
 	- MG clock (only for armada-7k-pp2)
+	- MG Core clock (only for armada-7k-pp2)
 	- AXI clock (only for armada-7k-pp2)
-- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk"
-  and "axi_clk" (the 2 latter only for armada-7k-pp2).
+- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk",
+  "mg_core_clk" and "axi_clk" (the 3 latter only for armada-7k-pp2).
 
 The ethernet ports are represented by subnodes. At least one port is
 required.
@@ -80,8 +81,8 @@ cpm_ethernet: ethernet@0 {
 	compatible = "marvell,armada-7k-pp22";
 	reg = <0x0 0x100000>, <0x129000 0xb000>;
 	clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>,
-		 <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>;
-	clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk";
+		 <&cpm_syscon0 1 5>, <&cpm_syscon0 1 6>, <&cpm_syscon0 1 18>;
+	clock-names = "pp_clk", "gop_clk", "mg_clk", "mg_core_clk", "axi_clk";
 
 	eth0: eth0 {
 		interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
index 42a248301615..e22d8cfea687 100644
--- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
+++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
@@ -57,6 +57,13 @@ KSZ9031:
       - txd2-skew-ps : Skew control of TX data 2 pad
       - txd3-skew-ps : Skew control of TX data 3 pad
 
+    - micrel,force-master:
+        Boolean, force phy to master mode. Only set this option if the phy
+        reference clock provided at CLK125_NDO pin is used as MAC reference
+        clock because the clock jitter in slave mode is to high (errata#2).
+        Attention: The link partner must be configurable as slave otherwise
+        no link will be established.
+
 Examples:
 
 	mdio {
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index c306f55d335b..890526dbfc26 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -18,6 +18,7 @@ Required properties:
 
       - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
       - "renesas,etheravb-r8a7796" for the R8A7796 SoC.
+      - "renesas,etheravb-r8a77965" for the R8A77965 SoC.
       - "renesas,etheravb-r8a77970" for the R8A77970 SoC.
       - "renesas,etheravb-r8a77980" for the R8A77980 SoC.
       - "renesas,etheravb-r8a77995" for the R8A77995 SoC.
diff --git a/Documentation/devicetree/bindings/nvmem/zii,rave-sp-eeprom.txt b/Documentation/devicetree/bindings/nvmem/zii,rave-sp-eeprom.txt
new file mode 100644
index 000000000000..d5e22fc67d66
--- /dev/null
+++ b/Documentation/devicetree/bindings/nvmem/zii,rave-sp-eeprom.txt
@@ -0,0 +1,40 @@
+Zodiac Inflight Innovations RAVE EEPROM Bindings
+
+RAVE SP EEPROM device is a "MFD cell" device exposing physical EEPROM
+attached to RAVE Supervisory Processor. It is expected that its Device
+Tree node is specified as a child of the node corresponding to the
+parent RAVE SP device (as documented in
+Documentation/devicetree/bindings/mfd/zii,rave-sp.txt)
+
+Required properties:
+
+- compatible: Should be "zii,rave-sp-eeprom"
+
+Optional properties:
+
+- zii,eeprom-name: Unique EEPROM identifier describing its function in the
+  system. Will be used as created NVMEM deivce's name.
+
+Data cells:
+
+Data cells are child nodes of eerpom node, bindings for which are
+documented in Documentation/bindings/nvmem/nvmem.txt
+
+Example:
+
+	rave-sp {
+		compatible = "zii,rave-sp-rdu1";
+		current-speed = <38400>;
+
+		eeprom@a4 {
+			compatible = "zii,rave-sp-eeprom";
+			reg = <0xa4 0x4000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			zii,eeprom-name = "main-eeprom";
+
+			wdt_timeout: wdt-timeout@81 {
+				reg = <0x81 2>;
+			};
+		};
+	}
diff --git a/Documentation/devicetree/bindings/opp/kryo-cpufreq.txt b/Documentation/devicetree/bindings/opp/kryo-cpufreq.txt
new file mode 100644
index 000000000000..c2127b96805a
--- /dev/null
+++ b/Documentation/devicetree/bindings/opp/kryo-cpufreq.txt
@@ -0,0 +1,680 @@
+Qualcomm Technologies, Inc. KRYO CPUFreq and OPP bindings
+===================================
+
+In Certain Qualcomm Technologies, Inc. SoCs like apq8096 and msm8996
+that have KRYO processors, the CPU ferequencies subset and voltage value
+of each OPP varies based on the silicon variant in use.
+Qualcomm Technologies, Inc. Process Voltage Scaling Tables
+defines the voltage and frequency value based on the msm-id in SMEM
+and speedbin blown in the efuse combination.
+The qcom-cpufreq-kryo driver reads the msm-id and efuse value from the SoC
+to provide the OPP framework with required information (existing HW bitmap).
+This is used to determine the voltage and frequency value for each OPP of
+operating-points-v2 table when it is parsed by the OPP framework.
+
+Required properties:
+--------------------
+In 'cpus' nodes:
+- operating-points-v2: Phandle to the operating-points-v2 table to use.
+
+In 'operating-points-v2' table:
+- compatible: Should be
+	- 'operating-points-v2-kryo-cpu' for apq8096 and msm8996.
+- nvmem-cells: A phandle pointing to a nvmem-cells node representing the
+		efuse registers that has information about the
+		speedbin that is used to select the right frequency/voltage
+		value pair.
+		Please refer the for nvmem-cells
+		bindings Documentation/devicetree/bindings/nvmem/nvmem.txt
+		and also examples below.
+
+In every OPP node:
+- opp-supported-hw: A single 32 bit bitmap value, representing compatible HW.
+		    Bitmap:
+			0:	MSM8996 V3, speedbin 0
+			1:	MSM8996 V3, speedbin 1
+			2:	MSM8996 V3, speedbin 2
+			3:	unused
+			4:	MSM8996 SG, speedbin 0
+			5:	MSM8996 SG, speedbin 1
+			6:	MSM8996 SG, speedbin 2
+			7-31:	unused
+
+Example 1:
+---------
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "qcom,kryo";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+			clocks = <&kryocc 0>;
+			cpu-supply = <&pm8994_s11_saw>;
+			operating-points-v2 = <&cluster0_opp>;
+			#cooling-cells = <2>;
+			next-level-cache = <&L2_0>;
+			L2_0: l2-cache {
+			      compatible = "cache";
+			      cache-level = <2>;
+			};
+		};
+
+		CPU1: cpu@1 {
+			device_type = "cpu";
+			compatible = "qcom,kryo";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+			clocks = <&kryocc 0>;
+			cpu-supply = <&pm8994_s11_saw>;
+			operating-points-v2 = <&cluster0_opp>;
+			#cooling-cells = <2>;
+			next-level-cache = <&L2_0>;
+		};
+
+		CPU2: cpu@100 {
+			device_type = "cpu";
+			compatible = "qcom,kryo";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+			clocks = <&kryocc 1>;
+			cpu-supply = <&pm8994_s11_saw>;
+			operating-points-v2 = <&cluster1_opp>;
+			#cooling-cells = <2>;
+			next-level-cache = <&L2_1>;
+			L2_1: l2-cache {
+			      compatible = "cache";
+			      cache-level = <2>;
+			};
+		};
+
+		CPU3: cpu@101 {
+			device_type = "cpu";
+			compatible = "qcom,kryo";
+			reg = <0x0 0x101>;
+			enable-method = "psci";
+			clocks = <&kryocc 1>;
+			cpu-supply = <&pm8994_s11_saw>;
+			operating-points-v2 = <&cluster1_opp>;
+			#cooling-cells = <2>;
+			next-level-cache = <&L2_1>;
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+
+				core1 {
+					cpu = <&CPU1>;
+				};
+			};
+
+			cluster1 {
+				core0 {
+					cpu = <&CPU2>;
+				};
+
+				core1 {
+					cpu = <&CPU3>;
+				};
+			};
+		};
+	};
+
+	cluster0_opp: opp_table0 {
+		compatible = "operating-points-v2-kryo-cpu";
+		nvmem-cells = <&speedbin_efuse>;
+		opp-shared;
+
+		opp-307200000 {
+			opp-hz = /bits/ 64 <307200000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x77>;
+			clock-latency-ns = <200000>;
+		};
+		opp-384000000 {
+			opp-hz = /bits/ 64 <384000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-422400000 {
+			opp-hz = /bits/ 64 <422400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-460800000 {
+			opp-hz = /bits/ 64 <460800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-480000000 {
+			opp-hz = /bits/ 64 <480000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-537600000 {
+			opp-hz = /bits/ 64 <537600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-556800000 {
+			opp-hz = /bits/ 64 <556800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-614400000 {
+			opp-hz = /bits/ 64 <614400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-652800000 {
+			opp-hz = /bits/ 64 <652800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-691200000 {
+			opp-hz = /bits/ 64 <691200000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-729600000 {
+			opp-hz = /bits/ 64 <729600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-768000000 {
+			opp-hz = /bits/ 64 <768000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-844800000 {
+			opp-hz = /bits/ 64 <844800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x77>;
+			clock-latency-ns = <200000>;
+		};
+		opp-902400000 {
+			opp-hz = /bits/ 64 <902400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-960000000 {
+			opp-hz = /bits/ 64 <960000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-979200000 {
+			opp-hz = /bits/ 64 <979200000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1036800000 {
+			opp-hz = /bits/ 64 <1036800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1056000000 {
+			opp-hz = /bits/ 64 <1056000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1113600000 {
+			opp-hz = /bits/ 64 <1113600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1132800000 {
+			opp-hz = /bits/ 64 <1132800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1190400000 {
+			opp-hz = /bits/ 64 <1190400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1209600000 {
+			opp-hz = /bits/ 64 <1209600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1228800000 {
+			opp-hz = /bits/ 64 <1228800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1286400000 {
+			opp-hz = /bits/ 64 <1286400000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1324800000 {
+			opp-hz = /bits/ 64 <1324800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x5>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1363200000 {
+			opp-hz = /bits/ 64 <1363200000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x72>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1401600000 {
+			opp-hz = /bits/ 64 <1401600000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x5>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1440000000 {
+			opp-hz = /bits/ 64 <1440000000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1478400000 {
+			opp-hz = /bits/ 64 <1478400000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x1>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1497600000 {
+			opp-hz = /bits/ 64 <1497600000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x4>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1516800000 {
+			opp-hz = /bits/ 64 <1516800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1593600000 {
+			opp-hz = /bits/ 64 <1593600000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x71>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1996800000 {
+			opp-hz = /bits/ 64 <1996800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x20>;
+			clock-latency-ns = <200000>;
+		};
+		opp-2188800000 {
+			opp-hz = /bits/ 64 <2188800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x10>;
+			clock-latency-ns = <200000>;
+		};
+	};
+
+	cluster1_opp: opp_table1 {
+		compatible = "operating-points-v2-kryo-cpu";
+		nvmem-cells = <&speedbin_efuse>;
+		opp-shared;
+
+		opp-307200000 {
+			opp-hz = /bits/ 64 <307200000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x77>;
+			clock-latency-ns = <200000>;
+		};
+		opp-384000000 {
+			opp-hz = /bits/ 64 <384000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-403200000 {
+			opp-hz = /bits/ 64 <403200000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-460800000 {
+			opp-hz = /bits/ 64 <460800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-480000000 {
+			opp-hz = /bits/ 64 <480000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-537600000 {
+			opp-hz = /bits/ 64 <537600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-556800000 {
+			opp-hz = /bits/ 64 <556800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-614400000 {
+			opp-hz = /bits/ 64 <614400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-652800000 {
+			opp-hz = /bits/ 64 <652800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-691200000 {
+			opp-hz = /bits/ 64 <691200000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-729600000 {
+			opp-hz = /bits/ 64 <729600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-748800000 {
+			opp-hz = /bits/ 64 <748800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-806400000 {
+			opp-hz = /bits/ 64 <806400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-825600000 {
+			opp-hz = /bits/ 64 <825600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-883200000 {
+			opp-hz = /bits/ 64 <883200000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-902400000 {
+			opp-hz = /bits/ 64 <902400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-940800000 {
+			opp-hz = /bits/ 64 <940800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-979200000 {
+			opp-hz = /bits/ 64 <979200000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1036800000 {
+			opp-hz = /bits/ 64 <1036800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1056000000 {
+			opp-hz = /bits/ 64 <1056000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1113600000 {
+			opp-hz = /bits/ 64 <1113600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1132800000 {
+			opp-hz = /bits/ 64 <1132800000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1190400000 {
+			opp-hz = /bits/ 64 <1190400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1209600000 {
+			opp-hz = /bits/ 64 <1209600000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1248000000 {
+			opp-hz = /bits/ 64 <1248000000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1286400000 {
+			opp-hz = /bits/ 64 <1286400000>;
+			opp-microvolt = <905000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1324800000 {
+			opp-hz = /bits/ 64 <1324800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1363200000 {
+			opp-hz = /bits/ 64 <1363200000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1401600000 {
+			opp-hz = /bits/ 64 <1401600000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1440000000 {
+			opp-hz = /bits/ 64 <1440000000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1478400000 {
+			opp-hz = /bits/ 64 <1478400000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1516800000 {
+			opp-hz = /bits/ 64 <1516800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1555200000 {
+			opp-hz = /bits/ 64 <1555200000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1593600000 {
+			opp-hz = /bits/ 64 <1593600000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1632000000 {
+			opp-hz = /bits/ 64 <1632000000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1670400000 {
+			opp-hz = /bits/ 64 <1670400000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1708800000 {
+			opp-hz = /bits/ 64 <1708800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1747200000 {
+			opp-hz = /bits/ 64 <1747200000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x70>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1785600000 {
+			opp-hz = /bits/ 64 <1785600000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x7>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1804800000 {
+			opp-hz = /bits/ 64 <1804800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x6>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1824000000 {
+			opp-hz = /bits/ 64 <1824000000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x71>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1900800000 {
+			opp-hz = /bits/ 64 <1900800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x74>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1920000000 {
+			opp-hz = /bits/ 64 <1920000000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x1>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1977600000 {
+			opp-hz = /bits/ 64 <1977600000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x30>;
+			clock-latency-ns = <200000>;
+		};
+		opp-1996800000 {
+			opp-hz = /bits/ 64 <1996800000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x1>;
+			clock-latency-ns = <200000>;
+		};
+		opp-2054400000 {
+			opp-hz = /bits/ 64 <2054400000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x30>;
+			clock-latency-ns = <200000>;
+		};
+		opp-2073600000 {
+			opp-hz = /bits/ 64 <2073600000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x1>;
+			clock-latency-ns = <200000>;
+		};
+		opp-2150400000 {
+			opp-hz = /bits/ 64 <2150400000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x31>;
+			clock-latency-ns = <200000>;
+		};
+		opp-2246400000 {
+			opp-hz = /bits/ 64 <2246400000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x10>;
+			clock-latency-ns = <200000>;
+		};
+		opp-2342400000 {
+			opp-hz = /bits/ 64 <2342400000>;
+			opp-microvolt = <1140000 905000 1140000>;
+			opp-supported-hw = <0x10>;
+			clock-latency-ns = <200000>;
+		};
+	};
+
+....
+
+reserved-memory {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	ranges;
+....
+	smem_mem: smem-mem@86000000 {
+		reg = <0x0 0x86000000 0x0 0x200000>;
+		no-map;
+	};
+....
+};
+
+smem {
+	compatible = "qcom,smem";
+	memory-region = <&smem_mem>;
+	hwlocks = <&tcsr_mutex 3>;
+};
+
+soc {
+....
+	qfprom: qfprom@74000 {
+		compatible = "qcom,qfprom";
+		reg = <0x00074000 0x8ff>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		....
+		speedbin_efuse: speedbin@133 {
+			reg = <0x133 0x1>;
+			bits = <5 3>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt
index 4e4f30288c8b..c396c4c0af92 100644
--- a/Documentation/devicetree/bindings/opp/opp.txt
+++ b/Documentation/devicetree/bindings/opp/opp.txt
@@ -82,7 +82,10 @@ This defines voltage-current-frequency combinations along with other related
 properties.
 
 Required properties:
-- opp-hz: Frequency in Hz, expressed as a 64-bit big-endian integer.
+- opp-hz: Frequency in Hz, expressed as a 64-bit big-endian integer. This is a
+  required property for all device nodes but devices like power domains. The
+  power domain nodes must have another (implementation dependent) property which
+  uniquely identifies the OPP nodes.
 
 Optional properties:
 - opp-microvolt: voltage in micro Volts.
@@ -159,7 +162,7 @@ Optional properties:
 
 - status: Marks the node enabled/disabled.
 
-- required-opp: This contains phandle to an OPP node in another device's OPP
+- required-opps: This contains phandle to an OPP node in another device's OPP
   table. It may contain an array of phandles, where each phandle points to an
   OPP of a different device. It should not contain multiple phandles to the OPP
   nodes in the same OPP table. This specifies the minimum required OPP of the
diff --git a/Documentation/devicetree/bindings/phy/phy-mtk-xsphy.txt b/Documentation/devicetree/bindings/phy/phy-mtk-xsphy.txt
new file mode 100644
index 000000000000..e7caefa0b9c2
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/phy-mtk-xsphy.txt
@@ -0,0 +1,109 @@
+MediaTek XS-PHY binding
+--------------------------
+
+The XS-PHY controller supports physical layer functionality for USB3.1
+GEN2 controller on MediaTek SoCs.
+
+Required properties (controller (parent) node):
+ - compatible	: should be "mediatek,<soc-model>-xsphy", "mediatek,xsphy",
+		  soc-model is the name of SoC, such as mt3611 etc;
+		  when using "mediatek,xsphy" compatible string, you need SoC specific
+		  ones in addition, one of:
+		  - "mediatek,mt3611-xsphy"
+
+ - #address-cells, #size-cells : should use the same values as the root node
+ - ranges: must be present
+
+Optional properties (controller (parent) node):
+ - reg		: offset and length of register shared by multiple U3 ports,
+		  exclude port's private register, if only U2 ports provided,
+		  shouldn't use the property.
+ - mediatek,src-ref-clk-mhz	: u32, frequency of reference clock for slew rate
+		  calibrate
+ - mediatek,src-coef	: u32, coefficient for slew rate calibrate, depends on
+		  SoC process
+
+Required nodes	: a sub-node is required for each port the controller
+		  provides. Address range information including the usual
+		  'reg' property is used inside these nodes to describe
+		  the controller's topology.
+
+Required properties (port (child) node):
+- reg		: address and length of the register set for the port.
+- clocks	: a list of phandle + clock-specifier pairs, one for each
+		  entry in clock-names
+- clock-names	: must contain
+		  "ref": 48M reference clock for HighSpeed analog phy; and 26M
+			reference clock for SuperSpeedPlus analog phy, sometimes is
+			24M, 25M or 27M, depended on platform.
+- #phy-cells	: should be 1
+		  cell after port phandle is phy type from:
+			- PHY_TYPE_USB2
+			- PHY_TYPE_USB3
+
+The following optional properties are only for debug or HQA test
+Optional properties (PHY_TYPE_USB2 port (child) node):
+- mediatek,eye-src	: u32, the value of slew rate calibrate
+- mediatek,eye-vrt	: u32, the selection of VRT reference voltage
+- mediatek,eye-term	: u32, the selection of HS_TX TERM reference voltage
+- mediatek,efuse-intr	: u32, the selection of Internal Resistor
+
+Optional properties (PHY_TYPE_USB3 port (child) node):
+- mediatek,efuse-intr	: u32, the selection of Internal Resistor
+- mediatek,efuse-tx-imp	: u32, the selection of TX Impedance
+- mediatek,efuse-rx-imp	: u32, the selection of RX Impedance
+
+Banks layout of xsphy
+-------------------------------------------------------------
+port        offset    bank
+u2 port0    0x0000    MISC
+            0x0100    FMREG
+            0x0300    U2PHY_COM
+u2 port1    0x1000    MISC
+            0x1100    FMREG
+            0x1300    U2PHY_COM
+u2 port2    0x2000    MISC
+            ...
+u31 common  0x3000    DIG_GLB
+            0x3100    PHYA_GLB
+u31 port0   0x3400    DIG_LN_TOP
+            0x3500    DIG_LN_TX0
+            0x3600    DIG_LN_RX0
+            0x3700    DIG_LN_DAIF
+            0x3800    PHYA_LN
+u31 port1   0x3a00    DIG_LN_TOP
+            0x3b00    DIG_LN_TX0
+            0x3c00    DIG_LN_RX0
+            0x3d00    DIG_LN_DAIF
+            0x3e00    PHYA_LN
+            ...
+
+DIG_GLB & PHYA_GLB are shared by U31 ports.
+
+Example:
+
+u3phy: usb-phy@11c40000 {
+	compatible = "mediatek,mt3611-xsphy", "mediatek,xsphy";
+	reg = <0 0x11c43000 0 0x0200>;
+	mediatek,src-ref-clk-mhz = <26>;
+	mediatek,src-coef = <17>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+	ranges;
+
+	u2port0: usb-phy@11c40000 {
+		reg = <0 0x11c40000 0 0x0400>;
+		clocks = <&clk48m>;
+		clock-names = "ref";
+		mediatek,eye-src = <4>;
+		#phy-cells = <1>;
+	};
+
+	u3port0: usb-phy@11c43000 {
+		reg = <0 0x11c43400 0 0x0500>;
+		clocks = <&clk26m>;
+		clock-names = "ref";
+		mediatek,efuse-intr = <28>;
+		#phy-cells = <1>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt b/Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt
index dcf1b8f691d5..266a1bb8bb6e 100644
--- a/Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt
+++ b/Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt
@@ -9,7 +9,8 @@ Required properties:
 	       "qcom,ipq8074-qmp-pcie-phy" for PCIe phy on IPQ8074
 	       "qcom,msm8996-qmp-pcie-phy" for 14nm PCIe phy on msm8996,
 	       "qcom,msm8996-qmp-usb3-phy" for 14nm USB3 phy on msm8996,
-	       "qcom,qmp-v3-usb3-phy" for USB3 QMP V3 phy.
+	       "qcom,sdm845-qmp-usb3-phy" for USB3 QMP V3 phy on sdm845,
+	       "qcom,sdm845-qmp-usb3-uni-phy" for USB3 QMP V3 UNI phy on sdm845.
 
  - reg: offset and length of register set for PHY's common serdes block.
 
diff --git a/Documentation/devicetree/bindings/phy/qcom-qusb2-phy.txt b/Documentation/devicetree/bindings/phy/qcom-qusb2-phy.txt
index 42c97426836e..03025d97998b 100644
--- a/Documentation/devicetree/bindings/phy/qcom-qusb2-phy.txt
+++ b/Documentation/devicetree/bindings/phy/qcom-qusb2-phy.txt
@@ -6,7 +6,7 @@ QUSB2 controller supports LS/FS/HS usb connectivity on Qualcomm chipsets.
 Required properties:
  - compatible: compatible list, contains
 	       "qcom,msm8996-qusb2-phy" for 14nm PHY on msm8996,
-	       "qcom,qusb2-v2-phy" for QUSB2 V2 PHY.
+	       "qcom,sdm845-qusb2-phy" for 10nm PHY on sdm845.
 
  - reg: offset and length of the PHY register set.
  - #phy-cells: must be 0.
@@ -27,6 +27,27 @@ Optional properties:
 		tuning parameter value for qusb2 phy.
 
  - qcom,tcsr-syscon: Phandle to TCSR syscon register region.
+ - qcom,imp-res-offset-value: It is a 6 bit value that specifies offset to be
+		added to PHY refgen RESCODE via IMP_CTRL1 register. It is a PHY
+		tuning parameter that may vary for different boards of same SOC.
+		This property is applicable to only QUSB2 v2 PHY (sdm845).
+ - qcom,hstx-trim-value: It is a 4 bit value that specifies tuning for HSTX
+		output current.
+		Possible range is - 15mA to 24mA (stepsize of 600 uA).
+		See dt-bindings/phy/phy-qcom-qusb2.h for applicable values.
+		This property is applicable to only QUSB2 v2 PHY (sdm845).
+		Default value is 22.2mA for sdm845.
+ - qcom,preemphasis-level: It is a 2 bit value that specifies pre-emphasis level.
+		Possible range is 0 to 15% (stepsize of 5%).
+		See dt-bindings/phy/phy-qcom-qusb2.h for applicable values.
+		This property is applicable to only QUSB2 v2 PHY (sdm845).
+		Default value is 10% for sdm845.
+- qcom,preemphasis-width: It is a 1 bit value that specifies how long the HSTX
+		pre-emphasis (specified using qcom,preemphasis-level) must be in
+		effect. Duration could be half-bit of full-bit.
+		See dt-bindings/phy/phy-qcom-qusb2.h for applicable values.
+		This property is applicable to only QUSB2 v2 PHY (sdm845).
+		Default value is full-bit width for sdm845.
 
 Example:
 	hsusb_phy: phy@7411000 {
diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
index ed5eb547afc8..64bc5c2a76da 100644
--- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
@@ -56,9 +56,9 @@ pins it needs, and how they should be configured, with regard to muxer
 configuration, drive strength and pullups. If one of these options is
 not set, its actual value will be unspecified.
 
-This driver supports the generic pin multiplexing and configuration
-bindings. For details on each properties, you can refer to
-./pinctrl-bindings.txt.
+Allwinner A1X Pin Controller supports the generic pin multiplexing and
+configuration bindings. For details on each properties, you can refer to
+ ./pinctrl-bindings.txt.
 
 Required sub-node properties:
   - pins
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index f3355313c020..4733f76cbe48 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -127,7 +127,7 @@ inside a PM domain with index 0 of a power controller represented by a node
 with the label "power".
 
 Optional properties:
-- required-opp: This contains phandle to an OPP node in another device's OPP
+- required-opps: This contains phandle to an OPP node in another device's OPP
   table. It may contain an array of phandles, where each phandle points to an
   OPP of a different device. It should not contain multiple phandles to the OPP
   nodes in the same OPP table. This specifies the minimum required OPP of the
@@ -175,14 +175,14 @@ Example:
 		compatible = "foo,i-leak-current";
 		reg = <0x12350000 0x1000>;
 		power-domains = <&power 0>;
-		required-opp = <&domain0_opp_0>;
+		required-opps = <&domain0_opp_0>;
 	};
 
 	leaky-device1@12350000 {
 		compatible = "foo,i-leak-current";
 		reg = <0x12350000 0x1000>;
 		power-domains = <&power 1>;
-		required-opp = <&domain1_opp_1>;
+		required-opps = <&domain1_opp_1>;
 	};
 
 [1]. Documentation/devicetree/bindings/power/domain-idle-state.txt
diff --git a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
index 4a4766e9c254..e66fd4eab71c 100644
--- a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
+++ b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
@@ -31,6 +31,8 @@ SoC is on the same page.
 
 Required properties:
 - compatible: should be one of:
+  - "rockchip,px30-io-voltage-domain" for px30
+  - "rockchip,px30-pmu-io-voltage-domain" for px30 pmu-domains
   - "rockchip,rk3188-io-voltage-domain" for rk3188
   - "rockchip,rk3228-io-voltage-domain" for rk3228
   - "rockchip,rk3288-io-voltage-domain" for rk3288
@@ -51,6 +53,19 @@ a phandle the relevant regulator.  All specified supplies must be able
 to report their voltage.  The IO Voltage Domain for any non-specified
 supplies will be not be touched.
 
+Possible supplies for PX30:
+- vccio6-supply: The supply connected to VCCIO6.
+- vccio1-supply: The supply connected to VCCIO1.
+- vccio2-supply: The supply connected to VCCIO2.
+- vccio3-supply: The supply connected to VCCIO3.
+- vccio4-supply: The supply connected to VCCIO4.
+- vccio5-supply: The supply connected to VCCIO5.
+- vccio-oscgpi-supply: The supply connected to VCCIO_OSCGPI.
+
+Possible supplies for PX30 pmu-domains:
+- pmuio1-supply: The supply connected to PMUIO1.
+- pmuio2-supply: The supply connected to PMUIO2.
+
 Possible supplies for rk3188:
 - ap0-supply:    The supply connected to AP0_VCC.
 - ap1-supply:    The supply connected to AP1_VCC.
diff --git a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.txt b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.txt
index 8ff65fa632fd..c06c045126fc 100644
--- a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.txt
+++ b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.txt
@@ -21,7 +21,7 @@ Required properties:
 - interrupts : identifier to the device interrupt
 - clocks : a list of phandle + clock-specifier pairs, one for each
 	   entry in clock names.
-- clocks-names :
+- clock-names :
    * "xtal" for external xtal clock identifier
    * "pclk" for the bus core clock, either the clk81 clock or the gate clock
    * "baud" for the source of the baudrate generator, can be either the xtal
diff --git a/Documentation/devicetree/bindings/serial/mvebu-uart.txt b/Documentation/devicetree/bindings/serial/mvebu-uart.txt
index 2ae2fee7e023..b7e0e32b9ac6 100644
--- a/Documentation/devicetree/bindings/serial/mvebu-uart.txt
+++ b/Documentation/devicetree/bindings/serial/mvebu-uart.txt
@@ -24,7 +24,7 @@ Required properties:
     - Must contain two elements for the extended variant of the IP
       (marvell,armada-3700-uart-ext): "uart-tx" and "uart-rx",
       respectively the UART TX interrupt and the UART RX interrupt. A
-      corresponding interrupts-names property must be defined.
+      corresponding interrupt-names property must be defined.
     - For backward compatibility reasons, a single element interrupts
       property is also supported for the standard variant of the IP,
       containing only the UART sum interrupt. This form is deprecated
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index ad962f4ec3aa..106808b55b6d 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -17,6 +17,8 @@ Required properties:
     - "renesas,scifa-r8a7745" for R8A7745 (RZ/G1E) SCIFA compatible UART.
     - "renesas,scifb-r8a7745" for R8A7745 (RZ/G1E) SCIFB compatible UART.
     - "renesas,hscif-r8a7745" for R8A7745 (RZ/G1E) HSCIF compatible UART.
+    - "renesas,scif-r8a77470" for R8A77470 (RZ/G1C) SCIF compatible UART.
+    - "renesas,hscif-r8a77470" for R8A77470 (RZ/G1C) HSCIF compatible UART.
     - "renesas,scif-r8a7778" for R8A7778 (R-Car M1) SCIF compatible UART.
     - "renesas,scif-r8a7779" for R8A7779 (R-Car H1) SCIF compatible UART.
     - "renesas,scif-r8a7790" for R8A7790 (R-Car H2) SCIF compatible UART.
@@ -41,6 +43,8 @@ Required properties:
     - "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART.
     - "renesas,scif-r8a7796" for R8A7796 (R-Car M3-W) SCIF compatible UART.
     - "renesas,hscif-r8a7796" for R8A7796 (R-Car M3-W) HSCIF compatible UART.
+    - "renesas,scif-r8a77965" for R8A77965 (R-Car M3-N) SCIF compatible UART.
+    - "renesas,hscif-r8a77965" for R8A77965 (R-Car M3-N) HSCIF compatible UART.
     - "renesas,scif-r8a77970" for R8A77970 (R-Car V3M) SCIF compatible UART.
     - "renesas,hscif-r8a77970" for R8A77970 (R-Car V3M) HSCIF compatible UART.
     - "renesas,scif-r8a77980" for R8A77980 (R-Car V3H) SCIF compatible UART.
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,apr.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,apr.txt
new file mode 100644
index 000000000000..bcc612cc7423
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,apr.txt
@@ -0,0 +1,84 @@
+Qualcomm APR (Asynchronous Packet Router) binding
+
+This binding describes the Qualcomm APR. APR is a IPC protocol for
+communication between Application processor and QDSP. APR is mainly
+used for audio/voice services on the QDSP.
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,apr-v<VERSION-NUMBER>", example "qcom,apr-v2"
+
+- reg
+	Usage: required
+	Value type: <u32>
+	Definition: Destination processor ID.
+	Possible values are :
+			1 - APR simulator
+			2 - PC
+			3 - MODEM
+			4 - ADSP
+			5 - APPS
+			6 - MODEM2
+			7 - APPS2
+
+= APR SERVICES
+Each subnode of the APR node represents service tied to this apr. The name
+of the nodes are not important. The properties of these nodes are defined
+by the individual bindings for the specific service
+- All APR services MUST contain the following property:
+
+- reg
+	Usage: required
+	Value type: <u32>
+	Definition: APR Service ID
+	Possible values are :
+			3 - DSP Core Service
+			4 - Audio Front End Service.
+			5 - Voice Stream Manager Service.
+			6 - Voice processing manager.
+			7 - Audio Stream Manager Service.
+			8 - Audio Device Manager Service.
+			9 - Multimode voice manager.
+			10 - Core voice stream.
+			11 - Core voice processor.
+			12 - Ultrasound stream manager.
+			13 - Listen stream manager.
+
+= EXAMPLE
+The following example represents a QDSP based sound card on a MSM8996 device
+which uses apr as communication between Apps and QDSP.
+
+	apr@4 {
+		compatible = "qcom,apr-v2";
+		reg = <APR_DOMAIN_ADSP>;
+
+		q6core@3 {
+			compatible = "qcom,q6core";
+			reg = <APR_SVC_ADSP_CORE>;
+		};
+
+		q6afe@4 {
+			compatible = "qcom,q6afe";
+			reg = <APR_SVC_AFE>;
+
+			dais {
+				#sound-dai-cells = <1>;
+				hdmi@1 {
+					reg = <1>;
+				};
+			};
+		};
+
+		q6asm@7 {
+			compatible = "qcom,q6asm";
+			reg = <APR_SVC_ASM>;
+			...
+		};
+
+		q6adm@8 {
+			compatible = "qcom,q6adm";
+			reg = <APR_SVC_ADM>;
+			...
+		};
+	};
diff --git a/Documentation/devicetree/bindings/sound/adi,ssm2305.txt b/Documentation/devicetree/bindings/sound/adi,ssm2305.txt
new file mode 100644
index 000000000000..a9c9d83c8a30
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/adi,ssm2305.txt
@@ -0,0 +1,14 @@
+Analog Devices SSM2305 Speaker Amplifier
+========================================
+
+Required properties:
+  - compatible : "adi,ssm2305"
+  - shutdown-gpios : The gpio connected to the shutdown pin.
+                     The gpio signal is ACTIVE_LOW.
+
+Example:
+
+ssm2305: analog-amplifier {
+	compatible = "adi,ssm2305";
+	shutdown-gpios = <&gpio3 20 GPIO_ACTIVE_LOW>;
+};
diff --git a/Documentation/devicetree/bindings/sound/atmel-i2s.txt b/Documentation/devicetree/bindings/sound/atmel-i2s.txt
new file mode 100644
index 000000000000..735368b8a73f
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/atmel-i2s.txt
@@ -0,0 +1,47 @@
+* Atmel I2S controller
+
+Required properties:
+- compatible:     Should be "atmel,sama5d2-i2s".
+- reg:            Should be the physical base address of the controller and the
+                  length of memory mapped region.
+- interrupts:     Should contain the interrupt for the controller.
+- dmas:           Should be one per channel name listed in the dma-names property,
+                  as described in atmel-dma.txt and dma.txt files.
+- dma-names:      Two dmas have to be defined, "tx" and "rx".
+                  This IP also supports one shared channel for both rx and tx;
+                  if this mode is used, one "rx-tx" name must be used.
+- clocks:         Must contain an entry for each entry in clock-names.
+                  Please refer to clock-bindings.txt.
+- clock-names:    Should be one of each entry matching the clocks phandles list:
+                  - "pclk" (peripheral clock) Required.
+                  - "gclk" (generated clock) Optional (1).
+                  - "aclk" (Audio PLL clock) Optional (1).
+                  - "muxclk" (I2S mux clock) Optional (1).
+
+Optional properties:
+- pinctrl-0:      Should specify pin control groups used for this controller.
+- princtrl-names: Should contain only one value - "default".
+
+
+(1) : Only the peripheral clock is required. The generated clock, the Audio
+      PLL clock adn the I2S mux clock are optional and should only be set
+      together, when Master Mode is required.
+
+Example:
+
+	i2s@f8050000 {
+		compatible = "atmel,sama5d2-i2s";
+		reg = <0xf8050000 0x300>;
+		interrupts = <54 IRQ_TYPE_LEVEL_HIGH 7>;
+		dmas = <&dma0
+			(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+			 AT91_XDMAC_DT_PERID(31))>,
+		       <&dma0
+			(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+			 AT91_XDMAC_DT_PERID(32))>;
+		dma-names = "tx", "rx";
+		clocks = <&i2s0_clk>, <&i2s0_gclk>, <&audio_pll_pmc>, <&i2s0muxck>;
+		clock-names = "pclk", "gclk", "aclk", "muxclk";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_i2s0_default>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/cs42xx8.txt b/Documentation/devicetree/bindings/sound/cs42xx8.txt
index f631fbca6284..8619a156d038 100644
--- a/Documentation/devicetree/bindings/sound/cs42xx8.txt
+++ b/Documentation/devicetree/bindings/sound/cs42xx8.txt
@@ -16,7 +16,7 @@ Required properties:
 
 Example:
 
-codec: cs42888@48 {
+cs42888: codec@48 {
 	compatible = "cirrus,cs42888";
 	reg = <0x48>;
 	clocks = <&codec_mclk 0>;
diff --git a/Documentation/devicetree/bindings/sound/fsl,asrc.txt b/Documentation/devicetree/bindings/sound/fsl,asrc.txt
index f5a14115b459..1d4d9f938689 100644
--- a/Documentation/devicetree/bindings/sound/fsl,asrc.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,asrc.txt
@@ -31,14 +31,16 @@ Required properties:
 			  it. This property is optional depending on the SoC
 			  design.
 
-   - big-endian		: If this property is absent, the little endian mode
-			  will be in use as default. Otherwise, the big endian
-			  mode will be in use for all the device registers.
-
    - fsl,asrc-rate	: Defines a mutual sample rate used by DPCM Back Ends.
 
    - fsl,asrc-width	: Defines a mutual sample width used by DPCM Back Ends.
 
+Optional properties:
+
+   - big-endian		: If this property is absent, the little endian mode
+			  will be in use as default. Otherwise, the big endian
+			  mode will be in use for all the device registers.
+
 Example:
 
 asrc: asrc@2034000 {
diff --git a/Documentation/devicetree/bindings/sound/fsl,esai.txt b/Documentation/devicetree/bindings/sound/fsl,esai.txt
index cacd18bb9ba6..5b9914367610 100644
--- a/Documentation/devicetree/bindings/sound/fsl,esai.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,esai.txt
@@ -42,6 +42,8 @@ Required properties:
 			  means all the settings for Receiving would be
 			  duplicated from Transmition related registers.
 
+Optional properties:
+
   - big-endian		: If this property is absent, the native endian mode
 			  will be in use as default, or the big endian mode
 			  will be in use for all the device registers.
diff --git a/Documentation/devicetree/bindings/sound/fsl,spdif.txt b/Documentation/devicetree/bindings/sound/fsl,spdif.txt
index 38cfa7573441..8b324f82a782 100644
--- a/Documentation/devicetree/bindings/sound/fsl,spdif.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,spdif.txt
@@ -33,6 +33,8 @@ Required properties:
 			  it. This property is optional depending on the SoC
 			  design.
 
+Optional properties:
+
    - big-endian		: If this property is absent, the native endian mode
 			  will be in use as default, or the big endian mode
 			  will be in use for all the device registers.
diff --git a/Documentation/devicetree/bindings/sound/fsl-sai.txt b/Documentation/devicetree/bindings/sound/fsl-sai.txt
index 740b467adf7d..dd9e59738e08 100644
--- a/Documentation/devicetree/bindings/sound/fsl-sai.txt
+++ b/Documentation/devicetree/bindings/sound/fsl-sai.txt
@@ -28,9 +28,6 @@ Required properties:
 			  pinctrl-names. See ../pinctrl/pinctrl-bindings.txt
 			  for details of the property values.
 
-  - big-endian		: Boolean property, required if all the FTM_PWM
-			  registers are big-endian rather than little-endian.
-
   - lsb-first		: Configures whether the LSB or the MSB is transmitted
 			  first for the fifo data. If this property is absent,
 			  the MSB is transmitted first as default, or the LSB
@@ -48,6 +45,11 @@ Required properties:
 			  receive data by following their own bit clocks and
 			  frame sync clocks separately.
 
+Optional properties:
+
+  - big-endian		: Boolean property, required if all the SAI
+			  registers are big-endian rather than little-endian.
+
 Optional properties (for mx6ul):
 
   - fsl,sai-mclk-direction-output: This is a boolean property. If present,
diff --git a/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt b/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
index e2f7f4951215..560762e0a168 100644
--- a/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
+++ b/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
@@ -1,7 +1,9 @@
 Mediatek AFE PCM controller for mt2701
 
 Required properties:
-- compatible = "mediatek,mt2701-audio";
+- compatible: should be one of the followings.
+	      - "mediatek,mt2701-audio"
+	      - "mediatek,mt7622-audio"
 - interrupts: should contain AFE and ASYS interrupts
 - interrupt-names: should be "afe" and "asys"
 - power-domains: should define the power domain
diff --git a/Documentation/devicetree/bindings/sound/mt6351.txt b/Documentation/devicetree/bindings/sound/mt6351.txt
new file mode 100644
index 000000000000..7fb2cb99245e
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mt6351.txt
@@ -0,0 +1,16 @@
+Mediatek MT6351 Audio Codec
+
+The communication between MT6351 and SoC is through Mediatek PMIC wrapper.
+For more detail, please visit Mediatek PMIC wrapper documentation.
+
+Must be a child node of PMIC wrapper.
+
+Required properties:
+
+- compatible : "mediatek,mt6351-sound".
+
+Example:
+
+mt6351_snd {
+	compatible = "mediatek,mt6351-sound";
+};
diff --git a/Documentation/devicetree/bindings/sound/mt6797-afe-pcm.txt b/Documentation/devicetree/bindings/sound/mt6797-afe-pcm.txt
new file mode 100644
index 000000000000..0ae29de15bfd
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mt6797-afe-pcm.txt
@@ -0,0 +1,42 @@
+Mediatek AFE PCM controller for mt6797
+
+Required properties:
+- compatible = "mediatek,mt6797-audio";
+- reg: register location and size
+- interrupts: should contain AFE interrupt
+- power-domains: should define the power domain
+- clocks: Must contain an entry for each entry in clock-names
+- clock-names: should have these clock names:
+		"infra_sys_audio_clk",
+		"infra_sys_audio_26m",
+		"mtkaif_26m_clk",
+		"top_mux_audio",
+		"top_mux_aud_intbus",
+		"top_sys_pll3_d4",
+		"top_sys_pll1_d4",
+		"top_clk26m_clk";
+
+Example:
+
+	afe: mt6797-afe-pcm@11220000  {
+		compatible = "mediatek,mt6797-audio";
+		reg = <0 0x11220000 0 0x1000>;
+		interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_LOW>;
+		power-domains = <&scpsys MT6797_POWER_DOMAIN_AUDIO>;
+		clocks = <&infrasys CLK_INFRA_AUDIO>,
+			 <&infrasys CLK_INFRA_AUDIO_26M>,
+			 <&infrasys CLK_INFRA_AUDIO_26M_PAD_TOP>,
+			 <&topckgen CLK_TOP_MUX_AUDIO>,
+			 <&topckgen CLK_TOP_MUX_AUD_INTBUS>,
+			 <&topckgen CLK_TOP_SYSPLL3_D4>,
+			 <&topckgen CLK_TOP_SYSPLL1_D4>,
+			 <&clk26m>;
+		clock-names = "infra_sys_audio_clk",
+			      "infra_sys_audio_26m",
+			      "mtkaif_26m_clk",
+			      "top_mux_audio",
+			      "top_mux_aud_intbus",
+			      "top_sys_pll3_d4",
+			      "top_sys_pll1_d4",
+			      "top_clk26m_clk";
+	};
diff --git a/Documentation/devicetree/bindings/sound/mt6797-mt6351.txt b/Documentation/devicetree/bindings/sound/mt6797-mt6351.txt
new file mode 100644
index 000000000000..1d95a8840f19
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mt6797-mt6351.txt
@@ -0,0 +1,14 @@
+MT6797 with MT6351 CODEC
+
+Required properties:
+- compatible: "mediatek,mt6797-mt6351-sound"
+- mediatek,platform: the phandle of MT6797 ASoC platform
+- mediatek,audio-codec: the phandles of MT6351 codec
+
+Example:
+
+	sound {
+		compatible = "mediatek,mt6797-mt6351-sound";
+		mediatek,audio-codec = <&mt6351_snd>;
+		mediatek,platform = <&afe>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
new file mode 100644
index 000000000000..aa54e49fc8a2
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
@@ -0,0 +1,109 @@
+* Qualcomm Technologies APQ8096 ASoC sound card driver
+
+This binding describes the APQ8096 sound card, which uses qdsp for audio.
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,apq8096-sndcard"
+
+- qcom,audio-routing:
+	Usage: Optional
+	Value type: <stringlist>
+	Definition:  A list of the connections between audio components.
+		  Each entry is a pair of strings, the first being the
+		  connection's sink, the second being the connection's
+		  source. Valid names could be power supplies, MicBias
+		  of codec and the jacks on the board:
+		  Valid names include:
+
+		Board Connectors:
+			"Headphone Left"
+			"Headphone Right"
+			"Earphone"
+			"Line Out1"
+			"Line Out2"
+			"Line Out3"
+			"Line Out4"
+			"Analog Mic1"
+			"Analog Mic2"
+			"Analog Mic3"
+			"Analog Mic4"
+			"Analog Mic5"
+			"Analog Mic6"
+			"Digital Mic2"
+			"Digital Mic3"
+
+		Audio pins and MicBias on WCD9335 Codec:
+			"MIC_BIAS1
+			"MIC_BIAS2"
+			"MIC_BIAS3"
+			"MIC_BIAS4"
+			"AMIC1"
+			"AMIC2"
+			"AMIC3"
+			"AMIC4"
+			"AMIC5"
+			"AMIC6"
+			"AMIC6"
+			"DMIC1"
+			"DMIC2"
+			"DMIC3"
+= dailinks
+Each subnode of sndcard represents either a dailink, and subnodes of each
+dailinks would be cpu/codec/platform dais.
+
+- link-name:
+	Usage: required
+	Value type: <string>
+	Definition: User friendly name for dai link
+
+= CPU, PLATFORM, CODEC dais subnodes
+- cpu:
+	Usage: required
+	Value type: <subnode>
+	Definition: cpu dai sub-node
+
+- codec:
+	Usage: Optional
+	Value type: <subnode>
+	Definition: codec dai sub-node
+
+- platform:
+	Usage: Optional
+	Value type: <subnode>
+	Definition: platform dai sub-node
+
+- sound-dai:
+	Usage: required
+	Value type: <phandle with arguments>
+	Definition: dai phandle/s and port of CPU/CODEC/PLATFORM node.
+
+Example:
+
+audio {
+	compatible = "qcom,apq8096-sndcard";
+	qcom,model = "DB820c";
+
+	mm1-dai-link {
+		link-name = "MultiMedia1";
+		cpu {
+			sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA1>;
+		};
+	};
+
+	hdmi-dai-link {
+		link-name = "HDMI Playback";
+		cpu {
+			sound-dai = <&q6afe HDMI_RX>;
+		};
+
+		platform {
+			sound-dai = <&q6adm>;
+		};
+
+		codec {
+			sound-dai = <&hdmi 0>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/qcom,q6adm.txt b/Documentation/devicetree/bindings/sound/qcom,q6adm.txt
new file mode 100644
index 000000000000..cb709e5dbc44
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,q6adm.txt
@@ -0,0 +1,33 @@
+Qualcomm Audio Device Manager (Q6ADM) binding
+
+Q6ADM is one of the APR audio service on Q6DSP.
+Please refer to qcom,apr.txt for details of the coommon apr service bindings
+used by the apr service device.
+
+- but must contain the following property:
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6adm-v<MAJOR-NUMBER>.<MINOR-NUMBER>".
+		   Or "qcom,q6adm" where the version number can be queried
+		   from DSP.
+		   example "qcom,q6adm-v2.0"
+
+
+= ADM routing
+"routing" subnode of the ADM node represents adm routing specific configuration
+
+- #sound-dai-cells
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 0
+
+= EXAMPLE
+q6adm@8 {
+	compatible = "qcom,q6adm";
+	reg = <APR_SVC_ADM>;
+	q6routing: routing {
+		#sound-dai-cells = <0>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/qcom,q6afe.txt b/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
new file mode 100644
index 000000000000..bdbf87df8c0b
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
@@ -0,0 +1,172 @@
+Qualcomm Audio Front End (Q6AFE) binding
+
+AFE is one of the APR audio service on Q6DSP
+Please refer to qcom,apr.txt for details of the common apr service bindings
+used by all apr services. Must contain the following properties.
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6afe-v<MAJOR-NUMBER>.<MINOR-NUMBER>"
+		  Or "qcom,q6afe" where the version number can be queried
+		  from DSP.
+		  example "qcom,q6afe"
+
+= AFE DAIs (Digial Audio Interface)
+"dais" subnode of the AFE node. It represents afe dais, each afe dai is a
+subnode of "dais" representing board specific dai setup.
+"dais" node should have following properties followed by dai children.
+
+- #sound-dai-cells
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 1
+
+- #address-cells
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 1
+
+- #size-cells
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 0
+
+== AFE DAI is subnode of "dais" and represent a dai, it includes board specific
+configuration of each dai. Must contain the following properties.
+
+- reg
+	Usage: required
+	Value type: <u32>
+	Definition: Must be dai id
+
+- qcom,sd-lines
+	Usage: required for mi2s interface
+	Value type: <prop-encoded-array>
+	Definition: Must be list of serial data lines used by this dai.
+	should be one or more of the 1-4 sd lines.
+
+ - qcom,tdm-sync-mode:
+	Usage: required for tdm interface
+	Value type: <prop-encoded-array>
+	Definition: Synchronization mode.
+		0 - Short sync bit mode
+		1 - Long sync mode
+		2 - Short sync slot mode
+
+ - qcom,tdm-sync-src:
+	Usage: required for tdm interface
+	Value type: <prop-encoded-array>
+	Definition: Synchronization source.
+		0 - External source
+		1 - Internal source
+
+ - qcom,tdm-data-out:
+	Usage: required for tdm interface
+	Value type: <prop-encoded-array>
+	Definition: Data out signal to drive with other masters.
+		0 - Disable
+		1 - Enable
+
+ - qcom,tdm-invert-sync:
+	Usage: required for tdm interface
+	Value type: <prop-encoded-array>
+	Definition: Invert the sync.
+		0 - Normal
+		1 - Invert
+
+ - qcom,tdm-data-delay:
+	Usage: required for tdm interface
+	Value type: <prop-encoded-array>
+	Definition: Number of bit clock to delay data
+		with respect to sync edge.
+		0 - 0 bit clock cycle
+		1 - 1 bit clock cycle
+		2 - 2 bit clock cycle
+
+ - qcom,tdm-data-align:
+	Usage: required for tdm interface
+	Value type: <prop-encoded-array>
+	Definition: Indicate how data is packed
+		within the slot. For example, 32 slot width in case of
+		sample bit width is 24.
+		0 - MSB
+		1 - LSB
+
+= EXAMPLE
+
+q6afe@4 {
+	compatible = "qcom,q6afe";
+	reg = <APR_SVC_AFE>;
+
+	dais {
+		#sound-dai-cells = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		hdmi@1 {
+			reg = <1>;
+		};
+
+		tdm@24 {
+			reg = <24>;
+			qcom,tdm-sync-mode = <1>:
+			qcom,tdm-sync-src = <1>;
+			qcom,tdm-data-out = <0>;
+			qcom,tdm-invert-sync = <1>;
+			qcom,tdm-data-delay = <1>;
+			qcom,tdm-data-align = <0>;
+
+		};
+
+		tdm@25 {
+			reg = <25>;
+			qcom,tdm-sync-mode = <1>:
+			qcom,tdm-sync-src = <1>;
+			qcom,tdm-data-out = <0>;
+			qcom,tdm-invert-sync = <1>;
+			qcom,tdm-data-delay <1>:
+			qcom,tdm-data-align = <0>;
+		};
+
+		prim-mi2s-rx@16 {
+			reg = <16>;
+			qcom,sd-lines = <1 3>;
+		};
+
+		prim-mi2s-tx@17 {
+			reg = <17>;
+			qcom,sd-lines = <2>;
+		};
+
+		sec-mi2s-rx@18 {
+			reg = <18>;
+			qcom,sd-lines = <1 4>;
+		};
+
+		sec-mi2s-tx@19 {
+			reg = <19>;
+			qcom,sd-lines = <2>;
+		};
+
+		tert-mi2s-rx@20 {
+			reg = <20>;
+			qcom,sd-lines = <2 4>;
+		};
+
+		tert-mi2s-tx@21 {
+			reg = <21>;
+			qcom,sd-lines = <1>;
+		};
+
+		quat-mi2s-rx@22 {
+			reg = <22>;
+			qcom,sd-lines = <1>;
+		};
+
+		quat-mi2s-tx@23 {
+			reg = <23>;
+			qcom,sd-lines = <2>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/qcom,q6asm.txt b/Documentation/devicetree/bindings/sound/qcom,q6asm.txt
new file mode 100644
index 000000000000..2178eb91146f
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,q6asm.txt
@@ -0,0 +1,33 @@
+Qualcomm Audio Stream Manager (Q6ASM) binding
+
+Q6ASM is one of the APR audio service on Q6DSP.
+Please refer to qcom,apr.txt for details of the common apr service bindings
+used by the apr service device.
+
+- but must contain the following property:
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6asm-v<MAJOR-NUMBER>.<MINOR-NUMBER>".
+		    Or "qcom,q6asm" where the version number can be queried
+		    from DSP.
+		    example "qcom,q6asm-v2.0"
+
+= ASM DAIs (Digial Audio Interface)
+"dais" subnode of the ASM node represents dai specific configuration
+
+- #sound-dai-cells
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 1
+
+= EXAMPLE
+
+q6asm@7 {
+	compatible = "qcom,q6asm";
+	reg = <APR_SVC_ASM>;
+	q6asmdai: dais {
+		#sound-dai-cells = <1>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/qcom,q6core.txt b/Documentation/devicetree/bindings/sound/qcom,q6core.txt
new file mode 100644
index 000000000000..7f36ff8bec18
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,q6core.txt
@@ -0,0 +1,21 @@
+Qualcomm ADSP Core service binding
+
+Q6CORE is one of the APR audio service on Q6DSP.
+Please refer to qcom,apr.txt for details of the common apr service bindings
+used by the apr service device.
+
+- but must contain the following property:
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6core-v<MAJOR-NUMBER>.<MINOR-NUMBER>".
+		   Or "qcom,q6core" where the version number can be queried
+		   from DSP.
+		   example "qcom,q6core-v2.0"
+
+= EXAMPLE
+q6core@3 {
+	compatible = "qcom,q6core";
+	reg = <APR_SVC_ADSP_CORE>;
+};
diff --git a/Documentation/devicetree/bindings/sound/rt274.txt b/Documentation/devicetree/bindings/sound/rt274.txt
index e9a6178c78cf..791a1bd767b9 100644
--- a/Documentation/devicetree/bindings/sound/rt274.txt
+++ b/Documentation/devicetree/bindings/sound/rt274.txt
@@ -26,7 +26,7 @@ Pins on the device (for linking into audio routes) for RT274:
 
 Example:
 
-codec: rt274@1c {
+rt274: codec@1c {
 	compatible = "realtek,rt274";
 	reg = <0x1c>;
 	interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
diff --git a/Documentation/devicetree/bindings/sound/rt5514.txt b/Documentation/devicetree/bindings/sound/rt5514.txt
index 4f33b0d96afe..b25ed08c7a5a 100644
--- a/Documentation/devicetree/bindings/sound/rt5514.txt
+++ b/Documentation/devicetree/bindings/sound/rt5514.txt
@@ -32,7 +32,7 @@ Pins on the device (for linking into audio routes) for I2C:
 
 Example:
 
-codec: rt5514@57 {
+rt5514: codec@57 {
 	compatible = "realtek,rt5514";
 	reg = <0x57>;
 };
diff --git a/Documentation/devicetree/bindings/sound/rt5616.txt b/Documentation/devicetree/bindings/sound/rt5616.txt
index e41085818559..540a4bf252e4 100644
--- a/Documentation/devicetree/bindings/sound/rt5616.txt
+++ b/Documentation/devicetree/bindings/sound/rt5616.txt
@@ -26,7 +26,7 @@ Pins on the device (for linking into audio routes) for RT5616:
 
 Example:
 
-codec: rt5616@1b {
+rt5616: codec@1b {
 	compatible = "realtek,rt5616";
 	reg = <0x1b>;
 };
diff --git a/Documentation/devicetree/bindings/sound/rt5640.txt b/Documentation/devicetree/bindings/sound/rt5640.txt
index 57fe64643050..e40e4893eed8 100644
--- a/Documentation/devicetree/bindings/sound/rt5640.txt
+++ b/Documentation/devicetree/bindings/sound/rt5640.txt
@@ -22,6 +22,41 @@ Optional properties:
 
 - realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin.
 
+- realtek,dmic1-data-pin
+  0: dmic1 is not used
+  1: using IN1P pin as dmic1 data pin
+  2: using GPIO3 pin as dmic1 data pin
+
+- realtek,dmic2-data-pin
+  0: dmic2 is not used
+  1: using IN1N pin as dmic2 data pin
+  2: using GPIO4 pin as dmic2 data pin
+
+- realtek,jack-detect-source
+  u32. Valid values:
+  0: jack-detect is not used
+  1: Use GPIO1 for jack-detect
+  2: Use JD1_IN4P for jack-detect
+  3: Use JD2_IN4N for jack-detect
+  4: Use GPIO2 for jack-detect
+  5: Use GPIO3 for jack-detect
+  6: Use GPIO4 for jack-detect
+
+- realtek,jack-detect-not-inverted
+  bool. Normal jack-detect switches give an inverted signal, set this bool
+  in the rare case you've a jack-detect switch which is not inverted.
+
+- realtek,over-current-threshold-microamp
+  u32, micbias over-current detection threshold in µA, valid values are
+  600, 1500 and 2000µA.
+
+- realtek,over-current-scale-factor
+  u32, micbias over-current detection scale-factor, valid values are:
+  0: Scale current by 0.5
+  1: Scale current by 0.75
+  2: Scale current by 1.0
+  3: Scale current by 1.5
+
 Pins on the device (for linking into audio routes) for RT5639/RT5640:
 
   * DMIC1
diff --git a/Documentation/devicetree/bindings/sound/rt5645.txt b/Documentation/devicetree/bindings/sound/rt5645.txt
index 7cee1f518f59..a03f9a872a71 100644
--- a/Documentation/devicetree/bindings/sound/rt5645.txt
+++ b/Documentation/devicetree/bindings/sound/rt5645.txt
@@ -69,4 +69,4 @@ codec: rt5650@1a {
 	realtek,dmic-en = "true";
 	realtek,en-jd-func = "true";
 	realtek,jd-mode = <3>;
-};
\ No newline at end of file
+};
diff --git a/Documentation/devicetree/bindings/sound/rt5651.txt b/Documentation/devicetree/bindings/sound/rt5651.txt
index b85221864cec..a41199a5cd79 100644
--- a/Documentation/devicetree/bindings/sound/rt5651.txt
+++ b/Documentation/devicetree/bindings/sound/rt5651.txt
@@ -50,7 +50,7 @@ Pins on the device (for linking into audio routes) for RT5651:
 
 Example:
 
-codec: rt5651@1a {
+rt5651: codec@1a {
 	compatible = "realtek,rt5651";
 	reg = <0x1a>;
 	realtek,dmic-en = "true";
diff --git a/Documentation/devicetree/bindings/sound/rt5663.txt b/Documentation/devicetree/bindings/sound/rt5663.txt
index 497bcfc58b71..23386446c63d 100644
--- a/Documentation/devicetree/bindings/sound/rt5663.txt
+++ b/Documentation/devicetree/bindings/sound/rt5663.txt
@@ -47,7 +47,7 @@ Pins on the device (for linking into audio routes) for RT5663:
 
 Example:
 
-codec: rt5663@12 {
+rt5663: codec@12 {
 	compatible = "realtek,rt5663";
 	reg = <0x12>;
 	interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
diff --git a/Documentation/devicetree/bindings/sound/rt5668.txt b/Documentation/devicetree/bindings/sound/rt5668.txt
new file mode 100644
index 000000000000..c88b96e7764b
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rt5668.txt
@@ -0,0 +1,50 @@
+RT5668B audio CODEC
+
+This device supports I2C only.
+
+Required properties:
+
+- compatible : "realtek,rt5668b"
+
+- reg : The I2C address of the device.
+
+Optional properties:
+
+- interrupts : The CODEC's interrupt output.
+
+- realtek,dmic1-data-pin
+  0: dmic1 is not used
+  1: using GPIO2 pin as dmic1 data pin
+  2: using GPIO5 pin as dmic1 data pin
+
+- realtek,dmic1-clk-pin
+  0: using GPIO1 pin as dmic1 clock pin
+  1: using GPIO3 pin as dmic1 clock pin
+
+- realtek,jd-src
+  0: No JD is used
+  1: using JD1 as JD source
+
+- realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin.
+
+Pins on the device (for linking into audio routes) for RT5668B:
+
+  * DMIC L1
+  * DMIC R1
+  * IN1P
+  * HPOL
+  * HPOR
+
+Example:
+
+rt5668 {
+	compatible = "realtek,rt5668b";
+	reg = <0x1a>;
+	interrupt-parent = <&gpio>;
+	interrupts = <TEGRA_GPIO(U, 6) GPIO_ACTIVE_HIGH>;
+	realtek,ldo1-en-gpios =
+		<&gpio TEGRA_GPIO(R, 2) GPIO_ACTIVE_HIGH>;
+	realtek,dmic1-data-pin = <1>;
+	realtek,dmic1-clk-pin = <1>;
+	realtek,jd-src = <1>;
+};
diff --git a/Documentation/devicetree/bindings/sound/sgtl5000.txt b/Documentation/devicetree/bindings/sound/sgtl5000.txt
index 9a36c7e2a143..0f214457476f 100644
--- a/Documentation/devicetree/bindings/sound/sgtl5000.txt
+++ b/Documentation/devicetree/bindings/sound/sgtl5000.txt
@@ -39,7 +39,7 @@ VDDIO		1.8V		2.5V		3.3V
 
 Example:
 
-codec: sgtl5000@a {
+sgtl5000: codec@a {
 	compatible = "fsl,sgtl5000";
 	reg = <0x0a>;
 	#sound-dai-cells = <0>;
diff --git a/Documentation/devicetree/bindings/sound/simple-card.txt b/Documentation/devicetree/bindings/sound/simple-card.txt
index 17c13e74667d..a4c72d09cd45 100644
--- a/Documentation/devicetree/bindings/sound/simple-card.txt
+++ b/Documentation/devicetree/bindings/sound/simple-card.txt
@@ -86,6 +86,11 @@ Optional CPU/CODEC subnodes properties:
 					  in dai startup() and disabled with
 					  clk_disable_unprepare() in dai
 					  shutdown().
+					  If a clock is specified and a
+					  multiplication factor is given with
+					  mclk-fs, the clock will be set to the
+					  calculated mclk frequency when the
+					  stream starts.
 - system-clock-direction-out		: specifies clock direction as 'out' on
 					  initialization. It is useful for some aCPUs with
 					  fixed clocks.
diff --git a/Documentation/devicetree/bindings/sound/ti,tas6424.txt b/Documentation/devicetree/bindings/sound/ti,tas6424.txt
index 1c4ada0eef4e..eacb54f34188 100644
--- a/Documentation/devicetree/bindings/sound/ti,tas6424.txt
+++ b/Documentation/devicetree/bindings/sound/ti,tas6424.txt
@@ -6,6 +6,8 @@ Required properties:
 	- compatible: "ti,tas6424" - TAS6424
 	- reg: I2C slave address
 	- sound-dai-cells: must be equal to 0
+	- standby-gpios: GPIO used to shut the TAS6424 down.
+	- mute-gpios: GPIO used to mute all the outputs
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/sound/tscs42xx.txt b/Documentation/devicetree/bindings/sound/tscs42xx.txt
index 2ac2f0996697..7eea32e9d078 100644
--- a/Documentation/devicetree/bindings/sound/tscs42xx.txt
+++ b/Documentation/devicetree/bindings/sound/tscs42xx.txt
@@ -8,9 +8,15 @@ Required Properties:
 	- reg : 	<0x71> for analog mic
 			<0x69> for digital mic
 
+	- clock-names:	Must one of  the following "mclk1", "xtal", "mclk2"
+
+	- clocks:	phandle of the clock that provides the codec sysclk
+
 Example:
 
 wookie: codec@69 {
 	compatible = "tempo,tscs42A2";
 	reg = <0x69>;
+	clock-names = "xtal";
+	clocks = <&audio_xtal>;
 };
diff --git a/Documentation/devicetree/bindings/sound/tscs454.txt b/Documentation/devicetree/bindings/sound/tscs454.txt
new file mode 100644
index 000000000000..3ba3e2d2c206
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/tscs454.txt
@@ -0,0 +1,23 @@
+TSCS454 Audio CODEC
+
+Required Properties:
+
+	- compatible :	"tempo,tscs454"
+
+	- reg : 	<0x69>
+
+	- clock-names:	Must one of  the following "xtal", "mclk1", "mclk2"
+
+	- clocks:	phandle of the clock that provides the codec sysclk
+
+	Note: If clock is not provided then bit clock is assumed
+
+Example:
+
+redwood: codec@69 {
+	#sound-dai-cells = <1>;
+	compatible = "tempo,tscs454";
+	reg = <0x69>;
+	clock-names = "mclk1";
+	clocks = <&audio_mclk>;
+};
diff --git a/Documentation/devicetree/bindings/sound/wm8510.txt b/Documentation/devicetree/bindings/sound/wm8510.txt
index fa1a32b85577..e6b6cc041f89 100644
--- a/Documentation/devicetree/bindings/sound/wm8510.txt
+++ b/Documentation/devicetree/bindings/sound/wm8510.txt
@@ -12,7 +12,7 @@ Required properties:
 
 Example:
 
-codec: wm8510@1a {
+wm8510: codec@1a {
 	compatible = "wlf,wm8510";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8523.txt b/Documentation/devicetree/bindings/sound/wm8523.txt
index 04746186b283..f3a6485f4b8a 100644
--- a/Documentation/devicetree/bindings/sound/wm8523.txt
+++ b/Documentation/devicetree/bindings/sound/wm8523.txt
@@ -10,7 +10,7 @@ Required properties:
 
 Example:
 
-codec: wm8523@1a {
+wm8523: codec@1a {
 	compatible = "wlf,wm8523";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8524.txt b/Documentation/devicetree/bindings/sound/wm8524.txt
index 0f0553563fc1..f6c0c263b135 100644
--- a/Documentation/devicetree/bindings/sound/wm8524.txt
+++ b/Documentation/devicetree/bindings/sound/wm8524.txt
@@ -10,7 +10,7 @@ Required properties:
 
 Example:
 
-codec: wm8524 {
+wm8524: codec {
 	compatible = "wlf,wm8524";
 	wlf,mute-gpios = <&gpio1 8 GPIO_ACTIVE_LOW>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8580.txt b/Documentation/devicetree/bindings/sound/wm8580.txt
index 78fce9b14954..ff3f9f5f2111 100644
--- a/Documentation/devicetree/bindings/sound/wm8580.txt
+++ b/Documentation/devicetree/bindings/sound/wm8580.txt
@@ -10,7 +10,7 @@ Required properties:
 
 Example:
 
-codec: wm8580@1a {
+wm8580: codec@1a {
 	compatible = "wlf,wm8580";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8711.txt b/Documentation/devicetree/bindings/sound/wm8711.txt
index 8ed9998cd23c..c30a1387c4bf 100644
--- a/Documentation/devicetree/bindings/sound/wm8711.txt
+++ b/Documentation/devicetree/bindings/sound/wm8711.txt
@@ -12,7 +12,7 @@ Required properties:
 
 Example:
 
-codec: wm8711@1a {
+wm8711: codec@1a {
 	compatible = "wlf,wm8711";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8728.txt b/Documentation/devicetree/bindings/sound/wm8728.txt
index a8b5c3668e60..a3608b4c78b9 100644
--- a/Documentation/devicetree/bindings/sound/wm8728.txt
+++ b/Documentation/devicetree/bindings/sound/wm8728.txt
@@ -12,7 +12,7 @@ Required properties:
 
 Example:
 
-codec: wm8728@1a {
+wm8728: codec@1a {
 	compatible = "wlf,wm8728";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8731.txt b/Documentation/devicetree/bindings/sound/wm8731.txt
index 236690e99b87..f660d9bb0e69 100644
--- a/Documentation/devicetree/bindings/sound/wm8731.txt
+++ b/Documentation/devicetree/bindings/sound/wm8731.txt
@@ -12,7 +12,7 @@ Required properties:
 
 Example:
 
-codec: wm8731@1a {
+wm8731: codec@1a {
 	compatible = "wlf,wm8731";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8737.txt b/Documentation/devicetree/bindings/sound/wm8737.txt
index 4bc2cea3b140..eda1ec6a7563 100644
--- a/Documentation/devicetree/bindings/sound/wm8737.txt
+++ b/Documentation/devicetree/bindings/sound/wm8737.txt
@@ -12,7 +12,7 @@ Required properties:
 
 Example:
 
-codec: wm8737@1a {
+wm8737: codec@1a {
 	compatible = "wlf,wm8737";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8741.txt b/Documentation/devicetree/bindings/sound/wm8741.txt
index a13315408719..b69e196c741c 100644
--- a/Documentation/devicetree/bindings/sound/wm8741.txt
+++ b/Documentation/devicetree/bindings/sound/wm8741.txt
@@ -21,7 +21,7 @@ Optional properties:
 
 Example:
 
-codec: wm8741@1a {
+wm8741: codec@1a {
 	compatible = "wlf,wm8741";
 	reg = <0x1a>;
 
diff --git a/Documentation/devicetree/bindings/sound/wm8750.txt b/Documentation/devicetree/bindings/sound/wm8750.txt
index 8db239fd5ecd..682f221f6f38 100644
--- a/Documentation/devicetree/bindings/sound/wm8750.txt
+++ b/Documentation/devicetree/bindings/sound/wm8750.txt
@@ -12,7 +12,7 @@ Required properties:
 
 Example:
 
-codec: wm8750@1a {
+wm8750: codec@1a {
 	compatible = "wlf,wm8750";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8753.txt b/Documentation/devicetree/bindings/sound/wm8753.txt
index 8eee61282105..eca9e5a825a9 100644
--- a/Documentation/devicetree/bindings/sound/wm8753.txt
+++ b/Documentation/devicetree/bindings/sound/wm8753.txt
@@ -34,7 +34,7 @@ Pins on the device (for linking into audio routes):
 
 Example:
 
-codec: wm8753@1a {
+wm8753: codec@1a {
 	compatible = "wlf,wm8753";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8770.txt b/Documentation/devicetree/bindings/sound/wm8770.txt
index 866e00ca150b..cac762a1105d 100644
--- a/Documentation/devicetree/bindings/sound/wm8770.txt
+++ b/Documentation/devicetree/bindings/sound/wm8770.txt
@@ -10,7 +10,7 @@ Required properties:
 
 Example:
 
-codec: wm8770@1 {
+wm8770: codec@1 {
 	compatible = "wlf,wm8770";
 	reg = <1>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8776.txt b/Documentation/devicetree/bindings/sound/wm8776.txt
index 3b9ca49abc2b..01173369c3ed 100644
--- a/Documentation/devicetree/bindings/sound/wm8776.txt
+++ b/Documentation/devicetree/bindings/sound/wm8776.txt
@@ -12,7 +12,7 @@ Required properties:
 
 Example:
 
-codec: wm8776@1a {
+wm8776: codec@1a {
 	compatible = "wlf,wm8776";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8804.txt b/Documentation/devicetree/bindings/sound/wm8804.txt
index 6fd124b16496..2c1641c17a91 100644
--- a/Documentation/devicetree/bindings/sound/wm8804.txt
+++ b/Documentation/devicetree/bindings/sound/wm8804.txt
@@ -19,7 +19,7 @@ Optional properties:
 
 Example:
 
-codec: wm8804@1a {
+wm8804: codec@1a {
 	compatible = "wlf,wm8804";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8903.txt b/Documentation/devicetree/bindings/sound/wm8903.txt
index afc51caf1137..6371c2434afe 100644
--- a/Documentation/devicetree/bindings/sound/wm8903.txt
+++ b/Documentation/devicetree/bindings/sound/wm8903.txt
@@ -57,7 +57,7 @@ Pins on the device (for linking into audio routes):
 
 Example:
 
-codec: wm8903@1a {
+wm8903: codec@1a {
 	compatible = "wlf,wm8903";
 	reg = <0x1a>;
 	interrupts = < 347 >;
diff --git a/Documentation/devicetree/bindings/sound/wm8960.txt b/Documentation/devicetree/bindings/sound/wm8960.txt
index 2deb8a3da9c5..6d29ac3750ee 100644
--- a/Documentation/devicetree/bindings/sound/wm8960.txt
+++ b/Documentation/devicetree/bindings/sound/wm8960.txt
@@ -23,7 +23,7 @@ Optional properties:
 
 Example:
 
-codec: wm8960@1a {
+wm8960: codec@1a {
 	compatible = "wlf,wm8960";
 	reg = <0x1a>;
 
diff --git a/Documentation/devicetree/bindings/sound/wm8962.txt b/Documentation/devicetree/bindings/sound/wm8962.txt
index 7f82b59ec8f9..dcfa9a3369fd 100644
--- a/Documentation/devicetree/bindings/sound/wm8962.txt
+++ b/Documentation/devicetree/bindings/sound/wm8962.txt
@@ -24,7 +24,7 @@ Optional properties:
 
 Example:
 
-codec: wm8962@1a {
+wm8962: codec@1a {
 	compatible = "wlf,wm8962";
 	reg = <0x1a>;
 
diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt
index 68c4e8d96bed..4a9dead1b7d3 100644
--- a/Documentation/devicetree/bindings/sound/wm8994.txt
+++ b/Documentation/devicetree/bindings/sound/wm8994.txt
@@ -59,7 +59,7 @@ Optional properties:
 
 Example:
 
-codec: wm8994@1a {
+wm8994: codec@1a {
 	compatible = "wlf,wm8994";
 	reg = <0x1a>;
 
diff --git a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
index 1b596fd38dc4..b957acff57aa 100644
--- a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
@@ -49,19 +49,6 @@ on the SoC (only first trip points defined in DT will be configured):
  - samsung,exynos5433-tmu: 8
  - samsung,exynos7-tmu: 8
 
-Following properties are mandatory (depending on SoC):
-- samsung,tmu_gain: Gain value for internal TMU operation.
-- samsung,tmu_reference_voltage: Value of TMU IP block's reference voltage
-- samsung,tmu_noise_cancel_mode: Mode for noise cancellation
-- samsung,tmu_efuse_value: Default level of temperature - it is needed when
-			   in factory fusing produced wrong value
-- samsung,tmu_min_efuse_value: Minimum temperature fused value
-- samsung,tmu_max_efuse_value: Maximum temperature fused value
-- samsung,tmu_first_point_trim: First point trimming value
-- samsung,tmu_second_point_trim: Second point trimming value
-- samsung,tmu_default_temp_offset: Default temperature offset
-- samsung,tmu_cal_type: Callibration type
-
 ** Optional properties:
 
 - vtmu-supply: This entry is optional and provides the regulator node supplying
@@ -78,7 +65,7 @@ Example 1):
 		clocks = <&clock 383>;
 		clock-names = "tmu_apbif";
 		vtmu-supply = <&tmu_regulator_node>;
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#thermal-sensor-cells = <0>;
 	};
 
 Example 2):
@@ -89,7 +76,7 @@ Example 2):
 		interrupts = <0 58 0>;
 		clocks = <&clock 21>;
 		clock-names = "tmu_apbif";
-		#include "exynos5440-tmu-sensor-conf.dtsi"
+		#thermal-sensor-cells = <0>;
 	};
 
 Example 3): (In case of Exynos5420 "with misplaced TRIMINFO register")
@@ -99,7 +86,7 @@ Example 3): (In case of Exynos5420 "with misplaced TRIMINFO register")
 		interrupts = <0 184 0>;
 		clocks = <&clock 318>, <&clock 318>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#thermal-sensor-cells = <0>;
 	};
 
 	tmu_cpu3: tmu@1006c000 {
@@ -108,7 +95,7 @@ Example 3): (In case of Exynos5420 "with misplaced TRIMINFO register")
 		interrupts = <0 185 0>;
 		clocks = <&clock 318>, <&clock 319>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#thermal-sensor-cells = <0>;
 	};
 
 	tmu_gpu: tmu@100a0000 {
@@ -117,7 +104,7 @@ Example 3): (In case of Exynos5420 "with misplaced TRIMINFO register")
 		interrupts = <0 215 0>;
 		clocks = <&clock 319>, <&clock 318>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#thermal-sensor-cells = <0>;
 	};
 
 Note: For multi-instance tmu each instance should have an alias correctly
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
index 1719d47a5e2f..cc553f0952c5 100644
--- a/Documentation/devicetree/bindings/thermal/thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -55,8 +55,7 @@ of heat dissipation). For example a fan's cooling states correspond to
 the different fan speeds possible. Cooling states are referred to by
 single unsigned integers, where larger numbers mean greater heat
 dissipation. The precise set of cooling states associated with a device
-(as referred to by the cooling-min-level and cooling-max-level
-properties) should be defined in a particular device's binding.
+should be defined in a particular device's binding.
 For more examples of cooling devices, refer to the example sections below.
 
 Required properties:
@@ -69,15 +68,6 @@ Required properties:
 			See Cooling device maps section below for more details
 			on how consumers refer to cooling devices.
 
-Optional properties:
-- cooling-min-level:	An integer indicating the smallest
-  Type: unsigned	cooling state accepted. Typically 0.
-  Size: one cell
-
-- cooling-max-level:	An integer indicating the largest
-  Type: unsigned	cooling state accepted.
-  Size: one cell
-
 * Trip points
 
 The trip node is a node to describe a point in the temperature domain
@@ -226,8 +216,6 @@ cpus {
 			396000  950000
 			198000  850000
 		>;
-		cooling-min-level = <0>;
-		cooling-max-level = <3>;
 		#cooling-cells = <2>; /* min followed by max */
 	};
 	...
@@ -241,8 +229,6 @@ cpus {
 	 */
 	fan0: fan@48 {
 		...
-		cooling-min-level = <0>;
-		cooling-max-level = <9>;
 		#cooling-cells = <2>; /* min followed by max */
 	};
 };
diff --git a/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
new file mode 100644
index 000000000000..ea22dfe485be
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
@@ -0,0 +1,21 @@
+Nuvoton NPCM7xx timer
+
+Nuvoton NPCM7xx have three timer modules, each timer module provides five 24-bit
+timer counters.
+
+Required properties:
+- compatible      : "nuvoton,npcm750-timer" for Poleg NPCM750.
+- reg             : Offset and length of the register set for the device.
+- interrupts      : Contain the timer interrupt with flags for
+                    falling edge.
+- clocks          : phandle of timer reference clock (usually a 25 MHz clock).
+
+Example:
+
+timer@f0008000 {
+    compatible = "nuvoton,npcm750-timer";
+    interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+    reg = <0xf0008000 0x50>;
+    clocks = <&clk NPCM7XX_CLK_TIMER>;
+};
+
diff --git a/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt b/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
index b4aa7ddb5b13..f82087b220f4 100644
--- a/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
+++ b/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
@@ -15,7 +15,7 @@ Required properties:
 - interrupts :	Should be the clock event device interrupt.
 - clocks :	The clocks provided by the SoC to drive the timer, must contain
 		an entry for each entry in clock-names.
-- clock-names : Must include the following entries: "igp" and "per".
+- clock-names : Must include the following entries: "ipg" and "per".
 
 Example:
 tpm5: tpm@40260000 {
diff --git a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
index 0e03344e2e8b..2e9318151df7 100644
--- a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
+++ b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
@@ -76,6 +76,10 @@ Optional properties:
   needs to make sure it does not send more than 90%
   maximum_periodic_data_per_frame. The use case is multiple transactions, but
   less frame rate.
+- mux-controls: The mux control for toggling host/device output of this
+  controller. It's expected that a mux state of 0 indicates device mode and a
+  mux state of 1 indicates host mode.
+- mux-control-names: Shall be "usb_switch" if mux-controls is specified.
 
 i.mx specific properties
 - fsl,usbmisc: phandler of non-core register device, with one
@@ -102,4 +106,6 @@ Example:
 		rx-burst-size-dword = <0x10>;
 		extcon = <0>, <&usb_id>;
 		phy-clkgate-delay-us = <400>;
+		mux-controls = <&usb_switch>;
+		mux-control-names = "usb_switch";
 	};
diff --git a/Documentation/devicetree/bindings/usb/dwc3.txt b/Documentation/devicetree/bindings/usb/dwc3.txt
index 0dbd3083e7dd..7f13ebef06cb 100644
--- a/Documentation/devicetree/bindings/usb/dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/dwc3.txt
@@ -7,6 +7,26 @@ Required properties:
  - compatible: must be "snps,dwc3"
  - reg : Address and length of the register set for the device
  - interrupts: Interrupts used by the dwc3 controller.
+ - clock-names: should contain "ref", "bus_early", "suspend"
+ - clocks: list of phandle and clock specifier pairs corresponding to
+           entries in the clock-names property.
+
+Exception for clocks:
+  clocks are optional if the parent node (i.e. glue-layer) is compatible to
+  one of the following:
+    "amlogic,meson-axg-dwc3"
+    "amlogic,meson-gxl-dwc3"
+    "cavium,octeon-7130-usb-uctl"
+    "qcom,dwc3"
+    "samsung,exynos5250-dwusb3"
+    "samsung,exynos7-dwusb3"
+    "sprd,sc9860-dwc3"
+    "st,stih407-dwc3"
+    "ti,am437x-dwc3"
+    "ti,dwc3"
+    "ti,keystone-dwc3"
+    "rockchip,rk3399-dwc3"
+    "xlnx,zynqmp-dwc3"
 
 Optional properties:
  - usb-phy : array of phandle for the PHY device.  The first element
@@ -15,6 +35,7 @@ Optional properties:
  - phys: from the *Generic PHY* bindings
  - phy-names: from the *Generic PHY* bindings; supported names are "usb2-phy"
 	or "usb3-phy".
+ - resets: a single pair of phandle and reset specifier
  - snps,usb3_lpm_capable: determines if platform is USB3 LPM capable
  - snps,disable_scramble_quirk: true when SW should disable data scrambling.
 	Only really useful for FPGA builds.
diff --git a/Documentation/devicetree/bindings/usb/fcs,fusb302.txt b/Documentation/devicetree/bindings/usb/fcs,fusb302.txt
index 472facfa5a71..6087dc7f209e 100644
--- a/Documentation/devicetree/bindings/usb/fcs,fusb302.txt
+++ b/Documentation/devicetree/bindings/usb/fcs,fusb302.txt
@@ -6,12 +6,6 @@ Required properties :
 - interrupts             : Interrupt specifier
 
 Optional properties :
-- fcs,max-sink-microvolt : Maximum voltage to negotiate when configured as sink
-- fcs,max-sink-microamp  : Maximum current to negotiate when configured as sink
-- fcs,max-sink-microwatt : Maximum power to negotiate when configured as sink
-			   If this is less then max-sink-microvolt *
-			   max-sink-microamp then the configured current will
-			   be clamped.
 - fcs,operating-sink-microwatt :
 			   Minimum amount of power accepted from a sink
 			   when negotiating
diff --git a/Documentation/devicetree/bindings/usb/hisilicon,histb-xhci.txt b/Documentation/devicetree/bindings/usb/hisilicon,histb-xhci.txt
new file mode 100644
index 000000000000..f4633496b122
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/hisilicon,histb-xhci.txt
@@ -0,0 +1,45 @@
+HiSilicon STB xHCI
+
+The device node for HiSilicon STB xHCI host controller
+
+Required properties:
+ - compatible: should be "hisilicon,hi3798cv200-xhci"
+ - reg: specifies physical base address and size of the registers
+ - interrupts : interrupt used by the controller
+ - clocks: a list of phandle + clock-specifier pairs, one for each
+	entry in clock-names
+ - clock-names: must contain
+	"bus": for bus clock
+	"utmi": for utmi clock
+	"pipe": for pipe clock
+	"suspend": for suspend clock
+ - resets: a list of phandle and reset specifier pairs as listed in
+	reset-names property.
+ - reset-names: must contain
+	"soft": for soft reset
+ - phys: a list of phandle + phy specifier pairs
+ - phy-names: must contain at least one of following:
+	"inno": for inno phy
+	"combo": for combo phy
+
+Optional properties:
+  - usb2-lpm-disable: indicate if we don't want to enable USB2 HW LPM
+  - usb3-lpm-capable: determines if platform is USB3 LPM capable
+  - imod-interval-ns: default interrupt moderation interval is 40000ns
+
+Example:
+
+xhci0: xchi@f98a0000 {
+	compatible = "hisilicon,hi3798cv200-xhci";
+	reg = <0xf98a0000 0x10000>;
+	interrupts = <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&crg HISTB_USB3_BUS_CLK>,
+		 <&crg HISTB_USB3_UTMI_CLK>,
+		 <&crg HISTB_USB3_PIPE_CLK>,
+		 <&crg HISTB_USB3_SUSPEND_CLK>;
+	clock-names = "bus", "utmi", "pipe", "suspend";
+	resets = <&crg 0xb0 12>;
+	reset-names = "soft";
+	phys = <&usb2_phy1_port1 0>, <&combphy0 PHY_TYPE_USB3>;
+	phy-names = "inno", "combo";
+};
diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.txt b/Documentation/devicetree/bindings/usb/qcom,dwc3.txt
index bc8a2fa5d2bf..95afdcf3c337 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.txt
@@ -1,54 +1,95 @@
 Qualcomm SuperSpeed DWC3 USB SoC controller
 
 Required properties:
-- compatible:	should contain "qcom,dwc3"
+- compatible:		Compatible list, contains
+			"qcom,dwc3"
+			"qcom,msm8996-dwc3" for msm8996 SOC.
+			"qcom,sdm845-dwc3" for sdm845 SOC.
+- reg:			Offset and length of register set for QSCRATCH wrapper
+- power-domains:	specifies a phandle to PM domain provider node
 - clocks:		A list of phandle + clock-specifier pairs for the
 				clocks listed in clock-names
-- clock-names:	Should contain the following:
+- clock-names:		Should contain the following:
   "core"		Master/Core clock, have to be >= 125 MHz for SS
 				operation and >= 60MHz for HS operation
+  "mock_utmi"		Mock utmi clock needed for ITP/SOF generation in
+				host mode. Its frequency should be 19.2MHz.
+  "sleep"		Sleep clock, used for wakeup when USB3 core goes
+				into low power mode (U3).
 
 Optional clocks:
-  "iface"		System bus AXI clock.  Not present on all platforms
-  "sleep"		Sleep clock, used when USB3 core goes into low
-				power mode (U3).
+  "iface"		System bus AXI clock.
+			Not present on "qcom,msm8996-dwc3" compatible.
+  "cfg_noc"		System Config NOC clock.
+			Not present on "qcom,msm8996-dwc3" compatible.
+- assigned-clocks:	Should be:
+				MOCK_UTMI_CLK
+				MASTER_CLK
+- assigned-clock-rates: Should be:
+                                19.2Mhz (192000000) for MOCK_UTMI_CLK
+                                >=125Mhz (125000000) for MASTER_CLK in SS mode
+                                >=60Mhz (60000000) for MASTER_CLK in HS mode
+
+Optional properties:
+- resets:		Phandle to reset control that resets core and wrapper.
+- interrupts:		specifies interrupts from controller wrapper used
+			to wakeup from low power/susepnd state.	Must contain
+			one or more entry for interrupt-names property
+- interrupt-names:	Must include the following entries:
+			- "hs_phy_irq": The interrupt that is asserted when a
+			   wakeup event is received on USB2 bus
+			- "ss_phy_irq": The interrupt that is asserted when a
+			   wakeup event is received on USB3 bus
+			- "dm_hs_phy_irq" and "dp_hs_phy_irq": Separate
+			   interrupts for any wakeup event on DM and DP lines
+- qcom,select-utmi-as-pipe-clk: if present, disable USB3 pipe_clk requirement.
+				Used when dwc3 operates without SSPHY and only
+				HS/FS/LS modes are supported.
 
 Required child node:
 A child node must exist to represent the core DWC3 IP block. The name of
 the node is not important. The content of the node is defined in dwc3.txt.
 
 Phy documentation is provided in the following places:
-Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt
+Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt   - USB3 QMP PHY
+Documentation/devicetree/bindings/phy/qcom-qusb2-phy.txt - USB2 QUSB2 PHY
 
 Example device nodes:
 
 		hs_phy: phy@100f8800 {
-			compatible = "qcom,dwc3-hs-usb-phy";
-			reg = <0x100f8800 0x30>;
-			clocks = <&gcc USB30_0_UTMI_CLK>;
-			clock-names = "ref";
-			#phy-cells = <0>;
-
+			compatible = "qcom,qusb2-v2-phy";
+			...
 		};
 
 		ss_phy: phy@100f8830 {
-			compatible = "qcom,dwc3-ss-usb-phy";
-			reg = <0x100f8830 0x30>;
-			clocks = <&gcc USB30_0_MASTER_CLK>;
-			clock-names = "ref";
-			#phy-cells = <0>;
-
+			compatible = "qcom,qmp-v3-usb3-phy";
+			...
 		};
 
-		usb3_0: usb30@0 {
+		usb3_0: usb30@a6f8800 {
 			compatible = "qcom,dwc3";
+			reg = <0xa6f8800 0x400>;
 			#address-cells = <1>;
 			#size-cells = <1>;
-			clocks = <&gcc USB30_0_MASTER_CLK>;
-			clock-names = "core";
-
 			ranges;
 
+			interrupts = <0 131 0>, <0 486 0>, <0 488 0>, <0 489 0>;
+			interrupt-names = "hs_phy_irq", "ss_phy_irq",
+				  "dm_hs_phy_irq", "dp_hs_phy_irq";
+
+			clocks = <&gcc GCC_USB30_PRIM_MASTER_CLK>,
+				<&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>,
+				<&gcc GCC_USB30_PRIM_SLEEP_CLK>;
+			clock-names = "core", "mock_utmi", "sleep";
+
+			assigned-clocks = <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>,
+					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
+			assigned-clock-rates = <19200000>, <133000000>;
+
+			resets = <&gcc GCC_USB30_PRIM_BCR>;
+			reset-names = "core_reset";
+			power-domains = <&gcc USB30_PRIM_GDSC>;
+			qcom,select-utmi-as-pipe-clk;
 
 			dwc3@10000000 {
 				compatible = "snps,dwc3";
diff --git a/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt b/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt
new file mode 100644
index 000000000000..09e847e92e5e
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt
@@ -0,0 +1,17 @@
+Richtek RT1711H TypeC PD Controller.
+
+Required properties:
+ - compatible : Must be "richtek,rt1711h".
+ - reg : Must be 0x4e, it's slave address of RT1711H.
+ - interrupt-parent : the phandle for the interrupt controller that
+   provides interrupts for this device.
+ - interrupts : <a b> where a is the interrupt number and b represents an
+   encoding of the sense and level information for the interrupt.
+
+Example :
+rt1711h@4e {
+	compatible = "richtek,rt1711h";
+	reg = <0x4e>;
+	interrupt-parent = <&gpio26>;
+	interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+};
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
index c4c00dff4b56..bd1dd316fb23 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -28,7 +28,10 @@ Required properties:
   - interrupts: one XHCI interrupt should be described here.
 
 Optional properties:
-  - clocks: reference to a clock
+  - clocks: reference to the clocks
+  - clock-names: mandatory if there is a second clock, in this case
+    the name must be "core" for the first clock and "reg" for the
+    second one
   - usb2-lpm-disable: indicate if we don't want to enable USB2 HW LPM
   - usb3-lpm-capable: determines if platform is USB3 LPM capable
   - quirk-broken-port-ped: set if the controller has broken port disable mechanism
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index b5f978a4cac6..36003832c2a8 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -75,6 +75,7 @@ cnxt	Conexant Systems, Inc.
 compulab	CompuLab Ltd.
 cortina	Cortina Systems, Inc.
 cosmic	Cosmic Circuits
+crane	Crane Connectivity Solutions
 creative	Creative Technology Ltd
 crystalfontz	Crystalfontz America, Inc.
 cubietech	Cubietech, Ltd.
@@ -182,6 +183,7 @@ karo	Ka-Ro electronics GmbH
 keithkoep	Keith & Koep GmbH
 keymile	Keymile GmbH
 khadas	Khadas
+kiebackpeter    Kieback & Peter GmbH
 kinetic Kinetic Technologies
 kingnovel	Kingnovel Technology Co., Ltd.
 kosagi	Sutajio Ko-Usagi PTE Ltd.
diff --git a/Documentation/devicetree/overlay-notes.txt b/Documentation/devicetree/overlay-notes.txt
index a4feb6dde8cd..725fb8d255c1 100644
--- a/Documentation/devicetree/overlay-notes.txt
+++ b/Documentation/devicetree/overlay-notes.txt
@@ -98,6 +98,14 @@ Finally, if you need to remove all overlays in one-go, just call
 of_overlay_remove_all() which will remove every single one in the correct
 order.
 
+In addition, there is the option to register notifiers that get called on
+overlay operations. See of_overlay_notifier_register/unregister and
+enum of_overlay_notify_action for details.
+
+Note that a notifier callback is not supposed to store pointers to a device
+tree node or its content beyond OF_OVERLAY_POST_REMOVE corresponding to the
+respective node it received.
+
 Overlay DTS Format
 ------------------
 
diff --git a/Documentation/doc-guide/parse-headers.rst b/Documentation/doc-guide/parse-headers.rst
index 96a0423d5dba..82a3e43b6864 100644
--- a/Documentation/doc-guide/parse-headers.rst
+++ b/Documentation/doc-guide/parse-headers.rst
@@ -177,14 +177,14 @@ BUGS
 ****
 
 
-Report bugs to Mauro Carvalho Chehab <mchehab@s-opensource.com>
+Report bugs to Mauro Carvalho Chehab <mchehab@kernel.org>
 
 
 COPYRIGHT
 *********
 
 
-Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.
+Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab+samsung@kernel.org>.
 
 License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.
 
diff --git a/Documentation/clk.txt b/Documentation/driver-api/clk.rst
index 511628bb3d3a..511628bb3d3a 100644
--- a/Documentation/clk.txt
+++ b/Documentation/driver-api/clk.rst
diff --git a/Documentation/driver-api/device_connection.rst b/Documentation/driver-api/device_connection.rst
index affbc5566ab0..ba364224c349 100644
--- a/Documentation/driver-api/device_connection.rst
+++ b/Documentation/driver-api/device_connection.rst
@@ -40,4 +40,4 @@ API
 ---
 
 .. kernel-doc:: drivers/base/devcon.c
-   : functions: device_connection_find_match device_connection_find device_connection_add device_connection_remove
+   :functions: device_connection_find_match device_connection_find device_connection_add device_connection_remove
diff --git a/Documentation/driver-api/firmware/fallback-mechanisms.rst b/Documentation/driver-api/firmware/fallback-mechanisms.rst
index f353783ae0be..d35fed65eae9 100644
--- a/Documentation/driver-api/firmware/fallback-mechanisms.rst
+++ b/Documentation/driver-api/firmware/fallback-mechanisms.rst
@@ -72,9 +72,12 @@ the firmware requested, and establishes it in the device hierarchy by
 associating the device used to make the request as the device's parent.
 The sysfs directory's file attributes are defined and controlled through
 the new device's class (firmware_class) and group (fw_dev_attr_groups).
-This is actually where the original firmware_class.c file name comes from,
-as originally the only firmware loading mechanism available was the
-mechanism we now use as a fallback mechanism.
+This is actually where the original firmware_class module name came from,
+given that originally the only firmware loading mechanism available was the
+mechanism we now use as a fallback mechanism, which registers a struct class
+firmware_class. Because the attributes exposed are part of the module name, the
+module name firmware_class cannot be renamed in the future, to ensure backward
+compatibility with old userspace.
 
 To load firmware using the sysfs interface we expose a loading indicator,
 and a file upload firmware into:
@@ -83,7 +86,7 @@ and a file upload firmware into:
   * /sys/$DEVPATH/data
 
 To upload firmware you will echo 1 onto the loading file to indicate
-you are loading firmware. You then cat the firmware into the data file,
+you are loading firmware. You then write the firmware into the data file,
 and you notify the kernel the firmware is ready by echo'ing 0 onto
 the loading file.
 
@@ -136,7 +139,8 @@ by kobject uevents. This is specially exacerbated due to the fact that most
 distributions today disable CONFIG_FW_LOADER_USER_HELPER_FALLBACK.
 
 Refer to do_firmware_uevent() for details of the kobject event variables
-setup. Variables passwdd with a kobject add event:
+setup. The variables currently passed to userspace with a "kobject add"
+event are:
 
 * FIRMWARE=firmware name
 * TIMEOUT=timeout value
diff --git a/Documentation/driver-api/firmware/firmware_cache.rst b/Documentation/driver-api/firmware/firmware_cache.rst
index 2210e5bfb332..c2e69d9c6bf1 100644
--- a/Documentation/driver-api/firmware/firmware_cache.rst
+++ b/Documentation/driver-api/firmware/firmware_cache.rst
@@ -29,8 +29,8 @@ Some implementation details about the firmware cache setup:
 * If an asynchronous call is used the firmware cache is only set up for a
   device if if the second argument (uevent) to request_firmware_nowait() is
   true. When uevent is true it requests that a kobject uevent be sent to
-  userspace for the firmware request. For details refer to the Fackback
-  mechanism documented below.
+  userspace for the firmware request through the sysfs fallback mechanism
+  if the firmware file is not found.
 
 * If the firmware cache is determined to be needed as per the above two
   criteria the firmware cache is setup by adding a devres entry for the
diff --git a/Documentation/driver-api/firmware/request_firmware.rst b/Documentation/driver-api/firmware/request_firmware.rst
index cf4516dfbf96..f62bdcbfed5b 100644
--- a/Documentation/driver-api/firmware/request_firmware.rst
+++ b/Documentation/driver-api/firmware/request_firmware.rst
@@ -17,17 +17,22 @@ an error is returned.
 
 request_firmware
 ----------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
    :functions: request_firmware
 
+firmware_request_nowarn
+-----------------------
+.. kernel-doc:: drivers/base/firmware_loader/main.c
+   :functions: firmware_request_nowarn
+
 request_firmware_direct
 -----------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
    :functions: request_firmware_direct
 
 request_firmware_into_buf
 -------------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
    :functions: request_firmware_into_buf
 
 Asynchronous firmware requests
@@ -41,7 +46,7 @@ in atomic contexts.
 
 request_firmware_nowait
 -----------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
    :functions: request_firmware_nowait
 
 Special optimizations on reboot
@@ -50,12 +55,12 @@ Special optimizations on reboot
 Some devices have an optimization in place to enable the firmware to be
 retained during system reboot. When such optimizations are used the driver
 author must ensure the firmware is still available on resume from suspend,
-this can be done with firmware_request_cache() insted of requesting for the
-firmare to be loaded.
+this can be done with firmware_request_cache() instead of requesting for the
+firmware to be loaded.
 
 firmware_request_cache()
------------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+------------------------
+.. kernel-doc:: drivers/base/firmware_loader/main.c
    :functions: firmware_request_cache
 
 request firmware API expected driver use
diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst
new file mode 100644
index 000000000000..2c2aaca894bf
--- /dev/null
+++ b/Documentation/driver-api/fpga/fpga-bridge.rst
@@ -0,0 +1,49 @@
+FPGA Bridge
+===========
+
+API to implement a new FPGA bridge
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: include/linux/fpga/fpga-bridge.h
+   :functions: fpga_bridge
+
+.. kernel-doc:: include/linux/fpga/fpga-bridge.h
+   :functions: fpga_bridge_ops
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_create
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_free
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_register
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_unregister
+
+API to control an FPGA bridge
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+You probably won't need these directly.  FPGA regions should handle this.
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: of_fpga_bridge_get
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_get
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_put
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_get_to_list
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: of_fpga_bridge_get_to_list
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_enable
+
+.. kernel-doc:: drivers/fpga/fpga-bridge.c
+   :functions: fpga_bridge_disable
diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst
new file mode 100644
index 000000000000..bcf2dd24e179
--- /dev/null
+++ b/Documentation/driver-api/fpga/fpga-mgr.rst
@@ -0,0 +1,220 @@
+FPGA Manager
+============
+
+Overview
+--------
+
+The FPGA manager core exports a set of functions for programming an FPGA with
+an image.  The API is manufacturer agnostic.  All manufacturer specifics are
+hidden away in a low level driver which registers a set of ops with the core.
+The FPGA image data itself is very manufacturer specific, but for our purposes
+it's just binary data.  The FPGA manager core won't parse it.
+
+The FPGA image to be programmed can be in a scatter gather list, a single
+contiguous buffer, or a firmware file.  Because allocating contiguous kernel
+memory for the buffer should be avoided, users are encouraged to use a scatter
+gather list instead if possible.
+
+The particulars for programming the image are presented in a structure (struct
+fpga_image_info).  This struct contains parameters such as pointers to the
+FPGA image as well as image-specific particulars such as whether the image was
+built for full or partial reconfiguration.
+
+How to support a new FPGA device
+--------------------------------
+
+To add another FPGA manager, write a driver that implements a set of ops.  The
+probe function calls fpga_mgr_register(), such as::
+
+	static const struct fpga_manager_ops socfpga_fpga_ops = {
+		.write_init = socfpga_fpga_ops_configure_init,
+		.write = socfpga_fpga_ops_configure_write,
+		.write_complete = socfpga_fpga_ops_configure_complete,
+		.state = socfpga_fpga_ops_state,
+	};
+
+	static int socfpga_fpga_probe(struct platform_device *pdev)
+	{
+		struct device *dev = &pdev->dev;
+		struct socfpga_fpga_priv *priv;
+		struct fpga_manager *mgr;
+		int ret;
+
+		priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+		if (!priv)
+			return -ENOMEM;
+
+		/*
+		 * do ioremaps, get interrupts, etc. and save
+		 * them in priv
+		 */
+
+		mgr = fpga_mgr_create(dev, "Altera SOCFPGA FPGA Manager",
+				      &socfpga_fpga_ops, priv);
+		if (!mgr)
+			return -ENOMEM;
+
+		platform_set_drvdata(pdev, mgr);
+
+		ret = fpga_mgr_register(mgr);
+		if (ret)
+			fpga_mgr_free(mgr);
+
+		return ret;
+	}
+
+	static int socfpga_fpga_remove(struct platform_device *pdev)
+	{
+		struct fpga_manager *mgr = platform_get_drvdata(pdev);
+
+		fpga_mgr_unregister(mgr);
+
+		return 0;
+	}
+
+
+The ops will implement whatever device specific register writes are needed to
+do the programming sequence for this particular FPGA.  These ops return 0 for
+success or negative error codes otherwise.
+
+The programming sequence is::
+ 1. .write_init
+ 2. .write or .write_sg (may be called once or multiple times)
+ 3. .write_complete
+
+The .write_init function will prepare the FPGA to receive the image data.  The
+buffer passed into .write_init will be atmost .initial_header_size bytes long,
+if the whole bitstream is not immediately available then the core code will
+buffer up at least this much before starting.
+
+The .write function writes a buffer to the FPGA. The buffer may be contain the
+whole FPGA image or may be a smaller chunk of an FPGA image.  In the latter
+case, this function is called multiple times for successive chunks. This interface
+is suitable for drivers which use PIO.
+
+The .write_sg version behaves the same as .write except the input is a sg_table
+scatter list. This interface is suitable for drivers which use DMA.
+
+The .write_complete function is called after all the image has been written
+to put the FPGA into operating mode.
+
+The ops include a .state function which will read the hardware FPGA manager and
+return a code of type enum fpga_mgr_states.  It doesn't result in a change in
+hardware state.
+
+How to write an image buffer to a supported FPGA
+------------------------------------------------
+
+Some sample code::
+
+	#include <linux/fpga/fpga-mgr.h>
+
+	struct fpga_manager *mgr;
+	struct fpga_image_info *info;
+	int ret;
+
+	/*
+	 * Get a reference to FPGA manager.  The manager is not locked, so you can
+	 * hold onto this reference without it preventing programming.
+	 *
+	 * This example uses the device node of the manager.  Alternatively, use
+	 * fpga_mgr_get(dev) instead if you have the device.
+	 */
+	mgr = of_fpga_mgr_get(mgr_node);
+
+	/* struct with information about the FPGA image to program. */
+	info = fpga_image_info_alloc(dev);
+
+	/* flags indicates whether to do full or partial reconfiguration */
+	info->flags = FPGA_MGR_PARTIAL_RECONFIG;
+
+	/*
+	 * At this point, indicate where the image is. This is pseudo-code; you're
+	 * going to use one of these three.
+	 */
+	if (image is in a scatter gather table) {
+
+		info->sgt = [your scatter gather table]
+
+	} else if (image is in a buffer) {
+
+		info->buf = [your image buffer]
+		info->count = [image buffer size]
+
+	} else if (image is in a firmware file) {
+
+		info->firmware_name = devm_kstrdup(dev, firmware_name, GFP_KERNEL);
+
+	}
+
+	/* Get exclusive control of FPGA manager */
+	ret = fpga_mgr_lock(mgr);
+
+	/* Load the buffer to the FPGA */
+	ret = fpga_mgr_buf_load(mgr, &info, buf, count);
+
+	/* Release the FPGA manager */
+	fpga_mgr_unlock(mgr);
+	fpga_mgr_put(mgr);
+
+	/* Deallocate the image info if you're done with it */
+	fpga_image_info_free(info);
+
+API for implementing a new FPGA Manager driver
+----------------------------------------------
+
+.. kernel-doc:: include/linux/fpga/fpga-mgr.h
+   :functions: fpga_manager
+
+.. kernel-doc:: include/linux/fpga/fpga-mgr.h
+   :functions: fpga_manager_ops
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_create
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_free
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_register
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_unregister
+
+API for programming a FPGA
+--------------------------
+
+.. kernel-doc:: include/linux/fpga/fpga-mgr.h
+   :functions: fpga_image_info
+
+.. kernel-doc:: include/linux/fpga/fpga-mgr.h
+   :functions: fpga_mgr_states
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_image_info_alloc
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_image_info_free
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: of_fpga_mgr_get
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_get
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_put
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_lock
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_unlock
+
+.. kernel-doc:: include/linux/fpga/fpga-mgr.h
+   :functions: fpga_mgr_states
+
+Note - use :c:func:`fpga_region_program_fpga()` instead of :c:func:`fpga_mgr_load()`
+
+.. kernel-doc:: drivers/fpga/fpga-mgr.c
+   :functions: fpga_mgr_load
diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst
new file mode 100644
index 000000000000..f89e4a311722
--- /dev/null
+++ b/Documentation/driver-api/fpga/fpga-region.rst
@@ -0,0 +1,102 @@
+FPGA Region
+===========
+
+Overview
+--------
+
+This document is meant to be an brief overview of the FPGA region API usage.  A
+more conceptual look at regions can be found in the Device Tree binding
+document [#f1]_.
+
+For the purposes of this API document, let's just say that a region associates
+an FPGA Manager and a bridge (or bridges) with a reprogrammable region of an
+FPGA or the whole FPGA.  The API provides a way to register a region and to
+program a region.
+
+Currently the only layer above fpga-region.c in the kernel is the Device Tree
+support (of-fpga-region.c) described in [#f1]_.  The DT support layer uses regions
+to program the FPGA and then DT to handle enumeration.  The common region code
+is intended to be used by other schemes that have other ways of accomplishing
+enumeration after programming.
+
+An fpga-region can be set up to know the following things:
+
+ * which FPGA manager to use to do the programming
+
+ * which bridges to disable before programming and enable afterwards.
+
+Additional info needed to program the FPGA image is passed in the struct
+fpga_image_info including:
+
+ * pointers to the image as either a scatter-gather buffer, a contiguous
+   buffer, or the name of firmware file
+
+ * flags indicating specifics such as whether the image if for partial
+   reconfiguration.
+
+How to program a FPGA using a region
+------------------------------------
+
+First, allocate the info struct::
+
+	info = fpga_image_info_alloc(dev);
+	if (!info)
+		return -ENOMEM;
+
+Set flags as needed, i.e.::
+
+	info->flags |= FPGA_MGR_PARTIAL_RECONFIG;
+
+Point to your FPGA image, such as::
+
+	info->sgt = &sgt;
+
+Add info to region and do the programming::
+
+	region->info = info;
+	ret = fpga_region_program_fpga(region);
+
+:c:func:`fpga_region_program_fpga()` operates on info passed in the
+fpga_image_info (region->info).  This function will attempt to:
+
+ * lock the region's mutex
+ * lock the region's FPGA manager
+ * build a list of FPGA bridges if a method has been specified to do so
+ * disable the bridges
+ * program the FPGA
+ * re-enable the bridges
+ * release the locks
+
+Then you will want to enumerate whatever hardware has appeared in the FPGA.
+
+How to add a new FPGA region
+----------------------------
+
+An example of usage can be seen in the probe function of [#f2]_.
+
+.. [#f1] ../devicetree/bindings/fpga/fpga-region.txt
+.. [#f2] ../../drivers/fpga/of-fpga-region.c
+
+API to program a FGPA
+---------------------
+
+.. kernel-doc:: drivers/fpga/fpga-region.c
+   :functions: fpga_region_program_fpga
+
+API to add a new FPGA region
+----------------------------
+
+.. kernel-doc:: include/linux/fpga/fpga-region.h
+   :functions: fpga_region
+
+.. kernel-doc:: drivers/fpga/fpga-region.c
+   :functions: fpga_region_create
+
+.. kernel-doc:: drivers/fpga/fpga-region.c
+   :functions: fpga_region_free
+
+.. kernel-doc:: drivers/fpga/fpga-region.c
+   :functions: fpga_region_register
+
+.. kernel-doc:: drivers/fpga/fpga-region.c
+   :functions: fpga_region_unregister
diff --git a/Documentation/driver-api/fpga/index.rst b/Documentation/driver-api/fpga/index.rst
new file mode 100644
index 000000000000..c51e5ebd544a
--- /dev/null
+++ b/Documentation/driver-api/fpga/index.rst
@@ -0,0 +1,13 @@
+==============
+FPGA Subsystem
+==============
+
+:Author: Alan Tull
+
+.. toctree::
+   :maxdepth: 2
+
+   intro
+   fpga-mgr
+   fpga-bridge
+   fpga-region
diff --git a/Documentation/driver-api/fpga/intro.rst b/Documentation/driver-api/fpga/intro.rst
new file mode 100644
index 000000000000..51cd81dbb4dc
--- /dev/null
+++ b/Documentation/driver-api/fpga/intro.rst
@@ -0,0 +1,54 @@
+Introduction
+============
+
+The FPGA subsystem supports reprogramming FPGAs dynamically under
+Linux.  Some of the core intentions of the FPGA subsystems are:
+
+* The FPGA subsystem is vendor agnostic.
+
+* The FPGA subsystem separates upper layers (userspace interfaces and
+  enumeration) from lower layers that know how to program a specific
+  FPGA.
+
+* Code should not be shared between upper and lower layers.  This
+  should go without saying.  If that seems necessary, there's probably
+  framework functionality that that can be added that will benefit
+  other users.  Write the linux-fpga mailing list and maintainers and
+  seek out a solution that expands the framework for broad reuse.
+
+* Generally, when adding code, think of the future.  Plan for re-use.
+
+The framework in the kernel is divided into:
+
+FPGA Manager
+------------
+
+If you are adding a new FPGA or a new method of programming a FPGA,
+this is the subsystem for you.  Low level FPGA manager drivers contain
+the knowledge of how to program a specific device.  This subsystem
+includes the framework in fpga-mgr.c and the low level drivers that
+are registered with it.
+
+FPGA Bridge
+-----------
+
+FPGA Bridges prevent spurious signals from going out of a FPGA or a
+region of a FPGA during programming.  They are disabled before
+programming begins and re-enabled afterwards.  An FPGA bridge may be
+actual hard hardware that gates a bus to a cpu or a soft ("freeze")
+bridge in FPGA fabric that surrounds a partial reconfiguration region
+of an FPGA.  This subsystem includes fpga-bridge.c and the low level
+drivers that are registered with it.
+
+FPGA Region
+-----------
+
+If you are adding a new interface to the FPGA framework, add it on top
+of a FPGA region to allow the most reuse of your interface.
+
+The FPGA Region framework (fpga-region.c) associates managers and
+bridges as reconfigurable regions.  A region may refer to the whole
+FPGA in full reconfiguration or to a partial reconfiguration region.
+
+The Device Tree FPGA Region support (of-fpga-region.c) handles
+reprogramming FPGAs when device tree overlays are applied.
diff --git a/Documentation/driver-api/gpio/driver.rst b/Documentation/driver-api/gpio/driver.rst
index 505ee906d7d9..cbe0242842d1 100644
--- a/Documentation/driver-api/gpio/driver.rst
+++ b/Documentation/driver-api/gpio/driver.rst
@@ -44,7 +44,7 @@ common to each controller of that type:
 
  - methods to establish GPIO line direction
  - methods used to access GPIO line values
- - method to set electrical configuration to a a given GPIO line
+ - method to set electrical configuration for a given GPIO line
  - method to return the IRQ number associated to a given GPIO line
  - flag saying whether calls to its methods may sleep
  - optional line names array to identify lines
@@ -143,7 +143,7 @@ resistor will make the line tend to high level unless one of the transistors on
 the rail actively pulls it down.
 
 The level on the line will go as high as the VDD on the pull-up resistor, which
-may be higher than the level supported by the transistor, achieveing a
+may be higher than the level supported by the transistor, achieving a
 level-shift to the higher VDD.
 
 Integrated electronics often have an output driver stage in the form of a CMOS
@@ -382,7 +382,7 @@ Real-Time compliance for GPIO IRQ chips
 
 Any provider of irqchips needs to be carefully tailored to support Real Time
 preemption. It is desirable that all irqchips in the GPIO subsystem keep this
-in mind and does the proper testing to assure they are real time-enabled.
+in mind and do the proper testing to assure they are real time-enabled.
 So, pay attention on above " RT_FULL:" notes, please.
 The following is a checklist to follow when preparing a driver for real
 time-compliance:
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index 6d8352c0f354..f4180e7c7ed5 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -17,7 +17,9 @@ available subsections can be seen below.
    basics
    infrastructure
    pm/index
+   clk
    device-io
+   device_connection
    dma-buf
    device_link
    message-based
@@ -49,6 +51,7 @@ available subsections can be seen below.
    dmaengine/index
    slimbus
    soundwire/index
+   fpga/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/driver-api/infrastructure.rst b/Documentation/driver-api/infrastructure.rst
index 6d9ff316b608..bee1b9a1702f 100644
--- a/Documentation/driver-api/infrastructure.rst
+++ b/Documentation/driver-api/infrastructure.rst
@@ -28,7 +28,7 @@ Device Drivers Base
 .. kernel-doc:: drivers/base/node.c
    :internal:
 
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
    :export:
 
 .. kernel-doc:: drivers/base/transport_class.c
diff --git a/Documentation/driver-api/soundwire/error_handling.rst b/Documentation/driver-api/soundwire/error_handling.rst
new file mode 100644
index 000000000000..aa3a0a23a066
--- /dev/null
+++ b/Documentation/driver-api/soundwire/error_handling.rst
@@ -0,0 +1,65 @@
+========================
+SoundWire Error Handling
+========================
+
+The SoundWire PHY was designed with care and errors on the bus are going to
+be very unlikely, and if they happen it should be limited to single bit
+errors. Examples of this design can be found in the synchronization
+mechanism (sync loss after two errors) and short CRCs used for the Bulk
+Register Access.
+
+The errors can be detected with multiple mechanisms:
+
+1. Bus clash or parity errors: This mechanism relies on low-level detectors
+   that are independent of the payload and usages, and they cover both control
+   and audio data. The current implementation only logs such errors.
+   Improvements could be invalidating an entire programming sequence and
+   restarting from a known position. In the case of such errors outside of a
+   control/command sequence, there is no concealment or recovery for audio
+   data enabled by the SoundWire protocol, the location of the error will also
+   impact its audibility (most-significant bits will be more impacted in PCM),
+   and after a number of such errors are detected the bus might be reset. Note
+   that bus clashes due to programming errors (two streams using the same bit
+   slots) or electrical issues during the transmit/receive transition cannot
+   be distinguished, although a recurring bus clash when audio is enabled is a
+   indication of a bus allocation issue. The interrupt mechanism can also help
+   identify Slaves which detected a Bus Clash or a Parity Error, but they may
+   not be responsible for the errors so resetting them individually is not a
+   viable recovery strategy.
+
+2. Command status: Each command is associated with a status, which only
+   covers transmission of the data between devices. The ACK status indicates
+   that the command was received and will be executed by the end of the
+   current frame. A NAK indicates that the command was in error and will not
+   be applied. In case of a bad programming (command sent to non-existent
+   Slave or to a non-implemented register) or electrical issue, no response
+   signals the command was ignored. Some Master implementations allow for a
+   command to be retransmitted several times.  If the retransmission fails,
+   backtracking and restarting the entire programming sequence might be a
+   solution. Alternatively some implementations might directly issue a bus
+   reset and re-enumerate all devices.
+
+3. Timeouts: In a number of cases such as ChannelPrepare or
+   ClockStopPrepare, the bus driver is supposed to poll a register field until
+   it transitions to a NotFinished value of zero. The MIPI SoundWire spec 1.1
+   does not define timeouts but the MIPI SoundWire DisCo document adds
+   recommendation on timeouts. If such configurations do not complete, the
+   driver will return a -ETIMEOUT. Such timeouts are symptoms of a faulty
+   Slave device and are likely impossible to recover from.
+
+Errors during global reconfiguration sequences are extremely difficult to
+handle:
+
+1. BankSwitch: An error during the last command issuing a BankSwitch is
+   difficult to backtrack from. Retransmitting the Bank Switch command may be
+   possible in a single segment setup, but this can lead to synchronization
+   problems when enabling multiple bus segments (a command with side effects
+   such as frame reconfiguration would be handled at different times). A global
+   hard-reset might be the best solution.
+
+Note that SoundWire does not provide a mechanism to detect illegal values
+written in valid registers. In a number of cases the standard even mentions
+that the Slave might behave in implementation-defined ways. The bus
+implementation does not provide a recovery mechanism for such errors, Slave
+or Master driver implementers are responsible for writing valid values in
+valid registers and implement additional range checking if needed.
diff --git a/Documentation/driver-api/soundwire/index.rst b/Documentation/driver-api/soundwire/index.rst
index 647e94654752..6db026028f27 100644
--- a/Documentation/driver-api/soundwire/index.rst
+++ b/Documentation/driver-api/soundwire/index.rst
@@ -6,6 +6,9 @@ SoundWire Documentation
    :maxdepth: 1
 
    summary
+   stream
+   error_handling
+   locking
 
 .. only::  subproject
 
diff --git a/Documentation/driver-api/soundwire/locking.rst b/Documentation/driver-api/soundwire/locking.rst
new file mode 100644
index 000000000000..253f73555255
--- /dev/null
+++ b/Documentation/driver-api/soundwire/locking.rst
@@ -0,0 +1,106 @@
+=================
+SoundWire Locking
+=================
+
+This document explains locking mechanism of the SoundWire Bus. Bus uses
+following locks in order to avoid race conditions in Bus operations on
+shared resources.
+
+  - Bus lock
+
+  - Message lock
+
+Bus lock
+========
+
+SoundWire Bus lock is a mutex and is part of Bus data structure
+(sdw_bus) which is used for every Bus instance. This lock is used to
+serialize each of the following operations(s) within SoundWire Bus instance.
+
+  - Addition and removal of Slave(s), changing Slave status.
+
+  - Prepare, Enable, Disable and De-prepare stream operations.
+
+  - Access of Stream data structure.
+
+Message lock
+============
+
+SoundWire message transfer lock. This mutex is part of
+Bus data structure (sdw_bus). This lock is used to serialize the message
+transfers (read/write) within a SoundWire Bus instance.
+
+Below examples show how locks are acquired.
+
+Example 1
+---------
+
+Message transfer.
+
+  1. For every message transfer
+
+     a. Acquire Message lock.
+
+     b. Transfer message (Read/Write) to Slave1 or broadcast message on
+        Bus in case of bank switch.
+
+     c. Release Message lock ::
+
+	+----------+                    +---------+
+	|          |                    |         |
+	|   Bus    |                    | Master  |
+	|          |                    | Driver  |
+	|          |                    |         |
+	+----+-----+                    +----+----+
+	     |                               |
+	     |     bus->ops->xfer_msg()      |
+	     <-------------------------------+   a. Acquire Message lock
+	     |                               |   b. Transfer message
+	     |                               |
+	     +------------------------------->   c. Release Message lock
+	     |    return success/error       |   d. Return success/error
+	     |                               |
+	     +                               +
+
+Example 2
+---------
+
+Prepare operation.
+
+  1. Acquire lock for Bus instance associated with Master 1.
+
+  2. For every message transfer in Prepare operation
+
+     a. Acquire Message lock.
+
+     b. Transfer message (Read/Write) to Slave1 or broadcast message on
+        Bus in case of bank switch.
+
+     c. Release Message lock.
+
+  3. Release lock for Bus instance associated with Master 1 ::
+
+	+----------+                    +---------+
+	|          |                    |         |
+	|   Bus    |                    | Master  |
+	|          |                    | Driver  |
+	|          |                    |         |
+	+----+-----+                    +----+----+
+	     |                               |
+	     |    sdw_prepare_stream()       |
+	     <-------------------------------+   1. Acquire bus lock
+	     |                               |   2. Perform stream prepare
+	     |                               |
+	     |                               |
+	     |     bus->ops->xfer_msg()      |
+	     <-------------------------------+   a. Acquire Message lock
+	     |                               |   b. Transfer message
+	     |                               |
+	     +------------------------------->   c. Release Message lock
+	     |    return success/error       |   d. Return success/error
+	     |                               |
+	     |                               |
+	     |    return success/error       |   3. Release bus lock
+	     +------------------------------->   4. Return success/error
+	     |                               |
+	     +                               +
diff --git a/Documentation/driver-api/soundwire/stream.rst b/Documentation/driver-api/soundwire/stream.rst
new file mode 100644
index 000000000000..29121aa55fb9
--- /dev/null
+++ b/Documentation/driver-api/soundwire/stream.rst
@@ -0,0 +1,372 @@
+=========================
+Audio Stream in SoundWire
+=========================
+
+An audio stream is a logical or virtual connection created between
+
+  (1) System memory buffer(s) and Codec(s)
+
+  (2) DSP memory buffer(s) and Codec(s)
+
+  (3) FIFO(s) and Codec(s)
+
+  (4) Codec(s) and Codec(s)
+
+which is typically driven by a DMA(s) channel through the data link. An
+audio stream contains one or more channels of data. All channels within
+stream must have same sample rate and same sample size.
+
+Assume a stream with two channels (Left & Right) is opened using SoundWire
+interface. Below are some ways a stream can be represented in SoundWire.
+
+Stream Sample in memory (System memory, DSP memory or FIFOs) ::
+
+	-------------------------
+	| L | R | L | R | L | R |
+	-------------------------
+
+Example 1: Stereo Stream with L and R channels is rendered from Master to
+Slave. Both Master and Slave is using single port. ::
+
+	+---------------+                    Clock Signal  +---------------+
+	|    Master     +----------------------------------+     Slave     |
+	|   Interface   |                                  |   Interface   |
+	|               |                                  |       1       |
+	|               |                     Data Signal  |               |
+	|    L  +  R    +----------------------------------+    L  +  R    |
+	|     (Data)    |     Data Direction               |     (Data)    |
+	+---------------+  +----------------------->       +---------------+
+
+
+Example 2: Stereo Stream with L and R channels is captured from Slave to
+Master. Both Master and Slave is using single port. ::
+
+
+	+---------------+                    Clock Signal  +---------------+
+	|    Master     +----------------------------------+     Slave     |
+	|   Interface   |                                  |   Interface   |
+	|               |                                  |       1       |
+	|               |                     Data Signal  |               |
+	|    L  +  R    +----------------------------------+    L  +  R    |
+	|     (Data)    |     Data Direction               |     (Data)    |
+	+---------------+  <-----------------------+       +---------------+
+
+
+Example 3: Stereo Stream with L and R channels is rendered by Master. Each
+of the L and R channel is received by two different Slaves. Master and both
+Slaves are using single port. ::
+
+	+---------------+                    Clock Signal  +---------------+
+	|    Master     +---------+------------------------+     Slave     |
+	|   Interface   |         |                        |   Interface   |
+	|               |         |                        |       1       |
+	|               |         |           Data Signal  |               |
+	|    L  +  R    +---+------------------------------+       L       |
+	|     (Data)    |   |     |    Data Direction      |     (Data)    |
+	+---------------+   |     |   +------------->      +---------------+
+	                    |     |
+	                    |     |
+	                    |     |                        +---------------+
+	                    |     +----------------------> |     Slave     |
+	                    |                              |   Interface   |
+	                    |                              |       2       |
+	                    |                              |               |
+	                    +----------------------------> |       R       |
+	                                                   |     (Data)    |
+	                                                   +---------------+
+
+
+Example 4: Stereo Stream with L and R channel is rendered by two different
+Ports of the Master and is received by only single Port of the Slave
+interface. ::
+
+	+--------------------+
+	|                    |
+	|     +--------------+                             +----------------+
+	|     |             ||                             |                |
+	|     |  Data Port  ||  L Channel                  |                |
+	|     |      1      |------------+                 |                |
+	|     |  L Channel  ||           |                 +-----+----+     |
+	|     |   (Data)    ||           |   L + R Channel ||    Data |     |
+	| Master  +----------+           | +---+---------> ||    Port |     |
+	| Interface          |           |                 ||     1   |     |
+	|     +--------------+           |                 ||         |     |
+	|     |             ||           |                 +----------+     |
+	|     |  Data Port  |------------+                 |                |
+	|     |      2      ||  R Channel                  |     Slave      |
+	|     |  R Channel  ||                             |   Interface    |
+	|     |   (Data)    ||                             |       1        |
+	|     +--------------+         Clock Signal        |     L  +  R    |
+	|                    +---------------------------> |      (Data)    |
+	+--------------------+                             |                |
+							   +----------------+
+
+SoundWire Stream Management flow
+================================
+
+Stream definitions
+------------------
+
+  (1) Current stream: This is classified as the stream on which operation has
+      to be performed like prepare, enable, disable, de-prepare etc.
+
+  (2) Active stream: This is classified as the stream which is already active
+      on Bus other than current stream. There can be multiple active streams
+      on the Bus.
+
+SoundWire Bus manages stream operations for each stream getting
+rendered/captured on the SoundWire Bus. This section explains Bus operations
+done for each of the stream allocated/released on Bus. Following are the
+stream states maintained by the Bus for each of the audio stream.
+
+
+SoundWire stream states
+-----------------------
+
+Below shows the SoundWire stream states and state transition diagram. ::
+
+	+-----------+     +------------+     +----------+     +----------+
+	| ALLOCATED +---->| CONFIGURED +---->| PREPARED +---->| ENABLED  |
+	|   STATE   |     |    STATE   |     |  STATE   |     |  STATE   |
+	+-----------+     +------------+     +----------+     +----+-----+
+	                                                           ^
+	                                                           |
+	                                                           |
+	                                                           v
+	         +----------+           +------------+        +----+-----+
+	         | RELEASED |<----------+ DEPREPARED |<-------+ DISABLED |
+	         |  STATE   |           |   STATE    |        |  STATE   |
+	         +----------+           +------------+        +----------+
+
+NOTE: State transition between prepare and deprepare is supported in Spec
+but not in the software (subsystem)
+
+NOTE2: Stream state transition checks need to be handled by caller
+framework, for example ALSA/ASoC. No checks for stream transition exist in
+SoundWire subsystem.
+
+Stream State Operations
+-----------------------
+
+Below section explains the operations done by the Bus on Master(s) and
+Slave(s) as part of stream state transitions.
+
+SDW_STREAM_ALLOCATED
+~~~~~~~~~~~~~~~~~~~~
+
+Allocation state for stream. This is the entry state
+of the stream. Operations performed before entering in this state:
+
+  (1) A stream runtime is allocated for the stream. This stream
+      runtime is used as a reference for all the operations performed
+      on the stream.
+
+  (2) The resources required for holding stream runtime information are
+      allocated and initialized. This holds all stream related information
+      such as stream type (PCM/PDM) and parameters, Master and Slave
+      interface associated with the stream, stream state etc.
+
+After all above operations are successful, stream state is set to
+``SDW_STREAM_ALLOCATED``.
+
+Bus implements below API for allocate a stream which needs to be called once
+per stream. From ASoC DPCM framework, this stream state maybe linked to
+.startup() operation.
+
+  .. code-block:: c
+  int sdw_alloc_stream(char * stream_name);
+
+
+SDW_STREAM_CONFIGURED
+~~~~~~~~~~~~~~~~~~~~~
+
+Configuration state of stream. Operations performed before entering in
+this state:
+
+  (1) The resources allocated for stream information in SDW_STREAM_ALLOCATED
+      state are updated here. This includes stream parameters, Master(s)
+      and Slave(s) runtime information associated with current stream.
+
+  (2) All the Master(s) and Slave(s) associated with current stream provide
+      the port information to Bus which includes port numbers allocated by
+      Master(s) and Slave(s) for current stream and their channel mask.
+
+After all above operations are successful, stream state is set to
+``SDW_STREAM_CONFIGURED``.
+
+Bus implements below APIs for CONFIG state which needs to be called by
+the respective Master(s) and Slave(s) associated with stream. These APIs can
+only be invoked once by respective Master(s) and Slave(s). From ASoC DPCM
+framework, this stream state is linked to .hw_params() operation.
+
+  .. code-block:: c
+  int sdw_stream_add_master(struct sdw_bus * bus,
+		struct sdw_stream_config * stream_config,
+		struct sdw_ports_config * ports_config,
+		struct sdw_stream_runtime * stream);
+
+  int sdw_stream_add_slave(struct sdw_slave * slave,
+		struct sdw_stream_config * stream_config,
+		struct sdw_ports_config * ports_config,
+		struct sdw_stream_runtime * stream);
+
+
+SDW_STREAM_PREPARED
+~~~~~~~~~~~~~~~~~~~
+
+Prepare state of stream. Operations performed before entering in this state:
+
+  (1) Bus parameters such as bandwidth, frame shape, clock frequency,
+      are computed based on current stream as well as already active
+      stream(s) on Bus. Re-computation is required to accommodate current
+      stream on the Bus.
+
+  (2) Transport and port parameters of all Master(s) and Slave(s) port(s) are
+      computed for the current as well as already active stream based on frame
+      shape and clock frequency computed in step 1.
+
+  (3) Computed Bus and transport parameters are programmed in Master(s) and
+      Slave(s) registers. The banked registers programming is done on the
+      alternate bank (bank currently unused). Port(s) are enabled for the
+      already active stream(s) on the alternate bank (bank currently unused).
+      This is done in order to not disrupt already active stream(s).
+
+  (4) Once all the values are programmed, Bus initiates switch to alternate
+      bank where all new values programmed gets into effect.
+
+  (5) Ports of Master(s) and Slave(s) for current stream are prepared by
+      programming PrepareCtrl register.
+
+After all above operations are successful, stream state is set to
+``SDW_STREAM_PREPARED``.
+
+Bus implements below API for PREPARE state which needs to be called once per
+stream. From ASoC DPCM framework, this stream state is linked to
+.prepare() operation.
+
+  .. code-block:: c
+  int sdw_prepare_stream(struct sdw_stream_runtime * stream);
+
+
+SDW_STREAM_ENABLED
+~~~~~~~~~~~~~~~~~~
+
+Enable state of stream. The data port(s) are enabled upon entering this state.
+Operations performed before entering in this state:
+
+  (1) All the values computed in SDW_STREAM_PREPARED state are programmed
+      in alternate bank (bank currently unused). It includes programming of
+      already active stream(s) as well.
+
+  (2) All the Master(s) and Slave(s) port(s) for the current stream are
+      enabled on alternate bank (bank currently unused) by programming
+      ChannelEn register.
+
+  (3) Once all the values are programmed, Bus initiates switch to alternate
+      bank where all new values programmed gets into effect and port(s)
+      associated with current stream are enabled.
+
+After all above operations are successful, stream state is set to
+``SDW_STREAM_ENABLED``.
+
+Bus implements below API for ENABLE state which needs to be called once per
+stream. From ASoC DPCM framework, this stream state is linked to
+.trigger() start operation.
+
+  .. code-block:: c
+  int sdw_enable_stream(struct sdw_stream_runtime * stream);
+
+SDW_STREAM_DISABLED
+~~~~~~~~~~~~~~~~~~~
+
+Disable state of stream. The data port(s) are disabled upon exiting this state.
+Operations performed before entering in this state:
+
+  (1) All the Master(s) and Slave(s) port(s) for the current stream are
+      disabled on alternate bank (bank currently unused) by programming
+      ChannelEn register.
+
+  (2) All the current configuration of Bus and active stream(s) are programmed
+      into alternate bank (bank currently unused).
+
+  (3) Once all the values are programmed, Bus initiates switch to alternate
+      bank where all new values programmed gets into effect and port(s) associated
+      with current stream are disabled.
+
+After all above operations are successful, stream state is set to
+``SDW_STREAM_DISABLED``.
+
+Bus implements below API for DISABLED state which needs to be called once
+per stream. From ASoC DPCM framework, this stream state is linked to
+.trigger() stop operation.
+
+  .. code-block:: c
+  int sdw_disable_stream(struct sdw_stream_runtime * stream);
+
+
+SDW_STREAM_DEPREPARED
+~~~~~~~~~~~~~~~~~~~~~
+
+De-prepare state of stream. Operations performed before entering in this
+state:
+
+  (1) All the port(s) of Master(s) and Slave(s) for current stream are
+      de-prepared by programming PrepareCtrl register.
+
+  (2) The payload bandwidth of current stream is reduced from the total
+      bandwidth requirement of bus and new parameters calculated and
+      applied by performing bank switch etc.
+
+After all above operations are successful, stream state is set to
+``SDW_STREAM_DEPREPARED``.
+
+Bus implements below API for DEPREPARED state which needs to be called once
+per stream. From ASoC DPCM framework, this stream state is linked to
+.trigger() stop operation.
+
+  .. code-block:: c
+  int sdw_deprepare_stream(struct sdw_stream_runtime * stream);
+
+
+SDW_STREAM_RELEASED
+~~~~~~~~~~~~~~~~~~~
+
+Release state of stream. Operations performed before entering in this state:
+
+  (1) Release port resources for all Master(s) and Slave(s) port(s)
+      associated with current stream.
+
+  (2) Release Master(s) and Slave(s) runtime resources associated with
+      current stream.
+
+  (3) Release stream runtime resources associated with current stream.
+
+After all above operations are successful, stream state is set to
+``SDW_STREAM_RELEASED``.
+
+Bus implements below APIs for RELEASE state which needs to be called by
+all the Master(s) and Slave(s) associated with stream. From ASoC DPCM
+framework, this stream state is linked to .hw_free() operation.
+
+  .. code-block:: c
+  int sdw_stream_remove_master(struct sdw_bus * bus,
+		struct sdw_stream_runtime * stream);
+  int sdw_stream_remove_slave(struct sdw_slave * slave,
+		struct sdw_stream_runtime * stream);
+
+
+The .shutdown() ASoC DPCM operation calls below Bus API to release
+stream assigned as part of ALLOCATED state.
+
+In .shutdown() the data structure maintaining stream state are freed up.
+
+  .. code-block:: c
+  void sdw_release_stream(struct sdw_stream_runtime * stream);
+
+Not Supported
+=============
+
+1. A single port with multiple channels supported cannot be used between two
+streams or across stream. For example a port with 4 channels cannot be used
+to handle 2 independent stereo streams even though it's possible in theory
+in SoundWire.
diff --git a/Documentation/driver-api/uio-howto.rst b/Documentation/driver-api/uio-howto.rst
index 92056c20e070..fb2eb73be4a3 100644
--- a/Documentation/driver-api/uio-howto.rst
+++ b/Documentation/driver-api/uio-howto.rst
@@ -711,7 +711,8 @@ The vmbus device regions are mapped into uio device resources:
 
 If a subchannel is created by a request to host, then the uio_hv_generic
 device driver will create a sysfs binary file for the per-channel ring buffer.
-For example:
+For example::
+
 	/sys/bus/vmbus/devices/3811fe4d-0fa0-4b62-981a-74fc1084c757/channels/21/ring
 
 Further information
diff --git a/Documentation/driver-api/usb/dwc3.rst b/Documentation/driver-api/usb/dwc3.rst
index c3dc84a50ce5..8b36ff11cef9 100644
--- a/Documentation/driver-api/usb/dwc3.rst
+++ b/Documentation/driver-api/usb/dwc3.rst
@@ -674,9 +674,8 @@ operations, both of which can be traced. Format is::
   	__entry->flags & DWC3_EP_ENABLED ? 'E' : 'e',
   	__entry->flags & DWC3_EP_STALL ? 'S' : 's',
   	__entry->flags & DWC3_EP_WEDGE ? 'W' : 'w',
-  	__entry->flags & DWC3_EP_BUSY ? 'B' : 'b',
+  	__entry->flags & DWC3_EP_TRANSFER_STARTED ? 'B' : 'b',
   	__entry->flags & DWC3_EP_PENDING_REQUEST ? 'P' : 'p',
-  	__entry->flags & DWC3_EP_MISSED_ISOC ? 'M' : 'm',
   	__entry->flags & DWC3_EP_END_TRANSFER_PENDING ? 'E' : 'e',
   	__entry->direction ? '<' : '>'
   )
diff --git a/Documentation/driver-api/usb/typec.rst b/Documentation/driver-api/usb/typec.rst
index feb31946490b..48ff58095f11 100644
--- a/Documentation/driver-api/usb/typec.rst
+++ b/Documentation/driver-api/usb/typec.rst
@@ -210,7 +210,7 @@ If the connector is dual-role capable, there may also be a switch for the data
 role. USB Type-C Connector Class does not supply separate API for them. The
 port drivers can use USB Role Class API with those.
 
-Illustration of the muxes behind a connector that supports an alternate mode:
+Illustration of the muxes behind a connector that supports an alternate mode::
 
                      ------------------------
                      |       Connector      |
diff --git a/Documentation/features/lib/strncasecmp/arch-support.txt b/Documentation/features/core/cBPF-JIT/arch-support.txt
index 4f3a6a0e4e68..90459cdde314 100644
--- a/Documentation/features/lib/strncasecmp/arch-support.txt
+++ b/Documentation/features/core/cBPF-JIT/arch-support.txt
@@ -1,7 +1,7 @@
 #
-# Feature name:          strncasecmp
-#         Kconfig:       __HAVE_ARCH_STRNCASECMP
-#         description:   arch provides an optimized strncasecmp() function
+# Feature name:          cBPF-JIT
+#         Kconfig:       HAVE_CBPF_JIT
+#         description:   arch supports cBPF JIT optimizations
 #
     -----------------------
     |         arch |status|
@@ -16,14 +16,16 @@
     |        ia64: | TODO |
     |        m68k: | TODO |
     |  microblaze: | TODO |
-    |        mips: | TODO |
+    |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
-    |     powerpc: | TODO |
+    |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
-    |       sparc: | TODO |
+    |       sparc: |  ok  |
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: | TODO |
diff --git a/Documentation/features/core/BPF-JIT/arch-support.txt b/Documentation/features/core/eBPF-JIT/arch-support.txt
index 0b96b4e1e7d4..c90a0382fe66 100644
--- a/Documentation/features/core/BPF-JIT/arch-support.txt
+++ b/Documentation/features/core/eBPF-JIT/arch-support.txt
@@ -1,7 +1,7 @@
 #
-# Feature name:          BPF-JIT
-#         Kconfig:       HAVE_BPF_JIT
-#         description:   arch supports BPF JIT optimizations
+# Feature name:          eBPF-JIT
+#         Kconfig:       HAVE_EBPF_JIT
+#         description:   arch supports eBPF JIT optimizations
 #
     -----------------------
     |         arch |status|
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: |  ok  |
diff --git a/Documentation/features/core/generic-idle-thread/arch-support.txt b/Documentation/features/core/generic-idle-thread/arch-support.txt
index 372a2b18a617..0ef6acdb991c 100644
--- a/Documentation/features/core/generic-idle-thread/arch-support.txt
+++ b/Documentation/features/core/generic-idle-thread/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
-    |    openrisc: | TODO |
+    |    openrisc: |  ok  |
     |      parisc: |  ok  |
     |     powerpc: |  ok  |
+    |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/core/jump-labels/arch-support.txt b/Documentation/features/core/jump-labels/arch-support.txt
index ad97217b003b..27cbd63abfd2 100644
--- a/Documentation/features/core/jump-labels/arch-support.txt
+++ b/Documentation/features/core/jump-labels/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: |  ok  |
diff --git a/Documentation/features/core/tracehook/arch-support.txt b/Documentation/features/core/tracehook/arch-support.txt
index 36ee7bef5d18..f44c274e40ed 100644
--- a/Documentation/features/core/tracehook/arch-support.txt
+++ b/Documentation/features/core/tracehook/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: |  ok  |
     |       nios2: |  ok  |
     |    openrisc: |  ok  |
     |      parisc: |  ok  |
     |     powerpc: |  ok  |
+    |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt
index f5c99fa576d3..282ecc8ea1da 100644
--- a/Documentation/features/debug/KASAN/arch-support.txt
+++ b/Documentation/features/debug/KASAN/arch-support.txt
@@ -17,15 +17,17 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
     |          um: | TODO |
     |   unicore32: | TODO |
-    |         x86: |  ok  | 64-bit only
+    |         x86: |  ok  |
     |      xtensa: |  ok  |
     -----------------------
diff --git a/Documentation/features/debug/gcov-profile-all/arch-support.txt b/Documentation/features/debug/gcov-profile-all/arch-support.txt
index 5170a9934843..01b2b3004e0a 100644
--- a/Documentation/features/debug/gcov-profile-all/arch-support.txt
+++ b/Documentation/features/debug/gcov-profile-all/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: |  ok  |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: | TODO |
diff --git a/Documentation/features/debug/kgdb/arch-support.txt b/Documentation/features/debug/kgdb/arch-support.txt
index 13b6e994ae1f..3b4dff22329f 100644
--- a/Documentation/features/debug/kgdb/arch-support.txt
+++ b/Documentation/features/debug/kgdb/arch-support.txt
@@ -11,16 +11,18 @@
     |         arm: |  ok  |
     |       arm64: |  ok  |
     |         c6x: | TODO |
-    |       h8300: | TODO |
+    |       h8300: |  ok  |
     |     hexagon: |  ok  |
     |        ia64: | TODO |
     |        m68k: | TODO |
     |  microblaze: |  ok  |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: |  ok  |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
index 419bb38820e7..7e963d0ae646 100644
--- a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
+++ b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/debug/kprobes/arch-support.txt b/Documentation/features/debug/kprobes/arch-support.txt
index 52b3ace0a030..4ada027faf16 100644
--- a/Documentation/features/debug/kprobes/arch-support.txt
+++ b/Documentation/features/debug/kprobes/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: | TODO |
     |         arc: |  ok  |
     |         arm: |  ok  |
-    |       arm64: | TODO |
+    |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
     |     hexagon: | TODO |
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/debug/kretprobes/arch-support.txt b/Documentation/features/debug/kretprobes/arch-support.txt
index 180d24419518..044e13fcca5d 100644
--- a/Documentation/features/debug/kretprobes/arch-support.txt
+++ b/Documentation/features/debug/kretprobes/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: | TODO |
     |         arc: |  ok  |
     |         arm: |  ok  |
-    |       arm64: | TODO |
+    |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
     |     hexagon: | TODO |
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/debug/optprobes/arch-support.txt b/Documentation/features/debug/optprobes/arch-support.txt
index 0a1241f45e41..dce7669c918f 100644
--- a/Documentation/features/debug/optprobes/arch-support.txt
+++ b/Documentation/features/debug/optprobes/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
-    |     powerpc: | TODO |
+    |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/debug/stackprotector/arch-support.txt b/Documentation/features/debug/stackprotector/arch-support.txt
index 570019572383..74b89a9c8b3a 100644
--- a/Documentation/features/debug/stackprotector/arch-support.txt
+++ b/Documentation/features/debug/stackprotector/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: |  ok  |
     |       sparc: | TODO |
diff --git a/Documentation/features/debug/uprobes/arch-support.txt b/Documentation/features/debug/uprobes/arch-support.txt
index 0b8d922eb799..1a3f9d3229bf 100644
--- a/Documentation/features/debug/uprobes/arch-support.txt
+++ b/Documentation/features/debug/uprobes/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: | TODO |
     |         arc: | TODO |
     |         arm: |  ok  |
-    |       arm64: | TODO |
+    |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
     |     hexagon: | TODO |
@@ -17,13 +17,15 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: | TODO |
-    |       sparc: | TODO |
+    |       sparc: |  ok  |
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  |
diff --git a/Documentation/features/debug/user-ret-profiler/arch-support.txt b/Documentation/features/debug/user-ret-profiler/arch-support.txt
index 13852ae62e9e..1d78d1069a5f 100644
--- a/Documentation/features/debug/user-ret-profiler/arch-support.txt
+++ b/Documentation/features/debug/user-ret-profiler/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/io/dma-api-debug/arch-support.txt b/Documentation/features/io/dma-api-debug/arch-support.txt
deleted file mode 100644
index e438ed675623..000000000000
--- a/Documentation/features/io/dma-api-debug/arch-support.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-#
-# Feature name:          dma-api-debug
-#         Kconfig:       HAVE_DMA_API_DEBUG
-#         description:   arch supports DMA debug facilities
-#
-    -----------------------
-    |         arch |status|
-    -----------------------
-    |       alpha: | TODO |
-    |         arc: | TODO |
-    |         arm: |  ok  |
-    |       arm64: |  ok  |
-    |         c6x: |  ok  |
-    |       h8300: | TODO |
-    |     hexagon: | TODO |
-    |        ia64: |  ok  |
-    |        m68k: | TODO |
-    |  microblaze: |  ok  |
-    |        mips: |  ok  |
-    |       nios2: | TODO |
-    |    openrisc: | TODO |
-    |      parisc: | TODO |
-    |     powerpc: |  ok  |
-    |        s390: |  ok  |
-    |          sh: |  ok  |
-    |       sparc: |  ok  |
-    |          um: | TODO |
-    |   unicore32: | TODO |
-    |         x86: |  ok  |
-    |      xtensa: |  ok  |
-    -----------------------
diff --git a/Documentation/features/io/dma-contiguous/arch-support.txt b/Documentation/features/io/dma-contiguous/arch-support.txt
index 47f64a433df0..30c072d2b67c 100644
--- a/Documentation/features/io/dma-contiguous/arch-support.txt
+++ b/Documentation/features/io/dma-contiguous/arch-support.txt
@@ -17,11 +17,13 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
-    |        s390: | TODO |
+    |       riscv: |  ok  |
+    |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |
     |          um: | TODO |
diff --git a/Documentation/features/io/sg-chain/arch-support.txt b/Documentation/features/io/sg-chain/arch-support.txt
index 07f357fadbff..6554f0372c3f 100644
--- a/Documentation/features/io/sg-chain/arch-support.txt
+++ b/Documentation/features/io/sg-chain/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: |  ok  |
diff --git a/Documentation/features/locking/cmpxchg-local/arch-support.txt b/Documentation/features/locking/cmpxchg-local/arch-support.txt
index 482a0b09d1f8..51704a2dc8d1 100644
--- a/Documentation/features/locking/cmpxchg-local/arch-support.txt
+++ b/Documentation/features/locking/cmpxchg-local/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: | TODO |
     |         arc: | TODO |
     |         arm: | TODO |
-    |       arm64: | TODO |
+    |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
     |     hexagon: | TODO |
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/locking/lockdep/arch-support.txt b/Documentation/features/locking/lockdep/arch-support.txt
index bb35c5ba6286..bd39c5edd460 100644
--- a/Documentation/features/locking/lockdep/arch-support.txt
+++ b/Documentation/features/locking/lockdep/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: |  ok  |
     |        mips: |  ok  |
+    |       nds32: |  ok  |
     |       nios2: | TODO |
-    |    openrisc: | TODO |
+    |    openrisc: |  ok  |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/locking/queued-rwlocks/arch-support.txt b/Documentation/features/locking/queued-rwlocks/arch-support.txt
index 627e9a6b2db9..da7aff3bee0b 100644
--- a/Documentation/features/locking/queued-rwlocks/arch-support.txt
+++ b/Documentation/features/locking/queued-rwlocks/arch-support.txt
@@ -9,21 +9,23 @@
     |       alpha: | TODO |
     |         arc: | TODO |
     |         arm: | TODO |
-    |       arm64: | TODO |
+    |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
     |     hexagon: | TODO |
     |        ia64: | TODO |
     |        m68k: | TODO |
     |  microblaze: | TODO |
-    |        mips: | TODO |
+    |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
-    |    openrisc: | TODO |
+    |    openrisc: |  ok  |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
-    |       sparc: | TODO |
+    |       sparc: |  ok  |
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  |
diff --git a/Documentation/features/locking/queued-spinlocks/arch-support.txt b/Documentation/features/locking/queued-spinlocks/arch-support.txt
index 9edda216cdfb..478e9101322c 100644
--- a/Documentation/features/locking/queued-spinlocks/arch-support.txt
+++ b/Documentation/features/locking/queued-spinlocks/arch-support.txt
@@ -16,14 +16,16 @@
     |        ia64: | TODO |
     |        m68k: | TODO |
     |  microblaze: | TODO |
-    |        mips: | TODO |
+    |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
-    |    openrisc: | TODO |
+    |    openrisc: |  ok  |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
-    |       sparc: | TODO |
+    |       sparc: |  ok  |
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  |
diff --git a/Documentation/features/locking/rwsem-optimized/arch-support.txt b/Documentation/features/locking/rwsem-optimized/arch-support.txt
index 8d9afb10b16e..e54b1f1a8091 100644
--- a/Documentation/features/locking/rwsem-optimized/arch-support.txt
+++ b/Documentation/features/locking/rwsem-optimized/arch-support.txt
@@ -1,6 +1,6 @@
 #
 # Feature name:          rwsem-optimized
-#         Kconfig:       Optimized asm/rwsem.h
+#         Kconfig:       !RWSEM_GENERIC_SPINLOCK
 #         description:   arch provides optimized rwsem APIs
 #
     -----------------------
@@ -8,8 +8,8 @@
     -----------------------
     |       alpha: |  ok  |
     |         arc: | TODO |
-    |         arm: | TODO |
-    |       arm64: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
     |     hexagon: | TODO |
@@ -17,14 +17,16 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
-    |          um: | TODO |
+    |          um: |  ok  |
     |   unicore32: | TODO |
     |         x86: |  ok  |
     |      xtensa: |  ok  |
diff --git a/Documentation/features/perf/kprobes-event/arch-support.txt b/Documentation/features/perf/kprobes-event/arch-support.txt
index d01239ee34b3..7331402d1887 100644
--- a/Documentation/features/perf/kprobes-event/arch-support.txt
+++ b/Documentation/features/perf/kprobes-event/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: | TODO |
     |         arc: | TODO |
     |         arm: |  ok  |
-    |       arm64: | TODO |
+    |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
     |     hexagon: |  ok  |
@@ -17,13 +17,15 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: |  ok  |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: |  ok  |
-    |       sparc: | TODO |
+    |       sparc: |  ok  |
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  |
diff --git a/Documentation/features/perf/perf-regs/arch-support.txt b/Documentation/features/perf/perf-regs/arch-support.txt
index 458faba5311a..53feeee6cdad 100644
--- a/Documentation/features/perf/perf-regs/arch-support.txt
+++ b/Documentation/features/perf/perf-regs/arch-support.txt
@@ -17,11 +17,13 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
-    |        s390: | TODO |
+    |       riscv: | TODO |
+    |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |
     |          um: | TODO |
diff --git a/Documentation/features/perf/perf-stackdump/arch-support.txt b/Documentation/features/perf/perf-stackdump/arch-support.txt
index 545d01c69c88..16164348e0ea 100644
--- a/Documentation/features/perf/perf-stackdump/arch-support.txt
+++ b/Documentation/features/perf/perf-stackdump/arch-support.txt
@@ -17,11 +17,13 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
-    |        s390: | TODO |
+    |       riscv: | TODO |
+    |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |
     |          um: | TODO |
diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
index 85a6c9d4571c..dbdf62907703 100644
--- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -40,10 +40,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/sched/numa-balancing/arch-support.txt b/Documentation/features/sched/numa-balancing/arch-support.txt
index 347508863872..c68bb2c2cb62 100644
--- a/Documentation/features/sched/numa-balancing/arch-support.txt
+++ b/Documentation/features/sched/numa-balancing/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: | TODO |
     |         arc: |  ..  |
     |         arm: |  ..  |
-    |       arm64: |  ..  |
+    |       arm64: |  ok  |
     |         c6x: |  ..  |
     |       h8300: |  ..  |
     |     hexagon: |  ..  |
@@ -17,11 +17,13 @@
     |        m68k: |  ..  |
     |  microblaze: |  ..  |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: |  ..  |
     |    openrisc: |  ..  |
     |      parisc: |  ..  |
     |     powerpc: |  ok  |
-    |        s390: |  ..  |
+    |       riscv: | TODO |
+    |        s390: |  ok  |
     |          sh: |  ..  |
     |       sparc: | TODO |
     |          um: |  ..  |
diff --git a/Documentation/features/scripts/features-refresh.sh b/Documentation/features/scripts/features-refresh.sh
new file mode 100755
index 000000000000..9e72d38a0720
--- /dev/null
+++ b/Documentation/features/scripts/features-refresh.sh
@@ -0,0 +1,98 @@
+#
+# Small script that refreshes the kernel feature support status in place.
+#
+
+for F_FILE in Documentation/features/*/*/arch-support.txt; do
+	F=$(grep "^#         Kconfig:" "$F_FILE" | cut -c26-)
+
+	#
+	# Each feature F is identified by a pair (O, K), where 'O' can
+	# be either the empty string (for 'nop') or "not" (the logical
+	# negation operator '!'); other operators are not supported.
+	#
+	O=""
+	K=$F
+	if [[ "$F" == !* ]]; then
+		O="not"
+		K=$(echo $F | sed -e 's/^!//g')
+	fi
+
+	#
+	# F := (O, K) is 'valid' iff there is a Kconfig file (for some
+	# arch) which contains K.
+	#
+	# Notice that this definition entails an 'asymmetry' between
+	# the case 'O = ""' and the case 'O = "not"'. E.g., F may be
+	# _invalid_ if:
+	#
+	# [case 'O = ""']
+	#   1) no arch provides support for F,
+	#   2) K does not exist (e.g., it was renamed/mis-typed);
+	#
+	# [case 'O = "not"']
+	#   3) all archs provide support for F,
+	#   4) as in (2).
+	#
+	# The rationale for adopting this definition (and, thus, for
+	# keeping the asymmetry) is:
+	#
+	#       We want to be able to 'detect' (2) (or (4)).
+	#
+	# (1) and (3) may further warn the developers about the fact
+	# that K can be removed.
+	#
+	F_VALID="false"
+	for ARCH_DIR in arch/*/; do
+		K_FILES=$(find $ARCH_DIR -name "Kconfig*")
+		K_GREP=$(grep "$K" $K_FILES)
+		if [ ! -z "$K_GREP" ]; then
+			F_VALID="true"
+			break
+		fi
+	done
+	if [ "$F_VALID" = "false" ]; then
+		printf "WARNING: '%s' is not a valid Kconfig\n" "$F"
+	fi
+
+	T_FILE="$F_FILE.tmp"
+	grep "^#" $F_FILE > $T_FILE
+	echo "    -----------------------" >> $T_FILE
+	echo "    |         arch |status|" >> $T_FILE
+	echo "    -----------------------" >> $T_FILE
+	for ARCH_DIR in arch/*/; do
+		ARCH=$(echo $ARCH_DIR | sed -e 's/arch//g' | sed -e 's/\///g')
+		K_FILES=$(find $ARCH_DIR -name "Kconfig*")
+		K_GREP=$(grep "$K" $K_FILES)
+		#
+		# Arch support status values for (O, K) are updated according
+		# to the following rules.
+		#
+		#   - ("", K) is 'supported by a given arch', if there is a
+		#     Kconfig file for that arch which contains K;
+		#
+		#   - ("not", K) is 'supported by a given arch', if there is
+		#     no Kconfig file for that arch which contains K;
+		#
+		#   - otherwise: preserve the previous status value (if any),
+		#                default to 'not yet supported'.
+		#
+		# Notice that, according these rules, invalid features may be
+		# updated/modified.
+		#
+		if [ "$O" = "" ] && [ ! -z "$K_GREP" ]; then
+			printf "    |%12s: |  ok  |\n" "$ARCH" >> $T_FILE
+		elif [ "$O" = "not" ] && [ -z "$K_GREP" ]; then
+			printf "    |%12s: |  ok  |\n" "$ARCH" >> $T_FILE
+		else
+			S=$(grep -v "^#" "$F_FILE" | grep " $ARCH:")
+			if [ ! -z "$S" ]; then
+				echo "$S" >> $T_FILE
+			else
+				printf "    |%12s: | TODO |\n" "$ARCH" \
+					>> $T_FILE
+			fi
+		fi
+	done
+	echo "    -----------------------" >> $T_FILE
+	mv $T_FILE $F_FILE
+done
diff --git a/Documentation/features/seccomp/seccomp-filter/arch-support.txt b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
index e4fad58a05e5..d4271b493b41 100644
--- a/Documentation/features/seccomp/seccomp-filter/arch-support.txt
+++ b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
-    |      parisc: | TODO |
-    |     powerpc: | TODO |
+    |      parisc: |  ok  |
+    |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/time/arch-tick-broadcast/arch-support.txt b/Documentation/features/time/arch-tick-broadcast/arch-support.txt
index 8052904b25fc..83d9e68462bb 100644
--- a/Documentation/features/time/arch-tick-broadcast/arch-support.txt
+++ b/Documentation/features/time/arch-tick-broadcast/arch-support.txt
@@ -17,12 +17,14 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: | TODO |
-    |          sh: | TODO |
+    |          sh: |  ok  |
     |       sparc: | TODO |
     |          um: | TODO |
     |   unicore32: | TODO |
diff --git a/Documentation/features/time/clockevents/arch-support.txt b/Documentation/features/time/clockevents/arch-support.txt
index 7c76b946297e..3d4908fce6da 100644
--- a/Documentation/features/time/clockevents/arch-support.txt
+++ b/Documentation/features/time/clockevents/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: |  ok  |
     |  microblaze: |  ok  |
     |        mips: |  ok  |
+    |       nds32: |  ok  |
     |       nios2: |  ok  |
     |    openrisc: |  ok  |
-    |      parisc: | TODO |
+    |      parisc: |  ok  |
     |     powerpc: |  ok  |
+    |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/time/context-tracking/arch-support.txt b/Documentation/features/time/context-tracking/arch-support.txt
index 9433b3e523b3..c29974afffaa 100644
--- a/Documentation/features/time/context-tracking/arch-support.txt
+++ b/Documentation/features/time/context-tracking/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: |  ok  |
diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt
index 212dde0b578c..8d73c463ec27 100644
--- a/Documentation/features/time/irq-time-acct/arch-support.txt
+++ b/Documentation/features/time/irq-time-acct/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: |  ..  |
-    |     powerpc: |  ..  |
+    |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ..  |
     |          sh: | TODO |
     |       sparc: |  ..  |
diff --git a/Documentation/features/time/modern-timekeeping/arch-support.txt b/Documentation/features/time/modern-timekeeping/arch-support.txt
index 4074028f72f7..e7c6ea6b8fb3 100644
--- a/Documentation/features/time/modern-timekeeping/arch-support.txt
+++ b/Documentation/features/time/modern-timekeeping/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: |  ok  |
     |        mips: |  ok  |
+    |       nds32: |  ok  |
     |       nios2: |  ok  |
     |    openrisc: |  ok  |
     |      parisc: |  ok  |
     |     powerpc: |  ok  |
+    |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/time/virt-cpuacct/arch-support.txt b/Documentation/features/time/virt-cpuacct/arch-support.txt
index a394d8820517..4646457461cf 100644
--- a/Documentation/features/time/virt-cpuacct/arch-support.txt
+++ b/Documentation/features/time/virt-cpuacct/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: |  ok  |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: |  ok  |
diff --git a/Documentation/features/vm/ELF-ASLR/arch-support.txt b/Documentation/features/vm/ELF-ASLR/arch-support.txt
index 082f93d5b40e..1f71d090ff2c 100644
--- a/Documentation/features/vm/ELF-ASLR/arch-support.txt
+++ b/Documentation/features/vm/ELF-ASLR/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
-    |      parisc: | TODO |
+    |      parisc: |  ok  |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/vm/PG_uncached/arch-support.txt b/Documentation/features/vm/PG_uncached/arch-support.txt
index 605e0abb756d..fbd5aa463b0a 100644
--- a/Documentation/features/vm/PG_uncached/arch-support.txt
+++ b/Documentation/features/vm/PG_uncached/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/vm/THP/arch-support.txt b/Documentation/features/vm/THP/arch-support.txt
index 7a8eb0bd5ca8..5d7ecc378f29 100644
--- a/Documentation/features/vm/THP/arch-support.txt
+++ b/Documentation/features/vm/THP/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: |  ..  |
     |  microblaze: |  ..  |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: |  ..  |
     |    openrisc: |  ..  |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: |  ..  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt
index 35fb99b2b3ea..f7af9678eb66 100644
--- a/Documentation/features/vm/TLB/arch-support.txt
+++ b/Documentation/features/vm/TLB/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: |  ..  |
     |  microblaze: |  ..  |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: |  ..  |
     |    openrisc: |  ..  |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/vm/huge-vmap/arch-support.txt b/Documentation/features/vm/huge-vmap/arch-support.txt
index ed8b943ad8fc..d0713ccc7117 100644
--- a/Documentation/features/vm/huge-vmap/arch-support.txt
+++ b/Documentation/features/vm/huge-vmap/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: | TODO |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/features/vm/ioremap_prot/arch-support.txt b/Documentation/features/vm/ioremap_prot/arch-support.txt
index 589947bdf0a8..8527601a3739 100644
--- a/Documentation/features/vm/ioremap_prot/arch-support.txt
+++ b/Documentation/features/vm/ioremap_prot/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: | TODO |
     |          sh: |  ok  |
     |       sparc: | TODO |
diff --git a/Documentation/features/vm/numa-memblock/arch-support.txt b/Documentation/features/vm/numa-memblock/arch-support.txt
index 8b8bea0318a0..1a988052cd24 100644
--- a/Documentation/features/vm/numa-memblock/arch-support.txt
+++ b/Documentation/features/vm/numa-memblock/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: | TODO |
     |         arc: |  ..  |
     |         arm: |  ..  |
-    |       arm64: |  ..  |
+    |       arm64: |  ok  |
     |         c6x: |  ..  |
     |       h8300: |  ..  |
     |     hexagon: |  ..  |
@@ -17,10 +17,12 @@
     |        m68k: |  ..  |
     |  microblaze: |  ok  |
     |        mips: |  ok  |
+    |       nds32: | TODO |
     |       nios2: |  ..  |
     |    openrisc: |  ..  |
     |      parisc: |  ..  |
     |     powerpc: |  ok  |
+    |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/features/vm/pte_special/arch-support.txt b/Documentation/features/vm/pte_special/arch-support.txt
index 055004f467d2..6a608a6dcf71 100644
--- a/Documentation/features/vm/pte_special/arch-support.txt
+++ b/Documentation/features/vm/pte_special/arch-support.txt
@@ -17,10 +17,12 @@
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
+    |       nds32: | TODO |
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
+    |       riscv: | TODO |
     |        s390: |  ok  |
     |          sh: |  ok  |
     |       sparc: |  ok  |
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 75d2d57e2c44..2c391338c675 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -69,31 +69,31 @@ prototypes:
 
 locking rules:
 	all may block
-		i_mutex(inode)
-lookup:		yes
-create:		yes
-link:		yes (both)
-mknod:		yes
-symlink:	yes
-mkdir:		yes
-unlink:		yes (both)
-rmdir:		yes (both)	(see below)
-rename:	yes (all)	(see below)
+		i_rwsem(inode)
+lookup:		shared
+create:		exclusive
+link:		exclusive (both)
+mknod:		exclusive
+symlink:	exclusive
+mkdir:		exclusive
+unlink:		exclusive (both)
+rmdir:		exclusive (both)(see below)
+rename:		exclusive (all)	(see below)
 readlink:	no
 get_link:	no
-setattr:	yes
+setattr:	exclusive
 permission:	no (may not block if called in rcu-walk mode)
 get_acl:	no
 getattr:	no
 listxattr:	no
 fiemap:		no
 update_time:	no
-atomic_open:	yes
+atomic_open:	exclusive
 tmpfile:	no
 
 
-	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
-victim.
+	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem
+	exclusive on victim.
 	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
 
 See Documentation/filesystems/directory-locking for more detailed discussion
@@ -111,10 +111,10 @@ prototypes:
 
 locking rules:
 	all may block
-		i_mutex(inode)
+		i_rwsem(inode)
 list:		no
 get:		no
-set:		yes
+set:		exclusive
 
 --------------------------- super_operations ---------------------------
 prototypes:
@@ -217,14 +217,14 @@ prototypes:
 locking rules:
 	All except set_page_dirty and freepage may block
 
-			PageLocked(page)	i_mutex
+			PageLocked(page)	i_rwsem
 writepage:		yes, unlocks (see below)
 readpage:		yes, unlocks
 writepages:
 set_page_dirty		no
 readpages:
-write_begin:		locks the page		yes
-write_end:		yes, unlocks		yes
+write_begin:		locks the page		exclusive
+write_end:		yes, unlocks		exclusive
 bmap:
 invalidatepage:		yes
 releasepage:		yes
@@ -439,7 +439,10 @@ prototypes:
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
-	unsigned int (*poll) (struct file *, struct poll_table_struct *);
+	int (*iterate_shared) (struct file *, struct dir_context *);
+	__poll_t (*poll) (struct file *, struct poll_table_struct *);
+	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -470,7 +473,7 @@ prototypes:
 };
 
 locking rules:
-	All may block.
+	All except for ->poll_mask may block.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
@@ -480,6 +483,10 @@ mutex or just to use i_size_read() instead.
 Note: this does not protect the file->f_pos against concurrent modifications
 since this is something the userspace has to take care about.
 
+->iterate() is called with i_rwsem exclusive.
+
+->iterate_shared() is called with i_rwsem at least shared.
+
 ->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
 Most instances call fasync_helper(), which does that maintenance, so it's
 not normally something one needs to worry about.  Return values > 0 will be
@@ -498,6 +505,9 @@ in sys_read() and friends.
 the lease within the individual filesystem to record the result of the
 operation
 
+->poll_mask can be called with or without the waitqueue lock for the waitqueue
+returned from ->get_poll_head.
+
 --------------------------- dquot_operations -------------------------------
 prototypes:
 	int (*write_dquot) (struct dquot *);
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index cfbc18f0d9c9..48b424de85bb 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -191,11 +191,21 @@ Currently, the following pairs of encryption modes are supported:
 
 - AES-256-XTS for contents and AES-256-CTS-CBC for filenames
 - AES-128-CBC for contents and AES-128-CTS-CBC for filenames
+- Speck128/256-XTS for contents and Speck128/256-CTS-CBC for filenames
 
 It is strongly recommended to use AES-256-XTS for contents encryption.
 AES-128-CBC was added only for low-powered embedded devices with
 crypto accelerators such as CAAM or CESA that do not support XTS.
 
+Similarly, Speck128/256 support was only added for older or low-end
+CPUs which cannot do AES fast enough -- especially ARM CPUs which have
+NEON instructions but not the Cryptography Extensions -- and for which
+it would not otherwise be feasible to use encryption at all.  It is
+not recommended to use Speck on CPUs that have AES instructions.
+Speck support is only available if it has been enabled in the crypto
+API via CONFIG_CRYPTO_SPECK.  Also, on ARM platforms, to get
+acceptable performance CONFIG_CRYPTO_SPECK_NEON must be enabled.
+
 New encryption modes can be added relatively easily, without changes
 to individual filesystems.  However, authenticated encryption (AE)
 modes are not currently supported because of the difficulty of dealing
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 2a84bb334894..520f6a84cf50 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -515,7 +515,8 @@ guarantees:
 
 The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
 bits on both physical and virtual pages associated with a process, and the
-soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
+soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst
+for details).
 To clear the bits for all the pages associated with the process
     > echo 1 > /proc/PID/clear_refs
 
@@ -536,7 +537,8 @@ Any other value written to /proc/PID/clear_refs will have no effect.
 
 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
 using /proc/kpageflags and number of times a page is mapped using
-/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
+/proc/kpagecount. For detailed explanation, see
+Documentation/admin-guide/mm/pagemap.rst.
 
 The /proc/pid/numa_maps is an extension based on maps, showing the memory
 locality and binding policy, as well as the memory usage (in pages) of
@@ -564,7 +566,7 @@ address   policy    mapping details
 
 Where:
 "address" is the starting address for the mapping;
-"policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
+"policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst);
 "mapping details" summarizes mapping data such as mapping type, page usage counters,
 node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
 size, in KB, that is backing the mapping up.
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index a85355cf85f4..d06e9a59a9f4 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -105,8 +105,9 @@ policy for the file will revert to "default" policy.
 NUMA memory allocation policies have optional flags that can be used in
 conjunction with their modes.  These optional flags can be specified
 when tmpfs is mounted by appending them to the mode before the NodeList.
-See Documentation/vm/numa_memory_policy.txt for a list of all available
-memory allocation policy mode flags and their effect on memory policy.
+See Documentation/admin-guide/mm/numa_memory_policy.rst for a list of
+all available memory allocation policy mode flags and their effect on
+memory policy.
 
 	=static		is equivalent to	MPOL_F_STATIC_NODES
 	=relative	is equivalent to	MPOL_F_RELATIVE_NODES
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 5fd325df59e2..829a7b7857a4 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -856,7 +856,9 @@ struct file_operations {
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
-	unsigned int (*poll) (struct file *, struct poll_table_struct *);
+	__poll_t (*poll) (struct file *, struct poll_table_struct *);
+	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -901,6 +903,17 @@ otherwise noted.
 	activity on this file and (optionally) go to sleep until there
 	is activity. Called by the select(2) and poll(2) system calls
 
+  get_poll_head: Returns the struct wait_queue_head that callers can
+  wait on.  Callers need to check the returned events using ->poll_mask
+  once woken.  Can return NULL to indicate polling is not supported,
+  or any error code using the ERR_PTR convention to indicate that a
+  grave error occured and ->poll_mask shall not be called.
+
+  poll_mask: return the mask of EPOLL* values describing the file descriptor
+  state.  Called either before going to sleep on the waitqueue returned by
+  get_poll_head, or after it has been woken.  If ->get_poll_head and
+  ->poll_mask are implemented ->poll does not need to be implement.
+
   unlocked_ioctl: called by the ioctl(2) system call.
 
   compat_ioctl: called by the ioctl(2) system call when 32 bit system calls
diff --git a/Documentation/fpga/fpga-mgr.txt b/Documentation/fpga/fpga-mgr.txt
deleted file mode 100644
index cc6413ed6fc9..000000000000
--- a/Documentation/fpga/fpga-mgr.txt
+++ /dev/null
@@ -1,199 +0,0 @@
-FPGA Manager Core
-
-Alan Tull 2015
-
-Overview
-========
-
-The FPGA manager core exports a set of functions for programming an FPGA with
-an image.  The API is manufacturer agnostic.  All manufacturer specifics are
-hidden away in a low level driver which registers a set of ops with the core.
-The FPGA image data itself is very manufacturer specific, but for our purposes
-it's just binary data.  The FPGA manager core won't parse it.
-
-The FPGA image to be programmed can be in a scatter gather list, a single
-contiguous buffer, or a firmware file.  Because allocating contiguous kernel
-memory for the buffer should be avoided, users are encouraged to use a scatter
-gather list instead if possible.
-
-The particulars for programming the image are presented in a structure (struct
-fpga_image_info).  This struct contains parameters such as pointers to the
-FPGA image as well as image-specific particulars such as whether the image was
-built for full or partial reconfiguration.
-
-API Functions:
-==============
-
-To program the FPGA:
---------------------
-
-	int fpga_mgr_load(struct fpga_manager *mgr,
-			  struct fpga_image_info *info);
-
-Load the FPGA from an image which is indicated in the info.  If successful,
-the FPGA ends up in operating mode.  Return 0 on success or a negative error
-code.
-
-To allocate or free a struct fpga_image_info:
----------------------------------------------
-
-	struct fpga_image_info *fpga_image_info_alloc(struct device *dev);
-
-	void fpga_image_info_free(struct fpga_image_info *info);
-
-To get/put a reference to a FPGA manager:
------------------------------------------
-
-	struct fpga_manager *of_fpga_mgr_get(struct device_node *node);
-	struct fpga_manager *fpga_mgr_get(struct device *dev);
-	void fpga_mgr_put(struct fpga_manager *mgr);
-
-Given a DT node or device, get a reference to a FPGA manager.  This pointer
-can be saved until you are ready to program the FPGA.  fpga_mgr_put releases
-the reference.
-
-
-To get exclusive control of a FPGA manager:
--------------------------------------------
-
-	int fpga_mgr_lock(struct fpga_manager *mgr);
-	void fpga_mgr_unlock(struct fpga_manager *mgr);
-
-The user should call fpga_mgr_lock and verify that it returns 0 before
-attempting to program the FPGA.  Likewise, the user should call
-fpga_mgr_unlock when done programming the FPGA.
-
-
-To register or unregister the low level FPGA-specific driver:
--------------------------------------------------------------
-
-	int fpga_mgr_register(struct device *dev, const char *name,
-			      const struct fpga_manager_ops *mops,
-			      void *priv);
-
-	void fpga_mgr_unregister(struct device *dev);
-
-Use of these two functions is described below in "How To Support a new FPGA
-device."
-
-
-How to write an image buffer to a supported FPGA
-================================================
-#include <linux/fpga/fpga-mgr.h>
-
-struct fpga_manager *mgr;
-struct fpga_image_info *info;
-int ret;
-
-/*
- * Get a reference to FPGA manager.  The manager is not locked, so you can
- * hold onto this reference without it preventing programming.
- *
- * This example uses the device node of the manager.  Alternatively, use
- * fpga_mgr_get(dev) instead if you have the device.
- */
-mgr = of_fpga_mgr_get(mgr_node);
-
-/* struct with information about the FPGA image to program. */
-info = fpga_image_info_alloc(dev);
-
-/* flags indicates whether to do full or partial reconfiguration */
-info->flags = FPGA_MGR_PARTIAL_RECONFIG;
-
-/*
- * At this point, indicate where the image is. This is pseudo-code; you're
- * going to use one of these three.
- */
-if (image is in a scatter gather table) {
-
-	info->sgt = [your scatter gather table]
-
-} else if (image is in a buffer) {
-
-	info->buf = [your image buffer]
-	info->count = [image buffer size]
-
-} else if (image is in a firmware file) {
-
-	info->firmware_name = devm_kstrdup(dev, firmware_name, GFP_KERNEL);
-
-}
-
-/* Get exclusive control of FPGA manager */
-ret = fpga_mgr_lock(mgr);
-
-/* Load the buffer to the FPGA */
-ret = fpga_mgr_buf_load(mgr, &info, buf, count);
-
-/* Release the FPGA manager */
-fpga_mgr_unlock(mgr);
-fpga_mgr_put(mgr);
-
-/* Deallocate the image info if you're done with it */
-fpga_image_info_free(info);
-
-How to support a new FPGA device
-================================
-To add another FPGA manager, write a driver that implements a set of ops.  The
-probe function calls fpga_mgr_register(), such as:
-
-static const struct fpga_manager_ops socfpga_fpga_ops = {
-       .write_init = socfpga_fpga_ops_configure_init,
-       .write = socfpga_fpga_ops_configure_write,
-       .write_complete = socfpga_fpga_ops_configure_complete,
-       .state = socfpga_fpga_ops_state,
-};
-
-static int socfpga_fpga_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct socfpga_fpga_priv *priv;
-	int ret;
-
-	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	/* ... do ioremaps, get interrupts, etc. and save
-	   them in priv... */
-
-	return fpga_mgr_register(dev, "Altera SOCFPGA FPGA Manager",
-				 &socfpga_fpga_ops, priv);
-}
-
-static int socfpga_fpga_remove(struct platform_device *pdev)
-{
-	fpga_mgr_unregister(&pdev->dev);
-
-	return 0;
-}
-
-
-The ops will implement whatever device specific register writes are needed to
-do the programming sequence for this particular FPGA.  These ops return 0 for
-success or negative error codes otherwise.
-
-The programming sequence is:
- 1. .write_init
- 2. .write or .write_sg (may be called once or multiple times)
- 3. .write_complete
-
-The .write_init function will prepare the FPGA to receive the image data.  The
-buffer passed into .write_init will be atmost .initial_header_size bytes long,
-if the whole bitstream is not immediately available then the core code will
-buffer up at least this much before starting.
-
-The .write function writes a buffer to the FPGA. The buffer may be contain the
-whole FPGA image or may be a smaller chunk of an FPGA image.  In the latter
-case, this function is called multiple times for successive chunks. This interface
-is suitable for drivers which use PIO.
-
-The .write_sg version behaves the same as .write except the input is a sg_table
-scatter list. This interface is suitable for drivers which use DMA.
-
-The .write_complete function is called after all the image has been written
-to put the FPGA into operating mode.
-
-The ops include a .state function which will read the hardware FPGA manager and
-return a code of type enum fpga_mgr_states.  It doesn't result in a change in
-hardware state.
diff --git a/Documentation/fpga/fpga-region.txt b/Documentation/fpga/fpga-region.txt
deleted file mode 100644
index 139a02ba1ff6..000000000000
--- a/Documentation/fpga/fpga-region.txt
+++ /dev/null
@@ -1,95 +0,0 @@
-FPGA Regions
-
-Alan Tull 2017
-
-CONTENTS
- - Introduction
- - The FPGA region API
- - Usage example
-
-Introduction
-============
-
-This document is meant to be an brief overview of the FPGA region API usage.  A
-more conceptual look at regions can be found in [1].
-
-For the purposes of this API document, let's just say that a region associates
-an FPGA Manager and a bridge (or bridges) with a reprogrammable region of an
-FPGA or the whole FPGA.  The API provides a way to register a region and to
-program a region.
-
-Currently the only layer above fpga-region.c in the kernel is the Device Tree
-support (of-fpga-region.c) described in [1].  The DT support layer uses regions
-to program the FPGA and then DT to handle enumeration.  The common region code
-is intended to be used by other schemes that have other ways of accomplishing
-enumeration after programming.
-
-An fpga-region can be set up to know the following things:
-* which FPGA manager to use to do the programming
-* which bridges to disable before programming and enable afterwards.
-
-Additional info needed to program the FPGA image is passed in the struct
-fpga_image_info [2] including:
-* pointers to the image as either a scatter-gather buffer, a contiguous
-  buffer, or the name of firmware file
-* flags indicating specifics such as whether the image if for partial
-  reconfiguration.
-
-===================
-The FPGA region API
-===================
-
-To register or unregister a region:
------------------------------------
-
-	int fpga_region_register(struct device *dev,
-				 struct fpga_region *region);
-	int fpga_region_unregister(struct fpga_region *region);
-
-An example of usage can be seen in the probe function of [3]
-
-To program an FPGA:
--------------------
-	int fpga_region_program_fpga(struct fpga_region *region);
-
-This function operates on info passed in the fpga_image_info
-(region->info).
-
-This function will attempt to:
- * lock the region's mutex
- * lock the region's FPGA manager
- * build a list of FPGA bridges if a method has been specified to do so
- * disable the bridges
- * program the FPGA
- * re-enable the bridges
- * release the locks
-
-=============
-Usage example
-=============
-
-First, allocate the info struct:
-
-	info = fpga_image_info_alloc(dev);
-	if (!info)
-		return -ENOMEM;
-
-Set flags as needed, i.e.
-
-	info->flags |= FPGA_MGR_PARTIAL_RECONFIG;
-
-Point to your FPGA image, such as:
-
-	info->sgt = &sgt;
-
-Add info to region and do the programming:
-
-	region->info = info;
-	ret = fpga_region_program_fpga(region);
-
-Then enumerate whatever hardware has appeared in the FPGA.
-
---
-[1] ../devicetree/bindings/fpga/fpga-region.txt
-[2] ./fpga-mgr.txt
-[3] ../../drivers/fpga/of-fpga-region.c
diff --git a/Documentation/fpga/overview.txt b/Documentation/fpga/overview.txt
deleted file mode 100644
index 0f1236e7e675..000000000000
--- a/Documentation/fpga/overview.txt
+++ /dev/null
@@ -1,23 +0,0 @@
-Linux kernel FPGA support
-
-Alan Tull 2017
-
-The main point of this project has been to separate the out the upper layers
-that know when to reprogram a FPGA from the lower layers that know how to
-reprogram a specific FPGA device.  The intention is to make this manufacturer
-agnostic, understanding that of course the FPGA images are very device specific
-themselves.
-
-The framework in the kernel includes:
-* low level FPGA manager drivers that know how to program a specific device
-* the fpga-mgr framework they are registered with
-* low level FPGA bridge drivers for hard/soft bridges which are intended to
-  be disable during FPGA programming
-* the fpga-bridge framework they are registered with
-* the fpga-region framework which associates and controls managers and bridges
-  as reconfigurable regions
-* the of-fpga-region support for reprogramming FPGAs when device tree overlays
-  are applied.
-
-I would encourage you the user to add code that creates FPGA regions rather
-that trying to control managers and bridges separately.
diff --git a/Documentation/gpu/drivers.rst b/Documentation/gpu/drivers.rst
index e8c84419a2a1..f982558fc25d 100644
--- a/Documentation/gpu/drivers.rst
+++ b/Documentation/gpu/drivers.rst
@@ -10,8 +10,10 @@ GPU Driver Documentation
    tegra
    tinydrm
    tve200
+   v3d
    vc4
    bridge/dw-hdmi
+   xen-front
 
 .. only::  subproject and html
 
diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 41dc881b00dc..055df45596c1 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -58,6 +58,12 @@ Intel GVT-g Host Support(vGPU device model)
 .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
    :internal:
 
+Workarounds
+-----------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_workarounds.c
+   :doc: Hardware workarounds
+
 Display Hardware Handling
 =========================
 
@@ -249,6 +255,103 @@ Memory Management and Command Submission
 This sections covers all things related to the GEM implementation in the
 i915 driver.
 
+Intel GPU Basics
+----------------
+
+An Intel GPU has multiple engines. There are several engine types.
+
+- RCS engine is for rendering 3D and performing compute, this is named
+  `I915_EXEC_RENDER` in user space.
+- BCS is a blitting (copy) engine, this is named `I915_EXEC_BLT` in user
+  space.
+- VCS is a video encode and decode engine, this is named `I915_EXEC_BSD`
+  in user space
+- VECS is video enhancement engine, this is named `I915_EXEC_VEBOX` in user
+  space.
+- The enumeration `I915_EXEC_DEFAULT` does not refer to specific engine;
+  instead it is to be used by user space to specify a default rendering
+  engine (for 3D) that may or may not be the same as RCS.
+
+The Intel GPU family is a family of integrated GPU's using Unified
+Memory Access. For having the GPU "do work", user space will feed the
+GPU batch buffers via one of the ioctls `DRM_IOCTL_I915_GEM_EXECBUFFER2`
+or `DRM_IOCTL_I915_GEM_EXECBUFFER2_WR`. Most such batchbuffers will
+instruct the GPU to perform work (for example rendering) and that work
+needs memory from which to read and memory to which to write. All memory
+is encapsulated within GEM buffer objects (usually created with the ioctl
+`DRM_IOCTL_I915_GEM_CREATE`). An ioctl providing a batchbuffer for the GPU
+to create will also list all GEM buffer objects that the batchbuffer reads
+and/or writes. For implementation details of memory management see
+`GEM BO Management Implementation Details`_.
+
+The i915 driver allows user space to create a context via the ioctl
+`DRM_IOCTL_I915_GEM_CONTEXT_CREATE` which is identified by a 32-bit
+integer. Such a context should be viewed by user-space as -loosely-
+analogous to the idea of a CPU process of an operating system. The i915
+driver guarantees that commands issued to a fixed context are to be
+executed so that writes of a previously issued command are seen by
+reads of following commands. Actions issued between different contexts
+(even if from the same file descriptor) are NOT given that guarantee
+and the only way to synchronize across contexts (even from the same
+file descriptor) is through the use of fences. At least as far back as
+Gen4, also have that a context carries with it a GPU HW context;
+the HW context is essentially (most of atleast) the state of a GPU.
+In addition to the ordering guarantees, the kernel will restore GPU
+state via HW context when commands are issued to a context, this saves
+user space the need to restore (most of atleast) the GPU state at the
+start of each batchbuffer. The non-deprecated ioctls to submit batchbuffer
+work can pass that ID (in the lower bits of drm_i915_gem_execbuffer2::rsvd1)
+to identify what context to use with the command.
+
+The GPU has its own memory management and address space. The kernel
+driver maintains the memory translation table for the GPU. For older
+GPUs (i.e. those before Gen8), there is a single global such translation
+table, a global Graphics Translation Table (GTT). For newer generation
+GPUs each context has its own translation table, called Per-Process
+Graphics Translation Table (PPGTT). Of important note, is that although
+PPGTT is named per-process it is actually per context. When user space
+submits a batchbuffer, the kernel walks the list of GEM buffer objects
+used by the batchbuffer and guarantees that not only is the memory of
+each such GEM buffer object resident but it is also present in the
+(PP)GTT. If the GEM buffer object is not yet placed in the (PP)GTT,
+then it is given an address. Two consequences of this are: the kernel
+needs to edit the batchbuffer submitted to write the correct value of
+the GPU address when a GEM BO is assigned a GPU address and the kernel
+might evict a different GEM BO from the (PP)GTT to make address room
+for another GEM BO. Consequently, the ioctls submitting a batchbuffer
+for execution also include a list of all locations within buffers that
+refer to GPU-addresses so that the kernel can edit the buffer correctly.
+This process is dubbed relocation.
+
+GEM BO Management Implementation Details
+----------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_vma.h
+   :doc: Virtual Memory Address
+
+Buffer Object Eviction
+----------------------
+
+This section documents the interface functions for evicting buffer
+objects to make space available in the virtual gpu address spaces. Note
+that this is mostly orthogonal to shrinking buffer objects caches, which
+has the goal to make main memory (shared with the gpu through the
+unified memory architecture) available.
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_evict.c
+   :internal:
+
+Buffer Object Memory Shrinking
+------------------------------
+
+This section documents the interface function for shrinking memory usage
+of buffer object caches. Shrinking is used to make main memory
+available. Note that this is mostly orthogonal to evicting buffer
+objects, which has the goal to make space in gpu virtual address spaces.
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_shrinker.c
+   :internal:
+
 Batchbuffer Parsing
 -------------------
 
@@ -267,6 +370,12 @@ Batchbuffer Pools
 .. kernel-doc:: drivers/gpu/drm/i915/i915_gem_batch_pool.c
    :internal:
 
+User Batchbuffer Execution
+--------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_execbuffer.c
+   :doc: User command execution
+
 Logical Rings, Logical Ring Contexts and Execlists
 --------------------------------------------------
 
@@ -312,28 +421,14 @@ Object Tiling IOCTLs
 .. kernel-doc:: drivers/gpu/drm/i915/i915_gem_tiling.c
    :doc: buffer object tiling
 
-Buffer Object Eviction
-----------------------
-
-This section documents the interface functions for evicting buffer
-objects to make space available in the virtual gpu address spaces. Note
-that this is mostly orthogonal to shrinking buffer objects caches, which
-has the goal to make main memory (shared with the gpu through the
-unified memory architecture) available.
-
-.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_evict.c
-   :internal:
-
-Buffer Object Memory Shrinking
-------------------------------
+WOPCM
+=====
 
-This section documents the interface function for shrinking memory usage
-of buffer object caches. Shrinking is used to make main memory
-available. Note that this is mostly orthogonal to evicting buffer
-objects, which has the goal to make space in gpu virtual address spaces.
+WOPCM Layout
+------------
 
-.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_shrinker.c
-   :internal:
+.. kernel-doc:: drivers/gpu/drm/i915/intel_wopcm.c
+   :doc: WOPCM Layout
 
 GuC
 ===
@@ -359,6 +454,12 @@ GuC Firmware Layout
 .. kernel-doc:: drivers/gpu/drm/i915/intel_guc_fwif.h
    :doc: GuC Firmware Layout
 
+GuC Address Space
+-----------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_guc.c
+   :doc: GuC Address Space
+
 Tracing
 =======
 
diff --git a/Documentation/gpu/kms-properties.csv b/Documentation/gpu/kms-properties.csv
index 6b28b014cb7d..07ed22ea3bd6 100644
--- a/Documentation/gpu/kms-properties.csv
+++ b/Documentation/gpu/kms-properties.csv
@@ -98,5 +98,4 @@ radeon,DVI-I,“coherent�,RANGE,"Min=0, Max=1",Connector,TBD
 ,,"""underscan vborder""",RANGE,"Min=0, Max=128",Connector,TBD
 ,Audio,“audio�,ENUM,"{ ""off"", ""on"", ""auto"" }",Connector,TBD
 ,FMT Dithering,“dither�,ENUM,"{ ""off"", ""on"" }",Connector,TBD
-rcar-du,Generic,"""alpha""",RANGE,"Min=0, Max=255",Plane,TBD
 ,,"""colorkey""",RANGE,"Min=0, Max=0x01ffffff",Plane,TBD
diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index f4d0b3476d9c..a7c150d6b63f 100644
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@@ -212,6 +212,24 @@ probably use drm_fb_helper_fbdev_teardown().
 
 Contact: Maintainer of the driver you plan to convert
 
+Clean up mmap forwarding
+------------------------
+
+A lot of drivers forward gem mmap calls to dma-buf mmap for imported buffers.
+And also a lot of them forward dma-buf mmap to the gem mmap implementations.
+Would be great to refactor this all into a set of small common helpers.
+
+Contact: Daniel Vetter
+
+Put a reservation_object into drm_gem_object
+--------------------------------------------
+
+This would remove the need for the ->gem_prime_res_obj callback. It would also
+allow us to implement generic helpers for waiting for a bo, allowing for quite a
+bit of refactoring in the various wait ioctl implementations.
+
+Contact: Daniel Vetter
+
 idr_init_base()
 ---------------
 
diff --git a/Documentation/gpu/xen-front.rst b/Documentation/gpu/xen-front.rst
new file mode 100644
index 000000000000..d988da7d1983
--- /dev/null
+++ b/Documentation/gpu/xen-front.rst
@@ -0,0 +1,31 @@
+====================================================
+ drm/xen-front Xen para-virtualized frontend driver
+====================================================
+
+This frontend driver implements Xen para-virtualized display
+according to the display protocol described at
+include/xen/interface/io/displif.h
+
+Driver modes of operation in terms of display buffers used
+==========================================================
+
+.. kernel-doc:: drivers/gpu/drm/xen/xen_drm_front.h
+   :doc: Driver modes of operation in terms of display buffers used
+
+Buffers allocated by the frontend driver
+----------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/xen/xen_drm_front.h
+   :doc: Buffers allocated by the frontend driver
+
+Buffers allocated by the backend
+--------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/xen/xen_drm_front.h
+   :doc: Buffers allocated by the backend
+
+Driver limitations
+==================
+
+.. kernel-doc:: drivers/gpu/drm/xen/xen_drm_front.h
+   :doc: Driver limitations
diff --git a/Documentation/hwmon/hwmon-kernel-api.txt b/Documentation/hwmon/hwmon-kernel-api.txt
index 53a806696c64..eb7a78aebb38 100644
--- a/Documentation/hwmon/hwmon-kernel-api.txt
+++ b/Documentation/hwmon/hwmon-kernel-api.txt
@@ -71,7 +71,8 @@ hwmon_device_register_with_info is the most comprehensive and preferred means
 to register a hardware monitoring device. It creates the standard sysfs
 attributes in the hardware monitoring core, letting the driver focus on reading
 from and writing to the chip instead of having to bother with sysfs attributes.
-Its parameters are described in more detail below.
+The parent device parameter cannot be NULL with non-NULL chip info. Its
+parameters are described in more detail below.
 
 devm_hwmon_device_register_with_info is similar to
 hwmon_device_register_with_info. However, it is device managed, meaning the
diff --git a/Documentation/hwmon/ltc2990 b/Documentation/hwmon/ltc2990
index c25211e90bdc..3ed68f676c0f 100644
--- a/Documentation/hwmon/ltc2990
+++ b/Documentation/hwmon/ltc2990
@@ -8,6 +8,7 @@ Supported chips:
     Datasheet: http://www.linear.com/product/ltc2990
 
 Author: Mike Looijmans <mike.looijmans@topic.nl>
+        Tom Levens <tom.levens@cern.ch>
 
 
 Description
@@ -16,10 +17,8 @@ Description
 LTC2990 is a Quad I2C Voltage, Current and Temperature Monitor.
 The chip's inputs can measure 4 voltages, or two inputs together (1+2 and 3+4)
 can be combined to measure a differential voltage, which is typically used to
-measure current through a series resistor, or a temperature.
-
-This driver currently uses the 2x differential mode only. In order to support
-other modes, the driver will need to be expanded.
+measure current through a series resistor, or a temperature with an external
+diode.
 
 
 Usage Notes
@@ -32,12 +31,19 @@ devices explicitly.
 Sysfs attributes
 ----------------
 
+in0_input     Voltage at Vcc pin in millivolt (range 2.5V to 5V)
+temp1_input   Internal chip temperature in millidegrees Celcius
+
+A subset of the following attributes are visible, depending on the measurement
+mode of the chip.
+
+in[1-4]_input Voltage at V[1-4] pin in millivolt
+temp2_input   External temperature sensor TR1 in millidegrees Celcius
+temp3_input   External temperature sensor TR2 in millidegrees Celcius
+curr1_input   Current in mA across V1-V2 assuming a 1mOhm sense resistor
+curr2_input   Current in mA across V3-V4 assuming a 1mOhm sense resistor
+
 The "curr*_input" measurements actually report the voltage drop across the
 input pins in microvolts. This is equivalent to the current through a 1mOhm
 sense resistor. Divide the reported value by the actual sense resistor value
 in mOhm to get the actual value.
-
-in0_input     Voltage at Vcc pin in millivolt (range 2.5V to 5V)
-temp1_input   Internal chip temperature in millidegrees Celcius
-curr1_input   Current in mA across v1-v2 assuming a 1mOhm sense resistor.
-curr2_input   Current in mA across v3-v4 assuming a 1mOhm sense resistor.
diff --git a/Documentation/i2c/busses/i2c-ocores b/Documentation/i2c/busses/i2c-ocores
index c269aaa2f26a..9e1dfe7553ad 100644
--- a/Documentation/i2c/busses/i2c-ocores
+++ b/Documentation/i2c/busses/i2c-ocores
@@ -2,7 +2,7 @@ Kernel driver i2c-ocores
 
 Supported adapters:
   * OpenCores.org I2C controller by Richard Herveille (see datasheet link)
-    Datasheet: http://www.opencores.org/projects.cgi/web/i2c/overview
+    https://opencores.org/project/i2c/overview
 
 Author: Peter Korsgaard <jacmet@sunsite.dk>
 
diff --git a/Documentation/i2c/dev-interface b/Documentation/i2c/dev-interface
index d04e6e4964ee..fbed645ccd75 100644
--- a/Documentation/i2c/dev-interface
+++ b/Documentation/i2c/dev-interface
@@ -9,8 +9,8 @@ i2c adapters present on your system at a given time. i2cdetect is part of
 the i2c-tools package.
 
 I2C device files are character device files with major device number 89
-and a minor device number corresponding to the number assigned as 
-explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ..., 
+and a minor device number corresponding to the number assigned as
+explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ...,
 i2c-10, ...). All 256 minor device numbers are reserved for i2c.
 
 
@@ -23,11 +23,6 @@ First, you need to include these two headers:
   #include <linux/i2c-dev.h>
   #include <i2c/smbus.h>
 
-(Please note that there are two files named "i2c-dev.h" out there. One is
-distributed with the Linux kernel and the other one is included in the
-source tree of i2c-tools. They used to be different in content but since 2012
-they're identical. You should use "linux/i2c-dev.h").
-
 Now, you have to decide which adapter you want to access. You should
 inspect /sys/class/i2c-dev/ or run "i2cdetect -l" to decide this.
 Adapter numbers are assigned somewhat dynamically, so you can not
@@ -38,7 +33,7 @@ Next thing, open the device file, as follows:
   int file;
   int adapter_nr = 2; /* probably dynamically determined */
   char filename[20];
-  
+
   snprintf(filename, 19, "/dev/i2c-%d", adapter_nr);
   file = open(filename, O_RDWR);
   if (file < 0) {
@@ -72,8 +67,10 @@ the device supports them. Both are illustrated below.
     /* res contains the read word */
   }
 
-  /* Using I2C Write, equivalent of 
-     i2c_smbus_write_word_data(file, reg, 0x6543) */
+  /*
+   * Using I2C Write, equivalent of
+   * i2c_smbus_write_word_data(file, reg, 0x6543)
+   */
   buf[0] = reg;
   buf[1] = 0x43;
   buf[2] = 0x65;
@@ -140,14 +137,14 @@ ioctl(file, I2C_RDWR, struct i2c_rdwr_ioctl_data *msgset)
   set in each message, overriding the values set with the above ioctl's.
 
 ioctl(file, I2C_SMBUS, struct i2c_smbus_ioctl_data *args)
-  Not meant to be called  directly; instead, use the access functions
-  below.
+  If possible, use the provided i2c_smbus_* methods described below instead
+  of issuing direct ioctls.
 
 You can do plain i2c transactions by using read(2) and write(2) calls.
 You do not need to pass the address byte; instead, set it through
 ioctl I2C_SLAVE before you try to access the device.
 
-You can do SMBus level transactions (see documentation file smbus-protocol 
+You can do SMBus level transactions (see documentation file smbus-protocol
 for details) through the following functions:
   __s32 i2c_smbus_write_quick(int file, __u8 value);
   __s32 i2c_smbus_read_byte(int file);
@@ -158,7 +155,7 @@ for details) through the following functions:
   __s32 i2c_smbus_write_word_data(int file, __u8 command, __u16 value);
   __s32 i2c_smbus_process_call(int file, __u8 command, __u16 value);
   __s32 i2c_smbus_read_block_data(int file, __u8 command, __u8 *values);
-  __s32 i2c_smbus_write_block_data(int file, __u8 command, __u8 length, 
+  __s32 i2c_smbus_write_block_data(int file, __u8 command, __u8 length,
                                    __u8 *values);
 All these transactions return -1 on failure; you can read errno to see
 what happened. The 'write' transactions return 0 on success; the
@@ -166,10 +163,9 @@ what happened. The 'write' transactions return 0 on success; the
 returns the number of values read. The block buffers need not be longer
 than 32 bytes.
 
-The above functions are all inline functions, that resolve to calls to
-the i2c_smbus_access function, that on its turn calls a specific ioctl
-with the data in a specific format. Read the source code if you
-want to know what happens behind the screens.
+The above functions are made available by linking against the libi2c library,
+which is provided by the i2c-tools project.  See:
+https://git.kernel.org/pub/scm/utils/i2c-tools/i2c-tools.git/.
 
 
 Implementation details
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 3b99ab931d41..fdc585703498 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -45,7 +45,7 @@ the kernel interface as seen by application developers.
 .. toctree::
    :maxdepth: 2
 
-   userspace-api/index	      
+   userspace-api/index
 
 
 Introduction to kernel development
@@ -89,6 +89,7 @@ needed).
    sound/index
    crypto/index
    filesystems/index
+   vm/index
 
 Architecture-specific documentation
 -----------------------------------
diff --git a/Documentation/ioctl/botching-up-ioctls.txt b/Documentation/ioctl/botching-up-ioctls.txt
index d02cfb48901c..883fb034bd04 100644
--- a/Documentation/ioctl/botching-up-ioctls.txt
+++ b/Documentation/ioctl/botching-up-ioctls.txt
@@ -73,7 +73,9 @@ will have a second iteration or at least an extension for any given interface.
    future extensions is going right down the gutters since someone will submit
    an ioctl struct with random stack garbage in the yet unused parts. Which
    then bakes in the ABI that those fields can never be used for anything else
-   but garbage.
+   but garbage. This is also the reason why you must explicitly pad all
+   structures, even if you never use them in an array - the padding the compiler
+   might insert could contain garbage.
 
  * Have simple testcases for all of the above.
 
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 84bb74dcae12..a12488d45c40 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -217,7 +217,6 @@ Code  Seq#(hex)	Include File		Comments
 'd'	02-40	pcmcia/ds.h		conflict!
 'd'	F0-FF	linux/digi1.h
 'e'	all	linux/digi1.h		conflict!
-'e'	00-1F	drivers/net/irda/irtty-sir.h	conflict!
 'f'	00-1F	linux/ext2_fs.h		conflict!
 'f'	00-1F	linux/ext3_fs.h		conflict!
 'f'	00-0F	fs/jfs/jfs_dinode.h	conflict!
@@ -247,7 +246,6 @@ Code  Seq#(hex)	Include File		Comments
 'm'	all	linux/synclink.h	conflict!
 'm'	00-19	drivers/message/fusion/mptctl.h	conflict!
 'm'	00	drivers/scsi/megaraid/megaraid_ioctl.h	conflict!
-'m'	00-1F	net/irda/irmod.h	conflict!
 'n'	00-7F	linux/ncp_fs.h and fs/ncpfs/ioctl.c
 'n'	80-8F	uapi/linux/nilfs2_api.h	NILFS2
 'n'	E0-FF	linux/matroxfb.h	matroxfb
@@ -298,7 +296,8 @@ Code  Seq#(hex)	Include File		Comments
 0x90	00	drivers/cdrom/sbpcd.h
 0x92	00-0F	drivers/usb/mon/mon_bin.c
 0x93	60-7F	linux/auto_fs.h
-0x94	all	fs/btrfs/ioctl.h
+0x94	all	fs/btrfs/ioctl.h	Btrfs filesystem
+		and linux/fs.h		some lifted to vfs/generic
 0x97	00-7F	fs/ceph/ioctl.h		Ceph file system
 0x99	00-0F				537-Addinboard driver
 					<mailto:buk@buks.ipn.de>
@@ -329,6 +328,7 @@ Code  Seq#(hex)	Include File		Comments
 0xCA	80-BF	uapi/scsi/cxlflash_ioctl.h
 0xCB	00-1F	CBM serial IEC bus	in development:
 					<mailto:michael.klein@puffin.lb.shuttle.de>
+0xCC	00-0F	drivers/misc/ibmvmc.h    pseries VMC driver
 0xCD	01	linux/reiserfs_fs.h
 0xCF	02	fs/cifs/ioctl.c
 0xDB	00-0F	drivers/char/mwave/mwavepub.h
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index f5b9493f04ad..0e966e8f9ec7 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -198,14 +198,6 @@ applicable everywhere (see syntax).
     enables the third modular state for all config symbols.
     At most one symbol may have the "modules" option set.
 
-  - "env"=<value>
-    This imports the environment variable into Kconfig. It behaves like
-    a default, except that the value comes from the environment, this
-    also means that the behaviour when mixing it with normal defaults is
-    undefined at this point. The symbol is currently not exported back
-    to the build environment (if this is desired, it can be done via
-    another symbol).
-
   - "allnoconfig_y"
     This declares the symbol as one that should have the value y when
     using "allnoconfig". Used for symbols that hide other symbols.
diff --git a/Documentation/kbuild/kconfig-macro-language.txt b/Documentation/kbuild/kconfig-macro-language.txt
new file mode 100644
index 000000000000..07da2ea68dce
--- /dev/null
+++ b/Documentation/kbuild/kconfig-macro-language.txt
@@ -0,0 +1,242 @@
+Concept
+-------
+
+The basic idea was inspired by Make. When we look at Make, we notice sort of
+two languages in one. One language describes dependency graphs consisting of
+targets and prerequisites. The other is a macro language for performing textual
+substitution.
+
+There is clear distinction between the two language stages. For example, you
+can write a makefile like follows:
+
+    APP := foo
+    SRC := foo.c
+    CC := gcc
+
+    $(APP): $(SRC)
+            $(CC) -o $(APP) $(SRC)
+
+The macro language replaces the variable references with their expanded form,
+and handles as if the source file were input like follows:
+
+    foo: foo.c
+            gcc -o foo foo.c
+
+Then, Make analyzes the dependency graph and determines the targets to be
+updated.
+
+The idea is quite similar in Kconfig - it is possible to describe a Kconfig
+file like this:
+
+    CC := gcc
+
+    config CC_HAS_FOO
+            def_bool $(shell, $(srctree)/scripts/gcc-check-foo.sh $(CC))
+
+The macro language in Kconfig processes the source file into the following
+intermediate:
+
+    config CC_HAS_FOO
+            def_bool y
+
+Then, Kconfig moves onto the evaluation stage to resolve inter-symbol
+dependency as explained in kconfig-language.txt.
+
+
+Variables
+---------
+
+Like in Make, a variable in Kconfig works as a macro variable.  A macro
+variable is expanded "in place" to yield a text string that may then be
+expanded further. To get the value of a variable, enclose the variable name in
+$( ). The parentheses are required even for single-letter variable names; $X is
+a syntax error. The curly brace form as in ${CC} is not supported either.
+
+There are two types of variables: simply expanded variables and recursively
+expanded variables.
+
+A simply expanded variable is defined using the := assignment operator. Its
+righthand side is expanded immediately upon reading the line from the Kconfig
+file.
+
+A recursively expanded variable is defined using the = assignment operator.
+Its righthand side is simply stored as the value of the variable without
+expanding it in any way. Instead, the expansion is performed when the variable
+is used.
+
+There is another type of assignment operator; += is used to append text to a
+variable. The righthand side of += is expanded immediately if the lefthand
+side was originally defined as a simple variable. Otherwise, its evaluation is
+deferred.
+
+The variable reference can take parameters, in the following form:
+
+  $(name,arg1,arg2,arg3)
+
+You can consider the parameterized reference as a function. (more precisely,
+"user-defined function" in contrast to "built-in function" listed below).
+
+Useful functions must be expanded when they are used since the same function is
+expanded differently if different parameters are passed. Hence, a user-defined
+function is defined using the = assignment operator. The parameters are
+referenced within the body definition with $(1), $(2), etc.
+
+In fact, recursively expanded variables and user-defined functions are the same
+internally. (In other words, "variable" is "function with zero argument".)
+When we say "variable" in a broad sense, it includes "user-defined function".
+
+
+Built-in functions
+------------------
+
+Like Make, Kconfig provides several built-in functions. Every function takes a
+particular number of arguments.
+
+In Make, every built-in function takes at least one argument. Kconfig allows
+zero argument for built-in functions, such as $(fileno), $(lineno). You could
+consider those as "built-in variable", but it is just a matter of how we call
+it after all. Let's say "built-in function" here to refer to natively supported
+functionality.
+
+Kconfig currently supports the following built-in functions.
+
+ - $(shell,command)
+
+  The "shell" function accepts a single argument that is expanded and passed
+  to a subshell for execution. The standard output of the command is then read
+  and returned as the value of the function. Every newline in the output is
+  replaced with a space. Any trailing newlines are deleted. The standard error
+  is not returned, nor is any program exit status.
+
+ - $(info,text)
+
+  The "info" function takes a single argument and prints it to stdout.
+  It evaluates to an empty string.
+
+ - $(warning-if,condition,text)
+
+  The "warning-if" function takes two arguments. If the condition part is "y",
+  the text part is sent to stderr. The text is prefixed with the name of the
+  current Kconfig file and the current line number.
+
+ - $(error-if,condition,text)
+
+  The "error-if" function is similar to "warning-if", but it terminates the
+  parsing immediately if the condition part is "y".
+
+ - $(filename)
+
+  The 'filename' takes no argument, and $(filename) is expanded to the file
+  name being parsed.
+
+ - $(lineno)
+
+  The 'lineno' takes no argument, and $(lineno) is expanded to the line number
+  being parsed.
+
+
+Make vs Kconfig
+---------------
+
+Kconfig adopts Make-like macro language, but the function call syntax is
+slightly different.
+
+A function call in Make looks like this:
+
+  $(func-name arg1,arg2,arg3)
+
+The function name and the first argument are separated by at least one
+whitespace. Then, leading whitespaces are trimmed from the first argument,
+while whitespaces in the other arguments are kept. You need to use a kind of
+trick to start the first parameter with spaces. For example, if you want
+to make "info" function print "  hello", you can write like follows:
+
+  empty :=
+  space := $(empty) $(empty)
+  $(info $(space)$(space)hello)
+
+Kconfig uses only commas for delimiters, and keeps all whitespaces in the
+function call. Some people prefer putting a space after each comma delimiter:
+
+  $(func-name, arg1, arg2, arg3)
+
+In this case, "func-name" will receive " arg1", " arg2", " arg3". The presence
+of leading spaces may matter depending on the function. The same applies to
+Make - for example, $(subst .c, .o, $(sources)) is a typical mistake; it
+replaces ".c" with " .o".
+
+In Make, a user-defined function is referenced by using a built-in function,
+'call', like this:
+
+    $(call my-func,arg1,arg2,arg3)
+
+Kconfig invokes user-defined functions and built-in functions in the same way.
+The omission of 'call' makes the syntax shorter.
+
+In Make, some functions treat commas verbatim instead of argument separators.
+For example, $(shell echo hello, world) runs the command "echo hello, world".
+Likewise, $(info hello, world) prints "hello, world" to stdout. You could say
+this is _useful_ inconsistency.
+
+In Kconfig, for simpler implementation and grammatical consistency, commas that
+appear in the $( ) context are always delimiters. It means
+
+  $(shell, echo hello, world)
+
+is an error because it is passing two parameters where the 'shell' function
+accepts only one. To pass commas in arguments, you can use the following trick:
+
+  comma := ,
+  $(shell, echo hello$(comma) world)
+
+
+Caveats
+-------
+
+A variable (or function) cannot be expanded across tokens. So, you cannot use
+a variable as a shorthand for an expression that consists of multiple tokens.
+The following works:
+
+    RANGE_MIN := 1
+    RANGE_MAX := 3
+
+    config FOO
+            int "foo"
+            range $(RANGE_MIN) $(RANGE_MAX)
+
+But, the following does not work:
+
+    RANGES := 1 3
+
+    config FOO
+            int "foo"
+            range $(RANGES)
+
+A variable cannot be expanded to any keyword in Kconfig.  The following does
+not work:
+
+    MY_TYPE := tristate
+
+    config FOO
+            $(MY_TYPE) "foo"
+            default y
+
+Obviously from the design, $(shell command) is expanded in the textual
+substitution phase. You cannot pass symbols to the 'shell' function.
+The following does not work as expected.
+
+    config ENDIAN_FLAG
+            string
+            default "-mbig-endian" if CPU_BIG_ENDIAN
+            default "-mlittle-endian" if CPU_LITTLE_ENDIAN
+
+    config CC_HAS_ENDIAN_FLAG
+            def_bool $(shell $(srctree)/scripts/gcc-check-flag ENDIAN_FLAG)
+
+Instead, you can do like follows so that any function call is statically
+expanded.
+
+    config CC_HAS_ENDIAN_FLAG
+            bool
+            default $(shell $(srctree)/scripts/gcc-check-flag -mbig-endian) if CPU_BIG_ENDIAN
+            default $(shell $(srctree)/scripts/gcc-check-flag -mlittle-endian) if CPU_LITTLE_ENDIAN
diff --git a/Documentation/livepatch/shadow-vars.txt b/Documentation/livepatch/shadow-vars.txt
index 89c66634d600..ecc09a7be5dd 100644
--- a/Documentation/livepatch/shadow-vars.txt
+++ b/Documentation/livepatch/shadow-vars.txt
@@ -34,9 +34,13 @@ meta-data and shadow-data:
   - data[] - storage for shadow data
 
 It is important to note that the klp_shadow_alloc() and
-klp_shadow_get_or_alloc() calls, described below, store a *copy* of the
-data that the functions are provided.  Callers should provide whatever
-mutual exclusion is required of the shadow data.
+klp_shadow_get_or_alloc() are zeroing the variable by default.
+They also allow to call a custom constructor function when a non-zero
+value is needed. Callers should provide whatever mutual exclusion
+is required.
+
+Note that the constructor is called under klp_shadow_lock spinlock. It allows
+to do actions that can be done only once when a new variable is allocated.
 
 * klp_shadow_get() - retrieve a shadow variable data pointer
   - search hashtable for <obj, id> pair
@@ -47,7 +51,7 @@ mutual exclusion is required of the shadow data.
     - WARN and return NULL
   - if <obj, id> doesn't already exist
     - allocate a new shadow variable
-    - copy data into the new shadow variable
+    - initialize the variable using a custom constructor and data when provided
     - add <obj, id> to the global hashtable
 
 * klp_shadow_get_or_alloc() - get existing or alloc a new shadow variable
@@ -56,16 +60,20 @@ mutual exclusion is required of the shadow data.
     - return existing shadow variable
   - if <obj, id> doesn't already exist
     - allocate a new shadow variable
-    - copy data into the new shadow variable
+    - initialize the variable using a custom constructor and data when provided
     - add <obj, id> pair to the global hashtable
 
 * klp_shadow_free() - detach and free a <obj, id> shadow variable
   - find and remove a <obj, id> reference from global hashtable
-    - if found, free shadow variable
+    - if found
+      - call destructor function if defined
+      - free shadow variable
 
 * klp_shadow_free_all() - detach and free all <*, id> shadow variables
   - find and remove any <*, id> references from global hashtable
-    - if found, free shadow variable
+    - if found
+      - call destructor function if defined
+      - free shadow variable
 
 
 2. Use cases
@@ -107,7 +115,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp);
 
 	/* Attach a corresponding shadow variable, then initialize it */
-	ps_lock = klp_shadow_alloc(sta, PS_LOCK, NULL, sizeof(*ps_lock), gfp);
+	ps_lock = klp_shadow_alloc(sta, PS_LOCK, sizeof(*ps_lock), gfp,
+				   NULL, NULL);
 	if (!ps_lock)
 		goto shadow_fail;
 	spin_lock_init(ps_lock);
@@ -131,7 +140,7 @@ variable:
 
 void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 {
-	klp_shadow_free(sta, PS_LOCK);
+	klp_shadow_free(sta, PS_LOCK, NULL);
 	kfree(sta);
 	...
 
@@ -148,16 +157,24 @@ shadow variables to parents already in-flight.
 For commit 1d147bfa6429, a good spot to allocate a shadow spinlock is
 inside ieee80211_sta_ps_deliver_wakeup():
 
+int ps_lock_shadow_ctor(void *obj, void *shadow_data, void *ctor_data)
+{
+	spinlock_t *lock = shadow_data;
+
+	spin_lock_init(lock);
+	return 0;
+}
+
 #define PS_LOCK 1
 void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 {
-	DEFINE_SPINLOCK(ps_lock_fallback);
 	spinlock_t *ps_lock;
 
 	/* sync with ieee80211_tx_h_unicast_ps_buf */
 	ps_lock = klp_shadow_get_or_alloc(sta, PS_LOCK,
-			&ps_lock_fallback, sizeof(ps_lock_fallback),
-			GFP_ATOMIC);
+			sizeof(*ps_lock), GFP_ATOMIC,
+			ps_lock_shadow_ctor, NULL);
+
 	if (ps_lock)
 		spin_lock(ps_lock);
 	...
diff --git a/Documentation/media/uapi/rc/keytable.c.rst b/Documentation/media/uapi/rc/keytable.c.rst
index e6ce1e3f5a78..217237f93b37 100644
--- a/Documentation/media/uapi/rc/keytable.c.rst
+++ b/Documentation/media/uapi/rc/keytable.c.rst
@@ -7,7 +7,7 @@ file: uapi/v4l/keytable.c
 
     /* keytable.c - This program allows checking/replacing keys at IR
 
-       Copyright (C) 2006-2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+       Copyright (C) 2006-2009 Mauro Carvalho Chehab <mchehab@kernel.org>
 
        This program is free software; you can redistribute it and/or modify
        it under the terms of the GNU General Public License as published by
diff --git a/Documentation/media/uapi/v4l/v4l2grab.c.rst b/Documentation/media/uapi/v4l/v4l2grab.c.rst
index 5aabd0b7b089..f0d0ab6abd41 100644
--- a/Documentation/media/uapi/v4l/v4l2grab.c.rst
+++ b/Documentation/media/uapi/v4l/v4l2grab.c.rst
@@ -6,7 +6,7 @@ file: media/v4l/v4l2grab.c
 .. code-block:: c
 
     /* V4L2 video picture grabber
-       Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+       Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@kernel.org>
 
        This program is free software; you can redistribute it and/or modify
        it under the terms of the GNU General Public License as published by
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 6dafc8085acc..a02d6bbfc9d0 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1920,9 +1920,6 @@ There are some more advanced barrier functions:
 		/* assign ownership */
 		desc->status = DEVICE_OWN;
 
-		/* force memory to sync before notifying device via MMIO */
-		wmb();
-
 		/* notify device of new descriptors */
 		writel(DESC_NOTIFY, doorbell);
 	}
@@ -1930,11 +1927,15 @@ There are some more advanced barrier functions:
      The dma_rmb() allows us guarantee the device has released ownership
      before we read the data from the descriptor, and the dma_wmb() allows
      us to guarantee the data is written to the descriptor before the device
-     can see it now has ownership.  The wmb() is needed to guarantee that the
-     cache coherent memory writes have completed before attempting a write to
-     the cache incoherent MMIO region.
+     can see it now has ownership.  Note that, when using writel(), a prior
+     wmb() is not needed to guarantee that the cache coherent memory writes
+     have completed before writing to the MMIO region.  The cheaper
+     writel_relaxed() does not provide this guarantee and must not be used
+     here.
 
-     See Documentation/DMA-API.txt for more information on consistent memory.
+     See the subsection "Kernel I/O barrier effects" for more information on
+     relaxed I/O accessors and the Documentation/DMA-API.txt file for more
+     information on consistent memory.
 
 
 MMIO WRITE BARRIER
@@ -2903,7 +2904,7 @@ is discarded from the CPU's cache and reloaded.  To deal with this, the
 appropriate part of the kernel must invalidate the overlapping bits of the
 cache on each CPU.
 
-See Documentation/cachetlb.txt for more information on cache management.
+See Documentation/core-api/cachetlb.rst for more information on cache management.
 
 
 CACHE COHERENCY VS MMIO
@@ -3083,7 +3084,7 @@ CIRCULAR BUFFERS
 Memory barriers can be used to implement circular buffering without the need
 of a lock to serialise the producer with the consumer.  See:
 
-	Documentation/circular-buffers.txt
+	Documentation/core-api/circular-buffers.rst
 
 for details.
 
diff --git a/Documentation/misc-devices/ibmvmc.rst b/Documentation/misc-devices/ibmvmc.rst
new file mode 100644
index 000000000000..46ded79554d4
--- /dev/null
+++ b/Documentation/misc-devices/ibmvmc.rst
@@ -0,0 +1,226 @@
+.. SPDX-License-Identifier: GPL-2.0+
+======================================================
+IBM Virtual Management Channel Kernel Driver (IBMVMC)
+======================================================
+
+:Authors:
+	Dave Engebretsen <engebret@us.ibm.com>,
+	Adam Reznechek <adreznec@linux.vnet.ibm.com>,
+	Steven Royer <seroyer@linux.vnet.ibm.com>,
+	Bryant G. Ly <bryantly@linux.vnet.ibm.com>,
+
+Introduction
+============
+
+Note: Knowledge of virtualization technology is required to understand
+this document.
+
+A good reference document would be:
+
+https://openpowerfoundation.org/wp-content/uploads/2016/05/LoPAPR_DRAFT_v11_24March2016_cmt1.pdf
+
+The Virtual Management Channel (VMC) is a logical device which provides an
+interface between the hypervisor and a management partition. This interface
+is like a message passing interface. This management partition is intended
+to provide an alternative to systems that use a Hardware Management
+Console (HMC) - based system management.
+
+The primary hardware management solution that is developed by IBM relies
+on an appliance server named the Hardware Management Console (HMC),
+packaged as an external tower or rack-mounted personal computer. In a
+Power Systems environment, a single HMC can manage multiple POWER
+processor-based systems.
+
+Management Application
+----------------------
+
+In the management partition, a management application exists which enables
+a system administrator to configure the system’s partitioning
+characteristics via a command line interface (CLI) or Representational
+State Transfer Application (REST API's).
+
+The management application runs on a Linux logical partition on a
+POWER8 or newer processor-based server that is virtualized by PowerVM.
+System configuration, maintenance, and control functions which
+traditionally require an HMC can be implemented in the management
+application using a combination of HMC to hypervisor interfaces and
+existing operating system methods. This tool provides a subset of the
+functions implemented by the HMC and enables basic partition configuration.
+The set of HMC to hypervisor messages supported by the management
+application component are passed to the hypervisor over a VMC interface,
+which is defined below.
+
+The VMC enables the management partition to provide basic partitioning
+functions:
+
+- Logical Partitioning Configuration
+- Start, and stop actions for individual partitions
+- Display of partition status
+- Management of virtual Ethernet
+- Management of virtual Storage
+- Basic system management
+
+Virtual Management Channel (VMC)
+--------------------------------
+
+A logical device, called the Virtual Management Channel (VMC), is defined
+for communicating between the management application and the hypervisor. It
+basically creates the pipes that enable virtualization management
+software. This device is presented to a designated management partition as
+a virtual device.
+
+This communication device uses Command/Response Queue (CRQ) and the
+Remote Direct Memory Access (RDMA) interfaces. A three-way handshake is
+defined that must take place to establish that both the hypervisor and
+management partition sides of the channel are running prior to
+sending/receiving any of the protocol messages.
+
+This driver also utilizes Transport Event CRQs. CRQ messages are sent
+when the hypervisor detects one of the peer partitions has abnormally
+terminated, or one side has called H_FREE_CRQ to close their CRQ.
+Two new classes of CRQ messages are introduced for the VMC device. VMC
+Administrative messages are used for each partition using the VMC to
+communicate capabilities to their partner. HMC Interface messages are used
+for the actual flow of HMC messages between the management partition and
+the hypervisor. As most HMC messages far exceed the size of a CRQ buffer,
+a virtual DMA (RMDA) of the HMC message data is done prior to each HMC
+Interface CRQ message. Only the management partition drives RDMA
+operations; hypervisors never directly cause the movement of message data.
+
+
+Terminology
+-----------
+RDMA
+        Remote Direct Memory Access is DMA transfer from the server to its
+        client or from the server to its partner partition. DMA refers
+        to both physical I/O to and from memory operations and to memory
+        to memory move operations.
+CRQ
+        Command/Response Queue a facility which is used to communicate
+        between partner partitions. Transport events which are signaled
+        from the hypervisor to partition are also reported in this queue.
+
+Example Management Partition VMC Driver Interface
+=================================================
+
+This section provides an example for the management application
+implementation where a device driver is used to interface to the VMC
+device. This driver consists of a new device, for example /dev/ibmvmc,
+which provides interfaces to open, close, read, write, and perform
+ioctl’s against the VMC device.
+
+VMC Interface Initialization
+----------------------------
+
+The device driver is responsible for initializing the VMC when the driver
+is loaded. It first creates and initializes the CRQ. Next, an exchange of
+VMC capabilities is performed to indicate the code version and number of
+resources available in both the management partition and the hypervisor.
+Finally, the hypervisor requests that the management partition create an
+initial pool of VMC buffers, one buffer for each possible HMC connection,
+which will be used for management application  session initialization.
+Prior to completion of this initialization sequence, the device returns
+EBUSY to open() calls. EIO is returned for all open() failures.
+
+::
+
+        Management Partition		Hypervisor
+                        CRQ INIT
+        ---------------------------------------->
+        	   CRQ INIT COMPLETE
+        <----------------------------------------
+        	      CAPABILITIES
+        ---------------------------------------->
+        	 CAPABILITIES RESPONSE
+        <----------------------------------------
+              ADD BUFFER (HMC IDX=0,1,..)         _
+        <----------------------------------------  |
+        	  ADD BUFFER RESPONSE              | - Perform # HMCs Iterations
+        ----------------------------------------> -
+
+VMC Interface Open
+------------------
+
+After the basic VMC channel has been initialized, an HMC session level
+connection can be established. The application layer performs an open() to
+the VMC device and executes an ioctl() against it, indicating the HMC ID
+(32 bytes of data) for this session. If the VMC device is in an invalid
+state, EIO will be returned for the ioctl(). The device driver creates a
+new HMC session value (ranging from 1 to 255) and HMC index value (starting
+at index 0 and ranging to 254) for this HMC ID. The driver then does an
+RDMA of the HMC ID to the hypervisor, and then sends an Interface Open
+message to the hypervisor to establish the session over the VMC. After the
+hypervisor receives this information, it sends Add Buffer messages to the
+management partition to seed an initial pool of buffers for the new HMC
+connection. Finally, the hypervisor sends an Interface Open Response
+message, to indicate that it is ready for normal runtime messaging. The
+following illustrates this VMC flow:
+
+::
+
+        Management Partition             Hypervisor
+        	      RDMA HMC ID
+        ---------------------------------------->
+        	    Interface Open
+        ---------------------------------------->
+        	      Add Buffer                  _
+        <----------------------------------------  |
+        	  Add Buffer Response              | - Perform N Iterations
+        ----------------------------------------> -
+        	Interface Open Response
+        <----------------------------------------
+
+VMC Interface Runtime
+---------------------
+
+During normal runtime, the management application and the hypervisor
+exchange HMC messages via the Signal VMC message and RDMA operations. When
+sending data to the hypervisor, the management application performs a
+write() to the VMC device, and the driver RDMA’s the data to the hypervisor
+and then sends a Signal Message. If a write() is attempted before VMC
+device buffers have been made available by the hypervisor, or no buffers
+are currently available, EBUSY is returned in response to the write(). A
+write() will return EIO for all other errors, such as an invalid device
+state. When the hypervisor sends a message to the management, the data is
+put into a VMC buffer and an Signal Message is sent to the VMC driver in
+the management partition. The driver RDMA’s the buffer into the partition
+and passes the data up to the appropriate management application via a
+read() to the VMC device. The read() request blocks if there is no buffer
+available to read. The management application may use select() to wait for
+the VMC device to become ready with data to read.
+
+::
+
+        Management Partition             Hypervisor
+        		MSG RDMA
+        ---------------------------------------->
+        		SIGNAL MSG
+        ---------------------------------------->
+        		SIGNAL MSG
+        <----------------------------------------
+        		MSG RDMA
+        <----------------------------------------
+
+VMC Interface Close
+-------------------
+
+HMC session level connections are closed by the management partition when
+the application layer performs a close() against the device. This action
+results in an Interface Close message flowing to the hypervisor, which
+causes the session to be terminated. The device driver must free any
+storage allocated for buffers for this HMC connection.
+
+::
+
+        Management Partition             Hypervisor
+        	     INTERFACE CLOSE
+        ---------------------------------------->
+                INTERFACE CLOSE RESPONSE
+        <----------------------------------------
+
+Additional Information
+======================
+
+For more information on the documentation for CRQ Messages, VMC Messages,
+HMC interface Buffers, and signal messages please refer to the Linux on
+Power Architecture Platform Reference. Section F.
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index a4508ec1816b..fd55c7de9991 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -169,7 +169,7 @@ access to BPF code as well.
 BPF engine and instruction set
 ------------------------------
 
-Under tools/net/ there's a small helper tool called bpf_asm which can
+Under tools/bpf/ there's a small helper tool called bpf_asm which can
 be used to write low-level filters for example scenarios mentioned in the
 previous section. Asm-like syntax mentioned here has been implemented in
 bpf_asm and will be used for further explanations (instead of dealing with
@@ -359,7 +359,7 @@ $ ./bpf_asm -c foo
 In particular, as usage with xt_bpf or cls_bpf can result in more complex BPF
 filters that might not be obvious at first, it's good to test filters before
 attaching to a live system. For that purpose, there's a small tool called
-bpf_dbg under tools/net/ in the kernel source directory. This debugger allows
+bpf_dbg under tools/bpf/ in the kernel source directory. This debugger allows
 for testing BPF filters against given pcap files, single stepping through the
 BPF code on the pcap's packets and to do BPF machine register dumps.
 
@@ -483,7 +483,7 @@ Example output from dmesg:
 [ 3389.935851] JIT code: 00000030: 00 e8 28 94 ff e0 83 f8 01 75 07 b8 ff ff 00 00
 [ 3389.935852] JIT code: 00000040: eb 02 31 c0 c9 c3
 
-In the kernel source tree under tools/net/, there's bpf_jit_disasm for
+In the kernel source tree under tools/bpf/, there's bpf_jit_disasm for
 generating disassembly out of the kernel log's hexdump:
 
 # ./bpf_jit_disasm
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 5dc1a040a2f1..35ffaa281b26 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1390,26 +1390,26 @@ mld_qrv - INTEGER
 	Default: 2 (as specified by RFC3810 9.1)
 	Minimum: 1 (as specified by RFC6636 4.5)
 
-max_dst_opts_cnt - INTEGER
+max_dst_opts_number - INTEGER
 	Maximum number of non-padding TLVs allowed in a Destination
 	options extension header. If this value is less than zero
 	then unknown options are disallowed and the number of known
 	TLVs allowed is the absolute value of this number.
 	Default: 8
 
-max_hbh_opts_cnt - INTEGER
+max_hbh_opts_number - INTEGER
 	Maximum number of non-padding TLVs allowed in a Hop-by-Hop
 	options extension header. If this value is less than zero
 	then unknown options are disallowed and the number of known
 	TLVs allowed is the absolute value of this number.
 	Default: 8
 
-max dst_opts_len - INTEGER
+max_dst_opts_length - INTEGER
 	Maximum length allowed for a Destination options extension
 	header.
 	Default: INT_MAX (unlimited)
 
-max hbh_opts_len - INTEGER
+max_hbh_length - INTEGER
 	Maximum length allowed for a Hop-by-Hop options extension
 	header.
 	Default: INT_MAX (unlimited)
@@ -2126,18 +2126,3 @@ max_dgram_qlen - INTEGER
 
 	Default: 10
 
-
-UNDOCUMENTED:
-
-/proc/sys/net/irda/*
-	fast_poll_increase FIXME
-	warn_noreply_time FIXME
-	discovery_slots FIXME
-	slot_timeout FIXME
-	max_baud_rate FIXME
-	discovery_timeout FIXME
-	lap_keepalive_time FIXME
-	max_noreply_time FIXME
-	max_tx_data_size FIXME
-	max_tx_window FIXME
-	min_tx_turn_time FIXME
diff --git a/Documentation/networking/ppp_generic.txt b/Documentation/networking/ppp_generic.txt
index 091d20273dcb..61daf4b39600 100644
--- a/Documentation/networking/ppp_generic.txt
+++ b/Documentation/networking/ppp_generic.txt
@@ -300,12 +300,6 @@ unattached instance are:
 The ioctl calls available on an instance of /dev/ppp attached to a
 channel are:
 
-* PPPIOCDETACH detaches the instance from the channel.  This ioctl is
-  deprecated since the same effect can be achieved by closing the
-  instance.  In order to prevent possible races this ioctl will fail
-  with an EINVAL error if more than one file descriptor refers to this
-  instance (i.e. as a result of dup(), dup2() or fork()).
-
 * PPPIOCCONNECT connects this channel to a PPP interface.  The
   argument should point to an int containing the interface unit
   number.  It will return an EINVAL error if the channel is already
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
index 31abd04b9572..6f55eb960a6d 100644
--- a/Documentation/power/suspend-and-cpuhotplug.txt
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -168,7 +168,7 @@ update on the CPUs, as discussed below:
 
 [Please bear in mind that the kernel requests the microcode images from
 userspace, using the request_firmware() function defined in
-drivers/base/firmware_class.c]
+drivers/base/firmware_loader/main.c]
 
 
 a. When all the CPUs are identical:
diff --git a/Documentation/process/2.Process.rst b/Documentation/process/2.Process.rst
index ce5561bb3f8e..a9c46dd0706b 100644
--- a/Documentation/process/2.Process.rst
+++ b/Documentation/process/2.Process.rst
@@ -18,17 +18,17 @@ major kernel release happening every two or three months.  The recent
 release history looks like this:
 
 	======  =================
-	2.6.38	March 14, 2011
-	2.6.37	January 4, 2011
-	2.6.36	October 20, 2010
-	2.6.35	August 1, 2010
-	2.6.34	May 15, 2010
-	2.6.33	February 24, 2010
+	4.11	April 30, 2017
+	4.12	July 2, 2017
+	4.13	September 3, 2017
+	4.14	November 12, 2017
+	4.15	January 28, 2018
+	4.16	April 1, 2018
 	======  =================
 
-Every 2.6.x release is a major kernel release with new features, internal
-API changes, and more.  A typical 2.6 release can contain nearly 10,000
-changesets with changes to several hundred thousand lines of code.  2.6 is
+Every 4.x release is a major kernel release with new features, internal
+API changes, and more.  A typical 4.x release contain about 13,000
+changesets with changes to several hundred thousand lines of code.  4.x is
 thus the leading edge of Linux kernel development; the kernel uses a
 rolling development model which is continually integrating major changes.
 
@@ -70,20 +70,19 @@ will get up to somewhere between -rc6 and -rc9 before the kernel is
 considered to be sufficiently stable and the final 2.6.x release is made.
 At that point the whole process starts over again.
 
-As an example, here is how the 2.6.38 development cycle went (all dates in
-2011):
+As an example, here is how the 4.16 development cycle went (all dates in
+2018):
 
 	==============  ===============================
-	January 4	2.6.37 stable release
-	January 18	2.6.38-rc1, merge window closes
-	January 21	2.6.38-rc2
-	February 1	2.6.38-rc3
-	February 7	2.6.38-rc4
-	February 15	2.6.38-rc5
-	February 21	2.6.38-rc6
-	March 1		2.6.38-rc7
-	March 7		2.6.38-rc8
-	March 14	2.6.38 stable release
+	January 28	4.15 stable release
+	February 11	4.16-rc1, merge window closes
+	February 18	4.16-rc2
+	February 25	4.16-rc3
+	March 4		4.16-rc4
+	March 11	4.16-rc5
+	March 18	4.16-rc6
+	March 25	4.16-rc7
+	April 1		4.17 stable release
 	==============  ===============================
 
 How do the developers decide when to close the development cycle and create
@@ -99,37 +98,42 @@ release is made.  In the real world, this kind of perfection is hard to
 achieve; there are just too many variables in a project of this size.
 There comes a point where delaying the final release just makes the problem
 worse; the pile of changes waiting for the next merge window will grow
-larger, creating even more regressions the next time around.  So most 2.6.x
+larger, creating even more regressions the next time around.  So most 4.x
 kernels go out with a handful of known regressions though, hopefully, none
 of them are serious.
 
 Once a stable release is made, its ongoing maintenance is passed off to the
 "stable team," currently consisting of Greg Kroah-Hartman.  The stable team
-will release occasional updates to the stable release using the 2.6.x.y
+will release occasional updates to the stable release using the 4.x.y
 numbering scheme.  To be considered for an update release, a patch must (1)
 fix a significant bug, and (2) already be merged into the mainline for the
 next development kernel.  Kernels will typically receive stable updates for
 a little more than one development cycle past their initial release.  So,
-for example, the 2.6.36 kernel's history looked like:
+for example, the 4.13 kernel's history looked like:
 
 	==============  ===============================
-	October 10	2.6.36 stable release
-	November 22	2.6.36.1
-	December 9	2.6.36.2
-	January 7	2.6.36.3
-	February 17	2.6.36.4
+	September 3 	4.13 stable release
+	September 13	4.13.1
+	September 20	4.13.2
+	September 27	4.13.3
+	October 5	4.13.4
+	October 12  	4.13.5
+	...		...
+	November 24	4.13.16
 	==============  ===============================
 
-2.6.36.4 was the final stable update for the 2.6.36 release.
+4.13.16 was the final stable update of the 4.13 release.
 
 Some kernels are designated "long term" kernels; they will receive support
 for a longer period.  As of this writing, the current long term kernels
 and their maintainers are:
 
-	======  ======================  ===========================
-	2.6.27	Willy Tarreau		(Deep-frozen stable kernel)
-	2.6.32	Greg Kroah-Hartman
-	2.6.35	Andi Kleen		(Embedded flag kernel)
+	======  ======================  ==============================
+	3.16	Ben Hutchings		(very long-term stable kernel)
+	4.1	Sasha Levin
+	4.4	Greg Kroah-Hartman	(very long-term stable kernel)
+	4.9	Greg Kroah-Hartman
+	4.14	Greg Kroah-Hartman
 	======  ======================  ===========================
 
 The selection of a kernel for long-term support is purely a matter of a
diff --git a/Documentation/process/5.Posting.rst b/Documentation/process/5.Posting.rst
index c209d70da66f..c418c5d6cae4 100644
--- a/Documentation/process/5.Posting.rst
+++ b/Documentation/process/5.Posting.rst
@@ -10,8 +10,8 @@ of conventions and procedures which are used in the posting of patches;
 following them will make life much easier for everybody involved.  This
 document will attempt to cover these expectations in reasonable detail;
 more information can also be found in the files process/submitting-patches.rst,
-process/submitting-drivers.rst, and process/submit-checklist.rst in the kernel documentation
-directory.
+process/submitting-drivers.rst, and process/submit-checklist.rst in the kernel
+documentation directory.
 
 
 When to post
@@ -198,8 +198,8 @@ pass it to diff with the "-X" option.
 
 The tags mentioned above are used to describe how various developers have
 been associated with the development of this patch.  They are described in
-detail in the process/submitting-patches.rst document; what follows here is a brief
-summary.  Each of these lines has the format:
+detail in the process/submitting-patches.rst document; what follows here is a
+brief summary.  Each of these lines has the format:
 
 ::
 
@@ -210,8 +210,8 @@ The tags in common use are:
  - Signed-off-by: this is a developer's certification that he or she has
    the right to submit the patch for inclusion into the kernel.  It is an
    agreement to the Developer's Certificate of Origin, the full text of
-   which can be found in Documentation/process/submitting-patches.rst.  Code without a
-   proper signoff cannot be merged into the mainline.
+   which can be found in Documentation/process/submitting-patches.rst.  Code
+   without a proper signoff cannot be merged into the mainline.
 
  - Co-developed-by: states that the patch was also created by another developer
    along with the original author.  This is useful at times when multiple
@@ -226,8 +226,8 @@ The tags in common use are:
    it to work.
 
  - Reviewed-by: the named developer has reviewed the patch for correctness;
-   see the reviewer's statement in Documentation/process/submitting-patches.rst for more
-   detail.
+   see the reviewer's statement in Documentation/process/submitting-patches.rst
+   for more detail.
 
  - Reported-by: names a user who reported a problem which is fixed by this
    patch; this tag is used to give credit to the (often underappreciated)
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index 1c9fe657ed01..37bd0628b6ee 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -52,6 +52,7 @@ lack of a better place.
    adding-syscalls
    magic-number
    volatile-considered-harmful
+   clang-format
 
 .. only::  subproject and html
 
diff --git a/Documentation/process/magic-number.rst b/Documentation/process/magic-number.rst
index 00cecf1fcba9..633be1043690 100644
--- a/Documentation/process/magic-number.rst
+++ b/Documentation/process/magic-number.rst
@@ -157,8 +157,5 @@ memory management. See ``include/sound/sndmagic.h`` for complete list of them. M
 OSS sound drivers have their magic numbers constructed from the soundcard PCI
 ID - these are not listed here as well.
 
-IrDA subsystem also uses large number of own magic numbers, see
-``include/net/irda/irda.h`` for a complete list of them.
-
 HFS is another larger user of magic numbers - you can find them in
 ``fs/hfs/hfs.h``.
diff --git a/Documentation/process/maintainer-pgp-guide.rst b/Documentation/process/maintainer-pgp-guide.rst
index b453561a7148..aff9b1a4d77b 100644
--- a/Documentation/process/maintainer-pgp-guide.rst
+++ b/Documentation/process/maintainer-pgp-guide.rst
@@ -219,7 +219,7 @@ Our goal is to protect your master key by moving it to offline media, so
 if you only have a combined **[SC]** key, then you should create a separate
 signing subkey::
 
-    $ gpg --quick-add-key [fpr] ed25519 sign
+    $ gpg --quick-addkey [fpr] ed25519 sign
 
 Remember to tell the keyservers about this change, so others can pull down
 your new subkey::
@@ -450,11 +450,18 @@ functionality.  There are several options available:
 others. If you want to use ECC keys, your best bet among commercially
 available devices is the Nitrokey Start.
 
+.. note::
+
+    If you are listed in MAINTAINERS or have an account at kernel.org,
+    you `qualify for a free Nitrokey Start`_ courtesy of The Linux
+    Foundation.
+
 .. _`Nitrokey Start`: https://shop.nitrokey.com/shop/product/nitrokey-start-6
 .. _`Nitrokey Pro`: https://shop.nitrokey.com/shop/product/nitrokey-pro-3
 .. _`Yubikey 4`: https://www.yubico.com/product/yubikey-4-series/
 .. _Gnuk: http://www.fsij.org/doc-gnuk/
 .. _`LWN has a good review`: https://lwn.net/Articles/736231/
+.. _`qualify for a free Nitrokey Start`: https://www.kernel.org/nitrokey-digital-tokens-for-kernel-developers.html
 
 Configure your smartcard device
 -------------------------------
@@ -482,7 +489,7 @@ there are no convenient command-line switches::
 You should set the user PIN (1), Admin PIN (3), and the Reset Code (4).
 Please make sure to record and store these in a safe place -- especially
 the Admin PIN and the Reset Code (which allows you to completely wipe
-the smartcard).  You so rarely need to use the Admin PIN, that you will
+the smartcard). You so rarely need to use the Admin PIN, that you will
 inevitably forget what it is if you do not record it.
 
 Getting back to the main card menu, you can also set other values (such
@@ -494,6 +501,12 @@ additionally leak information about your smartcard should you lose it.
     Despite having the name "PIN", neither the user PIN nor the admin
     PIN on the card need to be numbers.
 
+.. warning::
+
+    Some devices may require that you move the subkeys onto the device
+    before you can change the passphrase. Please check the documentation
+    provided by the device manufacturer.
+
 Move the subkeys to your smartcard
 ----------------------------------
 
@@ -655,6 +668,20 @@ want to import these changes back into your regular working directory::
     $ gpg --export | gpg --homedir ~/.gnupg --import
     $ unset GNUPGHOME
 
+Using gpg-agent over ssh
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+You can forward your gpg-agent over ssh if you need to sign tags or
+commits on a remote system. Please refer to the instructions provided
+on the GnuPG wiki:
+
+- `Agent Forwarding over SSH`_
+
+It works more smoothly if you can modify the sshd server settings on the
+remote end.
+
+.. _`Agent Forwarding over SSH`: https://wiki.gnupg.org/AgentForwarding
+
 
 Using PGP with Git
 ==================
@@ -692,6 +719,7 @@ should be used (``[fpr]`` is the fingerprint of your key)::
 tell git to always use it instead of the legacy ``gpg`` from version 1::
 
     $ git config --global gpg.program gpg2
+    $ git config --global gpgv.program gpgv2
 
 How to work with signed tags
 ----------------------------
@@ -731,6 +759,13 @@ If you are verifying someone else's git tag, then you will need to
 import their PGP key. Please refer to the
 ":ref:`verify_identities`" section below.
 
+.. note::
+
+    If you get "``gpg: Can't check signature: unknown pubkey
+    algorithm``" error, you need to tell git to use gpgv2 for
+    verification, so it properly processes signatures made by ECC keys.
+    See instructions at the start of this section.
+
 Configure git to always sign annotated tags
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index f7152ed565e5..908bb55be407 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -761,7 +761,7 @@ requests, especially from new, unknown developers.  If in doubt you can use
 the pull request as the cover letter for a normal posting of the patch
 series, giving the maintainer the option of using either.
 
-A pull request should have [GIT] or [PULL] in the subject line.  The
+A pull request should have [GIT PULL] in the subject line.  The
 request itself should include the repository name and the branch of
 interest on a single line; it should look something like::
 
diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt
index 8ce78f82ae23..b14e03ff3528 100644
--- a/Documentation/scheduler/sched-deadline.txt
+++ b/Documentation/scheduler/sched-deadline.txt
@@ -49,7 +49,7 @@ CONTENTS
 2.1 Main algorithm
 ------------------
 
- SCHED_DEADLINE uses three parameters, named "runtime", "period", and
+ SCHED_DEADLINE [18] uses three parameters, named "runtime", "period", and
  "deadline", to schedule tasks. A SCHED_DEADLINE task should receive
  "runtime" microseconds of execution time every "period" microseconds, and
  these "runtime" microseconds are available within "deadline" microseconds
@@ -117,6 +117,10 @@ CONTENTS
          scheduling deadline = scheduling deadline + period
          remaining runtime = remaining runtime + runtime
 
+ The SCHED_FLAG_DL_OVERRUN flag in sched_attr's sched_flags field allows a task
+ to get informed about runtime overruns through the delivery of SIGXCPU
+ signals.
+
 
 2.2 Bandwidth reclaiming
 ------------------------
@@ -279,6 +283,19 @@ CONTENTS
     running_bw is incremented.
 
 
+2.3 Energy-aware scheduling
+------------------------
+
+ When cpufreq's schedutil governor is selected, SCHED_DEADLINE implements the
+ GRUB-PA [19] algorithm, reducing the CPU operating frequency to the minimum
+ value that still allows to meet the deadlines. This behavior is currently
+ implemented only for ARM architectures.
+
+ A particular care must be taken in case the time needed for changing frequency
+ is of the same order of magnitude of the reservation period. In such cases,
+ setting a fixed CPU frequency results in a lower amount of deadline misses.
+
+
 3. Scheduling Real-Time Tasks
 =============================
 
@@ -505,6 +522,12 @@ CONTENTS
   17 - L. Abeni, G. Lipari, A. Parri, Y. Sun, Multicore CPU reclaiming: parallel
        or sequential?. In Proceedings of the 31st Annual ACM Symposium on Applied
        Computing, 2016.
+  18 - J. Lelli, C. Scordino, L. Abeni, D. Faggioli, Deadline scheduling in the
+       Linux kernel, Software: Practice and Experience, 46(6): 821-839, June
+       2016.
+  19 - C. Scordino, L. Abeni, J. Lelli, Energy-Aware Real-Time Scheduling in
+       the Linux Kernel, 33rd ACM/SIGAPP Symposium On Applied Computing (SAC
+       2018), Pau, France, April 2018.
 
 
 4. Bandwidth management
diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 11e447bdb3a5..1b7436932a2b 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -82,24 +82,13 @@ function
  1. invokes optional hostt->eh_timed_out() callback.  Return value can
     be one of
 
-    - BLK_EH_HANDLED
-	This indicates that eh_timed_out() dealt with the timeout.
-	The command is passed back to the block layer and completed
-	via __blk_complete_requests().
-
-	*NOTE* After returning BLK_EH_HANDLED the SCSI layer is
-	assumed to be finished with the command, and no other
-	functions from the SCSI layer will be called. So this
-	should typically only be returned if the eh_timed_out()
-	handler raced with normal completion.
-
     - BLK_EH_RESET_TIMER
 	This indicates that more time is required to finish the
 	command.  Timer is restarted.  This action is counted as a
 	retry and only allowed scmd->allowed + 1(!) times.  Once the
-	limit is reached, action for BLK_EH_NOT_HANDLED is taken instead.
+	limit is reached, action for BLK_EH_DONE is taken instead.
 
-    - BLK_EH_NOT_HANDLED
+    - BLK_EH_DONE
         eh_timed_out() callback did not handle the command.
 	Step #2 is taken.
 
diff --git a/Documentation/security/index.rst b/Documentation/security/index.rst
index 298a94a33f05..85492bfca530 100644
--- a/Documentation/security/index.rst
+++ b/Documentation/security/index.rst
@@ -9,5 +9,7 @@ Security Documentation
    IMA-templates
    keys/index
    LSM
+   LSM-sctp
+   SELinux-sctp
    self-protection
    tpm/index
diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index aed6b4fb8e46..4d83c1c0ca04 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -1062,7 +1062,7 @@ output (with ``--no-upload`` option) to kernel bugzilla or alsa-devel
 ML (see the section `Links and Addresses`_).
 
 ``power_save`` and ``power_save_controller`` options are for power-saving
-mode.  See powersave.txt for details.
+mode.  See powersave.rst for details.
 
 Note 2: If you get click noises on output, try the module option
 ``position_fix=1`` or ``2``.  ``position_fix=1`` will use the SD_LPIB
@@ -1133,7 +1133,7 @@ line_outs_monitor
 enable_monitor
     Enable Analog Out on Channel 63/64 by default.
 
-See hdspm.txt for details.
+See hdspm.rst for details.
 
 Module snd-ice1712
 ------------------
@@ -2224,6 +2224,13 @@ quirk_alias
     Quirk alias list, pass strings like ``0123abcd:5678beef``, which
     applies the existing quirk for the device 5678:beef to a new
     device 0123:abcd.
+use_vmalloc
+    Use vmalloc() for allocations of the PCM buffers (default: yes).
+    For architectures with non-coherent memory like ARM or MIPS, the
+    mmap access may give inconsistent results with vmalloc'ed
+    buffers.  If mmap is used on such architectures, turn off this
+    option, so that the DMA-coherent buffers are allocated and used
+    instead.
 
 This module supports multiple devices, autoprobe and hotplugging.
 
diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index 1fee5a4f6660..7c2d37571af0 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -263,6 +263,8 @@ hp-dock
     HP dock support
 mute-led-gpio
     Mute LED control via GPIO
+hp-mic-fix
+    Fix for headset mic pin on HP boxes
 
 STAC9200
 ========
diff --git a/Documentation/sound/soc/codec.rst b/Documentation/sound/soc/codec.rst
index f87612b94812..8a9737eb7597 100644
--- a/Documentation/sound/soc/codec.rst
+++ b/Documentation/sound/soc/codec.rst
@@ -139,7 +139,7 @@ DAPM description
 ----------------
 The Dynamic Audio Power Management description describes the codec power
 components and their relationships and registers to the ASoC core.
-Please read dapm.txt for details of building the description.
+Please read dapm.rst for details of building the description.
 
 Please also see the examples in other codec drivers.
 
@@ -179,12 +179,12 @@ i.e.
 
   static int wm8974_mute(struct snd_soc_dai *dai, int mute)
   {
-	struct snd_soc_codec *codec = dai->codec;
-	u16 mute_reg = snd_soc_read(codec, WM8974_DAC) & 0xffbf;
+	struct snd_soc_component *component = dai->component;
+	u16 mute_reg = snd_soc_component_read32(component, WM8974_DAC) & 0xffbf;
 
 	if (mute)
-		snd_soc_write(codec, WM8974_DAC, mute_reg | 0x40);
+		snd_soc_component_write(component, WM8974_DAC, mute_reg | 0x40);
 	else
-		snd_soc_write(codec, WM8974_DAC, mute_reg);
+		snd_soc_component_write(component, WM8974_DAC, mute_reg);
 	return 0;
   }
diff --git a/Documentation/sound/soc/platform.rst b/Documentation/sound/soc/platform.rst
index d5574904d981..c1badea53d3d 100644
--- a/Documentation/sound/soc/platform.rst
+++ b/Documentation/sound/soc/platform.rst
@@ -23,30 +23,26 @@ The platform DMA driver optionally supports the following ALSA operations:-
   };
 
 The platform driver exports its DMA functionality via struct
-snd_soc_platform_driver:-
+snd_soc_component_driver:-
 ::
 
-  struct snd_soc_platform_driver {
-	char *name;
+  struct snd_soc_component_driver {
+	const char *name;
 
-	int (*probe)(struct platform_device *pdev);
-	int (*remove)(struct platform_device *pdev);
-	int (*suspend)(struct platform_device *pdev, struct snd_soc_cpu_dai *cpu_dai);
-	int (*resume)(struct platform_device *pdev, struct snd_soc_cpu_dai *cpu_dai);
+	...
+	int (*probe)(struct snd_soc_component *);
+	void (*remove)(struct snd_soc_component *);
+	int (*suspend)(struct snd_soc_component *);
+	int (*resume)(struct snd_soc_component *);
 
 	/* pcm creation and destruction */
-	int (*pcm_new)(struct snd_card *, struct snd_soc_codec_dai *, struct snd_pcm *);
+	int (*pcm_new)(struct snd_soc_pcm_runtime *);
 	void (*pcm_free)(struct snd_pcm *);
 
-	/*
-	 * For platform caused delay reporting.
-	 * Optional.
-	 */
-	snd_pcm_sframes_t (*delay)(struct snd_pcm_substream *,
-		struct snd_soc_dai *);
-
-	/* platform stream ops */
-	struct snd_pcm_ops *pcm_ops;
+	...
+	const struct snd_pcm_ops *ops;
+	const struct snd_compr_ops *compr_ops;
+	...
   };
 
 Please refer to the ALSA driver documentation for details of audio DMA.
@@ -66,7 +62,7 @@ Each SoC DAI driver must provide the following features:-
 4. SYSCLK configuration
 5. Suspend and resume (optional)
 
-Please see codec.txt for a description of items 1 - 4.
+Please see codec.rst for a description of items 1 - 4.
 
 
 SoC DSP Drivers
diff --git a/Documentation/sphinx/parse-headers.pl b/Documentation/sphinx/parse-headers.pl
index a958d8b5e99d..d410f47567e9 100755
--- a/Documentation/sphinx/parse-headers.pl
+++ b/Documentation/sphinx/parse-headers.pl
@@ -387,11 +387,11 @@ tree for more details.
 
 =head1 BUGS
 
-Report bugs to Mauro Carvalho Chehab <mchehab@s-opensource.com>
+Report bugs to Mauro Carvalho Chehab <mchehab@kernel.org>
 
 =head1 COPYRIGHT
 
-Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.
+Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab+samsung@kernel.org>.
 
 License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.
 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 17256f2ad919..697ef8c225df 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -515,7 +515,7 @@ nr_hugepages
 
 Change the minimum size of the hugepage pool.
 
-See Documentation/vm/hugetlbpage.txt
+See Documentation/admin-guide/mm/hugetlbpage.rst
 
 ==============================================================
 
@@ -524,7 +524,7 @@ nr_overcommit_hugepages
 Change the maximum size of the hugepage pool. The maximum is
 nr_hugepages + nr_overcommit_hugepages.
 
-See Documentation/vm/hugetlbpage.txt
+See Documentation/admin-guide/mm/hugetlbpage.rst
 
 ==============================================================
 
@@ -667,7 +667,7 @@ and don't use much of it.
 
 The default value is 0.
 
-See Documentation/vm/overcommit-accounting and
+See Documentation/vm/overcommit-accounting.rst and
 mm/mmap.c::__vm_enough_memory() for more information.
 
 ==============================================================
diff --git a/Documentation/trace/coresight-cpu-debug.txt b/Documentation/trace/coresight-cpu-debug.txt
index 2b9b51cd501e..89ab09e78e8d 100644
--- a/Documentation/trace/coresight-cpu-debug.txt
+++ b/Documentation/trace/coresight-cpu-debug.txt
@@ -177,11 +177,11 @@ Here is an example of the debugging output format:
 ARM external debug module:
 coresight-cpu-debug 850000.debug: CPU[0]:
 coresight-cpu-debug 850000.debug:  EDPRSR:  00000001 (Power:On DLK:Unlock)
-coresight-cpu-debug 850000.debug:  EDPCSR:  [<ffff00000808e9bc>] handle_IPI+0x174/0x1d8
+coresight-cpu-debug 850000.debug:  EDPCSR:  handle_IPI+0x174/0x1d8
 coresight-cpu-debug 850000.debug:  EDCIDSR: 00000000
 coresight-cpu-debug 850000.debug:  EDVIDSR: 90000000 (State:Non-secure Mode:EL1/0 Width:64bits VMID:0)
 coresight-cpu-debug 852000.debug: CPU[1]:
 coresight-cpu-debug 852000.debug:  EDPRSR:  00000001 (Power:On DLK:Unlock)
-coresight-cpu-debug 852000.debug:  EDPCSR:  [<ffff0000087fab34>] debug_notifier_call+0x23c/0x358
+coresight-cpu-debug 852000.debug:  EDPCSR:  debug_notifier_call+0x23c/0x358
 coresight-cpu-debug 852000.debug:  EDCIDSR: 00000000
 coresight-cpu-debug 852000.debug:  EDVIDSR: 90000000 (State:Non-secure Mode:EL1/0 Width:64bits VMID:0)
diff --git a/Documentation/trace/coresight.txt b/Documentation/trace/coresight.txt
index 6f0120c3a4f1..1d74ad0202b6 100644
--- a/Documentation/trace/coresight.txt
+++ b/Documentation/trace/coresight.txt
@@ -187,13 +187,19 @@ that can be performed on them (see "struct coresight_ops").  The
 specific to that component only.  "Implementation defined" customisations are
 expected to be accessed and controlled using those entries.
 
-Last but not least, "struct module *owner" is expected to be set to reflect
-the information carried in "THIS_MODULE".
 
 How to use the tracer modules
 -----------------------------
 
-Before trace collection can start, a coresight sink needs to be identify.
+There are two ways to use the Coresight framework: 1) using the perf cmd line
+tools and 2) interacting directly with the Coresight devices using the sysFS
+interface.  Preference is given to the former as using the sysFS interface
+requires a deep understanding of the Coresight HW.  The following sections
+provide details on using both methods.
+
+1) Using the sysFS interface:
+
+Before trace collection can start, a coresight sink needs to be identified.
 There is no limit on the amount of sinks (nor sources) that can be enabled at
 any given moment.  As a generic operation, all device pertaining to the sink
 class will have an "active" entry in sysfs:
@@ -298,42 +304,48 @@ Instruction     13570831        0x8026B584      E28DD00C        false   ADD
 Instruction     0       0x8026B588      E8BD8000        true    LDM      sp!,{pc}
 Timestamp                                       Timestamp: 17107041535
 
-How to use the STM module
--------------------------
+2) Using perf framework:
 
-Using the System Trace Macrocell module is the same as the tracers - the only
-difference is that clients are driving the trace capture rather
-than the program flow through the code.
+Coresight tracers are represented using the Perf framework's Performance
+Monitoring Unit (PMU) abstraction.  As such the perf framework takes charge of
+controlling when tracing gets enabled based on when the process of interest is
+scheduled.  When configured in a system, Coresight PMUs will be listed when
+queried by the perf command line tool:
 
-As with any other CoreSight component, specifics about the STM tracer can be
-found in sysfs with more information on each entry being found in [1]:
+	linaro@linaro-nano:~$ ./perf list pmu
 
-root@genericarmv8:~# ls /sys/bus/coresight/devices/20100000.stm
-enable_source   hwevent_select  port_enable     subsystem       uevent
-hwevent_enable  mgmt            port_select     traceid
-root@genericarmv8:~#
+		List of pre-defined events (to be used in -e):
 
-Like any other source a sink needs to be identified and the STM enabled before
-being used:
+		cs_etm//                                    [Kernel PMU event]
 
-root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20010000.etf/enable_sink
-root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20100000.stm/enable_source
+	linaro@linaro-nano:~$
 
-From there user space applications can request and use channels using the devfs
-interface provided for that purpose by the generic STM API:
+Regardless of the number of tracers available in a system (usually equal to the
+amount of processor cores), the "cs_etm" PMU will be listed only once.
 
-root@genericarmv8:~# ls -l /dev/20100000.stm
-crw-------    1 root     root       10,  61 Jan  3 18:11 /dev/20100000.stm
-root@genericarmv8:~#
+A Coresight PMU works the same way as any other PMU, i.e the name of the PMU is
+listed along with configuration options within forward slashes '/'.  Since a
+Coresight system will typically have more than one sink, the name of the sink to
+work with needs to be specified as an event option.  Names for sink to choose
+from are listed in sysFS under ($SYSFS)/bus/coresight/devices:
 
-Details on how to use the generic STM API can be found here [2].
+	root@linaro-nano:~# ls /sys/bus/coresight/devices/
+		20010000.etf   20040000.funnel  20100000.stm  22040000.etm
+		22140000.etm  230c0000.funnel  23240000.etm 20030000.tpiu
+		20070000.etr     20120000.replicator  220c0000.funnel
+		23040000.etm  23140000.etm     23340000.etm
 
-[1]. Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
-[2]. Documentation/trace/stm.txt
+	root@linaro-nano:~# perf record -e cs_etm/@20070000.etr/u --per-thread program
 
+The syntax within the forward slashes '/' is important.  The '@' character
+tells the parser that a sink is about to be specified and that this is the sink
+to use for the trace session.
 
-Using perf tools
-----------------
+More information on the above and other example on how to use Coresight with
+the perf tools can be found in the "HOWTO.md" file of the openCSD gitHub
+repository [3].
+
+2.1) AutoFDO analysis using the perf tools:
 
 perf can be used to record and analyze trace of programs.
 
@@ -381,3 +393,38 @@ sort example is from the AutoFDO tutorial (https://gcc.gnu.org/wiki/AutoFDO/Tuto
 	$ taskset -c 2 ./sort_autofdo
 	Bubble sorting array of 30000 elements
 	5806 ms
+
+
+How to use the STM module
+-------------------------
+
+Using the System Trace Macrocell module is the same as the tracers - the only
+difference is that clients are driving the trace capture rather
+than the program flow through the code.
+
+As with any other CoreSight component, specifics about the STM tracer can be
+found in sysfs with more information on each entry being found in [1]:
+
+root@genericarmv8:~# ls /sys/bus/coresight/devices/20100000.stm
+enable_source   hwevent_select  port_enable     subsystem       uevent
+hwevent_enable  mgmt            port_select     traceid
+root@genericarmv8:~#
+
+Like any other source a sink needs to be identified and the STM enabled before
+being used:
+
+root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20010000.etf/enable_sink
+root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20100000.stm/enable_source
+
+From there user space applications can request and use channels using the devfs
+interface provided for that purpose by the generic STM API:
+
+root@genericarmv8:~# ls -l /dev/20100000.stm
+crw-------    1 root     root       10,  61 Jan  3 18:11 /dev/20100000.stm
+root@genericarmv8:~#
+
+Details on how to use the generic STM API can be found here [2].
+
+[1]. Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
+[2]. Documentation/trace/stm.txt
+[3]. https://github.com/Linaro/perf-opencsd
diff --git a/Documentation/trace/ftrace-uses.rst b/Documentation/trace/ftrace-uses.rst
index 998a60a93015..00283b6dd101 100644
--- a/Documentation/trace/ftrace-uses.rst
+++ b/Documentation/trace/ftrace-uses.rst
@@ -12,7 +12,7 @@ Written for: 4.14
 Introduction
 ============
 
-The ftrace infrastructure was originially created to attach callbacks to the
+The ftrace infrastructure was originally created to attach callbacks to the
 beginning of functions in order to record and trace the flow of the kernel.
 But callbacks to the start of a function can have other use cases. Either
 for live kernel patching, or for security monitoring. This document describes
@@ -30,7 +30,7 @@ The ftrace context
   This requires extra care to what can be done inside a callback. A callback
   can be called outside the protective scope of RCU.
 
-The ftrace infrastructure has some protections agains recursions and RCU
+The ftrace infrastructure has some protections against recursions and RCU
 but one must still be very careful how they use the callbacks.
 
 
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index e45f0786f3f9..6b80ac4bbaae 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -224,6 +224,8 @@ of ftrace. Here is a list of some of the key files:
 	has a side effect of enabling or disabling specific functions
 	to be traced. Echoing names of functions into this file
 	will limit the trace to only those functions.
+	This influences the tracers "function" and "function_graph"
+	and thus also function profiling (see "function_profile_enabled").
 
 	The functions listed in "available_filter_functions" are what
 	can be written into this file.
@@ -265,6 +267,8 @@ of ftrace. Here is a list of some of the key files:
 	Functions listed in this file will cause the function graph
 	tracer to only trace these functions and the functions that
 	they call. (See the section "dynamic ftrace" for more details).
+	Note, set_ftrace_filter and set_ftrace_notrace still affects
+	what functions are being traced.
 
   set_graph_notrace:
 
@@ -277,7 +281,8 @@ of ftrace. Here is a list of some of the key files:
 
 	This lists the functions that ftrace has processed and can trace.
 	These are the function names that you can pass to
-	"set_ftrace_filter" or "set_ftrace_notrace".
+	"set_ftrace_filter", "set_ftrace_notrace",
+	"set_graph_function", or "set_graph_notrace".
 	(See the section "dynamic ftrace" below for more details.)
 
   dyn_ftrace_total_info:
@@ -461,9 +466,17 @@ of ftrace. Here is a list of some of the key files:
 		and ticks at the same rate as the hardware clocksource.
 
 	boot:
-		Same as mono. Used to be a separate clock which accounted
-		for the time spent in suspend while CLOCK_MONOTONIC did
-		not.
+		This is the boot clock (CLOCK_BOOTTIME) and is based on the
+		fast monotonic clock, but also accounts for time spent in
+		suspend. Since the clock access is designed for use in
+		tracing in the suspend path, some side effects are possible
+		if clock is accessed after the suspend time is accounted before
+		the fast mono clock is updated. In this case, the clock update
+		appears to happen slightly sooner than it normally would have.
+		Also on 32-bit systems, it's possible that the 64-bit boot offset
+		sees a partial update. These effects are rare and post
+		processing should be able to handle them. See comments in the
+		ktime_get_boot_fast_ns() function for more information.
 
 	To set a clock, simply echo the clock name into this file::
 
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 0a0930ab4156..921739d00f69 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -36,6 +36,9 @@ Documentation/memory-barriers.txt
 부분� 있고, ��하진 않았지만 사람� �해 쓰였다보니 불완전한 부분� 있습니다.
 � 문서는 리눅스�서 제공하는 다양한 메모리 배리어들� 사용하기 위한
 안내서입니다만, 뭔가 ��하다 싶으면 (그런게 많� �니다) 질문� 부�드립니다.
+�부 ��한 �들� 공��� 메모리 �관성 모�과 tools/memory-model/ � 있는
+관련 문서를 참고해서 해결� 수 있� �니다.  그러나, � 메모리 모�조차� 그
+관리�들� �견� 집합으로 �야지, 절대 옳� 예언�로 신봉해선 안� �니다.
 
 다시 �하지만, � 문서는 리눅스가 하드웨어� 기대하는 사항� 대한 명세서가
 아닙니다.
@@ -77,7 +80,7 @@ Documentation/memory-barriers.txt
 
      - 메모리 배리어� 종류.
      - 메모리 배리어� 대해 가정해선 안� 것.
-     - ��터 �존성 배리어.
+     - ��터 �존성 배리어 (역사�).
      - 컨트롤 �존성.
      - SMP 배리어 �맞추기.
      - 메모리 배리어 시퀀스� 예.
@@ -255,17 +258,20 @@ CPU �게 기대할 수 있는 최소한� 보장사항 몇가지가 있습니
  (*) 어떤 CPU 든, �존성� 존재하는 메모리 액세스들� 해당 CPU �신�게
      있어서는 순서대로 메모리 시스템� 수행 요청�니다. 즉, 다�� 대해서:
 
-	Q = READ_ONCE(P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
+	Q = READ_ONCE(P); D = READ_ONCE(*Q);
 
      CPU 는 다�과 같� 메모리 오�레�션 시퀀스를 수행 요청합니다:
 
 	Q = LOAD P, D = LOAD *Q
 
-     그리고 그 시퀀스 내�서� 순서는 항� 지켜집니다.  대부분� 시스템�서
-     smp_read_barrier_depends() 는 아무�� 안하지만 DEC Alpha �서는
-     명시�으로 사용�어야 합니다.  보통� 경우�는 smp_read_barrier_depends()
-     를 �접 사용하는 대신 rcu_dereference() 같� 것들� 사용해야 함�
-     알아�세요.
+     그리고 그 시퀀스 내�서� 순서는 항� 지켜집니다.  하지만, DEC Alpha �서
+     READ_ONCE() 는 메모리 배리어 명령� 내게 �어 있어서, DEC Alpha CPU 는
+     다�과 같� 메모리 오�레�션들� 내놓게 �니다:
+
+	Q = LOAD P, MEMORY_BARRIER, D = LOAD *Q, MEMORY_BARRIER
+
+     DEC Alpha �서 수행�든 아니든, READ_ONCE() 는 컴파�러로부터� 악�향
+     �한 제거합니다.
 
  (*) 특정 CPU 내�서 겹치는 �역� 메모리� 행해지는 로드와 스토어 들� 해당
      CPU 안�서는 순서가 바뀌지 않� 것으로 보여집니다.  즉, 다�� 대해서:
@@ -421,8 +427,8 @@ CPU �게 기대할 수 있는 최소한� 보장사항 몇가지가 있습니
      ��터 �존성 배리어는 �기 배리어� 보다 완화� 형태입니다.  �개� 로드
      오�레�션� 있고 �번째 것� 첫번째 것� 결과� �존하고 있� 때(예:
      �번째 로드가 참조할 주소를 첫번째 로드가 �는 경우), �번째 로드가 �어올
-     ��터는 첫번째 로드� �해 그 주소가 얻어지기 전� 업��트 �어 있��
-     보장하기 위해서 ��터 �존성 배리어가 필요할 수 있습니다.
+     ��터는 첫번째 로드� �해 그 주소가 얻어진 뒤� 업��트 �� 보장하기
+     위해서 ��터 �존성 배리어가 필요할 수 있습니다.
 
      ��터 �존성 배리어는 �호 �존�� 로드 오�레�션들 사�� 부분� 순서
      세우기입니다; 스토어 오�레�션들�나 �립�� 로드들, �는 중복�는
@@ -570,8 +576,14 @@ ACQUIRE 는 해당 오í�¼ë ˆì�´ì…˜ì�˜ 로드 부분ì—�만 ì �ìš©ë�˜ê³  RELEASE ë
 	    Documentation/DMA-API.txt
 
 
-��터 �존성 배리어
---------------------
+��터 �존성 배리어 (역사�)
+-----------------------------
+
+리눅스 커� v4.15 기준으로, smp_read_barrier_depends() 가 READ_ONCE() �
+추가�었는�, �는 � 섹션� 주�를 기울여야 하는 사람들� DEC Alpha 아키��
+전용 코드를 만드는 사람들과 READ_ONCE() �체를 만드는 사람들 �임� �미합니다.
+그런 분들� 위해, 그리고 역사� 관심 있는 분들� 위해, 여기 ��터 �존성
+배리어� 대한 �야기를 �습니다.
 
 ��터 �존성 배리어� 사용� 있어 지켜야 하는 사항들� 약간 미묘하고, ��터
 �존성 배리어가 사용�어야 하는 �황� 항� 명백하지는 않습니다.  설명� 위해
@@ -1787,7 +1799,7 @@ CPU 메모리 배리어
 	범용		mb()			smp_mb()
 	쓰기		wmb()			smp_wmb()
 	�기		rmb()			smp_rmb()
-	��터 �존성	read_barrier_depends()	smp_read_barrier_depends()
+	��터 �존성				READ_ONCE()
 
 
 ��터 �존성 배리어를 제외한 모든 메모리 배리어는 컴파�러 배리어를
@@ -2796,8 +2808,9 @@ CPU 2 는 C/D 를 갖습니다)ê°€ 병렬로 ì—°ê²°ë�˜ì–´ 있는 시스템ì�„ ë‹
 
 
 여기� 개입하기 위해선, ��터 �존성 배리어나 �기 배리어를 로드 오�레�션들
-사�� 넣어야 합니다.  �렇게 함으로� �시가 다� 요청� 처리하기 전� �관성
-�를 처리하�� 강제하게 �니다.
+사�� 넣어야 합니다 (v4.15 부터는 READ_ONCE() 매�로� �해 무조건�으로
+그렇게 �니다).  �렇게 함으로� �시가 다� 요청� 처리하기 전� �관성 �를
+처리하�� 강제하게 �니다.
 
 	CPU 1		CPU 2		COMMENT
 	===============	===============	=======================================
@@ -2826,7 +2839,10 @@ CPU 2 는 C/D 를 갖습니다)ê°€ 병렬로 ì—°ê²°ë�˜ì–´ 있는 시스템ì�„ ë‹
 다른 CPU 들� 분할� �시를 가지고 있� 수 있지만, 그런 CPU 들� �범한 메모리
 액세스를 위해서� � 분할� �시들 사�� 조정� 해야만 합니다.  Alpha 는 가장
 약한 메모리 순서 시맨틱 (semantic) � 선�함으로� 메모리 배리어가 명시�으로
-사용�지 않았� 때�는 그런 조정� 필요하지 않게 했습니다.
+사용�지 않았� 때�는 그런 조정� 필요하지 않게 했으며, �는 Alpha 가 당시�
+� 높� CPU �� ��를 가질 수 있게 했습니다.  하지만, (다시 �하건대, v4.15
+�후부터는) Alpha 아키�� 전용 코드와 READ_ONCE() 매�로 내부�서를 제외하고는
+smp_read_barrier_depends() 가 사용�지 않아야 함� 알아�시기 바�니다.
 
 
 �시 �관성 VS DMA
@@ -2846,7 +2862,7 @@ CPU ì�˜ ìº�ì‹œì—�ì„œ RAM 으로 쓰여지는 ë�”í‹° ìº�ì‹œ ë�¼ì�¸ì—� ì�˜í•´ ë�®ì
 문제를 해결하기 위해선, 커�� �절한 부분�서 � CPU � �시 안� 문제가 �는
 비트들� 무효화 시켜야 합니다.
 
-�시 관리� 대한 � 많� 정보를 위해선 Documentation/cachetlb.txt 를
+�시 관리� 대한 � 많� 정보를 위해선 Documentation/core-api/cachetlb.rst 를
 참고하세요.
 
 
@@ -2988,7 +3004,9 @@ Alpha CPU � �부 버전� 분할� ��터 �시를 가지고 있어서
 메모리 �관성 시스템과 함께 �개� �시를 �기화 시켜서, ��터 변경과 새로운
 ��터� 발견� 올바른 순서로 �어나게 하기 때문입니다.
 
-리눅스 커�� 메모리 배리어 모�� Alpha � 기초해서 정��었습니다.
+리눅스 커�� 메모리 배리어 모�� Alpha � 기초해서 정��었습니다만, v4.15
+부터는 리눅스 커�� READ_ONCE() 내� smp_read_barrier_depends() 를 추가해서
+Alpha � 메모리 모�로� �향력� �게 줄어들긴 했습니다.
 
 위� "�시 �관성" 서브섹션� 참고하세요.
 
@@ -3023,7 +3041,7 @@ smp_mb() 가 아니� virt_mb() 를 사용해야 합니다.
 �기화� �� 사용하지 않고 구현하는�� 사용� 수 있습니다.  � �세한 내용�
 위해선 다�� 참고하세요:
 
-	Documentation/circular-buffers.txt
+	Documentation/core-api/circular-buffers.rst
 
 
 =========
diff --git a/Documentation/translations/zh_CN/video4linux/v4l2-framework.txt b/Documentation/translations/zh_CN/video4linux/v4l2-framework.txt
index 698660b7f21f..c77c0f060864 100644
--- a/Documentation/translations/zh_CN/video4linux/v4l2-framework.txt
+++ b/Documentation/translations/zh_CN/video4linux/v4l2-framework.txt
@@ -6,7 +6,7 @@ communicating in English you can also ask the Chinese maintainer for
 help.  Contact the Chinese maintainer if this translation is outdated
 or if there is a problem with the translation.
 
-Maintainer: Mauro Carvalho Chehab <mchehab@infradead.org>
+Maintainer: Mauro Carvalho Chehab <mchehab@kernel.org>
 Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
 ---------------------------------------------------------------------
 Documentation/video4linux/v4l2-framework.txt 的中文翻译
@@ -14,7 +14,7 @@ Documentation/video4linux/v4l2-framework.txt 的中文翻译
 如果想评论或更新本文的内容，请直接�系原文档的维护者。如果你使用英文
 交�有困难的�，也�以�中文版维护者求助。如果本翻译更新��时或者翻
 译存在问题，请�系中文版维护者。
-英文版维护者： Mauro Carvalho Chehab <mchehab@infradead.org>
+英文版维护者： Mauro Carvalho Chehab <mchehab@kernel.org>
 中文版维护者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
 中文版翻译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
 中文版校译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 7b2eb1b7d4ca..a3233da7fa88 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -19,6 +19,7 @@ place where this information is gathered.
    no_new_privs
    seccomp_filter
    unshare
+   spec_ctrl
 
 .. only::  subproject and html
 
diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst
new file mode 100644
index 000000000000..32f3d55c54b7
--- /dev/null
+++ b/Documentation/userspace-api/spec_ctrl.rst
@@ -0,0 +1,94 @@
+===================
+Speculation Control
+===================
+
+Quite some CPUs have speculation-related misfeatures which are in
+fact vulnerabilities causing data leaks in various forms even across
+privilege domains.
+
+The kernel provides mitigation for such vulnerabilities in various
+forms. Some of these mitigations are compile-time configurable and some
+can be supplied on the kernel command line.
+
+There is also a class of mitigations which are very expensive, but they can
+be restricted to a certain set of processes or tasks in controlled
+environments. The mechanism to control these mitigations is via
+:manpage:`prctl(2)`.
+
+There are two prctl options which are related to this:
+
+ * PR_GET_SPECULATION_CTRL
+
+ * PR_SET_SPECULATION_CTRL
+
+PR_GET_SPECULATION_CTRL
+-----------------------
+
+PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
+which is selected with arg2 of prctl(2). The return value uses bits 0-3 with
+the following meaning:
+
+==== ===================== ===================================================
+Bit  Define                Description
+==== ===================== ===================================================
+0    PR_SPEC_PRCTL         Mitigation can be controlled per task by
+                           PR_SET_SPECULATION_CTRL.
+1    PR_SPEC_ENABLE        The speculation feature is enabled, mitigation is
+                           disabled.
+2    PR_SPEC_DISABLE       The speculation feature is disabled, mitigation is
+                           enabled.
+3    PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A
+                           subsequent prctl(..., PR_SPEC_ENABLE) will fail.
+==== ===================== ===================================================
+
+If all bits are 0 the CPU is not affected by the speculation misfeature.
+
+If PR_SPEC_PRCTL is set, then the per-task control of the mitigation is
+available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation
+misfeature will fail.
+
+PR_SET_SPECULATION_CTRL
+-----------------------
+
+PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
+is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand
+in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE or
+PR_SPEC_FORCE_DISABLE.
+
+Common error codes
+------------------
+======= =================================================================
+Value   Meaning
+======= =================================================================
+EINVAL  The prctl is not implemented by the architecture or unused
+        prctl(2) arguments are not 0.
+
+ENODEV  arg2 is selecting a not supported speculation misfeature.
+======= =================================================================
+
+PR_SET_SPECULATION_CTRL error codes
+-----------------------------------
+======= =================================================================
+Value   Meaning
+======= =================================================================
+0       Success
+
+ERANGE  arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor
+        PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE.
+
+ENXIO   Control of the selected speculation misfeature is not possible.
+        See PR_GET_SPECULATION_CTRL.
+
+EPERM   Speculation was disabled with PR_SPEC_FORCE_DISABLE and caller
+        tried to enable it again.
+======= =================================================================
+
+Speculation misfeature controls
+-------------------------------
+- PR_SPEC_STORE_BYPASS: Speculative Store Bypass
+
+  Invocations:
+   * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0);
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
index ef6a5111eaa1..f1a4d3c3ba0b 100644
--- a/Documentation/vfio.txt
+++ b/Documentation/vfio.txt
@@ -252,15 +252,14 @@ into VFIO core.  When devices are bound and unbound to the driver,
 the driver should call vfio_add_group_dev() and vfio_del_group_dev()
 respectively::
 
-	extern int vfio_add_group_dev(struct iommu_group *iommu_group,
-	                              struct device *dev,
+	extern int vfio_add_group_dev(struct device *dev,
 				      const struct vfio_device_ops *ops,
 				      void *device_data);
 
 	extern void *vfio_del_group_dev(struct device *dev);
 
 vfio_add_group_dev() indicates to the core to begin tracking the
-specified iommu_group and register the specified dev as owned by
+iommu_group of the specified dev and register the dev as owned by
 a VFIO bus driver.  The driver provides an ops structure for callbacks
 similar to a file operations structure::
 
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 1c7958b57fe9..758bf403a169 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1960,6 +1960,9 @@ ARM 32-bit VFP control registers have the following id bit patterns:
 ARM 64-bit FP registers have the following id bit patterns:
   0x4030 0000 0012 0 <regno:12>
 
+ARM firmware pseudo-registers have the following bit pattern:
+  0x4030 0000 0014 <regno:16>
+
 
 arm64 registers are mapped using the lower 32 bits. The upper 16 of
 that is the register group type, or coprocessor number:
@@ -1976,6 +1979,9 @@ arm64 CCSIDR registers are demultiplexed by CSSELR value:
 arm64 system registers have the following id bit patterns:
   0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
 
+arm64 firmware pseudo-registers have the following bit pattern:
+  0x6030 0000 0014 <regno:16>
+
 
 MIPS registers are mapped using the lower 32 bits.  The upper 16 of that is
 the register group type:
@@ -2510,7 +2516,8 @@ Possible features:
 	  and execute guest code when KVM_RUN is called.
 	- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
-	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
+	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision
+          backward compatible with v0.2) for the CPU.
 	  Depends on KVM_CAP_ARM_PSCI_0_2.
 	- KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
 	  Depends on KVM_CAP_ARM_PMU_V3.
diff --git a/Documentation/virtual/kvm/arm/psci.txt b/Documentation/virtual/kvm/arm/psci.txt
new file mode 100644
index 000000000000..aafdab887b04
--- /dev/null
+++ b/Documentation/virtual/kvm/arm/psci.txt
@@ -0,0 +1,30 @@
+KVM implements the PSCI (Power State Coordination Interface)
+specification in order to provide services such as CPU on/off, reset
+and power-off to the guest.
+
+The PSCI specification is regularly updated to provide new features,
+and KVM implements these updates if they make sense from a virtualization
+point of view.
+
+This means that a guest booted on two different versions of KVM can
+observe two different "firmware" revisions. This could cause issues if
+a given guest is tied to a particular PSCI revision (unlikely), or if
+a migration causes a different PSCI version to be exposed out of the
+blue to an unsuspecting guest.
+
+In order to remedy this situation, KVM exposes a set of "firmware
+pseudo-registers" that can be manipulated using the GET/SET_ONE_REG
+interface. These registers can be saved/restored by userspace, and set
+to a convenient value if required.
+
+The following register is defined:
+
+* KVM_REG_ARM_PSCI_VERSION:
+
+  - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set
+    (and thus has already been initialized)
+  - Returns the current PSCI version on GET_ONE_REG (defaulting to the
+    highest PSCI version implemented by KVM and compatible with v0.2)
+  - Allows any PSCI version implemented by KVM and compatible with
+    v0.2 to be set with SET_ONE_REG
+  - Affects the whole VM (even if the register view is per-vcpu)
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index d4f33eb805dd..ab022dcd0911 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -72,8 +72,8 @@ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
 
 flag                               || value || meaning
 ==================================================================================
-KVM_HINTS_DEDICATED                ||     0 || guest checks this feature bit to
-                                   ||       || determine if there is vCPU pinning
-                                   ||       || and there is no vCPU over-commitment,
+KVM_HINTS_REALTIME                 ||     0 || guest checks this feature bit to
+                                   ||       || determine that vCPUs are never
+                                   ||       || preempted for an unlimited time,
                                    ||       || allowing optimizations
 ----------------------------------------------------------------------------------
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index 0278f2c85efb..f4a4f3e884cf 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -1,62 +1,50 @@
 00-INDEX
 	- this file.
-active_mm.txt
+active_mm.rst
 	- An explanation from Linus about tsk->active_mm vs tsk->mm.
-balance
+balance.rst
 	- various information on memory balancing.
-cleancache.txt
+cleancache.rst
 	- Intro to cleancache and page-granularity victim cache.
-frontswap.txt
+frontswap.rst
 	- Outline frontswap, part of the transcendent memory frontend.
-highmem.txt
+highmem.rst
 	- Outline of highmem and common issues.
-hmm.txt
+hmm.rst
 	- Documentation of heterogeneous memory management
-hugetlbpage.txt
-	- a brief summary of hugetlbpage support in the Linux kernel.
-hugetlbfs_reserv.txt
+hugetlbfs_reserv.rst
 	- A brief overview of hugetlbfs reservation design/implementation.
-hwpoison.txt
+hwpoison.rst
 	- explains what hwpoison is
-idle_page_tracking.txt
-	- description of the idle page tracking feature.
-ksm.txt
+ksm.rst
 	- how to use the Kernel Samepage Merging feature.
-mmu_notifier.txt
+mmu_notifier.rst
 	- a note about clearing pte/pmd and mmu notifications
-numa
+numa.rst
 	- information about NUMA specific code in the Linux vm.
-numa_memory_policy.txt
-	- documentation of concepts and APIs of the 2.6 memory policy support.
-overcommit-accounting
+overcommit-accounting.rst
 	- description of the Linux kernels overcommit handling modes.
-page_frags
+page_frags.rst
 	- description of page fragments allocator
-page_migration
+page_migration.rst
 	- description of page migration in NUMA systems.
-pagemap.txt
-	- pagemap, from the userspace perspective
-page_owner.txt
+page_owner.rst
 	- tracking about who allocated each page
-remap_file_pages.txt
+remap_file_pages.rst
 	- a note about remap_file_pages() system call
-slub.txt
+slub.rst
 	- a short users guide for SLUB.
-soft-dirty.txt
-	- short explanation for soft-dirty PTEs
-split_page_table_lock
+split_page_table_lock.rst
 	- Separate per-table lock to improve scalability of the old page_table_lock.
-swap_numa.txt
+swap_numa.rst
 	- automatic binding of swap device to numa node
-transhuge.txt
+transhuge.rst
 	- Transparent Hugepage Support, alternative way of using hugepages.
-unevictable-lru.txt
+unevictable-lru.rst
 	- Unevictable LRU infrastructure
-userfaultfd.txt
-	- description of userfaultfd system call
 z3fold.txt
 	- outline of z3fold allocator for storing compressed pages
-zsmalloc.txt
+zsmalloc.rst
 	- outline of zsmalloc allocator for storing compressed pages
-zswap.txt
+zswap.rst
 	- Intro to compressed cache for swap pages
diff --git a/Documentation/vm/active_mm.rst b/Documentation/vm/active_mm.rst
new file mode 100644
index 000000000000..c84471b180f8
--- /dev/null
+++ b/Documentation/vm/active_mm.rst
@@ -0,0 +1,91 @@
+.. _active_mm:
+
+=========
+Active MM
+=========
+
+::
+
+ List:       linux-kernel
+ Subject:    Re: active_mm
+ From:       Linus Torvalds <torvalds () transmeta ! com>
+ Date:       1999-07-30 21:36:24
+
+ Cc'd to linux-kernel, because I don't write explanations all that often,
+ and when I do I feel better about more people reading them.
+
+ On Fri, 30 Jul 1999, David Mosberger wrote:
+ >
+ > Is there a brief description someplace on how "mm" vs. "active_mm" in
+ > the task_struct are supposed to be used?  (My apologies if this was
+ > discussed on the mailing lists---I just returned from vacation and
+ > wasn't able to follow linux-kernel for a while).
+
+ Basically, the new setup is:
+
+  - we have "real address spaces" and "anonymous address spaces". The
+    difference is that an anonymous address space doesn't care about the
+    user-level page tables at all, so when we do a context switch into an
+    anonymous address space we just leave the previous address space
+    active.
+
+    The obvious use for a "anonymous address space" is any thread that
+    doesn't need any user mappings - all kernel threads basically fall into
+    this category, but even "real" threads can temporarily say that for
+    some amount of time they are not going to be interested in user space,
+    and that the scheduler might as well try to avoid wasting time on
+    switching the VM state around. Currently only the old-style bdflush
+    sync does that.
+
+  - "tsk->mm" points to the "real address space". For an anonymous process,
+    tsk->mm will be NULL, for the logical reason that an anonymous process
+    really doesn't _have_ a real address space at all.
+
+  - however, we obviously need to keep track of which address space we
+    "stole" for such an anonymous user. For that, we have "tsk->active_mm",
+    which shows what the currently active address space is.
+
+    The rule is that for a process with a real address space (ie tsk->mm is
+    non-NULL) the active_mm obviously always has to be the same as the real
+    one.
+
+    For a anonymous process, tsk->mm == NULL, and tsk->active_mm is the
+    "borrowed" mm while the anonymous process is running. When the
+    anonymous process gets scheduled away, the borrowed address space is
+    returned and cleared.
+
+ To support all that, the "struct mm_struct" now has two counters: a
+ "mm_users" counter that is how many "real address space users" there are,
+ and a "mm_count" counter that is the number of "lazy" users (ie anonymous
+ users) plus one if there are any real users.
+
+ Usually there is at least one real user, but it could be that the real
+ user exited on another CPU while a lazy user was still active, so you do
+ actually get cases where you have a address space that is _only_ used by
+ lazy users. That is often a short-lived state, because once that thread
+ gets scheduled away in favour of a real thread, the "zombie" mm gets
+ released because "mm_users" becomes zero.
+
+ Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
+ more. "init_mm" should be considered just a "lazy context when no other
+ context is available", and in fact it is mainly used just at bootup when
+ no real VM has yet been created. So code that used to check
+
+ 	if (current->mm == &init_mm)
+
+ should generally just do
+
+ 	if (!current->mm)
+
+ instead (which makes more sense anyway - the test is basically one of "do
+ we have a user context", and is generally done by the page fault handler
+ and things like that).
+
+ Anyway, I put a pre-patch-2.3.13-1 on ftp.kernel.org just a moment ago,
+ because it slightly changes the interfaces to accommodate the alpha (who
+ would have thought it, but the alpha actually ends up having one of the
+ ugliest context switch codes - unlike the other architectures where the MM
+ and register state is separate, the alpha PALcode joins the two, and you
+ need to switch both together).
+
+ (From http://marc.info/?l=linux-kernel&m=93337278602211&w=2)
diff --git a/Documentation/vm/active_mm.txt b/Documentation/vm/active_mm.txt
deleted file mode 100644
index dbf45817405f..000000000000
--- a/Documentation/vm/active_mm.txt
+++ /dev/null
@@ -1,83 +0,0 @@
-List:       linux-kernel
-Subject:    Re: active_mm
-From:       Linus Torvalds <torvalds () transmeta ! com>
-Date:       1999-07-30 21:36:24
-
-Cc'd to linux-kernel, because I don't write explanations all that often,
-and when I do I feel better about more people reading them.
-
-On Fri, 30 Jul 1999, David Mosberger wrote:
->
-> Is there a brief description someplace on how "mm" vs. "active_mm" in
-> the task_struct are supposed to be used?  (My apologies if this was
-> discussed on the mailing lists---I just returned from vacation and
-> wasn't able to follow linux-kernel for a while).
-
-Basically, the new setup is:
-
- - we have "real address spaces" and "anonymous address spaces". The
-   difference is that an anonymous address space doesn't care about the
-   user-level page tables at all, so when we do a context switch into an
-   anonymous address space we just leave the previous address space
-   active.
-
-   The obvious use for a "anonymous address space" is any thread that
-   doesn't need any user mappings - all kernel threads basically fall into
-   this category, but even "real" threads can temporarily say that for
-   some amount of time they are not going to be interested in user space,
-   and that the scheduler might as well try to avoid wasting time on
-   switching the VM state around. Currently only the old-style bdflush
-   sync does that.
-
- - "tsk->mm" points to the "real address space". For an anonymous process,
-   tsk->mm will be NULL, for the logical reason that an anonymous process
-   really doesn't _have_ a real address space at all.
-
- - however, we obviously need to keep track of which address space we
-   "stole" for such an anonymous user. For that, we have "tsk->active_mm",
-   which shows what the currently active address space is.
-
-   The rule is that for a process with a real address space (ie tsk->mm is
-   non-NULL) the active_mm obviously always has to be the same as the real
-   one.
-
-   For a anonymous process, tsk->mm == NULL, and tsk->active_mm is the
-   "borrowed" mm while the anonymous process is running. When the
-   anonymous process gets scheduled away, the borrowed address space is
-   returned and cleared.
-
-To support all that, the "struct mm_struct" now has two counters: a
-"mm_users" counter that is how many "real address space users" there are,
-and a "mm_count" counter that is the number of "lazy" users (ie anonymous
-users) plus one if there are any real users.
-
-Usually there is at least one real user, but it could be that the real
-user exited on another CPU while a lazy user was still active, so you do
-actually get cases where you have a address space that is _only_ used by
-lazy users. That is often a short-lived state, because once that thread
-gets scheduled away in favour of a real thread, the "zombie" mm gets
-released because "mm_users" becomes zero.
-
-Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
-more. "init_mm" should be considered just a "lazy context when no other
-context is available", and in fact it is mainly used just at bootup when
-no real VM has yet been created. So code that used to check
-
-	if (current->mm == &init_mm)
-
-should generally just do
-
-	if (!current->mm)
-
-instead (which makes more sense anyway - the test is basically one of "do
-we have a user context", and is generally done by the page fault handler
-and things like that).
-
-Anyway, I put a pre-patch-2.3.13-1 on ftp.kernel.org just a moment ago,
-because it slightly changes the interfaces to accommodate the alpha (who
-would have thought it, but the alpha actually ends up having one of the
-ugliest context switch codes - unlike the other architectures where the MM
-and register state is separate, the alpha PALcode joins the two, and you
-need to switch both together).
-
-(From http://marc.info/?l=linux-kernel&m=93337278602211&w=2)
diff --git a/Documentation/vm/balance b/Documentation/vm/balance.rst
index 964595481af6..6a1fadf3e173 100644
--- a/Documentation/vm/balance
+++ b/Documentation/vm/balance.rst
@@ -1,3 +1,9 @@
+.. _balance:
+
+================
+Memory Balancing
+================
+
 Started Jan 2000 by Kanoj Sarcar <kanoj@sgi.com>
 
 Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as
@@ -62,11 +68,11 @@ for non-sleepable allocations. Second, the HIGHMEM zone is also balanced,
 so as to give a fighting chance for replace_with_highmem() to get a
 HIGHMEM page, as well as to ensure that HIGHMEM allocations do not
 fall back into regular zone. This also makes sure that HIGHMEM pages
-are not leaked (for example, in situations where a HIGHMEM page is in 
+are not leaked (for example, in situations where a HIGHMEM page is in
 the swapcache but is not being used by anyone)
 
 kswapd also needs to know about the zones it should balance. kswapd is
-primarily needed in a situation where balancing can not be done, 
+primarily needed in a situation where balancing can not be done,
 probably because all allocation requests are coming from intr context
 and all process contexts are sleeping. For 2.3, kswapd does not really
 need to balance the highmem zone, since intr context does not request
@@ -89,7 +95,8 @@ pages is below watermark[WMARK_LOW]; in which case zone_wake_kswapd is also set.
 
 
 (Good) Ideas that I have heard:
+
 1. Dynamic experience should influence balancing: number of failed requests
-for a zone can be tracked and fed into the balancing scheme (jalvo@mbay.net)
+   for a zone can be tracked and fed into the balancing scheme (jalvo@mbay.net)
 2. Implement a replace_with_highmem()-like replace_with_regular() to preserve
-dma pages. (lkd@tantalophile.demon.co.uk)
+   dma pages. (lkd@tantalophile.demon.co.uk)
diff --git a/Documentation/vm/cleancache.txt b/Documentation/vm/cleancache.rst
index e4b49df7a048..68cba9131c31 100644
--- a/Documentation/vm/cleancache.txt
+++ b/Documentation/vm/cleancache.rst
@@ -1,4 +1,11 @@
-MOTIVATION
+.. _cleancache:
+
+==========
+Cleancache
+==========
+
+Motivation
+==========
 
 Cleancache is a new optional feature provided by the VFS layer that
 potentially dramatically increases page cache effectiveness for
@@ -21,9 +28,10 @@ Transcendent memory "drivers" for cleancache are currently implemented
 in Xen (using hypervisor memory) and zcache (using in-kernel compressed
 memory) and other implementations are in development.
 
-FAQs are included below.
+:ref:`FAQs <faq>` are included below.
 
-IMPLEMENTATION OVERVIEW
+Implementation Overview
+=======================
 
 A cleancache "backend" that provides transcendent memory registers itself
 to the kernel's cleancache "frontend" by calling cleancache_register_ops,
@@ -80,22 +88,33 @@ different Linux threads are simultaneously putting and invalidating a page
 with the same handle, the results are indeterminate.  Callers must
 lock the page to ensure serial behavior.
 
-CLEANCACHE PERFORMANCE METRICS
+Cleancache Performance Metrics
+==============================
 
 If properly configured, monitoring of cleancache is done via debugfs in
-the /sys/kernel/debug/cleancache directory.  The effectiveness of cleancache
+the `/sys/kernel/debug/cleancache` directory.  The effectiveness of cleancache
 can be measured (across all filesystems) with:
 
-succ_gets	- number of gets that were successful
-failed_gets	- number of gets that failed
-puts		- number of puts attempted (all "succeed")
-invalidates	- number of invalidates attempted
+``succ_gets``
+	number of gets that were successful
+
+``failed_gets``
+	number of gets that failed
+
+``puts``
+	number of puts attempted (all "succeed")
+
+``invalidates``
+	number of invalidates attempted
 
 A backend implementation may provide additional metrics.
 
+.. _faq:
+
 FAQ
+===
 
-1) Where's the value? (Andrew Morton)
+* Where's the value? (Andrew Morton)
 
 Cleancache provides a significant performance benefit to many workloads
 in many environments with negligible overhead by improving the
@@ -137,8 +156,8 @@ device that stores pages of data in a compressed state.  And
 the proposed "RAMster" driver shares RAM across multiple physical
 systems.
 
-2) Why does cleancache have its sticky fingers so deep inside the
-   filesystems and VFS? (Andrew Morton and Christoph Hellwig)
+* Why does cleancache have its sticky fingers so deep inside the
+  filesystems and VFS? (Andrew Morton and Christoph Hellwig)
 
 The core hooks for cleancache in VFS are in most cases a single line
 and the minimum set are placed precisely where needed to maintain
@@ -168,9 +187,9 @@ filesystems in the future.
 The total impact of the hooks to existing fs and mm files is only
 about 40 lines added (not counting comments and blank lines).
 
-3) Why not make cleancache asynchronous and batched so it can
-   more easily interface with real devices with DMA instead
-   of copying each individual page? (Minchan Kim)
+* Why not make cleancache asynchronous and batched so it can more
+  easily interface with real devices with DMA instead of copying each
+  individual page? (Minchan Kim)
 
 The one-page-at-a-time copy semantics simplifies the implementation
 on both the frontend and backend and also allows the backend to
@@ -182,8 +201,8 @@ are avoided.  While the interface seems odd for a "real device"
 or for real kernel-addressable RAM, it makes perfect sense for
 transcendent memory.
 
-4) Why is non-shared cleancache "exclusive"?  And where is the
-   page "invalidated" after a "get"? (Minchan Kim)
+* Why is non-shared cleancache "exclusive"?  And where is the
+  page "invalidated" after a "get"? (Minchan Kim)
 
 The main reason is to free up space in transcendent memory and
 to avoid unnecessary cleancache_invalidate calls.  If you want inclusive,
@@ -193,7 +212,7 @@ be easily extended to add a "get_no_invalidate" call.
 
 The invalidate is done by the cleancache backend implementation.
 
-5) What's the performance impact?
+* What's the performance impact?
 
 Performance analysis has been presented at OLS'09 and LCA'10.
 Briefly, performance gains can be significant on most workloads,
@@ -206,7 +225,7 @@ single-core systems with slow memory-copy speeds, cleancache
 has little value, but in newer multicore machines, especially
 consolidated/virtualized machines, it has great value.
 
-6) How do I add cleancache support for filesystem X? (Boaz Harrash)
+* How do I add cleancache support for filesystem X? (Boaz Harrash)
 
 Filesystems that are well-behaved and conform to certain
 restrictions can utilize cleancache simply by making a call to
@@ -217,26 +236,26 @@ not enable the optional cleancache.
 
 Some points for a filesystem to consider:
 
-- The FS should be block-device-based (e.g. a ram-based FS such
-  as tmpfs should not enable cleancache)
-- To ensure coherency/correctness, the FS must ensure that all
-  file removal or truncation operations either go through VFS or
-  add hooks to do the equivalent cleancache "invalidate" operations
-- To ensure coherency/correctness, either inode numbers must
-  be unique across the lifetime of the on-disk file OR the
-  FS must provide an "encode_fh" function.
-- The FS must call the VFS superblock alloc and deactivate routines
-  or add hooks to do the equivalent cleancache calls done there.
-- To maximize performance, all pages fetched from the FS should
-  go through the do_mpag_readpage routine or the FS should add
-  hooks to do the equivalent (cf. btrfs)
-- Currently, the FS blocksize must be the same as PAGESIZE.  This
-  is not an architectural restriction, but no backends currently
-  support anything different.
-- A clustered FS should invoke the "shared_init_fs" cleancache
-  hook to get best performance for some backends.
-
-7) Why not use the KVA of the inode as the key? (Christoph Hellwig)
+  - The FS should be block-device-based (e.g. a ram-based FS such
+    as tmpfs should not enable cleancache)
+  - To ensure coherency/correctness, the FS must ensure that all
+    file removal or truncation operations either go through VFS or
+    add hooks to do the equivalent cleancache "invalidate" operations
+  - To ensure coherency/correctness, either inode numbers must
+    be unique across the lifetime of the on-disk file OR the
+    FS must provide an "encode_fh" function.
+  - The FS must call the VFS superblock alloc and deactivate routines
+    or add hooks to do the equivalent cleancache calls done there.
+  - To maximize performance, all pages fetched from the FS should
+    go through the do_mpag_readpage routine or the FS should add
+    hooks to do the equivalent (cf. btrfs)
+  - Currently, the FS blocksize must be the same as PAGESIZE.  This
+    is not an architectural restriction, but no backends currently
+    support anything different.
+  - A clustered FS should invoke the "shared_init_fs" cleancache
+    hook to get best performance for some backends.
+
+* Why not use the KVA of the inode as the key? (Christoph Hellwig)
 
 If cleancache would use the inode virtual address instead of
 inode/filehandle, the pool id could be eliminated.  But, this
@@ -251,7 +270,7 @@ of cleancache would be lost because the cache of pages in cleanache
 is potentially much larger than the kernel pagecache and is most
 useful if the pages survive inode cache removal.
 
-8) Why is a global variable required?
+* Why is a global variable required?
 
 The cleancache_enabled flag is checked in all of the frequently-used
 cleancache hooks.  The alternative is a function call to check a static
@@ -262,14 +281,14 @@ global variable allows cleancache to be enabled by default at compile
 time, but have insignificant performance impact when cleancache remains
 disabled at runtime.
 
-9) Does cleanache work with KVM?
+* Does cleanache work with KVM?
 
 The memory model of KVM is sufficiently different that a cleancache
 backend may have less value for KVM.  This remains to be tested,
 especially in an overcommitted system.
 
-10) Does cleancache work in userspace?  It sounds useful for
-   memory hungry caches like web browsers.  (Jamie Lokier)
+* Does cleancache work in userspace?  It sounds useful for
+  memory hungry caches like web browsers.  (Jamie Lokier)
 
 No plans yet, though we agree it sounds useful, at least for
 apps that bypass the page cache (e.g. O_DIRECT).
diff --git a/Documentation/vm/conf.py b/Documentation/vm/conf.py
new file mode 100644
index 000000000000..3b0b601af558
--- /dev/null
+++ b/Documentation/vm/conf.py
@@ -0,0 +1,10 @@
+# -*- coding: utf-8; mode: python -*-
+
+project = "Linux Memory Management Documentation"
+
+tags.add("subproject")
+
+latex_documents = [
+    ('index', 'memory-management.tex', project,
+     'The kernel development community', 'manual'),
+]
diff --git a/Documentation/vm/frontswap.txt b/Documentation/vm/frontswap.rst
index c71a019be600..1979f430c1c5 100644
--- a/Documentation/vm/frontswap.txt
+++ b/Documentation/vm/frontswap.rst
@@ -1,13 +1,20 @@
+.. _frontswap:
+
+=========
+Frontswap
+=========
+
 Frontswap provides a "transcendent memory" interface for swap pages.
 In some environments, dramatic performance savings may be obtained because
 swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk.
 
-(Note, frontswap -- and cleancache (merged at 3.0) -- are the "frontends"
+(Note, frontswap -- and :ref:`cleancache` (merged at 3.0) -- are the "frontends"
 and the only necessary changes to the core kernel for transcendent memory;
 all other supporting code -- the "backends" -- is implemented as drivers.
-See the LWN.net article "Transcendent memory in a nutshell" for a detailed
-overview of frontswap and related kernel parts:
-https://lwn.net/Articles/454795/ )
+See the LWN.net article `Transcendent memory in a nutshell`_
+for a detailed overview of frontswap and related kernel parts)
+
+.. _Transcendent memory in a nutshell: https://lwn.net/Articles/454795/
 
 Frontswap is so named because it can be thought of as the opposite of
 a "backing" store for a swap device.  The storage is assumed to be
@@ -50,19 +57,27 @@ or the store fails AND the page is invalidated.  This ensures stale data may
 never be obtained from frontswap.
 
 If properly configured, monitoring of frontswap is done via debugfs in
-the /sys/kernel/debug/frontswap directory.  The effectiveness of
+the `/sys/kernel/debug/frontswap` directory.  The effectiveness of
 frontswap can be measured (across all swap devices) with:
 
-failed_stores	- how many store attempts have failed
-loads		- how many loads were attempted (all should succeed)
-succ_stores	- how many store attempts have succeeded
-invalidates	- how many invalidates were attempted
+``failed_stores``
+	how many store attempts have failed
+
+``loads``
+	how many loads were attempted (all should succeed)
+
+``succ_stores``
+	how many store attempts have succeeded
+
+``invalidates``
+	how many invalidates were attempted
 
 A backend implementation may provide additional metrics.
 
 FAQ
+===
 
-1) Where's the value?
+* Where's the value?
 
 When a workload starts swapping, performance falls through the floor.
 Frontswap significantly increases performance in many such workloads by
@@ -117,8 +132,8 @@ A KVM implementation is underway and has been RFC'ed to lkml.  And,
 using frontswap, investigation is also underway on the use of NVM as
 a memory extension technology.
 
-2) Sure there may be performance advantages in some situations, but
-   what's the space/time overhead of frontswap?
+* Sure there may be performance advantages in some situations, but
+  what's the space/time overhead of frontswap?
 
 If CONFIG_FRONTSWAP is disabled, every frontswap hook compiles into
 nothingness and the only overhead is a few extra bytes per swapon'ed
@@ -148,8 +163,8 @@ pressure that can potentially outweigh the other advantages.  A
 backend, such as zcache, must implement policies to carefully (but
 dynamically) manage memory limits to ensure this doesn't happen.
 
-3) OK, how about a quick overview of what this frontswap patch does
-   in terms that a kernel hacker can grok?
+* OK, how about a quick overview of what this frontswap patch does
+  in terms that a kernel hacker can grok?
 
 Let's assume that a frontswap "backend" has registered during
 kernel initialization; this registration indicates that this
@@ -188,9 +203,9 @@ and (potentially) a swap device write are replaced by a "frontswap backend
 store" and (possibly) a "frontswap backend loads", which are presumably much
 faster.
 
-4) Can't frontswap be configured as a "special" swap device that is
-   just higher priority than any real swap device (e.g. like zswap,
-   or maybe swap-over-nbd/NFS)?
+* Can't frontswap be configured as a "special" swap device that is
+  just higher priority than any real swap device (e.g. like zswap,
+  or maybe swap-over-nbd/NFS)?
 
 No.  First, the existing swap subsystem doesn't allow for any kind of
 swap hierarchy.  Perhaps it could be rewritten to accommodate a hierarchy,
@@ -240,9 +255,9 @@ installation, frontswap is useless.  Swapless portable devices
 can still use frontswap but a backend for such devices must configure
 some kind of "ghost" swap device and ensure that it is never used.
 
-5) Why this weird definition about "duplicate stores"?  If a page
-   has been previously successfully stored, can't it always be
-   successfully overwritten?
+* Why this weird definition about "duplicate stores"?  If a page
+  has been previously successfully stored, can't it always be
+  successfully overwritten?
 
 Nearly always it can, but no, sometimes it cannot.  Consider an example
 where data is compressed and the original 4K page has been compressed
@@ -254,7 +269,7 @@ the old data and ensure that it is no longer accessible.  Since the
 swap subsystem then writes the new data to the read swap device,
 this is the correct course of action to ensure coherency.
 
-6) What is frontswap_shrink for?
+* What is frontswap_shrink for?
 
 When the (non-frontswap) swap subsystem swaps out a page to a real
 swap device, that page is only taking up low-value pre-allocated disk
@@ -267,7 +282,7 @@ to "repatriate" pages sent to a remote machine back to the local machine;
 this is driven using the frontswap_shrink mechanism when memory pressure
 subsides.
 
-7) Why does the frontswap patch create the new include file swapfile.h?
+* Why does the frontswap patch create the new include file swapfile.h?
 
 The frontswap code depends on some swap-subsystem-internal data
 structures that have, over the years, moved back and forth between
diff --git a/Documentation/vm/highmem.txt b/Documentation/vm/highmem.rst
index 4324d24ffacd..0f69a9fec34d 100644
--- a/Documentation/vm/highmem.txt
+++ b/Documentation/vm/highmem.rst
@@ -1,25 +1,14 @@
+.. _highmem:
 
-			     ====================
-			     HIGH MEMORY HANDLING
-			     ====================
+====================
+High Memory Handling
+====================
 
 By: Peter Zijlstra <a.p.zijlstra@chello.nl>
 
-Contents:
-
- (*) What is high memory?
-
- (*) Temporary virtual mappings.
-
- (*) Using kmap_atomic.
-
- (*) Cost of temporary mappings.
-
- (*) i386 PAE.
+.. contents:: :local:
 
-
-====================
-WHAT IS HIGH MEMORY?
+What Is High Memory?
 ====================
 
 High memory (highmem) is used when the size of physical memory approaches or
@@ -38,7 +27,7 @@ kernel entry/exit.  This means the available virtual memory space (4GiB on
 i386) has to be divided between user and kernel space.
 
 The traditional split for architectures using this approach is 3:1, 3GiB for
-userspace and the top 1GiB for kernel space:
+userspace and the top 1GiB for kernel space::
 
 		+--------+ 0xffffffff
 		| Kernel |
@@ -58,40 +47,38 @@ and user maps.  Some hardware (like some ARMs), however, have limited virtual
 space when they use mm context tags.
 
 
-==========================
-TEMPORARY VIRTUAL MAPPINGS
+Temporary Virtual Mappings
 ==========================
 
 The kernel contains several ways of creating temporary mappings:
 
- (*) vmap().  This can be used to make a long duration mapping of multiple
-     physical pages into a contiguous virtual space.  It needs global
-     synchronization to unmap.
+* vmap().  This can be used to make a long duration mapping of multiple
+  physical pages into a contiguous virtual space.  It needs global
+  synchronization to unmap.
 
- (*) kmap().  This permits a short duration mapping of a single page.  It needs
-     global synchronization, but is amortized somewhat.  It is also prone to
-     deadlocks when using in a nested fashion, and so it is not recommended for
-     new code.
+* kmap().  This permits a short duration mapping of a single page.  It needs
+  global synchronization, but is amortized somewhat.  It is also prone to
+  deadlocks when using in a nested fashion, and so it is not recommended for
+  new code.
 
- (*) kmap_atomic().  This permits a very short duration mapping of a single
-     page.  Since the mapping is restricted to the CPU that issued it, it
-     performs well, but the issuing task is therefore required to stay on that
-     CPU until it has finished, lest some other task displace its mappings.
+* kmap_atomic().  This permits a very short duration mapping of a single
+  page.  Since the mapping is restricted to the CPU that issued it, it
+  performs well, but the issuing task is therefore required to stay on that
+  CPU until it has finished, lest some other task displace its mappings.
 
-     kmap_atomic() may also be used by interrupt contexts, since it is does not
-     sleep and the caller may not sleep until after kunmap_atomic() is called.
+  kmap_atomic() may also be used by interrupt contexts, since it is does not
+  sleep and the caller may not sleep until after kunmap_atomic() is called.
 
-     It may be assumed that k[un]map_atomic() won't fail.
+  It may be assumed that k[un]map_atomic() won't fail.
 
 
-=================
-USING KMAP_ATOMIC
+Using kmap_atomic
 =================
 
 When and where to use kmap_atomic() is straightforward.  It is used when code
 wants to access the contents of a page that might be allocated from high memory
 (see __GFP_HIGHMEM), for example a page in the pagecache.  The API has two
-functions, and they can be used in a manner similar to the following:
+functions, and they can be used in a manner similar to the following::
 
 	/* Find the page of interest. */
 	struct page *page = find_get_page(mapping, offset);
@@ -109,7 +96,7 @@ Note that the kunmap_atomic() call takes the result of the kmap_atomic() call
 not the argument.
 
 If you need to map two pages because you want to copy from one page to
-another you need to keep the kmap_atomic calls strictly nested, like:
+another you need to keep the kmap_atomic calls strictly nested, like::
 
 	vaddr1 = kmap_atomic(page1);
 	vaddr2 = kmap_atomic(page2);
@@ -120,8 +107,7 @@ another you need to keep the kmap_atomic calls strictly nested, like:
 	kunmap_atomic(vaddr1);
 
 
-==========================
-COST OF TEMPORARY MAPPINGS
+Cost of Temporary Mappings
 ==========================
 
 The cost of creating temporary mappings can be quite high.  The arch has to
@@ -136,25 +122,24 @@ If CONFIG_MMU is not set, then there can be no temporary mappings and no
 highmem.  In such a case, the arithmetic approach will also be used.
 
 
-========
 i386 PAE
 ========
 
 The i386 arch, under some circumstances, will permit you to stick up to 64GiB
 of RAM into your 32-bit machine.  This has a number of consequences:
 
- (*) Linux needs a page-frame structure for each page in the system and the
-     pageframes need to live in the permanent mapping, which means:
+* Linux needs a page-frame structure for each page in the system and the
+  pageframes need to live in the permanent mapping, which means:
 
- (*) you can have 896M/sizeof(struct page) page-frames at most; with struct
-     page being 32-bytes that would end up being something in the order of 112G
-     worth of pages; the kernel, however, needs to store more than just
-     page-frames in that memory...
+* you can have 896M/sizeof(struct page) page-frames at most; with struct
+  page being 32-bytes that would end up being something in the order of 112G
+  worth of pages; the kernel, however, needs to store more than just
+  page-frames in that memory...
 
- (*) PAE makes your page tables larger - which slows the system down as more
-     data has to be accessed to traverse in TLB fills and the like.  One
-     advantage is that PAE has more PTE bits and can provide advanced features
-     like NX and PAT.
+* PAE makes your page tables larger - which slows the system down as more
+  data has to be accessed to traverse in TLB fills and the like.  One
+  advantage is that PAE has more PTE bits and can provide advanced features
+  like NX and PAT.
 
 The general recommendation is that you don't use more than 8GiB on a 32-bit
 machine - although more might work for you and your workload, you're pretty
diff --git a/Documentation/vm/hmm.txt b/Documentation/vm/hmm.rst
index 2d1d6f69e91b..cdf3911582c8 100644
--- a/Documentation/vm/hmm.txt
+++ b/Documentation/vm/hmm.rst
@@ -1,4 +1,8 @@
+.. hmm:
+
+=====================================
 Heterogeneous Memory Management (HMM)
+=====================================
 
 Provide infrastructure and helpers to integrate non-conventional memory (device
 memory like GPU on board memory) into regular kernel path, with the cornerstone
@@ -6,10 +10,10 @@ of this being specialized struct page for such memory (see sections 5 to 7 of
 this document).
 
 HMM also provides optional helpers for SVM (Share Virtual Memory), i.e.,
-allowing a device to transparently access program address coherently with the
-CPU meaning that any valid pointer on the CPU is also a valid pointer for the
-device. This is becoming mandatory to simplify the use of advanced hetero-
-geneous computing where GPU, DSP, or FPGA are used to perform various
+allowing a device to transparently access program address coherently with
+the CPU meaning that any valid pointer on the CPU is also a valid pointer
+for the device. This is becoming mandatory to simplify the use of advanced
+heterogeneous computing where GPU, DSP, or FPGA are used to perform various
 computations on behalf of a process.
 
 This document is divided as follows: in the first section I expose the problems
@@ -21,19 +25,10 @@ fifth section deals with how device memory is represented inside the kernel.
 Finally, the last section presents a new migration helper that allows lever-
 aging the device DMA engine.
 
+.. contents:: :local:
 
-1) Problems of using a device specific memory allocator:
-2) I/O bus, device memory characteristics
-3) Shared address space and migration
-4) Address space mirroring implementation and API
-5) Represent and manage device memory from core kernel point of view
-6) Migration to and from device memory
-7) Memory cgroup (memcg) and rss accounting
-
-
--------------------------------------------------------------------------------
-
-1) Problems of using a device specific memory allocator:
+Problems of using a device specific memory allocator
+====================================================
 
 Devices with a large amount of on board memory (several gigabytes) like GPUs
 have historically managed their memory through dedicated driver specific APIs.
@@ -77,9 +72,8 @@ are only do-able with a shared address space. It is also more reasonable to use
 a shared address space for all other patterns.
 
 
--------------------------------------------------------------------------------
-
-2) I/O bus, device memory characteristics
+I/O bus, device memory characteristics
+======================================
 
 I/O buses cripple shared address spaces due to a few limitations. Most I/O
 buses only allow basic memory access from device to main memory; even cache
@@ -109,9 +103,8 @@ access any memory but we must also permit any memory to be migrated to device
 memory while device is using it (blocking CPU access while it happens).
 
 
--------------------------------------------------------------------------------
-
-3) Shared address space and migration
+Shared address space and migration
+==================================
 
 HMM intends to provide two main features. First one is to share the address
 space by duplicating the CPU page table in the device page table so the same
@@ -148,23 +141,23 @@ ages device memory by migrating the part of the data set that is actively being
 used by the device.
 
 
--------------------------------------------------------------------------------
-
-4) Address space mirroring implementation and API
+Address space mirroring implementation and API
+==============================================
 
 Address space mirroring's main objective is to allow duplication of a range of
 CPU page table into a device page table; HMM helps keep both synchronized. A
 device driver that wants to mirror a process address space must start with the
-registration of an hmm_mirror struct:
+registration of an hmm_mirror struct::
 
  int hmm_mirror_register(struct hmm_mirror *mirror,
                          struct mm_struct *mm);
  int hmm_mirror_register_locked(struct hmm_mirror *mirror,
                                 struct mm_struct *mm);
 
+
 The locked variant is to be used when the driver is already holding mmap_sem
 of the mm in write mode. The mirror struct has a set of callbacks that are used
-to propagate CPU page tables:
+to propagate CPU page tables::
 
  struct hmm_mirror_ops {
      /* sync_cpu_device_pagetables() - synchronize page tables
@@ -193,10 +186,10 @@ The device driver must perform the update action to the range (mark range
 read only, or fully unmap, ...). The device must be done with the update before
 the driver callback returns.
 
-
 When the device driver wants to populate a range of virtual addresses, it can
-use either:
- int hmm_vma_get_pfns(struct vm_area_struct *vma,
+use either::
+
+  int hmm_vma_get_pfns(struct vm_area_struct *vma,
                       struct hmm_range *range,
                       unsigned long start,
                       unsigned long end,
@@ -221,7 +214,7 @@ provides a set of flags to help the driver identify special CPU page table
 entries.
 
 Locking with the update() callback is the most important aspect the driver must
-respect in order to keep things properly synchronized. The usage pattern is:
+respect in order to keep things properly synchronized. The usage pattern is::
 
  int driver_populate_range(...)
  {
@@ -262,9 +255,8 @@ report commands as executed is serialized (there is no point in doing this
 concurrently).
 
 
--------------------------------------------------------------------------------
-
-5) Represent and manage device memory from core kernel point of view
+Represent and manage device memory from core kernel point of view
+=================================================================
 
 Several different designs were tried to support device memory. First one used
 a device specific data structure to keep information about migrated memory and
@@ -280,14 +272,14 @@ unaware of the difference. We only need to make sure that no one ever tries to
 map those pages from the CPU side.
 
 HMM provides a set of helpers to register and hotplug device memory as a new
-region needing a struct page. This is offered through a very simple API:
+region needing a struct page. This is offered through a very simple API::
 
  struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
                                    struct device *device,
                                    unsigned long size);
  void hmm_devmem_remove(struct hmm_devmem *devmem);
 
-The hmm_devmem_ops is where most of the important things are:
+The hmm_devmem_ops is where most of the important things are::
 
  struct hmm_devmem_ops {
      void (*free)(struct hmm_devmem *devmem, struct page *page);
@@ -306,13 +298,12 @@ which it cannot do. This second callback must trigger a migration back to
 system memory.
 
 
--------------------------------------------------------------------------------
-
-6) Migration to and from device memory
+Migration to and from device memory
+===================================
 
 Because the CPU cannot access device memory, migration must use the device DMA
 engine to perform copy from and to device memory. For this we need a new
-migration helper:
+migration helper::
 
  int migrate_vma(const struct migrate_vma_ops *ops,
                  struct vm_area_struct *vma,
@@ -331,7 +322,7 @@ migration might be for a range of addresses the device is actively accessing.
 
 The migrate_vma_ops struct defines two callbacks. First one (alloc_and_copy())
 controls destination memory allocation and copy operation. Second one is there
-to allow the device driver to perform cleanup operations after migration.
+to allow the device driver to perform cleanup operations after migration::
 
  struct migrate_vma_ops {
      void (*alloc_and_copy)(struct vm_area_struct *vma,
@@ -365,9 +356,8 @@ bandwidth but this is considered as a rare event and a price that we are
 willing to pay to keep all the code simpler.
 
 
--------------------------------------------------------------------------------
-
-7) Memory cgroup (memcg) and rss accounting
+Memory cgroup (memcg) and rss accounting
+========================================
 
 For now device memory is accounted as any regular page in rss counters (either
 anonymous if device page is used for anonymous, file if device page is used for
diff --git a/Documentation/vm/hugetlbfs_reserv.txt b/Documentation/vm/hugetlbfs_reserv.rst
index 9aca09a76bed..9d200762114f 100644
--- a/Documentation/vm/hugetlbfs_reserv.txt
+++ b/Documentation/vm/hugetlbfs_reserv.rst
@@ -1,6 +1,13 @@
-Hugetlbfs Reservation Overview
-------------------------------
-Huge pages as described at 'Documentation/vm/hugetlbpage.txt' are typically
+.. _hugetlbfs_reserve:
+
+=====================
+Hugetlbfs Reservation
+=====================
+
+Overview
+========
+
+Huge pages as described at :ref:`hugetlbpage` are typically
 preallocated for application use.  These huge pages are instantiated in a
 task's address space at page fault time if the VMA indicates huge pages are
 to be used.  If no huge page exists at page fault time, the task is sent
@@ -17,47 +24,55 @@ describe how huge page reserve processing is done in the v4.10 kernel.
 
 
 Audience
---------
+========
 This description is primarily targeted at kernel developers who are modifying
 hugetlbfs code.
 
 
 The Data Structures
--------------------
+===================
+
 resv_huge_pages
 	This is a global (per-hstate) count of reserved huge pages.  Reserved
 	huge pages are only available to the task which reserved them.
 	Therefore, the number of huge pages generally available is computed
-	as (free_huge_pages - resv_huge_pages).
+	as (``free_huge_pages - resv_huge_pages``).
 Reserve Map
-	A reserve map is described by the structure:
-	struct resv_map {
-		struct kref refs;
-		spinlock_t lock;
-		struct list_head regions;
-		long adds_in_progress;
-		struct list_head region_cache;
-		long region_cache_count;
-	};
+	A reserve map is described by the structure::
+
+		struct resv_map {
+			struct kref refs;
+			spinlock_t lock;
+			struct list_head regions;
+			long adds_in_progress;
+			struct list_head region_cache;
+			long region_cache_count;
+		};
+
 	There is one reserve map for each huge page mapping in the system.
 	The regions list within the resv_map describes the regions within
-	the mapping.  A region is described as:
-	struct file_region {
-		struct list_head link;
-		long from;
-		long to;
-	};
+	the mapping.  A region is described as::
+
+		struct file_region {
+			struct list_head link;
+			long from;
+			long to;
+		};
+
 	The 'from' and 'to' fields of the file region structure are huge page
 	indices into the mapping.  Depending on the type of mapping, a
 	region in the reserv_map may indicate reservations exist for the
 	range, or reservations do not exist.
 Flags for MAP_PRIVATE Reservations
 	These are stored in the bottom bits of the reservation map pointer.
-	#define HPAGE_RESV_OWNER    (1UL << 0) Indicates this task is the
-		owner of the reservations associated with the mapping.
-	#define HPAGE_RESV_UNMAPPED (1UL << 1) Indicates task originally
-		mapping this range (and creating reserves) has unmapped a
-		page from this task (the child) due to a failed COW.
+
+	``#define HPAGE_RESV_OWNER    (1UL << 0)``
+		Indicates this task is the owner of the reservations
+		associated with the mapping.
+	``#define HPAGE_RESV_UNMAPPED (1UL << 1)``
+		Indicates task originally mapping this range (and creating
+		reserves) has unmapped a page from this task (the child)
+		due to a failed COW.
 Page Flags
 	The PagePrivate page flag is used to indicate that a huge page
 	reservation must be restored when the huge page is freed.  More
@@ -65,12 +80,14 @@ Page Flags
 
 
 Reservation Map Location (Private or Shared)
---------------------------------------------
+============================================
+
 A huge page mapping or segment is either private or shared.  If private,
 it is typically only available to a single address space (task).  If shared,
 it can be mapped into multiple address spaces (tasks).  The location and
 semantics of the reservation map is significantly different for two types
 of mappings.  Location differences are:
+
 - For private mappings, the reservation map hangs off the the VMA structure.
   Specifically, vma->vm_private_data.  This reserve map is created at the
   time the mapping (mmap(MAP_PRIVATE)) is created.
@@ -82,15 +99,15 @@ of mappings.  Location differences are:
 
 
 Creating Reservations
----------------------
+=====================
 Reservations are created when a huge page backed shared memory segment is
 created (shmget(SHM_HUGETLB)) or a mapping is created via mmap(MAP_HUGETLB).
-These operations result in a call to the routine hugetlb_reserve_pages()
+These operations result in a call to the routine hugetlb_reserve_pages()::
 
-int hugetlb_reserve_pages(struct inode *inode,
-					long from, long to,
-					struct vm_area_struct *vma,
-					vm_flags_t vm_flags)
+	int hugetlb_reserve_pages(struct inode *inode,
+				  long from, long to,
+				  struct vm_area_struct *vma,
+				  vm_flags_t vm_flags)
 
 The first thing hugetlb_reserve_pages() does is check for the NORESERVE
 flag was specified in either the shmget() or mmap() call.  If NORESERVE
@@ -105,6 +122,7 @@ the 'from' and 'to' arguments have been adjusted by this offset.
 
 One of the big differences between PRIVATE and SHARED mappings is the way
 in which reservations are represented in the reservation map.
+
 - For shared mappings, an entry in the reservation map indicates a reservation
   exists or did exist for the corresponding page.  As reservations are
   consumed, the reservation map is not modified.
@@ -121,12 +139,13 @@ to indicate this VMA owns the reservations.
 The reservation map is consulted to determine how many huge page reservations
 are needed for the current mapping/segment.  For private mappings, this is
 always the value (to - from).  However, for shared mappings it is possible that some reservations may already exist within the range (to - from).  See the
-section "Reservation Map Modifications" for details on how this is accomplished.
+section :ref:`Reservation Map Modifications <resv_map_modifications>`
+for details on how this is accomplished.
 
 The mapping may be associated with a subpool.  If so, the subpool is consulted
 to ensure there is sufficient space for the mapping.  It is possible that the
 subpool has set aside reservations that can be used for the mapping.  See the
-section "Subpool Reservations" for more details.
+section :ref:`Subpool Reservations <sub_pool_resv>` for more details.
 
 After consulting the reservation map and subpool, the number of needed new
 reservations is known.  The routine hugetlb_acct_memory() is called to check
@@ -135,9 +154,11 @@ calls into routines that potentially allocate and adjust surplus page counts.
 However, within those routines the code is simply checking to ensure there
 are enough free huge pages to accommodate the reservation.  If there are,
 the global reservation count resv_huge_pages is adjusted something like the
-following.
+following::
+
 	if (resv_needed <= (resv_huge_pages - free_huge_pages))
 		resv_huge_pages += resv_needed;
+
 Note that the global lock hugetlb_lock is held when checking and adjusting
 these counters.
 
@@ -152,14 +173,18 @@ If hugetlb_reserve_pages() was successful, the global reservation count and
 reservation map associated with the mapping will be modified as required to
 ensure reservations exist for the range 'from' - 'to'.
 
+.. _consume_resv:
 
 Consuming Reservations/Allocating a Huge Page
----------------------------------------------
+=============================================
+
 Reservations are consumed when huge pages associated with the reservations
 are allocated and instantiated in the corresponding mapping.  The allocation
-is performed within the routine alloc_huge_page().
-struct page *alloc_huge_page(struct vm_area_struct *vma,
-                                    unsigned long addr, int avoid_reserve)
+is performed within the routine alloc_huge_page()::
+
+	struct page *alloc_huge_page(struct vm_area_struct *vma,
+				     unsigned long addr, int avoid_reserve)
+
 alloc_huge_page is passed a VMA pointer and a virtual address, so it can
 consult the reservation map to determine if a reservation exists.  In addition,
 alloc_huge_page takes the argument avoid_reserve which indicates reserves
@@ -170,8 +195,9 @@ page are being allocated.
 
 The helper routine vma_needs_reservation() is called to determine if a
 reservation exists for the address within the mapping(vma).  See the section
-"Reservation Map Helper Routines" for detailed information on what this
-routine does.  The value returned from vma_needs_reservation() is generally
+:ref:`Reservation Map Helper Routines <resv_map_helpers>` for detailed
+information on what this routine does.
+The value returned from vma_needs_reservation() is generally
 0 or 1.  0 if a reservation exists for the address, 1 if no reservation exists.
 If a reservation does not exist, and there is a subpool associated with the
 mapping the subpool is consulted to determine if it contains reservations.
@@ -180,21 +206,25 @@ However, in every case the avoid_reserve argument overrides the use of
 a reservation for the allocation.  After determining whether a reservation
 exists and can be used for the allocation, the routine dequeue_huge_page_vma()
 is called.  This routine takes two arguments related to reservations:
+
 - avoid_reserve, this is the same value/argument passed to alloc_huge_page()
 - chg, even though this argument is of type long only the values 0 or 1 are
   passed to dequeue_huge_page_vma.  If the value is 0, it indicates a
   reservation exists (see the section "Memory Policy and Reservations" for
   possible issues).  If the value is 1, it indicates a reservation does not
   exist and the page must be taken from the global free pool if possible.
+
 The free lists associated with the memory policy of the VMA are searched for
 a free page.  If a page is found, the value free_huge_pages is decremented
 when the page is removed from the free list.  If there was a reservation
-associated with the page, the following adjustments are made:
+associated with the page, the following adjustments are made::
+
 	SetPagePrivate(page);	/* Indicates allocating this page consumed
 				 * a reservation, and if an error is
 				 * encountered such that the page must be
 				 * freed, the reservation will be restored. */
 	resv_huge_pages--;	/* Decrement the global reservation count */
+
 Note, if no huge page can be found that satisfies the VMA's memory policy
 an attempt will be made to allocate one using the buddy allocator.  This
 brings up the issue of surplus huge pages and overcommit which is beyond
@@ -222,12 +252,14 @@ mapping.  In such cases, the reservation count and subpool free page count
 will be off by one.  This rare condition can be identified by comparing the
 return value from vma_needs_reservation and vma_commit_reservation.  If such
 a race is detected, the subpool and global reserve counts are adjusted to
-compensate.  See the section "Reservation Map Helper Routines" for more
+compensate.  See the section
+:ref:`Reservation Map Helper Routines <resv_map_helpers>` for more
 information on these routines.
 
 
 Instantiate Huge Pages
-----------------------
+======================
+
 After huge page allocation, the page is typically added to the page tables
 of the allocating task.  Before this, pages in a shared mapping are added
 to the page cache and pages in private mappings are added to an anonymous
@@ -237,7 +269,8 @@ to the global reservation count (resv_huge_pages).
 
 
 Freeing Huge Pages
-------------------
+==================
+
 Huge page freeing is performed by the routine free_huge_page().  This routine
 is the destructor for hugetlbfs compound pages.  As a result, it is only
 passed a pointer to the page struct.  When a huge page is freed, reservation
@@ -247,7 +280,8 @@ on an error path where a global reserve count must be restored.
 
 The page->private field points to any subpool associated with the page.
 If the PagePrivate flag is set, it indicates the global reserve count should
-be adjusted (see the section "Consuming Reservations/Allocating a Huge Page"
+be adjusted (see the section
+:ref:`Consuming Reservations/Allocating a Huge Page <consume_resv>`
 for information on how these are set).
 
 The routine first calls hugepage_subpool_put_pages() for the page.  If this
@@ -259,9 +293,11 @@ Therefore, the global resv_huge_pages counter is incremented in this case.
 If the PagePrivate flag was set in the page, the global resv_huge_pages counter
 will always be incremented.
 
+.. _sub_pool_resv:
 
 Subpool Reservations
---------------------
+====================
+
 There is a struct hstate associated with each huge page size.  The hstate
 tracks all huge pages of the specified size.  A subpool represents a subset
 of pages within a hstate that is associated with a mounted hugetlbfs
@@ -295,7 +331,8 @@ the global pools.
 
 
 COW and Reservations
---------------------
+====================
+
 Since shared mappings all point to and use the same underlying pages, the
 biggest reservation concern for COW is private mappings.  In this case,
 two tasks can be pointing at the same previously allocated page.  One task
@@ -326,30 +363,36 @@ faults on a non-present page.  But, the original owner of the
 mapping/reservation will behave as expected.
 
 
+.. _resv_map_modifications:
+
 Reservation Map Modifications
------------------------------
+=============================
+
 The following low level routines are used to make modifications to a
 reservation map.  Typically, these routines are not called directly.  Rather,
 a reservation map helper routine is called which calls one of these low level
 routines.  These low level routines are fairly well documented in the source
-code (mm/hugetlb.c).  These routines are:
-long region_chg(struct resv_map *resv, long f, long t);
-long region_add(struct resv_map *resv, long f, long t);
-void region_abort(struct resv_map *resv, long f, long t);
-long region_count(struct resv_map *resv, long f, long t);
+code (mm/hugetlb.c).  These routines are::
+
+	long region_chg(struct resv_map *resv, long f, long t);
+	long region_add(struct resv_map *resv, long f, long t);
+	void region_abort(struct resv_map *resv, long f, long t);
+	long region_count(struct resv_map *resv, long f, long t);
 
 Operations on the reservation map typically involve two operations:
+
 1) region_chg() is called to examine the reserve map and determine how
    many pages in the specified range [f, t) are NOT currently represented.
 
    The calling code performs global checks and allocations to determine if
    there are enough huge pages for the operation to succeed.
 
-2a) If the operation can succeed, region_add() is called to actually modify
-    the reservation map for the same range [f, t) previously passed to
-    region_chg().
-2b) If the operation can not succeed, region_abort is called for the same range
-    [f, t) to abort the operation.
+2)
+  a) If the operation can succeed, region_add() is called to actually modify
+     the reservation map for the same range [f, t) previously passed to
+     region_chg().
+  b) If the operation can not succeed, region_abort is called for the same
+     range [f, t) to abort the operation.
 
 Note that this is a two step process where region_add() and region_abort()
 are guaranteed to succeed after a prior call to region_chg() for the same
@@ -371,6 +414,7 @@ and make the appropriate adjustments.
 
 The routine region_del() is called to remove regions from a reservation map.
 It is typically called in the following situations:
+
 - When a file in the hugetlbfs filesystem is being removed, the inode will
   be released and the reservation map freed.  Before freeing the reservation
   map, all the individual file_region structures must be freed.  In this case
@@ -384,6 +428,7 @@ It is typically called in the following situations:
   removed, region_del() is called to remove the corresponding entry from the
   reservation map.  In this case, region_del is passed the range
   [page_idx, page_idx + 1).
+
 In every case, region_del() will return the number of pages removed from the
 reservation map.  In VERY rare cases, region_del() can fail.  This can only
 happen in the hole punch case where it has to split an existing file_region
@@ -403,9 +448,11 @@ outstanding (outstanding = (end - start) - region_count(resv, start, end)).
 Since the mapping is going away, the subpool and global reservation counts
 are decremented by the number of outstanding reservations.
 
+.. _resv_map_helpers:
 
 Reservation Map Helper Routines
--------------------------------
+===============================
+
 Several helper routines exist to query and modify the reservation maps.
 These routines are only interested with reservations for a specific huge
 page, so they just pass in an address instead of a range.  In addition,
@@ -414,32 +461,40 @@ or shared) and the location of the reservation map (inode or VMA) can be
 determined.  These routines simply call the underlying routines described
 in the section "Reservation Map Modifications".  However, they do take into
 account the 'opposite' meaning of reservation map entries for private and
-shared mappings and hide this detail from the caller.
+shared mappings and hide this detail from the caller::
+
+	long vma_needs_reservation(struct hstate *h,
+				   struct vm_area_struct *vma,
+				   unsigned long addr)
 
-long vma_needs_reservation(struct hstate *h,
-				struct vm_area_struct *vma, unsigned long addr)
 This routine calls region_chg() for the specified page.  If no reservation
-exists, 1 is returned.  If a reservation exists, 0 is returned.
+exists, 1 is returned.  If a reservation exists, 0 is returned::
+
+	long vma_commit_reservation(struct hstate *h,
+				    struct vm_area_struct *vma,
+				    unsigned long addr)
 
-long vma_commit_reservation(struct hstate *h,
-				struct vm_area_struct *vma, unsigned long addr)
 This calls region_add() for the specified page.  As in the case of region_chg
 and region_add, this routine is to be called after a previous call to
 vma_needs_reservation.  It will add a reservation entry for the page.  It
 returns 1 if the reservation was added and 0 if not.  The return value should
 be compared with the return value of the previous call to
 vma_needs_reservation.  An unexpected difference indicates the reservation
-map was modified between calls.
+map was modified between calls::
+
+	void vma_end_reservation(struct hstate *h,
+				 struct vm_area_struct *vma,
+				 unsigned long addr)
 
-void vma_end_reservation(struct hstate *h,
-				struct vm_area_struct *vma, unsigned long addr)
 This calls region_abort() for the specified page.  As in the case of region_chg
 and region_abort, this routine is to be called after a previous call to
 vma_needs_reservation.  It will abort/end the in progress reservation add
-operation.
+operation::
+
+	long vma_add_reservation(struct hstate *h,
+				 struct vm_area_struct *vma,
+				 unsigned long addr)
 
-long vma_add_reservation(struct hstate *h,
-				struct vm_area_struct *vma, unsigned long addr)
 This is a special wrapper routine to help facilitate reservation cleanup
 on error paths.  It is only called from the routine restore_reserve_on_error().
 This routine is used in conjunction with vma_needs_reservation in an attempt
@@ -453,8 +508,10 @@ be done on error paths.
 
 
 Reservation Cleanup in Error Paths
-----------------------------------
-As mentioned in the section "Reservation Map Helper Routines", reservation
+==================================
+
+As mentioned in the section
+:ref:`Reservation Map Helper Routines <resv_map_helpers>`, reservation
 map modifications are performed in two steps.  First vma_needs_reservation
 is called before a page is allocated.  If the allocation is successful,
 then vma_commit_reservation is called.  If not, vma_end_reservation is called.
@@ -494,13 +551,14 @@ so that a reservation will not be leaked when the huge page is freed.
 
 
 Reservations and Memory Policy
-------------------------------
+==============================
 Per-node huge page lists existed in struct hstate when git was first used
 to manage Linux code.  The concept of reservations was added some time later.
 When reservations were added, no attempt was made to take memory policy
 into account.  While cpusets are not exactly the same as memory policy, this
 comment in hugetlb_acct_memory sums up the interaction between reservations
-and cpusets/memory policy.
+and cpusets/memory policy::
+
 	/*
 	 * When cpuset is configured, it breaks the strict hugetlb page
 	 * reservation as the accounting is done on a global variable. Such
@@ -525,5 +583,13 @@ of cpusets or memory policy there is no guarantee that huge pages will be
 available on the required nodes.  This is true even if there are a sufficient
 number of global reservations.
 
+Hugetlbfs regression testing
+============================
+
+The most complete set of hugetlb tests are in the libhugetlbfs repository.
+If you modify any hugetlb related code, use the libhugetlbfs test suite
+to check for regressions.  In addition, if you add any new hugetlb
+functionality, please add appropriate tests to libhugetlbfs.
 
+--
 Mike Kravetz, 7 April 2017
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.rst
index e912d7eee769..09bd24a92784 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.rst
@@ -1,7 +1,14 @@
+.. hwpoison:
+
+========
+hwpoison
+========
+
 What is hwpoison?
+=================
 
 Upcoming Intel CPUs have support for recovering from some memory errors
-(``MCA recovery''). This requires the OS to declare a page "poisoned",
+(``MCA recovery``). This requires the OS to declare a page "poisoned",
 kill the processes associated with it and avoid using it in the future.
 
 This patchkit implements the necessary infrastructure in the VM.
@@ -46,9 +53,10 @@ address. This in theory allows other applications to handle
 memory failures too. The expection is that near all applications
 won't do that, but some very specialized ones might.
 
----
+Failure recovery modes
+======================
 
-There are two (actually three) modi memory failure recovery can be in:
+There are two (actually three) modes memory failure recovery can be in:
 
 vm.memory_failure_recovery sysctl set to zero:
 	All memory failures cause a panic. Do not attempt recovery.
@@ -67,9 +75,8 @@ late kill
 	This is best for memory error unaware applications and default
 	Note some pages are always handled as late kill.
 
----
-
-User control:
+User control
+============
 
 vm.memory_failure_recovery
 	See sysctl.txt
@@ -79,11 +86,19 @@ vm.memory_failure_early_kill
 
 PR_MCE_KILL
 	Set early/late kill mode/revert to system default
-	arg1: PR_MCE_KILL_CLEAR: Revert to system default
-	arg1: PR_MCE_KILL_SET: arg2 defines thread specific mode
-		PR_MCE_KILL_EARLY: Early kill
-		PR_MCE_KILL_LATE:  Late kill
-		PR_MCE_KILL_DEFAULT: Use system global default
+
+	arg1: PR_MCE_KILL_CLEAR:
+		Revert to system default
+	arg1: PR_MCE_KILL_SET:
+		arg2 defines thread specific mode
+
+		PR_MCE_KILL_EARLY:
+			Early kill
+		PR_MCE_KILL_LATE:
+			Late kill
+		PR_MCE_KILL_DEFAULT
+			Use system global default
+
 	Note that if you want to have a dedicated thread which handles
 	the SIGBUS(BUS_MCEERR_AO) on behalf of the process, you should
 	call prctl(PR_MCE_KILL_EARLY) on the designated thread. Otherwise,
@@ -92,77 +107,64 @@ PR_MCE_KILL
 PR_MCE_KILL_GET
 	return current mode
 
+Testing
+=======
 
----
-
-Testing:
-
-madvise(MADV_HWPOISON, ....)
-	(as root)
-	Poison a page in the process for testing
-
+* madvise(MADV_HWPOISON, ....) (as root) - Poison a page in the
+  process for testing
 
-hwpoison-inject module through debugfs
+* hwpoison-inject module through debugfs ``/sys/kernel/debug/hwpoison/``
 
-/sys/kernel/debug/hwpoison/
+  corrupt-pfn
+	Inject hwpoison fault at PFN echoed into this file. This does
+	some early filtering to avoid corrupted unintended pages in test suites.
 
-corrupt-pfn
+  unpoison-pfn
+	Software-unpoison page at PFN echoed into this file. This way
+	a page can be reused again.  This only works for Linux
+	injected failures, not for real memory failures.
 
-Inject hwpoison fault at PFN echoed into this file. This does
-some early filtering to avoid corrupted unintended pages in test suites.
+  Note these injection interfaces are not stable and might change between
+  kernel versions
 
-unpoison-pfn
+  corrupt-filter-dev-major, corrupt-filter-dev-minor
+	Only handle memory failures to pages associated with the file
+	system defined by block device major/minor.  -1U is the
+	wildcard value.  This should be only used for testing with
+	artificial injection.
 
-Software-unpoison page at PFN echoed into this file. This
-way a page can be reused again.
-This only works for Linux injected failures, not for real
-memory failures.
+  corrupt-filter-memcg
+	Limit injection to pages owned by memgroup. Specified by inode
+	number of the memcg.
 
-Note these injection interfaces are not stable and might change between
-kernel versions
+	Example::
 
-corrupt-filter-dev-major
-corrupt-filter-dev-minor
+		mkdir /sys/fs/cgroup/mem/hwpoison
 
-Only handle memory failures to pages associated with the file system defined
-by block device major/minor.  -1U is the wildcard value.
-This should be only used for testing with artificial injection.
+	        usemem -m 100 -s 1000 &
+		echo `jobs -p` > /sys/fs/cgroup/mem/hwpoison/tasks
 
-corrupt-filter-memcg
+		memcg_ino=$(ls -id /sys/fs/cgroup/mem/hwpoison | cut -f1 -d' ')
+		echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg
 
-Limit injection to pages owned by memgroup. Specified by inode number
-of the memcg.
+		page-types -p `pidof init`   --hwpoison  # shall do nothing
+		page-types -p `pidof usemem` --hwpoison  # poison its pages
 
-Example:
-        mkdir /sys/fs/cgroup/mem/hwpoison
+  corrupt-filter-flags-mask, corrupt-filter-flags-value
+	When specified, only poison pages if ((page_flags & mask) ==
+	value).  This allows stress testing of many kinds of
+	pages. The page_flags are the same as in /proc/kpageflags. The
+	flag bits are defined in include/linux/kernel-page-flags.h and
+	documented in Documentation/admin-guide/mm/pagemap.rst
 
-        usemem -m 100 -s 1000 &
-        echo `jobs -p` > /sys/fs/cgroup/mem/hwpoison/tasks
+* Architecture specific MCE injector
 
-        memcg_ino=$(ls -id /sys/fs/cgroup/mem/hwpoison | cut -f1 -d' ')
-        echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg
+  x86 has mce-inject, mce-test
 
-        page-types -p `pidof init`   --hwpoison  # shall do nothing
-        page-types -p `pidof usemem` --hwpoison  # poison its pages
+  Some portable hwpoison test programs in mce-test, see below.
 
-corrupt-filter-flags-mask
-corrupt-filter-flags-value
-
-When specified, only poison pages if ((page_flags & mask) == value).
-This allows stress testing of many kinds of pages. The page_flags
-are the same as in /proc/kpageflags. The flag bits are defined in
-include/linux/kernel-page-flags.h and documented in
-Documentation/vm/pagemap.txt
-
-Architecture specific MCE injector
-
-x86 has mce-inject, mce-test
-
-Some portable hwpoison test programs in mce-test, see blow.
-
----
-
-References:
+References
+==========
 
 http://halobates.de/mce-lc09-2.pdf
 	Overview presentation from LinuxCon 09
@@ -174,14 +176,11 @@ git://git.kernel.org/pub/scm/utils/cpu/mce/mce-inject.git
 	x86 specific injector
 
 
----
-
-Limitations:
-
+Limitations
+===========
 - Not all page types are supported and never will. Most kernel internal
-objects cannot be recovered, only LRU pages for now.
+  objects cannot be recovered, only LRU pages for now.
 - Right now hugepage support is missing.
 
 ---
 Andi Kleen, Oct 2009
-
diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst
new file mode 100644
index 000000000000..c4ded22197ca
--- /dev/null
+++ b/Documentation/vm/index.rst
@@ -0,0 +1,50 @@
+=====================================
+Linux Memory Management Documentation
+=====================================
+
+This is a collection of documents about Linux memory management (mm) subsystem.
+
+User guides for MM features
+===========================
+
+The following documents provide guides for controlling and tuning
+various features of the Linux memory management
+
+.. toctree::
+   :maxdepth: 1
+
+   swap_numa
+   zswap
+
+Kernel developers MM documentation
+==================================
+
+The below documents describe MM internals with different level of
+details ranging from notes and mailing list responses to elaborate
+descriptions of data structures and algorithms.
+
+.. toctree::
+   :maxdepth: 1
+
+   active_mm
+   balance
+   cleancache
+   frontswap
+   highmem
+   hmm
+   hwpoison
+   hugetlbfs_reserv
+   ksm
+   mmu_notifier
+   numa
+   overcommit-accounting
+   page_migration
+   page_frags
+   page_owner
+   remap_file_pages
+   slub
+   split_page_table_lock
+   transhuge
+   unevictable-lru
+   z3fold
+   zsmalloc
diff --git a/Documentation/vm/ksm.rst b/Documentation/vm/ksm.rst
new file mode 100644
index 000000000000..d32016d9be2c
--- /dev/null
+++ b/Documentation/vm/ksm.rst
@@ -0,0 +1,87 @@
+.. _ksm:
+
+=======================
+Kernel Samepage Merging
+=======================
+
+KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
+added to the Linux kernel in 2.6.32.  See ``mm/ksm.c`` for its implementation,
+and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
+
+The userspace interface of KSM is described in :ref:`Documentation/admin-guide/mm/ksm.rst <admin_guide_ksm>`
+
+Design
+======
+
+Overview
+--------
+
+.. kernel-doc:: mm/ksm.c
+   :DOC: Overview
+
+Reverse mapping
+---------------
+KSM maintains reverse mapping information for KSM pages in the stable
+tree.
+
+If a KSM page is shared between less than ``max_page_sharing`` VMAs,
+the node of the stable tree that represents such KSM page points to a
+list of :c:type:`struct rmap_item` and the ``page->mapping`` of the
+KSM page points to the stable tree node.
+
+When the sharing passes this threshold, KSM adds a second dimension to
+the stable tree. The tree node becomes a "chain" that links one or
+more "dups". Each "dup" keeps reverse mapping information for a KSM
+page with ``page->mapping`` pointing to that "dup".
+
+Every "chain" and all "dups" linked into a "chain" enforce the
+invariant that they represent the same write protected memory content,
+even if each "dup" will be pointed by a different KSM page copy of
+that content.
+
+This way the stable tree lookup computational complexity is unaffected
+if compared to an unlimited list of reverse mappings. It is still
+enforced that there cannot be KSM page content duplicates in the
+stable tree itself.
+
+The deduplication limit enforced by ``max_page_sharing`` is required
+to avoid the virtual memory rmap lists to grow too large. The rmap
+walk has O(N) complexity where N is the number of rmap_items
+(i.e. virtual mappings) that are sharing the page, which is in turn
+capped by ``max_page_sharing``. So this effectively spreads the linear
+O(N) computational complexity from rmap walk context over different
+KSM pages. The ksmd walk over the stable_node "chains" is also O(N),
+but N is the number of stable_node "dups", not the number of
+rmap_items, so it has not a significant impact on ksmd performance. In
+practice the best stable_node "dup" candidate will be kept and found
+at the head of the "dups" list.
+
+High values of ``max_page_sharing`` result in faster memory merging
+(because there will be fewer stable_node dups queued into the
+stable_node chain->hlist to check for pruning) and higher
+deduplication factor at the expense of slower worst case for rmap
+walks for any KSM page which can happen during swapping, compaction,
+NUMA balancing and page migration.
+
+The ``stable_node_dups/stable_node_chains`` ratio is also affected by the
+``max_page_sharing`` tunable, and an high ratio may indicate fragmentation
+in the stable_node dups, which could be solved by introducing
+fragmentation algorithms in ksmd which would refile rmap_items from
+one stable_node dup to another stable_node dup, in order to free up
+stable_node "dups" with few rmap_items in them, but that may increase
+the ksmd CPU usage and possibly slowdown the readonly computations on
+the KSM pages of the applications.
+
+The whole list of stable_node "dups" linked in the stable_node
+"chains" is scanned periodically in order to prune stale stable_nodes.
+The frequency of such scans is defined by
+``stable_node_chains_prune_millisecs`` sysfs tunable.
+
+Reference
+---------
+.. kernel-doc:: mm/ksm.c
+   :functions: mm_slot ksm_scan stable_node rmap_item
+
+--
+Izik Eidus,
+Hugh Dickins, 17 Nov 2009
diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt
deleted file mode 100644
index 6686bd267dc9..000000000000
--- a/Documentation/vm/ksm.txt
+++ /dev/null
@@ -1,178 +0,0 @@
-How to use the Kernel Samepage Merging feature
-----------------------------------------------
-
-KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
-added to the Linux kernel in 2.6.32.  See mm/ksm.c for its implementation,
-and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
-
-The KSM daemon ksmd periodically scans those areas of user memory which
-have been registered with it, looking for pages of identical content which
-can be replaced by a single write-protected page (which is automatically
-copied if a process later wants to update its content).
-
-KSM was originally developed for use with KVM (where it was known as
-Kernel Shared Memory), to fit more virtual machines into physical memory,
-by sharing the data common between them.  But it can be useful to any
-application which generates many instances of the same data.
-
-KSM only merges anonymous (private) pages, never pagecache (file) pages.
-KSM's merged pages were originally locked into kernel memory, but can now
-be swapped out just like other user pages (but sharing is broken when they
-are swapped back in: ksmd must rediscover their identity and merge again).
-
-KSM only operates on those areas of address space which an application
-has advised to be likely candidates for merging, by using the madvise(2)
-system call: int madvise(addr, length, MADV_MERGEABLE).
-
-The app may call int madvise(addr, length, MADV_UNMERGEABLE) to cancel
-that advice and restore unshared pages: whereupon KSM unmerges whatever
-it merged in that range.  Note: this unmerging call may suddenly require
-more memory than is available - possibly failing with EAGAIN, but more
-probably arousing the Out-Of-Memory killer.
-
-If KSM is not configured into the running kernel, madvise MADV_MERGEABLE
-and MADV_UNMERGEABLE simply fail with EINVAL.  If the running kernel was
-built with CONFIG_KSM=y, those calls will normally succeed: even if the
-the KSM daemon is not currently running, MADV_MERGEABLE still registers
-the range for whenever the KSM daemon is started; even if the range
-cannot contain any pages which KSM could actually merge; even if
-MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.
-
-If a region of memory must be split into at least one new MADV_MERGEABLE
-or MADV_UNMERGEABLE region, the madvise may return ENOMEM if the process
-will exceed vm.max_map_count (see Documentation/sysctl/vm.txt).
-
-Like other madvise calls, they are intended for use on mapped areas of
-the user address space: they will report ENOMEM if the specified range
-includes unmapped gaps (though working on the intervening mapped areas),
-and might fail with EAGAIN if not enough memory for internal structures.
-
-Applications should be considerate in their use of MADV_MERGEABLE,
-restricting its use to areas likely to benefit.  KSM's scans may use a lot
-of processing power: some installations will disable KSM for that reason.
-
-The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/,
-readable by all but writable only by root:
-
-pages_to_scan    - how many present pages to scan before ksmd goes to sleep
-                   e.g. "echo 100 > /sys/kernel/mm/ksm/pages_to_scan"
-                   Default: 100 (chosen for demonstration purposes)
-
-sleep_millisecs  - how many milliseconds ksmd should sleep before next scan
-                   e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
-                   Default: 20 (chosen for demonstration purposes)
-
-merge_across_nodes - specifies if pages from different numa nodes can be merged.
-                   When set to 0, ksm merges only pages which physically
-                   reside in the memory area of same NUMA node. That brings
-                   lower latency to access of shared pages. Systems with more
-                   nodes, at significant NUMA distances, are likely to benefit
-                   from the lower latency of setting 0. Smaller systems, which
-                   need to minimize memory usage, are likely to benefit from
-                   the greater sharing of setting 1 (default). You may wish to
-                   compare how your system performs under each setting, before
-                   deciding on which to use. merge_across_nodes setting can be
-                   changed only when there are no ksm shared pages in system:
-                   set run 2 to unmerge pages first, then to 1 after changing
-                   merge_across_nodes, to remerge according to the new setting.
-                   Default: 1 (merging across nodes as in earlier releases)
-
-run              - set 0 to stop ksmd from running but keep merged pages,
-                   set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
-                   set 2 to stop ksmd and unmerge all pages currently merged,
-                         but leave mergeable areas registered for next run
-                   Default: 0 (must be changed to 1 to activate KSM,
-                               except if CONFIG_SYSFS is disabled)
-
-use_zero_pages   - specifies whether empty pages (i.e. allocated pages
-                   that only contain zeroes) should be treated specially.
-                   When set to 1, empty pages are merged with the kernel
-                   zero page(s) instead of with each other as it would
-                   happen normally. This can improve the performance on
-                   architectures with coloured zero pages, depending on
-                   the workload. Care should be taken when enabling this
-                   setting, as it can potentially degrade the performance
-                   of KSM for some workloads, for example if the checksums
-                   of pages candidate for merging match the checksum of
-                   an empty page. This setting can be changed at any time,
-                   it is only effective for pages merged after the change.
-                   Default: 0 (normal KSM behaviour as in earlier releases)
-
-max_page_sharing - Maximum sharing allowed for each KSM page. This
-                   enforces a deduplication limit to avoid the virtual
-                   memory rmap lists to grow too large. The minimum
-                   value is 2 as a newly created KSM page will have at
-                   least two sharers. The rmap walk has O(N)
-                   complexity where N is the number of rmap_items
-                   (i.e. virtual mappings) that are sharing the page,
-                   which is in turn capped by max_page_sharing. So
-                   this effectively spread the the linear O(N)
-                   computational complexity from rmap walk context
-                   over different KSM pages. The ksmd walk over the
-                   stable_node "chains" is also O(N), but N is the
-                   number of stable_node "dups", not the number of
-                   rmap_items, so it has not a significant impact on
-                   ksmd performance. In practice the best stable_node
-                   "dup" candidate will be kept and found at the head
-                   of the "dups" list. The higher this value the
-                   faster KSM will merge the memory (because there
-                   will be fewer stable_node dups queued into the
-                   stable_node chain->hlist to check for pruning) and
-                   the higher the deduplication factor will be, but
-                   the slowest the worst case rmap walk could be for
-                   any given KSM page. Slowing down the rmap_walk
-                   means there will be higher latency for certain
-                   virtual memory operations happening during
-                   swapping, compaction, NUMA balancing and page
-                   migration, in turn decreasing responsiveness for
-                   the caller of those virtual memory operations. The
-                   scheduler latency of other tasks not involved with
-                   the VM operations doing the rmap walk is not
-                   affected by this parameter as the rmap walks are
-                   always schedule friendly themselves.
-
-stable_node_chains_prune_millisecs - How frequently to walk the whole
-                   list of stable_node "dups" linked in the
-                   stable_node "chains" in order to prune stale
-                   stable_nodes. Smaller milllisecs values will free
-                   up the KSM metadata with lower latency, but they
-                   will make ksmd use more CPU during the scan. This
-                   only applies to the stable_node chains so it's a
-                   noop if not a single KSM page hit the
-                   max_page_sharing yet (there would be no stable_node
-                   chains in such case).
-
-The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:
-
-pages_shared     - how many shared pages are being used
-pages_sharing    - how many more sites are sharing them i.e. how much saved
-pages_unshared   - how many pages unique but repeatedly checked for merging
-pages_volatile   - how many pages changing too fast to be placed in a tree
-full_scans       - how many times all mergeable areas have been scanned
-
-stable_node_chains - number of stable node chains allocated, this is
-		     effectively the number of KSM pages that hit the
-		     max_page_sharing limit
-stable_node_dups   - number of stable node dups queued into the
-		     stable_node chains
-
-A high ratio of pages_sharing to pages_shared indicates good sharing, but
-a high ratio of pages_unshared to pages_sharing indicates wasted effort.
-pages_volatile embraces several different kinds of activity, but a high
-proportion there would also indicate poor use of madvise MADV_MERGEABLE.
-
-The maximum possible page_sharing/page_shared ratio is limited by the
-max_page_sharing tunable. To increase the ratio max_page_sharing must
-be increased accordingly.
-
-The stable_node_dups/stable_node_chains ratio is also affected by the
-max_page_sharing tunable, and an high ratio may indicate fragmentation
-in the stable_node dups, which could be solved by introducing
-fragmentation algorithms in ksmd which would refile rmap_items from
-one stable_node dup to another stable_node dup, in order to freeup
-stable_node "dups" with few rmap_items in them, but that may increase
-the ksmd CPU usage and possibly slowdown the readonly computations on
-the KSM pages of the applications.
-
-Izik Eidus,
-Hugh Dickins, 17 Nov 2009
diff --git a/Documentation/vm/mmu_notifier.rst b/Documentation/vm/mmu_notifier.rst
new file mode 100644
index 000000000000..47baa1cf28c5
--- /dev/null
+++ b/Documentation/vm/mmu_notifier.rst
@@ -0,0 +1,99 @@
+.. _mmu_notifier:
+
+When do you need to notify inside page table lock ?
+===================================================
+
+When clearing a pte/pmd we are given a choice to notify the event through
+(notify version of \*_clear_flush call mmu_notifier_invalidate_range) under
+the page table lock. But that notification is not necessary in all cases.
+
+For secondary TLB (non CPU TLB) like IOMMU TLB or device TLB (when device use
+thing like ATS/PASID to get the IOMMU to walk the CPU page table to access a
+process virtual address space). There is only 2 cases when you need to notify
+those secondary TLB while holding page table lock when clearing a pte/pmd:
+
+  A) page backing address is free before mmu_notifier_invalidate_range_end()
+  B) a page table entry is updated to point to a new page (COW, write fault
+     on zero page, __replace_page(), ...)
+
+Case A is obvious you do not want to take the risk for the device to write to
+a page that might now be used by some completely different task.
+
+Case B is more subtle. For correctness it requires the following sequence to
+happen:
+
+  - take page table lock
+  - clear page table entry and notify ([pmd/pte]p_huge_clear_flush_notify())
+  - set page table entry to point to new page
+
+If clearing the page table entry is not followed by a notify before setting
+the new pte/pmd value then you can break memory model like C11 or C++11 for
+the device.
+
+Consider the following scenario (device use a feature similar to ATS/PASID):
+
+Two address addrA and addrB such that \|addrA - addrB\| >= PAGE_SIZE we assume
+they are write protected for COW (other case of B apply too).
+
+::
+
+ [Time N] --------------------------------------------------------------------
+ CPU-thread-0  {try to write to addrA}
+ CPU-thread-1  {try to write to addrB}
+ CPU-thread-2  {}
+ CPU-thread-3  {}
+ DEV-thread-0  {read addrA and populate device TLB}
+ DEV-thread-2  {read addrB and populate device TLB}
+ [Time N+1] ------------------------------------------------------------------
+ CPU-thread-0  {COW_step0: {mmu_notifier_invalidate_range_start(addrA)}}
+ CPU-thread-1  {COW_step0: {mmu_notifier_invalidate_range_start(addrB)}}
+ CPU-thread-2  {}
+ CPU-thread-3  {}
+ DEV-thread-0  {}
+ DEV-thread-2  {}
+ [Time N+2] ------------------------------------------------------------------
+ CPU-thread-0  {COW_step1: {update page table to point to new page for addrA}}
+ CPU-thread-1  {COW_step1: {update page table to point to new page for addrB}}
+ CPU-thread-2  {}
+ CPU-thread-3  {}
+ DEV-thread-0  {}
+ DEV-thread-2  {}
+ [Time N+3] ------------------------------------------------------------------
+ CPU-thread-0  {preempted}
+ CPU-thread-1  {preempted}
+ CPU-thread-2  {write to addrA which is a write to new page}
+ CPU-thread-3  {}
+ DEV-thread-0  {}
+ DEV-thread-2  {}
+ [Time N+3] ------------------------------------------------------------------
+ CPU-thread-0  {preempted}
+ CPU-thread-1  {preempted}
+ CPU-thread-2  {}
+ CPU-thread-3  {write to addrB which is a write to new page}
+ DEV-thread-0  {}
+ DEV-thread-2  {}
+ [Time N+4] ------------------------------------------------------------------
+ CPU-thread-0  {preempted}
+ CPU-thread-1  {COW_step3: {mmu_notifier_invalidate_range_end(addrB)}}
+ CPU-thread-2  {}
+ CPU-thread-3  {}
+ DEV-thread-0  {}
+ DEV-thread-2  {}
+ [Time N+5] ------------------------------------------------------------------
+ CPU-thread-0  {preempted}
+ CPU-thread-1  {}
+ CPU-thread-2  {}
+ CPU-thread-3  {}
+ DEV-thread-0  {read addrA from old page}
+ DEV-thread-2  {read addrB from new page}
+
+So here because at time N+2 the clear page table entry was not pair with a
+notification to invalidate the secondary TLB, the device see the new value for
+addrB before seing the new value for addrA. This break total memory ordering
+for the device.
+
+When changing a pte to write protect or to point to a new write protected page
+with same content (KSM) it is fine to delay the mmu_notifier_invalidate_range
+call to mmu_notifier_invalidate_range_end() outside the page table lock. This
+is true even if the thread doing the page table update is preempted right after
+releasing page table lock but before call mmu_notifier_invalidate_range_end().
diff --git a/Documentation/vm/mmu_notifier.txt b/Documentation/vm/mmu_notifier.txt
deleted file mode 100644
index 23b462566bb7..000000000000
--- a/Documentation/vm/mmu_notifier.txt
+++ /dev/null
@@ -1,93 +0,0 @@
-When do you need to notify inside page table lock ?
-
-When clearing a pte/pmd we are given a choice to notify the event through
-(notify version of *_clear_flush call mmu_notifier_invalidate_range) under
-the page table lock. But that notification is not necessary in all cases.
-
-For secondary TLB (non CPU TLB) like IOMMU TLB or device TLB (when device use
-thing like ATS/PASID to get the IOMMU to walk the CPU page table to access a
-process virtual address space). There is only 2 cases when you need to notify
-those secondary TLB while holding page table lock when clearing a pte/pmd:
-
-  A) page backing address is free before mmu_notifier_invalidate_range_end()
-  B) a page table entry is updated to point to a new page (COW, write fault
-     on zero page, __replace_page(), ...)
-
-Case A is obvious you do not want to take the risk for the device to write to
-a page that might now be used by some completely different task.
-
-Case B is more subtle. For correctness it requires the following sequence to
-happen:
-  - take page table lock
-  - clear page table entry and notify ([pmd/pte]p_huge_clear_flush_notify())
-  - set page table entry to point to new page
-
-If clearing the page table entry is not followed by a notify before setting
-the new pte/pmd value then you can break memory model like C11 or C++11 for
-the device.
-
-Consider the following scenario (device use a feature similar to ATS/PASID):
-
-Two address addrA and addrB such that |addrA - addrB| >= PAGE_SIZE we assume
-they are write protected for COW (other case of B apply too).
-
-[Time N] --------------------------------------------------------------------
-CPU-thread-0  {try to write to addrA}
-CPU-thread-1  {try to write to addrB}
-CPU-thread-2  {}
-CPU-thread-3  {}
-DEV-thread-0  {read addrA and populate device TLB}
-DEV-thread-2  {read addrB and populate device TLB}
-[Time N+1] ------------------------------------------------------------------
-CPU-thread-0  {COW_step0: {mmu_notifier_invalidate_range_start(addrA)}}
-CPU-thread-1  {COW_step0: {mmu_notifier_invalidate_range_start(addrB)}}
-CPU-thread-2  {}
-CPU-thread-3  {}
-DEV-thread-0  {}
-DEV-thread-2  {}
-[Time N+2] ------------------------------------------------------------------
-CPU-thread-0  {COW_step1: {update page table to point to new page for addrA}}
-CPU-thread-1  {COW_step1: {update page table to point to new page for addrB}}
-CPU-thread-2  {}
-CPU-thread-3  {}
-DEV-thread-0  {}
-DEV-thread-2  {}
-[Time N+3] ------------------------------------------------------------------
-CPU-thread-0  {preempted}
-CPU-thread-1  {preempted}
-CPU-thread-2  {write to addrA which is a write to new page}
-CPU-thread-3  {}
-DEV-thread-0  {}
-DEV-thread-2  {}
-[Time N+3] ------------------------------------------------------------------
-CPU-thread-0  {preempted}
-CPU-thread-1  {preempted}
-CPU-thread-2  {}
-CPU-thread-3  {write to addrB which is a write to new page}
-DEV-thread-0  {}
-DEV-thread-2  {}
-[Time N+4] ------------------------------------------------------------------
-CPU-thread-0  {preempted}
-CPU-thread-1  {COW_step3: {mmu_notifier_invalidate_range_end(addrB)}}
-CPU-thread-2  {}
-CPU-thread-3  {}
-DEV-thread-0  {}
-DEV-thread-2  {}
-[Time N+5] ------------------------------------------------------------------
-CPU-thread-0  {preempted}
-CPU-thread-1  {}
-CPU-thread-2  {}
-CPU-thread-3  {}
-DEV-thread-0  {read addrA from old page}
-DEV-thread-2  {read addrB from new page}
-
-So here because at time N+2 the clear page table entry was not pair with a
-notification to invalidate the secondary TLB, the device see the new value for
-addrB before seing the new value for addrA. This break total memory ordering
-for the device.
-
-When changing a pte to write protect or to point to a new write protected page
-with same content (KSM) it is fine to delay the mmu_notifier_invalidate_range
-call to mmu_notifier_invalidate_range_end() outside the page table lock. This
-is true even if the thread doing the page table update is preempted right after
-releasing page table lock but before call mmu_notifier_invalidate_range_end().
diff --git a/Documentation/vm/numa b/Documentation/vm/numa.rst
index a31b85b9bb88..185d8a568168 100644
--- a/Documentation/vm/numa
+++ b/Documentation/vm/numa.rst
@@ -1,6 +1,10 @@
+.. _numa:
+
 Started Nov 1999 by Kanoj Sarcar <kanoj@sgi.com>
 
+=============
 What is NUMA?
+=============
 
 This question can be answered from a couple of perspectives:  the
 hardware view and the Linux software view.
@@ -106,7 +110,7 @@ to improve NUMA locality using various CPU affinity command line interfaces,
 such as taskset(1) and numactl(1), and program interfaces such as
 sched_setaffinity(2).  Further, one can modify the kernel's default local
 allocation behavior using Linux NUMA memory policy.
-[see Documentation/vm/numa_memory_policy.txt.]
+[see Documentation/admin-guide/mm/numa_memory_policy.rst.]
 
 System administrators can restrict the CPUs and nodes' memories that a non-
 privileged user can specify in the scheduling or NUMA commands and functions
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
deleted file mode 100644
index 622b927816e7..000000000000
--- a/Documentation/vm/numa_memory_policy.txt
+++ /dev/null
@@ -1,452 +0,0 @@
-
-What is Linux Memory Policy?
-
-In the Linux kernel, "memory policy" determines from which node the kernel will
-allocate memory in a NUMA system or in an emulated NUMA system.  Linux has
-supported platforms with Non-Uniform Memory Access architectures since 2.4.?.
-The current memory policy support was added to Linux 2.6 around May 2004.  This
-document attempts to describe the concepts and APIs of the 2.6 memory policy
-support.
-
-Memory policies should not be confused with cpusets
-(Documentation/cgroup-v1/cpusets.txt)
-which is an administrative mechanism for restricting the nodes from which
-memory may be allocated by a set of processes. Memory policies are a
-programming interface that a NUMA-aware application can take advantage of.  When
-both cpusets and policies are applied to a task, the restrictions of the cpuset
-takes priority.  See "MEMORY POLICIES AND CPUSETS" below for more details.
-
-MEMORY POLICY CONCEPTS
-
-Scope of Memory Policies
-
-The Linux kernel supports _scopes_ of memory policy, described here from
-most general to most specific:
-
-    System Default Policy:  this policy is "hard coded" into the kernel.  It
-    is the policy that governs all page allocations that aren't controlled
-    by one of the more specific policy scopes discussed below.  When the
-    system is "up and running", the system default policy will use "local
-    allocation" described below.  However, during boot up, the system
-    default policy will be set to interleave allocations across all nodes
-    with "sufficient" memory, so as not to overload the initial boot node
-    with boot-time allocations.
-
-    Task/Process Policy:  this is an optional, per-task policy.  When defined
-    for a specific task, this policy controls all page allocations made by or
-    on behalf of the task that aren't controlled by a more specific scope.
-    If a task does not define a task policy, then all page allocations that
-    would have been controlled by the task policy "fall back" to the System
-    Default Policy.
-
-	The task policy applies to the entire address space of a task. Thus,
-	it is inheritable, and indeed is inherited, across both fork()
-	[clone() w/o the CLONE_VM flag] and exec*().  This allows a parent task
-	to establish the task policy for a child task exec()'d from an
-	executable image that has no awareness of memory policy.  See the
-	MEMORY POLICY APIS section, below, for an overview of the system call
-	that a task may use to set/change its task/process policy.
-
-	In a multi-threaded task, task policies apply only to the thread
-	[Linux kernel task] that installs the policy and any threads
-	subsequently created by that thread.  Any sibling threads existing
-	at the time a new task policy is installed retain their current
-	policy.
-
-	A task policy applies only to pages allocated after the policy is
-	installed.  Any pages already faulted in by the task when the task
-	changes its task policy remain where they were allocated based on
-	the policy at the time they were allocated.
-
-    VMA Policy:  A "VMA" or "Virtual Memory Area" refers to a range of a task's
-    virtual address space.  A task may define a specific policy for a range
-    of its virtual address space.   See the MEMORY POLICIES APIS section,
-    below, for an overview of the mbind() system call used to set a VMA
-    policy.
-
-    A VMA policy will govern the allocation of pages that back this region of
-    the address space.  Any regions of the task's address space that don't
-    have an explicit VMA policy will fall back to the task policy, which may
-    itself fall back to the System Default Policy.
-
-    VMA policies have a few complicating details:
-
-	VMA policy applies ONLY to anonymous pages.  These include pages
-	allocated for anonymous segments, such as the task stack and heap, and
-	any regions of the address space mmap()ed with the MAP_ANONYMOUS flag.
-	If a VMA policy is applied to a file mapping, it will be ignored if
-	the mapping used the MAP_SHARED flag.  If the file mapping used the
-	MAP_PRIVATE flag, the VMA policy will only be applied when an
-	anonymous page is allocated on an attempt to write to the mapping--
-	i.e., at Copy-On-Write.
-
-	VMA policies are shared between all tasks that share a virtual address
-	space--a.k.a. threads--independent of when the policy is installed; and
-	they are inherited across fork().  However, because VMA policies refer
-	to a specific region of a task's address space, and because the address
-	space is discarded and recreated on exec*(), VMA policies are NOT
-	inheritable across exec().  Thus, only NUMA-aware applications may
-	use VMA policies.
-
-	A task may install a new VMA policy on a sub-range of a previously
-	mmap()ed region.  When this happens, Linux splits the existing virtual
-	memory area into 2 or 3 VMAs, each with it's own policy.
-
-	By default, VMA policy applies only to pages allocated after the policy
-	is installed.  Any pages already faulted into the VMA range remain
-	where they were allocated based on the policy at the time they were
-	allocated.  However, since 2.6.16, Linux supports page migration via
-	the mbind() system call, so that page contents can be moved to match
-	a newly installed policy.
-
-    Shared Policy:  Conceptually, shared policies apply to "memory objects"
-    mapped shared into one or more tasks' distinct address spaces.  An
-    application installs a shared policies the same way as VMA policies--using
-    the mbind() system call specifying a range of virtual addresses that map
-    the shared object.  However, unlike VMA policies, which can be considered
-    to be an attribute of a range of a task's address space, shared policies
-    apply directly to the shared object.  Thus, all tasks that attach to the
-    object share the policy, and all pages allocated for the shared object,
-    by any task, will obey the shared policy.
-
-	As of 2.6.22, only shared memory segments, created by shmget() or
-	mmap(MAP_ANONYMOUS|MAP_SHARED), support shared policy.  When shared
-	policy support was added to Linux, the associated data structures were
-	added to hugetlbfs shmem segments.  At the time, hugetlbfs did not
-	support allocation at fault time--a.k.a lazy allocation--so hugetlbfs
-	shmem segments were never "hooked up" to the shared policy support.
-	Although hugetlbfs segments now support lazy allocation, their support
-	for shared policy has not been completed.
-
-	As mentioned above [re: VMA policies], allocations of page cache
-	pages for regular files mmap()ed with MAP_SHARED ignore any VMA
-	policy installed on the virtual address range backed by the shared
-	file mapping.  Rather, shared page cache pages, including pages backing
-	private mappings that have not yet been written by the task, follow
-	task policy, if any, else System Default Policy.
-
-	The shared policy infrastructure supports different policies on subset
-	ranges of the shared object.  However, Linux still splits the VMA of
-	the task that installs the policy for each range of distinct policy.
-	Thus, different tasks that attach to a shared memory segment can have
-	different VMA configurations mapping that one shared object.  This
-	can be seen by examining the /proc/<pid>/numa_maps of tasks sharing
-	a shared memory region, when one task has installed shared policy on
-	one or more ranges of the region.
-
-Components of Memory Policies
-
-    A Linux memory policy consists of a "mode", optional mode flags, and an
-    optional set of nodes.  The mode determines the behavior of the policy,
-    the optional mode flags determine the behavior of the mode, and the
-    optional set of nodes can be viewed as the arguments to the policy
-    behavior.
-
-   Internally, memory policies are implemented by a reference counted
-   structure, struct mempolicy.  Details of this structure will be discussed
-   in context, below, as required to explain the behavior.
-
-   Linux memory policy supports the following 4 behavioral modes:
-
-	Default Mode--MPOL_DEFAULT:  This mode is only used in the memory
-	policy APIs.  Internally, MPOL_DEFAULT is converted to the NULL
-	memory policy in all policy scopes.  Any existing non-default policy
-	will simply be removed when MPOL_DEFAULT is specified.  As a result,
-	MPOL_DEFAULT means "fall back to the next most specific policy scope."
-
-	    For example, a NULL or default task policy will fall back to the
-	    system default policy.  A NULL or default vma policy will fall
-	    back to the task policy.
-
-	    When specified in one of the memory policy APIs, the Default mode
-	    does not use the optional set of nodes.
-
-	    It is an error for the set of nodes specified for this policy to
-	    be non-empty.
-
-	MPOL_BIND:  This mode specifies that memory must come from the
-	set of nodes specified by the policy.  Memory will be allocated from
-	the node in the set with sufficient free memory that is closest to
-	the node where the allocation takes place.
-
-	MPOL_PREFERRED:  This mode specifies that the allocation should be
-	attempted from the single node specified in the policy.  If that
-	allocation fails, the kernel will search other nodes, in order of
-	increasing distance from the preferred node based on information
-	provided by the platform firmware.
-
-	    Internally, the Preferred policy uses a single node--the
-	    preferred_node member of struct mempolicy.  When the internal
-	    mode flag MPOL_F_LOCAL is set, the preferred_node is ignored and
-	    the policy is interpreted as local allocation.  "Local" allocation
-	    policy can be viewed as a Preferred policy that starts at the node
-	    containing the cpu where the allocation takes place.
-
-	    It is possible for the user to specify that local allocation is
-	    always preferred by passing an empty nodemask with this mode.
-	    If an empty nodemask is passed, the policy cannot use the
-	    MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags described
-	    below.
-
-	MPOL_INTERLEAVED:  This mode specifies that page allocations be
-	interleaved, on a page granularity, across the nodes specified in
-	the policy.  This mode also behaves slightly differently, based on
-	the context where it is used:
-
-	    For allocation of anonymous pages and shared memory pages,
-	    Interleave mode indexes the set of nodes specified by the policy
-	    using the page offset of the faulting address into the segment
-	    [VMA] containing the address modulo the number of nodes specified
-	    by the policy.  It then attempts to allocate a page, starting at
-	    the selected node, as if the node had been specified by a Preferred
-	    policy or had been selected by a local allocation.  That is,
-	    allocation will follow the per node zonelist.
-
-	    For allocation of page cache pages, Interleave mode indexes the set
-	    of nodes specified by the policy using a node counter maintained
-	    per task.  This counter wraps around to the lowest specified node
-	    after it reaches the highest specified node.  This will tend to
-	    spread the pages out over the nodes specified by the policy based
-	    on the order in which they are allocated, rather than based on any
-	    page offset into an address range or file.  During system boot up,
-	    the temporary interleaved system default policy works in this
-	    mode.
-
-   Linux memory policy supports the following optional mode flags:
-
-	MPOL_F_STATIC_NODES:  This flag specifies that the nodemask passed by
-	the user should not be remapped if the task or VMA's set of allowed
-	nodes changes after the memory policy has been defined.
-
-	    Without this flag, anytime a mempolicy is rebound because of a
-	    change in the set of allowed nodes, the node (Preferred) or
-	    nodemask (Bind, Interleave) is remapped to the new set of
-	    allowed nodes.  This may result in nodes being used that were
-	    previously undesired.
-
-	    With this flag, if the user-specified nodes overlap with the
-	    nodes allowed by the task's cpuset, then the memory policy is
-	    applied to their intersection.  If the two sets of nodes do not
-	    overlap, the Default policy is used.
-
-	    For example, consider a task that is attached to a cpuset with
-	    mems 1-3 that sets an Interleave policy over the same set.  If
-	    the cpuset's mems change to 3-5, the Interleave will now occur
-	    over nodes 3, 4, and 5.  With this flag, however, since only node
-	    3 is allowed from the user's nodemask, the "interleave" only
-	    occurs over that node.  If no nodes from the user's nodemask are
-	    now allowed, the Default behavior is used.
-
-	    MPOL_F_STATIC_NODES cannot be combined with the
-	    MPOL_F_RELATIVE_NODES flag.  It also cannot be used for
-	    MPOL_PREFERRED policies that were created with an empty nodemask
-	    (local allocation).
-
-	MPOL_F_RELATIVE_NODES:  This flag specifies that the nodemask passed
-	by the user will be mapped relative to the set of the task or VMA's
-	set of allowed nodes.  The kernel stores the user-passed nodemask,
-	and if the allowed nodes changes, then that original nodemask will
-	be remapped relative to the new set of allowed nodes.
-
-	    Without this flag (and without MPOL_F_STATIC_NODES), anytime a
-	    mempolicy is rebound because of a change in the set of allowed
-	    nodes, the node (Preferred) or nodemask (Bind, Interleave) is
-	    remapped to the new set of allowed nodes.  That remap may not
-	    preserve the relative nature of the user's passed nodemask to its
-	    set of allowed nodes upon successive rebinds: a nodemask of
-	    1,3,5 may be remapped to 7-9 and then to 1-3 if the set of
-	    allowed nodes is restored to its original state.
-
-	    With this flag, the remap is done so that the node numbers from
-	    the user's passed nodemask are relative to the set of allowed
-	    nodes.  In other words, if nodes 0, 2, and 4 are set in the user's
-	    nodemask, the policy will be effected over the first (and in the
-	    Bind or Interleave case, the third and fifth) nodes in the set of
-	    allowed nodes.  The nodemask passed by the user represents nodes
-	    relative to task or VMA's set of allowed nodes.
-
-	    If the user's nodemask includes nodes that are outside the range
-	    of the new set of allowed nodes (for example, node 5 is set in
-	    the user's nodemask when the set of allowed nodes is only 0-3),
-	    then the remap wraps around to the beginning of the nodemask and,
-	    if not already set, sets the node in the mempolicy nodemask.
-
-	    For example, consider a task that is attached to a cpuset with
-	    mems 2-5 that sets an Interleave policy over the same set with
-	    MPOL_F_RELATIVE_NODES.  If the cpuset's mems change to 3-7, the
-	    interleave now occurs over nodes 3,5-7.  If the cpuset's mems
-	    then change to 0,2-3,5, then the interleave occurs over nodes
-	    0,2-3,5.
-
-	    Thanks to the consistent remapping, applications preparing
-	    nodemasks to specify memory policies using this flag should
-	    disregard their current, actual cpuset imposed memory placement
-	    and prepare the nodemask as if they were always located on
-	    memory nodes 0 to N-1, where N is the number of memory nodes the
-	    policy is intended to manage.  Let the kernel then remap to the
-	    set of memory nodes allowed by the task's cpuset, as that may
-	    change over time.
-
-	    MPOL_F_RELATIVE_NODES cannot be combined with the
-	    MPOL_F_STATIC_NODES flag.  It also cannot be used for
-	    MPOL_PREFERRED policies that were created with an empty nodemask
-	    (local allocation).
-
-MEMORY POLICY REFERENCE COUNTING
-
-To resolve use/free races, struct mempolicy contains an atomic reference
-count field.  Internal interfaces, mpol_get()/mpol_put() increment and
-decrement this reference count, respectively.  mpol_put() will only free
-the structure back to the mempolicy kmem cache when the reference count
-goes to zero.
-
-When a new memory policy is allocated, its reference count is initialized
-to '1', representing the reference held by the task that is installing the
-new policy.  When a pointer to a memory policy structure is stored in another
-structure, another reference is added, as the task's reference will be dropped
-on completion of the policy installation.
-
-During run-time "usage" of the policy, we attempt to minimize atomic operations
-on the reference count, as this can lead to cache lines bouncing between cpus
-and NUMA nodes.  "Usage" here means one of the following:
-
-1) querying of the policy, either by the task itself [using the get_mempolicy()
-   API discussed below] or by another task using the /proc/<pid>/numa_maps
-   interface.
-
-2) examination of the policy to determine the policy mode and associated node
-   or node lists, if any, for page allocation.  This is considered a "hot
-   path".  Note that for MPOL_BIND, the "usage" extends across the entire
-   allocation process, which may sleep during page reclaimation, because the
-   BIND policy nodemask is used, by reference, to filter ineligible nodes.
-
-We can avoid taking an extra reference during the usages listed above as
-follows:
-
-1) we never need to get/free the system default policy as this is never
-   changed nor freed, once the system is up and running.
-
-2) for querying the policy, we do not need to take an extra reference on the
-   target task's task policy nor vma policies because we always acquire the
-   task's mm's mmap_sem for read during the query.  The set_mempolicy() and
-   mbind() APIs [see below] always acquire the mmap_sem for write when
-   installing or replacing task or vma policies.  Thus, there is no possibility
-   of a task or thread freeing a policy while another task or thread is
-   querying it.
-
-3) Page allocation usage of task or vma policy occurs in the fault path where
-   we hold them mmap_sem for read.  Again, because replacing the task or vma
-   policy requires that the mmap_sem be held for write, the policy can't be
-   freed out from under us while we're using it for page allocation.
-
-4) Shared policies require special consideration.  One task can replace a
-   shared memory policy while another task, with a distinct mmap_sem, is
-   querying or allocating a page based on the policy.  To resolve this
-   potential race, the shared policy infrastructure adds an extra reference
-   to the shared policy during lookup while holding a spin lock on the shared
-   policy management structure.  This requires that we drop this extra
-   reference when we're finished "using" the policy.  We must drop the
-   extra reference on shared policies in the same query/allocation paths
-   used for non-shared policies.  For this reason, shared policies are marked
-   as such, and the extra reference is dropped "conditionally"--i.e., only
-   for shared policies.
-
-   Because of this extra reference counting, and because we must lookup
-   shared policies in a tree structure under spinlock, shared policies are
-   more expensive to use in the page allocation path.  This is especially
-   true for shared policies on shared memory regions shared by tasks running
-   on different NUMA nodes.  This extra overhead can be avoided by always
-   falling back to task or system default policy for shared memory regions,
-   or by prefaulting the entire shared memory region into memory and locking
-   it down.  However, this might not be appropriate for all applications.
-
-MEMORY POLICY APIs
-
-Linux supports 3 system calls for controlling memory policy.  These APIS
-always affect only the calling task, the calling task's address space, or
-some shared object mapped into the calling task's address space.
-
-	Note:  the headers that define these APIs and the parameter data types
-	for user space applications reside in a package that is not part of
-	the Linux kernel.  The kernel system call interfaces, with the 'sys_'
-	prefix, are defined in <linux/syscalls.h>; the mode and flag
-	definitions are defined in <linux/mempolicy.h>.
-
-Set [Task] Memory Policy:
-
-	long set_mempolicy(int mode, const unsigned long *nmask,
-					unsigned long maxnode);
-
-	Set's the calling task's "task/process memory policy" to mode
-	specified by the 'mode' argument and the set of nodes defined
-	by 'nmask'.  'nmask' points to a bit mask of node ids containing
-	at least 'maxnode' ids.  Optional mode flags may be passed by
-	combining the 'mode' argument with the flag (for example:
-	MPOL_INTERLEAVE | MPOL_F_STATIC_NODES).
-
-	See the set_mempolicy(2) man page for more details
-
-
-Get [Task] Memory Policy or Related Information
-
-	long get_mempolicy(int *mode,
-			   const unsigned long *nmask, unsigned long maxnode,
-			   void *addr, int flags);
-
-	Queries the "task/process memory policy" of the calling task, or
-	the policy or location of a specified virtual address, depending
-	on the 'flags' argument.
-
-	See the get_mempolicy(2) man page for more details
-
-
-Install VMA/Shared Policy for a Range of Task's Address Space
-
-	long mbind(void *start, unsigned long len, int mode,
-		   const unsigned long *nmask, unsigned long maxnode,
-		   unsigned flags);
-
-	mbind() installs the policy specified by (mode, nmask, maxnodes) as
-	a VMA policy for the range of the calling task's address space
-	specified by the 'start' and 'len' arguments.  Additional actions
-	may be requested via the 'flags' argument.
-
-	See the mbind(2) man page for more details.
-
-MEMORY POLICY COMMAND LINE INTERFACE
-
-Although not strictly part of the Linux implementation of memory policy,
-a command line tool, numactl(8), exists that allows one to:
-
-+ set the task policy for a specified program via set_mempolicy(2), fork(2) and
-  exec(2)
-
-+ set the shared policy for a shared memory segment via mbind(2)
-
-The numactl(8) tool is packaged with the run-time version of the library
-containing the memory policy system call wrappers.  Some distributions
-package the headers and compile-time libraries in a separate development
-package.
-
-
-MEMORY POLICIES AND CPUSETS
-
-Memory policies work within cpusets as described above.  For memory policies
-that require a node or set of nodes, the nodes are restricted to the set of
-nodes whose memories are allowed by the cpuset constraints.  If the nodemask
-specified for the policy contains nodes that are not allowed by the cpuset and
-MPOL_F_RELATIVE_NODES is not used, the intersection of the set of nodes
-specified for the policy and the set of nodes with memory is used.  If the
-result is the empty set, the policy is considered invalid and cannot be
-installed.  If MPOL_F_RELATIVE_NODES is used, the policy's nodes are mapped
-onto and folded into the task's set of allowed nodes as previously described.
-
-The interaction of memory policies and cpusets can be problematic when tasks
-in two cpusets share access to a memory region, such as shared memory segments
-created by shmget() of mmap() with the MAP_ANONYMOUS and MAP_SHARED flags, and
-any of the tasks install shared policy on the region, only nodes whose
-memories are allowed in both cpusets may be used in the policies.  Obtaining
-this information requires "stepping outside" the memory policy APIs to use the
-cpuset information and requires that one know in what cpusets other task might
-be attaching to the shared region.  Furthermore, if the cpusets' allowed
-memory sets are disjoint, "local" allocation is the only valid policy.
diff --git a/Documentation/vm/overcommit-accounting b/Documentation/vm/overcommit-accounting
deleted file mode 100644
index cbfaaa674118..000000000000
--- a/Documentation/vm/overcommit-accounting
+++ /dev/null
@@ -1,80 +0,0 @@
-The Linux kernel supports the following overcommit handling modes
-
-0	-	Heuristic overcommit handling. Obvious overcommits of
-		address space are refused. Used for a typical system. It
-		ensures a seriously wild allocation fails while allowing
-		overcommit to reduce swap usage.  root is allowed to 
-		allocate slightly more memory in this mode. This is the 
-		default.
-
-1	-	Always overcommit. Appropriate for some scientific
-		applications. Classic example is code using sparse arrays
-		and just relying on the virtual memory consisting almost
-		entirely of zero pages.
-
-2	-	Don't overcommit. The total address space commit
-		for the system is not permitted to exceed swap + a
-		configurable amount (default is 50%) of physical RAM.
-		Depending on the amount you use, in most situations
-		this means a process will not be killed while accessing
-		pages but will receive errors on memory allocation as
-		appropriate.
-
-		Useful for applications that want to guarantee their
-		memory allocations will be available in the future
-		without having to initialize every page.
-
-The overcommit policy is set via the sysctl `vm.overcommit_memory'.
-
-The overcommit amount can be set via `vm.overcommit_ratio' (percentage)
-or `vm.overcommit_kbytes' (absolute value).
-
-The current overcommit limit and amount committed are viewable in
-/proc/meminfo as CommitLimit and Committed_AS respectively.
-
-Gotchas
--------
-
-The C language stack growth does an implicit mremap. If you want absolute
-guarantees and run close to the edge you MUST mmap your stack for the 
-largest size you think you will need. For typical stack usage this does
-not matter much but it's a corner case if you really really care
-
-In mode 2 the MAP_NORESERVE flag is ignored. 
-
-
-How It Works
-------------
-
-The overcommit is based on the following rules
-
-For a file backed map
-	SHARED or READ-only	-	0 cost (the file is the map not swap)
-	PRIVATE WRITABLE	-	size of mapping per instance
-
-For an anonymous or /dev/zero map
-	SHARED			-	size of mapping
-	PRIVATE READ-only	-	0 cost (but of little use)
-	PRIVATE WRITABLE	-	size of mapping per instance
-
-Additional accounting
-	Pages made writable copies by mmap
-	shmfs memory drawn from the same pool
-
-Status
-------
-
-o	We account mmap memory mappings
-o	We account mprotect changes in commit
-o	We account mremap changes in size
-o	We account brk
-o	We account munmap
-o	We report the commit status in /proc
-o	Account and check on fork
-o	Review stack handling/building on exec
-o	SHMfs accounting
-o	Implement actual limit enforcement
-
-To Do
------
-o	Account ptrace pages (this is hard)
diff --git a/Documentation/vm/overcommit-accounting.rst b/Documentation/vm/overcommit-accounting.rst
new file mode 100644
index 000000000000..0dd54bbe4afa
--- /dev/null
+++ b/Documentation/vm/overcommit-accounting.rst
@@ -0,0 +1,87 @@
+.. _overcommit_accounting:
+
+=====================
+Overcommit Accounting
+=====================
+
+The Linux kernel supports the following overcommit handling modes
+
+0
+	Heuristic overcommit handling. Obvious overcommits of address
+	space are refused. Used for a typical system. It ensures a
+	seriously wild allocation fails while allowing overcommit to
+	reduce swap usage.  root is allowed to allocate slightly more
+	memory in this mode. This is the default.
+
+1
+	Always overcommit. Appropriate for some scientific
+	applications. Classic example is code using sparse arrays and
+	just relying on the virtual memory consisting almost entirely
+	of zero pages.
+
+2
+	Don't overcommit. The total address space commit for the
+	system is not permitted to exceed swap + a configurable amount
+	(default is 50%) of physical RAM.  Depending on the amount you
+	use, in most situations this means a process will not be
+	killed while accessing pages but will receive errors on memory
+	allocation as appropriate.
+
+	Useful for applications that want to guarantee their memory
+	allocations will be available in the future without having to
+	initialize every page.
+
+The overcommit policy is set via the sysctl ``vm.overcommit_memory``.
+
+The overcommit amount can be set via ``vm.overcommit_ratio`` (percentage)
+or ``vm.overcommit_kbytes`` (absolute value).
+
+The current overcommit limit and amount committed are viewable in
+``/proc/meminfo`` as CommitLimit and Committed_AS respectively.
+
+Gotchas
+=======
+
+The C language stack growth does an implicit mremap. If you want absolute
+guarantees and run close to the edge you MUST mmap your stack for the
+largest size you think you will need. For typical stack usage this does
+not matter much but it's a corner case if you really really care
+
+In mode 2 the MAP_NORESERVE flag is ignored.
+
+
+How It Works
+============
+
+The overcommit is based on the following rules
+
+For a file backed map
+	| SHARED or READ-only	-	0 cost (the file is the map not swap)
+	| PRIVATE WRITABLE	-	size of mapping per instance
+
+For an anonymous or ``/dev/zero`` map
+	| SHARED			-	size of mapping
+	| PRIVATE READ-only	-	0 cost (but of little use)
+	| PRIVATE WRITABLE	-	size of mapping per instance
+
+Additional accounting
+	| Pages made writable copies by mmap
+	| shmfs memory drawn from the same pool
+
+Status
+======
+
+*	We account mmap memory mappings
+*	We account mprotect changes in commit
+*	We account mremap changes in size
+*	We account brk
+*	We account munmap
+*	We report the commit status in /proc
+*	Account and check on fork
+*	Review stack handling/building on exec
+*	SHMfs accounting
+*	Implement actual limit enforcement
+
+To Do
+=====
+*	Account ptrace pages (this is hard)
diff --git a/Documentation/vm/page_frags b/Documentation/vm/page_frags.rst
index a6714565dbf9..637cc49d1b2f 100644
--- a/Documentation/vm/page_frags
+++ b/Documentation/vm/page_frags.rst
@@ -1,5 +1,8 @@
+.. _page_frags:
+
+==============
 Page fragments
---------------
+==============
 
 A page fragment is an arbitrary-length arbitrary-offset area of memory
 which resides within a 0 or higher order compound page.  Multiple
diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration.rst
index 496868072e24..f68d61335abb 100644
--- a/Documentation/vm/page_migration
+++ b/Documentation/vm/page_migration.rst
@@ -1,5 +1,8 @@
+.. _page_migration:
+
+==============
 Page migration
---------------
+==============
 
 Page migration allows the moving of the physical location of pages between
 nodes in a numa system while the process is running. This means that the
@@ -20,7 +23,7 @@ Page migration functions are provided by the numactl package by Andi Kleen
 (a version later than 0.9.3 is required. Get it from
 ftp://oss.sgi.com/www/projects/libnuma/download/). numactl provides libnuma
 which provides an interface similar to other numa functionality for page
-migration.  cat /proc/<pid>/numa_maps allows an easy review of where the
+migration.  cat ``/proc/<pid>/numa_maps`` allows an easy review of where the
 pages of a process are located. See also the numa_maps documentation in the
 proc(5) man page.
 
@@ -56,8 +59,8 @@ description for those trying to use migrate_pages() from the kernel
 (for userspace usage see the Andi Kleen's numactl package mentioned above)
 and then a low level description of how the low level details work.
 
-A. In kernel use of migrate_pages()
------------------------------------
+In kernel use of migrate_pages()
+================================
 
 1. Remove pages from the LRU.
 
@@ -78,8 +81,8 @@ A. In kernel use of migrate_pages()
    the new page for each page that is considered for
    moving.
 
-B. How migrate_pages() works
-----------------------------
+How migrate_pages() works
+=========================
 
 migrate_pages() does several passes over its list of pages. A page is moved
 if all references to a page are removable at the time. The page has
@@ -142,8 +145,8 @@ Steps:
 20. The new page is moved to the LRU and can be scanned by the swapper
     etc again.
 
-C. Non-LRU page migration
--------------------------
+Non-LRU page migration
+======================
 
 Although original migration aimed for reducing the latency of memory access
 for NUMA, compaction who want to create high-order page is also main customer.
@@ -164,89 +167,91 @@ migration path.
 If a driver want to make own pages movable, it should define three functions
 which are function pointers of struct address_space_operations.
 
-1. bool (*isolate_page) (struct page *page, isolate_mode_t mode);
+1. ``bool (*isolate_page) (struct page *page, isolate_mode_t mode);``
 
-What VM expects on isolate_page function of driver is to return *true*
-if driver isolates page successfully. On returing true, VM marks the page
-as PG_isolated so concurrent isolation in several CPUs skip the page
-for isolation. If a driver cannot isolate the page, it should return *false*.
+   What VM expects on isolate_page function of driver is to return *true*
+   if driver isolates page successfully. On returing true, VM marks the page
+   as PG_isolated so concurrent isolation in several CPUs skip the page
+   for isolation. If a driver cannot isolate the page, it should return *false*.
 
-Once page is successfully isolated, VM uses page.lru fields so driver
-shouldn't expect to preserve values in that fields.
+   Once page is successfully isolated, VM uses page.lru fields so driver
+   shouldn't expect to preserve values in that fields.
 
-2. int (*migratepage) (struct address_space *mapping,
-		struct page *newpage, struct page *oldpage, enum migrate_mode);
+2. ``int (*migratepage) (struct address_space *mapping,``
+|	``struct page *newpage, struct page *oldpage, enum migrate_mode);``
 
-After isolation, VM calls migratepage of driver with isolated page.
-The function of migratepage is to move content of the old page to new page
-and set up fields of struct page newpage. Keep in mind that you should
-indicate to the VM the oldpage is no longer movable via __ClearPageMovable()
-under page_lock if you migrated the oldpage successfully and returns
-MIGRATEPAGE_SUCCESS. If driver cannot migrate the page at the moment, driver
-can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time
-because VM interprets -EAGAIN as "temporal migration failure". On returning
-any error except -EAGAIN, VM will give up the page migration without retrying
-in this time.
+   After isolation, VM calls migratepage of driver with isolated page.
+   The function of migratepage is to move content of the old page to new page
+   and set up fields of struct page newpage. Keep in mind that you should
+   indicate to the VM the oldpage is no longer movable via __ClearPageMovable()
+   under page_lock if you migrated the oldpage successfully and returns
+   MIGRATEPAGE_SUCCESS. If driver cannot migrate the page at the moment, driver
+   can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time
+   because VM interprets -EAGAIN as "temporal migration failure". On returning
+   any error except -EAGAIN, VM will give up the page migration without retrying
+   in this time.
 
-Driver shouldn't touch page.lru field VM using in the functions.
+   Driver shouldn't touch page.lru field VM using in the functions.
 
-3. void (*putback_page)(struct page *);
+3. ``void (*putback_page)(struct page *);``
 
-If migration fails on isolated page, VM should return the isolated page
-to the driver so VM calls driver's putback_page with migration failed page.
-In this function, driver should put the isolated page back to the own data
-structure.
+   If migration fails on isolated page, VM should return the isolated page
+   to the driver so VM calls driver's putback_page with migration failed page.
+   In this function, driver should put the isolated page back to the own data
+   structure.
 
 4. non-lru movable page flags
 
-There are two page flags for supporting non-lru movable page.
+   There are two page flags for supporting non-lru movable page.
 
-* PG_movable
+   * PG_movable
 
-Driver should use the below function to make page movable under page_lock.
+     Driver should use the below function to make page movable under page_lock::
 
 	void __SetPageMovable(struct page *page, struct address_space *mapping)
 
-It needs argument of address_space for registering migration family functions
-which will be called by VM. Exactly speaking, PG_movable is not a real flag of
-struct page. Rather than, VM reuses page->mapping's lower bits to represent it.
+     It needs argument of address_space for registering migration
+     family functions which will be called by VM. Exactly speaking,
+     PG_movable is not a real flag of struct page. Rather than, VM
+     reuses page->mapping's lower bits to represent it.
 
+::
 	#define PAGE_MAPPING_MOVABLE 0x2
 	page->mapping = page->mapping | PAGE_MAPPING_MOVABLE;
 
-so driver shouldn't access page->mapping directly. Instead, driver should
-use page_mapping which mask off the low two bits of page->mapping under
-page lock so it can get right struct address_space.
-
-For testing of non-lru movable page, VM supports __PageMovable function.
-However, it doesn't guarantee to identify non-lru movable page because
-page->mapping field is unified with other variables in struct page.
-As well, if driver releases the page after isolation by VM, page->mapping
-doesn't have stable value although it has PAGE_MAPPING_MOVABLE
-(Look at __ClearPageMovable). But __PageMovable is cheap to catch whether
-page is LRU or non-lru movable once the page has been isolated. Because
-LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also
-good for just peeking to test non-lru movable pages before more expensive
-checking with lock_page in pfn scanning to select victim.
-
-For guaranteeing non-lru movable page, VM provides PageMovable function.
-Unlike __PageMovable, PageMovable functions validates page->mapping and
-mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden
-destroying of page->mapping.
-
-Driver using __SetPageMovable should clear the flag via __ClearMovablePage
-under page_lock before the releasing the page.
-
-* PG_isolated
-
-To prevent concurrent isolation among several CPUs, VM marks isolated page
-as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru
-movable page, it can skip it. Driver doesn't need to manipulate the flag
-because VM will set/clear it automatically. Keep in mind that if driver
-sees PG_isolated page, it means the page have been isolated by VM so it
-shouldn't touch page.lru field.
-PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag
-for own purpose.
+     so driver shouldn't access page->mapping directly. Instead, driver should
+     use page_mapping which mask off the low two bits of page->mapping under
+     page lock so it can get right struct address_space.
+
+     For testing of non-lru movable page, VM supports __PageMovable function.
+     However, it doesn't guarantee to identify non-lru movable page because
+     page->mapping field is unified with other variables in struct page.
+     As well, if driver releases the page after isolation by VM, page->mapping
+     doesn't have stable value although it has PAGE_MAPPING_MOVABLE
+     (Look at __ClearPageMovable). But __PageMovable is cheap to catch whether
+     page is LRU or non-lru movable once the page has been isolated. Because
+     LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also
+     good for just peeking to test non-lru movable pages before more expensive
+     checking with lock_page in pfn scanning to select victim.
+
+     For guaranteeing non-lru movable page, VM provides PageMovable function.
+     Unlike __PageMovable, PageMovable functions validates page->mapping and
+     mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden
+     destroying of page->mapping.
+
+     Driver using __SetPageMovable should clear the flag via __ClearMovablePage
+     under page_lock before the releasing the page.
+
+   * PG_isolated
+
+     To prevent concurrent isolation among several CPUs, VM marks isolated page
+     as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru
+     movable page, it can skip it. Driver doesn't need to manipulate the flag
+     because VM will set/clear it automatically. Keep in mind that if driver
+     sees PG_isolated page, it means the page have been isolated by VM so it
+     shouldn't touch page.lru field.
+     PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag
+     for own purpose.
 
 Christoph Lameter, May 8, 2006.
 Minchan Kim, Mar 28, 2016.
diff --git a/Documentation/vm/page_owner.txt b/Documentation/vm/page_owner.rst
index ffff1439076a..0ed5ab8c7ab4 100644
--- a/Documentation/vm/page_owner.txt
+++ b/Documentation/vm/page_owner.rst
@@ -1,7 +1,11 @@
+.. _page_owner:
+
+==================================================
 page owner: Tracking about who allocated each page
------------------------------------------------------------
+==================================================
 
-* Introduction
+Introduction
+============
 
 page owner is for the tracking about who allocated each page.
 It can be used to debug memory leak or to find a memory hogger.
@@ -34,13 +38,15 @@ not affect to allocation performance, especially if the static keys jump
 label patching functionality is available. Following is the kernel's code
 size change due to this facility.
 
-- Without page owner
+- Without page owner::
+
    text    data     bss     dec     hex filename
-  40662    1493     644   42799    a72f mm/page_alloc.o
+   40662   1493     644   42799    a72f mm/page_alloc.o
+
+- With page owner::
 
-- With page owner
    text    data     bss     dec     hex filename
-  40892    1493     644   43029    a815 mm/page_alloc.o
+   40892   1493     644   43029    a815 mm/page_alloc.o
    1427      24       8    1459     5b3 mm/page_ext.o
    2722      50       0    2772     ad4 mm/page_owner.o
 
@@ -62,21 +68,23 @@ are catched and marked, although they are mostly allocated from struct
 page extension feature. Anyway, after that, no page is left in
 un-tracking state.
 
-* Usage
+Usage
+=====
+
+1) Build user-space helper::
 
-1) Build user-space helper
 	cd tools/vm
 	make page_owner_sort
 
-2) Enable page owner
-	Add "page_owner=on" to boot cmdline.
+2) Enable page owner: add "page_owner=on" to boot cmdline.
 
 3) Do the job what you want to debug
 
-4) Analyze information from page owner
+4) Analyze information from page owner::
+
 	cat /sys/kernel/debug/page_owner > page_owner_full.txt
 	grep -v ^PFN page_owner_full.txt > page_owner.txt
 	./page_owner_sort page_owner.txt sorted_page_owner.txt
 
-	See the result about who allocated each page
-	in the sorted_page_owner.txt.
+   See the result about who allocated each page
+   in the ``sorted_page_owner.txt``.
diff --git a/Documentation/vm/remap_file_pages.txt b/Documentation/vm/remap_file_pages.rst
index f609142f406a..7bef6718e3a9 100644
--- a/Documentation/vm/remap_file_pages.txt
+++ b/Documentation/vm/remap_file_pages.rst
@@ -1,3 +1,9 @@
+.. _remap_file_pages:
+
+==============================
+remap_file_pages() system call
+==============================
+
 The remap_file_pages() system call is used to create a nonlinear mapping,
 that is, a mapping in which the pages of the file are mapped into a
 nonsequential order in memory. The advantage of using remap_file_pages()
diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst
new file mode 100644
index 000000000000..3a775fd64e2d
--- /dev/null
+++ b/Documentation/vm/slub.rst
@@ -0,0 +1,361 @@
+.. _slub:
+
+==========================
+Short users guide for SLUB
+==========================
+
+The basic philosophy of SLUB is very different from SLAB. SLAB
+requires rebuilding the kernel to activate debug options for all
+slab caches. SLUB always includes full debugging but it is off by default.
+SLUB can enable debugging only for selected slabs in order to avoid
+an impact on overall system performance which may make a bug more
+difficult to find.
+
+In order to switch debugging on one can add an option ``slub_debug``
+to the kernel command line. That will enable full debugging for
+all slabs.
+
+Typically one would then use the ``slabinfo`` command to get statistical
+data and perform operation on the slabs. By default ``slabinfo`` only lists
+slabs that have data in them. See "slabinfo -h" for more options when
+running the command. ``slabinfo`` can be compiled with
+::
+
+	gcc -o slabinfo tools/vm/slabinfo.c
+
+Some of the modes of operation of ``slabinfo`` require that slub debugging
+be enabled on the command line. F.e. no tracking information will be
+available without debugging on and validation can only partially
+be performed if debugging was not switched on.
+
+Some more sophisticated uses of slub_debug:
+-------------------------------------------
+
+Parameters may be given to ``slub_debug``. If none is specified then full
+debugging is enabled. Format:
+
+slub_debug=<Debug-Options>
+	Enable options for all slabs
+slub_debug=<Debug-Options>,<slab name>
+	Enable options only for select slabs
+
+
+Possible debug options are::
+
+	F		Sanity checks on (enables SLAB_DEBUG_CONSISTENCY_CHECKS
+			Sorry SLAB legacy issues)
+	Z		Red zoning
+	P		Poisoning (object and padding)
+	U		User tracking (free and alloc)
+	T		Trace (please only use on single slabs)
+	A		Toggle failslab filter mark for the cache
+	O		Switch debugging off for caches that would have
+			caused higher minimum slab orders
+	-		Switch all debugging off (useful if the kernel is
+			configured with CONFIG_SLUB_DEBUG_ON)
+
+F.e. in order to boot just with sanity checks and red zoning one would specify::
+
+	slub_debug=FZ
+
+Trying to find an issue in the dentry cache? Try::
+
+	slub_debug=,dentry
+
+to only enable debugging on the dentry cache.
+
+Red zoning and tracking may realign the slab.  We can just apply sanity checks
+to the dentry cache with::
+
+	slub_debug=F,dentry
+
+Debugging options may require the minimum possible slab order to increase as
+a result of storing the metadata (for example, caches with PAGE_SIZE object
+sizes).  This has a higher liklihood of resulting in slab allocation errors
+in low memory situations or if there's high fragmentation of memory.  To
+switch off debugging for such caches by default, use::
+
+	slub_debug=O
+
+In case you forgot to enable debugging on the kernel command line: It is
+possible to enable debugging manually when the kernel is up. Look at the
+contents of::
+
+	/sys/kernel/slab/<slab name>/
+
+Look at the writable files. Writing 1 to them will enable the
+corresponding debug option. All options can be set on a slab that does
+not contain objects. If the slab already contains objects then sanity checks
+and tracing may only be enabled. The other options may cause the realignment
+of objects.
+
+Careful with tracing: It may spew out lots of information and never stop if
+used on the wrong slab.
+
+Slab merging
+============
+
+If no debug options are specified then SLUB may merge similar slabs together
+in order to reduce overhead and increase cache hotness of objects.
+``slabinfo -a`` displays which slabs were merged together.
+
+Slab validation
+===============
+
+SLUB can validate all object if the kernel was booted with slub_debug. In
+order to do so you must have the ``slabinfo`` tool. Then you can do
+::
+
+	slabinfo -v
+
+which will test all objects. Output will be generated to the syslog.
+
+This also works in a more limited way if boot was without slab debug.
+In that case ``slabinfo -v`` simply tests all reachable objects. Usually
+these are in the cpu slabs and the partial slabs. Full slabs are not
+tracked by SLUB in a non debug situation.
+
+Getting more performance
+========================
+
+To some degree SLUB's performance is limited by the need to take the
+list_lock once in a while to deal with partial slabs. That overhead is
+governed by the order of the allocation for each slab. The allocations
+can be influenced by kernel parameters:
+
+.. slub_min_objects=x		(default 4)
+.. slub_min_order=x		(default 0)
+.. slub_max_order=x		(default 3 (PAGE_ALLOC_COSTLY_ORDER))
+
+``slub_min_objects``
+	allows to specify how many objects must at least fit into one
+	slab in order for the allocation order to be acceptable.  In
+	general slub will be able to perform this number of
+	allocations on a slab without consulting centralized resources
+	(list_lock) where contention may occur.
+
+``slub_min_order``
+	specifies a minim order of slabs. A similar effect like
+	``slub_min_objects``.
+
+``slub_max_order``
+	specified the order at which ``slub_min_objects`` should no
+	longer be checked. This is useful to avoid SLUB trying to
+	generate super large order pages to fit ``slub_min_objects``
+	of a slab cache with large object sizes into one high order
+	page. Setting command line parameter
+	``debug_guardpage_minorder=N`` (N > 0), forces setting
+	``slub_max_order`` to 0, what cause minimum possible order of
+	slabs allocation.
+
+SLUB Debug output
+=================
+
+Here is a sample of slub debug output::
+
+ ====================================================================
+ BUG kmalloc-8: Redzone overwritten
+ --------------------------------------------------------------------
+
+ INFO: 0xc90f6d28-0xc90f6d2b. First byte 0x00 instead of 0xcc
+ INFO: Slab 0xc528c530 flags=0x400000c3 inuse=61 fp=0xc90f6d58
+ INFO: Object 0xc90f6d20 @offset=3360 fp=0xc90f6d58
+ INFO: Allocated in get_modalias+0x61/0xf5 age=53 cpu=1 pid=554
+
+ Bytes b4 0xc90f6d10:  00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
+   Object 0xc90f6d20:  31 30 31 39 2e 30 30 35                         1019.005
+  Redzone 0xc90f6d28:  00 cc cc cc                                     .
+  Padding 0xc90f6d50:  5a 5a 5a 5a 5a 5a 5a 5a                         ZZZZZZZZ
+
+   [<c010523d>] dump_trace+0x63/0x1eb
+   [<c01053df>] show_trace_log_lvl+0x1a/0x2f
+   [<c010601d>] show_trace+0x12/0x14
+   [<c0106035>] dump_stack+0x16/0x18
+   [<c017e0fa>] object_err+0x143/0x14b
+   [<c017e2cc>] check_object+0x66/0x234
+   [<c017eb43>] __slab_free+0x239/0x384
+   [<c017f446>] kfree+0xa6/0xc6
+   [<c02e2335>] get_modalias+0xb9/0xf5
+   [<c02e23b7>] dmi_dev_uevent+0x27/0x3c
+   [<c027866a>] dev_uevent+0x1ad/0x1da
+   [<c0205024>] kobject_uevent_env+0x20a/0x45b
+   [<c020527f>] kobject_uevent+0xa/0xf
+   [<c02779f1>] store_uevent+0x4f/0x58
+   [<c027758e>] dev_attr_store+0x29/0x2f
+   [<c01bec4f>] sysfs_write_file+0x16e/0x19c
+   [<c0183ba7>] vfs_write+0xd1/0x15a
+   [<c01841d7>] sys_write+0x3d/0x72
+   [<c0104112>] sysenter_past_esp+0x5f/0x99
+   [<b7f7b410>] 0xb7f7b410
+   =======================
+
+ FIX kmalloc-8: Restoring Redzone 0xc90f6d28-0xc90f6d2b=0xcc
+
+If SLUB encounters a corrupted object (full detection requires the kernel
+to be booted with slub_debug) then the following output will be dumped
+into the syslog:
+
+1. Description of the problem encountered
+
+   This will be a message in the system log starting with::
+
+     ===============================================
+     BUG <slab cache affected>: <What went wrong>
+     -----------------------------------------------
+
+     INFO: <corruption start>-<corruption_end> <more info>
+     INFO: Slab <address> <slab information>
+     INFO: Object <address> <object information>
+     INFO: Allocated in <kernel function> age=<jiffies since alloc> cpu=<allocated by
+	cpu> pid=<pid of the process>
+     INFO: Freed in <kernel function> age=<jiffies since free> cpu=<freed by cpu>
+	pid=<pid of the process>
+
+   (Object allocation / free information is only available if SLAB_STORE_USER is
+   set for the slab. slub_debug sets that option)
+
+2. The object contents if an object was involved.
+
+   Various types of lines can follow the BUG SLUB line:
+
+   Bytes b4 <address> : <bytes>
+	Shows a few bytes before the object where the problem was detected.
+	Can be useful if the corruption does not stop with the start of the
+	object.
+
+   Object <address> : <bytes>
+	The bytes of the object. If the object is inactive then the bytes
+	typically contain poison values. Any non-poison value shows a
+	corruption by a write after free.
+
+   Redzone <address> : <bytes>
+	The Redzone following the object. The Redzone is used to detect
+	writes after the object. All bytes should always have the same
+	value. If there is any deviation then it is due to a write after
+	the object boundary.
+
+	(Redzone information is only available if SLAB_RED_ZONE is set.
+	slub_debug sets that option)
+
+   Padding <address> : <bytes>
+	Unused data to fill up the space in order to get the next object
+	properly aligned. In the debug case we make sure that there are
+	at least 4 bytes of padding. This allows the detection of writes
+	before the object.
+
+3. A stackdump
+
+   The stackdump describes the location where the error was detected. The cause
+   of the corruption is may be more likely found by looking at the function that
+   allocated or freed the object.
+
+4. Report on how the problem was dealt with in order to ensure the continued
+   operation of the system.
+
+   These are messages in the system log beginning with::
+
+	FIX <slab cache affected>: <corrective action taken>
+
+   In the above sample SLUB found that the Redzone of an active object has
+   been overwritten. Here a string of 8 characters was written into a slab that
+   has the length of 8 characters. However, a 8 character string needs a
+   terminating 0. That zero has overwritten the first byte of the Redzone field.
+   After reporting the details of the issue encountered the FIX SLUB message
+   tells us that SLUB has restored the Redzone to its proper value and then
+   system operations continue.
+
+Emergency operations
+====================
+
+Minimal debugging (sanity checks alone) can be enabled by booting with::
+
+	slub_debug=F
+
+This will be generally be enough to enable the resiliency features of slub
+which will keep the system running even if a bad kernel component will
+keep corrupting objects. This may be important for production systems.
+Performance will be impacted by the sanity checks and there will be a
+continual stream of error messages to the syslog but no additional memory
+will be used (unlike full debugging).
+
+No guarantees. The kernel component still needs to be fixed. Performance
+may be optimized further by locating the slab that experiences corruption
+and enabling debugging only for that cache
+
+I.e.::
+
+	slub_debug=F,dentry
+
+If the corruption occurs by writing after the end of the object then it
+may be advisable to enable a Redzone to avoid corrupting the beginning
+of other objects::
+
+	slub_debug=FZ,dentry
+
+Extended slabinfo mode and plotting
+===================================
+
+The ``slabinfo`` tool has a special 'extended' ('-X') mode that includes:
+ - Slabcache Totals
+ - Slabs sorted by size (up to -N <num> slabs, default 1)
+ - Slabs sorted by loss (up to -N <num> slabs, default 1)
+
+Additionally, in this mode ``slabinfo`` does not dynamically scale
+sizes (G/M/K) and reports everything in bytes (this functionality is
+also available to other slabinfo modes via '-B' option) which makes
+reporting more precise and accurate. Moreover, in some sense the `-X'
+mode also simplifies the analysis of slabs' behaviour, because its
+output can be plotted using the ``slabinfo-gnuplot.sh`` script. So it
+pushes the analysis from looking through the numbers (tons of numbers)
+to something easier -- visual analysis.
+
+To generate plots:
+
+a) collect slabinfo extended records, for example::
+
+	while [ 1 ]; do slabinfo -X >> FOO_STATS; sleep 1; done
+
+b) pass stats file(-s) to ``slabinfo-gnuplot.sh`` script::
+
+	slabinfo-gnuplot.sh FOO_STATS [FOO_STATS2 .. FOO_STATSN]
+
+   The ``slabinfo-gnuplot.sh`` script will pre-processes the collected records
+   and generates 3 png files (and 3 pre-processing cache files) per STATS
+   file:
+   - Slabcache Totals: FOO_STATS-totals.png
+   - Slabs sorted by size: FOO_STATS-slabs-by-size.png
+   - Slabs sorted by loss: FOO_STATS-slabs-by-loss.png
+
+Another use case, when ``slabinfo-gnuplot.sh`` can be useful, is when you
+need to compare slabs' behaviour "prior to" and "after" some code
+modification.  To help you out there, ``slabinfo-gnuplot.sh`` script
+can 'merge' the `Slabcache Totals` sections from different
+measurements. To visually compare N plots:
+
+a) Collect as many STATS1, STATS2, .. STATSN files as you need::
+
+	while [ 1 ]; do slabinfo -X >> STATS<X>; sleep 1; done
+
+b) Pre-process those STATS files::
+
+	slabinfo-gnuplot.sh STATS1 STATS2 .. STATSN
+
+c) Execute ``slabinfo-gnuplot.sh`` in '-t' mode, passing all of the
+   generated pre-processed \*-totals::
+
+	slabinfo-gnuplot.sh -t STATS1-totals STATS2-totals .. STATSN-totals
+
+   This will produce a single plot (png file).
+
+   Plots, expectedly, can be large so some fluctuations or small spikes
+   can go unnoticed. To deal with that, ``slabinfo-gnuplot.sh`` has two
+   options to 'zoom-in'/'zoom-out':
+
+   a) ``-s %d,%d`` -- overwrites the default image width and heigh
+   b) ``-r %d,%d`` -- specifies a range of samples to use (for example,
+      in ``slabinfo -X >> FOO_STATS; sleep 1;`` case, using a ``-r
+      40,60`` range will plot only samples collected between 40th and
+      60th seconds).
+
+Christoph Lameter, May 30, 2007
+Sergey Senozhatsky, October 23, 2015
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
deleted file mode 100644
index 84652419bff2..000000000000
--- a/Documentation/vm/slub.txt
+++ /dev/null
@@ -1,342 +0,0 @@
-Short users guide for SLUB
---------------------------
-
-The basic philosophy of SLUB is very different from SLAB. SLAB
-requires rebuilding the kernel to activate debug options for all
-slab caches. SLUB always includes full debugging but it is off by default.
-SLUB can enable debugging only for selected slabs in order to avoid
-an impact on overall system performance which may make a bug more
-difficult to find.
-
-In order to switch debugging on one can add an option "slub_debug"
-to the kernel command line. That will enable full debugging for
-all slabs.
-
-Typically one would then use the "slabinfo" command to get statistical
-data and perform operation on the slabs. By default slabinfo only lists
-slabs that have data in them. See "slabinfo -h" for more options when
-running the command. slabinfo can be compiled with
-
-gcc -o slabinfo tools/vm/slabinfo.c
-
-Some of the modes of operation of slabinfo require that slub debugging
-be enabled on the command line. F.e. no tracking information will be
-available without debugging on and validation can only partially
-be performed if debugging was not switched on.
-
-Some more sophisticated uses of slub_debug:
--------------------------------------------
-
-Parameters may be given to slub_debug. If none is specified then full
-debugging is enabled. Format:
-
-slub_debug=<Debug-Options>       Enable options for all slabs
-slub_debug=<Debug-Options>,<slab name>
-				Enable options only for select slabs
-
-Possible debug options are
-	F		Sanity checks on (enables SLAB_DEBUG_CONSISTENCY_CHECKS
-			Sorry SLAB legacy issues)
-	Z		Red zoning
-	P		Poisoning (object and padding)
-	U		User tracking (free and alloc)
-	T		Trace (please only use on single slabs)
-	A		Toggle failslab filter mark for the cache
-	O		Switch debugging off for caches that would have
-			caused higher minimum slab orders
-	-		Switch all debugging off (useful if the kernel is
-			configured with CONFIG_SLUB_DEBUG_ON)
-
-F.e. in order to boot just with sanity checks and red zoning one would specify:
-
-	slub_debug=FZ
-
-Trying to find an issue in the dentry cache? Try
-
-	slub_debug=,dentry
-
-to only enable debugging on the dentry cache.
-
-Red zoning and tracking may realign the slab.  We can just apply sanity checks
-to the dentry cache with
-
-	slub_debug=F,dentry
-
-Debugging options may require the minimum possible slab order to increase as
-a result of storing the metadata (for example, caches with PAGE_SIZE object
-sizes).  This has a higher liklihood of resulting in slab allocation errors
-in low memory situations or if there's high fragmentation of memory.  To
-switch off debugging for such caches by default, use
-
-	slub_debug=O
-
-In case you forgot to enable debugging on the kernel command line: It is
-possible to enable debugging manually when the kernel is up. Look at the
-contents of:
-
-/sys/kernel/slab/<slab name>/
-
-Look at the writable files. Writing 1 to them will enable the
-corresponding debug option. All options can be set on a slab that does
-not contain objects. If the slab already contains objects then sanity checks
-and tracing may only be enabled. The other options may cause the realignment
-of objects.
-
-Careful with tracing: It may spew out lots of information and never stop if
-used on the wrong slab.
-
-Slab merging
-------------
-
-If no debug options are specified then SLUB may merge similar slabs together
-in order to reduce overhead and increase cache hotness of objects.
-slabinfo -a displays which slabs were merged together.
-
-Slab validation
----------------
-
-SLUB can validate all object if the kernel was booted with slub_debug. In
-order to do so you must have the slabinfo tool. Then you can do
-
-slabinfo -v
-
-which will test all objects. Output will be generated to the syslog.
-
-This also works in a more limited way if boot was without slab debug.
-In that case slabinfo -v simply tests all reachable objects. Usually
-these are in the cpu slabs and the partial slabs. Full slabs are not
-tracked by SLUB in a non debug situation.
-
-Getting more performance
-------------------------
-
-To some degree SLUB's performance is limited by the need to take the
-list_lock once in a while to deal with partial slabs. That overhead is
-governed by the order of the allocation for each slab. The allocations
-can be influenced by kernel parameters:
-
-slub_min_objects=x		(default 4)
-slub_min_order=x		(default 0)
-slub_max_order=x		(default 3 (PAGE_ALLOC_COSTLY_ORDER))
-
-slub_min_objects allows to specify how many objects must at least fit
-into one slab in order for the allocation order to be acceptable.
-In general slub will be able to perform this number of allocations
-on a slab without consulting centralized resources (list_lock) where
-contention may occur.
-
-slub_min_order specifies a minim order of slabs. A similar effect like
-slub_min_objects.
-
-slub_max_order specified the order at which slub_min_objects should no
-longer be checked. This is useful to avoid SLUB trying to generate
-super large order pages to fit slub_min_objects of a slab cache with
-large object sizes into one high order page. Setting command line
-parameter debug_guardpage_minorder=N (N > 0), forces setting
-slub_max_order to 0, what cause minimum possible order of slabs
-allocation.
-
-SLUB Debug output
------------------
-
-Here is a sample of slub debug output:
-
-====================================================================
-BUG kmalloc-8: Redzone overwritten
---------------------------------------------------------------------
-
-INFO: 0xc90f6d28-0xc90f6d2b. First byte 0x00 instead of 0xcc
-INFO: Slab 0xc528c530 flags=0x400000c3 inuse=61 fp=0xc90f6d58
-INFO: Object 0xc90f6d20 @offset=3360 fp=0xc90f6d58
-INFO: Allocated in get_modalias+0x61/0xf5 age=53 cpu=1 pid=554
-
-Bytes b4 0xc90f6d10:  00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
-  Object 0xc90f6d20:  31 30 31 39 2e 30 30 35                         1019.005
- Redzone 0xc90f6d28:  00 cc cc cc                                     .
- Padding 0xc90f6d50:  5a 5a 5a 5a 5a 5a 5a 5a                         ZZZZZZZZ
-
-  [<c010523d>] dump_trace+0x63/0x1eb
-  [<c01053df>] show_trace_log_lvl+0x1a/0x2f
-  [<c010601d>] show_trace+0x12/0x14
-  [<c0106035>] dump_stack+0x16/0x18
-  [<c017e0fa>] object_err+0x143/0x14b
-  [<c017e2cc>] check_object+0x66/0x234
-  [<c017eb43>] __slab_free+0x239/0x384
-  [<c017f446>] kfree+0xa6/0xc6
-  [<c02e2335>] get_modalias+0xb9/0xf5
-  [<c02e23b7>] dmi_dev_uevent+0x27/0x3c
-  [<c027866a>] dev_uevent+0x1ad/0x1da
-  [<c0205024>] kobject_uevent_env+0x20a/0x45b
-  [<c020527f>] kobject_uevent+0xa/0xf
-  [<c02779f1>] store_uevent+0x4f/0x58
-  [<c027758e>] dev_attr_store+0x29/0x2f
-  [<c01bec4f>] sysfs_write_file+0x16e/0x19c
-  [<c0183ba7>] vfs_write+0xd1/0x15a
-  [<c01841d7>] sys_write+0x3d/0x72
-  [<c0104112>] sysenter_past_esp+0x5f/0x99
-  [<b7f7b410>] 0xb7f7b410
-  =======================
-
-FIX kmalloc-8: Restoring Redzone 0xc90f6d28-0xc90f6d2b=0xcc
-
-If SLUB encounters a corrupted object (full detection requires the kernel
-to be booted with slub_debug) then the following output will be dumped
-into the syslog:
-
-1. Description of the problem encountered
-
-This will be a message in the system log starting with
-
-===============================================
-BUG <slab cache affected>: <What went wrong>
------------------------------------------------
-
-INFO: <corruption start>-<corruption_end> <more info>
-INFO: Slab <address> <slab information>
-INFO: Object <address> <object information>
-INFO: Allocated in <kernel function> age=<jiffies since alloc> cpu=<allocated by
-	cpu> pid=<pid of the process>
-INFO: Freed in <kernel function> age=<jiffies since free> cpu=<freed by cpu>
-	 pid=<pid of the process>
-
-(Object allocation / free information is only available if SLAB_STORE_USER is
-set for the slab. slub_debug sets that option)
-
-2. The object contents if an object was involved.
-
-Various types of lines can follow the BUG SLUB line:
-
-Bytes b4 <address> : <bytes>
-	Shows a few bytes before the object where the problem was detected.
-	Can be useful if the corruption does not stop with the start of the
-	object.
-
-Object <address> : <bytes>
-	The bytes of the object. If the object is inactive then the bytes
-	typically contain poison values. Any non-poison value shows a
-	corruption by a write after free.
-
-Redzone <address> : <bytes>
-	The Redzone following the object. The Redzone is used to detect
-	writes after the object. All bytes should always have the same
-	value. If there is any deviation then it is due to a write after
-	the object boundary.
-
-	(Redzone information is only available if SLAB_RED_ZONE is set.
-	slub_debug sets that option)
-
-Padding <address> : <bytes>
-	Unused data to fill up the space in order to get the next object
-	properly aligned. In the debug case we make sure that there are
-	at least 4 bytes of padding. This allows the detection of writes
-	before the object.
-
-3. A stackdump
-
-The stackdump describes the location where the error was detected. The cause
-of the corruption is may be more likely found by looking at the function that
-allocated or freed the object.
-
-4. Report on how the problem was dealt with in order to ensure the continued
-operation of the system.
-
-These are messages in the system log beginning with
-
-FIX <slab cache affected>: <corrective action taken>
-
-In the above sample SLUB found that the Redzone of an active object has
-been overwritten. Here a string of 8 characters was written into a slab that
-has the length of 8 characters. However, a 8 character string needs a
-terminating 0. That zero has overwritten the first byte of the Redzone field.
-After reporting the details of the issue encountered the FIX SLUB message
-tells us that SLUB has restored the Redzone to its proper value and then
-system operations continue.
-
-Emergency operations:
----------------------
-
-Minimal debugging (sanity checks alone) can be enabled by booting with
-
-	slub_debug=F
-
-This will be generally be enough to enable the resiliency features of slub
-which will keep the system running even if a bad kernel component will
-keep corrupting objects. This may be important for production systems.
-Performance will be impacted by the sanity checks and there will be a
-continual stream of error messages to the syslog but no additional memory
-will be used (unlike full debugging).
-
-No guarantees. The kernel component still needs to be fixed. Performance
-may be optimized further by locating the slab that experiences corruption
-and enabling debugging only for that cache
-
-I.e.
-
-	slub_debug=F,dentry
-
-If the corruption occurs by writing after the end of the object then it
-may be advisable to enable a Redzone to avoid corrupting the beginning
-of other objects.
-
-	slub_debug=FZ,dentry
-
-Extended slabinfo mode and plotting
------------------------------------
-
-The slabinfo tool has a special 'extended' ('-X') mode that includes:
- - Slabcache Totals
- - Slabs sorted by size (up to -N <num> slabs, default 1)
- - Slabs sorted by loss (up to -N <num> slabs, default 1)
-
-Additionally, in this mode slabinfo does not dynamically scale sizes (G/M/K)
-and reports everything in bytes (this functionality is also available to
-other slabinfo modes via '-B' option) which makes reporting more precise and
-accurate. Moreover, in some sense the `-X' mode also simplifies the analysis
-of slabs' behaviour, because its output can be plotted using the
-slabinfo-gnuplot.sh script. So it pushes the analysis from looking through
-the numbers (tons of numbers) to something easier -- visual analysis.
-
-To generate plots:
-a) collect slabinfo extended records, for example:
-
-  while [ 1 ]; do slabinfo -X >> FOO_STATS; sleep 1; done
-
-b) pass stats file(-s) to slabinfo-gnuplot.sh script:
-  slabinfo-gnuplot.sh FOO_STATS [FOO_STATS2 .. FOO_STATSN]
-
-The slabinfo-gnuplot.sh script will pre-processes the collected records
-and generates 3 png files (and 3 pre-processing cache files) per STATS
-file:
- - Slabcache Totals: FOO_STATS-totals.png
- - Slabs sorted by size: FOO_STATS-slabs-by-size.png
- - Slabs sorted by loss: FOO_STATS-slabs-by-loss.png
-
-Another use case, when slabinfo-gnuplot can be useful, is when you need
-to compare slabs' behaviour "prior to" and "after" some code modification.
-To help you out there, slabinfo-gnuplot.sh script can 'merge' the
-`Slabcache Totals` sections from different measurements. To visually
-compare N plots:
-
-a) Collect as many STATS1, STATS2, .. STATSN files as you need
-  while [ 1 ]; do slabinfo -X >> STATS<X>; sleep 1; done
-
-b) Pre-process those STATS files
-  slabinfo-gnuplot.sh STATS1 STATS2 .. STATSN
-
-c) Execute slabinfo-gnuplot.sh in '-t' mode, passing all of the
-generated pre-processed *-totals
-  slabinfo-gnuplot.sh -t STATS1-totals STATS2-totals .. STATSN-totals
-
-This will produce a single plot (png file).
-
-Plots, expectedly, can be large so some fluctuations or small spikes
-can go unnoticed. To deal with that, `slabinfo-gnuplot.sh' has two
-options to 'zoom-in'/'zoom-out':
- a) -s %d,%d  overwrites the default image width and heigh
- b) -r %d,%d  specifies a range of samples to use (for example,
-              in `slabinfo -X >> FOO_STATS; sleep 1;' case, using
-              a "-r 40,60" range will plot only samples collected
-              between 40th and 60th seconds).
-
-Christoph Lameter, May 30, 2007
-Sergey Senozhatsky, October 23, 2015
diff --git a/Documentation/vm/split_page_table_lock b/Documentation/vm/split_page_table_lock.rst
index 62842a857dab..889b00be469f 100644
--- a/Documentation/vm/split_page_table_lock
+++ b/Documentation/vm/split_page_table_lock.rst
@@ -1,3 +1,6 @@
+.. _split_page_table_lock:
+
+=====================
 Split page table lock
 =====================
 
@@ -11,6 +14,7 @@ access to the table. At the moment we use split lock for PTE and PMD
 tables. Access to higher level tables protected by mm->page_table_lock.
 
 There are helpers to lock/unlock a table and other accessor functions:
+
  - pte_offset_map_lock()
 	maps pte and takes PTE table lock, returns pointer to the taken
 	lock;
@@ -34,12 +38,13 @@ Split page table lock for PMD tables is enabled, if it's enabled for PTE
 tables and the architecture supports it (see below).
 
 Hugetlb and split page table lock
----------------------------------
+=================================
 
 Hugetlb can support several page sizes. We use split lock only for PMD
 level, but not for PUD.
 
 Hugetlb-specific helpers:
+
  - huge_pte_lock()
 	takes pmd split lock for PMD_SIZE page, mm->page_table_lock
 	otherwise;
@@ -47,7 +52,7 @@ Hugetlb-specific helpers:
 	returns pointer to table lock;
 
 Support of split page table lock by an architecture
----------------------------------------------------
+===================================================
 
 There's no need in special enabling of PTE split page table lock:
 everything required is done by pgtable_page_ctor() and pgtable_page_dtor(),
@@ -73,7 +78,7 @@ NOTE: pgtable_page_ctor() and pgtable_pmd_page_ctor() can fail -- it must
 be handled properly.
 
 page->ptl
----------
+=========
 
 page->ptl is used to access split page table lock, where 'page' is struct
 page of page containing the table. It shares storage with page->private
@@ -81,6 +86,7 @@ page of page containing the table. It shares storage with page->private
 
 To avoid increasing size of struct page and have best performance, we use a
 trick:
+
  - if spinlock_t fits into long, we use page->ptr as spinlock, so we
    can avoid indirect access and save a cache line.
  - if size of spinlock_t is bigger then size of long, we use page->ptl as
diff --git a/Documentation/vm/swap_numa.txt b/Documentation/vm/swap_numa.rst
index d5960c9124f5..e0466f2db8fa 100644
--- a/Documentation/vm/swap_numa.txt
+++ b/Documentation/vm/swap_numa.rst
@@ -1,5 +1,8 @@
+.. _swap_numa:
+
+===========================================
 Automatically bind swap device to numa node
--------------------------------------------
+===========================================
 
 If the system has more than one swap device and swap device has the node
 information, we can make use of this information to decide which swap
@@ -7,15 +10,16 @@ device to use in get_swap_pages() to get better performance.
 
 
 How to use this feature
------------------------
+=======================
 
 Swap device has priority and that decides the order of it to be used. To make
 use of automatically binding, there is no need to manipulate priority settings
 for swap devices. e.g. on a 2 node machine, assume 2 swap devices swapA and
 swapB, with swapA attached to node 0 and swapB attached to node 1, are going
-to be swapped on. Simply swapping them on by doing:
-# swapon /dev/swapA
-# swapon /dev/swapB
+to be swapped on. Simply swapping them on by doing::
+
+	# swapon /dev/swapA
+	# swapon /dev/swapB
 
 Then node 0 will use the two swap devices in the order of swapA then swapB and
 node 1 will use the two swap devices in the order of swapB then swapA. Note
@@ -24,32 +28,39 @@ that the order of them being swapped on doesn't matter.
 A more complex example on a 4 node machine. Assume 6 swap devices are going to
 be swapped on: swapA and swapB are attached to node 0, swapC is attached to
 node 1, swapD and swapE are attached to node 2 and swapF is attached to node3.
-The way to swap them on is the same as above:
-# swapon /dev/swapA
-# swapon /dev/swapB
-# swapon /dev/swapC
-# swapon /dev/swapD
-# swapon /dev/swapE
-# swapon /dev/swapF
-
-Then node 0 will use them in the order of:
-swapA/swapB -> swapC -> swapD -> swapE -> swapF
+The way to swap them on is the same as above::
+
+	# swapon /dev/swapA
+	# swapon /dev/swapB
+	# swapon /dev/swapC
+	# swapon /dev/swapD
+	# swapon /dev/swapE
+	# swapon /dev/swapF
+
+Then node 0 will use them in the order of::
+
+	swapA/swapB -> swapC -> swapD -> swapE -> swapF
+
 swapA and swapB will be used in a round robin mode before any other swap device.
 
-node 1 will use them in the order of:
-swapC -> swapA -> swapB -> swapD -> swapE -> swapF
+node 1 will use them in the order of::
+
+	swapC -> swapA -> swapB -> swapD -> swapE -> swapF
+
+node 2 will use them in the order of::
+
+	swapD/swapE -> swapA -> swapB -> swapC -> swapF
 
-node 2 will use them in the order of:
-swapD/swapE -> swapA -> swapB -> swapC -> swapF
 Similaly, swapD and swapE will be used in a round robin mode before any
 other swap devices.
 
-node 3 will use them in the order of:
-swapF -> swapA -> swapB -> swapC -> swapD -> swapE
+node 3 will use them in the order of::
+
+	swapF -> swapA -> swapB -> swapC -> swapD -> swapE
 
 
 Implementation details
-----------------------
+======================
 
 The current code uses a priority based list, swap_avail_list, to decide
 which swap device to use and if multiple swap devices share the same
diff --git a/Documentation/vm/transhuge.rst b/Documentation/vm/transhuge.rst
new file mode 100644
index 000000000000..a8cf6809e36e
--- /dev/null
+++ b/Documentation/vm/transhuge.rst
@@ -0,0 +1,197 @@
+.. _transhuge:
+
+============================
+Transparent Hugepage Support
+============================
+
+This document describes design principles Transparent Hugepage (THP)
+Support and its interaction with other parts of the memory management.
+
+Design principles
+=================
+
+- "graceful fallback": mm components which don't have transparent hugepage
+  knowledge fall back to breaking huge pmd mapping into table of ptes and,
+  if necessary, split a transparent hugepage. Therefore these components
+  can continue working on the regular pages or regular pte mappings.
+
+- if a hugepage allocation fails because of memory fragmentation,
+  regular pages should be gracefully allocated instead and mixed in
+  the same vma without any failure or significant delay and without
+  userland noticing
+
+- if some task quits and more hugepages become available (either
+  immediately in the buddy or through the VM), guest physical memory
+  backed by regular pages should be relocated on hugepages
+  automatically (with khugepaged)
+
+- it doesn't require memory reservation and in turn it uses hugepages
+  whenever possible (the only possible reservation here is kernelcore=
+  to avoid unmovable pages to fragment all the memory but such a tweak
+  is not specific to transparent hugepage support and it's a generic
+  feature that applies to all dynamic high order allocations in the
+  kernel)
+
+get_user_pages and follow_page
+==============================
+
+get_user_pages and follow_page if run on a hugepage, will return the
+head or tail pages as usual (exactly as they would do on
+hugetlbfs). Most gup users will only care about the actual physical
+address of the page and its temporary pinning to release after the I/O
+is complete, so they won't ever notice the fact the page is huge. But
+if any driver is going to mangle over the page structure of the tail
+page (like for checking page->mapping or other bits that are relevant
+for the head page and not the tail page), it should be updated to jump
+to check head page instead. Taking reference on any head/tail page would
+prevent page from being split by anyone.
+
+.. note::
+   these aren't new constraints to the GUP API, and they match the
+   same constrains that applies to hugetlbfs too, so any driver capable
+   of handling GUP on hugetlbfs will also work fine on transparent
+   hugepage backed mappings.
+
+In case you can't handle compound pages if they're returned by
+follow_page, the FOLL_SPLIT bit can be specified as parameter to
+follow_page, so that it will split the hugepages before returning
+them. Migration for example passes FOLL_SPLIT as parameter to
+follow_page because it's not hugepage aware and in fact it can't work
+at all on hugetlbfs (but it instead works fine on transparent
+hugepages thanks to FOLL_SPLIT). migration simply can't deal with
+hugepages being returned (as it's not only checking the pfn of the
+page and pinning it during the copy but it pretends to migrate the
+memory in regular page sizes and with regular pte/pmd mappings).
+
+Graceful fallback
+=================
+
+Code walking pagetables but unaware about huge pmds can simply call
+split_huge_pmd(vma, pmd, addr) where the pmd is the one returned by
+pmd_offset. It's trivial to make the code transparent hugepage aware
+by just grepping for "pmd_offset" and adding split_huge_pmd where
+missing after pmd_offset returns the pmd. Thanks to the graceful
+fallback design, with a one liner change, you can avoid to write
+hundred if not thousand of lines of complex code to make your code
+hugepage aware.
+
+If you're not walking pagetables but you run into a physical hugepage
+but you can't handle it natively in your code, you can split it by
+calling split_huge_page(page). This is what the Linux VM does before
+it tries to swapout the hugepage for example. split_huge_page() can fail
+if the page is pinned and you must handle this correctly.
+
+Example to make mremap.c transparent hugepage aware with a one liner
+change::
+
+	diff --git a/mm/mremap.c b/mm/mremap.c
+	--- a/mm/mremap.c
+	+++ b/mm/mremap.c
+	@@ -41,6 +41,7 @@ static pmd_t *get_old_pmd(struct mm_stru
+			return NULL;
+
+		pmd = pmd_offset(pud, addr);
+	+	split_huge_pmd(vma, pmd, addr);
+		if (pmd_none_or_clear_bad(pmd))
+			return NULL;
+
+Locking in hugepage aware code
+==============================
+
+We want as much code as possible hugepage aware, as calling
+split_huge_page() or split_huge_pmd() has a cost.
+
+To make pagetable walks huge pmd aware, all you need to do is to call
+pmd_trans_huge() on the pmd returned by pmd_offset. You must hold the
+mmap_sem in read (or write) mode to be sure an huge pmd cannot be
+created from under you by khugepaged (khugepaged collapse_huge_page
+takes the mmap_sem in write mode in addition to the anon_vma lock). If
+pmd_trans_huge returns false, you just fallback in the old code
+paths. If instead pmd_trans_huge returns true, you have to take the
+page table lock (pmd_lock()) and re-run pmd_trans_huge. Taking the
+page table lock will prevent the huge pmd to be converted into a
+regular pmd from under you (split_huge_pmd can run in parallel to the
+pagetable walk). If the second pmd_trans_huge returns false, you
+should just drop the page table lock and fallback to the old code as
+before. Otherwise you can proceed to process the huge pmd and the
+hugepage natively. Once finished you can drop the page table lock.
+
+Refcounts and transparent huge pages
+====================================
+
+Refcounting on THP is mostly consistent with refcounting on other compound
+pages:
+
+  - get_page()/put_page() and GUP operate in head page's ->_refcount.
+
+  - ->_refcount in tail pages is always zero: get_page_unless_zero() never
+    succeed on tail pages.
+
+  - map/unmap of the pages with PTE entry increment/decrement ->_mapcount
+    on relevant sub-page of the compound page.
+
+  - map/unmap of the whole compound page accounted in compound_mapcount
+    (stored in first tail page). For file huge pages, we also increment
+    ->_mapcount of all sub-pages in order to have race-free detection of
+    last unmap of subpages.
+
+PageDoubleMap() indicates that the page is *possibly* mapped with PTEs.
+
+For anonymous pages PageDoubleMap() also indicates ->_mapcount in all
+subpages is offset up by one. This additional reference is required to
+get race-free detection of unmap of subpages when we have them mapped with
+both PMDs and PTEs.
+
+This is optimization required to lower overhead of per-subpage mapcount
+tracking. The alternative is alter ->_mapcount in all subpages on each
+map/unmap of the whole compound page.
+
+For anonymous pages, we set PG_double_map when a PMD of the page got split
+for the first time, but still have PMD mapping. The additional references
+go away with last compound_mapcount.
+
+File pages get PG_double_map set on first map of the page with PTE and
+goes away when the page gets evicted from page cache.
+
+split_huge_page internally has to distribute the refcounts in the head
+page to the tail pages before clearing all PG_head/tail bits from the page
+structures. It can be done easily for refcounts taken by page table
+entries. But we don't have enough information on how to distribute any
+additional pins (i.e. from get_user_pages). split_huge_page() fails any
+requests to split pinned huge page: it expects page count to be equal to
+sum of mapcount of all sub-pages plus one (split_huge_page caller must
+have reference for head page).
+
+split_huge_page uses migration entries to stabilize page->_refcount and
+page->_mapcount of anonymous pages. File pages just got unmapped.
+
+We safe against physical memory scanners too: the only legitimate way
+scanner can get reference to a page is get_page_unless_zero().
+
+All tail pages have zero ->_refcount until atomic_add(). This prevents the
+scanner from getting a reference to the tail page up to that point. After the
+atomic_add() we don't care about the ->_refcount value. We already known how
+many references should be uncharged from the head page.
+
+For head page get_page_unless_zero() will succeed and we don't mind. It's
+clear where reference should go after split: it will stay on head page.
+
+Note that split_huge_pmd() doesn't have any limitation on refcounting:
+pmd can be split at any point and never fails.
+
+Partial unmap and deferred_split_huge_page()
+============================================
+
+Unmapping part of THP (with munmap() or other way) is not going to free
+memory immediately. Instead, we detect that a subpage of THP is not in use
+in page_remove_rmap() and queue the THP for splitting if memory pressure
+comes. Splitting will free up unused subpages.
+
+Splitting the page right away is not an option due to locking context in
+the place where we can detect partial unmap. It's also might be
+counterproductive since in many cases partial unmap happens during exit(2) if
+a THP crosses a VMA boundary.
+
+Function deferred_split_huge_page() is used to queue page for splitting.
+The splitting itself will happen when we get memory pressure via shrinker
+interface.
diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
deleted file mode 100644
index 4dde03b44ad1..000000000000
--- a/Documentation/vm/transhuge.txt
+++ /dev/null
@@ -1,527 +0,0 @@
-= Transparent Hugepage Support =
-
-== Objective ==
-
-Performance critical computing applications dealing with large memory
-working sets are already running on top of libhugetlbfs and in turn
-hugetlbfs. Transparent Hugepage Support is an alternative means of
-using huge pages for the backing of virtual memory with huge pages
-that supports the automatic promotion and demotion of page sizes and
-without the shortcomings of hugetlbfs.
-
-Currently it only works for anonymous memory mappings and tmpfs/shmem.
-But in the future it can expand to other filesystems.
-
-The reason applications are running faster is because of two
-factors. The first factor is almost completely irrelevant and it's not
-of significant interest because it'll also have the downside of
-requiring larger clear-page copy-page in page faults which is a
-potentially negative effect. The first factor consists in taking a
-single page fault for each 2M virtual region touched by userland (so
-reducing the enter/exit kernel frequency by a 512 times factor). This
-only matters the first time the memory is accessed for the lifetime of
-a memory mapping. The second long lasting and much more important
-factor will affect all subsequent accesses to the memory for the whole
-runtime of the application. The second factor consist of two
-components: 1) the TLB miss will run faster (especially with
-virtualization using nested pagetables but almost always also on bare
-metal without virtualization) and 2) a single TLB entry will be
-mapping a much larger amount of virtual memory in turn reducing the
-number of TLB misses. With virtualization and nested pagetables the
-TLB can be mapped of larger size only if both KVM and the Linux guest
-are using hugepages but a significant speedup already happens if only
-one of the two is using hugepages just because of the fact the TLB
-miss is going to run faster.
-
-== Design ==
-
-- "graceful fallback": mm components which don't have transparent hugepage
-  knowledge fall back to breaking huge pmd mapping into table of ptes and,
-  if necessary, split a transparent hugepage. Therefore these components
-  can continue working on the regular pages or regular pte mappings.
-
-- if a hugepage allocation fails because of memory fragmentation,
-  regular pages should be gracefully allocated instead and mixed in
-  the same vma without any failure or significant delay and without
-  userland noticing
-
-- if some task quits and more hugepages become available (either
-  immediately in the buddy or through the VM), guest physical memory
-  backed by regular pages should be relocated on hugepages
-  automatically (with khugepaged)
-
-- it doesn't require memory reservation and in turn it uses hugepages
-  whenever possible (the only possible reservation here is kernelcore=
-  to avoid unmovable pages to fragment all the memory but such a tweak
-  is not specific to transparent hugepage support and it's a generic
-  feature that applies to all dynamic high order allocations in the
-  kernel)
-
-Transparent Hugepage Support maximizes the usefulness of free memory
-if compared to the reservation approach of hugetlbfs by allowing all
-unused memory to be used as cache or other movable (or even unmovable
-entities). It doesn't require reservation to prevent hugepage
-allocation failures to be noticeable from userland. It allows paging
-and all other advanced VM features to be available on the
-hugepages. It requires no modifications for applications to take
-advantage of it.
-
-Applications however can be further optimized to take advantage of
-this feature, like for example they've been optimized before to avoid
-a flood of mmap system calls for every malloc(4k). Optimizing userland
-is by far not mandatory and khugepaged already can take care of long
-lived page allocations even for hugepage unaware applications that
-deals with large amounts of memory.
-
-In certain cases when hugepages are enabled system wide, application
-may end up allocating more memory resources. An application may mmap a
-large region but only touch 1 byte of it, in that case a 2M page might
-be allocated instead of a 4k page for no good. This is why it's
-possible to disable hugepages system-wide and to only have them inside
-MADV_HUGEPAGE madvise regions.
-
-Embedded systems should enable hugepages only inside madvise regions
-to eliminate any risk of wasting any precious byte of memory and to
-only run faster.
-
-Applications that gets a lot of benefit from hugepages and that don't
-risk to lose memory by using hugepages, should use
-madvise(MADV_HUGEPAGE) on their critical mmapped regions.
-
-== sysfs ==
-
-Transparent Hugepage Support for anonymous memory can be entirely disabled
-(mostly for debugging purposes) or only enabled inside MADV_HUGEPAGE
-regions (to avoid the risk of consuming more memory resources) or enabled
-system wide. This can be achieved with one of:
-
-echo always >/sys/kernel/mm/transparent_hugepage/enabled
-echo madvise >/sys/kernel/mm/transparent_hugepage/enabled
-echo never >/sys/kernel/mm/transparent_hugepage/enabled
-
-It's also possible to limit defrag efforts in the VM to generate
-anonymous hugepages in case they're not immediately free to madvise
-regions or to never try to defrag memory and simply fallback to regular
-pages unless hugepages are immediately available. Clearly if we spend CPU
-time to defrag memory, we would expect to gain even more by the fact we
-use hugepages later instead of regular pages. This isn't always
-guaranteed, but it may be more likely in case the allocation is for a
-MADV_HUGEPAGE region.
-
-echo always >/sys/kernel/mm/transparent_hugepage/defrag
-echo defer >/sys/kernel/mm/transparent_hugepage/defrag
-echo defer+madvise >/sys/kernel/mm/transparent_hugepage/defrag
-echo madvise >/sys/kernel/mm/transparent_hugepage/defrag
-echo never >/sys/kernel/mm/transparent_hugepage/defrag
-
-"always" means that an application requesting THP will stall on allocation
-failure and directly reclaim pages and compact memory in an effort to
-allocate a THP immediately. This may be desirable for virtual machines
-that benefit heavily from THP use and are willing to delay the VM start
-to utilise them.
-
-"defer" means that an application will wake kswapd in the background
-to reclaim pages and wake kcompactd to compact memory so that THP is
-available in the near future. It's the responsibility of khugepaged
-to then install the THP pages later.
-
-"defer+madvise" will enter direct reclaim and compaction like "always", but
-only for regions that have used madvise(MADV_HUGEPAGE); all other regions
-will wake kswapd in the background to reclaim pages and wake kcompactd to
-compact memory so that THP is available in the near future.
-
-"madvise" will enter direct reclaim like "always" but only for regions
-that are have used madvise(MADV_HUGEPAGE). This is the default behaviour.
-
-"never" should be self-explanatory.
-
-By default kernel tries to use huge zero page on read page fault to
-anonymous mapping. It's possible to disable huge zero page by writing 0
-or enable it back by writing 1:
-
-echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page
-echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page
-
-Some userspace (such as a test program, or an optimized memory allocation
-library) may want to know the size (in bytes) of a transparent hugepage:
-
-cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size
-
-khugepaged will be automatically started when
-transparent_hugepage/enabled is set to "always" or "madvise, and it'll
-be automatically shutdown if it's set to "never".
-
-khugepaged runs usually at low frequency so while one may not want to
-invoke defrag algorithms synchronously during the page faults, it
-should be worth invoking defrag at least in khugepaged. However it's
-also possible to disable defrag in khugepaged by writing 0 or enable
-defrag in khugepaged by writing 1:
-
-echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
-echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
-
-You can also control how many pages khugepaged should scan at each
-pass:
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/pages_to_scan
-
-and how many milliseconds to wait in khugepaged between each pass (you
-can set this to 0 to run khugepaged at 100% utilization of one core):
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/scan_sleep_millisecs
-
-and how many milliseconds to wait in khugepaged if there's an hugepage
-allocation failure to throttle the next allocation attempt.
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/alloc_sleep_millisecs
-
-The khugepaged progress can be seen in the number of pages collapsed:
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/pages_collapsed
-
-for each pass:
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/full_scans
-
-max_ptes_none specifies how many extra small pages (that are
-not already mapped) can be allocated when collapsing a group
-of small pages into one large page.
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none
-
-A higher value leads to use additional memory for programs.
-A lower value leads to gain less thp performance. Value of
-max_ptes_none can waste cpu time very little, you can
-ignore it.
-
-max_ptes_swap specifies how many pages can be brought in from
-swap when collapsing a group of pages into a transparent huge page.
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap
-
-A higher value can cause excessive swap IO and waste
-memory. A lower value can prevent THPs from being
-collapsed, resulting fewer pages being collapsed into
-THPs, and lower memory access performance.
-
-== Boot parameter ==
-
-You can change the sysfs boot time defaults of Transparent Hugepage
-Support by passing the parameter "transparent_hugepage=always" or
-"transparent_hugepage=madvise" or "transparent_hugepage=never"
-(without "") to the kernel command line.
-
-== Hugepages in tmpfs/shmem ==
-
-You can control hugepage allocation policy in tmpfs with mount option
-"huge=". It can have following values:
-
-  - "always":
-    Attempt to allocate huge pages every time we need a new page;
-
-  - "never":
-    Do not allocate huge pages;
-
-  - "within_size":
-    Only allocate huge page if it will be fully within i_size.
-    Also respect fadvise()/madvise() hints;
-
-  - "advise:
-    Only allocate huge pages if requested with fadvise()/madvise();
-
-The default policy is "never".
-
-"mount -o remount,huge= /mountpoint" works fine after mount: remounting
-huge=never will not attempt to break up huge pages at all, just stop more
-from being allocated.
-
-There's also sysfs knob to control hugepage allocation policy for internal
-shmem mount: /sys/kernel/mm/transparent_hugepage/shmem_enabled. The mount
-is used for SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or
-MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem.
-
-In addition to policies listed above, shmem_enabled allows two further
-values:
-
-  - "deny":
-    For use in emergencies, to force the huge option off from
-    all mounts;
-  - "force":
-    Force the huge option on for all - very useful for testing;
-
-== Need of application restart ==
-
-The transparent_hugepage/enabled values and tmpfs mount option only affect
-future behavior. So to make them effective you need to restart any
-application that could have been using hugepages. This also applies to the
-regions registered in khugepaged.
-
-== Monitoring usage ==
-
-The number of anonymous transparent huge pages currently used by the
-system is available by reading the AnonHugePages field in /proc/meminfo.
-To identify what applications are using anonymous transparent huge pages,
-it is necessary to read /proc/PID/smaps and count the AnonHugePages fields
-for each mapping.
-
-The number of file transparent huge pages mapped to userspace is available
-by reading ShmemPmdMapped and ShmemHugePages fields in /proc/meminfo.
-To identify what applications are mapping file transparent huge pages, it
-is necessary to read /proc/PID/smaps and count the FileHugeMapped fields
-for each mapping.
-
-Note that reading the smaps file is expensive and reading it
-frequently will incur overhead.
-
-There are a number of counters in /proc/vmstat that may be used to
-monitor how successfully the system is providing huge pages for use.
-
-thp_fault_alloc is incremented every time a huge page is successfully
-	allocated to handle a page fault. This applies to both the
-	first time a page is faulted and for COW faults.
-
-thp_collapse_alloc is incremented by khugepaged when it has found
-	a range of pages to collapse into one huge page and has
-	successfully allocated a new huge page to store the data.
-
-thp_fault_fallback is incremented if a page fault fails to allocate
-	a huge page and instead falls back to using small pages.
-
-thp_collapse_alloc_failed is incremented if khugepaged found a range
-	of pages that should be collapsed into one huge page but failed
-	the allocation.
-
-thp_file_alloc is incremented every time a file huge page is successfully
-	allocated.
-
-thp_file_mapped is incremented every time a file huge page is mapped into
-	user address space.
-
-thp_split_page is incremented every time a huge page is split into base
-	pages. This can happen for a variety of reasons but a common
-	reason is that a huge page is old and is being reclaimed.
-	This action implies splitting all PMD the page mapped with.
-
-thp_split_page_failed is incremented if kernel fails to split huge
-	page. This can happen if the page was pinned by somebody.
-
-thp_deferred_split_page is incremented when a huge page is put onto split
-	queue. This happens when a huge page is partially unmapped and
-	splitting it would free up some memory. Pages on split queue are
-	going to be split under memory pressure.
-
-thp_split_pmd is incremented every time a PMD split into table of PTEs.
-	This can happen, for instance, when application calls mprotect() or
-	munmap() on part of huge page. It doesn't split huge page, only
-	page table entry.
-
-thp_zero_page_alloc is incremented every time a huge zero page is
-	successfully allocated. It includes allocations which where
-	dropped due race with other allocation. Note, it doesn't count
-	every map of the huge zero page, only its allocation.
-
-thp_zero_page_alloc_failed is incremented if kernel fails to allocate
-	huge zero page and falls back to using small pages.
-
-As the system ages, allocating huge pages may be expensive as the
-system uses memory compaction to copy data around memory to free a
-huge page for use. There are some counters in /proc/vmstat to help
-monitor this overhead.
-
-compact_stall is incremented every time a process stalls to run
-	memory compaction so that a huge page is free for use.
-
-compact_success is incremented if the system compacted memory and
-	freed a huge page for use.
-
-compact_fail is incremented if the system tries to compact memory
-	but failed.
-
-compact_pages_moved is incremented each time a page is moved. If
-	this value is increasing rapidly, it implies that the system
-	is copying a lot of data to satisfy the huge page allocation.
-	It is possible that the cost of copying exceeds any savings
-	from reduced TLB misses.
-
-compact_pagemigrate_failed is incremented when the underlying mechanism
-	for moving a page failed.
-
-compact_blocks_moved is incremented each time memory compaction examines
-	a huge page aligned range of pages.
-
-It is possible to establish how long the stalls were using the function
-tracer to record how long was spent in __alloc_pages_nodemask and
-using the mm_page_alloc tracepoint to identify which allocations were
-for huge pages.
-
-== get_user_pages and follow_page ==
-
-get_user_pages and follow_page if run on a hugepage, will return the
-head or tail pages as usual (exactly as they would do on
-hugetlbfs). Most gup users will only care about the actual physical
-address of the page and its temporary pinning to release after the I/O
-is complete, so they won't ever notice the fact the page is huge. But
-if any driver is going to mangle over the page structure of the tail
-page (like for checking page->mapping or other bits that are relevant
-for the head page and not the tail page), it should be updated to jump
-to check head page instead. Taking reference on any head/tail page would
-prevent page from being split by anyone.
-
-NOTE: these aren't new constraints to the GUP API, and they match the
-same constrains that applies to hugetlbfs too, so any driver capable
-of handling GUP on hugetlbfs will also work fine on transparent
-hugepage backed mappings.
-
-In case you can't handle compound pages if they're returned by
-follow_page, the FOLL_SPLIT bit can be specified as parameter to
-follow_page, so that it will split the hugepages before returning
-them. Migration for example passes FOLL_SPLIT as parameter to
-follow_page because it's not hugepage aware and in fact it can't work
-at all on hugetlbfs (but it instead works fine on transparent
-hugepages thanks to FOLL_SPLIT). migration simply can't deal with
-hugepages being returned (as it's not only checking the pfn of the
-page and pinning it during the copy but it pretends to migrate the
-memory in regular page sizes and with regular pte/pmd mappings).
-
-== Optimizing the applications ==
-
-To be guaranteed that the kernel will map a 2M page immediately in any
-memory region, the mmap region has to be hugepage naturally
-aligned. posix_memalign() can provide that guarantee.
-
-== Hugetlbfs ==
-
-You can use hugetlbfs on a kernel that has transparent hugepage
-support enabled just fine as always. No difference can be noted in
-hugetlbfs other than there will be less overall fragmentation. All
-usual features belonging to hugetlbfs are preserved and
-unaffected. libhugetlbfs will also work fine as usual.
-
-== Graceful fallback ==
-
-Code walking pagetables but unaware about huge pmds can simply call
-split_huge_pmd(vma, pmd, addr) where the pmd is the one returned by
-pmd_offset. It's trivial to make the code transparent hugepage aware
-by just grepping for "pmd_offset" and adding split_huge_pmd where
-missing after pmd_offset returns the pmd. Thanks to the graceful
-fallback design, with a one liner change, you can avoid to write
-hundred if not thousand of lines of complex code to make your code
-hugepage aware.
-
-If you're not walking pagetables but you run into a physical hugepage
-but you can't handle it natively in your code, you can split it by
-calling split_huge_page(page). This is what the Linux VM does before
-it tries to swapout the hugepage for example. split_huge_page() can fail
-if the page is pinned and you must handle this correctly.
-
-Example to make mremap.c transparent hugepage aware with a one liner
-change:
-
-diff --git a/mm/mremap.c b/mm/mremap.c
---- a/mm/mremap.c
-+++ b/mm/mremap.c
-@@ -41,6 +41,7 @@ static pmd_t *get_old_pmd(struct mm_stru
-		return NULL;
-
-	pmd = pmd_offset(pud, addr);
-+	split_huge_pmd(vma, pmd, addr);
-	if (pmd_none_or_clear_bad(pmd))
-		return NULL;
-
-== Locking in hugepage aware code ==
-
-We want as much code as possible hugepage aware, as calling
-split_huge_page() or split_huge_pmd() has a cost.
-
-To make pagetable walks huge pmd aware, all you need to do is to call
-pmd_trans_huge() on the pmd returned by pmd_offset. You must hold the
-mmap_sem in read (or write) mode to be sure an huge pmd cannot be
-created from under you by khugepaged (khugepaged collapse_huge_page
-takes the mmap_sem in write mode in addition to the anon_vma lock). If
-pmd_trans_huge returns false, you just fallback in the old code
-paths. If instead pmd_trans_huge returns true, you have to take the
-page table lock (pmd_lock()) and re-run pmd_trans_huge. Taking the
-page table lock will prevent the huge pmd to be converted into a
-regular pmd from under you (split_huge_pmd can run in parallel to the
-pagetable walk). If the second pmd_trans_huge returns false, you
-should just drop the page table lock and fallback to the old code as
-before. Otherwise you can proceed to process the huge pmd and the
-hugepage natively. Once finished you can drop the page table lock.
-
-== Refcounts and transparent huge pages ==
-
-Refcounting on THP is mostly consistent with refcounting on other compound
-pages:
-
-  - get_page()/put_page() and GUP operate in head page's ->_refcount.
-
-  - ->_refcount in tail pages is always zero: get_page_unless_zero() never
-    succeed on tail pages.
-
-  - map/unmap of the pages with PTE entry increment/decrement ->_mapcount
-    on relevant sub-page of the compound page.
-
-  - map/unmap of the whole compound page accounted in compound_mapcount
-    (stored in first tail page). For file huge pages, we also increment
-    ->_mapcount of all sub-pages in order to have race-free detection of
-    last unmap of subpages.
-
-PageDoubleMap() indicates that the page is *possibly* mapped with PTEs.
-
-For anonymous pages PageDoubleMap() also indicates ->_mapcount in all
-subpages is offset up by one. This additional reference is required to
-get race-free detection of unmap of subpages when we have them mapped with
-both PMDs and PTEs.
-
-This is optimization required to lower overhead of per-subpage mapcount
-tracking. The alternative is alter ->_mapcount in all subpages on each
-map/unmap of the whole compound page.
-
-For anonymous pages, we set PG_double_map when a PMD of the page got split
-for the first time, but still have PMD mapping. The additional references
-go away with last compound_mapcount.
-
-File pages get PG_double_map set on first map of the page with PTE and
-goes away when the page gets evicted from page cache.
-
-split_huge_page internally has to distribute the refcounts in the head
-page to the tail pages before clearing all PG_head/tail bits from the page
-structures. It can be done easily for refcounts taken by page table
-entries. But we don't have enough information on how to distribute any
-additional pins (i.e. from get_user_pages). split_huge_page() fails any
-requests to split pinned huge page: it expects page count to be equal to
-sum of mapcount of all sub-pages plus one (split_huge_page caller must
-have reference for head page).
-
-split_huge_page uses migration entries to stabilize page->_refcount and
-page->_mapcount of anonymous pages. File pages just got unmapped.
-
-We safe against physical memory scanners too: the only legitimate way
-scanner can get reference to a page is get_page_unless_zero().
-
-All tail pages have zero ->_refcount until atomic_add(). This prevents the
-scanner from getting a reference to the tail page up to that point. After the
-atomic_add() we don't care about the ->_refcount value. We already known how
-many references should be uncharged from the head page.
-
-For head page get_page_unless_zero() will succeed and we don't mind. It's
-clear where reference should go after split: it will stay on head page.
-
-Note that split_huge_pmd() doesn't have any limitation on refcounting:
-pmd can be split at any point and never fails.
-
-== Partial unmap and deferred_split_huge_page() ==
-
-Unmapping part of THP (with munmap() or other way) is not going to free
-memory immediately. Instead, we detect that a subpage of THP is not in use
-in page_remove_rmap() and queue the THP for splitting if memory pressure
-comes. Splitting will free up unused subpages.
-
-Splitting the page right away is not an option due to locking context in
-the place where we can detect partial unmap. It's also might be
-counterproductive since in many cases partial unmap happens during exit(2) if
-a THP crosses a VMA boundary.
-
-Function deferred_split_huge_page() is used to queue page for splitting.
-The splitting itself will happen when we get memory pressure via shrinker
-interface.
diff --git a/Documentation/vm/unevictable-lru.txt b/Documentation/vm/unevictable-lru.rst
index e14718572476..fdd84cb8d511 100644
--- a/Documentation/vm/unevictable-lru.txt
+++ b/Documentation/vm/unevictable-lru.rst
@@ -1,37 +1,13 @@
-			==============================
-			UNEVICTABLE LRU INFRASTRUCTURE
-			==============================
-
-========
-CONTENTS
-========
-
- (*) The Unevictable LRU
-
-     - The unevictable page list.
-     - Memory control group interaction.
-     - Marking address spaces unevictable.
-     - Detecting Unevictable Pages.
-     - vmscan's handling of unevictable pages.
-
- (*) mlock()'d pages.
-
-     - History.
-     - Basic management.
-     - mlock()/mlockall() system call handling.
-     - Filtering special vmas.
-     - munlock()/munlockall() system call handling.
-     - Migrating mlocked pages.
-     - Compacting mlocked pages.
-     - mmap(MAP_LOCKED) system call handling.
-     - munmap()/exit()/exec() system call handling.
-     - try_to_unmap().
-     - try_to_munlock() reverse map scan.
-     - Page reclaim in shrink_*_list().
+.. _unevictable_lru:
 
+==============================
+Unevictable LRU Infrastructure
+==============================
 
-============
-INTRODUCTION
+.. contents:: :local:
+
+
+Introduction
 ============
 
 This document describes the Linux memory manager's "Unevictable LRU"
@@ -46,8 +22,8 @@ details - the "what does it do?" - by reading the code.  One hopes that the
 descriptions below add value by provide the answer to "why does it do that?".
 
 
-===================
-THE UNEVICTABLE LRU
+
+The Unevictable LRU
 ===================
 
 The Unevictable LRU facility adds an additional LRU list to track unevictable
@@ -66,17 +42,17 @@ completely unresponsive.
 
 The unevictable list addresses the following classes of unevictable pages:
 
- (*) Those owned by ramfs.
+ * Those owned by ramfs.
 
- (*) Those mapped into SHM_LOCK'd shared memory regions.
+ * Those mapped into SHM_LOCK'd shared memory regions.
 
- (*) Those mapped into VM_LOCKED [mlock()ed] VMAs.
+ * Those mapped into VM_LOCKED [mlock()ed] VMAs.
 
 The infrastructure may also be able to handle other conditions that make pages
 unevictable, either by definition or by circumstance, in the future.
 
 
-THE UNEVICTABLE PAGE LIST
+The Unevictable Page List
 -------------------------
 
 The Unevictable LRU infrastructure consists of an additional, per-zone, LRU list
@@ -118,7 +94,7 @@ the unevictable list when one task has the page isolated from the LRU and other
 tasks are changing the "evictability" state of the page.
 
 
-MEMORY CONTROL GROUP INTERACTION
+Memory Control Group Interaction
 --------------------------------
 
 The unevictable LRU facility interacts with the memory control group [aka
@@ -144,7 +120,9 @@ effects:
      the control group to thrash or to OOM-kill tasks.
 
 
-MARKING ADDRESS SPACES UNEVICTABLE
+.. _mark_addr_space_unevict:
+
+Marking Address Spaces Unevictable
 ----------------------------------
 
 For facilities such as ramfs none of the pages attached to the address space
@@ -152,15 +130,15 @@ may be evicted.  To prevent eviction of any such pages, the AS_UNEVICTABLE
 address space flag is provided, and this can be manipulated by a filesystem
 using a number of wrapper functions:
 
- (*) void mapping_set_unevictable(struct address_space *mapping);
+ * ``void mapping_set_unevictable(struct address_space *mapping);``
 
 	Mark the address space as being completely unevictable.
 
- (*) void mapping_clear_unevictable(struct address_space *mapping);
+ * ``void mapping_clear_unevictable(struct address_space *mapping);``
 
 	Mark the address space as being evictable.
 
- (*) int mapping_unevictable(struct address_space *mapping);
+ * ``int mapping_unevictable(struct address_space *mapping);``
 
 	Query the address space, and return true if it is completely
 	unevictable.
@@ -177,12 +155,13 @@ These are currently used in two places in the kernel:
      ensure they're in memory.
 
 
-DETECTING UNEVICTABLE PAGES
+Detecting Unevictable Pages
 ---------------------------
 
 The function page_evictable() in vmscan.c determines whether a page is
-evictable or not using the query function outlined above [see section "Marking
-address spaces unevictable"] to check the AS_UNEVICTABLE flag.
+evictable or not using the query function outlined above [see section
+:ref:`Marking address spaces unevictable <mark_addr_space_unevict>`]
+to check the AS_UNEVICTABLE flag.
 
 For address spaces that are so marked after being populated (as SHM regions
 might be), the lock action (eg: SHM_LOCK) can be lazy, and need not populate
@@ -202,7 +181,7 @@ flag, PG_mlocked (as wrapped by PageMlocked()), which is set when a page is
 faulted into a VM_LOCKED vma, or found in a vma being VM_LOCKED.
 
 
-VMSCAN'S HANDLING OF UNEVICTABLE PAGES
+Vmscan's Handling of Unevictable Pages
 --------------------------------------
 
 If unevictable pages are culled in the fault path, or moved to the unevictable
@@ -233,8 +212,7 @@ extra evictabilty checks should not occur in the majority of calls to
 putback_lru_page().
 
 
-=============
-MLOCKED PAGES
+MLOCKED Pages
 =============
 
 The unevictable page list is also useful for mlock(), in addition to ramfs and
@@ -242,7 +220,7 @@ SYSV SHM.  Note that mlock() is only available in CONFIG_MMU=y situations; in
 NOMMU situations, all mappings are effectively mlocked.
 
 
-HISTORY
+History
 -------
 
 The "Unevictable mlocked Pages" infrastructure is based on work originally
@@ -263,7 +241,7 @@ replaced by walking the reverse map to determine whether any VM_LOCKED VMAs
 mapped the page.  More on this below.
 
 
-BASIC MANAGEMENT
+Basic Management
 ----------------
 
 mlocked pages - pages mapped into a VM_LOCKED VMA - are a class of unevictable
@@ -304,10 +282,10 @@ mlocked pages become unlocked and rescued from the unevictable list when:
  (4) before a page is COW'd in a VM_LOCKED VMA.
 
 
-mlock()/mlockall() SYSTEM CALL HANDLING
+mlock()/mlockall() System Call Handling
 ---------------------------------------
 
-Both [do_]mlock() and [do_]mlockall() system call handlers call mlock_fixup()
+Both [do\_]mlock() and [do\_]mlockall() system call handlers call mlock_fixup()
 for each VMA in the range specified by the call.  In the case of mlockall(),
 this is the entire active address space of the task.  Note that mlock_fixup()
 is used for both mlocking and munlocking a range of memory.  A call to mlock()
@@ -351,7 +329,7 @@ mlock_vma_page() is unable to isolate the page from the LRU, vmscan will handle
 it later if and when it attempts to reclaim the page.
 
 
-FILTERING SPECIAL VMAS
+Filtering Special VMAs
 ----------------------
 
 mlock_fixup() filters several classes of "special" VMAs:
@@ -379,8 +357,9 @@ VM_LOCKED flag.  Therefore, we won't have to deal with them later during
 munlock(), munmap() or task exit.  Neither does mlock_fixup() account these
 VMAs against the task's "locked_vm".
 
+.. _munlock_munlockall_handling:
 
-munlock()/munlockall() SYSTEM CALL HANDLING
+munlock()/munlockall() System Call Handling
 -------------------------------------------
 
 The munlock() and munlockall() system calls are handled by the same functions -
@@ -426,7 +405,7 @@ This is fine, because we'll catch it later if and if vmscan tries to reclaim
 the page.  This should be relatively rare.
 
 
-MIGRATING MLOCKED PAGES
+Migrating MLOCKED Pages
 -----------------------
 
 A page that is being migrated has been isolated from the LRU lists and is held
@@ -451,7 +430,7 @@ list because of a race between munlock and migration, page migration uses the
 putback_lru_page() function to add migrated pages back to the LRU.
 
 
-COMPACTING MLOCKED PAGES
+Compacting MLOCKED Pages
 ------------------------
 
 The unevictable LRU can be scanned for compactable regions and the default
@@ -461,7 +440,7 @@ unevictable LRU is enabled, the work of compaction is mostly handled by
 the page migration code and the same work flow as described in MIGRATING
 MLOCKED PAGES will apply.
 
-MLOCKING TRANSPARENT HUGE PAGES
+MLOCKING Transparent Huge Pages
 -------------------------------
 
 A transparent huge page is represented by a single entry on an LRU list.
@@ -483,7 +462,7 @@ to unevictable LRU and the rest can be reclaimed.
 
 See also comment in follow_trans_huge_pmd().
 
-mmap(MAP_LOCKED) SYSTEM CALL HANDLING
+mmap(MAP_LOCKED) System Call Handling
 -------------------------------------
 
 In addition the mlock()/mlockall() system calls, an application can request
@@ -514,7 +493,7 @@ memory range accounted as locked_vm, as the protections could be changed later
 and pages allocated into that region.
 
 
-munmap()/exit()/exec() SYSTEM CALL HANDLING
+munmap()/exit()/exec() System Call Handling
 -------------------------------------------
 
 When unmapping an mlocked region of memory, whether by an explicit call to
@@ -568,16 +547,18 @@ munlock or munmap system calls, mm teardown (munlock_vma_pages_all), reclaim,
 holepunching, and truncation of file pages and their anonymous COWed pages.
 
 
-try_to_munlock() REVERSE MAP SCAN
+try_to_munlock() Reverse Map Scan
 ---------------------------------
 
- [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the
-     page_referenced() reverse map walker.
+.. warning::
+   [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the
+   page_referenced() reverse map walker.
 
-When munlock_vma_page() [see section "munlock()/munlockall() System Call
-Handling" above] tries to munlock a page, it needs to determine whether or not
-the page is mapped by any VM_LOCKED VMA without actually attempting to unmap
-all PTEs from the page.  For this purpose, the unevictable/mlock infrastructure
+When munlock_vma_page() [see section :ref:`munlock()/munlockall() System Call
+Handling <munlock_munlockall_handling>` above] tries to munlock a
+page, it needs to determine whether or not the page is mapped by any
+VM_LOCKED VMA without actually attempting to unmap all PTEs from the
+page.  For this purpose, the unevictable/mlock infrastructure
 introduced a variant of try_to_unmap() called try_to_munlock().
 
 try_to_munlock() calls the same functions as try_to_unmap() for anonymous and
@@ -595,7 +576,7 @@ large region or tearing down a large address space that has been mlocked via
 mlockall(), overall this is a fairly rare event.
 
 
-PAGE RECLAIM IN shrink_*_list()
+Page Reclaim in shrink_*_list()
 -------------------------------
 
 shrink_active_list() culls any obviously unevictable pages - i.e.
diff --git a/Documentation/vm/z3fold.txt b/Documentation/vm/z3fold.rst
index 38e4dac810b6..224e3c61d686 100644
--- a/Documentation/vm/z3fold.txt
+++ b/Documentation/vm/z3fold.rst
@@ -1,5 +1,8 @@
+.. _z3fold:
+
+======
 z3fold
-------
+======
 
 z3fold is a special purpose allocator for storing compressed pages.
 It is designed to store up to three compressed pages per physical page.
@@ -7,6 +10,7 @@ It is a zbud derivative which allows for higher compression
 ratio keeping the simplicity and determinism of its predecessor.
 
 The main differences between z3fold and zbud are:
+
 * unlike zbud, z3fold allows for up to PAGE_SIZE allocations
 * z3fold can hold up to 3 compressed pages in its page
 * z3fold doesn't export any API itself and is thus intended to be used
diff --git a/Documentation/vm/zsmalloc.txt b/Documentation/vm/zsmalloc.rst
index 64ed63c4f69d..6e79893d6132 100644
--- a/Documentation/vm/zsmalloc.txt
+++ b/Documentation/vm/zsmalloc.rst
@@ -1,5 +1,8 @@
+.. _zsmalloc:
+
+========
 zsmalloc
---------
+========
 
 This allocator is designed for use with zram. Thus, the allocator is
 supposed to work well under low memory conditions. In particular, it
@@ -31,40 +34,49 @@ be mapped using zs_map_object() to get a usable pointer and subsequently
 unmapped using zs_unmap_object().
 
 stat
-----
+====
 
 With CONFIG_ZSMALLOC_STAT, we could see zsmalloc internal information via
-/sys/kernel/debug/zsmalloc/<user name>. Here is a sample of stat output:
+``/sys/kernel/debug/zsmalloc/<user name>``. Here is a sample of stat output::
 
-# cat /sys/kernel/debug/zsmalloc/zram0/classes
+ # cat /sys/kernel/debug/zsmalloc/zram0/classes
 
  class  size almost_full almost_empty obj_allocated   obj_used pages_used pages_per_zspage
-    ..
-    ..
+    ...
+    ...
      9   176           0            1           186        129          8                4
     10   192           1            0          2880       2872        135                3
     11   208           0            1           819        795         42                2
     12   224           0            1           219        159         12                4
-    ..
-    ..
+    ...
+    ...
+
 
+class
+	index
+size
+	object size zspage stores
+almost_empty
+	the number of ZS_ALMOST_EMPTY zspages(see below)
+almost_full
+	the number of ZS_ALMOST_FULL zspages(see below)
+obj_allocated
+	the number of objects allocated
+obj_used
+	the number of objects allocated to the user
+pages_used
+	the number of pages allocated for the class
+pages_per_zspage
+	the number of 0-order pages to make a zspage
 
-class: index
-size: object size zspage stores
-almost_empty: the number of ZS_ALMOST_EMPTY zspages(see below)
-almost_full: the number of ZS_ALMOST_FULL zspages(see below)
-obj_allocated: the number of objects allocated
-obj_used: the number of objects allocated to the user
-pages_used: the number of pages allocated for the class
-pages_per_zspage: the number of 0-order pages to make a zspage
+We assign a zspage to ZS_ALMOST_EMPTY fullness group when n <= N / f, where
 
-We assign a zspage to ZS_ALMOST_EMPTY fullness group when:
-      n <= N / f, where
-n = number of allocated objects
-N = total number of objects zspage can store
-f = fullness_threshold_frac(ie, 4 at the moment)
+* n = number of allocated objects
+* N = total number of objects zspage can store
+* f = fullness_threshold_frac(ie, 4 at the moment)
 
 Similarly, we assign zspage to:
-      ZS_ALMOST_FULL  when n > N / f
-      ZS_EMPTY        when n == 0
-      ZS_FULL         when n == N
+
+* ZS_ALMOST_FULL  when n > N / f
+* ZS_EMPTY        when n == 0
+* ZS_FULL         when n == N
diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.rst
index 0b3a1148f9f0..1444ecd40911 100644
--- a/Documentation/vm/zswap.txt
+++ b/Documentation/vm/zswap.rst
@@ -1,4 +1,11 @@
-Overview:
+.. _zswap:
+
+=====
+zswap
+=====
+
+Overview
+========
 
 Zswap is a lightweight compressed cache for swap pages. It takes pages that are
 in the process of being swapped out and attempts to compress them into a
@@ -7,32 +14,34 @@ for potentially reduced swap I/O.  This trade-off can also result in a
 significant performance improvement if reads from the compressed cache are
 faster than reads from a swap device.
 
-NOTE: Zswap is a new feature as of v3.11 and interacts heavily with memory
-reclaim.  This interaction has not been fully explored on the large set of
-potential configurations and workloads that exist.  For this reason, zswap
-is a work in progress and should be considered experimental.
+.. note::
+   Zswap is a new feature as of v3.11 and interacts heavily with memory
+   reclaim.  This interaction has not been fully explored on the large set of
+   potential configurations and workloads that exist.  For this reason, zswap
+   is a work in progress and should be considered experimental.
+
+   Some potential benefits:
 
-Some potential benefits:
 * Desktop/laptop users with limited RAM capacities can mitigate the
-    performance impact of swapping.
+  performance impact of swapping.
 * Overcommitted guests that share a common I/O resource can
-    dramatically reduce their swap I/O pressure, avoiding heavy handed I/O
-    throttling by the hypervisor. This allows more work to get done with less
-    impact to the guest workload and guests sharing the I/O subsystem
+  dramatically reduce their swap I/O pressure, avoiding heavy handed I/O
+  throttling by the hypervisor. This allows more work to get done with less
+  impact to the guest workload and guests sharing the I/O subsystem
 * Users with SSDs as swap devices can extend the life of the device by
-    drastically reducing life-shortening writes.
+  drastically reducing life-shortening writes.
 
 Zswap evicts pages from compressed cache on an LRU basis to the backing swap
 device when the compressed pool reaches its size limit.  This requirement had
 been identified in prior community discussions.
 
 Zswap is disabled by default but can be enabled at boot time by setting
-the "enabled" attribute to 1 at boot time. ie: zswap.enabled=1.  Zswap
+the ``enabled`` attribute to 1 at boot time. ie: ``zswap.enabled=1``.  Zswap
 can also be enabled and disabled at runtime using the sysfs interface.
 An example command to enable zswap at runtime, assuming sysfs is mounted
-at /sys, is:
+at ``/sys``, is::
 
-echo 1 > /sys/module/zswap/parameters/enabled
+	echo 1 > /sys/module/zswap/parameters/enabled
 
 When zswap is disabled at runtime it will stop storing pages that are
 being swapped out.  However, it will _not_ immediately write out or fault
@@ -43,7 +52,8 @@ pages out of the compressed pool, a swapoff on the swap device(s) will
 fault back into memory all swapped out pages, including those in the
 compressed pool.
 
-Design:
+Design
+======
 
 Zswap receives pages for compression through the Frontswap API and is able to
 evict pages from its own compressed pool on an LRU basis and write them back to
@@ -53,12 +63,12 @@ Zswap makes use of zpool for the managing the compressed memory pool.  Each
 allocation in zpool is not directly accessible by address.  Rather, a handle is
 returned by the allocation routine and that handle must be mapped before being
 accessed.  The compressed memory pool grows on demand and shrinks as compressed
-pages are freed.  The pool is not preallocated.  By default, a zpool of type
-zbud is created, but it can be selected at boot time by setting the "zpool"
-attribute, e.g. zswap.zpool=zbud.  It can also be changed at runtime using the
-sysfs "zpool" attribute, e.g.
+pages are freed.  The pool is not preallocated.  By default, a zpool
+of type zbud is created, but it can be selected at boot time by
+setting the ``zpool`` attribute, e.g. ``zswap.zpool=zbud``. It can
+also be changed at runtime using the sysfs ``zpool`` attribute, e.g.::
 
-echo zbud > /sys/module/zswap/parameters/zpool
+	echo zbud > /sys/module/zswap/parameters/zpool
 
 The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which
 means the compression ratio will always be 2:1 or worse (because of half-full
@@ -83,14 +93,16 @@ via frontswap, to free the compressed entry.
 
 Zswap seeks to be simple in its policies.  Sysfs attributes allow for one user
 controlled policy:
+
 * max_pool_percent - The maximum percentage of memory that the compressed
-    pool can occupy.
+  pool can occupy.
 
-The default compressor is lzo, but it can be selected at boot time by setting
-the “compressor� attribute, e.g. zswap.compressor=lzo.  It can also be changed
-at runtime using the sysfs "compressor" attribute, e.g.
+The default compressor is lzo, but it can be selected at boot time by
+setting the ``compressor`` attribute, e.g. ``zswap.compressor=lzo``.
+It can also be changed at runtime using the sysfs "compressor"
+attribute, e.g.::
 
-echo lzo > /sys/module/zswap/parameters/compressor
+	echo lzo > /sys/module/zswap/parameters/compressor
 
 When the zpool and/or compressor parameter is changed at runtime, any existing
 compressed pages are not modified; they are left in their own zpool.  When a
@@ -106,11 +118,12 @@ compressed length of the page is set to zero and the pattern or same-filled
 value is stored.
 
 Same-value filled pages identification feature is enabled by default and can be
-disabled at boot time by setting the "same_filled_pages_enabled" attribute to 0,
-e.g. zswap.same_filled_pages_enabled=0. It can also be enabled and disabled at
-runtime using the sysfs "same_filled_pages_enabled" attribute, e.g.
+disabled at boot time by setting the ``same_filled_pages_enabled`` attribute
+to 0, e.g. ``zswap.same_filled_pages_enabled=0``. It can also be enabled and
+disabled at runtime using the sysfs ``same_filled_pages_enabled``
+attribute, e.g.::
 
-echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled
+	echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled
 
 When zswap same-filled page identification is disabled at runtime, it will stop
 checking for the same-value filled pages during store operation. However, the
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index 71c30984e94d..a16aa2113840 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -17,12 +17,14 @@ MBA (Memory Bandwidth Allocation) - "mba"
 
 To use the feature mount the file system:
 
- # mount -t resctrl resctrl [-o cdp[,cdpl2]] /sys/fs/resctrl
+ # mount -t resctrl resctrl [-o cdp[,cdpl2][,mba_MBps]] /sys/fs/resctrl
 
 mount options are:
 
 "cdp": Enable code/data prioritization in L3 cache allocations.
 "cdpl2": Enable code/data prioritization in L2 cache allocations.
+"mba_MBps": Enable the MBA Software Controller(mba_sc) to specify MBA
+ bandwidth in MBps
 
 L2 and L3 CDP are controlled seperately.
 
@@ -270,10 +272,11 @@ and 0xA are not.  On a system with a 20-bit mask each bit represents 5%
 of the capacity of the cache. You could partition the cache into four
 equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
-Memory bandwidth(b/w) percentage
---------------------------------
-For Memory b/w resource, user controls the resource by indicating the
-percentage of total memory b/w.
+Memory bandwidth Allocation and monitoring
+------------------------------------------
+
+For Memory bandwidth resource, by default the user controls the resource
+by indicating the percentage of total memory bandwidth.
 
 The minimum bandwidth percentage value for each cpu model is predefined
 and can be looked up through "info/MB/min_bandwidth". The bandwidth
@@ -285,7 +288,47 @@ to the next control step available on the hardware.
 The bandwidth throttling is a core specific mechanism on some of Intel
 SKUs. Using a high bandwidth and a low bandwidth setting on two threads
 sharing a core will result in both threads being throttled to use the
-low bandwidth.
+low bandwidth. The fact that Memory bandwidth allocation(MBA) is a core
+specific mechanism where as memory bandwidth monitoring(MBM) is done at
+the package level may lead to confusion when users try to apply control
+via the MBA and then monitor the bandwidth to see if the controls are
+effective. Below are such scenarios:
+
+1. User may *not* see increase in actual bandwidth when percentage
+   values are increased:
+
+This can occur when aggregate L2 external bandwidth is more than L3
+external bandwidth. Consider an SKL SKU with 24 cores on a package and
+where L2 external  is 10GBps (hence aggregate L2 external bandwidth is
+240GBps) and L3 external bandwidth is 100GBps. Now a workload with '20
+threads, having 50% bandwidth, each consuming 5GBps' consumes the max L3
+bandwidth of 100GBps although the percentage value specified is only 50%
+<< 100%. Hence increasing the bandwidth percentage will not yeild any
+more bandwidth. This is because although the L2 external bandwidth still
+has capacity, the L3 external bandwidth is fully used. Also note that
+this would be dependent on number of cores the benchmark is run on.
+
+2. Same bandwidth percentage may mean different actual bandwidth
+   depending on # of threads:
+
+For the same SKU in #1, a 'single thread, with 10% bandwidth' and '4
+thread, with 10% bandwidth' can consume upto 10GBps and 40GBps although
+they have same percentage bandwidth of 10%. This is simply because as
+threads start using more cores in an rdtgroup, the actual bandwidth may
+increase or vary although user specified bandwidth percentage is same.
+
+In order to mitigate this and make the interface more user friendly,
+resctrl added support for specifying the bandwidth in MBps as well.  The
+kernel underneath would use a software feedback mechanism or a "Software
+Controller(mba_sc)" which reads the actual bandwidth using MBM counters
+and adjust the memowy bandwidth percentages to ensure
+
+	"actual bandwidth < user specified bandwidth".
+
+By default, the schemata would take the bandwidth percentage values
+where as user can switch to the "MBA software controller" mode using
+a mount option 'mba_MBps'. The schemata format is specified in the below
+sections.
 
 L3 schemata file details (code and data prioritization disabled)
 ----------------------------------------------------------------
@@ -308,13 +351,20 @@ schemata format is always:
 
 	L2:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
 
-Memory b/w Allocation details
------------------------------
+Memory bandwidth Allocation (default mode)
+------------------------------------------
 
 Memory b/w domain is L3 cache.
 
 	MB:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;...
 
+Memory bandwidth Allocation specified in MBps
+---------------------------------------------
+
+Memory bandwidth domain is L3 cache.
+
+	MB:<cache_id0>=bw_MBps0;<cache_id1>=bw_MBps1;...
+
 Reading/writing the schemata file
 ---------------------------------
 Reading the schemata file will show the state of all resources
@@ -358,6 +408,15 @@ allocations can overlap or not. The allocations specifies the maximum
 b/w that the group may be able to use and the system admin can configure
 the b/w accordingly.
 
+If the MBA is specified in MB(megabytes) then user can enter the max b/w in MB
+rather than the percentage values.
+
+# echo "L3:0=3;1=c\nMB:0=1024;1=500" > /sys/fs/resctrl/p0/schemata
+# echo "L3:0=3;1=3\nMB:0=1024;1=500" > /sys/fs/resctrl/p1/schemata
+
+In the above example the tasks in "p1" and "p0" on socket 0 would use a max b/w
+of 1024MB where as on socket 1 they would use 500MB.
+
 Example 2
 ---------
 Again two sockets, but this time with a more realistic 20-bit mask.
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index b297c48389b9..8d109ef67ab6 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -187,9 +187,9 @@ PCI
 
 IOMMU (input/output memory management unit)
 
- Currently four x86-64 PCI-DMA mapping implementations exist:
+ Multiple x86-64 PCI-DMA mapping implementations exist, for example:
 
-   1. <arch/x86_64/kernel/pci-nommu.c>: use no hardware/software IOMMU at all
+   1. <lib/dma-direct.c>: use no hardware/software IOMMU at all
       (e.g. because you have < 3 GB memory).
       Kernel boot message: "PCI-DMA: Disabling IOMMU"
 
@@ -208,7 +208,7 @@ IOMMU (input/output memory management unit)
       Kernel boot message: "PCI-DMA: Using Calgary IOMMU"
 
  iommu=[<size>][,noagp][,off][,force][,noforce][,leak[=<nr_of_leak_pages>]
-	[,memaper[=<order>]][,merge][,forcesac][,fullflush][,nomerge]
+	[,memaper[=<order>]][,merge][,fullflush][,nomerge]
 	[,noaperture][,calgary]
 
   General iommu options:
@@ -235,14 +235,7 @@ IOMMU (input/output memory management unit)
                        (experimental).
     nomerge            Don't do scatter-gather (SG) merging.
     noaperture         Ask the IOMMU not to touch the aperture for AGP.
-    forcesac           Force single-address cycle (SAC) mode for masks <40bits
-                       (experimental).
     noagp              Don't initialize the AGP driver and use full aperture.
-    allowdac           Allow double-address cycle (DAC) mode, i.e. DMA >4GB.
-                       DAC is used with 32-bit PCI to push a 64-bit address in
-                       two cycles. When off all DMA over >4GB is forced through
-                       an IOMMU or software bounce buffering.
-    nodac              Forbid DAC mode, i.e. DMA >4GB.
     panic              Always panic when IOMMU overflows.
     calgary            Use the Calgary IOMMU if it is available
 
diff --git a/Kconfig b/Kconfig
index 8c4c1cb0f9cd..a90d9f9e268b 100644
--- a/Kconfig
+++ b/Kconfig
@@ -3,10 +3,10 @@
 # For a description of the syntax of this configuration file,
 # see Documentation/kbuild/kconfig-language.txt.
 #
-mainmenu "Linux/$ARCH $KERNELVERSION Kernel Configuration"
+mainmenu "Linux/$(ARCH) $(KERNELVERSION) Kernel Configuration"
 
-config SRCARCH
-	string
-	option env="SRCARCH"
+comment "Compiler: $(CC_VERSION_TEXT)"
 
-source "arch/$SRCARCH/Kconfig"
+source "scripts/Kconfig.include"
+
+source "arch/$(SRCARCH)/Kconfig"
diff --git a/LICENSES/exceptions/Linux-syscall-note b/LICENSES/exceptions/Linux-syscall-note
index 6b60b61be4e9..9abdad71fafd 100644
--- a/LICENSES/exceptions/Linux-syscall-note
+++ b/LICENSES/exceptions/Linux-syscall-note
@@ -1,6 +1,6 @@
 SPDX-Exception-Identifier: Linux-syscall-note
 SPDX-URL: https://spdx.org/licenses/Linux-syscall-note.html
-SPDX-Licenses: GPL-2.0, GPL-2.0+, GPL-1.0+, LGPL-2.0, LGPL-2.0+, LGPL-2.1, LGPL-2.1+
+SPDX-Licenses: GPL-2.0, GPL-2.0+, GPL-1.0+, LGPL-2.0, LGPL-2.0+, LGPL-2.1, LGPL-2.1+, GPL-2.0-only, GPL-2.0-or-later
 Usage-Guide:
   This exception is used together with one of the above SPDX-Licenses
   to mark user space API (uapi) header files so they can be included
diff --git a/LICENSES/other/Apache-2.0 b/LICENSES/other/Apache-2.0
new file mode 100644
index 000000000000..7cd903f573e5
--- /dev/null
+++ b/LICENSES/other/Apache-2.0
@@ -0,0 +1,183 @@
+Valid-License-Identifier: Apache-2.0
+SPDX-URL: https://spdx.org/licenses/Apache-2.0.html
+Usage-Guide:
+  To use the Apache License version 2.0 put the following SPDX tag/value
+  pair into a comment according to the placement guidelines in the
+  licensing rules documentation:
+    SPDX-License-Identifier: Apache-2.0
+License-Text:
+
+Apache License
+
+Version 2.0, January 2004
+
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and
+distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by the
+copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all other
+entities that control, are controlled by, or are under common control with
+that entity. For the purposes of this definition, "control" means (i) the
+power, direct or indirect, to cause the direction or management of such
+entity, whether by contract or otherwise, or (ii) ownership of fifty
+percent (50%) or more of the outstanding shares, or (iii) beneficial
+ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity exercising
+permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation source,
+and configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation
+or translation of a Source form, including but not limited to compiled
+object code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form,
+made available under the License, as indicated by a copyright notice that
+is included in or attached to the work (an example is provided in the
+Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object form,
+that is based on (or derived from) the Work and for which the editorial
+revisions, annotations, elaborations, or other modifications represent, as
+a whole, an original work of authorship. For the purposes of this License,
+Derivative Works shall not include works that remain separable from, or
+merely link (or bind by name) to the interfaces of, the Work and Derivative
+Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original
+version of the Work and any modifications or additions to that Work or
+Derivative Works thereof, that is intentionally submitted to Licensor for
+inclusion in the Work by the copyright owner or by an individual or Legal
+Entity authorized to submit on behalf of the copyright owner. For the
+purposes of this definition, "submitted" means any form of electronic,
+verbal, or written communication sent to the Licensor or its
+representatives, including but not limited to communication on electronic
+mailing lists, source code control systems, and issue tracking systems that
+are managed by, or on behalf of, the Licensor for the purpose of discussing
+and improving the Work, but excluding communication that is conspicuously
+marked or otherwise designated in writing by the copyright owner as "Not a
+Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on
+behalf of whom a Contribution has been received by Licensor and
+subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this
+   License, each Contributor hereby grants to You a perpetual, worldwide,
+   non-exclusive, no-charge, royalty-free, irrevocable copyright license to
+   reproduce, prepare Derivative Works of, publicly display, publicly
+   perform, sublicense, and distribute the Work and such Derivative Works
+   in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this
+   License, each Contributor hereby grants to You a perpetual, worldwide,
+   non-exclusive, no-charge, royalty-free, irrevocable (except as stated in
+   this section) patent license to make, have made, use, offer to sell,
+   sell, import, and otherwise transfer the Work, where such license
+   applies only to those patent claims licensable by such Contributor that
+   are necessarily infringed by their Contribution(s) alone or by
+   combination of their Contribution(s) with the Work to which such
+   Contribution(s) was submitted. If You institute patent litigation
+   against any entity (including a cross-claim or counterclaim in a
+   lawsuit) alleging that the Work or a Contribution incorporated within
+   the Work constitutes direct or contributory patent infringement, then
+   any patent licenses granted to You under this License for that Work
+   shall terminate as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or
+   Derivative Works thereof in any medium, with or without modifications,
+   and in Source or Object form, provided that You meet the following
+   conditions:
+
+   a. You must give any other recipients of the Work or Derivative Works a
+      copy of this License; and
+
+   b. You must cause any modified files to carry prominent notices stating
+      that You changed the files; and
+
+   c. You must retain, in the Source form of any Derivative Works that You
+      distribute, all copyright, patent, trademark, and attribution notices
+      from the Source form of the Work, excluding those notices that do not
+      pertain to any part of the Derivative Works; and
+
+   d. If the Work includes a "NOTICE" text file as part of its
+      distribution, then any Derivative Works that You distribute must
+      include a readable copy of the attribution notices contained within
+      such NOTICE file, excluding those notices that do not pertain to any
+      part of the Derivative Works, in at least one of the following
+      places: within a NOTICE text file distributed as part of the
+      Derivative Works; within the Source form or documentation, if
+      provided along with the Derivative Works; or, within a display
+      generated by the Derivative Works, if and wherever such third-party
+      notices normally appear. The contents of the NOTICE file are for
+      informational purposes only and do not modify the License. You may
+      add Your own attribution notices within Derivative Works that You
+      distribute, alongside or as an addendum to the NOTICE text from the
+      Work, provided that such additional attribution notices cannot be
+      construed as modifying the License.
+
+    You may add Your own copyright statement to Your modifications and may
+    provide additional or different license terms and conditions for use,
+    reproduction, or distribution of Your modifications, or for any such
+    Derivative Works as a whole, provided Your use, reproduction, and
+    distribution of the Work otherwise complies with the conditions stated
+    in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any
+   Contribution intentionally submitted for inclusion in the Work by You to
+   the Licensor shall be under the terms and conditions of this License,
+   without any additional terms or conditions. Notwithstanding the above,
+   nothing herein shall supersede or modify the terms of any separate
+   license agreement you may have executed with Licensor regarding such
+   Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to
+   in writing, Licensor provides the Work (and each Contributor provides
+   its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
+   OF ANY KIND, either express or implied, including, without limitation,
+   any warranties or conditions of TITLE, NON-INFRINGEMENT,
+   MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely
+   responsible for determining the appropriateness of using or
+   redistributing the Work and assume any risks associated with Your
+   exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether
+   in tort (including negligence), contract, or otherwise, unless required
+   by applicable law (such as deliberate and grossly negligent acts) or
+   agreed to in writing, shall any Contributor be liable to You for
+   damages, including any direct, indirect, special, incidental, or
+   consequential damages of any character arising as a result of this
+   License or out of the use or inability to use the Work (including but
+   not limited to damages for loss of goodwill, work stoppage, computer
+   failure or malfunction, or any and all other commercial damages or
+   losses), even if such Contributor has been advised of the possibility of
+   such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the
+   Work or Derivative Works thereof, You may choose to offer, and charge a
+   fee for, acceptance of support, warranty, indemnity, or other liability
+   obligations and/or rights consistent with this License. However, in
+   accepting such obligations, You may act only on Your own behalf and on
+   Your sole responsibility, not on behalf of any other Contributor, and
+   only if You agree to indemnify, defend, and hold each Contributor
+   harmless for any liability incurred by, or claims asserted against, such
+   Contributor by reason of your accepting any such warranty or additional
+   liability.
+
+END OF TERMS AND CONDITIONS
diff --git a/LICENSES/other/CC-BY-SA-4.0 b/LICENSES/other/CC-BY-SA-4.0
new file mode 100644
index 000000000000..f9158e831e79
--- /dev/null
+++ b/LICENSES/other/CC-BY-SA-4.0
@@ -0,0 +1,397 @@
+Valid-License-Identifier: CC-BY-SA-4.0
+SPDX-URL: https://spdx.org/licenses/CC-BY-SA-4.0
+Usage-Guide:
+  To use the Creative Commons Attribution Share Alike 4.0 International
+  license put the following SPDX tag/value pair into a comment according to
+  the placement guidelines in the licensing rules documentation:
+    SPDX-License-Identifier: CC-BY-SA-4.0
+License-Text:
+
+Creative Commons Attribution-ShareAlike 4.0 International
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and
+does not provide legal services or legal advice. Distribution of Creative
+Commons public licenses does not create a lawyer-client or other
+relationship. Creative Commons makes its licenses and related information
+available on an "as-is" basis. Creative Commons gives no warranties
+regarding its licenses, any material licensed under their terms and
+conditions, or any related information. Creative Commons disclaims all
+liability for damages resulting from their use to the fullest extent
+possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and
+conditions that creators and other rights holders may use to share original
+works of authorship and other material subject to copyright and certain
+other rights specified in the public license below. The following
+considerations are for informational purposes only, are not exhaustive, and
+do not form part of our licenses.
+
+Considerations for licensors: Our public licenses are intended for use by
+those authorized to give the public permission to use material in ways
+otherwise restricted by copyright and certain other rights. Our licenses
+are irrevocable. Licensors should read and understand the terms and
+conditions of the license they choose before applying it. Licensors should
+also secure all rights necessary before applying our licenses so that the
+public can reuse the material as expected. Licensors should clearly mark
+any material not subject to the license. This includes other CC-licensed
+material, or material used under an exception or limitation to
+copyright. More considerations for licensors :
+wiki.creativecommons.org/Considerations_for_licensors
+
+Considerations for the public: By using one of our public licenses, a
+licensor grants the public permission to use the licensed material under
+specified terms and conditions. If the licensor's permission is not
+necessary for any reason - for example, because of any applicable exception
+or limitation to copyright - then that use is not regulated by the
+license. Our licenses grant only permissions under copyright and certain
+other rights that a licensor has authority to grant. Use of the licensed
+material may still be restricted for other reasons, including because
+others have copyright or other rights in the material. A licensor may make
+special requests, such as asking that all changes be marked or described.
+
+Although not required by our licenses, you are encouraged to respect those
+requests where reasonable. More considerations for the public :
+wiki.creativecommons.org/Considerations_for_licensees
+
+Creative Commons Attribution-ShareAlike 4.0 International Public License
+
+By exercising the Licensed Rights (defined below), You accept and agree to
+be bound by the terms and conditions of this Creative Commons
+Attribution-ShareAlike 4.0 International Public License ("Public
+License"). To the extent this Public License may be interpreted as a
+contract, You are granted the Licensed Rights in consideration of Your
+acceptance of these terms and conditions, and the Licensor grants You such
+rights in consideration of benefits the Licensor receives from making the
+Licensed Material available under these terms and conditions.
+
+Section 1 - Definitions.
+
+    a. Adapted Material means material subject to Copyright and Similar
+       Rights that is derived from or based upon the Licensed Material and
+       in which the Licensed Material is translated, altered, arranged,
+       transformed, or otherwise modified in a manner requiring permission
+       under the Copyright and Similar Rights held by the Licensor. For
+       purposes of this Public License, where the Licensed Material is a
+       musical work, performance, or sound recording, Adapted Material is
+       always produced where the Licensed Material is synched in timed
+       relation with a moving image.
+
+    b. Adapter's License means the license You apply to Your Copyright and
+       Similar Rights in Your contributions to Adapted Material in
+       accordance with the terms and conditions of this Public License.
+
+    c. BY-SA Compatible License means a license listed at
+       creativecommons.org/compatiblelicenses, approved by Creative Commons
+       as essentially the equivalent of this Public License.
+
+    d. Copyright and Similar Rights means copyright and/or similar rights
+       closely related to copyright including, without limitation,
+       performance, broadcast, sound recording, and Sui Generis Database
+       Rights, without regard to how the rights are labeled or
+       categorized. For purposes of this Public License, the rights
+       specified in Section 2(b)(1)-(2) are not Copyright and Similar
+       Rights.
+
+    e. Effective Technological Measures means those measures that, in the
+       absence of proper authority, may not be circumvented under laws
+       fulfilling obligations under Article 11 of the WIPO Copyright Treaty
+       adopted on December 20, 1996, and/or similar international
+       agreements.
+
+    f. Exceptions and Limitations means fair use, fair dealing, and/or any
+       other exception or limitation to Copyright and Similar Rights that
+       applies to Your use of the Licensed Material.
+
+    g. License Elements means the license attributes listed in the name of
+       a Creative Commons Public License. The License Elements of this
+       Public License are Attribution and ShareAlike.
+
+    h. Licensed Material means the artistic or literary work, database, or
+       other material to which the Licensor applied this Public License.
+
+    i. Licensed Rights means the rights granted to You subject to the terms
+       and conditions of this Public License, which are limited to all
+       Copyright and Similar Rights that apply to Your use of the Licensed
+       Material and that the Licensor has authority to license.
+
+    j. Licensor means the individual(s) or entity(ies) granting rights
+       under this Public License.
+
+    k. Share means to provide material to the public by any means or
+       process that requires permission under the Licensed Rights, such as
+       reproduction, public display, public performance, distribution,
+       dissemination, communication, or importation, and to make material
+       available to the public including in ways that members of the public
+       may access the material from a place and at a time individually
+       chosen by them.
+
+    l. Sui Generis Database Rights means rights other than copyright
+       resulting from Directive 96/9/EC of the European Parliament and of
+       the Council of 11 March 1996 on the legal protection of databases,
+       as amended and/or succeeded, as well as other essentially equivalent
+       rights anywhere in the world.  m. You means the individual or entity
+       exercising the Licensed Rights under this Public License. Your has a
+       corresponding meaning.
+
+Section 2 - Scope.
+
+    a. License grant.
+
+        1. Subject to the terms and conditions of this Public License, the
+           Licensor hereby grants You a worldwide, royalty-free,
+           non-sublicensable, non-exclusive, irrevocable license to
+           exercise the Licensed Rights in the Licensed Material to:
+
+            A. reproduce and Share the Licensed Material, in whole or in part; and
+
+            B. produce, reproduce, and Share Adapted Material.
+
+        2. Exceptions and Limitations. For the avoidance of doubt, where
+           Exceptions and Limitations apply to Your use, this Public
+           License does not apply, and You do not need to comply with its
+           terms and conditions.
+
+        3. Term. The term of this Public License is specified in Section 6(a).
+
+        4. Media and formats; technical modifications allowed. The Licensor
+           authorizes You to exercise the Licensed Rights in all media and
+           formats whether now known or hereafter created, and to make
+           technical modifications necessary to do so. The Licensor waives
+           and/or agrees not to assert any right or authority to forbid You
+           from making technical modifications necessary to exercise the
+           Licensed Rights, including technical modifications necessary to
+           circumvent Effective Technological Measures. For purposes of
+           this Public License, simply making modifications authorized by
+           this Section 2(a)(4) never produces Adapted Material.
+
+        5. Downstream recipients.
+
+            A. Offer from the Licensor - Licensed Material. Every recipient
+               of the Licensed Material automatically receives an offer
+               from the Licensor to exercise the Licensed Rights under the
+               terms and conditions of this Public License.
+
+            B. Additional offer from the Licensor - Adapted Material. Every
+               recipient of Adapted Material from You automatically
+               receives an offer from the Licensor to exercise the Licensed
+               Rights in the Adapted Material under the conditions of the
+               Adapter's License You apply.
+
+            C. No downstream restrictions. You may not offer or impose any
+               additional or different terms or conditions on, or apply any
+               Effective Technological Measures to, the Licensed Material
+               if doing so restricts exercise of the Licensed Rights by any
+               recipient of the Licensed Material.
+
+        6. No endorsement. Nothing in this Public License constitutes or
+           may be construed as permission to assert or imply that You are,
+           or that Your use of the Licensed Material is, connected with, or
+           sponsored, endorsed, or granted official status by, the Licensor
+           or others designated to receive attribution as provided in
+           Section 3(a)(1)(A)(i).
+
+    b. Other rights.
+
+        1. Moral rights, such as the right of integrity, are not licensed
+           under this Public License, nor are publicity, privacy, and/or
+           other similar personality rights; however, to the extent
+           possible, the Licensor waives and/or agrees not to assert any
+           such rights held by the Licensor to the limited extent necessary
+           to allow You to exercise the Licensed Rights, but not otherwise.
+
+        2. Patent and trademark rights are not licensed under this Public
+           License.
+
+        3. To the extent possible, the Licensor waives any right to collect
+           royalties from You for the exercise of the Licensed Rights,
+           whether directly or through a collecting society under any
+           voluntary or waivable statutory or compulsory licensing
+           scheme. In all other cases the Licensor expressly reserves any
+           right to collect such royalties.
+
+Section 3 - License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the
+following conditions.
+
+    a. Attribution.
+
+        1. If You Share the Licensed Material (including in modified form),
+           You must:
+
+            A. retain the following if it is supplied by the Licensor with
+               the Licensed Material:
+
+                i. identification of the creator(s) of the Licensed
+                   Material and any others designated to receive
+                   attribution, in any reasonable manner requested by the
+                   Licensor (including by pseudonym if designated);
+
+                ii. a copyright notice;
+
+                iii. a notice that refers to this Public License;
+
+                iv. a notice that refers to the disclaimer of warranties;
+
+                v. a URI or hyperlink to the Licensed Material to the extent reasonably practicable;
+
+            B. indicate if You modified the Licensed Material and retain an
+               indication of any previous modifications; and
+
+            C. indicate the Licensed Material is licensed under this Public
+            License, and include the text of, or the URI or hyperlink to,
+            this Public License.
+
+        2. You may satisfy the conditions in Section 3(a)(1) in any
+           reasonable manner based on the medium, means, and context in
+           which You Share the Licensed Material. For example, it may be
+           reasonable to satisfy the conditions by providing a URI or
+           hyperlink to a resource that includes the required information.
+
+        3. If requested by the Licensor, You must remove any of the
+           information required by Section 3(a)(1)(A) to the extent
+           reasonably practicable.  b. ShareAlike.In addition to the
+           conditions in Section 3(a), if You Share Adapted Material You
+           produce, the following conditions also apply.
+
+           1. The Adapter's License You apply must be a Creative Commons
+              license with the same License Elements, this version or
+              later, or a BY-SA Compatible License.
+
+           2. You must include the text of, or the URI or hyperlink to, the
+              Adapter's License You apply. You may satisfy this condition
+              in any reasonable manner based on the medium, means, and
+              context in which You Share Adapted Material.
+
+           3. You may not offer or impose any additional or different terms
+              or conditions on, or apply any Effective Technological
+              Measures to, Adapted Material that restrict exercise of the
+              rights granted under the Adapter's License You apply.
+
+Section 4 - Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that apply to
+Your use of the Licensed Material:
+
+    a. for the avoidance of doubt, Section 2(a)(1) grants You the right to
+       extract, reuse, reproduce, and Share all or a substantial portion of
+       the contents of the database;
+
+    b. if You include all or a substantial portion of the database contents
+       in a database in which You have Sui Generis Database Rights, then
+       the database in which You have Sui Generis Database Rights (but not
+       its individual contents) is Adapted Material, including for purposes
+       of Section 3(b); and
+
+    c. You must comply with the conditions in Section 3(a) if You Share all
+       or a substantial portion of the contents of the database.
+
+    For the avoidance of doubt, this Section 4 supplements and does not
+    replace Your obligations under this Public License where the Licensed
+    Rights include other Copyright and Similar Rights.
+
+Section 5 - Disclaimer of Warranties and Limitation of Liability.
+
+    a. Unless otherwise separately undertaken by the Licensor, to the
+       extent possible, the Licensor offers the Licensed Material as-is and
+       as-available, and makes no representations or warranties of any kind
+       concerning the Licensed Material, whether express, implied,
+       statutory, or other. This includes, without limitation, warranties
+       of title, merchantability, fitness for a particular purpose,
+       non-infringement, absence of latent or other defects, accuracy, or
+       the presence or absence of errors, whether or not known or
+       discoverable. Where disclaimers of warranties are not allowed in
+       full or in part, this disclaimer may not apply to You.
+
+    b. To the extent possible, in no event will the Licensor be liable to
+       You on any legal theory (including, without limitation, negligence)
+       or otherwise for any direct, special, indirect, incidental,
+       consequential, punitive, exemplary, or other losses, costs,
+       expenses, or damages arising out of this Public License or use of
+       the Licensed Material, even if the Licensor has been advised of the
+       possibility of such losses, costs, expenses, or damages. Where a
+       limitation of liability is not allowed in full or in part, this
+       limitation may not apply to You.
+
+    c. The disclaimer of warranties and limitation of liability provided
+       above shall be interpreted in a manner that, to the extent possible,
+       most closely approximates an absolute disclaimer and waiver of all
+       liability.
+
+Section 6 - Term and Termination.
+
+    a. This Public License applies for the term of the Copyright and
+       Similar Rights licensed here. However, if You fail to comply with
+       this Public License, then Your rights under this Public License
+       terminate automatically.
+
+    b. Where Your right to use the Licensed Material has terminated under
+       Section 6(a), it reinstates:
+
+        1. automatically as of the date the violation is cured, provided it
+           is cured within 30 days of Your discovery of the violation; or
+
+        2. upon express reinstatement by the Licensor.
+
+    c. For the avoidance of doubt, this Section 6(b) does not affect any
+       right the Licensor may have to seek remedies for Your violations of
+       this Public License.
+
+    d. For the avoidance of doubt, the Licensor may also offer the Licensed
+       Material under separate terms or conditions or stop distributing the
+       Licensed Material at any time; however, doing so will not terminate
+       this Public License.
+
+    e. Sections 1, 5, 6, 7, and 8 survive termination of this Public License.
+
+Section 7 - Other Terms and Conditions.
+
+    a. The Licensor shall not be bound by any additional or different terms
+       or conditions communicated by You unless expressly agreed.
+
+    b. Any arrangements, understandings, or agreements regarding the
+       Licensed Material not stated herein are separate from and
+       independent of the terms and conditions of this Public License.
+
+Section 8 - Interpretation.
+
+    a. For the avoidance of doubt, this Public License does not, and shall
+       not be interpreted to, reduce, limit, restrict, or impose conditions
+       on any use of the Licensed Material that could lawfully be made
+       without permission under this Public License.
+
+    b. To the extent possible, if any provision of this Public License is
+       deemed unenforceable, it shall be automatically reformed to the
+       minimum extent necessary to make it enforceable. If the provision
+       cannot be reformed, it shall be severed from this Public License
+       without affecting the enforceability of the remaining terms and
+       conditions.
+
+    c. No term or condition of this Public License will be waived and no
+       failure to comply consented to unless expressly agreed to by the
+       Licensor.
+
+    d. Nothing in this Public License constitutes or may be interpreted as
+       a limitation upon, or waiver of, any privileges and immunities that
+       apply to the Licensor or You, including from the legal processes of
+       any jurisdiction or authority.
+
+Creative Commons is not a party to its public licenses. Notwithstanding,
+Creative Commons may elect to apply one of its public licenses to material
+it publishes and in those instances will be considered the "Licensor." The
+text of the Creative Commons public licenses is dedicated to the public
+domain under the CC0 Public Domain Dedication. Except for the limited
+purpose of indicating that material is shared under a Creative Commons
+public license or as otherwise permitted by the Creative Commons policies
+published at creativecommons.org/policies, Creative Commons does not
+authorize the use of the trademark "Creative Commons" or any other
+trademark or logo of Creative Commons without its prior written consent
+including, without limitation, in connection with any unauthorized
+modifications to any of its public licenses or any other arrangements,
+understandings, or agreements concerning use of licensed material. For the
+avoidance of doubt, this paragraph does not form part of the public
+licenses.
+
+Creative Commons may be contacted at creativecommons.org.
diff --git a/LICENSES/other/CDDL-1.0 b/LICENSES/other/CDDL-1.0
new file mode 100644
index 000000000000..195a1687930a
--- /dev/null
+++ b/LICENSES/other/CDDL-1.0
@@ -0,0 +1,364 @@
+Valid-License-Identifier: CDDL-1.0
+SPDX-URL: https://spdx.org/licenses/CDDL-1.0.html
+Usage-Guide:
+  To use the Common Development and Distribution License 1.0 put the
+  following SPDX tag/value pair into a comment according to the placement
+  guidelines in the licensing rules documentation:
+    SPDX-License-Identifier: CDDL-1.0
+
+License-Text:
+
+COMMON DEVELOPMENT AND DISTRIBUTION LICENSE (CDDL)
+Version 1.0
+
+    1. Definitions.
+
+        1.1. "Contributor" means each individual or entity that creates or
+             contributes to the creation of Modifications.
+
+        1.2. "Contributor Version" means the combination of the Original
+	     Software, prior Modifications used by a Contributor (if any),
+	     and the Modifications made by that particular Contributor.
+
+        1.3. "Covered Software" means (a) the Original Software, or (b)
+             Modifications, or (c) the combination of files containing
+             Original Software with files containing Modifications, in each
+             case including portions thereof.
+
+	1.4. "Executable" means the Covered Software in any form other than
+             Source Code.
+
+        1.5. "Initial Developer" means the individual or entity that first
+             makes Original Software available under this License.
+
+        1.6. "Larger Work" means a work which combines Covered Software or
+             portions thereof with code not governed by the terms of this
+             License.
+
+        1.7. "License" means this document.
+
+        1.8. "Licensable" means having the right to grant, to the maximum
+             extent possible, whether at the time of the initial grant or
+             subsequently acquired, any and all of the rights conveyed herein.
+
+        1.9. "Modifications" means the Source Code and Executable form of
+             any of the following:
+
+            A. Any file that results from an addition to, deletion from or
+               modification of the contents of a file containing Original
+               Software or previous Modifications;
+
+            B. Any new file that contains any part of the Original Software
+               or previous Modification; or
+
+            C. Any new file that is contributed or otherwise made available
+               under the terms of this License.
+
+        1.10. "Original Software" means the Source Code and Executable form
+              of computer software code that is originally released under
+              this License.
+
+        1.11. "Patent Claims" means any patent claim(s), now owned or
+              hereafter acquired, including without limitation, method,
+              process, and apparatus claims, in any patent Licensable by
+              grantor.
+
+        1.12. "Source Code" means (a) the common form of computer software
+	      code in which modifications are made and (b) associated
+              documentation included in or with such code.
+
+        1.13. "You" (or "Your") means an individual or a legal entity
+              exercising rights under, and complying with all of the terms
+              of, this License. For legal entities, "You" includes any
+              entity which controls, is controlled by, or is under common
+              control with You. For purposes of this definition, "control"
+              means (a) the power, direct or indirect, to cause the
+              direction or management of such entity, whether by contract
+              or otherwise, or (b) ownership of more than fifty percent
+              (50%) of the outstanding shares or beneficial ownership of
+              such entity.
+
+    2. License Grants.
+        2.1. The Initial Developer Grant.
+
+        Conditioned upon Your compliance with Section 3.1 below and subject
+        to third party intellectual property claims, the Initial Developer
+        hereby grants You a world-wide, royalty-free, non-exclusive
+        license:
+
+            (a) under intellectual property rights (other than patent or
+                trademark) Licensable by Initial Developer, to use,
+                reproduce, modify, display, perform, sublicense and
+                distribute the Original Software (or portions thereof),
+                with or without Modifications, and/or as part of a Larger
+                Work; and
+
+            (b) under Patent Claims infringed by the making, using or
+                selling of Original Software, to make, have made, use,
+                practice, sell, and offer for sale, and/or otherwise
+                dispose of the Original Software (or portions thereof).
+
+            (c) The licenses granted in Sections 2.1(a) and (b) are
+                effective on the date Initial Developer first distributes
+                or otherwise makes the Original Software available to a
+                third party under the terms of this License.
+
+            (d) Notwithstanding Section 2.1(b) above, no patent license is
+                granted: (1) for code that You delete from the Original
+                Software, or (2) for infringements caused by: (i) the
+                modification of the Original Software, or (ii) the
+                combination of the Original Software with other software or
+                devices.
+
+        2.2. Contributor Grant.
+
+        Conditioned upon Your compliance with Section 3.1 below and subject
+        to third party intellectual property claims, each Contributor
+        hereby grants You a world-wide, royalty-free, non-exclusive
+        license:
+
+            (a) under intellectual property rights (other than patent or
+	        trademark) Licensable by Contributor to use, reproduce,
+	        modify, display, perform, sublicense and distribute the
+	        Modifications created by such Contributor (or portions
+	        thereof), either on an unmodified basis, with other
+	        Modifications, as Covered Software and/or as part of a
+	        Larger Work; and
+
+            (b) under Patent Claims infringed by the making, using, or
+                selling of Modifications made by that Contributor either
+                alone and/or in combination with its Contributor Version
+                (or portions of such combination), to make, use, sell,
+                offer for sale, have made, and/or otherwise dispose of: (1)
+                Modifications made by that Contributor (or portions
+                thereof); and (2) the combination of Modifications made by
+                that Contributor with its Contributor Version (or portions
+                of such combination).
+
+            (c) The licenses granted in Sections 2.2(a) and 2.2(b) are
+                effective on the date Contributor first distributes or
+                otherwise makes the Modifications available to a third
+                party.
+
+            (d) Notwithstanding Section 2.2(b) above, no patent license is
+                granted: (1) for any code that Contributor has deleted from
+                the Contributor Version; (2) for infringements caused by:
+                (i) third party modifications of Contributor Version, or
+                (ii) the combination of Modifications made by that
+                Contributor with other software (except as part of the
+                Contributor Version) or other devices; or (3) under Patent
+                Claims infringed by Covered Software in the absence of
+                Modifications made by that Contributor.
+
+    3. Distribution Obligations.
+        3.1. Availability of Source Code.
+
+        Any Covered Software that You distribute or otherwise make
+        available in Executable form must also be made available in Source
+        Code form and that Source Code form must be distributed only under
+        the terms of this License. You must include a copy of this License
+        with every copy of the Source Code form of the Covered Software You
+        distribute or otherwise make available. You must inform recipients
+        of any such Covered Software in Executable form as to how they can
+        obtain such Covered Software in Source Code form in a reasonable
+        manner on or through a medium customarily used for software
+        exchange.
+
+        3.2. Modifications.
+
+        The Modifications that You create or to which You contribute are
+        governed by the terms of this License. You represent that You
+        believe Your Modifications are Your original creation(s) and/or You
+        have sufficient rights to grant the rights conveyed by this
+        License.
+
+        3.3. Required Notices.
+
+        You must include a notice in each of Your Modifications that
+        identifies You as the Contributor of the Modification. You may not
+        remove or alter any copyright, patent or trademark notices
+        contained within the Covered Software, or any notices of licensing
+        or any descriptive text giving attribution to any Contributor or
+        the Initial Developer.
+
+        3.4. Application of Additional Terms.
+
+        You may not offer or impose any terms on any Covered Software in
+        Source Code form that alters or restricts the applicable version of
+        this License or the recipients' rights hereunder. You may choose to
+        offer, and to charge a fee for, warranty, support, indemnity or
+        liability obligations to one or more recipients of Covered
+        Software. However, you may do so only on Your own behalf, and not
+        on behalf of the Initial Developer or any Contributor. You must
+        make it absolutely clear that any such warranty, support, indemnity
+        or liability obligation is offered by You alone, and You hereby
+        agree to indemnify the Initial Developer and every Contributor for
+        any liability incurred by the Initial Developer or such Contributor
+        as a result of warranty, support, indemnity or liability terms You
+        offer.
+
+        3.5. Distribution of Executable Versions.
+
+        You may distribute the Executable form of the Covered Software
+        under the terms of this License or under the terms of a license of
+        Your choice, which may contain terms different from this License,
+        provided that You are in compliance with the terms of this License
+        and that the license for the Executable form does not attempt to
+        limit or alter the recipient's rights in the Source Code form from
+        the rights set forth in this License. If You distribute the Covered
+        Software in Executable form under a different license, You must
+        make it absolutely clear that any terms which differ from this
+        License are offered by You alone, not by the Initial Developer or
+        Contributor. You hereby agree to indemnify the Initial Developer
+        and every Contributor for any liability incurred by the Initial
+        Developer or such Contributor as a result of any such terms You
+        offer.
+
+        3.6. Larger Works.
+
+        You may create a Larger Work by combining Covered Software with
+        other code not governed by the terms of this License and distribute
+        the Larger Work as a single product. In such a case, You must make
+        sure the requirements of this License are fulfilled for the Covered
+        Software.
+
+    4. Versions of the License.
+        4.1. New Versions.
+
+        Sun Microsystems, Inc. is the initial license steward and may
+        publish revised and/or new versions of this License from time to
+        time. Each version will be given a distinguishing version
+        number. Except as provided in Section 4.3, no one other than the
+        license steward has the right to modify this License.
+
+        4.2. Effect of New Versions.
+
+        You may always continue to use, distribute or otherwise make the
+        Covered Software available under the terms of the version of the
+        License under which You originally received the Covered
+        Software. If the Initial Developer includes a notice in the
+        Original Software prohibiting it from being distributed or
+        otherwise made available under any subsequent version of the
+        License, You must distribute and make the Covered Software
+        available under the terms of the version of the License under which
+        You originally received the Covered Software. Otherwise, You may
+        also choose to use, distribute or otherwise make the Covered
+        Software available under the terms of any subsequent version of the
+        License published by the license steward.
+
+        4.3. Modified Versions.
+
+        When You are an Initial Developer and You want to create a new
+        license for Your Original Software, You may create and use a
+        modified version of this License if You: (a) rename the license and
+        remove any references to the name of the license steward (except to
+        note that the license differs from this License); and (b) otherwise
+        make it clear that the license contains terms which differ from
+        this License.
+
+    5. DISCLAIMER OF WARRANTY.
+
+    COVERED SOFTWARE IS PROVIDED UNDER THIS LICENSE ON AN "AS IS" BASIS,
+    WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+    WITHOUT LIMITATION, WARRANTIES THAT THE COVERED SOFTWARE IS FREE OF
+    DEFECTS, MERCHANTABLE, FIT FOR A PARTICULAR PURPOSE OR
+    NON-INFRINGING. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF
+    THE COVERED SOFTWARE IS WITH YOU. SHOULD ANY COVERED SOFTWARE PROVE
+    DEFECTIVE IN ANY RESPECT, YOU (NOT THE INITIAL DEVELOPER OR ANY OTHER
+    CONTRIBUTOR) ASSUME THE COST OF ANY NECESSARY SERVICING, REPAIR OR
+    CORRECTION. THIS DISCLAIMER OF WARRANTY CONSTITUTES AN ESSENTIAL PART
+    OF THIS LICENSE. NO USE OF ANY COVERED SOFTWARE IS AUTHORIZED HEREUNDER
+    EXCEPT UNDER THIS DISCLAIMER.
+
+    6. TERMINATION.
+
+        6.1. This License and the rights granted hereunder will terminate
+        automatically if You fail to comply with terms herein and fail to
+        cure such breach within 30 days of becoming aware of the
+        breach. Provisions which, by their nature, must remain in effect
+        beyond the termination of this License shall survive.
+
+        6.2. If You assert a patent infringement claim (excluding
+        declaratory judgment actions) against Initial Developer or a
+        Contributor (the Initial Developer or Contributor against whom You
+        assert such claim is referred to as "Participant") alleging that
+        the Participant Software (meaning the Contributor Version where the
+        Participant is a Contributor or the Original Software where the
+        Participant is the Initial Developer) directly or indirectly
+        infringes any patent, then any and all rights granted directly or
+        indirectly to You by such Participant, the Initial Developer (if
+        the Initial Developer is not the Participant) and all Contributors
+        under Sections 2.1 and/or 2.2 of this License shall, upon 60 days
+        notice from Participant terminate prospectively and automatically
+        at the expiration of such 60 day notice period, unless if within
+        such 60 day period You withdraw Your claim with respect to the
+        Participant Software against such Participant either unilaterally
+        or pursuant to a written agreement with Participant.
+
+        6.3. In the event of termination under Sections 6.1 or 6.2 above,
+        all end user licenses that have been validly granted by You or any
+        distributor hereunder prior to termination (excluding licenses
+        granted to You by any distributor) shall survive termination.
+
+    7. LIMITATION OF LIABILITY.
+
+    UNDER NO CIRCUMSTANCES AND UNDER NO LEGAL THEORY, WHETHER TORT
+    (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE, SHALL YOU, THE INITIAL
+    DEVELOPER, ANY OTHER CONTRIBUTOR, OR ANY DISTRIBUTOR OF COVERED
+    SOFTWARE, OR ANY SUPPLIER OF ANY OF SUCH PARTIES, BE LIABLE TO ANY
+    PERSON FOR ANY INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES
+    OF ANY CHARACTER INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOST
+    PROFITS, LOSS OF GOODWILL, WORK STOPPAGE, COMPUTER FAILURE OR
+    MALFUNCTION, OR ANY AND ALL OTHER COMMERCIAL DAMAGES OR LOSSES, EVEN IF
+    SUCH PARTY SHALL HAVE BEEN INFORMED OF THE POSSIBILITY OF SUCH
+    DAMAGES. THIS LIMITATION OF LIABILITY SHALL NOT APPLY TO LIABILITY FOR
+    DEATH OR PERSONAL INJURY RESULTING FROM SUCH PARTY'S NEGLIGENCE TO THE
+    EXTENT APPLICABLE LAW PROHIBITS SUCH LIMITATION. SOME JURISDICTIONS DO
+    NOT ALLOW THE EXCLUSION OR LIMITATION OF INCIDENTAL OR CONSEQUENTIAL
+    DAMAGES, SO THIS EXCLUSION AND LIMITATION MAY NOT APPLY TO YOU.
+
+    8. U.S. GOVERNMENT END USERS.
+
+    The Covered Software is a "commercial item," as that term is defined in
+    48 C.F.R. 2.101 (Oct. 1995), consisting of "commercial computer
+    software" (as that term is defined at 48 C.F.R. $ 252.227-7014(a)(1))
+    and "commercial computer software documentation" as such terms are used
+    in 48 C.F.R. 12.212 (Sept. 1995). Consistent with 48 C.F.R. 12.212 and
+    48 C.F.R. 227.7202-1 through 227.7202-4 (June 1995), all
+    U.S. Government End Users acquire Covered Software with only those
+    rights set forth herein. This U.S. Government Rights clause is in lieu
+    of, and supersedes, any other FAR, DFAR, or other clause or provision
+    that addresses Government rights in computer software under this
+    License.
+
+    9. MISCELLANEOUS.
+
+    This License represents the complete agreement concerning subject
+    matter hereof. If any provision of this License is held to be
+    unenforceable, such provision shall be reformed only to the extent
+    necessary to make it enforceable. This License shall be governed by the
+    law of the jurisdiction specified in a notice contained within the
+    Original Software (except to the extent applicable law, if any,
+    provides otherwise), excluding such jurisdiction's conflict-of-law
+    provisions. Any litigation relating to this License shall be subject to
+    the jurisdiction of the courts located in the jurisdiction and venue
+    specified in a notice contained within the Original Software, with the
+    losing party responsible for costs, including, without limitation,
+    court costs and reasonable attorneys' fees and expenses. The
+    application of the United Nations Convention on Contracts for the
+    International Sale of Goods is expressly excluded. Any law or
+    regulation which provides that the language of a contract shall be
+    construed against the drafter shall not apply to this License. You
+    agree that You alone are responsible for compliance with the United
+    States export administration regulations (and the export control laws
+    and regulation of any other countries) when You use, distribute or
+    otherwise make available any Covered Software.
+
+    10. RESPONSIBILITY FOR CLAIMS.
+
+    As between Initial Developer and the Contributors, each party is
+    responsible for claims and damages arising, directly or indirectly, out
+    of its utilization of rights under this License and You agree to work
+    with Initial Developer and Contributors to distribute such
+    responsibility on an equitable basis. Nothing herein is intended or
+    shall be deemed to constitute any admission of liability.
diff --git a/LICENSES/other/Linux-OpenIB b/LICENSES/other/Linux-OpenIB
new file mode 100644
index 000000000000..1ad85f6b3a89
--- /dev/null
+++ b/LICENSES/other/Linux-OpenIB
@@ -0,0 +1,26 @@
+Valid-License-Identifier: Linux-OpenIB
+SPDX-URL: https://spdx.org/licenses/Linux-OpenIB.html
+Usage-Guide:
+  To use the Linux Kernel Variant of OpenIB.org license put the following
+  SPDX tag/value pair into a comment according to the placement guidelines
+  in the licensing rules documentation:
+    SPDX-License-Identifier: Linux-OpenIB
+License-Text:
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    - Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+
+    - Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
diff --git a/LICENSES/other/X11 b/LICENSES/other/X11
new file mode 100644
index 000000000000..fe4353fd0000
--- /dev/null
+++ b/LICENSES/other/X11
@@ -0,0 +1,37 @@
+Valid-License-Identifier: X11
+SPDX-URL: https://spdx.org/licenses/X11.html
+Usage-Guide:
+  To use the X11 put the following SPDX tag/value pair into a comment
+  according to the placement guidelines in the licensing rules
+  documentation:
+    SPDX-License-Identifier: X11
+License-Text:
+
+
+X11 License
+
+Copyright (C) 1996 X Consortium
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the "Software"),
+to deal in the Software without restriction, including without limitation
+the rights to use, copy, modify, merge, publish, distribute, sublicense,
+and/or sell copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+X CONSORTIUM BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+Except as contained in this notice, the name of the X Consortium shall not
+be used in advertising or otherwise to promote the sale, use or other
+dealings in this Software without prior written authorization from the X
+Consortium.
+
+X Window System is a trademark of X Consortium, Inc.
diff --git a/LICENSES/preferred/GPL-2.0 b/LICENSES/preferred/GPL-2.0
index b8db91d3a1cb..ff0812fd89cc 100644
--- a/LICENSES/preferred/GPL-2.0
+++ b/LICENSES/preferred/GPL-2.0
@@ -1,5 +1,7 @@
 Valid-License-Identifier: GPL-2.0
+Valid-License-Identifier: GPL-2.0-only
 Valid-License-Identifier: GPL-2.0+
+Valid-License-Identifier: GPL-2.0-or-later
 SPDX-URL: https://spdx.org/licenses/GPL-2.0.html
 Usage-Guide:
   To use this license in source code, put one of the following SPDX
@@ -7,8 +9,12 @@ Usage-Guide:
   guidelines in the licensing rules documentation.
   For 'GNU General Public License (GPL) version 2 only' use:
     SPDX-License-Identifier: GPL-2.0
+  or
+    SPDX-License-Identifier: GPL-2.0-only
   For 'GNU General Public License (GPL) version 2 or any later version' use:
     SPDX-License-Identifier: GPL-2.0+
+  or
+    SPDX-License-Identifier: GPL-2.0-or-later
 License-Text:
 
 		    GNU GENERAL PUBLIC LICENSE
diff --git a/MAINTAINERS b/MAINTAINERS
index 0a1410d5a621..f446443a556e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -137,9 +137,9 @@ Maintainers List (try to look for most precise areas first)
 		-----------------------------------
 
 3C59X NETWORK DRIVER
-M:	Steffen Klassert <klassert@mathematik.tu-chemnitz.de>
+M:	Steffen Klassert <klassert@kernel.org>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 F:	Documentation/networking/vortex.txt
 F:	drivers/net/ethernet/3com/3c59x.c
 
@@ -564,8 +564,9 @@ S:	Maintained
 F:	drivers/media/dvb-frontends/af9033*
 
 AFFS FILE SYSTEM
+M:	David Sterba <dsterba@suse.com>
 L:	linux-fsdevel@vger.kernel.org
-S:	Orphan
+S:	Odd Fixes
 F:	Documentation/filesystems/affs.txt
 F:	fs/affs/
 
@@ -766,12 +767,14 @@ F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
 F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
 F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
 F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
 F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
 F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
 F:	drivers/gpu/drm/amd/amdkfd/
 F:	drivers/gpu/drm/amd/include/cik_structs.h
 F:	drivers/gpu/drm/amd/include/kgd_kfd_interface.h
 F:	drivers/gpu/drm/amd/include/vi_structs.h
+F:	drivers/gpu/drm/amd/include/v9_structs.h
 F:	include/uapi/linux/kfd_ioctl.h
 
 AMD SEATTLE DEVICE TREE SUPPORT
@@ -905,6 +908,8 @@ ANDROID ION DRIVER
 M:	Laura Abbott <labbott@redhat.com>
 M:	Sumit Semwal <sumit.semwal@linaro.org>
 L:	devel@driverdev.osuosl.org
+L:	dri-devel@lists.freedesktop.org
+L:	linaro-mm-sig@lists.linaro.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/staging/android/ion
 F:	drivers/staging/android/uapi/ion.h
@@ -1208,7 +1213,6 @@ F:	drivers/*/*alpine*
 ARM/ARTPEC MACHINE SUPPORT
 M:	Jesper Nilsson <jesper.nilsson@axis.com>
 M:	Lars Persson <lars.persson@axis.com>
-M:	Niklas Cassel <niklas.cassel@axis.com>
 S:	Maintained
 L:	linux-arm-kernel@axis.com
 F:	arch/arm/mach-artpec
@@ -1373,7 +1377,8 @@ F:	arch/arm/mach-ebsa110/
 F:	drivers/net/ethernet/amd/am79c961a.*
 
 ARM/ENERGY MICRO (SILICON LABS) EFM32 SUPPORT
-M:	Uwe Kleine-König <kernel@pengutronix.de>
+M:	Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 N:	efm32
@@ -1401,7 +1406,8 @@ F:	arch/arm/mach-footbridge/
 
 ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
 M:	Shawn Guo <shawnguo@kernel.org>
-M:	Sascha Hauer <kernel@pengutronix.de>
+M:	Sascha Hauer <s.hauer@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 R:	Fabio Estevam <fabio.estevam@nxp.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -1416,7 +1422,8 @@ F:	include/soc/imx/
 
 ARM/FREESCALE VYBRID ARM ARCHITECTURE
 M:	Shawn Guo <shawnguo@kernel.org>
-M:	Sascha Hauer <kernel@pengutronix.de>
+M:	Sascha Hauer <s.hauer@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 R:	Stefan Agner <stefan@agner.ch>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -2326,8 +2333,16 @@ S:	Maintained
 F:	drivers/gpio/gpio-ath79.c
 F:	Documentation/devicetree/bindings/gpio/gpio-ath79.txt
 
+ATHEROS 71XX/9XXX USB PHY DRIVER
+M:	Alban Bedel <albeu@free.fr>
+W:	https://github.com/AlbanBedel/linux
+T:	git git://github.com/AlbanBedel/linux
+S:	Maintained
+F:	drivers/phy/qualcomm/phy-ath79-usb.c
+F:	Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
+
 ATHEROS ATH GENERIC UTILITIES
-M:	"Luis R. Rodriguez" <mcgrof@do-not-panic.com>
+M:	Kalle Valo <kvalo@codeaurora.org>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
 F:	drivers/net/wireless/ath/*
@@ -2342,7 +2357,7 @@ S:	Maintained
 F:	drivers/net/wireless/ath/ath5k/
 
 ATHEROS ATH6KL WIRELESS DRIVER
-M:	Kalle Valo <kvalo@qca.qualcomm.com>
+M:	Kalle Valo <kvalo@codeaurora.org>
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/en/users/Drivers/ath6kl
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
@@ -2549,7 +2564,6 @@ F:	Documentation/devicetree/bindings/sound/axentia,*
 F:	sound/soc/atmel/tse850-pcm5142.c
 
 AZ6007 DVB DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -2614,7 +2628,7 @@ S:	Maintained
 F:	drivers/net/hamradio/baycom*
 
 BCACHE (BLOCK LAYER CACHE)
-M:	Michael Lyle <mlyle@lyle.org>
+M:	Coly Li <colyli@suse.de>
 M:	Kent Overstreet <kent.overstreet@gmail.com>
 L:	linux-bcache@vger.kernel.org
 W:	http://bcache.evilpiepirate.org
@@ -3078,7 +3092,6 @@ F:	include/linux/btrfs*
 F:	include/uapi/linux/btrfs*
 
 BTTV VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -3428,6 +3441,12 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
 F:	drivers/input/touchscreen/chipone_icn8318.c
 
+CHIPONE ICN8505 I2C TOUCHSCREEN DRIVER
+M:	Hans de Goede <hdegoede@redhat.com>
+L:	linux-input@vger.kernel.org
+S:	Maintained
+F:	drivers/input/touchscreen/chipone_icn8505.c
+
 CHROME HARDWARE PLATFORM SUPPORT
 M:	Benson Leung <bleung@chromium.org>
 M:	Olof Johansson <olof@lixom.net>
@@ -3688,7 +3707,6 @@ F:	drivers/cpufreq/arm_big_little_dt.c
 
 CPU POWER MONITORING SUBSYSTEM
 M:	Thomas Renninger <trenn@suse.com>
-M:	Shuah Khan <shuahkh@osg.samsung.com>
 M:	Shuah Khan <shuah@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
@@ -3807,7 +3825,6 @@ S:	Maintained
 F:	drivers/media/dvb-frontends/cx24120*
 
 CX88 VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -4245,6 +4262,9 @@ F:	include/trace/events/fs_dax.h
 
 DEVICE DIRECT ACCESS (DAX)
 M:	Dan Williams <dan.j.williams@intel.com>
+M:	Dave Jiang <dave.jiang@intel.com>
+M:	Ross Zwisler <ross.zwisler@linux.intel.com>
+M:	Vishal Verma <vishal.l.verma@intel.com>
 L:	linux-nvdimm@lists.01.org
 S:	Supported
 F:	drivers/dax/
@@ -4305,7 +4325,7 @@ F:	Documentation/driver-api/dma-buf.rst
 T:	git git://anongit.freedesktop.org/drm/drm-misc
 
 DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
-M:	Vinod Koul <vinod.koul@intel.com>
+M:	Vinod Koul <vkoul@kernel.org>
 L:	dmaengine@vger.kernel.org
 Q:	https://patchwork.kernel.org/project/linux-dmaengine/list/
 S:	Maintained
@@ -4326,12 +4346,14 @@ W:	http://git.infradead.org/users/hch/dma-mapping.git
 S:	Supported
 F:	lib/dma-debug.c
 F:	lib/dma-direct.c
+F:	lib/dma-noncoherent.c
 F:	lib/dma-virt.c
 F:	drivers/base/dma-mapping.c
 F:	drivers/base/dma-coherent.c
 F:	include/asm-generic/dma-mapping.h
 F:	include/linux/dma-direct.h
 F:	include/linux/dma-mapping.h
+F:	include/linux/dma-noncoherent.h
 
 DME1737 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
@@ -4665,7 +4687,7 @@ F:	Documentation/devicetree/bindings/display/exynos/
 
 DRM DRIVERS FOR FREESCALE DCU
 M:	Stefan Agner <stefan@agner.ch>
-M:	Alison Wang <alison.wang@freescale.com>
+M:	Alison Wang <alison.wang@nxp.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Supported
 F:	drivers/gpu/drm/fsl-dcu/
@@ -4776,6 +4798,14 @@ S:	Maintained
 F:	drivers/gpu/drm/omapdrm/
 F:	Documentation/devicetree/bindings/display/ti/
 
+DRM DRIVERS FOR V3D
+M:	Eric Anholt <eric@anholt.net>
+S:	Supported
+F:	drivers/gpu/drm/v3d/
+F:	include/uapi/drm/v3d_drm.h
+F:	Documentation/devicetree/bindings/display/brcm,bcm-v3d.txt
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+
 DRM DRIVERS FOR VC4
 M:	Eric Anholt <eric@anholt.net>
 T:	git git://github.com/anholt/linux
@@ -4822,6 +4852,15 @@ S:	Maintained
 F:	drivers/gpu/drm/tinydrm/
 F:	include/drm/tinydrm/
 
+DRM DRIVERS FOR XEN
+M:	Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+L:	dri-devel@lists.freedesktop.org
+L:	xen-devel@lists.xen.org
+S:	Supported
+F:	drivers/gpu/drm/xen/
+F:	Documentation/gpu/xen-front.rst
+
 DRM TTM SUBSYSTEM
 M:	Christian Koenig <christian.koenig@amd.com>
 M:	Roger He <Hongbo.He@amd.com>
@@ -5045,7 +5084,6 @@ F:	drivers/edac/thunderx_edac*
 
 EDAC-CORE
 M:	Borislav Petkov <bp@alien8.de>
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-edac@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next
@@ -5074,7 +5112,6 @@ S:	Maintained
 F:	drivers/edac/fsl_ddr_edac.*
 
 EDAC-GHES
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
@@ -5091,21 +5128,18 @@ S:	Maintained
 F:	drivers/edac/i5000_edac.c
 
 EDAC-I5400
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	drivers/edac/i5400_edac.c
 
 EDAC-I7300
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	drivers/edac/i7300_edac.c
 
 EDAC-I7CORE
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
@@ -5155,7 +5189,6 @@ S:	Maintained
 F:	drivers/edac/r82600_edac.c
 
 EDAC-SBRIDGE
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
@@ -5214,7 +5247,6 @@ S:	Maintained
 F:	drivers/net/ethernet/ibm/ehea/
 
 EM28XX VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -5391,7 +5423,6 @@ S:	Maintained
 F:	drivers/iommu/exynos-iommu.c
 
 EZchip NPS platform support
-M:	Elad Kanfi <eladkan@mellanox.com>
 M:	Vineet Gupta <vgupta@synopsys.com>
 S:	Supported
 F:	arch/arc/plat-eznps
@@ -5417,6 +5448,11 @@ S:	Maintained
 F:	Documentation/hwmon/f71805f
 F:	drivers/hwmon/f71805f.c
 
+FADDR2LINE
+M:	Josh Poimboeuf <jpoimboe@redhat.com>
+S:	Maintained
+F:	scripts/faddr2line
+
 FANOTIFY
 M:	Jan Kara <jack@suse.cz>
 R:	Amir Goldstein <amir73il@gmail.com>
@@ -5569,6 +5605,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/atull/linux-fpga.git
 Q:	http://patchwork.kernel.org/project/linux-fpga/list/
 F:	Documentation/fpga/
+F:	Documentation/driver-api/fpga/
 F:	Documentation/devicetree/bindings/fpga/
 F:	drivers/fpga/
 F:	include/linux/fpga/
@@ -5652,7 +5689,8 @@ F:	drivers/net/ethernet/freescale/fec.h
 F:	Documentation/devicetree/bindings/net/fsl-fec.txt
 
 FREESCALE IMX / MXC FRAMEBUFFER DRIVER
-M:	Sascha Hauer <kernel@pengutronix.de>
+M:	Sascha Hauer <s.hauer@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 L:	linux-fbdev@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -5784,6 +5822,14 @@ F:	fs/crypto/
 F:	include/linux/fscrypt*.h
 F:	Documentation/filesystems/fscrypt.rst
 
+FSNOTIFY: FILESYSTEM NOTIFICATION INFRASTRUCTURE
+M:	Jan Kara <jack@suse.cz>
+R:	Amir Goldstein <amir73il@gmail.com>
+L:	linux-fsdevel@vger.kernel.org
+S:	Maintained
+F:	fs/notify/
+F:	include/linux/fsnotify*.h
+
 FUJITSU LAPTOP EXTRAS
 M:	Jonathan Woithe <jwoithe@just42.net>
 L:	platform-driver-x86@vger.kernel.org
@@ -5943,8 +5989,8 @@ S:	Maintained
 F:	scripts/get_maintainer.pl
 
 GFS2 FILE SYSTEM
-M:	Steven Whitehouse <swhiteho@redhat.com>
 M:	Bob Peterson <rpeterso@redhat.com>
+M:	Andreas Gruenbacher <agruenba@redhat.com>
 L:	cluster-devel@redhat.com
 W:	http://sources.redhat.com/cluster/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2.git
@@ -6212,6 +6258,7 @@ L:	linux-hwmon@vger.kernel.org
 W:	http://hwmon.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/hwmon/
 F:	Documentation/hwmon/
 F:	drivers/hwmon/
 F:	include/linux/hwmon*.h
@@ -6256,7 +6303,7 @@ S:	Odd Fixes
 F:	drivers/media/usb/hdpvr/
 
 HEWLETT PACKARD ENTERPRISE ILO NMI WATCHDOG DRIVER
-M:	Jimmy Vance <jimmy.vance@hpe.com>
+M:	Jerry Hoemann <jerry.hoemann@hpe.com>
 S:	Supported
 F:	Documentation/watchdog/hpwdt.txt
 F:	drivers/watchdog/hpwdt.c
@@ -6498,9 +6545,15 @@ F:	Documentation/networking/hinic.txt
 F:	drivers/net/ethernet/huawei/hinic/
 
 HUGETLB FILESYSTEM
-M:	Nadia Yvette Chambers <nyc@holomorphy.com>
+M:	Mike Kravetz <mike.kravetz@oracle.com>
+L:	linux-mm@kvack.org
 S:	Maintained
 F:	fs/hugetlbfs/
+F:	mm/hugetlb.c
+F:	include/linux/hugetlb.h
+F:	Documentation/admin-guide/mm/hugetlbpage.rst
+F:	Documentation/vm/hugetlbfs_reserv.rst
+F:	Documentation/ABI/testing/sysfs-kernel-mm-hugepages
 
 HVA ST MEDIA DRIVER
 M:	Jean-Christophe Trotin <jean-christophe.trotin@st.com>
@@ -6740,6 +6793,12 @@ L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	drivers/scsi/ibmvscsi/ibmvfc*
 
+IBM Power Virtual Management Channel Driver
+M:	Bryant G. Ly <bryantly@linux.vnet.ibm.com>
+M:	Steven Royer <seroyer@linux.vnet.ibm.com>
+S:	Supported
+F:	drivers/misc/ibmvmc.*
+
 IBM Power Virtual SCSI Device Drivers
 M:	Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
 L:	linux-scsi@vger.kernel.org
@@ -7023,14 +7082,13 @@ L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/fbdev/i810/
 
-INTEL ASoC BDW/HSW DRIVERS
+INTEL ASoC DRIVERS
+M:	Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
+M:	Liam Girdwood <liam.r.girdwood@linux.intel.com>
 M:	Jie Yang <yang.jie@linux.intel.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
-F:	sound/soc/intel/common/sst-dsp*
-F:	sound/soc/intel/common/sst-firmware.c
-F:	sound/soc/intel/boards/broadwell.c
-F:	sound/soc/intel/haswell/
+F:	sound/soc/intel/
 
 INTEL C600 SERIES SAS CONTROLLER DRIVER
 M:	Intel SCU Linux support <intel-linux-scu@intel.com>
@@ -7396,16 +7454,6 @@ S:	Obsolete
 F:	include/uapi/linux/ipx.h
 F:	drivers/staging/ipx/
 
-IRDA SUBSYSTEM
-M:	Samuel Ortiz <samuel@sortiz.org>
-L:	irda-users@lists.sourceforge.net (subscribers-only)
-L:	netdev@vger.kernel.org
-W:	http://irda.sourceforge.net/
-S:	Obsolete
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sameo/irda-2.6.git
-F:	Documentation/networking/irda.txt
-F:	drivers/staging/irda/
-
 IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
 M:	Marc Zyngier <marc.zyngier@arm.com>
 S:	Maintained
@@ -7636,8 +7684,9 @@ M:	Masahiro Yamada <yamada.masahiro@socionext.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git kconfig
 L:	linux-kbuild@vger.kernel.org
 S:	Maintained
-F:	Documentation/kbuild/kconfig-language.txt
+F:	Documentation/kbuild/kconfig*
 F:	scripts/kconfig/
+F:	scripts/Kconfig.include
 
 KDUMP
 M:	Dave Young <dyoung@redhat.com>
@@ -7670,9 +7719,11 @@ L:	linux-kbuild@vger.kernel.org
 S:	Maintained
 F:	Documentation/kbuild/
 F:	Makefile
-F:	scripts/Makefile.*
+F:	scripts/Kbuild*
+F:	scripts/Makefile*
 F:	scripts/basic/
 F:	scripts/mk*
+F:	scripts/mod/
 F:	scripts/package/
 
 KERNEL JANITORS
@@ -7697,10 +7748,10 @@ F:	include/linux/sunrpc/
 F:	include/uapi/linux/sunrpc/
 
 KERNEL SELFTEST FRAMEWORK
-M:	Shuah Khan <shuahkh@osg.samsung.com>
 M:	Shuah Khan <shuah@kernel.org>
 L:	linux-kselftest@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git
+Q:	https://patchwork.kernel.org/project/linux-kselftest/list/
 S:	Maintained
 F:	tools/testing/selftests/
 F:	Documentation/dev-tools/kselftest*
@@ -7738,7 +7789,7 @@ F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
 KERNEL VIRTUAL MACHINE FOR ARM (KVM/arm)
-M:	Christoffer Dall <christoffer.dall@linaro.org>
+M:	Christoffer Dall <christoffer.dall@arm.com>
 M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.cs.columbia.edu
@@ -7752,7 +7803,7 @@ F:	virt/kvm/arm/
 F:	include/kvm/arm_*
 
 KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
-M:	Christoffer Dall <christoffer.dall@linaro.org>
+M:	Christoffer Dall <christoffer.dall@arm.com>
 M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.cs.columbia.edu
@@ -8048,6 +8099,9 @@ F:	tools/lib/lockdep/
 
 LIBNVDIMM BLK: MMIO-APERTURE DRIVER
 M:	Ross Zwisler <ross.zwisler@linux.intel.com>
+M:	Dan Williams <dan.j.williams@intel.com>
+M:	Vishal Verma <vishal.l.verma@intel.com>
+M:	Dave Jiang <dave.jiang@intel.com>
 L:	linux-nvdimm@lists.01.org
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
@@ -8056,6 +8110,9 @@ F:	drivers/nvdimm/region_devs.c
 
 LIBNVDIMM BTT: BLOCK TRANSLATION TABLE
 M:	Vishal Verma <vishal.l.verma@intel.com>
+M:	Dan Williams <dan.j.williams@intel.com>
+M:	Ross Zwisler <ross.zwisler@linux.intel.com>
+M:	Dave Jiang <dave.jiang@intel.com>
 L:	linux-nvdimm@lists.01.org
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
@@ -8063,6 +8120,9 @@ F:	drivers/nvdimm/btt*
 
 LIBNVDIMM PMEM: PERSISTENT MEMORY DRIVER
 M:	Ross Zwisler <ross.zwisler@linux.intel.com>
+M:	Dan Williams <dan.j.williams@intel.com>
+M:	Vishal Verma <vishal.l.verma@intel.com>
+M:	Dave Jiang <dave.jiang@intel.com>
 L:	linux-nvdimm@lists.01.org
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
@@ -8078,6 +8138,9 @@ F:	Documentation/devicetree/bindings/pmem/pmem-region.txt
 
 LIBNVDIMM: NON-VOLATILE MEMORY DEVICE SUBSYSTEM
 M:	Dan Williams <dan.j.williams@intel.com>
+M:	Ross Zwisler <ross.zwisler@linux.intel.com>
+M:	Vishal Verma <vishal.l.verma@intel.com>
+M:	Dave Jiang <dave.jiang@intel.com>
 L:	linux-nvdimm@lists.01.org
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm.git
@@ -8194,7 +8257,7 @@ F:	drivers/misc/lkdtm/*
 
 LINUX KERNEL MEMORY CONSISTENCY MODEL (LKMM)
 M:	Alan Stern <stern@rowland.harvard.edu>
-M:	Andrea Parri <parri.andrea@gmail.com>
+M:	Andrea Parri <andrea.parri@amarulasolutions.com>
 M:	Will Deacon <will.deacon@arm.com>
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Boqun Feng <boqun.feng@gmail.com>
@@ -8301,6 +8364,7 @@ F:	Documentation/admin-guide/LSM/LoadPin.rst
 LOCKING PRIMITIVES
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
+M:	Will Deacon <will.deacon@arm.com>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
 S:	Maintained
@@ -8852,7 +8916,6 @@ F:	Documentation/devicetree/bindings/media/nvidia,tegra-vde.txt
 F:	drivers/staging/media/tegra-vde/
 
 MEDIA INPUT INFRASTRUCTURE (V4L/DVB)
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 P:	LinuxTV.org Project
 L:	linux-media@vger.kernel.org
@@ -9012,7 +9075,6 @@ Q:	http://patchwork.ozlabs.org/project/netdev/list/
 F:	drivers/net/ethernet/mellanox/mlx5/core/en_*
 
 MELLANOX ETHERNET INNOVA DRIVER
-M:	Ilan Tayari <ilant@mellanox.com>
 R:	Boris Pismenny <borisp@mellanox.com>
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -9022,7 +9084,6 @@ F:	drivers/net/ethernet/mellanox/mlx5/core/fpga/*
 F:	include/linux/mlx5/mlx5_ifc_fpga.h
 
 MELLANOX ETHERNET INNOVA IPSEC DRIVER
-M:	Ilan Tayari <ilant@mellanox.com>
 R:	Boris Pismenny <borisp@mellanox.com>
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -9078,7 +9139,6 @@ F:	include/uapi/rdma/mlx4-abi.h
 
 MELLANOX MLX5 core VPI driver
 M:	Saeed Mahameed <saeedm@mellanox.com>
-M:	Matan Barak <matanb@mellanox.com>
 M:	Leon Romanovsky <leonro@mellanox.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
@@ -9089,7 +9149,6 @@ F:	drivers/net/ethernet/mellanox/mlx5/core/
 F:	include/linux/mlx5/
 
 MELLANOX MLX5 IB driver
-M:	Matan Barak <matanb@mellanox.com>
 M:	Leon Romanovsky <leonro@mellanox.com>
 L:	linux-rdma@vger.kernel.org
 W:	http://www.mellanox.com
@@ -9690,7 +9749,7 @@ S:	Maintained
 F:	drivers/net/ethernet/netronome/
 
 NETWORK BLOCK DEVICE (NBD)
-M:	Josef Bacik <jbacik@fb.com>
+M:	Josef Bacik <josef@toxicpanda.com>
 S:	Maintained
 L:	linux-block@vger.kernel.org
 L:	nbd@other.debian.org
@@ -9706,6 +9765,7 @@ W:	https://fedorahosted.org/dropwatch/
 F:	net/core/drop_monitor.c
 
 NETWORKING DRIVERS
+M:	"David S. Miller" <davem@davemloft.net>
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
@@ -9765,6 +9825,7 @@ F:	include/uapi/linux/net_namespace.h
 F:	tools/testing/selftests/net/
 F:	lib/net_utils.c
 F:	lib/random32.c
+F:	Documentation/networking/
 
 NETWORKING [IPSEC]
 M:	Steffen Klassert <steffen.klassert@secunet.com>
@@ -9821,7 +9882,6 @@ F:	net/netfilter/xt_CONNSECMARK.c
 F:	net/netfilter/xt_SECMARK.c
 
 NETWORKING [TLS]
-M:	Ilya Lesokhin <ilyal@mellanox.com>
 M:	Aviad Yehezkel <aviadye@mellanox.com>
 M:	Dave Watson <davejwatson@fb.com>
 L:	netdev@vger.kernel.org
@@ -9861,7 +9921,7 @@ F:	include/linux/platform_data/nxp-nci.h
 F:	Documentation/devicetree/bindings/net/nfc/
 
 NFS, SUNRPC, AND LOCKD CLIENTS
-M:	Trond Myklebust <trond.myklebust@primarydata.com>
+M:	Trond Myklebust <trond.myklebust@hammerspace.com>
 M:	Anna Schumaker <anna.schumaker@netapp.com>
 L:	linux-nfs@vger.kernel.org
 W:	http://client.linux-nfs.org
@@ -10881,7 +10941,6 @@ F:	drivers/pci/host/
 F:	drivers/pci/dwc/
 
 PCIE DRIVER FOR AXIS ARTPEC
-M:	Niklas Cassel <niklas.cassel@axis.com>
 M:	Jesper Nilsson <jesper.nilsson@axis.com>
 L:	linux-arm-kernel@axis.com
 L:	linux-pci@vger.kernel.org
@@ -11242,6 +11301,7 @@ M:	Sebastian Reichel <sre@kernel.org>
 L:	linux-pm@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sre/linux-power-supply.git
 S:	Maintained
+F:	Documentation/ABI/testing/sysfs-class-power
 F:	Documentation/devicetree/bindings/power/supply/
 F:	include/linux/power_supply.h
 F:	drivers/power/supply/
@@ -11622,7 +11682,7 @@ S:	Maintained
 F:	drivers/media/tuners/qt1010*
 
 QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
-M:	Kalle Valo <kvalo@qca.qualcomm.com>
+M:	Kalle Valo <kvalo@codeaurora.org>
 L:	ath10k@lists.infradead.org
 W:	http://wireless.kernel.org/en/users/Drivers/ath10k
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
@@ -11644,6 +11704,13 @@ F:	Documentation/devicetree/bindings/media/qcom,camss.txt
 F:	Documentation/media/v4l-drivers/qcom_camss.rst
 F:	drivers/media/platform/qcom/camss-8x16/
 
+QUALCOMM CPUFREQ DRIVER MSM8996/APQ8096
+M:  Ilia Lin <ilia.lin@gmail.com>
+L:  linux-pm@vger.kernel.org
+S:  Maintained
+F:  Documentation/devicetree/bindings/opp/kryo-cpufreq.txt
+F:  drivers/cpufreq/qcom-cpufreq-kryo.c
+
 QUALCOMM EMAC GIGABIT ETHERNET DRIVER
 M:	Timur Tabi <timur@codeaurora.org>
 L:	netdev@vger.kernel.org
@@ -11673,7 +11740,7 @@ S:	Maintained
 F:	drivers/media/platform/qcom/venus/
 
 QUALCOMM WCN36XX WIRELESS DRIVER
-M:	Eugene Krasnikov <k.eugene.e@gmail.com>
+M:	Kalle Valo <kvalo@codeaurora.org>
 L:	wcn36xx@lists.infradead.org
 W:	http://wireless.kernel.org/en/users/Drivers/wcn36xx
 T:	git git://github.com/KrasnikovEugene/wcn36xx.git
@@ -11868,7 +11935,7 @@ F:	include/linux/rtc.h
 F:	include/uapi/linux/rtc.h
 F:	include/linux/rtc/
 F:	include/linux/platform_data/rtc-*
-F:	tools/testing/selftests/timers/rtctest.c
+F:	tools/testing/selftests/rtc/
 
 REALTEK AUDIO CODECS
 M:	Bard Liao <bardliao@realtek.com>
@@ -12211,7 +12278,7 @@ F:	Documentation/s390/vfio-ccw.txt
 F:	include/uapi/linux/vfio_ccw.h
 
 S390 ZCRYPT DRIVER
-M:	Harald Freudenberger <freude@de.ibm.com>
+M:	Harald Freudenberger <freude@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
@@ -12240,7 +12307,6 @@ S:	Odd Fixes
 F:	drivers/media/i2c/saa6588*
 
 SAA7134 VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -12479,6 +12545,7 @@ F:	drivers/scsi/st_*.h
 SCTP PROTOCOL
 M:	Vlad Yasevich <vyasevich@gmail.com>
 M:	Neil Horman <nhorman@tuxdriver.com>
+M:	Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
 L:	linux-sctp@vger.kernel.org
 W:	http://lksctp.sourceforge.net
 S:	Maintained
@@ -12744,7 +12811,6 @@ S:	Maintained
 F:	drivers/media/radio/si4713/radio-usb-si4713.c
 
 SIANO DVB DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -12816,7 +12882,8 @@ F:	include/linux/siphash.h
 
 SIOX
 M:	Gavin Schenk <g.schenk@eckelmann.de>
-M:	Uwe Kleine-König <kernel@pengutronix.de>
+M:	Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 S:	Supported
 F:	drivers/siox/*
 F:	include/trace/events/siox.h
@@ -13095,7 +13162,7 @@ F:	include/uapi/sound/
 F:	sound/
 
 SOUND - COMPRESSED AUDIO
-M:	Vinod Koul <vinod.koul@intel.com>
+M:	Vinod Koul <vkoul@kernel.org>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
 S:	Supported
@@ -13255,6 +13322,12 @@ M:	Jan-Benedict Glaw <jbglaw@lug-owl.de>
 S:	Maintained
 F:	arch/alpha/kernel/srm_env.c
 
+ST STM32 I2C/SMBUS DRIVER
+M:	Pierre-Yves MORDRET <pierre-yves.mordret@st.com>
+L:	linux-i2c@vger.kernel.org
+S:	Maintained
+F:	drivers/i2c/busses/i2c-stm32*
+
 STABLE BRANCH
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	stable@vger.kernel.org
@@ -13734,7 +13807,6 @@ S:	Maintained
 F:	drivers/media/i2c/tda9840*
 
 TEA5761 TUNER DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -13743,7 +13815,6 @@ S:	Odd fixes
 F:	drivers/media/tuners/tea5761.*
 
 TEA5767 TUNER DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -13833,7 +13904,6 @@ S:	Supported
 F:	drivers/iommu/tegra*
 
 TEGRA KBC DRIVER
-M:	Rakesh Iyer <riyer@nvidia.com>
 M:	Laxman Dewangan <ldewangan@nvidia.com>
 S:	Supported
 F:	drivers/input/keyboard/tegra-kbc.c
@@ -13936,7 +14006,7 @@ THUNDERBOLT DRIVER
 M:	Andreas Noever <andreas.noever@gmail.com>
 M:	Michael Jamet <michael.jamet@intel.com>
 M:	Mika Westerberg <mika.westerberg@linux.intel.com>
-M:	Yehezkel Bernat <yehezkel.bernat@intel.com>
+M:	Yehezkel Bernat <YehezkelShB@gmail.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
 S:	Maintained
 F:	Documentation/admin-guide/thunderbolt.rst
@@ -13946,7 +14016,7 @@ F:	include/linux/thunderbolt.h
 THUNDERBOLT NETWORK DRIVER
 M:	Michael Jamet <michael.jamet@intel.com>
 M:	Mika Westerberg <mika.westerberg@linux.intel.com>
-M:	Yehezkel Bernat <yehezkel.bernat@intel.com>
+M:	Yehezkel Bernat <YehezkelShB@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/thunderbolt.c
@@ -14160,7 +14230,6 @@ F:	Documentation/networking/tlan.txt
 F:	drivers/net/ethernet/ti/tlan.*
 
 TM6000 VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -14359,6 +14428,15 @@ S:	Maintained
 F:	drivers/tc/
 F:	include/linux/tc.h
 
+TURBOSTAT UTILITY
+M:	"Len Brown" <lenb@kernel.org>
+L:	linux-pm@vger.kernel.org
+B:	https://bugzilla.kernel.org
+Q:	https://patchwork.kernel.org/project/linux-pm/list/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat
+S:	Supported
+F:	tools/power/x86/turbostat/
+
 TW5864 VIDEO4LINUX DRIVER
 M:	Bluecherry Maintainers <maintainers@bluecherrydvr.com>
 M:	Anton Sviridenko <anton@corp.bluecherry.net>
@@ -14643,13 +14721,13 @@ F:	drivers/usb/common/usb-otg-fsm.c
 
 USB OVER IP DRIVER
 M:	Valentina Manea <valentina.manea.m@gmail.com>
-M:	Shuah Khan <shuahkh@osg.samsung.com>
 M:	Shuah Khan <shuah@kernel.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	Documentation/usb/usbip_protocol.txt
 F:	drivers/usb/usbip/
 F:	tools/usb/usbip/
+F:	tools/testing/selftests/drivers/usb/usbip/
 
 USB PEGASUS DRIVER
 M:	Petko Manolov <petkan@nucleusys.com>
@@ -15387,7 +15465,6 @@ S:	Maintained
 F:	arch/x86/entry/vdso/
 
 XC2028/3028 TUNER DRIVER
-M:	Mauro Carvalho Chehab <mchehab@s-opensource.com>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
@@ -15465,6 +15542,13 @@ S:	Supported
 F:	arch/x86/xen/*swiotlb*
 F:	drivers/xen/*swiotlb*
 
+XEN SOUND FRONTEND DRIVER
+M:	Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Supported
+F:	sound/xen/*
+
 XFS FILESYSTEM
 M:	Darrick J. Wong <darrick.wong@oracle.com>
 M:	linux-xfs@vger.kernel.org
@@ -15503,6 +15587,14 @@ L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	drivers/char/xillybus/
 
+XLP9XX I2C DRIVER
+M:	George Cherian <george.cherian@cavium.com>
+M:	Jan Glauber <jglauber@cavium.com>
+L:	linux-i2c@vger.kernel.org
+W:	http://www.cavium.com
+S:	Supported
+F:	drivers/i2c/busses/i2c-xlp9xx.c
+
 XRA1403 GPIO EXPANDER
 M:	Nandor Han <nandor.han@ge.com>
 M:	Semi Malinen <semi.malinen@ge.com>
@@ -15621,7 +15713,7 @@ L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zsmalloc.c
 F:	include/linux/zsmalloc.h
-F:	Documentation/vm/zsmalloc.txt
+F:	Documentation/vm/zsmalloc.rst
 
 ZSWAP COMPRESSED SWAP CACHING
 M:	Seth Jennings <sjenning@redhat.com>
diff --git a/Makefile b/Makefile
index e811e0c509c5..bbc979aeea29 100644
--- a/Makefile
+++ b/Makefile
@@ -2,8 +2,8 @@
 VERSION = 4
 PATCHLEVEL = 17
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
-NAME = Fearless Coyote
+EXTRAVERSION =
+NAME = Merciless Moray
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -316,12 +316,9 @@ SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
 # CROSS_COMPILE can be set on the command line
 # make CROSS_COMPILE=ia64-linux-
 # Alternatively CROSS_COMPILE can be set in the environment.
-# A third alternative is to store a setting in .config so that plain
-# "make" in the configured kernel build directory always uses that.
 # Default value for CROSS_COMPILE is not to prefix executables
 # Note: Some architectures assign CROSS_COMPILE in their arch/*/Makefile
 ARCH		?= $(SUBARCH)
-CROSS_COMPILE	?= $(CONFIG_CROSS_COMPILE:"%"=%)
 
 # Architecture as present in compile.h
 UTS_MACHINE 	:= $(ARCH)
@@ -445,6 +442,8 @@ export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE
 export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL
 export KBUILD_ARFLAGS
 
+export CC_VERSION_TEXT := $(shell $(CC) --version | head -n 1)
+
 # When compiling out-of-tree modules, put MODVERDIR in the module
 # tree rather than in the kernel tree. The kernel tree might
 # even be read-only.
@@ -500,8 +499,11 @@ RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk
 RETPOLINE_CFLAGS := $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG)))
 export RETPOLINE_CFLAGS
 
+KBUILD_CFLAGS	+= $(call cc-option,-fno-PIE)
+KBUILD_AFLAGS	+= $(call cc-option,-fno-PIE)
+
 # check for 'asm goto'
-ifeq ($(call shell-cached,$(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
   CC_HAVE_ASM_GOTO := 1
   KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
   KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
@@ -621,9 +623,9 @@ endif # $(dot-config)
 # Defaults to vmlinux, but the arch makefile usually adds further targets
 all: vmlinux
 
-KBUILD_CFLAGS	+= $(call cc-option,-fno-PIE)
-KBUILD_AFLAGS	+= $(call cc-option,-fno-PIE)
-CFLAGS_GCOV	:= -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,)
+CFLAGS_GCOV	:= -fprofile-arcs -ftest-coverage \
+	$(call cc-option,-fno-tree-loop-im) \
+	$(call cc-disable-warning,maybe-uninitialized,)
 export CFLAGS_GCOV CFLAGS_KCOV
 
 # The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default
@@ -799,13 +801,12 @@ KBUILD_CFLAGS += $(call cc-option, -fno-inline-functions-called-once)
 endif
 
 ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
-KBUILD_CFLAGS	+= $(call cc-option,-ffunction-sections,)
-KBUILD_CFLAGS	+= $(call cc-option,-fdata-sections,)
+KBUILD_CFLAGS_KERNEL	+= $(call cc-option,-ffunction-sections,)
+KBUILD_CFLAGS_KERNEL	+= $(call cc-option,-fdata-sections,)
 endif
 
 # arch Makefile may override CC so keep this after arch Makefile is included
-NOSTDINC_FLAGS += -nostdinc -isystem $(call shell-cached,$(CC) -print-file-name=include)
-CHECKFLAGS     += $(NOSTDINC_FLAGS)
+NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include)
 
 # warn about C99 declaration after statement
 KBUILD_CFLAGS += $(call cc-option,-Wdeclaration-after-statement,)
@@ -875,6 +876,12 @@ ifeq ($(CONFIG_STRIP_ASM_SYMS),y)
 LDFLAGS_vmlinux	+= $(call ld-option, -X,)
 endif
 
+# insure the checker run with the right endianness
+CHECKFLAGS += $(if $(CONFIG_CPU_BIG_ENDIAN),-mbig-endian,-mlittle-endian)
+
+# the checker needs the correct machine size
+CHECKFLAGS += $(if $(CONFIG_64BIT),-m64,-m32)
+
 # Default kernel image to build when no specific target is given.
 # KBUILD_IMAGE may be overruled on the command line or
 # set in the environment
@@ -1622,7 +1629,6 @@ clean: $(clean-dirs)
 		-o -name '*.asn1.[ch]' \
 		-o -name '*.symtypes' -o -name 'modules.order' \
 		-o -name modules.builtin -o -name '.tmp_*.o.*' \
-		-o -name .cache.mk \
 		-o -name '*.c.[012]*.*' \
 		-o -name '*.ll' \
 		-o -name '*.gcno' \) -type f -print | xargs rm -f
@@ -1760,7 +1766,7 @@ quiet_cmd_rmfiles = $(if $(wildcard $(rm-files)),CLEAN   $(wildcard $(rm-files))
 # Run depmod only if we have System.map and depmod is executable
 quiet_cmd_depmod = DEPMOD  $(KERNELRELEASE)
       cmd_depmod = $(CONFIG_SHELL) $(srctree)/scripts/depmod.sh $(DEPMOD) \
-                   $(KERNELRELEASE) "$(patsubst y,_,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX))"
+                   $(KERNELRELEASE)
 
 # Create temporary dir for module support files
 # clean it up only when building all modules
diff --git a/arch/Kconfig b/arch/Kconfig
index 8e0d665c8d53..8a7f7e1f2ca7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -278,9 +278,6 @@ config HAVE_CLK
 	  The <linux/clk.h> calls support software clock gating and
 	  thus are a key power management tool on many systems.
 
-config HAVE_DMA_API_DEBUG
-	bool
-
 config HAVE_HW_BREAKPOINT
 	bool
 	depends on PERF_EVENTS
@@ -464,6 +461,10 @@ config GCC_PLUGIN_LATENT_ENTROPY
 config GCC_PLUGIN_STRUCTLEAK
 	bool "Force initialization of variables containing userspace addresses"
 	depends on GCC_PLUGINS
+	# Currently STRUCTLEAK inserts initialization out of live scope of
+	# variables from KASAN point of view. This leads to KASAN false
+	# positive reports. Prohibit this combination for now.
+	depends on !KASAN_EXTRA
 	help
 	  This plugin zero-initializes any structures containing a
 	  __user attribute. This can prevent some classes of information
@@ -596,21 +597,6 @@ config CC_STACKPROTECTOR_AUTO
 
 endchoice
 
-config LD_DEAD_CODE_DATA_ELIMINATION
-	bool
-	help
-	  Select this if the architecture wants to do dead code and
-	  data elimination with the linker by compiling with
-	  -ffunction-sections -fdata-sections and linking with
-	  --gc-sections.
-
-	  This requires that the arch annotates or otherwise protects
-	  its external entry points from being discarded. Linker scripts
-	  must also merge .text.*, .data.*, and .bss.* correctly into
-	  output sections. Care must be taken not to pull in unrelated
-	  sections (e.g., '.text.init'). Typically '.' in section names
-	  is used to distinguish them from label names / C identifiers.
-
 config HAVE_ARCH_WITHIN_STACK_FRAMES
 	bool
 	help
@@ -686,12 +672,6 @@ config MODULES_USE_ELF_REL
 	  Modules only use ELF REL relocations.  Modules with ELF RELA
 	  relocations will give an error.
 
-config HAVE_UNDERSCORE_SYMBOL_PREFIX
-	bool
-	help
-	  Some architectures generate an _ in front of C symbols; things like
-	  module loading and assembly files need to know about this.
-
 config HAVE_IRQ_EXIT_ON_IRQ_STACK
 	bool
 	help
@@ -870,6 +850,21 @@ config OLD_SIGACTION
 config COMPAT_OLD_SIGACTION
 	bool
 
+config 64BIT_TIME
+	def_bool ARCH_HAS_64BIT_TIME
+	help
+	  This should be selected by all architectures that need to support
+	  new system calls with a 64-bit time_t. This is relevant on all 32-bit
+	  architectures, and 64-bit architectures as part of compat syscall
+	  handling.
+
+config COMPAT_32BIT_TIME
+	def_bool (!64BIT && 64BIT_TIME) || COMPAT
+	help
+	  This enables 32 bit time_t support in addition to 64 bit time_t support.
+	  This is relevant on all 32-bit architectures, and 64-bit architectures
+	  as part of compat syscall handling.
+
 config ARCH_NO_COHERENT_DMA_MMAP
 	bool
 
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index b2022885ced8..0c4805a572c8 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -10,6 +10,8 @@ config ALPHA
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
+	select NEED_DMA_MAP_STATE
+	select NEED_SG_DMA_LENGTH
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select AUTO_IRQ_AFFINITY if SMP
@@ -64,15 +66,6 @@ config ZONE_DMA
 	bool
 	default y
 
-config ARCH_DMA_ADDR_T_64BIT
-	def_bool y
-
-config NEED_DMA_MAP_STATE
-       def_bool y
-
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
 config GENERIC_ISA_DMA
 	bool
 	default y
@@ -211,6 +204,7 @@ config ALPHA_EIGER
 config ALPHA_JENSEN
 	bool "Jensen"
 	depends on BROKEN
+	select DMA_DIRECT_OPS
 	help
 	  DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one
 	  of the first-generation Alpha systems. A number of these systems
@@ -345,9 +339,6 @@ config PCI_DOMAINS
 config PCI_SYSCALL
 	def_bool PCI
 
-config IOMMU_HELPER
-	def_bool PCI
-
 config ALPHA_NONAME
 	bool
 	depends on ALPHA_BOOK1 || ALPHA_NONAME_CH
@@ -585,7 +576,7 @@ config ARCH_DISCONTIGMEM_ENABLE
 	  Say Y to support efficient handling of discontiguous physical memory,
 	  for architectures which are either NUMA (Non-Uniform Memory Access)
 	  or have huge holes in the physical address space for other reasons.
-	  See <file:Documentation/vm/numa> for more.
+	  See <file:Documentation/vm/numa.rst> for more.
 
 source "mm/Kconfig"
 
diff --git a/arch/alpha/Makefile b/arch/alpha/Makefile
index 2cc3cc519c54..c5ec8c09c0c6 100644
--- a/arch/alpha/Makefile
+++ b/arch/alpha/Makefile
@@ -11,7 +11,7 @@
 NM := $(NM) -B
 
 LDFLAGS_vmlinux	:= -static -N #-relax
-CHECKFLAGS	+= -D__alpha__ -m64
+CHECKFLAGS	+= -D__alpha__
 cflags-y	:= -pipe -mno-fp-regs -ffixed-8
 cflags-y	+= $(call cc-option, -fno-jump-tables)
 
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index 9b68790013e2..0580cb8c84b2 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 
+generic-y += compat.h
 generic-y += exec.h
 generic-y += export.h
 generic-y += fb.h
diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h
index b78f61f20796..8beeafd4f68e 100644
--- a/arch/alpha/include/asm/dma-mapping.h
+++ b/arch/alpha/include/asm/dma-mapping.h
@@ -2,11 +2,15 @@
 #ifndef _ALPHA_DMA_MAPPING_H
 #define _ALPHA_DMA_MAPPING_H
 
-extern const struct dma_map_ops *dma_ops;
+extern const struct dma_map_ops alpha_pci_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return dma_ops;
+#ifdef CONFIG_ALPHA_JENSEN
+	return &dma_direct_ops;
+#else
+	return &alpha_pci_ops;
+#endif
 }
 
 #endif	/* _ALPHA_DMA_MAPPING_H */
diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index b9ec55351924..cf6bc1e64d66 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -56,11 +56,6 @@ struct pci_controller {
 
 /* IOMMU controls.  */
 
-/* The PCI address space does not equal the physical memory address space.
-   The networking and block device layers use this boolean for bounce buffer
-   decisions.  */
-#define PCI_DMA_BUS_IS_PHYS  0
-
 /* TODO: integrate with include/asm-generic/pci.h ? */
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
diff --git a/arch/alpha/include/uapi/asm/Kbuild b/arch/alpha/include/uapi/asm/Kbuild
index 9afaba5e5503..1a5b75310cf4 100644
--- a/arch/alpha/include/uapi/asm/Kbuild
+++ b/arch/alpha/include/uapi/asm/Kbuild
@@ -2,4 +2,8 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += bpf_perf_event.h
+generic-y += ipcbuf.h
+generic-y += msgbuf.h
 generic-y += poll.h
+generic-y += sembuf.h
+generic-y += shmbuf.h
diff --git a/arch/alpha/include/uapi/asm/ipcbuf.h b/arch/alpha/include/uapi/asm/ipcbuf.h
deleted file mode 100644
index 90d6445a14df..000000000000
--- a/arch/alpha/include/uapi/asm/ipcbuf.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/ipcbuf.h>
diff --git a/arch/alpha/include/uapi/asm/msgbuf.h b/arch/alpha/include/uapi/asm/msgbuf.h
deleted file mode 100644
index 8c5d4d8c1b16..000000000000
--- a/arch/alpha/include/uapi/asm/msgbuf.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ALPHA_MSGBUF_H
-#define _ALPHA_MSGBUF_H
-
-/* 
- * The msqid64_ds structure for alpha architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct msqid64_ds {
-	struct ipc64_perm msg_perm;
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-	__kernel_time_t msg_ctime;	/* last change time */
-	unsigned long  msg_cbytes;	/* current number of bytes on queue */
-	unsigned long  msg_qnum;	/* number of messages in queue */
-	unsigned long  msg_qbytes;	/* max number of bytes on queue */
-	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
-	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	unsigned long  __unused1;
-	unsigned long  __unused2;
-};
-
-#endif /* _ALPHA_MSGBUF_H */
diff --git a/arch/alpha/include/uapi/asm/sembuf.h b/arch/alpha/include/uapi/asm/sembuf.h
deleted file mode 100644
index f28ffa668b2f..000000000000
--- a/arch/alpha/include/uapi/asm/sembuf.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ALPHA_SEMBUF_H
-#define _ALPHA_SEMBUF_H
-
-/* 
- * The semid64_ds structure for alpha architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct semid64_ds {
-	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
-	__kernel_time_t	sem_otime;		/* last semop time */
-	__kernel_time_t	sem_ctime;		/* last change time */
-	unsigned long	sem_nsems;		/* no. of semaphores in array */
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-};
-
-#endif /* _ALPHA_SEMBUF_H */
diff --git a/arch/alpha/include/uapi/asm/shmbuf.h b/arch/alpha/include/uapi/asm/shmbuf.h
deleted file mode 100644
index 7e041ca2eb40..000000000000
--- a/arch/alpha/include/uapi/asm/shmbuf.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ALPHA_SHMBUF_H
-#define _ALPHA_SHMBUF_H
-
-/* 
- * The shmid64_ds structure for alpha architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct shmid64_ds {
-	struct ipc64_perm	shm_perm;	/* operation perms */
-	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_time_t		shm_atime;	/* last attach time */
-	__kernel_time_t		shm_dtime;	/* last detach time */
-	__kernel_time_t		shm_ctime;	/* last change time */
-	__kernel_pid_t		shm_cpid;	/* pid of creator */
-	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	unsigned long		shm_nattch;	/* no. of current attaches */
-	unsigned long		__unused1;
-	unsigned long		__unused2;
-};
-
-struct shminfo64 {
-	unsigned long	shmmax;
-	unsigned long	shmmin;
-	unsigned long	shmmni;
-	unsigned long	shmseg;
-	unsigned long	shmall;
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* _ALPHA_SHMBUF_H */
diff --git a/arch/alpha/include/uapi/asm/siginfo.h b/arch/alpha/include/uapi/asm/siginfo.h
index 0cf3b527b274..db3f0138536f 100644
--- a/arch/alpha/include/uapi/asm/siginfo.h
+++ b/arch/alpha/include/uapi/asm/siginfo.h
@@ -7,18 +7,4 @@
 
 #include <asm-generic/siginfo.h>
 
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME	0	/* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-/*
- * SIGTRAP si_codes
- */
-#ifdef __KERNEL__
-#define TRAP_FIXME	0	/* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
 #endif
diff --git a/arch/alpha/kernel/io.c b/arch/alpha/kernel/io.c
index 3e3d49c254c5..c025a3e5e357 100644
--- a/arch/alpha/kernel/io.c
+++ b/arch/alpha/kernel/io.c
@@ -37,20 +37,20 @@ unsigned int ioread32(void __iomem *addr)
 
 void iowrite8(u8 b, void __iomem *addr)
 {
-	IO_CONCAT(__IO_PREFIX,iowrite8)(b, addr);
 	mb();
+	IO_CONCAT(__IO_PREFIX,iowrite8)(b, addr);
 }
 
 void iowrite16(u16 b, void __iomem *addr)
 {
-	IO_CONCAT(__IO_PREFIX,iowrite16)(b, addr);
 	mb();
+	IO_CONCAT(__IO_PREFIX,iowrite16)(b, addr);
 }
 
 void iowrite32(u32 b, void __iomem *addr)
 {
-	IO_CONCAT(__IO_PREFIX,iowrite32)(b, addr);
 	mb();
+	IO_CONCAT(__IO_PREFIX,iowrite32)(b, addr);
 }
 
 EXPORT_SYMBOL(ioread8);
@@ -176,26 +176,26 @@ u64 readq(const volatile void __iomem *addr)
 
 void writeb(u8 b, volatile void __iomem *addr)
 {
-	__raw_writeb(b, addr);
 	mb();
+	__raw_writeb(b, addr);
 }
 
 void writew(u16 b, volatile void __iomem *addr)
 {
-	__raw_writew(b, addr);
 	mb();
+	__raw_writew(b, addr);
 }
 
 void writel(u32 b, volatile void __iomem *addr)
 {
-	__raw_writel(b, addr);
 	mb();
+	__raw_writel(b, addr);
 }
 
 void writeq(u64 b, volatile void __iomem *addr)
 {
-	__raw_writeq(b, addr);
 	mb();
+	__raw_writeq(b, addr);
 }
 
 EXPORT_SYMBOL(readb);
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 89faa6f4de47..6e921754c8fc 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -871,8 +871,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer,
 		   send a signal.  Old exceptions are not signaled.  */
 		fex = (exc >> IEEE_STATUS_TO_EXCSUM_SHIFT) & swcr;
  		if (fex) {
-			siginfo_t info;
-			int si_code = 0;
+			int si_code = FPE_FLTUNK;
 
 			if (fex & IEEE_TRAP_ENABLE_DNO) si_code = FPE_FLTUND;
 			if (fex & IEEE_TRAP_ENABLE_INE) si_code = FPE_FLTRES;
@@ -881,11 +880,9 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer,
 			if (fex & IEEE_TRAP_ENABLE_DZE) si_code = FPE_FLTDIV;
 			if (fex & IEEE_TRAP_ENABLE_INV) si_code = FPE_FLTINV;
 
-			info.si_signo = SIGFPE;
-			info.si_errno = 0;
-			info.si_code = si_code;
-			info.si_addr = NULL;  /* FIXME */
- 			send_sig_info(SIGFPE, &info, current);
+			send_sig_fault(SIGFPE, si_code,
+				       (void __user *)NULL,  /* FIXME */
+				       0, current);
  		}
 		return 0;
 	}
diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c
index b6ebb65127a8..c7c5879869d3 100644
--- a/arch/alpha/kernel/pci-noop.c
+++ b/arch/alpha/kernel/pci-noop.c
@@ -102,36 +102,3 @@ SYSCALL_DEFINE5(pciconfig_write, unsigned long, bus, unsigned long, dfn,
 	else
 		return -ENODEV;
 }
-
-static void *alpha_noop_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t gfp,
-				       unsigned long attrs)
-{
-	void *ret;
-
-	if (!dev || *dev->dma_mask >= 0xffffffffUL)
-		gfp &= ~GFP_DMA;
-	ret = (void *)__get_free_pages(gfp, get_order(size));
-	if (ret) {
-		memset(ret, 0, size);
-		*dma_handle = virt_to_phys(ret);
-	}
-	return ret;
-}
-
-static int alpha_noop_supported(struct device *dev, u64 mask)
-{
-	return mask < 0x00ffffffUL ? 0 : 1;
-}
-
-const struct dma_map_ops alpha_noop_ops = {
-	.alloc			= alpha_noop_alloc_coherent,
-	.free			= dma_noop_free_coherent,
-	.map_page		= dma_noop_map_page,
-	.map_sg			= dma_noop_map_sg,
-	.mapping_error		= dma_noop_mapping_error,
-	.dma_supported		= alpha_noop_supported,
-};
-
-const struct dma_map_ops *dma_ops = &alpha_noop_ops;
-EXPORT_SYMBOL(dma_ops);
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 83b34b9188ea..6923b0d9c1e1 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -950,6 +950,4 @@ const struct dma_map_ops alpha_pci_ops = {
 	.mapping_error		= alpha_pci_mapping_error,
 	.dma_supported		= alpha_pci_supported,
 };
-
-const struct dma_map_ops *dma_ops = &alpha_pci_ops;
-EXPORT_SYMBOL(dma_ops);
+EXPORT_SYMBOL(alpha_pci_ops);
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 9ebb3bcbc626..8c0c4ee0be6e 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -219,14 +219,8 @@ do_sigreturn(struct sigcontext __user *sc)
 
 	/* Send SIGTRAP if we're single-stepping: */
 	if (ptrace_cancel_bpt (current)) {
-		siginfo_t info;
-
-		info.si_signo = SIGTRAP;
-		info.si_errno = 0;
-		info.si_code = TRAP_BRKPT;
-		info.si_addr = (void __user *) regs->pc;
-		info.si_trapno = 0;
-		send_sig_info(SIGTRAP, &info, current);
+		send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *) regs->pc, 0,
+			       current);
 	}
 	return;
 
@@ -253,14 +247,8 @@ do_rt_sigreturn(struct rt_sigframe __user *frame)
 
 	/* Send SIGTRAP if we're single-stepping: */
 	if (ptrace_cancel_bpt (current)) {
-		siginfo_t info;
-
-		info.si_signo = SIGTRAP;
-		info.si_errno = 0;
-		info.si_code = TRAP_BRKPT;
-		info.si_addr = (void __user *) regs->pc;
-		info.si_trapno = 0;
-		send_sig_info(SIGTRAP, &info, current);
+		send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *) regs->pc, 0,
+			       current);
 	}
 	return;
 
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index f43bd05dede2..bc9627698796 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -213,7 +213,6 @@ do_entArith(unsigned long summary, unsigned long write_mask,
 	    struct pt_regs *regs)
 {
 	long si_code = FPE_FLTINV;
-	siginfo_t info;
 
 	if (summary & 1) {
 		/* Software-completion summary bit is set, so try to
@@ -228,17 +227,12 @@ do_entArith(unsigned long summary, unsigned long write_mask,
 	}
 	die_if_kernel("Arithmetic fault", regs, 0, NULL);
 
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_code = si_code;
-	info.si_addr = (void __user *) regs->pc;
-	send_sig_info(SIGFPE, &info, current);
+	send_sig_fault(SIGFPE, si_code, (void __user *) regs->pc, 0, current);
 }
 
 asmlinkage void
 do_entIF(unsigned long type, struct pt_regs *regs)
 {
-	siginfo_t info;
 	int signo, code;
 
 	if ((regs->ps & ~IPL_MAX) == 0) {
@@ -270,31 +264,20 @@ do_entIF(unsigned long type, struct pt_regs *regs)
 
 	switch (type) {
 	      case 0: /* breakpoint */
-		info.si_signo = SIGTRAP;
-		info.si_errno = 0;
-		info.si_code = TRAP_BRKPT;
-		info.si_trapno = 0;
-		info.si_addr = (void __user *) regs->pc;
-
 		if (ptrace_cancel_bpt(current)) {
 			regs->pc -= 4;	/* make pc point to former bpt */
 		}
 
-		send_sig_info(SIGTRAP, &info, current);
+		send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc, 0,
+			       current);
 		return;
 
 	      case 1: /* bugcheck */
-		info.si_signo = SIGTRAP;
-		info.si_errno = 0;
-		info.si_code = TRAP_FIXME;
-		info.si_addr = (void __user *) regs->pc;
-		info.si_trapno = 0;
-		send_sig_info(SIGTRAP, &info, current);
+		send_sig_fault(SIGTRAP, TRAP_UNK, (void __user *) regs->pc, 0,
+			       current);
 		return;
 		
 	      case 2: /* gentrap */
-		info.si_addr = (void __user *) regs->pc;
-		info.si_trapno = regs->r16;
 		switch ((long) regs->r16) {
 		case GEN_INTOVF:
 			signo = SIGFPE;
@@ -326,7 +309,7 @@ do_entIF(unsigned long type, struct pt_regs *regs)
 			break;
 		case GEN_ROPRAND:
 			signo = SIGFPE;
-			code = FPE_FIXME;
+			code = FPE_FLTUNK;
 			break;
 
 		case GEN_DECOVF:
@@ -348,15 +331,12 @@ do_entIF(unsigned long type, struct pt_regs *regs)
 		case GEN_SUBRNG7:
 		default:
 			signo = SIGTRAP;
-			code = TRAP_FIXME;
+			code = TRAP_UNK;
 			break;
 		}
 
-		info.si_signo = signo;
-		info.si_errno = 0;
-		info.si_code = code;
-		info.si_addr = (void __user *) regs->pc;
-		send_sig_info(signo, &info, current);
+		send_sig_fault(signo, code, (void __user *) regs->pc, regs->r16,
+			       current);
 		return;
 
 	      case 4: /* opDEC */
@@ -380,11 +360,9 @@ do_entIF(unsigned long type, struct pt_regs *regs)
 			if (si_code == 0)
 				return;
 			if (si_code > 0) {
-				info.si_signo = SIGFPE;
-				info.si_errno = 0;
-				info.si_code = si_code;
-				info.si_addr = (void __user *) regs->pc;
-				send_sig_info(SIGFPE, &info, current);
+				send_sig_fault(SIGFPE, si_code,
+					       (void __user *) regs->pc, 0,
+					       current);
 				return;
 			}
 		}
@@ -409,11 +387,7 @@ do_entIF(unsigned long type, struct pt_regs *regs)
 		      ;
 	}
 
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_ILLOPC;
-	info.si_addr = (void __user *) regs->pc;
-	send_sig_info(SIGILL, &info, current);
+	send_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)regs->pc, 0, current);
 }
 
 /* There is an ifdef in the PALcode in MILO that enables a 
@@ -426,15 +400,9 @@ do_entIF(unsigned long type, struct pt_regs *regs)
 asmlinkage void
 do_entDbg(struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	die_if_kernel("Instruction fault", regs, 0, NULL);
 
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_ILLOPC;
-	info.si_addr = (void __user *) regs->pc;
-	force_sig_info(SIGILL, &info, current);
+	force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)regs->pc, 0, current);
 }
 
 
@@ -758,7 +726,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 
 	unsigned long tmp1, tmp2, tmp3, tmp4;
 	unsigned long fake_reg, *reg_addr = &fake_reg;
-	siginfo_t info;
+	int si_code;
 	long error;
 
 	/* Check the UAC bits to decide what the user wants us to do
@@ -981,34 +949,27 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 
 give_sigsegv:
 	regs->pc -= 4;  /* make pc point to faulting insn */
-	info.si_signo = SIGSEGV;
-	info.si_errno = 0;
 
 	/* We need to replicate some of the logic in mm/fault.c,
 	   since we don't have access to the fault code in the
 	   exception handling return path.  */
 	if ((unsigned long)va >= TASK_SIZE)
-		info.si_code = SEGV_ACCERR;
+		si_code = SEGV_ACCERR;
 	else {
 		struct mm_struct *mm = current->mm;
 		down_read(&mm->mmap_sem);
 		if (find_vma(mm, (unsigned long)va))
-			info.si_code = SEGV_ACCERR;
+			si_code = SEGV_ACCERR;
 		else
-			info.si_code = SEGV_MAPERR;
+			si_code = SEGV_MAPERR;
 		up_read(&mm->mmap_sem);
 	}
-	info.si_addr = va;
-	send_sig_info(SIGSEGV, &info, current);
+	send_sig_fault(SIGSEGV, si_code, va, 0, current);
 	return;
 
 give_sigbus:
 	regs->pc -= 4;
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRALN;
-	info.si_addr = va;
-	send_sig_info(SIGBUS, &info, current);
+	send_sig_fault(SIGBUS, BUS_ADRALN, va, 0, current);
 	return;
 }
 
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index cd3c572ee912..de2bd217adad 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -88,7 +88,6 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	struct mm_struct *mm = current->mm;
 	const struct exception_table_entry *fixup;
 	int fault, si_code = SEGV_MAPERR;
-	siginfo_t info;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
@@ -221,21 +220,13 @@ retry:
 	up_read(&mm->mmap_sem);
 	/* Send a sigbus, regardless of whether we were in kernel
 	   or user mode.  */
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRERR;
-	info.si_addr = (void __user *) address;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *) address, 0, current);
 	if (!user_mode(regs))
 		goto no_context;
 	return;
 
  do_sigsegv:
-	info.si_signo = SIGSEGV;
-	info.si_errno = 0;
-	info.si_code = si_code;
-	info.si_addr = (void __user *) address;
-	force_sig_info(SIGSEGV, &info, current);
+	force_sig_fault(SIGSEGV, si_code, (void __user *) address, 0, current);
 	return;
 
 #ifdef CONFIG_ALPHA_LARGE_VMALLOC
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index d76bf4a83740..89d47eac18b2 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -9,11 +9,15 @@
 config ARC
 	def_bool y
 	select ARC_TIMERS
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
+	select DMA_NONCOHERENT_OPS
+	select DMA_NONCOHERENT_MMAP
 	select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC)
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_FIND_FIRST_BIT
@@ -453,16 +457,11 @@ config ARC_HAS_PAE40
 	default n
 	depends on ISA_ARCV2
 	select HIGHMEM
+	select PHYS_ADDR_T_64BIT
 	help
 	  Enable access to physical memory beyond 4G, only supported on
 	  ARC cores with 40 bit Physical Addressing support
 
-config ARCH_PHYS_ADDR_T_64BIT
-	def_bool ARC_HAS_PAE40
-
-config ARCH_DMA_ADDR_T_64BIT
-	bool
-
 config ARC_KVADDR_SIZE
 	int "Kernel Virtual Address Space size (MB)"
 	range 0 512
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 4bd5d4369e05..feed50ce89fa 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,7 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 generic-y += bugs.h
+generic-y += compat.h
 generic-y += device.h
 generic-y += div64.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += extable.h
 generic-y += fb.h
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
deleted file mode 100644
index 7a16824bfe98..000000000000
--- a/arch/arc/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * DMA Mapping glue for ARC
- *
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef ASM_ARC_DMA_MAPPING_H
-#define ASM_ARC_DMA_MAPPING_H
-
-extern const struct dma_map_ops arc_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &arc_dma_ops;
-}
-
-#endif
diff --git a/arch/arc/include/asm/pci.h b/arch/arc/include/asm/pci.h
index ba56c23c1b20..4ff53c041c64 100644
--- a/arch/arc/include/asm/pci.h
+++ b/arch/arc/include/asm/pci.h
@@ -16,12 +16,6 @@
 #define PCIBIOS_MIN_MEM 0x100000
 
 #define pcibios_assign_all_busses()	1
-/*
- * The PCI address space does equal the physical memory address space.
- * The networking and block device layers use this boolean for bounce
- * buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS	1
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 1dcc404b5aec..8c1071840979 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -16,13 +16,12 @@
  * The default DMA address == Phy address which is 0x8000_0000 based.
  */
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 
-
-static void *arc_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	unsigned long order = get_order(size);
 	struct page *page;
@@ -89,7 +88,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 	return kvaddr;
 }
 
-static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	phys_addr_t paddr = dma_handle;
@@ -105,9 +104,9 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
 	__free_pages(page, get_order(size));
 }
 
-static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-			void *cpu_addr, dma_addr_t dma_addr, size_t size,
-			unsigned long attrs)
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
 {
 	unsigned long user_count = vma_pages(vma);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
@@ -130,149 +129,14 @@ static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
-/*
- * streaming DMA Mapping API...
- * CPU accesses page via normal paddr, thus needs to explicitly made
- * consistent before each use
- */
-static void _dma_cache_sync(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	switch (dir) {
-	case DMA_FROM_DEVICE:
-		dma_cache_inv(paddr, size);
-		break;
-	case DMA_TO_DEVICE:
-		dma_cache_wback(paddr, size);
-		break;
-	case DMA_BIDIRECTIONAL:
-		dma_cache_wback_inv(paddr, size);
-		break;
-	default:
-		pr_err("Invalid DMA dir [%d] for OP @ %pa[p]\n", dir, &paddr);
-	}
+	dma_cache_wback(paddr, size);
 }
 
-/*
- * arc_dma_map_page - map a portion of a page for streaming DMA
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_page().
- *
- * Note: while it takes struct page as arg, caller can "abuse" it to pass
- * a region larger than PAGE_SIZE, provided it is physically contiguous
- * and this still works correctly
- */
-static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	phys_addr_t paddr = page_to_phys(page) + offset;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		_dma_cache_sync(paddr, size, dir);
-
-	return paddr;
-}
-
-/*
- * arc_dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
- *
- * After this call, reads by the CPU to the buffer are guaranteed to see
- * whatever the device wrote there.
- *
- * Note: historically this routine was not implemented for ARC
- */
-static void arc_dma_unmap_page(struct device *dev, dma_addr_t handle,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-	phys_addr_t paddr = handle;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		_dma_cache_sync(paddr, size, dir);
+	dma_cache_inv(paddr, size);
 }
-
-static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg,
-	   int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
-					       s->length, dir);
-
-	return nents;
-}
-
-static void arc_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, enum dma_data_direction dir,
-			     unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		arc_dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir,
-				   attrs);
-}
-
-static void arc_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
-{
-	_dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE);
-}
-
-static void arc_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
-{
-	_dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
-}
-
-static void arc_dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sglist, int nelems,
-		enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		_dma_cache_sync(sg_phys(sg), sg->length, dir);
-}
-
-static void arc_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sglist, int nelems,
-		enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		_dma_cache_sync(sg_phys(sg), sg->length, dir);
-}
-
-static int arc_dma_supported(struct device *dev, u64 dma_mask)
-{
-	/* Support 32 bit DMA mask exclusively */
-	return dma_mask == DMA_BIT_MASK(32);
-}
-
-const struct dma_map_ops arc_dma_ops = {
-	.alloc			= arc_dma_alloc,
-	.free			= arc_dma_free,
-	.mmap			= arc_dma_mmap,
-	.map_page		= arc_dma_map_page,
-	.unmap_page		= arc_dma_unmap_page,
-	.map_sg			= arc_dma_map_sg,
-	.unmap_sg		= arc_dma_unmap_sg,
-	.sync_single_for_device	= arc_dma_sync_single_for_device,
-	.sync_single_for_cpu	= arc_dma_sync_single_for_cpu,
-	.sync_sg_for_cpu	= arc_dma_sync_sg_for_cpu,
-	.sync_sg_for_device	= arc_dma_sync_sg_for_device,
-	.dma_supported		= arc_dma_supported,
-};
-EXPORT_SYMBOL(arc_dma_ops);
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index a0b7bd6d030d..b884bbd6f354 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -70,6 +70,8 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	int write = regs->ecr_cause & ECR_C_PROTV_STORE;  /* ST/EX */
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
+	clear_siginfo(&info);
+
 	/*
 	 * We fault-in kernel-space virtual memory on-demand. The
 	 * 'reference' page table is init_mm.pgd.
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a7f8e7f4b88f..8f460bdd4be1 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -60,7 +60,6 @@ config ARM
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
@@ -96,6 +95,7 @@ config ARM
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN
 	select IRQ_FORCED_THREADING
 	select MODULES_USE_ELF_REL
+	select NEED_DMA_MAP_STATE
 	select NO_BOOTMEM
 	select OF_EARLY_FLATTREE if OF
 	select OF_RESERVED_MEM if OF
@@ -119,9 +119,6 @@ config ARM_HAS_SG_CHAIN
 	select ARCH_HAS_SG_CHAIN
 	bool
 
-config NEED_SG_DMA_LENGTH
-	bool
-
 config ARM_DMA_USE_IOMMU
 	bool
 	select ARM_HAS_SG_CHAIN
@@ -224,9 +221,6 @@ config ARCH_MAY_HAVE_PC_FDC
 config ZONE_DMA
 	bool
 
-config NEED_DMA_MAP_STATE
-       def_bool y
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
@@ -1704,6 +1698,7 @@ config ARCH_WANT_GENERAL_HUGETLB
 config ARM_MODULE_PLTS
 	bool "Use PLTs to allow module memory to spill over into vmalloc area"
 	depends on MODULES
+	default y
 	help
 	  Allocate PLTs when loading modules so that jumps and calls whose
 	  targets are too far away for their relative offsets to be encoded
@@ -1714,7 +1709,8 @@ config ARM_MODULE_PLTS
 	  rounding up to page size, the actual memory footprint is usually
 	  the same.
 
-	  Say y if you are getting out of memory errors while loading modules
+	  Disabling this is usually safe for small single-platform
+	  configurations. If unsure, say y.
 
 source "mm/Kconfig"
 
@@ -1778,12 +1774,6 @@ config SECCOMP
 	  and the task is only allowed to execute a few safe syscalls
 	  defined by each seccomp mode.
 
-config SWIOTLB
-	def_bool y
-
-config IOMMU_HELPER
-	def_bool SWIOTLB
-
 config PARAVIRT
 	bool "Enable paravirtualization code"
 	help
@@ -1815,6 +1805,7 @@ config XEN
 	depends on MMU
 	select ARCH_DMA_ADDR_T_64BIT
 	select ARM_PSCI
+	select SWIOTLB
 	select SWIOTLB_XEN
 	select PARAVIRT
 	help
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index e4e537f27339..1dc4045e1af6 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -106,7 +106,7 @@ tune-$(CONFIG_CPU_V6K)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
 tune-y := $(tune-y)
 
 ifeq ($(CONFIG_AEABI),y)
-CFLAGS_ABI	:=-mabi=aapcs-linux -mno-thumb-interwork -mfpu=vfp
+CFLAGS_ABI	:=-mabi=aapcs-linux -mfpu=vfp
 else
 CFLAGS_ABI	:=$(call cc-option,-mapcs-32,-mabi=apcs-gnu) $(call cc-option,-mno-thumb-interwork,)
 endif
@@ -135,7 +135,7 @@ endif
 KBUILD_CFLAGS	+=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm
 KBUILD_AFLAGS	+=$(CFLAGS_ABI) $(AFLAGS_ISA) $(arch-y) $(tune-y) -include asm/unified.h -msoft-float
 
-CHECKFLAGS	+= -D__arm__ -m32
+CHECKFLAGS	+= -D__arm__
 
 #Default value
 head-y		:= arch/arm/kernel/head$(MMUEXT).o
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 45a6b9b7af2a..a3c5fbcad4ab 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -113,15 +113,13 @@ CFLAGS_fdt_ro.o := $(nossp_flags)
 CFLAGS_fdt_rw.o := $(nossp_flags)
 CFLAGS_fdt_wip.o := $(nossp_flags)
 
-ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj)
+ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj)
 asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
-KBSS_SZ = $(shell $(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \
-		perl -e 'while (<>) { \
-			$$bss_start=hex($$1) if /^([[:xdigit:]]+) B __bss_start$$/; \
-			$$bss_end=hex($$1) if /^([[:xdigit:]]+) B __bss_stop$$/; \
-		}; printf "%d\n", $$bss_end - $$bss_start;')
+KBSS_SZ = $(shell echo $$(($$($(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \
+		sed -n -e 's/^\([^ ]*\) [AB] __bss_start$$/-0x\1/p' \
+		       -e 's/^\([^ ]*\) [AB] __bss_stop$$/+0x\1/p') )) )
 LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
 # Supply ZRELADDR to the decompressor via a linker symbol.
 ifneq ($(CONFIG_AUTO_ZRELADDR),y)
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 45c8823c3750..517e0e18f0b8 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -29,19 +29,19 @@
 #if defined(CONFIG_DEBUG_ICEDCC)
 
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7)
-		.macro	loadsp, rb, tmp
+		.macro	loadsp, rb, tmp1, tmp2
 		.endm
 		.macro	writeb, ch, rb
 		mcr	p14, 0, \ch, c0, c5, 0
 		.endm
 #elif defined(CONFIG_CPU_XSCALE)
-		.macro	loadsp, rb, tmp
+		.macro	loadsp, rb, tmp1, tmp2
 		.endm
 		.macro	writeb, ch, rb
 		mcr	p14, 0, \ch, c8, c0, 0
 		.endm
 #else
-		.macro	loadsp, rb, tmp
+		.macro	loadsp, rb, tmp1, tmp2
 		.endm
 		.macro	writeb, ch, rb
 		mcr	p14, 0, \ch, c1, c0, 0
@@ -57,7 +57,7 @@
 		.endm
 
 #if defined(CONFIG_ARCH_SA1100)
-		.macro	loadsp, rb, tmp
+		.macro	loadsp, rb, tmp1, tmp2
 		mov	\rb, #0x80000000	@ physical base address
 #ifdef CONFIG_DEBUG_LL_SER3
 		add	\rb, \rb, #0x00050000	@ Ser3
@@ -66,8 +66,8 @@
 #endif
 		.endm
 #else
-		.macro	loadsp,	rb, tmp
-		addruart \rb, \tmp
+		.macro	loadsp,	rb, tmp1, tmp2
+		addruart \rb, \tmp1, \tmp2
 		.endm
 #endif
 #endif
@@ -561,8 +561,6 @@ not_relocated:	mov	r0, #0
 		bl	decompress_kernel
 		bl	cache_clean_flush
 		bl	cache_off
-		mov	r1, r7			@ restore architecture number
-		mov	r2, r8			@ restore atags pointer
 
 #ifdef CONFIG_ARM_VIRT_EXT
 		mrs	r0, spsr		@ Get saved CPU boot mode
@@ -1297,7 +1295,7 @@ phex:		adr	r3, phexbuf
 		b	1b
 
 @ puts corrupts {r0, r1, r2, r3}
-puts:		loadsp	r3, r1
+puts:		loadsp	r3, r2, r1
 1:		ldrb	r2, [r0], #1
 		teq	r2, #0
 		moveq	pc, lr
@@ -1314,8 +1312,8 @@ puts:		loadsp	r3, r1
 @ putc corrupts {r0, r1, r2, r3}
 putc:
 		mov	r2, r0
+		loadsp	r3, r1, r0
 		mov	r0, #0
-		loadsp	r3, r1
 		b	2b
 
 @ memdump corrupts {r0, r1, r2, r3, r10, r11, r12, lr}
@@ -1365,6 +1363,8 @@ __hyp_reentry_vectors:
 
 __enter_kernel:
 		mov	r0, #0			@ must be 0
+		mov	r1, r7			@ restore architecture number
+		mov	r2, r8			@ restore atags pointer
  ARM(		mov	pc, r4		)	@ call kernel
  M_CLASS(	add	r4, r4, #1	)	@ enter in Thumb mode for M class
  THUMB(		bx	r4		)	@ entry point is always ARM for A/R classes
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 4cc09e43eea2..6916d7532ad2 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -163,7 +163,7 @@
 			};
 
 			uart0: serial@12000 {
-				compatible = "snps,dw-apb-uart";
+				compatible = "marvell,armada-38x-uart";
 				reg = <0x12000 0x100>;
 				reg-shift = <2>;
 				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
@@ -173,7 +173,7 @@
 			};
 
 			uart1: serial@12100 {
-				compatible = "snps,dw-apb-uart";
+				compatible = "marvell,armada-38x-uart";
 				reg = <0x12100 0x100>;
 				reg-shift = <2>;
 				interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/bcm-cygnus.dtsi b/arch/arm/boot/dts/bcm-cygnus.dtsi
index 699fdf94d139..9fe4f5a6379e 100644
--- a/arch/arm/boot/dts/bcm-cygnus.dtsi
+++ b/arch/arm/boot/dts/bcm-cygnus.dtsi
@@ -69,7 +69,7 @@
 		timer@20200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x20200 0x100>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&periph_clk>;
 		};
 
diff --git a/arch/arm/boot/dts/da850-lcdk.dts b/arch/arm/boot/dts/da850-lcdk.dts
index a1f4d6d5a569..0edf769ea95c 100644
--- a/arch/arm/boot/dts/da850-lcdk.dts
+++ b/arch/arm/boot/dts/da850-lcdk.dts
@@ -21,8 +21,8 @@
 		stdout-path = "serial2:115200n8";
 	};
 
-	memory {
-		device_type = "memory";
+	memory@c0000000 {
+		/* 128 MB DDR2 SDRAM @ 0xc0000000 */
 		reg = <0xc0000000 0x08000000>;
 	};
 
diff --git a/arch/arm/boot/dts/da850.dtsi b/arch/arm/boot/dts/da850.dtsi
index c66cf7895363..12010002dbdb 100644
--- a/arch/arm/boot/dts/da850.dtsi
+++ b/arch/arm/boot/dts/da850.dtsi
@@ -7,10 +7,19 @@
  * Free Software Foundation;  either version 2 of the  License, or (at your
  * option) any later version.
  */
-#include "skeleton.dtsi"
 #include <dt-bindings/interrupt-controller/irq.h>
 
 / {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	chosen { };
+	aliases { };
+
+	memory@c0000000 {
+		device_type = "memory";
+		reg = <0xc0000000 0x0>;
+	};
+
 	arm {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -46,8 +55,6 @@
 		pmx_core: pinmux@14120 {
 			compatible = "pinctrl-single";
 			reg = <0x14120 0x50>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			#pinctrl-cells = <2>;
 			pinctrl-single,bit-per-mux;
 			pinctrl-single,register-width = <32>;
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
index d6657b3bae84..85d7b5148b0a 100644
--- a/arch/arm/boot/dts/dm8148-evm.dts
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "DM8148 EVM";
-	compatible = "ti,dm8148-evm", "ti,dm8148";
+	compatible = "ti,dm8148-evm", "ti,dm8148", "ti,dm814";
 
 	memory@80000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
index 63883b3479f9..6418f9cdbe83 100644
--- a/arch/arm/boot/dts/dm8148-t410.dts
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -9,7 +9,7 @@
 
 / {
 	model = "HP t410 Smart Zero Client";
-	compatible = "hp,t410", "ti,dm8148";
+	compatible = "hp,t410", "ti,dm8148", "ti,dm814";
 
 	memory@80000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts
index c72a2132aa82..1d030d567307 100644
--- a/arch/arm/boot/dts/dm8168-evm.dts
+++ b/arch/arm/boot/dts/dm8168-evm.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "DM8168 EVM";
-	compatible = "ti,dm8168-evm", "ti,dm8168";
+	compatible = "ti,dm8168-evm", "ti,dm8168", "ti,dm816";
 
 	memory@80000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/dra62x-j5eco-evm.dts b/arch/arm/boot/dts/dra62x-j5eco-evm.dts
index fee0547f7302..31b824ad5d29 100644
--- a/arch/arm/boot/dts/dra62x-j5eco-evm.dts
+++ b/arch/arm/boot/dts/dra62x-j5eco-evm.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "DRA62x J5 Eco EVM";
-	compatible = "ti,dra62x-j5eco-evm", "ti,dra62x", "ti,dm8148";
+	compatible = "ti,dra62x-j5eco-evm", "ti,dra62x", "ti,dm8148", "ti,dm814";
 
 	memory@80000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/gemini-nas4220b.dts b/arch/arm/boot/dts/gemini-nas4220b.dts
index 8bbb6f85d161..4785fbcc41ed 100644
--- a/arch/arm/boot/dts/gemini-nas4220b.dts
+++ b/arch/arm/boot/dts/gemini-nas4220b.dts
@@ -134,37 +134,37 @@
 						function = "gmii";
 						groups = "gmii_gmac0_grp";
 					};
-					/* Settings come from OpenWRT */
+					/* Settings come from OpenWRT, pins on SL3516 */
 					conf0 {
-						pins = "R8 GMAC0 RXDV", "U11 GMAC1 RXDV";
+						pins = "V8 GMAC0 RXDV", "T10 GMAC1 RXDV";
 						skew-delay = <0>;
 					};
 					conf1 {
-						pins = "T8 GMAC0 RXC", "T11 GMAC1 RXC";
+						pins = "Y7 GMAC0 RXC", "Y11 GMAC1 RXC";
 						skew-delay = <15>;
 					};
 					conf2 {
-						pins = "P8 GMAC0 TXEN", "V11 GMAC1 TXEN";
+						pins = "T8 GMAC0 TXEN", "W11 GMAC1 TXEN";
 						skew-delay = <7>;
 					};
 					conf3 {
-						pins = "V7 GMAC0 TXC";
+						pins = "U8 GMAC0 TXC";
 						skew-delay = <11>;
 					};
 					conf4 {
-						pins = "P10 GMAC1 TXC";
+						pins = "V11 GMAC1 TXC";
 						skew-delay = <10>;
 					};
 					conf5 {
 						/* The data lines all have default skew */
-						pins = "U8 GMAC0 RXD0", "V8 GMAC0 RXD1",
-						       "P9 GMAC0 RXD2", "R9 GMAC0 RXD3",
-						       "U7 GMAC0 TXD0", "T7 GMAC0 TXD1",
-						       "R7 GMAC0 TXD2", "P7 GMAC0 TXD3",
-						       "R11 GMAC1 RXD0", "P11 GMAC1 RXD1",
-						       "V12 GMAC1 RXD2", "U12 GMAC1 RXD3",
-						       "R10 GMAC1 TXD0", "T10 GMAC1 TXD1",
-						       "U10 GMAC1 TXD2", "V10 GMAC1 TXD3";
+						pins = "W8 GMAC0 RXD0", "V9 GMAC0 RXD1",
+						       "Y8 GMAC0 RXD2", "U9 GMAC0 RXD3",
+						       "T7 GMAC0 TXD0", "U6 GMAC0 TXD1",
+						       "V7 GMAC0 TXD2", "U7 GMAC0 TXD3",
+						       "Y12 GMAC1 RXD0", "V12 GMAC1 RXD1",
+						       "T11 GMAC1 RXD2", "W12 GMAC1 RXD3",
+						       "U10 GMAC1 TXD0", "Y10 GMAC1 TXD1",
+						       "W10 GMAC1 TXD2", "T9 GMAC1 TXD3";
 						skew-delay = <7>;
 					};
 					/* Set up drive strength on GMAC0 to 16 mA */
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index bf343195697e..54111ed218b1 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -303,7 +303,7 @@
 			};
 
 			can1: can@53fe4000 {
-				compatible = "fsl,imx35-flexcan";
+				compatible = "fsl,imx35-flexcan", "fsl,imx25-flexcan";
 				reg = <0x53fe4000 0x1000>;
 				clocks = <&clks 33>, <&clks 33>;
 				clock-names = "ipg", "per";
@@ -312,7 +312,7 @@
 			};
 
 			can2: can@53fe8000 {
-				compatible = "fsl,imx35-flexcan";
+				compatible = "fsl,imx35-flexcan", "fsl,imx25-flexcan";
 				reg = <0x53fe8000 0x1000>;
 				clocks = <&clks 34>, <&clks 34>;
 				clock-names = "ipg", "per";
diff --git a/arch/arm/boot/dts/imx51-zii-rdu1.dts b/arch/arm/boot/dts/imx51-zii-rdu1.dts
index 0c99ac04ad08..6464f2560e06 100644
--- a/arch/arm/boot/dts/imx51-zii-rdu1.dts
+++ b/arch/arm/boot/dts/imx51-zii-rdu1.dts
@@ -523,7 +523,7 @@
 	};
 
 	touchscreen@20 {
-		compatible = "syna,rmi4_i2c";
+		compatible = "syna,rmi4-i2c";
 		reg = <0x20>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_ts>;
@@ -541,8 +541,8 @@
 
 		rmi4-f11@11 {
 			reg = <0x11>;
-			touch-inverted-y;
-			touch-swapped-x-y;
+			touchscreen-inverted-y;
+			touchscreen-swapped-x-y;
 			syna,sensor-type = <1>;
 		};
 	};
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 7d647d043f52..3d65c0192f69 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -551,7 +551,7 @@
 			};
 
 			can1: can@53fc8000 {
-				compatible = "fsl,imx53-flexcan";
+				compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
 				reg = <0x53fc8000 0x4000>;
 				interrupts = <82>;
 				clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>,
@@ -561,7 +561,7 @@
 			};
 
 			can2: can@53fcc000 {
-				compatible = "fsl,imx53-flexcan";
+				compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
 				reg = <0x53fcc000 0x4000>;
 				interrupts = <83>;
 				clocks = <&clks IMX5_CLK_CAN2_IPG_GATE>,
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
index 4d42335c0dee..ce85b3ca1a55 100644
--- a/arch/arm/boot/dts/imx7s.dtsi
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -868,6 +868,7 @@
 
 			crypto: caam@30900000 {
 				compatible = "fsl,sec-v4.0";
+				fsl,sec-era = <8>;
 				#address-cells = <1>;
 				#size-cells = <1>;
 				reg = <0x30900000 0x40000>;
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index b47cac23a04b..6fa7bba3e801 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -26,7 +26,7 @@
 		gpio = <&gpio1 3 0>;   /* gpio_3 */
 		startup-delay-us = <70000>;
 		enable-active-high;
-		vin-supply = <&vmmc2>;
+		vin-supply = <&vaux3>;
 	};
 
 	/* HS USB Host PHY on PORT 1 */
@@ -82,6 +82,7 @@
 		twl_audio: audio {
 			compatible = "ti,twl4030-audio";
 			codec {
+				ti,hs_extmute_gpio = <&gpio2 25 GPIO_ACTIVE_HIGH>;
 			};
 		};
 	};
@@ -199,6 +200,7 @@
 		pinctrl-single,pins = <
 			OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0)        /* i2c1_scl.i2c1_scl */
 			OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0)        /* i2c1_sda.i2c1_sda */
+			OMAP3_CORE1_IOPAD(0x20ba, PIN_OUTPUT | MUX_MODE4)        /* gpmc_ncs6.gpio_57 */
 		>;
 	};
 };
@@ -213,7 +215,7 @@
 	};
 	wl127x_gpio: pinmux_wl127x_gpio_pin {
 		pinctrl-single,pins = <
-			OMAP3_WKUP_IOPAD(0x2a0c, PIN_INPUT | MUX_MODE4)		/* sys_boot0.gpio_2 */
+			OMAP3_WKUP_IOPAD(0x2a0a, PIN_INPUT | MUX_MODE4)		/* sys_boot0.gpio_2 */
 			OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4)	/* sys_boot1.gpio_3 */
 		>;
 	};
@@ -260,6 +262,11 @@
 #include "twl4030.dtsi"
 #include "twl4030_omap3.dtsi"
 
+&vaux3 {
+	regulator-min-microvolt = <2800000>;
+	regulator-max-microvolt = <2800000>;
+};
+
 &twl {
 	twl_power: power {
 		compatible = "ti,twl4030-power-idle-osc-off", "ti,twl4030-power-idle";
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 475904894b86..e554b6e039f3 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -163,10 +163,10 @@
 
 			cm2: cm2@8000 {
 				compatible = "ti,omap4-cm2", "simple-bus";
-				reg = <0x8000 0x3000>;
+				reg = <0x8000 0x2000>;
 				#address-cells = <1>;
 				#size-cells = <1>;
-				ranges = <0 0x8000 0x3000>;
+				ranges = <0 0x8000 0x2000>;
 
 				cm2_clocks: clocks {
 					#address-cells = <1>;
@@ -250,11 +250,11 @@
 
 				prm: prm@6000 {
 					compatible = "ti,omap4-prm";
-					reg = <0x6000 0x3000>;
+					reg = <0x6000 0x2000>;
 					interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
 					#address-cells = <1>;
 					#size-cells = <1>;
-					ranges = <0 0x6000 0x3000>;
+					ranges = <0 0x6000 0x2000>;
 
 					prm_clocks: clocks {
 						#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts
index 063fdb65dc60..f07f9018c3e7 100644
--- a/arch/arm/boot/dts/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/r8a7790-lager.dts
@@ -379,7 +379,7 @@
 				port@0 {
 					reg = <0>;
 					adv7511_in: endpoint {
-						remote-endpoint = <&du_out_lvds0>;
+						remote-endpoint = <&lvds0_out>;
 					};
 				};
 
@@ -467,10 +467,8 @@
 	status = "okay";
 
 	clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 722>,
-		 <&cpg CPG_MOD 726>, <&cpg CPG_MOD 725>,
 		 <&x13_clk>, <&x2_clk>;
-	clock-names = "du.0", "du.1", "du.2", "lvds.0", "lvds.1",
-		      "dclkin.0", "dclkin.1";
+	clock-names = "du.0", "du.1", "du.2", "dclkin.0", "dclkin.1";
 
 	ports {
 		port@0 {
@@ -478,12 +476,26 @@
 				remote-endpoint = <&adv7123_in>;
 			};
 		};
+	};
+};
+
+&lvds0 {
+	status = "okay";
+
+	ports {
 		port@1 {
 			endpoint {
 				remote-endpoint = <&adv7511_in>;
 			};
 		};
-		port@2 {
+	};
+};
+
+&lvds1 {
+	status = "okay";
+
+	ports {
+		port@1 {
 			lvds_connector: endpoint {
 			};
 		};
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index e4367cecad18..05a0fc23ac88 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -1627,18 +1627,13 @@
 
 		du: display@feb00000 {
 			compatible = "renesas,du-r8a7790";
-			reg = <0 0xfeb00000 0 0x70000>,
-			      <0 0xfeb90000 0 0x1c>,
-			      <0 0xfeb94000 0 0x1c>;
-			reg-names = "du", "lvds.0", "lvds.1";
+			reg = <0 0xfeb00000 0 0x70000>;
 			interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 269 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
-				 <&cpg CPG_MOD 722>, <&cpg CPG_MOD 726>,
-				 <&cpg CPG_MOD 725>;
-			clock-names = "du.0", "du.1", "du.2", "lvds.0",
-				      "lvds.1";
+				 <&cpg CPG_MOD 722>;
+			clock-names = "du.0", "du.1", "du.2";
 			status = "disabled";
 
 			ports {
@@ -1653,11 +1648,65 @@
 				port@1 {
 					reg = <1>;
 					du_out_lvds0: endpoint {
+						remote-endpoint = <&lvds0_in>;
 					};
 				};
 				port@2 {
 					reg = <2>;
 					du_out_lvds1: endpoint {
+						remote-endpoint = <&lvds1_in>;
+					};
+				};
+			};
+		};
+
+		lvds0: lvds@feb90000 {
+			compatible = "renesas,r8a7790-lvds";
+			reg = <0 0xfeb90000 0 0x1c>;
+			clocks = <&cpg CPG_MOD 726>;
+			power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
+			resets = <&cpg 726>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					lvds0_in: endpoint {
+						remote-endpoint = <&du_out_lvds0>;
+					};
+				};
+				port@1 {
+					reg = <1>;
+					lvds0_out: endpoint {
+					};
+				};
+			};
+		};
+
+		lvds1: lvds@feb94000 {
+			compatible = "renesas,r8a7790-lvds";
+			reg = <0 0xfeb94000 0 0x1c>;
+			clocks = <&cpg CPG_MOD 725>;
+			power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
+			resets = <&cpg 725>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					lvds1_in: endpoint {
+						remote-endpoint = <&du_out_lvds1>;
+					};
+				};
+				port@1 {
+					reg = <1>;
+					lvds1_out: endpoint {
 					};
 				};
 			};
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index f40321a1c917..9d7213a0b8b8 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -468,10 +468,9 @@
 	pinctrl-names = "default";
 	status = "okay";
 
-	clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+	clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
 		 <&x13_clk>, <&x2_clk>;
-	clock-names = "du.0", "du.1", "lvds.0",
-		      "dclkin.0", "dclkin.1";
+	clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
 
 	ports {
 		port@0 {
@@ -479,6 +478,13 @@
 				remote-endpoint = <&adv7511_in>;
 			};
 		};
+	};
+};
+
+&lvds0 {
+	status = "okay";
+
+	ports {
 		port@1 {
 			lvds_connector: endpoint {
 			};
diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts
index c14e6fe9e4f6..ae9ed9ff53ef 100644
--- a/arch/arm/boot/dts/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/r8a7791-porter.dts
@@ -441,10 +441,9 @@
 	pinctrl-names = "default";
 	status = "okay";
 
-	clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+	clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
 		 <&x3_clk>, <&x16_clk>;
-	clock-names = "du.0", "du.1", "lvds.0",
-		      "dclkin.0", "dclkin.1";
+	clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
 
 	ports {
 		port@0 {
@@ -455,6 +454,17 @@
 	};
 };
 
+&lvds0 {
+	status = "okay";
+
+	ports {
+		port@1 {
+			lvds_connector: endpoint {
+			};
+		};
+	};
+};
+
 &rcar_sound {
 	pinctrl-0 = <&ssi_pins &audio_clk_pins>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index f11dab71b03a..506b20885413 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -1633,15 +1633,12 @@
 
 		du: display@feb00000 {
 			compatible = "renesas,du-r8a7791";
-			reg = <0 0xfeb00000 0 0x40000>,
-			      <0 0xfeb90000 0 0x1c>;
-			reg-names = "du", "lvds.0";
+			reg = <0 0xfeb00000 0 0x40000>;
 			interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 724>,
-				 <&cpg CPG_MOD 723>,
-				 <&cpg CPG_MOD 726>;
-			clock-names = "du.0", "du.1", "lvds.0";
+				 <&cpg CPG_MOD 723>;
+			clock-names = "du.0", "du.1";
 			status = "disabled";
 
 			ports {
@@ -1656,6 +1653,33 @@
 				port@1 {
 					reg = <1>;
 					du_out_lvds0: endpoint {
+						remote-endpoint = <&lvds0_in>;
+					};
+				};
+			};
+		};
+
+		lvds0: lvds@feb90000 {
+			compatible = "renesas,r8a7791-lvds";
+			reg = <0 0xfeb90000 0 0x1c>;
+			clocks = <&cpg CPG_MOD 726>;
+			power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
+			resets = <&cpg 726>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					lvds0_in: endpoint {
+						remote-endpoint = <&du_out_lvds0>;
+					};
+				};
+				port@1 {
+					reg = <1>;
+					lvds0_out: endpoint {
 					};
 				};
 			};
diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts
index 9ed6961f2d9a..96e117d8b2cc 100644
--- a/arch/arm/boot/dts/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/r8a7793-gose.dts
@@ -447,10 +447,9 @@
 	pinctrl-names = "default";
 	status = "okay";
 
-	clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+	clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
 		 <&x13_clk>, <&x2_clk>;
-	clock-names = "du.0", "du.1", "lvds.0",
-		      "dclkin.0", "dclkin.1";
+	clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
 
 	ports {
 		port@0 {
@@ -458,6 +457,11 @@
 				remote-endpoint = <&adv7511_in>;
 			};
 		};
+	};
+};
+
+&lvds0 {
+	ports {
 		port@1 {
 			lvds_connector: endpoint {
 			};
diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi
index f9c5a557107d..4f526030dc7c 100644
--- a/arch/arm/boot/dts/r8a7793.dtsi
+++ b/arch/arm/boot/dts/r8a7793.dtsi
@@ -1292,15 +1292,12 @@
 
 		du: display@feb00000 {
 			compatible = "renesas,du-r8a7793";
-			reg = <0 0xfeb00000 0 0x40000>,
-			      <0 0xfeb90000 0 0x1c>;
-			reg-names = "du", "lvds.0";
+			reg = <0 0xfeb00000 0 0x40000>;
 			interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 724>,
-				 <&cpg CPG_MOD 723>,
-				 <&cpg CPG_MOD 726>;
-			clock-names = "du.0", "du.1", "lvds.0";
+				 <&cpg CPG_MOD 723>;
+			clock-names = "du.0", "du.1";
 			status = "disabled";
 
 			ports {
@@ -1315,6 +1312,34 @@
 				port@1 {
 					reg = <1>;
 					du_out_lvds0: endpoint {
+						remote-endpoint = <&lvds0_in>;
+					};
+				};
+			};
+		};
+
+		lvds0: lvds@feb90000 {
+			compatible = "renesas,r8a7793-lvds";
+			reg = <0 0xfeb90000 0 0x1c>;
+			clocks = <&cpg CPG_MOD 726>;
+			power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
+			resets = <&cpg 726>;
+
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					lvds0_in: endpoint {
+						remote-endpoint = <&du_out_lvds0>;
+					};
+				};
+				port@1 {
+					reg = <1>;
+					lvds0_out: endpoint {
 					};
 				};
 			};
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
index 2459d133f1be..f50b19447de6 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
@@ -161,7 +161,7 @@
 	};
 
 	at24@50 {
-		compatible = "at24,24c01";
+		compatible = "atmel,24c01";
 		pagesize = <8>;
 		reg = <0x50>;
 	};
@@ -213,7 +213,7 @@
 			#size-cells = <0>;
 			reg = <6>;
 			eeprom@51 {
-				compatible = "at,24c01";
+				compatible = "atmel,24c01";
 				pagesize = <8>;
 				reg = <0x51>;
 			};
@@ -224,7 +224,7 @@
 			#size-cells = <0>;
 			reg = <7>;
 			eeprom@51 {
-				compatible = "at,24c01";
+				compatible = "atmel,24c01";
 				pagesize = <8>;
 				reg = <0x51>;
 			};
diff --git a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
index c0743305f31b..eb96ac3e6c1d 100644
--- a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
+++ b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
@@ -12,6 +12,8 @@
 			#size-cells = <1>;
 			compatible = "st,stm32mp157-pinctrl";
 			ranges = <0 0x50002000 0xa400>;
+			interrupt-parent = <&exti>;
+			st,syscfg = <&exti 0x60 0xff>;
 			pins-are-numbered;
 
 			gpioa: gpio@50002000 {
@@ -166,6 +168,8 @@
 			compatible = "st,stm32mp157-z-pinctrl";
 			ranges = <0 0x54004000 0x400>;
 			pins-are-numbered;
+			interrupt-parent = <&exti>;
+			st,syscfg = <&exti 0x60 0xff>;
 			status = "disabled";
 
 			gpioz: gpio@54004000 {
diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi
index 9e17e42b02b2..4fa0df853c8a 100644
--- a/arch/arm/boot/dts/stm32mp157c.dtsi
+++ b/arch/arm/boot/dts/stm32mp157c.dtsi
@@ -183,6 +183,13 @@
 			status = "disabled";
 		};
 
+		exti: interrupt-controller@5000d000 {
+			compatible = "st,stm32mp1-exti", "syscon";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			reg = <0x5000d000 0x400>;
+		};
+
 		usart1: serial@5c000000 {
 			compatible = "st,stm32h7-uart";
 			reg = <0x5c000000 0x400>;
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 77e8436beed4..3a1c6b45c9a1 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -76,7 +76,7 @@
 			allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi";
 			clocks = <&ccu CLK_AHB_LCD0>, <&ccu CLK_AHB_HDMI0>,
 				 <&ccu CLK_AHB_DE_BE0>, <&ccu CLK_AHB_DE_FE0>,
-				 <&ccu CLK_DE_BE0>, <&ccu CLK_AHB_DE_FE0>,
+				 <&ccu CLK_DE_BE0>, <&ccu CLK_DE_FE0>,
 				 <&ccu CLK_TCON0_CH1>, <&ccu CLK_HDMI>,
 				 <&ccu CLK_DRAM_DE_FE0>, <&ccu CLK_DRAM_DE_BE0>;
 			status = "disabled";
@@ -88,7 +88,7 @@
 			allwinner,pipeline = "de_fe0-de_be0-lcd0";
 			clocks = <&ccu CLK_AHB_LCD0>, <&ccu CLK_AHB_DE_BE0>,
 				 <&ccu CLK_AHB_DE_FE0>, <&ccu CLK_DE_BE0>,
-				 <&ccu CLK_AHB_DE_FE0>, <&ccu CLK_TCON0_CH0>,
+				 <&ccu CLK_DE_FE0>, <&ccu CLK_TCON0_CH0>,
 				 <&ccu CLK_DRAM_DE_FE0>, <&ccu CLK_DRAM_DE_BE0>;
 			status = "disabled";
 		};
@@ -99,7 +99,7 @@
 			allwinner,pipeline = "de_fe0-de_be0-lcd0-tve0";
 			clocks = <&ccu CLK_AHB_TVE0>, <&ccu CLK_AHB_LCD0>,
 				 <&ccu CLK_AHB_DE_BE0>, <&ccu CLK_AHB_DE_FE0>,
-				 <&ccu CLK_DE_BE0>, <&ccu CLK_AHB_DE_FE0>,
+				 <&ccu CLK_DE_BE0>, <&ccu CLK_DE_FE0>,
 				 <&ccu CLK_TCON0_CH1>, <&ccu CLK_DRAM_TVE0>,
 				 <&ccu CLK_DRAM_DE_FE0>, <&ccu CLK_DRAM_DE_BE0>;
 			status = "disabled";
diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts
index 3328fe583c9b..232f124ce62c 100644
--- a/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts
+++ b/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts
@@ -117,6 +117,7 @@
 	phy-handle = <&int_mii_phy>;
 	phy-mode = "mii";
 	allwinner,leds-active-low;
+	status = "okay";
 };
 
 &hdmi {
diff --git a/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts b/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts
index d1311098ea45..ad173605b1b8 100644
--- a/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts
+++ b/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts
@@ -51,7 +51,7 @@
 
 	leds {
 		/* The LEDs use PG0~2 pins, which conflict with MMC1 */
-		status = "disbaled";
+		status = "disabled";
 	};
 };
 
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 0a7136462a1a..983dd5c14794 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -741,7 +741,7 @@
 		phy_type = "ulpi";
 		clocks = <&tegra_car TEGRA20_CLK_USB2>,
 			 <&tegra_car TEGRA20_CLK_PLL_U>,
-			 <&tegra_car TEGRA20_CLK_PLL_P_OUT4>;
+			 <&tegra_car TEGRA20_CLK_CDEV2>;
 		clock-names = "reg", "pll_u", "ulpi-link";
 		resets = <&tegra_car 58>, <&tegra_car 22>;
 		reset-names = "usb", "utmi-pads";
diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig
index 2a63fa10c813..553777ac2814 100644
--- a/arch/arm/configs/gemini_defconfig
+++ b/arch/arm/configs/gemini_defconfig
@@ -1,6 +1,7 @@
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SYSVIPC=y
 CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_USER_NS=y
 CONFIG_RELAY=y
@@ -12,15 +13,21 @@ CONFIG_ARCH_GEMINI=y
 CONFIG_PCI=y
 CONFIG_PREEMPT=y
 CONFIG_AEABI=y
+CONFIG_HIGHMEM=y
+CONFIG_CMA=y
 CONFIG_CMDLINE="console=ttyS0,115200n8"
 CONFIG_KEXEC=y
 CONFIG_BINFMT_MISC=y
 CONFIG_PM=y
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
+CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_CFI_STAA=y
@@ -33,6 +40,11 @@ CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_ATA=y
 CONFIG_PATA_FTIDE010=y
+CONFIG_NETDEVICES=y
+CONFIG_GEMINI_ETHERNET=y
+CONFIG_MDIO_BITBANG=y
+CONFIG_MDIO_GPIO=y
+CONFIG_REALTEK_PHY=y
 CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
@@ -43,9 +55,19 @@ CONFIG_SERIAL_8250_NR_UARTS=1
 CONFIG_SERIAL_8250_RUNTIME_UARTS=1
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
+CONFIG_I2C_GPIO=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
+CONFIG_SENSORS_GPIO_FAN=y
+CONFIG_SENSORS_LM75=y
+CONFIG_THERMAL=y
 CONFIG_WATCHDOG=y
-CONFIG_GEMINI_WATCHDOG=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_DRM=y
+CONFIG_DRM_PANEL_ILITEK_IL9322=y
+CONFIG_DRM_TVE200=y
+CONFIG_LOGO=y
 CONFIG_USB=y
 CONFIG_USB_MON=y
 CONFIG_USB_FOTG210_HCD=y
@@ -54,6 +76,7 @@ CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_GPIO=y
 CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_DISK=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_RTC_CLASS=y
 CONFIG_DMADEVICES=y
diff --git a/arch/arm/configs/socfpga_defconfig b/arch/arm/configs/socfpga_defconfig
index 2620ce790db0..371fca4e1ab7 100644
--- a/arch/arm/configs/socfpga_defconfig
+++ b/arch/arm/configs/socfpga_defconfig
@@ -57,6 +57,7 @@ CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_DENALI_DT=y
 CONFIG_MTD_SPI_NOR=y
+# CONFIG_MTD_SPI_NOR_USE_4K_SECTORS is not set
 CONFIG_SPI_CADENCE_QUADSPI=y
 CONFIG_OF_OVERLAY=y
 CONFIG_OF_CONFIGFS=y
diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S
index 99207c45ec10..f82cd8cf5a09 100644
--- a/arch/arm/crypto/sha1-armv4-large.S
+++ b/arch/arm/crypto/sha1-armv4-large.S
@@ -1,4 +1,14 @@
 #define __ARM_ARCH__ __LINUX_ARM_ARCH__
+@ SPDX-License-Identifier: GPL-2.0
+
+@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
+@ has relicensed it under the GPLv2. Therefore this program is free software;
+@ you can redistribute it and/or modify it under the terms of the GNU General
+@ Public License version 2 as published by the Free Software Foundation.
+@
+@ The original headers, including the original license headers, are
+@ included below for completeness.
+
 @ ====================================================================
 @ Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
index fac0533ea633..b9ec44060ed3 100644
--- a/arch/arm/crypto/sha256-armv4.pl
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -1,12 +1,19 @@
 #!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore this program is free software;
+# you can redistribute it and/or modify it under the terms of the GNU General
+# Public License version 2 as published by the Free Software Foundation.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
 
 # ====================================================================
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
 # details see http://www.openssl.org/~appro/cryptogams/.
-#
-# Permission to use under GPL terms is granted.
 # ====================================================================
 
 # SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
index 555a1a8eec90..3b58300d611c 100644
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ b/arch/arm/crypto/sha256-core.S_shipped
@@ -1,11 +1,18 @@
+@ SPDX-License-Identifier: GPL-2.0
+
+@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
+@ has relicensed it under the GPLv2. Therefore this program is free software;
+@ you can redistribute it and/or modify it under the terms of the GNU General
+@ Public License version 2 as published by the Free Software Foundation.
+@
+@ The original headers, including the original license headers, are
+@ included below for completeness.
 
 @ ====================================================================
 @ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
 @ CRYPTOGAMS licenses depending on where you obtain it. For further
 @ details see http://www.openssl.org/~appro/cryptogams/.
-@
-@ Permission to use under GPL terms is granted.
 @ ====================================================================
 
 @ SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
index a2b11a844357..fb5d15048c0b 100644
--- a/arch/arm/crypto/sha512-armv4.pl
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -1,12 +1,19 @@
 #!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore this program is free software;
+# you can redistribute it and/or modify it under the terms of the GNU General
+# Public License version 2 as published by the Free Software Foundation.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
 
 # ====================================================================
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
 # details see http://www.openssl.org/~appro/cryptogams/.
-#
-# Permission to use under GPL terms is granted.
 # ====================================================================
 
 # SHA512 block procedure for ARMv4. September 2007.
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
index 3694c4d4ca2b..b1c334a49cda 100644
--- a/arch/arm/crypto/sha512-core.S_shipped
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -1,11 +1,18 @@
+@ SPDX-License-Identifier: GPL-2.0
+
+@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
+@ has relicensed it under the GPLv2. Therefore this program is free software;
+@ you can redistribute it and/or modify it under the terms of the GNU General
+@ Public License version 2 as published by the Free Software Foundation.
+@
+@ The original headers, including the original license headers, are
+@ included below for completeness.
 
 @ ====================================================================
 @ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
 @ CRYPTOGAMS licenses depending on where you obtain it. For further
 @ details see http://www.openssl.org/~appro/cryptogams/.
-@
-@ Permission to use under GPL terms is granted.
 @ ====================================================================
 
 @ SHA512 block procedure for ARMv4. September 2007.
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 873e3c189279..1d66db9c9db5 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -1,3 +1,4 @@
+generic-y += compat.h
 generic-y += current.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index bc8d4bbd82e2..0cd4dccbae78 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -447,6 +447,14 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.size \name , . - \name
 	.endm
 
+	.macro	csdb
+#ifdef CONFIG_THUMB2_KERNEL
+	.inst.w	0xf3af8014
+#else
+	.inst	0xe320f014
+#endif
+	.endm
+
 	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
 #ifndef CONFIG_CPU_USE_DOMAINS
 	adds	\tmp, \addr, #\size - 1
@@ -536,4 +544,14 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+#ifdef CONFIG_KPROBES
+#define _ASM_NOKPROBE(entry)				\
+	.pushsection "_kprobe_blacklist", "aw" ;	\
+	.balign 4 ;					\
+	.long entry;					\
+	.popsection
+#else
+#define _ASM_NOKPROBE(entry)
+#endif
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 40f5c410fd8c..69772e742a0a 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -17,6 +17,12 @@
 #define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory")
 #define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory")
 #define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
+#ifdef CONFIG_THUMB2_KERNEL
+#define CSDB	".inst.w 0xf3af8014"
+#else
+#define CSDB	".inst	0xe320f014"
+#endif
+#define csdb() __asm__ __volatile__(CSDB : : : "memory")
 #elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
 #define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
 				    : : "r" (0) : "memory")
@@ -37,6 +43,13 @@
 #define dmb(x) __asm__ __volatile__ ("" : : : "memory")
 #endif
 
+#ifndef CSDB
+#define CSDB
+#endif
+#ifndef csdb
+#define csdb()
+#endif
+
 #ifdef CONFIG_ARM_HEAVY_MB
 extern void (*soc_mb)(void);
 extern void arm_heavy_mb(void);
@@ -63,6 +76,25 @@ extern void arm_heavy_mb(void);
 #define __smp_rmb()	__smp_mb()
 #define __smp_wmb()	dmb(ishst)
 
+#ifdef CONFIG_CPU_SPECTRE
+static inline unsigned long array_index_mask_nospec(unsigned long idx,
+						    unsigned long sz)
+{
+	unsigned long mask;
+
+	asm volatile(
+		"cmp	%1, %2\n"
+	"	sbc	%0, %1, %1\n"
+	CSDB
+	: "=r" (mask)
+	: "r" (idx), "Ir" (sz)
+	: "cc");
+
+	return mask;
+}
+#define array_index_mask_nospec array_index_mask_nospec
+#endif
+
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/arm/include/asm/bugs.h b/arch/arm/include/asm/bugs.h
index a97f1ea708d1..73a99c72a930 100644
--- a/arch/arm/include/asm/bugs.h
+++ b/arch/arm/include/asm/bugs.h
@@ -10,12 +10,14 @@
 #ifndef __ASM_BUGS_H
 #define __ASM_BUGS_H
 
-#ifdef CONFIG_MMU
 extern void check_writebuffer_bugs(void);
 
-#define check_bugs() check_writebuffer_bugs()
+#ifdef CONFIG_MMU
+extern void check_bugs(void);
+extern void check_other_bugs(void);
 #else
 #define check_bugs() do { } while (0)
+#define check_other_bugs() do { } while (0)
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 4c9fa72b59f5..07e27f212dc7 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -65,6 +65,9 @@
 #define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
 #define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
 
+#define BPIALL				__ACCESS_CP15(c7, 0, c5, 6)
+#define ICIALLU				__ACCESS_CP15(c7, 0, c5, 0)
+
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
 static inline unsigned long get_cr(void)
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index cb546425da8a..26021980504d 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -77,8 +77,16 @@
 #define ARM_CPU_PART_CORTEX_A12		0x4100c0d0
 #define ARM_CPU_PART_CORTEX_A17		0x4100c0e0
 #define ARM_CPU_PART_CORTEX_A15		0x4100c0f0
+#define ARM_CPU_PART_CORTEX_A53		0x4100d030
+#define ARM_CPU_PART_CORTEX_A57		0x4100d070
+#define ARM_CPU_PART_CORTEX_A72		0x4100d080
+#define ARM_CPU_PART_CORTEX_A73		0x4100d090
+#define ARM_CPU_PART_CORTEX_A75		0x4100d0a0
 #define ARM_CPU_PART_MASK		0xff00fff0
 
+/* Broadcom cores */
+#define ARM_CPU_PART_BRAHMA_B15		0x420000f0
+
 /* DEC implemented cores */
 #define ARM_CPU_PART_SA1100		0x4400a110
 
diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h
index 3b73fdcf3627..8de1100d1067 100644
--- a/arch/arm/include/asm/kgdb.h
+++ b/arch/arm/include/asm/kgdb.h
@@ -77,7 +77,7 @@ extern int kgdb_fault_expected;
 
 #define KGDB_MAX_NO_CPUS	1
 #define BUFMAX			400
-#define NUMREGBYTES		(DBG_MAX_REG_NUM << 2)
+#define NUMREGBYTES		(GDB_MAX_REGS << 2)
 #define NUMCRITREGBYTES		(32 << 2)
 
 #define _R0			0
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 5a953ecb0d78..231e87ad45d5 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -61,8 +61,6 @@ struct kvm_vcpu;
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
 
-extern char __kvm_hyp_vector[];
-
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index c6a749568dd6..343fc9e6f78d 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -21,6 +21,7 @@
 
 #include <linux/types.h>
 #include <linux/kvm_types.h>
+#include <asm/cputype.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -77,6 +78,9 @@ struct kvm_arch {
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 	int max_vcpus;
+
+	/* Mandated version of PSCI */
+	u32 psci_version;
 };
 
 #define KVM_NR_MEM_OBJS     40
@@ -308,8 +312,17 @@ static inline void kvm_arm_vhe_guest_exit(void) {}
 
 static inline bool kvm_arm_harden_branch_predictor(void)
 {
-	/* No way to detect it yet, pretend it is not there. */
-	return false;
+	switch(read_cpuid_part()) {
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	case ARM_CPU_PART_BRAHMA_B15:
+	case ARM_CPU_PART_CORTEX_A12:
+	case ARM_CPU_PART_CORTEX_A15:
+	case ARM_CPU_PART_CORTEX_A17:
+		return true;
+#endif
+	default:
+		return false;
+	}
 }
 
 static inline void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) {}
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 707a1f06dc5d..c94d291fd1a8 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -309,9 +309,46 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return 8;
 }
 
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+				      gpa_t gpa, void *data, unsigned long len)
+{
+	int srcu_idx = srcu_read_lock(&kvm->srcu);
+	int ret = kvm_read_guest(kvm, gpa, data, len);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return ret;
+}
+
 static inline void *kvm_get_hyp_vector(void)
 {
-	return kvm_ksym_ref(__kvm_hyp_vector);
+	switch(read_cpuid_part()) {
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	case ARM_CPU_PART_CORTEX_A12:
+	case ARM_CPU_PART_CORTEX_A17:
+	{
+		extern char __kvm_hyp_vector_bp_inv[];
+		return kvm_ksym_ref(__kvm_hyp_vector_bp_inv);
+	}
+
+	case ARM_CPU_PART_BRAHMA_B15:
+	case ARM_CPU_PART_CORTEX_A15:
+	{
+		extern char __kvm_hyp_vector_ic_inv[];
+		return kvm_ksym_ref(__kvm_hyp_vector_ic_inv);
+	}
+#endif
+	default:
+	{
+		extern char __kvm_hyp_vector[];
+		return kvm_ksym_ref(__kvm_hyp_vector);
+	}
+	}
 }
 
 static inline int kvm_map_vectors(void)
diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h
index 6d1491c8ee22..5e088c83d3d8 100644
--- a/arch/arm/include/asm/mpu.h
+++ b/arch/arm/include/asm/mpu.h
@@ -12,60 +12,101 @@
 /* ID_MMFR0 data relevant to MPU */
 #define MMFR0_PMSA		(0xF << 4)
 #define MMFR0_PMSAv7		(3 << 4)
+#define MMFR0_PMSAv8		(4 << 4)
 
 /* MPU D/I Size Register fields */
-#define MPU_RSR_SZ		1
-#define MPU_RSR_EN		0
-#define MPU_RSR_SD		8
+#define PMSAv7_RSR_SZ		1
+#define PMSAv7_RSR_EN		0
+#define PMSAv7_RSR_SD		8
 
 /* Number of subregions (SD) */
-#define MPU_NR_SUBREGS		8
-#define MPU_MIN_SUBREG_SIZE	256
+#define PMSAv7_NR_SUBREGS	8
+#define PMSAv7_MIN_SUBREG_SIZE	256
 
 /* The D/I RSR value for an enabled region spanning the whole of memory */
-#define MPU_RSR_ALL_MEM		63
+#define PMSAv7_RSR_ALL_MEM	63
 
 /* Individual bits in the DR/IR ACR */
-#define MPU_ACR_XN		(1 << 12)
-#define MPU_ACR_SHARED		(1 << 2)
+#define PMSAv7_ACR_XN		(1 << 12)
+#define PMSAv7_ACR_SHARED	(1 << 2)
 
 /* C, B and TEX[2:0] bits only have semantic meanings when grouped */
-#define MPU_RGN_CACHEABLE	0xB
-#define MPU_RGN_SHARED_CACHEABLE (MPU_RGN_CACHEABLE | MPU_ACR_SHARED)
-#define MPU_RGN_STRONGLY_ORDERED 0
+#define PMSAv7_RGN_CACHEABLE		0xB
+#define PMSAv7_RGN_SHARED_CACHEABLE	(PMSAv7_RGN_CACHEABLE | PMSAv7_ACR_SHARED)
+#define PMSAv7_RGN_STRONGLY_ORDERED	0
 
 /* Main region should only be shared for SMP */
 #ifdef CONFIG_SMP
-#define MPU_RGN_NORMAL		(MPU_RGN_CACHEABLE | MPU_ACR_SHARED)
+#define PMSAv7_RGN_NORMAL	(PMSAv7_RGN_CACHEABLE | PMSAv7_ACR_SHARED)
 #else
-#define MPU_RGN_NORMAL		MPU_RGN_CACHEABLE
+#define PMSAv7_RGN_NORMAL	PMSAv7_RGN_CACHEABLE
 #endif
 
 /* Access permission bits of ACR (only define those that we use)*/
-#define MPU_AP_PL1RO_PL0NA	(0x5 << 8)
-#define MPU_AP_PL1RW_PL0RW	(0x3 << 8)
-#define MPU_AP_PL1RW_PL0R0	(0x2 << 8)
-#define MPU_AP_PL1RW_PL0NA	(0x1 << 8)
+#define PMSAv7_AP_PL1RO_PL0NA	(0x5 << 8)
+#define PMSAv7_AP_PL1RW_PL0RW	(0x3 << 8)
+#define PMSAv7_AP_PL1RW_PL0R0	(0x2 << 8)
+#define PMSAv7_AP_PL1RW_PL0NA	(0x1 << 8)
+
+#define PMSAv8_BAR_XN		1
+
+#define PMSAv8_LAR_EN		1
+#define PMSAv8_LAR_IDX(n)	(((n) & 0x7) << 1)
+
+
+#define PMSAv8_AP_PL1RW_PL0NA	(0 << 1)
+#define PMSAv8_AP_PL1RW_PL0RW	(1 << 1)
+#define PMSAv8_AP_PL1RO_PL0RO	(3 << 1)
+
+#ifdef CONFIG_SMP
+#define PMSAv8_RGN_SHARED	(3 << 3) // inner sharable
+#else
+#define PMSAv8_RGN_SHARED	(0 << 3)
+#endif
+
+#define PMSAv8_RGN_DEVICE_nGnRnE	0
+#define PMSAv8_RGN_NORMAL		1
+
+#define PMSAv8_MAIR(attr, mt)	((attr) << ((mt) * 8))
+
+#ifdef CONFIG_CPU_V7M
+#define PMSAv8_MINALIGN		32
+#else
+#define PMSAv8_MINALIGN		64
+#endif
 
 /* For minimal static MPU region configurations */
-#define MPU_PROBE_REGION	0
-#define MPU_BG_REGION		1
-#define MPU_RAM_REGION		2
-#define MPU_ROM_REGION		3
+#define PMSAv7_PROBE_REGION	0
+#define PMSAv7_BG_REGION	1
+#define PMSAv7_RAM_REGION	2
+#define PMSAv7_ROM_REGION	3
+
+/* Fixed for PMSAv8 only */
+#define PMSAv8_XIP_REGION	0
+#define PMSAv8_KERNEL_REGION	1
 
 /* Maximum number of regions Linux is interested in */
-#define MPU_MAX_REGIONS		16
+#define MPU_MAX_REGIONS	16
 
-#define MPU_DATA_SIDE		0
-#define MPU_INSTR_SIDE		1
+#define PMSAv7_DATA_SIDE	0
+#define PMSAv7_INSTR_SIDE	1
 
 #ifndef __ASSEMBLY__
 
 struct mpu_rgn {
 	/* Assume same attributes for d/i-side  */
-	u32 drbar;
-	u32 drsr;
-	u32 dracr;
+	union {
+		u32 drbar;   /* PMSAv7 */
+		u32 prbar;   /* PMSAv8 */
+	};
+	union {
+		u32 drsr;   /* PMSAv7 */
+		u32 prlar;  /* PMSAv8 */
+	};
+	union {
+		u32 dracr;  /* PMSAv7 */
+		u32 unused; /* not used in PMSAv8 */
+	};
 };
 
 struct mpu_rgn_info {
@@ -75,16 +116,17 @@ struct mpu_rgn_info {
 extern struct mpu_rgn_info mpu_rgn_info;
 
 #ifdef CONFIG_ARM_MPU
+extern void __init pmsav7_adjust_lowmem_bounds(void);
+extern void __init pmsav8_adjust_lowmem_bounds(void);
 
-extern void __init adjust_lowmem_bounds_mpu(void);
-extern void __init mpu_setup(void);
-
+extern void __init pmsav7_setup(void);
+extern void __init pmsav8_setup(void);
 #else
-
-static inline void adjust_lowmem_bounds_mpu(void) {}
-static inline void mpu_setup(void) {}
-
-#endif /* !CONFIG_ARM_MPU */
+static inline void pmsav7_adjust_lowmem_bounds(void) {};
+static inline void pmsav8_adjust_lowmem_bounds(void) {};
+static inline void pmsav7_setup(void) {};
+static inline void pmsav8_setup(void) {};
+#endif
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index 1f0de808d111..0abd389cf0ec 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -19,13 +19,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 }
 #endif /* CONFIG_PCI_DOMAINS */
 
-/*
- * The PCI address space does equal the physical memory address space.
- * The networking and block device layers use this boolean for bounce
- * buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS     (1)
-
 #define HAVE_PCI_MMAP
 #define ARCH_GENERIC_PCI_MMAP_RESOURCE
 
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index f2e1af45bd6f..e25f4392e1b2 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -37,6 +37,10 @@ extern struct processor {
 	 */
 	void (*_proc_init)(void);
 	/*
+	 * Check for processor bugs
+	 */
+	void (*check_bugs)(void);
+	/*
 	 * Disable any processor specifics
 	 */
 	void (*_proc_fin)(void);
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
index 78f6db114faf..8e76db83c498 100644
--- a/arch/arm/include/asm/system_misc.h
+++ b/arch/arm/include/asm/system_misc.h
@@ -8,6 +8,7 @@
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
 #include <linux/reboot.h>
+#include <linux/percpu.h>
 
 extern void cpu_init(void);
 
@@ -15,6 +16,20 @@ void soft_restart(unsigned long);
 extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 extern void (*arm_pm_idle)(void);
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+typedef void (*harden_branch_predictor_fn_t)(void);
+DECLARE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn);
+static inline void harden_branch_predictor(void)
+{
+	harden_branch_predictor_fn_t fn = per_cpu(harden_branch_predictor_fn,
+						  smp_processor_id());
+	if (fn)
+		fn();
+}
+#else
+#define harden_branch_predictor() do { } while (0)
+#endif
+
 #define UDBG_UNDEFINED	(1 << 0)
 #define UDBG_SYSCALL	(1 << 1)
 #define UDBG_BADABORT	(1 << 2)
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 0bf2347495f1..3d614e90c19f 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -152,7 +152,7 @@ extern int __get_user_64t_4(void *);
 #define __get_user_check(x, p)						\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
-		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register typeof(*(p)) __user *__p asm("r0") = (p);	\
 		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h
index 634e77107425..187ccf6496ad 100644
--- a/arch/arm/include/asm/v7m.h
+++ b/arch/arm/include/asm/v7m.h
@@ -64,9 +64,17 @@
 #define MPU_CTRL_ENABLE		1
 #define MPU_CTRL_PRIVDEFENA	(1 << 2)
 
-#define MPU_RNR			0x98
-#define MPU_RBAR		0x9c
-#define MPU_RASR		0xa0
+#define PMSAv7_RNR		0x98
+#define PMSAv7_RBAR		0x9c
+#define PMSAv7_RASR		0xa0
+
+#define PMSAv8_RNR		0x98
+#define PMSAv8_RBAR		0x9c
+#define PMSAv8_RLAR		0xa0
+#define PMSAv8_RBAR_A(n)	(PMSAv8_RBAR + 8*(n))
+#define PMSAv8_RLAR_A(n)	(PMSAv8_RLAR + 8*(n))
+#define PMSAv8_MAIR0		0xc0
+#define PMSAv8_MAIR1		0xc4
 
 /* Cache opeartions */
 #define	V7M_SCB_ICIALLU		0x250	/* I-cache invalidate all to PoU */
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index 2ba95d6fe852..caae4843cb70 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -195,6 +195,12 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_VFP_FPINST		0x1009
 #define KVM_REG_ARM_VFP_FPINST2		0x100A
 
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r)		(KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+					 KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
diff --git a/arch/arm/include/uapi/asm/siginfo.h b/arch/arm/include/uapi/asm/siginfo.h
deleted file mode 100644
index d0513880be21..000000000000
--- a/arch/arm/include/uapi/asm/siginfo.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_SIGINFO_H
-#define __ASM_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME	0	/* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-#endif
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index b59ac4bf82b8..8cad59465af3 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -31,6 +31,7 @@ else
 obj-y		+= entry-armv.o
 endif
 
+obj-$(CONFIG_MMU)		+= bugs.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index f369ece99958..27c5381518d8 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -194,9 +194,11 @@ int main(void)
   DEFINE(MPU_RNG_INFO_USED,	offsetof(struct mpu_rgn_info, used));
 
   DEFINE(MPU_RNG_SIZE,		sizeof(struct mpu_rgn));
-  DEFINE(MPU_RGN_DRBAR,		offsetof(struct mpu_rgn, drbar));
-  DEFINE(MPU_RGN_DRSR,		offsetof(struct mpu_rgn, drsr));
-  DEFINE(MPU_RGN_DRACR,		offsetof(struct mpu_rgn, dracr));
+  DEFINE(MPU_RGN_DRBAR,	offsetof(struct mpu_rgn, drbar));
+  DEFINE(MPU_RGN_DRSR,	offsetof(struct mpu_rgn, drsr));
+  DEFINE(MPU_RGN_DRACR,	offsetof(struct mpu_rgn, dracr));
+  DEFINE(MPU_RGN_PRBAR,	offsetof(struct mpu_rgn, prbar));
+  DEFINE(MPU_RGN_PRLAR,	offsetof(struct mpu_rgn, prlar));
 #endif
   return 0; 
 }
diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c
new file mode 100644
index 000000000000..7be511310191
--- /dev/null
+++ b/arch/arm/kernel/bugs.c
@@ -0,0 +1,18 @@
+// SPDX-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <asm/bugs.h>
+#include <asm/proc-fns.h>
+
+void check_other_bugs(void)
+{
+#ifdef MULTI_CPU
+	if (processor.check_bugs)
+		processor.check_bugs();
+#endif
+}
+
+void __init check_bugs(void)
+{
+	check_writebuffer_bugs();
+	check_other_bugs();
+}
diff --git a/arch/arm/kernel/dma.c b/arch/arm/kernel/dma.c
index e651c4d0a0d9..6739d37c2bc5 100644
--- a/arch/arm/kernel/dma.c
+++ b/arch/arm/kernel/dma.c
@@ -276,21 +276,9 @@ static int proc_dma_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int proc_dma_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_dma_show, NULL);
-}
-
-static const struct file_operations proc_dma_operations = {
-	.open		= proc_dma_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_dma_init(void)
 {
-	proc_create("dma", 0, NULL, &proc_dma_operations);
+	proc_create_single("dma", 0, NULL, proc_dma_show);
 	return 0;
 }
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 3c4f88701f22..20df608bf343 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -242,9 +242,7 @@ local_restart:
 	tst	r10, #_TIF_SYSCALL_WORK		@ are we tracing syscalls?
 	bne	__sys_trace
 
-	cmp	scno, #NR_syscalls		@ check upper syscall limit
-	badr	lr, ret_fast_syscall		@ return address
-	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
+	invoke_syscall tbl, scno, r10, ret_fast_syscall
 
 	add	r1, sp, #S_OFF
 2:	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
@@ -278,14 +276,8 @@ __sys_trace:
 	mov	r1, scno
 	add	r0, sp, #S_OFF
 	bl	syscall_trace_enter
-
-	badr	lr, __sys_trace_return		@ return address
-	mov	scno, r0			@ syscall number (possibly new)
-	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	cmp	scno, #NR_syscalls		@ check upper syscall limit
-	ldmccia	r1, {r0 - r6}			@ have to reload r0 - r6
-	stmccia	sp, {r4, r5}			@ and update the stack args
-	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
+	mov	scno, r0
+	invoke_syscall tbl, scno, r10, __sys_trace_return, reload=1
 	cmp	scno, #-1			@ skip the syscall?
 	bne	2b
 	add	sp, sp, #S_OFF			@ restore stack
@@ -363,6 +355,10 @@ sys_syscall:
 		bic	scno, r0, #__NR_OABI_SYSCALL_BASE
 		cmp	scno, #__NR_syscall - __NR_SYSCALL_BASE
 		cmpne	scno, #NR_syscalls	@ check range
+#ifdef CONFIG_CPU_SPECTRE
+		movhs	scno, #0
+		csdb
+#endif
 		stmloia	sp, {r5, r6}		@ shuffle args
 		movlo	r0, r1
 		movlo	r1, r2
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 0f07579af472..773424843d6e 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -378,6 +378,31 @@
 #endif
 	.endm
 
+	.macro	invoke_syscall, table, nr, tmp, ret, reload=0
+#ifdef CONFIG_CPU_SPECTRE
+	mov	\tmp, \nr
+	cmp	\tmp, #NR_syscalls		@ check upper syscall limit
+	movcs	\tmp, #0
+	csdb
+	badr	lr, \ret			@ return address
+	.if	\reload
+	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
+	ldmccia	r1, {r0 - r6}			@ reload r0-r6
+	stmccia	sp, {r4, r5}			@ update stack arguments
+	.endif
+	ldrcc	pc, [\table, \tmp, lsl #2]	@ call sys_* routine
+#else
+	cmp	\nr, #NR_syscalls		@ check upper syscall limit
+	badr	lr, \ret			@ return address
+	.if	\reload
+	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
+	ldmccia	r1, {r0 - r6}			@ reload r0-r6
+	stmccia	sp, {r4, r5}			@ update stack arguments
+	.endif
+	ldrcc	pc, [\table, \nr, lsl #2]	@ call sys_* routine
+#endif
+	.endm
+
 /*
  * These are the registers used in the syscall handler, and allow us to
  * have in theory up to 7 arguments to a function - r0 to r6.
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 2e38f85b757a..dd546d65a383 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -68,14 +68,6 @@ ENTRY(stext)
 	beq	__error_p				@ yes, error 'p'
 
 #ifdef CONFIG_ARM_MPU
-	/* Calculate the size of a region covering just the kernel */
-	ldr	r5, =PLAT_PHYS_OFFSET		@ Region start: PHYS_OFFSET
-	ldr     r6, =(_end)			@ Cover whole kernel
-	sub	r6, r6, r5			@ Minimum size of region to map
-	clz	r6, r6				@ Region size must be 2^N...
-	rsb	r6, r6, #31			@ ...so round up region size
-	lsl	r6, r6, #MPU_RSR_SZ		@ Put size in right field
-	orr	r6, r6, #(1 << MPU_RSR_EN)	@ Set region enabled bit
 	bl	__setup_mpu
 #endif
 
@@ -83,8 +75,8 @@ ENTRY(stext)
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
 	add	r12, r12, r10
 	ret	r12
-1:	bl	__after_proc_init
-	b	__mmap_switched
+1:	ldr	lr, =__mmap_switched
+	b	__after_proc_init
 ENDPROC(stext)
 
 #ifdef CONFIG_SMP
@@ -110,8 +102,6 @@ ENTRY(secondary_startup)
 	ldr	r7, __secondary_data
 
 #ifdef CONFIG_ARM_MPU
-	/* Use MPU region info supplied by __cpu_up */
-	ldr	r6, [r7]			@ get secondary_data.mpu_rgn_info
 	bl      __secondary_setup_mpu		@ Initialize the MPU
 #endif
 
@@ -133,12 +123,45 @@ __secondary_data:
 /*
  * Set the Control Register and Read the process ID.
  */
+	.text
 __after_proc_init:
+#ifdef CONFIG_ARM_MPU
+M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
+M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+M_CLASS(ldr	r3, [r12, 0x50])
+AR_CLASS(mrc	p15, 0, r3, c0, c1, 4)          @ Read ID_MMFR0
+	and	r3, r3, #(MMFR0_PMSA)           @ PMSA field
+	teq	r3, #(MMFR0_PMSAv7)             @ PMSA v7
+	beq	1f
+	teq	r3, #(MMFR0_PMSAv8)		@ PMSA v8
+	/*
+	 * Memory region attributes for PMSAv8:
+	 *
+	 *   n = AttrIndx[2:0]
+	 *                      n       MAIR
+	 *   DEVICE_nGnRnE      000     00000000
+	 *   NORMAL             001     11111111
+	 */
+	ldreq	r3, =PMSAv8_MAIR(0x00, PMSAv8_RGN_DEVICE_nGnRnE) | \
+		     PMSAv8_MAIR(0xff, PMSAv8_RGN_NORMAL)
+AR_CLASS(mcreq	p15, 0, r3, c10, c2, 0)		@ MAIR 0
+M_CLASS(streq	r3, [r12, #PMSAv8_MAIR0])
+	moveq	r3, #0
+AR_CLASS(mcreq	p15, 0, r3, c10, c2, 1)		@ MAIR 1
+M_CLASS(streq	r3, [r12, #PMSAv8_MAIR1])
+
+1:
+#endif
 #ifdef CONFIG_CPU_CP15
 	/*
 	 * CP15 system control register value returned in r0 from
 	 * the CPU init function.
 	 */
+
+#ifdef CONFIG_ARM_MPU
+	biceq	r0, r0, #CR_BR			@ Disable the 'default mem-map'
+	orreq	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
+#endif
 #if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
 	orr	r0, r0, #CR_A
 #else
@@ -154,7 +177,15 @@ __after_proc_init:
 	bic	r0, r0, #CR_I
 #endif
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
+	isb
 #elif defined (CONFIG_CPU_V7M)
+#ifdef CONFIG_ARM_MPU
+	ldreq	r3, [r12, MPU_CTRL]
+	biceq	r3, #MPU_CTRL_PRIVDEFENA
+	orreq	r3, #MPU_CTRL_ENABLE
+	streq	r3, [r12, MPU_CTRL]
+	isb
+#endif
 	/* For V7M systems we want to modify the CCR similarly to the SCTLR */
 #ifdef CONFIG_CPU_DCACHE_DISABLE
 	bic	r0, r0, #V7M_SCB_CCR_DC
@@ -165,9 +196,7 @@ __after_proc_init:
 #ifdef CONFIG_CPU_ICACHE_DISABLE
 	bic	r0, r0, #V7M_SCB_CCR_IC
 #endif
-	movw	r3, #:lower16:(BASEADDR_V7M_SCB + V7M_SCB_CCR)
-	movt	r3, #:upper16:(BASEADDR_V7M_SCB + V7M_SCB_CCR)
-	str	r0, [r3]
+	str	r0, [r12, V7M_SCB_CCR]
 #endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */
 	ret	lr
 ENDPROC(__after_proc_init)
@@ -184,7 +213,7 @@ ENDPROC(__after_proc_init)
 .endm
 
 /* Setup a single MPU region, either D or I side (D-side for unified) */
-.macro setup_region bar, acr, sr, side = MPU_DATA_SIDE, unused
+.macro setup_region bar, acr, sr, side = PMSAv7_DATA_SIDE, unused
 	mcr	p15, 0, \bar, c6, c1, (0 + \side)	@ I/DRBAR
 	mcr	p15, 0, \acr, c6, c1, (4 + \side)	@ I/DRACR
 	mcr	p15, 0, \sr, c6, c1, (2 + \side)		@ I/DRSR
@@ -192,14 +221,14 @@ ENDPROC(__after_proc_init)
 #else
 .macro set_region_nr tmp, rgnr, base
 	mov	\tmp, \rgnr
-	str     \tmp, [\base, #MPU_RNR]
+	str     \tmp, [\base, #PMSAv7_RNR]
 .endm
 
 .macro setup_region bar, acr, sr, unused, base
 	lsl     \acr, \acr, #16
 	orr     \acr, \acr, \sr
-	str     \bar, [\base, #MPU_RBAR]
-	str     \acr, [\base, #MPU_RASR]
+	str     \bar, [\base, #PMSAv7_RBAR]
+	str     \acr, [\base, #PMSAv7_RASR]
 .endm
 
 #endif
@@ -210,8 +239,9 @@ ENDPROC(__after_proc_init)
  * Region 2: Normal, Shared, cacheable for RAM. From PHYS_OFFSET, size from r6
  * Region 3: Normal, shared, inaccessible from PL0 to protect the vectors page
  *
- * r6: Value to be written to DRSR (and IRSR if required) for MPU_RAM_REGION
+ * r6: Value to be written to DRSR (and IRSR if required) for PMSAv7_RAM_REGION
 */
+	__HEAD
 
 ENTRY(__setup_mpu)
 
@@ -223,7 +253,22 @@ AR_CLASS(mrc	p15, 0, r0, c0, c1, 4)		@ Read ID_MMFR0
 M_CLASS(ldr	r0, [r12, 0x50])
 	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
 	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
-	bxne	lr
+	beq	__setup_pmsa_v7
+	teq	r0, #(MMFR0_PMSAv8)		@ PMSA v8
+	beq	__setup_pmsa_v8
+
+	ret	lr
+ENDPROC(__setup_mpu)
+
+ENTRY(__setup_pmsa_v7)
+	/* Calculate the size of a region covering just the kernel */
+	ldr	r5, =PLAT_PHYS_OFFSET		@ Region start: PHYS_OFFSET
+	ldr     r6, =(_end)			@ Cover whole kernel
+	sub	r6, r6, r5			@ Minimum size of region to map
+	clz	r6, r6				@ Region size must be 2^N...
+	rsb	r6, r6, #31			@ ...so round up region size
+	lsl	r6, r6, #PMSAv7_RSR_SZ		@ Put size in right field
+	orr	r6, r6, #(1 << PMSAv7_RSR_EN)	@ Set region enabled bit
 
 	/* Determine whether the D/I-side memory map is unified. We set the
 	 * flags here and continue to use them for the rest of this function */
@@ -234,77 +279,189 @@ M_CLASS(ldr    r0, [r12, #MPU_TYPE])
 	tst	r0, #MPUIR_nU			@ MPUIR_nU = 0 for unified
 
 	/* Setup second region first to free up r6 */
-	set_region_nr r0, #MPU_RAM_REGION, r12
+	set_region_nr r0, #PMSAv7_RAM_REGION, r12
 	isb
 	/* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */
 	ldr	r0, =PLAT_PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
-	ldr	r5,=(MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL)
+	ldr	r5,=(PMSAv7_AP_PL1RW_PL0RW | PMSAv7_RGN_NORMAL)
 
-	setup_region r0, r5, r6, MPU_DATA_SIDE, r12	@ PHYS_OFFSET, shared, enabled
+	setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12	@ PHYS_OFFSET, shared, enabled
 	beq	1f					@ Memory-map not unified
-	setup_region r0, r5, r6, MPU_INSTR_SIDE, r12	@ PHYS_OFFSET, shared, enabled
+	setup_region r0, r5, r6, PMSAv7_INSTR_SIDE, r12	@ PHYS_OFFSET, shared, enabled
 1:	isb
 
 	/* First/background region */
-	set_region_nr r0, #MPU_BG_REGION, r12
+	set_region_nr r0, #PMSAv7_BG_REGION, r12
 	isb
 	/* Execute Never,  strongly ordered, inaccessible to PL0, rw PL1  */
 	mov	r0, #0				@ BG region starts at 0x0
-	ldr	r5,=(MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA)
-	mov	r6, #MPU_RSR_ALL_MEM		@ 4GB region, enabled
+	ldr	r5,=(PMSAv7_ACR_XN | PMSAv7_RGN_STRONGLY_ORDERED | PMSAv7_AP_PL1RW_PL0NA)
+	mov	r6, #PMSAv7_RSR_ALL_MEM		@ 4GB region, enabled
 
-	setup_region r0, r5, r6, MPU_DATA_SIDE, r12	@ 0x0, BG region, enabled
+	setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12	@ 0x0, BG region, enabled
 	beq	2f					@ Memory-map not unified
-	setup_region r0, r5, r6, MPU_INSTR_SIDE r12	@ 0x0, BG region, enabled
+	setup_region r0, r5, r6, PMSAv7_INSTR_SIDE r12	@ 0x0, BG region, enabled
 2:	isb
 
 #ifdef CONFIG_XIP_KERNEL
-	set_region_nr r0, #MPU_ROM_REGION, r12
+	set_region_nr r0, #PMSAv7_ROM_REGION, r12
 	isb
 
-	ldr	r5,=(MPU_AP_PL1RO_PL0NA | MPU_RGN_NORMAL)
+	ldr	r5,=(PMSAv7_AP_PL1RO_PL0NA | PMSAv7_RGN_NORMAL)
 
 	ldr	r0, =CONFIG_XIP_PHYS_ADDR		@ ROM start
 	ldr     r6, =(_exiprom)				@ ROM end
 	sub	r6, r6, r0				@ Minimum size of region to map
 	clz	r6, r6					@ Region size must be 2^N...
 	rsb	r6, r6, #31				@ ...so round up region size
-	lsl	r6, r6, #MPU_RSR_SZ			@ Put size in right field
-	orr	r6, r6, #(1 << MPU_RSR_EN)		@ Set region enabled bit
+	lsl	r6, r6, #PMSAv7_RSR_SZ			@ Put size in right field
+	orr	r6, r6, #(1 << PMSAv7_RSR_EN)		@ Set region enabled bit
 
-	setup_region r0, r5, r6, MPU_DATA_SIDE, r12	@ XIP_PHYS_ADDR, shared, enabled
+	setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12	@ XIP_PHYS_ADDR, shared, enabled
 	beq	3f					@ Memory-map not unified
-	setup_region r0, r5, r6, MPU_INSTR_SIDE, r12	@ XIP_PHYS_ADDR, shared, enabled
+	setup_region r0, r5, r6, PMSAv7_INSTR_SIDE, r12	@ XIP_PHYS_ADDR, shared, enabled
 3:	isb
 #endif
+	ret	lr
+ENDPROC(__setup_pmsa_v7)
+
+ENTRY(__setup_pmsa_v8)
+	mov	r0, #0
+AR_CLASS(mcr	p15, 0, r0, c6, c2, 1)		@ PRSEL
+M_CLASS(str	r0, [r12, #PMSAv8_RNR])
+	isb
+
+#ifdef CONFIG_XIP_KERNEL
+	ldr	r5, =CONFIG_XIP_PHYS_ADDR		@ ROM start
+	ldr     r6, =(_exiprom)				@ ROM end
+	sub	r6, r6, #1
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN)
+
+AR_CLASS(mcr	p15, 0, r5, c6, c8, 0)			@ PRBAR0
+AR_CLASS(mcr	p15, 0, r6, c6, c8, 1)			@ PRLAR0
+M_CLASS(str	r5, [r12, #PMSAv8_RBAR_A(0)])
+M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(0)])
+#endif
+
+	ldr	r5, =KERNEL_START
+	ldr	r6, =KERNEL_END
+	sub	r6, r6, #1
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN)
+
+AR_CLASS(mcr	p15, 0, r5, c6, c8, 4)			@ PRBAR1
+AR_CLASS(mcr	p15, 0, r6, c6, c8, 5)			@ PRLAR1
+M_CLASS(str	r5, [r12, #PMSAv8_RBAR_A(1)])
+M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(1)])
+
+	/* Setup Background: 0x0 - min(KERNEL_START, XIP_PHYS_ADDR) */
+#ifdef CONFIG_XIP_KERNEL
+	ldr	r6, =KERNEL_START
+	ldr	r5, =CONFIG_XIP_PHYS_ADDR
+	cmp	r6, r5
+	movcs	r6, r5
+#else
+	ldr	r6, =KERNEL_START
+#endif
+	cmp	r6, #0
+	beq	1f
+
+	mov	r5, #0
+	sub	r6, r6, #1
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN)
+
+AR_CLASS(mcr	p15, 0, r5, c6, c9, 0)			@ PRBAR2
+AR_CLASS(mcr	p15, 0, r6, c6, c9, 1)			@ PRLAR2
+M_CLASS(str	r5, [r12, #PMSAv8_RBAR_A(2)])
+M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(2)])
+
+1:
+	/* Setup Background: max(KERNEL_END, _exiprom) - 0xffffffff */
+#ifdef CONFIG_XIP_KERNEL
+	ldr	r5, =KERNEL_END
+	ldr	r6, =(_exiprom)
+	cmp	r5, r6
+	movcc	r5, r6
+#else
+	ldr	r5, =KERNEL_END
+#endif
+	mov	r6, #0xffffffff
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN)
 
-	/* Enable the MPU */
-AR_CLASS(mrc	p15, 0, r0, c1, c0, 0)		@ Read SCTLR
-AR_CLASS(bic	r0, r0, #CR_BR)			@ Disable the 'default mem-map'
-AR_CLASS(orr	r0, r0, #CR_M)			@ Set SCTRL.M (MPU on)
-AR_CLASS(mcr	p15, 0, r0, c1, c0, 0)		@ Enable MPU
+AR_CLASS(mcr	p15, 0, r5, c6, c9, 4)			@ PRBAR3
+AR_CLASS(mcr	p15, 0, r6, c6, c9, 5)			@ PRLAR3
+M_CLASS(str	r5, [r12, #PMSAv8_RBAR_A(3)])
+M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(3)])
 
-M_CLASS(ldr	r0, [r12, #MPU_CTRL])
-M_CLASS(bic	r0, #MPU_CTRL_PRIVDEFENA)
-M_CLASS(orr	r0, #MPU_CTRL_ENABLE)
-M_CLASS(str	r0, [r12, #MPU_CTRL])
+#ifdef CONFIG_XIP_KERNEL
+	/* Setup Background: min(_exiprom, KERNEL_END) - max(KERNEL_START, XIP_PHYS_ADDR) */
+	ldr	r5, =(_exiprom)
+	ldr	r6, =KERNEL_END
+	cmp	r5, r6
+	movcs	r5, r6
+
+	ldr	r6, =KERNEL_START
+	ldr	r0, =CONFIG_XIP_PHYS_ADDR
+	cmp	r6, r0
+	movcc	r6, r0
+
+	sub	r6, r6, #1
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN)
+
+#ifdef CONFIG_CPU_V7M
+	/* There is no alias for n == 4 */
+	mov	r0, #4
+	str	r0, [r12, #PMSAv8_RNR]			@ PRSEL
 	isb
 
+	str	r5, [r12, #PMSAv8_RBAR_A(0)]
+	str	r6, [r12, #PMSAv8_RLAR_A(0)]
+#else
+	mcr	p15, 0, r5, c6, c10, 1			@ PRBAR4
+	mcr	p15, 0, r6, c6, c10, 2			@ PRLAR4
+#endif
+#endif
 	ret	lr
-ENDPROC(__setup_mpu)
+ENDPROC(__setup_pmsa_v8)
 
 #ifdef CONFIG_SMP
 /*
  * r6: pointer at mpu_rgn_info
  */
 
+	.text
 ENTRY(__secondary_setup_mpu)
+	/* Use MPU region info supplied by __cpu_up */
+	ldr	r6, [r7]			@ get secondary_data.mpu_rgn_info
+
 	/* Probe for v7 PMSA compliance */
 	mrc	p15, 0, r0, c0, c1, 4		@ Read ID_MMFR0
 	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
 	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
-	bne	__error_p
+	beq	__secondary_setup_pmsa_v7
+	teq	r0, #(MMFR0_PMSAv8)		@ PMSA v8
+	beq	__secondary_setup_pmsa_v8
+	b	__error_p
+ENDPROC(__secondary_setup_mpu)
 
+/*
+ * r6: pointer at mpu_rgn_info
+ */
+ENTRY(__secondary_setup_pmsa_v7)
 	/* Determine whether the D/I-side memory map is unified. We set the
 	 * flags here and continue to use them for the rest of this function */
 	mrc	p15, 0, r0, c0, c0, 4		@ MPUIR
@@ -328,25 +485,45 @@ ENTRY(__secondary_setup_mpu)
 	ldr	r6, [r3, #MPU_RGN_DRSR]
 	ldr	r5, [r3, #MPU_RGN_DRACR]
 
-	setup_region r0, r5, r6, MPU_DATA_SIDE
+	setup_region r0, r5, r6, PMSAv7_DATA_SIDE
 	beq	2f
-	setup_region r0, r5, r6, MPU_INSTR_SIDE
+	setup_region r0, r5, r6, PMSAv7_INSTR_SIDE
 2:	isb
 
 	mrc	p15, 0, r0, c0, c0, 4		@ Reevaluate the MPUIR
 	cmp	r4, #0
 	bgt	1b
 
-	/* Enable the MPU */
-	mrc	p15, 0, r0, c1, c0, 0		@ Read SCTLR
-	bic	r0, r0, #CR_BR			@ Disable the 'default mem-map'
-	orr	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
-	mcr	p15, 0, r0, c1, c0, 0		@ Enable MPU
+	ret	lr
+ENDPROC(__secondary_setup_pmsa_v7)
+
+ENTRY(__secondary_setup_pmsa_v8)
+	ldr	r4, [r6, #MPU_RNG_INFO_USED]
+#ifndef CONFIG_XIP_KERNEL
+	add	r4, r4, #1
+#endif
+	mov	r5, #MPU_RNG_SIZE
+	add	r3, r6, #MPU_RNG_INFO_RNGS
+	mla	r3, r4, r5, r3
+
+1:
+	sub	r3, r3, #MPU_RNG_SIZE
+	sub	r4, r4, #1
+
+	mcr	p15, 0, r4, c6, c2, 1		@ PRSEL
 	isb
 
-	ret	lr
-ENDPROC(__secondary_setup_mpu)
+	ldr	r5, [r3, #MPU_RGN_PRBAR]
+	ldr	r6, [r3, #MPU_RGN_PRLAR]
 
+	mcr	p15, 0, r5, c6, c3, 0		@ PRBAR
+	mcr	p15, 0, r6, c6, c3, 1           @ PRLAR
+
+	cmp	r4, #0
+	bgt	1b
+
+	ret	lr
+ENDPROC(__secondary_setup_pmsa_v8)
 #endif /* CONFIG_SMP */
 #endif /* CONFIG_ARM_MPU */
 #include "head-common.S"
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 6b38d7a634c1..dd2eb5f76b9f 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -83,7 +83,7 @@ void machine_crash_nonpanic_core(void *unused)
 {
 	struct pt_regs regs;
 
-	crash_setup_regs(&regs, NULL);
+	crash_setup_regs(&regs, get_irq_regs());
 	printk(KERN_DEBUG "CPU %u will stop doing anything useful since another CPU has crashed\n",
 	       smp_processor_id());
 	crash_save_cpu(&regs, smp_processor_id());
@@ -95,6 +95,27 @@ void machine_crash_nonpanic_core(void *unused)
 		cpu_relax();
 }
 
+void crash_smp_send_stop(void)
+{
+	static int cpus_stopped;
+	unsigned long msecs;
+
+	if (cpus_stopped)
+		return;
+
+	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+	smp_call_function(machine_crash_nonpanic_core, NULL, false);
+	msecs = 1000; /* Wait at most a second for the other cpus to stop */
+	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+		mdelay(1);
+		msecs--;
+	}
+	if (atomic_read(&waiting_for_crash_ipi) > 0)
+		pr_warn("Non-crashing CPUs did not react to IPI\n");
+
+	cpus_stopped = 1;
+}
+
 static void machine_kexec_mask_interrupts(void)
 {
 	unsigned int i;
@@ -120,19 +141,8 @@ static void machine_kexec_mask_interrupts(void)
 
 void machine_crash_shutdown(struct pt_regs *regs)
 {
-	unsigned long msecs;
-
 	local_irq_disable();
-
-	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	smp_call_function(machine_crash_nonpanic_core, NULL, false);
-	msecs = 1000; /* Wait at most a second for the other cpus to stop */
-	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
-		mdelay(1);
-		msecs--;
-	}
-	if (atomic_read(&waiting_for_crash_ipi) > 0)
-		pr_warn("Non-crashing CPUs did not react to IPI\n");
+	crash_smp_send_stop();
 
 	crash_save_cpu(regs, smp_processor_id());
 	machine_kexec_mask_interrupts();
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 7724b0f661b3..36718a424358 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -205,6 +205,7 @@ void ptrace_break(struct task_struct *tsk, struct pt_regs *regs)
 {
 	siginfo_t info;
 
+	clear_siginfo(&info);
 	info.si_signo = SIGTRAP;
 	info.si_errno = 0;
 	info.si_code  = TRAP_BRKPT;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index fc40a2b40595..35ca494c028c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -754,7 +754,7 @@ int __init arm_add_memory(u64 start, u64 size)
 	else
 		size -= aligned_start - start;
 
-#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
+#ifndef CONFIG_PHYS_ADDR_T_64BIT
 	if (aligned_start > ULONG_MAX) {
 		pr_crit("Ignoring memory at 0x%08llx outside 32-bit physical address space\n",
 			(long long)start);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 2da087926ebe..0978282d5fc2 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -31,6 +31,7 @@
 #include <linux/irq_work.h>
 
 #include <linux/atomic.h>
+#include <asm/bugs.h>
 #include <asm/smp.h>
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
@@ -236,8 +237,6 @@ int __cpu_disable(void)
 	flush_cache_louis();
 	local_flush_tlb_all();
 
-	clear_tasks_mm_cpumask(cpu);
-
 	return 0;
 }
 
@@ -255,6 +254,7 @@ void __cpu_die(unsigned int cpu)
 	}
 	pr_debug("CPU%u: shutdown\n", cpu);
 
+	clear_tasks_mm_cpumask(cpu);
 	/*
 	 * platform_cpu_kill() is generally expected to do the powering off
 	 * and/or cutting of clocks to the dying CPU.  Optionally, this may
@@ -405,6 +405,9 @@ asmlinkage void secondary_start_kernel(void)
 	 * before we continue - which happens after __cpu_up returns.
 	 */
 	set_cpu_online(cpu, true);
+
+	check_other_bugs();
+
 	complete(&cpu_running);
 
 	local_irq_enable();
diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index a40ebb7c0896..d08099269e35 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -3,6 +3,7 @@
 #include <linux/slab.h>
 #include <linux/mm_types.h>
 
+#include <asm/bugs.h>
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
 #include <asm/pgalloc.h>
@@ -36,6 +37,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 		cpu_switch_mm(mm->pgd, mm);
 		local_flush_bp_all();
 		local_flush_tlb_all();
+		check_other_bugs();
 	}
 
 	return ret;
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 3bda08bee674..80517f293eb9 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -91,18 +91,6 @@ static int proc_status_show(struct seq_file *m, void *v)
 		seq_printf(m, "Last process:\t\t%d\n", previous_pid);
 	return 0;
 }
-
-static int proc_status_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_status_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_status_fops = {
-	.open		= proc_status_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 /*
@@ -112,6 +100,7 @@ static void set_segfault(struct pt_regs *regs, unsigned long addr)
 {
 	siginfo_t info;
 
+	clear_siginfo(&info);
 	down_read(&current->mm->mmap_sem);
 	if (find_vma(current->mm, addr) == NULL)
 		info.si_code = SEGV_MAPERR;
@@ -260,7 +249,8 @@ static int __init swp_emulation_init(void)
 		return 0;
 
 #ifdef CONFIG_PROC_FS
-	if (!proc_create("cpu/swp_emulation", S_IRUGO, NULL, &proc_status_fops))
+	if (!proc_create_single("cpu/swp_emulation", S_IRUGO, NULL,
+			proc_status_show))
 		return -ENOMEM;
 #endif /* CONFIG_PROC_FS */
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 5e3633c24e63..badf02ca3693 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -19,6 +19,7 @@
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
 #include <linux/kdebug.h>
+#include <linux/kprobes.h>
 #include <linux/module.h>
 #include <linux/kexec.h>
 #include <linux/bug.h>
@@ -417,7 +418,8 @@ void unregister_undef_hook(struct undef_hook *hook)
 	raw_spin_unlock_irqrestore(&undef_lock, flags);
 }
 
-static int call_undef_hook(struct pt_regs *regs, unsigned int instr)
+static nokprobe_inline
+int call_undef_hook(struct pt_regs *regs, unsigned int instr)
 {
 	struct undef_hook *hook;
 	unsigned long flags;
@@ -439,6 +441,7 @@ asmlinkage void do_undefinstr(struct pt_regs *regs)
 	siginfo_t info;
 	void __user *pc;
 
+	clear_siginfo(&info);
 	pc = (void __user *)instruction_pointer(regs);
 
 	if (processor_mode(regs) == SVC_MODE) {
@@ -490,6 +493,7 @@ die_sig:
 
 	arm_notify_die("Oops - undefined instruction", regs, &info, 0, 6);
 }
+NOKPROBE_SYMBOL(do_undefinstr)
 
 /*
  * Handle FIQ similarly to NMI on x86 systems.
@@ -537,6 +541,7 @@ static int bad_syscall(int n, struct pt_regs *regs)
 {
 	siginfo_t info;
 
+	clear_siginfo(&info);
 	if ((current->personality & PER_MASK) != PER_LINUX) {
 		send_sig(SIGSEGV, current, 1);
 		return regs->ARM_r0;
@@ -604,6 +609,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 {
 	siginfo_t info;
 
+	clear_siginfo(&info);
 	if ((no >> 16) != (__ARM_NR_BASE>> 16))
 		return bad_syscall(no, regs);
 
@@ -740,6 +746,8 @@ baddataabort(int code, unsigned long instr, struct pt_regs *regs)
 	unsigned long addr = instruction_pointer(regs);
 	siginfo_t info;
 
+	clear_siginfo(&info);
+
 #ifdef CONFIG_DEBUG_USER
 	if (user_debug & UDBG_BADABORT) {
 		pr_err("[%d] %s: bad data abort: code %d instr 0x%08lx\n",
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index d32f5d35f602..3593d5c1acd2 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -13,6 +13,7 @@
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
+#include <asm/mpu.h>
 #include <asm/page.h>
 
 #include "vmlinux.lds.h"
@@ -148,6 +149,9 @@ SECTIONS
 	__init_end = .;
 
 	BSS_SECTION(0, 0, 8)
+#ifdef CONFIG_ARM_MPU
+	. = ALIGN(PMSAv8_MINALIGN);
+#endif
 	_end = .;
 
 	STABS_DEBUG
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index b77dc675ae55..23150c0f0f4d 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -12,6 +12,7 @@
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
+#include <asm/mpu.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
@@ -54,6 +55,9 @@ SECTIONS
 	. = ALIGN(1<<SECTION_SHIFT);
 #endif
 
+#ifdef CONFIG_ARM_MPU
+	. = ALIGN(PMSAv8_MINALIGN);
+#endif
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
 		ARM_TEXT
@@ -143,6 +147,9 @@ SECTIONS
 	_edata = .;
 
 	BSS_SECTION(0, 0, 0)
+#ifdef CONFIG_ARM_MPU
+	. = ALIGN(PMSAv8_MINALIGN);
+#endif
 	_end = .;
 
 	STABS_DEBUG
diff --git a/arch/arm/kernel/vmlinux.lds.h b/arch/arm/kernel/vmlinux.lds.h
index 71281e08e1d4..ae5fdff18406 100644
--- a/arch/arm/kernel/vmlinux.lds.h
+++ b/arch/arm/kernel/vmlinux.lds.h
@@ -27,24 +27,24 @@
 
 #define PROC_INFO							\
 		. = ALIGN(4);						\
-		VMLINUX_SYMBOL(__proc_info_begin) = .;			\
+		__proc_info_begin = .;					\
 		*(.proc.info.init)					\
-		VMLINUX_SYMBOL(__proc_info_end) = .;
+		__proc_info_end = .;
 
 #define HYPERVISOR_TEXT							\
-		VMLINUX_SYMBOL(__hyp_text_start) = .;			\
+		__hyp_text_start = .;					\
 		*(.hyp.text)						\
-		VMLINUX_SYMBOL(__hyp_text_end) = .;
+		__hyp_text_end = .;
 
 #define IDMAP_TEXT							\
 		ALIGN_FUNCTION();					\
-		VMLINUX_SYMBOL(__idmap_text_start) = .;			\
+		__idmap_text_start = .;					\
 		*(.idmap.text)						\
-		VMLINUX_SYMBOL(__idmap_text_end) = .;			\
+		__idmap_text_end = .;					\
 		. = ALIGN(PAGE_SIZE);					\
-		VMLINUX_SYMBOL(__hyp_idmap_text_start) = .;		\
+		__hyp_idmap_text_start = .;				\
 		*(.hyp.idmap.text)					\
-		VMLINUX_SYMBOL(__hyp_idmap_text_end) = .;
+		__hyp_idmap_text_end = .;
 
 #define ARM_DISCARD							\
 		*(.ARM.exidx.exit.text)					\
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 1e0784ebbfd6..a18f33edc471 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
+#include <kvm/arm_psci.h>
 #include <asm/cputype.h>
 #include <linux/uaccess.h>
 #include <asm/kvm.h>
@@ -176,6 +177,7 @@ static unsigned long num_core_regs(void)
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 {
 	return num_core_regs() + kvm_arm_num_coproc_regs(vcpu)
+		+ kvm_arm_get_fw_num_regs(vcpu)
 		+ NUM_TIMER_REGS;
 }
 
@@ -196,6 +198,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 		uindices++;
 	}
 
+	ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+	if (ret)
+		return ret;
+	uindices += kvm_arm_get_fw_num_regs(vcpu);
+
 	ret = copy_timer_indices(vcpu, uindices);
 	if (ret)
 		return ret;
@@ -214,6 +221,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return get_core_reg(vcpu, reg);
 
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+		return kvm_arm_get_fw_reg(vcpu, reg);
+
 	if (is_timer_reg(reg->id))
 		return get_timer_reg(vcpu, reg);
 
@@ -230,6 +240,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return set_core_reg(vcpu, reg);
 
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+		return kvm_arm_set_fw_reg(vcpu, reg);
+
 	if (is_timer_reg(reg->id))
 		return set_timer_reg(vcpu, reg);
 
diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S
index 95a2faefc070..aa3f9a9837ac 100644
--- a/arch/arm/kvm/hyp/hyp-entry.S
+++ b/arch/arm/kvm/hyp/hyp-entry.S
@@ -16,6 +16,7 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/linkage.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
@@ -71,6 +72,90 @@ __kvm_hyp_vector:
 	W(b)	hyp_irq
 	W(b)	hyp_fiq
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	.align 5
+__kvm_hyp_vector_ic_inv:
+	.global __kvm_hyp_vector_ic_inv
+
+	/*
+	 * We encode the exception entry in the bottom 3 bits of
+	 * SP, and we have to guarantee to be 8 bytes aligned.
+	 */
+	W(add)	sp, sp, #1	/* Reset 	  7 */
+	W(add)	sp, sp, #1	/* Undef	  6 */
+	W(add)	sp, sp, #1	/* Syscall	  5 */
+	W(add)	sp, sp, #1	/* Prefetch abort 4 */
+	W(add)	sp, sp, #1	/* Data abort	  3 */
+	W(add)	sp, sp, #1	/* HVC		  2 */
+	W(add)	sp, sp, #1	/* IRQ		  1 */
+	W(nop)			/* FIQ		  0 */
+
+	mcr	p15, 0, r0, c7, c5, 0	/* ICIALLU */
+	isb
+
+	b	decode_vectors
+
+	.align 5
+__kvm_hyp_vector_bp_inv:
+	.global __kvm_hyp_vector_bp_inv
+
+	/*
+	 * We encode the exception entry in the bottom 3 bits of
+	 * SP, and we have to guarantee to be 8 bytes aligned.
+	 */
+	W(add)	sp, sp, #1	/* Reset 	  7 */
+	W(add)	sp, sp, #1	/* Undef	  6 */
+	W(add)	sp, sp, #1	/* Syscall	  5 */
+	W(add)	sp, sp, #1	/* Prefetch abort 4 */
+	W(add)	sp, sp, #1	/* Data abort	  3 */
+	W(add)	sp, sp, #1	/* HVC		  2 */
+	W(add)	sp, sp, #1	/* IRQ		  1 */
+	W(nop)			/* FIQ		  0 */
+
+	mcr	p15, 0, r0, c7, c5, 6	/* BPIALL */
+	isb
+
+decode_vectors:
+
+#ifdef CONFIG_THUMB2_KERNEL
+	/*
+	 * Yet another silly hack: Use VPIDR as a temp register.
+	 * Thumb2 is really a pain, as SP cannot be used with most
+	 * of the bitwise instructions. The vect_br macro ensures
+	 * things gets cleaned-up.
+	 */
+	mcr	p15, 4, r0, c0, c0, 0	/* VPIDR */
+	mov	r0, sp
+	and	r0, r0, #7
+	sub	sp, sp, r0
+	push	{r1, r2}
+	mov	r1, r0
+	mrc	p15, 4, r0, c0, c0, 0	/* VPIDR */
+	mrc	p15, 0, r2, c0, c0, 0	/* MIDR  */
+	mcr	p15, 4, r2, c0, c0, 0	/* VPIDR */
+#endif
+
+.macro vect_br val, targ
+ARM(	eor	sp, sp, #\val	)
+ARM(	tst	sp, #7		)
+ARM(	eorne	sp, sp, #\val	)
+
+THUMB(	cmp	r1, #\val	)
+THUMB(	popeq	{r1, r2}	)
+
+	beq	\targ
+.endm
+
+	vect_br	0, hyp_fiq
+	vect_br	1, hyp_irq
+	vect_br	2, hyp_hvc
+	vect_br	3, hyp_dabt
+	vect_br	4, hyp_pabt
+	vect_br	5, hyp_svc
+	vect_br	6, hyp_undef
+	vect_br	7, hyp_reset
+#endif
+
 .macro invalid_vector label, cause
 	.align
 \label:	mov	r0, #\cause
@@ -118,7 +203,7 @@ hyp_hvc:
 	lsr     r2, r2, #16
 	and     r2, r2, #0xff
 	cmp     r2, #0
-	bne	guest_trap		@ Guest called HVC
+	bne	guest_hvc_trap		@ Guest called HVC
 
 	/*
 	 * Getting here means host called HVC, we shift parameters and branch
@@ -149,7 +234,14 @@ hyp_hvc:
 	bx	ip
 
 1:
-	push	{lr}
+	/*
+	 * Pushing r2 here is just a way of keeping the stack aligned to
+	 * 8 bytes on any path that can trigger a HYP exception. Here,
+	 * we may well be about to jump into the guest, and the guest
+	 * exit would otherwise be badly decoded by our fancy
+	 * "decode-exception-without-a-branch" code...
+	 */
+	push	{r2, lr}
 
 	mov	lr, r0
 	mov	r0, r1
@@ -159,7 +251,21 @@ hyp_hvc:
 THUMB(	orr	lr, #1)
 	blx	lr			@ Call the HYP function
 
-	pop	{lr}
+	pop	{r2, lr}
+	eret
+
+guest_hvc_trap:
+	movw	r2, #:lower16:ARM_SMCCC_ARCH_WORKAROUND_1
+	movt	r2, #:upper16:ARM_SMCCC_ARCH_WORKAROUND_1
+	ldr	r0, [sp]		@ Guest's r0
+	teq	r0, r2
+	bne	guest_trap
+	add	sp, sp, #12
+	@ Returns:
+	@ r0 = 0
+	@ r1 = HSR value (perfectly predictable)
+	@ r2 = ARM_SMCCC_ARCH_WORKAROUND_1
+	mov	r0, #0
 	eret
 
 guest_trap:
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index df73914e81c8..746e7801dcdf 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -38,6 +38,7 @@ ENTRY(__get_user_1)
 	mov	r0, #0
 	ret	lr
 ENDPROC(__get_user_1)
+_ASM_NOKPROBE(__get_user_1)
 
 ENTRY(__get_user_2)
 	check_uaccess r0, 2, r1, r2, __get_user_bad
@@ -58,6 +59,7 @@ rb	.req	r0
 	mov	r0, #0
 	ret	lr
 ENDPROC(__get_user_2)
+_ASM_NOKPROBE(__get_user_2)
 
 ENTRY(__get_user_4)
 	check_uaccess r0, 4, r1, r2, __get_user_bad
@@ -65,6 +67,7 @@ ENTRY(__get_user_4)
 	mov	r0, #0
 	ret	lr
 ENDPROC(__get_user_4)
+_ASM_NOKPROBE(__get_user_4)
 
 ENTRY(__get_user_8)
 	check_uaccess r0, 8, r1, r2, __get_user_bad8
@@ -78,6 +81,7 @@ ENTRY(__get_user_8)
 	mov	r0, #0
 	ret	lr
 ENDPROC(__get_user_8)
+_ASM_NOKPROBE(__get_user_8)
 
 #ifdef __ARMEB__
 ENTRY(__get_user_32t_8)
@@ -91,6 +95,7 @@ ENTRY(__get_user_32t_8)
 	mov	r0, #0
 	ret	lr
 ENDPROC(__get_user_32t_8)
+_ASM_NOKPROBE(__get_user_32t_8)
 
 ENTRY(__get_user_64t_1)
 	check_uaccess r0, 1, r1, r2, __get_user_bad8
@@ -98,6 +103,7 @@ ENTRY(__get_user_64t_1)
 	mov	r0, #0
 	ret	lr
 ENDPROC(__get_user_64t_1)
+_ASM_NOKPROBE(__get_user_64t_1)
 
 ENTRY(__get_user_64t_2)
 	check_uaccess r0, 2, r1, r2, __get_user_bad8
@@ -114,6 +120,7 @@ rb	.req	r0
 	mov	r0, #0
 	ret	lr
 ENDPROC(__get_user_64t_2)
+_ASM_NOKPROBE(__get_user_64t_2)
 
 ENTRY(__get_user_64t_4)
 	check_uaccess r0, 4, r1, r2, __get_user_bad8
@@ -121,6 +128,7 @@ ENTRY(__get_user_64t_4)
 	mov	r0, #0
 	ret	lr
 ENDPROC(__get_user_64t_4)
+_ASM_NOKPROBE(__get_user_64t_4)
 #endif
 
 __get_user_bad8:
@@ -131,6 +139,8 @@ __get_user_bad:
 	ret	lr
 ENDPROC(__get_user_bad)
 ENDPROC(__get_user_bad8)
+_ASM_NOKPROBE(__get_user_bad)
+_ASM_NOKPROBE(__get_user_bad8)
 
 .pushsection __ex_table, "a"
 	.long	1b, __get_user_bad
diff --git a/arch/arm/mach-axxia/Kconfig b/arch/arm/mach-axxia/Kconfig
index bb2ce1c63fd9..d3eae6037913 100644
--- a/arch/arm/mach-axxia/Kconfig
+++ b/arch/arm/mach-axxia/Kconfig
@@ -2,7 +2,6 @@
 config ARCH_AXXIA
 	bool "LSI Axxia platforms"
 	depends on ARCH_MULTI_V7 && ARM_LPAE
-	select ARCH_DMA_ADDR_T_64BIT
 	select ARM_AMBA
 	select ARM_GIC
 	select ARM_TIMER_SP804
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index c2f3b0d216a4..c46a728df44e 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -211,7 +211,6 @@ config ARCH_BRCMSTB
 	select BRCMSTB_L2_IRQ
 	select BCM7120_L2_IRQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
-	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select ZONE_DMA if ARM_LPAE
 	select SOC_BRCMSTB
 	select SOC_BUS
diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index 004f9c8de032..d1e8ce7b4bd2 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -205,12 +205,17 @@ static const short da830_evm_mmc_sd_pins[] = {
 	-1
 };
 
+#define DA830_MMCSD_WP_PIN		GPIO_TO_PIN(2, 1)
+#define DA830_MMCSD_CD_PIN		GPIO_TO_PIN(2, 2)
+
 static struct gpiod_lookup_table mmc_gpios_table = {
 	.dev_id = "da830-mmc.0",
 	.table = {
 		/* gpio chip 1 contains gpio range 32-63 */
-		GPIO_LOOKUP("davinci_gpio.1", 2, "cd", GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP("davinci_gpio.1", 1, "wp", GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("davinci_gpio.0", DA830_MMCSD_CD_PIN, "cd",
+			    GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("davinci_gpio.0", DA830_MMCSD_WP_PIN, "wp",
+			    GPIO_ACTIVE_LOW),
 	},
 };
 
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index 3063478bcc36..158ed9a1483f 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -763,12 +763,17 @@ static const short da850_evm_mcasp_pins[] __initconst = {
 	-1
 };
 
+#define DA850_MMCSD_CD_PIN		GPIO_TO_PIN(4, 0)
+#define DA850_MMCSD_WP_PIN		GPIO_TO_PIN(4, 1)
+
 static struct gpiod_lookup_table mmc_gpios_table = {
 	.dev_id = "da830-mmc.0",
 	.table = {
 		/* gpio chip 2 contains gpio range 64-95 */
-		GPIO_LOOKUP("davinci_gpio.2", 0, "cd", GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP("davinci_gpio.2", 1, "wp", GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_CD_PIN, "cd",
+			    GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_WP_PIN, "wp",
+			    GPIO_ACTIVE_LOW),
 	},
 };
 
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index cb30637d9eaf..23ab9e8bc04c 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -19,6 +19,7 @@
 #include <linux/gpio.h>
 #include <linux/gpio/machine.h>
 #include <linux/clk.h>
+#include <linux/dm9000.h>
 #include <linux/videodev2.h>
 #include <media/i2c/tvp514x.h>
 #include <linux/spi/spi.h>
@@ -109,12 +110,15 @@ static struct platform_device davinci_nand_device = {
 	},
 };
 
+#define DM355_I2C_SDA_PIN	GPIO_TO_PIN(0, 15)
+#define DM355_I2C_SCL_PIN	GPIO_TO_PIN(0, 14)
+
 static struct gpiod_lookup_table i2c_recovery_gpiod_table = {
-	.dev_id = "i2c_davinci",
+	.dev_id = "i2c_davinci.1",
 	.table = {
-		GPIO_LOOKUP("davinci_gpio", 15, "sda",
+		GPIO_LOOKUP("davinci_gpio.0", DM355_I2C_SDA_PIN, "sda",
 			    GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
-		GPIO_LOOKUP("davinci_gpio", 14, "scl",
+		GPIO_LOOKUP("davinci_gpio.0", DM355_I2C_SCL_PIN, "scl",
 			    GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
 	},
 };
@@ -179,11 +183,16 @@ static struct resource dm355evm_dm9000_rsrc[] = {
 	},
 };
 
+static struct dm9000_plat_data dm335evm_dm9000_platdata;
+
 static struct platform_device dm355evm_dm9000 = {
 	.name		= "dm9000",
 	.id		= -1,
 	.resource	= dm355evm_dm9000_rsrc,
 	.num_resources	= ARRAY_SIZE(dm355evm_dm9000_rsrc),
+	.dev		= {
+		.platform_data = &dm335evm_dm9000_platdata,
+	},
 };
 
 static struct tvp514x_platform_data tvp5146_pdata = {
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 95b55aae1366..509e64ab1994 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -17,6 +17,7 @@
 #include <linux/i2c.h>
 #include <linux/platform_data/pcf857x.h>
 #include <linux/platform_data/at24.h>
+#include <linux/platform_data/gpio-davinci.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
@@ -596,12 +597,15 @@ static struct i2c_board_info __initdata i2c_info[] =  {
 	},
 };
 
+#define DM644X_I2C_SDA_PIN	GPIO_TO_PIN(2, 12)
+#define DM644X_I2C_SCL_PIN	GPIO_TO_PIN(2, 11)
+
 static struct gpiod_lookup_table i2c_recovery_gpiod_table = {
-	.dev_id = "i2c_davinci",
+	.dev_id = "i2c_davinci.1",
 	.table = {
-		GPIO_LOOKUP("davinci_gpio", 44, "sda",
+		GPIO_LOOKUP("davinci_gpio.0", DM644X_I2C_SDA_PIN, "sda",
 			    GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
-		GPIO_LOOKUP("davinci_gpio", 43, "scl",
+		GPIO_LOOKUP("davinci_gpio.0", DM644X_I2C_SCL_PIN, "scl",
 			    GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
 	},
 };
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index 2d37f5b0e1f5..a3c0d1e87647 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -532,11 +532,12 @@ static struct vpif_display_config dm646x_vpif_display_config = {
 	.set_clock	= set_vpif_clock,
 	.subdevinfo	= dm646x_vpif_subdev,
 	.subdev_count	= ARRAY_SIZE(dm646x_vpif_subdev),
+	.i2c_adapter_id = 1,
 	.chan_config[0] = {
 		.outputs = dm6467_ch0_outputs,
 		.output_count = ARRAY_SIZE(dm6467_ch0_outputs),
 	},
-	.card_name	= "DM646x EVM",
+	.card_name	= "DM646x EVM Video Display",
 };
 
 /**
@@ -674,6 +675,7 @@ static struct vpif_capture_config dm646x_vpif_capture_cfg = {
 	.setup_input_channel_mode = setup_vpif_input_channel_mode,
 	.subdev_info = vpif_capture_sdev_info,
 	.subdev_count = ARRAY_SIZE(vpif_capture_sdev_info),
+	.i2c_adapter_id = 1,
 	.chan_config[0] = {
 		.inputs = dm6467_ch0_inputs,
 		.input_count = ARRAY_SIZE(dm6467_ch0_inputs),
@@ -694,6 +696,7 @@ static struct vpif_capture_config dm646x_vpif_capture_cfg = {
 			.fid_pol = 0,
 		},
 	},
+	.card_name = "DM646x EVM Video Capture",
 };
 
 static void __init evm_init_video(void)
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index 0d32042b728f..be8b892a6ea7 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -123,12 +123,16 @@ static const short hawk_mmcsd0_pins[] = {
 	-1
 };
 
+#define DA850_HAWK_MMCSD_CD_PIN		GPIO_TO_PIN(3, 12)
+#define DA850_HAWK_MMCSD_WP_PIN		GPIO_TO_PIN(3, 13)
+
 static struct gpiod_lookup_table mmc_gpios_table = {
 	.dev_id = "da830-mmc.0",
 	.table = {
-		/* CD: gpio3_12: gpio60: chip 1 contains gpio range 32-63*/
-		GPIO_LOOKUP("davinci_gpio.0", 28, "cd", GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP("davinci_gpio.0", 29, "wp", GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("davinci_gpio.0", DA850_HAWK_MMCSD_CD_PIN, "cd",
+			    GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("davinci_gpio.0", DA850_HAWK_MMCSD_WP_PIN, "wp",
+			    GPIO_ACTIVE_LOW),
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index 109ab1fa0d2c..c32ca27ab343 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -488,7 +488,8 @@ static u8 dm646x_default_priorities[DAVINCI_N_AINTC_IRQ] = {
 	[IRQ_DM646X_MCASP0TXINT]        = 7,
 	[IRQ_DM646X_MCASP0RXINT]        = 7,
 	[IRQ_DM646X_RESERVED_3]         = 7,
-	[IRQ_DM646X_MCASP1TXINT]        = 7,    /* clockevent */
+	[IRQ_DM646X_MCASP1TXINT]        = 7,
+	[IRQ_TINT0_TINT12]              = 7,    /* clockevent */
 	[IRQ_TINT0_TINT34]              = 7,    /* clocksource */
 	[IRQ_TINT1_TINT12]              = 7,    /* DSP timer */
 	[IRQ_TINT1_TINT34]              = 7,    /* system tick */
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index e70feec6fad5..faf48a3b1fea 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -323,7 +323,7 @@ void __init ep93xx_register_eth(struct ep93xx_eth_data *data, int copy_addr)
 
 /* All EP93xx devices use the same two GPIO pins for I2C bit-banging */
 static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.0",
 	.table		= {
 		/* Use local offsets on gpiochip/port "G" */
 		GPIO_LOOKUP_IDX("G", 1, NULL, 0,
@@ -635,6 +635,7 @@ EXPORT_SYMBOL(ep93xx_keypad_release_gpio);
  *************************************************************************/
 static struct resource ep93xx_i2s_resource[] = {
 	DEFINE_RES_MEM(EP93XX_I2S_PHYS_BASE, 0x100),
+	DEFINE_RES_IRQ(IRQ_EP93XX_SAI),
 };
 
 static struct platform_device ep93xx_i2s_device = {
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 647c319f9f5f..2ca405816846 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -112,7 +112,6 @@ config SOC_EXYNOS5440
 	bool "SAMSUNG EXYNOS5440"
 	default y
 	depends on ARCH_EXYNOS5
-	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select HAVE_ARM_ARCH_TIMER
 	select AUTO_ZRELADDR
 	select PINCTRL_EXYNOS5440
diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig
index 81110ec34226..5552968f07f8 100644
--- a/arch/arm/mach-highbank/Kconfig
+++ b/arch/arm/mach-highbank/Kconfig
@@ -1,7 +1,6 @@
 config ARCH_HIGHBANK
 	bool "Calxeda ECX-1000/2000 (Highbank/Midway)"
 	depends on ARCH_MULTI_V7
-	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
diff --git a/arch/arm/mach-ixp4xx/avila-setup.c b/arch/arm/mach-ixp4xx/avila-setup.c
index 77def6169f50..44cbbce6bda6 100644
--- a/arch/arm/mach-ixp4xx/avila-setup.c
+++ b/arch/arm/mach-ixp4xx/avila-setup.c
@@ -51,7 +51,7 @@ static struct platform_device avila_flash = {
 };
 
 static struct gpiod_lookup_table avila_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.0",
 	.table		= {
 		GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", AVILA_SDA_PIN,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c
index 0f5c99941a7d..397190f3a8da 100644
--- a/arch/arm/mach-ixp4xx/dsmg600-setup.c
+++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c
@@ -70,7 +70,7 @@ static struct platform_device dsmg600_flash = {
 };
 
 static struct gpiod_lookup_table dsmg600_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.0",
 	.table		= {
 		GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", DSMG600_SDA_PIN,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/fsg-setup.c b/arch/arm/mach-ixp4xx/fsg-setup.c
index 033f79b35d51..f0a152e365b1 100644
--- a/arch/arm/mach-ixp4xx/fsg-setup.c
+++ b/arch/arm/mach-ixp4xx/fsg-setup.c
@@ -56,7 +56,7 @@ static struct platform_device fsg_flash = {
 };
 
 static struct gpiod_lookup_table fsg_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.0",
 	.table		= {
 		GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", FSG_SDA_PIN,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index b168e2fbdbeb..3ec829d52cdd 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -124,7 +124,7 @@ static struct platform_device ixdp425_flash_nand = {
 #endif	/* CONFIG_MTD_NAND_PLATFORM */
 
 static struct gpiod_lookup_table ixdp425_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.0",
 	.table		= {
 		GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", IXDP425_SDA_PIN,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
index 76dfff03cb71..4138d6aa4c52 100644
--- a/arch/arm/mach-ixp4xx/nas100d-setup.c
+++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
@@ -102,7 +102,7 @@ static struct platform_device nas100d_leds = {
 };
 
 static struct gpiod_lookup_table nas100d_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.0",
 	.table		= {
 		GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", NAS100D_SDA_PIN,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c
index 91da63a7d7b5..341b263482ef 100644
--- a/arch/arm/mach-ixp4xx/nslu2-setup.c
+++ b/arch/arm/mach-ixp4xx/nslu2-setup.c
@@ -70,7 +70,7 @@ static struct platform_device nslu2_flash = {
 };
 
 static struct gpiod_lookup_table nslu2_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.0",
 	.table		= {
 		GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", NSLU2_SDA_PIN,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-keystone/pm_domain.c b/arch/arm/mach-keystone/pm_domain.c
index fe57e2692629..abca83d22ff3 100644
--- a/arch/arm/mach-keystone/pm_domain.c
+++ b/arch/arm/mach-keystone/pm_domain.c
@@ -29,6 +29,7 @@ static struct dev_pm_domain keystone_pm_domain = {
 
 static struct pm_clk_notifier_block platform_domain_notifier = {
 	.pm_domain = &keystone_pm_domain,
+	.con_ids = { NULL },
 };
 
 static const struct of_device_id of_keystone_table[] = {
diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c
index 793a24a53c52..d7ca9e2b40d2 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq.c
+++ b/arch/arm/mach-omap1/ams-delta-fiq.c
@@ -58,22 +58,24 @@ static irqreturn_t deferred_fiq(int irq, void *dev_id)
 		irq_num = gpio_to_irq(gpio);
 		fiq_count = fiq_buffer[FIQ_CNT_INT_00 + gpio];
 
-		while (irq_counter[gpio] < fiq_count) {
-			if (gpio != AMS_DELTA_GPIO_PIN_KEYBRD_CLK) {
-				struct irq_data *d = irq_get_irq_data(irq_num);
-
-				/*
-				 * It looks like handle_edge_irq() that
-				 * OMAP GPIO edge interrupts default to,
-				 * expects interrupt already unmasked.
-				 */
-				if (irq_chip && irq_chip->irq_unmask)
+		if (irq_counter[gpio] < fiq_count &&
+				gpio != AMS_DELTA_GPIO_PIN_KEYBRD_CLK) {
+			struct irq_data *d = irq_get_irq_data(irq_num);
+
+			/*
+			 * handle_simple_irq() that OMAP GPIO edge
+			 * interrupts default to since commit 80ac93c27441
+			 * requires interrupt already acked and unmasked.
+			 */
+			if (irq_chip) {
+				if (irq_chip->irq_ack)
+					irq_chip->irq_ack(d);
+				if (irq_chip->irq_unmask)
 					irq_chip->irq_unmask(d);
 			}
-			generic_handle_irq(irq_num);
-
-			irq_counter[gpio]++;
 		}
+		for (; irq_counter[gpio] < fiq_count; irq_counter[gpio]++)
+			generic_handle_irq(irq_num);
 	}
 	return IRQ_HANDLED;
 }
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 4603c30fef73..0d9ce58bc464 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -243,8 +243,4 @@ arch/arm/mach-omap2/pm-asm-offsets.s: arch/arm/mach-omap2/pm-asm-offsets.c
 include/generated/ti-pm-asm-offsets.h: arch/arm/mach-omap2/pm-asm-offsets.s FORCE
 	$(call filechk,offsets,__TI_PM_ASM_OFFSETS_H__)
 
-# For rule to generate ti-emif-asm-offsets.h dependency
-include drivers/memory/Makefile.asm-offsets
-
-arch/arm/mach-omap2/sleep33xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h
-arch/arm/mach-omap2/sleep43xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h
+$(obj)/sleep33xx.o $(obj)/sleep43xx.o: include/generated/ti-pm-asm-offsets.h
diff --git a/arch/arm/mach-omap2/pm-asm-offsets.c b/arch/arm/mach-omap2/pm-asm-offsets.c
index 6d4392da7c11..b9846b19e5e2 100644
--- a/arch/arm/mach-omap2/pm-asm-offsets.c
+++ b/arch/arm/mach-omap2/pm-asm-offsets.c
@@ -7,9 +7,12 @@
 
 #include <linux/kbuild.h>
 #include <linux/platform_data/pm33xx.h>
+#include <linux/ti-emif-sram.h>
 
 int main(void)
 {
+	ti_emif_asm_offsets();
+
 	DEFINE(AMX3_PM_WFI_FLAGS_OFFSET,
 	       offsetof(struct am33xx_pm_sram_data, wfi_flags));
 	DEFINE(AMX3_PM_L2_AUX_CTRL_VAL_OFFSET,
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 76eb6ec5f157..1e6a967cd2d5 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -188,7 +188,7 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag)
 				       ((prev & OMAP_POWERSTATE_MASK) << 0));
 			trace_power_domain_target_rcuidle(pwrdm->name,
 							  trace_state,
-							  smp_processor_id());
+							  raw_smp_processor_id());
 		}
 		break;
 	default:
@@ -518,7 +518,7 @@ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst)
 	if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) {
 		/* Trace the pwrdm desired target state */
 		trace_power_domain_target_rcuidle(pwrdm->name, pwrst,
-						  smp_processor_id());
+						  raw_smp_processor_id());
 		/* Program the pwrdm desired target state */
 		ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst);
 	}
diff --git a/arch/arm/mach-omap2/sleep33xx.S b/arch/arm/mach-omap2/sleep33xx.S
index 218d79930b04..322b3bb868b4 100644
--- a/arch/arm/mach-omap2/sleep33xx.S
+++ b/arch/arm/mach-omap2/sleep33xx.S
@@ -6,7 +6,6 @@
  *	Dave Gerlach, Vaibhav Bedia
  */
 
-#include <generated/ti-emif-asm-offsets.h>
 #include <generated/ti-pm-asm-offsets.h>
 #include <linux/linkage.h>
 #include <linux/ti-emif-sram.h>
diff --git a/arch/arm/mach-omap2/sleep43xx.S b/arch/arm/mach-omap2/sleep43xx.S
index b24be624e8b9..8903814a6677 100644
--- a/arch/arm/mach-omap2/sleep43xx.S
+++ b/arch/arm/mach-omap2/sleep43xx.S
@@ -6,7 +6,6 @@
  *	Dave Gerlach, Vaibhav Bedia
  */
 
-#include <generated/ti-emif-asm-offsets.h>
 #include <generated/ti-pm-asm-offsets.h>
 #include <linux/linkage.h>
 #include <linux/ti-emif-sram.h>
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index 5877e547cecd..0adb1bd6208e 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -322,7 +322,7 @@ static struct soc_camera_link palmz72_iclink = {
 };
 
 static struct gpiod_lookup_table palmz72_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.0",
 	.table		= {
 		GPIO_LOOKUP_IDX("gpio-pxa", 118, NULL, 0,
 				GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 90d0f277de55..207dcc2e94e7 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -460,7 +460,7 @@ static struct platform_device smc91x_device = {
 
 /* i2c */
 static struct gpiod_lookup_table viper_i2c_gpiod_table = {
-	.dev_id		= "i2c-gpio",
+	.dev_id		= "i2c-gpio.1",
 	.table		= {
 		GPIO_LOOKUP_IDX("gpio-pxa", VIPER_RTC_I2C_SDA_GPIO,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
@@ -789,7 +789,7 @@ static int __init viper_tpm_setup(char *str)
 __setup("tpm=", viper_tpm_setup);
 
 struct gpiod_lookup_table viper_tpm_i2c_gpiod_table = {
-	.dev_id = "i2c-gpio",
+	.dev_id = "i2c-gpio.2",
 	.table = {
 		GPIO_LOOKUP_IDX("gpio-pxa", VIPER_TPM_I2C_SDA_GPIO,
 				NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-rockchip/Kconfig b/arch/arm/mach-rockchip/Kconfig
index a4065966881a..fafd3d7f9f8c 100644
--- a/arch/arm/mach-rockchip/Kconfig
+++ b/arch/arm/mach-rockchip/Kconfig
@@ -3,7 +3,6 @@ config ARCH_ROCKCHIP
 	depends on ARCH_MULTI_V7
 	select PINCTRL
 	select PINCTRL_ROCKCHIP
-	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_AMBA
 	select ARM_GIC
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index bdb5ec1cf560..39aef4876ed4 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -657,25 +657,13 @@ static int ecard_devices_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ecard_devices_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ecard_devices_proc_show, NULL);
-}
-
-static const struct file_operations bus_ecard_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ecard_devices_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static struct proc_dir_entry *proc_bus_ecard_dir = NULL;
 
 static void ecard_proc_init(void)
 {
 	proc_bus_ecard_dir = proc_mkdir("bus/ecard", NULL);
-	proc_create("devices", 0, proc_bus_ecard_dir, &bus_ecard_proc_fops);
+	proc_create_single("devices", 0, proc_bus_ecard_dir,
+			ecard_devices_proc_show);
 }
 
 #define ec_set_resource(ec,nr,st,sz)				\
diff --git a/arch/arm/mach-s3c24xx/mach-jive.c b/arch/arm/mach-s3c24xx/mach-jive.c
index 59589a4a0d4b..885e8f12e4b9 100644
--- a/arch/arm/mach-s3c24xx/mach-jive.c
+++ b/arch/arm/mach-s3c24xx/mach-jive.c
@@ -427,9 +427,9 @@ static struct gpiod_lookup_table jive_wm8750_gpiod_table = {
 	.dev_id         = "spi_gpio",
 	.table          = {
 		GPIO_LOOKUP("GPIOB", 4,
-			    "gpio-sck", GPIO_ACTIVE_HIGH),
+			    "sck", GPIO_ACTIVE_HIGH),
 		GPIO_LOOKUP("GPIOB", 9,
-			    "gpio-mosi", GPIO_ACTIVE_HIGH),
+			    "mosi", GPIO_ACTIVE_HIGH),
 		GPIO_LOOKUP("GPIOH", 10,
 			    "cs", GPIO_ACTIVE_HIGH),
 		{ },
diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
index ace010479eb6..f45aed2519ba 100644
--- a/arch/arm/mach-sa1100/simpad.c
+++ b/arch/arm/mach-sa1100/simpad.c
@@ -327,7 +327,7 @@ static struct platform_device simpad_gpio_leds = {
  * i2c
  */
 static struct gpiod_lookup_table simpad_i2c_gpiod_table = {
-	.dev_id = "i2c-gpio",
+	.dev_id = "i2c-gpio.0",
 	.table = {
 		GPIO_LOOKUP_IDX("gpio", 21, NULL, 0,
 				GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 280e7312a9e1..fe60cd09a5ca 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -29,7 +29,6 @@ config ARCH_RMOBILE
 menuconfig ARCH_RENESAS
 	bool "Renesas ARM SoCs"
 	depends on ARCH_MULTI_V7 && MMU
-	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select ARCH_SHMOBILE
 	select ARM_GIC
 	select GPIOLIB
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index 1e0aeb47bac6..7f3b83e0d324 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -15,6 +15,5 @@ menuconfig ARCH_TEGRA
 	select RESET_CONTROLLER
 	select SOC_BUS
 	select ZONE_DMA if ARM_LPAE
-	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	help
 	  This enables support for NVIDIA Tegra based systems.
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 7f14acf67caf..96a7b6cf459b 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -415,6 +415,7 @@ config CPU_V7
 	select CPU_CP15_MPU if !MMU
 	select CPU_HAS_ASID if MMU
 	select CPU_PABRT_V7
+	select CPU_SPECTRE if MMU
 	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V7 if MMU
 
@@ -661,6 +662,7 @@ config ARM_LPAE
 	bool "Support for the Large Physical Address Extension"
 	depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \
 		!CPU_32v4 && !CPU_32v3
+	select PHYS_ADDR_T_64BIT
 	help
 	  Say Y if you have an ARMv7 processor supporting the LPAE page
 	  table format and you would like to access memory beyond the
@@ -673,12 +675,6 @@ config ARM_PV_FIXUP
 	def_bool y
 	depends on ARM_LPAE && ARM_PATCH_PHYS_VIRT && ARCH_KEYSTONE
 
-config ARCH_PHYS_ADDR_T_64BIT
-	def_bool ARM_LPAE
-
-config ARCH_DMA_ADDR_T_64BIT
-	bool
-
 config ARM_THUMB
 	bool "Support Thumb user binaries" if !CPU_THUMBONLY && EXPERT
 	depends on CPU_THUMB_CAPABLE
@@ -826,6 +822,28 @@ config CPU_BPREDICT_DISABLE
 	help
 	  Say Y here to disable branch prediction.  If unsure, say N.
 
+config CPU_SPECTRE
+	bool
+
+config HARDEN_BRANCH_PREDICTOR
+	bool "Harden the branch predictor against aliasing attacks" if EXPERT
+	depends on CPU_SPECTRE
+	default y
+	help
+	   Speculation attacks against some high-performance processors rely
+	   on being able to manipulate the branch predictor for a victim
+	   context by executing aliasing branches in the attacker context.
+	   Such attacks can be partially mitigated against by clearing
+	   internal branch predictor state and limiting the prediction
+	   logic in some situations.
+
+	   This config option will take CPU-specific actions to harden
+	   the branch predictor against aliasing attacks and may rely on
+	   specific instruction sequences or control bits being set by
+	   the system firmware.
+
+	   If unsure, say Y.
+
 config TLS_REG_EMUL
 	bool
 	select NEED_KUSER_HELPERS
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 9dbb84923e12..7cb1699fbfc4 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_MMU)		+= fault-armv.o flush.o idmap.o ioremap.o \
 
 ifneq ($(CONFIG_MMU),y)
 obj-y				+= nommu.o
-obj-$(CONFIG_ARM_MPU)		+= pmsa-v7.o
+obj-$(CONFIG_ARM_MPU)		+= pmsa-v7.o pmsa-v8.o
 endif
 
 obj-$(CONFIG_ARM_PTDUMP_CORE)	+= dump.o
@@ -97,7 +97,7 @@ obj-$(CONFIG_CPU_MOHAWK)	+= proc-mohawk.o
 obj-$(CONFIG_CPU_FEROCEON)	+= proc-feroceon.o
 obj-$(CONFIG_CPU_V6)		+= proc-v6.o
 obj-$(CONFIG_CPU_V6K)		+= proc-v6.o
-obj-$(CONFIG_CPU_V7)		+= proc-v7.o
+obj-$(CONFIG_CPU_V7)		+= proc-v7.o proc-v7-bugs.o
 obj-$(CONFIG_CPU_V7M)		+= proc-v7m.o
 
 AFLAGS_proc-v6.o	:=-Wa,-march=armv6
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 2c96190e018b..bd2c739d8083 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -950,6 +950,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (ai_usermode & UM_SIGNAL) {
 		siginfo_t si;
 
+		clear_siginfo(&si);
 		si.si_signo = SIGBUS;
 		si.si_errno = 0;
 		si.si_code = BUS_ADRALN;
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 619f24a42d09..f448a0663b10 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -241,12 +241,3 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 void arch_teardown_dma_ops(struct device *dev)
 {
 }
-
-#define PREALLOC_DMA_DEBUG_ENTRIES	4096
-
-static int __init dma_debug_do_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-	return 0;
-}
-core_initcall(dma_debug_do_init);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 8c398fedbbb6..af27f1c22d93 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -466,12 +466,6 @@ void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
 void __init dma_contiguous_remap(void)
 {
 	int i;
-
-	if (!dma_mmu_remap_num)
-		return;
-
-	/* call flush_cache_all() since CMA area would be large enough */
-	flush_cache_all();
 	for (i = 0; i < dma_mmu_remap_num; i++) {
 		phys_addr_t start = dma_mmu_remap[i].base;
 		phys_addr_t end = start + dma_mmu_remap[i].size;
@@ -504,15 +498,7 @@ void __init dma_contiguous_remap(void)
 		flush_tlb_kernel_range(__phys_to_virt(start),
 				       __phys_to_virt(end));
 
-		/*
-		 * All the memory in CMA region will be on ZONE_MOVABLE.
-		 * If that zone is considered as highmem, the memory in CMA
-		 * region is also considered as highmem even if it's
-		 * physical address belong to lowmem. In this case,
-		 * re-mapping isn't required.
-		 */
-		if (!is_highmem_idx(ZONE_MOVABLE))
-			iotable_init(&map, 1);
+		iotable_init(&map, 1);
 	}
 }
 
@@ -845,7 +831,7 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		 unsigned long attrs)
 {
 	int ret;
-	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long nr_vma_pages = vma_pages(vma);
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long pfn = dma_to_pfn(dev, dma_addr);
 	unsigned long off = vma->vm_pgoff;
@@ -1165,15 +1151,6 @@ int arm_dma_supported(struct device *dev, u64 mask)
 	return __dma_supported(dev, mask, false);
 }
 
-#define PREALLOC_DMA_DEBUG_ENTRIES	4096
-
-static int __init dma_debug_do_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-	return 0;
-}
-core_initcall(dma_debug_do_init);
-
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 
 static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index b75eada23d0a..84becc911ee3 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -163,6 +163,11 @@ __do_user_fault(struct task_struct *tsk, unsigned long addr,
 {
 	struct siginfo si;
 
+	if (addr > TASK_SIZE)
+		harden_branch_predictor();
+
+	clear_siginfo(&si);
+
 #ifdef CONFIG_DEBUG_USER
 	if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
 	    ((user_debug & UDBG_BUS)  && (sig == SIGBUS))) {
@@ -557,6 +562,7 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		inf->name, fsr, addr);
 	show_pte(current->mm, addr);
 
+	clear_siginfo(&info);
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code  = inf->code;
@@ -589,6 +595,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 	pr_alert("Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
 		inf->name, ifsr, addr);
 
+	clear_siginfo(&info);
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code  = inf->code;
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 7c087961b7ce..5dd6c58d653b 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -99,6 +99,38 @@ void __init arm_mm_memblock_reserve(void)
 	memblock_reserve(0, 1);
 }
 
+static void __init adjust_lowmem_bounds_mpu(void)
+{
+	unsigned long pmsa = read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA;
+
+	switch (pmsa) {
+	case MMFR0_PMSAv7:
+		pmsav7_adjust_lowmem_bounds();
+		break;
+	case MMFR0_PMSAv8:
+		pmsav8_adjust_lowmem_bounds();
+		break;
+	default:
+		break;
+	}
+}
+
+static void __init mpu_setup(void)
+{
+	unsigned long pmsa = read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA;
+
+	switch (pmsa) {
+	case MMFR0_PMSAv7:
+		pmsav7_setup();
+		break;
+	case MMFR0_PMSAv8:
+		pmsav8_setup();
+		break;
+	default:
+		break;
+	}
+}
+
 void __init adjust_lowmem_bounds(void)
 {
 	phys_addr_t end;
diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
index e2853bfff74e..699fa2e88725 100644
--- a/arch/arm/mm/pmsa-v7.c
+++ b/arch/arm/mm/pmsa-v7.c
@@ -102,7 +102,7 @@ static inline u32 irbar_read(void)
 
 static inline void rgnr_write(u32 v)
 {
-	writel_relaxed(v, BASEADDR_V7M_SCB + MPU_RNR);
+	writel_relaxed(v, BASEADDR_V7M_SCB + PMSAv7_RNR);
 }
 
 /* Data-side / unified region attributes */
@@ -110,28 +110,28 @@ static inline void rgnr_write(u32 v)
 /* Region access control register */
 static inline void dracr_write(u32 v)
 {
-	u32 rsr = readl_relaxed(BASEADDR_V7M_SCB + MPU_RASR) & GENMASK(15, 0);
+	u32 rsr = readl_relaxed(BASEADDR_V7M_SCB + PMSAv7_RASR) & GENMASK(15, 0);
 
-	writel_relaxed((v << 16) | rsr, BASEADDR_V7M_SCB + MPU_RASR);
+	writel_relaxed((v << 16) | rsr, BASEADDR_V7M_SCB + PMSAv7_RASR);
 }
 
 /* Region size register */
 static inline void drsr_write(u32 v)
 {
-	u32 racr = readl_relaxed(BASEADDR_V7M_SCB + MPU_RASR) & GENMASK(31, 16);
+	u32 racr = readl_relaxed(BASEADDR_V7M_SCB + PMSAv7_RASR) & GENMASK(31, 16);
 
-	writel_relaxed(v | racr, BASEADDR_V7M_SCB + MPU_RASR);
+	writel_relaxed(v | racr, BASEADDR_V7M_SCB + PMSAv7_RASR);
 }
 
 /* Region base address register */
 static inline void drbar_write(u32 v)
 {
-	writel_relaxed(v, BASEADDR_V7M_SCB + MPU_RBAR);
+	writel_relaxed(v, BASEADDR_V7M_SCB + PMSAv7_RBAR);
 }
 
 static inline u32 drbar_read(void)
 {
-	return readl_relaxed(BASEADDR_V7M_SCB + MPU_RBAR);
+	return readl_relaxed(BASEADDR_V7M_SCB + PMSAv7_RBAR);
 }
 
 /* ARMv7-M only supports a unified MPU, so I-side operations are nop */
@@ -143,11 +143,6 @@ static inline unsigned long irbar_read(void) {return 0;}
 
 #endif
 
-static int __init mpu_present(void)
-{
-	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
-}
-
 static bool __init try_split_region(phys_addr_t base, phys_addr_t size, struct region *region)
 {
 	unsigned long  subreg, bslots, sslots;
@@ -161,7 +156,7 @@ static bool __init try_split_region(phys_addr_t base, phys_addr_t size, struct r
 
 	bdiff = base - abase;
 	sdiff = p2size - asize;
-	subreg = p2size / MPU_NR_SUBREGS;
+	subreg = p2size / PMSAv7_NR_SUBREGS;
 
 	if ((bdiff % subreg) || (sdiff % subreg))
 		return false;
@@ -172,17 +167,17 @@ static bool __init try_split_region(phys_addr_t base, phys_addr_t size, struct r
 	if (bslots || sslots) {
 		int i;
 
-		if (subreg < MPU_MIN_SUBREG_SIZE)
+		if (subreg < PMSAv7_MIN_SUBREG_SIZE)
 			return false;
 
-		if (bslots + sslots > MPU_NR_SUBREGS)
+		if (bslots + sslots > PMSAv7_NR_SUBREGS)
 			return false;
 
 		for (i = 0; i < bslots; i++)
 			_set_bit(i, &region->subreg);
 
 		for (i = 1; i <= sslots; i++)
-			_set_bit(MPU_NR_SUBREGS - i, &region->subreg);
+			_set_bit(PMSAv7_NR_SUBREGS - i, &region->subreg);
 	}
 
 	region->base = abase;
@@ -233,7 +228,7 @@ static int __init allocate_region(phys_addr_t base, phys_addr_t size,
 }
 
 /* MPU initialisation functions */
-void __init adjust_lowmem_bounds_mpu(void)
+void __init pmsav7_adjust_lowmem_bounds(void)
 {
 	phys_addr_t  specified_mem_size = 0, total_mem_size = 0;
 	struct memblock_region *reg;
@@ -243,10 +238,7 @@ void __init adjust_lowmem_bounds_mpu(void)
 	unsigned int mem_max_regions;
 	int num, i;
 
-	if (!mpu_present())
-		return;
-
-	/* Free-up MPU_PROBE_REGION */
+	/* Free-up PMSAv7_PROBE_REGION */
 	mpu_min_region_order = __mpu_min_region_order();
 
 	/* How many regions are supported */
@@ -301,12 +293,12 @@ void __init adjust_lowmem_bounds_mpu(void)
 	num = allocate_region(mem_start, specified_mem_size, mem_max_regions, mem);
 
 	for (i = 0; i < num; i++) {
-		unsigned long  subreg = mem[i].size / MPU_NR_SUBREGS;
+		unsigned long  subreg = mem[i].size / PMSAv7_NR_SUBREGS;
 
 		total_mem_size += mem[i].size - subreg * hweight_long(mem[i].subreg);
 
 		pr_debug("MPU: base %pa size %pa disable subregions: %*pbl\n",
-			 &mem[i].base, &mem[i].size, MPU_NR_SUBREGS, &mem[i].subreg);
+			 &mem[i].base, &mem[i].size, PMSAv7_NR_SUBREGS, &mem[i].subreg);
 	}
 
 	if (total_mem_size != specified_mem_size) {
@@ -349,7 +341,7 @@ static int __init __mpu_min_region_order(void)
 	u32 drbar_result, irbar_result;
 
 	/* We've kept a region free for this probing */
-	rgnr_write(MPU_PROBE_REGION);
+	rgnr_write(PMSAv7_PROBE_REGION);
 	isb();
 	/*
 	 * As per ARM ARM, write 0xFFFFFFFC to DRBAR to find the minimum
@@ -388,8 +380,8 @@ static int __init mpu_setup_region(unsigned int number, phys_addr_t start,
 		return -ENOMEM;
 
 	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
-	size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
-	size_data |= subregions << MPU_RSR_SD;
+	size_data = ((size_order - 1) << PMSAv7_RSR_SZ) | 1 << PMSAv7_RSR_EN;
+	size_data |= subregions << PMSAv7_RSR_SD;
 
 	if (need_flush)
 		flush_cache_all();
@@ -424,18 +416,15 @@ static int __init mpu_setup_region(unsigned int number, phys_addr_t start,
 /*
 * Set up default MPU regions, doing nothing if there is no MPU
 */
-void __init mpu_setup(void)
+void __init pmsav7_setup(void)
 {
 	int i, region = 0, err = 0;
 
-	if (!mpu_present())
-		return;
-
 	/* Setup MPU (order is important) */
 
 	/* Background */
 	err |= mpu_setup_region(region++, 0, 32,
-				MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0RW,
+				PMSAv7_ACR_XN | PMSAv7_RGN_STRONGLY_ORDERED | PMSAv7_AP_PL1RW_PL0RW,
 				0, false);
 
 #ifdef CONFIG_XIP_KERNEL
@@ -448,13 +437,13 @@ void __init mpu_setup(void)
                  * with BG region (which is uncachable), thus we need
                  * to clean and invalidate cache.
 		 */
-		bool need_flush = region == MPU_RAM_REGION;
+		bool need_flush = region == PMSAv7_RAM_REGION;
 
 		if (!xip[i].size)
 			continue;
 
 		err |= mpu_setup_region(region++, xip[i].base, ilog2(xip[i].size),
-					MPU_AP_PL1RO_PL0NA | MPU_RGN_NORMAL,
+					PMSAv7_AP_PL1RO_PL0NA | PMSAv7_RGN_NORMAL,
 					xip[i].subreg, need_flush);
 	}
 #endif
@@ -465,14 +454,14 @@ void __init mpu_setup(void)
 			continue;
 
 		err |= mpu_setup_region(region++, mem[i].base, ilog2(mem[i].size),
-					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL,
+					PMSAv7_AP_PL1RW_PL0RW | PMSAv7_RGN_NORMAL,
 					mem[i].subreg, false);
 	}
 
 	/* Vectors */
 #ifndef CONFIG_CPU_V7M
 	err |= mpu_setup_region(region++, vectors_base, ilog2(2 * PAGE_SIZE),
-				MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL,
+				PMSAv7_AP_PL1RW_PL0NA | PMSAv7_RGN_NORMAL,
 				0, false);
 #endif
 	if (err) {
diff --git a/arch/arm/mm/pmsa-v8.c b/arch/arm/mm/pmsa-v8.c
new file mode 100644
index 000000000000..617a83def88a
--- /dev/null
+++ b/arch/arm/mm/pmsa-v8.c
@@ -0,0 +1,307 @@
+/*
+ * Based on linux/arch/arm/pmsa-v7.c
+ *
+ * ARM PMSAv8 supporting functions.
+ */
+
+#include <linux/memblock.h>
+#include <linux/range.h>
+
+#include <asm/cp15.h>
+#include <asm/cputype.h>
+#include <asm/mpu.h>
+
+#include <asm/memory.h>
+#include <asm/sections.h>
+
+#include "mm.h"
+
+#ifndef CONFIG_CPU_V7M
+
+#define PRSEL	__ACCESS_CP15(c6, 0, c2, 1)
+#define PRBAR	__ACCESS_CP15(c6, 0, c3, 0)
+#define PRLAR	__ACCESS_CP15(c6, 0, c3, 1)
+
+static inline u32 prlar_read(void)
+{
+	return read_sysreg(PRLAR);
+}
+
+static inline u32 prbar_read(void)
+{
+	return read_sysreg(PRBAR);
+}
+
+static inline void prsel_write(u32 v)
+{
+	write_sysreg(v, PRSEL);
+}
+
+static inline void prbar_write(u32 v)
+{
+	write_sysreg(v, PRBAR);
+}
+
+static inline void prlar_write(u32 v)
+{
+	write_sysreg(v, PRLAR);
+}
+#else
+
+static inline u32 prlar_read(void)
+{
+	return readl_relaxed(BASEADDR_V7M_SCB + PMSAv8_RLAR);
+}
+
+static inline u32 prbar_read(void)
+{
+	return readl_relaxed(BASEADDR_V7M_SCB + PMSAv8_RBAR);
+}
+
+static inline void prsel_write(u32 v)
+{
+	writel_relaxed(v, BASEADDR_V7M_SCB + PMSAv8_RNR);
+}
+
+static inline void prbar_write(u32 v)
+{
+	writel_relaxed(v, BASEADDR_V7M_SCB + PMSAv8_RBAR);
+}
+
+static inline void prlar_write(u32 v)
+{
+	writel_relaxed(v, BASEADDR_V7M_SCB + PMSAv8_RLAR);
+}
+
+#endif
+
+static struct range __initdata io[MPU_MAX_REGIONS];
+static struct range __initdata mem[MPU_MAX_REGIONS];
+
+static unsigned int __initdata mpu_max_regions;
+
+static __init bool is_region_fixed(int number)
+{
+	switch (number) {
+	case PMSAv8_XIP_REGION:
+	case PMSAv8_KERNEL_REGION:
+		return true;
+	default:
+		return false;
+	}
+}
+
+void __init pmsav8_adjust_lowmem_bounds(void)
+{
+	phys_addr_t mem_end;
+	struct memblock_region *reg;
+	bool first = true;
+
+	for_each_memblock(memory, reg) {
+		if (first) {
+			phys_addr_t phys_offset = PHYS_OFFSET;
+
+			/*
+			 * Initially only use memory continuous from
+			 * PHYS_OFFSET */
+			if (reg->base != phys_offset)
+				panic("First memory bank must be contiguous from PHYS_OFFSET");
+			mem_end = reg->base + reg->size;
+			first = false;
+		} else {
+			/*
+			 * memblock auto merges contiguous blocks, remove
+			 * all blocks afterwards in one go (we can't remove
+			 * blocks separately while iterating)
+			 */
+			pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
+				  &mem_end, &reg->base);
+			memblock_remove(reg->base, 0 - reg->base);
+			break;
+		}
+	}
+}
+
+static int __init __mpu_max_regions(void)
+{
+	static int max_regions;
+	u32 mpuir;
+
+	if (max_regions)
+		return max_regions;
+
+	mpuir = read_cpuid_mputype();
+
+	max_regions  = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
+
+	return max_regions;
+}
+
+static int __init __pmsav8_setup_region(unsigned int number, u32 bar, u32 lar)
+{
+	if (number > mpu_max_regions
+	    || number >= MPU_MAX_REGIONS)
+		return -ENOENT;
+
+	dsb();
+	prsel_write(number);
+	isb();
+	prbar_write(bar);
+	prlar_write(lar);
+
+	mpu_rgn_info.rgns[number].prbar = bar;
+	mpu_rgn_info.rgns[number].prlar = lar;
+
+	mpu_rgn_info.used++;
+
+	return 0;
+}
+
+static int __init pmsav8_setup_ram(unsigned int number, phys_addr_t start,phys_addr_t end)
+{
+	u32 bar, lar;
+
+	if (is_region_fixed(number))
+		return -EINVAL;
+
+	bar = start;
+	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);;
+
+	bar |= PMSAv8_AP_PL1RW_PL0RW | PMSAv8_RGN_SHARED;
+	lar |= PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN;
+
+	return __pmsav8_setup_region(number, bar, lar);
+}
+
+static int __init pmsav8_setup_io(unsigned int number, phys_addr_t start,phys_addr_t end)
+{
+	u32 bar, lar;
+
+	if (is_region_fixed(number))
+		return -EINVAL;
+
+	bar = start;
+	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);;
+
+	bar |= PMSAv8_AP_PL1RW_PL0RW | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN;
+	lar |= PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN;
+
+	return __pmsav8_setup_region(number, bar, lar);
+}
+
+static int __init pmsav8_setup_fixed(unsigned int number, phys_addr_t start,phys_addr_t end)
+{
+	u32 bar, lar;
+
+	if (!is_region_fixed(number))
+		return -EINVAL;
+
+	bar = start;
+	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);
+
+	bar |= PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED;
+	lar |= PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN;
+
+	prsel_write(number);
+	isb();
+
+	if (prbar_read() != bar || prlar_read() != lar)
+		return -EINVAL;
+
+	/* Reserved region was set up early, we just need a record for secondaries */
+	mpu_rgn_info.rgns[number].prbar = bar;
+	mpu_rgn_info.rgns[number].prlar = lar;
+
+	mpu_rgn_info.used++;
+
+	return 0;
+}
+
+#ifndef CONFIG_CPU_V7M
+static int __init pmsav8_setup_vector(unsigned int number, phys_addr_t start,phys_addr_t end)
+{
+	u32 bar, lar;
+
+	if (number == PMSAv8_KERNEL_REGION)
+		return -EINVAL;
+
+	bar = start;
+	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);
+
+	bar |= PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED;
+	lar |= PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN;
+
+	return __pmsav8_setup_region(number, bar, lar);
+}
+#endif
+
+void __init pmsav8_setup(void)
+{
+	int i, err = 0;
+	int region = PMSAv8_KERNEL_REGION;
+
+	/* How many regions are supported ? */
+	mpu_max_regions = __mpu_max_regions();
+
+	/* RAM: single chunk of memory */
+	add_range(mem,  ARRAY_SIZE(mem), 0,  memblock.memory.regions[0].base,
+		  memblock.memory.regions[0].base + memblock.memory.regions[0].size);
+
+	/* IO: cover full 4G range */
+	add_range(io, ARRAY_SIZE(io), 0, 0, 0xffffffff);
+
+	/* RAM and IO: exclude kernel */
+	subtract_range(mem, ARRAY_SIZE(mem), __pa(KERNEL_START), __pa(KERNEL_END));
+	subtract_range(io, ARRAY_SIZE(io),  __pa(KERNEL_START), __pa(KERNEL_END));
+
+#ifdef CONFIG_XIP_KERNEL
+	/* RAM and IO: exclude xip */
+	subtract_range(mem, ARRAY_SIZE(mem), CONFIG_XIP_PHYS_ADDR, __pa(_exiprom));
+	subtract_range(io, ARRAY_SIZE(io), CONFIG_XIP_PHYS_ADDR, __pa(_exiprom));
+#endif
+
+#ifndef CONFIG_CPU_V7M
+	/* RAM and IO: exclude vectors */
+	subtract_range(mem, ARRAY_SIZE(mem),  vectors_base, vectors_base + 2 * PAGE_SIZE);
+	subtract_range(io, ARRAY_SIZE(io),  vectors_base, vectors_base + 2 * PAGE_SIZE);
+#endif
+	/* IO: exclude RAM */
+	for (i = 0; i < ARRAY_SIZE(mem); i++)
+		subtract_range(io, ARRAY_SIZE(io), mem[i].start, mem[i].end);
+
+	/* Now program MPU */
+
+#ifdef CONFIG_XIP_KERNEL
+	/* ROM */
+	err |= pmsav8_setup_fixed(PMSAv8_XIP_REGION, CONFIG_XIP_PHYS_ADDR, __pa(_exiprom));
+#endif
+	/* Kernel */
+	err |= pmsav8_setup_fixed(region++, __pa(KERNEL_START), __pa(KERNEL_END));
+
+
+	/* IO */
+	for (i = 0; i < ARRAY_SIZE(io); i++) {
+		if (!io[i].end)
+			continue;
+
+		err |= pmsav8_setup_io(region++, io[i].start, io[i].end);
+	}
+
+	/* RAM */
+	for (i = 0; i < ARRAY_SIZE(mem); i++) {
+		if (!mem[i].end)
+			continue;
+
+		err |= pmsav8_setup_ram(region++, mem[i].start, mem[i].end);
+	}
+
+	/* Vectors */
+#ifndef CONFIG_CPU_V7M
+	err |= pmsav8_setup_vector(region++, vectors_base, vectors_base + 2 * PAGE_SIZE);
+#endif
+	if (err)
+		pr_warn("MPU region initialization failure! %d", err);
+	else
+		pr_info("Using ARM PMSAv8 Compliant MPU. Used %d of %d regions\n",
+			mpu_rgn_info.used, mpu_max_regions);
+}
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index f10e31d0730a..81d0efb055c6 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -273,13 +273,14 @@
 	mcr	p15, 0, ip, c7, c10, 4		@ data write barrier
 	.endm
 
-.macro define_processor_functions name:req, dabort:req, pabort:req, nommu=0, suspend=0
+.macro define_processor_functions name:req, dabort:req, pabort:req, nommu=0, suspend=0, bugs=0
 	.type	\name\()_processor_functions, #object
 	.align 2
 ENTRY(\name\()_processor_functions)
 	.word	\dabort
 	.word	\pabort
 	.word	cpu_\name\()_proc_init
+	.word	\bugs
 	.word	cpu_\name\()_proc_fin
 	.word	cpu_\name\()_reset
 	.word	cpu_\name\()_do_idle
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index c6141a5435c3..f8d45ad2a515 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -41,11 +41,6 @@
  *	even on Cortex-A8 revisions not affected by 430973.
  *	If IBE is not set, the flush BTAC/BTB won't do anything.
  */
-ENTRY(cpu_ca8_switch_mm)
-#ifdef CONFIG_MMU
-	mov	r2, #0
-	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
-#endif
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
 	mmid	r1, r1				@ get mm->context.id
@@ -66,7 +61,6 @@ ENTRY(cpu_v7_switch_mm)
 #endif
 	bx	lr
 ENDPROC(cpu_v7_switch_mm)
-ENDPROC(cpu_ca8_switch_mm)
 
 /*
  *	cpu_v7_set_pte_ext(ptep, pte)
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
new file mode 100644
index 000000000000..5544b82a2e7a
--- /dev/null
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/arm-smccc.h>
+#include <linux/kernel.h>
+#include <linux/psci.h>
+#include <linux/smp.h>
+
+#include <asm/cp15.h>
+#include <asm/cputype.h>
+#include <asm/proc-fns.h>
+#include <asm/system_misc.h>
+
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+DEFINE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn);
+
+extern void cpu_v7_iciallu_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
+extern void cpu_v7_bpiall_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
+extern void cpu_v7_smc_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
+extern void cpu_v7_hvc_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
+
+static void harden_branch_predictor_bpiall(void)
+{
+	write_sysreg(0, BPIALL);
+}
+
+static void harden_branch_predictor_iciallu(void)
+{
+	write_sysreg(0, ICIALLU);
+}
+
+static void __maybe_unused call_smc_arch_workaround_1(void)
+{
+	arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
+}
+
+static void __maybe_unused call_hvc_arch_workaround_1(void)
+{
+	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
+}
+
+static void cpu_v7_spectre_init(void)
+{
+	const char *spectre_v2_method = NULL;
+	int cpu = smp_processor_id();
+
+	if (per_cpu(harden_branch_predictor_fn, cpu))
+		return;
+
+	switch (read_cpuid_part()) {
+	case ARM_CPU_PART_CORTEX_A8:
+	case ARM_CPU_PART_CORTEX_A9:
+	case ARM_CPU_PART_CORTEX_A12:
+	case ARM_CPU_PART_CORTEX_A17:
+	case ARM_CPU_PART_CORTEX_A73:
+	case ARM_CPU_PART_CORTEX_A75:
+		if (processor.switch_mm != cpu_v7_bpiall_switch_mm)
+			goto bl_error;
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			harden_branch_predictor_bpiall;
+		spectre_v2_method = "BPIALL";
+		break;
+
+	case ARM_CPU_PART_CORTEX_A15:
+	case ARM_CPU_PART_BRAHMA_B15:
+		if (processor.switch_mm != cpu_v7_iciallu_switch_mm)
+			goto bl_error;
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			harden_branch_predictor_iciallu;
+		spectre_v2_method = "ICIALLU";
+		break;
+
+#ifdef CONFIG_ARM_PSCI
+	default:
+		/* Other ARM CPUs require no workaround */
+		if (read_cpuid_implementor() == ARM_CPU_IMP_ARM)
+			break;
+		/* fallthrough */
+		/* Cortex A57/A72 require firmware workaround */
+	case ARM_CPU_PART_CORTEX_A57:
+	case ARM_CPU_PART_CORTEX_A72: {
+		struct arm_smccc_res res;
+
+		if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
+			break;
+
+		switch (psci_ops.conduit) {
+		case PSCI_CONDUIT_HVC:
+			arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+			if ((int)res.a0 != 0)
+				break;
+			if (processor.switch_mm != cpu_v7_hvc_switch_mm && cpu)
+				goto bl_error;
+			per_cpu(harden_branch_predictor_fn, cpu) =
+				call_hvc_arch_workaround_1;
+			processor.switch_mm = cpu_v7_hvc_switch_mm;
+			spectre_v2_method = "hypervisor";
+			break;
+
+		case PSCI_CONDUIT_SMC:
+			arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+			if ((int)res.a0 != 0)
+				break;
+			if (processor.switch_mm != cpu_v7_smc_switch_mm && cpu)
+				goto bl_error;
+			per_cpu(harden_branch_predictor_fn, cpu) =
+				call_smc_arch_workaround_1;
+			processor.switch_mm = cpu_v7_smc_switch_mm;
+			spectre_v2_method = "firmware";
+			break;
+
+		default:
+			break;
+		}
+	}
+#endif
+	}
+
+	if (spectre_v2_method)
+		pr_info("CPU%u: Spectre v2: using %s workaround\n",
+			smp_processor_id(), spectre_v2_method);
+	return;
+
+bl_error:
+	pr_err("CPU%u: Spectre v2: incorrect context switching function, system vulnerable\n",
+		cpu);
+}
+#else
+static void cpu_v7_spectre_init(void)
+{
+}
+#endif
+
+static __maybe_unused bool cpu_v7_check_auxcr_set(bool *warned,
+						  u32 mask, const char *msg)
+{
+	u32 aux_cr;
+
+	asm("mrc p15, 0, %0, c1, c0, 1" : "=r" (aux_cr));
+
+	if ((aux_cr & mask) != mask) {
+		if (!*warned)
+			pr_err("CPU%u: %s", smp_processor_id(), msg);
+		*warned = true;
+		return false;
+	}
+	return true;
+}
+
+static DEFINE_PER_CPU(bool, spectre_warned);
+
+static bool check_spectre_auxcr(bool *warned, u32 bit)
+{
+	return IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR) &&
+		cpu_v7_check_auxcr_set(warned, bit,
+				       "Spectre v2: firmware did not set auxiliary control register IBE bit, system vulnerable\n");
+}
+
+void cpu_v7_ca8_ibe(void)
+{
+	if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(6)))
+		cpu_v7_spectre_init();
+}
+
+void cpu_v7_ca15_ibe(void)
+{
+	if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0)))
+		cpu_v7_spectre_init();
+}
+
+void cpu_v7_bugs_init(void)
+{
+	cpu_v7_spectre_init();
+}
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index b528a15f460d..6fe52819e014 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -9,6 +9,7 @@
  *
  *  This is the "shell" of the ARMv7 processor support.
  */
+#include <linux/arm-smccc.h>
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <asm/assembler.h>
@@ -93,6 +94,37 @@ ENTRY(cpu_v7_dcache_clean_area)
 	ret	lr
 ENDPROC(cpu_v7_dcache_clean_area)
 
+#ifdef CONFIG_ARM_PSCI
+	.arch_extension sec
+ENTRY(cpu_v7_smc_switch_mm)
+	stmfd	sp!, {r0 - r3}
+	movw	r0, #:lower16:ARM_SMCCC_ARCH_WORKAROUND_1
+	movt	r0, #:upper16:ARM_SMCCC_ARCH_WORKAROUND_1
+	smc	#0
+	ldmfd	sp!, {r0 - r3}
+	b	cpu_v7_switch_mm
+ENDPROC(cpu_v7_smc_switch_mm)
+	.arch_extension virt
+ENTRY(cpu_v7_hvc_switch_mm)
+	stmfd	sp!, {r0 - r3}
+	movw	r0, #:lower16:ARM_SMCCC_ARCH_WORKAROUND_1
+	movt	r0, #:upper16:ARM_SMCCC_ARCH_WORKAROUND_1
+	hvc	#0
+	ldmfd	sp!, {r0 - r3}
+	b	cpu_v7_switch_mm
+ENDPROC(cpu_v7_smc_switch_mm)
+#endif
+ENTRY(cpu_v7_iciallu_switch_mm)
+	mov	r3, #0
+	mcr	p15, 0, r3, c7, c5, 0		@ ICIALLU
+	b	cpu_v7_switch_mm
+ENDPROC(cpu_v7_iciallu_switch_mm)
+ENTRY(cpu_v7_bpiall_switch_mm)
+	mov	r3, #0
+	mcr	p15, 0, r3, c7, c5, 6		@ flush BTAC/BTB
+	b	cpu_v7_switch_mm
+ENDPROC(cpu_v7_bpiall_switch_mm)
+
 	string	cpu_v7_name, "ARMv7 Processor"
 	.align
 
@@ -158,31 +190,6 @@ ENTRY(cpu_v7_do_resume)
 ENDPROC(cpu_v7_do_resume)
 #endif
 
-/*
- * Cortex-A8
- */
-	globl_equ	cpu_ca8_proc_init,	cpu_v7_proc_init
-	globl_equ	cpu_ca8_proc_fin,	cpu_v7_proc_fin
-	globl_equ	cpu_ca8_reset,		cpu_v7_reset
-	globl_equ	cpu_ca8_do_idle,	cpu_v7_do_idle
-	globl_equ	cpu_ca8_dcache_clean_area, cpu_v7_dcache_clean_area
-	globl_equ	cpu_ca8_set_pte_ext,	cpu_v7_set_pte_ext
-	globl_equ	cpu_ca8_suspend_size,	cpu_v7_suspend_size
-#ifdef CONFIG_ARM_CPU_SUSPEND
-	globl_equ	cpu_ca8_do_suspend,	cpu_v7_do_suspend
-	globl_equ	cpu_ca8_do_resume,	cpu_v7_do_resume
-#endif
-
-/*
- * Cortex-A9 processor functions
- */
-	globl_equ	cpu_ca9mp_proc_init,	cpu_v7_proc_init
-	globl_equ	cpu_ca9mp_proc_fin,	cpu_v7_proc_fin
-	globl_equ	cpu_ca9mp_reset,	cpu_v7_reset
-	globl_equ	cpu_ca9mp_do_idle,	cpu_v7_do_idle
-	globl_equ	cpu_ca9mp_dcache_clean_area, cpu_v7_dcache_clean_area
-	globl_equ	cpu_ca9mp_switch_mm,	cpu_v7_switch_mm
-	globl_equ	cpu_ca9mp_set_pte_ext,	cpu_v7_set_pte_ext
 .globl	cpu_ca9mp_suspend_size
 .equ	cpu_ca9mp_suspend_size, cpu_v7_suspend_size + 4 * 2
 #ifdef CONFIG_ARM_CPU_SUSPEND
@@ -547,12 +554,79 @@ __v7_setup_stack:
 
 	__INITDATA
 
+	.weak cpu_v7_bugs_init
+
 	@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
-	define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+	define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1, bugs=cpu_v7_bugs_init
+
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	@ generic v7 bpiall on context switch
+	globl_equ	cpu_v7_bpiall_proc_init,	cpu_v7_proc_init
+	globl_equ	cpu_v7_bpiall_proc_fin,		cpu_v7_proc_fin
+	globl_equ	cpu_v7_bpiall_reset,		cpu_v7_reset
+	globl_equ	cpu_v7_bpiall_do_idle,		cpu_v7_do_idle
+	globl_equ	cpu_v7_bpiall_dcache_clean_area, cpu_v7_dcache_clean_area
+	globl_equ	cpu_v7_bpiall_set_pte_ext,	cpu_v7_set_pte_ext
+	globl_equ	cpu_v7_bpiall_suspend_size,	cpu_v7_suspend_size
+#ifdef CONFIG_ARM_CPU_SUSPEND
+	globl_equ	cpu_v7_bpiall_do_suspend,	cpu_v7_do_suspend
+	globl_equ	cpu_v7_bpiall_do_resume,	cpu_v7_do_resume
+#endif
+	define_processor_functions v7_bpiall, dabort=v7_early_abort, pabort=v7_pabort, suspend=1, bugs=cpu_v7_bugs_init
+
+#define HARDENED_BPIALL_PROCESSOR_FUNCTIONS v7_bpiall_processor_functions
+#else
+#define HARDENED_BPIALL_PROCESSOR_FUNCTIONS v7_processor_functions
+#endif
+
 #ifndef CONFIG_ARM_LPAE
-	define_processor_functions ca8, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
-	define_processor_functions ca9mp, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+	@ Cortex-A8 - always needs bpiall switch_mm implementation
+	globl_equ	cpu_ca8_proc_init,	cpu_v7_proc_init
+	globl_equ	cpu_ca8_proc_fin,	cpu_v7_proc_fin
+	globl_equ	cpu_ca8_reset,		cpu_v7_reset
+	globl_equ	cpu_ca8_do_idle,	cpu_v7_do_idle
+	globl_equ	cpu_ca8_dcache_clean_area, cpu_v7_dcache_clean_area
+	globl_equ	cpu_ca8_set_pte_ext,	cpu_v7_set_pte_ext
+	globl_equ	cpu_ca8_switch_mm,	cpu_v7_bpiall_switch_mm
+	globl_equ	cpu_ca8_suspend_size,	cpu_v7_suspend_size
+#ifdef CONFIG_ARM_CPU_SUSPEND
+	globl_equ	cpu_ca8_do_suspend,	cpu_v7_do_suspend
+	globl_equ	cpu_ca8_do_resume,	cpu_v7_do_resume
+#endif
+	define_processor_functions ca8, dabort=v7_early_abort, pabort=v7_pabort, suspend=1, bugs=cpu_v7_ca8_ibe
+
+	@ Cortex-A9 - needs more registers preserved across suspend/resume
+	@ and bpiall switch_mm for hardening
+	globl_equ	cpu_ca9mp_proc_init,	cpu_v7_proc_init
+	globl_equ	cpu_ca9mp_proc_fin,	cpu_v7_proc_fin
+	globl_equ	cpu_ca9mp_reset,	cpu_v7_reset
+	globl_equ	cpu_ca9mp_do_idle,	cpu_v7_do_idle
+	globl_equ	cpu_ca9mp_dcache_clean_area, cpu_v7_dcache_clean_area
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	globl_equ	cpu_ca9mp_switch_mm,	cpu_v7_bpiall_switch_mm
+#else
+	globl_equ	cpu_ca9mp_switch_mm,	cpu_v7_switch_mm
+#endif
+	globl_equ	cpu_ca9mp_set_pte_ext,	cpu_v7_set_pte_ext
+	define_processor_functions ca9mp, dabort=v7_early_abort, pabort=v7_pabort, suspend=1, bugs=cpu_v7_bugs_init
 #endif
+
+	@ Cortex-A15 - needs iciallu switch_mm for hardening
+	globl_equ	cpu_ca15_proc_init,	cpu_v7_proc_init
+	globl_equ	cpu_ca15_proc_fin,	cpu_v7_proc_fin
+	globl_equ	cpu_ca15_reset,		cpu_v7_reset
+	globl_equ	cpu_ca15_do_idle,	cpu_v7_do_idle
+	globl_equ	cpu_ca15_dcache_clean_area, cpu_v7_dcache_clean_area
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	globl_equ	cpu_ca15_switch_mm,	cpu_v7_iciallu_switch_mm
+#else
+	globl_equ	cpu_ca15_switch_mm,	cpu_v7_switch_mm
+#endif
+	globl_equ	cpu_ca15_set_pte_ext,	cpu_v7_set_pte_ext
+	globl_equ	cpu_ca15_suspend_size,	cpu_v7_suspend_size
+	globl_equ	cpu_ca15_do_suspend,	cpu_v7_do_suspend
+	globl_equ	cpu_ca15_do_resume,	cpu_v7_do_resume
+	define_processor_functions ca15, dabort=v7_early_abort, pabort=v7_pabort, suspend=1, bugs=cpu_v7_ca15_ibe
 #ifdef CONFIG_CPU_PJ4B
 	define_processor_functions pj4b, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
 #endif
@@ -669,7 +743,7 @@ __v7_ca7mp_proc_info:
 __v7_ca12mp_proc_info:
 	.long	0x410fc0d0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca12mp_proc_info, __v7_ca12mp_setup
+	__v7_proc __v7_ca12mp_proc_info, __v7_ca12mp_setup, proc_fns = HARDENED_BPIALL_PROCESSOR_FUNCTIONS
 	.size	__v7_ca12mp_proc_info, . - __v7_ca12mp_proc_info
 
 	/*
@@ -679,7 +753,7 @@ __v7_ca12mp_proc_info:
 __v7_ca15mp_proc_info:
 	.long	0x410fc0f0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca15mp_proc_info, __v7_ca15mp_setup
+	__v7_proc __v7_ca15mp_proc_info, __v7_ca15mp_setup, proc_fns = ca15_processor_functions
 	.size	__v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
 
 	/*
@@ -689,7 +763,7 @@ __v7_ca15mp_proc_info:
 __v7_b15mp_proc_info:
 	.long	0x420f00f0
 	.long	0xff0ffff0
-	__v7_proc __v7_b15mp_proc_info, __v7_b15mp_setup, cache_fns = b15_cache_fns
+	__v7_proc __v7_b15mp_proc_info, __v7_b15mp_setup, proc_fns = ca15_processor_functions, cache_fns = b15_cache_fns
 	.size	__v7_b15mp_proc_info, . - __v7_b15mp_proc_info
 
 	/*
@@ -699,9 +773,25 @@ __v7_b15mp_proc_info:
 __v7_ca17mp_proc_info:
 	.long	0x410fc0e0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca17mp_proc_info, __v7_ca17mp_setup
+	__v7_proc __v7_ca17mp_proc_info, __v7_ca17mp_setup, proc_fns = HARDENED_BPIALL_PROCESSOR_FUNCTIONS
 	.size	__v7_ca17mp_proc_info, . - __v7_ca17mp_proc_info
 
+	/* ARM Ltd. Cortex A73 processor */
+	.type	__v7_ca73_proc_info, #object
+__v7_ca73_proc_info:
+	.long	0x410fd090
+	.long	0xff0ffff0
+	__v7_proc __v7_ca73_proc_info, __v7_setup, proc_fns = HARDENED_BPIALL_PROCESSOR_FUNCTIONS
+	.size	__v7_ca73_proc_info, . - __v7_ca73_proc_info
+
+	/* ARM Ltd. Cortex A75 processor */
+	.type	__v7_ca75_proc_info, #object
+__v7_ca75_proc_info:
+	.long	0x410fd0a0
+	.long	0xff0ffff0
+	__v7_proc __v7_ca75_proc_info, __v7_setup, proc_fns = HARDENED_BPIALL_PROCESSOR_FUNCTIONS
+	.size	__v7_ca75_proc_info, . - __v7_ca75_proc_info
+
 	/*
 	 * Qualcomm Inc. Krait processors.
 	 */
diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c
index bcdecc25461b..b2aa9b32bff2 100644
--- a/arch/arm/probes/kprobes/opt-arm.c
+++ b/arch/arm/probes/kprobes/opt-arm.c
@@ -165,13 +165,14 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 {
 	unsigned long flags;
 	struct kprobe *p = &op->kp;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	struct kprobe_ctlblk *kcb;
 
 	/* Save skipped registers */
 	regs->ARM_pc = (unsigned long)op->kp.addr;
 	regs->ARM_ORIG_r0 = ~0UL;
 
 	local_irq_save(flags);
+	kcb = get_kprobe_ctlblk();
 
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(&op->kp);
@@ -191,6 +192,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(optimized_callback)
 
 int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *orig)
 {
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 4c375e11ae95..35d0f823e823 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -218,8 +218,7 @@ static void vfp_raise_sigfpe(unsigned int sicode, struct pt_regs *regs)
 {
 	siginfo_t info;
 
-	memset(&info, 0, sizeof(info));
-
+	clear_siginfo(&info);
 	info.si_signo = SIGFPE;
 	info.si_code = sicode;
 	info.si_addr = (void __user *)(instruction_pointer(regs) - 4);
@@ -257,7 +256,7 @@ static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_
 
 	if (exceptions == VFP_EXCEPTION_ERROR) {
 		vfp_panic("unhandled bounce", inst);
-		vfp_raise_sigfpe(FPE_FIXME, regs);
+		vfp_raise_sigfpe(FPE_FLTINV, regs);
 		return;
 	}
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index eb2cf4938f6d..b25ed7834f6c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -105,7 +105,6 @@ config ARM64
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -133,6 +132,8 @@ config ARM64
 	select IRQ_FORCED_THREADING
 	select MODULES_USE_ELF_RELA
 	select MULTI_IRQ_HANDLER
+	select NEED_DMA_MAP_STATE
+	select NEED_SG_DMA_LENGTH
 	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
@@ -142,6 +143,7 @@ config ARM64
 	select POWER_SUPPLY
 	select REFCOUNT_FULL
 	select SPARSE_IRQ
+	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
 	help
@@ -150,9 +152,6 @@ config ARM64
 config 64BIT
 	def_bool y
 
-config ARCH_PHYS_ADDR_T_64BIT
-	def_bool y
-
 config MMU
 	def_bool y
 
@@ -237,24 +236,9 @@ config ZONE_DMA32
 config HAVE_GENERIC_GUP
 	def_bool y
 
-config ARCH_DMA_ADDR_T_64BIT
-	def_bool y
-
-config NEED_DMA_MAP_STATE
-	def_bool y
-
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
 config SMP
 	def_bool y
 
-config SWIOTLB
-	def_bool y
-
-config IOMMU_HELPER
-	def_bool SWIOTLB
-
 config KERNEL_MODE_NEON
 	def_bool y
 
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 15402861bb59..3c353b4715dc 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -56,7 +56,11 @@ KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst)
 KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
 KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)
 
+ifeq ($(cc-name),clang)
+KBUILD_CFLAGS	+= -DCONFIG_ARCH_SUPPORTS_INT128
+else
 KBUILD_CFLAGS	+= $(call cc-ifversion, -ge, 0500, -DCONFIG_ARCH_SUPPORTS_INT128)
+endif
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
@@ -74,7 +78,7 @@ LDFLAGS		+= -maarch64linux
 UTS_MACHINE	:= aarch64
 endif
 
-CHECKFLAGS	+= -D__aarch64__ -m64
+CHECKFLAGS	+= -D__aarch64__
 
 ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
 KBUILD_LDFLAGS_MODULE	+= -T $(srctree)/arch/arm64/kernel/module.lds
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index c89d0c307f8d..e6b059378dc0 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -17,6 +17,7 @@
 /dts-v1/;
 #include <dt-bindings/reset/altr,rst-mgr-s10.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/clock/stratix10-clock.h>
 
 / {
 	compatible = "altr,socfpga-stratix10";
@@ -92,9 +93,32 @@
 		interrupt-parent = <&intc>;
 		ranges = <0 0 0 0xffffffff>;
 
-		clkmgr@ffd1000 {
-			compatible = "altr,clk-mgr";
+		clkmgr: clock-controller@ffd10000 {
+			compatible = "intel,stratix10-clkmgr";
 			reg = <0xffd10000 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		clocks {
+			cb_intosc_hs_div2_clk: cb-intosc-hs-div2-clk {
+				#clock-cells = <0>;
+				compatible = "fixed-clock";
+			};
+
+			cb_intosc_ls_clk: cb-intosc-ls-clk {
+				#clock-cells = <0>;
+				compatible = "fixed-clock";
+			};
+
+			f2s_free_clk: f2s-free-clk {
+				#clock-cells = <0>;
+				compatible = "fixed-clock";
+			};
+
+			osc1: osc1 {
+				#clock-cells = <0>;
+				compatible = "fixed-clock";
+			};
 		};
 
 		gmac0: ethernet@ff800000 {
@@ -105,6 +129,8 @@
 			mac-address = [00 00 00 00 00 00];
 			resets = <&rst EMAC0_RESET>;
 			reset-names = "stmmaceth";
+			clocks = <&clkmgr STRATIX10_EMAC0_CLK>;
+			clock-names = "stmmaceth";
 			status = "disabled";
 		};
 
@@ -116,6 +142,8 @@
 			mac-address = [00 00 00 00 00 00];
 			resets = <&rst EMAC1_RESET>;
 			reset-names = "stmmaceth";
+			clocks = <&clkmgr STRATIX10_EMAC1_CLK>;
+			clock-names = "stmmaceth";
 			status = "disabled";
 		};
 
@@ -127,6 +155,8 @@
 			mac-address = [00 00 00 00 00 00];
 			resets = <&rst EMAC2_RESET>;
 			reset-names = "stmmaceth";
+			clocks = <&clkmgr STRATIX10_EMAC2_CLK>;
+			clock-names = "stmmaceth";
 			status = "disabled";
 		};
 
@@ -177,6 +207,7 @@
 			reg = <0xffc02800 0x100>;
 			interrupts = <0 103 4>;
 			resets = <&rst I2C0_RESET>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
 			status = "disabled";
 		};
 
@@ -187,6 +218,7 @@
 			reg = <0xffc02900 0x100>;
 			interrupts = <0 104 4>;
 			resets = <&rst I2C1_RESET>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
 			status = "disabled";
 		};
 
@@ -197,6 +229,7 @@
 			reg = <0xffc02a00 0x100>;
 			interrupts = <0 105 4>;
 			resets = <&rst I2C2_RESET>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
 			status = "disabled";
 		};
 
@@ -207,6 +240,7 @@
 			reg = <0xffc02b00 0x100>;
 			interrupts = <0 106 4>;
 			resets = <&rst I2C3_RESET>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
 			status = "disabled";
 		};
 
@@ -217,6 +251,7 @@
 			reg = <0xffc02c00 0x100>;
 			interrupts = <0 107 4>;
 			resets = <&rst I2C4_RESET>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
 			status = "disabled";
 		};
 
@@ -229,6 +264,9 @@
 			fifo-depth = <0x400>;
 			resets = <&rst SDMMC_RESET>;
 			reset-names = "reset";
+			clocks = <&clkmgr STRATIX10_L4_MP_CLK>,
+				 <&clkmgr STRATIX10_SDMMC_CLK>;
+			clock-names = "biu", "ciu";
 			status = "disabled";
 		};
 
@@ -237,6 +275,25 @@
 			reg = <0xffe00000 0x100000>;
 		};
 
+		pdma: pdma@ffda0000 {
+			compatible = "arm,pl330", "arm,primecell";
+			reg = <0xffda0000 0x1000>;
+			interrupts = <0 81 4>,
+				     <0 82 4>,
+				     <0 83 4>,
+				     <0 84 4>,
+				     <0 85 4>,
+				     <0 86 4>,
+				     <0 87 4>,
+				     <0 88 4>,
+				     <0 89 4>;
+			#dma-cells = <1>;
+			#dma-channels = <8>;
+			#dma-requests = <32>;
+			clocks = <&clkmgr STRATIX10_L4_MAIN_CLK>;
+			clock-names = "apb_pclk";
+		};
+
 		rst: rstmgr@ffd11000 {
 			#reset-cells = <1>;
 			compatible = "altr,rst-mgr";
@@ -288,24 +345,32 @@
 			compatible = "snps,dw-apb-timer";
 			interrupts = <0 113 4>;
 			reg = <0xffc03000 0x100>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
+			clock-names = "timer";
 		};
 
 		timer1: timer1@ffc03100 {
 			compatible = "snps,dw-apb-timer";
 			interrupts = <0 114 4>;
 			reg = <0xffc03100 0x100>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
+			clock-names = "timer";
 		};
 
 		timer2: timer2@ffd00000 {
 			compatible = "snps,dw-apb-timer";
 			interrupts = <0 115 4>;
 			reg = <0xffd00000 0x100>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
+			clock-names = "timer";
 		};
 
 		timer3: timer3@ffd00100 {
 			compatible = "snps,dw-apb-timer";
 			interrupts = <0 116 4>;
 			reg = <0xffd00100 0x100>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
+			clock-names = "timer";
 		};
 
 		uart0: serial0@ffc02000 {
@@ -315,6 +380,7 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			resets = <&rst UART0_RESET>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
 			status = "disabled";
 		};
 
@@ -325,6 +391,7 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			resets = <&rst UART1_RESET>;
+			clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
 			status = "disabled";
 		};
 
@@ -387,5 +454,17 @@
 			resets = <&rst WATCHDOG3_RESET>;
 			status = "disabled";
 		};
+
+		eccmgr {
+			compatible = "altr,socfpga-s10-ecc-manager";
+			interrupts = <0 15 4>, <0 95 4>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			sdramedac {
+				compatible = "altr,sdram-edac-s10";
+				interrupts = <16 4>, <48 4>;
+			};
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index eaf13fe29287..f9b1ef12db48 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -50,6 +50,21 @@
 		/* We expect the bootloader to fill in the reg */
 		reg = <0 0 0 0>;
 	};
+
+	ref_033v: 033-v-ref {
+		compatible = "regulator-fixed";
+		regulator-name = "0.33V";
+		regulator-min-microvolt = <330000>;
+		regulator-max-microvolt = <330000>;
+	};
+
+	soc {
+		clocks {
+			osc1 {
+				clock-frequency = <25000000>;
+			};
+		};
+	};
 };
 
 &gpio1 {
@@ -79,7 +94,7 @@
 			rxd2-skew-ps = <420>; /* 0ps */
 			rxd3-skew-ps = <420>; /* 0ps */
 			txen-skew-ps = <0>; /* -420ps */
-			txc-skew-ps = <1860>; /* 960ps */
+			txc-skew-ps = <900>; /* 0ps */
 			rxdv-skew-ps = <420>; /* 0ps */
 			rxc-skew-ps = <1680>; /* 780ps */
 		};
@@ -105,3 +120,30 @@
 &watchdog0 {
 	status = "okay";
 };
+
+&i2c1 {
+	status = "okay";
+	clock-frequency = <100000>;
+
+	adc@14 {
+		compatible = "lltc,ltc2497";
+		reg = <0x14>;
+		vref-supply = <&ref_033v>;
+	};
+
+	temp@4c {
+		compatible = "maxim,max1619";
+		reg = <0x4c>;
+	};
+
+	eeprom@51 {
+		compatible = "atmel,24c32";
+		reg = <0x51>;
+		pagesize = <32>;
+	};
+
+	rtc@68 {
+		compatible = "dallas,ds1339";
+		reg = <0x68>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
index 4eef36b22538..88e712ea757a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
@@ -212,3 +212,7 @@
 	pinctrl-0 = <&uart_ao_a_pins>;
 	pinctrl-names = "default";
 };
+
+&usb0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index 22bf37404ff1..3e3eb31748a3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -271,3 +271,15 @@
 	pinctrl-0 = <&uart_ao_a_pins>;
 	pinctrl-names = "default";
 };
+
+&usb0 {
+	status = "okay";
+};
+
+&usb2_phy0 {
+	/*
+	 * even though the schematics don't show it:
+	 * HDMI_5V is also used as supply for the USB VBUS.
+	 */
+	phy-supply = <&hdmi_5v>;
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
index 69c721a70e44..6739697be1de 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
@@ -215,3 +215,7 @@
 	pinctrl-0 = <&uart_ao_a_pins>;
 	pinctrl-names = "default";
 };
+
+&usb0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
index 0a0953fbc7d4..0cfd701809de 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
@@ -185,3 +185,7 @@
 	pinctrl-0 = <&uart_ao_a_pins>;
 	pinctrl-names = "default";
 };
+
+&usb0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index e1a39cbed8c9..dba365ed4bd5 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -20,6 +20,67 @@
 			no-map;
 		};
 	};
+
+	soc {
+		usb0: usb@c9000000 {
+			status = "disabled";
+			compatible = "amlogic,meson-gxl-dwc3";
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			clocks = <&clkc CLKID_USB>;
+			clock-names = "usb_general";
+			resets = <&reset RESET_USB_OTG>;
+			reset-names = "usb_otg";
+
+			dwc3: dwc3@c9000000 {
+				compatible = "snps,dwc3";
+				reg = <0x0 0xc9000000 0x0 0x100000>;
+				interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+				dr_mode = "host";
+				maximum-speed = "high-speed";
+				snps,dis_u2_susphy_quirk;
+				phys = <&usb3_phy>, <&usb2_phy0>, <&usb2_phy1>;
+			};
+		};
+	};
+};
+
+&apb {
+	usb2_phy0: phy@78000 {
+		compatible = "amlogic,meson-gxl-usb2-phy";
+		#phy-cells = <0>;
+		reg = <0x0 0x78000 0x0 0x20>;
+		clocks = <&clkc CLKID_USB>;
+		clock-names = "phy";
+		resets = <&reset RESET_USB_OTG>;
+		reset-names = "phy";
+		status = "okay";
+	};
+
+	usb2_phy1: phy@78020 {
+		compatible = "amlogic,meson-gxl-usb2-phy";
+		#phy-cells = <0>;
+		reg = <0x0 0x78020 0x0 0x20>;
+		clocks = <&clkc CLKID_USB>;
+		clock-names = "phy";
+		resets = <&reset RESET_USB_OTG>;
+		reset-names = "phy";
+		status = "okay";
+	};
+
+	usb3_phy: phy@78080 {
+		compatible = "amlogic,meson-gxl-usb3-phy";
+		#phy-cells = <0>;
+		reg = <0x0 0x78080 0x0 0x20>;
+		interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&clkc CLKID_USB>, <&clkc_AO CLKID_AO_CEC_32K>;
+		clock-names = "phy", "peripheral";
+		resets = <&reset RESET_USB_OTG>, <&reset RESET_USB_OTG>;
+		reset-names = "phy", "peripheral";
+		status = "okay";
+	};
 };
 
 &ethmac {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
index 4fd46c1546a7..0868da476e41 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
@@ -406,3 +406,7 @@
 	status = "okay";
 	vref-supply = <&vddio_ao18>;
 };
+
+&usb0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
index d076a7c425dd..247888d68a3a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
@@ -80,6 +80,19 @@
 	};
 };
 
+&apb {
+	usb2_phy2: phy@78040 {
+		compatible = "amlogic,meson-gxl-usb2-phy";
+		#phy-cells = <0>;
+		reg = <0x0 0x78040 0x0 0x20>;
+		clocks = <&clkc CLKID_USB>;
+		clock-names = "phy";
+		resets = <&reset RESET_USB_OTG>;
+		reset-names = "phy";
+		status = "okay";
+	};
+};
+
 &clkc_AO {
 	compatible = "amlogic,meson-gxm-aoclkc", "amlogic,meson-gx-aoclkc";
 };
@@ -100,3 +113,7 @@
 &hdmi_tx {
 	compatible = "amlogic,meson-gxm-dw-hdmi", "amlogic,meson-gx-dw-hdmi";
 };
+
+&dwc3 {
+	phys = <&usb3_phy>, <&usb2_phy0>, <&usb2_phy1>, <&usb2_phy2>;
+};
diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
index 2ac43221ddb6..69804c5f1197 100644
--- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
@@ -56,8 +56,6 @@
 
 			gpio_keys {
 				compatible = "gpio-keys";
-				#address-cells = <1>;
-				#size-cells = <0>;
 
 				power-button {
 					debounce_interval = <50>;
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
index 4b5465da81d8..8c68e0c26f1b 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
@@ -36,11 +36,11 @@
 		#size-cells = <1>;
 		ranges = <0x0 0x0 0x67d00000 0x00800000>;
 
-		sata0: ahci@210000 {
+		sata0: ahci@0 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
-			reg = <0x00210000 0x1000>;
+			reg = <0x00000000 0x1000>;
 			reg-names = "ahci";
-			interrupts = <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -52,9 +52,9 @@
 			};
 		};
 
-		sata_phy0: sata_phy@212100 {
+		sata_phy0: sata_phy@2100 {
 			compatible = "brcm,iproc-sr-sata-phy";
-			reg = <0x00212100 0x1000>;
+			reg = <0x00002100 0x1000>;
 			reg-names = "phy";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -66,11 +66,11 @@
 			};
 		};
 
-		sata1: ahci@310000 {
+		sata1: ahci@10000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
-			reg = <0x00310000 0x1000>;
+			reg = <0x00010000 0x1000>;
 			reg-names = "ahci";
-			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -82,9 +82,9 @@
 			};
 		};
 
-		sata_phy1: sata_phy@312100 {
+		sata_phy1: sata_phy@12100 {
 			compatible = "brcm,iproc-sr-sata-phy";
-			reg = <0x00312100 0x1000>;
+			reg = <0x00012100 0x1000>;
 			reg-names = "phy";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -96,11 +96,11 @@
 			};
 		};
 
-		sata2: ahci@120000 {
+		sata2: ahci@20000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
-			reg = <0x00120000 0x1000>;
+			reg = <0x00020000 0x1000>;
 			reg-names = "ahci";
-			interrupts = <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 325 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -112,9 +112,9 @@
 			};
 		};
 
-		sata_phy2: sata_phy@122100 {
+		sata_phy2: sata_phy@22100 {
 			compatible = "brcm,iproc-sr-sata-phy";
-			reg = <0x00122100 0x1000>;
+			reg = <0x00022100 0x1000>;
 			reg-names = "phy";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -126,11 +126,11 @@
 			};
 		};
 
-		sata3: ahci@130000 {
+		sata3: ahci@30000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
-			reg = <0x00130000 0x1000>;
+			reg = <0x00030000 0x1000>;
 			reg-names = "ahci";
-			interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -142,9 +142,9 @@
 			};
 		};
 
-		sata_phy3: sata_phy@132100 {
+		sata_phy3: sata_phy@32100 {
 			compatible = "brcm,iproc-sr-sata-phy";
-			reg = <0x00132100 0x1000>;
+			reg = <0x00032100 0x1000>;
 			reg-names = "phy";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -156,11 +156,11 @@
 			};
 		};
 
-		sata4: ahci@330000 {
+		sata4: ahci@100000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
-			reg = <0x00330000 0x1000>;
+			reg = <0x00100000 0x1000>;
 			reg-names = "ahci";
-			interrupts = <GIC_SPI 351 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -172,9 +172,9 @@
 			};
 		};
 
-		sata_phy4: sata_phy@332100 {
+		sata_phy4: sata_phy@102100 {
 			compatible = "brcm,iproc-sr-sata-phy";
-			reg = <0x00332100 0x1000>;
+			reg = <0x00102100 0x1000>;
 			reg-names = "phy";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -186,11 +186,11 @@
 			};
 		};
 
-		sata5: ahci@400000 {
+		sata5: ahci@110000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
-			reg = <0x00400000 0x1000>;
+			reg = <0x00110000 0x1000>;
 			reg-names = "ahci";
-			interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -202,9 +202,9 @@
 			};
 		};
 
-		sata_phy5: sata_phy@402100 {
+		sata_phy5: sata_phy@112100 {
 			compatible = "brcm,iproc-sr-sata-phy";
-			reg = <0x00402100 0x1000>;
+			reg = <0x00112100 0x1000>;
 			reg-names = "phy";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -216,11 +216,11 @@
 			};
 		};
 
-		sata6: ahci@410000 {
+		sata6: ahci@120000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
-			reg = <0x00410000 0x1000>;
+			reg = <0x00120000 0x1000>;
 			reg-names = "ahci";
-			interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -232,9 +232,9 @@
 			};
 		};
 
-		sata_phy6: sata_phy@412100 {
+		sata_phy6: sata_phy@122100 {
 			compatible = "brcm,iproc-sr-sata-phy";
-			reg = <0x00412100 0x1000>;
+			reg = <0x00122100 0x1000>;
 			reg-names = "phy";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -246,11 +246,11 @@
 			};
 		};
 
-		sata7: ahci@420000 {
+		sata7: ahci@130000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
-			reg = <0x00420000 0x1000>;
+			reg = <0x00130000 0x1000>;
 			reg-names = "ahci";
-			interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";
@@ -262,9 +262,9 @@
 			};
 		};
 
-		sata_phy7: sata_phy@422100 {
+		sata_phy7: sata_phy@132100 {
 			compatible = "brcm,iproc-sr-sata-phy";
-			reg = <0x00422100 0x1000>;
+			reg = <0x00132100 0x1000>;
 			reg-names = "phy";
 			#address-cells = <1>;
 			#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/exynos/exynos5433.dtsi b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
index c0231d077fa6..1ad8677f6a0a 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
@@ -1317,7 +1317,7 @@
 			reg = <0x14d60000 0x100>;
 			dmas = <&pdma0 31 &pdma0 30>;
 			dma-names = "tx", "rx";
-			interrupts = <GIC_SPI 435 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 435 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cmu_peric CLK_PCLK_I2S1>,
 				 <&cmu_peric CLK_PCLK_I2S1>,
 				 <&cmu_peric CLK_SCLK_I2S1>;
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index 724a0d3b7683..edb4ee0b8896 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -299,7 +299,6 @@
 		/* GPIO blocks 16 thru 19 do not appear to be routed to pins */
 
 		dwmmc_0: dwmmc0@f723d000 {
-			max-frequency = <150000000>;
 			cap-mmc-highspeed;
 			mmc-hs200-1_8v;
 			non-removable;
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
index 48cad7919efa..ed2f1237ea1e 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
@@ -38,9 +38,10 @@
 			compatible = "marvell,armada-7k-pp22";
 			reg = <0x0 0x100000>, <0x129000 0xb000>;
 			clocks = <&CP110_LABEL(clk) 1 3>, <&CP110_LABEL(clk) 1 9>,
-				 <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 18>;
+				 <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 6>,
+				 <&CP110_LABEL(clk) 1 18>;
 			clock-names = "pp_clk", "gop_clk",
-				      "mg_clk", "axi_clk";
+				      "mg_clk", "mg_core_clk", "axi_clk";
 			marvell,system-controller = <&CP110_LABEL(syscon0)>;
 			status = "disabled";
 			dma-coherent;
@@ -141,6 +142,8 @@
 			#size-cells = <0>;
 			compatible = "marvell,xmdio";
 			reg = <0x12a600 0x10>;
+			clocks = <&CP110_LABEL(clk) 1 5>,
+				 <&CP110_LABEL(clk) 1 6>, <&CP110_LABEL(clk) 1 18>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
index a8baad7b80df..13f57fff1477 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
@@ -46,7 +46,7 @@
 				compatible = "ethernet-phy-ieee802.3-c22";
 				reg = <0x0>;
 				interrupt-parent = <&gpio>;
-				interrupts = <TEGRA_MAIN_GPIO(M, 5) IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <TEGRA_MAIN_GPIO(M, 5) IRQ_TYPE_LEVEL_LOW>;
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
index e62bda1cf2d9..c32dd3419c87 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
@@ -414,7 +414,7 @@
 			mmc-ddr-1_8v;
 			mmc-hs200-1_8v;
 			mmc-pwrseq = <&emmc_pwrseq>;
-			cdns,phy-input-delay-legacy = <4>;
+			cdns,phy-input-delay-legacy = <9>;
 			cdns,phy-input-delay-mmc-highspeed = <2>;
 			cdns,phy-input-delay-mmc-ddr = <3>;
 			cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
index 2c1a92fafbfb..440c2e6a638b 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
@@ -67,3 +67,11 @@
 		reg = <0>;
 	};
 };
+
+&pinctrl_ether_rgmii {
+	tx {
+		pins = "RGMII_TXCLK", "RGMII_TXD0", "RGMII_TXD1",
+		       "RGMII_TXD2", "RGMII_TXD3", "RGMII_TXCTL";
+		drive-strength = <9>;
+	};
+};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
index 9efe20d07589..3a5ed789c056 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
@@ -519,7 +519,7 @@
 			mmc-ddr-1_8v;
 			mmc-hs200-1_8v;
 			mmc-pwrseq = <&emmc_pwrseq>;
-			cdns,phy-input-delay-legacy = <4>;
+			cdns,phy-input-delay-legacy = <9>;
 			cdns,phy-input-delay-mmc-highspeed = <2>;
 			cdns,phy-input-delay-mmc-ddr = <3>;
 			cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
index 7c8f710d9bfa..e85d6ddea3c2 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
@@ -334,7 +334,7 @@
 			mmc-ddr-1_8v;
 			mmc-hs200-1_8v;
 			mmc-pwrseq = <&emmc_pwrseq>;
-			cdns,phy-input-delay-legacy = <4>;
+			cdns,phy-input-delay-legacy = <9>;
 			cdns,phy-input-delay-mmc-highspeed = <2>;
 			cdns,phy-input-delay-mmc-ddr = <3>;
 			cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index cb5a243110c4..e3fdb0fd6f70 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -47,6 +47,12 @@ config CRYPTO_SM3_ARM64_CE
 	select CRYPTO_HASH
 	select CRYPTO_SM3
 
+config CRYPTO_SM4_ARM64_CE
+	tristate "SM4 symmetric cipher (ARMv8.2 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_SM4
+
 config CRYPTO_GHASH_ARM64_CE
 	tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions"
 	depends on KERNEL_MODE_NEON
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index f35ac684b1c0..bcafd016618e 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -23,6 +23,9 @@ sha3-ce-y := sha3-ce-glue.o sha3-ce-core.o
 obj-$(CONFIG_CRYPTO_SM3_ARM64_CE) += sm3-ce.o
 sm3-ce-y := sm3-ce-glue.o sm3-ce-core.o
 
+obj-$(CONFIG_CRYPTO_SM4_ARM64_CE) += sm4-ce.o
+sm4-ce-y := sm4-ce-glue.o sm4-ce-core.o
+
 obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
 ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
 
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index e3a375c4cb83..88f5aef7934c 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -19,24 +19,33 @@
 	 *			     u32 *macp, u8 const rk[], u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_auth_data)
-	ldr	w8, [x3]			/* leftover from prev round? */
+	frame_push	7
+
+	mov	x19, x0
+	mov	x20, x1
+	mov	x21, x2
+	mov	x22, x3
+	mov	x23, x4
+	mov	x24, x5
+
+	ldr	w25, [x22]			/* leftover from prev round? */
 	ld1	{v0.16b}, [x0]			/* load mac */
-	cbz	w8, 1f
-	sub	w8, w8, #16
+	cbz	w25, 1f
+	sub	w25, w25, #16
 	eor	v1.16b, v1.16b, v1.16b
-0:	ldrb	w7, [x1], #1			/* get 1 byte of input */
-	subs	w2, w2, #1
-	add	w8, w8, #1
+0:	ldrb	w7, [x20], #1			/* get 1 byte of input */
+	subs	w21, w21, #1
+	add	w25, w25, #1
 	ins	v1.b[0], w7
 	ext	v1.16b, v1.16b, v1.16b, #1	/* rotate in the input bytes */
 	beq	8f				/* out of input? */
-	cbnz	w8, 0b
+	cbnz	w25, 0b
 	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.4s}, [x4]			/* load first round key */
-	prfm	pldl1strm, [x1]
-	cmp	w5, #12				/* which key size? */
-	add	x6, x4, #16
-	sub	w7, w5, #2			/* modified # of rounds */
+1:	ld1	{v3.4s}, [x23]			/* load first round key */
+	prfm	pldl1strm, [x20]
+	cmp	w24, #12			/* which key size? */
+	add	x6, x23, #16
+	sub	w7, w24, #2			/* modified # of rounds */
 	bmi	2f
 	bne	5f
 	mov	v5.16b, v3.16b
@@ -55,33 +64,43 @@ ENTRY(ce_aes_ccm_auth_data)
 	ld1	{v5.4s}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
-	subs	w2, w2, #16			/* last data? */
+	subs	w21, w21, #16			/* last data? */
 	eor	v0.16b, v0.16b, v5.16b		/* final round */
 	bmi	6f
-	ld1	{v1.16b}, [x1], #16		/* load next input block */
+	ld1	{v1.16b}, [x20], #16		/* load next input block */
 	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
-	bne	1b
-6:	st1	{v0.16b}, [x0]			/* store mac */
+	beq	6f
+
+	if_will_cond_yield_neon
+	st1	{v0.16b}, [x19]			/* store mac */
+	do_cond_yield_neon
+	ld1	{v0.16b}, [x19]			/* reload mac */
+	endif_yield_neon
+
+	b	1b
+6:	st1	{v0.16b}, [x19]			/* store mac */
 	beq	10f
-	adds	w2, w2, #16
+	adds	w21, w21, #16
 	beq	10f
-	mov	w8, w2
-7:	ldrb	w7, [x1], #1
+	mov	w25, w21
+7:	ldrb	w7, [x20], #1
 	umov	w6, v0.b[0]
 	eor	w6, w6, w7
-	strb	w6, [x0], #1
-	subs	w2, w2, #1
+	strb	w6, [x19], #1
+	subs	w21, w21, #1
 	beq	10f
 	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
 	b	7b
-8:	mov	w7, w8
-	add	w8, w8, #16
+8:	mov	w7, w25
+	add	w25, w25, #16
 9:	ext	v1.16b, v1.16b, v1.16b, #1
 	adds	w7, w7, #1
 	bne	9b
 	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.16b}, [x0]
-10:	str	w8, [x3]
+	st1	{v0.16b}, [x19]
+10:	str	w25, [x22]
+
+	frame_pop
 	ret
 ENDPROC(ce_aes_ccm_auth_data)
 
@@ -126,19 +145,29 @@ ENTRY(ce_aes_ccm_final)
 ENDPROC(ce_aes_ccm_final)
 
 	.macro	aes_ccm_do_crypt,enc
-	ldr	x8, [x6, #8]			/* load lower ctr */
-	ld1	{v0.16b}, [x5]			/* load mac */
-CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
+	frame_push	8
+
+	mov	x19, x0
+	mov	x20, x1
+	mov	x21, x2
+	mov	x22, x3
+	mov	x23, x4
+	mov	x24, x5
+	mov	x25, x6
+
+	ldr	x26, [x25, #8]			/* load lower ctr */
+	ld1	{v0.16b}, [x24]			/* load mac */
+CPU_LE(	rev	x26, x26		)	/* keep swabbed ctr in reg */
 0:	/* outer loop */
-	ld1	{v1.8b}, [x6]			/* load upper ctr */
-	prfm	pldl1strm, [x1]
-	add	x8, x8, #1
-	rev	x9, x8
-	cmp	w4, #12				/* which key size? */
-	sub	w7, w4, #2			/* get modified # of rounds */
+	ld1	{v1.8b}, [x25]			/* load upper ctr */
+	prfm	pldl1strm, [x20]
+	add	x26, x26, #1
+	rev	x9, x26
+	cmp	w23, #12			/* which key size? */
+	sub	w7, w23, #2			/* get modified # of rounds */
 	ins	v1.d[1], x9			/* no carry in lower ctr */
-	ld1	{v3.4s}, [x3]			/* load first round key */
-	add	x10, x3, #16
+	ld1	{v3.4s}, [x22]			/* load first round key */
+	add	x10, x22, #16
 	bmi	1f
 	bne	4f
 	mov	v5.16b, v3.16b
@@ -165,9 +194,9 @@ CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 	bpl	2b
 	aese	v0.16b, v4.16b
 	aese	v1.16b, v4.16b
-	subs	w2, w2, #16
-	bmi	6f				/* partial block? */
-	ld1	{v2.16b}, [x1], #16		/* load next input block */
+	subs	w21, w21, #16
+	bmi	7f				/* partial block? */
+	ld1	{v2.16b}, [x20], #16		/* load next input block */
 	.if	\enc == 1
 	eor	v2.16b, v2.16b, v5.16b		/* final round enc+mac */
 	eor	v1.16b, v1.16b, v2.16b		/* xor with crypted ctr */
@@ -176,18 +205,29 @@ CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 	eor	v1.16b, v2.16b, v5.16b		/* final round enc */
 	.endif
 	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
-	st1	{v1.16b}, [x0], #16		/* write output block */
-	bne	0b
-CPU_LE(	rev	x8, x8			)
-	st1	{v0.16b}, [x5]			/* store mac */
-	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
-5:	ret
-
-6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
+	st1	{v1.16b}, [x19], #16		/* write output block */
+	beq	5f
+
+	if_will_cond_yield_neon
+	st1	{v0.16b}, [x24]			/* store mac */
+	do_cond_yield_neon
+	ld1	{v0.16b}, [x24]			/* reload mac */
+	endif_yield_neon
+
+	b	0b
+5:
+CPU_LE(	rev	x26, x26			)
+	st1	{v0.16b}, [x24]			/* store mac */
+	str	x26, [x25, #8]			/* store lsb end of ctr (BE) */
+
+6:	frame_pop
+	ret
+
+7:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
 	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
-	st1	{v0.16b}, [x5]			/* store mac */
-	add	w2, w2, #16			/* process partial tail block */
-7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
+	st1	{v0.16b}, [x24]			/* store mac */
+	add	w21, w21, #16			/* process partial tail block */
+8:	ldrb	w9, [x20], #1			/* get 1 byte of input */
 	umov	w6, v1.b[0]			/* get top crypted ctr byte */
 	umov	w7, v0.b[0]			/* get top mac byte */
 	.if	\enc == 1
@@ -197,13 +237,13 @@ CPU_LE(	rev	x8, x8			)
 	eor	w9, w9, w6
 	eor	w7, w7, w9
 	.endif
-	strb	w9, [x0], #1			/* store out byte */
-	strb	w7, [x5], #1			/* store mac byte */
-	subs	w2, w2, #1
-	beq	5b
+	strb	w9, [x19], #1			/* store out byte */
+	strb	w7, [x24], #1			/* store mac byte */
+	subs	w21, w21, #1
+	beq	6b
 	ext	v0.16b, v0.16b, v0.16b, #1	/* shift out mac byte */
 	ext	v1.16b, v1.16b, v1.16b, #1	/* shift out ctr byte */
-	b	7b
+	b	8b
 	.endm
 
 	/*
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index 50330f5c3adc..623e74ed1c67 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -30,18 +30,21 @@
 	.endm
 
 	/* prepare for encryption with key in rk[] */
-	.macro		enc_prepare, rounds, rk, ignore
-	load_round_keys	\rounds, \rk
+	.macro		enc_prepare, rounds, rk, temp
+	mov		\temp, \rk
+	load_round_keys	\rounds, \temp
 	.endm
 
 	/* prepare for encryption (again) but with new key in rk[] */
-	.macro		enc_switch_key, rounds, rk, ignore
-	load_round_keys	\rounds, \rk
+	.macro		enc_switch_key, rounds, rk, temp
+	mov		\temp, \rk
+	load_round_keys	\rounds, \temp
 	.endm
 
 	/* prepare for decryption with key in rk[] */
-	.macro		dec_prepare, rounds, rk, ignore
-	load_round_keys	\rounds, \rk
+	.macro		dec_prepare, rounds, rk, temp
+	mov		\temp, \rk
+	load_round_keys	\rounds, \temp
 	.endm
 
 	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index a68412e1e3a4..483a7130cf0e 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -14,12 +14,12 @@
 	.align		4
 
 aes_encrypt_block4x:
-	encrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
+	encrypt_block4x	v0, v1, v2, v3, w22, x21, x8, w7
 	ret
 ENDPROC(aes_encrypt_block4x)
 
 aes_decrypt_block4x:
-	decrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
+	decrypt_block4x	v0, v1, v2, v3, w22, x21, x8, w7
 	ret
 ENDPROC(aes_decrypt_block4x)
 
@@ -31,57 +31,71 @@ ENDPROC(aes_decrypt_block4x)
 	 */
 
 AES_ENTRY(aes_ecb_encrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	5
 
-	enc_prepare	w3, x2, x5
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+
+.Lecbencrestart:
+	enc_prepare	w22, x21, x5
 
 .LecbencloopNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lecbenc1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 pt blocks */
 	bl		aes_encrypt_block4x
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
+	cond_yield_neon	.Lecbencrestart
 	b		.LecbencloopNx
 .Lecbenc1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lecbencout
 .Lecbencloop:
-	ld1		{v0.16b}, [x1], #16		/* get next pt block */
-	encrypt_block	v0, w3, x2, x5, w6
-	st1		{v0.16b}, [x0], #16
-	subs		w4, w4, #1
+	ld1		{v0.16b}, [x20], #16		/* get next pt block */
+	encrypt_block	v0, w22, x21, x5, w6
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	bne		.Lecbencloop
 .Lecbencout:
-	ldp		x29, x30, [sp], #16
+	frame_pop
 	ret
 AES_ENDPROC(aes_ecb_encrypt)
 
 
 AES_ENTRY(aes_ecb_decrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	5
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
 
-	dec_prepare	w3, x2, x5
+.Lecbdecrestart:
+	dec_prepare	w22, x21, x5
 
 .LecbdecloopNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lecbdec1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 ct blocks */
 	bl		aes_decrypt_block4x
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
+	cond_yield_neon	.Lecbdecrestart
 	b		.LecbdecloopNx
 .Lecbdec1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lecbdecout
 .Lecbdecloop:
-	ld1		{v0.16b}, [x1], #16		/* get next ct block */
-	decrypt_block	v0, w3, x2, x5, w6
-	st1		{v0.16b}, [x0], #16
-	subs		w4, w4, #1
+	ld1		{v0.16b}, [x20], #16		/* get next ct block */
+	decrypt_block	v0, w22, x21, x5, w6
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	bne		.Lecbdecloop
 .Lecbdecout:
-	ldp		x29, x30, [sp], #16
+	frame_pop
 	ret
 AES_ENDPROC(aes_ecb_decrypt)
 
@@ -94,78 +108,100 @@ AES_ENDPROC(aes_ecb_decrypt)
 	 */
 
 AES_ENTRY(aes_cbc_encrypt)
-	ld1		{v4.16b}, [x5]			/* get iv */
-	enc_prepare	w3, x2, x6
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+
+.Lcbcencrestart:
+	ld1		{v4.16b}, [x24]			/* get iv */
+	enc_prepare	w22, x21, x6
 
 .Lcbcencloop4x:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lcbcenc1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 pt blocks */
 	eor		v0.16b, v0.16b, v4.16b		/* ..and xor with iv */
-	encrypt_block	v0, w3, x2, x6, w7
+	encrypt_block	v0, w22, x21, x6, w7
 	eor		v1.16b, v1.16b, v0.16b
-	encrypt_block	v1, w3, x2, x6, w7
+	encrypt_block	v1, w22, x21, x6, w7
 	eor		v2.16b, v2.16b, v1.16b
-	encrypt_block	v2, w3, x2, x6, w7
+	encrypt_block	v2, w22, x21, x6, w7
 	eor		v3.16b, v3.16b, v2.16b
-	encrypt_block	v3, w3, x2, x6, w7
-	st1		{v0.16b-v3.16b}, [x0], #64
+	encrypt_block	v3, w22, x21, x6, w7
+	st1		{v0.16b-v3.16b}, [x19], #64
 	mov		v4.16b, v3.16b
+	st1		{v4.16b}, [x24]			/* return iv */
+	cond_yield_neon	.Lcbcencrestart
 	b		.Lcbcencloop4x
 .Lcbcenc1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lcbcencout
 .Lcbcencloop:
-	ld1		{v0.16b}, [x1], #16		/* get next pt block */
+	ld1		{v0.16b}, [x20], #16		/* get next pt block */
 	eor		v4.16b, v4.16b, v0.16b		/* ..and xor with iv */
-	encrypt_block	v4, w3, x2, x6, w7
-	st1		{v4.16b}, [x0], #16
-	subs		w4, w4, #1
+	encrypt_block	v4, w22, x21, x6, w7
+	st1		{v4.16b}, [x19], #16
+	subs		w23, w23, #1
 	bne		.Lcbcencloop
 .Lcbcencout:
-	st1		{v4.16b}, [x5]			/* return iv */
+	st1		{v4.16b}, [x24]			/* return iv */
+	frame_pop
 	ret
 AES_ENDPROC(aes_cbc_encrypt)
 
 
 AES_ENTRY(aes_cbc_decrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
 
-	ld1		{v7.16b}, [x5]			/* get iv */
-	dec_prepare	w3, x2, x6
+.Lcbcdecrestart:
+	ld1		{v7.16b}, [x24]			/* get iv */
+	dec_prepare	w22, x21, x6
 
 .LcbcdecloopNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lcbcdec1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 ct blocks */
 	mov		v4.16b, v0.16b
 	mov		v5.16b, v1.16b
 	mov		v6.16b, v2.16b
 	bl		aes_decrypt_block4x
-	sub		x1, x1, #16
+	sub		x20, x20, #16
 	eor		v0.16b, v0.16b, v7.16b
 	eor		v1.16b, v1.16b, v4.16b
-	ld1		{v7.16b}, [x1], #16		/* reload 1 ct block */
+	ld1		{v7.16b}, [x20], #16		/* reload 1 ct block */
 	eor		v2.16b, v2.16b, v5.16b
 	eor		v3.16b, v3.16b, v6.16b
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
+	st1		{v7.16b}, [x24]			/* return iv */
+	cond_yield_neon	.Lcbcdecrestart
 	b		.LcbcdecloopNx
 .Lcbcdec1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lcbcdecout
 .Lcbcdecloop:
-	ld1		{v1.16b}, [x1], #16		/* get next ct block */
+	ld1		{v1.16b}, [x20], #16		/* get next ct block */
 	mov		v0.16b, v1.16b			/* ...and copy to v0 */
-	decrypt_block	v0, w3, x2, x6, w7
+	decrypt_block	v0, w22, x21, x6, w7
 	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
 	mov		v7.16b, v1.16b			/* ct is next iv */
-	st1		{v0.16b}, [x0], #16
-	subs		w4, w4, #1
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	bne		.Lcbcdecloop
 .Lcbcdecout:
-	st1		{v7.16b}, [x5]			/* return iv */
-	ldp		x29, x30, [sp], #16
+	st1		{v7.16b}, [x24]			/* return iv */
+	frame_pop
 	ret
 AES_ENDPROC(aes_cbc_decrypt)
 
@@ -176,19 +212,26 @@ AES_ENDPROC(aes_cbc_decrypt)
 	 */
 
 AES_ENTRY(aes_ctr_encrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	6
 
-	enc_prepare	w3, x2, x6
-	ld1		{v4.16b}, [x5]
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+
+.Lctrrestart:
+	enc_prepare	w22, x21, x6
+	ld1		{v4.16b}, [x24]
 
 	umov		x6, v4.d[1]		/* keep swabbed ctr in reg */
 	rev		x6, x6
-	cmn		w6, w4			/* 32 bit overflow? */
-	bcs		.Lctrloop
 .LctrloopNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lctr1x
+	cmn		w6, #4			/* 32 bit overflow? */
+	bcs		.Lctr1x
 	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
 	dup		v7.4s, w6
 	mov		v0.16b, v4.16b
@@ -200,25 +243,27 @@ AES_ENTRY(aes_ctr_encrypt)
 	mov		v1.s[3], v8.s[0]
 	mov		v2.s[3], v8.s[1]
 	mov		v3.s[3], v8.s[2]
-	ld1		{v5.16b-v7.16b}, [x1], #48	/* get 3 input blocks */
+	ld1		{v5.16b-v7.16b}, [x20], #48	/* get 3 input blocks */
 	bl		aes_encrypt_block4x
 	eor		v0.16b, v5.16b, v0.16b
-	ld1		{v5.16b}, [x1], #16		/* get 1 input block  */
+	ld1		{v5.16b}, [x20], #16		/* get 1 input block  */
 	eor		v1.16b, v6.16b, v1.16b
 	eor		v2.16b, v7.16b, v2.16b
 	eor		v3.16b, v5.16b, v3.16b
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
 	add		x6, x6, #4
 	rev		x7, x6
 	ins		v4.d[1], x7
-	cbz		w4, .Lctrout
+	cbz		w23, .Lctrout
+	st1		{v4.16b}, [x24]		/* return next CTR value */
+	cond_yield_neon	.Lctrrestart
 	b		.LctrloopNx
 .Lctr1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lctrout
 .Lctrloop:
 	mov		v0.16b, v4.16b
-	encrypt_block	v0, w3, x2, x8, w7
+	encrypt_block	v0, w22, x21, x8, w7
 
 	adds		x6, x6, #1		/* increment BE ctr */
 	rev		x7, x6
@@ -226,22 +271,22 @@ AES_ENTRY(aes_ctr_encrypt)
 	bcs		.Lctrcarry		/* overflow? */
 
 .Lctrcarrydone:
-	subs		w4, w4, #1
+	subs		w23, w23, #1
 	bmi		.Lctrtailblock		/* blocks <0 means tail block */
-	ld1		{v3.16b}, [x1], #16
+	ld1		{v3.16b}, [x20], #16
 	eor		v3.16b, v0.16b, v3.16b
-	st1		{v3.16b}, [x0], #16
+	st1		{v3.16b}, [x19], #16
 	bne		.Lctrloop
 
 .Lctrout:
-	st1		{v4.16b}, [x5]		/* return next CTR value */
-	ldp		x29, x30, [sp], #16
+	st1		{v4.16b}, [x24]		/* return next CTR value */
+.Lctrret:
+	frame_pop
 	ret
 
 .Lctrtailblock:
-	st1		{v0.16b}, [x0]
-	ldp		x29, x30, [sp], #16
-	ret
+	st1		{v0.16b}, [x19]
+	b		.Lctrret
 
 .Lctrcarry:
 	umov		x7, v4.d[0]		/* load upper word of ctr  */
@@ -274,10 +319,16 @@ CPU_LE(	.quad		1, 0x87		)
 CPU_BE(	.quad		0x87, 1		)
 
 AES_ENTRY(aes_xts_encrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x6
 
-	ld1		{v4.16b}, [x6]
+	ld1		{v4.16b}, [x24]
 	cbz		w7, .Lxtsencnotfirst
 
 	enc_prepare	w3, x5, x8
@@ -286,15 +337,17 @@ AES_ENTRY(aes_xts_encrypt)
 	ldr		q7, .Lxts_mul_x
 	b		.LxtsencNx
 
+.Lxtsencrestart:
+	ld1		{v4.16b}, [x24]
 .Lxtsencnotfirst:
-	enc_prepare	w3, x2, x8
+	enc_prepare	w22, x21, x8
 .LxtsencloopNx:
 	ldr		q7, .Lxts_mul_x
 	next_tweak	v4, v4, v7, v8
 .LxtsencNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lxtsenc1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 pt blocks */
 	next_tweak	v5, v4, v7, v8
 	eor		v0.16b, v0.16b, v4.16b
 	next_tweak	v6, v5, v7, v8
@@ -307,35 +360,43 @@ AES_ENTRY(aes_xts_encrypt)
 	eor		v0.16b, v0.16b, v4.16b
 	eor		v1.16b, v1.16b, v5.16b
 	eor		v2.16b, v2.16b, v6.16b
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
 	mov		v4.16b, v7.16b
-	cbz		w4, .Lxtsencout
+	cbz		w23, .Lxtsencout
+	st1		{v4.16b}, [x24]
+	cond_yield_neon	.Lxtsencrestart
 	b		.LxtsencloopNx
 .Lxtsenc1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lxtsencout
 .Lxtsencloop:
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	eor		v0.16b, v1.16b, v4.16b
-	encrypt_block	v0, w3, x2, x8, w7
+	encrypt_block	v0, w22, x21, x8, w7
 	eor		v0.16b, v0.16b, v4.16b
-	st1		{v0.16b}, [x0], #16
-	subs		w4, w4, #1
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	beq		.Lxtsencout
 	next_tweak	v4, v4, v7, v8
 	b		.Lxtsencloop
 .Lxtsencout:
-	st1		{v4.16b}, [x6]
-	ldp		x29, x30, [sp], #16
+	st1		{v4.16b}, [x24]
+	frame_pop
 	ret
 AES_ENDPROC(aes_xts_encrypt)
 
 
 AES_ENTRY(aes_xts_decrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	6
 
-	ld1		{v4.16b}, [x6]
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x6
+
+	ld1		{v4.16b}, [x24]
 	cbz		w7, .Lxtsdecnotfirst
 
 	enc_prepare	w3, x5, x8
@@ -344,15 +405,17 @@ AES_ENTRY(aes_xts_decrypt)
 	ldr		q7, .Lxts_mul_x
 	b		.LxtsdecNx
 
+.Lxtsdecrestart:
+	ld1		{v4.16b}, [x24]
 .Lxtsdecnotfirst:
-	dec_prepare	w3, x2, x8
+	dec_prepare	w22, x21, x8
 .LxtsdecloopNx:
 	ldr		q7, .Lxts_mul_x
 	next_tweak	v4, v4, v7, v8
 .LxtsdecNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lxtsdec1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 ct blocks */
 	next_tweak	v5, v4, v7, v8
 	eor		v0.16b, v0.16b, v4.16b
 	next_tweak	v6, v5, v7, v8
@@ -365,26 +428,28 @@ AES_ENTRY(aes_xts_decrypt)
 	eor		v0.16b, v0.16b, v4.16b
 	eor		v1.16b, v1.16b, v5.16b
 	eor		v2.16b, v2.16b, v6.16b
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
 	mov		v4.16b, v7.16b
-	cbz		w4, .Lxtsdecout
+	cbz		w23, .Lxtsdecout
+	st1		{v4.16b}, [x24]
+	cond_yield_neon	.Lxtsdecrestart
 	b		.LxtsdecloopNx
 .Lxtsdec1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lxtsdecout
 .Lxtsdecloop:
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	eor		v0.16b, v1.16b, v4.16b
-	decrypt_block	v0, w3, x2, x8, w7
+	decrypt_block	v0, w22, x21, x8, w7
 	eor		v0.16b, v0.16b, v4.16b
-	st1		{v0.16b}, [x0], #16
-	subs		w4, w4, #1
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	beq		.Lxtsdecout
 	next_tweak	v4, v4, v7, v8
 	b		.Lxtsdecloop
 .Lxtsdecout:
-	st1		{v4.16b}, [x6]
-	ldp		x29, x30, [sp], #16
+	st1		{v4.16b}, [x24]
+	frame_pop
 	ret
 AES_ENDPROC(aes_xts_decrypt)
 
@@ -393,43 +458,61 @@ AES_ENDPROC(aes_xts_decrypt)
 	 *		  int blocks, u8 dg[], int enc_before, int enc_after)
 	 */
 AES_ENTRY(aes_mac_update)
-	ld1		{v0.16b}, [x4]			/* get dg */
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x6
+
+	ld1		{v0.16b}, [x23]			/* get dg */
 	enc_prepare	w2, x1, x7
 	cbz		w5, .Lmacloop4x
 
 	encrypt_block	v0, w2, x1, x7, w8
 
 .Lmacloop4x:
-	subs		w3, w3, #4
+	subs		w22, w22, #4
 	bmi		.Lmac1x
-	ld1		{v1.16b-v4.16b}, [x0], #64	/* get next pt block */
+	ld1		{v1.16b-v4.16b}, [x19], #64	/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
-	encrypt_block	v0, w2, x1, x7, w8
+	encrypt_block	v0, w21, x20, x7, w8
 	eor		v0.16b, v0.16b, v2.16b
-	encrypt_block	v0, w2, x1, x7, w8
+	encrypt_block	v0, w21, x20, x7, w8
 	eor		v0.16b, v0.16b, v3.16b
-	encrypt_block	v0, w2, x1, x7, w8
+	encrypt_block	v0, w21, x20, x7, w8
 	eor		v0.16b, v0.16b, v4.16b
-	cmp		w3, wzr
-	csinv		x5, x6, xzr, eq
+	cmp		w22, wzr
+	csinv		x5, x24, xzr, eq
 	cbz		w5, .Lmacout
-	encrypt_block	v0, w2, x1, x7, w8
+	encrypt_block	v0, w21, x20, x7, w8
+	st1		{v0.16b}, [x23]			/* return dg */
+	cond_yield_neon	.Lmacrestart
 	b		.Lmacloop4x
 .Lmac1x:
-	add		w3, w3, #4
+	add		w22, w22, #4
 .Lmacloop:
-	cbz		w3, .Lmacout
-	ld1		{v1.16b}, [x0], #16		/* get next pt block */
+	cbz		w22, .Lmacout
+	ld1		{v1.16b}, [x19], #16		/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
 
-	subs		w3, w3, #1
-	csinv		x5, x6, xzr, eq
+	subs		w22, w22, #1
+	csinv		x5, x24, xzr, eq
 	cbz		w5, .Lmacout
 
-	encrypt_block	v0, w2, x1, x7, w8
+.Lmacenc:
+	encrypt_block	v0, w21, x20, x7, w8
 	b		.Lmacloop
 
 .Lmacout:
-	st1		{v0.16b}, [x4]			/* return dg */
+	st1		{v0.16b}, [x23]			/* return dg */
+	frame_pop
 	ret
+
+.Lmacrestart:
+	ld1		{v0.16b}, [x23]			/* get dg */
+	enc_prepare	w21, x20, x0
+	b		.Lmacloop4x
 AES_ENDPROC(aes_mac_update)
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index ca0472500433..e613a87f8b53 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -565,54 +565,61 @@ ENDPROC(aesbs_decrypt8)
 	 *		     int blocks)
 	 */
 	.macro		__ecb_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	5
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
 
 99:	mov		x5, #1
-	lsl		x5, x5, x4
-	subs		w4, w4, #8
-	csel		x4, x4, xzr, pl
+	lsl		x5, x5, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
 	csel		x5, x5, xzr, mi
 
-	ld1		{v0.16b}, [x1], #16
+	ld1		{v0.16b}, [x20], #16
 	tbnz		x5, #1, 0f
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	tbnz		x5, #2, 0f
-	ld1		{v2.16b}, [x1], #16
+	ld1		{v2.16b}, [x20], #16
 	tbnz		x5, #3, 0f
-	ld1		{v3.16b}, [x1], #16
+	ld1		{v3.16b}, [x20], #16
 	tbnz		x5, #4, 0f
-	ld1		{v4.16b}, [x1], #16
+	ld1		{v4.16b}, [x20], #16
 	tbnz		x5, #5, 0f
-	ld1		{v5.16b}, [x1], #16
+	ld1		{v5.16b}, [x20], #16
 	tbnz		x5, #6, 0f
-	ld1		{v6.16b}, [x1], #16
+	ld1		{v6.16b}, [x20], #16
 	tbnz		x5, #7, 0f
-	ld1		{v7.16b}, [x1], #16
+	ld1		{v7.16b}, [x20], #16
 
-0:	mov		bskey, x2
-	mov		rounds, x3
+0:	mov		bskey, x21
+	mov		rounds, x22
 	bl		\do8
 
-	st1		{\o0\().16b}, [x0], #16
+	st1		{\o0\().16b}, [x19], #16
 	tbnz		x5, #1, 1f
-	st1		{\o1\().16b}, [x0], #16
+	st1		{\o1\().16b}, [x19], #16
 	tbnz		x5, #2, 1f
-	st1		{\o2\().16b}, [x0], #16
+	st1		{\o2\().16b}, [x19], #16
 	tbnz		x5, #3, 1f
-	st1		{\o3\().16b}, [x0], #16
+	st1		{\o3\().16b}, [x19], #16
 	tbnz		x5, #4, 1f
-	st1		{\o4\().16b}, [x0], #16
+	st1		{\o4\().16b}, [x19], #16
 	tbnz		x5, #5, 1f
-	st1		{\o5\().16b}, [x0], #16
+	st1		{\o5\().16b}, [x19], #16
 	tbnz		x5, #6, 1f
-	st1		{\o6\().16b}, [x0], #16
+	st1		{\o6\().16b}, [x19], #16
 	tbnz		x5, #7, 1f
-	st1		{\o7\().16b}, [x0], #16
+	st1		{\o7\().16b}, [x19], #16
 
-	cbnz		x4, 99b
+	cbz		x23, 1f
+	cond_yield_neon
+	b		99b
 
-1:	ldp		x29, x30, [sp], #16
+1:	frame_pop
 	ret
 	.endm
 
@@ -632,43 +639,49 @@ ENDPROC(aesbs_ecb_decrypt)
 	 */
 	.align		4
 ENTRY(aesbs_cbc_decrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
 
 99:	mov		x6, #1
-	lsl		x6, x6, x4
-	subs		w4, w4, #8
-	csel		x4, x4, xzr, pl
+	lsl		x6, x6, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
 	csel		x6, x6, xzr, mi
 
-	ld1		{v0.16b}, [x1], #16
+	ld1		{v0.16b}, [x20], #16
 	mov		v25.16b, v0.16b
 	tbnz		x6, #1, 0f
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	mov		v26.16b, v1.16b
 	tbnz		x6, #2, 0f
-	ld1		{v2.16b}, [x1], #16
+	ld1		{v2.16b}, [x20], #16
 	mov		v27.16b, v2.16b
 	tbnz		x6, #3, 0f
-	ld1		{v3.16b}, [x1], #16
+	ld1		{v3.16b}, [x20], #16
 	mov		v28.16b, v3.16b
 	tbnz		x6, #4, 0f
-	ld1		{v4.16b}, [x1], #16
+	ld1		{v4.16b}, [x20], #16
 	mov		v29.16b, v4.16b
 	tbnz		x6, #5, 0f
-	ld1		{v5.16b}, [x1], #16
+	ld1		{v5.16b}, [x20], #16
 	mov		v30.16b, v5.16b
 	tbnz		x6, #6, 0f
-	ld1		{v6.16b}, [x1], #16
+	ld1		{v6.16b}, [x20], #16
 	mov		v31.16b, v6.16b
 	tbnz		x6, #7, 0f
-	ld1		{v7.16b}, [x1]
+	ld1		{v7.16b}, [x20]
 
-0:	mov		bskey, x2
-	mov		rounds, x3
+0:	mov		bskey, x21
+	mov		rounds, x22
 	bl		aesbs_decrypt8
 
-	ld1		{v24.16b}, [x5]			// load IV
+	ld1		{v24.16b}, [x24]		// load IV
 
 	eor		v1.16b, v1.16b, v25.16b
 	eor		v6.16b, v6.16b, v26.16b
@@ -679,34 +692,36 @@ ENTRY(aesbs_cbc_decrypt)
 	eor		v3.16b, v3.16b, v30.16b
 	eor		v5.16b, v5.16b, v31.16b
 
-	st1		{v0.16b}, [x0], #16
+	st1		{v0.16b}, [x19], #16
 	mov		v24.16b, v25.16b
 	tbnz		x6, #1, 1f
-	st1		{v1.16b}, [x0], #16
+	st1		{v1.16b}, [x19], #16
 	mov		v24.16b, v26.16b
 	tbnz		x6, #2, 1f
-	st1		{v6.16b}, [x0], #16
+	st1		{v6.16b}, [x19], #16
 	mov		v24.16b, v27.16b
 	tbnz		x6, #3, 1f
-	st1		{v4.16b}, [x0], #16
+	st1		{v4.16b}, [x19], #16
 	mov		v24.16b, v28.16b
 	tbnz		x6, #4, 1f
-	st1		{v2.16b}, [x0], #16
+	st1		{v2.16b}, [x19], #16
 	mov		v24.16b, v29.16b
 	tbnz		x6, #5, 1f
-	st1		{v7.16b}, [x0], #16
+	st1		{v7.16b}, [x19], #16
 	mov		v24.16b, v30.16b
 	tbnz		x6, #6, 1f
-	st1		{v3.16b}, [x0], #16
+	st1		{v3.16b}, [x19], #16
 	mov		v24.16b, v31.16b
 	tbnz		x6, #7, 1f
-	ld1		{v24.16b}, [x1], #16
-	st1		{v5.16b}, [x0], #16
-1:	st1		{v24.16b}, [x5]			// store IV
+	ld1		{v24.16b}, [x20], #16
+	st1		{v5.16b}, [x19], #16
+1:	st1		{v24.16b}, [x24]		// store IV
 
-	cbnz		x4, 99b
+	cbz		x23, 2f
+	cond_yield_neon
+	b		99b
 
-	ldp		x29, x30, [sp], #16
+2:	frame_pop
 	ret
 ENDPROC(aesbs_cbc_decrypt)
 
@@ -731,87 +746,93 @@ CPU_BE(	.quad		0x87, 1		)
 	 */
 __xts_crypt8:
 	mov		x6, #1
-	lsl		x6, x6, x4
-	subs		w4, w4, #8
-	csel		x4, x4, xzr, pl
+	lsl		x6, x6, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
 	csel		x6, x6, xzr, mi
 
-	ld1		{v0.16b}, [x1], #16
+	ld1		{v0.16b}, [x20], #16
 	next_tweak	v26, v25, v30, v31
 	eor		v0.16b, v0.16b, v25.16b
 	tbnz		x6, #1, 0f
 
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	next_tweak	v27, v26, v30, v31
 	eor		v1.16b, v1.16b, v26.16b
 	tbnz		x6, #2, 0f
 
-	ld1		{v2.16b}, [x1], #16
+	ld1		{v2.16b}, [x20], #16
 	next_tweak	v28, v27, v30, v31
 	eor		v2.16b, v2.16b, v27.16b
 	tbnz		x6, #3, 0f
 
-	ld1		{v3.16b}, [x1], #16
+	ld1		{v3.16b}, [x20], #16
 	next_tweak	v29, v28, v30, v31
 	eor		v3.16b, v3.16b, v28.16b
 	tbnz		x6, #4, 0f
 
-	ld1		{v4.16b}, [x1], #16
-	str		q29, [sp, #16]
+	ld1		{v4.16b}, [x20], #16
+	str		q29, [sp, #.Lframe_local_offset]
 	eor		v4.16b, v4.16b, v29.16b
 	next_tweak	v29, v29, v30, v31
 	tbnz		x6, #5, 0f
 
-	ld1		{v5.16b}, [x1], #16
-	str		q29, [sp, #32]
+	ld1		{v5.16b}, [x20], #16
+	str		q29, [sp, #.Lframe_local_offset + 16]
 	eor		v5.16b, v5.16b, v29.16b
 	next_tweak	v29, v29, v30, v31
 	tbnz		x6, #6, 0f
 
-	ld1		{v6.16b}, [x1], #16
-	str		q29, [sp, #48]
+	ld1		{v6.16b}, [x20], #16
+	str		q29, [sp, #.Lframe_local_offset + 32]
 	eor		v6.16b, v6.16b, v29.16b
 	next_tweak	v29, v29, v30, v31
 	tbnz		x6, #7, 0f
 
-	ld1		{v7.16b}, [x1], #16
-	str		q29, [sp, #64]
+	ld1		{v7.16b}, [x20], #16
+	str		q29, [sp, #.Lframe_local_offset + 48]
 	eor		v7.16b, v7.16b, v29.16b
 	next_tweak	v29, v29, v30, v31
 
-0:	mov		bskey, x2
-	mov		rounds, x3
+0:	mov		bskey, x21
+	mov		rounds, x22
 	br		x7
 ENDPROC(__xts_crypt8)
 
 	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
-	stp		x29, x30, [sp, #-80]!
-	mov		x29, sp
+	frame_push	6, 64
 
-	ldr		q30, .Lxts_mul_x
-	ld1		{v25.16b}, [x5]
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+
+0:	ldr		q30, .Lxts_mul_x
+	ld1		{v25.16b}, [x24]
 
 99:	adr		x7, \do8
 	bl		__xts_crypt8
 
-	ldp		q16, q17, [sp, #16]
-	ldp		q18, q19, [sp, #48]
+	ldp		q16, q17, [sp, #.Lframe_local_offset]
+	ldp		q18, q19, [sp, #.Lframe_local_offset + 32]
 
 	eor		\o0\().16b, \o0\().16b, v25.16b
 	eor		\o1\().16b, \o1\().16b, v26.16b
 	eor		\o2\().16b, \o2\().16b, v27.16b
 	eor		\o3\().16b, \o3\().16b, v28.16b
 
-	st1		{\o0\().16b}, [x0], #16
+	st1		{\o0\().16b}, [x19], #16
 	mov		v25.16b, v26.16b
 	tbnz		x6, #1, 1f
-	st1		{\o1\().16b}, [x0], #16
+	st1		{\o1\().16b}, [x19], #16
 	mov		v25.16b, v27.16b
 	tbnz		x6, #2, 1f
-	st1		{\o2\().16b}, [x0], #16
+	st1		{\o2\().16b}, [x19], #16
 	mov		v25.16b, v28.16b
 	tbnz		x6, #3, 1f
-	st1		{\o3\().16b}, [x0], #16
+	st1		{\o3\().16b}, [x19], #16
 	mov		v25.16b, v29.16b
 	tbnz		x6, #4, 1f
 
@@ -820,18 +841,22 @@ ENDPROC(__xts_crypt8)
 	eor		\o6\().16b, \o6\().16b, v18.16b
 	eor		\o7\().16b, \o7\().16b, v19.16b
 
-	st1		{\o4\().16b}, [x0], #16
+	st1		{\o4\().16b}, [x19], #16
 	tbnz		x6, #5, 1f
-	st1		{\o5\().16b}, [x0], #16
+	st1		{\o5\().16b}, [x19], #16
 	tbnz		x6, #6, 1f
-	st1		{\o6\().16b}, [x0], #16
+	st1		{\o6\().16b}, [x19], #16
 	tbnz		x6, #7, 1f
-	st1		{\o7\().16b}, [x0], #16
+	st1		{\o7\().16b}, [x19], #16
+
+	cbz		x23, 1f
+	st1		{v25.16b}, [x24]
 
-	cbnz		x4, 99b
+	cond_yield_neon	0b
+	b		99b
 
-1:	st1		{v25.16b}, [x5]
-	ldp		x29, x30, [sp], #80
+1:	st1		{v25.16b}, [x24]
+	frame_pop
 	ret
 	.endm
 
@@ -856,24 +881,31 @@ ENDPROC(aesbs_xts_decrypt)
 	 *		     int rounds, int blocks, u8 iv[], u8 final[])
 	 */
 ENTRY(aesbs_ctr_encrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
-
-	cmp		x6, #0
-	cset		x10, ne
-	add		x4, x4, x10		// do one extra block if final
-
-	ldp		x7, x8, [x5]
-	ld1		{v0.16b}, [x5]
+	frame_push	8
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+	mov		x25, x6
+
+	cmp		x25, #0
+	cset		x26, ne
+	add		x23, x23, x26		// do one extra block if final
+
+98:	ldp		x7, x8, [x24]
+	ld1		{v0.16b}, [x24]
 CPU_LE(	rev		x7, x7		)
 CPU_LE(	rev		x8, x8		)
 	adds		x8, x8, #1
 	adc		x7, x7, xzr
 
 99:	mov		x9, #1
-	lsl		x9, x9, x4
-	subs		w4, w4, #8
-	csel		x4, x4, xzr, pl
+	lsl		x9, x9, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
 	csel		x9, x9, xzr, le
 
 	tbnz		x9, #1, 0f
@@ -891,82 +923,85 @@ CPU_LE(	rev		x8, x8		)
 	tbnz		x9, #7, 0f
 	next_ctr	v7
 
-0:	mov		bskey, x2
-	mov		rounds, x3
+0:	mov		bskey, x21
+	mov		rounds, x22
 	bl		aesbs_encrypt8
 
-	lsr		x9, x9, x10		// disregard the extra block
+	lsr		x9, x9, x26		// disregard the extra block
 	tbnz		x9, #0, 0f
 
-	ld1		{v8.16b}, [x1], #16
+	ld1		{v8.16b}, [x20], #16
 	eor		v0.16b, v0.16b, v8.16b
-	st1		{v0.16b}, [x0], #16
+	st1		{v0.16b}, [x19], #16
 	tbnz		x9, #1, 1f
 
-	ld1		{v9.16b}, [x1], #16
+	ld1		{v9.16b}, [x20], #16
 	eor		v1.16b, v1.16b, v9.16b
-	st1		{v1.16b}, [x0], #16
+	st1		{v1.16b}, [x19], #16
 	tbnz		x9, #2, 2f
 
-	ld1		{v10.16b}, [x1], #16
+	ld1		{v10.16b}, [x20], #16
 	eor		v4.16b, v4.16b, v10.16b
-	st1		{v4.16b}, [x0], #16
+	st1		{v4.16b}, [x19], #16
 	tbnz		x9, #3, 3f
 
-	ld1		{v11.16b}, [x1], #16
+	ld1		{v11.16b}, [x20], #16
 	eor		v6.16b, v6.16b, v11.16b
-	st1		{v6.16b}, [x0], #16
+	st1		{v6.16b}, [x19], #16
 	tbnz		x9, #4, 4f
 
-	ld1		{v12.16b}, [x1], #16
+	ld1		{v12.16b}, [x20], #16
 	eor		v3.16b, v3.16b, v12.16b
-	st1		{v3.16b}, [x0], #16
+	st1		{v3.16b}, [x19], #16
 	tbnz		x9, #5, 5f
 
-	ld1		{v13.16b}, [x1], #16
+	ld1		{v13.16b}, [x20], #16
 	eor		v7.16b, v7.16b, v13.16b
-	st1		{v7.16b}, [x0], #16
+	st1		{v7.16b}, [x19], #16
 	tbnz		x9, #6, 6f
 
-	ld1		{v14.16b}, [x1], #16
+	ld1		{v14.16b}, [x20], #16
 	eor		v2.16b, v2.16b, v14.16b
-	st1		{v2.16b}, [x0], #16
+	st1		{v2.16b}, [x19], #16
 	tbnz		x9, #7, 7f
 
-	ld1		{v15.16b}, [x1], #16
+	ld1		{v15.16b}, [x20], #16
 	eor		v5.16b, v5.16b, v15.16b
-	st1		{v5.16b}, [x0], #16
+	st1		{v5.16b}, [x19], #16
 
 8:	next_ctr	v0
-	cbnz		x4, 99b
+	st1		{v0.16b}, [x24]
+	cbz		x23, 0f
+
+	cond_yield_neon	98b
+	b		99b
 
-0:	st1		{v0.16b}, [x5]
-	ldp		x29, x30, [sp], #16
+0:	frame_pop
 	ret
 
 	/*
 	 * If we are handling the tail of the input (x6 != NULL), return the
 	 * final keystream block back to the caller.
 	 */
-1:	cbz		x6, 8b
-	st1		{v1.16b}, [x6]
+1:	cbz		x25, 8b
+	st1		{v1.16b}, [x25]
 	b		8b
-2:	cbz		x6, 8b
-	st1		{v4.16b}, [x6]
+2:	cbz		x25, 8b
+	st1		{v4.16b}, [x25]
 	b		8b
-3:	cbz		x6, 8b
-	st1		{v6.16b}, [x6]
+3:	cbz		x25, 8b
+	st1		{v6.16b}, [x25]
 	b		8b
-4:	cbz		x6, 8b
-	st1		{v3.16b}, [x6]
+4:	cbz		x25, 8b
+	st1		{v3.16b}, [x25]
 	b		8b
-5:	cbz		x6, 8b
-	st1		{v7.16b}, [x6]
+5:	cbz		x25, 8b
+	st1		{v7.16b}, [x25]
 	b		8b
-6:	cbz		x6, 8b
-	st1		{v2.16b}, [x6]
+6:	cbz		x25, 8b
+	st1		{v2.16b}, [x25]
 	b		8b
-7:	cbz		x6, 8b
-	st1		{v5.16b}, [x6]
+7:	cbz		x25, 8b
+	st1		{v5.16b}, [x25]
 	b		8b
 ENDPROC(aesbs_ctr_encrypt)
diff --git a/arch/arm64/crypto/crc32-ce-core.S b/arch/arm64/crypto/crc32-ce-core.S
index 16ed3c7ebd37..8061bf0f9c66 100644
--- a/arch/arm64/crypto/crc32-ce-core.S
+++ b/arch/arm64/crypto/crc32-ce-core.S
@@ -100,9 +100,10 @@
 	dCONSTANT	.req	d0
 	qCONSTANT	.req	q0
 
-	BUF		.req	x0
-	LEN		.req	x1
-	CRC		.req	x2
+	BUF		.req	x19
+	LEN		.req	x20
+	CRC		.req	x21
+	CONST		.req	x22
 
 	vzr		.req	v9
 
@@ -123,7 +124,14 @@ ENTRY(crc32_pmull_le)
 ENTRY(crc32c_pmull_le)
 	adr_l		x3, .Lcrc32c_constants
 
-0:	bic		LEN, LEN, #15
+0:	frame_push	4, 64
+
+	mov		BUF, x0
+	mov		LEN, x1
+	mov		CRC, x2
+	mov		CONST, x3
+
+	bic		LEN, LEN, #15
 	ld1		{v1.16b-v4.16b}, [BUF], #0x40
 	movi		vzr.16b, #0
 	fmov		dCONSTANT, CRC
@@ -132,7 +140,7 @@ ENTRY(crc32c_pmull_le)
 	cmp		LEN, #0x40
 	b.lt		less_64
 
-	ldr		qCONSTANT, [x3]
+	ldr		qCONSTANT, [CONST]
 
 loop_64:		/* 64 bytes Full cache line folding */
 	sub		LEN, LEN, #0x40
@@ -162,10 +170,21 @@ loop_64:		/* 64 bytes Full cache line folding */
 	eor		v4.16b, v4.16b, v8.16b
 
 	cmp		LEN, #0x40
-	b.ge		loop_64
+	b.lt		less_64
+
+	if_will_cond_yield_neon
+	stp		q1, q2, [sp, #.Lframe_local_offset]
+	stp		q3, q4, [sp, #.Lframe_local_offset + 32]
+	do_cond_yield_neon
+	ldp		q1, q2, [sp, #.Lframe_local_offset]
+	ldp		q3, q4, [sp, #.Lframe_local_offset + 32]
+	ldr		qCONSTANT, [CONST]
+	movi		vzr.16b, #0
+	endif_yield_neon
+	b		loop_64
 
 less_64:		/* Folding cache line into 128bit */
-	ldr		qCONSTANT, [x3, #16]
+	ldr		qCONSTANT, [CONST, #16]
 
 	pmull2		v5.1q, v1.2d, vCONSTANT.2d
 	pmull		v1.1q, v1.1d, vCONSTANT.1d
@@ -204,8 +223,8 @@ fold_64:
 	eor		v1.16b, v1.16b, v2.16b
 
 	/* final 32-bit fold */
-	ldr		dCONSTANT, [x3, #32]
-	ldr		d3, [x3, #40]
+	ldr		dCONSTANT, [CONST, #32]
+	ldr		d3, [CONST, #40]
 
 	ext		v2.16b, v1.16b, vzr.16b, #4
 	and		v1.16b, v1.16b, v3.16b
@@ -213,7 +232,7 @@ fold_64:
 	eor		v1.16b, v1.16b, v2.16b
 
 	/* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
-	ldr		qCONSTANT, [x3, #48]
+	ldr		qCONSTANT, [CONST, #48]
 
 	and		v2.16b, v1.16b, v3.16b
 	ext		v2.16b, vzr.16b, v2.16b, #8
@@ -223,6 +242,7 @@ fold_64:
 	eor		v1.16b, v1.16b, v2.16b
 	mov		w0, v1.s[1]
 
+	frame_pop
 	ret
 ENDPROC(crc32_pmull_le)
 ENDPROC(crc32c_pmull_le)
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index f179c01bd55c..663ea71cdb38 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -74,13 +74,19 @@
 	.text
 	.cpu		generic+crypto
 
-	arg1_low32	.req	w0
-	arg2		.req	x1
-	arg3		.req	x2
+	arg1_low32	.req	w19
+	arg2		.req	x20
+	arg3		.req	x21
 
 	vzr		.req	v13
 
 ENTRY(crc_t10dif_pmull)
+	frame_push	3, 128
+
+	mov		arg1_low32, w0
+	mov		arg2, x1
+	mov		arg3, x2
+
 	movi		vzr.16b, #0		// init zero register
 
 	// adjust the 16-bit initial_crc value, scale it to 32 bits
@@ -175,8 +181,25 @@ CPU_LE(	ext		v12.16b, v12.16b, v12.16b, #8	)
 	subs		arg3, arg3, #128
 
 	// check if there is another 64B in the buffer to be able to fold
-	b.ge		_fold_64_B_loop
+	b.lt		_fold_64_B_end
+
+	if_will_cond_yield_neon
+	stp		q0, q1, [sp, #.Lframe_local_offset]
+	stp		q2, q3, [sp, #.Lframe_local_offset + 32]
+	stp		q4, q5, [sp, #.Lframe_local_offset + 64]
+	stp		q6, q7, [sp, #.Lframe_local_offset + 96]
+	do_cond_yield_neon
+	ldp		q0, q1, [sp, #.Lframe_local_offset]
+	ldp		q2, q3, [sp, #.Lframe_local_offset + 32]
+	ldp		q4, q5, [sp, #.Lframe_local_offset + 64]
+	ldp		q6, q7, [sp, #.Lframe_local_offset + 96]
+	ldr_l		q10, rk3, x8
+	movi		vzr.16b, #0		// init zero register
+	endif_yield_neon
+
+	b		_fold_64_B_loop
 
+_fold_64_B_end:
 	// at this point, the buffer pointer is pointing at the last y Bytes
 	// of the buffer the 64B of folded data is in 4 of the vector
 	// registers: v0, v1, v2, v3
@@ -304,6 +327,7 @@ _barrett:
 _cleanup:
 	// scale the result back to 16 bits
 	lsr		x0, x0, #16
+	frame_pop
 	ret
 
 _less_than_128:
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 11ebf1ae248a..dcffb9e77589 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -213,22 +213,31 @@
 	.endm
 
 	.macro		__pmull_ghash, pn
-	ld1		{SHASH.2d}, [x3]
-	ld1		{XL.2d}, [x1]
+	frame_push	5
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+
+0:	ld1		{SHASH.2d}, [x22]
+	ld1		{XL.2d}, [x20]
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
 	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	__pmull_pre_\pn
 
 	/* do the head block first, if supplied */
-	cbz		x4, 0f
-	ld1		{T1.2d}, [x4]
-	b		1f
+	cbz		x23, 1f
+	ld1		{T1.2d}, [x23]
+	mov		x23, xzr
+	b		2f
 
-0:	ld1		{T1.2d}, [x2], #16
-	sub		w0, w0, #1
+1:	ld1		{T1.2d}, [x21], #16
+	sub		w19, w19, #1
 
-1:	/* multiply XL by SHASH in GF(2^128) */
+2:	/* multiply XL by SHASH in GF(2^128) */
 CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	ext		T2.16b, XL.16b, XL.16b, #8
@@ -250,9 +259,18 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 	eor		T2.16b, T2.16b, XH.16b
 	eor		XL.16b, XL.16b, T2.16b
 
-	cbnz		w0, 0b
+	cbz		w19, 3f
+
+	if_will_cond_yield_neon
+	st1		{XL.2d}, [x20]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b		1b
 
-	st1		{XL.2d}, [x1]
+3:	st1		{XL.2d}, [x20]
+	frame_pop
 	ret
 	.endm
 
@@ -304,38 +322,55 @@ ENDPROC(pmull_ghash_update_p8)
 	.endm
 
 	.macro		pmull_gcm_do_crypt, enc
-	ld1		{SHASH.2d}, [x4]
-	ld1		{XL.2d}, [x1]
-	ldr		x8, [x5, #8]			// load lower counter
+	frame_push	10
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+	mov		x25, x6
+	mov		x26, x7
+	.if		\enc == 1
+	ldr		x27, [sp, #96]			// first stacked arg
+	.endif
+
+	ldr		x28, [x24, #8]			// load lower counter
+CPU_LE(	rev		x28, x28	)
+
+0:	mov		x0, x25
+	load_round_keys	w26, x0
+	ld1		{SHASH.2d}, [x23]
+	ld1		{XL.2d}, [x20]
 
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
-CPU_LE(	rev		x8, x8		)
 	shl		MASK.2d, MASK.2d, #57
 	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	.if		\enc == 1
-	ld1		{KS.16b}, [x7]
+	ld1		{KS.16b}, [x27]
 	.endif
 
-0:	ld1		{CTR.8b}, [x5]			// load upper counter
-	ld1		{INP.16b}, [x3], #16
-	rev		x9, x8
-	add		x8, x8, #1
-	sub		w0, w0, #1
+1:	ld1		{CTR.8b}, [x24]			// load upper counter
+	ld1		{INP.16b}, [x22], #16
+	rev		x9, x28
+	add		x28, x28, #1
+	sub		w19, w19, #1
 	ins		CTR.d[1], x9			// set lower counter
 
 	.if		\enc == 1
 	eor		INP.16b, INP.16b, KS.16b	// encrypt input
-	st1		{INP.16b}, [x2], #16
+	st1		{INP.16b}, [x21], #16
 	.endif
 
 	rev64		T1.16b, INP.16b
 
-	cmp		w6, #12
-	b.ge		2f				// AES-192/256?
+	cmp		w26, #12
+	b.ge		4f				// AES-192/256?
 
-1:	enc_round	CTR, v21
+2:	enc_round	CTR, v21
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 	ext		IN1.16b, T1.16b, T1.16b, #8
@@ -390,27 +425,39 @@ CPU_LE(	rev		x8, x8		)
 
 	.if		\enc == 0
 	eor		INP.16b, INP.16b, KS.16b
-	st1		{INP.16b}, [x2], #16
+	st1		{INP.16b}, [x21], #16
 	.endif
 
-	cbnz		w0, 0b
+	cbz		w19, 3f
 
-CPU_LE(	rev		x8, x8		)
-	st1		{XL.2d}, [x1]
-	str		x8, [x5, #8]			// store lower counter
+	if_will_cond_yield_neon
+	st1		{XL.2d}, [x20]
+	.if		\enc == 1
+	st1		{KS.16b}, [x27]
+	.endif
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
 
+	b		1b
+
+3:	st1		{XL.2d}, [x20]
 	.if		\enc == 1
-	st1		{KS.16b}, [x7]
+	st1		{KS.16b}, [x27]
 	.endif
 
+CPU_LE(	rev		x28, x28	)
+	str		x28, [x24, #8]			// store lower counter
+
+	frame_pop
 	ret
 
-2:	b.eq		3f				// AES-192?
+4:	b.eq		5f				// AES-192?
 	enc_round	CTR, v17
 	enc_round	CTR, v18
-3:	enc_round	CTR, v19
+5:	enc_round	CTR, v19
 	enc_round	CTR, v20
-	b		1b
+	b		2b
 	.endm
 
 	/*
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index cfc9c92814fd..7cf0b1aa6ea8 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -63,11 +63,12 @@ static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
 
 asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[],
 				  const u8 src[], struct ghash_key const *k,
-				  u8 ctr[], int rounds, u8 ks[]);
+				  u8 ctr[], u32 const rk[], int rounds,
+				  u8 ks[]);
 
 asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[],
 				  const u8 src[], struct ghash_key const *k,
-				  u8 ctr[], int rounds);
+				  u8 ctr[], u32 const rk[], int rounds);
 
 asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[],
 					u32 const rk[], int rounds);
@@ -368,26 +369,29 @@ static int gcm_encrypt(struct aead_request *req)
 		pmull_gcm_encrypt_block(ks, iv, NULL,
 					num_rounds(&ctx->aes_key));
 		put_unaligned_be32(3, iv + GCM_IV_SIZE);
+		kernel_neon_end();
 
-		err = skcipher_walk_aead_encrypt(&walk, req, true);
+		err = skcipher_walk_aead_encrypt(&walk, req, false);
 
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
+			kernel_neon_begin();
 			pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
 					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, num_rounds(&ctx->aes_key), ks);
+					  iv, ctx->aes_key.key_enc,
+					  num_rounds(&ctx->aes_key), ks);
+			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
 		}
-		kernel_neon_end();
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
 				    num_rounds(&ctx->aes_key));
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
-		err = skcipher_walk_aead_encrypt(&walk, req, true);
+		err = skcipher_walk_aead_encrypt(&walk, req, false);
 
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -467,15 +471,19 @@ static int gcm_decrypt(struct aead_request *req)
 		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc,
 					num_rounds(&ctx->aes_key));
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
+		kernel_neon_end();
 
-		err = skcipher_walk_aead_decrypt(&walk, req, true);
+		err = skcipher_walk_aead_decrypt(&walk, req, false);
 
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
+			kernel_neon_begin();
 			pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
 					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, num_rounds(&ctx->aes_key));
+					  iv, ctx->aes_key.key_enc,
+					  num_rounds(&ctx->aes_key));
+			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
@@ -483,14 +491,12 @@ static int gcm_decrypt(struct aead_request *req)
 		if (walk.nbytes)
 			pmull_gcm_encrypt_block(iv, iv, NULL,
 						num_rounds(&ctx->aes_key));
-
-		kernel_neon_end();
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
 				    num_rounds(&ctx->aes_key));
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
-		err = skcipher_walk_aead_decrypt(&walk, req, true);
+		err = skcipher_walk_aead_decrypt(&walk, req, false);
 
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 46049850727d..78eb35fb5056 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -69,30 +69,36 @@
 	 *			  int blocks)
 	 */
 ENTRY(sha1_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
 	/* load round constants */
-	loadrc		k0.4s, 0x5a827999, w6
+0:	loadrc		k0.4s, 0x5a827999, w6
 	loadrc		k1.4s, 0x6ed9eba1, w6
 	loadrc		k2.4s, 0x8f1bbcdc, w6
 	loadrc		k3.4s, 0xca62c1d6, w6
 
 	/* load state */
-	ld1		{dgav.4s}, [x0]
-	ldr		dgb, [x0, #16]
+	ld1		{dgav.4s}, [x19]
+	ldr		dgb, [x19, #16]
 
 	/* load sha1_ce_state::finalize */
 	ldr_l		w4, sha1_ce_offsetof_finalize, x4
-	ldr		w4, [x0, x4]
+	ldr		w4, [x19, x4]
 
 	/* load input */
-0:	ld1		{v8.4s-v11.4s}, [x1], #64
-	sub		w2, w2, #1
+1:	ld1		{v8.4s-v11.4s}, [x20], #64
+	sub		w21, w21, #1
 
 CPU_LE(	rev32		v8.16b, v8.16b		)
 CPU_LE(	rev32		v9.16b, v9.16b		)
 CPU_LE(	rev32		v10.16b, v10.16b	)
 CPU_LE(	rev32		v11.16b, v11.16b	)
 
-1:	add		t0.4s, v8.4s, k0.4s
+2:	add		t0.4s, v8.4s, k0.4s
 	mov		dg0v.16b, dgav.16b
 
 	add_update	c, ev, k0,  8,  9, 10, 11, dgb
@@ -123,16 +129,25 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	add		dgbv.2s, dgbv.2s, dg1v.2s
 	add		dgav.4s, dgav.4s, dg0v.4s
 
-	cbnz		w2, 0b
+	cbz		w21, 3f
+
+	if_will_cond_yield_neon
+	st1		{dgav.4s}, [x19]
+	str		dgb, [x19, #16]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b		1b
 
 	/*
 	 * Final block: add padding and total bit count.
 	 * Skip if the input size was not a round multiple of the block size,
 	 * the padding is handled by the C code in that case.
 	 */
-	cbz		x4, 3f
+3:	cbz		x4, 4f
 	ldr_l		w4, sha1_ce_offsetof_count, x4
-	ldr		x4, [x0, x4]
+	ldr		x4, [x19, x4]
 	movi		v9.2d, #0
 	mov		x8, #0x80000000
 	movi		v10.2d, #0
@@ -141,10 +156,11 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	mov		x4, #0
 	mov		v11.d[0], xzr
 	mov		v11.d[1], x7
-	b		1b
+	b		2b
 
 	/* store new state */
-3:	st1		{dgav.4s}, [x0]
-	str		dgb, [x0, #16]
+4:	st1		{dgav.4s}, [x19]
+	str		dgb, [x19, #16]
+	frame_pop
 	ret
 ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 4c3c89b812ce..cd8b36412469 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -79,30 +79,36 @@
 	 */
 	.text
 ENTRY(sha2_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
 	/* load round constants */
-	adr_l		x8, .Lsha2_rcon
+0:	adr_l		x8, .Lsha2_rcon
 	ld1		{ v0.4s- v3.4s}, [x8], #64
 	ld1		{ v4.4s- v7.4s}, [x8], #64
 	ld1		{ v8.4s-v11.4s}, [x8], #64
 	ld1		{v12.4s-v15.4s}, [x8]
 
 	/* load state */
-	ld1		{dgav.4s, dgbv.4s}, [x0]
+	ld1		{dgav.4s, dgbv.4s}, [x19]
 
 	/* load sha256_ce_state::finalize */
 	ldr_l		w4, sha256_ce_offsetof_finalize, x4
-	ldr		w4, [x0, x4]
+	ldr		w4, [x19, x4]
 
 	/* load input */
-0:	ld1		{v16.4s-v19.4s}, [x1], #64
-	sub		w2, w2, #1
+1:	ld1		{v16.4s-v19.4s}, [x20], #64
+	sub		w21, w21, #1
 
 CPU_LE(	rev32		v16.16b, v16.16b	)
 CPU_LE(	rev32		v17.16b, v17.16b	)
 CPU_LE(	rev32		v18.16b, v18.16b	)
 CPU_LE(	rev32		v19.16b, v19.16b	)
 
-1:	add		t0.4s, v16.4s, v0.4s
+2:	add		t0.4s, v16.4s, v0.4s
 	mov		dg0v.16b, dgav.16b
 	mov		dg1v.16b, dgbv.16b
 
@@ -131,16 +137,24 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	add		dgbv.4s, dgbv.4s, dg1v.4s
 
 	/* handled all input blocks? */
-	cbnz		w2, 0b
+	cbz		w21, 3f
+
+	if_will_cond_yield_neon
+	st1		{dgav.4s, dgbv.4s}, [x19]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b		1b
 
 	/*
 	 * Final block: add padding and total bit count.
 	 * Skip if the input size was not a round multiple of the block size,
 	 * the padding is handled by the C code in that case.
 	 */
-	cbz		x4, 3f
+3:	cbz		x4, 4f
 	ldr_l		w4, sha256_ce_offsetof_count, x4
-	ldr		x4, [x0, x4]
+	ldr		x4, [x19, x4]
 	movi		v17.2d, #0
 	mov		x8, #0x80000000
 	movi		v18.2d, #0
@@ -149,9 +163,10 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	mov		x4, #0
 	mov		v19.d[0], xzr
 	mov		v19.d[1], x7
-	b		1b
+	b		2b
 
 	/* store new state */
-3:	st1		{dgav.4s, dgbv.4s}, [x0]
+4:	st1		{dgav.4s, dgbv.4s}, [x19]
+	frame_pop
 	ret
 ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha256-core.S_shipped b/arch/arm64/crypto/sha256-core.S_shipped
index 3ce82cc860bc..7c7ce2e3bad6 100644
--- a/arch/arm64/crypto/sha256-core.S_shipped
+++ b/arch/arm64/crypto/sha256-core.S_shipped
@@ -1,3 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// This code is taken from the OpenSSL project but the author (Andy Polyakov)
+// has relicensed it under the GPLv2. Therefore this program is free software;
+// you can redistribute it and/or modify it under the terms of the GNU General
+// Public License version 2 as published by the Free Software Foundation.
+//
+// The original headers, including the original license headers, are
+// included below for completeness.
+
 // Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
 //
 // Licensed under the OpenSSL license (the "License").  You may not use
@@ -10,8 +20,6 @@
 // project. The module is, however, dual licensed under OpenSSL and
 // CRYPTOGAMS licenses depending on where you obtain it. For further
 // details see http://www.openssl.org/~appro/cryptogams/.
-//
-// Permission to use under GPLv2 terms is granted.
 // ====================================================================
 //
 // SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
index 332ad7530690..a7d587fa54f6 100644
--- a/arch/arm64/crypto/sha3-ce-core.S
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -41,9 +41,16 @@
 	 */
 	.text
 ENTRY(sha3_ce_transform)
-	/* load state */
-	add	x8, x0, #32
-	ld1	{ v0.1d- v3.1d}, [x0]
+	frame_push	4
+
+	mov	x19, x0
+	mov	x20, x1
+	mov	x21, x2
+	mov	x22, x3
+
+0:	/* load state */
+	add	x8, x19, #32
+	ld1	{ v0.1d- v3.1d}, [x19]
 	ld1	{ v4.1d- v7.1d}, [x8], #32
 	ld1	{ v8.1d-v11.1d}, [x8], #32
 	ld1	{v12.1d-v15.1d}, [x8], #32
@@ -51,13 +58,13 @@ ENTRY(sha3_ce_transform)
 	ld1	{v20.1d-v23.1d}, [x8], #32
 	ld1	{v24.1d}, [x8]
 
-0:	sub	w2, w2, #1
+1:	sub	w21, w21, #1
 	mov	w8, #24
 	adr_l	x9, .Lsha3_rcon
 
 	/* load input */
-	ld1	{v25.8b-v28.8b}, [x1], #32
-	ld1	{v29.8b-v31.8b}, [x1], #24
+	ld1	{v25.8b-v28.8b}, [x20], #32
+	ld1	{v29.8b-v31.8b}, [x20], #24
 	eor	v0.8b, v0.8b, v25.8b
 	eor	v1.8b, v1.8b, v26.8b
 	eor	v2.8b, v2.8b, v27.8b
@@ -66,10 +73,10 @@ ENTRY(sha3_ce_transform)
 	eor	v5.8b, v5.8b, v30.8b
 	eor	v6.8b, v6.8b, v31.8b
 
-	tbnz	x3, #6, 2f		// SHA3-512
+	tbnz	x22, #6, 3f		// SHA3-512
 
-	ld1	{v25.8b-v28.8b}, [x1], #32
-	ld1	{v29.8b-v30.8b}, [x1], #16
+	ld1	{v25.8b-v28.8b}, [x20], #32
+	ld1	{v29.8b-v30.8b}, [x20], #16
 	eor	 v7.8b,  v7.8b, v25.8b
 	eor	 v8.8b,  v8.8b, v26.8b
 	eor	 v9.8b,  v9.8b, v27.8b
@@ -77,34 +84,34 @@ ENTRY(sha3_ce_transform)
 	eor	v11.8b, v11.8b, v29.8b
 	eor	v12.8b, v12.8b, v30.8b
 
-	tbnz	x3, #4, 1f		// SHA3-384 or SHA3-224
+	tbnz	x22, #4, 2f		// SHA3-384 or SHA3-224
 
 	// SHA3-256
-	ld1	{v25.8b-v28.8b}, [x1], #32
+	ld1	{v25.8b-v28.8b}, [x20], #32
 	eor	v13.8b, v13.8b, v25.8b
 	eor	v14.8b, v14.8b, v26.8b
 	eor	v15.8b, v15.8b, v27.8b
 	eor	v16.8b, v16.8b, v28.8b
-	b	3f
+	b	4f
 
-1:	tbz	x3, #2, 3f		// bit 2 cleared? SHA-384
+2:	tbz	x22, #2, 4f		// bit 2 cleared? SHA-384
 
 	// SHA3-224
-	ld1	{v25.8b-v28.8b}, [x1], #32
-	ld1	{v29.8b}, [x1], #8
+	ld1	{v25.8b-v28.8b}, [x20], #32
+	ld1	{v29.8b}, [x20], #8
 	eor	v13.8b, v13.8b, v25.8b
 	eor	v14.8b, v14.8b, v26.8b
 	eor	v15.8b, v15.8b, v27.8b
 	eor	v16.8b, v16.8b, v28.8b
 	eor	v17.8b, v17.8b, v29.8b
-	b	3f
+	b	4f
 
 	// SHA3-512
-2:	ld1	{v25.8b-v26.8b}, [x1], #16
+3:	ld1	{v25.8b-v26.8b}, [x20], #16
 	eor	 v7.8b,  v7.8b, v25.8b
 	eor	 v8.8b,  v8.8b, v26.8b
 
-3:	sub	w8, w8, #1
+4:	sub	w8, w8, #1
 
 	eor3	v29.16b,  v4.16b,  v9.16b, v14.16b
 	eor3	v26.16b,  v1.16b,  v6.16b, v11.16b
@@ -183,17 +190,33 @@ ENTRY(sha3_ce_transform)
 
 	eor	 v0.16b,  v0.16b, v31.16b
 
-	cbnz	w8, 3b
-	cbnz	w2, 0b
+	cbnz	w8, 4b
+	cbz	w21, 5f
+
+	if_will_cond_yield_neon
+	add	x8, x19, #32
+	st1	{ v0.1d- v3.1d}, [x19]
+	st1	{ v4.1d- v7.1d}, [x8], #32
+	st1	{ v8.1d-v11.1d}, [x8], #32
+	st1	{v12.1d-v15.1d}, [x8], #32
+	st1	{v16.1d-v19.1d}, [x8], #32
+	st1	{v20.1d-v23.1d}, [x8], #32
+	st1	{v24.1d}, [x8]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b	1b
 
 	/* save state */
-	st1	{ v0.1d- v3.1d}, [x0], #32
-	st1	{ v4.1d- v7.1d}, [x0], #32
-	st1	{ v8.1d-v11.1d}, [x0], #32
-	st1	{v12.1d-v15.1d}, [x0], #32
-	st1	{v16.1d-v19.1d}, [x0], #32
-	st1	{v20.1d-v23.1d}, [x0], #32
-	st1	{v24.1d}, [x0]
+5:	st1	{ v0.1d- v3.1d}, [x19], #32
+	st1	{ v4.1d- v7.1d}, [x19], #32
+	st1	{ v8.1d-v11.1d}, [x19], #32
+	st1	{v12.1d-v15.1d}, [x19], #32
+	st1	{v16.1d-v19.1d}, [x19], #32
+	st1	{v20.1d-v23.1d}, [x19], #32
+	st1	{v24.1d}, [x19]
+	frame_pop
 	ret
 ENDPROC(sha3_ce_transform)
 
diff --git a/arch/arm64/crypto/sha512-armv8.pl b/arch/arm64/crypto/sha512-armv8.pl
index c55efb308544..2d8655d5b1af 100644
--- a/arch/arm64/crypto/sha512-armv8.pl
+++ b/arch/arm64/crypto/sha512-armv8.pl
@@ -1,4 +1,14 @@
 #! /usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore this program is free software;
+# you can redistribute it and/or modify it under the terms of the GNU General
+# Public License version 2 as published by the Free Software Foundation.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
+
 # Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
 #
 # Licensed under the OpenSSL license (the "License").  You may not use
@@ -11,8 +21,6 @@
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
 # details see http://www.openssl.org/~appro/cryptogams/.
-#
-# Permission to use under GPLv2 terms is granted.
 # ====================================================================
 #
 # SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S
index 7f3bca5c59a2..ce65e3abe4f2 100644
--- a/arch/arm64/crypto/sha512-ce-core.S
+++ b/arch/arm64/crypto/sha512-ce-core.S
@@ -107,17 +107,23 @@
 	 */
 	.text
 ENTRY(sha512_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
 	/* load state */
-	ld1		{v8.2d-v11.2d}, [x0]
+0:	ld1		{v8.2d-v11.2d}, [x19]
 
 	/* load first 4 round constants */
 	adr_l		x3, .Lsha512_rcon
 	ld1		{v20.2d-v23.2d}, [x3], #64
 
 	/* load input */
-0:	ld1		{v12.2d-v15.2d}, [x1], #64
-	ld1		{v16.2d-v19.2d}, [x1], #64
-	sub		w2, w2, #1
+1:	ld1		{v12.2d-v15.2d}, [x20], #64
+	ld1		{v16.2d-v19.2d}, [x20], #64
+	sub		w21, w21, #1
 
 CPU_LE(	rev64		v12.16b, v12.16b	)
 CPU_LE(	rev64		v13.16b, v13.16b	)
@@ -196,9 +202,18 @@ CPU_LE(	rev64		v19.16b, v19.16b	)
 	add		v11.2d, v11.2d, v3.2d
 
 	/* handled all input blocks? */
-	cbnz		w2, 0b
+	cbz		w21, 3f
+
+	if_will_cond_yield_neon
+	st1		{v8.2d-v11.2d}, [x19]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b		1b
 
 	/* store new state */
-3:	st1		{v8.2d-v11.2d}, [x0]
+3:	st1		{v8.2d-v11.2d}, [x19]
+	frame_pop
 	ret
 ENDPROC(sha512_ce_transform)
diff --git a/arch/arm64/crypto/sha512-core.S_shipped b/arch/arm64/crypto/sha512-core.S_shipped
index bd0f59f06c9d..e063a6106720 100644
--- a/arch/arm64/crypto/sha512-core.S_shipped
+++ b/arch/arm64/crypto/sha512-core.S_shipped
@@ -1,3 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// This code is taken from the OpenSSL project but the author (Andy Polyakov)
+// has relicensed it under the GPLv2. Therefore this program is free software;
+// you can redistribute it and/or modify it under the terms of the GNU General
+// Public License version 2 as published by the Free Software Foundation.
+//
+// The original headers, including the original license headers, are
+// included below for completeness.
+
 // Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
 //
 // Licensed under the OpenSSL license (the "License").  You may not use
@@ -10,8 +20,6 @@
 // project. The module is, however, dual licensed under OpenSSL and
 // CRYPTOGAMS licenses depending on where you obtain it. For further
 // details see http://www.openssl.org/~appro/cryptogams/.
-//
-// Permission to use under GPLv2 terms is granted.
 // ====================================================================
 //
 // SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sm4-ce-core.S b/arch/arm64/crypto/sm4-ce-core.S
new file mode 100644
index 000000000000..af3bfbc3f4d4
--- /dev/null
+++ b/arch/arm64/crypto/sm4-ce-core.S
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.irp		b, 0, 1, 2, 3, 4, 5, 6, 7, 8
+	.set		.Lv\b\().4s, \b
+	.endr
+
+	.macro		sm4e, rd, rn
+	.inst		0xcec08400 | .L\rd | (.L\rn << 5)
+	.endm
+
+	/*
+	 * void sm4_ce_do_crypt(const u32 *rk, u32 *out, const u32 *in);
+	 */
+	.text
+ENTRY(sm4_ce_do_crypt)
+	ld1		{v8.4s}, [x2]
+	ld1		{v0.4s-v3.4s}, [x0], #64
+CPU_LE(	rev32		v8.16b, v8.16b		)
+	ld1		{v4.4s-v7.4s}, [x0]
+	sm4e		v8.4s, v0.4s
+	sm4e		v8.4s, v1.4s
+	sm4e		v8.4s, v2.4s
+	sm4e		v8.4s, v3.4s
+	sm4e		v8.4s, v4.4s
+	sm4e		v8.4s, v5.4s
+	sm4e		v8.4s, v6.4s
+	sm4e		v8.4s, v7.4s
+	rev64		v8.4s, v8.4s
+	ext		v8.16b, v8.16b, v8.16b, #8
+CPU_LE(	rev32		v8.16b, v8.16b		)
+	st1		{v8.4s}, [x1]
+	ret
+ENDPROC(sm4_ce_do_crypt)
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
new file mode 100644
index 000000000000..b7fb5274b250
--- /dev/null
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/sm4.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/types.h>
+
+MODULE_ALIAS_CRYPTO("sm4");
+MODULE_ALIAS_CRYPTO("sm4-ce");
+MODULE_DESCRIPTION("SM4 symmetric cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sm4_ce_do_crypt(const u32 *rk, void *out, const void *in);
+
+static void sm4_ce_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!may_use_simd()) {
+		crypto_sm4_encrypt(tfm, out, in);
+	} else {
+		kernel_neon_begin();
+		sm4_ce_do_crypt(ctx->rkey_enc, out, in);
+		kernel_neon_end();
+	}
+}
+
+static void sm4_ce_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!may_use_simd()) {
+		crypto_sm4_decrypt(tfm, out, in);
+	} else {
+		kernel_neon_begin();
+		sm4_ce_do_crypt(ctx->rkey_dec, out, in);
+		kernel_neon_end();
+	}
+}
+
+static struct crypto_alg sm4_ce_alg = {
+	.cra_name			= "sm4",
+	.cra_driver_name		= "sm4-ce",
+	.cra_priority			= 200,
+	.cra_flags			= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize			= SM4_BLOCK_SIZE,
+	.cra_ctxsize			= sizeof(struct crypto_sm4_ctx),
+	.cra_module			= THIS_MODULE,
+	.cra_u.cipher = {
+		.cia_min_keysize	= SM4_KEY_SIZE,
+		.cia_max_keysize	= SM4_KEY_SIZE,
+		.cia_setkey		= crypto_sm4_set_key,
+		.cia_encrypt		= sm4_ce_encrypt,
+		.cia_decrypt		= sm4_ce_decrypt
+	}
+};
+
+static int __init sm4_ce_mod_init(void)
+{
+	return crypto_register_alg(&sm4_ce_alg);
+}
+
+static void __exit sm4_ce_mod_fini(void)
+{
+	crypto_unregister_alg(&sm4_ce_alg);
+}
+
+module_cpu_feature_match(SM3, sm4_ce_mod_init);
+module_exit(sm4_ce_mod_fini);
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 9ef0797380cb..f9b0b09153e0 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -117,7 +117,7 @@ static inline void atomic_and(int i, atomic_t *v)
 	/* LSE atomics */
 	"	mvn	%w[i], %w[i]\n"
 	"	stclr	%w[i], %[v]")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: [i] "+&r" (w0), [v] "+Q" (v->counter)
 	: "r" (x1)
 	: __LL_SC_CLOBBERS);
 }
@@ -135,7 +135,7 @@ static inline int atomic_fetch_and##name(int i, atomic_t *v)		\
 	/* LSE atomics */						\
 	"	mvn	%w[i], %w[i]\n"					\
 	"	ldclr" #mb "	%w[i], %w[i], %[v]")			\
-	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: [i] "+&r" (w0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
 	: __LL_SC_CLOBBERS, ##cl);					\
 									\
@@ -161,7 +161,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	/* LSE atomics */
 	"	neg	%w[i], %w[i]\n"
 	"	stadd	%w[i], %[v]")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
+	: [i] "+&r" (w0), [v] "+Q" (v->counter)
 	: "r" (x1)
 	: __LL_SC_CLOBBERS);
 }
@@ -180,7 +180,7 @@ static inline int atomic_sub_return##name(int i, atomic_t *v)		\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], w30, %[v]\n"			\
 	"	add	%w[i], %w[i], w30")				\
-	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: [i] "+&r" (w0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
 	: __LL_SC_CLOBBERS , ##cl);					\
 									\
@@ -207,7 +207,7 @@ static inline int atomic_fetch_sub##name(int i, atomic_t *v)		\
 	/* LSE atomics */						\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[i], %[v]")			\
-	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: [i] "+&r" (w0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
 	: __LL_SC_CLOBBERS, ##cl);					\
 									\
@@ -314,7 +314,7 @@ static inline void atomic64_and(long i, atomic64_t *v)
 	/* LSE atomics */
 	"	mvn	%[i], %[i]\n"
 	"	stclr	%[i], %[v]")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: [i] "+&r" (x0), [v] "+Q" (v->counter)
 	: "r" (x1)
 	: __LL_SC_CLOBBERS);
 }
@@ -332,7 +332,7 @@ static inline long atomic64_fetch_and##name(long i, atomic64_t *v)	\
 	/* LSE atomics */						\
 	"	mvn	%[i], %[i]\n"					\
 	"	ldclr" #mb "	%[i], %[i], %[v]")			\
-	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: [i] "+&r" (x0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
 	: __LL_SC_CLOBBERS, ##cl);					\
 									\
@@ -358,7 +358,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 	/* LSE atomics */
 	"	neg	%[i], %[i]\n"
 	"	stadd	%[i], %[v]")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
+	: [i] "+&r" (x0), [v] "+Q" (v->counter)
 	: "r" (x1)
 	: __LL_SC_CLOBBERS);
 }
@@ -377,7 +377,7 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v)	\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], x30, %[v]\n"			\
 	"	add	%[i], %[i], x30")				\
-	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: [i] "+&r" (x0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
 	: __LL_SC_CLOBBERS, ##cl);					\
 									\
@@ -404,7 +404,7 @@ static inline long atomic64_fetch_sub##name(long i, atomic64_t *v)	\
 	/* LSE atomics */						\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %[i], %[v]")			\
-	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: [i] "+&r" (x0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
 	: __LL_SC_CLOBBERS, ##cl);					\
 									\
@@ -435,7 +435,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	"	sub	x30, x30, %[ret]\n"
 	"	cbnz	x30, 1b\n"
 	"2:")
-	: [ret] "+r" (x0), [v] "+Q" (v->counter)
+	: [ret] "+&r" (x0), [v] "+Q" (v->counter)
 	:
 	: __LL_SC_CLOBBERS, "cc", "memory");
 
@@ -516,7 +516,7 @@ static inline long __cmpxchg_double##name(unsigned long old1,		\
 	"	eor	%[old1], %[old1], %[oldval1]\n"			\
 	"	eor	%[old2], %[old2], %[oldval2]\n"			\
 	"	orr	%[old1], %[old1], %[old2]")			\
-	: [old1] "+r" (x0), [old2] "+r" (x1),				\
+	: [old1] "+&r" (x0), [old2] "+&r" (x1),				\
 	  [v] "+Q" (*(unsigned long *)ptr)				\
 	: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4),		\
 	  [oldval1] "r" (oldval1), [oldval2] "r" (oldval2)		\
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index c00c62e1a4a3..1a037b94eba1 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -34,7 +34,6 @@
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
-typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_pid_t;
 typedef u16		__compat_uid_t;
@@ -66,16 +65,6 @@ typedef u32		compat_ulong_t;
 typedef u64		compat_u64;
 typedef u32		compat_uptr_t;
 
-struct compat_timespec {
-	compat_time_t	tv_sec;
-	s32		tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t	tv_sec;
-	s32		tv_usec;
-};
-
 struct compat_stat {
 #ifdef __AARCH64EB__
 	short		st_dev;
@@ -192,10 +181,10 @@ struct compat_ipc64_perm {
 
 struct compat_semid64_ds {
 	struct compat_ipc64_perm sem_perm;
-	compat_time_t  sem_otime;
-	compat_ulong_t __unused1;
-	compat_time_t  sem_ctime;
-	compat_ulong_t __unused2;
+	compat_ulong_t sem_otime;
+	compat_ulong_t sem_otime_high;
+	compat_ulong_t sem_ctime;
+	compat_ulong_t sem_ctime_high;
 	compat_ulong_t sem_nsems;
 	compat_ulong_t __unused3;
 	compat_ulong_t __unused4;
@@ -203,12 +192,12 @@ struct compat_semid64_ds {
 
 struct compat_msqid64_ds {
 	struct compat_ipc64_perm msg_perm;
-	compat_time_t  msg_stime;
-	compat_ulong_t __unused1;
-	compat_time_t  msg_rtime;
-	compat_ulong_t __unused2;
-	compat_time_t  msg_ctime;
-	compat_ulong_t __unused3;
+	compat_ulong_t msg_stime;
+	compat_ulong_t msg_stime_high;
+	compat_ulong_t msg_rtime;
+	compat_ulong_t msg_rtime_high;
+	compat_ulong_t msg_ctime;
+	compat_ulong_t msg_ctime_high;
 	compat_ulong_t msg_cbytes;
 	compat_ulong_t msg_qnum;
 	compat_ulong_t msg_qbytes;
@@ -221,12 +210,12 @@ struct compat_msqid64_ds {
 struct compat_shmid64_ds {
 	struct compat_ipc64_perm shm_perm;
 	compat_size_t  shm_segsz;
-	compat_time_t  shm_atime;
-	compat_ulong_t __unused1;
-	compat_time_t  shm_dtime;
-	compat_ulong_t __unused2;
-	compat_time_t  shm_ctime;
-	compat_ulong_t __unused3;
+	compat_ulong_t shm_atime;
+	compat_ulong_t shm_atime_high;
+	compat_ulong_t shm_dtime;
+	compat_ulong_t shm_dtime_high;
+	compat_ulong_t shm_ctime;
+	compat_ulong_t shm_ctime_high;
 	compat_pid_t   shm_cpid;
 	compat_pid_t   shm_lpid;
 	compat_ulong_t shm_nattch;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 30014a9f8f2b..ea690b3562af 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
 #define ARM_CPU_IMP_CAVIUM		0x43
 #define ARM_CPU_IMP_BRCM		0x42
 #define ARM_CPU_IMP_QCOM		0x51
+#define ARM_CPU_IMP_NVIDIA		0x4E
 
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
@@ -99,6 +100,9 @@
 #define QCOM_CPU_PART_FALKOR		0xC00
 #define QCOM_CPU_PART_KRYO		0x200
 
+#define NVIDIA_CPU_PART_DENVER		0x003
+#define NVIDIA_CPU_PART_CARMEL		0x004
+
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -114,6 +118,8 @@
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
+#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 23b33e8ea03a..1dab3a984608 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -333,7 +333,7 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 	} else {
 		u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
 		sctlr |= (1 << 25);
-		vcpu_write_sys_reg(vcpu, SCTLR_EL1, sctlr);
+		vcpu_write_sys_reg(vcpu, sctlr, SCTLR_EL1);
 	}
 }
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index ab46bc70add6..469de8acd06f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -75,6 +75,9 @@ struct kvm_arch {
 
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
+
+	/* Mandated version of PSCI */
+	u32 psci_version;
 };
 
 #define KVM_NR_MEM_OBJS     40
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 082110993647..6128992c2ded 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -360,6 +360,22 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
 }
 
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+				      gpa_t gpa, void *data, unsigned long len)
+{
+	int srcu_idx = srcu_read_lock(&kvm->srcu);
+	int ret = kvm_read_guest(kvm, gpa, data, len);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return ret;
+}
+
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
 /*
  * EL2 vectors can be mapped and rerouted in a number of ways,
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index b6dbbe3123a9..97d0ef12e2ff 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -39,7 +39,7 @@ struct mod_arch_specific {
 u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
 			  Elf64_Sym *sym);
 
-u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val);
+u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val);
 
 #ifdef CONFIG_RANDOMIZE_BASE
 extern u64 module_alloc_base;
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
index 8747f7c5e0e7..9e690686e8aa 100644
--- a/arch/arm64/include/asm/pci.h
+++ b/arch/arm64/include/asm/pci.h
@@ -18,11 +18,6 @@
 #define pcibios_assign_all_busses() \
 	(pci_has_flag(PCI_REASSIGN_ALL_BUS))
 
-/*
- * PCI address space differs from physical memory address space
- */
-#define PCI_DMA_BUS_IS_PHYS	(0)
-
 #define ARCH_GENERIC_PCI_MMAP_RESOURCE	1
 
 extern int isa_dma_bridge_buggy;
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7e2c27e63cd8..7c4c8f318ba9 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -230,7 +230,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	}
 }
 
-extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
+extern void __sync_icache_dcache(pte_t pteval);
 
 /*
  * PTE bits configuration in the presence of hardware Dirty Bit Management
@@ -253,7 +253,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	pte_t old_pte;
 
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
-		__sync_icache_dcache(pte, addr);
+		__sync_icache_dcache(pte);
 
 	/*
 	 * If the existing pte is valid, check for potential race with
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index ebdae15d665d..26c5bd7d88d8 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -122,11 +122,6 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
-	/*
-	 * Ensure prior spin_lock operations to other locks have completed
-	 * on this CPU before we test whether "lock" is locked.
-	 */
-	smp_mb(); /* ^^^ */
 	return !arch_spin_value_unlocked(READ_ONCE(*lock));
 }
 
diff --git a/arch/arm64/include/asm/stat.h b/arch/arm64/include/asm/stat.h
index 15e35598ac40..eab738019707 100644
--- a/arch/arm64/include/asm/stat.h
+++ b/arch/arm64/include/asm/stat.h
@@ -20,6 +20,7 @@
 
 #ifdef CONFIG_COMPAT
 
+#include <linux/compat_time.h>
 #include <asm/compat.h>
 
 /*
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 9abbf3044654..04b3256f8e6d 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -206,6 +206,12 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
 
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r)		(KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+					 KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 66be504edb6c..d894a20b70b2 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -75,3 +75,11 @@ NOKPROBE_SYMBOL(_mcount);
 	/* arm-smccc */
 EXPORT_SYMBOL(__arm_smccc_smc);
 EXPORT_SYMBOL(__arm_smccc_hvc);
+
+	/* tishift.S */
+extern long long __ashlti3(long long a, int b);
+EXPORT_SYMBOL(__ashlti3);
+extern long long __ashrti3(long long a, int b);
+EXPORT_SYMBOL(__ashrti3);
+extern long long __lshrti3(long long a, int b);
+EXPORT_SYMBOL(__lshrti3);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index a900befadfe8..e4a1182deff7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -316,6 +316,7 @@ static const struct midr_range arm64_bp_harden_smccc_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
 	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
 	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
+	MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
 	{},
 };
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 536d572e5596..9d1b06d67c53 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -868,6 +868,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 	static const struct midr_range kpti_safe_list[] = {
 		MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
 		MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+		{ /* sentinel */ }
 	};
 	char const *str = "command line option";
 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 87a35364e750..4bcdd0318729 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -882,7 +882,7 @@ asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 			si_code = FPE_FLTRES;
 	}
 
-	memset(&info, 0, sizeof(info));
+	clear_siginfo(&info);
 	info.si_signo = SIGFPE;
 	info.si_code = si_code;
 	info.si_addr = (void __user *)instruction_pointer(regs);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 74bb56f656ef..413dbe530da8 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -30,7 +30,6 @@
 #include <linux/smp.h>
 #include <linux/uaccess.h>
 
-#include <asm/compat.h>
 #include <asm/current.h>
 #include <asm/debug-monitors.h>
 #include <asm/hw_breakpoint.h>
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index fa3637284a3d..f0690c2ca3e0 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -43,7 +43,7 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
 }
 
 #ifdef CONFIG_ARM64_ERRATUM_843419
-u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val)
+u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val)
 {
 	struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
 							  &mod->arch.init;
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 719fde8dcc19..155fd91e78f4 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -215,7 +215,7 @@ static int reloc_insn_adrp(struct module *mod, __le32 *place, u64 val)
 		insn &= ~BIT(31);
 	} else {
 		/* out of range for ADR -> emit a veneer */
-		val = module_emit_adrp_veneer(mod, place, val & ~0xfff);
+		val = module_emit_veneer_for_adrp(mod, place, val & ~0xfff);
 		if (!val)
 			return -ENOEXEC;
 		insn = aarch64_insn_gen_branch_imm((u64)place, val,
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 1d091d048d04..0bbac612146e 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
 #include <linux/bug.h>
 #include <linux/sched/task_stack.h>
 
-#include <asm/compat.h>
 #include <asm/perf_regs.h>
 #include <asm/ptrace.h>
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 71d99af24ef2..7ff81fed46e1 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -25,6 +25,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task_stack.h>
 #include <linux/mm.h>
+#include <linux/nospec.h>
 #include <linux/smp.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
@@ -249,15 +250,20 @@ static struct perf_event *ptrace_hbp_get_event(unsigned int note_type,
 
 	switch (note_type) {
 	case NT_ARM_HW_BREAK:
-		if (idx < ARM_MAX_BRP)
-			bp = tsk->thread.debug.hbp_break[idx];
+		if (idx >= ARM_MAX_BRP)
+			goto out;
+		idx = array_index_nospec(idx, ARM_MAX_BRP);
+		bp = tsk->thread.debug.hbp_break[idx];
 		break;
 	case NT_ARM_HW_WATCH:
-		if (idx < ARM_MAX_WRP)
-			bp = tsk->thread.debug.hbp_watch[idx];
+		if (idx >= ARM_MAX_WRP)
+			goto out;
+		idx = array_index_nospec(idx, ARM_MAX_WRP);
+		bp = tsk->thread.debug.hbp_watch[idx];
 		break;
 	}
 
+out:
 	return bp;
 }
 
@@ -1458,9 +1464,7 @@ static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num,
 {
 	int ret;
 	u32 kdata;
-	mm_segment_t old_fs = get_fs();
 
-	set_fs(KERNEL_DS);
 	/* Watchpoint */
 	if (num < 0) {
 		ret = compat_ptrace_hbp_get(NT_ARM_HW_WATCH, tsk, num, &kdata);
@@ -1471,7 +1475,6 @@ static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num,
 	} else {
 		ret = compat_ptrace_hbp_get(NT_ARM_HW_BREAK, tsk, num, &kdata);
 	}
-	set_fs(old_fs);
 
 	if (!ret)
 		ret = put_user(kdata, data);
@@ -1484,7 +1487,6 @@ static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num,
 {
 	int ret;
 	u32 kdata = 0;
-	mm_segment_t old_fs = get_fs();
 
 	if (num == 0)
 		return 0;
@@ -1493,12 +1495,10 @@ static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num,
 	if (ret)
 		return ret;
 
-	set_fs(KERNEL_DS);
 	if (num < 0)
 		ret = compat_ptrace_hbp_set(NT_ARM_HW_WATCH, tsk, num, &kdata);
 	else
 		ret = compat_ptrace_hbp_set(NT_ARM_HW_BREAK, tsk, num, &kdata);
-	set_fs(old_fs);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 93ab57dcfc14..a6109825eeb9 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -112,6 +112,7 @@ long compat_arm_syscall(struct pt_regs *regs)
 		break;
 	}
 
+	clear_siginfo(&info);
 	info.si_signo = SIGILL;
 	info.si_errno = 0;
 	info.si_code  = ILL_ILLTRP;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index ba964da31a25..d399d459397b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -277,7 +277,8 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
 	 * If we were single stepping, we want to get the step exception after
 	 * we return from the trap.
 	 */
-	user_fastforward_single_step(current);
+	if (user_mode(regs))
+		user_fastforward_single_step(current);
 }
 
 static LIST_HEAD(undef_hook);
@@ -366,7 +367,7 @@ void force_signal_inject(int signal, int code, unsigned long address)
 	}
 
 	/* Force signals we don't understand to SIGKILL */
-	if (WARN_ON(signal != SIGKILL ||
+	if (WARN_ON(signal != SIGKILL &&
 		    siginfo_layout(signal, code) != SIL_FAULT)) {
 		signal = SIGKILL;
 	}
@@ -634,6 +635,7 @@ asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 	siginfo_t info;
 	void __user *pc = (void __user *)instruction_pointer(regs);
 
+	clear_siginfo(&info);
 	info.si_signo = SIGILL;
 	info.si_errno = 0;
 	info.si_code  = ILL_ILLOPC;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 959e50d2588c..56a0260ceb11 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
+#include <kvm/arm_psci.h>
 #include <asm/cputype.h>
 #include <linux/uaccess.h>
 #include <asm/kvm.h>
@@ -205,7 +206,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 {
 	return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
-                + NUM_TIMER_REGS;
+		+ kvm_arm_get_fw_num_regs(vcpu)	+ NUM_TIMER_REGS;
 }
 
 /**
@@ -225,6 +226,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 		uindices++;
 	}
 
+	ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+	if (ret)
+		return ret;
+	uindices += kvm_arm_get_fw_num_regs(vcpu);
+
 	ret = copy_timer_indices(vcpu, uindices);
 	if (ret)
 		return ret;
@@ -243,6 +249,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return get_core_reg(vcpu, reg);
 
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+		return kvm_arm_get_fw_reg(vcpu, reg);
+
 	if (is_timer_reg(reg->id))
 		return get_timer_reg(vcpu, reg);
 
@@ -259,6 +268,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return set_core_reg(vcpu, reg);
 
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+		return kvm_arm_set_fw_reg(vcpu, reg);
+
 	if (is_timer_reg(reg->id))
 		return set_timer_reg(vcpu, reg);
 
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 86801b6055d6..39be799d0417 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -18,11 +18,20 @@
 #include <linux/compiler.h>
 #include <linux/irqchip/arm-gic.h>
 #include <linux/kvm_host.h>
+#include <linux/swab.h>
 
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
+static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_mode_is_32bit(vcpu))
+		return !!(read_sysreg_el2(spsr) & COMPAT_PSR_E_BIT);
+
+	return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
+}
+
 /*
  * __vgic_v2_perform_cpuif_access -- perform a GICV access on behalf of the
  *				     guest.
@@ -64,14 +73,19 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 	addr += fault_ipa - vgic->vgic_cpu_base;
 
 	if (kvm_vcpu_dabt_iswrite(vcpu)) {
-		u32 data = vcpu_data_guest_to_host(vcpu,
-						   vcpu_get_reg(vcpu, rd),
-						   sizeof(u32));
+		u32 data = vcpu_get_reg(vcpu, rd);
+		if (__is_be(vcpu)) {
+			/* guest pre-swabbed data, undo this for writel() */
+			data = swab32(data);
+		}
 		writel_relaxed(data, addr);
 	} else {
 		u32 data = readl_relaxed(addr);
-		vcpu_set_reg(vcpu, rd, vcpu_data_host_to_guest(vcpu, data,
-							       sizeof(u32)));
+		if (__is_be(vcpu)) {
+			/* guest expects swabbed data */
+			data = swab32(data);
+		}
+		vcpu_set_reg(vcpu, rd, data);
 	}
 
 	return 1;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 806b0b126a64..6e3b969391fd 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -996,14 +996,12 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz)
 
 	if (id == SYS_ID_AA64PFR0_EL1) {
 		if (val & (0xfUL << ID_AA64PFR0_SVE_SHIFT))
-			pr_err_once("kvm [%i]: SVE unsupported for guests, suppressing\n",
-				    task_pid_nr(current));
+			kvm_debug("SVE unsupported for guests, suppressing\n");
 
 		val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
 	} else if (id == SYS_ID_AA64MMFR1_EL1) {
 		if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))
-			pr_err_once("kvm [%i]: LORegions unsupported for guests, suppressing\n",
-				    task_pid_nr(current));
+			kvm_debug("LORegions unsupported for guests, suppressing\n");
 
 		val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT);
 	}
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 0ead8a1d1679..137710f4dac3 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -19,5 +19,9 @@ CFLAGS_atomic_ll_sc.o	:= -fcall-used-x0 -ffixed-x1 -ffixed-x2		\
 		   -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15	\
 		   -fcall-saved-x18 -fomit-frame-pointer
 CFLAGS_REMOVE_atomic_ll_sc.o := -pg
+GCOV_PROFILE_atomic_ll_sc.o	:= n
+KASAN_SANITIZE_atomic_ll_sc.o	:= n
+KCOV_INSTRUMENT_atomic_ll_sc.o	:= n
+UBSAN_SANITIZE_atomic_ll_sc.o	:= n
 
 lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S
index d3db9b2cd479..0fdff97794de 100644
--- a/arch/arm64/lib/tishift.S
+++ b/arch/arm64/lib/tishift.S
@@ -1,17 +1,6 @@
-/*
- * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2017-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  */
 
 #include <linux/linkage.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index a96ec0181818..db01f2709842 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -508,16 +508,6 @@ static int __init arm64_dma_init(void)
 }
 arch_initcall(arm64_dma_init);
 
-#define PREALLOC_DMA_DEBUG_ENTRIES	4096
-
-static int __init dma_debug_do_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-	return 0;
-}
-fs_initcall(dma_debug_do_init);
-
-
 #ifdef CONFIG_IOMMU_DMA
 #include <linux/dma-iommu.h>
 #include <linux/platform_device.h>
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 4165485e8b6e..576f15153080 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -293,6 +293,57 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 static void __do_user_fault(struct siginfo *info, unsigned int esr)
 {
 	current->thread.fault_address = (unsigned long)info->si_addr;
+
+	/*
+	 * If the faulting address is in the kernel, we must sanitize the ESR.
+	 * From userspace's point of view, kernel-only mappings don't exist
+	 * at all, so we report them as level 0 translation faults.
+	 * (This is not quite the way that "no mapping there at all" behaves:
+	 * an alignment fault not caused by the memory type would take
+	 * precedence over translation fault for a real access to empty
+	 * space. Unfortunately we can't easily distinguish "alignment fault
+	 * not caused by memory type" from "alignment fault caused by memory
+	 * type", so we ignore this wrinkle and just return the translation
+	 * fault.)
+	 */
+	if (current->thread.fault_address >= TASK_SIZE) {
+		switch (ESR_ELx_EC(esr)) {
+		case ESR_ELx_EC_DABT_LOW:
+			/*
+			 * These bits provide only information about the
+			 * faulting instruction, which userspace knows already.
+			 * We explicitly clear bits which are architecturally
+			 * RES0 in case they are given meanings in future.
+			 * We always report the ESR as if the fault was taken
+			 * to EL1 and so ISV and the bits in ISS[23:14] are
+			 * clear. (In fact it always will be a fault to EL1.)
+			 */
+			esr &= ESR_ELx_EC_MASK | ESR_ELx_IL |
+				ESR_ELx_CM | ESR_ELx_WNR;
+			esr |= ESR_ELx_FSC_FAULT;
+			break;
+		case ESR_ELx_EC_IABT_LOW:
+			/*
+			 * Claim a level 0 translation fault.
+			 * All other bits are architecturally RES0 for faults
+			 * reported with that DFSC value, so we clear them.
+			 */
+			esr &= ESR_ELx_EC_MASK | ESR_ELx_IL;
+			esr |= ESR_ELx_FSC_FAULT;
+			break;
+		default:
+			/*
+			 * This should never happen (entry.S only brings us
+			 * into this code for insn and data aborts from a lower
+			 * exception level). Fail safe by not providing an ESR
+			 * context record at all.
+			 */
+			WARN(1, "ESR 0x%x is not DABT or IABT from EL0\n", esr);
+			esr = 0;
+			break;
+		}
+	}
+
 	current->thread.fault_code = esr;
 	arm64_force_sig_info(info, esr_to_fault_info(esr)->name, current);
 }
@@ -305,11 +356,12 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 	 */
 	if (user_mode(regs)) {
 		const struct fault_info *inf = esr_to_fault_info(esr);
-		struct siginfo si = {
-			.si_signo	= inf->sig,
-			.si_code	= inf->code,
-			.si_addr	= (void __user *)addr,
-		};
+		struct siginfo si;
+
+		clear_siginfo(&si);
+		si.si_signo	= inf->sig;
+		si.si_code	= inf->code;
+		si.si_addr	= (void __user *)addr;
 
 		__do_user_fault(&si, esr);
 	} else {
@@ -583,6 +635,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 			nmi_exit();
 	}
 
+	clear_siginfo(&info);
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code  = inf->code;
@@ -687,6 +740,7 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 		show_pte(addr);
 	}
 
+	clear_siginfo(&info);
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code  = inf->code;
@@ -729,6 +783,7 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 		local_irq_enable();
 	}
 
+	clear_siginfo(&info);
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
 	info.si_code  = BUS_ADRALN;
@@ -772,7 +827,6 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 					      struct pt_regs *regs)
 {
 	const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
-	struct siginfo info;
 	int rv;
 
 	/*
@@ -788,6 +842,9 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 	if (!inf->fn(addr, esr, regs)) {
 		rv = 1;
 	} else {
+		struct siginfo info;
+
+		clear_siginfo(&info);
 		info.si_signo = inf->sig;
 		info.si_errno = 0;
 		info.si_code  = inf->code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index e36ed5087b5c..1059884f9a6f 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -58,7 +58,7 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 	flush_ptrace_access(vma, page, uaddr, dst, len);
 }
 
-void __sync_icache_dcache(pte_t pte, unsigned long addr)
+void __sync_icache_dcache(pte_t pte)
 {
 	struct page *page = pte_page(pte);
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9f3c47acf8ff..1b18b4722420 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -646,8 +646,10 @@ static int keep_initrd __initdata;
 
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (!keep_initrd)
+	if (!keep_initrd) {
 		free_reserved_area((void *)start, (void *)end, 0, "initrd");
+		memblock_free(__virt_to_phys(start), end - start);
+	}
 }
 
 static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index dabfc1ecda3d..12145874c02b 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -204,7 +204,7 @@ void __init kasan_init(void)
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
 	kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
-			   pfn_to_nid(virt_to_pfn(lm_alias(_text))));
+			   early_pfn_to_nid(virt_to_pfn(lm_alias(_text))));
 
 	kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
 				   (void *)mod_shadow_start);
@@ -224,7 +224,7 @@ void __init kasan_init(void)
 
 		kasan_map_populate((unsigned long)kasan_mem_to_shadow(start),
 				   (unsigned long)kasan_mem_to_shadow(end),
-				   pfn_to_nid(virt_to_pfn(start)));
+				   early_pfn_to_nid(virt_to_pfn(start)));
 	}
 
 	/*
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 2dbb2c9f1ec1..493ff75670ff 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -933,13 +933,15 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
 {
 	pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
 					pgprot_val(mk_sect_prot(prot)));
+	pud_t new_pud = pfn_pud(__phys_to_pfn(phys), sect_prot);
 
-	/* ioremap_page_range doesn't honour BBM */
-	if (pud_present(READ_ONCE(*pudp)))
+	/* Only allow permission changes for now */
+	if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)),
+				   pud_val(new_pud)))
 		return 0;
 
 	BUG_ON(phys & ~PUD_MASK);
-	set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot));
+	set_pud(pudp, new_pud);
 	return 1;
 }
 
@@ -947,13 +949,15 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
 {
 	pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
 					pgprot_val(mk_sect_prot(prot)));
+	pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), sect_prot);
 
-	/* ioremap_page_range doesn't honour BBM */
-	if (pmd_present(READ_ONCE(*pmdp)))
+	/* Only allow permission changes for now */
+	if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)),
+				   pmd_val(new_pmd)))
 		return 0;
 
 	BUG_ON(phys & ~PMD_MASK);
-	set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot));
+	set_pmd(pmdp, new_pmd);
 	return 1;
 }
 
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index c6b4dd1418b4..bf59855628ac 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -6,11 +6,13 @@
 
 config C6X
 	def_bool y
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select CLKDEV_LOOKUP
+	select DMA_NONCOHERENT_OPS
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_DMA_API_DEBUG
 	select HAVE_MEMBLOCK
 	select SPARSE_IRQ
 	select IRQ_DOMAIN
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index fd4c840de837..33a2c94fed0d 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -1,10 +1,12 @@
 generic-y += atomic.h
 generic-y += barrier.h
 generic-y += bugs.h
+generic-y += compat.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/c6x/include/asm/dma-mapping.h b/arch/c6x/include/asm/dma-mapping.h
deleted file mode 100644
index 05daf1038111..000000000000
--- a/arch/c6x/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- *  Port on Texas Instruments TMS320C6x architecture
- *
- *  Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated
- *  Author: Aurelien Jacquiot <aurelien.jacquiot@ti.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- *
- */
-#ifndef _ASM_C6X_DMA_MAPPING_H
-#define _ASM_C6X_DMA_MAPPING_H
-
-extern const struct dma_map_ops c6x_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &c6x_dma_ops;
-}
-
-extern void coherent_mem_init(u32 start, u32 size);
-void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
-		gfp_t gfp, unsigned long attrs);
-void c6x_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs);
-
-#endif	/* _ASM_C6X_DMA_MAPPING_H */
diff --git a/arch/c6x/include/asm/setup.h b/arch/c6x/include/asm/setup.h
index 852afb209afb..350f34debb19 100644
--- a/arch/c6x/include/asm/setup.h
+++ b/arch/c6x/include/asm/setup.h
@@ -28,5 +28,7 @@ extern unsigned char c6x_fuse_mac[6];
 extern void machine_init(unsigned long dt_ptr);
 extern void time_init(void);
 
+extern void coherent_mem_init(u32 start, u32 size);
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_C6X_SETUP_H */
diff --git a/arch/c6x/kernel/Makefile b/arch/c6x/kernel/Makefile
index 02f340d7b8fe..fbe74174de87 100644
--- a/arch/c6x/kernel/Makefile
+++ b/arch/c6x/kernel/Makefile
@@ -8,6 +8,6 @@ extra-y := head.o vmlinux.lds
 obj-y := process.o traps.o irq.o signal.o ptrace.o
 obj-y += setup.o sys_c6x.o time.o devicetree.o
 obj-y += switch_to.o entry.o vectors.o c6x_ksyms.o
-obj-y += soc.o dma.o
+obj-y += soc.o
 
 obj-$(CONFIG_MODULES)           += module.o
diff --git a/arch/c6x/kernel/dma.c b/arch/c6x/kernel/dma.c
deleted file mode 100644
index 9fff8be75f58..000000000000
--- a/arch/c6x/kernel/dma.c
+++ /dev/null
@@ -1,149 +0,0 @@
-/*
- *  Copyright (C) 2011 Texas Instruments Incorporated
- *  Author: Mark Salter <msalter@redhat.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/mm_types.h>
-#include <linux/scatterlist.h>
-
-#include <asm/cacheflush.h>
-
-static void c6x_dma_sync(dma_addr_t handle, size_t size,
-			 enum dma_data_direction dir)
-{
-	unsigned long paddr = handle;
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	switch (dir) {
-	case DMA_FROM_DEVICE:
-		L2_cache_block_invalidate(paddr, paddr + size);
-		break;
-	case DMA_TO_DEVICE:
-		L2_cache_block_writeback(paddr, paddr + size);
-		break;
-	case DMA_BIDIRECTIONAL:
-		L2_cache_block_writeback_invalidate(paddr, paddr + size);
-		break;
-	default:
-		break;
-	}
-}
-
-static dma_addr_t c6x_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	dma_addr_t handle = virt_to_phys(page_address(page) + offset);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		c6x_dma_sync(handle, size, dir);
-
-	return handle;
-}
-
-static void c6x_dma_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		c6x_dma_sync(handle, size, dir);
-}
-
-static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sglist, sg, nents, i) {
-		sg->dma_address = sg_phys(sg);
-		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			c6x_dma_sync(sg->dma_address, sg->length, dir);
-	}
-
-	return nents;
-}
-
-static void c6x_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-		  int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	for_each_sg(sglist, sg, nents, i)
-		c6x_dma_sync(sg_dma_address(sg), sg->length, dir);
-}
-
-static void c6x_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	c6x_dma_sync(handle, size, dir);
-
-}
-
-static void c6x_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	c6x_dma_sync(handle, size, dir);
-
-}
-
-static void c6x_dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sglist, int nents,
-		enum dma_data_direction dir)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sglist, sg, nents, i)
-		c6x_dma_sync_single_for_cpu(dev, sg_dma_address(sg),
-					sg->length, dir);
-
-}
-
-static void c6x_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sglist, int nents,
-		enum dma_data_direction dir)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sglist, sg, nents, i)
-		c6x_dma_sync_single_for_device(dev, sg_dma_address(sg),
-					   sg->length, dir);
-
-}
-
-const struct dma_map_ops c6x_dma_ops = {
-	.alloc			= c6x_dma_alloc,
-	.free			= c6x_dma_free,
-	.map_page		= c6x_dma_map_page,
-	.unmap_page		= c6x_dma_unmap_page,
-	.map_sg			= c6x_dma_map_sg,
-	.unmap_sg		= c6x_dma_unmap_sg,
-	.sync_single_for_device	= c6x_dma_sync_single_for_device,
-	.sync_single_for_cpu	= c6x_dma_sync_single_for_cpu,
-	.sync_sg_for_device	= c6x_dma_sync_sg_for_device,
-	.sync_sg_for_cpu	= c6x_dma_sync_sg_for_cpu,
-};
-EXPORT_SYMBOL(c6x_dma_ops);
-
-/* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
-	return 0;
-}
-fs_initcall(dma_init);
diff --git a/arch/c6x/kernel/traps.c b/arch/c6x/kernel/traps.c
index 4c1d4b84dd2b..5c60aea3b75a 100644
--- a/arch/c6x/kernel/traps.c
+++ b/arch/c6x/kernel/traps.c
@@ -244,7 +244,6 @@ static struct exception_info eexcept_table[128] = {
 static void do_trap(struct exception_info *except_info, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
-	siginfo_t info;
 
 	if (except_info->code != TRAP_BRKPT)
 		pr_err("TRAP: %s PC[0x%lx] signo[%d] code[%d]\n",
@@ -253,12 +252,8 @@ static void do_trap(struct exception_info *except_info, struct pt_regs *regs)
 
 	die_if_kernel(except_info->kernel_str, regs, addr);
 
-	info.si_signo = except_info->signo;
-	info.si_errno = 0;
-	info.si_code  = except_info->code;
-	info.si_addr  = (void __user *)addr;
-
-	force_sig_info(except_info->signo, &info, current);
+	force_sig_fault(except_info->signo, except_info->code,
+			(void __user *)addr, current);
 }
 
 /*
diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c
index 95e38ad27c69..d0a8e0c4b27e 100644
--- a/arch/c6x/mm/dma-coherent.c
+++ b/arch/c6x/mm/dma-coherent.c
@@ -19,10 +19,12 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/memblock.h>
 
+#include <asm/cacheflush.h>
 #include <asm/page.h>
+#include <asm/setup.h>
 
 /*
  * DMA coherent memory management, can be redefined using the memdma=
@@ -73,7 +75,7 @@ static void __free_dma_pages(u32 addr, int order)
  * Allocate DMA coherent memory space and return both the kernel
  * virtual and DMA address for that space.
  */
-void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		gfp_t gfp, unsigned long attrs)
 {
 	u32 paddr;
@@ -98,7 +100,7 @@ void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 /*
  * Free DMA coherent memory as defined by the above mapping.
  */
-void c6x_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	int order;
@@ -139,3 +141,35 @@ void __init coherent_mem_init(phys_addr_t start, u32 size)
 	dma_bitmap = phys_to_virt(bitmap_phys);
 	memset(dma_bitmap, 0, dma_pages * PAGE_SIZE);
 }
+
+static void c6x_dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	BUG_ON(!valid_dma_direction(dir));
+
+	switch (dir) {
+	case DMA_FROM_DEVICE:
+		L2_cache_block_invalidate(paddr, paddr + size);
+		break;
+	case DMA_TO_DEVICE:
+		L2_cache_block_writeback(paddr, paddr + size);
+		break;
+	case DMA_BIDIRECTIONAL:
+		L2_cache_block_writeback_invalidate(paddr, paddr + size);
+		break;
+	default:
+		break;
+	}
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	return c6x_dma_sync(dev, paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	return c6x_dma_sync(dev, paddr, size, dir);
+}
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 14bac06b7116..a5d0b2991f47 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -3,6 +3,7 @@ generic-y += barrier.h
 generic-y += bugs.h
 generic-y += cacheflush.h
 generic-y += checksum.h
+generic-y += compat.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += device.h
diff --git a/arch/h8300/include/asm/pci.h b/arch/h8300/include/asm/pci.h
index 7c9e55d62215..d4d345a52092 100644
--- a/arch/h8300/include/asm/pci.h
+++ b/arch/h8300/include/asm/pci.h
@@ -15,6 +15,4 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
 	/* We don't do dynamic PCI IRQ allocation */
 }
 
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
 #endif /* _ASM_H8300_PCI_H */
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 76d2f20d525e..37adb2003033 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -19,6 +19,7 @@ config HEXAGON
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select NEED_SG_DMA_LENGTH
 	select NO_IOPORT_MAP
 	select GENERIC_IOMAP
 	select GENERIC_SMP_IDLE_THREAD
@@ -63,9 +64,6 @@ config GENERIC_CSUM
 config GENERIC_IRQ_PROBE
 	def_bool y
 
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool n
 
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index e9743f689fb8..dd2fd9c0d292 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -2,6 +2,7 @@
 generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
+generic-y += compat.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h
index 9e8621d94ee9..e17262ad125e 100644
--- a/arch/hexagon/include/asm/io.h
+++ b/arch/hexagon/include/asm/io.h
@@ -216,6 +216,12 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 	memcpy((void *) dst, src, count);
 }
 
+static inline void memset_io(volatile void __iomem *addr, int value,
+			     size_t size)
+{
+	memset((void __force *)addr, value, size);
+}
+
 #define PCI_IO_ADDR	(volatile void __iomem *)
 
 /*
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index ad8347c29dcf..77459df34e2e 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -208,7 +208,6 @@ const struct dma_map_ops hexagon_dma_ops = {
 	.sync_single_for_cpu = hexagon_sync_single_for_cpu,
 	.sync_single_for_device = hexagon_sync_single_for_device,
 	.mapping_error	= hexagon_mapping_error,
-	.is_phys	= 1,
 };
 
 void __init hexagon_dma_init(void)
diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c
index 2942a9204a9a..91ee04842c22 100644
--- a/arch/hexagon/kernel/traps.c
+++ b/arch/hexagon/kernel/traps.c
@@ -412,10 +412,6 @@ void do_trap0(struct pt_regs *regs)
 	case TRAP_DEBUG:
 		/* Trap0 0xdb is debug breakpoint */
 		if (user_mode(regs)) {
-			struct siginfo info;
-
-			info.si_signo = SIGTRAP;
-			info.si_errno = 0;
 			/*
 			 * Some architecures add some per-thread state
 			 * to distinguish between breakpoint traps and
@@ -423,9 +419,8 @@ void do_trap0(struct pt_regs *regs)
 			 * set the si_code value appropriately, or we
 			 * may want to use a different trap0 flavor.
 			 */
-			info.si_code = TRAP_BRKPT;
-			info.si_addr = (void __user *) pt_elr(regs);
-			force_sig_info(SIGTRAP, &info, current);
+			force_sig_fault(SIGTRAP, TRAP_BRKPT,
+					(void __user *) pt_elr(regs), current);
 		} else {
 #ifdef CONFIG_KGDB
 			kgdb_handle_exception(pt_cause(regs), SIGTRAP,
diff --git a/arch/hexagon/lib/checksum.c b/arch/hexagon/lib/checksum.c
index 617506d1a559..7cd0a2259269 100644
--- a/arch/hexagon/lib/checksum.c
+++ b/arch/hexagon/lib/checksum.c
@@ -199,3 +199,4 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
 	memcpy(dst, src, len);
 	return csum_partial(dst, len, sum);
 }
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 3eec33c5cfd7..933bbcef5363 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -50,7 +50,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
-	siginfo_t info;
+	int si_signo;
 	int si_code = SEGV_MAPERR;
 	int fault;
 	const struct exception_table_entry *fixup;
@@ -140,28 +140,22 @@ good_area:
 	 * unable to fix up the page fault.
 	 */
 	if (fault & VM_FAULT_SIGBUS) {
-		info.si_signo = SIGBUS;
-		info.si_code = BUS_ADRERR;
+		si_signo = SIGBUS;
+		si_code = BUS_ADRERR;
 	}
 	/* Address is not in the memory map */
 	else {
-		info.si_signo = SIGSEGV;
-		info.si_code = SEGV_ACCERR;
+		si_signo = SIGSEGV;
+		si_code  = SEGV_ACCERR;
 	}
-	info.si_errno = 0;
-	info.si_addr = (void __user *)address;
-	force_sig_info(info.si_signo, &info, current);
+	force_sig_fault(si_signo, si_code, (void __user *)address, current);
 	return;
 
 bad_area:
 	up_read(&mm->mmap_sem);
 
 	if (user_mode(regs)) {
-		info.si_signo = SIGSEGV;
-		info.si_errno = 0;
-		info.si_code = si_code;
-		info.si_addr = (void *)address;
-		force_sig_info(info.si_signo, &info, current);
+		force_sig_fault(SIGSEGV, si_code, (void __user *)address, current);
 		return;
 	}
 	/* Kernel-mode fault falls through */
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index bbe12a038d21..792437d526c6 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -29,7 +29,6 @@ config IA64
 	select HAVE_FUNCTION_TRACER
 	select TTY
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_DMA_API_DEBUG
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_VIRT_CPU_ACCOUNTING
@@ -54,6 +53,8 @@ config IA64
 	select MODULES_USE_ELF_RELA
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_AUDITSYSCALL
+	select NEED_DMA_MAP_STATE
+	select NEED_SG_DMA_LENGTH
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
@@ -78,18 +79,6 @@ config MMU
 	bool
 	default y
 
-config ARCH_DMA_ADDR_T_64BIT
-	def_bool y
-
-config NEED_DMA_MAP_STATE
-	def_bool y
-
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
-config SWIOTLB
-       bool
-
 config STACKTRACE_SUPPORT
 	def_bool y
 
@@ -146,7 +135,6 @@ config IA64_GENERIC
 	bool "generic"
 	select NUMA
 	select ACPI_NUMA
-	select DMA_DIRECT_OPS
 	select SWIOTLB
 	select PCI_MSI
 	help
@@ -167,7 +155,6 @@ config IA64_GENERIC
 
 config IA64_DIG
 	bool "DIG-compliant"
-	select DMA_DIRECT_OPS
 	select SWIOTLB
 
 config IA64_DIG_VTD
@@ -183,7 +170,6 @@ config IA64_HP_ZX1
 
 config IA64_HP_ZX1_SWIOTLB
 	bool "HP-zx1/sx1000 with software I/O TLB"
-	select DMA_DIRECT_OPS
 	select SWIOTLB
 	help
 	  Build a kernel that runs on HP zx1 and sx1000 systems even when they
@@ -207,7 +193,6 @@ config IA64_SGI_UV
 	bool "SGI-UV"
 	select NUMA
 	select ACPI_NUMA
-	select DMA_DIRECT_OPS
 	select SWIOTLB
 	help
 	  Selecting this option will optimize the kernel for use on UV based
@@ -218,7 +203,6 @@ config IA64_SGI_UV
 
 config IA64_HP_SIM
 	bool "Ski-simulator"
-	select DMA_DIRECT_OPS
 	select SWIOTLB
 	depends on !PM
 
@@ -397,7 +381,7 @@ config ARCH_DISCONTIGMEM_ENABLE
 	  Say Y to support efficient handling of discontiguous physical memory,
 	  for architectures which are either NUMA (Non-Uniform Memory Access)
 	  or have huge holes in the physical address space for other reasons.
- 	  See <file:Documentation/vm/numa> for more.
+	  See <file:Documentation/vm/numa.rst> for more.
 
 config ARCH_FLATMEM_ENABLE
 	def_bool y
@@ -613,6 +597,3 @@ source "security/Kconfig"
 source "crypto/Kconfig"
 
 source "lib/Kconfig"
-
-config IOMMU_HELPER
-	def_bool (IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_GENERIC || SWIOTLB)
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index 2dd7f519ad0b..45f59808b842 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -18,7 +18,7 @@ READELF := $(CROSS_COMPILE)readelf
 
 export AWK
 
-CHECKFLAGS	+= -m64 -D__ia64=1 -D__ia64__=1 -D_LP64 -D__LP64__
+CHECKFLAGS	+= -D__ia64=1 -D__ia64__=1 -D_LP64 -D__LP64__
 
 OBJCOPYFLAGS	:= --strip-all
 LDFLAGS_vmlinux	:= -static
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index aec4a3354abe..ee5b652d320a 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1845,9 +1845,6 @@ static void ioc_init(unsigned long hpa, struct ioc *ioc)
 	ioc_resource_init(ioc);
 	ioc_sac_init(ioc);
 
-	if ((long) ~iovp_mask > (long) ia64_max_iommu_merge_mask)
-		ia64_max_iommu_merge_mask = ~iovp_mask;
-
 	printk(KERN_INFO PFX
 		"%s %d.%d HPA 0x%lx IOVA space %dMb at 0x%lx\n",
 		ioc->name, (ioc->rev >> 4) & 0xF, ioc->rev & 0xF,
@@ -1942,19 +1939,6 @@ static const struct seq_operations ioc_seq_ops = {
 	.show  = ioc_show
 };
 
-static int
-ioc_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &ioc_seq_ops);
-}
-
-static const struct file_operations ioc_fops = {
-	.open    = ioc_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release
-};
-
 static void __init
 ioc_proc_init(void)
 {
@@ -1964,7 +1948,7 @@ ioc_proc_init(void)
 	if (!dir)
 		return;
 
-	proc_create(ioc_list->name, 0, dir, &ioc_fops);
+	proc_create_seq(ioc_list->name, 0, dir, &ioc_seq_ops);
 }
 #endif
 
diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c
index a419ccf33cde..663388a73d4e 100644
--- a/arch/ia64/hp/sim/simserial.c
+++ b/arch/ia64/hp/sim/simserial.c
@@ -435,19 +435,6 @@ static int rs_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int rs_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, rs_proc_show, NULL);
-}
-
-static const struct file_operations rs_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= rs_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static const struct tty_operations hp_ops = {
 	.open = rs_open,
 	.close = rs_close,
@@ -462,7 +449,7 @@ static const struct tty_operations hp_ops = {
 	.unthrottle = rs_unthrottle,
 	.send_xchar = rs_send_xchar,
 	.hangup = rs_hangup,
-	.proc_fops = &rs_proc_fops,
+	.proc_show = rs_proc_show,
 };
 
 static const struct tty_port_operations hp_port_ops = {
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 6dd867873364..557bbc8ba9f5 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -1,3 +1,4 @@
+generic-y += compat.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h
index bdc4669c71c3..ccde7c2ba00f 100644
--- a/arch/ia64/include/asm/hardirq.h
+++ b/arch/ia64/include/asm/hardirq.h
@@ -13,7 +13,7 @@
 
 #define __ARCH_IRQ_STAT	1
 
-#define local_softirq_pending()		(local_cpu_data->softirq_pending)
+#define local_softirq_pending_ref	ia64_cpu_info.softirq_pending
 
 #include <linux/threads.h>
 #include <linux/irq.h>
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index b1d04e8bafc8..780e8744ba85 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -30,23 +30,6 @@ struct pci_vector_struct {
 #define PCIBIOS_MIN_IO		0x1000
 #define PCIBIOS_MIN_MEM		0x10000000
 
-/*
- * PCI_DMA_BUS_IS_PHYS should be set to 1 if there is _necessarily_ a direct
- * correspondence between device bus addresses and CPU physical addresses.
- * Platforms with a hardware I/O MMU _must_ turn this off to suppress the
- * bounce buffer handling code in the block and network device layers.
- * Platforms with separate bus address spaces _must_ turn this off and provide
- * a device DMA mapping implementation that takes care of the necessary
- * address translation.
- *
- * For now, the ia64 platforms which may have separate/multiple bus address
- * spaces all have I/O MMUs which support the merging of physically
- * discontiguous buffers, so we can use that as the sole factor to determine
- * the setting of PCI_DMA_BUS_IS_PHYS.
- */
-extern unsigned long ia64_max_iommu_merge_mask;
-#define PCI_DMA_BUS_IS_PHYS	(ia64_max_iommu_merge_mask == ~0UL)
-
 #define HAVE_PCI_MMAP
 #define ARCH_GENERIC_PCI_MMAP_RESOURCE
 #define arch_can_pci_mmap_wc()	1
diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild
index c0527cfc48f0..3982e673e967 100644
--- a/arch/ia64/include/uapi/asm/Kbuild
+++ b/arch/ia64/include/uapi/asm/Kbuild
@@ -2,5 +2,9 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += bpf_perf_event.h
+generic-y += ipcbuf.h
 generic-y += kvm_para.h
+generic-y += msgbuf.h
 generic-y += poll.h
+generic-y += sembuf.h
+generic-y += shmbuf.h
diff --git a/arch/ia64/include/uapi/asm/ipcbuf.h b/arch/ia64/include/uapi/asm/ipcbuf.h
deleted file mode 100644
index 90d6445a14df..000000000000
--- a/arch/ia64/include/uapi/asm/ipcbuf.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/ipcbuf.h>
diff --git a/arch/ia64/include/uapi/asm/msgbuf.h b/arch/ia64/include/uapi/asm/msgbuf.h
deleted file mode 100644
index aa25df92d9dc..000000000000
--- a/arch/ia64/include/uapi/asm/msgbuf.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_IA64_MSGBUF_H
-#define _ASM_IA64_MSGBUF_H
-
-/*
- * The msqid64_ds structure for IA-64 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct msqid64_ds {
-	struct ipc64_perm msg_perm;
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-	__kernel_time_t msg_ctime;	/* last change time */
-	unsigned long  msg_cbytes;	/* current number of bytes on queue */
-	unsigned long  msg_qnum;	/* number of messages in queue */
-	unsigned long  msg_qbytes;	/* max number of bytes on queue */
-	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
-	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	unsigned long  __unused1;
-	unsigned long  __unused2;
-};
-
-#endif /* _ASM_IA64_MSGBUF_H */
diff --git a/arch/ia64/include/uapi/asm/sembuf.h b/arch/ia64/include/uapi/asm/sembuf.h
deleted file mode 100644
index 6ed058760afc..000000000000
--- a/arch/ia64/include/uapi/asm/sembuf.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_IA64_SEMBUF_H
-#define _ASM_IA64_SEMBUF_H
-
-/*
- * The semid64_ds structure for IA-64 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct semid64_ds {
-	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
-	__kernel_time_t	sem_otime;		/* last semop time */
-	__kernel_time_t	sem_ctime;		/* last change time */
-	unsigned long	sem_nsems;		/* no. of semaphores in array */
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-};
-
-#endif /* _ASM_IA64_SEMBUF_H */
diff --git a/arch/ia64/include/uapi/asm/shmbuf.h b/arch/ia64/include/uapi/asm/shmbuf.h
deleted file mode 100644
index 6ef57cb70dee..000000000000
--- a/arch/ia64/include/uapi/asm/shmbuf.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_IA64_SHMBUF_H
-#define _ASM_IA64_SHMBUF_H
-
-/*
- * The shmid64_ds structure for IA-64 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct shmid64_ds {
-	struct ipc64_perm	shm_perm;	/* operation perms */
-	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_time_t		shm_atime;	/* last attach time */
-	__kernel_time_t		shm_dtime;	/* last detach time */
-	__kernel_time_t		shm_ctime;	/* last change time */
-	__kernel_pid_t		shm_cpid;	/* pid of creator */
-	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	unsigned long		shm_nattch;	/* no. of current attaches */
-	unsigned long		__unused1;
-	unsigned long		__unused2;
-};
-
-struct shminfo64 {
-	unsigned long	shmmax;
-	unsigned long	shmmin;
-	unsigned long	shmmni;
-	unsigned long	shmseg;
-	unsigned long	shmall;
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* _ASM_IA64_SHMBUF_H */
diff --git a/arch/ia64/include/uapi/asm/siginfo.h b/arch/ia64/include/uapi/asm/siginfo.h
index 5aa454ed89db..52b5af424511 100644
--- a/arch/ia64/include/uapi/asm/siginfo.h
+++ b/arch/ia64/include/uapi/asm/siginfo.h
@@ -27,11 +27,4 @@
 #define __ISR_VALID_BIT	0
 #define __ISR_VALID	(1 << __ISR_VALID_BIT)
 
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME	0	/* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
 #endif /* _UAPI_ASM_IA64_SIGINFO_H */
diff --git a/arch/ia64/kernel/brl_emu.c b/arch/ia64/kernel/brl_emu.c
index 9bcc908bc85e..a61f6c6a36f8 100644
--- a/arch/ia64/kernel/brl_emu.c
+++ b/arch/ia64/kernel/brl_emu.c
@@ -62,6 +62,7 @@ ia64_emulate_brl (struct pt_regs *regs, unsigned long ar_ec)
 	struct illegal_op_return rv;
 	long tmp_taken, unimplemented_address;
 
+	clear_siginfo(&siginfo);
 	rv.fkt = (unsigned long) -1;
 
 	/*
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index f2d57e66fd86..7a471d8d67d4 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -9,16 +9,6 @@ int iommu_detected __read_mostly;
 const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
-	return 0;
-}
-fs_initcall(dma_init);
-
 const struct dma_map_ops *dma_get_ops(struct device *dev)
 {
 	return dma_ops;
diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c
index b6e597860888..f4a94241265c 100644
--- a/arch/ia64/kernel/palinfo.c
+++ b/arch/ia64/kernel/palinfo.c
@@ -920,18 +920,6 @@ static int proc_palinfo_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int proc_palinfo_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_palinfo_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_palinfo_fops = {
-	.open		= proc_palinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int palinfo_add_proc(unsigned int cpu)
 {
 	pal_func_cpu_u_t f;
@@ -948,8 +936,8 @@ static int palinfo_add_proc(unsigned int cpu)
 
 	for (j=0; j < NR_PALINFO_ENTRIES; j++) {
 		f.func_id = j;
-		proc_create_data(palinfo_entries[j].name, 0, cpu_dir,
-				 &proc_palinfo_fops, (void *)f.value);
+		proc_create_single_data(palinfo_entries[j].name, 0, cpu_dir,
+				proc_palinfo_show, (void *)f.value);
 	}
 	return 0;
 }
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 8fb280e33114..3b38c717008a 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -5708,13 +5708,6 @@ const struct seq_operations pfm_seq_ops = {
  	.show =		pfm_proc_show
 };
 
-static int
-pfm_proc_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &pfm_seq_ops);
-}
-
-
 /*
  * we come here as soon as local_cpu_data->pfm_syst_wide is set. this happens
  * during pfm_enable() hence before pfm_start(). We cannot assume monitoring
@@ -6537,13 +6530,6 @@ found:
 	return 0;
 }
 
-static const struct file_operations pfm_proc_fops = {
-	.open		= pfm_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 int __init
 pfm_init(void)
 {
@@ -6615,7 +6601,7 @@ pfm_init(void)
 	/*
 	 * create /proc/perfmon (mostly for debugging purposes)
 	 */
-	perfmon_dir = proc_create("perfmon", S_IRUGO, NULL, &pfm_proc_fops);
+	perfmon_dir = proc_create_seq("perfmon", S_IRUGO, NULL, &pfm_seq_ops);
 	if (perfmon_dir == NULL) {
 		printk(KERN_ERR "perfmon: cannot create /proc entry, perfmon disabled\n");
 		pmu_conf = NULL;
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index 52c404b08904..aba1f463a8dd 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -54,8 +54,6 @@ MODULE_AUTHOR("Jesse Barnes <jbarnes@sgi.com>");
 MODULE_DESCRIPTION("/proc interface to IA-64 SAL features");
 MODULE_LICENSE("GPL");
 
-static const struct file_operations proc_salinfo_fops;
-
 typedef struct {
 	const char		*name;		/* name of the proc entry */
 	unsigned long           feature;        /* feature bit */
@@ -578,6 +576,17 @@ static int salinfo_cpu_pre_down(unsigned int cpu)
 	return 0;
 }
 
+/*
+ * 'data' contains an integer that corresponds to the feature we're
+ * testing
+ */
+static int proc_salinfo_show(struct seq_file *m, void *v)
+{
+	unsigned long data = (unsigned long)v;
+	seq_puts(m, (sal_platform_features & data) ? "1\n" : "0\n");
+	return 0;
+}
+
 static int __init
 salinfo_init(void)
 {
@@ -593,9 +602,9 @@ salinfo_init(void)
 
 	for (i=0; i < NR_SALINFO_ENTRIES; i++) {
 		/* pass the feature bit in question as misc data */
-		*sdir++ = proc_create_data(salinfo_entries[i].name, 0, salinfo_dir,
-					   &proc_salinfo_fops,
-					   (void *)salinfo_entries[i].feature);
+		*sdir++ = proc_create_single_data(salinfo_entries[i].name, 0,
+				salinfo_dir, proc_salinfo_show,
+				(void *)salinfo_entries[i].feature);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(salinfo_log_name); i++) {
@@ -633,27 +642,4 @@ salinfo_init(void)
 	return 0;
 }
 
-/*
- * 'data' contains an integer that corresponds to the feature we're
- * testing
- */
-static int proc_salinfo_show(struct seq_file *m, void *v)
-{
-	unsigned long data = (unsigned long)v;
-	seq_puts(m, (sal_platform_features & data) ? "1\n" : "0\n");
-	return 0;
-}
-
-static int proc_salinfo_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_salinfo_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_salinfo_fops = {
-	.open		= proc_salinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 module_init(salinfo_init);
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index dee56bcb993d..ad43cbf70628 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -124,18 +124,6 @@ unsigned long ia64_i_cache_stride_shift = ~0;
 unsigned long ia64_cache_stride_shift = ~0;
 
 /*
- * The merge_mask variable needs to be set to (max(iommu_page_size(iommu)) - 1).  This
- * mask specifies a mask of address bits that must be 0 in order for two buffers to be
- * mergeable by the I/O MMU (i.e., the end address of the first buffer and the start
- * address of the second buffer must be aligned to (merge_mask+1) in order to be
- * mergeable).  By default, we assume there is no I/O MMU which can merge physically
- * discontiguous buffers, so we set the merge_mask to ~0UL, which corresponds to a iommu
- * page-size of 2^64.
- */
-unsigned long ia64_max_iommu_merge_mask = ~0UL;
-EXPORT_SYMBOL(ia64_max_iommu_merge_mask);
-
-/*
  * We use a special marker for the end of memory and it uses the extra (+1) slot
  */
 struct rsvd_region rsvd_region[IA64_MAX_RSVD_REGIONS + 1] __initdata;
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 54547c7cf8a2..d1234a5ba4c5 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -153,6 +153,7 @@ ia64_rt_sigreturn (struct sigscratch *scr)
 	return retval;
 
   give_sigsegv:
+	clear_siginfo(&si);
 	si.si_signo = SIGSEGV;
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
@@ -236,6 +237,7 @@ force_sigsegv_info (int sig, void __user *addr)
 	unsigned long flags;
 	struct siginfo si;
 
+	clear_siginfo(&si);
 	if (sig == SIGSEGV) {
 		/*
 		 * Acquiring siglock around the sa_handler-update is almost
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index 6d4e76a4267f..c6f4932073a1 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -104,6 +104,7 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
 	int sig, code;
 
 	/* SIGILL, SIGFPE, SIGSEGV, and SIGBUS want these field initialized: */
+	clear_siginfo(&siginfo);
 	siginfo.si_addr = (void __user *) (regs->cr_iip + ia64_psr(regs)->ri);
 	siginfo.si_imm = break_num;
 	siginfo.si_flags = 0;		/* clear __ISR_VALID */
@@ -293,7 +294,6 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
 {
 	long exception, bundle[2];
 	unsigned long fault_ip;
-	struct siginfo siginfo;
 
 	fault_ip = regs->cr_iip;
 	if (!fp_fault && (ia64_psr(regs)->ri == 0))
@@ -344,13 +344,16 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
 			printk(KERN_ERR "handle_fpu_swa: fp_emulate() returned -1\n");
 			return -1;
 		} else {
+			struct siginfo siginfo;
+
 			/* is next instruction a trap? */
 			if (exception & 2) {
 				ia64_increment_ip(regs);
 			}
+			clear_siginfo(&siginfo);
 			siginfo.si_signo = SIGFPE;
 			siginfo.si_errno = 0;
-			siginfo.si_code = FPE_FIXME;	/* default code */
+			siginfo.si_code = FPE_FLTUNK;	/* default code */
 			siginfo.si_addr = (void __user *) (regs->cr_iip + ia64_psr(regs)->ri);
 			if (isr & 0x11) {
 				siginfo.si_code = FPE_FLTINV;
@@ -372,9 +375,12 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
 			return -1;
 		} else if (exception != 0) {
 			/* raise exception */
+			struct siginfo siginfo;
+
+			clear_siginfo(&siginfo);
 			siginfo.si_signo = SIGFPE;
 			siginfo.si_errno = 0;
-			siginfo.si_code = FPE_FIXME;	/* default code */
+			siginfo.si_code = FPE_FLTUNK;	/* default code */
 			siginfo.si_addr = (void __user *) (regs->cr_iip + ia64_psr(regs)->ri);
 			if (isr & 0x880) {
 				siginfo.si_code = FPE_FLTOVF;
@@ -420,7 +426,7 @@ ia64_illegal_op_fault (unsigned long ec, long arg1, long arg2, long arg3,
 	if (die_if_kernel(buf, &regs, 0))
 		return rv;
 
-	memset(&si, 0, sizeof(si));
+	clear_siginfo(&si);
 	si.si_signo = SIGILL;
 	si.si_code = ILL_ILLOPC;
 	si.si_addr = (void __user *) (regs.cr_iip + ia64_psr(&regs)->ri);
@@ -434,7 +440,6 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 	    long arg7, struct pt_regs regs)
 {
 	unsigned long code, error = isr, iip;
-	struct siginfo siginfo;
 	char buf[128];
 	int result, sig;
 	static const char *reason[] = {
@@ -485,6 +490,7 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 
 	      case 26: /* NaT Consumption */
 		if (user_mode(&regs)) {
+			struct siginfo siginfo;
 			void __user *addr;
 
 			if (((isr >> 4) & 0xf) == 2) {
@@ -499,6 +505,7 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 				addr = (void __user *) (regs.cr_iip
 							+ ia64_psr(&regs)->ri);
 			}
+			clear_siginfo(&siginfo);
 			siginfo.si_signo = sig;
 			siginfo.si_code = code;
 			siginfo.si_errno = 0;
@@ -515,6 +522,9 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 
 	      case 31: /* Unsupported Data Reference */
 		if (user_mode(&regs)) {
+			struct siginfo siginfo;
+
+			clear_siginfo(&siginfo);
 			siginfo.si_signo = SIGILL;
 			siginfo.si_code = ILL_ILLOPN;
 			siginfo.si_errno = 0;
@@ -531,6 +541,10 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 	      case 29: /* Debug */
 	      case 35: /* Taken Branch Trap */
 	      case 36: /* Single Step Trap */
+	      {
+		struct siginfo siginfo;
+
+		clear_siginfo(&siginfo);
 		if (fsys_mode(current, &regs)) {
 			extern char __kernel_syscall_via_break[];
 			/*
@@ -578,11 +592,15 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 		siginfo.si_isr   = isr;
 		force_sig_info(SIGTRAP, &siginfo, current);
 		return;
+	      }
 
 	      case 32: /* fp fault */
 	      case 33: /* fp trap */
 		result = handle_fpu_swa((vector == 32) ? 1 : 0, &regs, isr);
 		if ((result < 0) || (current->thread.flags & IA64_THREAD_FPEMU_SIGFPE)) {
+			struct siginfo siginfo;
+
+			clear_siginfo(&siginfo);
 			siginfo.si_signo = SIGFPE;
 			siginfo.si_errno = 0;
 			siginfo.si_code = FPE_FLTINV;
@@ -616,6 +634,9 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 		} else {
 			/* Unimplemented Instr. Address Trap */
 			if (user_mode(&regs)) {
+				struct siginfo siginfo;
+
+				clear_siginfo(&siginfo);
 				siginfo.si_signo = SIGILL;
 				siginfo.si_code = ILL_BADIADDR;
 				siginfo.si_errno = 0;
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 72e9b4242564..e309f9859acc 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -1537,6 +1537,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
 		/* NOT_REACHED */
 	}
   force_sigbus:
+	clear_siginfo(&si);
 	si.si_signo = SIGBUS;
 	si.si_errno = 0;
 	si.si_code = BUS_ADRALN;
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index dfdc152d6737..817fa120645f 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -85,7 +85,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	int signal = SIGSEGV, code = SEGV_MAPERR;
 	struct vm_area_struct *vma, *prev_vma;
 	struct mm_struct *mm = current->mm;
-	struct siginfo si;
 	unsigned long mask;
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -249,6 +248,9 @@ retry:
 		return;
 	}
 	if (user_mode(regs)) {
+		struct siginfo si;
+
+		clear_siginfo(&si);
 		si.si_signo = signal;
 		si.si_errno = 0;
 		si.si_code = code;
diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c
index 11f2275570fb..8479e9a7ce16 100644
--- a/arch/ia64/sn/kernel/io_common.c
+++ b/arch/ia64/sn/kernel/io_common.c
@@ -480,11 +480,6 @@ sn_io_early_init(void)
 	tioca_init_provider();
 	tioce_init_provider();
 
-	/*
-	 * This is needed to avoid bounce limit checks in the blk layer
-	 */
-	ia64_max_iommu_merge_mask = ~PAGE_MASK;
-
 	sn_irq_lh_init();
 	INIT_LIST_HEAD(&sn_sysdata_list);
 	sn_init_cpei_timer();
diff --git a/arch/ia64/sn/kernel/sn2/prominfo_proc.c b/arch/ia64/sn/kernel/sn2/prominfo_proc.c
index ec4de2b09653..e15457bf21ac 100644
--- a/arch/ia64/sn/kernel/sn2/prominfo_proc.c
+++ b/arch/ia64/sn/kernel/sn2/prominfo_proc.c
@@ -140,18 +140,6 @@ static int proc_fit_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int proc_fit_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_fit_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_fit_fops = {
-	.open		= proc_fit_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int proc_version_show(struct seq_file *m, void *v)
 {
 	unsigned long nasid = (unsigned long)m->private;
@@ -174,18 +162,6 @@ static int proc_version_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int proc_version_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_version_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_version_fops = {
-	.open		= proc_version_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /* module entry points */
 int __init prominfo_init(void);
 void __exit prominfo_exit(void);
@@ -217,10 +193,10 @@ int __init prominfo_init(void)
 		if (!dir)
 			continue;
 		nasid = cnodeid_to_nasid(cnodeid);
-		proc_create_data("fit", 0, dir,
-				 &proc_fit_fops, (void *)nasid);
-		proc_create_data("version", 0, dir,
-				 &proc_version_fops, (void *)nasid);
+		proc_create_single_data("fit", 0, dir, proc_fit_show, 
+				(void *)nasid);
+		proc_create_single_data("version", 0, dir, proc_version_show,
+				(void *)nasid);
 	}
 	return 0;
 }
diff --git a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
index 29cf8f8c08e9..c2a4d84297b0 100644
--- a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
+++ b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
@@ -18,33 +18,18 @@ static int partition_id_show(struct seq_file *s, void *p)
 	return 0;
 }
 
-static int partition_id_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, partition_id_show, NULL);
-}
-
 static int system_serial_number_show(struct seq_file *s, void *p)
 {
 	seq_printf(s, "%s\n", sn_system_serial_number());
 	return 0;
 }
 
-static int system_serial_number_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, system_serial_number_show, NULL);
-}
-
 static int licenseID_show(struct seq_file *s, void *p)
 {
 	seq_printf(s, "0x%llx\n", sn_partition_serial_number_val());
 	return 0;
 }
 
-static int licenseID_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, licenseID_show, NULL);
-}
-
 static int coherence_id_show(struct seq_file *s, void *p)
 {
 	seq_printf(s, "%d\n", partition_coherence_id());
@@ -52,43 +37,10 @@ static int coherence_id_show(struct seq_file *s, void *p)
 	return 0;
 }
 
-static int coherence_id_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, coherence_id_show, NULL);
-}
-
 /* /proc/sgi_sn/sn_topology uses seq_file, see sn_hwperf.c */
 extern int sn_topology_open(struct inode *, struct file *);
 extern int sn_topology_release(struct inode *, struct file *);
 
-static const struct file_operations proc_partition_id_fops = {
-	.open		= partition_id_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static const struct file_operations proc_system_sn_fops = {
-	.open		= system_serial_number_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static const struct file_operations proc_license_id_fops = {
-	.open		= licenseID_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static const struct file_operations proc_coherence_id_fops = {
-	.open		= coherence_id_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static const struct file_operations proc_sn_topo_fops = {
 	.open		= sn_topology_open,
 	.read		= seq_read,
@@ -104,13 +56,13 @@ void register_sn_procfs(void)
 	if (!(sgi_proc_dir = proc_mkdir("sgi_sn", NULL)))
 		return;
 
-	proc_create("partition_id", 0444, sgi_proc_dir,
-		    &proc_partition_id_fops);
-	proc_create("system_serial_number", 0444, sgi_proc_dir,
-		    &proc_system_sn_fops);
-	proc_create("licenseID", 0444, sgi_proc_dir, &proc_license_id_fops);
-	proc_create("coherence_id", 0444, sgi_proc_dir,
-		    &proc_coherence_id_fops);
+	proc_create_single("partition_id", 0444, sgi_proc_dir,
+			partition_id_show);
+	proc_create_single("system_serial_number", 0444, sgi_proc_dir,
+			system_serial_number_show);
+	proc_create_single("licenseID", 0444, sgi_proc_dir, licenseID_show);
+	proc_create_single("coherence_id", 0444, sgi_proc_dir,
+			coherence_id_show);
 	proc_create("sn_topology", 0444, sgi_proc_dir, &proc_sn_topo_fops);
 }
 
diff --git a/arch/m68k/68000/timers.c b/arch/m68k/68000/timers.c
index 252455bce144..71ddb4c98726 100644
--- a/arch/m68k/68000/timers.c
+++ b/arch/m68k/68000/timers.c
@@ -125,7 +125,9 @@ int m68328_hwclk(int set, struct rtc_time *t)
 {
 	if (!set) {
 		long now = RTCTIME;
-		t->tm_year = t->tm_mon = t->tm_mday = 1;
+		t->tm_year = 1;
+		t->tm_mon = 0;
+		t->tm_mday = 1;
 		t->tm_hour = (now >> 24) % 24;
 		t->tm_min = (now >> 16) % 60;
 		t->tm_sec = now % 60;
diff --git a/arch/m68k/Kconfig.bus b/arch/m68k/Kconfig.bus
index d5e66ec136db..aef698fa50e5 100644
--- a/arch/m68k/Kconfig.bus
+++ b/arch/m68k/Kconfig.bus
@@ -59,6 +59,10 @@ config ATARI_ROM_ISA
 config GENERIC_ISA_DMA
 	def_bool ISA
 
+source "drivers/zorro/Kconfig"
+
+endif
+
 config PCI
 	bool "PCI support"
 	depends on M54xx
@@ -66,10 +70,8 @@ config PCI
 	  Enable the PCI bus. Support for the PCI bus hardware built into the
 	  ColdFire 547x and 548x processors.
 
+if PCI
 source "drivers/pci/Kconfig"
-
-source "drivers/zorro/Kconfig"
-
 endif
 
 if !MMU
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index 0d27706f14d4..b2a6bc63f8cd 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -221,8 +221,10 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) {
     t->tm_hour=rtc->hours;
     t->tm_mday=rtc->day_of_month;
     t->tm_wday=rtc->day_of_week;
-    t->tm_mon=rtc->month;
+    t->tm_mon = rtc->month - 1;
     t->tm_year=rtc->year;
+    if (t->tm_year < 70)
+	t->tm_year += 100;
   } else {
     rtc->second=t->tm_sec;
     rtc->minute=t->tm_min;
@@ -230,8 +232,8 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) {
     rtc->day_of_month=t->tm_mday;
     if(t->tm_wday!=-1)
       rtc->day_of_week=t->tm_wday;
-    rtc->month=t->tm_mon;
-    rtc->year=t->tm_year;
+    rtc->month = t->tm_mon + 1;
+    rtc->year = t->tm_year % 100;
   }
 
   return 0;
diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c
index 3097fa2ca746..62b0eb6cf69a 100644
--- a/arch/m68k/coldfire/pci.c
+++ b/arch/m68k/coldfire/pci.c
@@ -23,20 +23,10 @@
 
 /*
  * Memory and IO mappings. We use a 1:1 mapping for local host memory to
- * PCI bus memory (no reason not to really). IO space doesn't matter, we
- * always use access functions for that. The device configuration space is
- * mapped over the IO map space when we enable it in the PCICAR register.
+ * PCI bus memory (no reason not to really). IO space is mapped in its own
+ * separate address region. The device configuration space is mapped over
+ * the IO map space when we enable it in the PCICAR register.
  */
-#define	PCI_MEM_PA	0xf0000000		/* Host physical address */
-#define	PCI_MEM_BA	0xf0000000		/* Bus physical address */
-#define	PCI_MEM_SIZE	0x08000000		/* 128 MB */
-#define	PCI_MEM_MASK	(PCI_MEM_SIZE - 1)
-
-#define	PCI_IO_PA	0xf8000000		/* Host physical address */
-#define	PCI_IO_BA	0x00000000		/* Bus physical address */
-#define	PCI_IO_SIZE	0x00010000		/* 64k */
-#define	PCI_IO_MASK	(PCI_IO_SIZE - 1)
-
 static struct pci_bus *rootbus;
 static unsigned long iospace;
 
@@ -56,13 +46,6 @@ static unsigned char mcf_host_irq[] = {
 	0, 69, 69, 71, 71,
 };
 
-
-static inline void syncio(void)
-{
-	/* The ColdFire "nop" instruction waits for all bus IO to complete */
-	__asm__ __volatile__ ("nop");
-}
-
 /*
  * Configuration space access functions. Configuration space access is
  * through the IO mapping window, enabling it via the PCICAR register.
@@ -84,9 +67,9 @@ static int mcf_pci_readconfig(struct pci_bus *bus, unsigned int devfn,
 			return PCIBIOS_SUCCESSFUL;
 	}
 
-	syncio();
 	addr = mcf_mk_pcicar(bus->number, devfn, where);
 	__raw_writel(PCICAR_E | addr, PCICAR);
+	__raw_readl(PCICAR);
 	addr = iospace + (where & 0x3);
 
 	switch (size) {
@@ -101,8 +84,8 @@ static int mcf_pci_readconfig(struct pci_bus *bus, unsigned int devfn,
 		break;
 	}
 
-	syncio();
 	__raw_writel(0, PCICAR);
+	__raw_readl(PCICAR);
 	return PCIBIOS_SUCCESSFUL;
 }
 
@@ -116,9 +99,9 @@ static int mcf_pci_writeconfig(struct pci_bus *bus, unsigned int devfn,
 			return PCIBIOS_SUCCESSFUL;
 	}
 
-	syncio();
 	addr = mcf_mk_pcicar(bus->number, devfn, where);
 	__raw_writel(PCICAR_E | addr, PCICAR);
+	__raw_readl(PCICAR);
 	addr = iospace + (where & 0x3);
 
 	switch (size) {
@@ -133,8 +116,8 @@ static int mcf_pci_writeconfig(struct pci_bus *bus, unsigned int devfn,
 		break;
 	}
 
-	syncio();
 	__raw_writel(0, PCICAR);
+	__raw_readl(PCICAR);
 	return PCIBIOS_SUCCESSFUL;
 }
 
@@ -144,89 +127,6 @@ static struct pci_ops mcf_pci_ops = {
 };
 
 /*
- *	IO address space access functions. Pretty strait forward, these are
- *	directly mapped in to the IO mapping window. And that is mapped into
- *	virtual address space.
- */
-u8 mcf_pci_inb(u32 addr)
-{
-	return __raw_readb(iospace + (addr & PCI_IO_MASK));
-}
-EXPORT_SYMBOL(mcf_pci_inb);
-
-u16 mcf_pci_inw(u32 addr)
-{
-	return le16_to_cpu(__raw_readw(iospace + (addr & PCI_IO_MASK)));
-}
-EXPORT_SYMBOL(mcf_pci_inw);
-
-u32 mcf_pci_inl(u32 addr)
-{
-	return le32_to_cpu(__raw_readl(iospace + (addr & PCI_IO_MASK)));
-}
-EXPORT_SYMBOL(mcf_pci_inl);
-
-void mcf_pci_insb(u32 addr, u8 *buf, u32 len)
-{
-	for (; len; len--)
-		*buf++ = mcf_pci_inb(addr);
-}
-EXPORT_SYMBOL(mcf_pci_insb);
-
-void mcf_pci_insw(u32 addr, u16 *buf, u32 len)
-{
-	for (; len; len--)
-		*buf++ = mcf_pci_inw(addr);
-}
-EXPORT_SYMBOL(mcf_pci_insw);
-
-void mcf_pci_insl(u32 addr, u32 *buf, u32 len)
-{
-	for (; len; len--)
-		*buf++ = mcf_pci_inl(addr);
-}
-EXPORT_SYMBOL(mcf_pci_insl);
-
-void mcf_pci_outb(u8 v, u32 addr)
-{
-	__raw_writeb(v, iospace + (addr & PCI_IO_MASK));
-}
-EXPORT_SYMBOL(mcf_pci_outb);
-
-void mcf_pci_outw(u16 v, u32 addr)
-{
-	__raw_writew(cpu_to_le16(v), iospace + (addr & PCI_IO_MASK));
-}
-EXPORT_SYMBOL(mcf_pci_outw);
-
-void mcf_pci_outl(u32 v, u32 addr)
-{
-	__raw_writel(cpu_to_le32(v), iospace + (addr & PCI_IO_MASK));
-}
-EXPORT_SYMBOL(mcf_pci_outl);
-
-void mcf_pci_outsb(u32 addr, const u8 *buf, u32 len)
-{
-	for (; len; len--)
-		mcf_pci_outb(*buf++, addr);
-}
-EXPORT_SYMBOL(mcf_pci_outsb);
-
-void mcf_pci_outsw(u32 addr, const u16 *buf, u32 len)
-{
-	for (; len; len--)
-		mcf_pci_outw(*buf++, addr);
-}
-EXPORT_SYMBOL(mcf_pci_outsw);
-
-void mcf_pci_outsl(u32 addr, const u32 *buf, u32 len)
-{
-	for (; len; len--)
-		mcf_pci_outl(*buf++, addr);
-}
-EXPORT_SYMBOL(mcf_pci_outsl);
-
-/*
  * Initialize the PCI bus registers, and scan the bus.
  */
 static struct resource mcf_pci_mem = {
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 37a8e5ab8728..a874e54404d1 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -98,8 +98,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -204,7 +204,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -233,12 +233,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -259,7 +259,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -310,7 +310,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -414,6 +413,7 @@ CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 CONFIG_HYDRA=y
 CONFIG_APNE=y
 CONFIG_ZORRO8390=y
@@ -485,6 +485,7 @@ CONFIG_RTC_DRV_MSM6242=m
 CONFIG_RTC_DRV_RP5C01=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_HEARTBEAT=y
 CONFIG_PROC_HARDWARE=y
 CONFIG_AMIGA_BUILTIN_SERIAL=y
@@ -621,6 +622,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -647,6 +649,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 6a466266b852..8ce39e23aa42 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -96,8 +96,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -202,7 +202,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -231,12 +231,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -257,7 +257,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -308,7 +308,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -392,6 +391,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
@@ -446,6 +446,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_HEARTBEAT=y
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
@@ -580,6 +581,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -606,6 +608,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index b0691a7a3345..346c4e75edf8 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -96,8 +96,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -202,7 +202,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -231,12 +231,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -257,7 +257,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -308,7 +308,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -401,6 +400,7 @@ CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
@@ -461,6 +461,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_HEARTBEAT=y
 CONFIG_PROC_HARDWARE=y
 CONFIG_NATFEAT=y
@@ -602,6 +603,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -628,6 +630,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 6f6470fa9a50..fca9c7aa71a3 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -94,8 +94,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -200,7 +200,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -229,12 +229,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -255,7 +255,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -306,7 +306,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -391,6 +390,7 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
@@ -439,6 +439,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
@@ -572,6 +573,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -598,6 +600,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 31a1a2b5e860..f9eab174915c 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -96,8 +96,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -202,7 +202,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -231,12 +231,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -257,7 +257,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -308,7 +308,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -393,6 +392,7 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
@@ -449,6 +449,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
@@ -582,6 +583,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -608,6 +610,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 390d4a87441c..b52e597899eb 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -95,8 +95,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -201,7 +201,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -230,12 +230,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -256,7 +256,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -310,7 +310,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -410,6 +409,7 @@ CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_MACSONIC=y
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
@@ -471,6 +471,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
@@ -604,6 +605,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -630,6 +632,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 77be97d82dc3..2a84eeec5b02 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -105,8 +105,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -211,7 +211,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -240,12 +240,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -266,7 +266,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -320,7 +320,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -452,6 +451,7 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_MACSONIC=y
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 CONFIG_HYDRA=y
 CONFIG_MAC8390=y
 CONFIG_NE2000=y
@@ -541,6 +541,7 @@ CONFIG_RTC_DRV_RP5C01=m
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_HEARTBEAT=y
 CONFIG_PROC_HARDWARE=y
 CONFIG_NATFEAT=y
@@ -684,6 +685,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -710,6 +712,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 2ca140757b0f..476e69994340 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -93,8 +93,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -199,7 +199,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -228,12 +228,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -254,7 +254,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -305,7 +305,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -391,6 +390,7 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
@@ -439,6 +439,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
@@ -572,6 +573,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -598,6 +600,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 6a3b4dcc5aab..1477cda9146e 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -94,8 +94,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -200,7 +200,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -229,12 +229,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -255,7 +255,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -306,7 +306,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -391,6 +390,7 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
@@ -439,6 +439,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
@@ -572,6 +573,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -598,6 +600,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 2a3e29c97652..b3a543dc48a0 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -94,8 +94,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -200,7 +200,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -229,12 +229,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -255,7 +255,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -306,7 +306,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -400,6 +399,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
@@ -461,6 +461,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_HEARTBEAT=y
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
@@ -595,6 +596,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -621,6 +623,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index cba2494c99b2..d543ed5dfa96 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -91,8 +91,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -197,7 +197,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -226,12 +226,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -252,7 +252,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -303,7 +303,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -388,6 +387,7 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
@@ -441,6 +441,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
@@ -573,6 +574,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -599,6 +601,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index d911561137fd..a67e54246023 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -91,8 +91,8 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_RT=m
@@ -197,7 +197,7 @@ CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -226,12 +226,12 @@ CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -252,7 +252,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
@@ -303,7 +303,6 @@ CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
@@ -389,6 +388,7 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
@@ -441,6 +441,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
 CONFIG_PROC_HARDWARE=y
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
@@ -574,6 +575,7 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
@@ -600,6 +602,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 88a9d27df1ac..4d8d68c4e3dd 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,4 +1,5 @@
 generic-y += barrier.h
+generic-y += compat.h
 generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += exec.h
diff --git a/arch/m68k/include/asm/atarihw.h b/arch/m68k/include/asm/atarihw.h
index 972c8f33f055..9000b249d225 100644
--- a/arch/m68k/include/asm/atarihw.h
+++ b/arch/m68k/include/asm/atarihw.h
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <asm/bootinfo-atari.h>
 #include <asm/raw_io.h>
+#include <asm/kmap.h>
 
 extern u_long atari_mch_cookie;
 extern u_long atari_mch_type;
diff --git a/arch/m68k/include/asm/delay.h b/arch/m68k/include/asm/delay.h
index 7f474121e4ca..751712f8beea 100644
--- a/arch/m68k/include/asm/delay.h
+++ b/arch/m68k/include/asm/delay.h
@@ -49,8 +49,6 @@ extern void __bad_udelay(void);
  * The simpler m68k and ColdFire processors do not have a 32*32->64
  * multiply instruction. So we need to handle them a little differently.
  * We use a bit of shifting and a single 32*32->32 multiply to get close.
- * This is a macro so that the const version can factor out the first
- * multiply and shift.
  */
 #define	HZSCALE		(268435456 / (1000000 / HZ))
 
@@ -115,6 +113,13 @@ static inline void __udelay(unsigned long usecs)
  */
 #define	HZSCALE		(268435456 / (1000000 / HZ))
 
-#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000))
+static inline void ndelay(unsigned long nsec)
+{
+	__delay(DIV_ROUND_UP(nsec *
+			     ((((HZSCALE) >> 11) *
+			       (loops_per_jiffy >> 11)) >> 6),
+			     1000));
+}
+#define ndelay(n) ndelay(n)
 
 #endif /* defined(_M68K_DELAY_H) */
diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h
index 756089cc019c..ca2849afb087 100644
--- a/arch/m68k/include/asm/io.h
+++ b/arch/m68k/include/asm/io.h
@@ -1,14 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifdef __uClinux__
+#if defined(__uClinux__) || defined(CONFIG_COLDFIRE)
 #include <asm/io_no.h>
 #else
 #include <asm/io_mm.h>
 #endif
-
-#define readb_relaxed(addr)	readb(addr)
-#define readw_relaxed(addr)	readw(addr)
-#define readl_relaxed(addr)	readl(addr)
-
-#define writeb_relaxed(b, addr)	writeb(b, addr)
-#define writew_relaxed(b, addr)	writew(b, addr)
-#define writel_relaxed(b, addr)	writel(b, addr)
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index ed5333e87879..fe485f4f5fac 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -26,6 +26,7 @@
 #include <linux/compiler.h>
 #include <asm/raw_io.h>
 #include <asm/virtconvert.h>
+#include <asm/kmap.h>
 
 #include <asm-generic/iomap.h>
 
@@ -85,53 +86,7 @@
 #endif /* ATARI_ROM_ISA */
 
 
-#if defined(CONFIG_PCI) && defined(CONFIG_COLDFIRE)
-
-#define HAVE_ARCH_PIO_SIZE
-#define PIO_OFFSET	0
-#define PIO_MASK	0xffff
-#define PIO_RESERVED	0x10000
-
-u8 mcf_pci_inb(u32 addr);
-u16 mcf_pci_inw(u32 addr);
-u32 mcf_pci_inl(u32 addr);
-void mcf_pci_insb(u32 addr, u8 *buf, u32 len);
-void mcf_pci_insw(u32 addr, u16 *buf, u32 len);
-void mcf_pci_insl(u32 addr, u32 *buf, u32 len);
-
-void mcf_pci_outb(u8 v, u32 addr);
-void mcf_pci_outw(u16 v, u32 addr);
-void mcf_pci_outl(u32 v, u32 addr);
-void mcf_pci_outsb(u32 addr, const u8 *buf, u32 len);
-void mcf_pci_outsw(u32 addr, const u16 *buf, u32 len);
-void mcf_pci_outsl(u32 addr, const u32 *buf, u32 len);
-
-#define	inb	mcf_pci_inb
-#define	inb_p	mcf_pci_inb
-#define	inw	mcf_pci_inw
-#define	inw_p	mcf_pci_inw
-#define	inl	mcf_pci_inl
-#define	inl_p	mcf_pci_inl
-#define	insb	mcf_pci_insb
-#define	insw	mcf_pci_insw
-#define	insl	mcf_pci_insl
-
-#define	outb	mcf_pci_outb
-#define	outb_p	mcf_pci_outb
-#define	outw	mcf_pci_outw
-#define	outw_p	mcf_pci_outw
-#define	outl	mcf_pci_outl
-#define	outl_p	mcf_pci_outl
-#define	outsb	mcf_pci_outsb
-#define	outsw	mcf_pci_outsw
-#define	outsl	mcf_pci_outsl
-
-#define readb(addr)	in_8(addr)
-#define writeb(v, addr)	out_8((addr), (v))
-#define readw(addr)	in_le16(addr)
-#define writew(v, addr)	out_le16((addr), (v))
-
-#elif defined(CONFIG_ISA) || defined(CONFIG_ATARI_ROM_ISA)
+#if defined(CONFIG_ISA) || defined(CONFIG_ATARI_ROM_ISA)
 
 #if MULTI_ISA == 0
 #undef MULTI_ISA
@@ -414,8 +369,7 @@ static inline void isa_delay(void)
 #define writew(val, addr)	out_le16((addr), (val))
 #endif /* CONFIG_ATARI_ROM_ISA */
 
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA) && \
-    !(defined(CONFIG_PCI) && defined(CONFIG_COLDFIRE))
+#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
 /*
  * We need to define dummy functions for GENERIC_IOMAP support.
  */
@@ -461,39 +415,6 @@ static inline void isa_delay(void)
 
 #define mmiowb()
 
-static inline void __iomem *ioremap(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-#define ioremap_uc ioremap_nocache
-static inline void __iomem *ioremap_wt(unsigned long physaddr,
-					 unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
-}
-static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
-				      unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
-}
-
-static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count)
-{
-	__builtin_memset((void __force *) addr, val, count);
-}
-static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
-{
-	__builtin_memcpy(dst, (void __force *) src, count);
-}
-static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count)
-{
-	__builtin_memcpy((void __force *) dst, src, count);
-}
-
 #ifndef CONFIG_SUN3
 #define IO_SPACE_LIMIT 0xffff
 #else
@@ -515,13 +436,12 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int
  */
 #define xlate_dev_kmem_ptr(p)	p
 
-static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
-{
-	return (void __iomem *) port;
-}
+#define readb_relaxed(addr)	readb(addr)
+#define readw_relaxed(addr)	readw(addr)
+#define readl_relaxed(addr)	readl(addr)
 
-static inline void ioport_unmap(void __iomem *p)
-{
-}
+#define writeb_relaxed(b, addr)	writeb(b, addr)
+#define writew_relaxed(b, addr)	writew(b, addr)
+#define writel_relaxed(b, addr)	writel(b, addr)
 
 #endif /* _IO_H */
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 86f45b403bcc..83a0a6d449f4 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -2,191 +2,148 @@
 #ifndef _M68KNOMMU_IO_H
 #define _M68KNOMMU_IO_H
 
-#ifdef __KERNEL__
-
-#define ARCH_HAS_IOREMAP_WT
-
-#include <asm/virtconvert.h>
-#include <asm-generic/iomap.h>
-
 /*
- * These are for ISA/PCI shared memory _only_ and should never be used
- * on any other type of memory, including Zorro memory. They are meant to
- * access the bus in the bus byte order which is little-endian!.
- *
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the m68k architecture, we just read/write the
- * memory location directly.
- */
-/* ++roman: The assignments to temp. vars avoid that gcc sometimes generates
- * two accesses to memory, which may be undesirable for some devices.
+ * Convert a physical memory address into a IO memory address.
+ * For us this is trivially a type cast.
  */
+#define iomem(a)	((void __iomem *) (a))
 
 /*
- * swap functions are sometimes needed to interface little-endian hardware
+ * The non-MMU m68k and ColdFire IO and memory mapped hardware access
+ * functions have always worked in CPU native endian. We need to define
+ * that behavior here first before we include asm-generic/io.h.
  */
-static inline unsigned short _swapw(volatile unsigned short v)
-{
-    return ((v << 8) | (v >> 8));
-}
-
-static inline unsigned int _swapl(volatile unsigned long v)
-{
-    return ((v << 24) | ((v & 0xff00) << 8) | ((v & 0xff0000) >> 8) | (v >> 24));
-}
-
-#define readb(addr) \
+#define __raw_readb(addr) \
     ({ unsigned char __v = (*(volatile unsigned char *) (addr)); __v; })
-#define readw(addr) \
+#define __raw_readw(addr) \
     ({ unsigned short __v = (*(volatile unsigned short *) (addr)); __v; })
-#define readl(addr) \
+#define __raw_readl(addr) \
     ({ unsigned int __v = (*(volatile unsigned int *) (addr)); __v; })
 
-#define writeb(b,addr) (void)((*(volatile unsigned char *) (addr)) = (b))
-#define writew(b,addr) (void)((*(volatile unsigned short *) (addr)) = (b))
-#define writel(b,addr) (void)((*(volatile unsigned int *) (addr)) = (b))
+#define __raw_writeb(b, addr) (void)((*(volatile unsigned char *) (addr)) = (b))
+#define __raw_writew(b, addr) (void)((*(volatile unsigned short *) (addr)) = (b))
+#define __raw_writel(b, addr) (void)((*(volatile unsigned int *) (addr)) = (b))
 
-#define __raw_readb readb
-#define __raw_readw readw
-#define __raw_readl readl
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
+#if defined(CONFIG_COLDFIRE)
+/*
+ * For ColdFire platforms we may need to do some extra checks for what
+ * type of address range we are accessing. Include the ColdFire platform
+ * definitions so we can figure out if need to do something special.
+ */
+#include <asm/byteorder.h>
+#include <asm/coldfire.h>
+#include <asm/mcfsim.h>
+#endif /* CONFIG_COLDFIRE */
 
-static inline void io_outsb(unsigned int addr, const void *buf, int len)
+#if defined(IOMEMBASE)
+/*
+ * The ColdFire SoC internal peripherals are mapped into virtual address
+ * space using the ACR registers of the cache control unit. This means we
+ * are using a 1:1 physical:virtual mapping for them. We can quickly
+ * determine if we are accessing an internal peripheral device given the
+ * physical or vitrual address using the same range check. This check logic
+ * applies just the same of there is no MMU but something like a PCI bus
+ * is present.
+ */
+static int __cf_internalio(unsigned long addr)
 {
-	volatile unsigned char *ap = (volatile unsigned char *) addr;
-	unsigned char *bp = (unsigned char *) buf;
-	while (len--)
-		*ap = *bp++;
+	return (addr >= IOMEMBASE) && (addr <= IOMEMBASE + IOMEMSIZE - 1);
 }
 
-static inline void io_outsw(unsigned int addr, const void *buf, int len)
+static int cf_internalio(const volatile void __iomem *addr)
 {
-	volatile unsigned short *ap = (volatile unsigned short *) addr;
-	unsigned short *bp = (unsigned short *) buf;
-	while (len--)
-		*ap = _swapw(*bp++);
+	return __cf_internalio((unsigned long) addr);
 }
 
-static inline void io_outsl(unsigned int addr, const void *buf, int len)
+/*
+ * We need to treat built-in peripherals and bus based address ranges
+ * differently. Local built-in peripherals (and the ColdFire SoC parts
+ * have quite a lot of them) are always native endian - which is big
+ * endian on m68k/ColdFire. Bus based address ranges, like the PCI bus,
+ * are accessed little endian - so we need to byte swap those.
+ */
+#define readw readw
+static inline u16 readw(const volatile void __iomem *addr)
 {
-	volatile unsigned int *ap = (volatile unsigned int *) addr;
-	unsigned int *bp = (unsigned int *) buf;
-	while (len--)
-		*ap = _swapl(*bp++);
+	if (cf_internalio(addr))
+		return __raw_readw(addr);
+	return __le16_to_cpu(__raw_readw(addr));
 }
 
-static inline void io_insb(unsigned int addr, void *buf, int len)
+#define readl readl
+static inline u32 readl(const volatile void __iomem *addr)
 {
-	volatile unsigned char *ap = (volatile unsigned char *) addr;
-	unsigned char *bp = (unsigned char *) buf;
-	while (len--)
-		*bp++ = *ap;
+	if (cf_internalio(addr))
+		return __raw_readl(addr);
+	return __le32_to_cpu(__raw_readl(addr));
 }
 
-static inline void io_insw(unsigned int addr, void *buf, int len)
+#define writew writew
+static inline void writew(u16 value, volatile void __iomem *addr)
 {
-	volatile unsigned short *ap = (volatile unsigned short *) addr;
-	unsigned short *bp = (unsigned short *) buf;
-	while (len--)
-		*bp++ = _swapw(*ap);
+	if (cf_internalio(addr))
+		__raw_writew(value, addr);
+	else
+		__raw_writew(__cpu_to_le16(value), addr);
 }
 
-static inline void io_insl(unsigned int addr, void *buf, int len)
+#define writel writel
+static inline void writel(u32 value, volatile void __iomem *addr)
 {
-	volatile unsigned int *ap = (volatile unsigned int *) addr;
-	unsigned int *bp = (unsigned int *) buf;
-	while (len--)
-		*bp++ = _swapl(*ap);
+	if (cf_internalio(addr))
+		__raw_writel(value, addr);
+	else
+		__raw_writel(__cpu_to_le32(value), addr);
 }
 
-#define mmiowb()
-
-/*
- *	make the short names macros so specific devices
- *	can override them as required
- */
-
-#define memset_io(a,b,c)	memset((void *)(a),(b),(c))
-#define memcpy_fromio(a,b,c)	memcpy((a),(void *)(b),(c))
-#define memcpy_toio(a,b,c)	memcpy((void *)(a),(b),(c))
-
-#define inb(addr)    readb(addr)
-#define inw(addr)    readw(addr)
-#define inl(addr)    readl(addr)
-#define outb(x,addr) ((void) writeb(x,addr))
-#define outw(x,addr) ((void) writew(x,addr))
-#define outl(x,addr) ((void) writel(x,addr))
-
-#define inb_p(addr)    inb(addr)
-#define inw_p(addr)    inw(addr)
-#define inl_p(addr)    inl(addr)
-#define outb_p(x,addr) outb(x,addr)
-#define outw_p(x,addr) outw(x,addr)
-#define outl_p(x,addr) outl(x,addr)
+#else
 
-#define outsb(a,b,l) io_outsb(a,b,l)
-#define outsw(a,b,l) io_outsw(a,b,l)
-#define outsl(a,b,l) io_outsl(a,b,l)
+#define readb __raw_readb
+#define readw __raw_readw
+#define readl __raw_readl
+#define writeb __raw_writeb
+#define writew __raw_writew
+#define writel __raw_writel
 
-#define insb(a,b,l) io_insb(a,b,l)
-#define insw(a,b,l) io_insw(a,b,l)
-#define insl(a,b,l) io_insl(a,b,l)
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-
-/* Values for nocacheflag and cmode */
-#define IOMAP_FULL_CACHING		0
-#define IOMAP_NOCACHE_SER		1
-#define IOMAP_NOCACHE_NONSER		2
-#define IOMAP_WRITETHROUGH		3
-
-static inline void *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag)
-{
-	return (void *) physaddr;
-}
-static inline void *ioremap(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-static inline void *ioremap_nocache(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-static inline void *ioremap_wt(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
-}
-static inline void *ioremap_fullcache(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
-}
-
-#define	iounmap(addr)	do { } while(0)
+#endif /* IOMEMBASE */
 
+#if defined(CONFIG_PCI)
 /*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
+ * Support for PCI bus access uses the asm-generic access functions.
+ * We need to supply the base address and masks for the normal memory
+ * and IO address space mappings.
  */
-#define xlate_dev_mem_ptr(p)	__va(p)
+#define PCI_MEM_PA	0xf0000000		/* Host physical address */
+#define PCI_MEM_BA	0xf0000000		/* Bus physical address */
+#define PCI_MEM_SIZE	0x08000000		/* 128 MB */
+#define PCI_MEM_MASK	(PCI_MEM_SIZE - 1)
+
+#define PCI_IO_PA	0xf8000000		/* Host physical address */
+#define PCI_IO_BA	0x00000000		/* Bus physical address */
+#define PCI_IO_SIZE	0x00010000		/* 64k */
+#define PCI_IO_MASK	(PCI_IO_SIZE - 1)
+
+#define HAVE_ARCH_PIO_SIZE
+#define PIO_OFFSET	0
+#define PIO_MASK	0xffff
+#define PIO_RESERVED	0x10000
+#define PCI_IOBASE	((void __iomem *) PCI_IO_PA)
+#define PCI_SPACE_LIMIT	PCI_IO_MASK
+#endif /* CONFIG_PCI */
 
 /*
- * Convert a virtual cached pointer to an uncached pointer
+ * These are defined in kmap.h as static inline functions. To maintain
+ * previous behavior we put these define guards here so io_mm.h doesn't
+ * see them.
  */
-#define xlate_dev_kmem_ptr(p)	p
+#ifdef CONFIG_MMU
+#define memset_io memset_io
+#define memcpy_fromio memcpy_fromio
+#define memcpy_toio memcpy_toio
+#endif
 
-static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
-{
-	return (void __iomem *) port;
-}
-
-static inline void ioport_unmap(void __iomem *p)
-{
-}
-
-#endif /* __KERNEL__ */
+#include <asm/kmap.h>
+#include <asm/virtconvert.h>
+#include <asm-generic/io.h>
 
 #endif /* _M68KNOMMU_IO_H */
diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h
new file mode 100644
index 000000000000..84b8333db8ad
--- /dev/null
+++ b/arch/m68k/include/asm/kmap.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _KMAP_H
+#define _KMAP_H
+
+#ifdef CONFIG_MMU
+
+/* Values for nocacheflag and cmode */
+#define IOMAP_FULL_CACHING		0
+#define IOMAP_NOCACHE_SER		1
+#define IOMAP_NOCACHE_NONSER		2
+#define IOMAP_WRITETHROUGH		3
+
+/*
+ * These functions exported by arch/m68k/mm/kmap.c.
+ * Only needed on MMU enabled systems.
+ */
+extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size,
+			       int cacheflag);
+extern void iounmap(void __iomem *addr);
+extern void __iounmap(void *addr, unsigned long size);
+
+#define ioremap ioremap
+static inline void __iomem *ioremap(unsigned long physaddr, unsigned long size)
+{
+	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
+}
+
+#define ioremap_nocache ioremap_nocache
+static inline void __iomem *ioremap_nocache(unsigned long physaddr,
+					    unsigned long size)
+{
+	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
+}
+
+#define ioremap_uc ioremap_nocache
+static inline void __iomem *ioremap_wt(unsigned long physaddr,
+				       unsigned long size)
+{
+	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
+}
+
+#define ioremap_fillcache ioremap_fullcache
+static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
+					      unsigned long size)
+{
+	return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
+}
+
+static inline void memset_io(volatile void __iomem *addr, unsigned char val,
+			     int count)
+{
+	__builtin_memset((void __force *) addr, val, count);
+}
+
+static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
+				 int count)
+{
+	__builtin_memcpy(dst, (void __force *) src, count);
+}
+
+static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
+			       int count)
+{
+	__builtin_memcpy((void __force *) dst, src, count);
+}
+
+#endif /* CONFIG_MMU */
+
+#define ioport_map ioport_map
+static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	return (void __iomem *) port;
+}
+
+#define ioport_unmap ioport_unmap
+static inline void ioport_unmap(void __iomem *p)
+{
+}
+
+#endif /* _KMAP_H */
diff --git a/arch/m68k/include/asm/nubus.h b/arch/m68k/include/asm/nubus.h
index d0d2039e434e..c2281da6c51a 100644
--- a/arch/m68k/include/asm/nubus.h
+++ b/arch/m68k/include/asm/nubus.h
@@ -3,6 +3,7 @@
 #define _ASM_M68K_NUBUS_H
 
 #include <asm/raw_io.h>
+#include <asm/kmap.h>
 
 #define nubus_readb raw_inb
 #define nubus_readw raw_inw
diff --git a/arch/m68k/include/asm/pci.h b/arch/m68k/include/asm/pci.h
index ef26fae8cf0b..5a4bc223743b 100644
--- a/arch/m68k/include/asm/pci.h
+++ b/arch/m68k/include/asm/pci.h
@@ -4,12 +4,6 @@
 
 #include <asm-generic/pci.h>
 
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
 #define	pcibios_assign_all_busses()	1
 
 #define	PCIBIOS_MIN_IO		0x00000100
diff --git a/arch/m68k/include/asm/q40_master.h b/arch/m68k/include/asm/q40_master.h
index 3a89c088800c..9b00fb8079e6 100644
--- a/arch/m68k/include/asm/q40_master.h
+++ b/arch/m68k/include/asm/q40_master.h
@@ -8,7 +8,7 @@
 #define _Q40_MASTER_H
 
 #include <asm/raw_io.h>
-
+#include <asm/kmap.h>
 
 #define q40_master_addr 0xff000000
 
diff --git a/arch/m68k/include/asm/raw_io.h b/arch/m68k/include/asm/raw_io.h
index 05e940c29b54..85761255dde5 100644
--- a/arch/m68k/include/asm/raw_io.h
+++ b/arch/m68k/include/asm/raw_io.h
@@ -13,20 +13,6 @@
 
 #include <asm/byteorder.h>
 
-
-/* Values for nocacheflag and cmode */
-#define IOMAP_FULL_CACHING		0
-#define IOMAP_NOCACHE_SER		1
-#define IOMAP_NOCACHE_NONSER		2
-#define IOMAP_WRITETHROUGH		3
-
-extern void iounmap(void __iomem *addr);
-
-extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size,
-		       int cacheflag);
-extern void __iounmap(void *addr, unsigned long size);
-
-
 /* ++roman: The assignments to temp. vars avoid that gcc sometimes generates
  * two accesses to memory, which may be undesirable for some devices.
  */
diff --git a/arch/m68k/include/asm/uaccess_mm.h b/arch/m68k/include/asm/uaccess_mm.h
index 75c172e909ac..c4cb889660aa 100644
--- a/arch/m68k/include/asm/uaccess_mm.h
+++ b/arch/m68k/include/asm/uaccess_mm.h
@@ -141,10 +141,12 @@ asm volatile ("\n"					\
 	case 4:								\
 		__get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT);	\
 		break;							\
-/*	case 8:	disabled because gcc-4.1 has a broken typeof		\
- 	    {								\
- 		const void *__gu_ptr = (ptr);				\
- 		u64 __gu_val;						\
+	case 8: {							\
+		const void *__gu_ptr = (ptr);				\
+		union {							\
+			u64 l;						\
+			__typeof__(*(ptr)) t;				\
+		} __gu_val;						\
 		asm volatile ("\n"					\
 			"1:	"MOVES".l	(%2)+,%1\n"		\
 			"2:	"MOVES".l	(%2),%R1\n"		\
@@ -162,13 +164,13 @@ asm volatile ("\n"					\
 			"	.long	1b,10b\n"			\
 			"	.long	2b,10b\n"			\
 			"	.previous"				\
-			: "+d" (__gu_err), "=&r" (__gu_val),		\
+			: "+d" (__gu_err), "=&r" (__gu_val.l),		\
 			  "+a" (__gu_ptr)				\
 			: "i" (-EFAULT)					\
 			: "memory");					\
-		(x) = (__force typeof(*(ptr)))__gu_val;			\
+		(x) = __gu_val.t;					\
 		break;							\
-	    }	*/							\
+	}								\
 	default:							\
 		__gu_err = __get_user_bad();				\
 		break;							\
diff --git a/arch/m68k/include/asm/vga.h b/arch/m68k/include/asm/vga.h
index 010a624d1b39..4742e6bc3ab8 100644
--- a/arch/m68k/include/asm/vga.h
+++ b/arch/m68k/include/asm/vga.h
@@ -2,7 +2,15 @@
 #ifndef _ASM_M68K_VGA_H
 #define _ASM_M68K_VGA_H
 
+/*
+ * Some ColdFire platforms do in fact have a PCI bus. So for those we want
+ * to use the real IO access functions, don't fake them out or redirect them
+ * for that case.
+ */
+#ifndef CONFIG_PCI
+
 #include <asm/raw_io.h>
+#include <asm/kmap.h>
 
 /*
  * FIXME
@@ -25,4 +33,5 @@
 #define writeb			raw_outb
 #define writew			raw_outw
 
+#endif /* CONFIG_PCI */
 #endif /* _ASM_M68K_VGA_H */
diff --git a/arch/m68k/include/asm/virtconvert.h b/arch/m68k/include/asm/virtconvert.h
index 4aea6be7b220..dfe43083b579 100644
--- a/arch/m68k/include/asm/virtconvert.h
+++ b/arch/m68k/include/asm/virtconvert.h
@@ -16,11 +16,13 @@
 /*
  * Change virtual addresses to physical addresses and vv.
  */
+#define virt_to_phys virt_to_phys
 static inline unsigned long virt_to_phys(void *address)
 {
 	return __pa(address);
 }
 
+#define phys_to_virt phys_to_virt
 static inline void *phys_to_virt(unsigned long address)
 {
 	return __va(address);
diff --git a/arch/m68k/include/asm/zorro.h b/arch/m68k/include/asm/zorro.h
index 96f64bf7bcaa..60fc4b6f294d 100644
--- a/arch/m68k/include/asm/zorro.h
+++ b/arch/m68k/include/asm/zorro.h
@@ -3,6 +3,7 @@
 #define _ASM_M68K_ZORRO_H
 
 #include <asm/raw_io.h>
+#include <asm/kmap.h>
 
 #define z_readb raw_inb
 #define z_readw raw_inw
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index c01b9b8f97bf..463572c4943f 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -9,6 +9,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
+#include <linux/platform_device.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
@@ -165,3 +166,12 @@ const struct dma_map_ops m68k_dma_ops = {
 	.sync_sg_for_device	= m68k_dma_sync_sg_for_device,
 };
 EXPORT_SYMBOL(m68k_dma_ops);
+
+void arch_setup_pdev_archdata(struct platform_device *pdev)
+{
+	if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE &&
+	    pdev->dev.dma_mask == NULL) {
+		pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+		pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
+	}
+}
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index dd25bfc22fb4..f35e3ebd6331 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -527,21 +527,9 @@ static int hardware_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int hardware_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hardware_proc_show, NULL);
-}
-
-static const struct file_operations hardware_proc_fops = {
-	.open		= hardware_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_hardware_init(void)
 {
-	proc_create("hardware", 0, NULL, &hardware_proc_fops);
+	proc_create_single("hardware", 0, NULL, hardware_proc_show);
 	return 0;
 }
 module_init(proc_hardware_init);
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index f7cd5ecfacd3..72850b85ecf8 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -576,41 +576,42 @@ static inline int rt_save_fpu_state(struct ucontext __user *uc, struct pt_regs *
 
 static inline void siginfo_build_tests(void)
 {
-	/* This needs to be tested on m68k as it has a lesser
-	 * alignment requirment than x86 and that can cause surprises.
+	/*
+	 * This needs to be tested on m68k as it has a lesser
+	 * alignment requirement than x86 and that can cause surprises.
 	 */
 
 	/* This is part of the ABI and can never change in size: */
 	BUILD_BUG_ON(sizeof(siginfo_t) != 128);
 
-	/* Ensure the know fields never change in location */
+	/* Ensure the known fields never change in location */
 	BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_code)  != 8);
 
 	/* _kill */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x0C);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x0c);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x10);
 
 	/* _timer */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_tid)     != 0x0C);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_tid)     != 0x0c);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x10);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_value)   != 0x14);
 
 	/* _rt */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)   != 0x0C);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)   != 0x0c);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_uid)   != 0x10);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x14);
 
 	/* _sigchld */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)    != 0x0C);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)    != 0x0c);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_uid)    != 0x10);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x14);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_utime)  != 0x18);
-	BUILD_BUG_ON(offsetof(siginfo_t, si_stime)  != 0x1C);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_stime)  != 0x1c);
 
 	/* _sigfault */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x0C);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x0c);
 
 	/* _sigfault._mcerr */
 	BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x10);
@@ -623,11 +624,11 @@ static inline void siginfo_build_tests(void)
 	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x12);
 
 	/* _sigpoll */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x0C);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x0c);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_fd)     != 0x10);
 
 	/* _sigsys */
-	BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x0C);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x0c);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_syscall)   != 0x10);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_arch)      != 0x14);
 
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 97dd4e26f234..3a8b47f8f97b 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -71,23 +71,26 @@ static irqreturn_t timer_interrupt(int irq, void *dummy)
 	return IRQ_HANDLED;
 }
 
-void read_persistent_clock(struct timespec *ts)
+#ifdef CONFIG_M68KCLASSIC
+#if !IS_BUILTIN(CONFIG_RTC_DRV_GENERIC)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	struct rtc_time time;
+
 	ts->tv_sec = 0;
 	ts->tv_nsec = 0;
 
-	if (mach_hwclk) {
-		mach_hwclk(0, &time);
+	if (!mach_hwclk)
+		return;
 
-		if ((time.tm_year += 1900) < 1970)
-			time.tm_year += 100;
-		ts->tv_sec = mktime(time.tm_year, time.tm_mon, time.tm_mday,
-				      time.tm_hour, time.tm_min, time.tm_sec);
-	}
+	mach_hwclk(0, &time);
+
+	ts->tv_sec = mktime64(time.tm_year + 1900, time.tm_mon + 1, time.tm_mday,
+			      time.tm_hour, time.tm_min, time.tm_sec);
 }
+#endif
 
-#if defined(CONFIG_ARCH_USES_GETTIMEOFFSET) && IS_ENABLED(CONFIG_RTC_DRV_GENERIC)
+#if IS_ENABLED(CONFIG_RTC_DRV_GENERIC)
 static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm)
 {
 	mach_hwclk(0, tm);
@@ -145,8 +148,8 @@ static int __init rtc_init(void)
 }
 
 module_init(rtc_init);
-
-#endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */
+#endif /* CONFIG_RTC_DRV_GENERIC */
+#endif /* CONFIG M68KCLASSIC */
 
 void __init time_init(void)
 {
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index c1cc4e99aa94..b2fd000b9285 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -1007,9 +1007,9 @@ void bad_super_trap (struct frame *fp)
 
 asmlinkage void trap_c(struct frame *fp)
 {
-	int sig;
+	int sig, si_code;
+	void __user *addr;
 	int vector = (fp->ptregs.vector >> 2) & 0xff;
-	siginfo_t info;
 
 	if (fp->ptregs.sr & PS_S) {
 		if (vector == VEC_TRACE) {
@@ -1029,21 +1029,21 @@ asmlinkage void trap_c(struct frame *fp)
 	/* send the appropriate signal to the user program */
 	switch (vector) {
 	    case VEC_ADDRERR:
-		info.si_code = BUS_ADRALN;
+		si_code = BUS_ADRALN;
 		sig = SIGBUS;
 		break;
 	    case VEC_ILLEGAL:
 	    case VEC_LINE10:
 	    case VEC_LINE11:
-		info.si_code = ILL_ILLOPC;
+		si_code = ILL_ILLOPC;
 		sig = SIGILL;
 		break;
 	    case VEC_PRIV:
-		info.si_code = ILL_PRVOPC;
+		si_code = ILL_PRVOPC;
 		sig = SIGILL;
 		break;
 	    case VEC_COPROC:
-		info.si_code = ILL_COPROC;
+		si_code = ILL_COPROC;
 		sig = SIGILL;
 		break;
 	    case VEC_TRAP1:
@@ -1060,76 +1060,74 @@ asmlinkage void trap_c(struct frame *fp)
 	    case VEC_TRAP12:
 	    case VEC_TRAP13:
 	    case VEC_TRAP14:
-		info.si_code = ILL_ILLTRP;
+		si_code = ILL_ILLTRP;
 		sig = SIGILL;
 		break;
 	    case VEC_FPBRUC:
 	    case VEC_FPOE:
 	    case VEC_FPNAN:
-		info.si_code = FPE_FLTINV;
+		si_code = FPE_FLTINV;
 		sig = SIGFPE;
 		break;
 	    case VEC_FPIR:
-		info.si_code = FPE_FLTRES;
+		si_code = FPE_FLTRES;
 		sig = SIGFPE;
 		break;
 	    case VEC_FPDIVZ:
-		info.si_code = FPE_FLTDIV;
+		si_code = FPE_FLTDIV;
 		sig = SIGFPE;
 		break;
 	    case VEC_FPUNDER:
-		info.si_code = FPE_FLTUND;
+		si_code = FPE_FLTUND;
 		sig = SIGFPE;
 		break;
 	    case VEC_FPOVER:
-		info.si_code = FPE_FLTOVF;
+		si_code = FPE_FLTOVF;
 		sig = SIGFPE;
 		break;
 	    case VEC_ZERODIV:
-		info.si_code = FPE_INTDIV;
+		si_code = FPE_INTDIV;
 		sig = SIGFPE;
 		break;
 	    case VEC_CHK:
 	    case VEC_TRAP:
-		info.si_code = FPE_INTOVF;
+		si_code = FPE_INTOVF;
 		sig = SIGFPE;
 		break;
 	    case VEC_TRACE:		/* ptrace single step */
-		info.si_code = TRAP_TRACE;
+		si_code = TRAP_TRACE;
 		sig = SIGTRAP;
 		break;
 	    case VEC_TRAP15:		/* breakpoint */
-		info.si_code = TRAP_BRKPT;
+		si_code = TRAP_BRKPT;
 		sig = SIGTRAP;
 		break;
 	    default:
-		info.si_code = ILL_ILLOPC;
+		si_code = ILL_ILLOPC;
 		sig = SIGILL;
 		break;
 	}
-	info.si_signo = sig;
-	info.si_errno = 0;
 	switch (fp->ptregs.format) {
 	    default:
-		info.si_addr = (void *) fp->ptregs.pc;
+		addr = (void __user *) fp->ptregs.pc;
 		break;
 	    case 2:
-		info.si_addr = (void *) fp->un.fmt2.iaddr;
+		addr = (void __user *) fp->un.fmt2.iaddr;
 		break;
 	    case 7:
-		info.si_addr = (void *) fp->un.fmt7.effaddr;
+		addr = (void __user *) fp->un.fmt7.effaddr;
 		break;
 	    case 9:
-		info.si_addr = (void *) fp->un.fmt9.iaddr;
+		addr = (void __user *) fp->un.fmt9.iaddr;
 		break;
 	    case 10:
-		info.si_addr = (void *) fp->un.fmta.daddr;
+		addr = (void __user *) fp->un.fmta.daddr;
 		break;
 	    case 11:
-		info.si_addr = (void *) fp->un.fmtb.daddr;
+		addr = (void __user*) fp->un.fmtb.daddr;
 		break;
 	}
-	force_sig_info (sig, &info, current);
+	force_sig_fault(sig, si_code, addr, current);
 }
 
 void die_if_kernel (char *str, struct pt_regs *fp, int nr)
@@ -1161,12 +1159,6 @@ asmlinkage void fpsp040_die(void)
 #ifdef CONFIG_M68KFPU_EMU
 asmlinkage void fpemu_signal(int signal, int code, void *addr)
 {
-	siginfo_t info;
-
-	info.si_signo = signal;
-	info.si_errno = 0;
-	info.si_code = code;
-	info.si_addr = addr;
-	force_sig_info(signal, &info, current);
+	force_sig_fault(signal, code, addr, current);
 }
 #endif
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 0c3275aa0197..e522307db47c 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -1005,7 +1005,7 @@ int __init mac_platform_init(void)
 		struct resource swim_rsrc = {
 			.flags = IORESOURCE_MEM,
 			.start = (resource_size_t)swim_base,
-			.end   = (resource_size_t)swim_base + 0x2000,
+			.end   = (resource_size_t)swim_base + 0x1FFF,
 		};
 
 		platform_device_register_simple("swim", -1, &swim_rsrc, 1);
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 03253c4f8e6a..f2ff3779875a 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -21,35 +21,32 @@ extern void die_if_kernel(char *, struct pt_regs *, long);
 
 int send_fault_sig(struct pt_regs *regs)
 {
-	siginfo_t siginfo;
+	int signo, si_code;
+	void __user *addr;
 
-	clear_siginfo(&siginfo);
-	siginfo.si_signo = current->thread.signo;
-	siginfo.si_code = current->thread.code;
-	siginfo.si_addr = (void *)current->thread.faddr;
-	pr_debug("send_fault_sig: %p,%d,%d\n", siginfo.si_addr,
-		 siginfo.si_signo, siginfo.si_code);
+	signo = current->thread.signo;
+	si_code = current->thread.code;
+	addr = (void __user *)current->thread.faddr;
+	pr_debug("send_fault_sig: %p,%d,%d\n", addr, signo, si_code);
 
 	if (user_mode(regs)) {
-		force_sig_info(siginfo.si_signo,
-			       &siginfo, current);
+		force_sig_fault(signo, si_code, addr, current);
 	} else {
 		if (fixup_exception(regs))
 			return -1;
 
-		//if (siginfo.si_signo == SIGBUS)
-		//	force_sig_info(siginfo.si_signo,
-		//		       &siginfo, current);
+		//if (signo == SIGBUS)
+		//	force_sig_fault(si_signo, si_code, addr, current);
 
 		/*
 		 * Oops. The kernel tried to access some bad page. We'll have to
 		 * terminate things with extreme prejudice.
 		 */
-		if ((unsigned long)siginfo.si_addr < PAGE_SIZE)
+		if ((unsigned long)addr < PAGE_SIZE)
 			pr_alert("Unable to handle kernel NULL pointer dereference");
 		else
 			pr_alert("Unable to handle kernel access");
-		pr_cont(" at virtual address %p\n", siginfo.si_addr);
+		pr_cont(" at virtual address %p\n", addr);
 		die_if_kernel("Oops", regs, 0 /*error_code*/);
 		do_exit(SIGKILL);
 	}
diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c
index c2a38321c96d..40a3b327da07 100644
--- a/arch/m68k/mm/kmap.c
+++ b/arch/m68k/mm/kmap.c
@@ -89,7 +89,8 @@ static inline void free_io_area(void *addr)
 	for (p = &iolist ; (tmp = *p) ; p = &tmp->next) {
 		if (tmp->addr == addr) {
 			*p = tmp->next;
-			__iounmap(tmp->addr, tmp->size);
+			/* remove gap added in get_io_area() */
+			__iounmap(tmp->addr, tmp->size - IO_SIZE);
 			kfree(tmp);
 			return;
 		}
@@ -125,6 +126,10 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla
 			return (void __iomem *)physaddr;
 	}
 #endif
+#ifdef CONFIG_COLDFIRE
+	if (__cf_internalio(physaddr))
+		return (void __iomem *) physaddr;
+#endif
 
 #ifdef DEBUG
 	printk("ioremap: 0x%lx,0x%lx(%d) - ", physaddr, size, cacheflag);
@@ -235,6 +240,10 @@ void iounmap(void __iomem *addr)
 	     ((unsigned long)addr > 0x60000000)))
 			free_io_area((__force void *)addr);
 #else
+#ifdef CONFIG_COLDFIRE
+	if (cf_internalio(addr))
+		return;
+#endif
 	free_io_area((__force void *)addr);
 #endif
 }
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 8778612d1f31..f8a710fd84cd 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -153,12 +153,14 @@ int mvme147_hwclk(int op, struct rtc_time *t)
 	if (!op) {
 		m147_rtc->ctrl = RTC_READ;
 		t->tm_year = bcd2int (m147_rtc->bcd_year);
-		t->tm_mon  = bcd2int (m147_rtc->bcd_mth);
+		t->tm_mon  = bcd2int(m147_rtc->bcd_mth) - 1;
 		t->tm_mday = bcd2int (m147_rtc->bcd_dom);
 		t->tm_hour = bcd2int (m147_rtc->bcd_hr);
 		t->tm_min  = bcd2int (m147_rtc->bcd_min);
 		t->tm_sec  = bcd2int (m147_rtc->bcd_sec);
 		m147_rtc->ctrl = 0;
+		if (t->tm_year < 70)
+			t->tm_year += 100;
 	}
 	return 0;
 }
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 6fa06d4d16bf..4ffd9ef98de4 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -400,12 +400,14 @@ int mvme16x_hwclk(int op, struct rtc_time *t)
 	if (!op) {
 		rtc->ctrl = RTC_READ;
 		t->tm_year = bcd2int (rtc->bcd_year);
-		t->tm_mon  = bcd2int (rtc->bcd_mth);
+		t->tm_mon  = bcd2int(rtc->bcd_mth) - 1;
 		t->tm_mday = bcd2int (rtc->bcd_dom);
 		t->tm_hour = bcd2int (rtc->bcd_hr);
 		t->tm_min  = bcd2int (rtc->bcd_min);
 		t->tm_sec  = bcd2int (rtc->bcd_sec);
 		rtc->ctrl = 0;
+		if (t->tm_year < 70)
+			t->tm_year += 100;
 	}
 	return 0;
 }
diff --git a/arch/m68k/sun3/intersil.c b/arch/m68k/sun3/intersil.c
index 2cd0bcbe6f30..d911070af02a 100644
--- a/arch/m68k/sun3/intersil.c
+++ b/arch/m68k/sun3/intersil.c
@@ -48,9 +48,9 @@ int sun3_hwclk(int set, struct rtc_time *t)
 		todintersil->hour = t->tm_hour;
 		todintersil->minute = t->tm_min;
 		todintersil->second = t->tm_sec;
-		todintersil->month = t->tm_mon;
+		todintersil->month = t->tm_mon + 1;
 		todintersil->day = t->tm_mday;
-		todintersil->year = t->tm_year - 68;
+		todintersil->year = (t->tm_year - 68) % 100;
 		todintersil->weekday = t->tm_wday;
 	} else {
 		/* read clock */
@@ -58,10 +58,12 @@ int sun3_hwclk(int set, struct rtc_time *t)
 		t->tm_hour = todintersil->hour;
 		t->tm_min = todintersil->minute;
 		t->tm_sec = todintersil->second;
-		t->tm_mon = todintersil->month;
+		t->tm_mon = todintersil->month - 1;
 		t->tm_mday = todintersil->day;
 		t->tm_year = todintersil->year + 68;
 		t->tm_wday = todintersil->weekday;
+		if (t->tm_year < 70)
+			t->tm_year += 100;
 	}
 
 	intersil_clock->cmd_reg = START_VAL;
diff --git a/arch/m68k/sun3x/time.c b/arch/m68k/sun3x/time.c
index 7a2c53d9f779..047e2bcee3d7 100644
--- a/arch/m68k/sun3x/time.c
+++ b/arch/m68k/sun3x/time.c
@@ -52,8 +52,8 @@ int sun3x_hwclk(int set, struct rtc_time *t)
 		h->hour = bin2bcd(t->tm_hour);
 		h->wday = bin2bcd(t->tm_wday);
 		h->mday = bin2bcd(t->tm_mday);
-		h->month = bin2bcd(t->tm_mon);
-		h->year = bin2bcd(t->tm_year);
+		h->month = bin2bcd(t->tm_mon + 1);
+		h->year = bin2bcd(t->tm_year % 100);
 		h->csr &= ~C_WRITE;
 	} else {
 		h->csr |= C_READ;
@@ -62,9 +62,11 @@ int sun3x_hwclk(int set, struct rtc_time *t)
 		t->tm_hour = bcd2bin(h->hour);
 		t->tm_wday = bcd2bin(h->wday);
 		t->tm_mday = bcd2bin(h->mday);
-		t->tm_mon = bcd2bin(h->month);
+		t->tm_mon = bcd2bin(h->month) - 1;
 		t->tm_year = bcd2bin(h->year);
 		h->csr &= ~C_READ;
+		if (t->tm_year < 70)
+			t->tm_year += 100;
 	}
 
 	local_irq_restore(flags);
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 3817a3e2146c..d14782100088 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -19,7 +19,6 @@ config MICROBLAZE
 	select HAVE_ARCH_HASH
 	select HAVE_ARCH_KGDB
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 3c80a5a308ed..fe6a6c6e5003 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -2,6 +2,7 @@ generic-y += barrier.h
 generic-y += bitops.h
 generic-y += bug.h
 generic-y += bugs.h
+generic-y += compat.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index 5de871eb4a59..00337861472e 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -62,12 +62,6 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
 
 #define HAVE_PCI_LEGACY	1
 
-/* The PCI address space does equal the physical memory
- * address space (no IOMMU).  The IDE and SCSI device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS     (1)
-
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
 extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index c91e8cef98dd..3145e7dc8ab1 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -184,14 +184,3 @@ const struct dma_map_ops dma_nommu_ops = {
 	.sync_sg_for_device	= dma_nommu_sync_sg_for_device,
 };
 EXPORT_SYMBOL(dma_nommu_ops);
-
-/* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
-	return 0;
-}
-fs_initcall(dma_init);
diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c
index e6f338d0496b..eafff21fcb0e 100644
--- a/arch/microblaze/kernel/exceptions.c
+++ b/arch/microblaze/kernel/exceptions.c
@@ -60,16 +60,10 @@ asmlinkage void sw_exception(struct pt_regs *regs)
 
 void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 {
-	siginfo_t info;
-
 	if (kernel_mode(regs))
 		die("Exception in kernel mode", regs, signr);
 
-	info.si_signo = signr;
-	info.si_errno = 0;
-	info.si_code = code;
-	info.si_addr = (void __user *) addr;
-	force_sig_info(signr, &info, current);
+	force_sig_fault(signr, code, (void __user *)addr, current);
 }
 
 asmlinkage void full_exception(struct pt_regs *regs, unsigned int type,
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index f91b30f8aaa8..af607447c683 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -88,7 +88,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
-	siginfo_t info;
 	int code = SEGV_MAPERR;
 	int is_write = error_code & ESR_S;
 	int fault;
@@ -269,11 +268,6 @@ bad_area_nosemaphore:
 	/* User mode accesses cause a SIGSEGV */
 	if (user_mode(regs)) {
 		_exception(SIGSEGV, regs, code, address);
-/*		info.si_signo = SIGSEGV;
-		info.si_errno = 0;
-		info.si_code = code;
-		info.si_addr = (void *) address;
-		force_sig_info(SIGSEGV, &info, current);*/
 		return;
 	}
 
@@ -295,11 +289,7 @@ out_of_memory:
 do_sigbus:
 	up_read(&mm->mmap_sem);
 	if (user_mode(regs)) {
-		info.si_signo = SIGBUS;
-		info.si_errno = 0;
-		info.si_code = BUS_ADRERR;
-		info.si_addr = (void __user *)address;
-		force_sig_info(SIGBUS, &info, current);
+		force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, current);
 		return;
 	}
 	bad_page_fault(regs, address, SIGBUS);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 225c95da23ce..7074b2215f36 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -42,7 +42,6 @@ config MIPS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_EXIT_THREAD
@@ -132,7 +131,7 @@ config MIPS_GENERIC
 
 config MIPS_ALCHEMY
 	bool "Alchemy processor based machines"
-	select ARCH_PHYS_ADDR_T_64BIT
+	select PHYS_ADDR_T_64BIT
 	select CEVT_R4K
 	select CSRC_R4K
 	select IRQ_MIPS_CPU
@@ -890,7 +889,7 @@ config CAVIUM_OCTEON_SOC
 	bool "Cavium Networks Octeon SoC based boards"
 	select CEVT_R4K
 	select ARCH_HAS_PHYS_TO_DMA
-	select ARCH_PHYS_ADDR_T_64BIT
+	select PHYS_ADDR_T_64BIT
 	select DMA_COHERENT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
@@ -912,6 +911,7 @@ config CAVIUM_OCTEON_SOC
 	select MIPS_NR_CPU_NR_MAP_1024
 	select BUILTIN_DTB
 	select MTD_COMPLEX_MAPPINGS
+	select SWIOTLB
 	select SYS_SUPPORTS_RELOCATABLE
 	help
 	  This option supports all of the Octeon reference boards from Cavium
@@ -936,7 +936,7 @@ config NLM_XLR_BOARD
 	select SWAP_IO_SPACE
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
-	select ARCH_PHYS_ADDR_T_64BIT
+	select PHYS_ADDR_T_64BIT
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
 	select DMA_COHERENT
@@ -962,7 +962,7 @@ config NLM_XLP_BOARD
 	select HW_HAS_PCI
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
-	select ARCH_PHYS_ADDR_T_64BIT
+	select PHYS_ADDR_T_64BIT
 	select GPIOLIB
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -1101,9 +1101,6 @@ config GPIO_TXX9
 config FW_CFE
 	bool
 
-config ARCH_DMA_ADDR_T_64BIT
-	def_bool (HIGHMEM && ARCH_PHYS_ADDR_T_64BIT) || 64BIT
-
 config ARCH_SUPPORTS_UPROBES
 	bool
 
@@ -1122,9 +1119,6 @@ config DMA_NONCOHERENT
 	bool
 	select NEED_DMA_MAP_STATE
 
-config NEED_DMA_MAP_STATE
-	bool
-
 config SYS_HAS_EARLY_PRINTK
 	bool
 
@@ -1373,6 +1367,7 @@ config CPU_LOONGSON3
 	select MIPS_PGD_C0_CONTEXT
 	select MIPS_L1_CACHE_SHIFT_6
 	select GPIOLIB
+	select SWIOTLB
 	help
 		The Loongson 3 processor implements the MIPS64R2 instruction
 		set with many extensions.
@@ -1770,7 +1765,7 @@ config CPU_MIPS32_R5_XPA
 	depends on SYS_SUPPORTS_HIGHMEM
 	select XPA
 	select HIGHMEM
-	select ARCH_PHYS_ADDR_T_64BIT
+	select PHYS_ADDR_T_64BIT
 	default n
 	help
 	  Choose this option if you want to enable the Extended Physical
@@ -2402,9 +2397,6 @@ config SB1_PASS_2_1_WORKAROUNDS
 	default y
 
 
-config ARCH_PHYS_ADDR_T_64BIT
-       bool
-
 choice
 	prompt "SmartMIPS or microMIPS ASE support"
 
@@ -2556,7 +2548,7 @@ config ARCH_DISCONTIGMEM_ENABLE
 	  Say Y to support efficient handling of discontiguous physical memory,
 	  for architectures which are either NUMA (Non-Uniform Memory Access)
 	  or have huge holes in the physical address space for other reasons.
-	  See <file:Documentation/vm/numa> for more.
+	  See <file:Documentation/vm/numa.rst> for more.
 
 config ARCH_SPARSEMEM_ENABLE
 	bool
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 5e9fce076ab6..e2122cca4ae2 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -309,9 +309,6 @@ ifdef CONFIG_MIPS
 CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
 	egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \
 	sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g')
-ifdef CONFIG_64BIT
-CHECKFLAGS		+= -m64
-endif
 endif
 
 OBJCOPYFLAGS		+= --remove-section=.reginfo
diff --git a/arch/mips/boot/compressed/uart-16550.c b/arch/mips/boot/compressed/uart-16550.c
index b3043c08f769..aee8d7b8f091 100644
--- a/arch/mips/boot/compressed/uart-16550.c
+++ b/arch/mips/boot/compressed/uart-16550.c
@@ -18,9 +18,9 @@
 #define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset))
 #endif
 
-#if defined(CONFIG_MACH_JZ4740) || defined(CONFIG_MACH_JZ4780)
-#include <asm/mach-jz4740/base.h>
-#define PORT(offset) (CKSEG1ADDR(JZ4740_UART0_BASE_ADDR) + (4 * offset))
+#ifdef CONFIG_MACH_INGENIC
+#define INGENIC_UART0_BASE_ADDR	0x10030000
+#define PORT(offset) (CKSEG1ADDR(INGENIC_UART0_BASE_ADDR) + (4 * offset))
 #endif
 
 #ifdef CONFIG_CPU_XLR
diff --git a/arch/mips/boot/dts/img/boston.dts b/arch/mips/boot/dts/img/boston.dts
index 1bd105428f61..65af3f6ba81c 100644
--- a/arch/mips/boot/dts/img/boston.dts
+++ b/arch/mips/boot/dts/img/boston.dts
@@ -51,6 +51,8 @@
 		ranges = <0x02000000 0 0x40000000
 			  0x40000000 0 0x40000000>;
 
+		bus-range = <0x00 0xff>;
+
 		interrupt-map-mask = <0 0 0 7>;
 		interrupt-map = <0 0 0 1 &pci0_intc 1>,
 				<0 0 0 2 &pci0_intc 2>,
@@ -79,6 +81,8 @@
 		ranges = <0x02000000 0 0x20000000
 			  0x20000000 0 0x20000000>;
 
+		bus-range = <0x00 0xff>;
+
 		interrupt-map-mask = <0 0 0 7>;
 		interrupt-map = <0 0 0 1 &pci1_intc 1>,
 				<0 0 0 2 &pci1_intc 2>,
@@ -107,6 +111,8 @@
 		ranges = <0x02000000 0 0x16000000
 			  0x16000000 0 0x100000>;
 
+		bus-range = <0x00 0xff>;
+
 		interrupt-map-mask = <0 0 0 7>;
 		interrupt-map = <0 0 0 1 &pci2_intc 1>,
 				<0 0 0 2 &pci2_intc 2>,
diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts
index 38078594cf97..50cff3cbcc6d 100644
--- a/arch/mips/boot/dts/ingenic/ci20.dts
+++ b/arch/mips/boot/dts/ingenic/ci20.dts
@@ -36,6 +36,28 @@
 	clock-frequency = <48000000>;
 };
 
+&mmc0 {
+	status = "okay";
+
+	bus-width = <4>;
+	max-frequency = <50000000>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_mmc0>;
+
+	cd-gpios = <&gpf 20 GPIO_ACTIVE_LOW>;
+};
+
+&mmc1 {
+	status = "okay";
+
+	bus-width = <4>;
+	max-frequency = <50000000>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_mmc1>;
+};
+
 &uart0 {
 	status = "okay";
 
@@ -203,4 +225,16 @@
 		groups = "nemc-cs6";
 		bias-disable;
 	};
+
+	pins_mmc0: mmc0 {
+		function = "mmc0";
+		groups = "mmc0-1bit-e", "mmc0-4bit-e";
+		bias-disable;
+	};
+
+	pins_mmc1: mmc1 {
+		function = "mmc1";
+		groups = "mmc1-1bit-d", "mmc1-4bit-d";
+		bias-disable;
+	};
 };
diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index 9b5794667aee..b72e53bb7292 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dt-bindings/clock/jz4780-cgu.h>
+#include <dt-bindings/dma/jz4780-dma.h>
 
 / {
 	#address-cells = <1>;
@@ -241,6 +242,57 @@
 		status = "disabled";
 	};
 
+	dma: dma@13420000 {
+		compatible = "ingenic,jz4780-dma";
+		reg = <0x13420000 0x10000>;
+		#dma-cells = <2>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <10>;
+
+		clocks = <&cgu JZ4780_CLK_PDMA>;
+	};
+
+	mmc0: mmc@13450000 {
+		compatible = "ingenic,jz4780-mmc";
+		reg = <0x13450000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <37>;
+
+		clocks = <&cgu JZ4780_CLK_MSC0>;
+		clock-names = "mmc";
+
+		cap-sd-highspeed;
+		cap-mmc-highspeed;
+		cap-sdio-irq;
+		dmas = <&dma JZ4780_DMA_MSC0_RX 0xffffffff>,
+		       <&dma JZ4780_DMA_MSC0_TX 0xffffffff>;
+		dma-names = "rx", "tx";
+
+		status = "disabled";
+	};
+
+	mmc1: mmc@13460000 {
+		compatible = "ingenic,jz4780-mmc";
+		reg = <0x13460000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <36>;
+
+		clocks = <&cgu JZ4780_CLK_MSC1>;
+		clock-names = "mmc";
+
+		cap-sd-highspeed;
+		cap-mmc-highspeed;
+		cap-sdio-irq;
+		dmas = <&dma JZ4780_DMA_MSC1_RX 0xffffffff>,
+		       <&dma JZ4780_DMA_MSC1_TX 0xffffffff>;
+		dma-names = "rx", "tx";
+
+		status = "disabled";
+	};
+
 	bch: bch@134d0000 {
 		compatible = "ingenic,jz4780-bch";
 		reg = <0x134d0000 0x10000>;
diff --git a/arch/mips/boot/dts/xilfpga/Makefile b/arch/mips/boot/dts/xilfpga/Makefile
index 9987e0e378c5..69ca00590b8d 100644
--- a/arch/mips/boot/dts/xilfpga/Makefile
+++ b/arch/mips/boot/dts/xilfpga/Makefile
@@ -1,4 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0
 dtb-$(CONFIG_FIT_IMAGE_FDT_XILFPGA)	+= nexys4ddr.dtb
-
-obj-y				+= $(patsubst %.dtb, %.dtb.o, $(dtb-y))
diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig
index b5eee1a57d6c..4984e462be30 100644
--- a/arch/mips/cavium-octeon/Kconfig
+++ b/arch/mips/cavium-octeon/Kconfig
@@ -67,18 +67,6 @@ config CAVIUM_OCTEON_LOCK_L2_MEMCPY
 	help
 	  Lock the kernel's implementation of memcpy() into L2.
 
-config IOMMU_HELPER
-	bool
-
-config NEED_SG_DMA_LENGTH
-	bool
-
-config SWIOTLB
-	def_bool y
-	select DMA_DIRECT_OPS
-	select IOMMU_HELPER
-	select NEED_SG_DMA_LENGTH
-
 config OCTEON_ILM
 	tristate "Module to measure interrupt latency using Octeon CIU Timer"
 	help
diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig
index b5f4ad8f2c45..be23fd25eeaa 100644
--- a/arch/mips/configs/ci20_defconfig
+++ b/arch/mips/configs/ci20_defconfig
@@ -104,10 +104,14 @@ CONFIG_REGULATOR_FIXED_VOLTAGE=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
+CONFIG_MMC_JZ4740=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_JZ4740=y
+CONFIG_DMADEVICES=y
+CONFIG_DMA_JZ4780=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_MEMORY=y
+CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_PROC_KCORE=y
 # CONFIG_PROC_PAGE_MONITOR is not set
diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform
index b51432dd10b6..0dd0d5d460a5 100644
--- a/arch/mips/generic/Platform
+++ b/arch/mips/generic/Platform
@@ -16,3 +16,4 @@ all-$(CONFIG_MIPS_GENERIC)	:= vmlinux.gz.itb
 its-y					:= vmlinux.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_BOSTON)	+= board-boston.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_NI169445)	+= board-ni169445.its.S
+its-$(CONFIG_FIT_IMAGE_FDT_XILFPGA)	+= board-xilfpga.its.S
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 9a0fa66b81ac..78675f19440f 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -14,7 +14,6 @@
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
-typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_suseconds_t;
 
@@ -38,24 +37,16 @@ typedef struct {
 typedef s32		compat_timer_t;
 typedef s32		compat_key_t;
 
+typedef s16		compat_short_t;
 typedef s32		compat_int_t;
 typedef s32		compat_long_t;
 typedef s64		compat_s64;
+typedef u16		compat_ushort_t;
 typedef u32		compat_uint_t;
 typedef u32		compat_ulong_t;
 typedef u64		compat_u64;
 typedef u32		compat_uptr_t;
 
-struct compat_timespec {
-	compat_time_t	tv_sec;
-	s32		tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t	tv_sec;
-	s32		tv_usec;
-};
-
 struct compat_stat {
 	compat_dev_t	st_dev;
 	s32		st_pad1[3];
@@ -168,35 +159,35 @@ struct compat_ipc64_perm {
 
 struct compat_semid64_ds {
 	struct compat_ipc64_perm sem_perm;
-	compat_time_t	sem_otime;
-	compat_time_t	sem_ctime;
+	compat_ulong_t	sem_otime;
+	compat_ulong_t	sem_ctime;
 	compat_ulong_t	sem_nsems;
-	compat_ulong_t	__unused1;
-	compat_ulong_t	__unused2;
+	compat_ulong_t	sem_otime_high;
+	compat_ulong_t	sem_ctime_high;
 };
 
 struct compat_msqid64_ds {
 	struct compat_ipc64_perm msg_perm;
 #ifndef CONFIG_CPU_LITTLE_ENDIAN
-	compat_ulong_t	__unused1;
+	compat_ulong_t	msg_stime_high;
 #endif
-	compat_time_t	msg_stime;
+	compat_ulong_t	msg_stime;
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
-	compat_ulong_t	__unused1;
+	compat_ulong_t	msg_stime_high;
 #endif
 #ifndef CONFIG_CPU_LITTLE_ENDIAN
-	compat_ulong_t	__unused2;
+	compat_ulong_t	msg_rtime_high;
 #endif
-	compat_time_t	msg_rtime;
+	compat_ulong_t	msg_rtime;
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
-	compat_ulong_t	__unused2;
+	compat_ulong_t	msg_rtime_high;
 #endif
 #ifndef CONFIG_CPU_LITTLE_ENDIAN
-	compat_ulong_t	__unused3;
+	compat_ulong_t	msg_ctime_high;
 #endif
-	compat_time_t	msg_ctime;
+	compat_ulong_t	msg_ctime;
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
-	compat_ulong_t	__unused3;
+	compat_ulong_t	msg_ctime_high;
 #endif
 	compat_ulong_t	msg_cbytes;
 	compat_ulong_t	msg_qnum;
@@ -210,14 +201,16 @@ struct compat_msqid64_ds {
 struct compat_shmid64_ds {
 	struct compat_ipc64_perm shm_perm;
 	compat_size_t	shm_segsz;
-	compat_time_t	shm_atime;
-	compat_time_t	shm_dtime;
-	compat_time_t	shm_ctime;
+	compat_ulong_t	shm_atime;
+	compat_ulong_t	shm_dtime;
+	compat_ulong_t	shm_ctime;
 	compat_pid_t	shm_cpid;
 	compat_pid_t	shm_lpid;
 	compat_ulong_t	shm_nattch;
-	compat_ulong_t	__unused1;
-	compat_ulong_t	__unused2;
+	compat_ushort_t	shm_atime_high;
+	compat_ushort_t	shm_dtime_high;
+	compat_ushort_t	shm_ctime_high;
+	compat_ushort_t	__unused2;
 };
 
 /* MIPS has unusual order of fields in stack_t */
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 0cbf3af37eca..a7d0b836f2f7 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -307,7 +307,7 @@ static inline void iounmap(const volatile void __iomem *addr)
 #if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_LOONGSON3_ENHANCEMENT)
 #define war_io_reorder_wmb()		wmb()
 #else
-#define war_io_reorder_wmb()		do { } while (0)
+#define war_io_reorder_wmb()		barrier()
 #endif
 
 #define __BUILD_MEMORY_SINGLE(pfx, bwlq, type, irq)			\
@@ -377,6 +377,8 @@ static inline type pfx##read##bwlq(const volatile void __iomem *mem)	\
 		BUG();							\
 	}								\
 									\
+	/* prevent prefetching of coherent DMA data prematurely */	\
+	rmb();								\
 	return pfx##ioswab##bwlq(__mem, __val);				\
 }
 
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 2339f42f047a..436099883022 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -121,13 +121,6 @@ extern unsigned long PCIBIOS_MIN_MEM;
 #include <linux/string.h>
 #include <asm/io.h>
 
-/*
- * The PCI address space does equal the physical memory address space.
- * The networking and block device layers use this boolean for bounce
- * buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS     (1)
-
 #ifdef CONFIG_PCI_DOMAINS_GENERIC
 static inline int pci_proc_domain(struct pci_bus *bus)
 {
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index b71306947290..06629011a434 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -654,6 +654,13 @@ __clear_user(void __user *addr, __kernel_size_t size)
 {
 	__kernel_size_t res;
 
+#ifdef CONFIG_CPU_MICROMIPS
+/* micromips memset / bzero also clobbers t7 & t8 */
+#define bzero_clobbers "$4", "$5", "$6", __UA_t0, __UA_t1, "$15", "$24", "$31"
+#else
+#define bzero_clobbers "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"
+#endif /* CONFIG_CPU_MICROMIPS */
+
 	if (eva_kernel_access()) {
 		__asm__ __volatile__(
 			"move\t$4, %1\n\t"
@@ -663,7 +670,7 @@ __clear_user(void __user *addr, __kernel_size_t size)
 			"move\t%0, $6"
 			: "=r" (res)
 			: "r" (addr), "r" (size)
-			: "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+			: bzero_clobbers);
 	} else {
 		might_fault();
 		__asm__ __volatile__(
@@ -674,7 +681,7 @@ __clear_user(void __user *addr, __kernel_size_t size)
 			"move\t%0, $6"
 			: "=r" (res)
 			: "r" (addr), "r" (size)
-			: "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+			: bzero_clobbers);
 	}
 
 	return res;
diff --git a/arch/mips/include/uapi/asm/msgbuf.h b/arch/mips/include/uapi/asm/msgbuf.h
index eb4d0f9d7364..46aa15b13e4e 100644
--- a/arch/mips/include/uapi/asm/msgbuf.h
+++ b/arch/mips/include/uapi/asm/msgbuf.h
@@ -9,33 +9,15 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - extension of time_t to 64-bit on 32-bitsystem to solve the y2038 problem
  * - 2 miscellaneous unsigned long values
  */
 
+#if defined(__mips64)
 struct msqid64_ds {
 	struct ipc64_perm msg_perm;
-#if !defined(__mips64) && defined(__MIPSEB__)
-	unsigned long	__unused1;
-#endif
 	__kernel_time_t msg_stime;	/* last msgsnd time */
-#if !defined(__mips64) && defined(__MIPSEL__)
-	unsigned long	__unused1;
-#endif
-#if !defined(__mips64) && defined(__MIPSEB__)
-	unsigned long	__unused2;
-#endif
 	__kernel_time_t msg_rtime;	/* last msgrcv time */
-#if !defined(__mips64) && defined(__MIPSEL__)
-	unsigned long	__unused2;
-#endif
-#if !defined(__mips64) && defined(__MIPSEB__)
-	unsigned long	__unused3;
-#endif
 	__kernel_time_t msg_ctime;	/* last change time */
-#if !defined(__mips64) && defined(__MIPSEL__)
-	unsigned long	__unused3;
-#endif
 	unsigned long  msg_cbytes;	/* current number of bytes on queue */
 	unsigned long  msg_qnum;	/* number of messages in queue */
 	unsigned long  msg_qbytes;	/* max number of bytes on queue */
@@ -44,5 +26,42 @@ struct msqid64_ds {
 	unsigned long  __unused4;
 	unsigned long  __unused5;
 };
+#elif defined (__MIPSEB__)
+struct msqid64_ds {
+	struct ipc64_perm msg_perm;
+	unsigned long  msg_stime_high;
+	unsigned long  msg_stime;	/* last msgsnd time */
+	unsigned long  msg_rtime_high;
+	unsigned long  msg_rtime;	/* last msgrcv time */
+	unsigned long  msg_ctime_high;
+	unsigned long  msg_ctime;	/* last change time */
+	unsigned long  msg_cbytes;	/* current number of bytes on queue */
+	unsigned long  msg_qnum;	/* number of messages in queue */
+	unsigned long  msg_qbytes;	/* max number of bytes on queue */
+	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
+	__kernel_pid_t msg_lrpid;	/* last receive pid */
+	unsigned long  __unused4;
+	unsigned long  __unused5;
+};
+#elif defined (__MIPSEL__)
+struct msqid64_ds {
+	struct ipc64_perm msg_perm;
+	unsigned long  msg_stime;	/* last msgsnd time */
+	unsigned long  msg_stime_high;
+	unsigned long  msg_rtime;	/* last msgrcv time */
+	unsigned long  msg_rtime_high;
+	unsigned long  msg_ctime;	/* last change time */
+	unsigned long  msg_ctime_high;
+	unsigned long  msg_cbytes;	/* current number of bytes on queue */
+	unsigned long  msg_qnum;	/* number of messages in queue */
+	unsigned long  msg_qbytes;	/* max number of bytes on queue */
+	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
+	__kernel_pid_t msg_lrpid;	/* last receive pid */
+	unsigned long  __unused4;
+	unsigned long  __unused5;
+};
+#else
+#warning no endianess set
+#endif
 
 #endif /* _ASM_MSGBUF_H */
diff --git a/arch/mips/include/uapi/asm/sembuf.h b/arch/mips/include/uapi/asm/sembuf.h
index 2c0f507ab7d1..60c89e6cb25b 100644
--- a/arch/mips/include/uapi/asm/sembuf.h
+++ b/arch/mips/include/uapi/asm/sembuf.h
@@ -7,10 +7,11 @@
  * Note extra padding because this structure is passed back and forth
  * between kernel and user space.
  *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
+ * Pad space is left for 2 miscellaneous 64-bit values on mips64,
+ * but used for the upper 32 bit of the time values on mips32.
  */
 
+#ifdef __mips64
 struct semid64_ds {
 	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
 	__kernel_time_t sem_otime;		/* last semop time */
@@ -19,5 +20,15 @@ struct semid64_ds {
 	unsigned long	__unused1;
 	unsigned long	__unused2;
 };
+#else
+struct semid64_ds {
+	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
+	unsigned long   sem_otime;		/* last semop time */
+	unsigned long   sem_ctime;		/* last change time */
+	unsigned long	sem_nsems;		/* no. of semaphores in array */
+	unsigned long	sem_otime_high;
+	unsigned long	sem_ctime_high;
+};
+#endif
 
 #endif /* _ASM_SEMBUF_H */
diff --git a/arch/mips/include/uapi/asm/shmbuf.h b/arch/mips/include/uapi/asm/shmbuf.h
index 379e6bca518b..9b9bba3401f2 100644
--- a/arch/mips/include/uapi/asm/shmbuf.h
+++ b/arch/mips/include/uapi/asm/shmbuf.h
@@ -7,10 +7,13 @@
  * Note extra padding because this structure is passed back and forth
  * between kernel and user space.
  *
- * Pad space is left for:
- * - 2 miscellaneous 32-bit rsp. 64-bit values
+ * As MIPS was lacking proper padding after shm_?time, we use 48 bits
+ * of the padding at the end to store a few additional bits of the time.
+ * libc implementations need to take care to convert this into a proper
+ * data structure when moving to 64-bit time_t.
  */
 
+#ifdef __mips64
 struct shmid64_ds {
 	struct ipc64_perm	shm_perm;	/* operation perms */
 	size_t			shm_segsz;	/* size of segment (bytes) */
@@ -23,6 +26,22 @@ struct shmid64_ds {
 	unsigned long		__unused1;
 	unsigned long		__unused2;
 };
+#else
+struct shmid64_ds {
+	struct ipc64_perm	shm_perm;	/* operation perms */
+	size_t			shm_segsz;	/* size of segment (bytes) */
+	unsigned long		shm_atime;	/* last attach time */
+	unsigned long		shm_dtime;	/* last detach time */
+	unsigned long		shm_ctime;	/* last change time */
+	__kernel_pid_t		shm_cpid;	/* pid of creator */
+	__kernel_pid_t		shm_lpid;	/* pid of last operator */
+	unsigned long		shm_nattch;	/* no. of current attaches */
+	unsigned short		shm_atime_high;
+	unsigned short		shm_dtime_high;
+	unsigned short		shm_ctime_high;
+	unsigned short		__unused1;
+};
+#endif
 
 struct shminfo64 {
 	unsigned long	shmmax;
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index b9e9bf628849..3775a8d694fb 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -721,6 +721,10 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	if (value & ~known_bits)
 		return -EOPNOTSUPP;
 
+	/* Setting FRE without FR is not supported.  */
+	if ((value & (PR_FP_MODE_FR | PR_FP_MODE_FRE)) == PR_FP_MODE_FRE)
+		return -EOPNOTSUPP;
+
 	/* Avoid inadvertently triggering emulation */
 	if ((value & PR_FP_MODE_FR) && raw_cpu_has_fpu &&
 	    !(raw_current_cpu_data.fpu_id & MIPS_FPIR_F64))
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 0b23b1ad99e6..0c0c23c9c9f5 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -463,7 +463,7 @@ static int fpr_get_msa(struct task_struct *target,
 /*
  * Copy the floating-point context to the supplied NT_PRFPREG buffer.
  * Choose the appropriate helper for general registers, and then copy
- * the FCSR register separately.
+ * the FCSR and FIR registers separately.
  */
 static int fpr_get(struct task_struct *target,
 		   const struct user_regset *regset,
@@ -471,6 +471,7 @@ static int fpr_get(struct task_struct *target,
 		   void *kbuf, void __user *ubuf)
 {
 	const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+	const int fir_pos = fcr31_pos + sizeof(u32);
 	int err;
 
 	if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
@@ -483,6 +484,12 @@ static int fpr_get(struct task_struct *target,
 	err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				  &target->thread.fpu.fcr31,
 				  fcr31_pos, fcr31_pos + sizeof(u32));
+	if (err)
+		return err;
+
+	err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &boot_cpu_data.fpu_id,
+				  fir_pos, fir_pos + sizeof(u32));
 
 	return err;
 }
@@ -531,7 +538,8 @@ static int fpr_set_msa(struct task_struct *target,
 /*
  * Copy the supplied NT_PRFPREG buffer to the floating-point context.
  * Choose the appropriate helper for general registers, and then copy
- * the FCSR register separately.
+ * the FCSR register separately.  Ignore the incoming FIR register
+ * contents though, as the register is read-only.
  *
  * We optimize for the case where `count % sizeof(elf_fpreg_t) == 0',
  * which is supposed to have been guaranteed by the kernel before
@@ -545,6 +553,7 @@ static int fpr_set(struct task_struct *target,
 		   const void *kbuf, const void __user *ubuf)
 {
 	const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+	const int fir_pos = fcr31_pos + sizeof(u32);
 	u32 fcr31;
 	int err;
 
@@ -572,6 +581,11 @@ static int fpr_set(struct task_struct *target,
 		ptrace_setfcr31(target, fcr31);
 	}
 
+	if (count > 0)
+		err = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+						fir_pos,
+						fir_pos + sizeof(u32));
+
 	return err;
 }
 
@@ -793,7 +807,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			fregs = get_fpu_regs(child);
 
 #ifdef CONFIG_32BIT
-			if (test_thread_flag(TIF_32BIT_FPREGS)) {
+			if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
 				/*
 				 * The odd registers are actually the high
 				 * order bits of the values stored in the even
@@ -804,7 +818,7 @@ long arch_ptrace(struct task_struct *child, long request,
 				break;
 			}
 #endif
-			tmp = get_fpr32(&fregs[addr - FPR_BASE], 0);
+			tmp = get_fpr64(&fregs[addr - FPR_BASE], 0);
 			break;
 		case PC:
 			tmp = regs->cp0_epc;
@@ -888,7 +902,7 @@ long arch_ptrace(struct task_struct *child, long request,
 
 			init_fp_ctx(child);
 #ifdef CONFIG_32BIT
-			if (test_thread_flag(TIF_32BIT_FPREGS)) {
+			if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
 				/*
 				 * The odd registers are actually the high
 				 * order bits of the values stored in the even
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 2b9260f92ccd..f30c381d3e1c 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -99,7 +99,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 				break;
 			}
 			fregs = get_fpu_regs(child);
-			if (test_thread_flag(TIF_32BIT_FPREGS)) {
+			if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
 				/*
 				 * The odd registers are actually the high
 				 * order bits of the values stored in the even
@@ -109,7 +109,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 						addr & 1);
 				break;
 			}
-			tmp = get_fpr32(&fregs[addr - FPR_BASE], 0);
+			tmp = get_fpr64(&fregs[addr - FPR_BASE], 0);
 			break;
 		case PC:
 			tmp = regs->cp0_epc;
@@ -212,7 +212,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 				       sizeof(child->thread.fpu));
 				child->thread.fpu.fcr31 = 0;
 			}
-			if (test_thread_flag(TIF_32BIT_FPREGS)) {
+			if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
 				/*
 				 * The odd registers are actually the high
 				 * order bits of the values stored in the even
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index c4db910a8794..b5d9e1784aff 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -8,13 +8,13 @@
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
  * Copyright (C) 2016, Imagination Technologies Ltd.
  */
+#include <linux/compat.h>
 #include <linux/compiler.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/syscalls.h>
 
-#include <asm/compat.h>
 #include <asm/compat-signal.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 967e9e4e795e..d67fa74622ee 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -699,17 +699,11 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
 asmlinkage void do_ov(struct pt_regs *regs)
 {
 	enum ctx_state prev_state;
-	siginfo_t info;
-
-	clear_siginfo(&info);
-	info.si_signo = SIGFPE;
-	info.si_code = FPE_INTOVF;
-	info.si_addr = (void __user *)regs->cp0_epc;
 
 	prev_state = exception_enter();
 	die_if_kernel("Integer overflow", regs);
 
-	force_sig_info(SIGFPE, &info, current);
+	force_sig_fault(SIGFPE, FPE_INTOVF, (void __user *)regs->cp0_epc, current);
 	exception_exit(prev_state);
 }
 
@@ -722,32 +716,27 @@ asmlinkage void do_ov(struct pt_regs *regs)
 void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
 		     struct task_struct *tsk)
 {
-	struct siginfo si;
-
-	clear_siginfo(&si);
-	si.si_addr = fault_addr;
-	si.si_signo = SIGFPE;
+	int si_code = FPE_FLTUNK;
 
 	if (fcr31 & FPU_CSR_INV_X)
-		si.si_code = FPE_FLTINV;
+		si_code = FPE_FLTINV;
 	else if (fcr31 & FPU_CSR_DIV_X)
-		si.si_code = FPE_FLTDIV;
+		si_code = FPE_FLTDIV;
 	else if (fcr31 & FPU_CSR_OVF_X)
-		si.si_code = FPE_FLTOVF;
+		si_code = FPE_FLTOVF;
 	else if (fcr31 & FPU_CSR_UDF_X)
-		si.si_code = FPE_FLTUND;
+		si_code = FPE_FLTUND;
 	else if (fcr31 & FPU_CSR_INE_X)
-		si.si_code = FPE_FLTRES;
+		si_code = FPE_FLTRES;
 
-	force_sig_info(SIGFPE, &si, tsk);
+	force_sig_fault(SIGFPE, si_code, fault_addr, tsk);
 }
 
 int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 {
-	struct siginfo si;
+	int si_code;
 	struct vm_area_struct *vma;
 
-	clear_siginfo(&si);
 	switch (sig) {
 	case 0:
 		return 0;
@@ -757,23 +746,18 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 		return 1;
 
 	case SIGBUS:
-		si.si_addr = fault_addr;
-		si.si_signo = sig;
-		si.si_code = BUS_ADRERR;
-		force_sig_info(sig, &si, current);
+		force_sig_fault(SIGBUS, BUS_ADRERR, fault_addr, current);
 		return 1;
 
 	case SIGSEGV:
-		si.si_addr = fault_addr;
-		si.si_signo = sig;
 		down_read(&current->mm->mmap_sem);
 		vma = find_vma(current->mm, (unsigned long)fault_addr);
 		if (vma && (vma->vm_start <= (unsigned long)fault_addr))
-			si.si_code = SEGV_ACCERR;
+			si_code = SEGV_ACCERR;
 		else
-			si.si_code = SEGV_MAPERR;
+			si_code = SEGV_MAPERR;
 		up_read(&current->mm->mmap_sem);
-		force_sig_info(sig, &si, current);
+		force_sig_fault(SIGSEGV, si_code, fault_addr, current);
 		return 1;
 
 	default:
@@ -896,10 +880,8 @@ out:
 void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
 	const char *str)
 {
-	siginfo_t info;
 	char b[40];
 
-	clear_siginfo(&info);
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_TRAP, str, regs, code, current->thread.trap_nr,
 			 SIGTRAP) == NOTIFY_STOP)
@@ -921,13 +903,9 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
 	case BRK_DIVZERO:
 		scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
 		die_if_kernel(b, regs);
-		if (code == BRK_DIVZERO)
-			info.si_code = FPE_INTDIV;
-		else
-			info.si_code = FPE_INTOVF;
-		info.si_signo = SIGFPE;
-		info.si_addr = (void __user *) regs->cp0_epc;
-		force_sig_info(SIGFPE, &info, current);
+		force_sig_fault(SIGFPE,
+				code == BRK_DIVZERO ? FPE_INTDIV : FPE_INTOVF,
+				(void __user *) regs->cp0_epc, current);
 		break;
 	case BRK_BUG:
 		die_if_kernel("Kernel bug detected", regs);
@@ -952,9 +930,7 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
 		scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
 		die_if_kernel(b, regs);
 		if (si_code) {
-			info.si_signo = SIGTRAP;
-			info.si_code = si_code;
-			force_sig_info(SIGTRAP, &info, current);
+			force_sig_fault(SIGTRAP, si_code, NULL,	current);
 		} else {
 			force_sig(SIGTRAP, current);
 		}
@@ -1506,13 +1482,8 @@ asmlinkage void do_mdmx(struct pt_regs *regs)
  */
 asmlinkage void do_watch(struct pt_regs *regs)
 {
-	siginfo_t info;
 	enum ctx_state prev_state;
 
-	clear_siginfo(&info);
-	info.si_signo = SIGTRAP;
-	info.si_code = TRAP_HWBKPT;
-
 	prev_state = exception_enter();
 	/*
 	 * Clear WP (bit 22) bit of cause register so we don't loop
@@ -1528,7 +1499,7 @@ asmlinkage void do_watch(struct pt_regs *regs)
 	if (test_tsk_thread_flag(current, TIF_LOAD_WATCH)) {
 		mips_read_watch_registers();
 		local_irq_enable();
-		force_sig_info(SIGTRAP, &info, current);
+		force_sig_fault(SIGTRAP, TRAP_HWBKPT, NULL, current);
 	} else {
 		mips_clear_watch_registers();
 		local_irq_enable();
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 2549fdd27ee1..0f725e9cee8f 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -45,7 +45,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "cache",	  VCPU_STAT(cache_exits),	 KVM_STAT_VCPU },
 	{ "signal",	  VCPU_STAT(signal_exits),	 KVM_STAT_VCPU },
 	{ "interrupt",	  VCPU_STAT(int_exits),		 KVM_STAT_VCPU },
-	{ "cop_unsuable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU },
+	{ "cop_unusable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU },
 	{ "tlbmod",	  VCPU_STAT(tlbmod_exits),	 KVM_STAT_VCPU },
 	{ "tlbmiss_ld",	  VCPU_STAT(tlbmiss_ld_exits),	 KVM_STAT_VCPU },
 	{ "tlbmiss_st",	  VCPU_STAT(tlbmiss_st_exits),	 KVM_STAT_VCPU },
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index a1456664d6c2..f7327979a8f8 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -219,7 +219,7 @@
 1:	PTR_ADDIU	a0, 1			/* fill bytewise */
 	R10KCBARRIER(0(ra))
 	bne		t1, a0, 1b
-	sb		a1, -1(a0)
+	 EX(sb, a1, -1(a0), .Lsmall_fixup\@)
 
 2:	jr		ra			/* done */
 	move		a2, zero
@@ -252,13 +252,18 @@
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, STORMASK
 	LONG_L		t0, THREAD_BUADDR(t0)
-	LONG_ADDU	a2, t1
+	LONG_ADDU	a2, a0
 	jr		ra
 	LONG_SUBU	a2, t0
 
 .Llast_fixup\@:
 	jr		ra
-	andi		v1, a2, STORMASK
+	 nop
+
+.Lsmall_fixup\@:
+	PTR_SUBU	a2, t1, a0
+	jr		ra
+	 PTR_ADDIU	a2, 1
 
 	.endm
 
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index 72af0c183969..c79e6a565572 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -130,21 +130,6 @@ config LOONGSON_UART_BASE
 	default y
 	depends on EARLY_PRINTK || SERIAL_8250
 
-config IOMMU_HELPER
-	bool
-
-config NEED_SG_DMA_LENGTH
-	bool
-
-config SWIOTLB
-	bool "Soft IOMMU Support for All-Memory DMA"
-	default y
-	depends on CPU_LOONGSON3
-	select DMA_DIRECT_OPS
-	select IOMMU_HELPER
-	select NEED_SG_DMA_LENGTH
-	select NEED_DMA_MAP_STATE
-
 config PHYS48_TO_HT40
 	bool
 	default y if CPU_LOONGSON3
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 6f534b209971..e12dfa48b478 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -851,9 +851,12 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 	/*
 	 * Either no secondary cache or the available caches don't have the
 	 * subset property so we have to flush the primary caches
-	 * explicitly
+	 * explicitly.
+	 * If we would need IPI to perform an INDEX-type operation, then
+	 * we have to use the HIT-type alternative as IPI cannot be used
+	 * here due to interrupts possibly being disabled.
 	 */
-	if (size >= dcache_size) {
+	if (!r4k_op_needs_ipi(R4K_INDEX) && size >= dcache_size) {
 		r4k_blast_dcache();
 	} else {
 		R4600_HIT_CACHEOP_WAR_IMPL;
@@ -890,7 +893,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 		return;
 	}
 
-	if (size >= dcache_size) {
+	if (!r4k_op_needs_ipi(R4K_INDEX) && size >= dcache_size) {
 		r4k_blast_dcache();
 	} else {
 		R4600_HIT_CACHEOP_WAR_IMPL;
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index dcafa43613b6..f9fef0028ca2 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -402,13 +402,3 @@ static const struct dma_map_ops mips_default_dma_map_ops = {
 
 const struct dma_map_ops *mips_dma_map_ops = &mips_default_dma_map_ops;
 EXPORT_SYMBOL(mips_dma_map_ops);
-
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init mips_dma_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
-	return 0;
-}
-fs_initcall(mips_dma_init);
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 4f8f5bf46977..5f71f2b903b7 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -42,7 +42,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 	const int field = sizeof(unsigned long) * 2;
-	siginfo_t info;
+	int si_code;
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
@@ -63,7 +63,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 		return;
 #endif
 
-	info.si_code = SEGV_MAPERR;
+	si_code = SEGV_MAPERR;
 
 	/*
 	 * We fault-in kernel-space virtual memory on-demand. The
@@ -112,7 +112,7 @@ retry:
  * we can handle it..
  */
 good_area:
-	info.si_code = SEGV_ACCERR;
+	si_code = SEGV_ACCERR;
 
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
@@ -223,11 +223,7 @@ bad_area_nosemaphore:
 			pr_cont("\n");
 		}
 		current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
-		info.si_signo = SIGSEGV;
-		info.si_errno = 0;
-		/* info.si_code has been set above */
-		info.si_addr = (void __user *) address;
-		force_sig_info(SIGSEGV, &info, tsk);
+		force_sig_fault(SIGSEGV, si_code, (void __user *)address, tsk);
 		return;
 	}
 
@@ -283,11 +279,7 @@ do_sigbus:
 #endif
 	current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
 	tsk->thread.cp0_badvaddr = address;
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRERR;
-	info.si_addr = (void __user *) address;
-	force_sig_info(SIGBUS, &info, tsk);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, tsk);
 
 	return;
 #ifndef CONFIG_64BIT
diff --git a/arch/mips/netlogic/Kconfig b/arch/mips/netlogic/Kconfig
index 7fcfc7fe9f14..412351c5acc6 100644
--- a/arch/mips/netlogic/Kconfig
+++ b/arch/mips/netlogic/Kconfig
@@ -83,10 +83,4 @@ endif
 config NLM_COMMON
 	bool
 
-config IOMMU_HELPER
-	bool
-
-config NEED_SG_DMA_LENGTH
-	bool
-
 endif
diff --git a/arch/mips/pci/ops-pmcmsp.c b/arch/mips/pci/ops-pmcmsp.c
index dd2d9f7e9412..7649372103af 100644
--- a/arch/mips/pci/ops-pmcmsp.c
+++ b/arch/mips/pci/ops-pmcmsp.c
@@ -83,18 +83,6 @@ static int show_msp_pci_counts(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int msp_pci_rd_cnt_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, show_msp_pci_counts, NULL);
-}
-
-static const struct file_operations msp_pci_rd_cnt_fops = {
-	.open		= msp_pci_rd_cnt_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /*****************************************************************************
  *
  *  FUNCTION: gen_pci_cfg_wr_show
@@ -160,18 +148,6 @@ static int gen_pci_cfg_wr_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int gen_pci_cfg_wr_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, gen_pci_cfg_wr_show, NULL);
-}
-
-static const struct file_operations gen_pci_cfg_wr_fops = {
-	.open		= gen_pci_cfg_wr_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /*****************************************************************************
  *
  *  FUNCTION: pci_proc_init
@@ -188,8 +164,8 @@ static const struct file_operations gen_pci_cfg_wr_fops = {
  ****************************************************************************/
 static void pci_proc_init(void)
 {
-	proc_create("pmc_msp_pci_rd_cnt", 0, NULL, &msp_pci_rd_cnt_fops);
-	proc_create("pmc_msp_pci_cfg_wr", 0, NULL, &gen_pci_cfg_wr_fops);
+	proc_create_single("pmc_msp_pci_rd_cnt", 0, NULL, show_msp_pci_counts);
+	proc_create_single("pmc_msp_pci_cfg_wr", 0, NULL, gen_pci_cfg_wr_show);
 }
 #endif /* CONFIG_PROC_FS && PCI_COUNTERS */
 
diff --git a/arch/mips/sibyte/common/bus_watcher.c b/arch/mips/sibyte/common/bus_watcher.c
index a4e55999ecb4..4bb85de9229b 100644
--- a/arch/mips/sibyte/common/bus_watcher.c
+++ b/arch/mips/sibyte/common/bus_watcher.c
@@ -142,24 +142,12 @@ static int bw_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int bw_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, bw_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations bw_proc_fops = {
-	.open		= bw_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static void create_proc_decoder(struct bw_stats_struct *stats)
 {
 	struct proc_dir_entry *ent;
 
-	ent = proc_create_data("bus_watcher", S_IWUSR | S_IRUGO, NULL,
-			       &bw_proc_fops, stats);
+	ent = proc_create_single_data("bus_watcher", S_IWUSR | S_IRUGO, NULL,
+			bw_proc_show, stats);
 	if (!ent) {
 		printk(KERN_INFO "Unable to initialize bus_watcher /proc entry\n");
 		return;
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 249f38d3388f..6aed974276d8 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -5,10 +5,19 @@
 
 config NDS32
         def_bool y
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_WANT_FRAME_POINTERS if FTRACE
 	select CLKSRC_MMIO
 	select CLONE_BACKWARDS
 	select COMMON_CLK
+	select DMA_NONCOHERENT_OPS
+	select GENERIC_ASHLDI3
+	select GENERIC_ASHRDI3
+	select GENERIC_LSHRDI3
+	select GENERIC_CMPDI2
+	select GENERIC_MULDI3
+	select GENERIC_UCMPDI2
 	select GENERIC_ATOMIC64
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
@@ -82,6 +91,7 @@ endmenu
 
 menu "Kernel Features"
 source "kernel/Kconfig.preempt"
+source "kernel/Kconfig.freezer"
 source "mm/Kconfig"
 source "kernel/Kconfig.hz"
 endmenu
diff --git a/arch/nds32/Kconfig.cpu b/arch/nds32/Kconfig.cpu
index ba44cc539da9..b8c8984d1456 100644
--- a/arch/nds32/Kconfig.cpu
+++ b/arch/nds32/Kconfig.cpu
@@ -1,10 +1,11 @@
 comment "Processor Features"
 
 config CPU_BIG_ENDIAN
-	bool "Big endian"
+	def_bool !CPU_LITTLE_ENDIAN
 
 config CPU_LITTLE_ENDIAN
-        def_bool !CPU_BIG_ENDIAN
+	bool "Little endian"
+	default y
 
 config HWZOL
 	bool "hardware zero overhead loop support"
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 91f933d5a962..513bb2e9baf9 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -23,9 +23,6 @@ export	TEXTADDR
 # If we have a machine-specific directory, then include it in the build.
 core-y				+= arch/nds32/kernel/ arch/nds32/mm/
 libs-y				+= arch/nds32/lib/
-LIBGCC_PATH     		:= \
-  $(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name)
-libs-y				+= $(LIBGCC_PATH)
 
 ifneq '$(CONFIG_NDS32_BUILTIN_DTB)' '""'
 BUILTIN_DTB := y
@@ -35,8 +32,12 @@ endif
 
 ifdef CONFIG_CPU_LITTLE_ENDIAN
 KBUILD_CFLAGS   += $(call cc-option, -EL)
+KBUILD_AFLAGS   += $(call cc-option, -EL)
+LDFLAGS         += $(call cc-option, -EL)
 else
 KBUILD_CFLAGS   += $(call cc-option, -EB)
+KBUILD_AFLAGS   += $(call cc-option, -EB)
+LDFLAGS         += $(call cc-option, -EB)
 endif
 
 boot := arch/nds32/boot
diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild
index 06bdf8167f5a..dbc4e5422550 100644
--- a/arch/nds32/include/asm/Kbuild
+++ b/arch/nds32/include/asm/Kbuild
@@ -9,13 +9,16 @@ generic-y += checksum.h
 generic-y += clkdev.h
 generic-y += cmpxchg.h
 generic-y += cmpxchg-local.h
+generic-y += compat.h
 generic-y += cputime.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += export.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
@@ -49,6 +52,7 @@ generic-y += switch_to.h
 generic-y += timex.h
 generic-y += topology.h
 generic-y += trace_clock.h
+generic-y += xor.h
 generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
diff --git a/arch/nds32/include/asm/bitfield.h b/arch/nds32/include/asm/bitfield.h
index c73f71d67744..8e84fc385b94 100644
--- a/arch/nds32/include/asm/bitfield.h
+++ b/arch/nds32/include/asm/bitfield.h
@@ -336,7 +336,7 @@
 #define INT_MASK_mskIDIVZE	( 0x1  << INT_MASK_offIDIVZE )
 #define INT_MASK_mskDSSIM	( 0x1  << INT_MASK_offDSSIM )
 
-#define INT_MASK_INITAIAL_VAL	0x10003
+#define INT_MASK_INITAIAL_VAL	(INT_MASK_mskDSSIM|INT_MASK_mskIDIVZE)
 
 /******************************************************************************
  * ir15: INT_PEND (Interrupt Pending Register)
@@ -396,6 +396,7 @@
 #define MMU_CTL_D8KB		1
 #define MMU_CTL_UNA		( 0x1  << MMU_CTL_offUNA )
 
+#define MMU_CTL_CACHEABLE_NON   0
 #define MMU_CTL_CACHEABLE_WB	2
 #define MMU_CTL_CACHEABLE_WT	3
 
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index 1240f148ec0f..10b48f0d8e85 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -32,6 +32,8 @@ void flush_anon_page(struct vm_area_struct *vma,
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 void flush_kernel_dcache_page(struct page *page);
+void flush_kernel_vmap_range(void *addr, int size);
+void invalidate_kernel_vmap_range(void *addr, int size);
 void flush_icache_range(unsigned long start, unsigned long end);
 void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #define flush_dcache_mmap_lock(mapping)   xa_lock_irq(&(mapping)->i_pages)
diff --git a/arch/nds32/include/asm/dma-mapping.h b/arch/nds32/include/asm/dma-mapping.h
deleted file mode 100644
index 2dd47d245c25..000000000000
--- a/arch/nds32/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (C) 2005-2017 Andes Technology Corporation
-
-#ifndef ASMNDS32_DMA_MAPPING_H
-#define ASMNDS32_DMA_MAPPING_H
-
-extern struct dma_map_ops nds32_dma_ops;
-
-static inline struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &nds32_dma_ops;
-}
-
-#endif
diff --git a/arch/nds32/include/asm/io.h b/arch/nds32/include/asm/io.h
index 966e71b3c960..71cd226d6863 100644
--- a/arch/nds32/include/asm/io.h
+++ b/arch/nds32/include/asm/io.h
@@ -4,6 +4,8 @@
 #ifndef __ASM_NDS32_IO_H
 #define __ASM_NDS32_IO_H
 
+#include <linux/types.h>
+
 extern void iounmap(volatile void __iomem *addr);
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
diff --git a/arch/nds32/include/asm/page.h b/arch/nds32/include/asm/page.h
index e27365c097b6..947f0491c9a7 100644
--- a/arch/nds32/include/asm/page.h
+++ b/arch/nds32/include/asm/page.h
@@ -27,6 +27,9 @@ extern void copy_user_highpage(struct page *to, struct page *from,
 			       unsigned long vaddr, struct vm_area_struct *vma);
 extern void clear_user_highpage(struct page *page, unsigned long vaddr);
 
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+		    struct page *to);
+void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
 #define __HAVE_ARCH_COPY_USER_HIGHPAGE
 #define clear_user_highpage	clear_user_highpage
 #else
diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h
index 6783937edbeb..d3e19a55cf53 100644
--- a/arch/nds32/include/asm/pgtable.h
+++ b/arch/nds32/include/asm/pgtable.h
@@ -152,6 +152,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PAGE_CACHE_L1	__pgprot(_HAVE_PAGE_L | _PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE)
 #define PAGE_MEMORY	__pgprot(_HAVE_PAGE_L | _PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE_SHRD)
 #define PAGE_KERNEL	__pgprot(_PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE_SHRD)
+#define PAGE_SHARED	__pgprot(_PAGE_V | _PAGE_M_URW_KRW | _PAGE_D | _PAGE_CACHE_SHRD)
 #define PAGE_DEVICE    __pgprot(_PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_G | _PAGE_C_DEV)
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c
index d291800fc621..d0dbd4fe9645 100644
--- a/arch/nds32/kernel/dma.c
+++ b/arch/nds32/kernel/dma.c
@@ -3,17 +3,14 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/export.h>
 #include <linux/string.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/io.h>
 #include <linux/cache.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/dma-mapping.h>
 #include <asm/proc-fns.h>
 
 /*
@@ -22,11 +19,6 @@
 static pte_t *consistent_pte;
 static DEFINE_RAW_SPINLOCK(consistent_lock);
 
-enum master_type {
-	FOR_CPU = 0,
-	FOR_DEVICE = 1,
-};
-
 /*
  * VM region handling support.
  *
@@ -124,10 +116,8 @@ out:
 	return c;
 }
 
-/* FIXME: attrs is not used. */
-static void *nds32_dma_alloc_coherent(struct device *dev, size_t size,
-				      dma_addr_t * handle, gfp_t gfp,
-				      unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	struct page *page;
 	struct arch_vm_region *c;
@@ -232,8 +222,8 @@ no_page:
 	return NULL;
 }
 
-static void nds32_dma_free(struct device *dev, size_t size, void *cpu_addr,
-			   dma_addr_t handle, unsigned long attrs)
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t handle, unsigned long attrs)
 {
 	struct arch_vm_region *c;
 	unsigned long flags, addr;
@@ -333,145 +323,69 @@ static int __init consistent_init(void)
 }
 
 core_initcall(consistent_init);
-static void consistent_sync(void *vaddr, size_t size, int direction, int master_type);
-static dma_addr_t nds32_dma_map_page(struct device *dev, struct page *page,
-				     unsigned long offset, size_t size,
-				     enum dma_data_direction dir,
-				     unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		consistent_sync((void *)(page_address(page) + offset), size, dir, FOR_DEVICE);
-	return page_to_phys(page) + offset;
-}
-
-static void nds32_dma_unmap_page(struct device *dev, dma_addr_t handle,
-				 size_t size, enum dma_data_direction dir,
-				 unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		consistent_sync(phys_to_virt(handle), size, dir, FOR_CPU);
-}
-
-/*
- * Make an area consistent for devices.
- */
-static void consistent_sync(void *vaddr, size_t size, int direction, int master_type)
-{
-	unsigned long start = (unsigned long)vaddr;
-	unsigned long end = start + size;
-
-	if (master_type == FOR_CPU) {
-		switch (direction) {
-		case DMA_TO_DEVICE:
-			break;
-		case DMA_FROM_DEVICE:
-		case DMA_BIDIRECTIONAL:
-			cpu_dma_inval_range(start, end);
-			break;
-		default:
-			BUG();
-		}
-	} else {
-		/* FOR_DEVICE */
-		switch (direction) {
-		case DMA_FROM_DEVICE:
-			break;
-		case DMA_TO_DEVICE:
-		case DMA_BIDIRECTIONAL:
-			cpu_dma_wb_range(start, end);
-			break;
-		default:
-			BUG();
-		}
-	}
-}
 
-static int nds32_dma_map_sg(struct device *dev, struct scatterlist *sg,
-			    int nents, enum dma_data_direction dir,
-			    unsigned long attrs)
+static inline void cache_op(phys_addr_t paddr, size_t size,
+		void (*fn)(unsigned long start, unsigned long end))
 {
-	int i;
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned offset = paddr & ~PAGE_MASK;
+	size_t left = size;
+	unsigned long start;
 
-	for (i = 0; i < nents; i++, sg++) {
-		void *virt;
-		unsigned long pfn;
-		struct page *page = sg_page(sg);
+	do {
+		size_t len = left;
 
-		sg->dma_address = sg_phys(sg);
-		pfn = page_to_pfn(page) + sg->offset / PAGE_SIZE;
-		page = pfn_to_page(pfn);
 		if (PageHighMem(page)) {
-			virt = kmap_atomic(page);
-			consistent_sync(virt, sg->length, dir, FOR_CPU);
-			kunmap_atomic(virt);
+			void *addr;
+
+			if (offset + len > PAGE_SIZE) {
+				if (offset >= PAGE_SIZE) {
+					page += offset >> PAGE_SHIFT;
+					offset &= ~PAGE_MASK;
+				}
+				len = PAGE_SIZE - offset;
+			}
+
+			addr = kmap_atomic(page);
+			start = (unsigned long)(addr + offset);
+			fn(start, start + len);
+			kunmap_atomic(addr);
 		} else {
-			if (sg->offset > PAGE_SIZE)
-				panic("sg->offset:%08x > PAGE_SIZE\n",
-				      sg->offset);
-			virt = page_address(page) + sg->offset;
-			consistent_sync(virt, sg->length, dir, FOR_CPU);
+			start = (unsigned long)phys_to_virt(paddr);
+			fn(start, start + size);
 		}
-	}
-	return nents;
+		offset = 0;
+		page++;
+		left -= len;
+	} while (left);
 }
 
-static void nds32_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-			       int nhwentries, enum dma_data_direction dir,
-			       unsigned long attrs)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-}
-
-static void
-nds32_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
-			      size_t size, enum dma_data_direction dir)
-{
-	consistent_sync((void *)phys_to_virt(handle), size, dir, FOR_CPU);
-}
-
-static void
-nds32_dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
-				 size_t size, enum dma_data_direction dir)
-{
-	consistent_sync((void *)phys_to_virt(handle), size, dir, FOR_DEVICE);
-}
-
-static void
-nds32_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents,
-			  enum dma_data_direction dir)
-{
-	int i;
-
-	for (i = 0; i < nents; i++, sg++) {
-		char *virt =
-		    page_address((struct page *)sg->page_link) + sg->offset;
-		consistent_sync(virt, sg->length, dir, FOR_CPU);
+	switch (dir) {
+	case DMA_FROM_DEVICE:
+		break;
+	case DMA_TO_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		cache_op(paddr, size, cpu_dma_wb_range);
+		break;
+	default:
+		BUG();
 	}
 }
 
-static void
-nds32_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-			     int nents, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	int i;
-
-	for (i = 0; i < nents; i++, sg++) {
-		char *virt =
-		    page_address((struct page *)sg->page_link) + sg->offset;
-		consistent_sync(virt, sg->length, dir, FOR_DEVICE);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		cache_op(paddr, size, cpu_dma_inval_range);
+		break;
+	default:
+		BUG();
 	}
 }
-
-struct dma_map_ops nds32_dma_ops = {
-	.alloc = nds32_dma_alloc_coherent,
-	.free = nds32_dma_free,
-	.map_page = nds32_dma_map_page,
-	.unmap_page = nds32_dma_unmap_page,
-	.map_sg = nds32_dma_map_sg,
-	.unmap_sg = nds32_dma_unmap_sg,
-	.sync_single_for_device = nds32_dma_sync_single_for_device,
-	.sync_single_for_cpu = nds32_dma_sync_single_for_cpu,
-	.sync_sg_for_cpu = nds32_dma_sync_sg_for_cpu,
-	.sync_sg_for_device = nds32_dma_sync_sg_for_device,
-};
-
-EXPORT_SYMBOL(nds32_dma_ops);
diff --git a/arch/nds32/kernel/ex-entry.S b/arch/nds32/kernel/ex-entry.S
index a72e83d804f5..b8ae4e9a6b93 100644
--- a/arch/nds32/kernel/ex-entry.S
+++ b/arch/nds32/kernel/ex-entry.S
@@ -118,7 +118,7 @@ common_exception_handler:
 	/* interrupt */
 2:
 #ifdef CONFIG_TRACE_IRQFLAGS
-	jal     arch_trace_hardirqs_off
+	jal     trace_hardirqs_off
 #endif
 	move	$r0, $sp
 	sethi	$lp, hi20(ret_from_intr)
diff --git a/arch/nds32/kernel/head.S b/arch/nds32/kernel/head.S
index 71f57bd70f3b..c5fdae174ced 100644
--- a/arch/nds32/kernel/head.S
+++ b/arch/nds32/kernel/head.S
@@ -57,14 +57,32 @@ _nodtb:
 	isb
 	mtsr    $r4, $L1_PPTB       ! load page table pointer\n"
 
-/* set NTC0 cacheable/writeback, mutliple page size in use */
+#ifdef CONFIG_CPU_DCACHE_DISABLE
+	#define MMU_CTL_NTCC MMU_CTL_CACHEABLE_NON
+#else
+	#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+		#define MMU_CTL_NTCC MMU_CTL_CACHEABLE_WT
+	#else
+		#define MMU_CTL_NTCC MMU_CTL_CACHEABLE_WB
+	#endif
+#endif
+
+/* set NTC cacheability, mutliple page size in use */
 	mfsr    $r3, $MMU_CTL
-	li      $r0, #~MMU_CTL_mskNTC0
-	and     $r3, $r3, $r0
+#if CONFIG_MEMORY_START >= 0xc0000000
+	ori     $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC3)
+#elif CONFIG_MEMORY_START >= 0x80000000
+	ori     $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC2)
+#elif CONFIG_MEMORY_START >= 0x40000000
+	ori     $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC1)
+#else
+	ori     $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC0)
+#endif
+
 #ifdef CONFIG_ANDES_PAGE_SIZE_4KB
-	ori     $r3, $r3, #(MMU_CTL_mskMPZIU|(MMU_CTL_CACHEABLE_WB << MMU_CTL_offNTC0))
+	ori     $r3, $r3, #(MMU_CTL_mskMPZIU)
 #else
-	ori     $r3, $r3, #(MMU_CTL_mskMPZIU|(MMU_CTL_CACHEABLE_WB << MMU_CTL_offNTC0)|MMU_CTL_D8KB)
+	ori     $r3, $r3, #(MMU_CTL_mskMPZIU|MMU_CTL_D8KB)
 #endif
 #ifdef CONFIG_HW_SUPPORT_UNALIGNMENT_ACCESS
 	li      $r0, #MMU_CTL_UNA
diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c
index ba910e9e4ecb..2f5b2ccebe47 100644
--- a/arch/nds32/kernel/setup.c
+++ b/arch/nds32/kernel/setup.c
@@ -293,6 +293,9 @@ void __init setup_arch(char **cmdline_p)
 	/* paging_init() sets up the MMU and marks all pages as reserved */
 	paging_init();
 
+	/* invalidate all TLB entries because the new mapping is created */
+	__nds32__tlbop_flua();
+
 	/* use generic way to parse */
 	parse_early_param();
 
diff --git a/arch/nds32/kernel/stacktrace.c b/arch/nds32/kernel/stacktrace.c
index bc70113c0e84..8b231e910ea6 100644
--- a/arch/nds32/kernel/stacktrace.c
+++ b/arch/nds32/kernel/stacktrace.c
@@ -9,6 +9,7 @@ void save_stack_trace(struct stack_trace *trace)
 {
 	save_stack_trace_tsk(current, trace);
 }
+EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
@@ -45,3 +46,4 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		fpn = (unsigned long *)fpp;
 	}
 }
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c
index 6e34eb9824a4..a6205fd4db52 100644
--- a/arch/nds32/kernel/traps.c
+++ b/arch/nds32/kernel/traps.c
@@ -222,19 +222,13 @@ void die_if_kernel(const char *str, struct pt_regs *regs, int err)
 
 int bad_syscall(int n, struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	if (current->personality != PER_LINUX) {
 		send_sig(SIGSEGV, current, 1);
 		return regs->uregs[0];
 	}
 
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_ILLTRP;
-	info.si_addr = (void __user *)instruction_pointer(regs) - 4;
-
-	force_sig_info(SIGILL, &info, current);
+	force_sig_fault(SIGILL, ILL_ILLTRP,
+			(void __user *)instruction_pointer(regs) - 4, current);
 	die_if_kernel("Oops - bad syscall", regs, n);
 	return regs->uregs[0];
 }
@@ -287,16 +281,11 @@ void __init early_trap_init(void)
 void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 		  int error_code, int si_code)
 {
-	struct siginfo info;
-
 	tsk->thread.trap_no = ENTRY_DEBUG_RELATED;
 	tsk->thread.error_code = error_code;
 
-	memset(&info, 0, sizeof(info));
-	info.si_signo = SIGTRAP;
-	info.si_code = si_code;
-	info.si_addr = (void __user *)instruction_pointer(regs);
-	force_sig_info(SIGTRAP, &info, tsk);
+	force_sig_fault(SIGTRAP, si_code,
+			(void __user *)instruction_pointer(regs), tsk);
 }
 
 void do_debug_trap(unsigned long entry, unsigned long addr,
@@ -318,29 +307,22 @@ void do_debug_trap(unsigned long entry, unsigned long addr,
 
 void unhandled_interruption(struct pt_regs *regs)
 {
-	siginfo_t si;
 	pr_emerg("unhandled_interruption\n");
 	show_regs(regs);
 	if (!user_mode(regs))
 		do_exit(SIGKILL);
-	si.si_signo = SIGKILL;
-	si.si_errno = 0;
-	force_sig_info(SIGKILL, &si, current);
+	force_sig(SIGKILL, current);
 }
 
 void unhandled_exceptions(unsigned long entry, unsigned long addr,
 			  unsigned long type, struct pt_regs *regs)
 {
-	siginfo_t si;
 	pr_emerg("Unhandled Exception: entry: %lx addr:%lx itype:%lx\n", entry,
 		 addr, type);
 	show_regs(regs);
 	if (!user_mode(regs))
 		do_exit(SIGKILL);
-	si.si_signo = SIGKILL;
-	si.si_errno = 0;
-	si.si_addr = (void *)addr;
-	force_sig_info(SIGKILL, &si, current);
+	force_sig(SIGKILL, current);
 }
 
 extern int do_page_fault(unsigned long entry, unsigned long addr,
@@ -363,14 +345,11 @@ void do_dispatch_tlb_misc(unsigned long entry, unsigned long addr,
 
 void do_revinsn(struct pt_regs *regs)
 {
-	siginfo_t si;
 	pr_emerg("Reserved Instruction\n");
 	show_regs(regs);
 	if (!user_mode(regs))
 		do_exit(SIGILL);
-	si.si_signo = SIGILL;
-	si.si_errno = 0;
-	force_sig_info(SIGILL, &si, current);
+	force_sig(SIGILL, current);
 }
 
 #ifdef CONFIG_ALIGNMENT_TRAP
diff --git a/arch/nds32/kernel/vdso.c b/arch/nds32/kernel/vdso.c
index f1198d7a5654..016f15891f6d 100644
--- a/arch/nds32/kernel/vdso.c
+++ b/arch/nds32/kernel/vdso.c
@@ -23,7 +23,7 @@
 #include <asm/vdso_timer_info.h>
 #include <asm/cache_info.h>
 extern struct cache_info L1_cache_info[2];
-extern char vdso_start, vdso_end;
+extern char vdso_start[], vdso_end[];
 static unsigned long vdso_pages __ro_after_init;
 static unsigned long timer_mapping_base;
 
@@ -66,16 +66,16 @@ static int __init vdso_init(void)
 	int i;
 	struct page **vdso_pagelist;
 
-	if (memcmp(&vdso_start, "\177ELF", 4)) {
+	if (memcmp(vdso_start, "\177ELF", 4)) {
 		pr_err("vDSO is not a valid ELF object!\n");
 		return -EINVAL;
 	}
 	/* Creat a timer io mapping to get clock cycles counter */
 	get_timer_node_info();
 
-	vdso_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
+	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
 	pr_info("vdso: %ld pages (%ld code @ %p, %ld data @ %p)\n",
-		vdso_pages + 1, vdso_pages, &vdso_start, 1L, vdso_data);
+		vdso_pages + 1, vdso_pages, vdso_start, 1L, vdso_data);
 
 	/* Allocate the vDSO pagelist */
 	vdso_pagelist = kcalloc(vdso_pages, sizeof(struct page *), GFP_KERNEL);
@@ -83,7 +83,7 @@ static int __init vdso_init(void)
 		return -ENOMEM;
 
 	for (i = 0; i < vdso_pages; i++)
-		vdso_pagelist[i] = virt_to_page(&vdso_start + i * PAGE_SIZE);
+		vdso_pagelist[i] = virt_to_page(vdso_start + i * PAGE_SIZE);
 	vdso_spec[1].pages = &vdso_pagelist[0];
 
 	return 0;
diff --git a/arch/nds32/lib/copy_page.S b/arch/nds32/lib/copy_page.S
index 4a2ff85f17ee..f8701ed161a8 100644
--- a/arch/nds32/lib/copy_page.S
+++ b/arch/nds32/lib/copy_page.S
@@ -2,6 +2,7 @@
 // Copyright (C) 2005-2017 Andes Technology Corporation
 
 #include <linux/linkage.h>
+#include <asm/export.h>
 #include <asm/page.h>
 
 	.text
@@ -16,6 +17,7 @@ ENTRY(copy_page)
 	popm	$r2, $r10
 	ret
 ENDPROC(copy_page)
+EXPORT_SYMBOL(copy_page)
 
 ENTRY(clear_page)
 	pushm	$r1, $r9
@@ -35,3 +37,4 @@ ENTRY(clear_page)
 	popm	$r1, $r9
         ret
 ENDPROC(clear_page)
+EXPORT_SYMBOL(clear_page)
diff --git a/arch/nds32/mm/alignment.c b/arch/nds32/mm/alignment.c
index b96a01b10ca7..e1aed9dc692d 100644
--- a/arch/nds32/mm/alignment.c
+++ b/arch/nds32/mm/alignment.c
@@ -19,7 +19,7 @@
 #define RA(inst)	(((inst) >> 15) & 0x1FUL)
 #define RB(inst)	(((inst) >> 10) & 0x1FUL)
 #define SV(inst)	(((inst) >> 8) & 0x3UL)
-#define IMM(inst)	(((inst) >> 0) & 0x3FFFUL)
+#define IMM(inst)	(((inst) >> 0) & 0x7FFFUL)
 
 #define RA3(inst)	(((inst) >> 3) & 0x7UL)
 #define RT3(inst)	(((inst) >> 6) & 0x7UL)
@@ -28,6 +28,9 @@
 #define RA5(inst)	(((inst) >> 0) & 0x1FUL)
 #define RT4(inst)	(((inst) >> 5) & 0xFUL)
 
+#define GET_IMMSVAL(imm_value) \
+	(((imm_value >> 14) & 0x1) ? (imm_value - 0x8000) : imm_value)
+
 #define __get8_data(val,addr,err)	\
 	__asm__(					\
 	"1:	lbi.bi	%1, [%2], #1\n"			\
@@ -467,7 +470,7 @@ static inline int do_32(unsigned long inst, struct pt_regs *regs)
 	}
 
 	if (imm)
-		shift = IMM(inst) * len;
+		shift = GET_IMMSVAL(IMM(inst)) * len;
 	else
 		shift = *idx_to_addr(regs, RB(inst)) << SV(inst);
 
@@ -552,7 +555,7 @@ static struct ctl_table alignment_tbl[3] = {
 
 static struct ctl_table nds32_sysctl_table[2] = {
 	{
-	 .procname = "unaligned_acess",
+	 .procname = "unaligned_access",
 	 .mode = 0555,
 	 .child = alignment_tbl},
 	{}
diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c
index 6eb786a399a2..ce8fd34497bf 100644
--- a/arch/nds32/mm/cacheflush.c
+++ b/arch/nds32/mm/cacheflush.c
@@ -147,6 +147,25 @@ void flush_cache_vunmap(unsigned long start, unsigned long end)
 	cpu_icache_inval_all();
 }
 
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+		    struct page *to)
+{
+	cpu_dcache_wbinval_page((unsigned long)vaddr);
+	cpu_icache_inval_page((unsigned long)vaddr);
+	copy_page(vto, vfrom);
+	cpu_dcache_wbinval_page((unsigned long)vto);
+	cpu_icache_inval_page((unsigned long)vto);
+}
+
+void clear_user_page(void *addr, unsigned long vaddr, struct page *page)
+{
+	cpu_dcache_wbinval_page((unsigned long)vaddr);
+	cpu_icache_inval_page((unsigned long)vaddr);
+	clear_page(addr);
+	cpu_dcache_wbinval_page((unsigned long)addr);
+	cpu_icache_inval_page((unsigned long)addr);
+}
+
 void copy_user_highpage(struct page *to, struct page *from,
 			unsigned long vaddr, struct vm_area_struct *vma)
 {
@@ -156,11 +175,9 @@ void copy_user_highpage(struct page *to, struct page *from,
 	pto = page_to_phys(to);
 	pfrom = page_to_phys(from);
 
+	local_irq_save(flags);
 	if (aliasing(vaddr, (unsigned long)kfrom))
 		cpu_dcache_wb_page((unsigned long)kfrom);
-	if (aliasing(vaddr, (unsigned long)kto))
-		cpu_dcache_inval_page((unsigned long)kto);
-	local_irq_save(flags);
 	vto = kremap0(vaddr, pto);
 	vfrom = kremap1(vaddr, pfrom);
 	copy_page((void *)vto, (void *)vfrom);
@@ -198,21 +215,25 @@ void flush_dcache_page(struct page *page)
 	if (mapping && !mapping_mapped(mapping))
 		set_bit(PG_dcache_dirty, &page->flags);
 	else {
-		int i, pc;
-		unsigned long vto, kaddr, flags;
+		unsigned long kaddr, flags;
+
 		kaddr = (unsigned long)page_address(page);
-		cpu_dcache_wbinval_page(kaddr);
-		pc = CACHE_SET(DCACHE) * CACHE_LINE_SIZE(DCACHE) / PAGE_SIZE;
 		local_irq_save(flags);
-		for (i = 0; i < pc; i++) {
-			vto =
-			    kremap0(kaddr + i * PAGE_SIZE, page_to_phys(page));
-			cpu_dcache_wbinval_page(vto);
-			kunmap01(vto);
+		cpu_dcache_wbinval_page(kaddr);
+		if (mapping) {
+			unsigned long vaddr, kto;
+
+			vaddr = page->index << PAGE_SHIFT;
+			if (aliasing(vaddr, kaddr)) {
+				kto = kremap0(vaddr, page_to_phys(page));
+				cpu_dcache_wbinval_page(kto);
+				kunmap01(kto);
+			}
 		}
 		local_irq_restore(flags);
 	}
 }
+EXPORT_SYMBOL(flush_dcache_page);
 
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		       unsigned long vaddr, void *dst, void *src, int len)
@@ -251,7 +272,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
 void flush_anon_page(struct vm_area_struct *vma,
 		     struct page *page, unsigned long vaddr)
 {
-	unsigned long flags;
+	unsigned long kaddr, flags, ktmp;
 	if (!PageAnon(page))
 		return;
 
@@ -261,7 +282,12 @@ void flush_anon_page(struct vm_area_struct *vma,
 	local_irq_save(flags);
 	if (vma->vm_flags & VM_EXEC)
 		cpu_icache_inval_page(vaddr & PAGE_MASK);
-	cpu_dcache_wbinval_page((unsigned long)page_address(page));
+	kaddr = (unsigned long)page_address(page);
+	if (aliasing(vaddr, kaddr)) {
+		ktmp = kremap0(vaddr, page_to_phys(page));
+		cpu_dcache_wbinval_page(ktmp);
+		kunmap01(ktmp);
+	}
 	local_irq_restore(flags);
 }
 
@@ -272,6 +298,25 @@ void flush_kernel_dcache_page(struct page *page)
 	cpu_dcache_wbinval_page((unsigned long)page_address(page));
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+void flush_kernel_vmap_range(void *addr, int size)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	cpu_dcache_wb_range((unsigned long)addr, (unsigned long)addr +  size);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_kernel_vmap_range);
+
+void invalidate_kernel_vmap_range(void *addr, int size)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	cpu_dcache_inval_range((unsigned long)addr, (unsigned long)addr + size);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(invalidate_kernel_vmap_range);
 
 void flush_icache_range(unsigned long start, unsigned long end)
 {
@@ -283,6 +328,7 @@ void flush_icache_range(unsigned long start, unsigned long end)
 	cpu_cache_wbinval_range(start, end, 1);
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(flush_icache_range);
 
 void flush_icache_page(struct vm_area_struct *vma, struct page *page)
 {
diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index 3a246fb8098c..9bdb7c3ecbb6 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -72,7 +72,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
-	siginfo_t info;
+	int si_code;
 	int fault;
 	unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -80,7 +80,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 	error_code = error_code & (ITYPE_mskINST | ITYPE_mskETYPE);
 	tsk = current;
 	mm = tsk->mm;
-	info.si_code = SEGV_MAPERR;
+	si_code = SEGV_MAPERR;
 	/*
 	 * We fault-in kernel-space virtual memory on-demand. The
 	 * 'reference' page table is init_mm.pgd.
@@ -161,7 +161,7 @@ retry:
 	 */
 
 good_area:
-	info.si_code = SEGV_ACCERR;
+	si_code = SEGV_ACCERR;
 
 	/* first do some preliminary protection checks */
 	if (entry == ENTRY_PTE_NOT_PRESENT) {
@@ -266,11 +266,7 @@ bad_area_nosemaphore:
 		tsk->thread.address = addr;
 		tsk->thread.error_code = error_code;
 		tsk->thread.trap_no = entry;
-		info.si_signo = SIGSEGV;
-		info.si_errno = 0;
-		/* info.si_code has been set above */
-		info.si_addr = (void *)addr;
-		force_sig_info(SIGSEGV, &info, tsk);
+		force_sig_fault(SIGSEGV, si_code, (void __user *)addr, tsk);
 		return;
 	}
 
@@ -339,11 +335,7 @@ do_sigbus:
 	tsk->thread.address = addr;
 	tsk->thread.error_code = error_code;
 	tsk->thread.trap_no = entry;
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRERR;
-	info.si_addr = (void *)addr;
-	force_sig_info(SIGBUS, &info, tsk);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)addr, tsk);
 
 	return;
 
diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c
index 93ee0160720b..c713d2ad55dc 100644
--- a/arch/nds32/mm/init.c
+++ b/arch/nds32/mm/init.c
@@ -30,6 +30,7 @@ extern unsigned long phys_initrd_size;
  * zero-initialized data and COW.
  */
 struct page *empty_zero_page;
+EXPORT_SYMBOL(empty_zero_page);
 
 static void __init zone_sizes_init(void)
 {
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index d232da2cbb38..64ed3d656956 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -4,6 +4,7 @@ generic-y += bitops.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += cmpxchg.h
+generic-y += compat.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c
index 8184e7d6b385..3bc3cd22b750 100644
--- a/arch/nios2/kernel/traps.c
+++ b/arch/nios2/kernel/traps.c
@@ -26,13 +26,7 @@ static DEFINE_SPINLOCK(die_lock);
 
 static void _send_sig(int signo, int code, unsigned long addr)
 {
-	siginfo_t info;
-
-	info.si_signo = signo;
-	info.si_errno = 0;
-	info.si_code = code;
-	info.si_addr = (void __user *) addr;
-	force_sig_info(signo, &info, current);
+	force_sig_fault(signo, code, (void __user *) addr, current);
 }
 
 void die(const char *str, struct pt_regs *regs, long err)
diff --git a/arch/openrisc/Makefile b/arch/openrisc/Makefile
index cf8802962864..89076a66eee2 100644
--- a/arch/openrisc/Makefile
+++ b/arch/openrisc/Makefile
@@ -25,7 +25,6 @@ LDFLAGS_vmlinux :=
 LIBGCC 		:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 
 KBUILD_CFLAGS	+= -pipe -ffixed-r10 -D__linux__
-CHECKFLAGS	+= -mbig-endian
 
 ifeq ($(CONFIG_OPENRISC_HAVE_INST_MUL),y)
 	KBUILD_CFLAGS += $(call cc-option,-mhard-mul)
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index f05c722a21f8..65964d390b10 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -2,6 +2,7 @@ generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += checksum.h
+generic-y += compat.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index a945f00011b4..ec7fd45704d2 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -247,14 +247,3 @@ const struct dma_map_ops or1k_dma_map_ops = {
 	.sync_single_for_device = or1k_sync_single_for_device,
 };
 EXPORT_SYMBOL(or1k_dma_map_ops);
-
-/* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
-	return 0;
-}
-fs_initcall(dma_init);
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 113c175fe469..fac246e6f37a 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -250,27 +250,16 @@ void __init trap_init(void)
 
 asmlinkage void do_trap(struct pt_regs *regs, unsigned long address)
 {
-	siginfo_t info;
-	memset(&info, 0, sizeof(info));
-	info.si_signo = SIGTRAP;
-	info.si_code = TRAP_TRACE;
-	info.si_addr = (void *)address;
-	force_sig_info(SIGTRAP, &info, current);
+	force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)address, current);
 
 	regs->pc += 4;
 }
 
 asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address)
 {
-	siginfo_t info;
-
 	if (user_mode(regs)) {
 		/* Send a SIGBUS */
-		info.si_signo = SIGBUS;
-		info.si_errno = 0;
-		info.si_code = BUS_ADRALN;
-		info.si_addr = (void __user *)address;
-		force_sig_info(SIGBUS, &info, current);
+		force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)address, current);
 	} else {
 		printk("KERNEL: Unaligned Access 0x%.8lx\n", address);
 		show_registers(regs);
@@ -281,15 +270,9 @@ asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address)
 
 asmlinkage void do_bus_fault(struct pt_regs *regs, unsigned long address)
 {
-	siginfo_t info;
-
 	if (user_mode(regs)) {
 		/* Send a SIGBUS */
-		info.si_signo = SIGBUS;
-		info.si_errno = 0;
-		info.si_code = BUS_ADRERR;
-		info.si_addr = (void *)address;
-		force_sig_info(SIGBUS, &info, current);
+		force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, current);
 	} else {		/* Kernel mode */
 		printk("KERNEL: Bus error (SIGBUS) 0x%.8lx\n", address);
 		show_registers(regs);
@@ -464,7 +447,6 @@ static inline void simulate_swa(struct pt_regs *regs, unsigned long address,
 asmlinkage void do_illegal_instruction(struct pt_regs *regs,
 				       unsigned long address)
 {
-	siginfo_t info;
 	unsigned int op;
 	unsigned int insn = *((unsigned int *)address);
 
@@ -485,11 +467,7 @@ asmlinkage void do_illegal_instruction(struct pt_regs *regs,
 
 	if (user_mode(regs)) {
 		/* Send a SIGILL */
-		info.si_signo = SIGILL;
-		info.si_errno = 0;
-		info.si_code = ILL_ILLOPC;
-		info.si_addr = (void *)address;
-		force_sig_info(SIGBUS, &info, current);
+		force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)address, current);
 	} else {		/* Kernel mode */
 		printk("KERNEL: Illegal instruction (SIGILL) 0x%.8lx\n",
 		       address);
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index d0021dfae20a..9f011d16cc46 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -52,7 +52,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
-	siginfo_t info;
+	int si_code;
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
@@ -97,7 +97,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	}
 
 	mm = tsk->mm;
-	info.si_code = SEGV_MAPERR;
+	si_code = SEGV_MAPERR;
 
 	/*
 	 * If we're in an interrupt or have no user
@@ -139,7 +139,7 @@ retry:
 	 */
 
 good_area:
-	info.si_code = SEGV_ACCERR;
+	si_code = SEGV_ACCERR;
 
 	/* first do some preliminary protection checks */
 
@@ -213,11 +213,7 @@ bad_area_nosemaphore:
 	/* User mode accesses just cause a SIGSEGV */
 
 	if (user_mode(regs)) {
-		info.si_signo = SIGSEGV;
-		info.si_errno = 0;
-		/* info.si_code has been set above */
-		info.si_addr = (void *)address;
-		force_sig_info(SIGSEGV, &info, tsk);
+		force_sig_fault(SIGSEGV, si_code, (void __user *)address, tsk);
 		return;
 	}
 
@@ -282,11 +278,7 @@ do_sigbus:
 	 * Send a sigbus, regardless of whether we were in kernel
 	 * or user mode.
 	 */
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRERR;
-	info.si_addr = (void *)address;
-	force_sig_info(SIGBUS, &info, tsk);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, tsk);
 
 	/* Kernel mode? Handle exceptions or die */
 	if (!user_mode(regs))
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index fc5a574c3482..4d8f64d48597 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -51,6 +51,8 @@ config PARISC
 	select GENERIC_CLOCKEVENTS
 	select ARCH_NO_COHERENT_DMA_MMAP
 	select CPU_NO_EFFICIENT_FFS
+	select NEED_DMA_MAP_STATE
+	select NEED_SG_DMA_LENGTH
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
@@ -111,12 +113,6 @@ config PM
 config STACKTRACE_SUPPORT
 	def_bool y
 
-config NEED_DMA_MAP_STATE
-	def_bool y
-
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
 config ISA_DMA_API
 	bool
 
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index e2364ff59180..714284ea6cc2 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -22,13 +22,13 @@ KBUILD_IMAGE := vmlinuz
 KBUILD_DEFCONFIG := default_defconfig
 
 NM		= sh $(srctree)/arch/parisc/nm
-CHECKFLAGS	+= -D__hppa__=1 -mbig-endian
+CHECKFLAGS	+= -D__hppa__=1
 LIBGCC		= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 export LIBGCC
 
 ifdef CONFIG_64BIT
 UTS_MACHINE	:= parisc64
-CHECKFLAGS	+= -D__LP64__=1 -m64
+CHECKFLAGS	+= -D__LP64__=1
 CC_ARCHES	= hppa64
 LD_BFD		:= elf64-hppa-linux
 else # 32-bit
@@ -123,6 +123,9 @@ INSTALL_TARGETS = zinstall install
 
 PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
 
+# Default kernel to build
+all: bzImage
+
 zImage: vmlinuz
 Image: vmlinux
 
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index 57b8b2a2fd4e..ab8a54771507 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -13,7 +13,6 @@
 
 typedef u32	compat_size_t;
 typedef s32	compat_ssize_t;
-typedef s32	compat_time_t;
 typedef s32	compat_clock_t;
 typedef s32	compat_pid_t;
 typedef u32	__compat_uid_t;
@@ -40,16 +39,6 @@ typedef u32	compat_ulong_t;
 typedef u64	compat_u64;
 typedef u32	compat_uptr_t;
 
-struct compat_timespec {
-	compat_time_t		tv_sec;
-	s32			tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t		tv_sec;
-	s32			tv_usec;
-};
-
 struct compat_stat {
 	compat_dev_t		st_dev;	/* dev_t is 32 bits on parisc */
 	compat_ino_t		st_ino;	/* 32 bits */
@@ -149,10 +138,10 @@ struct compat_ipc64_perm {
 
 struct compat_semid64_ds {
 	struct compat_ipc64_perm sem_perm;
-	unsigned int __unused1;
-	compat_time_t sem_otime;
-	unsigned int __unused2;
-	compat_time_t sem_ctime;
+	unsigned int sem_otime_high;
+	unsigned int sem_otime;
+	unsigned int sem_ctime_high;
+	unsigned int sem_ctime;
 	compat_ulong_t sem_nsems;
 	compat_ulong_t __unused3;
 	compat_ulong_t __unused4;
@@ -160,12 +149,12 @@ struct compat_semid64_ds {
 
 struct compat_msqid64_ds {
 	struct compat_ipc64_perm msg_perm;
-	unsigned int __unused1;
-	compat_time_t msg_stime;
-	unsigned int __unused2;
-	compat_time_t msg_rtime;
-	unsigned int __unused3;
-	compat_time_t msg_ctime;
+	unsigned int msg_stime_high;
+	unsigned int msg_stime;
+	unsigned int msg_rtime_high;
+	unsigned int msg_rtime;
+	unsigned int msg_ctime_high;
+	unsigned int msg_ctime;
 	compat_ulong_t msg_cbytes;
 	compat_ulong_t msg_qnum;
 	compat_ulong_t msg_qbytes;
@@ -177,12 +166,12 @@ struct compat_msqid64_ds {
 
 struct compat_shmid64_ds {
 	struct compat_ipc64_perm shm_perm;
-	unsigned int __unused1;
-	compat_time_t shm_atime;
-	unsigned int __unused2;
-	compat_time_t shm_dtime;
-	unsigned int __unused3;
-	compat_time_t shm_ctime;
+	unsigned int shm_atime_high;
+	unsigned int shm_atime;
+	unsigned int shm_dtime_high;
+	unsigned int shm_dtime;
+	unsigned int shm_ctime_high;
+	unsigned int shm_ctime;
 	unsigned int __unused4;
 	compat_size_t shm_segsz;
 	compat_pid_t shm_cpid;
diff --git a/arch/parisc/include/asm/hardirq.h b/arch/parisc/include/asm/hardirq.h
index 077815169258..1a1235a9d533 100644
--- a/arch/parisc/include/asm/hardirq.h
+++ b/arch/parisc/include/asm/hardirq.h
@@ -34,14 +34,6 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 #define __IRQ_STAT(cpu, member) (irq_stat[cpu].member)
 #define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
 #define __inc_irq_stat(member)	__this_cpu_inc(irq_stat.member)
-#define local_softirq_pending()	this_cpu_read(irq_stat.__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING
-
-#define set_softirq_pending(x)	\
-		this_cpu_write(irq_stat.__softirq_pending, (x))
-#define or_softirq_pending(x)	this_cpu_or(irq_stat.__softirq_pending, (x))
-
 #define ack_bad_irq(irq) WARN(1, "unexpected IRQ trap at vector %02x\n", irq)
 
 #endif /* _PARISC_HARDIRQ_H */
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 96b7deec512d..3328fd17c19d 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -88,29 +88,6 @@ struct pci_hba_data {
 #endif /* !CONFIG_64BIT */
 
 /*
- * If the PCI device's view of memory is the same as the CPU's view of memory,
- * PCI_DMA_BUS_IS_PHYS is true.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#ifdef CONFIG_PA20
-/* All PA-2.0 machines have an IOMMU. */
-#define PCI_DMA_BUS_IS_PHYS	0
-#define parisc_has_iommu()	do { } while (0)
-#else
-
-#if defined(CONFIG_IOMMU_CCIO) || defined(CONFIG_IOMMU_SBA)
-extern int parisc_bus_is_phys; 	/* in arch/parisc/kernel/setup.c */
-#define PCI_DMA_BUS_IS_PHYS	parisc_bus_is_phys
-#define parisc_has_iommu()	do { parisc_bus_is_phys = 0; } while (0)
-#else
-#define PCI_DMA_BUS_IS_PHYS	1
-#define parisc_has_iommu()	do { } while (0)
-#endif
-
-#endif	/* !CONFIG_PA20 */
-
-
-/*
 ** Most PCI devices (eg Tulip, NCR720) also export the same registers
 ** to both MMIO and I/O port space.  Due to poor performance of I/O Port
 ** access under HP PCI bus adapters, strongly recommend the use of MMIO
diff --git a/arch/parisc/include/uapi/asm/msgbuf.h b/arch/parisc/include/uapi/asm/msgbuf.h
index b48b810e626b..6a2e9ab2ef8d 100644
--- a/arch/parisc/include/uapi/asm/msgbuf.h
+++ b/arch/parisc/include/uapi/asm/msgbuf.h
@@ -10,31 +10,30 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
 
 struct msqid64_ds {
 	struct ipc64_perm msg_perm;
-#if __BITS_PER_LONG != 64
-	unsigned int   __pad1;
-#endif
+#if __BITS_PER_LONG == 64
 	__kernel_time_t msg_stime;	/* last msgsnd time */
-#if __BITS_PER_LONG != 64
-	unsigned int   __pad2;
-#endif
 	__kernel_time_t msg_rtime;	/* last msgrcv time */
-#if __BITS_PER_LONG != 64
-	unsigned int   __pad3;
-#endif
 	__kernel_time_t msg_ctime;	/* last change time */
-	unsigned long msg_cbytes;	/* current number of bytes on queue */
-	unsigned long msg_qnum;		/* number of messages in queue */
-	unsigned long msg_qbytes;	/* max number of bytes on queue */
-	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
-	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	unsigned long __unused1;
-	unsigned long __unused2;
+#else
+	unsigned long	msg_stime_high;
+	unsigned long	msg_stime;	/* last msgsnd time */
+	unsigned long	msg_rtime_high;
+	unsigned long	msg_rtime;	/* last msgrcv time */
+	unsigned long	msg_ctime_high;
+	unsigned long	msg_ctime;	/* last change time */
+#endif
+	unsigned long	msg_cbytes;	/* current number of bytes on queue */
+	unsigned long	msg_qnum;	/* number of messages in queue */
+	unsigned long	msg_qbytes;	/* max number of bytes on queue */
+	__kernel_pid_t	msg_lspid;	/* pid of last msgsnd */
+	__kernel_pid_t	msg_lrpid;	/* last receive pid */
+	unsigned long	__unused1;
+	unsigned long	__unused2;
 };
 
 #endif /* _PARISC_MSGBUF_H */
diff --git a/arch/parisc/include/uapi/asm/sembuf.h b/arch/parisc/include/uapi/asm/sembuf.h
index 746c5d86a9b1..3c31163b1241 100644
--- a/arch/parisc/include/uapi/asm/sembuf.h
+++ b/arch/parisc/include/uapi/asm/sembuf.h
@@ -10,21 +10,21 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
 
 struct semid64_ds {
 	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
-#if __BITS_PER_LONG != 64
-	unsigned int	__pad1;
-#endif
+#if __BITS_PER_LONG == 64
 	__kernel_time_t	sem_otime;		/* last semop time */
-#if __BITS_PER_LONG != 64
-	unsigned int	__pad2;
-#endif
 	__kernel_time_t	sem_ctime;		/* last change time */
-	unsigned long 	sem_nsems;		/* no. of semaphores in array */
+#else
+	unsigned long	sem_otime_high;
+	unsigned long	sem_otime;		/* last semop time */
+	unsigned long	sem_ctime_high;
+	unsigned long	sem_ctime;		/* last change time */
+#endif
+	unsigned long	sem_nsems;		/* no. of semaphores in array */
 	unsigned long	__unused1;
 	unsigned long	__unused2;
 };
diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h
index cd4dbce55d0b..c89b3dd8db21 100644
--- a/arch/parisc/include/uapi/asm/shmbuf.h
+++ b/arch/parisc/include/uapi/asm/shmbuf.h
@@ -10,25 +10,22 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
 
 struct shmid64_ds {
 	struct ipc64_perm	shm_perm;	/* operation perms */
-#if __BITS_PER_LONG != 64
-	unsigned int		__pad1;
-#endif
+#if __BITS_PER_LONG == 64
 	__kernel_time_t		shm_atime;	/* last attach time */
-#if __BITS_PER_LONG != 64
-	unsigned int		__pad2;
-#endif
 	__kernel_time_t		shm_dtime;	/* last detach time */
-#if __BITS_PER_LONG != 64
-	unsigned int		__pad3;
-#endif
 	__kernel_time_t		shm_ctime;	/* last change time */
-#if __BITS_PER_LONG != 64
+#else
+	unsigned long		shm_atime_high;
+	unsigned long		shm_atime;	/* last attach time */
+	unsigned long		shm_dtime_high;
+	unsigned long		shm_dtime;	/* last detach time */
+	unsigned long		shm_ctime_high;
+	unsigned long		shm_ctime;	/* last change time */
 	unsigned int		__pad4;
 #endif
 	__kernel_size_t		shm_segsz;	/* size of segment (bytes) */
diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile
index eafd06ab59ef..e5de34d00b1a 100644
--- a/arch/parisc/kernel/Makefile
+++ b/arch/parisc/kernel/Makefile
@@ -23,7 +23,7 @@ obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_PA11)	+= pci-dma.o
 obj-$(CONFIG_PCI)	+= pci.o
 obj-$(CONFIG_MODULES)	+= module.o
-obj-$(CONFIG_64BIT)	+= binfmt_elf32.o sys_parisc32.o signal32.o
+obj-$(CONFIG_64BIT)	+= sys_parisc32.o signal32.o
 obj-$(CONFIG_STACKTRACE)+= stacktrace.o
 obj-$(CONFIG_AUDIT)	+= audit.o
 obj64-$(CONFIG_AUDIT)	+= compat_audit.o
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 3b8507f71050..e0e1c9775c32 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -268,7 +268,7 @@ static struct parisc_device *find_device_by_addr(unsigned long hpa)
  * Walks up the device tree looking for a device of the specified type.
  * If it finds it, it returns it.  If not, it returns NULL.
  */
-const struct parisc_device * __init
+const struct parisc_device *
 find_pa_parent_type(const struct parisc_device *padev, int type)
 {
 	const struct device *dev = &padev->dev;
@@ -448,7 +448,8 @@ static int match_by_id(struct device * dev, void * data)
  * Checks all the children of @parent for a matching @id.  If none
  * found, it allocates a new device and returns it.
  */
-static struct parisc_device * alloc_tree_node(struct device *parent, char id)
+static struct parisc_device * __init alloc_tree_node(
+			struct device *parent, char id)
 {
 	struct match_id_data d = {
 		.id = id,
@@ -825,8 +826,8 @@ static void walk_lower_bus(struct parisc_device *dev)
  * devices which are not physically connected (such as extra serial &
  * keyboard ports).  This problem is not yet solved.
  */
-static void walk_native_bus(unsigned long io_io_low, unsigned long io_io_high,
-                            struct device *parent)
+static void __init walk_native_bus(unsigned long io_io_low,
+	unsigned long io_io_high, struct device *parent)
 {
 	int i, devices_found = 0;
 	unsigned long hpa = io_io_low;
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 91bc0cac03a1..6df07ce4f3c2 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -367,19 +367,6 @@ static int proc_pcxl_dma_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int proc_pcxl_dma_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_pcxl_dma_show, NULL);
-}
-
-static const struct file_operations proc_pcxl_dma_ops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_pcxl_dma_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init
 pcxl_dma_init(void)
 {
@@ -397,8 +384,8 @@ pcxl_dma_init(void)
 			"pcxl_dma_init: Unable to create gsc /proc dir entry\n");
 	else {
 		struct proc_dir_entry* ent;
-		ent = proc_create("pcxl_dma", 0, proc_gsc_root,
-				  &proc_pcxl_dma_ops);
+		ent = proc_create_single("pcxl_dma", 0, proc_gsc_root,
+				proc_pcxl_dma_show);
 		if (!ent)
 			printk(KERN_WARNING
 				"pci-dma.c: Unable to create pcxl_dma /proc entry.\n");
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 13ee3569959a..ae684ac6efb6 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -174,7 +174,7 @@ void pcibios_set_master(struct pci_dev *dev)
  * pcibios_init_bridge() initializes cache line and default latency
  * for pci controllers and pci-pci bridges
  */
-void __init pcibios_init_bridge(struct pci_dev *dev)
+void __ref pcibios_init_bridge(struct pci_dev *dev)
 {
 	unsigned short bridge_ctl, bridge_ctl_new;
 
diff --git a/arch/parisc/kernel/pdc_chassis.c b/arch/parisc/kernel/pdc_chassis.c
index 3e04242de5a7..28e07482b0f1 100644
--- a/arch/parisc/kernel/pdc_chassis.c
+++ b/arch/parisc/kernel/pdc_chassis.c
@@ -266,18 +266,6 @@ static int pdc_chassis_warn_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int pdc_chassis_warn_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pdc_chassis_warn_show, NULL);
-}
-
-static const struct file_operations pdc_chassis_warn_fops = {
-	.open		= pdc_chassis_warn_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init pdc_chassis_create_procfs(void)
 {
 	unsigned long test;
@@ -292,7 +280,7 @@ static int __init pdc_chassis_create_procfs(void)
 
 	printk(KERN_INFO "Enabling PDC chassis warnings support v%s\n",
 			PDC_CHASSIS_VER);
-	proc_create("chassis", 0400, NULL, &pdc_chassis_warn_fops);
+	proc_create_single("chassis", 0400, NULL, pdc_chassis_warn_show);
 	return 0;
 }
 
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 1a2be6e639b5..7aa1d4d0d444 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -76,8 +76,6 @@ void user_enable_single_step(struct task_struct *task)
 	set_tsk_thread_flag(task, TIF_SINGLESTEP);
 
 	if (pa_psw(task)->n) {
-		struct siginfo si;
-
 		/* Nullified, just crank over the queue. */
 		task_regs(task)->iaoq[0] = task_regs(task)->iaoq[1];
 		task_regs(task)->iasq[0] = task_regs(task)->iasq[1];
@@ -90,11 +88,9 @@ void user_enable_single_step(struct task_struct *task)
 		ptrace_disable(task);
 		/* Don't wake up the task, but let the
 		   parent know something happened. */
-		si.si_code = TRAP_TRACE;
-		si.si_addr = (void __user *) (task_regs(task)->iaoq[0] & ~3);
-		si.si_signo = SIGTRAP;
-		si.si_errno = 0;
-		force_sig_info(SIGTRAP, &si, task);
+		force_sig_fault(SIGTRAP, TRAP_TRACE,
+				(void __user *) (task_regs(task)->iaoq[0] & ~3),
+				task);
 		/* notify_parent(task, SIGCHLD); */
 		return;
 	}
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 0e9675f857a5..8d3a7b80ac42 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -58,11 +58,6 @@ struct proc_dir_entry * proc_runway_root __read_mostly = NULL;
 struct proc_dir_entry * proc_gsc_root __read_mostly = NULL;
 struct proc_dir_entry * proc_mckinley_root __read_mostly = NULL;
 
-#if !defined(CONFIG_PA20) && (defined(CONFIG_IOMMU_CCIO) || defined(CONFIG_IOMMU_SBA))
-int parisc_bus_is_phys __read_mostly = 1;	/* Assume no IOMMU is present */
-EXPORT_SYMBOL(parisc_bus_is_phys);
-#endif
-
 void __init setup_cmdline(char **cmdline_p)
 {
 	extern unsigned int boot_args[];
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 4065b5e48c9d..5e26dbede5fc 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -423,8 +423,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 }
 
 #ifdef CONFIG_PROC_FS
-int __init
-setup_profiling_timer(unsigned int multiplier)
+int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
 }
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index c3830400ca28..a1e772f909cb 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -205,7 +205,7 @@ static int __init rtc_init(void)
 device_initcall(rtc_init);
 #endif
 
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	static struct pdc_tod tod_data;
 	if (pdc_tod_read(&tod_data) == 0) {
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 68e671a11987..4309ad31a874 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -297,13 +297,8 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err)
 #define GDB_BREAK_INSN 0x10004
 static void handle_gdb_break(struct pt_regs *regs, int wot)
 {
-	struct siginfo si;
-
-	si.si_signo = SIGTRAP;
-	si.si_errno = 0;
-	si.si_code = wot;
-	si.si_addr = (void __user *) (regs->iaoq[0] & ~3);
-	force_sig_info(SIGTRAP, &si, current);
+	force_sig_fault(SIGTRAP, wot,
+			(void __user *) (regs->iaoq[0] & ~3), current);
 }
 
 static void handle_break(struct pt_regs *regs)
@@ -487,7 +482,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 {
 	unsigned long fault_address = 0;
 	unsigned long fault_space = 0;
-	struct siginfo si;
+	int si_code;
 
 	if (code == 1)
 	    pdc_console_restart();  /* switch back to pdc if HPMC */
@@ -571,7 +566,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	case  8:
 		/* Illegal instruction trap */
 		die_if_kernel("Illegal instruction", regs, code);
-		si.si_code = ILL_ILLOPC;
+		si_code = ILL_ILLOPC;
 		goto give_sigill;
 
 	case  9:
@@ -582,7 +577,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	case 10:
 		/* Privileged operation trap */
 		die_if_kernel("Privileged operation", regs, code);
-		si.si_code = ILL_PRVOPC;
+		si_code = ILL_PRVOPC;
 		goto give_sigill;
 
 	case 11:
@@ -605,20 +600,16 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 		}
 
 		die_if_kernel("Privileged register usage", regs, code);
-		si.si_code = ILL_PRVREG;
+		si_code = ILL_PRVREG;
 	give_sigill:
-		si.si_signo = SIGILL;
-		si.si_errno = 0;
-		si.si_addr = (void __user *) regs->iaoq[0];
-		force_sig_info(SIGILL, &si, current);
+		force_sig_fault(SIGILL, si_code,
+				(void __user *) regs->iaoq[0], current);
 		return;
 
 	case 12:
 		/* Overflow Trap, let the userland signal handler do the cleanup */
-		si.si_signo = SIGFPE;
-		si.si_code = FPE_INTOVF;
-		si.si_addr = (void __user *) regs->iaoq[0];
-		force_sig_info(SIGFPE, &si, current);
+		force_sig_fault(SIGFPE, FPE_INTOVF,
+				(void __user *) regs->iaoq[0], current);
 		return;
 		
 	case 13:
@@ -626,13 +617,11 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 		   The condition succeeds in an instruction which traps
 		   on condition  */
 		if(user_mode(regs)){
-			si.si_signo = SIGFPE;
 			/* Let userspace app figure it out from the insn pointed
 			 * to by si_addr.
 			 */
-			si.si_code = FPE_CONDTRAP;
-			si.si_addr = (void __user *) regs->iaoq[0];
-			force_sig_info(SIGFPE, &si, current);
+			force_sig_fault(SIGFPE, FPE_CONDTRAP,
+					(void __user *) regs->iaoq[0], current);
 			return;
 		} 
 		/* The kernel doesn't want to handle condition codes */
@@ -741,14 +730,10 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 			return;
 
 		die_if_kernel("Protection id trap", regs, code);
-		si.si_code = SEGV_MAPERR;
-		si.si_signo = SIGSEGV;
-		si.si_errno = 0;
-		if (code == 7)
-		    si.si_addr = (void __user *) regs->iaoq[0];
-		else
-		    si.si_addr = (void __user *) regs->ior;
-		force_sig_info(SIGSEGV, &si, current);
+		force_sig_fault(SIGSEGV, SEGV_MAPERR,
+				(code == 7)?
+				((void __user *) regs->iaoq[0]) :
+				((void __user *) regs->ior), current);
 		return;
 
 	case 28: 
@@ -762,11 +747,8 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 				"handle_interruption() pid=%d command='%s'\n",
 				task_pid_nr(current), current->comm);
 			/* SIGBUS, for lack of a better one. */
-			si.si_signo = SIGBUS;
-			si.si_code = BUS_OBJERR;
-			si.si_errno = 0;
-			si.si_addr = (void __user *) regs->ior;
-			force_sig_info(SIGBUS, &si, current);
+			force_sig_fault(SIGBUS, BUS_OBJERR,
+					(void __user *)regs->ior, current);
 			return;
 		}
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
@@ -781,11 +763,8 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 				"User fault %d on space 0x%08lx, pid=%d command='%s'\n",
 				code, fault_space,
 				task_pid_nr(current), current->comm);
-		si.si_signo = SIGSEGV;
-		si.si_errno = 0;
-		si.si_code = SEGV_MAPERR;
-		si.si_addr = (void __user *) regs->ior;
-		force_sig_info(SIGSEGV, &si, current);
+		force_sig_fault(SIGSEGV, SEGV_MAPERR,
+				(void __user *)regs->ior, current);
 		return;
 	    }
 	}
@@ -837,6 +816,17 @@ void __init initialize_ivt(const void *iva)
 	if (pdc_instr(&instr) == PDC_OK)
 		ivap[0] = instr;
 
+	/*
+	 * Rules for the checksum of the HPMC handler:
+	 * 1. The IVA does not point to PDC/PDH space (ie: the OS has installed
+	 *    its own IVA).
+	 * 2. The word at IVA + 32 is nonzero.
+	 * 3. If Length (IVA + 60) is not zero, then Length (IVA + 60) and
+	 *    Address (IVA + 56) are word-aligned.
+	 * 4. The checksum of the 8 words starting at IVA + 32 plus the sum of
+	 *    the Length/4 words starting at Address is zero.
+	 */
+
 	/* Compute Checksum for HPMC handler */
 	length = os_hpmc_size;
 	ivap[7] = length;
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index e36f7b75ab07..932bfc0b7cd8 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -452,7 +452,6 @@ void handle_unaligned(struct pt_regs *regs)
 	unsigned long newbase = R1(regs->iir)?regs->gr[R1(regs->iir)]:0;
 	int modify = 0;
 	int ret = ERR_NOTHANDLED;
-	struct siginfo si;
 	register int flop=0;	/* true if this is a flop */
 
 	__inc_irq_stat(irq_unaligned_count);
@@ -690,21 +689,15 @@ void handle_unaligned(struct pt_regs *regs)
 
 		if (ret == ERR_PAGEFAULT)
 		{
-			si.si_signo = SIGSEGV;
-			si.si_errno = 0;
-			si.si_code = SEGV_MAPERR;
-			si.si_addr = (void __user *)regs->ior;
-			force_sig_info(SIGSEGV, &si, current);
+			force_sig_fault(SIGSEGV, SEGV_MAPERR,
+					(void __user *)regs->ior, current);
 		}
 		else
 		{
 force_sigbus:
 			/* couldn't handle it ... */
-			si.si_signo = SIGBUS;
-			si.si_errno = 0;
-			si.si_code = BUS_ADRALN;
-			si.si_addr = (void __user *)regs->ior;
-			force_sig_info(SIGBUS, &si, current);
+			force_sig_fault(SIGBUS, BUS_ADRALN,
+					(void __user *)regs->ior, current);
 		}
 		
 		return;
diff --git a/arch/parisc/math-emu/driver.c b/arch/parisc/math-emu/driver.c
index 2fb59d2e2b29..0590e05571d1 100644
--- a/arch/parisc/math-emu/driver.c
+++ b/arch/parisc/math-emu/driver.c
@@ -81,7 +81,6 @@ int
 handle_fpe(struct pt_regs *regs)
 {
 	extern void printbinary(unsigned long x, int nbits);
-	struct siginfo si;
 	unsigned int orig_sw, sw;
 	int signalcode;
 	/* need an intermediate copy of float regs because FPU emulation
@@ -117,11 +116,8 @@ handle_fpe(struct pt_regs *regs)
 
 	memcpy(regs->fr, frcopy, sizeof regs->fr);
 	if (signalcode != 0) {
-	    si.si_signo = signalcode >> 24;
-	    si.si_errno = 0;
-	    si.si_code = signalcode & 0xffffff;
-	    si.si_addr = (void __user *) regs->iaoq[0];
-	    force_sig_info(si.si_signo, &si, current);
+	    force_sig_fault(signalcode >> 24, signalcode & 0xffffff,
+			    (void __user *) regs->iaoq[0], current);
 	    return -1;
 	}
 
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index e247edbca68e..a80117980fc2 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -353,23 +353,22 @@ bad_area:
 	up_read(&mm->mmap_sem);
 
 	if (user_mode(regs)) {
-		struct siginfo si;
-		unsigned int lsb = 0;
+		int signo, si_code;
 
 		switch (code) {
 		case 15:	/* Data TLB miss fault/Data page fault */
 			/* send SIGSEGV when outside of vma */
 			if (!vma ||
 			    address < vma->vm_start || address >= vma->vm_end) {
-				si.si_signo = SIGSEGV;
-				si.si_code = SEGV_MAPERR;
+				signo = SIGSEGV;
+				si_code = SEGV_MAPERR;
 				break;
 			}
 
 			/* send SIGSEGV for wrong permissions */
 			if ((vma->vm_flags & acc_type) != acc_type) {
-				si.si_signo = SIGSEGV;
-				si.si_code = SEGV_ACCERR;
+				signo = SIGSEGV;
+				si_code = SEGV_ACCERR;
 				break;
 			}
 
@@ -377,43 +376,40 @@ bad_area:
 			/* fall through */
 		case 17:	/* NA data TLB miss / page fault */
 		case 18:	/* Unaligned access - PCXS only */
-			si.si_signo = SIGBUS;
-			si.si_code = (code == 18) ? BUS_ADRALN : BUS_ADRERR;
+			signo = SIGBUS;
+			si_code = (code == 18) ? BUS_ADRALN : BUS_ADRERR;
 			break;
 		case 16:	/* Non-access instruction TLB miss fault */
 		case 26:	/* PCXL: Data memory access rights trap */
 		default:
-			si.si_signo = SIGSEGV;
-			si.si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR;
+			signo = SIGSEGV;
+			si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR;
 			break;
 		}
-
 #ifdef CONFIG_MEMORY_FAILURE
 		if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+			unsigned int lsb = 0;
 			printk(KERN_ERR
 	"MCE: Killing %s:%d due to hardware memory corruption fault at %08lx\n",
 			tsk->comm, tsk->pid, address);
-			si.si_signo = SIGBUS;
-			si.si_code = BUS_MCEERR_AR;
+			/*
+			 * Either small page or large page may be poisoned.
+			 * In other words, VM_FAULT_HWPOISON_LARGE and
+			 * VM_FAULT_HWPOISON are mutually exclusive.
+			 */
+			if (fault & VM_FAULT_HWPOISON_LARGE)
+				lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+			else if (fault & VM_FAULT_HWPOISON)
+				lsb = PAGE_SHIFT;
+
+			force_sig_mceerr(BUS_MCEERR_AR, (void __user *) address,
+					 lsb, current);
+			return;
 		}
 #endif
+		show_signal_msg(regs, code, address, tsk, vma);
 
-		/*
-		 * Either small page or large page may be poisoned.
-		 * In other words, VM_FAULT_HWPOISON_LARGE and
-		 * VM_FAULT_HWPOISON are mutually exclusive.
-		 */
-		if (fault & VM_FAULT_HWPOISON_LARGE)
-			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
-		else if (fault & VM_FAULT_HWPOISON)
-			lsb = PAGE_SHIFT;
-		else
-			show_signal_msg(regs, code, address, tsk, vma);
-		si.si_addr_lsb = lsb;
-
-		si.si_errno = 0;
-		si.si_addr = (void __user *) address;
-		force_sig_info(si.si_signo, &si, current);
+		force_sig_fault(signo, si_code, (void __user *) address, current);
 		return;
 	}
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index cab32ee824d2..2607d2d33405 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -516,7 +516,7 @@ static void __init map_pages(unsigned long start_vaddr,
 	}
 }
 
-void free_initmem(void)
+void __ref free_initmem(void)
 {
 	unsigned long init_begin = (unsigned long)__init_begin;
 	unsigned long init_end = (unsigned long)__init_end;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c32a181a7cbb..9c0ee1859323 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -13,12 +13,6 @@ config 64BIT
 	bool
 	default y if PPC64
 
-config ARCH_PHYS_ADDR_T_64BIT
-       def_bool PPC64 || PHYS_64BIT
-
-config ARCH_DMA_ADDR_T_64BIT
-	def_bool ARCH_PHYS_ADDR_T_64BIT
-
 config MMU
 	bool
 	default y
@@ -187,7 +181,6 @@ config PPC
 	select HAVE_CONTEXT_TRACKING		if PPC64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if MPROFILE_KERNEL
 	select HAVE_EBPF_JIT			if PPC64
@@ -205,6 +198,7 @@ config PPC
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
+	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION
 	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
@@ -223,9 +217,11 @@ config PPC
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select HAVE_IRQ_TIME_ACCOUNTING
+	select IOMMU_HELPER			if PPC64
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
 	select MODULES_USE_ELF_RELA
+	select NEED_SG_DMA_LENGTH
 	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
@@ -478,19 +474,6 @@ config MPROFILE_KERNEL
 	depends on PPC64 && CPU_LITTLE_ENDIAN
 	def_bool !DISABLE_MPROFILE_KERNEL
 
-config IOMMU_HELPER
-	def_bool PPC64
-
-config SWIOTLB
-	bool "SWIOTLB support"
-	default n
-	select IOMMU_HELPER
-	---help---
-	  Support for IO bounce buffering for systems without an IOMMU.
-	  This allows us to DMA to the full physical address space on
-	  platforms where the size of a physical address is larger
-	  than the bus address.  Not all platforms support this.
-
 config HOTPLUG_CPU
 	bool "Support for enabling/disabling CPUs"
 	depends on SMP && (PPC_PSERIES || \
@@ -883,7 +866,7 @@ config PPC_MEM_KEYS
 	  page-based protections, but without requiring modification of the
 	  page tables when an application changes protection domains.
 
-	  For details, see Documentation/vm/protection-keys.txt
+	  For details, see Documentation/vm/protection-keys.rst
 
 	  If unsure, say y.
 
@@ -913,9 +896,6 @@ config ZONE_DMA
 config NEED_DMA_MAP_STATE
 	def_bool (PPC64 || NOT_COHERENT_CACHE)
 
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
 config GENERIC_ISA_DMA
 	bool
 	depends on ISA_DMA_API
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 62168e1158f1..85c8af2bb272 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -17,7 +17,6 @@
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
-typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_pid_t;
 typedef u32		__compat_uid_t;
@@ -45,16 +44,6 @@ typedef u32		compat_ulong_t;
 typedef u64		compat_u64;
 typedef u32		compat_uptr_t;
 
-struct compat_timespec {
-	compat_time_t	tv_sec;
-	s32		tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t	tv_sec;
-	s32		tv_usec;
-};
-
 struct compat_stat {
 	compat_dev_t	st_dev;
 	compat_ino_t	st_ino;
@@ -173,10 +162,10 @@ struct compat_ipc64_perm {
 
 struct compat_semid64_ds {
 	struct compat_ipc64_perm sem_perm;
-	unsigned int __unused1;
-	compat_time_t sem_otime;
-	unsigned int __unused2;
-	compat_time_t sem_ctime;
+	unsigned int sem_otime_high;
+	unsigned int sem_otime;
+	unsigned int sem_ctime_high;
+	unsigned int sem_ctime;
 	compat_ulong_t sem_nsems;
 	compat_ulong_t __unused3;
 	compat_ulong_t __unused4;
@@ -184,12 +173,12 @@ struct compat_semid64_ds {
 
 struct compat_msqid64_ds {
 	struct compat_ipc64_perm msg_perm;
-	unsigned int __unused1;
-	compat_time_t msg_stime;
-	unsigned int __unused2;
-	compat_time_t msg_rtime;
-	unsigned int __unused3;
-	compat_time_t msg_ctime;
+	unsigned int msg_stime_high;
+	unsigned int msg_stime;
+	unsigned int msg_rtime_high;
+	unsigned int msg_rtime;
+	unsigned int msg_ctime_high;
+	unsigned int msg_ctime;
 	compat_ulong_t msg_cbytes;
 	compat_ulong_t msg_qnum;
 	compat_ulong_t msg_qbytes;
@@ -201,12 +190,12 @@ struct compat_msqid64_ds {
 
 struct compat_shmid64_ds {
 	struct compat_ipc64_perm shm_perm;
-	unsigned int __unused1;
-	compat_time_t shm_atime;
-	unsigned int __unused2;
-	compat_time_t shm_dtime;
-	unsigned int __unused3;
-	compat_time_t shm_ctime;
+	unsigned int shm_atime_high;
+	unsigned int shm_atime;
+	unsigned int shm_dtime_high;
+	unsigned int shm_dtime;
+	unsigned int shm_ctime_high;
+	unsigned int shm_ctime;
 	unsigned int __unused4;
 	compat_size_t shm_segsz;
 	compat_pid_t shm_cpid;
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 471b2274fbeb..c40b4380951c 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -74,6 +74,27 @@
  */
 #define EX_R3		EX_DAR
 
+#define STF_ENTRY_BARRIER_SLOT						\
+	STF_ENTRY_BARRIER_FIXUP_SECTION;				\
+	nop;								\
+	nop;								\
+	nop
+
+#define STF_EXIT_BARRIER_SLOT						\
+	STF_EXIT_BARRIER_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop;								\
+	nop;								\
+	nop;								\
+	nop
+
+/*
+ * r10 must be free to use, r13 must be paca
+ */
+#define INTERRUPT_TO_KERNEL						\
+	STF_ENTRY_BARRIER_SLOT
+
 /*
  * Macros for annotating the expected destination of (h)rfid
  *
@@ -90,16 +111,19 @@
 	rfid
 
 #define RFI_TO_USER							\
+	STF_EXIT_BARRIER_SLOT;						\
 	RFI_FLUSH_SLOT;							\
 	rfid;								\
 	b	rfi_flush_fallback
 
 #define RFI_TO_USER_OR_KERNEL						\
+	STF_EXIT_BARRIER_SLOT;						\
 	RFI_FLUSH_SLOT;							\
 	rfid;								\
 	b	rfi_flush_fallback
 
 #define RFI_TO_GUEST							\
+	STF_EXIT_BARRIER_SLOT;						\
 	RFI_FLUSH_SLOT;							\
 	rfid;								\
 	b	rfi_flush_fallback
@@ -108,21 +132,25 @@
 	hrfid
 
 #define HRFI_TO_USER							\
+	STF_EXIT_BARRIER_SLOT;						\
 	RFI_FLUSH_SLOT;							\
 	hrfid;								\
 	b	hrfi_flush_fallback
 
 #define HRFI_TO_USER_OR_KERNEL						\
+	STF_EXIT_BARRIER_SLOT;						\
 	RFI_FLUSH_SLOT;							\
 	hrfid;								\
 	b	hrfi_flush_fallback
 
 #define HRFI_TO_GUEST							\
+	STF_EXIT_BARRIER_SLOT;						\
 	RFI_FLUSH_SLOT;							\
 	hrfid;								\
 	b	hrfi_flush_fallback
 
 #define HRFI_TO_UNKNOWN							\
+	STF_EXIT_BARRIER_SLOT;						\
 	RFI_FLUSH_SLOT;							\
 	hrfid;								\
 	b	hrfi_flush_fallback
@@ -254,6 +282,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define __EXCEPTION_PROLOG_1_PRE(area)					\
 	OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR);		\
 	OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR);		\
+	INTERRUPT_TO_KERNEL;						\
 	SAVE_CTR(r10, area);						\
 	mfcr	r9;
 
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 1e82eb3caabd..a9b64df34e2a 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -187,6 +187,22 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET label##1b-label##3b;		\
 	.popsection;
 
+#define STF_ENTRY_BARRIER_FIXUP_SECTION			\
+953:							\
+	.pushsection __stf_entry_barrier_fixup,"a";	\
+	.align 2;					\
+954:							\
+	FTR_ENTRY_OFFSET 953b-954b;			\
+	.popsection;
+
+#define STF_EXIT_BARRIER_FIXUP_SECTION			\
+955:							\
+	.pushsection __stf_exit_barrier_fixup,"a";	\
+	.align 2;					\
+956:							\
+	FTR_ENTRY_OFFSET 955b-956b;			\
+	.popsection;
+
 #define RFI_FLUSH_FIXUP_SECTION				\
 951:							\
 	.pushsection __rfi_flush_fixup,"a";		\
@@ -199,6 +215,9 @@ label##3:					       	\
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 
+extern long stf_barrier_fallback;
+extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
+extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
 extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
 
 void apply_feature_fixups(void);
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 9abddde372ab..b2dabd06659d 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -69,17 +69,30 @@ struct dyn_arch_ftrace {
 #endif
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && !defined(__ASSEMBLY__)
-#ifdef PPC64_ELF_ABI_v1
+/*
+ * Some syscall entry functions on powerpc start with "ppc_" (fork and clone,
+ * for instance) or ppc32_/ppc64_. We should also match the sys_ variant with
+ * those.
+ */
 #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+#ifdef PPC64_ELF_ABI_v1
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+	/* We need to skip past the initial dot, and the __se_sys alias */
+	return !strcmp(sym + 1, name) ||
+		(!strncmp(sym, ".__se_sys", 9) && !strcmp(sym + 6, name)) ||
+		(!strncmp(sym, ".ppc_", 5) && !strcmp(sym + 5, name + 4)) ||
+		(!strncmp(sym, ".ppc32_", 7) && !strcmp(sym + 7, name + 4)) ||
+		(!strncmp(sym, ".ppc64_", 7) && !strcmp(sym + 7, name + 4));
+}
+#else
 static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
 {
-	/*
-	 * Compare the symbol name with the system call name. Skip the .sys or .SyS
-	 * prefix from the symbol name and the sys prefix from the system call name and
-	 * just match the rest. This is only needed on ppc64 since symbol names on
-	 * 32bit do not start with a period so the generic function will work.
-	 */
-	return !strcmp(sym + 4, name + 3);
+	return !strcmp(sym, name) ||
+		(!strncmp(sym, "__se_sys", 8) && !strcmp(sym + 5, name)) ||
+		(!strncmp(sym, "ppc_", 4) && !strcmp(sym + 4, name + 4)) ||
+		(!strncmp(sym, "ppc32_", 6) && !strcmp(sym + 6, name + 4)) ||
+		(!strncmp(sym, "ppc64_", 6) && !strcmp(sym + 6, name + 4));
 }
 #endif
 #endif /* CONFIG_FTRACE_SYSCALLS && !__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index 5986d473722b..383f628acbf8 100644
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -25,15 +25,8 @@ typedef struct {
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 #define __ARCH_IRQ_STAT
-
-#define local_softirq_pending()	__this_cpu_read(irq_stat.__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED
 
-#define set_softirq_pending(x) __this_cpu_write(irq_stat.__softirq_pending, (x))
-#define or_softirq_pending(x) __this_cpu_or(irq_stat.__softirq_pending, (x))
-
 static inline void ack_bad_irq(unsigned int irq)
 {
 	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 2e2dddab5d65..662c8347d699 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -279,6 +279,7 @@
 #define H_GET_MPP_X		0x314
 #define H_SET_MODE		0x31C
 #define H_CLEAR_HPT		0x358
+#define H_REQUEST_VMC		0x360
 #define H_RESIZE_HPT_PREPARE	0x36C
 #define H_RESIZE_HPT_COMMIT	0x370
 #define H_REGISTER_PROC_TBL	0x37C
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4c02a7378d06..e7377b73cfec 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -96,6 +96,7 @@ struct kvmppc_vcore {
 	struct kvm_vcpu *runner;
 	struct kvm *kvm;
 	u64 tb_offset;		/* guest timebase - host timebase */
+	u64 tb_offset_applied;	/* timebase offset currently in force */
 	ulong lpcr;
 	u32 arch_compat;
 	ulong pcr;
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 4185f1c96125..3f109a3e3edb 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -165,7 +165,6 @@ struct paca_struct {
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
 	u16 trap_save;			/* Used when bad stack is encountered */
 	u8 irq_soft_mask;		/* mask for irq soft masking */
-	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 irq_happened;		/* irq happened while soft-disabled */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 401c62aad5e4..2af9ded80540 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -92,24 +92,6 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
 
 #define HAVE_PCI_LEGACY	1
 
-#ifdef CONFIG_PPC64
-
-/* The PCI address space does not equal the physical memory address
- * space (we have an IOMMU).  The IDE and SCSI device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS	(0)
-
-#else /* 32-bit */
-
-/* The PCI address space does equal the physical memory
- * address space (no IOMMU).  The IDE and SCSI device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS     (1)
-
-#endif /* CONFIG_PPC64 */
-
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
 extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h
index d1c2d2e658cf..2f3ff7a27881 100644
--- a/arch/powerpc/include/asm/powernv.h
+++ b/arch/powerpc/include/asm/powernv.h
@@ -15,7 +15,7 @@
 extern void powernv_set_nmmu_ptcr(unsigned long ptcr);
 extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 			unsigned long flags,
-			struct npu_context *(*cb)(struct npu_context *, void *),
+			void (*cb)(struct npu_context *, void *),
 			void *priv);
 extern void pnv_npu2_destroy_context(struct npu_context *context,
 				struct pci_dev *gpdev);
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index fa4d2e1cf772..44989b22383c 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -12,6 +12,17 @@
 extern unsigned long powerpc_security_features;
 extern bool rfi_flush;
 
+/* These are bit flags */
+enum stf_barrier_type {
+	STF_BARRIER_NONE	= 0x1,
+	STF_BARRIER_FALLBACK	= 0x2,
+	STF_BARRIER_EIEIO	= 0x4,
+	STF_BARRIER_SYNC_ORI	= 0x8,
+};
+
+void setup_stf_barrier(void);
+void do_stf_barrier_fixups(enum stf_barrier_type types);
+
 static inline void security_ftr_set(unsigned long feature)
 {
 	powerpc_security_features |= feature;
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 9f421641a35c..16b077801a5f 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -91,6 +91,7 @@ extern int start_topology_update(void);
 extern int stop_topology_update(void);
 extern int prrn_is_enabled(void);
 extern int find_and_online_cpu_nid(int cpu);
+extern int timed_topology_update(int nsecs);
 #else
 static inline int start_topology_update(void)
 {
@@ -108,16 +109,12 @@ static inline int find_and_online_cpu_nid(int cpu)
 {
 	return 0;
 }
+static inline int timed_topology_update(int nsecs)
+{
+	return 0;
+}
 #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
 
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES)
-#if defined(CONFIG_PPC_SPLPAR)
-extern int timed_topology_update(int nsecs);
-#else
-#define	timed_topology_update(nsecs)
-#endif /* CONFIG_PPC_SPLPAR */
-#endif /* CONFIG_HOTPLUG_CPU || CONFIG_NEED_MULTIPLE_NODES */
-
 #include <asm-generic/topology.h>
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/include/uapi/asm/msgbuf.h b/arch/powerpc/include/uapi/asm/msgbuf.h
index 65beb0942500..2b1b37797a47 100644
--- a/arch/powerpc/include/uapi/asm/msgbuf.h
+++ b/arch/powerpc/include/uapi/asm/msgbuf.h
@@ -10,18 +10,18 @@
 
 struct msqid64_ds {
 	struct ipc64_perm msg_perm;
-#ifndef __powerpc64__
-	unsigned int	__unused1;
-#endif
+#ifdef __powerpc64__
 	__kernel_time_t msg_stime;	/* last msgsnd time */
-#ifndef __powerpc64__
-	unsigned int	__unused2;
-#endif
 	__kernel_time_t msg_rtime;	/* last msgrcv time */
-#ifndef __powerpc64__
-	unsigned int	__unused3;
-#endif
 	__kernel_time_t msg_ctime;	/* last change time */
+#else
+	unsigned long  msg_stime_high;
+	unsigned long  msg_stime;	/* last msgsnd time */
+	unsigned long  msg_rtime_high;
+	unsigned long  msg_rtime;	/* last msgrcv time */
+	unsigned long  msg_ctime_high;
+	unsigned long  msg_ctime;	/* last change time */
+#endif
 	unsigned long  msg_cbytes;	/* current number of bytes on queue */
 	unsigned long  msg_qnum;	/* number of messages in queue */
 	unsigned long  msg_qbytes;	/* max number of bytes on queue */
diff --git a/arch/powerpc/include/uapi/asm/sembuf.h b/arch/powerpc/include/uapi/asm/sembuf.h
index 8f393d60f02d..3f60946f77e3 100644
--- a/arch/powerpc/include/uapi/asm/sembuf.h
+++ b/arch/powerpc/include/uapi/asm/sembuf.h
@@ -15,20 +15,20 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
+ * - 2 miscellaneous 32/64-bit values
  */
 
 struct semid64_ds {
 	struct ipc64_perm sem_perm;	/* permissions .. see ipc.h */
 #ifndef __powerpc64__
-	unsigned long	__unused1;
-#endif
+	unsigned long	sem_otime_high;
+	unsigned long	sem_otime;	/* last semop time */
+	unsigned long	sem_ctime_high;
+	unsigned long	sem_ctime;	/* last change time */
+#else
 	__kernel_time_t	sem_otime;	/* last semop time */
-#ifndef __powerpc64__
-	unsigned long	__unused2;
-#endif
 	__kernel_time_t	sem_ctime;	/* last change time */
+#endif
 	unsigned long	sem_nsems;	/* no. of semaphores in array */
 	unsigned long	__unused3;
 	unsigned long	__unused4;
diff --git a/arch/powerpc/include/uapi/asm/shmbuf.h b/arch/powerpc/include/uapi/asm/shmbuf.h
index deb1c3e503d3..b591c4d7e4c5 100644
--- a/arch/powerpc/include/uapi/asm/shmbuf.h
+++ b/arch/powerpc/include/uapi/asm/shmbuf.h
@@ -16,25 +16,22 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
 
 struct shmid64_ds {
 	struct ipc64_perm	shm_perm;	/* operation perms */
-#ifndef __powerpc64__
-	unsigned long		__unused1;
-#endif
+#ifdef __powerpc64__
 	__kernel_time_t		shm_atime;	/* last attach time */
-#ifndef __powerpc64__
-	unsigned long		__unused2;
-#endif
 	__kernel_time_t		shm_dtime;	/* last detach time */
-#ifndef __powerpc64__
-	unsigned long		__unused3;
-#endif
 	__kernel_time_t		shm_ctime;	/* last change time */
-#ifndef __powerpc64__
+#else
+	unsigned long		shm_atime_high;
+	unsigned long		shm_atime;	/* last attach time */
+	unsigned long		shm_dtime_high;
+	unsigned long		shm_dtime;	/* last detach time */
+	unsigned long		shm_ctime_high;
+	unsigned long		shm_ctime;	/* last change time */
 	unsigned long		__unused4;
 #endif
 	size_t			shm_segsz;	/* size of segment (bytes) */
diff --git a/arch/powerpc/include/uapi/asm/siginfo.h b/arch/powerpc/include/uapi/asm/siginfo.h
index 9f142451a01f..1d51d9b88221 100644
--- a/arch/powerpc/include/uapi/asm/siginfo.h
+++ b/arch/powerpc/include/uapi/asm/siginfo.h
@@ -15,19 +15,4 @@
 
 #include <asm-generic/siginfo.h>
 
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME	0	/* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-/*
- * SIGTRAP si_codes
- */
-#ifdef __KERNEL__
-#define TRAP_FIXME	0	/* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-
 #endif	/* _ASM_POWERPC_SIGINFO_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6bee65f3cfd3..8817c5a6bcc2 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -13,6 +13,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/compat.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -42,7 +43,6 @@
 #include <asm/paca.h>
 #include <asm/lppaca.h>
 #include <asm/cache.h>
-#include <asm/compat.h>
 #include <asm/mmu.h>
 #include <asm/hvcall.h>
 #include <asm/xics.h>
@@ -562,6 +562,7 @@ int main(void)
 	OFFSET(VCORE_NAPPING_THREADS, kvmppc_vcore, napping_threads);
 	OFFSET(VCORE_KVM, kvmppc_vcore, kvm);
 	OFFSET(VCORE_TB_OFFSET, kvmppc_vcore, tb_offset);
+	OFFSET(VCORE_TB_OFFSET_APPL, kvmppc_vcore, tb_offset_applied);
 	OFFSET(VCORE_LPCR, kvmppc_vcore, lpcr);
 	OFFSET(VCORE_PCR, kvmppc_vcore, pcr);
 	OFFSET(VCORE_DPDES, kvmppc_vcore, dpdes);
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 3f30c994e931..458b928dbd84 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -28,6 +28,7 @@ _GLOBAL(__setup_cpu_power7)
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
+	mtspr	SPRN_PCR,r0
 	mfspr	r3,SPRN_LPCR
 	li	r4,(LPCR_LPES1 >> LPCR_LPES_SH)
 	bl	__init_LPCR_ISA206
@@ -41,6 +42,7 @@ _GLOBAL(__restore_cpu_power7)
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
+	mtspr	SPRN_PCR,r0
 	mfspr	r3,SPRN_LPCR
 	li	r4,(LPCR_LPES1 >> LPCR_LPES_SH)
 	bl	__init_LPCR_ISA206
@@ -57,6 +59,7 @@ _GLOBAL(__setup_cpu_power8)
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
+	mtspr	SPRN_PCR,r0
 	mfspr	r3,SPRN_LPCR
 	ori	r3, r3, LPCR_PECEDH
 	li	r4,0 /* LPES = 0 */
@@ -78,6 +81,7 @@ _GLOBAL(__restore_cpu_power8)
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
+	mtspr	SPRN_PCR,r0
 	mfspr   r3,SPRN_LPCR
 	ori	r3, r3, LPCR_PECEDH
 	li	r4,0 /* LPES = 0 */
@@ -99,6 +103,7 @@ _GLOBAL(__setup_cpu_power9)
 	mtspr	SPRN_PSSCR,r0
 	mtspr	SPRN_LPID,r0
 	mtspr	SPRN_PID,r0
+	mtspr	SPRN_PCR,r0
 	mfspr	r3,SPRN_LPCR
 	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE  | LPCR_HEIC)
 	or	r3, r3, r4
@@ -123,6 +128,7 @@ _GLOBAL(__restore_cpu_power9)
 	mtspr	SPRN_PSSCR,r0
 	mtspr	SPRN_LPID,r0
 	mtspr	SPRN_PID,r0
+	mtspr	SPRN_PCR,r0
 	mfspr   r3,SPRN_LPCR
 	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
 	or	r3, r3, r4
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index da20569de9d4..138157deeadf 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -309,8 +309,6 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_coherent_mask);
 
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
 int dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	if (ppc_md.dma_set_mask)
@@ -361,7 +359,6 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask);
 
 static int __init dma_init(void)
 {
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 #ifdef CONFIG_PCI
 	dma_debug_add_bus(&pci_bus_type);
 #endif
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 8ab51f6ca03a..c904477abaf3 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -101,6 +101,7 @@ static void __restore_cpu_cpufeatures(void)
 	if (hv_mode) {
 		mtspr(SPRN_LPID, 0);
 		mtspr(SPRN_HFSCR, system_registers.hfscr);
+		mtspr(SPRN_PCR, 0);
 	}
 	mtspr(SPRN_FSCR, system_registers.fscr);
 
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index bc640e4c5ca5..90bb39b1a23c 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1775,18 +1775,6 @@ static int proc_eeh_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int proc_eeh_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_eeh_show, NULL);
-}
-
-static const struct file_operations proc_eeh_operations = {
-	.open      = proc_eeh_open,
-	.read      = seq_read,
-	.llseek    = seq_lseek,
-	.release   = single_release,
-};
-
 #ifdef CONFIG_DEBUG_FS
 static int eeh_enable_dbgfs_set(void *data, u64 val)
 {
@@ -1828,7 +1816,7 @@ DEFINE_SIMPLE_ATTRIBUTE(eeh_freeze_dbgfs_ops, eeh_freeze_dbgfs_get,
 static int __init eeh_init_proc(void)
 {
 	if (machine_is(pseries) || machine_is(powernv)) {
-		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
+		proc_create_single("powerpc/eeh", 0, NULL, proc_eeh_show);
 #ifdef CONFIG_DEBUG_FS
 		debugfs_create_file("eeh_enable", 0600,
                                     powerpc_debugfs_root, NULL,
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 2d4956e97aa9..ee5a67d57aab 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -807,7 +807,8 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev)
 	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/* PCI Command: 0x4 */
-	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1] |
+			      PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
 
 	/* Check the PCIe link is ready */
 	eeh_bridge_check_link(edev);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ae6a849db60b..f283958129f2 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -885,7 +885,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 
-EXC_REAL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED)
+EXC_REAL_OOL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED)
 EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900, IRQS_DISABLED)
 TRAMP_KVM(PACA_EXGEN, 0x900)
 EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt)
@@ -961,6 +961,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
 	mtctr	r13;							\
 	GET_PACA(r13);							\
 	std	r10,PACA_EXGEN+EX_R10(r13);				\
+	INTERRUPT_TO_KERNEL;						\
 	KVMTEST_PR(0xc00); /* uses r10, branch to do_kvm_0xc00_system_call */ \
 	HMT_MEDIUM;							\
 	mfctr	r9;
@@ -969,7 +970,8 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
 #define SYSCALL_KVMTEST							\
 	HMT_MEDIUM;							\
 	mr	r9,r13;							\
-	GET_PACA(r13);
+	GET_PACA(r13);							\
+	INTERRUPT_TO_KERNEL;
 #endif
 	
 #define LOAD_SYSCALL_HANDLER(reg)					\
@@ -1507,6 +1509,19 @@ masked_##_H##interrupt:					\
 	b	.;					\
 	MASKED_DEC_HANDLER(_H)
 
+TRAMP_REAL_BEGIN(stf_barrier_fallback)
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	sync
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ori	31,31,0
+	.rept 14
+	b	1f
+1:
+	.endr
+	blr
+
 TRAMP_REAL_BEGIN(rfi_flush_fallback)
 	SET_SCRATCH0(r13);
 	GET_PACA(r13);
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 79d005445c6c..e734f6e45abc 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -553,12 +553,12 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	lbz	r0,HSTATE_HWTHREAD_STATE(r13)
 	cmpwi	r0,KVM_HWTHREAD_IN_KERNEL
-	beq	1f
+	beq	0f
 	li	r0,KVM_HWTHREAD_IN_KERNEL
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 	/* Order setting hwthread_state vs. testing hwthread_req */
 	sync
-	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
+0:	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
 	cmpwi	r0,0
 	beq	1f
 	b	kvm_start_guest
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index fe6fc63251fe..38c5b4764bfe 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -441,7 +441,6 @@ static int mce_handle_ierror(struct pt_regs *regs,
 					if (pfn != ULONG_MAX) {
 						*phys_addr =
 							(pfn << PAGE_SHIFT);
-						handled = 1;
 					}
 				}
 			}
@@ -532,9 +531,7 @@ static int mce_handle_derror(struct pt_regs *regs,
 			 * kernel/exception-64s.h
 			 */
 			if (get_paca()->in_mce < MAX_MCE_DEPTH)
-				if (!mce_find_instr_ea_and_pfn(regs, addr,
-								phys_addr))
-					handled = 1;
+				mce_find_instr_ea_and_pfn(regs, addr, phys_addr);
 		}
 		found = 1;
 	}
@@ -572,7 +569,7 @@ static long mce_handle_error(struct pt_regs *regs,
 		const struct mce_ierror_table itable[])
 {
 	struct mce_error_info mce_err = { 0 };
-	uint64_t addr, phys_addr;
+	uint64_t addr, phys_addr = ULONG_MAX;
 	uint64_t srr1 = regs->msr;
 	long handled;
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 1237f13fed51..26ea9793d290 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -632,6 +632,7 @@ void do_break (struct pt_regs *regs, unsigned long address,
 	hw_breakpoint_disable();
 
 	/* Deliver the signal to userspace */
+	clear_siginfo(&info);
 	info.si_signo = SIGTRAP;
 	info.si_errno = 0;
 	info.si_code = TRAP_HWBKPT;
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index fb070d8cad07..d49063d0baa4 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -154,18 +154,6 @@ static ssize_t ppc_rtas_tone_volume_write(struct file *file,
 static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v);
 static int ppc_rtas_rmo_buf_show(struct seq_file *m, void *v);
 
-static int sensors_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ppc_rtas_sensors_show, NULL);
-}
-
-static const struct file_operations ppc_rtas_sensors_operations = {
-	.open		= sensors_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int poweron_open(struct inode *inode, struct file *file)
 {
 	return single_open(file, ppc_rtas_poweron_show, NULL);
@@ -231,18 +219,6 @@ static const struct file_operations ppc_rtas_tone_volume_operations = {
 	.release	= single_release,
 };
 
-static int rmo_buf_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ppc_rtas_rmo_buf_show, NULL);
-}
-
-static const struct file_operations ppc_rtas_rmo_buf_ops = {
-	.open		= rmo_buf_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int ppc_rtas_find_all_sensors(void);
 static void ppc_rtas_process_sensor(struct seq_file *m,
 	struct individual_sensor *s, int state, int error, const char *loc);
@@ -267,14 +243,14 @@ static int __init proc_rtas_init(void)
 		    &ppc_rtas_clock_operations);
 	proc_create("powerpc/rtas/poweron", 0644, NULL,
 		    &ppc_rtas_poweron_operations);
-	proc_create("powerpc/rtas/sensors", 0444, NULL,
-		    &ppc_rtas_sensors_operations);
+	proc_create_single("powerpc/rtas/sensors", 0444, NULL,
+			ppc_rtas_sensors_show);
 	proc_create("powerpc/rtas/frequency", 0644, NULL,
 		    &ppc_rtas_tone_freq_operations);
 	proc_create("powerpc/rtas/volume", 0644, NULL,
 		    &ppc_rtas_tone_volume_operations);
-	proc_create("powerpc/rtas/rmo_buffer", 0400, NULL,
-		    &ppc_rtas_rmo_buf_ops);
+	proc_create_single("powerpc/rtas/rmo_buffer", 0400, NULL,
+			ppc_rtas_rmo_buf_show);
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index bab5a27ea805..b98a722da915 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -8,6 +8,7 @@
 #include <linux/device.h>
 #include <linux/seq_buf.h>
 
+#include <asm/debugfs.h>
 #include <asm/security_features.h>
 
 
@@ -86,3 +87,151 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
 
 	return s.len;
 }
+
+/*
+ * Store-forwarding barrier support.
+ */
+
+static enum stf_barrier_type stf_enabled_flush_types;
+static bool no_stf_barrier;
+bool stf_barrier;
+
+static int __init handle_no_stf_barrier(char *p)
+{
+	pr_info("stf-barrier: disabled on command line.");
+	no_stf_barrier = true;
+	return 0;
+}
+
+early_param("no_stf_barrier", handle_no_stf_barrier);
+
+/* This is the generic flag used by other architectures */
+static int __init handle_ssbd(char *p)
+{
+	if (!p || strncmp(p, "auto", 5) == 0 || strncmp(p, "on", 2) == 0 ) {
+		/* Until firmware tells us, we have the barrier with auto */
+		return 0;
+	} else if (strncmp(p, "off", 3) == 0) {
+		handle_no_stf_barrier(NULL);
+		return 0;
+	} else
+		return 1;
+
+	return 0;
+}
+early_param("spec_store_bypass_disable", handle_ssbd);
+
+/* This is the generic flag used by other architectures */
+static int __init handle_no_ssbd(char *p)
+{
+	handle_no_stf_barrier(NULL);
+	return 0;
+}
+early_param("nospec_store_bypass_disable", handle_no_ssbd);
+
+static void stf_barrier_enable(bool enable)
+{
+	if (enable)
+		do_stf_barrier_fixups(stf_enabled_flush_types);
+	else
+		do_stf_barrier_fixups(STF_BARRIER_NONE);
+
+	stf_barrier = enable;
+}
+
+void setup_stf_barrier(void)
+{
+	enum stf_barrier_type type;
+	bool enable, hv;
+
+	hv = cpu_has_feature(CPU_FTR_HVMODE);
+
+	/* Default to fallback in case fw-features are not available */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		type = STF_BARRIER_EIEIO;
+	else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		type = STF_BARRIER_SYNC_ORI;
+	else if (cpu_has_feature(CPU_FTR_ARCH_206))
+		type = STF_BARRIER_FALLBACK;
+	else
+		type = STF_BARRIER_NONE;
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		(security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) ||
+		 (security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) && hv));
+
+	if (type == STF_BARRIER_FALLBACK) {
+		pr_info("stf-barrier: fallback barrier available\n");
+	} else if (type == STF_BARRIER_SYNC_ORI) {
+		pr_info("stf-barrier: hwsync barrier available\n");
+	} else if (type == STF_BARRIER_EIEIO) {
+		pr_info("stf-barrier: eieio barrier available\n");
+	}
+
+	stf_enabled_flush_types = type;
+
+	if (!no_stf_barrier)
+		stf_barrier_enable(enable);
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	if (stf_barrier && stf_enabled_flush_types != STF_BARRIER_NONE) {
+		const char *type;
+		switch (stf_enabled_flush_types) {
+		case STF_BARRIER_EIEIO:
+			type = "eieio";
+			break;
+		case STF_BARRIER_SYNC_ORI:
+			type = "hwsync";
+			break;
+		case STF_BARRIER_FALLBACK:
+			type = "fallback";
+			break;
+		default:
+			type = "unknown";
+		}
+		return sprintf(buf, "Mitigation: Kernel entry/exit barrier (%s)\n", type);
+	}
+
+	if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) &&
+	    !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR))
+		return sprintf(buf, "Not affected\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int stf_barrier_set(void *data, u64 val)
+{
+	bool enable;
+
+	if (val == 1)
+		enable = true;
+	else if (val == 0)
+		enable = false;
+	else
+		return -EINVAL;
+
+	/* Only do anything if we're changing state */
+	if (enable != stf_barrier)
+		stf_barrier_enable(enable);
+
+	return 0;
+}
+
+static int stf_barrier_get(void *data, u64 *val)
+{
+	*val = stf_barrier ? 1 : 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set, "%llu\n");
+
+static __init int stf_barrier_debugfs_init(void)
+{
+	debugfs_create_file("stf_barrier", 0600, powerpc_debugfs_root, NULL, &fops_stf_barrier);
+	return 0;
+}
+device_initcall(stf_barrier_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 44c30dd38067..b78f142a4148 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -890,6 +890,17 @@ static void __ref init_fallback_flush(void)
 		return;
 
 	l1d_size = ppc64_caches.l1d.size;
+
+	/*
+	 * If there is no d-cache-size property in the device tree, l1d_size
+	 * could be zero. That leads to the loop in the asm wrapping around to
+	 * 2^64-1, and then walking off the end of the fallback area and
+	 * eventually causing a page fault which is fatal. Just default to
+	 * something vaguely sane.
+	 */
+	if (!l1d_size)
+		l1d_size = (64 * 1024);
+
 	limit = min(ppc64_bolted_size(), ppc64_rma_size);
 
 	/*
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e16ec7b3b427..9ca7148b5881 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -566,10 +566,35 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 #endif
 
 #ifdef CONFIG_NMI_IPI
-static void stop_this_cpu(struct pt_regs *regs)
-#else
+static void nmi_stop_this_cpu(struct pt_regs *regs)
+{
+	/*
+	 * This is a special case because it never returns, so the NMI IPI
+	 * handling would never mark it as done, which makes any later
+	 * smp_send_nmi_ipi() call spin forever. Mark it done now.
+	 *
+	 * IRQs are already hard disabled by the smp_handle_nmi_ipi.
+	 */
+	nmi_ipi_lock();
+	nmi_ipi_busy_count--;
+	nmi_ipi_unlock();
+
+	/* Remove this CPU */
+	set_cpu_online(smp_processor_id(), false);
+
+	spin_begin();
+	while (1)
+		spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
+}
+
+#else /* CONFIG_NMI_IPI */
+
 static void stop_this_cpu(void *dummy)
-#endif
 {
 	/* Remove this CPU */
 	set_cpu_online(smp_processor_id(), false);
@@ -582,12 +607,22 @@ static void stop_this_cpu(void *dummy)
 
 void smp_send_stop(void)
 {
-#ifdef CONFIG_NMI_IPI
-	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000);
-#else
+	static bool stopped = false;
+
+	/*
+	 * Prevent waiting on csd lock from a previous smp_send_stop.
+	 * This is racy, but in general callers try to do the right
+	 * thing and only fire off one smp_send_stop (e.g., see
+	 * kernel/panic.c)
+	 */
+	if (stopped)
+		return;
+
+	stopped = true;
+
 	smp_call_function(stop_this_cpu, NULL, 0);
-#endif
 }
+#endif /* CONFIG_NMI_IPI */
 
 struct thread_info *current_set[NR_CPUS];
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 0904492e7032..0e17dcb48720 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -296,7 +296,6 @@ NOKPROBE_SYMBOL(die);
 void user_single_step_siginfo(struct task_struct *tsk,
 				struct pt_regs *regs, siginfo_t *info)
 {
-	memset(info, 0, sizeof(*info));
 	info->si_signo = SIGTRAP;
 	info->si_code = TRAP_TRACE;
 	info->si_addr = (void __user *)regs->nip;
@@ -334,7 +333,7 @@ void _exception_pkey(int signr, struct pt_regs *regs, int code,
 	 */
 	thread_pkey_regs_save(&current->thread);
 
-	memset(&info, 0, sizeof(info));
+	clear_siginfo(&info);
 	info.si_signo = signr;
 	info.si_code = code;
 	info.si_addr = (void __user *) addr;
@@ -970,7 +969,7 @@ void unknown_exception(struct pt_regs *regs)
 	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
 	       regs->nip, regs->msr, regs->trap);
 
-	_exception(SIGTRAP, regs, TRAP_FIXME, 0);
+	_exception(SIGTRAP, regs, TRAP_UNK, 0);
 
 	exception_exit(prev_state);
 }
@@ -992,7 +991,7 @@ bail:
 
 void RunModeException(struct pt_regs *regs)
 {
-	_exception(SIGTRAP, regs, TRAP_FIXME, 0);
+	_exception(SIGTRAP, regs, TRAP_UNK, 0);
 }
 
 void single_step_exception(struct pt_regs *regs)
@@ -1032,7 +1031,7 @@ static void emulate_single_step(struct pt_regs *regs)
 
 static inline int __parse_fpscr(unsigned long fpscr)
 {
-	int ret = FPE_FIXME;
+	int ret = FPE_FLTUNK;
 
 	/* Invalid operation */
 	if ((fpscr & FPSCR_VE) && (fpscr & FPSCR_VX))
@@ -1973,7 +1972,7 @@ void SPEFloatingPointException(struct pt_regs *regs)
 	extern int do_spe_mathemu(struct pt_regs *regs);
 	unsigned long spefscr;
 	int fpexc_mode;
-	int code = FPE_FIXME;
+	int code = FPE_FLTUNK;
 	int err;
 
 	flush_spe_to_thread(current);
@@ -2042,7 +2041,7 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
 		printk(KERN_ERR "unrecognized spe instruction "
 		       "in %s at %lx\n", current->comm, regs->nip);
 	} else {
-		_exception(SIGFPE, regs, FPE_FIXME, regs->nip);
+		_exception(SIGFPE, regs, FPE_FLTUNK, regs->nip);
 		return;
 	}
 }
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index c8af90ff49f0..dd10e6f1d1b7 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -89,7 +89,7 @@ SECTIONS
 	 */
 	.text BLOCK(0) : AT(ADDR(.text) - LOAD_OFFSET) {
 #ifdef CONFIG_LD_HEAD_STUB_CATCH
-		*(.linker_stub_catch);
+		KEEP(*(.linker_stub_catch));
 		. = . ;
 #endif
 
@@ -98,7 +98,7 @@ SECTIONS
 		ALIGN_FUNCTION();
 #endif
 		/* careful! __ftr_alt_* sections need to be close to .text */
-		*(.text.hot .text .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
+		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
 		SCHED_TEXT
 		CPUIDLE_TEXT
 		LOCK_TEXT
@@ -134,6 +134,20 @@ SECTIONS
 
 #ifdef CONFIG_PPC64
 	. = ALIGN(8);
+	__stf_entry_barrier_fixup : AT(ADDR(__stf_entry_barrier_fixup) - LOAD_OFFSET) {
+		__start___stf_entry_barrier_fixup = .;
+		*(__stf_entry_barrier_fixup)
+		__stop___stf_entry_barrier_fixup = .;
+	}
+
+	. = ALIGN(8);
+	__stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
+		__start___stf_exit_barrier_fixup = .;
+		*(__stf_exit_barrier_fixup)
+		__stop___stf_exit_barrier_fixup = .;
+	}
+
+	. = ALIGN(8);
 	__rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
 		__start___rfi_flush_fixup = .;
 		*(__rfi_flush_fixup)
@@ -170,10 +184,10 @@ SECTIONS
 	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
 		INIT_DATA
 		__vtop_table_begin = .;
-		*(.vtop_fixup);
+		KEEP(*(.vtop_fixup));
 		__vtop_table_end = .;
 		__ptov_table_begin = .;
-		*(.ptov_fixup);
+		KEEP(*(.ptov_fixup));
 		__ptov_table_end = .;
 	}
 
@@ -194,26 +208,26 @@ SECTIONS
 	. = ALIGN(8);
 	__ftr_fixup : AT(ADDR(__ftr_fixup) - LOAD_OFFSET) {
 		__start___ftr_fixup = .;
-		*(__ftr_fixup)
+		KEEP(*(__ftr_fixup))
 		__stop___ftr_fixup = .;
 	}
 	. = ALIGN(8);
 	__mmu_ftr_fixup : AT(ADDR(__mmu_ftr_fixup) - LOAD_OFFSET) {
 		__start___mmu_ftr_fixup = .;
-		*(__mmu_ftr_fixup)
+		KEEP(*(__mmu_ftr_fixup))
 		__stop___mmu_ftr_fixup = .;
 	}
 	. = ALIGN(8);
 	__lwsync_fixup : AT(ADDR(__lwsync_fixup) - LOAD_OFFSET) {
 		__start___lwsync_fixup = .;
-		*(__lwsync_fixup)
+		KEEP(*(__lwsync_fixup))
 		__stop___lwsync_fixup = .;
 	}
 #ifdef CONFIG_PPC64
 	. = ALIGN(8);
 	__fw_ftr_fixup : AT(ADDR(__fw_ftr_fixup) - LOAD_OFFSET) {
 		__start___fw_ftr_fixup = .;
-		*(__fw_ftr_fixup)
+		KEEP(*(__fw_ftr_fixup))
 		__stop___fw_ftr_fixup = .;
 	}
 #endif
@@ -226,7 +240,7 @@ SECTIONS
 	. = ALIGN(8);
 	.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
 		__machine_desc_start = . ;
-		*(.machine.desc)
+		KEEP(*(.machine.desc))
 		__machine_desc_end = . ;
 	}
 #ifdef CONFIG_RELOCATABLE
@@ -274,7 +288,7 @@ SECTIONS
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
 		DATA_DATA
 		*(.data.rel*)
-		*(.sdata)
+		*(SDATA_MAIN)
 		*(.sdata2)
 		*(.got.plt) *(.got)
 		*(.plt)
@@ -289,7 +303,7 @@ SECTIONS
 
 	.opd : AT(ADDR(.opd) - LOAD_OFFSET) {
 		__start_opd = .;
-		*(.opd)
+		KEEP(*(.opd))
 		__end_opd = .;
 	}
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index a57eafec4dc2..361f42c8c73e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -162,7 +162,7 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG))
 		asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
 			     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
-	asm volatile("ptesync": : :"memory");
+	asm volatile("eieio ; tlbsync ; ptesync": : :"memory");
 }
 
 static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned long addr)
@@ -173,7 +173,7 @@ static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned long addr)
 	/* RIC=1 PRS=0 R=1 IS=2 */
 	asm volatile(PPC_TLBIE_5(%0, %1, 1, 0, 1)
 		     : : "r" (rb), "r" (kvm->arch.lpid) : "memory");
-	asm volatile("ptesync": : :"memory");
+	asm volatile("eieio ; tlbsync ; ptesync": : :"memory");
 }
 
 unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
@@ -584,7 +584,7 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep)) {
-		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0,
+		old = kvmppc_radix_update_pte(kvm, ptep, ~0UL, 0,
 					      gpa, shift);
 		kvmppc_radix_tlbie_page(kvm, gpa, shift);
 		if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) {
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 4d07fca5121c..9963f65c212b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2441,6 +2441,7 @@ static void init_vcore_to_run(struct kvmppc_vcore *vc)
 	vc->in_guest = 0;
 	vc->napping_threads = 0;
 	vc->conferring_threads = 0;
+	vc->tb_offset_applied = 0;
 }
 
 static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bd63fa8a08b5..07ca1b2a7966 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -692,6 +692,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 22:	ld	r8,VCORE_TB_OFFSET(r5)
 	cmpdi	r8,0
 	beq	37f
+	std	r8, VCORE_TB_OFFSET_APPL(r5)
 	mftb	r6		/* current host timebase */
 	add	r8,r8,r6
 	mtspr	SPRN_TBU40,r8	/* update upper 40 bits */
@@ -940,18 +941,6 @@ FTR_SECTION_ELSE
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 8:
 
-	/*
-	 * Set the decrementer to the guest decrementer.
-	 */
-	ld	r8,VCPU_DEC_EXPIRES(r4)
-	/* r8 is a host timebase value here, convert to guest TB */
-	ld	r5,HSTATE_KVM_VCORE(r13)
-	ld	r6,VCORE_TB_OFFSET(r5)
-	add	r8,r8,r6
-	mftb	r7
-	subf	r3,r7,r8
-	mtspr	SPRN_DEC,r3
-
 	ld	r5, VCPU_SPRG0(r4)
 	ld	r6, VCPU_SPRG1(r4)
 	ld	r7, VCPU_SPRG2(r4)
@@ -1005,6 +994,18 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPCR,r8
 	isync
 
+	/*
+	 * Set the decrementer to the guest decrementer.
+	 */
+	ld	r8,VCPU_DEC_EXPIRES(r4)
+	/* r8 is a host timebase value here, convert to guest TB */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r6,VCORE_TB_OFFSET_APPL(r5)
+	add	r8,r8,r6
+	mftb	r7
+	subf	r3,r7,r8
+	mtspr	SPRN_DEC,r3
+
 	/* Check if HDEC expires soon */
 	mfspr	r3, SPRN_HDEC
 	EXTEND_HDEC(r3)
@@ -1597,8 +1598,27 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 
 guest_bypass:
 	stw	r12, STACK_SLOT_TRAP(r1)
-	mr 	r3, r12
+
+	/* Save DEC */
+	/* Do this before kvmhv_commence_exit so we know TB is guest TB */
+	ld	r3, HSTATE_KVM_VCORE(r13)
+	mfspr	r5,SPRN_DEC
+	mftb	r6
+	/* On P9, if the guest has large decr enabled, don't sign extend */
+BEGIN_FTR_SECTION
+	ld	r4, VCORE_LPCR(r3)
+	andis.	r4, r4, LPCR_LD@h
+	bne	16f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+	extsw	r5,r5
+16:	add	r5,r5,r6
+	/* r5 is a guest timebase value here, convert to host TB */
+	ld	r4,VCORE_TB_OFFSET_APPL(r3)
+	subf	r5,r4,r5
+	std	r5,VCPU_DEC_EXPIRES(r9)
+
 	/* Increment exit count, poke other threads to exit */
+	mr 	r3, r12
 	bl	kvmhv_commence_exit
 	nop
 	ld	r9, HSTATE_KVM_VCPU(r13)
@@ -1639,23 +1659,6 @@ guest_bypass:
 	mtspr	SPRN_PURR,r3
 	mtspr	SPRN_SPURR,r4
 
-	/* Save DEC */
-	ld	r3, HSTATE_KVM_VCORE(r13)
-	mfspr	r5,SPRN_DEC
-	mftb	r6
-	/* On P9, if the guest has large decr enabled, don't sign extend */
-BEGIN_FTR_SECTION
-	ld	r4, VCORE_LPCR(r3)
-	andis.	r4, r4, LPCR_LD@h
-	bne	16f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	extsw	r5,r5
-16:	add	r5,r5,r6
-	/* r5 is a guest timebase value here, convert to host TB */
-	ld	r4,VCORE_TB_OFFSET(r3)
-	subf	r5,r4,r5
-	std	r5,VCPU_DEC_EXPIRES(r9)
-
 BEGIN_FTR_SECTION
 	b	8f
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
@@ -1905,6 +1908,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	cmpwi	cr2, r0, 0
 	beq	cr2, 4f
 
+	/*
+	 * Radix: do eieio; tlbsync; ptesync sequence in case we
+	 * interrupted the guest between a tlbie and a ptesync.
+	 */
+	eieio
+	tlbsync
+	ptesync
+
 	/* Radix: Handle the case where the guest used an illegal PID */
 	LOAD_REG_ADDR(r4, mmu_base_pid)
 	lwz	r3, VCPU_GUEST_PID(r9)
@@ -2017,9 +2028,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 27:
 	/* Subtract timebase offset from timebase */
-	ld	r8,VCORE_TB_OFFSET(r5)
+	ld	r8, VCORE_TB_OFFSET_APPL(r5)
 	cmpdi	r8,0
 	beq	17f
+	li	r0, 0
+	std	r0, VCORE_TB_OFFSET_APPL(r5)
 	mftb	r6			/* current guest timebase */
 	subf	r8,r8,r6
 	mtspr	SPRN_TBU40,r8		/* update upper 40 bits */
@@ -2700,7 +2713,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	add	r3, r3, r5
 	ld	r4, HSTATE_KVM_VCPU(r13)
 	ld	r5, HSTATE_KVM_VCORE(r13)
-	ld	r6, VCORE_TB_OFFSET(r5)
+	ld	r6, VCORE_TB_OFFSET_APPL(r5)
 	subf	r3, r6, r3	/* convert to host TB value */
 	std	r3, VCPU_DEC_EXPIRES(r4)
 
@@ -2799,7 +2812,7 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/* Restore guest decrementer */
 	ld	r3, VCPU_DEC_EXPIRES(r4)
 	ld	r5, HSTATE_KVM_VCORE(r13)
-	ld	r6, VCORE_TB_OFFSET(r5)
+	ld	r6, VCORE_TB_OFFSET_APPL(r5)
 	add	r3, r3, r6	/* convert host TB to guest TB value */
 	mftb	r7
 	subf	r3, r7, r3
@@ -3606,12 +3619,9 @@ kvmppc_fix_pmao:
  */
 kvmhv_start_timing:
 	ld	r5, HSTATE_KVM_VCORE(r13)
-	lbz	r6, VCORE_IN_GUEST(r5)
-	cmpwi	r6, 0
-	beq	5f				/* if in guest, need to */
-	ld	r6, VCORE_TB_OFFSET(r5)		/* subtract timebase offset */
-5:	mftb	r5
-	subf	r5, r6, r5
+	ld	r6, VCORE_TB_OFFSET_APPL(r5)
+	mftb	r5
+	subf	r5, r6, r5	/* subtract current timebase offset */
 	std	r3, VCPU_CUR_ACTIVITY(r4)
 	std	r5, VCPU_ACTIVITY_START(r4)
 	blr
@@ -3622,15 +3632,12 @@ kvmhv_start_timing:
  */
 kvmhv_accumulate_time:
 	ld	r5, HSTATE_KVM_VCORE(r13)
-	lbz	r8, VCORE_IN_GUEST(r5)
-	cmpwi	r8, 0
-	beq	4f				/* if in guest, need to */
-	ld	r8, VCORE_TB_OFFSET(r5)		/* subtract timebase offset */
-4:	ld	r5, VCPU_CUR_ACTIVITY(r4)
+	ld	r8, VCORE_TB_OFFSET_APPL(r5)
+	ld	r5, VCPU_CUR_ACTIVITY(r4)
 	ld	r6, VCPU_ACTIVITY_START(r4)
 	std	r3, VCPU_CUR_ACTIVITY(r4)
 	mftb	r7
-	subf	r7, r8, r7
+	subf	r7, r8, r7	/* subtract current timebase offset */
 	std	r7, VCPU_ACTIVITY_START(r4)
 	cmpdi	r5, 0
 	beqlr
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index c7a5deadd1cc..99c3620b40d9 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -11,6 +11,9 @@
 #define XGLUE(a,b) a##b
 #define GLUE(a,b) XGLUE(a,b)
 
+/* Dummy interrupt used when taking interrupts out of a queue in H_CPPR */
+#define XICS_DUMMY	1
+
 static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
 {
 	u8 cppr;
@@ -205,6 +208,10 @@ skip_ipi:
 				goto skip_ipi;
 		}
 
+		/* If it's the dummy interrupt, continue searching */
+		if (hirq == XICS_DUMMY)
+			goto skip_ipi;
+
 		/* If fetching, update queue pointers */
 		if (scan_type == scan_fetch) {
 			q->idx = idx;
@@ -385,9 +392,76 @@ static void GLUE(X_PFX,push_pending_to_hw)(struct kvmppc_xive_vcpu *xc)
 	__x_writeb(prio, __x_tima + TM_SPC_SET_OS_PENDING);
 }
 
+static void GLUE(X_PFX,scan_for_rerouted_irqs)(struct kvmppc_xive *xive,
+					       struct kvmppc_xive_vcpu *xc)
+{
+	unsigned int prio;
+
+	/* For each priority that is now masked */
+	for (prio = xc->cppr; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
+		struct xive_q *q = &xc->queues[prio];
+		struct kvmppc_xive_irq_state *state;
+		struct kvmppc_xive_src_block *sb;
+		u32 idx, toggle, entry, irq, hw_num;
+		struct xive_irq_data *xd;
+		__be32 *qpage;
+		u16 src;
+
+		idx = q->idx;
+		toggle = q->toggle;
+		qpage = READ_ONCE(q->qpage);
+		if (!qpage)
+			continue;
+
+		/* For each interrupt in the queue */
+		for (;;) {
+			entry = be32_to_cpup(qpage + idx);
+
+			/* No more ? */
+			if ((entry >> 31) == toggle)
+				break;
+			irq = entry & 0x7fffffff;
+
+			/* Skip dummies and IPIs */
+			if (irq == XICS_DUMMY || irq == XICS_IPI)
+				goto next;
+			sb = kvmppc_xive_find_source(xive, irq, &src);
+			if (!sb)
+				goto next;
+			state = &sb->irq_state[src];
+
+			/* Has it been rerouted ? */
+			if (xc->server_num == state->act_server)
+				goto next;
+
+			/*
+			 * Allright, it *has* been re-routed, kill it from
+			 * the queue.
+			 */
+			qpage[idx] = cpu_to_be32((entry & 0x80000000) | XICS_DUMMY);
+
+			/* Find the HW interrupt */
+			kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+			/* If it's not an LSI, set PQ to 11 the EOI will force a resend */
+			if (!(xd->flags & XIVE_IRQ_FLAG_LSI))
+				GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_11);
+
+			/* EOI the source */
+			GLUE(X_PFX,source_eoi)(hw_num, xd);
+
+		next:
+			idx = (idx + 1) & q->msk;
+			if (idx == 0)
+				toggle ^= 1;
+		}
+	}
+}
+
 X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
 	u8 old_cppr;
 
 	pr_devel("H_CPPR(cppr=%ld)\n", cppr);
@@ -407,14 +481,34 @@ X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
 	 */
 	smp_mb();
 
-	/*
-	 * We are masking less, we need to look for pending things
-	 * to deliver and set VP pending bits accordingly to trigger
-	 * a new interrupt otherwise we might miss MFRR changes for
-	 * which we have optimized out sending an IPI signal.
-	 */
-	if (cppr > old_cppr)
+	if (cppr > old_cppr) {
+		/*
+		 * We are masking less, we need to look for pending things
+		 * to deliver and set VP pending bits accordingly to trigger
+		 * a new interrupt otherwise we might miss MFRR changes for
+		 * which we have optimized out sending an IPI signal.
+		 */
 		GLUE(X_PFX,push_pending_to_hw)(xc);
+	} else {
+		/*
+		 * We are masking more, we need to check the queue for any
+		 * interrupt that has been routed to another CPU, take
+		 * it out (replace it with the dummy) and retrigger it.
+		 *
+		 * This is necessary since those interrupts may otherwise
+		 * never be processed, at least not until this CPU restores
+		 * its CPPR.
+		 *
+		 * This is in theory racy vs. HW adding new interrupts to
+		 * the queue. In practice this works because the interesting
+		 * cases are when the guest has done a set_xive() to move the
+		 * interrupt away, which flushes the xive, followed by the
+		 * target CPU doing a H_CPPR. So any new interrupt coming into
+		 * the queue must still be routed to us and isn't a source
+		 * of concern.
+		 */
+		GLUE(X_PFX,scan_for_rerouted_irqs)(xive, xc);
+	}
 
 	/* Apply new CPPR */
 	xc->hw_cppr = cppr;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6038e2e7aee0..876d4f294fdd 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -305,6 +305,13 @@ void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu)
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL);
 }
 
+#ifdef CONFIG_ALTIVEC
+void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu)
+{
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALTIVEC_UNAVAIL);
+}
+#endif
+
 void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
 {
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DECREMENTER);
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 35f80ab7cbd8..e1bcdc32a851 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -23,6 +23,7 @@
 #include <asm/page.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/security_features.h>
 #include <asm/firmware.h>
 
 struct fixup_entry {
@@ -55,7 +56,7 @@ static int patch_alt_instruction(unsigned int *src, unsigned int *dest,
 		unsigned int *target = (unsigned int *)branch_target(src);
 
 		/* Branch within the section doesn't need translating */
-		if (target < alt_start || target >= alt_end) {
+		if (target < alt_start || target > alt_end) {
 			instr = translate_branch(dest, src);
 			if (!instr)
 				return 1;
@@ -117,6 +118,120 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
+void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___stf_entry_barrier_fixup),
+	end = PTRRELOC(&__stop___stf_entry_barrier_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types & STF_BARRIER_FALLBACK) {
+		instrs[i++] = 0x7d4802a6; /* mflr r10		*/
+		instrs[i++] = 0x60000000; /* branch patched below */
+		instrs[i++] = 0x7d4803a6; /* mtlr r10		*/
+	} else if (types & STF_BARRIER_EIEIO) {
+		instrs[i++] = 0x7e0006ac; /* eieio + bit 6 hint */
+	} else if (types & STF_BARRIER_SYNC_ORI) {
+		instrs[i++] = 0x7c0004ac; /* hwsync		*/
+		instrs[i++] = 0xe94d0000; /* ld r10,0(r13)	*/
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		if (types & STF_BARRIER_FALLBACK)
+			patch_branch(dest + 1, (unsigned long)&stf_barrier_fallback,
+				     BRANCH_SET_LINK);
+		else
+			patch_instruction(dest + 1, instrs[1]);
+
+		patch_instruction(dest + 2, instrs[2]);
+	}
+
+	printk(KERN_DEBUG "stf-barrier: patched %d entry locations (%s barrier)\n", i,
+		(types == STF_BARRIER_NONE)                  ? "no" :
+		(types == STF_BARRIER_FALLBACK)              ? "fallback" :
+		(types == STF_BARRIER_EIEIO)                 ? "eieio" :
+		(types == (STF_BARRIER_SYNC_ORI))            ? "hwsync"
+		                                           : "unknown");
+}
+
+void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
+{
+	unsigned int instrs[6], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___stf_exit_barrier_fixup),
+	end = PTRRELOC(&__stop___stf_exit_barrier_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+	instrs[3] = 0x60000000; /* nop */
+	instrs[4] = 0x60000000; /* nop */
+	instrs[5] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types & STF_BARRIER_FALLBACK || types & STF_BARRIER_SYNC_ORI) {
+		if (cpu_has_feature(CPU_FTR_HVMODE)) {
+			instrs[i++] = 0x7db14ba6; /* mtspr 0x131, r13 (HSPRG1) */
+			instrs[i++] = 0x7db04aa6; /* mfspr r13, 0x130 (HSPRG0) */
+		} else {
+			instrs[i++] = 0x7db243a6; /* mtsprg 2,r13	*/
+			instrs[i++] = 0x7db142a6; /* mfsprg r13,1    */
+	        }
+		instrs[i++] = 0x7c0004ac; /* hwsync		*/
+		instrs[i++] = 0xe9ad0000; /* ld r13,0(r13)	*/
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		if (cpu_has_feature(CPU_FTR_HVMODE)) {
+			instrs[i++] = 0x7db14aa6; /* mfspr r13, 0x131 (HSPRG1) */
+		} else {
+			instrs[i++] = 0x7db242a6; /* mfsprg r13,2 */
+		}
+	} else if (types & STF_BARRIER_EIEIO) {
+		instrs[i++] = 0x7e0006ac; /* eieio + bit 6 hint */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+		patch_instruction(dest + 1, instrs[1]);
+		patch_instruction(dest + 2, instrs[2]);
+		patch_instruction(dest + 3, instrs[3]);
+		patch_instruction(dest + 4, instrs[4]);
+		patch_instruction(dest + 5, instrs[5]);
+	}
+	printk(KERN_DEBUG "stf-barrier: patched %d exit locations (%s barrier)\n", i,
+		(types == STF_BARRIER_NONE)                  ? "no" :
+		(types == STF_BARRIER_FALLBACK)              ? "fallback" :
+		(types == STF_BARRIER_EIEIO)                 ? "eieio" :
+		(types == (STF_BARRIER_SYNC_ORI))            ? "hwsync"
+		                                           : "unknown");
+}
+
+
+void do_stf_barrier_fixups(enum stf_barrier_type types)
+{
+	do_stf_entry_barrier_fixups(types);
+	do_stf_exit_barrier_fixups(types);
+}
+
 void do_rfi_flush_fixups(enum l1d_flush_type types)
 {
 	unsigned int instrs[3], *dest;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index c01d627e687a..ef268d5d9db7 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -168,6 +168,7 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address,
 		return SIGBUS;
 
 	current->thread.trap_nr = BUS_ADRERR;
+	clear_siginfo(&info);
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
 	info.si_code = BUS_ADRERR;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 737f8a4632cc..c3c39b02b2ba 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -133,6 +133,7 @@ int __meminit arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *
 			start, start + size, rc);
 		return -EFAULT;
 	}
+	flush_inval_dcache_range(start, start + size);
 
 	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
 }
@@ -159,6 +160,7 @@ int __meminit arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap
 
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);
+	flush_inval_dcache_range(start, start + size);
 	ret = remove_section_mapping(start, start + size);
 
 	/* Ensure all vmalloc mappings are flushed in case they also
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index ecc66d5f02c9..ad054dd0d666 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -7,6 +7,7 @@
  * 2 of the License, or (at your option) any later version.
 **/
 
+#include <linux/compat_time.h>
 #include <linux/oprofile.h>
 #include <linux/sched.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 67d3125d0610..84b58abc08ee 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -222,6 +222,7 @@ config PTE_64BIT
 config PHYS_64BIT
 	bool 'Large physical address support' if E500 || PPC_86xx
 	depends on (44x || E500 || PPC_86xx) && !PPC_83xx && !PPC_82xx
+	select PHYS_ADDR_T_64BIT
 	---help---
 	  This option enables kernel support for larger than 32-bit physical
 	  addresses.  This feature may not be available on all cores.
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index 870c0a82d560..1e002e94d0f6 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -44,7 +44,7 @@ static void spufs_handle_event(struct spu_context *ctx,
 		return;
 	}
 
-	memset(&info, 0, sizeof(info));
+	clear_siginfo(&info);
 
 	switch (type) {
 	case SPE_EVENT_INVALID_DMA:
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 9033c8194eda..c9ef3c532169 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -1093,20 +1093,8 @@ static int show_spu_loadavg(struct seq_file *s, void *private)
 		LOAD_INT(c), LOAD_FRAC(c),
 		count_active_contexts(),
 		atomic_read(&nr_spu_contexts),
-		idr_get_cursor(&task_active_pid_ns(current)->idr));
+		idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
 	return 0;
-}
-
-static int spu_loadavg_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, show_spu_loadavg, NULL);
-}
-
-static const struct file_operations spu_loadavg_fops = {
-	.open		= spu_loadavg_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
 };
 
 int __init spu_sched_init(void)
@@ -1135,7 +1123,7 @@ int __init spu_sched_init(void)
 
 	mod_timer(&spuloadavg_timer, 0);
 
-	entry = proc_create("spu_loadavg", 0, NULL, &spu_loadavg_fops);
+	entry = proc_create_single("spu_loadavg", 0, NULL, show_spu_loadavg);
 	if (!entry)
 		goto out_stop_kthread;
 
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index de470caf0784..fc222a0c2ac4 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -82,19 +82,6 @@ static const struct file_operations memtrace_fops = {
 	.open	= simple_open,
 };
 
-static void flush_memory_region(u64 base, u64 size)
-{
-	unsigned long line_size = ppc64_caches.l1d.size;
-	u64 end = base + size;
-	u64 addr;
-
-	base = round_down(base, line_size);
-	end = round_up(end, line_size);
-
-	for (addr = base; addr < end; addr += line_size)
-		asm volatile("dcbf 0,%0" : "=r" (addr) :: "memory");
-}
-
 static int check_memblock_online(struct memory_block *mem, void *arg)
 {
 	if (mem->state != MEM_ONLINE)
@@ -132,10 +119,6 @@ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
 	walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
 			  change_memblock_state);
 
-	/* RCU grace period? */
-	flush_memory_region((u64)__va(start_pfn << PAGE_SHIFT),
-			    nr_pages << PAGE_SHIFT);
-
 	lock_device_hotplug();
 	remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
 	unlock_device_hotplug();
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 69a4f9e8bd55..525e966dce34 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -34,6 +34,19 @@
 #define npu_to_phb(x) container_of(x, struct pnv_phb, npu)
 
 /*
+ * spinlock to protect initialisation of an npu_context for a particular
+ * mm_struct.
+ */
+static DEFINE_SPINLOCK(npu_context_lock);
+
+/*
+ * When an address shootdown range exceeds this threshold we invalidate the
+ * entire TLB on the GPU for the given PID rather than each specific address in
+ * the range.
+ */
+#define ATSD_THRESHOLD (2*1024*1024)
+
+/*
  * Other types of TCE cache invalidation are not functional in the
  * hardware.
  */
@@ -401,7 +414,7 @@ struct npu_context {
 	bool nmmu_flush;
 
 	/* Callback to stop translation requests on a given GPU */
-	struct npu_context *(*release_cb)(struct npu_context *, void *);
+	void (*release_cb)(struct npu_context *context, void *priv);
 
 	/*
 	 * Private pointer passed to the above callback for usage by
@@ -671,11 +684,19 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
 	struct npu_context *npu_context = mn_to_npu_context(mn);
 	unsigned long address;
 
-	for (address = start; address < end; address += PAGE_SIZE)
-		mmio_invalidate(npu_context, 1, address, false);
+	if (end - start > ATSD_THRESHOLD) {
+		/*
+		 * Just invalidate the entire PID if the address range is too
+		 * large.
+		 */
+		mmio_invalidate(npu_context, 0, 0, true);
+	} else {
+		for (address = start; address < end; address += PAGE_SIZE)
+			mmio_invalidate(npu_context, 1, address, false);
 
-	/* Do the flush only on the final addess == end */
-	mmio_invalidate(npu_context, 1, address, true);
+		/* Do the flush only on the final addess == end */
+		mmio_invalidate(npu_context, 1, address, true);
+	}
 }
 
 static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
@@ -696,11 +717,12 @@ static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
  * Returns an error if there no contexts are currently available or a
  * npu_context which should be passed to pnv_npu2_handle_fault().
  *
- * mmap_sem must be held in write mode.
+ * mmap_sem must be held in write mode and must not be called from interrupt
+ * context.
  */
 struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 			unsigned long flags,
-			struct npu_context *(*cb)(struct npu_context *, void *),
+			void (*cb)(struct npu_context *, void *),
 			void *priv)
 {
 	int rc;
@@ -743,7 +765,9 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 	/*
 	 * Setup the NPU context table for a particular GPU. These need to be
 	 * per-GPU as we need the tables to filter ATSDs when there are no
-	 * active contexts on a particular GPU.
+	 * active contexts on a particular GPU. It is safe for these to be
+	 * called concurrently with destroy as the OPAL call takes appropriate
+	 * locks and refcounts on init/destroy.
 	 */
 	rc = opal_npu_init_context(nphb->opal_id, mm->context.id, flags,
 				PCI_DEVID(gpdev->bus->number, gpdev->devfn));
@@ -754,8 +778,29 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 	 * We store the npu pci device so we can more easily get at the
 	 * associated npus.
 	 */
+	spin_lock(&npu_context_lock);
 	npu_context = mm->context.npu_context;
+	if (npu_context) {
+		if (npu_context->release_cb != cb ||
+			npu_context->priv != priv) {
+			spin_unlock(&npu_context_lock);
+			opal_npu_destroy_context(nphb->opal_id, mm->context.id,
+						PCI_DEVID(gpdev->bus->number,
+							gpdev->devfn));
+			return ERR_PTR(-EINVAL);
+		}
+
+		WARN_ON(!kref_get_unless_zero(&npu_context->kref));
+	}
+	spin_unlock(&npu_context_lock);
+
 	if (!npu_context) {
+		/*
+		 * We can set up these fields without holding the
+		 * npu_context_lock as the npu_context hasn't been returned to
+		 * the caller meaning it can't be destroyed. Parallel allocation
+		 * is protected against by mmap_sem.
+		 */
 		rc = -ENOMEM;
 		npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL);
 		if (npu_context) {
@@ -774,8 +819,6 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 		}
 
 		mm->context.npu_context = npu_context;
-	} else {
-		WARN_ON(!kref_get_unless_zero(&npu_context->kref));
 	}
 
 	npu_context->release_cb = cb;
@@ -814,15 +857,16 @@ static void pnv_npu2_release_context(struct kref *kref)
 		mm_context_remove_copro(npu_context->mm);
 
 	npu_context->mm->context.npu_context = NULL;
-	mmu_notifier_unregister(&npu_context->mn,
-				npu_context->mm);
-
-	kfree(npu_context);
 }
 
+/*
+ * Destroy a context on the given GPU. May free the npu_context if it is no
+ * longer active on any GPUs. Must not be called from interrupt context.
+ */
 void pnv_npu2_destroy_context(struct npu_context *npu_context,
 			struct pci_dev *gpdev)
 {
+	int removed;
 	struct pnv_phb *nphb;
 	struct npu *npu;
 	struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
@@ -844,7 +888,21 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context,
 	WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL);
 	opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
 				PCI_DEVID(gpdev->bus->number, gpdev->devfn));
-	kref_put(&npu_context->kref, pnv_npu2_release_context);
+	spin_lock(&npu_context_lock);
+	removed = kref_put(&npu_context->kref, pnv_npu2_release_context);
+	spin_unlock(&npu_context_lock);
+
+	/*
+	 * We need to do this outside of pnv_npu2_release_context so that it is
+	 * outside the spinlock as mmu_notifier_destroy uses SRCU.
+	 */
+	if (removed) {
+		mmu_notifier_unregister(&npu_context->mn,
+					npu_context->mm);
+
+		kfree(npu_context);
+	}
+
 }
 EXPORT_SYMBOL(pnv_npu2_destroy_context);
 
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
index 1bceb95f422d..5584247f5029 100644
--- a/arch/powerpc/platforms/powernv/opal-nvram.c
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -44,6 +44,10 @@ static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index)
 	return count;
 }
 
+/*
+ * This can be called in the panic path with interrupts off, so use
+ * mdelay in that case.
+ */
 static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
 {
 	s64 rc = OPAL_BUSY;
@@ -58,10 +62,16 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_write_nvram(__pa(buf), count, off);
 		if (rc == OPAL_BUSY_EVENT) {
-			msleep(OPAL_BUSY_DELAY_MS);
+			if (in_interrupt() || irqs_disabled())
+				mdelay(OPAL_BUSY_DELAY_MS);
+			else
+				msleep(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
 		} else if (rc == OPAL_BUSY) {
-			msleep(OPAL_BUSY_DELAY_MS);
+			if (in_interrupt() || irqs_disabled())
+				mdelay(OPAL_BUSY_DELAY_MS);
+			else
+				msleep(OPAL_BUSY_DELAY_MS);
 		}
 	}
 
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index f8868864f373..aa2a5139462e 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -48,10 +48,12 @@ unsigned long __init opal_get_boot_time(void)
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
+		if (rc == OPAL_BUSY_EVENT) {
+			mdelay(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
-		else if (rc == OPAL_BUSY)
-			mdelay(10);
+		} else if (rc == OPAL_BUSY) {
+			mdelay(OPAL_BUSY_DELAY_MS);
+		}
 	}
 	if (rc != OPAL_SUCCESS)
 		return 0;
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index ef8c9ce53a61..a6648ec99ca7 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -131,6 +131,7 @@ static void __init pnv_setup_arch(void)
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
 
 	pnv_setup_rfi_flush();
+	setup_stf_barrier();
 
 	/* Initialize SMP */
 	pnv_smp_init();
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index b55ad4286dc7..fdb32e056ef4 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -710,6 +710,7 @@ static void __init pSeries_setup_arch(void)
 	fwnmi_init();
 
 	pseries_setup_rfi_flush();
+	setup_stf_barrier();
 
 	/* By default, only probe PCI (can be overridden by rtas_pci) */
 	pci_add_flags(PCI_PROBE_ONLY);
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index d22aeb0b69e1..b48454be5b98 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -389,6 +389,10 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
 	if (xive_pool_vps == XIVE_INVALID_VP)
 		return;
 
+	/* Check if pool VP already active, if it is, pull it */
+	if (in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2) & TM_QW2W2_VP)
+		in_be64(xive_tima + TM_SPC_PULL_POOL_CTX);
+
 	/* Enable the pool VP */
 	vp = xive_pool_vps + cpu;
 	pr_debug("CPU %d setting up pool VP 0x%x\n", cpu, vp);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 23d8acca5c90..274bc064c41f 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -3,14 +3,23 @@
 # see Documentation/kbuild/kconfig-language.txt.
 #
 
+config 64BIT
+	bool
+
+config 32BIT
+	bool
+
 config RISCV
 	def_bool y
+	# even on 32-bit, physical (and DMA) addresses are > 32-bits
+	select PHYS_ADDR_T_64BIT
 	select OF
 	select OF_EARLY_FLATTREE
 	select OF_IRQ
 	select ARCH_WANT_FRAME_POINTERS
 	select CLONE_BACKWARDS
 	select COMMON_CLK
+	select DMA_DIRECT_OPS
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_DEVICES
 	select GENERIC_IRQ_SHOW
@@ -21,7 +30,6 @@ config RISCV
 	select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_GENERIC_DMA_COHERENT
 	select IRQ_DOMAIN
@@ -38,16 +46,9 @@ config RISCV
 config MMU
 	def_bool y
 
-# even on 32-bit, physical (and DMA) addresses are > 32-bits
-config ARCH_PHYS_ADDR_T_64BIT
-	def_bool y
-
 config ZONE_DMA32
 	bool
-	default y
-
-config ARCH_DMA_ADDR_T_64BIT
-	def_bool y
+	default y if 64BIT
 
 config PAGE_OFFSET
 	hex
@@ -89,9 +90,6 @@ config PGTABLE_LEVELS
 config HAVE_KPROBES
 	def_bool n
 
-config DMA_DIRECT_OPS
-	def_bool y
-
 menu "Platform type"
 
 choice
@@ -103,7 +101,6 @@ choice
 
 config ARCH_RV32I
 	bool "RV32I"
-	select CPU_SUPPORTS_32BIT_KERNEL
 	select 32BIT
 	select GENERIC_ASHLDI3
 	select GENERIC_ASHRDI3
@@ -111,13 +108,13 @@ config ARCH_RV32I
 
 config ARCH_RV64I
 	bool "RV64I"
-	select CPU_SUPPORTS_64BIT_KERNEL
 	select 64BIT
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select SWIOTLB
 
 endchoice
 
@@ -173,11 +170,6 @@ config NR_CPUS
 	depends on SMP
 	default "8"
 
-config CPU_SUPPORTS_32BIT_KERNEL
-	bool
-config CPU_SUPPORTS_64BIT_KERNEL
-	bool
-
 choice
 	prompt "CPU Tuning"
 	default TUNE_GENERIC
@@ -204,24 +196,6 @@ endmenu
 
 menu "Kernel type"
 
-choice
-	prompt "Kernel code model"
-	default 64BIT
-
-config 32BIT
-	bool "32-bit kernel"
-	depends on CPU_SUPPORTS_32BIT_KERNEL
-	help
-	  Select this option to build a 32-bit kernel.
-
-config 64BIT
-	bool "64-bit kernel"
-	depends on CPU_SUPPORTS_64BIT_KERNEL
-	help
-	  Select this option to build a 64-bit kernel.
-
-endchoice
-
 source "mm/Kconfig"
 
 source "kernel/Kconfig.preempt"
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 1e5fd280fb4d..4286a5f83876 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -15,7 +15,6 @@ generic-y += fcntl.h
 generic-y += futex.h
 generic-y += hardirq.h
 generic-y += hash.h
-generic-y += handle_irq.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h
new file mode 100644
index 000000000000..8facc1c8fa05
--- /dev/null
+++ b/arch/riscv/include/asm/dma-mapping.h
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _RISCV_ASM_DMA_MAPPING_H
+#define _RISCV_ASM_DMA_MAPPING_H 1
+
+#ifdef CONFIG_SWIOTLB
+#include <linux/swiotlb.h>
+static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
+{
+	return &swiotlb_dma_ops;
+}
+#else
+#include <asm-generic/dma-mapping.h>
+#endif /* CONFIG_SWIOTLB */
+
+#endif /* _RISCV_ASM_DMA_MAPPING_H */
diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h
index 0f2fc9ef20fc..b3638c505728 100644
--- a/arch/riscv/include/asm/pci.h
+++ b/arch/riscv/include/asm/pci.h
@@ -26,9 +26,6 @@
 /* RISC-V shim does not initialize PCI bus */
 #define pcibios_assign_all_busses() 1
 
-/* We do not have an IOMMU */
-#define PCI_DMA_BUS_IS_PHYS 1
-
 extern int isa_dma_bridge_buggy;
 
 #ifdef CONFIG_PCI
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index c11f40c1b2a8..ee44a48faf79 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -29,6 +29,7 @@
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/sched/task.h>
+#include <linux/swiotlb.h>
 
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -206,6 +207,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_bootmem();
 	paging_init();
 	unflatten_device_tree();
+	swiotlb_init(1);
 
 #ifdef CONFIG_SMP
 	setup_smp();
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 93132cb59184..b99d9dd21fd0 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -63,18 +63,6 @@ void die(struct pt_regs *regs, const char *str)
 		do_exit(SIGSEGV);
 }
 
-static inline void do_trap_siginfo(int signo, int code,
-	unsigned long addr, struct task_struct *tsk)
-{
-	siginfo_t info;
-
-	info.si_signo = signo;
-	info.si_errno = 0;
-	info.si_code = code;
-	info.si_addr = (void __user *)addr;
-	force_sig_info(signo, &info, tsk);
-}
-
 void do_trap(struct pt_regs *regs, int signo, int code,
 	unsigned long addr, struct task_struct *tsk)
 {
@@ -87,7 +75,7 @@ void do_trap(struct pt_regs *regs, int signo, int code,
 		show_regs(regs);
 	}
 
-	do_trap_siginfo(signo, code, addr, tsk);
+	force_sig_fault(signo, code, (void __user *)addr, tsk);
 }
 
 static void do_trap_error(struct pt_regs *regs, int signo, int code,
@@ -149,7 +137,7 @@ asmlinkage void do_trap_break(struct pt_regs *regs)
 	}
 #endif /* CONFIG_GENERIC_BUG */
 
-	do_trap_siginfo(SIGTRAP, TRAP_BRKPT, regs->sepc, current);
+	force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)(regs->sepc), current);
 	regs->sepc += 0x4;
 }
 
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 324568d33921..f6561b783b61 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -52,7 +52,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 # Add -lgcc so rv32 gets static muldi3 and lshrdi3 definitions.
 # Make sure only to export the intended __vdso_xxx symbol offsets.
 quiet_cmd_vdsold = VDSOLD  $@
-      cmd_vdsold = $(CC) $(KCFLAGS) -nostdlib $(SYSCFLAGS_$(@F)) \
+      cmd_vdsold = $(CC) $(KCFLAGS) $(call cc-option, -no-pie) -nostdlib $(SYSCFLAGS_$(@F)) \
                            -Wl,-T,$(filter-out FORCE,$^) -o $@.tmp -lgcc && \
                    $(CROSS_COMPILE)objcopy \
                            $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@
diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index 9fdff3fe1a42..e63940bb57cd 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -8,3 +8,4 @@ obj-$(CONFIG_APPLDATA_BASE)	+= appldata/
 obj-y				+= net/
 obj-$(CONFIG_PCI)		+= pci/
 obj-$(CONFIG_NUMA)		+= numa/
+obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 32a0d5b958bf..b7deee7e738f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -35,9 +35,6 @@ config GENERIC_BUG
 config GENERIC_BUG_RELATIVE_POINTERS
 	def_bool y
 
-config ARCH_DMA_ADDR_T_64BIT
-	def_bool y
-
 config GENERIC_LOCKBREAK
 	def_bool y if SMP && PREEMPT
 
@@ -47,10 +44,6 @@ config PGSTE
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
-config KEXEC
-	def_bool y
-	select KEXEC_CORE
-
 config AUDIT_ARCH
 	def_bool y
 
@@ -137,7 +130,6 @@ config S390
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select DMA_DIRECT_OPS
 	select HAVE_DYNAMIC_FTRACE
@@ -290,12 +282,12 @@ config MARCH_Z13
 	  older machines.
 
 config MARCH_Z14
-	bool "IBM z14"
+	bool "IBM z14 ZR1 and z14"
 	select HAVE_MARCH_Z14_FEATURES
 	help
-	  Select this to enable optimizations for IBM z14 (3906 series).
-	  The kernel will be slightly faster but will not work on older
-	  machines.
+	  Select this to enable optimizations for IBM z14 ZR1 and z14 (3907
+	  and 3906 series). The kernel will be slightly faster but will not
+	  work on older machines.
 
 endchoice
 
@@ -525,6 +517,26 @@ source kernel/Kconfig.preempt
 
 source kernel/Kconfig.hz
 
+config KEXEC
+	def_bool y
+	select KEXEC_CORE
+
+config KEXEC_FILE
+	bool "kexec file based system call"
+	select KEXEC_CORE
+	select BUILD_BIN2C
+	depends on CRYPTO
+	depends on CRYPTO_SHA256
+	depends on CRYPTO_SHA256_S390
+	help
+	  Enable the kexec file based system call. In contrast to the normal
+	  kexec system call this system call takes file descriptors for the
+	  kernel and initramfs as arguments.
+
+config ARCH_HAS_KEXEC_PURGATORY
+	def_bool y
+	depends on KEXEC_FILE
+
 config ARCH_RANDOM
 	def_bool y
 	prompt "s390 architectural random number generation API"
@@ -693,7 +705,11 @@ config QDIO
 menuconfig PCI
 	bool "PCI support"
 	select PCI_MSI
+	select IOMMU_HELPER
 	select IOMMU_SUPPORT
+	select NEED_DMA_MAP_STATE
+	select NEED_SG_DMA_LENGTH
+
 	help
 	  Enable PCI support.
 
@@ -717,15 +733,6 @@ config PCI_DOMAINS
 config HAS_IOMEM
 	def_bool PCI
 
-config IOMMU_HELPER
-	def_bool PCI
-
-config NEED_SG_DMA_LENGTH
-	def_bool PCI
-
-config NEED_DMA_MAP_STATE
-	def_bool PCI
-
 config CHSC_SCH
 	def_tristate m
 	prompt "Support for CHSC subchannels"
@@ -831,6 +838,10 @@ config CCW
 
 source "drivers/Kconfig"
 
+config HAVE_PNETID
+	tristate
+	default (SMC || CCWGROUP)
+
 source "fs/Kconfig"
 
 source "arch/s390/Kconfig.debug"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index c79936d02f7b..68a690442be0 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -18,7 +18,7 @@ KBUILD_CFLAGS	+= -m64
 KBUILD_AFLAGS	+= -m64
 UTS_MACHINE	:= s390x
 STACK_SIZE	:= 16384
-CHECKFLAGS	+= -D__s390__ -D__s390x__ -mbig-endian
+CHECKFLAGS	+= -D__s390__ -D__s390x__
 
 export LD_BFD
 
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index da9dad35c28e..d1fa37fcce83 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -3,12 +3,6 @@
 # Makefile for the linux s390-specific parts of the memory manager.
 #
 
-COMPILE_VERSION := __linux_compile_version_id__`hostname |  \
-			tr -c '[0-9A-Za-z]' '_'`__`date | \
-			tr -c '[0-9A-Za-z]' '_'`_t
-
-ccflags-y  := -DCOMPILE_VERSION=$(COMPILE_VERSION) -gstabs -I.
-
 targets := image
 targets += bzImage
 subdir- := compressed
diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore
index ae06b9b4c02f..2088cc140629 100644
--- a/arch/s390/boot/compressed/.gitignore
+++ b/arch/s390/boot/compressed/.gitignore
@@ -1,3 +1,4 @@
 sizes.h
 vmlinux
 vmlinux.lds
+vmlinux.bin.full
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/debug_defconfig
index 5af8458951cf..941d8cc6c9f5 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -24,13 +24,13 @@ CONFIG_CPUSETS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_PERF=y
-CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
+CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
@@ -59,10 +59,11 @@ CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_LIVEPATCH=y
 CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=256
+CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -260,9 +261,9 @@ CONFIG_IP_VS_NQ=m
 CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
+CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
@@ -283,7 +284,7 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
+CONFIG_NF_TABLES_IPV6=y
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -304,8 +305,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_SECURITY=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=m
-CONFIG_NET_SCTPPROBE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
 CONFIG_RDS_TCP=m
@@ -364,11 +364,11 @@ CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
 CONFIG_DNS_RESOLVER=y
+CONFIG_OPENVSWITCH=m
 CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
-CONFIG_NET_TCPPROBE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
@@ -380,9 +380,9 @@ CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_BLK_DEV_RAM_DAX=y
 CONFIG_VIRTIO_BLK=y
 CONFIG_BLK_DEV_RBD=m
+CONFIG_BLK_DEV_NVME=m
 CONFIG_ENCLOSURE_SERVICES=m
 CONFIG_GENWQE=m
 CONFIG_RAID_ATTRS=m
@@ -461,6 +461,7 @@ CONFIG_PPTP=m
 CONFIG_PPPOL2TP=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
+CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
@@ -474,6 +475,9 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
+CONFIG_DRM=y
+CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
@@ -482,7 +486,9 @@ CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
+CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
+CONFIG_VIRTIO_INPUT=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -598,7 +604,6 @@ CONFIG_DETECT_HUNG_TASK=y
 CONFIG_WQ_WATCHDOG=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_DEBUG_TIMEKEEPING=y
-CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
@@ -641,6 +646,8 @@ CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_TEST_BPF=m
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_S390_PTDUMP=y
+CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
@@ -649,17 +656,20 @@ CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
 CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_INTEGRITY_SIGNATURE=y
+CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
 CONFIG_IMA=y
+CONFIG_IMA_DEFAULT_HASH_SHA256=y
+CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
-CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_USER=m
+# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
 CONFIG_CRYPTO_PCRYPT=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_GCM=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -707,9 +717,8 @@ CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_ASYMMETRIC_KEY_TYPE=y
-CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_X509_CERTIFICATE_PARSER=m
+CONFIG_PKCS7_MESSAGE_PARSER=y
+CONFIG_SYSTEM_TRUSTED_KEYRING=y
 CONFIG_CRC7=m
 CONFIG_CRC8=m
 CONFIG_RANDOM32_SELFTEST=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
deleted file mode 100644
index d52eafe57ae8..000000000000
--- a/arch/s390/configs/gcov_defconfig
+++ /dev/null
@@ -1,661 +0,0 @@
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_AUDIT=y
-CONFIG_NO_HZ_IDLE=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_XACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_NUMA_BALANCING=y
-# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set
-CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
-CONFIG_BLK_CGROUP=y
-CONFIG_CFS_BANDWIDTH=y
-CONFIG_RT_GROUP_SCHED=y
-CONFIG_CGROUP_PIDS=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_HUGETLB=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_CGROUP_PERF=y
-CONFIG_CHECKPOINT_RESTORE=y
-CONFIG_NAMESPACES=y
-CONFIG_USER_NS=y
-CONFIG_SCHED_AUTOGROUP=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_BPF_SYSCALL=y
-CONFIG_USERFAULTFD=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_KPROBES=y
-CONFIG_JUMP_LABEL=y
-CONFIG_GCOV_KERNEL=y
-CONFIG_GCOV_PROFILE_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_FORCE_LOAD=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_BLK_DEV_INTEGRITY=y
-CONFIG_BLK_DEV_THROTTLING=y
-CONFIG_BLK_WBT=y
-CONFIG_BLK_WBT_SQ=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_CFQ_GROUP_IOSCHED=y
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=512
-CONFIG_NUMA=y
-CONFIG_HZ_100=y
-CONFIG_MEMORY_HOTPLUG=y
-CONFIG_MEMORY_HOTREMOVE=y
-CONFIG_KSM=y
-CONFIG_TRANSPARENT_HUGEPAGE=y
-CONFIG_CLEANCACHE=y
-CONFIG_FRONTSWAP=y
-CONFIG_MEM_SOFT_DIRTY=y
-CONFIG_ZSWAP=y
-CONFIG_ZBUD=m
-CONFIG_ZSMALLOC=m
-CONFIG_ZSMALLOC_STAT=y
-CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
-CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_PCI=y
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_S390=y
-CONFIG_CHSC_SCH=y
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_PACKET_DIAG=m
-CONFIG_UNIX=y
-CONFIG_UNIX_DIAG=m
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_SMC=m
-CONFIG_SMC_DIAG=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_NET_IPIP=m
-CONFIG_NET_IPGRE_DEMUX=m
-CONFIG_NET_IPGRE=m
-CONFIG_NET_IPGRE_BROADCAST=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
-CONFIG_NET_IPVTI=m
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
-CONFIG_INET_DIAG=m
-CONFIG_INET_UDP_DIAG=m
-CONFIG_TCP_CONG_ADVANCED=y
-CONFIG_TCP_CONG_HSTCP=m
-CONFIG_TCP_CONG_HYBLA=m
-CONFIG_TCP_CONG_SCALABLE=m
-CONFIG_TCP_CONG_LP=m
-CONFIG_TCP_CONG_VENO=m
-CONFIG_TCP_CONG_YEAH=m
-CONFIG_TCP_CONG_ILLINOIS=m
-CONFIG_IPV6_ROUTER_PREF=y
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
-CONFIG_IPV6_VTI=m
-CONFIG_IPV6_SIT=m
-CONFIG_IPV6_GRE=m
-CONFIG_IPV6_MULTIPLE_TABLES=y
-CONFIG_IPV6_SUBTREES=y
-CONFIG_NETFILTER=y
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_SECMARK=y
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CONNTRACK_TIMEOUT=y
-CONFIG_NF_CONNTRACK_TIMESTAMP=y
-CONFIG_NF_CONNTRACK_AMANDA=m
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_H323=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_NETBIOS_NS=m
-CONFIG_NF_CONNTRACK_SNMP=m
-CONFIG_NF_CONNTRACK_PPTP=m
-CONFIG_NF_CONNTRACK_SANE=m
-CONFIG_NF_CONNTRACK_SIP=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NF_CT_NETLINK=m
-CONFIG_NF_CT_NETLINK_TIMEOUT=m
-CONFIG_NF_TABLES=m
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_CT=m
-CONFIG_NFT_COUNTER=m
-CONFIG_NFT_LOG=m
-CONFIG_NFT_LIMIT=m
-CONFIG_NFT_NAT=m
-CONFIG_NFT_COMPAT=m
-CONFIG_NFT_HASH=m
-CONFIG_NETFILTER_XT_SET=m
-CONFIG_NETFILTER_XT_TARGET_AUDIT=m
-CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
-CONFIG_NETFILTER_XT_TARGET_CT=m
-CONFIG_NETFILTER_XT_TARGET_DSCP=m
-CONFIG_NETFILTER_XT_TARGET_HMARK=m
-CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
-CONFIG_NETFILTER_XT_TARGET_LOG=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFLOG=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TEE=m
-CONFIG_NETFILTER_XT_TARGET_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_TRACE=m
-CONFIG_NETFILTER_XT_TARGET_SECMARK=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
-CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
-CONFIG_NETFILTER_XT_MATCH_BPF=m
-CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
-CONFIG_NETFILTER_XT_MATCH_CONNLABEL=m
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_CPU=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
-CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_ESP=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_IPVS=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_NFACCT=m
-CONFIG_NETFILTER_XT_MATCH_OSF=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
-CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_QUOTA=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_TIME=m
-CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_IP_SET=m
-CONFIG_IP_SET_BITMAP_IP=m
-CONFIG_IP_SET_BITMAP_IPMAC=m
-CONFIG_IP_SET_BITMAP_PORT=m
-CONFIG_IP_SET_HASH_IP=m
-CONFIG_IP_SET_HASH_IPPORT=m
-CONFIG_IP_SET_HASH_IPPORTIP=m
-CONFIG_IP_SET_HASH_IPPORTNET=m
-CONFIG_IP_SET_HASH_NETPORTNET=m
-CONFIG_IP_SET_HASH_NET=m
-CONFIG_IP_SET_HASH_NETNET=m
-CONFIG_IP_SET_HASH_NETPORT=m
-CONFIG_IP_SET_HASH_NETIFACE=m
-CONFIG_IP_SET_LIST_SET=m
-CONFIG_IP_VS=m
-CONFIG_IP_VS_PROTO_TCP=y
-CONFIG_IP_VS_PROTO_UDP=y
-CONFIG_IP_VS_PROTO_ESP=y
-CONFIG_IP_VS_PROTO_AH=y
-CONFIG_IP_VS_RR=m
-CONFIG_IP_VS_WRR=m
-CONFIG_IP_VS_LC=m
-CONFIG_IP_VS_WLC=m
-CONFIG_IP_VS_LBLC=m
-CONFIG_IP_VS_LBLCR=m
-CONFIG_IP_VS_DH=m
-CONFIG_IP_VS_SH=m
-CONFIG_IP_VS_SED=m
-CONFIG_IP_VS_NQ=m
-CONFIG_IP_VS_FTP=m
-CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_CHAIN_ROUTE_IPV4=m
-CONFIG_NF_TABLES_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_AH=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_RPFILTER=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_NAT=m
-CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
-CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
-CONFIG_IP_NF_ARPFILTER=m
-CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
-CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_IP6_NF_IPTABLES=m
-CONFIG_IP6_NF_MATCH_AH=m
-CONFIG_IP6_NF_MATCH_EUI64=m
-CONFIG_IP6_NF_MATCH_FRAG=m
-CONFIG_IP6_NF_MATCH_OPTS=m
-CONFIG_IP6_NF_MATCH_HL=m
-CONFIG_IP6_NF_MATCH_IPV6HEADER=m
-CONFIG_IP6_NF_MATCH_MH=m
-CONFIG_IP6_NF_MATCH_RPFILTER=m
-CONFIG_IP6_NF_MATCH_RT=m
-CONFIG_IP6_NF_TARGET_HL=m
-CONFIG_IP6_NF_FILTER=m
-CONFIG_IP6_NF_TARGET_REJECT=m
-CONFIG_IP6_NF_MANGLE=m
-CONFIG_IP6_NF_RAW=m
-CONFIG_IP6_NF_SECURITY=m
-CONFIG_IP6_NF_NAT=m
-CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=m
-CONFIG_NET_SCTPPROBE=m
-CONFIG_RDS=m
-CONFIG_RDS_RDMA=m
-CONFIG_RDS_TCP=m
-CONFIG_L2TP=m
-CONFIG_L2TP_DEBUGFS=m
-CONFIG_L2TP_V3=y
-CONFIG_L2TP_IP=m
-CONFIG_L2TP_ETH=m
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_VLAN_8021Q_GVRP=y
-CONFIG_NET_SCHED=y
-CONFIG_NET_SCH_CBQ=m
-CONFIG_NET_SCH_HTB=m
-CONFIG_NET_SCH_HFSC=m
-CONFIG_NET_SCH_PRIO=m
-CONFIG_NET_SCH_MULTIQ=m
-CONFIG_NET_SCH_RED=m
-CONFIG_NET_SCH_SFB=m
-CONFIG_NET_SCH_SFQ=m
-CONFIG_NET_SCH_TEQL=m
-CONFIG_NET_SCH_TBF=m
-CONFIG_NET_SCH_GRED=m
-CONFIG_NET_SCH_DSMARK=m
-CONFIG_NET_SCH_NETEM=m
-CONFIG_NET_SCH_DRR=m
-CONFIG_NET_SCH_MQPRIO=m
-CONFIG_NET_SCH_CHOKE=m
-CONFIG_NET_SCH_QFQ=m
-CONFIG_NET_SCH_CODEL=m
-CONFIG_NET_SCH_FQ_CODEL=m
-CONFIG_NET_SCH_INGRESS=m
-CONFIG_NET_SCH_PLUG=m
-CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
-CONFIG_NET_CLS_ROUTE4=m
-CONFIG_NET_CLS_FW=m
-CONFIG_NET_CLS_U32=m
-CONFIG_CLS_U32_PERF=y
-CONFIG_CLS_U32_MARK=y
-CONFIG_NET_CLS_RSVP=m
-CONFIG_NET_CLS_RSVP6=m
-CONFIG_NET_CLS_FLOW=m
-CONFIG_NET_CLS_CGROUP=y
-CONFIG_NET_CLS_BPF=m
-CONFIG_NET_CLS_ACT=y
-CONFIG_NET_ACT_POLICE=m
-CONFIG_NET_ACT_GACT=m
-CONFIG_GACT_PROB=y
-CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
-CONFIG_NET_ACT_NAT=m
-CONFIG_NET_ACT_PEDIT=m
-CONFIG_NET_ACT_SIMP=m
-CONFIG_NET_ACT_SKBEDIT=m
-CONFIG_NET_ACT_CSUM=m
-CONFIG_DNS_RESOLVER=y
-CONFIG_NETLINK_DIAG=m
-CONFIG_CGROUP_NET_PRIO=y
-CONFIG_BPF_JIT=y
-CONFIG_NET_PKTGEN=m
-CONFIG_NET_TCPPROBE=m
-CONFIG_DEVTMPFS=y
-CONFIG_DMA_CMA=y
-CONFIG_CMA_SIZE_MBYTES=0
-CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_BLK_DEV_DRBD=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_BLK_DEV_RAM_DAX=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_ENCLOSURE_SERVICES=m
-CONFIG_GENWQE=m
-CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
-CONFIG_BLK_DEV_SR=m
-CONFIG_CHR_DEV_SG=y
-CONFIG_CHR_DEV_SCH=m
-CONFIG_SCSI_ENCLOSURE=m
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_SCSI_SPI_ATTRS=m
-CONFIG_SCSI_FC_ATTRS=y
-CONFIG_SCSI_SAS_LIBSAS=m
-CONFIG_SCSI_SRP_ATTRS=m
-CONFIG_ISCSI_TCP=m
-CONFIG_SCSI_DEBUG=m
-CONFIG_ZFCP=y
-CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=y
-CONFIG_SCSI_DH_RDAC=m
-CONFIG_SCSI_DH_HP_SW=m
-CONFIG_SCSI_DH_EMC=m
-CONFIG_SCSI_DH_ALUA=m
-CONFIG_SCSI_OSD_INITIATOR=m
-CONFIG_SCSI_OSD_ULD=m
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
-CONFIG_BLK_DEV_DM=m
-CONFIG_DM_CRYPT=m
-CONFIG_DM_SNAPSHOT=m
-CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_MIRROR=m
-CONFIG_DM_LOG_USERSPACE=m
-CONFIG_DM_RAID=m
-CONFIG_DM_ZERO=m
-CONFIG_DM_MULTIPATH=m
-CONFIG_DM_MULTIPATH_QL=m
-CONFIG_DM_MULTIPATH_ST=m
-CONFIG_DM_DELAY=m
-CONFIG_DM_UEVENT=y
-CONFIG_DM_FLAKEY=m
-CONFIG_DM_VERITY=m
-CONFIG_DM_SWITCH=m
-CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_EQUALIZER=m
-CONFIG_IFB=m
-CONFIG_MACVLAN=m
-CONFIG_MACVTAP=m
-CONFIG_VXLAN=m
-CONFIG_TUN=m
-CONFIG_VETH=m
-CONFIG_VIRTIO_NET=m
-CONFIG_NLMON=m
-# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_VENDOR_CHELSIO is not set
-# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MARVELL is not set
-CONFIG_MLX4_EN=m
-CONFIG_MLX5_CORE=m
-CONFIG_MLX5_CORE_EN=y
-# CONFIG_NET_VENDOR_NATSEMI is not set
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPTP=m
-CONFIG_PPPOL2TP=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-CONFIG_LEGACY_PTY_COUNT=0
-CONFIG_HW_RANDOM_VIRTIO=m
-CONFIG_RAW_DRIVER=m
-CONFIG_HANGCHECK_TIMER=m
-CONFIG_TN3270_FS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_WATCHDOG_NOWAYOUT=y
-CONFIG_SOFT_WATCHDOG=m
-CONFIG_DIAG288_WATCHDOG=m
-# CONFIG_HID is not set
-# CONFIG_USB_SUPPORT is not set
-CONFIG_INFINIBAND=m
-CONFIG_INFINIBAND_USER_ACCESS=m
-CONFIG_MLX4_INFINIBAND=m
-CONFIG_MLX5_INFINIBAND=m
-CONFIG_VFIO=m
-CONFIG_VFIO_PCI=m
-CONFIG_VIRTIO_BALLOON=m
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_EXT4_FS_SECURITY=y
-CONFIG_EXT4_ENCRYPTION=y
-CONFIG_JBD2_DEBUG=y
-CONFIG_JFS_FS=m
-CONFIG_JFS_POSIX_ACL=y
-CONFIG_JFS_SECURITY=y
-CONFIG_JFS_STATISTICS=y
-CONFIG_XFS_FS=y
-CONFIG_XFS_QUOTA=y
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_XFS_RT=y
-CONFIG_GFS2_FS=m
-CONFIG_GFS2_FS_LOCKING_DLM=y
-CONFIG_OCFS2_FS=m
-CONFIG_BTRFS_FS=y
-CONFIG_BTRFS_FS_POSIX_ACL=y
-CONFIG_NILFS2_FS=m
-CONFIG_FS_DAX=y
-CONFIG_EXPORTFS_BLOCK_OPS=y
-CONFIG_FANOTIFY=y
-CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
-CONFIG_QUOTA_NETLINK_INTERFACE=y
-CONFIG_QFMT_V1=m
-CONFIG_QFMT_V2=m
-CONFIG_AUTOFS4_FS=m
-CONFIG_FUSE_FS=y
-CONFIG_CUSE=m
-CONFIG_OVERLAY_FS=m
-CONFIG_OVERLAY_FS_REDIRECT_DIR=y
-CONFIG_FSCACHE=m
-CONFIG_CACHEFILES=m
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_HUGETLBFS=y
-CONFIG_CONFIGFS_FS=m
-CONFIG_ECRYPT_FS=m
-CONFIG_CRAMFS=m
-CONFIG_SQUASHFS=m
-CONFIG_SQUASHFS_XATTR=y
-CONFIG_SQUASHFS_LZO=y
-CONFIG_SQUASHFS_XZ=y
-CONFIG_ROMFS_FS=m
-CONFIG_NFS_FS=m
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=m
-CONFIG_NFS_SWAP=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3_ACL=y
-CONFIG_NFSD_V4=y
-CONFIG_NFSD_V4_SECURITY_LABEL=y
-CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
-CONFIG_CIFS_STATS2=y
-CONFIG_CIFS_WEAK_PW_HASH=y
-CONFIG_CIFS_UPCALL=y
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-# CONFIG_CIFS_DEBUG is not set
-CONFIG_CIFS_DFS_UPCALL=y
-CONFIG_NLS_DEFAULT="utf8"
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_UTF8=m
-CONFIG_DLM=m
-CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_DWARF4=y
-CONFIG_GDB_SCRIPTS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
-CONFIG_FRAME_WARN=1024
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_PANIC_ON_OOPS=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_RCU_CPU_STALL_TIMEOUT=60
-CONFIG_LATENCYTOP=y
-CONFIG_SCHED_TRACER=y
-CONFIG_FTRACE_SYSCALLS=y
-CONFIG_STACK_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_FUNCTION_PROFILER=y
-CONFIG_HIST_TRIGGERS=y
-CONFIG_LKDTM=m
-CONFIG_PERCPU_TEST=m
-CONFIG_ATOMIC64_SELFTEST=y
-CONFIG_TEST_BPF=m
-CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_S390_PTDUMP=y
-CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
-CONFIG_ENCRYPTED_KEYS=m
-CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
-CONFIG_SECURITY_SELINUX=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
-CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_INTEGRITY_SIGNATURE=y
-CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
-CONFIG_IMA=y
-CONFIG_IMA_WRITE_POLICY=y
-CONFIG_IMA_APPRAISE=y
-CONFIG_CRYPTO_DH=m
-CONFIG_CRYPTO_ECDH=m
-CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
-CONFIG_CRYPTO_PCRYPT=m
-CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_MCRYPTD=m
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_CHACHA20POLY1305=m
-CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_KEYWRAP=m
-CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
-CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_AES_TI=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
-CONFIG_CRYPTO_CAST5=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SEED=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_842=m
-CONFIG_CRYPTO_LZ4=m
-CONFIG_CRYPTO_LZ4HC=m
-CONFIG_CRYPTO_ANSI_CPRNG=m
-CONFIG_CRYPTO_USER_API_HASH=m
-CONFIG_CRYPTO_USER_API_SKCIPHER=m
-CONFIG_CRYPTO_USER_API_RNG=m
-CONFIG_CRYPTO_USER_API_AEAD=m
-CONFIG_ZCRYPT=m
-CONFIG_PKEY=m
-CONFIG_CRYPTO_PAES_S390=m
-CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
-CONFIG_CRYPTO_SHA512_S390=m
-CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_CRC7=m
-CONFIG_CRC8=m
-CONFIG_CORDIC=m
-CONFIG_CMM=m
-CONFIG_APPLDATA_BASE=y
-CONFIG_KVM=m
-CONFIG_KVM_S390_UCONTROL=y
-CONFIG_VHOST_NET=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 20ed149e1137..eb6f75f24208 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -25,13 +25,13 @@ CONFIG_CPUSETS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_PERF=y
-CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
+CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
@@ -45,6 +45,8 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG=y
+CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_INTEGRITY=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
@@ -62,6 +64,7 @@ CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -256,9 +259,9 @@ CONFIG_IP_VS_NQ=m
 CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
+CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
@@ -279,7 +282,7 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
+CONFIG_NF_TABLES_IPV6=y
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -300,8 +303,7 @@ CONFIG_IP6_NF_RAW=m
 CONFIG_IP6_NF_SECURITY=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=m
-CONFIG_NET_SCTPPROBE=m
+CONFIG_NF_TABLES_BRIDGE=y
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
 CONFIG_RDS_TCP=m
@@ -359,11 +361,11 @@ CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
 CONFIG_DNS_RESOLVER=y
+CONFIG_OPENVSWITCH=m
 CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
-CONFIG_NET_TCPPROBE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
@@ -375,8 +377,9 @@ CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_BLK_DEV_RAM_DAX=y
 CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_RBD=m
+CONFIG_BLK_DEV_NVME=m
 CONFIG_ENCLOSURE_SERVICES=m
 CONFIG_GENWQE=m
 CONFIG_RAID_ATTRS=m
@@ -455,6 +458,7 @@ CONFIG_PPTP=m
 CONFIG_PPPOL2TP=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
+CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
@@ -468,6 +472,9 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
+CONFIG_DRM=y
+CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
@@ -476,7 +483,9 @@ CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
+CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
+CONFIG_VIRTIO_INPUT=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -507,7 +516,6 @@ CONFIG_AUTOFS4_FS=m
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
-CONFIG_OVERLAY_FS_REDIRECT_DIR=y
 CONFIG_FSCACHE=m
 CONFIG_CACHEFILES=m
 CONFIG_ISO9660_FS=y
@@ -592,8 +600,10 @@ CONFIG_SECURITY_SELINUX_DISABLE=y
 CONFIG_INTEGRITY_SIGNATURE=y
 CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
 CONFIG_IMA=y
+CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
+CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_USER=m
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
index 8720e9203ecf..dd95cdbd22ce 100644
--- a/arch/s390/crypto/arch_random.c
+++ b/arch/s390/crypto/arch_random.c
@@ -2,14 +2,37 @@
 /*
  * s390 arch random implementation.
  *
- * Copyright IBM Corp. 2017
- * Author(s): Harald Freudenberger <freude@de.ibm.com>
+ * Copyright IBM Corp. 2017, 2018
+ * Author(s): Harald Freudenberger
+ *
+ * The s390_arch_random_generate() function may be called from random.c
+ * in interrupt context. So this implementation does the best to be very
+ * fast. There is a buffer of random data which is asynchronously checked
+ * and filled by a workqueue thread.
+ * If there are enough bytes in the buffer the s390_arch_random_generate()
+ * just delivers these bytes. Otherwise false is returned until the
+ * worker thread refills the buffer.
+ * The worker fills the rng buffer by pulling fresh entropy from the
+ * high quality (but slow) true hardware random generator. This entropy
+ * is then spread over the buffer with an pseudo random generator PRNG.
+ * As the arch_get_random_seed_long() fetches 8 bytes and the calling
+ * function add_interrupt_randomness() counts this as 1 bit entropy the
+ * distribution needs to make sure there is in fact 1 bit entropy contained
+ * in 8 bytes of the buffer. The current values pull 32 byte entropy
+ * and scatter this into a 2048 byte buffer. So 8 byte in the buffer
+ * will contain 1 bit of entropy.
+ * The worker thread is rescheduled based on the charge level of the
+ * buffer but at least with 500 ms delay to avoid too much CPU consumption.
+ * So the max. amount of rng data delivered via arch_get_random_seed is
+ * limited to 4k bytes per second.
  */
 
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 #include <linux/static_key.h>
+#include <linux/workqueue.h>
 #include <asm/cpacf.h>
 
 DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
@@ -17,11 +40,83 @@ DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
 atomic64_t s390_arch_random_counter = ATOMIC64_INIT(0);
 EXPORT_SYMBOL(s390_arch_random_counter);
 
+#define ARCH_REFILL_TICKS (HZ/2)
+#define ARCH_PRNG_SEED_SIZE 32
+#define ARCH_RNG_BUF_SIZE 2048
+
+static DEFINE_SPINLOCK(arch_rng_lock);
+static u8 *arch_rng_buf;
+static unsigned int arch_rng_buf_idx;
+
+static void arch_rng_refill_buffer(struct work_struct *);
+static DECLARE_DELAYED_WORK(arch_rng_work, arch_rng_refill_buffer);
+
+bool s390_arch_random_generate(u8 *buf, unsigned int nbytes)
+{
+	/* lock rng buffer */
+	if (!spin_trylock(&arch_rng_lock))
+		return false;
+
+	/* try to resolve the requested amount of bytes from the buffer */
+	arch_rng_buf_idx -= nbytes;
+	if (arch_rng_buf_idx < ARCH_RNG_BUF_SIZE) {
+		memcpy(buf, arch_rng_buf + arch_rng_buf_idx, nbytes);
+		atomic64_add(nbytes, &s390_arch_random_counter);
+		spin_unlock(&arch_rng_lock);
+		return true;
+	}
+
+	/* not enough bytes in rng buffer, refill is done asynchronously */
+	spin_unlock(&arch_rng_lock);
+
+	return false;
+}
+EXPORT_SYMBOL(s390_arch_random_generate);
+
+static void arch_rng_refill_buffer(struct work_struct *unused)
+{
+	unsigned int delay = ARCH_REFILL_TICKS;
+
+	spin_lock(&arch_rng_lock);
+	if (arch_rng_buf_idx > ARCH_RNG_BUF_SIZE) {
+		/* buffer is exhausted and needs refill */
+		u8 seed[ARCH_PRNG_SEED_SIZE];
+		u8 prng_wa[240];
+		/* fetch ARCH_PRNG_SEED_SIZE bytes of entropy */
+		cpacf_trng(NULL, 0, seed, sizeof(seed));
+		/* blow this entropy up to ARCH_RNG_BUF_SIZE with PRNG */
+		memset(prng_wa, 0, sizeof(prng_wa));
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
+			   &prng_wa, NULL, 0, seed, sizeof(seed));
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
+			   &prng_wa, arch_rng_buf, ARCH_RNG_BUF_SIZE, NULL, 0);
+		arch_rng_buf_idx = ARCH_RNG_BUF_SIZE;
+	}
+	delay += (ARCH_REFILL_TICKS * arch_rng_buf_idx) / ARCH_RNG_BUF_SIZE;
+	spin_unlock(&arch_rng_lock);
+
+	/* kick next check */
+	queue_delayed_work(system_long_wq, &arch_rng_work, delay);
+}
+
 static int __init s390_arch_random_init(void)
 {
-	/* check if subfunction CPACF_PRNO_TRNG is available */
-	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+	/* all the needed PRNO subfunctions available ? */
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG) &&
+	    cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN)) {
+
+		/* alloc arch random working buffer */
+		arch_rng_buf = kmalloc(ARCH_RNG_BUF_SIZE, GFP_KERNEL);
+		if (!arch_rng_buf)
+			return -ENOMEM;
+
+		/* kick worker queue job to fill the random buffer */
+		queue_delayed_work(system_long_wq,
+				   &arch_rng_work, ARCH_REFILL_TICKS);
+
+		/* enable arch random to the outside world */
 		static_branch_enable(&s390_arch_random_available);
+	}
 
 	return 0;
 }
diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.S
index e8077f0971f8..2bf01ba44107 100644
--- a/arch/s390/crypto/crc32be-vx.S
+++ b/arch/s390/crypto/crc32be-vx.S
@@ -13,6 +13,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/nospec-insn.h>
 #include <asm/vx-insn.h>
 
 /* Vector register range containing CRC-32 constants */
@@ -67,6 +68,8 @@
 
 .previous
 
+	GEN_BR_THUNK %r14
+
 .text
 /*
  * The CRC-32 function(s) use these calling conventions:
@@ -203,6 +206,6 @@ ENTRY(crc32_be_vgfm_16)
 
 .Ldone:
 	VLGVF	%r2,%v2,3
-	br	%r14
+	BR_EX	%r14
 
 .previous
diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.S
index d8c67a58c0c5..7d6f568bd3ad 100644
--- a/arch/s390/crypto/crc32le-vx.S
+++ b/arch/s390/crypto/crc32le-vx.S
@@ -14,6 +14,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/nospec-insn.h>
 #include <asm/vx-insn.h>
 
 /* Vector register range containing CRC-32 constants */
@@ -76,6 +77,7 @@
 
 .previous
 
+	GEN_BR_THUNK %r14
 
 .text
 
@@ -264,6 +266,6 @@ crc32_le_vgfm_generic:
 
 .Ldone:
 	VLGVF	%r2,%v2,2
-	br	%r14
+	BR_EX	%r14
 
 .previous
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 46a3178d8bc6..f40600eb1762 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -8,6 +8,7 @@ CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
+# CONFIG_CPU_ISOLATION is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
@@ -23,12 +24,12 @@ CONFIG_CPUSETS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_PERF=y
-CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
+CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
@@ -47,6 +48,7 @@ CONFIG_LIVEPATCH=y
 CONFIG_NR_CPUS=256
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -129,10 +131,13 @@ CONFIG_EQUALIZER=m
 CONFIG_TUN=m
 CONFIG_VIRTIO_NET=y
 # CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
+# CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
+# CONFIG_VT is not set
 CONFIG_DEVKMEM=y
 CONFIG_RAW_DRIVER=m
 CONFIG_VIRTIO_BALLOON=y
@@ -177,13 +182,15 @@ CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_FUNCTION_PROFILER=y
-CONFIG_KPROBES_SANITY_TEST=y
+# CONFIG_RUNTIME_TESTING_MENU is not set
 CONFIG_S390_PTDUMP=y
 CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_AUTHENC=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
 CONFIG_CRYPTO_CBC=y
+CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -213,6 +220,8 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_DEFLATE=m
diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c
index ae0ed8dd5f1b..5d85a039391c 100644
--- a/arch/s390/hypfs/hypfs_sprp.c
+++ b/arch/s390/hypfs/hypfs_sprp.c
@@ -13,7 +13,6 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
-#include <asm/compat.h>
 #include <asm/diag.h>
 #include <asm/sclp.h>
 #include "hypfs.h"
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 43bbe63e2992..06b513d192b9 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -320,7 +320,7 @@ static void hypfs_kill_super(struct super_block *sb)
 
 	if (sb->s_root)
 		hypfs_delete_tree(sb->s_root);
-	if (sb_info->update_file)
+	if (sb_info && sb_info->update_file)
 		hypfs_remove(sb_info->update_file);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h
index 09aed1095336..c67b82dfa558 100644
--- a/arch/s390/include/asm/archrandom.h
+++ b/arch/s390/include/asm/archrandom.h
@@ -15,16 +15,11 @@
 
 #include <linux/static_key.h>
 #include <linux/atomic.h>
-#include <asm/cpacf.h>
 
 DECLARE_STATIC_KEY_FALSE(s390_arch_random_available);
 extern atomic64_t s390_arch_random_counter;
 
-static void s390_arch_random_generate(u8 *buf, unsigned int nbytes)
-{
-	cpacf_trng(NULL, 0, buf, nbytes);
-	atomic64_add(nbytes, &s390_arch_random_counter);
-}
+bool s390_arch_random_generate(u8 *buf, unsigned int nbytes);
 
 static inline bool arch_has_random(void)
 {
@@ -51,8 +46,7 @@ static inline bool arch_get_random_int(unsigned int *v)
 static inline bool arch_get_random_seed_long(unsigned long *v)
 {
 	if (static_branch_likely(&s390_arch_random_available)) {
-		s390_arch_random_generate((u8 *)v, sizeof(*v));
-		return true;
+		return s390_arch_random_generate((u8 *)v, sizeof(*v));
 	}
 	return false;
 }
@@ -60,8 +54,7 @@ static inline bool arch_get_random_seed_long(unsigned long *v)
 static inline bool arch_get_random_seed_int(unsigned int *v)
 {
 	if (static_branch_likely(&s390_arch_random_available)) {
-		s390_arch_random_generate((u8 *)v, sizeof(*v));
-		return true;
+		return s390_arch_random_generate((u8 *)v, sizeof(*v));
 	}
 	return false;
 }
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index 20bce136b2e5..a29dd430fb40 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -231,4 +231,5 @@ int ccw_device_siosl(struct ccw_device *);
 extern void ccw_device_get_schid(struct ccw_device *, struct subchannel_id *);
 
 struct channel_path_desc_fmt0 *ccw_device_get_chp_desc(struct ccw_device *, int);
+u8 *ccw_device_get_util_str(struct ccw_device *cdev, int chp_idx);
 #endif /* _S390_CCWDEV_H_ */
diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h
index 99aa817dad32..860cab7479c3 100644
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -73,4 +73,14 @@ extern void ccwgroup_remove_ccwdev(struct ccw_device *cdev);
 
 #define to_ccwgroupdev(x) container_of((x), struct ccwgroup_device, dev)
 #define to_ccwgroupdrv(x) container_of((x), struct ccwgroup_driver, driver)
+
+#if IS_ENABLED(CONFIG_CCWGROUP)
+bool dev_is_ccwgroup(struct device *dev);
+#else /* CONFIG_CCWGROUP */
+static inline bool dev_is_ccwgroup(struct device *dev)
+{
+	return false;
+}
+#endif /* CONFIG_CCWGROUP */
+
 #endif
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 9830fb6b076e..97db2fba546a 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -53,7 +53,6 @@
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
-typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_pid_t;
 typedef u16		__compat_uid_t;
@@ -97,16 +96,6 @@ typedef struct {
 	u32 gprs_high[NUM_GPRS];
 } s390_compat_regs_high;
 
-struct compat_timespec {
-	compat_time_t	tv_sec;
-	s32		tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t	tv_sec;
-	s32		tv_usec;
-};
-
 struct compat_stat {
 	compat_dev_t	st_dev;
 	u16		__pad1;
@@ -243,10 +232,10 @@ struct compat_ipc64_perm {
 
 struct compat_semid64_ds {
 	struct compat_ipc64_perm sem_perm;
-	compat_time_t  sem_otime;
-	compat_ulong_t __pad1;
-	compat_time_t  sem_ctime;
-	compat_ulong_t __pad2;
+	compat_ulong_t sem_otime;
+	compat_ulong_t sem_otime_high;
+	compat_ulong_t sem_ctime;
+	compat_ulong_t sem_ctime_high;
 	compat_ulong_t sem_nsems;
 	compat_ulong_t __unused1;
 	compat_ulong_t __unused2;
@@ -254,12 +243,12 @@ struct compat_semid64_ds {
 
 struct compat_msqid64_ds {
 	struct compat_ipc64_perm msg_perm;
-	compat_time_t   msg_stime;
-	compat_ulong_t __pad1;
-	compat_time_t   msg_rtime;
-	compat_ulong_t __pad2;
-	compat_time_t   msg_ctime;
-	compat_ulong_t __pad3;
+	compat_ulong_t msg_stime;
+	compat_ulong_t msg_stime_high;
+	compat_ulong_t msg_rtime;
+	compat_ulong_t msg_rtime_high;
+	compat_ulong_t msg_ctime;
+	compat_ulong_t msg_ctime_high;
 	compat_ulong_t msg_cbytes;
 	compat_ulong_t msg_qnum;
 	compat_ulong_t msg_qbytes;
@@ -272,12 +261,12 @@ struct compat_msqid64_ds {
 struct compat_shmid64_ds {
 	struct compat_ipc64_perm shm_perm;
 	compat_size_t  shm_segsz;
-	compat_time_t  shm_atime;
-	compat_ulong_t __pad1;
-	compat_time_t  shm_dtime;
-	compat_ulong_t __pad2;
-	compat_time_t  shm_ctime;
-	compat_ulong_t __pad3;
+	compat_ulong_t shm_atime;
+	compat_ulong_t shm_atime_high;
+	compat_ulong_t shm_dtime;
+	compat_ulong_t shm_dtime_high;
+	compat_ulong_t shm_ctime;
+	compat_ulong_t shm_ctime_high;
 	compat_pid_t   shm_cpid;
 	compat_pid_t   shm_lpid;
 	compat_ulong_t shm_nattch;
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index f58d17e9dd65..de023a9a88ca 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -113,7 +113,7 @@ struct hws_basic_entry {
 
 struct hws_diag_entry {
 	unsigned int def:16;	    /* 0-15  Data Entry Format		 */
-	unsigned int R:14;	    /* 16-19 and 20-30 reserved		 */
+	unsigned int R:15;	    /* 16-19 and 20-30 reserved		 */
 	unsigned int I:1;	    /* 31 entry valid or invalid	 */
 	u8	     data[];	    /* Machine-dependent sample data	 */
 } __packed;
@@ -129,7 +129,9 @@ struct hws_trailer_entry {
 			unsigned int f:1;	/* 0 - Block Full Indicator   */
 			unsigned int a:1;	/* 1 - Alert request control  */
 			unsigned int t:1;	/* 2 - Timestamp format	      */
-			unsigned long long:61;	/* 3 - 63: Reserved	      */
+			unsigned int :29;	/* 3 - 31: Reserved	      */
+			unsigned int bsdes:16;	/* 32-47: size of basic SDE   */
+			unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
 		};
 		unsigned long long flags;	/* 0 - 63: All indicators     */
 	};
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 1a61b1b997f2..7d22a474a040 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -125,8 +125,9 @@
  * ELF register definitions..
  */
 
+#include <linux/compat.h>
+
 #include <asm/ptrace.h>
-#include <asm/compat.h>
 #include <asm/syscall.h>
 #include <asm/user.h>
 
@@ -136,7 +137,6 @@ typedef s390_regs elf_gregset_t;
 typedef s390_fp_regs compat_elf_fpregset_t;
 typedef s390_compat_regs compat_elf_gregset_t;
 
-#include <linux/compat.h>
 #include <linux/sched/mm.h>	/* for task_struct */
 #include <asm/mmu_context.h>
 
diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h
index a296c6acfd07..dfbc3c6c0674 100644
--- a/arch/s390/include/asm/hardirq.h
+++ b/arch/s390/include/asm/hardirq.h
@@ -14,6 +14,8 @@
 #include <asm/lowcore.h>
 
 #define local_softirq_pending() (S390_lowcore.softirq_pending)
+#define set_softirq_pending(x) (S390_lowcore.softirq_pending = (x))
+#define or_softirq_pending(x)  (S390_lowcore.softirq_pending |= (x))
 
 #define __ARCH_IRQ_STAT
 #define __ARCH_HAS_DO_SOFTIRQ
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 1d708a419326..825dd0f7f221 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -46,4 +46,27 @@
 static inline void crash_setup_regs(struct pt_regs *newregs,
 					struct pt_regs *oldregs) { }
 
+struct kimage;
+struct s390_load_data {
+	/* Pointer to the kernel buffer. Used to register cmdline etc.. */
+	void *kernel_buf;
+
+	/* Total size of loaded segments in memory. Used as an offset. */
+	size_t memsz;
+
+	/* Load address of initrd. Used to register INITRD_START in kernel. */
+	unsigned long initrd_load_addr;
+};
+
+int kexec_file_add_purgatory(struct kimage *image,
+			     struct s390_load_data *data);
+int kexec_file_add_initrd(struct kimage *image,
+			  struct s390_load_data *data,
+			  char *initrd, unsigned long initrd_len);
+int *kexec_file_update_kernel(struct kimage *iamge,
+			      struct s390_load_data *data);
+
+extern const struct kexec_file_ops s390_kexec_image_ops;
+extern const struct kexec_file_ops s390_kexec_elf_ops;
+
 #endif /*_S390_KEXEC_H */
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
new file mode 100644
index 000000000000..a01f81186e86
--- /dev/null
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -0,0 +1,196 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_NOSPEC_ASM_H
+#define _ASM_S390_NOSPEC_ASM_H
+
+#include <asm/alternative-asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/dwarf.h>
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_EXPOLINE
+
+_LC_BR_R1 = __LC_BR_R1
+
+/*
+ * The expoline macros are used to create thunks in the same format
+ * as gcc generates them. The 'comdat' section flag makes sure that
+ * the various thunks are merged into a single copy.
+ */
+	.macro __THUNK_PROLOG_NAME name
+	.pushsection .text.\name,"axG",@progbits,\name,comdat
+	.globl \name
+	.hidden \name
+	.type \name,@function
+\name:
+	CFI_STARTPROC
+	.endm
+
+	.macro __THUNK_EPILOG
+	CFI_ENDPROC
+	.popsection
+	.endm
+
+	.macro __THUNK_PROLOG_BR r1,r2
+	__THUNK_PROLOG_NAME __s390x_indirect_jump_r\r2\()use_r\r1
+	.endm
+
+	.macro __THUNK_PROLOG_BC d0,r1,r2
+	__THUNK_PROLOG_NAME __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+	.endm
+
+	.macro __THUNK_BR r1,r2
+	jg	__s390x_indirect_jump_r\r2\()use_r\r1
+	.endm
+
+	.macro __THUNK_BC d0,r1,r2
+	jg	__s390x_indirect_branch_\d0\()_\r2\()use_\r1
+	.endm
+
+	.macro __THUNK_BRASL r1,r2,r3
+	brasl	\r1,__s390x_indirect_jump_r\r3\()use_r\r2
+	.endm
+
+	.macro	__DECODE_RR expand,reg,ruse
+	.set __decode_fail,1
+	.irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+	.ifc \reg,%r\r1
+	.irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+	.ifc \ruse,%r\r2
+	\expand \r1,\r2
+	.set __decode_fail,0
+	.endif
+	.endr
+	.endif
+	.endr
+	.if __decode_fail == 1
+	.error "__DECODE_RR failed"
+	.endif
+	.endm
+
+	.macro	__DECODE_RRR expand,rsave,rtarget,ruse
+	.set __decode_fail,1
+	.irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+	.ifc \rsave,%r\r1
+	.irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+	.ifc \rtarget,%r\r2
+	.irp r3,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+	.ifc \ruse,%r\r3
+	\expand \r1,\r2,\r3
+	.set __decode_fail,0
+	.endif
+	.endr
+	.endif
+	.endr
+	.endif
+	.endr
+	.if __decode_fail == 1
+	.error "__DECODE_RRR failed"
+	.endif
+	.endm
+
+	.macro	__DECODE_DRR expand,disp,reg,ruse
+	.set __decode_fail,1
+	.irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+	.ifc \reg,%r\r1
+	.irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+	.ifc \ruse,%r\r2
+	\expand \disp,\r1,\r2
+	.set __decode_fail,0
+	.endif
+	.endr
+	.endif
+	.endr
+	.if __decode_fail == 1
+	.error "__DECODE_DRR failed"
+	.endif
+	.endm
+
+	.macro __THUNK_EX_BR reg,ruse
+	# Be very careful when adding instructions to this macro!
+	# The ALTERNATIVE replacement code has a .+10 which targets
+	# the "br \reg" after the code has been patched.
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+	exrl	0,555f
+	j	.
+#else
+	.ifc \reg,%r1
+	ALTERNATIVE "ex %r0,_LC_BR_R1", ".insn ril,0xc60000000000,0,.+10", 35
+	j	.
+	.else
+	larl	\ruse,555f
+	ex	0,0(\ruse)
+	j	.
+	.endif
+#endif
+555:	br	\reg
+	.endm
+
+	.macro __THUNK_EX_BC disp,reg,ruse
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+	exrl	0,556f
+	j	.
+#else
+	larl	\ruse,556f
+	ex	0,0(\ruse)
+	j	.
+#endif
+556:	b	\disp(\reg)
+	.endm
+
+	.macro GEN_BR_THUNK reg,ruse=%r1
+	__DECODE_RR __THUNK_PROLOG_BR,\reg,\ruse
+	__THUNK_EX_BR \reg,\ruse
+	__THUNK_EPILOG
+	.endm
+
+	.macro GEN_B_THUNK disp,reg,ruse=%r1
+	__DECODE_DRR __THUNK_PROLOG_BC,\disp,\reg,\ruse
+	__THUNK_EX_BC \disp,\reg,\ruse
+	__THUNK_EPILOG
+	.endm
+
+	.macro BR_EX reg,ruse=%r1
+557:	__DECODE_RR __THUNK_BR,\reg,\ruse
+	.pushsection .s390_indirect_branches,"a",@progbits
+	.long	557b-.
+	.popsection
+	.endm
+
+	 .macro B_EX disp,reg,ruse=%r1
+558:	__DECODE_DRR __THUNK_BC,\disp,\reg,\ruse
+	.pushsection .s390_indirect_branches,"a",@progbits
+	.long	558b-.
+	.popsection
+	.endm
+
+	.macro BASR_EX rsave,rtarget,ruse=%r1
+559:	__DECODE_RRR __THUNK_BRASL,\rsave,\rtarget,\ruse
+	.pushsection .s390_indirect_branches,"a",@progbits
+	.long	559b-.
+	.popsection
+	.endm
+
+#else
+	.macro GEN_BR_THUNK reg,ruse=%r1
+	.endm
+
+	.macro GEN_B_THUNK disp,reg,ruse=%r1
+	.endm
+
+	 .macro BR_EX reg,ruse=%r1
+	br	\reg
+	.endm
+
+	 .macro B_EX disp,reg,ruse=%r1
+	b	\disp(\reg)
+	.endm
+
+	.macro BASR_EX rsave,rtarget,ruse=%r1
+	basr	\rsave,\rtarget
+	.endm
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_S390_NOSPEC_ASM_H */
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 12fe3591034f..94f8db468c9b 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_S390_PCI_H
 #define __ASM_S390_PCI_H
 
-/* must be set before including asm-generic/pci.h */
-#define PCI_DMA_BUS_IS_PHYS (0)
 /* must be set before including pci_clp.h */
 #define PCI_BAR_COUNT	6
 
diff --git a/arch/s390/include/asm/pnet.h b/arch/s390/include/asm/pnet.h
new file mode 100644
index 000000000000..6e278584f8f1
--- /dev/null
+++ b/arch/s390/include/asm/pnet.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  IBM System z PNET ID Support
+ *
+ *    Copyright IBM Corp. 2018
+ */
+
+#ifndef _ASM_S390_PNET_H
+#define _ASM_S390_PNET_H
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+#define PNETIDS_LEN		64	/* Total utility string length in bytes
+					 * to cover up to 4 PNETIDs of 16 bytes
+					 * for up to 4 device ports
+					 */
+#define MAX_PNETID_LEN		16	/* Max.length of a single port PNETID */
+#define MAX_PNETID_PORTS	(PNETIDS_LEN / MAX_PNETID_LEN)
+					/* Max. # of ports with a PNETID */
+
+int pnet_id_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid);
+#endif /* _ASM_S390_PNET_H */
diff --git a/arch/s390/include/asm/purgatory.h b/arch/s390/include/asm/purgatory.h
new file mode 100644
index 000000000000..6090670df51f
--- /dev/null
+++ b/arch/s390/include/asm/purgatory.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#ifndef _S390_PURGATORY_H_
+#define _S390_PURGATORY_H_
+#ifndef __ASSEMBLY__
+
+#include <linux/purgatory.h>
+
+int verify_sha256_digest(void);
+
+extern u64 kernel_entry;
+extern u64 kernel_type;
+
+extern u64 crash_start;
+extern u64 crash_size;
+
+#endif	/* __ASSEMBLY__ */
+#endif /* _S390_PURGATORY_H_ */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 124154fdfc97..9c30ebe046f3 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  S390 version
- *    Copyright IBM Corp. 1999, 2010
+ *    Copyright IBM Corp. 1999, 2017
  */
 #ifndef _ASM_S390_SETUP_H
 #define _ASM_S390_SETUP_H
@@ -37,17 +37,31 @@
 #define LPP_MAGIC		_BITUL(31)
 #define LPP_PID_MASK		_AC(0xffffffff, UL)
 
+/* Offsets to entry points in kernel/head.S  */
+
+#define STARTUP_NORMAL_OFFSET	0x10000
+#define STARTUP_KDUMP_OFFSET	0x10010
+
+/* Offsets to parameters in kernel/head.S  */
+
+#define IPL_DEVICE_OFFSET	0x10400
+#define INITRD_START_OFFSET	0x10408
+#define INITRD_SIZE_OFFSET	0x10410
+#define OLDMEM_BASE_OFFSET	0x10418
+#define OLDMEM_SIZE_OFFSET	0x10420
+#define COMMAND_LINE_OFFSET	0x10480
+
 #ifndef __ASSEMBLY__
 
 #include <asm/lowcore.h>
 #include <asm/types.h>
 
-#define IPL_DEVICE        (*(unsigned long *)  (0x10400))
-#define INITRD_START      (*(unsigned long *)  (0x10408))
-#define INITRD_SIZE       (*(unsigned long *)  (0x10410))
-#define OLDMEM_BASE	  (*(unsigned long *)  (0x10418))
-#define OLDMEM_SIZE	  (*(unsigned long *)  (0x10420))
-#define COMMAND_LINE      ((char *)            (0x10480))
+#define IPL_DEVICE	(*(unsigned long *)  (IPL_DEVICE_OFFSET))
+#define INITRD_START	(*(unsigned long *)  (INITRD_START_OFFSET))
+#define INITRD_SIZE	(*(unsigned long *)  (INITRD_SIZE_OFFSET))
+#define OLDMEM_BASE	(*(unsigned long *)  (OLDMEM_BASE_OFFSET))
+#define OLDMEM_SIZE	(*(unsigned long *)  (OLDMEM_SIZE_OFFSET))
+#define COMMAND_LINE	((char *)	     (COMMAND_LINE_OFFSET))
 
 extern int memory_end_set;
 extern unsigned long memory_end;
@@ -121,12 +135,12 @@ extern void (*_machine_power_off)(void);
 
 #else /* __ASSEMBLY__ */
 
-#define IPL_DEVICE        0x10400
-#define INITRD_START      0x10408
-#define INITRD_SIZE       0x10410
-#define OLDMEM_BASE	  0x10418
-#define OLDMEM_SIZE	  0x10420
-#define COMMAND_LINE      0x10480
+#define IPL_DEVICE	(IPL_DEVICE_OFFSET)
+#define INITRD_START	(INITRD_START_OFFSET)
+#define INITRD_SIZE	(INITRD_SIZE_OFFSET)
+#define OLDMEM_BASE	(OLDMEM_BASE_OFFSET)
+#define OLDMEM_SIZE	(OLDMEM_SIZE_OFFSET)
+#define COMMAND_LINE	(COMMAND_LINE_OFFSET)
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_S390_SETUP_H */
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 83ba57533ce6..3c883c368eb0 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -45,6 +45,9 @@ struct thread_info {
 void arch_release_task_struct(struct task_struct *tsk);
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 
+void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
+
 #endif
 
 /*
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index faef3f7e8353..e364873e0d10 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -9,9 +9,12 @@ generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h
 generic-y += mman.h
+generic-y += msgbuf.h
 generic-y += param.h
 generic-y += poll.h
 generic-y += resource.h
+generic-y += sembuf.h
+generic-y += shmbuf.h
 generic-y += sockios.h
 generic-y += swab.h
 generic-y += termbits.h
diff --git a/arch/s390/include/uapi/asm/msgbuf.h b/arch/s390/include/uapi/asm/msgbuf.h
deleted file mode 100644
index 604f847cd68c..000000000000
--- a/arch/s390/include/uapi/asm/msgbuf.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _S390_MSGBUF_H
-#define _S390_MSGBUF_H
-
-/* 
- * The msqid64_ds structure for S/390 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct msqid64_ds {
-	struct ipc64_perm msg_perm;
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-#ifndef __s390x__
-	unsigned long	__unused1;
-#endif /* ! __s390x__ */
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-#ifndef __s390x__
-	unsigned long	__unused2;
-#endif /* ! __s390x__ */
-	__kernel_time_t msg_ctime;	/* last change time */
-#ifndef __s390x__
-	unsigned long	__unused3;
-#endif /* ! __s390x__ */
-	unsigned long  msg_cbytes;	/* current number of bytes on queue */
-	unsigned long  msg_qnum;	/* number of messages in queue */
-	unsigned long  msg_qbytes;	/* max number of bytes on queue */
-	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
-	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	unsigned long  __unused4;
-	unsigned long  __unused5;
-};
-
-#endif /* _S390_MSGBUF_H */
diff --git a/arch/s390/include/uapi/asm/sembuf.h b/arch/s390/include/uapi/asm/sembuf.h
deleted file mode 100644
index 3e917697b668..000000000000
--- a/arch/s390/include/uapi/asm/sembuf.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _S390_SEMBUF_H
-#define _S390_SEMBUF_H
-
-/* 
- * The semid64_ds structure for S/390 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem (for !__s390x__)
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
-	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
-	__kernel_time_t	sem_otime;		/* last semop time */
-#ifndef __s390x__
-	unsigned long	__unused1;
-#endif /* ! __s390x__ */
-	__kernel_time_t	sem_ctime;		/* last change time */
-#ifndef __s390x__
-	unsigned long	__unused2;
-#endif /* ! __s390x__ */
-	unsigned long	sem_nsems;		/* no. of semaphores in array */
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* _S390_SEMBUF_H */
diff --git a/arch/s390/include/uapi/asm/shmbuf.h b/arch/s390/include/uapi/asm/shmbuf.h
deleted file mode 100644
index 9cdce8d7ce60..000000000000
--- a/arch/s390/include/uapi/asm/shmbuf.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _S390_SHMBUF_H
-#define _S390_SHMBUF_H
-
-/* 
- * The shmid64_ds structure for S/390 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem (for !__s390x__)
- * - 2 miscellaneous 32-bit values
- */
-
-struct shmid64_ds {
-	struct ipc64_perm	shm_perm;	/* operation perms */
-	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_time_t		shm_atime;	/* last attach time */
-#ifndef __s390x__
-	unsigned long		__unused1;
-#endif /* ! __s390x__ */
-	__kernel_time_t		shm_dtime;	/* last detach time */
-#ifndef __s390x__
-	unsigned long		__unused2;
-#endif /* ! __s390x__ */
-	__kernel_time_t		shm_ctime;	/* last change time */
-#ifndef __s390x__
-	unsigned long		__unused3;
-#endif /* ! __s390x__ */
-	__kernel_pid_t		shm_cpid;	/* pid of creator */
-	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	unsigned long		shm_nattch;	/* no. of current attaches */
-	unsigned long		__unused4;
-	unsigned long		__unused5;
-};
-
-struct shminfo64 {
-	unsigned long	shmmax;
-	unsigned long	shmmin;
-	unsigned long	shmmni;
-	unsigned long	shmseg;
-	unsigned long	shmall;
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* _S390_SHMBUF_H */
diff --git a/arch/s390/include/uapi/asm/signal.h b/arch/s390/include/uapi/asm/signal.h
index c57f9d28d894..9a14a611ed82 100644
--- a/arch/s390/include/uapi/asm/signal.h
+++ b/arch/s390/include/uapi/asm/signal.h
@@ -97,22 +97,31 @@ typedef unsigned long sigset_t;
 #include <asm-generic/signal-defs.h>
 
 #ifndef __KERNEL__
-/* Here we must cater to libcs that poke about in kernel headers.  */
 
+/*
+ * There are two system calls in regard to sigaction, sys_rt_sigaction
+ * and sys_sigaction. Internally the kernel uses the struct old_sigaction
+ * for the older sys_sigaction system call, and the kernel version of the
+ * struct sigaction for the newer sys_rt_sigaction.
+ *
+ * The uapi definition for struct sigaction has made a strange distinction
+ * between 31-bit and 64-bit in the past. For 64-bit the uapi structure
+ * looks like the kernel struct sigaction, but for 31-bit it used to
+ * look like the kernel struct old_sigaction. That practically made the
+ * structure unusable for either system call. To get around this problem
+ * the glibc always had its own definitions for the sigaction structures.
+ *
+ * The current struct sigaction uapi definition below is suitable for the
+ * sys_rt_sigaction system call only.
+ */
 struct sigaction {
         union {
           __sighandler_t _sa_handler;
           void (*_sa_sigaction)(int, struct siginfo *, void *);
         } _u;
-#ifndef __s390x__ /* lovely */
-        sigset_t sa_mask;
-        unsigned long sa_flags;
-        void (*sa_restorer)(void);
-#else  /* __s390x__ */
         unsigned long sa_flags;
         void (*sa_restorer)(void);
 	sigset_t sa_mask;
-#endif /* __s390x__ */
 };
 
 #define sa_handler      _u._sa_handler
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index b06a6f79c1ec..2fed39b26b42 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -6,22 +6,26 @@
 ifdef CONFIG_FUNCTION_TRACER
 
 # Do not trace tracer code
-CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace.o		= $(CC_FLAGS_FTRACE)
 
 # Do not trace early setup code
-CFLAGS_REMOVE_als.o	= $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_early.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_als.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_early.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_early_nobss.o	= $(CC_FLAGS_FTRACE)
 
 endif
 
-GCOV_PROFILE_als.o	:= n
-GCOV_PROFILE_early.o	:= n
+GCOV_PROFILE_als.o		:= n
+GCOV_PROFILE_early.o		:= n
+GCOV_PROFILE_early_nobss.o	:= n
 
-KCOV_INSTRUMENT_als.o	:= n
-KCOV_INSTRUMENT_early.o	:= n
+KCOV_INSTRUMENT_als.o		:= n
+KCOV_INSTRUMENT_early.o		:= n
+KCOV_INSTRUMENT_early_nobss.o	:= n
 
-UBSAN_SANITIZE_als.o	:= n
-UBSAN_SANITIZE_early.o	:= n
+UBSAN_SANITIZE_als.o		:= n
+UBSAN_SANITIZE_early.o		:= n
+UBSAN_SANITIZE_early_nobss.o	:= n
 
 #
 # Use -march=z900 for als.c to be able to print an error
@@ -57,7 +61,7 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o
+obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o early_nobss.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
@@ -65,6 +69,7 @@ obj-y	+= nospec-branch.o
 
 extra-y				+= head.o head64.o vmlinux.lds
 
+obj-$(CONFIG_SYSFS)		+= nospec-sysfs.o
 CFLAGS_REMOVE_nospec-branch.o	+= $(CC_FLAGS_EXPOLINE)
 
 obj-$(CONFIG_MODULES)		+= module.o
@@ -82,6 +87,9 @@ obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o
 
+obj-$(CONFIG_KEXEC_FILE)	+= machine_kexec_file.o kexec_image.o
+obj-$(CONFIG_KEXEC_FILE)	+= kexec_elf.o
+
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o perf_cpum_sf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf_events.o perf_regs.o
 
@@ -90,3 +98,6 @@ obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 # vdso
 obj-y				+= vdso64/
 obj-$(CONFIG_COMPAT)		+= vdso32/
+
+chkbss := head.o head64.o als.o early_nobss.o
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index cfe2c45c5180..11aea745a2a6 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -10,6 +10,7 @@
 #include <linux/kbuild.h>
 #include <linux/kvm_host.h>
 #include <linux/sched.h>
+#include <linux/purgatory.h>
 #include <asm/idle.h>
 #include <asm/vdso.h>
 #include <asm/pgtable.h>
@@ -180,6 +181,7 @@ int main(void)
 	OFFSET(__LC_MACHINE_FLAGS, lowcore, machine_flags);
 	OFFSET(__LC_PREEMPT_COUNT, lowcore, preempt_count);
 	OFFSET(__LC_GMAP, lowcore, gmap);
+	OFFSET(__LC_BR_R1, lowcore, br_r1_trampoline);
 	/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
 	OFFSET(__LC_DUMP_REIPL, lowcore, ipib);
 	/* hardware defined lowcore locations 0x1000 - 0x18ff */
@@ -204,5 +206,9 @@ int main(void)
 	OFFSET(__GMAP_ASCE, gmap, asce);
 	OFFSET(__SIE_PROG0C, kvm_s390_sie_block, prog0c);
 	OFFSET(__SIE_PROG20, kvm_s390_sie_block, prog20);
+	/* kexec_sha_region */
+	OFFSET(__KEXEC_SHA_REGION_START, kexec_sha_region, start);
+	OFFSET(__KEXEC_SHA_REGION_LEN, kexec_sha_region, len);
+	DEFINE(__KEXEC_SHA_REGION_SIZE, sizeof(struct kexec_sha_region));
 	return 0;
 }
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index f6c56009e822..b65874b0b412 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -9,18 +9,22 @@
 
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
 #include <asm/ptrace.h>
 #include <asm/sigp.h>
 
+	GEN_BR_THUNK %r9
+	GEN_BR_THUNK %r14
+
 ENTRY(s390_base_mcck_handler)
 	basr	%r13,0
 0:	lg	%r15,__LC_PANIC_STACK	# load panic stack
 	aghi	%r15,-STACK_FRAME_OVERHEAD
 	larl	%r1,s390_base_mcck_handler_fn
-	lg	%r1,0(%r1)
-	ltgr	%r1,%r1
+	lg	%r9,0(%r1)
+	ltgr	%r9,%r9
 	jz	1f
-	basr	%r14,%r1
+	BASR_EX	%r14,%r9
 1:	la	%r1,4095
 	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
 	lpswe	__LC_MCK_OLD_PSW
@@ -37,10 +41,10 @@ ENTRY(s390_base_ext_handler)
 	basr	%r13,0
 0:	aghi	%r15,-STACK_FRAME_OVERHEAD
 	larl	%r1,s390_base_ext_handler_fn
-	lg	%r1,0(%r1)
-	ltgr	%r1,%r1
+	lg	%r9,0(%r1)
+	ltgr	%r9,%r9
 	jz	1f
-	basr	%r14,%r1
+	BASR_EX	%r14,%r9
 1:	lmg	%r0,%r15,__LC_SAVE_AREA_ASYNC
 	ni	__LC_EXT_OLD_PSW+1,0xfd	# clear wait state bit
 	lpswe	__LC_EXT_OLD_PSW
@@ -57,10 +61,10 @@ ENTRY(s390_base_pgm_handler)
 	basr	%r13,0
 0:	aghi	%r15,-STACK_FRAME_OVERHEAD
 	larl	%r1,s390_base_pgm_handler_fn
-	lg	%r1,0(%r1)
-	ltgr	%r1,%r1
+	lg	%r9,0(%r1)
+	ltgr	%r9,%r9
 	jz	1f
-	basr	%r14,%r1
+	BASR_EX	%r14,%r9
 	lmg	%r0,%r15,__LC_SAVE_AREA_SYNC
 	lpswe	__LC_PGM_OLD_PSW
 1:	lpswe	disabled_wait_psw-0b(%r13)
@@ -117,7 +121,7 @@ ENTRY(diag308_reset)
 	larl	%r4,.Lcontinue_psw	# Restore PSW flags
 	lpswe	0(%r4)
 .Lcontinue:
-	br	%r14
+	BR_EX	%r14
 .align 16
 .Lrestart_psw:
 	.long	0x00080000,0x80000000 + .Lrestart_part2
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index 11e9d8b5c1b0..607c5e9fba3d 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -182,3 +182,4 @@ COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int,
 COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb);
 COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
 COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags);
+COMPAT_SYSCALL_WRAP5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags)
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 32daa0f84325..827699eb48fa 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -34,32 +34,6 @@
 static void __init setup_boot_command_line(void);
 
 /*
- * Get the TOD clock running.
- */
-static void __init reset_tod_clock(void)
-{
-	u64 time;
-
-	if (store_tod_clock(&time) == 0)
-		return;
-	/* TOD clock not running. Set the clock to Unix Epoch. */
-	if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
-		disabled_wait(0);
-
-	memset(tod_clock_base, 0, 16);
-	*(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
-	S390_lowcore.last_update_clock = TOD_UNIX_EPOCH;
-}
-
-/*
- * Clear bss memory
- */
-static noinline __init void clear_bss_section(void)
-{
-	memset(__bss_start, 0, __bss_stop - __bss_start);
-}
-
-/*
  * Initialize storage key for kernel pages
  */
 static noinline __init void init_kernel_storage_key(void)
@@ -310,57 +284,6 @@ static int __init cad_setup(char *str)
 }
 early_param("cad", cad_setup);
 
-static __init void memmove_early(void *dst, const void *src, size_t n)
-{
-	unsigned long addr;
-	long incr;
-	psw_t old;
-
-	if (!n)
-		return;
-	incr = 1;
-	if (dst > src) {
-		incr = -incr;
-		dst += n - 1;
-		src += n - 1;
-	}
-	old = S390_lowcore.program_new_psw;
-	S390_lowcore.program_new_psw.mask = __extract_psw();
-	asm volatile(
-		"	larl	%[addr],1f\n"
-		"	stg	%[addr],%[psw_pgm_addr]\n"
-		"0:     mvc	0(1,%[dst]),0(%[src])\n"
-		"	agr	%[dst],%[incr]\n"
-		"	agr	%[src],%[incr]\n"
-		"	brctg	%[n],0b\n"
-		"1:\n"
-		: [addr] "=&d" (addr),
-		  [psw_pgm_addr] "=Q" (S390_lowcore.program_new_psw.addr),
-		  [dst] "+&a" (dst), [src] "+&a" (src),  [n] "+d" (n)
-		: [incr] "d" (incr)
-		: "cc", "memory");
-	S390_lowcore.program_new_psw = old;
-}
-
-static __init noinline void rescue_initrd(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-	unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
-	/*
-	 * Just like in case of IPL from VM reader we make sure there is a
-	 * gap of 4MB between end of kernel and start of initrd.
-	 * That way we can also be sure that saving an NSS will succeed,
-	 * which however only requires different segments.
-	 */
-	if (!INITRD_START || !INITRD_SIZE)
-		return;
-	if (INITRD_START >= min_initrd_addr)
-		return;
-	memmove_early((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
-	INITRD_START = min_initrd_addr;
-#endif
-}
-
 /* Set up boot command line */
 static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t))
 {
@@ -410,9 +333,6 @@ static void __init setup_boot_command_line(void)
 
 void __init startup_init(void)
 {
-	reset_tod_clock();
-	rescue_initrd();
-	clear_bss_section();
 	time_early_init();
 	init_kernel_storage_key();
 	lockdep_off();
diff --git a/arch/s390/kernel/early_nobss.c b/arch/s390/kernel/early_nobss.c
new file mode 100644
index 000000000000..2d84fc48df3a
--- /dev/null
+++ b/arch/s390/kernel/early_nobss.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *    Copyright IBM Corp. 2007, 2018
+ */
+
+/*
+ * Early setup functions which may not rely on an initialized bss
+ * section. The last thing that is supposed to happen here is
+ * initialization of the bss section.
+ */
+
+#include <linux/processor.h>
+#include <linux/string.h>
+#include <asm/sections.h>
+#include <asm/lowcore.h>
+#include <asm/setup.h>
+#include <asm/timex.h>
+#include "entry.h"
+
+static void __init reset_tod_clock(void)
+{
+	u64 time;
+
+	if (store_tod_clock(&time) == 0)
+		return;
+	/* TOD clock not running. Set the clock to Unix Epoch. */
+	if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
+		disabled_wait(0);
+
+	memset(tod_clock_base, 0, 16);
+	*(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
+	S390_lowcore.last_update_clock = TOD_UNIX_EPOCH;
+}
+
+static void __init rescue_initrd(void)
+{
+	unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
+
+	/*
+	 * Just like in case of IPL from VM reader we make sure there is a
+	 * gap of 4MB between end of kernel and start of initrd.
+	 * That way we can also be sure that saving an NSS will succeed,
+	 * which however only requires different segments.
+	 */
+	if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD))
+		return;
+	if (!INITRD_START || !INITRD_SIZE)
+		return;
+	if (INITRD_START >= min_initrd_addr)
+		return;
+	memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
+	INITRD_START = min_initrd_addr;
+}
+
+static void __init clear_bss_section(void)
+{
+	memset(__bss_start, 0, __bss_stop - __bss_start);
+}
+
+void __init startup_init_nobss(void)
+{
+	reset_tod_clock();
+	rescue_initrd();
+	clear_bss_section();
+}
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 3f22f139a041..f03402efab4b 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -28,6 +28,7 @@
 #include <asm/setup.h>
 #include <asm/nmi.h>
 #include <asm/export.h>
+#include <asm/nospec-insn.h>
 
 __PT_R0      =	__PT_GPRS
 __PT_R1      =	__PT_GPRS + 8
@@ -183,67 +184,9 @@ _LPP_OFFSET	= __LC_LPP
 		    "jnz .+8; .long 0xb2e8d000", 82
 	.endm
 
-#ifdef CONFIG_EXPOLINE
-
-	.macro GEN_BR_THUNK name,reg,tmp
-	.section .text.\name,"axG",@progbits,\name,comdat
-	.globl \name
-	.hidden \name
-	.type \name,@function
-\name:
-	CFI_STARTPROC
-#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
-	exrl	0,0f
-#else
-	larl	\tmp,0f
-	ex	0,0(\tmp)
-#endif
-	j	.
-0:	br	\reg
-	CFI_ENDPROC
-	.endm
-
-	GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1
-	GEN_BR_THUNK __s390x_indirect_jump_r1use_r14,%r14,%r1
-	GEN_BR_THUNK __s390x_indirect_jump_r11use_r14,%r14,%r11
-
-	.macro BASR_R14_R9
-0:	brasl	%r14,__s390x_indirect_jump_r1use_r9
-	.pushsection .s390_indirect_branches,"a",@progbits
-	.long	0b-.
-	.popsection
-	.endm
-
-	.macro BR_R1USE_R14
-0:	jg	__s390x_indirect_jump_r1use_r14
-	.pushsection .s390_indirect_branches,"a",@progbits
-	.long	0b-.
-	.popsection
-	.endm
-
-	.macro BR_R11USE_R14
-0:	jg	__s390x_indirect_jump_r11use_r14
-	.pushsection .s390_indirect_branches,"a",@progbits
-	.long	0b-.
-	.popsection
-	.endm
-
-#else	/* CONFIG_EXPOLINE */
-
-	.macro BASR_R14_R9
-	basr	%r14,%r9
-	.endm
-
-	.macro BR_R1USE_R14
-	br	%r14
-	.endm
-
-	.macro BR_R11USE_R14
-	br	%r14
-	.endm
-
-#endif /* CONFIG_EXPOLINE */
-
+	GEN_BR_THUNK %r9
+	GEN_BR_THUNK %r14
+	GEN_BR_THUNK %r14,%r11
 
 	.section .kprobes.text, "ax"
 .Ldummy:
@@ -260,7 +203,7 @@ _LPP_OFFSET	= __LC_LPP
 ENTRY(__bpon)
 	.globl __bpon
 	BPON
-	BR_R1USE_R14
+	BR_EX	%r14
 
 /*
  * Scheduler resume function, called by switch_to
@@ -284,7 +227,7 @@ ENTRY(__switch_to)
 	mvc	__LC_CURRENT_PID(4,%r0),0(%r3)	# store pid of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40
-	BR_R1USE_R14
+	BR_EX	%r14
 
 .L__critical_start:
 
@@ -351,7 +294,7 @@ sie_exit:
 	xgr	%r5,%r5
 	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
 	lg	%r2,__SF_SIE_REASON(%r15)	# return exit reason code
-	BR_R1USE_R14
+	BR_EX	%r14
 .Lsie_fault:
 	lghi	%r14,-EFAULT
 	stg	%r14,__SF_SIE_REASON(%r15)	# set exit reason code
@@ -410,7 +353,7 @@ ENTRY(system_call)
 	lgf	%r9,0(%r8,%r10)			# get system call add.
 	TSTMSK	__TI_flags(%r12),_TIF_TRACE
 	jnz	.Lsysc_tracesys
-	BASR_R14_R9				# call sys_xxxx
+	BASR_EX	%r14,%r9			# call sys_xxxx
 	stg	%r2,__PT_R2(%r11)		# store return value
 
 .Lsysc_return:
@@ -595,7 +538,7 @@ ENTRY(system_call)
 	lmg	%r3,%r7,__PT_R3(%r11)
 	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
 	lg	%r2,__PT_ORIG_GPR2(%r11)
-	BASR_R14_R9			# call sys_xxx
+	BASR_EX	%r14,%r9		# call sys_xxx
 	stg	%r2,__PT_R2(%r11)	# store return value
 .Lsysc_tracenogo:
 	TSTMSK	__TI_flags(%r12),_TIF_TRACE
@@ -619,7 +562,7 @@ ENTRY(ret_from_fork)
 	lmg	%r9,%r10,__PT_R9(%r11)	# load gprs
 ENTRY(kernel_thread_starter)
 	la	%r2,0(%r10)
-	BASR_R14_R9
+	BASR_EX	%r14,%r9
 	j	.Lsysc_tracenogo
 
 /*
@@ -701,7 +644,7 @@ ENTRY(pgm_check_handler)
 	je	.Lpgm_return
 	lgf	%r9,0(%r10,%r1)		# load address of handler routine
 	lgr	%r2,%r11		# pass pointer to pt_regs
-	BASR_R14_R9			# branch to interrupt-handler
+	BASR_EX	%r14,%r9		# branch to interrupt-handler
 .Lpgm_return:
 	LOCKDEP_SYS_EXIT
 	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
@@ -1019,7 +962,7 @@ ENTRY(psw_idle)
 	stpt	__TIMER_IDLE_ENTER(%r2)
 .Lpsw_idle_lpsw:
 	lpswe	__SF_EMPTY(%r15)
-	BR_R1USE_R14
+	BR_EX	%r14
 .Lpsw_idle_end:
 
 /*
@@ -1061,7 +1004,7 @@ ENTRY(save_fpu_regs)
 .Lsave_fpu_regs_done:
 	oi	__LC_CPU_FLAGS+7,_CIF_FPU
 .Lsave_fpu_regs_exit:
-	BR_R1USE_R14
+	BR_EX	%r14
 .Lsave_fpu_regs_end:
 EXPORT_SYMBOL(save_fpu_regs)
 
@@ -1107,7 +1050,7 @@ load_fpu_regs:
 .Lload_fpu_regs_done:
 	ni	__LC_CPU_FLAGS+7,255-_CIF_FPU
 .Lload_fpu_regs_exit:
-	BR_R1USE_R14
+	BR_EX	%r14
 .Lload_fpu_regs_end:
 
 .L__critical_end:
@@ -1322,7 +1265,7 @@ cleanup_critical:
 	jl	0f
 	clg	%r9,BASED(.Lcleanup_table+104)	# .Lload_fpu_regs_end
 	jl	.Lcleanup_load_fpu_regs
-0:	BR_R11USE_R14
+0:	BR_EX	%r14
 
 	.align	8
 .Lcleanup_table:
@@ -1358,7 +1301,7 @@ cleanup_critical:
 	ni	__SIE_PROG0C+3(%r9),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	larl	%r9,sie_exit			# skip forward to sie_exit
-	BR_R11USE_R14
+	BR_EX	%r14
 #endif
 
 .Lcleanup_system_call:
@@ -1412,7 +1355,7 @@ cleanup_critical:
 	stg	%r15,56(%r11)		# r15 stack pointer
 	# set new psw address and exit
 	larl	%r9,.Lsysc_do_svc
-	BR_R11USE_R14
+	BR_EX	%r14,%r11
 .Lcleanup_system_call_insn:
 	.quad	system_call
 	.quad	.Lsysc_stmg
@@ -1424,7 +1367,7 @@ cleanup_critical:
 
 .Lcleanup_sysc_tif:
 	larl	%r9,.Lsysc_tif
-	BR_R11USE_R14
+	BR_EX	%r14,%r11
 
 .Lcleanup_sysc_restore:
 	# check if stpt has been executed
@@ -1441,14 +1384,14 @@ cleanup_critical:
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
 1:	lmg	%r8,%r9,__LC_RETURN_PSW
-	BR_R11USE_R14
+	BR_EX	%r14,%r11
 .Lcleanup_sysc_restore_insn:
 	.quad	.Lsysc_exit_timer
 	.quad	.Lsysc_done - 4
 
 .Lcleanup_io_tif:
 	larl	%r9,.Lio_tif
-	BR_R11USE_R14
+	BR_EX	%r14,%r11
 
 .Lcleanup_io_restore:
 	# check if stpt has been executed
@@ -1462,7 +1405,7 @@ cleanup_critical:
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
 1:	lmg	%r8,%r9,__LC_RETURN_PSW
-	BR_R11USE_R14
+	BR_EX	%r14,%r11
 .Lcleanup_io_restore_insn:
 	.quad	.Lio_exit_timer
 	.quad	.Lio_done - 4
@@ -1515,17 +1458,17 @@ cleanup_critical:
 	# prepare return psw
 	nihh	%r8,0xfcfd		# clear irq & wait state bits
 	lg	%r9,48(%r11)		# return from psw_idle
-	BR_R11USE_R14
+	BR_EX	%r14,%r11
 .Lcleanup_idle_insn:
 	.quad	.Lpsw_idle_lpsw
 
 .Lcleanup_save_fpu_regs:
 	larl	%r9,save_fpu_regs
-	BR_R11USE_R14
+	BR_EX	%r14,%r11
 
 .Lcleanup_load_fpu_regs:
 	larl	%r9,load_fpu_regs
-	BR_R11USE_R14
+	BR_EX	%r14,%r11
 
 /*
  * Integer constants
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index e87758f8fbdc..961abfac2c5f 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -58,6 +58,7 @@ void do_notify_resume(struct pt_regs *regs);
 void __init init_IRQ(void);
 void do_IRQ(struct pt_regs *regs, int irq);
 void do_restart(void);
+void __init startup_init_nobss(void);
 void __init startup_init(void);
 void die(struct pt_regs *regs, const char *str);
 int setup_profiling_timer(unsigned int multiplier);
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 38a973ccf501..791cb9000e86 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -40,8 +40,12 @@ ENTRY(startup_continue)
 	stg	%r15,__LC_KERNEL_STACK	# set end of kernel stack
 	aghi	%r15,-160
 #
-# Save ipl parameters, clear bss memory, initialize storage key for kernel pages,
-# and create a kernel NSS if the SAVESYS= parm is defined
+# Early setup functions that may not rely on an initialized bss section,
+# like moving the initrd. Returns with an initialized bss section.
+#
+	brasl	%r14,startup_init_nobss
+#
+# Early machine initialization and detection functions.
 #
 	brasl	%r14,startup_init
 	lpswe	.Lentry-.LPG1(13)	# jump to _stext in primary-space,
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 94f2099bceb0..3d17c41074ca 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -176,10 +176,9 @@ void do_softirq_own_stack(void)
 		new -= STACK_FRAME_OVERHEAD;
 		((struct stack_frame *) new)->back_chain = old;
 		asm volatile("   la    15,0(%0)\n"
-			     "   basr  14,%2\n"
+			     "   brasl 14,__do_softirq\n"
 			     "   la    15,0(%1)\n"
-			     : : "a" (new), "a" (old),
-			         "a" (__do_softirq)
+			     : : "a" (new), "a" (old)
 			     : "0", "1", "2", "3", "4", "5", "14",
 			       "cc", "memory" );
 	} else {
diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
new file mode 100644
index 000000000000..5a286b012043
--- /dev/null
+++ b/arch/s390/kernel/kexec_elf.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ELF loader for kexec_file_load system call.
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <asm/setup.h>
+
+static int kexec_file_add_elf_kernel(struct kimage *image,
+				     struct s390_load_data *data,
+				     char *kernel, unsigned long kernel_len)
+{
+	struct kexec_buf buf;
+	const Elf_Ehdr *ehdr;
+	const Elf_Phdr *phdr;
+	int i, ret;
+
+	ehdr = (Elf_Ehdr *)kernel;
+	buf.image = image;
+
+	phdr = (void *)ehdr + ehdr->e_phoff;
+	for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		buf.buffer = kernel + phdr->p_offset;
+		buf.bufsz = phdr->p_filesz;
+
+		buf.mem = ALIGN(phdr->p_paddr, phdr->p_align);
+		buf.memsz = phdr->p_memsz;
+
+		if (phdr->p_paddr == 0) {
+			data->kernel_buf = buf.buffer;
+			data->memsz += STARTUP_NORMAL_OFFSET;
+
+			buf.buffer += STARTUP_NORMAL_OFFSET;
+			buf.bufsz -= STARTUP_NORMAL_OFFSET;
+
+			buf.mem += STARTUP_NORMAL_OFFSET;
+			buf.memsz -= STARTUP_NORMAL_OFFSET;
+		}
+
+		if (image->type == KEXEC_TYPE_CRASH)
+			buf.mem += crashk_res.start;
+
+		ret = kexec_add_buffer(&buf);
+		if (ret)
+			return ret;
+
+		data->memsz += buf.memsz;
+	}
+
+	return 0;
+}
+
+static void *s390_elf_load(struct kimage *image,
+			   char *kernel, unsigned long kernel_len,
+			   char *initrd, unsigned long initrd_len,
+			   char *cmdline, unsigned long cmdline_len)
+{
+	struct s390_load_data data = {0};
+	const Elf_Ehdr *ehdr;
+	const Elf_Phdr *phdr;
+	size_t size;
+	int i, ret;
+
+	/* image->fobs->probe already checked for valid ELF magic number. */
+	ehdr = (Elf_Ehdr *)kernel;
+
+	if (ehdr->e_type != ET_EXEC ||
+	    ehdr->e_ident[EI_CLASS] != ELFCLASS64 ||
+	    !elf_check_arch(ehdr))
+		return ERR_PTR(-EINVAL);
+
+	if (!ehdr->e_phnum || ehdr->e_phentsize != sizeof(Elf_Phdr))
+		return ERR_PTR(-EINVAL);
+
+	size = ehdr->e_ehsize + ehdr->e_phoff;
+	size += ehdr->e_phentsize * ehdr->e_phnum;
+	if (size > kernel_len)
+		return ERR_PTR(-EINVAL);
+
+	phdr = (void *)ehdr + ehdr->e_phoff;
+	size = ALIGN(size, phdr->p_align);
+	for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+		if (phdr->p_type == PT_INTERP)
+			return ERR_PTR(-EINVAL);
+
+		if (phdr->p_offset > kernel_len)
+			return ERR_PTR(-EINVAL);
+
+		size += ALIGN(phdr->p_filesz, phdr->p_align);
+	}
+
+	if (size > kernel_len)
+		return ERR_PTR(-EINVAL);
+
+	ret = kexec_file_add_elf_kernel(image, &data, kernel, kernel_len);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (!data.memsz)
+		return ERR_PTR(-EINVAL);
+
+	if (initrd) {
+		ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	ret = kexec_file_add_purgatory(image, &data);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return kexec_file_update_kernel(image, &data);
+}
+
+static int s390_elf_probe(const char *buf, unsigned long len)
+{
+	const Elf_Ehdr *ehdr;
+
+	if (len < sizeof(Elf_Ehdr))
+		return -ENOEXEC;
+
+	ehdr = (Elf_Ehdr *)buf;
+
+	/* Only check the ELF magic number here and do proper validity check
+	 * in the loader. Any check here that fails would send the erroneous
+	 * ELF file to the image loader that does not care what it gets.
+	 * (Most likely) causing behavior not intended by the user.
+	 */
+	if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0)
+		return -ENOEXEC;
+
+	return 0;
+}
+
+const struct kexec_file_ops s390_kexec_elf_ops = {
+	.probe = s390_elf_probe,
+	.load = s390_elf_load,
+};
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
new file mode 100644
index 000000000000..3800852595e8
--- /dev/null
+++ b/arch/s390/kernel/kexec_image.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Image loader for kexec_file_load system call.
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <asm/setup.h>
+
+static int kexec_file_add_image_kernel(struct kimage *image,
+				       struct s390_load_data *data,
+				       char *kernel, unsigned long kernel_len)
+{
+	struct kexec_buf buf;
+	int ret;
+
+	buf.image = image;
+
+	buf.buffer = kernel + STARTUP_NORMAL_OFFSET;
+	buf.bufsz = kernel_len - STARTUP_NORMAL_OFFSET;
+
+	buf.mem = STARTUP_NORMAL_OFFSET;
+	if (image->type == KEXEC_TYPE_CRASH)
+		buf.mem += crashk_res.start;
+	buf.memsz = buf.bufsz;
+
+	ret = kexec_add_buffer(&buf);
+
+	data->kernel_buf = kernel;
+	data->memsz += buf.memsz + STARTUP_NORMAL_OFFSET;
+
+	return ret;
+}
+
+static void *s390_image_load(struct kimage *image,
+			     char *kernel, unsigned long kernel_len,
+			     char *initrd, unsigned long initrd_len,
+			     char *cmdline, unsigned long cmdline_len)
+{
+	struct s390_load_data data = {0};
+	int ret;
+
+	ret = kexec_file_add_image_kernel(image, &data, kernel, kernel_len);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (initrd) {
+		ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	ret = kexec_file_add_purgatory(image, &data);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return kexec_file_update_kernel(image, &data);
+}
+
+static int s390_image_probe(const char *buf, unsigned long len)
+{
+	/* Can't reliably tell if an image is valid.  Therefore give the
+	 * user whatever he wants.
+	 */
+	return 0;
+}
+
+const struct kexec_file_ops s390_kexec_image_ops = {
+	.probe = s390_image_probe,
+	.load = s390_image_load,
+};
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
new file mode 100644
index 000000000000..f413f57f8d20
--- /dev/null
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * s390 code for kexec_file_load system call
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/elf.h>
+#include <linux/kexec.h>
+#include <asm/setup.h>
+
+const struct kexec_file_ops * const kexec_file_loaders[] = {
+	&s390_kexec_elf_ops,
+	&s390_kexec_image_ops,
+	NULL,
+};
+
+int *kexec_file_update_kernel(struct kimage *image,
+			      struct s390_load_data *data)
+{
+	unsigned long *loc;
+
+	if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	if (image->cmdline_buf_len)
+		memcpy(data->kernel_buf + COMMAND_LINE_OFFSET,
+		       image->cmdline_buf, image->cmdline_buf_len);
+
+	if (image->type == KEXEC_TYPE_CRASH) {
+		loc = (unsigned long *)(data->kernel_buf + OLDMEM_BASE_OFFSET);
+		*loc = crashk_res.start;
+
+		loc = (unsigned long *)(data->kernel_buf + OLDMEM_SIZE_OFFSET);
+		*loc = crashk_res.end - crashk_res.start + 1;
+	}
+
+	if (image->initrd_buf) {
+		loc = (unsigned long *)(data->kernel_buf + INITRD_START_OFFSET);
+		*loc = data->initrd_load_addr;
+
+		loc = (unsigned long *)(data->kernel_buf + INITRD_SIZE_OFFSET);
+		*loc = image->initrd_buf_len;
+	}
+
+	return NULL;
+}
+
+static int kexec_file_update_purgatory(struct kimage *image)
+{
+	u64 entry, type;
+	int ret;
+
+	if (image->type == KEXEC_TYPE_CRASH) {
+		entry = STARTUP_KDUMP_OFFSET;
+		type = KEXEC_TYPE_CRASH;
+	} else {
+		entry = STARTUP_NORMAL_OFFSET;
+		type = KEXEC_TYPE_DEFAULT;
+	}
+
+	ret = kexec_purgatory_get_set_symbol(image, "kernel_entry", &entry,
+					     sizeof(entry), false);
+	if (ret)
+		return ret;
+
+	ret = kexec_purgatory_get_set_symbol(image, "kernel_type", &type,
+					     sizeof(type), false);
+	if (ret)
+		return ret;
+
+	if (image->type == KEXEC_TYPE_CRASH) {
+		u64 crash_size;
+
+		ret = kexec_purgatory_get_set_symbol(image, "crash_start",
+						     &crashk_res.start,
+						     sizeof(crashk_res.start),
+						     false);
+		if (ret)
+			return ret;
+
+		crash_size = crashk_res.end - crashk_res.start + 1;
+		ret = kexec_purgatory_get_set_symbol(image, "crash_size",
+						     &crash_size,
+						     sizeof(crash_size),
+						     false);
+	}
+	return ret;
+}
+
+int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data)
+{
+	struct kexec_buf buf;
+	int ret;
+
+	buf.image = image;
+
+	data->memsz = ALIGN(data->memsz, PAGE_SIZE);
+	buf.mem = data->memsz;
+	if (image->type == KEXEC_TYPE_CRASH)
+		buf.mem += crashk_res.start;
+
+	ret = kexec_load_purgatory(image, &buf);
+	if (ret)
+		return ret;
+
+	ret = kexec_file_update_purgatory(image);
+	return ret;
+}
+
+int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data,
+			  char *initrd, unsigned long initrd_len)
+{
+	struct kexec_buf buf;
+	int ret;
+
+	buf.image = image;
+
+	buf.buffer = initrd;
+	buf.bufsz = initrd_len;
+
+	data->memsz = ALIGN(data->memsz, PAGE_SIZE);
+	buf.mem = data->memsz;
+	if (image->type == KEXEC_TYPE_CRASH)
+		buf.mem += crashk_res.start;
+	buf.memsz = buf.bufsz;
+
+	data->initrd_load_addr = buf.mem;
+	data->memsz += buf.memsz;
+
+	ret = kexec_add_buffer(&buf);
+	return ret;
+}
+
+/*
+ * The kernel is loaded to a fixed location. Turn off kexec_locate_mem_hole
+ * and provide kbuf->mem by hand.
+ */
+int arch_kexec_walk_mem(struct kexec_buf *kbuf,
+			int (*func)(struct resource *, void *))
+{
+	return 1;
+}
+
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+				     Elf_Shdr *section,
+				     const Elf_Shdr *relsec,
+				     const Elf_Shdr *symtab)
+{
+	Elf_Rela *relas;
+	int i;
+
+	relas = (void *)pi->ehdr + relsec->sh_offset;
+
+	for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) {
+		const Elf_Sym *sym;	/* symbol to relocate */
+		unsigned long addr;	/* final location after relocation */
+		unsigned long val;	/* relocated symbol value */
+		void *loc;		/* tmp location to modify */
+
+		sym = (void *)pi->ehdr + symtab->sh_offset;
+		sym += ELF64_R_SYM(relas[i].r_info);
+
+		if (sym->st_shndx == SHN_UNDEF)
+			return -ENOEXEC;
+
+		if (sym->st_shndx == SHN_COMMON)
+			return -ENOEXEC;
+
+		if (sym->st_shndx >= pi->ehdr->e_shnum &&
+		    sym->st_shndx != SHN_ABS)
+			return -ENOEXEC;
+
+		loc = pi->purgatory_buf;
+		loc += section->sh_offset;
+		loc += relas[i].r_offset;
+
+		val = sym->st_value;
+		if (sym->st_shndx != SHN_ABS)
+			val += pi->sechdrs[sym->st_shndx].sh_addr;
+		val += relas[i].r_addend;
+
+		addr = section->sh_addr + relas[i].r_offset;
+
+		switch (ELF64_R_TYPE(relas[i].r_info)) {
+		case R_390_8:		/* Direct 8 bit.   */
+			*(u8 *)loc = val;
+			break;
+		case R_390_12:		/* Direct 12 bit.  */
+			*(u16 *)loc &= 0xf000;
+			*(u16 *)loc |= val & 0xfff;
+			break;
+		case R_390_16:		/* Direct 16 bit.  */
+			*(u16 *)loc = val;
+			break;
+		case R_390_20:		/* Direct 20 bit.  */
+			*(u32 *)loc &= 0xf00000ff;
+			*(u32 *)loc |= (val & 0xfff) << 16;	/* DL */
+			*(u32 *)loc |= (val & 0xff000) >> 4;	/* DH */
+			break;
+		case R_390_32:		/* Direct 32 bit.  */
+			*(u32 *)loc = val;
+			break;
+		case R_390_64:		/* Direct 64 bit.  */
+			*(u64 *)loc = val;
+			break;
+		case R_390_PC16:	/* PC relative 16 bit.	*/
+			*(u16 *)loc = (val - addr);
+			break;
+		case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
+			*(u16 *)loc = (val - addr) >> 1;
+			break;
+		case R_390_PC32DBL:	/* PC relative 32 bit shifted by 1.  */
+			*(u32 *)loc = (val - addr) >> 1;
+			break;
+		case R_390_PC32:	/* PC relative 32 bit.	*/
+			*(u32 *)loc = (val - addr);
+			break;
+		case R_390_PC64:	/* PC relative 64 bit.	*/
+			*(u64 *)loc = (val - addr);
+			break;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
+				  unsigned long buf_len)
+{
+	/* A kernel must be at least large enough to contain head.S. During
+	 * load memory in head.S will be accessed, e.g. to register the next
+	 * command line. If the next kernel were smaller the current kernel
+	 * will panic at load.
+	 *
+	 * 0x11000 = sizeof(head.S)
+	 */
+	if (buf_len < 0x11000)
+		return -ENOEXEC;
+
+	return kexec_image_probe_default(image, buf, buf_len);
+}
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 82df7d80fab2..27110f3294ed 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -9,13 +9,17 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
+#include <asm/nospec-insn.h>
 #include <asm/ptrace.h>
 #include <asm/export.h>
 
+	GEN_BR_THUNK %r1
+	GEN_BR_THUNK %r14
+
 	.section .kprobes.text, "ax"
 
 ENTRY(ftrace_stub)
-	br	%r14
+	BR_EX	%r14
 
 #define STACK_FRAME_SIZE  (STACK_FRAME_OVERHEAD + __PT_SIZE)
 #define STACK_PTREGS	  (STACK_FRAME_OVERHEAD)
@@ -23,7 +27,7 @@ ENTRY(ftrace_stub)
 #define STACK_PTREGS_PSW  (STACK_PTREGS + __PT_PSW)
 
 ENTRY(_mcount)
-	br	%r14
+	BR_EX	%r14
 
 EXPORT_SYMBOL(_mcount)
 
@@ -53,7 +57,7 @@ ENTRY(ftrace_caller)
 #endif
 	lgr	%r3,%r14
 	la	%r5,STACK_PTREGS(%r15)
-	basr	%r14,%r1
+	BASR_EX	%r14,%r1
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 # The j instruction gets runtime patched to a nop instruction.
 # See ftrace_enable_ftrace_graph_caller.
@@ -68,7 +72,7 @@ ftrace_graph_caller_end:
 #endif
 	lg	%r1,(STACK_PTREGS_PSW+8)(%r15)
 	lmg	%r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
-	br	%r1
+	BR_EX	%r1
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
@@ -81,6 +85,6 @@ ENTRY(return_to_handler)
 	aghi	%r15,STACK_FRAME_OVERHEAD
 	lgr	%r14,%r2
 	lmg	%r2,%r5,32(%r15)
-	br	%r14
+	BR_EX	%r14
 
 #endif
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 5a83be955c70..0dc8ac8548ee 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -465,11 +465,11 @@ int module_finalize(const Elf_Ehdr *hdr,
 			apply_alternatives(aseg, aseg + s->sh_size);
 
 		if (IS_ENABLED(CONFIG_EXPOLINE) &&
-		    (!strcmp(".nospec_call_table", secname)))
+		    (!strncmp(".s390_indirect", secname, 14)))
 			nospec_revert(aseg, aseg + s->sh_size);
 
 		if (IS_ENABLED(CONFIG_EXPOLINE) &&
-		    (!strcmp(".nospec_return_table", secname)))
+		    (!strncmp(".s390_return", secname, 12)))
 			nospec_revert(aseg, aseg + s->sh_size);
 	}
 
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index f236ce8757e8..18ae7b9c71d6 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -36,31 +36,13 @@ early_param("nospec", nospec_setup_early);
 static int __init nospec_report(void)
 {
 	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
-		pr_info("Spectre V2 mitigation: execute trampolines.\n");
+		pr_info("Spectre V2 mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
-		pr_info("Spectre V2 mitigation: limited branch prediction.\n");
+		pr_info("Spectre V2 mitigation: limited branch prediction\n");
 	return 0;
 }
 arch_initcall(nospec_report);
 
-#ifdef CONFIG_SYSFS
-ssize_t cpu_show_spectre_v1(struct device *dev,
-			    struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
-}
-
-ssize_t cpu_show_spectre_v2(struct device *dev,
-			    struct device_attribute *attr, char *buf)
-{
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
-		return sprintf(buf, "Mitigation: execute trampolines\n");
-	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
-		return sprintf(buf, "Mitigation: limited branch prediction.\n");
-	return sprintf(buf, "Vulnerable\n");
-}
-#endif
-
 #ifdef CONFIG_EXPOLINE
 
 int nospec_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);
@@ -111,7 +93,6 @@ static void __init_or_module __nospec_revert(s32 *start, s32 *end)
 	s32 *epo;
 
 	/* Second part of the instruction replace is always a nop */
-	memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x00, 0x00 }, 4);
 	for (epo = start; epo < end; epo++) {
 		instr = (u8 *) epo + *epo;
 		if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x04)
@@ -132,18 +113,34 @@ static void __init_or_module __nospec_revert(s32 *start, s32 *end)
 			br = thunk + (*(int *)(thunk + 2)) * 2;
 		else
 			continue;
-		if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0)
+		/* Check for unconditional branch 0x07f? or 0x47f???? */
+		if ((br[0] & 0xbf) != 0x07 || (br[1] & 0xf0) != 0xf0)
 			continue;
+
+		memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x07, 0x00 }, 4);
 		switch (type) {
 		case BRCL_EXPOLINE:
-			/* brcl to thunk, replace with br + nop */
 			insnbuf[0] = br[0];
 			insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+			if (br[0] == 0x47) {
+				/* brcl to b, replace with bc + nopr */
+				insnbuf[2] = br[2];
+				insnbuf[3] = br[3];
+			} else {
+				/* brcl to br, replace with bcr + nop */
+			}
 			break;
 		case BRASL_EXPOLINE:
-			/* brasl to thunk, replace with basr + nop */
-			insnbuf[0] = 0x0d;
 			insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+			if (br[0] == 0x47) {
+				/* brasl to b, replace with bas + nopr */
+				insnbuf[0] = 0x4d;
+				insnbuf[2] = br[2];
+				insnbuf[3] = br[3];
+			} else {
+				/* brasl to br, replace with basr + nop */
+				insnbuf[0] = 0x0d;
+			}
 			break;
 		}
 
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
new file mode 100644
index 000000000000..8affad5f18cb
--- /dev/null
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/device.h>
+#include <linux/cpu.h>
+#include <asm/facility.h>
+#include <asm/nospec-branch.h>
+
+ssize_t cpu_show_spectre_v1(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+		return sprintf(buf, "Mitigation: execute trampolines\n");
+	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
+		return sprintf(buf, "Mitigation: limited branch prediction\n");
+	return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index c5bc3f209652..feebb2944882 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -123,7 +123,7 @@ CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV, 0x00a1);
 CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1);
 CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2);
 CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3);
-CPUMF_EVENT_ATTR(cf_z13, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z13, L1D_RO_EXCL_WRITES, 0x0080);
 CPUMF_EVENT_ATTR(cf_z13, DTLB1_WRITES, 0x0081);
 CPUMF_EVENT_ATTR(cf_z13, DTLB1_MISSES, 0x0082);
 CPUMF_EVENT_ATTR(cf_z13, DTLB1_HPAGE_WRITES, 0x0083);
@@ -179,7 +179,7 @@ CPUMF_EVENT_ATTR(cf_z13, TX_C_TABORT_NO_SPECIAL, 0x00db);
 CPUMF_EVENT_ATTR(cf_z13, TX_C_TABORT_SPECIAL, 0x00dc);
 CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
-CPUMF_EVENT_ATTR(cf_z14, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z14, L1D_RO_EXCL_WRITES, 0x0080);
 CPUMF_EVENT_ATTR(cf_z14, DTLB2_WRITES, 0x0081);
 CPUMF_EVENT_ATTR(cf_z14, DTLB2_MISSES, 0x0082);
 CPUMF_EVENT_ATTR(cf_z14, DTLB2_HPAGE_WRITES, 0x0083);
@@ -371,7 +371,7 @@ static struct attribute *cpumcf_zec12_pmu_event_attr[] __initdata = {
 };
 
 static struct attribute *cpumcf_z13_pmu_event_attr[] __initdata = {
-	CPUMF_EVENT_PTR(cf_z13, L1D_WRITES_RO_EXCL),
+	CPUMF_EVENT_PTR(cf_z13, L1D_RO_EXCL_WRITES),
 	CPUMF_EVENT_PTR(cf_z13, DTLB1_WRITES),
 	CPUMF_EVENT_PTR(cf_z13, DTLB1_MISSES),
 	CPUMF_EVENT_PTR(cf_z13, DTLB1_HPAGE_WRITES),
@@ -431,7 +431,7 @@ static struct attribute *cpumcf_z13_pmu_event_attr[] __initdata = {
 };
 
 static struct attribute *cpumcf_z14_pmu_event_attr[] __initdata = {
-	CPUMF_EVENT_PTR(cf_z14, L1D_WRITES_RO_EXCL),
+	CPUMF_EVENT_PTR(cf_z14, L1D_RO_EXCL_WRITES),
 	CPUMF_EVENT_PTR(cf_z14, DTLB2_WRITES),
 	CPUMF_EVENT_PTR(cf_z14, DTLB2_MISSES),
 	CPUMF_EVENT_PTR(cf_z14, DTLB2_HPAGE_WRITES),
@@ -583,6 +583,7 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 		model = cpumcf_z13_pmu_event_attr;
 		break;
 	case 0x3906:
+	case 0x3907:
 		model = cpumcf_z14_pmu_event_attr;
 		break;
 	default:
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 1c9ddd7aa5ec..0292d68e7dde 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -753,6 +753,10 @@ static int __hw_perf_event_init(struct perf_event *event)
 	 */
 	rate = 0;
 	if (attr->freq) {
+		if (!attr->sample_freq) {
+			err = -EINVAL;
+			goto out;
+		}
 		rate = freq_to_sample_rate(&si, attr->sample_freq);
 		rate = hw_limit_rate(&si, rate);
 		attr->freq = 0;
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 70576a2f69cf..6e758bb6cd29 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -29,6 +29,7 @@
 #include <linux/random.h>
 #include <linux/export.h>
 #include <linux/init_task.h>
+#include <asm/cpu_mf.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/vtimer.h>
@@ -48,6 +49,15 @@ void flush_thread(void)
 {
 }
 
+void arch_setup_new_exec(void)
+{
+	if (S390_lowcore.current_pid != current->pid) {
+		S390_lowcore.current_pid = current->pid;
+		if (test_facility(40))
+			lpp(&S390_lowcore.lpp);
+	}
+}
+
 void arch_release_task_struct(struct task_struct *tsk)
 {
 	runtime_instr_release(tsk);
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 73cc3750f0d3..7f14adf512c6 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -7,8 +7,11 @@
 
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
 #include <asm/sigp.h>
 
+	GEN_BR_THUNK %r9
+
 #
 # Issue "store status" for the current CPU to its prefix page
 # and call passed function afterwards
@@ -67,9 +70,9 @@ ENTRY(store_status)
 	st	%r4,0(%r1)
 	st	%r5,4(%r1)
 	stg	%r2,8(%r1)
-	lgr	%r1,%r2
+	lgr	%r9,%r2
 	lgr	%r2,%r3
-	br	%r1
+	BR_EX	%r9
 
 	.section .bss
 	.align	8
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index fc3b4aa185cc..d82a9ec64ea9 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -821,6 +821,7 @@ static int __init setup_hwcaps(void)
 		strcpy(elf_platform, "z13");
 		break;
 	case 0x3906:
+	case 0x3907:
 		strcpy(elf_platform, "z14");
 		break;
 	}
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index e99187149f17..a049a7b9d6e8 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -13,6 +13,7 @@
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
 #include <asm/sigp.h>
 
 /*
@@ -24,6 +25,8 @@
  * (see below) in the resume process.
  * This function runs with disabled interrupts.
  */
+	GEN_BR_THUNK %r14
+
 	.section .text
 ENTRY(swsusp_arch_suspend)
 	stmg	%r6,%r15,__SF_GPRS(%r15)
@@ -103,7 +106,7 @@ ENTRY(swsusp_arch_suspend)
 	spx	0x318(%r1)
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
 	lghi	%r2,0
-	br	%r14
+	BR_EX	%r14
 
 /*
  * Restore saved memory image to correct place and restore register context.
@@ -197,11 +200,10 @@ pgm_check_entry:
 	larl	%r15,init_thread_union
 	ahi	%r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)
 	larl	%r2,.Lpanic_string
-	larl	%r3,sclp_early_printk
 	lghi	%r1,0
 	sam31
 	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
-	basr	%r14,%r3
+	brasl	%r14,sclp_early_printk
 	larl	%r3,.Ldisabled_wait_31
 	lpsw	0(%r3)
 4:
@@ -267,7 +269,7 @@ restore_registers:
 	/* Return 0 */
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
 	lghi	%r2,0
-	br	%r14
+	BR_EX	%r14
 
 	.section .data..nosave,"aw",@progbits
 	.align	8
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index b38d48464368..8b210ead7956 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -388,3 +388,4 @@
 378  common	s390_guarded_storage	sys_s390_guarded_storage	compat_sys_s390_guarded_storage
 379  common	statx			sys_statx			compat_sys_statx
 380  common	s390_sthyi		sys_s390_sthyi			compat_sys_s390_sthyi
+381  common	kexec_file_load		sys_kexec_file_load		compat_sys_kexec_file_load
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index fc7e04c2195b..54f5496913fa 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -294,21 +294,9 @@ static int sysinfo_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int sysinfo_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sysinfo_show, NULL);
-}
-
-static const struct file_operations sysinfo_fops = {
-	.open		= sysinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init sysinfo_create_proc(void)
 {
-	proc_create("sysinfo", 0444, NULL, &sysinfo_fops);
+	proc_create_single("sysinfo", 0444, NULL, sysinfo_show);
 	return 0;
 }
 device_initcall(sysinfo_create_proc);
@@ -386,18 +374,6 @@ static const struct seq_operations service_level_seq_ops = {
 	.show		= service_level_show
 };
 
-static int service_level_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &service_level_seq_ops);
-}
-
-static const struct file_operations service_level_ops = {
-	.open		= service_level_open,
-	.read		= seq_read,
-	.llseek 	= seq_lseek,
-	.release	= seq_release
-};
-
 static void service_level_vm_print(struct seq_file *m,
 				   struct service_level *slr)
 {
@@ -420,7 +396,7 @@ static struct service_level service_level_vm = {
 
 static __init int create_proc_service_level(void)
 {
-	proc_create("service_levels", 0, NULL, &service_level_ops);
+	proc_create_seq("service_levels", 0, NULL, &service_level_seq_ops);
 	if (MACHINE_IS_VM)
 		register_service_level(&service_level_vm);
 	return 0;
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index a5297a22bc1e..8003b38c1688 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -44,14 +44,8 @@ int is_valid_bugaddr(unsigned long addr)
 
 void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 {
-	siginfo_t info;
-
 	if (user_mode(regs)) {
-		info.si_signo = si_signo;
-		info.si_errno = 0;
-		info.si_code = si_code;
-		info.si_addr = get_trap_ip(regs);
-		force_sig_info(si_signo, &info, current);
+		force_sig_fault(si_signo, si_code, get_trap_ip(regs), current);
 		report_user_fault(regs, si_signo, 0);
         } else {
                 const struct exception_table_entry *fixup;
@@ -80,18 +74,12 @@ NOKPROBE_SYMBOL(do_trap);
 
 void do_per_trap(struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0, SIGTRAP) == NOTIFY_STOP)
 		return;
 	if (!current->ptrace)
 		return;
-	info.si_signo = SIGTRAP;
-	info.si_errno = 0;
-	info.si_code = TRAP_HWBKPT;
-	info.si_addr =
-		(void __force __user *) current->thread.per_event.address;
-	force_sig_info(SIGTRAP, &info, current);
+	force_sig_fault(SIGTRAP, TRAP_HWBKPT,
+		(void __force __user *) current->thread.per_event.address, current);
 }
 NOKPROBE_SYMBOL(do_per_trap);
 
@@ -165,7 +153,6 @@ void translation_exception(struct pt_regs *regs)
 
 void illegal_op(struct pt_regs *regs)
 {
-	siginfo_t info;
         __u8 opcode[6];
 	__u16 __user *location;
 	int is_uprobe_insn = 0;
@@ -177,13 +164,9 @@ void illegal_op(struct pt_regs *regs)
 		if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
 			return;
 		if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
-			if (current->ptrace) {
-				info.si_signo = SIGTRAP;
-				info.si_errno = 0;
-				info.si_code = TRAP_BRKPT;
-				info.si_addr = location;
-				force_sig_info(SIGTRAP, &info, current);
-			} else
+			if (current->ptrace)
+				force_sig_fault(SIGTRAP, TRAP_BRKPT, location, current);
+			else
 				signal = SIGILL;
 #ifdef CONFIG_UPROBES
 		} else if (*((__u16 *) opcode) == UPROBE_SWBP_INSN) {
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
index d9d1f512f019..5007fac01bb5 100644
--- a/arch/s390/kernel/uprobes.c
+++ b/arch/s390/kernel/uprobes.c
@@ -150,6 +150,15 @@ unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
 	return orig;
 }
 
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+			     struct pt_regs *regs)
+{
+	if (ctx == RP_CHECK_CHAIN_CALL)
+		return user_stack_pointer(regs) <= ret->stack;
+	else
+		return user_stack_pointer(regs) < ret->stack;
+}
+
 /* Instruction Emulation */
 
 static void adjust_psw_addr(psw_t *psw, unsigned long len)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 08d12cfaf091..f0414f52817b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -82,10 +82,10 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
-		VMLINUX_SYMBOL(_sinittext) = . ;
+		_sinittext = .;
 		INIT_TEXT
 		. = ALIGN(PAGE_SIZE);
-		VMLINUX_SYMBOL(_einittext) = . ;
+		_einittext = .;
 	}
 
 	/*
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ebfa0442e569..a3bce0e84346 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -26,7 +26,6 @@
 #include <asm/gmap.h>
 #include <asm/io.h>
 #include <asm/ptrace.h>
-#include <asm/compat.h>
 #include <asm/sclp.h>
 #include "gaccess.h"
 #include "kvm-s390.h"
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 8961e3970901..969882b54266 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -578,7 +578,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 
 	gpa = READ_ONCE(scb_o->itdba) & ~0xffUL;
 	if (gpa && (scb_s->ecb & ECB_TE)) {
-		if (!(gpa & ~0x1fffU)) {
+		if (!(gpa & ~0x1fffUL)) {
 			rc = set_validity_icpt(scb_s, 0x0080U);
 			goto unpin;
 		}
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 9bfe0802684b..57ab40188d4b 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -8,3 +8,6 @@ obj-y += mem.o xor.o
 lib-$(CONFIG_SMP) += spinlock.o
 lib-$(CONFIG_KPROBES) += probes.o
 lib-$(CONFIG_UPROBES) += probes.o
+
+chkbss := mem.o
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 495c9c4bacc7..2311f15be9cf 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -7,6 +7,9 @@
 
 #include <linux/linkage.h>
 #include <asm/export.h>
+#include <asm/nospec-insn.h>
+
+	GEN_BR_THUNK %r14
 
 /*
  * void *memmove(void *dest, const void *src, size_t n)
@@ -33,14 +36,14 @@ ENTRY(memmove)
 .Lmemmove_forward_remainder:
 	larl	%r5,.Lmemmove_mvc
 	ex	%r4,0(%r5)
-	br	%r14
+	BR_EX	%r14
 .Lmemmove_reverse:
 	ic	%r0,0(%r4,%r3)
 	stc	%r0,0(%r4,%r1)
 	brctg	%r4,.Lmemmove_reverse
 	ic	%r0,0(%r4,%r3)
 	stc	%r0,0(%r4,%r1)
-	br	%r14
+	BR_EX	%r14
 .Lmemmove_mvc:
 	mvc	0(1,%r1),0(%r3)
 EXPORT_SYMBOL(memmove)
@@ -77,7 +80,7 @@ ENTRY(memset)
 .Lmemset_clear_remainder:
 	larl	%r3,.Lmemset_xc
 	ex	%r4,0(%r3)
-	br	%r14
+	BR_EX	%r14
 .Lmemset_fill:
 	cghi	%r4,1
 	lgr	%r1,%r2
@@ -95,10 +98,10 @@ ENTRY(memset)
 	stc	%r3,0(%r1)
 	larl	%r5,.Lmemset_mvc
 	ex	%r4,0(%r5)
-	br	%r14
+	BR_EX	%r14
 .Lmemset_fill_exit:
 	stc	%r3,0(%r1)
-	br	%r14
+	BR_EX	%r14
 .Lmemset_xc:
 	xc	0(1,%r1),0(%r1)
 .Lmemset_mvc:
@@ -121,7 +124,7 @@ ENTRY(memcpy)
 .Lmemcpy_remainder:
 	larl	%r5,.Lmemcpy_mvc
 	ex	%r4,0(%r5)
-	br	%r14
+	BR_EX	%r14
 .Lmemcpy_loop:
 	mvc	0(256,%r1),0(%r3)
 	la	%r1,256(%r1)
@@ -159,10 +162,10 @@ ENTRY(__memset\bits)
 	\insn	%r3,0(%r1)
 	larl	%r5,.L__memset_mvc\bits
 	ex	%r4,0(%r5)
-	br	%r14
+	BR_EX	%r14
 .L__memset_exit\bits:
 	\insn	%r3,0(%r2)
-	br	%r14
+	BR_EX	%r14
 .L__memset_mvc\bits:
 	mvc	\bytes(1,%r1),0(%r1)
 .endm
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 93faeca52284..e074480d3598 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -265,14 +265,10 @@ void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault)
  */
 static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
 {
-	struct siginfo si;
-
 	report_user_fault(regs, SIGSEGV, 1);
-	si.si_signo = SIGSEGV;
-	si.si_errno = 0;
-	si.si_code = si_code;
-	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
-	force_sig_info(SIGSEGV, &si, current);
+	force_sig_fault(SIGSEGV, si_code,
+			(void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK),
+			current);
 }
 
 static noinline void do_no_context(struct pt_regs *regs)
@@ -316,18 +312,13 @@ static noinline void do_low_address(struct pt_regs *regs)
 
 static noinline void do_sigbus(struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
-	struct siginfo si;
-
 	/*
 	 * Send a sigbus, regardless of whether we were in kernel
 	 * or user mode.
 	 */
-	si.si_signo = SIGBUS;
-	si.si_errno = 0;
-	si.si_code = BUS_ADRERR;
-	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
-	force_sig_info(SIGBUS, &si, tsk);
+	force_sig_fault(SIGBUS, BUS_ADRERR,
+			(void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK),
+			current);
 }
 
 static noinline int signal_return(struct pt_regs *regs)
diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile
index e0d5f245e42b..e2b85ffdbb0c 100644
--- a/arch/s390/net/Makefile
+++ b/arch/s390/net/Makefile
@@ -3,3 +3,4 @@
 # Arch-specific network modules
 #
 obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+obj-$(CONFIG_HAVE_PNETID) += pnet.o
diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S
index 25bb4643c4f4..9f794869c1b0 100644
--- a/arch/s390/net/bpf_jit.S
+++ b/arch/s390/net/bpf_jit.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/nospec-insn.h>
 #include "bpf_jit.h"
 
 /*
@@ -54,7 +55,7 @@ ENTRY(sk_load_##NAME##_pos);						\
 	clg	%r3,STK_OFF_HLEN(%r15);	/* Offset + SIZE > hlen? */	\
 	jh	sk_load_##NAME##_slow;					\
 	LOAD	%r14,-SIZE(%r3,%r12);	/* Get data from skb */		\
-	b	OFF_OK(%r6);		/* Return */			\
+	B_EX	OFF_OK,%r6;		/* Return */			\
 									\
 sk_load_##NAME##_slow:;							\
 	lgr	%r2,%r7;		/* Arg1 = skb pointer */	\
@@ -64,11 +65,14 @@ sk_load_##NAME##_slow:;							\
 	brasl	%r14,skb_copy_bits;	/* Get data from skb */		\
 	LOAD	%r14,STK_OFF_TMP(%r15);	/* Load from temp bufffer */	\
 	ltgr	%r2,%r2;		/* Set cc to (%r2 != 0) */	\
-	br	%r6;			/* Return */
+	BR_EX	%r6;			/* Return */
 
 sk_load_common(word, 4, llgf)	/* r14 = *(u32 *) (skb->data+offset) */
 sk_load_common(half, 2, llgh)	/* r14 = *(u16 *) (skb->data+offset) */
 
+	GEN_BR_THUNK %r6
+	GEN_B_THUNK OFF_OK,%r6
+
 /*
  * Load 1 byte from SKB (optimized version)
  */
@@ -80,7 +84,7 @@ ENTRY(sk_load_byte_pos)
 	clg	%r3,STK_OFF_HLEN(%r15)	# Offset >= hlen?
 	jnl	sk_load_byte_slow
 	llgc	%r14,0(%r3,%r12)	# Get byte from skb
-	b	OFF_OK(%r6)		# Return OK
+	B_EX	OFF_OK,%r6		# Return OK
 
 sk_load_byte_slow:
 	lgr	%r2,%r7			# Arg1 = skb pointer
@@ -90,7 +94,7 @@ sk_load_byte_slow:
 	brasl	%r14,skb_copy_bits	# Get data from skb
 	llgc	%r14,STK_OFF_TMP(%r15)	# Load result from temp buffer
 	ltgr	%r2,%r2			# Set cc to (%r2 != 0)
-	br	%r6			# Return cc
+	BR_EX	%r6			# Return cc
 
 #define sk_negative_common(NAME, SIZE, LOAD)				\
 sk_load_##NAME##_slow_neg:;						\
@@ -104,7 +108,7 @@ sk_load_##NAME##_slow_neg:;						\
 	jz	bpf_error;						\
 	LOAD	%r14,0(%r2);		/* Get data from pointer */	\
 	xr	%r3,%r3;		/* Set cc to zero */		\
-	br	%r6;			/* Return cc */
+	BR_EX	%r6;			/* Return cc */
 
 sk_negative_common(word, 4, llgf)
 sk_negative_common(half, 2, llgh)
@@ -113,4 +117,4 @@ sk_negative_common(byte, 1, llgc)
 bpf_error:
 # force a return 0 from jit handler
 	ltgr	%r15,%r15	# Set condition code
-	br	%r6
+	BR_EX	%r6
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 78a19c93b380..dd2bcf0e7d00 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -25,6 +25,8 @@
 #include <linux/bpf.h>
 #include <asm/cacheflush.h>
 #include <asm/dis.h>
+#include <asm/facility.h>
+#include <asm/nospec-branch.h>
 #include <asm/set_memory.h>
 #include "bpf_jit.h"
 
@@ -41,6 +43,8 @@ struct bpf_jit {
 	int base_ip;		/* Base address for literal pool */
 	int ret0_ip;		/* Address of return 0 */
 	int exit_ip;		/* Address of exit */
+	int r1_thunk_ip;	/* Address of expoline thunk for 'br %r1' */
+	int r14_thunk_ip;	/* Address of expoline thunk for 'br %r14' */
 	int tail_call_start;	/* Tail call start offset */
 	int labels[1];		/* Labels for local jumps */
 };
@@ -250,6 +254,19 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	REG_SET_SEEN(b2);					\
 })
 
+#define EMIT6_PCREL_RILB(op, b, target)				\
+({								\
+	int rel = (target - jit->prg) / 2;			\
+	_EMIT6(op | reg_high(b) << 16 | rel >> 16, rel & 0xffff);	\
+	REG_SET_SEEN(b);					\
+})
+
+#define EMIT6_PCREL_RIL(op, target)				\
+({								\
+	int rel = (target - jit->prg) / 2;			\
+	_EMIT6(op | rel >> 16, rel & 0xffff);			\
+})
+
 #define _EMIT6_IMM(op, imm)					\
 ({								\
 	unsigned int __imm = (imm);				\
@@ -469,8 +486,45 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 	EMIT4(0xb9040000, REG_2, BPF_REG_0);
 	/* Restore registers */
 	save_restore_regs(jit, REGS_RESTORE, stack_depth);
+	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+		jit->r14_thunk_ip = jit->prg;
+		/* Generate __s390_indirect_jump_r14 thunk */
+		if (test_facility(35)) {
+			/* exrl %r0,.+10 */
+			EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10);
+		} else {
+			/* larl %r1,.+14 */
+			EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
+			/* ex 0,0(%r1) */
+			EMIT4_DISP(0x44000000, REG_0, REG_1, 0);
+		}
+		/* j . */
+		EMIT4_PCREL(0xa7f40000, 0);
+	}
 	/* br %r14 */
 	_EMIT2(0x07fe);
+
+	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable &&
+	    (jit->seen & SEEN_FUNC)) {
+		jit->r1_thunk_ip = jit->prg;
+		/* Generate __s390_indirect_jump_r1 thunk */
+		if (test_facility(35)) {
+			/* exrl %r0,.+10 */
+			EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10);
+			/* j . */
+			EMIT4_PCREL(0xa7f40000, 0);
+			/* br %r1 */
+			_EMIT2(0x07f1);
+		} else {
+			/* larl %r1,.+14 */
+			EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
+			/* ex 0,S390_lowcore.br_r1_tampoline */
+			EMIT4_DISP(0x44000000, REG_0, REG_0,
+				   offsetof(struct lowcore, br_r1_trampoline));
+			/* j . */
+			EMIT4_PCREL(0xa7f40000, 0);
+		}
+	}
 }
 
 /*
@@ -966,8 +1020,13 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		/* lg %w1,<d(imm)>(%l) */
 		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
 			      EMIT_CONST_U64(func));
-		/* basr %r14,%w1 */
-		EMIT2(0x0d00, REG_14, REG_W1);
+		if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+			/* brasl %r14,__s390_indirect_jump_r1 */
+			EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
+		} else {
+			/* basr %r14,%w1 */
+			EMIT2(0x0d00, REG_14, REG_W1);
+		}
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
 		if ((jit->seen & SEEN_SKB) &&
diff --git a/arch/s390/net/pnet.c b/arch/s390/net/pnet.c
new file mode 100644
index 000000000000..e22f1b10a6c7
--- /dev/null
+++ b/arch/s390/net/pnet.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  IBM System z PNET ID Support
+ *
+ *    Copyright IBM Corp. 2018
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <asm/ccwgroup.h>
+#include <asm/ccwdev.h>
+#include <asm/pnet.h>
+
+/*
+ * Get the PNETIDs from a device.
+ * s390 hardware supports the definition of a so-called Physical Network
+ * Identifier (short PNETID) per network device port. These PNETIDs can be
+ * used to identify network devices that are attached to the same physical
+ * network (broadcast domain).
+ *
+ * The device can be
+ * - a ccwgroup device with all bundled subchannels having the same PNETID
+ * - a PCI attached network device
+ *
+ * Returns:
+ * 0:		PNETIDs extracted from device.
+ * -ENOMEM:	No memory to extract utility string.
+ * -EOPNOTSUPP: Device type without utility string support
+ */
+static int pnet_ids_by_device(struct device *dev, u8 *pnetids)
+{
+	memset(pnetids, 0, PNETIDS_LEN);
+	if (dev_is_ccwgroup(dev)) {
+		struct ccwgroup_device *gdev = to_ccwgroupdev(dev);
+		u8 *util_str;
+
+		util_str = ccw_device_get_util_str(gdev->cdev[0], 0);
+		if (!util_str)
+			return -ENOMEM;
+		memcpy(pnetids, util_str, PNETIDS_LEN);
+		kfree(util_str);
+		return 0;
+	}
+	if (dev_is_pci(dev)) {
+		struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
+
+		memcpy(pnetids, zdev->util_str, sizeof(zdev->util_str));
+		return 0;
+	}
+	return -EOPNOTSUPP;
+}
+
+/*
+ * Extract the pnetid for a device port.
+ *
+ * Return 0 if a pnetid is found and -ENOENT otherwise.
+ */
+int pnet_id_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid)
+{
+	u8 pnetids[MAX_PNETID_PORTS][MAX_PNETID_LEN];
+	static const u8 zero[MAX_PNETID_LEN] = { 0 };
+	int rc = 0;
+
+	if (!dev || port >= MAX_PNETID_PORTS)
+		return -ENOENT;
+
+	if (!pnet_ids_by_device(dev, (u8 *)pnetids) &&
+	    memcmp(pnetids[port], zero, MAX_PNETID_LEN))
+		memcpy(pnetid, pnetids[port], MAX_PNETID_LEN);
+	else
+		rc = -ENOENT;
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnet_id_by_dev_port);
+
+MODULE_DESCRIPTION("pnetid determination from utility strings");
+MODULE_LICENSE("GPL");
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 93cd0f1ca12b..19b2d2a9b43d 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -19,7 +19,6 @@
 #include <linux/uaccess.h>
 #include <asm/pci_debug.h>
 #include <asm/pci_clp.h>
-#include <asm/compat.h>
 #include <asm/clp.h>
 #include <uapi/asm/clp.h>
 
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 2d15d84c20ed..d387a0fbdd7e 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -668,15 +668,6 @@ void zpci_dma_exit(void)
 	kmem_cache_destroy(dma_region_table_cache);
 }
 
-#define PREALLOC_DMA_DEBUG_ENTRIES	(1 << 16)
-
-static int __init dma_debug_do_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-	return 0;
-}
-fs_initcall(dma_debug_do_init);
-
 const struct dma_map_ops s390_pci_dma_ops = {
 	.alloc		= s390_dma_alloc,
 	.free		= s390_dma_free,
@@ -685,8 +676,6 @@ const struct dma_map_ops s390_pci_dma_ops = {
 	.map_page	= s390_dma_map_pages,
 	.unmap_page	= s390_dma_unmap_pages,
 	.mapping_error	= s390_mapping_error,
-	/* if we support direct DMA this must be conditional */
-	.is_phys	= 0,
 	/* dma_supported is unconditionally true without a callback */
 };
 EXPORT_SYMBOL_GPL(s390_pci_dma_ops);
diff --git a/arch/s390/purgatory/.gitignore b/arch/s390/purgatory/.gitignore
new file mode 100644
index 000000000000..e9e66f178a6d
--- /dev/null
+++ b/arch/s390/purgatory/.gitignore
@@ -0,0 +1,2 @@
+kexec-purgatory.c
+purgatory.ro
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
new file mode 100644
index 000000000000..1ace023cbdce
--- /dev/null
+++ b/arch/s390/purgatory/Makefile
@@ -0,0 +1,37 @@
+# SPDX-License-Identifier: GPL-2.0
+
+OBJECT_FILES_NON_STANDARD := y
+
+purgatory-y := head.o purgatory.o string.o sha256.o mem.o
+
+targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
+PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
+
+$(obj)/sha256.o: $(srctree)/lib/sha256.c
+	$(call if_changed_rule,cc_o_c)
+
+$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S
+	$(call if_changed_rule,as_o_S)
+
+$(obj)/string.o: $(srctree)/arch/s390/lib/string.c
+	$(call if_changed_rule,cc_o_c)
+
+LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
+LDFLAGS_purgatory.ro += -z nodefaultlib
+KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
+KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
+KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
+KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+
+$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
+		$(call if_changed,ld)
+
+CMD_BIN2C = $(objtree)/scripts/basic/bin2c
+quiet_cmd_bin2c = BIN2C   $@
+      cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
+
+$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
+	$(call if_changed,bin2c)
+
+obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += kexec-purgatory.o
diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S
new file mode 100644
index 000000000000..660c96a05a9b
--- /dev/null
+++ b/arch/s390/purgatory/head.S
@@ -0,0 +1,279 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Purgatory setup code
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/page.h>
+#include <asm/sigp.h>
+
+/* The purgatory is the code running between two kernels. It's main purpose
+ * is to verify that the next kernel was not corrupted after load and to
+ * start it.
+ *
+ * If the next kernel is a crash kernel there are some peculiarities to
+ * consider:
+ *
+ * First the purgatory is called twice. Once only to verify the
+ * sha digest. So if the crash kernel got corrupted the old kernel can try
+ * to trigger a stand-alone dumper. And once to actually load the crash kernel.
+ *
+ * Second the purgatory also has to swap the crash memory region with its
+ * destination at address 0. As the purgatory is part of crash memory this
+ * requires some finesse. The tactic here is that the purgatory first copies
+ * itself to the end of the destination and then swaps the rest of the
+ * memory running from there.
+ */
+
+#define bufsz purgatory_end-stack
+
+.macro MEMCPY dst,src,len
+	lgr	%r0,\dst
+	lgr	%r1,\len
+	lgr	%r2,\src
+	lgr	%r3,\len
+
+20:	mvcle	%r0,%r2,0
+	jo	20b
+.endm
+
+.macro MEMSWAP dst,src,buf,len
+10:	cghi	\len,bufsz
+	jh	11f
+	lgr	%r4,\len
+	j	12f
+11:	lghi	%r4,bufsz
+
+12:	MEMCPY	\buf,\dst,%r4
+	MEMCPY	\dst,\src,%r4
+	MEMCPY	\src,\buf,%r4
+
+	agr	\dst,%r4
+	agr	\src,%r4
+	sgr	\len,%r4
+
+	cghi	\len,0
+	jh	10b
+.endm
+
+.macro START_NEXT_KERNEL base
+	lg	%r4,kernel_entry-\base(%r13)
+	lg	%r5,load_psw_mask-\base(%r13)
+	ogr	%r4,%r5
+	stg	%r4,0(%r0)
+
+	xgr	%r0,%r0
+	diag	%r0,%r0,0x308
+.endm
+
+.text
+.align PAGE_SIZE
+ENTRY(purgatory_start)
+	/* The purgatory might be called after a diag308 so better set
+	 * architecture and addressing mode.
+	 */
+	lhi	%r1,1
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
+	sam64
+
+	larl	%r5,gprregs
+	stmg	%r6,%r15,0(%r5)
+
+	basr	%r13,0
+.base_crash:
+
+	/* Setup stack */
+	larl	%r15,purgatory_end
+	aghi	%r15,-160
+
+	/* If the next kernel is KEXEC_TYPE_CRASH the purgatory is called
+	 * directly with a flag passed in %r2 whether the purgatory shall do
+	 * checksum verification only (%r2 = 0 -> verification only).
+	 *
+	 * Check now and preserve over C function call by storing in
+	 * %r10 whith
+	 *	1 -> checksum verification only
+	 *	0 -> load new kernel
+	 */
+	lghi	%r10,0
+	lg	%r11,kernel_type-.base_crash(%r13)
+	cghi	%r11,1		/* KEXEC_TYPE_CRASH */
+	jne	.do_checksum_verification
+	cghi	%r2,0		/* checksum verification only */
+	jne	.do_checksum_verification
+	lghi	%r10,1
+
+.do_checksum_verification:
+	brasl	%r14,verify_sha256_digest
+
+	cghi	%r10,1		/* checksum verification only */
+	je	.return_old_kernel
+	cghi	%r2,0		/* checksum match */
+	jne	.disabled_wait
+
+	/* If the next kernel is a crash kernel the purgatory has to swap
+	 * the mem regions first.
+	 */
+	cghi	%r11,1 /* KEXEC_TYPE_CRASH */
+	je	.start_crash_kernel
+
+	/* start normal kernel */
+	START_NEXT_KERNEL .base_crash
+
+.return_old_kernel:
+	lmg	%r6,%r15,gprregs-.base_crash(%r13)
+	br	%r14
+
+.disabled_wait:
+	lpswe	disabled_wait_psw-.base_crash(%r13)
+
+.start_crash_kernel:
+	/* Location of purgatory_start in crash memory */
+	lgr	%r8,%r13
+	aghi	%r8,-(.base_crash-purgatory_start)
+
+	/* Destination for this code i.e. end of memory to be swapped. */
+	lg	%r9,crash_size-.base_crash(%r13)
+	aghi	%r9,-(purgatory_end-purgatory_start)
+
+	/* Destination in crash memory, i.e. same as r9 but in crash memory. */
+	lg	%r10,crash_start-.base_crash(%r13)
+	agr	%r10,%r9
+
+	/* Buffer location (in crash memory) and size. As the purgatory is
+	 * behind the point of no return it can re-use the stack as buffer.
+	 */
+	lghi	%r11,bufsz
+	larl	%r12,stack
+
+	MEMCPY	%r12,%r9,%r11	/* dst	-> (crash) buf */
+	MEMCPY	%r9,%r8,%r11	/* self -> dst */
+
+	/* Jump to new location. */
+	lgr	%r7,%r9
+	aghi	%r7,.jump_to_dst-purgatory_start
+	br	%r7
+
+.jump_to_dst:
+	basr	%r13,0
+.base_dst:
+
+	/* clear buffer */
+	MEMCPY	%r12,%r10,%r11	/* (crash) buf -> (crash) dst */
+
+	/* Load new buffer location after jump */
+	larl	%r7,stack
+	aghi	%r10,stack-purgatory_start
+	MEMCPY	%r10,%r7,%r11	/* (new) buf -> (crash) buf */
+
+	/* Now the code is set up to run from its designated location. Start
+	 * swapping the rest of crash memory now.
+	 *
+	 * The registers will be used as follow:
+	 *
+	 *	%r0-%r4	reserved for macros defined above
+	 *	%r5-%r6 tmp registers
+	 *	%r7	pointer to current struct sha region
+	 *	%r8	index to iterate over all sha regions
+	 *	%r9	pointer in crash memory
+	 *	%r10	pointer in old kernel
+	 *	%r11	total size (still) to be moved
+	 *	%r12	pointer to buffer
+	 */
+	lgr	%r12,%r7
+	lgr	%r11,%r9
+	lghi	%r10,0
+	lg	%r9,crash_start-.base_dst(%r13)
+	lghi	%r8,16	/* KEXEC_SEGMENTS_MAX */
+	larl	%r7,purgatory_sha_regions
+
+	j .loop_first
+
+	/* Loop over all purgatory_sha_regions. */
+.loop_next:
+	aghi	%r8,-1
+	cghi	%r8,0
+	je	.loop_out
+
+	aghi	%r7,__KEXEC_SHA_REGION_SIZE
+
+.loop_first:
+	lg	%r5,__KEXEC_SHA_REGION_START(%r7)
+	cghi	%r5,0
+	je	.loop_next
+
+	/* Copy [end last sha region, start current sha region) */
+	/* Note: kexec_sha_region->start points in crash memory */
+	sgr	%r5,%r9
+	MEMCPY	%r9,%r10,%r5
+
+	agr	%r9,%r5
+	agr	%r10,%r5
+	sgr	%r11,%r5
+
+	/* Swap sha region */
+	lg	%r6,__KEXEC_SHA_REGION_LEN(%r7)
+	MEMSWAP	%r9,%r10,%r12,%r6
+	sg	%r11,__KEXEC_SHA_REGION_LEN(%r7)
+	j	.loop_next
+
+.loop_out:
+	/* Copy rest of crash memory */
+	MEMCPY	%r9,%r10,%r11
+
+	/* start crash kernel */
+	START_NEXT_KERNEL .base_dst
+
+
+load_psw_mask:
+	.long	0x00080000,0x80000000
+
+	.align	8
+disabled_wait_psw:
+	.quad	0x0002000180000000
+	.quad	0x0000000000000000 + .do_checksum_verification
+
+gprregs:
+	.rept	10
+	.quad	0
+	.endr
+
+purgatory_sha256_digest:
+	.global purgatory_sha256_digest
+	.rept	32	/* SHA256_DIGEST_SIZE */
+	.byte	0
+	.endr
+
+purgatory_sha_regions:
+	.global purgatory_sha_regions
+	.rept	16 * __KEXEC_SHA_REGION_SIZE	/* KEXEC_SEGMENTS_MAX */
+	.byte	0
+	.endr
+
+kernel_entry:
+	.global kernel_entry
+	.quad	0
+
+kernel_type:
+	.global kernel_type
+	.quad	0
+
+crash_start:
+	.global crash_start
+	.quad	0
+
+crash_size:
+	.global crash_size
+	.quad	0
+
+	.align	PAGE_SIZE
+stack:
+	/* The buffer to move this code must be as big as the code. */
+	.skip	stack-purgatory_start
+	.align	PAGE_SIZE
+purgatory_end:
diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c
new file mode 100644
index 000000000000..4e2beb3c29b7
--- /dev/null
+++ b/arch/s390/purgatory/purgatory.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Purgatory code running between two kernels.
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/kexec.h>
+#include <linux/sha256.h>
+#include <linux/string.h>
+#include <asm/purgatory.h>
+
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
+
+u64 kernel_entry;
+u64 kernel_type;
+
+u64 crash_start;
+u64 crash_size;
+
+int verify_sha256_digest(void)
+{
+	struct kexec_sha_region *ptr, *end;
+	u8 digest[SHA256_DIGEST_SIZE];
+	struct sha256_state sctx;
+
+	sha256_init(&sctx);
+	end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
+
+	for (ptr = purgatory_sha_regions; ptr < end; ptr++)
+		sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len);
+
+	sha256_final(&sctx, digest);
+
+	if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)))
+		return 1;
+
+	return 0;
+}
diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
new file mode 100644
index 000000000000..d92f2d94a5d9
--- /dev/null
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+
+quiet_cmd_chkbss = CHKBSS  $<
+define cmd_chkbss
+	if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
+		echo "error: $< .bss section is not empty" >&2; exit 1; \
+	fi; \
+	touch $@;
+endef
+
+$(obj)/built-in.a: $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+
+%.o.chkbss: %.o
+	$(call cmd,chkbss)
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 97fe29316476..ae619d54018c 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -9,11 +9,11 @@ config SUPERH
 	select HAVE_IDE if HAS_IOPORT_MAP
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
+	select NO_BOOTMEM
 	select ARCH_DISCARD_MEMBLOCK
 	select HAVE_OPROFILE
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_DMA_API_DEBUG
 	select HAVE_PERF_EVENTS
 	select HAVE_DEBUG_BUGVERBOSE
 	select ARCH_HAVE_CUSTOM_GPIO_H
@@ -50,6 +50,9 @@ config SUPERH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_NMI
+	select NEED_DMA_MAP_STATE
+	select NEED_SG_DMA_LENGTH
+
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
 	  and consumer electronics; it was also used in the Sega Dreamcast
@@ -57,7 +60,7 @@ config SUPERH
 	  <http://www.linux-sh.org/>.
 
 config SUPERH32
-	def_bool ARCH = "sh"
+	def_bool "$(ARCH)" = "sh"
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select HAVE_IOREMAP_PROT if MMU && !X2TLB
@@ -76,7 +79,7 @@ config SUPERH32
 	select HAVE_CC_STACKPROTECTOR
 
 config SUPERH64
-	def_bool ARCH = "sh64"
+	def_bool "$(ARCH)" = "sh64"
 	select HAVE_EXIT_THREAD
 	select KALLSYMS
 
@@ -160,12 +163,6 @@ config DMA_COHERENT
 config DMA_NONCOHERENT
 	def_bool !DMA_COHERENT
 
-config NEED_DMA_MAP_STATE
-	def_bool DMA_NONCOHERENT
-
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
 config PGTABLE_LEVELS
 	default 3 if X2TLB
 	default 2
diff --git a/arch/sh/drivers/dma/dma-api.c b/arch/sh/drivers/dma/dma-api.c
index c0eec08d8f95..b05be597b19f 100644
--- a/arch/sh/drivers/dma/dma-api.c
+++ b/arch/sh/drivers/dma/dma-api.c
@@ -339,18 +339,6 @@ static int dma_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int dma_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, dma_proc_show, NULL);
-}
-
-static const struct file_operations dma_proc_fops = {
-	.open		= dma_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 int register_dmac(struct dma_info *info)
 {
 	unsigned int total_channels, i;
@@ -423,7 +411,7 @@ EXPORT_SYMBOL(unregister_dmac);
 static int __init dma_api_init(void)
 {
 	printk(KERN_NOTICE "DMA: Registering DMA API.\n");
-	return proc_create("dma", 0, NULL, &dma_proc_fops) ? 0 : -ENOMEM;
+	return proc_create_single("dma", 0, NULL, dma_proc_show) ? 0 : -ENOMEM;
 }
 subsys_initcall(dma_api_init);
 
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 1efcce74997b..46dd82ab2c29 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -1,3 +1,4 @@
+generic-y += compat.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index 0033f0df2b3b..10a36b1cf2ea 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -71,12 +71,6 @@ extern unsigned long PCIBIOS_MIN_IO, PCIBIOS_MIN_MEM;
  * SuperH has everything mapped statically like x86.
  */
 
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS	(dma_ops->is_phys)
-
 #ifdef CONFIG_PCI
 /*
  * None of the SH PCI controllers support MWI, it is always treated as a
diff --git a/arch/sh/kernel/cpu/sh2/probe.c b/arch/sh/kernel/cpu/sh2/probe.c
index 4205f6d42b69..a5bd03642678 100644
--- a/arch/sh/kernel/cpu/sh2/probe.c
+++ b/arch/sh/kernel/cpu/sh2/probe.c
@@ -43,7 +43,11 @@ void __ref cpu_probe(void)
 #endif
 
 #if defined(CONFIG_CPU_J2)
+#if defined(CONFIG_SMP)
 	unsigned cpu = hard_smp_processor_id();
+#else
+	unsigned cpu = 0;
+#endif
 	if (cpu == 0) of_scan_flat_dt(scan_cache, NULL);
 	if (j2_ccr_base) __raw_writel(0x80000303, j2_ccr_base + 4*cpu);
 	if (cpu != 0) return;
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
index 178457d7620c..3e3a32fc676e 100644
--- a/arch/sh/kernel/dma-nommu.c
+++ b/arch/sh/kernel/dma-nommu.c
@@ -78,7 +78,6 @@ const struct dma_map_ops nommu_dma_ops = {
 	.sync_single_for_device	= nommu_sync_single_for_device,
 	.sync_sg_for_device	= nommu_sync_sg_for_device,
 #endif
-	.is_phys		= 1,
 };
 
 void __init no_iommu_init(void)
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index afe965712a69..8648ed05ccf0 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -347,13 +347,8 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 
 		/* Deliver the signal to userspace */
 		if (!arch_check_bp_in_kernelspace(bp)) {
-			siginfo_t info;
-
-			info.si_signo = args->signr;
-			info.si_errno = notifier_to_errno(rc);
-			info.si_code = TRAP_HWBKPT;
-
-			force_sig_info(args->signr, &info, current);
+			force_sig_fault(SIGTRAP, TRAP_HWBKPT,
+					(void __user *)NULL, current);
 		}
 
 		rcu_read_unlock();
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 245dbeb20afe..5717c7cbdd97 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -44,7 +44,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 
 	seq_printf(p, "%*s: ", prec, "NMI");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stat[j].__nmi_count);
+		seq_printf(p, "%10u ", nmi_count(j));
 	seq_printf(p, "  Non-maskable interrupts\n");
 
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index d34e998b809f..c286cf5da6e7 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -11,7 +11,6 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/initrd.h>
-#include <linux/bootmem.h>
 #include <linux/console.h>
 #include <linux/root_dev.h>
 #include <linux/utsname.h>
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index b3770bb26211..60709ad17fc7 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -477,7 +477,6 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 {
 	unsigned long error_code = 0;
 	mm_segment_t oldfs;
-	siginfo_t info;
 	insn_size_t instruction;
 	int tmp;
 
@@ -537,11 +536,7 @@ uspace_segv:
 		       "access (PC %lx PR %lx)\n", current->comm, regs->pc,
 		       regs->pr);
 
-		info.si_signo = SIGBUS;
-		info.si_errno = 0;
-		info.si_code = si_code;
-		info.si_addr = (void __user *)address;
-		force_sig_info(SIGBUS, &info, current);
+		force_sig_fault(SIGBUS, si_code, (void __user *)address, current);
 	} else {
 		inc_unaligned_kernel_access();
 
@@ -598,19 +593,20 @@ int is_dsp_inst(struct pt_regs *regs)
 #ifdef CONFIG_CPU_SH2A
 asmlinkage void do_divide_error(unsigned long r4)
 {
-	siginfo_t info;
+	int code;
 
 	switch (r4) {
 	case TRAP_DIVZERO_ERROR:
-		info.si_code = FPE_INTDIV;
+		code = FPE_INTDIV;
 		break;
 	case TRAP_DIVOVF_ERROR:
-		info.si_code = FPE_INTOVF;
+		code = FPE_INTOVF;
 		break;
+	default:
+		/* Let gcc know unhandled cases don't make it past here */
+		return;
 	}
-
-	info.si_signo = SIGFPE;
-	force_sig_info(info.si_signo, &info, current);
+	force_sig_fault(SIGFPE, code, NULL, current);
 }
 #endif
 
diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c
index c86f4360c6ce..a0fa8fc88739 100644
--- a/arch/sh/math-emu/math.c
+++ b/arch/sh/math-emu/math.c
@@ -507,7 +507,6 @@ static int ieee_fpe_handler(struct pt_regs *regs)
 	unsigned short insn = *(unsigned short *)regs->pc;
 	unsigned short finsn;
 	unsigned long nextpc;
-	siginfo_t info;
 	int nib[4] = {
 		(insn >> 12) & 0xf,
 		(insn >> 8) & 0xf,
@@ -560,11 +559,8 @@ static int ieee_fpe_handler(struct pt_regs *regs)
 				~(FPSCR_CAUSE_MASK | FPSCR_FLAG_MASK);
 			task_thread_info(tsk)->status |= TS_USEDFPU;
 		} else {
-			info.si_signo = SIGFPE;
-			info.si_errno = 0;
-			info.si_code = FPE_FLTINV;
-			info.si_addr = (void __user *)regs->pc;
-			force_sig_info(SIGFPE, &info, tsk);
+			force_sig_fault(SIGFPE, FPE_FLTINV,
+					(void __user *)regs->pc, tsk);
 		}
 
 		regs->pc = nextpc;
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 8ce98691d822..fceb2adfcac7 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -20,18 +20,9 @@
 #include <asm/cacheflush.h>
 #include <asm/addrspace.h>
 
-#define PREALLOC_DMA_DEBUG_ENTRIES	4096
-
 const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-static int __init dma_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-	return 0;
-}
-fs_initcall(dma_init);
-
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 dma_addr_t *dma_handle, gfp_t gfp,
 				 unsigned long attrs)
@@ -59,7 +50,9 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 
 	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
 
-	*dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset);
+	*dma_handle = virt_to_phys(ret);
+	if (!WARN_ON(!dev))
+		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
 
 	return ret_nocache;
 }
@@ -69,9 +62,12 @@ void dma_generic_free_coherent(struct device *dev, size_t size,
 			       unsigned long attrs)
 {
 	int order = get_order(size);
-	unsigned long pfn = (dma_handle >> PAGE_SHIFT) + dev->dma_pfn_offset;
+	unsigned long pfn = dma_handle >> PAGE_SHIFT;
 	int k;
 
+	if (!WARN_ON(!dev))
+		pfn += dev->dma_pfn_offset;
+
 	for (k = 0; k < (1 << order); k++)
 		__free_pages(pfn_to_page(pfn + k), 0);
 
@@ -143,7 +139,7 @@ int __init platform_resource_setup_memory(struct platform_device *pdev,
 	if (!memsize)
 		return 0;
 
-	buf = dma_alloc_coherent(NULL, memsize, &dma_handle, GFP_KERNEL);
+	buf = dma_alloc_coherent(&pdev->dev, memsize, &dma_handle, GFP_KERNEL);
 	if (!buf) {
 		pr_warning("%s: unable to allocate memory\n", name);
 		return -ENOMEM;
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 6fd1bf7481c7..b8e7bb84b6b1 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -42,14 +42,7 @@ static void
 force_sig_info_fault(int si_signo, int si_code, unsigned long address,
 		     struct task_struct *tsk)
 {
-	siginfo_t info;
-
-	info.si_signo	= si_signo;
-	info.si_errno	= 0;
-	info.si_code	= si_code;
-	info.si_addr	= (void __user *)address;
-
-	force_sig_info(si_signo, &info, tsk);
+	force_sig_fault(si_signo, si_code, (void __user *)address, tsk);
 }
 
 /*
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index ce0bbaa7e404..4034035fbede 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -211,59 +211,15 @@ void __init allocate_pgdat(unsigned int nid)
 
 	NODE_DATA(nid) = __va(phys);
 	memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
-
-	NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
 #endif
 
 	NODE_DATA(nid)->node_start_pfn = start_pfn;
 	NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
 }
 
-static void __init bootmem_init_one_node(unsigned int nid)
-{
-	unsigned long total_pages, paddr;
-	unsigned long end_pfn;
-	struct pglist_data *p;
-
-	p = NODE_DATA(nid);
-
-	/* Nothing to do.. */
-	if (!p->node_spanned_pages)
-		return;
-
-	end_pfn = pgdat_end_pfn(p);
-
-	total_pages = bootmem_bootmap_pages(p->node_spanned_pages);
-
-	paddr = memblock_alloc(total_pages << PAGE_SHIFT, PAGE_SIZE);
-	if (!paddr)
-		panic("Can't allocate bootmap for nid[%d]\n", nid);
-
-	init_bootmem_node(p, paddr >> PAGE_SHIFT, p->node_start_pfn, end_pfn);
-
-	free_bootmem_with_active_regions(nid, end_pfn);
-
-	/*
-	 * XXX Handle initial reservations for the system memory node
-	 * only for the moment, we'll refactor this later for handling
-	 * reservations in other nodes.
-	 */
-	if (nid == 0) {
-		struct memblock_region *reg;
-
-		/* Reserve the sections we're already using. */
-		for_each_memblock(reserved, reg) {
-			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
-		}
-	}
-
-	sparse_memory_present_with_active_regions(nid);
-}
-
 static void __init do_init_bootmem(void)
 {
 	struct memblock_region *reg;
-	int i;
 
 	/* Add active regions with valid PFNs. */
 	for_each_memblock(memory, reg) {
@@ -279,9 +235,12 @@ static void __init do_init_bootmem(void)
 
 	plat_mem_setup();
 
-	for_each_online_node(i)
-		bootmem_init_one_node(i);
+	for_each_memblock(memory, reg) {
+		int nid = memblock_get_region_node(reg);
 
+		memory_present(nid, memblock_region_memory_base_pfn(reg),
+			memblock_region_memory_end_pfn(reg));
+	}
 	sparse_init();
 }
 
@@ -322,7 +281,6 @@ void __init paging_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 	unsigned long vaddr, end;
-	int nid;
 
 	sh_mv.mv_mem_init();
 
@@ -377,21 +335,7 @@ void __init paging_init(void)
 	kmap_coherent_init();
 
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-
-	for_each_online_node(nid) {
-		pg_data_t *pgdat = NODE_DATA(nid);
-		unsigned long low, start_pfn;
-
-		start_pfn = pgdat->bdata->node_min_pfn;
-		low = pgdat->bdata->node_low_pfn;
-
-		if (max_zone_pfns[ZONE_NORMAL] < low)
-			max_zone_pfns[ZONE_NORMAL] = low;
-
-		printk("Node %u: start_pfn = 0x%lx, low = 0x%lx\n",
-		       nid, start_pfn, low);
-	}
-
+	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 	free_area_init_nodes(max_zone_pfns);
 }
 
diff --git a/arch/sh/mm/numa.c b/arch/sh/mm/numa.c
index 05713d190247..830e8b3684e4 100644
--- a/arch/sh/mm/numa.c
+++ b/arch/sh/mm/numa.c
@@ -8,7 +8,6 @@
  * for more details.
  */
 #include <linux/module.h>
-#include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/numa.h>
@@ -26,9 +25,7 @@ EXPORT_SYMBOL_GPL(node_data);
  */
 void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
 {
-	unsigned long bootmap_pages;
 	unsigned long start_pfn, end_pfn;
-	unsigned long bootmem_paddr;
 
 	/* Don't allow bogus node assignment */
 	BUG_ON(nid >= MAX_NUMNODES || nid <= 0);
@@ -48,25 +45,9 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
 					     SMP_CACHE_BYTES, end));
 	memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
 
-	NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
 	NODE_DATA(nid)->node_start_pfn = start_pfn;
 	NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
 
-	/* Node-local bootmap */
-	bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-	bootmem_paddr = memblock_alloc_base(bootmap_pages << PAGE_SHIFT,
-				       PAGE_SIZE, end);
-	init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
-			  start_pfn, end_pfn);
-
-	free_bootmem_with_active_regions(nid, end_pfn);
-
-	/* Reserve the pgdat and bootmap space with the bootmem allocator */
-	reserve_bootmem_node(NODE_DATA(nid), start_pfn << PAGE_SHIFT,
-			     sizeof(struct pglist_data), BOOTMEM_DEFAULT);
-	reserve_bootmem_node(NODE_DATA(nid), bootmem_paddr,
-			     bootmap_pages << PAGE_SHIFT, BOOTMEM_DEFAULT);
-
 	/* It's up */
 	node_set_online(nid);
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 8767e45f1b2b..b42ba888217d 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -1,6 +1,6 @@
 config 64BIT
-	bool "64-bit kernel" if ARCH = "sparc"
-	default ARCH = "sparc64"
+	bool "64-bit kernel" if "$(ARCH)" = "sparc"
+	default "$(ARCH)" = "sparc64"
 	help
 	  SPARC is a family of RISC microprocessors designed and marketed by
 	  Sun Microsystems, incorporated.  They are very widely found in Sun
@@ -25,7 +25,6 @@ config SPARC
 	select RTC_CLASS
 	select RTC_DRV_M48T59
 	select RTC_SYSTOHC
-	select HAVE_DMA_API_DEBUG
 	select HAVE_ARCH_JUMP_LABEL if SPARC64
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -44,6 +43,8 @@ config SPARC
 	select ARCH_HAS_SG_CHAIN
 	select CPU_NO_EFFICIENT_FFS
 	select LOCKDEP_SMALL if LOCKDEP
+	select NEED_DMA_MAP_STATE
+	select NEED_SG_DMA_LENGTH
 
 config SPARC32
 	def_bool !64BIT
@@ -67,6 +68,7 @@ config SPARC64
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_DEBUG_KMEMLEAK
+	select IOMMU_HELPER
 	select SPARSE_IRQ
 	select RTC_DRV_CMOS
 	select RTC_DRV_BQ4802
@@ -102,14 +104,6 @@ config ARCH_ATU
 	bool
 	default y if SPARC64
 
-config ARCH_DMA_ADDR_T_64BIT
-	bool
-	default y if ARCH_ATU
-
-config IOMMU_HELPER
-	bool
-	default y if SPARC64
-
 config STACKTRACE_SUPPORT
 	bool
 	default y if SPARC64
@@ -146,12 +140,6 @@ config ZONE_DMA
 	bool
 	default y if SPARC32
 
-config NEED_DMA_MAP_STATE
-	def_bool y
-
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
 config GENERIC_ISA_DMA
 	bool
 	default y if SPARC32
diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index edac927e4952..966a13d2b127 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -39,7 +39,7 @@ else
 # sparc64
 #
 
-CHECKFLAGS    += -D__sparc__ -D__sparc_v9__ -D__arch64__ -m64
+CHECKFLAGS    += -D__sparc__ -D__sparc_v9__ -D__arch64__
 LDFLAGS       := -m elf64_sparc
 export BITS   := 64
 UTS_MACHINE   := sparc64
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index 615283e16f22..4eb51d2dae98 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -11,7 +11,6 @@
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
-typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_pid_t;
 typedef u16		__compat_uid_t;
@@ -39,16 +38,6 @@ typedef u32		compat_ulong_t;
 typedef u64		compat_u64;
 typedef u32		compat_uptr_t;
 
-struct compat_timespec {
-	compat_time_t	tv_sec;
-	s32		tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t	tv_sec;
-	s32		tv_usec;
-};
-
 struct compat_stat {
 	compat_dev_t	st_dev;
 	compat_ino_t	st_ino;
@@ -168,6 +157,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
+#ifdef CONFIG_COMPAT
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
 	struct pt_regs *regs = current_thread_info()->kregs;
@@ -184,6 +174,7 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 
 	return (void __user *) usp;
 }
+#endif
 
 struct compat_ipc64_perm {
 	compat_key_t key;
@@ -201,10 +192,10 @@ struct compat_ipc64_perm {
 
 struct compat_semid64_ds {
 	struct compat_ipc64_perm sem_perm;
-	unsigned int	__pad1;
-	compat_time_t	sem_otime;
-	unsigned int	__pad2;
-	compat_time_t	sem_ctime;
+	unsigned int	sem_otime_high;
+	unsigned int	sem_otime;
+	unsigned int	sem_ctime_high;
+	unsigned int	sem_ctime;
 	u32		sem_nsems;
 	u32		__unused1;
 	u32		__unused2;
@@ -212,12 +203,12 @@ struct compat_semid64_ds {
 
 struct compat_msqid64_ds {
 	struct compat_ipc64_perm msg_perm;
-	unsigned int	__pad1;
-	compat_time_t	msg_stime;
-	unsigned int	__pad2;
-	compat_time_t	msg_rtime;
-	unsigned int	__pad3;
-	compat_time_t	msg_ctime;
+	unsigned int	msg_stime_high;
+	unsigned int	msg_stime;
+	unsigned int	msg_rtime_high;
+	unsigned int	msg_rtime;
+	unsigned int	msg_ctime_high;
+	unsigned int	msg_ctime;
 	unsigned int	msg_cbytes;
 	unsigned int	msg_qnum;
 	unsigned int	msg_qbytes;
@@ -229,12 +220,12 @@ struct compat_msqid64_ds {
 
 struct compat_shmid64_ds {
 	struct compat_ipc64_perm shm_perm;
-	unsigned int	__pad1;
-	compat_time_t	shm_atime;
-	unsigned int	__pad2;
-	compat_time_t	shm_dtime;
-	unsigned int	__pad3;
-	compat_time_t	shm_ctime;
+	unsigned int	shm_atime_high;
+	unsigned int	shm_atime;
+	unsigned int	shm_dtime_high;
+	unsigned int	shm_dtime;
+	unsigned int	shm_ctime_high;
+	unsigned int	shm_ctime;
 	compat_size_t	shm_segsz;
 	compat_pid_t	shm_cpid;
 	compat_pid_t	shm_lpid;
@@ -243,6 +234,7 @@ struct compat_shmid64_ds {
 	unsigned int	__unused2;
 };
 
+#ifdef CONFIG_COMPAT
 static inline int is_compat_task(void)
 {
 	return test_thread_flag(TIF_32BIT);
@@ -254,5 +246,6 @@ static inline bool in_compat_syscall(void)
 	return pt_regs_trap_type(current_pt_regs()) == 0x110;
 }
 #define in_compat_syscall in_compat_syscall
+#endif
 
 #endif /* _ASM_SPARC64_COMPAT_H */
diff --git a/arch/sparc/include/asm/hardirq_64.h b/arch/sparc/include/asm/hardirq_64.h
index f56540271993..75b92bfe04b5 100644
--- a/arch/sparc/include/asm/hardirq_64.h
+++ b/arch/sparc/include/asm/hardirq_64.h
@@ -10,8 +10,9 @@
 #include <asm/cpudata.h>
 
 #define __ARCH_IRQ_STAT
-#define local_softirq_pending() \
-	(local_cpu_data().__softirq_pending)
+
+#define local_softirq_pending_ref \
+	__cpu_data.__softirq_pending
 
 void ack_bad_irq(unsigned int irq);
 
diff --git a/include/linux/iommu-common.h b/arch/sparc/include/asm/iommu-common.h
index 802c90c79d1f..802c90c79d1f 100644
--- a/include/linux/iommu-common.h
+++ b/arch/sparc/include/asm/iommu-common.h
diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h
index 9ed6b54caa4b..0ef6dedf747e 100644
--- a/arch/sparc/include/asm/iommu_64.h
+++ b/arch/sparc/include/asm/iommu_64.h
@@ -17,7 +17,7 @@
 #define IOPTE_WRITE   0x0000000000000002UL
 
 #define IOMMU_NUM_CTXS	4096
-#include <linux/iommu-common.h>
+#include <asm/iommu-common.h>
 
 struct iommu_arena {
 	unsigned long	*map;
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index 98917e48727d..cfc0ee9476c6 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -17,10 +17,6 @@
 
 #define PCI_IRQ_NONE		0xffffffff
 
-/* Dynamic DMA mapping stuff.
- */
-#define PCI_DMA_BUS_IS_PHYS	(0)
-
 #endif /* __KERNEL__ */
 
 #ifndef CONFIG_LEON_PCI
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index 671274e36cfa..fac77813402c 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -17,12 +17,6 @@
 
 #define PCI_IRQ_NONE		0xffffffff
 
-/* The PCI address space does not equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS	(0)
-
 /* PCI IOMMU mapping bypass support. */
 
 /* PCI 64-bit addressing works for all slots on all controller
diff --git a/arch/sparc/include/uapi/asm/jsflash.h b/arch/sparc/include/uapi/asm/jsflash.h
deleted file mode 100644
index 68c98a54281a..000000000000
--- a/arch/sparc/include/uapi/asm/jsflash.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * jsflash.h: OS Flash SIMM support for JavaStations.
- *
- * Copyright (C) 1999  Pete Zaitcev
- */
-
-#ifndef _SPARC_JSFLASH_H
-#define _SPARC_JSFLASH_H
-
-#ifndef _SPARC_TYPES_H
-#include <linux/types.h>
-#endif
-
-/*
- * Semantics of the offset is a full address.
- * Hardcode it or get it from probe ioctl.
- *
- * We use full bus address, so that we would be
- * automatically compatible with possible future systems.
- */
-
-#define JSFLASH_IDENT   (('F'<<8)|54)
-struct jsflash_ident_arg {
-	__u64 off;                /* 0x20000000 is included */
-	__u32 size;
-	char name[32];		/* With trailing zero */
-};
-
-#define JSFLASH_ERASE   (('F'<<8)|55)
-/* Put 0 as argument, may be flags or sector number... */
-
-#define JSFLASH_PROGRAM (('F'<<8)|56)
-struct jsflash_program_arg {
-	__u64 data;		/* char* for sparc and sparc64 */
-	__u64 off;
-	__u32 size;
-};
-
-#endif /* _SPARC_JSFLASH_H */
diff --git a/arch/sparc/include/uapi/asm/msgbuf.h b/arch/sparc/include/uapi/asm/msgbuf.h
index b601c4f4d956..ffc46c211d6d 100644
--- a/arch/sparc/include/uapi/asm/msgbuf.h
+++ b/arch/sparc/include/uapi/asm/msgbuf.h
@@ -8,25 +8,22 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
-
-#if defined(__sparc__) && defined(__arch64__)
-# define PADDING(x)
-#else
-# define PADDING(x) unsigned int x;
-#endif
-
-
 struct msqid64_ds {
 	struct ipc64_perm msg_perm;
-	PADDING(__pad1)
+#if defined(__sparc__) && defined(__arch64__)
 	__kernel_time_t msg_stime;	/* last msgsnd time */
-	PADDING(__pad2)
 	__kernel_time_t msg_rtime;	/* last msgrcv time */
-	PADDING(__pad3)
 	__kernel_time_t msg_ctime;	/* last change time */
+#else
+	unsigned long msg_stime_high;
+	unsigned long msg_stime;	/* last msgsnd time */
+	unsigned long msg_rtime_high;
+	unsigned long msg_rtime;	/* last msgrcv time */
+	unsigned long msg_ctime_high;
+	unsigned long msg_ctime;	/* last change time */
+#endif
 	unsigned long  msg_cbytes;	/* current number of bytes on queue */
 	unsigned long  msg_qnum;	/* number of messages in queue */
 	unsigned long  msg_qbytes;	/* max number of bytes on queue */
@@ -35,5 +32,4 @@ struct msqid64_ds {
 	unsigned long  __unused1;
 	unsigned long  __unused2;
 };
-#undef PADDING
 #endif /* _SPARC_MSGBUF_H */
diff --git a/arch/sparc/include/uapi/asm/oradax.h b/arch/sparc/include/uapi/asm/oradax.h
index 722951908b0a..4f6676fe4bcc 100644
--- a/arch/sparc/include/uapi/asm/oradax.h
+++ b/arch/sparc/include/uapi/asm/oradax.h
@@ -3,7 +3,7 @@
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
+ * the Free Software Foundation, either version 2 of the License, or
  * (at your option) any later version.
  *
  * This program is distributed in the hope that it will be useful,
diff --git a/arch/sparc/include/uapi/asm/sembuf.h b/arch/sparc/include/uapi/asm/sembuf.h
index f49b0ffa0ab8..f3d309c2e1cd 100644
--- a/arch/sparc/include/uapi/asm/sembuf.h
+++ b/arch/sparc/include/uapi/asm/sembuf.h
@@ -8,25 +8,23 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
-#if defined(__sparc__) && defined(__arch64__)
-# define PADDING(x)
-#else
-# define PADDING(x) unsigned int x;
-#endif
 
 struct semid64_ds {
 	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
-	PADDING(__pad1)
+#if defined(__sparc__) && defined(__arch64__)
 	__kernel_time_t	sem_otime;		/* last semop time */
-	PADDING(__pad2)
 	__kernel_time_t	sem_ctime;		/* last change time */
+#else
+	unsigned long	sem_otime_high;
+	unsigned long	sem_otime;		/* last semop time */
+	unsigned long	sem_ctime_high;
+	unsigned long	sem_ctime;		/* last change time */
+#endif
 	unsigned long	sem_nsems;		/* no. of semaphores in array */
 	unsigned long	__unused1;
 	unsigned long	__unused2;
 };
-#undef PADDING
 
 #endif /* _SPARC64_SEMBUF_H */
diff --git a/arch/sparc/include/uapi/asm/shmbuf.h b/arch/sparc/include/uapi/asm/shmbuf.h
index 286631db705c..06618b84822d 100644
--- a/arch/sparc/include/uapi/asm/shmbuf.h
+++ b/arch/sparc/include/uapi/asm/shmbuf.h
@@ -8,24 +8,23 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
 
-#if defined(__sparc__) && defined(__arch64__)
-# define PADDING(x)
-#else
-# define PADDING(x) unsigned int x;
-#endif
-
 struct shmid64_ds {
 	struct ipc64_perm	shm_perm;	/* operation perms */
-	PADDING(__pad1)
+#if defined(__sparc__) && defined(__arch64__)
 	__kernel_time_t		shm_atime;	/* last attach time */
-	PADDING(__pad2)
 	__kernel_time_t		shm_dtime;	/* last detach time */
-	PADDING(__pad3)
 	__kernel_time_t		shm_ctime;	/* last change time */
+#else
+	unsigned long		shm_atime_high;
+	unsigned long		shm_atime;	/* last attach time */
+	unsigned long		shm_dtime_high;
+	unsigned long		shm_dtime;	/* last detach time */
+	unsigned long		shm_ctime_high;
+	unsigned long		shm_ctime;	/* last change time */
+#endif
 	size_t			shm_segsz;	/* size of segment (bytes) */
 	__kernel_pid_t		shm_cpid;	/* pid of creator */
 	__kernel_pid_t		shm_lpid;	/* pid of last operator */
@@ -46,6 +45,4 @@ struct shminfo64 {
 	unsigned long	__unused4;
 };
 
-#undef PADDING
-
 #endif /* _SPARC_SHMBUF_H */
diff --git a/arch/sparc/include/uapi/asm/siginfo.h b/arch/sparc/include/uapi/asm/siginfo.h
index 896ce447d16a..e7049550ac82 100644
--- a/arch/sparc/include/uapi/asm/siginfo.h
+++ b/arch/sparc/include/uapi/asm/siginfo.h
@@ -18,13 +18,6 @@
 #define SI_NOINFO	32767		/* no information in siginfo_t */
 
 /*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME	0	/* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-/*
  * SIGEMT si_codes
  */
 #define EMT_TAGOVF	1	/* tag overflow */
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 76cb57750dda..cf8640841b7a 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -59,7 +59,7 @@ obj-$(CONFIG_SPARC32)   += leon_pmc.o
 
 obj-$(CONFIG_SPARC64)   += reboot.o
 obj-$(CONFIG_SPARC64)   += sysfs.o
-obj-$(CONFIG_SPARC64)   += iommu.o
+obj-$(CONFIG_SPARC64)   += iommu.o iommu-common.o
 obj-$(CONFIG_SPARC64)   += central.o
 obj-$(CONFIG_SPARC64)   += starfire.o
 obj-$(CONFIG_SPARC64)   += power.o
@@ -74,8 +74,6 @@ obj-$(CONFIG_SPARC64)	+= pcr.o
 obj-$(CONFIG_SPARC64)	+= nmi.o
 obj-$(CONFIG_SPARC64_SMP) += cpumap.o
 
-obj-y                     += dma.o
-
 obj-$(CONFIG_PCIC_PCI)    += pcic.o
 obj-$(CONFIG_LEON_PCI)    += leon_pci.o
 obj-$(CONFIG_SPARC_GRPCI2)+= leon_pci_grpci2.o
diff --git a/arch/sparc/kernel/dma.c b/arch/sparc/kernel/dma.c
deleted file mode 100644
index f73e7597c971..000000000000
--- a/arch/sparc/kernel/dma.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
-
-#define PREALLOC_DMA_DEBUG_ENTRIES       (1 << 15)
-
-static int __init dma_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-	return 0;
-}
-fs_initcall(dma_init);
diff --git a/lib/iommu-common.c b/arch/sparc/kernel/iommu-common.c
index 55b00de106b5..59cb16691322 100644
--- a/lib/iommu-common.c
+++ b/arch/sparc/kernel/iommu-common.c
@@ -8,9 +8,9 @@
 #include <linux/bitmap.h>
 #include <linux/bug.h>
 #include <linux/iommu-helper.h>
-#include <linux/iommu-common.h>
 #include <linux/dma-mapping.h>
 #include <linux/hash.h>
+#include <asm/iommu-common.h>
 
 static unsigned long iommu_large_alloc = 15;
 
@@ -93,7 +93,6 @@ void iommu_tbl_pool_init(struct iommu_map_table *iommu,
 	p->hint = p->start;
 	p->end = num_entries;
 }
-EXPORT_SYMBOL(iommu_tbl_pool_init);
 
 unsigned long iommu_tbl_range_alloc(struct device *dev,
 				struct iommu_map_table *iommu,
@@ -224,7 +223,6 @@ bail:
 
 	return n;
 }
-EXPORT_SYMBOL(iommu_tbl_range_alloc);
 
 static struct iommu_pool *get_pool(struct iommu_map_table *tbl,
 				   unsigned long entry)
@@ -264,4 +262,3 @@ void iommu_tbl_range_free(struct iommu_map_table *iommu, u64 dma_addr,
 	bitmap_clear(iommu->map, entry, npages);
 	spin_unlock_irqrestore(&(pool->lock), flags);
 }
-EXPORT_SYMBOL(iommu_tbl_range_free);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index b08dc3416f06..40d008b0bd3e 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -14,7 +14,7 @@
 #include <linux/errno.h>
 #include <linux/iommu-helper.h>
 #include <linux/bitmap.h>
-#include <linux/iommu-common.h>
+#include <asm/iommu-common.h>
 
 #ifdef CONFIG_PCI
 #include <linux/pci.h>
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 3bcef9ce74df..cca9134cfa7d 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -678,25 +678,14 @@ static int sparc_io_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int sparc_io_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sparc_io_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations sparc_io_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= sparc_io_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif /* CONFIG_PROC_FS */
 
 static void register_proc_sparc_ioport(void)
 {
 #ifdef CONFIG_PROC_FS
-	proc_create_data("io_map", 0, NULL, &sparc_io_proc_fops, &sparc_iomap);
-	proc_create_data("dvma_map", 0, NULL, &sparc_io_proc_fops, &_sparc_dvma);
+	proc_create_single_data("io_map", 0, NULL, sparc_io_proc_show,
+			&sparc_iomap);
+	proc_create_single_data("dvma_map", 0, NULL, sparc_io_proc_show,
+			&_sparc_dvma);
 #endif
 }
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 86b625f9d8dc..c0fa3ef6cf01 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -16,7 +16,7 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/bitmap.h>
-#include <linux/iommu-common.h>
+#include <asm/iommu-common.h>
 
 #include <asm/hypervisor.h>
 #include <asm/iommu.h>
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 249367228c33..565d9ac883d0 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -16,7 +16,7 @@
 #include <linux/export.h>
 #include <linux/log2.h>
 #include <linux/of_device.h>
-#include <linux/iommu-common.h>
+#include <asm/iommu-common.h>
 
 #include <asm/iommu.h>
 #include <asm/irq.h>
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 454a8af28f13..6c086086ca8f 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -518,14 +518,7 @@ void synchronize_user_stack(void)
 
 static void stack_unaligned(unsigned long sp)
 {
-	siginfo_t info;
-
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRALN;
-	info.si_addr = (void __user *) sp;
-	info.si_trapno = 0;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) sp, 0, current);
 }
 
 void fault_in_user_windows(void)
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index e8c3cb6b6d08..7f3d9c59719a 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -147,17 +147,11 @@ SYSCALL_DEFINE0(nis_syscall)
 asmlinkage void
 sparc_breakpoint (struct pt_regs *regs)
 {
-	siginfo_t info;
 
 #ifdef DEBUG_SPARC_BREAKPOINT
         printk ("TRAP: Entering kernel PC=%x, nPC=%x\n", regs->pc, regs->npc);
 #endif
-	info.si_signo = SIGTRAP;
-	info.si_errno = 0;
-	info.si_code = TRAP_BRKPT;
-	info.si_addr = (void __user *)regs->pc;
-	info.si_trapno = 0;
-	force_sig_info(SIGTRAP, &info, current);
+	force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc, 0, current);
 
 #ifdef DEBUG_SPARC_BREAKPOINT
 	printk ("TRAP: Returning to space: PC=%x nPC=%x\n", regs->pc, regs->npc);
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 9ef8de63f28b..7e49bbc925a5 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -502,7 +502,6 @@ SYSCALL_DEFINE0(nis_syscall)
 asmlinkage void sparc_breakpoint(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
-	siginfo_t info;
 
 	if (test_thread_flag(TIF_32BIT)) {
 		regs->tpc &= 0xffffffff;
@@ -511,12 +510,7 @@ asmlinkage void sparc_breakpoint(struct pt_regs *regs)
 #ifdef DEBUG_SPARC_BREAKPOINT
         printk ("TRAP: Entering kernel PC=%lx, nPC=%lx\n", regs->tpc, regs->tnpc);
 #endif
-	info.si_signo = SIGTRAP;
-	info.si_errno = 0;
-	info.si_code = TRAP_BRKPT;
-	info.si_addr = (void __user *)regs->tpc;
-	info.si_trapno = 0;
-	force_sig_info(SIGTRAP, &info, current);
+	force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->tpc, 0, current);
 #ifdef DEBUG_SPARC_BREAKPOINT
 	printk ("TRAP: Returning to space: PC=%lx nPC=%lx\n", regs->tpc, regs->tnpc);
 #endif
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index b1ed763e4787..bcdfc6168dd5 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -93,8 +93,6 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs)
 
 void do_hw_interrupt(struct pt_regs *regs, unsigned long type)
 {
-	siginfo_t info;
-
 	if(type < 0x80) {
 		/* Sun OS's puke from bad traps, Linux survives! */
 		printk("Unimplemented Sparc TRAP, type = %02lx\n", type);
@@ -104,19 +102,13 @@ void do_hw_interrupt(struct pt_regs *regs, unsigned long type)
 	if(regs->psr & PSR_PS)
 		die_if_kernel("Kernel bad trap", regs);
 
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_ILLTRP;
-	info.si_addr = (void __user *)regs->pc;
-	info.si_trapno = type - 0x80;
-	force_sig_info(SIGILL, &info, current);
+	force_sig_fault(SIGILL, ILL_ILLTRP,
+			(void __user *)regs->pc, type - 0x80, current);
 }
 
 void do_illegal_instruction(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 			    unsigned long psr)
 {
-	siginfo_t info;
-
 	if(psr & PSR_PS)
 		die_if_kernel("Kernel illegal instruction", regs);
 #ifdef TRAP_DEBUG
@@ -124,27 +116,15 @@ void do_illegal_instruction(struct pt_regs *regs, unsigned long pc, unsigned lon
 	       regs->pc, *(unsigned long *)regs->pc);
 #endif
 
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_ILLOPC;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	send_sig_info(SIGILL, &info, current);
+	send_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)pc, 0, current);
 }
 
 void do_priv_instruction(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 			 unsigned long psr)
 {
-	siginfo_t info;
-
 	if(psr & PSR_PS)
 		die_if_kernel("Penguin instruction from Penguin mode??!?!", regs);
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_PRVOPC;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	send_sig_info(SIGILL, &info, current);
+	send_sig_fault(SIGILL, ILL_PRVOPC, (void __user *)pc, 0, current);
 }
 
 /* XXX User may want to be allowed to do this. XXX */
@@ -152,8 +132,6 @@ void do_priv_instruction(struct pt_regs *regs, unsigned long pc, unsigned long n
 void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 			    unsigned long psr)
 {
-	siginfo_t info;
-
 	if(regs->psr & PSR_PS) {
 		printk("KERNEL MNA at pc %08lx npc %08lx called by %08lx\n", pc, npc,
 		       regs->u_regs[UREG_RETPC]);
@@ -165,12 +143,9 @@ void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc, unsigned lon
 	instruction_dump ((unsigned long *) regs->pc);
 	printk ("do_MNA!\n");
 #endif
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRALN;
-	info.si_addr = /* FIXME: Should dig out mna address */ (void *)0;
-	info.si_trapno = 0;
-	send_sig_info(SIGBUS, &info, current);
+	send_sig_fault(SIGBUS, BUS_ADRALN,
+		       /* FIXME: Should dig out mna address */ (void *)0,
+		       0, current);
 }
 
 static unsigned long init_fsr = 0x0UL;
@@ -226,9 +201,9 @@ void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 		 unsigned long psr)
 {
 	static int calls;
-	siginfo_t info;
 	unsigned long fsr;
 	int ret = 0;
+	int code;
 #ifndef CONFIG_SMP
 	struct task_struct *fpt = last_task_used_math;
 #else
@@ -303,24 +278,20 @@ void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 	}
 
 	fsr = fpt->thread.fsr;
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	info.si_code = FPE_FIXME;
+	code = FPE_FLTUNK;
 	if ((fsr & 0x1c000) == (1 << 14)) {
 		if (fsr & 0x10)
-			info.si_code = FPE_FLTINV;
+			code = FPE_FLTINV;
 		else if (fsr & 0x08)
-			info.si_code = FPE_FLTOVF;
+			code = FPE_FLTOVF;
 		else if (fsr & 0x04)
-			info.si_code = FPE_FLTUND;
+			code = FPE_FLTUND;
 		else if (fsr & 0x02)
-			info.si_code = FPE_FLTDIV;
+			code = FPE_FLTDIV;
 		else if (fsr & 0x01)
-			info.si_code = FPE_FLTRES;
+			code = FPE_FLTRES;
 	}
-	send_sig_info(SIGFPE, &info, fpt);
+	send_sig_fault(SIGFPE, code, (void __user *)pc, 0, fpt);
 #ifndef CONFIG_SMP
 	last_task_used_math = NULL;
 #endif
@@ -332,16 +303,9 @@ void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 void handle_tag_overflow(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 			 unsigned long psr)
 {
-	siginfo_t info;
-
 	if(psr & PSR_PS)
 		die_if_kernel("Penguin overflow trap from kernel mode", regs);
-	info.si_signo = SIGEMT;
-	info.si_errno = 0;
-	info.si_code = EMT_TAGOVF;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	send_sig_info(SIGEMT, &info, current);
+	send_sig_fault(SIGEMT, EMT_TAGOVF, (void __user *)pc, 0, current);
 }
 
 void handle_watchpoint(struct pt_regs *regs, unsigned long pc, unsigned long npc,
@@ -359,61 +323,33 @@ void handle_watchpoint(struct pt_regs *regs, unsigned long pc, unsigned long npc
 void handle_reg_access(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 		       unsigned long psr)
 {
-	siginfo_t info;
-
 #ifdef TRAP_DEBUG
 	printk("Register Access Exception at PC %08lx NPC %08lx PSR %08lx\n",
 	       pc, npc, psr);
 #endif
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_OBJERR;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)pc, 0, current);
 }
 
 void handle_cp_disabled(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 			unsigned long psr)
 {
-	siginfo_t info;
-
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_COPROC;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	send_sig_info(SIGILL, &info, current);
+	send_sig_fault(SIGILL, ILL_COPROC, (void __user *)pc, 0, current);
 }
 
 void handle_cp_exception(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 			 unsigned long psr)
 {
-	siginfo_t info;
-
 #ifdef TRAP_DEBUG
 	printk("Co-Processor Exception at PC %08lx NPC %08lx PSR %08lx\n",
 	       pc, npc, psr);
 #endif
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_COPROC;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	send_sig_info(SIGILL, &info, current);
+	send_sig_fault(SIGILL, ILL_COPROC, (void __user *)pc, 0, current);
 }
 
 void handle_hw_divzero(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 		       unsigned long psr)
 {
-	siginfo_t info;
-
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_code = FPE_INTDIV;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	send_sig_info(SIGFPE, &info, current);
+	send_sig_fault(SIGFPE, FPE_INTDIV, (void __user *)pc, 0, current);
 }
 
 #ifdef CONFIG_DEBUG_BUGVERBOSE
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 462a21abd105..aa624ed79db1 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -87,7 +87,6 @@ static void dump_tl1_traplog(struct tl1_traplog *p)
 void bad_trap(struct pt_regs *regs, long lvl)
 {
 	char buffer[36];
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "bad trap", regs,
 		       0, lvl, SIGTRAP) == NOTIFY_STOP)
@@ -107,12 +106,8 @@ void bad_trap(struct pt_regs *regs, long lvl)
 		regs->tpc &= 0xffffffff;
 		regs->tnpc &= 0xffffffff;
 	}
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_ILLTRP;
-	info.si_addr = (void __user *)regs->tpc;
-	info.si_trapno = lvl;
-	force_sig_info(SIGILL, &info, current);
+	force_sig_fault(SIGILL, ILL_ILLTRP,
+			(void __user *)regs->tpc, lvl, current);
 }
 
 void bad_trap_tl1(struct pt_regs *regs, long lvl)
@@ -191,7 +186,6 @@ EXPORT_SYMBOL_GPL(unregister_dimm_printer);
 void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
 {
 	enum ctx_state prev_state = exception_enter();
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "instruction access exception", regs,
 		       0, 0x8, SIGTRAP) == NOTIFY_STOP)
@@ -206,12 +200,8 @@ void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, un
 		regs->tpc &= 0xffffffff;
 		regs->tnpc &= 0xffffffff;
 	}
-	info.si_signo = SIGSEGV;
-	info.si_errno = 0;
-	info.si_code = SEGV_MAPERR;
-	info.si_addr = (void __user *)regs->tpc;
-	info.si_trapno = 0;
-	force_sig_info(SIGSEGV, &info, current);
+	force_sig_fault(SIGSEGV, SEGV_MAPERR,
+			(void __user *)regs->tpc, 0, current);
 out:
 	exception_exit(prev_state);
 }
@@ -230,7 +220,6 @@ void sun4v_insn_access_exception(struct pt_regs *regs, unsigned long addr, unsig
 {
 	unsigned short type = (type_ctx >> 16);
 	unsigned short ctx  = (type_ctx & 0xffff);
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "instruction access exception", regs,
 		       0, 0x8, SIGTRAP) == NOTIFY_STOP)
@@ -247,12 +236,7 @@ void sun4v_insn_access_exception(struct pt_regs *regs, unsigned long addr, unsig
 		regs->tpc &= 0xffffffff;
 		regs->tnpc &= 0xffffffff;
 	}
-	info.si_signo = SIGSEGV;
-	info.si_errno = 0;
-	info.si_code = SEGV_MAPERR;
-	info.si_addr = (void __user *) addr;
-	info.si_trapno = 0;
-	force_sig_info(SIGSEGV, &info, current);
+	force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *) addr, 0, current);
 }
 
 void sun4v_insn_access_exception_tl1(struct pt_regs *regs, unsigned long addr, unsigned long type_ctx)
@@ -307,7 +291,6 @@ bool is_no_fault_exception(struct pt_regs *regs)
 void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
 {
 	enum ctx_state prev_state = exception_enter();
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "data access exception", regs,
 		       0, 0x30, SIGTRAP) == NOTIFY_STOP)
@@ -338,12 +321,7 @@ void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, un
 	if (is_no_fault_exception(regs))
 		return;
 
-	info.si_signo = SIGSEGV;
-	info.si_errno = 0;
-	info.si_code = SEGV_MAPERR;
-	info.si_addr = (void __user *)sfar;
-	info.si_trapno = 0;
-	force_sig_info(SIGSEGV, &info, current);
+	force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)sfar, 0, current);
 out:
 	exception_exit(prev_state);
 }
@@ -559,8 +537,6 @@ static void spitfire_cee_log(unsigned long afsr, unsigned long afar, unsigned lo
 
 static void spitfire_ue_log(unsigned long afsr, unsigned long afar, unsigned long udbh, unsigned long udbl, unsigned long tt, int tl1, struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	printk(KERN_WARNING "CPU[%d]: Uncorrectable Error AFSR[%lx] "
 	       "AFAR[%lx] UDBL[%lx] UDBH[%ld] TT[%lx] TL>1[%d]\n",
 	       smp_processor_id(), afsr, afar, udbl, udbh, tt, tl1);
@@ -595,12 +571,7 @@ static void spitfire_ue_log(unsigned long afsr, unsigned long afar, unsigned lon
 		regs->tpc &= 0xffffffff;
 		regs->tnpc &= 0xffffffff;
 	}
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_OBJERR;
-	info.si_addr = (void *)0;
-	info.si_trapno = 0;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_OBJERR, (void *)0, 0, current);
 }
 
 void spitfire_access_error(struct pt_regs *regs, unsigned long status_encoded, unsigned long afar)
@@ -2190,7 +2161,6 @@ bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
 
 	if (attrs & SUN4V_ERR_ATTRS_MEMORY) {
 		unsigned long addr = ent->err_raddr;
-		siginfo_t info;
 
 		if (addr == ~(u64)0) {
 			/* This seems highly unlikely to ever occur */
@@ -2211,21 +2181,13 @@ bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
 				addr += PAGE_SIZE;
 			}
 		}
-		info.si_signo = SIGKILL;
-		info.si_errno = 0;
-		info.si_trapno = 0;
-		force_sig_info(info.si_signo, &info, current);
+		force_sig(SIGKILL, current);
 
 		return true;
 	}
 	if (attrs & SUN4V_ERR_ATTRS_PIO) {
-		siginfo_t info;
-
-		info.si_signo = SIGBUS;
-		info.si_code = BUS_ADRERR;
-		info.si_addr = (void __user *)sun4v_get_vaddr(regs);
-		force_sig_info(info.si_signo, &info, current);
-
+		force_sig_fault(SIGBUS, BUS_ADRERR,
+				(void __user *)sun4v_get_vaddr(regs), 0, current);
 		return true;
 	}
 
@@ -2362,30 +2324,27 @@ static void do_fpe_common(struct pt_regs *regs)
 		regs->tnpc += 4;
 	} else {
 		unsigned long fsr = current_thread_info()->xfsr[0];
-		siginfo_t info;
+		int code;
 
 		if (test_thread_flag(TIF_32BIT)) {
 			regs->tpc &= 0xffffffff;
 			regs->tnpc &= 0xffffffff;
 		}
-		info.si_signo = SIGFPE;
-		info.si_errno = 0;
-		info.si_addr = (void __user *)regs->tpc;
-		info.si_trapno = 0;
-		info.si_code = FPE_FIXME;
+		code = FPE_FLTUNK;
 		if ((fsr & 0x1c000) == (1 << 14)) {
 			if (fsr & 0x10)
-				info.si_code = FPE_FLTINV;
+				code = FPE_FLTINV;
 			else if (fsr & 0x08)
-				info.si_code = FPE_FLTOVF;
+				code = FPE_FLTOVF;
 			else if (fsr & 0x04)
-				info.si_code = FPE_FLTUND;
+				code = FPE_FLTUND;
 			else if (fsr & 0x02)
-				info.si_code = FPE_FLTDIV;
+				code = FPE_FLTDIV;
 			else if (fsr & 0x01)
-				info.si_code = FPE_FLTRES;
+				code = FPE_FLTRES;
 		}
-		force_sig_info(SIGFPE, &info, current);
+		force_sig_fault(SIGFPE, code,
+				(void __user *)regs->tpc, 0, current);
 	}
 }
 
@@ -2428,7 +2387,6 @@ out:
 void do_tof(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "tagged arithmetic overflow", regs,
 		       0, 0x26, SIGEMT) == NOTIFY_STOP)
@@ -2440,12 +2398,8 @@ void do_tof(struct pt_regs *regs)
 		regs->tpc &= 0xffffffff;
 		regs->tnpc &= 0xffffffff;
 	}
-	info.si_signo = SIGEMT;
-	info.si_errno = 0;
-	info.si_code = EMT_TAGOVF;
-	info.si_addr = (void __user *)regs->tpc;
-	info.si_trapno = 0;
-	force_sig_info(SIGEMT, &info, current);
+	force_sig_fault(SIGEMT, EMT_TAGOVF,
+			(void __user *)regs->tpc, 0, current);
 out:
 	exception_exit(prev_state);
 }
@@ -2453,7 +2407,6 @@ out:
 void do_div0(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "integer division by zero", regs,
 		       0, 0x28, SIGFPE) == NOTIFY_STOP)
@@ -2465,12 +2418,8 @@ void do_div0(struct pt_regs *regs)
 		regs->tpc &= 0xffffffff;
 		regs->tnpc &= 0xffffffff;
 	}
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_code = FPE_INTDIV;
-	info.si_addr = (void __user *)regs->tpc;
-	info.si_trapno = 0;
-	force_sig_info(SIGFPE, &info, current);
+	force_sig_fault(SIGFPE, FPE_INTDIV,
+			(void __user *)regs->tpc, 0, current);
 out:
 	exception_exit(prev_state);
 }
@@ -2632,7 +2581,6 @@ void do_illegal_instruction(struct pt_regs *regs)
 	unsigned long pc = regs->tpc;
 	unsigned long tstate = regs->tstate;
 	u32 insn;
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "illegal instruction", regs,
 		       0, 0x10, SIGILL) == NOTIFY_STOP)
@@ -2666,12 +2614,7 @@ void do_illegal_instruction(struct pt_regs *regs)
 			}
 		}
 	}
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_ILLOPC;
-	info.si_addr = (void __user *)pc;
-	info.si_trapno = 0;
-	force_sig_info(SIGILL, &info, current);
+	force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)pc, 0, current);
 out:
 	exception_exit(prev_state);
 }
@@ -2679,7 +2622,6 @@ out:
 void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr)
 {
 	enum ctx_state prev_state = exception_enter();
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "memory address unaligned", regs,
 		       0, 0x34, SIGSEGV) == NOTIFY_STOP)
@@ -2692,20 +2634,13 @@ void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned lo
 	if (is_no_fault_exception(regs))
 		return;
 
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRALN;
-	info.si_addr = (void __user *)sfar;
-	info.si_trapno = 0;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)sfar, 0, current);
 out:
 	exception_exit(prev_state);
 }
 
 void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_ctx)
 {
-	siginfo_t info;
-
 	if (notify_die(DIE_TRAP, "memory address unaligned", regs,
 		       0, 0x34, SIGSEGV) == NOTIFY_STOP)
 		return;
@@ -2717,12 +2652,7 @@ void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_c
 	if (is_no_fault_exception(regs))
 		return;
 
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRALN;
-	info.si_addr = (void __user *) addr;
-	info.si_trapno = 0;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) addr, 0, current);
 }
 
 /* sun4v_mem_corrupt_detect_precise() - Handle precise exception on an ADI
@@ -2775,7 +2705,6 @@ void sun4v_mem_corrupt_detect_precise(struct pt_regs *regs, unsigned long addr,
 void do_privop(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "privileged operation", regs,
 		       0, 0x11, SIGILL) == NOTIFY_STOP)
@@ -2785,12 +2714,8 @@ void do_privop(struct pt_regs *regs)
 		regs->tpc &= 0xffffffff;
 		regs->tnpc &= 0xffffffff;
 	}
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_PRVOPC;
-	info.si_addr = (void __user *)regs->tpc;
-	info.si_trapno = 0;
-	force_sig_info(SIGILL, &info, current);
+	force_sig_fault(SIGILL, ILL_PRVOPC,
+			(void __user *)regs->tpc, 0, current);
 out:
 	exception_exit(prev_state);
 }
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 7642d7e4f0d9..64ac8c0c1429 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -311,14 +311,9 @@ static inline int ok_for_user(struct pt_regs *regs, unsigned int insn,
 
 static void user_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
 {
-	siginfo_t info;
-
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRALN;
-	info.si_addr = (void __user *)safe_compute_effective_address(regs, insn);
-	info.si_trapno = 0;
-	send_sig_info(SIGBUS, &info, current);
+	send_sig_fault(SIGBUS, BUS_ADRALN,
+		       (void __user *)safe_compute_effective_address(regs, insn),
+		       0, current);
 }
 
 asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index 1a0fa10cb6b7..32bae68e34c1 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -403,7 +403,7 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 	if (err) {
 		printk(KERN_ERR "VIO: Could not register device %s, err=%d\n",
 		       dev_name(&vdev->dev), err);
-		kfree(vdev);
+		put_device(&vdev->dev);
 		return NULL;
 	}
 	if (vdev->dp)
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index a8103a84b4ac..9f75b6444bf1 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -127,19 +127,11 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 static void __do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 			       unsigned long addr)
 {
-	siginfo_t info;
-
-	info.si_signo = sig;
-	info.si_code = code;
-	info.si_errno = 0;
-	info.si_addr = (void __user *) addr;
-	info.si_trapno = 0;
-
 	if (unlikely(show_unhandled_signals))
-		show_signal_msg(regs, sig, info.si_code,
+		show_signal_msg(regs, sig, code,
 				addr, current);
 
-	force_sig_info (sig, &info, current);
+	force_sig_fault(sig, code, (void __user *) addr, 0, current);
 }
 
 static unsigned long compute_si_addr(struct pt_regs *regs, int text_fault)
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 41363f46797b..63166fcf9e25 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -170,11 +170,7 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 			     int fault_code)
 {
 	unsigned long addr;
-	siginfo_t info;
 
-	info.si_code = code;
-	info.si_signo = sig;
-	info.si_errno = 0;
 	if (fault_code & FAULT_CODE_ITLB) {
 		addr = regs->tpc;
 	} else {
@@ -187,13 +183,11 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 		else
 			addr = fault_addr;
 	}
-	info.si_addr = (void __user *) addr;
-	info.si_trapno = 0;
 
 	if (unlikely(show_unhandled_signals))
 		show_signal_msg(regs, sig, code, addr, current);
 
-	force_sig_info(sig, &info, current);
+	force_sig_fault(sig, code, (void __user *) addr, 0, current);
 }
 
 static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn)
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index c68add8df3ae..07f84c842cc3 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -54,10 +54,6 @@ config HZ
 	int
 	default 100
 
-config SUBARCH
-	string
-	option env="SUBARCH"
-
 config NR_CPUS
 	int
 	range 1 1
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index d4e8c497ae86..dcf5ea28a281 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -208,19 +208,6 @@ static int fake_ide_media_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int fake_ide_media_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, fake_ide_media_proc_show, NULL);
-}
-
-static const struct file_operations fake_ide_media_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= fake_ide_media_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static void make_ide_entries(const char *dev_name)
 {
 	struct proc_dir_entry *dir, *ent;
@@ -231,7 +218,8 @@ static void make_ide_entries(const char *dev_name)
 	dir = proc_mkdir(dev_name, proc_ide);
 	if(!dir) return;
 
-	ent = proc_create("media", S_IRUGO, dir, &fake_ide_media_proc_fops);
+	ent = proc_create_single("media", S_IRUGO, dir,
+			fake_ide_media_proc_show);
 	if(!ent) return;
 	snprintf(name, sizeof(name), "ide0/%s", dev_name);
 	proc_symlink(dev_name, proc_ide_root, name);
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index bb5a196c3061..b10dde6cb793 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,6 +1,7 @@
 generic-y += barrier.h
 generic-y += bpf_perf_event.h
 generic-y += bug.h
+generic-y += compat.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += device.h
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index bc2a516c190f..1a1d88a4d940 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -115,17 +115,10 @@ long arch_ptrace(struct task_struct *child, long request,
 static void send_sigtrap(struct task_struct *tsk, struct uml_pt_regs *regs,
 		  int error_code)
 {
-	struct siginfo info;
-
-	memset(&info, 0, sizeof(info));
-	info.si_signo = SIGTRAP;
-	info.si_code = TRAP_BRKPT;
-
-	/* User-mode eip? */
-	info.si_addr = UPT_IS_USER(regs) ? (void __user *) UPT_IP(regs) : NULL;
-
 	/* Send us the fake SIGTRAP */
-	force_sig_info(SIGTRAP, &info, tsk);
+	force_sig_fault(SIGTRAP, TRAP_BRKPT,
+			/* User-mode eip? */
+			UPT_IS_USER(regs) ? (void __user *) UPT_IP(regs) : NULL, tsk);
 }
 
 /*
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index b2b02df9896e..ec9a42c14c56 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -162,13 +162,9 @@ static void show_segv_info(struct uml_pt_regs *regs)
 
 static void bad_segv(struct faultinfo fi, unsigned long ip)
 {
-	struct siginfo si;
-
-	si.si_signo = SIGSEGV;
-	si.si_code = SEGV_ACCERR;
-	si.si_addr = (void __user *) FAULT_ADDRESS(fi);
 	current->thread.arch.faultinfo = fi;
-	force_sig_info(SIGSEGV, &si, current);
+	force_sig_fault(SIGSEGV, SEGV_ACCERR, (void __user *) FAULT_ADDRESS(fi),
+			current);
 }
 
 void fatal_sigsegv(void)
@@ -214,8 +210,8 @@ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
 unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 		   struct uml_pt_regs *regs)
 {
-	struct siginfo si;
 	jmp_buf *catcher;
+	int si_code;
 	int err;
 	int is_write = FAULT_WRITE(fi);
 	unsigned long address = FAULT_ADDRESS(fi);
@@ -239,7 +235,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 
 	if (SEGV_IS_FIXABLE(&fi))
 		err = handle_page_fault(address, ip, is_write, is_user,
-					&si.si_code);
+					&si_code);
 	else {
 		err = -EFAULT;
 		/*
@@ -271,18 +267,14 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 	show_segv_info(regs);
 
 	if (err == -EACCES) {
-		si.si_signo = SIGBUS;
-		si.si_errno = 0;
-		si.si_code = BUS_ADRERR;
-		si.si_addr = (void __user *)address;
 		current->thread.arch.faultinfo = fi;
-		force_sig_info(SIGBUS, &si, current);
+		force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address,
+				current);
 	} else {
 		BUG_ON(err != -EFAULT);
-		si.si_signo = SIGSEGV;
-		si.si_addr = (void __user *) address;
 		current->thread.arch.faultinfo = fi;
-		force_sig_info(SIGSEGV, &si, current);
+		force_sig_fault(SIGSEGV, si_code, (void __user *) address,
+				current);
 	}
 
 out:
@@ -294,9 +286,7 @@ out:
 
 void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
 {
-	struct faultinfo *fi;
-	struct siginfo clean_si;
-
+	int code, err;
 	if (!UPT_IS_USER(regs)) {
 		if (sig == SIGBUS)
 			printk(KERN_ERR "Bus error - the host /dev/shm or /tmp "
@@ -306,29 +296,21 @@ void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
 
 	arch_examine_signal(sig, regs);
 
-	clear_siginfo(&clean_si);
-	clean_si.si_signo = si->si_signo;
-	clean_si.si_errno = si->si_errno;
-	clean_si.si_code = si->si_code;
-	switch (sig) {
-	case SIGILL:
-	case SIGFPE:
-	case SIGSEGV:
-	case SIGBUS:
-	case SIGTRAP:
-		fi = UPT_FAULTINFO(regs);
-		clean_si.si_addr = (void __user *) FAULT_ADDRESS(*fi);
+	/* Is the signal layout for the signal known?
+	 * Signal data must be scrubbed to prevent information leaks.
+	 */
+	code = si->si_code;
+	err = si->si_errno;
+	if ((err == 0) && (siginfo_layout(sig, code) == SIL_FAULT)) {
+		struct faultinfo *fi = UPT_FAULTINFO(regs);
 		current->thread.arch.faultinfo = *fi;
-#ifdef __ARCH_SI_TRAPNO
-		clean_si.si_trapno = si->si_trapno;
-#endif
-		break;
-	default:
-		printk(KERN_ERR "Attempted to relay unknown signal %d (si_code = %d)\n",
-			sig, si->si_code);
+		force_sig_fault(sig, code, (void __user *)FAULT_ADDRESS(*fi),
+				current);
+	} else {
+		printk(KERN_ERR "Attempted to relay unknown signal %d (si_code = %d) with errno %d\n",
+		       sig, code, err);
+		force_sig(sig, current);
 	}
-
-	force_sig_info(sig, &clean_si, current);
 }
 
 void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs)
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 462e59a7ae78..03f991e44288 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -19,6 +19,8 @@ config UNICORE32
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IOMAP
 	select MODULES_USE_ELF_REL
+	select NEED_DMA_MAP_STATE
+	select SWIOTLB
 	help
 	  UniCore-32 is 32-bit Instruction Set Architecture,
 	  including a series of low-power-consumption RISC chip
@@ -61,9 +63,6 @@ config ARCH_MAY_HAVE_PC_FDC
 config ZONE_DMA
 	def_bool y
 
-config NEED_DMA_MAP_STATE
-       def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 6f70c76c81fc..bfc7abe77905 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -1,5 +1,6 @@
 generic-y += atomic.h
 generic-y += bugs.h
+generic-y += compat.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/unicore32/kernel/fpu-ucf64.c b/arch/unicore32/kernel/fpu-ucf64.c
index 12c8c9527b8e..8594b168f25e 100644
--- a/arch/unicore32/kernel/fpu-ucf64.c
+++ b/arch/unicore32/kernel/fpu-ucf64.c
@@ -52,14 +52,14 @@
  * Raise a SIGFPE for the current process.
  * sicode describes the signal being raised.
  */
-void ucf64_raise_sigfpe(unsigned int sicode, struct pt_regs *regs)
+void ucf64_raise_sigfpe(struct pt_regs *regs)
 {
 	siginfo_t info;
 
-	memset(&info, 0, sizeof(info));
+	clear_siginfo(&info);
 
 	info.si_signo = SIGFPE;
-	info.si_code = sicode;
+	info.si_code = FPE_FLTUNK;
 	info.si_addr = (void __user *)(instruction_pointer(regs) - 4);
 
 	/*
@@ -94,7 +94,7 @@ void ucf64_exchandler(u32 inst, u32 fpexc, struct pt_regs *regs)
 		pr_debug("UniCore-F64 FPSCR 0x%08x INST 0x%08x\n",
 				cff(FPSCR), inst);
 
-		ucf64_raise_sigfpe(0, regs);
+		ucf64_raise_sigfpe(regs);
 		return;
 	}
 
diff --git a/arch/unicore32/mm/Kconfig b/arch/unicore32/mm/Kconfig
index e9154a59d561..82759b6aba67 100644
--- a/arch/unicore32/mm/Kconfig
+++ b/arch/unicore32/mm/Kconfig
@@ -39,14 +39,3 @@ config CPU_TLB_SINGLE_ENTRY_DISABLE
 	default y
 	help
 	  Say Y here to disable the TLB single entry operations.
-
-config SWIOTLB
-	def_bool y
-	select DMA_DIRECT_OPS
-
-config IOMMU_HELPER
-	def_bool SWIOTLB
-
-config NEED_SG_DMA_LENGTH
-	def_bool SWIOTLB
-
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index bbefcc46a45e..381473412937 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -125,6 +125,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 	tsk->thread.address = addr;
 	tsk->thread.error_code = fsr;
 	tsk->thread.trap_no = 14;
+	clear_siginfo(&si);
 	si.si_signo = sig;
 	si.si_errno = 0;
 	si.si_code = code;
@@ -472,6 +473,7 @@ asmlinkage void do_DataAbort(unsigned long addr, unsigned int fsr,
 	printk(KERN_ALERT "Unhandled fault: %s (0x%03x) at 0x%08lx\n",
 	       inf->name, fsr, addr);
 
+	clear_siginfo(&info);
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code = inf->code;
@@ -491,6 +493,7 @@ asmlinkage void do_PrefetchAbort(unsigned long addr,
 	printk(KERN_ALERT "Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
 	       inf->name, ifsr, addr);
 
+	clear_siginfo(&info);
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code = inf->code;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 00fcf81f2c56..ed796c92701f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Select 32 or 64 bit
 config 64BIT
-	bool "64-bit kernel" if ARCH = "x86"
-	default ARCH != "i386"
+	bool "64-bit kernel" if "$(ARCH)" = "x86"
+	default "$(ARCH)" != "i386"
 	---help---
 	  Say yes to build a 64-bit kernel - formerly known as x86_64
 	  Say no to build a 32-bit kernel - formerly known as i386
@@ -28,6 +28,8 @@ config X86_64
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA
+	select NEED_DMA_MAP_STATE
+	select SWIOTLB
 	select X86_DEV_DMA_OPS
 	select ARCH_HAS_SYSCALL_WRAPPER
 
@@ -52,6 +54,7 @@ config X86
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
+	select ARCH_HAS_FILTER_PGPROT
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
@@ -59,6 +62,7 @@ config X86
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
+	select ARCH_HAS_UACCESS_MCSAFE		if X86_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
@@ -133,7 +137,6 @@ config X86
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
@@ -183,6 +186,7 @@ config X86
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
 	select IRQ_FORCED_THREADING
+	select NEED_SG_DMA_LENGTH
 	select PCI_LOCKLESS_CONFIG
 	select PERF_EVENTS
 	select RTC_LIB
@@ -235,13 +239,6 @@ config ARCH_MMAP_RND_COMPAT_BITS_MAX
 config SBUS
 	bool
 
-config NEED_DMA_MAP_STATE
-	def_bool y
-	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB
-
-config NEED_SG_DMA_LENGTH
-	def_bool y
-
 config GENERIC_ISA_DMA
 	def_bool y
 	depends on ISA_DMA_API
@@ -273,6 +270,9 @@ config ARCH_HAS_CPU_RELAX
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
+config ARCH_HAS_FILTER_PGPROT
+	def_bool y
+
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
@@ -871,6 +871,7 @@ config DMI
 
 config GART_IOMMU
 	bool "Old AMD GART IOMMU support"
+	select IOMMU_HELPER
 	select SWIOTLB
 	depends on X86_64 && PCI && AMD_NB
 	---help---
@@ -892,6 +893,7 @@ config GART_IOMMU
 
 config CALGARY_IOMMU
 	bool "IBM Calgary IOMMU support"
+	select IOMMU_HELPER
 	select SWIOTLB
 	depends on X86_64 && PCI
 	---help---
@@ -919,20 +921,6 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT
 	  Calgary anyway, pass 'iommu=calgary' on the kernel command line.
 	  If unsure, say Y.
 
-# need this always selected by IOMMU for the VIA workaround
-config SWIOTLB
-	def_bool y if X86_64
-	---help---
-	  Support for software bounce buffers used on x86-64 systems
-	  which don't have a hardware IOMMU. Using this PCI devices
-	  which can only access 32-bits of memory can be used on systems
-	  with more than 3 GB of memory.
-	  If unsure, say Y.
-
-config IOMMU_HELPER
-	def_bool y
-	depends on CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU
-
 config MAXSMP
 	bool "Enable Maximum number of SMP Processors and NUMA Nodes"
 	depends on X86_64 && SMP && DEBUG_KERNEL
@@ -1454,6 +1442,7 @@ config HIGHMEM
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
 	depends on X86_32 && !HIGHMEM4G
+	select PHYS_ADDR_T_64BIT
 	select SWIOTLB
 	---help---
 	  PAE is required for NX support, and furthermore enables
@@ -1481,14 +1470,6 @@ config X86_5LEVEL
 
 	  Say N if unsure.
 
-config ARCH_PHYS_ADDR_T_64BIT
-	def_bool y
-	depends on X86_64 || X86_PAE
-
-config ARCH_DMA_ADDR_T_64BIT
-	def_bool y
-	depends on X86_64 || HIGHMEM64G
-
 config X86_DIRECT_GBPAGES
 	def_bool y
 	depends on X86_64 && !DEBUG_PAGEALLOC
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 60135cbd905c..f0a6ea22429d 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -94,7 +94,7 @@ ifeq ($(CONFIG_X86_32),y)
 else
         BITS := 64
         UTS_MACHINE := x86_64
-        CHECKFLAGS += -D__x86_64__ -m64
+        CHECKFLAGS += -D__x86_64__
 
         biarch := -m64
         KBUILD_AFLAGS += -m64
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index 0cb325734cfb..af6cda0b7900 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
 
-#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE || CONFIG_X86_5LEVEL
 
 static unsigned long fs;
 static inline void set_fs(unsigned long seg)
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 47d3efff6805..a8a8642d2b0b 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -109,23 +109,34 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 }
 
 static efi_status_t
-__setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
+__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 {
 	struct pci_setup_rom *rom = NULL;
 	efi_status_t status;
 	unsigned long size;
-	uint64_t attributes;
+	uint64_t attributes, romsize;
+	void *romimage;
 
-	status = efi_early->call(pci->attributes, pci,
-				 EfiPciIoAttributeOperationGet, 0, 0,
-				 &attributes);
+	status = efi_call_proto(efi_pci_io_protocol, attributes, pci,
+				EfiPciIoAttributeOperationGet, 0, 0,
+				&attributes);
 	if (status != EFI_SUCCESS)
 		return status;
 
-	if (!pci->romimage || !pci->romsize)
+	/*
+	 * Some firmware images contain EFI function pointers at the place where the
+	 * romimage and romsize fields are supposed to be. Typically the EFI
+	 * code is mapped at high addresses, translating to an unrealistically
+	 * large romsize. The UEFI spec limits the size of option ROMs to 16
+	 * MiB so we reject any ROMs over 16 MiB in size to catch this.
+	 */
+	romimage = (void *)(unsigned long)efi_table_attr(efi_pci_io_protocol,
+							 romimage, pci);
+	romsize = efi_table_attr(efi_pci_io_protocol, romsize, pci);
+	if (!romimage || !romsize || romsize > SZ_16M)
 		return EFI_INVALID_PARAMETER;
 
-	size = pci->romsize + sizeof(*rom);
+	size = romsize + sizeof(*rom);
 
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
 	if (status != EFI_SUCCESS) {
@@ -141,29 +152,32 @@ __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
 	rom->pcilen = pci->romsize;
 	*__rom = rom;
 
-	status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
-				 PCI_VENDOR_ID, 1, &(rom->vendor));
+	status = efi_call_proto(efi_pci_io_protocol, pci.read, pci,
+				EfiPciIoWidthUint16, PCI_VENDOR_ID, 1,
+				&rom->vendor);
 
 	if (status != EFI_SUCCESS) {
 		efi_printk(sys_table, "Failed to read rom->vendor\n");
 		goto free_struct;
 	}
 
-	status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
-				 PCI_DEVICE_ID, 1, &(rom->devid));
+	status = efi_call_proto(efi_pci_io_protocol, pci.read, pci,
+				EfiPciIoWidthUint16, PCI_DEVICE_ID, 1,
+				&rom->devid);
 
 	if (status != EFI_SUCCESS) {
 		efi_printk(sys_table, "Failed to read rom->devid\n");
 		goto free_struct;
 	}
 
-	status = efi_early->call(pci->get_location, pci, &(rom->segment),
-				 &(rom->bus), &(rom->device), &(rom->function));
+	status = efi_call_proto(efi_pci_io_protocol, get_location, pci,
+				&rom->segment, &rom->bus, &rom->device,
+				&rom->function);
 
 	if (status != EFI_SUCCESS)
 		goto free_struct;
 
-	memcpy(rom->romdata, pci->romimage, pci->romsize);
+	memcpy(rom->romdata, romimage, romsize);
 	return status;
 
 free_struct:
@@ -175,7 +189,7 @@ static void
 setup_efi_pci32(struct boot_params *params, void **pci_handle,
 		unsigned long size)
 {
-	efi_pci_io_protocol_32 *pci = NULL;
+	efi_pci_io_protocol_t *pci = NULL;
 	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
 	u32 *handles = (u32 *)(unsigned long)pci_handle;
 	efi_status_t status;
@@ -202,7 +216,7 @@ setup_efi_pci32(struct boot_params *params, void **pci_handle,
 		if (!pci)
 			continue;
 
-		status = __setup_efi_pci32(pci, &rom);
+		status = __setup_efi_pci(pci, &rom);
 		if (status != EFI_SUCCESS)
 			continue;
 
@@ -216,73 +230,11 @@ setup_efi_pci32(struct boot_params *params, void **pci_handle,
 	}
 }
 
-static efi_status_t
-__setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom)
-{
-	struct pci_setup_rom *rom;
-	efi_status_t status;
-	unsigned long size;
-	uint64_t attributes;
-
-	status = efi_early->call(pci->attributes, pci,
-				 EfiPciIoAttributeOperationGet, 0,
-				 &attributes);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	if (!pci->romimage || !pci->romsize)
-		return EFI_INVALID_PARAMETER;
-
-	size = pci->romsize + sizeof(*rom);
-
-	status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for rom\n");
-		return status;
-	}
-
-	rom->data.type = SETUP_PCI;
-	rom->data.len = size - sizeof(struct setup_data);
-	rom->data.next = 0;
-	rom->pcilen = pci->romsize;
-	*__rom = rom;
-
-	status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
-				 PCI_VENDOR_ID, 1, &(rom->vendor));
-
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to read rom->vendor\n");
-		goto free_struct;
-	}
-
-	status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
-				 PCI_DEVICE_ID, 1, &(rom->devid));
-
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to read rom->devid\n");
-		goto free_struct;
-	}
-
-	status = efi_early->call(pci->get_location, pci, &(rom->segment),
-				 &(rom->bus), &(rom->device), &(rom->function));
-
-	if (status != EFI_SUCCESS)
-		goto free_struct;
-
-	memcpy(rom->romdata, pci->romimage, pci->romsize);
-	return status;
-
-free_struct:
-	efi_call_early(free_pool, rom);
-	return status;
-
-}
-
 static void
 setup_efi_pci64(struct boot_params *params, void **pci_handle,
 		unsigned long size)
 {
-	efi_pci_io_protocol_64 *pci = NULL;
+	efi_pci_io_protocol_t *pci = NULL;
 	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
 	u64 *handles = (u64 *)(unsigned long)pci_handle;
 	efi_status_t status;
@@ -309,7 +261,7 @@ setup_efi_pci64(struct boot_params *params, void **pci_handle,
 		if (!pci)
 			continue;
 
-		status = __setup_efi_pci64(pci, &rom);
+		status = __setup_efi_pci(pci, &rom);
 		if (status != EFI_SUCCESS)
 			continue;
 
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index fca012baba19..64037895b085 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -306,6 +306,25 @@ ENTRY(startup_64)
 	leaq	boot_stack_end(%rbx), %rsp
 
 	/*
+	 * paging_prepare() and cleanup_trampoline() below can have GOT
+	 * references. Adjust the table with address we are running at.
+	 *
+	 * Zero RAX for adjust_got: the GOT was not adjusted before;
+	 * there's no adjustment to undo.
+	 */
+	xorq	%rax, %rax
+
+	/*
+	 * Calculate the address the binary is loaded at and use it as
+	 * a GOT adjustment.
+	 */
+	call	1f
+1:	popq	%rdi
+	subq	$1b, %rdi
+
+	call	adjust_got
+
+	/*
 	 * At this point we are in long mode with 4-level paging enabled,
 	 * but we might want to enable 5-level paging or vice versa.
 	 *
@@ -346,6 +365,7 @@ ENTRY(startup_64)
 	 * this function call.
 	 */
 	pushq	%rsi
+	movq	%rsi, %rdi		/* real mode address */
 	call	paging_prepare
 	popq	%rsi
 
@@ -370,10 +390,14 @@ trampoline_return:
 	/*
 	 * cleanup_trampoline() would restore trampoline memory.
 	 *
+	 * RDI is address of the page table to use instead of page table
+	 * in trampoline memory (if required).
+	 *
 	 * RSI holds real mode data and needs to be preserved across
 	 * this function call.
 	 */
 	pushq	%rsi
+	leaq	top_pgtable(%rbx), %rdi
 	call	cleanup_trampoline
 	popq	%rsi
 
@@ -381,6 +405,21 @@ trampoline_return:
 	pushq	$0
 	popfq
 
+	/*
+	 * Previously we've adjusted the GOT with address the binary was
+	 * loaded at. Now we need to re-adjust for relocation address.
+	 *
+	 * Calculate the address the binary is loaded at, so that we can
+	 * undo the previous GOT adjustment.
+	 */
+	call	1f
+1:	popq	%rax
+	subq	$1b, %rax
+
+	/* The new adjustment is the relocation address */
+	movq	%rbx, %rdi
+	call	adjust_got
+
 /*
  * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
@@ -482,19 +521,6 @@ relocated:
 	rep	stosq
 
 /*
- * Adjust our own GOT
- */
-	leaq	_got(%rip), %rdx
-	leaq	_egot(%rip), %rcx
-1:
-	cmpq	%rcx, %rdx
-	jae	2f
-	addq	%rbx, (%rdx)
-	addq	$8, %rdx
-	jmp	1b
-2:
-	
-/*
  * Do the extraction, and jump to the new kernel..
  */
 	pushq	%rsi			/* Save the real mode argument */
@@ -512,6 +538,27 @@ relocated:
  */
 	jmp	*%rax
 
+/*
+ * Adjust the global offset table
+ *
+ * RAX is the previous adjustment of the table to undo (use 0 if it's the
+ * first time we touch GOT).
+ * RDI is the new adjustment to apply.
+ */
+adjust_got:
+	/* Walk through the GOT adding the address to the entries */
+	leaq	_got(%rip), %rdx
+	leaq	_egot(%rip), %rcx
+1:
+	cmpq	%rcx, %rdx
+	jae	2f
+	subq	%rax, (%rdx)	/* Undo previous adjustment */
+	addq	%rdi, (%rdx)	/* Apply the new adjustment */
+	addq	$8, %rdx
+	jmp	1b
+2:
+	ret
+
 	.code32
 /*
  * This is the 32-bit trampoline that will be copied over to low memory.
@@ -649,3 +696,10 @@ boot_stack_end:
 	.balign 4096
 pgtable:
 	.fill BOOT_PGT_SIZE, 1, 0
+
+/*
+ * The page table is going to be used instead of page table in the trampoline
+ * memory.
+ */
+top_pgtable:
+	.fill PAGE_SIZE, 1, 0
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index a0a50b91ecef..b87a7582853d 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -47,7 +47,7 @@
 #include <linux/decompress/mm.h>
 
 #ifdef CONFIG_X86_5LEVEL
-unsigned int pgtable_l5_enabled __ro_after_init;
+unsigned int __pgtable_l5_enabled;
 unsigned int pgdir_shift __ro_after_init = 39;
 unsigned int ptrs_per_p4d __ro_after_init = 1;
 #endif
@@ -734,7 +734,7 @@ void choose_random_location(unsigned long input,
 
 #ifdef CONFIG_X86_5LEVEL
 	if (__read_cr4() & X86_CR4_LA57) {
-		pgtable_l5_enabled = 1;
+		__pgtable_l5_enabled = 1;
 		pgdir_shift = 48;
 		ptrs_per_p4d = 512;
 	}
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 9e11be4cae19..a423bdb42686 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -12,10 +12,8 @@
 #undef CONFIG_PARAVIRT_SPINLOCKS
 #undef CONFIG_KASAN
 
-#ifdef CONFIG_X86_5LEVEL
-/* cpu_feature_enabled() cannot be used that early */
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
 
 #include <linux/linkage.h>
 #include <linux/screen_info.h>
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 32af1cbcd903..8c5107545251 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -23,14 +23,6 @@ struct paging_config {
 static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
 
 /*
- * The page table is going to be used instead of page table in the trampoline
- * memory.
- *
- * It must not be in BSS as BSS is cleared after cleanup_trampoline().
- */
-static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
-
-/*
  * Trampoline address will be printed by extract_kernel() for debugging
  * purposes.
  *
@@ -39,16 +31,23 @@ static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
  */
 unsigned long *trampoline_32bit __section(.data);
 
-struct paging_config paging_prepare(void)
+extern struct boot_params *boot_params;
+int cmdline_find_option_bool(const char *option);
+
+struct paging_config paging_prepare(void *rmode)
 {
 	struct paging_config paging_config = {};
 	unsigned long bios_start, ebda_start;
 
+	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
+	boot_params = rmode;
+
 	/*
 	 * Check if LA57 is desired and supported.
 	 *
-	 * There are two parts to the check:
+	 * There are several parts to the check:
 	 *   - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y
+	 *   - if user asked to disable 5-level paging: no5lvl in cmdline
 	 *   - if the machine supports 5-level paging:
 	 *     + CPUID leaf 7 is supported
 	 *     + the leaf has the feature bit set
@@ -56,6 +55,7 @@ struct paging_config paging_prepare(void)
 	 * That's substitute for boot_cpu_has() in early boot code.
 	 */
 	if (IS_ENABLED(CONFIG_X86_5LEVEL) &&
+			!cmdline_find_option_bool("no5lvl") &&
 			native_cpuid_eax(0) >= 7 &&
 			(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
 		paging_config.l5_required = 1;
@@ -134,19 +134,19 @@ out:
 	return paging_config;
 }
 
-void cleanup_trampoline(void)
+void cleanup_trampoline(void *pgtable)
 {
 	void *trampoline_pgtable;
 
-	trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET;
+	trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long);
 
 	/*
 	 * Move the top level page table out of trampoline memory,
 	 * if it's there.
 	 */
 	if ((void *)__native_read_cr3() == trampoline_pgtable) {
-		memcpy(top_pgtable, trampoline_pgtable, PAGE_SIZE);
-		native_write_cr3((unsigned long)top_pgtable);
+		memcpy(pgtable, trampoline_pgtable, PAGE_SIZE);
+		native_write_cr3((unsigned long)pgtable);
 	}
 
 	/* Restore trampoline memory */
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 5f07333bb224..a450ad573dcb 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -15,7 +15,6 @@ obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
 
 obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
 obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
-obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
 
 obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
@@ -24,7 +23,6 @@ obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
-obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
 obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
@@ -38,6 +36,16 @@ obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
 obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
 obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
 
+obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
+obj-$(CONFIG_CRYPTO_AEGIS128L_AESNI_SSE2) += aegis128l-aesni.o
+obj-$(CONFIG_CRYPTO_AEGIS256_AESNI_SSE2) += aegis256-aesni.o
+
+obj-$(CONFIG_CRYPTO_MORUS640_GLUE) += morus640_glue.o
+obj-$(CONFIG_CRYPTO_MORUS1280_GLUE) += morus1280_glue.o
+
+obj-$(CONFIG_CRYPTO_MORUS640_SSE2) += morus640-sse2.o
+obj-$(CONFIG_CRYPTO_MORUS1280_SSE2) += morus1280-sse2.o
+
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \
@@ -55,11 +63,12 @@ ifeq ($(avx2_supported),yes)
 	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha1-mb/
 	obj-$(CONFIG_CRYPTO_SHA256_MB) += sha256-mb/
 	obj-$(CONFIG_CRYPTO_SHA512_MB) += sha512-mb/
+
+	obj-$(CONFIG_CRYPTO_MORUS1280_AVX2) += morus1280-avx2.o
 endif
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
 twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
-salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
 serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
 
 aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
@@ -68,10 +77,16 @@ camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
 twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
-salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
 chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o
 serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
 
+aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
+aegis128l-aesni-y := aegis128l-aesni-asm.o aegis128l-aesni-glue.o
+aegis256-aesni-y := aegis256-aesni-asm.o aegis256-aesni-glue.o
+
+morus640-sse2-y := morus640-sse2-asm.o morus640-sse2-glue.o
+morus1280-sse2-y := morus1280-sse2-asm.o morus1280-sse2-glue.o
+
 ifeq ($(avx_supported),yes)
 	camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
 					camellia_aesni_avx_glue.o
@@ -87,6 +102,8 @@ ifeq ($(avx2_supported),yes)
 	camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
 	chacha20-x86_64-y += chacha20-avx2-x86_64.o
 	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
+
+	morus1280-avx2-y := morus1280-avx2-asm.o morus1280-avx2-glue.o
 endif
 
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
new file mode 100644
index 000000000000..9254e0b6cc06
--- /dev/null
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -0,0 +1,749 @@
+/*
+ * AES-NI + SSE2 implementation of AEGIS-128
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+#define STATE0	%xmm0
+#define STATE1	%xmm1
+#define STATE2	%xmm2
+#define STATE3	%xmm3
+#define STATE4	%xmm4
+#define KEY	%xmm5
+#define MSG	%xmm5
+#define T0	%xmm6
+#define T1	%xmm7
+
+#define STATEP	%rdi
+#define LEN	%rsi
+#define SRC	%rdx
+#define DST	%rcx
+
+.section .rodata.cst16.aegis128_const, "aM", @progbits, 32
+.align 16
+.Laegis128_const_0:
+	.byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d
+	.byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62
+.Laegis128_const_1:
+	.byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1
+	.byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd
+
+.section .rodata.cst16.aegis128_counter, "aM", @progbits, 16
+.align 16
+.Laegis128_counter:
+	.byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+
+.text
+
+/*
+ * aegis128_update
+ * input:
+ *   STATE[0-4] - input state
+ * output:
+ *   STATE[0-4] - output state (shifted positions)
+ * changed:
+ *   T0
+ */
+.macro aegis128_update
+	movdqa STATE4, T0
+	aesenc STATE0, STATE4
+	aesenc STATE1, STATE0
+	aesenc STATE2, STATE1
+	aesenc STATE3, STATE2
+	aesenc T0,     STATE3
+.endm
+
+/*
+ * __load_partial: internal ABI
+ * input:
+ *   LEN - bytes
+ *   SRC - src
+ * output:
+ *   MSG  - message block
+ * changed:
+ *   T0
+ *   %r8
+ *   %r9
+ */
+__load_partial:
+	xor %r9, %r9
+	pxor MSG, MSG
+
+	mov LEN, %r8
+	and $0x1, %r8
+	jz .Lld_partial_1
+
+	mov LEN, %r8
+	and $0x1E, %r8
+	add SRC, %r8
+	mov (%r8), %r9b
+
+.Lld_partial_1:
+	mov LEN, %r8
+	and $0x2, %r8
+	jz .Lld_partial_2
+
+	mov LEN, %r8
+	and $0x1C, %r8
+	add SRC, %r8
+	shl $0x10, %r9
+	mov (%r8), %r9w
+
+.Lld_partial_2:
+	mov LEN, %r8
+	and $0x4, %r8
+	jz .Lld_partial_4
+
+	mov LEN, %r8
+	and $0x18, %r8
+	add SRC, %r8
+	shl $32, %r9
+	mov (%r8), %r8d
+	xor %r8, %r9
+
+.Lld_partial_4:
+	movq %r9, MSG
+
+	mov LEN, %r8
+	and $0x8, %r8
+	jz .Lld_partial_8
+
+	mov LEN, %r8
+	and $0x10, %r8
+	add SRC, %r8
+	pslldq $8, MSG
+	movq (%r8), T0
+	pxor T0, MSG
+
+.Lld_partial_8:
+	ret
+ENDPROC(__load_partial)
+
+/*
+ * __store_partial: internal ABI
+ * input:
+ *   LEN - bytes
+ *   DST - dst
+ * output:
+ *   T0   - message block
+ * changed:
+ *   %r8
+ *   %r9
+ *   %r10
+ */
+__store_partial:
+	mov LEN, %r8
+	mov DST, %r9
+
+	movq T0, %r10
+
+	cmp $8, %r8
+	jl .Lst_partial_8
+
+	mov %r10, (%r9)
+	psrldq $8, T0
+	movq T0, %r10
+
+	sub $8, %r8
+	add $8, %r9
+
+.Lst_partial_8:
+	cmp $4, %r8
+	jl .Lst_partial_4
+
+	mov %r10d, (%r9)
+	shr $32, %r10
+
+	sub $4, %r8
+	add $4, %r9
+
+.Lst_partial_4:
+	cmp $2, %r8
+	jl .Lst_partial_2
+
+	mov %r10w, (%r9)
+	shr $0x10, %r10
+
+	sub $2, %r8
+	add $2, %r9
+
+.Lst_partial_2:
+	cmp $1, %r8
+	jl .Lst_partial_1
+
+	mov %r10b, (%r9)
+
+.Lst_partial_1:
+	ret
+ENDPROC(__store_partial)
+
+/*
+ * void crypto_aegis128_aesni_init(void *state, const void *key, const void *iv);
+ */
+ENTRY(crypto_aegis128_aesni_init)
+	FRAME_BEGIN
+
+	/* load IV: */
+	movdqu (%rdx), T1
+
+	/* load key: */
+	movdqa (%rsi), KEY
+	pxor KEY, T1
+	movdqa T1, STATE0
+	movdqa KEY, STATE3
+	movdqa KEY, STATE4
+
+	/* load the constants: */
+	movdqa .Laegis128_const_0, STATE2
+	movdqa .Laegis128_const_1, STATE1
+	pxor STATE2, STATE3
+	pxor STATE1, STATE4
+
+	/* update 10 times with KEY / KEY xor IV: */
+	aegis128_update; pxor KEY, STATE4
+	aegis128_update; pxor T1,  STATE3
+	aegis128_update; pxor KEY, STATE2
+	aegis128_update; pxor T1,  STATE1
+	aegis128_update; pxor KEY, STATE0
+	aegis128_update; pxor T1,  STATE4
+	aegis128_update; pxor KEY, STATE3
+	aegis128_update; pxor T1,  STATE2
+	aegis128_update; pxor KEY, STATE1
+	aegis128_update; pxor T1,  STATE0
+
+	/* store the state: */
+	movdqu STATE0, 0x00(STATEP)
+	movdqu STATE1, 0x10(STATEP)
+	movdqu STATE2, 0x20(STATEP)
+	movdqu STATE3, 0x30(STATEP)
+	movdqu STATE4, 0x40(STATEP)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128_aesni_init)
+
+/*
+ * void crypto_aegis128_aesni_ad(void *state, unsigned int length,
+ *                               const void *data);
+ */
+ENTRY(crypto_aegis128_aesni_ad)
+	FRAME_BEGIN
+
+	cmp $0x10, LEN
+	jb .Lad_out
+
+	/* load the state: */
+	movdqu 0x00(STATEP), STATE0
+	movdqu 0x10(STATEP), STATE1
+	movdqu 0x20(STATEP), STATE2
+	movdqu 0x30(STATEP), STATE3
+	movdqu 0x40(STATEP), STATE4
+
+	mov SRC, %r8
+	and $0xF, %r8
+	jnz .Lad_u_loop
+
+.align 8
+.Lad_a_loop:
+	movdqa 0x00(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE4
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_1
+
+	movdqa 0x10(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE3
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_2
+
+	movdqa 0x20(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE2
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_3
+
+	movdqa 0x30(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE1
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_4
+
+	movdqa 0x40(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE0
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_0
+
+	add $0x50, SRC
+	jmp .Lad_a_loop
+
+.align 8
+.Lad_u_loop:
+	movdqu 0x00(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE4
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_1
+
+	movdqu 0x10(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE3
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_2
+
+	movdqu 0x20(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE2
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_3
+
+	movdqu 0x30(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE1
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_4
+
+	movdqu 0x40(SRC), MSG
+	aegis128_update
+	pxor MSG, STATE0
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_0
+
+	add $0x50, SRC
+	jmp .Lad_u_loop
+
+	/* store the state: */
+.Lad_out_0:
+	movdqu STATE0, 0x00(STATEP)
+	movdqu STATE1, 0x10(STATEP)
+	movdqu STATE2, 0x20(STATEP)
+	movdqu STATE3, 0x30(STATEP)
+	movdqu STATE4, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lad_out_1:
+	movdqu STATE4, 0x00(STATEP)
+	movdqu STATE0, 0x10(STATEP)
+	movdqu STATE1, 0x20(STATEP)
+	movdqu STATE2, 0x30(STATEP)
+	movdqu STATE3, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lad_out_2:
+	movdqu STATE3, 0x00(STATEP)
+	movdqu STATE4, 0x10(STATEP)
+	movdqu STATE0, 0x20(STATEP)
+	movdqu STATE1, 0x30(STATEP)
+	movdqu STATE2, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lad_out_3:
+	movdqu STATE2, 0x00(STATEP)
+	movdqu STATE3, 0x10(STATEP)
+	movdqu STATE4, 0x20(STATEP)
+	movdqu STATE0, 0x30(STATEP)
+	movdqu STATE1, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lad_out_4:
+	movdqu STATE1, 0x00(STATEP)
+	movdqu STATE2, 0x10(STATEP)
+	movdqu STATE3, 0x20(STATEP)
+	movdqu STATE4, 0x30(STATEP)
+	movdqu STATE0, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lad_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128_aesni_ad)
+
+.macro encrypt_block a s0 s1 s2 s3 s4 i
+	movdq\a (\i * 0x10)(SRC), MSG
+	movdqa MSG, T0
+	pxor \s1, T0
+	pxor \s4, T0
+	movdqa \s2, T1
+	pand \s3, T1
+	pxor T1, T0
+	movdq\a T0, (\i * 0x10)(DST)
+
+	aegis128_update
+	pxor MSG, \s4
+
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lenc_out_\i
+.endm
+
+/*
+ * void crypto_aegis128_aesni_enc(void *state, unsigned int length,
+ *                                const void *src, void *dst);
+ */
+ENTRY(crypto_aegis128_aesni_enc)
+	FRAME_BEGIN
+
+	cmp $0x10, LEN
+	jb .Lenc_out
+
+	/* load the state: */
+	movdqu 0x00(STATEP), STATE0
+	movdqu 0x10(STATEP), STATE1
+	movdqu 0x20(STATEP), STATE2
+	movdqu 0x30(STATEP), STATE3
+	movdqu 0x40(STATEP), STATE4
+
+	mov  SRC,  %r8
+	or   DST,  %r8
+	and $0xF, %r8
+	jnz .Lenc_u_loop
+
+.align 8
+.Lenc_a_loop:
+	encrypt_block a STATE0 STATE1 STATE2 STATE3 STATE4 0
+	encrypt_block a STATE4 STATE0 STATE1 STATE2 STATE3 1
+	encrypt_block a STATE3 STATE4 STATE0 STATE1 STATE2 2
+	encrypt_block a STATE2 STATE3 STATE4 STATE0 STATE1 3
+	encrypt_block a STATE1 STATE2 STATE3 STATE4 STATE0 4
+
+	add $0x50, SRC
+	add $0x50, DST
+	jmp .Lenc_a_loop
+
+.align 8
+.Lenc_u_loop:
+	encrypt_block u STATE0 STATE1 STATE2 STATE3 STATE4 0
+	encrypt_block u STATE4 STATE0 STATE1 STATE2 STATE3 1
+	encrypt_block u STATE3 STATE4 STATE0 STATE1 STATE2 2
+	encrypt_block u STATE2 STATE3 STATE4 STATE0 STATE1 3
+	encrypt_block u STATE1 STATE2 STATE3 STATE4 STATE0 4
+
+	add $0x50, SRC
+	add $0x50, DST
+	jmp .Lenc_u_loop
+
+	/* store the state: */
+.Lenc_out_0:
+	movdqu STATE4, 0x00(STATEP)
+	movdqu STATE0, 0x10(STATEP)
+	movdqu STATE1, 0x20(STATEP)
+	movdqu STATE2, 0x30(STATEP)
+	movdqu STATE3, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lenc_out_1:
+	movdqu STATE3, 0x00(STATEP)
+	movdqu STATE4, 0x10(STATEP)
+	movdqu STATE0, 0x20(STATEP)
+	movdqu STATE1, 0x30(STATEP)
+	movdqu STATE2, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lenc_out_2:
+	movdqu STATE2, 0x00(STATEP)
+	movdqu STATE3, 0x10(STATEP)
+	movdqu STATE4, 0x20(STATEP)
+	movdqu STATE0, 0x30(STATEP)
+	movdqu STATE1, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lenc_out_3:
+	movdqu STATE1, 0x00(STATEP)
+	movdqu STATE2, 0x10(STATEP)
+	movdqu STATE3, 0x20(STATEP)
+	movdqu STATE4, 0x30(STATEP)
+	movdqu STATE0, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lenc_out_4:
+	movdqu STATE0, 0x00(STATEP)
+	movdqu STATE1, 0x10(STATEP)
+	movdqu STATE2, 0x20(STATEP)
+	movdqu STATE3, 0x30(STATEP)
+	movdqu STATE4, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Lenc_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128_aesni_enc)
+
+/*
+ * void crypto_aegis128_aesni_enc_tail(void *state, unsigned int length,
+ *                                     const void *src, void *dst);
+ */
+ENTRY(crypto_aegis128_aesni_enc_tail)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu 0x00(STATEP), STATE0
+	movdqu 0x10(STATEP), STATE1
+	movdqu 0x20(STATEP), STATE2
+	movdqu 0x30(STATEP), STATE3
+	movdqu 0x40(STATEP), STATE4
+
+	/* encrypt message: */
+	call __load_partial
+
+	movdqa MSG, T0
+	pxor STATE1, T0
+	pxor STATE4, T0
+	movdqa STATE2, T1
+	pand STATE3, T1
+	pxor T1, T0
+
+	call __store_partial
+
+	aegis128_update
+	pxor MSG, STATE4
+
+	/* store the state: */
+	movdqu STATE4, 0x00(STATEP)
+	movdqu STATE0, 0x10(STATEP)
+	movdqu STATE1, 0x20(STATEP)
+	movdqu STATE2, 0x30(STATEP)
+	movdqu STATE3, 0x40(STATEP)
+
+	FRAME_END
+ENDPROC(crypto_aegis128_aesni_enc_tail)
+
+.macro decrypt_block a s0 s1 s2 s3 s4 i
+	movdq\a (\i * 0x10)(SRC), MSG
+	pxor \s1, MSG
+	pxor \s4, MSG
+	movdqa \s2, T1
+	pand \s3, T1
+	pxor T1, MSG
+	movdq\a MSG, (\i * 0x10)(DST)
+
+	aegis128_update
+	pxor MSG, \s4
+
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Ldec_out_\i
+.endm
+
+/*
+ * void crypto_aegis128_aesni_dec(void *state, unsigned int length,
+ *                                const void *src, void *dst);
+ */
+ENTRY(crypto_aegis128_aesni_dec)
+	FRAME_BEGIN
+
+	cmp $0x10, LEN
+	jb .Ldec_out
+
+	/* load the state: */
+	movdqu 0x00(STATEP), STATE0
+	movdqu 0x10(STATEP), STATE1
+	movdqu 0x20(STATEP), STATE2
+	movdqu 0x30(STATEP), STATE3
+	movdqu 0x40(STATEP), STATE4
+
+	mov  SRC, %r8
+	or   DST, %r8
+	and $0xF, %r8
+	jnz .Ldec_u_loop
+
+.align 8
+.Ldec_a_loop:
+	decrypt_block a STATE0 STATE1 STATE2 STATE3 STATE4 0
+	decrypt_block a STATE4 STATE0 STATE1 STATE2 STATE3 1
+	decrypt_block a STATE3 STATE4 STATE0 STATE1 STATE2 2
+	decrypt_block a STATE2 STATE3 STATE4 STATE0 STATE1 3
+	decrypt_block a STATE1 STATE2 STATE3 STATE4 STATE0 4
+
+	add $0x50, SRC
+	add $0x50, DST
+	jmp .Ldec_a_loop
+
+.align 8
+.Ldec_u_loop:
+	decrypt_block u STATE0 STATE1 STATE2 STATE3 STATE4 0
+	decrypt_block u STATE4 STATE0 STATE1 STATE2 STATE3 1
+	decrypt_block u STATE3 STATE4 STATE0 STATE1 STATE2 2
+	decrypt_block u STATE2 STATE3 STATE4 STATE0 STATE1 3
+	decrypt_block u STATE1 STATE2 STATE3 STATE4 STATE0 4
+
+	add $0x50, SRC
+	add $0x50, DST
+	jmp .Ldec_u_loop
+
+	/* store the state: */
+.Ldec_out_0:
+	movdqu STATE4, 0x00(STATEP)
+	movdqu STATE0, 0x10(STATEP)
+	movdqu STATE1, 0x20(STATEP)
+	movdqu STATE2, 0x30(STATEP)
+	movdqu STATE3, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Ldec_out_1:
+	movdqu STATE3, 0x00(STATEP)
+	movdqu STATE4, 0x10(STATEP)
+	movdqu STATE0, 0x20(STATEP)
+	movdqu STATE1, 0x30(STATEP)
+	movdqu STATE2, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Ldec_out_2:
+	movdqu STATE2, 0x00(STATEP)
+	movdqu STATE3, 0x10(STATEP)
+	movdqu STATE4, 0x20(STATEP)
+	movdqu STATE0, 0x30(STATEP)
+	movdqu STATE1, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Ldec_out_3:
+	movdqu STATE1, 0x00(STATEP)
+	movdqu STATE2, 0x10(STATEP)
+	movdqu STATE3, 0x20(STATEP)
+	movdqu STATE4, 0x30(STATEP)
+	movdqu STATE0, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Ldec_out_4:
+	movdqu STATE0, 0x00(STATEP)
+	movdqu STATE1, 0x10(STATEP)
+	movdqu STATE2, 0x20(STATEP)
+	movdqu STATE3, 0x30(STATEP)
+	movdqu STATE4, 0x40(STATEP)
+	FRAME_END
+	ret
+
+.Ldec_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128_aesni_dec)
+
+/*
+ * void crypto_aegis128_aesni_dec_tail(void *state, unsigned int length,
+ *                                     const void *src, void *dst);
+ */
+ENTRY(crypto_aegis128_aesni_dec_tail)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu 0x00(STATEP), STATE0
+	movdqu 0x10(STATEP), STATE1
+	movdqu 0x20(STATEP), STATE2
+	movdqu 0x30(STATEP), STATE3
+	movdqu 0x40(STATEP), STATE4
+
+	/* decrypt message: */
+	call __load_partial
+
+	pxor STATE1, MSG
+	pxor STATE4, MSG
+	movdqa STATE2, T1
+	pand STATE3, T1
+	pxor T1, MSG
+
+	movdqa MSG, T0
+	call __store_partial
+
+	/* mask with byte count: */
+	movq LEN, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	movdqa .Laegis128_counter, T1
+	pcmpgtb T1, T0
+	pand T0, MSG
+
+	aegis128_update
+	pxor MSG, STATE4
+
+	/* store the state: */
+	movdqu STATE4, 0x00(STATEP)
+	movdqu STATE0, 0x10(STATEP)
+	movdqu STATE1, 0x20(STATEP)
+	movdqu STATE2, 0x30(STATEP)
+	movdqu STATE3, 0x40(STATEP)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128_aesni_dec_tail)
+
+/*
+ * void crypto_aegis128_aesni_final(void *state, void *tag_xor,
+ *                                  u64 assoclen, u64 cryptlen);
+ */
+ENTRY(crypto_aegis128_aesni_final)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu 0x00(STATEP), STATE0
+	movdqu 0x10(STATEP), STATE1
+	movdqu 0x20(STATEP), STATE2
+	movdqu 0x30(STATEP), STATE3
+	movdqu 0x40(STATEP), STATE4
+
+	/* prepare length block: */
+	movq %rdx, MSG
+	movq %rcx, T0
+	pslldq $8, T0
+	pxor T0, MSG
+	psllq $3, MSG /* multiply by 8 (to get bit count) */
+
+	pxor STATE3, MSG
+
+	/* update state: */
+	aegis128_update; pxor MSG, STATE4
+	aegis128_update; pxor MSG, STATE3
+	aegis128_update; pxor MSG, STATE2
+	aegis128_update; pxor MSG, STATE1
+	aegis128_update; pxor MSG, STATE0
+	aegis128_update; pxor MSG, STATE4
+	aegis128_update; pxor MSG, STATE3
+
+	/* xor tag: */
+	movdqu (%rsi), MSG
+
+	pxor STATE0, MSG
+	pxor STATE1, MSG
+	pxor STATE2, MSG
+	pxor STATE3, MSG
+	pxor STATE4, MSG
+
+	movdqu MSG, (%rsi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128_aesni_final)
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
new file mode 100644
index 000000000000..5de7c0d46edf
--- /dev/null
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -0,0 +1,407 @@
+/*
+ * The AEGIS-128 Authenticated-Encryption Algorithm
+ *   Glue for AES-NI + SSE2 implementation
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/cryptd.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/cpu_device_id.h>
+
+#define AEGIS128_BLOCK_ALIGN 16
+#define AEGIS128_BLOCK_SIZE 16
+#define AEGIS128_NONCE_SIZE 16
+#define AEGIS128_STATE_BLOCKS 5
+#define AEGIS128_KEY_SIZE 16
+#define AEGIS128_MIN_AUTH_SIZE 8
+#define AEGIS128_MAX_AUTH_SIZE 16
+
+asmlinkage void crypto_aegis128_aesni_init(void *state, void *key, void *iv);
+
+asmlinkage void crypto_aegis128_aesni_ad(
+		void *state, unsigned int length, const void *data);
+
+asmlinkage void crypto_aegis128_aesni_enc(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis128_aesni_dec(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis128_aesni_enc_tail(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis128_aesni_dec_tail(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis128_aesni_final(
+		void *state, void *tag_xor, unsigned int cryptlen,
+		unsigned int assoclen);
+
+struct aegis_block {
+	u8 bytes[AEGIS128_BLOCK_SIZE] __aligned(AEGIS128_BLOCK_ALIGN);
+};
+
+struct aegis_state {
+	struct aegis_block blocks[AEGIS128_STATE_BLOCKS];
+};
+
+struct aegis_ctx {
+	struct aegis_block key;
+};
+
+struct aegis_crypt_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_blocks)(void *state, unsigned int length, const void *src,
+			     void *dst);
+	void (*crypt_tail)(void *state, unsigned int length, const void *src,
+			   void *dst);
+};
+
+static void crypto_aegis128_aesni_process_ad(
+		struct aegis_state *state, struct scatterlist *sg_src,
+		unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	struct aegis_block buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= AEGIS128_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = AEGIS128_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+				crypto_aegis128_aesni_ad(state,
+							 AEGIS128_BLOCK_SIZE,
+							 buf.bytes);
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			crypto_aegis128_aesni_ad(state, left, src);
+
+			src += left & ~(AEGIS128_BLOCK_SIZE - 1);
+			left &= AEGIS128_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+		pos += left;
+		assoclen -= size;
+
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, AEGIS128_BLOCK_SIZE - pos);
+		crypto_aegis128_aesni_ad(state, AEGIS128_BLOCK_SIZE, buf.bytes);
+	}
+}
+
+static void crypto_aegis128_aesni_process_crypt(
+		struct aegis_state *state, struct aead_request *req,
+		const struct aegis_crypt_ops *ops)
+{
+	struct skcipher_walk walk;
+	u8 *src, *dst;
+	unsigned int chunksize, base;
+
+	ops->skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+		chunksize = walk.nbytes;
+
+		ops->crypt_blocks(state, chunksize, src, dst);
+
+		base = chunksize & ~(AEGIS128_BLOCK_SIZE - 1);
+		src += base;
+		dst += base;
+		chunksize &= AEGIS128_BLOCK_SIZE - 1;
+
+		if (chunksize > 0)
+			ops->crypt_tail(state, chunksize, src, dst);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+static struct aegis_ctx *crypto_aegis128_aesni_ctx(struct crypto_aead *aead)
+{
+	u8 *ctx = crypto_aead_ctx(aead);
+	ctx = PTR_ALIGN(ctx, __alignof__(struct aegis_ctx));
+	return (void *)ctx;
+}
+
+static int crypto_aegis128_aesni_setkey(struct crypto_aead *aead, const u8 *key,
+					unsigned int keylen)
+{
+	struct aegis_ctx *ctx = crypto_aegis128_aesni_ctx(aead);
+
+	if (keylen != AEGIS128_KEY_SIZE) {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key.bytes, key, AEGIS128_KEY_SIZE);
+
+	return 0;
+}
+
+static int crypto_aegis128_aesni_setauthsize(struct crypto_aead *tfm,
+						unsigned int authsize)
+{
+	if (authsize > AEGIS128_MAX_AUTH_SIZE)
+		return -EINVAL;
+	if (authsize < AEGIS128_MIN_AUTH_SIZE)
+		return -EINVAL;
+	return 0;
+}
+
+static void crypto_aegis128_aesni_crypt(struct aead_request *req,
+					struct aegis_block *tag_xor,
+					unsigned int cryptlen,
+					const struct aegis_crypt_ops *ops)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_ctx *ctx = crypto_aegis128_aesni_ctx(tfm);
+	struct aegis_state state;
+
+	kernel_fpu_begin();
+
+	crypto_aegis128_aesni_init(&state, ctx->key.bytes, req->iv);
+	crypto_aegis128_aesni_process_ad(&state, req->src, req->assoclen);
+	crypto_aegis128_aesni_process_crypt(&state, req, ops);
+	crypto_aegis128_aesni_final(&state, tag_xor, req->assoclen, cryptlen);
+
+	kernel_fpu_end();
+}
+
+static int crypto_aegis128_aesni_encrypt(struct aead_request *req)
+{
+	static const struct aegis_crypt_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_blocks = crypto_aegis128_aesni_enc,
+		.crypt_tail = crypto_aegis128_aesni_enc_tail,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_block tag = {};
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_aegis128_aesni_crypt(req, &tag, cryptlen, &OPS);
+
+	scatterwalk_map_and_copy(tag.bytes, req->dst,
+				 req->assoclen + cryptlen, authsize, 1);
+	return 0;
+}
+
+static int crypto_aegis128_aesni_decrypt(struct aead_request *req)
+{
+	static const struct aegis_block zeros = {};
+
+	static const struct aegis_crypt_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_blocks = crypto_aegis128_aesni_dec,
+		.crypt_tail = crypto_aegis128_aesni_dec_tail,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag.bytes, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
+
+	crypto_aegis128_aesni_crypt(req, &tag, cryptlen, &OPS);
+
+	return crypto_memneq(tag.bytes, zeros.bytes, authsize) ? -EBADMSG : 0;
+}
+
+static int crypto_aegis128_aesni_init_tfm(struct crypto_aead *aead)
+{
+	return 0;
+}
+
+static void crypto_aegis128_aesni_exit_tfm(struct crypto_aead *aead)
+{
+}
+
+static int cryptd_aegis128_aesni_setkey(struct crypto_aead *aead,
+					const u8 *key, unsigned int keylen)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
+}
+
+static int cryptd_aegis128_aesni_setauthsize(struct crypto_aead *aead,
+					     unsigned int authsize)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
+}
+
+static int cryptd_aegis128_aesni_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_encrypt(req);
+}
+
+static int cryptd_aegis128_aesni_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_decrypt(req);
+}
+
+static int cryptd_aegis128_aesni_init_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead *cryptd_tfm;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_tfm = cryptd_alloc_aead("__aegis128-aesni", CRYPTO_ALG_INTERNAL,
+				       CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	*ctx = cryptd_tfm;
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
+	return 0;
+}
+
+static void cryptd_aegis128_aesni_exit_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_free_aead(*ctx);
+}
+
+static struct aead_alg crypto_aegis128_aesni_alg[] = {
+	{
+		.setkey = crypto_aegis128_aesni_setkey,
+		.setauthsize = crypto_aegis128_aesni_setauthsize,
+		.encrypt = crypto_aegis128_aesni_encrypt,
+		.decrypt = crypto_aegis128_aesni_decrypt,
+		.init = crypto_aegis128_aesni_init_tfm,
+		.exit = crypto_aegis128_aesni_exit_tfm,
+
+		.ivsize = AEGIS128_NONCE_SIZE,
+		.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
+		.chunksize = AEGIS128_BLOCK_SIZE,
+
+		.base = {
+			.cra_flags = CRYPTO_ALG_INTERNAL,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct aegis_ctx) +
+				__alignof__(struct aegis_ctx),
+			.cra_alignmask = 0,
+
+			.cra_name = "__aegis128",
+			.cra_driver_name = "__aegis128-aesni",
+
+			.cra_module = THIS_MODULE,
+		}
+	}, {
+		.setkey = cryptd_aegis128_aesni_setkey,
+		.setauthsize = cryptd_aegis128_aesni_setauthsize,
+		.encrypt = cryptd_aegis128_aesni_encrypt,
+		.decrypt = cryptd_aegis128_aesni_decrypt,
+		.init = cryptd_aegis128_aesni_init_tfm,
+		.exit = cryptd_aegis128_aesni_exit_tfm,
+
+		.ivsize = AEGIS128_NONCE_SIZE,
+		.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
+		.chunksize = AEGIS128_BLOCK_SIZE,
+
+		.base = {
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct cryptd_aead *),
+			.cra_alignmask = 0,
+
+			.cra_priority = 400,
+
+			.cra_name = "aegis128",
+			.cra_driver_name = "aegis128-aesni",
+
+			.cra_module = THIS_MODULE,
+		}
+	}
+};
+
+static const struct x86_cpu_id aesni_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_AES),
+	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
+
+static int __init crypto_aegis128_aesni_module_init(void)
+{
+	if (!x86_match_cpu(aesni_cpu_id))
+		return -ENODEV;
+
+	return crypto_register_aeads(crypto_aegis128_aesni_alg,
+				     ARRAY_SIZE(crypto_aegis128_aesni_alg));
+}
+
+static void __exit crypto_aegis128_aesni_module_exit(void)
+{
+	crypto_unregister_aeads(crypto_aegis128_aesni_alg,
+				ARRAY_SIZE(crypto_aegis128_aesni_alg));
+}
+
+module_init(crypto_aegis128_aesni_module_init);
+module_exit(crypto_aegis128_aesni_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("AEGIS-128 AEAD algorithm -- AESNI+SSE2 implementation");
+MODULE_ALIAS_CRYPTO("aegis128");
+MODULE_ALIAS_CRYPTO("aegis128-aesni");
diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S
new file mode 100644
index 000000000000..9263c344f2c7
--- /dev/null
+++ b/arch/x86/crypto/aegis128l-aesni-asm.S
@@ -0,0 +1,825 @@
+/*
+ * AES-NI + SSE2 implementation of AEGIS-128L
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+#define STATE0	%xmm0
+#define STATE1	%xmm1
+#define STATE2	%xmm2
+#define STATE3	%xmm3
+#define STATE4	%xmm4
+#define STATE5	%xmm5
+#define STATE6	%xmm6
+#define STATE7	%xmm7
+#define MSG0	%xmm8
+#define MSG1	%xmm9
+#define T0	%xmm10
+#define T1	%xmm11
+#define T2	%xmm12
+#define T3	%xmm13
+
+#define STATEP	%rdi
+#define LEN	%rsi
+#define SRC	%rdx
+#define DST	%rcx
+
+.section .rodata.cst16.aegis128l_const, "aM", @progbits, 32
+.align 16
+.Laegis128l_const_0:
+	.byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d
+	.byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62
+.Laegis128l_const_1:
+	.byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1
+	.byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd
+
+.section .rodata.cst16.aegis128l_counter, "aM", @progbits, 16
+.align 16
+.Laegis128l_counter0:
+	.byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+.Laegis128l_counter1:
+	.byte 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17
+	.byte 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f
+
+.text
+
+/*
+ * __load_partial: internal ABI
+ * input:
+ *   LEN - bytes
+ *   SRC - src
+ * output:
+ *   MSG0 - first message block
+ *   MSG1 - second message block
+ * changed:
+ *   T0
+ *   %r8
+ *   %r9
+ */
+__load_partial:
+	xor %r9, %r9
+	pxor MSG0, MSG0
+	pxor MSG1, MSG1
+
+	mov LEN, %r8
+	and $0x1, %r8
+	jz .Lld_partial_1
+
+	mov LEN, %r8
+	and $0x1E, %r8
+	add SRC, %r8
+	mov (%r8), %r9b
+
+.Lld_partial_1:
+	mov LEN, %r8
+	and $0x2, %r8
+	jz .Lld_partial_2
+
+	mov LEN, %r8
+	and $0x1C, %r8
+	add SRC, %r8
+	shl $0x10, %r9
+	mov (%r8), %r9w
+
+.Lld_partial_2:
+	mov LEN, %r8
+	and $0x4, %r8
+	jz .Lld_partial_4
+
+	mov LEN, %r8
+	and $0x18, %r8
+	add SRC, %r8
+	shl $32, %r9
+	mov (%r8), %r8d
+	xor %r8, %r9
+
+.Lld_partial_4:
+	movq %r9, MSG0
+
+	mov LEN, %r8
+	and $0x8, %r8
+	jz .Lld_partial_8
+
+	mov LEN, %r8
+	and $0x10, %r8
+	add SRC, %r8
+	pslldq $8, MSG0
+	movq (%r8), T0
+	pxor T0, MSG0
+
+.Lld_partial_8:
+	mov LEN, %r8
+	and $0x10, %r8
+	jz .Lld_partial_16
+
+	movdqa MSG0, MSG1
+	movdqu (SRC), MSG0
+
+.Lld_partial_16:
+	ret
+ENDPROC(__load_partial)
+
+/*
+ * __store_partial: internal ABI
+ * input:
+ *   LEN - bytes
+ *   DST - dst
+ * output:
+ *   T0   - first message block
+ *   T1   - second message block
+ * changed:
+ *   %r8
+ *   %r9
+ *   %r10
+ */
+__store_partial:
+	mov LEN, %r8
+	mov DST, %r9
+
+	cmp $16, %r8
+	jl .Lst_partial_16
+
+	movdqu T0, (%r9)
+	movdqa T1, T0
+
+	sub $16, %r8
+	add $16, %r9
+
+.Lst_partial_16:
+	movq T0, %r10
+
+	cmp $8, %r8
+	jl .Lst_partial_8
+
+	mov %r10, (%r9)
+	psrldq $8, T0
+	movq T0, %r10
+
+	sub $8, %r8
+	add $8, %r9
+
+.Lst_partial_8:
+	cmp $4, %r8
+	jl .Lst_partial_4
+
+	mov %r10d, (%r9)
+	shr $32, %r10
+
+	sub $4, %r8
+	add $4, %r9
+
+.Lst_partial_4:
+	cmp $2, %r8
+	jl .Lst_partial_2
+
+	mov %r10w, (%r9)
+	shr $0x10, %r10
+
+	sub $2, %r8
+	add $2, %r9
+
+.Lst_partial_2:
+	cmp $1, %r8
+	jl .Lst_partial_1
+
+	mov %r10b, (%r9)
+
+.Lst_partial_1:
+	ret
+ENDPROC(__store_partial)
+
+.macro update
+	movdqa STATE7, T0
+	aesenc STATE0, STATE7
+	aesenc STATE1, STATE0
+	aesenc STATE2, STATE1
+	aesenc STATE3, STATE2
+	aesenc STATE4, STATE3
+	aesenc STATE5, STATE4
+	aesenc STATE6, STATE5
+	aesenc T0,     STATE6
+.endm
+
+.macro update0
+	update
+	pxor MSG0, STATE7
+	pxor MSG1, STATE3
+.endm
+
+.macro update1
+	update
+	pxor MSG0, STATE6
+	pxor MSG1, STATE2
+.endm
+
+.macro update2
+	update
+	pxor MSG0, STATE5
+	pxor MSG1, STATE1
+.endm
+
+.macro update3
+	update
+	pxor MSG0, STATE4
+	pxor MSG1, STATE0
+.endm
+
+.macro update4
+	update
+	pxor MSG0, STATE3
+	pxor MSG1, STATE7
+.endm
+
+.macro update5
+	update
+	pxor MSG0, STATE2
+	pxor MSG1, STATE6
+.endm
+
+.macro update6
+	update
+	pxor MSG0, STATE1
+	pxor MSG1, STATE5
+.endm
+
+.macro update7
+	update
+	pxor MSG0, STATE0
+	pxor MSG1, STATE4
+.endm
+
+.macro state_load
+	movdqu 0x00(STATEP), STATE0
+	movdqu 0x10(STATEP), STATE1
+	movdqu 0x20(STATEP), STATE2
+	movdqu 0x30(STATEP), STATE3
+	movdqu 0x40(STATEP), STATE4
+	movdqu 0x50(STATEP), STATE5
+	movdqu 0x60(STATEP), STATE6
+	movdqu 0x70(STATEP), STATE7
+.endm
+
+.macro state_store s0 s1 s2 s3 s4 s5 s6 s7
+	movdqu \s7, 0x00(STATEP)
+	movdqu \s0, 0x10(STATEP)
+	movdqu \s1, 0x20(STATEP)
+	movdqu \s2, 0x30(STATEP)
+	movdqu \s3, 0x40(STATEP)
+	movdqu \s4, 0x50(STATEP)
+	movdqu \s5, 0x60(STATEP)
+	movdqu \s6, 0x70(STATEP)
+.endm
+
+.macro state_store0
+	state_store STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7
+.endm
+
+.macro state_store1
+	state_store STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6
+.endm
+
+.macro state_store2
+	state_store STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5
+.endm
+
+.macro state_store3
+	state_store STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4
+.endm
+
+.macro state_store4
+	state_store STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3
+.endm
+
+.macro state_store5
+	state_store STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2
+.endm
+
+.macro state_store6
+	state_store STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1
+.endm
+
+.macro state_store7
+	state_store STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0
+.endm
+
+/*
+ * void crypto_aegis128l_aesni_init(void *state, const void *key, const void *iv);
+ */
+ENTRY(crypto_aegis128l_aesni_init)
+	FRAME_BEGIN
+
+	/* load key: */
+	movdqa (%rsi), MSG1
+	movdqa MSG1, STATE0
+	movdqa MSG1, STATE4
+	movdqa MSG1, STATE5
+	movdqa MSG1, STATE6
+	movdqa MSG1, STATE7
+
+	/* load IV: */
+	movdqu (%rdx), MSG0
+	pxor MSG0, STATE0
+	pxor MSG0, STATE4
+
+	/* load the constants: */
+	movdqa .Laegis128l_const_0, STATE2
+	movdqa .Laegis128l_const_1, STATE1
+	movdqa STATE1, STATE3
+	pxor STATE2, STATE5
+	pxor STATE1, STATE6
+	pxor STATE2, STATE7
+
+	/* update 10 times with IV and KEY: */
+	update0
+	update1
+	update2
+	update3
+	update4
+	update5
+	update6
+	update7
+	update0
+	update1
+
+	state_store1
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128l_aesni_init)
+
+.macro ad_block a i
+	movdq\a (\i * 0x20 + 0x00)(SRC), MSG0
+	movdq\a (\i * 0x20 + 0x10)(SRC), MSG1
+	update\i
+	sub $0x20, LEN
+	cmp $0x20, LEN
+	jl .Lad_out_\i
+.endm
+
+/*
+ * void crypto_aegis128l_aesni_ad(void *state, unsigned int length,
+ *                                const void *data);
+ */
+ENTRY(crypto_aegis128l_aesni_ad)
+	FRAME_BEGIN
+
+	cmp $0x20, LEN
+	jb .Lad_out
+
+	state_load
+
+	mov  SRC, %r8
+	and $0xf, %r8
+	jnz .Lad_u_loop
+
+.align 8
+.Lad_a_loop:
+	ad_block a 0
+	ad_block a 1
+	ad_block a 2
+	ad_block a 3
+	ad_block a 4
+	ad_block a 5
+	ad_block a 6
+	ad_block a 7
+
+	add $0x100, SRC
+	jmp .Lad_a_loop
+
+.align 8
+.Lad_u_loop:
+	ad_block u 0
+	ad_block u 1
+	ad_block u 2
+	ad_block u 3
+	ad_block u 4
+	ad_block u 5
+	ad_block u 6
+	ad_block u 7
+
+	add $0x100, SRC
+	jmp .Lad_u_loop
+
+.Lad_out_0:
+	state_store0
+	FRAME_END
+	ret
+
+.Lad_out_1:
+	state_store1
+	FRAME_END
+	ret
+
+.Lad_out_2:
+	state_store2
+	FRAME_END
+	ret
+
+.Lad_out_3:
+	state_store3
+	FRAME_END
+	ret
+
+.Lad_out_4:
+	state_store4
+	FRAME_END
+	ret
+
+.Lad_out_5:
+	state_store5
+	FRAME_END
+	ret
+
+.Lad_out_6:
+	state_store6
+	FRAME_END
+	ret
+
+.Lad_out_7:
+	state_store7
+	FRAME_END
+	ret
+
+.Lad_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128l_aesni_ad)
+
+.macro crypt m0 m1 s0 s1 s2 s3 s4 s5 s6 s7
+	pxor \s1, \m0
+	pxor \s6, \m0
+	movdqa \s2, T3
+	pand \s3, T3
+	pxor T3, \m0
+
+	pxor \s2, \m1
+	pxor \s5, \m1
+	movdqa \s6, T3
+	pand \s7, T3
+	pxor T3, \m1
+.endm
+
+.macro crypt0 m0 m1
+	crypt \m0 \m1 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7
+.endm
+
+.macro crypt1 m0 m1
+	crypt \m0 \m1 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6
+.endm
+
+.macro crypt2 m0 m1
+	crypt \m0 \m1 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5
+.endm
+
+.macro crypt3 m0 m1
+	crypt \m0 \m1 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4
+.endm
+
+.macro crypt4 m0 m1
+	crypt \m0 \m1 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3
+.endm
+
+.macro crypt5 m0 m1
+	crypt \m0 \m1 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2
+.endm
+
+.macro crypt6 m0 m1
+	crypt \m0 \m1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1
+.endm
+
+.macro crypt7 m0 m1
+	crypt \m0 \m1 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0
+.endm
+
+.macro encrypt_block a i
+	movdq\a (\i * 0x20 + 0x00)(SRC), MSG0
+	movdq\a (\i * 0x20 + 0x10)(SRC), MSG1
+	movdqa MSG0, T0
+	movdqa MSG1, T1
+	crypt\i T0, T1
+	movdq\a T0, (\i * 0x20 + 0x00)(DST)
+	movdq\a T1, (\i * 0x20 + 0x10)(DST)
+
+	update\i
+
+	sub $0x20, LEN
+	cmp $0x20, LEN
+	jl .Lenc_out_\i
+.endm
+
+.macro decrypt_block a i
+	movdq\a (\i * 0x20 + 0x00)(SRC), MSG0
+	movdq\a (\i * 0x20 + 0x10)(SRC), MSG1
+	crypt\i MSG0, MSG1
+	movdq\a MSG0, (\i * 0x20 + 0x00)(DST)
+	movdq\a MSG1, (\i * 0x20 + 0x10)(DST)
+
+	update\i
+
+	sub $0x20, LEN
+	cmp $0x20, LEN
+	jl .Ldec_out_\i
+.endm
+
+/*
+ * void crypto_aegis128l_aesni_enc(void *state, unsigned int length,
+ *                                 const void *src, void *dst);
+ */
+ENTRY(crypto_aegis128l_aesni_enc)
+	FRAME_BEGIN
+
+	cmp $0x20, LEN
+	jb .Lenc_out
+
+	state_load
+
+	mov  SRC, %r8
+	or   DST, %r8
+	and $0xf, %r8
+	jnz .Lenc_u_loop
+
+.align 8
+.Lenc_a_loop:
+	encrypt_block a 0
+	encrypt_block a 1
+	encrypt_block a 2
+	encrypt_block a 3
+	encrypt_block a 4
+	encrypt_block a 5
+	encrypt_block a 6
+	encrypt_block a 7
+
+	add $0x100, SRC
+	add $0x100, DST
+	jmp .Lenc_a_loop
+
+.align 8
+.Lenc_u_loop:
+	encrypt_block u 0
+	encrypt_block u 1
+	encrypt_block u 2
+	encrypt_block u 3
+	encrypt_block u 4
+	encrypt_block u 5
+	encrypt_block u 6
+	encrypt_block u 7
+
+	add $0x100, SRC
+	add $0x100, DST
+	jmp .Lenc_u_loop
+
+.Lenc_out_0:
+	state_store0
+	FRAME_END
+	ret
+
+.Lenc_out_1:
+	state_store1
+	FRAME_END
+	ret
+
+.Lenc_out_2:
+	state_store2
+	FRAME_END
+	ret
+
+.Lenc_out_3:
+	state_store3
+	FRAME_END
+	ret
+
+.Lenc_out_4:
+	state_store4
+	FRAME_END
+	ret
+
+.Lenc_out_5:
+	state_store5
+	FRAME_END
+	ret
+
+.Lenc_out_6:
+	state_store6
+	FRAME_END
+	ret
+
+.Lenc_out_7:
+	state_store7
+	FRAME_END
+	ret
+
+.Lenc_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128l_aesni_enc)
+
+/*
+ * void crypto_aegis128l_aesni_enc_tail(void *state, unsigned int length,
+ *                                      const void *src, void *dst);
+ */
+ENTRY(crypto_aegis128l_aesni_enc_tail)
+	FRAME_BEGIN
+
+	state_load
+
+	/* encrypt message: */
+	call __load_partial
+
+	movdqa MSG0, T0
+	movdqa MSG1, T1
+	crypt0 T0, T1
+
+	call __store_partial
+
+	update0
+
+	state_store0
+
+	FRAME_END
+ENDPROC(crypto_aegis128l_aesni_enc_tail)
+
+/*
+ * void crypto_aegis128l_aesni_dec(void *state, unsigned int length,
+ *                                 const void *src, void *dst);
+ */
+ENTRY(crypto_aegis128l_aesni_dec)
+	FRAME_BEGIN
+
+	cmp $0x20, LEN
+	jb .Ldec_out
+
+	state_load
+
+	mov  SRC, %r8
+	or   DST, %r8
+	and $0xF, %r8
+	jnz .Ldec_u_loop
+
+.align 8
+.Ldec_a_loop:
+	decrypt_block a 0
+	decrypt_block a 1
+	decrypt_block a 2
+	decrypt_block a 3
+	decrypt_block a 4
+	decrypt_block a 5
+	decrypt_block a 6
+	decrypt_block a 7
+
+	add $0x100, SRC
+	add $0x100, DST
+	jmp .Ldec_a_loop
+
+.align 8
+.Ldec_u_loop:
+	decrypt_block u 0
+	decrypt_block u 1
+	decrypt_block u 2
+	decrypt_block u 3
+	decrypt_block u 4
+	decrypt_block u 5
+	decrypt_block u 6
+	decrypt_block u 7
+
+	add $0x100, SRC
+	add $0x100, DST
+	jmp .Ldec_u_loop
+
+.Ldec_out_0:
+	state_store0
+	FRAME_END
+	ret
+
+.Ldec_out_1:
+	state_store1
+	FRAME_END
+	ret
+
+.Ldec_out_2:
+	state_store2
+	FRAME_END
+	ret
+
+.Ldec_out_3:
+	state_store3
+	FRAME_END
+	ret
+
+.Ldec_out_4:
+	state_store4
+	FRAME_END
+	ret
+
+.Ldec_out_5:
+	state_store5
+	FRAME_END
+	ret
+
+.Ldec_out_6:
+	state_store6
+	FRAME_END
+	ret
+
+.Ldec_out_7:
+	state_store7
+	FRAME_END
+	ret
+
+.Ldec_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128l_aesni_dec)
+
+/*
+ * void crypto_aegis128l_aesni_dec_tail(void *state, unsigned int length,
+ *                                      const void *src, void *dst);
+ */
+ENTRY(crypto_aegis128l_aesni_dec_tail)
+	FRAME_BEGIN
+
+	state_load
+
+	/* decrypt message: */
+	call __load_partial
+
+	crypt0 MSG0, MSG1
+
+	movdqa MSG0, T0
+	movdqa MSG1, T1
+	call __store_partial
+
+	/* mask with byte count: */
+	movq LEN, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	movdqa T0, T1
+	movdqa .Laegis128l_counter0, T2
+	movdqa .Laegis128l_counter1, T3
+	pcmpgtb T2, T0
+	pcmpgtb T3, T1
+	pand T0, MSG0
+	pand T1, MSG1
+
+	update0
+
+	state_store0
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128l_aesni_dec_tail)
+
+/*
+ * void crypto_aegis128l_aesni_final(void *state, void *tag_xor,
+ *                                   u64 assoclen, u64 cryptlen);
+ */
+ENTRY(crypto_aegis128l_aesni_final)
+	FRAME_BEGIN
+
+	state_load
+
+	/* prepare length block: */
+	movq %rdx, MSG0
+	movq %rcx, T0
+	pslldq $8, T0
+	pxor T0, MSG0
+	psllq $3, MSG0 /* multiply by 8 (to get bit count) */
+
+	pxor STATE2, MSG0
+	movdqa MSG0, MSG1
+
+	/* update state: */
+	update0
+	update1
+	update2
+	update3
+	update4
+	update5
+	update6
+
+	/* xor tag: */
+	movdqu (%rsi), T0
+
+	pxor STATE1, T0
+	pxor STATE2, T0
+	pxor STATE3, T0
+	pxor STATE4, T0
+	pxor STATE5, T0
+	pxor STATE6, T0
+	pxor STATE7, T0
+
+	movdqu T0, (%rsi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis128l_aesni_final)
diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c
new file mode 100644
index 000000000000..876e4866e633
--- /dev/null
+++ b/arch/x86/crypto/aegis128l-aesni-glue.c
@@ -0,0 +1,407 @@
+/*
+ * The AEGIS-128L Authenticated-Encryption Algorithm
+ *   Glue for AES-NI + SSE2 implementation
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/cryptd.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/cpu_device_id.h>
+
+#define AEGIS128L_BLOCK_ALIGN 16
+#define AEGIS128L_BLOCK_SIZE 32
+#define AEGIS128L_NONCE_SIZE 16
+#define AEGIS128L_STATE_BLOCKS 8
+#define AEGIS128L_KEY_SIZE 16
+#define AEGIS128L_MIN_AUTH_SIZE 8
+#define AEGIS128L_MAX_AUTH_SIZE 16
+
+asmlinkage void crypto_aegis128l_aesni_init(void *state, void *key, void *iv);
+
+asmlinkage void crypto_aegis128l_aesni_ad(
+		void *state, unsigned int length, const void *data);
+
+asmlinkage void crypto_aegis128l_aesni_enc(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis128l_aesni_dec(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis128l_aesni_enc_tail(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis128l_aesni_dec_tail(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis128l_aesni_final(
+		void *state, void *tag_xor, unsigned int cryptlen,
+		unsigned int assoclen);
+
+struct aegis_block {
+	u8 bytes[AEGIS128L_BLOCK_SIZE] __aligned(AEGIS128L_BLOCK_ALIGN);
+};
+
+struct aegis_state {
+	struct aegis_block blocks[AEGIS128L_STATE_BLOCKS];
+};
+
+struct aegis_ctx {
+	struct aegis_block key;
+};
+
+struct aegis_crypt_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_blocks)(void *state, unsigned int length, const void *src,
+			     void *dst);
+	void (*crypt_tail)(void *state, unsigned int length, const void *src,
+			   void *dst);
+};
+
+static void crypto_aegis128l_aesni_process_ad(
+		struct aegis_state *state, struct scatterlist *sg_src,
+		unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	struct aegis_block buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= AEGIS128L_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = AEGIS128L_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+				crypto_aegis128l_aesni_ad(state,
+							  AEGIS128L_BLOCK_SIZE,
+							  buf.bytes);
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			crypto_aegis128l_aesni_ad(state, left, src);
+
+			src += left & ~(AEGIS128L_BLOCK_SIZE - 1);
+			left &= AEGIS128L_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+		pos += left;
+		assoclen -= size;
+
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, AEGIS128L_BLOCK_SIZE - pos);
+		crypto_aegis128l_aesni_ad(state, AEGIS128L_BLOCK_SIZE, buf.bytes);
+	}
+}
+
+static void crypto_aegis128l_aesni_process_crypt(
+		struct aegis_state *state, struct aead_request *req,
+		const struct aegis_crypt_ops *ops)
+{
+	struct skcipher_walk walk;
+	u8 *src, *dst;
+	unsigned int chunksize, base;
+
+	ops->skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+		chunksize = walk.nbytes;
+
+		ops->crypt_blocks(state, chunksize, src, dst);
+
+		base = chunksize & ~(AEGIS128L_BLOCK_SIZE - 1);
+		src += base;
+		dst += base;
+		chunksize &= AEGIS128L_BLOCK_SIZE - 1;
+
+		if (chunksize > 0)
+			ops->crypt_tail(state, chunksize, src, dst);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+static struct aegis_ctx *crypto_aegis128l_aesni_ctx(struct crypto_aead *aead)
+{
+	u8 *ctx = crypto_aead_ctx(aead);
+	ctx = PTR_ALIGN(ctx, __alignof__(struct aegis_ctx));
+	return (void *)ctx;
+}
+
+static int crypto_aegis128l_aesni_setkey(struct crypto_aead *aead,
+					 const u8 *key, unsigned int keylen)
+{
+	struct aegis_ctx *ctx = crypto_aegis128l_aesni_ctx(aead);
+
+	if (keylen != AEGIS128L_KEY_SIZE) {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key.bytes, key, AEGIS128L_KEY_SIZE);
+
+	return 0;
+}
+
+static int crypto_aegis128l_aesni_setauthsize(struct crypto_aead *tfm,
+					      unsigned int authsize)
+{
+	if (authsize > AEGIS128L_MAX_AUTH_SIZE)
+		return -EINVAL;
+	if (authsize < AEGIS128L_MIN_AUTH_SIZE)
+		return -EINVAL;
+	return 0;
+}
+
+static void crypto_aegis128l_aesni_crypt(struct aead_request *req,
+					 struct aegis_block *tag_xor,
+					 unsigned int cryptlen,
+					 const struct aegis_crypt_ops *ops)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_ctx *ctx = crypto_aegis128l_aesni_ctx(tfm);
+	struct aegis_state state;
+
+	kernel_fpu_begin();
+
+	crypto_aegis128l_aesni_init(&state, ctx->key.bytes, req->iv);
+	crypto_aegis128l_aesni_process_ad(&state, req->src, req->assoclen);
+	crypto_aegis128l_aesni_process_crypt(&state, req, ops);
+	crypto_aegis128l_aesni_final(&state, tag_xor, req->assoclen, cryptlen);
+
+	kernel_fpu_end();
+}
+
+static int crypto_aegis128l_aesni_encrypt(struct aead_request *req)
+{
+	static const struct aegis_crypt_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_blocks = crypto_aegis128l_aesni_enc,
+		.crypt_tail = crypto_aegis128l_aesni_enc_tail,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_block tag = {};
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_aegis128l_aesni_crypt(req, &tag, cryptlen, &OPS);
+
+	scatterwalk_map_and_copy(tag.bytes, req->dst,
+				 req->assoclen + cryptlen, authsize, 1);
+	return 0;
+}
+
+static int crypto_aegis128l_aesni_decrypt(struct aead_request *req)
+{
+	static const struct aegis_block zeros = {};
+
+	static const struct aegis_crypt_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_blocks = crypto_aegis128l_aesni_dec,
+		.crypt_tail = crypto_aegis128l_aesni_dec_tail,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag.bytes, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
+
+	crypto_aegis128l_aesni_crypt(req, &tag, cryptlen, &OPS);
+
+	return crypto_memneq(tag.bytes, zeros.bytes, authsize) ? -EBADMSG : 0;
+}
+
+static int crypto_aegis128l_aesni_init_tfm(struct crypto_aead *aead)
+{
+	return 0;
+}
+
+static void crypto_aegis128l_aesni_exit_tfm(struct crypto_aead *aead)
+{
+}
+
+static int cryptd_aegis128l_aesni_setkey(struct crypto_aead *aead,
+					 const u8 *key, unsigned int keylen)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
+}
+
+static int cryptd_aegis128l_aesni_setauthsize(struct crypto_aead *aead,
+					      unsigned int authsize)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
+}
+
+static int cryptd_aegis128l_aesni_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_encrypt(req);
+}
+
+static int cryptd_aegis128l_aesni_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_decrypt(req);
+}
+
+static int cryptd_aegis128l_aesni_init_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead *cryptd_tfm;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_tfm = cryptd_alloc_aead("__aegis128l-aesni", CRYPTO_ALG_INTERNAL,
+				       CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	*ctx = cryptd_tfm;
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
+	return 0;
+}
+
+static void cryptd_aegis128l_aesni_exit_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_free_aead(*ctx);
+}
+
+static struct aead_alg crypto_aegis128l_aesni_alg[] = {
+	{
+		.setkey = crypto_aegis128l_aesni_setkey,
+		.setauthsize = crypto_aegis128l_aesni_setauthsize,
+		.encrypt = crypto_aegis128l_aesni_encrypt,
+		.decrypt = crypto_aegis128l_aesni_decrypt,
+		.init = crypto_aegis128l_aesni_init_tfm,
+		.exit = crypto_aegis128l_aesni_exit_tfm,
+
+		.ivsize = AEGIS128L_NONCE_SIZE,
+		.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
+		.chunksize = AEGIS128L_BLOCK_SIZE,
+
+		.base = {
+			.cra_flags = CRYPTO_ALG_INTERNAL,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct aegis_ctx) +
+				__alignof__(struct aegis_ctx),
+			.cra_alignmask = 0,
+
+			.cra_name = "__aegis128l",
+			.cra_driver_name = "__aegis128l-aesni",
+
+			.cra_module = THIS_MODULE,
+		}
+	}, {
+		.setkey = cryptd_aegis128l_aesni_setkey,
+		.setauthsize = cryptd_aegis128l_aesni_setauthsize,
+		.encrypt = cryptd_aegis128l_aesni_encrypt,
+		.decrypt = cryptd_aegis128l_aesni_decrypt,
+		.init = cryptd_aegis128l_aesni_init_tfm,
+		.exit = cryptd_aegis128l_aesni_exit_tfm,
+
+		.ivsize = AEGIS128L_NONCE_SIZE,
+		.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
+		.chunksize = AEGIS128L_BLOCK_SIZE,
+
+		.base = {
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct cryptd_aead *),
+			.cra_alignmask = 0,
+
+			.cra_priority = 400,
+
+			.cra_name = "aegis128l",
+			.cra_driver_name = "aegis128l-aesni",
+
+			.cra_module = THIS_MODULE,
+		}
+	}
+};
+
+static const struct x86_cpu_id aesni_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_AES),
+	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
+
+static int __init crypto_aegis128l_aesni_module_init(void)
+{
+	if (!x86_match_cpu(aesni_cpu_id))
+		return -ENODEV;
+
+	return crypto_register_aeads(crypto_aegis128l_aesni_alg,
+				     ARRAY_SIZE(crypto_aegis128l_aesni_alg));
+}
+
+static void __exit crypto_aegis128l_aesni_module_exit(void)
+{
+	crypto_unregister_aeads(crypto_aegis128l_aesni_alg,
+				ARRAY_SIZE(crypto_aegis128l_aesni_alg));
+}
+
+module_init(crypto_aegis128l_aesni_module_init);
+module_exit(crypto_aegis128l_aesni_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("AEGIS-128L AEAD algorithm -- AESNI+SSE2 implementation");
+MODULE_ALIAS_CRYPTO("aegis128l");
+MODULE_ALIAS_CRYPTO("aegis128l-aesni");
diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S
new file mode 100644
index 000000000000..1d977d515bf9
--- /dev/null
+++ b/arch/x86/crypto/aegis256-aesni-asm.S
@@ -0,0 +1,702 @@
+/*
+ * AES-NI + SSE2 implementation of AEGIS-128L
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+#define STATE0	%xmm0
+#define STATE1	%xmm1
+#define STATE2	%xmm2
+#define STATE3	%xmm3
+#define STATE4	%xmm4
+#define STATE5	%xmm5
+#define MSG	%xmm6
+#define T0	%xmm7
+#define T1	%xmm8
+#define T2	%xmm9
+#define T3	%xmm10
+
+#define STATEP	%rdi
+#define LEN	%rsi
+#define SRC	%rdx
+#define DST	%rcx
+
+.section .rodata.cst16.aegis256_const, "aM", @progbits, 32
+.align 16
+.Laegis256_const_0:
+	.byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d
+	.byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62
+.Laegis256_const_1:
+	.byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1
+	.byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd
+
+.section .rodata.cst16.aegis256_counter, "aM", @progbits, 16
+.align 16
+.Laegis256_counter:
+	.byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+
+.text
+
+/*
+ * __load_partial: internal ABI
+ * input:
+ *   LEN - bytes
+ *   SRC - src
+ * output:
+ *   MSG  - message block
+ * changed:
+ *   T0
+ *   %r8
+ *   %r9
+ */
+__load_partial:
+	xor %r9, %r9
+	pxor MSG, MSG
+
+	mov LEN, %r8
+	and $0x1, %r8
+	jz .Lld_partial_1
+
+	mov LEN, %r8
+	and $0x1E, %r8
+	add SRC, %r8
+	mov (%r8), %r9b
+
+.Lld_partial_1:
+	mov LEN, %r8
+	and $0x2, %r8
+	jz .Lld_partial_2
+
+	mov LEN, %r8
+	and $0x1C, %r8
+	add SRC, %r8
+	shl $0x10, %r9
+	mov (%r8), %r9w
+
+.Lld_partial_2:
+	mov LEN, %r8
+	and $0x4, %r8
+	jz .Lld_partial_4
+
+	mov LEN, %r8
+	and $0x18, %r8
+	add SRC, %r8
+	shl $32, %r9
+	mov (%r8), %r8d
+	xor %r8, %r9
+
+.Lld_partial_4:
+	movq %r9, MSG
+
+	mov LEN, %r8
+	and $0x8, %r8
+	jz .Lld_partial_8
+
+	mov LEN, %r8
+	and $0x10, %r8
+	add SRC, %r8
+	pslldq $8, MSG
+	movq (%r8), T0
+	pxor T0, MSG
+
+.Lld_partial_8:
+	ret
+ENDPROC(__load_partial)
+
+/*
+ * __store_partial: internal ABI
+ * input:
+ *   LEN - bytes
+ *   DST - dst
+ * output:
+ *   T0   - message block
+ * changed:
+ *   %r8
+ *   %r9
+ *   %r10
+ */
+__store_partial:
+	mov LEN, %r8
+	mov DST, %r9
+
+	movq T0, %r10
+
+	cmp $8, %r8
+	jl .Lst_partial_8
+
+	mov %r10, (%r9)
+	psrldq $8, T0
+	movq T0, %r10
+
+	sub $8, %r8
+	add $8, %r9
+
+.Lst_partial_8:
+	cmp $4, %r8
+	jl .Lst_partial_4
+
+	mov %r10d, (%r9)
+	shr $32, %r10
+
+	sub $4, %r8
+	add $4, %r9
+
+.Lst_partial_4:
+	cmp $2, %r8
+	jl .Lst_partial_2
+
+	mov %r10w, (%r9)
+	shr $0x10, %r10
+
+	sub $2, %r8
+	add $2, %r9
+
+.Lst_partial_2:
+	cmp $1, %r8
+	jl .Lst_partial_1
+
+	mov %r10b, (%r9)
+
+.Lst_partial_1:
+	ret
+ENDPROC(__store_partial)
+
+.macro update
+	movdqa STATE5, T0
+	aesenc STATE0, STATE5
+	aesenc STATE1, STATE0
+	aesenc STATE2, STATE1
+	aesenc STATE3, STATE2
+	aesenc STATE4, STATE3
+	aesenc T0,     STATE4
+.endm
+
+.macro update0 m
+	update
+	pxor \m, STATE5
+.endm
+
+.macro update1 m
+	update
+	pxor \m, STATE4
+.endm
+
+.macro update2 m
+	update
+	pxor \m, STATE3
+.endm
+
+.macro update3 m
+	update
+	pxor \m, STATE2
+.endm
+
+.macro update4 m
+	update
+	pxor \m, STATE1
+.endm
+
+.macro update5 m
+	update
+	pxor \m, STATE0
+.endm
+
+.macro state_load
+	movdqu 0x00(STATEP), STATE0
+	movdqu 0x10(STATEP), STATE1
+	movdqu 0x20(STATEP), STATE2
+	movdqu 0x30(STATEP), STATE3
+	movdqu 0x40(STATEP), STATE4
+	movdqu 0x50(STATEP), STATE5
+.endm
+
+.macro state_store s0 s1 s2 s3 s4 s5
+	movdqu \s5, 0x00(STATEP)
+	movdqu \s0, 0x10(STATEP)
+	movdqu \s1, 0x20(STATEP)
+	movdqu \s2, 0x30(STATEP)
+	movdqu \s3, 0x40(STATEP)
+	movdqu \s4, 0x50(STATEP)
+.endm
+
+.macro state_store0
+	state_store STATE0 STATE1 STATE2 STATE3 STATE4 STATE5
+.endm
+
+.macro state_store1
+	state_store STATE5 STATE0 STATE1 STATE2 STATE3 STATE4
+.endm
+
+.macro state_store2
+	state_store STATE4 STATE5 STATE0 STATE1 STATE2 STATE3
+.endm
+
+.macro state_store3
+	state_store STATE3 STATE4 STATE5 STATE0 STATE1 STATE2
+.endm
+
+.macro state_store4
+	state_store STATE2 STATE3 STATE4 STATE5 STATE0 STATE1
+.endm
+
+.macro state_store5
+	state_store STATE1 STATE2 STATE3 STATE4 STATE5 STATE0
+.endm
+
+/*
+ * void crypto_aegis256_aesni_init(void *state, const void *key, const void *iv);
+ */
+ENTRY(crypto_aegis256_aesni_init)
+	FRAME_BEGIN
+
+	/* load key: */
+	movdqa 0x00(%rsi), MSG
+	movdqa 0x10(%rsi), T1
+	movdqa MSG, STATE4
+	movdqa T1, STATE5
+
+	/* load IV: */
+	movdqu 0x00(%rdx), T2
+	movdqu 0x10(%rdx), T3
+	pxor MSG, T2
+	pxor T1, T3
+	movdqa T2, STATE0
+	movdqa T3, STATE1
+
+	/* load the constants: */
+	movdqa .Laegis256_const_0, STATE3
+	movdqa .Laegis256_const_1, STATE2
+	pxor STATE3, STATE4
+	pxor STATE2, STATE5
+
+	/* update 10 times with IV and KEY: */
+	update0 MSG
+	update1 T1
+	update2 T2
+	update3 T3
+	update4 MSG
+	update5 T1
+	update0 T2
+	update1 T3
+	update2 MSG
+	update3 T1
+	update4 T2
+	update5 T3
+	update0 MSG
+	update1 T1
+	update2 T2
+	update3 T3
+
+	state_store3
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis256_aesni_init)
+
+.macro ad_block a i
+	movdq\a (\i * 0x10)(SRC), MSG
+	update\i MSG
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lad_out_\i
+.endm
+
+/*
+ * void crypto_aegis256_aesni_ad(void *state, unsigned int length,
+ *                               const void *data);
+ */
+ENTRY(crypto_aegis256_aesni_ad)
+	FRAME_BEGIN
+
+	cmp $0x10, LEN
+	jb .Lad_out
+
+	state_load
+
+	mov  SRC, %r8
+	and $0xf, %r8
+	jnz .Lad_u_loop
+
+.align 8
+.Lad_a_loop:
+	ad_block a 0
+	ad_block a 1
+	ad_block a 2
+	ad_block a 3
+	ad_block a 4
+	ad_block a 5
+
+	add $0x60, SRC
+	jmp .Lad_a_loop
+
+.align 8
+.Lad_u_loop:
+	ad_block u 0
+	ad_block u 1
+	ad_block u 2
+	ad_block u 3
+	ad_block u 4
+	ad_block u 5
+
+	add $0x60, SRC
+	jmp .Lad_u_loop
+
+.Lad_out_0:
+	state_store0
+	FRAME_END
+	ret
+
+.Lad_out_1:
+	state_store1
+	FRAME_END
+	ret
+
+.Lad_out_2:
+	state_store2
+	FRAME_END
+	ret
+
+.Lad_out_3:
+	state_store3
+	FRAME_END
+	ret
+
+.Lad_out_4:
+	state_store4
+	FRAME_END
+	ret
+
+.Lad_out_5:
+	state_store5
+	FRAME_END
+	ret
+
+.Lad_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis256_aesni_ad)
+
+.macro crypt m s0 s1 s2 s3 s4 s5
+	pxor \s1, \m
+	pxor \s4, \m
+	pxor \s5, \m
+	movdqa \s2, T3
+	pand \s3, T3
+	pxor T3, \m
+.endm
+
+.macro crypt0 m
+	crypt \m STATE0 STATE1 STATE2 STATE3 STATE4 STATE5
+.endm
+
+.macro crypt1 m
+	crypt \m STATE5 STATE0 STATE1 STATE2 STATE3 STATE4
+.endm
+
+.macro crypt2 m
+	crypt \m STATE4 STATE5 STATE0 STATE1 STATE2 STATE3
+.endm
+
+.macro crypt3 m
+	crypt \m STATE3 STATE4 STATE5 STATE0 STATE1 STATE2
+.endm
+
+.macro crypt4 m
+	crypt \m STATE2 STATE3 STATE4 STATE5 STATE0 STATE1
+.endm
+
+.macro crypt5 m
+	crypt \m STATE1 STATE2 STATE3 STATE4 STATE5 STATE0
+.endm
+
+.macro encrypt_block a i
+	movdq\a (\i * 0x10)(SRC), MSG
+	movdqa MSG, T0
+	crypt\i T0
+	movdq\a T0, (\i * 0x10)(DST)
+
+	update\i MSG
+
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Lenc_out_\i
+.endm
+
+.macro decrypt_block a i
+	movdq\a (\i * 0x10)(SRC), MSG
+	crypt\i MSG
+	movdq\a MSG, (\i * 0x10)(DST)
+
+	update\i MSG
+
+	sub $0x10, LEN
+	cmp $0x10, LEN
+	jl .Ldec_out_\i
+.endm
+
+/*
+ * void crypto_aegis256_aesni_enc(void *state, unsigned int length,
+ *                                const void *src, void *dst);
+ */
+ENTRY(crypto_aegis256_aesni_enc)
+	FRAME_BEGIN
+
+	cmp $0x10, LEN
+	jb .Lenc_out
+
+	state_load
+
+	mov  SRC, %r8
+	or   DST, %r8
+	and $0xf, %r8
+	jnz .Lenc_u_loop
+
+.align 8
+.Lenc_a_loop:
+	encrypt_block a 0
+	encrypt_block a 1
+	encrypt_block a 2
+	encrypt_block a 3
+	encrypt_block a 4
+	encrypt_block a 5
+
+	add $0x60, SRC
+	add $0x60, DST
+	jmp .Lenc_a_loop
+
+.align 8
+.Lenc_u_loop:
+	encrypt_block u 0
+	encrypt_block u 1
+	encrypt_block u 2
+	encrypt_block u 3
+	encrypt_block u 4
+	encrypt_block u 5
+
+	add $0x60, SRC
+	add $0x60, DST
+	jmp .Lenc_u_loop
+
+.Lenc_out_0:
+	state_store0
+	FRAME_END
+	ret
+
+.Lenc_out_1:
+	state_store1
+	FRAME_END
+	ret
+
+.Lenc_out_2:
+	state_store2
+	FRAME_END
+	ret
+
+.Lenc_out_3:
+	state_store3
+	FRAME_END
+	ret
+
+.Lenc_out_4:
+	state_store4
+	FRAME_END
+	ret
+
+.Lenc_out_5:
+	state_store5
+	FRAME_END
+	ret
+
+.Lenc_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis256_aesni_enc)
+
+/*
+ * void crypto_aegis256_aesni_enc_tail(void *state, unsigned int length,
+ *                                     const void *src, void *dst);
+ */
+ENTRY(crypto_aegis256_aesni_enc_tail)
+	FRAME_BEGIN
+
+	state_load
+
+	/* encrypt message: */
+	call __load_partial
+
+	movdqa MSG, T0
+	crypt0 T0
+
+	call __store_partial
+
+	update0 MSG
+
+	state_store0
+
+	FRAME_END
+ENDPROC(crypto_aegis256_aesni_enc_tail)
+
+/*
+ * void crypto_aegis256_aesni_dec(void *state, unsigned int length,
+ *                                const void *src, void *dst);
+ */
+ENTRY(crypto_aegis256_aesni_dec)
+	FRAME_BEGIN
+
+	cmp $0x10, LEN
+	jb .Ldec_out
+
+	state_load
+
+	mov  SRC, %r8
+	or   DST, %r8
+	and $0xF, %r8
+	jnz .Ldec_u_loop
+
+.align 8
+.Ldec_a_loop:
+	decrypt_block a 0
+	decrypt_block a 1
+	decrypt_block a 2
+	decrypt_block a 3
+	decrypt_block a 4
+	decrypt_block a 5
+
+	add $0x60, SRC
+	add $0x60, DST
+	jmp .Ldec_a_loop
+
+.align 8
+.Ldec_u_loop:
+	decrypt_block u 0
+	decrypt_block u 1
+	decrypt_block u 2
+	decrypt_block u 3
+	decrypt_block u 4
+	decrypt_block u 5
+
+	add $0x60, SRC
+	add $0x60, DST
+	jmp .Ldec_u_loop
+
+.Ldec_out_0:
+	state_store0
+	FRAME_END
+	ret
+
+.Ldec_out_1:
+	state_store1
+	FRAME_END
+	ret
+
+.Ldec_out_2:
+	state_store2
+	FRAME_END
+	ret
+
+.Ldec_out_3:
+	state_store3
+	FRAME_END
+	ret
+
+.Ldec_out_4:
+	state_store4
+	FRAME_END
+	ret
+
+.Ldec_out_5:
+	state_store5
+	FRAME_END
+	ret
+
+.Ldec_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis256_aesni_dec)
+
+/*
+ * void crypto_aegis256_aesni_dec_tail(void *state, unsigned int length,
+ *                                     const void *src, void *dst);
+ */
+ENTRY(crypto_aegis256_aesni_dec_tail)
+	FRAME_BEGIN
+
+	state_load
+
+	/* decrypt message: */
+	call __load_partial
+
+	crypt0 MSG
+
+	movdqa MSG, T0
+	call __store_partial
+
+	/* mask with byte count: */
+	movq LEN, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	movdqa .Laegis256_counter, T1
+	pcmpgtb T1, T0
+	pand T0, MSG
+
+	update0 MSG
+
+	state_store0
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis256_aesni_dec_tail)
+
+/*
+ * void crypto_aegis256_aesni_final(void *state, void *tag_xor,
+ *                                  u64 assoclen, u64 cryptlen);
+ */
+ENTRY(crypto_aegis256_aesni_final)
+	FRAME_BEGIN
+
+	state_load
+
+	/* prepare length block: */
+	movq %rdx, MSG
+	movq %rcx, T0
+	pslldq $8, T0
+	pxor T0, MSG
+	psllq $3, MSG /* multiply by 8 (to get bit count) */
+
+	pxor STATE3, MSG
+
+	/* update state: */
+	update0 MSG
+	update1 MSG
+	update2 MSG
+	update3 MSG
+	update4 MSG
+	update5 MSG
+	update0 MSG
+
+	/* xor tag: */
+	movdqu (%rsi), MSG
+
+	pxor STATE0, MSG
+	pxor STATE1, MSG
+	pxor STATE2, MSG
+	pxor STATE3, MSG
+	pxor STATE4, MSG
+	pxor STATE5, MSG
+
+	movdqu MSG, (%rsi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_aegis256_aesni_final)
diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c
new file mode 100644
index 000000000000..2b5dd3af8f4d
--- /dev/null
+++ b/arch/x86/crypto/aegis256-aesni-glue.c
@@ -0,0 +1,407 @@
+/*
+ * The AEGIS-256 Authenticated-Encryption Algorithm
+ *   Glue for AES-NI + SSE2 implementation
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/cryptd.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/cpu_device_id.h>
+
+#define AEGIS256_BLOCK_ALIGN 16
+#define AEGIS256_BLOCK_SIZE 16
+#define AEGIS256_NONCE_SIZE 32
+#define AEGIS256_STATE_BLOCKS 6
+#define AEGIS256_KEY_SIZE 32
+#define AEGIS256_MIN_AUTH_SIZE 8
+#define AEGIS256_MAX_AUTH_SIZE 16
+
+asmlinkage void crypto_aegis256_aesni_init(void *state, void *key, void *iv);
+
+asmlinkage void crypto_aegis256_aesni_ad(
+		void *state, unsigned int length, const void *data);
+
+asmlinkage void crypto_aegis256_aesni_enc(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis256_aesni_dec(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis256_aesni_enc_tail(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis256_aesni_dec_tail(
+		void *state, unsigned int length, const void *src, void *dst);
+
+asmlinkage void crypto_aegis256_aesni_final(
+		void *state, void *tag_xor, unsigned int cryptlen,
+		unsigned int assoclen);
+
+struct aegis_block {
+	u8 bytes[AEGIS256_BLOCK_SIZE] __aligned(AEGIS256_BLOCK_ALIGN);
+};
+
+struct aegis_state {
+	struct aegis_block blocks[AEGIS256_STATE_BLOCKS];
+};
+
+struct aegis_ctx {
+	struct aegis_block key[AEGIS256_KEY_SIZE / AEGIS256_BLOCK_SIZE];
+};
+
+struct aegis_crypt_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_blocks)(void *state, unsigned int length, const void *src,
+			     void *dst);
+	void (*crypt_tail)(void *state, unsigned int length, const void *src,
+			   void *dst);
+};
+
+static void crypto_aegis256_aesni_process_ad(
+		struct aegis_state *state, struct scatterlist *sg_src,
+		unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	struct aegis_block buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= AEGIS256_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = AEGIS256_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+				crypto_aegis256_aesni_ad(state,
+							 AEGIS256_BLOCK_SIZE,
+							 buf.bytes);
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			crypto_aegis256_aesni_ad(state, left, src);
+
+			src += left & ~(AEGIS256_BLOCK_SIZE - 1);
+			left &= AEGIS256_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+		pos += left;
+		assoclen -= size;
+
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, AEGIS256_BLOCK_SIZE - pos);
+		crypto_aegis256_aesni_ad(state, AEGIS256_BLOCK_SIZE, buf.bytes);
+	}
+}
+
+static void crypto_aegis256_aesni_process_crypt(
+		struct aegis_state *state, struct aead_request *req,
+		const struct aegis_crypt_ops *ops)
+{
+	struct skcipher_walk walk;
+	u8 *src, *dst;
+	unsigned int chunksize, base;
+
+	ops->skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+		chunksize = walk.nbytes;
+
+		ops->crypt_blocks(state, chunksize, src, dst);
+
+		base = chunksize & ~(AEGIS256_BLOCK_SIZE - 1);
+		src += base;
+		dst += base;
+		chunksize &= AEGIS256_BLOCK_SIZE - 1;
+
+		if (chunksize > 0)
+			ops->crypt_tail(state, chunksize, src, dst);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+static struct aegis_ctx *crypto_aegis256_aesni_ctx(struct crypto_aead *aead)
+{
+	u8 *ctx = crypto_aead_ctx(aead);
+	ctx = PTR_ALIGN(ctx, __alignof__(struct aegis_ctx));
+	return (void *)ctx;
+}
+
+static int crypto_aegis256_aesni_setkey(struct crypto_aead *aead, const u8 *key,
+					unsigned int keylen)
+{
+	struct aegis_ctx *ctx = crypto_aegis256_aesni_ctx(aead);
+
+	if (keylen != AEGIS256_KEY_SIZE) {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, AEGIS256_KEY_SIZE);
+
+	return 0;
+}
+
+static int crypto_aegis256_aesni_setauthsize(struct crypto_aead *tfm,
+						unsigned int authsize)
+{
+	if (authsize > AEGIS256_MAX_AUTH_SIZE)
+		return -EINVAL;
+	if (authsize < AEGIS256_MIN_AUTH_SIZE)
+		return -EINVAL;
+	return 0;
+}
+
+static void crypto_aegis256_aesni_crypt(struct aead_request *req,
+					struct aegis_block *tag_xor,
+					unsigned int cryptlen,
+					const struct aegis_crypt_ops *ops)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_ctx *ctx = crypto_aegis256_aesni_ctx(tfm);
+	struct aegis_state state;
+
+	kernel_fpu_begin();
+
+	crypto_aegis256_aesni_init(&state, ctx->key, req->iv);
+	crypto_aegis256_aesni_process_ad(&state, req->src, req->assoclen);
+	crypto_aegis256_aesni_process_crypt(&state, req, ops);
+	crypto_aegis256_aesni_final(&state, tag_xor, req->assoclen, cryptlen);
+
+	kernel_fpu_end();
+}
+
+static int crypto_aegis256_aesni_encrypt(struct aead_request *req)
+{
+	static const struct aegis_crypt_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_blocks = crypto_aegis256_aesni_enc,
+		.crypt_tail = crypto_aegis256_aesni_enc_tail,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_block tag = {};
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_aegis256_aesni_crypt(req, &tag, cryptlen, &OPS);
+
+	scatterwalk_map_and_copy(tag.bytes, req->dst,
+				 req->assoclen + cryptlen, authsize, 1);
+	return 0;
+}
+
+static int crypto_aegis256_aesni_decrypt(struct aead_request *req)
+{
+	static const struct aegis_block zeros = {};
+
+	static const struct aegis_crypt_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_blocks = crypto_aegis256_aesni_dec,
+		.crypt_tail = crypto_aegis256_aesni_dec_tail,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag.bytes, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
+
+	crypto_aegis256_aesni_crypt(req, &tag, cryptlen, &OPS);
+
+	return crypto_memneq(tag.bytes, zeros.bytes, authsize) ? -EBADMSG : 0;
+}
+
+static int crypto_aegis256_aesni_init_tfm(struct crypto_aead *aead)
+{
+	return 0;
+}
+
+static void crypto_aegis256_aesni_exit_tfm(struct crypto_aead *aead)
+{
+}
+
+static int cryptd_aegis256_aesni_setkey(struct crypto_aead *aead,
+					const u8 *key, unsigned int keylen)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
+}
+
+static int cryptd_aegis256_aesni_setauthsize(struct crypto_aead *aead,
+					     unsigned int authsize)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
+}
+
+static int cryptd_aegis256_aesni_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_encrypt(req);
+}
+
+static int cryptd_aegis256_aesni_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_decrypt(req);
+}
+
+static int cryptd_aegis256_aesni_init_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead *cryptd_tfm;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_tfm = cryptd_alloc_aead("__aegis256-aesni", CRYPTO_ALG_INTERNAL,
+				       CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	*ctx = cryptd_tfm;
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
+	return 0;
+}
+
+static void cryptd_aegis256_aesni_exit_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_free_aead(*ctx);
+}
+
+static struct aead_alg crypto_aegis256_aesni_alg[] = {
+	{
+		.setkey = crypto_aegis256_aesni_setkey,
+		.setauthsize = crypto_aegis256_aesni_setauthsize,
+		.encrypt = crypto_aegis256_aesni_encrypt,
+		.decrypt = crypto_aegis256_aesni_decrypt,
+		.init = crypto_aegis256_aesni_init_tfm,
+		.exit = crypto_aegis256_aesni_exit_tfm,
+
+		.ivsize = AEGIS256_NONCE_SIZE,
+		.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
+		.chunksize = AEGIS256_BLOCK_SIZE,
+
+		.base = {
+			.cra_flags = CRYPTO_ALG_INTERNAL,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct aegis_ctx) +
+				__alignof__(struct aegis_ctx),
+			.cra_alignmask = 0,
+
+			.cra_name = "__aegis256",
+			.cra_driver_name = "__aegis256-aesni",
+
+			.cra_module = THIS_MODULE,
+		}
+	}, {
+		.setkey = cryptd_aegis256_aesni_setkey,
+		.setauthsize = cryptd_aegis256_aesni_setauthsize,
+		.encrypt = cryptd_aegis256_aesni_encrypt,
+		.decrypt = cryptd_aegis256_aesni_decrypt,
+		.init = cryptd_aegis256_aesni_init_tfm,
+		.exit = cryptd_aegis256_aesni_exit_tfm,
+
+		.ivsize = AEGIS256_NONCE_SIZE,
+		.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
+		.chunksize = AEGIS256_BLOCK_SIZE,
+
+		.base = {
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = 1,
+			.cra_ctxsize = sizeof(struct cryptd_aead *),
+			.cra_alignmask = 0,
+
+			.cra_priority = 400,
+
+			.cra_name = "aegis256",
+			.cra_driver_name = "aegis256-aesni",
+
+			.cra_module = THIS_MODULE,
+		}
+	}
+};
+
+static const struct x86_cpu_id aesni_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_AES),
+	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
+
+static int __init crypto_aegis256_aesni_module_init(void)
+{
+	if (!x86_match_cpu(aesni_cpu_id))
+		return -ENODEV;
+
+	return crypto_register_aeads(crypto_aegis256_aesni_alg,
+				    ARRAY_SIZE(crypto_aegis256_aesni_alg));
+}
+
+static void __exit crypto_aegis256_aesni_module_exit(void)
+{
+	crypto_unregister_aeads(crypto_aegis256_aesni_alg,
+				ARRAY_SIZE(crypto_aegis256_aesni_alg));
+}
+
+module_init(crypto_aegis256_aesni_module_init);
+module_exit(crypto_aegis256_aesni_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("AEGIS-256 AEAD algorithm -- AESNI+SSE2 implementation");
+MODULE_ALIAS_CRYPTO("aegis256");
+MODULE_ALIAS_CRYPTO("aegis256-aesni");
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 0420bab19efb..2ddbe3a1868b 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -364,5 +364,5 @@ module_exit(ghash_pclmulqdqni_mod_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm, "
-		   "acclerated by PCLMULQDQ-NI");
+		   "accelerated by PCLMULQDQ-NI");
 MODULE_ALIAS_CRYPTO("ghash");
diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S
new file mode 100644
index 000000000000..37d422e77931
--- /dev/null
+++ b/arch/x86/crypto/morus1280-avx2-asm.S
@@ -0,0 +1,621 @@
+/*
+ * AVX2 implementation of MORUS-1280
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+#define SHUFFLE_MASK(i0, i1, i2, i3) \
+	(i0 | (i1 << 2) | (i2 << 4) | (i3 << 6))
+
+#define MASK1 SHUFFLE_MASK(3, 0, 1, 2)
+#define MASK2 SHUFFLE_MASK(2, 3, 0, 1)
+#define MASK3 SHUFFLE_MASK(1, 2, 3, 0)
+
+#define STATE0		%ymm0
+#define STATE0_LOW	%xmm0
+#define STATE1		%ymm1
+#define STATE2		%ymm2
+#define STATE3		%ymm3
+#define STATE4		%ymm4
+#define KEY		%ymm5
+#define MSG		%ymm5
+#define MSG_LOW		%xmm5
+#define T0		%ymm6
+#define T0_LOW		%xmm6
+#define T1		%ymm7
+
+.section .rodata.cst32.morus1280_const, "aM", @progbits, 32
+.align 32
+.Lmorus1280_const:
+	.byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d
+	.byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62
+	.byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1
+	.byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd
+
+.section .rodata.cst32.morus1280_counter, "aM", @progbits, 32
+.align 32
+.Lmorus1280_counter:
+	.byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+	.byte 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17
+	.byte 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f
+
+.text
+
+.macro morus1280_round s0, s1, s2, s3, s4, b, w
+	vpand \s1, \s2, T0
+	vpxor T0, \s0, \s0
+	vpxor \s3, \s0, \s0
+	vpsllq $\b, \s0, T0
+	vpsrlq $(64 - \b), \s0, \s0
+	vpxor T0, \s0, \s0
+	vpermq $\w, \s3, \s3
+.endm
+
+/*
+ * __morus1280_update: internal ABI
+ * input:
+ *   STATE[0-4] - input state
+ *   MSG        - message block
+ * output:
+ *   STATE[0-4] - output state
+ * changed:
+ *   T0
+ */
+__morus1280_update:
+	morus1280_round STATE0, STATE1, STATE2, STATE3, STATE4, 13, MASK1
+	vpxor MSG, STATE1, STATE1
+	morus1280_round STATE1, STATE2, STATE3, STATE4, STATE0, 46, MASK2
+	vpxor MSG, STATE2, STATE2
+	morus1280_round STATE2, STATE3, STATE4, STATE0, STATE1, 38, MASK3
+	vpxor MSG, STATE3, STATE3
+	morus1280_round STATE3, STATE4, STATE0, STATE1, STATE2,  7, MASK2
+	vpxor MSG, STATE4, STATE4
+	morus1280_round STATE4, STATE0, STATE1, STATE2, STATE3,  4, MASK1
+	ret
+ENDPROC(__morus1280_update)
+
+/*
+ * __morus1280_update_zero: internal ABI
+ * input:
+ *   STATE[0-4] - input state
+ * output:
+ *   STATE[0-4] - output state
+ * changed:
+ *   T0
+ */
+__morus1280_update_zero:
+	morus1280_round STATE0, STATE1, STATE2, STATE3, STATE4, 13, MASK1
+	morus1280_round STATE1, STATE2, STATE3, STATE4, STATE0, 46, MASK2
+	morus1280_round STATE2, STATE3, STATE4, STATE0, STATE1, 38, MASK3
+	morus1280_round STATE3, STATE4, STATE0, STATE1, STATE2,  7, MASK2
+	morus1280_round STATE4, STATE0, STATE1, STATE2, STATE3,  4, MASK1
+	ret
+ENDPROC(__morus1280_update_zero)
+
+/*
+ * __load_partial: internal ABI
+ * input:
+ *   %rsi - src
+ *   %rcx - bytes
+ * output:
+ *   MSG  - message block
+ * changed:
+ *   %r8
+ *   %r9
+ */
+__load_partial:
+	xor %r9, %r9
+	vpxor MSG, MSG, MSG
+
+	mov %rcx, %r8
+	and $0x1, %r8
+	jz .Lld_partial_1
+
+	mov %rcx, %r8
+	and $0x1E, %r8
+	add %rsi, %r8
+	mov (%r8), %r9b
+
+.Lld_partial_1:
+	mov %rcx, %r8
+	and $0x2, %r8
+	jz .Lld_partial_2
+
+	mov %rcx, %r8
+	and $0x1C, %r8
+	add %rsi, %r8
+	shl $16, %r9
+	mov (%r8), %r9w
+
+.Lld_partial_2:
+	mov %rcx, %r8
+	and $0x4, %r8
+	jz .Lld_partial_4
+
+	mov %rcx, %r8
+	and $0x18, %r8
+	add %rsi, %r8
+	shl $32, %r9
+	mov (%r8), %r8d
+	xor %r8, %r9
+
+.Lld_partial_4:
+	movq %r9, MSG_LOW
+
+	mov %rcx, %r8
+	and $0x8, %r8
+	jz .Lld_partial_8
+
+	mov %rcx, %r8
+	and $0x10, %r8
+	add %rsi, %r8
+	pshufd $MASK2, MSG_LOW, MSG_LOW
+	pinsrq $0, (%r8), MSG_LOW
+
+.Lld_partial_8:
+	mov %rcx, %r8
+	and $0x10, %r8
+	jz .Lld_partial_16
+
+	vpermq $MASK2, MSG, MSG
+	movdqu (%rsi), MSG_LOW
+
+.Lld_partial_16:
+	ret
+ENDPROC(__load_partial)
+
+/*
+ * __store_partial: internal ABI
+ * input:
+ *   %rdx - dst
+ *   %rcx - bytes
+ * output:
+ *   T0   - message block
+ * changed:
+ *   %r8
+ *   %r9
+ *   %r10
+ */
+__store_partial:
+	mov %rcx, %r8
+	mov %rdx, %r9
+
+	cmp $16, %r8
+	jl .Lst_partial_16
+
+	movdqu T0_LOW, (%r9)
+	vpermq $MASK2, T0, T0
+
+	sub $16, %r8
+	add $16, %r9
+
+.Lst_partial_16:
+	movq T0_LOW, %r10
+
+	cmp $8, %r8
+	jl .Lst_partial_8
+
+	mov %r10, (%r9)
+	pextrq $1, T0_LOW, %r10
+
+	sub $8, %r8
+	add $8, %r9
+
+.Lst_partial_8:
+	cmp $4, %r8
+	jl .Lst_partial_4
+
+	mov %r10d, (%r9)
+	shr $32, %r10
+
+	sub $4, %r8
+	add $4, %r9
+
+.Lst_partial_4:
+	cmp $2, %r8
+	jl .Lst_partial_2
+
+	mov %r10w, (%r9)
+	shr $16, %r10
+
+	sub $2, %r8
+	add $2, %r9
+
+.Lst_partial_2:
+	cmp $1, %r8
+	jl .Lst_partial_1
+
+	mov %r10b, (%r9)
+
+.Lst_partial_1:
+	ret
+ENDPROC(__store_partial)
+
+/*
+ * void crypto_morus1280_avx2_init(void *state, const void *key,
+ *                                 const void *iv);
+ */
+ENTRY(crypto_morus1280_avx2_init)
+	FRAME_BEGIN
+
+	/* load IV: */
+	vpxor STATE0, STATE0, STATE0
+	movdqu (%rdx), STATE0_LOW
+	/* load key: */
+	vmovdqu (%rsi), KEY
+	vmovdqa KEY, STATE1
+	/* load all ones: */
+	vpcmpeqd STATE2, STATE2, STATE2
+	/* load all zeros: */
+	vpxor STATE3, STATE3, STATE3
+	/* load the constant: */
+	vmovdqa .Lmorus1280_const, STATE4
+
+	/* update 16 times with zero: */
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+
+	/* xor-in the key again after updates: */
+	vpxor KEY, STATE1, STATE1
+
+	/* store the state: */
+	vmovdqu STATE0, (0 * 32)(%rdi)
+	vmovdqu STATE1, (1 * 32)(%rdi)
+	vmovdqu STATE2, (2 * 32)(%rdi)
+	vmovdqu STATE3, (3 * 32)(%rdi)
+	vmovdqu STATE4, (4 * 32)(%rdi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_avx2_init)
+
+/*
+ * void crypto_morus1280_avx2_ad(void *state, const void *data,
+ *                               unsigned int length);
+ */
+ENTRY(crypto_morus1280_avx2_ad)
+	FRAME_BEGIN
+
+	cmp $32, %rdx
+	jb .Lad_out
+
+	/* load the state: */
+	vmovdqu (0 * 32)(%rdi), STATE0
+	vmovdqu (1 * 32)(%rdi), STATE1
+	vmovdqu (2 * 32)(%rdi), STATE2
+	vmovdqu (3 * 32)(%rdi), STATE3
+	vmovdqu (4 * 32)(%rdi), STATE4
+
+	mov %rsi,  %r8
+	and $0x1F, %r8
+	jnz .Lad_u_loop
+
+.align 4
+.Lad_a_loop:
+	vmovdqa (%rsi), MSG
+	call __morus1280_update
+	sub $32, %rdx
+	add $32, %rsi
+	cmp $32, %rdx
+	jge .Lad_a_loop
+
+	jmp .Lad_cont
+.align 4
+.Lad_u_loop:
+	vmovdqu (%rsi), MSG
+	call __morus1280_update
+	sub $32, %rdx
+	add $32, %rsi
+	cmp $32, %rdx
+	jge .Lad_u_loop
+
+.Lad_cont:
+	/* store the state: */
+	vmovdqu STATE0, (0 * 32)(%rdi)
+	vmovdqu STATE1, (1 * 32)(%rdi)
+	vmovdqu STATE2, (2 * 32)(%rdi)
+	vmovdqu STATE3, (3 * 32)(%rdi)
+	vmovdqu STATE4, (4 * 32)(%rdi)
+
+.Lad_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_avx2_ad)
+
+/*
+ * void crypto_morus1280_avx2_enc(void *state, const void *src, void *dst,
+ *                                unsigned int length);
+ */
+ENTRY(crypto_morus1280_avx2_enc)
+	FRAME_BEGIN
+
+	cmp $32, %rcx
+	jb .Lenc_out
+
+	/* load the state: */
+	vmovdqu (0 * 32)(%rdi), STATE0
+	vmovdqu (1 * 32)(%rdi), STATE1
+	vmovdqu (2 * 32)(%rdi), STATE2
+	vmovdqu (3 * 32)(%rdi), STATE3
+	vmovdqu (4 * 32)(%rdi), STATE4
+
+	mov %rsi,  %r8
+	or  %rdx,  %r8
+	and $0x1F, %r8
+	jnz .Lenc_u_loop
+
+.align 4
+.Lenc_a_loop:
+	vmovdqa (%rsi), MSG
+	vmovdqa MSG, T0
+	vpxor STATE0, T0, T0
+	vpermq $MASK3, STATE1, T1
+	vpxor T1, T0, T0
+	vpand STATE2, STATE3, T1
+	vpxor T1, T0, T0
+	vmovdqa T0, (%rdx)
+
+	call __morus1280_update
+	sub $32, %rcx
+	add $32, %rsi
+	add $32, %rdx
+	cmp $32, %rcx
+	jge .Lenc_a_loop
+
+	jmp .Lenc_cont
+.align 4
+.Lenc_u_loop:
+	vmovdqu (%rsi), MSG
+	vmovdqa MSG, T0
+	vpxor STATE0, T0, T0
+	vpermq $MASK3, STATE1, T1
+	vpxor T1, T0, T0
+	vpand STATE2, STATE3, T1
+	vpxor T1, T0, T0
+	vmovdqu T0, (%rdx)
+
+	call __morus1280_update
+	sub $32, %rcx
+	add $32, %rsi
+	add $32, %rdx
+	cmp $32, %rcx
+	jge .Lenc_u_loop
+
+.Lenc_cont:
+	/* store the state: */
+	vmovdqu STATE0, (0 * 32)(%rdi)
+	vmovdqu STATE1, (1 * 32)(%rdi)
+	vmovdqu STATE2, (2 * 32)(%rdi)
+	vmovdqu STATE3, (3 * 32)(%rdi)
+	vmovdqu STATE4, (4 * 32)(%rdi)
+
+.Lenc_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_avx2_enc)
+
+/*
+ * void crypto_morus1280_avx2_enc_tail(void *state, const void *src, void *dst,
+ *                                     unsigned int length);
+ */
+ENTRY(crypto_morus1280_avx2_enc_tail)
+	FRAME_BEGIN
+
+	/* load the state: */
+	vmovdqu (0 * 32)(%rdi), STATE0
+	vmovdqu (1 * 32)(%rdi), STATE1
+	vmovdqu (2 * 32)(%rdi), STATE2
+	vmovdqu (3 * 32)(%rdi), STATE3
+	vmovdqu (4 * 32)(%rdi), STATE4
+
+	/* encrypt message: */
+	call __load_partial
+
+	vmovdqa MSG, T0
+	vpxor STATE0, T0, T0
+	vpermq $MASK3, STATE1, T1
+	vpxor T1, T0, T0
+	vpand STATE2, STATE3, T1
+	vpxor T1, T0, T0
+
+	call __store_partial
+
+	call __morus1280_update
+
+	/* store the state: */
+	vmovdqu STATE0, (0 * 32)(%rdi)
+	vmovdqu STATE1, (1 * 32)(%rdi)
+	vmovdqu STATE2, (2 * 32)(%rdi)
+	vmovdqu STATE3, (3 * 32)(%rdi)
+	vmovdqu STATE4, (4 * 32)(%rdi)
+
+	FRAME_END
+ENDPROC(crypto_morus1280_avx2_enc_tail)
+
+/*
+ * void crypto_morus1280_avx2_dec(void *state, const void *src, void *dst,
+ *                                unsigned int length);
+ */
+ENTRY(crypto_morus1280_avx2_dec)
+	FRAME_BEGIN
+
+	cmp $32, %rcx
+	jb .Ldec_out
+
+	/* load the state: */
+	vmovdqu (0 * 32)(%rdi), STATE0
+	vmovdqu (1 * 32)(%rdi), STATE1
+	vmovdqu (2 * 32)(%rdi), STATE2
+	vmovdqu (3 * 32)(%rdi), STATE3
+	vmovdqu (4 * 32)(%rdi), STATE4
+
+	mov %rsi,  %r8
+	or  %rdx,  %r8
+	and $0x1F, %r8
+	jnz .Ldec_u_loop
+
+.align 4
+.Ldec_a_loop:
+	vmovdqa (%rsi), MSG
+	vpxor STATE0, MSG, MSG
+	vpermq $MASK3, STATE1, T0
+	vpxor T0, MSG, MSG
+	vpand STATE2, STATE3, T0
+	vpxor T0, MSG, MSG
+	vmovdqa MSG, (%rdx)
+
+	call __morus1280_update
+	sub $32, %rcx
+	add $32, %rsi
+	add $32, %rdx
+	cmp $32, %rcx
+	jge .Ldec_a_loop
+
+	jmp .Ldec_cont
+.align 4
+.Ldec_u_loop:
+	vmovdqu (%rsi), MSG
+	vpxor STATE0, MSG, MSG
+	vpermq $MASK3, STATE1, T0
+	vpxor T0, MSG, MSG
+	vpand STATE2, STATE3, T0
+	vpxor T0, MSG, MSG
+	vmovdqu MSG, (%rdx)
+
+	call __morus1280_update
+	sub $32, %rcx
+	add $32, %rsi
+	add $32, %rdx
+	cmp $32, %rcx
+	jge .Ldec_u_loop
+
+.Ldec_cont:
+	/* store the state: */
+	vmovdqu STATE0, (0 * 32)(%rdi)
+	vmovdqu STATE1, (1 * 32)(%rdi)
+	vmovdqu STATE2, (2 * 32)(%rdi)
+	vmovdqu STATE3, (3 * 32)(%rdi)
+	vmovdqu STATE4, (4 * 32)(%rdi)
+
+.Ldec_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_avx2_dec)
+
+/*
+ * void crypto_morus1280_avx2_dec_tail(void *state, const void *src, void *dst,
+ *                                     unsigned int length);
+ */
+ENTRY(crypto_morus1280_avx2_dec_tail)
+	FRAME_BEGIN
+
+	/* load the state: */
+	vmovdqu (0 * 32)(%rdi), STATE0
+	vmovdqu (1 * 32)(%rdi), STATE1
+	vmovdqu (2 * 32)(%rdi), STATE2
+	vmovdqu (3 * 32)(%rdi), STATE3
+	vmovdqu (4 * 32)(%rdi), STATE4
+
+	/* decrypt message: */
+	call __load_partial
+
+	vpxor STATE0, MSG, MSG
+	vpermq $MASK3, STATE1, T0
+	vpxor T0, MSG, MSG
+	vpand STATE2, STATE3, T0
+	vpxor T0, MSG, MSG
+	vmovdqa MSG, T0
+
+	call __store_partial
+
+	/* mask with byte count: */
+	movq %rcx, T0_LOW
+	vpbroadcastb T0_LOW, T0
+	vmovdqa .Lmorus1280_counter, T1
+	vpcmpgtb T1, T0, T0
+	vpand T0, MSG, MSG
+
+	call __morus1280_update
+
+	/* store the state: */
+	vmovdqu STATE0, (0 * 32)(%rdi)
+	vmovdqu STATE1, (1 * 32)(%rdi)
+	vmovdqu STATE2, (2 * 32)(%rdi)
+	vmovdqu STATE3, (3 * 32)(%rdi)
+	vmovdqu STATE4, (4 * 32)(%rdi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_avx2_dec_tail)
+
+/*
+ * void crypto_morus1280_avx2_final(void *state, void *tag_xor,
+ *                                  u64 assoclen, u64 cryptlen);
+ */
+ENTRY(crypto_morus1280_avx2_final)
+	FRAME_BEGIN
+
+	/* load the state: */
+	vmovdqu (0 * 32)(%rdi), STATE0
+	vmovdqu (1 * 32)(%rdi), STATE1
+	vmovdqu (2 * 32)(%rdi), STATE2
+	vmovdqu (3 * 32)(%rdi), STATE3
+	vmovdqu (4 * 32)(%rdi), STATE4
+
+	/* xor state[0] into state[4]: */
+	vpxor STATE0, STATE4, STATE4
+
+	/* prepare length block: */
+	vpxor MSG, MSG, MSG
+	vpinsrq $0, %rdx, MSG_LOW, MSG_LOW
+	vpinsrq $1, %rcx, MSG_LOW, MSG_LOW
+	vpsllq $3, MSG, MSG /* multiply by 8 (to get bit count) */
+
+	/* update state: */
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+
+	/* xor tag: */
+	vmovdqu (%rsi), MSG
+
+	vpxor STATE0, MSG, MSG
+	vpermq $MASK3, STATE1, T0
+	vpxor T0, MSG, MSG
+	vpand STATE2, STATE3, T0
+	vpxor T0, MSG, MSG
+	vmovdqu MSG, (%rsi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_avx2_final)
diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c
new file mode 100644
index 000000000000..f111f36d26dc
--- /dev/null
+++ b/arch/x86/crypto/morus1280-avx2-glue.c
@@ -0,0 +1,68 @@
+/*
+ * The MORUS-1280 Authenticated-Encryption Algorithm
+ *   Glue for AVX2 implementation
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/internal/aead.h>
+#include <crypto/morus1280_glue.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/cpu_device_id.h>
+
+asmlinkage void crypto_morus1280_avx2_init(void *state, const void *key,
+					   const void *iv);
+asmlinkage void crypto_morus1280_avx2_ad(void *state, const void *data,
+					 unsigned int length);
+
+asmlinkage void crypto_morus1280_avx2_enc(void *state, const void *src,
+					  void *dst, unsigned int length);
+asmlinkage void crypto_morus1280_avx2_dec(void *state, const void *src,
+					  void *dst, unsigned int length);
+
+asmlinkage void crypto_morus1280_avx2_enc_tail(void *state, const void *src,
+					       void *dst, unsigned int length);
+asmlinkage void crypto_morus1280_avx2_dec_tail(void *state, const void *src,
+					       void *dst, unsigned int length);
+
+asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor,
+					    u64 assoclen, u64 cryptlen);
+
+MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400);
+
+static const struct x86_cpu_id avx2_cpu_id[] = {
+    X86_FEATURE_MATCH(X86_FEATURE_AVX2),
+    {}
+};
+MODULE_DEVICE_TABLE(x86cpu, avx2_cpu_id);
+
+static int __init crypto_morus1280_avx2_module_init(void)
+{
+	if (!x86_match_cpu(avx2_cpu_id))
+		return -ENODEV;
+
+	return crypto_register_aeads(crypto_morus1280_avx2_algs,
+				     ARRAY_SIZE(crypto_morus1280_avx2_algs));
+}
+
+static void __exit crypto_morus1280_avx2_module_exit(void)
+{
+	crypto_unregister_aeads(crypto_morus1280_avx2_algs,
+				ARRAY_SIZE(crypto_morus1280_avx2_algs));
+}
+
+module_init(crypto_morus1280_avx2_module_init);
+module_exit(crypto_morus1280_avx2_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("MORUS-1280 AEAD algorithm -- AVX2 implementation");
+MODULE_ALIAS_CRYPTO("morus1280");
+MODULE_ALIAS_CRYPTO("morus1280-avx2");
diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S
new file mode 100644
index 000000000000..1fe637c7be9d
--- /dev/null
+++ b/arch/x86/crypto/morus1280-sse2-asm.S
@@ -0,0 +1,895 @@
+/*
+ * SSE2 implementation of MORUS-1280
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+#define SHUFFLE_MASK(i0, i1, i2, i3) \
+	(i0 | (i1 << 2) | (i2 << 4) | (i3 << 6))
+
+#define MASK2 SHUFFLE_MASK(2, 3, 0, 1)
+
+#define STATE0_LO	%xmm0
+#define STATE0_HI	%xmm1
+#define STATE1_LO	%xmm2
+#define STATE1_HI	%xmm3
+#define STATE2_LO	%xmm4
+#define STATE2_HI	%xmm5
+#define STATE3_LO	%xmm6
+#define STATE3_HI	%xmm7
+#define STATE4_LO	%xmm8
+#define STATE4_HI	%xmm9
+#define KEY_LO		%xmm10
+#define KEY_HI		%xmm11
+#define MSG_LO		%xmm10
+#define MSG_HI		%xmm11
+#define T0_LO		%xmm12
+#define T0_HI		%xmm13
+#define T1_LO		%xmm14
+#define T1_HI		%xmm15
+
+.section .rodata.cst16.morus640_const, "aM", @progbits, 16
+.align 16
+.Lmorus640_const_0:
+	.byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d
+	.byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62
+.Lmorus640_const_1:
+	.byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1
+	.byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd
+
+.section .rodata.cst16.morus640_counter, "aM", @progbits, 16
+.align 16
+.Lmorus640_counter_0:
+	.byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+.Lmorus640_counter_1:
+	.byte 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17
+	.byte 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f
+
+.text
+
+.macro rol1 hi, lo
+	/*
+	 * HI_1 | HI_0 || LO_1 | LO_0
+	 *  ==>
+	 * HI_0 | HI_1 || LO_1 | LO_0
+	 *  ==>
+	 * HI_0 | LO_1 || LO_0 | HI_1
+	 */
+	pshufd $MASK2, \hi, \hi
+	movdqa \hi, T0_LO
+	punpcklqdq \lo, T0_LO
+	punpckhqdq \hi, \lo
+	movdqa \lo, \hi
+	movdqa T0_LO, \lo
+.endm
+
+.macro rol2 hi, lo
+	movdqa \lo, T0_LO
+	movdqa \hi, \lo
+	movdqa T0_LO, \hi
+.endm
+
+.macro rol3 hi, lo
+	/*
+	 * HI_1 | HI_0 || LO_1 | LO_0
+	 *  ==>
+	 * HI_0 | HI_1 || LO_1 | LO_0
+	 *  ==>
+	 * LO_0 | HI_1 || HI_0 | LO_1
+	 */
+	pshufd $MASK2, \hi, \hi
+	movdqa \lo, T0_LO
+	punpckhqdq \hi, T0_LO
+	punpcklqdq \lo, \hi
+	movdqa T0_LO, \lo
+.endm
+
+.macro morus1280_round s0_l, s0_h, s1_l, s1_h, s2_l, s2_h, s3_l, s3_h, s4_l, s4_h, b, w
+	movdqa \s1_l, T0_LO
+	pand \s2_l, T0_LO
+	pxor T0_LO, \s0_l
+
+	movdqa \s1_h, T0_LO
+	pand \s2_h, T0_LO
+	pxor T0_LO, \s0_h
+
+	pxor \s3_l, \s0_l
+	pxor \s3_h, \s0_h
+
+	movdqa \s0_l, T0_LO
+	psllq $\b, T0_LO
+	psrlq $(64 - \b), \s0_l
+	pxor T0_LO, \s0_l
+
+	movdqa \s0_h, T0_LO
+	psllq $\b, T0_LO
+	psrlq $(64 - \b), \s0_h
+	pxor T0_LO, \s0_h
+
+	\w \s3_h, \s3_l
+.endm
+
+/*
+ * __morus1280_update: internal ABI
+ * input:
+ *   STATE[0-4] - input state
+ *   MSG        - message block
+ * output:
+ *   STATE[0-4] - output state
+ * changed:
+ *   T0
+ */
+__morus1280_update:
+	morus1280_round \
+		STATE0_LO, STATE0_HI, \
+		STATE1_LO, STATE1_HI, \
+		STATE2_LO, STATE2_HI, \
+		STATE3_LO, STATE3_HI, \
+		STATE4_LO, STATE4_HI, \
+		13, rol1
+	pxor MSG_LO, STATE1_LO
+	pxor MSG_HI, STATE1_HI
+	morus1280_round \
+		STATE1_LO, STATE1_HI, \
+		STATE2_LO, STATE2_HI, \
+		STATE3_LO, STATE3_HI, \
+		STATE4_LO, STATE4_HI, \
+		STATE0_LO, STATE0_HI, \
+		46, rol2
+	pxor MSG_LO, STATE2_LO
+	pxor MSG_HI, STATE2_HI
+	morus1280_round \
+		STATE2_LO, STATE2_HI, \
+		STATE3_LO, STATE3_HI, \
+		STATE4_LO, STATE4_HI, \
+		STATE0_LO, STATE0_HI, \
+		STATE1_LO, STATE1_HI, \
+		38, rol3
+	pxor MSG_LO, STATE3_LO
+	pxor MSG_HI, STATE3_HI
+	morus1280_round \
+		STATE3_LO, STATE3_HI, \
+		STATE4_LO, STATE4_HI, \
+		STATE0_LO, STATE0_HI, \
+		STATE1_LO, STATE1_HI, \
+		STATE2_LO, STATE2_HI, \
+		7, rol2
+	pxor MSG_LO, STATE4_LO
+	pxor MSG_HI, STATE4_HI
+	morus1280_round \
+		STATE4_LO, STATE4_HI, \
+		STATE0_LO, STATE0_HI, \
+		STATE1_LO, STATE1_HI, \
+		STATE2_LO, STATE2_HI, \
+		STATE3_LO, STATE3_HI, \
+		4, rol1
+	ret
+ENDPROC(__morus1280_update)
+
+/*
+ * __morus1280_update_zero: internal ABI
+ * input:
+ *   STATE[0-4] - input state
+ * output:
+ *   STATE[0-4] - output state
+ * changed:
+ *   T0
+ */
+__morus1280_update_zero:
+	morus1280_round \
+		STATE0_LO, STATE0_HI, \
+		STATE1_LO, STATE1_HI, \
+		STATE2_LO, STATE2_HI, \
+		STATE3_LO, STATE3_HI, \
+		STATE4_LO, STATE4_HI, \
+		13, rol1
+	morus1280_round \
+		STATE1_LO, STATE1_HI, \
+		STATE2_LO, STATE2_HI, \
+		STATE3_LO, STATE3_HI, \
+		STATE4_LO, STATE4_HI, \
+		STATE0_LO, STATE0_HI, \
+		46, rol2
+	morus1280_round \
+		STATE2_LO, STATE2_HI, \
+		STATE3_LO, STATE3_HI, \
+		STATE4_LO, STATE4_HI, \
+		STATE0_LO, STATE0_HI, \
+		STATE1_LO, STATE1_HI, \
+		38, rol3
+	morus1280_round \
+		STATE3_LO, STATE3_HI, \
+		STATE4_LO, STATE4_HI, \
+		STATE0_LO, STATE0_HI, \
+		STATE1_LO, STATE1_HI, \
+		STATE2_LO, STATE2_HI, \
+		7, rol2
+	morus1280_round \
+		STATE4_LO, STATE4_HI, \
+		STATE0_LO, STATE0_HI, \
+		STATE1_LO, STATE1_HI, \
+		STATE2_LO, STATE2_HI, \
+		STATE3_LO, STATE3_HI, \
+		4, rol1
+	ret
+ENDPROC(__morus1280_update_zero)
+
+/*
+ * __load_partial: internal ABI
+ * input:
+ *   %rsi - src
+ *   %rcx - bytes
+ * output:
+ *   MSG  - message block
+ * changed:
+ *   %r8
+ *   %r9
+ */
+__load_partial:
+	xor %r9, %r9
+	pxor MSG_LO, MSG_LO
+	pxor MSG_HI, MSG_HI
+
+	mov %rcx, %r8
+	and $0x1, %r8
+	jz .Lld_partial_1
+
+	mov %rcx, %r8
+	and $0x1E, %r8
+	add %rsi, %r8
+	mov (%r8), %r9b
+
+.Lld_partial_1:
+	mov %rcx, %r8
+	and $0x2, %r8
+	jz .Lld_partial_2
+
+	mov %rcx, %r8
+	and $0x1C, %r8
+	add %rsi, %r8
+	shl $16, %r9
+	mov (%r8), %r9w
+
+.Lld_partial_2:
+	mov %rcx, %r8
+	and $0x4, %r8
+	jz .Lld_partial_4
+
+	mov %rcx, %r8
+	and $0x18, %r8
+	add %rsi, %r8
+	shl $32, %r9
+	mov (%r8), %r8d
+	xor %r8, %r9
+
+.Lld_partial_4:
+	movq %r9, MSG_LO
+
+	mov %rcx, %r8
+	and $0x8, %r8
+	jz .Lld_partial_8
+
+	mov %rcx, %r8
+	and $0x10, %r8
+	add %rsi, %r8
+	pslldq $8, MSG_LO
+	movq (%r8), T0_LO
+	pxor T0_LO, MSG_LO
+
+.Lld_partial_8:
+	mov %rcx, %r8
+	and $0x10, %r8
+	jz .Lld_partial_16
+
+	movdqa MSG_LO, MSG_HI
+	movdqu (%rsi), MSG_LO
+
+.Lld_partial_16:
+	ret
+ENDPROC(__load_partial)
+
+/*
+ * __store_partial: internal ABI
+ * input:
+ *   %rdx - dst
+ *   %rcx - bytes
+ * output:
+ *   T0   - message block
+ * changed:
+ *   %r8
+ *   %r9
+ *   %r10
+ */
+__store_partial:
+	mov %rcx, %r8
+	mov %rdx, %r9
+
+	cmp $16, %r8
+	jl .Lst_partial_16
+
+	movdqu T0_LO, (%r9)
+	movdqa T0_HI, T0_LO
+
+	sub $16, %r8
+	add $16, %r9
+
+.Lst_partial_16:
+	movq T0_LO, %r10
+
+	cmp $8, %r8
+	jl .Lst_partial_8
+
+	mov %r10, (%r9)
+	psrldq $8, T0_LO
+	movq T0_LO, %r10
+
+	sub $8, %r8
+	add $8, %r9
+
+.Lst_partial_8:
+	cmp $4, %r8
+	jl .Lst_partial_4
+
+	mov %r10d, (%r9)
+	shr $32, %r10
+
+	sub $4, %r8
+	add $4, %r9
+
+.Lst_partial_4:
+	cmp $2, %r8
+	jl .Lst_partial_2
+
+	mov %r10w, (%r9)
+	shr $16, %r10
+
+	sub $2, %r8
+	add $2, %r9
+
+.Lst_partial_2:
+	cmp $1, %r8
+	jl .Lst_partial_1
+
+	mov %r10b, (%r9)
+
+.Lst_partial_1:
+	ret
+ENDPROC(__store_partial)
+
+/*
+ * void crypto_morus1280_sse2_init(void *state, const void *key,
+ *                                 const void *iv);
+ */
+ENTRY(crypto_morus1280_sse2_init)
+	FRAME_BEGIN
+
+	/* load IV: */
+	pxor STATE0_HI, STATE0_HI
+	movdqu (%rdx), STATE0_LO
+	/* load key: */
+	movdqu  0(%rsi), KEY_LO
+	movdqu 16(%rsi), KEY_HI
+	movdqa KEY_LO, STATE1_LO
+	movdqa KEY_HI, STATE1_HI
+	/* load all ones: */
+	pcmpeqd STATE2_LO, STATE2_LO
+	pcmpeqd STATE2_HI, STATE2_HI
+	/* load all zeros: */
+	pxor STATE3_LO, STATE3_LO
+	pxor STATE3_HI, STATE3_HI
+	/* load the constant: */
+	movdqa .Lmorus640_const_0, STATE4_LO
+	movdqa .Lmorus640_const_1, STATE4_HI
+
+	/* update 16 times with zero: */
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+	call __morus1280_update_zero
+
+	/* xor-in the key again after updates: */
+	pxor KEY_LO, STATE1_LO
+	pxor KEY_HI, STATE1_HI
+
+	/* store the state: */
+	movdqu STATE0_LO, (0 * 16)(%rdi)
+	movdqu STATE0_HI, (1 * 16)(%rdi)
+	movdqu STATE1_LO, (2 * 16)(%rdi)
+	movdqu STATE1_HI, (3 * 16)(%rdi)
+	movdqu STATE2_LO, (4 * 16)(%rdi)
+	movdqu STATE2_HI, (5 * 16)(%rdi)
+	movdqu STATE3_LO, (6 * 16)(%rdi)
+	movdqu STATE3_HI, (7 * 16)(%rdi)
+	movdqu STATE4_LO, (8 * 16)(%rdi)
+	movdqu STATE4_HI, (9 * 16)(%rdi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_sse2_init)
+
+/*
+ * void crypto_morus1280_sse2_ad(void *state, const void *data,
+ *                               unsigned int length);
+ */
+ENTRY(crypto_morus1280_sse2_ad)
+	FRAME_BEGIN
+
+	cmp $32, %rdx
+	jb .Lad_out
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0_LO
+	movdqu (1 * 16)(%rdi), STATE0_HI
+	movdqu (2 * 16)(%rdi), STATE1_LO
+	movdqu (3 * 16)(%rdi), STATE1_HI
+	movdqu (4 * 16)(%rdi), STATE2_LO
+	movdqu (5 * 16)(%rdi), STATE2_HI
+	movdqu (6 * 16)(%rdi), STATE3_LO
+	movdqu (7 * 16)(%rdi), STATE3_HI
+	movdqu (8 * 16)(%rdi), STATE4_LO
+	movdqu (9 * 16)(%rdi), STATE4_HI
+
+	mov %rsi, %r8
+	and $0xF, %r8
+	jnz .Lad_u_loop
+
+.align 4
+.Lad_a_loop:
+	movdqa  0(%rsi), MSG_LO
+	movdqa 16(%rsi), MSG_HI
+	call __morus1280_update
+	sub $32, %rdx
+	add $32, %rsi
+	cmp $32, %rdx
+	jge .Lad_a_loop
+
+	jmp .Lad_cont
+.align 4
+.Lad_u_loop:
+	movdqu  0(%rsi), MSG_LO
+	movdqu 16(%rsi), MSG_HI
+	call __morus1280_update
+	sub $32, %rdx
+	add $32, %rsi
+	cmp $32, %rdx
+	jge .Lad_u_loop
+
+.Lad_cont:
+	/* store the state: */
+	movdqu STATE0_LO, (0 * 16)(%rdi)
+	movdqu STATE0_HI, (1 * 16)(%rdi)
+	movdqu STATE1_LO, (2 * 16)(%rdi)
+	movdqu STATE1_HI, (3 * 16)(%rdi)
+	movdqu STATE2_LO, (4 * 16)(%rdi)
+	movdqu STATE2_HI, (5 * 16)(%rdi)
+	movdqu STATE3_LO, (6 * 16)(%rdi)
+	movdqu STATE3_HI, (7 * 16)(%rdi)
+	movdqu STATE4_LO, (8 * 16)(%rdi)
+	movdqu STATE4_HI, (9 * 16)(%rdi)
+
+.Lad_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_sse2_ad)
+
+/*
+ * void crypto_morus1280_sse2_enc(void *state, const void *src, void *dst,
+ *                                unsigned int length);
+ */
+ENTRY(crypto_morus1280_sse2_enc)
+	FRAME_BEGIN
+
+	cmp $32, %rcx
+	jb .Lenc_out
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0_LO
+	movdqu (1 * 16)(%rdi), STATE0_HI
+	movdqu (2 * 16)(%rdi), STATE1_LO
+	movdqu (3 * 16)(%rdi), STATE1_HI
+	movdqu (4 * 16)(%rdi), STATE2_LO
+	movdqu (5 * 16)(%rdi), STATE2_HI
+	movdqu (6 * 16)(%rdi), STATE3_LO
+	movdqu (7 * 16)(%rdi), STATE3_HI
+	movdqu (8 * 16)(%rdi), STATE4_LO
+	movdqu (9 * 16)(%rdi), STATE4_HI
+
+	mov %rsi, %r8
+	or  %rdx, %r8
+	and $0xF, %r8
+	jnz .Lenc_u_loop
+
+.align 4
+.Lenc_a_loop:
+	movdqa  0(%rsi), MSG_LO
+	movdqa 16(%rsi), MSG_HI
+	movdqa STATE1_LO, T1_LO
+	movdqa STATE1_HI, T1_HI
+	rol3 T1_HI, T1_LO
+	movdqa MSG_LO, T0_LO
+	movdqa MSG_HI, T0_HI
+	pxor T1_LO, T0_LO
+	pxor T1_HI, T0_HI
+	pxor STATE0_LO, T0_LO
+	pxor STATE0_HI, T0_HI
+	movdqa STATE2_LO, T1_LO
+	movdqa STATE2_HI, T1_HI
+	pand STATE3_LO, T1_LO
+	pand STATE3_HI, T1_HI
+	pxor T1_LO, T0_LO
+	pxor T1_HI, T0_HI
+	movdqa T0_LO,  0(%rdx)
+	movdqa T0_HI, 16(%rdx)
+
+	call __morus1280_update
+	sub $32, %rcx
+	add $32, %rsi
+	add $32, %rdx
+	cmp $32, %rcx
+	jge .Lenc_a_loop
+
+	jmp .Lenc_cont
+.align 4
+.Lenc_u_loop:
+	movdqu  0(%rsi), MSG_LO
+	movdqu 16(%rsi), MSG_HI
+	movdqa STATE1_LO, T1_LO
+	movdqa STATE1_HI, T1_HI
+	rol3 T1_HI, T1_LO
+	movdqa MSG_LO, T0_LO
+	movdqa MSG_HI, T0_HI
+	pxor T1_LO, T0_LO
+	pxor T1_HI, T0_HI
+	pxor STATE0_LO, T0_LO
+	pxor STATE0_HI, T0_HI
+	movdqa STATE2_LO, T1_LO
+	movdqa STATE2_HI, T1_HI
+	pand STATE3_LO, T1_LO
+	pand STATE3_HI, T1_HI
+	pxor T1_LO, T0_LO
+	pxor T1_HI, T0_HI
+	movdqu T0_LO,  0(%rdx)
+	movdqu T0_HI, 16(%rdx)
+
+	call __morus1280_update
+	sub $32, %rcx
+	add $32, %rsi
+	add $32, %rdx
+	cmp $32, %rcx
+	jge .Lenc_u_loop
+
+.Lenc_cont:
+	/* store the state: */
+	movdqu STATE0_LO, (0 * 16)(%rdi)
+	movdqu STATE0_HI, (1 * 16)(%rdi)
+	movdqu STATE1_LO, (2 * 16)(%rdi)
+	movdqu STATE1_HI, (3 * 16)(%rdi)
+	movdqu STATE2_LO, (4 * 16)(%rdi)
+	movdqu STATE2_HI, (5 * 16)(%rdi)
+	movdqu STATE3_LO, (6 * 16)(%rdi)
+	movdqu STATE3_HI, (7 * 16)(%rdi)
+	movdqu STATE4_LO, (8 * 16)(%rdi)
+	movdqu STATE4_HI, (9 * 16)(%rdi)
+
+.Lenc_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_sse2_enc)
+
+/*
+ * void crypto_morus1280_sse2_enc_tail(void *state, const void *src, void *dst,
+ *                                     unsigned int length);
+ */
+ENTRY(crypto_morus1280_sse2_enc_tail)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0_LO
+	movdqu (1 * 16)(%rdi), STATE0_HI
+	movdqu (2 * 16)(%rdi), STATE1_LO
+	movdqu (3 * 16)(%rdi), STATE1_HI
+	movdqu (4 * 16)(%rdi), STATE2_LO
+	movdqu (5 * 16)(%rdi), STATE2_HI
+	movdqu (6 * 16)(%rdi), STATE3_LO
+	movdqu (7 * 16)(%rdi), STATE3_HI
+	movdqu (8 * 16)(%rdi), STATE4_LO
+	movdqu (9 * 16)(%rdi), STATE4_HI
+
+	/* encrypt message: */
+	call __load_partial
+
+	movdqa STATE1_LO, T1_LO
+	movdqa STATE1_HI, T1_HI
+	rol3 T1_HI, T1_LO
+	movdqa MSG_LO, T0_LO
+	movdqa MSG_HI, T0_HI
+	pxor T1_LO, T0_LO
+	pxor T1_HI, T0_HI
+	pxor STATE0_LO, T0_LO
+	pxor STATE0_HI, T0_HI
+	movdqa STATE2_LO, T1_LO
+	movdqa STATE2_HI, T1_HI
+	pand STATE3_LO, T1_LO
+	pand STATE3_HI, T1_HI
+	pxor T1_LO, T0_LO
+	pxor T1_HI, T0_HI
+
+	call __store_partial
+
+	call __morus1280_update
+
+	/* store the state: */
+	movdqu STATE0_LO, (0 * 16)(%rdi)
+	movdqu STATE0_HI, (1 * 16)(%rdi)
+	movdqu STATE1_LO, (2 * 16)(%rdi)
+	movdqu STATE1_HI, (3 * 16)(%rdi)
+	movdqu STATE2_LO, (4 * 16)(%rdi)
+	movdqu STATE2_HI, (5 * 16)(%rdi)
+	movdqu STATE3_LO, (6 * 16)(%rdi)
+	movdqu STATE3_HI, (7 * 16)(%rdi)
+	movdqu STATE4_LO, (8 * 16)(%rdi)
+	movdqu STATE4_HI, (9 * 16)(%rdi)
+
+	FRAME_END
+ENDPROC(crypto_morus1280_sse2_enc_tail)
+
+/*
+ * void crypto_morus1280_sse2_dec(void *state, const void *src, void *dst,
+ *                                unsigned int length);
+ */
+ENTRY(crypto_morus1280_sse2_dec)
+	FRAME_BEGIN
+
+	cmp $32, %rcx
+	jb .Ldec_out
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0_LO
+	movdqu (1 * 16)(%rdi), STATE0_HI
+	movdqu (2 * 16)(%rdi), STATE1_LO
+	movdqu (3 * 16)(%rdi), STATE1_HI
+	movdqu (4 * 16)(%rdi), STATE2_LO
+	movdqu (5 * 16)(%rdi), STATE2_HI
+	movdqu (6 * 16)(%rdi), STATE3_LO
+	movdqu (7 * 16)(%rdi), STATE3_HI
+	movdqu (8 * 16)(%rdi), STATE4_LO
+	movdqu (9 * 16)(%rdi), STATE4_HI
+
+	mov %rsi, %r8
+	or  %rdx, %r8
+	and $0xF, %r8
+	jnz .Ldec_u_loop
+
+.align 4
+.Ldec_a_loop:
+	movdqa  0(%rsi), MSG_LO
+	movdqa 16(%rsi), MSG_HI
+	pxor STATE0_LO, MSG_LO
+	pxor STATE0_HI, MSG_HI
+	movdqa STATE1_LO, T1_LO
+	movdqa STATE1_HI, T1_HI
+	rol3 T1_HI, T1_LO
+	pxor T1_LO, MSG_LO
+	pxor T1_HI, MSG_HI
+	movdqa STATE2_LO, T1_LO
+	movdqa STATE2_HI, T1_HI
+	pand STATE3_LO, T1_LO
+	pand STATE3_HI, T1_HI
+	pxor T1_LO, MSG_LO
+	pxor T1_HI, MSG_HI
+	movdqa MSG_LO,  0(%rdx)
+	movdqa MSG_HI, 16(%rdx)
+
+	call __morus1280_update
+	sub $32, %rcx
+	add $32, %rsi
+	add $32, %rdx
+	cmp $32, %rcx
+	jge .Ldec_a_loop
+
+	jmp .Ldec_cont
+.align 4
+.Ldec_u_loop:
+	movdqu  0(%rsi), MSG_LO
+	movdqu 16(%rsi), MSG_HI
+	pxor STATE0_LO, MSG_LO
+	pxor STATE0_HI, MSG_HI
+	movdqa STATE1_LO, T1_LO
+	movdqa STATE1_HI, T1_HI
+	rol3 T1_HI, T1_LO
+	pxor T1_LO, MSG_LO
+	pxor T1_HI, MSG_HI
+	movdqa STATE2_LO, T1_LO
+	movdqa STATE2_HI, T1_HI
+	pand STATE3_LO, T1_LO
+	pand STATE3_HI, T1_HI
+	pxor T1_LO, MSG_LO
+	pxor T1_HI, MSG_HI
+	movdqu MSG_LO,  0(%rdx)
+	movdqu MSG_HI, 16(%rdx)
+
+	call __morus1280_update
+	sub $32, %rcx
+	add $32, %rsi
+	add $32, %rdx
+	cmp $32, %rcx
+	jge .Ldec_u_loop
+
+.Ldec_cont:
+	/* store the state: */
+	movdqu STATE0_LO, (0 * 16)(%rdi)
+	movdqu STATE0_HI, (1 * 16)(%rdi)
+	movdqu STATE1_LO, (2 * 16)(%rdi)
+	movdqu STATE1_HI, (3 * 16)(%rdi)
+	movdqu STATE2_LO, (4 * 16)(%rdi)
+	movdqu STATE2_HI, (5 * 16)(%rdi)
+	movdqu STATE3_LO, (6 * 16)(%rdi)
+	movdqu STATE3_HI, (7 * 16)(%rdi)
+	movdqu STATE4_LO, (8 * 16)(%rdi)
+	movdqu STATE4_HI, (9 * 16)(%rdi)
+
+.Ldec_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_sse2_dec)
+
+/*
+ * void crypto_morus1280_sse2_dec_tail(void *state, const void *src, void *dst,
+ *                                     unsigned int length);
+ */
+ENTRY(crypto_morus1280_sse2_dec_tail)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0_LO
+	movdqu (1 * 16)(%rdi), STATE0_HI
+	movdqu (2 * 16)(%rdi), STATE1_LO
+	movdqu (3 * 16)(%rdi), STATE1_HI
+	movdqu (4 * 16)(%rdi), STATE2_LO
+	movdqu (5 * 16)(%rdi), STATE2_HI
+	movdqu (6 * 16)(%rdi), STATE3_LO
+	movdqu (7 * 16)(%rdi), STATE3_HI
+	movdqu (8 * 16)(%rdi), STATE4_LO
+	movdqu (9 * 16)(%rdi), STATE4_HI
+
+	/* decrypt message: */
+	call __load_partial
+
+	pxor STATE0_LO, MSG_LO
+	pxor STATE0_HI, MSG_HI
+	movdqa STATE1_LO, T1_LO
+	movdqa STATE1_HI, T1_HI
+	rol3 T1_HI, T1_LO
+	pxor T1_LO, MSG_LO
+	pxor T1_HI, MSG_HI
+	movdqa STATE2_LO, T1_LO
+	movdqa STATE2_HI, T1_HI
+	pand STATE3_LO, T1_LO
+	pand STATE3_HI, T1_HI
+	pxor T1_LO, MSG_LO
+	pxor T1_HI, MSG_HI
+	movdqa MSG_LO, T0_LO
+	movdqa MSG_HI, T0_HI
+
+	call __store_partial
+
+	/* mask with byte count: */
+	movq %rcx, T0_LO
+	punpcklbw T0_LO, T0_LO
+	punpcklbw T0_LO, T0_LO
+	punpcklbw T0_LO, T0_LO
+	punpcklbw T0_LO, T0_LO
+	movdqa T0_LO, T0_HI
+	movdqa .Lmorus640_counter_0, T1_LO
+	movdqa .Lmorus640_counter_1, T1_HI
+	pcmpgtb T1_LO, T0_LO
+	pcmpgtb T1_HI, T0_HI
+	pand T0_LO, MSG_LO
+	pand T0_HI, MSG_HI
+
+	call __morus1280_update
+
+	/* store the state: */
+	movdqu STATE0_LO, (0 * 16)(%rdi)
+	movdqu STATE0_HI, (1 * 16)(%rdi)
+	movdqu STATE1_LO, (2 * 16)(%rdi)
+	movdqu STATE1_HI, (3 * 16)(%rdi)
+	movdqu STATE2_LO, (4 * 16)(%rdi)
+	movdqu STATE2_HI, (5 * 16)(%rdi)
+	movdqu STATE3_LO, (6 * 16)(%rdi)
+	movdqu STATE3_HI, (7 * 16)(%rdi)
+	movdqu STATE4_LO, (8 * 16)(%rdi)
+	movdqu STATE4_HI, (9 * 16)(%rdi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_sse2_dec_tail)
+
+/*
+ * void crypto_morus1280_sse2_final(void *state, void *tag_xor,
+ *                                  u64 assoclen, u64 cryptlen);
+ */
+ENTRY(crypto_morus1280_sse2_final)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0_LO
+	movdqu (1 * 16)(%rdi), STATE0_HI
+	movdqu (2 * 16)(%rdi), STATE1_LO
+	movdqu (3 * 16)(%rdi), STATE1_HI
+	movdqu (4 * 16)(%rdi), STATE2_LO
+	movdqu (5 * 16)(%rdi), STATE2_HI
+	movdqu (6 * 16)(%rdi), STATE3_LO
+	movdqu (7 * 16)(%rdi), STATE3_HI
+	movdqu (8 * 16)(%rdi), STATE4_LO
+	movdqu (9 * 16)(%rdi), STATE4_HI
+
+	/* xor state[0] into state[4]: */
+	pxor STATE0_LO, STATE4_LO
+	pxor STATE0_HI, STATE4_HI
+
+	/* prepare length block: */
+	movq %rdx, MSG_LO
+	movq %rcx, T0_LO
+	pslldq $8, T0_LO
+	pxor T0_LO, MSG_LO
+	psllq $3, MSG_LO /* multiply by 8 (to get bit count) */
+	pxor MSG_HI, MSG_HI
+
+	/* update state: */
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+	call __morus1280_update
+
+	/* xor tag: */
+	movdqu  0(%rsi), MSG_LO
+	movdqu 16(%rsi), MSG_HI
+
+	pxor STATE0_LO, MSG_LO
+	pxor STATE0_HI, MSG_HI
+	movdqa STATE1_LO, T0_LO
+	movdqa STATE1_HI, T0_HI
+	rol3 T0_HI, T0_LO
+	pxor T0_LO, MSG_LO
+	pxor T0_HI, MSG_HI
+	movdqa STATE2_LO, T0_LO
+	movdqa STATE2_HI, T0_HI
+	pand STATE3_LO, T0_LO
+	pand STATE3_HI, T0_HI
+	pxor T0_LO, MSG_LO
+	pxor T0_HI, MSG_HI
+
+	movdqu MSG_LO,  0(%rsi)
+	movdqu MSG_HI, 16(%rsi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus1280_sse2_final)
diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c
new file mode 100644
index 000000000000..839270aa713c
--- /dev/null
+++ b/arch/x86/crypto/morus1280-sse2-glue.c
@@ -0,0 +1,68 @@
+/*
+ * The MORUS-1280 Authenticated-Encryption Algorithm
+ *   Glue for SSE2 implementation
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/internal/aead.h>
+#include <crypto/morus1280_glue.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/cpu_device_id.h>
+
+asmlinkage void crypto_morus1280_sse2_init(void *state, const void *key,
+					   const void *iv);
+asmlinkage void crypto_morus1280_sse2_ad(void *state, const void *data,
+					 unsigned int length);
+
+asmlinkage void crypto_morus1280_sse2_enc(void *state, const void *src,
+					  void *dst, unsigned int length);
+asmlinkage void crypto_morus1280_sse2_dec(void *state, const void *src,
+					  void *dst, unsigned int length);
+
+asmlinkage void crypto_morus1280_sse2_enc_tail(void *state, const void *src,
+					       void *dst, unsigned int length);
+asmlinkage void crypto_morus1280_sse2_dec_tail(void *state, const void *src,
+					       void *dst, unsigned int length);
+
+asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor,
+					    u64 assoclen, u64 cryptlen);
+
+MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
+
+static const struct x86_cpu_id sse2_cpu_id[] = {
+    X86_FEATURE_MATCH(X86_FEATURE_XMM2),
+    {}
+};
+MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id);
+
+static int __init crypto_morus1280_sse2_module_init(void)
+{
+	if (!x86_match_cpu(sse2_cpu_id))
+		return -ENODEV;
+
+	return crypto_register_aeads(crypto_morus1280_sse2_algs,
+				     ARRAY_SIZE(crypto_morus1280_sse2_algs));
+}
+
+static void __exit crypto_morus1280_sse2_module_exit(void)
+{
+	crypto_unregister_aeads(crypto_morus1280_sse2_algs,
+				ARRAY_SIZE(crypto_morus1280_sse2_algs));
+}
+
+module_init(crypto_morus1280_sse2_module_init);
+module_exit(crypto_morus1280_sse2_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("MORUS-1280 AEAD algorithm -- SSE2 implementation");
+MODULE_ALIAS_CRYPTO("morus1280");
+MODULE_ALIAS_CRYPTO("morus1280-sse2");
diff --git a/arch/x86/crypto/morus1280_glue.c b/arch/x86/crypto/morus1280_glue.c
new file mode 100644
index 000000000000..0dccdda1eb3a
--- /dev/null
+++ b/arch/x86/crypto/morus1280_glue.c
@@ -0,0 +1,302 @@
+/*
+ * The MORUS-1280 Authenticated-Encryption Algorithm
+ *   Common x86 SIMD glue skeleton
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/cryptd.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/morus1280_glue.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <asm/fpu/api.h>
+
+struct morus1280_state {
+	struct morus1280_block s[MORUS_STATE_BLOCKS];
+};
+
+struct morus1280_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_blocks)(void *state, const void *src, void *dst,
+			     unsigned int length);
+	void (*crypt_tail)(void *state, const void *src, void *dst,
+			   unsigned int length);
+};
+
+static void crypto_morus1280_glue_process_ad(
+		struct morus1280_state *state,
+		const struct morus1280_glue_ops *ops,
+		struct scatterlist *sg_src, unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	struct morus1280_block buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= MORUS1280_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = MORUS1280_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+				ops->ad(state, buf.bytes, MORUS1280_BLOCK_SIZE);
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			ops->ad(state, src, left);
+			src += left & ~(MORUS1280_BLOCK_SIZE - 1);
+			left &= MORUS1280_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+
+		pos += left;
+		assoclen -= size;
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, MORUS1280_BLOCK_SIZE - pos);
+		ops->ad(state, buf.bytes, MORUS1280_BLOCK_SIZE);
+	}
+}
+
+static void crypto_morus1280_glue_process_crypt(struct morus1280_state *state,
+						struct morus1280_ops ops,
+						struct aead_request *req)
+{
+	struct skcipher_walk walk;
+	u8 *cursor_src, *cursor_dst;
+	unsigned int chunksize, base;
+
+	ops.skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		cursor_src = walk.src.virt.addr;
+		cursor_dst = walk.dst.virt.addr;
+		chunksize = walk.nbytes;
+
+		ops.crypt_blocks(state, cursor_src, cursor_dst, chunksize);
+
+		base = chunksize & ~(MORUS1280_BLOCK_SIZE - 1);
+		cursor_src += base;
+		cursor_dst += base;
+		chunksize &= MORUS1280_BLOCK_SIZE - 1;
+
+		if (chunksize > 0)
+			ops.crypt_tail(state, cursor_src, cursor_dst,
+				       chunksize);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+int crypto_morus1280_glue_setkey(struct crypto_aead *aead, const u8 *key,
+				 unsigned int keylen)
+{
+	struct morus1280_ctx *ctx = crypto_aead_ctx(aead);
+
+	if (keylen == MORUS1280_BLOCK_SIZE) {
+		memcpy(ctx->key.bytes, key, MORUS1280_BLOCK_SIZE);
+	} else if (keylen == MORUS1280_BLOCK_SIZE / 2) {
+		memcpy(ctx->key.bytes, key, keylen);
+		memcpy(ctx->key.bytes + keylen, key, keylen);
+	} else {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_morus1280_glue_setkey);
+
+int crypto_morus1280_glue_setauthsize(struct crypto_aead *tfm,
+				      unsigned int authsize)
+{
+	return (authsize <= MORUS_MAX_AUTH_SIZE) ? 0 : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(crypto_morus1280_glue_setauthsize);
+
+static void crypto_morus1280_glue_crypt(struct aead_request *req,
+					struct morus1280_ops ops,
+					unsigned int cryptlen,
+					struct morus1280_block *tag_xor)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus1280_ctx *ctx = crypto_aead_ctx(tfm);
+	struct morus1280_state state;
+
+	kernel_fpu_begin();
+
+	ctx->ops->init(&state, &ctx->key, req->iv);
+	crypto_morus1280_glue_process_ad(&state, ctx->ops, req->src, req->assoclen);
+	crypto_morus1280_glue_process_crypt(&state, ops, req);
+	ctx->ops->final(&state, tag_xor, req->assoclen, cryptlen);
+
+	kernel_fpu_end();
+}
+
+int crypto_morus1280_glue_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus1280_ctx *ctx = crypto_aead_ctx(tfm);
+	struct morus1280_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_blocks = ctx->ops->enc,
+		.crypt_tail = ctx->ops->enc_tail,
+	};
+
+	struct morus1280_block tag = {};
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_morus1280_glue_crypt(req, OPS, cryptlen, &tag);
+
+	scatterwalk_map_and_copy(tag.bytes, req->dst,
+				 req->assoclen + cryptlen, authsize, 1);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_morus1280_glue_encrypt);
+
+int crypto_morus1280_glue_decrypt(struct aead_request *req)
+{
+	static const u8 zeros[MORUS1280_BLOCK_SIZE] = {};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus1280_ctx *ctx = crypto_aead_ctx(tfm);
+	struct morus1280_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_blocks = ctx->ops->dec,
+		.crypt_tail = ctx->ops->dec_tail,
+	};
+
+	struct morus1280_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag.bytes, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
+
+	crypto_morus1280_glue_crypt(req, OPS, cryptlen, &tag);
+
+	return crypto_memneq(tag.bytes, zeros, authsize) ? -EBADMSG : 0;
+}
+EXPORT_SYMBOL_GPL(crypto_morus1280_glue_decrypt);
+
+void crypto_morus1280_glue_init_ops(struct crypto_aead *aead,
+				    const struct morus1280_glue_ops *ops)
+{
+	struct morus1280_ctx *ctx = crypto_aead_ctx(aead);
+	ctx->ops = ops;
+}
+EXPORT_SYMBOL_GPL(crypto_morus1280_glue_init_ops);
+
+int cryptd_morus1280_glue_setkey(struct crypto_aead *aead, const u8 *key,
+				 unsigned int keylen)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_setkey);
+
+int cryptd_morus1280_glue_setauthsize(struct crypto_aead *aead,
+				      unsigned int authsize)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_setauthsize);
+
+int cryptd_morus1280_glue_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_encrypt(req);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_encrypt);
+
+int cryptd_morus1280_glue_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_decrypt(req);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_decrypt);
+
+int cryptd_morus1280_glue_init_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead *cryptd_tfm;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	const char *name = crypto_aead_alg(aead)->base.cra_driver_name;
+	char internal_name[CRYPTO_MAX_ALG_NAME];
+
+	if (snprintf(internal_name, CRYPTO_MAX_ALG_NAME, "__%s", name)
+			>= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	cryptd_tfm = cryptd_alloc_aead(internal_name, CRYPTO_ALG_INTERNAL,
+				       CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	*ctx = cryptd_tfm;
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_init_tfm);
+
+void cryptd_morus1280_glue_exit_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_free_aead(*ctx);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_exit_tfm);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("MORUS-1280 AEAD mode -- glue for x86 optimizations");
diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S
new file mode 100644
index 000000000000..71c72a0a0862
--- /dev/null
+++ b/arch/x86/crypto/morus640-sse2-asm.S
@@ -0,0 +1,614 @@
+/*
+ * SSE2 implementation of MORUS-640
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+#define SHUFFLE_MASK(i0, i1, i2, i3) \
+	(i0 | (i1 << 2) | (i2 << 4) | (i3 << 6))
+
+#define MASK1 SHUFFLE_MASK(3, 0, 1, 2)
+#define MASK2 SHUFFLE_MASK(2, 3, 0, 1)
+#define MASK3 SHUFFLE_MASK(1, 2, 3, 0)
+
+#define STATE0	%xmm0
+#define STATE1	%xmm1
+#define STATE2	%xmm2
+#define STATE3	%xmm3
+#define STATE4	%xmm4
+#define KEY	%xmm5
+#define MSG	%xmm5
+#define T0	%xmm6
+#define T1	%xmm7
+
+.section .rodata.cst16.morus640_const, "aM", @progbits, 32
+.align 16
+.Lmorus640_const_0:
+	.byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d
+	.byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62
+.Lmorus640_const_1:
+	.byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1
+	.byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd
+
+.section .rodata.cst16.morus640_counter, "aM", @progbits, 16
+.align 16
+.Lmorus640_counter:
+	.byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+
+.text
+
+.macro morus640_round s0, s1, s2, s3, s4, b, w
+	movdqa \s1, T0
+	pand \s2, T0
+	pxor T0, \s0
+	pxor \s3, \s0
+	movdqa \s0, T0
+	pslld $\b, T0
+	psrld $(32 - \b), \s0
+	pxor T0, \s0
+	pshufd $\w, \s3, \s3
+.endm
+
+/*
+ * __morus640_update: internal ABI
+ * input:
+ *   STATE[0-4] - input state
+ *   MSG        - message block
+ * output:
+ *   STATE[0-4] - output state
+ * changed:
+ *   T0
+ */
+__morus640_update:
+	morus640_round STATE0, STATE1, STATE2, STATE3, STATE4,  5, MASK1
+	pxor MSG, STATE1
+	morus640_round STATE1, STATE2, STATE3, STATE4, STATE0, 31, MASK2
+	pxor MSG, STATE2
+	morus640_round STATE2, STATE3, STATE4, STATE0, STATE1,  7, MASK3
+	pxor MSG, STATE3
+	morus640_round STATE3, STATE4, STATE0, STATE1, STATE2, 22, MASK2
+	pxor MSG, STATE4
+	morus640_round STATE4, STATE0, STATE1, STATE2, STATE3, 13, MASK1
+	ret
+ENDPROC(__morus640_update)
+
+
+/*
+ * __morus640_update_zero: internal ABI
+ * input:
+ *   STATE[0-4] - input state
+ * output:
+ *   STATE[0-4] - output state
+ * changed:
+ *   T0
+ */
+__morus640_update_zero:
+	morus640_round STATE0, STATE1, STATE2, STATE3, STATE4,  5, MASK1
+	morus640_round STATE1, STATE2, STATE3, STATE4, STATE0, 31, MASK2
+	morus640_round STATE2, STATE3, STATE4, STATE0, STATE1,  7, MASK3
+	morus640_round STATE3, STATE4, STATE0, STATE1, STATE2, 22, MASK2
+	morus640_round STATE4, STATE0, STATE1, STATE2, STATE3, 13, MASK1
+	ret
+ENDPROC(__morus640_update_zero)
+
+/*
+ * __load_partial: internal ABI
+ * input:
+ *   %rsi - src
+ *   %rcx - bytes
+ * output:
+ *   MSG  - message block
+ * changed:
+ *   T0
+ *   %r8
+ *   %r9
+ */
+__load_partial:
+	xor %r9, %r9
+	pxor MSG, MSG
+
+	mov %rcx, %r8
+	and $0x1, %r8
+	jz .Lld_partial_1
+
+	mov %rcx, %r8
+	and $0x1E, %r8
+	add %rsi, %r8
+	mov (%r8), %r9b
+
+.Lld_partial_1:
+	mov %rcx, %r8
+	and $0x2, %r8
+	jz .Lld_partial_2
+
+	mov %rcx, %r8
+	and $0x1C, %r8
+	add %rsi, %r8
+	shl $16, %r9
+	mov (%r8), %r9w
+
+.Lld_partial_2:
+	mov %rcx, %r8
+	and $0x4, %r8
+	jz .Lld_partial_4
+
+	mov %rcx, %r8
+	and $0x18, %r8
+	add %rsi, %r8
+	shl $32, %r9
+	mov (%r8), %r8d
+	xor %r8, %r9
+
+.Lld_partial_4:
+	movq %r9, MSG
+
+	mov %rcx, %r8
+	and $0x8, %r8
+	jz .Lld_partial_8
+
+	mov %rcx, %r8
+	and $0x10, %r8
+	add %rsi, %r8
+	pslldq $8, MSG
+	movq (%r8), T0
+	pxor T0, MSG
+
+.Lld_partial_8:
+	ret
+ENDPROC(__load_partial)
+
+/*
+ * __store_partial: internal ABI
+ * input:
+ *   %rdx - dst
+ *   %rcx - bytes
+ * output:
+ *   T0   - message block
+ * changed:
+ *   %r8
+ *   %r9
+ *   %r10
+ */
+__store_partial:
+	mov %rcx, %r8
+	mov %rdx, %r9
+
+	movq T0, %r10
+
+	cmp $8, %r8
+	jl .Lst_partial_8
+
+	mov %r10, (%r9)
+	psrldq $8, T0
+	movq T0, %r10
+
+	sub $8, %r8
+	add $8, %r9
+
+.Lst_partial_8:
+	cmp $4, %r8
+	jl .Lst_partial_4
+
+	mov %r10d, (%r9)
+	shr $32, %r10
+
+	sub $4, %r8
+	add $4, %r9
+
+.Lst_partial_4:
+	cmp $2, %r8
+	jl .Lst_partial_2
+
+	mov %r10w, (%r9)
+	shr $16, %r10
+
+	sub $2, %r8
+	add $2, %r9
+
+.Lst_partial_2:
+	cmp $1, %r8
+	jl .Lst_partial_1
+
+	mov %r10b, (%r9)
+
+.Lst_partial_1:
+	ret
+ENDPROC(__store_partial)
+
+/*
+ * void crypto_morus640_sse2_init(void *state, const void *key, const void *iv);
+ */
+ENTRY(crypto_morus640_sse2_init)
+	FRAME_BEGIN
+
+	/* load IV: */
+	movdqu (%rdx), STATE0
+	/* load key: */
+	movdqu (%rsi), KEY
+	movdqa KEY, STATE1
+	/* load all ones: */
+	pcmpeqd STATE2, STATE2
+	/* load the constants: */
+	movdqa .Lmorus640_const_0, STATE3
+	movdqa .Lmorus640_const_1, STATE4
+
+	/* update 16 times with zero: */
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+	call __morus640_update_zero
+
+	/* xor-in the key again after updates: */
+	pxor KEY, STATE1
+
+	/* store the state: */
+	movdqu STATE0, (0 * 16)(%rdi)
+	movdqu STATE1, (1 * 16)(%rdi)
+	movdqu STATE2, (2 * 16)(%rdi)
+	movdqu STATE3, (3 * 16)(%rdi)
+	movdqu STATE4, (4 * 16)(%rdi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus640_sse2_init)
+
+/*
+ * void crypto_morus640_sse2_ad(void *state, const void *data,
+ *                              unsigned int length);
+ */
+ENTRY(crypto_morus640_sse2_ad)
+	FRAME_BEGIN
+
+	cmp $16, %rdx
+	jb .Lad_out
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0
+	movdqu (1 * 16)(%rdi), STATE1
+	movdqu (2 * 16)(%rdi), STATE2
+	movdqu (3 * 16)(%rdi), STATE3
+	movdqu (4 * 16)(%rdi), STATE4
+
+	mov %rsi, %r8
+	and $0xF, %r8
+	jnz .Lad_u_loop
+
+.align 4
+.Lad_a_loop:
+	movdqa (%rsi), MSG
+	call __morus640_update
+	sub $16, %rdx
+	add $16, %rsi
+	cmp $16, %rdx
+	jge .Lad_a_loop
+
+	jmp .Lad_cont
+.align 4
+.Lad_u_loop:
+	movdqu (%rsi), MSG
+	call __morus640_update
+	sub $16, %rdx
+	add $16, %rsi
+	cmp $16, %rdx
+	jge .Lad_u_loop
+
+.Lad_cont:
+	/* store the state: */
+	movdqu STATE0, (0 * 16)(%rdi)
+	movdqu STATE1, (1 * 16)(%rdi)
+	movdqu STATE2, (2 * 16)(%rdi)
+	movdqu STATE3, (3 * 16)(%rdi)
+	movdqu STATE4, (4 * 16)(%rdi)
+
+.Lad_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus640_sse2_ad)
+
+/*
+ * void crypto_morus640_sse2_enc(void *state, const void *src, void *dst,
+ *                               unsigned int length);
+ */
+ENTRY(crypto_morus640_sse2_enc)
+	FRAME_BEGIN
+
+	cmp $16, %rcx
+	jb .Lenc_out
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0
+	movdqu (1 * 16)(%rdi), STATE1
+	movdqu (2 * 16)(%rdi), STATE2
+	movdqu (3 * 16)(%rdi), STATE3
+	movdqu (4 * 16)(%rdi), STATE4
+
+	mov %rsi, %r8
+	or  %rdx, %r8
+	and $0xF, %r8
+	jnz .Lenc_u_loop
+
+.align 4
+.Lenc_a_loop:
+	movdqa (%rsi), MSG
+	movdqa MSG, T0
+	pxor STATE0, T0
+	pshufd $MASK3, STATE1, T1
+	pxor T1, T0
+	movdqa STATE2, T1
+	pand STATE3, T1
+	pxor T1, T0
+	movdqa T0, (%rdx)
+
+	call __morus640_update
+	sub $16, %rcx
+	add $16, %rsi
+	add $16, %rdx
+	cmp $16, %rcx
+	jge .Lenc_a_loop
+
+	jmp .Lenc_cont
+.align 4
+.Lenc_u_loop:
+	movdqu (%rsi), MSG
+	movdqa MSG, T0
+	pxor STATE0, T0
+	pshufd $MASK3, STATE1, T1
+	pxor T1, T0
+	movdqa STATE2, T1
+	pand STATE3, T1
+	pxor T1, T0
+	movdqu T0, (%rdx)
+
+	call __morus640_update
+	sub $16, %rcx
+	add $16, %rsi
+	add $16, %rdx
+	cmp $16, %rcx
+	jge .Lenc_u_loop
+
+.Lenc_cont:
+	/* store the state: */
+	movdqu STATE0, (0 * 16)(%rdi)
+	movdqu STATE1, (1 * 16)(%rdi)
+	movdqu STATE2, (2 * 16)(%rdi)
+	movdqu STATE3, (3 * 16)(%rdi)
+	movdqu STATE4, (4 * 16)(%rdi)
+
+.Lenc_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus640_sse2_enc)
+
+/*
+ * void crypto_morus640_sse2_enc_tail(void *state, const void *src, void *dst,
+ *                                    unsigned int length);
+ */
+ENTRY(crypto_morus640_sse2_enc_tail)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0
+	movdqu (1 * 16)(%rdi), STATE1
+	movdqu (2 * 16)(%rdi), STATE2
+	movdqu (3 * 16)(%rdi), STATE3
+	movdqu (4 * 16)(%rdi), STATE4
+
+	/* encrypt message: */
+	call __load_partial
+
+	movdqa MSG, T0
+	pxor STATE0, T0
+	pshufd $MASK3, STATE1, T1
+	pxor T1, T0
+	movdqa STATE2, T1
+	pand STATE3, T1
+	pxor T1, T0
+
+	call __store_partial
+
+	call __morus640_update
+
+	/* store the state: */
+	movdqu STATE0, (0 * 16)(%rdi)
+	movdqu STATE1, (1 * 16)(%rdi)
+	movdqu STATE2, (2 * 16)(%rdi)
+	movdqu STATE3, (3 * 16)(%rdi)
+	movdqu STATE4, (4 * 16)(%rdi)
+
+	FRAME_END
+ENDPROC(crypto_morus640_sse2_enc_tail)
+
+/*
+ * void crypto_morus640_sse2_dec(void *state, const void *src, void *dst,
+ *                               unsigned int length);
+ */
+ENTRY(crypto_morus640_sse2_dec)
+	FRAME_BEGIN
+
+	cmp $16, %rcx
+	jb .Ldec_out
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0
+	movdqu (1 * 16)(%rdi), STATE1
+	movdqu (2 * 16)(%rdi), STATE2
+	movdqu (3 * 16)(%rdi), STATE3
+	movdqu (4 * 16)(%rdi), STATE4
+
+	mov %rsi, %r8
+	or  %rdx, %r8
+	and $0xF, %r8
+	jnz .Ldec_u_loop
+
+.align 4
+.Ldec_a_loop:
+	movdqa (%rsi), MSG
+	pxor STATE0, MSG
+	pshufd $MASK3, STATE1, T0
+	pxor T0, MSG
+	movdqa STATE2, T0
+	pand STATE3, T0
+	pxor T0, MSG
+	movdqa MSG, (%rdx)
+
+	call __morus640_update
+	sub $16, %rcx
+	add $16, %rsi
+	add $16, %rdx
+	cmp $16, %rcx
+	jge .Ldec_a_loop
+
+	jmp .Ldec_cont
+.align 4
+.Ldec_u_loop:
+	movdqu (%rsi), MSG
+	pxor STATE0, MSG
+	pshufd $MASK3, STATE1, T0
+	pxor T0, MSG
+	movdqa STATE2, T0
+	pand STATE3, T0
+	pxor T0, MSG
+	movdqu MSG, (%rdx)
+
+	call __morus640_update
+	sub $16, %rcx
+	add $16, %rsi
+	add $16, %rdx
+	cmp $16, %rcx
+	jge .Ldec_u_loop
+
+.Ldec_cont:
+	/* store the state: */
+	movdqu STATE0, (0 * 16)(%rdi)
+	movdqu STATE1, (1 * 16)(%rdi)
+	movdqu STATE2, (2 * 16)(%rdi)
+	movdqu STATE3, (3 * 16)(%rdi)
+	movdqu STATE4, (4 * 16)(%rdi)
+
+.Ldec_out:
+	FRAME_END
+	ret
+ENDPROC(crypto_morus640_sse2_dec)
+
+/*
+ * void crypto_morus640_sse2_dec_tail(void *state, const void *src, void *dst,
+ *                                    unsigned int length);
+ */
+ENTRY(crypto_morus640_sse2_dec_tail)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0
+	movdqu (1 * 16)(%rdi), STATE1
+	movdqu (2 * 16)(%rdi), STATE2
+	movdqu (3 * 16)(%rdi), STATE3
+	movdqu (4 * 16)(%rdi), STATE4
+
+	/* decrypt message: */
+	call __load_partial
+
+	pxor STATE0, MSG
+	pshufd $MASK3, STATE1, T0
+	pxor T0, MSG
+	movdqa STATE2, T0
+	pand STATE3, T0
+	pxor T0, MSG
+	movdqa MSG, T0
+
+	call __store_partial
+
+	/* mask with byte count: */
+	movq %rcx, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	punpcklbw T0, T0
+	movdqa .Lmorus640_counter, T1
+	pcmpgtb T1, T0
+	pand T0, MSG
+
+	call __morus640_update
+
+	/* store the state: */
+	movdqu STATE0, (0 * 16)(%rdi)
+	movdqu STATE1, (1 * 16)(%rdi)
+	movdqu STATE2, (2 * 16)(%rdi)
+	movdqu STATE3, (3 * 16)(%rdi)
+	movdqu STATE4, (4 * 16)(%rdi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus640_sse2_dec_tail)
+
+/*
+ * void crypto_morus640_sse2_final(void *state, void *tag_xor,
+ *	                           u64 assoclen, u64 cryptlen);
+ */
+ENTRY(crypto_morus640_sse2_final)
+	FRAME_BEGIN
+
+	/* load the state: */
+	movdqu (0 * 16)(%rdi), STATE0
+	movdqu (1 * 16)(%rdi), STATE1
+	movdqu (2 * 16)(%rdi), STATE2
+	movdqu (3 * 16)(%rdi), STATE3
+	movdqu (4 * 16)(%rdi), STATE4
+
+	/* xor state[0] into state[4]: */
+	pxor STATE0, STATE4
+
+	/* prepare length block: */
+	movq %rdx, MSG
+	movq %rcx, T0
+	pslldq $8, T0
+	pxor T0, MSG
+	psllq $3, MSG /* multiply by 8 (to get bit count) */
+
+	/* update state: */
+	call __morus640_update
+	call __morus640_update
+	call __morus640_update
+	call __morus640_update
+	call __morus640_update
+	call __morus640_update
+	call __morus640_update
+	call __morus640_update
+	call __morus640_update
+	call __morus640_update
+
+	/* xor tag: */
+	movdqu (%rsi), MSG
+
+	pxor STATE0, MSG
+	pshufd $MASK3, STATE1, T0
+	pxor T0, MSG
+	movdqa STATE2, T0
+	pand STATE3, T0
+	pxor T0, MSG
+
+	movdqu MSG, (%rsi)
+
+	FRAME_END
+	ret
+ENDPROC(crypto_morus640_sse2_final)
diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c
new file mode 100644
index 000000000000..26b47e2db8d2
--- /dev/null
+++ b/arch/x86/crypto/morus640-sse2-glue.c
@@ -0,0 +1,68 @@
+/*
+ * The MORUS-640 Authenticated-Encryption Algorithm
+ *   Glue for SSE2 implementation
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/internal/aead.h>
+#include <crypto/morus640_glue.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/cpu_device_id.h>
+
+asmlinkage void crypto_morus640_sse2_init(void *state, const void *key,
+					  const void *iv);
+asmlinkage void crypto_morus640_sse2_ad(void *state, const void *data,
+					unsigned int length);
+
+asmlinkage void crypto_morus640_sse2_enc(void *state, const void *src,
+					 void *dst, unsigned int length);
+asmlinkage void crypto_morus640_sse2_dec(void *state, const void *src,
+					 void *dst, unsigned int length);
+
+asmlinkage void crypto_morus640_sse2_enc_tail(void *state, const void *src,
+					      void *dst, unsigned int length);
+asmlinkage void crypto_morus640_sse2_dec_tail(void *state, const void *src,
+					      void *dst, unsigned int length);
+
+asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor,
+					   u64 assoclen, u64 cryptlen);
+
+MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
+
+static const struct x86_cpu_id sse2_cpu_id[] = {
+    X86_FEATURE_MATCH(X86_FEATURE_XMM2),
+    {}
+};
+MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id);
+
+static int __init crypto_morus640_sse2_module_init(void)
+{
+	if (!x86_match_cpu(sse2_cpu_id))
+		return -ENODEV;
+
+	return crypto_register_aeads(crypto_morus640_sse2_algs,
+				     ARRAY_SIZE(crypto_morus640_sse2_algs));
+}
+
+static void __exit crypto_morus640_sse2_module_exit(void)
+{
+	crypto_unregister_aeads(crypto_morus640_sse2_algs,
+				ARRAY_SIZE(crypto_morus640_sse2_algs));
+}
+
+module_init(crypto_morus640_sse2_module_init);
+module_exit(crypto_morus640_sse2_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("MORUS-640 AEAD algorithm -- SSE2 implementation");
+MODULE_ALIAS_CRYPTO("morus640");
+MODULE_ALIAS_CRYPTO("morus640-sse2");
diff --git a/arch/x86/crypto/morus640_glue.c b/arch/x86/crypto/morus640_glue.c
new file mode 100644
index 000000000000..7b58fe4d9bd1
--- /dev/null
+++ b/arch/x86/crypto/morus640_glue.c
@@ -0,0 +1,298 @@
+/*
+ * The MORUS-640 Authenticated-Encryption Algorithm
+ *   Common x86 SIMD glue skeleton
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/cryptd.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/morus640_glue.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <asm/fpu/api.h>
+
+struct morus640_state {
+	struct morus640_block s[MORUS_STATE_BLOCKS];
+};
+
+struct morus640_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_blocks)(void *state, const void *src, void *dst,
+			     unsigned int length);
+	void (*crypt_tail)(void *state, const void *src, void *dst,
+			   unsigned int length);
+};
+
+static void crypto_morus640_glue_process_ad(
+		struct morus640_state *state,
+		const struct morus640_glue_ops *ops,
+		struct scatterlist *sg_src, unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	struct morus640_block buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= MORUS640_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = MORUS640_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+				ops->ad(state, buf.bytes, MORUS640_BLOCK_SIZE);
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			ops->ad(state, src, left);
+			src += left & ~(MORUS640_BLOCK_SIZE - 1);
+			left &= MORUS640_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+
+		pos += left;
+		assoclen -= size;
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, MORUS640_BLOCK_SIZE - pos);
+		ops->ad(state, buf.bytes, MORUS640_BLOCK_SIZE);
+	}
+}
+
+static void crypto_morus640_glue_process_crypt(struct morus640_state *state,
+					       struct morus640_ops ops,
+					       struct aead_request *req)
+{
+	struct skcipher_walk walk;
+	u8 *cursor_src, *cursor_dst;
+	unsigned int chunksize, base;
+
+	ops.skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		cursor_src = walk.src.virt.addr;
+		cursor_dst = walk.dst.virt.addr;
+		chunksize = walk.nbytes;
+
+		ops.crypt_blocks(state, cursor_src, cursor_dst, chunksize);
+
+		base = chunksize & ~(MORUS640_BLOCK_SIZE - 1);
+		cursor_src += base;
+		cursor_dst += base;
+		chunksize &= MORUS640_BLOCK_SIZE - 1;
+
+		if (chunksize > 0)
+			ops.crypt_tail(state, cursor_src, cursor_dst,
+				       chunksize);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+int crypto_morus640_glue_setkey(struct crypto_aead *aead, const u8 *key,
+				unsigned int keylen)
+{
+	struct morus640_ctx *ctx = crypto_aead_ctx(aead);
+
+	if (keylen != MORUS640_BLOCK_SIZE) {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key.bytes, key, MORUS640_BLOCK_SIZE);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_morus640_glue_setkey);
+
+int crypto_morus640_glue_setauthsize(struct crypto_aead *tfm,
+				     unsigned int authsize)
+{
+	return (authsize <= MORUS_MAX_AUTH_SIZE) ? 0 : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(crypto_morus640_glue_setauthsize);
+
+static void crypto_morus640_glue_crypt(struct aead_request *req,
+				       struct morus640_ops ops,
+				       unsigned int cryptlen,
+				       struct morus640_block *tag_xor)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus640_ctx *ctx = crypto_aead_ctx(tfm);
+	struct morus640_state state;
+
+	kernel_fpu_begin();
+
+	ctx->ops->init(&state, &ctx->key, req->iv);
+	crypto_morus640_glue_process_ad(&state, ctx->ops, req->src, req->assoclen);
+	crypto_morus640_glue_process_crypt(&state, ops, req);
+	ctx->ops->final(&state, tag_xor, req->assoclen, cryptlen);
+
+	kernel_fpu_end();
+}
+
+int crypto_morus640_glue_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus640_ctx *ctx = crypto_aead_ctx(tfm);
+	struct morus640_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_blocks = ctx->ops->enc,
+		.crypt_tail = ctx->ops->enc_tail,
+	};
+
+	struct morus640_block tag = {};
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_morus640_glue_crypt(req, OPS, cryptlen, &tag);
+
+	scatterwalk_map_and_copy(tag.bytes, req->dst,
+				 req->assoclen + cryptlen, authsize, 1);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_morus640_glue_encrypt);
+
+int crypto_morus640_glue_decrypt(struct aead_request *req)
+{
+	static const u8 zeros[MORUS640_BLOCK_SIZE] = {};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus640_ctx *ctx = crypto_aead_ctx(tfm);
+	struct morus640_ops OPS = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_blocks = ctx->ops->dec,
+		.crypt_tail = ctx->ops->dec_tail,
+	};
+
+	struct morus640_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag.bytes, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
+
+	crypto_morus640_glue_crypt(req, OPS, cryptlen, &tag);
+
+	return crypto_memneq(tag.bytes, zeros, authsize) ? -EBADMSG : 0;
+}
+EXPORT_SYMBOL_GPL(crypto_morus640_glue_decrypt);
+
+void crypto_morus640_glue_init_ops(struct crypto_aead *aead,
+				   const struct morus640_glue_ops *ops)
+{
+	struct morus640_ctx *ctx = crypto_aead_ctx(aead);
+	ctx->ops = ops;
+}
+EXPORT_SYMBOL_GPL(crypto_morus640_glue_init_ops);
+
+int cryptd_morus640_glue_setkey(struct crypto_aead *aead, const u8 *key,
+				unsigned int keylen)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus640_glue_setkey);
+
+int cryptd_morus640_glue_setauthsize(struct crypto_aead *aead,
+				     unsigned int authsize)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus640_glue_setauthsize);
+
+int cryptd_morus640_glue_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_encrypt(req);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus640_glue_encrypt);
+
+int cryptd_morus640_glue_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+
+	aead = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		aead = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, aead);
+
+	return crypto_aead_decrypt(req);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus640_glue_decrypt);
+
+int cryptd_morus640_glue_init_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead *cryptd_tfm;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+	const char *name = crypto_aead_alg(aead)->base.cra_driver_name;
+	char internal_name[CRYPTO_MAX_ALG_NAME];
+
+	if (snprintf(internal_name, CRYPTO_MAX_ALG_NAME, "__%s", name)
+			>= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	cryptd_tfm = cryptd_alloc_aead(internal_name, CRYPTO_ALG_INTERNAL,
+				       CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	*ctx = cryptd_tfm;
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cryptd_morus640_glue_init_tfm);
+
+void cryptd_morus640_glue_exit_tfm(struct crypto_aead *aead)
+{
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_free_aead(*ctx);
+}
+EXPORT_SYMBOL_GPL(cryptd_morus640_glue_exit_tfm);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("MORUS-640 AEAD mode -- glue for x86 optimizations");
diff --git a/arch/x86/crypto/salsa20-i586-asm_32.S b/arch/x86/crypto/salsa20-i586-asm_32.S
deleted file mode 100644
index 6014b7b9e52a..000000000000
--- a/arch/x86/crypto/salsa20-i586-asm_32.S
+++ /dev/null
@@ -1,938 +0,0 @@
-# Derived from:
-#	salsa20_pm.s version 20051229
-#	D. J. Bernstein
-#	Public domain.
-
-#include <linux/linkage.h>
-
-.text
-
-# enter salsa20_encrypt_bytes
-ENTRY(salsa20_encrypt_bytes)
-	mov	%esp,%eax
-	and	$31,%eax
-	add	$256,%eax
-	sub	%eax,%esp
-	# eax_stack = eax
-	movl	%eax,80(%esp)
-	# ebx_stack = ebx
-	movl	%ebx,84(%esp)
-	# esi_stack = esi
-	movl	%esi,88(%esp)
-	# edi_stack = edi
-	movl	%edi,92(%esp)
-	# ebp_stack = ebp
-	movl	%ebp,96(%esp)
-	# x = arg1
-	movl	4(%esp,%eax),%edx
-	# m = arg2
-	movl	8(%esp,%eax),%esi
-	# out = arg3
-	movl	12(%esp,%eax),%edi
-	# bytes = arg4
-	movl	16(%esp,%eax),%ebx
-	# bytes -= 0
-	sub	$0,%ebx
-	# goto done if unsigned<=
-	jbe	._done
-._start:
-	# in0 = *(uint32 *) (x + 0)
-	movl	0(%edx),%eax
-	# in1 = *(uint32 *) (x + 4)
-	movl	4(%edx),%ecx
-	# in2 = *(uint32 *) (x + 8)
-	movl	8(%edx),%ebp
-	# j0 = in0
-	movl	%eax,164(%esp)
-	# in3 = *(uint32 *) (x + 12)
-	movl	12(%edx),%eax
-	# j1 = in1
-	movl	%ecx,168(%esp)
-	# in4 = *(uint32 *) (x + 16)
-	movl	16(%edx),%ecx
-	# j2 = in2
-	movl	%ebp,172(%esp)
-	# in5 = *(uint32 *) (x + 20)
-	movl	20(%edx),%ebp
-	# j3 = in3
-	movl	%eax,176(%esp)
-	# in6 = *(uint32 *) (x + 24)
-	movl	24(%edx),%eax
-	# j4 = in4
-	movl	%ecx,180(%esp)
-	# in7 = *(uint32 *) (x + 28)
-	movl	28(%edx),%ecx
-	# j5 = in5
-	movl	%ebp,184(%esp)
-	# in8 = *(uint32 *) (x + 32)
-	movl	32(%edx),%ebp
-	# j6 = in6
-	movl	%eax,188(%esp)
-	# in9 = *(uint32 *) (x + 36)
-	movl	36(%edx),%eax
-	# j7 = in7
-	movl	%ecx,192(%esp)
-	# in10 = *(uint32 *) (x + 40)
-	movl	40(%edx),%ecx
-	# j8 = in8
-	movl	%ebp,196(%esp)
-	# in11 = *(uint32 *) (x + 44)
-	movl	44(%edx),%ebp
-	# j9 = in9
-	movl	%eax,200(%esp)
-	# in12 = *(uint32 *) (x + 48)
-	movl	48(%edx),%eax
-	# j10 = in10
-	movl	%ecx,204(%esp)
-	# in13 = *(uint32 *) (x + 52)
-	movl	52(%edx),%ecx
-	# j11 = in11
-	movl	%ebp,208(%esp)
-	# in14 = *(uint32 *) (x + 56)
-	movl	56(%edx),%ebp
-	# j12 = in12
-	movl	%eax,212(%esp)
-	# in15 = *(uint32 *) (x + 60)
-	movl	60(%edx),%eax
-	# j13 = in13
-	movl	%ecx,216(%esp)
-	# j14 = in14
-	movl	%ebp,220(%esp)
-	# j15 = in15
-	movl	%eax,224(%esp)
-	# x_backup = x
-	movl	%edx,64(%esp)
-._bytesatleast1:
-	#   bytes - 64
-	cmp	$64,%ebx
-	#   goto nocopy if unsigned>=
-	jae	._nocopy
-	#     ctarget = out
-	movl	%edi,228(%esp)
-	#     out = &tmp
-	leal	0(%esp),%edi
-	#     i = bytes
-	mov	%ebx,%ecx
-	#     while (i) { *out++ = *m++; --i }
-	rep	movsb
-	#     out = &tmp
-	leal	0(%esp),%edi
-	#     m = &tmp
-	leal	0(%esp),%esi
-._nocopy:
-	#   out_backup = out
-	movl	%edi,72(%esp)
-	#   m_backup = m
-	movl	%esi,68(%esp)
-	#   bytes_backup = bytes
-	movl	%ebx,76(%esp)
-	#   in0 = j0
-	movl	164(%esp),%eax
-	#   in1 = j1
-	movl	168(%esp),%ecx
-	#   in2 = j2
-	movl	172(%esp),%edx
-	#   in3 = j3
-	movl	176(%esp),%ebx
-	#   x0 = in0
-	movl	%eax,100(%esp)
-	#   x1 = in1
-	movl	%ecx,104(%esp)
-	#   x2 = in2
-	movl	%edx,108(%esp)
-	#   x3 = in3
-	movl	%ebx,112(%esp)
-	#   in4 = j4
-	movl	180(%esp),%eax
-	#   in5 = j5
-	movl	184(%esp),%ecx
-	#   in6 = j6
-	movl	188(%esp),%edx
-	#   in7 = j7
-	movl	192(%esp),%ebx
-	#   x4 = in4
-	movl	%eax,116(%esp)
-	#   x5 = in5
-	movl	%ecx,120(%esp)
-	#   x6 = in6
-	movl	%edx,124(%esp)
-	#   x7 = in7
-	movl	%ebx,128(%esp)
-	#   in8 = j8
-	movl	196(%esp),%eax
-	#   in9 = j9
-	movl	200(%esp),%ecx
-	#   in10 = j10
-	movl	204(%esp),%edx
-	#   in11 = j11
-	movl	208(%esp),%ebx
-	#   x8 = in8
-	movl	%eax,132(%esp)
-	#   x9 = in9
-	movl	%ecx,136(%esp)
-	#   x10 = in10
-	movl	%edx,140(%esp)
-	#   x11 = in11
-	movl	%ebx,144(%esp)
-	#   in12 = j12
-	movl	212(%esp),%eax
-	#   in13 = j13
-	movl	216(%esp),%ecx
-	#   in14 = j14
-	movl	220(%esp),%edx
-	#   in15 = j15
-	movl	224(%esp),%ebx
-	#   x12 = in12
-	movl	%eax,148(%esp)
-	#   x13 = in13
-	movl	%ecx,152(%esp)
-	#   x14 = in14
-	movl	%edx,156(%esp)
-	#   x15 = in15
-	movl	%ebx,160(%esp)
-	#   i = 20
-	mov	$20,%ebp
-	# p = x0
-	movl	100(%esp),%eax
-	# s = x5
-	movl	120(%esp),%ecx
-	# t = x10
-	movl	140(%esp),%edx
-	# w = x15
-	movl	160(%esp),%ebx
-._mainloop:
-	# x0 = p
-	movl	%eax,100(%esp)
-	# 				x10 = t
-	movl	%edx,140(%esp)
-	# p += x12
-	addl	148(%esp),%eax
-	# 		x5 = s
-	movl	%ecx,120(%esp)
-	# 				t += x6
-	addl	124(%esp),%edx
-	# 						x15 = w
-	movl	%ebx,160(%esp)
-	# 		r = x1
-	movl	104(%esp),%esi
-	# 		r += s
-	add	%ecx,%esi
-	# 						v = x11
-	movl	144(%esp),%edi
-	# 						v += w
-	add	%ebx,%edi
-	# p <<<= 7
-	rol	$7,%eax
-	# p ^= x4
-	xorl	116(%esp),%eax
-	# 				t <<<= 7
-	rol	$7,%edx
-	# 				t ^= x14
-	xorl	156(%esp),%edx
-	# 		r <<<= 7
-	rol	$7,%esi
-	# 		r ^= x9
-	xorl	136(%esp),%esi
-	# 						v <<<= 7
-	rol	$7,%edi
-	# 						v ^= x3
-	xorl	112(%esp),%edi
-	# x4 = p
-	movl	%eax,116(%esp)
-	# 				x14 = t
-	movl	%edx,156(%esp)
-	# p += x0
-	addl	100(%esp),%eax
-	# 		x9 = r
-	movl	%esi,136(%esp)
-	# 				t += x10
-	addl	140(%esp),%edx
-	# 						x3 = v
-	movl	%edi,112(%esp)
-	# p <<<= 9
-	rol	$9,%eax
-	# p ^= x8
-	xorl	132(%esp),%eax
-	# 				t <<<= 9
-	rol	$9,%edx
-	# 				t ^= x2
-	xorl	108(%esp),%edx
-	# 		s += r
-	add	%esi,%ecx
-	# 		s <<<= 9
-	rol	$9,%ecx
-	# 		s ^= x13
-	xorl	152(%esp),%ecx
-	# 						w += v
-	add	%edi,%ebx
-	# 						w <<<= 9
-	rol	$9,%ebx
-	# 						w ^= x7
-	xorl	128(%esp),%ebx
-	# x8 = p
-	movl	%eax,132(%esp)
-	# 				x2 = t
-	movl	%edx,108(%esp)
-	# p += x4
-	addl	116(%esp),%eax
-	# 		x13 = s
-	movl	%ecx,152(%esp)
-	# 				t += x14
-	addl	156(%esp),%edx
-	# 						x7 = w
-	movl	%ebx,128(%esp)
-	# p <<<= 13
-	rol	$13,%eax
-	# p ^= x12
-	xorl	148(%esp),%eax
-	# 				t <<<= 13
-	rol	$13,%edx
-	# 				t ^= x6
-	xorl	124(%esp),%edx
-	# 		r += s
-	add	%ecx,%esi
-	# 		r <<<= 13
-	rol	$13,%esi
-	# 		r ^= x1
-	xorl	104(%esp),%esi
-	# 						v += w
-	add	%ebx,%edi
-	# 						v <<<= 13
-	rol	$13,%edi
-	# 						v ^= x11
-	xorl	144(%esp),%edi
-	# x12 = p
-	movl	%eax,148(%esp)
-	# 				x6 = t
-	movl	%edx,124(%esp)
-	# p += x8
-	addl	132(%esp),%eax
-	# 		x1 = r
-	movl	%esi,104(%esp)
-	# 				t += x2
-	addl	108(%esp),%edx
-	# 						x11 = v
-	movl	%edi,144(%esp)
-	# p <<<= 18
-	rol	$18,%eax
-	# p ^= x0
-	xorl	100(%esp),%eax
-	# 				t <<<= 18
-	rol	$18,%edx
-	# 				t ^= x10
-	xorl	140(%esp),%edx
-	# 		s += r
-	add	%esi,%ecx
-	# 		s <<<= 18
-	rol	$18,%ecx
-	# 		s ^= x5
-	xorl	120(%esp),%ecx
-	# 						w += v
-	add	%edi,%ebx
-	# 						w <<<= 18
-	rol	$18,%ebx
-	# 						w ^= x15
-	xorl	160(%esp),%ebx
-	# x0 = p
-	movl	%eax,100(%esp)
-	# 				x10 = t
-	movl	%edx,140(%esp)
-	# p += x3
-	addl	112(%esp),%eax
-	# p <<<= 7
-	rol	$7,%eax
-	# 		x5 = s
-	movl	%ecx,120(%esp)
-	# 				t += x9
-	addl	136(%esp),%edx
-	# 						x15 = w
-	movl	%ebx,160(%esp)
-	# 		r = x4
-	movl	116(%esp),%esi
-	# 		r += s
-	add	%ecx,%esi
-	# 						v = x14
-	movl	156(%esp),%edi
-	# 						v += w
-	add	%ebx,%edi
-	# p ^= x1
-	xorl	104(%esp),%eax
-	# 				t <<<= 7
-	rol	$7,%edx
-	# 				t ^= x11
-	xorl	144(%esp),%edx
-	# 		r <<<= 7
-	rol	$7,%esi
-	# 		r ^= x6
-	xorl	124(%esp),%esi
-	# 						v <<<= 7
-	rol	$7,%edi
-	# 						v ^= x12
-	xorl	148(%esp),%edi
-	# x1 = p
-	movl	%eax,104(%esp)
-	# 				x11 = t
-	movl	%edx,144(%esp)
-	# p += x0
-	addl	100(%esp),%eax
-	# 		x6 = r
-	movl	%esi,124(%esp)
-	# 				t += x10
-	addl	140(%esp),%edx
-	# 						x12 = v
-	movl	%edi,148(%esp)
-	# p <<<= 9
-	rol	$9,%eax
-	# p ^= x2
-	xorl	108(%esp),%eax
-	# 				t <<<= 9
-	rol	$9,%edx
-	# 				t ^= x8
-	xorl	132(%esp),%edx
-	# 		s += r
-	add	%esi,%ecx
-	# 		s <<<= 9
-	rol	$9,%ecx
-	# 		s ^= x7
-	xorl	128(%esp),%ecx
-	# 						w += v
-	add	%edi,%ebx
-	# 						w <<<= 9
-	rol	$9,%ebx
-	# 						w ^= x13
-	xorl	152(%esp),%ebx
-	# x2 = p
-	movl	%eax,108(%esp)
-	# 				x8 = t
-	movl	%edx,132(%esp)
-	# p += x1
-	addl	104(%esp),%eax
-	# 		x7 = s
-	movl	%ecx,128(%esp)
-	# 				t += x11
-	addl	144(%esp),%edx
-	# 						x13 = w
-	movl	%ebx,152(%esp)
-	# p <<<= 13
-	rol	$13,%eax
-	# p ^= x3
-	xorl	112(%esp),%eax
-	# 				t <<<= 13
-	rol	$13,%edx
-	# 				t ^= x9
-	xorl	136(%esp),%edx
-	# 		r += s
-	add	%ecx,%esi
-	# 		r <<<= 13
-	rol	$13,%esi
-	# 		r ^= x4
-	xorl	116(%esp),%esi
-	# 						v += w
-	add	%ebx,%edi
-	# 						v <<<= 13
-	rol	$13,%edi
-	# 						v ^= x14
-	xorl	156(%esp),%edi
-	# x3 = p
-	movl	%eax,112(%esp)
-	# 				x9 = t
-	movl	%edx,136(%esp)
-	# p += x2
-	addl	108(%esp),%eax
-	# 		x4 = r
-	movl	%esi,116(%esp)
-	# 				t += x8
-	addl	132(%esp),%edx
-	# 						x14 = v
-	movl	%edi,156(%esp)
-	# p <<<= 18
-	rol	$18,%eax
-	# p ^= x0
-	xorl	100(%esp),%eax
-	# 				t <<<= 18
-	rol	$18,%edx
-	# 				t ^= x10
-	xorl	140(%esp),%edx
-	# 		s += r
-	add	%esi,%ecx
-	# 		s <<<= 18
-	rol	$18,%ecx
-	# 		s ^= x5
-	xorl	120(%esp),%ecx
-	# 						w += v
-	add	%edi,%ebx
-	# 						w <<<= 18
-	rol	$18,%ebx
-	# 						w ^= x15
-	xorl	160(%esp),%ebx
-	# x0 = p
-	movl	%eax,100(%esp)
-	# 				x10 = t
-	movl	%edx,140(%esp)
-	# p += x12
-	addl	148(%esp),%eax
-	# 		x5 = s
-	movl	%ecx,120(%esp)
-	# 				t += x6
-	addl	124(%esp),%edx
-	# 						x15 = w
-	movl	%ebx,160(%esp)
-	# 		r = x1
-	movl	104(%esp),%esi
-	# 		r += s
-	add	%ecx,%esi
-	# 						v = x11
-	movl	144(%esp),%edi
-	# 						v += w
-	add	%ebx,%edi
-	# p <<<= 7
-	rol	$7,%eax
-	# p ^= x4
-	xorl	116(%esp),%eax
-	# 				t <<<= 7
-	rol	$7,%edx
-	# 				t ^= x14
-	xorl	156(%esp),%edx
-	# 		r <<<= 7
-	rol	$7,%esi
-	# 		r ^= x9
-	xorl	136(%esp),%esi
-	# 						v <<<= 7
-	rol	$7,%edi
-	# 						v ^= x3
-	xorl	112(%esp),%edi
-	# x4 = p
-	movl	%eax,116(%esp)
-	# 				x14 = t
-	movl	%edx,156(%esp)
-	# p += x0
-	addl	100(%esp),%eax
-	# 		x9 = r
-	movl	%esi,136(%esp)
-	# 				t += x10
-	addl	140(%esp),%edx
-	# 						x3 = v
-	movl	%edi,112(%esp)
-	# p <<<= 9
-	rol	$9,%eax
-	# p ^= x8
-	xorl	132(%esp),%eax
-	# 				t <<<= 9
-	rol	$9,%edx
-	# 				t ^= x2
-	xorl	108(%esp),%edx
-	# 		s += r
-	add	%esi,%ecx
-	# 		s <<<= 9
-	rol	$9,%ecx
-	# 		s ^= x13
-	xorl	152(%esp),%ecx
-	# 						w += v
-	add	%edi,%ebx
-	# 						w <<<= 9
-	rol	$9,%ebx
-	# 						w ^= x7
-	xorl	128(%esp),%ebx
-	# x8 = p
-	movl	%eax,132(%esp)
-	# 				x2 = t
-	movl	%edx,108(%esp)
-	# p += x4
-	addl	116(%esp),%eax
-	# 		x13 = s
-	movl	%ecx,152(%esp)
-	# 				t += x14
-	addl	156(%esp),%edx
-	# 						x7 = w
-	movl	%ebx,128(%esp)
-	# p <<<= 13
-	rol	$13,%eax
-	# p ^= x12
-	xorl	148(%esp),%eax
-	# 				t <<<= 13
-	rol	$13,%edx
-	# 				t ^= x6
-	xorl	124(%esp),%edx
-	# 		r += s
-	add	%ecx,%esi
-	# 		r <<<= 13
-	rol	$13,%esi
-	# 		r ^= x1
-	xorl	104(%esp),%esi
-	# 						v += w
-	add	%ebx,%edi
-	# 						v <<<= 13
-	rol	$13,%edi
-	# 						v ^= x11
-	xorl	144(%esp),%edi
-	# x12 = p
-	movl	%eax,148(%esp)
-	# 				x6 = t
-	movl	%edx,124(%esp)
-	# p += x8
-	addl	132(%esp),%eax
-	# 		x1 = r
-	movl	%esi,104(%esp)
-	# 				t += x2
-	addl	108(%esp),%edx
-	# 						x11 = v
-	movl	%edi,144(%esp)
-	# p <<<= 18
-	rol	$18,%eax
-	# p ^= x0
-	xorl	100(%esp),%eax
-	# 				t <<<= 18
-	rol	$18,%edx
-	# 				t ^= x10
-	xorl	140(%esp),%edx
-	# 		s += r
-	add	%esi,%ecx
-	# 		s <<<= 18
-	rol	$18,%ecx
-	# 		s ^= x5
-	xorl	120(%esp),%ecx
-	# 						w += v
-	add	%edi,%ebx
-	# 						w <<<= 18
-	rol	$18,%ebx
-	# 						w ^= x15
-	xorl	160(%esp),%ebx
-	# x0 = p
-	movl	%eax,100(%esp)
-	# 				x10 = t
-	movl	%edx,140(%esp)
-	# p += x3
-	addl	112(%esp),%eax
-	# p <<<= 7
-	rol	$7,%eax
-	# 		x5 = s
-	movl	%ecx,120(%esp)
-	# 				t += x9
-	addl	136(%esp),%edx
-	# 						x15 = w
-	movl	%ebx,160(%esp)
-	# 		r = x4
-	movl	116(%esp),%esi
-	# 		r += s
-	add	%ecx,%esi
-	# 						v = x14
-	movl	156(%esp),%edi
-	# 						v += w
-	add	%ebx,%edi
-	# p ^= x1
-	xorl	104(%esp),%eax
-	# 				t <<<= 7
-	rol	$7,%edx
-	# 				t ^= x11
-	xorl	144(%esp),%edx
-	# 		r <<<= 7
-	rol	$7,%esi
-	# 		r ^= x6
-	xorl	124(%esp),%esi
-	# 						v <<<= 7
-	rol	$7,%edi
-	# 						v ^= x12
-	xorl	148(%esp),%edi
-	# x1 = p
-	movl	%eax,104(%esp)
-	# 				x11 = t
-	movl	%edx,144(%esp)
-	# p += x0
-	addl	100(%esp),%eax
-	# 		x6 = r
-	movl	%esi,124(%esp)
-	# 				t += x10
-	addl	140(%esp),%edx
-	# 						x12 = v
-	movl	%edi,148(%esp)
-	# p <<<= 9
-	rol	$9,%eax
-	# p ^= x2
-	xorl	108(%esp),%eax
-	# 				t <<<= 9
-	rol	$9,%edx
-	# 				t ^= x8
-	xorl	132(%esp),%edx
-	# 		s += r
-	add	%esi,%ecx
-	# 		s <<<= 9
-	rol	$9,%ecx
-	# 		s ^= x7
-	xorl	128(%esp),%ecx
-	# 						w += v
-	add	%edi,%ebx
-	# 						w <<<= 9
-	rol	$9,%ebx
-	# 						w ^= x13
-	xorl	152(%esp),%ebx
-	# x2 = p
-	movl	%eax,108(%esp)
-	# 				x8 = t
-	movl	%edx,132(%esp)
-	# p += x1
-	addl	104(%esp),%eax
-	# 		x7 = s
-	movl	%ecx,128(%esp)
-	# 				t += x11
-	addl	144(%esp),%edx
-	# 						x13 = w
-	movl	%ebx,152(%esp)
-	# p <<<= 13
-	rol	$13,%eax
-	# p ^= x3
-	xorl	112(%esp),%eax
-	# 				t <<<= 13
-	rol	$13,%edx
-	# 				t ^= x9
-	xorl	136(%esp),%edx
-	# 		r += s
-	add	%ecx,%esi
-	# 		r <<<= 13
-	rol	$13,%esi
-	# 		r ^= x4
-	xorl	116(%esp),%esi
-	# 						v += w
-	add	%ebx,%edi
-	# 						v <<<= 13
-	rol	$13,%edi
-	# 						v ^= x14
-	xorl	156(%esp),%edi
-	# x3 = p
-	movl	%eax,112(%esp)
-	# 				x9 = t
-	movl	%edx,136(%esp)
-	# p += x2
-	addl	108(%esp),%eax
-	# 		x4 = r
-	movl	%esi,116(%esp)
-	# 				t += x8
-	addl	132(%esp),%edx
-	# 						x14 = v
-	movl	%edi,156(%esp)
-	# p <<<= 18
-	rol	$18,%eax
-	# p ^= x0
-	xorl	100(%esp),%eax
-	# 				t <<<= 18
-	rol	$18,%edx
-	# 				t ^= x10
-	xorl	140(%esp),%edx
-	# 		s += r
-	add	%esi,%ecx
-	# 		s <<<= 18
-	rol	$18,%ecx
-	# 		s ^= x5
-	xorl	120(%esp),%ecx
-	# 						w += v
-	add	%edi,%ebx
-	# 						w <<<= 18
-	rol	$18,%ebx
-	# 						w ^= x15
-	xorl	160(%esp),%ebx
-	# i -= 4
-	sub	$4,%ebp
-	# goto mainloop if unsigned >
-	ja	._mainloop
-	# x0 = p
-	movl	%eax,100(%esp)
-	# x5 = s
-	movl	%ecx,120(%esp)
-	# x10 = t
-	movl	%edx,140(%esp)
-	# x15 = w
-	movl	%ebx,160(%esp)
-	#   out = out_backup
-	movl	72(%esp),%edi
-	#   m = m_backup
-	movl	68(%esp),%esi
-	#   in0 = x0
-	movl	100(%esp),%eax
-	#   in1 = x1
-	movl	104(%esp),%ecx
-	#   in0 += j0
-	addl	164(%esp),%eax
-	#   in1 += j1
-	addl	168(%esp),%ecx
-	#   in0 ^= *(uint32 *) (m + 0)
-	xorl	0(%esi),%eax
-	#   in1 ^= *(uint32 *) (m + 4)
-	xorl	4(%esi),%ecx
-	#   *(uint32 *) (out + 0) = in0
-	movl	%eax,0(%edi)
-	#   *(uint32 *) (out + 4) = in1
-	movl	%ecx,4(%edi)
-	#   in2 = x2
-	movl	108(%esp),%eax
-	#   in3 = x3
-	movl	112(%esp),%ecx
-	#   in2 += j2
-	addl	172(%esp),%eax
-	#   in3 += j3
-	addl	176(%esp),%ecx
-	#   in2 ^= *(uint32 *) (m + 8)
-	xorl	8(%esi),%eax
-	#   in3 ^= *(uint32 *) (m + 12)
-	xorl	12(%esi),%ecx
-	#   *(uint32 *) (out + 8) = in2
-	movl	%eax,8(%edi)
-	#   *(uint32 *) (out + 12) = in3
-	movl	%ecx,12(%edi)
-	#   in4 = x4
-	movl	116(%esp),%eax
-	#   in5 = x5
-	movl	120(%esp),%ecx
-	#   in4 += j4
-	addl	180(%esp),%eax
-	#   in5 += j5
-	addl	184(%esp),%ecx
-	#   in4 ^= *(uint32 *) (m + 16)
-	xorl	16(%esi),%eax
-	#   in5 ^= *(uint32 *) (m + 20)
-	xorl	20(%esi),%ecx
-	#   *(uint32 *) (out + 16) = in4
-	movl	%eax,16(%edi)
-	#   *(uint32 *) (out + 20) = in5
-	movl	%ecx,20(%edi)
-	#   in6 = x6
-	movl	124(%esp),%eax
-	#   in7 = x7
-	movl	128(%esp),%ecx
-	#   in6 += j6
-	addl	188(%esp),%eax
-	#   in7 += j7
-	addl	192(%esp),%ecx
-	#   in6 ^= *(uint32 *) (m + 24)
-	xorl	24(%esi),%eax
-	#   in7 ^= *(uint32 *) (m + 28)
-	xorl	28(%esi),%ecx
-	#   *(uint32 *) (out + 24) = in6
-	movl	%eax,24(%edi)
-	#   *(uint32 *) (out + 28) = in7
-	movl	%ecx,28(%edi)
-	#   in8 = x8
-	movl	132(%esp),%eax
-	#   in9 = x9
-	movl	136(%esp),%ecx
-	#   in8 += j8
-	addl	196(%esp),%eax
-	#   in9 += j9
-	addl	200(%esp),%ecx
-	#   in8 ^= *(uint32 *) (m + 32)
-	xorl	32(%esi),%eax
-	#   in9 ^= *(uint32 *) (m + 36)
-	xorl	36(%esi),%ecx
-	#   *(uint32 *) (out + 32) = in8
-	movl	%eax,32(%edi)
-	#   *(uint32 *) (out + 36) = in9
-	movl	%ecx,36(%edi)
-	#   in10 = x10
-	movl	140(%esp),%eax
-	#   in11 = x11
-	movl	144(%esp),%ecx
-	#   in10 += j10
-	addl	204(%esp),%eax
-	#   in11 += j11
-	addl	208(%esp),%ecx
-	#   in10 ^= *(uint32 *) (m + 40)
-	xorl	40(%esi),%eax
-	#   in11 ^= *(uint32 *) (m + 44)
-	xorl	44(%esi),%ecx
-	#   *(uint32 *) (out + 40) = in10
-	movl	%eax,40(%edi)
-	#   *(uint32 *) (out + 44) = in11
-	movl	%ecx,44(%edi)
-	#   in12 = x12
-	movl	148(%esp),%eax
-	#   in13 = x13
-	movl	152(%esp),%ecx
-	#   in12 += j12
-	addl	212(%esp),%eax
-	#   in13 += j13
-	addl	216(%esp),%ecx
-	#   in12 ^= *(uint32 *) (m + 48)
-	xorl	48(%esi),%eax
-	#   in13 ^= *(uint32 *) (m + 52)
-	xorl	52(%esi),%ecx
-	#   *(uint32 *) (out + 48) = in12
-	movl	%eax,48(%edi)
-	#   *(uint32 *) (out + 52) = in13
-	movl	%ecx,52(%edi)
-	#   in14 = x14
-	movl	156(%esp),%eax
-	#   in15 = x15
-	movl	160(%esp),%ecx
-	#   in14 += j14
-	addl	220(%esp),%eax
-	#   in15 += j15
-	addl	224(%esp),%ecx
-	#   in14 ^= *(uint32 *) (m + 56)
-	xorl	56(%esi),%eax
-	#   in15 ^= *(uint32 *) (m + 60)
-	xorl	60(%esi),%ecx
-	#   *(uint32 *) (out + 56) = in14
-	movl	%eax,56(%edi)
-	#   *(uint32 *) (out + 60) = in15
-	movl	%ecx,60(%edi)
-	#   bytes = bytes_backup
-	movl	76(%esp),%ebx
-	#   in8 = j8
-	movl	196(%esp),%eax
-	#   in9 = j9
-	movl	200(%esp),%ecx
-	#   in8 += 1
-	add	$1,%eax
-	#   in9 += 0 + carry
-	adc	$0,%ecx
-	#   j8 = in8
-	movl	%eax,196(%esp)
-	#   j9 = in9
-	movl	%ecx,200(%esp)
-	#   bytes - 64
-	cmp	$64,%ebx
-	#   goto bytesatleast65 if unsigned>
-	ja	._bytesatleast65
-	#     goto bytesatleast64 if unsigned>=
-	jae	._bytesatleast64
-	#       m = out
-	mov	%edi,%esi
-	#       out = ctarget
-	movl	228(%esp),%edi
-	#       i = bytes
-	mov	%ebx,%ecx
-	#       while (i) { *out++ = *m++; --i }
-	rep	movsb
-._bytesatleast64:
-	#     x = x_backup
-	movl	64(%esp),%eax
-	#     in8 = j8
-	movl	196(%esp),%ecx
-	#     in9 = j9
-	movl	200(%esp),%edx
-	#     *(uint32 *) (x + 32) = in8
-	movl	%ecx,32(%eax)
-	#     *(uint32 *) (x + 36) = in9
-	movl	%edx,36(%eax)
-._done:
-	#     eax = eax_stack
-	movl	80(%esp),%eax
-	#     ebx = ebx_stack
-	movl	84(%esp),%ebx
-	#     esi = esi_stack
-	movl	88(%esp),%esi
-	#     edi = edi_stack
-	movl	92(%esp),%edi
-	#     ebp = ebp_stack
-	movl	96(%esp),%ebp
-	#     leave
-	add	%eax,%esp
-	ret
-._bytesatleast65:
-	#   bytes -= 64
-	sub	$64,%ebx
-	#   out += 64
-	add	$64,%edi
-	#   m += 64
-	add	$64,%esi
-	# goto bytesatleast1
-	jmp	._bytesatleast1
-ENDPROC(salsa20_encrypt_bytes)
diff --git a/arch/x86/crypto/salsa20-x86_64-asm_64.S b/arch/x86/crypto/salsa20-x86_64-asm_64.S
deleted file mode 100644
index 03a4918f41ee..000000000000
--- a/arch/x86/crypto/salsa20-x86_64-asm_64.S
+++ /dev/null
@@ -1,805 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <linux/linkage.h>
-
-# enter salsa20_encrypt_bytes
-ENTRY(salsa20_encrypt_bytes)
-	mov	%rsp,%r11
-	and	$31,%r11
-	add	$256,%r11
-	sub	%r11,%rsp
-	# x = arg1
-	mov	%rdi,%r8
-	# m = arg2
-	mov	%rsi,%rsi
-	# out = arg3
-	mov	%rdx,%rdi
-	# bytes = arg4
-	mov	%rcx,%rdx
-	#               unsigned>? bytes - 0
-	cmp	$0,%rdx
-	# comment:fp stack unchanged by jump
-	# goto done if !unsigned>
-	jbe	._done
-	# comment:fp stack unchanged by fallthrough
-# start:
-._start:
-	# r11_stack = r11
-	movq	%r11,0(%rsp)
-	# r12_stack = r12
-	movq	%r12,8(%rsp)
-	# r13_stack = r13
-	movq	%r13,16(%rsp)
-	# r14_stack = r14
-	movq	%r14,24(%rsp)
-	# r15_stack = r15
-	movq	%r15,32(%rsp)
-	# rbx_stack = rbx
-	movq	%rbx,40(%rsp)
-	# rbp_stack = rbp
-	movq	%rbp,48(%rsp)
-	# in0 = *(uint64 *) (x + 0)
-	movq	0(%r8),%rcx
-	# in2 = *(uint64 *) (x + 8)
-	movq	8(%r8),%r9
-	# in4 = *(uint64 *) (x + 16)
-	movq	16(%r8),%rax
-	# in6 = *(uint64 *) (x + 24)
-	movq	24(%r8),%r10
-	# in8 = *(uint64 *) (x + 32)
-	movq	32(%r8),%r11
-	# in10 = *(uint64 *) (x + 40)
-	movq	40(%r8),%r12
-	# in12 = *(uint64 *) (x + 48)
-	movq	48(%r8),%r13
-	# in14 = *(uint64 *) (x + 56)
-	movq	56(%r8),%r14
-	# j0 = in0
-	movq	%rcx,56(%rsp)
-	# j2 = in2
-	movq	%r9,64(%rsp)
-	# j4 = in4
-	movq	%rax,72(%rsp)
-	# j6 = in6
-	movq	%r10,80(%rsp)
-	# j8 = in8
-	movq	%r11,88(%rsp)
-	# j10 = in10
-	movq	%r12,96(%rsp)
-	# j12 = in12
-	movq	%r13,104(%rsp)
-	# j14 = in14
-	movq	%r14,112(%rsp)
-	# x_backup = x
-	movq	%r8,120(%rsp)
-# bytesatleast1:
-._bytesatleast1:
-	#                   unsigned<? bytes - 64
-	cmp	$64,%rdx
-	# comment:fp stack unchanged by jump
-	#   goto nocopy if !unsigned<
-	jae	._nocopy
-	#     ctarget = out
-	movq	%rdi,128(%rsp)
-	#     out = &tmp
-	leaq	192(%rsp),%rdi
-	#     i = bytes
-	mov	%rdx,%rcx
-	#     while (i) { *out++ = *m++; --i }
-	rep	movsb
-	#     out = &tmp
-	leaq	192(%rsp),%rdi
-	#     m = &tmp
-	leaq	192(%rsp),%rsi
-	# comment:fp stack unchanged by fallthrough
-#   nocopy:
-._nocopy:
-	#   out_backup = out
-	movq	%rdi,136(%rsp)
-	#   m_backup = m
-	movq	%rsi,144(%rsp)
-	#   bytes_backup = bytes
-	movq	%rdx,152(%rsp)
-	#   x1 = j0
-	movq	56(%rsp),%rdi
-	#   x0 = x1
-	mov	%rdi,%rdx
-	#   (uint64) x1 >>= 32
-	shr	$32,%rdi
-	#   		x3 = j2
-	movq	64(%rsp),%rsi
-	#   		x2 = x3
-	mov	%rsi,%rcx
-	#   		(uint64) x3 >>= 32
-	shr	$32,%rsi
-	#   x5 = j4
-	movq	72(%rsp),%r8
-	#   x4 = x5
-	mov	%r8,%r9
-	#   (uint64) x5 >>= 32
-	shr	$32,%r8
-	#   x5_stack = x5
-	movq	%r8,160(%rsp)
-	#   		x7 = j6
-	movq	80(%rsp),%r8
-	#   		x6 = x7
-	mov	%r8,%rax
-	#   		(uint64) x7 >>= 32
-	shr	$32,%r8
-	#   x9 = j8
-	movq	88(%rsp),%r10
-	#   x8 = x9
-	mov	%r10,%r11
-	#   (uint64) x9 >>= 32
-	shr	$32,%r10
-	#   		x11 = j10
-	movq	96(%rsp),%r12
-	#   		x10 = x11
-	mov	%r12,%r13
-	#   		x10_stack = x10
-	movq	%r13,168(%rsp)
-	#   		(uint64) x11 >>= 32
-	shr	$32,%r12
-	#   x13 = j12
-	movq	104(%rsp),%r13
-	#   x12 = x13
-	mov	%r13,%r14
-	#   (uint64) x13 >>= 32
-	shr	$32,%r13
-	#   		x15 = j14
-	movq	112(%rsp),%r15
-	#   		x14 = x15
-	mov	%r15,%rbx
-	#   		(uint64) x15 >>= 32
-	shr	$32,%r15
-	#   		x15_stack = x15
-	movq	%r15,176(%rsp)
-	#   i = 20
-	mov	$20,%r15
-#   mainloop:
-._mainloop:
-	#   i_backup = i
-	movq	%r15,184(%rsp)
-	# 		x5 = x5_stack
-	movq	160(%rsp),%r15
-	# a = x12 + x0
-	lea	(%r14,%rdx),%rbp
-	# (uint32) a <<<= 7
-	rol	$7,%ebp
-	# x4 ^= a
-	xor	%rbp,%r9
-	# 		b = x1 + x5
-	lea	(%rdi,%r15),%rbp
-	# 		(uint32) b <<<= 7
-	rol	$7,%ebp
-	# 		x9 ^= b
-	xor	%rbp,%r10
-	# a = x0 + x4
-	lea	(%rdx,%r9),%rbp
-	# (uint32) a <<<= 9
-	rol	$9,%ebp
-	# x8 ^= a
-	xor	%rbp,%r11
-	# 		b = x5 + x9
-	lea	(%r15,%r10),%rbp
-	# 		(uint32) b <<<= 9
-	rol	$9,%ebp
-	# 		x13 ^= b
-	xor	%rbp,%r13
-	# a = x4 + x8
-	lea	(%r9,%r11),%rbp
-	# (uint32) a <<<= 13
-	rol	$13,%ebp
-	# x12 ^= a
-	xor	%rbp,%r14
-	# 		b = x9 + x13
-	lea	(%r10,%r13),%rbp
-	# 		(uint32) b <<<= 13
-	rol	$13,%ebp
-	# 		x1 ^= b
-	xor	%rbp,%rdi
-	# a = x8 + x12
-	lea	(%r11,%r14),%rbp
-	# (uint32) a <<<= 18
-	rol	$18,%ebp
-	# x0 ^= a
-	xor	%rbp,%rdx
-	# 		b = x13 + x1
-	lea	(%r13,%rdi),%rbp
-	# 		(uint32) b <<<= 18
-	rol	$18,%ebp
-	# 		x5 ^= b
-	xor	%rbp,%r15
-	# 				x10 = x10_stack
-	movq	168(%rsp),%rbp
-	# 		x5_stack = x5
-	movq	%r15,160(%rsp)
-	# 				c = x6 + x10
-	lea	(%rax,%rbp),%r15
-	# 				(uint32) c <<<= 7
-	rol	$7,%r15d
-	# 				x14 ^= c
-	xor	%r15,%rbx
-	# 				c = x10 + x14
-	lea	(%rbp,%rbx),%r15
-	# 				(uint32) c <<<= 9
-	rol	$9,%r15d
-	# 				x2 ^= c
-	xor	%r15,%rcx
-	# 				c = x14 + x2
-	lea	(%rbx,%rcx),%r15
-	# 				(uint32) c <<<= 13
-	rol	$13,%r15d
-	# 				x6 ^= c
-	xor	%r15,%rax
-	# 				c = x2 + x6
-	lea	(%rcx,%rax),%r15
-	# 				(uint32) c <<<= 18
-	rol	$18,%r15d
-	# 				x10 ^= c
-	xor	%r15,%rbp
-	# 						x15 = x15_stack
-	movq	176(%rsp),%r15
-	# 				x10_stack = x10
-	movq	%rbp,168(%rsp)
-	# 						d = x11 + x15
-	lea	(%r12,%r15),%rbp
-	# 						(uint32) d <<<= 7
-	rol	$7,%ebp
-	# 						x3 ^= d
-	xor	%rbp,%rsi
-	# 						d = x15 + x3
-	lea	(%r15,%rsi),%rbp
-	# 						(uint32) d <<<= 9
-	rol	$9,%ebp
-	# 						x7 ^= d
-	xor	%rbp,%r8
-	# 						d = x3 + x7
-	lea	(%rsi,%r8),%rbp
-	# 						(uint32) d <<<= 13
-	rol	$13,%ebp
-	# 						x11 ^= d
-	xor	%rbp,%r12
-	# 						d = x7 + x11
-	lea	(%r8,%r12),%rbp
-	# 						(uint32) d <<<= 18
-	rol	$18,%ebp
-	# 						x15 ^= d
-	xor	%rbp,%r15
-	# 						x15_stack = x15
-	movq	%r15,176(%rsp)
-	# 		x5 = x5_stack
-	movq	160(%rsp),%r15
-	# a = x3 + x0
-	lea	(%rsi,%rdx),%rbp
-	# (uint32) a <<<= 7
-	rol	$7,%ebp
-	# x1 ^= a
-	xor	%rbp,%rdi
-	# 		b = x4 + x5
-	lea	(%r9,%r15),%rbp
-	# 		(uint32) b <<<= 7
-	rol	$7,%ebp
-	# 		x6 ^= b
-	xor	%rbp,%rax
-	# a = x0 + x1
-	lea	(%rdx,%rdi),%rbp
-	# (uint32) a <<<= 9
-	rol	$9,%ebp
-	# x2 ^= a
-	xor	%rbp,%rcx
-	# 		b = x5 + x6
-	lea	(%r15,%rax),%rbp
-	# 		(uint32) b <<<= 9
-	rol	$9,%ebp
-	# 		x7 ^= b
-	xor	%rbp,%r8
-	# a = x1 + x2
-	lea	(%rdi,%rcx),%rbp
-	# (uint32) a <<<= 13
-	rol	$13,%ebp
-	# x3 ^= a
-	xor	%rbp,%rsi
-	# 		b = x6 + x7
-	lea	(%rax,%r8),%rbp
-	# 		(uint32) b <<<= 13
-	rol	$13,%ebp
-	# 		x4 ^= b
-	xor	%rbp,%r9
-	# a = x2 + x3
-	lea	(%rcx,%rsi),%rbp
-	# (uint32) a <<<= 18
-	rol	$18,%ebp
-	# x0 ^= a
-	xor	%rbp,%rdx
-	# 		b = x7 + x4
-	lea	(%r8,%r9),%rbp
-	# 		(uint32) b <<<= 18
-	rol	$18,%ebp
-	# 		x5 ^= b
-	xor	%rbp,%r15
-	# 				x10 = x10_stack
-	movq	168(%rsp),%rbp
-	# 		x5_stack = x5
-	movq	%r15,160(%rsp)
-	# 				c = x9 + x10
-	lea	(%r10,%rbp),%r15
-	# 				(uint32) c <<<= 7
-	rol	$7,%r15d
-	# 				x11 ^= c
-	xor	%r15,%r12
-	# 				c = x10 + x11
-	lea	(%rbp,%r12),%r15
-	# 				(uint32) c <<<= 9
-	rol	$9,%r15d
-	# 				x8 ^= c
-	xor	%r15,%r11
-	# 				c = x11 + x8
-	lea	(%r12,%r11),%r15
-	# 				(uint32) c <<<= 13
-	rol	$13,%r15d
-	# 				x9 ^= c
-	xor	%r15,%r10
-	# 				c = x8 + x9
-	lea	(%r11,%r10),%r15
-	# 				(uint32) c <<<= 18
-	rol	$18,%r15d
-	# 				x10 ^= c
-	xor	%r15,%rbp
-	# 						x15 = x15_stack
-	movq	176(%rsp),%r15
-	# 				x10_stack = x10
-	movq	%rbp,168(%rsp)
-	# 						d = x14 + x15
-	lea	(%rbx,%r15),%rbp
-	# 						(uint32) d <<<= 7
-	rol	$7,%ebp
-	# 						x12 ^= d
-	xor	%rbp,%r14
-	# 						d = x15 + x12
-	lea	(%r15,%r14),%rbp
-	# 						(uint32) d <<<= 9
-	rol	$9,%ebp
-	# 						x13 ^= d
-	xor	%rbp,%r13
-	# 						d = x12 + x13
-	lea	(%r14,%r13),%rbp
-	# 						(uint32) d <<<= 13
-	rol	$13,%ebp
-	# 						x14 ^= d
-	xor	%rbp,%rbx
-	# 						d = x13 + x14
-	lea	(%r13,%rbx),%rbp
-	# 						(uint32) d <<<= 18
-	rol	$18,%ebp
-	# 						x15 ^= d
-	xor	%rbp,%r15
-	# 						x15_stack = x15
-	movq	%r15,176(%rsp)
-	# 		x5 = x5_stack
-	movq	160(%rsp),%r15
-	# a = x12 + x0
-	lea	(%r14,%rdx),%rbp
-	# (uint32) a <<<= 7
-	rol	$7,%ebp
-	# x4 ^= a
-	xor	%rbp,%r9
-	# 		b = x1 + x5
-	lea	(%rdi,%r15),%rbp
-	# 		(uint32) b <<<= 7
-	rol	$7,%ebp
-	# 		x9 ^= b
-	xor	%rbp,%r10
-	# a = x0 + x4
-	lea	(%rdx,%r9),%rbp
-	# (uint32) a <<<= 9
-	rol	$9,%ebp
-	# x8 ^= a
-	xor	%rbp,%r11
-	# 		b = x5 + x9
-	lea	(%r15,%r10),%rbp
-	# 		(uint32) b <<<= 9
-	rol	$9,%ebp
-	# 		x13 ^= b
-	xor	%rbp,%r13
-	# a = x4 + x8
-	lea	(%r9,%r11),%rbp
-	# (uint32) a <<<= 13
-	rol	$13,%ebp
-	# x12 ^= a
-	xor	%rbp,%r14
-	# 		b = x9 + x13
-	lea	(%r10,%r13),%rbp
-	# 		(uint32) b <<<= 13
-	rol	$13,%ebp
-	# 		x1 ^= b
-	xor	%rbp,%rdi
-	# a = x8 + x12
-	lea	(%r11,%r14),%rbp
-	# (uint32) a <<<= 18
-	rol	$18,%ebp
-	# x0 ^= a
-	xor	%rbp,%rdx
-	# 		b = x13 + x1
-	lea	(%r13,%rdi),%rbp
-	# 		(uint32) b <<<= 18
-	rol	$18,%ebp
-	# 		x5 ^= b
-	xor	%rbp,%r15
-	# 				x10 = x10_stack
-	movq	168(%rsp),%rbp
-	# 		x5_stack = x5
-	movq	%r15,160(%rsp)
-	# 				c = x6 + x10
-	lea	(%rax,%rbp),%r15
-	# 				(uint32) c <<<= 7
-	rol	$7,%r15d
-	# 				x14 ^= c
-	xor	%r15,%rbx
-	# 				c = x10 + x14
-	lea	(%rbp,%rbx),%r15
-	# 				(uint32) c <<<= 9
-	rol	$9,%r15d
-	# 				x2 ^= c
-	xor	%r15,%rcx
-	# 				c = x14 + x2
-	lea	(%rbx,%rcx),%r15
-	# 				(uint32) c <<<= 13
-	rol	$13,%r15d
-	# 				x6 ^= c
-	xor	%r15,%rax
-	# 				c = x2 + x6
-	lea	(%rcx,%rax),%r15
-	# 				(uint32) c <<<= 18
-	rol	$18,%r15d
-	# 				x10 ^= c
-	xor	%r15,%rbp
-	# 						x15 = x15_stack
-	movq	176(%rsp),%r15
-	# 				x10_stack = x10
-	movq	%rbp,168(%rsp)
-	# 						d = x11 + x15
-	lea	(%r12,%r15),%rbp
-	# 						(uint32) d <<<= 7
-	rol	$7,%ebp
-	# 						x3 ^= d
-	xor	%rbp,%rsi
-	# 						d = x15 + x3
-	lea	(%r15,%rsi),%rbp
-	# 						(uint32) d <<<= 9
-	rol	$9,%ebp
-	# 						x7 ^= d
-	xor	%rbp,%r8
-	# 						d = x3 + x7
-	lea	(%rsi,%r8),%rbp
-	# 						(uint32) d <<<= 13
-	rol	$13,%ebp
-	# 						x11 ^= d
-	xor	%rbp,%r12
-	# 						d = x7 + x11
-	lea	(%r8,%r12),%rbp
-	# 						(uint32) d <<<= 18
-	rol	$18,%ebp
-	# 						x15 ^= d
-	xor	%rbp,%r15
-	# 						x15_stack = x15
-	movq	%r15,176(%rsp)
-	# 		x5 = x5_stack
-	movq	160(%rsp),%r15
-	# a = x3 + x0
-	lea	(%rsi,%rdx),%rbp
-	# (uint32) a <<<= 7
-	rol	$7,%ebp
-	# x1 ^= a
-	xor	%rbp,%rdi
-	# 		b = x4 + x5
-	lea	(%r9,%r15),%rbp
-	# 		(uint32) b <<<= 7
-	rol	$7,%ebp
-	# 		x6 ^= b
-	xor	%rbp,%rax
-	# a = x0 + x1
-	lea	(%rdx,%rdi),%rbp
-	# (uint32) a <<<= 9
-	rol	$9,%ebp
-	# x2 ^= a
-	xor	%rbp,%rcx
-	# 		b = x5 + x6
-	lea	(%r15,%rax),%rbp
-	# 		(uint32) b <<<= 9
-	rol	$9,%ebp
-	# 		x7 ^= b
-	xor	%rbp,%r8
-	# a = x1 + x2
-	lea	(%rdi,%rcx),%rbp
-	# (uint32) a <<<= 13
-	rol	$13,%ebp
-	# x3 ^= a
-	xor	%rbp,%rsi
-	# 		b = x6 + x7
-	lea	(%rax,%r8),%rbp
-	# 		(uint32) b <<<= 13
-	rol	$13,%ebp
-	# 		x4 ^= b
-	xor	%rbp,%r9
-	# a = x2 + x3
-	lea	(%rcx,%rsi),%rbp
-	# (uint32) a <<<= 18
-	rol	$18,%ebp
-	# x0 ^= a
-	xor	%rbp,%rdx
-	# 		b = x7 + x4
-	lea	(%r8,%r9),%rbp
-	# 		(uint32) b <<<= 18
-	rol	$18,%ebp
-	# 		x5 ^= b
-	xor	%rbp,%r15
-	# 				x10 = x10_stack
-	movq	168(%rsp),%rbp
-	# 		x5_stack = x5
-	movq	%r15,160(%rsp)
-	# 				c = x9 + x10
-	lea	(%r10,%rbp),%r15
-	# 				(uint32) c <<<= 7
-	rol	$7,%r15d
-	# 				x11 ^= c
-	xor	%r15,%r12
-	# 				c = x10 + x11
-	lea	(%rbp,%r12),%r15
-	# 				(uint32) c <<<= 9
-	rol	$9,%r15d
-	# 				x8 ^= c
-	xor	%r15,%r11
-	# 				c = x11 + x8
-	lea	(%r12,%r11),%r15
-	# 				(uint32) c <<<= 13
-	rol	$13,%r15d
-	# 				x9 ^= c
-	xor	%r15,%r10
-	# 				c = x8 + x9
-	lea	(%r11,%r10),%r15
-	# 				(uint32) c <<<= 18
-	rol	$18,%r15d
-	# 				x10 ^= c
-	xor	%r15,%rbp
-	# 						x15 = x15_stack
-	movq	176(%rsp),%r15
-	# 				x10_stack = x10
-	movq	%rbp,168(%rsp)
-	# 						d = x14 + x15
-	lea	(%rbx,%r15),%rbp
-	# 						(uint32) d <<<= 7
-	rol	$7,%ebp
-	# 						x12 ^= d
-	xor	%rbp,%r14
-	# 						d = x15 + x12
-	lea	(%r15,%r14),%rbp
-	# 						(uint32) d <<<= 9
-	rol	$9,%ebp
-	# 						x13 ^= d
-	xor	%rbp,%r13
-	# 						d = x12 + x13
-	lea	(%r14,%r13),%rbp
-	# 						(uint32) d <<<= 13
-	rol	$13,%ebp
-	# 						x14 ^= d
-	xor	%rbp,%rbx
-	# 						d = x13 + x14
-	lea	(%r13,%rbx),%rbp
-	# 						(uint32) d <<<= 18
-	rol	$18,%ebp
-	# 						x15 ^= d
-	xor	%rbp,%r15
-	# 						x15_stack = x15
-	movq	%r15,176(%rsp)
-	#   i = i_backup
-	movq	184(%rsp),%r15
-	#                  unsigned>? i -= 4
-	sub	$4,%r15
-	# comment:fp stack unchanged by jump
-	# goto mainloop if unsigned>
-	ja	._mainloop
-	#   (uint32) x2 += j2
-	addl	64(%rsp),%ecx
-	#   x3 <<= 32
-	shl	$32,%rsi
-	#   x3 += j2
-	addq	64(%rsp),%rsi
-	#   (uint64) x3 >>= 32
-	shr	$32,%rsi
-	#   x3 <<= 32
-	shl	$32,%rsi
-	#   x2 += x3
-	add	%rsi,%rcx
-	#   (uint32) x6 += j6
-	addl	80(%rsp),%eax
-	#   x7 <<= 32
-	shl	$32,%r8
-	#   x7 += j6
-	addq	80(%rsp),%r8
-	#   (uint64) x7 >>= 32
-	shr	$32,%r8
-	#   x7 <<= 32
-	shl	$32,%r8
-	#   x6 += x7
-	add	%r8,%rax
-	#   (uint32) x8 += j8
-	addl	88(%rsp),%r11d
-	#   x9 <<= 32
-	shl	$32,%r10
-	#   x9 += j8
-	addq	88(%rsp),%r10
-	#   (uint64) x9 >>= 32
-	shr	$32,%r10
-	#   x9 <<= 32
-	shl	$32,%r10
-	#   x8 += x9
-	add	%r10,%r11
-	#   (uint32) x12 += j12
-	addl	104(%rsp),%r14d
-	#   x13 <<= 32
-	shl	$32,%r13
-	#   x13 += j12
-	addq	104(%rsp),%r13
-	#   (uint64) x13 >>= 32
-	shr	$32,%r13
-	#   x13 <<= 32
-	shl	$32,%r13
-	#   x12 += x13
-	add	%r13,%r14
-	#   (uint32) x0 += j0
-	addl	56(%rsp),%edx
-	#   x1 <<= 32
-	shl	$32,%rdi
-	#   x1 += j0
-	addq	56(%rsp),%rdi
-	#   (uint64) x1 >>= 32
-	shr	$32,%rdi
-	#   x1 <<= 32
-	shl	$32,%rdi
-	#   x0 += x1
-	add	%rdi,%rdx
-	#   x5 = x5_stack
-	movq	160(%rsp),%rdi
-	#   (uint32) x4 += j4
-	addl	72(%rsp),%r9d
-	#   x5 <<= 32
-	shl	$32,%rdi
-	#   x5 += j4
-	addq	72(%rsp),%rdi
-	#   (uint64) x5 >>= 32
-	shr	$32,%rdi
-	#   x5 <<= 32
-	shl	$32,%rdi
-	#   x4 += x5
-	add	%rdi,%r9
-	#   x10 = x10_stack
-	movq	168(%rsp),%r8
-	#   (uint32) x10 += j10
-	addl	96(%rsp),%r8d
-	#   x11 <<= 32
-	shl	$32,%r12
-	#   x11 += j10
-	addq	96(%rsp),%r12
-	#   (uint64) x11 >>= 32
-	shr	$32,%r12
-	#   x11 <<= 32
-	shl	$32,%r12
-	#   x10 += x11
-	add	%r12,%r8
-	#   x15 = x15_stack
-	movq	176(%rsp),%rdi
-	#   (uint32) x14 += j14
-	addl	112(%rsp),%ebx
-	#   x15 <<= 32
-	shl	$32,%rdi
-	#   x15 += j14
-	addq	112(%rsp),%rdi
-	#   (uint64) x15 >>= 32
-	shr	$32,%rdi
-	#   x15 <<= 32
-	shl	$32,%rdi
-	#   x14 += x15
-	add	%rdi,%rbx
-	#   out = out_backup
-	movq	136(%rsp),%rdi
-	#   m = m_backup
-	movq	144(%rsp),%rsi
-	#   x0 ^= *(uint64 *) (m + 0)
-	xorq	0(%rsi),%rdx
-	#   *(uint64 *) (out + 0) = x0
-	movq	%rdx,0(%rdi)
-	#   x2 ^= *(uint64 *) (m + 8)
-	xorq	8(%rsi),%rcx
-	#   *(uint64 *) (out + 8) = x2
-	movq	%rcx,8(%rdi)
-	#   x4 ^= *(uint64 *) (m + 16)
-	xorq	16(%rsi),%r9
-	#   *(uint64 *) (out + 16) = x4
-	movq	%r9,16(%rdi)
-	#   x6 ^= *(uint64 *) (m + 24)
-	xorq	24(%rsi),%rax
-	#   *(uint64 *) (out + 24) = x6
-	movq	%rax,24(%rdi)
-	#   x8 ^= *(uint64 *) (m + 32)
-	xorq	32(%rsi),%r11
-	#   *(uint64 *) (out + 32) = x8
-	movq	%r11,32(%rdi)
-	#   x10 ^= *(uint64 *) (m + 40)
-	xorq	40(%rsi),%r8
-	#   *(uint64 *) (out + 40) = x10
-	movq	%r8,40(%rdi)
-	#   x12 ^= *(uint64 *) (m + 48)
-	xorq	48(%rsi),%r14
-	#   *(uint64 *) (out + 48) = x12
-	movq	%r14,48(%rdi)
-	#   x14 ^= *(uint64 *) (m + 56)
-	xorq	56(%rsi),%rbx
-	#   *(uint64 *) (out + 56) = x14
-	movq	%rbx,56(%rdi)
-	#   bytes = bytes_backup
-	movq	152(%rsp),%rdx
-	#   in8 = j8
-	movq	88(%rsp),%rcx
-	#   in8 += 1
-	add	$1,%rcx
-	#   j8 = in8
-	movq	%rcx,88(%rsp)
-	#                          unsigned>? unsigned<? bytes - 64
-	cmp	$64,%rdx
-	# comment:fp stack unchanged by jump
-	#   goto bytesatleast65 if unsigned>
-	ja	._bytesatleast65
-	# comment:fp stack unchanged by jump
-	#     goto bytesatleast64 if !unsigned<
-	jae	._bytesatleast64
-	#       m = out
-	mov	%rdi,%rsi
-	#       out = ctarget
-	movq	128(%rsp),%rdi
-	#       i = bytes
-	mov	%rdx,%rcx
-	#       while (i) { *out++ = *m++; --i }
-	rep	movsb
-	# comment:fp stack unchanged by fallthrough
-#     bytesatleast64:
-._bytesatleast64:
-	#     x = x_backup
-	movq	120(%rsp),%rdi
-	#     in8 = j8
-	movq	88(%rsp),%rsi
-	#     *(uint64 *) (x + 32) = in8
-	movq	%rsi,32(%rdi)
-	#     r11 = r11_stack
-	movq	0(%rsp),%r11
-	#     r12 = r12_stack
-	movq	8(%rsp),%r12
-	#     r13 = r13_stack
-	movq	16(%rsp),%r13
-	#     r14 = r14_stack
-	movq	24(%rsp),%r14
-	#     r15 = r15_stack
-	movq	32(%rsp),%r15
-	#     rbx = rbx_stack
-	movq	40(%rsp),%rbx
-	#     rbp = rbp_stack
-	movq	48(%rsp),%rbp
-	# comment:fp stack unchanged by fallthrough
-#     done:
-._done:
-	#     leave
-	add	%r11,%rsp
-	mov	%rdi,%rax
-	mov	%rsi,%rdx
-	ret
-#   bytesatleast65:
-._bytesatleast65:
-	#   bytes -= 64
-	sub	$64,%rdx
-	#   out += 64
-	add	$64,%rdi
-	#   m += 64
-	add	$64,%rsi
-	# comment:fp stack unchanged by jump
-	# goto bytesatleast1
-	jmp	._bytesatleast1
-ENDPROC(salsa20_encrypt_bytes)
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
deleted file mode 100644
index b07d7d959806..000000000000
--- a/arch/x86/crypto/salsa20_glue.c
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- * Glue code for optimized assembly version of  Salsa20.
- *
- * Copyright (c) 2007 Tan Swee Heng <thesweeheng@gmail.com>
- *
- * The assembly codes are public domain assembly codes written by Daniel. J.
- * Bernstein <djb@cr.yp.to>. The codes are modified to include indentation
- * and to remove extraneous comments and functions that are not needed.
- * - i586 version, renamed as salsa20-i586-asm_32.S
- *   available from <http://cr.yp.to/snuffle/salsa20/x86-pm/salsa20.s>
- * - x86-64 version, renamed as salsa20-x86_64-asm_64.S
- *   available from <http://cr.yp.to/snuffle/salsa20/amd64-3/salsa20.s>
- *
- * Also modified to set up the initial state using the generic C code rather
- * than in assembly.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <asm/unaligned.h>
-#include <crypto/internal/skcipher.h>
-#include <crypto/salsa20.h>
-#include <linux/module.h>
-
-asmlinkage void salsa20_encrypt_bytes(u32 state[16], const u8 *src, u8 *dst,
-				      u32 bytes);
-
-static int salsa20_asm_crypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	const struct salsa20_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	u32 state[16];
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, true);
-
-	crypto_salsa20_init(state, ctx, walk.iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		salsa20_encrypt_bytes(state, walk.src.virt.addr,
-				      walk.dst.virt.addr, nbytes);
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static struct skcipher_alg alg = {
-	.base.cra_name		= "salsa20",
-	.base.cra_driver_name	= "salsa20-asm",
-	.base.cra_priority	= 200,
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct salsa20_ctx),
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= SALSA20_MIN_KEY_SIZE,
-	.max_keysize		= SALSA20_MAX_KEY_SIZE,
-	.ivsize			= SALSA20_IV_SIZE,
-	.chunksize		= SALSA20_BLOCK_SIZE,
-	.setkey			= crypto_salsa20_setkey,
-	.encrypt		= salsa20_asm_crypt,
-	.decrypt		= salsa20_asm_crypt,
-};
-
-static int __init init(void)
-{
-	return crypto_register_skcipher(&alg);
-}
-
-static void __exit fini(void)
-{
-	crypto_unregister_skcipher(&alg);
-}
-
-module_init(init);
-module_exit(fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)");
-MODULE_ALIAS_CRYPTO("salsa20");
-MODULE_ALIAS_CRYPTO("salsa20-asm");
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 9af927e59d49..9de7f1e1dede 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -84,13 +84,13 @@ ENTRY(entry_SYSENTER_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	pushq   $0			/* pt_regs->r8  = 0 */
+	pushq   %r8			/* pt_regs->r8 */
 	xorl	%r8d, %r8d		/* nospec   r8 */
-	pushq   $0			/* pt_regs->r9  = 0 */
+	pushq   %r9			/* pt_regs->r9 */
 	xorl	%r9d, %r9d		/* nospec   r9 */
-	pushq   $0			/* pt_regs->r10 = 0 */
+	pushq   %r10			/* pt_regs->r10 */
 	xorl	%r10d, %r10d		/* nospec   r10 */
-	pushq   $0			/* pt_regs->r11 = 0 */
+	pushq   %r11			/* pt_regs->r11 */
 	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	xorl	%ebx, %ebx		/* nospec   rbx */
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index d6b27dab1b30..14a2f996e543 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -396,3 +396,4 @@
 382	i386	pkey_free		sys_pkey_free			__ia32_sys_pkey_free
 383	i386	statx			sys_statx			__ia32_sys_statx
 384	i386	arch_prctl		sys_arch_prctl			__ia32_compat_sys_arch_prctl
+385	i386	io_pgetevents		sys_io_pgetevents		__ia32_compat_sys_io_pgetevents
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe42666d0c..cd36232ab62f 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,7 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index d998a487c9b1..261802b1cc50 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -44,14 +44,14 @@ obj-y += $(vdso_img_objs)
 targets += $(vdso_img_cfiles)
 targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
 
-export CPPFLAGS_vdso.lds += -P -C
+CPPFLAGS_vdso.lds += -P -C
 
 VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 			-Wl,--no-undefined \
 			-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
 			$(DISABLE_LTO)
 
-$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
+$(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
@@ -100,11 +100,8 @@ VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
 			   -Wl,-z,max-page-size=4096 \
 			   -Wl,-z,common-page-size=4096
 
-# 64-bit objects to re-brand as x32
-vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y))
-
 # x32-rebranded versions
-vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o)
+vobjx32s-y := $(vobjs-y:.o=-x32.o)
 
 # same thing, but in the output directory
 vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
@@ -122,7 +119,7 @@ $(obj)/%.so: OBJCOPYFLAGS := -S
 $(obj)/%.so: $(obj)/%.so.dbg
 	$(call if_changed,objcopy)
 
-$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
+$(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
 	$(call if_changed,vdso)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
diff --git a/arch/x86/entry/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
deleted file mode 100644
index 541468e25265..000000000000
--- a/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
+++ /dev/null
@@ -1 +0,0 @@
-#include "../vdso-fakesections.c"
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 70b7845434cb..7782cdbcd67d 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -107,7 +107,7 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
 		thread->cr2		= ptr;
 		thread->trap_nr		= X86_TRAP_PF;
 
-		memset(&info, 0, sizeof(info));
+		clear_siginfo(&info);
 		info.si_signo		= SIGSEGV;
 		info.si_errno		= 0;
 		info.si_code		= SEGV_MAPERR;
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 786fd875de92..4b98101209a1 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -889,7 +889,7 @@ static void force_ibs_eilvt_setup(void)
 	if (!ibs_eilvt_valid())
 		goto out;
 
-	pr_info("IBS: LVT offset %d assigned\n", offset);
+	pr_info("LVT offset %d assigned\n", offset);
 
 	return;
 out:
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index f5cbbba99283..981ba5e8241b 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -19,6 +19,7 @@
 #include <asm/cpufeature.h>
 #include <asm/perf_event.h>
 #include <asm/msr.h>
+#include <asm/smp.h>
 
 #define NUM_COUNTERS_NB		4
 #define NUM_COUNTERS_L2		4
@@ -399,26 +400,8 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
 	}
 
 	if (amd_uncore_llc) {
-		unsigned int apicid = cpu_data(cpu).apicid;
-		unsigned int nshared, subleaf, prev_eax = 0;
-
 		uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
-		/*
-		 * Iterate over Cache Topology Definition leaves until no
-		 * more cache descriptions are available.
-		 */
-		for (subleaf = 0; subleaf < 5; subleaf++) {
-			cpuid_count(0x8000001d, subleaf, &eax, &ebx, &ecx, &edx);
-
-			/* EAX[0:4] gives type of cache */
-			if (!(eax & 0x1f))
-				break;
-
-			prev_eax = eax;
-		}
-		nshared = ((prev_eax >> 14) & 0xfff) + 1;
-
-		uncore->id = apicid - (apicid % nshared);
+		uncore->id = per_cpu(cpu_llc_id, cpu);
 
 		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
 		*per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index a6006e7bb729..6e461fb1e0d4 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -27,6 +27,7 @@
 #include <linux/cpu.h>
 #include <linux/bitops.h>
 #include <linux/device.h>
+#include <linux/nospec.h>
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
@@ -304,17 +305,20 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
 
 	config = attr->config;
 
-	cache_type = (config >>  0) & 0xff;
+	cache_type = (config >> 0) & 0xff;
 	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
 		return -EINVAL;
+	cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX);
 
 	cache_op = (config >>  8) & 0xff;
 	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
 		return -EINVAL;
+	cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX);
 
 	cache_result = (config >> 16) & 0xff;
 	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
 		return -EINVAL;
+	cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX);
 
 	val = hw_cache_event_ids[cache_type][cache_op][cache_result];
 
@@ -421,6 +425,8 @@ int x86_setup_perfctr(struct perf_event *event)
 	if (attr->config >= x86_pmu.max_events)
 		return -EINVAL;
 
+	attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events);
+
 	/*
 	 * The generic map:
 	 */
@@ -2391,7 +2397,7 @@ static unsigned long get_segment_base(unsigned int segment)
 
 #ifdef CONFIG_IA32_EMULATION
 
-#include <asm/compat.h>
+#include <linux/compat.h>
 
 static inline int
 perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 607bf565a90c..707b2a96e516 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3339,7 +3339,8 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	cpuc->lbr_sel = NULL;
 
-	flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
+	if (x86_pmu.version > 1)
+		flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
 
 	if (!cpuc->shared_regs)
 		return;
@@ -3502,6 +3503,8 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_dying		= intel_pmu_cpu_dying,
 };
 
+static struct attribute *intel_pmu_attrs[];
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -3533,6 +3536,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.format_attrs		= intel_arch3_formats_attr,
 	.events_sysfs_show	= intel_event_sysfs_show,
 
+	.attrs			= intel_pmu_attrs,
+
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
@@ -3911,8 +3916,6 @@ __init int intel_pmu_init(void)
 
 	x86_pmu.max_pebs_events		= min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
 
-
-	x86_pmu.attrs			= intel_pmu_attrs;
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
 	 * assume at least 3 events, when not running in a hypervisor:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9aca448bb8e6..9f8084f18d58 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -92,6 +92,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/perf_event.h>
+#include <linux/nospec.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include "../perf_event.h"
@@ -302,6 +303,7 @@ static int cstate_pmu_event_init(struct perf_event *event)
 	} else if (event->pmu == &cstate_pkg_pmu) {
 		if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
 			return -EINVAL;
+		cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
 		if (!pkg_msr[cfg].attr)
 			return -EINVAL;
 		event->hw.event_base = pkg_msr[cfg].msr;
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 3b993942a0e4..8d016ce5b80d 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1194,7 +1194,7 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
 		    filter->action == PERF_ADDR_FILTER_ACTION_START)
 			return -EOPNOTSUPP;
 
-		if (!filter->inode) {
+		if (!filter->path.dentry) {
 			if (!valid_kernel_ip(filter->offset))
 				return -EINVAL;
 
@@ -1221,7 +1221,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
 		return;
 
 	list_for_each_entry(filter, &head->list, entry) {
-		if (filter->inode && !offs[range]) {
+		if (filter->path.dentry && !offs[range]) {
 			msr_a = msr_b = 0;
 		} else {
 			/* apply the offset */
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index a7956fc7ca1d..15b07379e72d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -203,7 +203,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box,
 	hwc->idx = idx;
 	hwc->last_tag = ++box->tags[idx];
 
-	if (hwc->idx == UNCORE_PMC_IDX_FIXED) {
+	if (uncore_pmc_fixed(hwc->idx)) {
 		hwc->event_base = uncore_fixed_ctr(box);
 		hwc->config_base = uncore_fixed_ctl(box);
 		return;
@@ -218,7 +218,9 @@ void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *e
 	u64 prev_count, new_count, delta;
 	int shift;
 
-	if (event->hw.idx >= UNCORE_PMC_IDX_FIXED)
+	if (uncore_pmc_freerunning(event->hw.idx))
+		shift = 64 - uncore_freerunning_bits(box, event);
+	else if (uncore_pmc_fixed(event->hw.idx))
 		shift = 64 - uncore_fixed_ctr_bits(box);
 	else
 		shift = 64 - uncore_perf_ctr_bits(box);
@@ -449,15 +451,30 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	return ret ? -EINVAL : 0;
 }
 
-static void uncore_pmu_event_start(struct perf_event *event, int flags)
+void uncore_pmu_event_start(struct perf_event *event, int flags)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	int idx = event->hw.idx;
 
-	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+	if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
 		return;
 
-	if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
+	/*
+	 * Free running counter is read-only and always active.
+	 * Use the current counter value as start point.
+	 * There is no overflow interrupt for free running counter.
+	 * Use hrtimer to periodically poll the counter to avoid overflow.
+	 */
+	if (uncore_pmc_freerunning(event->hw.idx)) {
+		list_add_tail(&event->active_entry, &box->active_list);
+		local64_set(&event->hw.prev_count,
+			    uncore_read_counter(box, event));
+		if (box->n_active++ == 0)
+			uncore_pmu_start_hrtimer(box);
+		return;
+	}
+
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
 		return;
 
 	event->hw.state = 0;
@@ -474,11 +491,20 @@ static void uncore_pmu_event_start(struct perf_event *event, int flags)
 	}
 }
 
-static void uncore_pmu_event_stop(struct perf_event *event, int flags)
+void uncore_pmu_event_stop(struct perf_event *event, int flags)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	struct hw_perf_event *hwc = &event->hw;
 
+	/* Cannot disable free running counter which is read-only */
+	if (uncore_pmc_freerunning(hwc->idx)) {
+		list_del(&event->active_entry);
+		if (--box->n_active == 0)
+			uncore_pmu_cancel_hrtimer(box);
+		uncore_perf_event_update(box, event);
+		return;
+	}
+
 	if (__test_and_clear_bit(hwc->idx, box->active_mask)) {
 		uncore_disable_event(box, event);
 		box->n_active--;
@@ -502,7 +528,7 @@ static void uncore_pmu_event_stop(struct perf_event *event, int flags)
 	}
 }
 
-static int uncore_pmu_event_add(struct perf_event *event, int flags)
+int uncore_pmu_event_add(struct perf_event *event, int flags)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	struct hw_perf_event *hwc = &event->hw;
@@ -512,6 +538,17 @@ static int uncore_pmu_event_add(struct perf_event *event, int flags)
 	if (!box)
 		return -ENODEV;
 
+	/*
+	 * The free funning counter is assigned in event_init().
+	 * The free running counter event and free running counter
+	 * are 1:1 mapped. It doesn't need to be tracked in event_list.
+	 */
+	if (uncore_pmc_freerunning(hwc->idx)) {
+		if (flags & PERF_EF_START)
+			uncore_pmu_event_start(event, 0);
+		return 0;
+	}
+
 	ret = n = uncore_collect_events(box, event, false);
 	if (ret < 0)
 		return ret;
@@ -563,13 +600,21 @@ static int uncore_pmu_event_add(struct perf_event *event, int flags)
 	return 0;
 }
 
-static void uncore_pmu_event_del(struct perf_event *event, int flags)
+void uncore_pmu_event_del(struct perf_event *event, int flags)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	int i;
 
 	uncore_pmu_event_stop(event, PERF_EF_UPDATE);
 
+	/*
+	 * The event for free running counter is not tracked by event_list.
+	 * It doesn't need to force event->hw.idx = -1 to reassign the counter.
+	 * Because the event and the free running counter are 1:1 mapped.
+	 */
+	if (uncore_pmc_freerunning(event->hw.idx))
+		return;
+
 	for (i = 0; i < box->n_events; i++) {
 		if (event == box->event_list[i]) {
 			uncore_put_event_constraint(box, event);
@@ -603,6 +648,10 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
 	struct intel_uncore_box *fake_box;
 	int ret = -EINVAL, n;
 
+	/* The free running counter is always active. */
+	if (uncore_pmc_freerunning(event->hw.idx))
+		return 0;
+
 	fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
 	if (!fake_box)
 		return -ENOMEM;
@@ -690,6 +739,17 @@ static int uncore_pmu_event_init(struct perf_event *event)
 
 		/* fixed counters have event field hardcoded to zero */
 		hwc->config = 0ULL;
+	} else if (is_freerunning_event(event)) {
+		if (!check_valid_freerunning_event(box, event))
+			return -EINVAL;
+		event->hw.idx = UNCORE_PMC_IDX_FREERUNNING;
+		/*
+		 * The free running counter event and free running counter
+		 * are always 1:1 mapped.
+		 * The free running counter is always active.
+		 * Assign the free running counter here.
+		 */
+		event->hw.event_base = uncore_freerunning_counter(box, event);
 	} else {
 		hwc->config = event->attr.config &
 			      (pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32));
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 414dc7e7c950..c9e1e0bef3c3 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -12,8 +12,13 @@
 
 #define UNCORE_FIXED_EVENT		0xff
 #define UNCORE_PMC_IDX_MAX_GENERIC	8
+#define UNCORE_PMC_IDX_MAX_FIXED	1
+#define UNCORE_PMC_IDX_MAX_FREERUNNING	1
 #define UNCORE_PMC_IDX_FIXED		UNCORE_PMC_IDX_MAX_GENERIC
-#define UNCORE_PMC_IDX_MAX		(UNCORE_PMC_IDX_FIXED + 1)
+#define UNCORE_PMC_IDX_FREERUNNING	(UNCORE_PMC_IDX_FIXED + \
+					UNCORE_PMC_IDX_MAX_FIXED)
+#define UNCORE_PMC_IDX_MAX		(UNCORE_PMC_IDX_FREERUNNING + \
+					UNCORE_PMC_IDX_MAX_FREERUNNING)
 
 #define UNCORE_PCI_DEV_FULL_DATA(dev, func, type, idx)	\
 		((dev << 24) | (func << 16) | (type << 8) | idx)
@@ -35,6 +40,7 @@ struct intel_uncore_ops;
 struct intel_uncore_pmu;
 struct intel_uncore_box;
 struct uncore_event_desc;
+struct freerunning_counters;
 
 struct intel_uncore_type {
 	const char *name;
@@ -42,6 +48,7 @@ struct intel_uncore_type {
 	int num_boxes;
 	int perf_ctr_bits;
 	int fixed_ctr_bits;
+	int num_freerunning_types;
 	unsigned perf_ctr;
 	unsigned event_ctl;
 	unsigned event_mask;
@@ -59,6 +66,7 @@ struct intel_uncore_type {
 	struct intel_uncore_pmu *pmus;
 	struct intel_uncore_ops *ops;
 	struct uncore_event_desc *event_descs;
+	struct freerunning_counters *freerunning;
 	const struct attribute_group *attr_groups[4];
 	struct pmu *pmu; /* for custom pmu ops */
 };
@@ -129,6 +137,14 @@ struct uncore_event_desc {
 	const char *config;
 };
 
+struct freerunning_counters {
+	unsigned int counter_base;
+	unsigned int counter_offset;
+	unsigned int box_offset;
+	unsigned int num_counters;
+	unsigned int bits;
+};
+
 struct pci2phy_map {
 	struct list_head list;
 	int segment;
@@ -157,6 +173,16 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj,		\
 static struct kobj_attribute format_attr_##_var =			\
 	__ATTR(_name, 0444, __uncore_##_var##_show, NULL)
 
+static inline bool uncore_pmc_fixed(int idx)
+{
+	return idx == UNCORE_PMC_IDX_FIXED;
+}
+
+static inline bool uncore_pmc_freerunning(int idx)
+{
+	return idx == UNCORE_PMC_IDX_FREERUNNING;
+}
+
 static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
 {
 	return box->pmu->type->box_ctl;
@@ -214,6 +240,60 @@ static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
 	return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box);
 }
 
+
+/*
+ * In the uncore document, there is no event-code assigned to free running
+ * counters. Some events need to be defined to indicate the free running
+ * counters. The events are encoded as event-code + umask-code.
+ *
+ * The event-code for all free running counters is 0xff, which is the same as
+ * the fixed counters.
+ *
+ * The umask-code is used to distinguish a fixed counter and a free running
+ * counter, and different types of free running counters.
+ * - For fixed counters, the umask-code is 0x0X.
+ *   X indicates the index of the fixed counter, which starts from 0.
+ * - For free running counters, the umask-code uses the rest of the space.
+ *   It would bare the format of 0xXY.
+ *   X stands for the type of free running counters, which starts from 1.
+ *   Y stands for the index of free running counters of same type, which
+ *   starts from 0.
+ *
+ * For example, there are three types of IIO free running counters on Skylake
+ * server, IO CLOCKS counters, BANDWIDTH counters and UTILIZATION counters.
+ * The event-code for all the free running counters is 0xff.
+ * 'ioclk' is the first counter of IO CLOCKS. IO CLOCKS is the first type,
+ * which umask-code starts from 0x10.
+ * So 'ioclk' is encoded as event=0xff,umask=0x10
+ * 'bw_in_port2' is the third counter of BANDWIDTH counters. BANDWIDTH is
+ * the second type, which umask-code starts from 0x20.
+ * So 'bw_in_port2' is encoded as event=0xff,umask=0x22
+ */
+static inline unsigned int uncore_freerunning_idx(u64 config)
+{
+	return ((config >> 8) & 0xf);
+}
+
+#define UNCORE_FREERUNNING_UMASK_START		0x10
+
+static inline unsigned int uncore_freerunning_type(u64 config)
+{
+	return ((((config >> 8) - UNCORE_FREERUNNING_UMASK_START) >> 4) & 0xf);
+}
+
+static inline
+unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
+					struct perf_event *event)
+{
+	unsigned int type = uncore_freerunning_type(event->attr.config);
+	unsigned int idx = uncore_freerunning_idx(event->attr.config);
+	struct intel_uncore_pmu *pmu = box->pmu;
+
+	return pmu->type->freerunning[type].counter_base +
+	       pmu->type->freerunning[type].counter_offset * idx +
+	       pmu->type->freerunning[type].box_offset * pmu->pmu_idx;
+}
+
 static inline
 unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
@@ -276,11 +356,52 @@ static inline int uncore_fixed_ctr_bits(struct intel_uncore_box *box)
 	return box->pmu->type->fixed_ctr_bits;
 }
 
+static inline
+unsigned int uncore_freerunning_bits(struct intel_uncore_box *box,
+				     struct perf_event *event)
+{
+	unsigned int type = uncore_freerunning_type(event->attr.config);
+
+	return box->pmu->type->freerunning[type].bits;
+}
+
+static inline int uncore_num_freerunning(struct intel_uncore_box *box,
+					 struct perf_event *event)
+{
+	unsigned int type = uncore_freerunning_type(event->attr.config);
+
+	return box->pmu->type->freerunning[type].num_counters;
+}
+
+static inline int uncore_num_freerunning_types(struct intel_uncore_box *box,
+					       struct perf_event *event)
+{
+	return box->pmu->type->num_freerunning_types;
+}
+
+static inline bool check_valid_freerunning_event(struct intel_uncore_box *box,
+						 struct perf_event *event)
+{
+	unsigned int type = uncore_freerunning_type(event->attr.config);
+	unsigned int idx = uncore_freerunning_idx(event->attr.config);
+
+	return (type < uncore_num_freerunning_types(box, event)) &&
+	       (idx < uncore_num_freerunning(box, event));
+}
+
 static inline int uncore_num_counters(struct intel_uncore_box *box)
 {
 	return box->pmu->type->num_counters;
 }
 
+static inline bool is_freerunning_event(struct perf_event *event)
+{
+	u64 cfg = event->attr.config;
+
+	return ((cfg & UNCORE_FIXED_EVENT) == UNCORE_FIXED_EVENT) &&
+	       (((cfg >> 8) & 0xff) >= UNCORE_FREERUNNING_UMASK_START);
+}
+
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -346,6 +467,10 @@ struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_event_start(struct perf_event *event, int flags);
+void uncore_pmu_event_stop(struct perf_event *event, int flags);
+int uncore_pmu_event_add(struct perf_event *event, int flags);
+void uncore_pmu_event_del(struct perf_event *event, int flags);
 void uncore_pmu_event_read(struct perf_event *event);
 void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
 struct event_constraint *
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 93e7a8397cde..173e2674be6e 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -246,7 +246,7 @@ static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+	if (hwc->idx == UNCORE_PMC_IDX_FIXED)
 		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
 	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
 		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index aee5e8496be4..8527c3e1038b 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -285,6 +285,15 @@ static struct uncore_event_desc snb_uncore_imc_events[] = {
 #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE	0x5054
 #define SNB_UNCORE_PCI_IMC_CTR_BASE		SNB_UNCORE_PCI_IMC_DATA_READS_BASE
 
+enum perf_snb_uncore_imc_freerunning_types {
+	SNB_PCI_UNCORE_IMC_DATA		= 0,
+	SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snb_uncore_imc_freerunning[] = {
+	[SNB_PCI_UNCORE_IMC_DATA]     = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 },
+};
+
 static struct attribute *snb_uncore_imc_formats_attr[] = {
 	&format_attr_event.attr,
 	NULL,
@@ -341,9 +350,8 @@ static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf
 }
 
 /*
- * custom event_init() function because we define our own fixed, free
- * running counters, so we do not want to conflict with generic uncore
- * logic. Also simplifies processing
+ * Keep the custom event_init() function compatible with old event
+ * encoding for free running counters.
  */
 static int snb_uncore_imc_event_init(struct perf_event *event)
 {
@@ -405,11 +413,11 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 	switch (cfg) {
 	case SNB_UNCORE_PCI_IMC_DATA_READS:
 		base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
-		idx = UNCORE_PMC_IDX_FIXED;
+		idx = UNCORE_PMC_IDX_FREERUNNING;
 		break;
 	case SNB_UNCORE_PCI_IMC_DATA_WRITES:
 		base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
-		idx = UNCORE_PMC_IDX_FIXED + 1;
+		idx = UNCORE_PMC_IDX_FREERUNNING;
 		break;
 	default:
 		return -EINVAL;
@@ -430,75 +438,6 @@ static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_ev
 	return 0;
 }
 
-static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	u64 count;
-
-	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
-		return;
-
-	event->hw.state = 0;
-	box->n_active++;
-
-	list_add_tail(&event->active_entry, &box->active_list);
-
-	count = snb_uncore_imc_read_counter(box, event);
-	local64_set(&event->hw.prev_count, count);
-
-	if (box->n_active == 1)
-		uncore_pmu_start_hrtimer(box);
-}
-
-static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (!(hwc->state & PERF_HES_STOPPED)) {
-		box->n_active--;
-
-		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
-		hwc->state |= PERF_HES_STOPPED;
-
-		list_del(&event->active_entry);
-
-		if (box->n_active == 0)
-			uncore_pmu_cancel_hrtimer(box);
-	}
-
-	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
-		/*
-		 * Drain the remaining delta count out of a event
-		 * that we are disabling:
-		 */
-		uncore_perf_event_update(box, event);
-		hwc->state |= PERF_HES_UPTODATE;
-	}
-}
-
-static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (!box)
-		return -ENODEV;
-
-	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-	if (!(flags & PERF_EF_START))
-		hwc->state |= PERF_HES_ARCH;
-
-	snb_uncore_imc_event_start(event, 0);
-
-	return 0;
-}
-
-static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
-{
-	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-}
-
 int snb_pci2phy_map_init(int devid)
 {
 	struct pci_dev *dev = NULL;
@@ -530,10 +469,10 @@ int snb_pci2phy_map_init(int devid)
 static struct pmu snb_uncore_imc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= snb_uncore_imc_event_init,
-	.add		= snb_uncore_imc_event_add,
-	.del		= snb_uncore_imc_event_del,
-	.start		= snb_uncore_imc_event_start,
-	.stop		= snb_uncore_imc_event_stop,
+	.add		= uncore_pmu_event_add,
+	.del		= uncore_pmu_event_del,
+	.start		= uncore_pmu_event_start,
+	.stop		= uncore_pmu_event_stop,
 	.read		= uncore_pmu_event_read,
 };
 
@@ -552,12 +491,10 @@ static struct intel_uncore_type snb_uncore_imc = {
 	.name		= "imc",
 	.num_counters   = 2,
 	.num_boxes	= 1,
-	.fixed_ctr_bits	= 32,
-	.fixed_ctr	= SNB_UNCORE_PCI_IMC_CTR_BASE,
+	.num_freerunning_types	= SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+	.freerunning	= snb_uncore_imc_freerunning,
 	.event_descs	= snb_uncore_imc_events,
 	.format_group	= &snb_uncore_imc_format_group,
-	.perf_ctr	= SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
-	.event_mask	= SNB_UNCORE_PCI_IMC_EVENT_MASK,
 	.ops		= &snb_uncore_imc_ops,
 	.pmu		= &snb_uncore_imc_pmu,
 };
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index c98b943e58b4..87dc0263a2e1 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3028,10 +3028,27 @@ static struct intel_uncore_type bdx_uncore_cbox = {
 	.format_group		= &hswep_uncore_cbox_format_group,
 };
 
+static struct intel_uncore_type bdx_uncore_sbox = {
+	.name			= "sbox",
+	.num_counters		= 4,
+	.num_boxes		= 4,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= HSWEP_S0_MSR_PMON_CTL0,
+	.perf_ctr		= HSWEP_S0_MSR_PMON_CTR0,
+	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_S0_MSR_PMON_BOX_CTL,
+	.msr_offset		= HSWEP_SBOX_MSR_OFFSET,
+	.ops			= &hswep_uncore_sbox_msr_ops,
+	.format_group		= &hswep_uncore_sbox_format_group,
+};
+
+#define BDX_MSR_UNCORE_SBOX	3
+
 static struct intel_uncore_type *bdx_msr_uncores[] = {
 	&bdx_uncore_ubox,
 	&bdx_uncore_cbox,
 	&hswep_uncore_pcu,
+	&bdx_uncore_sbox,
 	NULL,
 };
 
@@ -3043,10 +3060,25 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
 
 void bdx_uncore_cpu_init(void)
 {
+	int pkg = topology_phys_to_logical_pkg(0);
+
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
 
+	/* BDX-DE doesn't have SBOX */
+	if (boot_cpu_data.x86_model == 86) {
+		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+	/* Detect systems with no SBOXes */
+	} else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) {
+		struct pci_dev *pdev;
+		u32 capid4;
+
+		pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3];
+		pci_read_config_dword(pdev, 0x94, &capid4);
+		if (((capid4 >> 6) & 0x3) == 0)
+			bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+	}
 	hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
 }
 
@@ -3264,6 +3296,11 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
 		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
 	},
+	{ /* PCU.3 (for Capability registers) */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   HSWEP_PCI_PCU_3),
+	},
 	{ /* end: all zeroes */ }
 };
 
@@ -3485,6 +3522,87 @@ static struct intel_uncore_type skx_uncore_iio = {
 	.format_group		= &skx_uncore_iio_format_group,
 };
 
+enum perf_uncore_iio_freerunning_type_id {
+	SKX_IIO_MSR_IOCLK			= 0,
+	SKX_IIO_MSR_BW				= 1,
+	SKX_IIO_MSR_UTIL			= 2,
+
+	SKX_IIO_FREERUNNING_TYPE_MAX,
+};
+
+
+static struct freerunning_counters skx_iio_freerunning[] = {
+	[SKX_IIO_MSR_IOCLK]	= { 0xa45, 0x1, 0x20, 1, 36 },
+	[SKX_IIO_MSR_BW]	= { 0xb00, 0x1, 0x10, 8, 36 },
+	[SKX_IIO_MSR_UTIL]	= { 0xb08, 0x1, 0x10, 8, 36 },
+};
+
+static struct uncore_event_desc skx_uncore_iio_freerunning_events[] = {
+	/* Free-Running IO CLOCKS Counter */
+	INTEL_UNCORE_EVENT_DESC(ioclk,			"event=0xff,umask=0x10"),
+	/* Free-Running IIO BANDWIDTH Counters */
+	INTEL_UNCORE_EVENT_DESC(bw_in_port0,		"event=0xff,umask=0x20"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port1,		"event=0xff,umask=0x21"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port2,		"event=0xff,umask=0x22"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port3,		"event=0xff,umask=0x23"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port0,		"event=0xff,umask=0x24"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port1,		"event=0xff,umask=0x25"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port2,		"event=0xff,umask=0x26"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port3,		"event=0xff,umask=0x27"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit,	"MiB"),
+	/* Free-running IIO UTILIZATION Counters */
+	INTEL_UNCORE_EVENT_DESC(util_in_port0,		"event=0xff,umask=0x30"),
+	INTEL_UNCORE_EVENT_DESC(util_out_port0,		"event=0xff,umask=0x31"),
+	INTEL_UNCORE_EVENT_DESC(util_in_port1,		"event=0xff,umask=0x32"),
+	INTEL_UNCORE_EVENT_DESC(util_out_port1,		"event=0xff,umask=0x33"),
+	INTEL_UNCORE_EVENT_DESC(util_in_port2,		"event=0xff,umask=0x34"),
+	INTEL_UNCORE_EVENT_DESC(util_out_port2,		"event=0xff,umask=0x35"),
+	INTEL_UNCORE_EVENT_DESC(util_in_port3,		"event=0xff,umask=0x36"),
+	INTEL_UNCORE_EVENT_DESC(util_out_port3,		"event=0xff,umask=0x37"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops skx_uncore_iio_freerunning_ops = {
+	.read_counter		= uncore_msr_read_counter,
+};
+
+static struct attribute *skx_uncore_iio_freerunning_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	NULL,
+};
+
+static const struct attribute_group skx_uncore_iio_freerunning_format_group = {
+	.name = "format",
+	.attrs = skx_uncore_iio_freerunning_formats_attr,
+};
+
+static struct intel_uncore_type skx_uncore_iio_free_running = {
+	.name			= "iio_free_running",
+	.num_counters		= 17,
+	.num_boxes		= 6,
+	.num_freerunning_types	= SKX_IIO_FREERUNNING_TYPE_MAX,
+	.freerunning		= skx_iio_freerunning,
+	.ops			= &skx_uncore_iio_freerunning_ops,
+	.event_descs		= skx_uncore_iio_freerunning_events,
+	.format_group		= &skx_uncore_iio_freerunning_format_group,
+};
+
 static struct attribute *skx_uncore_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -3558,6 +3676,7 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
 	&skx_uncore_ubox,
 	&skx_uncore_chabox,
 	&skx_uncore_iio,
+	&skx_uncore_iio_free_running,
 	&skx_uncore_irp,
 	&skx_uncore_pcu,
 	NULL,
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index e7edf19e64c2..b4771a6ddbc1 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/perf_event.h>
+#include <linux/nospec.h>
 #include <asm/intel-family.h>
 
 enum perf_msr_id {
@@ -158,9 +159,6 @@ static int msr_event_init(struct perf_event *event)
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
-	if (cfg >= PERF_MSR_EVENT_MAX)
-		return -EINVAL;
-
 	/* unsupported modes and filters */
 	if (event->attr.exclude_user   ||
 	    event->attr.exclude_kernel ||
@@ -171,6 +169,11 @@ static int msr_event_init(struct perf_event *event)
 	    event->attr.sample_period) /* no sampling */
 		return -EINVAL;
 
+	if (cfg >= PERF_MSR_EVENT_MAX)
+		return -EINVAL;
+
+	cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX);
+
 	if (!msr[cfg].attr)
 		return -EINVAL;
 
diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 367a8203cfcf..b173d404e3df 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1 +1,2 @@
-obj-y		:= hv_init.o mmu.o
+obj-y			:= hv_init.o mmu.o
+obj-$(CONFIG_X86_64)	+= hv_apic.o
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
new file mode 100644
index 000000000000..f68855499391
--- /dev/null
+++ b/arch/x86/hyperv/hv_apic.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Hyper-V specific APIC code.
+ *
+ * Copyright (C) 2018, Microsoft, Inc.
+ *
+ * Author : K. Y. Srinivasan <kys@microsoft.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/version.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/clockchips.h>
+#include <linux/hyperv.h>
+#include <linux/slab.h>
+#include <linux/cpuhotplug.h>
+#include <asm/hypervisor.h>
+#include <asm/mshyperv.h>
+#include <asm/apic.h>
+
+static struct apic orig_apic;
+
+static u64 hv_apic_icr_read(void)
+{
+	u64 reg_val;
+
+	rdmsrl(HV_X64_MSR_ICR, reg_val);
+	return reg_val;
+}
+
+static void hv_apic_icr_write(u32 low, u32 id)
+{
+	u64 reg_val;
+
+	reg_val = SET_APIC_DEST_FIELD(id);
+	reg_val = reg_val << 32;
+	reg_val |= low;
+
+	wrmsrl(HV_X64_MSR_ICR, reg_val);
+}
+
+static u32 hv_apic_read(u32 reg)
+{
+	u32 reg_val, hi;
+
+	switch (reg) {
+	case APIC_EOI:
+		rdmsr(HV_X64_MSR_EOI, reg_val, hi);
+		return reg_val;
+	case APIC_TASKPRI:
+		rdmsr(HV_X64_MSR_TPR, reg_val, hi);
+		return reg_val;
+
+	default:
+		return native_apic_mem_read(reg);
+	}
+}
+
+static void hv_apic_write(u32 reg, u32 val)
+{
+	switch (reg) {
+	case APIC_EOI:
+		wrmsr(HV_X64_MSR_EOI, val, 0);
+		break;
+	case APIC_TASKPRI:
+		wrmsr(HV_X64_MSR_TPR, val, 0);
+		break;
+	default:
+		native_apic_mem_write(reg, val);
+	}
+}
+
+static void hv_apic_eoi_write(u32 reg, u32 val)
+{
+	wrmsr(HV_X64_MSR_EOI, val, 0);
+}
+
+/*
+ * IPI implementation on Hyper-V.
+ */
+static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
+{
+	struct ipi_arg_ex **arg;
+	struct ipi_arg_ex *ipi_arg;
+	unsigned long flags;
+	int nr_bank = 0;
+	int ret = 1;
+
+	local_irq_save(flags);
+	arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	ipi_arg = *arg;
+	if (unlikely(!ipi_arg))
+		goto ipi_mask_ex_done;
+
+	ipi_arg->vector = vector;
+	ipi_arg->reserved = 0;
+	ipi_arg->vp_set.valid_bank_mask = 0;
+
+	if (!cpumask_equal(mask, cpu_present_mask)) {
+		ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+		nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
+	}
+	if (!nr_bank)
+		ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
+
+	ret = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
+			      ipi_arg, NULL);
+
+ipi_mask_ex_done:
+	local_irq_restore(flags);
+	return ((ret == 0) ? true : false);
+}
+
+static bool __send_ipi_mask(const struct cpumask *mask, int vector)
+{
+	int cur_cpu, vcpu;
+	struct ipi_arg_non_ex **arg;
+	struct ipi_arg_non_ex *ipi_arg;
+	int ret = 1;
+	unsigned long flags;
+
+	if (cpumask_empty(mask))
+		return true;
+
+	if (!hv_hypercall_pg)
+		return false;
+
+	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+		return false;
+
+	if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+		return __send_ipi_mask_ex(mask, vector);
+
+	local_irq_save(flags);
+	arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	ipi_arg = *arg;
+	if (unlikely(!ipi_arg))
+		goto ipi_mask_done;
+
+	ipi_arg->vector = vector;
+	ipi_arg->reserved = 0;
+	ipi_arg->cpu_mask = 0;
+
+	for_each_cpu(cur_cpu, mask) {
+		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
+		/*
+		 * This particular version of the IPI hypercall can
+		 * only target upto 64 CPUs.
+		 */
+		if (vcpu >= 64)
+			goto ipi_mask_done;
+
+		__set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask);
+	}
+
+	ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL);
+
+ipi_mask_done:
+	local_irq_restore(flags);
+	return ((ret == 0) ? true : false);
+}
+
+static bool __send_ipi_one(int cpu, int vector)
+{
+	struct cpumask mask = CPU_MASK_NONE;
+
+	cpumask_set_cpu(cpu, &mask);
+	return __send_ipi_mask(&mask, vector);
+}
+
+static void hv_send_ipi(int cpu, int vector)
+{
+	if (!__send_ipi_one(cpu, vector))
+		orig_apic.send_IPI(cpu, vector);
+}
+
+static void hv_send_ipi_mask(const struct cpumask *mask, int vector)
+{
+	if (!__send_ipi_mask(mask, vector))
+		orig_apic.send_IPI_mask(mask, vector);
+}
+
+static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
+{
+	unsigned int this_cpu = smp_processor_id();
+	struct cpumask new_mask;
+	const struct cpumask *local_mask;
+
+	cpumask_copy(&new_mask, mask);
+	cpumask_clear_cpu(this_cpu, &new_mask);
+	local_mask = &new_mask;
+	if (!__send_ipi_mask(local_mask, vector))
+		orig_apic.send_IPI_mask_allbutself(mask, vector);
+}
+
+static void hv_send_ipi_allbutself(int vector)
+{
+	hv_send_ipi_mask_allbutself(cpu_online_mask, vector);
+}
+
+static void hv_send_ipi_all(int vector)
+{
+	if (!__send_ipi_mask(cpu_online_mask, vector))
+		orig_apic.send_IPI_all(vector);
+}
+
+static void hv_send_ipi_self(int vector)
+{
+	if (!__send_ipi_one(smp_processor_id(), vector))
+		orig_apic.send_IPI_self(vector);
+}
+
+void __init hv_apic_init(void)
+{
+	if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) {
+		if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+			pr_info("Hyper-V: Using ext hypercalls for IPI\n");
+		else
+			pr_info("Hyper-V: Using IPI hypercalls\n");
+		/*
+		 * Set the IPI entry points.
+		 */
+		orig_apic = *apic;
+
+		apic->send_IPI = hv_send_ipi;
+		apic->send_IPI_mask = hv_send_ipi_mask;
+		apic->send_IPI_mask_allbutself = hv_send_ipi_mask_allbutself;
+		apic->send_IPI_allbutself = hv_send_ipi_allbutself;
+		apic->send_IPI_all = hv_send_ipi_all;
+		apic->send_IPI_self = hv_send_ipi_self;
+	}
+
+	if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) {
+		pr_info("Hyper-V: Using MSR based APIC access\n");
+		apic_set_eoi_write(hv_apic_eoi_write);
+		apic->read      = hv_apic_read;
+		apic->write     = hv_apic_write;
+		apic->icr_write = hv_apic_icr_write;
+		apic->icr_read  = hv_apic_icr_read;
+	}
+}
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index cfecc2272f2d..4c431e1c1eff 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -91,12 +91,19 @@ EXPORT_SYMBOL_GPL(hv_vp_index);
 struct hv_vp_assist_page **hv_vp_assist_page;
 EXPORT_SYMBOL_GPL(hv_vp_assist_page);
 
+void  __percpu **hyperv_pcpu_input_arg;
+EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
+
 u32 hv_max_vp_index;
 
 static int hv_cpu_init(unsigned int cpu)
 {
 	u64 msr_vp_index;
 	struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
+	void **input_arg;
+
+	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
+	*input_arg = page_address(alloc_page(GFP_KERNEL));
 
 	hv_get_vp_index(msr_vp_index);
 
@@ -217,6 +224,16 @@ static int hv_cpu_die(unsigned int cpu)
 {
 	struct hv_reenlightenment_control re_ctrl;
 	unsigned int new_cpu;
+	unsigned long flags;
+	void **input_arg;
+	void *input_pg = NULL;
+
+	local_irq_save(flags);
+	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
+	input_pg = *input_arg;
+	*input_arg = NULL;
+	local_irq_restore(flags);
+	free_page((unsigned long)input_pg);
 
 	if (hv_vp_assist_page && hv_vp_assist_page[cpu])
 		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
@@ -242,8 +259,9 @@ static int hv_cpu_die(unsigned int cpu)
  *
  * 1. Setup the hypercall page.
  * 2. Register Hyper-V specific clocksource.
+ * 3. Setup Hyper-V specific APIC entry points.
  */
-void hyperv_init(void)
+void __init hyperv_init(void)
 {
 	u64 guest_id, required_msrs;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
@@ -259,6 +277,16 @@ void hyperv_init(void)
 	if ((ms_hyperv.features & required_msrs) != required_msrs)
 		return;
 
+	/*
+	 * Allocate the per-CPU state for the hypercall input arg.
+	 * If this allocation fails, we will not be able to setup
+	 * (per-CPU) hypercall input page and thus this failure is
+	 * fatal on Hyper-V.
+	 */
+	hyperv_pcpu_input_arg = alloc_percpu(void  *);
+
+	BUG_ON(hyperv_pcpu_input_arg == NULL);
+
 	/* Allocate percpu VP index */
 	hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
 				    GFP_KERNEL);
@@ -296,7 +324,7 @@ void hyperv_init(void)
 	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
-	hyper_alloc_mmu();
+	hv_apic_init();
 
 	/*
 	 * Register Hyper-V specific clocksource.
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 56c9ebac946f..5f053d7d1bd9 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -25,20 +25,13 @@ struct hv_flush_pcpu {
 struct hv_flush_pcpu_ex {
 	u64 address_space;
 	u64 flags;
-	struct {
-		u64 format;
-		u64 valid_bank_mask;
-		u64 bank_contents[];
-	} hv_vp_set;
+	struct hv_vpset hv_vp_set;
 	u64 gva_list[];
 };
 
 /* Each gva in gva_list encodes up to 4096 pages to flush */
 #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
 
-static struct hv_flush_pcpu __percpu **pcpu_flush;
-
-static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex;
 
 /*
  * Fills in gva_list starting from offset. Returns the number of items added.
@@ -70,41 +63,6 @@ static inline int fill_gva_list(u64 gva_list[], int offset,
 	return gva_n - offset;
 }
 
-/* Return the number of banks in the resulting vp_set */
-static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush,
-				    const struct cpumask *cpus)
-{
-	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
-
-	/* valid_bank_mask can represent up to 64 banks */
-	if (hv_max_vp_index / 64 >= 64)
-		return 0;
-
-	/*
-	 * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
-	 * structs are not cleared between calls, we risk flushing unneeded
-	 * vCPUs otherwise.
-	 */
-	for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
-		flush->hv_vp_set.bank_contents[vcpu_bank] = 0;
-
-	/*
-	 * Some banks may end up being empty but this is acceptable.
-	 */
-	for_each_cpu(cpu, cpus) {
-		vcpu = hv_cpu_number_to_vp_number(cpu);
-		vcpu_bank = vcpu / 64;
-		vcpu_offset = vcpu % 64;
-		__set_bit(vcpu_offset, (unsigned long *)
-			  &flush->hv_vp_set.bank_contents[vcpu_bank]);
-		if (vcpu_bank >= nr_bank)
-			nr_bank = vcpu_bank + 1;
-	}
-	flush->hv_vp_set.valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
-
-	return nr_bank;
-}
-
 static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 				    const struct flush_tlb_info *info)
 {
@@ -116,7 +74,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 
 	trace_hyperv_mmu_flush_tlb_others(cpus, info);
 
-	if (!pcpu_flush || !hv_hypercall_pg)
+	if (!hv_hypercall_pg)
 		goto do_native;
 
 	if (cpumask_empty(cpus))
@@ -124,10 +82,8 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 
 	local_irq_save(flags);
 
-	flush_pcpu = this_cpu_ptr(pcpu_flush);
-
-	if (unlikely(!*flush_pcpu))
-		*flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+	flush_pcpu = (struct hv_flush_pcpu **)
+		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	flush = *flush_pcpu;
 
@@ -203,7 +159,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 
 	trace_hyperv_mmu_flush_tlb_others(cpus, info);
 
-	if (!pcpu_flush_ex || !hv_hypercall_pg)
+	if (!hv_hypercall_pg)
 		goto do_native;
 
 	if (cpumask_empty(cpus))
@@ -211,10 +167,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 
 	local_irq_save(flags);
 
-	flush_pcpu = this_cpu_ptr(pcpu_flush_ex);
-
-	if (unlikely(!*flush_pcpu))
-		*flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+	flush_pcpu = (struct hv_flush_pcpu_ex **)
+		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	flush = *flush_pcpu;
 
@@ -239,8 +193,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 	flush->hv_vp_set.valid_bank_mask = 0;
 
 	if (!cpumask_equal(cpus, cpu_present_mask)) {
-		flush->hv_vp_set.format = HV_GENERIC_SET_SPARCE_4K;
-		nr_bank = cpumask_to_vp_set(flush, cpus);
+		flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+		nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
 	}
 
 	if (!nr_bank) {
@@ -296,14 +250,3 @@ void hyperv_setup_mmu_ops(void)
 		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
 	}
 }
-
-void hyper_alloc_mmu(void)
-{
-	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
-		return;
-
-	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-		pcpu_flush = alloc_percpu(struct hv_flush_pcpu *);
-	else
-		pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *);
-}
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 386a6900e206..219faaec51df 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -136,7 +136,6 @@
 #endif
 
 #ifndef __ASSEMBLY__
-#ifndef __BPF__
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -146,6 +145,5 @@
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
-#endif
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h
new file mode 100644
index 000000000000..e958e28f7ab5
--- /dev/null
+++ b/arch/x86/include/asm/cacheinfo.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CACHEINFO_H
+#define _ASM_X86_CACHEINFO_H
+
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
+
+#endif /* _ASM_X86_CACHEINFO_H */
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index e1c8dab86670..fb97cf7c4137 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -17,7 +17,6 @@
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
-typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_pid_t;
 typedef u16		__compat_uid_t;
@@ -46,16 +45,6 @@ typedef u32		compat_u32;
 typedef u64 __attribute__((aligned(4))) compat_u64;
 typedef u32		compat_uptr_t;
 
-struct compat_timespec {
-	compat_time_t	tv_sec;
-	s32		tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t	tv_sec;
-	s32		tv_usec;
-};
-
 struct compat_stat {
 	compat_dev_t	st_dev;
 	u16		__pad1;
@@ -145,10 +134,10 @@ struct compat_ipc64_perm {
 
 struct compat_semid64_ds {
 	struct compat_ipc64_perm sem_perm;
-	compat_time_t  sem_otime;
-	compat_ulong_t __unused1;
-	compat_time_t  sem_ctime;
-	compat_ulong_t __unused2;
+	compat_ulong_t sem_otime;
+	compat_ulong_t sem_otime_high;
+	compat_ulong_t sem_ctime;
+	compat_ulong_t sem_ctime_high;
 	compat_ulong_t sem_nsems;
 	compat_ulong_t __unused3;
 	compat_ulong_t __unused4;
@@ -156,12 +145,12 @@ struct compat_semid64_ds {
 
 struct compat_msqid64_ds {
 	struct compat_ipc64_perm msg_perm;
-	compat_time_t  msg_stime;
-	compat_ulong_t __unused1;
-	compat_time_t  msg_rtime;
-	compat_ulong_t __unused2;
-	compat_time_t  msg_ctime;
-	compat_ulong_t __unused3;
+	compat_ulong_t msg_stime;
+	compat_ulong_t msg_stime_high;
+	compat_ulong_t msg_rtime;
+	compat_ulong_t msg_rtime_high;
+	compat_ulong_t msg_ctime;
+	compat_ulong_t msg_ctime_high;
 	compat_ulong_t msg_cbytes;
 	compat_ulong_t msg_qnum;
 	compat_ulong_t msg_qbytes;
@@ -174,12 +163,12 @@ struct compat_msqid64_ds {
 struct compat_shmid64_ds {
 	struct compat_ipc64_perm shm_perm;
 	compat_size_t  shm_segsz;
-	compat_time_t  shm_atime;
-	compat_ulong_t __unused1;
-	compat_time_t  shm_dtime;
-	compat_ulong_t __unused2;
-	compat_time_t  shm_ctime;
-	compat_ulong_t __unused3;
+	compat_ulong_t shm_atime;
+	compat_ulong_t shm_atime_high;
+	compat_ulong_t shm_dtime;
+	compat_ulong_t shm_dtime_high;
+	compat_ulong_t shm_ctime;
+	compat_ulong_t shm_ctime_high;
 	compat_pid_t   shm_cpid;
 	compat_pid_t   shm_lpid;
 	compat_ulong_t shm_nattch;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index b27da9602a6d..aced6c9290d6 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -140,6 +140,20 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 
 #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
 
+#if defined(__clang__) && !defined(CC_HAVE_ASM_GOTO)
+
+/*
+ * Workaround for the sake of BPF compilation which utilizes kernel
+ * headers, but clang does not support ASM GOTO and fails the build.
+ */
+#ifndef __BPF_TRACING__
+#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
+#endif
+
+#define static_cpu_has(bit)            boot_cpu_has(bit)
+
+#else
+
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
  * These will statically patch the target code for additional
@@ -195,6 +209,7 @@ t_no:
 		boot_cpu_has(bit) :				\
 		_static_cpu_has(bit)				\
 )
+#endif
 
 #define cpu_has_bug(c, bit)		cpu_has(c, (bit))
 #define set_cpu_bug(c, bit)		set_cpu_cap(c, (bit))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index d554c11e01ff..fb00a2fca990 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
-
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
@@ -207,13 +206,19 @@
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
-
+#define X86_FEATURE_MSR_SPEC_CTRL	( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
 #define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
-
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* "" AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -274,9 +279,10 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -320,6 +326,7 @@
 #define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
+#define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
@@ -333,6 +340,7 @@
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*
  * BUG word(s)
@@ -362,5 +370,6 @@
 #define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 89ce4bfd241f..ce4d176b3d13 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -30,10 +30,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
-int arch_dma_supported(struct device *dev, u64 mask);
-#define arch_dma_supported arch_dma_supported
-
-bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
+bool arch_dma_alloc_attrs(struct device **dev);
 #define arch_dma_alloc_attrs arch_dma_alloc_attrs
 
 #endif
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 09ad88572746..c18ed65287d5 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -46,10 +46,24 @@ int ftrace_int3_handler(struct pt_regs *regs);
 #endif /* CONFIG_FUNCTION_TRACER */
 
 
-#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS)
+#ifndef __ASSEMBLY__
+
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+	/*
+	 * Compare the symbol name with the system call name. Skip the
+	 * "__x64_sys", "__ia32_sys" or simple "sys" prefix.
+	 */
+	return !strcmp(sym + 3, name + 3) ||
+		(!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) ||
+		(!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3));
+}
+
+#ifndef COMPILE_OFFSETS
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION)
-#include <asm/compat.h>
+#include <linux/compat.h>
 
 /*
  * Because ia32 syscalls do not map to x86_64 syscall numbers
@@ -67,6 +81,7 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
 	return false;
 }
 #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
-#endif /* !__ASSEMBLY__  && !COMPILE_OFFSETS */
+#endif /* !COMPILE_OFFSETS */
+#endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 5ea2afd4c871..740a428acf1e 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -50,14 +50,6 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 #define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
 
-#define local_softirq_pending()	this_cpu_read(irq_stat.__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING
-
-#define set_softirq_pending(x)	\
-		this_cpu_write(irq_stat.__softirq_pending, (x))
-#define or_softirq_pending(x)	this_cpu_or(irq_stat.__softirq_pending, (x))
-
 extern void ack_bad_irq(unsigned int irq);
 
 extern u64 arch_irq_stat_cpu(unsigned int cpu);
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 416cb0e0c496..3bfa92c2793c 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -164,6 +164,11 @@
  */
 #define HV_X64_DEPRECATING_AEOI_RECOMMENDED	(1 << 9)
 
+/*
+ * Recommend using cluster IPI hypercalls.
+ */
+#define HV_X64_CLUSTER_IPI_RECOMMENDED         (1 << 10)
+
 /* Recommend using the newer ExProcessorMasks interface */
 #define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED	(1 << 11)
 
@@ -329,12 +334,17 @@ struct hv_tsc_emulation_status {
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\
 		(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
 
+#define HV_IPI_LOW_VECTOR	0x10
+#define HV_IPI_HIGH_VECTOR	0xff
+
 /* Declare the various hypercall operations. */
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE	0x0002
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST	0x0003
 #define HVCALL_NOTIFY_LONG_SPIN_WAIT		0x0008
+#define HVCALL_SEND_IPI				0x000b
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX  0x0013
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX   0x0014
+#define HVCALL_SEND_IPI_EX			0x0015
 #define HVCALL_POST_MESSAGE			0x005c
 #define HVCALL_SIGNAL_EVENT			0x005d
 
@@ -360,7 +370,7 @@ struct hv_tsc_emulation_status {
 #define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	BIT(3)
 
 enum HV_GENERIC_SET_FORMAT {
-	HV_GENERIC_SET_SPARCE_4K,
+	HV_GENERIC_SET_SPARSE_4K,
 	HV_GENERIC_SET_ALL,
 };
 
@@ -706,4 +716,22 @@ struct hv_enlightened_vmcs {
 #define HV_STIMER_AUTOENABLE		(1ULL << 3)
 #define HV_STIMER_SINT(config)		(__u8)(((config) >> 16) & 0x0F)
 
+struct ipi_arg_non_ex {
+	u32 vector;
+	u32 reserved;
+	u64 cpu_mask;
+};
+
+struct hv_vpset {
+	u64 format;
+	u64 valid_bank_mask;
+	u64 bank_contents[];
+};
+
+struct ipi_arg_ex {
+	u32 vector;
+	u32 reserved;
+	struct hv_vpset vp_set;
+};
+
 #endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index b3e32b010ab1..c2c01f84df75 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
 	return insn_offset_displacement(insn) + insn->displacement.nbytes;
 }
 
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+	return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+		(insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+		 X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
 #endif /* _ASM_X86_INSN_H */
diff --git a/arch/x86/include/asm/intel_mid_vrtc.h b/arch/x86/include/asm/intel_mid_vrtc.h
index 35555016b1be..0b44b1abe4d9 100644
--- a/arch/x86/include/asm/intel_mid_vrtc.h
+++ b/arch/x86/include/asm/intel_mid_vrtc.h
@@ -4,7 +4,7 @@
 
 extern unsigned char vrtc_cmos_read(unsigned char reg);
 extern void vrtc_cmos_write(unsigned char val, unsigned char reg);
-extern void vrtc_get_time(struct timespec *now);
-extern int vrtc_set_mmss(const struct timespec *now);
+extern void vrtc_get_time(struct timespec64 *now);
+extern int vrtc_set_mmss(const struct timespec64 *now);
 
 #endif
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index f6e5b9375d8c..6de64840dd22 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -94,10 +94,10 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 
 #ifdef CONFIG_X86_64
 
-build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "=r", )
-build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
-build_mmio_write(__writeq, "q", unsigned long, "r", )
+build_mmio_read(readq, "q", u64, "=r", :"memory")
+build_mmio_read(__readq, "q", u64, "=r", )
+build_mmio_write(writeq, "q", u64, "r", :"memory")
+build_mmio_write(__writeq, "q", u64, "r", )
 
 #define readq_relaxed(a)	__readq(a)
 #define writeq_relaxed(v, a)	__writeq(v, a)
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 404c5fdff859..548d90bbf919 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -34,11 +34,6 @@
  * (0x80 is the syscall vector, 0x30-0x3f are for ISA)
  */
 #define FIRST_EXTERNAL_VECTOR		0x20
-/*
- * We start allocating at 0x21 to spread out vectors evenly between
- * priority levels. (0x80 is the syscall vector)
- */
-#define VECTOR_OFFSET_START		1
 
 /*
  * Reserve the lowest usable vector (and hence lowest priority)  0x20 for
@@ -119,8 +114,6 @@
 #define FIRST_SYSTEM_VECTOR		NR_VECTORS
 #endif
 
-#define FPU_IRQ				  13
-
 /*
  * Size the maximum number of interrupts.
  *
diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h
index b885a961a150..a34897aef2c2 100644
--- a/arch/x86/include/asm/jailhouse_para.h
+++ b/arch/x86/include/asm/jailhouse_para.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL2.0 */
+/* SPDX-License-Identifier: GPL-2.0 */
 
 /*
  * Jailhouse paravirt detection
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 949c977bc4c9..f4b2588865e9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -924,7 +924,7 @@ struct kvm_x86_ops {
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
-	bool (*cpu_has_high_real_mode_segbase)(void);
+	bool (*has_emulated_msr)(int index);
 	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	struct kvm *(*vm_alloc)(void);
@@ -1013,6 +1013,7 @@ struct kvm_x86_ops {
 
 	bool (*has_wbinvd_exit)(void);
 
+	u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index 1775a32f7ea6..97198001e567 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -95,8 +95,8 @@ static inline unsigned char current_lock_cmos_reg(void)
 unsigned char rtc_cmos_read(unsigned char addr);
 void rtc_cmos_write(unsigned char val, unsigned char addr);
 
-extern int mach_set_rtc_mmss(const struct timespec *now);
-extern void mach_get_cmos_time(struct timespec *now);
+extern int mach_set_rtc_mmss(const struct timespec64 *now);
+extern void mach_get_cmos_time(struct timespec64 *now);
 
 #define RTC_IRQ 8
 
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 57e3785d0d26..cf9911b5a53c 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -193,7 +193,7 @@ static inline int init_new_context(struct task_struct *tsk,
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
-		/* pkey 0 is the default and always allocated */
+		/* pkey 0 is the default and allocated implicitly */
 		mm->context.pkey_allocation_map = 0x1;
 		/* -1 means unallocated or invalid */
 		mm->context.execute_only_pkey = -1;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index b90e79610cf7..997192131b7b 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -122,6 +122,7 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
 #if IS_ENABLED(CONFIG_HYPERV)
 extern struct clocksource *hyperv_cs;
 extern void *hv_hypercall_pg;
+extern void  __percpu  **hyperv_pcpu_input_arg;
 
 static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 {
@@ -258,9 +259,41 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number)
 	return hv_vp_index[cpu_number];
 }
 
-void hyperv_init(void);
+static inline int cpumask_to_vpset(struct hv_vpset *vpset,
+				    const struct cpumask *cpus)
+{
+	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
+
+	/* valid_bank_mask can represent up to 64 banks */
+	if (hv_max_vp_index / 64 >= 64)
+		return 0;
+
+	/*
+	 * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
+	 * structs are not cleared between calls, we risk flushing unneeded
+	 * vCPUs otherwise.
+	 */
+	for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
+		vpset->bank_contents[vcpu_bank] = 0;
+
+	/*
+	 * Some banks may end up being empty but this is acceptable.
+	 */
+	for_each_cpu(cpu, cpus) {
+		vcpu = hv_cpu_number_to_vp_number(cpu);
+		vcpu_bank = vcpu / 64;
+		vcpu_offset = vcpu % 64;
+		__set_bit(vcpu_offset, (unsigned long *)
+			  &vpset->bank_contents[vcpu_bank]);
+		if (vcpu_bank >= nr_bank)
+			nr_bank = vcpu_bank + 1;
+	}
+	vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
+	return nr_bank;
+}
+
+void __init hyperv_init(void);
 void hyperv_setup_mmu_ops(void);
-void hyper_alloc_mmu(void);
 void hyperv_report_panic(struct pt_regs *regs, long err);
 bool hv_is_hyperv_initialized(void);
 void hyperv_cleanup(void);
@@ -269,6 +302,13 @@ void hyperv_reenlightenment_intr(struct pt_regs *regs);
 void set_hv_tscchange_cb(void (*cb)(void));
 void clear_hv_tscchange_cb(void);
 void hyperv_stop_tsc_emulation(void);
+
+#ifdef CONFIG_X86_64
+void hv_apic_init(void);
+#else
+static inline void hv_apic_init(void) {}
+#endif
+
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline bool hv_is_hyperv_initialized(void) { return false; }
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 53d5b1b9255e..68b2c3150de1 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -42,6 +42,8 @@
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
 #define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP			(1 << 1)   /* Single Thread Indirect Branch Predictors */
+#define SPEC_CTRL_SSBD_SHIFT		2	   /* Speculative Store Bypass Disable bit */
+#define SPEC_CTRL_SSBD			(1 << SPEC_CTRL_SSBD_SHIFT)   /* Speculative Store Bypass Disable */
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
@@ -60,14 +62,19 @@
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
 #define NHM_C1_AUTO_DEMOTE		(1UL << 26)
 #define ATM_LNC_C6_AUTO_DEMOTE		(1UL << 25)
-#define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
+#define SNB_C3_AUTO_UNDEMOTE		(1UL << 27)
+#define SNB_C1_AUTO_UNDEMOTE		(1UL << 28)
 
 #define MSR_MTRRcap			0x000000fe
 
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+#define ARCH_CAP_SSB_NO			(1 << 4)   /*
+						    * Not susceptible to Speculative Store Bypass
+						    * attack, so no Speculative Store Bypass
+						    * control required.
+						    */
 
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
@@ -340,6 +347,8 @@
 #define MSR_AMD64_SEV_ENABLED_BIT	0
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
 
+#define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f928ad9b143f..8b38df98548e 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -217,6 +217,14 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_IBRS,
 };
 
+/* The Speculative Store Bypass disable variants */
+enum ssb_mitigation {
+	SPEC_STORE_BYPASS_NONE,
+	SPEC_STORE_BYPASS_DISABLE,
+	SPEC_STORE_BYPASS_PRCTL,
+	SPEC_STORE_BYPASS_SECCOMP,
+};
+
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];
 
@@ -241,22 +249,27 @@ static inline void vmexit_fill_RSB(void)
 #endif
 }
 
-#define alternative_msr_write(_msr, _val, _feature)		\
-	asm volatile(ALTERNATIVE("",				\
-				 "movl %[msr], %%ecx\n\t"	\
-				 "movl %[val], %%eax\n\t"	\
-				 "movl $0, %%edx\n\t"		\
-				 "wrmsr",			\
-				 _feature)			\
-		     : : [msr] "i" (_msr), [val] "i" (_val)	\
-		     : "eax", "ecx", "edx", "memory")
+static __always_inline
+void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
+{
+	asm volatile(ALTERNATIVE("", "wrmsr", %c[feature])
+		: : "c" (msr),
+		    "a" ((u32)val),
+		    "d" ((u32)(val >> 32)),
+		    [feature] "i" (feature)
+		: "memory");
+}
 
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
-			      X86_FEATURE_USE_IBPB);
+	u64 val = PRED_CMD_IBPB;
+
+	alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
 }
 
+/* The Intel SPEC CTRL MSR base value cache */
+extern u64 x86_spec_ctrl_base;
+
 /*
  * With retpoline, we must use IBRS to restrict branch prediction
  * before calling into firmware.
@@ -265,14 +278,18 @@ static inline void indirect_branch_prediction_barrier(void)
  */
 #define firmware_restrict_branch_speculation_start()			\
 do {									\
+	u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS;			\
+									\
 	preempt_disable();						\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,	\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 } while (0)
 
 #define firmware_restrict_branch_speculation_end()			\
 do {									\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,			\
+	u64 val = x86_spec_ctrl_base;					\
+									\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 	preempt_enable();						\
 } while (0)
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 2c5a966dc222..6afac386a434 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -53,7 +53,7 @@
 #define __PHYSICAL_MASK_SHIFT	52
 
 #ifdef CONFIG_X86_5LEVEL
-#define __VIRTUAL_MASK_SHIFT	(pgtable_l5_enabled ? 56 : 47)
+#define __VIRTUAL_MASK_SHIFT	(pgtable_l5_enabled() ? 56 : 47)
 #else
 #define __VIRTUAL_MASK_SHIFT	47
 #endif
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 9be2bf13825b..d49bbf4bb5c8 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -574,14 +574,14 @@ static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
 }
 
 #define set_pgd(pgdp, pgdval) do {					\
-	if (pgtable_l5_enabled)						\
+	if (pgtable_l5_enabled())						\
 		__set_pgd(pgdp, pgdval);				\
 	else								\
 		set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd });	\
 } while (0)
 
 #define pgd_clear(pgdp) do {						\
-	if (pgtable_l5_enabled)						\
+	if (pgtable_l5_enabled())						\
 		set_pgd(pgdp, __pgd(0));				\
 } while (0)
 
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d32175e30259..662963681ea6 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -117,9 +117,6 @@ void native_restore_msi_irqs(struct pci_dev *dev);
 #define native_setup_msi_irqs		NULL
 #define native_teardown_msi_irq		NULL
 #endif
-
-#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
-
 #endif  /* __KERNEL__ */
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 263c142a6a6c..ada6410fd2ec 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -167,7 +167,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 #if CONFIG_PGTABLE_LEVELS > 4
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
 {
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return;
 	paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT);
 	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
@@ -193,7 +193,7 @@ extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				  unsigned long address)
 {
-	if (pgtable_l5_enabled)
+	if (pgtable_l5_enabled())
 		___p4d_free_tlb(tlb, p4d);
 }
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5f49b4ff0c24..99ecde23c3ec 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -65,7 +65,7 @@ extern pmdval_t early_pmd_flags;
 
 #ifndef __PAGETABLE_P4D_FOLDED
 #define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
-#define pgd_clear(pgd)			(pgtable_l5_enabled ? native_pgd_clear(pgd) : 0)
+#define pgd_clear(pgd)			(pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0)
 #endif
 
 #ifndef set_p4d
@@ -601,6 +601,11 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
+static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
+{
+	return canon_pgprot(prot);
+}
+
 static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 					 enum page_cache_mode pcm,
 					 enum page_cache_mode new_pcm)
@@ -876,7 +881,7 @@ static inline unsigned long p4d_index(unsigned long address)
 #if CONFIG_PGTABLE_LEVELS > 4
 static inline int pgd_present(pgd_t pgd)
 {
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return 1;
 	return pgd_flags(pgd) & _PAGE_PRESENT;
 }
@@ -893,9 +898,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
 #define pgd_page(pgd)	pfn_to_page(pgd_pfn(pgd))
 
 /* to find an entry in a page-table-directory. */
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static __always_inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return (p4d_t *)pgd;
 	return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
 }
@@ -904,7 +909,7 @@ static inline int pgd_bad(pgd_t pgd)
 {
 	unsigned long ignore_flags = _PAGE_USER;
 
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return 0;
 
 	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
@@ -915,7 +920,7 @@ static inline int pgd_bad(pgd_t pgd)
 
 static inline int pgd_none(pgd_t pgd)
 {
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return 0;
 	/*
 	 * There is no need to do a workaround for the KNL stray
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index e3225e83db7d..d9a001a4a872 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -15,7 +15,7 @@
 # include <asm/pgtable-2level_types.h>
 #endif
 
-#define pgtable_l5_enabled 0
+#define pgtable_l5_enabled() 0
 
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 877bc27718ae..3c5385f9a88f 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -220,7 +220,7 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	pgd_t pgd;
 
-	if (pgtable_l5_enabled || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
+	if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
 		*p4dp = p4d;
 		return;
 	}
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index d5c21a382475..054765ab2da2 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -22,12 +22,23 @@ typedef struct { pteval_t pte; } pte_t;
 
 #ifdef CONFIG_X86_5LEVEL
 extern unsigned int __pgtable_l5_enabled;
-#ifndef pgtable_l5_enabled
-#define pgtable_l5_enabled cpu_feature_enabled(X86_FEATURE_LA57)
-#endif
+
+#ifdef USE_EARLY_PGTABLE_L5
+/*
+ * cpu_feature_enabled() is not available in early boot code.
+ * Use variable instead.
+ */
+static inline bool pgtable_l5_enabled(void)
+{
+	return __pgtable_l5_enabled;
+}
 #else
-#define pgtable_l5_enabled 0
-#endif
+#define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57)
+#endif /* USE_EARLY_PGTABLE_L5 */
+
+#else
+#define pgtable_l5_enabled() 0
+#endif /* CONFIG_X86_5LEVEL */
 
 extern unsigned int pgdir_shift;
 extern unsigned int ptrs_per_p4d;
@@ -102,21 +113,21 @@ extern unsigned int ptrs_per_p4d;
 
 #define LDT_PGD_ENTRY_L4	-3UL
 #define LDT_PGD_ENTRY_L5	-112UL
-#define LDT_PGD_ENTRY		(pgtable_l5_enabled ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
+#define LDT_PGD_ENTRY		(pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 
-#define __VMALLOC_BASE_L4	0xffffc90000000000
-#define __VMALLOC_BASE_L5 	0xffa0000000000000
+#define __VMALLOC_BASE_L4	0xffffc90000000000UL
+#define __VMALLOC_BASE_L5 	0xffa0000000000000UL
 
 #define VMALLOC_SIZE_TB_L4	32UL
 #define VMALLOC_SIZE_TB_L5	12800UL
 
-#define __VMEMMAP_BASE_L4	0xffffea0000000000
-#define __VMEMMAP_BASE_L5	0xffd4000000000000
+#define __VMEMMAP_BASE_L4	0xffffea0000000000UL
+#define __VMEMMAP_BASE_L5	0xffd4000000000000UL
 
 #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 # define VMALLOC_START		vmalloc_base
-# define VMALLOC_SIZE_TB	(pgtable_l5_enabled ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
+# define VMALLOC_SIZE_TB	(pgtable_l5_enabled() ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
 # define VMEMMAP_START		vmemmap_base
 #else
 # define VMALLOC_START		__VMALLOC_BASE_L4
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index a0ba1ffda0df..851c04b7a092 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_PKEYS_H
 #define _ASM_X86_PKEYS_H
 
+#define ARCH_DEFAULT_PKEY	0
+
 #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)
 
 extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
@@ -15,7 +17,7 @@ extern int __execute_only_pkey(struct mm_struct *mm);
 static inline int execute_only_pkey(struct mm_struct *mm)
 {
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
-		return 0;
+		return ARCH_DEFAULT_PKEY;
 
 	return __execute_only_pkey(mm);
 }
@@ -49,13 +51,21 @@ bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
 {
 	/*
 	 * "Allocated" pkeys are those that have been returned
-	 * from pkey_alloc().  pkey 0 is special, and never
-	 * returned from pkey_alloc().
+	 * from pkey_alloc() or pkey 0 which is allocated
+	 * implicitly when the mm is created.
 	 */
-	if (pkey <= 0)
+	if (pkey < 0)
 		return false;
 	if (pkey >= arch_max_pkey())
 		return false;
+	/*
+	 * The exec-only pkey is set in the allocation map, but
+	 * is not available to any of the user interfaces like
+	 * mprotect_pkey().
+	 */
+	if (pkey == mm->context.execute_only_pkey)
+		return false;
+
 	return mm_pkey_allocation_map(mm) & (1U << pkey);
 }
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 4fa4206029e3..e28add6b791f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -186,15 +186,6 @@ extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
-extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern u32 get_scattered_cpuid_leaf(unsigned int level,
-				    unsigned int sub_leaf,
-				    enum cpuid_regs_idx reg);
-extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
-
-extern void detect_extended_topology(struct cpuinfo_x86 *c);
-extern void detect_ht(struct cpuinfo_x86 *c);
 
 #ifdef CONFIG_X86_32
 extern int have_cpuid_p(void);
@@ -749,13 +740,11 @@ enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
-extern void early_trap_init(void);
 void early_trap_pf_init(void);
 
 /* Defined in head.S */
 extern struct desc_ptr		early_gdt_descr;
 
-extern void cpu_set_gdt(int);
 extern void switch_to_new_gdt(int);
 extern void load_direct_gdt(int);
 extern void load_fixmap_gdt(int);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index a7471dcd2205..b6033680d458 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -12,7 +12,7 @@ void pvclock_set_flags(u8 flags);
 unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
 void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
 			    struct pvclock_vcpu_time_info *vcpu,
-			    struct timespec *ts);
+			    struct timespec64 *ts);
 void pvclock_resume(void);
 
 void pvclock_touch_watchdogs(void);
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 5e16b5d40d32..3e70bed8a978 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -7,6 +7,14 @@
 #include <asm-generic/qspinlock_types.h>
 #include <asm/paravirt.h>
 
+#define _Q_PENDING_LOOPS	(1 << 9)
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+
 #define	queued_spin_unlock queued_spin_unlock
 /**
  * queued_spin_unlock - release a queued spinlock
@@ -16,15 +24,9 @@
  */
 static inline void native_queued_spin_unlock(struct qspinlock *lock)
 {
-	smp_store_release((u8 *)lock, 0);
+	smp_store_release(&lock->locked, 0);
 }
 
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __pv_init_lock_hash(void);
-extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
-
 static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 {
 	pv_queued_spin_lock_slowpath(lock, val);
@@ -40,11 +42,6 @@ static inline bool vcpu_is_preempted(long cpu)
 {
 	return pv_vcpu_is_preempted(cpu);
 }
-#else
-static inline void queued_spin_unlock(struct qspinlock *lock)
-{
-	native_queued_spin_unlock(lock);
-}
 #endif
 
 #ifdef CONFIG_PARAVIRT
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 923307ea11c7..9ef5ee03d2d7 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -22,8 +22,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
  *
  * void __pv_queued_spin_unlock(struct qspinlock *lock)
  * {
- *	struct __qspinlock *l = (void *)lock;
- *	u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+ *	u8 lockval = cmpxchg(&lock->locked, _Q_LOCKED_VAL, 0);
  *
  *	if (likely(lockval == _Q_LOCKED_VAL))
  *		return;
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index f75bff8f9d82..547c4fe50711 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -171,7 +171,6 @@ static inline int wbinvd_on_all_cpus(void)
 	wbinvd();
 	return 0;
 }
-#define smp_num_siblings	1
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus;
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 4617a2bf123c..199218719a86 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -27,8 +27,8 @@
 # endif
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
-# define MAX_PHYSADDR_BITS	(pgtable_l5_enabled ? 52 : 44)
-# define MAX_PHYSMEM_BITS	(pgtable_l5_enabled ? 52 : 46)
+# define MAX_PHYSADDR_BITS	(pgtable_l5_enabled() ? 52 : 44)
+# define MAX_PHYSMEM_BITS	(pgtable_l5_enabled() ? 52 : 46)
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
new file mode 100644
index 000000000000..ae7c2c5cd7f0
--- /dev/null
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SPECCTRL_H_
+#define _ASM_X86_SPECCTRL_H_
+
+#include <linux/thread_info.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
+ * the guest has, while on VMEXIT we restore the host view. This
+ * would be easier if SPEC_CTRL were architecturally maskable or
+ * shadowable for guests but this is not (currently) the case.
+ * Takes the guest view of SPEC_CTRL MSR as a parameter and also
+ * the guest's version of VIRT_SPEC_CTRL, if emulated.
+ */
+extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest);
+
+/**
+ * x86_spec_ctrl_set_guest - Set speculation control registers for the guest
+ * @guest_spec_ctrl:		The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl:	The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ *				(may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+static inline
+void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+{
+	x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true);
+}
+
+/**
+ * x86_spec_ctrl_restore_host - Restore host speculation control registers
+ * @guest_spec_ctrl:		The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl:	The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ *				(may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+static inline
+void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+{
+	x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false);
+}
+
+/* AMD specific Speculative Store Bypass MSR data */
+extern u64 x86_amd_ls_cfg_base;
+extern u64 x86_amd_ls_cfg_ssbd_mask;
+
+static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn)
+{
+	BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT);
+	return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT);
+}
+
+static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl)
+{
+	BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT);
+	return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT);
+}
+
+static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
+{
+	return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
+}
+
+#ifdef CONFIG_SMP
+extern void speculative_store_bypass_ht_init(void);
+#else
+static inline void speculative_store_bypass_ht_init(void) { }
+#endif
+
+extern void speculative_store_bypass_update(unsigned long tif);
+
+static inline void speculative_store_bypass_update_current(void)
+{
+	speculative_store_bypass_update(current_thread_info()->flags);
+}
+
+#endif
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 133d9425fced..b6dc698f992a 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -111,4 +111,6 @@ static inline unsigned long caller_frame_pointer(void)
 	return (unsigned long)frame;
 }
 
+void show_opcodes(u8 *rip, const char *loglvl);
+void show_ip(struct pt_regs *regs, const char *loglvl);
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 533f74c300c2..d33f92b9fa22 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -116,7 +116,8 @@ int strcmp(const char *cs, const char *ct);
 #endif
 
 #define __HAVE_ARCH_MEMCPY_MCSAFE 1
-__must_check int memcpy_mcsafe_unrolled(void *dst, const void *src, size_t cnt);
+__must_check unsigned long __memcpy_mcsafe(void *dst, const void *src,
+		size_t cnt);
 DECLARE_STATIC_KEY_FALSE(mcsafe_key);
 
 /**
@@ -131,14 +132,15 @@ DECLARE_STATIC_KEY_FALSE(mcsafe_key);
  * actually do machine check recovery. Everyone else can just
  * use memcpy().
  *
- * Return 0 for success, -EFAULT for fail
+ * Return 0 for success, or number of bytes not copied if there was an
+ * exception.
  */
-static __always_inline __must_check int
+static __always_inline __must_check unsigned long
 memcpy_mcsafe(void *dst, const void *src, size_t cnt)
 {
 #ifdef CONFIG_X86_MCE
 	if (static_branch_unlikely(&mcsafe_key))
-		return memcpy_mcsafe_unrolled(dst, src, cnt);
+		return __memcpy_mcsafe(dst, src, cnt);
 	else
 #endif
 		memcpy(dst, src, cnt);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a5d9521bb2cb..2ff2a30a264f 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -79,6 +79,7 @@ struct thread_info {
 #define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
 #define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
+#define TIF_SSBD			5	/* Reduced data speculation */
 #define TIF_SYSCALL_EMU		6	/* syscall emulation active */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
@@ -105,6 +106,7 @@ struct thread_info {
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_SSBD		(1 << TIF_SSBD)
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
@@ -144,7 +146,7 @@ struct thread_info {
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP)
+	(_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_SSBD)
 
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 62546b3a398e..62acb613114b 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -47,6 +47,17 @@ copy_user_generic(void *to, const void *from, unsigned len)
 }
 
 static __always_inline __must_check unsigned long
+copy_to_user_mcsafe(void *to, const void *from, unsigned len)
+{
+	unsigned long ret;
+
+	__uaccess_begin();
+	ret = memcpy_mcsafe(to, from, len);
+	__uaccess_end();
+	return ret;
+}
+
+static __always_inline __must_check unsigned long
 raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 {
 	int ret = 0;
@@ -194,4 +205,7 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 unsigned long
 copy_user_handle_tail(char *to, char *from, unsigned len);
 
+unsigned long
+mcsafe_handle_tail(char *to, char *from, unsigned len);
+
 #endif /* _ASM_X86_UACCESS_64_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index ce8b4da07e35..2d27236c16a3 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -170,7 +170,7 @@ struct x86_cpuinit_ops {
 	void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
 };
 
-struct timespec;
+struct timespec64;
 
 /**
  * struct x86_legacy_devices - legacy x86 devices
@@ -264,8 +264,8 @@ struct x86_hyper_runtime {
 struct x86_platform_ops {
 	unsigned long (*calibrate_cpu)(void);
 	unsigned long (*calibrate_tsc)(void);
-	void (*get_wallclock)(struct timespec *ts);
-	int (*set_wallclock)(const struct timespec *ts);
+	void (*get_wallclock)(struct timespec64 *ts);
+	int (*set_wallclock)(const struct timespec64 *ts);
 	void (*iommu_shutdown)(void);
 	bool (*is_untracked_pat_range)(u64 start, u64 end);
 	void (*nmi_init)(void);
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 4c851ebb3ceb..0ede697c3961 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -29,7 +29,7 @@
 #define KVM_FEATURE_PV_TLB_FLUSH	9
 #define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 
-#define KVM_HINTS_DEDICATED      0
+#define KVM_HINTS_REALTIME      0
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/include/uapi/asm/msgbuf.h b/arch/x86/include/uapi/asm/msgbuf.h
index 809134c644a6..90ab9a795b49 100644
--- a/arch/x86/include/uapi/asm/msgbuf.h
+++ b/arch/x86/include/uapi/asm/msgbuf.h
@@ -1 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_X64_MSGBUF_H
+#define __ASM_X64_MSGBUF_H
+
+#if !defined(__x86_64__) || !defined(__ILP32__)
 #include <asm-generic/msgbuf.h>
+#else
+/*
+ * The msqid64_ds structure for x86 architecture with x32 ABI.
+ *
+ * On x86-32 and x86-64 we can just use the generic definition, but
+ * x32 uses the same binary layout as x86_64, which is differnet
+ * from other 32-bit architectures.
+ */
+
+struct msqid64_ds {
+	struct ipc64_perm msg_perm;
+	__kernel_time_t msg_stime;	/* last msgsnd time */
+	__kernel_time_t msg_rtime;	/* last msgrcv time */
+	__kernel_time_t msg_ctime;	/* last change time */
+	__kernel_ulong_t msg_cbytes;	/* current number of bytes on queue */
+	__kernel_ulong_t msg_qnum;	/* number of messages in queue */
+	__kernel_ulong_t msg_qbytes;	/* max number of bytes on queue */
+	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
+	__kernel_pid_t msg_lrpid;	/* last receive pid */
+	__kernel_ulong_t __unused4;
+	__kernel_ulong_t __unused5;
+};
+
+#endif
+
+#endif /* __ASM_GENERIC_MSGBUF_H */
diff --git a/arch/x86/include/uapi/asm/sembuf.h b/arch/x86/include/uapi/asm/sembuf.h
index cabd7476bd6c..89de6cd9f0a7 100644
--- a/arch/x86/include/uapi/asm/sembuf.h
+++ b/arch/x86/include/uapi/asm/sembuf.h
@@ -8,15 +8,24 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
+ *
+ * x86_64 and x32 incorrectly added padding here, so the structures
+ * are still incompatible with the padding on x86.
  */
 struct semid64_ds {
 	struct ipc64_perm sem_perm;	/* permissions .. see ipc.h */
+#ifdef __i386__
+	unsigned long	sem_otime;	/* last semop time */
+	unsigned long	sem_otime_high;
+	unsigned long	sem_ctime;	/* last change time */
+	unsigned long	sem_ctime_high;
+#else
 	__kernel_time_t	sem_otime;	/* last semop time */
 	__kernel_ulong_t __unused1;
 	__kernel_time_t	sem_ctime;	/* last change time */
 	__kernel_ulong_t __unused2;
+#endif
 	__kernel_ulong_t sem_nsems;	/* no. of semaphores in array */
 	__kernel_ulong_t __unused3;
 	__kernel_ulong_t __unused4;
diff --git a/arch/x86/include/uapi/asm/shmbuf.h b/arch/x86/include/uapi/asm/shmbuf.h
index 83c05fc2de38..644421f3823b 100644
--- a/arch/x86/include/uapi/asm/shmbuf.h
+++ b/arch/x86/include/uapi/asm/shmbuf.h
@@ -1 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_X86_SHMBUF_H
+#define __ASM_X86_SHMBUF_H
+
+#if !defined(__x86_64__) || !defined(__ILP32__)
 #include <asm-generic/shmbuf.h>
+#else
+/*
+ * The shmid64_ds structure for x86 architecture with x32 ABI.
+ *
+ * On x86-32 and x86-64 we can just use the generic definition, but
+ * x32 uses the same binary layout as x86_64, which is differnet
+ * from other 32-bit architectures.
+ */
+
+struct shmid64_ds {
+	struct ipc64_perm	shm_perm;	/* operation perms */
+	size_t			shm_segsz;	/* size of segment (bytes) */
+	__kernel_time_t		shm_atime;	/* last attach time */
+	__kernel_time_t		shm_dtime;	/* last detach time */
+	__kernel_time_t		shm_ctime;	/* last change time */
+	__kernel_pid_t		shm_cpid;	/* pid of creator */
+	__kernel_pid_t		shm_lpid;	/* pid of last operator */
+	__kernel_ulong_t	shm_nattch;	/* no. of current attaches */
+	__kernel_ulong_t	__unused4;
+	__kernel_ulong_t	__unused5;
+};
+
+struct shminfo64 {
+	__kernel_ulong_t	shmmax;
+	__kernel_ulong_t	shmmin;
+	__kernel_ulong_t	shmmni;
+	__kernel_ulong_t	shmseg;
+	__kernel_ulong_t	shmall;
+	__kernel_ulong_t	__unused1;
+	__kernel_ulong_t	__unused2;
+	__kernel_ulong_t	__unused3;
+	__kernel_ulong_t	__unused4;
+};
+
+#endif
+
+#endif /* __ASM_X86_SHMBUF_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dde444f932c1..3b20607d581b 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -215,6 +215,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 	apic_id = processor->local_apic_id;
 	enabled = processor->lapic_flags & ACPI_MADT_ENABLED;
 
+	/* Ignore invalid ID */
+	if (apic_id == 0xffffffff)
+		return 0;
+
 	/*
 	 * We need to register disabled CPU as well to permit
 	 * counting disabled CPUs. This allows us to size
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index c88e0b127810..b481b95bd8f6 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -14,8 +14,11 @@
 #include <asm/amd_nb.h>
 
 #define PCI_DEVICE_ID_AMD_17H_ROOT	0x1450
+#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT	0x15d0
 #define PCI_DEVICE_ID_AMD_17H_DF_F3	0x1463
 #define PCI_DEVICE_ID_AMD_17H_DF_F4	0x1464
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
 
 /* Protect the PCI config register pairs used for SMN and DF indirect access. */
 static DEFINE_MUTEX(smn_mutex);
@@ -24,6 +27,7 @@ static u32 *flush_words;
 
 static const struct pci_device_id amd_root_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) },
 	{}
 };
 
@@ -39,6 +43,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{}
 };
@@ -51,6 +56,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
 	{}
 };
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 8b04234e010b..7685444a106b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -116,6 +116,7 @@ static void init_x2apic_ldr(void)
 			goto update;
 	}
 	cmsk = cluster_hotplug_mask;
+	cmsk->clusterid = cluster;
 	cluster_hotplug_mask = NULL;
 update:
 	this_cpu_write(cluster_masks, cmsk);
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index dfcbe6924eaf..5d0de79fdab0 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1715,19 +1715,6 @@ static int proc_apm_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int proc_apm_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_apm_show, NULL);
-}
-
-static const struct file_operations apm_file_ops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_apm_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int apm(void *unused)
 {
 	unsigned short	bx;
@@ -2360,7 +2347,7 @@ static int __init apm_init(void)
 	set_desc_base(&gdt[APM_DS >> 3],
 		 (unsigned long)__va((unsigned long)apm_info.bios.dseg << 4));
 
-	proc_create("apm", 0, NULL, &apm_file_ops);
+	proc_create_single("apm", 0, NULL, proc_apm_show);
 
 	kapmd_task = kthread_create(apm, NULL, "kapmd");
 	if (IS_ERR(kapmd_task)) {
@@ -2446,7 +2433,7 @@ MODULE_PARM_DESC(idle_threshold,
 	"System idle percentage above which to make APM BIOS idle calls");
 module_param(idle_period, int, 0444);
 MODULE_PARM_DESC(idle_period,
-	"Period (in sec/100) over which to caculate the idle percentage");
+	"Period (in sec/100) over which to calculate the idle percentage");
 module_param(smp, bool, 0444);
 MODULE_PARM_DESC(smp,
 	"Set this to enable APM use on an SMP platform. Use with caution on older systems");
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a66229f51b12..7a40196967cb 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -17,7 +17,7 @@ KCOV_INSTRUMENT_perf_event.o := n
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_common.o		:= $(nostackp)
 
-obj-y			:= intel_cacheinfo.o scattered.o topology.o
+obj-y			:= cacheinfo.o scattered.o topology.o
 obj-y			+= common.o
 obj-y			+= rdrand.o
 obj-y			+= match.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 12bc0a1139da..082d7875cef8 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,7 +9,9 @@
 #include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
+#include <asm/cacheinfo.h>
 #include <asm/cpu.h>
+#include <asm/spec-ctrl.h>
 #include <asm/smp.h>
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
@@ -297,7 +299,6 @@ static int nearby_node(int apicid)
 }
 #endif
 
-#ifdef CONFIG_SMP
 /*
  * Fix up cpu_core_id for pre-F17h systems to be in the
  * [0 .. cores_per_node - 1] range. Not really needed but
@@ -327,6 +328,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		int err;
 		u32 eax, ebx, ecx, edx;
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
@@ -345,21 +347,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		}
 
 		/*
-		 * We may have multiple LLCs if L3 caches exist, so check if we
-		 * have an L3 cache by looking at the L3 cache CPUID leaf.
+		 * In case leaf B is available, use it to derive
+		 * topology information.
 		 */
-		if (cpuid_edx(0x80000006)) {
-			if (c->x86 == 0x17) {
-				/*
-				 * LLC is at the core complex level.
-				 * Core complex id is ApicId[3].
-				 */
-				per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
-			} else {
-				/* LLC is at the node level. */
-				per_cpu(cpu_llc_id, cpu) = node_id;
-			}
-		}
+		err = detect_extended_topology(c);
+		if (!err)
+			c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+
+		cacheinfo_amd_init_llc_id(c, cpu, node_id);
+
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
@@ -375,7 +371,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		legacy_fixup_core_id(c);
 	}
 }
-#endif
 
 /*
  * On a AMD dual core setup the lower bits of the APIC id distinguish the cores.
@@ -383,7 +378,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
  */
 static void amd_detect_cmp(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
 
@@ -394,17 +388,11 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	c->phys_proc_id = c->initial_apicid >> bits;
 	/* use socket ID also for last level cache */
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
-	amd_get_topology(c);
-#endif
 }
 
 u16 amd_get_nb_id(int cpu)
 {
-	u16 id = 0;
-#ifdef CONFIG_SMP
-	id = per_cpu(cpu_llc_id, cpu);
-#endif
-	return id;
+	return per_cpu(cpu_llc_id, cpu);
 }
 EXPORT_SYMBOL_GPL(amd_get_nb_id);
 
@@ -554,6 +542,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
 		nodes_per_socket = ((value >> 3) & 7) + 1;
 	}
+
+	if (c->x86 >= 0x15 && c->x86 <= 0x17) {
+		unsigned int bit;
+
+		switch (c->x86) {
+		case 0x15: bit = 54; break;
+		case 0x16: bit = 33; break;
+		case 0x17: bit = 10; break;
+		default: return;
+		}
+		/*
+		 * Try to cache the base value so further operations can
+		 * avoid RMW. If that faults, do not enable SSBD.
+		 */
+		if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+			setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
+			setup_force_cpu_cap(X86_FEATURE_SSBD);
+			x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
+		}
+	}
 }
 
 static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -791,6 +799,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 
 static void init_amd_zn(struct cpuinfo_x86 *c)
 {
+	set_cpu_cap(c, X86_FEATURE_ZEN);
 	/*
 	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
 	 * all up to and including B1.
@@ -842,6 +851,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	/* Multi core CPU? */
 	if (c->extended_cpuid_level >= 0x80000008) {
 		amd_detect_cmp(c);
+		amd_get_topology(c);
 		srat_detect_node(c);
 	}
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bfca937bdcc3..7416fc206b4a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,8 +12,10 @@
 #include <linux/utsname.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
 
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 #include <asm/cmdline.h>
 #include <asm/bugs.h>
 #include <asm/processor.h>
@@ -27,6 +29,27 @@
 #include <asm/intel-family.h>
 
 static void __init spectre_v2_select_mitigation(void);
+static void __init ssb_select_mitigation(void);
+
+/*
+ * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
+ * writes to SPEC_CTRL contain whatever reserved bits have been set.
+ */
+u64 __ro_after_init x86_spec_ctrl_base;
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
+
+/*
+ * The vendor and possibly platform specific bits which can be modified in
+ * x86_spec_ctrl_base.
+ */
+static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
+
+/*
+ * AMD specific MSR info for Speculative Store Bypass control.
+ * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu().
+ */
+u64 __ro_after_init x86_amd_ls_cfg_base;
+u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;
 
 void __init check_bugs(void)
 {
@@ -37,9 +60,27 @@ void __init check_bugs(void)
 		print_cpu_info(&boot_cpu_data);
 	}
 
+	/*
+	 * Read the SPEC_CTRL MSR to account for reserved bits which may
+	 * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
+	 * init code as it is not enumerated and depends on the family.
+	 */
+	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+	/* Allow STIBP in MSR_SPEC_CTRL if supported */
+	if (boot_cpu_has(X86_FEATURE_STIBP))
+		x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
+
 	/* Select the proper spectre mitigation before patching alternatives */
 	spectre_v2_select_mitigation();
 
+	/*
+	 * Select proper mitigation for any exposure to the Speculative Store
+	 * Bypass vulnerability.
+	 */
+	ssb_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -93,7 +134,76 @@ static const char *spectre_v2_strings[] = {
 #undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
-static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
+	SPECTRE_V2_NONE;
+
+void
+x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
+{
+	u64 msrval, guestval, hostval = x86_spec_ctrl_base;
+	struct thread_info *ti = current_thread_info();
+
+	/* Is MSR_SPEC_CTRL implemented ? */
+	if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
+		/*
+		 * Restrict guest_spec_ctrl to supported values. Clear the
+		 * modifiable bits in the host base value and or the
+		 * modifiable bits from the guest value.
+		 */
+		guestval = hostval & ~x86_spec_ctrl_mask;
+		guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
+
+		/* SSBD controlled in MSR_SPEC_CTRL */
+		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
+			hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
+
+		if (hostval != guestval) {
+			msrval = setguest ? guestval : hostval;
+			wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
+		}
+	}
+
+	/*
+	 * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update
+	 * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported.
+	 */
+	if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) &&
+	    !static_cpu_has(X86_FEATURE_VIRT_SSBD))
+		return;
+
+	/*
+	 * If the host has SSBD mitigation enabled, force it in the host's
+	 * virtual MSR value. If its not permanently enabled, evaluate
+	 * current's TIF_SSBD thread flag.
+	 */
+	if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE))
+		hostval = SPEC_CTRL_SSBD;
+	else
+		hostval = ssbd_tif_to_spec_ctrl(ti->flags);
+
+	/* Sanitize the guest value */
+	guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD;
+
+	if (hostval != guestval) {
+		unsigned long tif;
+
+		tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) :
+				 ssbd_spec_ctrl_to_tif(hostval);
+
+		speculative_store_bypass_update(tif);
+	}
+}
+EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl);
+
+static void x86_amd_ssb_disable(void)
+{
+	u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
+
+	if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+		wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+	else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+		wrmsrl(MSR_AMD64_LS_CFG, msrval);
+}
 
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
@@ -312,32 +422,289 @@ retpoline_auto:
 }
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"Speculative Store Bypass: " fmt
+
+static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE;
+
+/* The kernel command line selection */
+enum ssb_mitigation_cmd {
+	SPEC_STORE_BYPASS_CMD_NONE,
+	SPEC_STORE_BYPASS_CMD_AUTO,
+	SPEC_STORE_BYPASS_CMD_ON,
+	SPEC_STORE_BYPASS_CMD_PRCTL,
+	SPEC_STORE_BYPASS_CMD_SECCOMP,
+};
+
+static const char *ssb_strings[] = {
+	[SPEC_STORE_BYPASS_NONE]	= "Vulnerable",
+	[SPEC_STORE_BYPASS_DISABLE]	= "Mitigation: Speculative Store Bypass disabled",
+	[SPEC_STORE_BYPASS_PRCTL]	= "Mitigation: Speculative Store Bypass disabled via prctl",
+	[SPEC_STORE_BYPASS_SECCOMP]	= "Mitigation: Speculative Store Bypass disabled via prctl and seccomp",
+};
+
+static const struct {
+	const char *option;
+	enum ssb_mitigation_cmd cmd;
+} ssb_mitigation_options[] = {
+	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO },    /* Platform decides */
+	{ "on",		SPEC_STORE_BYPASS_CMD_ON },      /* Disable Speculative Store Bypass */
+	{ "off",	SPEC_STORE_BYPASS_CMD_NONE },    /* Don't touch Speculative Store Bypass */
+	{ "prctl",	SPEC_STORE_BYPASS_CMD_PRCTL },   /* Disable Speculative Store Bypass via prctl */
+	{ "seccomp",	SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */
+};
+
+static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
+{
+	enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO;
+	char arg[20];
+	int ret, i;
+
+	if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+		return SPEC_STORE_BYPASS_CMD_NONE;
+	} else {
+		ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
+					  arg, sizeof(arg));
+		if (ret < 0)
+			return SPEC_STORE_BYPASS_CMD_AUTO;
+
+		for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) {
+			if (!match_option(arg, ret, ssb_mitigation_options[i].option))
+				continue;
+
+			cmd = ssb_mitigation_options[i].cmd;
+			break;
+		}
+
+		if (i >= ARRAY_SIZE(ssb_mitigation_options)) {
+			pr_err("unknown option (%s). Switching to AUTO select\n", arg);
+			return SPEC_STORE_BYPASS_CMD_AUTO;
+		}
+	}
+
+	return cmd;
+}
+
+static enum ssb_mitigation __init __ssb_select_mitigation(void)
+{
+	enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
+	enum ssb_mitigation_cmd cmd;
+
+	if (!boot_cpu_has(X86_FEATURE_SSBD))
+		return mode;
+
+	cmd = ssb_parse_cmdline();
+	if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
+	    (cmd == SPEC_STORE_BYPASS_CMD_NONE ||
+	     cmd == SPEC_STORE_BYPASS_CMD_AUTO))
+		return mode;
+
+	switch (cmd) {
+	case SPEC_STORE_BYPASS_CMD_AUTO:
+	case SPEC_STORE_BYPASS_CMD_SECCOMP:
+		/*
+		 * Choose prctl+seccomp as the default mode if seccomp is
+		 * enabled.
+		 */
+		if (IS_ENABLED(CONFIG_SECCOMP))
+			mode = SPEC_STORE_BYPASS_SECCOMP;
+		else
+			mode = SPEC_STORE_BYPASS_PRCTL;
+		break;
+	case SPEC_STORE_BYPASS_CMD_ON:
+		mode = SPEC_STORE_BYPASS_DISABLE;
+		break;
+	case SPEC_STORE_BYPASS_CMD_PRCTL:
+		mode = SPEC_STORE_BYPASS_PRCTL;
+		break;
+	case SPEC_STORE_BYPASS_CMD_NONE:
+		break;
+	}
+
+	/*
+	 * We have three CPU feature flags that are in play here:
+	 *  - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
+	 *  - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
+	 *  - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
+	 */
+	if (mode == SPEC_STORE_BYPASS_DISABLE) {
+		setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
+		/*
+		 * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses
+		 * a completely different MSR and bit dependent on family.
+		 */
+		switch (boot_cpu_data.x86_vendor) {
+		case X86_VENDOR_INTEL:
+			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
+			x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
+			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+			break;
+		case X86_VENDOR_AMD:
+			x86_amd_ssb_disable();
+			break;
+		}
+	}
+
+	return mode;
+}
+
+static void ssb_select_mitigation(void)
+{
+	ssb_mode = __ssb_select_mitigation();
+
+	if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+		pr_info("%s\n", ssb_strings[ssb_mode]);
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Speculation prctl: " fmt
+
+static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+	bool update;
+
+	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
+	    ssb_mode != SPEC_STORE_BYPASS_SECCOMP)
+		return -ENXIO;
+
+	switch (ctrl) {
+	case PR_SPEC_ENABLE:
+		/* If speculation is force disabled, enable is not allowed */
+		if (task_spec_ssb_force_disable(task))
+			return -EPERM;
+		task_clear_spec_ssb_disable(task);
+		update = test_and_clear_tsk_thread_flag(task, TIF_SSBD);
+		break;
+	case PR_SPEC_DISABLE:
+		task_set_spec_ssb_disable(task);
+		update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+		break;
+	case PR_SPEC_FORCE_DISABLE:
+		task_set_spec_ssb_disable(task);
+		task_set_spec_ssb_force_disable(task);
+		update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	/*
+	 * If being set on non-current task, delay setting the CPU
+	 * mitigation until it is next scheduled.
+	 */
+	if (task == current && update)
+		speculative_store_bypass_update_current();
+
+	return 0;
+}
+
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+			     unsigned long ctrl)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssb_prctl_set(task, ctrl);
+	default:
+		return -ENODEV;
+	}
+}
+
+#ifdef CONFIG_SECCOMP
+void arch_seccomp_spec_mitigate(struct task_struct *task)
+{
+	if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
+		ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+}
+#endif
+
+static int ssb_prctl_get(struct task_struct *task)
+{
+	switch (ssb_mode) {
+	case SPEC_STORE_BYPASS_DISABLE:
+		return PR_SPEC_DISABLE;
+	case SPEC_STORE_BYPASS_SECCOMP:
+	case SPEC_STORE_BYPASS_PRCTL:
+		if (task_spec_ssb_force_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+		if (task_spec_ssb_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+	default:
+		if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+			return PR_SPEC_ENABLE;
+		return PR_SPEC_NOT_AFFECTED;
+	}
+}
+
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssb_prctl_get(task);
+	default:
+		return -ENODEV;
+	}
+}
+
+void x86_spec_ctrl_setup_ap(void)
+{
+	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+	if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
+		x86_amd_ssb_disable();
+}
 
 #ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+
+static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
+			       char *buf, unsigned int bug)
 {
-	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+	if (!boot_cpu_has_bug(bug))
 		return sprintf(buf, "Not affected\n");
-	if (boot_cpu_has(X86_FEATURE_PTI))
-		return sprintf(buf, "Mitigation: PTI\n");
+
+	switch (bug) {
+	case X86_BUG_CPU_MELTDOWN:
+		if (boot_cpu_has(X86_FEATURE_PTI))
+			return sprintf(buf, "Mitigation: PTI\n");
+
+		break;
+
+	case X86_BUG_SPECTRE_V1:
+		return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+
+	case X86_BUG_SPECTRE_V2:
+		return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+			       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+			       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+			       spectre_v2_module_string());
+
+	case X86_BUG_SPEC_STORE_BYPASS:
+		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
+
+	default:
+		break;
+	}
+
 	return sprintf(buf, "Vulnerable\n");
 }
 
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN);
+}
+
 ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
-		return sprintf(buf, "Not affected\n");
-	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1);
 }
 
 ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		return sprintf(buf, "Not affected\n");
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2);
+}
 
-	return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
-		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
-		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
-		       spectre_v2_module_string());
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
 }
 #endif
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 54d04d574148..38354c66df81 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -20,6 +20,8 @@
 #include <asm/amd_nb.h>
 #include <asm/smp.h>
 
+#include "cpu.h"
+
 #define LVL_1_INST	1
 #define LVL_1_DATA	2
 #define LVL_2		3
@@ -637,6 +639,45 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 	return i;
 }
 
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+{
+	/*
+	 * We may have multiple LLCs if L3 caches exist, so check if we
+	 * have an L3 cache by looking at the L3 cache CPUID leaf.
+	 */
+	if (!cpuid_edx(0x80000006))
+		return;
+
+	if (c->x86 < 0x17) {
+		/* LLC is at the node level. */
+		per_cpu(cpu_llc_id, cpu) = node_id;
+	} else if (c->x86 == 0x17 &&
+		   c->x86_model >= 0 && c->x86_model <= 0x1F) {
+		/*
+		 * LLC is at the core complex level.
+		 * Core complex ID is ApicId[3] for these processors.
+		 */
+		per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+	} else {
+		/*
+		 * LLC ID is calculated from the number of threads sharing the
+		 * cache.
+		 * */
+		u32 eax, ebx, ecx, edx, num_sharing_cache = 0;
+		u32 llc_index = find_num_cache_leaves(c) - 1;
+
+		cpuid_count(0x8000001d, llc_index, &eax, &ebx, &ecx, &edx);
+		if (eax)
+			num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
+
+		if (num_sharing_cache) {
+			int bits = get_count_order(num_sharing_cache) - 1;
+
+			per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
+		}
+	}
+}
+
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
 
@@ -650,7 +691,7 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 	}
 }
 
-unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
+void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 {
 	/* Cache sizes */
 	unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0;
@@ -802,7 +843,8 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 
 	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
 
-	return l2;
+	if (!l2)
+		cpu_detect_cache_sizes(c);
 }
 
 static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index e5ec0f11c0de..14433ff5b828 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -18,6 +18,13 @@
 #define RNG_ENABLED	(1 << 3)
 #define RNG_ENABLE	(1 << 6)	/* MSR_VIA_RNG */
 
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW	0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI		0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS	0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020
+
 static void init_c3(struct cpuinfo_x86 *c)
 {
 	u32  lo, hi;
@@ -112,6 +119,31 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 	}
 }
 
+static void centaur_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+	msr_ctl = vmx_msr_high | vmx_msr_low;
+
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+		set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+		set_cpu_cap(c, X86_FEATURE_VNMI);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+		      vmx_msr_low, vmx_msr_high);
+		msr_ctl2 = vmx_msr_high | vmx_msr_low;
+		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+			set_cpu_cap(c, X86_FEATURE_EPT);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+			set_cpu_cap(c, X86_FEATURE_VPID);
+	}
+}
+
 static void init_centaur(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_32
@@ -128,6 +160,24 @@ static void init_centaur(struct cpuinfo_x86 *c)
 	clear_cpu_cap(c, 0*32+31);
 #endif
 	early_init_centaur(c);
+	init_intel_cacheinfo(c);
+	detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+	detect_ht(c);
+#endif
+
+	if (c->cpuid_level > 9) {
+		unsigned int eax = cpuid_eax(10);
+
+		/*
+		 * Check for version and the number of counters
+		 * Version(eax[7:0]) can't be 0;
+		 * Counters(eax[15:8]) should be greater than 1;
+		 */
+		if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+	}
+
 	switch (c->x86) {
 #ifdef CONFIG_X86_32
 	case 5:
@@ -199,6 +249,9 @@ static void init_centaur(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 #endif
+
+	if (cpu_has(c, X86_FEATURE_VMX))
+		centaur_detect_vmx_virtcap(c);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8a5b185735e1..95c8e507580d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -66,6 +66,13 @@ cpumask_var_t cpu_callin_mask;
 /* representing cpus for which sibling maps can be computed */
 cpumask_var_t cpu_sibling_setup_mask;
 
+/* Number of siblings per CPU package */
+int smp_num_siblings = 1;
+EXPORT_SYMBOL(smp_num_siblings);
+
+/* Last level cache ID of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
+
 /* correctly size the local cpu masks */
 void __init setup_cpu_local_masks(void)
 {
@@ -577,6 +584,19 @@ static void get_model_name(struct cpuinfo_x86 *c)
 	*(s + 1) = '\0';
 }
 
+void detect_num_cpu_cores(struct cpuinfo_x86 *c)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	c->x86_max_cores = 1;
+	if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
+		return;
+
+	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
+	if (eax & 0x1f)
+		c->x86_max_cores = (eax >> 26) + 1;
+}
+
 void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 {
 	unsigned int n, dummy, ebx, ecx, edx, l2size;
@@ -757,17 +777,32 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	 * and they also have a different bit for STIBP support. Also,
 	 * a hypervisor might have set the individual AMD bits even on
 	 * Intel CPUs, for finer-grained selection of what's available.
-	 *
-	 * We use the AMD bits in 0x8000_0008 EBX as the generic hardware
-	 * features, which are visible in /proc/cpuinfo and used by the
-	 * kernel. So set those accordingly from the Intel bits.
 	 */
 	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
 		set_cpu_cap(c, X86_FEATURE_IBRS);
 		set_cpu_cap(c, X86_FEATURE_IBPB);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
 	}
+
 	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
 		set_cpu_cap(c, X86_FEATURE_STIBP);
+
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) ||
+	    cpu_has(c, X86_FEATURE_VIRT_SSBD))
+		set_cpu_cap(c, X86_FEATURE_SSBD);
+
+	if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
+		set_cpu_cap(c, X86_FEATURE_IBRS);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+	}
+
+	if (cpu_has(c, X86_FEATURE_AMD_IBPB))
+		set_cpu_cap(c, X86_FEATURE_IBPB);
+
+	if (cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+		set_cpu_cap(c, X86_FEATURE_STIBP);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+	}
 }
 
 void get_cpu_cap(struct cpuinfo_x86 *c)
@@ -848,6 +883,11 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_power = edx;
 	}
 
+	if (c->extended_cpuid_level >= 0x80000008) {
+		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
+		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
+	}
+
 	if (c->extended_cpuid_level >= 0x8000000a)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 
@@ -871,7 +911,6 @@ static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 
 		c->x86_virt_bits = (eax >> 8) & 0xff;
 		c->x86_phys_bits = eax & 0xff;
-		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
 	}
 #ifdef CONFIG_X86_32
 	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
@@ -923,21 +962,47 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
 	{}
 };
 
-static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+/* Only list CPUs which speculate but are non susceptible to SSB */
+static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
+	{ X86_VENDOR_AMD,	0x12,					},
+	{ X86_VENDOR_AMD,	0x11,					},
+	{ X86_VENDOR_AMD,	0x10,					},
+	{ X86_VENDOR_AMD,	0xf,					},
+	{}
+};
+
+static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
-	if (x86_match_cpu(cpu_no_meltdown))
-		return false;
+	if (x86_match_cpu(cpu_no_speculation))
+		return;
+
+	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
 	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
 
+	if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
+	   !(ia32_cap & ARCH_CAP_SSB_NO))
+		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
+
+	if (x86_match_cpu(cpu_no_meltdown))
+		return;
+
 	/* Rogue Data Cache Load? No! */
 	if (ia32_cap & ARCH_CAP_RDCL_NO)
-		return false;
+		return;
 
-	return true;
+	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 }
 
 /*
@@ -988,12 +1053,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
-	if (!x86_match_cpu(cpu_no_speculation)) {
-		if (cpu_vulnerable_to_meltdown(c))
-			setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
-		setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
-		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
-	}
+	cpu_set_bug_bits(c);
 
 	fpu__init_system(c);
 
@@ -1004,6 +1064,21 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	setup_clear_cpu_cap(X86_FEATURE_PCID);
 #endif
+
+	/*
+	 * Later in the boot process pgtable_l5_enabled() relies on
+	 * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not
+	 * enabled by this point we need to clear the feature bit to avoid
+	 * false-positives at the later stage.
+	 *
+	 * pgtable_l5_enabled() can be false here for several reasons:
+	 *  - 5-level paging is disabled compile-time;
+	 *  - it's 32-bit kernel;
+	 *  - machine doesn't support 5-level paging;
+	 *  - user specified 'no5lvl' in kernel command line.
+	 */
+	if (!pgtable_l5_enabled())
+		setup_clear_cpu_cap(X86_FEATURE_LA57);
 }
 
 void __init early_cpu_init(void)
@@ -1355,6 +1430,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 #endif
 	mtrr_ap_init();
 	validate_apic_and_package_id(c);
+	x86_spec_ctrl_setup_ap();
 }
 
 static __init int setup_noclflush(char *arg)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index e806b11a99af..38216f678fc3 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -47,7 +47,19 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
 
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
+extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+				    unsigned int sub_leaf,
+				    enum cpuid_regs_idx reg);
+extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
+
+extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
+extern int detect_extended_topology(struct cpuinfo_x86 *c);
+extern void detect_ht(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);
 
+extern void x86_spec_ctrl_setup_ap(void);
+
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b9693b80fc21..eb75564f2d25 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -188,7 +188,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		setup_clear_cpu_cap(X86_FEATURE_IBPB);
 		setup_clear_cpu_cap(X86_FEATURE_STIBP);
 		setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL);
+		setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL);
 		setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
+		setup_clear_cpu_cap(X86_FEATURE_SSBD);
+		setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD);
 	}
 
 	/*
@@ -453,24 +456,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #endif
 }
 
-/*
- * find out the number of processor cores on the die
- */
-static int intel_num_cpu_cores(struct cpuinfo_x86 *c)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
-		return 1;
-
-	/* Intel has a non-standard dependency on %ecx for this CPUID level. */
-	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
-	if (eax & 0x1f)
-		return (eax >> 26) + 1;
-	else
-		return 1;
-}
-
 static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 {
 	/* Intel VMX MSR indicated features */
@@ -653,8 +638,6 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 
 static void init_intel(struct cpuinfo_x86 *c)
 {
-	unsigned int l2 = 0;
-
 	early_init_intel(c);
 
 	intel_workarounds(c);
@@ -671,19 +654,13 @@ static void init_intel(struct cpuinfo_x86 *c)
 		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
 		 * detection.
 		 */
-		c->x86_max_cores = intel_num_cpu_cores(c);
+		detect_num_cpu_cores(c);
 #ifdef CONFIG_X86_32
 		detect_ht(c);
 #endif
 	}
 
-	l2 = init_intel_cacheinfo(c);
-
-	/* Detect legacy cache sizes if init_intel_cacheinfo did not */
-	if (l2 == 0) {
-		cpu_detect_cache_sizes(c);
-		l2 = c->x86_cache_size;
-	}
+	init_intel_cacheinfo(c);
 
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
@@ -696,7 +673,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 
 	if (boot_cpu_has(X86_FEATURE_DS)) {
-		unsigned int l1;
+		unsigned int l1, l2;
+
 		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
 		if (!(l1 & (1<<11)))
 			set_cpu_cap(c, X86_FEATURE_BTS);
@@ -724,6 +702,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 	 * Dixon is NOT a Celeron.
 	 */
 	if (c->x86 == 6) {
+		unsigned int l2 = c->x86_cache_size;
 		char *p = NULL;
 
 		switch (c->x86_model) {
@@ -835,6 +814,9 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
 	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
+	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
+	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
+	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
 	{ 0x76, TLB_INST_2M_4M,		8,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
 	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
 	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 589b948e6e01..24bfa63e86cf 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -33,8 +33,8 @@
 #include <asm/intel_rdt_sched.h>
 #include "intel_rdt.h"
 
-#define MAX_MBA_BW	100u
 #define MBA_IS_LINEAR	0x4
+#define MBA_MAX_MBPS	U32_MAX
 
 /* Mutex to protect rdtgroup access. */
 DEFINE_MUTEX(rdtgroup_mutex);
@@ -178,7 +178,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.msr_update		= mba_wrmsr,
 		.cache_level		= 3,
 		.parse_ctrlval		= parse_bw,
-		.format_str		= "%d=%*d",
+		.format_str		= "%d=%*u",
 		.fflags			= RFTYPE_RES_MB,
 	},
 };
@@ -230,6 +230,14 @@ static inline void cache_alloc_hsw_probe(void)
 	rdt_alloc_capable = true;
 }
 
+bool is_mba_sc(struct rdt_resource *r)
+{
+	if (!r)
+		return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc;
+
+	return r->membw.mba_sc;
+}
+
 /*
  * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
  * exposed to user interface and the h/w understandable delay values.
@@ -341,7 +349,7 @@ static int get_cache_id(int cpu, int level)
  * that can be written to QOS_MSRs.
  * There are currently no SKUs which support non linear delay values.
  */
-static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
+u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 {
 	if (r->membw.delay_linear)
 		return MAX_MBA_BW - bw;
@@ -431,25 +439,40 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	return NULL;
 }
 
+void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
+{
+	int i;
+
+	/*
+	 * Initialize the Control MSRs to having no control.
+	 * For Cache Allocation: Set all bits in cbm
+	 * For Memory Allocation: Set b/w requested to 100%
+	 * and the bandwidth in MBps to U32_MAX
+	 */
+	for (i = 0; i < r->num_closid; i++, dc++, dm++) {
+		*dc = r->default_ctrl;
+		*dm = MBA_MAX_MBPS;
+	}
+}
+
 static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
 {
 	struct msr_param m;
-	u32 *dc;
-	int i;
+	u32 *dc, *dm;
 
 	dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
 	if (!dc)
 		return -ENOMEM;
 
-	d->ctrl_val = dc;
+	dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL);
+	if (!dm) {
+		kfree(dc);
+		return -ENOMEM;
+	}
 
-	/*
-	 * Initialize the Control MSRs to having no control.
-	 * For Cache Allocation: Set all bits in cbm
-	 * For Memory Allocation: Set b/w requested to 100
-	 */
-	for (i = 0; i < r->num_closid; i++, dc++)
-		*dc = r->default_ctrl;
+	d->ctrl_val = dc;
+	d->mbps_val = dm;
+	setup_default_ctrlval(r, dc, dm);
 
 	m.low = 0;
 	m.high = r->num_closid;
@@ -588,6 +611,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		}
 
 		kfree(d->ctrl_val);
+		kfree(d->mbps_val);
 		kfree(d->rmid_busy_llc);
 		kfree(d->mbm_total);
 		kfree(d->mbm_local);
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 3fd7a70ee04a..39752825e376 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -28,6 +28,7 @@
 
 #define MBM_CNTR_WIDTH			24
 #define MBM_OVERFLOW_INTERVAL		1000
+#define MAX_MBA_BW			100u
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
@@ -180,10 +181,20 @@ struct rftype {
  * struct mbm_state - status for each MBM counter in each domain
  * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
  * @prev_msr	Value of IA32_QM_CTR for this RMID last time we read it
+ * @chunks_bw	Total local data moved. Used for bandwidth calculation
+ * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
+ * @prev_bw	The most recent bandwidth in MBps
+ * @delta_bw	Difference between the current and previous bandwidth
+ * @delta_comp	Indicates whether to compute the delta_bw
  */
 struct mbm_state {
 	u64	chunks;
 	u64	prev_msr;
+	u64	chunks_bw;
+	u64	prev_bw_msr;
+	u32	prev_bw;
+	u32	delta_bw;
+	bool	delta_comp;
 };
 
 /**
@@ -202,6 +213,7 @@ struct mbm_state {
  * @cqm_work_cpu:
  *		worker cpu for CQM h/w counters
  * @ctrl_val:	array of cache or mem ctrl values (indexed by CLOSID)
+ * @mbps_val:	When mba_sc is enabled, this holds the bandwidth in MBps
  * @new_ctrl:	new ctrl value to be loaded
  * @have_new_ctrl: did user provide new_ctrl for this domain
  */
@@ -217,6 +229,7 @@ struct rdt_domain {
 	int			mbm_work_cpu;
 	int			cqm_work_cpu;
 	u32			*ctrl_val;
+	u32			*mbps_val;
 	u32			new_ctrl;
 	bool			have_new_ctrl;
 };
@@ -259,6 +272,7 @@ struct rdt_cache {
  * @min_bw:		Minimum memory bandwidth percentage user can request
  * @bw_gran:		Granularity at which the memory bandwidth is allocated
  * @delay_linear:	True if memory B/W delay is in linear scale
+ * @mba_sc:		True if MBA software controller(mba_sc) is enabled
  * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
  */
 struct rdt_membw {
@@ -266,6 +280,7 @@ struct rdt_membw {
 	u32		min_bw;
 	u32		bw_gran;
 	u32		delay_linear;
+	bool		mba_sc;
 	u32		*mb_map;
 };
 
@@ -445,6 +460,9 @@ void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
 void mbm_setup_overflow_handler(struct rdt_domain *dom,
 				unsigned long delay_ms);
 void mbm_handle_overflow(struct work_struct *work);
+bool is_mba_sc(struct rdt_resource *r);
+void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm);
+u32 delay_bw_map(unsigned long bw, struct rdt_resource *r);
 void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
 void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 23e1d5c249c6..116d57b248d3 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -53,7 +53,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 		return false;
 	}
 
-	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+	if ((bw < r->membw.min_bw || bw > r->default_ctrl) &&
+	    !is_mba_sc(r)) {
 		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
 				    r->membw.min_bw, r->default_ctrl);
 		return false;
@@ -179,6 +180,8 @@ static int update_domains(struct rdt_resource *r, int closid)
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
+	bool mba_sc;
+	u32 *dc;
 	int cpu;
 
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
@@ -188,13 +191,20 @@ static int update_domains(struct rdt_resource *r, int closid)
 	msr_param.high = msr_param.low + 1;
 	msr_param.res = r;
 
+	mba_sc = is_mba_sc(r);
 	list_for_each_entry(d, &r->domains, list) {
-		if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) {
+		dc = !mba_sc ? d->ctrl_val : d->mbps_val;
+		if (d->have_new_ctrl && d->new_ctrl != dc[closid]) {
 			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
-			d->ctrl_val[closid] = d->new_ctrl;
+			dc[closid] = d->new_ctrl;
 		}
 	}
-	if (cpumask_empty(cpu_mask))
+
+	/*
+	 * Avoid writing the control msr with control values when
+	 * MBA software controller is enabled
+	 */
+	if (cpumask_empty(cpu_mask) || mba_sc)
 		goto done;
 	cpu = get_cpu();
 	/* Update CBM on this cpu if it's in cpu_mask. */
@@ -282,13 +292,17 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
 {
 	struct rdt_domain *dom;
 	bool sep = false;
+	u32 ctrl_val;
 
 	seq_printf(s, "%*s:", max_name_width, r->name);
 	list_for_each_entry(dom, &r->domains, list) {
 		if (sep)
 			seq_puts(s, ";");
+
+		ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] :
+			    dom->mbps_val[closid]);
 		seq_printf(s, r->format_str, dom->id, max_data_width,
-			   dom->ctrl_val[closid]);
+			   ctrl_val);
 		sep = true;
 	}
 	seq_puts(s, "\n");
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
index 681450eee428..b0f3aed76b75 100644
--- a/arch/x86/kernel/cpu/intel_rdt_monitor.c
+++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -225,10 +225,18 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr)
+{
+	u64 shift = 64 - MBM_CNTR_WIDTH, chunks;
+
+	chunks = (cur_msr << shift) - (prev_msr << shift);
+	return chunks >>= shift;
+}
+
 static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 {
-	u64 chunks, shift, tval;
 	struct mbm_state *m;
+	u64 chunks, tval;
 
 	tval = __rmid_read(rmid, rr->evtid);
 	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
@@ -254,14 +262,12 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 	}
 
 	if (rr->first) {
-		m->prev_msr = tval;
-		m->chunks = 0;
+		memset(m, 0, sizeof(struct mbm_state));
+		m->prev_bw_msr = m->prev_msr = tval;
 		return 0;
 	}
 
-	shift = 64 - MBM_CNTR_WIDTH;
-	chunks = (tval << shift) - (m->prev_msr << shift);
-	chunks >>= shift;
+	chunks = mbm_overflow_count(m->prev_msr, tval);
 	m->chunks += chunks;
 	m->prev_msr = tval;
 
@@ -270,6 +276,32 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 }
 
 /*
+ * Supporting function to calculate the memory bandwidth
+ * and delta bandwidth in MBps.
+ */
+static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+	struct mbm_state *m = &rr->d->mbm_local[rmid];
+	u64 tval, cur_bw, chunks;
+
+	tval = __rmid_read(rmid, rr->evtid);
+	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
+		return;
+
+	chunks = mbm_overflow_count(m->prev_bw_msr, tval);
+	m->chunks_bw += chunks;
+	m->chunks = m->chunks_bw;
+	cur_bw = (chunks * r->mon_scale) >> 20;
+
+	if (m->delta_comp)
+		m->delta_bw = abs(cur_bw - m->prev_bw);
+	m->delta_comp = false;
+	m->prev_bw = cur_bw;
+	m->prev_bw_msr = tval;
+}
+
+/*
  * This is called via IPI to read the CQM/MBM counters
  * on a domain.
  */
@@ -297,6 +329,118 @@ void mon_event_count(void *info)
 	}
 }
 
+/*
+ * Feedback loop for MBA software controller (mba_sc)
+ *
+ * mba_sc is a feedback loop where we periodically read MBM counters and
+ * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so
+ * that:
+ *
+ *   current bandwdith(cur_bw) < user specified bandwidth(user_bw)
+ *
+ * This uses the MBM counters to measure the bandwidth and MBA throttle
+ * MSRs to control the bandwidth for a particular rdtgrp. It builds on the
+ * fact that resctrl rdtgroups have both monitoring and control.
+ *
+ * The frequency of the checks is 1s and we just tag along the MBM overflow
+ * timer. Having 1s interval makes the calculation of bandwidth simpler.
+ *
+ * Although MBA's goal is to restrict the bandwidth to a maximum, there may
+ * be a need to increase the bandwidth to avoid uncecessarily restricting
+ * the L2 <-> L3 traffic.
+ *
+ * Since MBA controls the L2 external bandwidth where as MBM measures the
+ * L3 external bandwidth the following sequence could lead to such a
+ * situation.
+ *
+ * Consider an rdtgroup which had high L3 <-> memory traffic in initial
+ * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but
+ * after some time rdtgroup has mostly L2 <-> L3 traffic.
+ *
+ * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its
+ * throttle MSRs already have low percentage values.  To avoid
+ * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
+ */
+static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+{
+	u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val;
+	struct mbm_state *pmbm_data, *cmbm_data;
+	u32 cur_bw, delta_bw, user_bw;
+	struct rdt_resource *r_mba;
+	struct rdt_domain *dom_mba;
+	struct list_head *head;
+	struct rdtgroup *entry;
+
+	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
+	closid = rgrp->closid;
+	rmid = rgrp->mon.rmid;
+	pmbm_data = &dom_mbm->mbm_local[rmid];
+
+	dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba);
+	if (!dom_mba) {
+		pr_warn_once("Failure to get domain for MBA update\n");
+		return;
+	}
+
+	cur_bw = pmbm_data->prev_bw;
+	user_bw = dom_mba->mbps_val[closid];
+	delta_bw = pmbm_data->delta_bw;
+	cur_msr_val = dom_mba->ctrl_val[closid];
+
+	/*
+	 * For Ctrl groups read data from child monitor groups.
+	 */
+	head = &rgrp->mon.crdtgrp_list;
+	list_for_each_entry(entry, head, mon.crdtgrp_list) {
+		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+		cur_bw += cmbm_data->prev_bw;
+		delta_bw += cmbm_data->delta_bw;
+	}
+
+	/*
+	 * Scale up/down the bandwidth linearly for the ctrl group.  The
+	 * bandwidth step is the bandwidth granularity specified by the
+	 * hardware.
+	 *
+	 * The delta_bw is used when increasing the bandwidth so that we
+	 * dont alternately increase and decrease the control values
+	 * continuously.
+	 *
+	 * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if
+	 * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep
+	 * switching between 90 and 110 continuously if we only check
+	 * cur_bw < user_bw.
+	 */
+	if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
+		new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
+	} else if (cur_msr_val < MAX_MBA_BW &&
+		   (user_bw > (cur_bw + delta_bw))) {
+		new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
+	} else {
+		return;
+	}
+
+	cur_msr = r_mba->msr_base + closid;
+	wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba));
+	dom_mba->ctrl_val[closid] = new_msr_val;
+
+	/*
+	 * Delta values are updated dynamically package wise for each
+	 * rdtgrp everytime the throttle MSR changes value.
+	 *
+	 * This is because (1)the increase in bandwidth is not perfectly
+	 * linear and only "approximately" linear even when the hardware
+	 * says it is linear.(2)Also since MBA is a core specific
+	 * mechanism, the delta values vary based on number of cores used
+	 * by the rdtgrp.
+	 */
+	pmbm_data->delta_comp = true;
+	list_for_each_entry(entry, head, mon.crdtgrp_list) {
+		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+		cmbm_data->delta_comp = true;
+	}
+}
+
 static void mbm_update(struct rdt_domain *d, int rmid)
 {
 	struct rmid_read rr;
@@ -314,7 +458,16 @@ static void mbm_update(struct rdt_domain *d, int rmid)
 	}
 	if (is_mbm_local_enabled()) {
 		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
-		__mon_event_count(rmid, &rr);
+
+		/*
+		 * Call the MBA software controller only for the
+		 * control groups and when user has enabled
+		 * the software controller explicitly.
+		 */
+		if (!is_mba_sc(NULL))
+			__mon_event_count(rmid, &rr);
+		else
+			mbm_bw_count(rmid, &rr);
 	}
 }
 
@@ -385,6 +538,9 @@ void mbm_handle_overflow(struct work_struct *work)
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
 			mbm_update(d, crgrp->mon.rmid);
+
+		if (is_mba_sc(NULL))
+			update_mba_bw(prgrp, d);
 	}
 
 	schedule_delayed_work_on(cpu, &d->mbm_over, delay);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index fca759d272a1..749856a2e736 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1005,6 +1005,11 @@ static void l2_qos_cfg_update(void *arg)
 	wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
 }
 
+static inline bool is_mba_linear(void)
+{
+	return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear;
+}
+
 static int set_cache_qos_cfg(int level, bool enable)
 {
 	void (*update)(void *arg);
@@ -1041,6 +1046,28 @@ static int set_cache_qos_cfg(int level, bool enable)
 	return 0;
 }
 
+/*
+ * Enable or disable the MBA software controller
+ * which helps user specify bandwidth in MBps.
+ * MBA software controller is supported only if
+ * MBM is supported and MBA is in linear scale.
+ */
+static int set_mba_sc(bool mba_sc)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA];
+	struct rdt_domain *d;
+
+	if (!is_mbm_enabled() || !is_mba_linear() ||
+	    mba_sc == is_mba_sc(r))
+		return -EINVAL;
+
+	r->membw.mba_sc = mba_sc;
+	list_for_each_entry(d, &r->domains, list)
+		setup_default_ctrlval(r, d->ctrl_val, d->mbps_val);
+
+	return 0;
+}
+
 static int cdp_enable(int level, int data_type, int code_type)
 {
 	struct rdt_resource *r_ldata = &rdt_resources_all[data_type];
@@ -1123,6 +1150,10 @@ static int parse_rdtgroupfs_options(char *data)
 			ret = cdpl2_enable();
 			if (ret)
 				goto out;
+		} else if (!strcmp(token, "mba_MBps")) {
+			ret = set_mba_sc(true);
+			if (ret)
+				goto out;
 		} else {
 			ret = -EINVAL;
 			goto out;
@@ -1445,6 +1476,8 @@ static void rdt_kill_sb(struct super_block *sb)
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
+	set_mba_sc(false);
+
 	/*Put everything back to default values. */
 	for_each_alloc_enabled_rdt_resource(r)
 		reset_all_ctrls(r);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 475cb4f5f14f..c805a06e14c3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -48,7 +48,7 @@ static struct dentry *dfs_inj;
 
 static u8 n_banks;
 
-#define MAX_FLAG_OPT_SIZE	3
+#define MAX_FLAG_OPT_SIZE	4
 #define NBCFG			0x44
 
 enum injection_type {
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 42cf2880d0ed..cd76380af79f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1727,6 +1727,21 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
 	}
 }
 
+static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
+{
+	struct mca_config *cfg = &mca_cfg;
+
+	 /*
+	  * All newer Centaur CPUs support MCE broadcasting. Enable
+	  * synchronization with a one second timeout.
+	  */
+	if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) ||
+	     c->x86 > 6) {
+		if (cfg->monarch_timeout < 0)
+			cfg->monarch_timeout = USEC_PER_SEC;
+	}
+}
+
 static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
@@ -1739,6 +1754,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_amd_feature_init(c);
 		break;
 		}
+	case X86_VENDOR_CENTAUR:
+		mce_centaur_feature_init(c);
+		break;
 
 	default:
 		break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index f7666eef4a87..f591b01930db 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -94,6 +94,11 @@ static struct smca_bank_name smca_names[] = {
 	[SMCA_SMU]	= { "smu",		"System Management Unit" },
 };
 
+static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
+{
+	[0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
+};
+
 const char *smca_get_name(enum smca_bank_types t)
 {
 	if (t >= N_SMCA_BANK_TYPES)
@@ -431,8 +436,7 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
 	wrmsr(MSR_CU_DEF_ERR, low, high);
 }
 
-static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
-				  unsigned int block)
+static u32 smca_get_block_address(unsigned int bank, unsigned int block)
 {
 	u32 low, high;
 	u32 addr = 0;
@@ -443,24 +447,30 @@ static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
 	if (!block)
 		return MSR_AMD64_SMCA_MCx_MISC(bank);
 
+	/* Check our cache first: */
+	if (smca_bank_addrs[bank][block] != -1)
+		return smca_bank_addrs[bank][block];
+
 	/*
 	 * For SMCA enabled processors, BLKPTR field of the first MISC register
 	 * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
 	 */
-	if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
-		return addr;
+	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+		goto out;
 
 	if (!(low & MCI_CONFIG_MCAX))
-		return addr;
+		goto out;
 
-	if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+	if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
 	    (low & MASK_BLKPTR_LO))
-		return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+		addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
 
+out:
+	smca_bank_addrs[bank][block] = addr;
 	return addr;
 }
 
-static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high,
+static u32 get_block_address(u32 current_addr, u32 low, u32 high,
 			     unsigned int bank, unsigned int block)
 {
 	u32 addr = 0, offset = 0;
@@ -468,20 +478,8 @@ static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 hi
 	if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
 		return addr;
 
-	/* Get address from already initialized block. */
-	if (per_cpu(threshold_banks, cpu)) {
-		struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank];
-
-		if (bankp && bankp->blocks) {
-			struct threshold_block *blockp = &bankp->blocks[block];
-
-			if (blockp)
-				return blockp->address;
-		}
-	}
-
 	if (mce_flags.smca)
-		return smca_get_block_address(cpu, bank, block);
+		return smca_get_block_address(bank, block);
 
 	/* Fall back to method we used for older processors: */
 	switch (block) {
@@ -559,7 +557,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			smca_configure(bank, cpu);
 
 		for (block = 0; block < NR_BLOCKS; ++block) {
-			address = get_block_address(cpu, address, low, high, bank, block);
+			address = get_block_address(address, low, high, bank, block);
 			if (!address)
 				break;
 
@@ -1176,7 +1174,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	if (err)
 		goto out_free;
 recurse:
-	address = get_block_address(cpu, address, low, high, bank, ++block);
+	address = get_block_address(address, low, high, bank, ++block);
 	if (!address)
 		return 0;
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 10c4fc2c91f8..77e201301528 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -564,14 +564,12 @@ static int __reload_late(void *info)
 	apply_microcode_local(&err);
 	spin_unlock(&update_lock);
 
+	/* siblings return UCODE_OK because their engine got updated already */
 	if (err > UCODE_NFOUND) {
 		pr_warn("Error reloading microcode on CPU %d\n", cpu);
-		return -1;
-	/* siblings return UCODE_OK because their engine got updated already */
+		ret = -1;
 	} else if (err == UCODE_UPDATED || err == UCODE_OK) {
 		ret = 1;
-	} else {
-		return ret;
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 32b8e5724f96..1c2cfa0644aa 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -485,7 +485,6 @@ static void show_saved_mc(void)
  */
 static void save_mc_for_early(u8 *mc, unsigned int size)
 {
-#ifdef CONFIG_HOTPLUG_CPU
 	/* Synchronization during CPU hotplug. */
 	static DEFINE_MUTEX(x86_cpu_microcode_mutex);
 
@@ -495,7 +494,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size)
 	show_saved_mc();
 
 	mutex_unlock(&x86_cpu_microcode_mutex);
-#endif
 }
 
 static bool load_builtin_intel_microcode(struct cpio_data *cp)
diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile
index ad9e5ed81181..2ad9107ee980 100644
--- a/arch/x86/kernel/cpu/mtrr/Makefile
+++ b/arch/x86/kernel/cpu/mtrr/Makefile
@@ -1,3 +1,3 @@
-obj-y		:= main.o if.o generic.o cleanup.o
+obj-y		:= mtrr.o if.o generic.o cleanup.o
 obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index 7468de429087..9a19c800fe40 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -46,6 +46,7 @@
 #include <linux/pci.h>
 #include <linux/smp.h>
 #include <linux/syscore_ops.h>
+#include <linux/rcupdate.h>
 
 #include <asm/cpufeature.h>
 #include <asm/e820/api.h>
@@ -100,7 +101,7 @@ static int have_wrcomb(void)
 		if (dev->vendor == PCI_VENDOR_ID_SERVERWORKS &&
 		    dev->device == PCI_DEVICE_ID_SERVERWORKS_LE &&
 		    dev->revision <= 5) {
-			pr_info("mtrr: Serverworks LE rev < 6 detected. Write-combining disabled.\n");
+			pr_info("Serverworks LE rev < 6 detected. Write-combining disabled.\n");
 			pci_dev_put(dev);
 			return 0;
 		}
@@ -110,7 +111,7 @@ static int have_wrcomb(void)
 		 */
 		if (dev->vendor == PCI_VENDOR_ID_INTEL &&
 		    dev->device == PCI_DEVICE_ID_INTEL_82451NX) {
-			pr_info("mtrr: Intel 450NX MMC detected. Write-combining disabled.\n");
+			pr_info("Intel 450NX MMC detected. Write-combining disabled.\n");
 			pci_dev_put(dev);
 			return 0;
 		}
@@ -312,24 +313,24 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 		return error;
 
 	if (type >= MTRR_NUM_TYPES) {
-		pr_warn("mtrr: type: %u invalid\n", type);
+		pr_warn("type: %u invalid\n", type);
 		return -EINVAL;
 	}
 
 	/* If the type is WC, check that this processor supports it */
 	if ((type == MTRR_TYPE_WRCOMB) && !have_wrcomb()) {
-		pr_warn("mtrr: your processor doesn't support write-combining\n");
+		pr_warn("your processor doesn't support write-combining\n");
 		return -ENOSYS;
 	}
 
 	if (!size) {
-		pr_warn("mtrr: zero sized request\n");
+		pr_warn("zero sized request\n");
 		return -EINVAL;
 	}
 
 	if ((base | (base + size - 1)) >>
 	    (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) {
-		pr_warn("mtrr: base or size exceeds the MTRR width\n");
+		pr_warn("base or size exceeds the MTRR width\n");
 		return -EINVAL;
 	}
 
@@ -360,8 +361,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 				} else if (types_compatible(type, ltype))
 					continue;
 			}
-			pr_warn("mtrr: 0x%lx000,0x%lx000 overlaps existing"
-				" 0x%lx000,0x%lx000\n", base, size, lbase,
+			pr_warn("0x%lx000,0x%lx000 overlaps existing 0x%lx000,0x%lx000\n", base, size, lbase,
 				lsize);
 			goto out;
 		}
@@ -369,7 +369,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 		if (ltype != type) {
 			if (types_compatible(type, ltype))
 				continue;
-			pr_warn("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n",
+			pr_warn("type mismatch for %lx000,%lx000 old: %s new: %s\n",
 				base, size, mtrr_attrib_to_str(ltype),
 				mtrr_attrib_to_str(type));
 			goto out;
@@ -395,7 +395,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 			}
 		}
 	} else {
-		pr_info("mtrr: no more MTRRs available\n");
+		pr_info("no more MTRRs available\n");
 	}
 	error = i;
  out:
@@ -407,8 +407,8 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 static int mtrr_check(unsigned long base, unsigned long size)
 {
 	if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
-		pr_warn("mtrr: size and base must be multiples of 4 kiB\n");
-		pr_debug("mtrr: size: 0x%lx  base: 0x%lx\n", size, base);
+		pr_warn("size and base must be multiples of 4 kiB\n");
+		pr_debug("size: 0x%lx  base: 0x%lx\n", size, base);
 		dump_stack();
 		return -1;
 	}
@@ -499,22 +499,22 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 			}
 		}
 		if (reg < 0) {
-			pr_debug("mtrr: no MTRR for %lx000,%lx000 found\n",
+			pr_debug("no MTRR for %lx000,%lx000 found\n",
 				 base, size);
 			goto out;
 		}
 	}
 	if (reg >= max) {
-		pr_warn("mtrr: register: %d too big\n", reg);
+		pr_warn("register: %d too big\n", reg);
 		goto out;
 	}
 	mtrr_if->get(reg, &lbase, &lsize, &ltype);
 	if (lsize < 1) {
-		pr_warn("mtrr: MTRR %d not used\n", reg);
+		pr_warn("MTRR %d not used\n", reg);
 		goto out;
 	}
 	if (mtrr_usage_table[reg] < 1) {
-		pr_warn("mtrr: reg: %d has count=0\n", reg);
+		pr_warn("reg: %d has count=0\n", reg);
 		goto out;
 	}
 	if (--mtrr_usage_table[reg] < 1)
@@ -775,7 +775,7 @@ void __init mtrr_bp_init(void)
 	}
 
 	if (!mtrr_enabled()) {
-		pr_info("MTRR: Disabled\n");
+		pr_info("Disabled\n");
 
 		/*
 		 * PAT initialization relies on MTRR's rendezvous handler.
@@ -793,6 +793,9 @@ void mtrr_ap_init(void)
 
 	if (!use_intel() || mtrr_aps_delayed_init)
 		return;
+
+	rcu_cpu_starting(smp_processor_id());
+
 	/*
 	 * Ideally we should hold mtrr_mutex here to avoid mtrr entries
 	 * changed, but this routine will be called in cpu boot time,
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index b099024d339c..81c0afb39d0a 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -27,7 +27,7 @@
  * exists, use it for populating initial_apicid and cpu topology
  * detection.
  */
-void detect_extended_topology(struct cpuinfo_x86 *c)
+int detect_extended_topology(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	unsigned int eax, ebx, ecx, edx, sub_index;
@@ -36,7 +36,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
 	static bool printed;
 
 	if (c->cpuid_level < 0xb)
-		return;
+		return -1;
 
 	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 
@@ -44,7 +44,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
 	 * check if the cpuid leaf 0xb is actually implemented.
 	 */
 	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
-		return;
+		return -1;
 
 	set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
 
@@ -95,6 +95,6 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
 			       c->cpu_core_id);
 		printed = 1;
 	}
-	return;
 #endif
+	return 0;
 }
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 18fa9d74c182..666a284116ac 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -22,11 +22,14 @@
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
+#define OPCODE_BUFSIZE 64
+
 int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
-static unsigned int code_bytes = 64;
 static int die_counter;
 
+static struct pt_regs exec_summary_regs;
+
 bool in_task_stack(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info)
 {
@@ -69,9 +72,62 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+/*
+ * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus:
+ *
+ * In case where we don't have the exact kernel image (which, if we did, we can
+ * simply disassemble and navigate to the RIP), the purpose of the bigger
+ * prologue is to have more context and to be able to correlate the code from
+ * the different toolchains better.
+ *
+ * In addition, it helps in recreating the register allocation of the failing
+ * kernel and thus make sense of the register dump.
+ *
+ * What is more, the additional complication of a variable length insn arch like
+ * x86 warrants having longer byte sequence before rIP so that the disassembler
+ * can "sync" up properly and find instruction boundaries when decoding the
+ * opcode bytes.
+ *
+ * Thus, the 2/3rds prologue and 64 byte OPCODE_BUFSIZE is just a random
+ * guesstimate in attempt to achieve all of the above.
+ */
+void show_opcodes(u8 *rip, const char *loglvl)
+{
+	unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3;
+	u8 opcodes[OPCODE_BUFSIZE];
+	u8 *ip;
+	int i;
+
+	printk("%sCode: ", loglvl);
+
+	ip = (u8 *)rip - code_prologue;
+	if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) {
+		pr_cont("Bad RIP value.\n");
+		return;
+	}
+
+	for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) {
+		if (ip == rip)
+			pr_cont("<%02x> ", opcodes[i]);
+		else
+			pr_cont("%02x ", opcodes[i]);
+	}
+	pr_cont("\n");
+}
+
+void show_ip(struct pt_regs *regs, const char *loglvl)
+{
+#ifdef CONFIG_X86_32
+	printk("%sEIP: %pS\n", loglvl, (void *)regs->ip);
+#else
+	printk("%sRIP: %04x:%pS\n", loglvl, (int)regs->cs, (void *)regs->ip);
+#endif
+	show_opcodes((u8 *)regs->ip, loglvl);
+}
+
 void show_iret_regs(struct pt_regs *regs)
 {
-	printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
+	show_ip(regs, KERN_DEFAULT);
 	printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
 		regs->sp, regs->flags);
 }
@@ -267,7 +323,6 @@ unsigned long oops_begin(void)
 	bust_spinlocks(1);
 	return flags;
 }
-EXPORT_SYMBOL_GPL(oops_begin);
 NOKPROBE_SYMBOL(oops_begin);
 
 void __noreturn rewind_stack_do_exit(int signr);
@@ -287,6 +342,9 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 	raw_local_irq_restore(flags);
 	oops_exit();
 
+	/* Executive summary in case the oops scrolled away */
+	__show_regs(&exec_summary_regs, true);
+
 	if (!signr)
 		return;
 	if (in_interrupt())
@@ -305,10 +363,10 @@ NOKPROBE_SYMBOL(oops_end);
 
 int __die(const char *str, struct pt_regs *regs, long err)
 {
-#ifdef CONFIG_X86_32
-	unsigned short ss;
-	unsigned long sp;
-#endif
+	/* Save the regs of the first oops for the executive summary later. */
+	if (!die_counter)
+		exec_summary_regs = *regs;
+
 	printk(KERN_DEFAULT
 	       "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
 	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT"         : "",
@@ -318,26 +376,13 @@ int __die(const char *str, struct pt_regs *regs, long err)
 	       IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
 	       (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");
 
+	show_regs(regs);
+	print_modules();
+
 	if (notify_die(DIE_OOPS, str, regs, err,
 			current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
 		return 1;
 
-	print_modules();
-	show_regs(regs);
-#ifdef CONFIG_X86_32
-	if (user_mode(regs)) {
-		sp = regs->sp;
-		ss = regs->ss;
-	} else {
-		sp = kernel_stack_pointer(regs);
-		savesegment(ss, ss);
-	}
-	printk(KERN_EMERG "EIP: %pS SS:ESP: %04x:%08lx\n",
-	       (void *)regs->ip, ss, sp);
-#else
-	/* Executive summary in case the oops scrolled away */
-	printk(KERN_ALERT "RIP: %pS RSP: %016lx\n", (void *)regs->ip, regs->sp);
-#endif
 	return 0;
 }
 NOKPROBE_SYMBOL(__die);
@@ -356,30 +401,9 @@ void die(const char *str, struct pt_regs *regs, long err)
 	oops_end(flags, regs, sig);
 }
 
-static int __init code_bytes_setup(char *s)
-{
-	ssize_t ret;
-	unsigned long val;
-
-	if (!s)
-		return -EINVAL;
-
-	ret = kstrtoul(s, 0, &val);
-	if (ret)
-		return ret;
-
-	code_bytes = val;
-	if (code_bytes > 8192)
-		code_bytes = 8192;
-
-	return 1;
-}
-__setup("code_bytes=", code_bytes_setup);
-
 void show_regs(struct pt_regs *regs)
 {
 	bool all = true;
-	int i;
 
 	show_regs_print_info(KERN_DEFAULT);
 
@@ -389,36 +413,8 @@ void show_regs(struct pt_regs *regs)
 	__show_regs(regs, all);
 
 	/*
-	 * When in-kernel, we also print out the stack and code at the
-	 * time of the fault..
+	 * When in-kernel, we also print out the stack at the time of the fault..
 	 */
-	if (!user_mode(regs)) {
-		unsigned int code_prologue = code_bytes * 43 / 64;
-		unsigned int code_len = code_bytes;
-		unsigned char c;
-		u8 *ip;
-
+	if (!user_mode(regs))
 		show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
-
-		printk(KERN_DEFAULT "Code: ");
-
-		ip = (u8 *)regs->ip - code_prologue;
-		if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
-			/* try starting at IP */
-			ip = (u8 *)regs->ip;
-			code_len = code_len - code_prologue + 1;
-		}
-		for (i = 0; i < code_len; i++, ip++) {
-			if (ip < (u8 *)PAGE_OFFSET ||
-					probe_kernel_address(ip, c)) {
-				pr_cont(" Bad RIP value.");
-				break;
-			}
-			if (ip == (u8 *)regs->ip)
-				pr_cont("<%02x> ", c);
-			else
-				pr_cont("%02x ", c);
-		}
-	}
-	pr_cont("\n");
 }
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 6a2cb1442e05..d1f25c831447 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -155,7 +155,8 @@ static void __init __e820__range_add(struct e820_table *table, u64 start, u64 si
 	int x = table->nr_entries;
 
 	if (x >= ARRAY_SIZE(table->entries)) {
-		pr_err("e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", start, start + size - 1);
+		pr_err("too many entries; ignoring [mem %#010llx-%#010llx]\n",
+		       start, start + size - 1);
 		return;
 	}
 
@@ -190,9 +191,10 @@ void __init e820__print_table(char *who)
 	int i;
 
 	for (i = 0; i < e820_table->nr_entries; i++) {
-		pr_info("%s: [mem %#018Lx-%#018Lx] ", who,
-		       e820_table->entries[i].addr,
-		       e820_table->entries[i].addr + e820_table->entries[i].size - 1);
+		pr_info("%s: [mem %#018Lx-%#018Lx] ",
+			who,
+			e820_table->entries[i].addr,
+			e820_table->entries[i].addr + e820_table->entries[i].size - 1);
 
 		e820_print_type(e820_table->entries[i].type);
 		pr_cont("\n");
@@ -574,7 +576,7 @@ void __init e820__update_table_print(void)
 	if (e820__update_table(e820_table))
 		return;
 
-	pr_info("e820: modified physical RAM map:\n");
+	pr_info("modified physical RAM map:\n");
 	e820__print_table("modified");
 }
 
@@ -636,9 +638,8 @@ __init void e820__setup_pci_gap(void)
 	if (!found) {
 #ifdef CONFIG_X86_64
 		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
-		pr_err(
-			"e820: Cannot find an available gap in the 32-bit address range\n"
-			"e820: PCI devices with unassigned 32-bit BARs may not work!\n");
+		pr_err("Cannot find an available gap in the 32-bit address range\n");
+		pr_err("PCI devices with unassigned 32-bit BARs may not work!\n");
 #else
 		gapstart = 0x10000000;
 #endif
@@ -649,7 +650,8 @@ __init void e820__setup_pci_gap(void)
 	 */
 	pci_mem_start = gapstart;
 
-	pr_info("e820: [mem %#010lx-%#010lx] available for PCI devices\n", gapstart, gapstart + gapsize - 1);
+	pr_info("[mem %#010lx-%#010lx] available for PCI devices\n",
+		gapstart, gapstart + gapsize - 1);
 }
 
 /*
@@ -711,7 +713,7 @@ void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len)
 	memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));
 
 	early_memunmap(sdata, data_len);
-	pr_info("e820: extended physical RAM map:\n");
+	pr_info("extended physical RAM map:\n");
 	e820__print_table("extended");
 }
 
@@ -780,7 +782,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align)
 	addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 	if (addr) {
 		e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
-		pr_info("e820: update e820_table_kexec for e820__memblock_alloc_reserved()\n");
+		pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n");
 		e820__update_table_kexec();
 	}
 
@@ -830,8 +832,8 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type
 	if (last_pfn > max_arch_pfn)
 		last_pfn = max_arch_pfn;
 
-	pr_info("e820: last_pfn = %#lx max_arch_pfn = %#lx\n",
-			 last_pfn, max_arch_pfn);
+	pr_info("last_pfn = %#lx max_arch_pfn = %#lx\n",
+		last_pfn, max_arch_pfn);
 	return last_pfn;
 }
 
@@ -1005,7 +1007,7 @@ void __init e820__finish_early_params(void)
 		if (e820__update_table(e820_table) < 0)
 			early_panic("Invalid user supplied memory map");
 
-		pr_info("e820: user-defined physical RAM map:\n");
+		pr_info("user-defined physical RAM map:\n");
 		e820__print_table("user");
 	}
 }
@@ -1238,7 +1240,7 @@ void __init e820__memory_setup(void)
 	memcpy(e820_table_kexec, e820_table, sizeof(*e820_table_kexec));
 	memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));
 
-	pr_info("e820: BIOS-provided physical RAM map:\n");
+	pr_info("BIOS-provided physical RAM map:\n");
 	e820__print_table(who);
 }
 
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bae0d32e327b..da5d8ac60062 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -28,8 +28,6 @@
 #include <asm/irq_remapping.h>
 #include <asm/early_ioremap.h>
 
-#define dev_err(msg)  pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg)
-
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
 	u32 htcfg;
@@ -617,7 +615,8 @@ static void __init apple_airport_reset(int bus, int slot, int func)
 
 		pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
 		if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
-			dev_err("Cannot power up Apple AirPort card\n");
+			pr_err("pci 0000:%02x:%02x.%d: Cannot power up Apple AirPort card\n",
+			       bus, slot, func);
 			return;
 		}
 	}
@@ -628,7 +627,8 @@ static void __init apple_airport_reset(int bus, int slot, int func)
 
 	mmio = early_ioremap(addr, BCM4331_MMIO_SIZE);
 	if (!mmio) {
-		dev_err("Cannot iomap Apple AirPort card\n");
+		pr_err("pci 0000:%02x:%02x.%d: Cannot iomap Apple AirPort card\n",
+		       bus, slot, func);
 		return;
 	}
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 0c408f8c4ed4..a21d6ace648e 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -6,6 +6,10 @@
  */
 
 #define DISABLE_BRANCH_PROFILING
+
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
+
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
@@ -32,11 +36,6 @@
 #include <asm/microcode.h>
 #include <asm/kasan.h>
 
-#ifdef CONFIG_X86_5LEVEL
-#undef pgtable_l5_enabled
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
-
 /*
  * Manage page tables very early on.
  */
@@ -45,8 +44,7 @@ static unsigned int __initdata next_early_pgt;
 pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
 #ifdef CONFIG_X86_5LEVEL
-unsigned int __pgtable_l5_enabled __ro_after_init;
-EXPORT_SYMBOL(__pgtable_l5_enabled);
+unsigned int __pgtable_l5_enabled __initdata;
 unsigned int pgdir_shift __ro_after_init = 39;
 EXPORT_SYMBOL(pgdir_shift);
 unsigned int ptrs_per_p4d __ro_after_init = 1;
@@ -82,13 +80,14 @@ static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
 
 static bool __head check_la57_support(unsigned long physaddr)
 {
-	if (native_cpuid_eax(0) < 7)
-		return false;
-
-	if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+	/*
+	 * 5-level paging is detected and enabled at kernel decomression
+	 * stage. Only check if it has been enabled there.
+	 */
+	if (!(native_read_cr4() & X86_CR4_LA57))
 		return false;
 
-	*fixup_int(&pgtable_l5_enabled, physaddr) = 1;
+	*fixup_int(&__pgtable_l5_enabled, physaddr) = 1;
 	*fixup_int(&pgdir_shift, physaddr) = 48;
 	*fixup_int(&ptrs_per_p4d, physaddr) = 512;
 	*fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5;
@@ -104,6 +103,12 @@ static bool __head check_la57_support(unsigned long physaddr)
 }
 #endif
 
+/* Code in __startup_64() can be relocated during execution, but the compiler
+ * doesn't have to generate PC-relative relocations when accessing globals from
+ * that function. Clang actually does not generate them, which leads to
+ * boot-time crashes. To work around this problem, every global pointer must
+ * be adjusted using fixup_pointer().
+ */
 unsigned long __head __startup_64(unsigned long physaddr,
 				  struct boot_params *bp)
 {
@@ -113,6 +118,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	p4dval_t *p4d;
 	pudval_t *pud;
 	pmdval_t *pmd, pmd_entry;
+	pteval_t *mask_ptr;
 	bool la57;
 	int i;
 	unsigned int *next_pgt_ptr;
@@ -196,7 +202,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
 
 	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
 	/* Filter out unsupported __PAGE_KERNEL_* bits: */
-	pmd_entry &= __supported_pte_mask;
+	mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr);
+	pmd_entry &= *mask_ptr;
 	pmd_entry += sme_get_me_mask();
 	pmd_entry +=  physaddr;
 
@@ -273,7 +280,7 @@ again:
 	 * critical -- __PAGE_OFFSET would point us back into the dynamic
 	 * range and we might end up looping forever...
 	 */
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		p4d_p = pgd_p;
 	else if (pgd)
 		p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 8ce4212e2b8d..b6be34ee88e9 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -975,8 +975,7 @@ int __init hpet_enable(void)
 	cfg &= ~(HPET_CFG_ENABLE | HPET_CFG_LEGACY);
 	hpet_writel(cfg, HPET_CFG);
 	if (cfg)
-		pr_warn("HPET: Unrecognized bits %#x set in global cfg\n",
-			cfg);
+		pr_warn("Unrecognized bits %#x set in global cfg\n", cfg);
 
 	for (i = 0; i <= last; ++i) {
 		cfg = hpet_readl(HPET_Tn_CFG(i));
@@ -988,7 +987,7 @@ int __init hpet_enable(void)
 			 | HPET_TN_64BIT_CAP | HPET_TN_32BIT | HPET_TN_ROUTE
 			 | HPET_TN_FSB | HPET_TN_FSB_CAP);
 		if (cfg)
-			pr_warn("HPET: Unrecognized bits %#x set in cfg#%u\n",
+			pr_warn("Unrecognized bits %#x set in cfg#%u\n",
 				cfg, i);
 	}
 	hpet_print_config();
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index fa183a131edc..108c48d0d40e 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL2.0
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Jailhouse paravirt_ops implementation
  *
@@ -37,7 +37,7 @@ static uint32_t __init jailhouse_detect(void)
 	return jailhouse_cpuid_base();
 }
 
-static void jailhouse_get_wallclock(struct timespec *now)
+static void jailhouse_get_wallclock(struct timespec64 *now)
 {
 	memset(now, 0, sizeof(*now));
 }
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 3182908b7e6c..7326078eaa7a 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -398,11 +398,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	 * little bit simple
 	 */
 	efi_map_sz = efi_get_runtime_map_size();
-	efi_map_sz = ALIGN(efi_map_sz, 16);
 	params_cmdline_sz = sizeof(struct boot_params) + cmdline_len +
 				MAX_ELFCOREHDR_STR_LEN;
 	params_cmdline_sz = ALIGN(params_cmdline_sz, 16);
-	kbuf.bufsz = params_cmdline_sz + efi_map_sz +
+	kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) +
 				sizeof(struct setup_data) +
 				sizeof(struct efi_setup_data);
 
@@ -410,7 +409,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	if (!params)
 		return ERR_PTR(-ENOMEM);
 	efi_map_offset = params_cmdline_sz;
-	efi_setup_data_offset = efi_map_offset + efi_map_sz;
+	efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16);
 
 	/* Copy setup header onto bootparams. Documentation/x86/boot.txt */
 	setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0715f827607c..6f4d42377fe5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -370,6 +370,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 	if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;
 
+	/* We should not singlestep on the exception masking instructions */
+	if (insn_masking_exception(insn))
+		return 0;
+
 #ifdef CONFIG_X86_64
 	/* Only x86_64 has RIP relative instructions */
 	if (insn_rip_relative(insn)) {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7867417cfaff..5b2300b818af 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -457,7 +457,7 @@ static void __init sev_map_percpu_data(void)
 static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
 {
 	native_smp_prepare_cpus(max_cpus);
-	if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+	if (kvm_para_has_hint(KVM_HINTS_REALTIME))
 		static_branch_disable(&virt_spin_lock_key);
 }
 
@@ -553,7 +553,7 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
-	    !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
 		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
 
@@ -649,7 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
 	int cpu;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
-	    !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		for_each_possible_cpu(cpu) {
 			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
@@ -745,7 +745,7 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
-	if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+	if (kvm_para_has_hint(KVM_HINTS_REALTIME))
 		return;
 
 	__pv_init_lock_hash();
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 8b26c9e01cc4..bf8d1eb7fca3 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -53,7 +53,7 @@ static struct pvclock_wall_clock *wall_clock;
  * have elapsed since the hypervisor wrote the data. So we try to account for
  * that with system time
  */
-static void kvm_get_wallclock(struct timespec *now)
+static void kvm_get_wallclock(struct timespec64 *now)
 {
 	struct pvclock_vcpu_time_info *vcpu_time;
 	int low, high;
@@ -72,7 +72,7 @@ static void kvm_get_wallclock(struct timespec *now)
 	put_cpu();
 }
 
-static int kvm_set_wallclock(const struct timespec *now)
+static int kvm_set_wallclock(const struct timespec64 *now)
 {
 	return -ENODEV;
 }
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index d41d896481b8..c9b14020f4dd 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -166,7 +166,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 		 */
 		pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL);
 		/* Filter out unsuppored __PAGE_KERNEL* bits: */
-		pgprot_val(pte_prot) |= __supported_pte_mask;
+		pgprot_val(pte_prot) &= __supported_pte_mask;
 		pte = pfn_pte(pfn, pte_prot);
 		set_pte_at(mm, va, ptep, pte);
 		pte_unmap_unlock(ptep, ptl);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 60cdec6628b0..d1ab07ec8c9a 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -57,12 +57,17 @@ static void load_segments(void)
 static void machine_kexec_free_page_tables(struct kimage *image)
 {
 	free_page((unsigned long)image->arch.pgd);
+	image->arch.pgd = NULL;
 #ifdef CONFIG_X86_PAE
 	free_page((unsigned long)image->arch.pmd0);
+	image->arch.pmd0 = NULL;
 	free_page((unsigned long)image->arch.pmd1);
+	image->arch.pmd1 = NULL;
 #endif
 	free_page((unsigned long)image->arch.pte0);
+	image->arch.pte0 = NULL;
 	free_page((unsigned long)image->arch.pte1);
+	image->arch.pte1 = NULL;
 }
 
 static int machine_kexec_alloc_page_tables(struct kimage *image)
@@ -79,7 +84,6 @@ static int machine_kexec_alloc_page_tables(struct kimage *image)
 	    !image->arch.pmd0 || !image->arch.pmd1 ||
 #endif
 	    !image->arch.pte0 || !image->arch.pte1) {
-		machine_kexec_free_page_tables(image);
 		return -ENOMEM;
 	}
 	return 0;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index a5e55d832d0a..4c8acdfdc5a7 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -39,9 +39,13 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 static void free_transition_pgtable(struct kimage *image)
 {
 	free_page((unsigned long)image->arch.p4d);
+	image->arch.p4d = NULL;
 	free_page((unsigned long)image->arch.pud);
+	image->arch.pud = NULL;
 	free_page((unsigned long)image->arch.pmd);
+	image->arch.pmd = NULL;
 	free_page((unsigned long)image->arch.pte);
+	image->arch.pte = NULL;
 }
 
 static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
@@ -91,7 +95,6 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
 	return 0;
 err:
-	free_transition_pgtable(image);
 	return result;
 }
 
@@ -351,7 +354,8 @@ void arch_crash_save_vmcoreinfo(void)
 {
 	VMCOREINFO_NUMBER(phys_base);
 	VMCOREINFO_SYMBOL(init_top_pgt);
-	VMCOREINFO_NUMBER(pgtable_l5_enabled);
+	vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n",
+			pgtable_l5_enabled());
 
 #ifdef CONFIG_NUMA
 	VMCOREINFO_SYMBOL(node_data);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 77625b60a510..ab5d9dd668d2 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -15,13 +15,11 @@
 #include <asm/x86_init.h>
 #include <asm/iommu_table.h>
 
-static int forbid_dac __read_mostly;
+static bool disable_dac_quirk __read_mostly;
 
 const struct dma_map_ops *dma_ops = &dma_direct_ops;
 EXPORT_SYMBOL(dma_ops);
 
-static int iommu_sac_force __read_mostly;
-
 #ifdef CONFIG_IOMMU_DEBUG
 int panic_on_overflow __read_mostly = 1;
 int force_iommu __read_mostly = 1;
@@ -55,9 +53,6 @@ struct device x86_dma_fallback_dev = {
 };
 EXPORT_SYMBOL(x86_dma_fallback_dev);
 
-/* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES       65536
-
 void __init pci_iommu_alloc(void)
 {
 	struct iommu_table_entry *p;
@@ -76,7 +71,7 @@ void __init pci_iommu_alloc(void)
 	}
 }
 
-bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
+bool arch_dma_alloc_attrs(struct device **dev)
 {
 	if (!*dev)
 		*dev = &x86_dma_fallback_dev;
@@ -125,13 +120,13 @@ static __init int iommu_setup(char *p)
 		if (!strncmp(p, "nomerge", 7))
 			iommu_merge = 0;
 		if (!strncmp(p, "forcesac", 8))
-			iommu_sac_force = 1;
+			pr_warn("forcesac option ignored.\n");
 		if (!strncmp(p, "allowdac", 8))
-			forbid_dac = 0;
+			pr_warn("allowdac option ignored.\n");
 		if (!strncmp(p, "nodac", 5))
-			forbid_dac = 1;
+			pr_warn("nodac option ignored.\n");
 		if (!strncmp(p, "usedac", 6)) {
-			forbid_dac = -1;
+			disable_dac_quirk = true;
 			return 1;
 		}
 #ifdef CONFIG_SWIOTLB
@@ -156,40 +151,9 @@ static __init int iommu_setup(char *p)
 }
 early_param("iommu", iommu_setup);
 
-int arch_dma_supported(struct device *dev, u64 mask)
-{
-#ifdef CONFIG_PCI
-	if (mask > 0xffffffff && forbid_dac > 0) {
-		dev_info(dev, "PCI: Disallowing DAC for device\n");
-		return 0;
-	}
-#endif
-
-	/* Tell the device to use SAC when IOMMU force is on.  This
-	   allows the driver to use cheaper accesses in some cases.
-
-	   Problem with this is that if we overflow the IOMMU area and
-	   return DAC as fallback address the device may not handle it
-	   correctly.
-
-	   As a special case some controllers have a 39bit address
-	   mode that is as efficient as 32bit (aic79xx). Don't force
-	   SAC for these.  Assume all masks <= 40 bits are of this
-	   type. Normally this doesn't make any difference, but gives
-	   more gentle handling of IOMMU overflow. */
-	if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) {
-		dev_info(dev, "Force SAC with mask %Lx\n", mask);
-		return 0;
-	}
-
-	return 1;
-}
-EXPORT_SYMBOL(arch_dma_supported);
-
 static int __init pci_iommu_init(void)
 {
 	struct iommu_table_entry *p;
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 
 #ifdef CONFIG_PCI
 	dma_debug_add_bus(&pci_bus_type);
@@ -209,11 +173,17 @@ rootfs_initcall(pci_iommu_init);
 #ifdef CONFIG_PCI
 /* Many VIA bridges seem to corrupt data for DAC. Disable it here */
 
+static int via_no_dac_cb(struct pci_dev *pdev, void *data)
+{
+	pdev->dev.dma_32bit_limit = true;
+	return 0;
+}
+
 static void via_no_dac(struct pci_dev *dev)
 {
-	if (forbid_dac == 0) {
+	if (!disable_dac_quirk) {
 		dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n");
-		forbid_dac = 1;
+		pci_walk_bus(dev->subordinate, via_no_dac_cb, NULL);
 	}
 }
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID,
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
deleted file mode 100644
index ac7ea3a8242f..000000000000
--- a/arch/x86/kernel/pci-nommu.c
+++ /dev/null
@@ -1,90 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Fallback functions when the main IOMMU code is not compiled in. This
-   code is roughly equivalent to i386. */
-#include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/pci.h>
-#include <linux/mm.h>
-
-#include <asm/processor.h>
-#include <asm/iommu.h>
-#include <asm/dma.h>
-
-#define NOMMU_MAPPING_ERROR		0
-
-static int
-check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
-{
-	if (hwdev && !dma_capable(hwdev, bus, size)) {
-		if (*hwdev->dma_mask >= DMA_BIT_MASK(32))
-			printk(KERN_ERR
-			    "nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
-				name, (long long)bus, size,
-				(long long)*hwdev->dma_mask);
-		return 0;
-	}
-	return 1;
-}
-
-static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir,
-				 unsigned long attrs)
-{
-	dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset;
-	WARN_ON(size == 0);
-	if (!check_addr("map_single", dev, bus, size))
-		return NOMMU_MAPPING_ERROR;
-	return bus;
-}
-
-/* Map a set of buffers described by scatterlist in streaming
- * mode for DMA.  This is the scatter-gather version of the
- * above pci_map_single interface.  Here the scatter gather list
- * elements are each tagged with the appropriate dma address
- * and length.  They are obtained via sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- *       DMA address/length pairs than there are SG table elements.
- *       (for example via virtual mapping capabilities)
- *       The routine returns the number of addr/length pairs actually
- *       used, at most nents.
- *
- * Device ownership issues as mentioned above for pci_map_single are
- * the same here.
- */
-static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir,
-			unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	WARN_ON(nents == 0 || sg[0].length == 0);
-
-	for_each_sg(sg, s, nents, i) {
-		BUG_ON(!sg_page(s));
-		s->dma_address = sg_phys(s);
-		if (!check_addr("map_sg", hwdev, s->dma_address, s->length))
-			return 0;
-		s->dma_length = s->length;
-	}
-	return nents;
-}
-
-static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == NOMMU_MAPPING_ERROR;
-}
-
-const struct dma_map_ops nommu_dma_ops = {
-	.alloc			= dma_generic_alloc_coherent,
-	.free			= dma_generic_free_coherent,
-	.map_sg			= nommu_map_sg,
-	.map_page		= nommu_map_page,
-	.is_phys		= 1,
-	.mapping_error		= nommu_mapping_error,
-	.dma_supported		= x86_dma_supported,
-};
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e47b2dbbdef3..c06c4c16c6b6 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -151,17 +151,19 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 	regs_user_copy->sp = user_regs->sp;
 	regs_user_copy->cs = user_regs->cs;
 	regs_user_copy->ss = user_regs->ss;
-
 	/*
-	 * Most system calls don't save these registers, don't report them.
+	 * Store user space frame-pointer value on sample
+	 * to facilitate stack unwinding for cases when
+	 * user space executable code has such support
+	 * enabled at compile time:
 	 */
+	regs_user_copy->bp = user_regs->bp;
+
 	regs_user_copy->bx = -1;
-	regs_user_copy->bp = -1;
 	regs_user_copy->r12 = -1;
 	regs_user_copy->r13 = -1;
 	regs_user_copy->r14 = -1;
 	regs_user_copy->r15 = -1;
-
 	/*
 	 * For this to be at all useful, we need a reasonable guess for
 	 * the ABI.  Be careful: we're in NMI context, and we're
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 03408b942adb..30ca2d1a9231 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -38,6 +38,7 @@
 #include <asm/switch_to.h>
 #include <asm/desc.h>
 #include <asm/prctl.h>
+#include <asm/spec-ctrl.h>
 
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -278,6 +279,148 @@ static inline void switch_to_bitmap(struct tss_struct *tss,
 	}
 }
 
+#ifdef CONFIG_SMP
+
+struct ssb_state {
+	struct ssb_state	*shared_state;
+	raw_spinlock_t		lock;
+	unsigned int		disable_state;
+	unsigned long		local_state;
+};
+
+#define LSTATE_SSB	0
+
+static DEFINE_PER_CPU(struct ssb_state, ssb_state);
+
+void speculative_store_bypass_ht_init(void)
+{
+	struct ssb_state *st = this_cpu_ptr(&ssb_state);
+	unsigned int this_cpu = smp_processor_id();
+	unsigned int cpu;
+
+	st->local_state = 0;
+
+	/*
+	 * Shared state setup happens once on the first bringup
+	 * of the CPU. It's not destroyed on CPU hotunplug.
+	 */
+	if (st->shared_state)
+		return;
+
+	raw_spin_lock_init(&st->lock);
+
+	/*
+	 * Go over HT siblings and check whether one of them has set up the
+	 * shared state pointer already.
+	 */
+	for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) {
+		if (cpu == this_cpu)
+			continue;
+
+		if (!per_cpu(ssb_state, cpu).shared_state)
+			continue;
+
+		/* Link it to the state of the sibling: */
+		st->shared_state = per_cpu(ssb_state, cpu).shared_state;
+		return;
+	}
+
+	/*
+	 * First HT sibling to come up on the core.  Link shared state of
+	 * the first HT sibling to itself. The siblings on the same core
+	 * which come up later will see the shared state pointer and link
+	 * themself to the state of this CPU.
+	 */
+	st->shared_state = st;
+}
+
+/*
+ * Logic is: First HT sibling enables SSBD for both siblings in the core
+ * and last sibling to disable it, disables it for the whole core. This how
+ * MSR_SPEC_CTRL works in "hardware":
+ *
+ *  CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL
+ */
+static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
+{
+	struct ssb_state *st = this_cpu_ptr(&ssb_state);
+	u64 msr = x86_amd_ls_cfg_base;
+
+	if (!static_cpu_has(X86_FEATURE_ZEN)) {
+		msr |= ssbd_tif_to_amd_ls_cfg(tifn);
+		wrmsrl(MSR_AMD64_LS_CFG, msr);
+		return;
+	}
+
+	if (tifn & _TIF_SSBD) {
+		/*
+		 * Since this can race with prctl(), block reentry on the
+		 * same CPU.
+		 */
+		if (__test_and_set_bit(LSTATE_SSB, &st->local_state))
+			return;
+
+		msr |= x86_amd_ls_cfg_ssbd_mask;
+
+		raw_spin_lock(&st->shared_state->lock);
+		/* First sibling enables SSBD: */
+		if (!st->shared_state->disable_state)
+			wrmsrl(MSR_AMD64_LS_CFG, msr);
+		st->shared_state->disable_state++;
+		raw_spin_unlock(&st->shared_state->lock);
+	} else {
+		if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state))
+			return;
+
+		raw_spin_lock(&st->shared_state->lock);
+		st->shared_state->disable_state--;
+		if (!st->shared_state->disable_state)
+			wrmsrl(MSR_AMD64_LS_CFG, msr);
+		raw_spin_unlock(&st->shared_state->lock);
+	}
+}
+#else
+static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
+{
+	u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);
+
+	wrmsrl(MSR_AMD64_LS_CFG, msr);
+}
+#endif
+
+static __always_inline void amd_set_ssb_virt_state(unsigned long tifn)
+{
+	/*
+	 * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL,
+	 * so ssbd_tif_to_spec_ctrl() just works.
+	 */
+	wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
+}
+
+static __always_inline void intel_set_ssb_state(unsigned long tifn)
+{
+	u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn);
+
+	wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+}
+
+static __always_inline void __speculative_store_bypass_update(unsigned long tifn)
+{
+	if (static_cpu_has(X86_FEATURE_VIRT_SSBD))
+		amd_set_ssb_virt_state(tifn);
+	else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+		amd_set_core_ssb_state(tifn);
+	else
+		intel_set_ssb_state(tifn);
+}
+
+void speculative_store_bypass_update(unsigned long tif)
+{
+	preempt_disable();
+	__speculative_store_bypass_update(tif);
+	preempt_enable();
+}
+
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss)
 {
@@ -309,6 +452,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 
 	if ((tifp ^ tifn) & _TIF_NOCPUID)
 		set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
+
+	if ((tifp ^ tifn) & _TIF_SSBD)
+		__speculative_store_bypass_update(tifn);
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 5224c6099184..0ae659de21eb 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -76,16 +76,14 @@ void __show_regs(struct pt_regs *regs, int all)
 		savesegment(gs, gs);
 	}
 
-	printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
-	printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
-		raw_smp_processor_id());
+	show_ip(regs, KERN_DEFAULT);
 
 	printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
 		regs->ax, regs->bx, regs->cx, regs->dx);
 	printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
 		regs->si, regs->di, regs->bp, sp);
-	printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
-	       (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss);
+	printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n",
+	       (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags);
 
 	if (!all)
 		return;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 4b100fe0f508..12bb445fb98d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -542,6 +542,7 @@ void set_personality_64bit(void)
 	clear_thread_flag(TIF_X32);
 	/* Pretend that this comes from a 64bit execve */
 	task_pt_regs(current)->orig_ax = __NR_execve;
+	current_thread_info()->status &= ~TS_COMPAT;
 
 	/* Ensure the corresponding mm is not marked. */
 	if (current->mm)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index ed5c4cdf0a34..e2ee403865eb 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1377,7 +1377,6 @@ static void fill_sigtrap_info(struct task_struct *tsk,
 	tsk->thread.trap_nr = X86_TRAP_DB;
 	tsk->thread.error_code = error_code;
 
-	memset(info, 0, sizeof(*info));
 	info->si_signo = SIGTRAP;
 	info->si_code = si_code;
 	info->si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL;
@@ -1395,6 +1394,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 {
 	struct siginfo info;
 
+	clear_siginfo(&info);
 	fill_sigtrap_info(tsk, regs, error_code, si_code, &info);
 	/* Send us the fake SIGTRAP */
 	force_sig_info(SIGTRAP, &info, tsk);
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 761f6af6efa5..637982efecd8 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -123,28 +123,35 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 
 void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
 			    struct pvclock_vcpu_time_info *vcpu_time,
-			    struct timespec *ts)
+			    struct timespec64 *ts)
 {
 	u32 version;
 	u64 delta;
-	struct timespec now;
+	struct timespec64 now;
 
 	/* get wallclock at system boot */
 	do {
 		version = wall_clock->version;
 		rmb();		/* fetch version before time */
+		/*
+		 * Note: wall_clock->sec is a u32 value, so it can
+		 * only store dates between 1970 and 2106. To allow
+		 * times beyond that, we need to create a new hypercall
+		 * interface with an extended pvclock_wall_clock structure
+		 * like ARM has.
+		 */
 		now.tv_sec  = wall_clock->sec;
 		now.tv_nsec = wall_clock->nsec;
 		rmb();		/* fetch time before checking version */
 	} while ((wall_clock->version & 1) || (version != wall_clock->version));
 
 	delta = pvclock_clocksource_read(vcpu_time);	/* time since system boot */
-	delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
+	delta += now.tv_sec * NSEC_PER_SEC + now.tv_nsec;
 
 	now.tv_nsec = do_div(delta, NSEC_PER_SEC);
 	now.tv_sec = delta;
 
-	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+	set_normalized_timespec64(ts, now.tv_sec, now.tv_nsec);
 }
 
 void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti)
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index f7b82ed7b5b5..586f718b8e95 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -39,7 +39,7 @@ EXPORT_SYMBOL(rtc_lock);
  * jump to the next second precisely 500 ms later. Check the Motorola
  * MC146818A or Dallas DS12887 data sheet for details.
  */
-int mach_set_rtc_mmss(const struct timespec *now)
+int mach_set_rtc_mmss(const struct timespec64 *now)
 {
 	unsigned long long nowtime = now->tv_sec;
 	struct rtc_time tm;
@@ -60,7 +60,7 @@ int mach_set_rtc_mmss(const struct timespec *now)
 	return retval;
 }
 
-void mach_get_cmos_time(struct timespec *now)
+void mach_get_cmos_time(struct timespec64 *now)
 {
 	unsigned int status, year, mon, day, hour, min, sec, century = 0;
 	unsigned long flags;
@@ -118,7 +118,7 @@ void mach_get_cmos_time(struct timespec *now)
 	} else
 		year += CMOS_YEARS_OFFS;
 
-	now->tv_sec = mktime(year, mon, day, hour, min, sec);
+	now->tv_sec = mktime64(year, mon, day, hour, min, sec);
 	now->tv_nsec = 0;
 }
 
@@ -145,13 +145,13 @@ void rtc_cmos_write(unsigned char val, unsigned char addr)
 }
 EXPORT_SYMBOL(rtc_cmos_write);
 
-int update_persistent_clock(struct timespec now)
+int update_persistent_clock64(struct timespec64 now)
 {
 	return x86_platform.set_wallclock(&now);
 }
 
 /* not static: needed by APM */
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	x86_platform.get_wallclock(ts);
 }
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6285697b6e56..5c623dfe39d1 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -50,6 +50,7 @@
 #include <linux/init_ohci1394_dma.h>
 #include <linux/kvm_para.h>
 #include <linux/dma-contiguous.h>
+#include <xen/xen.h>
 
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -534,6 +535,11 @@ static void __init reserve_crashkernel(void)
 		high = true;
 	}
 
+	if (xen_pv_domain()) {
+		pr_info("Ignoring crashkernel for a Xen PV domain\n");
+		return;
+	}
+
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
 		/*
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 14c057f29979..9ccbf0576cd0 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -29,7 +29,7 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(NSIGFPE  != 15);
 	BUILD_BUG_ON(NSIGSEGV != 7);
 	BUILD_BUG_ON(NSIGBUS  != 5);
-	BUILD_BUG_ON(NSIGTRAP != 4);
+	BUILD_BUG_ON(NSIGTRAP != 5);
 	BUILD_BUG_ON(NSIGCHLD != 6);
 	BUILD_BUG_ON(NSIGSYS  != 1);
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ff99e2b6fc54..c2f7d1d2a5c3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -77,13 +77,9 @@
 #include <asm/i8259.h>
 #include <asm/misc.h>
 #include <asm/qspinlock.h>
-
-/* Number of siblings per CPU package */
-int smp_num_siblings = 1;
-EXPORT_SYMBOL(smp_num_siblings);
-
-/* Last level cache ID of each logical CPU */
-DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
+#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
+#include <asm/spec-ctrl.h>
 
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -242,6 +238,8 @@ static void notrace start_secondary(void *unused)
 	 */
 	check_tsc_sync_target();
 
+	speculative_store_bypass_ht_init();
+
 	/*
 	 * Lock vector_lock, set CPU online and bring the vector
 	 * allocator online. Online must be set with vector_lock held
@@ -390,15 +388,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
+/*
+ * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs.
+ *
+ * These are Intel CPUs that enumerate an LLC that is shared by
+ * multiple NUMA nodes. The LLC on these systems is shared for
+ * off-package data access but private to the NUMA node (half
+ * of the package) for on-package access.
+ *
+ * CPUID (the source of the information about the LLC) can only
+ * enumerate the cache as being shared *or* unshared, but not
+ * this particular configuration. The CPU in this case enumerates
+ * the cache to be shared across the entire package (spanning both
+ * NUMA nodes).
+ */
+
+static const struct x86_cpu_id snc_cpu[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X },
+	{}
+};
+
 static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
 	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
-	if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID &&
-	    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2))
-		return topology_sane(c, o, "llc");
+	/* Do not match if we do not have a valid APICID for cpu: */
+	if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
+		return false;
 
-	return false;
+	/* Do not match if LLC id does not match: */
+	if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
+		return false;
+
+	/*
+	 * Allow the SNC topology without warning. Return of false
+	 * means 'c' does not share the LLC of 'o'. This will be
+	 * reflected to userspace.
+	 */
+	if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu))
+		return false;
+
+	return topology_sane(c, o, "llc");
 }
 
 /*
@@ -456,7 +486,8 @@ static struct sched_domain_topology_level x86_topology[] = {
 
 /*
  * Set if a package/die has multiple NUMA nodes inside.
- * AMD Magny-Cours and Intel Cluster-on-Die have this.
+ * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
+ * Sub-NUMA Clustering have this.
  */
 static bool x86_has_numa_in_package;
 
@@ -1257,6 +1288,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	set_mtrr_aps_delayed_init();
 
 	smp_quirk_init_udelay();
+
+	speculative_store_bypass_ht_init();
 }
 
 void arch_enable_nonboot_cpus_begin(void)
@@ -1536,6 +1569,8 @@ static inline void mwait_play_dead(void)
 	void *mwait_ptr;
 	int i;
 
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return;
 	if (!this_cpu_has(X86_FEATURE_MWAIT))
 		return;
 	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index a3f15ed545b5..6a78d4b36a79 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
@@ -19,7 +20,6 @@
 #include <linux/elf.h>
 
 #include <asm/elf.h>
-#include <asm/compat.h>
 #include <asm/ia32.h>
 #include <asm/syscalls.h>
 #include <asm/mpx.h>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 03f3d7695dac..a535dd64de63 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -299,6 +299,7 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
 			NOTIFY_STOP) {
 		cond_local_irq_enable(regs);
+		clear_siginfo(&info);
 		do_trap(trapnr, signr, str, regs, error_code,
 			fill_trap_info(regs, signr, trapnr, &info));
 	}
@@ -854,6 +855,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 
 	task->thread.trap_nr	= trapnr;
 	task->thread.error_code = error_code;
+	clear_siginfo(&info);
 	info.si_signo		= SIGFPE;
 	info.si_errno		= 0;
 	info.si_addr		= (void __user *)uprobe_get_trap_addr(regs);
@@ -929,6 +931,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	local_irq_enable();
 
+	clear_siginfo(&info);
 	info.si_signo = SIGILL;
 	info.si_errno = 0;
 	info.si_code = ILL_BADSTK;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ef32297ff17e..74392d9d51e0 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -317,7 +317,7 @@ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2)
 	hpet2 -= hpet1;
 	tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
 	do_div(tmp, 1000000);
-	do_div(deltatsc, tmp);
+	deltatsc = div64_u64(deltatsc, tmp);
 
 	return (unsigned long) deltatsc;
 }
@@ -1067,6 +1067,7 @@ static struct clocksource clocksource_tsc_early = {
 	.resume			= tsc_resume,
 	.mark_unstable		= tsc_cs_mark_unstable,
 	.tick_stable		= tsc_cs_tick_stable,
+	.list			= LIST_HEAD_INIT(clocksource_tsc_early.list),
 };
 
 /*
@@ -1086,6 +1087,7 @@ static struct clocksource clocksource_tsc = {
 	.resume			= tsc_resume,
 	.mark_unstable		= tsc_cs_mark_unstable,
 	.tick_stable		= tsc_cs_tick_stable,
+	.list			= LIST_HEAD_INIT(clocksource_tsc.list),
 };
 
 void mark_tsc_unstable(char *reason)
@@ -1098,13 +1100,9 @@ void mark_tsc_unstable(char *reason)
 		clear_sched_clock_stable();
 	disable_sched_clock_irqtime();
 	pr_info("Marking TSC unstable due to %s\n", reason);
-	/* Change only the rating, when not registered */
-	if (clocksource_tsc.mult) {
-		clocksource_mark_unstable(&clocksource_tsc);
-	} else {
-		clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
-		clocksource_tsc.rating = 0;
-	}
+
+	clocksource_mark_unstable(&clocksource_tsc_early);
+	clocksource_mark_unstable(&clocksource_tsc);
 }
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);
@@ -1244,7 +1242,7 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 
 	/* Don't bother refining TSC on unstable systems */
 	if (tsc_unstable)
-		return;
+		goto unreg;
 
 	/*
 	 * Since the work is started early in boot, we may be
@@ -1297,11 +1295,12 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 
 out:
 	if (tsc_unstable)
-		return;
+		goto unreg;
 
 	if (boot_cpu_has(X86_FEATURE_ART))
 		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
 	clocksource_unregister(&clocksource_tsc_early);
 }
 
@@ -1311,8 +1310,8 @@ static int __init init_tsc_clocksource(void)
 	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
 		return 0;
 
-	if (check_tsc_unstable())
-		return 0;
+	if (tsc_unstable)
+		goto unreg;
 
 	if (tsc_clocksource_reliable)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
@@ -1328,6 +1327,7 @@ static int __init init_tsc_clocksource(void)
 		if (boot_cpu_has(X86_FEATURE_ART))
 			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
 		clocksource_unregister(&clocksource_tsc_early);
 		return 0;
 	}
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index f44ce0fb3583..ff20b35e98dd 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -278,6 +278,7 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
 	tsk->thread.error_code	= X86_PF_USER | X86_PF_WRITE;
 	tsk->thread.trap_nr	= X86_TRAP_PF;
 
+	clear_siginfo(&info);
 	info.si_signo	= SIGSEGV;
 	info.si_errno	= 0;
 	info.si_code	= SEGV_MAPERR;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 85c7ef23d99f..58d8d800875d 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -299,6 +299,10 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 	if (is_prefix_bad(insn))
 		return -ENOTSUPP;
 
+	/* We should not singlestep on the exception masking instructions */
+	if (insn_masking_exception(insn))
+		return -ENOTSUPP;
+
 	if (x86_64)
 		good_insns = good_insns_64;
 	else
@@ -1079,8 +1083,8 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
 		return orig_ret_vaddr;
 
 	if (nleft != rasize) {
-		pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, "
-			"%%ip=%#lx\n", current->pid, regs->sp, regs->ip);
+		pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
+		       current->pid, regs->sp, regs->ip);
 
 		force_sig_info(SIGSEGV, SEND_SIG_FORCED, current);
 	}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 795f3a80e576..5e1458f609a1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -117,11 +117,11 @@ SECTIONS
 
 #ifdef CONFIG_X86_64
 		. = ALIGN(PAGE_SIZE);
-		VMLINUX_SYMBOL(__entry_trampoline_start) = .;
+		__entry_trampoline_start = .;
 		_entry_trampoline = .;
 		*(.entry_trampoline)
 		. = ALIGN(PAGE_SIZE);
-		VMLINUX_SYMBOL(__entry_trampoline_end) = .;
+		__entry_trampoline_end = .;
 		ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
 #endif
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 82055b90a8b3..92bf2f2e7cdd 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -379,7 +379,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	/* cpuid 0x80000008.ebx */
 	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
-		F(IBPB) | F(IBRS);
+		F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD);
 
 	/* cpuid 0xC0000001.edx */
 	const u32 kvm_cpuid_C000_0001_edx_x86_features =
@@ -408,7 +408,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	/* cpuid 7.0.edx*/
 	const u32 kvm_cpuid_7_0_edx_x86_features =
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
-		F(ARCH_CAPABILITIES);
+		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
@@ -495,6 +495,11 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 				entry->ecx &= ~F(PKU);
 			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
 			cpuid_mask(&entry->edx, CPUID_7_EDX);
+			/*
+			 * We emulate ARCH_CAPABILITIES in software even
+			 * if the host doesn't support it.
+			 */
+			entry->edx |= F(ARCH_CAPABILITIES);
 		} else {
 			entry->ebx = 0;
 			entry->ecx = 0;
@@ -647,13 +652,20 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			g_phys_as = phys_as;
 		entry->eax = g_phys_as | (virt_as << 8);
 		entry->edx = 0;
-		/* IBRS and IBPB aren't necessarily present in hardware cpuid */
-		if (boot_cpu_has(X86_FEATURE_IBPB))
-			entry->ebx |= F(IBPB);
-		if (boot_cpu_has(X86_FEATURE_IBRS))
-			entry->ebx |= F(IBRS);
+		/*
+		 * IBRS, IBPB and VIRT_SSBD aren't necessarily present in
+		 * hardware cpuid
+		 */
+		if (boot_cpu_has(X86_FEATURE_AMD_IBPB))
+			entry->ebx |= F(AMD_IBPB);
+		if (boot_cpu_has(X86_FEATURE_AMD_IBRS))
+			entry->ebx |= F(AMD_IBRS);
+		if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
 		entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
 		cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX);
+		if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
 		break;
 	}
 	case 0x80000019:
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 98618e397342..46ff64da44ca 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1260,12 +1260,16 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 	}
 }
 
-static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
 {
-	struct kvm_run *run = vcpu->run;
+	kvm_hv_hypercall_set_result(vcpu, result);
+	++vcpu->stat.hypercalls;
+	return kvm_skip_emulated_instruction(vcpu);
+}
 
-	kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result);
-	return 1;
+static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+{
+	return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result);
 }
 
 static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
@@ -1296,8 +1300,10 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
 	if (param & ~KVM_HYPERV_CONN_ID_MASK)
 		return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
-	/* conn_to_evt is protected by vcpu->kvm->srcu */
+	/* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */
+	rcu_read_lock();
 	eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param);
+	rcu_read_unlock();
 	if (!eventfd)
 		return HV_STATUS_INVALID_PORT_ID;
 
@@ -1348,7 +1354,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	/* Hypercall continuation is not supported yet */
 	if (rep_cnt || rep_idx) {
 		ret = HV_STATUS_INVALID_HYPERCALL_CODE;
-		goto set_result;
+		goto out;
 	}
 
 	switch (code) {
@@ -1379,9 +1385,8 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-set_result:
-	kvm_hv_hypercall_set_result(vcpu, ret);
-	return 1;
+out:
+	return kvm_hv_hypercall_complete(vcpu, ret);
 }
 
 void kvm_hv_init_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 70dcb5548022..3773c4625114 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1463,23 +1463,6 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 	local_irq_restore(flags);
 }
 
-static void start_sw_period(struct kvm_lapic *apic)
-{
-	if (!apic->lapic_timer.period)
-		return;
-
-	if (apic_lvtt_oneshot(apic) &&
-	    ktime_after(ktime_get(),
-			apic->lapic_timer.target_expiration)) {
-		apic_timer_expired(apic);
-		return;
-	}
-
-	hrtimer_start(&apic->lapic_timer.timer,
-		apic->lapic_timer.target_expiration,
-		HRTIMER_MODE_ABS_PINNED);
-}
-
 static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor)
 {
 	ktime_t now, remaining;
@@ -1539,11 +1522,43 @@ static bool set_target_expiration(struct kvm_lapic *apic)
 
 static void advance_periodic_target_expiration(struct kvm_lapic *apic)
 {
-	apic->lapic_timer.tscdeadline +=
-		nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+	ktime_t now = ktime_get();
+	u64 tscl = rdtsc();
+	ktime_t delta;
+
+	/*
+	 * Synchronize both deadlines to the same time source or
+	 * differences in the periods (caused by differences in the
+	 * underlying clocks or numerical approximation errors) will
+	 * cause the two to drift apart over time as the errors
+	 * accumulate.
+	 */
 	apic->lapic_timer.target_expiration =
 		ktime_add_ns(apic->lapic_timer.target_expiration,
 				apic->lapic_timer.period);
+	delta = ktime_sub(apic->lapic_timer.target_expiration, now);
+	apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
+		nsec_to_cycles(apic->vcpu, delta);
+}
+
+static void start_sw_period(struct kvm_lapic *apic)
+{
+	if (!apic->lapic_timer.period)
+		return;
+
+	if (ktime_after(ktime_get(),
+			apic->lapic_timer.target_expiration)) {
+		apic_timer_expired(apic);
+
+		if (apic_lvtt_oneshot(apic))
+			return;
+
+		advance_periodic_target_expiration(apic);
+	}
+
+	hrtimer_start(&apic->lapic_timer.timer,
+		apic->lapic_timer.target_expiration,
+		HRTIMER_MODE_ABS_PINNED);
 }
 
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8494dbae41b9..d634f0332c0f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3007,6 +3007,7 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
 {
 	siginfo_t info;
 
+	clear_siginfo(&info);
 	info.si_signo	= SIGBUS;
 	info.si_errno	= 0;
 	info.si_code	= BUS_MCEERR_AR;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b58787daf9f8..26110c202b19 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -49,7 +49,7 @@
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
 #include <asm/irq_remapping.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 
 #include <asm/virtext.h>
 #include "trace.h"
@@ -213,6 +213,12 @@ struct vcpu_svm {
 	} host;
 
 	u64 spec_ctrl;
+	/*
+	 * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
+	 * translated into the appropriate L2_CFG bits on the host to
+	 * perform speculative control.
+	 */
+	u64 virt_spec_ctrl;
 
 	u32 *msrpm;
 
@@ -1423,12 +1429,23 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
 	seg->base = 0;
 }
 
+static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (is_guest_mode(vcpu))
+		return svm->nested.hsave->control.tsc_offset;
+
+	return vcpu->arch.tsc_offset;
+}
+
 static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 g_tsc_offset = 0;
 
 	if (is_guest_mode(vcpu)) {
+		/* Write L1's TSC offset.  */
 		g_tsc_offset = svm->vmcb->control.tsc_offset -
 			       svm->nested.hsave->control.tsc_offset;
 		svm->nested.hsave->control.tsc_offset = offset;
@@ -2049,6 +2066,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	vcpu->arch.microcode_version = 0x01000065;
 	svm->spec_ctrl = 0;
+	svm->virt_spec_ctrl = 0;
 
 	if (!init_event) {
 		svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
@@ -3322,6 +3340,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Restore the original control entries */
 	copy_vmcb_control_area(vmcb, hsave);
 
+	svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset;
 	kvm_clear_exception_queue(&svm->vcpu);
 	kvm_clear_interrupt_queue(&svm->vcpu);
 
@@ -3482,10 +3501,12 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	/* We don't want to see VMMCALLs from a nested guest */
 	clr_intercept(svm, INTERCEPT_VMMCALL);
 
+	svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset;
+	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset;
+
 	svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext;
 	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
 	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
-	svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
 	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
 	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
 
@@ -4035,12 +4056,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	switch (msr_info->index) {
-	case MSR_IA32_TSC: {
-		msr_info->data = svm->vmcb->control.tsc_offset +
-			kvm_scale_tsc(vcpu, rdtsc());
-
-		break;
-	}
 	case MSR_STAR:
 		msr_info->data = svm->vmcb->save.star;
 		break;
@@ -4100,11 +4115,18 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
+		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
 			return 1;
 
 		msr_info->data = svm->spec_ctrl;
 		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+			return 1;
+
+		msr_info->data = svm->virt_spec_ctrl;
+		break;
 	case MSR_F15H_IC_CFG: {
 
 		int family, model;
@@ -4193,12 +4215,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		svm->vmcb->save.g_pat = data;
 		mark_dirty(svm->vmcb, VMCB_NPT);
 		break;
-	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
+		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
 			return 1;
 
 		/* The STIBP bit doesn't fault even if it's not advertised */
@@ -4225,7 +4244,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBPB))
+		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB))
 			return 1;
 
 		if (data & ~PRED_CMD_IBPB)
@@ -4239,6 +4258,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			break;
 		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
 		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+			return 1;
+
+		if (data & ~SPEC_CTRL_SSBD)
+			return 1;
+
+		svm->virt_spec_ctrl = data;
+		break;
 	case MSR_STAR:
 		svm->vmcb->save.star = data;
 		break;
@@ -5265,9 +5294,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		}
 
 		if (!ret && svm) {
-			trace_kvm_pi_irte_update(svm->vcpu.vcpu_id,
-						 host_irq, e->gsi,
-						 vcpu_info.vector,
+			trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
+						 e->gsi, vcpu_info.vector,
 						 vcpu_info.pi_desc_addr, set);
 		}
 
@@ -5553,8 +5581,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 * is no need to worry about the conditional branch over the wrmsr
 	 * being speculatively taken.
 	 */
-	if (svm->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
 
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
@@ -5648,6 +5675,18 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 		);
 
+	/* Eliminate branch target predictions from guest mode */
+	vmexit_fill_RSB();
+
+#ifdef CONFIG_X86_64
+	wrmsrl(MSR_GS_BASE, svm->host.gs_base);
+#else
+	loadsegment(fs, svm->host.fs);
+#ifndef CONFIG_X86_32_LAZY_GS
+	loadsegment(gs, svm->host.gs);
+#endif
+#endif
+
 	/*
 	 * We do not use IBRS in the kernel. If this vCPU has used the
 	 * SPEC_CTRL MSR it may have left it on; save the value and
@@ -5666,20 +5705,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
 		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
-	if (svm->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
-
-	/* Eliminate branch target predictions from guest mode */
-	vmexit_fill_RSB();
-
-#ifdef CONFIG_X86_64
-	wrmsrl(MSR_GS_BASE, svm->host.gs_base);
-#else
-	loadsegment(fs, svm->host.fs);
-#ifndef CONFIG_X86_32_LAZY_GS
-	loadsegment(gs, svm->host.gs);
-#endif
-#endif
+	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
 
 	reload_tss(vcpu);
 
@@ -5782,7 +5808,7 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
-static bool svm_has_high_real_mode_segbase(void)
+static bool svm_has_emulated_msr(int index)
 {
 	return true;
 }
@@ -7008,7 +7034,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
 	.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
-	.cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
+	.has_emulated_msr = svm_has_emulated_msr,
 
 	.vcpu_create = svm_create_vcpu,
 	.vcpu_free = svm_free_vcpu,
@@ -7102,6 +7128,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
+	.read_l1_tsc_offset = svm_read_l1_tsc_offset,
 	.write_tsc_offset = svm_write_tsc_offset,
 
 	.set_tdp_cr3 = set_tdp_cr3,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index aafcc9881e88..40aa29204baf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,7 +51,7 @@
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/mmu_context.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 #include <asm/mshyperv.h>
 
 #include "trace.h"
@@ -1494,6 +1494,12 @@ static inline bool cpu_has_vmx_vmfunc(void)
 		SECONDARY_EXEC_ENABLE_VMFUNC;
 }
 
+static bool vmx_umip_emulated(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_DESC;
+}
+
 static inline bool report_flexpriority(void)
 {
 	return flexpriority_enabled;
@@ -2880,18 +2886,15 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 		vmx_update_msr_bitmap(&vmx->vcpu);
 }
 
-/*
- * reads and returns guest's timestamp counter "register"
- * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
- * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
- */
-static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
+static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 {
-	u64 host_tsc, tsc_offset;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	host_tsc = rdtsc();
-	tsc_offset = vmcs_read64(TSC_OFFSET);
-	return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
+	if (is_guest_mode(vcpu) &&
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
+
+	return vcpu->arch.tsc_offset;
 }
 
 /*
@@ -3524,12 +3527,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
-	case MSR_IA32_TSC:
-		msr_info->data = guest_read_tsc(vcpu);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
@@ -3646,17 +3645,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
-	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr_info);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
 		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
 			return 1;
 
 		vmx->spec_ctrl = data;
@@ -3682,7 +3677,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
@@ -4553,12 +4547,6 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
 	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
 }
 
-static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
-{
-	if (enable_ept)
-		vmx_flush_tlb(vcpu, true);
-}
-
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -4776,14 +4764,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	else
 		hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
 
-	if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
-		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
-			      SECONDARY_EXEC_DESC);
-		hw_cr4 &= ~X86_CR4_UMIP;
-	} else if (!is_guest_mode(vcpu) ||
-	           !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
-		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+	if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
+		if (cr4 & X86_CR4_UMIP) {
+			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 				SECONDARY_EXEC_DESC);
+			hw_cr4 &= ~X86_CR4_UMIP;
+		} else if (!is_guest_mode(vcpu) ||
+			!nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
+			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+					SECONDARY_EXEC_DESC);
+	}
 
 	if (cr4 & X86_CR4_VMXE) {
 		/*
@@ -9287,7 +9277,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	} else {
 		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
@@ -9315,7 +9305,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
 			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 }
 
@@ -9495,9 +9485,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 }
 STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
 
-static bool vmx_has_high_real_mode_segbase(void)
+static bool vmx_has_emulated_msr(int index)
 {
-	return enable_unrestricted_guest || emulate_invalid_guest_state;
+	switch (index) {
+	case MSR_IA32_SMBASE:
+		/*
+		 * We cannot do SMM unless we can run the guest in big
+		 * real mode.
+		 */
+		return enable_unrestricted_guest || emulate_invalid_guest_state;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		/* This is AMD only.  */
+		return false;
+	default:
+		return true;
+	}
 }
 
 static bool vmx_mpx_supported(void)
@@ -9512,12 +9514,6 @@ static bool vmx_xsaves_supported(void)
 		SECONDARY_EXEC_XSAVES;
 }
 
-static bool vmx_umip_emulated(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_DESC;
-}
-
 static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -9735,8 +9731,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * is no need to worry about the conditional branch over the wrmsr
 	 * being speculatively taken.
 	 */
-	if (vmx->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 
@@ -9884,8 +9879,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
 		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
-	if (vmx->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
@@ -10608,6 +10602,16 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+	    !page_address_valid(vcpu, vmcs12->apic_access_addr))
+		return -EINVAL;
+	else
+		return 0;
+}
+
 static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
 					   struct vmcs12 *vmcs12)
 {
@@ -11176,11 +11180,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 	}
 
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
-		vmcs_write64(TSC_OFFSET,
-			vcpu->arch.tsc_offset + vmcs12->tsc_offset);
-	else
-		vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
 
@@ -11222,7 +11223,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		}
 	} else if (nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 
 	/*
@@ -11299,6 +11300,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
+	if (nested_vmx_check_apic_access_controls(vcpu, vmcs12))
+		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
 	if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
@@ -11420,6 +11424,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	u32 msr_entry_idx;
 	u32 exit_qual;
+	int r;
 
 	enter_guest_mode(vcpu);
 
@@ -11429,26 +11434,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
 	vmx_segment_cache_clear(vmx);
 
-	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
-		leave_guest_mode(vcpu);
-		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-		nested_vmx_entry_failure(vcpu, vmcs12,
-					 EXIT_REASON_INVALID_STATE, exit_qual);
-		return 1;
-	}
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
+
+	r = EXIT_REASON_INVALID_STATE;
+	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+		goto fail;
 
 	nested_get_vmcs12_pages(vcpu, vmcs12);
 
+	r = EXIT_REASON_MSR_LOAD_FAIL;
 	msr_entry_idx = nested_vmx_load_msr(vcpu,
 					    vmcs12->vm_entry_msr_load_addr,
 					    vmcs12->vm_entry_msr_load_count);
-	if (msr_entry_idx) {
-		leave_guest_mode(vcpu);
-		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-		nested_vmx_entry_failure(vcpu, vmcs12,
-				EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
-		return 1;
-	}
+	if (msr_entry_idx)
+		goto fail;
 
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
@@ -11457,6 +11457,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
 	 */
 	return 0;
+
+fail:
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+	leave_guest_mode(vcpu);
+	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+	nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual);
+	return 1;
 }
 
 /*
@@ -12028,6 +12036,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	leave_guest_mode(vcpu);
 
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+
 	if (likely(!vmx->fail)) {
 		if (exit_reason == -1)
 			sync_vmcs12(vcpu, vmcs12);
@@ -12065,7 +12076,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	} else if (!nested_cpu_has_ept(vmcs12) &&
 		   nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
@@ -12224,10 +12235,16 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
 
 static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u64 tscl = rdtsc();
-	u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
-	u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+	struct vcpu_vmx *vmx;
+	u64 tscl, guest_tscl, delta_tsc;
+
+	if (kvm_mwait_in_guest(vcpu->kvm))
+		return -EOPNOTSUPP;
+
+	vmx = to_vmx(vcpu);
+	tscl = rdtsc();
+	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
 
 	/* Convert to host delta tsc if tsc scaling is enabled */
 	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
@@ -12533,7 +12550,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
 
-		trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
+		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
 		if (set)
@@ -12622,7 +12639,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.hardware_enable = hardware_enable,
 	.hardware_disable = hardware_disable,
 	.cpu_has_accelerated_tpr = report_flexpriority,
-	.cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
+	.has_emulated_msr = vmx_has_emulated_msr,
 
 	.vm_init = vmx_vm_init,
 	.vm_alloc = vmx_vm_alloc,
@@ -12712,6 +12729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
+	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
 	.write_tsc_offset = vmx_write_tsc_offset,
 
 	.set_tdp_cr3 = vmx_set_cr3,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b2ff74b12ec4..71e7cda6d014 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -114,7 +114,7 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
 static bool __read_mostly report_ignored_msrs = true;
 module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
 
-unsigned int min_timer_period_us = 500;
+unsigned int min_timer_period_us = 200;
 module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
 
 static bool __read_mostly kvmclock_periodic_sync = true;
@@ -843,7 +843,10 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4);
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 #ifdef CONFIG_X86_64
-	cr3 &= ~CR3_PCID_INVD;
+	bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+	if (pcid_enabled)
+		cr3 &= ~CR3_PCID_INVD;
 #endif
 
 	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
@@ -1058,6 +1061,7 @@ static u32 emulated_msrs[] = {
 	MSR_SMI_COUNT,
 	MSR_PLATFORM_INFO,
 	MSR_MISC_FEATURES_ENABLES,
+	MSR_AMD64_VIRT_SPEC_CTRL,
 };
 
 static unsigned num_emulated_msrs;
@@ -1490,7 +1494,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 
 static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
 {
-	u64 curr_offset = vcpu->arch.tsc_offset;
+	u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
 	vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
 }
 
@@ -1532,7 +1536,9 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 
 u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 {
-	return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
+	u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
+
+	return tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
 }
 EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
 
@@ -2362,6 +2368,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vcpu->arch.smbase = data;
 		break;
+	case MSR_IA32_TSC:
+		kvm_write_tsc(vcpu, msr_info);
+		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
 			return 1;
@@ -2605,6 +2614,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = vcpu->arch.microcode_version;
 		break;
+	case MSR_IA32_TSC:
+		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+		break;
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -2819,7 +2831,8 @@ out:
 static inline bool kvm_can_mwait_in_guest(void)
 {
 	return boot_cpu_has(X86_FEATURE_MWAIT) &&
-		!boot_cpu_has_bug(X86_BUG_MONITOR);
+		!boot_cpu_has_bug(X86_BUG_MONITOR) &&
+		boot_cpu_has(X86_FEATURE_ARAT);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -2894,7 +2907,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * fringe case that is not enabled except via specific settings
 		 * of the module parameters.
 		 */
-		r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+		r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
 		break;
 	case KVM_CAP_VAPIC:
 		r = !kvm_x86_ops->cpu_has_accelerated_tpr();
@@ -4594,14 +4607,8 @@ static void kvm_init_msr_list(void)
 	num_msrs_to_save = j;
 
 	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		switch (emulated_msrs[i]) {
-		case MSR_IA32_SMBASE:
-			if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
-				continue;
-			break;
-		default:
-			break;
-		}
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+			continue;
 
 		if (j < i)
 			emulated_msrs[j] = emulated_msrs[i];
@@ -6662,9 +6669,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
-	int op_64_bit, r;
-
-	r = kvm_skip_emulated_instruction(vcpu);
+	int op_64_bit;
 
 	if (kvm_hv_hypercall_enabled(vcpu->kvm))
 		return kvm_hv_hypercall(vcpu);
@@ -6712,8 +6717,9 @@ out:
 	if (!op_64_bit)
 		ret = (u32)ret;
 	kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+
 	++vcpu->stat.hypercalls;
-	return r;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
 
@@ -7970,6 +7976,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct msr_data apic_base_msr;
 	int mmu_reset_needed = 0;
+	int cpuid_update_needed = 0;
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 	int ret = -EINVAL;
@@ -8008,8 +8015,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr0 = sregs->cr0;
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
+	cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) &
+				(X86_CR4_OSXSAVE | X86_CR4_PKE));
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
-	if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE))
+	if (cpuid_update_needed)
 		kvm_update_cpuid(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 7d35ce672989..c9492f764902 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -302,13 +302,6 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 	    __rem;						\
 	 })
 
-#define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
-#define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
-#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
-#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
-                                              KVM_X86_DISABLE_EXITS_HTL | \
-                                              KVM_X86_DISABLE_EXITS_PAUSE)
-
 static inline bool kvm_mwait_in_guest(struct kvm *kvm)
 {
 	return kvm->arch.mwait_in_guest;
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 9a53a06e5a3e..c3b527a9f95d 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -184,11 +184,11 @@ ENDPROC(memcpy_orig)
 
 #ifndef CONFIG_UML
 /*
- * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
+ * __memcpy_mcsafe - memory copy with machine check exception handling
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(memcpy_mcsafe_unrolled)
+ENTRY(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -204,58 +204,29 @@ ENTRY(memcpy_mcsafe_unrolled)
 	subl $8, %ecx
 	negl %ecx
 	subl %ecx, %edx
-.L_copy_leading_bytes:
+.L_read_leading_bytes:
 	movb (%rsi), %al
+.L_write_leading_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_leading_bytes
+	jnz .L_read_leading_bytes
 
 .L_8byte_aligned:
-	/* Figure out how many whole cache lines (64-bytes) to copy */
-	movl %edx, %ecx
-	andl $63, %edx
-	shrl $6, %ecx
-	jz .L_no_whole_cache_lines
-
-	/* Loop copying whole cache lines */
-.L_cache_w0: movq (%rsi), %r8
-.L_cache_w1: movq 1*8(%rsi), %r9
-.L_cache_w2: movq 2*8(%rsi), %r10
-.L_cache_w3: movq 3*8(%rsi), %r11
-	movq %r8, (%rdi)
-	movq %r9, 1*8(%rdi)
-	movq %r10, 2*8(%rdi)
-	movq %r11, 3*8(%rdi)
-.L_cache_w4: movq 4*8(%rsi), %r8
-.L_cache_w5: movq 5*8(%rsi), %r9
-.L_cache_w6: movq 6*8(%rsi), %r10
-.L_cache_w7: movq 7*8(%rsi), %r11
-	movq %r8, 4*8(%rdi)
-	movq %r9, 5*8(%rdi)
-	movq %r10, 6*8(%rdi)
-	movq %r11, 7*8(%rdi)
-	leaq 64(%rsi), %rsi
-	leaq 64(%rdi), %rdi
-	decl %ecx
-	jnz .L_cache_w0
-
-	/* Are there any trailing 8-byte words? */
-.L_no_whole_cache_lines:
 	movl %edx, %ecx
 	andl $7, %edx
 	shrl $3, %ecx
 	jz .L_no_whole_words
 
-	/* Copy trailing words */
-.L_copy_trailing_words:
+.L_read_words:
 	movq (%rsi), %r8
-	mov %r8, (%rdi)
-	leaq 8(%rsi), %rsi
-	leaq 8(%rdi), %rdi
+.L_write_words:
+	movq %r8, (%rdi)
+	addq $8, %rsi
+	addq $8, %rdi
 	decl %ecx
-	jnz .L_copy_trailing_words
+	jnz .L_read_words
 
 	/* Any trailing bytes? */
 .L_no_whole_words:
@@ -264,38 +235,53 @@ ENTRY(memcpy_mcsafe_unrolled)
 
 	/* Copy trailing bytes */
 	movl %edx, %ecx
-.L_copy_trailing_bytes:
+.L_read_trailing_bytes:
 	movb (%rsi), %al
+.L_write_trailing_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_trailing_bytes
+	jnz .L_read_trailing_bytes
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorq %rax, %rax
 	ret
-ENDPROC(memcpy_mcsafe_unrolled)
-EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
+ENDPROC(__memcpy_mcsafe)
+EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"
-	/* Return -EFAULT for any failure */
-.L_memcpy_mcsafe_fail:
-	mov	$-EFAULT, %rax
+	/*
+	 * Return number of bytes not copied for any failure. Note that
+	 * there is no "tail" handling since the source buffer is 8-byte
+	 * aligned and poison is cacheline aligned.
+	 */
+.E_read_words:
+	shll	$3, %ecx
+.E_leading_bytes:
+	addl	%edx, %ecx
+.E_trailing_bytes:
+	mov	%ecx, %eax
 	ret
 
+	/*
+	 * For write fault handling, given the destination is unaligned,
+	 * we handle faults on multi-byte writes with a byte-by-byte
+	 * copy up to the write-protected page.
+	 */
+.E_write_words:
+	shll	$3, %ecx
+	addl	%edx, %ecx
+	movl	%ecx, %edx
+	jmp mcsafe_handle_tail
+
 	.previous
 
-	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE(.L_write_words, .E_write_words)
+	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
 #endif
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 75d3776123cc..9c5606d88f61 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -23,13 +23,13 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 	asm volatile(
 		"	testq  %[size8],%[size8]\n"
 		"	jz     4f\n"
-		"0:	movq %[zero],(%[dst])\n"
-		"	addq   %[eight],%[dst]\n"
+		"0:	movq $0,(%[dst])\n"
+		"	addq   $8,%[dst]\n"
 		"	decl %%ecx ; jnz   0b\n"
 		"4:	movq  %[size1],%%rcx\n"
 		"	testl %%ecx,%%ecx\n"
 		"	jz     2f\n"
-		"1:	movb   %b[zero],(%[dst])\n"
+		"1:	movb   $0,(%[dst])\n"
 		"	incq   %[dst]\n"
 		"	decl %%ecx ; jnz  1b\n"
 		"2:\n"
@@ -40,8 +40,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 		_ASM_EXTABLE(0b,3b)
 		_ASM_EXTABLE(1b,2b)
 		: [size8] "=&c"(size), [dst] "=&D" (__d0)
-		: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr),
-		  [zero] "r" (0UL), [eight] "r" (8UL));
+		: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr));
 	clac();
 	return size;
 }
@@ -75,6 +74,27 @@ copy_user_handle_tail(char *to, char *from, unsigned len)
 	return len;
 }
 
+/*
+ * Similar to copy_user_handle_tail, probe for the write fault point,
+ * but reuse __memcpy_mcsafe in case a new read error is encountered.
+ * clac() is handled in _copy_to_iter_mcsafe().
+ */
+__visible unsigned long
+mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++) {
+		/*
+		 * Call the assembly routine back directly since
+		 * memcpy_mcsafe() may silently fallback to memcpy.
+		 */
+		unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+		if (rem)
+			break;
+	}
+	return len;
+}
+
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 /**
  * clean_cache_range - write back a cache range with CLWB
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 62a7e9f65dec..2f3c9196b834 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
+#include <linux/highmem.h>
 
 #include <asm/pgtable.h>
 
@@ -334,16 +335,16 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
 			   pgprotval_t eff_in, unsigned long P)
 {
 	int i;
-	pte_t *start;
+	pte_t *pte;
 	pgprotval_t prot, eff;
 
-	start = (pte_t *)pmd_page_vaddr(addr);
 	for (i = 0; i < PTRS_PER_PTE; i++) {
-		prot = pte_flags(*start);
-		eff = effective_prot(eff_in, prot);
 		st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
+		pte = pte_offset_map(&addr, st->current_address);
+		prot = pte_flags(*pte);
+		eff = effective_prot(eff_in, prot);
 		note_page(m, st, __pgprot(prot), eff, 5);
-		start++;
+		pte_unmap(pte);
 	}
 }
 #ifdef CONFIG_KASAN
@@ -359,7 +360,7 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
 				void *pt)
 {
 	if (__pa(pt) == __pa(kasan_zero_pmd) ||
-	    (pgtable_l5_enabled && __pa(pt) == __pa(kasan_zero_p4d)) ||
+	    (pgtable_l5_enabled() && __pa(pt) == __pa(kasan_zero_p4d)) ||
 	    __pa(pt) == __pa(kasan_zero_pud)) {
 		pgprotval_t prot = pte_flags(kasan_zero_pte[0]);
 		note_page(m, st, __pgprot(prot), 0, 5);
@@ -475,8 +476,8 @@ static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 	}
 }
 
-#define pgd_large(a) (pgtable_l5_enabled ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
-#define pgd_none(a)  (pgtable_l5_enabled ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
+#define pgd_large(a) (pgtable_l5_enabled() ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
+#define pgd_none(a)  (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
 
 static inline bool is_hypervisor_range(int idx)
 {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 73bd8c95ac71..9a84a0d08727 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -209,6 +209,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
 	unsigned lsb = 0;
 	siginfo_t info;
 
+	clear_siginfo(&info);
 	info.si_signo	= si_signo;
 	info.si_errno	= 0;
 	info.si_code	= si_code;
@@ -439,7 +440,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_k))
 		return -1;
 
-	if (pgtable_l5_enabled) {
+	if (pgtable_l5_enabled()) {
 		if (pgd_none(*pgd)) {
 			set_pgd(pgd, *pgd_k);
 			arch_flush_lazy_mmu_mode();
@@ -454,7 +455,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (p4d_none(*p4d_k))
 		return -1;
 
-	if (p4d_none(*p4d) && !pgtable_l5_enabled) {
+	if (p4d_none(*p4d) && !pgtable_l5_enabled()) {
 		set_p4d(p4d, *p4d_k);
 		arch_flush_lazy_mmu_mode();
 	} else {
@@ -828,6 +829,8 @@ static inline void
 show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 		unsigned long address, struct task_struct *tsk)
 {
+	const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG;
+
 	if (!unhandled_signal(tsk, SIGSEGV))
 		return;
 
@@ -835,13 +838,14 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 		return;
 
 	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx",
-		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
-		tsk->comm, task_pid_nr(tsk), address,
+		loglvl, tsk->comm, task_pid_nr(tsk), address,
 		(void *)regs->ip, (void *)regs->sp, error_code);
 
 	print_vma_addr(KERN_CONT " in ", regs->ip);
 
 	printk(KERN_CONT "\n");
+
+	show_opcodes((u8 *)regs->ip, loglvl);
 }
 
 static void
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index a2f0c7e20fb0..fe7a12599d8e 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -123,7 +123,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 		result = ident_p4d_init(info, p4d, addr, next);
 		if (result)
 			return result;
-		if (pgtable_l5_enabled) {
+		if (pgtable_l5_enabled()) {
 			set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
 		} else {
 			/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0a400606dea0..17383f9677fa 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -180,7 +180,7 @@ static void sync_global_pgds_l4(unsigned long start, unsigned long end)
  */
 void sync_global_pgds(unsigned long start, unsigned long end)
 {
-	if (pgtable_l5_enabled)
+	if (pgtable_l5_enabled())
 		sync_global_pgds_l5(start, end);
 	else
 		sync_global_pgds_l4(start, end);
@@ -643,7 +643,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 	unsigned long vaddr = (unsigned long)__va(paddr);
 	int i = p4d_index(vaddr);
 
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask);
 
 	for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) {
@@ -723,7 +723,7 @@ kernel_physical_mapping_init(unsigned long paddr_start,
 					   page_size_mask);
 
 		spin_lock(&init_mm.page_table_lock);
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			pgd_populate(&init_mm, pgd, p4d);
 		else
 			p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d);
@@ -1100,7 +1100,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
 		 * 5-level case we should free them. This code will have to change
 		 * to adapt for boot-time switching between 4 and 5 level page tables.
 		 */
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			free_pud_table(pud_base, p4d);
 	}
 
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 980dbebd0ca7..e3e77527f8df 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -2,10 +2,8 @@
 #define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 
-#ifdef CONFIG_X86_5LEVEL
-/* Too early to use cpu_feature_enabled() */
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
 
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
@@ -182,7 +180,7 @@ static void __init clear_pgds(unsigned long start,
 		 * With folded p4d, pgd_clear() is nop, use p4d_clear()
 		 * instead.
 		 */
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			pgd_clear(pgd);
 		else
 			p4d_clear(p4d_offset(pgd, start));
@@ -197,7 +195,7 @@ static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr)
 {
 	unsigned long p4d;
 
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return (p4d_t *)pgd;
 
 	p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK;
@@ -284,7 +282,7 @@ void __init kasan_early_init(void)
 	for (i = 0; i < PTRS_PER_PUD; i++)
 		kasan_zero_pud[i] = __pud(pud_val);
 
-	for (i = 0; pgtable_l5_enabled && i < PTRS_PER_P4D; i++)
+	for (i = 0; pgtable_l5_enabled() && i < PTRS_PER_P4D; i++)
 		kasan_zero_p4d[i] = __p4d(p4d_val);
 
 	kasan_map_early_shadow(early_top_pgt);
@@ -315,7 +313,7 @@ void __init kasan_init(void)
 	 * bunch of things like kernel code, modules, EFI mapping, etc.
 	 * We need to take extra steps to not overwrite them.
 	 */
-	if (pgtable_l5_enabled) {
+	if (pgtable_l5_enabled()) {
 		void *ptr;
 
 		ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 615cc03ced84..61db77b0eda9 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -78,7 +78,7 @@ void __init kernel_randomize_memory(void)
 	struct rnd_state rand_state;
 	unsigned long remain_entropy;
 
-	vaddr_start = pgtable_l5_enabled ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
+	vaddr_start = pgtable_l5_enabled() ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
 	vaddr = vaddr_start;
 
 	/*
@@ -124,7 +124,7 @@ void __init kernel_randomize_memory(void)
 		 */
 		entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
 		prandom_bytes_state(&rand_state, &rand, sizeof(rand));
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			entropy = (rand % (entropy + 1)) & P4D_MASK;
 		else
 			entropy = (rand % (entropy + 1)) & PUD_MASK;
@@ -136,7 +136,7 @@ void __init kernel_randomize_memory(void)
 		 * randomization alignment.
 		 */
 		vaddr += get_padding(&kaslr_regions[i]);
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			vaddr = round_up(vaddr + 1, P4D_SIZE);
 		else
 			vaddr = round_up(vaddr + 1, PUD_SIZE);
@@ -212,7 +212,7 @@ void __meminit init_trampoline(void)
 		return;
 	}
 
-	if (pgtable_l5_enabled)
+	if (pgtable_l5_enabled())
 		init_trampoline_p4d();
 	else
 		init_trampoline_pud();
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 25504d5aa816..fa150855647c 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -136,13 +136,13 @@ static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
 
 	/* whine about and ignore invalid blks */
 	if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
-		pr_warning("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
-			   nid, start, end - 1);
+		pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+			nid, start, end - 1);
 		return 0;
 	}
 
 	if (mi->nr_blks >= NR_NODE_MEMBLKS) {
-		pr_err("NUMA: too many memblk ranges\n");
+		pr_err("too many memblk ranges\n");
 		return -EINVAL;
 	}
 
@@ -267,14 +267,14 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 			 */
 			if (bi->end > bj->start && bi->start < bj->end) {
 				if (bi->nid != bj->nid) {
-					pr_err("NUMA: node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n",
+					pr_err("node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n",
 					       bi->nid, bi->start, bi->end - 1,
 					       bj->nid, bj->start, bj->end - 1);
 					return -EINVAL;
 				}
-				pr_warning("NUMA: Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n",
-					   bi->nid, bi->start, bi->end - 1,
-					   bj->start, bj->end - 1);
+				pr_warn("Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n",
+					bi->nid, bi->start, bi->end - 1,
+					bj->start, bj->end - 1);
 			}
 
 			/*
@@ -364,7 +364,7 @@ static int __init numa_alloc_distance(void)
 	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
 				      size, PAGE_SIZE);
 	if (!phys) {
-		pr_warning("NUMA: Warning: can't allocate distance table!\n");
+		pr_warn("Warning: can't allocate distance table!\n");
 		/* don't retry until explicitly reset */
 		numa_distance = (void *)1LU;
 		return -ENOMEM;
@@ -410,14 +410,14 @@ void __init numa_set_distance(int from, int to, int distance)
 
 	if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
 			from < 0 || to < 0) {
-		pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
-			    from, to, distance);
+		pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+			     from, to, distance);
 		return;
 	}
 
 	if ((u8)distance != distance ||
 	    (from == to && distance != LOCAL_DISTANCE)) {
-		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+		pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
 			     from, to, distance);
 		return;
 	}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 0f3d50f4c48c..3bded76e8d5c 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -93,6 +93,18 @@ void arch_report_meminfo(struct seq_file *m)
 static inline void split_page_count(int level) { }
 #endif
 
+static inline int
+within(unsigned long addr, unsigned long start, unsigned long end)
+{
+	return addr >= start && addr < end;
+}
+
+static inline int
+within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
+{
+	return addr >= start && addr <= end;
+}
+
 #ifdef CONFIG_X86_64
 
 static inline unsigned long highmap_start_pfn(void)
@@ -106,20 +118,25 @@ static inline unsigned long highmap_end_pfn(void)
 	return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT;
 }
 
-#endif
-
-static inline int
-within(unsigned long addr, unsigned long start, unsigned long end)
+static bool __cpa_pfn_in_highmap(unsigned long pfn)
 {
-	return addr >= start && addr < end;
+	/*
+	 * Kernel text has an alias mapping at a high address, known
+	 * here as "highmap".
+	 */
+	return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn());
 }
 
-static inline int
-within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
+#else
+
+static bool __cpa_pfn_in_highmap(unsigned long pfn)
 {
-	return addr >= start && addr <= end;
+	/* There is no highmap on 32-bit */
+	return false;
 }
 
+#endif
+
 /*
  * Flushing functions
  */
@@ -172,7 +189,7 @@ static void __cpa_flush_all(void *arg)
 
 static void cpa_flush_all(unsigned long cache)
 {
-	BUG_ON(irqs_disabled());
+	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
 
 	on_each_cpu(__cpa_flush_all, (void *) cache, 1);
 }
@@ -236,7 +253,7 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
 	unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
 #endif
 
-	BUG_ON(irqs_disabled());
+	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
 
 	on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1);
 
@@ -1183,6 +1200,10 @@ static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
 		cpa->numpages = 1;
 		cpa->pfn = __pa(vaddr) >> PAGE_SHIFT;
 		return 0;
+
+	} else if (__cpa_pfn_in_highmap(cpa->pfn)) {
+		/* Faults in the highmap are OK, so do not warn: */
+		return -EFAULT;
 	} else {
 		WARN(1, KERN_WARNING "CPA: called for zero pte. "
 			"vaddr = %lx cpa->vaddr = %lx\n", vaddr,
@@ -1335,8 +1356,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 	 * to touch the high mapped kernel as well:
 	 */
 	if (!within(vaddr, (unsigned long)_text, _brk_end) &&
-	    within_inclusive(cpa->pfn, highmap_start_pfn(),
-			     highmap_end_pfn())) {
+	    __cpa_pfn_in_highmap(cpa->pfn)) {
 		unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) +
 					       __START_KERNEL_map - phys_base;
 		alias_cpa = *cpa;
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index d7bc0eea20a5..6e98e0a7c923 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -94,26 +94,27 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
 	 */
 	if (pkey != -1)
 		return pkey;
-	/*
-	 * Look for a protection-key-drive execute-only mapping
-	 * which is now being given permissions that are not
-	 * execute-only.  Move it back to the default pkey.
-	 */
-	if (vma_is_pkey_exec_only(vma) &&
-	    (prot & (PROT_READ|PROT_WRITE))) {
-		return 0;
-	}
+
 	/*
 	 * The mapping is execute-only.  Go try to get the
 	 * execute-only protection key.  If we fail to do that,
 	 * fall through as if we do not have execute-only
-	 * support.
+	 * support in this mm.
 	 */
 	if (prot == PROT_EXEC) {
 		pkey = execute_only_pkey(vma->vm_mm);
 		if (pkey > 0)
 			return pkey;
+	} else if (vma_is_pkey_exec_only(vma)) {
+		/*
+		 * Protections are *not* PROT_EXEC, but the mapping
+		 * is using the exec-only pkey.  This mapping was
+		 * PROT_EXEC and will no longer be.  Move back to
+		 * the default pkey.
+		 */
+		return ARCH_DEFAULT_PKEY;
 	}
+
 	/*
 	 * This is a vanilla, non-pkey mprotect (or we failed to
 	 * setup execute-only), inherit the pkey from the VMA we
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index f1fd52f449e0..4d418e705878 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -421,6 +421,16 @@ static inline bool pti_kernel_image_global_ok(void)
 	if (boot_cpu_has(X86_FEATURE_K8))
 		return false;
 
+	/*
+	 * RANDSTRUCT derives its hardening benefits from the
+	 * attacker's lack of knowledge about the layout of kernel
+	 * data structures.  Keep the kernel image non-global in
+	 * cases where RANDSTRUCT is in use to help keep the layout a
+	 * secret.
+	 */
+	if (IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT))
+		return false;
+
 	return true;
 }
 
@@ -430,12 +440,24 @@ static inline bool pti_kernel_image_global_ok(void)
  */
 void pti_clone_kernel_text(void)
 {
+	/*
+	 * rodata is part of the kernel image and is normally
+	 * readable on the filesystem or on the web.  But, do not
+	 * clone the areas past rodata, they might contain secrets.
+	 */
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
+	unsigned long end = (unsigned long)__end_rodata_hpage_align;
 
 	if (!pti_kernel_image_global_ok())
 		return;
 
+	pr_debug("mapping partial kernel image into user address space\n");
+
+	/*
+	 * Note that this will undo _some_ of the work that
+	 * pti_set_kernel_image_nonglobal() did to clear the
+	 * global bit.
+	 */
 	pti_clone_pmds(start, end, _PAGE_RW);
 }
 
@@ -458,8 +480,6 @@ void pti_set_kernel_image_nonglobal(void)
 	if (pti_kernel_image_global_ok())
 		return;
 
-	pr_debug("set kernel image non-global\n");
-
 	set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
 }
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e055d1a06699..6eb1f34c3c85 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -157,7 +157,7 @@ static void sync_current_stack_to_mm(struct mm_struct *mm)
 	unsigned long sp = current_stack_pointer;
 	pgd_t *pgd = pgd_offset(mm, sp);
 
-	if (pgtable_l5_enabled) {
+	if (pgtable_l5_enabled()) {
 		if (unlikely(pgd_none(*pgd))) {
 			pgd_t *pgd_ref = pgd_offset_k(sp);
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b725154182cc..d765acedc05c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1,4 +1,5 @@
-/* bpf_jit_comp.c : BPF JIT compiler
+/*
+ * bpf_jit_comp.c: BPF JIT compiler
  *
  * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com)
  * Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
@@ -17,7 +18,7 @@
 #include <asm/nospec-branch.h>
 
 /*
- * assembly code in arch/x86/net/bpf_jit.S
+ * Assembly code in arch/x86/net/bpf_jit.S
  */
 extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
 extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
@@ -45,14 +46,15 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT2(b1, b2)		EMIT((b1) + ((b2) << 8), 2)
 #define EMIT3(b1, b2, b3)	EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
 #define EMIT4(b1, b2, b3, b4)   EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+
 #define EMIT1_off32(b1, off) \
-	do {EMIT1(b1); EMIT(off, 4); } while (0)
+	do { EMIT1(b1); EMIT(off, 4); } while (0)
 #define EMIT2_off32(b1, b2, off) \
-	do {EMIT2(b1, b2); EMIT(off, 4); } while (0)
+	do { EMIT2(b1, b2); EMIT(off, 4); } while (0)
 #define EMIT3_off32(b1, b2, b3, off) \
-	do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
+	do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
 #define EMIT4_off32(b1, b2, b3, b4, off) \
-	do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
+	do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
 static bool is_imm8(int value)
 {
@@ -70,9 +72,10 @@ static bool is_uimm32(u64 value)
 }
 
 /* mov dst, src */
-#define EMIT_mov(DST, SRC) \
-	do {if (DST != SRC) \
-		EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
+#define EMIT_mov(DST, SRC)								 \
+	do {										 \
+		if (DST != SRC)								 \
+			EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
 	} while (0)
 
 static int bpf_size_to_x86_bytes(int bpf_size)
@@ -89,7 +92,8 @@ static int bpf_size_to_x86_bytes(int bpf_size)
 		return 0;
 }
 
-/* list of x86 cond jumps opcodes (. + s8)
+/*
+ * List of x86 cond jumps opcodes (. + s8)
  * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
  */
 #define X86_JB  0x72
@@ -106,35 +110,37 @@ static int bpf_size_to_x86_bytes(int bpf_size)
 #define CHOOSE_LOAD_FUNC(K, func) \
 	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
-/* pick a register outside of BPF range for JIT internal work */
+/* Pick a register outside of BPF range for JIT internal work */
 #define AUX_REG (MAX_BPF_JIT_REG + 1)
 
-/* The following table maps BPF registers to x64 registers.
+/*
+ * The following table maps BPF registers to x86-64 registers.
  *
- * x64 register r12 is unused, since if used as base address
+ * x86-64 register R12 is unused, since if used as base address
  * register in load/store instructions, it always needs an
  * extra byte of encoding and is callee saved.
  *
- *  r9 caches skb->len - skb->data_len
- * r10 caches skb->data, and used for blinding (if enabled)
+ * R9  caches skb->len - skb->data_len
+ * R10 caches skb->data, and used for blinding (if enabled)
  */
 static const int reg2hex[] = {
-	[BPF_REG_0] = 0,  /* rax */
-	[BPF_REG_1] = 7,  /* rdi */
-	[BPF_REG_2] = 6,  /* rsi */
-	[BPF_REG_3] = 2,  /* rdx */
-	[BPF_REG_4] = 1,  /* rcx */
-	[BPF_REG_5] = 0,  /* r8 */
-	[BPF_REG_6] = 3,  /* rbx callee saved */
-	[BPF_REG_7] = 5,  /* r13 callee saved */
-	[BPF_REG_8] = 6,  /* r14 callee saved */
-	[BPF_REG_9] = 7,  /* r15 callee saved */
-	[BPF_REG_FP] = 5, /* rbp readonly */
-	[BPF_REG_AX] = 2, /* r10 temp register */
-	[AUX_REG] = 3,    /* r11 temp register */
+	[BPF_REG_0] = 0,  /* RAX */
+	[BPF_REG_1] = 7,  /* RDI */
+	[BPF_REG_2] = 6,  /* RSI */
+	[BPF_REG_3] = 2,  /* RDX */
+	[BPF_REG_4] = 1,  /* RCX */
+	[BPF_REG_5] = 0,  /* R8  */
+	[BPF_REG_6] = 3,  /* RBX callee saved */
+	[BPF_REG_7] = 5,  /* R13 callee saved */
+	[BPF_REG_8] = 6,  /* R14 callee saved */
+	[BPF_REG_9] = 7,  /* R15 callee saved */
+	[BPF_REG_FP] = 5, /* RBP readonly */
+	[BPF_REG_AX] = 2, /* R10 temp register */
+	[AUX_REG] = 3,    /* R11 temp register */
 };
 
-/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15
+/*
+ * is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15
  * which need extra byte of encoding.
  * rax,rcx,...,rbp have simpler encoding
  */
@@ -153,7 +159,7 @@ static bool is_axreg(u32 reg)
 	return reg == BPF_REG_0;
 }
 
-/* add modifiers if 'reg' maps to x64 registers r8..r15 */
+/* Add modifiers if 'reg' maps to x86-64 registers R8..R15 */
 static u8 add_1mod(u8 byte, u32 reg)
 {
 	if (is_ereg(reg))
@@ -170,13 +176,13 @@ static u8 add_2mod(u8 byte, u32 r1, u32 r2)
 	return byte;
 }
 
-/* encode 'dst_reg' register into x64 opcode 'byte' */
+/* Encode 'dst_reg' register into x86-64 opcode 'byte' */
 static u8 add_1reg(u8 byte, u32 dst_reg)
 {
 	return byte + reg2hex[dst_reg];
 }
 
-/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */
+/* Encode 'dst_reg' and 'src_reg' registers into x86-64 opcode 'byte' */
 static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
 {
 	return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
@@ -184,27 +190,28 @@ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
 
 static void jit_fill_hole(void *area, unsigned int size)
 {
-	/* fill whole space with int3 instructions */
+	/* Fill whole space with INT3 instructions */
 	memset(area, 0xcc, size);
 }
 
 struct jit_context {
-	int cleanup_addr; /* epilogue code offset */
+	int cleanup_addr; /* Epilogue code offset */
 	bool seen_ld_abs;
 	bool seen_ax_reg;
 };
 
-/* maximum number of bytes emitted while JITing one eBPF insn */
+/* Maximum number of bytes emitted while JITing one eBPF insn */
 #define BPF_MAX_INSN_SIZE	128
 #define BPF_INSN_SAFETY		64
 
 #define AUX_STACK_SPACE \
-	(32 /* space for rbx, r13, r14, r15 */ + \
-	 8 /* space for skb_copy_bits() buffer */)
+	(32 /* Space for RBX, R13, R14, R15 */ + \
+	  8 /* Space for skb_copy_bits() buffer */)
 
 #define PROLOGUE_SIZE 37
 
-/* emit x64 prologue code for BPF program and check it's size.
+/*
+ * Emit x86-64 prologue code for BPF program and check its size.
  * bpf_tail_call helper will skip it while jumping into another program
  */
 static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
@@ -212,8 +219,11 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-	EMIT1(0x55); /* push rbp */
-	EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
+	/* push rbp */
+	EMIT1(0x55);
+
+	/* mov rbp,rsp */
+	EMIT3(0x48, 0x89, 0xE5);
 
 	/* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */
 	EMIT3_off32(0x48, 0x81, 0xEC,
@@ -222,14 +232,15 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	/* sub rbp, AUX_STACK_SPACE */
 	EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE);
 
-	/* all classic BPF filters use R6(rbx) save it */
+	/* All classic BPF filters use R6(rbx) save it */
 
 	/* mov qword ptr [rbp+0],rbx */
 	EMIT4(0x48, 0x89, 0x5D, 0);
 
-	/* bpf_convert_filter() maps classic BPF register X to R7 and uses R8
-	 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and
-	 * R8(r14). R9(r15) spill could be made conditional, but there is only
+	/*
+	 * bpf_convert_filter() maps classic BPF register X to R7 and uses R8
+	 * as temporary, so all tcpdump filters need to spill/fill R7(R13) and
+	 * R8(R14). R9(R15) spill could be made conditional, but there is only
 	 * one 'bpf_error' return path out of helper functions inside bpf_jit.S
 	 * The overhead of extra spill is negligible for any filter other
 	 * than synthetic ones. Therefore not worth adding complexity.
@@ -243,9 +254,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	EMIT4(0x4C, 0x89, 0x7D, 24);
 
 	if (!ebpf_from_cbpf) {
-		/* Clear the tail call counter (tail_call_cnt): for eBPF tail
+		/*
+		 * Clear the tail call counter (tail_call_cnt): for eBPF tail
 		 * calls we need to reset the counter to 0. It's done in two
-		 * instructions, resetting rax register to 0, and moving it
+		 * instructions, resetting RAX register to 0, and moving it
 		 * to the counter location.
 		 */
 
@@ -260,7 +272,9 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	*pprog = prog;
 }
 
-/* generate the following code:
+/*
+ * Generate the following code:
+ *
  * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
  *   if (index >= array->map.max_entries)
  *     goto out;
@@ -278,23 +292,26 @@ static void emit_bpf_tail_call(u8 **pprog)
 	int label1, label2, label3;
 	int cnt = 0;
 
-	/* rdi - pointer to ctx
+	/*
+	 * rdi - pointer to ctx
 	 * rsi - pointer to bpf_array
 	 * rdx - index in bpf_array
 	 */
 
-	/* if (index >= array->map.max_entries)
-	 *   goto out;
+	/*
+	 * if (index >= array->map.max_entries)
+	 *	goto out;
 	 */
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* Number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
-	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
-	 *   goto out;
+	/*
+	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+	 *	goto out;
 	 */
 	EMIT2_off32(0x8B, 0x85, 36);              /* mov eax, dword ptr [rbp + 36] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
@@ -308,8 +325,9 @@ static void emit_bpf_tail_call(u8 **pprog)
 	EMIT4_off32(0x48, 0x8B, 0x84, 0xD6,       /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
 		    offsetof(struct bpf_array, ptrs));
 
-	/* if (prog == NULL)
-	 *   goto out;
+	/*
+	 * if (prog == NULL)
+	 *	goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
 #define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
@@ -321,7 +339,8 @@ static void emit_bpf_tail_call(u8 **pprog)
 	      offsetof(struct bpf_prog, bpf_func));
 	EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE);   /* add rax, prologue_size */
 
-	/* now we're ready to jump into next BPF program
+	/*
+	 * Wow we're ready to jump into next BPF program
 	 * rdi == ctx (1st arg)
 	 * rax == prog->bpf_func + prologue_size
 	 */
@@ -340,7 +359,8 @@ static void emit_load_skb_data_hlen(u8 **pprog)
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-	/* r9d = skb->len - skb->data_len (headlen)
+	/*
+	 * r9d = skb->len - skb->data_len (headlen)
 	 * r10 = skb->data
 	 */
 	/* mov %r9d, off32(%rdi) */
@@ -361,7 +381,8 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
 	u8 b1, b2, b3;
 	int cnt = 0;
 
-	/* optimization: if imm32 is positive, use 'mov %eax, imm32'
+	/*
+	 * Optimization: if imm32 is positive, use 'mov %eax, imm32'
 	 * (which zero-extends imm32) to save 2 bytes.
 	 */
 	if (sign_propagate && (s32)imm32 < 0) {
@@ -373,7 +394,8 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
 		goto done;
 	}
 
-	/* optimization: if imm32 is zero, use 'xor %eax, %eax'
+	/*
+	 * Optimization: if imm32 is zero, use 'xor %eax, %eax'
 	 * to save 3 bytes.
 	 */
 	if (imm32 == 0) {
@@ -400,7 +422,8 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
 	int cnt = 0;
 
 	if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
-		/* For emitting plain u32, where sign bit must not be
+		/*
+		 * For emitting plain u32, where sign bit must not be
 		 * propagated LLVM tends to load imm64 over mov32
 		 * directly, so save couple of bytes by just doing
 		 * 'mov %eax, imm32' instead.
@@ -525,7 +548,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			else if (is_ereg(dst_reg))
 				EMIT1(add_1mod(0x40, dst_reg));
 
-			/* b3 holds 'normal' opcode, b2 short form only valid
+			/*
+			 * b3 holds 'normal' opcode, b2 short form only valid
 			 * in case dst is eax/rax.
 			 */
 			switch (BPF_OP(insn->code)) {
@@ -593,7 +617,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			/* mov rax, dst_reg */
 			EMIT_mov(BPF_REG_0, dst_reg);
 
-			/* xor edx, edx
+			/*
+			 * xor edx, edx
 			 * equivalent to 'xor rdx, rdx', but one byte less
 			 */
 			EMIT2(0x31, 0xd2);
@@ -655,7 +680,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			}
 			break;
 		}
-			/* shifts */
+			/* Shifts */
 		case BPF_ALU | BPF_LSH | BPF_K:
 		case BPF_ALU | BPF_RSH | BPF_K:
 		case BPF_ALU | BPF_ARSH | BPF_K:
@@ -686,7 +711,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_RSH | BPF_X:
 		case BPF_ALU64 | BPF_ARSH | BPF_X:
 
-			/* check for bad case when dst_reg == rcx */
+			/* Check for bad case when dst_reg == rcx */
 			if (dst_reg == BPF_REG_4) {
 				/* mov r11, dst_reg */
 				EMIT_mov(AUX_REG, dst_reg);
@@ -724,13 +749,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU | BPF_END | BPF_FROM_BE:
 			switch (imm32) {
 			case 16:
-				/* emit 'ror %ax, 8' to swap lower 2 bytes */
+				/* Emit 'ror %ax, 8' to swap lower 2 bytes */
 				EMIT1(0x66);
 				if (is_ereg(dst_reg))
 					EMIT1(0x41);
 				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
 
-				/* emit 'movzwl eax, ax' */
+				/* Emit 'movzwl eax, ax' */
 				if (is_ereg(dst_reg))
 					EMIT3(0x45, 0x0F, 0xB7);
 				else
@@ -738,7 +763,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
-				/* emit 'bswap eax' to swap lower 4 bytes */
+				/* Emit 'bswap eax' to swap lower 4 bytes */
 				if (is_ereg(dst_reg))
 					EMIT2(0x41, 0x0F);
 				else
@@ -746,7 +771,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				EMIT1(add_1reg(0xC8, dst_reg));
 				break;
 			case 64:
-				/* emit 'bswap rax' to swap 8 bytes */
+				/* Emit 'bswap rax' to swap 8 bytes */
 				EMIT3(add_1mod(0x48, dst_reg), 0x0F,
 				      add_1reg(0xC8, dst_reg));
 				break;
@@ -756,7 +781,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
 			switch (imm32) {
 			case 16:
-				/* emit 'movzwl eax, ax' to zero extend 16-bit
+				/*
+				 * Emit 'movzwl eax, ax' to zero extend 16-bit
 				 * into 64 bit
 				 */
 				if (is_ereg(dst_reg))
@@ -766,7 +792,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
-				/* emit 'mov eax, eax' to clear upper 32-bits */
+				/* Emit 'mov eax, eax' to clear upper 32-bits */
 				if (is_ereg(dst_reg))
 					EMIT1(0x45);
 				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
@@ -809,9 +835,9 @@ st:			if (is_imm8(insn->off))
 
 			/* STX: *(u8*)(dst_reg + off) = src_reg */
 		case BPF_STX | BPF_MEM | BPF_B:
-			/* emit 'mov byte ptr [rax + off], al' */
+			/* Emit 'mov byte ptr [rax + off], al' */
 			if (is_ereg(dst_reg) || is_ereg(src_reg) ||
-			    /* have to add extra byte for x86 SIL, DIL regs */
+			    /* We have to add extra byte for x86 SIL, DIL regs */
 			    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
 				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
 			else
@@ -840,25 +866,26 @@ stx:			if (is_imm8(insn->off))
 
 			/* LDX: dst_reg = *(u8*)(src_reg + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
-			/* emit 'movzx rax, byte ptr [rax + off]' */
+			/* Emit 'movzx rax, byte ptr [rax + off]' */
 			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_H:
-			/* emit 'movzx rax, word ptr [rax + off]' */
+			/* Emit 'movzx rax, word ptr [rax + off]' */
 			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_W:
-			/* emit 'mov eax, dword ptr [rax+0x14]' */
+			/* Emit 'mov eax, dword ptr [rax+0x14]' */
 			if (is_ereg(dst_reg) || is_ereg(src_reg))
 				EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
 			else
 				EMIT1(0x8B);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_DW:
-			/* emit 'mov rax, qword ptr [rax+0x14]' */
+			/* Emit 'mov rax, qword ptr [rax+0x14]' */
 			EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
-ldx:			/* if insn->off == 0 we can save one extra byte, but
-			 * special case of x86 r13 which always needs an offset
+ldx:			/*
+			 * If insn->off == 0 we can save one extra byte, but
+			 * special case of x86 R13 which always needs an offset
 			 * is not worth the hassle
 			 */
 			if (is_imm8(insn->off))
@@ -870,7 +897,7 @@ ldx:			/* if insn->off == 0 we can save one extra byte, but
 
 			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
 		case BPF_STX | BPF_XADD | BPF_W:
-			/* emit 'lock add dword ptr [rax + off], eax' */
+			/* Emit 'lock add dword ptr [rax + off], eax' */
 			if (is_ereg(dst_reg) || is_ereg(src_reg))
 				EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
 			else
@@ -897,14 +924,15 @@ xadd:			if (is_imm8(insn->off))
 				} else {
 					EMIT2(0x41, 0x52); /* push %r10 */
 					EMIT2(0x41, 0x51); /* push %r9 */
-					/* need to adjust jmp offset, since
+					/*
+					 * We need to adjust jmp offset, since
 					 * pop %r9, pop %r10 take 4 bytes after call insn
 					 */
 					jmp_offset += 4;
 				}
 			}
 			if (!imm32 || !is_simm32(jmp_offset)) {
-				pr_err("unsupported bpf func %d addr %p image %p\n",
+				pr_err("unsupported BPF func %d addr %p image %p\n",
 				       imm32, func, image);
 				return -EINVAL;
 			}
@@ -970,7 +998,7 @@ xadd:			if (is_imm8(insn->off))
 			else
 				EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);
 
-emit_cond_jmp:		/* convert BPF opcode to x86 */
+emit_cond_jmp:		/* Convert BPF opcode to x86 */
 			switch (BPF_OP(insn->code)) {
 			case BPF_JEQ:
 				jmp_cond = X86_JE;
@@ -996,22 +1024,22 @@ emit_cond_jmp:		/* convert BPF opcode to x86 */
 				jmp_cond = X86_JBE;
 				break;
 			case BPF_JSGT:
-				/* signed '>', GT in x86 */
+				/* Signed '>', GT in x86 */
 				jmp_cond = X86_JG;
 				break;
 			case BPF_JSLT:
-				/* signed '<', LT in x86 */
+				/* Signed '<', LT in x86 */
 				jmp_cond = X86_JL;
 				break;
 			case BPF_JSGE:
-				/* signed '>=', GE in x86 */
+				/* Signed '>=', GE in x86 */
 				jmp_cond = X86_JGE;
 				break;
 			case BPF_JSLE:
-				/* signed '<=', LE in x86 */
+				/* Signed '<=', LE in x86 */
 				jmp_cond = X86_JLE;
 				break;
-			default: /* to silence gcc warning */
+			default: /* to silence GCC warning */
 				return -EFAULT;
 			}
 			jmp_offset = addrs[i + insn->off] - addrs[i];
@@ -1027,9 +1055,19 @@ emit_cond_jmp:		/* convert BPF opcode to x86 */
 			break;
 
 		case BPF_JMP | BPF_JA:
-			jmp_offset = addrs[i + insn->off] - addrs[i];
+			if (insn->off == -1)
+				/* -1 jmp instructions will always jump
+				 * backwards two bytes. Explicitly handling
+				 * this case avoids wasting too many passes
+				 * when there are long sequences of replaced
+				 * dead code.
+				 */
+				jmp_offset = -2;
+			else
+				jmp_offset = addrs[i + insn->off] - addrs[i];
+
 			if (!jmp_offset)
-				/* optimize out nop jumps */
+				/* Optimize out nop jumps */
 				break;
 emit_jmp:
 			if (is_imm8(jmp_offset)) {
@@ -1051,7 +1089,7 @@ common_load:
 			ctx->seen_ld_abs = seen_ld_abs = true;
 			jmp_offset = func - (image + addrs[i]);
 			if (!func || !is_simm32(jmp_offset)) {
-				pr_err("unsupported bpf func %d addr %p image %p\n",
+				pr_err("unsupported BPF func %d addr %p image %p\n",
 				       imm32, func, image);
 				return -EINVAL;
 			}
@@ -1070,7 +1108,8 @@ common_load:
 						EMIT2_off32(0x81, 0xC6, imm32);
 				}
 			}
-			/* skb pointer is in R6 (%rbx), it will be copied into
+			/*
+			 * skb pointer is in R6 (%rbx), it will be copied into
 			 * %rdi if skb_copy_bits() call is necessary.
 			 * sk_load_* helpers also use %r10 and %r9d.
 			 * See bpf_jit.S
@@ -1101,7 +1140,7 @@ common_load:
 				goto emit_jmp;
 			}
 			seen_exit = true;
-			/* update cleanup_addr */
+			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
 			/* mov rbx, qword ptr [rbp+0] */
 			EMIT4(0x48, 0x8B, 0x5D, 0);
@@ -1119,10 +1158,11 @@ common_load:
 			break;
 
 		default:
-			/* By design x64 JIT should support all BPF instructions
+			/*
+			 * By design x86-64 JIT should support all BPF instructions.
 			 * This error will be seen if new instruction was added
-			 * to interpreter, but not to JIT
-			 * or if there is junk in bpf_prog
+			 * to the interpreter, but not to the JIT, or if there is
+			 * junk in bpf_prog.
 			 */
 			pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
 			return -EINVAL;
@@ -1174,7 +1214,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
-	/* If blinding was requested and we failed during blinding,
+	/*
+	 * If blinding was requested and we failed during blinding,
 	 * we must fall back to the interpreter.
 	 */
 	if (IS_ERR(tmp))
@@ -1208,8 +1249,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto out_addrs;
 	}
 
-	/* Before first pass, make a rough estimation of addrs[]
-	 * each bpf instruction is translated to less than 64 bytes
+	/*
+	 * Before first pass, make a rough estimation of addrs[]
+	 * each BPF instruction is translated to less than 64 bytes
 	 */
 	for (proglen = 0, i = 0; i < prog->len; i++) {
 		proglen += 64;
@@ -1218,14 +1260,16 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx.cleanup_addr = proglen;
 skip_init_addrs:
 
-	/* JITed image shrinks with every pass and the loop iterates
-	 * until the image stops shrinking. Very large bpf programs
+	/*
+	 * JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large BPF programs
 	 * may converge on the last pass. In such case do one more
-	 * pass to emit the final image
+	 * pass to emit the final image.
 	 */
 	for (pass = 0; pass < 20 || image; pass++) {
 		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
 		if (proglen <= 0) {
+out_image:
 			image = NULL;
 			if (header)
 				bpf_jit_binary_free(header);
@@ -1236,8 +1280,7 @@ skip_init_addrs:
 			if (proglen != oldproglen) {
 				pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
 				       proglen, oldproglen);
-				prog = orig_prog;
-				goto out_addrs;
+				goto out_image;
 			}
 			break;
 		}
@@ -1273,7 +1316,7 @@ skip_init_addrs:
 		prog = orig_prog;
 	}
 
-	if (!prog->is_func || extra_pass) {
+	if (!image || !prog->is_func || extra_pass) {
 out_addrs:
 		kfree(addrs);
 		kfree(jit_data);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index bed7e7f4e44c..e01f7ceb9e7a 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -225,7 +225,7 @@ int __init efi_alloc_page_tables(void)
 
 	pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
 	if (!pud) {
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			free_page((unsigned long) pgd_page_vaddr(*pgd));
 		free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
 		return -ENOMEM;
diff --git a/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
index 58024862a7eb..a52914aa3b6c 100644
--- a/arch/x86/platform/intel-mid/intel_mid_vrtc.c
+++ b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
@@ -57,7 +57,7 @@ void vrtc_cmos_write(unsigned char val, unsigned char reg)
 }
 EXPORT_SYMBOL_GPL(vrtc_cmos_write);
 
-void vrtc_get_time(struct timespec *now)
+void vrtc_get_time(struct timespec64 *now)
 {
 	u8 sec, min, hour, mday, mon;
 	unsigned long flags;
@@ -83,18 +83,18 @@ void vrtc_get_time(struct timespec *now)
 	pr_info("vRTC: sec: %d min: %d hour: %d day: %d "
 		"mon: %d year: %d\n", sec, min, hour, mday, mon, year);
 
-	now->tv_sec = mktime(year, mon, mday, hour, min, sec);
+	now->tv_sec = mktime64(year, mon, mday, hour, min, sec);
 	now->tv_nsec = 0;
 }
 
-int vrtc_set_mmss(const struct timespec *now)
+int vrtc_set_mmss(const struct timespec64 *now)
 {
 	unsigned long flags;
 	struct rtc_time tm;
 	int year;
 	int retval = 0;
 
-	rtc_time_to_tm(now->tv_sec, &tm);
+	rtc_time64_to_tm(now->tv_sec, &tm);
 	if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) {
 		/*
 		 * tm.year is the number of years since 1900, and the
@@ -110,8 +110,8 @@ int vrtc_set_mmss(const struct timespec *now)
 		vrtc_cmos_write(tm.tm_sec, RTC_SECONDS);
 		spin_unlock_irqrestore(&rtc_lock, flags);
 	} else {
-		pr_err("%s: Invalid vRTC value: write of %lx to vRTC failed\n",
-			__func__, now->tv_sec);
+		pr_err("%s: Invalid vRTC value: write of %llx to vRTC failed\n",
+			__func__, (s64)now->tv_sec);
 		retval = -EINVAL;
 	}
 	return retval;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 48b14b534897..67ccf64c8bd8 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -72,7 +72,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 	 * tables used by the image kernel.
 	 */
 
-	if (pgtable_l5_enabled) {
+	if (pgtable_l5_enabled()) {
 		p4d = (p4d_t *)get_safe_page(GFP_ATOMIC);
 		if (!p4d)
 			return -ENOMEM;
@@ -98,7 +98,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 		set_pgd(pgd + pgd_index(restore_jump_address), new_pgd);
 	} else {
 		/* No p4d for 4-level paging: point the pgd to the pud page table */
-		pgd_t new_pgd = __pgd(__pa(p4d) | pgprot_val(pgtable_prot));
+		pgd_t new_pgd = __pgd(__pa(pud) | pgprot_val(pgtable_prot));
 		set_pgd(pgd + pgd_index(restore_jump_address), new_pgd);
 	}
 
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 13ed827c7c66..9d529f22fd9d 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -1,5 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
-mainmenu "User Mode Linux/$SUBARCH $KERNELVERSION Kernel Configuration"
+mainmenu "User Mode Linux/$(SUBARCH) $(KERNELVERSION) Kernel Configuration"
+
+comment "Compiler: $(CC_VERSION_TEXT)"
+
+source "scripts/Kconfig.include"
 
 source "arch/um/Kconfig.common"
 
@@ -16,8 +20,8 @@ config UML_X86
 	select GENERIC_FIND_FIRST_BIT
 
 config 64BIT
-	bool "64-bit kernel" if SUBARCH = "x86"
-	default SUBARCH != "i386"
+	bool "64-bit kernel" if "$(SUBARCH)" = "x86"
+	default "$(SUBARCH)" != "i386"
 
 config X86_32
 	def_bool !64BIT
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index 10003359e633..b2d6967262b2 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -23,14 +23,14 @@ $(obj)/vdso.o: $(obj)/vdso.so
 
 targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y)
 
-export CPPFLAGS_vdso.lds += -P -C
+CPPFLAGS_vdso.lds += -P -C
 
 VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
        -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
 
 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
 
-$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
 
 $(obj)/%.so: OBJCOPYFLAGS := -S
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index a18703be9ead..1804b27f9632 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -115,6 +115,61 @@ static efi_system_table_t __init *xen_efi_probe(void)
 	return &efi_systab_xen;
 }
 
+/*
+ * Determine whether we're in secure boot mode.
+ *
+ * Please keep the logic in sync with
+ * drivers/firmware/efi/libstub/secureboot.c:efi_get_secureboot().
+ */
+static enum efi_secureboot_mode xen_efi_get_secureboot(void)
+{
+	static efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
+	static efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID;
+	efi_status_t status;
+	u8 moksbstate, secboot, setupmode;
+	unsigned long size;
+
+	size = sizeof(secboot);
+	status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
+				  NULL, &size, &secboot);
+
+	if (status == EFI_NOT_FOUND)
+		return efi_secureboot_mode_disabled;
+
+	if (status != EFI_SUCCESS)
+		goto out_efi_err;
+
+	size = sizeof(setupmode);
+	status = efi.get_variable(L"SetupMode", &efi_variable_guid,
+				  NULL, &size, &setupmode);
+
+	if (status != EFI_SUCCESS)
+		goto out_efi_err;
+
+	if (secboot == 0 || setupmode == 1)
+		return efi_secureboot_mode_disabled;
+
+	/* See if a user has put the shim into insecure mode. */
+	size = sizeof(moksbstate);
+	status = efi.get_variable(L"MokSBStateRT", &shim_guid,
+				  NULL, &size, &moksbstate);
+
+	/* If it fails, we don't care why. Default to secure. */
+	if (status != EFI_SUCCESS)
+		goto secure_boot_enabled;
+
+	if (moksbstate == 1)
+		return efi_secureboot_mode_disabled;
+
+ secure_boot_enabled:
+	pr_info("UEFI Secure Boot is enabled.\n");
+	return efi_secureboot_mode_enabled;
+
+ out_efi_err:
+	pr_err("Could not determine UEFI Secure Boot status.\n");
+	return efi_secureboot_mode_unknown;
+}
+
 void __init xen_efi_init(void)
 {
 	efi_system_table_t *efi_systab_xen;
@@ -129,6 +184,8 @@ void __init xen_efi_init(void)
 	boot_params.efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
 	boot_params.efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
 
+	boot_params.secure_boot = xen_efi_get_secureboot();
+
 	set_bit(EFI_BOOT, &efi.flags);
 	set_bit(EFI_PARAVIRT, &efi.flags);
 	set_bit(EFI_64BIT, &efi.flags);
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 826898701045..19c1ff542387 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -65,6 +65,19 @@ static void __init xen_hvm_init_mem_mapping(void)
 {
 	early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE);
 	HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn));
+
+	/*
+	 * The virtual address of the shared_info page has changed, so
+	 * the vcpu_info pointer for VCPU 0 is now stale.
+	 *
+	 * The prepare_boot_cpu callback will re-initialize it via
+	 * xen_vcpu_setup, but we can't rely on that to be called for
+	 * old Xen versions (xen_have_vector_callback == 0).
+	 *
+	 * It is, in any case, bad to have a stale vcpu_info pointer
+	 * so reset it now.
+	 */
+	xen_vcpu_info_reset(0);
 }
 
 static void __init init_hvm_pv_info(void)
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index c36d23aa6c35..357969a3697c 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -421,45 +421,33 @@ static void xen_load_gdt(const struct desc_ptr *dtr)
 {
 	unsigned long va = dtr->address;
 	unsigned int size = dtr->size + 1;
-	unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
-	unsigned long frames[pages];
-	int f;
-
-	/*
-	 * A GDT can be up to 64k in size, which corresponds to 8192
-	 * 8-byte entries, or 16 4k pages..
-	 */
+	unsigned long pfn, mfn;
+	int level;
+	pte_t *ptep;
+	void *virt;
 
-	BUG_ON(size > 65536);
+	/* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */
+	BUG_ON(size > PAGE_SIZE);
 	BUG_ON(va & ~PAGE_MASK);
 
-	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
-		int level;
-		pte_t *ptep;
-		unsigned long pfn, mfn;
-		void *virt;
-
-		/*
-		 * The GDT is per-cpu and is in the percpu data area.
-		 * That can be virtually mapped, so we need to do a
-		 * page-walk to get the underlying MFN for the
-		 * hypercall.  The page can also be in the kernel's
-		 * linear range, so we need to RO that mapping too.
-		 */
-		ptep = lookup_address(va, &level);
-		BUG_ON(ptep == NULL);
-
-		pfn = pte_pfn(*ptep);
-		mfn = pfn_to_mfn(pfn);
-		virt = __va(PFN_PHYS(pfn));
+	/*
+	 * The GDT is per-cpu and is in the percpu data area.
+	 * That can be virtually mapped, so we need to do a
+	 * page-walk to get the underlying MFN for the
+	 * hypercall.  The page can also be in the kernel's
+	 * linear range, so we need to RO that mapping too.
+	 */
+	ptep = lookup_address(va, &level);
+	BUG_ON(ptep == NULL);
 
-		frames[f] = mfn;
+	pfn = pte_pfn(*ptep);
+	mfn = pfn_to_mfn(pfn);
+	virt = __va(PFN_PHYS(pfn));
 
-		make_lowmem_page_readonly((void *)va);
-		make_lowmem_page_readonly(virt);
-	}
+	make_lowmem_page_readonly((void *)va);
+	make_lowmem_page_readonly(virt);
 
-	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+	if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct)))
 		BUG();
 }
 
@@ -470,34 +458,22 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
 {
 	unsigned long va = dtr->address;
 	unsigned int size = dtr->size + 1;
-	unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
-	unsigned long frames[pages];
-	int f;
-
-	/*
-	 * A GDT can be up to 64k in size, which corresponds to 8192
-	 * 8-byte entries, or 16 4k pages..
-	 */
+	unsigned long pfn, mfn;
+	pte_t pte;
 
-	BUG_ON(size > 65536);
+	/* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */
+	BUG_ON(size > PAGE_SIZE);
 	BUG_ON(va & ~PAGE_MASK);
 
-	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
-		pte_t pte;
-		unsigned long pfn, mfn;
+	pfn = virt_to_pfn(va);
+	mfn = pfn_to_mfn(pfn);
 
-		pfn = virt_to_pfn(va);
-		mfn = pfn_to_mfn(pfn);
+	pte = pfn_pte(pfn, PAGE_KERNEL_RO);
 
-		pte = pfn_pte(pfn, PAGE_KERNEL_RO);
-
-		if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
-			BUG();
-
-		frames[f] = mfn;
-	}
+	if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
+		BUG();
 
-	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+	if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct)))
 		BUG();
 }
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index d33e7dbe3129..2d76106788a3 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -42,13 +42,11 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
 }
 EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
 
-static void xen_flush_tlb_all(void)
+static noinline void xen_flush_tlb_all(void)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 
-	trace_xen_mmu_flush_tlb_all(0);
-
 	preempt_disable();
 
 	mcs = xen_mc_entry(sizeof(*op));
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 486c0a34d00b..2c30cabfda90 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1310,13 +1310,11 @@ unsigned long xen_read_cr2_direct(void)
 	return this_cpu_read(xen_vcpu_info.arch.cr2);
 }
 
-static void xen_flush_tlb(void)
+static noinline void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 
-	trace_xen_mmu_flush_tlb(0);
-
 	preempt_disable();
 
 	mcs = xen_mc_entry(sizeof(*op));
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 29163c43ebbd..e0f1bcf01d63 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -57,7 +57,7 @@ static u64 xen_clocksource_get_cycles(struct clocksource *cs)
 	return xen_clocksource_read();
 }
 
-static void xen_read_wallclock(struct timespec *ts)
+static void xen_read_wallclock(struct timespec64 *ts)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
 	struct pvclock_wall_clock *wall_clock = &(s->wc);
@@ -68,12 +68,12 @@ static void xen_read_wallclock(struct timespec *ts)
 	put_cpu_var(xen_vcpu);
 }
 
-static void xen_get_wallclock(struct timespec *now)
+static void xen_get_wallclock(struct timespec64 *now)
 {
 	xen_read_wallclock(now);
 }
 
-static int xen_set_wallclock(const struct timespec *now)
+static int xen_set_wallclock(const struct timespec64 *now)
 {
 	return -ENODEV;
 }
@@ -461,7 +461,7 @@ static void __init xen_time_init(void)
 {
 	struct pvclock_vcpu_time_info *pvti;
 	int cpu = smp_processor_id();
-	struct timespec tp;
+	struct timespec64 tp;
 
 	/* As Dom0 is never moved, no penalty on using TSC there */
 	if (xen_initial_domain())
@@ -479,7 +479,7 @@ static void __init xen_time_init(void)
 
 	/* Set initial system time with full resolution */
 	xen_read_wallclock(&tp);
-	do_settimeofday(&tp);
+	do_settimeofday64(&tp);
 
 	setup_force_cpu_cap(X86_FEATURE_TSC);
 
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index c921e8bccdc8..17df332269b2 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -19,7 +19,6 @@ config XTENSA
 	select HAVE_ARCH_KASAN if MMU
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_EXIT_THREAD
 	select HAVE_FUNCTION_TRACER
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 436b20337168..e5e1e61c538c 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -1,4 +1,5 @@
 generic-y += bug.h
+generic-y += compat.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma-contiguous.h
diff --git a/arch/xtensa/include/asm/pci.h b/arch/xtensa/include/asm/pci.h
index d5a82153a7c5..6ddf0a30c60d 100644
--- a/arch/xtensa/include/asm/pci.h
+++ b/arch/xtensa/include/asm/pci.h
@@ -42,8 +42,6 @@ extern struct pci_controller* pcibios_alloc_controller(void);
  * decisions.
  */
 
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
 /* Tell PCI code what kind of PCI resource mappings we support */
 #define HAVE_PCI_MMAP			1
 #define ARCH_GENERIC_PCI_MMAP_RESOURCE	1
diff --git a/arch/xtensa/include/uapi/asm/msgbuf.h b/arch/xtensa/include/uapi/asm/msgbuf.h
index 36e2e103ca38..d6915e9f071c 100644
--- a/arch/xtensa/include/uapi/asm/msgbuf.h
+++ b/arch/xtensa/include/uapi/asm/msgbuf.h
@@ -7,7 +7,6 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  *
  * This file is subject to the terms and conditions of the GNU General
@@ -21,19 +20,19 @@
 struct msqid64_ds {
 	struct ipc64_perm msg_perm;
 #ifdef __XTENSA_EB__
-	unsigned int	__unused1;
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-	unsigned int	__unused2;
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-	unsigned int	__unused3;
-	__kernel_time_t msg_ctime;	/* last change time */
+	unsigned long  msg_stime_high;
+	unsigned long  msg_stime;	/* last msgsnd time */
+	unsigned long  msg_rtime_high;
+	unsigned long  msg_rtime;	/* last msgrcv time */
+	unsigned long  msg_ctime_high;
+	unsigned long  msg_ctime;	/* last change time */
 #elif defined(__XTENSA_EL__)
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-	unsigned int	__unused1;
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-	unsigned int	__unused2;
-	__kernel_time_t msg_ctime;	/* last change time */
-	unsigned int	__unused3;
+	unsigned long  msg_stime;	/* last msgsnd time */
+	unsigned long  msg_stime_high;
+	unsigned long  msg_rtime;	/* last msgrcv time */
+	unsigned long  msg_rtime_high;
+	unsigned long  msg_ctime;	/* last change time */
+	unsigned long  msg_ctime_high;
 #else
 # error processor byte order undefined!
 #endif
diff --git a/arch/xtensa/include/uapi/asm/sembuf.h b/arch/xtensa/include/uapi/asm/sembuf.h
index f61b6331a10c..09f348d643f1 100644
--- a/arch/xtensa/include/uapi/asm/sembuf.h
+++ b/arch/xtensa/include/uapi/asm/sembuf.h
@@ -14,7 +14,6 @@
  * between kernel and user space.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  *
  */
@@ -27,15 +26,15 @@
 struct semid64_ds {
 	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
 #ifdef __XTENSA_EL__
-	__kernel_time_t	sem_otime;		/* last semop time */
-	unsigned long	__unused1;
-	__kernel_time_t	sem_ctime;		/* last change time */
-	unsigned long	__unused2;
+	unsigned long	sem_otime;		/* last semop time */
+	unsigned long	sem_otime_high;
+	unsigned long	sem_ctime;		/* last change time */
+	unsigned long	sem_ctime_high;
 #else
-	unsigned long	__unused1;
-	__kernel_time_t	sem_otime;		/* last semop time */
-	unsigned long	__unused2;
-	__kernel_time_t	sem_ctime;		/* last change time */
+	unsigned long	sem_otime_high;
+	unsigned long	sem_otime;		/* last semop time */
+	unsigned long	sem_ctime_high;
+	unsigned long	sem_ctime;		/* last change time */
 #endif
 	unsigned long	sem_nsems;		/* no. of semaphores in array */
 	unsigned long	__unused3;
diff --git a/arch/xtensa/include/uapi/asm/shmbuf.h b/arch/xtensa/include/uapi/asm/shmbuf.h
index 26550bdc8430..554a57a6a90f 100644
--- a/arch/xtensa/include/uapi/asm/shmbuf.h
+++ b/arch/xtensa/include/uapi/asm/shmbuf.h
@@ -4,10 +4,10 @@
  *
  * The shmid64_ds structure for Xtensa architecture.
  * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
+ * between kernel and user space, but the padding is on the wrong
+ * side for big-endian xtensa, for historic reasons.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -20,42 +20,21 @@
 #ifndef _XTENSA_SHMBUF_H
 #define _XTENSA_SHMBUF_H
 
-#if defined (__XTENSA_EL__)
 struct shmid64_ds {
 	struct ipc64_perm	shm_perm;	/* operation perms */
 	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_time_t		shm_atime;	/* last attach time */
-	unsigned long		__unused1;
-	__kernel_time_t		shm_dtime;	/* last detach time */
-	unsigned long		__unused2;
-	__kernel_time_t		shm_ctime;	/* last change time */
-	unsigned long		__unused3;
+	unsigned long		shm_atime;	/* last attach time */
+	unsigned long		shm_atime_high;
+	unsigned long		shm_dtime;	/* last detach time */
+	unsigned long		shm_dtime_high;
+	unsigned long		shm_ctime;	/* last change time */
+	unsigned long		shm_ctime_high;
 	__kernel_pid_t		shm_cpid;	/* pid of creator */
 	__kernel_pid_t		shm_lpid;	/* pid of last operator */
 	unsigned long		shm_nattch;	/* no. of current attaches */
 	unsigned long		__unused4;
 	unsigned long		__unused5;
 };
-#elif defined (__XTENSA_EB__)
-struct shmid64_ds {
-	struct ipc64_perm	shm_perm;	/* operation perms */
-	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_time_t		shm_atime;	/* last attach time */
-	unsigned long		__unused1;
-	__kernel_time_t		shm_dtime;	/* last detach time */
-	unsigned long		__unused2;
-	__kernel_time_t		shm_ctime;	/* last change time */
-	unsigned long		__unused3;
-	__kernel_pid_t		shm_cpid;	/* pid of creator */
-	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	unsigned long		shm_nattch;	/* no. of current attaches */
-	unsigned long		__unused4;
-	unsigned long		__unused5;
-};
-#else
-# error endian order not defined
-#endif
-
 
 struct shminfo64 {
 	unsigned long	shmmax;
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 732631ce250f..392b4a80ebc2 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -261,12 +261,3 @@ const struct dma_map_ops xtensa_dma_map_ops = {
 	.mapping_error = xtensa_dma_mapping_error,
 };
 EXPORT_SYMBOL(xtensa_dma_map_ops);
-
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init xtensa_dma_init(void)
-{
-	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-	return 0;
-}
-fs_initcall(xtensa_dma_init);
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 32c5207f1226..86507fa7c2d7 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -323,8 +323,6 @@ do_illegal_instruction(struct pt_regs *regs)
 void
 do_unaligned_user (struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	__die_if_kernel("Unhandled unaligned exception in kernel",
 			regs, SIGKILL);
 
@@ -334,12 +332,7 @@ do_unaligned_user (struct pt_regs *regs)
 			    "(pid = %d, pc = %#010lx)\n",
 			    regs->excvaddr, current->comm,
 			    task_pid_nr(current), regs->pc);
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRALN;
-	info.si_addr = (void *) regs->excvaddr;
-	force_sig_info(SIGSEGV, &info, current);
-
+	force_sig_fault(SIGBUS, BUS_ADRALN, (void *) regs->excvaddr, current);
 }
 #endif
 
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 8b9b6f44bb06..c111a833205a 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -39,13 +39,13 @@ void do_page_fault(struct pt_regs *regs)
 	struct mm_struct *mm = current->mm;
 	unsigned int exccause = regs->exccause;
 	unsigned int address = regs->excvaddr;
-	siginfo_t info;
+	int code;
 
 	int is_write, is_exec;
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-	info.si_code = SEGV_MAPERR;
+	code = SEGV_MAPERR;
 
 	/* We fault-in kernel-space virtual memory on-demand. The
 	 * 'reference' page table is init_mm.pgd.
@@ -91,7 +91,7 @@ retry:
 	 */
 
 good_area:
-	info.si_code = SEGV_ACCERR;
+	code = SEGV_ACCERR;
 
 	if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
@@ -157,11 +157,7 @@ bad_area:
 	if (user_mode(regs)) {
 		current->thread.bad_vaddr = address;
 		current->thread.error_code = is_write;
-		info.si_signo = SIGSEGV;
-		info.si_errno = 0;
-		/* info.si_code has been set above */
-		info.si_addr = (void *) address;
-		force_sig_info(SIGSEGV, &info, current);
+		force_sig_fault(SIGSEGV, code, (void *) address, current);
 		return;
 	}
 	bad_page_fault(regs, address, SIGSEGV);
@@ -186,11 +182,7 @@ do_sigbus:
 	 * or user mode.
 	 */
 	current->thread.bad_vaddr = address;
-	info.si_code = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRERR;
-	info.si_addr = (void *) address;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address, current);
 
 	/* Kernel mode? Handle exceptions or die */
 	if (!user_mode(regs))
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 92f567f9a21e..af81a62faba6 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -153,19 +153,6 @@ static int rs_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int rs_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, rs_proc_show, NULL);
-}
-
-static const struct file_operations rs_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= rs_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static const struct tty_operations serial_ops = {
 	.open = rs_open,
 	.close = rs_close,
@@ -176,7 +163,7 @@ static const struct tty_operations serial_ops = {
 	.chars_in_buffer = rs_chars_in_buffer,
 	.hangup = rs_hangup,
 	.wait_until_sent = rs_wait_until_sent,
-	.proc_fops = &rs_proc_fops,
+	.proc_show = rs_proc_show,
 };
 
 int __init rs_init(void)
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index d819dc77fe65..a9e8633388f4 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -55,13 +55,13 @@ BFQG_FLAG_FNS(empty)
 /* This should be called with the scheduler lock held. */
 static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 {
-	unsigned long long now;
+	u64 now;
 
 	if (!bfqg_stats_waiting(stats))
 		return;
 
-	now = sched_clock();
-	if (time_after64(now, stats->start_group_wait_time))
+	now = ktime_get_ns();
+	if (now > stats->start_group_wait_time)
 		blkg_stat_add(&stats->group_wait_time,
 			      now - stats->start_group_wait_time);
 	bfqg_stats_clear_waiting(stats);
@@ -77,20 +77,20 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 		return;
 	if (bfqg == curr_bfqg)
 		return;
-	stats->start_group_wait_time = sched_clock();
+	stats->start_group_wait_time = ktime_get_ns();
 	bfqg_stats_mark_waiting(stats);
 }
 
 /* This should be called with the scheduler lock held. */
 static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
 {
-	unsigned long long now;
+	u64 now;
 
 	if (!bfqg_stats_empty(stats))
 		return;
 
-	now = sched_clock();
-	if (time_after64(now, stats->start_empty_time))
+	now = ktime_get_ns();
+	if (now > stats->start_empty_time)
 		blkg_stat_add(&stats->empty_time,
 			      now - stats->start_empty_time);
 	bfqg_stats_clear_empty(stats);
@@ -116,7 +116,7 @@ void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
 	if (bfqg_stats_empty(stats))
 		return;
 
-	stats->start_empty_time = sched_clock();
+	stats->start_empty_time = ktime_get_ns();
 	bfqg_stats_mark_empty(stats);
 }
 
@@ -125,9 +125,9 @@ void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
 	struct bfqg_stats *stats = &bfqg->stats;
 
 	if (bfqg_stats_idling(stats)) {
-		unsigned long long now = sched_clock();
+		u64 now = ktime_get_ns();
 
-		if (time_after64(now, stats->start_idle_time))
+		if (now > stats->start_idle_time)
 			blkg_stat_add(&stats->idle_time,
 				      now - stats->start_idle_time);
 		bfqg_stats_clear_idling(stats);
@@ -138,7 +138,7 @@ void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
 
-	stats->start_idle_time = sched_clock();
+	stats->start_idle_time = ktime_get_ns();
 	bfqg_stats_mark_idling(stats);
 }
 
@@ -171,18 +171,18 @@ void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
 	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
 }
 
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
-				  uint64_t io_start_time, unsigned int op)
+void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
+				  u64 io_start_time_ns, unsigned int op)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
-	unsigned long long now = sched_clock();
+	u64 now = ktime_get_ns();
 
-	if (time_after64(now, io_start_time))
+	if (now > io_start_time_ns)
 		blkg_rwstat_add(&stats->service_time, op,
-				now - io_start_time);
-	if (time_after64(io_start_time, start_time))
+				now - io_start_time_ns);
+	if (io_start_time_ns > start_time_ns)
 		blkg_rwstat_add(&stats->wait_time, op,
-				io_start_time - start_time);
+				io_start_time_ns - start_time_ns);
 }
 
 #else /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
@@ -191,8 +191,8 @@ void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
 			      unsigned int op) { }
 void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
 void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
-				  uint64_t io_start_time, unsigned int op) { }
+void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
+				  u64 io_start_time_ns, unsigned int op) { }
 void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
 void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
 void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index f0ecd98509d8..495b9ddb3355 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -49,9 +49,39 @@
  *
  * In particular, to provide these low-latency guarantees, BFQ
  * explicitly privileges the I/O of two classes of time-sensitive
- * applications: interactive and soft real-time. This feature enables
- * BFQ to provide applications in these classes with a very low
- * latency. Finally, BFQ also features additional heuristics for
+ * applications: interactive and soft real-time. In more detail, BFQ
+ * behaves this way if the low_latency parameter is set (default
+ * configuration). This feature enables BFQ to provide applications in
+ * these classes with a very low latency.
+ *
+ * To implement this feature, BFQ constantly tries to detect whether
+ * the I/O requests in a bfq_queue come from an interactive or a soft
+ * real-time application. For brevity, in these cases, the queue is
+ * said to be interactive or soft real-time. In both cases, BFQ
+ * privileges the service of the queue, over that of non-interactive
+ * and non-soft-real-time queues. This privileging is performed,
+ * mainly, by raising the weight of the queue. So, for brevity, we
+ * call just weight-raising periods the time periods during which a
+ * queue is privileged, because deemed interactive or soft real-time.
+ *
+ * The detection of soft real-time queues/applications is described in
+ * detail in the comments on the function
+ * bfq_bfqq_softrt_next_start. On the other hand, the detection of an
+ * interactive queue works as follows: a queue is deemed interactive
+ * if it is constantly non empty only for a limited time interval,
+ * after which it does become empty. The queue may be deemed
+ * interactive again (for a limited time), if it restarts being
+ * constantly non empty, provided that this happens only after the
+ * queue has remained empty for a given minimum idle time.
+ *
+ * By default, BFQ computes automatically the above maximum time
+ * interval, i.e., the time interval after which a constantly
+ * non-empty queue stops being deemed interactive. Since a queue is
+ * weight-raised while it is deemed interactive, this maximum time
+ * interval happens to coincide with the (maximum) duration of the
+ * weight-raising for interactive queues.
+ *
+ * Finally, BFQ also features additional heuristics for
  * preserving both a low latency and a high throughput on NCQ-capable,
  * rotational or flash-based devices, and to get the job done quickly
  * for applications consisting in many I/O-bound processes.
@@ -61,14 +91,14 @@
  * all low-latency heuristics for that device, by setting low_latency
  * to 0.
  *
- * BFQ is described in [1], where also a reference to the initial, more
- * theoretical paper on BFQ can be found. The interested reader can find
- * in the latter paper full details on the main algorithm, as well as
- * formulas of the guarantees and formal proofs of all the properties.
- * With respect to the version of BFQ presented in these papers, this
- * implementation adds a few more heuristics, such as the one that
- * guarantees a low latency to soft real-time applications, and a
- * hierarchical extension based on H-WF2Q+.
+ * BFQ is described in [1], where also a reference to the initial,
+ * more theoretical paper on BFQ can be found. The interested reader
+ * can find in the latter paper full details on the main algorithm, as
+ * well as formulas of the guarantees and formal proofs of all the
+ * properties.  With respect to the version of BFQ presented in these
+ * papers, this implementation adds a few more heuristics, such as the
+ * ones that guarantee a low latency to interactive and soft real-time
+ * applications, and a hierarchical extension based on H-WF2Q+.
  *
  * B-WF2Q+ is based on WF2Q+, which is described in [2], together with
  * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
@@ -218,56 +248,46 @@ static struct kmem_cache *bfq_pool;
 #define BFQ_RATE_SHIFT		16
 
 /*
- * By default, BFQ computes the duration of the weight raising for
- * interactive applications automatically, using the following formula:
- * duration = (R / r) * T, where r is the peak rate of the device, and
- * R and T are two reference parameters.
- * In particular, R is the peak rate of the reference device (see
- * below), and T is a reference time: given the systems that are
- * likely to be installed on the reference device according to its
- * speed class, T is about the maximum time needed, under BFQ and
- * while reading two files in parallel, to load typical large
- * applications on these systems (see the comments on
- * max_service_from_wr below, for more details on how T is obtained).
- * In practice, the slower/faster the device at hand is, the more/less
- * it takes to load applications with respect to the reference device.
- * Accordingly, the longer/shorter BFQ grants weight raising to
- * interactive applications.
- *
- * BFQ uses four different reference pairs (R, T), depending on:
- * . whether the device is rotational or non-rotational;
- * . whether the device is slow, such as old or portable HDDs, as well as
- *   SD cards, or fast, such as newer HDDs and SSDs.
+ * When configured for computing the duration of the weight-raising
+ * for interactive queues automatically (see the comments at the
+ * beginning of this file), BFQ does it using the following formula:
+ * duration = (ref_rate / r) * ref_wr_duration,
+ * where r is the peak rate of the device, and ref_rate and
+ * ref_wr_duration are two reference parameters.  In particular,
+ * ref_rate is the peak rate of the reference storage device (see
+ * below), and ref_wr_duration is about the maximum time needed, with
+ * BFQ and while reading two files in parallel, to load typical large
+ * applications on the reference device (see the comments on
+ * max_service_from_wr below, for more details on how ref_wr_duration
+ * is obtained).  In practice, the slower/faster the device at hand
+ * is, the more/less it takes to load applications with respect to the
+ * reference device.  Accordingly, the longer/shorter BFQ grants
+ * weight raising to interactive applications.
  *
- * The device's speed class is dynamically (re)detected in
- * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ * BFQ uses two different reference pairs (ref_rate, ref_wr_duration),
+ * depending on whether the device is rotational or non-rotational.
  *
- * In the following definitions, R_slow[0]/R_fast[0] and
- * T_slow[0]/T_fast[0] are the reference values for a slow/fast
- * rotational device, whereas R_slow[1]/R_fast[1] and
- * T_slow[1]/T_fast[1] are the reference values for a slow/fast
- * non-rotational device. Finally, device_speed_thresh are the
- * thresholds used to switch between speed classes. The reference
- * rates are not the actual peak rates of the devices used as a
- * reference, but slightly lower values. The reason for using these
- * slightly lower values is that the peak-rate estimator tends to
- * yield slightly lower values than the actual peak rate (it can yield
- * the actual peak rate only if there is only one process doing I/O,
- * and the process does sequential I/O).
+ * In the following definitions, ref_rate[0] and ref_wr_duration[0]
+ * are the reference values for a rotational device, whereas
+ * ref_rate[1] and ref_wr_duration[1] are the reference values for a
+ * non-rotational device. The reference rates are not the actual peak
+ * rates of the devices used as a reference, but slightly lower
+ * values. The reason for using slightly lower values is that the
+ * peak-rate estimator tends to yield slightly lower values than the
+ * actual peak rate (it can yield the actual peak rate only if there
+ * is only one process doing I/O, and the process does sequential
+ * I/O).
  *
- * Both the reference peak rates and the thresholds are measured in
- * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ * The reference peak rates are measured in sectors/usec, left-shifted
+ * by BFQ_RATE_SHIFT.
  */
-static int R_slow[2] = {1000, 10700};
-static int R_fast[2] = {14000, 33000};
+static int ref_rate[2] = {14000, 33000};
 /*
- * To improve readability, a conversion function is used to initialize the
- * following arrays, which entails that they can be initialized only in a
- * function.
+ * To improve readability, a conversion function is used to initialize
+ * the following array, which entails that the array can be
+ * initialized only in a function.
  */
-static int T_slow[2];
-static int T_fast[2];
-static int device_speed_thresh[2];
+static int ref_wr_duration[2];
 
 /*
  * BFQ uses the above-detailed, time-based weight-raising mechanism to
@@ -487,46 +507,6 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd,
 }
 
 /*
- * See the comments on bfq_limit_depth for the purpose of
- * the depths set in the function.
- */
-static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
-{
-	bfqd->sb_shift = bt->sb.shift;
-
-	/*
-	 * In-word depths if no bfq_queue is being weight-raised:
-	 * leaving 25% of tags only for sync reads.
-	 *
-	 * In next formulas, right-shift the value
-	 * (1U<<bfqd->sb_shift), instead of computing directly
-	 * (1U<<(bfqd->sb_shift - something)), to be robust against
-	 * any possible value of bfqd->sb_shift, without having to
-	 * limit 'something'.
-	 */
-	/* no more than 50% of tags for async I/O */
-	bfqd->word_depths[0][0] = max((1U<<bfqd->sb_shift)>>1, 1U);
-	/*
-	 * no more than 75% of tags for sync writes (25% extra tags
-	 * w.r.t. async I/O, to prevent async I/O from starving sync
-	 * writes)
-	 */
-	bfqd->word_depths[0][1] = max(((1U<<bfqd->sb_shift) * 3)>>2, 1U);
-
-	/*
-	 * In-word depths in case some bfq_queue is being weight-
-	 * raised: leaving ~63% of tags for sync reads. This is the
-	 * highest percentage for which, in our tests, application
-	 * start-up times didn't suffer from any regression due to tag
-	 * shortage.
-	 */
-	/* no more than ~18% of tags for async I/O */
-	bfqd->word_depths[1][0] = max(((1U<<bfqd->sb_shift) * 3)>>4, 1U);
-	/* no more than ~37% of tags for sync writes (~20% extra tags) */
-	bfqd->word_depths[1][1] = max(((1U<<bfqd->sb_shift) * 6)>>4, 1U);
-}
-
-/*
  * Async I/O can easily starve sync I/O (both sync reads and sync
  * writes), by consuming all tags. Similarly, storms of sync writes,
  * such as those that sync(2) may trigger, can starve sync reads.
@@ -535,25 +515,11 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
  */
 static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
 {
-	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 	struct bfq_data *bfqd = data->q->elevator->elevator_data;
-	struct sbitmap_queue *bt;
 
 	if (op_is_sync(op) && !op_is_write(op))
 		return;
 
-	if (data->flags & BLK_MQ_REQ_RESERVED) {
-		if (unlikely(!tags->nr_reserved_tags)) {
-			WARN_ON_ONCE(1);
-			return;
-		}
-		bt = &tags->breserved_tags;
-	} else
-		bt = &tags->bitmap_tags;
-
-	if (unlikely(bfqd->sb_shift != bt->sb.shift))
-		bfq_update_depths(bfqd, bt);
-
 	data->shallow_depth =
 		bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)];
 
@@ -906,26 +872,30 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
 	if (bfqd->bfq_wr_max_time > 0)
 		return bfqd->bfq_wr_max_time;
 
-	dur = bfqd->RT_prod;
+	dur = bfqd->rate_dur_prod;
 	do_div(dur, bfqd->peak_rate);
 
 	/*
-	 * Limit duration between 3 and 13 seconds. Tests show that
-	 * higher values than 13 seconds often yield the opposite of
-	 * the desired result, i.e., worsen responsiveness by letting
-	 * non-interactive and non-soft-real-time applications
-	 * preserve weight raising for a too long time interval.
+	 * Limit duration between 3 and 25 seconds. The upper limit
+	 * has been conservatively set after the following worst case:
+	 * on a QEMU/KVM virtual machine
+	 * - running in a slow PC
+	 * - with a virtual disk stacked on a slow low-end 5400rpm HDD
+	 * - serving a heavy I/O workload, such as the sequential reading
+	 *   of several files
+	 * mplayer took 23 seconds to start, if constantly weight-raised.
+	 *
+	 * As for higher values than that accomodating the above bad
+	 * scenario, tests show that higher values would often yield
+	 * the opposite of the desired result, i.e., would worsen
+	 * responsiveness by allowing non-interactive applications to
+	 * preserve weight raising for too long.
 	 *
 	 * On the other end, lower values than 3 seconds make it
 	 * difficult for most interactive tasks to complete their jobs
 	 * before weight-raising finishes.
 	 */
-	if (dur > msecs_to_jiffies(13000))
-		dur = msecs_to_jiffies(13000);
-	else if (dur < msecs_to_jiffies(3000))
-		dur = msecs_to_jiffies(3000);
-
-	return dur;
+	return clamp_val(dur, msecs_to_jiffies(3000), msecs_to_jiffies(25000));
 }
 
 /* switch back from soft real-time to interactive weight raising */
@@ -1393,15 +1363,6 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
 }
 
 /*
- * Return the farthest future time instant according to jiffies
- * macros.
- */
-static unsigned long bfq_greatest_from_now(void)
-{
-	return jiffies + MAX_JIFFY_OFFSET;
-}
-
-/*
  * Return the farthest past time instant according to jiffies
  * macros.
  */
@@ -1545,7 +1506,8 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 	in_burst = bfq_bfqq_in_large_burst(bfqq);
 	soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
 		!in_burst &&
-		time_is_before_jiffies(bfqq->soft_rt_next_start);
+		time_is_before_jiffies(bfqq->soft_rt_next_start) &&
+		bfqq->dispatched == 0;
 	*interactive = !in_burst && idle_for_long_time;
 	wr_or_deserves_wr = bfqd->low_latency &&
 		(bfqq->wr_coeff > 1 ||
@@ -1858,6 +1820,8 @@ static int bfq_request_merge(struct request_queue *q, struct request **req,
 	return ELEVATOR_NO_MERGE;
 }
 
+static struct bfq_queue *bfq_init_rq(struct request *rq);
+
 static void bfq_request_merged(struct request_queue *q, struct request *req,
 			       enum elv_merge type)
 {
@@ -1866,7 +1830,7 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 	    blk_rq_pos(req) <
 	    blk_rq_pos(container_of(rb_prev(&req->rb_node),
 				    struct request, rb_node))) {
-		struct bfq_queue *bfqq = RQ_BFQQ(req);
+		struct bfq_queue *bfqq = bfq_init_rq(req);
 		struct bfq_data *bfqd = bfqq->bfqd;
 		struct request *prev, *next_rq;
 
@@ -1891,14 +1855,25 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 	}
 }
 
+/*
+ * This function is called to notify the scheduler that the requests
+ * rq and 'next' have been merged, with 'next' going away.  BFQ
+ * exploits this hook to address the following issue: if 'next' has a
+ * fifo_time lower that rq, then the fifo_time of rq must be set to
+ * the value of 'next', to not forget the greater age of 'next'.
+ *
+ * NOTE: in this function we assume that rq is in a bfq_queue, basing
+ * on that rq is picked from the hash table q->elevator->hash, which,
+ * in its turn, is filled only with I/O requests present in
+ * bfq_queues, while BFQ is in use for the request queue q. In fact,
+ * the function that fills this hash table (elv_rqhash_add) is called
+ * only by bfq_insert_request.
+ */
 static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 				struct request *next)
 {
-	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
-
-	if (!RB_EMPTY_NODE(&rq->rb_node))
-		goto end;
-	spin_lock_irq(&bfqq->bfqd->lock);
+	struct bfq_queue *bfqq = bfq_init_rq(rq),
+		*next_bfqq = bfq_init_rq(next);
 
 	/*
 	 * If next and rq belong to the same bfq_queue and next is older
@@ -1920,11 +1895,6 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 	if (bfqq->next_rq == next)
 		bfqq->next_rq = rq;
 
-	bfq_remove_request(q, next);
-	bfqg_stats_update_io_remove(bfqq_group(bfqq), next->cmd_flags);
-
-	spin_unlock_irq(&bfqq->bfqd->lock);
-end:
 	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
 }
 
@@ -2506,37 +2476,15 @@ static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
 /*
  * Update parameters related to throughput and responsiveness, as a
  * function of the estimated peak rate. See comments on
- * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ * bfq_calc_max_budget(), and on the ref_wr_duration array.
  */
 static void update_thr_responsiveness_params(struct bfq_data *bfqd)
 {
-	int dev_type = blk_queue_nonrot(bfqd->queue);
-
-	if (bfqd->bfq_user_max_budget == 0)
+	if (bfqd->bfq_user_max_budget == 0) {
 		bfqd->bfq_max_budget =
 			bfq_calc_max_budget(bfqd);
-
-	if (bfqd->device_speed == BFQ_BFQD_FAST &&
-	    bfqd->peak_rate < device_speed_thresh[dev_type]) {
-		bfqd->device_speed = BFQ_BFQD_SLOW;
-		bfqd->RT_prod = R_slow[dev_type] *
-			T_slow[dev_type];
-	} else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
-		   bfqd->peak_rate > device_speed_thresh[dev_type]) {
-		bfqd->device_speed = BFQ_BFQD_FAST;
-		bfqd->RT_prod = R_fast[dev_type] *
-			T_fast[dev_type];
+		bfq_log(bfqd, "new max_budget = %d", bfqd->bfq_max_budget);
 	}
-
-	bfq_log(bfqd,
-"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
-		dev_type == 0 ? "ROT" : "NONROT",
-		bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
-		bfqd->device_speed == BFQ_BFQD_FAST ?
-		(USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
-		(USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
-		(USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
-		BFQ_RATE_SHIFT);
 }
 
 static void bfq_reset_rate_computation(struct bfq_data *bfqd,
@@ -3266,23 +3214,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 				bfq_bfqq_softrt_next_start(bfqd, bfqq);
 		else {
 			/*
-			 * The application is still waiting for the
-			 * completion of one or more requests:
-			 * prevent it from possibly being incorrectly
-			 * deemed as soft real-time by setting its
-			 * soft_rt_next_start to infinity. In fact,
-			 * without this assignment, the application
-			 * would be incorrectly deemed as soft
-			 * real-time if:
-			 * 1) it issued a new request before the
-			 *    completion of all its in-flight
-			 *    requests, and
-			 * 2) at that time, its soft_rt_next_start
-			 *    happened to be in the past.
-			 */
-			bfqq->soft_rt_next_start =
-				bfq_greatest_from_now();
-			/*
 			 * Schedule an update of soft_rt_next_start to when
 			 * the task may be discovered to be isochronous.
 			 */
@@ -4540,14 +4471,12 @@ static inline void bfq_update_insert_stats(struct request_queue *q,
 					   unsigned int cmd_flags) {}
 #endif
 
-static void bfq_prepare_request(struct request *rq, struct bio *bio);
-
 static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 			       bool at_head)
 {
 	struct request_queue *q = hctx->queue;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
-	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_queue *bfqq;
 	bool idle_timer_disabled = false;
 	unsigned int cmd_flags;
 
@@ -4562,24 +4491,13 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	blk_mq_sched_request_inserted(rq);
 
 	spin_lock_irq(&bfqd->lock);
+	bfqq = bfq_init_rq(rq);
 	if (at_head || blk_rq_is_passthrough(rq)) {
 		if (at_head)
 			list_add(&rq->queuelist, &bfqd->dispatch);
 		else
 			list_add_tail(&rq->queuelist, &bfqd->dispatch);
-	} else {
-		if (WARN_ON_ONCE(!bfqq)) {
-			/*
-			 * This should never happen. Most likely rq is
-			 * a requeued regular request, being
-			 * re-inserted without being first
-			 * re-prepared. Do a prepare, to avoid
-			 * failure.
-			 */
-			bfq_prepare_request(rq, rq->bio);
-			bfqq = RQ_BFQQ(rq);
-		}
-
+	} else { /* bfqq is assumed to be non null here */
 		idle_timer_disabled = __bfq_insert_request(bfqd, rq);
 		/*
 		 * Update bfqq, because, if a queue merge has occurred
@@ -4778,8 +4696,8 @@ static void bfq_finish_requeue_request(struct request *rq)
 
 	if (rq->rq_flags & RQF_STARTED)
 		bfqg_stats_update_completion(bfqq_group(bfqq),
-					     rq_start_time_ns(rq),
-					     rq_io_start_time_ns(rq),
+					     rq->start_time_ns,
+					     rq->io_start_time_ns,
 					     rq->cmd_flags);
 
 	if (likely(rq->rq_flags & RQF_STARTED)) {
@@ -4922,11 +4840,48 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
 }
 
 /*
- * Allocate bfq data structures associated with this request.
+ * Only reset private fields. The actual request preparation will be
+ * performed by bfq_init_rq, when rq is either inserted or merged. See
+ * comments on bfq_init_rq for the reason behind this delayed
+ * preparation.
  */
 static void bfq_prepare_request(struct request *rq, struct bio *bio)
 {
+	/*
+	 * Regardless of whether we have an icq attached, we have to
+	 * clear the scheduler pointers, as they might point to
+	 * previously allocated bic/bfqq structs.
+	 */
+	rq->elv.priv[0] = rq->elv.priv[1] = NULL;
+}
+
+/*
+ * If needed, init rq, allocate bfq data structures associated with
+ * rq, and increment reference counters in the destination bfq_queue
+ * for rq. Return the destination bfq_queue for rq, or NULL is rq is
+ * not associated with any bfq_queue.
+ *
+ * This function is invoked by the functions that perform rq insertion
+ * or merging. One may have expected the above preparation operations
+ * to be performed in bfq_prepare_request, and not delayed to when rq
+ * is inserted or merged. The rationale behind this delayed
+ * preparation is that, after the prepare_request hook is invoked for
+ * rq, rq may still be transformed into a request with no icq, i.e., a
+ * request not associated with any queue. No bfq hook is invoked to
+ * signal this tranformation. As a consequence, should these
+ * preparation operations be performed when the prepare_request hook
+ * is invoked, and should rq be transformed one moment later, bfq
+ * would end up in an inconsistent state, because it would have
+ * incremented some queue counters for an rq destined to
+ * transformation, without any chance to correctly lower these
+ * counters back. In contrast, no transformation can still happen for
+ * rq after rq has been inserted or merged. So, it is safe to execute
+ * these preparation operations when rq is finally inserted or merged.
+ */
+static struct bfq_queue *bfq_init_rq(struct request *rq)
+{
 	struct request_queue *q = rq->q;
+	struct bio *bio = rq->bio;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct bfq_io_cq *bic;
 	const int is_sync = rq_is_sync(rq);
@@ -4934,11 +4889,20 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio)
 	bool new_queue = false;
 	bool bfqq_already_existing = false, split = false;
 
-	if (!rq->elv.icq)
-		return;
-	bic = icq_to_bic(rq->elv.icq);
+	if (unlikely(!rq->elv.icq))
+		return NULL;
 
-	spin_lock_irq(&bfqd->lock);
+	/*
+	 * Assuming that elv.priv[1] is set only if everything is set
+	 * for this rq. This holds true, because this function is
+	 * invoked only for insertion or merging, and, after such
+	 * events, a request cannot be manipulated any longer before
+	 * being removed from bfq.
+	 */
+	if (rq->elv.priv[1])
+		return rq->elv.priv[1];
+
+	bic = icq_to_bic(rq->elv.icq);
 
 	bfq_check_ioprio_change(bic, bio);
 
@@ -4998,7 +4962,7 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio)
 	if (unlikely(bfq_bfqq_just_created(bfqq)))
 		bfq_handle_burst(bfqd, bfqq);
 
-	spin_unlock_irq(&bfqd->lock);
+	return bfqq;
 }
 
 static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
@@ -5097,6 +5061,64 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
 	__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
 }
 
+/*
+ * See the comments on bfq_limit_depth for the purpose of
+ * the depths set in the function. Return minimum shallow depth we'll use.
+ */
+static unsigned int bfq_update_depths(struct bfq_data *bfqd,
+				      struct sbitmap_queue *bt)
+{
+	unsigned int i, j, min_shallow = UINT_MAX;
+
+	/*
+	 * In-word depths if no bfq_queue is being weight-raised:
+	 * leaving 25% of tags only for sync reads.
+	 *
+	 * In next formulas, right-shift the value
+	 * (1U<<bt->sb.shift), instead of computing directly
+	 * (1U<<(bt->sb.shift - something)), to be robust against
+	 * any possible value of bt->sb.shift, without having to
+	 * limit 'something'.
+	 */
+	/* no more than 50% of tags for async I/O */
+	bfqd->word_depths[0][0] = max((1U << bt->sb.shift) >> 1, 1U);
+	/*
+	 * no more than 75% of tags for sync writes (25% extra tags
+	 * w.r.t. async I/O, to prevent async I/O from starving sync
+	 * writes)
+	 */
+	bfqd->word_depths[0][1] = max(((1U << bt->sb.shift) * 3) >> 2, 1U);
+
+	/*
+	 * In-word depths in case some bfq_queue is being weight-
+	 * raised: leaving ~63% of tags for sync reads. This is the
+	 * highest percentage for which, in our tests, application
+	 * start-up times didn't suffer from any regression due to tag
+	 * shortage.
+	 */
+	/* no more than ~18% of tags for async I/O */
+	bfqd->word_depths[1][0] = max(((1U << bt->sb.shift) * 3) >> 4, 1U);
+	/* no more than ~37% of tags for sync writes (~20% extra tags) */
+	bfqd->word_depths[1][1] = max(((1U << bt->sb.shift) * 6) >> 4, 1U);
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < 2; j++)
+			min_shallow = min(min_shallow, bfqd->word_depths[i][j]);
+
+	return min_shallow;
+}
+
+static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+	struct blk_mq_tags *tags = hctx->sched_tags;
+	unsigned int min_shallow;
+
+	min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
+	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
+	return 0;
+}
+
 static void bfq_exit_queue(struct elevator_queue *e)
 {
 	struct bfq_data *bfqd = e->elevator_data;
@@ -5234,14 +5256,12 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->wr_busy_queues = 0;
 
 	/*
-	 * Begin by assuming, optimistically, that the device is a
-	 * high-speed one, and that its peak rate is equal to 2/3 of
-	 * the highest reference rate.
+	 * Begin by assuming, optimistically, that the device peak
+	 * rate is equal to 2/3 of the highest reference rate.
 	 */
-	bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
-			T_fast[blk_queue_nonrot(bfqd->queue)];
-	bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
-	bfqd->device_speed = BFQ_BFQD_FAST;
+	bfqd->rate_dur_prod = ref_rate[blk_queue_nonrot(bfqd->queue)] *
+		ref_wr_duration[blk_queue_nonrot(bfqd->queue)];
+	bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
 
 	spin_lock_init(&bfqd->lock);
 
@@ -5518,6 +5538,7 @@ static struct elevator_type iosched_bfq_mq = {
 		.requests_merged	= bfq_requests_merged,
 		.request_merged		= bfq_request_merged,
 		.has_work		= bfq_has_work,
+		.init_hctx		= bfq_init_hctx,
 		.init_sched		= bfq_init_queue,
 		.exit_sched		= bfq_exit_queue,
 	},
@@ -5548,8 +5569,8 @@ static int __init bfq_init(void)
 	/*
 	 * Times to load large popular applications for the typical
 	 * systems installed on the reference devices (see the
-	 * comments before the definitions of the next two
-	 * arrays). Actually, we use slightly slower values, as the
+	 * comments before the definition of the next
+	 * array). Actually, we use slightly lower values, as the
 	 * estimated peak rate tends to be smaller than the actual
 	 * peak rate.  The reason for this last fact is that estimates
 	 * are computed over much shorter time intervals than the long
@@ -5558,25 +5579,8 @@ static int __init bfq_init(void)
 	 * scheduler cannot rely on a peak-rate-evaluation workload to
 	 * be run for a long time.
 	 */
-	T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
-	T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
-	T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
-	T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
-
-	/*
-	 * Thresholds that determine the switch between speed classes
-	 * (see the comments before the definition of the array
-	 * device_speed_thresh). These thresholds are biased towards
-	 * transitions to the fast class. This is safer than the
-	 * opposite bias. In fact, a wrong transition to the slow
-	 * class results in short weight-raising periods, because the
-	 * speed of the device then tends to be higher that the
-	 * reference peak rate. On the opposite end, a wrong
-	 * transition to the fast class tends to increase
-	 * weight-raising periods, because of the opposite reason.
-	 */
-	device_speed_thresh[0] = (4 * R_slow[0]) / 3;
-	device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+	ref_wr_duration[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+	ref_wr_duration[1] = msecs_to_jiffies(2500); /* actually 3 sec */
 
 	ret = elv_register(&iosched_bfq_mq);
 	if (ret)
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index ae2f3dadec44..0f712e03b035 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -399,11 +399,6 @@ struct bfq_io_cq {
 	struct bfq_ttime saved_ttime;
 };
 
-enum bfq_device_speed {
-	BFQ_BFQD_FAST,
-	BFQ_BFQD_SLOW,
-};
-
 /**
  * struct bfq_data - per-device data structure.
  *
@@ -611,12 +606,11 @@ struct bfq_data {
 	/* Max service-rate for a soft real-time queue, in sectors/sec */
 	unsigned int bfq_wr_max_softrt_rate;
 	/*
-	 * Cached value of the product R*T, used for computing the
-	 * maximum duration of weight raising automatically.
+	 * Cached value of the product ref_rate*ref_wr_duration, used
+	 * for computing the maximum duration of weight raising
+	 * automatically.
 	 */
-	u64 RT_prod;
-	/* device-speed class for the low-latency heuristic */
-	enum bfq_device_speed device_speed;
+	u64 rate_dur_prod;
 
 	/* fallback dummy bfqq for extreme OOM conditions */
 	struct bfq_queue oom_bfqq;
@@ -636,12 +630,6 @@ struct bfq_data {
 	struct bfq_queue *bio_bfqq;
 
 	/*
-	 * Cached sbitmap shift, used to compute depth limits in
-	 * bfq_update_depths.
-	 */
-	unsigned int sb_shift;
-
-	/*
 	 * Depth limits used in bfq_limit_depth (see comments on the
 	 * function)
 	 */
@@ -732,9 +720,9 @@ struct bfqg_stats {
 	/* total time with empty current active q with other requests queued */
 	struct blkg_stat		empty_time;
 	/* fields after this shouldn't be cleared on stat reset */
-	uint64_t			start_group_wait_time;
-	uint64_t			start_idle_time;
-	uint64_t			start_empty_time;
+	u64				start_group_wait_time;
+	u64				start_idle_time;
+	u64				start_empty_time;
 	uint16_t			flags;
 #endif	/* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
 };
@@ -856,8 +844,8 @@ void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
 			      unsigned int op);
 void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
 void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
-				  uint64_t io_start_time, unsigned int op);
+void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
+				  u64 io_start_time_ns, unsigned int op);
 void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
 void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
 void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 9cfdd6c83b5b..add7c7c85335 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -56,12 +56,12 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	struct bio_set *bs = bio->bi_pool;
 	unsigned inline_vecs;
 
-	if (!bs || !bs->bio_integrity_pool) {
+	if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) {
 		bip = kmalloc(sizeof(struct bio_integrity_payload) +
 			      sizeof(struct bio_vec) * nr_vecs, gfp_mask);
 		inline_vecs = nr_vecs;
 	} else {
-		bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask);
+		bip = mempool_alloc(&bs->bio_integrity_pool, gfp_mask);
 		inline_vecs = BIP_INLINE_VECS;
 	}
 
@@ -74,7 +74,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 		unsigned long idx = 0;
 
 		bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx,
-					  bs->bvec_integrity_pool);
+					  &bs->bvec_integrity_pool);
 		if (!bip->bip_vec)
 			goto err;
 		bip->bip_max_vcnt = bvec_nr_vecs(idx);
@@ -90,7 +90,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	return bip;
 err:
-	mempool_free(bip, bs->bio_integrity_pool);
+	mempool_free(bip, &bs->bio_integrity_pool);
 	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
@@ -111,10 +111,10 @@ static void bio_integrity_free(struct bio *bio)
 		kfree(page_address(bip->bip_vec->bv_page) +
 		      bip->bip_vec->bv_offset);
 
-	if (bs && bs->bio_integrity_pool) {
-		bvec_free(bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
+	if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
+		bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
 
-		mempool_free(bip, bs->bio_integrity_pool);
+		mempool_free(bip, &bs->bio_integrity_pool);
 	} else {
 		kfree(bip);
 	}
@@ -465,16 +465,15 @@ EXPORT_SYMBOL(bio_integrity_clone);
 
 int bioset_integrity_create(struct bio_set *bs, int pool_size)
 {
-	if (bs->bio_integrity_pool)
+	if (mempool_initialized(&bs->bio_integrity_pool))
 		return 0;
 
-	bs->bio_integrity_pool = mempool_create_slab_pool(pool_size, bip_slab);
-	if (!bs->bio_integrity_pool)
+	if (mempool_init_slab_pool(&bs->bio_integrity_pool,
+				   pool_size, bip_slab))
 		return -1;
 
-	bs->bvec_integrity_pool = biovec_create_pool(pool_size);
-	if (!bs->bvec_integrity_pool) {
-		mempool_destroy(bs->bio_integrity_pool);
+	if (biovec_init_pool(&bs->bvec_integrity_pool, pool_size)) {
+		mempool_exit(&bs->bio_integrity_pool);
 		return -1;
 	}
 
@@ -484,8 +483,8 @@ EXPORT_SYMBOL(bioset_integrity_create);
 
 void bioset_integrity_free(struct bio_set *bs)
 {
-	mempool_destroy(bs->bio_integrity_pool);
-	mempool_destroy(bs->bvec_integrity_pool);
+	mempool_exit(&bs->bio_integrity_pool);
+	mempool_exit(&bs->bvec_integrity_pool);
 }
 EXPORT_SYMBOL(bioset_integrity_free);
 
diff --git a/block/bio.c b/block/bio.c
index 53e0f0a1ed94..5f7563598b1c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -53,7 +53,7 @@ static struct biovec_slab bvec_slabs[BVEC_POOL_NR] __read_mostly = {
  * fs_bio_set is the bio_set containing bio and iovec memory pools used by
  * IO code that does not need private memory pools.
  */
-struct bio_set *fs_bio_set;
+struct bio_set fs_bio_set;
 EXPORT_SYMBOL(fs_bio_set);
 
 /*
@@ -254,7 +254,7 @@ static void bio_free(struct bio *bio)
 	bio_uninit(bio);
 
 	if (bs) {
-		bvec_free(bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio));
+		bvec_free(&bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio));
 
 		/*
 		 * If we have front padding, adjust the bio pointer before freeing
@@ -262,7 +262,7 @@ static void bio_free(struct bio *bio)
 		p = bio;
 		p -= bs->front_pad;
 
-		mempool_free(p, bs->bio_pool);
+		mempool_free(p, &bs->bio_pool);
 	} else {
 		/* Bio was allocated by bio_kmalloc() */
 		kfree(bio);
@@ -454,7 +454,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
 		inline_vecs = nr_iovecs;
 	} else {
 		/* should not use nobvec bioset for nr_iovecs > 0 */
-		if (WARN_ON_ONCE(!bs->bvec_pool && nr_iovecs > 0))
+		if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) &&
+				 nr_iovecs > 0))
 			return NULL;
 		/*
 		 * generic_make_request() converts recursion to iteration; this
@@ -483,11 +484,11 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
 		    bs->rescue_workqueue)
 			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
-		p = mempool_alloc(bs->bio_pool, gfp_mask);
+		p = mempool_alloc(&bs->bio_pool, gfp_mask);
 		if (!p && gfp_mask != saved_gfp) {
 			punt_bios_to_rescuer(bs);
 			gfp_mask = saved_gfp;
-			p = mempool_alloc(bs->bio_pool, gfp_mask);
+			p = mempool_alloc(&bs->bio_pool, gfp_mask);
 		}
 
 		front_pad = bs->front_pad;
@@ -503,11 +504,11 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
 	if (nr_iovecs > inline_vecs) {
 		unsigned long idx = 0;
 
-		bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
+		bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool);
 		if (!bvl && gfp_mask != saved_gfp) {
 			punt_bios_to_rescuer(bs);
 			gfp_mask = saved_gfp;
-			bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
+			bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool);
 		}
 
 		if (unlikely(!bvl))
@@ -524,25 +525,25 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
 	return bio;
 
 err_free:
-	mempool_free(p, bs->bio_pool);
+	mempool_free(p, &bs->bio_pool);
 	return NULL;
 }
 EXPORT_SYMBOL(bio_alloc_bioset);
 
-void zero_fill_bio(struct bio *bio)
+void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
 {
 	unsigned long flags;
 	struct bio_vec bv;
 	struct bvec_iter iter;
 
-	bio_for_each_segment(bv, bio, iter) {
+	__bio_for_each_segment(bv, bio, iter, start) {
 		char *data = bvec_kmap_irq(&bv, &flags);
 		memset(data, 0, bv.bv_len);
 		flush_dcache_page(bv.bv_page);
 		bvec_kunmap_irq(data, &flags);
 	}
 }
-EXPORT_SYMBOL(zero_fill_bio);
+EXPORT_SYMBOL(zero_fill_bio_iter);
 
 /**
  * bio_put - release a reference to a bio
@@ -773,7 +774,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 			return 0;
 	}
 
-	if (bio->bi_vcnt >= bio->bi_max_vecs)
+	if (bio_full(bio))
 		return 0;
 
 	/*
@@ -821,52 +822,82 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 EXPORT_SYMBOL(bio_add_pc_page);
 
 /**
- *	bio_add_page	-	attempt to add page to bio
- *	@bio: destination bio
- *	@page: page to add
- *	@len: vec entry length
- *	@offset: vec entry offset
+ * __bio_try_merge_page - try appending data to an existing bvec.
+ * @bio: destination bio
+ * @page: page to add
+ * @len: length of the data to add
+ * @off: offset of the data in @page
  *
- *	Attempt to add a page to the bio_vec maplist. This will only fail
- *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
+ * Try to add the data at @page + @off to the last bvec of @bio.  This is a
+ * a useful optimisation for file systems with a block size smaller than the
+ * page size.
+ *
+ * Return %true on success or %false on failure.
  */
-int bio_add_page(struct bio *bio, struct page *page,
-		 unsigned int len, unsigned int offset)
+bool __bio_try_merge_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int off)
 {
-	struct bio_vec *bv;
-
-	/*
-	 * cloned bio must not modify vec list
-	 */
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
-		return 0;
+		return false;
 
-	/*
-	 * For filesystems with a blocksize smaller than the pagesize
-	 * we will often be called with the same page as last time and
-	 * a consecutive offset.  Optimize this special case.
-	 */
 	if (bio->bi_vcnt > 0) {
-		bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
-		if (page == bv->bv_page &&
-		    offset == bv->bv_offset + bv->bv_len) {
+		if (page == bv->bv_page && off == bv->bv_offset + bv->bv_len) {
 			bv->bv_len += len;
-			goto done;
+			bio->bi_iter.bi_size += len;
+			return true;
 		}
 	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(__bio_try_merge_page);
 
-	if (bio->bi_vcnt >= bio->bi_max_vecs)
-		return 0;
+/**
+ * __bio_add_page - add page to a bio in a new segment
+ * @bio: destination bio
+ * @page: page to add
+ * @len: length of the data to add
+ * @off: offset of the data in @page
+ *
+ * Add the data at @page + @off to @bio as a new bvec.  The caller must ensure
+ * that @bio has space for another bvec.
+ */
+void __bio_add_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int off)
+{
+	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt];
 
-	bv		= &bio->bi_io_vec[bio->bi_vcnt];
-	bv->bv_page	= page;
-	bv->bv_len	= len;
-	bv->bv_offset	= offset;
+	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
+	WARN_ON_ONCE(bio_full(bio));
+
+	bv->bv_page = page;
+	bv->bv_offset = off;
+	bv->bv_len = len;
 
-	bio->bi_vcnt++;
-done:
 	bio->bi_iter.bi_size += len;
+	bio->bi_vcnt++;
+}
+EXPORT_SYMBOL_GPL(__bio_add_page);
+
+/**
+ *	bio_add_page	-	attempt to add page to bio
+ *	@bio: destination bio
+ *	@page: page to add
+ *	@len: vec entry length
+ *	@offset: vec entry offset
+ *
+ *	Attempt to add a page to the bio_vec maplist. This will only fail
+ *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
+ */
+int bio_add_page(struct bio *bio, struct page *page,
+		 unsigned int len, unsigned int offset)
+{
+	if (!__bio_try_merge_page(bio, page, len, offset)) {
+		if (bio_full(bio))
+			return 0;
+		__bio_add_page(bio, page, len, offset);
+	}
 	return len;
 }
 EXPORT_SYMBOL(bio_add_page);
@@ -970,27 +1001,68 @@ void bio_advance(struct bio *bio, unsigned bytes)
 }
 EXPORT_SYMBOL(bio_advance);
 
+void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+			struct bio *src, struct bvec_iter *src_iter)
+{
+	struct bio_vec src_bv, dst_bv;
+	void *src_p, *dst_p;
+	unsigned bytes;
+
+	while (src_iter->bi_size && dst_iter->bi_size) {
+		src_bv = bio_iter_iovec(src, *src_iter);
+		dst_bv = bio_iter_iovec(dst, *dst_iter);
+
+		bytes = min(src_bv.bv_len, dst_bv.bv_len);
+
+		src_p = kmap_atomic(src_bv.bv_page);
+		dst_p = kmap_atomic(dst_bv.bv_page);
+
+		memcpy(dst_p + dst_bv.bv_offset,
+		       src_p + src_bv.bv_offset,
+		       bytes);
+
+		kunmap_atomic(dst_p);
+		kunmap_atomic(src_p);
+
+		flush_dcache_page(dst_bv.bv_page);
+
+		bio_advance_iter(src, src_iter, bytes);
+		bio_advance_iter(dst, dst_iter, bytes);
+	}
+}
+EXPORT_SYMBOL(bio_copy_data_iter);
+
 /**
- * bio_copy_data - copy contents of data buffers from one chain of bios to
- * another
- * @src: source bio list
- * @dst: destination bio list
- *
- * If @src and @dst are single bios, bi_next must be NULL - otherwise, treats
- * @src and @dst as linked lists of bios.
+ * bio_copy_data - copy contents of data buffers from one bio to another
+ * @src: source bio
+ * @dst: destination bio
  *
  * Stops when it reaches the end of either @src or @dst - that is, copies
  * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
  */
 void bio_copy_data(struct bio *dst, struct bio *src)
 {
-	struct bvec_iter src_iter, dst_iter;
-	struct bio_vec src_bv, dst_bv;
-	void *src_p, *dst_p;
-	unsigned bytes;
+	struct bvec_iter src_iter = src->bi_iter;
+	struct bvec_iter dst_iter = dst->bi_iter;
 
-	src_iter = src->bi_iter;
-	dst_iter = dst->bi_iter;
+	bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
+}
+EXPORT_SYMBOL(bio_copy_data);
+
+/**
+ * bio_list_copy_data - copy contents of data buffers from one chain of bios to
+ * another
+ * @src: source bio list
+ * @dst: destination bio list
+ *
+ * Stops when it reaches the end of either the @src list or @dst list - that is,
+ * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
+ * bios).
+ */
+void bio_list_copy_data(struct bio *dst, struct bio *src)
+{
+	struct bvec_iter src_iter = src->bi_iter;
+	struct bvec_iter dst_iter = dst->bi_iter;
 
 	while (1) {
 		if (!src_iter.bi_size) {
@@ -1009,26 +1081,10 @@ void bio_copy_data(struct bio *dst, struct bio *src)
 			dst_iter = dst->bi_iter;
 		}
 
-		src_bv = bio_iter_iovec(src, src_iter);
-		dst_bv = bio_iter_iovec(dst, dst_iter);
-
-		bytes = min(src_bv.bv_len, dst_bv.bv_len);
-
-		src_p = kmap_atomic(src_bv.bv_page);
-		dst_p = kmap_atomic(dst_bv.bv_page);
-
-		memcpy(dst_p + dst_bv.bv_offset,
-		       src_p + src_bv.bv_offset,
-		       bytes);
-
-		kunmap_atomic(dst_p);
-		kunmap_atomic(src_p);
-
-		bio_advance_iter(src, &src_iter, bytes);
-		bio_advance_iter(dst, &dst_iter, bytes);
+		bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
 	}
 }
-EXPORT_SYMBOL(bio_copy_data);
+EXPORT_SYMBOL(bio_list_copy_data);
 
 struct bio_map_data {
 	int is_our_pages;
@@ -1584,6 +1640,7 @@ void bio_set_pages_dirty(struct bio *bio)
 			set_page_dirty_lock(page);
 	}
 }
+EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
 
 static void bio_release_pages(struct bio *bio)
 {
@@ -1667,6 +1724,7 @@ void bio_check_pages_dirty(struct bio *bio)
 		bio_put(bio);
 	}
 }
+EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
 
 void generic_start_io_acct(struct request_queue *q, int rw,
 			   unsigned long sectors, struct hd_struct *part)
@@ -1749,6 +1807,9 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
+	if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL"))
+		bio->bi_next = NULL;
+
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that
@@ -1848,30 +1909,38 @@ EXPORT_SYMBOL_GPL(bio_trim);
  * create memory pools for biovec's in a bio_set.
  * use the global biovec slabs created for general use.
  */
-mempool_t *biovec_create_pool(int pool_entries)
+int biovec_init_pool(mempool_t *pool, int pool_entries)
 {
 	struct biovec_slab *bp = bvec_slabs + BVEC_POOL_MAX;
 
-	return mempool_create_slab_pool(pool_entries, bp->slab);
+	return mempool_init_slab_pool(pool, pool_entries, bp->slab);
 }
 
-void bioset_free(struct bio_set *bs)
+/*
+ * bioset_exit - exit a bioset initialized with bioset_init()
+ *
+ * May be called on a zeroed but uninitialized bioset (i.e. allocated with
+ * kzalloc()).
+ */
+void bioset_exit(struct bio_set *bs)
 {
 	if (bs->rescue_workqueue)
 		destroy_workqueue(bs->rescue_workqueue);
+	bs->rescue_workqueue = NULL;
 
-	mempool_destroy(bs->bio_pool);
-	mempool_destroy(bs->bvec_pool);
+	mempool_exit(&bs->bio_pool);
+	mempool_exit(&bs->bvec_pool);
 
 	bioset_integrity_free(bs);
-	bio_put_slab(bs);
-
-	kfree(bs);
+	if (bs->bio_slab)
+		bio_put_slab(bs);
+	bs->bio_slab = NULL;
 }
-EXPORT_SYMBOL(bioset_free);
+EXPORT_SYMBOL(bioset_exit);
 
 /**
- * bioset_create  - Create a bio_set
+ * bioset_init - Initialize a bio_set
+ * @bs:		pool to initialize
  * @pool_size:	Number of bio and bio_vecs to cache in the mempool
  * @front_pad:	Number of bytes to allocate in front of the returned bio
  * @flags:	Flags to modify behavior, currently %BIOSET_NEED_BVECS
@@ -1890,16 +1959,12 @@ EXPORT_SYMBOL(bioset_free);
  *    dispatch queued requests when the mempool runs out of space.
  *
  */
-struct bio_set *bioset_create(unsigned int pool_size,
-			      unsigned int front_pad,
-			      int flags)
+int bioset_init(struct bio_set *bs,
+		unsigned int pool_size,
+		unsigned int front_pad,
+		int flags)
 {
 	unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
-	struct bio_set *bs;
-
-	bs = kzalloc(sizeof(*bs), GFP_KERNEL);
-	if (!bs)
-		return NULL;
 
 	bs->front_pad = front_pad;
 
@@ -1908,34 +1973,29 @@ struct bio_set *bioset_create(unsigned int pool_size,
 	INIT_WORK(&bs->rescue_work, bio_alloc_rescue);
 
 	bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad);
-	if (!bs->bio_slab) {
-		kfree(bs);
-		return NULL;
-	}
+	if (!bs->bio_slab)
+		return -ENOMEM;
 
-	bs->bio_pool = mempool_create_slab_pool(pool_size, bs->bio_slab);
-	if (!bs->bio_pool)
+	if (mempool_init_slab_pool(&bs->bio_pool, pool_size, bs->bio_slab))
 		goto bad;
 
-	if (flags & BIOSET_NEED_BVECS) {
-		bs->bvec_pool = biovec_create_pool(pool_size);
-		if (!bs->bvec_pool)
-			goto bad;
-	}
+	if ((flags & BIOSET_NEED_BVECS) &&
+	    biovec_init_pool(&bs->bvec_pool, pool_size))
+		goto bad;
 
 	if (!(flags & BIOSET_NEED_RESCUER))
-		return bs;
+		return 0;
 
 	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
 	if (!bs->rescue_workqueue)
 		goto bad;
 
-	return bs;
+	return 0;
 bad:
-	bioset_free(bs);
-	return NULL;
+	bioset_exit(bs);
+	return -ENOMEM;
 }
-EXPORT_SYMBOL(bioset_create);
+EXPORT_SYMBOL(bioset_init);
 
 #ifdef CONFIG_BLK_CGROUP
 
@@ -2020,11 +2080,10 @@ static int __init init_bio(void)
 	bio_integrity_init();
 	biovec_init_slabs();
 
-	fs_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-	if (!fs_bio_set)
+	if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS))
 		panic("bio: can't allocate bios\n");
 
-	if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE))
+	if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE))
 		panic("bio: can't create integrity pool\n");
 
 	return 0;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1c16694ae145..eb85cb87c40f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1177,26 +1177,20 @@ int blkcg_init_queue(struct request_queue *q)
 
 	preloaded = !radix_tree_preload(GFP_KERNEL);
 
-	/*
-	 * Make sure the root blkg exists and count the existing blkgs.  As
-	 * @q is bypassing at this point, blkg_lookup_create() can't be
-	 * used.  Open code insertion.
-	 */
+	/* Make sure the root blkg exists. */
 	rcu_read_lock();
 	spin_lock_irq(q->queue_lock);
 	blkg = blkg_create(&blkcg_root, q, new_blkg);
+	if (IS_ERR(blkg))
+		goto err_unlock;
+	q->root_blkg = blkg;
+	q->root_rl.blkg = blkg;
 	spin_unlock_irq(q->queue_lock);
 	rcu_read_unlock();
 
 	if (preloaded)
 		radix_tree_preload_end();
 
-	if (IS_ERR(blkg))
-		return PTR_ERR(blkg);
-
-	q->root_blkg = blkg;
-	q->root_rl.blkg = blkg;
-
 	ret = blk_throtl_init(q);
 	if (ret) {
 		spin_lock_irq(q->queue_lock);
@@ -1204,6 +1198,13 @@ int blkcg_init_queue(struct request_queue *q)
 		spin_unlock_irq(q->queue_lock);
 	}
 	return ret;
+
+err_unlock:
+	spin_unlock_irq(q->queue_lock);
+	rcu_read_unlock();
+	if (preloaded)
+		radix_tree_preload_end();
+	return PTR_ERR(blkg);
 }
 
 /**
@@ -1410,9 +1411,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	__clear_bit(pol->plid, q->blkcg_pols);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
-		/* grab blkcg lock too while removing @pd from @blkg */
-		spin_lock(&blkg->blkcg->lock);
-
 		if (blkg->pd[pol->plid]) {
 			if (!blkg->pd[pol->plid]->offline &&
 			    pol->pd_offline_fn) {
@@ -1422,8 +1420,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}
-
-		spin_unlock(&blkg->blkcg->lock);
 	}
 
 	spin_unlock_irq(q->queue_lock);
diff --git a/block/blk-core.c b/block/blk-core.c
index 806ce2442819..3f56be15f17e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -196,11 +196,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->tag = -1;
 	rq->internal_tag = -1;
-	rq->start_time = jiffies;
-	set_start_time_ns(rq);
+	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
-	seqcount_init(&rq->gstate_seq);
-	u64_stats_init(&rq->aborted_gstate_sync);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -276,6 +273,10 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
+	/*
+	 * XXX this code looks suspicious - it's not consistent with advancing
+	 * req->bio in caller
+	 */
 	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
 		bio_endio(bio);
 }
@@ -356,7 +357,6 @@ EXPORT_SYMBOL(blk_start_queue_async);
 void blk_start_queue(struct request_queue *q)
 {
 	lockdep_assert_held(q->queue_lock);
-	WARN_ON(!in_interrupt() && !irqs_disabled());
 	WARN_ON_ONCE(q->mq_ops);
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
@@ -915,7 +915,6 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 
 	while (true) {
 		bool success = false;
-		int ret;
 
 		rcu_read_lock();
 		if (percpu_ref_tryget_live(&q->q_usage_counter)) {
@@ -947,14 +946,12 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 		 */
 		smp_rmb();
 
-		ret = wait_event_interruptible(q->mq_freeze_wq,
-				(atomic_read(&q->mq_freeze_depth) == 0 &&
-				 (preempt || !blk_queue_preempt_only(q))) ||
-				blk_queue_dying(q));
+		wait_event(q->mq_freeze_wq,
+			   (atomic_read(&q->mq_freeze_depth) == 0 &&
+			    (preempt || !blk_queue_preempt_only(q))) ||
+			   blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
-		if (ret)
-			return ret;
 	}
 }
 
@@ -995,18 +992,24 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
 					   spinlock_t *lock)
 {
 	struct request_queue *q;
+	int ret;
 
 	q = kmem_cache_alloc_node(blk_requestq_cachep,
 				gfp_mask | __GFP_ZERO, node_id);
 	if (!q)
 		return NULL;
 
+	INIT_LIST_HEAD(&q->queue_head);
+	q->last_merge = NULL;
+	q->end_sector = 0;
+	q->boundary_rq = NULL;
+
 	q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
 	if (q->id < 0)
 		goto fail_q;
 
-	q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-	if (!q->bio_split)
+	ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	if (ret)
 		goto fail_id;
 
 	q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id);
@@ -1078,7 +1081,7 @@ fail_bdi:
 fail_stats:
 	bdi_put(q->backing_dev_info);
 fail_split:
-	bioset_free(q->bio_split);
+	bioset_exit(&q->bio_split);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
 fail_q:
@@ -1172,16 +1175,8 @@ int blk_init_allocated_queue(struct request_queue *q)
 
 	q->sg_reserved_size = INT_MAX;
 
-	/* Protect q->elevator from elevator_change */
-	mutex_lock(&q->sysfs_lock);
-
-	/* init elevator */
-	if (elevator_init(q, NULL)) {
-		mutex_unlock(&q->sysfs_lock);
+	if (elevator_init(q))
 		goto out_exit_flush_rq;
-	}
-
-	mutex_unlock(&q->sysfs_lock);
 	return 0;
 
 out_exit_flush_rq:
@@ -1333,6 +1328,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
  * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
  * @flags: BLQ_MQ_REQ_* flags
+ * @gfp_mask: allocator flags
  *
  * Get a free request from @q.  This function may fail under memory
  * pressure or if @q is dead.
@@ -1342,7 +1338,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *__get_request(struct request_list *rl, unsigned int op,
-				     struct bio *bio, blk_mq_req_flags_t flags)
+		struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp_mask)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
@@ -1351,8 +1347,6 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	struct io_cq *icq = NULL;
 	const bool is_sync = op_is_sync(op);
 	int may_queue;
-	gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
-			 __GFP_DIRECT_RECLAIM;
 	req_flags_t rq_flags = RQF_ALLOCED;
 
 	lockdep_assert_held(q->queue_lock);
@@ -1516,8 +1510,9 @@ rq_starved:
  * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
  * @flags: BLK_MQ_REQ_* flags.
+ * @gfp: allocator flags
  *
- * Get a free request from @q.  If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
+ * Get a free request from @q.  If %BLK_MQ_REQ_NOWAIT is set in @flags,
  * this function keeps retrying under memory pressure and fails iff @q is dead.
  *
  * Must be called with @q->queue_lock held and,
@@ -1525,7 +1520,7 @@ rq_starved:
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *get_request(struct request_queue *q, unsigned int op,
-				   struct bio *bio, blk_mq_req_flags_t flags)
+		struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp)
 {
 	const bool is_sync = op_is_sync(op);
 	DEFINE_WAIT(wait);
@@ -1537,7 +1532,7 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
 
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
-	rq = __get_request(rl, op, bio, flags);
+	rq = __get_request(rl, op, bio, flags, gfp);
 	if (!IS_ERR(rq))
 		return rq;
 
@@ -1578,8 +1573,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
 				unsigned int op, blk_mq_req_flags_t flags)
 {
 	struct request *rq;
-	gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
-			 __GFP_DIRECT_RECLAIM;
+	gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC : GFP_NOIO;
 	int ret = 0;
 
 	WARN_ON_ONCE(q->mq_ops);
@@ -1591,7 +1585,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
 	if (ret)
 		return ERR_PTR(ret);
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, op, NULL, flags);
+	rq = get_request(q, op, NULL, flags, gfp_mask);
 	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
 		blk_queue_exit(q);
@@ -1606,13 +1600,13 @@ static struct request *blk_old_get_request(struct request_queue *q,
 }
 
 /**
- * blk_get_request_flags - allocate a request
+ * blk_get_request - allocate a request
  * @q: request queue to allocate a request for
  * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC.
  * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT.
  */
-struct request *blk_get_request_flags(struct request_queue *q, unsigned int op,
-				      blk_mq_req_flags_t flags)
+struct request *blk_get_request(struct request_queue *q, unsigned int op,
+				blk_mq_req_flags_t flags)
 {
 	struct request *req;
 
@@ -1631,14 +1625,6 @@ struct request *blk_get_request_flags(struct request_queue *q, unsigned int op,
 
 	return req;
 }
-EXPORT_SYMBOL(blk_get_request_flags);
-
-struct request *blk_get_request(struct request_queue *q, unsigned int op,
-				gfp_t gfp_mask)
-{
-	return blk_get_request_flags(q, op, gfp_mask & __GFP_DIRECT_RECLAIM ?
-				     0 : BLK_MQ_REQ_NOWAIT);
-}
 EXPORT_SYMBOL(blk_get_request);
 
 /**
@@ -1659,7 +1645,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	blk_delete_timer(rq);
 	blk_clear_rq_complete(rq);
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, &rq->issue_stat);
+	wbt_requeue(q->rq_wb, rq);
 
 	if (rq->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, rq);
@@ -1766,7 +1752,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	/* this is a bio leak */
 	WARN_ON(req->bio != NULL);
 
-	wbt_done(q->rq_wb, &req->issue_stat);
+	wbt_done(q->rq_wb, req);
 
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
@@ -2065,7 +2051,7 @@ get_rq:
 	 * Returns with the queue unlocked.
 	 */
 	blk_queue_enter_live(q);
-	req = get_request(q, bio->bi_opf, bio, 0);
+	req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
 	if (IS_ERR(req)) {
 		blk_queue_exit(q);
 		__wbt_done(q->rq_wb, wb_acct);
@@ -2077,7 +2063,7 @@ get_rq:
 		goto out_unlock;
 	}
 
-	wbt_track(&req->issue_stat, wb_acct);
+	wbt_track(req, wb_acct);
 
 	/*
 	 * After dropping the lock and possibly sleeping here, our request
@@ -2391,7 +2377,9 @@ blk_qc_t generic_make_request(struct bio *bio)
 
 	if (bio->bi_opf & REQ_NOWAIT)
 		flags = BLK_MQ_REQ_NOWAIT;
-	if (blk_queue_enter(q, flags) < 0) {
+	if (bio_flagged(bio, BIO_QUEUE_ENTERED))
+		blk_queue_enter_live(q);
+	else if (blk_queue_enter(q, flags) < 0) {
 		if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT))
 			bio_wouldblock_error(bio);
 		else
@@ -2726,7 +2714,7 @@ void blk_account_io_completion(struct request *req, unsigned int bytes)
 	}
 }
 
-void blk_account_io_done(struct request *req)
+void blk_account_io_done(struct request *req, u64 now)
 {
 	/*
 	 * Account IO completion.  flush_rq isn't accounted as a
@@ -2734,11 +2722,12 @@ void blk_account_io_done(struct request *req)
 	 * containing request is enough.
 	 */
 	if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
-		unsigned long duration = jiffies - req->start_time;
+		unsigned long duration;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
 		int cpu;
 
+		duration = nsecs_to_jiffies(now - req->start_time_ns);
 		cpu = part_stat_lock();
 		part = req->part;
 
@@ -2969,10 +2958,8 @@ static void blk_dequeue_request(struct request *rq)
 	 * and to it is freed is accounted as io that is in progress at
 	 * the driver side.
 	 */
-	if (blk_account_rq(rq)) {
+	if (blk_account_rq(rq))
 		q->in_flight[rq_is_sync(rq)]++;
-		set_io_start_time_ns(rq);
-	}
 }
 
 /**
@@ -2991,9 +2978,12 @@ void blk_start_request(struct request *req)
 	blk_dequeue_request(req);
 
 	if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
-		blk_stat_set_issue(&req->issue_stat, blk_rq_sectors(req));
+		req->io_start_time_ns = ktime_get_ns();
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+		req->throtl_size = blk_rq_sectors(req);
+#endif
 		req->rq_flags |= RQF_STATS;
-		wbt_issue(req->q->rq_wb, &req->issue_stat);
+		wbt_issue(req->q->rq_wb, req);
 	}
 
 	BUG_ON(blk_rq_is_complete(req));
@@ -3091,8 +3081,10 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		struct bio *bio = req->bio;
 		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_iter.bi_size)
+		if (bio_bytes == bio->bi_iter.bi_size) {
 			req->bio = bio->bi_next;
+			bio->bi_next = NULL;
+		}
 
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
@@ -3189,12 +3181,13 @@ EXPORT_SYMBOL_GPL(blk_unprep_request);
 void blk_finish_request(struct request *req, blk_status_t error)
 {
 	struct request_queue *q = req->q;
+	u64 now = ktime_get_ns();
 
 	lockdep_assert_held(req->q->queue_lock);
 	WARN_ON_ONCE(q->mq_ops);
 
 	if (req->rq_flags & RQF_STATS)
-		blk_stat_add(req);
+		blk_stat_add(req, now);
 
 	if (req->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, req);
@@ -3209,10 +3202,10 @@ void blk_finish_request(struct request *req, blk_status_t error)
 	if (req->rq_flags & RQF_DONTPREP)
 		blk_unprep_request(req);
 
-	blk_account_io_done(req);
+	blk_account_io_done(req, now);
 
 	if (req->end_io) {
-		wbt_done(req->q->rq_wb, &req->issue_stat);
+		wbt_done(req->q->rq_wb, req);
 		req->end_io(req, error);
 	} else {
 		if (blk_bidi_rq(req))
@@ -3518,7 +3511,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	struct bio *bio, *bio_src;
 
 	if (!bs)
-		bs = fs_bio_set;
+		bs = &fs_bio_set;
 
 	__rq_for_each_bio(bio_src, rq_src) {
 		bio = bio_clone_fast(bio_src, gfp_mask, bs);
@@ -3629,7 +3622,7 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
 		blk_run_queue_async(q);
 	else
 		__blk_run_queue(q);
-	spin_unlock(q->queue_lock);
+	spin_unlock_irq(q->queue_lock);
 }
 
 static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
@@ -3677,7 +3670,6 @@ EXPORT_SYMBOL(blk_check_plugged);
 void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 {
 	struct request_queue *q;
-	unsigned long flags;
 	struct request *rq;
 	LIST_HEAD(list);
 	unsigned int depth;
@@ -3697,11 +3689,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	q = NULL;
 	depth = 0;
 
-	/*
-	 * Save and disable interrupts here, to avoid doing it for every
-	 * queue lock we have to take.
-	 */
-	local_irq_save(flags);
 	while (!list_empty(&list)) {
 		rq = list_entry_rq(list.next);
 		list_del_init(&rq->queuelist);
@@ -3714,7 +3701,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 				queue_unplugged(q, depth, from_schedule);
 			q = rq->q;
 			depth = 0;
-			spin_lock(q->queue_lock);
+			spin_lock_irq(q->queue_lock);
 		}
 
 		/*
@@ -3741,8 +3728,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	 */
 	if (q)
 		queue_unplugged(q, depth, from_schedule);
-
-	local_irq_restore(flags);
 }
 
 void blk_finish_plug(struct blk_plug *plug)
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index feb30570eaf5..6121611e1316 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -333,34 +333,34 @@ static ssize_t integrity_device_show(struct blk_integrity *bi, char *page)
 }
 
 static struct integrity_sysfs_entry integrity_format_entry = {
-	.attr = { .name = "format", .mode = S_IRUGO },
+	.attr = { .name = "format", .mode = 0444 },
 	.show = integrity_format_show,
 };
 
 static struct integrity_sysfs_entry integrity_tag_size_entry = {
-	.attr = { .name = "tag_size", .mode = S_IRUGO },
+	.attr = { .name = "tag_size", .mode = 0444 },
 	.show = integrity_tag_size_show,
 };
 
 static struct integrity_sysfs_entry integrity_interval_entry = {
-	.attr = { .name = "protection_interval_bytes", .mode = S_IRUGO },
+	.attr = { .name = "protection_interval_bytes", .mode = 0444 },
 	.show = integrity_interval_show,
 };
 
 static struct integrity_sysfs_entry integrity_verify_entry = {
-	.attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR },
+	.attr = { .name = "read_verify", .mode = 0644 },
 	.show = integrity_verify_show,
 	.store = integrity_verify_store,
 };
 
 static struct integrity_sysfs_entry integrity_generate_entry = {
-	.attr = { .name = "write_generate", .mode = S_IRUGO | S_IWUSR },
+	.attr = { .name = "write_generate", .mode = 0644 },
 	.show = integrity_generate_show,
 	.store = integrity_generate_store,
 };
 
 static struct integrity_sysfs_entry integrity_device_entry = {
-	.attr = { .name = "device_is_integrity_capable", .mode = S_IRUGO },
+	.attr = { .name = "device_is_integrity_capable", .mode = 0444 },
 	.show = integrity_device_show,
 };
 
diff --git a/block/blk-lib.c b/block/blk-lib.c
index a676084d4740..8faa70f26fcd 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -62,10 +62,16 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		unsigned int req_sects;
 		sector_t end_sect, tmp;
 
-		/* Make sure bi_size doesn't overflow */
-		req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9);
+		/*
+		 * Issue in chunks of the user defined max discard setting,
+		 * ensuring that bi_size doesn't overflow
+		 */
+		req_sects = min_t(sector_t, nr_sects,
+					q->limits.max_discard_sectors);
+		if (req_sects > UINT_MAX >> 9)
+			req_sects = UINT_MAX >> 9;
 
-		/**
+		/*
 		 * If splitting a request, and the next starting sector would be
 		 * misaligned, stop the discard at the previous aligned sector.
 		 */
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 782940c65d8a..aaec38cc37b8 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -188,16 +188,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio)
 	switch (bio_op(*bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
-		split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs);
+		split = blk_bio_discard_split(q, *bio, &q->bio_split, &nsegs);
 		break;
 	case REQ_OP_WRITE_ZEROES:
-		split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs);
+		split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, &nsegs);
 		break;
 	case REQ_OP_WRITE_SAME:
-		split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs);
+		split = blk_bio_write_same_split(q, *bio, &q->bio_split, &nsegs);
 		break;
 	default:
-		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+		split = blk_bio_segment_split(q, *bio, &q->bio_split, &nsegs);
 		break;
 	}
 
@@ -210,6 +210,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio)
 		/* there isn't chance to merge the splitted bio */
 		split->bi_opf |= REQ_NOMERGE;
 
+		/*
+		 * Since we're recursing into make_request here, ensure
+		 * that we mark this bio as already having entered the queue.
+		 * If not, and the queue is going away, we can get stuck
+		 * forever on waiting for the queue reference to drop. But
+		 * that will never happen, as we're already holding a
+		 * reference to it.
+		 */
+		bio_set_flag(*bio, BIO_QUEUE_ENTERED);
+
 		bio_chain(split, *bio);
 		trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
 		generic_make_request(*bio);
@@ -724,13 +734,12 @@ static struct request *attempt_merge(struct request_queue *q,
 	}
 
 	/*
-	 * At this point we have either done a back merge
-	 * or front merge. We need the smaller start_time of
-	 * the merged requests to be the current request
-	 * for accounting purposes.
+	 * At this point we have either done a back merge or front merge. We
+	 * need the smaller start_time_ns of the merged requests to be the
+	 * current request for accounting purposes.
 	 */
-	if (time_after(req->start_time, next->start_time))
-		req->start_time = next->start_time;
+	if (next->start_time_ns < req->start_time_ns)
+		req->start_time_ns = next->start_time_ns;
 
 	req->biotail->bi_next = next->bio;
 	req->biotail = next->biotail;
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3080e18cb859..ffa622366922 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -344,7 +344,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),
 	RQF_NAME(ZONE_WRITE_LOCKED),
-	RQF_NAME(MQ_TIMEOUT_EXPIRED),
 	RQF_NAME(MQ_POLL_SLEPT),
 };
 #undef RQF_NAME
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 25c14c58385c..56c493c6cd90 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -268,19 +268,16 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
 
 /*
- * Reverse check our software queue for entries that we could potentially
- * merge with. Currently includes a hand-wavy stop count of 8, to not spend
- * too much time checking for merges.
+ * Iterate list of requests and see if we can merge this bio with any
+ * of them.
  */
-static bool blk_mq_attempt_merge(struct request_queue *q,
-				 struct blk_mq_ctx *ctx, struct bio *bio)
+bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
+			   struct bio *bio)
 {
 	struct request *rq;
 	int checked = 8;
 
-	lockdep_assert_held(&ctx->lock);
-
-	list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
+	list_for_each_entry_reverse(rq, list, queuelist) {
 		bool merged = false;
 
 		if (!checked--)
@@ -305,13 +302,30 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 			continue;
 		}
 
-		if (merged)
-			ctx->rq_merged++;
 		return merged;
 	}
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge);
+
+/*
+ * Reverse check our software queue for entries that we could potentially
+ * merge with. Currently includes a hand-wavy stop count of 8, to not spend
+ * too much time checking for merges.
+ */
+static bool blk_mq_attempt_merge(struct request_queue *q,
+				 struct blk_mq_ctx *ctx, struct bio *bio)
+{
+	lockdep_assert_held(&ctx->lock);
+
+	if (blk_mq_bio_list_merge(q, &ctx->rq_list, bio)) {
+		ctx->rq_merged++;
+		return true;
+	}
+
+	return false;
+}
 
 bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 {
@@ -571,6 +585,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 
 	if (!e) {
 		q->elevator = NULL;
+		q->nr_requests = q->tag_set->queue_depth;
 		return 0;
 	}
 
@@ -633,14 +648,3 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
 	blk_mq_sched_tags_teardown(q);
 	q->elevator = NULL;
 }
-
-int blk_mq_sched_init(struct request_queue *q)
-{
-	int ret;
-
-	mutex_lock(&q->sysfs_lock);
-	ret = elevator_init(q, NULL);
-	mutex_unlock(&q->sysfs_lock);
-
-	return ret;
-}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 1e9c9018ace1..0cb8f938dff9 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -33,8 +33,6 @@ int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 			    unsigned int hctx_idx);
 
-int blk_mq_sched_init(struct request_queue *q);
-
 static inline bool
 blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 {
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index a54b4b070f1c..aafb44224c89 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -166,15 +166,15 @@ static struct attribute *default_ctx_attrs[] = {
 };
 
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = {
-	.attr = {.name = "nr_tags", .mode = S_IRUGO },
+	.attr = {.name = "nr_tags", .mode = 0444 },
 	.show = blk_mq_hw_sysfs_nr_tags_show,
 };
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_reserved_tags = {
-	.attr = {.name = "nr_reserved_tags", .mode = S_IRUGO },
+	.attr = {.name = "nr_reserved_tags", .mode = 0444 },
 	.show = blk_mq_hw_sysfs_nr_reserved_tags_show,
 };
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = {
-	.attr = {.name = "cpu_list", .mode = S_IRUGO },
+	.attr = {.name = "cpu_list", .mode = 0444 },
 	.show = blk_mq_hw_sysfs_cpus_show,
 };
 
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 336dde07b230..70356a2a11ab 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -134,6 +134,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	ws = bt_wait_ptr(bt, data->hctx);
 	drop_ctx = data->ctx == NULL;
 	do {
+		struct sbitmap_queue *bt_prev;
+
 		/*
 		 * We're out of tags on this hardware queue, kick any
 		 * pending IO submits before going to sleep waiting for
@@ -159,6 +161,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 		if (data->ctx)
 			blk_mq_put_ctx(data->ctx);
 
+		bt_prev = bt;
 		io_schedule();
 
 		data->ctx = blk_mq_get_ctx(data->q);
@@ -170,6 +173,15 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 			bt = &tags->bitmap_tags;
 
 		finish_wait(&ws->wait, &wait);
+
+		/*
+		 * If destination hw queue is changed, fake wake up on
+		 * previous queue for compensating the wake up miss, so
+		 * other allocations on previous queue won't be starved.
+		 */
+		if (bt != bt_prev)
+			sbitmap_queue_wake_up(bt_prev);
+
 		ws = bt_wait_ptr(bt, data->hctx);
 	} while (1);
 
@@ -259,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * test and set the bit before assining ->rqs[].
 	 */
 	rq = tags->rqs[bitnr];
-	if (rq)
+	if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
 		iter_data->fn(rq, iter_data->data, reserved);
 
 	return true;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0dc9e341c2a7..d2de0a719ab8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -95,18 +95,15 @@ static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	if (blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) {
-		/*
-		 * index[0] counts the specific partition that was asked
-		 * for. index[1] counts the ones that are active on the
-		 * whole device, so increment that if mi->part is indeed
-		 * a partition, and not a whole device.
-		 */
-		if (rq->part == mi->part)
-			mi->inflight[0]++;
-		if (mi->part->partno)
-			mi->inflight[1]++;
-	}
+	/*
+	 * index[0] counts the specific partition that was asked for. index[1]
+	 * counts the ones that are active on the whole device, so increment
+	 * that if mi->part is indeed a partition, and not a whole device.
+	 */
+	if (rq->part == mi->part)
+		mi->inflight[0]++;
+	if (mi->part->partno)
+		mi->inflight[1]++;
 }
 
 void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
@@ -118,6 +115,25 @@ void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
 }
 
+static void blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
+				     struct request *rq, void *priv,
+				     bool reserved)
+{
+	struct mq_inflight *mi = priv;
+
+	if (rq->part == mi->part)
+		mi->inflight[rq_data_dir(rq)]++;
+}
+
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+			 unsigned int inflight[2])
+{
+	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+
+	inflight[0] = inflight[1] = 0;
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+}
+
 void blk_freeze_queue_start(struct request_queue *q)
 {
 	int freeze_depth;
@@ -293,7 +309,8 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->rq_disk = NULL;
 	rq->part = NULL;
-	rq->start_time = jiffies;
+	rq->start_time_ns = ktime_get_ns();
+	rq->io_start_time_ns = 0;
 	rq->nr_phys_segments = 0;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
@@ -312,11 +329,10 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 
 #ifdef CONFIG_BLK_CGROUP
 	rq->rl = NULL;
-	set_start_time_ns(rq);
-	rq->io_start_time_ns = 0;
 #endif
 
 	data->ctx->rq_dispatched[op_is_sync(op)]++;
+	refcount_set(&rq->ref, 1);
 	return rq;
 }
 
@@ -345,9 +361,11 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 
 		/*
 		 * Flush requests are special and go directly to the
-		 * dispatch list.
+		 * dispatch list. Don't include reserved tags in the
+		 * limiting, as it isn't useful.
 		 */
-		if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
+		if (!op_is_flush(op) && e->type->ops.mq.limit_depth &&
+		    !(data->flags & BLK_MQ_REQ_RESERVED))
 			e->type->ops.mq.limit_depth(op, data);
 	}
 
@@ -448,13 +466,27 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
 
+static void __blk_mq_free_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+	const int sched_tag = rq->internal_tag;
+
+	if (rq->tag != -1)
+		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
+	if (sched_tag != -1)
+		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+	blk_mq_sched_restart(hctx);
+	blk_queue_exit(q);
+}
+
 void blk_mq_free_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-	const int sched_tag = rq->internal_tag;
 
 	if (rq->rq_flags & RQF_ELVPRIV) {
 		if (e && e->type->ops.mq.finish_request)
@@ -472,27 +504,30 @@ void blk_mq_free_request(struct request *rq)
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
 
-	wbt_done(q->rq_wb, &rq->issue_stat);
+	wbt_done(q->rq_wb, rq);
 
 	if (blk_rq_rl(rq))
 		blk_put_rl(blk_rq_rl(rq));
 
-	blk_mq_rq_update_state(rq, MQ_RQ_IDLE);
-	if (rq->tag != -1)
-		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
-	if (sched_tag != -1)
-		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
-	blk_mq_sched_restart(hctx);
-	blk_queue_exit(q);
+	WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+	if (refcount_dec_and_test(&rq->ref))
+		__blk_mq_free_request(rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_free_request);
 
 inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 {
-	blk_account_io_done(rq);
+	u64 now = ktime_get_ns();
+
+	if (rq->rq_flags & RQF_STATS) {
+		blk_mq_poll_stats_start(rq->q);
+		blk_stat_add(rq, now);
+	}
+
+	blk_account_io_done(rq, now);
 
 	if (rq->end_io) {
-		wbt_done(rq->q->rq_wb, &rq->issue_stat);
+		wbt_done(rq->q->rq_wb, rq);
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
@@ -523,15 +558,12 @@ static void __blk_mq_complete_request(struct request *rq)
 	bool shared = false;
 	int cpu;
 
-	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT);
-	blk_mq_rq_update_state(rq, MQ_RQ_COMPLETE);
+	if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) !=
+			MQ_RQ_IN_FLIGHT)
+		return;
 
 	if (rq->internal_tag != -1)
 		blk_mq_sched_completed_request(rq);
-	if (rq->rq_flags & RQF_STATS) {
-		blk_mq_poll_stats_start(rq->q);
-		blk_stat_add(rq);
-	}
 
 	if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
 		rq->q->softirq_done_fn(rq);
@@ -573,36 +605,6 @@ static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
 		*srcu_idx = srcu_read_lock(hctx->srcu);
 }
 
-static void blk_mq_rq_update_aborted_gstate(struct request *rq, u64 gstate)
-{
-	unsigned long flags;
-
-	/*
-	 * blk_mq_rq_aborted_gstate() is used from the completion path and
-	 * can thus be called from irq context.  u64_stats_fetch in the
-	 * middle of update on the same CPU leads to lockup.  Disable irq
-	 * while updating.
-	 */
-	local_irq_save(flags);
-	u64_stats_update_begin(&rq->aborted_gstate_sync);
-	rq->aborted_gstate = gstate;
-	u64_stats_update_end(&rq->aborted_gstate_sync);
-	local_irq_restore(flags);
-}
-
-static u64 blk_mq_rq_aborted_gstate(struct request *rq)
-{
-	unsigned int start;
-	u64 aborted_gstate;
-
-	do {
-		start = u64_stats_fetch_begin(&rq->aborted_gstate_sync);
-		aborted_gstate = rq->aborted_gstate;
-	} while (u64_stats_fetch_retry(&rq->aborted_gstate_sync, start));
-
-	return aborted_gstate;
-}
-
 /**
  * blk_mq_complete_request - end I/O on a request
  * @rq:		the request being processed
@@ -613,28 +615,9 @@ static u64 blk_mq_rq_aborted_gstate(struct request *rq)
  **/
 void blk_mq_complete_request(struct request *rq)
 {
-	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
-	int srcu_idx;
-
-	if (unlikely(blk_should_fake_timeout(q)))
+	if (unlikely(blk_should_fake_timeout(rq->q)))
 		return;
-
-	/*
-	 * If @rq->aborted_gstate equals the current instance, timeout is
-	 * claiming @rq and we lost.  This is synchronized through
-	 * hctx_lock().  See blk_mq_timeout_work() for details.
-	 *
-	 * Completion path never blocks and we can directly use RCU here
-	 * instead of hctx_lock() which can be either RCU or SRCU.
-	 * However, that would complicate paths which want to synchronize
-	 * against us.  Let stay in sync with the issue path so that
-	 * hctx_lock() covers both issue and completion paths.
-	 */
-	hctx_lock(hctx, &srcu_idx);
-	if (blk_mq_rq_aborted_gstate(rq) != rq->gstate)
-		__blk_mq_complete_request(rq);
-	hctx_unlock(hctx, srcu_idx);
+	__blk_mq_complete_request(rq);
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
@@ -653,32 +636,18 @@ void blk_mq_start_request(struct request *rq)
 	trace_block_rq_issue(q, rq);
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
-		blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq));
+		rq->io_start_time_ns = ktime_get_ns();
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+		rq->throtl_size = blk_rq_sectors(rq);
+#endif
 		rq->rq_flags |= RQF_STATS;
-		wbt_issue(q->rq_wb, &rq->issue_stat);
+		wbt_issue(q->rq_wb, rq);
 	}
 
 	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
 
-	/*
-	 * Mark @rq in-flight which also advances the generation number,
-	 * and register for timeout.  Protect with a seqcount to allow the
-	 * timeout path to read both @rq->gstate and @rq->deadline
-	 * coherently.
-	 *
-	 * This is the only place where a request is marked in-flight.  If
-	 * the timeout path reads an in-flight @rq->gstate, the
-	 * @rq->deadline it reads together under @rq->gstate_seq is
-	 * guaranteed to be the matching one.
-	 */
-	preempt_disable();
-	write_seqcount_begin(&rq->gstate_seq);
-
-	blk_mq_rq_update_state(rq, MQ_RQ_IN_FLIGHT);
 	blk_add_timer(rq);
-
-	write_seqcount_end(&rq->gstate_seq);
-	preempt_enable();
+	WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
 
 	if (q->dma_drain_size && blk_rq_bytes(rq)) {
 		/*
@@ -691,11 +660,6 @@ void blk_mq_start_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_start_request);
 
-/*
- * When we reach here because queue is busy, it's safe to change the state
- * to IDLE without checking @rq->aborted_gstate because we should still be
- * holding the RCU read lock and thus protected against timeout.
- */
 static void __blk_mq_requeue_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -703,10 +667,10 @@ static void __blk_mq_requeue_request(struct request *rq)
 	blk_mq_put_driver_tag(rq);
 
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, &rq->issue_stat);
+	wbt_requeue(q->rq_wb, rq);
 
-	if (blk_mq_rq_state(rq) != MQ_RQ_IDLE) {
-		blk_mq_rq_update_state(rq, MQ_RQ_IDLE);
+	if (blk_mq_request_started(rq)) {
+		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
 		if (q->dma_drain_size && blk_rq_bytes(rq))
 			rq->nr_phys_segments--;
 	}
@@ -804,101 +768,79 @@ struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 }
 EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
-struct blk_mq_timeout_data {
-	unsigned long next;
-	unsigned int next_set;
-	unsigned int nr_expired;
-};
-
 static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
-	const struct blk_mq_ops *ops = req->q->mq_ops;
-	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
+	if (req->q->mq_ops->timeout) {
+		enum blk_eh_timer_return ret;
 
-	req->rq_flags |= RQF_MQ_TIMEOUT_EXPIRED;
-
-	if (ops->timeout)
-		ret = ops->timeout(req, reserved);
-
-	switch (ret) {
-	case BLK_EH_HANDLED:
-		__blk_mq_complete_request(req);
-		break;
-	case BLK_EH_RESET_TIMER:
-		/*
-		 * As nothing prevents from completion happening while
-		 * ->aborted_gstate is set, this may lead to ignored
-		 * completions and further spurious timeouts.
-		 */
-		blk_mq_rq_update_aborted_gstate(req, 0);
-		blk_add_timer(req);
-		break;
-	case BLK_EH_NOT_HANDLED:
-		break;
-	default:
-		printk(KERN_ERR "block: bad eh return: %d\n", ret);
-		break;
+		ret = req->q->mq_ops->timeout(req, reserved);
+		if (ret == BLK_EH_DONE)
+			return;
+		WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
 	}
+
+	blk_add_timer(req);
 }
 
-static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
-		struct request *rq, void *priv, bool reserved)
+static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 {
-	struct blk_mq_timeout_data *data = priv;
-	unsigned long gstate, deadline;
-	int start;
+	unsigned long deadline;
 
-	might_sleep();
-
-	if (rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED)
-		return;
+	if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
+		return false;
 
-	/* read coherent snapshots of @rq->state_gen and @rq->deadline */
-	while (true) {
-		start = read_seqcount_begin(&rq->gstate_seq);
-		gstate = READ_ONCE(rq->gstate);
-		deadline = blk_rq_deadline(rq);
-		if (!read_seqcount_retry(&rq->gstate_seq, start))
-			break;
-		cond_resched();
-	}
+	deadline = blk_rq_deadline(rq);
+	if (time_after_eq(jiffies, deadline))
+		return true;
 
-	/* if in-flight && overdue, mark for abortion */
-	if ((gstate & MQ_RQ_STATE_MASK) == MQ_RQ_IN_FLIGHT &&
-	    time_after_eq(jiffies, deadline)) {
-		blk_mq_rq_update_aborted_gstate(rq, gstate);
-		data->nr_expired++;
-		hctx->nr_expired++;
-	} else if (!data->next_set || time_after(data->next, deadline)) {
-		data->next = deadline;
-		data->next_set = 1;
-	}
+	if (*next == 0)
+		*next = deadline;
+	else if (time_after(*next, deadline))
+		*next = deadline;
+	return false;
 }
 
-static void blk_mq_terminate_expired(struct blk_mq_hw_ctx *hctx,
+static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		struct request *rq, void *priv, bool reserved)
 {
+	unsigned long *next = priv;
+
+	/*
+	 * Just do a quick check if it is expired before locking the request in
+	 * so we're not unnecessarilly synchronizing across CPUs.
+	 */
+	if (!blk_mq_req_expired(rq, next))
+		return;
+
+	/*
+	 * We have reason to believe the request may be expired. Take a
+	 * reference on the request to lock this request lifetime into its
+	 * currently allocated context to prevent it from being reallocated in
+	 * the event the completion by-passes this timeout handler.
+	 *
+	 * If the reference was already released, then the driver beat the
+	 * timeout handler to posting a natural completion.
+	 */
+	if (!refcount_inc_not_zero(&rq->ref))
+		return;
+
 	/*
-	 * We marked @rq->aborted_gstate and waited for RCU.  If there were
-	 * completions that we lost to, they would have finished and
-	 * updated @rq->gstate by now; otherwise, the completion path is
-	 * now guaranteed to see @rq->aborted_gstate and yield.  If
-	 * @rq->aborted_gstate still matches @rq->gstate, @rq is ours.
+	 * The request is now locked and cannot be reallocated underneath the
+	 * timeout handler's processing. Re-verify this exact request is truly
+	 * expired; if it is not expired, then the request was completed and
+	 * reallocated as a new request.
 	 */
-	if (!(rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED) &&
-	    READ_ONCE(rq->gstate) == rq->aborted_gstate)
+	if (blk_mq_req_expired(rq, next))
 		blk_mq_rq_timed_out(rq, reserved);
+	if (refcount_dec_and_test(&rq->ref))
+		__blk_mq_free_request(rq);
 }
 
 static void blk_mq_timeout_work(struct work_struct *work)
 {
 	struct request_queue *q =
 		container_of(work, struct request_queue, timeout_work);
-	struct blk_mq_timeout_data data = {
-		.next		= 0,
-		.next_set	= 0,
-		.nr_expired	= 0,
-	};
+	unsigned long next = 0;
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
@@ -918,39 +860,10 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
 
-	/* scan for the expired ones and set their ->aborted_gstate */
-	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
-
-	if (data.nr_expired) {
-		bool has_rcu = false;
-
-		/*
-		 * Wait till everyone sees ->aborted_gstate.  The
-		 * sequential waits for SRCUs aren't ideal.  If this ever
-		 * becomes a problem, we can add per-hw_ctx rcu_head and
-		 * wait in parallel.
-		 */
-		queue_for_each_hw_ctx(q, hctx, i) {
-			if (!hctx->nr_expired)
-				continue;
-
-			if (!(hctx->flags & BLK_MQ_F_BLOCKING))
-				has_rcu = true;
-			else
-				synchronize_srcu(hctx->srcu);
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next);
 
-			hctx->nr_expired = 0;
-		}
-		if (has_rcu)
-			synchronize_rcu();
-
-		/* terminate the ones we won */
-		blk_mq_queue_tag_busy_iter(q, blk_mq_terminate_expired, NULL);
-	}
-
-	if (data.next_set) {
-		data.next = blk_rq_timeout(round_jiffies_up(data.next));
-		mod_timer(&q->timeout, data.next);
+	if (next != 0) {
+		mod_timer(&q->timeout, next);
 	} else {
 		/*
 		 * Request timeouts are handled as a forward rolling timer. If
@@ -1013,7 +926,7 @@ static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr,
 	struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
 
 	spin_lock(&ctx->lock);
-	if (unlikely(!list_empty(&ctx->rq_list))) {
+	if (!list_empty(&ctx->rq_list)) {
 		dispatch_data->rq = list_entry_rq(ctx->rq_list.next);
 		list_del_init(&dispatch_data->rq->queuelist);
 		if (list_empty(&ctx->rq_list))
@@ -1562,7 +1475,7 @@ static void blk_mq_run_work_fn(struct work_struct *work)
 	 * If we are stopped, don't run the queue.
 	 */
 	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state))
-		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+		return;
 
 	__blk_mq_run_hw_queue(hctx);
 }
@@ -1700,15 +1613,6 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
 	blk_account_io_start(rq, true);
 }
 
-static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx,
-				   struct blk_mq_ctx *ctx,
-				   struct request *rq)
-{
-	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq, false);
-	spin_unlock(&ctx->lock);
-}
-
 static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
 	if (rq->tag != -1)
@@ -1866,7 +1770,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	wbt_track(&rq->issue_stat, wb_acct);
+	wbt_track(rq, wb_acct);
 
 	cookie = request_to_qc_t(data.hctx, rq);
 
@@ -1933,15 +1837,10 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
-	} else if (q->elevator) {
-		blk_mq_put_ctx(data.ctx);
-		blk_mq_bio_to_request(rq, bio);
-		blk_mq_sched_insert_request(rq, false, true, true);
 	} else {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_queue_io(data.hctx, data.ctx, rq);
-		blk_mq_run_hw_queue(data.hctx, true);
+		blk_mq_sched_insert_request(rq, false, true, true);
 	}
 
 	return cookie;
@@ -2040,8 +1939,7 @@ static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
 			return ret;
 	}
 
-	seqcount_init(&rq->gstate_seq);
-	u64_stats_init(&rq->aborted_gstate_sync);
+	WRITE_ONCE(rq->state, MQ_RQ_IDLE);
 	return 0;
 }
 
@@ -2329,7 +2227,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 
 static void blk_mq_map_swqueue(struct request_queue *q)
 {
-	unsigned int i;
+	unsigned int i, hctx_idx;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
@@ -2342,12 +2240,28 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	queue_for_each_hw_ctx(q, hctx, i) {
 		cpumask_clear(hctx->cpumask);
 		hctx->nr_ctx = 0;
+		hctx->dispatch_from = NULL;
 	}
 
 	/*
 	 * Map software to hardware queues.
+	 *
+	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
 	for_each_possible_cpu(i) {
+		hctx_idx = q->mq_map[i];
+		/* unmapped hw queue can be remapped after CPU topo changed */
+		if (!set->tags[hctx_idx] &&
+		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
+			/*
+			 * If tags initialization fail for some hctx,
+			 * that hctx won't be brought online.  In this
+			 * case, remap the current ctx to hctx[0] which
+			 * is guaranteed to always have tags allocated
+			 */
+			q->mq_map[i] = 0;
+		}
+
 		ctx = per_cpu_ptr(q->queue_ctx, i);
 		hctx = blk_mq_map_queue(q, i);
 
@@ -2359,8 +2273,21 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	mutex_unlock(&q->sysfs_lock);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		/* every hctx should get mapped by at least one CPU */
-		WARN_ON(!hctx->nr_ctx);
+		/*
+		 * If no software queues are mapped to this hardware queue,
+		 * disable it and free the request entries.
+		 */
+		if (!hctx->nr_ctx) {
+			/* Never unmap queue 0.  We need it as a
+			 * fallback in case of a new remap fails
+			 * allocation
+			 */
+			if (i && set->tags[i])
+				blk_mq_free_map_and_requests(set, i);
+
+			hctx->tags = NULL;
+			continue;
+		}
 
 		hctx->tags = set->tags[i];
 		WARN_ON(!hctx->tags);
@@ -2646,7 +2573,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
 		int ret;
 
-		ret = blk_mq_sched_init(q);
+		ret = elevator_init_mq(q);
 		if (ret)
 			return ERR_PTR(ret);
 	}
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 88c558f71819..89231e439b2f 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -7,6 +7,9 @@
 
 struct blk_mq_tag_set;
 
+/**
+ * struct blk_mq_ctx - State for a software queue facing the submitting CPUs
+ */
 struct blk_mq_ctx {
 	struct {
 		spinlock_t		lock;
@@ -27,20 +30,6 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 } ____cacheline_aligned_in_smp;
 
-/*
- * Bits for request->gstate.  The lower two bits carry MQ_RQ_* state value
- * and the upper bits the generation number.
- */
-enum mq_rq_state {
-	MQ_RQ_IDLE		= 0,
-	MQ_RQ_IN_FLIGHT		= 1,
-	MQ_RQ_COMPLETE		= 2,
-
-	MQ_RQ_STATE_BITS	= 2,
-	MQ_RQ_STATE_MASK	= (1 << MQ_RQ_STATE_BITS) - 1,
-	MQ_RQ_GEN_INC		= 1 << MQ_RQ_STATE_BITS,
-};
-
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
@@ -104,33 +93,9 @@ void blk_mq_release(struct request_queue *q);
  * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
  * @rq: target request.
  */
-static inline int blk_mq_rq_state(struct request *rq)
+static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
 {
-	return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK;
-}
-
-/**
- * blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request
- * @rq: target request.
- * @state: new state to set.
- *
- * Set @rq's state to @state.  The caller is responsible for ensuring that
- * there are no other updaters.  A request can transition into IN_FLIGHT
- * only from IDLE and doing so increments the generation number.
- */
-static inline void blk_mq_rq_update_state(struct request *rq,
-					  enum mq_rq_state state)
-{
-	u64 old_val = READ_ONCE(rq->gstate);
-	u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state;
-
-	if (state == MQ_RQ_IN_FLIGHT) {
-		WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE);
-		new_val += MQ_RQ_GEN_INC;
-	}
-
-	/* avoid exposing interim values */
-	WRITE_ONCE(rq->gstate, new_val);
+	return READ_ONCE(rq->state);
 }
 
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
@@ -185,7 +150,9 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
 }
 
 void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
-			unsigned int inflight[2]);
+		      unsigned int inflight[2]);
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+			 unsigned int inflight[2]);
 
 static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
 {
diff --git a/block/blk-stat.c b/block/blk-stat.c
index bd365a95fcf8..175c143ac5b9 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -47,19 +47,15 @@ static void __blk_stat_add(struct blk_rq_stat *stat, u64 value)
 	stat->nr_samples++;
 }
 
-void blk_stat_add(struct request *rq)
+void blk_stat_add(struct request *rq, u64 now)
 {
 	struct request_queue *q = rq->q;
 	struct blk_stat_callback *cb;
 	struct blk_rq_stat *stat;
 	int bucket;
-	u64 now, value;
+	u64 value;
 
-	now = __blk_stat_time(ktime_to_ns(ktime_get()));
-	if (now < blk_stat_time(&rq->issue_stat))
-		return;
-
-	value = now - blk_stat_time(&rq->issue_stat);
+	value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
 
 	blk_throtl_stat_add(rq, value);
 
diff --git a/block/blk-stat.h b/block/blk-stat.h
index 2dd36347252a..78399cdde9c9 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -8,21 +8,6 @@
 #include <linux/rcupdate.h>
 #include <linux/timer.h>
 
-/*
- * from upper:
- * 3 bits: reserved for other usage
- * 12 bits: size
- * 49 bits: time
- */
-#define BLK_STAT_RES_BITS	3
-#define BLK_STAT_SIZE_BITS	12
-#define BLK_STAT_RES_SHIFT	(64 - BLK_STAT_RES_BITS)
-#define BLK_STAT_SIZE_SHIFT	(BLK_STAT_RES_SHIFT - BLK_STAT_SIZE_BITS)
-#define BLK_STAT_TIME_MASK	((1ULL << BLK_STAT_SIZE_SHIFT) - 1)
-#define BLK_STAT_SIZE_MASK	\
-	(((1ULL << BLK_STAT_SIZE_BITS) - 1) << BLK_STAT_SIZE_SHIFT)
-#define BLK_STAT_RES_MASK	(~((1ULL << BLK_STAT_RES_SHIFT) - 1))
-
 /**
  * struct blk_stat_callback - Block statistics callback.
  *
@@ -80,35 +65,7 @@ struct blk_stat_callback {
 struct blk_queue_stats *blk_alloc_queue_stats(void);
 void blk_free_queue_stats(struct blk_queue_stats *);
 
-void blk_stat_add(struct request *);
-
-static inline u64 __blk_stat_time(u64 time)
-{
-	return time & BLK_STAT_TIME_MASK;
-}
-
-static inline u64 blk_stat_time(struct blk_issue_stat *stat)
-{
-	return __blk_stat_time(stat->stat);
-}
-
-static inline sector_t blk_capped_size(sector_t size)
-{
-	return size & ((1ULL << BLK_STAT_SIZE_BITS) - 1);
-}
-
-static inline sector_t blk_stat_size(struct blk_issue_stat *stat)
-{
-	return (stat->stat & BLK_STAT_SIZE_MASK) >> BLK_STAT_SIZE_SHIFT;
-}
-
-static inline void blk_stat_set_issue(struct blk_issue_stat *stat,
-	sector_t size)
-{
-	stat->stat = (stat->stat & BLK_STAT_RES_MASK) |
-		(ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK) |
-		(((u64)blk_capped_size(size)) << BLK_STAT_SIZE_SHIFT);
-}
+void blk_stat_add(struct request *rq, u64 now);
 
 /* record time/size info in request but not add a callback */
 void blk_stat_enable_accounting(struct request_queue *q);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index d00d1b0ec109..94987b1f69e1 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -491,188 +491,198 @@ static ssize_t queue_wc_store(struct request_queue *q, const char *page,
 	return count;
 }
 
+static ssize_t queue_fua_show(struct request_queue *q, char *page)
+{
+	return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags));
+}
+
 static ssize_t queue_dax_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(blk_queue_dax(q), page);
 }
 
 static struct queue_sysfs_entry queue_requests_entry = {
-	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "nr_requests", .mode = 0644 },
 	.show = queue_requests_show,
 	.store = queue_requests_store,
 };
 
 static struct queue_sysfs_entry queue_ra_entry = {
-	.attr = {.name = "read_ahead_kb", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "read_ahead_kb", .mode = 0644 },
 	.show = queue_ra_show,
 	.store = queue_ra_store,
 };
 
 static struct queue_sysfs_entry queue_max_sectors_entry = {
-	.attr = {.name = "max_sectors_kb", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "max_sectors_kb", .mode = 0644 },
 	.show = queue_max_sectors_show,
 	.store = queue_max_sectors_store,
 };
 
 static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
-	.attr = {.name = "max_hw_sectors_kb", .mode = S_IRUGO },
+	.attr = {.name = "max_hw_sectors_kb", .mode = 0444 },
 	.show = queue_max_hw_sectors_show,
 };
 
 static struct queue_sysfs_entry queue_max_segments_entry = {
-	.attr = {.name = "max_segments", .mode = S_IRUGO },
+	.attr = {.name = "max_segments", .mode = 0444 },
 	.show = queue_max_segments_show,
 };
 
 static struct queue_sysfs_entry queue_max_discard_segments_entry = {
-	.attr = {.name = "max_discard_segments", .mode = S_IRUGO },
+	.attr = {.name = "max_discard_segments", .mode = 0444 },
 	.show = queue_max_discard_segments_show,
 };
 
 static struct queue_sysfs_entry queue_max_integrity_segments_entry = {
-	.attr = {.name = "max_integrity_segments", .mode = S_IRUGO },
+	.attr = {.name = "max_integrity_segments", .mode = 0444 },
 	.show = queue_max_integrity_segments_show,
 };
 
 static struct queue_sysfs_entry queue_max_segment_size_entry = {
-	.attr = {.name = "max_segment_size", .mode = S_IRUGO },
+	.attr = {.name = "max_segment_size", .mode = 0444 },
 	.show = queue_max_segment_size_show,
 };
 
 static struct queue_sysfs_entry queue_iosched_entry = {
-	.attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "scheduler", .mode = 0644 },
 	.show = elv_iosched_show,
 	.store = elv_iosched_store,
 };
 
 static struct queue_sysfs_entry queue_hw_sector_size_entry = {
-	.attr = {.name = "hw_sector_size", .mode = S_IRUGO },
+	.attr = {.name = "hw_sector_size", .mode = 0444 },
 	.show = queue_logical_block_size_show,
 };
 
 static struct queue_sysfs_entry queue_logical_block_size_entry = {
-	.attr = {.name = "logical_block_size", .mode = S_IRUGO },
+	.attr = {.name = "logical_block_size", .mode = 0444 },
 	.show = queue_logical_block_size_show,
 };
 
 static struct queue_sysfs_entry queue_physical_block_size_entry = {
-	.attr = {.name = "physical_block_size", .mode = S_IRUGO },
+	.attr = {.name = "physical_block_size", .mode = 0444 },
 	.show = queue_physical_block_size_show,
 };
 
 static struct queue_sysfs_entry queue_chunk_sectors_entry = {
-	.attr = {.name = "chunk_sectors", .mode = S_IRUGO },
+	.attr = {.name = "chunk_sectors", .mode = 0444 },
 	.show = queue_chunk_sectors_show,
 };
 
 static struct queue_sysfs_entry queue_io_min_entry = {
-	.attr = {.name = "minimum_io_size", .mode = S_IRUGO },
+	.attr = {.name = "minimum_io_size", .mode = 0444 },
 	.show = queue_io_min_show,
 };
 
 static struct queue_sysfs_entry queue_io_opt_entry = {
-	.attr = {.name = "optimal_io_size", .mode = S_IRUGO },
+	.attr = {.name = "optimal_io_size", .mode = 0444 },
 	.show = queue_io_opt_show,
 };
 
 static struct queue_sysfs_entry queue_discard_granularity_entry = {
-	.attr = {.name = "discard_granularity", .mode = S_IRUGO },
+	.attr = {.name = "discard_granularity", .mode = 0444 },
 	.show = queue_discard_granularity_show,
 };
 
 static struct queue_sysfs_entry queue_discard_max_hw_entry = {
-	.attr = {.name = "discard_max_hw_bytes", .mode = S_IRUGO },
+	.attr = {.name = "discard_max_hw_bytes", .mode = 0444 },
 	.show = queue_discard_max_hw_show,
 };
 
 static struct queue_sysfs_entry queue_discard_max_entry = {
-	.attr = {.name = "discard_max_bytes", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "discard_max_bytes", .mode = 0644 },
 	.show = queue_discard_max_show,
 	.store = queue_discard_max_store,
 };
 
 static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
-	.attr = {.name = "discard_zeroes_data", .mode = S_IRUGO },
+	.attr = {.name = "discard_zeroes_data", .mode = 0444 },
 	.show = queue_discard_zeroes_data_show,
 };
 
 static struct queue_sysfs_entry queue_write_same_max_entry = {
-	.attr = {.name = "write_same_max_bytes", .mode = S_IRUGO },
+	.attr = {.name = "write_same_max_bytes", .mode = 0444 },
 	.show = queue_write_same_max_show,
 };
 
 static struct queue_sysfs_entry queue_write_zeroes_max_entry = {
-	.attr = {.name = "write_zeroes_max_bytes", .mode = S_IRUGO },
+	.attr = {.name = "write_zeroes_max_bytes", .mode = 0444 },
 	.show = queue_write_zeroes_max_show,
 };
 
 static struct queue_sysfs_entry queue_nonrot_entry = {
-	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "rotational", .mode = 0644 },
 	.show = queue_show_nonrot,
 	.store = queue_store_nonrot,
 };
 
 static struct queue_sysfs_entry queue_zoned_entry = {
-	.attr = {.name = "zoned", .mode = S_IRUGO },
+	.attr = {.name = "zoned", .mode = 0444 },
 	.show = queue_zoned_show,
 };
 
 static struct queue_sysfs_entry queue_nomerges_entry = {
-	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "nomerges", .mode = 0644 },
 	.show = queue_nomerges_show,
 	.store = queue_nomerges_store,
 };
 
 static struct queue_sysfs_entry queue_rq_affinity_entry = {
-	.attr = {.name = "rq_affinity", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "rq_affinity", .mode = 0644 },
 	.show = queue_rq_affinity_show,
 	.store = queue_rq_affinity_store,
 };
 
 static struct queue_sysfs_entry queue_iostats_entry = {
-	.attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "iostats", .mode = 0644 },
 	.show = queue_show_iostats,
 	.store = queue_store_iostats,
 };
 
 static struct queue_sysfs_entry queue_random_entry = {
-	.attr = {.name = "add_random", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "add_random", .mode = 0644 },
 	.show = queue_show_random,
 	.store = queue_store_random,
 };
 
 static struct queue_sysfs_entry queue_poll_entry = {
-	.attr = {.name = "io_poll", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "io_poll", .mode = 0644 },
 	.show = queue_poll_show,
 	.store = queue_poll_store,
 };
 
 static struct queue_sysfs_entry queue_poll_delay_entry = {
-	.attr = {.name = "io_poll_delay", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "io_poll_delay", .mode = 0644 },
 	.show = queue_poll_delay_show,
 	.store = queue_poll_delay_store,
 };
 
 static struct queue_sysfs_entry queue_wc_entry = {
-	.attr = {.name = "write_cache", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "write_cache", .mode = 0644 },
 	.show = queue_wc_show,
 	.store = queue_wc_store,
 };
 
+static struct queue_sysfs_entry queue_fua_entry = {
+	.attr = {.name = "fua", .mode = 0444 },
+	.show = queue_fua_show,
+};
+
 static struct queue_sysfs_entry queue_dax_entry = {
-	.attr = {.name = "dax", .mode = S_IRUGO },
+	.attr = {.name = "dax", .mode = 0444 },
 	.show = queue_dax_show,
 };
 
 static struct queue_sysfs_entry queue_wb_lat_entry = {
-	.attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "wbt_lat_usec", .mode = 0644 },
 	.show = queue_wb_lat_show,
 	.store = queue_wb_lat_store,
 };
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 static struct queue_sysfs_entry throtl_sample_time_entry = {
-	.attr = {.name = "throttle_sample_time", .mode = S_IRUGO | S_IWUSR },
+	.attr = {.name = "throttle_sample_time", .mode = 0644 },
 	.show = blk_throtl_sample_time_show,
 	.store = blk_throtl_sample_time_store,
 };
@@ -708,6 +718,7 @@ static struct attribute *default_attrs[] = {
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
+	&queue_fua_entry.attr,
 	&queue_dax_entry.attr,
 	&queue_wb_lat_entry.attr,
 	&queue_poll_delay_entry.attr,
@@ -813,8 +824,7 @@ static void __blk_release_queue(struct work_struct *work)
 	if (q->mq_ops)
 		blk_mq_debugfs_unregister(q);
 
-	if (q->bio_split)
-		bioset_free(q->bio_split);
+	bioset_exit(&q->bio_split);
 
 	ida_simple_remove(&blk_queue_ida, q->id);
 	call_rcu(&q->rcu_head, blk_free_queue_rcu);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index c5a131673733..82282e6fdcf8 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -36,8 +36,6 @@ static int throtl_quantum = 32;
  */
 #define LATENCY_FILTERED_HD (1000L) /* 1ms */
 
-#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
-
 static struct blkcg_policy blkcg_policy_throtl;
 
 /* A workqueue to queue throttle related work */
@@ -821,7 +819,7 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw)
 	if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw]))
 		return false;
 
-	return 1;
+	return true;
 }
 
 /* Trim the used slices and adjust slice start accordingly */
@@ -931,7 +929,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 
 	if (wait)
 		*wait = jiffy_wait;
-	return 0;
+	return false;
 }
 
 static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
@@ -974,7 +972,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 	jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed);
 	if (wait)
 		*wait = jiffy_wait;
-	return 0;
+	return false;
 }
 
 /*
@@ -1024,7 +1022,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	    tg_with_in_iops_limit(tg, bio, &iops_wait)) {
 		if (wait)
 			*wait = 0;
-		return 1;
+		return true;
 	}
 
 	max_wait = max(bps_wait, iops_wait);
@@ -1035,7 +1033,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	if (time_before(tg->slice_end[rw], jiffies + max_wait))
 		throtl_extend_slice(tg, rw, jiffies + max_wait);
 
-	return 0;
+	return false;
 }
 
 static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
@@ -1209,7 +1207,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
 
 	while (1) {
 		struct throtl_grp *tg = throtl_rb_first(parent_sq);
-		struct throtl_service_queue *sq = &tg->service_queue;
+		struct throtl_service_queue *sq;
 
 		if (!tg)
 			break;
@@ -1221,6 +1219,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
 
 		nr_disp += throtl_dispatch_tg(tg);
 
+		sq = &tg->service_queue;
 		if (sq->nr_queued[0] || sq->nr_queued[1])
 			tg_update_disptime(tg);
 
@@ -2139,7 +2138,7 @@ static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
 		bio->bi_cg_private = tg;
 		blkg_get(tg_to_blkg(tg));
 	}
-	blk_stat_set_issue(&bio->bi_issue_stat, bio_sectors(bio));
+	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
 #endif
 }
 
@@ -2251,7 +2250,7 @@ out:
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	if (throttled || !td->track_bio_latency)
-		bio->bi_issue_stat.stat |= SKIP_LATENCY;
+		bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY;
 #endif
 	return throttled;
 }
@@ -2281,8 +2280,7 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
 	struct request_queue *q = rq->q;
 	struct throtl_data *td = q->td;
 
-	throtl_track_latency(td, blk_stat_size(&rq->issue_stat),
-		req_op(rq), time_ns >> 10);
+	throtl_track_latency(td, rq->throtl_size, req_op(rq), time_ns >> 10);
 }
 
 void blk_throtl_bio_endio(struct bio *bio)
@@ -2302,8 +2300,8 @@ void blk_throtl_bio_endio(struct bio *bio)
 	finish_time_ns = ktime_get_ns();
 	tg->last_finish_time = finish_time_ns >> 10;
 
-	start_time = blk_stat_time(&bio->bi_issue_stat) >> 10;
-	finish_time = __blk_stat_time(finish_time_ns) >> 10;
+	start_time = bio_issue_time(&bio->bi_issue) >> 10;
+	finish_time = __bio_issue_time(finish_time_ns) >> 10;
 	if (!start_time || finish_time <= start_time) {
 		blkg_put(tg_to_blkg(tg));
 		return;
@@ -2311,16 +2309,15 @@ void blk_throtl_bio_endio(struct bio *bio)
 
 	lat = finish_time - start_time;
 	/* this is only for bio based driver */
-	if (!(bio->bi_issue_stat.stat & SKIP_LATENCY))
-		throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
-			bio_op(bio), lat);
+	if (!(bio->bi_issue.value & BIO_ISSUE_THROTL_SKIP_LATENCY))
+		throtl_track_latency(tg->td, bio_issue_size(&bio->bi_issue),
+				     bio_op(bio), lat);
 
 	if (tg->latency_target && lat >= tg->td->filtered_latency) {
 		int bucket;
 		unsigned int threshold;
 
-		bucket = request_bucket_index(
-			blk_stat_size(&bio->bi_issue_stat));
+		bucket = request_bucket_index(bio_issue_size(&bio->bi_issue));
 		threshold = tg->td->avg_buckets[rw][bucket].latency +
 			tg->latency_target;
 		if (lat > threshold)
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 652d4d4d3e97..4b8a48d48ba1 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -86,14 +86,11 @@ static void blk_rq_timed_out(struct request *req)
 	if (q->rq_timed_out_fn)
 		ret = q->rq_timed_out_fn(req);
 	switch (ret) {
-	case BLK_EH_HANDLED:
-		__blk_complete_request(req);
-		break;
 	case BLK_EH_RESET_TIMER:
 		blk_add_timer(req);
 		blk_clear_rq_complete(req);
 		break;
-	case BLK_EH_NOT_HANDLED:
+	case BLK_EH_DONE:
 		/*
 		 * LLD handles this for now but in the future
 		 * we can send a request msg to abort the command
@@ -214,7 +211,6 @@ void blk_add_timer(struct request *req)
 		req->timeout = q->rq_timeout;
 
 	blk_rq_set_deadline(req, jiffies + req->timeout);
-	req->rq_flags &= ~RQF_MQ_TIMEOUT_EXPIRED;
 
 	/*
 	 * Only the non-mq case needs to add the request to a protected list.
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index f92fc84b5e2c..4f89b28fa652 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -29,6 +29,26 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/wbt.h>
 
+static inline void wbt_clear_state(struct request *rq)
+{
+	rq->wbt_flags = 0;
+}
+
+static inline enum wbt_flags wbt_flags(struct request *rq)
+{
+	return rq->wbt_flags;
+}
+
+static inline bool wbt_is_tracked(struct request *rq)
+{
+	return rq->wbt_flags & WBT_TRACKED;
+}
+
+static inline bool wbt_is_read(struct request *rq)
+{
+	return rq->wbt_flags & WBT_READ;
+}
+
 enum {
 	/*
 	 * Default setting, we'll scale up (to 75% of QD max) or down (min 1)
@@ -101,9 +121,15 @@ static bool wb_recent_wait(struct rq_wb *rwb)
 	return time_before(jiffies, wb->dirty_sleep + HZ);
 }
 
-static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, bool is_kswapd)
+static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
+					  enum wbt_flags wb_acct)
 {
-	return &rwb->rq_wait[is_kswapd];
+	if (wb_acct & WBT_KSWAPD)
+		return &rwb->rq_wait[WBT_RWQ_KSWAPD];
+	else if (wb_acct & WBT_DISCARD)
+		return &rwb->rq_wait[WBT_RWQ_DISCARD];
+
+	return &rwb->rq_wait[WBT_RWQ_BG];
 }
 
 static void rwb_wake_all(struct rq_wb *rwb)
@@ -126,7 +152,7 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
 	if (!(wb_acct & WBT_TRACKED))
 		return;
 
-	rqw = get_rq_wait(rwb, wb_acct & WBT_KSWAPD);
+	rqw = get_rq_wait(rwb, wb_acct);
 	inflight = atomic_dec_return(&rqw->inflight);
 
 	/*
@@ -139,10 +165,13 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
 	}
 
 	/*
-	 * If the device does write back caching, drop further down
-	 * before we wake people up.
+	 * For discards, our limit is always the background. For writes, if
+	 * the device does write back caching, drop further down before we
+	 * wake people up.
 	 */
-	if (rwb->wc && !wb_recent_wait(rwb))
+	if (wb_acct & WBT_DISCARD)
+		limit = rwb->wb_background;
+	else if (rwb->wc && !wb_recent_wait(rwb))
 		limit = 0;
 	else
 		limit = rwb->wb_normal;
@@ -165,24 +194,24 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
  * Called on completion of a request. Note that it's also called when
  * a request is merged, when the request gets freed.
  */
-void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
+void wbt_done(struct rq_wb *rwb, struct request *rq)
 {
 	if (!rwb)
 		return;
 
-	if (!wbt_is_tracked(stat)) {
-		if (rwb->sync_cookie == stat) {
+	if (!wbt_is_tracked(rq)) {
+		if (rwb->sync_cookie == rq) {
 			rwb->sync_issue = 0;
 			rwb->sync_cookie = NULL;
 		}
 
-		if (wbt_is_read(stat))
+		if (wbt_is_read(rq))
 			wb_timestamp(rwb, &rwb->last_comp);
 	} else {
-		WARN_ON_ONCE(stat == rwb->sync_cookie);
-		__wbt_done(rwb, wbt_stat_to_mask(stat));
+		WARN_ON_ONCE(rq == rwb->sync_cookie);
+		__wbt_done(rwb, wbt_flags(rq));
 	}
-	wbt_clear_state(stat);
+	wbt_clear_state(rq);
 }
 
 /*
@@ -479,6 +508,9 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 {
 	unsigned int limit;
 
+	if ((rw & REQ_OP_MASK) == REQ_OP_DISCARD)
+		return rwb->wb_background;
+
 	/*
 	 * At this point we know it's a buffered write. If this is
 	 * kswapd trying to free memory, or REQ_SYNC is set, then
@@ -529,11 +561,12 @@ static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
  * Block if we will exceed our limit, or if we are currently waiting for
  * the timer to kick off queuing again.
  */
-static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock)
+static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
+		       unsigned long rw, spinlock_t *lock)
 	__releases(lock)
 	__acquires(lock)
 {
-	struct rq_wait *rqw = get_rq_wait(rwb, current_is_kswapd());
+	struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
 	DEFINE_WAIT(wait);
 
 	if (may_queue(rwb, rqw, &wait, rw))
@@ -559,21 +592,20 @@ static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock)
 
 static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
 {
-	const int op = bio_op(bio);
-
-	/*
-	 * If not a WRITE, do nothing
-	 */
-	if (op != REQ_OP_WRITE)
-		return false;
-
-	/*
-	 * Don't throttle WRITE_ODIRECT
-	 */
-	if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == (REQ_SYNC | REQ_IDLE))
+	switch (bio_op(bio)) {
+	case REQ_OP_WRITE:
+		/*
+		 * Don't throttle WRITE_ODIRECT
+		 */
+		if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) ==
+		    (REQ_SYNC | REQ_IDLE))
+			return false;
+		/* fallthrough */
+	case REQ_OP_DISCARD:
+		return true;
+	default:
 		return false;
-
-	return true;
+	}
 }
 
 /*
@@ -584,7 +616,7 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
  */
 enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
 {
-	unsigned int ret = 0;
+	enum wbt_flags ret = 0;
 
 	if (!rwb_enabled(rwb))
 		return 0;
@@ -598,41 +630,42 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
 		return ret;
 	}
 
-	__wbt_wait(rwb, bio->bi_opf, lock);
+	if (current_is_kswapd())
+		ret |= WBT_KSWAPD;
+	if (bio_op(bio) == REQ_OP_DISCARD)
+		ret |= WBT_DISCARD;
+
+	__wbt_wait(rwb, ret, bio->bi_opf, lock);
 
 	if (!blk_stat_is_active(rwb->cb))
 		rwb_arm_timer(rwb);
 
-	if (current_is_kswapd())
-		ret |= WBT_KSWAPD;
-
 	return ret | WBT_TRACKED;
 }
 
-void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+void wbt_issue(struct rq_wb *rwb, struct request *rq)
 {
 	if (!rwb_enabled(rwb))
 		return;
 
 	/*
-	 * Track sync issue, in case it takes a long time to complete. Allows
-	 * us to react quicker, if a sync IO takes a long time to complete.
-	 * Note that this is just a hint. 'stat' can go away when the
-	 * request completes, so it's important we never dereference it. We
-	 * only use the address to compare with, which is why we store the
-	 * sync_issue time locally.
+	 * Track sync issue, in case it takes a long time to complete. Allows us
+	 * to react quicker, if a sync IO takes a long time to complete. Note
+	 * that this is just a hint. The request can go away when it completes,
+	 * so it's important we never dereference it. We only use the address to
+	 * compare with, which is why we store the sync_issue time locally.
 	 */
-	if (wbt_is_read(stat) && !rwb->sync_issue) {
-		rwb->sync_cookie = stat;
-		rwb->sync_issue = blk_stat_time(stat);
+	if (wbt_is_read(rq) && !rwb->sync_issue) {
+		rwb->sync_cookie = rq;
+		rwb->sync_issue = rq->io_start_time_ns;
 	}
 }
 
-void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+void wbt_requeue(struct rq_wb *rwb, struct request *rq)
 {
 	if (!rwb_enabled(rwb))
 		return;
-	if (stat == rwb->sync_cookie) {
+	if (rq == rwb->sync_cookie) {
 		rwb->sync_issue = 0;
 		rwb->sync_cookie = NULL;
 	}
@@ -701,7 +734,7 @@ static int wbt_data_dir(const struct request *rq)
 
 	if (op == REQ_OP_READ)
 		return READ;
-	else if (op == REQ_OP_WRITE || op == REQ_OP_FLUSH)
+	else if (op_is_write(op))
 		return WRITE;
 
 	/* don't account */
@@ -713,8 +746,6 @@ int wbt_init(struct request_queue *q)
 	struct rq_wb *rwb;
 	int i;
 
-	BUILD_BUG_ON(WBT_NR_BITS > BLK_STAT_RES_BITS);
-
 	rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
 	if (!rwb)
 		return -ENOMEM;
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index a232c98fbf4d..300df531d0a6 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -14,12 +14,16 @@ enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
 	WBT_READ		= 2,	/* read */
 	WBT_KSWAPD		= 4,	/* write, from kswapd */
+	WBT_DISCARD		= 8,	/* discard */
 
-	WBT_NR_BITS		= 3,	/* number of bits */
+	WBT_NR_BITS		= 4,	/* number of bits */
 };
 
 enum {
-	WBT_NUM_RWQ		= 2,
+	WBT_RWQ_BG		= 0,
+	WBT_RWQ_KSWAPD,
+	WBT_RWQ_DISCARD,
+	WBT_NUM_RWQ,
 };
 
 /*
@@ -31,31 +35,6 @@ enum {
 	WBT_STATE_ON_MANUAL	= 2,
 };
 
-static inline void wbt_clear_state(struct blk_issue_stat *stat)
-{
-	stat->stat &= ~BLK_STAT_RES_MASK;
-}
-
-static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat)
-{
-	return (stat->stat & BLK_STAT_RES_MASK) >> BLK_STAT_RES_SHIFT;
-}
-
-static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct)
-{
-	stat->stat |= ((u64) wb_acct) << BLK_STAT_RES_SHIFT;
-}
-
-static inline bool wbt_is_tracked(struct blk_issue_stat *stat)
-{
-	return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_TRACKED;
-}
-
-static inline bool wbt_is_read(struct blk_issue_stat *stat)
-{
-	return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_READ;
-}
-
 struct rq_wait {
 	wait_queue_head_t wait;
 	atomic_t inflight;
@@ -84,7 +63,7 @@ struct rq_wb {
 
 	struct blk_stat_callback *cb;
 
-	s64 sync_issue;
+	u64 sync_issue;
 	void *sync_cookie;
 
 	unsigned int wc;
@@ -109,14 +88,19 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 
 #ifdef CONFIG_BLK_WBT
 
+static inline void wbt_track(struct request *rq, enum wbt_flags flags)
+{
+	rq->wbt_flags |= flags;
+}
+
 void __wbt_done(struct rq_wb *, enum wbt_flags);
-void wbt_done(struct rq_wb *, struct blk_issue_stat *);
+void wbt_done(struct rq_wb *, struct request *);
 enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
 int wbt_init(struct request_queue *);
 void wbt_exit(struct request_queue *);
 void wbt_update_limits(struct rq_wb *);
-void wbt_requeue(struct rq_wb *, struct blk_issue_stat *);
-void wbt_issue(struct rq_wb *, struct blk_issue_stat *);
+void wbt_requeue(struct rq_wb *, struct request *);
+void wbt_issue(struct rq_wb *, struct request *);
 void wbt_disable_default(struct request_queue *);
 void wbt_enable_default(struct request_queue *);
 
@@ -127,10 +111,13 @@ u64 wbt_default_latency_nsec(struct request_queue *);
 
 #else
 
+static inline void wbt_track(struct request *rq, enum wbt_flags flags)
+{
+}
 static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
 {
 }
-static inline void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
+static inline void wbt_done(struct rq_wb *rwb, struct request *rq)
 {
 }
 static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
@@ -148,10 +135,10 @@ static inline void wbt_exit(struct request_queue *q)
 static inline void wbt_update_limits(struct rq_wb *rwb)
 {
 }
-static inline void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq)
 {
 }
-static inline void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+static inline void wbt_issue(struct rq_wb *rwb, struct request *rq)
 {
 }
 static inline void wbt_disable_default(struct request_queue *q)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 08e84ef2bc05..3d08dc84db16 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -328,7 +328,11 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!rep.nr_zones)
 		return -EINVAL;
 
-	zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL);
+	if (rep.nr_zones > INT_MAX / sizeof(struct blk_zone))
+		return -ERANGE;
+
+	zones = kvmalloc(rep.nr_zones * sizeof(struct blk_zone),
+			GFP_KERNEL | __GFP_ZERO);
 	if (!zones)
 		return -ENOMEM;
 
@@ -350,7 +354,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	}
 
  out:
-	kfree(zones);
+	kvfree(zones);
 
 	return ret;
 }
diff --git a/block/blk.h b/block/blk.h
index b034fd2460c4..8d23aea96ce9 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -186,7 +186,7 @@ unsigned int blk_plug_queued_count(struct request_queue *q);
 
 void blk_account_io_start(struct request *req, bool new_io);
 void blk_account_io_completion(struct request *req, unsigned int bytes);
-void blk_account_io_done(struct request *req);
+void blk_account_io_done(struct request *req, u64 now);
 
 /*
  * EH timer and IO completion will both attempt to 'grab' the request, make
@@ -231,6 +231,9 @@ static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq
 		e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
 }
 
+int elevator_init(struct request_queue *);
+int elevator_init_mq(struct request_queue *q);
+void elevator_exit(struct request_queue *, struct elevator_queue *);
 int elv_register_queue(struct request_queue *q);
 void elv_unregister_queue(struct request_queue *q);
 
diff --git a/block/bounce.c b/block/bounce.c
index dd0b93f2a871..fd31347b7836 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -28,28 +28,29 @@
 #define POOL_SIZE	64
 #define ISA_POOL_SIZE	16
 
-static struct bio_set *bounce_bio_set, *bounce_bio_split;
-static mempool_t *page_pool, *isa_page_pool;
+static struct bio_set bounce_bio_set, bounce_bio_split;
+static mempool_t page_pool, isa_page_pool;
 
 #if defined(CONFIG_HIGHMEM)
 static __init int init_emergency_pool(void)
 {
+	int ret;
 #if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG)
 	if (max_pfn <= max_low_pfn)
 		return 0;
 #endif
 
-	page_pool = mempool_create_page_pool(POOL_SIZE, 0);
-	BUG_ON(!page_pool);
+	ret = mempool_init_page_pool(&page_pool, POOL_SIZE, 0);
+	BUG_ON(ret);
 	pr_info("pool size: %d pages\n", POOL_SIZE);
 
-	bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-	BUG_ON(!bounce_bio_set);
-	if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE))
+	ret = bioset_init(&bounce_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	BUG_ON(ret);
+	if (bioset_integrity_create(&bounce_bio_set, BIO_POOL_SIZE))
 		BUG_ON(1);
 
-	bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
-	BUG_ON(!bounce_bio_split);
+	ret = bioset_init(&bounce_bio_split, BIO_POOL_SIZE, 0, 0);
+	BUG_ON(ret);
 
 	return 0;
 }
@@ -63,14 +64,11 @@ __initcall(init_emergency_pool);
  */
 static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
 {
-	unsigned long flags;
 	unsigned char *vto;
 
-	local_irq_save(flags);
 	vto = kmap_atomic(to->bv_page);
 	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
 	kunmap_atomic(vto);
-	local_irq_restore(flags);
 }
 
 #else /* CONFIG_HIGHMEM */
@@ -94,12 +92,14 @@ static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
  */
 int init_emergency_isa_pool(void)
 {
-	if (isa_page_pool)
+	int ret;
+
+	if (mempool_initialized(&isa_page_pool))
 		return 0;
 
-	isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
-				       mempool_free_pages, (void *) 0);
-	BUG_ON(!isa_page_pool);
+	ret = mempool_init(&isa_page_pool, ISA_POOL_SIZE, mempool_alloc_pages_isa,
+			   mempool_free_pages, (void *) 0);
+	BUG_ON(ret);
 
 	pr_info("isa pool size: %d pages\n", ISA_POOL_SIZE);
 	return 0;
@@ -166,13 +166,13 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
 
 static void bounce_end_io_write(struct bio *bio)
 {
-	bounce_end_io(bio, page_pool);
+	bounce_end_io(bio, &page_pool);
 }
 
 static void bounce_end_io_write_isa(struct bio *bio)
 {
 
-	bounce_end_io(bio, isa_page_pool);
+	bounce_end_io(bio, &isa_page_pool);
 }
 
 static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
@@ -187,12 +187,12 @@ static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
 
 static void bounce_end_io_read(struct bio *bio)
 {
-	__bounce_end_io_read(bio, page_pool);
+	__bounce_end_io_read(bio, &page_pool);
 }
 
 static void bounce_end_io_read_isa(struct bio *bio)
 {
-	__bounce_end_io_read(bio, isa_page_pool);
+	__bounce_end_io_read(bio, &isa_page_pool);
 }
 
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
@@ -217,13 +217,13 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 		return;
 
 	if (!passthrough && sectors < bio_sectors(*bio_orig)) {
-		bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
+		bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
 		bio_chain(bio, *bio_orig);
 		generic_make_request(*bio_orig);
 		*bio_orig = bio;
 	}
 	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
-			bounce_bio_set);
+			&bounce_bio_set);
 
 	bio_for_each_segment_all(to, bio, i) {
 		struct page *page = to->bv_page;
@@ -250,7 +250,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 
 	bio->bi_flags |= (1 << BIO_BOUNCED);
 
-	if (pool == page_pool) {
+	if (pool == &page_pool) {
 		bio->bi_end_io = bounce_end_io_write;
 		if (rw == READ)
 			bio->bi_end_io = bounce_end_io_read;
@@ -282,10 +282,10 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	if (!(q->bounce_gfp & GFP_DMA)) {
 		if (q->limits.bounce_pfn >= blk_max_pfn)
 			return;
-		pool = page_pool;
+		pool = &page_pool;
 	} else {
-		BUG_ON(!isa_page_pool);
-		pool = isa_page_pool;
+		BUG_ON(!mempool_initialized(&isa_page_pool));
+		pool = &isa_page_pool;
 	}
 
 	/*
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index fc2e5ff2c4b9..9419def8c017 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -303,11 +303,9 @@ static void bsg_exit_rq(struct request_queue *q, struct request *req)
  * @name: device to give bsg device
  * @job_fn: bsg job handler
  * @dd_job_size: size of LLD data needed for each job
- * @release: @dev release function
  */
 struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
-		bsg_job_fn *job_fn, int dd_job_size,
-		void (*release)(struct device *))
+		bsg_job_fn *job_fn, int dd_job_size)
 {
 	struct request_queue *q;
 	int ret;
@@ -331,7 +329,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	blk_queue_softirq_done(q, bsg_softirq_done);
 	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
 
-	ret = bsg_register_queue(q, dev, name, &bsg_transport_ops, release);
+	ret = bsg_register_queue(q, dev, name, &bsg_transport_ops);
 	if (ret) {
 		printk(KERN_ERR "%s: bsg interface failed to "
 		       "initialize - register queue\n", dev->kobj.name);
diff --git a/block/bsg.c b/block/bsg.c
index defa06c11858..132e657e2d91 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -226,8 +226,7 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode)
 		return ERR_PTR(ret);
 
 	rq = blk_get_request(q, hdr->dout_xfer_len ?
-			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
-			GFP_KERNEL);
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(rq))
 		return rq;
 
@@ -249,7 +248,7 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode)
 			goto out;
 		}
 
-		next_rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
+		next_rq = blk_get_request(q, REQ_OP_SCSI_IN, 0);
 		if (IS_ERR(next_rq)) {
 			ret = PTR_ERR(next_rq);
 			goto out;
@@ -650,18 +649,6 @@ static struct bsg_device *bsg_alloc_device(void)
 	return bd;
 }
 
-static void bsg_kref_release_function(struct kref *kref)
-{
-	struct bsg_class_device *bcd =
-		container_of(kref, struct bsg_class_device, ref);
-	struct device *parent = bcd->parent;
-
-	if (bcd->release)
-		bcd->release(bcd->parent);
-
-	put_device(parent);
-}
-
 static int bsg_put_device(struct bsg_device *bd)
 {
 	int ret = 0, do_free;
@@ -694,7 +681,6 @@ static int bsg_put_device(struct bsg_device *bd)
 
 	kfree(bd);
 out:
-	kref_put(&q->bsg_dev.ref, bsg_kref_release_function);
 	if (do_free)
 		blk_put_queue(q);
 	return ret;
@@ -760,8 +746,6 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
 	 */
 	mutex_lock(&bsg_mutex);
 	bcd = idr_find(&bsg_minor_idr, iminor(inode));
-	if (bcd)
-		kref_get(&bcd->ref);
 	mutex_unlock(&bsg_mutex);
 
 	if (!bcd)
@@ -772,8 +756,6 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
 		return bd;
 
 	bd = bsg_add_device(inode, bcd->queue, file);
-	if (IS_ERR(bd))
-		kref_put(&bcd->ref, bsg_kref_release_function);
 
 	return bd;
 }
@@ -913,25 +895,17 @@ void bsg_unregister_queue(struct request_queue *q)
 		sysfs_remove_link(&q->kobj, "bsg");
 	device_unregister(bcd->class_dev);
 	bcd->class_dev = NULL;
-	kref_put(&bcd->ref, bsg_kref_release_function);
 	mutex_unlock(&bsg_mutex);
 }
 EXPORT_SYMBOL_GPL(bsg_unregister_queue);
 
 int bsg_register_queue(struct request_queue *q, struct device *parent,
-		const char *name, const struct bsg_ops *ops,
-		void (*release)(struct device *))
+		const char *name, const struct bsg_ops *ops)
 {
 	struct bsg_class_device *bcd;
 	dev_t dev;
 	int ret;
 	struct device *class_dev = NULL;
-	const char *devname;
-
-	if (name)
-		devname = name;
-	else
-		devname = dev_name(parent);
 
 	/*
 	 * we need a proper transport to send commands, not a stacked device
@@ -955,15 +929,12 @@ int bsg_register_queue(struct request_queue *q, struct device *parent,
 
 	bcd->minor = ret;
 	bcd->queue = q;
-	bcd->parent = get_device(parent);
-	bcd->release = release;
 	bcd->ops = ops;
-	kref_init(&bcd->ref);
 	dev = MKDEV(bsg_major, bcd->minor);
-	class_dev = device_create(bsg_class, parent, dev, NULL, "%s", devname);
+	class_dev = device_create(bsg_class, parent, dev, NULL, "%s", name);
 	if (IS_ERR(class_dev)) {
 		ret = PTR_ERR(class_dev);
-		goto put_dev;
+		goto idr_remove;
 	}
 	bcd->class_dev = class_dev;
 
@@ -978,8 +949,7 @@ int bsg_register_queue(struct request_queue *q, struct device *parent,
 
 unregister_class_dev:
 	device_unregister(class_dev);
-put_dev:
-	put_device(parent);
+idr_remove:
 	idr_remove(&bsg_minor_idr, bcd->minor);
 unlock:
 	mutex_unlock(&bsg_mutex);
@@ -993,7 +963,7 @@ int bsg_scsi_register_queue(struct request_queue *q, struct device *parent)
 		return -EINVAL;
 	}
 
-	return bsg_register_queue(q, parent, NULL, &bsg_scsi_ops, NULL);
+	return bsg_register_queue(q, parent, dev_name(parent), &bsg_scsi_ops);
 }
 EXPORT_SYMBOL_GPL(bsg_scsi_register_queue);
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 9f342ef1ad42..82b6c27b3245 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -210,9 +210,9 @@ struct cfqg_stats {
 	/* total time with empty current active q with other requests queued */
 	struct blkg_stat		empty_time;
 	/* fields after this shouldn't be cleared on stat reset */
-	uint64_t			start_group_wait_time;
-	uint64_t			start_idle_time;
-	uint64_t			start_empty_time;
+	u64				start_group_wait_time;
+	u64				start_idle_time;
+	u64				start_empty_time;
 	uint16_t			flags;
 #endif	/* CONFIG_DEBUG_BLK_CGROUP */
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
@@ -491,13 +491,13 @@ CFQG_FLAG_FNS(empty)
 /* This should be called with the queue_lock held. */
 static void cfqg_stats_update_group_wait_time(struct cfqg_stats *stats)
 {
-	unsigned long long now;
+	u64 now;
 
 	if (!cfqg_stats_waiting(stats))
 		return;
 
-	now = sched_clock();
-	if (time_after64(now, stats->start_group_wait_time))
+	now = ktime_get_ns();
+	if (now > stats->start_group_wait_time)
 		blkg_stat_add(&stats->group_wait_time,
 			      now - stats->start_group_wait_time);
 	cfqg_stats_clear_waiting(stats);
@@ -513,20 +513,20 @@ static void cfqg_stats_set_start_group_wait_time(struct cfq_group *cfqg,
 		return;
 	if (cfqg == curr_cfqg)
 		return;
-	stats->start_group_wait_time = sched_clock();
+	stats->start_group_wait_time = ktime_get_ns();
 	cfqg_stats_mark_waiting(stats);
 }
 
 /* This should be called with the queue_lock held. */
 static void cfqg_stats_end_empty_time(struct cfqg_stats *stats)
 {
-	unsigned long long now;
+	u64 now;
 
 	if (!cfqg_stats_empty(stats))
 		return;
 
-	now = sched_clock();
-	if (time_after64(now, stats->start_empty_time))
+	now = ktime_get_ns();
+	if (now > stats->start_empty_time)
 		blkg_stat_add(&stats->empty_time,
 			      now - stats->start_empty_time);
 	cfqg_stats_clear_empty(stats);
@@ -552,7 +552,7 @@ static void cfqg_stats_set_start_empty_time(struct cfq_group *cfqg)
 	if (cfqg_stats_empty(stats))
 		return;
 
-	stats->start_empty_time = sched_clock();
+	stats->start_empty_time = ktime_get_ns();
 	cfqg_stats_mark_empty(stats);
 }
 
@@ -561,9 +561,9 @@ static void cfqg_stats_update_idle_time(struct cfq_group *cfqg)
 	struct cfqg_stats *stats = &cfqg->stats;
 
 	if (cfqg_stats_idling(stats)) {
-		unsigned long long now = sched_clock();
+		u64 now = ktime_get_ns();
 
-		if (time_after64(now, stats->start_idle_time))
+		if (now > stats->start_idle_time)
 			blkg_stat_add(&stats->idle_time,
 				      now - stats->start_idle_time);
 		cfqg_stats_clear_idling(stats);
@@ -576,7 +576,7 @@ static void cfqg_stats_set_start_idle_time(struct cfq_group *cfqg)
 
 	BUG_ON(cfqg_stats_idling(stats));
 
-	stats->start_idle_time = sched_clock();
+	stats->start_idle_time = ktime_get_ns();
 	cfqg_stats_mark_idling(stats);
 }
 
@@ -701,17 +701,19 @@ static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
 }
 
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time,
-			unsigned int op)
+						u64 start_time_ns,
+						u64 io_start_time_ns,
+						unsigned int op)
 {
 	struct cfqg_stats *stats = &cfqg->stats;
-	unsigned long long now = sched_clock();
+	u64 now = ktime_get_ns();
 
-	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, op, now - io_start_time);
-	if (time_after64(io_start_time, start_time))
+	if (now > io_start_time_ns)
+		blkg_rwstat_add(&stats->service_time, op,
+				now - io_start_time_ns);
+	if (io_start_time_ns > start_time_ns)
 		blkg_rwstat_add(&stats->wait_time, op,
-				io_start_time - start_time);
+				io_start_time_ns - start_time_ns);
 }
 
 /* @stats = 0 */
@@ -797,8 +799,9 @@ static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg,
 static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
 			unsigned int op) { }
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time,
-			unsigned int op) { }
+						u64 start_time_ns,
+						u64 io_start_time_ns,
+						unsigned int op) { }
 
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
 
@@ -4225,8 +4228,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	cfqd->rq_in_driver--;
 	cfqq->dispatched--;
 	(RQ_CFQG(rq))->dispatched--;
-	cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq),
-				     rq_io_start_time_ns(rq), rq->cmd_flags);
+	cfqg_stats_update_completion(cfqq->cfqg, rq->start_time_ns,
+				     rq->io_start_time_ns, rq->cmd_flags);
 
 	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
@@ -4242,16 +4245,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 					cfqq_type(cfqq));
 
 		st->ttime.last_end_request = now;
-		/*
-		 * We have to do this check in jiffies since start_time is in
-		 * jiffies and it is not trivial to convert to ns. If
-		 * cfq_fifo_expire[1] ever comes close to 1 jiffie, this test
-		 * will become problematic but so far we are fine (the default
-		 * is 128 ms).
-		 */
-		if (!time_after(rq->start_time +
-				  nsecs_to_jiffies(cfqd->cfq_fifo_expire[1]),
-				jiffies))
+		if (rq->start_time_ns + cfqd->cfq_fifo_expire[1] <= now)
 			cfqd->last_delayed_sync = now;
 	}
 
@@ -4792,7 +4786,7 @@ USEC_STORE_FUNCTION(cfq_target_latency_us_store, &cfqd->cfq_target_latency, 1, U
 #undef USEC_STORE_FUNCTION
 
 #define CFQ_ATTR(name) \
-	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)
+	__ATTR(name, 0644, cfq_##name##_show, cfq_##name##_store)
 
 static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(quantum),
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 9de9f156e203..ef2f1f09e9b3 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -512,8 +512,7 @@ STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
 #undef STORE_FUNCTION
 
 #define DD_ATTR(name) \
-	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
-				      deadline_##name##_store)
+	__ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store)
 
 static struct elv_fs_entry deadline_attrs[] = {
 	DD_ATTR(read_expire),
diff --git a/block/elevator.c b/block/elevator.c
index e87e9b43aba0..fa828b5bfd4b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -199,76 +199,46 @@ static void elevator_release(struct kobject *kobj)
 	kfree(e);
 }
 
-int elevator_init(struct request_queue *q, char *name)
+/*
+ * Use the default elevator specified by config boot param for non-mq devices,
+ * or by config option.  Don't try to load modules as we could be running off
+ * async and request_module() isn't allowed from async.
+ */
+int elevator_init(struct request_queue *q)
 {
 	struct elevator_type *e = NULL;
-	int err;
+	int err = 0;
 
 	/*
 	 * q->sysfs_lock must be held to provide mutual exclusion between
 	 * elevator_switch() and here.
 	 */
-	lockdep_assert_held(&q->sysfs_lock);
-
+	mutex_lock(&q->sysfs_lock);
 	if (unlikely(q->elevator))
-		return 0;
-
-	INIT_LIST_HEAD(&q->queue_head);
-	q->last_merge = NULL;
-	q->end_sector = 0;
-	q->boundary_rq = NULL;
-
-	if (name) {
-		e = elevator_get(q, name, true);
-		if (!e)
-			return -EINVAL;
-	}
+		goto out_unlock;
 
-	/*
-	 * Use the default elevator specified by config boot param for
-	 * non-mq devices, or by config option. Don't try to load modules
-	 * as we could be running off async and request_module() isn't
-	 * allowed from async.
-	 */
-	if (!e && !q->mq_ops && *chosen_elevator) {
+	if (*chosen_elevator) {
 		e = elevator_get(q, chosen_elevator, false);
 		if (!e)
 			printk(KERN_ERR "I/O scheduler %s not found\n",
 							chosen_elevator);
 	}
 
+	if (!e)
+		e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false);
 	if (!e) {
-		/*
-		 * For blk-mq devices, we default to using mq-deadline,
-		 * if available, for single queue devices. If deadline
-		 * isn't available OR we have multiple queues, default
-		 * to "none".
-		 */
-		if (q->mq_ops) {
-			if (q->nr_hw_queues == 1)
-				e = elevator_get(q, "mq-deadline", false);
-			if (!e)
-				return 0;
-		} else
-			e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false);
-
-		if (!e) {
-			printk(KERN_ERR
-				"Default I/O scheduler not found. " \
-				"Using noop.\n");
-			e = elevator_get(q, "noop", false);
-		}
+		printk(KERN_ERR
+			"Default I/O scheduler not found. Using noop.\n");
+		e = elevator_get(q, "noop", false);
 	}
 
-	if (e->uses_mq)
-		err = blk_mq_init_sched(q, e);
-	else
-		err = e->ops.sq.elevator_init_fn(q, e);
+	err = e->ops.sq.elevator_init_fn(q, e);
 	if (err)
 		elevator_put(e);
+out_unlock:
+	mutex_unlock(&q->sysfs_lock);
 	return err;
 }
-EXPORT_SYMBOL(elevator_init);
 
 void elevator_exit(struct request_queue *q, struct elevator_queue *e)
 {
@@ -281,7 +251,6 @@ void elevator_exit(struct request_queue *q, struct elevator_queue *e)
 
 	kobject_put(&e->kobj);
 }
-EXPORT_SYMBOL(elevator_exit);
 
 static inline void __elv_rqhash_del(struct request *rq)
 {
@@ -1005,6 +974,40 @@ out:
 }
 
 /*
+ * For blk-mq devices, we default to using mq-deadline, if available, for single
+ * queue devices.  If deadline isn't available OR we have multiple queues,
+ * default to "none".
+ */
+int elevator_init_mq(struct request_queue *q)
+{
+	struct elevator_type *e;
+	int err = 0;
+
+	if (q->nr_hw_queues != 1)
+		return 0;
+
+	/*
+	 * q->sysfs_lock must be held to provide mutual exclusion between
+	 * elevator_switch() and here.
+	 */
+	mutex_lock(&q->sysfs_lock);
+	if (unlikely(q->elevator))
+		goto out_unlock;
+
+	e = elevator_get(q, "mq-deadline", false);
+	if (!e)
+		goto out_unlock;
+
+	err = blk_mq_init_sched(q, e);
+	if (err)
+		elevator_put(e);
+out_unlock:
+	mutex_unlock(&q->sysfs_lock);
+	return err;
+}
+
+
+/*
  * switch to new_e io scheduler. be careful not to introduce deadlocks -
  * we don't free the old io scheduler, before we have allocated what we
  * need for the new one. this way we have a chance of going back to the old
diff --git a/block/genhd.c b/block/genhd.c
index dc7e089373b9..f1543a45e73b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -82,6 +82,18 @@ void part_in_flight(struct request_queue *q, struct hd_struct *part,
 	}
 }
 
+void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+		       unsigned int inflight[2])
+{
+	if (q->mq_ops) {
+		blk_mq_in_flight_rw(q, part, inflight);
+		return;
+	}
+
+	inflight[0] = atomic_read(&part->in_flight[0]);
+	inflight[1] = atomic_read(&part->in_flight[1]);
+}
+
 struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
 {
 	struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);
@@ -1015,18 +1027,6 @@ static const struct seq_operations partitions_op = {
 	.stop	= disk_seqf_stop,
 	.show	= show_partition
 };
-
-static int partitions_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &partitions_op);
-}
-
-static const struct file_operations proc_partitions_operations = {
-	.open		= partitions_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
 #endif
 
 
@@ -1127,28 +1127,25 @@ static ssize_t disk_discard_alignment_show(struct device *dev,
 	return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
 }
 
-static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
-static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
-static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
-static DEVICE_ATTR(hidden, S_IRUGO, disk_hidden_show, NULL);
-static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
-static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
-static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
-static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
-		   NULL);
-static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
-static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
-static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
-static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show,
-		disk_badblocks_store);
+static DEVICE_ATTR(range, 0444, disk_range_show, NULL);
+static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL);
+static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL);
+static DEVICE_ATTR(hidden, 0444, disk_hidden_show, NULL);
+static DEVICE_ATTR(ro, 0444, disk_ro_show, NULL);
+static DEVICE_ATTR(size, 0444, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, 0444, disk_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, 0444, disk_discard_alignment_show, NULL);
+static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL);
+static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
+static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
-	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
+	__ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
 #endif
 #ifdef CONFIG_FAIL_IO_TIMEOUT
 static struct device_attribute dev_attr_fail_timeout =
-	__ATTR(io-timeout-fail,  S_IRUGO|S_IWUSR, part_timeout_show,
-		part_timeout_store);
+	__ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store);
 #endif
 
 static struct attribute *disk_attrs[] = {
@@ -1365,22 +1362,10 @@ static const struct seq_operations diskstats_op = {
 	.show	= diskstats_show
 };
 
-static int diskstats_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &diskstats_op);
-}
-
-static const struct file_operations proc_diskstats_operations = {
-	.open		= diskstats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int __init proc_genhd_init(void)
 {
-	proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
-	proc_create("partitions", 0, NULL, &proc_partitions_operations);
+	proc_create_seq("diskstats", 0, NULL, &diskstats_op);
+	proc_create_seq("partitions", 0, NULL, &partitions_op);
 	return 0;
 }
 module_init(proc_genhd_init);
@@ -1912,9 +1897,9 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev,
 	return count;
 }
 
-static const DEVICE_ATTR(events, S_IRUGO, disk_events_show, NULL);
-static const DEVICE_ATTR(events_async, S_IRUGO, disk_events_async_show, NULL);
-static const DEVICE_ATTR(events_poll_msecs, S_IRUGO|S_IWUSR,
+static const DEVICE_ATTR(events, 0444, disk_events_show, NULL);
+static const DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL);
+static const DEVICE_ATTR(events_poll_msecs, 0644,
 			 disk_events_poll_msecs_show,
 			 disk_events_poll_msecs_store);
 
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 0d6d25e32e1f..a1660bafc912 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -72,6 +72,19 @@ static const unsigned int kyber_batch_size[] = {
 	[KYBER_OTHER] = 8,
 };
 
+/*
+ * There is a same mapping between ctx & hctx and kcq & khd,
+ * we use request->mq_ctx->index_hw to index the kcq in khd.
+ */
+struct kyber_ctx_queue {
+	/*
+	 * Used to ensure operations on rq_list and kcq_map to be an atmoic one.
+	 * Also protect the rqs on rq_list when merge.
+	 */
+	spinlock_t lock;
+	struct list_head rq_list[KYBER_NUM_DOMAINS];
+} ____cacheline_aligned_in_smp;
+
 struct kyber_queue_data {
 	struct request_queue *q;
 
@@ -99,6 +112,8 @@ struct kyber_hctx_data {
 	struct list_head rqs[KYBER_NUM_DOMAINS];
 	unsigned int cur_domain;
 	unsigned int batching;
+	struct kyber_ctx_queue *kcqs;
+	struct sbitmap kcq_map[KYBER_NUM_DOMAINS];
 	wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS];
 	struct sbq_wait_state *domain_ws[KYBER_NUM_DOMAINS];
 	atomic_t wait_index[KYBER_NUM_DOMAINS];
@@ -107,10 +122,8 @@ struct kyber_hctx_data {
 static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
 			     void *key);
 
-static int rq_sched_domain(const struct request *rq)
+static unsigned int kyber_sched_domain(unsigned int op)
 {
-	unsigned int op = rq->cmd_flags;
-
 	if ((op & REQ_OP_MASK) == REQ_OP_READ)
 		return KYBER_READ;
 	else if ((op & REQ_OP_MASK) == REQ_OP_WRITE && op_is_sync(op))
@@ -284,6 +297,11 @@ static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd)
 	return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift;
 }
 
+static int kyber_bucket_fn(const struct request *rq)
+{
+	return kyber_sched_domain(rq->cmd_flags);
+}
+
 static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
 {
 	struct kyber_queue_data *kqd;
@@ -297,7 +315,7 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
 		goto err;
 	kqd->q = q;
 
-	kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, rq_sched_domain,
+	kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, kyber_bucket_fn,
 					  KYBER_NUM_DOMAINS, kqd);
 	if (!kqd->cb)
 		goto err_kqd;
@@ -376,8 +394,18 @@ static void kyber_exit_sched(struct elevator_queue *e)
 	kfree(kqd);
 }
 
+static void kyber_ctx_queue_init(struct kyber_ctx_queue *kcq)
+{
+	unsigned int i;
+
+	spin_lock_init(&kcq->lock);
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+		INIT_LIST_HEAD(&kcq->rq_list[i]);
+}
+
 static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 {
+	struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
 	struct kyber_hctx_data *khd;
 	int i;
 
@@ -385,6 +413,24 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 	if (!khd)
 		return -ENOMEM;
 
+	khd->kcqs = kmalloc_array_node(hctx->nr_ctx,
+				       sizeof(struct kyber_ctx_queue),
+				       GFP_KERNEL, hctx->numa_node);
+	if (!khd->kcqs)
+		goto err_khd;
+
+	for (i = 0; i < hctx->nr_ctx; i++)
+		kyber_ctx_queue_init(&khd->kcqs[i]);
+
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		if (sbitmap_init_node(&khd->kcq_map[i], hctx->nr_ctx,
+				      ilog2(8), GFP_KERNEL, hctx->numa_node)) {
+			while (--i >= 0)
+				sbitmap_free(&khd->kcq_map[i]);
+			goto err_kcqs;
+		}
+	}
+
 	spin_lock_init(&khd->lock);
 
 	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
@@ -400,12 +446,26 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 	khd->batching = 0;
 
 	hctx->sched_data = khd;
+	sbitmap_queue_min_shallow_depth(&hctx->sched_tags->bitmap_tags,
+					kqd->async_depth);
 
 	return 0;
+
+err_kcqs:
+	kfree(khd->kcqs);
+err_khd:
+	kfree(khd);
+	return -ENOMEM;
 }
 
 static void kyber_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 {
+	struct kyber_hctx_data *khd = hctx->sched_data;
+	int i;
+
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+		sbitmap_free(&khd->kcq_map[i]);
+	kfree(khd->kcqs);
 	kfree(hctx->sched_data);
 }
 
@@ -427,7 +487,7 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd,
 
 	nr = rq_get_domain_token(rq);
 	if (nr != -1) {
-		sched_domain = rq_sched_domain(rq);
+		sched_domain = kyber_sched_domain(rq->cmd_flags);
 		sbitmap_queue_clear(&kqd->domain_tokens[sched_domain], nr,
 				    rq->mq_ctx->cpu);
 	}
@@ -446,11 +506,51 @@ static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
 	}
 }
 
+static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+	struct kyber_hctx_data *khd = hctx->sched_data;
+	struct blk_mq_ctx *ctx = blk_mq_get_ctx(hctx->queue);
+	struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw];
+	unsigned int sched_domain = kyber_sched_domain(bio->bi_opf);
+	struct list_head *rq_list = &kcq->rq_list[sched_domain];
+	bool merged;
+
+	spin_lock(&kcq->lock);
+	merged = blk_mq_bio_list_merge(hctx->queue, rq_list, bio);
+	spin_unlock(&kcq->lock);
+	blk_mq_put_ctx(ctx);
+
+	return merged;
+}
+
 static void kyber_prepare_request(struct request *rq, struct bio *bio)
 {
 	rq_set_domain_token(rq, -1);
 }
 
+static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx,
+				  struct list_head *rq_list, bool at_head)
+{
+	struct kyber_hctx_data *khd = hctx->sched_data;
+	struct request *rq, *next;
+
+	list_for_each_entry_safe(rq, next, rq_list, queuelist) {
+		unsigned int sched_domain = kyber_sched_domain(rq->cmd_flags);
+		struct kyber_ctx_queue *kcq = &khd->kcqs[rq->mq_ctx->index_hw];
+		struct list_head *head = &kcq->rq_list[sched_domain];
+
+		spin_lock(&kcq->lock);
+		if (at_head)
+			list_move(&rq->queuelist, head);
+		else
+			list_move_tail(&rq->queuelist, head);
+		sbitmap_set_bit(&khd->kcq_map[sched_domain],
+				rq->mq_ctx->index_hw);
+		blk_mq_sched_request_inserted(rq);
+		spin_unlock(&kcq->lock);
+	}
+}
+
 static void kyber_finish_request(struct request *rq)
 {
 	struct kyber_queue_data *kqd = rq->q->elevator->elevator_data;
@@ -469,7 +569,7 @@ static void kyber_completed_request(struct request *rq)
 	 * Check if this request met our latency goal. If not, quickly gather
 	 * some statistics and start throttling.
 	 */
-	sched_domain = rq_sched_domain(rq);
+	sched_domain = kyber_sched_domain(rq->cmd_flags);
 	switch (sched_domain) {
 	case KYBER_READ:
 		target = kqd->read_lat_nsec;
@@ -485,29 +585,48 @@ static void kyber_completed_request(struct request *rq)
 	if (blk_stat_is_active(kqd->cb))
 		return;
 
-	now = __blk_stat_time(ktime_to_ns(ktime_get()));
-	if (now < blk_stat_time(&rq->issue_stat))
+	now = ktime_get_ns();
+	if (now < rq->io_start_time_ns)
 		return;
 
-	latency = now - blk_stat_time(&rq->issue_stat);
+	latency = now - rq->io_start_time_ns;
 
 	if (latency > target)
 		blk_stat_activate_msecs(kqd->cb, 10);
 }
 
-static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd,
-				  struct blk_mq_hw_ctx *hctx)
+struct flush_kcq_data {
+	struct kyber_hctx_data *khd;
+	unsigned int sched_domain;
+	struct list_head *list;
+};
+
+static bool flush_busy_kcq(struct sbitmap *sb, unsigned int bitnr, void *data)
 {
-	LIST_HEAD(rq_list);
-	struct request *rq, *next;
+	struct flush_kcq_data *flush_data = data;
+	struct kyber_ctx_queue *kcq = &flush_data->khd->kcqs[bitnr];
 
-	blk_mq_flush_busy_ctxs(hctx, &rq_list);
-	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
-		unsigned int sched_domain;
+	spin_lock(&kcq->lock);
+	list_splice_tail_init(&kcq->rq_list[flush_data->sched_domain],
+			      flush_data->list);
+	sbitmap_clear_bit(sb, bitnr);
+	spin_unlock(&kcq->lock);
 
-		sched_domain = rq_sched_domain(rq);
-		list_move_tail(&rq->queuelist, &khd->rqs[sched_domain]);
-	}
+	return true;
+}
+
+static void kyber_flush_busy_kcqs(struct kyber_hctx_data *khd,
+				  unsigned int sched_domain,
+				  struct list_head *list)
+{
+	struct flush_kcq_data data = {
+		.khd = khd,
+		.sched_domain = sched_domain,
+		.list = list,
+	};
+
+	sbitmap_for_each_set(&khd->kcq_map[sched_domain],
+			     flush_busy_kcq, &data);
 }
 
 static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
@@ -570,26 +689,23 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd,
 static struct request *
 kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
 			  struct kyber_hctx_data *khd,
-			  struct blk_mq_hw_ctx *hctx,
-			  bool *flushed)
+			  struct blk_mq_hw_ctx *hctx)
 {
 	struct list_head *rqs;
 	struct request *rq;
 	int nr;
 
 	rqs = &khd->rqs[khd->cur_domain];
-	rq = list_first_entry_or_null(rqs, struct request, queuelist);
 
 	/*
-	 * If there wasn't already a pending request and we haven't flushed the
-	 * software queues yet, flush the software queues and check again.
+	 * If we already have a flushed request, then we just need to get a
+	 * token for it. Otherwise, if there are pending requests in the kcqs,
+	 * flush the kcqs, but only if we can get a token. If not, we should
+	 * leave the requests in the kcqs so that they can be merged. Note that
+	 * khd->lock serializes the flushes, so if we observed any bit set in
+	 * the kcq_map, we will always get a request.
 	 */
-	if (!rq && !*flushed) {
-		kyber_flush_busy_ctxs(khd, hctx);
-		*flushed = true;
-		rq = list_first_entry_or_null(rqs, struct request, queuelist);
-	}
-
+	rq = list_first_entry_or_null(rqs, struct request, queuelist);
 	if (rq) {
 		nr = kyber_get_domain_token(kqd, khd, hctx);
 		if (nr >= 0) {
@@ -598,6 +714,16 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
 			list_del_init(&rq->queuelist);
 			return rq;
 		}
+	} else if (sbitmap_any_bit_set(&khd->kcq_map[khd->cur_domain])) {
+		nr = kyber_get_domain_token(kqd, khd, hctx);
+		if (nr >= 0) {
+			kyber_flush_busy_kcqs(khd, khd->cur_domain, rqs);
+			rq = list_first_entry(rqs, struct request, queuelist);
+			khd->batching++;
+			rq_set_domain_token(rq, nr);
+			list_del_init(&rq->queuelist);
+			return rq;
+		}
 	}
 
 	/* There were either no pending requests or no tokens. */
@@ -608,7 +734,6 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
 	struct kyber_hctx_data *khd = hctx->sched_data;
-	bool flushed = false;
 	struct request *rq;
 	int i;
 
@@ -619,7 +744,7 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	 * from the batch.
 	 */
 	if (khd->batching < kyber_batch_size[khd->cur_domain]) {
-		rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+		rq = kyber_dispatch_cur_domain(kqd, khd, hctx);
 		if (rq)
 			goto out;
 	}
@@ -640,7 +765,7 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
 		else
 			khd->cur_domain++;
 
-		rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+		rq = kyber_dispatch_cur_domain(kqd, khd, hctx);
 		if (rq)
 			goto out;
 	}
@@ -657,10 +782,12 @@ static bool kyber_has_work(struct blk_mq_hw_ctx *hctx)
 	int i;
 
 	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
-		if (!list_empty_careful(&khd->rqs[i]))
+		if (!list_empty_careful(&khd->rqs[i]) ||
+		    sbitmap_any_bit_set(&khd->kcq_map[i]))
 			return true;
 	}
-	return sbitmap_any_bit_set(&hctx->ctx_map);
+
+	return false;
 }
 
 #define KYBER_LAT_SHOW_STORE(op)					\
@@ -831,7 +958,9 @@ static struct elevator_type kyber_sched = {
 		.init_hctx = kyber_init_hctx,
 		.exit_hctx = kyber_exit_hctx,
 		.limit_depth = kyber_limit_depth,
+		.bio_merge = kyber_bio_merge,
 		.prepare_request = kyber_prepare_request,
+		.insert_requests = kyber_insert_requests,
 		.finish_request = kyber_finish_request,
 		.requeue_request = kyber_finish_request,
 		.completed_request = kyber_completed_request,
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 8ec0ba9f5386..099a9e05854c 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -630,8 +630,7 @@ STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
 #undef STORE_FUNCTION
 
 #define DD_ATTR(name) \
-	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
-				      deadline_##name##_store)
+	__ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store)
 
 static struct elv_fs_entry deadline_attrs[] = {
 	DD_ATTR(read_expire),
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 08dabcd8b6ae..3dcfd4ec0e11 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -145,13 +145,15 @@ ssize_t part_stat_show(struct device *dev,
 		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
 }
 
-ssize_t part_inflight_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
+	struct request_queue *q = part_to_disk(p)->queue;
+	unsigned int inflight[2];
 
-	return sprintf(buf, "%8u %8u\n", atomic_read(&p->in_flight[0]),
-		atomic_read(&p->in_flight[1]));
+	part_in_flight_rw(q, p, inflight);
+	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
 }
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -177,18 +179,17 @@ ssize_t part_fail_store(struct device *dev,
 }
 #endif
 
-static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
-static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
-static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
-static DEVICE_ATTR(ro, S_IRUGO, part_ro_show, NULL);
-static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
-static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
-		   NULL);
-static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
-static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
+static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
+static DEVICE_ATTR(start, 0444, part_start_show, NULL);
+static DEVICE_ATTR(size, 0444, part_size_show, NULL);
+static DEVICE_ATTR(ro, 0444, part_ro_show, NULL);
+static DEVICE_ATTR(alignment_offset, 0444, part_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, 0444, part_discard_alignment_show, NULL);
+static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
-	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
+	__ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
 #endif
 
 static struct attribute *part_attrs[] = {
@@ -289,8 +290,7 @@ static ssize_t whole_disk_show(struct device *dev,
 {
 	return 0;
 }
-static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH,
-		   whole_disk_show, NULL);
+static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL);
 
 /*
  * Must be called either with bd_mutex held, before a disk can be opened or
@@ -516,7 +516,7 @@ rescan:
 
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
-	check_disk_size_change(disk, bdev);
+	check_disk_size_change(disk, bdev, true);
 	bdev->bd_invalidated = 0;
 	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
 		return 0;
@@ -641,7 +641,7 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
 		return res;
 
 	set_capacity(disk, 0);
-	check_disk_size_change(disk, bdev);
+	check_disk_size_change(disk, bdev, false);
 	bdev->bd_invalidated = 0;
 	/* tell userspace that the media / partition table may have changed */
 	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 60b471f8621b..533f4aee8567 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -321,8 +321,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		at_head = 1;
 
 	ret = -ENOMEM;
-	rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
-			GFP_KERNEL);
+	rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 	req = scsi_req(rq);
@@ -449,8 +448,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	}
 
-	rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
-			__GFP_RECLAIM);
+	rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto error_free_buffer;
@@ -501,7 +499,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		break;
 	}
 
-	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_RECLAIM)) {
+	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, GFP_NOIO)) {
 		err = DRIVER_ERROR << 24;
 		goto error;
 	}
@@ -538,7 +536,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	struct request *rq;
 	int err;
 
-	rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM);
+	rq = blk_get_request(q, REQ_OP_SCSI_OUT, 0);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 76e8c88c97b4..f3e40ac56d93 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -289,6 +289,107 @@ config CRYPTO_CHACHA20POLY1305
 	  with the Poly1305 authenticator. It is defined in RFC7539 for use in
 	  IETF protocols.
 
+config CRYPTO_AEGIS128
+	tristate "AEGIS-128 AEAD algorithm"
+	select CRYPTO_AEAD
+	select CRYPTO_AES  # for AES S-box tables
+	help
+	 Support for the AEGIS-128 dedicated AEAD algorithm.
+
+config CRYPTO_AEGIS128L
+	tristate "AEGIS-128L AEAD algorithm"
+	select CRYPTO_AEAD
+	select CRYPTO_AES  # for AES S-box tables
+	help
+	 Support for the AEGIS-128L dedicated AEAD algorithm.
+
+config CRYPTO_AEGIS256
+	tristate "AEGIS-256 AEAD algorithm"
+	select CRYPTO_AEAD
+	select CRYPTO_AES  # for AES S-box tables
+	help
+	 Support for the AEGIS-256 dedicated AEAD algorithm.
+
+config CRYPTO_AEGIS128_AESNI_SSE2
+	tristate "AEGIS-128 AEAD algorithm (x86_64 AESNI+SSE2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_AEAD
+	select CRYPTO_CRYPTD
+	help
+	 AESNI+SSE2 implementation of the AEGSI-128 dedicated AEAD algorithm.
+
+config CRYPTO_AEGIS128L_AESNI_SSE2
+	tristate "AEGIS-128L AEAD algorithm (x86_64 AESNI+SSE2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_AEAD
+	select CRYPTO_CRYPTD
+	help
+	 AESNI+SSE2 implementation of the AEGSI-128L dedicated AEAD algorithm.
+
+config CRYPTO_AEGIS256_AESNI_SSE2
+	tristate "AEGIS-256 AEAD algorithm (x86_64 AESNI+SSE2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_AEAD
+	select CRYPTO_CRYPTD
+	help
+	 AESNI+SSE2 implementation of the AEGSI-256 dedicated AEAD algorithm.
+
+config CRYPTO_MORUS640
+	tristate "MORUS-640 AEAD algorithm"
+	select CRYPTO_AEAD
+	help
+	  Support for the MORUS-640 dedicated AEAD algorithm.
+
+config CRYPTO_MORUS640_GLUE
+	tristate
+	depends on X86
+	select CRYPTO_AEAD
+	select CRYPTO_CRYPTD
+	help
+	  Common glue for SIMD optimizations of the MORUS-640 dedicated AEAD
+	  algorithm.
+
+config CRYPTO_MORUS640_SSE2
+	tristate "MORUS-640 AEAD algorithm (x86_64 SSE2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_AEAD
+	select CRYPTO_MORUS640_GLUE
+	help
+	  SSE2 implementation of the MORUS-640 dedicated AEAD algorithm.
+
+config CRYPTO_MORUS1280
+	tristate "MORUS-1280 AEAD algorithm"
+	select CRYPTO_AEAD
+	help
+	  Support for the MORUS-1280 dedicated AEAD algorithm.
+
+config CRYPTO_MORUS1280_GLUE
+	tristate
+	depends on X86
+	select CRYPTO_AEAD
+	select CRYPTO_CRYPTD
+	help
+	  Common glue for SIMD optimizations of the MORUS-1280 dedicated AEAD
+	  algorithm.
+
+config CRYPTO_MORUS1280_SSE2
+	tristate "MORUS-1280 AEAD algorithm (x86_64 SSE2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_AEAD
+	select CRYPTO_MORUS1280_GLUE
+	help
+	  SSE2 optimizedimplementation of the MORUS-1280 dedicated AEAD
+	  algorithm.
+
+config CRYPTO_MORUS1280_AVX2
+	tristate "MORUS-1280 AEAD algorithm (x86_64 AVX2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_AEAD
+	select CRYPTO_MORUS1280_GLUE
+	help
+	  AVX2 optimized implementation of the MORUS-1280 dedicated AEAD
+	  algorithm.
+
 config CRYPTO_SEQIV
 	tristate "Sequence Number IV Generator"
 	select CRYPTO_AEAD
@@ -1335,34 +1436,6 @@ config CRYPTO_SALSA20
 	  The Salsa20 stream cipher algorithm is designed by Daniel J.
 	  Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
 
-config CRYPTO_SALSA20_586
-	tristate "Salsa20 stream cipher algorithm (i586)"
-	depends on (X86 || UML_X86) && !64BIT
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_SALSA20
-	help
-	  Salsa20 stream cipher algorithm.
-
-	  Salsa20 is a stream cipher submitted to eSTREAM, the ECRYPT
-	  Stream Cipher Project. See <http://www.ecrypt.eu.org/stream/>
-
-	  The Salsa20 stream cipher algorithm is designed by Daniel J.
-	  Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
-
-config CRYPTO_SALSA20_X86_64
-	tristate "Salsa20 stream cipher algorithm (x86_64)"
-	depends on (X86 || UML_X86) && 64BIT
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_SALSA20
-	help
-	  Salsa20 stream cipher algorithm.
-
-	  Salsa20 is a stream cipher submitted to eSTREAM, the ECRYPT
-	  Stream Cipher Project. See <http://www.ecrypt.eu.org/stream/>
-
-	  The Salsa20 stream cipher algorithm is designed by Daniel J.
-	  Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
-
 config CRYPTO_CHACHA20
 	tristate "ChaCha20 cipher algorithm"
 	select CRYPTO_BLKCIPHER
@@ -1695,6 +1768,15 @@ config CRYPTO_LZ4HC
 	help
 	  This is the LZ4 high compression mode algorithm.
 
+config CRYPTO_ZSTD
+	tristate "Zstd compression algorithm"
+	select CRYPTO_ALGAPI
+	select CRYPTO_ACOMP2
+	select ZSTD_COMPRESS
+	select ZSTD_DECOMPRESS
+	help
+	  This is the zstd algorithm.
+
 comment "Random Number Generation"
 
 config CRYPTO_ANSI_CPRNG
diff --git a/crypto/Makefile b/crypto/Makefile
index 3a5f01616f74..6d1d40eeb964 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -86,6 +86,11 @@ obj-$(CONFIG_CRYPTO_KEYWRAP) += keywrap.o
 obj-$(CONFIG_CRYPTO_GCM) += gcm.o
 obj-$(CONFIG_CRYPTO_CCM) += ccm.o
 obj-$(CONFIG_CRYPTO_CHACHA20POLY1305) += chacha20poly1305.o
+obj-$(CONFIG_CRYPTO_AEGIS128) += aegis128.o
+obj-$(CONFIG_CRYPTO_AEGIS128L) += aegis128l.o
+obj-$(CONFIG_CRYPTO_AEGIS256) += aegis256.o
+obj-$(CONFIG_CRYPTO_MORUS640) += morus640.o
+obj-$(CONFIG_CRYPTO_MORUS1280) += morus1280.o
 obj-$(CONFIG_CRYPTO_PCRYPT) += pcrypt.o
 obj-$(CONFIG_CRYPTO_CRYPTD) += cryptd.o
 obj-$(CONFIG_CRYPTO_MCRYPTD) += mcryptd.o
@@ -137,6 +142,7 @@ obj-$(CONFIG_CRYPTO_USER_API_HASH) += algif_hash.o
 obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o
 obj-$(CONFIG_CRYPTO_USER_API_RNG) += algif_rng.o
 obj-$(CONFIG_CRYPTO_USER_API_AEAD) += algif_aead.o
+obj-$(CONFIG_CRYPTO_ZSTD) += zstd.o
 
 ecdh_generic-y := ecc.o
 ecdh_generic-y += ecdh.o
diff --git a/crypto/aegis.h b/crypto/aegis.h
new file mode 100644
index 000000000000..f1c6900ddb80
--- /dev/null
+++ b/crypto/aegis.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AEGIS common definitions
+ *
+ * Copyright (c) 2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (c) 2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#ifndef _CRYPTO_AEGIS_H
+#define _CRYPTO_AEGIS_H
+
+#include <crypto/aes.h>
+#include <linux/types.h>
+
+#define AEGIS_BLOCK_SIZE 16
+
+union aegis_block {
+	__le64 words64[AEGIS_BLOCK_SIZE / sizeof(__le64)];
+	u32 words32[AEGIS_BLOCK_SIZE / sizeof(u32)];
+	u8 bytes[AEGIS_BLOCK_SIZE];
+};
+
+#define AEGIS_BLOCK_ALIGN (__alignof__(union aegis_block))
+#define AEGIS_ALIGNED(p) IS_ALIGNED((uintptr_t)p, AEGIS_BLOCK_ALIGN)
+
+static const union aegis_block crypto_aegis_const[2] = {
+	{ .words64 = {
+		cpu_to_le64(U64_C(0x0d08050302010100)),
+		cpu_to_le64(U64_C(0x6279e99059372215)),
+	} },
+	{ .words64 = {
+		cpu_to_le64(U64_C(0xf12fc26d55183ddb)),
+		cpu_to_le64(U64_C(0xdd28b57342311120)),
+	} },
+};
+
+static void crypto_aegis_block_xor(union aegis_block *dst,
+				   const union aegis_block *src)
+{
+	dst->words64[0] ^= src->words64[0];
+	dst->words64[1] ^= src->words64[1];
+}
+
+static void crypto_aegis_block_and(union aegis_block *dst,
+				   const union aegis_block *src)
+{
+	dst->words64[0] &= src->words64[0];
+	dst->words64[1] &= src->words64[1];
+}
+
+static void crypto_aegis_aesenc(union aegis_block *dst,
+				const union aegis_block *src,
+				const union aegis_block *key)
+{
+	u32 *d = dst->words32;
+	const u8  *s  = src->bytes;
+	const u32 *k  = key->words32;
+	const u32 *t0 = crypto_ft_tab[0];
+	const u32 *t1 = crypto_ft_tab[1];
+	const u32 *t2 = crypto_ft_tab[2];
+	const u32 *t3 = crypto_ft_tab[3];
+	u32 d0, d1, d2, d3;
+
+	d0 = t0[s[ 0]] ^ t1[s[ 5]] ^ t2[s[10]] ^ t3[s[15]] ^ k[0];
+	d1 = t0[s[ 4]] ^ t1[s[ 9]] ^ t2[s[14]] ^ t3[s[ 3]] ^ k[1];
+	d2 = t0[s[ 8]] ^ t1[s[13]] ^ t2[s[ 2]] ^ t3[s[ 7]] ^ k[2];
+	d3 = t0[s[12]] ^ t1[s[ 1]] ^ t2[s[ 6]] ^ t3[s[11]] ^ k[3];
+
+	d[0] = d0;
+	d[1] = d1;
+	d[2] = d2;
+	d[3] = d3;
+}
+
+#endif /* _CRYPTO_AEGIS_H */
diff --git a/crypto/aegis128.c b/crypto/aegis128.c
new file mode 100644
index 000000000000..38271303ce16
--- /dev/null
+++ b/crypto/aegis128.c
@@ -0,0 +1,463 @@
+/*
+ * The AEGIS-128 Authenticated-Encryption Algorithm
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+
+#include "aegis.h"
+
+#define AEGIS128_NONCE_SIZE 16
+#define AEGIS128_STATE_BLOCKS 5
+#define AEGIS128_KEY_SIZE 16
+#define AEGIS128_MIN_AUTH_SIZE 8
+#define AEGIS128_MAX_AUTH_SIZE 16
+
+struct aegis_state {
+	union aegis_block blocks[AEGIS128_STATE_BLOCKS];
+};
+
+struct aegis_ctx {
+	union aegis_block key;
+};
+
+struct aegis128_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_chunk)(struct aegis_state *state, u8 *dst,
+			    const u8 *src, unsigned int size);
+};
+
+static void crypto_aegis128_update(struct aegis_state *state)
+{
+	union aegis_block tmp;
+	unsigned int i;
+
+	tmp = state->blocks[AEGIS128_STATE_BLOCKS - 1];
+	for (i = AEGIS128_STATE_BLOCKS - 1; i > 0; i--)
+		crypto_aegis_aesenc(&state->blocks[i], &state->blocks[i - 1],
+				    &state->blocks[i]);
+	crypto_aegis_aesenc(&state->blocks[0], &tmp, &state->blocks[0]);
+}
+
+static void crypto_aegis128_update_a(struct aegis_state *state,
+				     const union aegis_block *msg)
+{
+	crypto_aegis128_update(state);
+	crypto_aegis_block_xor(&state->blocks[0], msg);
+}
+
+static void crypto_aegis128_update_u(struct aegis_state *state, const void *msg)
+{
+	crypto_aegis128_update(state);
+	crypto_xor(state->blocks[0].bytes, msg, AEGIS_BLOCK_SIZE);
+}
+
+static void crypto_aegis128_init(struct aegis_state *state,
+				 const union aegis_block *key,
+				 const u8 *iv)
+{
+	union aegis_block key_iv;
+	unsigned int i;
+
+	key_iv = *key;
+	crypto_xor(key_iv.bytes, iv, AEGIS_BLOCK_SIZE);
+
+	state->blocks[0] = key_iv;
+	state->blocks[1] = crypto_aegis_const[1];
+	state->blocks[2] = crypto_aegis_const[0];
+	state->blocks[3] = *key;
+	state->blocks[4] = *key;
+
+	crypto_aegis_block_xor(&state->blocks[3], &crypto_aegis_const[0]);
+	crypto_aegis_block_xor(&state->blocks[4], &crypto_aegis_const[1]);
+
+	for (i = 0; i < 5; i++) {
+		crypto_aegis128_update_a(state, key);
+		crypto_aegis128_update_a(state, &key_iv);
+	}
+}
+
+static void crypto_aegis128_ad(struct aegis_state *state,
+			       const u8 *src, unsigned int size)
+{
+	if (AEGIS_ALIGNED(src)) {
+		const union aegis_block *src_blk =
+				(const union aegis_block *)src;
+
+		while (size >= AEGIS_BLOCK_SIZE) {
+			crypto_aegis128_update_a(state, src_blk);
+
+			size -= AEGIS_BLOCK_SIZE;
+			src_blk++;
+		}
+	} else {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			crypto_aegis128_update_u(state, src);
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+		}
+	}
+}
+
+static void crypto_aegis128_encrypt_chunk(struct aegis_state *state, u8 *dst,
+					  const u8 *src, unsigned int size)
+{
+	union aegis_block tmp;
+
+	if (AEGIS_ALIGNED(src) && AEGIS_ALIGNED(dst)) {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			union aegis_block *dst_blk =
+					(union aegis_block *)dst;
+			const union aegis_block *src_blk =
+					(const union aegis_block *)src;
+
+			tmp = state->blocks[2];
+			crypto_aegis_block_and(&tmp, &state->blocks[3]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+			crypto_aegis_block_xor(&tmp, src_blk);
+
+			crypto_aegis128_update_a(state, src_blk);
+
+			*dst_blk = tmp;
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+			dst += AEGIS_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			tmp = state->blocks[2];
+			crypto_aegis_block_and(&tmp, &state->blocks[3]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+			crypto_xor(tmp.bytes, src, AEGIS_BLOCK_SIZE);
+
+			crypto_aegis128_update_u(state, src);
+
+			memcpy(dst, tmp.bytes, AEGIS_BLOCK_SIZE);
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+			dst += AEGIS_BLOCK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union aegis_block msg = {};
+		memcpy(msg.bytes, src, size);
+
+		tmp = state->blocks[2];
+		crypto_aegis_block_and(&tmp, &state->blocks[3]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+
+		crypto_aegis128_update_a(state, &msg);
+
+		crypto_aegis_block_xor(&msg, &tmp);
+
+		memcpy(dst, msg.bytes, size);
+	}
+}
+
+static void crypto_aegis128_decrypt_chunk(struct aegis_state *state, u8 *dst,
+					  const u8 *src, unsigned int size)
+{
+	union aegis_block tmp;
+
+	if (AEGIS_ALIGNED(src) && AEGIS_ALIGNED(dst)) {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			union aegis_block *dst_blk =
+					(union aegis_block *)dst;
+			const union aegis_block *src_blk =
+					(const union aegis_block *)src;
+
+			tmp = state->blocks[2];
+			crypto_aegis_block_and(&tmp, &state->blocks[3]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+			crypto_aegis_block_xor(&tmp, src_blk);
+
+			crypto_aegis128_update_a(state, &tmp);
+
+			*dst_blk = tmp;
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+			dst += AEGIS_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			tmp = state->blocks[2];
+			crypto_aegis_block_and(&tmp, &state->blocks[3]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+			crypto_xor(tmp.bytes, src, AEGIS_BLOCK_SIZE);
+
+			crypto_aegis128_update_a(state, &tmp);
+
+			memcpy(dst, tmp.bytes, AEGIS_BLOCK_SIZE);
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+			dst += AEGIS_BLOCK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union aegis_block msg = {};
+		memcpy(msg.bytes, src, size);
+
+		tmp = state->blocks[2];
+		crypto_aegis_block_and(&tmp, &state->blocks[3]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+		crypto_aegis_block_xor(&msg, &tmp);
+
+		memset(msg.bytes + size, 0, AEGIS_BLOCK_SIZE - size);
+
+		crypto_aegis128_update_a(state, &msg);
+
+		memcpy(dst, msg.bytes, size);
+	}
+}
+
+static void crypto_aegis128_process_ad(struct aegis_state *state,
+				       struct scatterlist *sg_src,
+				       unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	union aegis_block buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= AEGIS_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = AEGIS_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+				crypto_aegis128_update_a(state, &buf);
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			crypto_aegis128_ad(state, src, left);
+			src += left & ~(AEGIS_BLOCK_SIZE - 1);
+			left &= AEGIS_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+
+		pos += left;
+		assoclen -= size;
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, AEGIS_BLOCK_SIZE - pos);
+		crypto_aegis128_update_a(state, &buf);
+	}
+}
+
+static void crypto_aegis128_process_crypt(struct aegis_state *state,
+					  struct aead_request *req,
+					  const struct aegis128_ops *ops)
+{
+	struct skcipher_walk walk;
+	u8 *src, *dst;
+	unsigned int chunksize;
+
+	ops->skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+		chunksize = walk.nbytes;
+
+		ops->crypt_chunk(state, dst, src, chunksize);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+static void crypto_aegis128_final(struct aegis_state *state,
+				  union aegis_block *tag_xor,
+				  u64 assoclen, u64 cryptlen)
+{
+	u64 assocbits = assoclen * 8;
+	u64 cryptbits = cryptlen * 8;
+
+	union aegis_block tmp;
+	unsigned int i;
+
+	tmp.words64[0] = cpu_to_le64(assocbits);
+	tmp.words64[1] = cpu_to_le64(cryptbits);
+
+	crypto_aegis_block_xor(&tmp, &state->blocks[3]);
+
+	for (i = 0; i < 7; i++)
+		crypto_aegis128_update_a(state, &tmp);
+
+	for (i = 0; i < AEGIS128_STATE_BLOCKS; i++)
+		crypto_aegis_block_xor(tag_xor, &state->blocks[i]);
+}
+
+static int crypto_aegis128_setkey(struct crypto_aead *aead, const u8 *key,
+				  unsigned int keylen)
+{
+	struct aegis_ctx *ctx = crypto_aead_ctx(aead);
+
+	if (keylen != AEGIS128_KEY_SIZE) {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key.bytes, key, AEGIS128_KEY_SIZE);
+	return 0;
+}
+
+static int crypto_aegis128_setauthsize(struct crypto_aead *tfm,
+				       unsigned int authsize)
+{
+	if (authsize > AEGIS128_MAX_AUTH_SIZE)
+		return -EINVAL;
+	if (authsize < AEGIS128_MIN_AUTH_SIZE)
+		return -EINVAL;
+	return 0;
+}
+
+static void crypto_aegis128_crypt(struct aead_request *req,
+				  union aegis_block *tag_xor,
+				  unsigned int cryptlen,
+				  const struct aegis128_ops *ops)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aegis_state state;
+
+	crypto_aegis128_init(&state, &ctx->key, req->iv);
+	crypto_aegis128_process_ad(&state, req->src, req->assoclen);
+	crypto_aegis128_process_crypt(&state, req, ops);
+	crypto_aegis128_final(&state, tag_xor, req->assoclen, cryptlen);
+}
+
+static int crypto_aegis128_encrypt(struct aead_request *req)
+{
+	static const struct aegis128_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_chunk = crypto_aegis128_encrypt_chunk,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	union aegis_block tag = {};
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_aegis128_crypt(req, &tag, cryptlen, &ops);
+
+	scatterwalk_map_and_copy(tag.bytes, req->dst, req->assoclen + cryptlen,
+				 authsize, 1);
+	return 0;
+}
+
+static int crypto_aegis128_decrypt(struct aead_request *req)
+{
+	static const struct aegis128_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_chunk = crypto_aegis128_decrypt_chunk,
+	};
+	static const u8 zeros[AEGIS128_MAX_AUTH_SIZE] = {};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	union aegis_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag.bytes, req->src, req->assoclen + cryptlen,
+				 authsize, 0);
+
+	crypto_aegis128_crypt(req, &tag, cryptlen, &ops);
+
+	return crypto_memneq(tag.bytes, zeros, authsize) ? -EBADMSG : 0;
+}
+
+static int crypto_aegis128_init_tfm(struct crypto_aead *tfm)
+{
+	return 0;
+}
+
+static void crypto_aegis128_exit_tfm(struct crypto_aead *tfm)
+{
+}
+
+static struct aead_alg crypto_aegis128_alg = {
+	.setkey = crypto_aegis128_setkey,
+	.setauthsize = crypto_aegis128_setauthsize,
+	.encrypt = crypto_aegis128_encrypt,
+	.decrypt = crypto_aegis128_decrypt,
+	.init = crypto_aegis128_init_tfm,
+	.exit = crypto_aegis128_exit_tfm,
+
+	.ivsize = AEGIS128_NONCE_SIZE,
+	.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
+	.chunksize = AEGIS_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx),
+		.cra_alignmask = 0,
+
+		.cra_priority = 100,
+
+		.cra_name = "aegis128",
+		.cra_driver_name = "aegis128-generic",
+
+		.cra_module = THIS_MODULE,
+	}
+};
+
+static int __init crypto_aegis128_module_init(void)
+{
+	return crypto_register_aead(&crypto_aegis128_alg);
+}
+
+static void __exit crypto_aegis128_module_exit(void)
+{
+	crypto_unregister_aead(&crypto_aegis128_alg);
+}
+
+module_init(crypto_aegis128_module_init);
+module_exit(crypto_aegis128_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("AEGIS-128 AEAD algorithm");
+MODULE_ALIAS_CRYPTO("aegis128");
+MODULE_ALIAS_CRYPTO("aegis128-generic");
diff --git a/crypto/aegis128l.c b/crypto/aegis128l.c
new file mode 100644
index 000000000000..0cc1a7525c85
--- /dev/null
+++ b/crypto/aegis128l.c
@@ -0,0 +1,527 @@
+/*
+ * The AEGIS-128L Authenticated-Encryption Algorithm
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+
+#include "aegis.h"
+
+#define AEGIS128L_CHUNK_BLOCKS 2
+#define AEGIS128L_CHUNK_SIZE (AEGIS128L_CHUNK_BLOCKS * AEGIS_BLOCK_SIZE)
+#define AEGIS128L_NONCE_SIZE 16
+#define AEGIS128L_STATE_BLOCKS 8
+#define AEGIS128L_KEY_SIZE 16
+#define AEGIS128L_MIN_AUTH_SIZE 8
+#define AEGIS128L_MAX_AUTH_SIZE 16
+
+union aegis_chunk {
+	union aegis_block blocks[AEGIS128L_CHUNK_BLOCKS];
+	u8 bytes[AEGIS128L_CHUNK_SIZE];
+};
+
+struct aegis_state {
+	union aegis_block blocks[AEGIS128L_STATE_BLOCKS];
+};
+
+struct aegis_ctx {
+	union aegis_block key;
+};
+
+struct aegis128l_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_chunk)(struct aegis_state *state, u8 *dst,
+			    const u8 *src, unsigned int size);
+};
+
+static void crypto_aegis128l_update(struct aegis_state *state)
+{
+	union aegis_block tmp;
+	unsigned int i;
+
+	tmp = state->blocks[AEGIS128L_STATE_BLOCKS - 1];
+	for (i = AEGIS128L_STATE_BLOCKS - 1; i > 0; i--)
+		crypto_aegis_aesenc(&state->blocks[i], &state->blocks[i - 1],
+				    &state->blocks[i]);
+	crypto_aegis_aesenc(&state->blocks[0], &tmp, &state->blocks[0]);
+}
+
+static void crypto_aegis128l_update_a(struct aegis_state *state,
+				      const union aegis_chunk *msg)
+{
+	crypto_aegis128l_update(state);
+	crypto_aegis_block_xor(&state->blocks[0], &msg->blocks[0]);
+	crypto_aegis_block_xor(&state->blocks[4], &msg->blocks[1]);
+}
+
+static void crypto_aegis128l_update_u(struct aegis_state *state,
+				      const void *msg)
+{
+	crypto_aegis128l_update(state);
+	crypto_xor(state->blocks[0].bytes, msg + 0 * AEGIS_BLOCK_SIZE,
+			AEGIS_BLOCK_SIZE);
+	crypto_xor(state->blocks[4].bytes, msg + 1 * AEGIS_BLOCK_SIZE,
+			AEGIS_BLOCK_SIZE);
+}
+
+static void crypto_aegis128l_init(struct aegis_state *state,
+				  const union aegis_block *key,
+				  const u8 *iv)
+{
+	union aegis_block key_iv;
+	union aegis_chunk chunk;
+	unsigned int i;
+
+	memcpy(chunk.blocks[0].bytes, iv, AEGIS_BLOCK_SIZE);
+	chunk.blocks[1] = *key;
+
+	key_iv = *key;
+	crypto_aegis_block_xor(&key_iv, &chunk.blocks[0]);
+
+	state->blocks[0] = key_iv;
+	state->blocks[1] = crypto_aegis_const[1];
+	state->blocks[2] = crypto_aegis_const[0];
+	state->blocks[3] = crypto_aegis_const[1];
+	state->blocks[4] = key_iv;
+	state->blocks[5] = *key;
+	state->blocks[6] = *key;
+	state->blocks[7] = *key;
+
+	crypto_aegis_block_xor(&state->blocks[5], &crypto_aegis_const[0]);
+	crypto_aegis_block_xor(&state->blocks[6], &crypto_aegis_const[1]);
+	crypto_aegis_block_xor(&state->blocks[7], &crypto_aegis_const[0]);
+
+	for (i = 0; i < 10; i++) {
+		crypto_aegis128l_update_a(state, &chunk);
+	}
+}
+
+static void crypto_aegis128l_ad(struct aegis_state *state,
+				const u8 *src, unsigned int size)
+{
+	if (AEGIS_ALIGNED(src)) {
+		const union aegis_chunk *src_chunk =
+				(const union aegis_chunk *)src;
+
+		while (size >= AEGIS128L_CHUNK_SIZE) {
+                    crypto_aegis128l_update_a(state, src_chunk);
+
+			size -= AEGIS128L_CHUNK_SIZE;
+			src_chunk += 1;
+		}
+	} else {
+		while (size >= AEGIS128L_CHUNK_SIZE) {
+			crypto_aegis128l_update_u(state, src);
+
+			size -= AEGIS128L_CHUNK_SIZE;
+			src += AEGIS128L_CHUNK_SIZE;
+		}
+	}
+}
+
+static void crypto_aegis128l_encrypt_chunk(struct aegis_state *state, u8 *dst,
+					   const u8 *src, unsigned int size)
+{
+	union aegis_chunk tmp;
+	union aegis_block *tmp0 = &tmp.blocks[0];
+	union aegis_block *tmp1 = &tmp.blocks[1];
+
+	if (AEGIS_ALIGNED(src) && AEGIS_ALIGNED(dst)) {
+		while (size >= AEGIS128L_CHUNK_SIZE) {
+			union aegis_chunk *dst_blk =
+					(union aegis_chunk *)dst;
+			const union aegis_chunk *src_blk =
+					(const union aegis_chunk *)src;
+
+			*tmp0 = state->blocks[2];
+			crypto_aegis_block_and(tmp0, &state->blocks[3]);
+			crypto_aegis_block_xor(tmp0, &state->blocks[6]);
+			crypto_aegis_block_xor(tmp0, &state->blocks[1]);
+			crypto_aegis_block_xor(tmp0, &src_blk->blocks[0]);
+
+			*tmp1 = state->blocks[6];
+			crypto_aegis_block_and(tmp1, &state->blocks[7]);
+			crypto_aegis_block_xor(tmp1, &state->blocks[5]);
+			crypto_aegis_block_xor(tmp1, &state->blocks[2]);
+			crypto_aegis_block_xor(tmp1, &src_blk->blocks[1]);
+
+			crypto_aegis128l_update_a(state, src_blk);
+
+			*dst_blk = tmp;
+
+			size -= AEGIS128L_CHUNK_SIZE;
+			src += AEGIS128L_CHUNK_SIZE;
+			dst += AEGIS128L_CHUNK_SIZE;
+		}
+	} else {
+		while (size >= AEGIS128L_CHUNK_SIZE) {
+			*tmp0 = state->blocks[2];
+			crypto_aegis_block_and(tmp0, &state->blocks[3]);
+			crypto_aegis_block_xor(tmp0, &state->blocks[6]);
+			crypto_aegis_block_xor(tmp0, &state->blocks[1]);
+			crypto_xor(tmp0->bytes, src + 0 * AEGIS_BLOCK_SIZE,
+				   AEGIS_BLOCK_SIZE);
+
+			*tmp1 = state->blocks[6];
+			crypto_aegis_block_and(tmp1, &state->blocks[7]);
+			crypto_aegis_block_xor(tmp1, &state->blocks[5]);
+			crypto_aegis_block_xor(tmp1, &state->blocks[2]);
+			crypto_xor(tmp1->bytes, src + 1 * AEGIS_BLOCK_SIZE,
+				   AEGIS_BLOCK_SIZE);
+
+			crypto_aegis128l_update_u(state, src);
+
+			memcpy(dst, tmp.bytes, AEGIS128L_CHUNK_SIZE);
+
+			size -= AEGIS128L_CHUNK_SIZE;
+			src += AEGIS128L_CHUNK_SIZE;
+			dst += AEGIS128L_CHUNK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union aegis_chunk msg = {};
+		memcpy(msg.bytes, src, size);
+
+		*tmp0 = state->blocks[2];
+		crypto_aegis_block_and(tmp0, &state->blocks[3]);
+		crypto_aegis_block_xor(tmp0, &state->blocks[6]);
+		crypto_aegis_block_xor(tmp0, &state->blocks[1]);
+
+		*tmp1 = state->blocks[6];
+		crypto_aegis_block_and(tmp1, &state->blocks[7]);
+		crypto_aegis_block_xor(tmp1, &state->blocks[5]);
+		crypto_aegis_block_xor(tmp1, &state->blocks[2]);
+
+		crypto_aegis128l_update_a(state, &msg);
+
+		crypto_aegis_block_xor(&msg.blocks[0], tmp0);
+		crypto_aegis_block_xor(&msg.blocks[1], tmp1);
+
+		memcpy(dst, msg.bytes, size);
+	}
+}
+
+static void crypto_aegis128l_decrypt_chunk(struct aegis_state *state, u8 *dst,
+					   const u8 *src, unsigned int size)
+{
+	union aegis_chunk tmp;
+	union aegis_block *tmp0 = &tmp.blocks[0];
+	union aegis_block *tmp1 = &tmp.blocks[1];
+
+	if (AEGIS_ALIGNED(src) && AEGIS_ALIGNED(dst)) {
+		while (size >= AEGIS128L_CHUNK_SIZE) {
+			union aegis_chunk *dst_blk =
+					(union aegis_chunk *)dst;
+			const union aegis_chunk *src_blk =
+					(const union aegis_chunk *)src;
+
+			*tmp0 = state->blocks[2];
+			crypto_aegis_block_and(tmp0, &state->blocks[3]);
+			crypto_aegis_block_xor(tmp0, &state->blocks[6]);
+			crypto_aegis_block_xor(tmp0, &state->blocks[1]);
+			crypto_aegis_block_xor(tmp0, &src_blk->blocks[0]);
+
+			*tmp1 = state->blocks[6];
+			crypto_aegis_block_and(tmp1, &state->blocks[7]);
+			crypto_aegis_block_xor(tmp1, &state->blocks[5]);
+			crypto_aegis_block_xor(tmp1, &state->blocks[2]);
+			crypto_aegis_block_xor(tmp1, &src_blk->blocks[1]);
+
+			crypto_aegis128l_update_a(state, &tmp);
+
+			*dst_blk = tmp;
+
+			size -= AEGIS128L_CHUNK_SIZE;
+			src += AEGIS128L_CHUNK_SIZE;
+			dst += AEGIS128L_CHUNK_SIZE;
+		}
+	} else {
+		while (size >= AEGIS128L_CHUNK_SIZE) {
+			*tmp0 = state->blocks[2];
+			crypto_aegis_block_and(tmp0, &state->blocks[3]);
+			crypto_aegis_block_xor(tmp0, &state->blocks[6]);
+			crypto_aegis_block_xor(tmp0, &state->blocks[1]);
+			crypto_xor(tmp0->bytes, src + 0 * AEGIS_BLOCK_SIZE,
+				   AEGIS_BLOCK_SIZE);
+
+			*tmp1 = state->blocks[6];
+			crypto_aegis_block_and(tmp1, &state->blocks[7]);
+			crypto_aegis_block_xor(tmp1, &state->blocks[5]);
+			crypto_aegis_block_xor(tmp1, &state->blocks[2]);
+			crypto_xor(tmp1->bytes, src + 1 * AEGIS_BLOCK_SIZE,
+				   AEGIS_BLOCK_SIZE);
+
+			crypto_aegis128l_update_a(state, &tmp);
+
+			memcpy(dst, tmp.bytes, AEGIS128L_CHUNK_SIZE);
+
+			size -= AEGIS128L_CHUNK_SIZE;
+			src += AEGIS128L_CHUNK_SIZE;
+			dst += AEGIS128L_CHUNK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union aegis_chunk msg = {};
+		memcpy(msg.bytes, src, size);
+
+		*tmp0 = state->blocks[2];
+		crypto_aegis_block_and(tmp0, &state->blocks[3]);
+		crypto_aegis_block_xor(tmp0, &state->blocks[6]);
+		crypto_aegis_block_xor(tmp0, &state->blocks[1]);
+		crypto_aegis_block_xor(&msg.blocks[0], tmp0);
+
+		*tmp1 = state->blocks[6];
+		crypto_aegis_block_and(tmp1, &state->blocks[7]);
+		crypto_aegis_block_xor(tmp1, &state->blocks[5]);
+		crypto_aegis_block_xor(tmp1, &state->blocks[2]);
+		crypto_aegis_block_xor(&msg.blocks[1], tmp1);
+
+		memset(msg.bytes + size, 0, AEGIS128L_CHUNK_SIZE - size);
+
+		crypto_aegis128l_update_a(state, &msg);
+
+		memcpy(dst, msg.bytes, size);
+	}
+}
+
+static void crypto_aegis128l_process_ad(struct aegis_state *state,
+					struct scatterlist *sg_src,
+					unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	union aegis_chunk buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= AEGIS128L_CHUNK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = AEGIS128L_CHUNK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+				crypto_aegis128l_update_a(state, &buf);
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			crypto_aegis128l_ad(state, src, left);
+			src += left & ~(AEGIS128L_CHUNK_SIZE - 1);
+			left &= AEGIS128L_CHUNK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+
+		pos += left;
+		assoclen -= size;
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, AEGIS128L_CHUNK_SIZE - pos);
+		crypto_aegis128l_update_a(state, &buf);
+	}
+}
+
+static void crypto_aegis128l_process_crypt(struct aegis_state *state,
+					   struct aead_request *req,
+					   const struct aegis128l_ops *ops)
+{
+	struct skcipher_walk walk;
+	u8 *src, *dst;
+	unsigned int chunksize;
+
+	ops->skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+		chunksize = walk.nbytes;
+
+		ops->crypt_chunk(state, dst, src, chunksize);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+static void crypto_aegis128l_final(struct aegis_state *state,
+				   union aegis_block *tag_xor,
+				   u64 assoclen, u64 cryptlen)
+{
+	u64 assocbits = assoclen * 8;
+	u64 cryptbits = cryptlen * 8;
+
+	union aegis_chunk tmp;
+	unsigned int i;
+
+	tmp.blocks[0].words64[0] = cpu_to_le64(assocbits);
+	tmp.blocks[0].words64[1] = cpu_to_le64(cryptbits);
+
+	crypto_aegis_block_xor(&tmp.blocks[0], &state->blocks[2]);
+
+	tmp.blocks[1] = tmp.blocks[0];
+	for (i = 0; i < 7; i++)
+		crypto_aegis128l_update_a(state, &tmp);
+
+	for (i = 0; i < 7; i++)
+		crypto_aegis_block_xor(tag_xor, &state->blocks[i]);
+}
+
+static int crypto_aegis128l_setkey(struct crypto_aead *aead, const u8 *key,
+				   unsigned int keylen)
+{
+	struct aegis_ctx *ctx = crypto_aead_ctx(aead);
+
+	if (keylen != AEGIS128L_KEY_SIZE) {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key.bytes, key, AEGIS128L_KEY_SIZE);
+	return 0;
+}
+
+static int crypto_aegis128l_setauthsize(struct crypto_aead *tfm,
+					unsigned int authsize)
+{
+	if (authsize > AEGIS128L_MAX_AUTH_SIZE)
+		return -EINVAL;
+	if (authsize < AEGIS128L_MIN_AUTH_SIZE)
+		return -EINVAL;
+	return 0;
+}
+
+static void crypto_aegis128l_crypt(struct aead_request *req,
+				   union aegis_block *tag_xor,
+				   unsigned int cryptlen,
+				   const struct aegis128l_ops *ops)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aegis_state state;
+
+	crypto_aegis128l_init(&state, &ctx->key, req->iv);
+	crypto_aegis128l_process_ad(&state, req->src, req->assoclen);
+	crypto_aegis128l_process_crypt(&state, req, ops);
+	crypto_aegis128l_final(&state, tag_xor, req->assoclen, cryptlen);
+}
+
+static int crypto_aegis128l_encrypt(struct aead_request *req)
+{
+	static const struct aegis128l_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_chunk = crypto_aegis128l_encrypt_chunk,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	union aegis_block tag = {};
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_aegis128l_crypt(req, &tag, cryptlen, &ops);
+
+	scatterwalk_map_and_copy(tag.bytes, req->dst, req->assoclen + cryptlen,
+				 authsize, 1);
+	return 0;
+}
+
+static int crypto_aegis128l_decrypt(struct aead_request *req)
+{
+	static const struct aegis128l_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_chunk = crypto_aegis128l_decrypt_chunk,
+	};
+	static const u8 zeros[AEGIS128L_MAX_AUTH_SIZE] = {};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	union aegis_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag.bytes, req->src, req->assoclen + cryptlen,
+				 authsize, 0);
+
+	crypto_aegis128l_crypt(req, &tag, cryptlen, &ops);
+
+	return crypto_memneq(tag.bytes, zeros, authsize) ? -EBADMSG : 0;
+}
+
+static int crypto_aegis128l_init_tfm(struct crypto_aead *tfm)
+{
+	return 0;
+}
+
+static void crypto_aegis128l_exit_tfm(struct crypto_aead *tfm)
+{
+}
+
+static struct aead_alg crypto_aegis128l_alg = {
+	.setkey = crypto_aegis128l_setkey,
+	.setauthsize = crypto_aegis128l_setauthsize,
+	.encrypt = crypto_aegis128l_encrypt,
+	.decrypt = crypto_aegis128l_decrypt,
+	.init = crypto_aegis128l_init_tfm,
+	.exit = crypto_aegis128l_exit_tfm,
+
+	.ivsize = AEGIS128L_NONCE_SIZE,
+	.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
+	.chunksize = AEGIS128L_CHUNK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx),
+		.cra_alignmask = 0,
+
+		.cra_priority = 100,
+
+		.cra_name = "aegis128l",
+		.cra_driver_name = "aegis128l-generic",
+
+		.cra_module = THIS_MODULE,
+	}
+};
+
+static int __init crypto_aegis128l_module_init(void)
+{
+	return crypto_register_aead(&crypto_aegis128l_alg);
+}
+
+static void __exit crypto_aegis128l_module_exit(void)
+{
+	crypto_unregister_aead(&crypto_aegis128l_alg);
+}
+
+module_init(crypto_aegis128l_module_init);
+module_exit(crypto_aegis128l_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("AEGIS-128L AEAD algorithm");
+MODULE_ALIAS_CRYPTO("aegis128l");
+MODULE_ALIAS_CRYPTO("aegis128l-generic");
diff --git a/crypto/aegis256.c b/crypto/aegis256.c
new file mode 100644
index 000000000000..a489d741d33a
--- /dev/null
+++ b/crypto/aegis256.c
@@ -0,0 +1,478 @@
+/*
+ * The AEGIS-256 Authenticated-Encryption Algorithm
+ *
+ * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+
+#include "aegis.h"
+
+#define AEGIS256_NONCE_SIZE 32
+#define AEGIS256_STATE_BLOCKS 6
+#define AEGIS256_KEY_SIZE 32
+#define AEGIS256_MIN_AUTH_SIZE 8
+#define AEGIS256_MAX_AUTH_SIZE 16
+
+struct aegis_state {
+	union aegis_block blocks[AEGIS256_STATE_BLOCKS];
+};
+
+struct aegis_ctx {
+	union aegis_block key[AEGIS256_KEY_SIZE / AEGIS_BLOCK_SIZE];
+};
+
+struct aegis256_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_chunk)(struct aegis_state *state, u8 *dst,
+			    const u8 *src, unsigned int size);
+};
+
+static void crypto_aegis256_update(struct aegis_state *state)
+{
+	union aegis_block tmp;
+	unsigned int i;
+
+	tmp = state->blocks[AEGIS256_STATE_BLOCKS - 1];
+	for (i = AEGIS256_STATE_BLOCKS - 1; i > 0; i--)
+		crypto_aegis_aesenc(&state->blocks[i], &state->blocks[i - 1],
+				    &state->blocks[i]);
+	crypto_aegis_aesenc(&state->blocks[0], &tmp, &state->blocks[0]);
+}
+
+static void crypto_aegis256_update_a(struct aegis_state *state,
+				     const union aegis_block *msg)
+{
+	crypto_aegis256_update(state);
+	crypto_aegis_block_xor(&state->blocks[0], msg);
+}
+
+static void crypto_aegis256_update_u(struct aegis_state *state, const void *msg)
+{
+	crypto_aegis256_update(state);
+	crypto_xor(state->blocks[0].bytes, msg, AEGIS_BLOCK_SIZE);
+}
+
+static void crypto_aegis256_init(struct aegis_state *state,
+				 const union aegis_block *key,
+				 const u8 *iv)
+{
+	union aegis_block key_iv[2];
+	unsigned int i;
+
+	key_iv[0] = key[0];
+	key_iv[1] = key[1];
+	crypto_xor(key_iv[0].bytes, iv + 0 * AEGIS_BLOCK_SIZE,
+			AEGIS_BLOCK_SIZE);
+	crypto_xor(key_iv[1].bytes, iv + 1 * AEGIS_BLOCK_SIZE,
+			AEGIS_BLOCK_SIZE);
+
+	state->blocks[0] = key_iv[0];
+	state->blocks[1] = key_iv[1];
+	state->blocks[2] = crypto_aegis_const[1];
+	state->blocks[3] = crypto_aegis_const[0];
+	state->blocks[4] = key[0];
+	state->blocks[5] = key[1];
+
+	crypto_aegis_block_xor(&state->blocks[4], &crypto_aegis_const[0]);
+	crypto_aegis_block_xor(&state->blocks[5], &crypto_aegis_const[1]);
+
+	for (i = 0; i < 4; i++) {
+		crypto_aegis256_update_a(state, &key[0]);
+		crypto_aegis256_update_a(state, &key[1]);
+		crypto_aegis256_update_a(state, &key_iv[0]);
+		crypto_aegis256_update_a(state, &key_iv[1]);
+	}
+}
+
+static void crypto_aegis256_ad(struct aegis_state *state,
+			       const u8 *src, unsigned int size)
+{
+	if (AEGIS_ALIGNED(src)) {
+		const union aegis_block *src_blk =
+				(const union aegis_block *)src;
+
+		while (size >= AEGIS_BLOCK_SIZE) {
+			crypto_aegis256_update_a(state, src_blk);
+
+			size -= AEGIS_BLOCK_SIZE;
+			src_blk++;
+		}
+	} else {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			crypto_aegis256_update_u(state, src);
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+		}
+	}
+}
+
+static void crypto_aegis256_encrypt_chunk(struct aegis_state *state, u8 *dst,
+					  const u8 *src, unsigned int size)
+{
+	union aegis_block tmp;
+
+	if (AEGIS_ALIGNED(src) && AEGIS_ALIGNED(dst)) {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			union aegis_block *dst_blk =
+					(union aegis_block *)dst;
+			const union aegis_block *src_blk =
+					(const union aegis_block *)src;
+
+			tmp = state->blocks[2];
+			crypto_aegis_block_and(&tmp, &state->blocks[3]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[5]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+			crypto_aegis_block_xor(&tmp, src_blk);
+
+			crypto_aegis256_update_a(state, src_blk);
+
+			*dst_blk = tmp;
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+			dst += AEGIS_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			tmp = state->blocks[2];
+			crypto_aegis_block_and(&tmp, &state->blocks[3]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[5]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+			crypto_xor(tmp.bytes, src, AEGIS_BLOCK_SIZE);
+
+			crypto_aegis256_update_u(state, src);
+
+			memcpy(dst, tmp.bytes, AEGIS_BLOCK_SIZE);
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+			dst += AEGIS_BLOCK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union aegis_block msg = {};
+		memcpy(msg.bytes, src, size);
+
+		tmp = state->blocks[2];
+		crypto_aegis_block_and(&tmp, &state->blocks[3]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[5]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+
+		crypto_aegis256_update_a(state, &msg);
+
+		crypto_aegis_block_xor(&msg, &tmp);
+
+		memcpy(dst, msg.bytes, size);
+	}
+}
+
+static void crypto_aegis256_decrypt_chunk(struct aegis_state *state, u8 *dst,
+					  const u8 *src, unsigned int size)
+{
+	union aegis_block tmp;
+
+	if (AEGIS_ALIGNED(src) && AEGIS_ALIGNED(dst)) {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			union aegis_block *dst_blk =
+					(union aegis_block *)dst;
+			const union aegis_block *src_blk =
+					(const union aegis_block *)src;
+
+			tmp = state->blocks[2];
+			crypto_aegis_block_and(&tmp, &state->blocks[3]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[5]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+			crypto_aegis_block_xor(&tmp, src_blk);
+
+			crypto_aegis256_update_a(state, &tmp);
+
+			*dst_blk = tmp;
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+			dst += AEGIS_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= AEGIS_BLOCK_SIZE) {
+			tmp = state->blocks[2];
+			crypto_aegis_block_and(&tmp, &state->blocks[3]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[5]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+			crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+			crypto_xor(tmp.bytes, src, AEGIS_BLOCK_SIZE);
+
+			crypto_aegis256_update_a(state, &tmp);
+
+			memcpy(dst, tmp.bytes, AEGIS_BLOCK_SIZE);
+
+			size -= AEGIS_BLOCK_SIZE;
+			src += AEGIS_BLOCK_SIZE;
+			dst += AEGIS_BLOCK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union aegis_block msg = {};
+		memcpy(msg.bytes, src, size);
+
+		tmp = state->blocks[2];
+		crypto_aegis_block_and(&tmp, &state->blocks[3]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[5]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[4]);
+		crypto_aegis_block_xor(&tmp, &state->blocks[1]);
+		crypto_aegis_block_xor(&msg, &tmp);
+
+		memset(msg.bytes + size, 0, AEGIS_BLOCK_SIZE - size);
+
+		crypto_aegis256_update_a(state, &msg);
+
+		memcpy(dst, msg.bytes, size);
+	}
+}
+
+static void crypto_aegis256_process_ad(struct aegis_state *state,
+				       struct scatterlist *sg_src,
+				       unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	union aegis_block buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= AEGIS_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = AEGIS_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+				crypto_aegis256_update_a(state, &buf);
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			crypto_aegis256_ad(state, src, left);
+			src += left & ~(AEGIS_BLOCK_SIZE - 1);
+			left &= AEGIS_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+
+		pos += left;
+		assoclen -= size;
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, AEGIS_BLOCK_SIZE - pos);
+		crypto_aegis256_update_a(state, &buf);
+	}
+}
+
+static void crypto_aegis256_process_crypt(struct aegis_state *state,
+					  struct aead_request *req,
+					  const struct aegis256_ops *ops)
+{
+	struct skcipher_walk walk;
+	u8 *src, *dst;
+	unsigned int chunksize;
+
+	ops->skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+		chunksize = walk.nbytes;
+
+		ops->crypt_chunk(state, dst, src, chunksize);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+static void crypto_aegis256_final(struct aegis_state *state,
+				  union aegis_block *tag_xor,
+				  u64 assoclen, u64 cryptlen)
+{
+	u64 assocbits = assoclen * 8;
+	u64 cryptbits = cryptlen * 8;
+
+	union aegis_block tmp;
+	unsigned int i;
+
+	tmp.words64[0] = cpu_to_le64(assocbits);
+	tmp.words64[1] = cpu_to_le64(cryptbits);
+
+	crypto_aegis_block_xor(&tmp, &state->blocks[3]);
+
+	for (i = 0; i < 7; i++)
+		crypto_aegis256_update_a(state, &tmp);
+
+	for (i = 0; i < AEGIS256_STATE_BLOCKS; i++)
+		crypto_aegis_block_xor(tag_xor, &state->blocks[i]);
+}
+
+static int crypto_aegis256_setkey(struct crypto_aead *aead, const u8 *key,
+				  unsigned int keylen)
+{
+	struct aegis_ctx *ctx = crypto_aead_ctx(aead);
+
+	if (keylen != AEGIS256_KEY_SIZE) {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key[0].bytes, key, AEGIS_BLOCK_SIZE);
+	memcpy(ctx->key[1].bytes, key + AEGIS_BLOCK_SIZE,
+			AEGIS_BLOCK_SIZE);
+	return 0;
+}
+
+static int crypto_aegis256_setauthsize(struct crypto_aead *tfm,
+				       unsigned int authsize)
+{
+	if (authsize > AEGIS256_MAX_AUTH_SIZE)
+		return -EINVAL;
+	if (authsize < AEGIS256_MIN_AUTH_SIZE)
+		return -EINVAL;
+	return 0;
+}
+
+static void crypto_aegis256_crypt(struct aead_request *req,
+				  union aegis_block *tag_xor,
+				  unsigned int cryptlen,
+				  const struct aegis256_ops *ops)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aegis_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aegis_state state;
+
+	crypto_aegis256_init(&state, ctx->key, req->iv);
+	crypto_aegis256_process_ad(&state, req->src, req->assoclen);
+	crypto_aegis256_process_crypt(&state, req, ops);
+	crypto_aegis256_final(&state, tag_xor, req->assoclen, cryptlen);
+}
+
+static int crypto_aegis256_encrypt(struct aead_request *req)
+{
+	static const struct aegis256_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_chunk = crypto_aegis256_encrypt_chunk,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	union aegis_block tag = {};
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_aegis256_crypt(req, &tag, cryptlen, &ops);
+
+	scatterwalk_map_and_copy(tag.bytes, req->dst, req->assoclen + cryptlen,
+				 authsize, 1);
+	return 0;
+}
+
+static int crypto_aegis256_decrypt(struct aead_request *req)
+{
+	static const struct aegis256_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_chunk = crypto_aegis256_decrypt_chunk,
+	};
+	static const u8 zeros[AEGIS256_MAX_AUTH_SIZE] = {};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	union aegis_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag.bytes, req->src, req->assoclen + cryptlen,
+				 authsize, 0);
+
+	crypto_aegis256_crypt(req, &tag, cryptlen, &ops);
+
+	return crypto_memneq(tag.bytes, zeros, authsize) ? -EBADMSG : 0;
+}
+
+static int crypto_aegis256_init_tfm(struct crypto_aead *tfm)
+{
+	return 0;
+}
+
+static void crypto_aegis256_exit_tfm(struct crypto_aead *tfm)
+{
+}
+
+static struct aead_alg crypto_aegis256_alg = {
+	.setkey = crypto_aegis256_setkey,
+	.setauthsize = crypto_aegis256_setauthsize,
+	.encrypt = crypto_aegis256_encrypt,
+	.decrypt = crypto_aegis256_decrypt,
+	.init = crypto_aegis256_init_tfm,
+	.exit = crypto_aegis256_exit_tfm,
+
+	.ivsize = AEGIS256_NONCE_SIZE,
+	.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
+	.chunksize = AEGIS_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx),
+		.cra_alignmask = 0,
+
+		.cra_priority = 100,
+
+		.cra_name = "aegis256",
+		.cra_driver_name = "aegis256-generic",
+
+		.cra_module = THIS_MODULE,
+	}
+};
+
+static int __init crypto_aegis256_module_init(void)
+{
+	return crypto_register_aead(&crypto_aegis256_alg);
+}
+
+static void __exit crypto_aegis256_module_exit(void)
+{
+	crypto_unregister_aead(&crypto_aegis256_alg);
+}
+
+module_init(crypto_aegis256_module_init);
+module_exit(crypto_aegis256_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("AEGIS-256 AEAD algorithm");
+MODULE_ALIAS_CRYPTO("aegis256");
+MODULE_ALIAS_CRYPTO("aegis256-generic");
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 7846c0c20cfe..89ed613c017e 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -347,7 +347,6 @@ static const struct proto_ops alg_proto_ops = {
 	.sendpage	=	sock_no_sendpage,
 	.sendmsg	=	sock_no_sendmsg,
 	.recvmsg	=	sock_no_recvmsg,
-	.poll		=	sock_no_poll,
 
 	.bind		=	alg_bind,
 	.release	=	af_alg_release,
@@ -1061,19 +1060,12 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
 }
 EXPORT_SYMBOL_GPL(af_alg_async_cb);
 
-/**
- * af_alg_poll - poll system call handler
- */
-__poll_t af_alg_poll(struct file *file, struct socket *sock,
-			 poll_table *wait)
+__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct af_alg_ctx *ctx = ask->private;
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	__poll_t mask = 0;
 
 	if (!ctx->more || ctx->used)
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -1083,7 +1075,7 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock,
 
 	return mask;
 }
-EXPORT_SYMBOL_GPL(af_alg_poll);
+EXPORT_SYMBOL_GPL(af_alg_poll_mask);
 
 /**
  * af_alg_alloc_areq - allocate struct af_alg_async_req
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 2a0271b5f62a..c0755cf4f53f 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -10,6 +10,7 @@
  *
  */
 
+#include <crypto/algapi.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/fips.h>
@@ -59,6 +60,15 @@ static int crypto_check_alg(struct crypto_alg *alg)
 	if (alg->cra_blocksize > PAGE_SIZE / 8)
 		return -EINVAL;
 
+	if (!alg->cra_type && (alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+			       CRYPTO_ALG_TYPE_CIPHER) {
+		if (alg->cra_alignmask > MAX_CIPHER_ALIGNMASK)
+			return -EINVAL;
+
+		if (alg->cra_blocksize > MAX_CIPHER_BLOCKSIZE)
+			return -EINVAL;
+	}
+
 	if (alg->cra_priority < 0)
 		return -EINVAL;
 
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 4b07edd5a9ff..330cf9f2b767 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -375,7 +375,7 @@ static struct proto_ops algif_aead_ops = {
 	.sendmsg	=	aead_sendmsg,
 	.sendpage	=	af_alg_sendpage,
 	.recvmsg	=	aead_recvmsg,
-	.poll		=	af_alg_poll,
+	.poll_mask	=	af_alg_poll_mask,
 };
 
 static int aead_check_key(struct socket *sock)
@@ -471,7 +471,7 @@ static struct proto_ops algif_aead_ops_nokey = {
 	.sendmsg	=	aead_sendmsg_nokey,
 	.sendpage	=	aead_sendpage_nokey,
 	.recvmsg	=	aead_recvmsg_nokey,
-	.poll		=	af_alg_poll,
+	.poll_mask	=	af_alg_poll_mask,
 };
 
 static void *aead_bind(const char *name, u32 type, u32 mask)
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 6c9b1927a520..bfcf595fd8f9 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -288,7 +288,6 @@ static struct proto_ops algif_hash_ops = {
 	.mmap		=	sock_no_mmap,
 	.bind		=	sock_no_bind,
 	.setsockopt	=	sock_no_setsockopt,
-	.poll		=	sock_no_poll,
 
 	.release	=	af_alg_release,
 	.sendmsg	=	hash_sendmsg,
@@ -396,7 +395,6 @@ static struct proto_ops algif_hash_ops_nokey = {
 	.mmap		=	sock_no_mmap,
 	.bind		=	sock_no_bind,
 	.setsockopt	=	sock_no_setsockopt,
-	.poll		=	sock_no_poll,
 
 	.release	=	af_alg_release,
 	.sendmsg	=	hash_sendmsg_nokey,
diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c
index 150c2b6480ed..22df3799a17b 100644
--- a/crypto/algif_rng.c
+++ b/crypto/algif_rng.c
@@ -106,7 +106,6 @@ static struct proto_ops algif_rng_ops = {
 	.bind		=	sock_no_bind,
 	.accept		=	sock_no_accept,
 	.setsockopt	=	sock_no_setsockopt,
-	.poll		=	sock_no_poll,
 	.sendmsg	=	sock_no_sendmsg,
 	.sendpage	=	sock_no_sendpage,
 
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index c4e885df4564..15cf3c5222e0 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -205,7 +205,7 @@ static struct proto_ops algif_skcipher_ops = {
 	.sendmsg	=	skcipher_sendmsg,
 	.sendpage	=	af_alg_sendpage,
 	.recvmsg	=	skcipher_recvmsg,
-	.poll		=	af_alg_poll,
+	.poll_mask	=	af_alg_poll_mask,
 };
 
 static int skcipher_check_key(struct socket *sock)
@@ -301,7 +301,7 @@ static struct proto_ops algif_skcipher_ops_nokey = {
 	.sendmsg	=	skcipher_sendmsg_nokey,
 	.sendpage	=	skcipher_sendpage_nokey,
 	.recvmsg	=	skcipher_recvmsg_nokey,
-	.poll		=	af_alg_poll,
+	.poll_mask	=	af_alg_poll_mask,
 };
 
 static void *skcipher_bind(const char *name, u32 type, u32 mask)
diff --git a/crypto/api.c b/crypto/api.c
index 1d5290c67108..0ee632bba064 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -204,9 +204,14 @@ static struct crypto_alg *crypto_alg_lookup(const char *name, u32 type,
 
 	down_read(&crypto_alg_sem);
 	alg = __crypto_alg_lookup(name, type | test, mask | test);
-	if (!alg && test)
-		alg = __crypto_alg_lookup(name, type, mask) ?
-		      ERR_PTR(-ELIBBAD) : NULL;
+	if (!alg && test) {
+		alg = __crypto_alg_lookup(name, type, mask);
+		if (alg && !crypto_is_larval(alg)) {
+			/* Test failed */
+			crypto_mod_put(alg);
+			alg = ERR_PTR(-ELIBBAD);
+		}
+	}
 	up_read(&crypto_alg_sem);
 
 	return alg;
diff --git a/crypto/authenc.c b/crypto/authenc.c
index d3d6d72fe649..4fa8d40d947b 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -108,6 +108,7 @@ static int crypto_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 				       CRYPTO_TFM_RES_MASK);
 
 out:
+	memzero_explicit(&keys, sizeof(keys));
 	return err;
 
 badkey:
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 15f91ddd7f0e..50b804747e20 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -90,6 +90,7 @@ static int crypto_authenc_esn_setkey(struct crypto_aead *authenc_esn, const u8 *
 					   CRYPTO_TFM_RES_MASK);
 
 out:
+	memzero_explicit(&keys, sizeof(keys));
 	return err;
 
 badkey:
diff --git a/crypto/cfb.c b/crypto/cfb.c
index 94ee39bed758..a0d68c09e1b9 100644
--- a/crypto/cfb.c
+++ b/crypto/cfb.c
@@ -53,9 +53,8 @@ static void crypto_cfb_encrypt_one(struct crypto_skcipher *tfm,
 static void crypto_cfb_final(struct skcipher_walk *walk,
 			     struct crypto_skcipher *tfm)
 {
-	const unsigned int bsize = crypto_cfb_bsize(tfm);
 	const unsigned long alignmask = crypto_skcipher_alignmask(tfm);
-	u8 tmp[bsize + alignmask];
+	u8 tmp[MAX_CIPHER_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
 	u8 *stream = PTR_ALIGN(tmp + 0, alignmask + 1);
 	u8 *src = walk->src.virt.addr;
 	u8 *dst = walk->dst.virt.addr;
@@ -94,7 +93,7 @@ static int crypto_cfb_encrypt_inplace(struct skcipher_walk *walk,
 	unsigned int nbytes = walk->nbytes;
 	u8 *src = walk->src.virt.addr;
 	u8 *iv = walk->iv;
-	u8 tmp[bsize];
+	u8 tmp[MAX_CIPHER_BLOCKSIZE];
 
 	do {
 		crypto_cfb_encrypt_one(tfm, iv, tmp);
@@ -164,7 +163,7 @@ static int crypto_cfb_decrypt_inplace(struct skcipher_walk *walk,
 	unsigned int nbytes = walk->nbytes;
 	u8 *src = walk->src.virt.addr;
 	u8 *iv = walk->iv;
-	u8 tmp[bsize];
+	u8 tmp[MAX_CIPHER_BLOCKSIZE];
 
 	do {
 		crypto_cfb_encrypt_one(tfm, iv, tmp);
diff --git a/crypto/cipher.c b/crypto/cipher.c
index 94fa3551476b..57836c30a49a 100644
--- a/crypto/cipher.c
+++ b/crypto/cipher.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <crypto/algapi.h>
 #include <linux/kernel.h>
 #include <linux/crypto.h>
 #include <linux/errno.h>
@@ -67,7 +68,7 @@ static void cipher_crypt_unaligned(void (*fn)(struct crypto_tfm *, u8 *,
 {
 	unsigned long alignmask = crypto_tfm_alg_alignmask(tfm);
 	unsigned int size = crypto_tfm_alg_blocksize(tfm);
-	u8 buffer[size + alignmask];
+	u8 buffer[MAX_CIPHER_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
 	u8 *tmp = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
 
 	memcpy(tmp, src, size);
diff --git a/crypto/crc32_generic.c b/crypto/crc32_generic.c
index 718cbce8d169..00facd27bcc2 100644
--- a/crypto/crc32_generic.c
+++ b/crypto/crc32_generic.c
@@ -29,6 +29,7 @@
  * This is crypto api shash wrappers to crc32_le.
  */
 
+#include <asm/unaligned.h>
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
@@ -39,11 +40,6 @@
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
 
-static u32 __crc32_le(u32 crc, unsigned char const *p, size_t len)
-{
-	return crc32_le(crc, p, len);
-}
-
 /** No default init with ~0 */
 static int crc32_cra_init(struct crypto_tfm *tfm)
 {
@@ -54,7 +50,6 @@ static int crc32_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-
 /*
  * Setting the seed allows arbitrary accumulators and flexible XOR policy
  * If your algorithm starts with ~0, then XOR with ~0 before you set
@@ -69,7 +64,7 @@ static int crc32_setkey(struct crypto_shash *hash, const u8 *key,
 		crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
-	*mctx = le32_to_cpup((__le32 *)key);
+	*mctx = get_unaligned_le32(key);
 	return 0;
 }
 
@@ -88,7 +83,7 @@ static int crc32_update(struct shash_desc *desc, const u8 *data,
 {
 	u32 *crcp = shash_desc_ctx(desc);
 
-	*crcp = __crc32_le(*crcp, data, len);
+	*crcp = crc32_le(*crcp, data, len);
 	return 0;
 }
 
@@ -96,7 +91,7 @@ static int crc32_update(struct shash_desc *desc, const u8 *data,
 static int __crc32_finup(u32 *crcp, const u8 *data, unsigned int len,
 			 u8 *out)
 {
-	*(__le32 *)out = cpu_to_le32(__crc32_le(*crcp, data, len));
+	put_unaligned_le32(crc32_le(*crcp, data, len), out);
 	return 0;
 }
 
@@ -110,7 +105,7 @@ static int crc32_final(struct shash_desc *desc, u8 *out)
 {
 	u32 *crcp = shash_desc_ctx(desc);
 
-	*(__le32 *)out = cpu_to_le32p(crcp);
+	put_unaligned_le32(*crcp, out);
 	return 0;
 }
 
diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c
index 372320399622..7283066ecc98 100644
--- a/crypto/crc32c_generic.c
+++ b/crypto/crc32c_generic.c
@@ -35,6 +35,7 @@
  *
  */
 
+#include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -82,7 +83,7 @@ static int chksum_setkey(struct crypto_shash *tfm, const u8 *key,
 		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
-	mctx->key = le32_to_cpu(*(__le32 *)key);
+	mctx->key = get_unaligned_le32(key);
 	return 0;
 }
 
@@ -99,13 +100,13 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	*(__le32 *)out = ~cpu_to_le32p(&ctx->crc);
+	put_unaligned_le32(~ctx->crc, out);
 	return 0;
 }
 
 static int __chksum_finup(u32 *crcp, const u8 *data, unsigned int len, u8 *out)
 {
-	*(__le32 *)out = ~cpu_to_le32(__crc32c_le(*crcp, data, len));
+	put_unaligned_le32(~__crc32c_le(*crcp, data, len), out);
 	return 0;
 }
 
@@ -148,7 +149,6 @@ static struct shash_alg alg = {
 		.cra_priority		=	100,
 		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
-		.cra_alignmask		=	3,
 		.cra_ctxsize		=	sizeof(struct chksum_ctx),
 		.cra_module		=	THIS_MODULE,
 		.cra_init		=	crc32c_cra_init,
diff --git a/crypto/ctr.c b/crypto/ctr.c
index 854d924f9d8e..435b75bd619e 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -58,7 +58,7 @@ static void crypto_ctr_crypt_final(struct blkcipher_walk *walk,
 	unsigned int bsize = crypto_cipher_blocksize(tfm);
 	unsigned long alignmask = crypto_cipher_alignmask(tfm);
 	u8 *ctrblk = walk->iv;
-	u8 tmp[bsize + alignmask];
+	u8 tmp[MAX_CIPHER_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
 	u8 *keystream = PTR_ALIGN(tmp + 0, alignmask + 1);
 	u8 *src = walk->src.virt.addr;
 	u8 *dst = walk->dst.virt.addr;
@@ -106,7 +106,7 @@ static int crypto_ctr_crypt_inplace(struct blkcipher_walk *walk,
 	unsigned int nbytes = walk->nbytes;
 	u8 *ctrblk = walk->iv;
 	u8 *src = walk->src.virt.addr;
-	u8 tmp[bsize + alignmask];
+	u8 tmp[MAX_CIPHER_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
 	u8 *keystream = PTR_ALIGN(tmp + 0, alignmask + 1);
 
 	do {
diff --git a/crypto/cts.c b/crypto/cts.c
index 4773c188e6d9..4e28d83ae37d 100644
--- a/crypto/cts.c
+++ b/crypto/cts.c
@@ -40,6 +40,7 @@
  * rfc3962 includes errata information in its Appendix A.
  */
 
+#include <crypto/algapi.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -104,7 +105,7 @@ static int cts_cbc_encrypt(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct skcipher_request *subreq = &rctx->subreq;
 	int bsize = crypto_skcipher_blocksize(tfm);
-	u8 d[bsize * 2] __aligned(__alignof__(u32));
+	u8 d[MAX_CIPHER_BLOCKSIZE * 2] __aligned(__alignof__(u32));
 	struct scatterlist *sg;
 	unsigned int offset;
 	int lastn;
@@ -183,7 +184,7 @@ static int cts_cbc_decrypt(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct skcipher_request *subreq = &rctx->subreq;
 	int bsize = crypto_skcipher_blocksize(tfm);
-	u8 d[bsize * 2] __aligned(__alignof__(u32));
+	u8 d[MAX_CIPHER_BLOCKSIZE * 2] __aligned(__alignof__(u32));
 	struct scatterlist *sg;
 	unsigned int offset;
 	u8 *space;
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 4faa2781c964..466a112a4446 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1134,8 +1134,10 @@ static inline void drbg_dealloc_state(struct drbg_state *drbg)
 	if (!drbg)
 		return;
 	kzfree(drbg->Vbuf);
+	drbg->Vbuf = NULL;
 	drbg->V = NULL;
 	kzfree(drbg->Cbuf);
+	drbg->Cbuf = NULL;
 	drbg->C = NULL;
 	kzfree(drbg->scratchpadbuf);
 	drbg->scratchpadbuf = NULL;
diff --git a/crypto/ecc.c b/crypto/ecc.c
index 9c066b5ac12d..815541309a95 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -515,7 +515,7 @@ static void vli_mmod_fast_256(u64 *result, const u64 *product,
 static bool vli_mmod_fast(u64 *result, u64 *product,
 			  const u64 *curve_prime, unsigned int ndigits)
 {
-	u64 tmp[2 * ndigits];
+	u64 tmp[2 * ECC_MAX_DIGITS];
 
 	switch (ndigits) {
 	case 3:
@@ -536,7 +536,7 @@ static bool vli_mmod_fast(u64 *result, u64 *product,
 static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right,
 			      const u64 *curve_prime, unsigned int ndigits)
 {
-	u64 product[2 * ndigits];
+	u64 product[2 * ECC_MAX_DIGITS];
 
 	vli_mult(product, left, right, ndigits);
 	vli_mmod_fast(result, product, curve_prime, ndigits);
@@ -546,7 +546,7 @@ static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right,
 static void vli_mod_square_fast(u64 *result, const u64 *left,
 				const u64 *curve_prime, unsigned int ndigits)
 {
-	u64 product[2 * ndigits];
+	u64 product[2 * ECC_MAX_DIGITS];
 
 	vli_square(product, left, ndigits);
 	vli_mmod_fast(result, product, curve_prime, ndigits);
@@ -560,8 +560,8 @@ static void vli_mod_square_fast(u64 *result, const u64 *left,
 static void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod,
 			unsigned int ndigits)
 {
-	u64 a[ndigits], b[ndigits];
-	u64 u[ndigits], v[ndigits];
+	u64 a[ECC_MAX_DIGITS], b[ECC_MAX_DIGITS];
+	u64 u[ECC_MAX_DIGITS], v[ECC_MAX_DIGITS];
 	u64 carry;
 	int cmp_result;
 
@@ -649,8 +649,8 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
 				      u64 *curve_prime, unsigned int ndigits)
 {
 	/* t1 = x, t2 = y, t3 = z */
-	u64 t4[ndigits];
-	u64 t5[ndigits];
+	u64 t4[ECC_MAX_DIGITS];
+	u64 t5[ECC_MAX_DIGITS];
 
 	if (vli_is_zero(z1, ndigits))
 		return;
@@ -711,7 +711,7 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
 static void apply_z(u64 *x1, u64 *y1, u64 *z, u64 *curve_prime,
 		    unsigned int ndigits)
 {
-	u64 t1[ndigits];
+	u64 t1[ECC_MAX_DIGITS];
 
 	vli_mod_square_fast(t1, z, curve_prime, ndigits);    /* z^2 */
 	vli_mod_mult_fast(x1, x1, t1, curve_prime, ndigits); /* x1 * z^2 */
@@ -724,7 +724,7 @@ static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
 				u64 *p_initial_z, u64 *curve_prime,
 				unsigned int ndigits)
 {
-	u64 z[ndigits];
+	u64 z[ECC_MAX_DIGITS];
 
 	vli_set(x2, x1, ndigits);
 	vli_set(y2, y1, ndigits);
@@ -750,7 +750,7 @@ static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
 		     unsigned int ndigits)
 {
 	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
-	u64 t5[ndigits];
+	u64 t5[ECC_MAX_DIGITS];
 
 	/* t5 = x2 - x1 */
 	vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
@@ -791,9 +791,9 @@ static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
 		       unsigned int ndigits)
 {
 	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
-	u64 t5[ndigits];
-	u64 t6[ndigits];
-	u64 t7[ndigits];
+	u64 t5[ECC_MAX_DIGITS];
+	u64 t6[ECC_MAX_DIGITS];
+	u64 t7[ECC_MAX_DIGITS];
 
 	/* t5 = x2 - x1 */
 	vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
@@ -846,9 +846,9 @@ static void ecc_point_mult(struct ecc_point *result,
 			   unsigned int ndigits)
 {
 	/* R0 and R1 */
-	u64 rx[2][ndigits];
-	u64 ry[2][ndigits];
-	u64 z[ndigits];
+	u64 rx[2][ECC_MAX_DIGITS];
+	u64 ry[2][ECC_MAX_DIGITS];
+	u64 z[ECC_MAX_DIGITS];
 	int i, nb;
 	int num_bits = vli_num_bits(scalar, ndigits);
 
@@ -943,13 +943,13 @@ int ecc_is_key_valid(unsigned int curve_id, unsigned int ndigits,
 int ecc_gen_privkey(unsigned int curve_id, unsigned int ndigits, u64 *privkey)
 {
 	const struct ecc_curve *curve = ecc_get_curve(curve_id);
-	u64 priv[ndigits];
+	u64 priv[ECC_MAX_DIGITS];
 	unsigned int nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
 	unsigned int nbits = vli_num_bits(curve->n, ndigits);
 	int err;
 
 	/* Check that N is included in Table 1 of FIPS 186-4, section 6.1.1 */
-	if (nbits < 160)
+	if (nbits < 160 || ndigits > ARRAY_SIZE(priv))
 		return -EINVAL;
 
 	/*
@@ -988,10 +988,10 @@ int ecc_make_pub_key(unsigned int curve_id, unsigned int ndigits,
 {
 	int ret = 0;
 	struct ecc_point *pk;
-	u64 priv[ndigits];
+	u64 priv[ECC_MAX_DIGITS];
 	const struct ecc_curve *curve = ecc_get_curve(curve_id);
 
-	if (!private_key || !curve) {
+	if (!private_key || !curve || ndigits > ARRAY_SIZE(priv)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1025,30 +1025,25 @@ int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 {
 	int ret = 0;
 	struct ecc_point *product, *pk;
-	u64 *priv, *rand_z;
+	u64 priv[ECC_MAX_DIGITS];
+	u64 rand_z[ECC_MAX_DIGITS];
+	unsigned int nbytes;
 	const struct ecc_curve *curve = ecc_get_curve(curve_id);
 
-	if (!private_key || !public_key || !curve) {
+	if (!private_key || !public_key || !curve ||
+	    ndigits > ARRAY_SIZE(priv) || ndigits > ARRAY_SIZE(rand_z)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	priv = kmalloc_array(ndigits, sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
 
-	rand_z = kmalloc_array(ndigits, sizeof(*rand_z), GFP_KERNEL);
-	if (!rand_z) {
-		ret = -ENOMEM;
-		goto kfree_out;
-	}
+	get_random_bytes(rand_z, nbytes);
 
 	pk = ecc_alloc_point(ndigits);
 	if (!pk) {
 		ret = -ENOMEM;
-		goto kfree_out;
+		goto out;
 	}
 
 	product = ecc_alloc_point(ndigits);
@@ -1057,8 +1052,6 @@ int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 		goto err_alloc_product;
 	}
 
-	get_random_bytes(rand_z, ndigits << ECC_DIGITS_TO_BYTES_SHIFT);
-
 	ecc_swap_digits(public_key, pk->x, ndigits);
 	ecc_swap_digits(&public_key[ndigits], pk->y, ndigits);
 	ecc_swap_digits(private_key, priv, ndigits);
@@ -1073,9 +1066,6 @@ int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 	ecc_free_point(product);
 err_alloc_product:
 	ecc_free_point(pk);
-kfree_out:
-	kzfree(priv);
-	kzfree(rand_z);
 out:
 	return ret;
 }
diff --git a/crypto/ecc.h b/crypto/ecc.h
index e4fd4492c765..f75a86baa3bd 100644
--- a/crypto/ecc.h
+++ b/crypto/ecc.h
@@ -26,7 +26,9 @@
 #ifndef _CRYPTO_ECC_H
 #define _CRYPTO_ECC_H
 
-#define ECC_MAX_DIGITS	4 /* 256 */
+#define ECC_CURVE_NIST_P192_DIGITS  3
+#define ECC_CURVE_NIST_P256_DIGITS  4
+#define ECC_MAX_DIGITS              ECC_CURVE_NIST_P256_DIGITS
 
 #define ECC_DIGITS_TO_BYTES_SHIFT 3
 
diff --git a/crypto/ecdh.c b/crypto/ecdh.c
index d2ec33f0e098..bf6300175b9c 100644
--- a/crypto/ecdh.c
+++ b/crypto/ecdh.c
@@ -30,8 +30,8 @@ static inline struct ecdh_ctx *ecdh_get_ctx(struct crypto_kpp *tfm)
 static unsigned int ecdh_supported_curve(unsigned int curve_id)
 {
 	switch (curve_id) {
-	case ECC_CURVE_NIST_P192: return 3;
-	case ECC_CURVE_NIST_P256: return 4;
+	case ECC_CURVE_NIST_P192: return ECC_CURVE_NIST_P192_DIGITS;
+	case ECC_CURVE_NIST_P256: return ECC_CURVE_NIST_P256_DIGITS;
 	default: return 0;
 	}
 }
diff --git a/crypto/morus1280.c b/crypto/morus1280.c
new file mode 100644
index 000000000000..6180b2557836
--- /dev/null
+++ b/crypto/morus1280.c
@@ -0,0 +1,549 @@
+/*
+ * The MORUS-1280 Authenticated-Encryption Algorithm
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/morus_common.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+
+#define MORUS1280_WORD_SIZE 8
+#define MORUS1280_BLOCK_SIZE (MORUS_BLOCK_WORDS * MORUS1280_WORD_SIZE)
+#define MORUS1280_BLOCK_ALIGN (__alignof__(__le64))
+#define MORUS1280_ALIGNED(p) IS_ALIGNED((uintptr_t)p, MORUS1280_BLOCK_ALIGN)
+
+struct morus1280_block {
+	u64 words[MORUS_BLOCK_WORDS];
+};
+
+union morus1280_block_in {
+	__le64 words[MORUS_BLOCK_WORDS];
+	u8 bytes[MORUS1280_BLOCK_SIZE];
+};
+
+struct morus1280_state {
+	struct morus1280_block s[MORUS_STATE_BLOCKS];
+};
+
+struct morus1280_ctx {
+	struct morus1280_block key;
+};
+
+struct morus1280_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_chunk)(struct morus1280_state *state,
+			    u8 *dst, const u8 *src, unsigned int size);
+};
+
+static const struct morus1280_block crypto_morus1280_const[1] = {
+	{ .words = {
+		U64_C(0x0d08050302010100),
+		U64_C(0x6279e99059372215),
+		U64_C(0xf12fc26d55183ddb),
+		U64_C(0xdd28b57342311120),
+	} },
+};
+
+static void crypto_morus1280_round(struct morus1280_block *b0,
+				   struct morus1280_block *b1,
+				   struct morus1280_block *b2,
+				   struct morus1280_block *b3,
+				   struct morus1280_block *b4,
+				   const struct morus1280_block *m,
+				   unsigned int b, unsigned int w)
+{
+	unsigned int i;
+	struct morus1280_block tmp;
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		b0->words[i] ^= b1->words[i] & b2->words[i];
+		b0->words[i] ^= b3->words[i];
+		b0->words[i] ^= m->words[i];
+		b0->words[i] = rol64(b0->words[i], b);
+	}
+
+	tmp = *b3;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		b3->words[(i + w) % MORUS_BLOCK_WORDS] = tmp.words[i];
+}
+
+static void crypto_morus1280_update(struct morus1280_state *state,
+				    const struct morus1280_block *m)
+{
+	static const struct morus1280_block z = {};
+
+	struct morus1280_block *s = state->s;
+
+	crypto_morus1280_round(&s[0], &s[1], &s[2], &s[3], &s[4], &z, 13, 1);
+	crypto_morus1280_round(&s[1], &s[2], &s[3], &s[4], &s[0], m,  46, 2);
+	crypto_morus1280_round(&s[2], &s[3], &s[4], &s[0], &s[1], m,  38, 3);
+	crypto_morus1280_round(&s[3], &s[4], &s[0], &s[1], &s[2], m,   7, 2);
+	crypto_morus1280_round(&s[4], &s[0], &s[1], &s[2], &s[3], m,   4, 1);
+}
+
+static void crypto_morus1280_load_a(struct morus1280_block *dst, const u8 *src)
+{
+	unsigned int i;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		dst->words[i] = le64_to_cpu(*(const __le64 *)src);
+		src += MORUS1280_WORD_SIZE;
+	}
+}
+
+static void crypto_morus1280_load_u(struct morus1280_block *dst, const u8 *src)
+{
+	unsigned int i;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		dst->words[i] = get_unaligned_le64(src);
+		src += MORUS1280_WORD_SIZE;
+	}
+}
+
+static void crypto_morus1280_load(struct morus1280_block *dst, const u8 *src)
+{
+	if (MORUS1280_ALIGNED(src))
+		crypto_morus1280_load_a(dst, src);
+	else
+		crypto_morus1280_load_u(dst, src);
+}
+
+static void crypto_morus1280_store_a(u8 *dst, const struct morus1280_block *src)
+{
+	unsigned int i;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		*(__le64 *)dst = cpu_to_le64(src->words[i]);
+		dst += MORUS1280_WORD_SIZE;
+	}
+}
+
+static void crypto_morus1280_store_u(u8 *dst, const struct morus1280_block *src)
+{
+	unsigned int i;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		put_unaligned_le64(src->words[i], dst);
+		dst += MORUS1280_WORD_SIZE;
+	}
+}
+
+static void crypto_morus1280_store(u8 *dst, const struct morus1280_block *src)
+{
+	if (MORUS1280_ALIGNED(dst))
+		crypto_morus1280_store_a(dst, src);
+	else
+		crypto_morus1280_store_u(dst, src);
+}
+
+static void crypto_morus1280_ad(struct morus1280_state *state, const u8 *src,
+				unsigned int size)
+{
+	struct morus1280_block m;
+
+	if (MORUS1280_ALIGNED(src)) {
+		while (size >= MORUS1280_BLOCK_SIZE) {
+			crypto_morus1280_load_a(&m, src);
+			crypto_morus1280_update(state, &m);
+
+			size -= MORUS1280_BLOCK_SIZE;
+			src += MORUS1280_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= MORUS1280_BLOCK_SIZE) {
+			crypto_morus1280_load_u(&m, src);
+			crypto_morus1280_update(state, &m);
+
+			size -= MORUS1280_BLOCK_SIZE;
+			src += MORUS1280_BLOCK_SIZE;
+		}
+	}
+}
+
+static void crypto_morus1280_core(const struct morus1280_state *state,
+				  struct morus1280_block *blk)
+{
+	unsigned int i;
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		blk->words[(i + 3) % MORUS_BLOCK_WORDS] ^= state->s[1].words[i];
+
+        for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		blk->words[i] ^= state->s[0].words[i];
+		blk->words[i] ^= state->s[2].words[i] & state->s[3].words[i];
+	}
+}
+
+static void crypto_morus1280_encrypt_chunk(struct morus1280_state *state,
+					   u8 *dst, const u8 *src,
+					   unsigned int size)
+{
+	struct morus1280_block c, m;
+
+	if (MORUS1280_ALIGNED(src) && MORUS1280_ALIGNED(dst)) {
+		while (size >= MORUS1280_BLOCK_SIZE) {
+			crypto_morus1280_load_a(&m, src);
+			c = m;
+			crypto_morus1280_core(state, &c);
+			crypto_morus1280_store_a(dst, &c);
+			crypto_morus1280_update(state, &m);
+
+			src += MORUS1280_BLOCK_SIZE;
+			dst += MORUS1280_BLOCK_SIZE;
+			size -= MORUS1280_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= MORUS1280_BLOCK_SIZE) {
+			crypto_morus1280_load_u(&m, src);
+			c = m;
+			crypto_morus1280_core(state, &c);
+			crypto_morus1280_store_u(dst, &c);
+			crypto_morus1280_update(state, &m);
+
+			src += MORUS1280_BLOCK_SIZE;
+			dst += MORUS1280_BLOCK_SIZE;
+			size -= MORUS1280_BLOCK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union morus1280_block_in tail;
+
+		memcpy(tail.bytes, src, size);
+		memset(tail.bytes + size, 0, MORUS1280_BLOCK_SIZE - size);
+
+		crypto_morus1280_load_a(&m, tail.bytes);
+		c = m;
+		crypto_morus1280_core(state, &c);
+		crypto_morus1280_store_a(tail.bytes, &c);
+		crypto_morus1280_update(state, &m);
+
+		memcpy(dst, tail.bytes, size);
+	}
+}
+
+static void crypto_morus1280_decrypt_chunk(struct morus1280_state *state,
+					   u8 *dst, const u8 *src,
+					   unsigned int size)
+{
+	struct morus1280_block m;
+
+	if (MORUS1280_ALIGNED(src) && MORUS1280_ALIGNED(dst)) {
+		while (size >= MORUS1280_BLOCK_SIZE) {
+			crypto_morus1280_load_a(&m, src);
+			crypto_morus1280_core(state, &m);
+			crypto_morus1280_store_a(dst, &m);
+			crypto_morus1280_update(state, &m);
+
+			src += MORUS1280_BLOCK_SIZE;
+			dst += MORUS1280_BLOCK_SIZE;
+			size -= MORUS1280_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= MORUS1280_BLOCK_SIZE) {
+			crypto_morus1280_load_u(&m, src);
+			crypto_morus1280_core(state, &m);
+			crypto_morus1280_store_u(dst, &m);
+			crypto_morus1280_update(state, &m);
+
+			src += MORUS1280_BLOCK_SIZE;
+			dst += MORUS1280_BLOCK_SIZE;
+			size -= MORUS1280_BLOCK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union morus1280_block_in tail;
+
+		memcpy(tail.bytes, src, size);
+		memset(tail.bytes + size, 0, MORUS1280_BLOCK_SIZE - size);
+
+		crypto_morus1280_load_a(&m, tail.bytes);
+		crypto_morus1280_core(state, &m);
+		crypto_morus1280_store_a(tail.bytes, &m);
+		memset(tail.bytes + size, 0, MORUS1280_BLOCK_SIZE - size);
+		crypto_morus1280_load_a(&m, tail.bytes);
+		crypto_morus1280_update(state, &m);
+
+		memcpy(dst, tail.bytes, size);
+	}
+}
+
+static void crypto_morus1280_init(struct morus1280_state *state,
+				  const struct morus1280_block *key,
+				  const u8 *iv)
+{
+	static const struct morus1280_block z = {};
+
+	union morus1280_block_in tmp;
+	unsigned int i;
+
+	memcpy(tmp.bytes, iv, MORUS_NONCE_SIZE);
+	memset(tmp.bytes + MORUS_NONCE_SIZE, 0,
+	       MORUS1280_BLOCK_SIZE - MORUS_NONCE_SIZE);
+
+	crypto_morus1280_load(&state->s[0], tmp.bytes);
+	state->s[1] = *key;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		state->s[2].words[i] = U64_C(0xFFFFFFFFFFFFFFFF);
+	state->s[3] = z;
+	state->s[4] = crypto_morus1280_const[0];
+
+	for (i = 0; i < 16; i++)
+		crypto_morus1280_update(state, &z);
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		state->s[1].words[i] ^= key->words[i];
+}
+
+static void crypto_morus1280_process_ad(struct morus1280_state *state,
+					struct scatterlist *sg_src,
+					unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	struct morus1280_block m;
+	union morus1280_block_in buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= MORUS1280_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = MORUS1280_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+
+				crypto_morus1280_load_a(&m, buf.bytes);
+				crypto_morus1280_update(state, &m);
+
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			crypto_morus1280_ad(state, src, left);
+			src += left & ~(MORUS1280_BLOCK_SIZE - 1);
+			left &= MORUS1280_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+
+		pos += left;
+		assoclen -= size;
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, MORUS1280_BLOCK_SIZE - pos);
+
+		crypto_morus1280_load_a(&m, buf.bytes);
+		crypto_morus1280_update(state, &m);
+	}
+}
+
+static void crypto_morus1280_process_crypt(struct morus1280_state *state,
+					   struct aead_request *req,
+					   const struct morus1280_ops *ops)
+{
+	struct skcipher_walk walk;
+	u8 *dst;
+	const u8 *src;
+
+	ops->skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+
+		ops->crypt_chunk(state, dst, src, walk.nbytes);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+static void crypto_morus1280_final(struct morus1280_state *state,
+				   struct morus1280_block *tag_xor,
+				   u64 assoclen, u64 cryptlen)
+{
+	u64 assocbits = assoclen * 8;
+	u64 cryptbits = cryptlen * 8;
+
+	struct morus1280_block tmp;
+	unsigned int i;
+
+	tmp.words[0] = cpu_to_le64(assocbits);
+	tmp.words[1] = cpu_to_le64(cryptbits);
+	tmp.words[2] = 0;
+	tmp.words[3] = 0;
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		state->s[4].words[i] ^= state->s[0].words[i];
+
+	for (i = 0; i < 10; i++)
+		crypto_morus1280_update(state, &tmp);
+
+	crypto_morus1280_core(state, tag_xor);
+}
+
+static int crypto_morus1280_setkey(struct crypto_aead *aead, const u8 *key,
+				   unsigned int keylen)
+{
+	struct morus1280_ctx *ctx = crypto_aead_ctx(aead);
+	union morus1280_block_in tmp;
+
+	if (keylen == MORUS1280_BLOCK_SIZE)
+		crypto_morus1280_load(&ctx->key, key);
+	else if (keylen == MORUS1280_BLOCK_SIZE / 2) {
+		memcpy(tmp.bytes, key, keylen);
+		memcpy(tmp.bytes + keylen, key, keylen);
+
+		crypto_morus1280_load(&ctx->key, tmp.bytes);
+	} else {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int crypto_morus1280_setauthsize(struct crypto_aead *tfm,
+					unsigned int authsize)
+{
+	return (authsize <= MORUS_MAX_AUTH_SIZE) ? 0 : -EINVAL;
+}
+
+static void crypto_morus1280_crypt(struct aead_request *req,
+				   struct morus1280_block *tag_xor,
+				   unsigned int cryptlen,
+				   const struct morus1280_ops *ops)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus1280_ctx *ctx = crypto_aead_ctx(tfm);
+	struct morus1280_state state;
+
+	crypto_morus1280_init(&state, &ctx->key, req->iv);
+	crypto_morus1280_process_ad(&state, req->src, req->assoclen);
+	crypto_morus1280_process_crypt(&state, req, ops);
+	crypto_morus1280_final(&state, tag_xor, req->assoclen, cryptlen);
+}
+
+static int crypto_morus1280_encrypt(struct aead_request *req)
+{
+	static const struct morus1280_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_chunk = crypto_morus1280_encrypt_chunk,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus1280_block tag = {};
+	union morus1280_block_in tag_out;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_morus1280_crypt(req, &tag, cryptlen, &ops);
+	crypto_morus1280_store(tag_out.bytes, &tag);
+
+	scatterwalk_map_and_copy(tag_out.bytes, req->dst,
+				 req->assoclen + cryptlen, authsize, 1);
+	return 0;
+}
+
+static int crypto_morus1280_decrypt(struct aead_request *req)
+{
+	static const struct morus1280_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_chunk = crypto_morus1280_decrypt_chunk,
+	};
+	static const u8 zeros[MORUS1280_BLOCK_SIZE] = {};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	union morus1280_block_in tag_in;
+	struct morus1280_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag_in.bytes, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
+
+	crypto_morus1280_load(&tag, tag_in.bytes);
+	crypto_morus1280_crypt(req, &tag, cryptlen, &ops);
+	crypto_morus1280_store(tag_in.bytes, &tag);
+
+	return crypto_memneq(tag_in.bytes, zeros, authsize) ? -EBADMSG : 0;
+}
+
+static int crypto_morus1280_init_tfm(struct crypto_aead *tfm)
+{
+	return 0;
+}
+
+static void crypto_morus1280_exit_tfm(struct crypto_aead *tfm)
+{
+}
+
+static struct aead_alg crypto_morus1280_alg = {
+	.setkey = crypto_morus1280_setkey,
+	.setauthsize = crypto_morus1280_setauthsize,
+	.encrypt = crypto_morus1280_encrypt,
+	.decrypt = crypto_morus1280_decrypt,
+	.init = crypto_morus1280_init_tfm,
+	.exit = crypto_morus1280_exit_tfm,
+
+	.ivsize = MORUS_NONCE_SIZE,
+	.maxauthsize = MORUS_MAX_AUTH_SIZE,
+	.chunksize = MORUS1280_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct morus1280_ctx),
+		.cra_alignmask = 0,
+
+		.cra_priority = 100,
+
+		.cra_name = "morus1280",
+		.cra_driver_name = "morus1280-generic",
+
+		.cra_module = THIS_MODULE,
+	}
+};
+
+
+static int __init crypto_morus1280_module_init(void)
+{
+	return crypto_register_aead(&crypto_morus1280_alg);
+}
+
+static void __exit crypto_morus1280_module_exit(void)
+{
+	crypto_unregister_aead(&crypto_morus1280_alg);
+}
+
+module_init(crypto_morus1280_module_init);
+module_exit(crypto_morus1280_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("MORUS-1280 AEAD algorithm");
+MODULE_ALIAS_CRYPTO("morus1280");
+MODULE_ALIAS_CRYPTO("morus1280-generic");
diff --git a/crypto/morus640.c b/crypto/morus640.c
new file mode 100644
index 000000000000..9fbcde307daf
--- /dev/null
+++ b/crypto/morus640.c
@@ -0,0 +1,544 @@
+/*
+ * The MORUS-640 Authenticated-Encryption Algorithm
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/morus_common.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+
+#define MORUS640_WORD_SIZE 4
+#define MORUS640_BLOCK_SIZE (MORUS_BLOCK_WORDS * MORUS640_WORD_SIZE)
+#define MORUS640_BLOCK_ALIGN (__alignof__(__le32))
+#define MORUS640_ALIGNED(p) IS_ALIGNED((uintptr_t)p, MORUS640_BLOCK_ALIGN)
+
+struct morus640_block {
+	u32 words[MORUS_BLOCK_WORDS];
+};
+
+union morus640_block_in {
+	__le32 words[MORUS_BLOCK_WORDS];
+	u8 bytes[MORUS640_BLOCK_SIZE];
+};
+
+struct morus640_state {
+	struct morus640_block s[MORUS_STATE_BLOCKS];
+};
+
+struct morus640_ctx {
+	struct morus640_block key;
+};
+
+struct morus640_ops {
+	int (*skcipher_walk_init)(struct skcipher_walk *walk,
+				  struct aead_request *req, bool atomic);
+
+	void (*crypt_chunk)(struct morus640_state *state,
+			    u8 *dst, const u8 *src, unsigned int size);
+};
+
+static const struct morus640_block crypto_morus640_const[2] = {
+	{ .words = {
+		U32_C(0x02010100),
+		U32_C(0x0d080503),
+		U32_C(0x59372215),
+		U32_C(0x6279e990),
+	} },
+	{ .words = {
+		U32_C(0x55183ddb),
+		U32_C(0xf12fc26d),
+		U32_C(0x42311120),
+		U32_C(0xdd28b573),
+	} },
+};
+
+static void crypto_morus640_round(struct morus640_block *b0,
+				  struct morus640_block *b1,
+				  struct morus640_block *b2,
+				  struct morus640_block *b3,
+				  struct morus640_block *b4,
+				  const struct morus640_block *m,
+				  unsigned int b, unsigned int w)
+{
+	unsigned int i;
+	struct morus640_block tmp;
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		b0->words[i] ^= b1->words[i] & b2->words[i];
+		b0->words[i] ^= b3->words[i];
+		b0->words[i] ^= m->words[i];
+		b0->words[i] = rol32(b0->words[i], b);
+	}
+
+	tmp = *b3;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		b3->words[(i + w) % MORUS_BLOCK_WORDS] = tmp.words[i];
+}
+
+static void crypto_morus640_update(struct morus640_state *state,
+				   const struct morus640_block *m)
+{
+	static const struct morus640_block z = {};
+
+	struct morus640_block *s = state->s;
+
+	crypto_morus640_round(&s[0], &s[1], &s[2], &s[3], &s[4], &z,  5, 1);
+	crypto_morus640_round(&s[1], &s[2], &s[3], &s[4], &s[0], m,  31, 2);
+	crypto_morus640_round(&s[2], &s[3], &s[4], &s[0], &s[1], m,   7, 3);
+	crypto_morus640_round(&s[3], &s[4], &s[0], &s[1], &s[2], m,  22, 2);
+	crypto_morus640_round(&s[4], &s[0], &s[1], &s[2], &s[3], m,  13, 1);
+}
+
+static void crypto_morus640_load_a(struct morus640_block *dst, const u8 *src)
+{
+	unsigned int i;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		dst->words[i] = le32_to_cpu(*(const __le32 *)src);
+		src += MORUS640_WORD_SIZE;
+	}
+}
+
+static void crypto_morus640_load_u(struct morus640_block *dst, const u8 *src)
+{
+	unsigned int i;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		dst->words[i] = get_unaligned_le32(src);
+		src += MORUS640_WORD_SIZE;
+	}
+}
+
+static void crypto_morus640_load(struct morus640_block *dst, const u8 *src)
+{
+	if (MORUS640_ALIGNED(src))
+		crypto_morus640_load_a(dst, src);
+	else
+		crypto_morus640_load_u(dst, src);
+}
+
+static void crypto_morus640_store_a(u8 *dst, const struct morus640_block *src)
+{
+	unsigned int i;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		*(__le32 *)dst = cpu_to_le32(src->words[i]);
+		dst += MORUS640_WORD_SIZE;
+	}
+}
+
+static void crypto_morus640_store_u(u8 *dst, const struct morus640_block *src)
+{
+	unsigned int i;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		put_unaligned_le32(src->words[i], dst);
+		dst += MORUS640_WORD_SIZE;
+	}
+}
+
+static void crypto_morus640_store(u8 *dst, const struct morus640_block *src)
+{
+	if (MORUS640_ALIGNED(dst))
+		crypto_morus640_store_a(dst, src);
+	else
+		crypto_morus640_store_u(dst, src);
+}
+
+static void crypto_morus640_ad(struct morus640_state *state, const u8 *src,
+			       unsigned int size)
+{
+	struct morus640_block m;
+
+	if (MORUS640_ALIGNED(src)) {
+		while (size >= MORUS640_BLOCK_SIZE) {
+			crypto_morus640_load_a(&m, src);
+			crypto_morus640_update(state, &m);
+
+			size -= MORUS640_BLOCK_SIZE;
+			src += MORUS640_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= MORUS640_BLOCK_SIZE) {
+			crypto_morus640_load_u(&m, src);
+			crypto_morus640_update(state, &m);
+
+			size -= MORUS640_BLOCK_SIZE;
+			src += MORUS640_BLOCK_SIZE;
+		}
+	}
+}
+
+static void crypto_morus640_core(const struct morus640_state *state,
+				 struct morus640_block *blk)
+{
+	unsigned int i;
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		blk->words[(i + 3) % MORUS_BLOCK_WORDS] ^= state->s[1].words[i];
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++) {
+		blk->words[i] ^= state->s[0].words[i];
+		blk->words[i] ^= state->s[2].words[i] & state->s[3].words[i];
+	}
+}
+
+static void crypto_morus640_encrypt_chunk(struct morus640_state *state, u8 *dst,
+					  const u8 *src, unsigned int size)
+{
+	struct morus640_block c, m;
+
+	if (MORUS640_ALIGNED(src) && MORUS640_ALIGNED(dst)) {
+		while (size >= MORUS640_BLOCK_SIZE) {
+			crypto_morus640_load_a(&m, src);
+			c = m;
+			crypto_morus640_core(state, &c);
+			crypto_morus640_store_a(dst, &c);
+			crypto_morus640_update(state, &m);
+
+			src += MORUS640_BLOCK_SIZE;
+			dst += MORUS640_BLOCK_SIZE;
+			size -= MORUS640_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= MORUS640_BLOCK_SIZE) {
+			crypto_morus640_load_u(&m, src);
+			c = m;
+			crypto_morus640_core(state, &c);
+			crypto_morus640_store_u(dst, &c);
+			crypto_morus640_update(state, &m);
+
+			src += MORUS640_BLOCK_SIZE;
+			dst += MORUS640_BLOCK_SIZE;
+			size -= MORUS640_BLOCK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union morus640_block_in tail;
+
+		memcpy(tail.bytes, src, size);
+		memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size);
+
+		crypto_morus640_load_a(&m, tail.bytes);
+		c = m;
+		crypto_morus640_core(state, &c);
+		crypto_morus640_store_a(tail.bytes, &c);
+		crypto_morus640_update(state, &m);
+
+		memcpy(dst, tail.bytes, size);
+	}
+}
+
+static void crypto_morus640_decrypt_chunk(struct morus640_state *state, u8 *dst,
+					  const u8 *src, unsigned int size)
+{
+	struct morus640_block m;
+
+	if (MORUS640_ALIGNED(src) && MORUS640_ALIGNED(dst)) {
+		while (size >= MORUS640_BLOCK_SIZE) {
+			crypto_morus640_load_a(&m, src);
+			crypto_morus640_core(state, &m);
+			crypto_morus640_store_a(dst, &m);
+			crypto_morus640_update(state, &m);
+
+			src += MORUS640_BLOCK_SIZE;
+			dst += MORUS640_BLOCK_SIZE;
+			size -= MORUS640_BLOCK_SIZE;
+		}
+	} else {
+		while (size >= MORUS640_BLOCK_SIZE) {
+			crypto_morus640_load_u(&m, src);
+			crypto_morus640_core(state, &m);
+			crypto_morus640_store_u(dst, &m);
+			crypto_morus640_update(state, &m);
+
+			src += MORUS640_BLOCK_SIZE;
+			dst += MORUS640_BLOCK_SIZE;
+			size -= MORUS640_BLOCK_SIZE;
+		}
+	}
+
+	if (size > 0) {
+		union morus640_block_in tail;
+
+		memcpy(tail.bytes, src, size);
+
+		crypto_morus640_load_a(&m, src);
+		crypto_morus640_core(state, &m);
+		crypto_morus640_store_a(tail.bytes, &m);
+		memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size);
+		crypto_morus640_load_a(&m, tail.bytes);
+		crypto_morus640_update(state, &m);
+
+		memcpy(dst, tail.bytes, size);
+	}
+}
+
+static void crypto_morus640_init(struct morus640_state *state,
+				 const struct morus640_block *key,
+				 const u8 *iv)
+{
+	static const struct morus640_block z = {};
+
+	unsigned int i;
+
+	crypto_morus640_load(&state->s[0], iv);
+	state->s[1] = *key;
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		state->s[2].words[i] = U32_C(0xFFFFFFFF);
+	state->s[3] = crypto_morus640_const[0];
+	state->s[4] = crypto_morus640_const[1];
+
+	for (i = 0; i < 16; i++)
+		crypto_morus640_update(state, &z);
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		state->s[1].words[i] ^= key->words[i];
+}
+
+static void crypto_morus640_process_ad(struct morus640_state *state,
+				       struct scatterlist *sg_src,
+				       unsigned int assoclen)
+{
+	struct scatter_walk walk;
+	struct morus640_block m;
+	union morus640_block_in buf;
+	unsigned int pos = 0;
+
+	scatterwalk_start(&walk, sg_src);
+	while (assoclen != 0) {
+		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int left = size;
+		void *mapped = scatterwalk_map(&walk);
+		const u8 *src = (const u8 *)mapped;
+
+		if (pos + size >= MORUS640_BLOCK_SIZE) {
+			if (pos > 0) {
+				unsigned int fill = MORUS640_BLOCK_SIZE - pos;
+				memcpy(buf.bytes + pos, src, fill);
+
+				crypto_morus640_load_a(&m, buf.bytes);
+				crypto_morus640_update(state, &m);
+
+				pos = 0;
+				left -= fill;
+				src += fill;
+			}
+
+			crypto_morus640_ad(state, src, left);
+			src += left & ~(MORUS640_BLOCK_SIZE - 1);
+			left &= MORUS640_BLOCK_SIZE - 1;
+		}
+
+		memcpy(buf.bytes + pos, src, left);
+
+		pos += left;
+		assoclen -= size;
+		scatterwalk_unmap(mapped);
+		scatterwalk_advance(&walk, size);
+		scatterwalk_done(&walk, 0, assoclen);
+	}
+
+	if (pos > 0) {
+		memset(buf.bytes + pos, 0, MORUS640_BLOCK_SIZE - pos);
+
+		crypto_morus640_load_a(&m, buf.bytes);
+		crypto_morus640_update(state, &m);
+	}
+}
+
+static void crypto_morus640_process_crypt(struct morus640_state *state,
+					  struct aead_request *req,
+					  const struct morus640_ops *ops)
+{
+	struct skcipher_walk walk;
+	u8 *dst;
+	const u8 *src;
+
+	ops->skcipher_walk_init(&walk, req, false);
+
+	while (walk.nbytes) {
+		src = walk.src.virt.addr;
+		dst = walk.dst.virt.addr;
+
+		ops->crypt_chunk(state, dst, src, walk.nbytes);
+
+		skcipher_walk_done(&walk, 0);
+	}
+}
+
+static void crypto_morus640_final(struct morus640_state *state,
+				  struct morus640_block *tag_xor,
+				  u64 assoclen, u64 cryptlen)
+{
+	u64 assocbits = assoclen * 8;
+	u64 cryptbits = cryptlen * 8;
+
+	u32 assocbits_lo = (u32)assocbits;
+	u32 assocbits_hi = (u32)(assocbits >> 32);
+	u32 cryptbits_lo = (u32)cryptbits;
+	u32 cryptbits_hi = (u32)(cryptbits >> 32);
+
+	struct morus640_block tmp;
+	unsigned int i;
+
+	tmp.words[0] = cpu_to_le32(assocbits_lo);
+	tmp.words[1] = cpu_to_le32(assocbits_hi);
+	tmp.words[2] = cpu_to_le32(cryptbits_lo);
+	tmp.words[3] = cpu_to_le32(cryptbits_hi);
+
+	for (i = 0; i < MORUS_BLOCK_WORDS; i++)
+		state->s[4].words[i] ^= state->s[0].words[i];
+
+	for (i = 0; i < 10; i++)
+		crypto_morus640_update(state, &tmp);
+
+	crypto_morus640_core(state, tag_xor);
+}
+
+static int crypto_morus640_setkey(struct crypto_aead *aead, const u8 *key,
+				  unsigned int keylen)
+{
+	struct morus640_ctx *ctx = crypto_aead_ctx(aead);
+
+	if (keylen != MORUS640_BLOCK_SIZE) {
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	crypto_morus640_load(&ctx->key, key);
+	return 0;
+}
+
+static int crypto_morus640_setauthsize(struct crypto_aead *tfm,
+				       unsigned int authsize)
+{
+	return (authsize <= MORUS_MAX_AUTH_SIZE) ? 0 : -EINVAL;
+}
+
+static void crypto_morus640_crypt(struct aead_request *req,
+				  struct morus640_block *tag_xor,
+				  unsigned int cryptlen,
+				  const struct morus640_ops *ops)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus640_ctx *ctx = crypto_aead_ctx(tfm);
+	struct morus640_state state;
+
+	crypto_morus640_init(&state, &ctx->key, req->iv);
+	crypto_morus640_process_ad(&state, req->src, req->assoclen);
+	crypto_morus640_process_crypt(&state, req, ops);
+	crypto_morus640_final(&state, tag_xor, req->assoclen, cryptlen);
+}
+
+static int crypto_morus640_encrypt(struct aead_request *req)
+{
+	static const struct morus640_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_encrypt,
+		.crypt_chunk = crypto_morus640_encrypt_chunk,
+	};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct morus640_block tag = {};
+	union morus640_block_in tag_out;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen;
+
+	crypto_morus640_crypt(req, &tag, cryptlen, &ops);
+	crypto_morus640_store(tag_out.bytes, &tag);
+
+	scatterwalk_map_and_copy(tag_out.bytes, req->dst,
+				 req->assoclen + cryptlen, authsize, 1);
+	return 0;
+}
+
+static int crypto_morus640_decrypt(struct aead_request *req)
+{
+	static const struct morus640_ops ops = {
+		.skcipher_walk_init = skcipher_walk_aead_decrypt,
+		.crypt_chunk = crypto_morus640_decrypt_chunk,
+	};
+	static const u8 zeros[MORUS640_BLOCK_SIZE] = {};
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	union morus640_block_in tag_in;
+	struct morus640_block tag;
+	unsigned int authsize = crypto_aead_authsize(tfm);
+	unsigned int cryptlen = req->cryptlen - authsize;
+
+	scatterwalk_map_and_copy(tag_in.bytes, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
+
+	crypto_morus640_load(&tag, tag_in.bytes);
+	crypto_morus640_crypt(req, &tag, cryptlen, &ops);
+	crypto_morus640_store(tag_in.bytes, &tag);
+
+	return crypto_memneq(tag_in.bytes, zeros, authsize) ? -EBADMSG : 0;
+}
+
+static int crypto_morus640_init_tfm(struct crypto_aead *tfm)
+{
+	return 0;
+}
+
+static void crypto_morus640_exit_tfm(struct crypto_aead *tfm)
+{
+}
+
+static struct aead_alg crypto_morus640_alg = {
+	.setkey = crypto_morus640_setkey,
+	.setauthsize = crypto_morus640_setauthsize,
+	.encrypt = crypto_morus640_encrypt,
+	.decrypt = crypto_morus640_decrypt,
+	.init = crypto_morus640_init_tfm,
+	.exit = crypto_morus640_exit_tfm,
+
+	.ivsize = MORUS_NONCE_SIZE,
+	.maxauthsize = MORUS_MAX_AUTH_SIZE,
+	.chunksize = MORUS640_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct morus640_ctx),
+		.cra_alignmask = 0,
+
+		.cra_priority = 100,
+
+		.cra_name = "morus640",
+		.cra_driver_name = "morus640-generic",
+
+		.cra_module = THIS_MODULE,
+	}
+};
+
+static int __init crypto_morus640_module_init(void)
+{
+	return crypto_register_aead(&crypto_morus640_alg);
+}
+
+static void __exit crypto_morus640_module_exit(void)
+{
+	crypto_unregister_aead(&crypto_morus640_alg);
+}
+
+module_init(crypto_morus640_module_init);
+module_exit(crypto_morus640_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
+MODULE_DESCRIPTION("MORUS-640 AEAD algorithm");
+MODULE_ALIAS_CRYPTO("morus640");
+MODULE_ALIAS_CRYPTO("morus640-generic");
diff --git a/crypto/pcbc.c b/crypto/pcbc.c
index d9e45a958720..ef802f6e9642 100644
--- a/crypto/pcbc.c
+++ b/crypto/pcbc.c
@@ -14,6 +14,7 @@
  *
  */
 
+#include <crypto/algapi.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -72,7 +73,7 @@ static int crypto_pcbc_encrypt_inplace(struct skcipher_request *req,
 	unsigned int nbytes = walk->nbytes;
 	u8 *src = walk->src.virt.addr;
 	u8 *iv = walk->iv;
-	u8 tmpbuf[bsize];
+	u8 tmpbuf[MAX_CIPHER_BLOCKSIZE];
 
 	do {
 		memcpy(tmpbuf, src, bsize);
@@ -144,7 +145,7 @@ static int crypto_pcbc_decrypt_inplace(struct skcipher_request *req,
 	unsigned int nbytes = walk->nbytes;
 	u8 *src = walk->src.virt.addr;
 	u8 *iv = walk->iv;
-	u8 tmpbuf[bsize] __aligned(__alignof__(u32));
+	u8 tmpbuf[MAX_CIPHER_BLOCKSIZE] __aligned(__alignof__(u32));
 
 	do {
 		memcpy(tmpbuf, src, bsize);
diff --git a/crypto/proc.c b/crypto/proc.c
index 822fcef6d91c..f4eb6139973e 100644
--- a/crypto/proc.c
+++ b/crypto/proc.c
@@ -94,21 +94,9 @@ static const struct seq_operations crypto_seq_ops = {
 	.show		= c_show
 };
 
-static int crypto_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &crypto_seq_ops);
-}
-        
-static const struct file_operations proc_crypto_ops = {
-	.open		= crypto_info_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release
-};
-
 void __init crypto_init_proc(void)
 {
-	proc_create("crypto", 0, NULL, &proc_crypto_ops);
+	proc_create_seq("crypto", 0, NULL, &crypto_seq_ops);
 }
 
 void __exit crypto_exit_proc(void)
diff --git a/crypto/rsa.c b/crypto/rsa.c
index b067f3a93880..4167980c243d 100644
--- a/crypto/rsa.c
+++ b/crypto/rsa.c
@@ -215,7 +215,6 @@ static int rsa_verify(struct akcipher_request *req)
 		goto err_free_m;
 	}
 
-	ret = -ENOMEM;
 	s = mpi_read_raw_from_sgl(req->src, req->src_len);
 	if (!s) {
 		ret = -ENOMEM;
diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c
index 5074006a56c3..8c77bc78a09f 100644
--- a/crypto/salsa20_generic.c
+++ b/crypto/salsa20_generic.c
@@ -21,9 +21,17 @@
 
 #include <asm/unaligned.h>
 #include <crypto/internal/skcipher.h>
-#include <crypto/salsa20.h>
 #include <linux/module.h>
 
+#define SALSA20_IV_SIZE        8
+#define SALSA20_MIN_KEY_SIZE  16
+#define SALSA20_MAX_KEY_SIZE  32
+#define SALSA20_BLOCK_SIZE    64
+
+struct salsa20_ctx {
+	u32 initial_state[16];
+};
+
 static void salsa20_block(u32 *state, __le32 *stream)
 {
 	u32 x[16];
@@ -93,16 +101,15 @@ static void salsa20_docrypt(u32 *state, u8 *dst, const u8 *src,
 	}
 }
 
-void crypto_salsa20_init(u32 *state, const struct salsa20_ctx *ctx,
+static void salsa20_init(u32 *state, const struct salsa20_ctx *ctx,
 			 const u8 *iv)
 {
 	memcpy(state, ctx->initial_state, sizeof(ctx->initial_state));
 	state[6] = get_unaligned_le32(iv + 0);
 	state[7] = get_unaligned_le32(iv + 4);
 }
-EXPORT_SYMBOL_GPL(crypto_salsa20_init);
 
-int crypto_salsa20_setkey(struct crypto_skcipher *tfm, const u8 *key,
+static int salsa20_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			  unsigned int keysize)
 {
 	static const char sigma[16] = "expand 32-byte k";
@@ -143,7 +150,6 @@ int crypto_salsa20_setkey(struct crypto_skcipher *tfm, const u8 *key,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(crypto_salsa20_setkey);
 
 static int salsa20_crypt(struct skcipher_request *req)
 {
@@ -155,7 +161,7 @@ static int salsa20_crypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	crypto_salsa20_init(state, ctx, walk.iv);
+	salsa20_init(state, ctx, walk.iv);
 
 	while (walk.nbytes > 0) {
 		unsigned int nbytes = walk.nbytes;
@@ -183,7 +189,7 @@ static struct skcipher_alg alg = {
 	.max_keysize		= SALSA20_MAX_KEY_SIZE,
 	.ivsize			= SALSA20_IV_SIZE,
 	.chunksize		= SALSA20_BLOCK_SIZE,
-	.setkey			= crypto_salsa20_setkey,
+	.setkey			= salsa20_setkey,
 	.encrypt		= salsa20_crypt,
 	.decrypt		= salsa20_crypt,
 };
diff --git a/crypto/sm4_generic.c b/crypto/sm4_generic.c
index f537a2766c55..c18eebfd5edd 100644
--- a/crypto/sm4_generic.c
+++ b/crypto/sm4_generic.c
@@ -190,21 +190,23 @@ static void sm4_do_crypt(const u32 *rk, u32 *out, const u32 *in)
 
 /* encrypt a block of text */
 
-static void sm4_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+void crypto_sm4_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	sm4_do_crypt(ctx->rkey_enc, (u32 *)out, (u32 *)in);
 }
+EXPORT_SYMBOL_GPL(crypto_sm4_encrypt);
 
 /* decrypt a block of text */
 
-static void sm4_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+void crypto_sm4_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	sm4_do_crypt(ctx->rkey_dec, (u32 *)out, (u32 *)in);
 }
+EXPORT_SYMBOL_GPL(crypto_sm4_decrypt);
 
 static struct crypto_alg sm4_alg = {
 	.cra_name		=	"sm4",
@@ -219,8 +221,8 @@ static struct crypto_alg sm4_alg = {
 			.cia_min_keysize	=	SM4_KEY_SIZE,
 			.cia_max_keysize	=	SM4_KEY_SIZE,
 			.cia_setkey		=	crypto_sm4_set_key,
-			.cia_encrypt		=	sm4_encrypt,
-			.cia_decrypt		=	sm4_decrypt
+			.cia_encrypt		=	crypto_sm4_encrypt,
+			.cia_decrypt		=	crypto_sm4_decrypt
 		}
 	}
 };
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 51fe7c8744ae..d5bcdd905007 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -158,9 +158,9 @@ struct test_mb_aead_data {
 };
 
 static int do_mult_aead_op(struct test_mb_aead_data *data, int enc,
-				u32 num_mb)
+				u32 num_mb, int *rc)
 {
-	int i, rc[num_mb], err = 0;
+	int i, err = 0;
 
 	/* Fire up a bunch of concurrent requests */
 	for (i = 0; i < num_mb; i++) {
@@ -188,18 +188,26 @@ static int test_mb_aead_jiffies(struct test_mb_aead_data *data, int enc,
 {
 	unsigned long start, end;
 	int bcount;
-	int ret;
+	int ret = 0;
+	int *rc;
+
+	rc = kcalloc(num_mb, sizeof(*rc), GFP_KERNEL);
+	if (!rc)
+		return -ENOMEM;
 
 	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
-		ret = do_mult_aead_op(data, enc, num_mb);
+		ret = do_mult_aead_op(data, enc, num_mb, rc);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	pr_cont("%d operations in %d seconds (%ld bytes)\n",
 		bcount * num_mb, secs, (long)bcount * blen * num_mb);
-	return 0;
+
+out:
+	kfree(rc);
+	return ret;
 }
 
 static int test_mb_aead_cycles(struct test_mb_aead_data *data, int enc,
@@ -208,10 +216,15 @@ static int test_mb_aead_cycles(struct test_mb_aead_data *data, int enc,
 	unsigned long cycles = 0;
 	int ret = 0;
 	int i;
+	int *rc;
+
+	rc = kcalloc(num_mb, sizeof(*rc), GFP_KERNEL);
+	if (!rc)
+		return -ENOMEM;
 
 	/* Warm-up run. */
 	for (i = 0; i < 4; i++) {
-		ret = do_mult_aead_op(data, enc, num_mb);
+		ret = do_mult_aead_op(data, enc, num_mb, rc);
 		if (ret)
 			goto out;
 	}
@@ -221,7 +234,7 @@ static int test_mb_aead_cycles(struct test_mb_aead_data *data, int enc,
 		cycles_t start, end;
 
 		start = get_cycles();
-		ret = do_mult_aead_op(data, enc, num_mb);
+		ret = do_mult_aead_op(data, enc, num_mb, rc);
 		end = get_cycles();
 
 		if (ret)
@@ -230,11 +243,11 @@ static int test_mb_aead_cycles(struct test_mb_aead_data *data, int enc,
 		cycles += end - start;
 	}
 
-out:
-	if (ret == 0)
-		pr_cont("1 operation in %lu cycles (%d bytes)\n",
-			(cycles + 4) / (8 * num_mb), blen);
+	pr_cont("1 operation in %lu cycles (%d bytes)\n",
+		(cycles + 4) / (8 * num_mb), blen);
 
+out:
+	kfree(rc);
 	return ret;
 }
 
@@ -705,9 +718,10 @@ struct test_mb_ahash_data {
 	char *xbuf[XBUFSIZE];
 };
 
-static inline int do_mult_ahash_op(struct test_mb_ahash_data *data, u32 num_mb)
+static inline int do_mult_ahash_op(struct test_mb_ahash_data *data, u32 num_mb,
+				   int *rc)
 {
-	int i, rc[num_mb], err = 0;
+	int i, err = 0;
 
 	/* Fire up a bunch of concurrent requests */
 	for (i = 0; i < num_mb; i++)
@@ -731,18 +745,26 @@ static int test_mb_ahash_jiffies(struct test_mb_ahash_data *data, int blen,
 {
 	unsigned long start, end;
 	int bcount;
-	int ret;
+	int ret = 0;
+	int *rc;
+
+	rc = kcalloc(num_mb, sizeof(*rc), GFP_KERNEL);
+	if (!rc)
+		return -ENOMEM;
 
 	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
-		ret = do_mult_ahash_op(data, num_mb);
+		ret = do_mult_ahash_op(data, num_mb, rc);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	pr_cont("%d operations in %d seconds (%ld bytes)\n",
 		bcount * num_mb, secs, (long)bcount * blen * num_mb);
-	return 0;
+
+out:
+	kfree(rc);
+	return ret;
 }
 
 static int test_mb_ahash_cycles(struct test_mb_ahash_data *data, int blen,
@@ -751,10 +773,15 @@ static int test_mb_ahash_cycles(struct test_mb_ahash_data *data, int blen,
 	unsigned long cycles = 0;
 	int ret = 0;
 	int i;
+	int *rc;
+
+	rc = kcalloc(num_mb, sizeof(*rc), GFP_KERNEL);
+	if (!rc)
+		return -ENOMEM;
 
 	/* Warm-up run. */
 	for (i = 0; i < 4; i++) {
-		ret = do_mult_ahash_op(data, num_mb);
+		ret = do_mult_ahash_op(data, num_mb, rc);
 		if (ret)
 			goto out;
 	}
@@ -764,7 +791,7 @@ static int test_mb_ahash_cycles(struct test_mb_ahash_data *data, int blen,
 		cycles_t start, end;
 
 		start = get_cycles();
-		ret = do_mult_ahash_op(data, num_mb);
+		ret = do_mult_ahash_op(data, num_mb, rc);
 		end = get_cycles();
 
 		if (ret)
@@ -773,11 +800,11 @@ static int test_mb_ahash_cycles(struct test_mb_ahash_data *data, int blen,
 		cycles += end - start;
 	}
 
-out:
-	if (ret == 0)
-		pr_cont("1 operation in %lu cycles (%d bytes)\n",
-			(cycles + 4) / (8 * num_mb), blen);
+	pr_cont("1 operation in %lu cycles (%d bytes)\n",
+		(cycles + 4) / (8 * num_mb), blen);
 
+out:
+	kfree(rc);
 	return ret;
 }
 
@@ -1118,9 +1145,9 @@ struct test_mb_skcipher_data {
 };
 
 static int do_mult_acipher_op(struct test_mb_skcipher_data *data, int enc,
-				u32 num_mb)
+				u32 num_mb, int *rc)
 {
-	int i, rc[num_mb], err = 0;
+	int i, err = 0;
 
 	/* Fire up a bunch of concurrent requests */
 	for (i = 0; i < num_mb; i++) {
@@ -1148,18 +1175,26 @@ static int test_mb_acipher_jiffies(struct test_mb_skcipher_data *data, int enc,
 {
 	unsigned long start, end;
 	int bcount;
-	int ret;
+	int ret = 0;
+	int *rc;
+
+	rc = kcalloc(num_mb, sizeof(*rc), GFP_KERNEL);
+	if (!rc)
+		return -ENOMEM;
 
 	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
-		ret = do_mult_acipher_op(data, enc, num_mb);
+		ret = do_mult_acipher_op(data, enc, num_mb, rc);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	pr_cont("%d operations in %d seconds (%ld bytes)\n",
 		bcount * num_mb, secs, (long)bcount * blen * num_mb);
-	return 0;
+
+out:
+	kfree(rc);
+	return ret;
 }
 
 static int test_mb_acipher_cycles(struct test_mb_skcipher_data *data, int enc,
@@ -1168,10 +1203,15 @@ static int test_mb_acipher_cycles(struct test_mb_skcipher_data *data, int enc,
 	unsigned long cycles = 0;
 	int ret = 0;
 	int i;
+	int *rc;
+
+	rc = kcalloc(num_mb, sizeof(*rc), GFP_KERNEL);
+	if (!rc)
+		return -ENOMEM;
 
 	/* Warm-up run. */
 	for (i = 0; i < 4; i++) {
-		ret = do_mult_acipher_op(data, enc, num_mb);
+		ret = do_mult_acipher_op(data, enc, num_mb, rc);
 		if (ret)
 			goto out;
 	}
@@ -1181,7 +1221,7 @@ static int test_mb_acipher_cycles(struct test_mb_skcipher_data *data, int enc,
 		cycles_t start, end;
 
 		start = get_cycles();
-		ret = do_mult_acipher_op(data, enc, num_mb);
+		ret = do_mult_acipher_op(data, enc, num_mb, rc);
 		end = get_cycles();
 
 		if (ret)
@@ -1190,11 +1230,11 @@ static int test_mb_acipher_cycles(struct test_mb_skcipher_data *data, int enc,
 		cycles += end - start;
 	}
 
-out:
-	if (ret == 0)
-		pr_cont("1 operation in %lu cycles (%d bytes)\n",
-			(cycles + 4) / (8 * num_mb), blen);
+	pr_cont("1 operation in %lu cycles (%d bytes)\n",
+		(cycles + 4) / (8 * num_mb), blen);
 
+out:
+	kfree(rc);
 	return ret;
 }
 
@@ -1606,7 +1646,7 @@ static inline int tcrypt_test(const char *alg)
 	return ret;
 }
 
-static int do_test(const char *alg, u32 type, u32 mask, int m)
+static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 {
 	int i;
 	int ret = 0;
@@ -1621,7 +1661,7 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 		}
 
 		for (i = 1; i < 200; i++)
-			ret += do_test(NULL, 0, 0, i);
+			ret += do_test(NULL, 0, 0, i, num_mb);
 		break;
 
 	case 1:
@@ -1902,10 +1942,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 		ret += tcrypt_test("vmac(aes)");
 		break;
 
-	case 110:
-		ret += tcrypt_test("hmac(crc32)");
-		break;
-
 	case 111:
 		ret += tcrypt_test("hmac(sha3-224)");
 		break;
@@ -2903,7 +2939,7 @@ static int __init tcrypt_mod_init(void)
 			goto err_free_tv;
 	}
 
-	err = do_test(alg, type, mask, mode);
+	err = do_test(alg, type, mask, mode, num_mb);
 
 	if (err) {
 		printk(KERN_ERR "tcrypt: one or more tests failed!\n");
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index af4a01c5037b..d1d99843cce4 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -84,10 +84,8 @@ struct aead_test_suite {
 };
 
 struct cipher_test_suite {
-	struct {
-		const struct cipher_testvec *vecs;
-		unsigned int count;
-	} enc, dec;
+	const struct cipher_testvec *vecs;
+	unsigned int count;
 };
 
 struct comp_test_suite {
@@ -988,6 +986,7 @@ static int test_cipher(struct crypto_cipher *tfm, int enc,
 	unsigned int i, j, k;
 	char *q;
 	const char *e;
+	const char *input, *result;
 	void *data;
 	char *xbuf[XBUFSIZE];
 	int ret = -ENOMEM;
@@ -1008,14 +1007,16 @@ static int test_cipher(struct crypto_cipher *tfm, int enc,
 		if (fips_enabled && template[i].fips_skip)
 			continue;
 
+		input  = enc ? template[i].ptext : template[i].ctext;
+		result = enc ? template[i].ctext : template[i].ptext;
 		j++;
 
 		ret = -EINVAL;
-		if (WARN_ON(template[i].ilen > PAGE_SIZE))
+		if (WARN_ON(template[i].len > PAGE_SIZE))
 			goto out;
 
 		data = xbuf[0];
-		memcpy(data, template[i].input, template[i].ilen);
+		memcpy(data, input, template[i].len);
 
 		crypto_cipher_clear_flags(tfm, ~0);
 		if (template[i].wk)
@@ -1031,7 +1032,7 @@ static int test_cipher(struct crypto_cipher *tfm, int enc,
 		} else if (ret)
 			continue;
 
-		for (k = 0; k < template[i].ilen;
+		for (k = 0; k < template[i].len;
 		     k += crypto_cipher_blocksize(tfm)) {
 			if (enc)
 				crypto_cipher_encrypt_one(tfm, data + k,
@@ -1042,10 +1043,10 @@ static int test_cipher(struct crypto_cipher *tfm, int enc,
 		}
 
 		q = data;
-		if (memcmp(q, template[i].result, template[i].rlen)) {
+		if (memcmp(q, result, template[i].len)) {
 			printk(KERN_ERR "alg: cipher: Test %d failed "
 			       "on %s for %s\n", j, e, algo);
-			hexdump(q, template[i].rlen);
+			hexdump(q, template[i].len);
 			ret = -EINVAL;
 			goto out;
 		}
@@ -1073,6 +1074,7 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 	struct scatterlist sgout[8];
 	const char *e, *d;
 	struct crypto_wait wait;
+	const char *input, *result;
 	void *data;
 	char iv[MAX_IVLEN];
 	char *xbuf[XBUFSIZE];
@@ -1116,19 +1118,21 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 		if (fips_enabled && template[i].fips_skip)
 			continue;
 
-		if (template[i].iv)
+		if (template[i].iv && !(template[i].generates_iv && enc))
 			memcpy(iv, template[i].iv, ivsize);
 		else
 			memset(iv, 0, MAX_IVLEN);
 
+		input  = enc ? template[i].ptext : template[i].ctext;
+		result = enc ? template[i].ctext : template[i].ptext;
 		j++;
 		ret = -EINVAL;
-		if (WARN_ON(align_offset + template[i].ilen > PAGE_SIZE))
+		if (WARN_ON(align_offset + template[i].len > PAGE_SIZE))
 			goto out;
 
 		data = xbuf[0];
 		data += align_offset;
-		memcpy(data, template[i].input, template[i].ilen);
+		memcpy(data, input, template[i].len);
 
 		crypto_skcipher_clear_flags(tfm, ~0);
 		if (template[i].wk)
@@ -1144,15 +1148,15 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 		} else if (ret)
 			continue;
 
-		sg_init_one(&sg[0], data, template[i].ilen);
+		sg_init_one(&sg[0], data, template[i].len);
 		if (diff_dst) {
 			data = xoutbuf[0];
 			data += align_offset;
-			sg_init_one(&sgout[0], data, template[i].ilen);
+			sg_init_one(&sgout[0], data, template[i].len);
 		}
 
 		skcipher_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
-					   template[i].ilen, iv);
+					   template[i].len, iv);
 		ret = crypto_wait_req(enc ? crypto_skcipher_encrypt(req) :
 				      crypto_skcipher_decrypt(req), &wait);
 
@@ -1163,17 +1167,16 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 		}
 
 		q = data;
-		if (memcmp(q, template[i].result, template[i].rlen)) {
+		if (memcmp(q, result, template[i].len)) {
 			pr_err("alg: skcipher%s: Test %d failed (invalid result) on %s for %s\n",
 			       d, j, e, algo);
-			hexdump(q, template[i].rlen);
+			hexdump(q, template[i].len);
 			ret = -EINVAL;
 			goto out;
 		}
 
-		if (template[i].iv_out &&
-		    memcmp(iv, template[i].iv_out,
-			   crypto_skcipher_ivsize(tfm))) {
+		if (template[i].generates_iv && enc &&
+		    memcmp(iv, template[i].iv, crypto_skcipher_ivsize(tfm))) {
 			pr_err("alg: skcipher%s: Test %d failed (invalid output IV) on %s for %s\n",
 			       d, j, e, algo);
 			hexdump(iv, crypto_skcipher_ivsize(tfm));
@@ -1194,11 +1197,13 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 		if (fips_enabled && template[i].fips_skip)
 			continue;
 
-		if (template[i].iv)
+		if (template[i].iv && !(template[i].generates_iv && enc))
 			memcpy(iv, template[i].iv, ivsize);
 		else
 			memset(iv, 0, MAX_IVLEN);
 
+		input  = enc ? template[i].ptext : template[i].ctext;
+		result = enc ? template[i].ctext : template[i].ptext;
 		j++;
 		crypto_skcipher_clear_flags(tfm, ~0);
 		if (template[i].wk)
@@ -1226,7 +1231,7 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 
 			q = xbuf[IDX[k] >> PAGE_SHIFT] + offset_in_page(IDX[k]);
 
-			memcpy(q, template[i].input + temp, template[i].tap[k]);
+			memcpy(q, input + temp, template[i].tap[k]);
 
 			if (offset_in_page(q) + template[i].tap[k] < PAGE_SIZE)
 				q[template[i].tap[k]] = 0;
@@ -1248,7 +1253,7 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 		}
 
 		skcipher_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
-					   template[i].ilen, iv);
+					   template[i].len, iv);
 
 		ret = crypto_wait_req(enc ? crypto_skcipher_encrypt(req) :
 				      crypto_skcipher_decrypt(req), &wait);
@@ -1269,8 +1274,7 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc,
 				q = xbuf[IDX[k] >> PAGE_SHIFT] +
 				    offset_in_page(IDX[k]);
 
-			if (memcmp(q, template[i].result + temp,
-				   template[i].tap[k])) {
+			if (memcmp(q, result + temp, template[i].tap[k])) {
 				pr_err("alg: skcipher%s: Chunk test %d failed on %s at page %u for %s\n",
 				       d, j, e, k, algo);
 				hexdump(q, template[i].tap[k]);
@@ -1342,19 +1346,30 @@ static int test_comp(struct crypto_comp *tfm,
 		     int ctcount, int dtcount)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_comp_tfm(tfm));
+	char *output, *decomp_output;
 	unsigned int i;
-	char result[COMP_BUF_SIZE];
 	int ret;
 
+	output = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+	if (!output)
+		return -ENOMEM;
+
+	decomp_output = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+	if (!decomp_output) {
+		kfree(output);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < ctcount; i++) {
 		int ilen;
 		unsigned int dlen = COMP_BUF_SIZE;
 
-		memset(result, 0, sizeof (result));
+		memset(output, 0, sizeof(COMP_BUF_SIZE));
+		memset(decomp_output, 0, sizeof(COMP_BUF_SIZE));
 
 		ilen = ctemplate[i].inlen;
 		ret = crypto_comp_compress(tfm, ctemplate[i].input,
-		                           ilen, result, &dlen);
+					   ilen, output, &dlen);
 		if (ret) {
 			printk(KERN_ERR "alg: comp: compression failed "
 			       "on test %d for %s: ret=%d\n", i + 1, algo,
@@ -1362,7 +1377,17 @@ static int test_comp(struct crypto_comp *tfm,
 			goto out;
 		}
 
-		if (dlen != ctemplate[i].outlen) {
+		ilen = dlen;
+		dlen = COMP_BUF_SIZE;
+		ret = crypto_comp_decompress(tfm, output,
+					     ilen, decomp_output, &dlen);
+		if (ret) {
+			pr_err("alg: comp: compression failed: decompress: on test %d for %s failed: ret=%d\n",
+			       i + 1, algo, -ret);
+			goto out;
+		}
+
+		if (dlen != ctemplate[i].inlen) {
 			printk(KERN_ERR "alg: comp: Compression test %d "
 			       "failed for %s: output len = %d\n", i + 1, algo,
 			       dlen);
@@ -1370,10 +1395,11 @@ static int test_comp(struct crypto_comp *tfm,
 			goto out;
 		}
 
-		if (memcmp(result, ctemplate[i].output, dlen)) {
-			printk(KERN_ERR "alg: comp: Compression test %d "
-			       "failed for %s\n", i + 1, algo);
-			hexdump(result, dlen);
+		if (memcmp(decomp_output, ctemplate[i].input,
+			   ctemplate[i].inlen)) {
+			pr_err("alg: comp: compression failed: output differs: on test %d for %s\n",
+			       i + 1, algo);
+			hexdump(decomp_output, dlen);
 			ret = -EINVAL;
 			goto out;
 		}
@@ -1383,11 +1409,11 @@ static int test_comp(struct crypto_comp *tfm,
 		int ilen;
 		unsigned int dlen = COMP_BUF_SIZE;
 
-		memset(result, 0, sizeof (result));
+		memset(decomp_output, 0, sizeof(COMP_BUF_SIZE));
 
 		ilen = dtemplate[i].inlen;
 		ret = crypto_comp_decompress(tfm, dtemplate[i].input,
-		                             ilen, result, &dlen);
+					     ilen, decomp_output, &dlen);
 		if (ret) {
 			printk(KERN_ERR "alg: comp: decompression failed "
 			       "on test %d for %s: ret=%d\n", i + 1, algo,
@@ -1403,10 +1429,10 @@ static int test_comp(struct crypto_comp *tfm,
 			goto out;
 		}
 
-		if (memcmp(result, dtemplate[i].output, dlen)) {
+		if (memcmp(decomp_output, dtemplate[i].output, dlen)) {
 			printk(KERN_ERR "alg: comp: Decompression test %d "
 			       "failed for %s\n", i + 1, algo);
-			hexdump(result, dlen);
+			hexdump(decomp_output, dlen);
 			ret = -EINVAL;
 			goto out;
 		}
@@ -1415,11 +1441,13 @@ static int test_comp(struct crypto_comp *tfm,
 	ret = 0;
 
 out:
+	kfree(decomp_output);
+	kfree(output);
 	return ret;
 }
 
 static int test_acomp(struct crypto_acomp *tfm,
-		      const struct comp_testvec *ctemplate,
+			      const struct comp_testvec *ctemplate,
 		      const struct comp_testvec *dtemplate,
 		      int ctcount, int dtcount)
 {
@@ -1681,8 +1709,9 @@ out:
 static int alg_test_cipher(const struct alg_test_desc *desc,
 			   const char *driver, u32 type, u32 mask)
 {
+	const struct cipher_test_suite *suite = &desc->suite.cipher;
 	struct crypto_cipher *tfm;
-	int err = 0;
+	int err;
 
 	tfm = crypto_alloc_cipher(driver, type, mask);
 	if (IS_ERR(tfm)) {
@@ -1691,18 +1720,10 @@ static int alg_test_cipher(const struct alg_test_desc *desc,
 		return PTR_ERR(tfm);
 	}
 
-	if (desc->suite.cipher.enc.vecs) {
-		err = test_cipher(tfm, ENCRYPT, desc->suite.cipher.enc.vecs,
-				  desc->suite.cipher.enc.count);
-		if (err)
-			goto out;
-	}
-
-	if (desc->suite.cipher.dec.vecs)
-		err = test_cipher(tfm, DECRYPT, desc->suite.cipher.dec.vecs,
-				  desc->suite.cipher.dec.count);
+	err = test_cipher(tfm, ENCRYPT, suite->vecs, suite->count);
+	if (!err)
+		err = test_cipher(tfm, DECRYPT, suite->vecs, suite->count);
 
-out:
 	crypto_free_cipher(tfm);
 	return err;
 }
@@ -1710,8 +1731,9 @@ out:
 static int alg_test_skcipher(const struct alg_test_desc *desc,
 			     const char *driver, u32 type, u32 mask)
 {
+	const struct cipher_test_suite *suite = &desc->suite.cipher;
 	struct crypto_skcipher *tfm;
-	int err = 0;
+	int err;
 
 	tfm = crypto_alloc_skcipher(driver, type, mask);
 	if (IS_ERR(tfm)) {
@@ -1720,18 +1742,10 @@ static int alg_test_skcipher(const struct alg_test_desc *desc,
 		return PTR_ERR(tfm);
 	}
 
-	if (desc->suite.cipher.enc.vecs) {
-		err = test_skcipher(tfm, ENCRYPT, desc->suite.cipher.enc.vecs,
-				    desc->suite.cipher.enc.count);
-		if (err)
-			goto out;
-	}
-
-	if (desc->suite.cipher.dec.vecs)
-		err = test_skcipher(tfm, DECRYPT, desc->suite.cipher.dec.vecs,
-				    desc->suite.cipher.dec.count);
+	err = test_skcipher(tfm, ENCRYPT, suite->vecs, suite->count);
+	if (!err)
+		err = test_skcipher(tfm, DECRYPT, suite->vecs, suite->count);
 
-out:
 	crypto_free_skcipher(tfm);
 	return err;
 }
@@ -1774,8 +1788,9 @@ static int alg_test_comp(const struct alg_test_desc *desc, const char *driver,
 	return err;
 }
 
-static int alg_test_hash(const struct alg_test_desc *desc, const char *driver,
-			 u32 type, u32 mask)
+static int __alg_test_hash(const struct hash_testvec *template,
+			   unsigned int tcount, const char *driver,
+			   u32 type, u32 mask)
 {
 	struct crypto_ahash *tfm;
 	int err;
@@ -1787,16 +1802,51 @@ static int alg_test_hash(const struct alg_test_desc *desc, const char *driver,
 		return PTR_ERR(tfm);
 	}
 
-	err = test_hash(tfm, desc->suite.hash.vecs,
-			desc->suite.hash.count, true);
+	err = test_hash(tfm, template, tcount, true);
 	if (!err)
-		err = test_hash(tfm, desc->suite.hash.vecs,
-				desc->suite.hash.count, false);
-
+		err = test_hash(tfm, template, tcount, false);
 	crypto_free_ahash(tfm);
 	return err;
 }
 
+static int alg_test_hash(const struct alg_test_desc *desc, const char *driver,
+			 u32 type, u32 mask)
+{
+	const struct hash_testvec *template = desc->suite.hash.vecs;
+	unsigned int tcount = desc->suite.hash.count;
+	unsigned int nr_unkeyed, nr_keyed;
+	int err;
+
+	/*
+	 * For OPTIONAL_KEY algorithms, we have to do all the unkeyed tests
+	 * first, before setting a key on the tfm.  To make this easier, we
+	 * require that the unkeyed test vectors (if any) are listed first.
+	 */
+
+	for (nr_unkeyed = 0; nr_unkeyed < tcount; nr_unkeyed++) {
+		if (template[nr_unkeyed].ksize)
+			break;
+	}
+	for (nr_keyed = 0; nr_unkeyed + nr_keyed < tcount; nr_keyed++) {
+		if (!template[nr_unkeyed + nr_keyed].ksize) {
+			pr_err("alg: hash: test vectors for %s out of order, "
+			       "unkeyed ones must come first\n", desc->alg);
+			return -EINVAL;
+		}
+	}
+
+	err = 0;
+	if (nr_unkeyed) {
+		err = __alg_test_hash(template, nr_unkeyed, driver, type, mask);
+		template += nr_unkeyed;
+	}
+
+	if (!err && nr_keyed)
+		err = __alg_test_hash(template, nr_keyed, driver, type, mask);
+
+	return err;
+}
+
 static int alg_test_crc32c(const struct alg_test_desc *desc,
 			   const char *driver, u32 type, u32 mask)
 {
@@ -2316,6 +2366,33 @@ static int alg_test_null(const struct alg_test_desc *desc,
 /* Please keep this list sorted by algorithm name. */
 static const struct alg_test_desc alg_test_descs[] = {
 	{
+		.alg = "aegis128",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = __VECS(aegis128_enc_tv_template),
+				.dec = __VECS(aegis128_dec_tv_template),
+			}
+		}
+	}, {
+		.alg = "aegis128l",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = __VECS(aegis128l_enc_tv_template),
+				.dec = __VECS(aegis128l_dec_tv_template),
+			}
+		}
+	}, {
+		.alg = "aegis256",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = __VECS(aegis256_enc_tv_template),
+				.dec = __VECS(aegis256_dec_tv_template),
+			}
+		}
+	}, {
 		.alg = "ansi_cprng",
 		.test = alg_test_cprng,
 		.suite = {
@@ -2488,93 +2565,70 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(aes_cbc_enc_tv_template),
-				.dec = __VECS(aes_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(aes_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(anubis)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(anubis_cbc_enc_tv_template),
-				.dec = __VECS(anubis_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(anubis_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(blowfish)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(bf_cbc_enc_tv_template),
-				.dec = __VECS(bf_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(bf_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(camellia)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(camellia_cbc_enc_tv_template),
-				.dec = __VECS(camellia_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(camellia_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(cast5)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cast5_cbc_enc_tv_template),
-				.dec = __VECS(cast5_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(cast5_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(cast6)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cast6_cbc_enc_tv_template),
-				.dec = __VECS(cast6_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(cast6_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(des)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(des_cbc_enc_tv_template),
-				.dec = __VECS(des_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(des_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(des3_ede)",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(des3_ede_cbc_enc_tv_template),
-				.dec = __VECS(des3_ede_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(des3_ede_cbc_tv_template)
+		},
+	}, {
+		/* Same as cbc(aes) except the key is stored in
+		 * hardware secure memory which we reference by index
+		 */
+		.alg = "cbc(paes)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
 	}, {
 		.alg = "cbc(serpent)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(serpent_cbc_enc_tv_template),
-				.dec = __VECS(serpent_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(serpent_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbc(twofish)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(tf_cbc_enc_tv_template),
-				.dec = __VECS(tf_cbc_dec_tv_template)
-			}
-		}
+			.cipher = __VECS(tf_cbc_tv_template)
+		},
 	}, {
 		.alg = "cbcmac(aes)",
 		.fips_allowed = 1,
@@ -2596,11 +2650,8 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.alg = "chacha20",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(chacha20_enc_tv_template),
-				.dec = __VECS(chacha20_enc_tv_template),
-			}
-		}
+			.cipher = __VECS(chacha20_tv_template)
+		},
 	}, {
 		.alg = "cmac(aes)",
 		.fips_allowed = 1,
@@ -2643,92 +2694,69 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(aes_ctr_enc_tv_template),
-				.dec = __VECS(aes_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(aes_ctr_tv_template)
 		}
 	}, {
 		.alg = "ctr(blowfish)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(bf_ctr_enc_tv_template),
-				.dec = __VECS(bf_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(bf_ctr_tv_template)
 		}
 	}, {
 		.alg = "ctr(camellia)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(camellia_ctr_enc_tv_template),
-				.dec = __VECS(camellia_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(camellia_ctr_tv_template)
 		}
 	}, {
 		.alg = "ctr(cast5)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cast5_ctr_enc_tv_template),
-				.dec = __VECS(cast5_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(cast5_ctr_tv_template)
 		}
 	}, {
 		.alg = "ctr(cast6)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cast6_ctr_enc_tv_template),
-				.dec = __VECS(cast6_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(cast6_ctr_tv_template)
 		}
 	}, {
 		.alg = "ctr(des)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(des_ctr_enc_tv_template),
-				.dec = __VECS(des_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(des_ctr_tv_template)
 		}
 	}, {
 		.alg = "ctr(des3_ede)",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(des3_ede_ctr_enc_tv_template),
-				.dec = __VECS(des3_ede_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(des3_ede_ctr_tv_template)
 		}
 	}, {
+		/* Same as ctr(aes) except the key is stored in
+		 * hardware secure memory which we reference by index
+		 */
+		.alg = "ctr(paes)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "ctr(serpent)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(serpent_ctr_enc_tv_template),
-				.dec = __VECS(serpent_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(serpent_ctr_tv_template)
 		}
 	}, {
 		.alg = "ctr(twofish)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(tf_ctr_enc_tv_template),
-				.dec = __VECS(tf_ctr_dec_tv_template)
-			}
+			.cipher = __VECS(tf_ctr_tv_template)
 		}
 	}, {
 		.alg = "cts(cbc(aes))",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cts_mode_enc_tv_template),
-				.dec = __VECS(cts_mode_dec_tv_template)
-			}
+			.cipher = __VECS(cts_mode_tv_template)
 		}
 	}, {
 		.alg = "deflate",
@@ -2876,64 +2904,43 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(aes_enc_tv_template),
-				.dec = __VECS(aes_dec_tv_template)
-			}
+			.cipher = __VECS(aes_tv_template)
 		}
 	}, {
 		.alg = "ecb(anubis)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(anubis_enc_tv_template),
-				.dec = __VECS(anubis_dec_tv_template)
-			}
+			.cipher = __VECS(anubis_tv_template)
 		}
 	}, {
 		.alg = "ecb(arc4)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(arc4_enc_tv_template),
-				.dec = __VECS(arc4_dec_tv_template)
-			}
+			.cipher = __VECS(arc4_tv_template)
 		}
 	}, {
 		.alg = "ecb(blowfish)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(bf_enc_tv_template),
-				.dec = __VECS(bf_dec_tv_template)
-			}
+			.cipher = __VECS(bf_tv_template)
 		}
 	}, {
 		.alg = "ecb(camellia)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(camellia_enc_tv_template),
-				.dec = __VECS(camellia_dec_tv_template)
-			}
+			.cipher = __VECS(camellia_tv_template)
 		}
 	}, {
 		.alg = "ecb(cast5)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cast5_enc_tv_template),
-				.dec = __VECS(cast5_dec_tv_template)
-			}
+			.cipher = __VECS(cast5_tv_template)
 		}
 	}, {
 		.alg = "ecb(cast6)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cast6_enc_tv_template),
-				.dec = __VECS(cast6_dec_tv_template)
-			}
+			.cipher = __VECS(cast6_tv_template)
 		}
 	}, {
 		.alg = "ecb(cipher_null)",
@@ -2943,134 +2950,96 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.alg = "ecb(des)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(des_enc_tv_template),
-				.dec = __VECS(des_dec_tv_template)
-			}
+			.cipher = __VECS(des_tv_template)
 		}
 	}, {
 		.alg = "ecb(des3_ede)",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(des3_ede_enc_tv_template),
-				.dec = __VECS(des3_ede_dec_tv_template)
-			}
+			.cipher = __VECS(des3_ede_tv_template)
 		}
 	}, {
 		.alg = "ecb(fcrypt)",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = {
-				.enc = {
-					.vecs = fcrypt_pcbc_enc_tv_template,
-					.count = 1
-				},
-				.dec = {
-					.vecs = fcrypt_pcbc_dec_tv_template,
-					.count = 1
-				}
+				.vecs = fcrypt_pcbc_tv_template,
+				.count = 1
 			}
 		}
 	}, {
 		.alg = "ecb(khazad)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(khazad_enc_tv_template),
-				.dec = __VECS(khazad_dec_tv_template)
-			}
+			.cipher = __VECS(khazad_tv_template)
 		}
 	}, {
+		/* Same as ecb(aes) except the key is stored in
+		 * hardware secure memory which we reference by index
+		 */
+		.alg = "ecb(paes)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "ecb(seed)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(seed_enc_tv_template),
-				.dec = __VECS(seed_dec_tv_template)
-			}
+			.cipher = __VECS(seed_tv_template)
 		}
 	}, {
 		.alg = "ecb(serpent)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(serpent_enc_tv_template),
-				.dec = __VECS(serpent_dec_tv_template)
-			}
+			.cipher = __VECS(serpent_tv_template)
 		}
 	}, {
 		.alg = "ecb(sm4)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(sm4_enc_tv_template),
-				.dec = __VECS(sm4_dec_tv_template)
-			}
+			.cipher = __VECS(sm4_tv_template)
 		}
 	}, {
 		.alg = "ecb(speck128)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(speck128_enc_tv_template),
-				.dec = __VECS(speck128_dec_tv_template)
-			}
+			.cipher = __VECS(speck128_tv_template)
 		}
 	}, {
 		.alg = "ecb(speck64)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(speck64_enc_tv_template),
-				.dec = __VECS(speck64_dec_tv_template)
-			}
+			.cipher = __VECS(speck64_tv_template)
 		}
 	}, {
 		.alg = "ecb(tea)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(tea_enc_tv_template),
-				.dec = __VECS(tea_dec_tv_template)
-			}
+			.cipher = __VECS(tea_tv_template)
 		}
 	}, {
 		.alg = "ecb(tnepres)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(tnepres_enc_tv_template),
-				.dec = __VECS(tnepres_dec_tv_template)
-			}
+			.cipher = __VECS(tnepres_tv_template)
 		}
 	}, {
 		.alg = "ecb(twofish)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(tf_enc_tv_template),
-				.dec = __VECS(tf_dec_tv_template)
-			}
+			.cipher = __VECS(tf_tv_template)
 		}
 	}, {
 		.alg = "ecb(xeta)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(xeta_enc_tv_template),
-				.dec = __VECS(xeta_dec_tv_template)
-			}
+			.cipher = __VECS(xeta_tv_template)
 		}
 	}, {
 		.alg = "ecb(xtea)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(xtea_enc_tv_template),
-				.dec = __VECS(xtea_dec_tv_template)
-			}
+			.cipher = __VECS(xtea_tv_template)
 		}
 	}, {
 		.alg = "ecdh",
@@ -3097,12 +3066,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.hash = __VECS(ghash_tv_template)
 		}
 	}, {
-		.alg = "hmac(crc32)",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(bfin_crc_tv_template)
-		}
-	}, {
 		.alg = "hmac(md5)",
 		.test = alg_test_hash,
 		.suite = {
@@ -3192,55 +3155,37 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(aes_kw_enc_tv_template),
-				.dec = __VECS(aes_kw_dec_tv_template)
-			}
+			.cipher = __VECS(aes_kw_tv_template)
 		}
 	}, {
 		.alg = "lrw(aes)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(aes_lrw_enc_tv_template),
-				.dec = __VECS(aes_lrw_dec_tv_template)
-			}
+			.cipher = __VECS(aes_lrw_tv_template)
 		}
 	}, {
 		.alg = "lrw(camellia)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(camellia_lrw_enc_tv_template),
-				.dec = __VECS(camellia_lrw_dec_tv_template)
-			}
+			.cipher = __VECS(camellia_lrw_tv_template)
 		}
 	}, {
 		.alg = "lrw(cast6)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cast6_lrw_enc_tv_template),
-				.dec = __VECS(cast6_lrw_dec_tv_template)
-			}
+			.cipher = __VECS(cast6_lrw_tv_template)
 		}
 	}, {
 		.alg = "lrw(serpent)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(serpent_lrw_enc_tv_template),
-				.dec = __VECS(serpent_lrw_dec_tv_template)
-			}
+			.cipher = __VECS(serpent_lrw_tv_template)
 		}
 	}, {
 		.alg = "lrw(twofish)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(tf_lrw_enc_tv_template),
-				.dec = __VECS(tf_lrw_dec_tv_template)
-			}
+			.cipher = __VECS(tf_lrw_tv_template)
 		}
 	}, {
 		.alg = "lz4",
@@ -3291,23 +3236,42 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.hash = __VECS(michael_mic_tv_template)
 		}
 	}, {
+		.alg = "morus1280",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = __VECS(morus1280_enc_tv_template),
+				.dec = __VECS(morus1280_dec_tv_template),
+			}
+		}
+	}, {
+		.alg = "morus640",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = __VECS(morus640_enc_tv_template),
+				.dec = __VECS(morus640_dec_tv_template),
+			}
+		}
+	}, {
 		.alg = "ofb(aes)",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(aes_ofb_enc_tv_template),
-				.dec = __VECS(aes_ofb_dec_tv_template)
-			}
+			.cipher = __VECS(aes_ofb_tv_template)
 		}
 	}, {
+		/* Same as ofb(aes) except the key is stored in
+		 * hardware secure memory which we reference by index
+		 */
+		.alg = "ofb(paes)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "pcbc(fcrypt)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(fcrypt_pcbc_enc_tv_template),
-				.dec = __VECS(fcrypt_pcbc_dec_tv_template)
-			}
+			.cipher = __VECS(fcrypt_pcbc_tv_template)
 		}
 	}, {
 		.alg = "pkcs1pad(rsa,sha224)",
@@ -3339,10 +3303,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(aes_ctr_rfc3686_enc_tv_template),
-				.dec = __VECS(aes_ctr_rfc3686_dec_tv_template)
-			}
+			.cipher = __VECS(aes_ctr_rfc3686_tv_template)
 		}
 	}, {
 		.alg = "rfc4106(gcm(aes))",
@@ -3426,9 +3387,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.alg = "salsa20",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(salsa20_stream_enc_tv_template)
-			}
+			.cipher = __VECS(salsa20_stream_tv_template)
 		}
 	}, {
 		.alg = "sha1",
@@ -3552,66 +3511,60 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(aes_xts_enc_tv_template),
-				.dec = __VECS(aes_xts_dec_tv_template)
-			}
+			.cipher = __VECS(aes_xts_tv_template)
 		}
 	}, {
 		.alg = "xts(camellia)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(camellia_xts_enc_tv_template),
-				.dec = __VECS(camellia_xts_dec_tv_template)
-			}
+			.cipher = __VECS(camellia_xts_tv_template)
 		}
 	}, {
 		.alg = "xts(cast6)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(cast6_xts_enc_tv_template),
-				.dec = __VECS(cast6_xts_dec_tv_template)
-			}
+			.cipher = __VECS(cast6_xts_tv_template)
 		}
 	}, {
+		/* Same as xts(aes) except the key is stored in
+		 * hardware secure memory which we reference by index
+		 */
+		.alg = "xts(paes)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "xts(serpent)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(serpent_xts_enc_tv_template),
-				.dec = __VECS(serpent_xts_dec_tv_template)
-			}
+			.cipher = __VECS(serpent_xts_tv_template)
 		}
 	}, {
 		.alg = "xts(speck128)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(speck128_xts_enc_tv_template),
-				.dec = __VECS(speck128_xts_dec_tv_template)
-			}
+			.cipher = __VECS(speck128_xts_tv_template)
 		}
 	}, {
 		.alg = "xts(speck64)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(speck64_xts_enc_tv_template),
-				.dec = __VECS(speck64_xts_dec_tv_template)
-			}
+			.cipher = __VECS(speck64_xts_tv_template)
 		}
 	}, {
 		.alg = "xts(twofish)",
 		.test = alg_test_skcipher,
 		.suite = {
-			.cipher = {
-				.enc = __VECS(tf_xts_enc_tv_template),
-				.dec = __VECS(tf_xts_dec_tv_template)
-			}
+			.cipher = __VECS(tf_xts_tv_template)
 		}
 	}, {
+		.alg = "xts4096(paes)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
+		.alg = "xts512(paes)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "zlib-deflate",
 		.test = alg_test_comp,
 		.fips_allowed = 1,
@@ -3621,6 +3574,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 				.decomp = __VECS(zlib_deflate_decomp_tv_template)
 			}
 		}
+	}, {
+		.alg = "zstd",
+		.test = alg_test_comp,
+		.fips_allowed = 1,
+		.suite = {
+			.comp = {
+				.comp = __VECS(zstd_comp_tv_template),
+				.decomp = __VECS(zstd_decomp_tv_template)
+			}
+		}
 	}
 };
 
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 004c0a0f8004..b950aa234e43 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -44,14 +44,13 @@ struct hash_testvec {
 };
 
 /*
- * cipher_testvec:	structure to describe a cipher test
- * @key:	A pointer to a key used by the test
- * @klen:	The length of @key
- * @iv:		A pointer to the IV used by the test
- * @input:	A pointer to data used as input
- * @ilen	The length of data in @input
- * @result:	A pointer to what the test need to produce
- * @rlen:	The length of data in @result
+ * cipher_testvec:	structure to describe a symmetric cipher test
+ * @key:	Pointer to key
+ * @klen:	Length of @key in bytes
+ * @iv:		Pointer to IV (optional for some ciphers)
+ * @ptext:	Pointer to plaintext
+ * @ctext:	Pointer to ciphertext
+ * @len:	Length of @ptext and @ctext in bytes
  * @fail:	If set to one, the test need to fail
  * @wk:		Does the test need CRYPTO_TFM_REQ_WEAK_KEY
  * 		( e.g. test needs to fail due to a weak key )
@@ -60,23 +59,23 @@ struct hash_testvec {
  * @also_non_np: 	if set to 1, the test will be also done without
  * 			splitting data in @np SGs
  * @fips_skip:	Skip the test vector in FIPS mode
+ * @generates_iv: Encryption should ignore the given IV, and output @iv.
+ *		  Decryption takes @iv.  Needed for AES Keywrap ("kw(aes)").
  */
-
 struct cipher_testvec {
 	const char *key;
 	const char *iv;
-	const char *iv_out;
-	const char *input;
-	const char *result;
+	const char *ptext;
+	const char *ctext;
 	unsigned short tap[MAX_TAP];
 	int np;
 	unsigned char also_non_np;
 	bool fail;
 	unsigned char wk; /* weak key flag */
 	unsigned char klen;
-	unsigned short ilen;
-	unsigned short rlen;
+	unsigned short len;
 	bool fips_skip;
+	bool generates_iv;
 };
 
 struct aead_testvec {
@@ -5542,111 +5541,121 @@ static const struct hash_testvec poly1305_tv_template[] = {
 /*
  * DES test vectors.
  */
-static const struct cipher_testvec des_enc_tv_template[] = {
+static const struct cipher_testvec des_tv_template[] = {
 	{ /* From Applied Cryptography */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xe7",
-		.ilen	= 8,
-		.result	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7",
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d",
+		.len	= 8,
 	}, { /* Same key, different plaintext block */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x22\x33\x44\x55\x66\x77\x88\x99",
-		.ilen	= 8,
-		.result	= "\xf7\x9c\x89\x2a\x33\x8f\x4a\x8b",
-		.rlen	= 8,
+		.ptext	= "\x22\x33\x44\x55\x66\x77\x88\x99",
+		.ctext	= "\xf7\x9c\x89\x2a\x33\x8f\x4a\x8b",
+		.len	= 8,
 	}, { /* Sbox test from NBS */
 		.key	= "\x7c\xa1\x10\x45\x4a\x1a\x6e\x57",
 		.klen	= 8,
-		.input	= "\x01\xa1\xd6\xd0\x39\x77\x67\x42",
-		.ilen	= 8,
-		.result	= "\x69\x0f\x5b\x0d\x9a\x26\x93\x9b",
-		.rlen	= 8,
+		.ptext	= "\x01\xa1\xd6\xd0\x39\x77\x67\x42",
+		.ctext	= "\x69\x0f\x5b\x0d\x9a\x26\x93\x9b",
+		.len	= 8,
 	}, { /* Three blocks */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
 			  "\x22\x33\x44\x55\x66\x77\x88\x99"
 			  "\xca\xfe\xba\xbe\xfe\xed\xbe\xef",
-		.ilen	= 24,
-		.result	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
 			  "\xf7\x9c\x89\x2a\x33\x8f\x4a\x8b"
 			  "\xb4\x99\x26\xf7\x1f\xe1\xd4\x90",
-		.rlen	= 24,
+		.len	= 24,
 	}, { /* Weak key */
 		.fail	= true,
 		.wk	= 1,
 		.key	= "\x01\x01\x01\x01\x01\x01\x01\x01",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xe7",
-		.ilen	= 8,
-		.result	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7",
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d",
+		.len	= 8,
 	}, { /* Two blocks -- for testing encryption across pages */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
 			  "\x22\x33\x44\x55\x66\x77\x88\x99",
-		.ilen	= 16,
-		.result	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
 			  "\xf7\x9c\x89\x2a\x33\x8f\x4a\x8b",
-		.rlen	= 16,
+		.len	= 16,
 		.np	= 2,
 		.tap	= { 8, 8 }
+	}, {
+		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.klen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
+			  "\xa3\x99\x7b\xca\xaf\x69\xa0\xf5",
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
+			  "\x69\x0f\x5b\x0d\x9a\x26\x93\x9b",
+		.len	= 16,
+		.np	= 2,
+		.tap	= { 8, 8 }
+	}, {
+		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.klen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
+			  "\xa3\x99\x7b\xca\xaf\x69\xa0\xf5",
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
+			  "\x69\x0f\x5b\x0d\x9a\x26\x93\x9b",
+		.len	= 16,
+		.np	= 3,
+		.tap	= { 3, 12, 1 }
 	}, { /* Four blocks -- for testing encryption with chunking */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
 			  "\x22\x33\x44\x55\x66\x77\x88\x99"
 			  "\xca\xfe\xba\xbe\xfe\xed\xbe\xef"
 			  "\x22\x33\x44\x55\x66\x77\x88\x99",
-		.ilen	= 32,
-		.result	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
 			  "\xf7\x9c\x89\x2a\x33\x8f\x4a\x8b"
 			  "\xb4\x99\x26\xf7\x1f\xe1\xd4\x90"
 			  "\xf7\x9c\x89\x2a\x33\x8f\x4a\x8b",
-		.rlen	= 32,
+		.len	= 32,
 		.np	= 3,
 		.tap	= { 14, 10, 8 }
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
 			  "\x22\x33\x44\x55\x66\x77\x88\x99"
 			  "\xca\xfe\xba\xbe\xfe\xed\xbe\xef",
-		.ilen	= 24,
-		.result	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
 			  "\xf7\x9c\x89\x2a\x33\x8f\x4a\x8b"
 			  "\xb4\x99\x26\xf7\x1f\xe1\xd4\x90",
-		.rlen	= 24,
+		.len	= 24,
 		.np	= 4,
 		.tap	= { 2, 1, 3, 18 }
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
 			  "\x22\x33\x44\x55\x66\x77\x88\x99",
-		.ilen	= 16,
-		.result	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
 			  "\xf7\x9c\x89\x2a\x33\x8f\x4a\x8b",
-		.rlen	= 16,
+		.len	= 16,
 		.np	= 5,
 		.tap	= { 2, 2, 2, 2, 8 }
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xe7",
-		.ilen	= 8,
-		.result	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xe7",
+		.ctext	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d",
+		.len	= 8,
 		.np	= 8,
 		.tap	= { 1, 1, 1, 1, 1, 1, 1, 1 }
 	}, { /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
 		.klen	= 8,
-		.input	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
+		.ptext	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
 			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
 			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
 			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
@@ -5677,8 +5686,7 @@ static const struct cipher_testvec des_enc_tv_template[] = {
 			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
 			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
 			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
-		.ilen	= 248,
-		.result	= "\x88\xCB\x1F\xAB\x2F\x2A\x49\x57"
+		.ctext	= "\x88\xCB\x1F\xAB\x2F\x2A\x49\x57"
 			  "\x92\xB9\x77\xFF\x2F\x47\x58\xDD"
 			  "\xD7\x8A\x91\x95\x26\x33\x78\xB2"
 			  "\x33\xBA\xB2\x3E\x02\xF5\x1F\xEF"
@@ -5709,180 +5717,68 @@ static const struct cipher_testvec des_enc_tv_template[] = {
 			  "\x46\x31\x4C\x5E\x2E\x95\x61\xEF"
 			  "\xE1\x58\x39\x09\xB4\x8B\x40\xAC"
 			  "\x5F\x62\xC7\x72\xD9\xFC\xCB\x9A",
-		.rlen	= 248,
+		.len	= 248,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 248 - 10, 2, 8 },
 	},
 };
 
-static const struct cipher_testvec des_dec_tv_template[] = {
-	{ /* From Applied Cryptography */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.input	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d",
-		.ilen	= 8,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xe7",
-		.rlen	= 8,
-	}, { /* Sbox test from NBS */
-		.key	= "\x7c\xa1\x10\x45\x4a\x1a\x6e\x57",
-		.klen	= 8,
-		.input	= "\x69\x0f\x5b\x0d\x9a\x26\x93\x9b",
-		.ilen	= 8,
-		.result	= "\x01\xa1\xd6\xd0\x39\x77\x67\x42",
-		.rlen	= 8,
-	}, { /* Two blocks, for chunking test */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.input	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
-			  "\x69\x0f\x5b\x0d\x9a\x26\x93\x9b",
-		.ilen	= 16,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
-			  "\xa3\x99\x7b\xca\xaf\x69\xa0\xf5",
-		.rlen	= 16,
-		.np	= 2,
-		.tap	= { 8, 8 }
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.input	= "\xc9\x57\x44\x25\x6a\x5e\xd3\x1d"
-			  "\x69\x0f\x5b\x0d\x9a\x26\x93\x9b",
-		.ilen	= 16,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xe7"
-			  "\xa3\x99\x7b\xca\xaf\x69\xa0\xf5",
-		.rlen	= 16,
-		.np	= 3,
-		.tap	= { 3, 12, 1 }
-	}, { /* Generated with Crypto++ */
-		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
-		.klen	= 8,
-		.input	= "\x88\xCB\x1F\xAB\x2F\x2A\x49\x57"
-			  "\x92\xB9\x77\xFF\x2F\x47\x58\xDD"
-			  "\xD7\x8A\x91\x95\x26\x33\x78\xB2"
-			  "\x33\xBA\xB2\x3E\x02\xF5\x1F\xEF"
-			  "\x98\xC5\xA6\xD2\x7D\x79\xEC\xB3"
-			  "\x45\xF3\x4C\x61\xAC\x6C\xC2\x55"
-			  "\xE5\xD3\x06\x58\x8A\x42\x3E\xDD"
-			  "\x3D\x20\x45\xE9\x6F\x0D\x25\xA8"
-			  "\xA5\xC7\x69\xCE\xD5\x3B\x7B\xC9"
-			  "\x9E\x65\xE7\xA3\xF2\xE4\x18\x94"
-			  "\xD2\x81\xE9\x33\x2B\x2D\x49\xC4"
-			  "\xFE\xDA\x7F\xE2\xF2\x8C\x9C\xDC"
-			  "\x73\x58\x11\x1F\x81\xD7\x21\x1A"
-			  "\x80\xD0\x0D\xE8\x45\xD6\xD8\xD5"
-			  "\x2E\x51\x16\xCA\x09\x89\x54\x62"
-			  "\xF7\x04\x3D\x75\xB9\xA3\x84\xF4"
-			  "\x62\xF0\x02\x58\x83\xAF\x30\x87"
-			  "\x85\x3F\x01\xCD\x8E\x58\x42\xC4"
-			  "\x41\x73\xE0\x15\x0A\xE6\x2E\x80"
-			  "\x94\xF8\x5B\x3A\x4E\xDF\x51\xB2"
-			  "\x9D\xE4\xC4\x9D\xF7\x3F\xF8\x8E"
-			  "\x37\x22\x4D\x00\x2A\xEF\xC1\x0F"
-			  "\x14\xA0\x66\xAB\x79\x39\xD0\x8E"
-			  "\xE9\x95\x61\x74\x12\xED\x07\xD7"
-			  "\xDD\x95\xDC\x7B\x57\x25\x27\x9C"
-			  "\x51\x96\x16\xF7\x94\x61\xB8\x87"
-			  "\xF0\x21\x1B\x32\xFB\x07\x0F\x29"
-			  "\x56\xBD\x9D\x22\xA2\x9F\xA2\xB9"
-			  "\x46\x31\x4C\x5E\x2E\x95\x61\xEF"
-			  "\xE1\x58\x39\x09\xB4\x8B\x40\xAC"
-			  "\x5F\x62\xC7\x72\xD9\xFC\xCB\x9A",
-		.ilen	= 248,
-		.result	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
-			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
-			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
-			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
-			  "\xAB\x14\x7D\x09\x72\xDB\x44\xD0"
-			  "\x39\xA2\x0B\x97\x00\x69\xF5\x5E"
-			  "\xC7\x30\xBC\x25\x8E\x1A\x83\xEC"
-			  "\x55\xE1\x4A\xB3\x1C\xA8\x11\x7A"
-			  "\x06\x6F\xD8\x41\xCD\x36\x9F\x08"
-			  "\x94\xFD\x66\xF2\x5B\xC4\x2D\xB9"
-			  "\x22\x8B\x17\x80\xE9\x52\xDE\x47"
-			  "\xB0\x19\xA5\x0E\x77\x03\x6C\xD5"
-			  "\x3E\xCA\x33\x9C\x05\x91\xFA\x63"
-			  "\xEF\x58\xC1\x2A\xB6\x1F\x88\x14"
-			  "\x7D\xE6\x4F\xDB\x44\xAD\x16\xA2"
-			  "\x0B\x74\x00\x69\xD2\x3B\xC7\x30"
-			  "\x99\x02\x8E\xF7\x60\xEC\x55\xBE"
-			  "\x27\xB3\x1C\x85\x11\x7A\xE3\x4C"
-			  "\xD8\x41\xAA\x13\x9F\x08\x71\xFD"
-			  "\x66\xCF\x38\xC4\x2D\x96\x22\x8B"
-			  "\xF4\x5D\xE9\x52\xBB\x24\xB0\x19"
-			  "\x82\x0E\x77\xE0\x49\xD5\x3E\xA7"
-			  "\x10\x9C\x05\x6E\xFA\x63\xCC\x35"
-			  "\xC1\x2A\x93\x1F\x88\xF1\x5A\xE6"
-			  "\x4F\xB8\x21\xAD\x16\x7F\x0B\x74"
-			  "\xDD\x46\xD2\x3B\xA4\x0D\x99\x02"
-			  "\x6B\xF7\x60\xC9\x32\xBE\x27\x90"
-			  "\x1C\x85\xEE\x57\xE3\x4C\xB5\x1E"
-			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
-			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
-			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
-		.rlen	= 248,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 248 - 10, 2, 8 },
-	},
-};
-
-static const struct cipher_testvec des_cbc_enc_tv_template[] = {
+static const struct cipher_testvec des_cbc_tv_template[] = {
 	{ /* From OpenSSL */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
 		.iv	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.input	= "\x37\x36\x35\x34\x33\x32\x31\x20"
+		.ptext	= "\x37\x36\x35\x34\x33\x32\x31\x20"
 			  "\x4e\x6f\x77\x20\x69\x73\x20\x74"
 			  "\x68\x65\x20\x74\x69\x6d\x65\x20",
-		.ilen	= 24,
-		.result	= "\xcc\xd1\x73\xff\xab\x20\x39\xf4"
+		.ctext	= "\xcc\xd1\x73\xff\xab\x20\x39\xf4"
 			  "\xac\xd8\xae\xfd\xdf\xd8\xa1\xeb"
 			  "\x46\x8e\x91\x15\x78\x88\xba\x68",
-		.rlen	= 24,
+		.len	= 24,
 	}, { /* FIPS Pub 81 */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
 		.iv	= "\x12\x34\x56\x78\x90\xab\xcd\xef",
-		.input	= "\x4e\x6f\x77\x20\x69\x73\x20\x74",
-		.ilen	= 8,
-		.result	= "\xe5\xc7\xcd\xde\x87\x2b\xf2\x7c",
-		.rlen	= 8,
+		.ptext	= "\x4e\x6f\x77\x20\x69\x73\x20\x74",
+		.ctext	= "\xe5\xc7\xcd\xde\x87\x2b\xf2\x7c",
+		.len	= 8,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
 		.iv	= "\xe5\xc7\xcd\xde\x87\x2b\xf2\x7c",
-		.input	= "\x68\x65\x20\x74\x69\x6d\x65\x20",
-		.ilen	= 8,
-		.result	= "\x43\xe9\x34\x00\x8c\x38\x9c\x0f",
-		.rlen	= 8,
+		.ptext	= "\x68\x65\x20\x74\x69\x6d\x65\x20",
+		.ctext	= "\x43\xe9\x34\x00\x8c\x38\x9c\x0f",
+		.len	= 8,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
 		.iv	= "\x43\xe9\x34\x00\x8c\x38\x9c\x0f",
-		.input	= "\x66\x6f\x72\x20\x61\x6c\x6c\x20",
-		.ilen	= 8,
-		.result	= "\x68\x37\x88\x49\x9a\x7c\x05\xf6",
-		.rlen	= 8,
+		.ptext	= "\x66\x6f\x72\x20\x61\x6c\x6c\x20",
+		.ctext	= "\x68\x37\x88\x49\x9a\x7c\x05\xf6",
+		.len	= 8,
+		.np	= 2,
+		.tap	= { 4, 4 },
+		.also_non_np = 1,
 	}, { /* Copy of openssl vector for chunk testing */
 	     /* From OpenSSL */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
 		.iv	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.input	= "\x37\x36\x35\x34\x33\x32\x31\x20"
+		.ptext	= "\x37\x36\x35\x34\x33\x32\x31\x20"
 			  "\x4e\x6f\x77\x20\x69\x73\x20\x74"
 			  "\x68\x65\x20\x74\x69\x6d\x65\x20",
-		.ilen	= 24,
-		.result	= "\xcc\xd1\x73\xff\xab\x20\x39\xf4"
+		.ctext	= "\xcc\xd1\x73\xff\xab\x20\x39\xf4"
 			  "\xac\xd8\xae\xfd\xdf\xd8\xa1\xeb"
 			  "\x46\x8e\x91\x15\x78\x88\xba\x68",
-		.rlen	= 24,
+		.len	= 24,
 		.np	= 2,
 		.tap	= { 13, 11 }
 	}, { /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
 		.klen	= 8,
 		.iv	= "\xE7\x82\x1D\xB8\x53\x11\xAC\x47",
-		.input	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
+		.ptext	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
 			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
 			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
 			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
@@ -5913,85 +5809,7 @@ static const struct cipher_testvec des_cbc_enc_tv_template[] = {
 			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
 			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
 			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
-		.ilen	= 248,
-		.result	= "\x71\xCC\x56\x1C\x87\x2C\x43\x20"
-			  "\x1C\x20\x13\x09\xF9\x2B\x40\x47"
-			  "\x99\x10\xD1\x1B\x65\x33\x33\xBA"
-			  "\x88\x0D\xA2\xD1\x86\xFF\x4D\xF4"
-			  "\x5A\x0C\x12\x96\x32\x57\xAA\x26"
-			  "\xA7\xF4\x32\x8D\xBC\x10\x31\x9E"
-			  "\x81\x72\x74\xDE\x30\x19\x69\x49"
-			  "\x54\x9C\xC3\xEB\x0B\x97\xDD\xD1"
-			  "\xE8\x6D\x0D\x05\x83\xA5\x12\x08"
-			  "\x47\xF8\x88\x03\x86\x51\x3C\xEF"
-			  "\xE7\x11\x73\x4D\x44\x2B\xE2\x16"
-			  "\xE8\xA5\x06\x50\x66\x70\x0E\x14"
-			  "\xBA\x21\x3B\xD5\x23\x5B\xA7\x8F"
-			  "\x56\xB6\xA7\x44\xDB\x86\xAB\x69"
-			  "\x33\x3C\xBE\x64\xC4\x22\xD3\xFE"
-			  "\x49\x90\x88\x6A\x09\x8F\x76\x59"
-			  "\xCB\xB7\xA0\x2D\x79\x75\x92\x8A"
-			  "\x82\x1D\xC2\xFE\x09\x1F\x78\x6B"
-			  "\x2F\xD6\xA4\x87\x1E\xC4\x53\x63"
-			  "\x80\x02\x61\x2F\xE3\x46\xB6\xB5"
-			  "\xAA\x95\xF4\xEE\xA7\x64\x2B\x4F"
-			  "\x20\xCF\xD2\x47\x4E\x39\x65\xB3"
-			  "\x11\x87\xA2\x6C\x49\x7E\x36\xC7"
-			  "\x62\x8B\x48\x0D\x6A\x64\x00\xBD"
-			  "\x71\x91\x8C\xE9\x70\x19\x01\x4F"
-			  "\x4E\x68\x23\xBA\xDA\x24\x2E\x45"
-			  "\x02\x14\x33\x21\xAE\x58\x4B\xCF"
-			  "\x3B\x4B\xE8\xF8\xF6\x4F\x34\x93"
-			  "\xD7\x07\x8A\xD7\x18\x92\x36\x8C"
-			  "\x82\xA9\xBD\x6A\x31\x91\x39\x11"
-			  "\xC6\x4A\xF3\x55\xC7\x29\x2E\x63",
-		.rlen	= 248,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 248 - 10, 2, 8 },
-	},
-};
-
-static const struct cipher_testvec des_cbc_dec_tv_template[] = {
-	{ /* FIPS Pub 81 */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.iv	= "\x12\x34\x56\x78\x90\xab\xcd\xef",
-		.input	= "\xe5\xc7\xcd\xde\x87\x2b\xf2\x7c",
-		.ilen	= 8,
-		.result	= "\x4e\x6f\x77\x20\x69\x73\x20\x74",
-		.rlen	= 8,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.iv	= "\xe5\xc7\xcd\xde\x87\x2b\xf2\x7c",
-		.input	= "\x43\xe9\x34\x00\x8c\x38\x9c\x0f",
-		.ilen	= 8,
-		.result	= "\x68\x65\x20\x74\x69\x6d\x65\x20",
-		.rlen	= 8,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.iv	= "\x43\xe9\x34\x00\x8c\x38\x9c\x0f",
-		.input	= "\x68\x37\x88\x49\x9a\x7c\x05\xf6",
-		.ilen	= 8,
-		.result	= "\x66\x6f\x72\x20\x61\x6c\x6c\x20",
-		.rlen	= 8,
-	}, { /* Copy of above, for chunk testing */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.iv	= "\x43\xe9\x34\x00\x8c\x38\x9c\x0f",
-		.input	= "\x68\x37\x88\x49\x9a\x7c\x05\xf6",
-		.ilen	= 8,
-		.result	= "\x66\x6f\x72\x20\x61\x6c\x6c\x20",
-		.rlen	= 8,
-		.np	= 2,
-		.tap	= { 4, 4 }
-	}, { /* Generated with Crypto++ */
-		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
-		.klen	= 8,
-		.iv	= "\xE7\x82\x1D\xB8\x53\x11\xAC\x47",
-		.input	= "\x71\xCC\x56\x1C\x87\x2C\x43\x20"
+		.ctext	= "\x71\xCC\x56\x1C\x87\x2C\x43\x20"
 			  "\x1C\x20\x13\x09\xF9\x2B\x40\x47"
 			  "\x99\x10\xD1\x1B\x65\x33\x33\xBA"
 			  "\x88\x0D\xA2\xD1\x86\xFF\x4D\xF4"
@@ -6022,51 +5840,19 @@ static const struct cipher_testvec des_cbc_dec_tv_template[] = {
 			  "\xD7\x07\x8A\xD7\x18\x92\x36\x8C"
 			  "\x82\xA9\xBD\x6A\x31\x91\x39\x11"
 			  "\xC6\x4A\xF3\x55\xC7\x29\x2E\x63",
-		.ilen	= 248,
-		.result	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
-			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
-			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
-			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
-			  "\xAB\x14\x7D\x09\x72\xDB\x44\xD0"
-			  "\x39\xA2\x0B\x97\x00\x69\xF5\x5E"
-			  "\xC7\x30\xBC\x25\x8E\x1A\x83\xEC"
-			  "\x55\xE1\x4A\xB3\x1C\xA8\x11\x7A"
-			  "\x06\x6F\xD8\x41\xCD\x36\x9F\x08"
-			  "\x94\xFD\x66\xF2\x5B\xC4\x2D\xB9"
-			  "\x22\x8B\x17\x80\xE9\x52\xDE\x47"
-			  "\xB0\x19\xA5\x0E\x77\x03\x6C\xD5"
-			  "\x3E\xCA\x33\x9C\x05\x91\xFA\x63"
-			  "\xEF\x58\xC1\x2A\xB6\x1F\x88\x14"
-			  "\x7D\xE6\x4F\xDB\x44\xAD\x16\xA2"
-			  "\x0B\x74\x00\x69\xD2\x3B\xC7\x30"
-			  "\x99\x02\x8E\xF7\x60\xEC\x55\xBE"
-			  "\x27\xB3\x1C\x85\x11\x7A\xE3\x4C"
-			  "\xD8\x41\xAA\x13\x9F\x08\x71\xFD"
-			  "\x66\xCF\x38\xC4\x2D\x96\x22\x8B"
-			  "\xF4\x5D\xE9\x52\xBB\x24\xB0\x19"
-			  "\x82\x0E\x77\xE0\x49\xD5\x3E\xA7"
-			  "\x10\x9C\x05\x6E\xFA\x63\xCC\x35"
-			  "\xC1\x2A\x93\x1F\x88\xF1\x5A\xE6"
-			  "\x4F\xB8\x21\xAD\x16\x7F\x0B\x74"
-			  "\xDD\x46\xD2\x3B\xA4\x0D\x99\x02"
-			  "\x6B\xF7\x60\xC9\x32\xBE\x27\x90"
-			  "\x1C\x85\xEE\x57\xE3\x4C\xB5\x1E"
-			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
-			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
-			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
-		.rlen	= 248,
+		.len	= 248,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 248 - 10, 2, 8 },
 	},
 };
 
-static const struct cipher_testvec des_ctr_enc_tv_template[] = {
+static const struct cipher_testvec des_ctr_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
 		.klen	= 8,
 		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
+		.ptext	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
 			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
 			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
 			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
@@ -6097,8 +5883,7 @@ static const struct cipher_testvec des_ctr_enc_tv_template[] = {
 			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
 			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
 			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
-		.ilen	= 248,
-		.result	= "\x2F\x96\x06\x0F\x50\xC9\x68\x03"
+		.ctext	= "\x2F\x96\x06\x0F\x50\xC9\x68\x03"
 			  "\x0F\x31\xD4\x64\xA5\x29\x77\x35"
 			  "\xBC\x7A\x9F\x19\xE7\x0D\x33\x3E"
 			  "\x12\x0B\x8C\xAE\x48\xAE\xD9\x02"
@@ -6129,7 +5914,7 @@ static const struct cipher_testvec des_ctr_enc_tv_template[] = {
 			  "\x5C\xC4\x15\xC9\x9A\x21\xC5\xCD"
 			  "\x19\x7F\x99\x19\x53\xCE\x1D\x14"
 			  "\x69\x74\xA1\x06\x46\x0F\x4E\x75",
-		.rlen	= 248,
+		.len	= 248,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 248 - 10, 2, 8 },
@@ -6137,7 +5922,7 @@ static const struct cipher_testvec des_ctr_enc_tv_template[] = {
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
 		.klen	= 8,
 		.iv	= "\xE7\x82\x1D\xB8\x53\x11\xAC\x47",
-		.input	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
+		.ptext	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
 			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
 			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
 			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
@@ -6168,8 +5953,7 @@ static const struct cipher_testvec des_ctr_enc_tv_template[] = {
 			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
 			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
 			  "\xC6\x2F\xBB\x24\x8D\x19\x82",
-		.ilen	= 247,
-		.result	= "\x62\xE5\xF4\xDC\x99\xE7\x89\xE3"
+		.ctext	= "\x62\xE5\xF4\xDC\x99\xE7\x89\xE3"
 			  "\xF4\x10\xCC\x21\x99\xEB\xDC\x15"
 			  "\x19\x13\x93\x27\x9D\xB6\x6F\x45"
 			  "\x17\x55\x61\x72\xC8\xD3\x7F\xA5"
@@ -6200,193 +5984,44 @@ static const struct cipher_testvec des_ctr_enc_tv_template[] = {
 			  "\xDF\x85\x2D\xE1\xB2\xD6\xAB\x94"
 			  "\xA5\xA6\xE7\xB0\x51\x36\x52\x37"
 			  "\x91\x45\x05\x3E\x58\xBF\x32",
-		.rlen	= 247,
-		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 247 - 8, 8 },
-	},
-};
-
-static const struct cipher_testvec des_ctr_dec_tv_template[] = {
-	{ /* Generated with Crypto++ */
-		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
-		.klen	= 8,
-		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x2F\x96\x06\x0F\x50\xC9\x68\x03"
-			  "\x0F\x31\xD4\x64\xA5\x29\x77\x35"
-			  "\xBC\x7A\x9F\x19\xE7\x0D\x33\x3E"
-			  "\x12\x0B\x8C\xAE\x48\xAE\xD9\x02"
-			  "\x0A\xD4\xB0\xD6\x37\xB2\x65\x1C"
-			  "\x4B\x65\xEB\x24\xB5\x8E\xAD\x47"
-			  "\x0D\xDA\x79\x77\xA0\x29\xA0\x2B"
-			  "\xC8\x0F\x85\xDC\x03\x13\xA9\x04"
-			  "\x19\x40\xBE\xBE\x5C\x49\x4A\x69"
-			  "\xED\xE8\xE1\x9E\x14\x43\x74\xDE"
-			  "\xEC\x6E\x11\x3F\x36\xEF\x7B\xFB"
-			  "\xBE\x4C\x91\x43\x22\x65\x72\x48"
-			  "\xE2\x12\xED\x88\xAC\xA7\xC9\x91"
-			  "\x14\xA2\x36\x1C\x29\xFF\xC8\x4F"
-			  "\x72\x5C\x4B\xB0\x1E\x93\xC2\xFA"
-			  "\x9D\x53\x86\xA0\xAE\xC6\xB7\x3C"
-			  "\x59\x0C\xD0\x8F\xA6\xD8\xA4\x31"
-			  "\xB7\x30\x1C\x21\x38\xFB\x68\x8C"
-			  "\x2E\xF5\x6E\x73\xC3\x16\x5F\x12"
-			  "\x0C\x33\xB9\x1E\x7B\x70\xDE\x86"
-			  "\x32\xB3\xC1\x16\xAB\xD9\x49\x0B"
-			  "\x96\x28\x72\x6B\xF3\x30\xA9\xEB"
-			  "\x69\xE2\x1E\x58\x46\xA2\x8E\xC7"
-			  "\xC0\xEF\x07\xB7\x77\x2C\x00\x05"
-			  "\x46\xBD\xFE\x53\x81\x8B\xA4\x03"
-			  "\x20\x0F\xDB\x78\x0B\x1F\x53\x04"
-			  "\x4C\x60\x4C\xC3\x2A\x86\x86\x7E"
-			  "\x13\xD2\x26\xED\x5D\x3E\x9C\xF2"
-			  "\x5C\xC4\x15\xC9\x9A\x21\xC5\xCD"
-			  "\x19\x7F\x99\x19\x53\xCE\x1D\x14"
-			  "\x69\x74\xA1\x06\x46\x0F\x4E\x75",
-		.ilen	= 248,
-		.result	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
-			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
-			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
-			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
-			  "\xAB\x14\x7D\x09\x72\xDB\x44\xD0"
-			  "\x39\xA2\x0B\x97\x00\x69\xF5\x5E"
-			  "\xC7\x30\xBC\x25\x8E\x1A\x83\xEC"
-			  "\x55\xE1\x4A\xB3\x1C\xA8\x11\x7A"
-			  "\x06\x6F\xD8\x41\xCD\x36\x9F\x08"
-			  "\x94\xFD\x66\xF2\x5B\xC4\x2D\xB9"
-			  "\x22\x8B\x17\x80\xE9\x52\xDE\x47"
-			  "\xB0\x19\xA5\x0E\x77\x03\x6C\xD5"
-			  "\x3E\xCA\x33\x9C\x05\x91\xFA\x63"
-			  "\xEF\x58\xC1\x2A\xB6\x1F\x88\x14"
-			  "\x7D\xE6\x4F\xDB\x44\xAD\x16\xA2"
-			  "\x0B\x74\x00\x69\xD2\x3B\xC7\x30"
-			  "\x99\x02\x8E\xF7\x60\xEC\x55\xBE"
-			  "\x27\xB3\x1C\x85\x11\x7A\xE3\x4C"
-			  "\xD8\x41\xAA\x13\x9F\x08\x71\xFD"
-			  "\x66\xCF\x38\xC4\x2D\x96\x22\x8B"
-			  "\xF4\x5D\xE9\x52\xBB\x24\xB0\x19"
-			  "\x82\x0E\x77\xE0\x49\xD5\x3E\xA7"
-			  "\x10\x9C\x05\x6E\xFA\x63\xCC\x35"
-			  "\xC1\x2A\x93\x1F\x88\xF1\x5A\xE6"
-			  "\x4F\xB8\x21\xAD\x16\x7F\x0B\x74"
-			  "\xDD\x46\xD2\x3B\xA4\x0D\x99\x02"
-			  "\x6B\xF7\x60\xC9\x32\xBE\x27\x90"
-			  "\x1C\x85\xEE\x57\xE3\x4C\xB5\x1E"
-			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
-			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
-			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
-		.rlen	= 248,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 248 - 10, 2, 8 },
-	}, { /* Generated with Crypto++ */
-		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
-		.klen	= 8,
-		.iv	= "\xE7\x82\x1D\xB8\x53\x11\xAC\x47",
-		.input	= "\x62\xE5\xF4\xDC\x99\xE7\x89\xE3"
-			  "\xF4\x10\xCC\x21\x99\xEB\xDC\x15"
-			  "\x19\x13\x93\x27\x9D\xB6\x6F\x45"
-			  "\x17\x55\x61\x72\xC8\xD3\x7F\xA5"
-			  "\x32\xD0\xD3\x02\x15\xA4\x05\x23"
-			  "\x9C\x23\x61\x60\x77\x7B\x6C\x95"
-			  "\x26\x49\x42\x2E\xF3\xC1\x8C\x6D"
-			  "\xC8\x47\xD5\x94\xE7\x53\xC8\x23"
-			  "\x1B\xA5\x0B\xCB\x12\xD3\x7A\x12"
-			  "\xA4\x42\x15\x34\xF7\x5F\xDC\x58"
-			  "\x5B\x58\x4C\xAD\xD1\x33\x8E\xE6"
-			  "\xE5\xA0\xDA\x4D\x94\x3D\x63\xA8"
-			  "\x02\x82\xBB\x16\xB8\xDC\xB5\x58"
-			  "\xC3\x2D\x79\xE4\x25\x79\x43\xF9"
-			  "\x6D\xD3\xCA\xC0\xE8\x12\xD4\x7E"
-			  "\x04\x25\x79\xFD\x27\xFB\xC4\xEA"
-			  "\x32\x94\x48\x92\xF3\x68\x1A\x7F"
-			  "\x36\x33\x43\x79\xF7\xCA\xC2\x38"
-			  "\xC0\x68\xD4\x53\xA9\xCC\x43\x0C"
-			  "\x40\x57\x3E\xED\x00\x9F\x22\x6E"
-			  "\x80\x99\x0B\xCC\x40\x63\x46\x8A"
-			  "\xE8\xC4\x9B\x6D\x7A\x08\x6E\xA9"
-			  "\x6F\x84\xBC\xB3\xF4\x95\x0B\x2D"
-			  "\x6A\xBA\x37\x50\xC3\xCF\x9F\x7C"
-			  "\x59\x5E\xDE\x0B\x30\xFA\x34\x8A"
-			  "\xF8\xD1\xA2\xF8\x4E\xBD\x5D\x5E"
-			  "\x7D\x71\x99\xE0\xF6\xE5\x7C\xE0"
-			  "\x6D\xEE\x82\x89\x92\xD4\xF5\xD7"
-			  "\xDF\x85\x2D\xE1\xB2\xD6\xAB\x94"
-			  "\xA5\xA6\xE7\xB0\x51\x36\x52\x37"
-			  "\x91\x45\x05\x3E\x58\xBF\x32",
-		.ilen	= 247,
-		.result	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
-			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
-			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
-			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
-			  "\xAB\x14\x7D\x09\x72\xDB\x44\xD0"
-			  "\x39\xA2\x0B\x97\x00\x69\xF5\x5E"
-			  "\xC7\x30\xBC\x25\x8E\x1A\x83\xEC"
-			  "\x55\xE1\x4A\xB3\x1C\xA8\x11\x7A"
-			  "\x06\x6F\xD8\x41\xCD\x36\x9F\x08"
-			  "\x94\xFD\x66\xF2\x5B\xC4\x2D\xB9"
-			  "\x22\x8B\x17\x80\xE9\x52\xDE\x47"
-			  "\xB0\x19\xA5\x0E\x77\x03\x6C\xD5"
-			  "\x3E\xCA\x33\x9C\x05\x91\xFA\x63"
-			  "\xEF\x58\xC1\x2A\xB6\x1F\x88\x14"
-			  "\x7D\xE6\x4F\xDB\x44\xAD\x16\xA2"
-			  "\x0B\x74\x00\x69\xD2\x3B\xC7\x30"
-			  "\x99\x02\x8E\xF7\x60\xEC\x55\xBE"
-			  "\x27\xB3\x1C\x85\x11\x7A\xE3\x4C"
-			  "\xD8\x41\xAA\x13\x9F\x08\x71\xFD"
-			  "\x66\xCF\x38\xC4\x2D\x96\x22\x8B"
-			  "\xF4\x5D\xE9\x52\xBB\x24\xB0\x19"
-			  "\x82\x0E\x77\xE0\x49\xD5\x3E\xA7"
-			  "\x10\x9C\x05\x6E\xFA\x63\xCC\x35"
-			  "\xC1\x2A\x93\x1F\x88\xF1\x5A\xE6"
-			  "\x4F\xB8\x21\xAD\x16\x7F\x0B\x74"
-			  "\xDD\x46\xD2\x3B\xA4\x0D\x99\x02"
-			  "\x6B\xF7\x60\xC9\x32\xBE\x27\x90"
-			  "\x1C\x85\xEE\x57\xE3\x4C\xB5\x1E"
-			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
-			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
-			  "\xC6\x2F\xBB\x24\x8D\x19\x82",
-		.rlen	= 247,
+		.len	= 247,
 		.also_non_np = 1,
 		.np	= 2,
 		.tap	= { 247 - 8, 8 },
 	},
 };
 
-static const struct cipher_testvec des3_ede_enc_tv_template[] = {
+static const struct cipher_testvec des3_ede_tv_template[] = {
 	{ /* These are from openssl */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\x55\x55\x55\x55\x55\x55\x55\x55"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
 		.klen	= 24,
-		.input	= "\x73\x6f\x6d\x65\x64\x61\x74\x61",
-		.ilen	= 8,
-		.result	= "\x18\xd7\x48\xe5\x63\x62\x05\x72",
-		.rlen	= 8,
+		.ptext	= "\x73\x6f\x6d\x65\x64\x61\x74\x61",
+		.ctext	= "\x18\xd7\x48\xe5\x63\x62\x05\x72",
+		.len	= 8,
 	}, {
 		.key	= "\x03\x52\x02\x07\x67\x20\x82\x17"
 			  "\x86\x02\x87\x66\x59\x08\x21\x98"
 			  "\x64\x05\x6a\xbd\xfe\xa9\x34\x57",
 		.klen	= 24,
-		.input	= "\x73\x71\x75\x69\x67\x67\x6c\x65",
-		.ilen	= 8,
-		.result	= "\xc0\x7d\x2a\x0f\xa5\x66\xfa\x30",
-		.rlen	= 8,
+		.ptext	= "\x73\x71\x75\x69\x67\x67\x6c\x65",
+		.ctext	= "\xc0\x7d\x2a\x0f\xa5\x66\xfa\x30",
+		.len	= 8,
 	}, {
 		.key	= "\x10\x46\x10\x34\x89\x98\x80\x20"
 			  "\x91\x07\xd0\x15\x89\x19\x01\x01"
 			  "\x19\x07\x92\x10\x98\x1a\x01\x01",
 		.klen	= 24,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 8,
-		.result	= "\xe1\xef\x62\xc3\x32\xfe\x82\x5b",
-		.rlen	= 8,
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ctext	= "\xe1\xef\x62\xc3\x32\xfe\x82\x5b",
+		.len	= 8,
 	}, { /* Generated with Crypto++ */
 		.key	= "\xF3\x9C\xD6\xF3\x9C\xB9\x5A\x67"
 			  "\x00\x5A\x67\x00\x2D\xCE\xEB\x2D"
 			  "\xCE\xEB\xB4\x51\x72\xB4\x51\x72",
 		.klen	= 24,
-		.input	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
+		.ptext	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
 			  "\x8B\x12\x86\x69\xF0\x5B\xCF\x56"
 			  "\x39\xAD\x34\x9F\x66\xEA\x7D\xC4"
 			  "\x48\xD3\xBA\x0D\xB1\x18\xE3\x4A"
@@ -6448,8 +6083,7 @@ static const struct cipher_testvec des3_ede_enc_tv_template[] = {
 			  "\xFB\x42\xF6\x59\x20\x54\x3F\x86"
 			  "\x69\x9D\x64\xCF\x56\xDA\xAD\x34"
 			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
-		.ilen	= 496,
-		.result	= "\x4E\x9A\x40\x3D\x61\x7D\x17\xFA"
+		.ctext	= "\x4E\x9A\x40\x3D\x61\x7D\x17\xFA"
 			  "\x16\x86\x88\x0B\xD8\xAE\xF8\xE4"
 			  "\x81\x01\x04\x00\x76\xFA\xED\xD3"
 			  "\x44\x7E\x21\x9D\xF0\xFB\x2B\x64"
@@ -6511,186 +6145,21 @@ static const struct cipher_testvec des3_ede_enc_tv_template[] = {
 			  "\x12\xE1\x71\x4A\xF9\x2A\xF5\xF6"
 			  "\x93\x03\xD7\x51\x09\xFA\xBE\x68"
 			  "\xD8\x45\xFF\x33\xBA\xBB\x2B\x63",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec des3_ede_dec_tv_template[] = {
-	{ /* These are from openssl */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\x55\x55\x55\x55\x55\x55\x55\x55"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.klen	= 24,
-		.input	= "\x18\xd7\x48\xe5\x63\x62\x05\x72",
-		.ilen	= 8,
-		.result	= "\x73\x6f\x6d\x65\x64\x61\x74\x61",
-		.rlen	= 8,
-	}, {
-		.key	= "\x03\x52\x02\x07\x67\x20\x82\x17"
-			  "\x86\x02\x87\x66\x59\x08\x21\x98"
-			  "\x64\x05\x6a\xbd\xfe\xa9\x34\x57",
-		.klen	= 24,
-		.input	= "\xc0\x7d\x2a\x0f\xa5\x66\xfa\x30",
-		.ilen	= 8,
-		.result	= "\x73\x71\x75\x69\x67\x67\x6c\x65",
-		.rlen	= 8,
-	}, {
-		.key	= "\x10\x46\x10\x34\x89\x98\x80\x20"
-			  "\x91\x07\xd0\x15\x89\x19\x01\x01"
-			  "\x19\x07\x92\x10\x98\x1a\x01\x01",
-		.klen	= 24,
-		.input	= "\xe1\xef\x62\xc3\x32\xfe\x82\x5b",
-		.ilen	= 8,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 8,
-	}, { /* Generated with Crypto++ */
-		.key	= "\xF3\x9C\xD6\xF3\x9C\xB9\x5A\x67"
-			  "\x00\x5A\x67\x00\x2D\xCE\xEB\x2D"
-			  "\xCE\xEB\xB4\x51\x72\xB4\x51\x72",
-		.klen	= 24,
-		.input	= "\x4E\x9A\x40\x3D\x61\x7D\x17\xFA"
-			  "\x16\x86\x88\x0B\xD8\xAE\xF8\xE4"
-			  "\x81\x01\x04\x00\x76\xFA\xED\xD3"
-			  "\x44\x7E\x21\x9D\xF0\xFB\x2B\x64"
-			  "\xCA\x4E\x90\xE0\xC0\x63\x28\x92"
-			  "\xF3\x1F\xA4\x53\x2C\x77\xCC\x77"
-			  "\x69\x56\xD0\x19\xAD\x00\x2D\x97"
-			  "\xBC\xDE\x49\x6A\x82\xBC\x16\xE2"
-			  "\x2F\x3E\x72\xEE\xD1\xCE\xFC\x1B"
-			  "\xEA\x32\x56\xE4\x0B\xAF\x27\x36"
-			  "\xAF\x08\xB9\x61\xB7\x48\x23\x27"
-			  "\xEE\x4D\xC8\x79\x56\x06\xEB\xC7"
-			  "\x5B\xCA\x0A\xC6\x5E\x5C\xCB\xB6"
-			  "\x9D\xDA\x04\x59\xE2\x09\x48\x7E"
-			  "\x6B\x37\xC6\xFE\x92\xA9\x1E\x6E"
-			  "\x0D\x19\xFA\x33\x0F\xEE\x36\x68"
-			  "\x11\xBB\xF9\x5A\x73\xAB\x3A\xEA"
-			  "\xAC\x28\xD8\xD5\x27\xE8\x6B\x16"
-			  "\x45\x86\x50\x01\x70\x35\x99\x92"
-			  "\xDF\x0C\x07\x88\x8B\x7F\x9E\x4B"
-			  "\xD2\x04\x84\x90\xC4\x27\xDF\x0A"
-			  "\x49\xA8\xA7\x1A\x6D\x78\x16\xCA"
-			  "\xB3\x18\x5C\xC3\x93\x63\x5A\x68"
-			  "\x77\x02\xBA\xED\x62\x71\xB1\xD9"
-			  "\x5E\xE5\x6F\x1A\xCC\x1D\xBE\x2E"
-			  "\x11\xF3\xA6\x97\xCA\x8E\xBF\xB4"
-			  "\x56\xA1\x36\x6B\xB1\x0A\x3E\x70"
-			  "\xEA\xD7\xCD\x72\x7B\x79\xC8\xAD"
-			  "\x6B\xFE\xFB\xBA\x64\xAE\x19\xC1"
-			  "\x82\xCF\x8A\xA1\x50\x17\x7F\xB2"
-			  "\x6F\x7B\x0F\x52\xC5\x3E\x4A\x52"
-			  "\x3F\xD9\x3F\x01\xA6\x41\x1A\xB3"
-			  "\xB3\x7A\x0E\x8E\x75\xB2\xB1\x5F"
-			  "\xDB\xEA\x84\x13\x26\x6C\x85\x4E"
-			  "\xAE\x6B\xDC\xE7\xE7\xAD\xB0\x06"
-			  "\x5C\xBA\x92\xD0\x30\xBB\x8D\xD2"
-			  "\xAE\x4C\x70\x85\xA0\x07\xE3\x2C"
-			  "\xD1\x27\x9C\xCF\xDB\x13\xB7\xE5"
-			  "\xF9\x6A\x02\xD0\x39\x9D\xB6\xE7"
-			  "\xD1\x17\x25\x08\xF9\xA9\xA6\x67"
-			  "\x38\x80\xD1\x22\xAB\x1A\xD7\x26"
-			  "\xAD\xCA\x19\x1B\xFA\x18\xA7\x57"
-			  "\x31\xEC\xC9\xED\xDB\x79\xC0\x48"
-			  "\xAC\x31\x9F\x03\x8B\x62\x5B\x7E"
-			  "\x0E\xA6\xD0\x64\xEE\xEA\x00\xFC"
-			  "\x58\xC8\xDE\x51\x4E\x17\x15\x11"
-			  "\x66\x58\xB6\x90\xDC\xDF\xA1\x49"
-			  "\xCA\x79\xE9\x31\x31\x42\xDC\x56"
-			  "\x0B\xCD\xB6\x0D\xC7\x64\xF7\x19"
-			  "\xD9\x42\x05\x7F\xBC\x2F\xFC\x90"
-			  "\xAE\x29\x86\xAA\x43\x7A\x4F\x6B"
-			  "\xCE\xEA\xBC\x31\x8D\x65\x9D\x46"
-			  "\xEA\x77\xB4\xF9\x58\xEA\x5D\x84"
-			  "\xE4\xDC\x14\xBB\xBD\x15\x0E\xDA"
-			  "\xD8\xE4\xA4\x5D\x61\xF9\x58\x0F"
-			  "\xE4\x82\x77\xCE\x87\xC0\x09\xF0"
-			  "\xD6\x10\x9E\x34\xE1\x0C\x67\x55"
-			  "\x7B\x6D\xD5\x51\x4B\x00\xEE\xBA"
-			  "\xF2\x7B\xBE\x75\x07\x42\x9D\x99"
-			  "\x12\xE1\x71\x4A\xF9\x2A\xF5\xF6"
-			  "\x93\x03\xD7\x51\x09\xFA\xBE\x68"
-			  "\xD8\x45\xFF\x33\xBA\xBB\x2B\x63",
-		.ilen	= 496,
-		.result	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
-			  "\x8B\x12\x86\x69\xF0\x5B\xCF\x56"
-			  "\x39\xAD\x34\x9F\x66\xEA\x7D\xC4"
-			  "\x48\xD3\xBA\x0D\xB1\x18\xE3\x4A"
-			  "\xFE\x41\x28\x5C\x27\x8E\x11\x85"
-			  "\x6C\xF7\x5E\xC2\x55\x3C\xA0\x0B"
-			  "\x92\x65\xE9\x70\xDB\x4F\xD6\xB9"
-			  "\x00\xB4\x1F\xE6\x49\xFD\x44\x2F"
-			  "\x53\x3A\x8D\x14\x98\x63\xCA\x5D"
-			  "\xC1\xA8\x33\xA7\x0E\x91\x78\xEC"
-			  "\x77\xDE\x42\xD5\xBC\x07\x8B\x12"
-			  "\xE5\x4C\xF0\x5B\x22\x56\x39\x80"
-			  "\x6B\x9F\x66\xC9\x50\xC4\xAF\x36"
-			  "\xBA\x0D\x94\x7F\xE3\x4A\xDD\x41"
-			  "\x28\xB3\x1A\x8E\x11\xF8\x43\xF7"
-			  "\x5E\x21\x55\x3C\x87\x6E\x92\x65"
-			  "\xCC\x57\xDB\xA2\x35\xB9\x00\xEB"
-			  "\x72\xE6\x49\xD0\x44\x2F\xB6\x19"
-			  "\x8D\x14\xFF\x46\xCA\x5D\x24\xA8"
-			  "\x33\x9A\x6D\x91\x78\xC3\x77\xDE"
-			  "\xA1\x08\xBC\x07\xEE\x71\xE5\x4C"
-			  "\xD7\x5B\x22\xB5\x1C\x80\x6B\xF2"
-			  "\x45\xC9\x50\x3B\xAF\x36\x99\x60"
-			  "\x94\x7F\xC6\x4A\xDD\xA4\x0F\xB3"
-			  "\x1A\xED\x74\xF8\x43\x2A\x5E\x21"
-			  "\x88\x13\x87\x6E\xF1\x58\xCC\x57"
-			  "\x3E\xA2\x35\x9C\x67\xEB\x72\xC5"
-			  "\x49\xD0\xBB\x02\xB6\x19\xE0\x4B"
-			  "\xFF\x46\x29\x5D\x24\x8F\x16\x9A"
-			  "\x6D\xF4\x5F\xC3\xAA\x3D\xA1\x08"
-			  "\x93\x7A\xEE\x71\xD8\x4C\xD7\xBE"
-			  "\x01\xB5\x1C\xE7\x4E\xF2\x45\x2C"
-			  "\x50\x3B\x82\x15\x99\x60\xCB\x52"
-			  "\xC6\xA9\x30\xA4\x0F\x96\x79\xED"
-			  "\x74\xDF\x43\x2A\xBD\x04\x88\x13"
-			  "\xFA\x4D\xF1\x58\x23\x57\x3E\x81"
-			  "\x68\x9C\x67\xCE\x51\xC5\xAC\x37"
-			  "\xBB\x02\x95\x7C\xE0\x4B\xD2\x46"
-			  "\x29\xB0\x1B\x8F\x16\xF9\x40\xF4"
-			  "\x5F\x26\xAA\x3D\x84\x6F\x93\x7A"
-			  "\xCD\x54\xD8\xA3\x0A\xBE\x01\xE8"
-			  "\x73\xE7\x4E\xD1\x45\x2C\xB7\x1E"
-			  "\x82\x15\xFC\x47\xCB\x52\x25\xA9"
-			  "\x30\x9B\x62\x96\x79\xC0\x74\xDF"
-			  "\xA6\x09\xBD\x04\xEF\x76\xFA\x4D"
-			  "\xD4\x58\x23\x8A\x1D\x81\x68\xF3"
-			  "\x5A\xCE\x51\x38\xAC\x37\x9E\x61"
-			  "\x95\x7C\xC7\x4B\xD2\xA5\x0C\xB0"
-			  "\x1B\xE2\x75\xF9\x40\x2B\x5F\x26"
-			  "\x89\x10\x84\x6F\xF6\x59\xCD\x54"
-			  "\x3F\xA3\x0A\x9D\x64\xE8\x73\xDA"
-			  "\x4E\xD1\xB8\x03\xB7\x1E\xE1\x48"
-			  "\xFC\x47\x2E\x52\x25\x8C\x17\x9B"
-			  "\x62\xF5\x5C\xC0\xAB\x32\xA6\x09"
-			  "\x90\x7B\xEF\x76\xD9\x4D\xD4\xBF"
-			  "\x06\x8A\x1D\xE4\x4F\xF3\x5A\x2D"
-			  "\x51\x38\x83\x6A\x9E\x61\xC8\x53"
-			  "\xC7\xAE\x31\xA5\x0C\x97\x7E\xE2"
-			  "\x75\xDC\x40\x2B\xB2\x05\x89\x10"
-			  "\xFB\x42\xF6\x59\x20\x54\x3F\x86"
-			  "\x69\x9D\x64\xCF\x56\xDA\xAD\x34"
-			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
+static const struct cipher_testvec des3_ede_cbc_tv_template[] = {
 	{ /* Generated from openssl */
 		.key	= "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24"
 			  "\x44\x4D\x99\x5A\x12\xD6\x40\xC0"
 			  "\xEA\xC2\x84\xE8\x14\x95\xDB\xE8",
 		.klen	= 24,
 		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.input	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
+		.ptext	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
 			  "\x53\x20\x63\x65\x65\x72\x73\x74"
 			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
 			  "\x20\x79\x65\x53\x72\x63\x74\x65"
@@ -6706,8 +6175,7 @@ static const struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
 			  "\x20\x6f\x61\x4d\x79\x6e\x53\x20"
 			  "\x63\x65\x65\x72\x73\x74\x54\x20"
 			  "\x6f\x6f\x4d\x20\x6e\x61\x0a\x79",
-		.ilen	= 128,
-		.result	= "\x0e\x2d\xb6\x97\x3c\x56\x33\xf4"
+		.ctext	= "\x0e\x2d\xb6\x97\x3c\x56\x33\xf4"
 			  "\x67\x17\x21\xc7\x6e\x8a\xd5\x49"
 			  "\x74\xb3\x49\x05\xc5\x1c\xd0\xed"
 			  "\x12\x56\x5c\x53\x96\xb6\x00\x7d"
@@ -6723,7 +6191,7 @@ static const struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
 			  "\xd6\xbc\x5a\xd3\x2d\x54\x43\xcc"
 			  "\x9d\xde\xa5\x70\xe9\x42\x45\x8a"
 			  "\x6b\xfa\xb1\x91\x13\xb0\xd9\x19",
-		.rlen	= 128,
+		.len	= 128,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
 			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
@@ -6731,7 +6199,7 @@ static const struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\xB2\xD7\x48\xED\x06\x44\xF9\x12"
 			  "\xB7\x28\x4D\x83\x24\x59\xF2\x17",
-		.input	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
+		.ptext	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
 			  "\x8B\x12\x86\x69\xF0\x5B\xCF\x56"
 			  "\x39\xAD\x34\x9F\x66\xEA\x7D\xC4"
 			  "\x48\xD3\xBA\x0D\xB1\x18\xE3\x4A"
@@ -6793,125 +6261,7 @@ static const struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
 			  "\xFB\x42\xF6\x59\x20\x54\x3F\x86"
 			  "\x69\x9D\x64\xCF\x56\xDA\xAD\x34"
 			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
-		.ilen	= 496,
-		.result	= "\xF8\xF6\xB5\x60\x5C\x5A\x75\x84"
-			  "\x87\x81\x53\xBA\xC9\x6F\xEC\xD5"
-			  "\x1E\x68\x8E\x85\x12\x86\x1D\x38"
-			  "\x1C\x91\x40\xCC\x69\x6A\xD5\x35"
-			  "\x0D\x7C\xB5\x07\x7C\x7B\x2A\xAF"
-			  "\x32\xBC\xA1\xB3\x84\x31\x1B\x3C"
-			  "\x0A\x2B\xFA\xD3\x9F\xB0\x8C\x37"
-			  "\x8F\x9D\xA7\x6D\x6C\xFA\xD7\x90"
-			  "\xE3\x69\x54\xED\x3A\xC4\xF1\x6B"
-			  "\xB1\xCC\xFB\x7D\xD8\x8E\x17\x0B"
-			  "\x9C\xF6\x4C\xD6\xFF\x03\x4E\xD9"
-			  "\xE6\xA5\xAD\x25\xE6\x17\x69\x63"
-			  "\x11\x35\x61\x94\x88\x7B\x1C\x48"
-			  "\xF1\x24\x20\x29\x6B\x93\x1A\x8E"
-			  "\x43\x03\x89\xD8\xB1\xDA\x47\x7B"
-			  "\x79\x3A\x83\x76\xDA\xAE\xC6\xBB"
-			  "\x22\xF8\xE8\x3D\x9A\x65\x54\xD8"
-			  "\x4C\xE9\xE7\xE4\x63\x2F\x5C\x73"
-			  "\x5A\xC3\xAE\x46\xA8\xCD\x57\xE6"
-			  "\x67\x88\xA5\x20\x6F\x5F\x97\xC7"
-			  "\xCC\x15\xA2\x0A\x93\xEA\x33\xE7"
-			  "\x03\x5F\xEC\x64\x30\x6F\xEE\xD7"
-			  "\x7E\xDF\xD6\xE9\x6F\x3F\xD6\x1E"
-			  "\xBE\x67\x6C\x5B\x97\xA0\x09\xE6"
-			  "\xEE\xFE\x55\xA3\x29\x65\xE0\x12"
-			  "\xA1\x6A\x8A\x6F\xF2\xE6\xF1\x96"
-			  "\x87\xFB\x9C\x05\xDD\x80\xEC\xFF"
-			  "\xC5\xED\x50\xFE\xFC\x91\xCD\xCE"
-			  "\x25\x2C\x5F\xD9\xAD\x95\x7D\x99"
-			  "\xF0\x05\xC4\x71\x46\x5F\xF9\x0D"
-			  "\xD2\x63\xDF\x9B\x96\x2E\x2B\xA6"
-			  "\x2B\x1C\xD5\xFB\x96\x24\x60\x60"
-			  "\x54\x40\xB8\x62\xA4\xF8\x46\x95"
-			  "\x73\x28\xA3\xA6\x16\x2B\x17\xE7"
-			  "\x7A\xF8\x62\x54\x3B\x64\x69\xE1"
-			  "\x71\x34\x29\x5B\x4E\x05\x9B\xFA"
-			  "\x5E\xF1\x96\xB7\xCE\x16\x9B\x59"
-			  "\xF1\x1A\x4C\x51\x26\xFD\x79\xE2"
-			  "\x3B\x8E\x71\x69\x6A\x91\xB6\x65"
-			  "\x32\x09\xB8\xE4\x09\x1F\xEA\x39"
-			  "\xCE\x20\x65\x9F\xD6\xD1\xC7\xF0"
-			  "\x73\x50\x08\x56\x20\x9B\x94\x23"
-			  "\x14\x39\xB7\x2B\xB1\x2D\x6D\x6F"
-			  "\x41\x5B\xCC\xE2\x18\xAE\x62\x89"
-			  "\x78\x8E\x67\x23\xD0\xFB\x2B\xE5"
-			  "\x25\xC9\x48\x97\xB5\xD3\x17\xD5"
-			  "\x6A\x9F\xA7\x48\x0C\x2B\x73\x3B"
-			  "\x57\x08\xAE\x91\xF2\xB7\x57\x89"
-			  "\xF4\xD0\xB0\x07\xB0\x42\x6C\xAF"
-			  "\x98\x1A\xE7\xD1\xAC\x1E\xB5\x02"
-			  "\xD4\x56\x42\x79\x79\x7F\x2A\x77"
-			  "\x25\xE9\x7D\xC1\x88\x19\x2B\x49"
-			  "\x6F\x46\x59\xAB\x56\x1F\x61\xE0"
-			  "\x0C\x24\x9C\xC9\x5B\x63\xA9\x12"
-			  "\xCF\x88\x96\xB6\xA8\x24\xC6\xA8"
-			  "\x21\x85\x1A\x62\x7E\x34\xBB\xEB"
-			  "\xBD\x02\x2A\xC7\xD8\x89\x80\xC5"
-			  "\xB1\xBB\x60\xA5\x22\xFC\x6F\x38"
-			  "\x02\x80\xA3\x28\x22\x75\xE1\xE9"
-			  "\x90\xE9\xFA\x4B\x00\x10\xAC\x58"
-			  "\x83\x70\xFF\x86\xE6\xAA\x0F\x1F"
-			  "\x95\x63\x73\xA2\x44\xAC\xF8\xA5",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec des3_ede_cbc_dec_tv_template[] = {
-	{ /* Generated from openssl */
-		.key	= "\xE9\xC0\xFF\x2E\x76\x0B\x64\x24"
-			  "\x44\x4D\x99\x5A\x12\xD6\x40\xC0"
-			  "\xEA\xC2\x84\xE8\x14\x95\xDB\xE8",
-		.klen	= 24,
-		.iv	= "\x7D\x33\x88\x93\x0F\x93\xB2\x42",
-		.input	= "\x0e\x2d\xb6\x97\x3c\x56\x33\xf4"
-			  "\x67\x17\x21\xc7\x6e\x8a\xd5\x49"
-			  "\x74\xb3\x49\x05\xc5\x1c\xd0\xed"
-			  "\x12\x56\x5c\x53\x96\xb6\x00\x7d"
-			  "\x90\x48\xfc\xf5\x8d\x29\x39\xcc"
-			  "\x8a\xd5\x35\x18\x36\x23\x4e\xd7"
-			  "\x76\xd1\xda\x0c\x94\x67\xbb\x04"
-			  "\x8b\xf2\x03\x6c\xa8\xcf\xb6\xea"
-			  "\x22\x64\x47\xaa\x8f\x75\x13\xbf"
-			  "\x9f\xc2\xc3\xf0\xc9\x56\xc5\x7a"
-			  "\x71\x63\x2e\x89\x7b\x1e\x12\xca"
-			  "\xe2\x5f\xaf\xd8\xa4\xf8\xc9\x7a"
-			  "\xd6\xf9\x21\x31\x62\x44\x45\xa6"
-			  "\xd6\xbc\x5a\xd3\x2d\x54\x43\xcc"
-			  "\x9d\xde\xa5\x70\xe9\x42\x45\x8a"
-			  "\x6b\xfa\xb1\x91\x13\xb0\xd9\x19",
-		.ilen	= 128,
-		.result	= "\x6f\x54\x20\x6f\x61\x4d\x79\x6e"
-			  "\x53\x20\x63\x65\x65\x72\x73\x74"
-			  "\x54\x20\x6f\x6f\x4d\x20\x6e\x61"
-			  "\x20\x79\x65\x53\x72\x63\x74\x65"
-			  "\x20\x73\x6f\x54\x20\x6f\x61\x4d"
-			  "\x79\x6e\x53\x20\x63\x65\x65\x72"
-			  "\x73\x74\x54\x20\x6f\x6f\x4d\x20"
-			  "\x6e\x61\x20\x79\x65\x53\x72\x63"
-			  "\x74\x65\x20\x73\x6f\x54\x20\x6f"
-			  "\x61\x4d\x79\x6e\x53\x20\x63\x65"
-			  "\x65\x72\x73\x74\x54\x20\x6f\x6f"
-			  "\x4d\x20\x6e\x61\x20\x79\x65\x53"
-			  "\x72\x63\x74\x65\x20\x73\x6f\x54"
-			  "\x20\x6f\x61\x4d\x79\x6e\x53\x20"
-			  "\x63\x65\x65\x72\x73\x74\x54\x20"
-			  "\x6f\x6f\x4d\x20\x6e\x61\x0a\x79",
-		.rlen	= 128,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
-			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
-			  "\xEB\xB4\x51\x72\xB4\x51\x72\x1F",
-		.klen	= 24,
-		.iv	= "\xB2\xD7\x48\xED\x06\x44\xF9\x12"
-			  "\xB7\x28\x4D\x83\x24\x59\xF2\x17",
-		.input	= "\xF8\xF6\xB5\x60\x5C\x5A\x75\x84"
+		.ctext	= "\xF8\xF6\xB5\x60\x5C\x5A\x75\x84"
 			  "\x87\x81\x53\xBA\xC9\x6F\xEC\xD5"
 			  "\x1E\x68\x8E\x85\x12\x86\x1D\x38"
 			  "\x1C\x91\x40\xCC\x69\x6A\xD5\x35"
@@ -6973,77 +6323,14 @@ static const struct cipher_testvec des3_ede_cbc_dec_tv_template[] = {
 			  "\x90\xE9\xFA\x4B\x00\x10\xAC\x58"
 			  "\x83\x70\xFF\x86\xE6\xAA\x0F\x1F"
 			  "\x95\x63\x73\xA2\x44\xAC\xF8\xA5",
-		.ilen	= 496,
-		.result	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
-			  "\x8B\x12\x86\x69\xF0\x5B\xCF\x56"
-			  "\x39\xAD\x34\x9F\x66\xEA\x7D\xC4"
-			  "\x48\xD3\xBA\x0D\xB1\x18\xE3\x4A"
-			  "\xFE\x41\x28\x5C\x27\x8E\x11\x85"
-			  "\x6C\xF7\x5E\xC2\x55\x3C\xA0\x0B"
-			  "\x92\x65\xE9\x70\xDB\x4F\xD6\xB9"
-			  "\x00\xB4\x1F\xE6\x49\xFD\x44\x2F"
-			  "\x53\x3A\x8D\x14\x98\x63\xCA\x5D"
-			  "\xC1\xA8\x33\xA7\x0E\x91\x78\xEC"
-			  "\x77\xDE\x42\xD5\xBC\x07\x8B\x12"
-			  "\xE5\x4C\xF0\x5B\x22\x56\x39\x80"
-			  "\x6B\x9F\x66\xC9\x50\xC4\xAF\x36"
-			  "\xBA\x0D\x94\x7F\xE3\x4A\xDD\x41"
-			  "\x28\xB3\x1A\x8E\x11\xF8\x43\xF7"
-			  "\x5E\x21\x55\x3C\x87\x6E\x92\x65"
-			  "\xCC\x57\xDB\xA2\x35\xB9\x00\xEB"
-			  "\x72\xE6\x49\xD0\x44\x2F\xB6\x19"
-			  "\x8D\x14\xFF\x46\xCA\x5D\x24\xA8"
-			  "\x33\x9A\x6D\x91\x78\xC3\x77\xDE"
-			  "\xA1\x08\xBC\x07\xEE\x71\xE5\x4C"
-			  "\xD7\x5B\x22\xB5\x1C\x80\x6B\xF2"
-			  "\x45\xC9\x50\x3B\xAF\x36\x99\x60"
-			  "\x94\x7F\xC6\x4A\xDD\xA4\x0F\xB3"
-			  "\x1A\xED\x74\xF8\x43\x2A\x5E\x21"
-			  "\x88\x13\x87\x6E\xF1\x58\xCC\x57"
-			  "\x3E\xA2\x35\x9C\x67\xEB\x72\xC5"
-			  "\x49\xD0\xBB\x02\xB6\x19\xE0\x4B"
-			  "\xFF\x46\x29\x5D\x24\x8F\x16\x9A"
-			  "\x6D\xF4\x5F\xC3\xAA\x3D\xA1\x08"
-			  "\x93\x7A\xEE\x71\xD8\x4C\xD7\xBE"
-			  "\x01\xB5\x1C\xE7\x4E\xF2\x45\x2C"
-			  "\x50\x3B\x82\x15\x99\x60\xCB\x52"
-			  "\xC6\xA9\x30\xA4\x0F\x96\x79\xED"
-			  "\x74\xDF\x43\x2A\xBD\x04\x88\x13"
-			  "\xFA\x4D\xF1\x58\x23\x57\x3E\x81"
-			  "\x68\x9C\x67\xCE\x51\xC5\xAC\x37"
-			  "\xBB\x02\x95\x7C\xE0\x4B\xD2\x46"
-			  "\x29\xB0\x1B\x8F\x16\xF9\x40\xF4"
-			  "\x5F\x26\xAA\x3D\x84\x6F\x93\x7A"
-			  "\xCD\x54\xD8\xA3\x0A\xBE\x01\xE8"
-			  "\x73\xE7\x4E\xD1\x45\x2C\xB7\x1E"
-			  "\x82\x15\xFC\x47\xCB\x52\x25\xA9"
-			  "\x30\x9B\x62\x96\x79\xC0\x74\xDF"
-			  "\xA6\x09\xBD\x04\xEF\x76\xFA\x4D"
-			  "\xD4\x58\x23\x8A\x1D\x81\x68\xF3"
-			  "\x5A\xCE\x51\x38\xAC\x37\x9E\x61"
-			  "\x95\x7C\xC7\x4B\xD2\xA5\x0C\xB0"
-			  "\x1B\xE2\x75\xF9\x40\x2B\x5F\x26"
-			  "\x89\x10\x84\x6F\xF6\x59\xCD\x54"
-			  "\x3F\xA3\x0A\x9D\x64\xE8\x73\xDA"
-			  "\x4E\xD1\xB8\x03\xB7\x1E\xE1\x48"
-			  "\xFC\x47\x2E\x52\x25\x8C\x17\x9B"
-			  "\x62\xF5\x5C\xC0\xAB\x32\xA6\x09"
-			  "\x90\x7B\xEF\x76\xD9\x4D\xD4\xBF"
-			  "\x06\x8A\x1D\xE4\x4F\xF3\x5A\x2D"
-			  "\x51\x38\x83\x6A\x9E\x61\xC8\x53"
-			  "\xC7\xAE\x31\xA5\x0C\x97\x7E\xE2"
-			  "\x75\xDC\x40\x2B\xB2\x05\x89\x10"
-			  "\xFB\x42\xF6\x59\x20\x54\x3F\x86"
-			  "\x69\x9D\x64\xCF\x56\xDA\xAD\x34"
-			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
+static const struct cipher_testvec des3_ede_ctr_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
 			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
@@ -7051,7 +6338,7 @@ static const struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
 			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
+		.ptext	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
 			  "\x8B\x12\x86\x69\xF0\x5B\xCF\x56"
 			  "\x39\xAD\x34\x9F\x66\xEA\x7D\xC4"
 			  "\x48\xD3\xBA\x0D\xB1\x18\xE3\x4A"
@@ -7113,8 +6400,7 @@ static const struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
 			  "\xFB\x42\xF6\x59\x20\x54\x3F\x86"
 			  "\x69\x9D\x64\xCF\x56\xDA\xAD\x34"
 			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
-		.ilen	= 496,
-		.result	= "\x07\xC2\x08\x20\x72\x1F\x49\xEF"
+		.ctext	= "\x07\xC2\x08\x20\x72\x1F\x49\xEF"
 			  "\x19\xCD\x6F\x32\x53\x05\x22\x15"
 			  "\xA2\x85\x2B\xDB\x85\xD2\xD8\xB9"
 			  "\xDD\x0D\x1B\x45\xCB\x69\x11\xD4"
@@ -7176,7 +6462,7 @@ static const struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
 			  "\x46\xB9\x91\xB6\xE7\x3D\x51\x42"
 			  "\xFD\x51\xB0\xC6\x2C\x63\x13\x78"
 			  "\x5C\xEE\xFC\xCF\xC4\x70\x00\x34",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
@@ -7187,7 +6473,7 @@ static const struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\xB2\xD7\x48\xED\x06\x44\xF9\x12"
 			  "\xB7\x28\x4D\x83\x24\x59\xF2\x17",
-		.input	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
+		.ptext	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
 			  "\x8B\x12\x86\x69\xF0\x5B\xCF\x56"
 			  "\x39\xAD\x34\x9F\x66\xEA\x7D\xC4"
 			  "\x48\xD3\xBA\x0D\xB1\x18\xE3\x4A"
@@ -7250,222 +6536,7 @@ static const struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
 			  "\x69\x9D\x64\xCF\x56\xDA\xAD\x34"
 			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47"
 			  "\x2E\xB1\x18",
-		.ilen	= 499,
-		.result	= "\x23\xFF\x5C\x99\x75\xBB\x1F\xD4"
-			  "\xBC\x27\x9D\x36\x60\xA9\xC9\xF7"
-			  "\x94\x9D\x1B\xFF\x8E\x95\x57\x89"
-			  "\x8C\x2E\x33\x70\x43\x61\xE6\xD2"
-			  "\x82\x33\x63\xB6\xC4\x34\x5E\xF8"
-			  "\x96\x07\xA7\xD2\x3B\x8E\xC9\xAA"
-			  "\x7C\xA0\x55\x89\x2E\xE1\x85\x25"
-			  "\x14\x04\xDA\x6B\xE0\xEE\x56\xCF"
-			  "\x08\x2E\x69\xD4\x54\xDE\x22\x84"
-			  "\x69\xA6\xA7\xD3\x3A\x9A\xE8\x05"
-			  "\x63\xDB\xBF\x46\x3A\x26\x2E\x0F"
-			  "\x58\x5C\x46\xEA\x07\x40\xDA\xE1"
-			  "\x14\x1D\xCD\x4F\x06\xC0\xCA\x54"
-			  "\x1E\xC9\x45\x85\x67\x7C\xC2\xB5"
-			  "\x97\x5D\x61\x78\x2E\x46\xEC\x6A"
-			  "\x53\xF4\xD0\xAE\xFA\xB4\x86\x29"
-			  "\x9F\x17\x33\x24\xD8\xB9\xB2\x05"
-			  "\x93\x88\xEA\xF7\xA0\x70\x69\x49"
-			  "\x88\x6B\x73\x40\x41\x8D\xD9\xD9"
-			  "\x7E\x78\xE9\xBE\x6C\x14\x22\x7A"
-			  "\x66\xE1\xDA\xED\x10\xFF\x69\x1D"
-			  "\xB9\xAA\xF2\x56\x72\x1B\x23\xE2"
-			  "\x45\x54\x8B\xA3\x70\x23\xB4\x5E"
-			  "\x8E\x96\xC9\x05\x00\xB3\xB6\xC2"
-			  "\x2A\x02\x43\x7A\x62\xD5\xC8\xD2"
-			  "\xC2\xD0\xE4\x78\xA1\x7B\x3E\xE8"
-			  "\x9F\x7F\x7D\x40\x54\x30\x3B\xC0"
-			  "\xA5\x54\xFD\xCA\x25\xEC\x44\x3E"
-			  "\x1A\x54\x7F\x88\xD0\xE1\xFE\x71"
-			  "\xCE\x05\x49\x89\xBA\xD6\x72\xE7"
-			  "\xD6\x5D\x3F\xA2\xD9\xAB\xC5\x02"
-			  "\xD6\x43\x22\xAF\xA2\xE4\x80\x85"
-			  "\xD7\x87\xB9\xEA\x43\xDB\xC8\xEF"
-			  "\x5C\x82\x2E\x98\x0D\x30\x41\x6B"
-			  "\x08\x48\x8D\xF0\xF8\x60\xD7\x9D"
-			  "\xE9\xDE\x40\xAD\x0D\xAD\x0D\x58"
-			  "\x2A\x98\x35\xFE\xF7\xDD\x4B\x40"
-			  "\xDE\xB0\x05\xD9\x7B\x09\x4D\xBC"
-			  "\x42\xC0\xF1\x15\x0B\xFA\x26\x6B"
-			  "\xC6\x12\x13\x4F\xCB\x35\xBA\x35"
-			  "\xDD\x7A\x36\x9C\x12\x57\x55\x83"
-			  "\x78\x58\x09\xD0\xB0\xCF\x7C\x5C"
-			  "\x38\xCF\xBD\x79\x5B\x13\x4D\x97"
-			  "\xC1\x85\x6F\x97\xC9\xE8\xC2\xA4"
-			  "\x98\xE2\xBD\x77\x6B\x53\x39\x1A"
-			  "\x28\x10\xE7\xE0\xE7\xDE\x9D\x69"
-			  "\x78\x6F\x8E\xD2\xD9\x5D\xD2\x15"
-			  "\x9E\xB5\x4D\x8C\xC0\x78\x22\x2F"
-			  "\x17\x11\x2E\x99\xD7\xE3\xA4\x4F"
-			  "\x65\xA5\x6B\x03\x2C\x35\x6F\xDA"
-			  "\x8A\x19\x08\xE1\x08\x48\x59\x51"
-			  "\x53\x4B\xD1\xDF\xDA\x14\x50\x5F"
-			  "\xDF\xB5\x8C\xDF\xC6\xFD\x85\xFA"
-			  "\xD4\xF9\x64\x45\x65\x0D\x7D\xF4"
-			  "\xC8\xCD\x3F\x32\xAF\xDD\x30\xED"
-			  "\x7B\xAA\xAC\xF0\xDA\x7F\xDF\x75"
-			  "\x1C\xA4\xF1\xCB\x5E\x4F\x0B\xB4"
-			  "\x97\x73\x28\xDE\xCF\xAF\x82\xBD"
-			  "\xC4\xBA\xB4\x9C\x0D\x16\x77\x42"
-			  "\x42\x39\x7C\x53\xA4\xD4\xDD\x40"
-			  "\x5C\x60\x1F\x6E\xA7\xE2\xDC\xE7"
-			  "\x32\x0F\x05\x2F\xF2\x4C\x95\x3B"
-			  "\xF2\x79\xD9",
-		.rlen	= 499,
-		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 499 - 16, 16 },
-	},
-};
-
-static const struct cipher_testvec des3_ede_ctr_dec_tv_template[] = {
-	{ /* Generated with Crypto++ */
-		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
-			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
-			  "\xEB\xB4\x51\x72\xB4\x51\x72\x1F",
-		.klen	= 24,
-		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
-			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x07\xC2\x08\x20\x72\x1F\x49\xEF"
-			  "\x19\xCD\x6F\x32\x53\x05\x22\x15"
-			  "\xA2\x85\x2B\xDB\x85\xD2\xD8\xB9"
-			  "\xDD\x0D\x1B\x45\xCB\x69\x11\xD4"
-			  "\xEA\xBE\xB2\x45\x5D\x0C\xAE\xBE"
-			  "\xA0\xC1\x27\xAC\x65\x9F\x53\x7E"
-			  "\xAF\xC2\x1B\xB5\xB8\x6D\x36\x0C"
-			  "\x25\xC0\xF8\x6D\x0B\x29\x01\xDA"
-			  "\x13\x78\xDC\x89\x12\x12\x43\xFA"
-			  "\xF6\x12\xEF\x8D\x87\x62\x78\x83"
-			  "\xE2\xBE\x41\x20\x4C\x6D\x35\x1B"
-			  "\xD1\x0C\x30\xCF\xE2\xDE\x2B\x03"
-			  "\xBF\x45\x73\xD4\xE5\x59\x95\xD1"
-			  "\xB3\x9B\x27\x62\x97\xBD\xDE\x7F"
-			  "\xA4\xD2\x39\x80\xAA\x50\x23\xF0"
-			  "\x74\x88\x3D\xA8\x6A\x18\x79\x3B"
-			  "\xC4\x96\x6C\x8D\x22\x40\x92\x6E"
-			  "\xD6\xAD\x2A\x1F\xDE\x63\xC0\xE7"
-			  "\x07\xF7\x2D\xF7\xB5\xF3\xF0\xCC"
-			  "\x01\x7C\x2A\x9B\xC2\x10\xCA\xAA"
-			  "\xFD\x2B\x3F\xC5\xF3\xF6\xFC\x9B"
-			  "\x45\xDB\x53\xE4\x5B\xF3\xC9\x7B"
-			  "\x8E\x52\xFF\xC8\x02\xB8\xAC\x9D"
-			  "\xA1\x00\x39\xDA\x3D\x2D\x0E\x01"
-			  "\x09\x7D\x8D\x5E\xBE\x53\xB9\xB0"
-			  "\x8E\xE7\xE2\x96\x6A\xB2\x78\xEA"
-			  "\xDE\x23\x8B\xA5\xFA\x5C\xE3\xDA"
-			  "\xBF\x8E\x31\x6A\x55\xD1\x6A\xB2"
-			  "\xB5\x46\x6F\xA5\xF0\xEE\xBA\x1F"
-			  "\x9F\x98\xB0\x66\x4F\xD0\x3F\xA9"
-			  "\xDF\x5F\x58\xC4\xF4\xFF\x75\x5C"
-			  "\x40\x3A\x09\x7E\x6E\x1C\x97\xD4"
-			  "\xCC\xE7\xE7\x71\xCF\x0B\x15\x08"
-			  "\x71\xFA\x07\x97\xCD\xE6\xCA\x1D"
-			  "\x14\x28\x0C\xCF\x99\x13\x7A\xF1"
-			  "\xEB\xFA\xFA\x92\x07\xDE\x1D\xA1"
-			  "\xD3\x36\x69\xFE\x51\x4D\x9F\x2E"
-			  "\x83\x37\x4F\x1F\x48\x30\xED\x04"
-			  "\x4D\xA4\xEF\x3A\xCA\x76\xF4\x1C"
-			  "\x41\x8F\x63\x37\x78\x2F\x86\xA6"
-			  "\xEF\x41\x7E\xD2\xAF\x88\xAB\x67"
-			  "\x52\x71\xC3\x8E\xF8\x26\x93\x72"
-			  "\xAA\xD6\x0E\xE7\x0B\x46\xB1\x3A"
-			  "\xB4\x08\xA9\xA8\xA0\xCF\x20\x0C"
-			  "\x52\xBC\x8B\x05\x56\xB2\xBC\x31"
-			  "\x9B\x74\xB9\x29\x29\x96\x9A\x50"
-			  "\xDC\x45\xDC\x1A\xEB\x0C\x64\xD4"
-			  "\xD3\x05\x7E\x59\x55\xC3\xF4\x90"
-			  "\xC2\xAB\xF8\x9B\x8A\xDA\xCE\xA1"
-			  "\xC3\xF4\xAD\x77\xDD\x44\xC8\xAC"
-			  "\xA3\xF1\xC9\xD2\x19\x5C\xB0\xCA"
-			  "\xA2\x34\xC1\xF7\x6C\xFD\xAC\x65"
-			  "\x32\xDC\x48\xC4\xF2\x00\x6B\x77"
-			  "\xF1\x7D\x76\xAC\xC0\x31\x63\x2A"
-			  "\xA5\x3A\x62\xC8\x91\xB1\x03\x65"
-			  "\xCB\x43\xD1\x06\xDF\xC3\x67\xBC"
-			  "\xDC\xE0\xCD\x35\xCE\x49\x65\xA0"
-			  "\x52\x7B\xA7\x0D\x07\xA9\x1B\xB0"
-			  "\x40\x77\x72\xC2\xEA\x0E\x3A\x78"
-			  "\x46\xB9\x91\xB6\xE7\x3D\x51\x42"
-			  "\xFD\x51\xB0\xC6\x2C\x63\x13\x78"
-			  "\x5C\xEE\xFC\xCF\xC4\x70\x00\x34",
-		.ilen	= 496,
-		.result	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
-			  "\x8B\x12\x86\x69\xF0\x5B\xCF\x56"
-			  "\x39\xAD\x34\x9F\x66\xEA\x7D\xC4"
-			  "\x48\xD3\xBA\x0D\xB1\x18\xE3\x4A"
-			  "\xFE\x41\x28\x5C\x27\x8E\x11\x85"
-			  "\x6C\xF7\x5E\xC2\x55\x3C\xA0\x0B"
-			  "\x92\x65\xE9\x70\xDB\x4F\xD6\xB9"
-			  "\x00\xB4\x1F\xE6\x49\xFD\x44\x2F"
-			  "\x53\x3A\x8D\x14\x98\x63\xCA\x5D"
-			  "\xC1\xA8\x33\xA7\x0E\x91\x78\xEC"
-			  "\x77\xDE\x42\xD5\xBC\x07\x8B\x12"
-			  "\xE5\x4C\xF0\x5B\x22\x56\x39\x80"
-			  "\x6B\x9F\x66\xC9\x50\xC4\xAF\x36"
-			  "\xBA\x0D\x94\x7F\xE3\x4A\xDD\x41"
-			  "\x28\xB3\x1A\x8E\x11\xF8\x43\xF7"
-			  "\x5E\x21\x55\x3C\x87\x6E\x92\x65"
-			  "\xCC\x57\xDB\xA2\x35\xB9\x00\xEB"
-			  "\x72\xE6\x49\xD0\x44\x2F\xB6\x19"
-			  "\x8D\x14\xFF\x46\xCA\x5D\x24\xA8"
-			  "\x33\x9A\x6D\x91\x78\xC3\x77\xDE"
-			  "\xA1\x08\xBC\x07\xEE\x71\xE5\x4C"
-			  "\xD7\x5B\x22\xB5\x1C\x80\x6B\xF2"
-			  "\x45\xC9\x50\x3B\xAF\x36\x99\x60"
-			  "\x94\x7F\xC6\x4A\xDD\xA4\x0F\xB3"
-			  "\x1A\xED\x74\xF8\x43\x2A\x5E\x21"
-			  "\x88\x13\x87\x6E\xF1\x58\xCC\x57"
-			  "\x3E\xA2\x35\x9C\x67\xEB\x72\xC5"
-			  "\x49\xD0\xBB\x02\xB6\x19\xE0\x4B"
-			  "\xFF\x46\x29\x5D\x24\x8F\x16\x9A"
-			  "\x6D\xF4\x5F\xC3\xAA\x3D\xA1\x08"
-			  "\x93\x7A\xEE\x71\xD8\x4C\xD7\xBE"
-			  "\x01\xB5\x1C\xE7\x4E\xF2\x45\x2C"
-			  "\x50\x3B\x82\x15\x99\x60\xCB\x52"
-			  "\xC6\xA9\x30\xA4\x0F\x96\x79\xED"
-			  "\x74\xDF\x43\x2A\xBD\x04\x88\x13"
-			  "\xFA\x4D\xF1\x58\x23\x57\x3E\x81"
-			  "\x68\x9C\x67\xCE\x51\xC5\xAC\x37"
-			  "\xBB\x02\x95\x7C\xE0\x4B\xD2\x46"
-			  "\x29\xB0\x1B\x8F\x16\xF9\x40\xF4"
-			  "\x5F\x26\xAA\x3D\x84\x6F\x93\x7A"
-			  "\xCD\x54\xD8\xA3\x0A\xBE\x01\xE8"
-			  "\x73\xE7\x4E\xD1\x45\x2C\xB7\x1E"
-			  "\x82\x15\xFC\x47\xCB\x52\x25\xA9"
-			  "\x30\x9B\x62\x96\x79\xC0\x74\xDF"
-			  "\xA6\x09\xBD\x04\xEF\x76\xFA\x4D"
-			  "\xD4\x58\x23\x8A\x1D\x81\x68\xF3"
-			  "\x5A\xCE\x51\x38\xAC\x37\x9E\x61"
-			  "\x95\x7C\xC7\x4B\xD2\xA5\x0C\xB0"
-			  "\x1B\xE2\x75\xF9\x40\x2B\x5F\x26"
-			  "\x89\x10\x84\x6F\xF6\x59\xCD\x54"
-			  "\x3F\xA3\x0A\x9D\x64\xE8\x73\xDA"
-			  "\x4E\xD1\xB8\x03\xB7\x1E\xE1\x48"
-			  "\xFC\x47\x2E\x52\x25\x8C\x17\x9B"
-			  "\x62\xF5\x5C\xC0\xAB\x32\xA6\x09"
-			  "\x90\x7B\xEF\x76\xD9\x4D\xD4\xBF"
-			  "\x06\x8A\x1D\xE4\x4F\xF3\x5A\x2D"
-			  "\x51\x38\x83\x6A\x9E\x61\xC8\x53"
-			  "\xC7\xAE\x31\xA5\x0C\x97\x7E\xE2"
-			  "\x75\xDC\x40\x2B\xB2\x05\x89\x10"
-			  "\xFB\x42\xF6\x59\x20\x54\x3F\x86"
-			  "\x69\x9D\x64\xCF\x56\xDA\xAD\x34"
-			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	}, { /* Generated with Crypto++ */
-		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
-			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
-			  "\xEB\xB4\x51\x72\xB4\x51\x72\x1F",
-		.klen	= 24,
-		.iv	= "\xB2\xD7\x48\xED\x06\x44\xF9\x12"
-			  "\xB7\x28\x4D\x83\x24\x59\xF2\x17",
-		.input	= "\x23\xFF\x5C\x99\x75\xBB\x1F\xD4"
+		.ctext	= "\x23\xFF\x5C\x99\x75\xBB\x1F\xD4"
 			  "\xBC\x27\x9D\x36\x60\xA9\xC9\xF7"
 			  "\x94\x9D\x1B\xFF\x8E\x95\x57\x89"
 			  "\x8C\x2E\x33\x70\x43\x61\xE6\xD2"
@@ -7528,71 +6599,7 @@ static const struct cipher_testvec des3_ede_ctr_dec_tv_template[] = {
 			  "\x5C\x60\x1F\x6E\xA7\xE2\xDC\xE7"
 			  "\x32\x0F\x05\x2F\xF2\x4C\x95\x3B"
 			  "\xF2\x79\xD9",
-		.ilen	= 499,
-		.result	= "\x05\xEC\x77\xFB\x42\xD5\x59\x20"
-			  "\x8B\x12\x86\x69\xF0\x5B\xCF\x56"
-			  "\x39\xAD\x34\x9F\x66\xEA\x7D\xC4"
-			  "\x48\xD3\xBA\x0D\xB1\x18\xE3\x4A"
-			  "\xFE\x41\x28\x5C\x27\x8E\x11\x85"
-			  "\x6C\xF7\x5E\xC2\x55\x3C\xA0\x0B"
-			  "\x92\x65\xE9\x70\xDB\x4F\xD6\xB9"
-			  "\x00\xB4\x1F\xE6\x49\xFD\x44\x2F"
-			  "\x53\x3A\x8D\x14\x98\x63\xCA\x5D"
-			  "\xC1\xA8\x33\xA7\x0E\x91\x78\xEC"
-			  "\x77\xDE\x42\xD5\xBC\x07\x8B\x12"
-			  "\xE5\x4C\xF0\x5B\x22\x56\x39\x80"
-			  "\x6B\x9F\x66\xC9\x50\xC4\xAF\x36"
-			  "\xBA\x0D\x94\x7F\xE3\x4A\xDD\x41"
-			  "\x28\xB3\x1A\x8E\x11\xF8\x43\xF7"
-			  "\x5E\x21\x55\x3C\x87\x6E\x92\x65"
-			  "\xCC\x57\xDB\xA2\x35\xB9\x00\xEB"
-			  "\x72\xE6\x49\xD0\x44\x2F\xB6\x19"
-			  "\x8D\x14\xFF\x46\xCA\x5D\x24\xA8"
-			  "\x33\x9A\x6D\x91\x78\xC3\x77\xDE"
-			  "\xA1\x08\xBC\x07\xEE\x71\xE5\x4C"
-			  "\xD7\x5B\x22\xB5\x1C\x80\x6B\xF2"
-			  "\x45\xC9\x50\x3B\xAF\x36\x99\x60"
-			  "\x94\x7F\xC6\x4A\xDD\xA4\x0F\xB3"
-			  "\x1A\xED\x74\xF8\x43\x2A\x5E\x21"
-			  "\x88\x13\x87\x6E\xF1\x58\xCC\x57"
-			  "\x3E\xA2\x35\x9C\x67\xEB\x72\xC5"
-			  "\x49\xD0\xBB\x02\xB6\x19\xE0\x4B"
-			  "\xFF\x46\x29\x5D\x24\x8F\x16\x9A"
-			  "\x6D\xF4\x5F\xC3\xAA\x3D\xA1\x08"
-			  "\x93\x7A\xEE\x71\xD8\x4C\xD7\xBE"
-			  "\x01\xB5\x1C\xE7\x4E\xF2\x45\x2C"
-			  "\x50\x3B\x82\x15\x99\x60\xCB\x52"
-			  "\xC6\xA9\x30\xA4\x0F\x96\x79\xED"
-			  "\x74\xDF\x43\x2A\xBD\x04\x88\x13"
-			  "\xFA\x4D\xF1\x58\x23\x57\x3E\x81"
-			  "\x68\x9C\x67\xCE\x51\xC5\xAC\x37"
-			  "\xBB\x02\x95\x7C\xE0\x4B\xD2\x46"
-			  "\x29\xB0\x1B\x8F\x16\xF9\x40\xF4"
-			  "\x5F\x26\xAA\x3D\x84\x6F\x93\x7A"
-			  "\xCD\x54\xD8\xA3\x0A\xBE\x01\xE8"
-			  "\x73\xE7\x4E\xD1\x45\x2C\xB7\x1E"
-			  "\x82\x15\xFC\x47\xCB\x52\x25\xA9"
-			  "\x30\x9B\x62\x96\x79\xC0\x74\xDF"
-			  "\xA6\x09\xBD\x04\xEF\x76\xFA\x4D"
-			  "\xD4\x58\x23\x8A\x1D\x81\x68\xF3"
-			  "\x5A\xCE\x51\x38\xAC\x37\x9E\x61"
-			  "\x95\x7C\xC7\x4B\xD2\xA5\x0C\xB0"
-			  "\x1B\xE2\x75\xF9\x40\x2B\x5F\x26"
-			  "\x89\x10\x84\x6F\xF6\x59\xCD\x54"
-			  "\x3F\xA3\x0A\x9D\x64\xE8\x73\xDA"
-			  "\x4E\xD1\xB8\x03\xB7\x1E\xE1\x48"
-			  "\xFC\x47\x2E\x52\x25\x8C\x17\x9B"
-			  "\x62\xF5\x5C\xC0\xAB\x32\xA6\x09"
-			  "\x90\x7B\xEF\x76\xD9\x4D\xD4\xBF"
-			  "\x06\x8A\x1D\xE4\x4F\xF3\x5A\x2D"
-			  "\x51\x38\x83\x6A\x9E\x61\xC8\x53"
-			  "\xC7\xAE\x31\xA5\x0C\x97\x7E\xE2"
-			  "\x75\xDC\x40\x2B\xB2\x05\x89\x10"
-			  "\xFB\x42\xF6\x59\x20\x54\x3F\x86"
-			  "\x69\x9D\x64\xCF\x56\xDA\xAD\x34"
-			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47"
-			  "\x2E\xB1\x18",
-		.rlen	= 499,
+		.len	= 499,
 		.also_non_np = 1,
 		.np	= 2,
 		.tap	= { 499 - 16, 16 },
@@ -7602,45 +6609,40 @@ static const struct cipher_testvec des3_ede_ctr_dec_tv_template[] = {
 /*
  * Blowfish test vectors.
  */
-static const struct cipher_testvec bf_enc_tv_template[] = {
+static const struct cipher_testvec bf_tv_template[] = {
 	{ /* DES test vectors from OpenSSL */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 8,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 8,
-		.result	= "\x4e\xf9\x97\x45\x61\x98\xdd\x78",
-		.rlen	= 8,
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ctext	= "\x4e\xf9\x97\x45\x61\x98\xdd\x78",
+		.len	= 8,
 	}, {
 		.key	= "\x1f\x1f\x1f\x1f\x0e\x0e\x0e\x0e",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.ilen	= 8,
-		.result	= "\xa7\x90\x79\x51\x08\xea\x3c\xae",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.ctext	= "\xa7\x90\x79\x51\x08\xea\x3c\xae",
+		.len	= 8,
 	}, {
 		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
 		.klen	= 8,
-		.input	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ilen	= 8,
-		.result	= "\xe8\x7a\x24\x4e\x2c\xc8\x5e\x82",
-		.rlen	= 8,
+		.ptext	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.ctext	= "\xe8\x7a\x24\x4e\x2c\xc8\x5e\x82",
+		.len	= 8,
 	}, { /* Vary the keylength... */
 		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87"
 			  "\x78\x69\x5a\x4b\x3c\x2d\x1e\x0f",
 		.klen	= 16,
-		.input	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ilen	= 8,
-		.result	= "\x93\x14\x28\x87\xee\x3b\xe1\x5c",
-		.rlen	= 8,
+		.ptext	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.ctext	= "\x93\x14\x28\x87\xee\x3b\xe1\x5c",
+		.len	= 8,
 	}, {
 		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87"
 			  "\x78\x69\x5a\x4b\x3c\x2d\x1e\x0f"
 			  "\x00\x11\x22\x33\x44",
 		.klen	= 21,
-		.input	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ilen	= 8,
-		.result	= "\xe6\xf5\x1e\xd7\x9b\x9d\xb2\x1f",
-		.rlen	= 8,
+		.ptext	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.ctext	= "\xe6\xf5\x1e\xd7\x9b\x9d\xb2\x1f",
+		.len	= 8,
 	}, { /* Generated with bf488 */
 		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87"
 			  "\x78\x69\x5a\x4b\x3c\x2d\x1e\x0f"
@@ -7650,17 +6652,16 @@ static const struct cipher_testvec bf_enc_tv_template[] = {
 			  "\x1f\x1f\x1f\x1f\x0e\x0e\x0e\x0e"
 			  "\xff\xff\xff\xff\xff\xff\xff\xff",
 		.klen	= 56,
-		.input	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ilen	= 8,
-		.result	= "\xc0\x45\x04\x01\x2e\x4e\x1f\x53",
-		.rlen	= 8,
+		.ptext	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
+		.ctext	= "\xc0\x45\x04\x01\x2e\x4e\x1f\x53",
+		.len	= 8,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
 			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
 			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
 		.klen	= 32,
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -7723,136 +6724,7 @@ static const struct cipher_testvec bf_enc_tv_template[] = {
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
 			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
-		.ilen	= 504,
-		.result	= "\x96\x87\x3D\x0C\x7B\xFB\xBD\x1F"
-			  "\xE3\xC1\x99\x6D\x39\xD4\xC2\x7D"
-			  "\xD7\x87\xA1\xF2\xDF\x51\x71\x26"
-			  "\xC2\xF4\x6D\xFF\xF6\xCD\x6B\x40"
-			  "\xE1\xB3\xBF\xD4\x38\x2B\xC8\x3B"
-			  "\xD3\xB2\xD4\x61\xC7\x9F\x06\xE9"
-			  "\xCD\xF3\x88\x39\x39\x7A\xDF\x19"
-			  "\xE8\x03\x2A\x0B\x9E\xA0\x2B\x86"
-			  "\x31\xF8\x9D\xB1\xEE\x78\x9D\xB5"
-			  "\xCD\x8B\x7C\x2E\xF5\xA2\x2D\x5D"
-			  "\x6E\x66\xAF\x38\x6C\xD3\x13\xED"
-			  "\x14\xEA\x5D\xD0\x17\x77\x0F\x4A"
-			  "\x50\xF2\xD0\x0F\xC8\xF7\x1E\x7B"
-			  "\x9D\x5B\x54\x65\x4F\x16\x8A\x97"
-			  "\xF3\xF6\xD4\xAA\x87\x36\x77\x72"
-			  "\x99\x4A\xB5\x5E\x88\xC3\xCD\x7D"
-			  "\x1D\x97\xF9\x11\xBD\xE0\x1F\x1F"
-			  "\x96\x3E\x4B\x22\xF4\xC0\xE6\xB8"
-			  "\x47\x82\x98\x23\x33\x36\xBC\x1B"
-			  "\x36\xE7\xF6\xCF\x97\x37\x16\xC0"
-			  "\x87\x31\x8B\xB0\xDB\x19\x42\xA5"
-			  "\x1F\x90\x7E\x66\x34\xDD\x5E\xE9"
-			  "\x4F\xB2\x2B\x9A\xDE\xB3\x5D\x71"
-			  "\x4D\x68\xF0\xDC\xA6\xEA\xE3\x9B"
-			  "\x60\x00\x55\x57\x06\x8B\xD5\xB3"
-			  "\x86\x30\x78\xDA\x33\x9A\x9D\xCC"
-			  "\xBA\x0B\x81\x06\x77\x43\xC7\xC9"
-			  "\xDB\x37\x60\x11\x45\x59\x6D\x2D"
-			  "\x90\x3D\x65\x3E\xD0\x13\xC6\x3C"
-			  "\x0E\x78\x7D\x9A\x00\xD6\x2F\x0B"
-			  "\x3B\x53\x19\x1E\xA8\x9B\x11\xD9"
-			  "\x98\xE4\x7F\xC3\x6E\x51\x24\x70"
-			  "\x9F\x04\x9C\xC2\x9E\x44\x84\xE3"
-			  "\xE0\x8A\x44\xA2\x5C\x94\x74\x34"
-			  "\x37\x52\x7C\x03\xE8\x8E\x97\xE1"
-			  "\x5B\x5C\x0E\xB0\x70\xFE\x54\x3F"
-			  "\xD8\x65\xA9\xC5\xCD\xEC\xF4\x45"
-			  "\x55\xC5\xA7\xA3\x19\x80\x28\x51"
-			  "\xBE\x64\x4A\xC1\xD4\xE1\xBE\xEB"
-			  "\x73\x4C\xB6\xF9\x5F\x6D\x82\xBC"
-			  "\x3E\x42\x14\x49\x88\x51\xBF\x68"
-			  "\x45\x75\x27\x1B\x0A\x72\xED\xAF"
-			  "\xDA\xC4\x4D\x67\x0D\xEE\x75\xE3"
-			  "\x34\xDD\x91\x19\x42\x3A\xCB\xDA"
-			  "\x38\xFA\x3C\x93\x62\xF2\xE3\x81"
-			  "\xB3\xE4\xBB\xF6\x0D\x0B\x1D\x09"
-			  "\x9C\x52\x0D\x50\x63\xA4\xB2\xD2"
-			  "\x82\xA0\x23\x3F\x1F\xB6\xED\x6E"
-			  "\xC2\x9C\x1C\xD0\x9A\x40\xB6\xFC"
-			  "\x36\x56\x6E\x85\x73\xD7\x52\xBA"
-			  "\x35\x5E\x32\x89\x5D\x42\xF5\x36"
-			  "\x52\x8D\x46\x7D\xC8\x71\xAD\x33"
-			  "\xE1\xAF\x6A\xA8\xEC\xBA\x1C\xDC"
-			  "\xFE\x88\xE6\x16\xE4\xC8\x13\x00"
-			  "\x3C\xDA\x59\x32\x38\x19\xD5\xEB"
-			  "\xB6\x7F\x78\x45\x1B\x8E\x07\x8C"
-			  "\x66\x52\x75\xFF\xAF\xCE\x2D\x2B"
-			  "\x22\x29\xCA\xB3\x5F\x7F\xE3\x29"
-			  "\xB2\xB8\x9D\xEB\x16\xC8\xC5\x1D"
-			  "\xC9\x0D\x59\x82\x27\x57\x9D\x42"
-			  "\x54\x59\x09\xA5\x3D\xC5\x84\x68"
-			  "\x56\xEB\x36\x77\x3D\xAA\xB8\xF5"
-			  "\xC9\x1A\xFB\x5D\xDE\xBB\x43\xF4",
-		.rlen	= 504,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 504 - 10, 2, 8 },
-	},
-};
-
-static const struct cipher_testvec bf_dec_tv_template[] = {
-	{ /* DES test vectors from OpenSSL */
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 8,
-		.input	= "\x4e\xf9\x97\x45\x61\x98\xdd\x78",
-		.ilen	= 8,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 8,
-	}, {
-		.key	= "\x1f\x1f\x1f\x1f\x0e\x0e\x0e\x0e",
-		.klen	= 8,
-		.input	= "\xa7\x90\x79\x51\x08\xea\x3c\xae",
-		.ilen	= 8,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.rlen	= 8,
-	}, {
-		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
-		.klen	= 8,
-		.input	= "\xe8\x7a\x24\x4e\x2c\xc8\x5e\x82",
-		.ilen	= 8,
-		.result	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.rlen	= 8,
-	}, { /* Vary the keylength... */
-		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87"
-			  "\x78\x69\x5a\x4b\x3c\x2d\x1e\x0f",
-		.klen	= 16,
-		.input	= "\x93\x14\x28\x87\xee\x3b\xe1\x5c",
-		.ilen	= 8,
-		.result	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.rlen	= 8,
-	}, {
-		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87"
-			  "\x78\x69\x5a\x4b\x3c\x2d\x1e\x0f"
-			  "\x00\x11\x22\x33\x44",
-		.klen	= 21,
-		.input	= "\xe6\xf5\x1e\xd7\x9b\x9d\xb2\x1f",
-		.ilen	= 8,
-		.result	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.rlen	= 8,
-	}, { /* Generated with bf488, using OpenSSL, Libgcrypt and Nettle */
-		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87"
-			  "\x78\x69\x5a\x4b\x3c\x2d\x1e\x0f"
-			  "\x00\x11\x22\x33\x44\x55\x66\x77"
-			  "\x04\x68\x91\x04\xc2\xfd\x3b\x2f"
-			  "\x58\x40\x23\x64\x1a\xba\x61\x76"
-			  "\x1f\x1f\x1f\x1f\x0e\x0e\x0e\x0e"
-			  "\xff\xff\xff\xff\xff\xff\xff\xff",
-		.klen	= 56,
-		.input	= "\xc0\x45\x04\x01\x2e\x4e\x1f\x53",
-		.ilen	= 8,
-		.result	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.rlen	= 8,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.input	= "\x96\x87\x3D\x0C\x7B\xFB\xBD\x1F"
+		.ctext	= "\x96\x87\x3D\x0C\x7B\xFB\xBD\x1F"
 			  "\xE3\xC1\x99\x6D\x39\xD4\xC2\x7D"
 			  "\xD7\x87\xA1\xF2\xDF\x51\x71\x26"
 			  "\xC2\xF4\x6D\xFF\xF6\xCD\x6B\x40"
@@ -7915,93 +6787,28 @@ static const struct cipher_testvec bf_dec_tv_template[] = {
 			  "\x54\x59\x09\xA5\x3D\xC5\x84\x68"
 			  "\x56\xEB\x36\x77\x3D\xAA\xB8\xF5"
 			  "\xC9\x1A\xFB\x5D\xDE\xBB\x43\xF4",
-		.ilen	= 504,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
-		.rlen	= 504,
+		.len	= 504,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 504 - 10, 2, 8 },
 	},
 };
 
-static const struct cipher_testvec bf_cbc_enc_tv_template[] = {
+static const struct cipher_testvec bf_cbc_tv_template[] = {
 	{ /* From OpenSSL */
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
 		.klen	= 16,
 		.iv	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.input	= "\x37\x36\x35\x34\x33\x32\x31\x20"
+		.ptext	= "\x37\x36\x35\x34\x33\x32\x31\x20"
 			  "\x4e\x6f\x77\x20\x69\x73\x20\x74"
 			  "\x68\x65\x20\x74\x69\x6d\x65\x20"
 			  "\x66\x6f\x72\x20\x00\x00\x00\x00",
-		.ilen	= 32,
-		.result	= "\x6b\x77\xb4\xd6\x30\x06\xde\xe6"
+		.ctext	= "\x6b\x77\xb4\xd6\x30\x06\xde\xe6"
 			  "\x05\xb1\x56\xe2\x74\x03\x97\x93"
 			  "\x58\xde\xb9\xe7\x15\x46\x16\xd9"
 			  "\x59\xf1\x65\x2b\xd5\xff\x92\xcc",
-		.rlen	= 32,
+		.len	= 32,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -8009,7 +6816,7 @@ static const struct cipher_testvec bf_cbc_enc_tv_template[] = {
 			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -8072,8 +6879,7 @@ static const struct cipher_testvec bf_cbc_enc_tv_template[] = {
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
 			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
-		.ilen	= 504,
-		.result	= "\xB4\xFE\xA5\xBB\x3D\x2C\x27\x06"
+		.ctext	= "\xB4\xFE\xA5\xBB\x3D\x2C\x27\x06"
 			  "\x06\x2B\x3A\x92\xB2\xF5\x5E\x62"
 			  "\x84\xCD\xF7\x66\x7E\x41\x6C\x8E"
 			  "\x1B\xD9\x02\xB6\x48\xB0\x87\x25"
@@ -8136,171 +6942,14 @@ static const struct cipher_testvec bf_cbc_enc_tv_template[] = {
 			  "\xCD\xE9\xD5\x0C\xFE\x12\x39\xA9"
 			  "\x93\x9B\xEE\xB5\x97\x41\xD2\xA0"
 			  "\xB4\x98\xD8\x6B\x74\xE7\x65\xF4",
-		.rlen	= 504,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 504 - 10, 2, 8 },
-	},
-};
-
-static const struct cipher_testvec bf_cbc_dec_tv_template[] = {
-	{ /* From OpenSSL */
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
-		.klen	= 16,
-		.iv	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.input	= "\x6b\x77\xb4\xd6\x30\x06\xde\xe6"
-			  "\x05\xb1\x56\xe2\x74\x03\x97\x93"
-			  "\x58\xde\xb9\xe7\x15\x46\x16\xd9"
-			  "\x59\xf1\x65\x2b\xd5\xff\x92\xcc",
-		.ilen	= 32,
-		.result	= "\x37\x36\x35\x34\x33\x32\x31\x20"
-			  "\x4e\x6f\x77\x20\x69\x73\x20\x74"
-			  "\x68\x65\x20\x74\x69\x6d\x65\x20"
-			  "\x66\x6f\x72\x20\x00\x00\x00\x00",
-		.rlen	= 32,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\xB4\xFE\xA5\xBB\x3D\x2C\x27\x06"
-			  "\x06\x2B\x3A\x92\xB2\xF5\x5E\x62"
-			  "\x84\xCD\xF7\x66\x7E\x41\x6C\x8E"
-			  "\x1B\xD9\x02\xB6\x48\xB0\x87\x25"
-			  "\x01\x9C\x93\x63\x51\x60\x82\xD2"
-			  "\x4D\xE5\xC2\xB7\xAE\x60\xD8\xAD"
-			  "\x9F\xAB\x6C\xFA\x20\x05\xDA\x6F"
-			  "\x1F\xD1\xD8\x36\x0F\xB5\x16\x69"
-			  "\x3C\xAF\xB3\x30\x18\x33\xE6\xB5"
-			  "\x43\x29\x9D\x94\xF4\x2F\x0A\x65"
-			  "\x40\xB2\xB2\xB2\x42\x89\xEE\x8A"
-			  "\x60\xD3\x52\xA8\xED\x91\xDF\xE1"
-			  "\x91\x73\x7C\x28\xA1\x14\xC3\x4C"
-			  "\x82\x72\x4B\x7D\x7D\x32\xD5\x19"
-			  "\xE8\xB8\x6B\x30\x21\x09\x0E\x27"
-			  "\x10\x9D\x2D\x3A\x6A\x4B\x7B\xE6"
-			  "\x8D\x4E\x02\x32\xFF\x7F\x8E\x13"
-			  "\xB0\x96\xF4\xC2\xA1\x60\x8A\x69"
-			  "\xEF\x0F\x86\xD0\x25\x13\x1A\x7C"
-			  "\x6E\xF0\x41\xA3\xFB\xB3\xAB\x40"
-			  "\x7D\x19\xA0\x11\x4F\x3E\x1D\x43"
-			  "\x65\xFE\x15\x40\xD0\x62\x41\x02"
-			  "\xEA\x0C\x7A\xC3\x84\xEE\xB0\xBE"
-			  "\xBE\xC8\x57\x51\xCD\x4F\xAD\x5C"
-			  "\xCC\x79\xBA\x0D\x85\x3A\xED\x6B"
-			  "\xAC\x6B\xA3\x4D\xBC\xE8\x02\x6A"
-			  "\xC2\x6D\xBD\x5E\x89\x95\x86\x43"
-			  "\x2C\x17\x4B\xC6\x40\xA2\xBD\x24"
-			  "\x04\xF0\x86\x08\x78\x18\x42\xE0"
-			  "\x39\x1B\x22\x9E\x89\x4C\x04\x6B"
-			  "\x65\xC5\xB6\x0E\xF6\x63\xFC\xD7"
-			  "\xAE\x9E\x87\x13\xCC\xD3\x1A\xEC"
-			  "\xF0\x51\xCC\x93\x68\xFC\xE9\x19"
-			  "\x7C\x4E\x9B\xCC\x17\xAD\xD2\xFC"
-			  "\x97\x18\x92\xFF\x15\x11\xCE\xED"
-			  "\x04\x41\x05\xA3\x92\xFF\x3B\xE6"
-			  "\xB6\x8C\x90\xC6\xCD\x15\xA0\x04"
-			  "\x25\x8B\x5D\x5B\x5F\xDB\xAE\x68"
-			  "\xEF\xB3\x61\x18\xDB\x83\x9B\x39"
-			  "\xCA\x82\xD1\x88\xF0\xA2\x5C\x02"
-			  "\x87\xBD\x8D\x8F\xBB\x62\xF0\x35"
-			  "\x75\x6F\x06\x81\x0A\x97\x4D\xF0"
-			  "\x43\x12\x73\x77\xDB\x91\x83\x5B"
-			  "\xE7\x3A\xA6\x07\x7B\xBF\x2C\x50"
-			  "\x94\xDE\x7B\x65\xDA\x1C\xF1\x9F"
-			  "\x7E\x12\x40\xB2\x3E\x19\x23\xF1"
-			  "\x7C\x1B\x5F\xA8\xF3\xAC\x63\x87"
-			  "\xEB\x3E\x0C\xBE\xA3\x63\x97\x88"
-			  "\x8D\x27\xC6\x2A\xF8\xF2\x67\x9A"
-			  "\x0D\x14\x16\x2B\x6F\xCB\xD4\x76"
-			  "\x14\x48\x2E\xDE\x2A\x44\x5E\x45"
-			  "\xF1\x97\x82\xEF\xB7\xAE\xED\x3A"
-			  "\xED\x73\xD3\x79\xF7\x38\x1D\xD0"
-			  "\xC5\xF8\x69\x83\x28\x84\x87\x56"
-			  "\x3F\xAE\x81\x04\x79\x1F\xD1\x09"
-			  "\xC5\xE5\x05\x0D\x64\x16\xCE\x42"
-			  "\xC5\xF8\xDB\x57\x89\x33\x22\xFC"
-			  "\xB4\xD7\x94\xB9\xF3\xCC\x02\x90"
-			  "\x02\xBA\x55\x1E\x24\x3E\x02\x1D"
-			  "\xC6\xCD\x8F\xD9\xBD\xED\xB0\x51"
-			  "\xCD\xE9\xD5\x0C\xFE\x12\x39\xA9"
-			  "\x93\x9B\xEE\xB5\x97\x41\xD2\xA0"
-			  "\xB4\x98\xD8\x6B\x74\xE7\x65\xF4",
-		.ilen	= 504,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
-		.rlen	= 504,
+		.len	= 504,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 504 - 10, 2, 8 },
 	},
 };
 
-static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
+static const struct cipher_testvec bf_ctr_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -8308,7 +6957,7 @@ static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
 			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -8371,8 +7020,7 @@ static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
 			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
-		.ilen	= 504,
-		.result	= "\xC7\xA3\xDF\xB9\x05\xF4\x9E\x8D"
+		.ctext	= "\xC7\xA3\xDF\xB9\x05\xF4\x9E\x8D"
 			  "\x9E\xDF\x38\x18\x83\x07\xEF\xC1"
 			  "\x93\x3C\xAA\xAA\xFE\x06\x42\xCC"
 			  "\x0D\x70\x86\x5A\x44\xAD\x85\x17"
@@ -8435,7 +7083,7 @@ static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
 			  "\x64\xBB\x15\xB8\x56\xCF\xEE\xE5"
 			  "\x32\x44\x96\x1C\xD8\xEB\x95\xD2"
 			  "\xF3\x71\xEF\xEB\x4E\xBB\x4D\x29",
-		.rlen	= 504,
+		.len	= 504,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -8443,7 +7091,7 @@ static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
 			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -8506,8 +7154,7 @@ static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
 			  "\x2B\xC2\x59\xF0\x64\xFB\x92",
-		.ilen	= 503,
-		.result	= "\xC7\xA3\xDF\xB9\x05\xF4\x9E\x8D"
+		.ctext	= "\xC7\xA3\xDF\xB9\x05\xF4\x9E\x8D"
 			  "\x9E\xDF\x38\x18\x83\x07\xEF\xC1"
 			  "\x93\x3C\xAA\xAA\xFE\x06\x42\xCC"
 			  "\x0D\x70\x86\x5A\x44\xAD\x85\x17"
@@ -8570,7 +7217,7 @@ static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
 			  "\x64\xBB\x15\xB8\x56\xCF\xEE\xE5"
 			  "\x32\x44\x96\x1C\xD8\xEB\x95\xD2"
 			  "\xF3\x71\xEF\xEB\x4E\xBB\x4D",
-		.rlen	= 503,
+		.len	= 503,
 		.also_non_np = 1,
 		.np	= 2,
 		.tap	= { 503 - 8, 8 },
@@ -8581,210 +7228,7 @@ static const struct cipher_testvec bf_ctr_enc_tv_template[] = {
 			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
 		.klen	= 32,
 		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
-		.ilen	= 504,
-		.result	= "\x5F\x58\x6E\x60\x51\x6E\xDC\x3D"
-			  "\xD1\xBB\xF7\xB7\xFD\x04\x44\x82"
-			  "\xDC\x9F\x4B\x02\xF1\xD2\x5A\x6F"
-			  "\x25\xF9\x27\x21\xF2\xD2\x9A\x01"
-			  "\xBD\xAD\x3D\x93\x87\xCA\x0D\xFE"
-			  "\xB7\x2C\x17\x1F\x42\x8C\x13\xB2"
-			  "\x62\x44\x72\xB9\x5D\xC0\xF8\x37"
-			  "\xDF\xEA\x78\x81\x8F\xA6\x34\xB2"
-			  "\x07\x09\x7C\xB9\x3A\xA0\x2B\x18"
-			  "\x34\x6A\x9D\x3D\xA5\xEB\xF4\x60"
-			  "\xF8\x98\xA2\x39\x81\x23\x6C\xA9"
-			  "\x70\xCA\xCC\x45\xD8\x1F\xDF\x44"
-			  "\x2A\x67\x7A\x88\x28\xDC\x36\x83"
-			  "\x18\xD7\x48\x43\x17\x2B\x1B\xE6"
-			  "\x0B\x82\x59\x14\x26\x67\x08\x09"
-			  "\x5B\x5D\x38\xD0\x81\xCE\x54\x2A"
-			  "\xCD\x22\x94\x42\xF5\xBA\x74\x7E"
-			  "\xD9\x00\x40\xA9\x0D\x0B\xBD\x8E"
-			  "\xC4\x8E\x5E\x17\x8F\x48\xE2\xB8"
-			  "\xF4\xCC\x19\x76\xAB\x48\x29\xAA"
-			  "\x81\xD5\xCE\xD5\x8A\x3B\xC9\x21"
-			  "\xEF\x50\x4F\x04\x02\xBF\xE1\x1F"
-			  "\x59\x28\x1A\xE4\x18\x16\xA0\x29"
-			  "\xBF\x34\xA9\x2D\x28\x83\xC0\x5E"
-			  "\xEA\x44\xC4\x6E\xAB\x24\x79\x9D"
-			  "\x2D\xA1\xE8\x55\xCA\x74\xFC\xBD"
-			  "\xFE\xDD\xDA\xA5\xFB\x34\x90\x31"
-			  "\x0E\x62\x28\x9B\xDC\xD7\xA1\xBB"
-			  "\xF0\x1A\xB3\xE2\xD0\xFA\xBD\xE8"
-			  "\x5C\x5A\x10\x67\xF6\x6A\x17\x3F"
-			  "\xC5\xE9\x09\x08\xDD\x22\x77\x42"
-			  "\x26\x6A\x6A\x7A\x3F\x87\x80\x0C"
-			  "\xF0\xFF\x15\x8E\x84\x86\xC0\x10"
-			  "\x0F\x8D\x33\x06\xB8\x72\xA4\x47"
-			  "\x6B\xED\x2E\x05\x94\x6C\x5C\x5B"
-			  "\x13\xF6\x77\xEE\x3B\x16\xDF\xC2"
-			  "\x63\x66\x07\x6D\x3F\x6C\x51\x7C"
-			  "\x1C\xAC\x80\xB6\x58\x48\xB7\x9D"
-			  "\xB4\x19\xD8\x19\x45\x66\x27\x02"
-			  "\xA1\xA9\x99\xF3\x1F\xE5\xA7\x1D"
-			  "\x31\xE7\x1B\x0D\xFF\xBB\xB5\xA1"
-			  "\xF5\x9C\x45\x1E\x18\x19\xA1\xE7"
-			  "\xC2\xF1\xBF\x68\xC3\xEC\xCF\x53"
-			  "\x67\xA6\x2B\x7D\x3C\x6D\x24\xC3"
-			  "\xE8\xE6\x07\x5A\x09\xE0\x32\xA8"
-			  "\x52\xF6\xE9\xED\x0E\xC6\x0A\x6A"
-			  "\xFC\x60\x2A\xE0\x93\xCE\xB8\x2E"
-			  "\xA2\xA8\x0E\x79\x9E\x34\x5D\x37"
-			  "\x6F\x12\xFE\x48\x7B\xE7\xB9\x22"
-			  "\x29\xE8\xD7\xBE\x5D\xD1\x8B\xD9"
-			  "\x91\x51\x4E\x71\xF2\x98\x85\x16"
-			  "\x25\x7A\x76\x8A\x51\x0E\x65\x14"
-			  "\x81\xB5\x3A\x37\xFD\xEC\xB5\x8A"
-			  "\xE1\xCF\x41\x72\x14\x29\x4C\xF0"
-			  "\x20\xD9\x9A\xC5\x66\xA4\x03\x76"
-			  "\x5B\xA4\x15\x4F\x0E\x64\x39\x40"
-			  "\x25\xF9\x20\x22\xF5\x88\xF5\xBA"
-			  "\xE4\xDF\x45\x61\xBF\x8D\x7A\x24"
-			  "\x4B\x92\x71\xD9\x2F\x77\xA7\x95"
-			  "\xA8\x7F\x61\xD5\xA4\x57\xB0\xFB"
-			  "\xB5\x77\xBA\x1C\xEE\x71\xFA\xB0"
-			  "\x16\x4C\x18\x6B\xF2\x69\xA0\x07"
-			  "\xEF\xBE\xEC\x69\xAC\xA8\x63\x9E",
-		.rlen	= 504,
-	},
-};
-
-static const struct cipher_testvec bf_ctr_dec_tv_template[] = {
-	{ /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\xC7\xA3\xDF\xB9\x05\xF4\x9E\x8D"
-			  "\x9E\xDF\x38\x18\x83\x07\xEF\xC1"
-			  "\x93\x3C\xAA\xAA\xFE\x06\x42\xCC"
-			  "\x0D\x70\x86\x5A\x44\xAD\x85\x17"
-			  "\xE4\x1F\x5E\xA5\x89\xAC\x32\xBC"
-			  "\x3D\xA7\xE9\x0A\x5C\x70\x4D\xDE"
-			  "\x99\x38\x07\xCA\x1D\x21\xC1\x11"
-			  "\x97\xEB\x98\x75\xC4\x73\x45\x83"
-			  "\x46\x1C\x9C\x91\x87\xC1\xA0\x56"
-			  "\x98\xA1\x8B\xDB\x22\x76\xBD\x62"
-			  "\xA4\xBC\xE8\x86\xDA\xD2\x51\x13"
-			  "\x13\xD2\x96\x68\x69\x10\x67\x0C"
-			  "\xD0\x17\x25\x7C\xB2\xAE\x4F\x93"
-			  "\xA6\x82\x20\xCF\x0F\xA6\x47\x79"
-			  "\x88\x09\x40\x59\xBD\x12\x64\xB5"
-			  "\x19\x38\x0D\xFF\x86\xD9\x42\x20"
-			  "\x81\x0D\x96\x99\xAF\x22\x1F\x94"
-			  "\x5C\x6E\xEC\xEA\xA3\x39\xCB\x09"
-			  "\x43\x19\x7F\xD0\xBB\x10\xC2\x49"
-			  "\xF7\xE9\xF2\xEE\xBF\xF7\xF8\xB3"
-			  "\x0E\x1A\xF1\x8D\x70\x82\x0C\x04"
-			  "\xFD\x29\x1A\xAC\xC0\x92\x48\x34"
-			  "\x6A\xE3\x1D\x4F\xFC\x1C\x72\x6A"
-			  "\x57\xCB\xAD\xD0\x98\xAB\xB1\x01"
-			  "\x03\x6A\x45\xDD\x07\x71\x5F\x5B"
-			  "\xB5\x4A\xE4\xE5\xB9\xB9\xBC\xAC"
-			  "\x44\xF7\x41\xA4\x5F\x2E\xE9\x28"
-			  "\xE3\x05\xD2\x94\x78\x4C\x33\x1B"
-			  "\xBD\xC1\x6E\x51\xD9\xAD\xD9\x86"
-			  "\x15\x4A\x78\xAE\x7B\xAD\x3B\xBC"
-			  "\x2F\xE0\x0E\xC5\x7B\x54\x97\x5F"
-			  "\x60\x51\x14\x65\xF9\x91\xE9\xDA"
-			  "\x9A\xBC\xFC\x19\x29\x67\xAA\x63"
-			  "\x5E\xF2\x48\x88\xEB\x79\xE1\xE4"
-			  "\xF7\xF6\x4C\xA9\xE2\x8C\x3B\xE0"
-			  "\xED\x52\xAE\x90\x8F\x5B\x98\x34"
-			  "\x29\x94\x34\x7F\xF9\x6C\x1E\xB6"
-			  "\xA4\xE7\x2D\x06\x54\x9D\xC3\x02"
-			  "\xC1\x90\xA4\x72\x31\x6B\x24\x51"
-			  "\x0B\xB3\x7C\x63\x15\xBA\xAF\x5D"
-			  "\x41\xE0\x37\x6D\xBE\x41\x58\xDE"
-			  "\xF2\x07\x62\x99\xBE\xC1\x8C\x0F"
-			  "\x0F\x28\xFB\x8F\x0E\x1D\x91\xE2"
-			  "\xDA\x99\x5C\x49\xBA\x9C\xA8\x86"
-			  "\x82\x63\x11\xB3\x54\x49\x00\x08"
-			  "\x07\xF2\xE8\x1F\x34\x49\x61\xF4"
-			  "\x81\xE9\xF6\xA9\x5A\x28\x60\x1F"
-			  "\x66\x99\x08\x06\xF2\xE8\x2D\xD1"
-			  "\xD0\x67\xBA\x32\x1F\x02\x86\x7B"
-			  "\xFB\x79\x3D\xC5\xB1\x7F\x15\xAF"
-			  "\xD7\xBF\x31\x46\x22\x7F\xAE\x5B"
-			  "\x8B\x95\x47\xC2\xB1\x62\xA1\xCE"
-			  "\x52\xAC\x9C\x8B\xC2\x49\x7F\xBC"
-			  "\x9C\x89\xB8\xB6\xCA\xE3\x8F\xEA"
-			  "\xAC\xB4\x5D\xE4\x50\xDC\x3A\xB5"
-			  "\x91\x04\x94\x99\x03\x3B\x42\x6D"
-			  "\x9C\x4A\x02\xF5\xB5\x38\x98\xA8"
-			  "\x5C\x97\x2E\x4D\x79\x67\x71\xAF"
-			  "\xF0\x70\x77\xFF\x2D\xDA\xA0\x9E"
-			  "\x23\x8D\xD6\xA6\x68\x10\x78\x9A"
-			  "\x64\xBB\x15\xB8\x56\xCF\xEE\xE5"
-			  "\x32\x44\x96\x1C\xD8\xEB\x95\xD2"
-			  "\xF3\x71\xEF\xEB\x4E\xBB\x4D\x29",
-		.ilen	= 504,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -8847,153 +7291,7 @@ static const struct cipher_testvec bf_ctr_dec_tv_template[] = {
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
 			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
-		.rlen	= 504,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\xC7\xA3\xDF\xB9\x05\xF4\x9E\x8D"
-			  "\x9E\xDF\x38\x18\x83\x07\xEF\xC1"
-			  "\x93\x3C\xAA\xAA\xFE\x06\x42\xCC"
-			  "\x0D\x70\x86\x5A\x44\xAD\x85\x17"
-			  "\xE4\x1F\x5E\xA5\x89\xAC\x32\xBC"
-			  "\x3D\xA7\xE9\x0A\x5C\x70\x4D\xDE"
-			  "\x99\x38\x07\xCA\x1D\x21\xC1\x11"
-			  "\x97\xEB\x98\x75\xC4\x73\x45\x83"
-			  "\x46\x1C\x9C\x91\x87\xC1\xA0\x56"
-			  "\x98\xA1\x8B\xDB\x22\x76\xBD\x62"
-			  "\xA4\xBC\xE8\x86\xDA\xD2\x51\x13"
-			  "\x13\xD2\x96\x68\x69\x10\x67\x0C"
-			  "\xD0\x17\x25\x7C\xB2\xAE\x4F\x93"
-			  "\xA6\x82\x20\xCF\x0F\xA6\x47\x79"
-			  "\x88\x09\x40\x59\xBD\x12\x64\xB5"
-			  "\x19\x38\x0D\xFF\x86\xD9\x42\x20"
-			  "\x81\x0D\x96\x99\xAF\x22\x1F\x94"
-			  "\x5C\x6E\xEC\xEA\xA3\x39\xCB\x09"
-			  "\x43\x19\x7F\xD0\xBB\x10\xC2\x49"
-			  "\xF7\xE9\xF2\xEE\xBF\xF7\xF8\xB3"
-			  "\x0E\x1A\xF1\x8D\x70\x82\x0C\x04"
-			  "\xFD\x29\x1A\xAC\xC0\x92\x48\x34"
-			  "\x6A\xE3\x1D\x4F\xFC\x1C\x72\x6A"
-			  "\x57\xCB\xAD\xD0\x98\xAB\xB1\x01"
-			  "\x03\x6A\x45\xDD\x07\x71\x5F\x5B"
-			  "\xB5\x4A\xE4\xE5\xB9\xB9\xBC\xAC"
-			  "\x44\xF7\x41\xA4\x5F\x2E\xE9\x28"
-			  "\xE3\x05\xD2\x94\x78\x4C\x33\x1B"
-			  "\xBD\xC1\x6E\x51\xD9\xAD\xD9\x86"
-			  "\x15\x4A\x78\xAE\x7B\xAD\x3B\xBC"
-			  "\x2F\xE0\x0E\xC5\x7B\x54\x97\x5F"
-			  "\x60\x51\x14\x65\xF9\x91\xE9\xDA"
-			  "\x9A\xBC\xFC\x19\x29\x67\xAA\x63"
-			  "\x5E\xF2\x48\x88\xEB\x79\xE1\xE4"
-			  "\xF7\xF6\x4C\xA9\xE2\x8C\x3B\xE0"
-			  "\xED\x52\xAE\x90\x8F\x5B\x98\x34"
-			  "\x29\x94\x34\x7F\xF9\x6C\x1E\xB6"
-			  "\xA4\xE7\x2D\x06\x54\x9D\xC3\x02"
-			  "\xC1\x90\xA4\x72\x31\x6B\x24\x51"
-			  "\x0B\xB3\x7C\x63\x15\xBA\xAF\x5D"
-			  "\x41\xE0\x37\x6D\xBE\x41\x58\xDE"
-			  "\xF2\x07\x62\x99\xBE\xC1\x8C\x0F"
-			  "\x0F\x28\xFB\x8F\x0E\x1D\x91\xE2"
-			  "\xDA\x99\x5C\x49\xBA\x9C\xA8\x86"
-			  "\x82\x63\x11\xB3\x54\x49\x00\x08"
-			  "\x07\xF2\xE8\x1F\x34\x49\x61\xF4"
-			  "\x81\xE9\xF6\xA9\x5A\x28\x60\x1F"
-			  "\x66\x99\x08\x06\xF2\xE8\x2D\xD1"
-			  "\xD0\x67\xBA\x32\x1F\x02\x86\x7B"
-			  "\xFB\x79\x3D\xC5\xB1\x7F\x15\xAF"
-			  "\xD7\xBF\x31\x46\x22\x7F\xAE\x5B"
-			  "\x8B\x95\x47\xC2\xB1\x62\xA1\xCE"
-			  "\x52\xAC\x9C\x8B\xC2\x49\x7F\xBC"
-			  "\x9C\x89\xB8\xB6\xCA\xE3\x8F\xEA"
-			  "\xAC\xB4\x5D\xE4\x50\xDC\x3A\xB5"
-			  "\x91\x04\x94\x99\x03\x3B\x42\x6D"
-			  "\x9C\x4A\x02\xF5\xB5\x38\x98\xA8"
-			  "\x5C\x97\x2E\x4D\x79\x67\x71\xAF"
-			  "\xF0\x70\x77\xFF\x2D\xDA\xA0\x9E"
-			  "\x23\x8D\xD6\xA6\x68\x10\x78\x9A"
-			  "\x64\xBB\x15\xB8\x56\xCF\xEE\xE5"
-			  "\x32\x44\x96\x1C\xD8\xEB\x95\xD2"
-			  "\xF3\x71\xEF\xEB\x4E\xBB\x4D",
-		.ilen	= 503,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92",
-		.rlen	= 503,
-		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 503 - 8, 8 },
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x5F\x58\x6E\x60\x51\x6E\xDC\x3D"
+		.ctext	= "\x5F\x58\x6E\x60\x51\x6E\xDC\x3D"
 			  "\xD1\xBB\xF7\xB7\xFD\x04\x44\x82"
 			  "\xDC\x9F\x4B\x02\xF1\xD2\x5A\x6F"
 			  "\x25\xF9\x27\x21\xF2\xD2\x9A\x01"
@@ -9056,114 +7354,47 @@ static const struct cipher_testvec bf_ctr_dec_tv_template[] = {
 			  "\xB5\x77\xBA\x1C\xEE\x71\xFA\xB0"
 			  "\x16\x4C\x18\x6B\xF2\x69\xA0\x07"
 			  "\xEF\xBE\xEC\x69\xAC\xA8\x63\x9E",
-		.ilen	= 504,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
-		.rlen	= 504,
+		.len	= 504,
 	},
 };
 
 /*
  * Twofish test vectors.
  */
-static const struct cipher_testvec tf_enc_tv_template[] = {
+static const struct cipher_testvec tf_tv_template[] = {
 	{
 		.key	= zeroed_string,
 		.klen	= 16,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
+		.ptext	= zeroed_string,
+		.ctext	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
 			  "\xb6\xbf\xec\x2f\x2a\xe8\xc3\x5a",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
 			  "\x00\x11\x22\x33\x44\x55\x66\x77",
 		.klen	= 24,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\xcf\xd1\xd2\xe5\xa9\xbe\x9c\xdf"
+		.ptext	= zeroed_string,
+		.ctext	= "\xcf\xd1\xd2\xe5\xa9\xbe\x9c\xdf"
 			  "\x50\x1f\x13\xb8\x92\xbd\x22\x48",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
 			  "\x00\x11\x22\x33\x44\x55\x66\x77"
 			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
 		.klen	= 32,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\x37\x52\x7b\xe0\x05\x23\x34\xb8"
+		.ptext	= zeroed_string,
+		.ctext	= "\x37\x52\x7b\xe0\x05\x23\x34\xb8"
 			  "\x9f\x0c\xfc\xca\xe8\x7c\xfa\x20",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x3F\x85\x62\x3F\x1C\xF9\xD6\x1C"
 			  "\xF9\xD6\xB3\x90\x6D\x4A\x90\x6D"
 			  "\x4A\x27\x04\xE1\x27\x04\xE1\xBE"
 			  "\x9B\x78\xBE\x9B\x78\x55\x32\x0F",
 		.klen	= 32,
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -9225,113 +7456,7 @@ static const struct cipher_testvec tf_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\x88\xCB\x1E\xC2\xAF\x8A\x97\xFF"
-			  "\xF6\x90\x46\x9C\x4A\x0F\x08\xDC"
-			  "\xDE\xAB\xAD\xFA\xFC\xA8\xC2\x3D"
-			  "\xE0\xE4\x8B\x3F\xD5\xA3\xF7\x14"
-			  "\x34\x9E\xB6\x08\xB2\xDD\xA8\xF5"
-			  "\xDF\xFA\xC7\xE8\x09\x50\x76\x08"
-			  "\xA2\xB6\x6A\x59\xC0\x2B\x6D\x05"
-			  "\x89\xF6\x82\xF0\xD3\xDB\x06\x02"
-			  "\xB5\x11\x5C\x5E\x79\x1A\xAC\x43"
-			  "\x5C\xC0\x30\x4B\x6B\x16\xA1\x40"
-			  "\x80\x27\x88\xBA\x2C\x74\x42\xE0"
-			  "\x1B\xA5\x85\x08\xB9\xE6\x22\x7A"
-			  "\x36\x3B\x0D\x9F\xA0\x22\x6C\x2A"
-			  "\x91\x75\x47\xBC\x67\x21\x4E\xF9"
-			  "\xEA\xFF\xD9\xD5\xC0\xFC\x9E\x2C"
-			  "\x3E\xAD\xC6\x61\x0E\x93\x7A\x22"
-			  "\x09\xC8\x8D\xC1\x8E\xB4\x8B\x5C"
-			  "\xC6\x24\x42\xB8\x23\x66\x80\xA9"
-			  "\x32\x0B\x7A\x29\xBF\xB3\x0B\x63"
-			  "\x43\x27\x13\xA9\xBE\xEB\xBD\xF3"
-			  "\x33\x62\x70\xE2\x1B\x86\x7A\xA1"
-			  "\x51\x4A\x16\xFE\x29\x63\x7E\xD0"
-			  "\x7A\xA4\x6E\x2C\xF8\xC1\xDB\xE8"
-			  "\xCB\x4D\xD2\x8C\x04\x14\xB4\x66"
-			  "\x41\xB7\x3A\x96\x16\x7C\x1D\x5B"
-			  "\xB6\x41\x42\x64\x43\xEE\x6E\x7C"
-			  "\x8B\xAF\x01\x9C\xA4\x6E\x75\x8F"
-			  "\xDE\x10\x9F\xA6\xE7\xD6\x44\x97"
-			  "\x66\xA3\x96\x0F\x1C\x25\x60\xF5"
-			  "\x3C\x2E\x32\x69\x0E\x82\xFF\x27"
-			  "\x0F\xB5\x06\xDA\xD8\x31\x15\x6C"
-			  "\xDF\x18\x6C\x87\xF5\x3B\x11\x9A"
-			  "\x1B\x42\x1F\x5B\x29\x19\x96\x13"
-			  "\x68\x2E\x5E\x08\x1C\x8F\x32\x4B"
-			  "\x81\x77\x6D\xF4\xA0\x01\x42\xEC"
-			  "\xDD\x5B\xFD\x3A\x8E\x6A\x14\xFB"
-			  "\x83\x54\xDF\x0F\x86\xB7\xEA\x40"
-			  "\x46\x39\xF7\x2A\x89\x8D\x4E\x96"
-			  "\x5F\x5F\x6D\x76\xC6\x13\x9D\x3D"
-			  "\x1D\x5F\x0C\x7D\xE2\xBC\xC2\x16"
-			  "\x16\xBE\x89\x3E\xB0\x61\xA2\x5D"
-			  "\xAF\xD1\x40\x5F\x1A\xB8\x26\x41"
-			  "\xC6\xBD\x36\xEF\xED\x29\x50\x6D"
-			  "\x10\xEF\x26\xE8\xA8\x93\x11\x3F"
-			  "\x2D\x1F\x88\x20\x77\x45\xF5\x66"
-			  "\x08\xB9\xF1\xEF\xB1\x93\xA8\x81"
-			  "\x65\xC5\xCD\x3E\x8C\x06\x60\x2C"
-			  "\xB2\x10\x7A\xCA\x05\x25\x59\xDB"
-			  "\xC7\x28\xF5\x20\x35\x52\x9E\x62"
-			  "\xF8\x88\x24\x1C\x4D\x84\x12\x39"
-			  "\x39\xE4\x2E\xF4\xD4\x9D\x2B\xBC"
-			  "\x87\x66\xE6\xC0\x6B\x31\x9A\x66"
-			  "\x03\xDC\x95\xD8\x6B\xD0\x30\x8F"
-			  "\xDF\x8F\x8D\xFA\xEC\x1F\x08\xBD"
-			  "\xA3\x63\xE2\x71\x4F\x03\x94\x87"
-			  "\x50\xDF\x15\x1F\xED\x3A\xA3\x7F"
-			  "\x1F\x2A\xB5\xA1\x69\xAC\x4B\x0D"
-			  "\x84\x9B\x2A\xE9\x55\xDD\x46\x91"
-			  "\x15\x33\xF3\x2B\x9B\x46\x97\x00"
-			  "\xF0\x29\xD8\x59\x5D\x33\x37\xF9"
-			  "\x58\x33\x9B\x78\xC7\x58\x48\x6B"
-			  "\x2C\x75\x64\xC4\xCA\xC1\x7E\xD5",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec tf_dec_tv_template[] = {
-	{
-		.key	= zeroed_string,
-		.klen	= 16,
-		.input	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
-			  "\xb6\xbf\xec\x2f\x2a\xe8\xc3\x5a",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
-			  "\x00\x11\x22\x33\x44\x55\x66\x77",
-		.klen	= 24,
-		.input	= "\xcf\xd1\xd2\xe5\xa9\xbe\x9c\xdf"
-			  "\x50\x1f\x13\xb8\x92\xbd\x22\x48",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
-			  "\x00\x11\x22\x33\x44\x55\x66\x77"
-			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
-		.klen	= 32,
-		.input	= "\x37\x52\x7b\xe0\x05\x23\x34\xb8"
-			  "\x9f\x0c\xfc\xca\xe8\x7c\xfa\x20",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x3F\x85\x62\x3F\x1C\xF9\xD6\x1C"
-			  "\xF9\xD6\xB3\x90\x6D\x4A\x90\x6D"
-			  "\x4A\x27\x04\xE1\x27\x04\xE1\xBE"
-			  "\x9B\x78\xBE\x9B\x78\x55\x32\x0F",
-		.klen	= 32,
-		.input	= "\x88\xCB\x1E\xC2\xAF\x8A\x97\xFF"
+		.ctext	= "\x88\xCB\x1E\xC2\xAF\x8A\x97\xFF"
 			  "\xF6\x90\x46\x9C\x4A\x0F\x08\xDC"
 			  "\xDE\xAB\xAD\xFA\xFC\xA8\xC2\x3D"
 			  "\xE0\xE4\x8B\x3F\xD5\xA3\xF7\x14"
@@ -9393,119 +7518,52 @@ static const struct cipher_testvec tf_dec_tv_template[] = {
 			  "\xF0\x29\xD8\x59\x5D\x33\x37\xF9"
 			  "\x58\x33\x9B\x78\xC7\x58\x48\x6B"
 			  "\x2C\x75\x64\xC4\xCA\xC1\x7E\xD5",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec tf_cbc_enc_tv_template[] = {
+static const struct cipher_testvec tf_cbc_tv_template[] = {
 	{ /* Generated with Nettle */
 		.key	= zeroed_string,
 		.klen	= 16,
 		.iv	= zeroed_string,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
+		.ptext	= zeroed_string,
+		.ctext	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
 			  "\xb6\xbf\xec\x2f\x2a\xe8\xc3\x5a",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= zeroed_string,
 		.klen	= 16,
 		.iv	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
 			  "\xb6\xbf\xec\x2f\x2a\xe8\xc3\x5a",
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\xd4\x91\xdb\x16\xe7\xb1\xc3\x9e"
+		.ptext	= zeroed_string,
+		.ctext	= "\xd4\x91\xdb\x16\xe7\xb1\xc3\x9e"
 			  "\x86\xcb\x08\x6b\x78\x9f\x54\x19",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= zeroed_string,
 		.klen	= 16,
 		.iv	= "\xd4\x91\xdb\x16\xe7\xb1\xc3\x9e"
 			  "\x86\xcb\x08\x6b\x78\x9f\x54\x19",
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\x05\xef\x8c\x61\xa8\x11\x58\x26"
+		.ptext	= zeroed_string,
+		.ctext	= "\x05\xef\x8c\x61\xa8\x11\x58\x26"
 			  "\x34\xba\x5c\xb7\x10\x6a\xa6\x41",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= zeroed_string,
 		.klen	= 16,
 		.iv	= zeroed_string,
-		.input	= zeroed_string,
-		.ilen	= 48,
-		.result	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
+		.ptext	= zeroed_string,
+		.ctext	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
 			  "\xb6\xbf\xec\x2f\x2a\xe8\xc3\x5a"
 			  "\xd4\x91\xdb\x16\xe7\xb1\xc3\x9e"
 			  "\x86\xcb\x08\x6b\x78\x9f\x54\x19"
 			  "\x05\xef\x8c\x61\xa8\x11\x58\x26"
 			  "\x34\xba\x5c\xb7\x10\x6a\xa6\x41",
-		.rlen	= 48,
+		.len	= 48,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -9514,7 +7572,7 @@ static const struct cipher_testvec tf_cbc_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -9576,128 +7634,7 @@ static const struct cipher_testvec tf_cbc_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\xC8\xFF\xF2\x53\xA6\x27\x09\xD1"
-			  "\x33\x38\xC2\xC0\x0C\x14\x7E\xB5"
-			  "\x26\x1B\x05\x0C\x05\x12\x3F\xC0"
-			  "\xF9\x1C\x02\x28\x40\x96\x6F\xD0"
-			  "\x3D\x32\xDF\xDA\x56\x00\x6E\xEE"
-			  "\x5B\x2A\x72\x9D\xC2\x4D\x19\xBC"
-			  "\x8C\x53\xFA\x87\x6F\xDD\x81\xA3"
-			  "\xB1\xD3\x44\x65\xDF\xE7\x63\x38"
-			  "\x4A\xFC\xDC\xEC\x3F\x26\x8E\xB8"
-			  "\x43\xFC\xFE\x18\xB5\x11\x6D\x31"
-			  "\x81\x8B\x0D\x75\xF6\x80\xEC\x84"
-			  "\x04\xB9\xE6\x09\x63\xED\x39\xDB"
-			  "\xC3\xF6\x14\xD6\x6E\x5E\x8B\xBD"
-			  "\x3E\xFA\xD7\x98\x50\x6F\xD9\x63"
-			  "\x02\xCD\x0D\x39\x4B\x0D\xEC\x80"
-			  "\xE3\x6A\x17\xF4\xCC\xAD\xFF\x68"
-			  "\x45\xDD\xC8\x83\x1D\x41\x96\x0D"
-			  "\x91\x2E\x05\xD3\x59\x82\xE0\x43"
-			  "\x90\x4F\xB9\xF7\xAD\x6B\x2E\xAF"
-			  "\xA7\x84\x00\x53\xCD\x6F\xD1\x0C"
-			  "\x4E\xF9\x5A\x23\xFB\xCA\xC7\xD3"
-			  "\xA9\xAA\x9D\xB2\x3F\x66\xF1\xAC"
-			  "\x25\x21\x8F\xF7\xEF\xF2\x6A\xDF"
-			  "\xE8\xDA\x75\x1A\x8A\xF1\xDD\x38"
-			  "\x1F\xF9\x3D\x68\x4A\xBB\x9E\x34"
-			  "\x1F\x66\x1F\x9C\x2B\x54\xFF\x60"
-			  "\x7F\x29\x4B\x55\x80\x8F\x4E\xA7"
-			  "\xA6\x9A\x0A\xD9\x0D\x19\x00\xF8"
-			  "\x1F\xBC\x0C\x40\x6B\xEC\x99\x25"
-			  "\x94\x70\x74\x0E\x1D\xC5\xBC\x12"
-			  "\xF3\x42\xBE\x95\xBF\xFB\x4E\x55"
-			  "\x9A\xB9\xCE\x14\x16\x5B\xDC\xD3"
-			  "\x75\x42\x62\x04\x31\x1F\x95\x7C"
-			  "\x66\x1A\x97\xDC\x2F\x40\x5C\x39"
-			  "\x78\xE6\x02\xDB\x49\xE1\xC6\x47"
-			  "\xC2\x78\x9A\xBB\xF3\xBE\xCB\x93"
-			  "\xD8\xB8\xE8\xBB\x8C\xB3\x9B\xA7"
-			  "\xC2\x89\xF3\x91\x88\x83\x3D\xF0"
-			  "\x29\xA2\xCD\xB5\x79\x16\xC2\x40"
-			  "\x11\x03\x8E\x9C\xFD\xC9\x43\xC4"
-			  "\xC2\x19\xF0\x4A\x32\xEF\x0C\x2B"
-			  "\xD3\x2B\xE9\xD4\x4C\xDE\x95\xCF"
-			  "\x04\x03\xD3\x2C\x7F\x82\xC8\xFA"
-			  "\x0F\xD8\x7A\x39\x7B\x01\x41\x9C"
-			  "\x78\xB6\xC9\xBF\xF9\x78\x57\x88"
-			  "\xB1\xA5\xE1\xE0\xD9\x16\xD4\xC8"
-			  "\xEE\xC4\xBE\x7B\x55\x59\x00\x48"
-			  "\x1B\xBC\x14\xFA\x2A\x9D\xC9\x1C"
-			  "\xFB\x28\x3F\x95\xDD\xB7\xD6\xCE"
-			  "\x3A\x7F\x09\x0C\x0E\x69\x30\x7D"
-			  "\xBC\x68\x9C\x91\x2A\x59\x57\x04"
-			  "\xED\x1A\x1E\x00\xB1\x85\x92\x04"
-			  "\x28\x8C\x0C\x3C\xC1\xD5\x12\xF7"
-			  "\x4C\x3E\xB0\xE7\x86\x62\x68\x91"
-			  "\xFC\xC4\xE2\xCE\xA6\xDC\x5E\x93"
-			  "\x5D\x8D\x8C\x68\xB3\xB2\xB9\x64"
-			  "\x16\xB8\xC8\x6F\xD8\xEE\x21\xBD"
-			  "\xAC\x18\x0C\x7D\x0D\x05\xAB\xF1"
-			  "\xFA\xDD\xE2\x48\xDF\x4C\x02\x39"
-			  "\x69\xA1\x62\xBD\x49\x3A\x9D\x91"
-			  "\x30\x70\x56\xA4\x37\xDD\x7C\xC0"
-			  "\x0A\xA3\x30\x10\x26\x25\x41\x2C",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec tf_cbc_dec_tv_template[] = {
-	{ /* Reverse of the first four above */
-		.key	= zeroed_string,
-		.klen	= 16,
-		.iv	= zeroed_string,
-		.input	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
-			  "\xb6\xbf\xec\x2f\x2a\xe8\xc3\x5a",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, {
-		.key	= zeroed_string,
-		.klen	= 16,
-		.iv	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
-			  "\xb6\xbf\xec\x2f\x2a\xe8\xc3\x5a",
-		.input	= "\xd4\x91\xdb\x16\xe7\xb1\xc3\x9e"
-			  "\x86\xcb\x08\x6b\x78\x9f\x54\x19",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, {
-		.key	= zeroed_string,
-		.klen	= 16,
-		.iv	= "\xd4\x91\xdb\x16\xe7\xb1\xc3\x9e"
-			  "\x86\xcb\x08\x6b\x78\x9f\x54\x19",
-		.input	= "\x05\xef\x8c\x61\xa8\x11\x58\x26"
-			  "\x34\xba\x5c\xb7\x10\x6a\xa6\x41",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, {
-		.key	= zeroed_string,
-		.klen	= 16,
-		.iv	= zeroed_string,
-		.input	= "\x9f\x58\x9f\x5c\xf6\x12\x2c\x32"
-			  "\xb6\xbf\xec\x2f\x2a\xe8\xc3\x5a"
-			  "\xd4\x91\xdb\x16\xe7\xb1\xc3\x9e"
-			  "\x86\xcb\x08\x6b\x78\x9f\x54\x19"
-			  "\x05\xef\x8c\x61\xa8\x11\x58\x26"
-			  "\x34\xba\x5c\xb7\x10\x6a\xa6\x41",
-		.ilen	= 48,
-		.result	= zeroed_string,
-		.rlen	= 48,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\xC8\xFF\xF2\x53\xA6\x27\x09\xD1"
+		.ctext	= "\xC8\xFF\xF2\x53\xA6\x27\x09\xD1"
 			  "\x33\x38\xC2\xC0\x0C\x14\x7E\xB5"
 			  "\x26\x1B\x05\x0C\x05\x12\x3F\xC0"
 			  "\xF9\x1C\x02\x28\x40\x96\x6F\xD0"
@@ -9759,77 +7696,14 @@ static const struct cipher_testvec tf_cbc_dec_tv_template[] = {
 			  "\x69\xA1\x62\xBD\x49\x3A\x9D\x91"
 			  "\x30\x70\x56\xA4\x37\xDD\x7C\xC0"
 			  "\x0A\xA3\x30\x10\x26\x25\x41\x2C",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
+static const struct cipher_testvec tf_ctr_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -9838,7 +7712,7 @@ static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -9900,8 +7774,7 @@ static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\xDF\xDD\x69\xFA\xB0\x2E\xFD\xFE"
+		.ctext	= "\xDF\xDD\x69\xFA\xB0\x2E\xFD\xFE"
 			  "\x70\x9E\xC5\x4B\xC9\xD4\xA1\x30"
 			  "\x26\x9B\x89\xA1\xEE\x43\xE0\x52"
 			  "\x55\x17\x4E\xC7\x0E\x33\x1F\xF1"
@@ -9963,7 +7836,7 @@ static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 			  "\xE8\x47\x2A\x4D\xFD\xA1\xBC\xE3"
 			  "\xB9\x32\xE2\xC1\x82\xAC\xFE\xCC"
 			  "\xC5\xC9\x7F\x9E\xCF\x33\x7A\xDF",
-		.rlen	= 496,
+		.len	= 496,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -9972,7 +7845,7 @@ static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
 			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -10034,8 +7907,7 @@ static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\xEB\x44\xAF\x49\x27\xB8\xFB\x44"
+		.ctext	= "\xEB\x44\xAF\x49\x27\xB8\xFB\x44"
 			  "\x4C\xA6\xC3\x0C\x8B\xD0\x01\x0C"
 			  "\x53\xC8\x16\x38\xDE\x40\x4F\x91"
 			  "\x25\x6D\x4C\xA0\x9A\x87\x1E\xDA"
@@ -10097,7 +7969,7 @@ static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 			  "\x4C\xB6\xF8\xF4\x5F\x48\x52\x54"
 			  "\x94\x63\xA8\x4E\xCF\xD2\x1B\x1B"
 			  "\x22\x18\x6A\xAF\x6E\x3E\xE1\x0D",
-		.rlen	= 496,
+		.len	= 496,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -10106,7 +7978,7 @@ static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -10169,355 +8041,7 @@ static const struct cipher_testvec tf_ctr_enc_tv_template[] = {
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
 			  "\x2B\xC2\x59",
-		.ilen	= 499,
-		.result	= "\xDF\xDD\x69\xFA\xB0\x2E\xFD\xFE"
-			  "\x70\x9E\xC5\x4B\xC9\xD4\xA1\x30"
-			  "\x26\x9B\x89\xA1\xEE\x43\xE0\x52"
-			  "\x55\x17\x4E\xC7\x0E\x33\x1F\xF1"
-			  "\x9F\x8D\x40\x9F\x24\xFD\x92\xA0"
-			  "\xBC\x8F\x35\xDD\x67\x38\xD8\xAA"
-			  "\xCF\xF8\x48\xCA\xFB\xE4\x5C\x60"
-			  "\x01\x41\x21\x12\x38\xAB\x52\x4F"
-			  "\xA8\x57\x20\xE0\x21\x6A\x17\x0D"
-			  "\x0E\xF9\x8E\x49\x42\x00\x3C\x94"
-			  "\x14\xC0\xD0\x8D\x8A\x98\xEB\x29"
-			  "\xEC\xAE\x96\x44\xC0\x3C\x48\xDC"
-			  "\x29\x35\x25\x2F\xE7\x11\x6C\x68"
-			  "\xC8\x67\x0A\x2F\xF4\x07\xBE\xF9"
-			  "\x2C\x31\x87\x40\xAB\xB2\xB6\xFA"
-			  "\xD2\xC9\x6D\x5C\x50\xE9\xE6\x7E"
-			  "\xE3\x0A\xD2\xD5\x6D\x8D\x64\x9E"
-			  "\x70\xCE\x03\x76\xDD\xE0\xF0\x8C"
-			  "\x84\x86\x8B\x6A\xFE\xC7\xF9\x69"
-			  "\x2E\xFE\xFC\xC2\xC4\x1A\x55\x58"
-			  "\xB3\xBE\xE2\x7E\xED\x39\x42\x6C"
-			  "\xB4\x42\x97\x9A\xEC\xE1\x0A\x06"
-			  "\x02\xC5\x03\x9D\xC4\x48\x15\x66"
-			  "\x35\x6A\xC2\xC9\xA2\x26\x30\xBB"
-			  "\xDB\x2D\xC8\x08\x2B\xA0\x29\x1A"
-			  "\x23\x61\x48\xEA\x80\x04\x27\xAA"
-			  "\x69\x49\xE8\xE8\x4A\x83\x6B\x5A"
-			  "\xCA\x7C\xD3\xB1\xB5\x0B\xCC\x23"
-			  "\x74\x1F\xA9\x87\xCD\xED\xC0\x2D"
-			  "\xBF\xEB\xCF\x16\x2D\x2A\x2E\x1D"
-			  "\x96\xBA\x36\x11\x45\x41\xDA\xCE"
-			  "\xA4\x48\x80\x8B\x06\xF4\x98\x89"
-			  "\x8B\x23\x08\x53\xF4\xD4\x5A\x24"
-			  "\x8B\xF8\x43\x73\xD1\xEE\xC4\xB0"
-			  "\xF8\xFE\x09\x0C\x75\x05\x38\x0B"
-			  "\x7C\x81\xDE\x9D\xE4\x61\x37\x63"
-			  "\x63\xAD\x12\xD2\x04\xB9\xCE\x45"
-			  "\x5A\x1A\x6E\xB3\x78\x2A\xA4\x74"
-			  "\x86\xD0\xE3\xFF\xDA\x38\x9C\xB5"
-			  "\xB8\xB1\xDB\x38\x2F\xC5\x6A\xB4"
-			  "\xEB\x6E\x96\xE8\x43\x80\xB5\x51"
-			  "\x61\x2D\x48\xAA\x07\x65\x11\x8C"
-			  "\x48\xE3\x90\x7E\x78\x3A\xEC\x97"
-			  "\x05\x3D\x84\xE7\x90\x2B\xAA\xBD"
-			  "\x83\x29\x0E\x1A\x81\x73\x7B\xE0"
-			  "\x7A\x01\x4A\x37\x3B\x77\x7F\x8D"
-			  "\x49\xA4\x2F\x6E\xBE\x68\x99\x08"
-			  "\x99\xAA\x4C\x12\x04\xAE\x1F\x77"
-			  "\x35\x88\xF1\x65\x06\x0A\x0B\x4D"
-			  "\x47\xF9\x50\x38\x5D\x71\xF9\x6E"
-			  "\xDE\xEC\x61\x35\x2C\x4C\x96\x50"
-			  "\xE8\x28\x93\x9C\x7E\x01\xC6\x04"
-			  "\xB2\xD6\xBC\x6C\x17\xEB\xC1\x7D"
-			  "\x11\xE9\x43\x83\x76\xAA\x53\x37"
-			  "\x0C\x1D\x39\x89\x53\x72\x09\x7E"
-			  "\xD9\x85\x16\x04\xA5\x2C\x05\x6F"
-			  "\x17\x0C\x6E\x66\xAA\x84\xA7\xD9"
-			  "\xE2\xD9\xC4\xEB\x43\x3E\xB1\x8D"
-			  "\x7C\x36\xC7\x71\x70\x9C\x10\xD8"
-			  "\xE8\x47\x2A\x4D\xFD\xA1\xBC\xE3"
-			  "\xB9\x32\xE2\xC1\x82\xAC\xFE\xCC"
-			  "\xC5\xC9\x7F\x9E\xCF\x33\x7A\xDF"
-			  "\x6C\x82\x9D",
-		.rlen	= 499,
-		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 499 - 16, 16 },
-	},
-};
-
-static const struct cipher_testvec tf_ctr_dec_tv_template[] = {
-	{ /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\xDF\xDD\x69\xFA\xB0\x2E\xFD\xFE"
-			  "\x70\x9E\xC5\x4B\xC9\xD4\xA1\x30"
-			  "\x26\x9B\x89\xA1\xEE\x43\xE0\x52"
-			  "\x55\x17\x4E\xC7\x0E\x33\x1F\xF1"
-			  "\x9F\x8D\x40\x9F\x24\xFD\x92\xA0"
-			  "\xBC\x8F\x35\xDD\x67\x38\xD8\xAA"
-			  "\xCF\xF8\x48\xCA\xFB\xE4\x5C\x60"
-			  "\x01\x41\x21\x12\x38\xAB\x52\x4F"
-			  "\xA8\x57\x20\xE0\x21\x6A\x17\x0D"
-			  "\x0E\xF9\x8E\x49\x42\x00\x3C\x94"
-			  "\x14\xC0\xD0\x8D\x8A\x98\xEB\x29"
-			  "\xEC\xAE\x96\x44\xC0\x3C\x48\xDC"
-			  "\x29\x35\x25\x2F\xE7\x11\x6C\x68"
-			  "\xC8\x67\x0A\x2F\xF4\x07\xBE\xF9"
-			  "\x2C\x31\x87\x40\xAB\xB2\xB6\xFA"
-			  "\xD2\xC9\x6D\x5C\x50\xE9\xE6\x7E"
-			  "\xE3\x0A\xD2\xD5\x6D\x8D\x64\x9E"
-			  "\x70\xCE\x03\x76\xDD\xE0\xF0\x8C"
-			  "\x84\x86\x8B\x6A\xFE\xC7\xF9\x69"
-			  "\x2E\xFE\xFC\xC2\xC4\x1A\x55\x58"
-			  "\xB3\xBE\xE2\x7E\xED\x39\x42\x6C"
-			  "\xB4\x42\x97\x9A\xEC\xE1\x0A\x06"
-			  "\x02\xC5\x03\x9D\xC4\x48\x15\x66"
-			  "\x35\x6A\xC2\xC9\xA2\x26\x30\xBB"
-			  "\xDB\x2D\xC8\x08\x2B\xA0\x29\x1A"
-			  "\x23\x61\x48\xEA\x80\x04\x27\xAA"
-			  "\x69\x49\xE8\xE8\x4A\x83\x6B\x5A"
-			  "\xCA\x7C\xD3\xB1\xB5\x0B\xCC\x23"
-			  "\x74\x1F\xA9\x87\xCD\xED\xC0\x2D"
-			  "\xBF\xEB\xCF\x16\x2D\x2A\x2E\x1D"
-			  "\x96\xBA\x36\x11\x45\x41\xDA\xCE"
-			  "\xA4\x48\x80\x8B\x06\xF4\x98\x89"
-			  "\x8B\x23\x08\x53\xF4\xD4\x5A\x24"
-			  "\x8B\xF8\x43\x73\xD1\xEE\xC4\xB0"
-			  "\xF8\xFE\x09\x0C\x75\x05\x38\x0B"
-			  "\x7C\x81\xDE\x9D\xE4\x61\x37\x63"
-			  "\x63\xAD\x12\xD2\x04\xB9\xCE\x45"
-			  "\x5A\x1A\x6E\xB3\x78\x2A\xA4\x74"
-			  "\x86\xD0\xE3\xFF\xDA\x38\x9C\xB5"
-			  "\xB8\xB1\xDB\x38\x2F\xC5\x6A\xB4"
-			  "\xEB\x6E\x96\xE8\x43\x80\xB5\x51"
-			  "\x61\x2D\x48\xAA\x07\x65\x11\x8C"
-			  "\x48\xE3\x90\x7E\x78\x3A\xEC\x97"
-			  "\x05\x3D\x84\xE7\x90\x2B\xAA\xBD"
-			  "\x83\x29\x0E\x1A\x81\x73\x7B\xE0"
-			  "\x7A\x01\x4A\x37\x3B\x77\x7F\x8D"
-			  "\x49\xA4\x2F\x6E\xBE\x68\x99\x08"
-			  "\x99\xAA\x4C\x12\x04\xAE\x1F\x77"
-			  "\x35\x88\xF1\x65\x06\x0A\x0B\x4D"
-			  "\x47\xF9\x50\x38\x5D\x71\xF9\x6E"
-			  "\xDE\xEC\x61\x35\x2C\x4C\x96\x50"
-			  "\xE8\x28\x93\x9C\x7E\x01\xC6\x04"
-			  "\xB2\xD6\xBC\x6C\x17\xEB\xC1\x7D"
-			  "\x11\xE9\x43\x83\x76\xAA\x53\x37"
-			  "\x0C\x1D\x39\x89\x53\x72\x09\x7E"
-			  "\xD9\x85\x16\x04\xA5\x2C\x05\x6F"
-			  "\x17\x0C\x6E\x66\xAA\x84\xA7\xD9"
-			  "\xE2\xD9\xC4\xEB\x43\x3E\xB1\x8D"
-			  "\x7C\x36\xC7\x71\x70\x9C\x10\xD8"
-			  "\xE8\x47\x2A\x4D\xFD\xA1\xBC\xE3"
-			  "\xB9\x32\xE2\xC1\x82\xAC\xFE\xCC"
-			  "\xC5\xC9\x7F\x9E\xCF\x33\x7A\xDF",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
-			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\xEB\x44\xAF\x49\x27\xB8\xFB\x44"
-			  "\x4C\xA6\xC3\x0C\x8B\xD0\x01\x0C"
-			  "\x53\xC8\x16\x38\xDE\x40\x4F\x91"
-			  "\x25\x6D\x4C\xA0\x9A\x87\x1E\xDA"
-			  "\x88\x7E\x89\xE9\x67\x2B\x83\xA2"
-			  "\x5F\x2E\x23\x3E\x45\xB9\x77\x7B"
-			  "\xA6\x7E\x47\x36\x81\x9F\x9B\xF3"
-			  "\xE0\xF0\xD7\x47\xA9\xC8\xEF\x33"
-			  "\x0C\x43\xFE\x67\x50\x0A\x2C\x3E"
-			  "\xA0\xE1\x25\x8E\x80\x07\x4A\xC0"
-			  "\x64\x89\x9F\x6A\x27\x96\x07\xA6"
-			  "\x9B\xC8\x1B\x21\x60\xAE\x5D\x01"
-			  "\xE2\xCD\xC8\xAA\x6C\x9D\x1C\x34"
-			  "\x39\x18\x09\xA4\x82\x59\x78\xE7"
-			  "\xFC\x59\x65\xF2\x94\xFF\xFB\xE2"
-			  "\x3C\xDA\xB1\x90\x95\xBF\x91\xE3"
-			  "\xE6\x87\x31\x9E\x16\x85\xAD\xB1"
-			  "\x4C\xAE\x43\x4D\x19\x58\xB5\x5E"
-			  "\x2E\xF5\x09\xAA\x39\xF4\xC0\xB3"
-			  "\xD4\x4D\xDB\x73\x7A\xD4\xF1\xBF"
-			  "\x89\x16\x4D\x2D\xA2\x26\x33\x72"
-			  "\x18\x33\x7E\xD6\xD2\x16\xA4\x54"
-			  "\xF4\x8C\xB3\x52\xDF\x21\x9C\xEB"
-			  "\xBF\x49\xD3\xF9\x05\x06\xCB\xD2"
-			  "\xA9\xD2\x3B\x6E\x19\x8C\xBC\x19"
-			  "\xAB\x89\xD6\xD8\xCD\x56\x89\x5E"
-			  "\xAC\x00\xE3\x50\x63\x4A\x80\x9A"
-			  "\x05\xBC\x50\x39\xD3\x32\xD9\x0D"
-			  "\xE3\x20\x0D\x75\x54\xEC\xE6\x31"
-			  "\x14\xB9\x3A\x59\x00\x43\x37\x8E"
-			  "\x8C\x5A\x79\x62\x14\x76\x8A\xAE"
-			  "\x8F\xCC\xA1\x6C\x38\x78\xDD\x2D"
-			  "\x8B\x6D\xEA\xBD\x7B\x25\xFF\x60"
-			  "\xC9\x87\xB1\x79\x1E\xA5\x86\x68"
-			  "\x81\xB4\xE2\xC1\x05\x7D\x3A\x73"
-			  "\xD0\xDA\x75\x77\x9E\x05\x27\xF1"
-			  "\x08\xA9\x66\x64\x6C\xBC\x82\x17"
-			  "\x2C\x23\x5F\x62\x4D\x02\x1A\x58"
-			  "\xE7\xB7\x23\x6D\xE2\x20\xDA\xEF"
-			  "\xB4\xB3\x3F\xB2\x2B\x69\x98\x83"
-			  "\x95\x87\x13\x57\x60\xD7\xB5\xB1"
-			  "\xEE\x0A\x2F\x95\x36\x4C\x76\x5D"
-			  "\x5F\xD9\x19\xED\xB9\xA5\x48\xBF"
-			  "\xC8\xAB\x0F\x71\xCC\x61\x8E\x0A"
-			  "\xD0\x29\x44\xA8\xB9\xC1\xE8\xC8"
-			  "\xC9\xA8\x28\x81\xFB\x50\xF2\xF0"
-			  "\x26\xAE\x39\xB8\x91\xCD\xA8\xAC"
-			  "\xDE\x55\x1B\x50\x14\x53\x44\x17"
-			  "\x54\x46\xFC\xB1\xE4\x07\x6B\x9A"
-			  "\x01\x14\xF0\x2E\x2E\xDB\x46\x1B"
-			  "\x1A\x09\x97\xA9\xB6\x97\x79\x06"
-			  "\xFB\xCB\x85\xCF\xDD\xA1\x41\xB1"
-			  "\x00\xAA\xF7\xE0\x89\x73\xFB\xE5"
-			  "\xBF\x84\xDB\xC9\xCD\xC4\xA2\x0D"
-			  "\x3B\xAC\xF9\xDF\x96\xBF\x88\x23"
-			  "\x41\x67\xA1\x24\x99\x7E\xCC\x9B"
-			  "\x02\x8F\x6A\x49\xF6\x25\xBA\x7A"
-			  "\xF4\x78\xFD\x79\x62\x63\x4F\x14"
-			  "\xD6\x11\x11\x04\x05\x5F\x7E\xEA"
-			  "\x4C\xB6\xF8\xF4\x5F\x48\x52\x54"
-			  "\x94\x63\xA8\x4E\xCF\xD2\x1B\x1B"
-			  "\x22\x18\x6A\xAF\x6E\x3E\xE1\x0D",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\xDF\xDD\x69\xFA\xB0\x2E\xFD\xFE"
+		.ctext	= "\xDF\xDD\x69\xFA\xB0\x2E\xFD\xFE"
 			  "\x70\x9E\xC5\x4B\xC9\xD4\xA1\x30"
 			  "\x26\x9B\x89\xA1\xEE\x43\xE0\x52"
 			  "\x55\x17\x4E\xC7\x0E\x33\x1F\xF1"
@@ -10580,78 +8104,14 @@ static const struct cipher_testvec tf_ctr_dec_tv_template[] = {
 			  "\xB9\x32\xE2\xC1\x82\xAC\xFE\xCC"
 			  "\xC5\xC9\x7F\x9E\xCF\x33\x7A\xDF"
 			  "\x6C\x82\x9D",
-		.ilen	= 499,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59",
-		.rlen	= 499,
+		.len	= 499,
 		.also_non_np = 1,
 		.np	= 2,
 		.tap	= { 499 - 16, 16 },
 	},
 };
 
-static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
+static const struct cipher_testvec tf_lrw_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	{
 		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
@@ -10661,12 +8121,11 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\xa1\x6c\x50\x69\x26\xa4\xef\x7b"
+		.ctext	= "\xa1\x6c\x50\x69\x26\xa4\xef\x7b"
 			  "\x7c\xc6\x91\xeb\x72\xdd\x9b\xee",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x59\x70\x47\x14\xf5\x57\x47\x8c"
 			  "\xd7\x79\xe8\x0f\x54\x88\x79\x44"
@@ -10675,12 +8134,11 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\xab\x72\x0a\xad\x3b\x0c\xf0\xc9"
+		.ctext	= "\xab\x72\x0a\xad\x3b\x0c\xf0\xc9"
 			  "\x42\x2f\xf1\xae\xf1\x3c\xb1\xbd",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xd8\x2a\x91\x34\xb2\x6a\x56\x50"
 			  "\x30\xfe\x69\xe2\x37\x7f\x98\x47"
@@ -10689,12 +8147,11 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x85\xa7\x56\x67\x08\xfa\x42\xe1"
+		.ctext	= "\x85\xa7\x56\x67\x08\xfa\x42\xe1"
 			  "\x22\xe6\x82\xfc\xd9\xb4\xd7\xd4",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x0f\x6a\xef\xf8\xd3\xd2\xbb\x15"
 			  "\x25\x83\xf7\x3c\x1f\x01\x28\x74"
@@ -10704,12 +8161,11 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 		.klen	= 40,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\xd2\xaf\x69\x35\x24\x1d\x0e\x1c"
+		.ctext	= "\xd2\xaf\x69\x35\x24\x1d\x0e\x1c"
 			  "\x84\x8b\x05\xe4\xa2\x2f\x16\xf5",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x8a\xd4\xee\x10\x2f\xbd\x81\xff"
 			  "\xf8\x86\xce\xac\x93\xc5\xad\xc6"
@@ -10719,12 +8175,11 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 		.klen	= 40,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x4a\x23\x56\xd7\xff\x90\xd0\x9a"
+		.ctext	= "\x4a\x23\x56\xd7\xff\x90\xd0\x9a"
 			  "\x0d\x7c\x26\xfc\xf0\xf0\xf6\xe4",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -10735,12 +8190,11 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x30\xaf\x26\x05\x9d\x5d\x0a\x58"
+		.ctext	= "\x30\xaf\x26\x05\x9d\x5d\x0a\x58"
 			  "\xe2\xe7\xce\x8a\xb2\x56\x6d\x76",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xfb\x76\x15\xb2\x3d\x80\x89\x1d"
 			  "\xd4\x70\x98\x0b\xc7\x95\x84\xc8"
@@ -10751,12 +8205,11 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\xdf\xcf\xdc\xd2\xe1\xcf\x86\x75"
+		.ctext	= "\xdf\xcf\xdc\xd2\xe1\xcf\x86\x75"
 			  "\x17\x66\x5e\x0c\x14\xa1\x3d\x40",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -10767,7 +8220,7 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
+		.ptext	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
 			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
 			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
 			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
@@ -10831,196 +8284,7 @@ static const struct cipher_testvec tf_lrw_enc_tv_template[] = {
 			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
 			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.ilen	= 512,
-		.result	= "\x30\x38\xeb\xaf\x12\x43\x1a\x89"
-			  "\x62\xa2\x36\xe5\xcf\x77\x1e\xd9"
-			  "\x08\xc3\x0d\xdd\x95\xab\x19\x96"
-			  "\x27\x52\x41\xc3\xca\xfb\xf6\xee"
-			  "\x40\x2d\xdf\xdd\x00\x0c\xb9\x0a"
-			  "\x3a\xf0\xc0\xd1\xda\x63\x9e\x45"
-			  "\x42\xe9\x29\xc0\xb4\x07\xb4\x31"
-			  "\x66\x77\x72\xb5\xb6\xb3\x57\x46"
-			  "\x34\x9a\xfe\x03\xaf\x6b\x36\x07"
-			  "\x63\x8e\xc2\x5d\xa6\x0f\xb6\x7d"
-			  "\xfb\x6d\x82\x51\xb6\x98\xd0\x71"
-			  "\xe7\x10\x7a\xdf\xb2\xbd\xf1\x1d"
-			  "\x72\x2b\x54\x13\xe3\x6d\x79\x37"
-			  "\xa9\x39\x2c\xdf\x21\xab\x87\xd5"
-			  "\xee\xef\x9a\x12\x50\x39\x2e\x1b"
-			  "\x7d\xe6\x6a\x27\x48\xb9\xe7\xac"
-			  "\xaa\xcd\x79\x5f\xf2\xf3\xa0\x08"
-			  "\x6f\x2c\xf4\x0e\xd1\xb8\x89\x25"
-			  "\x31\x9d\xef\xb1\x1d\x27\x55\x04"
-			  "\xc9\x8c\xb7\x68\xdc\xb6\x67\x8a"
-			  "\xdb\xcf\x22\xf2\x3b\x6f\xce\xbb"
-			  "\x26\xbe\x4f\x27\x04\x42\xd1\x44"
-			  "\x4c\x08\xa3\x95\x4c\x7f\x1a\xaf"
-			  "\x1d\x28\x14\xfd\xb1\x1a\x34\x18"
-			  "\xf5\x1e\x28\x69\x95\x6a\x5a\xba"
-			  "\x8e\xb2\x58\x1d\x28\x17\x13\x3d"
-			  "\x38\x7d\x14\x8d\xab\x5d\xf9\xe8"
-			  "\x3c\x0f\x2b\x0d\x2b\x08\xb4\x4b"
-			  "\x6b\x0d\xc8\xa7\x84\xc2\x3a\x1a"
-			  "\xb7\xbd\xda\x92\x29\xb8\x5b\x5a"
-			  "\x63\xa5\x99\x82\x09\x72\x8f\xc6"
-			  "\xa4\x62\x24\x69\x8c\x2d\x26\x00"
-			  "\x99\x83\x91\xd6\xc6\xcf\x57\x67"
-			  "\x38\xea\xf2\xfc\x29\xe0\x73\x39"
-			  "\xf9\x13\x94\x6d\xe2\x58\x28\x75"
-			  "\x3e\xae\x71\x90\x07\x70\x1c\x38"
-			  "\x5b\x4c\x1e\xb5\xa5\x3b\x20\xef"
-			  "\xb1\x4c\x3e\x1a\x72\x62\xbb\x22"
-			  "\x82\x09\xe3\x18\x3f\x4f\x48\xfc"
-			  "\xdd\xac\xfc\xb6\x09\xdb\xd2\x7b"
-			  "\xd6\xb7\x7e\x41\x2f\x14\xf5\x0e"
-			  "\xc3\xac\x4a\xed\xe7\x82\xef\x31"
-			  "\x1f\x1a\x51\x1e\x29\x60\xc8\x98"
-			  "\x93\x51\x1d\x3d\x62\x59\x83\x82"
-			  "\x0c\xf1\xd7\x8d\xac\x33\x44\x81"
-			  "\x3c\x59\xb7\xd4\x5b\x65\x82\xc4"
-			  "\xec\xdc\x24\xfd\x0e\x1a\x79\x94"
-			  "\x34\xb0\x62\xfa\x98\x49\x26\x1f"
-			  "\xf4\x9e\x40\x44\x5b\x1f\xf8\xbe"
-			  "\x36\xff\xc6\xc6\x9d\xf2\xd6\xcc"
-			  "\x63\x93\x29\xb9\x0b\x6d\xd7\x6c"
-			  "\xdb\xf6\x21\x80\xf7\x5a\x37\x15"
-			  "\x0c\xe3\x36\xc8\x74\x75\x20\x91"
-			  "\xdf\x52\x2d\x0c\xe7\x45\xff\x46"
-			  "\xb3\xf4\xec\xc2\xbd\xd3\x37\xb6"
-			  "\x26\xa2\x5d\x7d\x61\xbf\x10\x46"
-			  "\x57\x8d\x05\x96\x70\x0b\xd6\x41"
-			  "\x5c\xe9\xd3\x54\x81\x39\x3a\xdd"
-			  "\x5f\x92\x81\x6e\x35\x03\xd4\x72"
-			  "\x3d\x5a\xe7\xb9\x3b\x0c\x84\x23"
-			  "\x45\x5d\xec\x72\xc1\x52\xef\x2e"
-			  "\x81\x00\xd3\xfe\x4c\x3c\x05\x61"
-			  "\x80\x18\xc4\x6c\x03\xd3\xb7\xba"
-			  "\x11\xd7\xb8\x6e\xea\xe1\x80\x30",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec tf_lrw_dec_tv_template[] = {
-	/* Generated from AES-LRW test vectors */
-	/* same as enc vectors with input and result reversed */
-	{
-		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
-			  "\x4c\x26\x84\x14\xb5\x68\x01\x85"
-			  "\x25\x8e\x2a\x05\xe7\x3e\x9d\x03"
-			  "\xee\x5a\x83\x0c\xcc\x09\x4c\x87",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\xa1\x6c\x50\x69\x26\xa4\xef\x7b"
-			  "\x7c\xc6\x91\xeb\x72\xdd\x9b\xee",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x59\x70\x47\x14\xf5\x57\x47\x8c"
-			  "\xd7\x79\xe8\x0f\x54\x88\x79\x44"
-			  "\x0d\x48\xf0\xb7\xb1\x5a\x53\xea"
-			  "\x1c\xaa\x6b\x29\xc2\xca\xfb\xaf",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input	= "\xab\x72\x0a\xad\x3b\x0c\xf0\xc9"
-			  "\x42\x2f\xf1\xae\xf1\x3c\xb1\xbd",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xd8\x2a\x91\x34\xb2\x6a\x56\x50"
-			  "\x30\xfe\x69\xe2\x37\x7f\x98\x47"
-			  "\xcd\xf9\x0b\x16\x0c\x64\x8f\xb6"
-			  "\xb0\x0d\x0d\x1b\xae\x85\x87\x1f",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x85\xa7\x56\x67\x08\xfa\x42\xe1"
-			  "\x22\xe6\x82\xfc\xd9\xb4\xd7\xd4",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x0f\x6a\xef\xf8\xd3\xd2\xbb\x15"
-			  "\x25\x83\xf7\x3c\x1f\x01\x28\x74"
-			  "\xca\xc6\xbc\x35\x4d\x4a\x65\x54"
-			  "\x90\xae\x61\xcf\x7b\xae\xbd\xcc"
-			  "\xad\xe4\x94\xc5\x4a\x29\xae\x70",
-		.klen	= 40,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\xd2\xaf\x69\x35\x24\x1d\x0e\x1c"
-			  "\x84\x8b\x05\xe4\xa2\x2f\x16\xf5",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x8a\xd4\xee\x10\x2f\xbd\x81\xff"
-			  "\xf8\x86\xce\xac\x93\xc5\xad\xc6"
-			  "\xa0\x19\x07\xc0\x9d\xf7\xbb\xdd"
-			  "\x52\x13\xb2\xb7\xf0\xff\x11\xd8"
-			  "\xd6\x08\xd0\xcd\x2e\xb1\x17\x6f",
-		.klen	= 40,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x4a\x23\x56\xd7\xff\x90\xd0\x9a"
-			  "\x0d\x7c\x26\xfc\xf0\xf0\xf6\xe4",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\xaf\x26\x05\x9d\x5d\x0a\x58"
-			  "\xe2\xe7\xce\x8a\xb2\x56\x6d\x76",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xfb\x76\x15\xb2\x3d\x80\x89\x1d"
-			  "\xd4\x70\x98\x0b\xc7\x95\x84\xc8"
-			  "\xb2\xfb\x64\xce\x60\x97\x87\x8d"
-			  "\x17\xfc\xe4\x5a\x49\xe8\x30\xb7"
-			  "\x6e\x78\x17\xe7\x2d\x5e\x12\xd4"
-			  "\x60\x64\x04\x7a\xf1\x2f\x9e\x0c",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\xdf\xcf\xdc\xd2\xe1\xcf\x86\x75"
-			  "\x17\x66\x5e\x0c\x14\xa1\x3d\x40",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x38\xeb\xaf\x12\x43\x1a\x89"
+		.ctext	= "\x30\x38\xeb\xaf\x12\x43\x1a\x89"
 			  "\x62\xa2\x36\xe5\xcf\x77\x1e\xd9"
 			  "\x08\xc3\x0d\xdd\x95\xab\x19\x96"
 			  "\x27\x52\x41\xc3\xca\xfb\xf6\xee"
@@ -11084,79 +8348,14 @@ static const struct cipher_testvec tf_lrw_dec_tv_template[] = {
 			  "\x81\x00\xd3\xfe\x4c\x3c\x05\x61"
 			  "\x80\x18\xc4\x6c\x03\xd3\xb7\xba"
 			  "\x11\xd7\xb8\x6e\xea\xe1\x80\x30",
-		.ilen	= 512,
-		.result	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
-			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
-			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
-			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
-			  "\x8f\xcb\x8d\x6b\xe3\xa6\x29\x90"
-			  "\xfe\x2a\x62\x82\xae\x6d\x8b\xf6"
-			  "\xad\x1e\x9e\x20\x5f\x38\xbe\x04"
-			  "\xda\x10\x8e\xed\xa2\xa4\x87\xab"
-			  "\xda\x6b\xb4\x0c\x75\xba\xd3\x7c"
-			  "\xc9\xac\x42\x31\x95\x7c\xc9\x04"
-			  "\xeb\xd5\x6e\x32\x69\x8a\xdb\xa6"
-			  "\x15\xd7\x3f\x4f\x2f\x66\x69\x03"
-			  "\x9c\x1f\x54\x0f\xde\x1f\xf3\x65"
-			  "\x4c\x96\x12\xed\x7c\x92\x03\x01"
-			  "\x6f\xbc\x35\x93\xac\xf1\x27\xf1"
-			  "\xb4\x96\x82\x5a\x5f\xb0\xa0\x50"
-			  "\x89\xa4\x8e\x66\x44\x85\xcc\xfd"
-			  "\x33\x14\x70\xe3\x96\xb2\xc3\xd3"
-			  "\xbb\x54\x5a\x1a\xf9\x74\xa2\xc5"
-			  "\x2d\x64\x75\xdd\xb4\x54\xe6\x74"
-			  "\x8c\xd3\x9d\x9e\x86\xab\x51\x53"
-			  "\xb7\x93\x3e\x6f\xd0\x4e\x2c\x40"
-			  "\xf6\xa8\x2e\x3e\x9d\xf4\x66\xa5"
-			  "\x76\x12\x73\x44\x1a\x56\xd7\x72"
-			  "\x88\xcd\x21\x8c\x4c\x0f\xfe\xda"
-			  "\x95\xe0\x3a\xa6\xa5\x84\x46\xcd"
-			  "\xd5\x3e\x9d\x3a\xe2\x67\xe6\x60"
-			  "\x1a\xe2\x70\x85\x58\xc2\x1b\x09"
-			  "\xe1\xd7\x2c\xca\xad\xa8\x8f\xf9"
-			  "\xac\xb3\x0e\xdb\xca\x2e\xe2\xb8"
-			  "\x51\x71\xd9\x3c\x6c\xf1\x56\xf8"
-			  "\xea\x9c\xf1\xfb\x0c\xe6\xb7\x10"
-			  "\x1c\xf8\xa9\x7c\xe8\x53\x35\xc1"
-			  "\x90\x3e\x76\x4a\x74\xa4\x21\x2c"
-			  "\xf6\x2c\x4e\x0f\x94\x3a\x88\x2e"
-			  "\x41\x09\x6a\x33\x7d\xf6\xdd\x3f"
-			  "\x8d\x23\x31\x74\x84\xeb\x88\x6e"
-			  "\xcc\xb9\xbc\x22\x83\x19\x07\x22"
-			  "\xa5\x2d\xdf\xa5\xf3\x80\x85\x78"
-			  "\x84\x39\x6a\x6d\x6a\x99\x4f\xa5"
-			  "\x15\xfe\x46\xb0\xe4\x6c\xa5\x41"
-			  "\x3c\xce\x8f\x42\x60\x71\xa7\x75"
-			  "\x08\x40\x65\x8a\x82\xbf\xf5\x43"
-			  "\x71\x96\xa9\x4d\x44\x8a\x20\xbe"
-			  "\xfa\x4d\xbb\xc0\x7d\x31\x96\x65"
-			  "\xe7\x75\xe5\x3e\xfd\x92\x3b\xc9"
-			  "\x55\xbb\x16\x7e\xf7\xc2\x8c\xa4"
-			  "\x40\x1d\xe5\xef\x0e\xdf\xe4\x9a"
-			  "\x62\x73\x65\xfd\x46\x63\x25\x3d"
-			  "\x2b\xaf\xe5\x64\xfe\xa5\x5c\xcf"
-			  "\x24\xf3\xb4\xac\x64\xba\xdf\x4b"
-			  "\xc6\x96\x7d\x81\x2d\x8d\x97\xf7"
-			  "\xc5\x68\x77\x84\x32\x2b\xcc\x85"
-			  "\x74\x96\xf0\x12\x77\x61\xb9\xeb"
-			  "\x71\xaa\x82\xcb\x1c\xdb\x89\xc8"
-			  "\xc6\xb5\xe3\x5c\x7d\x39\x07\x24"
-			  "\xda\x39\x87\x45\xc0\x2b\xbb\x01"
-			  "\xac\xbc\x2a\x5c\x7f\xfc\xe8\xce"
-			  "\x6d\x9c\x6f\xed\xd3\xc1\xa1\xd6"
-			  "\xc5\x55\xa9\x66\x2f\xe1\xc8\x32"
-			  "\xa6\x5d\xa4\x3a\x98\x73\xe8\x45"
-			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
-			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
-			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec tf_xts_enc_tv_template[] = {
+static const struct cipher_testvec tf_xts_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 {
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -11166,16 +8365,15 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 32,
-		.result	= "\x4b\xc9\x44\x4a\x11\xa3\xef\xac"
+		.ctext	= "\x4b\xc9\x44\x4a\x11\xa3\xef\xac"
 			  "\x30\x74\xe4\x44\x52\x77\x97\x43"
 			  "\xa7\x60\xb2\x45\x2e\xf9\x00\x90"
 			  "\x9f\xaa\xfd\x89\x6e\x9d\x4a\xe0",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
 			  "\x11\x11\x11\x11\x11\x11\x11\x11"
@@ -11184,16 +8382,15 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\x57\x0e\x8f\xe5\x2a\x35\x61\x4f"
+		.ctext	= "\x57\x0e\x8f\xe5\x2a\x35\x61\x4f"
 			  "\x32\xd3\xbd\x36\x05\x15\x44\x2c"
 			  "\x58\x06\xf7\xf8\x00\xa8\xb6\xd5"
 			  "\xc6\x28\x92\xdb\xd8\x34\xa2\xe9",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
 			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
@@ -11202,16 +8399,15 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\x96\x45\x8f\x8d\x7a\x75\xb1\xde"
+		.ctext	= "\x96\x45\x8f\x8d\x7a\x75\xb1\xde"
 			  "\x40\x0c\x89\x56\xf6\x4d\xa7\x07"
 			  "\x38\xbb\x5b\xe9\xcd\x84\xae\xb2"
 			  "\x7b\x6a\x62\xf4\x8c\xb5\x37\xea",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -11220,7 +8416,7 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -11284,8 +8480,7 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\xa9\x78\xae\x1e\xea\xa2\x44\x4c"
+		.ctext	= "\xa9\x78\xae\x1e\xea\xa2\x44\x4c"
 			  "\xa2\x7a\x64\x1f\xaf\x46\xc1\xe0"
 			  "\x6c\xb2\xf3\x92\x9a\xd6\x7d\x58"
 			  "\xb8\x2d\xb9\x5d\x58\x07\x66\x50"
@@ -11349,7 +8544,7 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 			  "\x43\xc4\x46\x24\x22\x4f\x8f\x7e"
 			  "\xe5\xf4\x6d\x1e\x0e\x18\x7a\xbb"
 			  "\xa6\x8f\xfb\x49\x49\xd8\x7e\x5a",
-		.rlen	= 512,
+		.len	= 512,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -11362,7 +8557,7 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 		.klen	= 64,
 		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -11426,8 +8621,7 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\xd7\x4b\x93\x7d\x13\xa2\xa2\xe1"
+		.ctext	= "\xd7\x4b\x93\x7d\x13\xa2\xa2\xe1"
 			  "\x35\x39\x71\x88\x76\x1e\xc9\xea"
 			  "\x86\xad\xf3\x14\x48\x3d\x5e\xe9"
 			  "\xe9\x2d\xb2\x56\x59\x35\x9d\xec"
@@ -11491,350 +8685,7 @@ static const struct cipher_testvec tf_xts_enc_tv_template[] = {
 			  "\xf3\xea\x67\x52\x78\xc2\xce\x70"
 			  "\xa4\x05\x0b\xb2\xb3\xa8\x30\x97"
 			  "\x37\x30\xe1\x91\x8d\xb3\x2a\xff",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec tf_xts_dec_tv_template[] = {
-	/* Generated from AES-XTS test vectors */
-	/* same as enc vectors with input and result reversed */
-	{
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x4b\xc9\x44\x4a\x11\xa3\xef\xac"
-			  "\x30\x74\xe4\x44\x52\x77\x97\x43"
-			  "\xa7\x60\xb2\x45\x2e\xf9\x00\x90"
-			  "\x9f\xaa\xfd\x89\x6e\x9d\x4a\xe0",
-		.ilen	= 32,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 32,
-	}, {
-		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 32,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x57\x0e\x8f\xe5\x2a\x35\x61\x4f"
-			  "\x32\xd3\xbd\x36\x05\x15\x44\x2c"
-			  "\x58\x06\xf7\xf8\x00\xa8\xb6\xd5"
-			  "\xc6\x28\x92\xdb\xd8\x34\xa2\xe9",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
-			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 32,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x96\x45\x8f\x8d\x7a\x75\xb1\xde"
-			  "\x40\x0c\x89\x56\xf6\x4d\xa7\x07"
-			  "\x38\xbb\x5b\xe9\xcd\x84\xae\xb2"
-			  "\x7b\x6a\x62\xf4\x8c\xb5\x37\xea",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xa9\x78\xae\x1e\xea\xa2\x44\x4c"
-			  "\xa2\x7a\x64\x1f\xaf\x46\xc1\xe0"
-			  "\x6c\xb2\xf3\x92\x9a\xd6\x7d\x58"
-			  "\xb8\x2d\xb9\x5d\x58\x07\x66\x50"
-			  "\xea\x35\x35\x8c\xb2\x46\x61\x06"
-			  "\x5d\x65\xfc\x57\x8f\x69\x74\xab"
-			  "\x8a\x06\x69\xb5\x6c\xda\x66\xc7"
-			  "\x52\x90\xbb\x8e\x6d\x8b\xb5\xa2"
-			  "\x78\x1d\xc2\xa9\xc2\x73\x00\xc3"
-			  "\x32\x36\x7c\x97\x6b\x4e\x8a\x50"
-			  "\xe4\x91\x83\x96\x8f\xf4\x94\x1a"
-			  "\xa6\x27\xe1\x33\xcb\x91\xc6\x5f"
-			  "\x94\x75\xbc\xd7\x3e\x3e\x6f\x9e"
-			  "\xa9\x31\x80\x5e\xe5\xdb\xc8\x53"
-			  "\x01\x73\x68\x32\x25\x19\xfa\xfb"
-			  "\xe4\xcf\xb9\x3e\xa2\xa0\x8f\x31"
-			  "\xbf\x54\x06\x93\xa8\xb1\x0f\xb6"
-			  "\x7c\x3c\xde\x6f\x0f\xfb\x0c\x11"
-			  "\x39\x80\x39\x09\x97\x65\xf2\x83"
-			  "\xae\xe6\xa1\x6f\x47\xb8\x49\xde"
-			  "\x99\x36\x20\x7d\x97\x3b\xec\xfa"
-			  "\xb4\x33\x6e\x7a\xc7\x46\x84\x49"
-			  "\x91\xcd\xe1\x57\x0d\xed\x40\x08"
-			  "\x13\xf1\x4e\x3e\xa4\xa4\x5c\xe6"
-			  "\xd2\x0c\x20\x8f\x3e\xdf\x3f\x47"
-			  "\x9a\x2f\xde\x6d\x66\xc9\x99\x4a"
-			  "\x2d\x9e\x9d\x4b\x1a\x27\xa2\x12"
-			  "\x99\xf0\xf8\xb1\xb6\xf6\x57\xc3"
-			  "\xca\x1c\xa3\x8e\xed\x39\x28\xb5"
-			  "\x10\x1b\x4b\x08\x42\x00\x4a\xd3"
-			  "\xad\x5a\xc6\x8e\xc8\xbb\x95\xc4"
-			  "\x4b\xaa\xfe\xd5\x42\xa8\xa3\x6d"
-			  "\x3c\xf3\x34\x91\x2d\xb4\xdd\x20"
-			  "\x0c\x90\x6d\xa3\x9b\x66\x9d\x24"
-			  "\x02\xa6\xa9\x3f\x3f\x58\x5d\x47"
-			  "\x24\x65\x63\x7e\xbd\x8c\xe6\x52"
-			  "\x7d\xef\x33\x53\x63\xec\xaa\x0b"
-			  "\x64\x15\xa9\xa6\x1f\x10\x00\x38"
-			  "\x35\xa8\xe7\xbe\x23\x70\x22\xe0"
-			  "\xd3\xb9\xe6\xfd\xe6\xaa\x03\x50"
-			  "\xf3\x3c\x27\x36\x8b\xcc\xfe\x9c"
-			  "\x9c\xa3\xb3\xe7\x68\x9b\xa2\x71"
-			  "\xe0\x07\xd9\x1f\x68\x1f\xac\x5e"
-			  "\x7a\x74\x85\xa9\x6a\x90\xab\x2c"
-			  "\x38\x51\xbc\x1f\x43\x4a\x56\x1c"
-			  "\xf8\x47\x03\x4e\x67\xa8\x1f\x99"
-			  "\x04\x39\x73\x32\xb2\x86\x79\xe7"
-			  "\x14\x28\x70\xb8\xe2\x7d\x69\x85"
-			  "\xb6\x0f\xc5\xd0\xd0\x01\x5c\xe6"
-			  "\x09\x0f\x75\xf7\xb6\x81\xd2\x11"
-			  "\x20\x9c\xa1\xee\x11\x44\x79\xd0"
-			  "\xb2\x34\x77\xda\x10\x9a\x6f\x6f"
-			  "\xef\x7c\xd9\xdc\x35\xb7\x61\xdd"
-			  "\xf1\xa4\xc6\x1c\xbf\x05\x22\xac"
-			  "\xfe\x2f\x85\x00\x44\xdf\x33\x16"
-			  "\x35\xb6\xa3\xd3\x70\xdf\x69\x35"
-			  "\x6a\xc7\xb4\x99\x45\x27\xc8\x8e"
-			  "\x5a\x14\x30\xd0\x55\x3e\x4f\x64"
-			  "\x0d\x38\xe3\xdf\x8b\xa8\x93\x26"
-			  "\x75\xae\xf6\xb5\x23\x0b\x17\x31"
-			  "\xbf\x27\xb8\xb5\x94\x31\xa7\x8f"
-			  "\x43\xc4\x46\x24\x22\x4f\x8f\x7e"
-			  "\xe5\xf4\x6d\x1e\x0e\x18\x7a\xbb"
-			  "\xa6\x8f\xfb\x49\x49\xd8\x7e\x5a",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x62\x49\x77\x57\x24\x70\x93\x69"
-			  "\x99\x59\x57\x49\x66\x96\x76\x27"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95"
-			  "\x02\x88\x41\x97\x16\x93\x99\x37"
-			  "\x51\x05\x82\x09\x74\x94\x45\x92",
-		.klen	= 64,
-		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xd7\x4b\x93\x7d\x13\xa2\xa2\xe1"
-			  "\x35\x39\x71\x88\x76\x1e\xc9\xea"
-			  "\x86\xad\xf3\x14\x48\x3d\x5e\xe9"
-			  "\xe9\x2d\xb2\x56\x59\x35\x9d\xec"
-			  "\x84\xfa\x7e\x9d\x6d\x33\x36\x8f"
-			  "\xce\xf4\xa9\x21\x0b\x5f\x96\xec"
-			  "\xcb\xf9\x57\x68\x33\x88\x39\xbf"
-			  "\x2f\xbb\x59\x03\xbd\x66\x8b\x11"
-			  "\x11\x65\x51\x2e\xb8\x67\x05\xd1"
-			  "\x27\x11\x5c\xd4\xcc\x97\xc2\xb3"
-			  "\xa9\x55\xaf\x07\x56\xd1\xdc\xf5"
-			  "\x85\xdc\x46\xe6\xf0\x24\xeb\x93"
-			  "\x4d\xf0\x9b\xf5\x73\x1c\xda\x03"
-			  "\x22\xc8\x3a\x4f\xb4\x19\x91\x09"
-			  "\x54\x0b\xf6\xfe\x17\x3d\x1a\x53"
-			  "\x72\x60\x79\xcb\x0e\x32\x8a\x77"
-			  "\xd5\xed\xdb\x33\xd7\x62\x16\x69"
-			  "\x63\xe0\xab\xb5\xf6\x9c\x5f\x3d"
-			  "\x69\x35\x61\x86\xf8\x86\xb9\x89"
-			  "\x6e\x59\x35\xac\xf6\x6b\x33\xa0"
-			  "\xea\xef\x96\x62\xd8\xa9\xcf\x56"
-			  "\xbf\xdb\x8a\xfd\xa1\x82\x77\x73"
-			  "\x3d\x94\x4a\x49\x42\x6d\x08\x60"
-			  "\xa1\xea\xab\xb6\x88\x13\x94\xb8"
-			  "\x51\x98\xdb\x35\x85\xdf\xf6\xb9"
-			  "\x8f\xcd\xdf\x80\xd3\x40\x2d\x72"
-			  "\xb8\xb2\x6c\x02\x43\x35\x22\x2a"
-			  "\x31\xed\xcd\x16\x19\xdf\x62\x0f"
-			  "\x29\xcf\x87\x04\xec\x02\x4f\xe4"
-			  "\xa2\xed\x73\xc6\x69\xd3\x7e\x89"
-			  "\x0b\x76\x10\x7c\xd6\xf9\x6a\x25"
-			  "\xed\xcc\x60\x5d\x61\x20\xc1\x97"
-			  "\x56\x91\x57\x28\xbe\x71\x0d\xcd"
-			  "\xde\xc4\x9e\x55\x91\xbe\xd1\x28"
-			  "\x9b\x90\xeb\x73\xf3\x68\x51\xc6"
-			  "\xdf\x82\xcc\xd8\x1f\xce\x5b\x27"
-			  "\xc0\x60\x5e\x33\xd6\xa7\x20\xea"
-			  "\xb2\x54\xc7\x5d\x6a\x3b\x67\x47"
-			  "\xcf\xa0\xe3\xab\x86\xaf\xc1\x42"
-			  "\xe6\xb0\x23\x4a\xaf\x53\xdf\xa0"
-			  "\xad\x12\x32\x31\x03\xf7\x21\xbe"
-			  "\x2d\xd5\x82\x42\xb6\x4a\x3d\xcd"
-			  "\xd8\x81\x77\xa9\x49\x98\x6c\x09"
-			  "\xc5\xa3\x61\x12\x62\x85\x6b\xcd"
-			  "\xb3\xf4\x20\x0c\x41\xc4\x05\x37"
-			  "\x46\x5f\xeb\x71\x8b\xf1\xaf\x6e"
-			  "\xba\xf3\x50\x2e\xfe\xa8\x37\xeb"
-			  "\xe8\x8c\x4f\xa4\x0c\xf1\x31\xc8"
-			  "\x6e\x71\x4f\xa5\xd7\x97\x73\xe0"
-			  "\x93\x4a\x2f\xda\x7b\xe0\x20\x54"
-			  "\x1f\x8d\x85\x79\x0b\x7b\x5e\x75"
-			  "\xb9\x07\x67\xcc\xc8\xe7\x21\x15"
-			  "\xa7\xc8\x98\xff\x4b\x80\x1c\x12"
-			  "\xa8\x54\xe1\x38\x52\xe6\x74\x81"
-			  "\x97\x47\xa1\x41\x0e\xc0\x50\xe3"
-			  "\x55\x0e\xc3\xa7\x70\x77\xce\x07"
-			  "\xed\x8c\x88\xe6\xa1\x5b\x14\xec"
-			  "\xe6\xde\x06\x6d\x74\xc5\xd9\xfa"
-			  "\xe5\x2f\x5a\xff\xc8\x05\xee\x27"
-			  "\x35\x61\xbf\x0b\x19\x78\x9b\xd2"
-			  "\x04\xc7\x05\xb1\x79\xb4\xff\x5f"
-			  "\xf3\xea\x67\x52\x78\xc2\xce\x70"
-			  "\xa4\x05\x0b\xb2\xb3\xa8\x30\x97"
-			  "\x37\x30\xe1\x91\x8d\xb3\x2a\xff",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
@@ -11845,51 +8696,47 @@ static const struct cipher_testvec tf_xts_dec_tv_template[] = {
  * Serpent test vectors.  These are backwards because Serpent writes
  * octet sequences in right-to-left mode.
  */
-static const struct cipher_testvec serpent_enc_tv_template[] = {
+static const struct cipher_testvec serpent_tv_template[] = {
 	{
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ilen	= 16,
-		.result	= "\x12\x07\xfc\xce\x9b\xd0\xd6\x47"
+		.ctext	= "\x12\x07\xfc\xce\x9b\xd0\xd6\x47"
 			  "\x6a\xe9\x8f\xbe\xd1\x43\xa0\xe2",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
 		.klen	= 16,
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ilen	= 16,
-		.result	= "\x4c\x7d\x8a\x32\x80\x72\xa2\x2c"
+		.ctext	= "\x4c\x7d\x8a\x32\x80\x72\xa2\x2c"
 			  "\x82\x3e\x4a\x1f\x3a\xcd\xa1\x6d",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
 		.klen	= 32,
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ilen	= 16,
-		.result	= "\xde\x26\x9f\xf8\x33\xe4\x32\xb8"
+		.ctext	= "\xde\x26\x9f\xf8\x33\xe4\x32\xb8"
 			  "\x5b\x2e\x88\xd2\x70\x1c\xe7\x5c",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80",
 		.klen	= 16,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\xdd\xd2\x6b\x98\xa5\xff\xd8\x2c"
+		.ptext	= zeroed_string,
+		.ctext	= "\xdd\xd2\x6b\x98\xa5\xff\xd8\x2c"
 			  "\x05\x34\x5a\x9d\xad\xbf\xaf\x49",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
 			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
 			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
 		.klen	= 32,
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -11951,8 +8798,7 @@ static const struct cipher_testvec serpent_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\xFB\xB0\x5D\xDE\xC0\xFE\xFC\xEB"
+		.ctext	= "\xFB\xB0\x5D\xDE\xC0\xFE\xFC\xEB"
 			  "\xB1\x80\x10\x43\xDE\x62\x70\xBD"
 			  "\xFA\x8A\x93\xEA\x6B\xF7\xC5\xD7"
 			  "\x0C\xD1\xBB\x29\x25\x14\x4C\x22"
@@ -12014,281 +8860,93 @@ static const struct cipher_testvec serpent_enc_tv_template[] = {
 			  "\x34\xC1\xC9\xF2\x28\x4A\xCD\x02"
 			  "\x75\x55\x9B\xFF\x36\x73\xAB\x7C"
 			  "\xF4\x46\x2E\xEB\xAC\xF3\xD2\xB7",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec tnepres_enc_tv_template[] = {
+static const struct cipher_testvec tnepres_tv_template[] = {
+	{ /* KeySize=0 */
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ctext	= "\x41\xcc\x6b\x31\x59\x31\x45\x97"
+			  "\x6d\x6f\xbb\x38\x4b\x37\x21\x28",
+		.len	= 16,
+	},
 	{ /* KeySize=128, PT=0, I=1 */
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.key    = "\x80\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen   = 16,
-		.ilen	= 16,
-		.result	= "\x49\xaf\xbf\xad\x9d\x5a\x34\x05"
+		.ctext	= "\x49\xaf\xbf\xad\x9d\x5a\x34\x05"
 			  "\x2c\xd8\xff\xa5\x98\x6b\xd2\xdd",
-		.rlen	= 16,
+		.len	= 16,
+	}, { /* KeySize=128 */
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.klen	= 16,
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ctext	= "\xea\xf4\xd7\xfc\xd8\x01\x34\x47"
+			  "\x81\x45\x0b\xfa\x0c\xd6\xad\x6e",
+		.len	= 16,
+	}, { /* KeySize=128, I=121 */
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80",
+		.klen	= 16,
+		.ptext	= zeroed_string,
+		.ctext	= "\x3d\xda\xbf\xc0\x06\xda\xab\x06"
+			  "\x46\x2a\xf4\xef\x81\x54\x4e\x26",
+		.len	= 16,
 	}, { /* KeySize=192, PT=0, I=1 */
 		.key	= "\x80\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 24,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 16,
-		.result	= "\xe7\x8e\x54\x02\xc7\x19\x55\x68"
+		.ctext	= "\xe7\x8e\x54\x02\xc7\x19\x55\x68"
 			  "\xac\x36\x78\xf7\xa3\xf6\x0c\x66",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* KeySize=256, PT=0, I=1 */
 		.key	= "\x80\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 32,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 16,
-		.result	= "\xab\xed\x96\xe7\x66\xbf\x28\xcb"
+		.ctext	= "\xab\xed\x96\xe7\x66\xbf\x28\xcb"
 			  "\xc0\xeb\xd2\x1a\x82\xef\x08\x19",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* KeySize=256, I=257 */
 		.key	= "\x1f\x1e\x1d\x1c\x1b\x1a\x19\x18"
 			  "\x17\x16\x15\x14\x13\x12\x11\x10"
 			  "\x0f\x0e\x0d\x0c\x0b\x0a\x09\x08"
 			  "\x07\x06\x05\x04\x03\x02\x01\x00",
 		.klen	= 32,
-		.input	= "\x0f\x0e\x0d\x0c\x0b\x0a\x09\x08"
+		.ptext	= "\x0f\x0e\x0d\x0c\x0b\x0a\x09\x08"
 			  "\x07\x06\x05\x04\x03\x02\x01\x00",
-		.ilen	= 16,
-		.result	= "\x5c\xe7\x1c\x70\xd2\x88\x2e\x5b"
+		.ctext	= "\x5c\xe7\x1c\x70\xd2\x88\x2e\x5b"
 			  "\xb8\x32\xe4\x33\xf8\x9f\x26\xde",
-		.rlen	= 16,
-	},
-};
-
-
-static const struct cipher_testvec serpent_dec_tv_template[] = {
-	{
-		.input	= "\x12\x07\xfc\xce\x9b\xd0\xd6\x47"
-			  "\x6a\xe9\x8f\xbe\xd1\x43\xa0\xe2",
-		.ilen	= 16,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.rlen	= 16,
-	}, {
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.klen	= 16,
-		.input	= "\x4c\x7d\x8a\x32\x80\x72\xa2\x2c"
-			  "\x82\x3e\x4a\x1f\x3a\xcd\xa1\x6d",
-		.ilen	= 16,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.rlen	= 16,
-	}, {
+		.len	= 16,
+	}, { /* KeySize=256 */
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
 		.klen	= 32,
-		.input	= "\xde\x26\x9f\xf8\x33\xe4\x32\xb8"
-			  "\x5b\x2e\x88\xd2\x70\x1c\xe7\x5c",
-		.ilen	= 16,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.rlen	= 16,
-	}, {
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80",
-		.klen	= 16,
-		.input	= "\xdd\xd2\x6b\x98\xa5\xff\xd8\x2c"
-			  "\x05\x34\x5a\x9d\xad\xbf\xaf\x49",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.input	= "\xFB\xB0\x5D\xDE\xC0\xFE\xFC\xEB"
-			  "\xB1\x80\x10\x43\xDE\x62\x70\xBD"
-			  "\xFA\x8A\x93\xEA\x6B\xF7\xC5\xD7"
-			  "\x0C\xD1\xBB\x29\x25\x14\x4C\x22"
-			  "\x77\xA6\x38\x00\xDB\xB9\xE2\x07"
-			  "\xD1\xAC\x82\xBA\xEA\x67\xAA\x39"
-			  "\x99\x34\x89\x5B\x54\xE9\x12\x13"
-			  "\x3B\x04\xE5\x12\x42\xC5\x79\xAB"
-			  "\x0D\xC7\x3C\x58\x2D\xA3\x98\xF6"
-			  "\xE4\x61\x9E\x17\x0B\xCE\xE8\xAA"
-			  "\xB5\x6C\x1A\x3A\x67\x52\x81\x6A"
-			  "\x04\xFF\x8A\x1B\x96\xFE\xE6\x87"
-			  "\x3C\xD4\x39\x7D\x36\x9B\x03\xD5"
-			  "\xB6\xA0\x75\x3C\x83\xE6\x1C\x73"
-			  "\x9D\x74\x2B\x77\x53\x2D\xE5\xBD"
-			  "\x69\xDA\x7A\x01\xF5\x6A\x70\x39"
-			  "\x30\xD4\x2C\xF2\x8E\x06\x4B\x39"
-			  "\xB3\x12\x1D\xB3\x17\x46\xE6\xD6"
-			  "\xB6\x31\x36\x34\x38\x3C\x1D\x69"
-			  "\x9F\x47\x28\x9A\x1D\x96\x70\x54"
-			  "\x8E\x88\xCB\xE0\xF5\x6A\xAE\x0A"
-			  "\x3C\xD5\x93\x1C\x21\xC9\x14\x3A"
-			  "\x23\x9C\x9B\x79\xC7\x75\xC8\x39"
-			  "\xA6\xAC\x65\x9A\x99\x37\xAF\x6D"
-			  "\xBD\xB5\x32\xFD\xD8\x9C\x95\x7B"
-			  "\xC6\x6A\x80\x64\xEA\xEF\x6D\x3F"
-			  "\xA9\xFE\x5B\x16\xA3\xCF\x32\xC8"
-			  "\xEF\x50\x22\x20\x93\x30\xBE\xE2"
-			  "\x38\x05\x65\xAF\xBA\xB6\xE4\x72"
-			  "\xA9\xEE\x05\x42\x88\xBD\x9D\x49"
-			  "\xAD\x93\xCA\x4D\x45\x11\x43\x4D"
-			  "\xB8\xF5\x74\x2B\x48\xE7\x21\xE4"
-			  "\x4E\x3A\x4C\xDE\x65\x7A\x5A\xAD"
-			  "\x86\xE6\x23\xEC\x6B\xA7\x17\xE6"
-			  "\xF6\xA1\xAC\x29\xAE\xF9\x9B\x69"
-			  "\x73\x65\x65\x51\xD6\x0B\x4E\x8C"
-			  "\x17\x15\x9D\xB0\xCF\xB2\x42\x2B"
-			  "\x51\xC3\x03\xE8\xB7\x7D\x2D\x39"
-			  "\xE8\x10\x93\x16\xC8\x68\x4C\x60"
-			  "\x87\x70\x14\xD0\x01\x57\xCB\x42"
-			  "\x13\x59\xB1\x7F\x12\x4F\xBB\xC7"
-			  "\xBD\x2B\xD4\xA9\x12\x26\x4F\xDE"
-			  "\xFD\x72\xEC\xD7\x6F\x97\x14\x90"
-			  "\x0E\x37\x13\xE6\x67\x1D\xE5\xFE"
-			  "\x9E\x18\x3C\x8F\x3A\x3F\x59\x9B"
-			  "\x71\x80\x05\x35\x3F\x40\x0B\x21"
-			  "\x76\xE5\xEF\x42\x6C\xDB\x31\x05"
-			  "\x5F\x05\xCF\x14\xE3\xF0\x61\xA2"
-			  "\x49\x03\x5E\x77\x2E\x20\xBA\xA1"
-			  "\xAF\x46\x51\xC0\x2B\xC4\x64\x1E"
-			  "\x65\xCC\x51\x58\x0A\xDF\xF0\x5F"
-			  "\x75\x9F\x48\xCD\x81\xEC\xC3\xF6"
-			  "\xED\xC9\x4B\x7B\x4E\x26\x23\xE1"
-			  "\xBB\xE9\x83\x0B\xCF\xE4\xDE\x00"
-			  "\x48\xFF\xBF\x6C\xB4\x72\x16\xEF"
-			  "\xC7\x46\xEE\x48\x8C\xB8\xAF\x45"
-			  "\x91\x76\xE7\x6E\x65\x3D\x15\x86"
-			  "\x10\xF8\xDB\x66\x97\x7C\x43\x4D"
-			  "\x79\x12\x4E\xCE\x06\xD1\xD1\x6A"
-			  "\x34\xC1\xC9\xF2\x28\x4A\xCD\x02"
-			  "\x75\x55\x9B\xFF\x36\x73\xAB\x7C"
-			  "\xF4\x46\x2E\xEB\xAC\xF3\xD2\xB7",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec tnepres_dec_tv_template[] = {
-	{
-		.input	= "\x41\xcc\x6b\x31\x59\x31\x45\x97"
-			  "\x6d\x6f\xbb\x38\x4b\x37\x21\x28",
-		.ilen	= 16,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.rlen	= 16,
-	}, {
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.klen	= 16,
-		.input	= "\xea\xf4\xd7\xfc\xd8\x01\x34\x47"
-			  "\x81\x45\x0b\xfa\x0c\xd6\xad\x6e",
-		.ilen	= 16,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.rlen	= 16,
-	}, {
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.klen	= 32,
-		.input	= "\x64\xa9\x1a\x37\xed\x9f\xe7\x49"
+		.ctext	= "\x64\xa9\x1a\x37\xed\x9f\xe7\x49"
 			  "\xa8\x4e\x76\xd6\xf5\x0d\x78\xee",
-		.ilen	= 16,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.rlen	= 16,
-	}, { /* KeySize=128, I=121 */
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80",
-		.klen	= 16,
-		.input	= "\x3d\xda\xbf\xc0\x06\xda\xab\x06"
-			  "\x46\x2a\xf4\xef\x81\x54\x4e\x26",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	},
+		.len	= 16,
+	}
 };
 
-static const struct cipher_testvec serpent_cbc_enc_tv_template[] = {
+static const struct cipher_testvec serpent_cbc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -12297,7 +8955,7 @@ static const struct cipher_testvec serpent_cbc_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -12359,8 +9017,7 @@ static const struct cipher_testvec serpent_cbc_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\x80\xCF\x11\x41\x1A\xB9\x4B\x9C"
+		.ctext	= "\x80\xCF\x11\x41\x1A\xB9\x4B\x9C"
 			  "\xFF\xB7\x6C\xEA\xF0\xAF\x77\x6E"
 			  "\x71\x75\x95\x9D\x4E\x1C\xCF\xAD"
 			  "\x81\x34\xE9\x8F\xAE\x5A\x91\x1C"
@@ -12422,155 +9079,14 @@ static const struct cipher_testvec serpent_cbc_enc_tv_template[] = {
 			  "\x02\xC4\xAF\xFA\xAD\x31\xF4\xBF"
 			  "\xFC\x66\xAA\x37\xF2\x37\x39\x6B"
 			  "\xBC\x08\x3A\xA2\x29\xB3\xDF\xD1",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec serpent_cbc_dec_tv_template[] = {
-	{ /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x80\xCF\x11\x41\x1A\xB9\x4B\x9C"
-			  "\xFF\xB7\x6C\xEA\xF0\xAF\x77\x6E"
-			  "\x71\x75\x95\x9D\x4E\x1C\xCF\xAD"
-			  "\x81\x34\xE9\x8F\xAE\x5A\x91\x1C"
-			  "\x38\x63\x35\x7E\x79\x18\x0A\xE8"
-			  "\x67\x06\x76\xD5\xFF\x22\x2F\xDA"
-			  "\xB6\x2D\x57\x13\xB6\x3C\xBC\x97"
-			  "\xFE\x53\x75\x35\x97\x7F\x51\xEA"
-			  "\xDF\x5D\xE8\x9D\xCC\xD9\xAE\xE7"
-			  "\x62\x67\xFF\x04\xC2\x18\x22\x5F"
-			  "\x2E\x06\xC1\xE2\x26\xCD\xC6\x1E"
-			  "\xE5\x2C\x4E\x87\x23\xDD\xF0\x41"
-			  "\x08\xA5\xB4\x3E\x07\x1E\x0B\xBB"
-			  "\x72\x84\xF8\x0A\x3F\x38\x5E\x91"
-			  "\x15\x26\xE1\xDB\xA4\x3D\x74\xD2"
-			  "\x41\x1E\x3F\xA9\xC6\x7D\x2A\xAB"
-			  "\x27\xDF\x89\x1D\x86\x3E\xF7\x5A"
-			  "\xF6\xE3\x0F\xC7\x6B\x4C\x96\x7C"
-			  "\x2D\x12\xA5\x05\x92\xCB\xD7\x4A"
-			  "\x4D\x1E\x88\x21\xE1\x63\xB4\xFC"
-			  "\x4A\xF2\xCD\x35\xB9\xD7\x70\x97"
-			  "\x5A\x5E\x7E\x96\x52\x20\xDC\x25"
-			  "\xE9\x6B\x36\xB4\xE0\x98\x85\x2C"
-			  "\x3C\xD2\xF7\x78\x8A\x73\x26\x9B"
-			  "\xAF\x0B\x11\xE8\x4D\x67\x23\xE9"
-			  "\x77\xDF\x58\xF6\x6F\x9E\xA4\xC5"
-			  "\x10\xA1\x82\x0E\x80\xA0\x8F\x4B"
-			  "\xA1\xC0\x12\x54\x4E\xC9\x20\x92"
-			  "\x11\x00\x10\x4E\xB3\x7C\xCA\x63"
-			  "\xE5\x3F\xD3\x41\x37\xCD\x74\xB7"
-			  "\xA5\x7C\x61\xB8\x0B\x7A\x7F\x4D"
-			  "\xFE\x96\x7D\x1B\xBE\x60\x37\xB7"
-			  "\x81\x92\x66\x67\x15\x1E\x39\x98"
-			  "\x52\xC0\xF4\x69\xC0\x99\x4F\x5A"
-			  "\x2E\x32\xAD\x7C\x8B\xE9\xAD\x05"
-			  "\x55\xF9\x0A\x1F\x97\x5C\xFA\x2B"
-			  "\xF4\x99\x76\x3A\x6E\x4D\xE1\x4C"
-			  "\x14\x4E\x6F\x87\xEE\x1A\x85\xA3"
-			  "\x96\xC6\x66\x49\xDA\x0D\x71\xAC"
-			  "\x04\x05\x46\xD3\x90\x0F\x64\x64"
-			  "\x01\x66\x2C\x62\x5D\x34\xD1\xCB"
-			  "\x3A\x24\xCE\x95\xEF\xAE\x2C\x97"
-			  "\x0E\x0C\x1D\x36\x49\xEB\xE9\x3D"
-			  "\x62\xA6\x19\x28\x9E\x26\xB4\x3F"
-			  "\xD7\x55\x42\x3C\xCD\x72\x0A\xF0"
-			  "\x7D\xE9\x95\x45\x86\xED\xB1\xE0"
-			  "\x8D\xE9\xC5\x86\x13\x24\x28\x7D"
-			  "\x74\xEF\xCA\x50\x12\x7E\x64\x8F"
-			  "\x1B\xF5\x5B\xFE\xE2\xAC\xFA\xE7"
-			  "\xBD\x38\x8C\x11\x20\xEF\xB1\xAA"
-			  "\x7B\xE5\xE5\x78\xAD\x9D\x2D\xA2"
-			  "\x8E\xDD\x48\xB3\xEF\x18\x92\x7E"
-			  "\xE6\x75\x0D\x54\x64\x11\xA3\x3A"
-			  "\xDB\x97\x0F\xD3\xDF\x07\xD3\x7E"
-			  "\x1E\xD1\x87\xE4\x74\xBB\x46\xF4"
-			  "\xBA\x23\x2D\x8D\x29\x07\x12\xCF"
-			  "\x34\xCD\x72\x7F\x01\x30\xE7\xA0"
-			  "\xF8\xDD\xA8\x08\xF0\xBC\xB1\xA2"
-			  "\xCC\xE1\x6B\x5F\xBE\xEA\xF1\xE4"
-			  "\x02\xC4\xAF\xFA\xAD\x31\xF4\xBF"
-			  "\xFC\x66\xAA\x37\xF2\x37\x39\x6B"
-			  "\xBC\x08\x3A\xA2\x29\xB3\xDF\xD1",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
+static const struct cipher_testvec serpent_ctr_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -12579,7 +9095,7 @@ static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -12641,8 +9157,7 @@ static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\x84\x68\xEC\xF2\x1C\x88\x20\xCA"
+		.ctext	= "\x84\x68\xEC\xF2\x1C\x88\x20\xCA"
 			  "\x37\x69\xE3\x3A\x22\x85\x48\x46"
 			  "\x70\xAA\x25\xB4\xCD\x8B\x04\x4E"
 			  "\x8D\x15\x2B\x98\xDF\x7B\x6D\xB9"
@@ -12704,7 +9219,7 @@ static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 			  "\xB2\xE6\x7E\x86\x7A\x12\x17\x5B"
 			  "\x30\xF3\x9B\x0D\xFA\x57\xE4\x50"
 			  "\x40\x53\x77\x8C\x15\xF8\x8D\x13",
-		.rlen	= 496,
+		.len	= 496,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -12713,7 +9228,7 @@ static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -12776,8 +9291,7 @@ static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
 			  "\x2B\xC2\x59",
-		.ilen	= 499,
-		.result	= "\x84\x68\xEC\xF2\x1C\x88\x20\xCA"
+		.ctext	= "\x84\x68\xEC\xF2\x1C\x88\x20\xCA"
 			  "\x37\x69\xE3\x3A\x22\x85\x48\x46"
 			  "\x70\xAA\x25\xB4\xCD\x8B\x04\x4E"
 			  "\x8D\x15\x2B\x98\xDF\x7B\x6D\xB9"
@@ -12840,7 +9354,7 @@ static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 			  "\x30\xF3\x9B\x0D\xFA\x57\xE4\x50"
 			  "\x40\x53\x77\x8C\x15\xF8\x8D\x13"
 			  "\x38\xE2\xE5",
-		.rlen	= 499,
+		.len	= 499,
 		.also_non_np = 1,
 		.np	= 2,
 		.tap	= { 499 - 16, 16 },
@@ -12852,208 +9366,7 @@ static const struct cipher_testvec serpent_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
 			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\x06\x9A\xF8\xB4\x53\x88\x62\xFC"
-			  "\x68\xB8\x2E\xDF\xC1\x05\x0F\x3D"
-			  "\xAF\x4D\x95\xAE\xC4\xE9\x1C\xDC"
-			  "\xF6\x2B\x8F\x90\x89\xF6\x7E\x1A"
-			  "\xA6\xB9\xE4\xF4\xFA\xCA\xE5\x7E"
-			  "\x71\x28\x06\x4F\xE8\x08\x39\xDA"
-			  "\xA5\x0E\xC8\xC0\xB8\x16\xE5\x69"
-			  "\xE5\xCA\xEC\x4F\x63\x2C\xC0\x9B"
-			  "\x9F\x3E\x39\x79\xF0\xCD\x64\x35"
-			  "\x4A\xD3\xC8\xA9\x31\xCD\x48\x5B"
-			  "\x92\x3D\x8F\x3F\x96\xBD\xB3\x18"
-			  "\x74\x2A\x5D\x29\x3F\x57\x8F\xE2"
-			  "\x67\x9A\xE0\xE5\xD4\x4A\xE2\x47"
-			  "\xBC\xF6\xEB\x14\xF3\x8C\x20\xC2"
-			  "\x7D\xE2\x43\x81\x86\x72\x2E\xB1"
-			  "\x39\xF6\x95\xE1\x1F\xCB\x76\x33"
-			  "\x5B\x7D\x23\x0F\x3A\x67\x2A\x2F"
-			  "\xB9\x37\x9D\xDD\x1F\x16\xA1\x3C"
-			  "\x70\xFE\x52\xAA\x93\x3C\xC4\x46"
-			  "\xB1\xE5\xFF\xDA\xAF\xE2\x84\xFE"
-			  "\x25\x92\xB2\x63\xBD\x49\x77\xB4"
-			  "\x22\xA4\x6A\xD5\x04\xE0\x45\x58"
-			  "\x1C\x34\x96\x7C\x03\x0C\x13\xA2"
-			  "\x05\x22\xE2\xCB\x5A\x35\x03\x09"
-			  "\x40\xD2\x82\x05\xCA\x58\x73\xF2"
-			  "\x29\x5E\x01\x47\x13\x32\x78\xBE"
-			  "\x06\xB0\x51\xDB\x6C\x31\xA0\x1C"
-			  "\x74\xBC\x8D\x25\xDF\xF8\x65\xD1"
-			  "\x38\x35\x11\x26\x4A\xB4\x06\x32"
-			  "\xFA\xD2\x07\x77\xB3\x74\x98\x80"
-			  "\x61\x59\xA8\x9F\xF3\x6F\x2A\xBF"
-			  "\xE6\xA5\x9A\xC4\x6B\xA6\x49\x6F"
-			  "\xBC\x47\xD9\xFB\xC6\xEF\x25\x65"
-			  "\x96\xAC\x9F\xE4\x81\x4B\xD8\xBA"
-			  "\xD6\x9B\xC9\x6D\x58\x40\x81\x02"
-			  "\x73\x44\x4E\x43\x6E\x37\xBB\x11"
-			  "\xE3\xF9\xB8\x2F\xEC\x76\x34\xEA"
-			  "\x90\xCD\xB7\x2E\x0E\x32\x71\xE8"
-			  "\xBB\x4E\x0B\x98\xA4\x17\x17\x5B"
-			  "\x07\xB5\x82\x3A\xC4\xE8\x42\x51"
-			  "\x5A\x4C\x4E\x7D\xBF\xC4\xC0\x4F"
-			  "\x68\xB8\xC6\x4A\x32\x6F\x0B\xD7"
-			  "\x85\xED\x6B\xFB\x72\xD2\xA5\x8F"
-			  "\xBF\xF9\xAC\x59\x50\xA8\x08\x70"
-			  "\xEC\xBD\x0A\xBF\xE5\x87\xA1\xC2"
-			  "\x92\x14\x78\xAF\xE8\xEA\x2E\xDD"
-			  "\xC1\x03\x9A\xAA\x89\x8B\x32\x46"
-			  "\x5B\x18\x27\xBA\x46\xAA\x64\xDE"
-			  "\xE3\xD5\xA3\xFC\x7B\x5B\x61\xDB"
-			  "\x7E\xDA\xEC\x30\x17\x19\xF8\x80"
-			  "\xB5\x5E\x27\xB5\x37\x3A\x1F\x28"
-			  "\x07\x73\xC3\x63\xCE\xFF\x8C\xFE"
-			  "\x81\x4E\xF8\x24\xF3\xB8\xC7\xE8"
-			  "\x16\x9A\xCC\x58\x2F\x88\x1C\x4B"
-			  "\xBB\x33\xA2\x73\xF0\x1C\x89\x0E"
-			  "\xDC\x34\x27\x89\x98\xCE\x1C\xA2"
-			  "\xD8\xB8\x90\xBE\xEC\x72\x28\x13"
-			  "\xAC\x7B\xF1\xD0\x7F\x7A\x28\x50"
-			  "\xB7\x99\x65\x8A\xC9\xC6\x21\x34"
-			  "\x7F\x67\x9D\xB7\x2C\xCC\xF5\x17"
-			  "\x2B\x89\xAC\xB0\xD7\x1E\x47\xB0"
-			  "\x61\xAF\xD4\x63\x6D\xB8\x2D\x20",
-		.rlen	= 496,
-	},
-};
-
-static const struct cipher_testvec serpent_ctr_dec_tv_template[] = {
-	{ /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x84\x68\xEC\xF2\x1C\x88\x20\xCA"
-			  "\x37\x69\xE3\x3A\x22\x85\x48\x46"
-			  "\x70\xAA\x25\xB4\xCD\x8B\x04\x4E"
-			  "\x8D\x15\x2B\x98\xDF\x7B\x6D\xB9"
-			  "\xE0\x4A\x73\x00\x65\xB6\x1A\x0D"
-			  "\x5C\x60\xDF\x34\xDC\x60\x4C\xDF"
-			  "\xB5\x1F\x26\x8C\xDA\xC1\x11\xA8"
-			  "\x80\xFA\x37\x7A\x89\xAA\xAE\x7B"
-			  "\x92\x6E\xB9\xDC\xC9\x62\x4F\x88"
-			  "\x0A\x5D\x97\x2F\x6B\xAC\x03\x7C"
-			  "\x22\xF6\x55\x5A\xFA\x35\xA5\x17"
-			  "\xA1\x5C\x5E\x2B\x63\x2D\xB9\x91"
-			  "\x3E\x83\x26\x00\x4E\xD5\xBE\xCE"
-			  "\x79\xC4\x3D\xFC\x70\xA0\xAD\x96"
-			  "\xBA\x58\x2A\x1C\xDF\xC2\x3A\xA5"
-			  "\x7C\xB5\x12\x89\xED\xBF\xB6\x09"
-			  "\x13\x4F\x7D\x61\x3C\x5C\x27\xFC"
-			  "\x5D\xE1\x4F\xA1\xEA\xB3\xCA\xB9"
-			  "\xE6\xD0\x97\x81\xDE\xD1\xFB\x8A"
-			  "\x30\xDB\xA3\x5D\xEC\x25\x0B\x86"
-			  "\x71\xC8\xA7\x67\xE8\xBC\x7D\x4C"
-			  "\xAE\x82\xD3\x73\x31\x09\xCB\xB3"
-			  "\x4D\xD4\xC0\x8A\x2B\xFA\xA6\x55"
-			  "\x39\x0A\xBC\x6E\x75\xAB\xC2\xE2"
-			  "\x8A\xF2\x26\xCD\x63\x38\x35\xF7"
-			  "\xAE\x12\x83\xCD\x8A\x9E\x7E\x4C"
-			  "\xFE\x4D\xD7\xCE\x5C\x6E\x4C\xAF"
-			  "\xE3\xCD\x76\xA7\x87\xA1\x54\x7C"
-			  "\xEC\x32\xC7\x83\x2A\xFF\xF8\xEA"
-			  "\x87\xB2\x47\xA3\x9D\xC2\x9C\xA2"
-			  "\xB7\x2C\x7C\x1A\x24\xCB\x88\x61"
-			  "\xFF\xA7\x1A\x16\x01\xDD\x4B\xFC"
-			  "\x2E\xE0\x48\x67\x09\x42\xCC\x91"
-			  "\xBE\x20\x38\xC0\x5E\x3B\x95\x00"
-			  "\xA1\x96\x66\x0B\x8A\xE9\x9E\xF7"
-			  "\x6B\x34\x0A\x51\xC0\x3B\xEB\x71"
-			  "\x07\x97\x38\x4B\x5C\x56\x98\x67"
-			  "\x78\x9C\xD0\x0E\x2B\xB5\x67\x90"
-			  "\x75\xF8\xFE\x6D\x4E\x85\xCC\x0D"
-			  "\x18\x06\x15\x9D\x5A\x10\x13\x37"
-			  "\xA3\xD6\x68\xA2\xDF\x7E\xC7\x12"
-			  "\xC9\x0D\x4D\x91\xB0\x2A\x55\xFF"
-			  "\x6F\x73\x13\xDF\x28\xB5\x2A\x2C"
-			  "\xE4\xFC\x20\xD9\xF1\x7A\x82\xB1"
-			  "\xCB\x57\xB6\x3D\x8C\xF4\x8E\x27"
-			  "\x37\xDC\x35\xF3\x79\x01\x53\xA4"
-			  "\x7B\x37\xDE\x7C\x04\xAE\x50\xDB"
-			  "\x9B\x1E\x8C\x07\xA7\x52\x49\x50"
-			  "\x34\x25\x65\xDD\xA9\x8F\x7E\xBD"
-			  "\x7A\xC9\x36\xAE\xDE\x21\x48\x64"
-			  "\xC2\x02\xBA\xBE\x11\x1E\x3D\x9C"
-			  "\x98\x52\xCC\x04\xBD\x5E\x61\x26"
-			  "\x10\xD3\x21\xD9\x6E\x25\x98\x77"
-			  "\x8E\x98\x63\xF6\xF6\x52\xFB\x13"
-			  "\xAA\x30\xF2\xB9\xA4\x43\x53\x39"
-			  "\x1C\x97\x07\x7E\x6B\xFF\x3D\x43"
-			  "\xA6\x71\x6B\x66\x8F\x58\x3F\x71"
-			  "\x90\x47\x40\x92\xE6\x69\xD1\x96"
-			  "\x34\xB3\x3B\xE5\x43\xE4\xD5\x56"
-			  "\xB2\xE6\x7E\x86\x7A\x12\x17\x5B"
-			  "\x30\xF3\x9B\x0D\xFA\x57\xE4\x50"
-			  "\x40\x53\x77\x8C\x15\xF8\x8D\x13",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -13115,155 +9428,7 @@ static const struct cipher_testvec serpent_ctr_dec_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x84\x68\xEC\xF2\x1C\x88\x20\xCA"
-			  "\x37\x69\xE3\x3A\x22\x85\x48\x46"
-			  "\x70\xAA\x25\xB4\xCD\x8B\x04\x4E"
-			  "\x8D\x15\x2B\x98\xDF\x7B\x6D\xB9"
-			  "\xE0\x4A\x73\x00\x65\xB6\x1A\x0D"
-			  "\x5C\x60\xDF\x34\xDC\x60\x4C\xDF"
-			  "\xB5\x1F\x26\x8C\xDA\xC1\x11\xA8"
-			  "\x80\xFA\x37\x7A\x89\xAA\xAE\x7B"
-			  "\x92\x6E\xB9\xDC\xC9\x62\x4F\x88"
-			  "\x0A\x5D\x97\x2F\x6B\xAC\x03\x7C"
-			  "\x22\xF6\x55\x5A\xFA\x35\xA5\x17"
-			  "\xA1\x5C\x5E\x2B\x63\x2D\xB9\x91"
-			  "\x3E\x83\x26\x00\x4E\xD5\xBE\xCE"
-			  "\x79\xC4\x3D\xFC\x70\xA0\xAD\x96"
-			  "\xBA\x58\x2A\x1C\xDF\xC2\x3A\xA5"
-			  "\x7C\xB5\x12\x89\xED\xBF\xB6\x09"
-			  "\x13\x4F\x7D\x61\x3C\x5C\x27\xFC"
-			  "\x5D\xE1\x4F\xA1\xEA\xB3\xCA\xB9"
-			  "\xE6\xD0\x97\x81\xDE\xD1\xFB\x8A"
-			  "\x30\xDB\xA3\x5D\xEC\x25\x0B\x86"
-			  "\x71\xC8\xA7\x67\xE8\xBC\x7D\x4C"
-			  "\xAE\x82\xD3\x73\x31\x09\xCB\xB3"
-			  "\x4D\xD4\xC0\x8A\x2B\xFA\xA6\x55"
-			  "\x39\x0A\xBC\x6E\x75\xAB\xC2\xE2"
-			  "\x8A\xF2\x26\xCD\x63\x38\x35\xF7"
-			  "\xAE\x12\x83\xCD\x8A\x9E\x7E\x4C"
-			  "\xFE\x4D\xD7\xCE\x5C\x6E\x4C\xAF"
-			  "\xE3\xCD\x76\xA7\x87\xA1\x54\x7C"
-			  "\xEC\x32\xC7\x83\x2A\xFF\xF8\xEA"
-			  "\x87\xB2\x47\xA3\x9D\xC2\x9C\xA2"
-			  "\xB7\x2C\x7C\x1A\x24\xCB\x88\x61"
-			  "\xFF\xA7\x1A\x16\x01\xDD\x4B\xFC"
-			  "\x2E\xE0\x48\x67\x09\x42\xCC\x91"
-			  "\xBE\x20\x38\xC0\x5E\x3B\x95\x00"
-			  "\xA1\x96\x66\x0B\x8A\xE9\x9E\xF7"
-			  "\x6B\x34\x0A\x51\xC0\x3B\xEB\x71"
-			  "\x07\x97\x38\x4B\x5C\x56\x98\x67"
-			  "\x78\x9C\xD0\x0E\x2B\xB5\x67\x90"
-			  "\x75\xF8\xFE\x6D\x4E\x85\xCC\x0D"
-			  "\x18\x06\x15\x9D\x5A\x10\x13\x37"
-			  "\xA3\xD6\x68\xA2\xDF\x7E\xC7\x12"
-			  "\xC9\x0D\x4D\x91\xB0\x2A\x55\xFF"
-			  "\x6F\x73\x13\xDF\x28\xB5\x2A\x2C"
-			  "\xE4\xFC\x20\xD9\xF1\x7A\x82\xB1"
-			  "\xCB\x57\xB6\x3D\x8C\xF4\x8E\x27"
-			  "\x37\xDC\x35\xF3\x79\x01\x53\xA4"
-			  "\x7B\x37\xDE\x7C\x04\xAE\x50\xDB"
-			  "\x9B\x1E\x8C\x07\xA7\x52\x49\x50"
-			  "\x34\x25\x65\xDD\xA9\x8F\x7E\xBD"
-			  "\x7A\xC9\x36\xAE\xDE\x21\x48\x64"
-			  "\xC2\x02\xBA\xBE\x11\x1E\x3D\x9C"
-			  "\x98\x52\xCC\x04\xBD\x5E\x61\x26"
-			  "\x10\xD3\x21\xD9\x6E\x25\x98\x77"
-			  "\x8E\x98\x63\xF6\xF6\x52\xFB\x13"
-			  "\xAA\x30\xF2\xB9\xA4\x43\x53\x39"
-			  "\x1C\x97\x07\x7E\x6B\xFF\x3D\x43"
-			  "\xA6\x71\x6B\x66\x8F\x58\x3F\x71"
-			  "\x90\x47\x40\x92\xE6\x69\xD1\x96"
-			  "\x34\xB3\x3B\xE5\x43\xE4\xD5\x56"
-			  "\xB2\xE6\x7E\x86\x7A\x12\x17\x5B"
-			  "\x30\xF3\x9B\x0D\xFA\x57\xE4\x50"
-			  "\x40\x53\x77\x8C\x15\xF8\x8D\x13"
-			  "\x38\xE2\xE5",
-		.ilen	= 499,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59",
-		.rlen	= 499,
-		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 499 - 16, 16 },
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
-			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x06\x9A\xF8\xB4\x53\x88\x62\xFC"
+		.ctext	= "\x06\x9A\xF8\xB4\x53\x88\x62\xFC"
 			  "\x68\xB8\x2E\xDF\xC1\x05\x0F\x3D"
 			  "\xAF\x4D\x95\xAE\xC4\xE9\x1C\xDC"
 			  "\xF6\x2B\x8F\x90\x89\xF6\x7E\x1A"
@@ -13325,74 +9490,11 @@ static const struct cipher_testvec serpent_ctr_dec_tv_template[] = {
 			  "\x7F\x67\x9D\xB7\x2C\xCC\xF5\x17"
 			  "\x2B\x89\xAC\xB0\xD7\x1E\x47\xB0"
 			  "\x61\xAF\xD4\x63\x6D\xB8\x2D\x20",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
+		.len	= 496,
 	},
 };
 
-static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
+static const struct cipher_testvec serpent_lrw_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	{
 		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
@@ -13402,12 +9504,11 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x6f\xbf\xd4\xa4\x5d\x71\x16\x79"
+		.ctext	= "\x6f\xbf\xd4\xa4\x5d\x71\x16\x79"
 			  "\x63\x9c\xa6\x8e\x40\xbe\x0d\x8a",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x59\x70\x47\x14\xf5\x57\x47\x8c"
 			  "\xd7\x79\xe8\x0f\x54\x88\x79\x44"
@@ -13416,12 +9517,11 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\xfd\xb2\x66\x98\x80\x96\x55\xad"
+		.ctext	= "\xfd\xb2\x66\x98\x80\x96\x55\xad"
 			  "\x08\x94\x54\x9c\x21\x7c\x69\xe3",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xd8\x2a\x91\x34\xb2\x6a\x56\x50"
 			  "\x30\xfe\x69\xe2\x37\x7f\x98\x47"
@@ -13430,12 +9530,11 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x14\x5e\x3d\x70\xc0\x6e\x9c\x34"
+		.ctext	= "\x14\x5e\x3d\x70\xc0\x6e\x9c\x34"
 			  "\x5b\x5e\xcf\x0f\xe4\x8c\x21\x5c",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x0f\x6a\xef\xf8\xd3\xd2\xbb\x15"
 			  "\x25\x83\xf7\x3c\x1f\x01\x28\x74"
@@ -13445,12 +9544,11 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 		.klen	= 40,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x25\x39\xaa\xa5\xf0\x65\xc8\xdc"
+		.ctext	= "\x25\x39\xaa\xa5\xf0\x65\xc8\xdc"
 			  "\x5d\x45\x95\x30\x8f\xff\x2f\x1b",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x8a\xd4\xee\x10\x2f\xbd\x81\xff"
 			  "\xf8\x86\xce\xac\x93\xc5\xad\xc6"
@@ -13460,12 +9558,11 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 		.klen	= 40,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x0c\x20\x20\x63\xd6\x8b\xfc\x8f"
+		.ctext	= "\x0c\x20\x20\x63\xd6\x8b\xfc\x8f"
 			  "\xc0\xe2\x17\xbb\xd2\x59\x6f\x26",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -13476,12 +9573,11 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\xc1\x35\x2e\x53\xf0\x96\x4d\x9c"
+		.ctext	= "\xc1\x35\x2e\x53\xf0\x96\x4d\x9c"
 			  "\x2e\x18\xe6\x99\xcd\xd3\x15\x68",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xfb\x76\x15\xb2\x3d\x80\x89\x1d"
 			  "\xd4\x70\x98\x0b\xc7\x95\x84\xc8"
@@ -13492,12 +9588,11 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x86\x0a\xc6\xa9\x1a\x9f\xe7\xe6"
+		.ctext	= "\x86\x0a\xc6\xa9\x1a\x9f\xe7\xe6"
 			  "\x64\x3b\x33\xd6\xd5\x84\xd6\xdf",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -13508,7 +9603,7 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
+		.ptext	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
 			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
 			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
 			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
@@ -13572,196 +9667,7 @@ static const struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
 			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.ilen	= 512,
-		.result	= "\xe3\x5a\x38\x0f\x4d\x92\x3a\x74"
-			  "\x15\xb1\x50\x8c\x9a\xd8\x99\x1d"
-			  "\x82\xec\xf1\x5f\x03\x6d\x02\x58"
-			  "\x90\x67\xfc\xdd\x8d\xe1\x38\x08"
-			  "\x7b\xc9\x9b\x4b\x04\x09\x50\x15"
-			  "\xce\xab\xda\x33\x30\x20\x12\xfa"
-			  "\x83\xc4\xa6\x9a\x2e\x7d\x90\xd9"
-			  "\xa6\xa6\x67\x43\xb4\xa7\xa8\x5c"
-			  "\xbb\x6a\x49\x2b\x8b\xf8\xd0\x22"
-			  "\xe5\x9e\xba\xe8\x8c\x67\xb8\x5b"
-			  "\x60\xbc\xf5\xa4\x95\x4e\x66\xe5"
-			  "\x6d\x8e\xa9\xf6\x65\x2e\x04\xf5"
-			  "\xba\xb5\xdb\x88\xc2\xf6\x7a\x4b"
-			  "\x89\x58\x7c\x9a\xae\x26\xe8\xb7"
-			  "\xb7\x28\xcc\xd6\xcc\xa5\x98\x4d"
-			  "\xb9\x91\xcb\xb4\xe4\x8b\x96\x47"
-			  "\x5f\x03\x8b\xdd\x94\xd1\xee\x12"
-			  "\xa7\x83\x80\xf2\xc1\x15\x74\x4f"
-			  "\x49\xf9\xb0\x7e\x6f\xdc\x73\x2f"
-			  "\xe2\xcf\xe0\x1b\x34\xa5\xa0\x52"
-			  "\xfb\x3c\x5d\x85\x91\xe6\x6d\x98"
-			  "\x04\xd6\xdd\x4c\x00\x64\xd9\x54"
-			  "\x5c\x3c\x08\x1d\x4c\x06\x9f\xb8"
-			  "\x1c\x4d\x8d\xdc\xa4\x3c\xb9\x3b"
-			  "\x9e\x85\xce\xc3\xa8\x4a\x0c\xd9"
-			  "\x04\xc3\x6f\x17\x66\xa9\x1f\x59"
-			  "\xd9\xe2\x19\x36\xa3\x88\xb8\x0b"
-			  "\x0f\x4a\x4d\xf8\xc8\x6f\xd5\x43"
-			  "\xeb\xa0\xab\x1f\x61\xc0\x06\xeb"
-			  "\x93\xb7\xb8\x6f\x0d\xbd\x07\x49"
-			  "\xb3\xac\x5d\xcf\x31\xa0\x27\x26"
-			  "\x21\xbe\x94\x2e\x19\xea\xf4\xee"
-			  "\xb5\x13\x89\xf7\x94\x0b\xef\x59"
-			  "\x44\xc5\x78\x8b\x3c\x3b\x71\x20"
-			  "\xf9\x35\x0c\x70\x74\xdc\x5b\xc2"
-			  "\xb4\x11\x0e\x2c\x61\xa1\x52\x46"
-			  "\x18\x11\x16\xc6\x86\x44\xa7\xaf"
-			  "\xd5\x0c\x7d\xa6\x9e\x25\x2d\x1b"
-			  "\x9a\x8f\x0f\xf8\x6a\x61\xa0\xea"
-			  "\x3f\x0e\x90\xd6\x8f\x83\x30\x64"
-			  "\xb5\x51\x2d\x08\x3c\xcd\x99\x36"
-			  "\x96\xd4\xb1\xb5\x48\x30\xca\x48"
-			  "\xf7\x11\xa8\xf5\x97\x8a\x6a\x6d"
-			  "\x12\x33\x2f\xc0\xe8\xda\xec\x8a"
-			  "\xe1\x88\x72\x63\xde\x20\xa3\xe1"
-			  "\x8e\xac\x84\x37\x35\xf5\xf7\x3f"
-			  "\x00\x02\x0e\xe4\xc1\x53\x68\x3f"
-			  "\xaa\xd5\xac\x52\x3d\x20\x2f\x4d"
-			  "\x7c\x83\xd0\xbd\xaa\x97\x35\x36"
-			  "\x98\x88\x59\x5d\xe7\x24\xe3\x90"
-			  "\x9d\x30\x47\xa7\xc3\x60\x35\xf4"
-			  "\xd5\xdb\x0e\x4d\x44\xc1\x81\x8b"
-			  "\xfd\xbd\xc3\x2b\xba\x68\xfe\x8d"
-			  "\x49\x5a\x3c\x8a\xa3\x01\xae\x25"
-			  "\x42\xab\xd2\x87\x1b\x35\xd6\xd2"
-			  "\xd7\x70\x1c\x1f\x72\xd1\xe1\x39"
-			  "\x1c\x58\xa2\xb4\xd0\x78\x55\x72"
-			  "\x76\x59\xea\xd9\xd7\x6e\x63\x8b"
-			  "\xcc\x9b\xa7\x74\x89\xfc\xa3\x68"
-			  "\x86\x28\xd1\xbb\x54\x8d\x66\xad"
-			  "\x2a\x92\xf9\x4e\x04\x3d\xae\xfd"
-			  "\x1b\x2b\x7f\xc3\x2f\x1a\x78\x0a"
-			  "\x5c\xc6\x84\xfe\x7c\xcb\x26\xfd"
-			  "\xd9\x51\x0f\xd7\x94\x2f\xc5\xa7",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec serpent_lrw_dec_tv_template[] = {
-	/* Generated from AES-LRW test vectors */
-	/* same as enc vectors with input and result reversed */
-	{
-		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
-			  "\x4c\x26\x84\x14\xb5\x68\x01\x85"
-			  "\x25\x8e\x2a\x05\xe7\x3e\x9d\x03"
-			  "\xee\x5a\x83\x0c\xcc\x09\x4c\x87",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x6f\xbf\xd4\xa4\x5d\x71\x16\x79"
-			  "\x63\x9c\xa6\x8e\x40\xbe\x0d\x8a",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x59\x70\x47\x14\xf5\x57\x47\x8c"
-			  "\xd7\x79\xe8\x0f\x54\x88\x79\x44"
-			  "\x0d\x48\xf0\xb7\xb1\x5a\x53\xea"
-			  "\x1c\xaa\x6b\x29\xc2\xca\xfb\xaf",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input	= "\xfd\xb2\x66\x98\x80\x96\x55\xad"
-			  "\x08\x94\x54\x9c\x21\x7c\x69\xe3",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xd8\x2a\x91\x34\xb2\x6a\x56\x50"
-			  "\x30\xfe\x69\xe2\x37\x7f\x98\x47"
-			  "\xcd\xf9\x0b\x16\x0c\x64\x8f\xb6"
-			  "\xb0\x0d\x0d\x1b\xae\x85\x87\x1f",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x14\x5e\x3d\x70\xc0\x6e\x9c\x34"
-			  "\x5b\x5e\xcf\x0f\xe4\x8c\x21\x5c",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x0f\x6a\xef\xf8\xd3\xd2\xbb\x15"
-			  "\x25\x83\xf7\x3c\x1f\x01\x28\x74"
-			  "\xca\xc6\xbc\x35\x4d\x4a\x65\x54"
-			  "\x90\xae\x61\xcf\x7b\xae\xbd\xcc"
-			  "\xad\xe4\x94\xc5\x4a\x29\xae\x70",
-		.klen	= 40,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x25\x39\xaa\xa5\xf0\x65\xc8\xdc"
-			  "\x5d\x45\x95\x30\x8f\xff\x2f\x1b",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x8a\xd4\xee\x10\x2f\xbd\x81\xff"
-			  "\xf8\x86\xce\xac\x93\xc5\xad\xc6"
-			  "\xa0\x19\x07\xc0\x9d\xf7\xbb\xdd"
-			  "\x52\x13\xb2\xb7\xf0\xff\x11\xd8"
-			  "\xd6\x08\xd0\xcd\x2e\xb1\x17\x6f",
-		.klen	= 40,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x0c\x20\x20\x63\xd6\x8b\xfc\x8f"
-			  "\xc0\xe2\x17\xbb\xd2\x59\x6f\x26",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\xc1\x35\x2e\x53\xf0\x96\x4d\x9c"
-			  "\x2e\x18\xe6\x99\xcd\xd3\x15\x68",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xfb\x76\x15\xb2\x3d\x80\x89\x1d"
-			  "\xd4\x70\x98\x0b\xc7\x95\x84\xc8"
-			  "\xb2\xfb\x64\xce\x60\x97\x87\x8d"
-			  "\x17\xfc\xe4\x5a\x49\xe8\x30\xb7"
-			  "\x6e\x78\x17\xe7\x2d\x5e\x12\xd4"
-			  "\x60\x64\x04\x7a\xf1\x2f\x9e\x0c",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x86\x0a\xc6\xa9\x1a\x9f\xe7\xe6"
-			  "\x64\x3b\x33\xd6\xd5\x84\xd6\xdf",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\xe3\x5a\x38\x0f\x4d\x92\x3a\x74"
+		.ctext	= "\xe3\x5a\x38\x0f\x4d\x92\x3a\x74"
 			  "\x15\xb1\x50\x8c\x9a\xd8\x99\x1d"
 			  "\x82\xec\xf1\x5f\x03\x6d\x02\x58"
 			  "\x90\x67\xfc\xdd\x8d\xe1\x38\x08"
@@ -13825,79 +9731,14 @@ static const struct cipher_testvec serpent_lrw_dec_tv_template[] = {
 			  "\x1b\x2b\x7f\xc3\x2f\x1a\x78\x0a"
 			  "\x5c\xc6\x84\xfe\x7c\xcb\x26\xfd"
 			  "\xd9\x51\x0f\xd7\x94\x2f\xc5\xa7",
-		.ilen	= 512,
-		.result	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
-			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
-			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
-			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
-			  "\x8f\xcb\x8d\x6b\xe3\xa6\x29\x90"
-			  "\xfe\x2a\x62\x82\xae\x6d\x8b\xf6"
-			  "\xad\x1e\x9e\x20\x5f\x38\xbe\x04"
-			  "\xda\x10\x8e\xed\xa2\xa4\x87\xab"
-			  "\xda\x6b\xb4\x0c\x75\xba\xd3\x7c"
-			  "\xc9\xac\x42\x31\x95\x7c\xc9\x04"
-			  "\xeb\xd5\x6e\x32\x69\x8a\xdb\xa6"
-			  "\x15\xd7\x3f\x4f\x2f\x66\x69\x03"
-			  "\x9c\x1f\x54\x0f\xde\x1f\xf3\x65"
-			  "\x4c\x96\x12\xed\x7c\x92\x03\x01"
-			  "\x6f\xbc\x35\x93\xac\xf1\x27\xf1"
-			  "\xb4\x96\x82\x5a\x5f\xb0\xa0\x50"
-			  "\x89\xa4\x8e\x66\x44\x85\xcc\xfd"
-			  "\x33\x14\x70\xe3\x96\xb2\xc3\xd3"
-			  "\xbb\x54\x5a\x1a\xf9\x74\xa2\xc5"
-			  "\x2d\x64\x75\xdd\xb4\x54\xe6\x74"
-			  "\x8c\xd3\x9d\x9e\x86\xab\x51\x53"
-			  "\xb7\x93\x3e\x6f\xd0\x4e\x2c\x40"
-			  "\xf6\xa8\x2e\x3e\x9d\xf4\x66\xa5"
-			  "\x76\x12\x73\x44\x1a\x56\xd7\x72"
-			  "\x88\xcd\x21\x8c\x4c\x0f\xfe\xda"
-			  "\x95\xe0\x3a\xa6\xa5\x84\x46\xcd"
-			  "\xd5\x3e\x9d\x3a\xe2\x67\xe6\x60"
-			  "\x1a\xe2\x70\x85\x58\xc2\x1b\x09"
-			  "\xe1\xd7\x2c\xca\xad\xa8\x8f\xf9"
-			  "\xac\xb3\x0e\xdb\xca\x2e\xe2\xb8"
-			  "\x51\x71\xd9\x3c\x6c\xf1\x56\xf8"
-			  "\xea\x9c\xf1\xfb\x0c\xe6\xb7\x10"
-			  "\x1c\xf8\xa9\x7c\xe8\x53\x35\xc1"
-			  "\x90\x3e\x76\x4a\x74\xa4\x21\x2c"
-			  "\xf6\x2c\x4e\x0f\x94\x3a\x88\x2e"
-			  "\x41\x09\x6a\x33\x7d\xf6\xdd\x3f"
-			  "\x8d\x23\x31\x74\x84\xeb\x88\x6e"
-			  "\xcc\xb9\xbc\x22\x83\x19\x07\x22"
-			  "\xa5\x2d\xdf\xa5\xf3\x80\x85\x78"
-			  "\x84\x39\x6a\x6d\x6a\x99\x4f\xa5"
-			  "\x15\xfe\x46\xb0\xe4\x6c\xa5\x41"
-			  "\x3c\xce\x8f\x42\x60\x71\xa7\x75"
-			  "\x08\x40\x65\x8a\x82\xbf\xf5\x43"
-			  "\x71\x96\xa9\x4d\x44\x8a\x20\xbe"
-			  "\xfa\x4d\xbb\xc0\x7d\x31\x96\x65"
-			  "\xe7\x75\xe5\x3e\xfd\x92\x3b\xc9"
-			  "\x55\xbb\x16\x7e\xf7\xc2\x8c\xa4"
-			  "\x40\x1d\xe5\xef\x0e\xdf\xe4\x9a"
-			  "\x62\x73\x65\xfd\x46\x63\x25\x3d"
-			  "\x2b\xaf\xe5\x64\xfe\xa5\x5c\xcf"
-			  "\x24\xf3\xb4\xac\x64\xba\xdf\x4b"
-			  "\xc6\x96\x7d\x81\x2d\x8d\x97\xf7"
-			  "\xc5\x68\x77\x84\x32\x2b\xcc\x85"
-			  "\x74\x96\xf0\x12\x77\x61\xb9\xeb"
-			  "\x71\xaa\x82\xcb\x1c\xdb\x89\xc8"
-			  "\xc6\xb5\xe3\x5c\x7d\x39\x07\x24"
-			  "\xda\x39\x87\x45\xc0\x2b\xbb\x01"
-			  "\xac\xbc\x2a\x5c\x7f\xfc\xe8\xce"
-			  "\x6d\x9c\x6f\xed\xd3\xc1\xa1\xd6"
-			  "\xc5\x55\xa9\x66\x2f\xe1\xc8\x32"
-			  "\xa6\x5d\xa4\x3a\x98\x73\xe8\x45"
-			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
-			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
-			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
+static const struct cipher_testvec serpent_xts_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 	{
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -13907,16 +9748,15 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 32,
-		.result	= "\xe1\x08\xb8\x1d\x2c\xf5\x33\x64"
+		.ctext	= "\xe1\x08\xb8\x1d\x2c\xf5\x33\x64"
 			  "\xc8\x12\x04\xc7\xb3\x70\xe8\xc4"
 			  "\x6a\x31\xc5\xf3\x00\xca\xb9\x16"
 			  "\xde\xe2\x77\x66\xf7\xfe\x62\x08",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
 			  "\x11\x11\x11\x11\x11\x11\x11\x11"
@@ -13925,16 +9765,15 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\x1a\x0a\x09\x5f\xcd\x07\x07\x98"
+		.ctext	= "\x1a\x0a\x09\x5f\xcd\x07\x07\x98"
 			  "\x41\x86\x12\xaf\xb3\xd7\x68\x13"
 			  "\xed\x81\xcd\x06\x87\x43\x1a\xbb"
 			  "\x13\x3d\xd6\x1e\x2b\xe1\x77\xbe",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
 			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
@@ -13943,16 +9782,15 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\xf9\x9b\x28\xb8\x5c\xaf\x8c\x61"
+		.ctext	= "\xf9\x9b\x28\xb8\x5c\xaf\x8c\x61"
 			  "\xb6\x1c\x81\x8f\x2c\x87\x60\x89"
 			  "\x0d\x8d\x7a\xe8\x60\x48\xcc\x86"
 			  "\xc1\x68\x45\xaa\x00\xe9\x24\xc5",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -13961,7 +9799,7 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -14025,8 +9863,7 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\xfe\x47\x4a\xc8\x60\x7e\xb4\x8b"
+		.ctext	= "\xfe\x47\x4a\xc8\x60\x7e\xb4\x8b"
 			  "\x0d\x10\xf4\xb0\x0d\xba\xf8\x53"
 			  "\x65\x6e\x38\x4b\xdb\xaa\xb1\x9e"
 			  "\x28\xca\xb0\x22\xb3\x85\x75\xf4"
@@ -14090,7 +9927,7 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 			  "\xef\x91\x64\x1d\x18\x07\x4e\x31"
 			  "\x88\x21\x7c\xb0\xa5\x12\x4c\x3c"
 			  "\xb0\x20\xbd\xda\xdf\xf9\x7c\xdd",
-		.rlen	= 512,
+		.len	= 512,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -14103,7 +9940,7 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 		.klen	= 64,
 		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -14167,8 +10004,7 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\x2b\xc9\xb4\x6b\x10\x94\xa9\x32"
+		.ctext	= "\x2b\xc9\xb4\x6b\x10\x94\xa9\x32"
 			  "\xaa\xb0\x20\xc6\x44\x3d\x74\x1f"
 			  "\x75\x01\xa7\xf6\xf5\xf7\x62\x1b"
 			  "\x80\x1b\x82\xcb\x01\x59\x91\x7f"
@@ -14232,350 +10068,7 @@ static const struct cipher_testvec serpent_xts_enc_tv_template[] = {
 			  "\x30\x05\xc8\x92\x98\x80\xff\x7a"
 			  "\xaf\x43\x0b\xc5\x20\x41\x92\x20"
 			  "\xd4\xa0\x91\x98\x11\x5f\x4d\xb1",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec serpent_xts_dec_tv_template[] = {
-	/* Generated from AES-XTS test vectors */
-	/* same as enc vectors with input and result reversed */
-	{
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xe1\x08\xb8\x1d\x2c\xf5\x33\x64"
-			  "\xc8\x12\x04\xc7\xb3\x70\xe8\xc4"
-			  "\x6a\x31\xc5\xf3\x00\xca\xb9\x16"
-			  "\xde\xe2\x77\x66\xf7\xfe\x62\x08",
-		.ilen	= 32,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 32,
-	}, {
-		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 32,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x1a\x0a\x09\x5f\xcd\x07\x07\x98"
-			  "\x41\x86\x12\xaf\xb3\xd7\x68\x13"
-			  "\xed\x81\xcd\x06\x87\x43\x1a\xbb"
-			  "\x13\x3d\xd6\x1e\x2b\xe1\x77\xbe",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
-			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 32,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xf9\x9b\x28\xb8\x5c\xaf\x8c\x61"
-			  "\xb6\x1c\x81\x8f\x2c\x87\x60\x89"
-			  "\x0d\x8d\x7a\xe8\x60\x48\xcc\x86"
-			  "\xc1\x68\x45\xaa\x00\xe9\x24\xc5",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xfe\x47\x4a\xc8\x60\x7e\xb4\x8b"
-			  "\x0d\x10\xf4\xb0\x0d\xba\xf8\x53"
-			  "\x65\x6e\x38\x4b\xdb\xaa\xb1\x9e"
-			  "\x28\xca\xb0\x22\xb3\x85\x75\xf4"
-			  "\x00\x5c\x75\x14\x06\xd6\x25\x82"
-			  "\xe6\xcb\x08\xf7\x29\x90\x23\x8e"
-			  "\xa4\x68\x57\xe4\xf0\xd8\x32\xf3"
-			  "\x80\x51\x67\xb5\x0b\x85\x69\xe8"
-			  "\x19\xfe\xc4\xc7\x3e\xea\x90\xd3"
-			  "\x8f\xa3\xf2\x0a\xac\x17\x4b\xa0"
-			  "\x63\x5a\x16\x0f\xf0\xce\x66\x1f"
-			  "\x2c\x21\x07\xf1\xa4\x03\xa3\x44"
-			  "\x41\x61\x87\x5d\x6b\xb3\xef\xd4"
-			  "\xfc\xaa\x32\x7e\x55\x58\x04\x41"
-			  "\xc9\x07\x33\xc6\xa2\x68\xd6\x5a"
-			  "\x55\x79\x4b\x6f\xcf\x89\xb9\x19"
-			  "\xe5\x54\x13\x15\xb2\x1a\xfa\x15"
-			  "\xc2\xf0\x06\x59\xfa\xa0\x25\x05"
-			  "\x58\xfa\x43\x91\x16\x85\x40\xbb"
-			  "\x0d\x34\x4d\xc5\x1e\x20\xd5\x08"
-			  "\xcd\x22\x22\x41\x11\x9f\x6c\x7c"
-			  "\x8d\x57\xc9\xba\x57\xe8\x2c\xf7"
-			  "\xa0\x42\xa8\xde\xfc\xa3\xca\x98"
-			  "\x4b\x43\xb1\xce\x4b\xbf\x01\x67"
-			  "\x6e\x29\x60\xbd\x10\x14\x84\x82"
-			  "\x83\x82\x0c\x63\x73\x92\x02\x7c"
-			  "\x55\x37\x20\x80\x17\x51\xc8\xbc"
-			  "\x46\x02\xcb\x38\x07\x6d\xe2\x85"
-			  "\xaa\x29\xaf\x24\x58\x0d\xf0\x75"
-			  "\x08\x0a\xa5\x34\x25\x16\xf3\x74"
-			  "\xa7\x0b\x97\xbe\xc1\xa9\xdc\x29"
-			  "\x1a\x0a\x56\xc1\x1a\x91\x97\x8c"
-			  "\x0b\xc7\x16\xed\x5a\x22\xa6\x2e"
-			  "\x8c\x2b\x4f\x54\x76\x47\x53\x8e"
-			  "\xe8\x00\xec\x92\xb9\x55\xe6\xa2"
-			  "\xf3\xe2\x4f\x6a\x66\x60\xd0\x87"
-			  "\xe6\xd1\xcc\xe3\x6a\xc5\x2d\x21"
-			  "\xcc\x9d\x6a\xb6\x75\xaa\xe2\x19"
-			  "\x21\x9f\xa1\x5e\x4c\xfd\x72\xf9"
-			  "\x94\x4e\x63\xc7\xae\xfc\xed\x47"
-			  "\xe2\xfe\x7a\x63\x77\xfe\x97\x82"
-			  "\xb1\x10\x6e\x36\x1d\xe1\xc4\x80"
-			  "\xec\x69\x41\xec\xa7\x8a\xe0\x2f"
-			  "\xe3\x49\x26\xa2\x41\xb2\x08\x0f"
-			  "\x28\xb4\xa7\x39\xa1\x99\x2d\x1e"
-			  "\x43\x42\x35\xd0\xcf\xec\x77\x67"
-			  "\xb2\x3b\x9e\x1c\x35\xde\x4f\x5e"
-			  "\x73\x3f\x5d\x6f\x07\x4b\x2e\x50"
-			  "\xab\x6c\x6b\xff\xea\x00\x67\xaa"
-			  "\x0e\x82\x32\xdd\x3d\xb5\xe5\x76"
-			  "\x2b\x77\x3f\xbe\x12\x75\xfb\x92"
-			  "\xc6\x89\x67\x4d\xca\xf7\xd4\x50"
-			  "\xc0\x74\x47\xcc\xd9\x0a\xd4\xc6"
-			  "\x3b\x17\x2e\xe3\x35\xbb\x53\xb5"
-			  "\x86\xad\x51\xcc\xd5\x96\xb8\xdc"
-			  "\x03\x57\xe6\x98\x52\x2f\x61\x62"
-			  "\xc4\x5c\x9c\x36\x71\x07\xfb\x94"
-			  "\xe3\x02\xc4\x2b\x08\x75\xc7\x35"
-			  "\xfb\x2e\x88\x7b\xbb\x67\x00\xe1"
-			  "\xc9\xdd\x99\xb2\x13\x53\x1a\x4e"
-			  "\x76\x87\x19\x04\x1a\x2f\x38\x3e"
-			  "\xef\x91\x64\x1d\x18\x07\x4e\x31"
-			  "\x88\x21\x7c\xb0\xa5\x12\x4c\x3c"
-			  "\xb0\x20\xbd\xda\xdf\xf9\x7c\xdd",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x62\x49\x77\x57\x24\x70\x93\x69"
-			  "\x99\x59\x57\x49\x66\x96\x76\x27"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95"
-			  "\x02\x88\x41\x97\x16\x93\x99\x37"
-			  "\x51\x05\x82\x09\x74\x94\x45\x92",
-		.klen	= 64,
-		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x2b\xc9\xb4\x6b\x10\x94\xa9\x32"
-			  "\xaa\xb0\x20\xc6\x44\x3d\x74\x1f"
-			  "\x75\x01\xa7\xf6\xf5\xf7\x62\x1b"
-			  "\x80\x1b\x82\xcb\x01\x59\x91\x7f"
-			  "\x80\x3a\x98\xf0\xd2\xca\xc4\xc3"
-			  "\x34\xfd\xe6\x11\xf9\x33\x45\x12"
-			  "\x48\xc5\x8c\x25\xf1\xc5\xc5\x23"
-			  "\xd3\x44\xb4\x73\xd5\x04\xc0\xb7"
-			  "\xca\x2f\xf5\xcd\xc5\xb4\xdd\xb0"
-			  "\xf4\x60\xe8\xfb\xc6\x9c\xc5\x78"
-			  "\xcd\xec\x7d\xdc\x19\x9c\x72\x64"
-			  "\x63\x0b\x38\x2e\x76\xdd\x2d\x36"
-			  "\x49\xb0\x1d\xea\x78\x9e\x00\xca"
-			  "\x20\xcc\x1b\x1e\x98\x74\xab\xed"
-			  "\x79\xf7\xd0\x6c\xd8\x93\x80\x29"
-			  "\xac\xa5\x5e\x34\xa9\xab\xa0\x55"
-			  "\x9a\xea\xaa\x95\x4d\x7b\xfe\x46"
-			  "\x26\x8a\xfd\x88\xa2\xa8\xa6\xae"
-			  "\x25\x42\x17\xbf\x76\x8f\x1c\x3d"
-			  "\xec\x9a\xda\x64\x96\xb5\x61\xff"
-			  "\x99\xeb\x12\x96\x85\x82\x9d\xd5"
-			  "\x81\x85\x14\xa8\x59\xac\x8c\x94"
-			  "\xbb\x3b\x85\x2b\xdf\xb3\x0c\xba"
-			  "\x82\xc6\x4d\xca\x86\xea\x53\x28"
-			  "\x4c\xe0\x4e\x31\xe3\x73\x2f\x79"
-			  "\x9d\x42\xe1\x03\xe3\x8b\xc4\xff"
-			  "\x05\xca\x81\x7b\xda\xa2\xde\x63"
-			  "\x3a\x10\xbe\xc2\xac\x32\xc4\x05"
-			  "\x47\x7e\xef\x67\xe2\x5f\x5b\xae"
-			  "\xed\xf1\x70\x34\x16\x9a\x07\x7b"
-			  "\xf2\x25\x2b\xb0\xf8\x3c\x15\x9a"
-			  "\xa6\x59\x55\x5f\xc1\xf4\x1e\xcd"
-			  "\x93\x1f\x06\xba\xd4\x9a\x22\x69"
-			  "\xfa\x8e\x95\x0d\xf3\x23\x59\x2c"
-			  "\xfe\x00\xba\xf0\x0e\xbc\x6d\xd6"
-			  "\x62\xf0\x7a\x0e\x83\x3e\xdb\x32"
-			  "\xfd\x43\x7d\xda\x42\x51\x87\x43"
-			  "\x9d\xf9\xef\xf4\x30\x97\xf8\x09"
-			  "\x88\xfc\x3f\x93\x70\xc1\x4a\xec"
-			  "\x27\x5f\x11\xac\x71\xc7\x48\x46"
-			  "\x2f\xf9\xdf\x8d\x9f\xf7\x2e\x56"
-			  "\x0d\x4e\xb0\x32\x76\xce\x86\x81"
-			  "\xcd\xdf\xe4\x00\xbf\xfd\x5f\x24"
-			  "\xaf\xf7\x9a\xde\xff\x18\xac\x14"
-			  "\x90\xc5\x01\x39\x34\x0f\x24\xf3"
-			  "\x13\x2f\x5e\x4f\x30\x9a\x36\x40"
-			  "\xec\xea\xbc\xcd\x9e\x0e\x5b\x23"
-			  "\x50\x88\x97\x40\x69\xb1\x37\xf5"
-			  "\xc3\x15\xf9\x3f\xb7\x79\x64\xe8"
-			  "\x7b\x10\x20\xb9\x2b\x46\x83\x5b"
-			  "\xd8\x39\xfc\xe4\xfa\x88\x52\xf2"
-			  "\x72\xb0\x97\x4e\x89\xb3\x48\x00"
-			  "\xc1\x16\x73\x50\x77\xba\xa6\x65"
-			  "\x20\x2d\xb0\x02\x27\x89\xda\x99"
-			  "\x45\xfb\xe9\xd3\x1d\x39\x2f\xd6"
-			  "\x2a\xda\x09\x12\x11\xaf\xe6\x57"
-			  "\x01\x04\x8a\xff\x86\x8b\xac\xf8"
-			  "\xee\xe4\x1c\x98\x5b\xcf\x6b\x76"
-			  "\xa3\x0e\x33\x74\x40\x18\x39\x72"
-			  "\x66\x50\x31\xfd\x70\xdf\xe8\x51"
-			  "\x96\x21\x36\xb2\x9b\xfa\x85\xd1"
-			  "\x30\x05\xc8\x92\x98\x80\xff\x7a"
-			  "\xaf\x43\x0b\xc5\x20\x41\x92\x20"
-			  "\xd4\xa0\x91\x98\x11\x5f\x4d\xb1",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
@@ -14587,17 +10080,16 @@ static const struct cipher_testvec serpent_xts_dec_tv_template[] = {
  * https://tools.ietf.org/html/draft-crypto-sm4-00#ref-GBT.32907-2016
  */
 
-static const struct cipher_testvec sm4_enc_tv_template[] = {
+static const struct cipher_testvec sm4_tv_template[] = {
 	{ /* SM4 Appendix A: Example Calculations. Example 1. */
 		.key	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
 			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
 		.klen	= 16,
-		.input	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
+		.ptext	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
 			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
-		.ilen	= 16,
-		.result	= "\x68\x1E\xDF\x34\xD2\x06\x96\x5E"
+		.ctext	= "\x68\x1E\xDF\x34\xD2\x06\x96\x5E"
 			  "\x86\xB3\xE9\x4F\x53\x6E\x42\x46",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /*
 	      *  SM4 Appendix A: Example Calculations.
 	      *  Last 10 iterations of Example 2.
@@ -14605,7 +10097,7 @@ static const struct cipher_testvec sm4_enc_tv_template[] = {
 		.key    = "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
 			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
 		.klen	= 16,
-		.input	= "\x99\x4a\xc3\xe7\xc3\x57\x89\x6a"
+		.ptext	= "\x99\x4a\xc3\xe7\xc3\x57\x89\x6a"
 			  "\x81\xfc\xa8\xe\x38\x3e\xef\x80"
 			  "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
 			  "\xf0\xf1\x30\x4c\x1\x27\x5a\x8f"
@@ -14625,50 +10117,7 @@ static const struct cipher_testvec sm4_enc_tv_template[] = {
 			  "\xed\xce\x0\x19\xe\x16\x2\x6e"
 			  "\x87\xff\x2c\xac\xe8\xe7\xe9\xbf"
 			  "\x31\x51\xec\x47\xc3\x51\x83\xc1",
-		.ilen	= 160,
-		.result	= "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
-			  "\xf0\xf1\x30\x4c\x1\x27\x5a\x8f"
-			  "\x45\xe1\x39\xb7\xae\xff\x1f\x27"
-			  "\xad\x57\x15\xab\x31\x5d\xc\xef"
-			  "\x8c\xc8\x80\xbd\x11\x98\xf3\x7b"
-			  "\xa2\xdd\x14\x20\xf9\xe8\xbb\x82"
-			  "\xf7\x32\xca\x4b\xa8\xf7\xb3\x4d"
-			  "\x27\xd1\xcd\xe6\xb6\x65\x5a\x23"
-			  "\xc2\xf3\x54\x84\x53\xe3\xb9\x20"
-			  "\xa5\x37\x0\xbe\xe7\x7b\x48\xfb"
-			  "\x21\x3d\x9e\x48\x1d\x9e\xf5\xbf"
-			  "\x77\xd5\xb4\x4a\x53\x71\x94\x7a"
-			  "\x88\xa6\x6e\x6\x93\xca\x43\xa5"
-			  "\xc4\xf6\xcd\x53\x4b\x7b\x8e\xfe"
-			  "\xb4\x28\x7c\x42\x29\x32\x5d\x88"
-			  "\xed\xce\x0\x19\xe\x16\x2\x6e"
-			  "\x87\xff\x2c\xac\xe8\xe7\xe9\xbf"
-			  "\x31\x51\xec\x47\xc3\x51\x83\xc1"
-			  "\x59\x52\x98\xc7\xc6\xfd\x27\x1f"
-			  "\x4\x2\xf8\x4\xc3\x3d\x3f\x66",
-		.rlen	= 160
-	}
-};
-
-static const struct cipher_testvec sm4_dec_tv_template[] = {
-	{ /* SM4 Appendix A: Example Calculations. Example 1. */
-		.key	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
-			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
-		.klen	= 16,
-		.input	= "\x68\x1E\xDF\x34\xD2\x06\x96\x5E"
-			  "\x86\xB3\xE9\x4F\x53\x6E\x42\x46",
-		.ilen	= 16,
-		.result	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
-			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
-		.rlen	= 16,
-	}, { /*
-	      *  SM4 Appendix A: Example Calculations.
-	      *  Last 10 iterations of Example 2.
-	      */
-		.key    = "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
-			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
-		.klen	= 16,
-		.input	= "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
+		.ctext	= "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
 			  "\xf0\xf1\x30\x4c\x1\x27\x5a\x8f"
 			  "\x45\xe1\x39\xb7\xae\xff\x1f\x27"
 			  "\xad\x57\x15\xab\x31\x5d\xc\xef"
@@ -14688,28 +10137,7 @@ static const struct cipher_testvec sm4_dec_tv_template[] = {
 			  "\x31\x51\xec\x47\xc3\x51\x83\xc1"
 			  "\x59\x52\x98\xc7\xc6\xfd\x27\x1f"
 			  "\x4\x2\xf8\x4\xc3\x3d\x3f\x66",
-		.ilen	= 160,
-		.result	= "\x99\x4a\xc3\xe7\xc3\x57\x89\x6a"
-			  "\x81\xfc\xa8\xe\x38\x3e\xef\x80"
-			  "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
-			  "\xf0\xf1\x30\x4c\x1\x27\x5a\x8f"
-			  "\x45\xe1\x39\xb7\xae\xff\x1f\x27"
-			  "\xad\x57\x15\xab\x31\x5d\xc\xef"
-			  "\x8c\xc8\x80\xbd\x11\x98\xf3\x7b"
-			  "\xa2\xdd\x14\x20\xf9\xe8\xbb\x82"
-			  "\xf7\x32\xca\x4b\xa8\xf7\xb3\x4d"
-			  "\x27\xd1\xcd\xe6\xb6\x65\x5a\x23"
-			  "\xc2\xf3\x54\x84\x53\xe3\xb9\x20"
-			  "\xa5\x37\x0\xbe\xe7\x7b\x48\xfb"
-			  "\x21\x3d\x9e\x48\x1d\x9e\xf5\xbf"
-			  "\x77\xd5\xb4\x4a\x53\x71\x94\x7a"
-			  "\x88\xa6\x6e\x6\x93\xca\x43\xa5"
-			  "\xc4\xf6\xcd\x53\x4b\x7b\x8e\xfe"
-			  "\xb4\x28\x7c\x42\x29\x32\x5d\x88"
-			  "\xed\xce\x0\x19\xe\x16\x2\x6e"
-			  "\x87\xff\x2c\xac\xe8\xe7\xe9\xbf"
-			  "\x31\x51\xec\x47\xc3\x51\x83\xc1",
-		.rlen	= 160
+		.len	= 160
 	}
 };
 
@@ -14727,86 +10155,45 @@ static const struct cipher_testvec sm4_dec_tv_template[] = {
  * the lowest memory address.
  */
 
-static const struct cipher_testvec speck128_enc_tv_template[] = {
+static const struct cipher_testvec speck128_tv_template[] = {
 	{ /* Speck128/128 */
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
 		.klen	= 16,
-		.input	= "\x20\x6d\x61\x64\x65\x20\x69\x74"
+		.ptext	= "\x20\x6d\x61\x64\x65\x20\x69\x74"
 			  "\x20\x65\x71\x75\x69\x76\x61\x6c",
-		.ilen	= 16,
-		.result	= "\x18\x0d\x57\x5c\xdf\xfe\x60\x78"
+		.ctext	= "\x18\x0d\x57\x5c\xdf\xfe\x60\x78"
 			  "\x65\x32\x78\x79\x51\x98\x5d\xa6",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* Speck128/192 */
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17",
 		.klen	= 24,
-		.input	= "\x65\x6e\x74\x20\x74\x6f\x20\x43"
+		.ptext	= "\x65\x6e\x74\x20\x74\x6f\x20\x43"
 			  "\x68\x69\x65\x66\x20\x48\x61\x72",
-		.ilen	= 16,
-		.result	= "\x86\x18\x3c\xe0\x5d\x18\xbc\xf9"
+		.ctext	= "\x86\x18\x3c\xe0\x5d\x18\xbc\xf9"
 			  "\x66\x55\x13\x13\x3a\xcf\xe4\x1b",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* Speck128/256 */
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
 		.klen	= 32,
-		.input	= "\x70\x6f\x6f\x6e\x65\x72\x2e\x20"
+		.ptext	= "\x70\x6f\x6f\x6e\x65\x72\x2e\x20"
 			  "\x49\x6e\x20\x74\x68\x6f\x73\x65",
-		.ilen	= 16,
-		.result	= "\x43\x8f\x18\x9c\x8d\xb4\xee\x4e"
-			  "\x3e\xf5\xc0\x05\x04\x01\x09\x41",
-		.rlen	= 16,
-	},
-};
-
-static const struct cipher_testvec speck128_dec_tv_template[] = {
-	{ /* Speck128/128 */
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.klen	= 16,
-		.input	= "\x18\x0d\x57\x5c\xdf\xfe\x60\x78"
-			  "\x65\x32\x78\x79\x51\x98\x5d\xa6",
-		.ilen	= 16,
-		.result	= "\x20\x6d\x61\x64\x65\x20\x69\x74"
-			  "\x20\x65\x71\x75\x69\x76\x61\x6c",
-		.rlen	= 16,
-	}, { /* Speck128/192 */
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17",
-		.klen	= 24,
-		.input	= "\x86\x18\x3c\xe0\x5d\x18\xbc\xf9"
-			  "\x66\x55\x13\x13\x3a\xcf\xe4\x1b",
-		.ilen	= 16,
-		.result	= "\x65\x6e\x74\x20\x74\x6f\x20\x43"
-			  "\x68\x69\x65\x66\x20\x48\x61\x72",
-		.rlen	= 16,
-	}, { /* Speck128/256 */
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.klen	= 32,
-		.input	= "\x43\x8f\x18\x9c\x8d\xb4\xee\x4e"
+		.ctext	= "\x43\x8f\x18\x9c\x8d\xb4\xee\x4e"
 			  "\x3e\xf5\xc0\x05\x04\x01\x09\x41",
-		.ilen	= 16,
-		.result	= "\x70\x6f\x6f\x6e\x65\x72\x2e\x20"
-			  "\x49\x6e\x20\x74\x68\x6f\x73\x65",
-		.rlen	= 16,
+		.len	= 16,
 	},
 };
 
 /*
  * Speck128-XTS test vectors, taken from the AES-XTS test vectors with the
- * result recomputed with Speck128 as the cipher
+ * ciphertext recomputed with Speck128 as the cipher
  */
-
-static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
+static const struct cipher_testvec speck128_xts_tv_template[] = {
 	{
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -14815,16 +10202,15 @@ static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 32,
-		.result	= "\xbe\xa0\xe7\x03\xd7\xfe\xab\x62"
+		.ctext	= "\xbe\xa0\xe7\x03\xd7\xfe\xab\x62"
 			  "\x3b\x99\x4a\x64\x74\x77\xac\xed"
 			  "\xd8\xf4\xa6\xcf\xae\xb9\x07\x42"
 			  "\x51\xd9\xb6\x1d\xe0\x5e\xbc\x54",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
 			  "\x11\x11\x11\x11\x11\x11\x11\x11"
@@ -14833,16 +10219,15 @@ static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\xfb\x53\x81\x75\x6f\x9f\x34\xad"
+		.ctext	= "\xfb\x53\x81\x75\x6f\x9f\x34\xad"
 			  "\x7e\x01\xed\x7b\xcc\xda\x4e\x4a"
 			  "\xd4\x84\xa4\x53\xd5\x88\x73\x1b"
 			  "\xfd\xcb\xae\x0d\xf3\x04\xee\xe6",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
 			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
@@ -14851,16 +10236,15 @@ static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\x21\x52\x84\x15\xd1\xf7\x21\x55"
+		.ctext	= "\x21\x52\x84\x15\xd1\xf7\x21\x55"
 			  "\xd9\x75\x4a\xd3\xc5\xdb\x9f\x7d"
 			  "\xda\x63\xb2\xf1\x82\xb0\x89\x59"
 			  "\x86\xd4\xaa\xaa\xdd\xff\x4f\x92",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -14869,7 +10253,7 @@ static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -14933,8 +10317,7 @@ static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\x57\xb5\xf8\x71\x6e\x6d\xdd\x82"
+		.ctext	= "\x57\xb5\xf8\x71\x6e\x6d\xdd\x82"
 			  "\x53\xd0\xed\x2d\x30\xc1\x20\xef"
 			  "\x70\x67\x5e\xff\x09\x70\xbb\xc1"
 			  "\x3a\x7b\x48\x26\xd9\x0b\xf4\x48"
@@ -14998,7 +10381,7 @@ static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
 			  "\xaa\xf2\x01\xa9\xc1\x8d\xee\xca"
 			  "\x47\x26\xef\x39\xb8\xb4\xf2\xd1"
 			  "\xd6\xbb\x1b\x2a\xc1\x34\x14\xcf",
-		.rlen	= 512,
+		.len	= 512,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -15011,271 +10394,7 @@ static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
 		.klen	= 64,
 		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\xc5\x85\x2a\x4b\x73\xe4\xf6\xf1"
-			  "\x7e\xf9\xf6\xe9\xa3\x73\x36\xcb"
-			  "\xaa\xb6\x22\xb0\x24\x6e\x3d\x73"
-			  "\x92\x99\xde\xd3\x76\xed\xcd\x63"
-			  "\x64\x3a\x22\x57\xc1\x43\x49\xd4"
-			  "\x79\x36\x31\x19\x62\xae\x10\x7e"
-			  "\x7d\xcf\x7a\xe2\x6b\xce\x27\xfa"
-			  "\xdc\x3d\xd9\x83\xd3\x42\x4c\xe0"
-			  "\x1b\xd6\x1d\x1a\x6f\xd2\x03\x00"
-			  "\xfc\x81\x99\x8a\x14\x62\xf5\x7e"
-			  "\x0d\xe7\x12\xe8\x17\x9d\x0b\xec"
-			  "\xe2\xf7\xc9\xa7\x63\xd1\x79\xb6"
-			  "\x62\x62\x37\xfe\x0a\x4c\x4a\x37"
-			  "\x70\xc7\x5e\x96\x5f\xbc\x8e\x9e"
-			  "\x85\x3c\x4f\x26\x64\x85\xbc\x68"
-			  "\xb0\xe0\x86\x5e\x26\x41\xce\x11"
-			  "\x50\xda\x97\x14\xe9\x9e\xc7\x6d"
-			  "\x3b\xdc\x43\xde\x2b\x27\x69\x7d"
-			  "\xfc\xb0\x28\xbd\x8f\xb1\xc6\x31"
-			  "\x14\x4d\xf0\x74\x37\xfd\x07\x25"
-			  "\x96\x55\xe5\xfc\x9e\x27\x2a\x74"
-			  "\x1b\x83\x4d\x15\x83\xac\x57\xa0"
-			  "\xac\xa5\xd0\x38\xef\x19\x56\x53"
-			  "\x25\x4b\xfc\xce\x04\x23\xe5\x6b"
-			  "\xf6\xc6\x6c\x32\x0b\xb3\x12\xc5"
-			  "\xed\x22\x34\x1c\x5d\xed\x17\x06"
-			  "\x36\xa3\xe6\x77\xb9\x97\x46\xb8"
-			  "\xe9\x3f\x7e\xc7\xbc\x13\x5c\xdc"
-			  "\x6e\x3f\x04\x5e\xd1\x59\xa5\x82"
-			  "\x35\x91\x3d\x1b\xe4\x97\x9f\x92"
-			  "\x1c\x5e\x5f\x6f\x41\xd4\x62\xa1"
-			  "\x8d\x39\xfc\x42\xfb\x38\x80\xb9"
-			  "\x0a\xe3\xcc\x6a\x93\xd9\x7a\xb1"
-			  "\xe9\x69\xaf\x0a\x6b\x75\x38\xa7"
-			  "\xa1\xbf\xf7\xda\x95\x93\x4b\x78"
-			  "\x19\xf5\x94\xf9\xd2\x00\x33\x37"
-			  "\xcf\xf5\x9e\x9c\xf3\xcc\xa6\xee"
-			  "\x42\xb2\x9e\x2c\x5f\x48\x23\x26"
-			  "\x15\x25\x17\x03\x3d\xfe\x2c\xfc"
-			  "\xeb\xba\xda\xe0\x00\x05\xb6\xa6"
-			  "\x07\xb3\xe8\x36\x5b\xec\x5b\xbf"
-			  "\xd6\x5b\x00\x74\xc6\x97\xf1\x6a"
-			  "\x49\xa1\xc3\xfa\x10\x52\xb9\x14"
-			  "\xad\xb7\x73\xf8\x78\x12\xc8\x59"
-			  "\x17\x80\x4c\x57\x39\xf1\x6d\x80"
-			  "\x25\x77\x0f\x5e\x7d\xf0\xaf\x21"
-			  "\xec\xce\xb7\xc8\x02\x8a\xed\x53"
-			  "\x2c\x25\x68\x2e\x1f\x85\x5e\x67"
-			  "\xd1\x07\x7a\x3a\x89\x08\xe0\x34"
-			  "\xdc\xdb\x26\xb4\x6b\x77\xfc\x40"
-			  "\x31\x15\x72\xa0\xf0\x73\xd9\x3b"
-			  "\xd5\xdb\xfe\xfc\x8f\xa9\x44\xa2"
-			  "\x09\x9f\xc6\x33\xe5\xe2\x88\xe8"
-			  "\xf3\xf0\x1a\xf4\xce\x12\x0f\xd6"
-			  "\xf7\x36\xe6\xa4\xf4\x7a\x10\x58"
-			  "\xcc\x1f\x48\x49\x65\x47\x75\xe9"
-			  "\x28\xe1\x65\x7b\xf2\xc4\xb5\x07"
-			  "\xf2\xec\x76\xd8\x8f\x09\xf3\x16"
-			  "\xa1\x51\x89\x3b\xeb\x96\x42\xac"
-			  "\x65\xe0\x67\x63\x29\xdc\xb4\x7d"
-			  "\xf2\x41\x51\x6a\xcb\xde\x3c\xfb"
-			  "\x66\x8d\x13\xca\xe0\x59\x2a\x00"
-			  "\xc9\x53\x4c\xe6\x9e\xe2\x73\xd5"
-			  "\x67\x19\xb2\xbd\x9a\x63\xd7\x5c",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	}
-};
-
-static const struct cipher_testvec speck128_xts_dec_tv_template[] = {
-	{
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xbe\xa0\xe7\x03\xd7\xfe\xab\x62"
-			  "\x3b\x99\x4a\x64\x74\x77\xac\xed"
-			  "\xd8\xf4\xa6\xcf\xae\xb9\x07\x42"
-			  "\x51\xd9\xb6\x1d\xe0\x5e\xbc\x54",
-		.ilen	= 32,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 32,
-	}, {
-		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 32,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xfb\x53\x81\x75\x6f\x9f\x34\xad"
-			  "\x7e\x01\xed\x7b\xcc\xda\x4e\x4a"
-			  "\xd4\x84\xa4\x53\xd5\x88\x73\x1b"
-			  "\xfd\xcb\xae\x0d\xf3\x04\xee\xe6",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
-			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 32,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x21\x52\x84\x15\xd1\xf7\x21\x55"
-			  "\xd9\x75\x4a\xd3\xc5\xdb\x9f\x7d"
-			  "\xda\x63\xb2\xf1\x82\xb0\x89\x59"
-			  "\x86\xd4\xaa\xaa\xdd\xff\x4f\x92",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x57\xb5\xf8\x71\x6e\x6d\xdd\x82"
-			  "\x53\xd0\xed\x2d\x30\xc1\x20\xef"
-			  "\x70\x67\x5e\xff\x09\x70\xbb\xc1"
-			  "\x3a\x7b\x48\x26\xd9\x0b\xf4\x48"
-			  "\xbe\xce\xb1\xc7\xb2\x67\xc4\xa7"
-			  "\x76\xf8\x36\x30\xb7\xb4\x9a\xd9"
-			  "\xf5\x9d\xd0\x7b\xc1\x06\x96\x44"
-			  "\x19\xc5\x58\x84\x63\xb9\x12\x68"
-			  "\x68\xc7\xaa\x18\x98\xf2\x1f\x5c"
-			  "\x39\xa6\xd8\x32\x2b\xc3\x51\xfd"
-			  "\x74\x79\x2e\xb4\x44\xd7\x69\xc4"
-			  "\xfc\x29\xe6\xed\x26\x1e\xa6\x9d"
-			  "\x1c\xbe\x00\x0e\x7f\x3a\xca\xfb"
-			  "\x6d\x13\x65\xa0\xf9\x31\x12\xe2"
-			  "\x26\xd1\xec\x2b\x0a\x8b\x59\x99"
-			  "\xa7\x49\xa0\x0e\x09\x33\x85\x50"
-			  "\xc3\x23\xca\x7a\xdd\x13\x45\x5f"
-			  "\xde\x4c\xa7\xcb\x00\x8a\x66\x6f"
-			  "\xa2\xb6\xb1\x2e\xe1\xa0\x18\xf6"
-			  "\xad\xf3\xbd\xeb\xc7\xef\x55\x4f"
-			  "\x79\x91\x8d\x36\x13\x7b\xd0\x4a"
-			  "\x6c\x39\xfb\x53\xb8\x6f\x02\x51"
-			  "\xa5\x20\xac\x24\x1c\x73\x59\x73"
-			  "\x58\x61\x3a\x87\x58\xb3\x20\x56"
-			  "\x39\x06\x2b\x4d\xd3\x20\x2b\x89"
-			  "\x3f\xa2\xf0\x96\xeb\x7f\xa4\xcd"
-			  "\x11\xae\xbd\xcb\x3a\xb4\xd9\x91"
-			  "\x09\x35\x71\x50\x65\xac\x92\xe3"
-			  "\x7b\x32\xc0\x7a\xdd\xd4\xc3\x92"
-			  "\x6f\xeb\x79\xde\x6f\xd3\x25\xc9"
-			  "\xcd\x63\xf5\x1e\x7a\x3b\x26\x9d"
-			  "\x77\x04\x80\xa9\xbf\x38\xb5\xbd"
-			  "\xb8\x05\x07\xbd\xfd\xab\x7b\xf8"
-			  "\x2a\x26\xcc\x49\x14\x6d\x55\x01"
-			  "\x06\x94\xd8\xb2\x2d\x53\x83\x1b"
-			  "\x8f\xd4\xdd\x57\x12\x7e\x18\xba"
-			  "\x8e\xe2\x4d\x80\xef\x7e\x6b\x9d"
-			  "\x24\xa9\x60\xa4\x97\x85\x86\x2a"
-			  "\x01\x00\x09\xf1\xcb\x4a\x24\x1c"
-			  "\xd8\xf6\xe6\x5b\xe7\x5d\xf2\xc4"
-			  "\x97\x1c\x10\xc6\x4d\x66\x4f\x98"
-			  "\x87\x30\xac\xd5\xea\x73\x49\x10"
-			  "\x80\xea\xe5\x5f\x4d\x5f\x03\x33"
-			  "\x66\x02\x35\x3d\x60\x06\x36\x4f"
-			  "\x14\x1c\xd8\x07\x1f\x78\xd0\xf8"
-			  "\x4f\x6c\x62\x7c\x15\xa5\x7c\x28"
-			  "\x7c\xcc\xeb\x1f\xd1\x07\x90\x93"
-			  "\x7e\xc2\xa8\x3a\x80\xc0\xf5\x30"
-			  "\xcc\x75\xcf\x16\x26\xa9\x26\x3b"
-			  "\xe7\x68\x2f\x15\x21\x5b\xe4\x00"
-			  "\xbd\x48\x50\xcd\x75\x70\xc4\x62"
-			  "\xbb\x41\xfb\x89\x4a\x88\x3b\x3b"
-			  "\x51\x66\x02\x69\x04\x97\x36\xd4"
-			  "\x75\xae\x0b\xa3\x42\xf8\xca\x79"
-			  "\x8f\x93\xe9\xcc\x38\xbd\xd6\xd2"
-			  "\xf9\x70\x4e\xc3\x6a\x8e\x25\xbd"
-			  "\xea\x15\x5a\xa0\x85\x7e\x81\x0d"
-			  "\x03\xe7\x05\x39\xf5\x05\x26\xee"
-			  "\xec\xaa\x1f\x3d\xc9\x98\x76\x01"
-			  "\x2c\xf4\xfc\xa3\x88\x77\x38\xc4"
-			  "\x50\x65\x50\x6d\x04\x1f\xdf\x5a"
-			  "\xaa\xf2\x01\xa9\xc1\x8d\xee\xca"
-			  "\x47\x26\xef\x39\xb8\xb4\xf2\xd1"
-			  "\xd6\xbb\x1b\x2a\xc1\x34\x14\xcf",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -15339,20 +10458,7 @@ static const struct cipher_testvec speck128_xts_dec_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x62\x49\x77\x57\x24\x70\x93\x69"
-			  "\x99\x59\x57\x49\x66\x96\x76\x27"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95"
-			  "\x02\x88\x41\x97\x16\x93\x99\x37"
-			  "\x51\x05\x82\x09\x74\x94\x45\x92",
-		.klen	= 64,
-		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xc5\x85\x2a\x4b\x73\xe4\xf6\xf1"
+		.ctext	= "\xc5\x85\x2a\x4b\x73\xe4\xf6\xf1"
 			  "\x7e\xf9\xf6\xe9\xa3\x73\x36\xcb"
 			  "\xaa\xb6\x22\xb0\x24\x6e\x3d\x73"
 			  "\x92\x99\xde\xd3\x76\xed\xcd\x63"
@@ -15416,124 +10522,36 @@ static const struct cipher_testvec speck128_xts_dec_tv_template[] = {
 			  "\x66\x8d\x13\xca\xe0\x59\x2a\x00"
 			  "\xc9\x53\x4c\xe6\x9e\xe2\x73\xd5"
 			  "\x67\x19\xb2\xbd\x9a\x63\xd7\x5c",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
 	}
 };
 
-static const struct cipher_testvec speck64_enc_tv_template[] = {
+static const struct cipher_testvec speck64_tv_template[] = {
 	{ /* Speck64/96 */
 		.key	= "\x00\x01\x02\x03\x08\x09\x0a\x0b"
 			  "\x10\x11\x12\x13",
 		.klen	= 12,
-		.input	= "\x65\x61\x6e\x73\x20\x46\x61\x74",
-		.ilen	= 8,
-		.result	= "\x6c\x94\x75\x41\xec\x52\x79\x9f",
-		.rlen	= 8,
+		.ptext	= "\x65\x61\x6e\x73\x20\x46\x61\x74",
+		.ctext	= "\x6c\x94\x75\x41\xec\x52\x79\x9f",
+		.len	= 8,
 	}, { /* Speck64/128 */
 		.key	= "\x00\x01\x02\x03\x08\x09\x0a\x0b"
 			  "\x10\x11\x12\x13\x18\x19\x1a\x1b",
 		.klen	= 16,
-		.input	= "\x2d\x43\x75\x74\x74\x65\x72\x3b",
-		.ilen	= 8,
-		.result	= "\x8b\x02\x4e\x45\x48\xa5\x6f\x8c",
-		.rlen	= 8,
-	},
-};
-
-static const struct cipher_testvec speck64_dec_tv_template[] = {
-	{ /* Speck64/96 */
-		.key	= "\x00\x01\x02\x03\x08\x09\x0a\x0b"
-			  "\x10\x11\x12\x13",
-		.klen	= 12,
-		.input	= "\x6c\x94\x75\x41\xec\x52\x79\x9f",
-		.ilen	= 8,
-		.result	= "\x65\x61\x6e\x73\x20\x46\x61\x74",
-		.rlen	= 8,
-	}, { /* Speck64/128 */
-		.key	= "\x00\x01\x02\x03\x08\x09\x0a\x0b"
-			  "\x10\x11\x12\x13\x18\x19\x1a\x1b",
-		.klen	= 16,
-		.input	= "\x8b\x02\x4e\x45\x48\xa5\x6f\x8c",
-		.ilen	= 8,
-		.result	= "\x2d\x43\x75\x74\x74\x65\x72\x3b",
-		.rlen	= 8,
+		.ptext	= "\x2d\x43\x75\x74\x74\x65\x72\x3b",
+		.ctext	= "\x8b\x02\x4e\x45\x48\xa5\x6f\x8c",
+		.len	= 8,
 	},
 };
 
 /*
- * Speck64-XTS test vectors, taken from the AES-XTS test vectors with the result
- * recomputed with Speck64 as the cipher, and key lengths adjusted
+ * Speck64-XTS test vectors, taken from the AES-XTS test vectors with the
+ * ciphertext recomputed with Speck64 as the cipher, and key lengths adjusted
  */
-
-static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
+static const struct cipher_testvec speck64_xts_tv_template[] = {
 	{
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -15541,16 +10559,15 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 32,
-		.result	= "\x84\xaf\x54\x07\x19\xd4\x7c\xa6"
+		.ctext	= "\x84\xaf\x54\x07\x19\xd4\x7c\xa6"
 			  "\xe4\xfe\xdf\xc4\x1f\x34\xc3\xc2"
 			  "\x80\xf5\x72\xe7\xcd\xf0\x99\x22"
 			  "\x35\xa7\x2f\x06\xef\xdc\x51\xaa",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
 			  "\x11\x11\x11\x11\x11\x11\x11\x11"
@@ -15558,16 +10575,15 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\x12\x56\x73\xcd\x15\x87\xa8\x59"
+		.ctext	= "\x12\x56\x73\xcd\x15\x87\xa8\x59"
 			  "\xcf\x84\xae\xd9\x1c\x66\xd6\x9f"
 			  "\xb3\x12\x69\x7e\x36\xeb\x52\xff"
 			  "\x62\xdd\xba\x90\xb3\xe1\xee\x99",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
 			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
@@ -15575,16 +10591,15 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\x15\x1b\xe4\x2c\xa2\x5a\x2d\x2c"
+		.ctext	= "\x15\x1b\xe4\x2c\xa2\x5a\x2d\x2c"
 			  "\x27\x36\xc0\xbf\x5d\xea\x36\x37"
 			  "\x2d\x1a\x88\xbc\x66\xb5\xd0\x0b"
 			  "\xa1\xbc\x19\xb2\x0f\x3b\x75\x34",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -15592,7 +10607,7 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -15656,8 +10671,7 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\xaf\xa1\x81\xa6\x32\xbb\x15\x8e"
+		.ctext	= "\xaf\xa1\x81\xa6\x32\xbb\x15\x8e"
 			  "\xf8\x95\x2e\xd3\xe6\xee\x7e\x09"
 			  "\x0c\x1a\xf5\x02\x97\x8b\xe3\xb3"
 			  "\x11\xc7\x39\x96\xd0\x95\xf4\x56"
@@ -15721,7 +10735,7 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 			  "\x50\xf7\x5f\xf4\xc2\xca\x41\x97"
 			  "\x37\xbe\x75\x74\xcd\xf0\x75\x6e"
 			  "\x25\x23\x94\xbd\xda\x8d\xb0\xd4",
-		.rlen	= 512,
+		.len	= 512,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -15730,7 +10744,7 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -15794,8 +10808,7 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\x55\xed\x71\xd3\x02\x8e\x15\x3b"
+		.ctext	= "\x55\xed\x71\xd3\x02\x8e\x15\x3b"
 			  "\xc6\x71\x29\x2d\x3e\x89\x9f\x59"
 			  "\x68\x6a\xcc\x8a\x56\x97\xf3\x95"
 			  "\x4e\x51\x08\xda\x2a\xf8\x6f\x3c"
@@ -15859,340 +10872,7 @@ static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
 			  "\x9b\x63\x76\x32\x2f\x19\x72\x10"
 			  "\x9f\x21\x0c\xf1\x66\x50\x7f\xa5"
 			  "\x0d\x1f\x46\xe0\xba\xd3\x2f\x3c",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	}
-};
-
-static const struct cipher_testvec speck64_xts_dec_tv_template[] = {
-	{
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 24,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x84\xaf\x54\x07\x19\xd4\x7c\xa6"
-			  "\xe4\xfe\xdf\xc4\x1f\x34\xc3\xc2"
-			  "\x80\xf5\x72\xe7\xcd\xf0\x99\x22"
-			  "\x35\xa7\x2f\x06\xef\xdc\x51\xaa",
-		.ilen	= 32,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 32,
-	}, {
-		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 24,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x12\x56\x73\xcd\x15\x87\xa8\x59"
-			  "\xcf\x84\xae\xd9\x1c\x66\xd6\x9f"
-			  "\xb3\x12\x69\x7e\x36\xeb\x52\xff"
-			  "\x62\xdd\xba\x90\xb3\xe1\xee\x99",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
-			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 24,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x15\x1b\xe4\x2c\xa2\x5a\x2d\x2c"
-			  "\x27\x36\xc0\xbf\x5d\xea\x36\x37"
-			  "\x2d\x1a\x88\xbc\x66\xb5\xd0\x0b"
-			  "\xa1\xbc\x19\xb2\x0f\x3b\x75\x34",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93",
-		.klen	= 24,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xaf\xa1\x81\xa6\x32\xbb\x15\x8e"
-			  "\xf8\x95\x2e\xd3\xe6\xee\x7e\x09"
-			  "\x0c\x1a\xf5\x02\x97\x8b\xe3\xb3"
-			  "\x11\xc7\x39\x96\xd0\x95\xf4\x56"
-			  "\xf4\xdd\x03\x38\x01\x44\x2c\xcf"
-			  "\x88\xae\x8e\x3c\xcd\xe7\xaa\x66"
-			  "\xfe\x3d\xc6\xfb\x01\x23\x51\x43"
-			  "\xd5\xd2\x13\x86\x94\x34\xe9\x62"
-			  "\xf9\x89\xe3\xd1\x7b\xbe\xf8\xef"
-			  "\x76\x35\x04\x3f\xdb\x23\x9d\x0b"
-			  "\x85\x42\xb9\x02\xd6\xcc\xdb\x96"
-			  "\xa7\x6b\x27\xb6\xd4\x45\x8f\x7d"
-			  "\xae\xd2\x04\xd5\xda\xc1\x7e\x24"
-			  "\x8c\x73\xbe\x48\x7e\xcf\x65\x28"
-			  "\x29\xe5\xbe\x54\x30\xcb\x46\x95"
-			  "\x4f\x2e\x8a\x36\xc8\x27\xc5\xbe"
-			  "\xd0\x1a\xaf\xab\x26\xcd\x9e\x69"
-			  "\xa1\x09\x95\x71\x26\xe9\xc4\xdf"
-			  "\xe6\x31\xc3\x46\xda\xaf\x0b\x41"
-			  "\x1f\xab\xb1\x8e\xd6\xfc\x0b\xb3"
-			  "\x82\xc0\x37\x27\xfc\x91\xa7\x05"
-			  "\xfb\xc5\xdc\x2b\x74\x96\x48\x43"
-			  "\x5d\x9c\x19\x0f\x60\x63\x3a\x1f"
-			  "\x6f\xf0\x03\xbe\x4d\xfd\xc8\x4a"
-			  "\xc6\xa4\x81\x6d\xc3\x12\x2a\x5c"
-			  "\x07\xff\xf3\x72\x74\x48\xb5\x40"
-			  "\x50\xb5\xdd\x90\x43\x31\x18\x15"
-			  "\x7b\xf2\xa6\xdb\x83\xc8\x4b\x4a"
-			  "\x29\x93\x90\x8b\xda\x07\xf0\x35"
-			  "\x6d\x90\x88\x09\x4e\x83\xf5\x5b"
-			  "\x94\x12\xbb\x33\x27\x1d\x3f\x23"
-			  "\x51\xa8\x7c\x07\xa2\xae\x77\xa6"
-			  "\x50\xfd\xcc\xc0\x4f\x80\x7a\x9f"
-			  "\x66\xdd\xcd\x75\x24\x8b\x33\xf7"
-			  "\x20\xdb\x83\x9b\x4f\x11\x63\x6e"
-			  "\xcf\x37\xef\xc9\x11\x01\x5c\x45"
-			  "\x32\x99\x7c\x3c\x9e\x42\x89\xe3"
-			  "\x70\x6d\x15\x9f\xb1\xe6\xb6\x05"
-			  "\xfe\x0c\xb9\x49\x2d\x90\x6d\xcc"
-			  "\x5d\x3f\xc1\xfe\x89\x0a\x2e\x2d"
-			  "\xa0\xa8\x89\x3b\x73\x39\xa5\x94"
-			  "\x4c\xa4\xa6\xbb\xa7\x14\x46\x89"
-			  "\x10\xff\xaf\xef\xca\xdd\x4f\x80"
-			  "\xb3\xdf\x3b\xab\xd4\xe5\x5a\xc7"
-			  "\x33\xca\x00\x8b\x8b\x3f\xea\xec"
-			  "\x68\x8a\xc2\x6d\xfd\xd4\x67\x0f"
-			  "\x22\x31\xe1\x0e\xfe\x5a\x04\xd5"
-			  "\x64\xa3\xf1\x1a\x76\x28\xcc\x35"
-			  "\x36\xa7\x0a\x74\xf7\x1c\x44\x9b"
-			  "\xc7\x1b\x53\x17\x02\xea\xd1\xad"
-			  "\x13\x51\x73\xc0\xa0\xb2\x05\x32"
-			  "\xa8\xa2\x37\x2e\xe1\x7a\x3a\x19"
-			  "\x26\xb4\x6c\x62\x5d\xb3\x1a\x1d"
-			  "\x59\xda\xee\x1a\x22\x18\xda\x0d"
-			  "\x88\x0f\x55\x8b\x72\x62\xfd\xc1"
-			  "\x69\x13\xcd\x0d\x5f\xc1\x09\x52"
-			  "\xee\xd6\xe3\x84\x4d\xee\xf6\x88"
-			  "\xaf\x83\xdc\x76\xf4\xc0\x93\x3f"
-			  "\x4a\x75\x2f\xb0\x0b\x3e\xc4\x54"
-			  "\x7d\x69\x8d\x00\x62\x77\x0d\x14"
-			  "\xbe\x7c\xa6\x7d\xc5\x24\x4f\xf3"
-			  "\x50\xf7\x5f\xf4\xc2\xca\x41\x97"
-			  "\x37\xbe\x75\x74\xcd\xf0\x75\x6e"
-			  "\x25\x23\x94\xbd\xda\x8d\xb0\xd4",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x62\x49\x77\x57\x24\x70\x93\x69"
-			  "\x99\x59\x57\x49\x66\x96\x76\x27",
-		.klen	= 32,
-		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x55\xed\x71\xd3\x02\x8e\x15\x3b"
-			  "\xc6\x71\x29\x2d\x3e\x89\x9f\x59"
-			  "\x68\x6a\xcc\x8a\x56\x97\xf3\x95"
-			  "\x4e\x51\x08\xda\x2a\xf8\x6f\x3c"
-			  "\x78\x16\xea\x80\xdb\x33\x75\x94"
-			  "\xf9\x29\xc4\x2b\x76\x75\x97\xc7"
-			  "\xf2\x98\x2c\xf9\xff\xc8\xd5\x2b"
-			  "\x18\xf1\xaf\xcf\x7c\xc5\x0b\xee"
-			  "\xad\x3c\x76\x7c\xe6\x27\xa2\x2a"
-			  "\xe4\x66\xe1\xab\xa2\x39\xfc\x7c"
-			  "\xf5\xec\x32\x74\xa3\xb8\x03\x88"
-			  "\x52\xfc\x2e\x56\x3f\xa1\xf0\x9f"
-			  "\x84\x5e\x46\xed\x20\x89\xb6\x44"
-			  "\x8d\xd0\xed\x54\x47\x16\xbe\x95"
-			  "\x8a\xb3\x6b\x72\xc4\x32\x52\x13"
-			  "\x1b\xb0\x82\xbe\xac\xf9\x70\xa6"
-			  "\x44\x18\xdd\x8c\x6e\xca\x6e\x45"
-			  "\x8f\x1e\x10\x07\x57\x25\x98\x7b"
-			  "\x17\x8c\x78\xdd\x80\xa7\xd9\xd8"
-			  "\x63\xaf\xb9\x67\x57\xfd\xbc\xdb"
-			  "\x44\xe9\xc5\x65\xd1\xc7\x3b\xff"
-			  "\x20\xa0\x80\x1a\xc3\x9a\xad\x5e"
-			  "\x5d\x3b\xd3\x07\xd9\xf5\xfd\x3d"
-			  "\x4a\x8b\xa8\xd2\x6e\x7a\x51\x65"
-			  "\x6c\x8e\x95\xe0\x45\xc9\x5f\x4a"
-			  "\x09\x3c\x3d\x71\x7f\x0c\x84\x2a"
-			  "\xc8\x48\x52\x1a\xc2\xd5\xd6\x78"
-			  "\x92\x1e\xa0\x90\x2e\xea\xf0\xf3"
-			  "\xdc\x0f\xb1\xaf\x0d\x9b\x06\x2e"
-			  "\x35\x10\x30\x82\x0d\xe7\xc5\x9b"
-			  "\xde\x44\x18\xbd\x9f\xd1\x45\xa9"
-			  "\x7b\x7a\x4a\xad\x35\x65\x27\xca"
-			  "\xb2\xc3\xd4\x9b\x71\x86\x70\xee"
-			  "\xf1\x89\x3b\x85\x4b\x5b\xaa\xaf"
-			  "\xfc\x42\xc8\x31\x59\xbe\x16\x60"
-			  "\x4f\xf9\xfa\x12\xea\xd0\xa7\x14"
-			  "\xf0\x7a\xf3\xd5\x8d\xbd\x81\xef"
-			  "\x52\x7f\x29\x51\x94\x20\x67\x3c"
-			  "\xd1\xaf\x77\x9f\x22\x5a\x4e\x63"
-			  "\xe7\xff\x73\x25\xd1\xdd\x96\x8a"
-			  "\x98\x52\x6d\xf3\xac\x3e\xf2\x18"
-			  "\x6d\xf6\x0a\x29\xa6\x34\x3d\xed"
-			  "\xe3\x27\x0d\x9d\x0a\x02\x44\x7e"
-			  "\x5a\x7e\x67\x0f\x0a\x9e\xd6\xad"
-			  "\x91\xe6\x4d\x81\x8c\x5c\x59\xaa"
-			  "\xfb\xeb\x56\x53\xd2\x7d\x4c\x81"
-			  "\x65\x53\x0f\x41\x11\xbd\x98\x99"
-			  "\xf9\xc6\xfa\x51\x2e\xa3\xdd\x8d"
-			  "\x84\x98\xf9\x34\xed\x33\x2a\x1f"
-			  "\x82\xed\xc1\x73\x98\xd3\x02\xdc"
-			  "\xe6\xc2\x33\x1d\xa2\xb4\xca\x76"
-			  "\x63\x51\x34\x9d\x96\x12\xae\xce"
-			  "\x83\xc9\x76\x5e\xa4\x1b\x53\x37"
-			  "\x17\xd5\xc0\x80\x1d\x62\xf8\x3d"
-			  "\x54\x27\x74\xbb\x10\x86\x57\x46"
-			  "\x68\xe1\xed\x14\xe7\x9d\xfc\x84"
-			  "\x47\xbc\xc2\xf8\x19\x4b\x99\xcf"
-			  "\x7a\xe9\xc4\xb8\x8c\x82\x72\x4d"
-			  "\x7b\x4f\x38\x55\x36\x71\x64\xc1"
-			  "\xfc\x5c\x75\x52\x33\x02\x18\xf8"
-			  "\x17\xe1\x2b\xc2\x43\x39\xbd\x76"
-			  "\x9b\x63\x76\x32\x2f\x19\x72\x10"
-			  "\x9f\x21\x0c\xf1\x66\x50\x7f\xa5"
-			  "\x0d\x1f\x46\xe0\xba\xd3\x2f\x3c",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
@@ -16200,37 +10880,34 @@ static const struct cipher_testvec speck64_xts_dec_tv_template[] = {
 };
 
 /* Cast6 test vectors from RFC 2612 */
-static const struct cipher_testvec cast6_enc_tv_template[] = {
+static const struct cipher_testvec cast6_tv_template[] = {
 	{
 		.key	= "\x23\x42\xbb\x9e\xfa\x38\x54\x2c"
 			  "\x0a\xf7\x56\x47\xf2\x9f\x61\x5d",
 		.klen	= 16,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\xc8\x42\xa0\x89\x72\xb4\x3d\x20"
+		.ptext	= zeroed_string,
+		.ctext	= "\xc8\x42\xa0\x89\x72\xb4\x3d\x20"
 			  "\x83\x6c\x91\xd1\xb7\x53\x0f\x6b",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x23\x42\xbb\x9e\xfa\x38\x54\x2c"
 			  "\xbe\xd0\xac\x83\x94\x0a\xc2\x98"
 			  "\xba\xc7\x7a\x77\x17\x94\x28\x63",
 		.klen	= 24,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\x1b\x38\x6c\x02\x10\xdc\xad\xcb"
+		.ptext	= zeroed_string,
+		.ctext	= "\x1b\x38\x6c\x02\x10\xdc\xad\xcb"
 			  "\xdd\x0e\x41\xaa\x08\xa7\xa7\xe8",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x23\x42\xbb\x9e\xfa\x38\x54\x2c"
 			  "\xbe\xd0\xac\x83\x94\x0a\xc2\x98"
 			  "\x8d\x7c\x47\xce\x26\x49\x08\x46"
 			  "\x1c\xc1\xb5\x13\x7a\xe6\xb6\x04",
 		.klen	= 32,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\x4f\x6a\x20\x38\x28\x68\x97\xb9"
+		.ptext	= zeroed_string,
+		.ctext	= "\x4f\x6a\x20\x38\x28\x68\x97\xb9"
 			  "\xc9\x87\x01\x36\x55\x33\x17\xfa",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -16239,7 +10916,7 @@ static const struct cipher_testvec cast6_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -16301,116 +10978,7 @@ static const struct cipher_testvec cast6_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\xC3\x70\x22\x32\xF5\x80\xCB\x54"
-			  "\xFC\x30\xE0\xF6\xEB\x39\x57\xA6"
-			  "\xB6\xB9\xC5\xA4\x91\x55\x14\x97"
-			  "\xC1\x20\xFF\x6C\x5C\xF0\x67\xEA"
-			  "\x2F\xED\xD8\xC9\xFB\x38\x3F\xFE"
-			  "\x93\xBE\xDC\x00\xD3\x7F\xAD\x4C"
-			  "\x5A\x08\x92\xD1\x47\x0C\xFA\x6C"
-			  "\xD0\x6A\x99\x10\x72\xF8\x47\x62"
-			  "\x81\x42\xF8\xD8\xF5\xBB\x94\x08"
-			  "\xAA\x97\xA2\x8B\x69\xB3\xD2\x7E"
-			  "\xBC\xB5\x00\x0C\xE5\x44\x4B\x58"
-			  "\xE8\x63\xDC\xB3\xC4\xE5\x23\x12"
-			  "\x5A\x72\x85\x47\x8B\xEC\x9F\x26"
-			  "\x84\xB6\xED\x10\x33\x63\x9B\x5F"
-			  "\x4D\x53\xEE\x94\x45\x8B\x60\x58"
-			  "\x86\x20\xF9\x1E\x82\x08\x3E\x58"
-			  "\x60\x1B\x34\x19\x02\xBE\x4E\x09"
-			  "\xBB\x7C\x15\xCC\x60\x27\x55\x7A"
-			  "\x12\xB8\xD8\x08\x89\x3C\xA6\xF3"
-			  "\xF1\xDD\xA7\x07\xA3\x12\x85\x28"
-			  "\xE9\x57\xAC\x80\x0C\x5C\x0F\x3A"
-			  "\x5D\xC2\x91\xC7\x90\xE4\x8C\x43"
-			  "\x92\xE4\x7C\x26\x69\x4D\x83\x68"
-			  "\x14\x96\x42\x47\xBD\xA9\xE4\x8A"
-			  "\x33\x19\xEB\x54\x8E\x0D\x4B\x6E"
-			  "\x91\x51\xB5\x36\x08\xDE\x1C\x06"
-			  "\x03\xBD\xDE\x81\x26\xF7\x99\xC2"
-			  "\xBA\xF7\x6D\x87\x0D\xE4\xA6\xCF"
-			  "\xC1\xF5\x27\x05\xB8\x02\x57\x72"
-			  "\xE6\x42\x13\x0B\xC6\x47\x05\x74"
-			  "\x24\x15\xF7\x0D\xC2\x23\x9D\xB9"
-			  "\x3C\x77\x18\x93\xBA\xB4\xFC\x8C"
-			  "\x98\x82\x67\x67\xB4\xD7\xD3\x43"
-			  "\x23\x08\x02\xB7\x9B\x99\x05\xFB"
-			  "\xD3\xB5\x00\x0A\xA9\x9D\x66\xD6"
-			  "\x2E\x49\x58\xD0\xA8\x57\x29\x7F"
-			  "\x0A\x0E\x7D\xFC\x92\x83\xCC\x67"
-			  "\xA2\xB1\x70\x3A\x8F\x87\x4A\x8D"
-			  "\x17\xE2\x58\x2B\x88\x0D\x68\x62"
-			  "\xBF\x35\xD1\x6F\xC0\xF0\x18\x62"
-			  "\xB2\xC7\x2D\x58\xC7\x16\xDE\x08"
-			  "\xEB\x84\x1D\x25\xA7\x38\x94\x06"
-			  "\x93\x9D\xF8\xFE\x88\x71\xE7\x84"
-			  "\x2C\xA0\x38\xA3\x1D\x48\xCF\x29"
-			  "\x0B\xBC\xD8\x50\x99\x1A\x26\xFB"
-			  "\x8E\x75\x3D\x73\xEB\x6A\xED\x29"
-			  "\xE0\x8E\xED\xFC\xFE\x6F\xF6\xBA"
-			  "\x41\xE2\x10\x4C\x01\x8B\x69\x2B"
-			  "\x25\x3F\x4D\x70\x7B\x92\xD6\x3B"
-			  "\xAC\xF9\x77\x18\xD9\x6A\x30\xA6"
-			  "\x2E\xFA\x30\xFF\xC8\xD5\x1D\x06"
-			  "\x59\x28\x1D\x86\x43\x04\x5D\x3B"
-			  "\x99\x4C\x04\x5A\x21\x17\x8B\x76"
-			  "\x8F\x72\xCB\xA1\x9C\x29\x4C\xC3"
-			  "\x65\xA2\x58\x2A\xC5\x66\x24\xBF"
-			  "\xBA\xE6\x0C\xDD\x34\x24\x74\xC8"
-			  "\x84\x0A\x66\x2C\xBE\x8F\x32\xA9"
-			  "\xE7\xE4\xA1\xD7\xDA\xAB\x23\x1E"
-			  "\xEB\xEE\x6C\x94\x6F\x9C\x2E\xD1"
-			  "\x49\x2C\xF3\xD4\x90\xCC\x93\x4C"
-			  "\x84\x52\x6D\x68\xDE\xC6\x64\xB2"
-			  "\x11\x74\x93\x57\xB4\x7E\xC6\x00",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec cast6_dec_tv_template[] = {
-	{
-		.key	= "\x23\x42\xbb\x9e\xfa\x38\x54\x2c"
-			  "\x0a\xf7\x56\x47\xf2\x9f\x61\x5d",
-		.klen	= 16,
-		.input	= "\xc8\x42\xa0\x89\x72\xb4\x3d\x20"
-			  "\x83\x6c\x91\xd1\xb7\x53\x0f\x6b",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, {
-		.key	= "\x23\x42\xbb\x9e\xfa\x38\x54\x2c"
-			  "\xbe\xd0\xac\x83\x94\x0a\xc2\x98"
-			  "\xba\xc7\x7a\x77\x17\x94\x28\x63",
-		.klen	= 24,
-		.input	= "\x1b\x38\x6c\x02\x10\xdc\xad\xcb"
-			  "\xdd\x0e\x41\xaa\x08\xa7\xa7\xe8",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, {
-		.key	= "\x23\x42\xbb\x9e\xfa\x38\x54\x2c"
-			  "\xbe\xd0\xac\x83\x94\x0a\xc2\x98"
-			  "\x8d\x7c\x47\xce\x26\x49\x08\x46"
-			  "\x1c\xc1\xb5\x13\x7a\xe6\xb6\x04",
-		.klen	= 32,
-		.input	= "\x4f\x6a\x20\x38\x28\x68\x97\xb9"
-			  "\xc9\x87\x01\x36\x55\x33\x17\xfa",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, { /* Generated from TF test vectors */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\xC3\x70\x22\x32\xF5\x80\xCB\x54"
+		.ctext	= "\xC3\x70\x22\x32\xF5\x80\xCB\x54"
 			  "\xFC\x30\xE0\xF6\xEB\x39\x57\xA6"
 			  "\xB6\xB9\xC5\xA4\x91\x55\x14\x97"
 			  "\xC1\x20\xFF\x6C\x5C\xF0\x67\xEA"
@@ -16472,77 +11040,14 @@ static const struct cipher_testvec cast6_dec_tv_template[] = {
 			  "\x49\x2C\xF3\xD4\x90\xCC\x93\x4C"
 			  "\x84\x52\x6D\x68\xDE\xC6\x64\xB2"
 			  "\x11\x74\x93\x57\xB4\x7E\xC6\x00",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec cast6_cbc_enc_tv_template[] = {
+static const struct cipher_testvec cast6_cbc_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -16551,7 +11056,7 @@ static const struct cipher_testvec cast6_cbc_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -16613,8 +11118,7 @@ static const struct cipher_testvec cast6_cbc_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\xDF\x77\x68\x96\xC7\xBA\xF8\xE2"
+		.ctext	= "\xDF\x77\x68\x96\xC7\xBA\xF8\xE2"
 			  "\x0E\x24\x99\x1A\xAA\xF3\xC6\x9F"
 			  "\xA0\x73\xB3\x70\xC3\x68\x64\x70"
 			  "\xAD\x33\x02\xFB\x88\x74\xAA\x78"
@@ -16676,14 +11180,14 @@ static const struct cipher_testvec cast6_cbc_enc_tv_template[] = {
 			  "\xC5\x5C\xAD\xB6\x07\xB6\x84\xF3"
 			  "\x4D\x59\x7D\xC5\x28\x69\xFA\x92"
 			  "\x22\x46\x89\x2D\x0F\x2B\x08\x24",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec cast6_cbc_dec_tv_template[] = {
+static const struct cipher_testvec cast6_ctr_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -16692,155 +11196,13 @@ static const struct cipher_testvec cast6_cbc_dec_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\xDF\x77\x68\x96\xC7\xBA\xF8\xE2"
-			  "\x0E\x24\x99\x1A\xAA\xF3\xC6\x9F"
-			  "\xA0\x73\xB3\x70\xC3\x68\x64\x70"
-			  "\xAD\x33\x02\xFB\x88\x74\xAA\x78"
-			  "\xC7\x47\x1A\x18\x61\x2D\xAC\x9F"
-			  "\x7E\x6F\xDF\x05\x13\x76\xA6\x72"
-			  "\xB7\x13\x09\x0F\x7D\x38\xDF\x25"
-			  "\x4E\xFD\x50\x45\xFA\x35\x6A\xC0"
-			  "\x57\x95\xE1\x21\x26\x10\x9A\x21"
-			  "\xA1\x8A\x51\x05\xD1\xB1\x78\x35"
-			  "\x98\xF5\xAE\xC0\xC1\x8B\x94\xFF"
-			  "\xD0\x69\x3F\x42\xC2\x01\xA7\x9B"
-			  "\x23\x16\x47\x72\x81\x13\x3A\x72"
-			  "\xEC\xD9\x40\x88\x00\x9C\xB0\xA8"
-			  "\x9C\xAC\xCE\x11\x73\x7B\x63\x3E"
-			  "\xA3\x63\x98\x7D\x35\xE4\xD9\x83"
-			  "\xE2\xD0\x52\x87\x0C\x1F\xB0\xB3"
-			  "\x41\x1A\x93\x8D\x76\x31\x9F\xF2"
-			  "\xFE\x09\xA3\x8F\x22\x6A\x3B\xB9"
-			  "\x6C\x9E\xE4\xA1\xA0\xC4\xE7\xA1"
-			  "\x21\x9C\x1A\xCA\x65\xDE\x44\x03"
-			  "\x99\xF2\xD2\x39\xE3\x3F\x0F\x37"
-			  "\x53\x50\x23\xA4\x81\x6E\xDA\xFB"
-			  "\xF8\x7B\x01\xD7\xB2\x32\x9C\xB8"
-			  "\xB1\x0E\x99\x17\xB5\x38\xF9\xD7"
-			  "\x86\x2D\x6E\x94\x5C\x99\x9D\xB3"
-			  "\xD3\x63\x4B\x2A\x7D\x44\x6A\xB2"
-			  "\xC1\x03\xE6\x5A\x37\xD8\x64\x18"
-			  "\xAA\x32\xCE\x29\xED\xC0\xA2\xCB"
-			  "\x8D\xAF\xCD\xBE\x8F\xB6\xEC\xB4"
-			  "\x89\x05\x81\x6E\x71\x4F\xC3\x28"
-			  "\x10\xC1\x62\xC4\x41\xE9\xD2\x39"
-			  "\xF3\x22\x39\x12\x2C\xC2\x95\x2D"
-			  "\xBF\x93\x58\x4B\x04\xD1\x8D\x57"
-			  "\xAE\xEB\x60\x03\x56\x35\xAD\x5A"
-			  "\xE9\xC3\xFF\x4E\x31\xE1\x37\xF8"
-			  "\x7D\xEE\x65\x8A\xB6\x88\x1A\x3E"
-			  "\x07\x09\x82\xBA\xF0\x80\x8A\xD0"
-			  "\xA0\x3F\x6A\xE9\x24\x87\x19\x65"
-			  "\x73\x3F\x12\x91\x47\x54\xBA\x39"
-			  "\x30\x5B\x1E\xE5\xC2\xF9\x3F\xEF"
-			  "\xD6\x75\xF9\xB8\x7C\x8B\x05\x76"
-			  "\xEE\xB7\x08\x25\x4B\xB6\x7B\x47"
-			  "\x72\xC0\x4C\xD4\xDA\xE0\x75\xF1"
-			  "\x7C\xE8\x94\x9E\x16\x6E\xB8\x12"
-			  "\xA1\xC1\x6E\x3B\x1C\x59\x41\x2D"
-			  "\x23\xFA\x7D\x77\xB8\x46\x75\xFE"
-			  "\x4F\x10\xD3\x09\x60\xA1\x36\x96"
-			  "\x5B\xC2\xDC\x6E\x84\x7D\x9B\x14"
-			  "\x80\x21\x83\x58\x3C\x76\xFD\x28"
-			  "\x1D\xF9\x93\x13\xD7\x0E\x62\x14"
-			  "\x5A\xC5\x4E\x08\xA5\x56\xA4\x3C"
-			  "\x68\x93\x44\x70\xDF\xCF\x4A\x51"
-			  "\x0B\x81\x29\x41\xE5\x62\x4D\x36"
-			  "\xB3\xEA\x94\xA6\xB9\xDD\x3F\x09"
-			  "\x62\x34\xA0\x6A\x7E\x7D\xF5\xF6"
-			  "\x01\x91\xB4\x27\xDA\x59\xD6\x17"
-			  "\x56\x4D\x82\x62\x37\xA3\x48\x01"
-			  "\x99\x91\x77\xB2\x08\x6B\x2C\x37"
-			  "\xC5\x5C\xAD\xB6\x07\xB6\x84\xF3"
-			  "\x4D\x59\x7D\xC5\x28\x69\xFA\x92"
-			  "\x22\x46\x89\x2D\x0F\x2B\x08\x24",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec cast6_ctr_enc_tv_template[] = {
-	{ /* Generated from TF test vectors */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A",
-		.ilen	= 17,
-		.result	= "\x26\x0A\xF1\xE2\x3F\x8A\xEF\xA3"
+		.ctext	= "\x26\x0A\xF1\xE2\x3F\x8A\xEF\xA3"
 			  "\x53\x9A\x5E\x1B\x2A\x1A\xC6\x0A"
 			  "\x57",
-		.rlen	= 17,
+		.len	= 17,
 	}, { /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -16849,7 +11211,7 @@ static const struct cipher_testvec cast6_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -16911,8 +11273,7 @@ static const struct cipher_testvec cast6_ctr_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\x26\x0A\xF1\xE2\x3F\x8A\xEF\xA3"
+		.ctext	= "\x26\x0A\xF1\xE2\x3F\x8A\xEF\xA3"
 			  "\x53\x9A\x5E\x1B\x2A\x1A\xC6\x0A"
 			  "\x57\xA3\xEF\x47\x2A\xE8\x88\xA7"
 			  "\x3C\xD0\xEC\xB9\x94\x50\x7D\x56"
@@ -16974,171 +11335,14 @@ static const struct cipher_testvec cast6_ctr_enc_tv_template[] = {
 			  "\x9B\x66\x8D\x32\xBA\x81\x34\x87"
 			  "\x0E\x74\x33\x30\x62\xB9\x89\xDF"
 			  "\xF9\xC5\xDD\x27\xB3\x39\xCB\xCB",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec cast6_ctr_dec_tv_template[] = {
-	{ /* Generated from TF test vectors */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x26\x0A\xF1\xE2\x3F\x8A\xEF\xA3"
-			  "\x53\x9A\x5E\x1B\x2A\x1A\xC6\x0A"
-			  "\x57",
-		.ilen	= 17,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A",
-		.rlen	= 17,
-	}, { /* Generated from TF test vectors */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x26\x0A\xF1\xE2\x3F\x8A\xEF\xA3"
-			  "\x53\x9A\x5E\x1B\x2A\x1A\xC6\x0A"
-			  "\x57\xA3\xEF\x47\x2A\xE8\x88\xA7"
-			  "\x3C\xD0\xEC\xB9\x94\x50\x7D\x56"
-			  "\xBC\xE1\xC1\xF5\xE1\xEE\x12\xF8"
-			  "\x4F\x03\x82\x3A\x93\x6B\x4C\xD3"
-			  "\xE3\xF3\xFA\xC2\x23\x55\x98\x20"
-			  "\x49\x76\x9B\x6B\xC1\x23\xBF\xE5"
-			  "\xD4\xC4\x2F\x61\xE1\x67\x2A\x30"
-			  "\x6F\x29\xCA\x54\xF8\x1B\xA6\x7D"
-			  "\x66\x45\xEE\xC8\x19\xBE\x50\xF0"
-			  "\x5F\x65\xF8\x1E\x4D\x07\x87\xD9"
-			  "\xD3\xD9\x1B\x09\x89\xFD\x42\xC5"
-			  "\xDB\xEB\x86\xF1\x67\x04\x0F\x5C"
-			  "\x81\xDF\x82\x12\xC7\x4C\x1B\x07"
-			  "\xDE\xE6\xFA\x29\x86\xD1\xB0\xBA"
-			  "\x3D\x6A\x69\x76\xEC\x0F\xB4\xE6"
-			  "\xCD\xA7\xF8\xA8\xB8\xE0\x33\xF5"
-			  "\x49\x61\x22\x52\x64\x8C\x46\x41"
-			  "\x1F\x48\x5F\x4F\xA2\x89\x36\x17"
-			  "\x20\xF8\x2F\x8F\x4B\xFA\xF2\xC0"
-			  "\x1E\x18\xA2\xF8\xB7\x6D\x98\xE3"
-			  "\x00\x14\x15\x59\xC1\x30\x64\xAF"
-			  "\xA8\x01\x38\xAB\xD4\x8B\xEC\x7C"
-			  "\x44\x9A\xC6\x2C\x2E\x2B\x2B\xF4"
-			  "\x02\x37\xC4\x69\xEF\x36\xC1\xF3"
-			  "\xA0\xFB\xFE\x29\xAD\x39\xCF\xD0"
-			  "\x51\x73\xA3\x22\x42\x41\xAB\xD2"
-			  "\x0F\x50\x14\xB9\x54\xD3\xD4\xFA"
-			  "\xBF\xC9\xBB\xCE\xC4\x1D\x2D\xAF"
-			  "\xC9\x3F\x07\x87\x42\x4B\x3A\x54"
-			  "\x34\x8E\x37\xA3\x03\x6F\x65\x66"
-			  "\xDB\x44\xC3\xE8\xD7\xDD\x7D\xDD"
-			  "\x61\xB4\x2B\x80\xA3\x98\x13\xF5"
-			  "\x5A\xD3\x34\x58\xC3\x6E\xF6\xB8"
-			  "\x0A\xC6\x50\x01\x8E\xD5\x6C\x7D"
-			  "\xFE\x16\xB6\xCF\xFC\x51\x40\xAE"
-			  "\xB3\x15\xAC\x90\x6F\x0B\x28\x3A"
-			  "\x60\x40\x38\x90\x20\x46\xC7\xB3"
-			  "\x0B\x12\x6D\x3B\x15\x14\xF9\xF4"
-			  "\x11\x41\x76\x6B\xB3\x60\x82\x3C"
-			  "\x84\xFB\x08\x2E\x92\x25\xCB\x79"
-			  "\x6F\x58\xC5\x94\x00\x00\x47\xB6"
-			  "\x9E\xDC\x0F\x29\x70\x46\x20\x76"
-			  "\x65\x75\x66\x5C\x00\x96\xB3\xE1"
-			  "\x0B\xA7\x11\x8B\x2E\x61\x4E\x45"
-			  "\x73\xFC\x91\xAB\x79\x41\x23\x14"
-			  "\x13\xB6\x72\x6C\x46\xB3\x03\x11"
-			  "\xE4\xF1\xEE\xC9\x7A\xCF\x96\x32"
-			  "\xB6\xF0\x8B\x97\xB4\xCF\x82\xB7"
-			  "\x15\x48\x44\x99\x09\xF6\xE0\xD7"
-			  "\xBC\xF1\x5B\x91\x4F\x30\x22\xA2"
-			  "\x45\xC4\x68\x55\xC2\xBE\xA7\xD2"
-			  "\x12\x53\x35\x9C\xF9\xE7\x35\x5D"
-			  "\x81\xE4\x86\x42\xC3\x58\xFB\xF0"
-			  "\x38\x9B\x8E\x5A\xEF\x83\x33\x0F"
-			  "\x00\x4E\x3F\x9F\xF5\x84\x62\xC4"
-			  "\x19\x35\x88\x22\x45\x59\x0E\x8F"
-			  "\xEC\x27\xDD\x4A\xA4\x1F\xBC\x41"
-			  "\x9B\x66\x8D\x32\xBA\x81\x34\x87"
-			  "\x0E\x74\x33\x30\x62\xB9\x89\xDF"
-			  "\xF9\xC5\xDD\x27\xB3\x39\xCB\xCB",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec cast6_lrw_enc_tv_template[] = {
+static const struct cipher_testvec cast6_lrw_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -17149,7 +11353,7 @@ static const struct cipher_testvec cast6_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
+		.ptext	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
 			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
 			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
 			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
@@ -17213,90 +11417,7 @@ static const struct cipher_testvec cast6_lrw_enc_tv_template[] = {
 			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
 			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.ilen	= 512,
-		.result	= "\x55\x25\x09\x8B\xB5\xD5\xF8\xBF"
-			  "\x37\x4A\xFE\x3C\x47\xD8\xE6\xEB"
-			  "\xCA\xA4\x9B\xB0\xAB\x6D\x64\xCA"
-			  "\x58\xB6\x73\xF0\xD7\x52\x34\xEF"
-			  "\xFB\x3E\x96\x81\xB7\x71\x34\xA4"
-			  "\x55\x20\xBE\x39\x5A\x2B\xF9\xD1"
-			  "\x65\x0B\xDA\xD3\x7E\xB3\xA6\xF7"
-			  "\x2E\x0B\x5A\x52\xDB\x39\x8C\x9B"
-			  "\x61\x17\x5F\xAF\xB6\x5A\xC8\x08"
-			  "\xA7\xB7\x2A\x11\x7C\x97\x38\x9D"
-			  "\x59\x0E\x66\x59\x5E\xD8\x8B\xCE"
-			  "\x70\xE0\xC3\x42\xB0\x8C\x0F\xBA"
-			  "\xB2\x0D\x81\xB6\xBE\x61\x1C\x2D"
-			  "\x7E\xEA\x91\x25\xAC\xEC\xF8\x28"
-			  "\x80\x1D\xF0\x30\xBA\x62\x77\x7D"
-			  "\xDB\x15\x69\xDF\xFA\x2A\x81\x64"
-			  "\x95\x5B\xA4\x7F\x3E\x4F\xE3\x30"
-			  "\xB0\x5C\xC2\x05\xF8\xF0\x29\xE7"
-			  "\x0A\xA0\x66\xB2\x5D\x0F\x39\x2B"
-			  "\xB4\xB3\x00\xA9\xD0\xAB\x63\x61"
-			  "\x5E\xDB\xFC\x11\x74\x25\x96\x65"
-			  "\xE8\xE2\x34\x57\x77\x15\x5E\x70"
-			  "\xFF\x10\x90\xC3\x64\xF0\x11\x0A"
-			  "\x63\x3A\xD3\x55\x92\x15\x4B\x0C"
-			  "\xC7\x08\x89\x17\x3B\x99\xAD\x63"
-			  "\xE7\x06\xDF\x52\xBC\x15\x64\x45"
-			  "\x9D\x7A\xFB\x69\xBC\x2D\x6E\xA9"
-			  "\x35\xD9\xD8\xF5\x0C\xC4\xA2\x23"
-			  "\x9C\x18\x8B\xA8\x8C\xFE\xF8\x0E"
-			  "\xBD\xAB\x60\x1A\x51\x17\x54\x27"
-			  "\xB6\xE8\xBE\x0F\xA9\xA5\x82\x19"
-			  "\x2F\x6F\x20\xA7\x47\xED\x74\x6C"
-			  "\x4E\xC1\xF8\x8C\x14\xF3\xBB\x1F"
-			  "\xED\x4D\x8F\x7C\x37\xEF\x19\xA1"
-			  "\x07\x16\xDE\x76\xCC\x5E\x94\x02"
-			  "\xFB\xBF\xE4\x81\x50\xCE\xFC\x0F"
-			  "\x9E\xCF\x3D\xF6\x67\x00\xBF\xA7"
-			  "\x6E\x21\x58\x36\x06\xDE\xB3\xD4"
-			  "\xA2\xFA\xD8\x4E\xE0\xB9\x7F\x23"
-			  "\x51\x21\x2B\x32\x68\xAA\xF8\xA8"
-			  "\x93\x08\xB5\x6D\xE6\x43\x2C\xB7"
-			  "\x31\xB2\x0F\xD0\xA2\x51\xC0\x25"
-			  "\x30\xC7\x10\x3F\x97\x27\x01\x8E"
-			  "\xFA\xD8\x4F\x78\xD8\x2E\x1D\xEB"
-			  "\xA1\x37\x52\x0F\x7B\x5E\x87\xA8"
-			  "\x22\xE2\xE6\x92\xA7\x5F\x11\x32"
-			  "\xCC\x93\x34\xFC\xD1\x7E\xAE\x54"
-			  "\xBC\x6A\x1B\x91\xD1\x2E\x21\xEC"
-			  "\x5D\xF1\xC4\xF1\x55\x20\xBF\xE5"
-			  "\x96\x3D\x69\x91\x20\x4E\xF2\x61"
-			  "\xDA\x77\xFE\xEE\xC3\x74\x57\x2A"
-			  "\x78\x39\xB0\xE0\xCF\x12\x56\xD6"
-			  "\x05\xDC\xF9\x19\x66\x44\x1D\xF9"
-			  "\x82\x37\xD4\xC2\x60\xB6\x31\xDF"
-			  "\x0C\xAF\xBC\x8B\x55\x9A\xC8\x2D"
-			  "\xAB\xA7\x88\x7B\x41\xE8\x29\xC9"
-			  "\x9B\x8D\xA7\x00\x86\x25\xB6\x14"
-			  "\xF5\x13\x73\xD7\x4B\x6B\x83\xF3"
-			  "\xAF\x96\x00\xE4\xB7\x3C\x65\xA6"
-			  "\x15\xB7\x94\x7D\x4E\x70\x4C\x75"
-			  "\xF3\xB4\x02\xA9\x17\x1C\x7A\x0A"
-			  "\xC0\xD5\x33\x11\x56\xDE\xDC\xF5"
-			  "\x8D\xD9\xCD\x3B\x22\x67\x18\xC7"
-			  "\xC4\xF5\x99\x61\xBC\xBB\x5B\x46",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec cast6_lrw_dec_tv_template[] = {
-	{ /* Generated from TF test vectors */
-		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x55\x25\x09\x8B\xB5\xD5\xF8\xBF"
+		.ctext	= "\x55\x25\x09\x8B\xB5\xD5\xF8\xBF"
 			  "\x37\x4A\xFE\x3C\x47\xD8\xE6\xEB"
 			  "\xCA\xA4\x9B\xB0\xAB\x6D\x64\xCA"
 			  "\x58\xB6\x73\xF0\xD7\x52\x34\xEF"
@@ -17360,79 +11481,14 @@ static const struct cipher_testvec cast6_lrw_dec_tv_template[] = {
 			  "\xC0\xD5\x33\x11\x56\xDE\xDC\xF5"
 			  "\x8D\xD9\xCD\x3B\x22\x67\x18\xC7"
 			  "\xC4\xF5\x99\x61\xBC\xBB\x5B\x46",
-		.ilen	= 512,
-		.result	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
-			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
-			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
-			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
-			  "\x8f\xcb\x8d\x6b\xe3\xa6\x29\x90"
-			  "\xfe\x2a\x62\x82\xae\x6d\x8b\xf6"
-			  "\xad\x1e\x9e\x20\x5f\x38\xbe\x04"
-			  "\xda\x10\x8e\xed\xa2\xa4\x87\xab"
-			  "\xda\x6b\xb4\x0c\x75\xba\xd3\x7c"
-			  "\xc9\xac\x42\x31\x95\x7c\xc9\x04"
-			  "\xeb\xd5\x6e\x32\x69\x8a\xdb\xa6"
-			  "\x15\xd7\x3f\x4f\x2f\x66\x69\x03"
-			  "\x9c\x1f\x54\x0f\xde\x1f\xf3\x65"
-			  "\x4c\x96\x12\xed\x7c\x92\x03\x01"
-			  "\x6f\xbc\x35\x93\xac\xf1\x27\xf1"
-			  "\xb4\x96\x82\x5a\x5f\xb0\xa0\x50"
-			  "\x89\xa4\x8e\x66\x44\x85\xcc\xfd"
-			  "\x33\x14\x70\xe3\x96\xb2\xc3\xd3"
-			  "\xbb\x54\x5a\x1a\xf9\x74\xa2\xc5"
-			  "\x2d\x64\x75\xdd\xb4\x54\xe6\x74"
-			  "\x8c\xd3\x9d\x9e\x86\xab\x51\x53"
-			  "\xb7\x93\x3e\x6f\xd0\x4e\x2c\x40"
-			  "\xf6\xa8\x2e\x3e\x9d\xf4\x66\xa5"
-			  "\x76\x12\x73\x44\x1a\x56\xd7\x72"
-			  "\x88\xcd\x21\x8c\x4c\x0f\xfe\xda"
-			  "\x95\xe0\x3a\xa6\xa5\x84\x46\xcd"
-			  "\xd5\x3e\x9d\x3a\xe2\x67\xe6\x60"
-			  "\x1a\xe2\x70\x85\x58\xc2\x1b\x09"
-			  "\xe1\xd7\x2c\xca\xad\xa8\x8f\xf9"
-			  "\xac\xb3\x0e\xdb\xca\x2e\xe2\xb8"
-			  "\x51\x71\xd9\x3c\x6c\xf1\x56\xf8"
-			  "\xea\x9c\xf1\xfb\x0c\xe6\xb7\x10"
-			  "\x1c\xf8\xa9\x7c\xe8\x53\x35\xc1"
-			  "\x90\x3e\x76\x4a\x74\xa4\x21\x2c"
-			  "\xf6\x2c\x4e\x0f\x94\x3a\x88\x2e"
-			  "\x41\x09\x6a\x33\x7d\xf6\xdd\x3f"
-			  "\x8d\x23\x31\x74\x84\xeb\x88\x6e"
-			  "\xcc\xb9\xbc\x22\x83\x19\x07\x22"
-			  "\xa5\x2d\xdf\xa5\xf3\x80\x85\x78"
-			  "\x84\x39\x6a\x6d\x6a\x99\x4f\xa5"
-			  "\x15\xfe\x46\xb0\xe4\x6c\xa5\x41"
-			  "\x3c\xce\x8f\x42\x60\x71\xa7\x75"
-			  "\x08\x40\x65\x8a\x82\xbf\xf5\x43"
-			  "\x71\x96\xa9\x4d\x44\x8a\x20\xbe"
-			  "\xfa\x4d\xbb\xc0\x7d\x31\x96\x65"
-			  "\xe7\x75\xe5\x3e\xfd\x92\x3b\xc9"
-			  "\x55\xbb\x16\x7e\xf7\xc2\x8c\xa4"
-			  "\x40\x1d\xe5\xef\x0e\xdf\xe4\x9a"
-			  "\x62\x73\x65\xfd\x46\x63\x25\x3d"
-			  "\x2b\xaf\xe5\x64\xfe\xa5\x5c\xcf"
-			  "\x24\xf3\xb4\xac\x64\xba\xdf\x4b"
-			  "\xc6\x96\x7d\x81\x2d\x8d\x97\xf7"
-			  "\xc5\x68\x77\x84\x32\x2b\xcc\x85"
-			  "\x74\x96\xf0\x12\x77\x61\xb9\xeb"
-			  "\x71\xaa\x82\xcb\x1c\xdb\x89\xc8"
-			  "\xc6\xb5\xe3\x5c\x7d\x39\x07\x24"
-			  "\xda\x39\x87\x45\xc0\x2b\xbb\x01"
-			  "\xac\xbc\x2a\x5c\x7f\xfc\xe8\xce"
-			  "\x6d\x9c\x6f\xed\xd3\xc1\xa1\xd6"
-			  "\xc5\x55\xa9\x66\x2f\xe1\xc8\x32"
-			  "\xa6\x5d\xa4\x3a\x98\x73\xe8\x45"
-			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
-			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
-			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec cast6_xts_enc_tv_template[] = {
+static const struct cipher_testvec cast6_xts_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -17445,7 +11501,7 @@ static const struct cipher_testvec cast6_xts_enc_tv_template[] = {
 		.klen	= 64,
 		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -17509,8 +11565,7 @@ static const struct cipher_testvec cast6_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\xDE\x6F\x22\xA5\xE8\x39\xE8\x78"
+		.ctext	= "\xDE\x6F\x22\xA5\xE8\x39\xE8\x78"
 			  "\x88\x5A\x4F\x8D\x82\x76\x52\x6D"
 			  "\xB2\x41\x16\xF4\x2B\xA6\xEB\xF6"
 			  "\xE2\xC5\x62\x8D\x61\xA1\x01\xED"
@@ -17574,207 +11629,54 @@ static const struct cipher_testvec cast6_xts_enc_tv_template[] = {
 			  "\x45\x72\x80\x17\x81\xBD\x9D\x62"
 			  "\xA1\xAC\xE8\xCF\xC6\x74\xCF\xDC"
 			  "\x22\x60\x4E\xE8\xA4\x5D\x85\xB9",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec cast6_xts_dec_tv_template[] = {
-	{ /* Generated from TF test vectors */
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x62\x49\x77\x57\x24\x70\x93\x69"
-			  "\x99\x59\x57\x49\x66\x96\x76\x27"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95"
-			  "\x02\x88\x41\x97\x16\x93\x99\x37"
-			  "\x51\x05\x82\x09\x74\x94\x45\x92",
-		.klen	= 64,
-		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xDE\x6F\x22\xA5\xE8\x39\xE8\x78"
-			  "\x88\x5A\x4F\x8D\x82\x76\x52\x6D"
-			  "\xB2\x41\x16\xF4\x2B\xA6\xEB\xF6"
-			  "\xE2\xC5\x62\x8D\x61\xA1\x01\xED"
-			  "\xD9\x38\x01\xC1\x43\x63\x4E\x88"
-			  "\xC9\x4B\x5A\x88\x80\xB7\x5C\x71"
-			  "\x47\xEE\x11\xD8\xB7\x2D\x5D\x13"
-			  "\x1A\xB1\x68\x5B\x61\xA7\xA9\x81"
-			  "\x8B\x83\xA1\x6A\xAA\x36\xD6\xB6"
-			  "\x60\x54\x09\x32\xFE\x6A\x76\x2E"
-			  "\x28\xFF\xD5\xD6\xDD\x1D\x45\x7D"
-			  "\xF0\x8B\xF3\x32\x4E\x6C\x12\xCB"
-			  "\xB8\x25\x70\xF8\x40\xBC\x90\x1B"
-			  "\x11\xC3\x59\xAF\xF0\x2F\x92\xDD"
-			  "\xD3\x3B\xCF\x60\xA1\x78\x94\x57"
-			  "\xAF\x76\xC1\x67\xA6\x3C\xCD\x98"
-			  "\xB1\xF7\x27\xB9\xA3\xBD\x10\xEA"
-			  "\xCD\x8B\xC2\xF2\x14\xF2\xB2\x67"
-			  "\x05\xDD\x1D\x58\x6E\x2F\x95\x08"
-			  "\x3A\xF8\x78\x76\x82\x56\xA7\xEC"
-			  "\x51\x4B\x85\x77\xC2\x4C\x4A\x34"
-			  "\x71\x38\x17\x91\x44\xE8\xFC\x65"
-			  "\x99\x0D\x52\x91\xEE\xF8\xEF\x27"
-			  "\x2A\x9E\x6E\x78\xC4\x26\x87\xF4"
-			  "\x8A\xF0\x2D\x04\xE8\x14\x92\x5D"
-			  "\x59\x22\x9B\x29\x5C\x18\xF0\xC3"
-			  "\x47\xF3\x76\xD8\xE4\xF3\x1B\xD1"
-			  "\x70\xA3\x0D\xB5\x70\x02\x1D\xA3"
-			  "\x91\x3B\x49\x73\x18\xAB\xD4\xC9"
-			  "\xC3\x1E\xEF\x1F\xFE\xD5\x59\x8A"
-			  "\xD7\xF6\xC9\x71\x67\x79\xD7\x0E"
-			  "\xBE\x1F\x8E\xEC\x55\x7E\x4F\x24"
-			  "\xE6\x87\xEA\xFE\x96\x25\x67\x8E"
-			  "\x93\x03\xFA\xFF\xCE\xAF\xB2\x3C"
-			  "\x6F\xEB\x57\xFB\xD3\x28\x87\xA9"
-			  "\xCE\xC2\xF5\x9C\xC6\x67\xB5\x97"
-			  "\x49\xF7\x04\xCB\xEF\x84\x98\x33"
-			  "\xAF\x38\xD3\x04\x1C\x24\x71\x38"
-			  "\xC7\x71\xDD\x43\x0D\x12\x4A\x18"
-			  "\xBA\xC4\xAF\xBA\xB2\x5B\xEB\x95"
-			  "\x02\x43\x5D\xCE\x19\xCC\xCD\x66"
-			  "\x91\x0B\x8C\x7F\x51\xC4\xBF\x3C"
-			  "\x8B\xF1\xCC\xAA\x29\xD7\x87\xCB"
-			  "\x3E\xC5\xF3\xC9\x75\xE8\xA3\x5B"
-			  "\x30\x45\xA9\xB7\xAF\x80\x64\x6F"
-			  "\x75\x4A\xA7\xC0\x6D\x19\x6B\xDE"
-			  "\x17\xDE\x6D\xEA\x87\x9F\x95\xAE"
-			  "\xF5\x3C\xEE\x54\xB8\x27\x84\xF8"
-			  "\x97\xA3\xE1\x6F\x38\x24\x34\x88"
-			  "\xCE\xBD\x32\x52\xE0\x00\x6C\x94"
-			  "\xC9\xD7\x5D\x37\x81\x33\x2E\x7F"
-			  "\x4F\x7E\x2E\x0D\x94\xBD\xEA\x59"
-			  "\x34\x39\xA8\x35\x12\xB7\xBC\xAC"
-			  "\xEA\x52\x9C\x78\x02\x6D\x92\x36"
-			  "\xFB\x59\x2B\xA4\xEA\x7B\x1B\x83"
-			  "\xE1\x4D\x5E\x2A\x7E\x92\xB1\x64"
-			  "\xDE\xE0\x27\x4B\x0A\x6F\x4C\xE3"
-			  "\xB0\xEB\x31\xE4\x69\x95\xAB\x35"
-			  "\x8B\x2C\xF5\x6B\x7F\xF1\xA2\x82"
-			  "\xF8\xD9\x47\x82\xA9\x82\x03\x91"
-			  "\x69\x1F\xBE\x4C\xE7\xC7\x34\x2F"
-			  "\x45\x72\x80\x17\x81\xBD\x9D\x62"
-			  "\xA1\xAC\xE8\xCF\xC6\x74\xCF\xDC"
-			  "\x22\x60\x4E\xE8\xA4\x5D\x85\xB9",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
-
 /*
  * AES test vectors.
  */
-static const struct cipher_testvec aes_enc_tv_template[] = {
+static const struct cipher_testvec aes_tv_template[] = {
 	{ /* From FIPS-197 */
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
 		.klen	= 16,
-		.input	= "\x00\x11\x22\x33\x44\x55\x66\x77"
+		.ptext	= "\x00\x11\x22\x33\x44\x55\x66\x77"
 			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
-		.ilen	= 16,
-		.result	= "\x69\xc4\xe0\xd8\x6a\x7b\x04\x30"
+		.ctext	= "\x69\xc4\xe0\xd8\x6a\x7b\x04\x30"
 			  "\xd8\xcd\xb7\x80\x70\xb4\xc5\x5a",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17",
 		.klen	= 24,
-		.input	= "\x00\x11\x22\x33\x44\x55\x66\x77"
+		.ptext	= "\x00\x11\x22\x33\x44\x55\x66\x77"
 			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
-		.ilen	= 16,
-		.result	= "\xdd\xa9\x7c\xa4\x86\x4c\xdf\xe0"
+		.ctext	= "\xdd\xa9\x7c\xa4\x86\x4c\xdf\xe0"
 			  "\x6e\xaf\x70\xa0\xec\x0d\x71\x91",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
 		.klen	= 32,
-		.input	= "\x00\x11\x22\x33\x44\x55\x66\x77"
+		.ptext	= "\x00\x11\x22\x33\x44\x55\x66\x77"
 			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
-		.ilen	= 16,
-		.result	= "\x8e\xa2\xb7\xca\x51\x67\x45\xbf"
+		.ctext	= "\x8e\xa2\xb7\xca\x51\x67\x45\xbf"
 			  "\xea\xfc\x49\x90\x4b\x49\x60\x89",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* Generated with Crypto++ */
 		.key	= "\xA6\xC9\x83\xA6\xC9\xEC\x0F\x32"
 			  "\x55\x0F\x32\x55\x78\x9B\xBE\x78"
 			  "\x9B\xBE\xE1\x04\x27\xE1\x04\x27"
 			  "\x4A\x6D\x90\x4A\x6D\x90\xB3\xD6",
 		.klen	= 32,
-		.input	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
+		.ptext	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
 			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
 			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
 			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
@@ -17836,8 +11738,7 @@ static const struct cipher_testvec aes_enc_tv_template[] = {
 			  "\xAE\x17\xA3\x0C\x75\x01\x6A\xD3"
 			  "\x3C\xC8\x31\x9A\x03\x8F\xF8\x61"
 			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
-		.ilen	= 496,
-		.result	= "\x71\x73\xF7\xDB\x24\x93\x21\x6D"
+		.ctext	= "\x71\x73\xF7\xDB\x24\x93\x21\x6D"
 			  "\x61\x1E\xBB\x63\x42\x79\xDB\x64"
 			  "\x6F\x82\xC0\xCA\xA3\x9B\xFA\x0B"
 			  "\xD9\x08\xC7\x4A\x90\xAE\x8F\x5F"
@@ -17899,197 +11800,24 @@ static const struct cipher_testvec aes_enc_tv_template[] = {
 			  "\x88\xE6\x68\x47\xE3\x2B\xC5\xFF"
 			  "\x09\x79\xA0\x43\x5C\x0D\x08\x58"
 			  "\x17\xBB\xC0\x6B\x62\x3F\x56\xE9",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec aes_dec_tv_template[] = {
-	{ /* From FIPS-197 */
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.klen	= 16,
-		.input	= "\x69\xc4\xe0\xd8\x6a\x7b\x04\x30"
-			  "\xd8\xcd\xb7\x80\x70\xb4\xc5\x5a",
-		.ilen	= 16,
-		.result	= "\x00\x11\x22\x33\x44\x55\x66\x77"
-			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
-		.rlen	= 16,
-	}, {
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17",
-		.klen	= 24,
-		.input	= "\xdd\xa9\x7c\xa4\x86\x4c\xdf\xe0"
-			  "\x6e\xaf\x70\xa0\xec\x0d\x71\x91",
-		.ilen	= 16,
-		.result	= "\x00\x11\x22\x33\x44\x55\x66\x77"
-			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
-		.rlen	= 16,
-	}, {
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.klen	= 32,
-		.input	= "\x8e\xa2\xb7\xca\x51\x67\x45\xbf"
-			  "\xea\xfc\x49\x90\x4b\x49\x60\x89",
-		.ilen	= 16,
-		.result	= "\x00\x11\x22\x33\x44\x55\x66\x77"
-			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
-		.rlen	= 16,
-	}, { /* Generated with Crypto++ */
-		.key	= "\xA6\xC9\x83\xA6\xC9\xEC\x0F\x32"
-			  "\x55\x0F\x32\x55\x78\x9B\xBE\x78"
-			  "\x9B\xBE\xE1\x04\x27\xE1\x04\x27"
-			  "\x4A\x6D\x90\x4A\x6D\x90\xB3\xD6",
-		.klen	= 32,
-		.input	= "\x71\x73\xF7\xDB\x24\x93\x21\x6D"
-			  "\x61\x1E\xBB\x63\x42\x79\xDB\x64"
-			  "\x6F\x82\xC0\xCA\xA3\x9B\xFA\x0B"
-			  "\xD9\x08\xC7\x4A\x90\xAE\x8F\x5F"
-			  "\x5E\x06\xF0\x5F\x31\x51\x18\x37"
-			  "\x45\xD7\xCA\x3A\xFD\x6C\x3F\xE1"
-			  "\xDD\x8D\x22\x65\x2B\x00\x50\xCE"
-			  "\xBA\x28\x67\xD7\xCE\x0E\x0D\xEA"
-			  "\x78\x69\x7F\xAE\x8F\x8B\x69\x37"
-			  "\x75\xE0\xDC\x96\xE0\xB7\xF4\x09"
-			  "\xCB\x6D\xA2\xFB\xDA\xAF\x09\xF8"
-			  "\x81\x82\x27\xFA\x45\x9C\x29\xA4"
-			  "\x22\x8B\x78\x69\x5B\x46\xF9\x39"
-			  "\x1B\xCC\xF9\x1D\x09\xEB\xBC\x5C"
-			  "\x41\x72\x51\x97\x1D\x07\x49\xA0"
-			  "\x1B\x8E\x65\x4B\xB2\x6A\x12\x03"
-			  "\x6A\x60\x95\xAC\xBD\xAC\x1A\x64"
-			  "\xDE\x5A\xA5\xF0\x83\x2F\xCB\xCA"
-			  "\x22\x74\xA6\x6C\x9B\x73\xCE\x3F"
-			  "\xE1\x8B\x22\x17\x59\x0C\x47\x89"
-			  "\x33\xA1\xD6\x47\x03\x19\x4F\xA8"
-			  "\x67\x69\xF0\x5B\xF0\x20\xAD\x06"
-			  "\x27\x81\x92\xD8\xC5\xBA\x98\x12"
-			  "\xBE\x24\xB5\x2F\x75\x02\xC2\xAD"
-			  "\x12\x2F\x07\x32\xEE\x39\xAF\x64"
-			  "\x05\x8F\xB3\xD4\xEB\x1B\x46\x6E"
-			  "\xD9\x21\xF9\xC4\xB7\xC9\x45\x68"
-			  "\xB4\xA1\x74\x9F\x82\x47\xEB\xCC"
-			  "\xBD\x0A\x14\x95\x0F\x8B\xA8\x2F"
-			  "\x4B\x1B\xA7\xBF\x82\xA6\x43\x0C"
-			  "\xB9\x39\x4A\xA8\x10\x6F\x50\x7B"
-			  "\x25\xFB\x26\x81\xE0\x2F\xF0\x96"
-			  "\x8D\x8B\xAC\x92\x0F\xF6\xED\x64"
-			  "\x63\x29\x4C\x8E\x18\x13\xC5\xBF"
-			  "\xFC\xA0\xD9\xBF\x7C\x3A\x0E\x29"
-			  "\x6F\xD1\x6C\x6F\xA5\xDA\xBF\xB1"
-			  "\x30\xEA\x44\x2D\xC3\x8F\x16\xE1"
-			  "\x66\xFA\xA3\x21\x3E\xFC\x13\xCA"
-			  "\xF0\xF6\xF0\x59\xBD\x8F\x38\x50"
-			  "\x31\xCB\x69\x3F\x96\x15\xD6\xF5"
-			  "\xAE\xFF\xF6\xAA\x41\x85\x4C\x10"
-			  "\x58\xE3\xF9\x44\xE6\x28\xDA\x9A"
-			  "\xDC\x6A\x80\x34\x73\x97\x1B\xC5"
-			  "\xCA\x26\x16\x77\x0E\x60\xAB\x89"
-			  "\x0F\x04\x27\xBD\xCE\x3E\x71\xB4"
-			  "\xA0\xD7\x22\x7E\xDB\xEB\x24\x70"
-			  "\x42\x71\x51\x78\x70\xB3\xE0\x3D"
-			  "\x84\x8E\x8D\x7B\xD0\x6D\xEA\x92"
-			  "\x11\x08\x42\x4F\xE5\xAD\x26\x92"
-			  "\xD2\x00\xAE\xA8\xE3\x4B\x37\x47"
-			  "\x22\xC1\x95\xC1\x63\x7F\xCB\x03"
-			  "\xF3\xE3\xD7\x9D\x60\xC7\xBC\xEA"
-			  "\x35\xA2\xFD\x45\x52\x39\x13\x6F"
-			  "\xC1\x53\xF3\x53\xDF\x33\x84\xD7"
-			  "\xD2\xC8\x37\xB0\x75\xE3\x41\x46"
-			  "\xB3\xC7\x83\x2E\x8A\xBB\xA4\xE5"
-			  "\x7F\x3C\xFD\x8B\xEB\xEA\x63\xBD"
-			  "\xB7\x46\xE7\xBF\x09\x9C\x0D\x0F"
-			  "\x40\x86\x7F\x51\xE1\x11\x9C\xCB"
-			  "\x88\xE6\x68\x47\xE3\x2B\xC5\xFF"
-			  "\x09\x79\xA0\x43\x5C\x0D\x08\x58"
-			  "\x17\xBB\xC0\x6B\x62\x3F\x56\xE9",
-		.ilen	= 496,
-		.result	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
-			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
-			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
-			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
-			  "\xAB\x14\x7D\x09\x72\xDB\x44\xD0"
-			  "\x39\xA2\x0B\x97\x00\x69\xF5\x5E"
-			  "\xC7\x30\xBC\x25\x8E\x1A\x83\xEC"
-			  "\x55\xE1\x4A\xB3\x1C\xA8\x11\x7A"
-			  "\x06\x6F\xD8\x41\xCD\x36\x9F\x08"
-			  "\x94\xFD\x66\xF2\x5B\xC4\x2D\xB9"
-			  "\x22\x8B\x17\x80\xE9\x52\xDE\x47"
-			  "\xB0\x19\xA5\x0E\x77\x03\x6C\xD5"
-			  "\x3E\xCA\x33\x9C\x05\x91\xFA\x63"
-			  "\xEF\x58\xC1\x2A\xB6\x1F\x88\x14"
-			  "\x7D\xE6\x4F\xDB\x44\xAD\x16\xA2"
-			  "\x0B\x74\x00\x69\xD2\x3B\xC7\x30"
-			  "\x99\x02\x8E\xF7\x60\xEC\x55\xBE"
-			  "\x27\xB3\x1C\x85\x11\x7A\xE3\x4C"
-			  "\xD8\x41\xAA\x13\x9F\x08\x71\xFD"
-			  "\x66\xCF\x38\xC4\x2D\x96\x22\x8B"
-			  "\xF4\x5D\xE9\x52\xBB\x24\xB0\x19"
-			  "\x82\x0E\x77\xE0\x49\xD5\x3E\xA7"
-			  "\x10\x9C\x05\x6E\xFA\x63\xCC\x35"
-			  "\xC1\x2A\x93\x1F\x88\xF1\x5A\xE6"
-			  "\x4F\xB8\x21\xAD\x16\x7F\x0B\x74"
-			  "\xDD\x46\xD2\x3B\xA4\x0D\x99\x02"
-			  "\x6B\xF7\x60\xC9\x32\xBE\x27\x90"
-			  "\x1C\x85\xEE\x57\xE3\x4C\xB5\x1E"
-			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
-			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
-			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB"
-			  "\x54\xE0\x49\xB2\x1B\xA7\x10\x79"
-			  "\x05\x6E\xD7\x40\xCC\x35\x9E\x07"
-			  "\x93\xFC\x65\xF1\x5A\xC3\x2C\xB8"
-			  "\x21\x8A\x16\x7F\xE8\x51\xDD\x46"
-			  "\xAF\x18\xA4\x0D\x76\x02\x6B\xD4"
-			  "\x3D\xC9\x32\x9B\x04\x90\xF9\x62"
-			  "\xEE\x57\xC0\x29\xB5\x1E\x87\x13"
-			  "\x7C\xE5\x4E\xDA\x43\xAC\x15\xA1"
-			  "\x0A\x73\xFF\x68\xD1\x3A\xC6\x2F"
-			  "\x98\x01\x8D\xF6\x5F\xEB\x54\xBD"
-			  "\x26\xB2\x1B\x84\x10\x79\xE2\x4B"
-			  "\xD7\x40\xA9\x12\x9E\x07\x70\xFC"
-			  "\x65\xCE\x37\xC3\x2C\x95\x21\x8A"
-			  "\xF3\x5C\xE8\x51\xBA\x23\xAF\x18"
-			  "\x81\x0D\x76\xDF\x48\xD4\x3D\xA6"
-			  "\x0F\x9B\x04\x6D\xF9\x62\xCB\x34"
-			  "\xC0\x29\x92\x1E\x87\xF0\x59\xE5"
-			  "\x4E\xB7\x20\xAC\x15\x7E\x0A\x73"
-			  "\xDC\x45\xD1\x3A\xA3\x0C\x98\x01"
-			  "\x6A\xF6\x5F\xC8\x31\xBD\x26\x8F"
-			  "\x1B\x84\xED\x56\xE2\x4B\xB4\x1D"
-			  "\xA9\x12\x7B\x07\x70\xD9\x42\xCE"
-			  "\x37\xA0\x09\x95\xFE\x67\xF3\x5C"
-			  "\xC5\x2E\xBA\x23\x8C\x18\x81\xEA"
-			  "\x53\xDF\x48\xB1\x1A\xA6\x0F\x78"
-			  "\x04\x6D\xD6\x3F\xCB\x34\x9D\x06"
-			  "\x92\xFB\x64\xF0\x59\xC2\x2B\xB7"
-			  "\x20\x89\x15\x7E\xE7\x50\xDC\x45"
-			  "\xAE\x17\xA3\x0C\x75\x01\x6A\xD3"
-			  "\x3C\xC8\x31\x9A\x03\x8F\xF8\x61"
-			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
+static const struct cipher_testvec aes_cbc_tv_template[] = {
 	{ /* From RFC 3602 */
 		.key    = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b"
 			  "\x51\x2e\x03\xd5\x34\x12\x00\x06",
 		.klen   = 16,
 		.iv	= "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
 			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
-		.input	= "Single block msg",
-		.ilen   = 16,
-		.result = "\xe3\x53\x77\x9c\x10\x79\xae\xb8"
+		.ptext	= "Single block msg",
+		.ctext	= "\xe3\x53\x77\x9c\x10\x79\xae\xb8"
 			  "\x27\x08\x94\x2d\xbe\x77\x18\x1a",
-		.rlen   = 16,
+		.len	= 16,
 		.also_non_np = 1,
 		.np	= 8,
 		.tap	= { 3, 2, 3, 2, 3, 1, 1, 1 },
@@ -18099,16 +11827,15 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 		.klen   = 16,
 		.iv     = "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
 			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
-		.input  = "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.ilen   = 32,
-		.result = "\xd2\x96\xcd\x94\xc2\xcc\xcf\x8a"
+		.ctext	= "\xd2\x96\xcd\x94\xc2\xcc\xcf\x8a"
 			  "\x3a\x86\x30\x28\xb5\xe1\xdc\x0a"
 			  "\x75\x86\x60\x2d\x25\x3c\xff\xf9"
 			  "\x1b\x82\x66\xbe\xa6\xd6\x1a\xb1",
-		.rlen   = 32,
+		.len	= 32,
 	}, { /* From NIST SP800-38A */
 		.key	= "\x8e\x73\xb0\xf7\xda\x0e\x64\x52"
 			  "\xc8\x10\xf3\x2b\x80\x90\x79\xe5"
@@ -18116,7 +11843,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.input	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
 			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
@@ -18124,8 +11851,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
 			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
 			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ilen	= 64,
-		.result	= "\x4f\x02\x1d\xb2\x43\xbc\x63\x3d"
+		.ctext	= "\x4f\x02\x1d\xb2\x43\xbc\x63\x3d"
 			  "\x71\x78\x18\x3a\x9f\xa0\x71\xe8"
 			  "\xb4\xd9\xad\xa9\xad\x7d\xed\xf4"
 			  "\xe5\xe7\x38\x76\x3f\x69\x14\x5a"
@@ -18133,7 +11859,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 			  "\x7f\xa9\xba\xac\x3d\xf1\x02\xe0"
 			  "\x08\xb0\xe2\x79\x88\x59\x88\x81"
 			  "\xd9\x20\xa9\xe6\x4f\x56\x15\xcd",
-		.rlen	= 64,
+		.len	= 64,
 	}, {
 		.key	= "\x60\x3d\xeb\x10\x15\xca\x71\xbe"
 			  "\x2b\x73\xae\xf0\x85\x7d\x77\x81"
@@ -18142,7 +11868,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.input	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
 			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
@@ -18150,8 +11876,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
 			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
 			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ilen	= 64,
-		.result	= "\xf5\x8c\x4c\x04\xd6\xe5\xf1\xba"
+		.ctext	= "\xf5\x8c\x4c\x04\xd6\xe5\xf1\xba"
 			  "\x77\x9e\xab\xfb\x5f\x7b\xfb\xd6"
 			  "\x9c\xfc\x4e\x96\x7e\xdb\x80\x8d"
 			  "\x67\x9f\x77\x7b\xc6\x70\x2c\x7d"
@@ -18159,7 +11884,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 			  "\xa5\x30\xe2\x63\x04\x23\x14\x61"
 			  "\xb2\xeb\x05\xe2\xc3\x9b\xe9\xfc"
 			  "\xda\x6c\x19\x07\x8c\x6a\x9d\x1b",
-		.rlen	= 64,
+		.len	= 64,
 	}, { /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55"
 			  "\x0F\x32\x55\x78\x9B\xBE\x78\x9B"
@@ -18168,7 +11893,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE7\x82\x1D\xB8\x53\x11\xAC\x47"
 			  "\xE2\x7D\x18\xD6\x71\x0C\xA7\x42",
-		.input	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
+		.ptext	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
 			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
 			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
 			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
@@ -18230,8 +11955,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 			  "\xAE\x17\xA3\x0C\x75\x01\x6A\xD3"
 			  "\x3C\xC8\x31\x9A\x03\x8F\xF8\x61"
 			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
-		.ilen	= 496,
-		.result	= "\xEA\x65\x8A\x19\xB0\x66\xC1\x3F"
+		.ctext	= "\xEA\x65\x8A\x19\xB0\x66\xC1\x3F"
 			  "\xCE\xF1\x97\x75\xC1\xFD\xB5\xAF"
 			  "\x52\x65\xF7\xFF\xBC\xD8\x2D\x9F"
 			  "\x2F\xB9\x26\x9B\x6F\x10\xB7\xB8"
@@ -18293,229 +12017,7 @@ static const struct cipher_testvec aes_cbc_enc_tv_template[] = {
 			  "\xBC\x06\x41\xE3\x01\xB4\x4E\x0A"
 			  "\xE0\x1F\x91\xF8\x82\x96\x2D\x65"
 			  "\xA3\xAA\x13\xCC\x50\xFF\x7B\x02",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec aes_cbc_dec_tv_template[] = {
-	{ /* From RFC 3602 */
-		.key    = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b"
-			  "\x51\x2e\x03\xd5\x34\x12\x00\x06",
-		.klen   = 16,
-		.iv     = "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
-			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
-		.input  = "\xe3\x53\x77\x9c\x10\x79\xae\xb8"
-			  "\x27\x08\x94\x2d\xbe\x77\x18\x1a",
-		.ilen   = 16,
-		.result = "Single block msg",
-		.rlen   = 16,
-		.also_non_np = 1,
-		.np	= 8,
-		.tap	= { 3, 2, 3, 2, 3, 1, 1, 1 },
-	}, {
-		.key    = "\xc2\x86\x69\x6d\x88\x7c\x9a\xa0"
-			  "\x61\x1b\xbb\x3e\x20\x25\xa4\x5a",
-		.klen   = 16,
-		.iv     = "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
-			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
-		.input  = "\xd2\x96\xcd\x94\xc2\xcc\xcf\x8a"
-			  "\x3a\x86\x30\x28\xb5\xe1\xdc\x0a"
-			  "\x75\x86\x60\x2d\x25\x3c\xff\xf9"
-			  "\x1b\x82\x66\xbe\xa6\xd6\x1a\xb1",
-		.ilen   = 32,
-		.result = "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.rlen   = 32,
-	}, { /* From NIST SP800-38A */
-		.key	= "\x8e\x73\xb0\xf7\xda\x0e\x64\x52"
-			  "\xc8\x10\xf3\x2b\x80\x90\x79\xe5"
-			  "\x62\xf8\xea\xd2\x52\x2c\x6b\x7b",
-		.klen	= 24,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.input	= "\x4f\x02\x1d\xb2\x43\xbc\x63\x3d"
-			  "\x71\x78\x18\x3a\x9f\xa0\x71\xe8"
-			  "\xb4\xd9\xad\xa9\xad\x7d\xed\xf4"
-			  "\xe5\xe7\x38\x76\x3f\x69\x14\x5a"
-			  "\x57\x1b\x24\x20\x12\xfb\x7a\xe0"
-			  "\x7f\xa9\xba\xac\x3d\xf1\x02\xe0"
-			  "\x08\xb0\xe2\x79\x88\x59\x88\x81"
-			  "\xd9\x20\xa9\xe6\x4f\x56\x15\xcd",
-		.ilen	= 64,
-		.result	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.rlen	= 64,
-	}, {
-		.key	= "\x60\x3d\xeb\x10\x15\xca\x71\xbe"
-			  "\x2b\x73\xae\xf0\x85\x7d\x77\x81"
-			  "\x1f\x35\x2c\x07\x3b\x61\x08\xd7"
-			  "\x2d\x98\x10\xa3\x09\x14\xdf\xf4",
-		.klen	= 32,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.input	= "\xf5\x8c\x4c\x04\xd6\xe5\xf1\xba"
-			  "\x77\x9e\xab\xfb\x5f\x7b\xfb\xd6"
-			  "\x9c\xfc\x4e\x96\x7e\xdb\x80\x8d"
-			  "\x67\x9f\x77\x7b\xc6\x70\x2c\x7d"
-			  "\x39\xf2\x33\x69\xa9\xd9\xba\xcf"
-			  "\xa5\x30\xe2\x63\x04\x23\x14\x61"
-			  "\xb2\xeb\x05\xe2\xc3\x9b\xe9\xfc"
-			  "\xda\x6c\x19\x07\x8c\x6a\x9d\x1b",
-		.ilen	= 64,
-		.result	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.rlen	= 64,
-	}, { /* Generated with Crypto++ */
-		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55"
-			  "\x0F\x32\x55\x78\x9B\xBE\x78\x9B"
-			  "\xBE\xE1\x04\x27\xE1\x04\x27\x4A"
-			  "\x6D\x90\x4A\x6D\x90\xB3\xD6\xF9",
-		.klen	= 32,
-		.iv	= "\xE7\x82\x1D\xB8\x53\x11\xAC\x47"
-			  "\xE2\x7D\x18\xD6\x71\x0C\xA7\x42",
-		.input	= "\xEA\x65\x8A\x19\xB0\x66\xC1\x3F"
-			  "\xCE\xF1\x97\x75\xC1\xFD\xB5\xAF"
-			  "\x52\x65\xF7\xFF\xBC\xD8\x2D\x9F"
-			  "\x2F\xB9\x26\x9B\x6F\x10\xB7\xB8"
-			  "\x26\xA1\x02\x46\xA2\xAD\xC6\xC0"
-			  "\x11\x15\xFF\x6D\x1E\x82\x04\xA6"
-			  "\xB1\x74\xD1\x08\x13\xFD\x90\x7C"
-			  "\xF5\xED\xD3\xDB\x5A\x0A\x0C\x2F"
-			  "\x0A\x70\xF1\x88\x07\xCF\x21\x26"
-			  "\x40\x40\x8A\xF5\x53\xF7\x24\x4F"
-			  "\x83\x38\x43\x5F\x08\x99\xEB\xE3"
-			  "\xDC\x02\x64\x67\x50\x6E\x15\xC3"
-			  "\x01\x1A\xA0\x81\x13\x65\xA6\x73"
-			  "\x71\xA6\x3B\x91\x83\x77\xBE\xFA"
-			  "\xDB\x71\x73\xA6\xC1\xAE\x43\xC3"
-			  "\x36\xCE\xD6\xEB\xF9\x30\x1C\x4F"
-			  "\x80\x38\x5E\x9C\x6E\xAB\x98\x2F"
-			  "\x53\xAF\xCF\xC8\x9A\xB8\x86\x43"
-			  "\x3E\x86\xE7\xA1\xF4\x2F\x30\x40"
-			  "\x03\xA8\x6C\x50\x42\x9F\x77\x59"
-			  "\x89\xA0\xC5\xEC\x9A\xB8\xDD\x99"
-			  "\x16\x24\x02\x07\x48\xAE\xF2\x31"
-			  "\x34\x0E\xC3\x85\xFE\x1C\x95\x99"
-			  "\x87\x58\x98\x8B\xE7\xC6\xC5\x70"
-			  "\x73\x81\x07\x7C\x56\x2F\xD8\x1B"
-			  "\xB7\xB9\x2B\xAB\xE3\x01\x87\x0F"
-			  "\xD8\xBB\xC0\x0D\xAC\x2C\x2F\x98"
-			  "\x3C\x0B\xA2\x99\x4A\x8C\xF7\x04"
-			  "\xE0\xE0\xCF\xD1\x81\x5B\xFE\xF5"
-			  "\x24\x04\xFD\xB8\xDF\x13\xD8\xCD"
-			  "\xF1\xE3\x3D\x98\x50\x02\x77\x9E"
-			  "\xBC\x22\xAB\xFA\xC2\x43\x1F\x66"
-			  "\x20\x02\x23\xDA\xDF\xA0\x89\xF6"
-			  "\xD8\xF3\x45\x24\x53\x6F\x16\x77"
-			  "\x02\x3E\x7B\x36\x5F\xA0\x3B\x78"
-			  "\x63\xA2\xBD\xB5\xA4\xCA\x1E\xD3"
-			  "\x57\xBC\x0B\x9F\x43\x51\x28\x4F"
-			  "\x07\x50\x6C\x68\x12\x07\xCF\xFA"
-			  "\x6B\x72\x0B\xEB\xF8\x88\x90\x2C"
-			  "\x7E\xF5\x91\xD1\x03\xD8\xD5\xBD"
-			  "\x22\x39\x7B\x16\x03\x01\x69\xAF"
-			  "\x3D\x38\x66\x28\x0C\xBE\x5B\xC5"
-			  "\x03\xB4\x2F\x51\x8A\x56\x17\x2B"
-			  "\x88\x42\x6D\x40\x68\x8F\xD0\x11"
-			  "\x19\xF9\x1F\x43\x79\x95\x31\xFA"
-			  "\x28\x7A\x3D\xF7\x66\xEB\xEF\xAC"
-			  "\x06\xB2\x01\xAD\xDB\x68\xDB\xEC"
-			  "\x8D\x53\x6E\x72\x68\xA3\xC7\x63"
-			  "\x43\x2B\x78\xE0\x04\x29\x8F\x72"
-			  "\xB2\x2C\xE6\x84\x03\x30\x6D\xCD"
-			  "\x26\x92\x37\xE1\x2F\xBB\x8B\x9D"
-			  "\xE4\x4C\xF6\x93\xBC\xD9\xAD\x44"
-			  "\x52\x65\xC7\xB0\x0E\x3F\x0E\x61"
-			  "\x56\x5D\x1C\x6D\xA7\x05\x2E\xBC"
-			  "\x58\x08\x15\xAB\x12\xAB\x17\x4A"
-			  "\x5E\x1C\xF2\xCD\xB8\xA2\xAE\xFB"
-			  "\x9B\x2E\x0E\x85\x34\x80\x0E\x3F"
-			  "\x4C\xB8\xDB\xCE\x1C\x90\xA1\x61"
-			  "\x6C\x69\x09\x35\x9E\xD4\xF4\xAD"
-			  "\xBC\x06\x41\xE3\x01\xB4\x4E\x0A"
-			  "\xE0\x1F\x91\xF8\x82\x96\x2D\x65"
-			  "\xA3\xAA\x13\xCC\x50\xFF\x7B\x02",
-		.ilen	= 496,
-		.result	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
-			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
-			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
-			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
-			  "\xAB\x14\x7D\x09\x72\xDB\x44\xD0"
-			  "\x39\xA2\x0B\x97\x00\x69\xF5\x5E"
-			  "\xC7\x30\xBC\x25\x8E\x1A\x83\xEC"
-			  "\x55\xE1\x4A\xB3\x1C\xA8\x11\x7A"
-			  "\x06\x6F\xD8\x41\xCD\x36\x9F\x08"
-			  "\x94\xFD\x66\xF2\x5B\xC4\x2D\xB9"
-			  "\x22\x8B\x17\x80\xE9\x52\xDE\x47"
-			  "\xB0\x19\xA5\x0E\x77\x03\x6C\xD5"
-			  "\x3E\xCA\x33\x9C\x05\x91\xFA\x63"
-			  "\xEF\x58\xC1\x2A\xB6\x1F\x88\x14"
-			  "\x7D\xE6\x4F\xDB\x44\xAD\x16\xA2"
-			  "\x0B\x74\x00\x69\xD2\x3B\xC7\x30"
-			  "\x99\x02\x8E\xF7\x60\xEC\x55\xBE"
-			  "\x27\xB3\x1C\x85\x11\x7A\xE3\x4C"
-			  "\xD8\x41\xAA\x13\x9F\x08\x71\xFD"
-			  "\x66\xCF\x38\xC4\x2D\x96\x22\x8B"
-			  "\xF4\x5D\xE9\x52\xBB\x24\xB0\x19"
-			  "\x82\x0E\x77\xE0\x49\xD5\x3E\xA7"
-			  "\x10\x9C\x05\x6E\xFA\x63\xCC\x35"
-			  "\xC1\x2A\x93\x1F\x88\xF1\x5A\xE6"
-			  "\x4F\xB8\x21\xAD\x16\x7F\x0B\x74"
-			  "\xDD\x46\xD2\x3B\xA4\x0D\x99\x02"
-			  "\x6B\xF7\x60\xC9\x32\xBE\x27\x90"
-			  "\x1C\x85\xEE\x57\xE3\x4C\xB5\x1E"
-			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
-			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
-			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB"
-			  "\x54\xE0\x49\xB2\x1B\xA7\x10\x79"
-			  "\x05\x6E\xD7\x40\xCC\x35\x9E\x07"
-			  "\x93\xFC\x65\xF1\x5A\xC3\x2C\xB8"
-			  "\x21\x8A\x16\x7F\xE8\x51\xDD\x46"
-			  "\xAF\x18\xA4\x0D\x76\x02\x6B\xD4"
-			  "\x3D\xC9\x32\x9B\x04\x90\xF9\x62"
-			  "\xEE\x57\xC0\x29\xB5\x1E\x87\x13"
-			  "\x7C\xE5\x4E\xDA\x43\xAC\x15\xA1"
-			  "\x0A\x73\xFF\x68\xD1\x3A\xC6\x2F"
-			  "\x98\x01\x8D\xF6\x5F\xEB\x54\xBD"
-			  "\x26\xB2\x1B\x84\x10\x79\xE2\x4B"
-			  "\xD7\x40\xA9\x12\x9E\x07\x70\xFC"
-			  "\x65\xCE\x37\xC3\x2C\x95\x21\x8A"
-			  "\xF3\x5C\xE8\x51\xBA\x23\xAF\x18"
-			  "\x81\x0D\x76\xDF\x48\xD4\x3D\xA6"
-			  "\x0F\x9B\x04\x6D\xF9\x62\xCB\x34"
-			  "\xC0\x29\x92\x1E\x87\xF0\x59\xE5"
-			  "\x4E\xB7\x20\xAC\x15\x7E\x0A\x73"
-			  "\xDC\x45\xD1\x3A\xA3\x0C\x98\x01"
-			  "\x6A\xF6\x5F\xC8\x31\xBD\x26\x8F"
-			  "\x1B\x84\xED\x56\xE2\x4B\xB4\x1D"
-			  "\xA9\x12\x7B\x07\x70\xD9\x42\xCE"
-			  "\x37\xA0\x09\x95\xFE\x67\xF3\x5C"
-			  "\xC5\x2E\xBA\x23\x8C\x18\x81\xEA"
-			  "\x53\xDF\x48\xB1\x1A\xA6\x0F\x78"
-			  "\x04\x6D\xD6\x3F\xCB\x34\x9D\x06"
-			  "\x92\xFB\x64\xF0\x59\xC2\x2B\xB7"
-			  "\x20\x89\x15\x7E\xE7\x50\xDC\x45"
-			  "\xAE\x17\xA3\x0C\x75\x01\x6A\xD3"
-			  "\x3C\xC8\x31\x9A\x03\x8F\xF8\x61"
-			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
@@ -20225,7 +13727,7 @@ static const struct aead_testvec hmac_sha512_des3_ede_cbc_enc_tv_temp[] = {
 	},
 };
 
-static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
+static const struct cipher_testvec aes_lrw_tv_template[] = {
 	/* from http://grouper.ieee.org/groups/1619/email/pdf00017.pdf */
 	{ /* LRW-32-AES 1 */
 		.key    = "\x45\x62\xac\x25\xf8\x28\x17\x6d"
@@ -20235,12 +13737,11 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 		.klen   = 32,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input  = "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen   = 16,
-		.result = "\xf1\xb2\x73\xcd\x65\xa3\xdf\x5f"
+		.ctext	= "\xf1\xb2\x73\xcd\x65\xa3\xdf\x5f"
 			  "\xe9\x5d\x48\x92\x54\x63\x4e\xb8",
-		.rlen   = 16,
+		.len	= 16,
 	}, { /* LRW-32-AES 2 */
 		.key    = "\x59\x70\x47\x14\xf5\x57\x47\x8c"
 			  "\xd7\x79\xe8\x0f\x54\x88\x79\x44"
@@ -20249,12 +13750,11 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 		.klen   = 32,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input  = "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen   = 16,
-		.result = "\x00\xc8\x2b\xae\x95\xbb\xcd\xe5"
+		.ctext	= "\x00\xc8\x2b\xae\x95\xbb\xcd\xe5"
 			  "\x27\x4f\x07\x69\xb2\x60\xe1\x36",
-		.rlen   = 16,
+		.len	= 16,
 	}, { /* LRW-32-AES 3 */
 		.key    = "\xd8\x2a\x91\x34\xb2\x6a\x56\x50"
 			  "\x30\xfe\x69\xe2\x37\x7f\x98\x47"
@@ -20263,12 +13763,11 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 		.klen   = 32,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input  = "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen   = 16,
-		.result = "\x76\x32\x21\x83\xed\x8f\xf1\x82"
+		.ctext	= "\x76\x32\x21\x83\xed\x8f\xf1\x82"
 			  "\xf9\x59\x62\x03\x69\x0e\x5e\x01",
-		.rlen   = 16,
+		.len	= 16,
 	}, { /* LRW-32-AES 4 */
 		.key    = "\x0f\x6a\xef\xf8\xd3\xd2\xbb\x15"
 			  "\x25\x83\xf7\x3c\x1f\x01\x28\x74"
@@ -20278,12 +13777,11 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 		.klen   = 40,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input  = "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen   = 16,
-		.result = "\x9c\x0f\x15\x2f\x55\xa2\xd8\xf0"
+		.ctext	= "\x9c\x0f\x15\x2f\x55\xa2\xd8\xf0"
 			  "\xd6\x7b\x8f\x9e\x28\x22\xbc\x41",
-		.rlen   = 16,
+		.len	= 16,
 	}, { /* LRW-32-AES 5 */
 		.key    = "\x8a\xd4\xee\x10\x2f\xbd\x81\xff"
 			  "\xf8\x86\xce\xac\x93\xc5\xad\xc6"
@@ -20293,12 +13791,11 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 		.klen   = 40,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input  = "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen   = 16,
-		.result = "\xd4\x27\x6a\x7f\x14\x91\x3d\x65"
+		.ctext	= "\xd4\x27\x6a\x7f\x14\x91\x3d\x65"
 			  "\xc8\x60\x48\x02\x87\xe3\x34\x06",
-		.rlen   = 16,
+		.len	= 16,
 	}, { /* LRW-32-AES 6 */
 		.key    = "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -20309,12 +13806,11 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 		.klen   = 48,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input  = "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen   = 16,
-		.result = "\xbd\x06\xb8\xe1\xdb\x98\x89\x9e"
+		.ctext	= "\xbd\x06\xb8\xe1\xdb\x98\x89\x9e"
 			  "\xc4\x98\xe4\x91\xcf\x1c\x70\x2b",
-		.rlen   = 16,
+		.len	= 16,
 	}, { /* LRW-32-AES 7 */
 		.key    = "\xfb\x76\x15\xb2\x3d\x80\x89\x1d"
 			  "\xd4\x70\x98\x0b\xc7\x95\x84\xc8"
@@ -20325,12 +13821,11 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 		.klen   = 48,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input  = "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen   = 16,
-		.result = "\x5b\x90\x8e\xc1\xab\xdd\x67\x5f"
+		.ctext	= "\x5b\x90\x8e\xc1\xab\xdd\x67\x5f"
 			  "\x3d\x69\x8a\x95\x53\xc8\x9c\xe5",
-		.rlen   = 16,
+		.len	= 16,
 	}, {
 /* http://www.mail-archive.com/stds-p1619@listserv.ieee.org/msg00173.html */
 		.key    = "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
@@ -20342,7 +13837,7 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 		.klen   = 48,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input  = "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
+		.ptext	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
 			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
 			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
 			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
@@ -20406,197 +13901,7 @@ static const struct cipher_testvec aes_lrw_enc_tv_template[] = {
 			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
 			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.ilen   = 512,
-		.result = "\x1a\x1d\xa9\x30\xad\xf9\x2f\x9b"
-			  "\xb6\x1d\xae\xef\xf0\x2f\xf8\x5a"
-			  "\x39\x3c\xbf\x2a\xb2\x45\xb2\x23"
-			  "\x1b\x63\x3c\xcf\xaa\xbe\xcf\x4e"
-			  "\xfa\xe8\x29\xc2\x20\x68\x2b\x3c"
-			  "\x2e\x8b\xf7\x6e\x25\xbd\xe3\x3d"
-			  "\x66\x27\xd6\xaf\xd6\x64\x3e\xe3"
-			  "\xe8\x58\x46\x97\x39\x51\x07\xde"
-			  "\xcb\x37\xbc\xa9\xc0\x5f\x75\xc3"
-			  "\x0e\x84\x23\x1d\x16\xd4\x1c\x59"
-			  "\x9c\x1a\x02\x55\xab\x3a\x97\x1d"
-			  "\xdf\xdd\xc7\x06\x51\xd7\x70\xae"
-			  "\x23\xc6\x8c\xf5\x1e\xa0\xe5\x82"
-			  "\xb8\xb2\xbf\x04\xa0\x32\x8e\x68"
-			  "\xeb\xaf\x6e\x2d\x94\x22\x2f\xce"
-			  "\x4c\xb5\x59\xe2\xa2\x2f\xa0\x98"
-			  "\x1a\x97\xc6\xd4\xb5\x00\x59\xf2"
-			  "\x84\x14\x72\xb1\x9a\x6e\xa3\x7f"
-			  "\xea\x20\xe7\xcb\x65\x77\x3a\xdf"
-			  "\xc8\x97\x67\x15\xc2\x2a\x27\xcc"
-			  "\x18\x55\xa1\x24\x0b\x24\x24\xaf"
-			  "\x5b\xec\x68\xb8\xc8\xf5\xba\x63"
-			  "\xff\xed\x89\xce\xd5\x3d\x88\xf3"
-			  "\x25\xef\x05\x7c\x3a\xef\xeb\xd8"
-			  "\x7a\x32\x0d\xd1\x1e\x58\x59\x99"
-			  "\x90\x25\xb5\x26\xb0\xe3\x2b\x6c"
-			  "\x4c\xa9\x8b\x84\x4f\x5e\x01\x50"
-			  "\x41\x30\x58\xc5\x62\x74\x52\x1d"
-			  "\x45\x24\x6a\x42\x64\x4f\x97\x1c"
-			  "\xa8\x66\xb5\x6d\x79\xd4\x0d\x48"
-			  "\xc5\x5f\xf3\x90\x32\xdd\xdd\xe1"
-			  "\xe4\xa9\x9f\xfc\xc3\x52\x5a\x46"
-			  "\xe4\x81\x84\x95\x36\x59\x7a\x6b"
-			  "\xaa\xb3\x60\xad\xce\x9f\x9f\x28"
-			  "\xe0\x01\x75\x22\xc4\x4e\xa9\x62"
-			  "\x5c\x62\x0d\x00\xcb\x13\xe8\x43"
-			  "\x72\xd4\x2d\x53\x46\xb5\xd1\x16"
-			  "\x22\x18\xdf\x34\x33\xf5\xd6\x1c"
-			  "\xb8\x79\x78\x97\x94\xff\x72\x13"
-			  "\x4c\x27\xfc\xcb\xbf\x01\x53\xa6"
-			  "\xb4\x50\x6e\xde\xdf\xb5\x43\xa4"
-			  "\x59\xdf\x52\xf9\x7c\xe0\x11\x6f"
-			  "\x2d\x14\x8e\x24\x61\x2c\xe1\x17"
-			  "\xcc\xce\x51\x0c\x19\x8a\x82\x30"
-			  "\x94\xd5\x3d\x6a\x53\x06\x5e\xbd"
-			  "\xb7\xeb\xfa\xfd\x27\x51\xde\x85"
-			  "\x1e\x86\x53\x11\x53\x94\x00\xee"
-			  "\x2b\x8c\x08\x2a\xbf\xdd\xae\x11"
-			  "\xcb\x1e\xa2\x07\x9a\x80\xcf\x62"
-			  "\x9b\x09\xdc\x95\x3c\x96\x8e\xb1"
-			  "\x09\xbd\xe4\xeb\xdb\xca\x70\x7a"
-			  "\x9e\xfa\x31\x18\x45\x3c\x21\x33"
-			  "\xb0\xb3\x2b\xea\xf3\x71\x2d\xe1"
-			  "\x03\xad\x1b\x48\xd4\x67\x27\xf0"
-			  "\x62\xe4\x3d\xfb\x9b\x08\x76\xe7"
-			  "\xdd\x2b\x01\x39\x04\x5a\x58\x7a"
-			  "\xf7\x11\x90\xec\xbd\x51\x5c\x32"
-			  "\x6b\xd7\x35\x39\x02\x6b\xf2\xa6"
-			  "\xd0\x0d\x07\xe1\x06\xc4\x5b\x7d"
-			  "\xe4\x6a\xd7\xee\x15\x1f\x83\xb4"
-			  "\xa3\xa7\x5e\xc3\x90\xb7\xef\xd3"
-			  "\xb7\x4f\xf8\x92\x4c\xb7\x3c\x29"
-			  "\xcd\x7e\x2b\x5d\x43\xea\x42\xe7"
-			  "\x74\x3f\x7d\x58\x88\x75\xde\x3e",
-		.rlen   = 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	}
-};
-
-static const struct cipher_testvec aes_lrw_dec_tv_template[] = {
-	/* from http://grouper.ieee.org/groups/1619/email/pdf00017.pdf */
-	/* same as enc vectors with input and result reversed */
-	{ /* LRW-32-AES 1 */
-		.key    = "\x45\x62\xac\x25\xf8\x28\x17\x6d"
-			  "\x4c\x26\x84\x14\xb5\x68\x01\x85"
-			  "\x25\x8e\x2a\x05\xe7\x3e\x9d\x03"
-			  "\xee\x5a\x83\x0c\xcc\x09\x4c\x87",
-		.klen   = 32,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input  = "\xf1\xb2\x73\xcd\x65\xa3\xdf\x5f"
-			  "\xe9\x5d\x48\x92\x54\x63\x4e\xb8",
-		.ilen   = 16,
-		.result = "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen   = 16,
-	}, { /* LRW-32-AES 2 */
-		.key    = "\x59\x70\x47\x14\xf5\x57\x47\x8c"
-			  "\xd7\x79\xe8\x0f\x54\x88\x79\x44"
-			  "\x0d\x48\xf0\xb7\xb1\x5a\x53\xea"
-			  "\x1c\xaa\x6b\x29\xc2\xca\xfb\xaf",
-		.klen   = 32,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input  = "\x00\xc8\x2b\xae\x95\xbb\xcd\xe5"
-			  "\x27\x4f\x07\x69\xb2\x60\xe1\x36",
-		.ilen   = 16,
-		.result  = "\x30\x31\x32\x33\x34\x35\x36\x37"
-			   "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen   = 16,
-	}, { /* LRW-32-AES 3 */
-		.key    = "\xd8\x2a\x91\x34\xb2\x6a\x56\x50"
-			  "\x30\xfe\x69\xe2\x37\x7f\x98\x47"
-			  "\xcd\xf9\x0b\x16\x0c\x64\x8f\xb6"
-			  "\xb0\x0d\x0d\x1b\xae\x85\x87\x1f",
-		.klen   = 32,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input  = "\x76\x32\x21\x83\xed\x8f\xf1\x82"
-			  "\xf9\x59\x62\x03\x69\x0e\x5e\x01",
-		.ilen   = 16,
-		.result = "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen   = 16,
-	}, { /* LRW-32-AES 4 */
-		.key    = "\x0f\x6a\xef\xf8\xd3\xd2\xbb\x15"
-			  "\x25\x83\xf7\x3c\x1f\x01\x28\x74"
-			  "\xca\xc6\xbc\x35\x4d\x4a\x65\x54"
-			  "\x90\xae\x61\xcf\x7b\xae\xbd\xcc"
-			  "\xad\xe4\x94\xc5\x4a\x29\xae\x70",
-		.klen   = 40,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input  = "\x9c\x0f\x15\x2f\x55\xa2\xd8\xf0"
-			  "\xd6\x7b\x8f\x9e\x28\x22\xbc\x41",
-		.ilen   = 16,
-		.result = "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen   = 16,
-	}, { /* LRW-32-AES 5 */
-		.key    = "\x8a\xd4\xee\x10\x2f\xbd\x81\xff"
-			  "\xf8\x86\xce\xac\x93\xc5\xad\xc6"
-			  "\xa0\x19\x07\xc0\x9d\xf7\xbb\xdd"
-			  "\x52\x13\xb2\xb7\xf0\xff\x11\xd8"
-			  "\xd6\x08\xd0\xcd\x2e\xb1\x17\x6f",
-		.klen   = 40,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input  = "\xd4\x27\x6a\x7f\x14\x91\x3d\x65"
-			  "\xc8\x60\x48\x02\x87\xe3\x34\x06",
-		.ilen   = 16,
-		.result = "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen   = 16,
-	}, { /* LRW-32-AES 6 */
-		.key    = "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen   = 48,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input  = "\xbd\x06\xb8\xe1\xdb\x98\x89\x9e"
-			  "\xc4\x98\xe4\x91\xcf\x1c\x70\x2b",
-		.ilen   = 16,
-		.result = "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen   = 16,
-	}, { /* LRW-32-AES 7 */
-		.key    = "\xfb\x76\x15\xb2\x3d\x80\x89\x1d"
-			  "\xd4\x70\x98\x0b\xc7\x95\x84\xc8"
-			  "\xb2\xfb\x64\xce\x60\x97\x87\x8d"
-			  "\x17\xfc\xe4\x5a\x49\xe8\x30\xb7"
-			  "\x6e\x78\x17\xe7\x2d\x5e\x12\xd4"
-			  "\x60\x64\x04\x7a\xf1\x2f\x9e\x0c",
-		.klen   = 48,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input  = "\x5b\x90\x8e\xc1\xab\xdd\x67\x5f"
-			  "\x3d\x69\x8a\x95\x53\xc8\x9c\xe5",
-		.ilen   = 16,
-		.result = "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen   = 16,
-	}, {
-/* http://www.mail-archive.com/stds-p1619@listserv.ieee.org/msg00173.html */
-		.key    = "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen   = 48,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x1a\x1d\xa9\x30\xad\xf9\x2f\x9b"
+		.ctext	= "\x1a\x1d\xa9\x30\xad\xf9\x2f\x9b"
 			  "\xb6\x1d\xae\xef\xf0\x2f\xf8\x5a"
 			  "\x39\x3c\xbf\x2a\xb2\x45\xb2\x23"
 			  "\x1b\x63\x3c\xcf\xaa\xbe\xcf\x4e"
@@ -20660,79 +13965,14 @@ static const struct cipher_testvec aes_lrw_dec_tv_template[] = {
 			  "\xb7\x4f\xf8\x92\x4c\xb7\x3c\x29"
 			  "\xcd\x7e\x2b\x5d\x43\xea\x42\xe7"
 			  "\x74\x3f\x7d\x58\x88\x75\xde\x3e",
-		.ilen   = 512,
-		.result	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
-			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
-			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
-			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
-			  "\x8f\xcb\x8d\x6b\xe3\xa6\x29\x90"
-			  "\xfe\x2a\x62\x82\xae\x6d\x8b\xf6"
-			  "\xad\x1e\x9e\x20\x5f\x38\xbe\x04"
-			  "\xda\x10\x8e\xed\xa2\xa4\x87\xab"
-			  "\xda\x6b\xb4\x0c\x75\xba\xd3\x7c"
-			  "\xc9\xac\x42\x31\x95\x7c\xc9\x04"
-			  "\xeb\xd5\x6e\x32\x69\x8a\xdb\xa6"
-			  "\x15\xd7\x3f\x4f\x2f\x66\x69\x03"
-			  "\x9c\x1f\x54\x0f\xde\x1f\xf3\x65"
-			  "\x4c\x96\x12\xed\x7c\x92\x03\x01"
-			  "\x6f\xbc\x35\x93\xac\xf1\x27\xf1"
-			  "\xb4\x96\x82\x5a\x5f\xb0\xa0\x50"
-			  "\x89\xa4\x8e\x66\x44\x85\xcc\xfd"
-			  "\x33\x14\x70\xe3\x96\xb2\xc3\xd3"
-			  "\xbb\x54\x5a\x1a\xf9\x74\xa2\xc5"
-			  "\x2d\x64\x75\xdd\xb4\x54\xe6\x74"
-			  "\x8c\xd3\x9d\x9e\x86\xab\x51\x53"
-			  "\xb7\x93\x3e\x6f\xd0\x4e\x2c\x40"
-			  "\xf6\xa8\x2e\x3e\x9d\xf4\x66\xa5"
-			  "\x76\x12\x73\x44\x1a\x56\xd7\x72"
-			  "\x88\xcd\x21\x8c\x4c\x0f\xfe\xda"
-			  "\x95\xe0\x3a\xa6\xa5\x84\x46\xcd"
-			  "\xd5\x3e\x9d\x3a\xe2\x67\xe6\x60"
-			  "\x1a\xe2\x70\x85\x58\xc2\x1b\x09"
-			  "\xe1\xd7\x2c\xca\xad\xa8\x8f\xf9"
-			  "\xac\xb3\x0e\xdb\xca\x2e\xe2\xb8"
-			  "\x51\x71\xd9\x3c\x6c\xf1\x56\xf8"
-			  "\xea\x9c\xf1\xfb\x0c\xe6\xb7\x10"
-			  "\x1c\xf8\xa9\x7c\xe8\x53\x35\xc1"
-			  "\x90\x3e\x76\x4a\x74\xa4\x21\x2c"
-			  "\xf6\x2c\x4e\x0f\x94\x3a\x88\x2e"
-			  "\x41\x09\x6a\x33\x7d\xf6\xdd\x3f"
-			  "\x8d\x23\x31\x74\x84\xeb\x88\x6e"
-			  "\xcc\xb9\xbc\x22\x83\x19\x07\x22"
-			  "\xa5\x2d\xdf\xa5\xf3\x80\x85\x78"
-			  "\x84\x39\x6a\x6d\x6a\x99\x4f\xa5"
-			  "\x15\xfe\x46\xb0\xe4\x6c\xa5\x41"
-			  "\x3c\xce\x8f\x42\x60\x71\xa7\x75"
-			  "\x08\x40\x65\x8a\x82\xbf\xf5\x43"
-			  "\x71\x96\xa9\x4d\x44\x8a\x20\xbe"
-			  "\xfa\x4d\xbb\xc0\x7d\x31\x96\x65"
-			  "\xe7\x75\xe5\x3e\xfd\x92\x3b\xc9"
-			  "\x55\xbb\x16\x7e\xf7\xc2\x8c\xa4"
-			  "\x40\x1d\xe5\xef\x0e\xdf\xe4\x9a"
-			  "\x62\x73\x65\xfd\x46\x63\x25\x3d"
-			  "\x2b\xaf\xe5\x64\xfe\xa5\x5c\xcf"
-			  "\x24\xf3\xb4\xac\x64\xba\xdf\x4b"
-			  "\xc6\x96\x7d\x81\x2d\x8d\x97\xf7"
-			  "\xc5\x68\x77\x84\x32\x2b\xcc\x85"
-			  "\x74\x96\xf0\x12\x77\x61\xb9\xeb"
-			  "\x71\xaa\x82\xcb\x1c\xdb\x89\xc8"
-			  "\xc6\xb5\xe3\x5c\x7d\x39\x07\x24"
-			  "\xda\x39\x87\x45\xc0\x2b\xbb\x01"
-			  "\xac\xbc\x2a\x5c\x7f\xfc\xe8\xce"
-			  "\x6d\x9c\x6f\xed\xd3\xc1\xa1\xd6"
-			  "\xc5\x55\xa9\x66\x2f\xe1\xc8\x32"
-			  "\xa6\x5d\xa4\x3a\x98\x73\xe8\x45"
-			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
-			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
-			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.rlen   = 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
 	}
 };
 
-static const struct cipher_testvec aes_xts_enc_tv_template[] = {
+static const struct cipher_testvec aes_xts_tv_template[] = {
 	/* http://grouper.ieee.org/groups/1619/email/pdf00086.pdf */
 	{ /* XTS-AES 1 */
 		.key    = "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -20743,16 +13983,15 @@ static const struct cipher_testvec aes_xts_enc_tv_template[] = {
 		.fips_skip = 1,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input  = "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen   = 32,
-		.result = "\x91\x7c\xf6\x9e\xbd\x68\xb2\xec"
+		.ctext	= "\x91\x7c\xf6\x9e\xbd\x68\xb2\xec"
 			  "\x9b\x9f\xe9\xa3\xea\xdd\xa6\x92"
 			  "\xcd\x43\xd2\xf5\x95\x98\xed\x85"
 			  "\x8c\x02\xc2\x65\x2f\xbf\x92\x2e",
-		.rlen   = 32,
+		.len	= 32,
 	}, { /* XTS-AES 2 */
 		.key    = "\x11\x11\x11\x11\x11\x11\x11\x11"
 			  "\x11\x11\x11\x11\x11\x11\x11\x11"
@@ -20761,16 +14000,15 @@ static const struct cipher_testvec aes_xts_enc_tv_template[] = {
 		.klen   = 32,
 		.iv     = "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input  = "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen   = 32,
-		.result = "\xc4\x54\x18\x5e\x6a\x16\x93\x6e"
+		.ctext	= "\xc4\x54\x18\x5e\x6a\x16\x93\x6e"
 			  "\x39\x33\x40\x38\xac\xef\x83\x8b"
 			  "\xfb\x18\x6f\xff\x74\x80\xad\xc4"
 			  "\x28\x93\x82\xec\xd6\xd3\x94\xf0",
-		.rlen   = 32,
+		.len	= 32,
 	}, { /* XTS-AES 3 */
 		.key    = "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
 			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
@@ -20779,16 +14017,15 @@ static const struct cipher_testvec aes_xts_enc_tv_template[] = {
 		.klen   = 32,
 		.iv     = "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input  = "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen   = 32,
-		.result = "\xaf\x85\x33\x6b\x59\x7a\xfc\x1a"
+		.ctext	= "\xaf\x85\x33\x6b\x59\x7a\xfc\x1a"
 			  "\x90\x0b\x2e\xb2\x1e\xc9\x49\xd2"
 			  "\x92\xdf\x4c\x04\x7e\x0b\x21\x53"
 			  "\x21\x86\xa5\x97\x1a\x22\x7a\x89",
-		.rlen   = 32,
+		.len	= 32,
 	}, { /* XTS-AES 4 */
 		.key    = "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -20797,7 +14034,7 @@ static const struct cipher_testvec aes_xts_enc_tv_template[] = {
 		.klen   = 32,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input  = "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -20861,8 +14098,7 @@ static const struct cipher_testvec aes_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen   = 512,
-		.result = "\x27\xa7\x47\x9b\xef\xa1\xd4\x76"
+		.ctext	= "\x27\xa7\x47\x9b\xef\xa1\xd4\x76"
 			  "\x48\x9f\x30\x8c\xd4\xcf\xa6\xe2"
 			  "\xa9\x6e\x4b\xbe\x32\x08\xff\x25"
 			  "\x28\x7d\xd3\x81\x96\x16\xe8\x9c"
@@ -20926,7 +14162,7 @@ static const struct cipher_testvec aes_xts_enc_tv_template[] = {
 			  "\xf2\x62\x73\x57\x79\xa4\x18\xf2"
 			  "\x0a\x28\x2d\xf9\x20\x14\x7b\xea"
 			  "\xbe\x42\x1e\xe5\x31\x9d\x05\x68",
-		.rlen   = 512,
+		.len	= 512,
 	}, { /* XTS-AES 10, XTS-AES-256, data unit 512 bytes */
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -20939,273 +14175,7 @@ static const struct cipher_testvec aes_xts_enc_tv_template[] = {
 		.klen	= 64,
 		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\x1c\x3b\x3a\x10\x2f\x77\x03\x86"
-			  "\xe4\x83\x6c\x99\xe3\x70\xcf\x9b"
-			  "\xea\x00\x80\x3f\x5e\x48\x23\x57"
-			  "\xa4\xae\x12\xd4\x14\xa3\xe6\x3b"
-			  "\x5d\x31\xe2\x76\xf8\xfe\x4a\x8d"
-			  "\x66\xb3\x17\xf9\xac\x68\x3f\x44"
-			  "\x68\x0a\x86\xac\x35\xad\xfc\x33"
-			  "\x45\xbe\xfe\xcb\x4b\xb1\x88\xfd"
-			  "\x57\x76\x92\x6c\x49\xa3\x09\x5e"
-			  "\xb1\x08\xfd\x10\x98\xba\xec\x70"
-			  "\xaa\xa6\x69\x99\xa7\x2a\x82\xf2"
-			  "\x7d\x84\x8b\x21\xd4\xa7\x41\xb0"
-			  "\xc5\xcd\x4d\x5f\xff\x9d\xac\x89"
-			  "\xae\xba\x12\x29\x61\xd0\x3a\x75"
-			  "\x71\x23\xe9\x87\x0f\x8a\xcf\x10"
-			  "\x00\x02\x08\x87\x89\x14\x29\xca"
-			  "\x2a\x3e\x7a\x7d\x7d\xf7\xb1\x03"
-			  "\x55\x16\x5c\x8b\x9a\x6d\x0a\x7d"
-			  "\xe8\xb0\x62\xc4\x50\x0d\xc4\xcd"
-			  "\x12\x0c\x0f\x74\x18\xda\xe3\xd0"
-			  "\xb5\x78\x1c\x34\x80\x3f\xa7\x54"
-			  "\x21\xc7\x90\xdf\xe1\xde\x18\x34"
-			  "\xf2\x80\xd7\x66\x7b\x32\x7f\x6c"
-			  "\x8c\xd7\x55\x7e\x12\xac\x3a\x0f"
-			  "\x93\xec\x05\xc5\x2e\x04\x93\xef"
-			  "\x31\xa1\x2d\x3d\x92\x60\xf7\x9a"
-			  "\x28\x9d\x6a\x37\x9b\xc7\x0c\x50"
-			  "\x84\x14\x73\xd1\xa8\xcc\x81\xec"
-			  "\x58\x3e\x96\x45\xe0\x7b\x8d\x96"
-			  "\x70\x65\x5b\xa5\xbb\xcf\xec\xc6"
-			  "\xdc\x39\x66\x38\x0a\xd8\xfe\xcb"
-			  "\x17\xb6\xba\x02\x46\x9a\x02\x0a"
-			  "\x84\xe1\x8e\x8f\x84\x25\x20\x70"
-			  "\xc1\x3e\x9f\x1f\x28\x9b\xe5\x4f"
-			  "\xbc\x48\x14\x57\x77\x8f\x61\x60"
-			  "\x15\xe1\x32\x7a\x02\xb1\x40\xf1"
-			  "\x50\x5e\xb3\x09\x32\x6d\x68\x37"
-			  "\x8f\x83\x74\x59\x5c\x84\x9d\x84"
-			  "\xf4\xc3\x33\xec\x44\x23\x88\x51"
-			  "\x43\xcb\x47\xbd\x71\xc5\xed\xae"
-			  "\x9b\xe6\x9a\x2f\xfe\xce\xb1\xbe"
-			  "\xc9\xde\x24\x4f\xbe\x15\x99\x2b"
-			  "\x11\xb7\x7c\x04\x0f\x12\xbd\x8f"
-			  "\x6a\x97\x5a\x44\xa0\xf9\x0c\x29"
-			  "\xa9\xab\xc3\xd4\xd8\x93\x92\x72"
-			  "\x84\xc5\x87\x54\xcc\xe2\x94\x52"
-			  "\x9f\x86\x14\xdc\xd2\xab\xa9\x91"
-			  "\x92\x5f\xed\xc4\xae\x74\xff\xac"
-			  "\x6e\x33\x3b\x93\xeb\x4a\xff\x04"
-			  "\x79\xda\x9a\x41\x0e\x44\x50\xe0"
-			  "\xdd\x7a\xe4\xc6\xe2\x91\x09\x00"
-			  "\x57\x5d\xa4\x01\xfc\x07\x05\x9f"
-			  "\x64\x5e\x8b\x7e\x9b\xfd\xef\x33"
-			  "\x94\x30\x54\xff\x84\x01\x14\x93"
-			  "\xc2\x7b\x34\x29\xea\xed\xb4\xed"
-			  "\x53\x76\x44\x1a\x77\xed\x43\x85"
-			  "\x1a\xd7\x7f\x16\xf5\x41\xdf\xd2"
-			  "\x69\xd5\x0d\x6a\x5f\x14\xfb\x0a"
-			  "\xab\x1c\xbb\x4c\x15\x50\xbe\x97"
-			  "\xf7\xab\x40\x66\x19\x3c\x4c\xaa"
-			  "\x77\x3d\xad\x38\x01\x4b\xd2\x09"
-			  "\x2f\xa7\x55\xc8\x24\xbb\x5e\x54"
-			  "\xc4\xf3\x6f\xfd\xa9\xfc\xea\x70"
-			  "\xb9\xc6\xe6\x93\xe1\x48\xc1\x51",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	}
-};
-
-static const struct cipher_testvec aes_xts_dec_tv_template[] = {
-	/* http://grouper.ieee.org/groups/1619/email/pdf00086.pdf */
-	{ /* XTS-AES 1 */
-		.key    = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen   = 32,
-		.fips_skip = 1,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input = "\x91\x7c\xf6\x9e\xbd\x68\xb2\xec"
-			 "\x9b\x9f\xe9\xa3\xea\xdd\xa6\x92"
-			 "\xcd\x43\xd2\xf5\x95\x98\xed\x85"
-			 "\x8c\x02\xc2\x65\x2f\xbf\x92\x2e",
-		.ilen   = 32,
-		.result  = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			   "\x00\x00\x00\x00\x00\x00\x00\x00"
-			   "\x00\x00\x00\x00\x00\x00\x00\x00"
-			   "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen   = 32,
-	}, { /* XTS-AES 2 */
-		.key    = "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen   = 32,
-		.iv     = "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input  = "\xc4\x54\x18\x5e\x6a\x16\x93\x6e"
-			  "\x39\x33\x40\x38\xac\xef\x83\x8b"
-			  "\xfb\x18\x6f\xff\x74\x80\xad\xc4"
-			  "\x28\x93\x82\xec\xd6\xd3\x94\xf0",
-		.ilen   = 32,
-		.result = "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen   = 32,
-	}, { /* XTS-AES 3 */
-		.key    = "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
-			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen   = 32,
-		.iv     = "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input = "\xaf\x85\x33\x6b\x59\x7a\xfc\x1a"
-			  "\x90\x0b\x2e\xb2\x1e\xc9\x49\xd2"
-			  "\x92\xdf\x4c\x04\x7e\x0b\x21\x53"
-			  "\x21\x86\xa5\x97\x1a\x22\x7a\x89",
-		.ilen   = 32,
-		.result  = "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen   = 32,
-	}, { /* XTS-AES 4 */
-		.key    = "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95",
-		.klen   = 32,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input  = "\x27\xa7\x47\x9b\xef\xa1\xd4\x76"
-			  "\x48\x9f\x30\x8c\xd4\xcf\xa6\xe2"
-			  "\xa9\x6e\x4b\xbe\x32\x08\xff\x25"
-			  "\x28\x7d\xd3\x81\x96\x16\xe8\x9c"
-			  "\xc7\x8c\xf7\xf5\xe5\x43\x44\x5f"
-			  "\x83\x33\xd8\xfa\x7f\x56\x00\x00"
-			  "\x05\x27\x9f\xa5\xd8\xb5\xe4\xad"
-			  "\x40\xe7\x36\xdd\xb4\xd3\x54\x12"
-			  "\x32\x80\x63\xfd\x2a\xab\x53\xe5"
-			  "\xea\x1e\x0a\x9f\x33\x25\x00\xa5"
-			  "\xdf\x94\x87\xd0\x7a\x5c\x92\xcc"
-			  "\x51\x2c\x88\x66\xc7\xe8\x60\xce"
-			  "\x93\xfd\xf1\x66\xa2\x49\x12\xb4"
-			  "\x22\x97\x61\x46\xae\x20\xce\x84"
-			  "\x6b\xb7\xdc\x9b\xa9\x4a\x76\x7a"
-			  "\xae\xf2\x0c\x0d\x61\xad\x02\x65"
-			  "\x5e\xa9\x2d\xc4\xc4\xe4\x1a\x89"
-			  "\x52\xc6\x51\xd3\x31\x74\xbe\x51"
-			  "\xa1\x0c\x42\x11\x10\xe6\xd8\x15"
-			  "\x88\xed\xe8\x21\x03\xa2\x52\xd8"
-			  "\xa7\x50\xe8\x76\x8d\xef\xff\xed"
-			  "\x91\x22\x81\x0a\xae\xb9\x9f\x91"
-			  "\x72\xaf\x82\xb6\x04\xdc\x4b\x8e"
-			  "\x51\xbc\xb0\x82\x35\xa6\xf4\x34"
-			  "\x13\x32\xe4\xca\x60\x48\x2a\x4b"
-			  "\xa1\xa0\x3b\x3e\x65\x00\x8f\xc5"
-			  "\xda\x76\xb7\x0b\xf1\x69\x0d\xb4"
-			  "\xea\xe2\x9c\x5f\x1b\xad\xd0\x3c"
-			  "\x5c\xcf\x2a\x55\xd7\x05\xdd\xcd"
-			  "\x86\xd4\x49\x51\x1c\xeb\x7e\xc3"
-			  "\x0b\xf1\x2b\x1f\xa3\x5b\x91\x3f"
-			  "\x9f\x74\x7a\x8a\xfd\x1b\x13\x0e"
-			  "\x94\xbf\xf9\x4e\xff\xd0\x1a\x91"
-			  "\x73\x5c\xa1\x72\x6a\xcd\x0b\x19"
-			  "\x7c\x4e\x5b\x03\x39\x36\x97\xe1"
-			  "\x26\x82\x6f\xb6\xbb\xde\x8e\xcc"
-			  "\x1e\x08\x29\x85\x16\xe2\xc9\xed"
-			  "\x03\xff\x3c\x1b\x78\x60\xf6\xde"
-			  "\x76\xd4\xce\xcd\x94\xc8\x11\x98"
-			  "\x55\xef\x52\x97\xca\x67\xe9\xf3"
-			  "\xe7\xff\x72\xb1\xe9\x97\x85\xca"
-			  "\x0a\x7e\x77\x20\xc5\xb3\x6d\xc6"
-			  "\xd7\x2c\xac\x95\x74\xc8\xcb\xbc"
-			  "\x2f\x80\x1e\x23\xe5\x6f\xd3\x44"
-			  "\xb0\x7f\x22\x15\x4b\xeb\xa0\xf0"
-			  "\x8c\xe8\x89\x1e\x64\x3e\xd9\x95"
-			  "\xc9\x4d\x9a\x69\xc9\xf1\xb5\xf4"
-			  "\x99\x02\x7a\x78\x57\x2a\xee\xbd"
-			  "\x74\xd2\x0c\xc3\x98\x81\xc2\x13"
-			  "\xee\x77\x0b\x10\x10\xe4\xbe\xa7"
-			  "\x18\x84\x69\x77\xae\x11\x9f\x7a"
-			  "\x02\x3a\xb5\x8c\xca\x0a\xd7\x52"
-			  "\xaf\xe6\x56\xbb\x3c\x17\x25\x6a"
-			  "\x9f\x6e\x9b\xf1\x9f\xdd\x5a\x38"
-			  "\xfc\x82\xbb\xe8\x72\xc5\x53\x9e"
-			  "\xdb\x60\x9e\xf4\xf7\x9c\x20\x3e"
-			  "\xbb\x14\x0f\x2e\x58\x3c\xb2\xad"
-			  "\x15\xb4\xaa\x5b\x65\x50\x16\xa8"
-			  "\x44\x92\x77\xdb\xd4\x77\xef\x2c"
-			  "\x8d\x6c\x01\x7d\xb7\x38\xb1\x8d"
-			  "\xeb\x4a\x42\x7d\x19\x23\xce\x3f"
-			  "\xf2\x62\x73\x57\x79\xa4\x18\xf2"
-			  "\x0a\x28\x2d\xf9\x20\x14\x7b\xea"
-			  "\xbe\x42\x1e\xe5\x31\x9d\x05\x68",
-		.ilen   = 512,
-		.result = "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -21269,20 +14239,7 @@ static const struct cipher_testvec aes_xts_dec_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen   = 512,
-	}, { /* XTS-AES 10, XTS-AES-256, data unit 512 bytes */
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x62\x49\x77\x57\x24\x70\x93\x69"
-			  "\x99\x59\x57\x49\x66\x96\x76\x27"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95"
-			  "\x02\x88\x41\x97\x16\x93\x99\x37"
-			  "\x51\x05\x82\x09\x74\x94\x45\x92",
-		.klen	= 64,
-		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x1c\x3b\x3a\x10\x2f\x77\x03\x86"
+		.ctext	= "\x1c\x3b\x3a\x10\x2f\x77\x03\x86"
 			  "\xe4\x83\x6c\x99\xe3\x70\xcf\x9b"
 			  "\xea\x00\x80\x3f\x5e\x48\x23\x57"
 			  "\xa4\xae\x12\xd4\x14\xa3\xe6\x3b"
@@ -21346,87 +14303,21 @@ static const struct cipher_testvec aes_xts_dec_tv_template[] = {
 			  "\x2f\xa7\x55\xc8\x24\xbb\x5e\x54"
 			  "\xc4\xf3\x6f\xfd\xa9\xfc\xea\x70"
 			  "\xb9\xc6\xe6\x93\xe1\x48\xc1\x51",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
 	}
 };
 
-
-static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
+static const struct cipher_testvec aes_ctr_tv_template[] = {
 	{ /* From NIST Special Publication 800-38A, Appendix F.5 */
 		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
 			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
 		.klen	= 16,
 		.iv	= "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.input	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
 			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
@@ -21434,8 +14325,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
 			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
 			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ilen	= 64,
-		.result	= "\x87\x4d\x61\x91\xb6\x20\xe3\x26"
+		.ctext	= "\x87\x4d\x61\x91\xb6\x20\xe3\x26"
 			  "\x1b\xef\x68\x64\x99\x0d\xb6\xce"
 			  "\x98\x06\xf6\x6b\x79\x70\xfd\xff"
 			  "\x86\x17\x18\x7b\xb9\xff\xfd\xff"
@@ -21443,7 +14333,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\x5b\x4f\x09\x02\x0d\xb0\x3e\xab"
 			  "\x1e\x03\x1d\xda\x2f\xbe\x03\xd1"
 			  "\x79\x21\x70\xa0\xf3\x00\x9c\xee",
-		.rlen	= 64,
+		.len	= 64,
 	}, {
 		.key	= "\x8e\x73\xb0\xf7\xda\x0e\x64\x52"
 			  "\xc8\x10\xf3\x2b\x80\x90\x79\xe5"
@@ -21451,7 +14341,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 		.klen	= 24,
 		.iv	= "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.input	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
 			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
@@ -21459,8 +14349,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
 			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
 			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ilen	= 64,
-		.result	= "\x1a\xbc\x93\x24\x17\x52\x1c\xa2"
+		.ctext	= "\x1a\xbc\x93\x24\x17\x52\x1c\xa2"
 			  "\x4f\x2b\x04\x59\xfe\x7e\x6e\x0b"
 			  "\x09\x03\x39\xec\x0a\xa6\xfa\xef"
 			  "\xd5\xcc\xc2\xc6\xf4\xce\x8e\x94"
@@ -21468,7 +14357,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\xd1\xbd\x1d\x66\x56\x20\xab\xf7"
 			  "\x4f\x78\xa7\xf6\xd2\x98\x09\x58"
 			  "\x5a\x97\xda\xec\x58\xc6\xb0\x50",
-		.rlen	= 64,
+		.len	= 64,
 	}, {
 		.key	= "\x60\x3d\xeb\x10\x15\xca\x71\xbe"
 			  "\x2b\x73\xae\xf0\x85\x7d\x77\x81"
@@ -21477,7 +14366,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.input	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
 			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
@@ -21485,8 +14374,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
 			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
 			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ilen	= 64,
-		.result	= "\x60\x1e\xc3\x13\x77\x57\x89\xa5"
+		.ctext	= "\x60\x1e\xc3\x13\x77\x57\x89\xa5"
 			  "\xb7\xa7\xf5\x04\xbb\xf3\xd2\x28"
 			  "\xf4\x43\xe3\xca\x4d\x62\xb5\x9a"
 			  "\xca\x84\xe9\x90\xca\xca\xf5\xc5"
@@ -21494,7 +14382,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\xe8\x70\x17\xba\x2d\x84\x98\x8d"
 			  "\xdf\xc9\xc5\x8d\xb6\x7a\xad\xa6"
 			  "\x13\xc2\xdd\x08\x45\x79\x41\xa6",
-		.rlen	= 64,
+		.len	= 64,
 	}, { /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55"
 			  "\x0F\x32\x55\x78\x9B\xBE\x78\x9B"
@@ -21503,7 +14391,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
 			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
+		.ptext	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
 			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
 			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
 			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
@@ -21565,8 +14453,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\xAE\x17\xA3\x0C\x75\x01\x6A\xD3"
 			  "\x3C\xC8\x31\x9A\x03\x8F\xF8\x61"
 			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
-		.ilen	= 496,
-		.result	= "\x04\xF3\xD3\x88\x17\xEF\xDC\xEF"
+		.ctext	= "\x04\xF3\xD3\x88\x17\xEF\xDC\xEF"
 			  "\x8B\x04\xF8\x3A\x66\x8D\x1A\x53"
 			  "\x57\x1F\x4B\x23\xE4\xA0\xAF\xF9"
 			  "\x69\x95\x35\x98\x8D\x4D\x8C\xC1"
@@ -21628,7 +14515,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\x10\x09\x9B\x46\x9B\xF2\x2C\x2B"
 			  "\xFA\x3A\x05\x4C\xFA\xD1\xFF\xFE"
 			  "\xF1\x4C\xE5\xB2\x91\x64\x0C\x51",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
@@ -21640,7 +14527,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE7\x82\x1D\xB8\x53\x11\xAC\x47"
 			  "\xE2\x7D\x18\xD6\x71\x0C\xA7\x42",
-		.input	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
+		.ptext	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
 			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
 			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
 			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
@@ -21703,299 +14590,7 @@ static const struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\x3C\xC8\x31\x9A\x03\x8F\xF8\x61"
 			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12"
 			  "\x7B\xE4\x4D",
-		.ilen	= 499,
-		.result	= "\xDA\x4E\x3F\xBC\xE8\xB6\x3A\xA2"
-			  "\xD5\x4D\x84\x4A\xA9\x0C\xE1\xA5"
-			  "\xB8\x73\xBC\xF9\xBB\x59\x2F\x44"
-			  "\x8B\xAB\x82\x6C\xB4\x32\x9A\xDE"
-			  "\x5A\x0B\xDB\x7A\x6B\xF2\x38\x9F"
-			  "\x06\xF7\xF7\xFF\xFF\xC0\x8A\x2E"
-			  "\x76\xEA\x06\x32\x23\xF3\x59\x2E"
-			  "\x75\xDE\x71\x86\x3C\x98\x23\x44"
-			  "\x5B\xF2\xFA\x6A\x00\xBB\xC1\xAD"
-			  "\x58\xBD\x3E\x6F\x2E\xB4\x19\x04"
-			  "\x70\x8B\x92\x55\x23\xE9\x6A\x3A"
-			  "\x78\x7A\x1B\x10\x85\x52\x9C\x12"
-			  "\xE4\x55\x81\x21\xCE\x53\xD0\x3B"
-			  "\x63\x77\x2C\x74\xD1\xF5\x60\xF3"
-			  "\xA1\xDE\x44\x3C\x8F\x4D\x2F\xDD"
-			  "\x8A\xFE\x3C\x42\x8E\xD3\xF2\x8E"
-			  "\xA8\x28\x69\x65\x31\xE1\x45\x83"
-			  "\xE4\x49\xC4\x9C\xA7\x28\xAA\x21"
-			  "\xCD\x5D\x0F\x15\xB7\x93\x07\x26"
-			  "\xB0\x65\x6D\x91\x90\x23\x7A\xC6"
-			  "\xDB\x68\xB0\xA1\x8E\xA4\x76\x4E"
-			  "\xC6\x91\x83\x20\x92\x4D\x63\x7A"
-			  "\x45\x18\x18\x74\x19\xAD\x71\x01"
-			  "\x6B\x23\xAD\x9D\x4E\xE4\x6E\x46"
-			  "\xC9\x73\x7A\xF9\x02\x95\xF4\x07"
-			  "\x0E\x7A\xA6\xC5\xAE\xFA\x15\x2C"
-			  "\x51\x71\xF1\xDC\x22\xB6\xAC\xD8"
-			  "\x19\x24\x44\xBC\x0C\xFB\x3C\x2D"
-			  "\xB1\x50\x47\x15\x0E\xDB\xB6\xD7"
-			  "\xE8\x61\xE5\x95\x52\x1E\x3E\x49"
-			  "\x70\xE9\x66\x04\x4C\xE1\xAF\xBD"
-			  "\xDD\x15\x3B\x20\x59\x24\xFF\xB0"
-			  "\x39\xAA\xE7\xBF\x23\xA3\x6E\xD5"
-			  "\x15\xF0\x61\x4F\xAE\x89\x10\x58"
-			  "\x5A\x33\x95\x52\x2A\xB5\x77\x9C"
-			  "\xA5\x43\x80\x40\x27\x2D\xAE\xD9"
-			  "\x3F\xE0\x80\x94\x78\x79\xCB\x7E"
-			  "\xAD\x12\x44\x4C\xEC\x27\xB0\xEE"
-			  "\x0B\x05\x2A\x82\x99\x58\xBB\x7A"
-			  "\x8D\x6D\x9D\x8E\xE2\x8E\xE7\x93"
-			  "\x2F\xB3\x09\x8D\x06\xD5\xEE\x70"
-			  "\x16\xAE\x35\xC5\x52\x0F\x46\x1F"
-			  "\x71\xF9\x5E\xF2\x67\xDC\x98\x2F"
-			  "\xA3\x23\xAA\xD5\xD0\x49\xF4\xA6"
-			  "\xF6\xB8\x32\xCD\xD6\x85\x73\x60"
-			  "\x59\x20\xE7\x55\x0E\x91\xE2\x0C"
-			  "\x3F\x1C\xEB\x3D\xDF\x52\x64\xF2"
-			  "\x7D\x8B\x5D\x63\x16\xB9\xB2\x5D"
-			  "\x5E\xAB\xB2\x97\xAB\x78\x44\xE7"
-			  "\xC6\x72\x20\xC5\x90\x9B\xDC\x5D"
-			  "\xB0\xEF\x44\xEF\x87\x31\x8D\xF4"
-			  "\xFB\x81\x5D\xF7\x96\x96\xD4\x50"
-			  "\x89\xA7\xF6\xB9\x67\x76\x40\x9E"
-			  "\x9D\x40\xD5\x2C\x30\xB8\x01\x8F"
-			  "\xE4\x7B\x71\x48\xA9\xA0\xA0\x1D"
-			  "\x87\x52\xA4\x91\xA9\xD7\xA9\x51"
-			  "\xD9\x59\xF7\xCC\x63\x22\xC1\x8D"
-			  "\x84\x7B\xD8\x22\x32\x5C\x6F\x1D"
-			  "\x6E\x9F\xFA\xDD\x49\x40\xDC\x37"
-			  "\x14\x8C\xE1\x80\x1B\xDD\x36\x2A"
-			  "\xD0\xE9\x54\x99\x5D\xBA\x3B\x11"
-			  "\xD8\xFE\xC9\x5B\x5C\x25\xE5\x76"
-			  "\xFB\xF2\x3F",
-		.rlen	= 499,
-		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 499 - 16, 16 },
-	},
-};
-
-static const struct cipher_testvec aes_ctr_dec_tv_template[] = {
-	{ /* From NIST Special Publication 800-38A, Appendix F.5 */
-		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
-			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
-		.klen	= 16,
-		.iv	= "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.input	= "\x87\x4d\x61\x91\xb6\x20\xe3\x26"
-			  "\x1b\xef\x68\x64\x99\x0d\xb6\xce"
-			  "\x98\x06\xf6\x6b\x79\x70\xfd\xff"
-			  "\x86\x17\x18\x7b\xb9\xff\xfd\xff"
-			  "\x5a\xe4\xdf\x3e\xdb\xd5\xd3\x5e"
-			  "\x5b\x4f\x09\x02\x0d\xb0\x3e\xab"
-			  "\x1e\x03\x1d\xda\x2f\xbe\x03\xd1"
-			  "\x79\x21\x70\xa0\xf3\x00\x9c\xee",
-		.ilen	= 64,
-		.result	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.rlen	= 64,
-	}, {
-		.key	= "\x8e\x73\xb0\xf7\xda\x0e\x64\x52"
-			  "\xc8\x10\xf3\x2b\x80\x90\x79\xe5"
-			  "\x62\xf8\xea\xd2\x52\x2c\x6b\x7b",
-		.klen	= 24,
-		.iv	= "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.input	= "\x1a\xbc\x93\x24\x17\x52\x1c\xa2"
-			  "\x4f\x2b\x04\x59\xfe\x7e\x6e\x0b"
-			  "\x09\x03\x39\xec\x0a\xa6\xfa\xef"
-			  "\xd5\xcc\xc2\xc6\xf4\xce\x8e\x94"
-			  "\x1e\x36\xb2\x6b\xd1\xeb\xc6\x70"
-			  "\xd1\xbd\x1d\x66\x56\x20\xab\xf7"
-			  "\x4f\x78\xa7\xf6\xd2\x98\x09\x58"
-			  "\x5a\x97\xda\xec\x58\xc6\xb0\x50",
-		.ilen	= 64,
-		.result	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.rlen	= 64,
-	}, {
-		.key	= "\x60\x3d\xeb\x10\x15\xca\x71\xbe"
-			  "\x2b\x73\xae\xf0\x85\x7d\x77\x81"
-			  "\x1f\x35\x2c\x07\x3b\x61\x08\xd7"
-			  "\x2d\x98\x10\xa3\x09\x14\xdf\xf4",
-		.klen	= 32,
-		.iv	= "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.input	= "\x60\x1e\xc3\x13\x77\x57\x89\xa5"
-			  "\xb7\xa7\xf5\x04\xbb\xf3\xd2\x28"
-			  "\xf4\x43\xe3\xca\x4d\x62\xb5\x9a"
-			  "\xca\x84\xe9\x90\xca\xca\xf5\xc5"
-			  "\x2b\x09\x30\xda\xa2\x3d\xe9\x4c"
-			  "\xe8\x70\x17\xba\x2d\x84\x98\x8d"
-			  "\xdf\xc9\xc5\x8d\xb6\x7a\xad\xa6"
-			  "\x13\xc2\xdd\x08\x45\x79\x41\xa6",
-		.ilen	= 64,
-		.result	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.rlen	= 64,
-	}, { /* Generated with Crypto++ */
-		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55"
-			  "\x0F\x32\x55\x78\x9B\xBE\x78\x9B"
-			  "\xBE\xE1\x04\x27\xE1\x04\x27\x4A"
-			  "\x6D\x90\x4A\x6D\x90\xB3\xD6\xF9",
-		.klen	= 32,
-		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
-			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x04\xF3\xD3\x88\x17\xEF\xDC\xEF"
-			  "\x8B\x04\xF8\x3A\x66\x8D\x1A\x53"
-			  "\x57\x1F\x4B\x23\xE4\xA0\xAF\xF9"
-			  "\x69\x95\x35\x98\x8D\x4D\x8C\xC1"
-			  "\xF0\xB2\x7F\x80\xBB\x54\x28\xA2"
-			  "\x7A\x1B\x9F\x77\xEC\x0E\x6E\xDE"
-			  "\xF0\xEC\xB8\xE4\x20\x62\xEE\xDB"
-			  "\x5D\xF5\xDD\xE3\x54\xFC\xDD\xEB"
-			  "\x6A\xEE\x65\xA1\x21\xD6\xD7\x81"
-			  "\x47\x61\x12\x4D\xC2\x8C\xFA\x78"
-			  "\x1F\x28\x02\x01\xC3\xFC\x1F\xEC"
-			  "\x0F\x10\x4F\xB3\x12\x45\xC6\x3B"
-			  "\x7E\x08\xF9\x5A\xD0\x5D\x73\x2D"
-			  "\x58\xA4\xE5\xCB\x1C\xB4\xCE\x74"
-			  "\x32\x41\x1F\x31\x9C\x08\xA2\x5D"
-			  "\x67\xEB\x72\x1D\xF8\xE7\x70\x54"
-			  "\x34\x4B\x31\x69\x84\x66\x96\x44"
-			  "\x56\xCC\x1E\xD9\xE6\x13\x6A\xB9"
-			  "\x2D\x0A\x05\x45\x2D\x90\xCC\xDF"
-			  "\x16\x5C\x5F\x79\x34\x52\x54\xFE"
-			  "\xFE\xCD\xAD\x04\x2E\xAD\x86\x06"
-			  "\x1F\x37\xE8\x28\xBC\xD3\x8F\x5B"
-			  "\x92\x66\x87\x3B\x8A\x0A\x1A\xCC"
-			  "\x6E\xAB\x9F\x0B\xFA\x5C\xE6\xFD"
-			  "\x3C\x98\x08\x12\xEC\xAA\x9E\x11"
-			  "\xCA\xB2\x1F\xCE\x5E\x5B\xB2\x72"
-			  "\x9C\xCC\x5D\xC5\xE0\x32\xC0\x56"
-			  "\xD5\x45\x16\xD2\xAF\x13\x66\xF7"
-			  "\x8C\x67\xAC\x79\xB2\xAF\x56\x27"
-			  "\x3F\xCC\xFE\xCB\x1E\xC0\x75\xF1"
-			  "\xA7\xC9\xC3\x1D\x8E\xDD\xF9\xD4"
-			  "\x42\xC8\x21\x08\x16\xF7\x01\xD7"
-			  "\xAC\x8E\x3F\x1D\x56\xC1\x06\xE4"
-			  "\x9C\x62\xD6\xA5\x6A\x50\x44\xB3"
-			  "\x35\x1C\x82\xB9\x10\xF9\x42\xA1"
-			  "\xFC\x74\x9B\x44\x4F\x25\x02\xE3"
-			  "\x08\xF5\xD4\x32\x39\x08\x11\xE8"
-			  "\xD2\x6B\x50\x53\xD4\x08\xD1\x6B"
-			  "\x3A\x4A\x68\x7B\x7C\xCD\x46\x5E"
-			  "\x0D\x07\x19\xDB\x67\xD7\x98\x91"
-			  "\xD7\x17\x10\x9B\x7B\x8A\x9B\x33"
-			  "\xAE\xF3\x00\xA6\xD4\x15\xD9\xEA"
-			  "\x85\x99\x22\xE8\x91\x38\x70\x83"
-			  "\x93\x01\x24\x6C\xFA\x9A\xB9\x07"
-			  "\xEA\x8D\x3B\xD9\x2A\x43\x59\x16"
-			  "\x2F\x69\xEE\x84\x36\x44\x76\x98"
-			  "\xF3\x04\x2A\x7C\x74\x3D\x29\x2B"
-			  "\x0D\xAD\x8F\x44\x82\x9E\x57\x8D"
-			  "\xAC\xED\x18\x1F\x50\xA4\xF5\x98"
-			  "\x1F\xBD\x92\x91\x1B\x2D\xA6\xD6"
-			  "\xD2\xE3\x02\xAA\x92\x3B\xC6\xB3"
-			  "\x1B\x39\x72\xD5\x26\xCA\x04\xE0"
-			  "\xFC\x58\x78\xBB\xB1\x3F\xA1\x9C"
-			  "\x42\x24\x3E\x2E\x22\xBB\x4B\xBA"
-			  "\xF4\x52\x0A\xE6\xAE\x47\xB4\x7D"
-			  "\x1D\xA8\xBE\x81\x1A\x75\xDA\xAC"
-			  "\xA6\x25\x1E\xEF\x3A\xC0\x6C\x63"
-			  "\xEF\xDC\xC9\x79\x10\x26\xE8\x61"
-			  "\x29\xFC\xA4\x05\xDF\x7D\x5C\x63"
-			  "\x10\x09\x9B\x46\x9B\xF2\x2C\x2B"
-			  "\xFA\x3A\x05\x4C\xFA\xD1\xFF\xFE"
-			  "\xF1\x4C\xE5\xB2\x91\x64\x0C\x51",
-		.ilen	= 496,
-		.result	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
-			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
-			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
-			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
-			  "\xAB\x14\x7D\x09\x72\xDB\x44\xD0"
-			  "\x39\xA2\x0B\x97\x00\x69\xF5\x5E"
-			  "\xC7\x30\xBC\x25\x8E\x1A\x83\xEC"
-			  "\x55\xE1\x4A\xB3\x1C\xA8\x11\x7A"
-			  "\x06\x6F\xD8\x41\xCD\x36\x9F\x08"
-			  "\x94\xFD\x66\xF2\x5B\xC4\x2D\xB9"
-			  "\x22\x8B\x17\x80\xE9\x52\xDE\x47"
-			  "\xB0\x19\xA5\x0E\x77\x03\x6C\xD5"
-			  "\x3E\xCA\x33\x9C\x05\x91\xFA\x63"
-			  "\xEF\x58\xC1\x2A\xB6\x1F\x88\x14"
-			  "\x7D\xE6\x4F\xDB\x44\xAD\x16\xA2"
-			  "\x0B\x74\x00\x69\xD2\x3B\xC7\x30"
-			  "\x99\x02\x8E\xF7\x60\xEC\x55\xBE"
-			  "\x27\xB3\x1C\x85\x11\x7A\xE3\x4C"
-			  "\xD8\x41\xAA\x13\x9F\x08\x71\xFD"
-			  "\x66\xCF\x38\xC4\x2D\x96\x22\x8B"
-			  "\xF4\x5D\xE9\x52\xBB\x24\xB0\x19"
-			  "\x82\x0E\x77\xE0\x49\xD5\x3E\xA7"
-			  "\x10\x9C\x05\x6E\xFA\x63\xCC\x35"
-			  "\xC1\x2A\x93\x1F\x88\xF1\x5A\xE6"
-			  "\x4F\xB8\x21\xAD\x16\x7F\x0B\x74"
-			  "\xDD\x46\xD2\x3B\xA4\x0D\x99\x02"
-			  "\x6B\xF7\x60\xC9\x32\xBE\x27\x90"
-			  "\x1C\x85\xEE\x57\xE3\x4C\xB5\x1E"
-			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
-			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
-			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB"
-			  "\x54\xE0\x49\xB2\x1B\xA7\x10\x79"
-			  "\x05\x6E\xD7\x40\xCC\x35\x9E\x07"
-			  "\x93\xFC\x65\xF1\x5A\xC3\x2C\xB8"
-			  "\x21\x8A\x16\x7F\xE8\x51\xDD\x46"
-			  "\xAF\x18\xA4\x0D\x76\x02\x6B\xD4"
-			  "\x3D\xC9\x32\x9B\x04\x90\xF9\x62"
-			  "\xEE\x57\xC0\x29\xB5\x1E\x87\x13"
-			  "\x7C\xE5\x4E\xDA\x43\xAC\x15\xA1"
-			  "\x0A\x73\xFF\x68\xD1\x3A\xC6\x2F"
-			  "\x98\x01\x8D\xF6\x5F\xEB\x54\xBD"
-			  "\x26\xB2\x1B\x84\x10\x79\xE2\x4B"
-			  "\xD7\x40\xA9\x12\x9E\x07\x70\xFC"
-			  "\x65\xCE\x37\xC3\x2C\x95\x21\x8A"
-			  "\xF3\x5C\xE8\x51\xBA\x23\xAF\x18"
-			  "\x81\x0D\x76\xDF\x48\xD4\x3D\xA6"
-			  "\x0F\x9B\x04\x6D\xF9\x62\xCB\x34"
-			  "\xC0\x29\x92\x1E\x87\xF0\x59\xE5"
-			  "\x4E\xB7\x20\xAC\x15\x7E\x0A\x73"
-			  "\xDC\x45\xD1\x3A\xA3\x0C\x98\x01"
-			  "\x6A\xF6\x5F\xC8\x31\xBD\x26\x8F"
-			  "\x1B\x84\xED\x56\xE2\x4B\xB4\x1D"
-			  "\xA9\x12\x7B\x07\x70\xD9\x42\xCE"
-			  "\x37\xA0\x09\x95\xFE\x67\xF3\x5C"
-			  "\xC5\x2E\xBA\x23\x8C\x18\x81\xEA"
-			  "\x53\xDF\x48\xB1\x1A\xA6\x0F\x78"
-			  "\x04\x6D\xD6\x3F\xCB\x34\x9D\x06"
-			  "\x92\xFB\x64\xF0\x59\xC2\x2B\xB7"
-			  "\x20\x89\x15\x7E\xE7\x50\xDC\x45"
-			  "\xAE\x17\xA3\x0C\x75\x01\x6A\xD3"
-			  "\x3C\xC8\x31\x9A\x03\x8F\xF8\x61"
-			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	}, { /* Generated with Crypto++ */
-		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55"
-			  "\x0F\x32\x55\x78\x9B\xBE\x78\x9B"
-			  "\xBE\xE1\x04\x27\xE1\x04\x27\x4A"
-			  "\x6D\x90\x4A\x6D\x90\xB3\xD6\xF9",
-		.klen	= 32,
-		.iv	= "\xE7\x82\x1D\xB8\x53\x11\xAC\x47"
-			  "\xE2\x7D\x18\xD6\x71\x0C\xA7\x42",
-		.input	= "\xDA\x4E\x3F\xBC\xE8\xB6\x3A\xA2"
+		.ctext	= "\xDA\x4E\x3F\xBC\xE8\xB6\x3A\xA2"
 			  "\xD5\x4D\x84\x4A\xA9\x0C\xE1\xA5"
 			  "\xB8\x73\xBC\xF9\xBB\x59\x2F\x44"
 			  "\x8B\xAB\x82\x6C\xB4\x32\x9A\xDE"
@@ -22058,105 +14653,39 @@ static const struct cipher_testvec aes_ctr_dec_tv_template[] = {
 			  "\xD0\xE9\x54\x99\x5D\xBA\x3B\x11"
 			  "\xD8\xFE\xC9\x5B\x5C\x25\xE5\x76"
 			  "\xFB\xF2\x3F",
-		.ilen	= 499,
-		.result	= "\x50\xB9\x22\xAE\x17\x80\x0C\x75"
-			  "\xDE\x47\xD3\x3C\xA5\x0E\x9A\x03"
-			  "\x6C\xF8\x61\xCA\x33\xBF\x28\x91"
-			  "\x1D\x86\xEF\x58\xE4\x4D\xB6\x1F"
-			  "\xAB\x14\x7D\x09\x72\xDB\x44\xD0"
-			  "\x39\xA2\x0B\x97\x00\x69\xF5\x5E"
-			  "\xC7\x30\xBC\x25\x8E\x1A\x83\xEC"
-			  "\x55\xE1\x4A\xB3\x1C\xA8\x11\x7A"
-			  "\x06\x6F\xD8\x41\xCD\x36\x9F\x08"
-			  "\x94\xFD\x66\xF2\x5B\xC4\x2D\xB9"
-			  "\x22\x8B\x17\x80\xE9\x52\xDE\x47"
-			  "\xB0\x19\xA5\x0E\x77\x03\x6C\xD5"
-			  "\x3E\xCA\x33\x9C\x05\x91\xFA\x63"
-			  "\xEF\x58\xC1\x2A\xB6\x1F\x88\x14"
-			  "\x7D\xE6\x4F\xDB\x44\xAD\x16\xA2"
-			  "\x0B\x74\x00\x69\xD2\x3B\xC7\x30"
-			  "\x99\x02\x8E\xF7\x60\xEC\x55\xBE"
-			  "\x27\xB3\x1C\x85\x11\x7A\xE3\x4C"
-			  "\xD8\x41\xAA\x13\x9F\x08\x71\xFD"
-			  "\x66\xCF\x38\xC4\x2D\x96\x22\x8B"
-			  "\xF4\x5D\xE9\x52\xBB\x24\xB0\x19"
-			  "\x82\x0E\x77\xE0\x49\xD5\x3E\xA7"
-			  "\x10\x9C\x05\x6E\xFA\x63\xCC\x35"
-			  "\xC1\x2A\x93\x1F\x88\xF1\x5A\xE6"
-			  "\x4F\xB8\x21\xAD\x16\x7F\x0B\x74"
-			  "\xDD\x46\xD2\x3B\xA4\x0D\x99\x02"
-			  "\x6B\xF7\x60\xC9\x32\xBE\x27\x90"
-			  "\x1C\x85\xEE\x57\xE3\x4C\xB5\x1E"
-			  "\xAA\x13\x7C\x08\x71\xDA\x43\xCF"
-			  "\x38\xA1\x0A\x96\xFF\x68\xF4\x5D"
-			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB"
-			  "\x54\xE0\x49\xB2\x1B\xA7\x10\x79"
-			  "\x05\x6E\xD7\x40\xCC\x35\x9E\x07"
-			  "\x93\xFC\x65\xF1\x5A\xC3\x2C\xB8"
-			  "\x21\x8A\x16\x7F\xE8\x51\xDD\x46"
-			  "\xAF\x18\xA4\x0D\x76\x02\x6B\xD4"
-			  "\x3D\xC9\x32\x9B\x04\x90\xF9\x62"
-			  "\xEE\x57\xC0\x29\xB5\x1E\x87\x13"
-			  "\x7C\xE5\x4E\xDA\x43\xAC\x15\xA1"
-			  "\x0A\x73\xFF\x68\xD1\x3A\xC6\x2F"
-			  "\x98\x01\x8D\xF6\x5F\xEB\x54\xBD"
-			  "\x26\xB2\x1B\x84\x10\x79\xE2\x4B"
-			  "\xD7\x40\xA9\x12\x9E\x07\x70\xFC"
-			  "\x65\xCE\x37\xC3\x2C\x95\x21\x8A"
-			  "\xF3\x5C\xE8\x51\xBA\x23\xAF\x18"
-			  "\x81\x0D\x76\xDF\x48\xD4\x3D\xA6"
-			  "\x0F\x9B\x04\x6D\xF9\x62\xCB\x34"
-			  "\xC0\x29\x92\x1E\x87\xF0\x59\xE5"
-			  "\x4E\xB7\x20\xAC\x15\x7E\x0A\x73"
-			  "\xDC\x45\xD1\x3A\xA3\x0C\x98\x01"
-			  "\x6A\xF6\x5F\xC8\x31\xBD\x26\x8F"
-			  "\x1B\x84\xED\x56\xE2\x4B\xB4\x1D"
-			  "\xA9\x12\x7B\x07\x70\xD9\x42\xCE"
-			  "\x37\xA0\x09\x95\xFE\x67\xF3\x5C"
-			  "\xC5\x2E\xBA\x23\x8C\x18\x81\xEA"
-			  "\x53\xDF\x48\xB1\x1A\xA6\x0F\x78"
-			  "\x04\x6D\xD6\x3F\xCB\x34\x9D\x06"
-			  "\x92\xFB\x64\xF0\x59\xC2\x2B\xB7"
-			  "\x20\x89\x15\x7E\xE7\x50\xDC\x45"
-			  "\xAE\x17\xA3\x0C\x75\x01\x6A\xD3"
-			  "\x3C\xC8\x31\x9A\x03\x8F\xF8\x61"
-			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12"
-			  "\x7B\xE4\x4D",
-		.rlen	= 499,
+		.len	= 499,
 		.also_non_np = 1,
 		.np	= 2,
 		.tap	= { 499 - 16, 16 },
 	},
 };
 
-static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
+static const struct cipher_testvec aes_ctr_rfc3686_tv_template[] = {
 	{ /* From RFC 3686 */
 		.key	= "\xae\x68\x52\xf8\x12\x10\x67\xcc"
 			  "\x4b\xf7\xa5\x76\x55\x77\xf3\x9e"
 			  "\x00\x00\x00\x30",
 		.klen	= 20,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "Single block msg",
-		.ilen	= 16,
-		.result = "\xe4\x09\x5d\x4f\xb7\xa7\xb3\x79"
+		.ptext	= "Single block msg",
+		.ctext	= "\xe4\x09\x5d\x4f\xb7\xa7\xb3\x79"
 			  "\x2d\x61\x75\xa3\x26\x13\x11\xb8",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x7e\x24\x06\x78\x17\xfa\xe0\xd7"
 			  "\x43\xd6\xce\x1f\x32\x53\x91\x63"
 			  "\x00\x6c\xb6\xdb",
 		.klen	= 20,
 		.iv	= "\xc0\x54\x3b\x59\xda\x48\xd9\x0b",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.ilen	= 32,
-		.result = "\x51\x04\xa1\x06\x16\x8a\x72\xd9"
+		.ctext	= "\x51\x04\xa1\x06\x16\x8a\x72\xd9"
 			  "\x79\x0d\x41\xee\x8e\xda\xd3\x88"
 			  "\xeb\x2e\x1e\xfc\x46\xda\x57\xc8"
 			  "\xfc\xe6\x30\xdf\x91\x41\xbe\x28",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x16\xaf\x5b\x14\x5f\xc9\xf5\x79"
 			  "\xc1\x75\xf9\x3e\x3b\xfb\x0e\xed"
@@ -22164,11 +14693,10 @@ static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 			  "\x00\x00\x00\x48",
 		.klen	= 28,
 		.iv	= "\x36\x73\x3c\x14\x7d\x6d\x93\xcb",
-		.input	= "Single block msg",
-		.ilen	= 16,
-		.result	= "\x4b\x55\x38\x4f\xe2\x59\xc9\xc8"
+		.ptext	= "Single block msg",
+		.ctext	= "\x4b\x55\x38\x4f\xe2\x59\xc9\xc8"
 			  "\x4e\x79\x35\xa0\x03\xcb\xe9\x28",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x7c\x5c\xb2\x40\x1b\x3d\xc3\x3c"
 			  "\x19\xe7\x34\x08\x19\xe0\xf6\x9c"
@@ -22176,16 +14704,15 @@ static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 			  "\x00\x96\xb0\x3b",
 		.klen	= 28,
 		.iv	= "\x02\x0c\x6e\xad\xc2\xcb\x50\x0d",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.ilen	= 32,
-		.result	= "\x45\x32\x43\xfc\x60\x9b\x23\x32"
+		.ctext	= "\x45\x32\x43\xfc\x60\x9b\x23\x32"
 			  "\x7e\xdf\xaa\xfa\x71\x31\xcd\x9f"
 			  "\x84\x90\x70\x1c\x5a\xd4\xa7\x9c"
 			  "\xfc\x1f\xe0\xff\x42\xf4\xfb\x00",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x77\x6b\xef\xf2\x85\x1d\xb0\x6f"
 			  "\x4c\x8a\x05\x42\xc8\x69\x6f\x6c"
@@ -22194,11 +14721,10 @@ static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 			  "\x00\x00\x00\x60",
 		.klen	= 36,
 		.iv	= "\xdb\x56\x72\xc9\x7a\xa8\xf0\xb2",
-		.input	= "Single block msg",
-		.ilen	= 16,
-		.result = "\x14\x5a\xd0\x1d\xbf\x82\x4e\xc7"
+		.ptext	= "Single block msg",
+		.ctext	= "\x14\x5a\xd0\x1d\xbf\x82\x4e\xc7"
 			  "\x56\x08\x63\xdc\x71\xe3\xe0\xc0",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xf6\xd6\x6d\x6b\xd5\x2d\x59\xbb"
 			  "\x07\x96\x36\x58\x79\xef\xf8\x86"
@@ -22207,16 +14733,15 @@ static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 			  "\x00\xfa\xac\x24",
 		.klen	= 36,
 		.iv	= "\xc1\x58\x5e\xf1\x5a\x43\xd8\x75",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.ilen	= 32,
-		.result = "\xf0\x5e\x23\x1b\x38\x94\x61\x2c"
+		.ctext	= "\xf0\x5e\x23\x1b\x38\x94\x61\x2c"
 			  "\x49\xee\x00\x0b\x80\x4e\xb2\xa9"
 			  "\xb8\x30\x6b\x50\x8f\x83\x9d\x6a"
 			  "\x55\x30\x83\x1d\x93\x44\xaf\x1c",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 	// generated using Crypto++
 		.key = "\x00\x01\x02\x03\x04\x05\x06\x07"
@@ -22226,7 +14751,7 @@ static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 			"\x00\x00\x00\x00",
 		.klen = 32 + 4,
 		.iv = "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input =
+		.ptext =
 			"\x00\x01\x02\x03\x04\x05\x06\x07"
 			"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			"\x10\x11\x12\x13\x14\x15\x16\x17"
@@ -22740,8 +15265,7 @@ static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 			"\x10\x2f\x4e\x6d\x8c\xab\xca\xe9"
 			"\x08\x27\x46\x65\x84\xa3\xc2\xe1"
 			"\x00\x21\x42\x63",
-		.ilen = 4100,
-		.result =
+		.ctext =
 			"\xf0\x5c\x74\xad\x4e\xbc\x99\xe2"
 			"\xae\xff\x91\x3a\x44\xcf\x38\x32"
 			"\x1e\xad\xa7\xcd\xa1\x39\x95\xaa"
@@ -23255,104 +15779,13 @@ static const struct cipher_testvec aes_ctr_rfc3686_enc_tv_template[] = {
 			"\x41\x01\x18\x5d\x5d\x07\x97\xa6"
 			"\x4b\xef\x31\x18\xea\xac\xb1\x84"
 			"\x21\xed\xda\x86",
-		.rlen = 4100,
+		.len	= 4100,
 		.np	= 2,
 		.tap	= { 4064, 36 },
 	},
 };
 
-static const struct cipher_testvec aes_ctr_rfc3686_dec_tv_template[] = {
-	{ /* From RFC 3686 */
-		.key	= "\xae\x68\x52\xf8\x12\x10\x67\xcc"
-			  "\x4b\xf7\xa5\x76\x55\x77\xf3\x9e"
-			  "\x00\x00\x00\x30",
-		.klen	= 20,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xe4\x09\x5d\x4f\xb7\xa7\xb3\x79"
-			  "\x2d\x61\x75\xa3\x26\x13\x11\xb8",
-		.ilen	= 16,
-		.result	= "Single block msg",
-		.rlen	= 16,
-	}, {
-		.key	= "\x7e\x24\x06\x78\x17\xfa\xe0\xd7"
-			  "\x43\xd6\xce\x1f\x32\x53\x91\x63"
-			  "\x00\x6c\xb6\xdb",
-		.klen	= 20,
-		.iv	= "\xc0\x54\x3b\x59\xda\x48\xd9\x0b",
-		.input	= "\x51\x04\xa1\x06\x16\x8a\x72\xd9"
-			  "\x79\x0d\x41\xee\x8e\xda\xd3\x88"
-			  "\xeb\x2e\x1e\xfc\x46\xda\x57\xc8"
-			  "\xfc\xe6\x30\xdf\x91\x41\xbe\x28",
-		.ilen	= 32,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.rlen	= 32,
-	}, {
-		.key	= "\x16\xaf\x5b\x14\x5f\xc9\xf5\x79"
-			  "\xc1\x75\xf9\x3e\x3b\xfb\x0e\xed"
-			  "\x86\x3d\x06\xcc\xfd\xb7\x85\x15"
-			  "\x00\x00\x00\x48",
-		.klen	= 28,
-		.iv	= "\x36\x73\x3c\x14\x7d\x6d\x93\xcb",
-		.input	= "\x4b\x55\x38\x4f\xe2\x59\xc9\xc8"
-			  "\x4e\x79\x35\xa0\x03\xcb\xe9\x28",
-		.ilen	= 16,
-		.result	= "Single block msg",
-		.rlen	= 16,
-	}, {
-		.key	= "\x7c\x5c\xb2\x40\x1b\x3d\xc3\x3c"
-			  "\x19\xe7\x34\x08\x19\xe0\xf6\x9c"
-			  "\x67\x8c\x3d\xb8\xe6\xf6\xa9\x1a"
-			  "\x00\x96\xb0\x3b",
-		.klen	= 28,
-		.iv	= "\x02\x0c\x6e\xad\xc2\xcb\x50\x0d",
-		.input	= "\x45\x32\x43\xfc\x60\x9b\x23\x32"
-			  "\x7e\xdf\xaa\xfa\x71\x31\xcd\x9f"
-			  "\x84\x90\x70\x1c\x5a\xd4\xa7\x9c"
-			  "\xfc\x1f\xe0\xff\x42\xf4\xfb\x00",
-		.ilen	= 32,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.rlen	= 32,
-	}, {
-		.key	= "\x77\x6b\xef\xf2\x85\x1d\xb0\x6f"
-			  "\x4c\x8a\x05\x42\xc8\x69\x6f\x6c"
-			  "\x6a\x81\xaf\x1e\xec\x96\xb4\xd3"
-			  "\x7f\xc1\xd6\x89\xe6\xc1\xc1\x04"
-			  "\x00\x00\x00\x60",
-		.klen	= 36,
-		.iv	= "\xdb\x56\x72\xc9\x7a\xa8\xf0\xb2",
-		.input	= "\x14\x5a\xd0\x1d\xbf\x82\x4e\xc7"
-			  "\x56\x08\x63\xdc\x71\xe3\xe0\xc0",
-		.ilen	= 16,
-		.result	= "Single block msg",
-		.rlen	= 16,
-	}, {
-		.key	= "\xf6\xd6\x6d\x6b\xd5\x2d\x59\xbb"
-			  "\x07\x96\x36\x58\x79\xef\xf8\x86"
-			  "\xc6\x6d\xd5\x1a\x5b\x6a\x99\x74"
-			  "\x4b\x50\x59\x0c\x87\xa2\x38\x84"
-			  "\x00\xfa\xac\x24",
-		.klen	= 36,
-		.iv	= "\xc1\x58\x5e\xf1\x5a\x43\xd8\x75",
-		.input	= "\xf0\x5e\x23\x1b\x38\x94\x61\x2c"
-			  "\x49\xee\x00\x0b\x80\x4e\xb2\xa9"
-			  "\xb8\x30\x6b\x50\x8f\x83\x9d\x6a"
-			  "\x55\x30\x83\x1d\x93\x44\xaf\x1c",
-		.ilen	= 32,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.rlen	= 32,
-	},
-};
-
-static const struct cipher_testvec aes_ofb_enc_tv_template[] = {
+static const struct cipher_testvec aes_ofb_tv_template[] = {
 	 /* From NIST Special Publication 800-38A, Appendix F.5 */
 	{
 		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
@@ -23360,7 +15793,7 @@ static const struct cipher_testvec aes_ofb_enc_tv_template[] = {
 		.klen	= 16,
 		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07\x08"
 			  "\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.input = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
 			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
 			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
 			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
@@ -23368,8 +15801,7 @@ static const struct cipher_testvec aes_ofb_enc_tv_template[] = {
 			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
 			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
 			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.ilen	= 64,
-		.result = "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
+		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
 			  "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a"
 			  "\x77\x89\x50\x8d\x16\x91\x8f\x03\xf5"
 			  "\x3c\x52\xda\xc5\x4e\xd8\x25"
@@ -23377,36 +15809,7 @@ static const struct cipher_testvec aes_ofb_enc_tv_template[] = {
 			  "\x44\xf7\xa8\x22\x60\xed\xcc"
 			  "\x30\x4c\x65\x28\xf6\x59\xc7\x78"
 			  "\x66\xa5\x10\xd9\xc1\xd6\xae\x5e",
-		.rlen	= 64,
-	}
-};
-
-static const struct cipher_testvec aes_ofb_dec_tv_template[] = {
-	 /* From NIST Special Publication 800-38A, Appendix F.5 */
-	{
-		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
-			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
-		.klen	= 16,
-		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07\x08"
-			  "\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.input = "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
-			  "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a"
-			  "\x77\x89\x50\x8d\x16\x91\x8f\x03\xf5"
-			  "\x3c\x52\xda\xc5\x4e\xd8\x25"
-			  "\x97\x40\x05\x1e\x9c\x5f\xec\xf6\x43"
-			  "\x44\xf7\xa8\x22\x60\xed\xcc"
-			  "\x30\x4c\x65\x28\xf6\x59\xc7\x78"
-			  "\x66\xa5\x10\xd9\xc1\xd6\xae\x5e",
-		.ilen	= 64,
-		.result = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
-			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
-			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
-			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
-			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
-			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
-			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
-			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
-		.rlen	= 64,
+		.len	= 64,
 	}
 };
 
@@ -27377,6 +19780,6241 @@ static const struct aead_testvec rfc7539esp_dec_tv_template[] = {
 	},
 };
 
+static const struct aead_testvec aegis128_enc_tv_template[] = {
+	{
+		.key	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81",
+		.klen	= 16,
+		.iv	= "\x1e\x92\x1c\xcf\x88\x3d\x54\x0d"
+			  "\x40\x6d\x59\x48\xfc\x92\x61\x03",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x07\xa5\x11\xf2\x9d\x40\xb8\x6d"
+			  "\xda\xb8\x12\x34\x4c\x53\xd9\x72",
+		.rlen	= 16,
+	}, {
+		.key	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87",
+		.klen	= 16,
+		.iv	= "\x5a\xb7\x56\x6e\x98\xb9\xfd\x29"
+			  "\xc1\x47\x0b\xda\xf6\xb6\x23\x09",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x79",
+		.ilen	= 1,
+		.result	= "\x9e\x78\x52\xae\xcb\x9e\xe4\xd3"
+			  "\x9a\xd7\x5d\xd7\xaa\x9a\xe9\x5a"
+			  "\xcc",
+		.rlen	= 17,
+	}, {
+		.key	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e",
+		.klen	= 16,
+		.iv	= "\x97\xdb\x90\x0e\xa8\x35\xa5\x45"
+			  "\x42\x21\xbd\x6b\xf0\xda\xe6\x0f",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47",
+		.ilen	= 15,
+		.result	= "\xc3\x80\x83\x04\x5f\xaa\x61\xc7"
+			  "\xca\xdd\x6f\xac\x85\x08\xb5\x35"
+			  "\x2b\xc2\x3e\x0b\x1b\x39\x37\x2b"
+			  "\x7a\x21\x16\xb3\xe6\x67\x66",
+		.rlen	= 31,
+	}, {
+		.key	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94",
+		.klen	= 16,
+		.iv	= "\xd3\x00\xc9\xad\xb8\xb0\x4e\x61"
+			  "\xc3\xfb\x6f\xfd\xea\xff\xa9\x15",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.ilen	= 16,
+		.result	= "\x23\x25\x30\xe5\x6a\xb6\x36\x7d"
+			  "\x38\xfd\x3a\xd2\xc2\x58\xa9\x11"
+			  "\x1e\xa8\x30\x9c\x16\xa4\xdb\x65"
+			  "\x51\x10\x16\x27\x70\x9b\x64\x29",
+		.rlen	= 32,
+	}, {
+		.key	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a",
+		.klen	= 16,
+		.iv	= "\x10\x25\x03\x4c\xc8\x2c\xf7\x7d"
+			  "\x44\xd5\x21\x8e\xe4\x23\x6b\x1c",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f"
+			  "\xd3",
+		.ilen	= 17,
+		.result	= "\x2a\x8d\x56\x91\xc6\xf3\x56\xa5"
+			  "\x1f\xf0\x89\x2e\x13\xad\xe6\xf6"
+			  "\x46\x80\xb1\x0e\x18\x30\x40\x97"
+			  "\x03\xdf\x64\x3c\xbe\x93\x9e\xc9"
+			  "\x3b",
+		.rlen	= 33,
+	}, {
+		.key	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0",
+		.klen	= 16,
+		.iv	= "\x4c\x49\x3d\xec\xd8\xa8\xa0\x98"
+			  "\xc5\xb0\xd3\x1f\xde\x48\x2e\x22",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25"
+			  "\xfe\x8d\x45\x19\x1e\xc0\x0b\x99"
+			  "\x88\x11\x39\x12\x1c\x3a\xbb",
+		.ilen	= 31,
+		.result	= "\x4e\xf6\xfa\x13\xde\x43\x63\x4c"
+			  "\xe2\x04\x3e\xe4\x85\x14\xb6\x3f"
+			  "\xb1\x8f\x4c\xdb\x41\xa2\x14\x99"
+			  "\xf5\x53\x0f\x73\x86\x7e\x97\xa1"
+			  "\x4b\x56\x5b\x94\xce\xcd\x74\xcd"
+			  "\x75\xc4\x53\x01\x89\x45\x59",
+		.rlen	= 47,
+	}, {
+		.key	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6",
+		.klen	= 16,
+		.iv	= "\x89\x6e\x77\x8b\xe8\x23\x49\xb4"
+			  "\x45\x8a\x85\xb1\xd8\x6c\xf1\x28",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b"
+			  "\x28\x50\x51\x9d\x24\x60\x8d\xb3"
+			  "\x49\x3e\x17\xea\xf6\x99\x5a\xdd",
+		.ilen	= 32,
+		.result	= "\xa4\x9a\xb7\xfd\xa0\xd4\xd6\x47"
+			  "\x95\xf4\x58\x38\x14\x83\x27\x01"
+			  "\x4c\xed\x32\x2c\xf7\xd6\x31\xf7"
+			  "\x38\x1b\x2c\xc9\xb6\x31\xce\xaa"
+			  "\xa5\x3c\x1a\x18\x5c\xce\xb9\xdf"
+			  "\x51\x52\x77\xf2\x5e\x85\x80\x41",
+		.rlen	= 48,
+	}, {
+		.key	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad",
+		.klen	= 16,
+		.iv	= "\xc5\x93\xb0\x2a\xf8\x9f\xf1\xd0"
+			  "\xc6\x64\x37\x42\xd2\x90\xb3\x2e",
+		.assoc	= "\xd5",
+		.alen	= 1,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xfb\xd4\x83\x71\x9e\x63\xad\x60"
+			  "\xb9\xf9\xeb\x34\x52\x49\xcf\xb7",
+		.rlen	= 16,
+	}, {
+		.key	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3",
+		.klen	= 16,
+		.iv	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76\x34",
+		.assoc	= "\x11\x81\x78\x32\x4d\xb9\x44\x73"
+			  "\x68\x75\x16\xf8\xcb\x7e\xa7",
+		.alen	= 15,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x0c\xaf\x2e\x96\xf6\x97\x08\x71"
+			  "\x7d\x3a\x84\xc4\x44\x57\x77\x7e",
+		.rlen	= 16,
+	}, {
+		.key	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9",
+		.klen	= 16,
+		.iv	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b",
+		.assoc	= "\x4e\xa5\xb2\xd1\x5d\x35\xed\x8f"
+			  "\xe8\x4f\xc8\x89\xc5\xa2\x69\xbc",
+		.alen	= 16,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xc7\x87\x09\x3b\xc7\x19\x74\x22"
+			  "\x22\xa5\x67\x10\xb2\x36\xb3\x45",
+		.rlen	= 16,
+	}, {
+		.key	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf",
+		.klen	= 16,
+		.iv	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41",
+		.assoc	= "\x8a\xca\xec\x70\x6d\xb1\x96\xab"
+			  "\x69\x29\x7a\x1b\xbf\xc7\x2c\xc2"
+			  "\x07",
+		.alen	= 17,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x02\xc6\x3b\x46\x65\xb2\xef\x91"
+			  "\x31\xf0\x45\x48\x8a\x2a\xed\xe4",
+		.rlen	= 16,
+	}, {
+		.key	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6",
+		.klen	= 16,
+		.iv	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47",
+		.assoc	= "\xc7\xef\x26\x10\x7d\x2c\x3f\xc6"
+			  "\xea\x03\x2c\xac\xb9\xeb\xef\xc9"
+			  "\x31\x6b\x08\x12\xfc\xd8\x37\x2d"
+			  "\xe0\x17\x3a\x2e\x83\x5c\x8f",
+		.alen	= 31,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x20\x85\xa8\xd0\x91\x48\x85\xf3"
+			  "\x5a\x16\xc0\x57\x68\x47\xdd\xcb",
+		.rlen	= 16,
+	}, {
+		.key	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc",
+		.klen	= 16,
+		.iv	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d",
+		.assoc	= "\x03\x14\x5f\xaf\x8d\xa8\xe7\xe2"
+			  "\x6b\xde\xde\x3e\xb3\x10\xb1\xcf"
+			  "\x5c\x2d\x14\x96\x01\x78\xb9\x47"
+			  "\xa1\x44\x19\x06\x5d\xbb\x2e\x2f",
+		.alen	= 32,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x6a\xf8\x8d\x9c\x42\x75\x35\x79"
+			  "\xc1\x96\xbd\x31\x6e\x69\x1b\x50",
+		.rlen	= 16,
+	}, {
+		.key	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2",
+		.klen	= 16,
+		.iv	= "\x31\x6f\x0b\xe6\x59\x85\xe6\x77"
+			  "\xcc\x81\x63\xab\xae\x6b\x43\x54",
+		.assoc	= "\x40",
+		.alen	= 1,
+		.input	= "\x4f",
+		.ilen	= 1,
+		.result	= "\x01\x24\xb1\xba\xf6\xd3\xdf\x83"
+			  "\x70\x45\xe3\x2a\x9d\x5c\x63\x98"
+			  "\x39",
+		.rlen	= 17,
+	}, {
+		.key	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8",
+		.klen	= 16,
+		.iv	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06\x5a",
+		.assoc	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37",
+		.alen	= 15,
+		.input	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67",
+		.ilen	= 15,
+		.result	= "\x18\x78\xc2\x6e\xe1\xf7\xe6\x8a"
+			  "\xca\x0e\x62\x00\xa8\x21\xb5\x21"
+			  "\x3d\x36\xdb\xf7\xcc\x31\x94\x9c"
+			  "\x98\xbd\x71\x7a\xef\xa4\xfa",
+		.rlen	= 31,
+	}, {
+		.key	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf",
+		.klen	= 16,
+		.iv	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60",
+		.assoc	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2",
+		.alen	= 16,
+		.input	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.ilen	= 16,
+		.result	= "\xea\xd1\x81\x75\xb4\x13\x1d\x86"
+			  "\xd4\x17\x26\xe5\xd6\x89\x39\x04"
+			  "\xa9\x6c\xca\xac\x40\x73\xb2\x4c"
+			  "\x9c\xb9\x0e\x79\x4c\x40\x65\xc6",
+		.rlen	= 32,
+	}, {
+		.key	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5",
+		.klen	= 16,
+		.iv	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66",
+		.assoc	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05",
+		.alen	= 17,
+		.input	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69"
+			  "\xd0",
+		.ilen	= 17,
+		.result	= "\xf4\xb2\x84\xd1\x81\xfa\x98\x1c"
+			  "\x38\x2d\x69\x90\x1c\x71\x38\x98"
+			  "\x9f\xe1\x19\x3b\x63\x91\xaf\x6e"
+			  "\x4b\x07\x2c\xac\x53\xc5\xd5\xfe"
+			  "\x93",
+		.rlen	= 33,
+	}, {
+		.key	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb",
+		.klen	= 16,
+		.iv	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d",
+		.assoc	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a",
+		.alen	= 31,
+		.input	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70"
+			  "\xfa\xa9\xd0\x4d\x5c\x40\x23\xcd"
+			  "\x98\x34\xab\x37\x56\xae\x32",
+		.ilen	= 31,
+		.result	= "\xa0\xe7\x0a\x60\xe7\xb8\x8a\xdb"
+			  "\x94\xd3\x93\xf2\x41\x86\x16\xdd"
+			  "\x4c\xe8\xe7\xe0\x62\x48\x89\x40"
+			  "\xc0\x49\x9b\x63\x32\xec\x8b\xdb"
+			  "\xdc\xa6\xea\x2c\xc2\x7f\xf5\x04"
+			  "\xcb\xe5\x47\xbb\xa7\xd1\x9d",
+		.rlen	= 47,
+	}, {
+		.key	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1",
+		.klen	= 16,
+		.iv	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73",
+		.assoc	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37",
+		.alen	= 32,
+		.input	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76"
+			  "\x24\x6b\xdc\xd1\x61\xe0\xa5\xe7"
+			  "\x5a\x61\x8a\x0f\x30\x0d\xd1\xec",
+		.ilen	= 32,
+		.result	= "\x62\xdc\x2d\x68\x2d\x71\xbb\x33"
+			  "\x13\xdf\xc0\x46\xf6\x61\x94\xa7"
+			  "\x60\xd3\xd4\xca\xd9\xbe\x82\xf3"
+			  "\xf1\x5b\xa0\xfa\x15\xba\xda\xea"
+			  "\x87\x68\x47\x08\x5d\xdd\x83\xb0"
+			  "\x60\xf4\x93\x20\xdf\x34\x8f\xea",
+		.rlen	= 48,
+	}, {
+		.key	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7",
+		.klen	= 16,
+		.iv	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79",
+		.assoc	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d",
+		.alen	= 33,
+		.input	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c"
+			  "\x4f\x2e\xe8\x55\x66\x80\x27\x00"
+			  "\x1b\x8f\x68\xe7\x0a\x6c\x71\xc3"
+			  "\x21\x78\x55\x9d\x9c\x65\x7b\xcd"
+			  "\x0a\x34\x97\xff\x47\x37\xb0\x2a"
+			  "\x80\x0d\x19\x98\x33\xa9\x7a\xe3"
+			  "\x2e\x4c\xc6\xf3\x8c\x88\x42\x01"
+			  "\xbd",
+		.ilen	= 65,
+		.result	= "\x84\xc5\x21\xab\xe1\xeb\xbb\x6d"
+			  "\xaa\x2a\xaf\xeb\x3b\x3b\x69\xe7"
+			  "\x2c\x47\xef\x9d\xb7\x53\x36\xb7"
+			  "\xb6\xf5\xe5\xa8\xc9\x9e\x02\xd7"
+			  "\x83\x88\xc2\xbd\x2f\xf9\x10\xc0"
+			  "\xf5\xa1\x6e\xd3\x97\x64\x82\xa3"
+			  "\xfb\xda\x2c\xb1\x94\xa1\x58\x32"
+			  "\xe8\xd4\x39\xfc\x9e\x26\xf9\xf1"
+			  "\x61\xe6\xae\x07\xf2\xe0\xa7\x44"
+			  "\x96\x28\x3b\xee\x6b\xc6\x16\x31"
+			  "\x3f",
+		.rlen	= 81,
+	}, {
+		.key	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe",
+		.klen	= 16,
+		.iv	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f",
+		.assoc	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac\xfa\x58\x7f\xe5\x73\x09\x8c"
+			  "\x1d\x40\x87\x8c\xd9\x75\xc0\x55"
+			  "\xa2\xda\x07\xd1\xc2\xa9\xd1\xbb"
+			  "\x09\x4f\x77\x62\x88\x2d\xf2\x68"
+			  "\x54",
+		.alen	= 65,
+		.input	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82"
+			  "\x79\xf0\xf3\xd9\x6c\x20\xa9\x1a"
+			  "\xdc\xbc\x47\xc0\xe4\xcb\x10\x99"
+			  "\x2f",
+		.ilen	= 33,
+		.result	= "\x8f\x23\x47\xfb\xf2\xac\x23\x83"
+			  "\x77\x09\xac\x74\xef\xd2\x56\xae"
+			  "\x20\x7b\x7b\xca\x45\x8e\xc8\xc2"
+			  "\x50\xbd\xc7\x44\x1c\x54\x98\xd8"
+			  "\x1f\xd0\x9a\x79\xaa\xf9\xe1\xb3"
+			  "\xb4\x98\x5a\x9b\xe4\x4d\xbf\x4e"
+			  "\x39",
+		.rlen	= 49,
+	}, {
+		.key	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04",
+		.klen	= 16,
+		.iv	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85",
+		.assoc	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07",
+		.alen	= 16,
+		.input	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.ilen	= 16,
+		.result	= "\x42\xc3\x58\xfb\x29\xe2\x4a\x56"
+			  "\xf1\xf5\xe1\x51\x55\x4b\x0a\x45"
+			  "\x46\xb5\x8d\xac\xb6\x34\xd8\x8b"
+			  "\xde\x20\x59\x77\xc1\x74\x90",
+		.rlen	= 31,
+	}, {
+		.key	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a",
+		.klen	= 16,
+		.iv	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c",
+		.assoc	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d",
+		.alen	= 16,
+		.input	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.ilen	= 16,
+		.result	= "\xb2\xfb\xf6\x97\x69\x7a\xe9\xec"
+			  "\xe2\x94\xa1\x8b\xa0\x2b\x60\x72"
+			  "\x1d\x04\xdd\x6a\xef\x46\x8f\x68"
+			  "\xe9\xe0\x17\x45\x70\x12",
+		.rlen	= 30,
+	}, {
+		.key	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10",
+		.klen	= 16,
+		.iv	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92",
+		.assoc	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13",
+		.alen	= 16,
+		.input	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.ilen	= 16,
+		.result	= "\x47\xda\x54\x42\x51\x72\xc4\x8b"
+			  "\xf5\x57\x0f\x2f\x49\x0e\x11\x3b"
+			  "\x78\x93\xec\xfc\xf4\xff\xe1\x2d",
+		.rlen	= 24,
+	},
+};
+
+/*
+ * AEGIS-128 test vectors - generated via reference implementation from
+ * SUPERCOP (https://bench.cr.yp.to/supercop.html):
+ *
+ *   https://bench.cr.yp.to/supercop/supercop-20170228.tar.xz
+ *   (see crypto_aead/aegis128/)
+ */
+static const struct aead_testvec aegis128_dec_tv_template[] = {
+	{
+		.key	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81",
+		.klen	= 16,
+		.iv	= "\x1e\x92\x1c\xcf\x88\x3d\x54\x0d"
+			  "\x40\x6d\x59\x48\xfc\x92\x61\x03",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x07\xa5\x11\xf2\x9d\x40\xb8\x6d"
+			  "\xda\xb8\x12\x34\x4c\x53\xd9\x72",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87",
+		.klen	= 16,
+		.iv	= "\x5a\xb7\x56\x6e\x98\xb9\xfd\x29"
+			  "\xc1\x47\x0b\xda\xf6\xb6\x23\x09",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x9e\x78\x52\xae\xcb\x9e\xe4\xd3"
+			  "\x9a\xd7\x5d\xd7\xaa\x9a\xe9\x5a"
+			  "\xcc",
+		.ilen	= 17,
+		.result	= "\x79",
+		.rlen	= 1,
+	}, {
+		.key	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e",
+		.klen	= 16,
+		.iv	= "\x97\xdb\x90\x0e\xa8\x35\xa5\x45"
+			  "\x42\x21\xbd\x6b\xf0\xda\xe6\x0f",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xc3\x80\x83\x04\x5f\xaa\x61\xc7"
+			  "\xca\xdd\x6f\xac\x85\x08\xb5\x35"
+			  "\x2b\xc2\x3e\x0b\x1b\x39\x37\x2b"
+			  "\x7a\x21\x16\xb3\xe6\x67\x66",
+		.ilen	= 31,
+		.result	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47",
+		.rlen	= 15,
+	}, {
+		.key	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94",
+		.klen	= 16,
+		.iv	= "\xd3\x00\xc9\xad\xb8\xb0\x4e\x61"
+			  "\xc3\xfb\x6f\xfd\xea\xff\xa9\x15",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x23\x25\x30\xe5\x6a\xb6\x36\x7d"
+			  "\x38\xfd\x3a\xd2\xc2\x58\xa9\x11"
+			  "\x1e\xa8\x30\x9c\x16\xa4\xdb\x65"
+			  "\x51\x10\x16\x27\x70\x9b\x64\x29",
+		.ilen	= 32,
+		.result	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.rlen	= 16,
+	}, {
+		.key	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a",
+		.klen	= 16,
+		.iv	= "\x10\x25\x03\x4c\xc8\x2c\xf7\x7d"
+			  "\x44\xd5\x21\x8e\xe4\x23\x6b\x1c",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x2a\x8d\x56\x91\xc6\xf3\x56\xa5"
+			  "\x1f\xf0\x89\x2e\x13\xad\xe6\xf6"
+			  "\x46\x80\xb1\x0e\x18\x30\x40\x97"
+			  "\x03\xdf\x64\x3c\xbe\x93\x9e\xc9"
+			  "\x3b",
+		.ilen	= 33,
+		.result	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f"
+			  "\xd3",
+		.rlen	= 17,
+	}, {
+		.key	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0",
+		.klen	= 16,
+		.iv	= "\x4c\x49\x3d\xec\xd8\xa8\xa0\x98"
+			  "\xc5\xb0\xd3\x1f\xde\x48\x2e\x22",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x4e\xf6\xfa\x13\xde\x43\x63\x4c"
+			  "\xe2\x04\x3e\xe4\x85\x14\xb6\x3f"
+			  "\xb1\x8f\x4c\xdb\x41\xa2\x14\x99"
+			  "\xf5\x53\x0f\x73\x86\x7e\x97\xa1"
+			  "\x4b\x56\x5b\x94\xce\xcd\x74\xcd"
+			  "\x75\xc4\x53\x01\x89\x45\x59",
+		.ilen	= 47,
+		.result	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25"
+			  "\xfe\x8d\x45\x19\x1e\xc0\x0b\x99"
+			  "\x88\x11\x39\x12\x1c\x3a\xbb",
+		.rlen	= 31,
+	}, {
+		.key	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6",
+		.klen	= 16,
+		.iv	= "\x89\x6e\x77\x8b\xe8\x23\x49\xb4"
+			  "\x45\x8a\x85\xb1\xd8\x6c\xf1\x28",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xa4\x9a\xb7\xfd\xa0\xd4\xd6\x47"
+			  "\x95\xf4\x58\x38\x14\x83\x27\x01"
+			  "\x4c\xed\x32\x2c\xf7\xd6\x31\xf7"
+			  "\x38\x1b\x2c\xc9\xb6\x31\xce\xaa"
+			  "\xa5\x3c\x1a\x18\x5c\xce\xb9\xdf"
+			  "\x51\x52\x77\xf2\x5e\x85\x80\x41",
+		.ilen	= 48,
+		.result	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b"
+			  "\x28\x50\x51\x9d\x24\x60\x8d\xb3"
+			  "\x49\x3e\x17\xea\xf6\x99\x5a\xdd",
+		.rlen	= 32,
+	}, {
+		.key	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad",
+		.klen	= 16,
+		.iv	= "\xc5\x93\xb0\x2a\xf8\x9f\xf1\xd0"
+			  "\xc6\x64\x37\x42\xd2\x90\xb3\x2e",
+		.assoc	= "\xd5",
+		.alen	= 1,
+		.input	= "\xfb\xd4\x83\x71\x9e\x63\xad\x60"
+			  "\xb9\xf9\xeb\x34\x52\x49\xcf\xb7",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3",
+		.klen	= 16,
+		.iv	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76\x34",
+		.assoc	= "\x11\x81\x78\x32\x4d\xb9\x44\x73"
+			  "\x68\x75\x16\xf8\xcb\x7e\xa7",
+		.alen	= 15,
+		.input	= "\x0c\xaf\x2e\x96\xf6\x97\x08\x71"
+			  "\x7d\x3a\x84\xc4\x44\x57\x77\x7e",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9",
+		.klen	= 16,
+		.iv	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b",
+		.assoc	= "\x4e\xa5\xb2\xd1\x5d\x35\xed\x8f"
+			  "\xe8\x4f\xc8\x89\xc5\xa2\x69\xbc",
+		.alen	= 16,
+		.input	= "\xc7\x87\x09\x3b\xc7\x19\x74\x22"
+			  "\x22\xa5\x67\x10\xb2\x36\xb3\x45",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf",
+		.klen	= 16,
+		.iv	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41",
+		.assoc	= "\x8a\xca\xec\x70\x6d\xb1\x96\xab"
+			  "\x69\x29\x7a\x1b\xbf\xc7\x2c\xc2"
+			  "\x07",
+		.alen	= 17,
+		.input	= "\x02\xc6\x3b\x46\x65\xb2\xef\x91"
+			  "\x31\xf0\x45\x48\x8a\x2a\xed\xe4",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6",
+		.klen	= 16,
+		.iv	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47",
+		.assoc	= "\xc7\xef\x26\x10\x7d\x2c\x3f\xc6"
+			  "\xea\x03\x2c\xac\xb9\xeb\xef\xc9"
+			  "\x31\x6b\x08\x12\xfc\xd8\x37\x2d"
+			  "\xe0\x17\x3a\x2e\x83\x5c\x8f",
+		.alen	= 31,
+		.input	= "\x20\x85\xa8\xd0\x91\x48\x85\xf3"
+			  "\x5a\x16\xc0\x57\x68\x47\xdd\xcb",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc",
+		.klen	= 16,
+		.iv	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d",
+		.assoc	= "\x03\x14\x5f\xaf\x8d\xa8\xe7\xe2"
+			  "\x6b\xde\xde\x3e\xb3\x10\xb1\xcf"
+			  "\x5c\x2d\x14\x96\x01\x78\xb9\x47"
+			  "\xa1\x44\x19\x06\x5d\xbb\x2e\x2f",
+		.alen	= 32,
+		.input	= "\x6a\xf8\x8d\x9c\x42\x75\x35\x79"
+			  "\xc1\x96\xbd\x31\x6e\x69\x1b\x50",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2",
+		.klen	= 16,
+		.iv	= "\x31\x6f\x0b\xe6\x59\x85\xe6\x77"
+			  "\xcc\x81\x63\xab\xae\x6b\x43\x54",
+		.assoc	= "\x40",
+		.alen	= 1,
+		.input	= "\x01\x24\xb1\xba\xf6\xd3\xdf\x83"
+			  "\x70\x45\xe3\x2a\x9d\x5c\x63\x98"
+			  "\x39",
+		.ilen	= 17,
+		.result	= "\x4f",
+		.rlen	= 1,
+	}, {
+		.key	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8",
+		.klen	= 16,
+		.iv	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06\x5a",
+		.assoc	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37",
+		.alen	= 15,
+		.input	= "\x18\x78\xc2\x6e\xe1\xf7\xe6\x8a"
+			  "\xca\x0e\x62\x00\xa8\x21\xb5\x21"
+			  "\x3d\x36\xdb\xf7\xcc\x31\x94\x9c"
+			  "\x98\xbd\x71\x7a\xef\xa4\xfa",
+		.ilen	= 31,
+		.result	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67",
+		.rlen	= 15,
+	}, {
+		.key	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf",
+		.klen	= 16,
+		.iv	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60",
+		.assoc	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2",
+		.alen	= 16,
+		.input	= "\xea\xd1\x81\x75\xb4\x13\x1d\x86"
+			  "\xd4\x17\x26\xe5\xd6\x89\x39\x04"
+			  "\xa9\x6c\xca\xac\x40\x73\xb2\x4c"
+			  "\x9c\xb9\x0e\x79\x4c\x40\x65\xc6",
+		.ilen	= 32,
+		.result	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.rlen	= 16,
+	}, {
+		.key	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5",
+		.klen	= 16,
+		.iv	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66",
+		.assoc	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05",
+		.alen	= 17,
+		.input	= "\xf4\xb2\x84\xd1\x81\xfa\x98\x1c"
+			  "\x38\x2d\x69\x90\x1c\x71\x38\x98"
+			  "\x9f\xe1\x19\x3b\x63\x91\xaf\x6e"
+			  "\x4b\x07\x2c\xac\x53\xc5\xd5\xfe"
+			  "\x93",
+		.ilen	= 33,
+		.result	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69"
+			  "\xd0",
+		.rlen	= 17,
+	}, {
+		.key	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb",
+		.klen	= 16,
+		.iv	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d",
+		.assoc	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a",
+		.alen	= 31,
+		.input	= "\xa0\xe7\x0a\x60\xe7\xb8\x8a\xdb"
+			  "\x94\xd3\x93\xf2\x41\x86\x16\xdd"
+			  "\x4c\xe8\xe7\xe0\x62\x48\x89\x40"
+			  "\xc0\x49\x9b\x63\x32\xec\x8b\xdb"
+			  "\xdc\xa6\xea\x2c\xc2\x7f\xf5\x04"
+			  "\xcb\xe5\x47\xbb\xa7\xd1\x9d",
+		.ilen	= 47,
+		.result	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70"
+			  "\xfa\xa9\xd0\x4d\x5c\x40\x23\xcd"
+			  "\x98\x34\xab\x37\x56\xae\x32",
+		.rlen	= 31,
+	}, {
+		.key	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1",
+		.klen	= 16,
+		.iv	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73",
+		.assoc	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37",
+		.alen	= 32,
+		.input	= "\x62\xdc\x2d\x68\x2d\x71\xbb\x33"
+			  "\x13\xdf\xc0\x46\xf6\x61\x94\xa7"
+			  "\x60\xd3\xd4\xca\xd9\xbe\x82\xf3"
+			  "\xf1\x5b\xa0\xfa\x15\xba\xda\xea"
+			  "\x87\x68\x47\x08\x5d\xdd\x83\xb0"
+			  "\x60\xf4\x93\x20\xdf\x34\x8f\xea",
+		.ilen	= 48,
+		.result	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76"
+			  "\x24\x6b\xdc\xd1\x61\xe0\xa5\xe7"
+			  "\x5a\x61\x8a\x0f\x30\x0d\xd1\xec",
+		.rlen	= 32,
+	}, {
+		.key	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7",
+		.klen	= 16,
+		.iv	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79",
+		.assoc	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d",
+		.alen	= 33,
+		.input	= "\x84\xc5\x21\xab\xe1\xeb\xbb\x6d"
+			  "\xaa\x2a\xaf\xeb\x3b\x3b\x69\xe7"
+			  "\x2c\x47\xef\x9d\xb7\x53\x36\xb7"
+			  "\xb6\xf5\xe5\xa8\xc9\x9e\x02\xd7"
+			  "\x83\x88\xc2\xbd\x2f\xf9\x10\xc0"
+			  "\xf5\xa1\x6e\xd3\x97\x64\x82\xa3"
+			  "\xfb\xda\x2c\xb1\x94\xa1\x58\x32"
+			  "\xe8\xd4\x39\xfc\x9e\x26\xf9\xf1"
+			  "\x61\xe6\xae\x07\xf2\xe0\xa7\x44"
+			  "\x96\x28\x3b\xee\x6b\xc6\x16\x31"
+			  "\x3f",
+		.ilen	= 81,
+		.result	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c"
+			  "\x4f\x2e\xe8\x55\x66\x80\x27\x00"
+			  "\x1b\x8f\x68\xe7\x0a\x6c\x71\xc3"
+			  "\x21\x78\x55\x9d\x9c\x65\x7b\xcd"
+			  "\x0a\x34\x97\xff\x47\x37\xb0\x2a"
+			  "\x80\x0d\x19\x98\x33\xa9\x7a\xe3"
+			  "\x2e\x4c\xc6\xf3\x8c\x88\x42\x01"
+			  "\xbd",
+		.rlen	= 65,
+	}, {
+		.key	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe",
+		.klen	= 16,
+		.iv	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f",
+		.assoc	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac\xfa\x58\x7f\xe5\x73\x09\x8c"
+			  "\x1d\x40\x87\x8c\xd9\x75\xc0\x55"
+			  "\xa2\xda\x07\xd1\xc2\xa9\xd1\xbb"
+			  "\x09\x4f\x77\x62\x88\x2d\xf2\x68"
+			  "\x54",
+		.alen	= 65,
+		.input	= "\x8f\x23\x47\xfb\xf2\xac\x23\x83"
+			  "\x77\x09\xac\x74\xef\xd2\x56\xae"
+			  "\x20\x7b\x7b\xca\x45\x8e\xc8\xc2"
+			  "\x50\xbd\xc7\x44\x1c\x54\x98\xd8"
+			  "\x1f\xd0\x9a\x79\xaa\xf9\xe1\xb3"
+			  "\xb4\x98\x5a\x9b\xe4\x4d\xbf\x4e"
+			  "\x39",
+		.ilen	= 49,
+		.result	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82"
+			  "\x79\xf0\xf3\xd9\x6c\x20\xa9\x1a"
+			  "\xdc\xbc\x47\xc0\xe4\xcb\x10\x99"
+			  "\x2f",
+		.rlen	= 33,
+	}, {
+		.key	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04",
+		.klen	= 16,
+		.iv	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85",
+		.assoc	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07",
+		.alen	= 16,
+		.input	= "\x42\xc3\x58\xfb\x29\xe2\x4a\x56"
+			  "\xf1\xf5\xe1\x51\x55\x4b\x0a\x45"
+			  "\x46\xb5\x8d\xac\xb6\x34\xd8\x8b"
+			  "\xde\x20\x59\x77\xc1\x74\x90",
+		.ilen	= 31,
+		.result	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.rlen	= 16,
+	}, {
+		.key	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a",
+		.klen	= 16,
+		.iv	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c",
+		.assoc	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d",
+		.alen	= 16,
+		.input	= "\xb2\xfb\xf6\x97\x69\x7a\xe9\xec"
+			  "\xe2\x94\xa1\x8b\xa0\x2b\x60\x72"
+			  "\x1d\x04\xdd\x6a\xef\x46\x8f\x68"
+			  "\xe9\xe0\x17\x45\x70\x12",
+		.ilen	= 30,
+		.result	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.rlen	= 16,
+	}, {
+		.key	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10",
+		.klen	= 16,
+		.iv	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92",
+		.assoc	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13",
+		.alen	= 16,
+		.input	= "\x47\xda\x54\x42\x51\x72\xc4\x8b"
+			  "\xf5\x57\x0f\x2f\x49\x0e\x11\x3b"
+			  "\x78\x93\xec\xfc\xf4\xff\xe1\x2d",
+		.ilen	= 24,
+		.result	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.rlen	= 16,
+	},
+};
+
+/*
+ * AEGIS-128L test vectors - generated via reference implementation from
+ * SUPERCOP (https://bench.cr.yp.to/supercop.html):
+ *
+ *   https://bench.cr.yp.to/supercop/supercop-20170228.tar.xz
+ *   (see crypto_aead/aegis128l/)
+ */
+static const struct aead_testvec aegis128l_enc_tv_template[] = {
+	{
+		.key	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81",
+		.klen	= 16,
+		.iv	= "\x1e\x92\x1c\xcf\x88\x3d\x54\x0d"
+			  "\x40\x6d\x59\x48\xfc\x92\x61\x03",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x30\x4f\xf3\xe9\xb1\xfa\x81\xa6"
+			  "\x20\x72\x78\xdd\x93\xc8\x57\xef",
+		.rlen	= 16,
+	}, {
+		.key	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87",
+		.klen	= 16,
+		.iv	= "\x5a\xb7\x56\x6e\x98\xb9\xfd\x29"
+			  "\xc1\x47\x0b\xda\xf6\xb6\x23\x09",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x79",
+		.ilen	= 1,
+		.result	= "\xa9\x24\xa0\xb6\x2d\xdd\x29\xdb"
+			  "\x40\xb3\x71\xc5\x22\x58\x31\x77"
+			  "\x6d",
+		.rlen	= 17,
+	}, {
+		.key	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e",
+		.klen	= 16,
+		.iv	= "\x97\xdb\x90\x0e\xa8\x35\xa5\x45"
+			  "\x42\x21\xbd\x6b\xf0\xda\xe6\x0f",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47",
+		.ilen	= 15,
+		.result	= "\xbb\x0a\x53\xc4\xaa\x7e\xa4\x03"
+			  "\x2b\xee\x62\x99\x7b\x98\x13\x1f"
+			  "\xe0\x76\x4c\x2e\x53\x99\x4f\xbe"
+			  "\xe1\xa8\x04\x7f\xe1\x71\xbe",
+		.rlen	= 31,
+	}, {
+		.key	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94",
+		.klen	= 16,
+		.iv	= "\xd3\x00\xc9\xad\xb8\xb0\x4e\x61"
+			  "\xc3\xfb\x6f\xfd\xea\xff\xa9\x15",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.ilen	= 16,
+		.result	= "\x66\xdf\x6e\x71\xc0\x6e\xa4\x4c"
+			  "\x9d\xb7\x8c\x9a\xdb\x1f\xd2\x2e"
+			  "\x23\xb6\xa4\xfb\xd3\x86\xdd\xbb"
+			  "\xde\x54\x9b\xf5\x92\x8b\x93\xc5",
+		.rlen	= 32,
+	}, {
+		.key	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a",
+		.klen	= 16,
+		.iv	= "\x10\x25\x03\x4c\xc8\x2c\xf7\x7d"
+			  "\x44\xd5\x21\x8e\xe4\x23\x6b\x1c",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f"
+			  "\xd3",
+		.ilen	= 17,
+		.result	= "\x4f\xc3\x69\xb6\xd3\xa4\x64\x8b"
+			  "\x71\xc3\x8a\x91\x22\x4f\x1b\xd2"
+			  "\x33\x6d\x86\xbc\xf8\x2f\x06\xf9"
+			  "\x82\x64\xc7\x72\x00\x30\xfc\xf0"
+			  "\xf8",
+		.rlen	= 33,
+	}, {
+		.key	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0",
+		.klen	= 16,
+		.iv	= "\x4c\x49\x3d\xec\xd8\xa8\xa0\x98"
+			  "\xc5\xb0\xd3\x1f\xde\x48\x2e\x22",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25"
+			  "\xfe\x8d\x45\x19\x1e\xc0\x0b\x99"
+			  "\x88\x11\x39\x12\x1c\x3a\xbb",
+		.ilen	= 31,
+		.result	= "\xe3\x93\x15\xae\x5f\x9d\x3c\xb5"
+			  "\xd6\x9d\xee\xee\xcf\xaa\xaf\xe1"
+			  "\x45\x10\x96\xe0\xbf\x55\x0f\x4c"
+			  "\x1a\xfd\xf4\xda\x4e\x10\xde\xc9"
+			  "\x0e\x6f\xc7\x3c\x49\x94\x41\xfc"
+			  "\x59\x28\x88\x3c\x79\x10\x6b",
+		.rlen	= 47,
+	}, {
+		.key	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6",
+		.klen	= 16,
+		.iv	= "\x89\x6e\x77\x8b\xe8\x23\x49\xb4"
+			  "\x45\x8a\x85\xb1\xd8\x6c\xf1\x28",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b"
+			  "\x28\x50\x51\x9d\x24\x60\x8d\xb3"
+			  "\x49\x3e\x17\xea\xf6\x99\x5a\xdd",
+		.ilen	= 32,
+		.result	= "\x1c\x8e\x22\x34\xfd\xab\xe6\x0d"
+			  "\x1c\x9f\x06\x54\x8b\x0b\xb4\x40"
+			  "\xde\x11\x59\x3e\xfd\x74\xf6\x42"
+			  "\x97\x17\xf7\x24\xb6\x7e\xc4\xc6"
+			  "\x06\xa3\x94\xda\x3d\x7f\x55\x0a"
+			  "\x92\x07\x2f\xa6\xf3\x6b\x2c\xfc",
+		.rlen	= 48,
+	}, {
+		.key	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad",
+		.klen	= 16,
+		.iv	= "\xc5\x93\xb0\x2a\xf8\x9f\xf1\xd0"
+			  "\xc6\x64\x37\x42\xd2\x90\xb3\x2e",
+		.assoc	= "\xd5",
+		.alen	= 1,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xa0\x2a\xb4\x9a\x91\x00\x15\xb8"
+			  "\x0f\x9a\x15\x60\x0e\x9b\x13\x8f",
+		.rlen	= 16,
+	}, {
+		.key	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3",
+		.klen	= 16,
+		.iv	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76\x34",
+		.assoc	= "\x11\x81\x78\x32\x4d\xb9\x44\x73"
+			  "\x68\x75\x16\xf8\xcb\x7e\xa7",
+		.alen	= 15,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x4c\x26\xad\x9c\x14\xfd\x9c\x8c"
+			  "\x84\xfb\x26\xfb\xd5\xca\x62\x39",
+		.rlen	= 16,
+	}, {
+		.key	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9",
+		.klen	= 16,
+		.iv	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b",
+		.assoc	= "\x4e\xa5\xb2\xd1\x5d\x35\xed\x8f"
+			  "\xe8\x4f\xc8\x89\xc5\xa2\x69\xbc",
+		.alen	= 16,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x45\x85\x0e\x0f\xf4\xae\x96\xa1"
+			  "\x99\x4d\x6d\xb4\x67\x32\xb0\x3a",
+		.rlen	= 16,
+	}, {
+		.key	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf",
+		.klen	= 16,
+		.iv	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41",
+		.assoc	= "\x8a\xca\xec\x70\x6d\xb1\x96\xab"
+			  "\x69\x29\x7a\x1b\xbf\xc7\x2c\xc2"
+			  "\x07",
+		.alen	= 17,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x33\xb1\x42\x97\x8e\x16\x7b\x63"
+			  "\x06\xba\x5b\xcb\xae\x6d\x8b\x56",
+		.rlen	= 16,
+	}, {
+		.key	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6",
+		.klen	= 16,
+		.iv	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47",
+		.assoc	= "\xc7\xef\x26\x10\x7d\x2c\x3f\xc6"
+			  "\xea\x03\x2c\xac\xb9\xeb\xef\xc9"
+			  "\x31\x6b\x08\x12\xfc\xd8\x37\x2d"
+			  "\xe0\x17\x3a\x2e\x83\x5c\x8f",
+		.alen	= 31,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xda\x44\x08\x8c\x2a\xa5\x07\x35"
+			  "\x0b\x54\x4e\x6d\xe3\xfd\xc4\x5f",
+		.rlen	= 16,
+	}, {
+		.key	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc",
+		.klen	= 16,
+		.iv	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d",
+		.assoc	= "\x03\x14\x5f\xaf\x8d\xa8\xe7\xe2"
+			  "\x6b\xde\xde\x3e\xb3\x10\xb1\xcf"
+			  "\x5c\x2d\x14\x96\x01\x78\xb9\x47"
+			  "\xa1\x44\x19\x06\x5d\xbb\x2e\x2f",
+		.alen	= 32,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x1b\xb1\xf1\xa8\x9e\xc2\xb2\x88"
+			  "\x40\x7f\x7b\x19\x7a\x52\x8c\xf0",
+		.rlen	= 16,
+	}, {
+		.key	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2",
+		.klen	= 16,
+		.iv	= "\x31\x6f\x0b\xe6\x59\x85\xe6\x77"
+			  "\xcc\x81\x63\xab\xae\x6b\x43\x54",
+		.assoc	= "\x40",
+		.alen	= 1,
+		.input	= "\x4f",
+		.ilen	= 1,
+		.result	= "\x6e\xc8\xfb\x15\x9d\x98\x49\xc9"
+			  "\xa0\x98\x09\x85\xbe\x56\x8e\x79"
+			  "\xf4",
+		.rlen	= 17,
+	}, {
+		.key	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8",
+		.klen	= 16,
+		.iv	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06\x5a",
+		.assoc	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37",
+		.alen	= 15,
+		.input	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67",
+		.ilen	= 15,
+		.result	= "\x99\x2e\x84\x50\x64\x5c\xab\x29"
+			  "\x20\xba\xb9\x2f\x62\x3a\xce\x2a"
+			  "\x75\x25\x3b\xe3\x40\xe0\x1d\xfc"
+			  "\x20\x63\x0b\x49\x7e\x97\x08",
+		.rlen	= 31,
+	}, {
+		.key	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf",
+		.klen	= 16,
+		.iv	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60",
+		.assoc	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2",
+		.alen	= 16,
+		.input	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.ilen	= 16,
+		.result	= "\xd9\x8e\xfd\x50\x8f\x02\x9f\xee"
+			  "\x78\x08\x12\xec\x09\xaf\x53\x14"
+			  "\x90\x3e\x3d\x76\xad\x71\x21\x08"
+			  "\x77\xe5\x4b\x15\xc2\xe6\xbc\xdb",
+		.rlen	= 32,
+	}, {
+		.key	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5",
+		.klen	= 16,
+		.iv	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66",
+		.assoc	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05",
+		.alen	= 17,
+		.input	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69"
+			  "\xd0",
+		.ilen	= 17,
+		.result	= "\xf3\xe7\x95\x86\xcf\x34\x95\x96"
+			  "\x17\xfe\x1b\xae\x1b\x31\xf2\x1a"
+			  "\xbd\xbc\xc9\x4e\x11\x29\x09\x5c"
+			  "\x05\xd3\xb4\x2e\x4a\x74\x59\x49"
+			  "\x7d",
+		.rlen	= 33,
+	}, {
+		.key	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb",
+		.klen	= 16,
+		.iv	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d",
+		.assoc	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a",
+		.alen	= 31,
+		.input	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70"
+			  "\xfa\xa9\xd0\x4d\x5c\x40\x23\xcd"
+			  "\x98\x34\xab\x37\x56\xae\x32",
+		.ilen	= 31,
+		.result	= "\x06\x96\xb2\xbf\x63\xf4\x1e\x24"
+			  "\x0d\x19\x15\x61\x65\x3b\x06\x26"
+			  "\x71\xe8\x7e\x16\xdb\x96\x01\x01"
+			  "\x52\xcd\x49\x5b\x07\x33\x4e\xe7"
+			  "\xaa\x91\xf5\xd5\xc6\xfe\x41\xb5"
+			  "\xed\x90\xce\xb9\xcd\xcc\xa1",
+		.rlen	= 47,
+	}, {
+		.key	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1",
+		.klen	= 16,
+		.iv	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73",
+		.assoc	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37",
+		.alen	= 32,
+		.input	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76"
+			  "\x24\x6b\xdc\xd1\x61\xe0\xa5\xe7"
+			  "\x5a\x61\x8a\x0f\x30\x0d\xd1\xec",
+		.ilen	= 32,
+		.result	= "\xf9\xd7\xee\x17\xfd\x24\xcd\xf1"
+			  "\xbc\x0f\x35\x97\x97\x0c\x4b\x18"
+			  "\xce\x58\xc8\x3b\xd4\x85\x93\x79"
+			  "\xcc\x9c\xea\xc1\x73\x13\x0b\x4c"
+			  "\xcc\x6f\x28\xf8\xa4\x4e\xb8\x56"
+			  "\x64\x4e\x47\xce\xb2\xb4\x92\xb4",
+		.rlen	= 48,
+	}, {
+		.key	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7",
+		.klen	= 16,
+		.iv	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79",
+		.assoc	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d",
+		.alen	= 33,
+		.input	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c"
+			  "\x4f\x2e\xe8\x55\x66\x80\x27\x00"
+			  "\x1b\x8f\x68\xe7\x0a\x6c\x71\xc3"
+			  "\x21\x78\x55\x9d\x9c\x65\x7b\xcd"
+			  "\x0a\x34\x97\xff\x47\x37\xb0\x2a"
+			  "\x80\x0d\x19\x98\x33\xa9\x7a\xe3"
+			  "\x2e\x4c\xc6\xf3\x8c\x88\x42\x01"
+			  "\xbd",
+		.ilen	= 65,
+		.result	= "\x58\xfa\x3a\x3d\xd9\x88\x63\xe8"
+			  "\xc5\x78\x50\x8b\x4a\xc9\xdf\x7f"
+			  "\x4b\xfa\xc8\x2e\x67\x43\xf3\x63"
+			  "\x42\x8e\x99\x5a\x9c\x0b\x84\x77"
+			  "\xbc\x46\x76\x48\x82\xc7\x57\x96"
+			  "\xe1\x65\xd1\xed\x1d\xdd\x80\x24"
+			  "\xa6\x4d\xa9\xf1\x53\x8b\x5e\x0e"
+			  "\x26\xb9\xcc\x37\xe5\x43\xe1\x5a"
+			  "\x8a\xd6\x8c\x5a\xe4\x95\xd1\x8d"
+			  "\xf7\x33\x64\xc1\xd3\xf2\xfc\x35"
+			  "\x01",
+		.rlen	= 81,
+	}, {
+		.key	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe",
+		.klen	= 16,
+		.iv	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f",
+		.assoc	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac\xfa\x58\x7f\xe5\x73\x09\x8c"
+			  "\x1d\x40\x87\x8c\xd9\x75\xc0\x55"
+			  "\xa2\xda\x07\xd1\xc2\xa9\xd1\xbb"
+			  "\x09\x4f\x77\x62\x88\x2d\xf2\x68"
+			  "\x54",
+		.alen	= 65,
+		.input	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82"
+			  "\x79\xf0\xf3\xd9\x6c\x20\xa9\x1a"
+			  "\xdc\xbc\x47\xc0\xe4\xcb\x10\x99"
+			  "\x2f",
+		.ilen	= 33,
+		.result	= "\x4c\xa9\xac\x71\xed\x10\xa6\x24"
+			  "\xb7\xa7\xdf\x8b\xf5\xc2\x41\xcb"
+			  "\x05\xc9\xd6\x97\xb6\x10\x7f\x17"
+			  "\xc2\xc0\x93\xcf\xe0\x94\xfd\x99"
+			  "\xf2\x62\x25\x28\x01\x23\x6f\x8b"
+			  "\x04\x52\xbc\xb0\x3e\x66\x52\x90"
+			  "\x9f",
+		.rlen	= 49,
+	}, {
+		.key	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04",
+		.klen	= 16,
+		.iv	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85",
+		.assoc	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07",
+		.alen	= 16,
+		.input	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.ilen	= 16,
+		.result	= "\x6d\xed\x04\x7a\x2f\x0c\x30\xa5"
+			  "\x96\xe6\x97\xe4\x10\xeb\x40\x95"
+			  "\xc5\x9a\xdf\x31\xd5\xa5\xa6\xec"
+			  "\x05\xa8\x31\x50\x11\x19\x44",
+		.rlen	= 31,
+	}, {
+		.key	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a",
+		.klen	= 16,
+		.iv	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c",
+		.assoc	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d",
+		.alen	= 16,
+		.input	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.ilen	= 16,
+		.result	= "\x30\x95\x7d\xea\xdc\x62\xc0\x88"
+			  "\xa1\xe3\x8d\x8c\xac\x04\x10\xa7"
+			  "\xfa\xfa\x07\xbd\xa0\xf0\x36\xeb"
+			  "\x21\x93\x2e\x31\x84\x83",
+		.rlen	= 30,
+	}, {
+		.key	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10",
+		.klen	= 16,
+		.iv	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92",
+		.assoc	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13",
+		.alen	= 16,
+		.input	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.ilen	= 16,
+		.result	= "\x93\xcd\xee\xd4\xcb\x9d\x8d\x16"
+			  "\x63\x0d\x43\xd5\x49\xca\xa8\x85"
+			  "\x49\xc0\xae\x13\xbc\x26\x1d\x4b",
+		.rlen	= 24,
+	},
+};
+
+static const struct aead_testvec aegis128l_dec_tv_template[] = {
+	{
+		.key	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81",
+		.klen	= 16,
+		.iv	= "\x1e\x92\x1c\xcf\x88\x3d\x54\x0d"
+			  "\x40\x6d\x59\x48\xfc\x92\x61\x03",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x30\x4f\xf3\xe9\xb1\xfa\x81\xa6"
+			  "\x20\x72\x78\xdd\x93\xc8\x57\xef",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87",
+		.klen	= 16,
+		.iv	= "\x5a\xb7\x56\x6e\x98\xb9\xfd\x29"
+			  "\xc1\x47\x0b\xda\xf6\xb6\x23\x09",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xa9\x24\xa0\xb6\x2d\xdd\x29\xdb"
+			  "\x40\xb3\x71\xc5\x22\x58\x31\x77"
+			  "\x6d",
+		.ilen	= 17,
+		.result	= "\x79",
+		.rlen	= 1,
+	}, {
+		.key	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e",
+		.klen	= 16,
+		.iv	= "\x97\xdb\x90\x0e\xa8\x35\xa5\x45"
+			  "\x42\x21\xbd\x6b\xf0\xda\xe6\x0f",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xbb\x0a\x53\xc4\xaa\x7e\xa4\x03"
+			  "\x2b\xee\x62\x99\x7b\x98\x13\x1f"
+			  "\xe0\x76\x4c\x2e\x53\x99\x4f\xbe"
+			  "\xe1\xa8\x04\x7f\xe1\x71\xbe",
+		.ilen	= 31,
+		.result	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47",
+		.rlen	= 15,
+	}, {
+		.key	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94",
+		.klen	= 16,
+		.iv	= "\xd3\x00\xc9\xad\xb8\xb0\x4e\x61"
+			  "\xc3\xfb\x6f\xfd\xea\xff\xa9\x15",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x66\xdf\x6e\x71\xc0\x6e\xa4\x4c"
+			  "\x9d\xb7\x8c\x9a\xdb\x1f\xd2\x2e"
+			  "\x23\xb6\xa4\xfb\xd3\x86\xdd\xbb"
+			  "\xde\x54\x9b\xf5\x92\x8b\x93\xc5",
+		.ilen	= 32,
+		.result	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.rlen	= 16,
+	}, {
+		.key	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a",
+		.klen	= 16,
+		.iv	= "\x10\x25\x03\x4c\xc8\x2c\xf7\x7d"
+			  "\x44\xd5\x21\x8e\xe4\x23\x6b\x1c",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x4f\xc3\x69\xb6\xd3\xa4\x64\x8b"
+			  "\x71\xc3\x8a\x91\x22\x4f\x1b\xd2"
+			  "\x33\x6d\x86\xbc\xf8\x2f\x06\xf9"
+			  "\x82\x64\xc7\x72\x00\x30\xfc\xf0"
+			  "\xf8",
+		.ilen	= 33,
+		.result	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f"
+			  "\xd3",
+		.rlen	= 17,
+	}, {
+		.key	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0",
+		.klen	= 16,
+		.iv	= "\x4c\x49\x3d\xec\xd8\xa8\xa0\x98"
+			  "\xc5\xb0\xd3\x1f\xde\x48\x2e\x22",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xe3\x93\x15\xae\x5f\x9d\x3c\xb5"
+			  "\xd6\x9d\xee\xee\xcf\xaa\xaf\xe1"
+			  "\x45\x10\x96\xe0\xbf\x55\x0f\x4c"
+			  "\x1a\xfd\xf4\xda\x4e\x10\xde\xc9"
+			  "\x0e\x6f\xc7\x3c\x49\x94\x41\xfc"
+			  "\x59\x28\x88\x3c\x79\x10\x6b",
+		.ilen	= 47,
+		.result	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25"
+			  "\xfe\x8d\x45\x19\x1e\xc0\x0b\x99"
+			  "\x88\x11\x39\x12\x1c\x3a\xbb",
+		.rlen	= 31,
+	}, {
+		.key	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6",
+		.klen	= 16,
+		.iv	= "\x89\x6e\x77\x8b\xe8\x23\x49\xb4"
+			  "\x45\x8a\x85\xb1\xd8\x6c\xf1\x28",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x1c\x8e\x22\x34\xfd\xab\xe6\x0d"
+			  "\x1c\x9f\x06\x54\x8b\x0b\xb4\x40"
+			  "\xde\x11\x59\x3e\xfd\x74\xf6\x42"
+			  "\x97\x17\xf7\x24\xb6\x7e\xc4\xc6"
+			  "\x06\xa3\x94\xda\x3d\x7f\x55\x0a"
+			  "\x92\x07\x2f\xa6\xf3\x6b\x2c\xfc",
+		.ilen	= 48,
+		.result	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b"
+			  "\x28\x50\x51\x9d\x24\x60\x8d\xb3"
+			  "\x49\x3e\x17\xea\xf6\x99\x5a\xdd",
+		.rlen	= 32,
+	}, {
+		.key	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad",
+		.klen	= 16,
+		.iv	= "\xc5\x93\xb0\x2a\xf8\x9f\xf1\xd0"
+			  "\xc6\x64\x37\x42\xd2\x90\xb3\x2e",
+		.assoc	= "\xd5",
+		.alen	= 1,
+		.input	= "\xa0\x2a\xb4\x9a\x91\x00\x15\xb8"
+			  "\x0f\x9a\x15\x60\x0e\x9b\x13\x8f",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3",
+		.klen	= 16,
+		.iv	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76\x34",
+		.assoc	= "\x11\x81\x78\x32\x4d\xb9\x44\x73"
+			  "\x68\x75\x16\xf8\xcb\x7e\xa7",
+		.alen	= 15,
+		.input	= "\x4c\x26\xad\x9c\x14\xfd\x9c\x8c"
+			  "\x84\xfb\x26\xfb\xd5\xca\x62\x39",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9",
+		.klen	= 16,
+		.iv	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b",
+		.assoc	= "\x4e\xa5\xb2\xd1\x5d\x35\xed\x8f"
+			  "\xe8\x4f\xc8\x89\xc5\xa2\x69\xbc",
+		.alen	= 16,
+		.input	= "\x45\x85\x0e\x0f\xf4\xae\x96\xa1"
+			  "\x99\x4d\x6d\xb4\x67\x32\xb0\x3a",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf",
+		.klen	= 16,
+		.iv	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41",
+		.assoc	= "\x8a\xca\xec\x70\x6d\xb1\x96\xab"
+			  "\x69\x29\x7a\x1b\xbf\xc7\x2c\xc2"
+			  "\x07",
+		.alen	= 17,
+		.input	= "\x33\xb1\x42\x97\x8e\x16\x7b\x63"
+			  "\x06\xba\x5b\xcb\xae\x6d\x8b\x56",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6",
+		.klen	= 16,
+		.iv	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47",
+		.assoc	= "\xc7\xef\x26\x10\x7d\x2c\x3f\xc6"
+			  "\xea\x03\x2c\xac\xb9\xeb\xef\xc9"
+			  "\x31\x6b\x08\x12\xfc\xd8\x37\x2d"
+			  "\xe0\x17\x3a\x2e\x83\x5c\x8f",
+		.alen	= 31,
+		.input	= "\xda\x44\x08\x8c\x2a\xa5\x07\x35"
+			  "\x0b\x54\x4e\x6d\xe3\xfd\xc4\x5f",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc",
+		.klen	= 16,
+		.iv	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d",
+		.assoc	= "\x03\x14\x5f\xaf\x8d\xa8\xe7\xe2"
+			  "\x6b\xde\xde\x3e\xb3\x10\xb1\xcf"
+			  "\x5c\x2d\x14\x96\x01\x78\xb9\x47"
+			  "\xa1\x44\x19\x06\x5d\xbb\x2e\x2f",
+		.alen	= 32,
+		.input	= "\x1b\xb1\xf1\xa8\x9e\xc2\xb2\x88"
+			  "\x40\x7f\x7b\x19\x7a\x52\x8c\xf0",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2",
+		.klen	= 16,
+		.iv	= "\x31\x6f\x0b\xe6\x59\x85\xe6\x77"
+			  "\xcc\x81\x63\xab\xae\x6b\x43\x54",
+		.assoc	= "\x40",
+		.alen	= 1,
+		.input	= "\x6e\xc8\xfb\x15\x9d\x98\x49\xc9"
+			  "\xa0\x98\x09\x85\xbe\x56\x8e\x79"
+			  "\xf4",
+		.ilen	= 17,
+		.result	= "\x4f",
+		.rlen	= 1,
+	}, {
+		.key	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8",
+		.klen	= 16,
+		.iv	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06\x5a",
+		.assoc	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37",
+		.alen	= 15,
+		.input	= "\x99\x2e\x84\x50\x64\x5c\xab\x29"
+			  "\x20\xba\xb9\x2f\x62\x3a\xce\x2a"
+			  "\x75\x25\x3b\xe3\x40\xe0\x1d\xfc"
+			  "\x20\x63\x0b\x49\x7e\x97\x08",
+		.ilen	= 31,
+		.result	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67",
+		.rlen	= 15,
+	}, {
+		.key	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf",
+		.klen	= 16,
+		.iv	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60",
+		.assoc	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2",
+		.alen	= 16,
+		.input	= "\xd9\x8e\xfd\x50\x8f\x02\x9f\xee"
+			  "\x78\x08\x12\xec\x09\xaf\x53\x14"
+			  "\x90\x3e\x3d\x76\xad\x71\x21\x08"
+			  "\x77\xe5\x4b\x15\xc2\xe6\xbc\xdb",
+		.ilen	= 32,
+		.result	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.rlen	= 16,
+	}, {
+		.key	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5",
+		.klen	= 16,
+		.iv	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66",
+		.assoc	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05",
+		.alen	= 17,
+		.input	= "\xf3\xe7\x95\x86\xcf\x34\x95\x96"
+			  "\x17\xfe\x1b\xae\x1b\x31\xf2\x1a"
+			  "\xbd\xbc\xc9\x4e\x11\x29\x09\x5c"
+			  "\x05\xd3\xb4\x2e\x4a\x74\x59\x49"
+			  "\x7d",
+		.ilen	= 33,
+		.result	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69"
+			  "\xd0",
+		.rlen	= 17,
+	}, {
+		.key	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb",
+		.klen	= 16,
+		.iv	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d",
+		.assoc	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a",
+		.alen	= 31,
+		.input	= "\x06\x96\xb2\xbf\x63\xf4\x1e\x24"
+			  "\x0d\x19\x15\x61\x65\x3b\x06\x26"
+			  "\x71\xe8\x7e\x16\xdb\x96\x01\x01"
+			  "\x52\xcd\x49\x5b\x07\x33\x4e\xe7"
+			  "\xaa\x91\xf5\xd5\xc6\xfe\x41\xb5"
+			  "\xed\x90\xce\xb9\xcd\xcc\xa1",
+		.ilen	= 47,
+		.result	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70"
+			  "\xfa\xa9\xd0\x4d\x5c\x40\x23\xcd"
+			  "\x98\x34\xab\x37\x56\xae\x32",
+		.rlen	= 31,
+	}, {
+		.key	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1",
+		.klen	= 16,
+		.iv	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73",
+		.assoc	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37",
+		.alen	= 32,
+		.input	= "\xf9\xd7\xee\x17\xfd\x24\xcd\xf1"
+			  "\xbc\x0f\x35\x97\x97\x0c\x4b\x18"
+			  "\xce\x58\xc8\x3b\xd4\x85\x93\x79"
+			  "\xcc\x9c\xea\xc1\x73\x13\x0b\x4c"
+			  "\xcc\x6f\x28\xf8\xa4\x4e\xb8\x56"
+			  "\x64\x4e\x47\xce\xb2\xb4\x92\xb4",
+		.ilen	= 48,
+		.result	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76"
+			  "\x24\x6b\xdc\xd1\x61\xe0\xa5\xe7"
+			  "\x5a\x61\x8a\x0f\x30\x0d\xd1\xec",
+		.rlen	= 32,
+	}, {
+		.key	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7",
+		.klen	= 16,
+		.iv	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79",
+		.assoc	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d",
+		.alen	= 33,
+		.input	= "\x58\xfa\x3a\x3d\xd9\x88\x63\xe8"
+			  "\xc5\x78\x50\x8b\x4a\xc9\xdf\x7f"
+			  "\x4b\xfa\xc8\x2e\x67\x43\xf3\x63"
+			  "\x42\x8e\x99\x5a\x9c\x0b\x84\x77"
+			  "\xbc\x46\x76\x48\x82\xc7\x57\x96"
+			  "\xe1\x65\xd1\xed\x1d\xdd\x80\x24"
+			  "\xa6\x4d\xa9\xf1\x53\x8b\x5e\x0e"
+			  "\x26\xb9\xcc\x37\xe5\x43\xe1\x5a"
+			  "\x8a\xd6\x8c\x5a\xe4\x95\xd1\x8d"
+			  "\xf7\x33\x64\xc1\xd3\xf2\xfc\x35"
+			  "\x01",
+		.ilen	= 81,
+		.result	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c"
+			  "\x4f\x2e\xe8\x55\x66\x80\x27\x00"
+			  "\x1b\x8f\x68\xe7\x0a\x6c\x71\xc3"
+			  "\x21\x78\x55\x9d\x9c\x65\x7b\xcd"
+			  "\x0a\x34\x97\xff\x47\x37\xb0\x2a"
+			  "\x80\x0d\x19\x98\x33\xa9\x7a\xe3"
+			  "\x2e\x4c\xc6\xf3\x8c\x88\x42\x01"
+			  "\xbd",
+		.rlen	= 65,
+	}, {
+		.key	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe",
+		.klen	= 16,
+		.iv	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f",
+		.assoc	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac\xfa\x58\x7f\xe5\x73\x09\x8c"
+			  "\x1d\x40\x87\x8c\xd9\x75\xc0\x55"
+			  "\xa2\xda\x07\xd1\xc2\xa9\xd1\xbb"
+			  "\x09\x4f\x77\x62\x88\x2d\xf2\x68"
+			  "\x54",
+		.alen	= 65,
+		.input	= "\x4c\xa9\xac\x71\xed\x10\xa6\x24"
+			  "\xb7\xa7\xdf\x8b\xf5\xc2\x41\xcb"
+			  "\x05\xc9\xd6\x97\xb6\x10\x7f\x17"
+			  "\xc2\xc0\x93\xcf\xe0\x94\xfd\x99"
+			  "\xf2\x62\x25\x28\x01\x23\x6f\x8b"
+			  "\x04\x52\xbc\xb0\x3e\x66\x52\x90"
+			  "\x9f",
+		.ilen	= 49,
+		.result	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82"
+			  "\x79\xf0\xf3\xd9\x6c\x20\xa9\x1a"
+			  "\xdc\xbc\x47\xc0\xe4\xcb\x10\x99"
+			  "\x2f",
+		.rlen	= 33,
+	}, {
+		.key	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04",
+		.klen	= 16,
+		.iv	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85",
+		.assoc	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07",
+		.alen	= 16,
+		.input	= "\x6d\xed\x04\x7a\x2f\x0c\x30\xa5"
+			  "\x96\xe6\x97\xe4\x10\xeb\x40\x95"
+			  "\xc5\x9a\xdf\x31\xd5\xa5\xa6\xec"
+			  "\x05\xa8\x31\x50\x11\x19\x44",
+		.ilen	= 31,
+		.result	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.rlen	= 16,
+	}, {
+		.key	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a",
+		.klen	= 16,
+		.iv	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c",
+		.assoc	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d",
+		.alen	= 16,
+		.input	= "\x30\x95\x7d\xea\xdc\x62\xc0\x88"
+			  "\xa1\xe3\x8d\x8c\xac\x04\x10\xa7"
+			  "\xfa\xfa\x07\xbd\xa0\xf0\x36\xeb"
+			  "\x21\x93\x2e\x31\x84\x83",
+		.ilen	= 30,
+		.result	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.rlen	= 16,
+	}, {
+		.key	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10",
+		.klen	= 16,
+		.iv	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92",
+		.assoc	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13",
+		.alen	= 16,
+		.input	= "\x93\xcd\xee\xd4\xcb\x9d\x8d\x16"
+			  "\x63\x0d\x43\xd5\x49\xca\xa8\x85"
+			  "\x49\xc0\xae\x13\xbc\x26\x1d\x4b",
+		.ilen	= 24,
+		.result	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.rlen	= 16,
+	},
+};
+
+/*
+ * AEGIS-256 test vectors - generated via reference implementation from
+ * SUPERCOP (https://bench.cr.yp.to/supercop.html):
+ *
+ *   https://bench.cr.yp.to/supercop/supercop-20170228.tar.xz
+ *   (see crypto_aead/aegis256/)
+ */
+static const struct aead_testvec aegis256_enc_tv_template[] = {
+	{
+		.key	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81"
+			  "\xca\xb0\x82\x21\x41\xa8\xe0\x06"
+			  "\x30\x0b\x37\xf6\xb6\x17\xe7\xb5",
+		.klen	= 32,
+		.iv	= "\x1e\x92\x1c\xcf\x88\x3d\x54\x0d"
+			  "\x40\x6d\x59\x48\xfc\x92\x61\x03"
+			  "\x95\x61\x05\x42\x82\x50\xc0\x0c"
+			  "\x60\x16\x6f\xec\x6d\x2f\xcf\x6b",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xd5\x65\x3a\xa9\x03\x51\xd7\xaa"
+			  "\xfa\x4b\xd8\xa2\x41\x9b\xc1\xb2",
+		.rlen	= 16,
+	}, {
+		.key	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87"
+			  "\xf4\x72\x8e\xa5\x46\x48\x62\x20"
+			  "\xf1\x38\x16\xce\x90\x76\x87\x8c",
+		.klen	= 32,
+		.iv	= "\x5a\xb7\x56\x6e\x98\xb9\xfd\x29"
+			  "\xc1\x47\x0b\xda\xf6\xb6\x23\x09"
+			  "\xbf\x23\x11\xc6\x87\xf0\x42\x26"
+			  "\x22\x44\x4e\xc4\x47\x8e\x6e\x41",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x79",
+		.ilen	= 1,
+		.result	= "\x84\xa2\x8f\xad\xdb\x8d\x2c\x16"
+			  "\x9e\x89\xd9\x06\xa6\xa8\x14\x29"
+			  "\x8b",
+		.rlen	= 17,
+	}, {
+		.key	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e"
+			  "\x1f\x35\x9a\x29\x4b\xe8\xe4\x39"
+			  "\xb3\x66\xf5\xa6\x6a\xd5\x26\x62",
+		.klen	= 32,
+		.iv	= "\x97\xdb\x90\x0e\xa8\x35\xa5\x45"
+			  "\x42\x21\xbd\x6b\xf0\xda\xe6\x0f"
+			  "\xe9\xe5\x1d\x4a\x8c\x90\xc4\x40"
+			  "\xe3\x71\x2d\x9c\x21\xed\x0e\x18",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47",
+		.ilen	= 15,
+		.result	= "\x09\x94\x1f\xa6\x13\xc3\x74\x75"
+			  "\x17\xad\x8a\x0e\xd8\x66\x9a\x28"
+			  "\xd7\x30\x66\x09\x2a\xdc\xfa\x2a"
+			  "\x9f\x3b\xd7\xdd\x66\xd1\x2b",
+		.rlen	= 31,
+	}, {
+		.key	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94"
+			  "\x49\xf7\xa5\xad\x50\x88\x66\x53"
+			  "\x74\x94\xd4\x7f\x44\x34\xc5\x39",
+		.klen	= 32,
+		.iv	= "\xd3\x00\xc9\xad\xb8\xb0\x4e\x61"
+			  "\xc3\xfb\x6f\xfd\xea\xff\xa9\x15"
+			  "\x14\xa8\x28\xce\x92\x30\x46\x59"
+			  "\xa4\x9f\x0b\x75\xfb\x4c\xad\xee",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.ilen	= 16,
+		.result	= "\x8a\x46\xa2\x22\x8c\x03\xab\x6f"
+			  "\x54\x63\x4e\x7f\xc9\x8e\xfa\x70"
+			  "\x7b\xe5\x8d\x78\xbc\xe9\xb6\xa1"
+			  "\x29\x17\xc8\x3b\x52\xa4\x98\x72",
+		.rlen	= 32,
+	}, {
+		.key	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a"
+			  "\x74\xb9\xb1\x32\x55\x28\xe8\x6d"
+			  "\x35\xc1\xb3\x57\x1f\x93\x64\x0f",
+		.klen	= 32,
+		.iv	= "\x10\x25\x03\x4c\xc8\x2c\xf7\x7d"
+			  "\x44\xd5\x21\x8e\xe4\x23\x6b\x1c"
+			  "\x3e\x6a\x34\x53\x97\xd0\xc8\x73"
+			  "\x66\xcd\xea\x4d\xd5\xab\x4c\xc5",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f"
+			  "\xd3",
+		.ilen	= 17,
+		.result	= "\x71\x6b\x37\x0b\x02\x61\x28\x12"
+			  "\x83\xab\x66\x90\x84\xc7\xd1\xc5"
+			  "\xb2\x7a\xb4\x7b\xb4\xfe\x02\xb2"
+			  "\xc0\x00\x39\x13\xb5\x51\x68\x44"
+			  "\xad",
+		.rlen	= 33,
+	}, {
+		.key	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0"
+			  "\x9e\x7c\xbc\xb6\x5b\xc8\x6a\x86"
+			  "\xf7\xef\x91\x30\xf9\xf2\x04\xe6",
+		.klen	= 32,
+		.iv	= "\x4c\x49\x3d\xec\xd8\xa8\xa0\x98"
+			  "\xc5\xb0\xd3\x1f\xde\x48\x2e\x22"
+			  "\x69\x2c\x3f\xd7\x9c\x70\x4a\x8d"
+			  "\x27\xfa\xc9\x26\xaf\x0a\xeb\x9c",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25"
+			  "\xfe\x8d\x45\x19\x1e\xc0\x0b\x99"
+			  "\x88\x11\x39\x12\x1c\x3a\xbb",
+		.ilen	= 31,
+		.result	= "\xaf\xa4\x34\x0d\x59\xe6\x1c\x2f"
+			  "\x06\x3b\x52\x18\x49\x75\x1b\xf0"
+			  "\x53\x09\x72\x7b\x45\x79\xe0\xbe"
+			  "\x89\x85\x23\x15\xb8\x79\x07\x4c"
+			  "\x53\x7a\x15\x37\x0a\xee\xb7\xfb"
+			  "\xc4\x1f\x12\x27\xcf\x77\x90",
+		.rlen	= 47,
+	}, {
+		.key	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6"
+			  "\xc8\x3e\xc8\x3a\x60\x68\xec\xa0"
+			  "\xb8\x1c\x70\x08\xd3\x51\xa3\xbd",
+		.klen	= 32,
+		.iv	= "\x89\x6e\x77\x8b\xe8\x23\x49\xb4"
+			  "\x45\x8a\x85\xb1\xd8\x6c\xf1\x28"
+			  "\x93\xef\x4b\x5b\xa1\x10\xcc\xa6"
+			  "\xe8\x28\xa8\xfe\x89\x69\x8b\x72",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b"
+			  "\x28\x50\x51\x9d\x24\x60\x8d\xb3"
+			  "\x49\x3e\x17\xea\xf6\x99\x5a\xdd",
+		.ilen	= 32,
+		.result	= "\xe2\xc9\x0b\x33\x31\x02\xb3\xb4"
+			  "\x33\xfe\xeb\xa8\xb7\x9b\xb2\xd7"
+			  "\xeb\x0f\x05\x2b\xba\xb3\xca\xef"
+			  "\xf6\xd1\xb6\xc0\xb9\x9b\x85\xc5"
+			  "\xbf\x7a\x3e\xcc\x31\x76\x09\x80"
+			  "\x32\x5d\xbb\xe8\x38\x0e\x77\xd3",
+		.rlen	= 48,
+	}, {
+		.key	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad"
+			  "\xf3\x00\xd4\xbf\x65\x08\x6e\xb9"
+			  "\x7a\x4a\x4f\xe0\xad\xb0\x42\x93",
+		.klen	= 32,
+		.iv	= "\xc5\x93\xb0\x2a\xf8\x9f\xf1\xd0"
+			  "\xc6\x64\x37\x42\xd2\x90\xb3\x2e"
+			  "\xbd\xb1\x57\xe0\xa6\xb0\x4e\xc0"
+			  "\xaa\x55\x87\xd6\x63\xc8\x2a\x49",
+		.assoc	= "\xd5",
+		.alen	= 1,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x96\x43\x30\xca\x6c\x4f\xd7\x12"
+			  "\xba\xd9\xb3\x18\x86\xdf\xc3\x52",
+		.rlen	= 16,
+	}, {
+		.key	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3"
+			  "\x1d\xc3\xdf\x43\x6a\xa8\xf0\xd3"
+			  "\x3b\x77\x2e\xb9\x87\x0f\xe1\x6a",
+		.klen	= 32,
+		.iv	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76\x34"
+			  "\xe8\x73\x62\x64\xab\x50\xd0\xda"
+			  "\x6b\x83\x66\xaf\x3e\x27\xc9\x1f",
+		.assoc	= "\x11\x81\x78\x32\x4d\xb9\x44\x73"
+			  "\x68\x75\x16\xf8\xcb\x7e\xa7",
+		.alen	= 15,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x2f\xab\x45\xe2\xa7\x46\xc5\x83"
+			  "\x11\x9f\xb0\x74\xee\xc7\x03\xdd",
+		.rlen	= 16,
+	}, {
+		.key	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9"
+			  "\x47\x85\xeb\xc7\x6f\x48\x72\xed"
+			  "\xfc\xa5\x0d\x91\x61\x6e\x81\x40",
+		.klen	= 32,
+		.iv	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b"
+			  "\x12\x35\x6e\xe8\xb0\xf0\x52\xf3"
+			  "\x2d\xb0\x45\x87\x18\x86\x68\xf6",
+		.assoc	= "\x4e\xa5\xb2\xd1\x5d\x35\xed\x8f"
+			  "\xe8\x4f\xc8\x89\xc5\xa2\x69\xbc",
+		.alen	= 16,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x16\x44\x73\x33\x5d\xf2\xb9\x04"
+			  "\x6b\x79\x98\xef\xdb\xd5\xc5\xf1",
+		.rlen	= 16,
+	}, {
+		.key	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf"
+			  "\x72\x47\xf6\x4b\x74\xe8\xf4\x06"
+			  "\xbe\xd3\xec\x6a\x3b\xcd\x20\x17",
+		.klen	= 32,
+		.iv	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41"
+			  "\x3c\xf8\x79\x6c\xb6\x90\xd4\x0d"
+			  "\xee\xde\x23\x60\xf2\xe5\x08\xcc",
+		.assoc	= "\x8a\xca\xec\x70\x6d\xb1\x96\xab"
+			  "\x69\x29\x7a\x1b\xbf\xc7\x2c\xc2"
+			  "\x07",
+		.alen	= 17,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xa4\x9b\xb8\x47\xc0\xed\x7a\x45"
+			  "\x98\x54\x8c\xed\x3d\x17\xf0\xdd",
+		.rlen	= 16,
+	}, {
+		.key	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6"
+			  "\x9c\x0a\x02\xd0\x79\x88\x76\x20"
+			  "\x7f\x00\xca\x42\x15\x2c\xbf\xed",
+		.klen	= 32,
+		.iv	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47"
+			  "\x67\xba\x85\xf1\xbb\x30\x56\x26"
+			  "\xaf\x0b\x02\x38\xcc\x44\xa7\xa3",
+		.assoc	= "\xc7\xef\x26\x10\x7d\x2c\x3f\xc6"
+			  "\xea\x03\x2c\xac\xb9\xeb\xef\xc9"
+			  "\x31\x6b\x08\x12\xfc\xd8\x37\x2d"
+			  "\xe0\x17\x3a\x2e\x83\x5c\x8f",
+		.alen	= 31,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x20\x24\xe2\x33\x5c\x60\xc9\xf0"
+			  "\xa4\x96\x2f\x0d\x53\xc2\xf8\xfc",
+		.rlen	= 16,
+	}, {
+		.key	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc"
+			  "\xc6\xcc\x0e\x54\x7f\x28\xf8\x3a"
+			  "\x40\x2e\xa9\x1a\xf0\x8b\x5e\xc4",
+		.klen	= 32,
+		.iv	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d"
+			  "\x91\x7c\x91\x75\xc0\xd0\xd8\x40"
+			  "\x71\x39\xe1\x10\xa6\xa3\x46\x7a",
+		.assoc	= "\x03\x14\x5f\xaf\x8d\xa8\xe7\xe2"
+			  "\x6b\xde\xde\x3e\xb3\x10\xb1\xcf"
+			  "\x5c\x2d\x14\x96\x01\x78\xb9\x47"
+			  "\xa1\x44\x19\x06\x5d\xbb\x2e\x2f",
+		.alen	= 32,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x6f\x4a\xb9\xe0\xff\x51\xa3\xf1"
+			  "\xd2\x64\x3e\x66\x6a\xb2\x03\xc0",
+		.rlen	= 16,
+	}, {
+		.key	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2"
+			  "\xf1\x8e\x19\xd8\x84\xc8\x7a\x53"
+			  "\x02\x5b\x88\xf3\xca\xea\xfe\x9b",
+		.klen	= 32,
+		.iv	= "\x31\x6f\x0b\xe6\x59\x85\xe6\x77"
+			  "\xcc\x81\x63\xab\xae\x6b\x43\x54"
+			  "\xbb\x3f\x9c\xf9\xc5\x70\x5a\x5a"
+			  "\x32\x67\xc0\xe9\x80\x02\xe5\x50",
+		.assoc	= "\x40",
+		.alen	= 1,
+		.input	= "\x4f",
+		.ilen	= 1,
+		.result	= "\x2c\xfb\xad\x7e\xbe\xa0\x9a\x5b"
+			  "\x7a\x3f\x81\xf7\xfc\x1b\x79\x83"
+			  "\xc7",
+		.rlen	= 17,
+	}, {
+		.key	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8"
+			  "\x1b\x50\x25\x5d\x89\x68\xfc\x6d"
+			  "\xc3\x89\x67\xcb\xa4\x49\x9d\x71",
+		.klen	= 32,
+		.iv	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06\x5a"
+			  "\xe6\x01\xa8\x7e\xca\x10\xdc\x73"
+			  "\xf4\x94\x9f\xc1\x5a\x61\x85\x27",
+		.assoc	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37",
+		.alen	= 15,
+		.input	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67",
+		.ilen	= 15,
+		.result	= "\x1f\x7f\xca\x3c\x2b\xe7\x27\xba"
+			  "\x7e\x98\x83\x02\x34\x23\xf7\x94"
+			  "\xde\x35\xe6\x1d\x14\x18\xe5\x38"
+			  "\x14\x80\x6a\xa7\x1b\xae\x1d",
+		.rlen	= 31,
+	}, {
+		.key	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf"
+			  "\x46\x13\x31\xe1\x8e\x08\x7e\x87"
+			  "\x85\xb6\x46\xa3\x7e\xa8\x3c\x48",
+		.klen	= 32,
+		.iv	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60"
+			  "\x10\xc3\xb3\x02\xcf\xb0\x5e\x8d"
+			  "\xb5\xc2\x7e\x9a\x35\xc0\x24\xfd",
+		.assoc	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2",
+		.alen	= 16,
+		.input	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.ilen	= 16,
+		.result	= "\x05\x86\x9e\xd7\x2b\xa3\x97\x01"
+			  "\xbe\x28\x98\x10\x6f\xe9\x61\x32"
+			  "\x96\xbb\xb1\x2e\x8f\x0c\x44\xb9"
+			  "\x46\x2d\x55\xe3\x42\x67\xf2\xaf",
+		.rlen	= 32,
+	}, {
+		.key	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5"
+			  "\x70\xd5\x3c\x65\x93\xa8\x00\xa0"
+			  "\x46\xe4\x25\x7c\x58\x08\xdb\x1e",
+		.klen	= 32,
+		.iv	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66"
+			  "\x3b\x86\xbf\x86\xd4\x50\xe0\xa7"
+			  "\x76\xef\x5c\x72\x0f\x1f\xc3\xd4",
+		.assoc	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05",
+		.alen	= 17,
+		.input	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69"
+			  "\xd0",
+		.ilen	= 17,
+		.result	= "\x9c\xe0\x06\x7b\x86\xcf\x2e\xd8"
+			  "\x45\x65\x1b\x72\x9b\xaa\xa3\x1e"
+			  "\x87\x9d\x26\xdf\xff\x81\x11\xd2"
+			  "\x47\x41\xb9\x24\xc1\x8a\xa3\x8b"
+			  "\x55",
+		.rlen	= 33,
+	}, {
+		.key	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb"
+			  "\x9a\x97\x48\xe9\x98\x48\x82\xba"
+			  "\x07\x11\x04\x54\x32\x67\x7b\xf5",
+		.klen	= 32,
+		.iv	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d"
+			  "\x65\x48\xcb\x0a\xda\xf0\x62\xc0"
+			  "\x38\x1d\x3b\x4a\xe9\x7e\x62\xaa",
+		.assoc	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a",
+		.alen	= 31,
+		.input	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70"
+			  "\xfa\xa9\xd0\x4d\x5c\x40\x23\xcd"
+			  "\x98\x34\xab\x37\x56\xae\x32",
+		.ilen	= 31,
+		.result	= "\xa0\xc8\xde\x83\x0d\xc3\x4e\xd5"
+			  "\x69\x7f\x7a\xdd\x8c\x46\xda\xba"
+			  "\x0a\x5c\x0e\x7f\xac\xee\x02\xd2"
+			  "\xe5\x4b\x0a\xba\xb8\xa4\x7b\x66"
+			  "\xde\xae\xdb\xc2\xc0\x0b\xf7\x2b"
+			  "\xdf\xb8\xea\xd8\xa9\x38\xed",
+		.rlen	= 47,
+	}, {
+		.key	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1"
+			  "\xc5\x5a\x53\x6e\x9d\xe8\x04\xd4"
+			  "\xc9\x3f\xe2\x2d\x0c\xc6\x1a\xcb",
+		.klen	= 32,
+		.iv	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73"
+			  "\x8f\x0a\xd6\x8f\xdf\x90\xe4\xda"
+			  "\xf9\x4a\x1a\x23\xc3\xdd\x02\x81",
+		.assoc	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37",
+		.alen	= 32,
+		.input	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76"
+			  "\x24\x6b\xdc\xd1\x61\xe0\xa5\xe7"
+			  "\x5a\x61\x8a\x0f\x30\x0d\xd1\xec",
+		.ilen	= 32,
+		.result	= "\xd3\x68\x14\x70\x3c\x01\x43\x86"
+			  "\x02\xab\xbe\x75\xaa\xe7\xf5\x53"
+			  "\x5c\x05\xbd\x9b\x19\xbb\x2a\x61"
+			  "\x8f\x69\x05\x75\x8e\xca\x60\x0c"
+			  "\x5b\xa2\x48\x61\x32\x74\x11\x2b"
+			  "\xf6\xcf\x06\x78\x6f\x78\x1a\x4a",
+		.rlen	= 48,
+	}, {
+		.key	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7"
+			  "\xef\x1c\x5f\xf2\xa3\x88\x86\xed"
+			  "\x8a\x6d\xc1\x05\xe7\x25\xb9\xa2",
+		.klen	= 32,
+		.iv	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79"
+			  "\xba\xcd\xe2\x13\xe4\x30\x66\xf4"
+			  "\xba\x78\xf9\xfb\x9d\x3c\xa1\x58",
+		.assoc	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d",
+		.alen	= 33,
+		.input	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c"
+			  "\x4f\x2e\xe8\x55\x66\x80\x27\x00"
+			  "\x1b\x8f\x68\xe7\x0a\x6c\x71\xc3"
+			  "\x21\x78\x55\x9d\x9c\x65\x7b\xcd"
+			  "\x0a\x34\x97\xff\x47\x37\xb0\x2a"
+			  "\x80\x0d\x19\x98\x33\xa9\x7a\xe3"
+			  "\x2e\x4c\xc6\xf3\x8c\x88\x42\x01"
+			  "\xbd",
+		.ilen	= 65,
+		.result	= "\x07\x0a\x35\xb0\x82\x03\x5a\xd2"
+			  "\x15\x3a\x6c\x72\x83\x9b\xb1\x75"
+			  "\xea\xf2\xfc\xff\xc6\xf1\x13\xa4"
+			  "\x1a\x93\x33\x79\x97\x82\x81\xc0"
+			  "\x96\xc2\x00\xab\x39\xae\xa1\x62"
+			  "\x53\xa3\x86\xc9\x07\x8c\xaf\x22"
+			  "\x47\x31\x29\xca\x4a\x95\xf5\xd5"
+			  "\x20\x63\x5a\x54\x80\x2c\x4a\x63"
+			  "\xfb\x18\x73\x31\x4f\x08\x21\x5d"
+			  "\x20\xe9\xc3\x7e\xea\x25\x77\x3a"
+			  "\x65",
+		.rlen	= 81,
+	}, {
+		.key	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe"
+			  "\x19\xde\x6b\x76\xa8\x28\x08\x07"
+			  "\x4b\x9a\xa0\xdd\xc1\x84\x58\x79",
+		.klen	= 32,
+		.iv	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f"
+			  "\xe4\x8f\xed\x97\xe9\xd0\xe8\x0d"
+			  "\x7c\xa6\xd8\xd4\x77\x9b\x40\x2e",
+		.assoc	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac\xfa\x58\x7f\xe5\x73\x09\x8c"
+			  "\x1d\x40\x87\x8c\xd9\x75\xc0\x55"
+			  "\xa2\xda\x07\xd1\xc2\xa9\xd1\xbb"
+			  "\x09\x4f\x77\x62\x88\x2d\xf2\x68"
+			  "\x54",
+		.alen	= 65,
+		.input	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82"
+			  "\x79\xf0\xf3\xd9\x6c\x20\xa9\x1a"
+			  "\xdc\xbc\x47\xc0\xe4\xcb\x10\x99"
+			  "\x2f",
+		.ilen	= 33,
+		.result	= "\x33\xc1\xda\xfa\x15\x21\x07\x8e"
+			  "\x93\x68\xea\x64\x7b\x3d\x4b\x6b"
+			  "\x71\x5e\x5e\x6b\x92\xaa\x65\xc2"
+			  "\x7a\x2a\xc1\xa9\x0a\xa1\x24\x81"
+			  "\x26\x3a\x5a\x09\xe8\xce\x73\x72"
+			  "\xde\x7b\x58\x9e\x85\xb9\xa4\x28"
+			  "\xda",
+		.rlen	= 49,
+	}, {
+		.key	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04"
+			  "\x44\xa1\x76\xfb\xad\xc8\x8a\x21"
+			  "\x0d\xc8\x7f\xb6\x9b\xe3\xf8\x4f",
+		.klen	= 32,
+		.iv	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85"
+			  "\x0e\x51\xf9\x1c\xee\x70\x6a\x27"
+			  "\x3d\xd3\xb7\xac\x51\xfa\xdf\x05",
+		.assoc	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07",
+		.alen	= 16,
+		.input	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.ilen	= 16,
+		.result	= "\x3e\xf8\x86\x3d\x39\xf8\x96\x02"
+			  "\x0f\xdf\xc9\x6e\x37\x1e\x57\x99"
+			  "\x07\x2a\x1a\xac\xd1\xda\xfd\x3b"
+			  "\xc7\xff\xbd\xbc\x85\x09\x0b",
+		.rlen	= 31,
+	}, {
+		.key	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a"
+			  "\x6e\x63\x82\x7f\xb2\x68\x0c\x3a"
+			  "\xce\xf5\x5e\x8e\x75\x42\x97\x26",
+		.klen	= 32,
+		.iv	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c"
+			  "\x39\x14\x05\xa0\xf3\x10\xec\x41"
+			  "\xff\x01\x95\x84\x2b\x59\x7f\xdb",
+		.assoc	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d",
+		.alen	= 16,
+		.input	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.ilen	= 16,
+		.result	= "\x2f\xc4\xd8\x0d\xa6\x07\xef\x2e"
+			  "\x6c\xd9\x84\x63\x70\x97\x61\x37"
+			  "\x08\x2f\x16\x90\x9e\x62\x30\x0d"
+			  "\x62\xd5\xc8\xf0\x46\x1a",
+		.rlen	= 30,
+	}, {
+		.key	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10"
+			  "\x98\x25\x8d\x03\xb7\x08\x8e\x54"
+			  "\x90\x23\x3d\x67\x4f\xa1\x36\xfc",
+		.klen	= 32,
+		.iv	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92"
+			  "\x63\xd6\x10\x24\xf8\xb0\x6e\x5a"
+			  "\xc0\x2e\x74\x5d\x06\xb8\x1e\xb2",
+		.assoc	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13",
+		.alen	= 16,
+		.input	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.ilen	= 16,
+		.result	= "\xce\xf3\x17\x87\x49\xc2\x00\x46"
+			  "\xc6\x12\x5c\x8f\x81\x38\xaa\x55"
+			  "\xf8\x67\x75\xf1\x75\xe3\x2a\x24",
+		.rlen	= 24,
+	},
+};
+
+static const struct aead_testvec aegis256_dec_tv_template[] = {
+	{
+		.key	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81"
+			  "\xca\xb0\x82\x21\x41\xa8\xe0\x06"
+			  "\x30\x0b\x37\xf6\xb6\x17\xe7\xb5",
+		.klen	= 32,
+		.iv	= "\x1e\x92\x1c\xcf\x88\x3d\x54\x0d"
+			  "\x40\x6d\x59\x48\xfc\x92\x61\x03"
+			  "\x95\x61\x05\x42\x82\x50\xc0\x0c"
+			  "\x60\x16\x6f\xec\x6d\x2f\xcf\x6b",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xd5\x65\x3a\xa9\x03\x51\xd7\xaa"
+			  "\xfa\x4b\xd8\xa2\x41\x9b\xc1\xb2",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87"
+			  "\xf4\x72\x8e\xa5\x46\x48\x62\x20"
+			  "\xf1\x38\x16\xce\x90\x76\x87\x8c",
+		.klen	= 32,
+		.iv	= "\x5a\xb7\x56\x6e\x98\xb9\xfd\x29"
+			  "\xc1\x47\x0b\xda\xf6\xb6\x23\x09"
+			  "\xbf\x23\x11\xc6\x87\xf0\x42\x26"
+			  "\x22\x44\x4e\xc4\x47\x8e\x6e\x41",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x84\xa2\x8f\xad\xdb\x8d\x2c\x16"
+			  "\x9e\x89\xd9\x06\xa6\xa8\x14\x29"
+			  "\x8b",
+		.ilen	= 17,
+		.result	= "\x79",
+		.rlen	= 1,
+	}, {
+		.key	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e"
+			  "\x1f\x35\x9a\x29\x4b\xe8\xe4\x39"
+			  "\xb3\x66\xf5\xa6\x6a\xd5\x26\x62",
+		.klen	= 32,
+		.iv	= "\x97\xdb\x90\x0e\xa8\x35\xa5\x45"
+			  "\x42\x21\xbd\x6b\xf0\xda\xe6\x0f"
+			  "\xe9\xe5\x1d\x4a\x8c\x90\xc4\x40"
+			  "\xe3\x71\x2d\x9c\x21\xed\x0e\x18",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x09\x94\x1f\xa6\x13\xc3\x74\x75"
+			  "\x17\xad\x8a\x0e\xd8\x66\x9a\x28"
+			  "\xd7\x30\x66\x09\x2a\xdc\xfa\x2a"
+			  "\x9f\x3b\xd7\xdd\x66\xd1\x2b",
+		.ilen	= 31,
+		.result	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47",
+		.rlen	= 15,
+	}, {
+		.key	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94"
+			  "\x49\xf7\xa5\xad\x50\x88\x66\x53"
+			  "\x74\x94\xd4\x7f\x44\x34\xc5\x39",
+		.klen	= 32,
+		.iv	= "\xd3\x00\xc9\xad\xb8\xb0\x4e\x61"
+			  "\xc3\xfb\x6f\xfd\xea\xff\xa9\x15"
+			  "\x14\xa8\x28\xce\x92\x30\x46\x59"
+			  "\xa4\x9f\x0b\x75\xfb\x4c\xad\xee",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x8a\x46\xa2\x22\x8c\x03\xab\x6f"
+			  "\x54\x63\x4e\x7f\xc9\x8e\xfa\x70"
+			  "\x7b\xe5\x8d\x78\xbc\xe9\xb6\xa1"
+			  "\x29\x17\xc8\x3b\x52\xa4\x98\x72",
+		.ilen	= 32,
+		.result	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.rlen	= 16,
+	}, {
+		.key	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a"
+			  "\x74\xb9\xb1\x32\x55\x28\xe8\x6d"
+			  "\x35\xc1\xb3\x57\x1f\x93\x64\x0f",
+		.klen	= 32,
+		.iv	= "\x10\x25\x03\x4c\xc8\x2c\xf7\x7d"
+			  "\x44\xd5\x21\x8e\xe4\x23\x6b\x1c"
+			  "\x3e\x6a\x34\x53\x97\xd0\xc8\x73"
+			  "\x66\xcd\xea\x4d\xd5\xab\x4c\xc5",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x71\x6b\x37\x0b\x02\x61\x28\x12"
+			  "\x83\xab\x66\x90\x84\xc7\xd1\xc5"
+			  "\xb2\x7a\xb4\x7b\xb4\xfe\x02\xb2"
+			  "\xc0\x00\x39\x13\xb5\x51\x68\x44"
+			  "\xad",
+		.ilen	= 33,
+		.result	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f"
+			  "\xd3",
+		.rlen	= 17,
+	}, {
+		.key	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0"
+			  "\x9e\x7c\xbc\xb6\x5b\xc8\x6a\x86"
+			  "\xf7\xef\x91\x30\xf9\xf2\x04\xe6",
+		.klen	= 32,
+		.iv	= "\x4c\x49\x3d\xec\xd8\xa8\xa0\x98"
+			  "\xc5\xb0\xd3\x1f\xde\x48\x2e\x22"
+			  "\x69\x2c\x3f\xd7\x9c\x70\x4a\x8d"
+			  "\x27\xfa\xc9\x26\xaf\x0a\xeb\x9c",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xaf\xa4\x34\x0d\x59\xe6\x1c\x2f"
+			  "\x06\x3b\x52\x18\x49\x75\x1b\xf0"
+			  "\x53\x09\x72\x7b\x45\x79\xe0\xbe"
+			  "\x89\x85\x23\x15\xb8\x79\x07\x4c"
+			  "\x53\x7a\x15\x37\x0a\xee\xb7\xfb"
+			  "\xc4\x1f\x12\x27\xcf\x77\x90",
+		.ilen	= 47,
+		.result	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25"
+			  "\xfe\x8d\x45\x19\x1e\xc0\x0b\x99"
+			  "\x88\x11\x39\x12\x1c\x3a\xbb",
+		.rlen	= 31,
+	}, {
+		.key	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6"
+			  "\xc8\x3e\xc8\x3a\x60\x68\xec\xa0"
+			  "\xb8\x1c\x70\x08\xd3\x51\xa3\xbd",
+		.klen	= 32,
+		.iv	= "\x89\x6e\x77\x8b\xe8\x23\x49\xb4"
+			  "\x45\x8a\x85\xb1\xd8\x6c\xf1\x28"
+			  "\x93\xef\x4b\x5b\xa1\x10\xcc\xa6"
+			  "\xe8\x28\xa8\xfe\x89\x69\x8b\x72",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xe2\xc9\x0b\x33\x31\x02\xb3\xb4"
+			  "\x33\xfe\xeb\xa8\xb7\x9b\xb2\xd7"
+			  "\xeb\x0f\x05\x2b\xba\xb3\xca\xef"
+			  "\xf6\xd1\xb6\xc0\xb9\x9b\x85\xc5"
+			  "\xbf\x7a\x3e\xcc\x31\x76\x09\x80"
+			  "\x32\x5d\xbb\xe8\x38\x0e\x77\xd3",
+		.ilen	= 48,
+		.result	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b"
+			  "\x28\x50\x51\x9d\x24\x60\x8d\xb3"
+			  "\x49\x3e\x17\xea\xf6\x99\x5a\xdd",
+		.rlen	= 32,
+	}, {
+		.key	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad"
+			  "\xf3\x00\xd4\xbf\x65\x08\x6e\xb9"
+			  "\x7a\x4a\x4f\xe0\xad\xb0\x42\x93",
+		.klen	= 32,
+		.iv	= "\xc5\x93\xb0\x2a\xf8\x9f\xf1\xd0"
+			  "\xc6\x64\x37\x42\xd2\x90\xb3\x2e"
+			  "\xbd\xb1\x57\xe0\xa6\xb0\x4e\xc0"
+			  "\xaa\x55\x87\xd6\x63\xc8\x2a\x49",
+		.assoc	= "\xd5",
+		.alen	= 1,
+		.input	= "\x96\x43\x30\xca\x6c\x4f\xd7\x12"
+			  "\xba\xd9\xb3\x18\x86\xdf\xc3\x52",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3"
+			  "\x1d\xc3\xdf\x43\x6a\xa8\xf0\xd3"
+			  "\x3b\x77\x2e\xb9\x87\x0f\xe1\x6a",
+		.klen	= 32,
+		.iv	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76\x34"
+			  "\xe8\x73\x62\x64\xab\x50\xd0\xda"
+			  "\x6b\x83\x66\xaf\x3e\x27\xc9\x1f",
+		.assoc	= "\x11\x81\x78\x32\x4d\xb9\x44\x73"
+			  "\x68\x75\x16\xf8\xcb\x7e\xa7",
+		.alen	= 15,
+		.input	= "\x2f\xab\x45\xe2\xa7\x46\xc5\x83"
+			  "\x11\x9f\xb0\x74\xee\xc7\x03\xdd",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9"
+			  "\x47\x85\xeb\xc7\x6f\x48\x72\xed"
+			  "\xfc\xa5\x0d\x91\x61\x6e\x81\x40",
+		.klen	= 32,
+		.iv	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b"
+			  "\x12\x35\x6e\xe8\xb0\xf0\x52\xf3"
+			  "\x2d\xb0\x45\x87\x18\x86\x68\xf6",
+		.assoc	= "\x4e\xa5\xb2\xd1\x5d\x35\xed\x8f"
+			  "\xe8\x4f\xc8\x89\xc5\xa2\x69\xbc",
+		.alen	= 16,
+		.input	= "\x16\x44\x73\x33\x5d\xf2\xb9\x04"
+			  "\x6b\x79\x98\xef\xdb\xd5\xc5\xf1",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf"
+			  "\x72\x47\xf6\x4b\x74\xe8\xf4\x06"
+			  "\xbe\xd3\xec\x6a\x3b\xcd\x20\x17",
+		.klen	= 32,
+		.iv	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41"
+			  "\x3c\xf8\x79\x6c\xb6\x90\xd4\x0d"
+			  "\xee\xde\x23\x60\xf2\xe5\x08\xcc",
+		.assoc	= "\x8a\xca\xec\x70\x6d\xb1\x96\xab"
+			  "\x69\x29\x7a\x1b\xbf\xc7\x2c\xc2"
+			  "\x07",
+		.alen	= 17,
+		.input	= "\xa4\x9b\xb8\x47\xc0\xed\x7a\x45"
+			  "\x98\x54\x8c\xed\x3d\x17\xf0\xdd",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6"
+			  "\x9c\x0a\x02\xd0\x79\x88\x76\x20"
+			  "\x7f\x00\xca\x42\x15\x2c\xbf\xed",
+		.klen	= 32,
+		.iv	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47"
+			  "\x67\xba\x85\xf1\xbb\x30\x56\x26"
+			  "\xaf\x0b\x02\x38\xcc\x44\xa7\xa3",
+		.assoc	= "\xc7\xef\x26\x10\x7d\x2c\x3f\xc6"
+			  "\xea\x03\x2c\xac\xb9\xeb\xef\xc9"
+			  "\x31\x6b\x08\x12\xfc\xd8\x37\x2d"
+			  "\xe0\x17\x3a\x2e\x83\x5c\x8f",
+		.alen	= 31,
+		.input	= "\x20\x24\xe2\x33\x5c\x60\xc9\xf0"
+			  "\xa4\x96\x2f\x0d\x53\xc2\xf8\xfc",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc"
+			  "\xc6\xcc\x0e\x54\x7f\x28\xf8\x3a"
+			  "\x40\x2e\xa9\x1a\xf0\x8b\x5e\xc4",
+		.klen	= 32,
+		.iv	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d"
+			  "\x91\x7c\x91\x75\xc0\xd0\xd8\x40"
+			  "\x71\x39\xe1\x10\xa6\xa3\x46\x7a",
+		.assoc	= "\x03\x14\x5f\xaf\x8d\xa8\xe7\xe2"
+			  "\x6b\xde\xde\x3e\xb3\x10\xb1\xcf"
+			  "\x5c\x2d\x14\x96\x01\x78\xb9\x47"
+			  "\xa1\x44\x19\x06\x5d\xbb\x2e\x2f",
+		.alen	= 32,
+		.input	= "\x6f\x4a\xb9\xe0\xff\x51\xa3\xf1"
+			  "\xd2\x64\x3e\x66\x6a\xb2\x03\xc0",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2"
+			  "\xf1\x8e\x19\xd8\x84\xc8\x7a\x53"
+			  "\x02\x5b\x88\xf3\xca\xea\xfe\x9b",
+		.klen	= 32,
+		.iv	= "\x31\x6f\x0b\xe6\x59\x85\xe6\x77"
+			  "\xcc\x81\x63\xab\xae\x6b\x43\x54"
+			  "\xbb\x3f\x9c\xf9\xc5\x70\x5a\x5a"
+			  "\x32\x67\xc0\xe9\x80\x02\xe5\x50",
+		.assoc	= "\x40",
+		.alen	= 1,
+		.input	= "\x2c\xfb\xad\x7e\xbe\xa0\x9a\x5b"
+			  "\x7a\x3f\x81\xf7\xfc\x1b\x79\x83"
+			  "\xc7",
+		.ilen	= 17,
+		.result	= "\x4f",
+		.rlen	= 1,
+	}, {
+		.key	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8"
+			  "\x1b\x50\x25\x5d\x89\x68\xfc\x6d"
+			  "\xc3\x89\x67\xcb\xa4\x49\x9d\x71",
+		.klen	= 32,
+		.iv	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06\x5a"
+			  "\xe6\x01\xa8\x7e\xca\x10\xdc\x73"
+			  "\xf4\x94\x9f\xc1\x5a\x61\x85\x27",
+		.assoc	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37",
+		.alen	= 15,
+		.input	= "\x1f\x7f\xca\x3c\x2b\xe7\x27\xba"
+			  "\x7e\x98\x83\x02\x34\x23\xf7\x94"
+			  "\xde\x35\xe6\x1d\x14\x18\xe5\x38"
+			  "\x14\x80\x6a\xa7\x1b\xae\x1d",
+		.ilen	= 31,
+		.result	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67",
+		.rlen	= 15,
+	}, {
+		.key	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf"
+			  "\x46\x13\x31\xe1\x8e\x08\x7e\x87"
+			  "\x85\xb6\x46\xa3\x7e\xa8\x3c\x48",
+		.klen	= 32,
+		.iv	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60"
+			  "\x10\xc3\xb3\x02\xcf\xb0\x5e\x8d"
+			  "\xb5\xc2\x7e\x9a\x35\xc0\x24\xfd",
+		.assoc	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2",
+		.alen	= 16,
+		.input	= "\x05\x86\x9e\xd7\x2b\xa3\x97\x01"
+			  "\xbe\x28\x98\x10\x6f\xe9\x61\x32"
+			  "\x96\xbb\xb1\x2e\x8f\x0c\x44\xb9"
+			  "\x46\x2d\x55\xe3\x42\x67\xf2\xaf",
+		.ilen	= 32,
+		.result	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.rlen	= 16,
+	}, {
+		.key	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5"
+			  "\x70\xd5\x3c\x65\x93\xa8\x00\xa0"
+			  "\x46\xe4\x25\x7c\x58\x08\xdb\x1e",
+		.klen	= 32,
+		.iv	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66"
+			  "\x3b\x86\xbf\x86\xd4\x50\xe0\xa7"
+			  "\x76\xef\x5c\x72\x0f\x1f\xc3\xd4",
+		.assoc	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05",
+		.alen	= 17,
+		.input	= "\x9c\xe0\x06\x7b\x86\xcf\x2e\xd8"
+			  "\x45\x65\x1b\x72\x9b\xaa\xa3\x1e"
+			  "\x87\x9d\x26\xdf\xff\x81\x11\xd2"
+			  "\x47\x41\xb9\x24\xc1\x8a\xa3\x8b"
+			  "\x55",
+		.ilen	= 33,
+		.result	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69"
+			  "\xd0",
+		.rlen	= 17,
+	}, {
+		.key	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb"
+			  "\x9a\x97\x48\xe9\x98\x48\x82\xba"
+			  "\x07\x11\x04\x54\x32\x67\x7b\xf5",
+		.klen	= 32,
+		.iv	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d"
+			  "\x65\x48\xcb\x0a\xda\xf0\x62\xc0"
+			  "\x38\x1d\x3b\x4a\xe9\x7e\x62\xaa",
+		.assoc	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a",
+		.alen	= 31,
+		.input	= "\xa0\xc8\xde\x83\x0d\xc3\x4e\xd5"
+			  "\x69\x7f\x7a\xdd\x8c\x46\xda\xba"
+			  "\x0a\x5c\x0e\x7f\xac\xee\x02\xd2"
+			  "\xe5\x4b\x0a\xba\xb8\xa4\x7b\x66"
+			  "\xde\xae\xdb\xc2\xc0\x0b\xf7\x2b"
+			  "\xdf\xb8\xea\xd8\xa9\x38\xed",
+		.ilen	= 47,
+		.result	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70"
+			  "\xfa\xa9\xd0\x4d\x5c\x40\x23\xcd"
+			  "\x98\x34\xab\x37\x56\xae\x32",
+		.rlen	= 31,
+	}, {
+		.key	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1"
+			  "\xc5\x5a\x53\x6e\x9d\xe8\x04\xd4"
+			  "\xc9\x3f\xe2\x2d\x0c\xc6\x1a\xcb",
+		.klen	= 32,
+		.iv	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73"
+			  "\x8f\x0a\xd6\x8f\xdf\x90\xe4\xda"
+			  "\xf9\x4a\x1a\x23\xc3\xdd\x02\x81",
+		.assoc	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37",
+		.alen	= 32,
+		.input	= "\xd3\x68\x14\x70\x3c\x01\x43\x86"
+			  "\x02\xab\xbe\x75\xaa\xe7\xf5\x53"
+			  "\x5c\x05\xbd\x9b\x19\xbb\x2a\x61"
+			  "\x8f\x69\x05\x75\x8e\xca\x60\x0c"
+			  "\x5b\xa2\x48\x61\x32\x74\x11\x2b"
+			  "\xf6\xcf\x06\x78\x6f\x78\x1a\x4a",
+		.ilen	= 48,
+		.result	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76"
+			  "\x24\x6b\xdc\xd1\x61\xe0\xa5\xe7"
+			  "\x5a\x61\x8a\x0f\x30\x0d\xd1\xec",
+		.rlen	= 32,
+	}, {
+		.key	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7"
+			  "\xef\x1c\x5f\xf2\xa3\x88\x86\xed"
+			  "\x8a\x6d\xc1\x05\xe7\x25\xb9\xa2",
+		.klen	= 32,
+		.iv	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79"
+			  "\xba\xcd\xe2\x13\xe4\x30\x66\xf4"
+			  "\xba\x78\xf9\xfb\x9d\x3c\xa1\x58",
+		.assoc	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d",
+		.alen	= 33,
+		.input	= "\x07\x0a\x35\xb0\x82\x03\x5a\xd2"
+			  "\x15\x3a\x6c\x72\x83\x9b\xb1\x75"
+			  "\xea\xf2\xfc\xff\xc6\xf1\x13\xa4"
+			  "\x1a\x93\x33\x79\x97\x82\x81\xc0"
+			  "\x96\xc2\x00\xab\x39\xae\xa1\x62"
+			  "\x53\xa3\x86\xc9\x07\x8c\xaf\x22"
+			  "\x47\x31\x29\xca\x4a\x95\xf5\xd5"
+			  "\x20\x63\x5a\x54\x80\x2c\x4a\x63"
+			  "\xfb\x18\x73\x31\x4f\x08\x21\x5d"
+			  "\x20\xe9\xc3\x7e\xea\x25\x77\x3a"
+			  "\x65",
+		.ilen	= 81,
+		.result	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c"
+			  "\x4f\x2e\xe8\x55\x66\x80\x27\x00"
+			  "\x1b\x8f\x68\xe7\x0a\x6c\x71\xc3"
+			  "\x21\x78\x55\x9d\x9c\x65\x7b\xcd"
+			  "\x0a\x34\x97\xff\x47\x37\xb0\x2a"
+			  "\x80\x0d\x19\x98\x33\xa9\x7a\xe3"
+			  "\x2e\x4c\xc6\xf3\x8c\x88\x42\x01"
+			  "\xbd",
+		.rlen	= 65,
+	}, {
+		.key	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe"
+			  "\x19\xde\x6b\x76\xa8\x28\x08\x07"
+			  "\x4b\x9a\xa0\xdd\xc1\x84\x58\x79",
+		.klen	= 32,
+		.iv	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f"
+			  "\xe4\x8f\xed\x97\xe9\xd0\xe8\x0d"
+			  "\x7c\xa6\xd8\xd4\x77\x9b\x40\x2e",
+		.assoc	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac\xfa\x58\x7f\xe5\x73\x09\x8c"
+			  "\x1d\x40\x87\x8c\xd9\x75\xc0\x55"
+			  "\xa2\xda\x07\xd1\xc2\xa9\xd1\xbb"
+			  "\x09\x4f\x77\x62\x88\x2d\xf2\x68"
+			  "\x54",
+		.alen	= 65,
+		.input	= "\x33\xc1\xda\xfa\x15\x21\x07\x8e"
+			  "\x93\x68\xea\x64\x7b\x3d\x4b\x6b"
+			  "\x71\x5e\x5e\x6b\x92\xaa\x65\xc2"
+			  "\x7a\x2a\xc1\xa9\x0a\xa1\x24\x81"
+			  "\x26\x3a\x5a\x09\xe8\xce\x73\x72"
+			  "\xde\x7b\x58\x9e\x85\xb9\xa4\x28"
+			  "\xda",
+		.ilen	= 49,
+		.result	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82"
+			  "\x79\xf0\xf3\xd9\x6c\x20\xa9\x1a"
+			  "\xdc\xbc\x47\xc0\xe4\xcb\x10\x99"
+			  "\x2f",
+		.rlen	= 33,
+	}, {
+		.key	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04"
+			  "\x44\xa1\x76\xfb\xad\xc8\x8a\x21"
+			  "\x0d\xc8\x7f\xb6\x9b\xe3\xf8\x4f",
+		.klen	= 32,
+		.iv	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85"
+			  "\x0e\x51\xf9\x1c\xee\x70\x6a\x27"
+			  "\x3d\xd3\xb7\xac\x51\xfa\xdf\x05",
+		.assoc	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07",
+		.alen	= 16,
+		.input	= "\x3e\xf8\x86\x3d\x39\xf8\x96\x02"
+			  "\x0f\xdf\xc9\x6e\x37\x1e\x57\x99"
+			  "\x07\x2a\x1a\xac\xd1\xda\xfd\x3b"
+			  "\xc7\xff\xbd\xbc\x85\x09\x0b",
+		.ilen	= 31,
+		.result	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.rlen	= 16,
+	}, {
+		.key	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a"
+			  "\x6e\x63\x82\x7f\xb2\x68\x0c\x3a"
+			  "\xce\xf5\x5e\x8e\x75\x42\x97\x26",
+		.klen	= 32,
+		.iv	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c"
+			  "\x39\x14\x05\xa0\xf3\x10\xec\x41"
+			  "\xff\x01\x95\x84\x2b\x59\x7f\xdb",
+		.assoc	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d",
+		.alen	= 16,
+		.input	= "\x2f\xc4\xd8\x0d\xa6\x07\xef\x2e"
+			  "\x6c\xd9\x84\x63\x70\x97\x61\x37"
+			  "\x08\x2f\x16\x90\x9e\x62\x30\x0d"
+			  "\x62\xd5\xc8\xf0\x46\x1a",
+		.ilen	= 30,
+		.result	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.rlen	= 16,
+	}, {
+		.key	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10"
+			  "\x98\x25\x8d\x03\xb7\x08\x8e\x54"
+			  "\x90\x23\x3d\x67\x4f\xa1\x36\xfc",
+		.klen	= 32,
+		.iv	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92"
+			  "\x63\xd6\x10\x24\xf8\xb0\x6e\x5a"
+			  "\xc0\x2e\x74\x5d\x06\xb8\x1e\xb2",
+		.assoc	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13",
+		.alen	= 16,
+		.input	= "\xce\xf3\x17\x87\x49\xc2\x00\x46"
+			  "\xc6\x12\x5c\x8f\x81\x38\xaa\x55"
+			  "\xf8\x67\x75\xf1\x75\xe3\x2a\x24",
+		.ilen	= 24,
+		.result	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.rlen	= 16,
+	},
+};
+
+/*
+ * MORUS-640 test vectors - generated via reference implementation from
+ * SUPERCOP (https://bench.cr.yp.to/supercop.html):
+ *
+ *   https://bench.cr.yp.to/supercop/supercop-20170228.tar.xz
+ *   (see crypto_aead/morus640128v2/)
+ */
+static const struct aead_testvec morus640_enc_tv_template[] = {
+	{
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 16,
+		.iv	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x89\x62\x7d\xf3\x07\x9d\x52\x05"
+			  "\x53\xc3\x04\x60\x93\xb4\x37\x9a",
+		.rlen	= 16,
+	}, {
+		.key	= "\x3c\x24\x39\x9f\x10\x7b\xa8\x1b"
+			  "\x80\xda\xb2\x91\xf9\x24\xc2\x06",
+		.klen	= 16,
+		.iv	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x69",
+		.ilen	= 1,
+		.result	= "\xa8\x8d\xe4\x90\xb5\x50\x8f\x78"
+			  "\xb6\x10\x9a\x59\x5f\x61\x37\x70"
+			  "\x09",
+		.rlen	= 17,
+	}, {
+		.key	= "\x79\x49\x73\x3e\x20\xf7\x51\x37"
+			  "\x01\xb4\x64\x22\xf3\x48\x85\x0c",
+		.klen	= 16,
+		.iv	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xa6\xa4\x1e\x76\xec\xd4\x50\xcc"
+			  "\x62\x58\xe9\x8f\xef\xa4\x17",
+		.ilen	= 15,
+		.result	= "\x76\xdd\xb9\x05\x3d\xce\x61\x38"
+			  "\xf3\xef\xf7\xe5\xd7\xfd\x70\xa5"
+			  "\xcf\x9d\x64\xb8\x0a\x9f\xfd\x8b"
+			  "\xd4\x6e\xfe\xd9\xc8\x63\x4b",
+		.rlen	= 31,
+	}, {
+		.key	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47\x12",
+		.klen	= 16,
+		.iv	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xe2\xc9\x58\x15\xfc\x4f\xf8\xe8"
+			  "\xe3\x32\x9b\x21\xe9\xc8\xd9\x97",
+		.ilen	= 16,
+		.result	= "\xdc\x72\xe8\x14\xfb\x63\xad\x72"
+			  "\x1f\x57\x9a\x1f\x88\x81\xdb\xd6"
+			  "\xc1\x91\x9d\xb9\x25\xc4\x99\x4c"
+			  "\x97\xcd\x8a\x0c\x9d\x68\x00\x1c",
+		.rlen	= 32,
+	}, {
+		.key	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.klen	= 16,
+		.iv	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x1f\xee\x92\xb4\x0c\xcb\xa1\x04"
+			  "\x64\x0c\x4d\xb2\xe3\xec\x9c\x9d"
+			  "\x09",
+		.ilen	= 17,
+		.result	= "\x6b\x4f\x3b\x90\x9a\xa2\xb3\x82"
+			  "\x0a\xb8\x55\xee\xeb\x73\x4d\x7f"
+			  "\x54\x11\x3a\x8a\x31\xa3\xb5\xf2"
+			  "\xcd\x49\xdb\xf3\xee\x26\xbd\xa2"
+			  "\x0d",
+		.rlen	= 33,
+	}, {
+		.key	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f",
+		.klen	= 16,
+		.iv	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x5c\x13\xcb\x54\x1c\x47\x4a\x1f"
+			  "\xe5\xe6\xff\x44\xdd\x11\x5f\xa3"
+			  "\x33\xdd\xc2\xf8\xdd\x18\x2b\x93"
+			  "\x57\x05\x01\x1c\x66\x22\xd3",
+		.ilen	= 31,
+		.result	= "\x59\xd1\x0f\x6b\xee\x27\x84\x92"
+			  "\xb7\xa9\xb5\xdd\x02\xa4\x12\xa5"
+			  "\x50\x32\xb4\x9a\x2e\x35\x83\x55"
+			  "\x36\x12\x12\xed\xa3\x31\xc5\x30"
+			  "\xa7\xe2\x4a\x6d\x05\x59\x43\x91"
+			  "\x75\xfa\x6c\x17\xc6\x73\xca",
+		.rlen	= 47,
+	}, {
+		.key	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25",
+		.klen	= 16,
+		.iv	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x98\x37\x05\xf3\x2c\xc2\xf3\x3b"
+			  "\x66\xc0\xb1\xd5\xd7\x35\x21\xaa"
+			  "\x5d\x9f\xce\x7c\xe2\xb8\xad\xad"
+			  "\x19\x33\xe0\xf4\x40\x81\x72\x28",
+		.ilen	= 32,
+		.result	= "\xdb\x49\x68\x0f\x91\x5b\x21\xb1"
+			  "\xcf\x50\xb2\x4c\x32\xe1\xa6\x69"
+			  "\xc0\xfb\x44\x1f\xa0\x9a\xeb\x39"
+			  "\x1b\xde\x68\x38\xcc\x27\x52\xc5"
+			  "\xf6\x3e\x74\xea\x66\x5b\x5f\x0c"
+			  "\x65\x9e\x58\xe6\x52\xa2\xfe\x59",
+		.rlen	= 48,
+	}, {
+		.key	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b",
+		.klen	= 16,
+		.iv	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad",
+		.assoc	= "\xc5",
+		.alen	= 1,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x56\xe7\x24\x52\xdd\x95\x60\x5b"
+			  "\x09\x48\x39\x69\x9c\xb3\x62\x46",
+		.rlen	= 16,
+	}, {
+		.key	= "\xe4\x25\xcd\xfa\x80\xdd\x46\xde"
+			  "\x07\xd1\x90\x8b\xcf\x23\x15\x31",
+		.klen	= 16,
+		.iv	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3",
+		.assoc	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76",
+		.alen	= 15,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xdd\xfa\x6c\x1f\x5d\x86\x87\x01"
+			  "\x13\xe5\x73\x46\x46\xf2\x5c\xe1",
+		.rlen	= 16,
+	}, {
+		.key	= "\x20\x4a\x07\x99\x91\x58\xee\xfa"
+			  "\x88\xab\x42\x1c\xc9\x47\xd7\x38",
+		.klen	= 16,
+		.iv	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9",
+		.assoc	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b",
+		.alen	= 16,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xa6\x1b\xb9\xd7\x5e\x3c\xcf\xac"
+			  "\xa9\x21\x45\x0b\x16\x52\xf7\xe1",
+		.rlen	= 16,
+	}, {
+		.key	= "\x5d\x6f\x41\x39\xa1\xd4\x97\x16"
+			  "\x09\x85\xf4\xae\xc3\x6b\x9a\x3e",
+		.klen	= 16,
+		.iv	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf",
+		.assoc	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41"
+			  "\x3c",
+		.alen	= 17,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x15\xff\xde\x3b\x34\xfc\xf6\xf9"
+			  "\xbb\xa8\x62\xad\x0a\xf5\x48\x60",
+		.rlen	= 16,
+	}, {
+		.key	= "\x99\x93\x7a\xd8\xb1\x50\x40\x31"
+			  "\x8a\x60\xa6\x3f\xbd\x90\x5d\x44",
+		.klen	= 16,
+		.iv	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6",
+		.assoc	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47"
+			  "\x67\xba\x85\xf1\xbb\x30\x56\x26"
+			  "\xaf\x0b\x02\x38\xcc\x44\xa7",
+		.alen	= 31,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xd2\x9d\xf8\x3b\xd7\x84\xe9\x2d"
+			  "\x4b\xef\x75\x16\x0a\x99\xae\x6b",
+		.rlen	= 16,
+	}, {
+		.key	= "\xd6\xb8\xb4\x77\xc1\xcb\xe9\x4d"
+			  "\x0a\x3a\x58\xd1\xb7\xb4\x1f\x4a",
+		.klen	= 16,
+		.iv	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc",
+		.assoc	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d"
+			  "\x91\x7c\x91\x75\xc0\xd0\xd8\x40"
+			  "\x71\x39\xe1\x10\xa6\xa3\x46\x7a",
+		.alen	= 32,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xe4\x8d\xa7\xa7\x45\xc1\x31\x4f"
+			  "\xce\xfb\xaf\xd6\xc2\xe6\xee\xc0",
+		.rlen	= 16,
+	}, {
+		.key	= "\x12\xdd\xee\x17\xd1\x47\x92\x69"
+			  "\x8b\x14\x0a\x62\xb1\xd9\xe2\x50",
+		.klen	= 16,
+		.iv	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2",
+		.assoc	= "\x31",
+		.alen	= 1,
+		.input	= "\x40",
+		.ilen	= 1,
+		.result	= "\xe2\x67\x38\x4f\xb9\xad\x7d\x38"
+			  "\x01\xfe\x84\x14\x85\xf8\xd1\xe3"
+			  "\x22",
+		.rlen	= 17,
+	}, {
+		.key	= "\x4f\x01\x27\xb6\xe1\xc3\x3a\x85"
+			  "\x0c\xee\xbc\xf4\xab\xfd\xa5\x57",
+		.klen	= 16,
+		.iv	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8",
+		.assoc	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06",
+		.alen	= 15,
+		.input	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37",
+		.ilen	= 15,
+		.result	= "\x77\x32\x61\xeb\xb4\x33\x29\x92"
+			  "\x29\x95\xc5\x8e\x85\x76\xab\xfc"
+			  "\x07\x95\xa7\x44\x74\xf7\x22\xff"
+			  "\xd8\xd8\x36\x3d\x8a\x7f\x9e",
+		.rlen	= 31,
+	}, {
+		.key	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67\x5d",
+		.klen	= 16,
+		.iv	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf",
+		.assoc	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60",
+		.alen	= 16,
+		.input	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2",
+		.ilen	= 16,
+		.result	= "\xd8\xfd\x44\x45\xf6\x42\x12\x38"
+			  "\xf2\x0b\xea\x4f\x9e\x11\x61\x07"
+			  "\x48\x67\x98\x18\x9b\xd0\x0c\x59"
+			  "\x67\xa4\x11\xb3\x2b\xd6\xc1\x70",
+		.rlen	= 32,
+	}, {
+		.key	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.klen	= 16,
+		.iv	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5",
+		.assoc	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66"
+			  "\x3b",
+		.alen	= 17,
+		.input	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05",
+		.ilen	= 17,
+		.result	= "\xb1\xab\x53\x4e\xc7\x40\x16\xb6"
+			  "\x71\x3a\x00\x9f\x41\x88\xb0\xb2"
+			  "\x71\x83\x85\x5f\xc8\x79\x0a\x99"
+			  "\x99\xdc\x89\x1c\x88\xd2\x3e\xf9"
+			  "\x83",
+		.rlen	= 33,
+	}, {
+		.key	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69",
+		.klen	= 16,
+		.iv	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb",
+		.assoc	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d"
+			  "\x65\x48\xcb\x0a\xda\xf0\x62\xc0"
+			  "\x38\x1d\x3b\x4a\xe9\x7e\x62",
+		.alen	= 31,
+		.input	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a",
+		.ilen	= 31,
+		.result	= "\x29\xc4\xf0\x03\xc1\x86\xdf\x06"
+			  "\x5c\x7b\xef\x64\x87\x00\xd1\x37"
+			  "\xa7\x08\xbc\x7f\x8f\x41\x54\xd0"
+			  "\x3e\xf1\xc3\xa2\x96\x84\xdd\x2a"
+			  "\x2d\x21\x30\xf9\x02\xdb\x06\x0c"
+			  "\xf1\x5a\x66\x69\xe0\xca\x83",
+		.rlen	= 47,
+	}, {
+		.key	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70",
+		.klen	= 16,
+		.iv	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1",
+		.assoc	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73"
+			  "\x8f\x0a\xd6\x8f\xdf\x90\xe4\xda"
+			  "\xf9\x4a\x1a\x23\xc3\xdd\x02\x81",
+		.alen	= 32,
+		.input	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37",
+		.ilen	= 32,
+		.result	= "\xe2\x2e\x44\xdf\xd3\x60\x6d\xb2"
+			  "\x70\x57\x37\xc5\xc2\x4f\x8d\x14"
+			  "\xc6\xbf\x8b\xec\xf5\x62\x67\xf2"
+			  "\x2f\xa1\xe6\xd6\xa7\xb1\x8c\x54"
+			  "\xe5\x6b\x49\xf9\x6e\x90\xc3\xaa"
+			  "\x7a\x00\x2e\x4d\x7f\x31\x2e\x81",
+		.rlen	= 48,
+	}, {
+		.key	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76",
+		.klen	= 16,
+		.iv	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7",
+		.assoc	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79"
+			  "\xba\xcd\xe2\x13\xe4\x30\x66\xf4"
+			  "\xba\x78\xf9\xfb\x9d\x3c\xa1\x58"
+			  "\x1a",
+		.alen	= 33,
+		.input	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d\x4d\x54\x51\x84\x61\xf6\x8e"
+			  "\x03\x31\xf2\x25\x16\xcc\xaa\xc6"
+			  "\x75\x73\x20\x30\x59\x54\xb2\xf0"
+			  "\x3a\x4b\xe0\x23\x8e\xa6\x08\x35"
+			  "\x8a",
+		.ilen	= 65,
+		.result	= "\xc7\xca\x26\x61\x57\xee\xa2\xb9"
+			  "\xb1\x37\xde\x95\x06\x90\x11\x08"
+			  "\x4d\x30\x9f\x24\xc0\x56\xb7\xe1"
+			  "\x0b\x9f\xd2\x57\xe9\xd2\xb1\x76"
+			  "\x56\x9a\xb4\x58\xc5\x08\xfc\xb5"
+			  "\xf2\x31\x9b\xc9\xcd\xb3\x64\xdb"
+			  "\x6f\x50\xbf\xf4\x73\x9d\xfb\x6b"
+			  "\xef\x35\x25\x48\xed\xcf\x29\xa8"
+			  "\xac\xc3\xb9\xcb\x61\x8f\x73\x92"
+			  "\x2c\x7a\x6f\xda\xf9\x09\x6f\xe1"
+			  "\xc4",
+		.rlen	= 81,
+	}, {
+		.key	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c",
+		.klen	= 16,
+		.iv	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe",
+		.assoc	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f"
+			  "\xe4\x8f\xed\x97\xe9\xd0\xe8\x0d"
+			  "\x7c\xa6\xd8\xd4\x77\x9b\x40\x2e"
+			  "\x28\xce\x57\x34\xcd\x6e\x84\x4c"
+			  "\x17\x3c\xe1\xb2\xa8\x0b\xbb\xf1"
+			  "\x96\x41\x0d\x69\xe8\x54\x0a\xc8"
+			  "\x15\x4e\x91\x92\x89\x4b\xb7\x9b"
+			  "\x21",
+		.alen	= 65,
+		.input	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac",
+		.ilen	= 33,
+		.result	= "\x57\xcd\x3d\x46\xc5\xf9\x68\x3b"
+			  "\x2c\x0f\xb4\x7e\x7b\x64\x3e\x40"
+			  "\xf3\x78\x63\x34\x89\x79\x39\x6b"
+			  "\x61\x64\x4a\x9a\xfa\x70\xa4\xd3"
+			  "\x54\x0b\xea\x05\xa6\x95\x64\xed"
+			  "\x3d\x69\xa2\x0c\x27\x56\x2f\x34"
+			  "\x66",
+		.rlen	= 49,
+	}, {
+		.key	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82",
+		.klen	= 16,
+		.iv	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04",
+		.assoc	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85",
+		.alen	= 16,
+		.input	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07",
+		.ilen	= 16,
+		.result	= "\xfc\x85\x06\x28\x8f\xe8\x23\x1f"
+			  "\x33\x98\x87\xde\x08\xb6\xb6\xae"
+			  "\x3e\xa4\xf8\x19\xf1\x92\x60\x39"
+			  "\xb9\x6b\x3f\xdf\xc8\xcb\x30",
+		.rlen	= 31,
+	}, {
+		.key	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.klen	= 16,
+		.iv	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a",
+		.assoc	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c",
+		.alen	= 16,
+		.input	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d",
+		.ilen	= 16,
+		.result	= "\x74\x7d\x70\x07\xe9\xba\x01\xee"
+			  "\x6c\xc6\x6f\x50\x25\x33\xbe\x50"
+			  "\x17\xb8\x17\x62\xed\x80\xa2\xf5"
+			  "\x03\xde\x85\x71\x5d\x34",
+		.rlen	= 30,
+	}, {
+		.key	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.klen	= 16,
+		.iv	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10",
+		.assoc	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92",
+		.alen	= 16,
+		.input	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13",
+		.ilen	= 16,
+		.result	= "\xf4\xb3\x85\xf9\xac\xde\xb1\x38"
+			  "\x29\xfd\x6c\x7c\x49\xe5\x1d\xaf"
+			  "\xba\xea\xd4\xfa\x3f\x11\x33\x98",
+		.rlen	= 24,
+	}, {
+		.key	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.klen	= 16,
+		.iv	= "\xbb\x3a\xf7\x57\xc6\x36\x7c\x22"
+			  "\x36\xab\xde\xc6\x6d\x32\x70\x17",
+		.assoc	= "\xcb\x03\x85\xbf\x0a\xd5\x26\xa9"
+			  "\x56\xe1\x0a\xeb\x6c\xfb\xa1\x98",
+		.alen	= 16,
+		.input	= "\xda\xcc\x14\x27\x4e\x74\xd1\x30"
+			  "\x76\x18\x37\x0f\x6a\xc4\xd1\x1a",
+		.ilen	= 16,
+		.result	= "\xe6\x5c\x49\x4f\x78\xf3\x62\x86"
+			  "\xe1\xb7\xa5\xc3\x32\x88\x3c\x8c"
+			  "\x6e",
+		.rlen	= 17,
+	},
+};
+
+static const struct aead_testvec morus640_dec_tv_template[] = {
+	{
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 16,
+		.iv	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x89\x62\x7d\xf3\x07\x9d\x52\x05"
+			  "\x53\xc3\x04\x60\x93\xb4\x37\x9a",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x3c\x24\x39\x9f\x10\x7b\xa8\x1b"
+			  "\x80\xda\xb2\x91\xf9\x24\xc2\x06",
+		.klen	= 16,
+		.iv	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xa8\x8d\xe4\x90\xb5\x50\x8f\x78"
+			  "\xb6\x10\x9a\x59\x5f\x61\x37\x70"
+			  "\x09",
+		.ilen	= 17,
+		.result	= "\x69",
+		.rlen	= 1,
+	}, {
+		.key	= "\x79\x49\x73\x3e\x20\xf7\x51\x37"
+			  "\x01\xb4\x64\x22\xf3\x48\x85\x0c",
+		.klen	= 16,
+		.iv	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x76\xdd\xb9\x05\x3d\xce\x61\x38"
+			  "\xf3\xef\xf7\xe5\xd7\xfd\x70\xa5"
+			  "\xcf\x9d\x64\xb8\x0a\x9f\xfd\x8b"
+			  "\xd4\x6e\xfe\xd9\xc8\x63\x4b",
+		.ilen	= 31,
+		.result	= "\xa6\xa4\x1e\x76\xec\xd4\x50\xcc"
+			  "\x62\x58\xe9\x8f\xef\xa4\x17",
+		.rlen	= 15,
+	}, {
+		.key	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47\x12",
+		.klen	= 16,
+		.iv	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xdc\x72\xe8\x14\xfb\x63\xad\x72"
+			  "\x1f\x57\x9a\x1f\x88\x81\xdb\xd6"
+			  "\xc1\x91\x9d\xb9\x25\xc4\x99\x4c"
+			  "\x97\xcd\x8a\x0c\x9d\x68\x00\x1c",
+		.ilen	= 32,
+		.result	= "\xe2\xc9\x58\x15\xfc\x4f\xf8\xe8"
+			  "\xe3\x32\x9b\x21\xe9\xc8\xd9\x97",
+		.rlen	= 16,
+	}, {
+		.key	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.klen	= 16,
+		.iv	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x6b\x4f\x3b\x90\x9a\xa2\xb3\x82"
+			  "\x0a\xb8\x55\xee\xeb\x73\x4d\x7f"
+			  "\x54\x11\x3a\x8a\x31\xa3\xb5\xf2"
+			  "\xcd\x49\xdb\xf3\xee\x26\xbd\xa2"
+			  "\x0d",
+		.ilen	= 33,
+		.result	= "\x1f\xee\x92\xb4\x0c\xcb\xa1\x04"
+			  "\x64\x0c\x4d\xb2\xe3\xec\x9c\x9d"
+			  "\x09",
+		.rlen	= 17,
+	}, {
+		.key	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f",
+		.klen	= 16,
+		.iv	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x59\xd1\x0f\x6b\xee\x27\x84\x92"
+			  "\xb7\xa9\xb5\xdd\x02\xa4\x12\xa5"
+			  "\x50\x32\xb4\x9a\x2e\x35\x83\x55"
+			  "\x36\x12\x12\xed\xa3\x31\xc5\x30"
+			  "\xa7\xe2\x4a\x6d\x05\x59\x43\x91"
+			  "\x75\xfa\x6c\x17\xc6\x73\xca",
+		.ilen	= 47,
+		.result	= "\x5c\x13\xcb\x54\x1c\x47\x4a\x1f"
+			  "\xe5\xe6\xff\x44\xdd\x11\x5f\xa3"
+			  "\x33\xdd\xc2\xf8\xdd\x18\x2b\x93"
+			  "\x57\x05\x01\x1c\x66\x22\xd3",
+		.rlen	= 31,
+	}, {
+		.key	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25",
+		.klen	= 16,
+		.iv	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xdb\x49\x68\x0f\x91\x5b\x21\xb1"
+			  "\xcf\x50\xb2\x4c\x32\xe1\xa6\x69"
+			  "\xc0\xfb\x44\x1f\xa0\x9a\xeb\x39"
+			  "\x1b\xde\x68\x38\xcc\x27\x52\xc5"
+			  "\xf6\x3e\x74\xea\x66\x5b\x5f\x0c"
+			  "\x65\x9e\x58\xe6\x52\xa2\xfe\x59",
+		.ilen	= 48,
+		.result	= "\x98\x37\x05\xf3\x2c\xc2\xf3\x3b"
+			  "\x66\xc0\xb1\xd5\xd7\x35\x21\xaa"
+			  "\x5d\x9f\xce\x7c\xe2\xb8\xad\xad"
+			  "\x19\x33\xe0\xf4\x40\x81\x72\x28",
+		.rlen	= 32,
+	}, {
+		.key	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b",
+		.klen	= 16,
+		.iv	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad",
+		.assoc	= "\xc5",
+		.alen	= 1,
+		.input	= "\x56\xe7\x24\x52\xdd\x95\x60\x5b"
+			  "\x09\x48\x39\x69\x9c\xb3\x62\x46",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xe4\x25\xcd\xfa\x80\xdd\x46\xde"
+			  "\x07\xd1\x90\x8b\xcf\x23\x15\x31",
+		.klen	= 16,
+		.iv	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3",
+		.assoc	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76",
+		.alen	= 15,
+		.input	= "\xdd\xfa\x6c\x1f\x5d\x86\x87\x01"
+			  "\x13\xe5\x73\x46\x46\xf2\x5c\xe1",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x20\x4a\x07\x99\x91\x58\xee\xfa"
+			  "\x88\xab\x42\x1c\xc9\x47\xd7\x38",
+		.klen	= 16,
+		.iv	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9",
+		.assoc	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b",
+		.alen	= 16,
+		.input	= "\xa6\x1b\xb9\xd7\x5e\x3c\xcf\xac"
+			  "\xa9\x21\x45\x0b\x16\x52\xf7\xe1",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x5d\x6f\x41\x39\xa1\xd4\x97\x16"
+			  "\x09\x85\xf4\xae\xc3\x6b\x9a\x3e",
+		.klen	= 16,
+		.iv	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf",
+		.assoc	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41"
+			  "\x3c",
+		.alen	= 17,
+		.input	= "\x15\xff\xde\x3b\x34\xfc\xf6\xf9"
+			  "\xbb\xa8\x62\xad\x0a\xf5\x48\x60",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x99\x93\x7a\xd8\xb1\x50\x40\x31"
+			  "\x8a\x60\xa6\x3f\xbd\x90\x5d\x44",
+		.klen	= 16,
+		.iv	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6",
+		.assoc	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47"
+			  "\x67\xba\x85\xf1\xbb\x30\x56\x26"
+			  "\xaf\x0b\x02\x38\xcc\x44\xa7",
+		.alen	= 31,
+		.input	= "\xd2\x9d\xf8\x3b\xd7\x84\xe9\x2d"
+			  "\x4b\xef\x75\x16\x0a\x99\xae\x6b",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xd6\xb8\xb4\x77\xc1\xcb\xe9\x4d"
+			  "\x0a\x3a\x58\xd1\xb7\xb4\x1f\x4a",
+		.klen	= 16,
+		.iv	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc",
+		.assoc	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d"
+			  "\x91\x7c\x91\x75\xc0\xd0\xd8\x40"
+			  "\x71\x39\xe1\x10\xa6\xa3\x46\x7a",
+		.alen	= 32,
+		.input	= "\xe4\x8d\xa7\xa7\x45\xc1\x31\x4f"
+			  "\xce\xfb\xaf\xd6\xc2\xe6\xee\xc0",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x12\xdd\xee\x17\xd1\x47\x92\x69"
+			  "\x8b\x14\x0a\x62\xb1\xd9\xe2\x50",
+		.klen	= 16,
+		.iv	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2",
+		.assoc	= "\x31",
+		.alen	= 1,
+		.input	= "\xe2\x67\x38\x4f\xb9\xad\x7d\x38"
+			  "\x01\xfe\x84\x14\x85\xf8\xd1\xe3"
+			  "\x22",
+		.ilen	= 17,
+		.result	= "\x40",
+		.rlen	= 1,
+	}, {
+		.key	= "\x4f\x01\x27\xb6\xe1\xc3\x3a\x85"
+			  "\x0c\xee\xbc\xf4\xab\xfd\xa5\x57",
+		.klen	= 16,
+		.iv	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8",
+		.assoc	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06",
+		.alen	= 15,
+		.input	= "\x77\x32\x61\xeb\xb4\x33\x29\x92"
+			  "\x29\x95\xc5\x8e\x85\x76\xab\xfc"
+			  "\x07\x95\xa7\x44\x74\xf7\x22\xff"
+			  "\xd8\xd8\x36\x3d\x8a\x7f\x9e",
+		.ilen	= 31,
+		.result	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37",
+		.rlen	= 15,
+	}, {
+		.key	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67\x5d",
+		.klen	= 16,
+		.iv	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf",
+		.assoc	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60",
+		.alen	= 16,
+		.input	= "\xd8\xfd\x44\x45\xf6\x42\x12\x38"
+			  "\xf2\x0b\xea\x4f\x9e\x11\x61\x07"
+			  "\x48\x67\x98\x18\x9b\xd0\x0c\x59"
+			  "\x67\xa4\x11\xb3\x2b\xd6\xc1\x70",
+		.ilen	= 32,
+		.result	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2",
+		.rlen	= 16,
+	}, {
+		.key	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.klen	= 16,
+		.iv	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5",
+		.assoc	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66"
+			  "\x3b",
+		.alen	= 17,
+		.input	= "\xb1\xab\x53\x4e\xc7\x40\x16\xb6"
+			  "\x71\x3a\x00\x9f\x41\x88\xb0\xb2"
+			  "\x71\x83\x85\x5f\xc8\x79\x0a\x99"
+			  "\x99\xdc\x89\x1c\x88\xd2\x3e\xf9"
+			  "\x83",
+		.ilen	= 33,
+		.result	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05",
+		.rlen	= 17,
+	}, {
+		.key	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69",
+		.klen	= 16,
+		.iv	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb",
+		.assoc	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d"
+			  "\x65\x48\xcb\x0a\xda\xf0\x62\xc0"
+			  "\x38\x1d\x3b\x4a\xe9\x7e\x62",
+		.alen	= 31,
+		.input	= "\x29\xc4\xf0\x03\xc1\x86\xdf\x06"
+			  "\x5c\x7b\xef\x64\x87\x00\xd1\x37"
+			  "\xa7\x08\xbc\x7f\x8f\x41\x54\xd0"
+			  "\x3e\xf1\xc3\xa2\x96\x84\xdd\x2a"
+			  "\x2d\x21\x30\xf9\x02\xdb\x06\x0c"
+			  "\xf1\x5a\x66\x69\xe0\xca\x83",
+		.ilen	= 47,
+		.result	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a",
+		.rlen	= 31,
+	}, {
+		.key	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70",
+		.klen	= 16,
+		.iv	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1",
+		.assoc	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73"
+			  "\x8f\x0a\xd6\x8f\xdf\x90\xe4\xda"
+			  "\xf9\x4a\x1a\x23\xc3\xdd\x02\x81",
+		.alen	= 32,
+		.input	= "\xe2\x2e\x44\xdf\xd3\x60\x6d\xb2"
+			  "\x70\x57\x37\xc5\xc2\x4f\x8d\x14"
+			  "\xc6\xbf\x8b\xec\xf5\x62\x67\xf2"
+			  "\x2f\xa1\xe6\xd6\xa7\xb1\x8c\x54"
+			  "\xe5\x6b\x49\xf9\x6e\x90\xc3\xaa"
+			  "\x7a\x00\x2e\x4d\x7f\x31\x2e\x81",
+		.ilen	= 48,
+		.result	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37",
+		.rlen	= 32,
+	}, {
+		.key	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76",
+		.klen	= 16,
+		.iv	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7",
+		.assoc	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79"
+			  "\xba\xcd\xe2\x13\xe4\x30\x66\xf4"
+			  "\xba\x78\xf9\xfb\x9d\x3c\xa1\x58"
+			  "\x1a",
+		.alen	= 33,
+		.input	= "\xc7\xca\x26\x61\x57\xee\xa2\xb9"
+			  "\xb1\x37\xde\x95\x06\x90\x11\x08"
+			  "\x4d\x30\x9f\x24\xc0\x56\xb7\xe1"
+			  "\x0b\x9f\xd2\x57\xe9\xd2\xb1\x76"
+			  "\x56\x9a\xb4\x58\xc5\x08\xfc\xb5"
+			  "\xf2\x31\x9b\xc9\xcd\xb3\x64\xdb"
+			  "\x6f\x50\xbf\xf4\x73\x9d\xfb\x6b"
+			  "\xef\x35\x25\x48\xed\xcf\x29\xa8"
+			  "\xac\xc3\xb9\xcb\x61\x8f\x73\x92"
+			  "\x2c\x7a\x6f\xda\xf9\x09\x6f\xe1"
+			  "\xc4",
+		.ilen	= 81,
+		.result	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d\x4d\x54\x51\x84\x61\xf6\x8e"
+			  "\x03\x31\xf2\x25\x16\xcc\xaa\xc6"
+			  "\x75\x73\x20\x30\x59\x54\xb2\xf0"
+			  "\x3a\x4b\xe0\x23\x8e\xa6\x08\x35"
+			  "\x8a",
+		.rlen	= 65,
+	}, {
+		.key	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c",
+		.klen	= 16,
+		.iv	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe",
+		.assoc	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f"
+			  "\xe4\x8f\xed\x97\xe9\xd0\xe8\x0d"
+			  "\x7c\xa6\xd8\xd4\x77\x9b\x40\x2e"
+			  "\x28\xce\x57\x34\xcd\x6e\x84\x4c"
+			  "\x17\x3c\xe1\xb2\xa8\x0b\xbb\xf1"
+			  "\x96\x41\x0d\x69\xe8\x54\x0a\xc8"
+			  "\x15\x4e\x91\x92\x89\x4b\xb7\x9b"
+			  "\x21",
+		.alen	= 65,
+		.input	= "\x57\xcd\x3d\x46\xc5\xf9\x68\x3b"
+			  "\x2c\x0f\xb4\x7e\x7b\x64\x3e\x40"
+			  "\xf3\x78\x63\x34\x89\x79\x39\x6b"
+			  "\x61\x64\x4a\x9a\xfa\x70\xa4\xd3"
+			  "\x54\x0b\xea\x05\xa6\x95\x64\xed"
+			  "\x3d\x69\xa2\x0c\x27\x56\x2f\x34"
+			  "\x66",
+		.ilen	= 49,
+		.result	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac",
+		.rlen	= 33,
+	}, {
+		.key	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82",
+		.klen	= 16,
+		.iv	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04",
+		.assoc	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85",
+		.alen	= 16,
+		.input	= "\xfc\x85\x06\x28\x8f\xe8\x23\x1f"
+			  "\x33\x98\x87\xde\x08\xb6\xb6\xae"
+			  "\x3e\xa4\xf8\x19\xf1\x92\x60\x39"
+			  "\xb9\x6b\x3f\xdf\xc8\xcb\x30",
+		.ilen	= 31,
+		.result	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07",
+		.rlen	= 16,
+	}, {
+		.key	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.klen	= 16,
+		.iv	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a",
+		.assoc	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c",
+		.alen	= 16,
+		.input	= "\x74\x7d\x70\x07\xe9\xba\x01\xee"
+			  "\x6c\xc6\x6f\x50\x25\x33\xbe\x50"
+			  "\x17\xb8\x17\x62\xed\x80\xa2\xf5"
+			  "\x03\xde\x85\x71\x5d\x34",
+		.ilen	= 30,
+		.result	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d",
+		.rlen	= 16,
+	}, {
+		.key	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.klen	= 16,
+		.iv	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10",
+		.assoc	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92",
+		.alen	= 16,
+		.input	= "\xf4\xb3\x85\xf9\xac\xde\xb1\x38"
+			  "\x29\xfd\x6c\x7c\x49\xe5\x1d\xaf"
+			  "\xba\xea\xd4\xfa\x3f\x11\x33\x98",
+		.ilen	= 24,
+		.result	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13",
+		.rlen	= 16,
+	}, {
+		.key	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.klen	= 16,
+		.iv	= "\xbb\x3a\xf7\x57\xc6\x36\x7c\x22"
+			  "\x36\xab\xde\xc6\x6d\x32\x70\x17",
+		.assoc	= "\xcb\x03\x85\xbf\x0a\xd5\x26\xa9"
+			  "\x56\xe1\x0a\xeb\x6c\xfb\xa1\x98",
+		.alen	= 16,
+		.input	= "\xe6\x5c\x49\x4f\x78\xf3\x62\x86"
+			  "\xe1\xb7\xa5\xc3\x32\x88\x3c\x8c"
+			  "\x6e",
+		.ilen	= 17,
+		.result	= "\xda\xcc\x14\x27\x4e\x74\xd1\x30"
+			  "\x76\x18\x37\x0f\x6a\xc4\xd1\x1a",
+		.rlen	= 16,
+	},
+};
+
+/*
+ * MORUS-1280 test vectors - generated via reference implementation from
+ * SUPERCOP (https://bench.cr.yp.to/supercop.html):
+ *
+ *   https://bench.cr.yp.to/supercop/supercop-20170228.tar.xz
+ *   (see crypto_aead/morus1280128v2/ and crypto_aead/morus1280256v2/ )
+ */
+static const struct aead_testvec morus1280_enc_tv_template[] = {
+	{
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 16,
+		.iv	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x91\x85\x0f\xf5\x52\x9e\xce\xce"
+			  "\x65\x99\xc7\xbf\xd3\x76\xe8\x98",
+		.rlen	= 16,
+	}, {
+		.key	= "\x3c\x24\x39\x9f\x10\x7b\xa8\x1b"
+			  "\x80\xda\xb2\x91\xf9\x24\xc2\x06",
+		.klen	= 16,
+		.iv	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x69",
+		.ilen	= 1,
+		.result	= "\x88\xc3\x4c\xf0\x2f\x43\x76\x13"
+			  "\x96\xda\x76\x34\x33\x4e\xd5\x39"
+			  "\x73",
+		.rlen	= 17,
+	}, {
+		.key	= "\x79\x49\x73\x3e\x20\xf7\x51\x37"
+			  "\x01\xb4\x64\x22\xf3\x48\x85\x0c",
+		.klen	= 16,
+		.iv	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xa6\xa4\x1e\x76\xec\xd4\x50\xcc"
+			  "\x62\x58\xe9\x8f\xef\xa4\x17\x91"
+			  "\xb4\x96\x9f\x6b\xce\x38\xa5\x46"
+			  "\x13\x7d\x64\x93\xd7\x05\xf5",
+		.ilen	= 31,
+		.result	= "\x3e\x5c\x3b\x58\x3b\x7d\x2a\x22"
+			  "\x75\x0b\x24\xa6\x0e\xc3\xde\x52"
+			  "\x97\x0b\x64\xd4\xce\x90\x52\xf7"
+			  "\xef\xdb\x6a\x38\xd2\xa8\xa1\x0d"
+			  "\xe0\x61\x33\x24\xc6\x4d\x51\xbc"
+			  "\xa4\x21\x74\xcf\x19\x16\x59",
+		.rlen	= 47,
+	}, {
+		.key	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47\x12",
+		.klen	= 16,
+		.iv	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xe2\xc9\x58\x15\xfc\x4f\xf8\xe8"
+			  "\xe3\x32\x9b\x21\xe9\xc8\xd9\x97"
+			  "\xde\x58\xab\xf0\xd3\xd8\x27\x60"
+			  "\xd5\xaa\x43\x6b\xb1\x64\x95\xa4",
+		.ilen	= 32,
+		.result	= "\x30\x82\x9c\x2b\x67\xcb\xf9\x1f"
+			  "\xde\x9f\x77\xb2\xda\x92\x61\x5c"
+			  "\x09\x0b\x2d\x9a\x26\xaa\x1c\x06"
+			  "\xab\x74\xb7\x2b\x95\x5f\x9f\xa1"
+			  "\x9a\xff\x50\xa0\xa2\xff\xc5\xad"
+			  "\x21\x8e\x84\x5c\x12\x61\xb2\xae",
+		.rlen	= 48,
+	}, {
+		.key	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.klen	= 16,
+		.iv	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x1f\xee\x92\xb4\x0c\xcb\xa1\x04"
+			  "\x64\x0c\x4d\xb2\xe3\xec\x9c\x9d"
+			  "\x09\x1a\xb7\x74\xd8\x78\xa9\x79"
+			  "\x96\xd8\x22\x43\x8c\xc3\x34\x7b"
+			  "\xc4",
+		.ilen	= 33,
+		.result	= "\x67\x5d\x8e\x45\xc8\x39\xf5\x17"
+			  "\xc1\x1d\x2a\xdd\x88\x67\xda\x1f"
+			  "\x6d\xe8\x37\x28\x5a\xc1\x5e\x9f"
+			  "\xa6\xec\xc6\x92\x05\x4b\xc0\xa3"
+			  "\x63\xef\x88\xa4\x9b\x0a\x5c\xed"
+			  "\x2b\x6a\xac\x63\x52\xaa\x10\x94"
+			  "\xd0",
+		.rlen	= 49,
+	}, {
+		.key	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f",
+		.klen	= 16,
+		.iv	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x5c\x13\xcb\x54\x1c\x47\x4a\x1f"
+			  "\xe5\xe6\xff\x44\xdd\x11\x5f\xa3"
+			  "\x33\xdd\xc2\xf8\xdd\x18\x2b\x93"
+			  "\x57\x05\x01\x1c\x66\x22\xd3\x51"
+			  "\xd3\xdf\x18\xc9\x30\x66\xed\xb1"
+			  "\x96\x58\xd5\x8c\x64\x8c\x7c\xf5"
+			  "\x01\xd0\x74\x5f\x9b\xaa\xf6\xd1"
+			  "\xe6\x16\xa2\xac\xde\x47\x40",
+		.ilen	= 63,
+		.result	= "\x7d\x61\x1a\x35\x20\xcc\x07\x88"
+			  "\x03\x98\x87\xcf\xc0\x6e\x4d\x19"
+			  "\xe3\xd4\x0b\xfb\x29\x8f\x49\x1a"
+			  "\x3a\x06\x77\xce\x71\x2c\xcd\xdd"
+			  "\xed\xf6\xc9\xbe\xa6\x3b\xb8\xfc"
+			  "\x6c\xbe\x77\xed\x74\x0e\x20\x85"
+			  "\xd0\x65\xde\x24\x6f\xe3\x25\xc5"
+			  "\xdf\x5b\x0f\xbd\x8a\x88\x78\xc9"
+			  "\xe5\x81\x37\xde\x84\x7a\xf6\x84"
+			  "\x99\x7a\x72\x9c\x54\x31\xa1",
+		.rlen	= 79,
+	}, {
+		.key	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25",
+		.klen	= 16,
+		.iv	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x98\x37\x05\xf3\x2c\xc2\xf3\x3b"
+			  "\x66\xc0\xb1\xd5\xd7\x35\x21\xaa"
+			  "\x5d\x9f\xce\x7c\xe2\xb8\xad\xad"
+			  "\x19\x33\xe0\xf4\x40\x81\x72\x28"
+			  "\xe1\x8b\x1c\xf8\x91\x78\xff\xaf"
+			  "\xb0\x68\x69\xf2\x27\x35\x91\x84"
+			  "\x2e\x37\x5b\x00\x04\xff\x16\x9c"
+			  "\xb5\x19\x39\xeb\xd9\xcd\x29\x9a",
+		.ilen	= 64,
+		.result	= "\x05\xc5\xb1\xf9\x1b\xb9\xab\x2c"
+			  "\xa5\x07\x12\xa7\x12\x39\x60\x66"
+			  "\x30\x81\x4a\x03\x78\x28\x45\x52"
+			  "\xd2\x2b\x24\xfd\x8b\xa5\xb7\x66"
+			  "\x6f\x45\xd7\x3b\x67\x6f\x51\xb9"
+			  "\xc0\x3d\x6c\xca\x1e\xae\xff\xb6"
+			  "\x79\xa9\xe4\x82\x5d\x4c\x2d\xdf"
+			  "\xeb\x71\x40\xc9\x2c\x40\x45\x6d"
+			  "\x73\x77\x01\xf3\x4f\xf3\x9d\x2a"
+			  "\x5d\x57\xa8\xa1\x18\xa2\xad\xcb",
+		.rlen	= 80,
+	}, {
+		.key	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b",
+		.klen	= 16,
+		.iv	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad",
+		.assoc	= "\xc5",
+		.alen	= 1,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x4d\xbf\x11\xac\x7f\x97\x0b\x2e"
+			  "\x89\x3b\x9d\x0f\x83\x1c\x08\xc3",
+		.rlen	= 16,
+	}, {
+		.key	= "\xe4\x25\xcd\xfa\x80\xdd\x46\xde"
+			  "\x07\xd1\x90\x8b\xcf\x23\x15\x31",
+		.klen	= 16,
+		.iv	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3",
+		.assoc	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76\x34"
+			  "\xe8\x73\x62\x64\xab\x50\xd0\xda"
+			  "\x6b\x83\x66\xaf\x3e\x27\xc9",
+		.alen	= 31,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x5b\xc0\x8d\x54\xe4\xec\xbe\x38"
+			  "\x03\x12\xf9\xcc\x9e\x46\x42\x92",
+		.rlen	= 16,
+	}, {
+		.key	= "\x20\x4a\x07\x99\x91\x58\xee\xfa"
+			  "\x88\xab\x42\x1c\xc9\x47\xd7\x38",
+		.klen	= 16,
+		.iv	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9",
+		.assoc	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b"
+			  "\x12\x35\x6e\xe8\xb0\xf0\x52\xf3"
+			  "\x2d\xb0\x45\x87\x18\x86\x68\xf6",
+		.alen	= 32,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x48\xc5\xc3\x4c\x40\x2e\x2f\xc2"
+			  "\x6d\x65\xe0\x67\x9c\x1d\xa0\xf0",
+		.rlen	= 16,
+	}, {
+		.key	= "\x5d\x6f\x41\x39\xa1\xd4\x97\x16"
+			  "\x09\x85\xf4\xae\xc3\x6b\x9a\x3e",
+		.klen	= 16,
+		.iv	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf",
+		.assoc	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41"
+			  "\x3c\xf8\x79\x6c\xb6\x90\xd4\x0d"
+			  "\xee\xde\x23\x60\xf2\xe5\x08\xcc"
+			  "\x97",
+		.alen	= 33,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x28\x64\x78\x51\x55\xd8\x56\x4a"
+			  "\x58\x3e\xf7\xbe\xee\x21\xfe\x94",
+		.rlen	= 16,
+	}, {
+		.key	= "\x99\x93\x7a\xd8\xb1\x50\x40\x31"
+			  "\x8a\x60\xa6\x3f\xbd\x90\x5d\x44",
+		.klen	= 16,
+		.iv	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6",
+		.assoc	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47"
+			  "\x67\xba\x85\xf1\xbb\x30\x56\x26"
+			  "\xaf\x0b\x02\x38\xcc\x44\xa7\xa3"
+			  "\xa6\xbf\x31\x93\x60\xcd\xda\x63"
+			  "\x2c\xb1\xaa\x19\xc8\x19\xf8\xeb"
+			  "\x03\xa1\xe8\xbe\x37\x54\xec\xa2"
+			  "\xcd\x2c\x45\x58\xbd\x8e\x80",
+		.alen	= 63,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xb3\xa6\x00\x4e\x09\x20\xac\x21"
+			  "\x77\x72\x69\x76\x2d\x36\xe5\xc8",
+		.rlen	= 16,
+	}, {
+		.key	= "\xd6\xb8\xb4\x77\xc1\xcb\xe9\x4d"
+			  "\x0a\x3a\x58\xd1\xb7\xb4\x1f\x4a",
+		.klen	= 16,
+		.iv	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc",
+		.assoc	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d"
+			  "\x91\x7c\x91\x75\xc0\xd0\xd8\x40"
+			  "\x71\x39\xe1\x10\xa6\xa3\x46\x7a"
+			  "\xb4\x6b\x35\xc2\xc1\xdf\xed\x60"
+			  "\x46\xc1\x3e\x7f\x8c\xc2\x0e\x7a"
+			  "\x30\x08\xd0\x5f\xa0\xaa\x0c\x6d"
+			  "\x9c\x2f\xdb\x97\xb8\x15\x69\x01",
+		.alen	= 64,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x65\x33\x7b\xa1\x63\xf4\x20\xdd"
+			  "\xe4\xb9\x4a\xaa\x9a\x21\xaa\x14",
+		.rlen	= 16,
+	}, {
+		.key	= "\x12\xdd\xee\x17\xd1\x47\x92\x69"
+			  "\x8b\x14\x0a\x62\xb1\xd9\xe2\x50",
+		.klen	= 16,
+		.iv	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2",
+		.assoc	= "\x31",
+		.alen	= 1,
+		.input	= "\x40",
+		.ilen	= 1,
+		.result	= "\x1d\x47\x17\x34\x86\xf5\x54\x1a"
+			  "\x6d\x28\xb8\x5d\x6c\xcf\xa0\xb9"
+			  "\xbf",
+		.rlen	= 17,
+	}, {
+		.key	= "\x4f\x01\x27\xb6\xe1\xc3\x3a\x85"
+			  "\x0c\xee\xbc\xf4\xab\xfd\xa5\x57",
+		.klen	= 16,
+		.iv	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8",
+		.assoc	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06\x5a"
+			  "\xe6\x01\xa8\x7e\xca\x10\xdc\x73"
+			  "\xf4\x94\x9f\xc1\x5a\x61\x85",
+		.alen	= 31,
+		.input	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37\xdb"
+			  "\xb0\xb2\x2b\x9f\x0b\xb8\xbd\x7a"
+			  "\x24\xa0\xd6\xb7\x11\x79\x6c",
+		.ilen	= 31,
+		.result	= "\x78\x90\x52\xae\x0f\xf7\x2e\xef"
+			  "\x63\x09\x08\x58\xb5\x56\xbd\x72"
+			  "\x6e\x42\xcf\x27\x04\x7c\xdb\x92"
+			  "\x18\xe9\xa4\x33\x90\xba\x62\xb5"
+			  "\x70\xd3\x88\x9b\x4f\x05\xa7\x51"
+			  "\x85\x87\x17\x09\x42\xed\x4e",
+		.rlen	= 47,
+	}, {
+		.key	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67\x5d",
+		.klen	= 16,
+		.iv	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf",
+		.assoc	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60"
+			  "\x10\xc3\xb3\x02\xcf\xb0\x5e\x8d"
+			  "\xb5\xc2\x7e\x9a\x35\xc0\x24\xfd",
+		.alen	= 32,
+		.input	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2"
+			  "\xdb\x74\x36\x23\x11\x58\x3f\x93"
+			  "\xe5\xcd\xb5\x90\xeb\xd8\x0c\xb3",
+		.ilen	= 32,
+		.result	= "\x1d\x2c\x57\xe0\x50\x38\x3d\x41"
+			  "\x2e\x71\xc8\x3b\x92\x43\x58\xaf"
+			  "\x5a\xfb\xad\x8f\xd9\xd5\x8a\x5e"
+			  "\xdb\xf3\xcd\x3a\x2b\xe1\x2c\x1a"
+			  "\xb0\xed\xe3\x0c\x6e\xf9\xf2\xd6"
+			  "\x90\xe6\xb1\x0e\xa5\x8a\xac\xb7",
+		.rlen	= 48,
+	}, {
+		.key	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.klen	= 16,
+		.iv	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5",
+		.assoc	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66"
+			  "\x3b\x86\xbf\x86\xd4\x50\xe0\xa7"
+			  "\x76\xef\x5c\x72\x0f\x1f\xc3\xd4"
+			  "\xee",
+		.alen	= 33,
+		.input	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05\x36\x42\xa7\x16\xf8\xc1\xad"
+			  "\xa7\xfb\x94\x68\xc5\x37\xab\x8a"
+			  "\x72",
+		.ilen	= 33,
+		.result	= "\x59\x10\x84\x1c\x83\x4c\x8b\xfc"
+			  "\xfd\x2e\x4b\x46\x84\xff\x78\x4e"
+			  "\x50\xda\x5c\xb9\x61\x1d\xf5\xb9"
+			  "\xfe\xbb\x7f\xae\x8c\xc1\x24\xbd"
+			  "\x8c\x6f\x1f\x9b\xce\xc6\xc1\x37"
+			  "\x08\x06\x5a\xe5\x96\x10\x95\xc2"
+			  "\x5e",
+		.rlen	= 49,
+	}, {
+		.key	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69",
+		.klen	= 16,
+		.iv	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb",
+		.assoc	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d"
+			  "\x65\x48\xcb\x0a\xda\xf0\x62\xc0"
+			  "\x38\x1d\x3b\x4a\xe9\x7e\x62\xaa"
+			  "\xfd\xc9\x4a\xa9\xa9\x39\x4b\x54"
+			  "\xc8\x0e\x24\x7f\x5e\x10\x7a\x45"
+			  "\x10\x0b\x56\x85\xad\x54\xaa\x66"
+			  "\xa8\x43\xcd\xd4\x9b\xb7\xfa",
+		.alen	= 63,
+		.input	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a\x60"
+			  "\x80\xf4\x4b\xf4\xc1\x3d\xd0\x93"
+			  "\xcf\x12\xc9\x59\x8f\x7a\x7f\xa8"
+			  "\x1b\xa5\x50\xed\x87\xa9\x72\x59"
+			  "\x9c\x44\xb2\xa4\x99\x98\x34",
+		.ilen	= 63,
+		.result	= "\x9a\x12\xbc\xdf\x72\xa8\x56\x22"
+			  "\x49\x2d\x07\x92\xfc\x3d\x6d\x5f"
+			  "\xef\x36\x19\xae\x91\xfa\xd6\x63"
+			  "\x46\xea\x8a\x39\x14\x21\xa6\x37"
+			  "\x18\xfc\x97\x3e\x16\xa5\x4d\x39"
+			  "\x45\x2e\x69\xcc\x9c\x5f\xdf\x6d"
+			  "\x5e\xa2\xbf\xac\x83\x32\x72\x52"
+			  "\x58\x58\x23\x40\xfd\xa5\xc2\xe6"
+			  "\xe9\x5a\x50\x98\x00\x58\xc9\x86"
+			  "\x4f\x20\x37\xdb\x7b\x22\xa3",
+		.rlen	= 79,
+	}, {
+		.key	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70",
+		.klen	= 16,
+		.iv	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1",
+		.assoc	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73"
+			  "\x8f\x0a\xd6\x8f\xdf\x90\xe4\xda"
+			  "\xf9\x4a\x1a\x23\xc3\xdd\x02\x81"
+			  "\x0b\x76\x4f\xd7\x0a\x4b\x5e\x51"
+			  "\xe3\x1d\xb9\xe5\x21\xb9\x8f\xd4"
+			  "\x3d\x72\x3e\x26\x16\xa9\xca\x32"
+			  "\x77\x47\x63\x14\x95\x3d\xe4\x34",
+		.alen	= 64,
+		.input	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37"
+			  "\x8f\xa1\x50\x23\x22\x4f\xe3\x91"
+			  "\xe9\x21\x5e\xbf\x52\x23\x95\x37"
+			  "\x48\x0c\x38\x8f\xf0\xff\x92\x24"
+			  "\x6b\x47\x49\xe3\x94\x1f\x1e\x01",
+		.ilen	= 64,
+		.result	= "\xe6\xeb\x92\x5a\x5b\xf0\x2d\xbb"
+			  "\x23\xec\x35\xe3\xae\xc9\xfb\x0b"
+			  "\x90\x14\x46\xeb\xa8\x8d\xb0\x9b"
+			  "\x39\xda\x8b\x48\xec\xb2\x00\x4e"
+			  "\x80\x6f\x46\x4f\x9b\x1e\xbb\x35"
+			  "\xea\x5a\xbc\xa2\x36\xa5\x89\x45"
+			  "\xc2\xd6\xd7\x15\x0b\xf6\x6c\x56"
+			  "\xec\x99\x7d\x61\xb3\x15\x93\xed"
+			  "\x83\x1e\xd9\x48\x84\x0b\x37\xfe"
+			  "\x95\x74\x44\xd5\x54\xa6\x27\x06",
+		.rlen	= 80,
+	}, {
+		.key	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76",
+		.klen	= 16,
+		.iv	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7",
+		.assoc	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79"
+			  "\xba\xcd\xe2\x13\xe4\x30\x66\xf4"
+			  "\xba\x78\xf9\xfb\x9d\x3c\xa1\x58"
+			  "\x1a\x22\x53\x05\x6b\x5c\x71\x4f"
+			  "\xfd\x2d\x4d\x4c\xe5\x62\xa5\x63"
+			  "\x6a\xda\x26\xc8\x7f\xff\xea\xfd"
+			  "\x46\x4a\xfa\x53\x8f\xc4\xcd\x68"
+			  "\x58",
+		.alen	= 65,
+		.input	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d\x4d\x54\x51\x84\x61\xf6\x8e"
+			  "\x03\x31\xf2\x25\x16\xcc\xaa\xc6"
+			  "\x75\x73\x20\x30\x59\x54\xb2\xf0"
+			  "\x3a\x4b\xe0\x23\x8e\xa6\x08\x35"
+			  "\x8a\xdf\x27\xa0\xe4\x60\x99\xae"
+			  "\x8e\x43\xd9\x39\x7b\x10\x40\x67"
+			  "\x5c\x7e\xc9\x70\x63\x34\xca\x59"
+			  "\xfe\x86\xbc\xb7\x9c\x39\xf3\x6d"
+			  "\x6a\x41\x64\x6f\x16\x7f\x65\x7e"
+			  "\x89\x84\x68\xeb\xb0\x51\xbe\x55"
+			  "\x33\x16\x59\x6c\x3b\xef\x88\xad"
+			  "\x2f\xab\xbc\x25\x76\x87\x41\x2f"
+			  "\x36",
+		.ilen	= 129,
+		.result	= "\x89\x24\x27\x86\xdc\xd7\x6b\xd9"
+			  "\xd1\xcd\xdc\x16\xdd\x2c\xc1\xfb"
+			  "\x52\xb5\xb3\xab\x50\x99\x3f\xa0"
+			  "\x38\xa4\x74\xa5\x04\x15\x63\x05"
+			  "\x8f\x54\x81\x06\x5a\x6b\xa4\x63"
+			  "\x6d\xa7\x21\xcb\xff\x42\x30\x8e"
+			  "\x3b\xd1\xca\x3f\x4b\x1a\xb8\xc3"
+			  "\x42\x01\xe6\xbc\x75\x15\x87\xee"
+			  "\xc9\x8e\x65\x01\xd9\xd8\xb5\x9f"
+			  "\x48\x86\xa6\x5f\x2c\xc7\xb5\xb0"
+			  "\xed\x5d\x14\x7c\x3f\x40\xb1\x0b"
+			  "\x72\xef\x94\x8d\x7a\x85\x56\xe5"
+			  "\x56\x08\x15\x56\xba\xaf\xbd\xf0"
+			  "\x20\xef\xa0\xf6\xa9\xad\xa2\xc9"
+			  "\x1c\x3b\x28\x51\x7e\x77\xb2\x18"
+			  "\x4f\x61\x64\x37\x22\x36\x6d\x78"
+			  "\xed\xed\x35\xe8\x83\xa5\xec\x25"
+			  "\x6b\xff\x5f\x1a\x09\x96\x3d\xdc"
+			  "\x20",
+		.rlen	= 145,
+	}, {
+		.key	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c",
+		.klen	= 16,
+		.iv	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe",
+		.assoc	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f"
+			  "\xe4\x8f\xed\x97\xe9\xd0\xe8\x0d"
+			  "\x7c\xa6\xd8\xd4\x77\x9b\x40\x2e"
+			  "\x28\xce\x57\x34\xcd\x6e\x84\x4c"
+			  "\x17\x3c\xe1\xb2\xa8\x0b\xbb\xf1"
+			  "\x96\x41\x0d\x69\xe8\x54\x0a\xc8"
+			  "\x15\x4e\x91\x92\x89\x4b\xb7\x9b"
+			  "\x21\xf7\x42\x89\xac\x12\x2a\x54"
+			  "\x69\xee\x18\xc7\x8d\xed\xe8\xfd"
+			  "\xbb\x04\x28\xe6\x8a\x3c\x98\xc1"
+			  "\x04\x2d\xa9\xa1\x24\x83\xff\xe9"
+			  "\x55\x7a\xf0\xd1\xf6\x63\x05\xe1"
+			  "\xd9\x1e\x75\x72\xc1\x9f\xae\x32"
+			  "\xe1\x6b\xcd\x9e\x61\x19\x23\x86"
+			  "\xd9\xd2\xaf\x8e\xd5\xd3\xa8\xa9"
+			  "\x51",
+		.alen	= 129,
+		.input	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac\xfa\x58\x7f\xe5\x73\x09\x8c"
+			  "\x1d\x40\x87\x8c\xd9\x75\xc0\x55"
+			  "\xa2\xda\x07\xd1\xc2\xa9\xd1\xbb"
+			  "\x09\x4f\x77\x62\x88\x2d\xf2\x68"
+			  "\x54",
+		.ilen	= 65,
+		.result	= "\x36\x78\xb9\x22\xde\x62\x35\x55"
+			  "\x1a\x7a\xf5\x45\xbc\xd7\x15\x82"
+			  "\x01\xe9\x5a\x07\xea\x46\xaf\x91"
+			  "\xcb\x73\xa5\xee\xe1\xb4\xbf\xc2"
+			  "\xdb\xd2\x9d\x59\xde\xfc\x83\x00"
+			  "\xf5\x46\xac\x97\xd5\x57\xa9\xb9"
+			  "\x1f\x8c\xe8\xca\x68\x8b\x91\x0c"
+			  "\x01\xbe\x0a\xaf\x7c\xf6\x67\xa4"
+			  "\xbf\xbc\x88\x3f\x5d\xd1\xf9\x19"
+			  "\x0f\x9d\xb2\xaf\xb9\x6e\x17\xdf"
+			  "\xa2",
+		.rlen	= 81,
+	}, {
+		.key	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82",
+		.klen	= 16,
+		.iv	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04",
+		.assoc	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85"
+			  "\x0e\x51\xf9\x1c\xee\x70\x6a\x27"
+			  "\x3d\xd3\xb7\xac\x51\xfa\xdf\x05",
+		.alen	= 32,
+		.input	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07"
+			  "\xd9\x02\x7c\x3d\x2f\x18\x4b\x2d"
+			  "\x6e\xde\xee\xa2\x08\x12\xc7\xba",
+		.ilen	= 32,
+		.result	= "\x08\x1b\x95\x0e\x41\x95\x02\x4b"
+			  "\x9c\xbb\xa8\xd0\x7c\xd3\x44\x6e"
+			  "\x89\x14\x33\x70\x0a\xbc\xea\x39"
+			  "\x88\xaa\x2b\xd5\x73\x11\x55\xf5"
+			  "\x33\x33\x9c\xd7\x42\x34\x49\x8e"
+			  "\x2f\x03\x30\x05\x47\xaf\x34",
+		.rlen	= 47,
+	}, {
+		.key	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.klen	= 16,
+		.iv	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a",
+		.assoc	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c"
+			  "\x39\x14\x05\xa0\xf3\x10\xec\x41"
+			  "\xff\x01\x95\x84\x2b\x59\x7f\xdb",
+		.alen	= 32,
+		.input	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d"
+			  "\x03\xc4\x88\xc1\x35\xb8\xcd\x47"
+			  "\x2f\x0c\xcd\x7a\xe2\x71\x66\x91",
+		.ilen	= 32,
+		.result	= "\x97\xca\xf4\xe0\x8d\x89\xbf\x68"
+			  "\x0c\x60\xb9\x27\xdf\xaa\x41\xc6"
+			  "\x25\xd8\xf7\x1f\x10\x15\x48\x61"
+			  "\x4c\x95\x00\xdf\x51\x9b\x7f\xe6"
+			  "\x24\x40\x9e\xbe\x3b\xeb\x1b\x98"
+			  "\xb9\x9c\xe5\xef\xf2\x05",
+		.rlen	= 46,
+	}, {
+		.key	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.klen	= 16,
+		.iv	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10",
+		.assoc	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92"
+			  "\x63\xd6\x10\x24\xf8\xb0\x6e\x5a"
+			  "\xc0\x2e\x74\x5d\x06\xb8\x1e\xb2",
+		.alen	= 32,
+		.input	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13"
+			  "\x2e\x86\x93\x45\x3a\x58\x4f\x61"
+			  "\xf0\x3a\xac\x53\xbc\xd0\x06\x68",
+		.ilen	= 32,
+		.result	= "\x63\x4c\x2a\x8e\xb4\x6b\x63\x0d"
+			  "\xb5\xec\x9b\x4e\x12\x23\xa3\xcf"
+			  "\x1a\x5a\x70\x15\x5a\x10\x40\x51"
+			  "\xca\x47\x4c\x9d\xc9\x97\xf4\x77"
+			  "\xdb\xc8\x10\x2d\xdc\x65\x20\x3f",
+		.rlen	= 40,
+	}, {
+		.key	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.klen	= 16,
+		.iv	= "\xbb\x3a\xf7\x57\xc6\x36\x7c\x22"
+			  "\x36\xab\xde\xc6\x6d\x32\x70\x17",
+		.assoc	= "\xcb\x03\x85\xbf\x0a\xd5\x26\xa9"
+			  "\x56\xe1\x0a\xeb\x6c\xfb\xa1\x98"
+			  "\x8d\x98\x1c\xa8\xfe\x50\xf0\x74"
+			  "\x81\x5c\x53\x35\xe0\x17\xbd\x88",
+		.alen	= 32,
+		.input	= "\xda\xcc\x14\x27\x4e\x74\xd1\x30"
+			  "\x76\x18\x37\x0f\x6a\xc4\xd1\x1a"
+			  "\x58\x49\x9f\xc9\x3f\xf8\xd1\x7a"
+			  "\xb2\x67\x8b\x2b\x96\x2f\xa5\x3e",
+		.ilen	= 32,
+		.result	= "\xf1\x62\x44\xc7\x5f\x19\xca\x43"
+			  "\x47\x2c\xaf\x68\x82\xbd\x51\xef"
+			  "\x3d\x65\xd8\x45\x2d\x06\x07\x78"
+			  "\x08\x2e\xb3\x23\xcd\x81\x12\x55"
+			  "\x1a",
+		.rlen	= 33,
+	}, {
+		.key	= "\xe9\x95\xa2\x8f\x93\x13\x7b\xb7"
+			  "\x96\x4e\x63\x33\x69\x8d\x02\x9b"
+			  "\x23\xf9\x22\xeb\x80\xa0\xb1\x81"
+			  "\xe2\x73\xc3\x21\x4d\x47\x8d\xf4",
+		.klen	= 32,
+		.iv	= "\xf8\x5e\x31\xf7\xd7\xb2\x25\x3e"
+			  "\xb7\x85\x90\x58\x67\x57\x33\x1d",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xdf\x2f\x83\xc0\x45\x4a\x2c\xcf"
+			  "\xb9\xd2\x41\xf6\x80\xa1\x52\x70",
+		.rlen	= 16,
+	}, {
+		.key	= "\x25\xba\xdc\x2e\xa3\x8f\x24\xd3"
+			  "\x17\x29\x15\xc5\x63\xb2\xc5\xa1"
+			  "\x4d\xbc\x2d\x6f\x85\x40\x33\x9a"
+			  "\xa3\xa0\xa1\xfa\x27\xa6\x2c\xca",
+		.klen	= 32,
+		.iv	= "\x34\x83\x6a\x96\xe7\x2d\xce\x5a"
+			  "\x38\x5f\x42\xe9\x61\x7b\xf5\x23",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x53",
+		.ilen	= 1,
+		.result	= "\x01\xd8\x55\x3c\xc0\x5a\x4b\xc7"
+			  "\x01\xf4\x08\xe3\x0d\xf7\xf0\x78"
+			  "\x53",
+		.rlen	= 17,
+	}, {
+		.key	= "\x62\xdf\x16\xcd\xb3\x0a\xcc\xef"
+			  "\x98\x03\xc7\x56\x5d\xd6\x87\xa8"
+			  "\x77\x7e\x39\xf3\x8a\xe0\xb5\xb4"
+			  "\x65\xce\x80\xd2\x01\x05\xcb\xa1",
+		.klen	= 32,
+		.iv	= "\x71\xa8\xa4\x35\xf7\xa9\x76\x75"
+			  "\xb8\x39\xf4\x7a\x5b\x9f\xb8\x29",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x8f\x3a\xc1\x05\x7f\xe7\xcb\x83"
+			  "\xf9\xa6\x4d\xc3\x58\x31\x19\x2c"
+			  "\xd7\x90\xc2\x56\x4e\xd8\x57\xc7"
+			  "\xf6\xf0\x27\xb4\x25\x4c\x83",
+		.ilen	= 31,
+		.result	= "\xc2\x4b\x41\x0f\x2d\xb9\x62\x07"
+			  "\xff\x8e\x74\xf8\xa1\xa6\xd5\x37"
+			  "\xa5\x64\x31\x5c\xca\x73\x9b\x43"
+			  "\xe6\x70\x63\x46\x95\xcb\xf7\xb5"
+			  "\x20\x8c\x75\x7a\x2a\x17\x2f\xa9"
+			  "\xb8\x4d\x11\x42\xd1\xf8\xf1",
+		.rlen	= 47,
+	}, {
+		.key	= "\x9e\x03\x4f\x6d\xc3\x86\x75\x0a"
+			  "\x19\xdd\x79\xe8\x57\xfb\x4a\xae"
+			  "\xa2\x40\x45\x77\x90\x80\x37\xce"
+			  "\x26\xfb\x5f\xaa\xdb\x64\x6b\x77",
+		.klen	= 32,
+		.iv	= "\xae\xcc\xde\xd5\x07\x25\x1f\x91"
+			  "\x39\x14\xa6\x0c\x55\xc4\x7b\x30",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xcc\x5f\xfb\xa4\x8f\x63\x74\x9f"
+			  "\x7a\x81\xff\x55\x52\x56\xdc\x33"
+			  "\x01\x52\xcd\xdb\x53\x78\xd9\xe1"
+			  "\xb7\x1d\x06\x8d\xff\xab\x22\x98",
+		.ilen	= 32,
+		.result	= "\xbb\x01\x7c\xd1\x2c\x33\x7b\x37"
+			  "\x0a\xee\xc4\x30\x19\xd7\x3a\x6f"
+			  "\xf8\x2b\x67\xf5\x3b\x84\x87\x2a"
+			  "\xfb\x07\x7a\x82\xb5\xe4\x85\x26"
+			  "\x1e\xa8\xe5\x04\x54\xce\xe5\x5f"
+			  "\xb5\x3f\xc1\xd5\x7f\xbd\xd2\xa6",
+		.rlen	= 48,
+	}, {
+		.key	= "\xdb\x28\x89\x0c\xd3\x01\x1e\x26"
+			  "\x9a\xb7\x2b\x79\x51\x1f\x0d\xb4"
+			  "\xcc\x03\x50\xfc\x95\x20\xb9\xe7"
+			  "\xe8\x29\x3e\x83\xb5\xc3\x0a\x4e",
+		.klen	= 32,
+		.iv	= "\xea\xf1\x18\x74\x17\xa0\xc8\xad"
+			  "\xba\xee\x58\x9d\x4f\xe8\x3d\x36",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x08\x84\x34\x44\x9f\xde\x1c\xbb"
+			  "\xfb\x5b\xb1\xe6\x4c\x7a\x9f\x39"
+			  "\x2c\x14\xd9\x5f\x59\x18\x5b\xfb"
+			  "\x79\x4b\xe5\x65\xd9\x0a\xc1\x6f"
+			  "\x2e",
+		.ilen	= 33,
+		.result	= "\xc2\xf4\x40\x55\xf9\x59\xff\x73"
+			  "\x08\xf5\x98\x92\x0c\x7b\x35\x9a"
+			  "\xa8\xf4\x42\x7e\x6f\x93\xca\x22"
+			  "\x23\x06\x1e\xf8\x89\x22\xf4\x46"
+			  "\x7c\x7c\x67\x75\xab\xe5\x75\xaa"
+			  "\x15\xd7\x83\x19\xfd\x31\x59\x5b"
+			  "\x32",
+		.rlen	= 49,
+	}, {
+		.key	= "\x17\x4d\xc3\xab\xe3\x7d\xc7\x42"
+			  "\x1b\x91\xdd\x0a\x4b\x43\xcf\xba"
+			  "\xf6\xc5\x5c\x80\x9a\xc0\x3b\x01"
+			  "\xa9\x56\x1d\x5b\x8f\x22\xa9\x25",
+		.klen	= 32,
+		.iv	= "\x27\x16\x51\x13\x27\x1c\x71\xc9"
+			  "\x3b\xc8\x0a\x2f\x49\x0c\x00\x3c",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x45\xa8\x6e\xe3\xaf\x5a\xc5\xd7"
+			  "\x7c\x35\x63\x77\x46\x9f\x61\x3f"
+			  "\x56\xd7\xe4\xe3\x5e\xb8\xdc\x14"
+			  "\x3a\x79\xc4\x3e\xb3\x69\x61\x46"
+			  "\x3c\xb6\x83\x4e\xb4\x26\xc7\x73"
+			  "\x22\xda\x52\x8b\x7d\x11\x98\xea"
+			  "\x62\xe1\x14\x1e\xdc\xfe\x0f\xad"
+			  "\x20\x76\x5a\xdc\x4e\x71\x13",
+		.ilen	= 63,
+		.result	= "\xc9\x82\x3b\x4b\x87\x84\xa5\xdb"
+			  "\xa0\x8c\xd3\x3e\x7f\x8d\xe8\x28"
+			  "\x2a\xdc\xfa\x01\x84\x87\x9a\x70"
+			  "\x81\x75\x37\x0a\xd2\x75\xa9\xb6"
+			  "\x21\x72\xee\x7e\x65\x95\xe5\xcc"
+			  "\x01\xb7\x39\xa6\x51\x15\xca\xff"
+			  "\x61\xdc\x97\x38\xcc\xf4\xca\xc7"
+			  "\x83\x9b\x05\x11\x72\x60\xf0\xb4"
+			  "\x7e\x06\xab\x0a\xc0\xbb\x59\x23"
+			  "\xaa\x2d\xfc\x4e\x35\x05\x59",
+		.rlen	= 79,
+	}, {
+		.key	= "\x54\x71\xfd\x4b\xf3\xf9\x6f\x5e"
+			  "\x9c\x6c\x8f\x9c\x45\x68\x92\xc1"
+			  "\x21\x87\x67\x04\x9f\x60\xbd\x1b"
+			  "\x6a\x84\xfc\x34\x6a\x81\x48\xfb",
+		.klen	= 32,
+		.iv	= "\x63\x3b\x8b\xb3\x37\x98\x1a\xe5"
+			  "\xbc\xa2\xbc\xc0\x43\x31\xc2\x42",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x81\xcd\xa8\x82\xbf\xd6\x6e\xf3"
+			  "\xfd\x0f\x15\x09\x40\xc3\x24\x45"
+			  "\x81\x99\xf0\x67\x63\x58\x5e\x2e"
+			  "\xfb\xa6\xa3\x16\x8d\xc8\x00\x1c"
+			  "\x4b\x62\x87\x7c\x15\x38\xda\x70"
+			  "\x3d\xea\xe7\xf2\x40\xba\xae\x79"
+			  "\x8f\x48\xfc\xbf\x45\x53\x2e\x78"
+			  "\xef\x79\xf0\x1b\x49\xf7\xfd\x9c",
+		.ilen	= 64,
+		.result	= "\x11\x7c\x7d\xef\xce\x29\x95\xec"
+			  "\x7e\x9f\x42\xa6\x26\x07\xa1\x75"
+			  "\x2f\x4e\x09\x9a\xf6\x6b\xc2\xfa"
+			  "\x0d\xd0\x17\xdc\x25\x1e\x9b\xdc"
+			  "\x5f\x8c\x1c\x60\x15\x4f\x9b\x20"
+			  "\x7b\xff\xcd\x82\x60\x84\xf4\xa5"
+			  "\x20\x9a\x05\x19\x5b\x02\x0a\x72"
+			  "\x43\x11\x26\x58\xcf\xc5\x41\xcf"
+			  "\x13\xcc\xde\x32\x92\xfa\x86\xf2"
+			  "\xaf\x16\xe8\x8f\xca\xb6\xfd\x54",
+		.rlen	= 80,
+	}, {
+		.key	= "\x90\x96\x36\xea\x03\x74\x18\x7a"
+			  "\x1d\x46\x42\x2d\x3f\x8c\x54\xc7"
+			  "\x4b\x4a\x73\x89\xa4\x00\x3f\x34"
+			  "\x2c\xb1\xdb\x0c\x44\xe0\xe8\xd2",
+		.klen	= 32,
+		.iv	= "\xa0\x5f\xc5\x52\x47\x13\xc2\x01"
+			  "\x3d\x7c\x6e\x52\x3d\x55\x85\x48",
+		.assoc	= "\xaf",
+		.alen	= 1,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x9b\xc5\x3b\x20\x0a\x88\x56\xbe"
+			  "\x69\xdf\xc4\xc4\x02\x46\x3a\xf0",
+		.rlen	= 16,
+	}, {
+		.key	= "\xcd\xbb\x70\x89\x13\xf0\xc1\x95"
+			  "\x9e\x20\xf4\xbf\x39\xb1\x17\xcd"
+			  "\x76\x0c\x7f\x0d\xa9\xa0\xc1\x4e"
+			  "\xed\xdf\xb9\xe4\x1e\x3f\x87\xa8",
+		.klen	= 32,
+		.iv	= "\xdc\x84\xfe\xf1\x58\x8f\x6b\x1c"
+			  "\xbe\x57\x20\xe3\x37\x7a\x48\x4f",
+		.assoc	= "\xeb\x4d\x8d\x59\x9c\x2e\x15\xa3"
+			  "\xde\x8d\x4d\x07\x36\x43\x78\xd0"
+			  "\x0b\x6d\x84\x4f\x2c\xf0\x82\x5b"
+			  "\x4e\xf6\x29\xd1\x8b\x6f\x56",
+		.alen	= 31,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xe0\x6d\xa1\x07\x98\x2f\x40\x2d"
+			  "\x2e\x9a\xd6\x61\x43\xc0\x74\x69",
+		.rlen	= 16,
+	}, {
+		.key	= "\x0a\xe0\xaa\x29\x24\x6c\x6a\xb1"
+			  "\x1f\xfa\xa6\x50\x33\xd5\xda\xd3"
+			  "\xa0\xce\x8a\x91\xae\x40\x43\x68"
+			  "\xae\x0d\x98\xbd\xf8\x9e\x26\x7f",
+		.klen	= 32,
+		.iv	= "\x19\xa9\x38\x91\x68\x0b\x14\x38"
+			  "\x3f\x31\xd2\x74\x31\x9e\x0a\x55",
+		.assoc	= "\x28\x72\xc7\xf8\xac\xaa\xbe\xbf"
+			  "\x5f\x67\xff\x99\x30\x67\x3b\xd6"
+			  "\x35\x2f\x90\xd3\x31\x90\x04\x74"
+			  "\x0f\x23\x08\xa9\x65\xce\xf6\xea",
+		.alen	= 32,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\xb9\x57\x13\x3e\x82\x31\x61\x65"
+			  "\x0d\x7f\x6c\x96\x93\x5c\x50\xe2",
+		.rlen	= 16,
+	}, {
+		.key	= "\x46\x04\xe3\xc8\x34\xe7\x12\xcd"
+			  "\xa0\xd4\x58\xe2\x2d\xf9\x9c\xda"
+			  "\xca\x91\x96\x15\xb4\xe0\xc5\x81"
+			  "\x70\x3a\x77\x95\xd2\xfd\xc5\x55",
+		.klen	= 32,
+		.iv	= "\x55\xcd\x72\x30\x78\x86\xbd\x54"
+			  "\xc0\x0b\x84\x06\x2b\xc2\xcd\x5b",
+		.assoc	= "\x64\x97\x00\x98\xbc\x25\x67\xdb"
+			  "\xe0\x41\xb1\x2a\x2a\x8c\xfe\xdd"
+			  "\x5f\xf2\x9c\x58\x36\x30\x86\x8e"
+			  "\xd1\x51\xe6\x81\x3f\x2d\x95\xc1"
+			  "\x01",
+		.alen	= 33,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x81\x96\x34\xde\xbb\x36\xdd\x3e"
+			  "\x4e\x5e\xcb\x44\x21\xb8\x3f\xf1",
+		.rlen	= 16,
+	}, {
+		.key	= "\x83\x29\x1d\x67\x44\x63\xbb\xe9"
+			  "\x20\xaf\x0a\x73\x27\x1e\x5f\xe0"
+			  "\xf5\x53\xa1\x9a\xb9\x80\x47\x9b"
+			  "\x31\x68\x56\x6e\xac\x5c\x65\x2c",
+		.klen	= 32,
+		.iv	= "\x92\xf2\xac\xcf\x88\x02\x65\x70"
+			  "\x41\xe5\x36\x97\x25\xe7\x90\x61",
+		.assoc	= "\xa1\xbb\x3a\x37\xcc\xa1\x10\xf7"
+			  "\x61\x1c\x63\xbc\x24\xb0\xc0\xe3"
+			  "\x8a\xb4\xa7\xdc\x3b\xd0\x08\xa8"
+			  "\x92\x7f\xc5\x5a\x19\x8c\x34\x97"
+			  "\x0f\x95\x9b\x18\xe4\x8d\xb4\x24"
+			  "\xb9\x33\x28\x18\xe1\x9d\x14\xe0"
+			  "\x64\xb2\x89\x7d\x78\xa8\x05\x7e"
+			  "\x07\x8c\xfc\x88\x2d\xb8\x53",
+		.alen	= 63,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x2e\x99\xb6\x79\x57\x56\x80\x36"
+			  "\x8e\xc4\x1c\x12\x7d\x71\x36\x0c",
+		.rlen	= 16,
+	}, {
+		.key	= "\xbf\x4e\x57\x07\x54\xdf\x64\x05"
+			  "\xa1\x89\xbc\x04\x21\x42\x22\xe6"
+			  "\x1f\x15\xad\x1e\xbe\x20\xc9\xb4"
+			  "\xf3\x95\x35\x46\x86\xbb\x04\x03",
+		.klen	= 32,
+		.iv	= "\xce\x17\xe5\x6f\x98\x7e\x0e\x8c"
+			  "\xc2\xbf\xe8\x29\x1f\x0b\x52\x68",
+		.assoc	= "\xdd\xe0\x74\xd6\xdc\x1d\xb8\x13"
+			  "\xe2\xf6\x15\x4d\x1e\xd4\x83\xe9"
+			  "\xb4\x76\xb3\x60\x40\x70\x8a\xc1"
+			  "\x53\xac\xa4\x32\xf3\xeb\xd3\x6e"
+			  "\x1e\x42\xa0\x46\x45\x9f\xc7\x22"
+			  "\xd3\x43\xbc\x7e\xa5\x47\x2a\x6f"
+			  "\x91\x19\x70\x1e\xe1\xfe\x25\x49"
+			  "\xd6\x8f\x93\xc7\x28\x3f\x3d\x03",
+		.alen	= 64,
+		.input	= "",
+		.ilen	= 0,
+		.result	= "\x7b\x25\x3d\x47\xd4\xa7\x08\xce"
+			  "\x3b\x89\x40\x36\xba\x6d\x0e\xa2",
+		.rlen	= 16,
+	}, {
+		.key	= "\xfc\x72\x90\xa6\x64\x5a\x0d\x21"
+			  "\x22\x63\x6e\x96\x1b\x67\xe4\xec"
+			  "\x49\xd7\xb9\xa2\xc3\xc0\x4b\xce"
+			  "\xb4\xc3\x14\x1e\x61\x1a\xa3\xd9",
+		.klen	= 32,
+		.iv	= "\x0b\x3c\x1f\x0e\xa8\xf9\xb7\xa7"
+			  "\x42\x9a\x9a\xba\x19\x30\x15\x6e",
+		.assoc	= "\x1a",
+		.alen	= 1,
+		.input	= "\x29",
+		.ilen	= 1,
+		.result	= "\xe6\x09\x6f\x95\x9a\x18\xc8\xf6"
+			  "\x17\x75\x81\x16\xdf\x26\xff\x67"
+			  "\x92",
+		.rlen	= 17,
+	}, {
+		.key	= "\x38\x97\xca\x45\x74\xd6\xb6\x3c"
+			  "\xa3\x3d\x20\x27\x15\x8b\xa7\xf2"
+			  "\x74\x9a\xc4\x27\xc8\x60\xcd\xe8"
+			  "\x75\xf0\xf2\xf7\x3b\x79\x42\xb0",
+		.klen	= 32,
+		.iv	= "\x47\x60\x59\xad\xb8\x75\x60\xc3"
+			  "\xc3\x74\x4c\x4c\x13\x54\xd8\x74",
+		.assoc	= "\x56\x29\xe7\x15\xfc\x14\x0a\x4a"
+			  "\xe4\xaa\x79\x70\x12\x1d\x08\xf6"
+			  "\x09\xfb\xca\x69\x4b\xb0\x8e\xf5"
+			  "\xd6\x07\x62\xe3\xa8\xa9\x12",
+		.alen	= 31,
+		.input	= "\x66\xf3\x75\x7d\x40\xb3\xb4\xd1"
+			  "\x04\xe1\xa6\x94\x10\xe6\x39\x77"
+			  "\xd3\xac\x4d\x8a\x8c\x58\x6e\xfb"
+			  "\x06\x13\x9a\xd9\x5e\xc0\xfa",
+		.ilen	= 31,
+		.result	= "\x82\xc0\x56\xf0\xd7\xc4\xc9\xfd"
+			  "\x3c\xd1\x2a\xd4\x15\x86\x9d\xda"
+			  "\xea\x6c\x6f\xa1\x33\xb0\x7a\x01"
+			  "\x57\xe7\xf3\x7b\x73\xe7\x54\x10"
+			  "\xc6\x91\xe2\xc6\xa0\x69\xe7\xe6"
+			  "\x76\xc3\xf5\x3a\x76\xfd\x4a",
+		.rlen	= 47,
+	}, {
+		.key	= "\x75\xbc\x04\xe5\x84\x52\x5e\x58"
+			  "\x24\x17\xd2\xb9\x0e\xaf\x6a\xf9"
+			  "\x9e\x5c\xd0\xab\xcd\x00\x4f\x01"
+			  "\x37\x1e\xd1\xcf\x15\xd8\xe2\x86",
+		.klen	= 32,
+		.iv	= "\x84\x85\x92\x4d\xc8\xf1\x08\xdf"
+			  "\x44\x4e\xff\xdd\x0d\x78\x9a\x7a",
+		.assoc	= "\x93\x4e\x21\xb4\x0c\x90\xb3\x66"
+			  "\x65\x84\x2b\x01\x0b\x42\xcb\xfc"
+			  "\x33\xbd\xd6\xed\x50\x50\x10\x0e"
+			  "\x97\x35\x41\xbb\x82\x08\xb1\xf2",
+		.alen	= 32,
+		.input	= "\xa2\x17\xaf\x1c\x50\x2e\x5d\xed"
+			  "\x85\xbb\x58\x26\x0a\x0b\xfc\x7d"
+			  "\xfe\x6e\x59\x0e\x91\xf8\xf0\x15"
+			  "\xc8\x40\x78\xb1\x38\x1f\x99\xa7",
+		.ilen	= 32,
+		.result	= "\x01\x47\x8e\x6c\xf6\x64\x89\x3a"
+			  "\x71\xce\xe4\xaa\x45\x70\xe6\x84"
+			  "\x62\x48\x08\x64\x86\x6a\xdf\xec"
+			  "\xb4\xa0\xfb\x34\x03\x0c\x19\xf4"
+			  "\x2b\x7b\x36\x73\xec\x54\xa9\x1e"
+			  "\x30\x85\xdb\xe4\xac\xe9\x2c\xca",
+		.rlen	= 48,
+	}, {
+		.key	= "\xb1\xe1\x3e\x84\x94\xcd\x07\x74"
+			  "\xa5\xf2\x84\x4a\x08\xd4\x2c\xff"
+			  "\xc8\x1e\xdb\x2f\xd2\xa0\xd1\x1b"
+			  "\xf8\x4c\xb0\xa8\xef\x37\x81\x5d",
+		.klen	= 32,
+		.iv	= "\xc0\xaa\xcc\xec\xd8\x6c\xb1\xfb"
+			  "\xc5\x28\xb1\x6e\x07\x9d\x5d\x81",
+		.assoc	= "\xd0\x73\x5a\x54\x1d\x0b\x5b\x82"
+			  "\xe5\x5f\xdd\x93\x05\x66\x8e\x02"
+			  "\x5e\x80\xe1\x71\x55\xf0\x92\x28"
+			  "\x59\x62\x20\x94\x5c\x67\x50\xc8"
+			  "\x58",
+		.alen	= 33,
+		.input	= "\xdf\x3c\xe9\xbc\x61\xaa\x06\x09"
+			  "\x06\x95\x0a\xb7\x04\x2f\xbe\x84"
+			  "\x28\x30\x64\x92\x96\x98\x72\x2e"
+			  "\x89\x6e\x57\x8a\x13\x7e\x38\x7e"
+			  "\xdb",
+		.ilen	= 33,
+		.result	= "\x85\xe0\xf8\x0f\x8e\x49\xe3\x60"
+			  "\xcb\x4a\x54\x94\xcf\xf5\x7e\x34"
+			  "\xe9\xf8\x80\x65\x53\xd0\x72\x70"
+			  "\x4f\x7d\x9d\xd1\x15\x6f\xb9\x2c"
+			  "\xfa\xe8\xdd\xac\x2e\xe1\x3f\x67"
+			  "\x63\x0f\x1a\x59\xb7\x89\xdb\xf4"
+			  "\xc3",
+		.rlen	= 49,
+	}, {
+		.key	= "\xee\x05\x77\x23\xa5\x49\xb0\x90"
+			  "\x26\xcc\x36\xdc\x02\xf8\xef\x05"
+			  "\xf3\xe1\xe7\xb3\xd8\x40\x53\x35"
+			  "\xb9\x79\x8f\x80\xc9\x96\x20\x33",
+		.klen	= 32,
+		.iv	= "\xfd\xce\x06\x8b\xe9\xe8\x5a\x17"
+			  "\x46\x02\x63\x00\x01\xc1\x20\x87",
+		.assoc	= "\x0c\x98\x94\xf3\x2d\x87\x04\x9e"
+			  "\x66\x39\x8f\x24\xff\x8a\x50\x08"
+			  "\x88\x42\xed\xf6\x5a\x90\x14\x42"
+			  "\x1a\x90\xfe\x6c\x36\xc6\xf0\x9f"
+			  "\x66\xa0\xb5\x2d\x2c\xf8\x25\x15"
+			  "\x55\x90\xa2\x7e\x77\x94\x96\x3a"
+			  "\x71\x1c\xf7\x44\xee\xa8\xc3\x42"
+			  "\xe2\xa3\x84\x04\x0b\xe1\xce",
+		.alen	= 63,
+		.input	= "\x1b\x61\x23\x5b\x71\x26\xae\x25"
+			  "\x87\x6f\xbc\x49\xfe\x53\x81\x8a"
+			  "\x53\xf2\x70\x17\x9b\x38\xf4\x48"
+			  "\x4b\x9b\x36\x62\xed\xdd\xd8\x54"
+			  "\xea\xcb\xb6\x79\x45\xfc\xaa\x54"
+			  "\x5c\x94\x47\x58\xa7\xff\x9c\x9e"
+			  "\x7c\xb6\xf1\xac\xc8\xfd\x8b\x35"
+			  "\xd5\xa4\x6a\xd4\x09\xc2\x08",
+		.ilen	= 63,
+		.result	= "\x00\xe5\x5b\x87\x5c\x20\x22\x8a"
+			  "\xda\x1f\xd3\xff\xbb\xb2\xb0\xf8"
+			  "\xef\xe9\xeb\x9e\x7c\x80\xf4\x2b"
+			  "\x59\xc0\x79\xbc\x17\xa0\x15\x01"
+			  "\xf5\x72\xfb\x5a\xe7\xaf\x07\xe3"
+			  "\x1b\x49\x21\x34\x23\x63\x55\x5e"
+			  "\xee\x4f\x34\x17\xfa\xfe\xa5\x0c"
+			  "\xed\x0b\x23\xea\x9b\xda\x57\x2f"
+			  "\xf6\xa9\xae\x0d\x4e\x40\x96\x45"
+			  "\x7f\xfa\xf0\xbf\xc4\x98\x78",
+		.rlen	= 79,
+	}, {
+		.key	= "\x2a\x2a\xb1\xc3\xb5\xc5\x59\xac"
+			  "\xa7\xa6\xe8\x6d\xfc\x1d\xb2\x0b"
+			  "\x1d\xa3\xf3\x38\xdd\xe0\xd5\x4e"
+			  "\x7b\xa7\x6e\x58\xa3\xf5\xbf\x0a",
+		.klen	= 32,
+		.iv	= "\x39\xf3\x3f\x2b\xf9\x64\x03\x33"
+			  "\xc7\xdd\x15\x91\xfb\xe6\xe2\x8d",
+		.assoc	= "\x49\xbc\xce\x92\x3d\x02\xad\xba"
+			  "\xe7\x13\x41\xb6\xf9\xaf\x13\x0f"
+			  "\xb2\x04\xf8\x7a\x5f\x30\x96\x5b"
+			  "\xdc\xbd\xdd\x44\x10\x25\x8f\x75"
+			  "\x75\x4d\xb9\x5b\x8e\x0a\x38\x13"
+			  "\x6f\x9f\x36\xe4\x3a\x3e\xac\xc9"
+			  "\x9d\x83\xde\xe5\x57\xfd\xe3\x0e"
+			  "\xb1\xa7\x1b\x44\x05\x67\xb7\x37",
+		.alen	= 64,
+		.input	= "\x58\x85\x5c\xfa\x81\xa1\x57\x40"
+			  "\x08\x4a\x6e\xda\xf8\x78\x44\x90"
+			  "\x7d\xb5\x7b\x9b\xa1\xd8\x76\x62"
+			  "\x0c\xc9\x15\x3b\xc7\x3c\x77\x2b"
+			  "\xf8\x78\xba\xa7\xa6\x0e\xbd\x52"
+			  "\x76\xa3\xdc\xbe\x6b\xa8\xb1\x2d"
+			  "\xa9\x1d\xd8\x4e\x31\x53\xab\x00"
+			  "\xa5\xa7\x01\x13\x04\x49\xf2\x04",
+		.ilen	= 64,
+		.result	= "\x28\xdd\xb9\x4a\x12\xc7\x0a\xe1"
+			  "\x58\x06\x1a\x9b\x8c\x67\xdf\xeb"
+			  "\x35\x35\x60\x9d\x06\x40\x65\xc1"
+			  "\x93\xe8\xb3\x82\x50\x29\xdd\xb5"
+			  "\x2b\xcb\xde\x18\x78\x6b\x42\xbe"
+			  "\x6d\x24\xd0\xb2\x7d\xd7\x08\x8f"
+			  "\x4a\x18\x98\xad\x8c\xf2\x97\xb4"
+			  "\xf4\x77\xe4\xbf\x41\x3b\xc4\x06"
+			  "\xce\x9e\x34\x81\xf0\x89\x11\x13"
+			  "\x02\x65\xa1\x7c\xdf\x07\x33\x06",
+		.rlen	= 80,
+	}, {
+		.key	= "\x67\x4f\xeb\x62\xc5\x40\x01\xc7"
+			  "\x28\x80\x9a\xfe\xf6\x41\x74\x12"
+			  "\x48\x65\xfe\xbc\xe2\x80\x57\x68"
+			  "\x3c\xd4\x4d\x31\x7d\x54\x5f\xe1",
+		.klen	= 32,
+		.iv	= "\x76\x18\x79\xca\x09\xdf\xac\x4e"
+			  "\x48\xb7\xc7\x23\xf5\x0a\xa5\x93",
+		.assoc	= "\x85\xe1\x08\x32\x4d\x7e\x56\xd5"
+			  "\x68\xed\xf3\x47\xf3\xd3\xd6\x15"
+			  "\xdd\xc7\x04\xfe\x64\xd0\x18\x75"
+			  "\x9d\xeb\xbc\x1d\xea\x84\x2e\x4c"
+			  "\x83\xf9\xbe\x8a\xef\x1c\x4b\x10"
+			  "\x89\xaf\xcb\x4b\xfe\xe7\xc1\x58"
+			  "\xca\xea\xc6\x87\xc0\x53\x03\xd9"
+			  "\x80\xaa\xb2\x83\xff\xee\xa1\x6a"
+			  "\x04",
+		.alen	= 65,
+		.input	= "\x94\xaa\x96\x9a\x91\x1d\x00\x5c"
+			  "\x88\x24\x20\x6b\xf2\x9c\x06\x96"
+			  "\xa7\x77\x87\x1f\xa6\x78\xf8\x7b"
+			  "\xcd\xf6\xf4\x13\xa1\x9b\x16\x02"
+			  "\x07\x24\xbf\xd5\x08\x20\xd0\x4f"
+			  "\x90\xb3\x70\x24\x2f\x51\xc7\xbb"
+			  "\xd6\x84\xc0\xef\x9a\xa8\xca\xcc"
+			  "\x74\xab\x97\x53\xfe\xd0\xdb\x37"
+			  "\x37\x6a\x0e\x9f\x3f\xa3\x2a\xe3"
+			  "\x1b\x34\x6d\x51\x72\x2b\x17\xe7"
+			  "\x4d\xaa\x2c\x18\xda\xa3\x33\x89"
+			  "\x2a\x9f\xf4\xd2\xed\x76\x3d\x3f"
+			  "\x3c\x15\x9d\x8e\x4f\x3c\x27\xb0"
+			  "\x42\x3f\x2f\x8a\xd4\xc2\x10\xb2"
+			  "\x27\x7f\xe3\x34\x80\x02\x49\x4b"
+			  "\x07\x68\x22\x2a\x88\x25\x53\xb2"
+			  "\x2f",
+		.ilen	= 129,
+		.result	= "\x85\x39\x69\x35\xfb\xf9\xb0\xa6"
+			  "\x85\x43\x88\xd0\xd7\x78\x60\x19"
+			  "\x3e\x1f\xb1\xa4\xd6\xc5\x96\xec"
+			  "\xf7\x84\x85\xc7\x27\x0f\x74\x57"
+			  "\x28\x9e\xdd\x90\x3c\x43\x12\xc5"
+			  "\x51\x3d\x39\x8f\xa5\xf4\xe0\x0b"
+			  "\x57\x04\xf1\x6d\xfe\x9b\x84\x27"
+			  "\xe8\xeb\x4d\xda\x02\x0a\xc5\x49"
+			  "\x1a\x55\x5e\x50\x56\x4d\x94\xda"
+			  "\x20\xf8\x12\x54\x50\xb3\x11\xda"
+			  "\xed\x44\x27\x67\xd5\xd1\x8b\x4b"
+			  "\x38\x67\x56\x65\x59\xda\xe6\x97"
+			  "\x81\xae\x2f\x92\x3b\xae\x22\x1c"
+			  "\x91\x59\x38\x18\x00\xe8\xba\x92"
+			  "\x04\x19\x56\xdf\xb0\x82\xeb\x6f"
+			  "\x2e\xdb\x54\x3c\x4b\xbb\x60\x90"
+			  "\x4c\x50\x10\x62\xba\x7a\xb1\x68"
+			  "\x37\xd7\x87\x4e\xe4\x66\x09\x1f"
+			  "\xa5",
+		.rlen	= 145,
+	}, {
+		.key	= "\xa3\x73\x24\x01\xd5\xbc\xaa\xe3"
+			  "\xa9\x5a\x4c\x90\xf0\x65\x37\x18"
+			  "\x72\x28\x0a\x40\xe7\x20\xd9\x82"
+			  "\xfe\x02\x2b\x09\x57\xb3\xfe\xb7",
+		.klen	= 32,
+		.iv	= "\xb3\x3d\xb3\x69\x19\x5b\x54\x6a"
+			  "\xc9\x91\x79\xb4\xef\x2e\x68\x99",
+		.assoc	= "\xc2\x06\x41\xd1\x5d\xfa\xff\xf1"
+			  "\xe9\xc7\xa5\xd9\xed\xf8\x98\x1b"
+			  "\x07\x89\x10\x82\x6a\x70\x9a\x8f"
+			  "\x5e\x19\x9b\xf5\xc5\xe3\xcd\x22"
+			  "\x92\xa5\xc2\xb8\x51\x2e\x5e\x0e"
+			  "\xa4\xbe\x5f\xb1\xc1\x90\xd7\xe7"
+			  "\xf7\x52\xae\x28\x29\xa8\x22\xa4"
+			  "\x4f\xae\x48\xc2\xfa\x75\x8b\x9e"
+			  "\xce\x83\x2a\x88\x07\x55\xbb\x89"
+			  "\xf6\xdf\xac\xdf\x83\x08\xbf\x7d"
+			  "\xac\x30\x8b\x8e\x02\xac\x00\xf1"
+			  "\x30\x46\xe1\xbc\x75\xbf\x49\xbb"
+			  "\x26\x4e\x29\xf0\x2f\x21\xc6\x13"
+			  "\x92\xd9\x3d\x11\xe4\x10\x00\x8e"
+			  "\xd4\xd4\x58\x65\xa6\x2b\xe3\x25"
+			  "\xb1\x8f\x15\x93\xe7\x71\xb9\x2c"
+			  "\x4b",
+		.alen	= 129,
+		.input	= "\xd1\xcf\xd0\x39\xa1\x99\xa9\x78"
+			  "\x09\xfe\xd2\xfd\xec\xc1\xc9\x9d"
+			  "\xd2\x39\x93\xa3\xab\x18\x7a\x95"
+			  "\x8f\x24\xd3\xeb\x7b\xfa\xb5\xd8"
+			  "\x15\xd1\xc3\x04\x69\x32\xe3\x4d"
+			  "\xaa\xc2\x04\x8b\xf2\xfa\xdc\x4a"
+			  "\x02\xeb\xa8\x90\x03\xfd\xea\x97"
+			  "\x43\xaf\x2e\x92\xf8\x57\xc5\x6a"
+			  "\x00",
+		.ilen	= 65,
+		.result	= "\x7d\xde\x53\x22\xe4\x23\x3b\x30"
+			  "\x78\xde\x35\x90\x7a\xd9\x0b\x93"
+			  "\xf6\x0e\x0b\xed\x40\xee\x10\x9c"
+			  "\x96\x3a\xd3\x34\xb2\xd0\x67\xcf"
+			  "\x63\x7f\x2d\x0c\xcf\x96\xec\x64"
+			  "\x1a\x87\xcc\x7d\x2c\x5e\x81\x4b"
+			  "\xd2\x8f\x4c\x7c\x00\xb1\xb4\xe0"
+			  "\x87\x4d\xb1\xbc\xd8\x78\x2c\x17"
+			  "\xf2\x3b\xd8\x28\x40\xe2\x76\xf6"
+			  "\x20\x13\x83\x46\xaf\xff\xe3\x0f"
+			  "\x72",
+		.rlen	= 81,
+	}, {
+		.key	= "\xe0\x98\x5e\xa1\xe5\x38\x53\xff"
+			  "\x2a\x35\xfe\x21\xea\x8a\xfa\x1e"
+			  "\x9c\xea\x15\xc5\xec\xc0\x5b\x9b"
+			  "\xbf\x2f\x0a\xe1\x32\x12\x9d\x8e",
+		.klen	= 32,
+		.iv	= "\xef\x61\xed\x08\x29\xd7\xfd\x86"
+			  "\x4a\x6b\x2b\x46\xe9\x53\x2a\xa0",
+		.assoc	= "\xfe\x2a\x7b\x70\x6d\x75\xa7\x0d"
+			  "\x6a\xa2\x57\x6a\xe7\x1c\x5b\x21"
+			  "\x31\x4b\x1b\x07\x6f\x10\x1c\xa8"
+			  "\x20\x46\x7a\xce\x9f\x42\x6d\xf9",
+		.alen	= 32,
+		.input	= "\x0d\xf4\x09\xd8\xb1\x14\x51\x94"
+			  "\x8a\xd8\x84\x8e\xe6\xe5\x8c\xa3"
+			  "\xfc\xfc\x9e\x28\xb0\xb8\xfc\xaf"
+			  "\x50\x52\xb1\xc4\x55\x59\x55\xaf",
+		.ilen	= 32,
+		.result	= "\x5a\xcd\x8c\x57\xf2\x6a\xb6\xbe"
+			  "\x53\xc7\xaa\x9a\x60\x74\x9c\xc4"
+			  "\xa2\xc2\xd0\x6d\xe1\x03\x63\xdc"
+			  "\xbb\x51\x7e\x9c\x89\x73\xde\x4e"
+			  "\x24\xf8\x52\x7c\x15\x41\x0e\xba"
+			  "\x69\x0e\x36\x5f\x2f\x22\x8c",
+		.rlen	= 47,
+	}, {
+		.key	= "\x1c\xbd\x98\x40\xf5\xb3\xfc\x1b"
+			  "\xaa\x0f\xb0\xb3\xe4\xae\xbc\x24"
+			  "\xc7\xac\x21\x49\xf1\x60\xdd\xb5"
+			  "\x80\x5d\xe9\xba\x0c\x71\x3c\x64",
+		.klen	= 32,
+		.iv	= "\x2c\x86\x26\xa8\x39\x52\xa6\xa2"
+			  "\xcb\x45\xdd\xd7\xe3\x77\xed\xa6",
+		.assoc	= "\x3b\x4f\xb5\x10\x7d\xf1\x50\x29"
+			  "\xeb\x7c\x0a\xfb\xe1\x40\x1e\x27"
+			  "\x5c\x0d\x27\x8b\x74\xb0\x9e\xc2"
+			  "\xe1\x74\x59\xa6\x79\xa1\x0c\xd0",
+		.alen	= 32,
+		.input	= "\x4a\x18\x43\x77\xc1\x90\xfa\xb0"
+			  "\x0b\xb2\x36\x20\xe0\x09\x4e\xa9"
+			  "\x26\xbe\xaa\xac\xb5\x58\x7e\xc8"
+			  "\x11\x7f\x90\x9c\x2f\xb8\xf4\x85",
+		.ilen	= 32,
+		.result	= "\x47\xd6\xce\x78\xd6\xbf\x4a\x51"
+			  "\xb8\xda\x92\x3c\xfd\xda\xac\x8e"
+			  "\x8d\x88\xd7\x4d\x90\xe5\xeb\xa1"
+			  "\xab\xd6\x7c\x76\xad\xea\x7d\x76"
+			  "\x53\xee\xb0\xcd\xd0\x02\xbb\x70"
+			  "\x5b\x6f\x7b\xe2\x8c\xe8",
+		.rlen	= 46,
+	}, {
+		.key	= "\x59\xe1\xd2\xdf\x05\x2f\xa4\x37"
+			  "\x2b\xe9\x63\x44\xde\xd3\x7f\x2b"
+			  "\xf1\x6f\x2d\xcd\xf6\x00\x5f\xcf"
+			  "\x42\x8a\xc8\x92\xe6\xd0\xdc\x3b",
+		.klen	= 32,
+		.iv	= "\x68\xab\x60\x47\x49\xce\x4f\xbe"
+			  "\x4c\x20\x8f\x68\xdd\x9c\xb0\xac",
+		.assoc	= "\x77\x74\xee\xaf\x8d\x6d\xf9\x45"
+			  "\x6c\x56\xbc\x8d\xdb\x65\xe0\x2e"
+			  "\x86\xd0\x32\x0f\x79\x50\x20\xdb"
+			  "\xa2\xa1\x37\x7e\x53\x00\xab\xa6",
+		.alen	= 32,
+		.input	= "\x86\x3d\x7d\x17\xd1\x0c\xa3\xcc"
+			  "\x8c\x8d\xe8\xb1\xda\x2e\x11\xaf"
+			  "\x51\x80\xb5\x30\xba\xf8\x00\xe2"
+			  "\xd3\xad\x6f\x75\x09\x18\x93\x5c",
+		.ilen	= 32,
+		.result	= "\x9f\xa9\x2b\xa4\x8f\x00\x05\x2b"
+			  "\xe7\x68\x81\x51\xbb\xfb\xdf\x60"
+			  "\xbb\xac\xe8\xc1\xdc\x68\xae\x68"
+			  "\x3a\xcd\x7a\x06\x49\xfe\x80\x11"
+			  "\xe6\x61\x99\xe2\xdd\xbe\x2c\xbf",
+		.rlen	= 40,
+	}, {
+		.key	= "\x96\x06\x0b\x7f\x15\xab\x4d\x53"
+			  "\xac\xc3\x15\xd6\xd8\xf7\x42\x31"
+			  "\x1b\x31\x38\x51\xfc\xa0\xe1\xe8"
+			  "\x03\xb8\xa7\x6b\xc0\x2f\x7b\x11",
+		.klen	= 32,
+		.iv	= "\xa5\xcf\x9a\xe6\x59\x4a\xf7\xd9"
+			  "\xcd\xfa\x41\xfa\xd7\xc0\x72\xb2",
+		.assoc	= "\xb4\x99\x28\x4e\x9d\xe8\xa2\x60"
+			  "\xed\x30\x6e\x1e\xd5\x89\xa3\x34"
+			  "\xb1\x92\x3e\x93\x7e\xf0\xa2\xf5"
+			  "\x64\xcf\x16\x57\x2d\x5f\x4a\x7d",
+		.alen	= 32,
+		.input	= "\xc3\x62\xb7\xb6\xe2\x87\x4c\xe7"
+			  "\x0d\x67\x9a\x43\xd4\x52\xd4\xb5"
+			  "\x7b\x43\xc1\xb5\xbf\x98\x82\xfc"
+			  "\x94\xda\x4e\x4d\xe4\x77\x32\x32",
+		.ilen	= 32,
+		.result	= "\xe2\x34\xfa\x25\xfd\xfb\x89\x5e"
+			  "\x5b\x4e\x0b\x15\x6e\x39\xfb\x0c"
+			  "\x73\xc7\xd9\x6b\xbe\xce\x9b\x70"
+			  "\xc7\x4f\x96\x16\x03\xfc\xea\xfb"
+			  "\x56",
+		.rlen	= 33,
+	},
+};
+
+static const struct aead_testvec morus1280_dec_tv_template[] = {
+	{
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 16,
+		.iv	= "\x0f\xc9\x8e\x67\x44\x9e\xaa\x86"
+			  "\x20\x36\x2c\x24\xfe\xc9\x30\x81",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x91\x85\x0f\xf5\x52\x9e\xce\xce"
+			  "\x65\x99\xc7\xbf\xd3\x76\xe8\x98",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x3c\x24\x39\x9f\x10\x7b\xa8\x1b"
+			  "\x80\xda\xb2\x91\xf9\x24\xc2\x06",
+		.klen	= 16,
+		.iv	= "\x4b\xed\xc8\x07\x54\x1a\x52\xa2"
+			  "\xa1\x10\xde\xb5\xf8\xed\xf3\x87",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x88\xc3\x4c\xf0\x2f\x43\x76\x13"
+			  "\x96\xda\x76\x34\x33\x4e\xd5\x39"
+			  "\x73",
+		.ilen	= 17,
+		.result	= "\x69",
+		.rlen	= 1,
+	}, {
+		.key	= "\x79\x49\x73\x3e\x20\xf7\x51\x37"
+			  "\x01\xb4\x64\x22\xf3\x48\x85\x0c",
+		.klen	= 16,
+		.iv	= "\x88\x12\x01\xa6\x64\x96\xfb\xbe"
+			  "\x22\xea\x90\x47\xf2\x11\xb5\x8e",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x3e\x5c\x3b\x58\x3b\x7d\x2a\x22"
+			  "\x75\x0b\x24\xa6\x0e\xc3\xde\x52"
+			  "\x97\x0b\x64\xd4\xce\x90\x52\xf7"
+			  "\xef\xdb\x6a\x38\xd2\xa8\xa1\x0d"
+			  "\xe0\x61\x33\x24\xc6\x4d\x51\xbc"
+			  "\xa4\x21\x74\xcf\x19\x16\x59",
+		.ilen	= 47,
+		.result	= "\xa6\xa4\x1e\x76\xec\xd4\x50\xcc"
+			  "\x62\x58\xe9\x8f\xef\xa4\x17\x91"
+			  "\xb4\x96\x9f\x6b\xce\x38\xa5\x46"
+			  "\x13\x7d\x64\x93\xd7\x05\xf5",
+		.rlen	= 31,
+	}, {
+		.key	= "\xb5\x6e\xad\xdd\x30\x72\xfa\x53"
+			  "\x82\x8e\x16\xb4\xed\x6d\x47\x12",
+		.klen	= 16,
+		.iv	= "\xc4\x37\x3b\x45\x74\x11\xa4\xda"
+			  "\xa2\xc5\x42\xd8\xec\x36\x78\x94",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x30\x82\x9c\x2b\x67\xcb\xf9\x1f"
+			  "\xde\x9f\x77\xb2\xda\x92\x61\x5c"
+			  "\x09\x0b\x2d\x9a\x26\xaa\x1c\x06"
+			  "\xab\x74\xb7\x2b\x95\x5f\x9f\xa1"
+			  "\x9a\xff\x50\xa0\xa2\xff\xc5\xad"
+			  "\x21\x8e\x84\x5c\x12\x61\xb2\xae",
+		.ilen	= 48,
+		.result	= "\xe2\xc9\x58\x15\xfc\x4f\xf8\xe8"
+			  "\xe3\x32\x9b\x21\xe9\xc8\xd9\x97"
+			  "\xde\x58\xab\xf0\xd3\xd8\x27\x60"
+			  "\xd5\xaa\x43\x6b\xb1\x64\x95\xa4",
+		.rlen	= 32,
+	}, {
+		.key	= "\xf2\x92\xe6\x7d\x40\xee\xa3\x6f"
+			  "\x03\x68\xc8\x45\xe7\x91\x0a\x18",
+		.klen	= 16,
+		.iv	= "\x01\x5c\x75\xe5\x84\x8d\x4d\xf6"
+			  "\x23\x9f\xf4\x6a\xe6\x5a\x3b\x9a",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x67\x5d\x8e\x45\xc8\x39\xf5\x17"
+			  "\xc1\x1d\x2a\xdd\x88\x67\xda\x1f"
+			  "\x6d\xe8\x37\x28\x5a\xc1\x5e\x9f"
+			  "\xa6\xec\xc6\x92\x05\x4b\xc0\xa3"
+			  "\x63\xef\x88\xa4\x9b\x0a\x5c\xed"
+			  "\x2b\x6a\xac\x63\x52\xaa\x10\x94"
+			  "\xd0",
+		.ilen	= 49,
+		.result	= "\x1f\xee\x92\xb4\x0c\xcb\xa1\x04"
+			  "\x64\x0c\x4d\xb2\xe3\xec\x9c\x9d"
+			  "\x09\x1a\xb7\x74\xd8\x78\xa9\x79"
+			  "\x96\xd8\x22\x43\x8c\xc3\x34\x7b"
+			  "\xc4",
+		.rlen	= 33,
+	}, {
+		.key	= "\x2e\xb7\x20\x1c\x50\x6a\x4b\x8b"
+			  "\x84\x42\x7a\xd7\xe1\xb5\xcd\x1f",
+		.klen	= 16,
+		.iv	= "\x3d\x80\xae\x84\x94\x09\xf6\x12"
+			  "\xa4\x79\xa6\xfb\xe0\x7f\xfd\xa0",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x7d\x61\x1a\x35\x20\xcc\x07\x88"
+			  "\x03\x98\x87\xcf\xc0\x6e\x4d\x19"
+			  "\xe3\xd4\x0b\xfb\x29\x8f\x49\x1a"
+			  "\x3a\x06\x77\xce\x71\x2c\xcd\xdd"
+			  "\xed\xf6\xc9\xbe\xa6\x3b\xb8\xfc"
+			  "\x6c\xbe\x77\xed\x74\x0e\x20\x85"
+			  "\xd0\x65\xde\x24\x6f\xe3\x25\xc5"
+			  "\xdf\x5b\x0f\xbd\x8a\x88\x78\xc9"
+			  "\xe5\x81\x37\xde\x84\x7a\xf6\x84"
+			  "\x99\x7a\x72\x9c\x54\x31\xa1",
+		.ilen	= 79,
+		.result	= "\x5c\x13\xcb\x54\x1c\x47\x4a\x1f"
+			  "\xe5\xe6\xff\x44\xdd\x11\x5f\xa3"
+			  "\x33\xdd\xc2\xf8\xdd\x18\x2b\x93"
+			  "\x57\x05\x01\x1c\x66\x22\xd3\x51"
+			  "\xd3\xdf\x18\xc9\x30\x66\xed\xb1"
+			  "\x96\x58\xd5\x8c\x64\x8c\x7c\xf5"
+			  "\x01\xd0\x74\x5f\x9b\xaa\xf6\xd1"
+			  "\xe6\x16\xa2\xac\xde\x47\x40",
+		.rlen	= 63,
+	}, {
+		.key	= "\x6b\xdc\x5a\xbb\x60\xe5\xf4\xa6"
+			  "\x05\x1d\x2c\x68\xdb\xda\x8f\x25",
+		.klen	= 16,
+		.iv	= "\x7a\xa5\xe8\x23\xa4\x84\x9e\x2d"
+			  "\x25\x53\x58\x8c\xda\xa3\xc0\xa6",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x05\xc5\xb1\xf9\x1b\xb9\xab\x2c"
+			  "\xa5\x07\x12\xa7\x12\x39\x60\x66"
+			  "\x30\x81\x4a\x03\x78\x28\x45\x52"
+			  "\xd2\x2b\x24\xfd\x8b\xa5\xb7\x66"
+			  "\x6f\x45\xd7\x3b\x67\x6f\x51\xb9"
+			  "\xc0\x3d\x6c\xca\x1e\xae\xff\xb6"
+			  "\x79\xa9\xe4\x82\x5d\x4c\x2d\xdf"
+			  "\xeb\x71\x40\xc9\x2c\x40\x45\x6d"
+			  "\x73\x77\x01\xf3\x4f\xf3\x9d\x2a"
+			  "\x5d\x57\xa8\xa1\x18\xa2\xad\xcb",
+		.ilen	= 80,
+		.result	= "\x98\x37\x05\xf3\x2c\xc2\xf3\x3b"
+			  "\x66\xc0\xb1\xd5\xd7\x35\x21\xaa"
+			  "\x5d\x9f\xce\x7c\xe2\xb8\xad\xad"
+			  "\x19\x33\xe0\xf4\x40\x81\x72\x28"
+			  "\xe1\x8b\x1c\xf8\x91\x78\xff\xaf"
+			  "\xb0\x68\x69\xf2\x27\x35\x91\x84"
+			  "\x2e\x37\x5b\x00\x04\xff\x16\x9c"
+			  "\xb5\x19\x39\xeb\xd9\xcd\x29\x9a",
+		.rlen	= 64,
+	}, {
+		.key	= "\xa7\x00\x93\x5b\x70\x61\x9d\xc2"
+			  "\x86\xf7\xde\xfa\xd5\xfe\x52\x2b",
+		.klen	= 16,
+		.iv	= "\xb6\xca\x22\xc3\xb4\x00\x47\x49"
+			  "\xa6\x2d\x0a\x1e\xd4\xc7\x83\xad",
+		.assoc	= "\xc5",
+		.alen	= 1,
+		.input	= "\x4d\xbf\x11\xac\x7f\x97\x0b\x2e"
+			  "\x89\x3b\x9d\x0f\x83\x1c\x08\xc3",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xe4\x25\xcd\xfa\x80\xdd\x46\xde"
+			  "\x07\xd1\x90\x8b\xcf\x23\x15\x31",
+		.klen	= 16,
+		.iv	= "\xf3\xee\x5c\x62\xc4\x7c\xf0\x65"
+			  "\x27\x08\xbd\xaf\xce\xec\x45\xb3",
+		.assoc	= "\x02\xb8\xea\xca\x09\x1b\x9a\xec"
+			  "\x47\x3e\xe9\xd4\xcc\xb5\x76\x34"
+			  "\xe8\x73\x62\x64\xab\x50\xd0\xda"
+			  "\x6b\x83\x66\xaf\x3e\x27\xc9",
+		.alen	= 31,
+		.input	= "\x5b\xc0\x8d\x54\xe4\xec\xbe\x38"
+			  "\x03\x12\xf9\xcc\x9e\x46\x42\x92",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x20\x4a\x07\x99\x91\x58\xee\xfa"
+			  "\x88\xab\x42\x1c\xc9\x47\xd7\x38",
+		.klen	= 16,
+		.iv	= "\x2f\x13\x95\x01\xd5\xf7\x99\x81"
+			  "\xa8\xe2\x6f\x41\xc8\x10\x08\xb9",
+		.assoc	= "\x3f\xdc\x24\x69\x19\x96\x43\x08"
+			  "\xc8\x18\x9b\x65\xc6\xd9\x39\x3b"
+			  "\x12\x35\x6e\xe8\xb0\xf0\x52\xf3"
+			  "\x2d\xb0\x45\x87\x18\x86\x68\xf6",
+		.alen	= 32,
+		.input	= "\x48\xc5\xc3\x4c\x40\x2e\x2f\xc2"
+			  "\x6d\x65\xe0\x67\x9c\x1d\xa0\xf0",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x5d\x6f\x41\x39\xa1\xd4\x97\x16"
+			  "\x09\x85\xf4\xae\xc3\x6b\x9a\x3e",
+		.klen	= 16,
+		.iv	= "\x6c\x38\xcf\xa1\xe5\x73\x41\x9d"
+			  "\x29\xbc\x21\xd2\xc2\x35\xcb\xbf",
+		.assoc	= "\x7b\x01\x5d\x08\x29\x12\xec\x24"
+			  "\x49\xf3\x4d\xf7\xc0\xfe\xfb\x41"
+			  "\x3c\xf8\x79\x6c\xb6\x90\xd4\x0d"
+			  "\xee\xde\x23\x60\xf2\xe5\x08\xcc"
+			  "\x97",
+		.alen	= 33,
+		.input	= "\x28\x64\x78\x51\x55\xd8\x56\x4a"
+			  "\x58\x3e\xf7\xbe\xee\x21\xfe\x94",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x99\x93\x7a\xd8\xb1\x50\x40\x31"
+			  "\x8a\x60\xa6\x3f\xbd\x90\x5d\x44",
+		.klen	= 16,
+		.iv	= "\xa8\x5c\x09\x40\xf5\xef\xea\xb8"
+			  "\xaa\x96\xd3\x64\xbc\x59\x8d\xc6",
+		.assoc	= "\xb8\x26\x97\xa8\x39\x8e\x94\x3f"
+			  "\xca\xcd\xff\x88\xba\x22\xbe\x47"
+			  "\x67\xba\x85\xf1\xbb\x30\x56\x26"
+			  "\xaf\x0b\x02\x38\xcc\x44\xa7\xa3"
+			  "\xa6\xbf\x31\x93\x60\xcd\xda\x63"
+			  "\x2c\xb1\xaa\x19\xc8\x19\xf8\xeb"
+			  "\x03\xa1\xe8\xbe\x37\x54\xec\xa2"
+			  "\xcd\x2c\x45\x58\xbd\x8e\x80",
+		.alen	= 63,
+		.input	= "\xb3\xa6\x00\x4e\x09\x20\xac\x21"
+			  "\x77\x72\x69\x76\x2d\x36\xe5\xc8",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xd6\xb8\xb4\x77\xc1\xcb\xe9\x4d"
+			  "\x0a\x3a\x58\xd1\xb7\xb4\x1f\x4a",
+		.klen	= 16,
+		.iv	= "\xe5\x81\x42\xdf\x05\x6a\x93\xd4"
+			  "\x2b\x70\x85\xf5\xb6\x7d\x50\xcc",
+		.assoc	= "\xf4\x4a\xd1\x47\x49\x09\x3d\x5b"
+			  "\x4b\xa7\xb1\x19\xb4\x46\x81\x4d"
+			  "\x91\x7c\x91\x75\xc0\xd0\xd8\x40"
+			  "\x71\x39\xe1\x10\xa6\xa3\x46\x7a"
+			  "\xb4\x6b\x35\xc2\xc1\xdf\xed\x60"
+			  "\x46\xc1\x3e\x7f\x8c\xc2\x0e\x7a"
+			  "\x30\x08\xd0\x5f\xa0\xaa\x0c\x6d"
+			  "\x9c\x2f\xdb\x97\xb8\x15\x69\x01",
+		.alen	= 64,
+		.input	= "\x65\x33\x7b\xa1\x63\xf4\x20\xdd"
+			  "\xe4\xb9\x4a\xaa\x9a\x21\xaa\x14",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x12\xdd\xee\x17\xd1\x47\x92\x69"
+			  "\x8b\x14\x0a\x62\xb1\xd9\xe2\x50",
+		.klen	= 16,
+		.iv	= "\x22\xa6\x7c\x7f\x15\xe6\x3c\xf0"
+			  "\xac\x4b\x37\x86\xb0\xa2\x13\xd2",
+		.assoc	= "\x31",
+		.alen	= 1,
+		.input	= "\x1d\x47\x17\x34\x86\xf5\x54\x1a"
+			  "\x6d\x28\xb8\x5d\x6c\xcf\xa0\xb9"
+			  "\xbf",
+		.ilen	= 17,
+		.result	= "\x40",
+		.rlen	= 1,
+	}, {
+		.key	= "\x4f\x01\x27\xb6\xe1\xc3\x3a\x85"
+			  "\x0c\xee\xbc\xf4\xab\xfd\xa5\x57",
+		.klen	= 16,
+		.iv	= "\x5e\xcb\xb6\x1e\x25\x62\xe4\x0c"
+			  "\x2d\x25\xe9\x18\xaa\xc6\xd5\xd8",
+		.assoc	= "\x6d\x94\x44\x86\x69\x00\x8f\x93"
+			  "\x4d\x5b\x15\x3c\xa8\x8f\x06\x5a"
+			  "\xe6\x01\xa8\x7e\xca\x10\xdc\x73"
+			  "\xf4\x94\x9f\xc1\x5a\x61\x85",
+		.alen	= 31,
+		.input	= "\x78\x90\x52\xae\x0f\xf7\x2e\xef"
+			  "\x63\x09\x08\x58\xb5\x56\xbd\x72"
+			  "\x6e\x42\xcf\x27\x04\x7c\xdb\x92"
+			  "\x18\xe9\xa4\x33\x90\xba\x62\xb5"
+			  "\x70\xd3\x88\x9b\x4f\x05\xa7\x51"
+			  "\x85\x87\x17\x09\x42\xed\x4e",
+		.ilen	= 47,
+		.result	= "\x7c\x5d\xd3\xee\xad\x9f\x39\x1a"
+			  "\x6d\x92\x42\x61\xa7\x58\x37\xdb"
+			  "\xb0\xb2\x2b\x9f\x0b\xb8\xbd\x7a"
+			  "\x24\xa0\xd6\xb7\x11\x79\x6c",
+		.rlen	= 31,
+	}, {
+		.key	= "\x8b\x26\x61\x55\xf1\x3e\xe3\xa1"
+			  "\x8d\xc8\x6e\x85\xa5\x21\x67\x5d",
+		.klen	= 16,
+		.iv	= "\x9b\xef\xf0\xbd\x35\xdd\x8d\x28"
+			  "\xad\xff\x9b\xa9\xa4\xeb\x98\xdf",
+		.assoc	= "\xaa\xb8\x7e\x25\x79\x7c\x37\xaf"
+			  "\xce\x36\xc7\xce\xa2\xb4\xc9\x60"
+			  "\x10\xc3\xb3\x02\xcf\xb0\x5e\x8d"
+			  "\xb5\xc2\x7e\x9a\x35\xc0\x24\xfd",
+		.alen	= 32,
+		.input	= "\x1d\x2c\x57\xe0\x50\x38\x3d\x41"
+			  "\x2e\x71\xc8\x3b\x92\x43\x58\xaf"
+			  "\x5a\xfb\xad\x8f\xd9\xd5\x8a\x5e"
+			  "\xdb\xf3\xcd\x3a\x2b\xe1\x2c\x1a"
+			  "\xb0\xed\xe3\x0c\x6e\xf9\xf2\xd6"
+			  "\x90\xe6\xb1\x0e\xa5\x8a\xac\xb7",
+		.ilen	= 48,
+		.result	= "\xb9\x82\x0c\x8d\xbd\x1b\xe2\x36"
+			  "\xee\x6c\xf4\xf2\xa1\x7d\xf9\xe2"
+			  "\xdb\x74\x36\x23\x11\x58\x3f\x93"
+			  "\xe5\xcd\xb5\x90\xeb\xd8\x0c\xb3",
+		.rlen	= 32,
+	}, {
+		.key	= "\xc8\x4b\x9b\xf5\x01\xba\x8c\xbd"
+			  "\x0e\xa3\x21\x16\x9f\x46\x2a\x63",
+		.klen	= 16,
+		.iv	= "\xd7\x14\x29\x5d\x45\x59\x36\x44"
+			  "\x2e\xd9\x4d\x3b\x9e\x0f\x5b\xe5",
+		.assoc	= "\xe6\xdd\xb8\xc4\x89\xf8\xe0\xca"
+			  "\x4f\x10\x7a\x5f\x9c\xd8\x8b\x66"
+			  "\x3b\x86\xbf\x86\xd4\x50\xe0\xa7"
+			  "\x76\xef\x5c\x72\x0f\x1f\xc3\xd4"
+			  "\xee",
+		.alen	= 33,
+		.input	= "\x59\x10\x84\x1c\x83\x4c\x8b\xfc"
+			  "\xfd\x2e\x4b\x46\x84\xff\x78\x4e"
+			  "\x50\xda\x5c\xb9\x61\x1d\xf5\xb9"
+			  "\xfe\xbb\x7f\xae\x8c\xc1\x24\xbd"
+			  "\x8c\x6f\x1f\x9b\xce\xc6\xc1\x37"
+			  "\x08\x06\x5a\xe5\x96\x10\x95\xc2"
+			  "\x5e",
+		.ilen	= 49,
+		.result	= "\xf5\xa6\x46\x2c\xce\x97\x8a\x51"
+			  "\x6f\x46\xa6\x83\x9b\xa1\xbc\xe8"
+			  "\x05\x36\x42\xa7\x16\xf8\xc1\xad"
+			  "\xa7\xfb\x94\x68\xc5\x37\xab\x8a"
+			  "\x72",
+		.rlen	= 33,
+	}, {
+		.key	= "\x05\x70\xd5\x94\x12\x36\x35\xd8"
+			  "\x8f\x7d\xd3\xa8\x99\x6a\xed\x69",
+		.klen	= 16,
+		.iv	= "\x14\x39\x63\xfc\x56\xd5\xdf\x5f"
+			  "\xaf\xb3\xff\xcc\x98\x33\x1d\xeb",
+		.assoc	= "\x23\x02\xf1\x64\x9a\x73\x89\xe6"
+			  "\xd0\xea\x2c\xf1\x96\xfc\x4e\x6d"
+			  "\x65\x48\xcb\x0a\xda\xf0\x62\xc0"
+			  "\x38\x1d\x3b\x4a\xe9\x7e\x62\xaa"
+			  "\xfd\xc9\x4a\xa9\xa9\x39\x4b\x54"
+			  "\xc8\x0e\x24\x7f\x5e\x10\x7a\x45"
+			  "\x10\x0b\x56\x85\xad\x54\xaa\x66"
+			  "\xa8\x43\xcd\xd4\x9b\xb7\xfa",
+		.alen	= 63,
+		.input	= "\x9a\x12\xbc\xdf\x72\xa8\x56\x22"
+			  "\x49\x2d\x07\x92\xfc\x3d\x6d\x5f"
+			  "\xef\x36\x19\xae\x91\xfa\xd6\x63"
+			  "\x46\xea\x8a\x39\x14\x21\xa6\x37"
+			  "\x18\xfc\x97\x3e\x16\xa5\x4d\x39"
+			  "\x45\x2e\x69\xcc\x9c\x5f\xdf\x6d"
+			  "\x5e\xa2\xbf\xac\x83\x32\x72\x52"
+			  "\x58\x58\x23\x40\xfd\xa5\xc2\xe6"
+			  "\xe9\x5a\x50\x98\x00\x58\xc9\x86"
+			  "\x4f\x20\x37\xdb\x7b\x22\xa3",
+		.ilen	= 79,
+		.result	= "\x32\xcb\x80\xcc\xde\x12\x33\x6d"
+			  "\xf0\x20\x58\x15\x95\xc6\x7f\xee"
+			  "\x2f\xf9\x4e\x2c\x1b\x98\x43\xc7"
+			  "\x68\x28\x73\x40\x9f\x96\x4a\x60"
+			  "\x80\xf4\x4b\xf4\xc1\x3d\xd0\x93"
+			  "\xcf\x12\xc9\x59\x8f\x7a\x7f\xa8"
+			  "\x1b\xa5\x50\xed\x87\xa9\x72\x59"
+			  "\x9c\x44\xb2\xa4\x99\x98\x34",
+		.rlen	= 63,
+	}, {
+		.key	= "\x41\x94\x0e\x33\x22\xb1\xdd\xf4"
+			  "\x10\x57\x85\x39\x93\x8f\xaf\x70",
+		.klen	= 16,
+		.iv	= "\x50\x5d\x9d\x9b\x66\x50\x88\x7b"
+			  "\x30\x8e\xb1\x5e\x92\x58\xe0\xf1",
+		.assoc	= "\x5f\x27\x2b\x03\xaa\xef\x32\x02"
+			  "\x50\xc4\xde\x82\x90\x21\x11\x73"
+			  "\x8f\x0a\xd6\x8f\xdf\x90\xe4\xda"
+			  "\xf9\x4a\x1a\x23\xc3\xdd\x02\x81"
+			  "\x0b\x76\x4f\xd7\x0a\x4b\x5e\x51"
+			  "\xe3\x1d\xb9\xe5\x21\xb9\x8f\xd4"
+			  "\x3d\x72\x3e\x26\x16\xa9\xca\x32"
+			  "\x77\x47\x63\x14\x95\x3d\xe4\x34",
+		.alen	= 64,
+		.input	= "\xe6\xeb\x92\x5a\x5b\xf0\x2d\xbb"
+			  "\x23\xec\x35\xe3\xae\xc9\xfb\x0b"
+			  "\x90\x14\x46\xeb\xa8\x8d\xb0\x9b"
+			  "\x39\xda\x8b\x48\xec\xb2\x00\x4e"
+			  "\x80\x6f\x46\x4f\x9b\x1e\xbb\x35"
+			  "\xea\x5a\xbc\xa2\x36\xa5\x89\x45"
+			  "\xc2\xd6\xd7\x15\x0b\xf6\x6c\x56"
+			  "\xec\x99\x7d\x61\xb3\x15\x93\xed"
+			  "\x83\x1e\xd9\x48\x84\x0b\x37\xfe"
+			  "\x95\x74\x44\xd5\x54\xa6\x27\x06",
+		.ilen	= 80,
+		.result	= "\x6e\xf0\xba\x6b\xee\x8e\xdc\x89"
+			  "\x71\xfb\x0a\xa6\x8f\xea\x41\xf4"
+			  "\x5a\xbb\x59\xb0\x20\x38\xc5\xe0"
+			  "\x29\x56\x52\x19\x79\xf5\xe9\x37"
+			  "\x8f\xa1\x50\x23\x22\x4f\xe3\x91"
+			  "\xe9\x21\x5e\xbf\x52\x23\x95\x37"
+			  "\x48\x0c\x38\x8f\xf0\xff\x92\x24"
+			  "\x6b\x47\x49\xe3\x94\x1f\x1e\x01",
+		.rlen	= 64,
+	}, {
+		.key	= "\x7e\xb9\x48\xd3\x32\x2d\x86\x10"
+			  "\x91\x31\x37\xcb\x8d\xb3\x72\x76",
+		.klen	= 16,
+		.iv	= "\x8d\x82\xd6\x3b\x76\xcc\x30\x97"
+			  "\xb1\x68\x63\xef\x8c\x7c\xa3\xf7",
+		.assoc	= "\x9c\x4b\x65\xa2\xba\x6b\xdb\x1e"
+			  "\xd1\x9e\x90\x13\x8a\x45\xd3\x79"
+			  "\xba\xcd\xe2\x13\xe4\x30\x66\xf4"
+			  "\xba\x78\xf9\xfb\x9d\x3c\xa1\x58"
+			  "\x1a\x22\x53\x05\x6b\x5c\x71\x4f"
+			  "\xfd\x2d\x4d\x4c\xe5\x62\xa5\x63"
+			  "\x6a\xda\x26\xc8\x7f\xff\xea\xfd"
+			  "\x46\x4a\xfa\x53\x8f\xc4\xcd\x68"
+			  "\x58",
+		.alen	= 65,
+		.input	= "\x89\x24\x27\x86\xdc\xd7\x6b\xd9"
+			  "\xd1\xcd\xdc\x16\xdd\x2c\xc1\xfb"
+			  "\x52\xb5\xb3\xab\x50\x99\x3f\xa0"
+			  "\x38\xa4\x74\xa5\x04\x15\x63\x05"
+			  "\x8f\x54\x81\x06\x5a\x6b\xa4\x63"
+			  "\x6d\xa7\x21\xcb\xff\x42\x30\x8e"
+			  "\x3b\xd1\xca\x3f\x4b\x1a\xb8\xc3"
+			  "\x42\x01\xe6\xbc\x75\x15\x87\xee"
+			  "\xc9\x8e\x65\x01\xd9\xd8\xb5\x9f"
+			  "\x48\x86\xa6\x5f\x2c\xc7\xb5\xb0"
+			  "\xed\x5d\x14\x7c\x3f\x40\xb1\x0b"
+			  "\x72\xef\x94\x8d\x7a\x85\x56\xe5"
+			  "\x56\x08\x15\x56\xba\xaf\xbd\xf0"
+			  "\x20\xef\xa0\xf6\xa9\xad\xa2\xc9"
+			  "\x1c\x3b\x28\x51\x7e\x77\xb2\x18"
+			  "\x4f\x61\x64\x37\x22\x36\x6d\x78"
+			  "\xed\xed\x35\xe8\x83\xa5\xec\x25"
+			  "\x6b\xff\x5f\x1a\x09\x96\x3d\xdc"
+			  "\x20",
+		.ilen	= 145,
+		.result	= "\xab\x14\xf3\x0a\xfe\x0a\x85\xa5"
+			  "\xf2\xd5\xbc\x38\x89\x0e\x04\xfb"
+			  "\x84\x7d\x65\x34\x25\xd8\x47\xfa"
+			  "\xeb\x83\x31\xf1\x54\x54\x89\x0d"
+			  "\x9d\x4d\x54\x51\x84\x61\xf6\x8e"
+			  "\x03\x31\xf2\x25\x16\xcc\xaa\xc6"
+			  "\x75\x73\x20\x30\x59\x54\xb2\xf0"
+			  "\x3a\x4b\xe0\x23\x8e\xa6\x08\x35"
+			  "\x8a\xdf\x27\xa0\xe4\x60\x99\xae"
+			  "\x8e\x43\xd9\x39\x7b\x10\x40\x67"
+			  "\x5c\x7e\xc9\x70\x63\x34\xca\x59"
+			  "\xfe\x86\xbc\xb7\x9c\x39\xf3\x6d"
+			  "\x6a\x41\x64\x6f\x16\x7f\x65\x7e"
+			  "\x89\x84\x68\xeb\xb0\x51\xbe\x55"
+			  "\x33\x16\x59\x6c\x3b\xef\x88\xad"
+			  "\x2f\xab\xbc\x25\x76\x87\x41\x2f"
+			  "\x36",
+		.rlen	= 129,
+	}, {
+		.key	= "\xba\xde\x82\x72\x42\xa9\x2f\x2c"
+			  "\x12\x0b\xe9\x5c\x87\xd7\x35\x7c",
+		.klen	= 16,
+		.iv	= "\xc9\xa7\x10\xda\x86\x48\xd9\xb3"
+			  "\x32\x42\x15\x80\x85\xa1\x65\xfe",
+		.assoc	= "\xd8\x70\x9f\x42\xca\xe6\x83\x3a"
+			  "\x52\x79\x42\xa5\x84\x6a\x96\x7f"
+			  "\xe4\x8f\xed\x97\xe9\xd0\xe8\x0d"
+			  "\x7c\xa6\xd8\xd4\x77\x9b\x40\x2e"
+			  "\x28\xce\x57\x34\xcd\x6e\x84\x4c"
+			  "\x17\x3c\xe1\xb2\xa8\x0b\xbb\xf1"
+			  "\x96\x41\x0d\x69\xe8\x54\x0a\xc8"
+			  "\x15\x4e\x91\x92\x89\x4b\xb7\x9b"
+			  "\x21\xf7\x42\x89\xac\x12\x2a\x54"
+			  "\x69\xee\x18\xc7\x8d\xed\xe8\xfd"
+			  "\xbb\x04\x28\xe6\x8a\x3c\x98\xc1"
+			  "\x04\x2d\xa9\xa1\x24\x83\xff\xe9"
+			  "\x55\x7a\xf0\xd1\xf6\x63\x05\xe1"
+			  "\xd9\x1e\x75\x72\xc1\x9f\xae\x32"
+			  "\xe1\x6b\xcd\x9e\x61\x19\x23\x86"
+			  "\xd9\xd2\xaf\x8e\xd5\xd3\xa8\xa9"
+			  "\x51",
+		.alen	= 129,
+		.input	= "\x36\x78\xb9\x22\xde\x62\x35\x55"
+			  "\x1a\x7a\xf5\x45\xbc\xd7\x15\x82"
+			  "\x01\xe9\x5a\x07\xea\x46\xaf\x91"
+			  "\xcb\x73\xa5\xee\xe1\xb4\xbf\xc2"
+			  "\xdb\xd2\x9d\x59\xde\xfc\x83\x00"
+			  "\xf5\x46\xac\x97\xd5\x57\xa9\xb9"
+			  "\x1f\x8c\xe8\xca\x68\x8b\x91\x0c"
+			  "\x01\xbe\x0a\xaf\x7c\xf6\x67\xa4"
+			  "\xbf\xbc\x88\x3f\x5d\xd1\xf9\x19"
+			  "\x0f\x9d\xb2\xaf\xb9\x6e\x17\xdf"
+			  "\xa2",
+		.ilen	= 81,
+		.result	= "\xe8\x39\x2d\xaa\x0e\x85\x2d\xc1"
+			  "\x72\xaf\x6e\xc9\x82\x33\xc7\x01"
+			  "\xaf\x40\x70\xb8\x2a\x78\xc9\x14"
+			  "\xac\xb1\x10\xca\x2e\xb3\x28\xe4"
+			  "\xac\xfa\x58\x7f\xe5\x73\x09\x8c"
+			  "\x1d\x40\x87\x8c\xd9\x75\xc0\x55"
+			  "\xa2\xda\x07\xd1\xc2\xa9\xd1\xbb"
+			  "\x09\x4f\x77\x62\x88\x2d\xf2\x68"
+			  "\x54",
+		.rlen	= 65,
+	}, {
+		.key	= "\xf7\x02\xbb\x11\x52\x24\xd8\x48"
+			  "\x93\xe6\x9b\xee\x81\xfc\xf7\x82",
+		.klen	= 16,
+		.iv	= "\x06\xcc\x4a\x79\x96\xc3\x82\xcf"
+			  "\xb3\x1c\xc7\x12\x7f\xc5\x28\x04",
+		.assoc	= "\x15\x95\xd8\xe1\xda\x62\x2c\x56"
+			  "\xd3\x53\xf4\x36\x7e\x8e\x59\x85"
+			  "\x0e\x51\xf9\x1c\xee\x70\x6a\x27"
+			  "\x3d\xd3\xb7\xac\x51\xfa\xdf\x05",
+		.alen	= 32,
+		.input	= "\x08\x1b\x95\x0e\x41\x95\x02\x4b"
+			  "\x9c\xbb\xa8\xd0\x7c\xd3\x44\x6e"
+			  "\x89\x14\x33\x70\x0a\xbc\xea\x39"
+			  "\x88\xaa\x2b\xd5\x73\x11\x55\xf5"
+			  "\x33\x33\x9c\xd7\x42\x34\x49\x8e"
+			  "\x2f\x03\x30\x05\x47\xaf\x34",
+		.ilen	= 47,
+		.result	= "\x24\x5e\x67\x49\x1e\x01\xd6\xdd"
+			  "\xf3\x89\x20\x5b\x7c\x57\x89\x07"
+			  "\xd9\x02\x7c\x3d\x2f\x18\x4b\x2d"
+			  "\x6e\xde\xee\xa2\x08\x12\xc7\xba",
+		.rlen	= 32,
+	}, {
+		.key	= "\x33\x27\xf5\xb1\x62\xa0\x80\x63"
+			  "\x14\xc0\x4d\x7f\x7b\x20\xba\x89",
+		.klen	= 16,
+		.iv	= "\x42\xf0\x84\x19\xa6\x3f\x2b\xea"
+			  "\x34\xf6\x79\xa3\x79\xe9\xeb\x0a",
+		.assoc	= "\x51\xb9\x12\x80\xea\xde\xd5\x71"
+			  "\x54\x2d\xa6\xc8\x78\xb2\x1b\x8c"
+			  "\x39\x14\x05\xa0\xf3\x10\xec\x41"
+			  "\xff\x01\x95\x84\x2b\x59\x7f\xdb",
+		.alen	= 32,
+		.input	= "\x97\xca\xf4\xe0\x8d\x89\xbf\x68"
+			  "\x0c\x60\xb9\x27\xdf\xaa\x41\xc6"
+			  "\x25\xd8\xf7\x1f\x10\x15\x48\x61"
+			  "\x4c\x95\x00\xdf\x51\x9b\x7f\xe6"
+			  "\x24\x40\x9e\xbe\x3b\xeb\x1b\x98"
+			  "\xb9\x9c\xe5\xef\xf2\x05",
+		.ilen	= 46,
+		.result	= "\x61\x83\xa0\xe8\x2e\x7d\x7f\xf8"
+			  "\x74\x63\xd2\xec\x76\x7c\x4c\x0d"
+			  "\x03\xc4\x88\xc1\x35\xb8\xcd\x47"
+			  "\x2f\x0c\xcd\x7a\xe2\x71\x66\x91",
+		.rlen	= 32,
+	}, {
+		.key	= "\x70\x4c\x2f\x50\x72\x1c\x29\x7f"
+			  "\x95\x9a\xff\x10\x75\x45\x7d\x8f",
+		.klen	= 16,
+		.iv	= "\x7f\x15\xbd\xb8\xb6\xba\xd3\x06"
+			  "\xb5\xd1\x2b\x35\x73\x0e\xad\x10",
+		.assoc	= "\x8e\xde\x4c\x20\xfa\x59\x7e\x8d"
+			  "\xd5\x07\x58\x59\x72\xd7\xde\x92"
+			  "\x63\xd6\x10\x24\xf8\xb0\x6e\x5a"
+			  "\xc0\x2e\x74\x5d\x06\xb8\x1e\xb2",
+		.alen	= 32,
+		.input	= "\x63\x4c\x2a\x8e\xb4\x6b\x63\x0d"
+			  "\xb5\xec\x9b\x4e\x12\x23\xa3\xcf"
+			  "\x1a\x5a\x70\x15\x5a\x10\x40\x51"
+			  "\xca\x47\x4c\x9d\xc9\x97\xf4\x77"
+			  "\xdb\xc8\x10\x2d\xdc\x65\x20\x3f",
+		.ilen	= 40,
+		.result	= "\x9d\xa7\xda\x88\x3e\xf8\x28\x14"
+			  "\xf5\x3e\x85\x7d\x70\xa0\x0f\x13"
+			  "\x2e\x86\x93\x45\x3a\x58\x4f\x61"
+			  "\xf0\x3a\xac\x53\xbc\xd0\x06\x68",
+		.rlen	= 32,
+	}, {
+		.key	= "\xac\x70\x69\xef\x82\x97\xd2\x9b"
+			  "\x15\x74\xb1\xa2\x6f\x69\x3f\x95",
+		.klen	= 16,
+		.iv	= "\xbb\x3a\xf7\x57\xc6\x36\x7c\x22"
+			  "\x36\xab\xde\xc6\x6d\x32\x70\x17",
+		.assoc	= "\xcb\x03\x85\xbf\x0a\xd5\x26\xa9"
+			  "\x56\xe1\x0a\xeb\x6c\xfb\xa1\x98"
+			  "\x8d\x98\x1c\xa8\xfe\x50\xf0\x74"
+			  "\x81\x5c\x53\x35\xe0\x17\xbd\x88",
+		.alen	= 32,
+		.input	= "\xf1\x62\x44\xc7\x5f\x19\xca\x43"
+			  "\x47\x2c\xaf\x68\x82\xbd\x51\xef"
+			  "\x3d\x65\xd8\x45\x2d\x06\x07\x78"
+			  "\x08\x2e\xb3\x23\xcd\x81\x12\x55"
+			  "\x1a",
+		.ilen	= 33,
+		.result	= "\xda\xcc\x14\x27\x4e\x74\xd1\x30"
+			  "\x76\x18\x37\x0f\x6a\xc4\xd1\x1a"
+			  "\x58\x49\x9f\xc9\x3f\xf8\xd1\x7a"
+			  "\xb2\x67\x8b\x2b\x96\x2f\xa5\x3e",
+		.rlen	= 32,
+	}, {
+		.key	= "\xe9\x95\xa2\x8f\x93\x13\x7b\xb7"
+			  "\x96\x4e\x63\x33\x69\x8d\x02\x9b"
+			  "\x23\xf9\x22\xeb\x80\xa0\xb1\x81"
+			  "\xe2\x73\xc3\x21\x4d\x47\x8d\xf4",
+		.klen	= 32,
+		.iv	= "\xf8\x5e\x31\xf7\xd7\xb2\x25\x3e"
+			  "\xb7\x85\x90\x58\x67\x57\x33\x1d",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xdf\x2f\x83\xc0\x45\x4a\x2c\xcf"
+			  "\xb9\xd2\x41\xf6\x80\xa1\x52\x70",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x25\xba\xdc\x2e\xa3\x8f\x24\xd3"
+			  "\x17\x29\x15\xc5\x63\xb2\xc5\xa1"
+			  "\x4d\xbc\x2d\x6f\x85\x40\x33\x9a"
+			  "\xa3\xa0\xa1\xfa\x27\xa6\x2c\xca",
+		.klen	= 32,
+		.iv	= "\x34\x83\x6a\x96\xe7\x2d\xce\x5a"
+			  "\x38\x5f\x42\xe9\x61\x7b\xf5\x23",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x01\xd8\x55\x3c\xc0\x5a\x4b\xc7"
+			  "\x01\xf4\x08\xe3\x0d\xf7\xf0\x78"
+			  "\x53",
+		.ilen	= 17,
+		.result	= "\x53",
+		.rlen	= 1,
+	}, {
+		.key	= "\x62\xdf\x16\xcd\xb3\x0a\xcc\xef"
+			  "\x98\x03\xc7\x56\x5d\xd6\x87\xa8"
+			  "\x77\x7e\x39\xf3\x8a\xe0\xb5\xb4"
+			  "\x65\xce\x80\xd2\x01\x05\xcb\xa1",
+		.klen	= 32,
+		.iv	= "\x71\xa8\xa4\x35\xf7\xa9\x76\x75"
+			  "\xb8\x39\xf4\x7a\x5b\x9f\xb8\x29",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xc2\x4b\x41\x0f\x2d\xb9\x62\x07"
+			  "\xff\x8e\x74\xf8\xa1\xa6\xd5\x37"
+			  "\xa5\x64\x31\x5c\xca\x73\x9b\x43"
+			  "\xe6\x70\x63\x46\x95\xcb\xf7\xb5"
+			  "\x20\x8c\x75\x7a\x2a\x17\x2f\xa9"
+			  "\xb8\x4d\x11\x42\xd1\xf8\xf1",
+		.ilen	= 47,
+		.result	= "\x8f\x3a\xc1\x05\x7f\xe7\xcb\x83"
+			  "\xf9\xa6\x4d\xc3\x58\x31\x19\x2c"
+			  "\xd7\x90\xc2\x56\x4e\xd8\x57\xc7"
+			  "\xf6\xf0\x27\xb4\x25\x4c\x83",
+		.rlen	= 31,
+	}, {
+		.key	= "\x9e\x03\x4f\x6d\xc3\x86\x75\x0a"
+			  "\x19\xdd\x79\xe8\x57\xfb\x4a\xae"
+			  "\xa2\x40\x45\x77\x90\x80\x37\xce"
+			  "\x26\xfb\x5f\xaa\xdb\x64\x6b\x77",
+		.klen	= 32,
+		.iv	= "\xae\xcc\xde\xd5\x07\x25\x1f\x91"
+			  "\x39\x14\xa6\x0c\x55\xc4\x7b\x30",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xbb\x01\x7c\xd1\x2c\x33\x7b\x37"
+			  "\x0a\xee\xc4\x30\x19\xd7\x3a\x6f"
+			  "\xf8\x2b\x67\xf5\x3b\x84\x87\x2a"
+			  "\xfb\x07\x7a\x82\xb5\xe4\x85\x26"
+			  "\x1e\xa8\xe5\x04\x54\xce\xe5\x5f"
+			  "\xb5\x3f\xc1\xd5\x7f\xbd\xd2\xa6",
+		.ilen	= 48,
+		.result	= "\xcc\x5f\xfb\xa4\x8f\x63\x74\x9f"
+			  "\x7a\x81\xff\x55\x52\x56\xdc\x33"
+			  "\x01\x52\xcd\xdb\x53\x78\xd9\xe1"
+			  "\xb7\x1d\x06\x8d\xff\xab\x22\x98",
+		.rlen	= 32,
+	}, {
+		.key	= "\xdb\x28\x89\x0c\xd3\x01\x1e\x26"
+			  "\x9a\xb7\x2b\x79\x51\x1f\x0d\xb4"
+			  "\xcc\x03\x50\xfc\x95\x20\xb9\xe7"
+			  "\xe8\x29\x3e\x83\xb5\xc3\x0a\x4e",
+		.klen	= 32,
+		.iv	= "\xea\xf1\x18\x74\x17\xa0\xc8\xad"
+			  "\xba\xee\x58\x9d\x4f\xe8\x3d\x36",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xc2\xf4\x40\x55\xf9\x59\xff\x73"
+			  "\x08\xf5\x98\x92\x0c\x7b\x35\x9a"
+			  "\xa8\xf4\x42\x7e\x6f\x93\xca\x22"
+			  "\x23\x06\x1e\xf8\x89\x22\xf4\x46"
+			  "\x7c\x7c\x67\x75\xab\xe5\x75\xaa"
+			  "\x15\xd7\x83\x19\xfd\x31\x59\x5b"
+			  "\x32",
+		.ilen	= 49,
+		.result	= "\x08\x84\x34\x44\x9f\xde\x1c\xbb"
+			  "\xfb\x5b\xb1\xe6\x4c\x7a\x9f\x39"
+			  "\x2c\x14\xd9\x5f\x59\x18\x5b\xfb"
+			  "\x79\x4b\xe5\x65\xd9\x0a\xc1\x6f"
+			  "\x2e",
+		.rlen	= 33,
+	}, {
+		.key	= "\x17\x4d\xc3\xab\xe3\x7d\xc7\x42"
+			  "\x1b\x91\xdd\x0a\x4b\x43\xcf\xba"
+			  "\xf6\xc5\x5c\x80\x9a\xc0\x3b\x01"
+			  "\xa9\x56\x1d\x5b\x8f\x22\xa9\x25",
+		.klen	= 32,
+		.iv	= "\x27\x16\x51\x13\x27\x1c\x71\xc9"
+			  "\x3b\xc8\x0a\x2f\x49\x0c\x00\x3c",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\xc9\x82\x3b\x4b\x87\x84\xa5\xdb"
+			  "\xa0\x8c\xd3\x3e\x7f\x8d\xe8\x28"
+			  "\x2a\xdc\xfa\x01\x84\x87\x9a\x70"
+			  "\x81\x75\x37\x0a\xd2\x75\xa9\xb6"
+			  "\x21\x72\xee\x7e\x65\x95\xe5\xcc"
+			  "\x01\xb7\x39\xa6\x51\x15\xca\xff"
+			  "\x61\xdc\x97\x38\xcc\xf4\xca\xc7"
+			  "\x83\x9b\x05\x11\x72\x60\xf0\xb4"
+			  "\x7e\x06\xab\x0a\xc0\xbb\x59\x23"
+			  "\xaa\x2d\xfc\x4e\x35\x05\x59",
+		.ilen	= 79,
+		.result	= "\x45\xa8\x6e\xe3\xaf\x5a\xc5\xd7"
+			  "\x7c\x35\x63\x77\x46\x9f\x61\x3f"
+			  "\x56\xd7\xe4\xe3\x5e\xb8\xdc\x14"
+			  "\x3a\x79\xc4\x3e\xb3\x69\x61\x46"
+			  "\x3c\xb6\x83\x4e\xb4\x26\xc7\x73"
+			  "\x22\xda\x52\x8b\x7d\x11\x98\xea"
+			  "\x62\xe1\x14\x1e\xdc\xfe\x0f\xad"
+			  "\x20\x76\x5a\xdc\x4e\x71\x13",
+		.rlen	= 63,
+	}, {
+		.key	= "\x54\x71\xfd\x4b\xf3\xf9\x6f\x5e"
+			  "\x9c\x6c\x8f\x9c\x45\x68\x92\xc1"
+			  "\x21\x87\x67\x04\x9f\x60\xbd\x1b"
+			  "\x6a\x84\xfc\x34\x6a\x81\x48\xfb",
+		.klen	= 32,
+		.iv	= "\x63\x3b\x8b\xb3\x37\x98\x1a\xe5"
+			  "\xbc\xa2\xbc\xc0\x43\x31\xc2\x42",
+		.assoc	= "",
+		.alen	= 0,
+		.input	= "\x11\x7c\x7d\xef\xce\x29\x95\xec"
+			  "\x7e\x9f\x42\xa6\x26\x07\xa1\x75"
+			  "\x2f\x4e\x09\x9a\xf6\x6b\xc2\xfa"
+			  "\x0d\xd0\x17\xdc\x25\x1e\x9b\xdc"
+			  "\x5f\x8c\x1c\x60\x15\x4f\x9b\x20"
+			  "\x7b\xff\xcd\x82\x60\x84\xf4\xa5"
+			  "\x20\x9a\x05\x19\x5b\x02\x0a\x72"
+			  "\x43\x11\x26\x58\xcf\xc5\x41\xcf"
+			  "\x13\xcc\xde\x32\x92\xfa\x86\xf2"
+			  "\xaf\x16\xe8\x8f\xca\xb6\xfd\x54",
+		.ilen	= 80,
+		.result	= "\x81\xcd\xa8\x82\xbf\xd6\x6e\xf3"
+			  "\xfd\x0f\x15\x09\x40\xc3\x24\x45"
+			  "\x81\x99\xf0\x67\x63\x58\x5e\x2e"
+			  "\xfb\xa6\xa3\x16\x8d\xc8\x00\x1c"
+			  "\x4b\x62\x87\x7c\x15\x38\xda\x70"
+			  "\x3d\xea\xe7\xf2\x40\xba\xae\x79"
+			  "\x8f\x48\xfc\xbf\x45\x53\x2e\x78"
+			  "\xef\x79\xf0\x1b\x49\xf7\xfd\x9c",
+		.rlen	= 64,
+	}, {
+		.key	= "\x90\x96\x36\xea\x03\x74\x18\x7a"
+			  "\x1d\x46\x42\x2d\x3f\x8c\x54\xc7"
+			  "\x4b\x4a\x73\x89\xa4\x00\x3f\x34"
+			  "\x2c\xb1\xdb\x0c\x44\xe0\xe8\xd2",
+		.klen	= 32,
+		.iv	= "\xa0\x5f\xc5\x52\x47\x13\xc2\x01"
+			  "\x3d\x7c\x6e\x52\x3d\x55\x85\x48",
+		.assoc	= "\xaf",
+		.alen	= 1,
+		.input	= "\x9b\xc5\x3b\x20\x0a\x88\x56\xbe"
+			  "\x69\xdf\xc4\xc4\x02\x46\x3a\xf0",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xcd\xbb\x70\x89\x13\xf0\xc1\x95"
+			  "\x9e\x20\xf4\xbf\x39\xb1\x17\xcd"
+			  "\x76\x0c\x7f\x0d\xa9\xa0\xc1\x4e"
+			  "\xed\xdf\xb9\xe4\x1e\x3f\x87\xa8",
+		.klen	= 32,
+		.iv	= "\xdc\x84\xfe\xf1\x58\x8f\x6b\x1c"
+			  "\xbe\x57\x20\xe3\x37\x7a\x48\x4f",
+		.assoc	= "\xeb\x4d\x8d\x59\x9c\x2e\x15\xa3"
+			  "\xde\x8d\x4d\x07\x36\x43\x78\xd0"
+			  "\x0b\x6d\x84\x4f\x2c\xf0\x82\x5b"
+			  "\x4e\xf6\x29\xd1\x8b\x6f\x56",
+		.alen	= 31,
+		.input	= "\xe0\x6d\xa1\x07\x98\x2f\x40\x2d"
+			  "\x2e\x9a\xd6\x61\x43\xc0\x74\x69",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x0a\xe0\xaa\x29\x24\x6c\x6a\xb1"
+			  "\x1f\xfa\xa6\x50\x33\xd5\xda\xd3"
+			  "\xa0\xce\x8a\x91\xae\x40\x43\x68"
+			  "\xae\x0d\x98\xbd\xf8\x9e\x26\x7f",
+		.klen	= 32,
+		.iv	= "\x19\xa9\x38\x91\x68\x0b\x14\x38"
+			  "\x3f\x31\xd2\x74\x31\x9e\x0a\x55",
+		.assoc	= "\x28\x72\xc7\xf8\xac\xaa\xbe\xbf"
+			  "\x5f\x67\xff\x99\x30\x67\x3b\xd6"
+			  "\x35\x2f\x90\xd3\x31\x90\x04\x74"
+			  "\x0f\x23\x08\xa9\x65\xce\xf6\xea",
+		.alen	= 32,
+		.input	= "\xb9\x57\x13\x3e\x82\x31\x61\x65"
+			  "\x0d\x7f\x6c\x96\x93\x5c\x50\xe2",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x46\x04\xe3\xc8\x34\xe7\x12\xcd"
+			  "\xa0\xd4\x58\xe2\x2d\xf9\x9c\xda"
+			  "\xca\x91\x96\x15\xb4\xe0\xc5\x81"
+			  "\x70\x3a\x77\x95\xd2\xfd\xc5\x55",
+		.klen	= 32,
+		.iv	= "\x55\xcd\x72\x30\x78\x86\xbd\x54"
+			  "\xc0\x0b\x84\x06\x2b\xc2\xcd\x5b",
+		.assoc	= "\x64\x97\x00\x98\xbc\x25\x67\xdb"
+			  "\xe0\x41\xb1\x2a\x2a\x8c\xfe\xdd"
+			  "\x5f\xf2\x9c\x58\x36\x30\x86\x8e"
+			  "\xd1\x51\xe6\x81\x3f\x2d\x95\xc1"
+			  "\x01",
+		.alen	= 33,
+		.input	= "\x81\x96\x34\xde\xbb\x36\xdd\x3e"
+			  "\x4e\x5e\xcb\x44\x21\xb8\x3f\xf1",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\x83\x29\x1d\x67\x44\x63\xbb\xe9"
+			  "\x20\xaf\x0a\x73\x27\x1e\x5f\xe0"
+			  "\xf5\x53\xa1\x9a\xb9\x80\x47\x9b"
+			  "\x31\x68\x56\x6e\xac\x5c\x65\x2c",
+		.klen	= 32,
+		.iv	= "\x92\xf2\xac\xcf\x88\x02\x65\x70"
+			  "\x41\xe5\x36\x97\x25\xe7\x90\x61",
+		.assoc	= "\xa1\xbb\x3a\x37\xcc\xa1\x10\xf7"
+			  "\x61\x1c\x63\xbc\x24\xb0\xc0\xe3"
+			  "\x8a\xb4\xa7\xdc\x3b\xd0\x08\xa8"
+			  "\x92\x7f\xc5\x5a\x19\x8c\x34\x97"
+			  "\x0f\x95\x9b\x18\xe4\x8d\xb4\x24"
+			  "\xb9\x33\x28\x18\xe1\x9d\x14\xe0"
+			  "\x64\xb2\x89\x7d\x78\xa8\x05\x7e"
+			  "\x07\x8c\xfc\x88\x2d\xb8\x53",
+		.alen	= 63,
+		.input	= "\x2e\x99\xb6\x79\x57\x56\x80\x36"
+			  "\x8e\xc4\x1c\x12\x7d\x71\x36\x0c",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xbf\x4e\x57\x07\x54\xdf\x64\x05"
+			  "\xa1\x89\xbc\x04\x21\x42\x22\xe6"
+			  "\x1f\x15\xad\x1e\xbe\x20\xc9\xb4"
+			  "\xf3\x95\x35\x46\x86\xbb\x04\x03",
+		.klen	= 32,
+		.iv	= "\xce\x17\xe5\x6f\x98\x7e\x0e\x8c"
+			  "\xc2\xbf\xe8\x29\x1f\x0b\x52\x68",
+		.assoc	= "\xdd\xe0\x74\xd6\xdc\x1d\xb8\x13"
+			  "\xe2\xf6\x15\x4d\x1e\xd4\x83\xe9"
+			  "\xb4\x76\xb3\x60\x40\x70\x8a\xc1"
+			  "\x53\xac\xa4\x32\xf3\xeb\xd3\x6e"
+			  "\x1e\x42\xa0\x46\x45\x9f\xc7\x22"
+			  "\xd3\x43\xbc\x7e\xa5\x47\x2a\x6f"
+			  "\x91\x19\x70\x1e\xe1\xfe\x25\x49"
+			  "\xd6\x8f\x93\xc7\x28\x3f\x3d\x03",
+		.alen	= 64,
+		.input	= "\x7b\x25\x3d\x47\xd4\xa7\x08\xce"
+			  "\x3b\x89\x40\x36\xba\x6d\x0e\xa2",
+		.ilen	= 16,
+		.result	= "",
+		.rlen	= 0,
+	}, {
+		.key	= "\xfc\x72\x90\xa6\x64\x5a\x0d\x21"
+			  "\x22\x63\x6e\x96\x1b\x67\xe4\xec"
+			  "\x49\xd7\xb9\xa2\xc3\xc0\x4b\xce"
+			  "\xb4\xc3\x14\x1e\x61\x1a\xa3\xd9",
+		.klen	= 32,
+		.iv	= "\x0b\x3c\x1f\x0e\xa8\xf9\xb7\xa7"
+			  "\x42\x9a\x9a\xba\x19\x30\x15\x6e",
+		.assoc	= "\x1a",
+		.alen	= 1,
+		.input	= "\xe6\x09\x6f\x95\x9a\x18\xc8\xf6"
+			  "\x17\x75\x81\x16\xdf\x26\xff\x67"
+			  "\x92",
+		.ilen	= 17,
+		.result	= "\x29",
+		.rlen	= 1,
+	}, {
+		.key	= "\x38\x97\xca\x45\x74\xd6\xb6\x3c"
+			  "\xa3\x3d\x20\x27\x15\x8b\xa7\xf2"
+			  "\x74\x9a\xc4\x27\xc8\x60\xcd\xe8"
+			  "\x75\xf0\xf2\xf7\x3b\x79\x42\xb0",
+		.klen	= 32,
+		.iv	= "\x47\x60\x59\xad\xb8\x75\x60\xc3"
+			  "\xc3\x74\x4c\x4c\x13\x54\xd8\x74",
+		.assoc	= "\x56\x29\xe7\x15\xfc\x14\x0a\x4a"
+			  "\xe4\xaa\x79\x70\x12\x1d\x08\xf6"
+			  "\x09\xfb\xca\x69\x4b\xb0\x8e\xf5"
+			  "\xd6\x07\x62\xe3\xa8\xa9\x12",
+		.alen	= 31,
+		.input	= "\x82\xc0\x56\xf0\xd7\xc4\xc9\xfd"
+			  "\x3c\xd1\x2a\xd4\x15\x86\x9d\xda"
+			  "\xea\x6c\x6f\xa1\x33\xb0\x7a\x01"
+			  "\x57\xe7\xf3\x7b\x73\xe7\x54\x10"
+			  "\xc6\x91\xe2\xc6\xa0\x69\xe7\xe6"
+			  "\x76\xc3\xf5\x3a\x76\xfd\x4a",
+		.ilen	= 47,
+		.result	= "\x66\xf3\x75\x7d\x40\xb3\xb4\xd1"
+			  "\x04\xe1\xa6\x94\x10\xe6\x39\x77"
+			  "\xd3\xac\x4d\x8a\x8c\x58\x6e\xfb"
+			  "\x06\x13\x9a\xd9\x5e\xc0\xfa",
+		.rlen	= 31,
+	}, {
+		.key	= "\x75\xbc\x04\xe5\x84\x52\x5e\x58"
+			  "\x24\x17\xd2\xb9\x0e\xaf\x6a\xf9"
+			  "\x9e\x5c\xd0\xab\xcd\x00\x4f\x01"
+			  "\x37\x1e\xd1\xcf\x15\xd8\xe2\x86",
+		.klen	= 32,
+		.iv	= "\x84\x85\x92\x4d\xc8\xf1\x08\xdf"
+			  "\x44\x4e\xff\xdd\x0d\x78\x9a\x7a",
+		.assoc	= "\x93\x4e\x21\xb4\x0c\x90\xb3\x66"
+			  "\x65\x84\x2b\x01\x0b\x42\xcb\xfc"
+			  "\x33\xbd\xd6\xed\x50\x50\x10\x0e"
+			  "\x97\x35\x41\xbb\x82\x08\xb1\xf2",
+		.alen	= 32,
+		.input	= "\x01\x47\x8e\x6c\xf6\x64\x89\x3a"
+			  "\x71\xce\xe4\xaa\x45\x70\xe6\x84"
+			  "\x62\x48\x08\x64\x86\x6a\xdf\xec"
+			  "\xb4\xa0\xfb\x34\x03\x0c\x19\xf4"
+			  "\x2b\x7b\x36\x73\xec\x54\xa9\x1e"
+			  "\x30\x85\xdb\xe4\xac\xe9\x2c\xca",
+		.ilen	= 48,
+		.result	= "\xa2\x17\xaf\x1c\x50\x2e\x5d\xed"
+			  "\x85\xbb\x58\x26\x0a\x0b\xfc\x7d"
+			  "\xfe\x6e\x59\x0e\x91\xf8\xf0\x15"
+			  "\xc8\x40\x78\xb1\x38\x1f\x99\xa7",
+		.rlen	= 32,
+	}, {
+		.key	= "\xb1\xe1\x3e\x84\x94\xcd\x07\x74"
+			  "\xa5\xf2\x84\x4a\x08\xd4\x2c\xff"
+			  "\xc8\x1e\xdb\x2f\xd2\xa0\xd1\x1b"
+			  "\xf8\x4c\xb0\xa8\xef\x37\x81\x5d",
+		.klen	= 32,
+		.iv	= "\xc0\xaa\xcc\xec\xd8\x6c\xb1\xfb"
+			  "\xc5\x28\xb1\x6e\x07\x9d\x5d\x81",
+		.assoc	= "\xd0\x73\x5a\x54\x1d\x0b\x5b\x82"
+			  "\xe5\x5f\xdd\x93\x05\x66\x8e\x02"
+			  "\x5e\x80\xe1\x71\x55\xf0\x92\x28"
+			  "\x59\x62\x20\x94\x5c\x67\x50\xc8"
+			  "\x58",
+		.alen	= 33,
+		.input	= "\x85\xe0\xf8\x0f\x8e\x49\xe3\x60"
+			  "\xcb\x4a\x54\x94\xcf\xf5\x7e\x34"
+			  "\xe9\xf8\x80\x65\x53\xd0\x72\x70"
+			  "\x4f\x7d\x9d\xd1\x15\x6f\xb9\x2c"
+			  "\xfa\xe8\xdd\xac\x2e\xe1\x3f\x67"
+			  "\x63\x0f\x1a\x59\xb7\x89\xdb\xf4"
+			  "\xc3",
+		.ilen	= 49,
+		.result	= "\xdf\x3c\xe9\xbc\x61\xaa\x06\x09"
+			  "\x06\x95\x0a\xb7\x04\x2f\xbe\x84"
+			  "\x28\x30\x64\x92\x96\x98\x72\x2e"
+			  "\x89\x6e\x57\x8a\x13\x7e\x38\x7e"
+			  "\xdb",
+		.rlen	= 33,
+	}, {
+		.key	= "\xee\x05\x77\x23\xa5\x49\xb0\x90"
+			  "\x26\xcc\x36\xdc\x02\xf8\xef\x05"
+			  "\xf3\xe1\xe7\xb3\xd8\x40\x53\x35"
+			  "\xb9\x79\x8f\x80\xc9\x96\x20\x33",
+		.klen	= 32,
+		.iv	= "\xfd\xce\x06\x8b\xe9\xe8\x5a\x17"
+			  "\x46\x02\x63\x00\x01\xc1\x20\x87",
+		.assoc	= "\x0c\x98\x94\xf3\x2d\x87\x04\x9e"
+			  "\x66\x39\x8f\x24\xff\x8a\x50\x08"
+			  "\x88\x42\xed\xf6\x5a\x90\x14\x42"
+			  "\x1a\x90\xfe\x6c\x36\xc6\xf0\x9f"
+			  "\x66\xa0\xb5\x2d\x2c\xf8\x25\x15"
+			  "\x55\x90\xa2\x7e\x77\x94\x96\x3a"
+			  "\x71\x1c\xf7\x44\xee\xa8\xc3\x42"
+			  "\xe2\xa3\x84\x04\x0b\xe1\xce",
+		.alen	= 63,
+		.input	= "\x00\xe5\x5b\x87\x5c\x20\x22\x8a"
+			  "\xda\x1f\xd3\xff\xbb\xb2\xb0\xf8"
+			  "\xef\xe9\xeb\x9e\x7c\x80\xf4\x2b"
+			  "\x59\xc0\x79\xbc\x17\xa0\x15\x01"
+			  "\xf5\x72\xfb\x5a\xe7\xaf\x07\xe3"
+			  "\x1b\x49\x21\x34\x23\x63\x55\x5e"
+			  "\xee\x4f\x34\x17\xfa\xfe\xa5\x0c"
+			  "\xed\x0b\x23\xea\x9b\xda\x57\x2f"
+			  "\xf6\xa9\xae\x0d\x4e\x40\x96\x45"
+			  "\x7f\xfa\xf0\xbf\xc4\x98\x78",
+		.ilen	= 79,
+		.result	= "\x1b\x61\x23\x5b\x71\x26\xae\x25"
+			  "\x87\x6f\xbc\x49\xfe\x53\x81\x8a"
+			  "\x53\xf2\x70\x17\x9b\x38\xf4\x48"
+			  "\x4b\x9b\x36\x62\xed\xdd\xd8\x54"
+			  "\xea\xcb\xb6\x79\x45\xfc\xaa\x54"
+			  "\x5c\x94\x47\x58\xa7\xff\x9c\x9e"
+			  "\x7c\xb6\xf1\xac\xc8\xfd\x8b\x35"
+			  "\xd5\xa4\x6a\xd4\x09\xc2\x08",
+		.rlen	= 63,
+	}, {
+		.key	= "\x2a\x2a\xb1\xc3\xb5\xc5\x59\xac"
+			  "\xa7\xa6\xe8\x6d\xfc\x1d\xb2\x0b"
+			  "\x1d\xa3\xf3\x38\xdd\xe0\xd5\x4e"
+			  "\x7b\xa7\x6e\x58\xa3\xf5\xbf\x0a",
+		.klen	= 32,
+		.iv	= "\x39\xf3\x3f\x2b\xf9\x64\x03\x33"
+			  "\xc7\xdd\x15\x91\xfb\xe6\xe2\x8d",
+		.assoc	= "\x49\xbc\xce\x92\x3d\x02\xad\xba"
+			  "\xe7\x13\x41\xb6\xf9\xaf\x13\x0f"
+			  "\xb2\x04\xf8\x7a\x5f\x30\x96\x5b"
+			  "\xdc\xbd\xdd\x44\x10\x25\x8f\x75"
+			  "\x75\x4d\xb9\x5b\x8e\x0a\x38\x13"
+			  "\x6f\x9f\x36\xe4\x3a\x3e\xac\xc9"
+			  "\x9d\x83\xde\xe5\x57\xfd\xe3\x0e"
+			  "\xb1\xa7\x1b\x44\x05\x67\xb7\x37",
+		.alen	= 64,
+		.input	= "\x28\xdd\xb9\x4a\x12\xc7\x0a\xe1"
+			  "\x58\x06\x1a\x9b\x8c\x67\xdf\xeb"
+			  "\x35\x35\x60\x9d\x06\x40\x65\xc1"
+			  "\x93\xe8\xb3\x82\x50\x29\xdd\xb5"
+			  "\x2b\xcb\xde\x18\x78\x6b\x42\xbe"
+			  "\x6d\x24\xd0\xb2\x7d\xd7\x08\x8f"
+			  "\x4a\x18\x98\xad\x8c\xf2\x97\xb4"
+			  "\xf4\x77\xe4\xbf\x41\x3b\xc4\x06"
+			  "\xce\x9e\x34\x81\xf0\x89\x11\x13"
+			  "\x02\x65\xa1\x7c\xdf\x07\x33\x06",
+		.ilen	= 80,
+		.result	= "\x58\x85\x5c\xfa\x81\xa1\x57\x40"
+			  "\x08\x4a\x6e\xda\xf8\x78\x44\x90"
+			  "\x7d\xb5\x7b\x9b\xa1\xd8\x76\x62"
+			  "\x0c\xc9\x15\x3b\xc7\x3c\x77\x2b"
+			  "\xf8\x78\xba\xa7\xa6\x0e\xbd\x52"
+			  "\x76\xa3\xdc\xbe\x6b\xa8\xb1\x2d"
+			  "\xa9\x1d\xd8\x4e\x31\x53\xab\x00"
+			  "\xa5\xa7\x01\x13\x04\x49\xf2\x04",
+		.rlen	= 64,
+	}, {
+		.key	= "\x67\x4f\xeb\x62\xc5\x40\x01\xc7"
+			  "\x28\x80\x9a\xfe\xf6\x41\x74\x12"
+			  "\x48\x65\xfe\xbc\xe2\x80\x57\x68"
+			  "\x3c\xd4\x4d\x31\x7d\x54\x5f\xe1",
+		.klen	= 32,
+		.iv	= "\x76\x18\x79\xca\x09\xdf\xac\x4e"
+			  "\x48\xb7\xc7\x23\xf5\x0a\xa5\x93",
+		.assoc	= "\x85\xe1\x08\x32\x4d\x7e\x56\xd5"
+			  "\x68\xed\xf3\x47\xf3\xd3\xd6\x15"
+			  "\xdd\xc7\x04\xfe\x64\xd0\x18\x75"
+			  "\x9d\xeb\xbc\x1d\xea\x84\x2e\x4c"
+			  "\x83\xf9\xbe\x8a\xef\x1c\x4b\x10"
+			  "\x89\xaf\xcb\x4b\xfe\xe7\xc1\x58"
+			  "\xca\xea\xc6\x87\xc0\x53\x03\xd9"
+			  "\x80\xaa\xb2\x83\xff\xee\xa1\x6a"
+			  "\x04",
+		.alen	= 65,
+		.input	= "\x85\x39\x69\x35\xfb\xf9\xb0\xa6"
+			  "\x85\x43\x88\xd0\xd7\x78\x60\x19"
+			  "\x3e\x1f\xb1\xa4\xd6\xc5\x96\xec"
+			  "\xf7\x84\x85\xc7\x27\x0f\x74\x57"
+			  "\x28\x9e\xdd\x90\x3c\x43\x12\xc5"
+			  "\x51\x3d\x39\x8f\xa5\xf4\xe0\x0b"
+			  "\x57\x04\xf1\x6d\xfe\x9b\x84\x27"
+			  "\xe8\xeb\x4d\xda\x02\x0a\xc5\x49"
+			  "\x1a\x55\x5e\x50\x56\x4d\x94\xda"
+			  "\x20\xf8\x12\x54\x50\xb3\x11\xda"
+			  "\xed\x44\x27\x67\xd5\xd1\x8b\x4b"
+			  "\x38\x67\x56\x65\x59\xda\xe6\x97"
+			  "\x81\xae\x2f\x92\x3b\xae\x22\x1c"
+			  "\x91\x59\x38\x18\x00\xe8\xba\x92"
+			  "\x04\x19\x56\xdf\xb0\x82\xeb\x6f"
+			  "\x2e\xdb\x54\x3c\x4b\xbb\x60\x90"
+			  "\x4c\x50\x10\x62\xba\x7a\xb1\x68"
+			  "\x37\xd7\x87\x4e\xe4\x66\x09\x1f"
+			  "\xa5",
+		.ilen	= 145,
+		.result	= "\x94\xaa\x96\x9a\x91\x1d\x00\x5c"
+			  "\x88\x24\x20\x6b\xf2\x9c\x06\x96"
+			  "\xa7\x77\x87\x1f\xa6\x78\xf8\x7b"
+			  "\xcd\xf6\xf4\x13\xa1\x9b\x16\x02"
+			  "\x07\x24\xbf\xd5\x08\x20\xd0\x4f"
+			  "\x90\xb3\x70\x24\x2f\x51\xc7\xbb"
+			  "\xd6\x84\xc0\xef\x9a\xa8\xca\xcc"
+			  "\x74\xab\x97\x53\xfe\xd0\xdb\x37"
+			  "\x37\x6a\x0e\x9f\x3f\xa3\x2a\xe3"
+			  "\x1b\x34\x6d\x51\x72\x2b\x17\xe7"
+			  "\x4d\xaa\x2c\x18\xda\xa3\x33\x89"
+			  "\x2a\x9f\xf4\xd2\xed\x76\x3d\x3f"
+			  "\x3c\x15\x9d\x8e\x4f\x3c\x27\xb0"
+			  "\x42\x3f\x2f\x8a\xd4\xc2\x10\xb2"
+			  "\x27\x7f\xe3\x34\x80\x02\x49\x4b"
+			  "\x07\x68\x22\x2a\x88\x25\x53\xb2"
+			  "\x2f",
+		.rlen	= 129,
+	}, {
+		.key	= "\xa3\x73\x24\x01\xd5\xbc\xaa\xe3"
+			  "\xa9\x5a\x4c\x90\xf0\x65\x37\x18"
+			  "\x72\x28\x0a\x40\xe7\x20\xd9\x82"
+			  "\xfe\x02\x2b\x09\x57\xb3\xfe\xb7",
+		.klen	= 32,
+		.iv	= "\xb3\x3d\xb3\x69\x19\x5b\x54\x6a"
+			  "\xc9\x91\x79\xb4\xef\x2e\x68\x99",
+		.assoc	= "\xc2\x06\x41\xd1\x5d\xfa\xff\xf1"
+			  "\xe9\xc7\xa5\xd9\xed\xf8\x98\x1b"
+			  "\x07\x89\x10\x82\x6a\x70\x9a\x8f"
+			  "\x5e\x19\x9b\xf5\xc5\xe3\xcd\x22"
+			  "\x92\xa5\xc2\xb8\x51\x2e\x5e\x0e"
+			  "\xa4\xbe\x5f\xb1\xc1\x90\xd7\xe7"
+			  "\xf7\x52\xae\x28\x29\xa8\x22\xa4"
+			  "\x4f\xae\x48\xc2\xfa\x75\x8b\x9e"
+			  "\xce\x83\x2a\x88\x07\x55\xbb\x89"
+			  "\xf6\xdf\xac\xdf\x83\x08\xbf\x7d"
+			  "\xac\x30\x8b\x8e\x02\xac\x00\xf1"
+			  "\x30\x46\xe1\xbc\x75\xbf\x49\xbb"
+			  "\x26\x4e\x29\xf0\x2f\x21\xc6\x13"
+			  "\x92\xd9\x3d\x11\xe4\x10\x00\x8e"
+			  "\xd4\xd4\x58\x65\xa6\x2b\xe3\x25"
+			  "\xb1\x8f\x15\x93\xe7\x71\xb9\x2c"
+			  "\x4b",
+		.alen	= 129,
+		.input	= "\x7d\xde\x53\x22\xe4\x23\x3b\x30"
+			  "\x78\xde\x35\x90\x7a\xd9\x0b\x93"
+			  "\xf6\x0e\x0b\xed\x40\xee\x10\x9c"
+			  "\x96\x3a\xd3\x34\xb2\xd0\x67\xcf"
+			  "\x63\x7f\x2d\x0c\xcf\x96\xec\x64"
+			  "\x1a\x87\xcc\x7d\x2c\x5e\x81\x4b"
+			  "\xd2\x8f\x4c\x7c\x00\xb1\xb4\xe0"
+			  "\x87\x4d\xb1\xbc\xd8\x78\x2c\x17"
+			  "\xf2\x3b\xd8\x28\x40\xe2\x76\xf6"
+			  "\x20\x13\x83\x46\xaf\xff\xe3\x0f"
+			  "\x72",
+		.ilen	= 81,
+		.result	= "\xd1\xcf\xd0\x39\xa1\x99\xa9\x78"
+			  "\x09\xfe\xd2\xfd\xec\xc1\xc9\x9d"
+			  "\xd2\x39\x93\xa3\xab\x18\x7a\x95"
+			  "\x8f\x24\xd3\xeb\x7b\xfa\xb5\xd8"
+			  "\x15\xd1\xc3\x04\x69\x32\xe3\x4d"
+			  "\xaa\xc2\x04\x8b\xf2\xfa\xdc\x4a"
+			  "\x02\xeb\xa8\x90\x03\xfd\xea\x97"
+			  "\x43\xaf\x2e\x92\xf8\x57\xc5\x6a"
+			  "\x00",
+		.rlen	= 65,
+	}, {
+		.key	= "\xe0\x98\x5e\xa1\xe5\x38\x53\xff"
+			  "\x2a\x35\xfe\x21\xea\x8a\xfa\x1e"
+			  "\x9c\xea\x15\xc5\xec\xc0\x5b\x9b"
+			  "\xbf\x2f\x0a\xe1\x32\x12\x9d\x8e",
+		.klen	= 32,
+		.iv	= "\xef\x61\xed\x08\x29\xd7\xfd\x86"
+			  "\x4a\x6b\x2b\x46\xe9\x53\x2a\xa0",
+		.assoc	= "\xfe\x2a\x7b\x70\x6d\x75\xa7\x0d"
+			  "\x6a\xa2\x57\x6a\xe7\x1c\x5b\x21"
+			  "\x31\x4b\x1b\x07\x6f\x10\x1c\xa8"
+			  "\x20\x46\x7a\xce\x9f\x42\x6d\xf9",
+		.alen	= 32,
+		.input	= "\x5a\xcd\x8c\x57\xf2\x6a\xb6\xbe"
+			  "\x53\xc7\xaa\x9a\x60\x74\x9c\xc4"
+			  "\xa2\xc2\xd0\x6d\xe1\x03\x63\xdc"
+			  "\xbb\x51\x7e\x9c\x89\x73\xde\x4e"
+			  "\x24\xf8\x52\x7c\x15\x41\x0e\xba"
+			  "\x69\x0e\x36\x5f\x2f\x22\x8c",
+		.ilen	= 47,
+		.result	= "\x0d\xf4\x09\xd8\xb1\x14\x51\x94"
+			  "\x8a\xd8\x84\x8e\xe6\xe5\x8c\xa3"
+			  "\xfc\xfc\x9e\x28\xb0\xb8\xfc\xaf"
+			  "\x50\x52\xb1\xc4\x55\x59\x55\xaf",
+		.rlen	= 32,
+	}, {
+		.key	= "\x1c\xbd\x98\x40\xf5\xb3\xfc\x1b"
+			  "\xaa\x0f\xb0\xb3\xe4\xae\xbc\x24"
+			  "\xc7\xac\x21\x49\xf1\x60\xdd\xb5"
+			  "\x80\x5d\xe9\xba\x0c\x71\x3c\x64",
+		.klen	= 32,
+		.iv	= "\x2c\x86\x26\xa8\x39\x52\xa6\xa2"
+			  "\xcb\x45\xdd\xd7\xe3\x77\xed\xa6",
+		.assoc	= "\x3b\x4f\xb5\x10\x7d\xf1\x50\x29"
+			  "\xeb\x7c\x0a\xfb\xe1\x40\x1e\x27"
+			  "\x5c\x0d\x27\x8b\x74\xb0\x9e\xc2"
+			  "\xe1\x74\x59\xa6\x79\xa1\x0c\xd0",
+		.alen	= 32,
+		.input	= "\x47\xd6\xce\x78\xd6\xbf\x4a\x51"
+			  "\xb8\xda\x92\x3c\xfd\xda\xac\x8e"
+			  "\x8d\x88\xd7\x4d\x90\xe5\xeb\xa1"
+			  "\xab\xd6\x7c\x76\xad\xea\x7d\x76"
+			  "\x53\xee\xb0\xcd\xd0\x02\xbb\x70"
+			  "\x5b\x6f\x7b\xe2\x8c\xe8",
+		.ilen	= 46,
+		.result	= "\x4a\x18\x43\x77\xc1\x90\xfa\xb0"
+			  "\x0b\xb2\x36\x20\xe0\x09\x4e\xa9"
+			  "\x26\xbe\xaa\xac\xb5\x58\x7e\xc8"
+			  "\x11\x7f\x90\x9c\x2f\xb8\xf4\x85",
+		.rlen	= 32,
+	}, {
+		.key	= "\x59\xe1\xd2\xdf\x05\x2f\xa4\x37"
+			  "\x2b\xe9\x63\x44\xde\xd3\x7f\x2b"
+			  "\xf1\x6f\x2d\xcd\xf6\x00\x5f\xcf"
+			  "\x42\x8a\xc8\x92\xe6\xd0\xdc\x3b",
+		.klen	= 32,
+		.iv	= "\x68\xab\x60\x47\x49\xce\x4f\xbe"
+			  "\x4c\x20\x8f\x68\xdd\x9c\xb0\xac",
+		.assoc	= "\x77\x74\xee\xaf\x8d\x6d\xf9\x45"
+			  "\x6c\x56\xbc\x8d\xdb\x65\xe0\x2e"
+			  "\x86\xd0\x32\x0f\x79\x50\x20\xdb"
+			  "\xa2\xa1\x37\x7e\x53\x00\xab\xa6",
+		.alen	= 32,
+		.input	= "\x9f\xa9\x2b\xa4\x8f\x00\x05\x2b"
+			  "\xe7\x68\x81\x51\xbb\xfb\xdf\x60"
+			  "\xbb\xac\xe8\xc1\xdc\x68\xae\x68"
+			  "\x3a\xcd\x7a\x06\x49\xfe\x80\x11"
+			  "\xe6\x61\x99\xe2\xdd\xbe\x2c\xbf",
+		.ilen	= 40,
+		.result	= "\x86\x3d\x7d\x17\xd1\x0c\xa3\xcc"
+			  "\x8c\x8d\xe8\xb1\xda\x2e\x11\xaf"
+			  "\x51\x80\xb5\x30\xba\xf8\x00\xe2"
+			  "\xd3\xad\x6f\x75\x09\x18\x93\x5c",
+		.rlen	= 32,
+	}, {
+		.key	= "\x96\x06\x0b\x7f\x15\xab\x4d\x53"
+			  "\xac\xc3\x15\xd6\xd8\xf7\x42\x31"
+			  "\x1b\x31\x38\x51\xfc\xa0\xe1\xe8"
+			  "\x03\xb8\xa7\x6b\xc0\x2f\x7b\x11",
+		.klen	= 32,
+		.iv	= "\xa5\xcf\x9a\xe6\x59\x4a\xf7\xd9"
+			  "\xcd\xfa\x41\xfa\xd7\xc0\x72\xb2",
+		.assoc	= "\xb4\x99\x28\x4e\x9d\xe8\xa2\x60"
+			  "\xed\x30\x6e\x1e\xd5\x89\xa3\x34"
+			  "\xb1\x92\x3e\x93\x7e\xf0\xa2\xf5"
+			  "\x64\xcf\x16\x57\x2d\x5f\x4a\x7d",
+		.alen	= 32,
+		.input	= "\xe2\x34\xfa\x25\xfd\xfb\x89\x5e"
+			  "\x5b\x4e\x0b\x15\x6e\x39\xfb\x0c"
+			  "\x73\xc7\xd9\x6b\xbe\xce\x9b\x70"
+			  "\xc7\x4f\x96\x16\x03\xfc\xea\xfb"
+			  "\x56",
+		.ilen	= 33,
+		.result	= "\xc3\x62\xb7\xb6\xe2\x87\x4c\xe7"
+			  "\x0d\x67\x9a\x43\xd4\x52\xd4\xb5"
+			  "\x7b\x43\xc1\xb5\xbf\x98\x82\xfc"
+			  "\x94\xda\x4e\x4d\xe4\x77\x32\x32",
+		.rlen	= 32,
+	},
+};
+
 /*
  * All key wrapping test vectors taken from
  * http://csrc.nist.gov/groups/STM/cavp/documents/mac/kwtestvectors.zip
@@ -27385,35 +26023,31 @@ static const struct aead_testvec rfc7539esp_dec_tv_template[] = {
  * semiblock of the ciphertext from the test vector. For decryption, iv is
  * the first semiblock of the ciphertext.
  */
-static const struct cipher_testvec aes_kw_enc_tv_template[] = {
+static const struct cipher_testvec aes_kw_tv_template[] = {
 	{
 		.key	= "\x75\x75\xda\x3a\x93\x60\x7c\xc2"
 			  "\xbf\xd8\xce\xc7\xaa\xdf\xd9\xa6",
 		.klen	= 16,
-		.input	= "\x42\x13\x6d\x3c\x38\x4a\x3e\xea"
+		.ptext	= "\x42\x13\x6d\x3c\x38\x4a\x3e\xea"
 			  "\xc9\x5a\x06\x6f\xd2\x8f\xed\x3f",
-		.ilen	= 16,
-		.result	= "\xf6\x85\x94\x81\x6f\x64\xca\xa3"
+		.ctext	= "\xf6\x85\x94\x81\x6f\x64\xca\xa3"
 			  "\xf5\x6f\xab\xea\x25\x48\xf5\xfb",
-		.rlen	= 16,
-		.iv_out	= "\x03\x1f\x6b\xd7\xe6\x1e\x64\x3d",
-	},
-};
-
-static const struct cipher_testvec aes_kw_dec_tv_template[] = {
-	{
+		.len	= 16,
+		.iv	= "\x03\x1f\x6b\xd7\xe6\x1e\x64\x3d",
+		.generates_iv = true,
+	}, {
 		.key	= "\x80\xaa\x99\x73\x27\xa4\x80\x6b"
 			  "\x6a\x7a\x41\xa5\x2b\x86\xc3\x71"
 			  "\x03\x86\xf9\x32\x78\x6e\xf7\x96"
 			  "\x76\xfa\xfb\x90\xb8\x26\x3c\x5f",
 		.klen	= 32,
-		.input	= "\xd3\x3d\x3d\x97\x7b\xf0\xa9\x15"
-			  "\x59\xf9\x9c\x8a\xcd\x29\x3d\x43",
-		.ilen	= 16,
-		.result	= "\x0a\x25\x6b\xa7\x5c\xfa\x03\xaa"
+		.ptext	= "\x0a\x25\x6b\xa7\x5c\xfa\x03\xaa"
 			  "\xa0\x2b\xa9\x42\x03\xf1\x5b\xaa",
-		.rlen	= 16,
+		.ctext	= "\xd3\x3d\x3d\x97\x7b\xf0\xa9\x15"
+			  "\x59\xf9\x9c\x8a\xcd\x29\x3d\x43",
+		.len	= 16,
 		.iv	= "\x42\x3c\x96\x0d\x8a\x2a\xc4\xc1",
+		.generates_iv = true,
 	},
 };
 
@@ -28340,36 +26974,33 @@ static const struct drbg_testvec drbg_nopr_ctr_aes128_tv_template[] = {
 };
 
 /* Cast5 test vectors from RFC 2144 */
-static const struct cipher_testvec cast5_enc_tv_template[] = {
+static const struct cipher_testvec cast5_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x12\x34\x56\x78"
 			  "\x23\x45\x67\x89\x34\x56\x78\x9a",
 		.klen	= 16,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.ilen	= 8,
-		.result	= "\x23\x8b\x4f\xe5\x84\x7e\x44\xb2",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.ctext	= "\x23\x8b\x4f\xe5\x84\x7e\x44\xb2",
+		.len	= 8,
 	}, {
 		.key	= "\x01\x23\x45\x67\x12\x34\x56\x78"
 			  "\x23\x45",
 		.klen	= 10,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.ilen	= 8,
-		.result	= "\xeb\x6a\x71\x1a\x2c\x02\x27\x1b",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.ctext	= "\xeb\x6a\x71\x1a\x2c\x02\x27\x1b",
+		.len	= 8,
 	}, {
 		.key	= "\x01\x23\x45\x67\x12",
 		.klen	= 5,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.ilen	= 8,
-		.result	= "\x7a\xc8\x16\xd1\x6e\x9b\x30\x2e",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.ctext	= "\x7a\xc8\x16\xd1\x6e\x9b\x30\x2e",
+		.len	= 8,
 	}, { /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
 		.klen	= 16,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -28431,8 +27062,7 @@ static const struct cipher_testvec cast5_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\x8D\xFC\x81\x9C\xCB\xAA\x5A\x1C"
+		.ctext	= "\x8D\xFC\x81\x9C\xCB\xAA\x5A\x1C"
 			  "\x7E\x95\xCF\x40\xAB\x4D\x6F\xEA"
 			  "\xD3\xD9\xB0\x9A\xB7\xC7\xE0\x2E"
 			  "\xD1\x39\x34\x92\x8F\xFA\x14\xF1"
@@ -28494,181 +27124,20 @@ static const struct cipher_testvec cast5_enc_tv_template[] = {
 			  "\x5D\x0B\x3F\x03\x8F\x30\xF9\xAE"
 			  "\x4F\xFE\x24\x9C\x9A\x02\xE5\x57"
 			  "\xF5\xBC\x25\xD6\x02\x56\x57\x1C",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec cast5_dec_tv_template[] = {
-	{
-		.key	= "\x01\x23\x45\x67\x12\x34\x56\x78"
-			  "\x23\x45\x67\x89\x34\x56\x78\x9a",
-		.klen	= 16,
-		.input	= "\x23\x8b\x4f\xe5\x84\x7e\x44\xb2",
-		.ilen	= 8,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.rlen	= 8,
-	}, {
-		.key	= "\x01\x23\x45\x67\x12\x34\x56\x78"
-			  "\x23\x45",
-		.klen	= 10,
-		.input	= "\xeb\x6a\x71\x1a\x2c\x02\x27\x1b",
-		.ilen	= 8,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.rlen	= 8,
-	}, {
-		.key	= "\x01\x23\x45\x67\x12",
-		.klen	= 5,
-		.input	= "\x7a\xc8\x16\xd1\x6e\x9b\x30\x2e",
-		.ilen	= 8,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.rlen	= 8,
-	}, { /* Generated from TF test vectors */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
-		.klen	= 16,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x8D\xFC\x81\x9C\xCB\xAA\x5A\x1C"
-			  "\x7E\x95\xCF\x40\xAB\x4D\x6F\xEA"
-			  "\xD3\xD9\xB0\x9A\xB7\xC7\xE0\x2E"
-			  "\xD1\x39\x34\x92\x8F\xFA\x14\xF1"
-			  "\xD5\xD2\x7B\x59\x1F\x35\x28\xC2"
-			  "\x20\xD9\x42\x06\xC9\x0B\x10\x04"
-			  "\xF8\x79\xCD\x32\x86\x75\x4C\xB6"
-			  "\x7B\x1C\x52\xB1\x91\x64\x22\x4B"
-			  "\x13\xC7\xAE\x98\x0E\xB5\xCF\x6F"
-			  "\x3F\xF4\x43\x96\x73\x0D\xA2\x05"
-			  "\xDB\xFD\x28\x90\x2C\x56\xB9\x37"
-			  "\x5B\x69\x0C\xAD\x84\x67\xFF\x15"
-			  "\x4A\xD4\xA7\xD3\xDD\x99\x47\x3A"
-			  "\xED\x34\x35\x78\x6B\x91\xC9\x32"
-			  "\xE1\xBF\xBC\xB4\x04\x85\x6A\x39"
-			  "\xC0\xBA\x51\xD0\x0F\x4E\xD1\xE2"
-			  "\x1C\xFD\x0E\x05\x07\xF4\x10\xED"
-			  "\xA2\x17\xFF\xF5\x64\xC6\x1A\x22"
-			  "\xAD\x78\xE7\xD7\x11\xE9\x99\xB9"
-			  "\xAA\xEC\x6F\xF8\x3B\xBF\xCE\x77"
-			  "\x93\xE8\xAD\x1D\x50\x6C\xAE\xBC"
-			  "\xBA\x5C\x80\xD1\x91\x65\x51\x1B"
-			  "\xE8\x0A\xCD\x99\x96\x71\x3D\xB6"
-			  "\x78\x75\x37\x55\xC1\xF5\x90\x40"
-			  "\x34\xF4\x7E\xC8\xCC\x3A\x5F\x6E"
-			  "\x36\xA1\xA1\xC2\x3A\x72\x42\x8E"
-			  "\x0E\x37\x88\xE8\xCE\x83\xCB\xAD"
-			  "\xE0\x69\x77\x50\xC7\x0C\x99\xCA"
-			  "\x19\x5B\x30\x25\x9A\xEF\x9B\x0C"
-			  "\xEF\x8F\x74\x4C\xCF\x49\x4E\xB9"
-			  "\xC5\xAE\x9E\x2E\x78\x9A\xB9\x48"
-			  "\xD5\x81\xE4\x37\x1D\xBF\x27\xD9"
-			  "\xC5\xD6\x65\x43\x45\x8C\xBB\xB6"
-			  "\x55\xF4\x06\xBB\x49\x53\x8B\x1B"
-			  "\x07\xA9\x96\x69\x5B\xCB\x0F\xBC"
-			  "\x93\x85\x90\x0F\x0A\x68\x40\x2A"
-			  "\x95\xED\x2D\x88\xBF\x71\xD0\xBB"
-			  "\xEC\xB0\x77\x6C\x79\xFC\x3C\x05"
-			  "\x49\x3F\xB8\x24\xEF\x8E\x09\xA2"
-			  "\x1D\xEF\x92\x02\x96\xD4\x7F\xC8"
-			  "\x03\xB2\xCA\xDB\x17\x5C\x52\xCF"
-			  "\xDD\x70\x37\x63\xAA\xA5\x83\x20"
-			  "\x52\x02\xF6\xB9\xE7\x6E\x0A\xB6"
-			  "\x79\x03\xA0\xDA\xA3\x79\x21\xBD"
-			  "\xE3\x37\x3A\xC0\xF7\x2C\x32\xBE"
-			  "\x8B\xE8\xA6\x00\xC7\x32\xD5\x06"
-			  "\xBB\xE3\xAB\x06\x21\x82\xB8\x32"
-			  "\x31\x34\x2A\xA7\x1F\x64\x99\xBF"
-			  "\xFA\xDA\x3D\x75\xF7\x48\xD5\x48"
-			  "\x4B\x52\x7E\xF6\x7C\xAB\x67\x59"
-			  "\xC5\xDC\xA8\xC6\x63\x85\x4A\xDF"
-			  "\xF0\x40\x5F\xCF\xE3\x58\x52\x67"
-			  "\x7A\x24\x32\xC5\xEC\x9E\xA9\x6F"
-			  "\x58\x56\xDD\x94\x1F\x71\x8D\xF4"
-			  "\x6E\xFF\x2C\xA7\xA5\xD8\xBA\xAF"
-			  "\x1D\x8B\xA2\x46\xB5\xC4\x9F\x57"
-			  "\x8D\xD8\xB3\x3C\x02\x0D\xBB\x84"
-			  "\xC7\xBD\xB4\x9A\x6E\xBB\xB1\x37"
-			  "\x95\x79\xC4\xA7\xEA\x1D\xDC\x33"
-			  "\x5D\x0B\x3F\x03\x8F\x30\xF9\xAE"
-			  "\x4F\xFE\x24\x9C\x9A\x02\xE5\x57"
-			  "\xF5\xBC\x25\xD6\x02\x56\x57\x1C",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec cast5_cbc_enc_tv_template[] = {
+static const struct cipher_testvec cast5_cbc_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
 		.klen	= 16,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -28730,83 +27199,7 @@ static const struct cipher_testvec cast5_cbc_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\x05\x28\xCE\x61\x90\x80\xE1\x78"
-			  "\xB9\x2A\x97\x7C\xB0\x83\xD8\x1A"
-			  "\xDE\x58\x7F\xD7\xFD\x72\xB8\xFB"
-			  "\xDA\xF0\x6E\x77\x14\x47\x82\xBA"
-			  "\x29\x0E\x25\x6E\xB4\x39\xD9\x7F"
-			  "\x05\xA7\xA7\x3A\xC1\x5D\x9E\x39"
-			  "\xA7\xFB\x0D\x05\x00\xF3\x58\x67"
-			  "\x60\xEC\x73\x77\x46\x85\x9B\x6A"
-			  "\x08\x3E\xBE\x59\xFB\xE4\x96\x34"
-			  "\xB4\x05\x49\x1A\x97\x43\xAD\xA0"
-			  "\xA9\x1E\x6E\x74\xF1\x94\xEC\xA8"
-			  "\xB5\x8A\x20\xEA\x89\x6B\x19\xAA"
-			  "\xA7\xF1\x33\x67\x90\x23\x0D\xEE"
-			  "\x81\xD5\x78\x4F\xD3\x63\xEA\x46"
-			  "\xB5\xB2\x6E\xBB\xCA\x76\x06\x10"
-			  "\x96\x2A\x0A\xBA\xF9\x41\x5A\x1D"
-			  "\x36\x7C\x56\x14\x54\x83\xFA\xA1"
-			  "\x27\xDD\xBA\x8A\x90\x29\xD6\xA6"
-			  "\xFA\x48\x3E\x1E\x23\x6E\x98\xA8"
-			  "\xA7\xD9\x67\x92\x5C\x13\xB4\x71"
-			  "\xA8\xAA\x89\x4A\xA4\xB3\x49\x7C"
-			  "\x7D\x7F\xCE\x6F\x29\x2E\x7E\x37"
-			  "\xC8\x52\x60\xD9\xE7\xCA\x60\x98"
-			  "\xED\xCD\xE8\x60\x83\xAD\x34\x4D"
-			  "\x96\x4A\x99\x2B\xB7\x14\x75\x66"
-			  "\x6C\x2C\x1A\xBA\x4B\xBB\x49\x56"
-			  "\xE1\x86\xA2\x0E\xD0\xF0\x07\xD3"
-			  "\x18\x38\x09\x9C\x0E\x8B\x86\x07"
-			  "\x90\x12\x37\x49\x27\x98\x69\x18"
-			  "\xB0\xCC\xFB\xD3\xBD\x04\xA0\x85"
-			  "\x4B\x22\x97\x07\xB6\x97\xE9\x95"
-			  "\x0F\x88\x36\xA9\x44\x00\xC6\xE9"
-			  "\x27\x53\x5C\x5B\x1F\xD3\xE2\xEE"
-			  "\xD0\xCD\x63\x30\xA9\xC0\xDD\x49"
-			  "\xFE\x16\xA4\x07\x0D\xE2\x5D\x97"
-			  "\xDE\x89\xBA\x2E\xF3\xA9\x5E\xBE"
-			  "\x03\x55\x0E\x02\x41\x4A\x45\x06"
-			  "\xBE\xEA\x32\xF2\xDC\x91\x5C\x20"
-			  "\x94\x02\x30\xD2\xFC\x29\xFA\x8E"
-			  "\x34\xA0\x31\xB8\x34\xBA\xAE\x54"
-			  "\xB5\x88\x1F\xDC\x43\xDC\x22\x9F"
-			  "\xDC\xCE\xD3\xFA\xA4\xA8\xBC\x8A"
-			  "\xC7\x5A\x43\x21\xA5\xB1\xDB\xC3"
-			  "\x84\x3B\xB4\x9B\xB5\xA7\xF1\x0A"
-			  "\xB6\x37\x21\x19\x55\xC2\xBD\x99"
-			  "\x49\x24\xBB\x7C\xB3\x8E\xEF\xD2"
-			  "\x3A\xCF\xA0\x31\x28\x0E\x25\xA2"
-			  "\x11\xB4\x18\x17\x1A\x65\x92\x56"
-			  "\xE8\xE0\x52\x9C\x61\x18\x2A\xB1"
-			  "\x1A\x01\x22\x45\x17\x62\x52\x6C"
-			  "\x91\x44\xCF\x98\xC7\xC0\x79\x26"
-			  "\x32\x66\x6F\x23\x7F\x94\x36\x88"
-			  "\x3C\xC9\xD0\xB7\x45\x30\x31\x86"
-			  "\x3D\xC6\xA3\x98\x62\x84\x1A\x8B"
-			  "\x16\x88\xC7\xA3\xE9\x4F\xE0\x86"
-			  "\xA4\x93\xA8\x34\x5A\xCA\xDF\xCA"
-			  "\x46\x38\xD2\xF4\xE0\x2D\x1E\xC9"
-			  "\x7C\xEF\x53\xB7\x60\x72\x41\xBF"
-			  "\x29\x00\x87\x02\xAF\x44\x4C\xB7"
-			  "\x8C\xF5\x3F\x19\xF4\x80\x45\xA7"
-			  "\x15\x5F\xDB\xE9\xB1\x83\xD2\xE6"
-			  "\x1D\x18\x66\x44\x5B\x8F\x14\xEB",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec cast5_cbc_dec_tv_template[] = {
-	{ /* Generated from TF test vectors */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
-		.klen	= 16,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x05\x28\xCE\x61\x90\x80\xE1\x78"
+		.ctext	= "\x05\x28\xCE\x61\x90\x80\xE1\x78"
 			  "\xB9\x2A\x97\x7C\xB0\x83\xD8\x1A"
 			  "\xDE\x58\x7F\xD7\xFD\x72\xB8\xFB"
 			  "\xDA\xF0\x6E\x77\x14\x47\x82\xBA"
@@ -28868,96 +27261,32 @@ static const struct cipher_testvec cast5_cbc_dec_tv_template[] = {
 			  "\x8C\xF5\x3F\x19\xF4\x80\x45\xA7"
 			  "\x15\x5F\xDB\xE9\xB1\x83\xD2\xE6"
 			  "\x1D\x18\x66\x44\x5B\x8F\x14\xEB",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec cast5_ctr_enc_tv_template[] = {
+static const struct cipher_testvec cast5_ctr_tv_template[] = {
 	{ /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
 		.klen	= 16,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A",
-		.ilen	= 17,
-		.result	= "\xFF\xC4\x2E\x82\x3D\xF8\xA8\x39"
+		.ctext	= "\xFF\xC4\x2E\x82\x3D\xF8\xA8\x39"
 			  "\x7C\x52\xC4\xD3\xBB\x62\xC6\xA8"
 			  "\x0C",
-		.rlen	= 17,
+		.len	= 17,
 	}, { /* Generated from TF test vectors */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
 		.klen	= 16,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -29019,96 +27348,7 @@ static const struct cipher_testvec cast5_ctr_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\xFF\xC4\x2E\x82\x3D\xF8\xA8\x39"
-			  "\x7C\x52\xC4\xD3\xBB\x62\xC6\xA8"
-			  "\x0C\x63\xA5\x55\xE3\xF8\x1C\x7F"
-			  "\xDC\x59\xF9\xA0\x52\xAD\x83\xDF"
-			  "\xD5\x3B\x53\x4A\xAA\x1F\x49\x44"
-			  "\xE8\x20\xCC\xF8\x97\xE6\xE0\x3C"
-			  "\x5A\xD2\x83\xEC\xEE\x25\x3F\xCF"
-			  "\x0D\xC2\x79\x80\x99\x6E\xFF\x7B"
-			  "\x64\xB0\x7B\x86\x29\x1D\x9F\x17"
-			  "\x10\xA5\xA5\xEB\x16\x55\x9E\xE3"
-			  "\x88\x18\x52\x56\x48\x58\xD1\x6B"
-			  "\xE8\x74\x6E\x48\xB0\x2E\x69\x63"
-			  "\x32\xAA\xAC\x26\x55\x45\x94\xDE"
-			  "\x30\x26\x26\xE6\x08\x82\x2F\x5F"
-			  "\xA7\x15\x94\x07\x75\x2D\xC6\x3A"
-			  "\x1B\xA0\x39\xFB\xBA\xB9\x06\x56"
-			  "\xF6\x9F\xF1\x2F\x9B\xF3\x89\x8B"
-			  "\x08\xC8\x9D\x5E\x6B\x95\x09\xC7"
-			  "\x98\xB7\x62\xA4\x1D\x25\xFA\xC5"
-			  "\x62\xC8\x5D\x6B\xB4\x85\x88\x7F"
-			  "\x3B\x29\xF9\xB4\x32\x62\x69\xBF"
-			  "\x32\xB8\xEB\xFD\x0E\x26\xAA\xA3"
-			  "\x44\x67\x90\x20\xAC\x41\xDF\x43"
-			  "\xC6\xC7\x19\x9F\x2C\x28\x74\xEB"
-			  "\x3E\x7F\x7A\x80\x5B\xE4\x08\x60"
-			  "\xC7\xC9\x71\x34\x44\xCE\x05\xFD"
-			  "\xA8\x91\xA8\x44\x5E\xD3\x89\x2C"
-			  "\xAE\x59\x0F\x07\x88\x79\x53\x26"
-			  "\xAF\xAC\xCB\x1D\x6F\x08\x25\x62"
-			  "\xD0\x82\x65\x66\xE4\x2A\x29\x1C"
-			  "\x9C\x64\x5F\x49\x9D\xF8\x62\xF9"
-			  "\xED\xC4\x13\x52\x75\xDC\xE4\xF9"
-			  "\x68\x0F\x8A\xCD\xA6\x8D\x75\xAA"
-			  "\x49\xA1\x86\x86\x37\x5C\x6B\x3D"
-			  "\x56\xE5\x6F\xBE\x27\xC0\x10\xF8"
-			  "\x3C\x4D\x17\x35\x14\xDC\x1C\xA0"
-			  "\x6E\xAE\xD1\x10\xDD\x83\x06\xC2"
-			  "\x23\xD3\xC7\x27\x15\x04\x2C\x27"
-			  "\xDD\x1F\x2E\x97\x09\x9C\x33\x7D"
-			  "\xAC\x50\x1B\x2E\xC9\x52\x0C\x14"
-			  "\x4B\x78\xC4\xDE\x07\x6A\x12\x02"
-			  "\x6E\xD7\x4B\x91\xB9\x88\x4D\x02"
-			  "\xC3\xB5\x04\xBC\xE0\x67\xCA\x18"
-			  "\x22\xA1\xAE\x9A\x21\xEF\xB2\x06"
-			  "\x35\xCD\xEC\x37\x70\x2D\xFC\x1E"
-			  "\xA8\x31\xE7\xFC\xE5\x8E\x88\x66"
-			  "\x16\xB5\xC8\x45\x21\x37\xBD\x24"
-			  "\xA9\xD5\x36\x12\x9F\x6E\x67\x80"
-			  "\x87\x54\xD5\xAF\x97\xE1\x15\xA7"
-			  "\x11\xF0\x63\x7B\xE1\x44\x14\x1C"
-			  "\x06\x32\x05\x8C\x6C\xDB\x9B\x36"
-			  "\x6A\x6B\xAD\x3A\x27\x55\x20\x4C"
-			  "\x76\x36\x43\xE8\x16\x60\xB5\xF3"
-			  "\xDF\x5A\xC6\xA5\x69\x78\x59\x51"
-			  "\x54\x68\x65\x06\x84\xDE\x3D\xAE"
-			  "\x38\x91\xBD\xCC\xA2\x8A\xEC\xE6"
-			  "\x9E\x83\xAE\x1E\x8E\x34\x5D\xDE"
-			  "\x91\xCE\x8F\xED\x40\xF7\xC8\x8B"
-			  "\x9A\x13\x4C\xAD\x89\x97\x9E\xD1"
-			  "\x91\x01\xD7\x21\x23\x28\x1E\xCC"
-			  "\x8C\x98\xDB\xDE\xFC\x72\x94\xAA"
-			  "\xC0\x0D\x96\xAA\x23\xF8\xFE\x13",
-		.rlen	= 496,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 496 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec cast5_ctr_dec_tv_template[] = {
-	{ /* Generated from TF test vectors */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
-		.klen	= 16,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\xFF\xC4\x2E\x82\x3D\xF8\xA8\x39"
-			  "\x7C\x52\xC4\xD3\xBB\x62\xC6\xA8"
-			  "\x0C",
-		.ilen	= 17,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A",
-		.rlen	= 17,
-	}, { /* Generated from TF test vectors */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A",
-		.klen	= 16,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F",
-		.input	= "\xFF\xC4\x2E\x82\x3D\xF8\xA8\x39"
+		.ctext	= "\xFF\xC4\x2E\x82\x3D\xF8\xA8\x39"
 			  "\x7C\x52\xC4\xD3\xBB\x62\xC6\xA8"
 			  "\x0C\x63\xA5\x55\xE3\xF8\x1C\x7F"
 			  "\xDC\x59\xF9\xA0\x52\xAD\x83\xDF"
@@ -29170,70 +27410,7 @@ static const struct cipher_testvec cast5_ctr_dec_tv_template[] = {
 			  "\x91\x01\xD7\x21\x23\x28\x1E\xCC"
 			  "\x8C\x98\xDB\xDE\xFC\x72\x94\xAA"
 			  "\xC0\x0D\x96\xAA\x23\xF8\xFE\x13",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
+		.len	= 496,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 496 - 20, 4, 16 },
@@ -29243,408 +27420,190 @@ static const struct cipher_testvec cast5_ctr_dec_tv_template[] = {
 /*
  * ARC4 test vectors from OpenSSL
  */
-static const struct cipher_testvec arc4_enc_tv_template[] = {
+static const struct cipher_testvec arc4_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.ilen	= 8,
-		.result	= "\x75\xb7\x87\x80\x99\xe0\xc5\x96",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.ctext	= "\x75\xb7\x87\x80\x99\xe0\xc5\x96",
+		.len	= 8,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 8,
-		.result	= "\x74\x94\xc2\xe7\x10\x4b\x08\x79",
-		.rlen	= 8,
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ctext	= "\x74\x94\xc2\xe7\x10\x4b\x08\x79",
+		.len	= 8,
 	}, {
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 8,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 8,
-		.result	= "\xde\x18\x89\x41\xa3\x37\x5d\x3a",
-		.rlen	= 8,
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ctext	= "\xde\x18\x89\x41\xa3\x37\x5d\x3a",
+		.len	= 8,
 	}, {
 		.key	= "\xef\x01\x23\x45",
 		.klen	= 4,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00",
-		.ilen	= 20,
-		.result	= "\xd6\xa1\x41\xa7\xec\x3c\x38\xdf"
+		.ctext	= "\xd6\xa1\x41\xa7\xec\x3c\x38\xdf"
 			  "\xbd\x61\x5a\x11\x62\xe1\xc7\xba"
 			  "\x36\xb6\x78\x58",
-		.rlen	= 20,
+		.len	= 20,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
 		.klen	= 8,
-		.input	= "\x12\x34\x56\x78\x9A\xBC\xDE\xF0"
+		.ptext	= "\x12\x34\x56\x78\x9A\xBC\xDE\xF0"
 			  "\x12\x34\x56\x78\x9A\xBC\xDE\xF0"
 			  "\x12\x34\x56\x78\x9A\xBC\xDE\xF0"
 			  "\x12\x34\x56\x78",
-		.ilen	= 28,
-		.result	= "\x66\xa0\x94\x9f\x8a\xf7\xd6\x89"
+		.ctext	= "\x66\xa0\x94\x9f\x8a\xf7\xd6\x89"
 			  "\x1f\x7f\x83\x2b\xa8\x33\xc0\x0c"
 			  "\x89\x2e\xbe\x30\x14\x3c\xe2\x87"
 			  "\x40\x01\x1e\xcf",
-		.rlen	= 28,
+		.len	= 28,
 	}, {
 		.key	= "\xef\x01\x23\x45",
 		.klen	= 4,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00",
-		.ilen	= 10,
-		.result	= "\xd6\xa1\x41\xa7\xec\x3c\x38\xdf"
+		.ctext	= "\xd6\xa1\x41\xa7\xec\x3c\x38\xdf"
 			  "\xbd\x61",
-		.rlen	= 10,
+		.len	= 10,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
 			"\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 16,
-		.input	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF",
-		.ilen	= 8,
-		.result	= "\x69\x72\x36\x59\x1B\x52\x42\xB1",
-		.rlen	= 8,
-	},
-};
-
-static const struct cipher_testvec arc4_dec_tv_template[] = {
-	{
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.input	= "\x75\xb7\x87\x80\x99\xe0\xc5\x96",
-		.ilen	= 8,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.rlen	= 8,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.input	= "\x74\x94\xc2\xe7\x10\x4b\x08\x79",
-		.ilen	= 8,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 8,
-	}, {
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 8,
-		.input	= "\xde\x18\x89\x41\xa3\x37\x5d\x3a",
-		.ilen	= 8,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 8,
-	}, {
-		.key	= "\xef\x01\x23\x45",
-		.klen	= 4,
-		.input	= "\xd6\xa1\x41\xa7\xec\x3c\x38\xdf"
-			  "\xbd\x61\x5a\x11\x62\xe1\xc7\xba"
-			  "\x36\xb6\x78\x58",
-		.ilen	= 20,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00",
-		.rlen	= 20,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef",
-		.klen	= 8,
-		.input	= "\x66\xa0\x94\x9f\x8a\xf7\xd6\x89"
-			  "\x1f\x7f\x83\x2b\xa8\x33\xc0\x0c"
-			  "\x89\x2e\xbe\x30\x14\x3c\xe2\x87"
-			  "\x40\x01\x1e\xcf",
-		.ilen	= 28,
-		.result	= "\x12\x34\x56\x78\x9A\xBC\xDE\xF0"
-			  "\x12\x34\x56\x78\x9A\xBC\xDE\xF0"
-			  "\x12\x34\x56\x78\x9A\xBC\xDE\xF0"
-			  "\x12\x34\x56\x78",
-		.rlen	= 28,
-	}, {
-		.key	= "\xef\x01\x23\x45",
-		.klen	= 4,
-		.input	= "\xd6\xa1\x41\xa7\xec\x3c\x38\xdf"
-			  "\xbd\x61",
-		.ilen	= 10,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00",
-		.rlen	= 10,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
-			"\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 16,
-		.input	= "\x69\x72\x36\x59\x1B\x52\x42\xB1",
-		.ilen	= 8,
-		.result	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF",
-		.rlen	= 8,
+		.ptext	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF",
+		.ctext	= "\x69\x72\x36\x59\x1B\x52\x42\xB1",
+		.len	= 8,
 	},
 };
 
 /*
  * TEA test vectors
  */
-static const struct cipher_testvec tea_enc_tv_template[] = {
+static const struct cipher_testvec tea_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
-		.input  = zeroed_string,
-		.ilen	= 8,
-		.result	= "\x0a\x3a\xea\x41\x40\xa9\xba\x94",
-		.rlen	= 8,
+		.ptext	= zeroed_string,
+		.ctext	= "\x0a\x3a\xea\x41\x40\xa9\xba\x94",
+		.len	= 8,
 	}, {
 		.key	= "\x2b\x02\x05\x68\x06\x14\x49\x76"
 			  "\x77\x5d\x0e\x26\x6c\x28\x78\x43",
 		.klen	= 16,
-		.input	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
-		.ilen	= 8,
-		.result	= "\x77\x5d\x2a\x6a\xf6\xce\x92\x09",
-		.rlen	= 8,
+		.ptext	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
+		.ctext	= "\x77\x5d\x2a\x6a\xf6\xce\x92\x09",
+		.len	= 8,
 	}, {
 		.key	= "\x09\x65\x43\x11\x66\x44\x39\x25"
 			  "\x51\x3a\x16\x10\x0a\x08\x12\x6e",
 		.klen	= 16,
-		.input	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
+		.ptext	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
 			  "\x65\x73\x74\x5f\x76\x65\x63\x74",
-		.ilen	= 16,
-		.result	= "\xbe\x7a\xbb\x81\x95\x2d\x1f\x1e"
+		.ctext	= "\xbe\x7a\xbb\x81\x95\x2d\x1f\x1e"
 			  "\xdd\x89\xa1\x25\x04\x21\xdf\x95",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x4d\x76\x32\x17\x05\x3f\x75\x2c"
 			  "\x5d\x04\x16\x36\x15\x72\x63\x2f",
 		.klen	= 16,
-		.input	= "\x54\x65\x61\x20\x69\x73\x20\x67"
+		.ptext	= "\x54\x65\x61\x20\x69\x73\x20\x67"
 			  "\x6f\x6f\x64\x20\x66\x6f\x72\x20"
 			  "\x79\x6f\x75\x21\x21\x21\x20\x72"
 			  "\x65\x61\x6c\x6c\x79\x21\x21\x21",
-		.ilen	= 32,
-		.result	= "\xe0\x4d\x5d\x3c\xb7\x8c\x36\x47"
-			  "\x94\x18\x95\x91\xa9\xfc\x49\xf8"
-			  "\x44\xd1\x2d\xc2\x99\xb8\x08\x2a"
-			  "\x07\x89\x73\xc2\x45\x92\xc6\x90",
-		.rlen	= 32,
-	}
-};
-
-static const struct cipher_testvec tea_dec_tv_template[] = {
-	{
-		.key    = zeroed_string,
-		.klen	= 16,
-		.input	= "\x0a\x3a\xea\x41\x40\xa9\xba\x94",
-		.ilen	= 8,
-		.result = zeroed_string,
-		.rlen	= 8,
-	}, {
-		.key	= "\x2b\x02\x05\x68\x06\x14\x49\x76"
-			  "\x77\x5d\x0e\x26\x6c\x28\x78\x43",
-		.klen	= 16,
-		.input	= "\x77\x5d\x2a\x6a\xf6\xce\x92\x09",
-		.ilen	= 8,
-		.result	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
-		.rlen	= 8,
-	}, {
-		.key	= "\x09\x65\x43\x11\x66\x44\x39\x25"
-			  "\x51\x3a\x16\x10\x0a\x08\x12\x6e",
-		.klen	= 16,
-		.input	= "\xbe\x7a\xbb\x81\x95\x2d\x1f\x1e"
-			  "\xdd\x89\xa1\x25\x04\x21\xdf\x95",
-		.ilen   = 16,
-		.result	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
-			  "\x65\x73\x74\x5f\x76\x65\x63\x74",
-		.rlen	= 16,
-	}, {
-		.key	= "\x4d\x76\x32\x17\x05\x3f\x75\x2c"
-			  "\x5d\x04\x16\x36\x15\x72\x63\x2f",
-		.klen	= 16,
-		.input	= "\xe0\x4d\x5d\x3c\xb7\x8c\x36\x47"
+		.ctext	= "\xe0\x4d\x5d\x3c\xb7\x8c\x36\x47"
 			  "\x94\x18\x95\x91\xa9\xfc\x49\xf8"
 			  "\x44\xd1\x2d\xc2\x99\xb8\x08\x2a"
 			  "\x07\x89\x73\xc2\x45\x92\xc6\x90",
-		.ilen	= 32,
-		.result	= "\x54\x65\x61\x20\x69\x73\x20\x67"
-			  "\x6f\x6f\x64\x20\x66\x6f\x72\x20"
-			  "\x79\x6f\x75\x21\x21\x21\x20\x72"
-			  "\x65\x61\x6c\x6c\x79\x21\x21\x21",
-		.rlen	= 32,
+		.len	= 32,
 	}
 };
 
 /*
  * XTEA test vectors
  */
-static const struct cipher_testvec xtea_enc_tv_template[] = {
+static const struct cipher_testvec xtea_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
-		.input  = zeroed_string,
-		.ilen	= 8,
-		.result	= "\xd8\xd4\xe9\xde\xd9\x1e\x13\xf7",
-		.rlen	= 8,
+		.ptext	= zeroed_string,
+		.ctext	= "\xd8\xd4\xe9\xde\xd9\x1e\x13\xf7",
+		.len	= 8,
 	}, {
 		.key	= "\x2b\x02\x05\x68\x06\x14\x49\x76"
 			  "\x77\x5d\x0e\x26\x6c\x28\x78\x43",
 		.klen	= 16,
-		.input	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
-		.ilen	= 8,
-		.result	= "\x94\xeb\xc8\x96\x84\x6a\x49\xa8",
-		.rlen	= 8,
+		.ptext	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
+		.ctext	= "\x94\xeb\xc8\x96\x84\x6a\x49\xa8",
+		.len	= 8,
 	}, {
 		.key	= "\x09\x65\x43\x11\x66\x44\x39\x25"
 			  "\x51\x3a\x16\x10\x0a\x08\x12\x6e",
 		.klen	= 16,
-		.input	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
+		.ptext	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
 			  "\x65\x73\x74\x5f\x76\x65\x63\x74",
-		.ilen	= 16,
-		.result	= "\x3e\xce\xae\x22\x60\x56\xa8\x9d"
+		.ctext	= "\x3e\xce\xae\x22\x60\x56\xa8\x9d"
 			  "\x77\x4d\xd4\xb4\x87\x24\xe3\x9a",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x4d\x76\x32\x17\x05\x3f\x75\x2c"
 			  "\x5d\x04\x16\x36\x15\x72\x63\x2f",
 		.klen	= 16,
-		.input	= "\x54\x65\x61\x20\x69\x73\x20\x67"
+		.ptext	= "\x54\x65\x61\x20\x69\x73\x20\x67"
 			  "\x6f\x6f\x64\x20\x66\x6f\x72\x20"
 			  "\x79\x6f\x75\x21\x21\x21\x20\x72"
 			  "\x65\x61\x6c\x6c\x79\x21\x21\x21",
-		.ilen	= 32,
-		.result	= "\x99\x81\x9f\x5d\x6f\x4b\x31\x3a"
-			  "\x86\xff\x6f\xd0\xe3\x87\x70\x07"
-			  "\x4d\xb8\xcf\xf3\x99\x50\xb3\xd4"
-			  "\x73\xa2\xfa\xc9\x16\x59\x5d\x81",
-		.rlen	= 32,
-	}
-};
-
-static const struct cipher_testvec xtea_dec_tv_template[] = {
-	{
-		.key    = zeroed_string,
-		.klen	= 16,
-		.input	= "\xd8\xd4\xe9\xde\xd9\x1e\x13\xf7",
-		.ilen	= 8,
-		.result = zeroed_string,
-		.rlen	= 8,
-	}, {
-		.key	= "\x2b\x02\x05\x68\x06\x14\x49\x76"
-			  "\x77\x5d\x0e\x26\x6c\x28\x78\x43",
-		.klen	= 16,
-		.input	= "\x94\xeb\xc8\x96\x84\x6a\x49\xa8",
-		.ilen	= 8,
-		.result	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
-		.rlen	= 8,
-	}, {
-		.key	= "\x09\x65\x43\x11\x66\x44\x39\x25"
-			  "\x51\x3a\x16\x10\x0a\x08\x12\x6e",
-		.klen	= 16,
-		.input	= "\x3e\xce\xae\x22\x60\x56\xa8\x9d"
-			  "\x77\x4d\xd4\xb4\x87\x24\xe3\x9a",
-		.ilen	= 16,
-		.result	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
-			  "\x65\x73\x74\x5f\x76\x65\x63\x74",
-		.rlen	= 16,
-	}, {
-		.key	= "\x4d\x76\x32\x17\x05\x3f\x75\x2c"
-			  "\x5d\x04\x16\x36\x15\x72\x63\x2f",
-		.klen	= 16,
-		.input	= "\x99\x81\x9f\x5d\x6f\x4b\x31\x3a"
+		.ctext	= "\x99\x81\x9f\x5d\x6f\x4b\x31\x3a"
 			  "\x86\xff\x6f\xd0\xe3\x87\x70\x07"
 			  "\x4d\xb8\xcf\xf3\x99\x50\xb3\xd4"
 			  "\x73\xa2\xfa\xc9\x16\x59\x5d\x81",
-		.ilen	= 32,
-		.result	= "\x54\x65\x61\x20\x69\x73\x20\x67"
-			  "\x6f\x6f\x64\x20\x66\x6f\x72\x20"
-			  "\x79\x6f\x75\x21\x21\x21\x20\x72"
-			  "\x65\x61\x6c\x6c\x79\x21\x21\x21",
-		.rlen	= 32,
+		.len	= 32,
 	}
 };
 
 /*
  * KHAZAD test vectors.
  */
-static const struct cipher_testvec khazad_enc_tv_template[] = {
+static const struct cipher_testvec khazad_tv_template[] = {
 	{
 		.key	= "\x80\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 16,
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 8,
-		.result	= "\x49\xa4\xce\x32\xac\x19\x0e\x3f",
-		.rlen	= 8,
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ctext	= "\x49\xa4\xce\x32\xac\x19\x0e\x3f",
+		.len	= 8,
 	}, {
 		.key	= "\x38\x38\x38\x38\x38\x38\x38\x38"
 			  "\x38\x38\x38\x38\x38\x38\x38\x38",
 		.klen	= 16,
-		.input	= "\x38\x38\x38\x38\x38\x38\x38\x38",
-		.ilen	= 8,
-		.result	= "\x7e\x82\x12\xa1\xd9\x5b\xe4\xf9",
-		.rlen	= 8,
+		.ptext	= "\x38\x38\x38\x38\x38\x38\x38\x38",
+		.ctext	= "\x7e\x82\x12\xa1\xd9\x5b\xe4\xf9",
+		.len	= 8,
 	}, {
 		.key	= "\xa2\xa2\xa2\xa2\xa2\xa2\xa2\xa2"
 			"\xa2\xa2\xa2\xa2\xa2\xa2\xa2\xa2",
 		.klen	= 16,
-		.input	= "\xa2\xa2\xa2\xa2\xa2\xa2\xa2\xa2",
-		.ilen	= 8,
-		.result	= "\xaa\xbe\xc1\x95\xc5\x94\x1a\x9c",
-		.rlen	= 8,
+		.ptext	= "\xa2\xa2\xa2\xa2\xa2\xa2\xa2\xa2",
+		.ctext	= "\xaa\xbe\xc1\x95\xc5\x94\x1a\x9c",
+		.len	= 8,
 	}, {
 		.key	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f"
 			"\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
 		.klen	= 16,
-		.input	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
-		.ilen	= 8,
-		.result = "\x04\x74\xf5\x70\x50\x16\xd3\xb8",
-		.rlen	= 8,
+		.ptext	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
+		.ctext	= "\x04\x74\xf5\x70\x50\x16\xd3\xb8",
+		.len	= 8,
 	}, {
 		.key	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f"
 			"\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
 		.klen	= 16,
-		.input	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f"
+		.ptext	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f"
 			"\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
-		.ilen	= 16,
-		.result = "\x04\x74\xf5\x70\x50\x16\xd3\xb8"
+		.ctext	= "\x04\x74\xf5\x70\x50\x16\xd3\xb8"
 			"\x04\x74\xf5\x70\x50\x16\xd3\xb8",
-		.rlen	= 16,
-	},
-};
-
-static const struct cipher_testvec khazad_dec_tv_template[] = {
-	{
-		.key	= "\x80\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 16,
-		.input	= "\x49\xa4\xce\x32\xac\x19\x0e\x3f",
-		.ilen	= 8,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 8,
-	}, {
-		.key	= "\x38\x38\x38\x38\x38\x38\x38\x38"
-			  "\x38\x38\x38\x38\x38\x38\x38\x38",
-		.klen	= 16,
-		.input	= "\x7e\x82\x12\xa1\xd9\x5b\xe4\xf9",
-		.ilen	= 8,
-		.result	= "\x38\x38\x38\x38\x38\x38\x38\x38",
-		.rlen	= 8,
-	}, {
-		.key	= "\xa2\xa2\xa2\xa2\xa2\xa2\xa2\xa2"
-			"\xa2\xa2\xa2\xa2\xa2\xa2\xa2\xa2",
-		.klen	= 16,
-		.input	= "\xaa\xbe\xc1\x95\xc5\x94\x1a\x9c",
-		.ilen	= 8,
-		.result	= "\xa2\xa2\xa2\xa2\xa2\xa2\xa2\xa2",
-		.rlen	= 8,
-	}, {
-		.key	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f"
-			"\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
-		.klen	= 16,
-		.input  = "\x04\x74\xf5\x70\x50\x16\xd3\xb8",
-		.ilen	= 8,
-		.result	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
-		.rlen	= 8,
-	}, {
-		.key	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f"
-			"\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
-		.klen	= 16,
-		.input  = "\x04\x74\xf5\x70\x50\x16\xd3\xb8"
-			"\x04\x74\xf5\x70\x50\x16\xd3\xb8",
-		.ilen	= 16,
-		.result	= "\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f"
-			"\x2f\x2f\x2f\x2f\x2f\x2f\x2f\x2f",
-		.rlen	= 16,
+		.len	= 16,
 	},
 };
 
@@ -29652,53 +27611,49 @@ static const struct cipher_testvec khazad_dec_tv_template[] = {
  * Anubis test vectors.
  */
 
-static const struct cipher_testvec anubis_enc_tv_template[] = {
+static const struct cipher_testvec anubis_tv_template[] = {
 	{
 		.key	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
 		.klen	= 16,
-		.input	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
+		.ptext	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
-		.ilen	= 16,
-		.result	= "\x6d\xc5\xda\xa2\x26\x7d\x62\x6f"
+		.ctext	= "\x6d\xc5\xda\xa2\x26\x7d\x62\x6f"
 			  "\x08\xb7\x52\x8e\x6e\x6e\x86\x90",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 
 		.key	= "\x03\x03\x03\x03\x03\x03\x03\x03"
 			  "\x03\x03\x03\x03\x03\x03\x03\x03"
 			  "\x03\x03\x03\x03",
 		.klen	= 20,
-		.input	= "\x03\x03\x03\x03\x03\x03\x03\x03"
+		.ptext	= "\x03\x03\x03\x03\x03\x03\x03\x03"
 			  "\x03\x03\x03\x03\x03\x03\x03\x03",
-		.ilen	= 16,
-		.result	= "\xdb\xf1\x42\xf4\xd1\x8a\xc7\x49"
+		.ctext	= "\xdb\xf1\x42\xf4\xd1\x8a\xc7\x49"
 			  "\x87\x41\x6f\x82\x0a\x98\x64\xae",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x24\x24\x24\x24\x24\x24\x24\x24"
 			  "\x24\x24\x24\x24\x24\x24\x24\x24"
 			  "\x24\x24\x24\x24\x24\x24\x24\x24"
 			  "\x24\x24\x24\x24",
 		.klen	= 28,
-		.input	= "\x24\x24\x24\x24\x24\x24\x24\x24"
+		.ptext	= "\x24\x24\x24\x24\x24\x24\x24\x24"
 			  "\x24\x24\x24\x24\x24\x24\x24\x24",
-		.ilen	= 16,
-		.result	= "\xfd\x1b\x4a\xe3\xbf\xf0\xad\x3d"
+		.ctext	= "\xfd\x1b\x4a\xe3\xbf\xf0\xad\x3d"
 			  "\x06\xd3\x61\x27\xfd\x13\x9e\xde",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x25\x25\x25\x25\x25\x25\x25\x25"
 			  "\x25\x25\x25\x25\x25\x25\x25\x25"
 			  "\x25\x25\x25\x25\x25\x25\x25\x25"
 			  "\x25\x25\x25\x25\x25\x25\x25\x25",
 		.klen	= 32,
-		.input	= "\x25\x25\x25\x25\x25\x25\x25\x25"
+		.ptext	= "\x25\x25\x25\x25\x25\x25\x25\x25"
 			  "\x25\x25\x25\x25\x25\x25\x25\x25",
-		.ilen	= 16,
-		.result	= "\x1a\x91\xfb\x2b\xb7\x78\x6b\xc4"
+		.ctext	= "\x1a\x91\xfb\x2b\xb7\x78\x6b\xc4"
 			"\x17\xd9\xff\x40\x3b\x0e\xe5\xfe",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x35\x35\x35\x35\x35\x35\x35\x35"
 			  "\x35\x35\x35\x35\x35\x35\x35\x35"
@@ -29706,93 +27661,28 @@ static const struct cipher_testvec anubis_enc_tv_template[] = {
 			  "\x35\x35\x35\x35\x35\x35\x35\x35"
 			  "\x35\x35\x35\x35\x35\x35\x35\x35",
 		.klen	= 40,
-		.input	= "\x35\x35\x35\x35\x35\x35\x35\x35"
+		.ptext	= "\x35\x35\x35\x35\x35\x35\x35\x35"
 			  "\x35\x35\x35\x35\x35\x35\x35\x35",
-		.ilen	= 16,
-		.result = "\xa5\x2c\x85\x6f\x9c\xba\xa0\x97"
+		.ctext	= "\xa5\x2c\x85\x6f\x9c\xba\xa0\x97"
 			  "\x9e\xc6\x84\x0f\x17\x21\x07\xee",
-		.rlen	= 16,
+		.len	= 16,
 	},
 };
 
-static const struct cipher_testvec anubis_dec_tv_template[] = {
+static const struct cipher_testvec anubis_cbc_tv_template[] = {
 	{
 		.key	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
 		.klen	= 16,
-		.input	= "\x6d\xc5\xda\xa2\x26\x7d\x62\x6f"
-			  "\x08\xb7\x52\x8e\x6e\x6e\x86\x90",
-		.ilen	= 16,
-		.result	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
-			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
-		.rlen	= 16,
-	}, {
-
-		.key	= "\x03\x03\x03\x03\x03\x03\x03\x03"
-			  "\x03\x03\x03\x03\x03\x03\x03\x03"
-			  "\x03\x03\x03\x03",
-		.klen	= 20,
-		.input	= "\xdb\xf1\x42\xf4\xd1\x8a\xc7\x49"
-			  "\x87\x41\x6f\x82\x0a\x98\x64\xae",
-		.ilen	= 16,
-		.result	= "\x03\x03\x03\x03\x03\x03\x03\x03"
-			  "\x03\x03\x03\x03\x03\x03\x03\x03",
-		.rlen	= 16,
-	}, {
-		.key	= "\x24\x24\x24\x24\x24\x24\x24\x24"
-			  "\x24\x24\x24\x24\x24\x24\x24\x24"
-			  "\x24\x24\x24\x24\x24\x24\x24\x24"
-			  "\x24\x24\x24\x24",
-		.klen	= 28,
-		.input	= "\xfd\x1b\x4a\xe3\xbf\xf0\xad\x3d"
-			  "\x06\xd3\x61\x27\xfd\x13\x9e\xde",
-		.ilen	= 16,
-		.result	= "\x24\x24\x24\x24\x24\x24\x24\x24"
-			  "\x24\x24\x24\x24\x24\x24\x24\x24",
-		.rlen	= 16,
-	}, {
-		.key	= "\x25\x25\x25\x25\x25\x25\x25\x25"
-			  "\x25\x25\x25\x25\x25\x25\x25\x25"
-			  "\x25\x25\x25\x25\x25\x25\x25\x25"
-			  "\x25\x25\x25\x25\x25\x25\x25\x25",
-		.klen	= 32,
-		.input	= "\x1a\x91\xfb\x2b\xb7\x78\x6b\xc4"
-			"\x17\xd9\xff\x40\x3b\x0e\xe5\xfe",
-		.ilen	= 16,
-		.result	= "\x25\x25\x25\x25\x25\x25\x25\x25"
-			  "\x25\x25\x25\x25\x25\x25\x25\x25",
-		.rlen	= 16,
-	}, {
-		.key	= "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35",
-		.input = "\xa5\x2c\x85\x6f\x9c\xba\xa0\x97"
-			 "\x9e\xc6\x84\x0f\x17\x21\x07\xee",
-		.klen	= 40,
-		.ilen	= 16,
-		.result	= "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35",
-		.rlen	= 16,
-	},
-};
-
-static const struct cipher_testvec anubis_cbc_enc_tv_template[] = {
-	{
-		.key	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
-			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
-		.klen	= 16,
-		.input	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
+		.ptext	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
 			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
-		.ilen	= 32,
-		.result	= "\x6d\xc5\xda\xa2\x26\x7d\x62\x6f"
+		.ctext	= "\x6d\xc5\xda\xa2\x26\x7d\x62\x6f"
 			  "\x08\xb7\x52\x8e\x6e\x6e\x86\x90"
 			  "\x86\xd8\xb5\x6f\x98\x5e\x8a\x66"
 			  "\x4f\x1f\x78\xa1\xbb\x37\xf1\xbe",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x35\x35\x35\x35\x35\x35\x35\x35"
 			  "\x35\x35\x35\x35\x35\x35\x35\x35"
@@ -29800,263 +27690,114 @@ static const struct cipher_testvec anubis_cbc_enc_tv_template[] = {
 			  "\x35\x35\x35\x35\x35\x35\x35\x35"
 			  "\x35\x35\x35\x35\x35\x35\x35\x35",
 		.klen	= 40,
-		.input	= "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35",
-		.ilen	= 32,
-		.result = "\xa5\x2c\x85\x6f\x9c\xba\xa0\x97"
-			  "\x9e\xc6\x84\x0f\x17\x21\x07\xee"
-			  "\xa2\xbc\x06\x98\xc6\x4b\xda\x75"
-			  "\x2e\xaa\xbe\x58\xce\x01\x5b\xc7",
-		.rlen	= 32,
-	},
-};
-
-static const struct cipher_testvec anubis_cbc_dec_tv_template[] = {
-	{
-		.key	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
-			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
-		.klen	= 16,
-		.input	= "\x6d\xc5\xda\xa2\x26\x7d\x62\x6f"
-			  "\x08\xb7\x52\x8e\x6e\x6e\x86\x90"
-			  "\x86\xd8\xb5\x6f\x98\x5e\x8a\x66"
-			  "\x4f\x1f\x78\xa1\xbb\x37\xf1\xbe",
-		.ilen	= 32,
-		.result	= "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
-			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
-			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
-			  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe",
-		.rlen	= 32,
-	}, {
-		.key	= "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35"
+		.ptext	= "\x35\x35\x35\x35\x35\x35\x35\x35"
 			  "\x35\x35\x35\x35\x35\x35\x35\x35"
 			  "\x35\x35\x35\x35\x35\x35\x35\x35"
 			  "\x35\x35\x35\x35\x35\x35\x35\x35",
-		.klen	= 40,
-		.input = "\xa5\x2c\x85\x6f\x9c\xba\xa0\x97"
+		.ctext	= "\xa5\x2c\x85\x6f\x9c\xba\xa0\x97"
 			  "\x9e\xc6\x84\x0f\x17\x21\x07\xee"
 			  "\xa2\xbc\x06\x98\xc6\x4b\xda\x75"
 			  "\x2e\xaa\xbe\x58\xce\x01\x5b\xc7",
-		.ilen	= 32,
-		.result	= "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35"
-			  "\x35\x35\x35\x35\x35\x35\x35\x35",
-		.rlen	= 32,
+		.len	= 32,
 	},
 };
 
 /*
  * XETA test vectors
  */
-static const struct cipher_testvec xeta_enc_tv_template[] = {
+static const struct cipher_testvec xeta_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
-		.input  = zeroed_string,
-		.ilen	= 8,
-		.result	= "\xaa\x22\x96\xe5\x6c\x61\xf3\x45",
-		.rlen	= 8,
+		.ptext	= zeroed_string,
+		.ctext	= "\xaa\x22\x96\xe5\x6c\x61\xf3\x45",
+		.len	= 8,
 	}, {
 		.key	= "\x2b\x02\x05\x68\x06\x14\x49\x76"
 			  "\x77\x5d\x0e\x26\x6c\x28\x78\x43",
 		.klen	= 16,
-		.input	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
-		.ilen	= 8,
-		.result	= "\x82\x3e\xeb\x35\xdc\xdd\xd9\xc3",
-		.rlen	= 8,
+		.ptext	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
+		.ctext	= "\x82\x3e\xeb\x35\xdc\xdd\xd9\xc3",
+		.len	= 8,
 	}, {
 		.key	= "\x09\x65\x43\x11\x66\x44\x39\x25"
 			  "\x51\x3a\x16\x10\x0a\x08\x12\x6e",
 		.klen	= 16,
-		.input	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
+		.ptext	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
 			  "\x65\x73\x74\x5f\x76\x65\x63\x74",
-		.ilen	= 16,
-		.result	= "\xe2\x04\xdb\xf2\x89\x85\x9e\xea"
+		.ctext	= "\xe2\x04\xdb\xf2\x89\x85\x9e\xea"
 			  "\x61\x35\xaa\xed\xb5\xcb\x71\x2c",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x4d\x76\x32\x17\x05\x3f\x75\x2c"
 			  "\x5d\x04\x16\x36\x15\x72\x63\x2f",
 		.klen	= 16,
-		.input	= "\x54\x65\x61\x20\x69\x73\x20\x67"
+		.ptext	= "\x54\x65\x61\x20\x69\x73\x20\x67"
 			  "\x6f\x6f\x64\x20\x66\x6f\x72\x20"
 			  "\x79\x6f\x75\x21\x21\x21\x20\x72"
 			  "\x65\x61\x6c\x6c\x79\x21\x21\x21",
-		.ilen	= 32,
-		.result	= "\x0b\x03\xcd\x8a\xbe\x95\xfd\xb1"
-			  "\xc1\x44\x91\x0b\xa5\xc9\x1b\xb4"
-			  "\xa9\xda\x1e\x9e\xb1\x3e\x2a\x8f"
-			  "\xea\xa5\x6a\x85\xd1\xf4\xa8\xa5",
-		.rlen	= 32,
-	}
-};
-
-static const struct cipher_testvec xeta_dec_tv_template[] = {
-	{
-		.key    = zeroed_string,
-		.klen	= 16,
-		.input	= "\xaa\x22\x96\xe5\x6c\x61\xf3\x45",
-		.ilen	= 8,
-		.result = zeroed_string,
-		.rlen	= 8,
-	}, {
-		.key	= "\x2b\x02\x05\x68\x06\x14\x49\x76"
-			  "\x77\x5d\x0e\x26\x6c\x28\x78\x43",
-		.klen	= 16,
-		.input	= "\x82\x3e\xeb\x35\xdc\xdd\xd9\xc3",
-		.ilen	= 8,
-		.result	= "\x74\x65\x73\x74\x20\x6d\x65\x2e",
-		.rlen	= 8,
-	}, {
-		.key	= "\x09\x65\x43\x11\x66\x44\x39\x25"
-			  "\x51\x3a\x16\x10\x0a\x08\x12\x6e",
-		.klen	= 16,
-		.input	= "\xe2\x04\xdb\xf2\x89\x85\x9e\xea"
-			  "\x61\x35\xaa\xed\xb5\xcb\x71\x2c",
-		.ilen	= 16,
-		.result	= "\x6c\x6f\x6e\x67\x65\x72\x5f\x74"
-			  "\x65\x73\x74\x5f\x76\x65\x63\x74",
-		.rlen	= 16,
-	}, {
-		.key	= "\x4d\x76\x32\x17\x05\x3f\x75\x2c"
-			  "\x5d\x04\x16\x36\x15\x72\x63\x2f",
-		.klen	= 16,
-		.input	= "\x0b\x03\xcd\x8a\xbe\x95\xfd\xb1"
+		.ctext	= "\x0b\x03\xcd\x8a\xbe\x95\xfd\xb1"
 			  "\xc1\x44\x91\x0b\xa5\xc9\x1b\xb4"
 			  "\xa9\xda\x1e\x9e\xb1\x3e\x2a\x8f"
 			  "\xea\xa5\x6a\x85\xd1\xf4\xa8\xa5",
-		.ilen	= 32,
-		.result	= "\x54\x65\x61\x20\x69\x73\x20\x67"
-			  "\x6f\x6f\x64\x20\x66\x6f\x72\x20"
-			  "\x79\x6f\x75\x21\x21\x21\x20\x72"
-			  "\x65\x61\x6c\x6c\x79\x21\x21\x21",
-		.rlen	= 32,
+		.len	= 32,
 	}
 };
 
 /*
  * FCrypt test vectors
  */
-static const struct cipher_testvec fcrypt_pcbc_enc_tv_template[] = {
+static const struct cipher_testvec fcrypt_pcbc_tv_template[] = {
 	{ /* http://www.openafs.org/pipermail/openafs-devel/2000-December/005320.html */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 8,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 8,
-		.result	= "\x0E\x09\x00\xC7\x3E\xF7\xED\x41",
-		.rlen	= 8,
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ctext	= "\x0E\x09\x00\xC7\x3E\xF7\xED\x41",
+		.len	= 8,
 	}, {
 		.key	= "\x11\x44\x77\xAA\xDD\x00\x33\x66",
 		.klen	= 8,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x12\x34\x56\x78\x9A\xBC\xDE\xF0",
-		.ilen	= 8,
-		.result	= "\xD8\xED\x78\x74\x77\xEC\x06\x80",
-		.rlen	= 8,
+		.ptext	= "\x12\x34\x56\x78\x9A\xBC\xDE\xF0",
+		.ctext	= "\xD8\xED\x78\x74\x77\xEC\x06\x80",
+		.len	= 8,
 	}, { /* From Arla */
 		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
 		.klen	= 8,
 		.iv	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.input	= "The quick brown fox jumps over the lazy dogs.\0\0",
-		.ilen	= 48,
-		.result	= "\x00\xf0\x0e\x11\x75\xe6\x23\x82"
+		.ptext	= "The quick brown fox jumps over the lazy dogs.\0\0",
+		.ctext	= "\x00\xf0\x0e\x11\x75\xe6\x23\x82"
 			  "\xee\xac\x98\x62\x44\x51\xe4\x84"
 			  "\xc3\x59\xd8\xaa\x64\x60\xae\xf7"
 			  "\xd2\xd9\x13\x79\x72\xa3\x45\x03"
 			  "\x23\xb5\x62\xd7\x0c\xf5\x27\xd1"
 			  "\xf8\x91\x3c\xac\x44\x22\x92\xef",
-		.rlen	= 48,
+		.len	= 48,
 	}, {
 		.key	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
 		.klen	= 8,
 		.iv	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
-		.input	= "The quick brown fox jumps over the lazy dogs.\0\0",
-		.ilen	= 48,
-		.result	= "\xca\x90\xf5\x9d\xcb\xd4\xd2\x3c"
+		.ptext	= "The quick brown fox jumps over the lazy dogs.\0\0",
+		.ctext	= "\xca\x90\xf5\x9d\xcb\xd4\xd2\x3c"
 			  "\x01\x88\x7f\x3e\x31\x6e\x62\x9d"
 			  "\xd8\xe0\x57\xa3\x06\x3a\x42\x58"
 			  "\x2a\x28\xfe\x72\x52\x2f\xdd\xe0"
 			  "\x19\x89\x09\x1c\x2a\x8e\x8c\x94"
 			  "\xfc\xc7\x68\xe4\x88\xaa\xde\x0f",
-		.rlen	= 48,
+		.len	= 48,
 	}, { /* split-page version */
 		.key	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
 		.klen	= 8,
 		.iv	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
-		.input	= "The quick brown fox jumps over the lazy dogs.\0\0",
-		.ilen	= 48,
-		.result	= "\xca\x90\xf5\x9d\xcb\xd4\xd2\x3c"
+		.ptext	= "The quick brown fox jumps over the lazy dogs.\0\0",
+		.ctext	= "\xca\x90\xf5\x9d\xcb\xd4\xd2\x3c"
 			  "\x01\x88\x7f\x3e\x31\x6e\x62\x9d"
 			  "\xd8\xe0\x57\xa3\x06\x3a\x42\x58"
 			  "\x2a\x28\xfe\x72\x52\x2f\xdd\xe0"
 			  "\x19\x89\x09\x1c\x2a\x8e\x8c\x94"
 			  "\xfc\xc7\x68\xe4\x88\xaa\xde\x0f",
-		.rlen	= 48,
-		.np	= 2,
-		.tap	= { 20, 28 },
-	}
-};
-
-static const struct cipher_testvec fcrypt_pcbc_dec_tv_template[] = {
-	{ /* http://www.openafs.org/pipermail/openafs-devel/2000-December/005320.html */
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 8,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x0E\x09\x00\xC7\x3E\xF7\xED\x41",
-		.ilen	= 8,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 8,
-	}, {
-		.key	= "\x11\x44\x77\xAA\xDD\x00\x33\x66",
-		.klen	= 8,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xD8\xED\x78\x74\x77\xEC\x06\x80",
-		.ilen	= 8,
-		.result	= "\x12\x34\x56\x78\x9A\xBC\xDE\xF0",
-		.rlen	= 8,
-	}, { /* From Arla */
-		.key	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
-		.klen	= 8,
-		.iv	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.input	= "\x00\xf0\x0e\x11\x75\xe6\x23\x82"
-			  "\xee\xac\x98\x62\x44\x51\xe4\x84"
-			  "\xc3\x59\xd8\xaa\x64\x60\xae\xf7"
-			  "\xd2\xd9\x13\x79\x72\xa3\x45\x03"
-			  "\x23\xb5\x62\xd7\x0c\xf5\x27\xd1"
-			  "\xf8\x91\x3c\xac\x44\x22\x92\xef",
-		.ilen	= 48,
-		.result	= "The quick brown fox jumps over the lazy dogs.\0\0",
-		.rlen	= 48,
-	}, {
-		.key	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.klen	= 8,
-		.iv	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
-		.input	= "\xca\x90\xf5\x9d\xcb\xd4\xd2\x3c"
-			  "\x01\x88\x7f\x3e\x31\x6e\x62\x9d"
-			  "\xd8\xe0\x57\xa3\x06\x3a\x42\x58"
-			  "\x2a\x28\xfe\x72\x52\x2f\xdd\xe0"
-			  "\x19\x89\x09\x1c\x2a\x8e\x8c\x94"
-			  "\xfc\xc7\x68\xe4\x88\xaa\xde\x0f",
-		.ilen	= 48,
-		.result	= "The quick brown fox jumps over the lazy dogs.\0\0",
-		.rlen	= 48,
-	}, { /* split-page version */
-		.key	= "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.klen	= 8,
-		.iv	= "\xf0\xe1\xd2\xc3\xb4\xa5\x96\x87",
-		.input	= "\xca\x90\xf5\x9d\xcb\xd4\xd2\x3c"
-			  "\x01\x88\x7f\x3e\x31\x6e\x62\x9d"
-			  "\xd8\xe0\x57\xa3\x06\x3a\x42\x58"
-			  "\x2a\x28\xfe\x72\x52\x2f\xdd\xe0"
-			  "\x19\x89\x09\x1c\x2a\x8e\x8c\x94"
-			  "\xfc\xc7\x68\xe4\x88\xaa\xde\x0f",
-		.ilen	= 48,
-		.result	= "The quick brown fox jumps over the lazy dogs.\0\0",
-		.rlen	= 48,
+		.len	= 48,
 		.np	= 2,
 		.tap	= { 20, 28 },
 	}
@@ -30065,47 +27806,44 @@ static const struct cipher_testvec fcrypt_pcbc_dec_tv_template[] = {
 /*
  * CAMELLIA test vectors.
  */
-static const struct cipher_testvec camellia_enc_tv_template[] = {
+static const struct cipher_testvec camellia_tv_template[] = {
 	{
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
 		.klen	= 16,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ilen	= 16,
-		.result	= "\x67\x67\x31\x38\x54\x96\x69\x73"
+		.ctext	= "\x67\x67\x31\x38\x54\x96\x69\x73"
 			  "\x08\x57\x06\x56\x48\xea\xbe\x43",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
 			  "\x00\x11\x22\x33\x44\x55\x66\x77",
 		.klen	= 24,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ilen	= 16,
-		.result	= "\xb4\x99\x34\x01\xb3\xe9\x96\xf8"
+		.ctext	= "\xb4\x99\x34\x01\xb3\xe9\x96\xf8"
 			  "\x4e\xe5\xce\xe7\xd7\x9b\x09\xb9",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
 			  "\x00\x11\x22\x33\x44\x55\x66\x77"
 			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
 		.klen	= 32,
-		.input	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
+		.ptext	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
 			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.ilen	= 16,
-		.result	= "\x9a\xcc\x23\x7d\xff\x16\xd7\x6c"
+		.ctext	= "\x9a\xcc\x23\x7d\xff\x16\xd7\x6c"
 			  "\x20\xef\x7c\x91\x9e\x3a\x75\x09",
-		.rlen	= 16,
+		.len	= 16,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x3F\x85\x62\x3F\x1C\xF9\xD6\x1C"
 			  "\xF9\xD6\xB3\x90\x6D\x4A\x90\x6D"
 			  "\x4A\x27\x04\xE1\x27\x04\xE1\xBE"
 			  "\x9B\x78\xBE\x9B\x78\x55\x32\x0F",
 		.klen	= 32,
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -30231,181 +27969,7 @@ static const struct cipher_testvec camellia_enc_tv_template[] = {
 			  "\xB1\x25\xBC\x53\xEA\x5E\xF5\x8C"
 			  "\x00\x97\x2E\xC5\x39\xD0\x67\xFE"
 			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D",
-		.ilen	= 1008,
-		.result	= "\xED\xCD\xDB\xB8\x68\xCE\xBD\xEA"
-			  "\x9D\x9D\xCD\x9F\x4F\xFC\x4D\xB7"
-			  "\xA5\xFF\x6F\x43\x0F\xBA\x32\x04"
-			  "\xB3\xC2\xB9\x03\xAA\x91\x56\x29"
-			  "\x0D\xD0\xFD\xC4\x65\xA5\x69\xB9"
-			  "\xF1\xF6\xB1\xA5\xB2\x75\x4F\x8A"
-			  "\x8D\x7D\x1B\x9B\xC7\x68\x72\xF8"
-			  "\x01\x9B\x17\x0A\x29\xE7\x61\x28"
-			  "\x7F\xA7\x50\xCA\x20\x2C\x96\x3B"
-			  "\x6E\x5C\x5D\x3F\xB5\x7F\xF3\x2B"
-			  "\x04\xEF\x9D\xD4\xCE\x41\x28\x8E"
-			  "\x83\x54\xAE\x7C\x82\x46\x10\xC9"
-			  "\xC4\x8A\x1E\x1F\x4C\xA9\xFC\xEC"
-			  "\x3C\x8C\x30\xFC\x59\xD2\x54\xC4"
-			  "\x6F\x50\xC6\xCA\x8C\x14\x5B\x9C"
-			  "\x18\x56\x5B\xF8\x33\x0E\x4A\xDB"
-			  "\xEC\xB5\x6E\x5B\x31\xC4\x0E\x98"
-			  "\x9F\x32\xBA\xA2\x18\xCF\x55\x43"
-			  "\xFE\x80\x8F\x60\xCF\x05\x30\x9B"
-			  "\x70\x50\x1E\x9C\x08\x87\xE6\x20"
-			  "\xD2\xF3\x27\xF8\x2A\x8D\x12\xB2"
-			  "\xBC\x5F\xFE\x52\x52\xF6\x7F\xB6"
-			  "\xB8\x30\x86\x3B\x0F\x94\x1E\x79"
-			  "\x13\x94\x35\xA2\xB1\x35\x5B\x05"
-			  "\x2A\x98\x6B\x96\x4C\xB1\x20\xBE"
-			  "\xB6\x14\xC2\x06\xBF\xFD\x5F\x2A"
-			  "\xF5\x33\xC8\x19\x45\x14\x44\x5D"
-			  "\xFE\x94\x7B\xBB\x63\x13\x57\xC3"
-			  "\x2A\x8F\x6C\x11\x2A\x07\xA7\x6A"
-			  "\xBF\x20\xD3\x99\xC6\x00\x0B\xBF"
-			  "\x83\x46\x25\x3A\xB0\xF6\xC5\xC8"
-			  "\x00\xCA\xE5\x28\x4A\x7C\x95\x9C"
-			  "\x7B\x43\xAB\xF9\xE4\xF8\x74\xAB"
-			  "\xA7\xB8\x9C\x0F\x53\x7B\xB6\x74"
-			  "\x60\x64\x0D\x1C\x80\xD1\x20\x9E"
-			  "\xDC\x14\x27\x9B\xFC\xBD\x5C\x96"
-			  "\xD2\x51\xDC\x96\xEE\xE5\xEA\x2B"
-			  "\x02\x7C\xAA\x3C\xDC\x9D\x7B\x01"
-			  "\x20\xC3\xE1\x0B\xDD\xAB\xF3\x1E"
-			  "\x19\xA8\x84\x29\x5F\xCC\xC3\x5B"
-			  "\xE4\x33\x59\xDC\x12\xEB\x2B\x4D"
-			  "\x5B\x55\x23\xB7\x40\x31\xDE\xEE"
-			  "\x18\xC9\x3C\x4D\xBC\xED\xE0\x42"
-			  "\xAD\xDE\xA0\xA3\xC3\xFE\x44\xD3"
-			  "\xE1\x9A\xDA\xAB\x32\xFC\x1A\xBF"
-			  "\x63\xA9\xF0\x6A\x08\x46\xBD\x48"
-			  "\x83\x06\xAB\x82\x99\x01\x16\x1A"
-			  "\x03\x36\xC5\x59\x6B\xB8\x8C\x9F"
-			  "\xC6\x51\x3D\xE5\x7F\xBF\xAB\xBC"
-			  "\xC9\xA1\x88\x34\x5F\xA9\x7C\x3B"
-			  "\x9F\x1B\x98\x2B\x4F\xFB\x9B\xF0"
-			  "\xCD\xB6\x45\xB2\x29\x2E\x34\x23"
-			  "\xA9\x97\xC0\x22\x8C\x42\x9B\x5F"
-			  "\x40\xC8\xD7\x3D\x82\x9A\x6F\xAA"
-			  "\x74\x83\x29\x05\xE8\xC4\x4D\x01"
-			  "\xB5\xE5\x84\x3F\x7F\xD3\xE0\x99"
-			  "\xDA\xE7\x6F\x30\xFD\xAA\x92\x30"
-			  "\xA5\x46\x8B\xA2\xE6\x58\x62\x7C"
-			  "\x2C\x35\x1B\x38\x85\x7D\xE8\xF3"
-			  "\x87\x4F\xDA\xD8\x5F\xFC\xB6\x44"
-			  "\xD0\xE3\x9B\x8B\xBF\xD6\xB8\xC4"
-			  "\x73\xAE\x1D\x8B\x5B\x74\x8B\xCB"
-			  "\xA4\xAD\xCF\x5D\xD4\x58\xC9\xCD"
-			  "\xF7\x90\x68\xCF\xC9\x11\x52\x3E"
-			  "\xE8\xA1\xA3\x78\x8B\xD0\xAC\x0A"
-			  "\xD4\xC9\xA3\xA5\x55\x30\xC8\x3E"
-			  "\xED\x28\x39\xE9\x63\xED\x41\x70"
-			  "\x51\xE3\xC4\xA0\xFC\xD5\x43\xCB"
-			  "\x4D\x65\xC8\xFD\x3A\x91\x8F\x60"
-			  "\x8A\xA6\x6D\x9D\x3E\x01\x23\x4B"
-			  "\x50\x47\xC9\xDC\x9B\xDE\x37\xC5"
-			  "\xBF\x67\xB1\x6B\x78\x38\xD5\x7E"
-			  "\xB6\xFF\x67\x83\x3B\x6E\xBE\x23"
-			  "\x45\xFA\x1D\x69\x44\xFD\xC6\xB9"
-			  "\xD0\x4A\x92\xD1\xBE\xF6\x4A\xB7"
-			  "\xCA\xA8\xA2\x9E\x13\x87\x57\x92"
-			  "\x64\x7C\x85\x0B\xB3\x29\x37\xD8"
-			  "\xE6\xAA\xAF\xC4\x03\x67\xA3\xBF"
-			  "\x2E\x45\x83\xB6\xD8\x54\x00\x89"
-			  "\xF6\xBC\x3A\x7A\x88\x58\x51\xED"
-			  "\xF4\x4E\x01\xA5\xC3\x2E\xD9\x42"
-			  "\xBD\x6E\x0D\x0B\x21\xB0\x1A\xCC"
-			  "\xA4\xD3\x3F\xDC\x9B\x81\xD8\xF1"
-			  "\xEA\x7A\x6A\xB7\x07\xC9\x6D\x91"
-			  "\x6D\x3A\xF5\x5F\xA6\xFF\x87\x1E"
-			  "\x3F\xDD\xC0\x72\xEA\xAC\x08\x15"
-			  "\x21\xE6\xC6\xB6\x0D\xD8\x51\x86"
-			  "\x2A\x03\x73\xF7\x29\xD4\xC4\xE4"
-			  "\x7F\x95\x10\xF7\xAB\x3F\x92\x23"
-			  "\xD3\xCE\x9C\x2E\x46\x3B\x63\x43"
-			  "\xBB\xC2\x82\x7A\x83\xD5\x55\xE2"
-			  "\xE7\x9B\x2F\x92\xAF\xFD\x81\x56"
-			  "\x79\xFD\x3E\xF9\x46\xE0\x25\xD4"
-			  "\x38\xDE\xBC\x2C\xC4\x7A\x2A\x8F"
-			  "\x94\x4F\xD0\xAD\x9B\x37\x18\xD4"
-			  "\x0E\x4D\x0F\x02\x3A\xDC\x5A\xA2"
-			  "\x39\x25\x55\x20\x5A\xA6\x02\x9F"
-			  "\xE6\x77\x21\x77\xE5\x4B\x7B\x0B"
-			  "\x30\xF8\x5F\x33\x0F\x49\xCD\xFF"
-			  "\xF2\xE4\x35\xF9\xF0\x63\xC3\x7E"
-			  "\xF1\xA6\x73\xB4\xDF\xE7\xBB\x78"
-			  "\xFF\x21\xA9\xF3\xF3\xCF\x5D\xBA"
-			  "\xED\x87\x98\xAC\xFE\x48\x97\x6D"
-			  "\xA6\x7F\x69\x31\xB1\xC4\xFF\x14"
-			  "\xC6\x76\xD4\x10\xDD\xF6\x49\x2C"
-			  "\x9C\xC8\x6D\x76\xC0\x8F\x5F\x55"
-			  "\x2F\x3C\x8A\x30\xAA\xC3\x16\x55"
-			  "\xC6\xFC\x8D\x8B\xB9\xE5\x80\x6C"
-			  "\xC8\x7E\xBD\x65\x58\x36\xD5\xBC"
-			  "\xF0\x33\x52\x29\x70\xF9\x5C\xE9"
-			  "\xAC\x1F\xB5\x73\x56\x66\x54\xAF"
-			  "\x1B\x8F\x7D\xED\xAB\x03\xCE\xE3"
-			  "\xAE\x47\xB6\x69\x86\xE9\x01\x31"
-			  "\x83\x18\x3D\xF4\x74\x7B\xF9\x42"
-			  "\x4C\xFD\x75\x4A\x6D\xF0\x03\xA6"
-			  "\x2B\x20\x63\xDA\x49\x65\x5E\x8B"
-			  "\xC0\x19\xE3\x8D\xD9\xF3\xB0\x34"
-			  "\xD3\x52\xFC\x68\x00\x43\x1B\x37"
-			  "\x31\x93\x51\x1C\x63\x97\x70\xB0"
-			  "\x99\x78\x83\x13\xFD\xCF\x53\x81"
-			  "\x36\x46\xB5\x42\x52\x2F\x32\xEB"
-			  "\x4A\x3D\xF1\x8F\x1C\x54\x2E\xFC"
-			  "\x41\x75\x5A\x8C\x8E\x6F\xE7\x1A"
-			  "\xAE\xEF\x3E\x82\x12\x0B\x74\x72"
-			  "\xF8\xB2\xAA\x7A\xD6\xFF\xFA\x55"
-			  "\x33\x1A\xBB\xD3\xA2\x7E\x97\x66",
-		.rlen	= 1008,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 1008 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec camellia_dec_tv_template[] = {
-	{
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.klen	= 16,
-		.input	= "\x67\x67\x31\x38\x54\x96\x69\x73"
-			  "\x08\x57\x06\x56\x48\xea\xbe\x43",
-		.ilen	= 16,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.rlen	= 16,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
-			  "\x00\x11\x22\x33\x44\x55\x66\x77",
-		.klen	= 24,
-		.input	= "\xb4\x99\x34\x01\xb3\xe9\x96\xf8"
-			  "\x4e\xe5\xce\xe7\xd7\x9b\x09\xb9",
-		.ilen	= 16,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.rlen	= 16,
-	}, {
-		.key	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10"
-			  "\x00\x11\x22\x33\x44\x55\x66\x77"
-			  "\x88\x99\xaa\xbb\xcc\xdd\xee\xff",
-		.klen	= 32,
-		.input	= "\x9a\xcc\x23\x7d\xff\x16\xd7\x6c"
-			  "\x20\xef\x7c\x91\x9e\x3a\x75\x09",
-		.ilen	= 16,
-		.result	= "\x01\x23\x45\x67\x89\xab\xcd\xef"
-			  "\xfe\xdc\xba\x98\x76\x54\x32\x10",
-		.rlen	= 16,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x3F\x85\x62\x3F\x1C\xF9\xD6\x1C"
-			  "\xF9\xD6\xB3\x90\x6D\x4A\x90\x6D"
-			  "\x4A\x27\x04\xE1\x27\x04\xE1\xBE"
-			  "\x9B\x78\xBE\x9B\x78\x55\x32\x0F",
-		.klen	= 32,
-		.input	= "\xED\xCD\xDB\xB8\x68\xCE\xBD\xEA"
+		.ctext	= "\xED\xCD\xDB\xB8\x68\xCE\xBD\xEA"
 			  "\x9D\x9D\xCD\x9F\x4F\xFC\x4D\xB7"
 			  "\xA5\xFF\x6F\x43\x0F\xBA\x32\x04"
 			  "\xB3\xC2\xB9\x03\xAA\x91\x56\x29"
@@ -30531,168 +28095,39 @@ static const struct cipher_testvec camellia_dec_tv_template[] = {
 			  "\xAE\xEF\x3E\x82\x12\x0B\x74\x72"
 			  "\xF8\xB2\xAA\x7A\xD6\xFF\xFA\x55"
 			  "\x33\x1A\xBB\xD3\xA2\x7E\x97\x66",
-		.ilen	= 1008,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06"
-			  "\x9D\x34\xCB\x3F\xD6\x6D\x04\x78"
-			  "\x0F\xA6\x1A\xB1\x48\xDF\x53\xEA"
-			  "\x81\x18\x8C\x23\xBA\x2E\xC5\x5C"
-			  "\xF3\x67\xFE\x95\x09\xA0\x37\xCE"
-			  "\x42\xD9\x70\x07\x7B\x12\xA9\x1D"
-			  "\xB4\x4B\xE2\x56\xED\x84\x1B\x8F"
-			  "\x26\xBD\x31\xC8\x5F\xF6\x6A\x01"
-			  "\x98\x0C\xA3\x3A\xD1\x45\xDC\x73"
-			  "\x0A\x7E\x15\xAC\x20\xB7\x4E\xE5"
-			  "\x59\xF0\x87\x1E\x92\x29\xC0\x34"
-			  "\xCB\x62\xF9\x6D\x04\x9B\x0F\xA6"
-			  "\x3D\xD4\x48\xDF\x76\x0D\x81\x18"
-			  "\xAF\x23\xBA\x51\xE8\x5C\xF3\x8A"
-			  "\x21\x95\x2C\xC3\x37\xCE\x65\xFC"
-			  "\x70\x07\x9E\x12\xA9\x40\xD7\x4B"
-			  "\xE2\x79\x10\x84\x1B\xB2\x26\xBD"
-			  "\x54\xEB\x5F\xF6\x8D\x01\x98\x2F"
-			  "\xC6\x3A\xD1\x68\xFF\x73\x0A\xA1"
-			  "\x15\xAC\x43\xDA\x4E\xE5\x7C\x13"
-			  "\x87\x1E\xB5\x29\xC0\x57\xEE\x62"
-			  "\xF9\x90\x04\x9B\x32\xC9\x3D\xD4"
-			  "\x6B\x02\x76\x0D\xA4\x18\xAF\x46"
-			  "\xDD\x51\xE8\x7F\x16\x8A\x21\xB8"
-			  "\x2C\xC3\x5A\xF1\x65\xFC\x93\x07"
-			  "\x9E\x35\xCC\x40\xD7\x6E\x05\x79"
-			  "\x10\xA7\x1B\xB2\x49\xE0\x54\xEB"
-			  "\x82\x19\x8D\x24\xBB\x2F\xC6\x5D"
-			  "\xF4\x68\xFF\x96\x0A\xA1\x38\xCF"
-			  "\x43\xDA\x71\x08\x7C\x13\xAA\x1E"
-			  "\xB5\x4C\xE3\x57\xEE\x85\x1C\x90"
-			  "\x27\xBE\x32\xC9\x60\xF7\x6B\x02"
-			  "\x99\x0D\xA4\x3B\xD2\x46\xDD\x74"
-			  "\x0B\x7F\x16\xAD\x21\xB8\x4F\xE6"
-			  "\x5A\xF1\x88\x1F\x93\x2A\xC1\x35"
-			  "\xCC\x63\xFA\x6E\x05\x9C\x10\xA7"
-			  "\x3E\xD5\x49\xE0\x77\x0E\x82\x19"
-			  "\xB0\x24\xBB\x52\xE9\x5D\xF4\x8B"
-			  "\x22\x96\x2D\xC4\x38\xCF\x66\xFD"
-			  "\x71\x08\x9F\x13\xAA\x41\xD8\x4C"
-			  "\xE3\x7A\x11\x85\x1C\xB3\x27\xBE"
-			  "\x55\xEC\x60\xF7\x8E\x02\x99\x30"
-			  "\xC7\x3B\xD2\x69\x00\x74\x0B\xA2"
-			  "\x16\xAD\x44\xDB\x4F\xE6\x7D\x14"
-			  "\x88\x1F\xB6\x2A\xC1\x58\xEF\x63"
-			  "\xFA\x91\x05\x9C\x33\xCA\x3E\xD5"
-			  "\x6C\x03\x77\x0E\xA5\x19\xB0\x47"
-			  "\xDE\x52\xE9\x80\x17\x8B\x22\xB9"
-			  "\x2D\xC4\x5B\xF2\x66\xFD\x94\x08"
-			  "\x9F\x36\xCD\x41\xD8\x6F\x06\x7A"
-			  "\x11\xA8\x1C\xB3\x4A\xE1\x55\xEC"
-			  "\x83\x1A\x8E\x25\xBC\x30\xC7\x5E"
-			  "\xF5\x69\x00\x97\x0B\xA2\x39\xD0"
-			  "\x44\xDB\x72\x09\x7D\x14\xAB\x1F"
-			  "\xB6\x4D\xE4\x58\xEF\x86\x1D\x91"
-			  "\x28\xBF\x33\xCA\x61\xF8\x6C\x03"
-			  "\x9A\x0E\xA5\x3C\xD3\x47\xDE\x75"
-			  "\x0C\x80\x17\xAE\x22\xB9\x50\xE7"
-			  "\x5B\xF2\x89\x20\x94\x2B\xC2\x36"
-			  "\xCD\x64\xFB\x6F\x06\x9D\x11\xA8"
-			  "\x3F\xD6\x4A\xE1\x78\x0F\x83\x1A"
-			  "\xB1\x25\xBC\x53\xEA\x5E\xF5\x8C"
-			  "\x00\x97\x2E\xC5\x39\xD0\x67\xFE"
-			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D",
-		.rlen	= 1008,
+		.len	= 1008,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 1008 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec camellia_cbc_enc_tv_template[] = {
+static const struct cipher_testvec camellia_cbc_tv_template[] = {
 	{
 		.key    = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b"
 			  "\x51\x2e\x03\xd5\x34\x12\x00\x06",
 		.klen   = 16,
 		.iv	= "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
 			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
-		.input	= "Single block msg",
-		.ilen   = 16,
-		.result = "\xea\x32\x12\x76\x3b\x50\x10\xe7"
+		.ptext	= "Single block msg",
+		.ctext	= "\xea\x32\x12\x76\x3b\x50\x10\xe7"
 			  "\x18\xf6\xfd\x5d\xf6\x8f\x13\x51",
-		.rlen   = 16,
+		.len	= 16,
 	}, {
 		.key    = "\xc2\x86\x69\x6d\x88\x7c\x9a\xa0"
 			  "\x61\x1b\xbb\x3e\x20\x25\xa4\x5a",
 		.klen   = 16,
 		.iv     = "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
 			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
-		.input  = "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.ilen   = 32,
-		.result = "\xa5\xdf\x6e\x50\xda\x70\x6c\x01"
+		.ctext	= "\xa5\xdf\x6e\x50\xda\x70\x6c\x01"
 			  "\x4a\xab\xf3\xf2\xd6\xfc\x6c\xfd"
 			  "\x19\xb4\x3e\x57\x1c\x02\x5e\xa0"
 			  "\x15\x78\xe0\x5e\xf2\xcb\x87\x16",
-		.rlen   = 32,
+		.len	= 32,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -30701,7 +28136,7 @@ static const struct cipher_testvec camellia_cbc_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -30827,8 +28262,7 @@ static const struct cipher_testvec camellia_cbc_enc_tv_template[] = {
 			  "\xB1\x25\xBC\x53\xEA\x5E\xF5\x8C"
 			  "\x00\x97\x2E\xC5\x39\xD0\x67\xFE"
 			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D",
-		.ilen	= 1008,
-		.result	= "\xCD\x3E\x2A\x3B\x3E\x94\xC5\x77"
+		.ctext	= "\xCD\x3E\x2A\x3B\x3E\x94\xC5\x77"
 			  "\xBA\xBB\x5B\xB1\xDE\x7B\xA4\x40"
 			  "\x88\x39\xE3\xFD\x94\x4B\x25\x58"
 			  "\xE1\x4B\xC4\x18\x7A\xFD\x17\x2B"
@@ -30954,310 +28388,14 @@ static const struct cipher_testvec camellia_cbc_enc_tv_template[] = {
 			  "\x43\x94\x23\x7E\xEE\xF0\xA5\x79"
 			  "\x55\x01\xD4\x58\xB2\xF2\x85\x49"
 			  "\x70\xC5\xB9\x0B\x3B\x7A\x6E\x6C",
-		.rlen	= 1008,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 1008 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec camellia_cbc_dec_tv_template[] = {
-	{
-		.key    = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b"
-			  "\x51\x2e\x03\xd5\x34\x12\x00\x06",
-		.klen   = 16,
-		.iv	= "\x3d\xaf\xba\x42\x9d\x9e\xb4\x30"
-			  "\xb4\x22\xda\x80\x2c\x9f\xac\x41",
-		.input	= "\xea\x32\x12\x76\x3b\x50\x10\xe7"
-			  "\x18\xf6\xfd\x5d\xf6\x8f\x13\x51",
-		.ilen   = 16,
-		.result = "Single block msg",
-		.rlen   = 16,
-	}, {
-		.key    = "\xc2\x86\x69\x6d\x88\x7c\x9a\xa0"
-			  "\x61\x1b\xbb\x3e\x20\x25\xa4\x5a",
-		.klen   = 16,
-		.iv     = "\x56\x2e\x17\x99\x6d\x09\x3d\x28"
-			  "\xdd\xb3\xba\x69\x5a\x2e\x6f\x58",
-		.input = "\xa5\xdf\x6e\x50\xda\x70\x6c\x01"
-			  "\x4a\xab\xf3\xf2\xd6\xfc\x6c\xfd"
-			  "\x19\xb4\x3e\x57\x1c\x02\x5e\xa0"
-			  "\x15\x78\xe0\x5e\xf2\xcb\x87\x16",
-		.ilen   = 32,
-		.result = "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
-		.rlen   = 32,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\xCD\x3E\x2A\x3B\x3E\x94\xC5\x77"
-			  "\xBA\xBB\x5B\xB1\xDE\x7B\xA4\x40"
-			  "\x88\x39\xE3\xFD\x94\x4B\x25\x58"
-			  "\xE1\x4B\xC4\x18\x7A\xFD\x17\x2B"
-			  "\xB9\xF9\xC2\x27\x6A\xB6\x31\x27"
-			  "\xA6\xAD\xEF\xE5\x5D\xE4\x02\x01"
-			  "\x56\x2E\x10\xC2\x2C\xFF\xC6\x83"
-			  "\xB5\xDC\x4F\x63\xAD\x0E\x63\x5E"
-			  "\x56\xC8\x18\x3D\x79\x86\x97\xEF"
-			  "\x57\x0E\x63\xA1\xC1\x41\x48\xB8"
-			  "\x98\xB7\x51\x6D\x18\xF6\x19\x82"
-			  "\x37\x49\x88\xA4\xEF\x91\x21\x47"
-			  "\x03\x28\xEA\x42\xF4\xFB\x7A\x58"
-			  "\x28\x90\x77\x46\xD8\xD2\x35\x16"
-			  "\x44\xA9\x9E\x49\x52\x2A\xE4\x16"
-			  "\x5D\xF7\x65\xEB\x0F\xC9\x29\xE6"
-			  "\xCF\x76\x91\x89\x8A\x94\x39\xFA"
-			  "\x6B\x5F\x63\x53\x74\x43\x91\xF5"
-			  "\x3F\xBC\x88\x53\xB2\x1A\x02\x3F"
-			  "\x9D\x32\x84\xEB\x56\x28\xD6\x06"
-			  "\xD5\xB2\x20\xA9\xFC\xC3\x76\x62"
-			  "\x32\xCC\x86\xC8\x36\x67\x5E\x7E"
-			  "\xA4\xAA\x15\x63\x6B\xA9\x86\xAF"
-			  "\x1A\x52\x82\x36\x5F\xF4\x3F\x7A"
-			  "\x9B\x78\x62\x3B\x02\x28\x60\xB3"
-			  "\xBA\x82\xB1\xDD\xC9\x60\x8F\x47"
-			  "\xF1\x6B\xFE\xE5\x39\x34\xA0\x28"
-			  "\xA4\xB3\xC9\x7E\xED\x28\x8D\x70"
-			  "\xB2\x1D\xFD\xC6\x00\xCF\x1A\x94"
-			  "\x28\xF8\xC1\x34\xB7\x58\xA5\x6C"
-			  "\x1A\x9D\xE4\xE4\xF6\xB9\xB4\xB0"
-			  "\x5D\x51\x54\x9A\x53\xA0\xF9\x32"
-			  "\xBD\x31\x54\x14\x7B\x33\xEE\x17"
-			  "\xD3\xC7\x1F\x48\xBF\x0B\x22\xA2"
-			  "\x7D\x0C\xDF\xD0\x2E\x98\xFA\xD2"
-			  "\xFA\xCF\x24\x1D\x99\x9B\xD0\x7E"
-			  "\xF4\x4F\x88\xFF\x45\x99\x4A\xF4"
-			  "\xF2\x0A\x5B\x3B\x21\xAB\x92\xAE"
-			  "\x40\x78\x91\x95\xC4\x2F\xA3\xE8"
-			  "\x18\xC7\x07\xA6\xC8\xC0\x66\x33"
-			  "\x35\xC0\xB4\xA0\xF8\xEE\x1E\xF3"
-			  "\x40\xF5\x40\x54\xF1\x84\x8C\xEA"
-			  "\x27\x38\x1F\xF8\x77\xC7\xDF\xD8"
-			  "\x1D\xE2\xD9\x59\x40\x4F\x59\xD4"
-			  "\xF8\x17\x99\x8D\x58\x2D\x72\x44"
-			  "\x9D\x1D\x91\x64\xD6\x3F\x0A\x82"
-			  "\xC7\x57\x3D\xEF\xD3\x41\xFA\xA7"
-			  "\x68\xA3\xB8\xA5\x93\x74\x2E\x85"
-			  "\x4C\x9D\x69\x59\xCE\x15\xAE\xBF"
-			  "\x9C\x8F\x14\x64\x5D\x7F\xCF\x0B"
-			  "\xCE\x43\x5D\x28\xC0\x2F\xFB\x18"
-			  "\x79\x9A\xFC\x43\x16\x7C\x6B\x7B"
-			  "\x38\xB8\x48\x36\x66\x4E\x20\x43"
-			  "\xBA\x76\x13\x9A\xC3\xF2\xEB\x52"
-			  "\xD7\xDC\xB2\x67\x63\x14\x25\xCD"
-			  "\xB1\x13\x4B\xDE\x8C\x59\x21\x84"
-			  "\x81\x8D\x97\x23\x45\x33\x7C\xF3"
-			  "\xC5\xBC\x79\x95\xAA\x84\x68\x31"
-			  "\x2D\x1A\x68\xFE\xEC\x92\x94\xDA"
-			  "\x94\x2A\x6F\xD6\xFE\xE5\x76\x97"
-			  "\xF4\x6E\xEE\xCB\x2B\x95\x4E\x36"
-			  "\x5F\x74\x8C\x86\x5B\x71\xD0\x20"
-			  "\x78\x1A\x7F\x18\x8C\xD9\xCD\xF5"
-			  "\x21\x41\x56\x72\x13\xE1\x86\x07"
-			  "\x07\x26\xF3\x4F\x7B\xEA\xB5\x18"
-			  "\xFE\x94\x2D\x9F\xE0\x72\x18\x65"
-			  "\xB2\xA5\x63\x48\xB4\x13\x22\xF7"
-			  "\x25\xF1\x80\xA8\x7F\x54\x86\x7B"
-			  "\x39\xAE\x95\x0C\x09\x32\x22\x2D"
-			  "\x4D\x73\x39\x0C\x09\x2C\x7C\x10"
-			  "\xD0\x4B\x53\xF6\x90\xC5\x99\x2F"
-			  "\x15\xE1\x7F\xC6\xC5\x7A\x52\x14"
-			  "\x65\xEE\x93\x54\xD0\x66\x15\x3C"
-			  "\x4C\x68\xFD\x64\x0F\xF9\x10\x39"
-			  "\x46\x7A\xDD\x97\x20\xEE\xC7\xD2"
-			  "\x98\x4A\xB6\xE6\xF5\xA8\x1F\x4F"
-			  "\xDB\xAB\x6D\xD5\x9B\x34\x16\x97"
-			  "\x2F\x64\xE5\x37\xEF\x0E\xA1\xE9"
-			  "\xBE\x31\x31\x96\x8B\x40\x18\x75"
-			  "\x11\x75\x14\x32\xA5\x2D\x1B\x6B"
-			  "\xDB\x59\xEB\xFA\x3D\x8E\x7C\xC4"
-			  "\xDE\x68\xC8\x9F\xC9\x99\xE3\xC6"
-			  "\x71\xB0\x12\x57\x89\x0D\xC0\x2B"
-			  "\x9F\x12\x6A\x04\x67\xF1\x95\x31"
-			  "\x59\xFD\x84\x95\x2C\x9C\x5B\xEC"
-			  "\x09\xB0\x43\x96\x4A\x64\x80\x40"
-			  "\xB9\x72\x19\xDD\x70\x42\xFA\xB1"
-			  "\x4A\x2C\x0C\x0A\x60\x6E\xE3\x7C"
-			  "\x37\x5A\xBE\xA4\x62\xCF\x29\xAB"
-			  "\x7F\x4D\xA6\xB3\xE2\xB6\x64\xC6"
-			  "\x33\x0B\xF3\xD5\x01\x38\x74\xA4"
-			  "\x67\x1E\x75\x68\xC3\xAD\x76\xE9"
-			  "\xE9\xBC\xF0\xEB\xD8\xFD\x31\x8A"
-			  "\x5F\xC9\x18\x94\x4B\x86\x66\xFC"
-			  "\xBD\x0B\x3D\xB3\x9F\xFA\x1F\xD9"
-			  "\x78\xC4\xE3\x24\x1C\x67\xA2\xF8"
-			  "\x43\xBC\x76\x75\xBF\x6C\x05\xB3"
-			  "\x32\xE8\x7C\x80\xDB\xC7\xB6\x61"
-			  "\x1A\x3E\x2B\xA7\x25\xED\x8F\xA0"
-			  "\x00\x4B\xF8\x90\xCA\xD8\xFB\x12"
-			  "\xAC\x1F\x18\xE9\xD2\x5E\xA2\x8E"
-			  "\xE4\x84\x6B\x9D\xEB\x1E\x6B\xA3"
-			  "\x7B\xDC\xCE\x15\x97\x27\xB2\x65"
-			  "\xBC\x0E\x47\xAB\x55\x13\x53\xAB"
-			  "\x0E\x34\x55\x02\x5F\x27\xC5\x89"
-			  "\xDF\xC5\x70\xC4\xDD\x76\x82\xEE"
-			  "\x68\xA6\x09\xB0\xE5\x5E\xF1\x0C"
-			  "\xE3\xF3\x09\x9B\xFE\x65\x4B\xB8"
-			  "\x30\xEC\xD5\x7C\x6A\xEC\x1D\xD2"
-			  "\x93\xB7\xA1\x1A\x02\xD4\xC0\xD6"
-			  "\x8D\x4D\x83\x9A\xED\x29\x4E\x14"
-			  "\x86\xD5\x3C\x1A\xD5\xB9\x0A\x6A"
-			  "\x72\x22\xD5\x92\x38\xF1\xA1\x86"
-			  "\xB2\x41\x51\xCA\x4E\xAB\x8F\xD3"
-			  "\x80\x56\xC3\xD7\x65\xE1\xB3\x86"
-			  "\xCB\xCE\x98\xA1\xD4\x59\x1C\x06"
-			  "\x01\xED\xF8\x29\x91\x19\x5C\x9A"
-			  "\xEE\x28\x1B\x48\xD7\x32\xEF\x9F"
-			  "\x6C\x2B\x66\x4E\x78\xD5\x8B\x72"
-			  "\x80\xE7\x29\xDC\x23\x55\x98\x54"
-			  "\xB1\xFF\x3E\x95\x56\xA8\x78\x78"
-			  "\xEF\xC4\xA5\x11\x2D\x2B\xD8\x93"
-			  "\x30\x6E\x7E\x51\xBB\x42\x5F\x03"
-			  "\x43\x94\x23\x7E\xEE\xF0\xA5\x79"
-			  "\x55\x01\xD4\x58\xB2\xF2\x85\x49"
-			  "\x70\xC5\xB9\x0B\x3B\x7A\x6E\x6C",
-		.ilen	= 1008,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06"
-			  "\x9D\x34\xCB\x3F\xD6\x6D\x04\x78"
-			  "\x0F\xA6\x1A\xB1\x48\xDF\x53\xEA"
-			  "\x81\x18\x8C\x23\xBA\x2E\xC5\x5C"
-			  "\xF3\x67\xFE\x95\x09\xA0\x37\xCE"
-			  "\x42\xD9\x70\x07\x7B\x12\xA9\x1D"
-			  "\xB4\x4B\xE2\x56\xED\x84\x1B\x8F"
-			  "\x26\xBD\x31\xC8\x5F\xF6\x6A\x01"
-			  "\x98\x0C\xA3\x3A\xD1\x45\xDC\x73"
-			  "\x0A\x7E\x15\xAC\x20\xB7\x4E\xE5"
-			  "\x59\xF0\x87\x1E\x92\x29\xC0\x34"
-			  "\xCB\x62\xF9\x6D\x04\x9B\x0F\xA6"
-			  "\x3D\xD4\x48\xDF\x76\x0D\x81\x18"
-			  "\xAF\x23\xBA\x51\xE8\x5C\xF3\x8A"
-			  "\x21\x95\x2C\xC3\x37\xCE\x65\xFC"
-			  "\x70\x07\x9E\x12\xA9\x40\xD7\x4B"
-			  "\xE2\x79\x10\x84\x1B\xB2\x26\xBD"
-			  "\x54\xEB\x5F\xF6\x8D\x01\x98\x2F"
-			  "\xC6\x3A\xD1\x68\xFF\x73\x0A\xA1"
-			  "\x15\xAC\x43\xDA\x4E\xE5\x7C\x13"
-			  "\x87\x1E\xB5\x29\xC0\x57\xEE\x62"
-			  "\xF9\x90\x04\x9B\x32\xC9\x3D\xD4"
-			  "\x6B\x02\x76\x0D\xA4\x18\xAF\x46"
-			  "\xDD\x51\xE8\x7F\x16\x8A\x21\xB8"
-			  "\x2C\xC3\x5A\xF1\x65\xFC\x93\x07"
-			  "\x9E\x35\xCC\x40\xD7\x6E\x05\x79"
-			  "\x10\xA7\x1B\xB2\x49\xE0\x54\xEB"
-			  "\x82\x19\x8D\x24\xBB\x2F\xC6\x5D"
-			  "\xF4\x68\xFF\x96\x0A\xA1\x38\xCF"
-			  "\x43\xDA\x71\x08\x7C\x13\xAA\x1E"
-			  "\xB5\x4C\xE3\x57\xEE\x85\x1C\x90"
-			  "\x27\xBE\x32\xC9\x60\xF7\x6B\x02"
-			  "\x99\x0D\xA4\x3B\xD2\x46\xDD\x74"
-			  "\x0B\x7F\x16\xAD\x21\xB8\x4F\xE6"
-			  "\x5A\xF1\x88\x1F\x93\x2A\xC1\x35"
-			  "\xCC\x63\xFA\x6E\x05\x9C\x10\xA7"
-			  "\x3E\xD5\x49\xE0\x77\x0E\x82\x19"
-			  "\xB0\x24\xBB\x52\xE9\x5D\xF4\x8B"
-			  "\x22\x96\x2D\xC4\x38\xCF\x66\xFD"
-			  "\x71\x08\x9F\x13\xAA\x41\xD8\x4C"
-			  "\xE3\x7A\x11\x85\x1C\xB3\x27\xBE"
-			  "\x55\xEC\x60\xF7\x8E\x02\x99\x30"
-			  "\xC7\x3B\xD2\x69\x00\x74\x0B\xA2"
-			  "\x16\xAD\x44\xDB\x4F\xE6\x7D\x14"
-			  "\x88\x1F\xB6\x2A\xC1\x58\xEF\x63"
-			  "\xFA\x91\x05\x9C\x33\xCA\x3E\xD5"
-			  "\x6C\x03\x77\x0E\xA5\x19\xB0\x47"
-			  "\xDE\x52\xE9\x80\x17\x8B\x22\xB9"
-			  "\x2D\xC4\x5B\xF2\x66\xFD\x94\x08"
-			  "\x9F\x36\xCD\x41\xD8\x6F\x06\x7A"
-			  "\x11\xA8\x1C\xB3\x4A\xE1\x55\xEC"
-			  "\x83\x1A\x8E\x25\xBC\x30\xC7\x5E"
-			  "\xF5\x69\x00\x97\x0B\xA2\x39\xD0"
-			  "\x44\xDB\x72\x09\x7D\x14\xAB\x1F"
-			  "\xB6\x4D\xE4\x58\xEF\x86\x1D\x91"
-			  "\x28\xBF\x33\xCA\x61\xF8\x6C\x03"
-			  "\x9A\x0E\xA5\x3C\xD3\x47\xDE\x75"
-			  "\x0C\x80\x17\xAE\x22\xB9\x50\xE7"
-			  "\x5B\xF2\x89\x20\x94\x2B\xC2\x36"
-			  "\xCD\x64\xFB\x6F\x06\x9D\x11\xA8"
-			  "\x3F\xD6\x4A\xE1\x78\x0F\x83\x1A"
-			  "\xB1\x25\xBC\x53\xEA\x5E\xF5\x8C"
-			  "\x00\x97\x2E\xC5\x39\xD0\x67\xFE"
-			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D",
-		.rlen	= 1008,
+		.len	= 1008,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 1008 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
+static const struct cipher_testvec camellia_ctr_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -31266,7 +28404,7 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -31328,8 +28466,7 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
 			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.ilen	= 496,
-		.result	= "\xF3\x06\x3A\x84\xCD\xBA\x8E\x11"
+		.ctext	= "\xF3\x06\x3A\x84\xCD\xBA\x8E\x11"
 			  "\xB7\x74\x6F\x5C\x97\xFB\x36\xFE"
 			  "\xDE\x71\x58\xD4\x15\xD1\xC1\xA4"
 			  "\xC9\x28\x74\xA6\x6B\xC7\x95\xA6"
@@ -31391,7 +28528,7 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 			  "\x7E\x42\xEC\xB6\x6F\x4D\x6B\x48"
 			  "\xE6\xA6\x50\x80\x78\x9E\xF1\xB0"
 			  "\x4D\xB2\x0D\x3D\xFC\x40\x25\x4D",
-		.rlen	= 496,
+		.len	= 496,
 	}, { /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
 			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
@@ -31400,7 +28537,7 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
 			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -31527,8 +28664,7 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 			  "\x00\x97\x2E\xC5\x39\xD0\x67\xFE"
 			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D"
 			  "\xE4\x7B\x12",
-		.ilen	= 1011,
-		.result	= "\xF3\x06\x3A\x84\xCD\xBA\x8E\x11"
+		.ctext	= "\xF3\x06\x3A\x84\xCD\xBA\x8E\x11"
 			  "\xB7\x74\x6F\x5C\x97\xFB\x36\xFE"
 			  "\xDE\x71\x58\xD4\x15\xD1\xC1\xA4"
 			  "\xC9\x28\x74\xA6\x6B\xC7\x95\xA6"
@@ -31655,7 +28791,7 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 			  "\x45\xE3\x35\x0D\x69\x91\x54\x1C"
 			  "\xE7\x2C\x49\x08\x8B\x72\xFA\x5C"
 			  "\xF1\x6B\xD9",
-		.rlen	= 1011,
+		.len	= 1011,
 		.also_non_np = 1,
 		.np	= 2,
 		.tap	= { 1011 - 16, 16 },
@@ -31667,7 +28803,7 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
 			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
+		.ptext	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
 			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
 			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
 			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
@@ -31793,8 +28929,7 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 			  "\xB1\x25\xBC\x53\xEA\x5E\xF5\x8C"
 			  "\x00\x97\x2E\xC5\x39\xD0\x67\xFE"
 			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D",
-		.ilen	= 1008,
-		.result	= "\x85\x79\x6C\x8B\x2B\x6D\x14\xF9"
+		.ctext	= "\x85\x79\x6C\x8B\x2B\x6D\x14\xF9"
 			  "\xA6\x83\xB6\x80\x5B\x3A\xF3\x7E"
 			  "\x30\x29\xEB\x1F\xDC\x19\x5F\xEB"
 			  "\xF7\xC4\x27\x04\x51\x87\xD7\x6F"
@@ -31920,678 +29055,11 @@ static const struct cipher_testvec camellia_ctr_enc_tv_template[] = {
 			  "\xC5\x9B\x03\x70\x29\x2A\x49\x09"
 			  "\x67\xA1\xEA\xD6\x3A\x5B\xBF\x71"
 			  "\x1D\x48\x64\x6C\xFB\xC0\x9E\x36",
-		.rlen	= 1008,
+		.len	= 1008,
 	},
 };
 
-static const struct cipher_testvec camellia_ctr_dec_tv_template[] = {
-	{ /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\xF3\x06\x3A\x84\xCD\xBA\x8E\x11"
-			  "\xB7\x74\x6F\x5C\x97\xFB\x36\xFE"
-			  "\xDE\x71\x58\xD4\x15\xD1\xC1\xA4"
-			  "\xC9\x28\x74\xA6\x6B\xC7\x95\xA6"
-			  "\x6C\x77\xF7\x2F\xDF\xC7\xBB\x85"
-			  "\x60\xFC\xE8\x94\xE8\xB5\x09\x2C"
-			  "\x1E\x43\xEF\x6C\xE9\x98\xC5\xA0"
-			  "\x7B\x13\xE5\x7F\xF8\x49\x9A\x8C"
-			  "\xE6\x7B\x08\xC3\x32\x66\x55\x4E"
-			  "\xA5\x44\x1D\x2C\x18\xC7\x29\x1F"
-			  "\x61\x28\x4A\xE3\xCD\xE5\x47\xB2"
-			  "\x82\x2F\x66\x83\x91\x51\xAE\xD7"
-			  "\x1C\x91\x3C\x57\xE3\x1D\x5A\xC9"
-			  "\xFD\xC5\x58\x58\xEF\xCC\x33\xC9"
-			  "\x0F\xEA\x26\x32\xD1\x15\x19\x2D"
-			  "\x25\xB4\x7F\xB0\xDF\xFB\x88\x60"
-			  "\x4E\x4D\x06\x7D\xCC\x1F\xED\x3B"
-			  "\x68\x84\xD5\xB3\x1B\xE7\xB9\xA1"
-			  "\x68\x8B\x2C\x1A\x44\xDA\x63\xD3"
-			  "\x29\xE9\x59\x32\x1F\x30\x1C\x43"
-			  "\xEA\x3A\xA3\x6B\x54\x3C\xAA\x11"
-			  "\xAD\x38\x20\xC9\xB9\x8A\x64\x66"
-			  "\x5A\x07\x49\xDF\xA1\x9C\xF9\x76"
-			  "\x36\x65\xB6\x81\x8F\x76\x09\xE5"
-			  "\xEB\xD1\x29\xA4\xE4\xF4\x4C\xCD"
-			  "\xAF\xFC\xB9\x16\xD9\xC3\x73\x6A"
-			  "\x33\x12\xF8\x7E\xBC\xCC\x7D\x80"
-			  "\xBF\x3C\x25\x06\x13\x84\xFA\x35"
-			  "\xF7\x40\xFA\xA1\x44\x13\x70\xD8"
-			  "\x01\xF9\x85\x15\x63\xEC\x7D\xB9"
-			  "\x02\xD8\xBA\x41\x6C\x92\x68\x66"
-			  "\x95\xDD\xD6\x42\xE7\xBB\xE1\xFD"
-			  "\x28\x3E\x94\xB6\xBD\xA7\xBF\x47"
-			  "\x58\x8D\xFF\x19\x30\x75\x0D\x48"
-			  "\x94\xE9\xA6\xCD\xB3\x8E\x1E\xCD"
-			  "\x59\xBC\x1A\xAC\x3C\x4F\xA9\xEB"
-			  "\xF4\xA7\xE4\x75\x4A\x18\x40\xC9"
-			  "\x1E\xEC\x06\x9C\x28\x4B\xF7\x2B"
-			  "\xE2\xEF\xD6\x42\x2E\xBB\xFC\x0A"
-			  "\x79\xA2\x99\x28\x93\x1B\x00\x57"
-			  "\x35\x1E\x1A\x93\x90\xA4\x68\x95"
-			  "\x5E\x57\x40\xD5\xA9\xAA\x19\x48"
-			  "\xEC\xFF\x76\x77\xDC\x78\x89\x76"
-			  "\xE5\x3B\x00\xEC\x58\x4D\xD1\xE3"
-			  "\xC8\x6C\x2C\x45\x5E\x5F\xD9\x4E"
-			  "\x71\xA5\x36\x6D\x03\xF1\xC7\xD5"
-			  "\xF3\x63\xC0\xD8\xCB\x2B\xF1\xA8"
-			  "\xB9\x2B\xE6\x0B\xB9\x65\x78\xA0"
-			  "\xC4\x46\xE6\x9B\x8B\x43\x2D\xAB"
-			  "\x70\xA6\xE0\x59\x1E\xAC\x9D\xE0"
-			  "\x76\x44\x45\xF3\x24\x11\x57\x98"
-			  "\x9A\x86\xB4\x12\x80\x28\x86\x20"
-			  "\x23\x9D\x2D\xE9\x38\x32\xB1\xE1"
-			  "\xCF\x0A\x23\x73\x7D\xC5\x80\x3D"
-			  "\x9F\x6D\xA0\xD0\xEE\x93\x8A\x79"
-			  "\x3A\xDD\x1D\xBB\x9E\x26\x5D\x01"
-			  "\x44\xD0\xD4\x4E\xC3\xF1\xE4\x38"
-			  "\x09\x62\x0A\x1A\x4E\xD2\x63\x0F"
-			  "\x6E\x3E\xD2\xA4\x3A\xF4\xF3\xFF"
-			  "\x7E\x42\xEC\xB6\x6F\x4D\x6B\x48"
-			  "\xE6\xA6\x50\x80\x78\x9E\xF1\xB0"
-			  "\x4D\xB2\x0D\x3D\xFC\x40\x25\x4D",
-		.ilen	= 496,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
-		.rlen	= 496,
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xE2\x24\x89\xEE\x53\xB8\x1D\x5F"
-			  "\xC4\x29\x8E\xF3\x35\x9A\xFF\x64",
-		.input	= "\xF3\x06\x3A\x84\xCD\xBA\x8E\x11"
-			  "\xB7\x74\x6F\x5C\x97\xFB\x36\xFE"
-			  "\xDE\x71\x58\xD4\x15\xD1\xC1\xA4"
-			  "\xC9\x28\x74\xA6\x6B\xC7\x95\xA6"
-			  "\x6C\x77\xF7\x2F\xDF\xC7\xBB\x85"
-			  "\x60\xFC\xE8\x94\xE8\xB5\x09\x2C"
-			  "\x1E\x43\xEF\x6C\xE9\x98\xC5\xA0"
-			  "\x7B\x13\xE5\x7F\xF8\x49\x9A\x8C"
-			  "\xE6\x7B\x08\xC3\x32\x66\x55\x4E"
-			  "\xA5\x44\x1D\x2C\x18\xC7\x29\x1F"
-			  "\x61\x28\x4A\xE3\xCD\xE5\x47\xB2"
-			  "\x82\x2F\x66\x83\x91\x51\xAE\xD7"
-			  "\x1C\x91\x3C\x57\xE3\x1D\x5A\xC9"
-			  "\xFD\xC5\x58\x58\xEF\xCC\x33\xC9"
-			  "\x0F\xEA\x26\x32\xD1\x15\x19\x2D"
-			  "\x25\xB4\x7F\xB0\xDF\xFB\x88\x60"
-			  "\x4E\x4D\x06\x7D\xCC\x1F\xED\x3B"
-			  "\x68\x84\xD5\xB3\x1B\xE7\xB9\xA1"
-			  "\x68\x8B\x2C\x1A\x44\xDA\x63\xD3"
-			  "\x29\xE9\x59\x32\x1F\x30\x1C\x43"
-			  "\xEA\x3A\xA3\x6B\x54\x3C\xAA\x11"
-			  "\xAD\x38\x20\xC9\xB9\x8A\x64\x66"
-			  "\x5A\x07\x49\xDF\xA1\x9C\xF9\x76"
-			  "\x36\x65\xB6\x81\x8F\x76\x09\xE5"
-			  "\xEB\xD1\x29\xA4\xE4\xF4\x4C\xCD"
-			  "\xAF\xFC\xB9\x16\xD9\xC3\x73\x6A"
-			  "\x33\x12\xF8\x7E\xBC\xCC\x7D\x80"
-			  "\xBF\x3C\x25\x06\x13\x84\xFA\x35"
-			  "\xF7\x40\xFA\xA1\x44\x13\x70\xD8"
-			  "\x01\xF9\x85\x15\x63\xEC\x7D\xB9"
-			  "\x02\xD8\xBA\x41\x6C\x92\x68\x66"
-			  "\x95\xDD\xD6\x42\xE7\xBB\xE1\xFD"
-			  "\x28\x3E\x94\xB6\xBD\xA7\xBF\x47"
-			  "\x58\x8D\xFF\x19\x30\x75\x0D\x48"
-			  "\x94\xE9\xA6\xCD\xB3\x8E\x1E\xCD"
-			  "\x59\xBC\x1A\xAC\x3C\x4F\xA9\xEB"
-			  "\xF4\xA7\xE4\x75\x4A\x18\x40\xC9"
-			  "\x1E\xEC\x06\x9C\x28\x4B\xF7\x2B"
-			  "\xE2\xEF\xD6\x42\x2E\xBB\xFC\x0A"
-			  "\x79\xA2\x99\x28\x93\x1B\x00\x57"
-			  "\x35\x1E\x1A\x93\x90\xA4\x68\x95"
-			  "\x5E\x57\x40\xD5\xA9\xAA\x19\x48"
-			  "\xEC\xFF\x76\x77\xDC\x78\x89\x76"
-			  "\xE5\x3B\x00\xEC\x58\x4D\xD1\xE3"
-			  "\xC8\x6C\x2C\x45\x5E\x5F\xD9\x4E"
-			  "\x71\xA5\x36\x6D\x03\xF1\xC7\xD5"
-			  "\xF3\x63\xC0\xD8\xCB\x2B\xF1\xA8"
-			  "\xB9\x2B\xE6\x0B\xB9\x65\x78\xA0"
-			  "\xC4\x46\xE6\x9B\x8B\x43\x2D\xAB"
-			  "\x70\xA6\xE0\x59\x1E\xAC\x9D\xE0"
-			  "\x76\x44\x45\xF3\x24\x11\x57\x98"
-			  "\x9A\x86\xB4\x12\x80\x28\x86\x20"
-			  "\x23\x9D\x2D\xE9\x38\x32\xB1\xE1"
-			  "\xCF\x0A\x23\x73\x7D\xC5\x80\x3D"
-			  "\x9F\x6D\xA0\xD0\xEE\x93\x8A\x79"
-			  "\x3A\xDD\x1D\xBB\x9E\x26\x5D\x01"
-			  "\x44\xD0\xD4\x4E\xC3\xF1\xE4\x38"
-			  "\x09\x62\x0A\x1A\x4E\xD2\x63\x0F"
-			  "\x6E\x3E\xD2\xA4\x3A\xF4\xF3\xFF"
-			  "\x7E\x42\xEC\xB6\x6F\x4D\x6B\x48"
-			  "\xE6\xA6\x50\x80\x78\x9E\xF1\xB0"
-			  "\x4D\xB2\x0D\x3D\xFC\x40\x25\x4D"
-			  "\x93\x11\x1C\xE9\xD2\x9F\x6E\x90"
-			  "\xE5\x41\x4A\xE2\x3C\x45\x29\x35"
-			  "\xEC\xD6\x47\x50\xCB\x7B\xA2\x32"
-			  "\xF7\x8B\x62\xF1\xE3\x9A\xFE\xC7"
-			  "\x1D\x8C\x02\x72\x68\x09\xE9\xB6"
-			  "\x4A\x80\xE6\xB1\x56\xDF\x90\xD4"
-			  "\x93\x74\xA4\xCE\x20\x23\xBF\x48"
-			  "\xA5\xDE\x1B\xFA\x40\x69\x31\x98"
-			  "\x62\x6E\xA5\xC7\xBF\x0C\x62\xE5"
-			  "\x6D\xE1\x93\xF1\x83\x10\x1C\xCA"
-			  "\xF6\x5C\x19\xF8\x90\x78\xCB\xE4"
-			  "\x0B\x3A\xB5\xF8\x43\x86\xD3\x3F"
-			  "\xBA\x83\x34\x3C\x42\xCC\x7D\x28"
-			  "\x29\x63\x4F\xD8\x02\x17\xC5\x07"
-			  "\x2C\xA4\xAC\x79\xCB\xC3\xA9\x09"
-			  "\x81\x45\x18\xED\xE4\xCB\x42\x3B"
-			  "\x87\x2D\x23\xDC\xC5\xBA\x45\xBD"
-			  "\x92\xE5\x02\x97\x96\xCE\xAD\xEC"
-			  "\xBA\xD8\x76\xF8\xCA\xC1\x31\xEC"
-			  "\x1E\x4F\x3F\x83\xF8\x33\xE8\x6E"
-			  "\xCC\xF8\x5F\xDD\x65\x50\x99\x69"
-			  "\xAF\x48\xCE\xA5\xBA\xB6\x14\x9F"
-			  "\x05\x93\xB2\xE6\x59\xC8\x28\xFE"
-			  "\x8F\x37\xF9\x64\xB9\xA5\x56\x8F"
-			  "\xF1\x1B\x90\xEF\xAE\xEB\xFC\x09"
-			  "\x11\x7A\xF2\x19\x0A\x0A\x9A\x3C"
-			  "\xE2\x5E\x29\xFA\x31\x9B\xC1\x74"
-			  "\x1E\x10\x3E\x07\xA9\x31\x6D\xF8"
-			  "\x81\xF5\xD5\x8A\x04\x23\x51\xAC"
-			  "\xA2\xE2\x63\xFD\x27\x1F\x79\x5B"
-			  "\x1F\xE8\xDA\x11\x49\x4D\x1C\xBA"
-			  "\x54\xCC\x0F\xBA\x92\x69\xE5\xCB"
-			  "\x41\x1A\x67\xA6\x40\x82\x70\x8C"
-			  "\x19\x79\x08\xA4\x51\x20\x7D\xC9"
-			  "\x12\x27\xAE\x20\x0D\x2C\xA1\x6D"
-			  "\xF4\x55\xD4\xE7\xE6\xD4\x28\x08"
-			  "\x00\x70\x12\x56\x56\x50\xAD\x14"
-			  "\x5C\x3E\xA2\xD1\x36\x3F\x36\x48"
-			  "\xED\xB1\x57\x3E\x5D\x15\xF6\x1E"
-			  "\x53\xE9\xA4\x3E\xED\x7D\xCF\x7D"
-			  "\x29\xAF\xF3\x1E\x51\xA8\x9F\x85"
-			  "\x8B\xF0\xBB\xCE\xCC\x39\xC3\x64"
-			  "\x4B\xF2\xAD\x70\x19\xD4\x44\x8F"
-			  "\x91\x76\xE8\x15\x66\x34\x9F\xF6"
-			  "\x0F\x15\xA4\xA8\x24\xF8\x58\xB1"
-			  "\x38\x46\x47\xC7\x9B\xCA\xE9\x42"
-			  "\x44\xAA\xE6\xB5\x9C\x91\xA4\xD3"
-			  "\x16\xA0\xED\x42\xBE\xB5\x06\x19"
-			  "\xBE\x67\xE8\xBC\x22\x32\xA4\x1E"
-			  "\x93\xEB\xBE\xE9\xE1\x93\xE5\x31"
-			  "\x3A\xA2\x75\xDF\xE3\x6B\xE7\xCC"
-			  "\xB4\x70\x20\xE0\x6D\x82\x7C\xC8"
-			  "\x94\x5C\x5E\x37\x18\xAD\xED\x8B"
-			  "\x44\x86\xCA\x5E\x07\xB7\x70\x8D"
-			  "\x40\x48\x19\x73\x7C\x78\x64\x0B"
-			  "\xDB\x01\xCA\xAE\x63\x19\xE9\xD1"
-			  "\x6B\x2C\x84\x10\x45\x42\x2E\xC3"
-			  "\xDF\x7F\xAA\xE8\x87\x1B\x63\x46"
-			  "\x74\x28\x9D\x05\x30\x20\x62\x41"
-			  "\xC0\x9F\x2C\x36\x2B\x78\xD7\x26"
-			  "\xDF\x58\x51\xED\xFA\xDC\x87\x79"
-			  "\xBF\x8C\xBF\xC4\x0F\xE5\x05\xDA"
-			  "\x45\xE3\x35\x0D\x69\x91\x54\x1C"
-			  "\xE7\x2C\x49\x08\x8B\x72\xFA\x5C"
-			  "\xF1\x6B\xD9",
-		.ilen	= 1011,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06"
-			  "\x9D\x34\xCB\x3F\xD6\x6D\x04\x78"
-			  "\x0F\xA6\x1A\xB1\x48\xDF\x53\xEA"
-			  "\x81\x18\x8C\x23\xBA\x2E\xC5\x5C"
-			  "\xF3\x67\xFE\x95\x09\xA0\x37\xCE"
-			  "\x42\xD9\x70\x07\x7B\x12\xA9\x1D"
-			  "\xB4\x4B\xE2\x56\xED\x84\x1B\x8F"
-			  "\x26\xBD\x31\xC8\x5F\xF6\x6A\x01"
-			  "\x98\x0C\xA3\x3A\xD1\x45\xDC\x73"
-			  "\x0A\x7E\x15\xAC\x20\xB7\x4E\xE5"
-			  "\x59\xF0\x87\x1E\x92\x29\xC0\x34"
-			  "\xCB\x62\xF9\x6D\x04\x9B\x0F\xA6"
-			  "\x3D\xD4\x48\xDF\x76\x0D\x81\x18"
-			  "\xAF\x23\xBA\x51\xE8\x5C\xF3\x8A"
-			  "\x21\x95\x2C\xC3\x37\xCE\x65\xFC"
-			  "\x70\x07\x9E\x12\xA9\x40\xD7\x4B"
-			  "\xE2\x79\x10\x84\x1B\xB2\x26\xBD"
-			  "\x54\xEB\x5F\xF6\x8D\x01\x98\x2F"
-			  "\xC6\x3A\xD1\x68\xFF\x73\x0A\xA1"
-			  "\x15\xAC\x43\xDA\x4E\xE5\x7C\x13"
-			  "\x87\x1E\xB5\x29\xC0\x57\xEE\x62"
-			  "\xF9\x90\x04\x9B\x32\xC9\x3D\xD4"
-			  "\x6B\x02\x76\x0D\xA4\x18\xAF\x46"
-			  "\xDD\x51\xE8\x7F\x16\x8A\x21\xB8"
-			  "\x2C\xC3\x5A\xF1\x65\xFC\x93\x07"
-			  "\x9E\x35\xCC\x40\xD7\x6E\x05\x79"
-			  "\x10\xA7\x1B\xB2\x49\xE0\x54\xEB"
-			  "\x82\x19\x8D\x24\xBB\x2F\xC6\x5D"
-			  "\xF4\x68\xFF\x96\x0A\xA1\x38\xCF"
-			  "\x43\xDA\x71\x08\x7C\x13\xAA\x1E"
-			  "\xB5\x4C\xE3\x57\xEE\x85\x1C\x90"
-			  "\x27\xBE\x32\xC9\x60\xF7\x6B\x02"
-			  "\x99\x0D\xA4\x3B\xD2\x46\xDD\x74"
-			  "\x0B\x7F\x16\xAD\x21\xB8\x4F\xE6"
-			  "\x5A\xF1\x88\x1F\x93\x2A\xC1\x35"
-			  "\xCC\x63\xFA\x6E\x05\x9C\x10\xA7"
-			  "\x3E\xD5\x49\xE0\x77\x0E\x82\x19"
-			  "\xB0\x24\xBB\x52\xE9\x5D\xF4\x8B"
-			  "\x22\x96\x2D\xC4\x38\xCF\x66\xFD"
-			  "\x71\x08\x9F\x13\xAA\x41\xD8\x4C"
-			  "\xE3\x7A\x11\x85\x1C\xB3\x27\xBE"
-			  "\x55\xEC\x60\xF7\x8E\x02\x99\x30"
-			  "\xC7\x3B\xD2\x69\x00\x74\x0B\xA2"
-			  "\x16\xAD\x44\xDB\x4F\xE6\x7D\x14"
-			  "\x88\x1F\xB6\x2A\xC1\x58\xEF\x63"
-			  "\xFA\x91\x05\x9C\x33\xCA\x3E\xD5"
-			  "\x6C\x03\x77\x0E\xA5\x19\xB0\x47"
-			  "\xDE\x52\xE9\x80\x17\x8B\x22\xB9"
-			  "\x2D\xC4\x5B\xF2\x66\xFD\x94\x08"
-			  "\x9F\x36\xCD\x41\xD8\x6F\x06\x7A"
-			  "\x11\xA8\x1C\xB3\x4A\xE1\x55\xEC"
-			  "\x83\x1A\x8E\x25\xBC\x30\xC7\x5E"
-			  "\xF5\x69\x00\x97\x0B\xA2\x39\xD0"
-			  "\x44\xDB\x72\x09\x7D\x14\xAB\x1F"
-			  "\xB6\x4D\xE4\x58\xEF\x86\x1D\x91"
-			  "\x28\xBF\x33\xCA\x61\xF8\x6C\x03"
-			  "\x9A\x0E\xA5\x3C\xD3\x47\xDE\x75"
-			  "\x0C\x80\x17\xAE\x22\xB9\x50\xE7"
-			  "\x5B\xF2\x89\x20\x94\x2B\xC2\x36"
-			  "\xCD\x64\xFB\x6F\x06\x9D\x11\xA8"
-			  "\x3F\xD6\x4A\xE1\x78\x0F\x83\x1A"
-			  "\xB1\x25\xBC\x53\xEA\x5E\xF5\x8C"
-			  "\x00\x97\x2E\xC5\x39\xD0\x67\xFE"
-			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D"
-			  "\xE4\x7B\x12",
-		.rlen	= 1011,
-		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 1011 - 16, 16 },
-	}, { /* Generated with Crypto++ */
-		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
-			  "\xD6\xB3\x90\x6D\x4A\x90\x6D\x4A"
-			  "\x27\x04\xE1\x27\x04\xE1\xBE\x9B"
-			  "\x78\xBE\x9B\x78\x55\x32\x0F\x55",
-		.klen	= 32,
-		.iv	= "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"
-			  "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFD",
-		.input	= "\x85\x79\x6C\x8B\x2B\x6D\x14\xF9"
-			  "\xA6\x83\xB6\x80\x5B\x3A\xF3\x7E"
-			  "\x30\x29\xEB\x1F\xDC\x19\x5F\xEB"
-			  "\xF7\xC4\x27\x04\x51\x87\xD7\x6F"
-			  "\xB8\x4E\x07\xFB\xAC\x3B\x08\xB4"
-			  "\x4D\xCB\xE8\xE1\x71\x7D\x4F\x48"
-			  "\xCD\x81\x64\xA5\xC4\x07\x1A\x9A"
-			  "\x4B\x62\x90\x0E\xC8\xB3\x2B\x6B"
-			  "\x8F\x9C\x6E\x72\x4B\xBA\xEF\x07"
-			  "\x2C\x56\x07\x5E\x37\x30\x60\xA9"
-			  "\xE3\xEF\xD6\x69\xE1\xA1\x77\x64"
-			  "\x93\x75\x7A\xB7\x7A\x3B\xE9\x43"
-			  "\x23\x35\x95\x91\x80\x8A\xC7\xCF"
-			  "\xC3\xD5\xBF\xE7\xFE\x4C\x06\x6B"
-			  "\x05\x19\x48\xE2\x62\xBA\x4F\xF2"
-			  "\xFB\xEE\xE4\xCB\x79\x9D\xA3\x10"
-			  "\x1D\x29\x8C\x1D\x7A\x88\x5A\xDD"
-			  "\x4E\xB6\x18\xAA\xCD\xE6\x33\x96"
-			  "\xD9\x0F\x90\x5A\x78\x76\x4D\x77"
-			  "\x3C\x20\x89\x3B\xA3\xF9\x07\xFD"
-			  "\xE4\xE8\x20\x2D\x15\x0A\x63\x49"
-			  "\xF5\x4F\x89\xD8\xDE\xA1\x28\x78"
-			  "\x28\x07\x09\x1B\x03\x94\x1D\x4B"
-			  "\x82\x28\x1E\x1D\x95\xBA\xAC\x85"
-			  "\x71\x6E\x3C\x18\x4B\x77\x74\x79"
-			  "\xBF\x67\x0A\x53\x3C\x94\xD9\x60"
-			  "\xE9\x6D\x40\x34\xA0\x2A\x53\x5D"
-			  "\x27\xD5\x47\xF9\xC3\x4B\x27\x29"
-			  "\xE4\x76\x9C\x3F\xA7\x1C\x87\xFC"
-			  "\x6E\x0F\xCF\x9B\x60\xF0\xF0\x8B"
-			  "\x70\x1C\x84\x81\x72\x4D\xB4\x98"
-			  "\x23\x62\xE7\x6A\x2B\xFC\xA5\xB2"
-			  "\xFF\xF5\x71\x07\xCD\x90\x23\x13"
-			  "\x19\xD7\x79\x36\x6C\x9D\x55\x8B"
-			  "\x93\x78\x86\x05\x69\x46\xD0\xC5"
-			  "\x39\x09\xEB\x79\xEF\xFA\x9F\xAE"
-			  "\xF3\xD5\x44\xC3\xFD\x86\xD2\x7C"
-			  "\x83\x4B\xD8\x75\x9C\x18\x04\x7B"
-			  "\x73\xAD\x72\xA4\xF6\xAB\xCF\x4B"
-			  "\xCC\x01\x45\x90\xA6\x43\x05\x0C"
-			  "\x6C\x4F\x62\x77\x57\x97\x9F\xEE"
-			  "\x75\xA7\x3C\x38\xD1\x0F\x3D\x0E"
-			  "\x2C\x43\x98\xFB\x13\x65\x73\xE4"
-			  "\x3C\x1E\xD6\x90\x08\xF7\xE0\x99"
-			  "\x3B\xF1\x9D\x6C\x48\xA9\x0E\x32"
-			  "\x17\xC2\xCC\x20\xA1\x19\x26\xAA"
-			  "\xE0\x75\x2F\xFB\x54\x66\x0A\xDF"
-			  "\xB5\xF2\x1F\xC1\x34\x3C\x30\x56"
-			  "\xE8\xDC\xF7\x92\x6B\xBF\x17\x24"
-			  "\xEC\x94\xB5\x3B\xD6\xCE\xA2\x54"
-			  "\x10\x7F\x50\xDE\x69\x77\xD5\x37"
-			  "\xFE\x9C\x10\x83\xC5\xEB\xC9\x53"
-			  "\xB7\xF3\xC4\x20\xAF\x0A\x7E\x57"
-			  "\x3A\xE6\x75\xFE\x89\x00\x6E\x48"
-			  "\xFB\x99\x17\x2C\xF6\x64\x40\x95"
-			  "\x5E\xDC\x7A\xA6\x70\xC7\xF4\xDD"
-			  "\x52\x05\x24\x34\xF9\x0E\xC8\x64"
-			  "\x6D\xE2\xD8\x80\x53\x31\x4C\xFE"
-			  "\xB4\x3A\x5F\x19\xCF\x42\x1B\x22"
-			  "\x0B\x2D\x7B\xF1\xC5\x43\xF7\x5E"
-			  "\x12\xA8\x01\x64\x16\x0B\x26\x5A"
-			  "\x0C\x95\x0F\x40\xC5\x5A\x06\x7C"
-			  "\xCF\xF5\xD5\xB7\x7A\x34\x23\xB6"
-			  "\xAA\x9E\xA8\x98\xA2\xF8\x3D\xD3"
-			  "\x3F\x23\x69\x63\x56\x96\x45\xD6"
-			  "\x74\x23\x1D\x5C\x63\xCC\xD8\x78"
-			  "\x16\xE2\x9C\xD2\x80\x02\xF2\x28"
-			  "\x69\x2F\xC4\xA8\x15\x15\x24\x3B"
-			  "\xCB\xF0\x14\xE4\x62\xC8\xF3\xD1"
-			  "\x03\x58\x1B\x33\x77\x74\x1F\xB4"
-			  "\x07\x86\xF2\x21\xB7\x41\xAE\xBF"
-			  "\x25\xC2\xFF\x51\xEF\xEA\xCE\xC4"
-			  "\x5F\xD9\xB8\x18\x6A\xF0\x0F\x0D"
-			  "\xF8\x04\xBB\x6D\x62\x33\x87\x26"
-			  "\x4F\x2F\x14\x6E\xDC\xDB\x66\x09"
-			  "\x2A\xEF\x7D\x84\x10\xAC\x82\x5E"
-			  "\xD2\xE4\xAD\x74\x7A\x6D\xCC\x3A"
-			  "\x7B\x62\xD8\xD6\x07\x2D\xF7\xDF"
-			  "\x9B\xB3\x82\xCF\x9C\x1D\x76\x5C"
-			  "\xAC\x7B\xD4\x9B\x45\xA1\x64\x11"
-			  "\x66\xF1\xA7\x0B\xF9\xDD\x00\xDD"
-			  "\xA4\x45\x3D\x3E\x03\xC9\x2E\xCB"
-			  "\xC3\x14\x84\x72\xFD\x41\xDC\xBD"
-			  "\x75\xBE\xA8\xE5\x16\x48\x64\x39"
-			  "\xCA\xF3\xE6\xDC\x25\x24\xF1\x6D"
-			  "\xB2\x8D\xC5\x38\x54\xD3\x5D\x6D"
-			  "\x0B\x29\x10\x15\x0E\x13\x3B\xAC"
-			  "\x7E\xCC\x9E\x3E\x18\x48\xA6\x02"
-			  "\xEF\x03\xB2\x2E\xE3\xD2\x70\x21"
-			  "\xB4\x19\x26\xBE\x3A\x3D\x05\xE0"
-			  "\xF8\x09\xAF\xE4\x31\x26\x92\x2F"
-			  "\x8F\x55\xAC\xED\x0B\xB2\xA5\x34"
-			  "\xBE\x50\xB1\x02\x22\x96\xE3\x40"
-			  "\x7B\x70\x50\x6E\x3B\xD5\xE5\xA0"
-			  "\x8E\xA2\xAD\x14\x60\x5C\x7A\x2B"
-			  "\x3D\x1B\x7F\xC1\xC0\x2C\x56\x36"
-			  "\xD2\x0A\x32\x06\x97\x34\xB9\xF4"
-			  "\x6F\x9F\x7E\x80\xD0\x9D\xF7\x6A"
-			  "\x21\xC1\xA2\x6A\xB1\x96\x5B\x4D"
-			  "\x7A\x15\x6C\xC4\x4E\xB8\xE0\x9E"
-			  "\x6C\x50\xF3\x9C\xC9\xB5\x23\xB7"
-			  "\xF1\xD4\x29\x4A\x23\xC4\xAD\x1E"
-			  "\x2C\x07\xD2\x43\x5F\x57\x93\xCA"
-			  "\x85\xF9\x9F\xAD\x4C\xF1\xE4\xB1"
-			  "\x1A\x8E\x28\xA4\xB6\x52\x77\x7E"
-			  "\x68\xC6\x47\xB9\x76\xCC\x65\x5F"
-			  "\x0B\xF9\x67\x93\xD8\x0E\x9A\x37"
-			  "\x5F\x41\xED\x64\x6C\xAD\x5F\xED"
-			  "\x3F\x8D\xFB\x8E\x1E\xA0\xE4\x1F"
-			  "\xC2\xC7\xED\x18\x43\xE1\x20\x86"
-			  "\x5D\xBC\x30\x70\x22\xA1\xDC\x53"
-			  "\x10\x3A\x8D\x47\x82\xCD\x7F\x59"
-			  "\x03\x2D\x6D\xF5\xE7\x79\xD4\x07"
-			  "\x68\x2A\xA5\x42\x19\x4D\xAF\xF5"
-			  "\xED\x47\x83\xBC\x5F\x62\x84\xDA"
-			  "\xDA\x41\xFF\xB0\x1D\x64\xA3\xC8"
-			  "\xBD\x4E\xE0\xB8\x7F\xEE\x55\x0A"
-			  "\x4E\x61\xB2\x51\xF6\x9C\x95\xF6"
-			  "\x92\xBB\xF6\xC5\xF0\x09\x86\xDE"
-			  "\x37\x9E\x29\xF9\x2A\x18\x73\x0D"
-			  "\xDC\x7E\x6B\x7B\x1B\x43\x8C\xEA"
-			  "\x13\xC8\x1A\x47\x0A\x2D\x6D\x56"
-			  "\xCD\xD2\xE7\x53\x1A\xAB\x1C\x3C"
-			  "\xC5\x9B\x03\x70\x29\x2A\x49\x09"
-			  "\x67\xA1\xEA\xD6\x3A\x5B\xBF\x71"
-			  "\x1D\x48\x64\x6C\xFB\xC0\x9E\x36",
-		.ilen	= 1008,
-		.result	= "\x56\xED\x84\x1B\x8F\x26\xBD\x31"
-			  "\xC8\x5F\xF6\x6A\x01\x98\x0C\xA3"
-			  "\x3A\xD1\x45\xDC\x73\x0A\x7E\x15"
-			  "\xAC\x20\xB7\x4E\xE5\x59\xF0\x87"
-			  "\x1E\x92\x29\xC0\x34\xCB\x62\xF9"
-			  "\x6D\x04\x9B\x0F\xA6\x3D\xD4\x48"
-			  "\xDF\x76\x0D\x81\x18\xAF\x23\xBA"
-			  "\x51\xE8\x5C\xF3\x8A\x21\x95\x2C"
-			  "\xC3\x37\xCE\x65\xFC\x70\x07\x9E"
-			  "\x12\xA9\x40\xD7\x4B\xE2\x79\x10"
-			  "\x84\x1B\xB2\x26\xBD\x54\xEB\x5F"
-			  "\xF6\x8D\x01\x98\x2F\xC6\x3A\xD1"
-			  "\x68\xFF\x73\x0A\xA1\x15\xAC\x43"
-			  "\xDA\x4E\xE5\x7C\x13\x87\x1E\xB5"
-			  "\x29\xC0\x57\xEE\x62\xF9\x90\x04"
-			  "\x9B\x32\xC9\x3D\xD4\x6B\x02\x76"
-			  "\x0D\xA4\x18\xAF\x46\xDD\x51\xE8"
-			  "\x7F\x16\x8A\x21\xB8\x2C\xC3\x5A"
-			  "\xF1\x65\xFC\x93\x07\x9E\x35\xCC"
-			  "\x40\xD7\x6E\x05\x79\x10\xA7\x1B"
-			  "\xB2\x49\xE0\x54\xEB\x82\x19\x8D"
-			  "\x24\xBB\x2F\xC6\x5D\xF4\x68\xFF"
-			  "\x96\x0A\xA1\x38\xCF\x43\xDA\x71"
-			  "\x08\x7C\x13\xAA\x1E\xB5\x4C\xE3"
-			  "\x57\xEE\x85\x1C\x90\x27\xBE\x32"
-			  "\xC9\x60\xF7\x6B\x02\x99\x0D\xA4"
-			  "\x3B\xD2\x46\xDD\x74\x0B\x7F\x16"
-			  "\xAD\x21\xB8\x4F\xE6\x5A\xF1\x88"
-			  "\x1F\x93\x2A\xC1\x35\xCC\x63\xFA"
-			  "\x6E\x05\x9C\x10\xA7\x3E\xD5\x49"
-			  "\xE0\x77\x0E\x82\x19\xB0\x24\xBB"
-			  "\x52\xE9\x5D\xF4\x8B\x22\x96\x2D"
-			  "\xC4\x38\xCF\x66\xFD\x71\x08\x9F"
-			  "\x13\xAA\x41\xD8\x4C\xE3\x7A\x11"
-			  "\x85\x1C\xB3\x27\xBE\x55\xEC\x60"
-			  "\xF7\x8E\x02\x99\x30\xC7\x3B\xD2"
-			  "\x69\x00\x74\x0B\xA2\x16\xAD\x44"
-			  "\xDB\x4F\xE6\x7D\x14\x88\x1F\xB6"
-			  "\x2A\xC1\x58\xEF\x63\xFA\x91\x05"
-			  "\x9C\x33\xCA\x3E\xD5\x6C\x03\x77"
-			  "\x0E\xA5\x19\xB0\x47\xDE\x52\xE9"
-			  "\x80\x17\x8B\x22\xB9\x2D\xC4\x5B"
-			  "\xF2\x66\xFD\x94\x08\x9F\x36\xCD"
-			  "\x41\xD8\x6F\x06\x7A\x11\xA8\x1C"
-			  "\xB3\x4A\xE1\x55\xEC\x83\x1A\x8E"
-			  "\x25\xBC\x30\xC7\x5E\xF5\x69\x00"
-			  "\x97\x0B\xA2\x39\xD0\x44\xDB\x72"
-			  "\x09\x7D\x14\xAB\x1F\xB6\x4D\xE4"
-			  "\x58\xEF\x86\x1D\x91\x28\xBF\x33"
-			  "\xCA\x61\xF8\x6C\x03\x9A\x0E\xA5"
-			  "\x3C\xD3\x47\xDE\x75\x0C\x80\x17"
-			  "\xAE\x22\xB9\x50\xE7\x5B\xF2\x89"
-			  "\x20\x94\x2B\xC2\x36\xCD\x64\xFB"
-			  "\x6F\x06\x9D\x11\xA8\x3F\xD6\x4A"
-			  "\xE1\x78\x0F\x83\x1A\xB1\x25\xBC"
-			  "\x53\xEA\x5E\xF5\x8C\x00\x97\x2E"
-			  "\xC5\x39\xD0\x67\xFE\x72\x09\xA0"
-			  "\x14\xAB\x42\xD9\x4D\xE4\x7B\x12"
-			  "\x86\x1D\xB4\x28\xBF\x56\xED\x61"
-			  "\xF8\x8F\x03\x9A\x31\xC8\x3C\xD3"
-			  "\x6A\x01\x75\x0C\xA3\x17\xAE\x45"
-			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7"
-			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06"
-			  "\x9D\x34\xCB\x3F\xD6\x6D\x04\x78"
-			  "\x0F\xA6\x1A\xB1\x48\xDF\x53\xEA"
-			  "\x81\x18\x8C\x23\xBA\x2E\xC5\x5C"
-			  "\xF3\x67\xFE\x95\x09\xA0\x37\xCE"
-			  "\x42\xD9\x70\x07\x7B\x12\xA9\x1D"
-			  "\xB4\x4B\xE2\x56\xED\x84\x1B\x8F"
-			  "\x26\xBD\x31\xC8\x5F\xF6\x6A\x01"
-			  "\x98\x0C\xA3\x3A\xD1\x45\xDC\x73"
-			  "\x0A\x7E\x15\xAC\x20\xB7\x4E\xE5"
-			  "\x59\xF0\x87\x1E\x92\x29\xC0\x34"
-			  "\xCB\x62\xF9\x6D\x04\x9B\x0F\xA6"
-			  "\x3D\xD4\x48\xDF\x76\x0D\x81\x18"
-			  "\xAF\x23\xBA\x51\xE8\x5C\xF3\x8A"
-			  "\x21\x95\x2C\xC3\x37\xCE\x65\xFC"
-			  "\x70\x07\x9E\x12\xA9\x40\xD7\x4B"
-			  "\xE2\x79\x10\x84\x1B\xB2\x26\xBD"
-			  "\x54\xEB\x5F\xF6\x8D\x01\x98\x2F"
-			  "\xC6\x3A\xD1\x68\xFF\x73\x0A\xA1"
-			  "\x15\xAC\x43\xDA\x4E\xE5\x7C\x13"
-			  "\x87\x1E\xB5\x29\xC0\x57\xEE\x62"
-			  "\xF9\x90\x04\x9B\x32\xC9\x3D\xD4"
-			  "\x6B\x02\x76\x0D\xA4\x18\xAF\x46"
-			  "\xDD\x51\xE8\x7F\x16\x8A\x21\xB8"
-			  "\x2C\xC3\x5A\xF1\x65\xFC\x93\x07"
-			  "\x9E\x35\xCC\x40\xD7\x6E\x05\x79"
-			  "\x10\xA7\x1B\xB2\x49\xE0\x54\xEB"
-			  "\x82\x19\x8D\x24\xBB\x2F\xC6\x5D"
-			  "\xF4\x68\xFF\x96\x0A\xA1\x38\xCF"
-			  "\x43\xDA\x71\x08\x7C\x13\xAA\x1E"
-			  "\xB5\x4C\xE3\x57\xEE\x85\x1C\x90"
-			  "\x27\xBE\x32\xC9\x60\xF7\x6B\x02"
-			  "\x99\x0D\xA4\x3B\xD2\x46\xDD\x74"
-			  "\x0B\x7F\x16\xAD\x21\xB8\x4F\xE6"
-			  "\x5A\xF1\x88\x1F\x93\x2A\xC1\x35"
-			  "\xCC\x63\xFA\x6E\x05\x9C\x10\xA7"
-			  "\x3E\xD5\x49\xE0\x77\x0E\x82\x19"
-			  "\xB0\x24\xBB\x52\xE9\x5D\xF4\x8B"
-			  "\x22\x96\x2D\xC4\x38\xCF\x66\xFD"
-			  "\x71\x08\x9F\x13\xAA\x41\xD8\x4C"
-			  "\xE3\x7A\x11\x85\x1C\xB3\x27\xBE"
-			  "\x55\xEC\x60\xF7\x8E\x02\x99\x30"
-			  "\xC7\x3B\xD2\x69\x00\x74\x0B\xA2"
-			  "\x16\xAD\x44\xDB\x4F\xE6\x7D\x14"
-			  "\x88\x1F\xB6\x2A\xC1\x58\xEF\x63"
-			  "\xFA\x91\x05\x9C\x33\xCA\x3E\xD5"
-			  "\x6C\x03\x77\x0E\xA5\x19\xB0\x47"
-			  "\xDE\x52\xE9\x80\x17\x8B\x22\xB9"
-			  "\x2D\xC4\x5B\xF2\x66\xFD\x94\x08"
-			  "\x9F\x36\xCD\x41\xD8\x6F\x06\x7A"
-			  "\x11\xA8\x1C\xB3\x4A\xE1\x55\xEC"
-			  "\x83\x1A\x8E\x25\xBC\x30\xC7\x5E"
-			  "\xF5\x69\x00\x97\x0B\xA2\x39\xD0"
-			  "\x44\xDB\x72\x09\x7D\x14\xAB\x1F"
-			  "\xB6\x4D\xE4\x58\xEF\x86\x1D\x91"
-			  "\x28\xBF\x33\xCA\x61\xF8\x6C\x03"
-			  "\x9A\x0E\xA5\x3C\xD3\x47\xDE\x75"
-			  "\x0C\x80\x17\xAE\x22\xB9\x50\xE7"
-			  "\x5B\xF2\x89\x20\x94\x2B\xC2\x36"
-			  "\xCD\x64\xFB\x6F\x06\x9D\x11\xA8"
-			  "\x3F\xD6\x4A\xE1\x78\x0F\x83\x1A"
-			  "\xB1\x25\xBC\x53\xEA\x5E\xF5\x8C"
-			  "\x00\x97\x2E\xC5\x39\xD0\x67\xFE"
-			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D",
-		.rlen	= 1008,
-	},
-};
-
-static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
+static const struct cipher_testvec camellia_lrw_tv_template[] = {
 	/* Generated from AES-LRW test vectors */
 	{
 		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
@@ -32601,12 +29069,11 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x92\x68\x19\xd7\xb7\x5b\x0a\x31"
+		.ctext	= "\x92\x68\x19\xd7\xb7\x5b\x0a\x31"
 			  "\x97\xcc\x72\xbe\x99\x17\xeb\x3e",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x59\x70\x47\x14\xf5\x57\x47\x8c"
 			  "\xd7\x79\xe8\x0f\x54\x88\x79\x44"
@@ -32615,12 +29082,11 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x73\x09\xb7\x50\xb6\x77\x30\x50"
+		.ctext	= "\x73\x09\xb7\x50\xb6\x77\x30\x50"
 			  "\x5c\x8a\x9c\x26\x77\x9d\xfc\x4a",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xd8\x2a\x91\x34\xb2\x6a\x56\x50"
 			  "\x30\xfe\x69\xe2\x37\x7f\x98\x47"
@@ -32629,12 +29095,11 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x90\xae\x83\xe0\x22\xb9\x60\x91"
+		.ctext	= "\x90\xae\x83\xe0\x22\xb9\x60\x91"
 			  "\xfa\xa9\xb7\x98\xe3\xed\x87\x01",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x0f\x6a\xef\xf8\xd3\xd2\xbb\x15"
 			  "\x25\x83\xf7\x3c\x1f\x01\x28\x74"
@@ -32644,12 +29109,11 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 		.klen	= 40,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x99\xe9\x6e\xd4\xc9\x21\xa5\xf0"
+		.ctext	= "\x99\xe9\x6e\xd4\xc9\x21\xa5\xf0"
 			  "\xd8\x83\xef\xd9\x07\x16\x5f\x35",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x8a\xd4\xee\x10\x2f\xbd\x81\xff"
 			  "\xf8\x86\xce\xac\x93\xc5\xad\xc6"
@@ -32659,12 +29123,11 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 		.klen	= 40,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x42\x88\xf4\xcb\x21\x11\x6d\x8e"
+		.ctext	= "\x42\x88\xf4\xcb\x21\x11\x6d\x8e"
 			  "\xde\x1a\xf2\x29\xf1\x4a\xe0\x15",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -32675,12 +29138,11 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x40\xaa\x34\x86\x4a\x8f\x78\xb9"
+		.ctext	= "\x40\xaa\x34\x86\x4a\x8f\x78\xb9"
 			  "\xdb\xdb\x0f\x3d\x48\x70\xbe\x8d",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xfb\x76\x15\xb2\x3d\x80\x89\x1d"
 			  "\xd4\x70\x98\x0b\xc7\x95\x84\xc8"
@@ -32691,12 +29153,11 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x30\x31\x32\x33\x34\x35\x36\x37"
+		.ptext	= "\x30\x31\x32\x33\x34\x35\x36\x37"
 			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.ilen	= 16,
-		.result	= "\x04\xab\x28\x37\x31\x7a\x26\xab"
+		.ctext	= "\x04\xab\x28\x37\x31\x7a\x26\xab"
 			  "\xa1\x70\x1b\x9c\xe7\xdd\x83\xff",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
 			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
@@ -32707,7 +29168,7 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 		.klen	= 48,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
+		.ptext	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
 			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
 			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
 			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
@@ -32771,8 +29232,7 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
 			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.ilen	= 512,
-		.result	= "\x90\x69\x8e\xf2\x14\x86\x59\xf9"
+		.ctext	= "\x90\x69\x8e\xf2\x14\x86\x59\xf9"
 			  "\xec\xe7\xfa\x3f\x48\x9d\x7f\x96"
 			  "\x67\x76\xac\x2c\xd2\x63\x18\x93"
 			  "\x13\xf8\xf1\xf6\x71\x77\xb3\xee"
@@ -32836,267 +29296,14 @@ static const struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 			  "\x93\x6c\x01\xf7\xcc\x4e\x20\xd1"
 			  "\xb2\x1a\xd8\x4c\xbd\x1d\x10\xe9"
 			  "\x5a\xa8\x92\x7f\xba\xe6\x0c\x95",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
-static const struct cipher_testvec camellia_lrw_dec_tv_template[] = {
-	/* Generated from AES-LRW test vectors */
-	/* same as enc vectors with input and result reversed */
-	{
-		.key	= "\x45\x62\xac\x25\xf8\x28\x17\x6d"
-			  "\x4c\x26\x84\x14\xb5\x68\x01\x85"
-			  "\x25\x8e\x2a\x05\xe7\x3e\x9d\x03"
-			  "\xee\x5a\x83\x0c\xcc\x09\x4c\x87",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x92\x68\x19\xd7\xb7\x5b\x0a\x31"
-			  "\x97\xcc\x72\xbe\x99\x17\xeb\x3e",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x59\x70\x47\x14\xf5\x57\x47\x8c"
-			  "\xd7\x79\xe8\x0f\x54\x88\x79\x44"
-			  "\x0d\x48\xf0\xb7\xb1\x5a\x53\xea"
-			  "\x1c\xaa\x6b\x29\xc2\xca\xfb\xaf",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input	= "\x73\x09\xb7\x50\xb6\x77\x30\x50"
-			  "\x5c\x8a\x9c\x26\x77\x9d\xfc\x4a",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xd8\x2a\x91\x34\xb2\x6a\x56\x50"
-			  "\x30\xfe\x69\xe2\x37\x7f\x98\x47"
-			  "\xcd\xf9\x0b\x16\x0c\x64\x8f\xb6"
-			  "\xb0\x0d\x0d\x1b\xae\x85\x87\x1f",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x90\xae\x83\xe0\x22\xb9\x60\x91"
-			  "\xfa\xa9\xb7\x98\xe3\xed\x87\x01",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x0f\x6a\xef\xf8\xd3\xd2\xbb\x15"
-			  "\x25\x83\xf7\x3c\x1f\x01\x28\x74"
-			  "\xca\xc6\xbc\x35\x4d\x4a\x65\x54"
-			  "\x90\xae\x61\xcf\x7b\xae\xbd\xcc"
-			  "\xad\xe4\x94\xc5\x4a\x29\xae\x70",
-		.klen	= 40,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x99\xe9\x6e\xd4\xc9\x21\xa5\xf0"
-			  "\xd8\x83\xef\xd9\x07\x16\x5f\x35",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\x8a\xd4\xee\x10\x2f\xbd\x81\xff"
-			  "\xf8\x86\xce\xac\x93\xc5\xad\xc6"
-			  "\xa0\x19\x07\xc0\x9d\xf7\xbb\xdd"
-			  "\x52\x13\xb2\xb7\xf0\xff\x11\xd8"
-			  "\xd6\x08\xd0\xcd\x2e\xb1\x17\x6f",
-		.klen	= 40,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x42\x88\xf4\xcb\x21\x11\x6d\x8e"
-			  "\xde\x1a\xf2\x29\xf1\x4a\xe0\x15",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x40\xaa\x34\x86\x4a\x8f\x78\xb9"
-			  "\xdb\xdb\x0f\x3d\x48\x70\xbe\x8d",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xfb\x76\x15\xb2\x3d\x80\x89\x1d"
-			  "\xd4\x70\x98\x0b\xc7\x95\x84\xc8"
-			  "\xb2\xfb\x64\xce\x60\x97\x87\x8d"
-			  "\x17\xfc\xe4\x5a\x49\xe8\x30\xb7"
-			  "\x6e\x78\x17\xe7\x2d\x5e\x12\xd4"
-			  "\x60\x64\x04\x7a\xf1\x2f\x9e\x0c",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x02\x00\x00\x00\x00",
-		.input	= "\x04\xab\x28\x37\x31\x7a\x26\xab"
-			  "\xa1\x70\x1b\x9c\xe7\xdd\x83\xff",
-		.ilen	= 16,
-		.result	= "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x41\x42\x43\x44\x45\x46",
-		.rlen	= 16,
-	}, {
-		.key	= "\xf8\xd4\x76\xff\xd6\x46\xee\x6c"
-			  "\x23\x84\xcb\x1c\x77\xd6\x19\x5d"
-			  "\xfe\xf1\xa9\xf3\x7b\xbc\x8d\x21"
-			  "\xa7\x9c\x21\xf8\xcb\x90\x02\x89"
-			  "\xa8\x45\x34\x8e\xc8\xc5\xb5\xf1"
-			  "\x26\xf5\x0e\x76\xfe\xfd\x1b\x1e",
-		.klen	= 48,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x90\x69\x8e\xf2\x14\x86\x59\xf9"
-			  "\xec\xe7\xfa\x3f\x48\x9d\x7f\x96"
-			  "\x67\x76\xac\x2c\xd2\x63\x18\x93"
-			  "\x13\xf8\xf1\xf6\x71\x77\xb3\xee"
-			  "\x93\xb2\xcc\xf3\x26\xc1\x16\x4f"
-			  "\xd4\xe8\x43\xc1\x68\xa3\x3e\x06"
-			  "\x38\x51\xff\xa8\xb9\xa4\xeb\xb1"
-			  "\x62\xdd\x78\x81\xea\x1d\xef\x04"
-			  "\x1d\x07\xc1\x67\xc8\xd6\x77\xa1"
-			  "\x84\x95\xf4\x9a\xd9\xbc\x2d\xe2"
-			  "\xf6\x80\xfc\x91\x2a\xbc\x42\xa0"
-			  "\x40\x41\x69\xaa\x71\xc0\x37\xec"
-			  "\x39\xf3\xf2\xec\x82\xc3\x88\x79"
-			  "\xbc\xc3\xaa\xb7\xcf\x6a\x72\x80"
-			  "\x4c\xf4\x84\x8f\x13\x9e\x94\x5c"
-			  "\xe5\xb2\x91\xbb\x92\x51\x4d\xf1"
-			  "\xd6\x0d\x71\x6b\x7a\xc2\x2f\x12"
-			  "\x6f\x75\xc7\x80\x99\x50\x84\xcf"
-			  "\xa8\xeb\xd6\xe1\x1c\x59\x81\x7e"
-			  "\xb9\xb3\xde\x7a\x93\x14\x12\xa2"
-			  "\xf7\x43\xb3\x9d\x1a\x87\x65\x91"
-			  "\x42\x08\x40\x82\x06\x1c\x2d\x55"
-			  "\x6e\x48\xd5\x74\x07\x6e\x9d\x80"
-			  "\xeb\xb4\x97\xa1\x36\xdf\xfa\x74"
-			  "\x79\x7f\x5a\x75\xe7\x71\xc8\x8c"
-			  "\x7e\xf8\x3a\x77\xcd\x32\x05\xf9"
-			  "\x3d\xd4\xe9\xa2\xbb\xc4\x8b\x83"
-			  "\x42\x5c\x82\xfa\xe9\x4b\x96\x3b"
-			  "\x7f\x89\x8b\xf9\xf1\x87\xda\xf0"
-			  "\x87\xef\x13\x5d\xf0\xe2\xc5\xc1"
-			  "\xed\x14\xa9\x57\x19\x63\x40\x04"
-			  "\x24\xeb\x6e\x19\xd1\x3d\x70\x78"
-			  "\xeb\xda\x55\x70\x2c\x4f\x41\x5b"
-			  "\x56\x9f\x1a\xd3\xac\xf1\xc0\xc3"
-			  "\x21\xec\xd7\xd2\x55\x32\x7c\x2e"
-			  "\x3c\x48\x8e\xb4\x85\x35\x47\xfe"
-			  "\xe2\x88\x79\x98\x6a\xc9\x8d\xff"
-			  "\xe9\x89\x6e\xb8\xe2\x97\x00\xbd"
-			  "\xa4\x8f\xba\xd0\x8c\xcb\x79\x99"
-			  "\xb3\xb2\xb2\x7a\xc3\xb7\xef\x75"
-			  "\x23\x52\x76\xc3\x50\x6e\x66\xf8"
-			  "\xa2\xe2\xce\xba\x40\x21\x3f\xc9"
-			  "\x0a\x32\x7f\xf7\x08\x8c\x66\xcf"
-			  "\xd3\xdf\x57\x59\x83\xb8\xe1\x85"
-			  "\xd6\x8f\xfb\x48\x1f\x3a\xc4\x2f"
-			  "\xb4\x2d\x58\xab\xd8\x7f\x5e\x3a"
-			  "\xbc\x62\x3e\xe2\x6a\x52\x0d\x76"
-			  "\x2f\x1c\x1a\x30\xed\x95\x2a\x44"
-			  "\x35\xa5\x83\x04\x84\x01\x99\x56"
-			  "\xb7\xe3\x10\x96\xfa\xdc\x19\xdd"
-			  "\xe2\x7f\xcb\xa0\x49\x1b\xff\x4c"
-			  "\x73\xf6\xbb\x94\x00\xe8\xa9\x3d"
-			  "\xe2\x20\xe9\x3f\xfa\x07\x5d\x77"
-			  "\x06\xd5\x4f\x4d\x02\xb8\x40\x1b"
-			  "\x30\xed\x1a\x50\x19\xef\xc4\x2c"
-			  "\x02\xd9\xc5\xd3\x11\x33\x37\xe5"
-			  "\x2b\xa3\x95\xa6\xee\xd8\x74\x1d"
-			  "\x68\xa0\xeb\xbf\xdd\x5e\x99\x96"
-			  "\x91\xc3\x94\x24\xa5\x12\xa2\x37"
-			  "\xb3\xac\xcf\x2a\xfd\x55\x34\xfe"
-			  "\x79\x92\x3e\xe6\x1b\x49\x57\x5d"
-			  "\x93\x6c\x01\xf7\xcc\x4e\x20\xd1"
-			  "\xb2\x1a\xd8\x4c\xbd\x1d\x10\xe9"
-			  "\x5a\xa8\x92\x7f\xba\xe6\x0c\x95",
-		.ilen	= 512,
-		.result	= "\x05\x11\xb7\x18\xab\xc6\x2d\xac"
-			  "\x70\x5d\xf6\x22\x94\xcd\xe5\x6c"
-			  "\x17\x6b\xf6\x1c\xf0\xf3\x6e\xf8"
-			  "\x50\x38\x1f\x71\x49\xb6\x57\xd6"
-			  "\x8f\xcb\x8d\x6b\xe3\xa6\x29\x90"
-			  "\xfe\x2a\x62\x82\xae\x6d\x8b\xf6"
-			  "\xad\x1e\x9e\x20\x5f\x38\xbe\x04"
-			  "\xda\x10\x8e\xed\xa2\xa4\x87\xab"
-			  "\xda\x6b\xb4\x0c\x75\xba\xd3\x7c"
-			  "\xc9\xac\x42\x31\x95\x7c\xc9\x04"
-			  "\xeb\xd5\x6e\x32\x69\x8a\xdb\xa6"
-			  "\x15\xd7\x3f\x4f\x2f\x66\x69\x03"
-			  "\x9c\x1f\x54\x0f\xde\x1f\xf3\x65"
-			  "\x4c\x96\x12\xed\x7c\x92\x03\x01"
-			  "\x6f\xbc\x35\x93\xac\xf1\x27\xf1"
-			  "\xb4\x96\x82\x5a\x5f\xb0\xa0\x50"
-			  "\x89\xa4\x8e\x66\x44\x85\xcc\xfd"
-			  "\x33\x14\x70\xe3\x96\xb2\xc3\xd3"
-			  "\xbb\x54\x5a\x1a\xf9\x74\xa2\xc5"
-			  "\x2d\x64\x75\xdd\xb4\x54\xe6\x74"
-			  "\x8c\xd3\x9d\x9e\x86\xab\x51\x53"
-			  "\xb7\x93\x3e\x6f\xd0\x4e\x2c\x40"
-			  "\xf6\xa8\x2e\x3e\x9d\xf4\x66\xa5"
-			  "\x76\x12\x73\x44\x1a\x56\xd7\x72"
-			  "\x88\xcd\x21\x8c\x4c\x0f\xfe\xda"
-			  "\x95\xe0\x3a\xa6\xa5\x84\x46\xcd"
-			  "\xd5\x3e\x9d\x3a\xe2\x67\xe6\x60"
-			  "\x1a\xe2\x70\x85\x58\xc2\x1b\x09"
-			  "\xe1\xd7\x2c\xca\xad\xa8\x8f\xf9"
-			  "\xac\xb3\x0e\xdb\xca\x2e\xe2\xb8"
-			  "\x51\x71\xd9\x3c\x6c\xf1\x56\xf8"
-			  "\xea\x9c\xf1\xfb\x0c\xe6\xb7\x10"
-			  "\x1c\xf8\xa9\x7c\xe8\x53\x35\xc1"
-			  "\x90\x3e\x76\x4a\x74\xa4\x21\x2c"
-			  "\xf6\x2c\x4e\x0f\x94\x3a\x88\x2e"
-			  "\x41\x09\x6a\x33\x7d\xf6\xdd\x3f"
-			  "\x8d\x23\x31\x74\x84\xeb\x88\x6e"
-			  "\xcc\xb9\xbc\x22\x83\x19\x07\x22"
-			  "\xa5\x2d\xdf\xa5\xf3\x80\x85\x78"
-			  "\x84\x39\x6a\x6d\x6a\x99\x4f\xa5"
-			  "\x15\xfe\x46\xb0\xe4\x6c\xa5\x41"
-			  "\x3c\xce\x8f\x42\x60\x71\xa7\x75"
-			  "\x08\x40\x65\x8a\x82\xbf\xf5\x43"
-			  "\x71\x96\xa9\x4d\x44\x8a\x20\xbe"
-			  "\xfa\x4d\xbb\xc0\x7d\x31\x96\x65"
-			  "\xe7\x75\xe5\x3e\xfd\x92\x3b\xc9"
-			  "\x55\xbb\x16\x7e\xf7\xc2\x8c\xa4"
-			  "\x40\x1d\xe5\xef\x0e\xdf\xe4\x9a"
-			  "\x62\x73\x65\xfd\x46\x63\x25\x3d"
-			  "\x2b\xaf\xe5\x64\xfe\xa5\x5c\xcf"
-			  "\x24\xf3\xb4\xac\x64\xba\xdf\x4b"
-			  "\xc6\x96\x7d\x81\x2d\x8d\x97\xf7"
-			  "\xc5\x68\x77\x84\x32\x2b\xcc\x85"
-			  "\x74\x96\xf0\x12\x77\x61\xb9\xeb"
-			  "\x71\xaa\x82\xcb\x1c\xdb\x89\xc8"
-			  "\xc6\xb5\xe3\x5c\x7d\x39\x07\x24"
-			  "\xda\x39\x87\x45\xc0\x2b\xbb\x01"
-			  "\xac\xbc\x2a\x5c\x7f\xfc\xe8\xce"
-			  "\x6d\x9c\x6f\xed\xd3\xc1\xa1\xd6"
-			  "\xc5\x55\xa9\x66\x2f\xe1\xc8\x32"
-			  "\xa6\x5d\xa4\x3a\x98\x73\xe8\x45"
-			  "\xa4\xc7\xa8\xb4\xf6\x13\x03\xf6"
-			  "\xe9\x2e\xc4\x29\x0f\x84\xdb\xc4"
-			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
+static const struct cipher_testvec camellia_xts_tv_template[] = {
 	/* Generated from AES-XTS test vectors */
 	{
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -33106,16 +29313,15 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 32,
-		.result	= "\x06\xcb\xa5\xf1\x04\x63\xb2\x41"
+		.ctext	= "\x06\xcb\xa5\xf1\x04\x63\xb2\x41"
 			  "\xdc\xca\xfa\x09\xba\x74\xb9\x05"
 			  "\x78\xba\xa4\xf8\x67\x4d\x7e\xad"
 			  "\x20\x18\xf5\x0c\x41\x16\x2a\x61",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
 			  "\x11\x11\x11\x11\x11\x11\x11\x11"
@@ -33124,16 +29330,15 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\xc2\xb9\xdc\x44\x1d\xdf\xf2\x86"
+		.ctext	= "\xc2\xb9\xdc\x44\x1d\xdf\xf2\x86"
 			  "\x8d\x35\x42\x0a\xa5\x5e\x3d\x4f"
 			  "\xb5\x37\x06\xff\xbd\xd4\x91\x70"
 			  "\x80\x1f\xb2\x39\x10\x89\x44\xf5",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
 			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
@@ -33142,16 +29347,15 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+		.ptext	= "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44"
 			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.ilen	= 32,
-		.result	= "\x52\x1f\x9d\xf5\x5a\x58\x5a\x7e"
+		.ctext	= "\x52\x1f\x9d\xf5\x5a\x58\x5a\x7e"
 			  "\x9f\xd0\x8e\x02\x9c\x9a\x6a\xa7"
 			  "\xb4\x3b\xce\xe7\x17\xaa\x89\x6a"
 			  "\x35\x3c\x6b\xb5\x61\x1c\x79\x38",
-		.rlen	= 32,
+		.len	= 32,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -33160,7 +29364,7 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 		.klen	= 32,
 		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -33224,8 +29428,7 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\xc7\xf9\x0a\xaa\xcb\xb5\x8f\x33"
+		.ctext	= "\xc7\xf9\x0a\xaa\xcb\xb5\x8f\x33"
 			  "\x60\xc3\xe9\x47\x90\xb7\x50\x57"
 			  "\xa3\xad\x81\x2f\xf5\x22\x96\x02"
 			  "\xaa\x7f\xea\xac\x29\x78\xca\x2a"
@@ -33289,7 +29492,7 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 			  "\xcc\x06\xdb\xe7\x82\x29\x63\xd1"
 			  "\x52\x84\x4f\xee\x27\xe8\x02\xd4"
 			  "\x34\x3c\x69\xc2\xbd\x20\xe6\x7a",
-		.rlen	= 512,
+		.len	= 512,
 	}, {
 		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
 			  "\x23\x53\x60\x28\x74\x71\x35\x26"
@@ -33302,7 +29505,7 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 		.klen	= 64,
 		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			  "\x10\x11\x12\x13\x14\x15\x16\x17"
 			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
@@ -33366,8 +29569,7 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
 			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.ilen	= 512,
-		.result	= "\x49\xcd\xb8\xbf\x2f\x73\x37\x28"
+		.ctext	= "\x49\xcd\xb8\xbf\x2f\x73\x37\x28"
 			  "\x9a\x7f\x6e\x57\x55\xb8\x07\x88"
 			  "\x4a\x0d\x8b\x55\x60\xed\xb6\x7b"
 			  "\xf1\x74\xac\x96\x05\x7b\x32\xca"
@@ -33431,350 +29633,7 @@ static const struct cipher_testvec camellia_xts_enc_tv_template[] = {
 			  "\xb1\x02\x0a\x5c\x79\x19\x3b\x75"
 			  "\xb7\x16\xd8\x12\x5c\xcd\x7d\x4e"
 			  "\xd5\xc6\x99\xcc\x4e\x6c\x94\x95",
-		.rlen	= 512,
-		.also_non_np = 1,
-		.np	= 3,
-		.tap	= { 512 - 20, 4, 16 },
-	},
-};
-
-static const struct cipher_testvec camellia_xts_dec_tv_template[] = {
-	/* Generated from AES-XTS test vectors */
-	/* same as enc vectors with input and result reversed */
-	{
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x06\xcb\xa5\xf1\x04\x63\xb2\x41"
-			  "\xdc\xca\xfa\x09\xba\x74\xb9\x05"
-			  "\x78\xba\xa4\xf8\x67\x4d\x7e\xad"
-			  "\x20\x18\xf5\x0c\x41\x16\x2a\x61",
-		.ilen	= 32,
-		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.rlen	= 32,
-	}, {
-		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x11\x11\x11\x11\x11\x11\x11\x11"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 32,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xc2\xb9\xdc\x44\x1d\xdf\xf2\x86"
-			  "\x8d\x35\x42\x0a\xa5\x5e\x3d\x4f"
-			  "\xb5\x37\x06\xff\xbd\xd4\x91\x70"
-			  "\x80\x1f\xb2\x39\x10\x89\x44\xf5",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
-			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22"
-			  "\x22\x22\x22\x22\x22\x22\x22\x22",
-		.klen	= 32,
-		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x52\x1f\x9d\xf5\x5a\x58\x5a\x7e"
-			  "\x9f\xd0\x8e\x02\x9c\x9a\x6a\xa7"
-			  "\xb4\x3b\xce\xe7\x17\xaa\x89\x6a"
-			  "\x35\x3c\x6b\xb5\x61\x1c\x79\x38",
-		.ilen	= 32,
-		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44"
-			  "\x44\x44\x44\x44\x44\x44\x44\x44",
-		.rlen	= 32,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95",
-		.klen	= 32,
-		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\xc7\xf9\x0a\xaa\xcb\xb5\x8f\x33"
-			  "\x60\xc3\xe9\x47\x90\xb7\x50\x57"
-			  "\xa3\xad\x81\x2f\xf5\x22\x96\x02"
-			  "\xaa\x7f\xea\xac\x29\x78\xca\x2a"
-			  "\x7c\xcd\x31\x1a\x3c\x40\x0a\x73"
-			  "\x09\x66\xad\x72\x0e\x4d\x5d\x77"
-			  "\xbc\xb8\x76\x80\x37\x59\xa9\x01"
-			  "\x9e\xfb\xdb\x6c\x93\xef\xb6\x8d"
-			  "\x1e\xc1\x94\xa8\xd4\xb5\xb0\x01"
-			  "\xd5\x01\x97\x28\xcd\x7a\x1f\xe8"
-			  "\x08\xda\x76\x00\x65\xcf\x7b\x31"
-			  "\xc6\xfa\xf2\x3b\x00\xa7\x6a\x9e"
-			  "\x6c\x43\x80\x87\xe0\xbb\x4e\xe5"
-			  "\xdc\x8a\xdf\xc3\x1d\x1b\x41\x04"
-			  "\xfb\x54\xdd\x29\x27\xc2\x65\x17"
-			  "\x36\x88\xb0\x85\x8d\x73\x7e\x4b"
-			  "\x1d\x16\x8a\x52\xbc\xa6\xbc\xa4"
-			  "\x8c\xd1\x04\x16\xbf\x8c\x01\x0f"
-			  "\x7e\x6b\x59\x15\x29\xd1\x9b\xd3"
-			  "\x6c\xee\xac\xdc\x45\x58\xca\x5b"
-			  "\x70\x0e\x6a\x12\x86\x82\x79\x9f"
-			  "\x16\xd4\x9d\x67\xcd\x70\x65\x26"
-			  "\x21\x72\x1e\xa1\x94\x8a\x83\x0c"
-			  "\x92\x42\x58\x5e\xa2\xc5\x31\xf3"
-			  "\x7b\xd1\x31\xd4\x15\x80\x31\x61"
-			  "\x5c\x53\x10\xdd\xea\xc8\x83\x5c"
-			  "\x7d\xa7\x05\x66\xcc\x1e\xbb\x05"
-			  "\x47\xae\xb4\x0f\x84\xd8\xf6\xb5"
-			  "\xa1\xc6\x52\x00\x52\xe8\xdc\xd9"
-			  "\x16\x31\xb2\x47\x91\x67\xaa\x28"
-			  "\x2c\x29\x85\xa3\xf7\xf2\x24\x93"
-			  "\x23\x80\x1f\xa8\x1b\x82\x8d\xdc"
-			  "\x9f\x0b\xcd\xb4\x3c\x20\xbc\xec"
-			  "\x4f\xc7\xee\xf8\xfd\xd9\xfb\x7e"
-			  "\x3f\x0d\x23\xfa\x3f\xa7\xcc\x66"
-			  "\x1c\xfe\xa6\x86\xf6\xf7\x85\xc7"
-			  "\x43\xc1\xd4\xfc\xe4\x79\xc9\x1d"
-			  "\xf8\x89\xcd\x20\x27\x84\x5d\x5c"
-			  "\x8e\x4f\x1f\xeb\x08\x21\x4f\xa3"
-			  "\xe0\x7e\x0b\x9c\xe7\x42\xcf\xb7"
-			  "\x3f\x43\xcc\x86\x71\x34\x6a\xd9"
-			  "\x5e\xec\x8f\x36\xc9\x0a\x03\xfe"
-			  "\x18\x41\xdc\x9e\x2e\x75\x20\x3e"
-			  "\xcc\x77\xe0\x8f\xe8\x43\x37\x4c"
-			  "\xed\x1a\x5a\xb3\xfa\x43\xc9\x71"
-			  "\x9f\xc5\xce\xcf\xff\xe7\x77\x1e"
-			  "\x35\x93\xde\x6b\xc0\x6a\x7e\xa9"
-			  "\x34\xb8\x27\x74\x08\xda\xf2\x4a"
-			  "\x23\x5b\x9f\x55\x3a\x57\x82\x52"
-			  "\xea\x6d\xc3\xc7\xf2\xc8\xb5\xdc"
-			  "\xc5\xb9\xbb\xaa\xf2\x29\x9f\x49"
-			  "\x7a\xef\xfe\xdc\x9f\xc9\x28\xe2"
-			  "\x96\x0b\x35\x84\x05\x0d\xd6\x2a"
-			  "\xea\x5a\xbf\x69\xde\xee\x4f\x8f"
-			  "\x84\xb9\xcf\xa7\x57\xea\xe0\xe8"
-			  "\x96\xef\x0f\x0e\xec\xc7\xa6\x74"
-			  "\xb1\xfe\x7a\x6d\x11\xdd\x0e\x15"
-			  "\x4a\x1e\x73\x7f\x55\xea\xf6\xe1"
-			  "\x5b\xb6\x71\xda\xb0\x0c\xba\x26"
-			  "\x5c\x48\x38\x6d\x1c\x32\xb2\x7d"
-			  "\x05\x87\xc2\x1e\x7e\x2d\xd4\x33"
-			  "\xcc\x06\xdb\xe7\x82\x29\x63\xd1"
-			  "\x52\x84\x4f\xee\x27\xe8\x02\xd4"
-			  "\x34\x3c\x69\xc2\xbd\x20\xe6\x7a",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
-	}, {
-		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
-			  "\x23\x53\x60\x28\x74\x71\x35\x26"
-			  "\x62\x49\x77\x57\x24\x70\x93\x69"
-			  "\x99\x59\x57\x49\x66\x96\x76\x27"
-			  "\x31\x41\x59\x26\x53\x58\x97\x93"
-			  "\x23\x84\x62\x64\x33\x83\x27\x95"
-			  "\x02\x88\x41\x97\x16\x93\x99\x37"
-			  "\x51\x05\x82\x09\x74\x94\x45\x92",
-		.klen	= 64,
-		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x49\xcd\xb8\xbf\x2f\x73\x37\x28"
-			  "\x9a\x7f\x6e\x57\x55\xb8\x07\x88"
-			  "\x4a\x0d\x8b\x55\x60\xed\xb6\x7b"
-			  "\xf1\x74\xac\x96\x05\x7b\x32\xca"
-			  "\xd1\x4e\xf1\x58\x29\x16\x24\x6c"
-			  "\xf2\xb3\xe4\x88\x84\xac\x4d\xee"
-			  "\x97\x07\x82\xf0\x07\x12\x38\x0a"
-			  "\x67\x62\xaf\xfd\x85\x9f\x0a\x55"
-			  "\xa5\x20\xc5\x60\xe4\x68\x53\xa4"
-			  "\x0e\x2e\x65\xe3\xe4\x0c\x30\x7c"
-			  "\x1c\x01\x4f\x55\xa9\x13\xeb\x25"
-			  "\x21\x87\xbc\xd3\xe7\x67\x4f\x38"
-			  "\xa8\x14\x25\x71\xe9\x2e\x4c\x21"
-			  "\x41\x82\x0c\x45\x39\x35\xa8\x75"
-			  "\x03\x29\x01\x84\x8c\xab\x48\xbe"
-			  "\x11\x56\x22\x67\xb7\x67\x1a\x09"
-			  "\xa1\x72\x25\x41\x3c\x39\x65\x80"
-			  "\x7d\x2f\xf8\x2c\x73\x04\x58\x9d"
-			  "\xdd\x16\x8b\x63\x70\x4e\xc5\x17"
-			  "\x21\xe0\x84\x51\x4b\x6f\x05\x52"
-			  "\xe3\x63\x34\xfa\xa4\xaf\x33\x20"
-			  "\xc1\xae\x32\xc4\xb8\x2b\xdb\x76"
-			  "\xd9\x02\x31\x2f\xa3\xc6\xd0\x7b"
-			  "\xaf\x1b\x84\xe3\x9b\xbf\xa6\xe0"
-			  "\xb8\x8a\x13\x88\x71\xf4\x11\xa5"
-			  "\xe9\xa9\x10\x33\xe0\xbe\x49\x89"
-			  "\x41\x22\xf5\x9d\x80\x3e\x3b\x76"
-			  "\x01\x16\x50\x6e\x7c\x6a\x81\xe9"
-			  "\x13\x2c\xde\xb2\x5f\x79\xba\xb2"
-			  "\xb1\x75\xae\xd2\x07\x98\x4b\x69"
-			  "\xae\x7d\x5b\x90\xc2\x6c\xe6\x98"
-			  "\xd3\x4c\xa1\xa3\x9c\xc9\x33\x6a"
-			  "\x0d\x23\xb1\x79\x25\x13\x4b\xe5"
-			  "\xaf\x93\x20\x5c\x7f\x06\x7a\x34"
-			  "\x0b\x78\xe3\x67\x26\xe0\xad\x95"
-			  "\xc5\x4e\x26\x22\xcf\x73\x77\x62"
-			  "\x3e\x10\xd7\x90\x4b\x52\x1c\xc9"
-			  "\xef\x38\x52\x18\x0e\x29\x7e\xef"
-			  "\x34\xfe\x31\x95\xc5\xbc\xa8\xe2"
-			  "\xa8\x4e\x9f\xea\xa6\xf0\xfe\x5d"
-			  "\xc5\x39\x86\xed\x2f\x6d\xa0\xfe"
-			  "\x96\xcd\x41\x10\x78\x4e\x0c\xc9"
-			  "\xc3\x6d\x0f\xb7\xe8\xe0\x62\xab"
-			  "\x8b\xf1\x21\x89\xa1\x12\xaa\xfa"
-			  "\x9d\x70\xbe\x4c\xa8\x98\x89\x01"
-			  "\xb9\xe2\x61\xde\x0c\x4a\x0b\xaa"
-			  "\x89\xf5\x14\x79\x18\x8f\x3b\x0d"
-			  "\x21\x17\xf8\x59\x15\x24\x64\x22"
-			  "\x57\x48\x80\xd5\x3d\x92\x30\x07"
-			  "\xd9\xa1\x4a\x23\x16\x43\x48\x0e"
-			  "\x2b\x2d\x1b\x87\xef\x7e\xbd\xfa"
-			  "\x49\xbc\x7e\x68\x6e\xa8\x46\x95"
-			  "\xad\x5e\xfe\x0a\xa8\xd3\x1a\x5d"
-			  "\x6b\x84\xf3\x00\xba\x52\x05\x02"
-			  "\xe3\x96\x4e\xb6\x79\x3f\x43\xd3"
-			  "\x4d\x3f\xd6\xab\x0a\xc4\x75\x2d"
-			  "\xd1\x08\xc3\x6a\xc8\x37\x29\xa0"
-			  "\xcc\x9a\x05\xdd\x5c\xe1\xff\x66"
-			  "\xf2\x7a\x1d\xf2\xaf\xa9\x48\x89"
-			  "\xf5\x21\x0f\x02\x48\x83\x74\xbf"
-			  "\x2e\xe6\x93\x7b\xa0\xf4\xb1\x2b"
-			  "\xb1\x02\x0a\x5c\x79\x19\x3b\x75"
-			  "\xb7\x16\xd8\x12\x5c\xcd\x7d\x4e"
-			  "\xd5\xc6\x99\xcc\x4e\x6c\x94\x95",
-		.ilen	= 512,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
-			  "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
-			  "\x10\x11\x12\x13\x14\x15\x16\x17"
-			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
-			  "\x20\x21\x22\x23\x24\x25\x26\x27"
-			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
-			  "\x30\x31\x32\x33\x34\x35\x36\x37"
-			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
-			  "\x40\x41\x42\x43\x44\x45\x46\x47"
-			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
-			  "\x50\x51\x52\x53\x54\x55\x56\x57"
-			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
-			  "\x60\x61\x62\x63\x64\x65\x66\x67"
-			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
-			  "\x70\x71\x72\x73\x74\x75\x76\x77"
-			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
-			  "\x80\x81\x82\x83\x84\x85\x86\x87"
-			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
-			  "\x90\x91\x92\x93\x94\x95\x96\x97"
-			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
-			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
-			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
-			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
-			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
-			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
-			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
-			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
-			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
-			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
-			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
-			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
-			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
-		.rlen	= 512,
+		.len	= 512,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 512 - 20, 4, 16 },
@@ -33784,91 +29643,45 @@ static const struct cipher_testvec camellia_xts_dec_tv_template[] = {
 /*
  * SEED test vectors
  */
-static const struct cipher_testvec seed_enc_tv_template[] = {
+static const struct cipher_testvec seed_tv_template[] = {
 	{
 		.key    = zeroed_string,
 		.klen	= 16,
-		.input  = "\x00\x01\x02\x03\x04\x05\x06\x07"
+		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ilen	= 16,
-		.result	= "\x5e\xba\xc6\xe0\x05\x4e\x16\x68"
+		.ctext	= "\x5e\xba\xc6\xe0\x05\x4e\x16\x68"
 			  "\x19\xaf\xf1\xcc\x6d\x34\x6c\xdb",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
 			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
 		.klen	= 16,
-		.input	= zeroed_string,
-		.ilen	= 16,
-		.result	= "\xc1\x1f\x22\xf2\x01\x40\x50\x50"
+		.ptext	= zeroed_string,
+		.ctext	= "\xc1\x1f\x22\xf2\x01\x40\x50\x50"
 			  "\x84\x48\x35\x97\xe4\x37\x0f\x43",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x47\x06\x48\x08\x51\xe6\x1b\xe8"
 			  "\x5d\x74\xbf\xb3\xfd\x95\x61\x85",
 		.klen	= 16,
-		.input	= "\x83\xa2\xf8\xa2\x88\x64\x1f\xb9"
+		.ptext	= "\x83\xa2\xf8\xa2\x88\x64\x1f\xb9"
 			  "\xa4\xe9\xa5\xcc\x2f\x13\x1c\x7d",
-		.ilen	= 16,
-		.result	= "\xee\x54\xd1\x3e\xbc\xae\x70\x6d"
+		.ctext	= "\xee\x54\xd1\x3e\xbc\xae\x70\x6d"
 			  "\x22\x6b\xc3\x14\x2c\xd4\x0d\x4a",
-		.rlen	= 16,
+		.len	= 16,
 	}, {
 		.key	= "\x28\xdb\xc3\xbc\x49\xff\xd8\x7d"
 			  "\xcf\xa5\x09\xb1\x1d\x42\x2b\xe7",
 		.klen	= 16,
-		.input	= "\xb4\x1e\x6b\xe2\xeb\xa8\x4a\x14"
+		.ptext	= "\xb4\x1e\x6b\xe2\xeb\xa8\x4a\x14"
 			  "\x8e\x2e\xed\x84\x59\x3c\x5e\xc7",
-		.ilen	= 16,
-		.result	= "\x9b\x9b\x7b\xfc\xd1\x81\x3c\xb9"
-			  "\x5d\x0b\x36\x18\xf4\x0f\x51\x22",
-		.rlen	= 16,
-	}
-};
-
-static const struct cipher_testvec seed_dec_tv_template[] = {
-	{
-		.key    = zeroed_string,
-		.klen	= 16,
-		.input	= "\x5e\xba\xc6\xe0\x05\x4e\x16\x68"
-			  "\x19\xaf\xf1\xcc\x6d\x34\x6c\xdb",
-		.ilen	= 16,
-		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.rlen	= 16,
-	}, {
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.klen	= 16,
-		.input	= "\xc1\x1f\x22\xf2\x01\x40\x50\x50"
-			  "\x84\x48\x35\x97\xe4\x37\x0f\x43",
-		.ilen	= 16,
-		.result	= zeroed_string,
-		.rlen	= 16,
-	}, {
-		.key	= "\x47\x06\x48\x08\x51\xe6\x1b\xe8"
-			  "\x5d\x74\xbf\xb3\xfd\x95\x61\x85",
-		.klen	= 16,
-		.input	= "\xee\x54\xd1\x3e\xbc\xae\x70\x6d"
-			  "\x22\x6b\xc3\x14\x2c\xd4\x0d\x4a",
-		.ilen	= 16,
-		.result	= "\x83\xa2\xf8\xa2\x88\x64\x1f\xb9"
-			  "\xa4\xe9\xa5\xcc\x2f\x13\x1c\x7d",
-		.rlen	= 16,
-	}, {
-		.key	= "\x28\xdb\xc3\xbc\x49\xff\xd8\x7d"
-			  "\xcf\xa5\x09\xb1\x1d\x42\x2b\xe7",
-		.klen	= 16,
-		.input	= "\x9b\x9b\x7b\xfc\xd1\x81\x3c\xb9"
+		.ctext	= "\x9b\x9b\x7b\xfc\xd1\x81\x3c\xb9"
 			  "\x5d\x0b\x36\x18\xf4\x0f\x51\x22",
-		.ilen	= 16,
-		.result	= "\xb4\x1e\x6b\xe2\xeb\xa8\x4a\x14"
-			  "\x8e\x2e\xed\x84\x59\x3c\x5e\xc7",
-		.rlen	= 16,
+		.len	= 16,
 	}
 };
 
-static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
+static const struct cipher_testvec salsa20_stream_tv_template[] = {
 	/*
 	* Testvectors from verified.test-vectors submitted to ECRYPT.
 	* They are truncated to size 39, 64, 111, 129 to test a variety
@@ -33879,24 +29692,23 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			"\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F",
 		.klen	= 16,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 39,
-		.result	= "\x2D\xD5\xC3\xF7\xBA\x2B\x20\xF7"
+		.ctext	= "\x2D\xD5\xC3\xF7\xBA\x2B\x20\xF7"
 			 "\x68\x02\x41\x0C\x68\x86\x88\x89"
 			 "\x5A\xD8\xC1\xBD\x4E\xA6\xC9\xB1"
 			 "\x40\xFB\x9B\x90\xE2\x10\x49\xBF"
 			 "\x58\x3F\x52\x79\x70\xEB\xC1",
-		.rlen	= 39,
+		.len	= 39,
 	}, { /* Set 5, vector 0 */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 16,
 		.iv     = "\x80\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -33904,8 +29716,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 64,
-		.result	= "\xB6\x6C\x1E\x44\x46\xDD\x95\x57"
+		.ctext	= "\xB6\x6C\x1E\x44\x46\xDD\x95\x57"
 			 "\xE5\x78\xE2\x23\xB0\xB7\x68\x01"
 			 "\x7B\x23\xB2\x67\xBB\x02\x34\xAE"
 			 "\x46\x26\xBF\x44\x3F\x21\x97\x76"
@@ -33913,7 +29724,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			 "\xCD\x0D\xE9\xA9\x53\x8F\x4A\x09"
 			 "\xCA\x9A\xC0\x73\x2E\x30\xBC\xF9"
 			 "\x8E\x4F\x13\xE4\xB9\xE2\x01\xD9",
-		.rlen	= 64,
+		.len	= 64,
 	}, { /* Set 3, vector 27 */
 		.key	= "\x1B\x1C\x1D\x1E\x1F\x20\x21\x22"
 			"\x23\x24\x25\x26\x27\x28\x29\x2A"
@@ -33921,7 +29732,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			"\x33\x34\x35\x36\x37\x38\x39\x3A",
 		.klen	= 32,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -33935,8 +29746,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 111,
-		.result	= "\xAE\x39\x50\x8E\xAC\x9A\xEC\xE7"
+		.ctext	= "\xAE\x39\x50\x8E\xAC\x9A\xEC\xE7"
 			 "\xBF\x97\xBB\x20\xB9\xDE\xE4\x1F"
 			 "\x87\xD9\x47\xF8\x28\x91\x35\x98"
 			 "\xDB\x72\xCC\x23\x29\x48\x56\x5E"
@@ -33950,7 +29760,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			 "\xB1\x41\x3F\x19\x2F\xC4\x3B\xC6"
 			 "\x95\x46\x45\x54\xE9\x75\x03\x08"
 			 "\x44\xAF\xE5\x8A\x81\x12\x09",
-		.rlen	= 111,
+		.len	= 111,
 	}, { /* Set 5, vector 27 */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -33958,7 +29768,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			"\x00\x00\x00\x00\x00\x00\x00\x00",
 		.klen	= 32,
 		.iv     = "\x00\x00\x00\x10\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -33975,8 +29785,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00",
-		.ilen	= 129,
-		.result	= "\xD2\xDB\x1A\x5C\xF1\xC1\xAC\xDB"
+		.ctext	= "\xD2\xDB\x1A\x5C\xF1\xC1\xAC\xDB"
 			 "\xE8\x1A\x7A\x43\x40\xEF\x53\x43"
 			 "\x5E\x7F\x4B\x1A\x50\x52\x3F\x8D"
 			 "\x28\x3D\xCF\x85\x1D\x69\x6E\x60"
@@ -33993,7 +29802,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			 "\x2E\x40\x48\x75\xE9\xE2\x21\x45"
 			 "\x0B\xC9\xB6\xB5\x66\xBC\x9A\x59"
 			 "\x5A",
-		.rlen	= 129,
+		.len	= 129,
 	}, { /* large test vector generated using Crypto++ */
 		.key =  "\x00\x01\x02\x03\x04\x05\x06\x07"
 			"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
@@ -34002,7 +29811,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 		.klen = 32,
 		.iv =	"\x00\x00\x00\x00\x00\x00\x00\x00"
 			"\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input =
+		.ptext =
 			"\x00\x01\x02\x03\x04\x05\x06\x07"
 			"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
 			"\x10\x11\x12\x13\x14\x15\x16\x17"
@@ -34516,8 +30325,7 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			"\x10\x2f\x4e\x6d\x8c\xab\xca\xe9"
 			"\x08\x27\x46\x65\x84\xa3\xc2\xe1"
 			"\x00\x21\x42\x63",
-		.ilen = 4100,
-		.result =
+		.ctext =
 			"\xb5\x81\xf5\x64\x18\x73\xe3\xf0"
 			"\x4c\x13\xf2\x77\x18\x60\x65\x5e"
 			"\x29\x01\xce\x98\x55\x53\xf9\x0c"
@@ -35031,13 +30839,13 @@ static const struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 			"\xfc\x3f\x09\x7a\x0b\xdc\xc5\x1b"
 			"\x87\x13\xc6\x5b\x59\x8d\xf2\xc8"
 			"\xaf\xdf\x11\x95",
-		.rlen	= 4100,
+		.len	= 4100,
 		.np	= 2,
 		.tap	= { 4064, 36 },
 	},
 };
 
-static const struct cipher_testvec chacha20_enc_tv_template[] = {
+static const struct cipher_testvec chacha20_tv_template[] = {
 	{ /* RFC7539 A.2. Test Vector #1 */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -35046,7 +30854,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 		.klen	= 32,
 		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -35054,8 +30862,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ilen	= 64,
-		.result	= "\x76\xb8\xe0\xad\xa0\xf1\x3d\x90"
+		.ctext	= "\x76\xb8\xe0\xad\xa0\xf1\x3d\x90"
 			  "\x40\x5d\x6a\xe5\x53\x86\xbd\x28"
 			  "\xbd\xd2\x19\xb8\xa0\x8d\xed\x1a"
 			  "\xa8\x36\xef\xcc\x8b\x77\x0d\xc7"
@@ -35063,7 +30870,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x77\x24\xe0\x3f\xb8\xd8\x4a\x37"
 			  "\x6a\x43\xb8\xf4\x15\x18\xa1\x1c"
 			  "\xc3\x87\xb6\x69\xb2\xee\x65\x86",
-		.rlen	= 64,
+		.len	= 64,
 	}, { /* RFC7539 A.2. Test Vector #2 */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x00"
@@ -35072,7 +30879,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 		.klen	= 32,
 		.iv     = "\x01\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input	= "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+		.ptext	= "\x41\x6e\x79\x20\x73\x75\x62\x6d"
 			  "\x69\x73\x73\x69\x6f\x6e\x20\x74"
 			  "\x6f\x20\x74\x68\x65\x20\x49\x45"
 			  "\x54\x46\x20\x69\x6e\x74\x65\x6e"
@@ -35119,8 +30926,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x20\x77\x68\x69\x63\x68\x20\x61"
 			  "\x72\x65\x20\x61\x64\x64\x72\x65"
 			  "\x73\x73\x65\x64\x20\x74\x6f",
-		.ilen	= 375,
-		.result	= "\xa3\xfb\xf0\x7d\xf3\xfa\x2f\xde"
+		.ctext	= "\xa3\xfb\xf0\x7d\xf3\xfa\x2f\xde"
 			  "\x4f\x37\x6c\xa2\x3e\x82\x73\x70"
 			  "\x41\x60\x5d\x9f\x4f\x4f\x57\xbd"
 			  "\x8c\xff\x2c\x1d\x4b\x79\x55\xec"
@@ -35167,7 +30973,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x7a\xc6\x1d\xd2\x9c\x6f\x21\xba"
 			  "\x5b\x86\x2f\x37\x30\xe3\x7c\xfd"
 			  "\xc4\xfd\x80\x6c\x22\xf2\x21",
-		.rlen	= 375,
+		.len	= 375,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 375 - 20, 4, 16 },
@@ -35180,7 +30986,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 		.klen	= 32,
 		.iv     = "\x2a\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x02",
-		.input	= "\x27\x54\x77\x61\x73\x20\x62\x72"
+		.ptext	= "\x27\x54\x77\x61\x73\x20\x62\x72"
 			  "\x69\x6c\x6c\x69\x67\x2c\x20\x61"
 			  "\x6e\x64\x20\x74\x68\x65\x20\x73"
 			  "\x6c\x69\x74\x68\x79\x20\x74\x6f"
@@ -35196,8 +31002,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x68\x65\x20\x6d\x6f\x6d\x65\x20"
 			  "\x72\x61\x74\x68\x73\x20\x6f\x75"
 			  "\x74\x67\x72\x61\x62\x65\x2e",
-		.ilen	= 127,
-		.result	= "\x62\xe6\x34\x7f\x95\xed\x87\xa4"
+		.ctext	= "\x62\xe6\x34\x7f\x95\xed\x87\xa4"
 			  "\x5f\xfa\xe7\x42\x6f\x27\xa1\xdf"
 			  "\x5f\xb6\x91\x10\x04\x4c\x0d\x73"
 			  "\x11\x8e\xff\xa9\x5b\x01\xe5\xcf"
@@ -35213,7 +31018,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x50\xd6\x15\x4b\x6d\xa7\x31\xb1"
 			  "\x87\xb5\x8d\xfd\x72\x8a\xfa\x36"
 			  "\x75\x7a\x79\x7a\xc1\x88\xd1",
-		.rlen	= 127,
+		.len	= 127,
 	}, { /* Self-made test vector for long data */
 		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
 			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
@@ -35222,7 +31027,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 		.klen	= 32,
 		.iv     = "\x1c\x00\x00\x00\x00\x00\x00\x00"
 			  "\x00\x00\x00\x00\x00\x00\x00\x01",
-		.input	= "\x49\xee\xe0\xdc\x24\x90\x40\xcd"
+		.ptext	= "\x49\xee\xe0\xdc\x24\x90\x40\xcd"
 			  "\xc5\x40\x8f\x47\x05\xbc\xdd\x81"
 			  "\x47\xc6\x8d\xe6\xb1\x8f\xd7\xcb"
 			  "\x09\x0e\x6e\x22\x48\x1f\xbf\xb8"
@@ -35383,8 +31188,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x08\x7c\xbc\x66\x8a\xb0\xb6\x9f"
 			  "\x92\xd6\x41\x7c\x5b\x2a\x00\x79"
 			  "\x72",
-		.ilen	= 1281,
-		.result	= "\x45\xe8\xe0\xb6\x9c\xca\xfd\x87"
+		.ctext	= "\x45\xe8\xe0\xb6\x9c\xca\xfd\x87"
 			  "\xe8\x1d\x37\x96\x8a\xe3\x40\x35"
 			  "\xcf\x5e\x3a\x46\x3d\xfb\xd0\x69"
 			  "\xde\xaf\x7a\xd5\x0d\xe9\x52\xec"
@@ -35545,7 +31349,7 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x23\x45\x89\x42\xa0\x30\xeb\xbf"
 			  "\xa1\xed\xad\xd5\x76\xfa\x24\x8f"
 			  "\x98",
-		.rlen	= 1281,
+		.len	= 1281,
 		.also_non_np = 1,
 		.np	= 3,
 		.tap	= { 1200, 1, 80 },
@@ -35555,30 +31359,28 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 /*
  * CTS (Cipher Text Stealing) mode tests
  */
-static const struct cipher_testvec cts_mode_enc_tv_template[] = {
+static const struct cipher_testvec cts_mode_tv_template[] = {
 	{ /* from rfc3962 */
 		.klen	= 16,
 		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
 			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.ilen	= 17,
-		.input  = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
+		.ptext	= "\x49\x20\x77\x6f\x75\x6c\x64\x20"
 			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
 			  "\x20",
-		.rlen	= 17,
-		.result	= "\xc6\x35\x35\x68\xf2\xbf\x8c\xb4"
+		.len	= 17,
+		.ctext	= "\xc6\x35\x35\x68\xf2\xbf\x8c\xb4"
 			  "\xd8\xa5\x80\x36\x2d\xa7\xff\x7f"
 			  "\x97",
 	}, {
 		.klen	= 16,
 		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
 			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.ilen   = 31,
-		.input  = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
+		.ptext	= "\x49\x20\x77\x6f\x75\x6c\x64\x20"
 			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
 			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
 			  "\x20\x47\x61\x75\x27\x73\x20",
-		.rlen   = 31,
-		.result = "\xfc\x00\x78\x3e\x0e\xfd\xb2\xc1"
+		.len	= 31,
+		.ctext	= "\xfc\x00\x78\x3e\x0e\xfd\xb2\xc1"
 			  "\xd4\x45\xd4\xc8\xef\xf7\xed\x22"
 			  "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
 			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5",
@@ -35586,13 +31388,12 @@ static const struct cipher_testvec cts_mode_enc_tv_template[] = {
 		.klen	= 16,
 		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
 			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.ilen   = 32,
-		.input  = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
+		.ptext	= "\x49\x20\x77\x6f\x75\x6c\x64\x20"
 			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
 			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
 			  "\x20\x47\x61\x75\x27\x73\x20\x43",
-		.rlen   = 32,
-		.result = "\x39\x31\x25\x23\xa7\x86\x62\xd5"
+		.len	= 32,
+		.ctext	= "\x39\x31\x25\x23\xa7\x86\x62\xd5"
 			  "\xbe\x7f\xcb\xcc\x98\xeb\xf5\xa8"
 			  "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
 			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5\x84",
@@ -35600,15 +31401,14 @@ static const struct cipher_testvec cts_mode_enc_tv_template[] = {
 		.klen	= 16,
 		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
 			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.ilen   = 47,
-		.input  = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
+		.ptext	= "\x49\x20\x77\x6f\x75\x6c\x64\x20"
 			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
 			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
 			  "\x20\x47\x61\x75\x27\x73\x20\x43"
 			  "\x68\x69\x63\x6b\x65\x6e\x2c\x20"
 			  "\x70\x6c\x65\x61\x73\x65\x2c",
-		.rlen   = 47,
-		.result = "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
+		.len	= 47,
+		.ctext	= "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
 			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5\x84"
 			  "\xb3\xff\xfd\x94\x0c\x16\xa1\x8c"
 			  "\x1b\x55\x49\xd2\xf8\x38\x02\x9e"
@@ -35618,15 +31418,14 @@ static const struct cipher_testvec cts_mode_enc_tv_template[] = {
 		.klen	= 16,
 		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
 			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.ilen   = 48,
-		.input  = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
+		.ptext	= "\x49\x20\x77\x6f\x75\x6c\x64\x20"
 			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
 			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
 			  "\x20\x47\x61\x75\x27\x73\x20\x43"
 			  "\x68\x69\x63\x6b\x65\x6e\x2c\x20"
 			  "\x70\x6c\x65\x61\x73\x65\x2c\x20",
-		.rlen   = 48,
-		.result = "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
+		.len	= 48,
+		.ctext	= "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
 			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5\x84"
 			  "\x9d\xad\x8b\xbb\x96\xc4\xcd\xc0"
 			  "\x3b\xc1\x03\xe1\xa1\x94\xbb\xd8"
@@ -35636,8 +31435,7 @@ static const struct cipher_testvec cts_mode_enc_tv_template[] = {
 		.klen	= 16,
 		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
 			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.ilen   = 64,
-		.input  = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
+		.ptext	= "\x49\x20\x77\x6f\x75\x6c\x64\x20"
 			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
 			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
 			  "\x20\x47\x61\x75\x27\x73\x20\x43"
@@ -35645,110 +31443,8 @@ static const struct cipher_testvec cts_mode_enc_tv_template[] = {
 			  "\x70\x6c\x65\x61\x73\x65\x2c\x20"
 			  "\x61\x6e\x64\x20\x77\x6f\x6e\x74"
 			  "\x6f\x6e\x20\x73\x6f\x75\x70\x2e",
-		.rlen   = 64,
-		.result = "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
-			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5\x84"
-			  "\x39\x31\x25\x23\xa7\x86\x62\xd5"
-			  "\xbe\x7f\xcb\xcc\x98\xeb\xf5\xa8"
-			  "\x48\x07\xef\xe8\x36\xee\x89\xa5"
-			  "\x26\x73\x0d\xbc\x2f\x7b\xc8\x40"
-			  "\x9d\xad\x8b\xbb\x96\xc4\xcd\xc0"
-			  "\x3b\xc1\x03\xe1\xa1\x94\xbb\xd8",
-	}
-};
-
-static const struct cipher_testvec cts_mode_dec_tv_template[] = {
-	{ /* from rfc3962 */
-		.klen	= 16,
-		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
-			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.rlen	= 17,
-		.result = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
-			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
-			  "\x20",
-		.ilen	= 17,
-		.input	= "\xc6\x35\x35\x68\xf2\xbf\x8c\xb4"
-			  "\xd8\xa5\x80\x36\x2d\xa7\xff\x7f"
-			  "\x97",
-	}, {
-		.klen	= 16,
-		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
-			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.rlen   = 31,
-		.result = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
-			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
-			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
-			  "\x20\x47\x61\x75\x27\x73\x20",
-		.ilen   = 31,
-		.input  = "\xfc\x00\x78\x3e\x0e\xfd\xb2\xc1"
-			  "\xd4\x45\xd4\xc8\xef\xf7\xed\x22"
-			  "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
-			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5",
-	}, {
-		.klen	= 16,
-		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
-			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.rlen   = 32,
-		.result = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
-			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
-			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
-			  "\x20\x47\x61\x75\x27\x73\x20\x43",
-		.ilen   = 32,
-		.input  = "\x39\x31\x25\x23\xa7\x86\x62\xd5"
-			  "\xbe\x7f\xcb\xcc\x98\xeb\xf5\xa8"
-			  "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
-			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5\x84",
-	}, {
-		.klen	= 16,
-		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
-			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.rlen   = 47,
-		.result = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
-			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
-			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
-			  "\x20\x47\x61\x75\x27\x73\x20\x43"
-			  "\x68\x69\x63\x6b\x65\x6e\x2c\x20"
-			  "\x70\x6c\x65\x61\x73\x65\x2c",
-		.ilen   = 47,
-		.input  = "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
-			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5\x84"
-			  "\xb3\xff\xfd\x94\x0c\x16\xa1\x8c"
-			  "\x1b\x55\x49\xd2\xf8\x38\x02\x9e"
-			  "\x39\x31\x25\x23\xa7\x86\x62\xd5"
-			  "\xbe\x7f\xcb\xcc\x98\xeb\xf5",
-	}, {
-		.klen	= 16,
-		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
-			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.rlen   = 48,
-		.result = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
-			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
-			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
-			  "\x20\x47\x61\x75\x27\x73\x20\x43"
-			  "\x68\x69\x63\x6b\x65\x6e\x2c\x20"
-			  "\x70\x6c\x65\x61\x73\x65\x2c\x20",
-		.ilen   = 48,
-		.input  = "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
-			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5\x84"
-			  "\x9d\xad\x8b\xbb\x96\xc4\xcd\xc0"
-			  "\x3b\xc1\x03\xe1\xa1\x94\xbb\xd8"
-			  "\x39\x31\x25\x23\xa7\x86\x62\xd5"
-			  "\xbe\x7f\xcb\xcc\x98\xeb\xf5\xa8",
-	}, {
-		.klen	= 16,
-		.key    = "\x63\x68\x69\x63\x6b\x65\x6e\x20"
-			  "\x74\x65\x72\x69\x79\x61\x6b\x69",
-		.rlen   = 64,
-		.result = "\x49\x20\x77\x6f\x75\x6c\x64\x20"
-			  "\x6c\x69\x6b\x65\x20\x74\x68\x65"
-			  "\x20\x47\x65\x6e\x65\x72\x61\x6c"
-			  "\x20\x47\x61\x75\x27\x73\x20\x43"
-			  "\x68\x69\x63\x6b\x65\x6e\x2c\x20"
-			  "\x70\x6c\x65\x61\x73\x65\x2c\x20"
-			  "\x61\x6e\x64\x20\x77\x6f\x6e\x74"
-			  "\x6f\x6e\x20\x73\x6f\x75\x70\x2e",
-		.ilen   = 64,
-		.input  = "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
+		.len	= 64,
+		.ctext	= "\x97\x68\x72\x68\xd6\xec\xcc\xc0"
 			  "\xc0\x7b\x25\xe2\x5e\xcf\xe5\x84"
 			  "\x39\x31\x25\x23\xa7\x86\x62\xd5"
 			  "\xbe\x7f\xcb\xcc\x98\xeb\xf5\xa8"
@@ -36058,6 +31754,15 @@ static const struct hash_testvec michael_mic_tv_template[] = {
  */
 static const struct hash_testvec crc32_tv_template[] = {
 	{
+		.psize = 0,
+		.digest = "\x00\x00\x00\x00",
+	},
+	{
+		.plaintext = "abcdefg",
+		.psize = 7,
+		.digest = "\xd8\xb5\x46\xac",
+	},
+	{
 		.key = "\x87\xa9\xcb\xed",
 		.ksize = 4,
 		.psize = 0,
@@ -36494,6 +32199,11 @@ static const struct hash_testvec crc32c_tv_template[] = {
 		.digest = "\x00\x00\x00\x00",
 	},
 	{
+		.plaintext = "abcdefg",
+		.psize = 7,
+		.digest = "\x41\xf4\x27\xe6",
+	},
+	{
 		.key = "\x87\xa9\xcb\xed",
 		.ksize = 4,
 		.psize = 0,
@@ -36921,94 +32631,6 @@ static const struct hash_testvec crc32c_tv_template[] = {
 	}
 };
 
-/*
- * Blakcifn CRC test vectors
- */
-static const struct hash_testvec bfin_crc_tv_template[] = {
-	{
-		.psize = 0,
-		.digest = "\x00\x00\x00\x00",
-	},
-	{
-		.key = "\x87\xa9\xcb\xed",
-		.ksize = 4,
-		.psize = 0,
-		.digest = "\x87\xa9\xcb\xed",
-	},
-	{
-		.key = "\xff\xff\xff\xff",
-		.ksize = 4,
-		.plaintext = "\x01\x02\x03\x04\x05\x06\x07\x08"
-			     "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
-			     "\x11\x12\x13\x14\x15\x16\x17\x18"
-			     "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
-			     "\x21\x22\x23\x24\x25\x26\x27\x28",
-		.psize = 40,
-		.digest = "\x84\x0c\x8d\xa2",
-	},
-	{
-		.key = "\xff\xff\xff\xff",
-		.ksize = 4,
-		.plaintext = "\x01\x02\x03\x04\x05\x06\x07\x08"
-			     "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
-			     "\x11\x12\x13\x14\x15\x16\x17\x18"
-			     "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
-			     "\x21\x22\x23\x24\x25\x26",
-		.psize = 38,
-		.digest = "\x8c\x58\xec\xb7",
-	},
-	{
-		.key = "\xff\xff\xff\xff",
-		.ksize = 4,
-		.plaintext = "\x01\x02\x03\x04\x05\x06\x07\x08"
-			     "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
-			     "\x11\x12\x13\x14\x15\x16\x17\x18"
-			     "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
-			     "\x21\x22\x23\x24\x25\x26\x27",
-		.psize = 39,
-		.digest = "\xdc\x50\x28\x7b",
-	},
-	{
-		.key = "\xff\xff\xff\xff",
-		.ksize = 4,
-		.plaintext = "\x01\x02\x03\x04\x05\x06\x07\x08"
-			     "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
-			     "\x11\x12\x13\x14\x15\x16\x17\x18"
-			     "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
-			     "\x21\x22\x23\x24\x25\x26\x27\x28"
-			     "\x29\x2a\x2b\x2c\x2d\x2e\x2f\x30"
-			     "\x31\x32\x33\x34\x35\x36\x37\x38"
-			     "\x39\x3a\x3b\x3c\x3d\x3e\x3f\x40"
-			     "\x41\x42\x43\x44\x45\x46\x47\x48"
-			     "\x49\x4a\x4b\x4c\x4d\x4e\x4f\x50"
-			     "\x51\x52\x53\x54\x55\x56\x57\x58"
-			     "\x59\x5a\x5b\x5c\x5d\x5e\x5f\x60"
-			     "\x61\x62\x63\x64\x65\x66\x67\x68"
-			     "\x69\x6a\x6b\x6c\x6d\x6e\x6f\x70"
-			     "\x71\x72\x73\x74\x75\x76\x77\x78"
-			     "\x79\x7a\x7b\x7c\x7d\x7e\x7f\x80"
-			     "\x81\x82\x83\x84\x85\x86\x87\x88"
-			     "\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90"
-			     "\x91\x92\x93\x94\x95\x96\x97\x98"
-			     "\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0"
-			     "\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8"
-			     "\xa9\xaa\xab\xac\xad\xae\xaf\xb0"
-			     "\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8"
-			     "\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0"
-			     "\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8"
-			     "\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0"
-			     "\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8"
-			     "\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0"
-			     "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8"
-			     "\xe9\xea\xeb\xec\xed\xee\xef\xf0",
-		.psize = 240,
-		.digest = "\x10\x19\x4a\x5c",
-		.np = 2,
-		.tap = { 31, 209 }
-	},
-
-};
-
 static const struct comp_testvec lz4_comp_tv_template[] = {
 	{
 		.inlen	= 255,
@@ -37131,4 +32753,75 @@ static const struct comp_testvec lz4hc_decomp_tv_template[] = {
 	},
 };
 
+static const struct comp_testvec zstd_comp_tv_template[] = {
+	{
+		.inlen	= 68,
+		.outlen	= 39,
+		.input	= "The algorithm is zstd. "
+			  "The algorithm is zstd. "
+			  "The algorithm is zstd.",
+		.output	= "\x28\xb5\x2f\xfd\x00\x50\xf5\x00\x00\xb8\x54\x68\x65"
+			  "\x20\x61\x6c\x67\x6f\x72\x69\x74\x68\x6d\x20\x69\x73"
+			  "\x20\x7a\x73\x74\x64\x2e\x20\x01\x00\x55\x73\x36\x01"
+			  ,
+	},
+	{
+		.inlen	= 244,
+		.outlen	= 151,
+		.input	= "zstd, short for Zstandard, is a fast lossless "
+			  "compression algorithm, targeting real-time "
+			  "compression scenarios at zlib-level and better "
+			  "compression ratios. The zstd compression library "
+			  "provides in-memory compression and decompression "
+			  "functions.",
+		.output	= "\x28\xb5\x2f\xfd\x00\x50\x75\x04\x00\x42\x4b\x1e\x17"
+			  "\x90\x81\x31\x00\xf2\x2f\xe4\x36\xc9\xef\x92\x88\x32"
+			  "\xc9\xf2\x24\x94\xd8\x68\x9a\x0f\x00\x0c\xc4\x31\x6f"
+			  "\x0d\x0c\x38\xac\x5c\x48\x03\xcd\x63\x67\xc0\xf3\xad"
+			  "\x4e\x90\xaa\x78\xa0\xa4\xc5\x99\xda\x2f\xb6\x24\x60"
+			  "\xe2\x79\x4b\xaa\xb6\x6b\x85\x0b\xc9\xc6\x04\x66\x86"
+			  "\xe2\xcc\xe2\x25\x3f\x4f\x09\xcd\xb8\x9d\xdb\xc1\x90"
+			  "\xa9\x11\xbc\x35\x44\x69\x2d\x9c\x64\x4f\x13\x31\x64"
+			  "\xcc\xfb\x4d\x95\x93\x86\x7f\x33\x7f\x1a\xef\xe9\x30"
+			  "\xf9\x67\xa1\x94\x0a\x69\x0f\x60\xcd\xc3\xab\x99\xdc"
+			  "\x42\xed\x97\x05\x00\x33\xc3\x15\x95\x3a\x06\xa0\x0e"
+			  "\x20\xa9\x0e\x82\xb9\x43\x45\x01",
+	},
+};
+
+static const struct comp_testvec zstd_decomp_tv_template[] = {
+	{
+		.inlen	= 43,
+		.outlen	= 68,
+		.input	= "\x28\xb5\x2f\xfd\x04\x50\xf5\x00\x00\xb8\x54\x68\x65"
+			  "\x20\x61\x6c\x67\x6f\x72\x69\x74\x68\x6d\x20\x69\x73"
+			  "\x20\x7a\x73\x74\x64\x2e\x20\x01\x00\x55\x73\x36\x01"
+			  "\x6b\xf4\x13\x35",
+		.output	= "The algorithm is zstd. "
+			  "The algorithm is zstd. "
+			  "The algorithm is zstd.",
+	},
+	{
+		.inlen	= 155,
+		.outlen	= 244,
+		.input	= "\x28\xb5\x2f\xfd\x04\x50\x75\x04\x00\x42\x4b\x1e\x17"
+			  "\x90\x81\x31\x00\xf2\x2f\xe4\x36\xc9\xef\x92\x88\x32"
+			  "\xc9\xf2\x24\x94\xd8\x68\x9a\x0f\x00\x0c\xc4\x31\x6f"
+			  "\x0d\x0c\x38\xac\x5c\x48\x03\xcd\x63\x67\xc0\xf3\xad"
+			  "\x4e\x90\xaa\x78\xa0\xa4\xc5\x99\xda\x2f\xb6\x24\x60"
+			  "\xe2\x79\x4b\xaa\xb6\x6b\x85\x0b\xc9\xc6\x04\x66\x86"
+			  "\xe2\xcc\xe2\x25\x3f\x4f\x09\xcd\xb8\x9d\xdb\xc1\x90"
+			  "\xa9\x11\xbc\x35\x44\x69\x2d\x9c\x64\x4f\x13\x31\x64"
+			  "\xcc\xfb\x4d\x95\x93\x86\x7f\x33\x7f\x1a\xef\xe9\x30"
+			  "\xf9\x67\xa1\x94\x0a\x69\x0f\x60\xcd\xc3\xab\x99\xdc"
+			  "\x42\xed\x97\x05\x00\x33\xc3\x15\x95\x3a\x06\xa0\x0e"
+			  "\x20\xa9\x0e\x82\xb9\x43\x45\x01\xaa\x6d\xda\x0d",
+		.output	= "zstd, short for Zstandard, is a fast lossless "
+			  "compression algorithm, targeting real-time "
+			  "compression scenarios at zlib-level and better "
+			  "compression ratios. The zstd compression library "
+			  "provides in-memory compression and decompression "
+			  "functions.",
+	},
+};
 #endif	/* _CRYPTO_TESTMGR_H */
diff --git a/crypto/zstd.c b/crypto/zstd.c
new file mode 100644
index 000000000000..9a76b3ed8b8b
--- /dev/null
+++ b/crypto/zstd.c
@@ -0,0 +1,265 @@
+/*
+ * Cryptographic API.
+ *
+ * Copyright (c) 2017-present, Facebook, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/vmalloc.h>
+#include <linux/zstd.h>
+#include <crypto/internal/scompress.h>
+
+
+#define ZSTD_DEF_LEVEL	3
+
+struct zstd_ctx {
+	ZSTD_CCtx *cctx;
+	ZSTD_DCtx *dctx;
+	void *cwksp;
+	void *dwksp;
+};
+
+static ZSTD_parameters zstd_params(void)
+{
+	return ZSTD_getParams(ZSTD_DEF_LEVEL, 0, 0);
+}
+
+static int zstd_comp_init(struct zstd_ctx *ctx)
+{
+	int ret = 0;
+	const ZSTD_parameters params = zstd_params();
+	const size_t wksp_size = ZSTD_CCtxWorkspaceBound(params.cParams);
+
+	ctx->cwksp = vzalloc(wksp_size);
+	if (!ctx->cwksp) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ctx->cctx = ZSTD_initCCtx(ctx->cwksp, wksp_size);
+	if (!ctx->cctx) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+out:
+	return ret;
+out_free:
+	vfree(ctx->cwksp);
+	goto out;
+}
+
+static int zstd_decomp_init(struct zstd_ctx *ctx)
+{
+	int ret = 0;
+	const size_t wksp_size = ZSTD_DCtxWorkspaceBound();
+
+	ctx->dwksp = vzalloc(wksp_size);
+	if (!ctx->dwksp) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ctx->dctx = ZSTD_initDCtx(ctx->dwksp, wksp_size);
+	if (!ctx->dctx) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+out:
+	return ret;
+out_free:
+	vfree(ctx->dwksp);
+	goto out;
+}
+
+static void zstd_comp_exit(struct zstd_ctx *ctx)
+{
+	vfree(ctx->cwksp);
+	ctx->cwksp = NULL;
+	ctx->cctx = NULL;
+}
+
+static void zstd_decomp_exit(struct zstd_ctx *ctx)
+{
+	vfree(ctx->dwksp);
+	ctx->dwksp = NULL;
+	ctx->dctx = NULL;
+}
+
+static int __zstd_init(void *ctx)
+{
+	int ret;
+
+	ret = zstd_comp_init(ctx);
+	if (ret)
+		return ret;
+	ret = zstd_decomp_init(ctx);
+	if (ret)
+		zstd_comp_exit(ctx);
+	return ret;
+}
+
+static void *zstd_alloc_ctx(struct crypto_scomp *tfm)
+{
+	int ret;
+	struct zstd_ctx *ctx;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	ret = __zstd_init(ctx);
+	if (ret) {
+		kfree(ctx);
+		return ERR_PTR(ret);
+	}
+
+	return ctx;
+}
+
+static int zstd_init(struct crypto_tfm *tfm)
+{
+	struct zstd_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	return __zstd_init(ctx);
+}
+
+static void __zstd_exit(void *ctx)
+{
+	zstd_comp_exit(ctx);
+	zstd_decomp_exit(ctx);
+}
+
+static void zstd_free_ctx(struct crypto_scomp *tfm, void *ctx)
+{
+	__zstd_exit(ctx);
+	kzfree(ctx);
+}
+
+static void zstd_exit(struct crypto_tfm *tfm)
+{
+	struct zstd_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	__zstd_exit(ctx);
+}
+
+static int __zstd_compress(const u8 *src, unsigned int slen,
+			   u8 *dst, unsigned int *dlen, void *ctx)
+{
+	size_t out_len;
+	struct zstd_ctx *zctx = ctx;
+	const ZSTD_parameters params = zstd_params();
+
+	out_len = ZSTD_compressCCtx(zctx->cctx, dst, *dlen, src, slen, params);
+	if (ZSTD_isError(out_len))
+		return -EINVAL;
+	*dlen = out_len;
+	return 0;
+}
+
+static int zstd_compress(struct crypto_tfm *tfm, const u8 *src,
+			 unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+	struct zstd_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	return __zstd_compress(src, slen, dst, dlen, ctx);
+}
+
+static int zstd_scompress(struct crypto_scomp *tfm, const u8 *src,
+			  unsigned int slen, u8 *dst, unsigned int *dlen,
+			  void *ctx)
+{
+	return __zstd_compress(src, slen, dst, dlen, ctx);
+}
+
+static int __zstd_decompress(const u8 *src, unsigned int slen,
+			     u8 *dst, unsigned int *dlen, void *ctx)
+{
+	size_t out_len;
+	struct zstd_ctx *zctx = ctx;
+
+	out_len = ZSTD_decompressDCtx(zctx->dctx, dst, *dlen, src, slen);
+	if (ZSTD_isError(out_len))
+		return -EINVAL;
+	*dlen = out_len;
+	return 0;
+}
+
+static int zstd_decompress(struct crypto_tfm *tfm, const u8 *src,
+			   unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+	struct zstd_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	return __zstd_decompress(src, slen, dst, dlen, ctx);
+}
+
+static int zstd_sdecompress(struct crypto_scomp *tfm, const u8 *src,
+			    unsigned int slen, u8 *dst, unsigned int *dlen,
+			    void *ctx)
+{
+	return __zstd_decompress(src, slen, dst, dlen, ctx);
+}
+
+static struct crypto_alg alg = {
+	.cra_name		= "zstd",
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct zstd_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_init		= zstd_init,
+	.cra_exit		= zstd_exit,
+	.cra_u			= { .compress = {
+	.coa_compress		= zstd_compress,
+	.coa_decompress		= zstd_decompress } }
+};
+
+static struct scomp_alg scomp = {
+	.alloc_ctx		= zstd_alloc_ctx,
+	.free_ctx		= zstd_free_ctx,
+	.compress		= zstd_scompress,
+	.decompress		= zstd_sdecompress,
+	.base			= {
+		.cra_name	= "zstd",
+		.cra_driver_name = "zstd-scomp",
+		.cra_module	 = THIS_MODULE,
+	}
+};
+
+static int __init zstd_mod_init(void)
+{
+	int ret;
+
+	ret = crypto_register_alg(&alg);
+	if (ret)
+		return ret;
+
+	ret = crypto_register_scomp(&scomp);
+	if (ret)
+		crypto_unregister_alg(&alg);
+
+	return ret;
+}
+
+static void __exit zstd_mod_fini(void)
+{
+	crypto_unregister_alg(&alg);
+	crypto_unregister_scomp(&scomp);
+}
+
+module_init(zstd_mod_init);
+module_exit(zstd_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Zstd Compression Algorithm");
+MODULE_ALIAS_CRYPTO("zstd");
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 2d8de2f8c1ed..cdd3136829f1 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -82,11 +82,11 @@ static SIMPLE_DEV_PM_OPS(acpi_ac_pm, NULL, acpi_ac_resume);
 #ifdef CONFIG_ACPI_PROCFS_POWER
 extern struct proc_dir_entry *acpi_lock_ac_dir(void);
 extern void *acpi_unlock_ac_dir(struct proc_dir_entry *acpi_ac_dir);
-static int acpi_ac_open_fs(struct inode *inode, struct file *file);
 #endif
 
 
 static int ac_sleep_before_get_state_ms;
+static int ac_check_pmic = 1;
 
 static struct acpi_driver acpi_ac_driver = {
 	.name = "ac",
@@ -111,16 +111,6 @@ struct acpi_ac {
 
 #define to_acpi_ac(x) power_supply_get_drvdata(x)
 
-#ifdef CONFIG_ACPI_PROCFS_POWER
-static const struct file_operations acpi_ac_fops = {
-	.owner = THIS_MODULE,
-	.open = acpi_ac_open_fs,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-#endif
-
 /* --------------------------------------------------------------------------
                                AC Adapter Management
    -------------------------------------------------------------------------- */
@@ -209,11 +199,6 @@ static int acpi_ac_seq_show(struct seq_file *seq, void *offset)
 	return 0;
 }
 
-static int acpi_ac_open_fs(struct inode *inode, struct file *file)
-{
-	return single_open(file, acpi_ac_seq_show, PDE_DATA(inode));
-}
-
 static int acpi_ac_add_fs(struct acpi_ac *ac)
 {
 	struct proc_dir_entry *entry = NULL;
@@ -228,9 +213,8 @@ static int acpi_ac_add_fs(struct acpi_ac *ac)
 	}
 
 	/* 'state' [R] */
-	entry = proc_create_data(ACPI_AC_FILE_STATE,
-				 S_IRUGO, acpi_device_dir(ac->device),
-				 &acpi_ac_fops, ac);
+	entry = proc_create_single_data(ACPI_AC_FILE_STATE, S_IRUGO,
+			acpi_device_dir(ac->device), acpi_ac_seq_show, ac);
 	if (!entry)
 		return -ENODEV;
 	return 0;
@@ -310,21 +294,43 @@ static int acpi_ac_battery_notify(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static int thinkpad_e530_quirk(const struct dmi_system_id *d)
+static int __init thinkpad_e530_quirk(const struct dmi_system_id *d)
 {
 	ac_sleep_before_get_state_ms = 1000;
 	return 0;
 }
 
-static const struct dmi_system_id ac_dmi_table[] = {
+static int __init ac_do_not_check_pmic_quirk(const struct dmi_system_id *d)
+{
+	ac_check_pmic = 0;
+	return 0;
+}
+
+static const struct dmi_system_id ac_dmi_table[]  __initconst = {
 	{
+	/* Thinkpad e530 */
 	.callback = thinkpad_e530_quirk,
-	.ident = "thinkpad e530",
 	.matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
 		DMI_MATCH(DMI_PRODUCT_NAME, "32597CG"),
 		},
 	},
+	{
+		/* ECS EF20EA */
+		.callback = ac_do_not_check_pmic_quirk,
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "EF20EA"),
+		},
+	},
+	{
+		/* Lenovo Ideapad Miix 320 */
+		.callback = ac_do_not_check_pmic_quirk,
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80XF"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 320-10ICR"),
+		},
+	},
 	{},
 };
 
@@ -384,7 +390,6 @@ end:
 		kfree(ac);
 	}
 
-	dmi_check_system(ac_dmi_table);
 	return result;
 }
 
@@ -442,13 +447,17 @@ static int __init acpi_ac_init(void)
 	if (acpi_disabled)
 		return -ENODEV;
 
-	for (i = 0; i < ARRAY_SIZE(acpi_ac_blacklist); i++)
-		if (acpi_dev_present(acpi_ac_blacklist[i].hid, "1",
-				     acpi_ac_blacklist[i].hrv)) {
-			pr_info(PREFIX "AC: found native %s PMIC, not loading\n",
-				acpi_ac_blacklist[i].hid);
-			return -ENODEV;
-		}
+	dmi_check_system(ac_dmi_table);
+
+	if (ac_check_pmic) {
+		for (i = 0; i < ARRAY_SIZE(acpi_ac_blacklist); i++)
+			if (acpi_dev_present(acpi_ac_blacklist[i].hid, "1",
+					     acpi_ac_blacklist[i].hrv)) {
+				pr_info(PREFIX "AC: found native %s PMIC, not loading\n",
+					acpi_ac_blacklist[i].hid);
+				return -ENODEV;
+			}
+	}
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	acpi_ac_dir = acpi_lock_ac_dir();
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index d553b0087947..2664452fa112 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/platform_data/clk-st.h>
 #include <linux/platform_device.h>
 #include <linux/pm_domain.h>
 #include <linux/clkdev.h>
@@ -72,6 +73,47 @@ static int acpi_apd_setup(struct apd_private_data *pdata)
 }
 
 #ifdef CONFIG_X86_AMD_PLATFORM_DEVICE
+
+static int misc_check_res(struct acpi_resource *ares, void *data)
+{
+	struct resource res;
+
+	return !acpi_dev_resource_memory(ares, &res);
+}
+
+static int st_misc_setup(struct apd_private_data *pdata)
+{
+	struct acpi_device *adev = pdata->adev;
+	struct platform_device *clkdev;
+	struct st_clk_data *clk_data;
+	struct resource_entry *rentry;
+	struct list_head resource_list;
+	int ret;
+
+	clk_data = devm_kzalloc(&adev->dev, sizeof(*clk_data), GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&resource_list);
+	ret = acpi_dev_get_resources(adev, &resource_list, misc_check_res,
+				     NULL);
+	if (ret < 0)
+		return -ENOENT;
+
+	list_for_each_entry(rentry, &resource_list, node) {
+		clk_data->base = devm_ioremap(&adev->dev, rentry->res->start,
+					      resource_size(rentry->res));
+		break;
+	}
+
+	acpi_dev_free_resource_list(&resource_list);
+
+	clkdev = platform_device_register_data(&adev->dev, "clk-st",
+					       PLATFORM_DEVID_NONE, clk_data,
+					       sizeof(*clk_data));
+	return PTR_ERR_OR_ZERO(clkdev);
+}
+
 static const struct apd_device_desc cz_i2c_desc = {
 	.setup = acpi_apd_setup,
 	.fixed_clk_rate = 133000000,
@@ -94,6 +136,10 @@ static const struct apd_device_desc cz_uart_desc = {
 	.fixed_clk_rate = 48000000,
 	.properties = uart_properties,
 };
+
+static const struct apd_device_desc st_misc_desc = {
+	.setup = st_misc_setup,
+};
 #endif
 
 #ifdef CONFIG_ARM64
@@ -179,6 +225,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = {
 	{ "AMD0020", APD_ADDR(cz_uart_desc) },
 	{ "AMDI0020", APD_ADDR(cz_uart_desc) },
 	{ "AMD0030", },
+	{ "AMD0040", APD_ADDR(st_misc_desc)},
 #endif
 #ifdef CONFIG_ARM64
 	{ "APMC0D0F", APD_ADDR(xgene_i2c_desc) },
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 2bcffec8dbf0..cb6ac5c65c2e 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -69,6 +69,10 @@ ACPI_MODULE_NAME("acpi_lpss");
 #define LPSS_SAVE_CTX			BIT(4)
 #define LPSS_NO_D3_DELAY		BIT(5)
 
+/* Crystal Cove PMIC shares same ACPI ID between different platforms */
+#define BYT_CRC_HRV			2
+#define CHT_CRC_HRV			3
+
 struct lpss_private_data;
 
 struct lpss_device_desc {
@@ -162,7 +166,7 @@ static void byt_pwm_setup(struct lpss_private_data *pdata)
 	if (!adev->pnp.unique_id || strcmp(adev->pnp.unique_id, "1"))
 		return;
 
-	if (!acpi_dev_present("INT33FD", NULL, -1))
+	if (!acpi_dev_present("INT33FD", NULL, BYT_CRC_HRV))
 		pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
 }
 
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 76fb96966f7b..2f2e737be0f8 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -2123,6 +2123,25 @@ static int __init intel_opregion_present(void)
 	return opregion;
 }
 
+static bool dmi_is_desktop(void)
+{
+	const char *chassis_type;
+
+	chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
+	if (!chassis_type)
+		return false;
+
+	if (!strcmp(chassis_type, "3") || /*  3: Desktop */
+	    !strcmp(chassis_type, "4") || /*  4: Low Profile Desktop */
+	    !strcmp(chassis_type, "5") || /*  5: Pizza Box */
+	    !strcmp(chassis_type, "6") || /*  6: Mini Tower */
+	    !strcmp(chassis_type, "7") || /*  7: Tower */
+	    !strcmp(chassis_type, "11"))  /* 11: Main Server Chassis */
+		return true;
+
+	return false;
+}
+
 int acpi_video_register(void)
 {
 	int ret = 0;
@@ -2143,8 +2162,12 @@ int acpi_video_register(void)
 	 * win8 ready (where we also prefer the native backlight driver, so
 	 * normally the acpi_video code should not register there anyways).
 	 */
-	if (only_lcd == -1)
-		only_lcd = acpi_osi_is_win8();
+	if (only_lcd == -1) {
+		if (dmi_is_desktop() && acpi_osi_is_win8())
+			only_lcd = true;
+		else
+			only_lcd = false;
+	}
 
 	dmi_check_system(video_dmi_table);
 
diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c
index ebb626ffb5fa..95600309ce42 100644
--- a/drivers/acpi/acpi_watchdog.c
+++ b/drivers/acpi/acpi_watchdog.c
@@ -17,18 +17,77 @@
 
 #include "internal.h"
 
+#ifdef CONFIG_RTC_MC146818_LIB
+#include <linux/mc146818rtc.h>
+
+/*
+ * There are several systems where the WDAT table is accessing RTC SRAM to
+ * store persistent information. This does not work well with the Linux RTC
+ * driver so on those systems we skip WDAT driver and prefer iTCO_wdt
+ * instead.
+ *
+ * See also https://bugzilla.kernel.org/show_bug.cgi?id=199033.
+ */
+static bool acpi_watchdog_uses_rtc(const struct acpi_table_wdat *wdat)
+{
+	const struct acpi_wdat_entry *entries;
+	int i;
+
+	entries = (struct acpi_wdat_entry *)(wdat + 1);
+	for (i = 0; i < wdat->entries; i++) {
+		const struct acpi_generic_address *gas;
+
+		gas = &entries[i].register_region;
+		if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
+			switch (gas->address) {
+			case RTC_PORT(0):
+			case RTC_PORT(1):
+			case RTC_PORT(2):
+			case RTC_PORT(3):
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+#else
+static bool acpi_watchdog_uses_rtc(const struct acpi_table_wdat *wdat)
+{
+	return false;
+}
+#endif
+
+static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void)
+{
+	const struct acpi_table_wdat *wdat = NULL;
+	acpi_status status;
+
+	if (acpi_disabled)
+		return NULL;
+
+	status = acpi_get_table(ACPI_SIG_WDAT, 0,
+				(struct acpi_table_header **)&wdat);
+	if (ACPI_FAILURE(status)) {
+		/* It is fine if there is no WDAT */
+		return NULL;
+	}
+
+	if (acpi_watchdog_uses_rtc(wdat)) {
+		pr_info("Skipping WDAT on this system because it uses RTC SRAM\n");
+		return NULL;
+	}
+
+	return wdat;
+}
+
 /**
  * Returns true if this system should prefer ACPI based watchdog instead of
  * the native one (which are typically the same hardware).
  */
 bool acpi_has_watchdog(void)
 {
-	struct acpi_table_header hdr;
-
-	if (acpi_disabled)
-		return false;
-
-	return ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_WDAT, 0, &hdr));
+	return !!acpi_watchdog_get_wdat();
 }
 EXPORT_SYMBOL_GPL(acpi_has_watchdog);
 
@@ -41,12 +100,10 @@ void __init acpi_watchdog_init(void)
 	struct platform_device *pdev;
 	struct resource *resources;
 	size_t nresources = 0;
-	acpi_status status;
 	int i;
 
-	status = acpi_get_table(ACPI_SIG_WDAT, 0,
-				(struct acpi_table_header **)&wdat);
-	if (ACPI_FAILURE(status)) {
+	wdat = acpi_watchdog_get_wdat();
+	if (!wdat) {
 		/* It is fine if there is no WDAT */
 		return;
 	}
diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h
index a2a85122fafe..5a9c2febc0fb 100644
--- a/drivers/acpi/acpica/acapps.h
+++ b/drivers/acpi/acpica/acapps.h
@@ -143,6 +143,8 @@ acpi_status
 fl_split_input_pathname(char *input_path,
 			char **out_directory_path, char **out_filename);
 
+char *fl_get_file_basename(char *file_pathname);
+
 char *ad_generate_filename(char *prefix, char *table_id);
 
 void
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 0bc550072a21..1e6204518496 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -82,7 +82,7 @@ ACPI_GLOBAL(u8, acpi_gbl_global_lock_pending);
  * interrupt level
  */
 ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock);	/* For GPE data structs and registers */
-ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock);	/* For ACPI H/W except GPE registers */
+ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock);	/* For ACPI H/W except GPE registers */
 ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock);
 
 /* Mutex for _OSI support */
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 514aaf948ea9..3825df923480 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -56,6 +56,10 @@ acpi_status acpi_ns_initialize_objects(void);
 
 acpi_status acpi_ns_initialize_devices(u32 flags);
 
+acpi_status
+acpi_ns_init_one_package(acpi_handle obj_handle,
+			 u32 level, void *context, void **return_value);
+
 /*
  * nsload -  Namespace loading
  */
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index 170802c62179..dc94de91033e 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -189,9 +189,15 @@ void acpi_db_dump_namespace(char *start_arg, char *depth_arg)
 	}
 
 	acpi_db_set_output_destination(ACPI_DB_DUPLICATE_OUTPUT);
-	acpi_os_printf("ACPI Namespace (from %4.4s (%p) subtree):\n",
-		       ((struct acpi_namespace_node *)subtree_entry)->name.
-		       ascii, subtree_entry);
+
+	if (((struct acpi_namespace_node *)subtree_entry)->parent) {
+		acpi_os_printf("ACPI Namespace (from %4.4s (%p) subtree):\n",
+			       ((struct acpi_namespace_node *)subtree_entry)->
+			       name.ascii, subtree_entry);
+	} else {
+		acpi_os_printf("ACPI Namespace (from %s):\n",
+			       ACPI_NAMESPACE_ROOT);
+	}
 
 	/* Display the subtree */
 
diff --git a/drivers/acpi/acpica/dbtest.c b/drivers/acpi/acpica/dbtest.c
index 3892680a5258..8a5462439a97 100644
--- a/drivers/acpi/acpica/dbtest.c
+++ b/drivers/acpi/acpica/dbtest.c
@@ -30,6 +30,8 @@ acpi_db_test_buffer_type(struct acpi_namespace_node *node, u32 bit_length);
 static acpi_status
 acpi_db_test_string_type(struct acpi_namespace_node *node, u32 byte_length);
 
+static acpi_status acpi_db_test_package_type(struct acpi_namespace_node *node);
+
 static acpi_status
 acpi_db_read_from_object(struct acpi_namespace_node *node,
 			 acpi_object_type expected_type,
@@ -273,6 +275,11 @@ acpi_db_test_one_object(acpi_handle obj_handle,
 		bit_length = byte_length * 8;
 		break;
 
+	case ACPI_TYPE_PACKAGE:
+
+		local_type = ACPI_TYPE_PACKAGE;
+		break;
+
 	case ACPI_TYPE_FIELD_UNIT:
 	case ACPI_TYPE_BUFFER_FIELD:
 	case ACPI_TYPE_LOCAL_REGION_FIELD:
@@ -305,6 +312,7 @@ acpi_db_test_one_object(acpi_handle obj_handle,
 
 	acpi_os_printf("%14s: %4.4s",
 		       acpi_ut_get_type_name(node->type), node->name.ascii);
+
 	if (!obj_desc) {
 		acpi_os_printf(" Ignoring, no attached object\n");
 		return (AE_OK);
@@ -322,14 +330,13 @@ acpi_db_test_one_object(acpi_handle obj_handle,
 		case ACPI_ADR_SPACE_SYSTEM_MEMORY:
 		case ACPI_ADR_SPACE_SYSTEM_IO:
 		case ACPI_ADR_SPACE_PCI_CONFIG:
-		case ACPI_ADR_SPACE_EC:
 
 			break;
 
 		default:
 
 			acpi_os_printf
-			    ("    %s space is not supported [%4.4s]\n",
+			    ("    %s space is not supported in this command [%4.4s]\n",
 			     acpi_ut_get_region_name(region_obj->region.
 						     space_id),
 			     region_obj->region.node->name.ascii);
@@ -359,6 +366,11 @@ acpi_db_test_one_object(acpi_handle obj_handle,
 		status = acpi_db_test_buffer_type(node, bit_length);
 		break;
 
+	case ACPI_TYPE_PACKAGE:
+
+		status = acpi_db_test_package_type(node);
+		break;
+
 	default:
 
 		acpi_os_printf(" Ignoring, type not implemented (%2.2X)",
@@ -366,6 +378,13 @@ acpi_db_test_one_object(acpi_handle obj_handle,
 		break;
 	}
 
+	/* Exit on error, but don't abort the namespace walk */
+
+	if (ACPI_FAILURE(status)) {
+		status = AE_OK;
+		goto exit;
+	}
+
 	switch (node->type) {
 	case ACPI_TYPE_LOCAL_REGION_FIELD:
 
@@ -373,12 +392,14 @@ acpi_db_test_one_object(acpi_handle obj_handle,
 		acpi_os_printf(" (%s)",
 			       acpi_ut_get_region_name(region_obj->region.
 						       space_id));
+
 		break;
 
 	default:
 		break;
 	}
 
+exit:
 	acpi_os_printf("\n");
 	return (status);
 }
@@ -431,7 +452,6 @@ acpi_db_test_integer_type(struct acpi_namespace_node *node, u32 bit_length)
 	if (temp1->integer.value == value_to_write) {
 		value_to_write = 0;
 	}
-
 	/* Write a new value */
 
 	write_value.type = ACPI_TYPE_INTEGER;
@@ -708,6 +728,35 @@ exit:
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_db_test_package_type
+ *
+ * PARAMETERS:  node                - Parent NS node for the object
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Test read for a Package object.
+ *
+ ******************************************************************************/
+
+static acpi_status acpi_db_test_package_type(struct acpi_namespace_node *node)
+{
+	union acpi_object *temp1 = NULL;
+	acpi_status status;
+
+	/* Read the original value */
+
+	status = acpi_db_read_from_object(node, ACPI_TYPE_PACKAGE, &temp1);
+	if (ACPI_FAILURE(status)) {
+		return (status);
+	}
+
+	acpi_os_printf(" %8.8X Elements", temp1->package.count);
+	acpi_os_free(temp1);
+	return (status);
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_db_read_from_object
  *
  * PARAMETERS:  node                - Parent NS node for the object
@@ -746,8 +795,8 @@ acpi_db_read_from_object(struct acpi_namespace_node *node,
 	acpi_gbl_method_executing = TRUE;
 	status = acpi_evaluate_object(read_handle, NULL,
 				      &param_objects, &return_obj);
-	acpi_gbl_method_executing = FALSE;
 
+	acpi_gbl_method_executing = FALSE;
 	if (ACPI_FAILURE(status)) {
 		acpi_os_printf("Could not read from object, %s",
 			       acpi_format_exception(status));
@@ -760,6 +809,7 @@ acpi_db_read_from_object(struct acpi_namespace_node *node,
 	case ACPI_TYPE_INTEGER:
 	case ACPI_TYPE_BUFFER:
 	case ACPI_TYPE_STRING:
+	case ACPI_TYPE_PACKAGE:
 		/*
 		 * Did we receive the type we wanted? Most important for the
 		 * Integer/Buffer case (when a field is larger than an Integer,
@@ -771,6 +821,7 @@ acpi_db_read_from_object(struct acpi_namespace_node *node,
 			     acpi_ut_get_type_name(expected_type),
 			     acpi_ut_get_type_name(ret_value->type));
 
+			acpi_os_free(return_obj.pointer);
 			return (AE_TYPE);
 		}
 
diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c
index d1422f984f6e..7592176a8fa2 100644
--- a/drivers/acpi/acpica/dswscope.c
+++ b/drivers/acpi/acpica/dswscope.c
@@ -115,7 +115,7 @@ acpi_ds_scope_stack_push(struct acpi_namespace_node *node,
 				      acpi_ut_get_type_name(old_scope_info->
 							    common.value)));
 	} else {
-		ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, "[\\___] (%s)", "ROOT"));
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, ACPI_NAMESPACE_ROOT));
 	}
 
 	ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC,
@@ -166,14 +166,14 @@ acpi_status acpi_ds_scope_stack_pop(struct acpi_walk_state *walk_state)
 
 	new_scope_info = walk_state->scope_info;
 	if (new_scope_info) {
-		ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC,
-				      "[%4.4s] (%s)\n",
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, "[%4.4s] (%s)\n",
 				      acpi_ut_get_node_name(new_scope_info->
 							    scope.node),
 				      acpi_ut_get_type_name(new_scope_info->
 							    common.value)));
 	} else {
-		ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, "[\\___] (ROOT)\n"));
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, "%s\n",
+				      ACPI_NAMESPACE_ROOT));
 	}
 
 	acpi_ut_delete_generic_state(scope_info);
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index abbd59063906..e10fec99a182 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -634,6 +634,12 @@ acpi_ev_detect_gpe(struct acpi_namespace_node *gpe_device,
 
 	flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
 
+	if (!gpe_event_info) {
+		gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number);
+		if (!gpe_event_info)
+			goto error_exit;
+	}
+
 	/* Get the info block for the entire GPE register */
 
 	gpe_register_info = gpe_event_info->register_info;
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index c80e3bdf4805..b2d5f66cc1b0 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -639,6 +639,28 @@ ACPI_EXPORT_SYMBOL(acpi_get_gpe_status)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_gispatch_gpe
+ *
+ * PARAMETERS:  gpe_device          - Parent GPE Device. NULL for GPE0/GPE1
+ *              gpe_number          - GPE level within the GPE block
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Detect and dispatch a General Purpose Event to either a function
+ *              (e.g. EC) or method (e.g. _Lxx/_Exx) handler.
+ *
+ ******************************************************************************/
+void acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)
+{
+	ACPI_FUNCTION_TRACE(acpi_dispatch_gpe);
+
+	acpi_ev_detect_gpe(gpe_device, NULL, gpe_number);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_dispatch_gpe)
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_finish_gpe
  *
  * PARAMETERS:  gpe_device          - Namespace node for the GPE Block
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index 99d92cb32803..f85c6f3271f6 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -174,6 +174,13 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state,
 		return_ACPI_STATUS(status);
 	}
 
+	/* Complete the initialization/resolution of package objects */
+
+	status = acpi_ns_walk_namespace(ACPI_TYPE_PACKAGE, ACPI_ROOT_OBJECT,
+					ACPI_UINT32_MAX, 0,
+					acpi_ns_init_one_package, NULL, NULL,
+					NULL);
+
 	/* Parameter Data (optional) */
 
 	if (parameter_node) {
@@ -430,6 +437,13 @@ acpi_ex_load_op(union acpi_operand_object *obj_desc,
 		return_ACPI_STATUS(status);
 	}
 
+	/* Complete the initialization/resolution of package objects */
+
+	status = acpi_ns_walk_namespace(ACPI_TYPE_PACKAGE, ACPI_ROOT_OBJECT,
+					ACPI_UINT32_MAX, 0,
+					acpi_ns_init_one_package, NULL, NULL,
+					NULL);
+
 	/* Store the ddb_handle into the Target operand */
 
 	status = acpi_ex_store(ddb_handle, target, walk_state);
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 27a86ad55b58..3de794bcf8fa 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -390,14 +390,14 @@ acpi_status acpi_hw_clear_acpi_status(void)
 			  ACPI_BITMASK_ALL_FIXED_STATUS,
 			  ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address)));
 
-	lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+	lock_flags = acpi_os_acquire_raw_lock(acpi_gbl_hardware_lock);
 
 	/* Clear the fixed events in PM1 A/B */
 
 	status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS,
 					ACPI_BITMASK_ALL_FIXED_STATUS);
 
-	acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+	acpi_os_release_raw_lock(acpi_gbl_hardware_lock, lock_flags);
 
 	if (ACPI_FAILURE(status)) {
 		goto exit;
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 5d1396870bd0..6e39a771a56e 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -227,7 +227,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
-	lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+	lock_flags = acpi_os_acquire_raw_lock(acpi_gbl_hardware_lock);
 
 	/*
 	 * At this point, we know that the parent register is one of the
@@ -288,7 +288,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
 
 unlock_and_exit:
 
-	acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+	acpi_os_release_raw_lock(acpi_gbl_hardware_lock, lock_flags);
 	return_ACPI_STATUS(status);
 }
 
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 77f2b5f4948a..d77257d1c827 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -242,6 +242,58 @@ error_exit:
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_ns_init_one_package
+ *
+ * PARAMETERS:  obj_handle      - Node
+ *              level           - Current nesting level
+ *              context         - Not used
+ *              return_value    - Not used
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Callback from acpi_walk_namespace. Invoked for every package
+ *              within the namespace. Used during dynamic load of an SSDT.
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_ns_init_one_package(acpi_handle obj_handle,
+			 u32 level, void *context, void **return_value)
+{
+	acpi_status status;
+	union acpi_operand_object *obj_desc;
+	struct acpi_namespace_node *node =
+	    (struct acpi_namespace_node *)obj_handle;
+
+	obj_desc = acpi_ns_get_attached_object(node);
+	if (!obj_desc) {
+		return (AE_OK);
+	}
+
+	/* Exit if package is already initialized */
+
+	if (obj_desc->package.flags & AOPOBJ_DATA_VALID) {
+		return (AE_OK);
+	}
+
+	status = acpi_ds_get_package_arguments(obj_desc);
+	if (ACPI_FAILURE(status)) {
+		return (AE_OK);
+	}
+
+	status =
+	    acpi_ut_walk_package_tree(obj_desc, NULL,
+				      acpi_ds_init_package_element, NULL);
+	if (ACPI_FAILURE(status)) {
+		return (AE_OK);
+	}
+
+	obj_desc->package.flags |= AOPOBJ_DATA_VALID;
+	return (AE_OK);
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_ns_init_one_object
  *
  * PARAMETERS:  obj_handle      - Node
@@ -360,27 +412,11 @@ acpi_ns_init_one_object(acpi_handle obj_handle,
 
 	case ACPI_TYPE_PACKAGE:
 
-		info->package_init++;
-		status = acpi_ds_get_package_arguments(obj_desc);
-		if (ACPI_FAILURE(status)) {
-			break;
-		}
-
-		ACPI_DEBUG_PRINT_RAW((ACPI_DB_PARSE,
-				      "%s: Completing resolution of Package elements\n",
-				      ACPI_GET_FUNCTION_NAME));
+		/* Complete the initialization/resolution of the package object */
 
-		/*
-		 * Resolve all named references in package objects (and all
-		 * sub-packages). This action has been deferred until the entire
-		 * namespace has been loaded, in order to support external and
-		 * forward references from individual package elements (05/2017).
-		 */
-		status = acpi_ut_walk_package_tree(obj_desc, NULL,
-						   acpi_ds_init_package_element,
-						   NULL);
-
-		obj_desc->package.flags |= AOPOBJ_DATA_VALID;
+		info->package_init++;
+		status =
+		    acpi_ns_init_one_package(obj_handle, level, NULL, NULL);
 		break;
 
 	default:
diff --git a/drivers/acpi/acpica/rsdump.c b/drivers/acpi/acpica/rsdump.c
index b12a0b1cd9ce..6601e71b45e3 100644
--- a/drivers/acpi/acpica/rsdump.c
+++ b/drivers/acpi/acpica/rsdump.c
@@ -539,7 +539,7 @@ static void acpi_rs_out_title(const char *title)
 
 static void acpi_rs_dump_byte_list(u16 length, u8 * data)
 {
-	u8 i;
+	u16 i;
 
 	for (i = 0; i < length; i++) {
 		acpi_os_printf("%25s%2.2X : %2.2X\n", "Byte", i, data[i]);
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index c5085b7ae8c9..5f8e7b561c90 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -88,7 +88,7 @@ acpi_tb_install_table_with_override(struct acpi_table_desc *new_table_desc,
  * DESCRIPTION: This function is called to verify and install an ACPI table.
  *              When this function is called by "Load" or "LoadTable" opcodes,
  *              or by acpi_load_table() API, the "Reload" parameter is set.
- *              After sucessfully returning from this function, table is
+ *              After successfully returning from this function, table is
  *              "INSTALLED" but not "VALIDATED".
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c
index 148aeb84e561..fffa6f5ae59e 100644
--- a/drivers/acpi/acpica/utbuffer.c
+++ b/drivers/acpi/acpica/utbuffer.c
@@ -53,7 +53,7 @@ void acpi_ut_dump_buffer(u8 *buffer, u32 count, u32 display, u32 base_offset)
 
 		/* Print current offset */
 
-		acpi_os_printf("%6.4X: ", (base_offset + i));
+		acpi_os_printf("%8.4X: ", (base_offset + i));
 
 		/* Print 16 hex chars */
 
@@ -219,7 +219,7 @@ acpi_ut_dump_buffer_to_file(ACPI_FILE file,
 
 		/* Print current offset */
 
-		fprintf(file, "%6.4X: ", (base_offset + i));
+		fprintf(file, "%8.4X: ", (base_offset + i));
 
 		/* Print 16 hex chars */
 
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index d2d93e388f40..2e465e6a0ab6 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -52,7 +52,7 @@ acpi_status acpi_ut_mutex_initialize(void)
 		return_ACPI_STATUS (status);
 	}
 
-	status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
+	status = acpi_os_create_raw_lock(&acpi_gbl_hardware_lock);
 	if (ACPI_FAILURE (status)) {
 		return_ACPI_STATUS (status);
 	}
@@ -109,7 +109,7 @@ void acpi_ut_mutex_terminate(void)
 	/* Delete the spinlocks */
 
 	acpi_os_delete_lock(acpi_gbl_gpe_lock);
-	acpi_os_delete_lock(acpi_gbl_hardware_lock);
+	acpi_os_delete_raw_lock(acpi_gbl_hardware_lock);
 	acpi_os_delete_lock(acpi_gbl_reference_count_lock);
 
 	/* Delete the reader/writer lock */
diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c
index 5b78fe08d7d7..ae6d8cc18cec 100644
--- a/drivers/acpi/acpica/utobject.c
+++ b/drivers/acpi/acpica/utobject.c
@@ -8,6 +8,7 @@
  *****************************************************************************/
 
 #include <acpi/acpi.h>
+#include <linux/kmemleak.h>
 #include "accommon.h"
 #include "acnamesp.h"
 
@@ -70,6 +71,7 @@ union acpi_operand_object *acpi_ut_create_internal_object_dbg(const char
 	if (!object) {
 		return_PTR(NULL);
 	}
+	kmemleak_not_leak(object);
 
 	switch (type) {
 	case ACPI_TYPE_REGION:
diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c
index 35ffd8d51c65..a98c334c3bb7 100644
--- a/drivers/acpi/acpica/utprint.c
+++ b/drivers/acpi/acpica/utprint.c
@@ -470,6 +470,7 @@ int vsnprintf(char *string, acpi_size size, const char *format, va_list args)
 		case 'X':
 
 			type |= ACPI_FORMAT_UPPER;
+			/* FALLTHROUGH */
 
 		case 'x':
 
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index bd57a77bbcb2..5bef0b059406 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -141,7 +141,7 @@ void acpi_ut_repair_name(char *name)
 	 * Special case for the root node. This can happen if we get an
 	 * error during the execution of module-level code.
 	 */
-	if (ACPI_COMPARE_NAME(name, "\\___")) {
+	if (ACPI_COMPARE_NAME(name, ACPI_ROOT_PATHNAME)) {
 		return;
 	}
 
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 1efefe919555..02c6fd9caff7 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -481,7 +481,7 @@ static void ghes_do_proc(struct ghes *ghes,
 		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
 			struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
 
-			ghes_edac_report_mem_error(ghes, sev, mem_err);
+			ghes_edac_report_mem_error(sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
 			ghes_handle_memory_failure(gdata, sev);
@@ -1087,10 +1087,6 @@ static int ghes_probe(struct platform_device *ghes_dev)
 		goto err;
 	}
 
-	rc = ghes_edac_register(ghes, &ghes_dev->dev);
-	if (rc < 0)
-		goto err;
-
 	switch (generic->notify.type) {
 	case ACPI_HEST_NOTIFY_POLLED:
 		timer_setup(&ghes->timer, ghes_poll_func, TIMER_DEFERRABLE);
@@ -1102,14 +1098,14 @@ static int ghes_probe(struct platform_device *ghes_dev)
 		if (rc) {
 			pr_err(GHES_PFX "Failed to map GSI to IRQ for generic hardware error source: %d\n",
 			       generic->header.source_id);
-			goto err_edac_unreg;
+			goto err;
 		}
 		rc = request_irq(ghes->irq, ghes_irq_func, IRQF_SHARED,
 				 "GHES IRQ", ghes);
 		if (rc) {
 			pr_err(GHES_PFX "Failed to register IRQ for generic hardware error source: %d\n",
 			       generic->header.source_id);
-			goto err_edac_unreg;
+			goto err;
 		}
 		break;
 
@@ -1132,14 +1128,16 @@ static int ghes_probe(struct platform_device *ghes_dev)
 	default:
 		BUG();
 	}
+
 	platform_set_drvdata(ghes_dev, ghes);
 
+	ghes_edac_register(ghes, &ghes_dev->dev);
+
 	/* Handle any pending errors right away */
 	ghes_proc(ghes);
 
 	return 0;
-err_edac_unreg:
-	ghes_edac_unregister(ghes);
+
 err:
 	if (ghes) {
 		ghes_fini(ghes);
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index bdb24d636d9a..b0113a5802a3 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -74,6 +74,8 @@ static async_cookie_t async_cookie;
 static bool battery_driver_registered;
 static int battery_bix_broken_package;
 static int battery_notification_delay_ms;
+static int battery_ac_is_broken;
+static int battery_check_pmic = 1;
 static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -81,14 +83,6 @@ MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
 #ifdef CONFIG_ACPI_PROCFS_POWER
 extern struct proc_dir_entry *acpi_lock_battery_dir(void);
 extern void *acpi_unlock_battery_dir(struct proc_dir_entry *acpi_battery_dir);
-
-enum acpi_battery_files {
-	info_tag = 0,
-	state_tag,
-	alarm_tag,
-	ACPI_BATTERY_NUMFILES,
-};
-
 #endif
 
 static const struct acpi_device_id battery_device_ids[] = {
@@ -215,6 +209,20 @@ static bool acpi_battery_is_degraded(struct acpi_battery *battery)
 		battery->full_charge_capacity < battery->design_capacity;
 }
 
+static int acpi_battery_handle_discharging(struct acpi_battery *battery)
+{
+	/*
+	 * Some devices wrongly report discharging if the battery's charge level
+	 * was above the device's start charging threshold atm the AC adapter
+	 * was plugged in and the device thus did not start a new charge cycle.
+	 */
+	if ((battery_ac_is_broken || power_supply_is_system_supplied()) &&
+	    battery->rate_now == 0)
+		return POWER_SUPPLY_STATUS_NOT_CHARGING;
+
+	return POWER_SUPPLY_STATUS_DISCHARGING;
+}
+
 static int acpi_battery_get_property(struct power_supply *psy,
 				     enum power_supply_property psp,
 				     union power_supply_propval *val)
@@ -230,7 +238,7 @@ static int acpi_battery_get_property(struct power_supply *psy,
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
 		if (battery->state & ACPI_BATTERY_STATE_DISCHARGING)
-			val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+			val->intval = acpi_battery_handle_discharging(battery);
 		else if (battery->state & ACPI_BATTERY_STATE_CHARGING)
 			val->intval = POWER_SUPPLY_STATUS_CHARGING;
 		else if (acpi_battery_is_charged(battery))
@@ -985,9 +993,10 @@ static const char *acpi_battery_units(const struct acpi_battery *battery)
 		"mA" : "mW";
 }
 
-static int acpi_battery_print_info(struct seq_file *seq, int result)
+static int acpi_battery_info_proc_show(struct seq_file *seq, void *offset)
 {
 	struct acpi_battery *battery = seq->private;
+	int result = acpi_battery_update(battery, false);
 
 	if (result)
 		goto end;
@@ -1041,9 +1050,10 @@ static int acpi_battery_print_info(struct seq_file *seq, int result)
 	return result;
 }
 
-static int acpi_battery_print_state(struct seq_file *seq, int result)
+static int acpi_battery_state_proc_show(struct seq_file *seq, void *offset)
 {
 	struct acpi_battery *battery = seq->private;
+	int result = acpi_battery_update(battery, false);
 
 	if (result)
 		goto end;
@@ -1088,9 +1098,10 @@ static int acpi_battery_print_state(struct seq_file *seq, int result)
 	return result;
 }
 
-static int acpi_battery_print_alarm(struct seq_file *seq, int result)
+static int acpi_battery_alarm_proc_show(struct seq_file *seq, void *offset)
 {
 	struct acpi_battery *battery = seq->private;
+	int result = acpi_battery_update(battery, false);
 
 	if (result)
 		goto end;
@@ -1142,82 +1153,22 @@ static ssize_t acpi_battery_write_alarm(struct file *file,
 	return result;
 }
 
-typedef int(*print_func)(struct seq_file *seq, int result);
-
-static print_func acpi_print_funcs[ACPI_BATTERY_NUMFILES] = {
-	acpi_battery_print_info,
-	acpi_battery_print_state,
-	acpi_battery_print_alarm,
-};
-
-static int acpi_battery_read(int fid, struct seq_file *seq)
+static int acpi_battery_alarm_proc_open(struct inode *inode, struct file *file)
 {
-	struct acpi_battery *battery = seq->private;
-	int result = acpi_battery_update(battery, false);
-	return acpi_print_funcs[fid](seq, result);
-}
-
-#define DECLARE_FILE_FUNCTIONS(_name) \
-static int acpi_battery_read_##_name(struct seq_file *seq, void *offset) \
-{ \
-	return acpi_battery_read(_name##_tag, seq); \
-} \
-static int acpi_battery_##_name##_open_fs(struct inode *inode, struct file *file) \
-{ \
-	return single_open(file, acpi_battery_read_##_name, PDE_DATA(inode)); \
+	return single_open(file, acpi_battery_alarm_proc_show, PDE_DATA(inode));
 }
 
-DECLARE_FILE_FUNCTIONS(info);
-DECLARE_FILE_FUNCTIONS(state);
-DECLARE_FILE_FUNCTIONS(alarm);
-
-#undef DECLARE_FILE_FUNCTIONS
-
-#define FILE_DESCRIPTION_RO(_name) \
-	{ \
-	.name = __stringify(_name), \
-	.mode = S_IRUGO, \
-	.ops = { \
-		.open = acpi_battery_##_name##_open_fs, \
-		.read = seq_read, \
-		.llseek = seq_lseek, \
-		.release = single_release, \
-		.owner = THIS_MODULE, \
-		}, \
-	}
-
-#define FILE_DESCRIPTION_RW(_name) \
-	{ \
-	.name = __stringify(_name), \
-	.mode = S_IFREG | S_IRUGO | S_IWUSR, \
-	.ops = { \
-		.open = acpi_battery_##_name##_open_fs, \
-		.read = seq_read, \
-		.llseek = seq_lseek, \
-		.write = acpi_battery_write_##_name, \
-		.release = single_release, \
-		.owner = THIS_MODULE, \
-		}, \
-	}
-
-static const struct battery_file {
-	struct file_operations ops;
-	umode_t mode;
-	const char *name;
-} acpi_battery_file[] = {
-	FILE_DESCRIPTION_RO(info),
-	FILE_DESCRIPTION_RO(state),
-	FILE_DESCRIPTION_RW(alarm),
+static const struct file_operations acpi_battery_alarm_fops = {
+	.owner		= THIS_MODULE,
+	.open		= acpi_battery_alarm_proc_open,
+	.read		= seq_read,
+	.write		= acpi_battery_write_alarm,
+	.llseek		= seq_lseek,
+	.release	= single_release,
 };
 
-#undef FILE_DESCRIPTION_RO
-#undef FILE_DESCRIPTION_RW
-
 static int acpi_battery_add_fs(struct acpi_device *device)
 {
-	struct proc_dir_entry *entry = NULL;
-	int i;
-
 	printk(KERN_WARNING PREFIX "Deprecated procfs I/F for battery is loaded,"
 			" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
 	if (!acpi_device_dir(device)) {
@@ -1227,28 +1178,24 @@ static int acpi_battery_add_fs(struct acpi_device *device)
 			return -ENODEV;
 	}
 
-	for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i) {
-		entry = proc_create_data(acpi_battery_file[i].name,
-					 acpi_battery_file[i].mode,
-					 acpi_device_dir(device),
-					 &acpi_battery_file[i].ops,
-					 acpi_driver_data(device));
-		if (!entry)
-			return -ENODEV;
-	}
+	if (!proc_create_single_data("info", S_IRUGO, acpi_device_dir(device),
+			acpi_battery_info_proc_show, acpi_driver_data(device)))
+		return -ENODEV;
+	if (!proc_create_single_data("state", S_IRUGO, acpi_device_dir(device),
+			acpi_battery_state_proc_show, acpi_driver_data(device)))
+		return -ENODEV;
+	if (!proc_create_data("alarm", S_IFREG | S_IRUGO | S_IWUSR,
+			acpi_device_dir(device), &acpi_battery_alarm_fops,
+			acpi_driver_data(device)))
+		return -ENODEV;
 	return 0;
 }
 
 static void acpi_battery_remove_fs(struct acpi_device *device)
 {
-	int i;
 	if (!acpi_device_dir(device))
 		return;
-	for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i)
-		remove_proc_entry(acpi_battery_file[i].name,
-				  acpi_device_dir(device));
-
-	remove_proc_entry(acpi_device_bid(device), acpi_battery_dir);
+	remove_proc_subtree(acpi_device_bid(device), acpi_battery_dir);
 	acpi_device_dir(device) = NULL;
 }
 
@@ -1332,23 +1279,64 @@ battery_notification_delay_quirk(const struct dmi_system_id *d)
 	return 0;
 }
 
+static int __init
+battery_ac_is_broken_quirk(const struct dmi_system_id *d)
+{
+	battery_ac_is_broken = 1;
+	return 0;
+}
+
+static int __init
+battery_do_not_check_pmic_quirk(const struct dmi_system_id *d)
+{
+	battery_check_pmic = 0;
+	return 0;
+}
+
 static const struct dmi_system_id bat_dmi_table[] __initconst = {
 	{
+		/* NEC LZ750/LS */
 		.callback = battery_bix_broken_package_quirk,
-		.ident = "NEC LZ750/LS",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"),
 		},
 	},
 	{
+		/* Acer Aspire V5-573G */
 		.callback = battery_notification_delay_quirk,
-		.ident = "Acer Aspire V5-573G",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-573G"),
 		},
 	},
+	{
+		/* Point of View mobii wintab p800w */
+		.callback = battery_ac_is_broken_quirk,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+			DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+			DMI_MATCH(DMI_BIOS_VERSION, "3BAIR1013"),
+			/* Above matches are too generic, add bios-date match */
+			DMI_MATCH(DMI_BIOS_DATE, "08/22/2014"),
+		},
+	},
+	{
+		/* ECS EF20EA */
+		.callback = battery_do_not_check_pmic_quirk,
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "EF20EA"),
+		},
+	},
+	{
+		/* Lenovo Ideapad Miix 320 */
+		.callback = battery_do_not_check_pmic_quirk,
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80XF"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 320-10ICR"),
+		},
+	},
 	{},
 };
 
@@ -1488,16 +1476,18 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 	unsigned int i;
 	int result;
 
-	for (i = 0; i < ARRAY_SIZE(acpi_battery_blacklist); i++)
-		if (acpi_dev_present(acpi_battery_blacklist[i], "1", -1)) {
-			pr_info(PREFIX ACPI_BATTERY_DEVICE_NAME
-				": found native %s PMIC, not loading\n",
-				acpi_battery_blacklist[i]);
-			return;
-		}
-
 	dmi_check_system(bat_dmi_table);
 
+	if (battery_check_pmic) {
+		for (i = 0; i < ARRAY_SIZE(acpi_battery_blacklist); i++)
+			if (acpi_dev_present(acpi_battery_blacklist[i], "1", -1)) {
+				pr_info(PREFIX ACPI_BATTERY_DEVICE_NAME
+					": found native %s PMIC, not loading\n",
+					acpi_battery_blacklist[i]);
+				return;
+			}
+	}
+
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	acpi_battery_dir = acpi_lock_battery_dir();
 	if (!acpi_battery_dir)
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index e1eee7a60fad..2345a5ee2dbb 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -263,19 +263,6 @@ static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
 	return 0;
 }
 
-static int acpi_button_state_open_fs(struct inode *inode, struct file *file)
-{
-	return single_open(file, acpi_button_state_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations acpi_button_state_fops = {
-	.owner = THIS_MODULE,
-	.open = acpi_button_state_open_fs,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 static int acpi_button_add_fs(struct acpi_device *device)
 {
 	struct acpi_button *button = acpi_driver_data(device);
@@ -311,9 +298,9 @@ static int acpi_button_add_fs(struct acpi_device *device)
 	}
 
 	/* create /proc/acpi/button/lid/LID/state */
-	entry = proc_create_data(ACPI_BUTTON_FILE_STATE,
-				 S_IRUGO, acpi_device_dir(device),
-				 &acpi_button_state_fops, device);
+	entry = proc_create_single_data(ACPI_BUTTON_FILE_STATE, S_IRUGO,
+			acpi_device_dir(device), acpi_button_state_seq_show,
+			device);
 	if (!entry) {
 		ret = -ENODEV;
 		goto remove_dev_dir;
@@ -635,4 +622,26 @@ module_param_call(lid_init_state,
 		  NULL, 0644);
 MODULE_PARM_DESC(lid_init_state, "Behavior for reporting LID initial state");
 
-module_acpi_driver(acpi_button_driver);
+static int acpi_button_register_driver(struct acpi_driver *driver)
+{
+	/*
+	 * Modules such as nouveau.ko and i915.ko have a link time dependency
+	 * on acpi_lid_open(), and would therefore not be loadable on ACPI
+	 * capable kernels booted in non-ACPI mode if the return value of
+	 * acpi_bus_register_driver() is returned from here with ACPI disabled
+	 * when this driver is built as a module.
+	 */
+	if (acpi_disabled)
+		return 0;
+
+	return acpi_bus_register_driver(driver);
+}
+
+static void acpi_button_unregister_driver(struct acpi_driver *driver)
+{
+	if (!acpi_disabled)
+		acpi_bus_unregister_driver(driver);
+}
+
+module_driver(acpi_button_driver, acpi_button_register_driver,
+	       acpi_button_unregister_driver);
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 735c74a4cbdb..d9ce4b162e2c 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -39,6 +39,7 @@
 
 #include <linux/cpufreq.h>
 #include <linux/delay.h>
+#include <linux/iopoll.h>
 #include <linux/ktime.h>
 #include <linux/rwsem.h>
 #include <linux/wait.h>
@@ -49,7 +50,7 @@ struct cppc_pcc_data {
 	struct mbox_chan *pcc_channel;
 	void __iomem *pcc_comm_addr;
 	bool pcc_channel_acquired;
-	ktime_t deadline;
+	unsigned int deadline_us;
 	unsigned int pcc_mpar, pcc_mrtt, pcc_nominal;
 
 	bool pending_pcc_write_cmd;	/* Any pending/batched PCC write cmds? */
@@ -156,6 +157,9 @@ show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, highest_perf);
 show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_perf);
 show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_perf);
 show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_nonlinear_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_freq);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_freq);
+
 show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf);
 show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time);
 
@@ -183,6 +187,8 @@ static struct attribute *cppc_attrs[] = {
 	&lowest_perf.attr,
 	&lowest_nonlinear_perf.attr,
 	&nominal_perf.attr,
+	&nominal_freq.attr,
+	&lowest_freq.attr,
 	NULL
 };
 
@@ -193,42 +199,31 @@ static struct kobj_type cppc_ktype = {
 
 static int check_pcc_chan(int pcc_ss_id, bool chk_err_bit)
 {
-	int ret = -EIO, status = 0;
+	int ret, status;
 	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
 	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
 		pcc_ss_data->pcc_comm_addr;
-	ktime_t next_deadline = ktime_add(ktime_get(),
-					  pcc_ss_data->deadline);
 
 	if (!pcc_ss_data->platform_owns_pcc)
 		return 0;
 
-	/* Retry in case the remote processor was too slow to catch up. */
-	while (!ktime_after(ktime_get(), next_deadline)) {
-		/*
-		 * Per spec, prior to boot the PCC space wil be initialized by
-		 * platform and should have set the command completion bit when
-		 * PCC can be used by OSPM
-		 */
-		status = readw_relaxed(&generic_comm_base->status);
-		if (status & PCC_CMD_COMPLETE_MASK) {
-			ret = 0;
-			if (chk_err_bit && (status & PCC_ERROR_MASK))
-				ret = -EIO;
-			break;
-		}
-		/*
-		 * Reducing the bus traffic in case this loop takes longer than
-		 * a few retries.
-		 */
-		udelay(3);
-	}
+	/*
+	 * Poll PCC status register every 3us(delay_us) for maximum of
+	 * deadline_us(timeout_us) until PCC command complete bit is set(cond)
+	 */
+	ret = readw_relaxed_poll_timeout(&generic_comm_base->status, status,
+					status & PCC_CMD_COMPLETE_MASK, 3,
+					pcc_ss_data->deadline_us);
 
-	if (likely(!ret))
+	if (likely(!ret)) {
 		pcc_ss_data->platform_owns_pcc = false;
-	else
-		pr_err("PCC check channel failed for ss: %d. Status=%x\n",
-		       pcc_ss_id, status);
+		if (chk_err_bit && (status & PCC_ERROR_MASK))
+			ret = -EIO;
+	}
+
+	if (unlikely(ret))
+		pr_err("PCC check channel failed for ss: %d. ret=%d\n",
+		       pcc_ss_id, ret);
 
 	return ret;
 }
@@ -580,7 +575,7 @@ static int register_pcc_channel(int pcc_ss_idx)
 		 * So add an arbitrary amount of wait on top of Nominal.
 		 */
 		usecs_lat = NUM_RETRIES * cppc_ss->latency;
-		pcc_data[pcc_ss_idx]->deadline = ns_to_ktime(usecs_lat * NSEC_PER_USEC);
+		pcc_data[pcc_ss_idx]->deadline_us = usecs_lat;
 		pcc_data[pcc_ss_idx]->pcc_mrtt = cppc_ss->min_turnaround_time;
 		pcc_data[pcc_ss_idx]->pcc_mpar = cppc_ss->max_access_rate;
 		pcc_data[pcc_ss_idx]->pcc_nominal = cppc_ss->latency;
@@ -613,7 +608,6 @@ bool __weak cpc_ffh_supported(void)
 	return false;
 }
 
-
 /**
  * pcc_data_alloc() - Allocate the pcc_data memory for pcc subspace
  *
@@ -641,6 +635,34 @@ int pcc_data_alloc(int pcc_ss_id)
 
 	return 0;
 }
+
+/* Check if CPPC revision + num_ent combination is supported */
+static bool is_cppc_supported(int revision, int num_ent)
+{
+	int expected_num_ent;
+
+	switch (revision) {
+	case CPPC_V2_REV:
+		expected_num_ent = CPPC_V2_NUM_ENT;
+		break;
+	case CPPC_V3_REV:
+		expected_num_ent = CPPC_V3_NUM_ENT;
+		break;
+	default:
+		pr_debug("Firmware exports unsupported CPPC revision: %d\n",
+			revision);
+		return false;
+	}
+
+	if (expected_num_ent != num_ent) {
+		pr_debug("Firmware exports %d entries. Expected: %d for CPPC rev:%d\n",
+			num_ent, expected_num_ent, revision);
+		return false;
+	}
+
+	return true;
+}
+
 /*
  * An example CPC table looks like the following.
  *
@@ -731,14 +753,6 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 				cpc_obj->type);
 		goto out_free;
 	}
-
-	/* Only support CPPCv2. Bail otherwise. */
-	if (num_ent != CPPC_NUM_ENT) {
-		pr_debug("Firmware exports %d entries. Expected: %d\n",
-				num_ent, CPPC_NUM_ENT);
-		goto out_free;
-	}
-
 	cpc_ptr->num_entries = num_ent;
 
 	/* Second entry should be revision. */
@@ -750,12 +764,10 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 				cpc_obj->type);
 		goto out_free;
 	}
+	cpc_ptr->version = cpc_rev;
 
-	if (cpc_rev != CPPC_REV) {
-		pr_debug("Firmware exports revision:%d. Expected:%d\n",
-				cpc_rev, CPPC_REV);
+	if (!is_cppc_supported(cpc_rev, num_ent))
 		goto out_free;
-	}
 
 	/* Iterate through remaining entries in _CPC */
 	for (i = 2; i < num_ent; i++) {
@@ -808,6 +820,18 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 		}
 	}
 	per_cpu(cpu_pcc_subspace_idx, pr->id) = pcc_subspace_id;
+
+	/*
+	 * Initialize the remaining cpc_regs as unsupported.
+	 * Example: In case FW exposes CPPC v2, the below loop will initialize
+	 * LOWEST_FREQ and NOMINAL_FREQ regs as unsupported
+	 */
+	for (i = num_ent - 2; i < MAX_CPC_REG_ENT; i++) {
+		cpc_ptr->cpc_regs[i].type = ACPI_TYPE_INTEGER;
+		cpc_ptr->cpc_regs[i].cpc_entry.int_value = 0;
+	}
+
+
 	/* Store CPU Logical ID */
 	cpc_ptr->cpu_id = pr->id;
 
@@ -1037,26 +1061,34 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 {
 	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
 	struct cpc_register_resource *highest_reg, *lowest_reg,
-		*lowest_non_linear_reg, *nominal_reg;
-	u64 high, low, nom, min_nonlinear;
+		*lowest_non_linear_reg, *nominal_reg,
+		*low_freq_reg = NULL, *nom_freq_reg = NULL;
+	u64 high, low, nom, min_nonlinear, low_f = 0, nom_f = 0;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-	struct cppc_pcc_data *pcc_ss_data;
+	struct cppc_pcc_data *pcc_ss_data = NULL;
 	int ret = 0, regs_in_pcc = 0;
 
-	if (!cpc_desc || pcc_ss_id < 0) {
+	if (!cpc_desc) {
 		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
 		return -ENODEV;
 	}
 
-	pcc_ss_data = pcc_data[pcc_ss_id];
 	highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
 	lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
 	lowest_non_linear_reg = &cpc_desc->cpc_regs[LOW_NON_LINEAR_PERF];
 	nominal_reg = &cpc_desc->cpc_regs[NOMINAL_PERF];
+	low_freq_reg = &cpc_desc->cpc_regs[LOWEST_FREQ];
+	nom_freq_reg = &cpc_desc->cpc_regs[NOMINAL_FREQ];
 
 	/* Are any of the regs PCC ?*/
 	if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) ||
-		CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg)) {
+		CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg) ||
+		CPC_IN_PCC(low_freq_reg) || CPC_IN_PCC(nom_freq_reg)) {
+		if (pcc_ss_id < 0) {
+			pr_debug("Invalid pcc_ss_id\n");
+			return -ENODEV;
+		}
+		pcc_ss_data = pcc_data[pcc_ss_id];
 		regs_in_pcc = 1;
 		down_write(&pcc_ss_data->pcc_lock);
 		/* Ring doorbell once to update PCC subspace */
@@ -1081,6 +1113,17 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 	if (!high || !low || !nom || !min_nonlinear)
 		ret = -EFAULT;
 
+	/* Read optional lowest and nominal frequencies if present */
+	if (CPC_SUPPORTED(low_freq_reg))
+		cpc_read(cpunum, low_freq_reg, &low_f);
+
+	if (CPC_SUPPORTED(nom_freq_reg))
+		cpc_read(cpunum, nom_freq_reg, &nom_f);
+
+	perf_caps->lowest_freq = low_f;
+	perf_caps->nominal_freq = nom_f;
+
+
 out_err:
 	if (regs_in_pcc)
 		up_write(&pcc_ss_data->pcc_lock);
@@ -1101,16 +1144,15 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 	struct cpc_register_resource *delivered_reg, *reference_reg,
 		*ref_perf_reg, *ctr_wrap_reg;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-	struct cppc_pcc_data *pcc_ss_data;
+	struct cppc_pcc_data *pcc_ss_data = NULL;
 	u64 delivered, reference, ref_perf, ctr_wrap_time;
 	int ret = 0, regs_in_pcc = 0;
 
-	if (!cpc_desc || pcc_ss_id < 0) {
+	if (!cpc_desc) {
 		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
 		return -ENODEV;
 	}
 
-	pcc_ss_data = pcc_data[pcc_ss_id];
 	delivered_reg = &cpc_desc->cpc_regs[DELIVERED_CTR];
 	reference_reg = &cpc_desc->cpc_regs[REFERENCE_CTR];
 	ref_perf_reg = &cpc_desc->cpc_regs[REFERENCE_PERF];
@@ -1126,6 +1168,11 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 	/* Are any of the regs PCC ?*/
 	if (CPC_IN_PCC(delivered_reg) || CPC_IN_PCC(reference_reg) ||
 		CPC_IN_PCC(ctr_wrap_reg) || CPC_IN_PCC(ref_perf_reg)) {
+		if (pcc_ss_id < 0) {
+			pr_debug("Invalid pcc_ss_id\n");
+			return -ENODEV;
+		}
+		pcc_ss_data = pcc_data[pcc_ss_id];
 		down_write(&pcc_ss_data->pcc_lock);
 		regs_in_pcc = 1;
 		/* Ring doorbell once to update PCC subspace */
@@ -1176,15 +1223,14 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
 	struct cpc_register_resource *desired_reg;
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
-	struct cppc_pcc_data *pcc_ss_data;
+	struct cppc_pcc_data *pcc_ss_data = NULL;
 	int ret = 0;
 
-	if (!cpc_desc || pcc_ss_id < 0) {
+	if (!cpc_desc) {
 		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
 		return -ENODEV;
 	}
 
-	pcc_ss_data = pcc_data[pcc_ss_id];
 	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
 
 	/*
@@ -1195,6 +1241,11 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	 * achieve that goal here
 	 */
 	if (CPC_IN_PCC(desired_reg)) {
+		if (pcc_ss_id < 0) {
+			pr_debug("Invalid pcc_ss_id\n");
+			return -ENODEV;
+		}
+		pcc_ss_data = pcc_data[pcc_ss_id];
 		down_read(&pcc_ss_data->pcc_lock); /* BEGIN Phase-I */
 		if (pcc_ss_data->platform_owns_pcc) {
 			ret = check_pcc_chan(pcc_ss_id, false);
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 3d96e4da2d98..a7c2673ffd36 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -1257,10 +1257,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	struct acpi_device *adev = ACPI_COMPANION(dev);
 
 	if (!adev)
-		return -ENODEV;
-
-	if (dev->pm_domain)
-		return -EEXIST;
+		return 0;
 
 	/*
 	 * Only attach the power domain to the first device if the
@@ -1268,7 +1265,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	 * management twice.
 	 */
 	if (!acpi_device_is_first_physical_node(adev, dev))
-		return -EBUSY;
+		return 0;
 
 	acpi_add_pm_notifier(adev, dev, acpi_pm_notify_work_func);
 	dev_pm_domain_set(dev, &acpi_general_pm_domain);
@@ -1278,7 +1275,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	}
 
 	dev->pm_domain->detach = acpi_dev_pm_detach;
-	return 0;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
 #endif /* CONFIG_PM */
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 30a572956557..bb94cf0731fe 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1034,6 +1034,12 @@ void acpi_ec_unblock_transactions(void)
 		acpi_ec_start(first_ec, true);
 }
 
+void acpi_ec_dispatch_gpe(void)
+{
+	if (first_ec)
+		acpi_dispatch_gpe(NULL, first_ec->gpe);
+}
+
 /* --------------------------------------------------------------------------
                                 Event Management
    -------------------------------------------------------------------------- */
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 1d0a501bc7f0..530a3f675490 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -188,6 +188,7 @@ int acpi_ec_ecdt_probe(void);
 int acpi_ec_dsdt_probe(void);
 void acpi_ec_block_transactions(void);
 void acpi_ec_unblock_transactions(void);
+void acpi_ec_dispatch_gpe(void);
 int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
diff --git a/drivers/acpi/reboot.c b/drivers/acpi/reboot.c
index 71769fd687b2..6fa9c2a4cfe9 100644
--- a/drivers/acpi/reboot.c
+++ b/drivers/acpi/reboot.c
@@ -8,8 +8,8 @@ void acpi_reboot(void)
 {
 	struct acpi_generic_address *rr;
 	struct pci_bus *bus0;
-	u8 reset_value;
 	unsigned int devfn;
+	u8 reset_value;
 
 	if (acpi_disabled)
 		return;
@@ -40,7 +40,7 @@ void acpi_reboot(void)
 		/* Form PCI device/function pair. */
 		devfn = PCI_DEVFN((rr->address >> 32) & 0xffff,
 				  (rr->address >> 16) & 0xffff);
-		printk(KERN_DEBUG "Resetting with ACPI PCI RESET_REG.");
+		printk(KERN_DEBUG "Resetting with ACPI PCI RESET_REG.\n");
 		/* Write the value that resets us. */
 		pci_bus_write_config_byte(bus0, devfn,
 				(rr->address & 0xffff), reset_value);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index cc234e6a6297..970dd87d347c 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2166,10 +2166,10 @@ int __init acpi_scan_init(void)
 	acpi_cmos_rtc_init();
 	acpi_container_init();
 	acpi_memory_hotplug_init();
+	acpi_watchdog_init();
 	acpi_pnp_init();
 	acpi_int340x_thermal_init();
 	acpi_amba_init();
-	acpi_watchdog_init();
 	acpi_init_lpit();
 
 	acpi_scan_add_handler(&generic_device_handler);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 99a1a650326d..5d0486f1cfcd 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -364,6 +364,19 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
 		},
 	},
+	/*
+	 * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
+	 * the Low Power S0 Idle firmware interface (see
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=199057).
+	 */
+	{
+	.callback = init_no_lps0,
+	.ident = "ThinkPad X1 Tablet(2016)",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"),
+		},
+	},
 	{},
 };
 
@@ -976,6 +989,13 @@ static void acpi_s2idle_wake(void)
 	    !irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq))) {
 		pm_system_cancel_wakeup();
 		s2idle_wakeup = true;
+		/*
+		 * On some platforms with the LPS0 _DSM device noirq resume
+		 * takes too much time for EC wakeup events to survive, so look
+		 * for them now.
+		 */
+		if (lps0_device_handle)
+			acpi_ec_dispatch_gpe();
 	}
 }
 
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 849c4fb19b03..4a3410aa6540 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -222,7 +222,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
  * acpi_parse_entries_array - for each proc_num find a suitable subtable
  *
  * @id: table id (for debugging purposes)
- * @table_size: single entry size
+ * @table_size: size of the root table
  * @table_header: where does the table start?
  * @proc: array of acpi_subtable_proc struct containing entry id
  *        and associated handler with it
@@ -233,6 +233,11 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
  * on it. Assumption is that there's only single handler for particular
  * entry id.
  *
+ * The table_size is not the size of the complete ACPI table (the length
+ * field in the header struct), but only the size of the root table; i.e.,
+ * the offset from the very first byte of the complete ACPI table, to the
+ * first byte of the very first subtable.
+ *
  * On success returns sum of all matching entries for all proc handlers.
  * Otherwise, -ENODEV or -EINVAL is returned.
  */
@@ -400,7 +405,7 @@ int __init acpi_table_parse(char *id, acpi_tbl_table_handler handler)
 		return -ENODEV;
 }
 
-/* 
+/*
  * The BIOS is supposed to supply a single APIC/MADT,
  * but some report two.  Provide a knob to use either.
  * (don't you wish instance 0 and 1 were not the same?)
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 594c228d2f02..41b706403ef7 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -20,6 +20,7 @@
 #include <linux/sizes.h>
 #include <linux/limits.h>
 #include <linux/clk/clk-conf.h>
+#include <linux/platform_device.h>
 
 #include <asm/irq.h>
 
@@ -69,11 +70,12 @@ static ssize_t driver_override_show(struct device *_dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct amba_device *dev = to_amba_device(_dev);
+	ssize_t len;
 
-	if (!dev->driver_override)
-		return 0;
-
-	return sprintf(buf, "%s\n", dev->driver_override);
+	device_lock(_dev);
+	len = sprintf(buf, "%s\n", dev->driver_override);
+	device_unlock(_dev);
+	return len;
 }
 
 static ssize_t driver_override_store(struct device *_dev,
@@ -81,9 +83,10 @@ static ssize_t driver_override_store(struct device *_dev,
 				     const char *buf, size_t count)
 {
 	struct amba_device *dev = to_amba_device(_dev);
-	char *driver_override, *old = dev->driver_override, *cp;
+	char *driver_override, *old, *cp;
 
-	if (count > PATH_MAX)
+	/* We need to keep extra room for a newline */
+	if (count >= (PAGE_SIZE - 1))
 		return -EINVAL;
 
 	driver_override = kstrndup(buf, count, GFP_KERNEL);
@@ -94,12 +97,15 @@ static ssize_t driver_override_store(struct device *_dev,
 	if (cp)
 		*cp = '\0';
 
+	device_lock(_dev);
+	old = dev->driver_override;
 	if (strlen(driver_override)) {
 		dev->driver_override = driver_override;
 	} else {
-	       kfree(driver_override);
-	       dev->driver_override = NULL;
+		kfree(driver_override);
+		dev->driver_override = NULL;
 	}
+	device_unlock(_dev);
 
 	kfree(old);
 
@@ -188,15 +194,18 @@ static const struct dev_pm_ops amba_pm = {
 /*
  * Primecells are part of the Advanced Microcontroller Bus Architecture,
  * so we call the bus "amba".
+ * DMA configuration for platform and AMBA bus is same. So here we reuse
+ * platform's DMA config routine.
  */
 struct bus_type amba_bustype = {
 	.name		= "amba",
 	.dev_groups	= amba_dev_groups,
 	.match		= amba_match,
 	.uevent		= amba_uevent,
+	.dma_configure	= platform_dma_configure,
 	.pm		= &amba_pm,
-	.force_dma	= true,
 };
+EXPORT_SYMBOL_GPL(amba_bustype);
 
 static int __init amba_init(void)
 {
@@ -243,7 +252,7 @@ static int amba_probe(struct device *dev)
 			break;
 
 		ret = dev_pm_domain_attach(dev, true);
-		if (ret == -EPROBE_DEFER)
+		if (ret)
 			break;
 
 		ret = amba_get_enable_pclk(pcdev);
@@ -370,7 +379,7 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 	}
 
 	ret = dev_pm_domain_attach(&dev->dev, true);
-	if (ret == -EPROBE_DEFER) {
+	if (ret) {
 		iounmap(tmp);
 		goto err_release;
 	}
diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig
index 7dce3795b887..ee4880bfdcdc 100644
--- a/drivers/android/Kconfig
+++ b/drivers/android/Kconfig
@@ -10,7 +10,7 @@ if ANDROID
 
 config ANDROID_BINDER_IPC
 	bool "Android Binder IPC Driver"
-	depends on MMU
+	depends on MMU && !M68K
 	default n
 	---help---
 	  Binder is used in Android for both communication between processes,
@@ -32,19 +32,6 @@ config ANDROID_BINDER_DEVICES
 	  created. Each binder device has its own context manager, and is
 	  therefore logically separated from the other devices.
 
-config ANDROID_BINDER_IPC_32BIT
-	bool "Use old (Android 4.4 and earlier) 32-bit binder API"
-	depends on !64BIT && ANDROID_BINDER_IPC
-	default y
-	---help---
-	  The Binder API has been changed to support both 32 and 64bit
-	  applications in a mixed environment.
-
-	  Enable this to support an old 32-bit Android user-space (v4.4 and
-	  earlier).
-
-	  Note that enabling this will break newer Android user-space.
-
 config ANDROID_BINDER_IPC_SELFTEST
 	bool "Android Binder IPC Driver Selftest"
 	depends on ANDROID_BINDER_IPC
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 764b63a5aade..95283f3bb51c 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -72,10 +72,6 @@
 #include <linux/security.h>
 #include <linux/spinlock.h>
 
-#ifdef CONFIG_ANDROID_BINDER_IPC_32BIT
-#define BINDER_IPC_32BIT 1
-#endif
-
 #include <uapi/linux/android/binder.h>
 #include "binder_alloc.h"
 #include "binder_trace.h"
@@ -2058,8 +2054,8 @@ static size_t binder_validate_object(struct binder_buffer *buffer, u64 offset)
 	struct binder_object_header *hdr;
 	size_t object_size = 0;
 
-	if (offset > buffer->data_size - sizeof(*hdr) ||
-	    buffer->data_size < sizeof(*hdr) ||
+	if (buffer->data_size < sizeof(*hdr) ||
+	    offset > buffer->data_size - sizeof(*hdr) ||
 	    !IS_ALIGNED(offset, sizeof(u32)))
 		return 0;
 
@@ -2839,6 +2835,14 @@ static void binder_transaction(struct binder_proc *proc,
 			else
 				return_error = BR_DEAD_REPLY;
 			mutex_unlock(&context->context_mgr_node_lock);
+			if (target_node && target_proc == proc) {
+				binder_user_error("%d:%d got transaction to context manager from process owning it\n",
+						  proc->pid, thread->pid);
+				return_error = BR_FAILED_REPLY;
+				return_error_param = -EINVAL;
+				return_error_line = __LINE__;
+				goto err_invalid_target_handle;
+			}
 		}
 		if (!target_node) {
 			/*
@@ -3917,10 +3921,11 @@ retry:
 			binder_inner_proc_unlock(proc);
 			if (put_user(e->cmd, (uint32_t __user *)ptr))
 				return -EFAULT;
+			cmd = e->cmd;
 			e->cmd = BR_OK;
 			ptr += sizeof(uint32_t);
 
-			binder_stat_br(proc, thread, e->cmd);
+			binder_stat_br(proc, thread, cmd);
 		} break;
 		case BINDER_WORK_TRANSACTION_COMPLETE: {
 			binder_inner_proc_unlock(proc);
@@ -4688,7 +4693,7 @@ static void binder_vma_close(struct vm_area_struct *vma)
 	binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES);
 }
 
-static int binder_vm_fault(struct vm_fault *vmf)
+static vm_fault_t binder_vm_fault(struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
 }
@@ -4722,7 +4727,9 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 		failure_string = "bad vm_flags";
 		goto err_bad_arg;
 	}
-	vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE;
+	vma->vm_flags |= VM_DONTCOPY | VM_MIXEDMAP;
+	vma->vm_flags &= ~VM_MAYWRITE;
+
 	vma->vm_ops = &binder_vm_ops;
 	vma->vm_private_data = proc;
 
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 5a426c877dfb..4f382d51def1 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -219,7 +219,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		mm = alloc->vma_vm_mm;
 
 	if (mm) {
-		down_write(&mm->mmap_sem);
+		down_read(&mm->mmap_sem);
 		vma = alloc->vma;
 	}
 
@@ -288,7 +288,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		/* vm_insert_page does not seem to increment the refcount */
 	}
 	if (mm) {
-		up_write(&mm->mmap_sem);
+		up_read(&mm->mmap_sem);
 		mmput(mm);
 	}
 	return 0;
@@ -321,7 +321,7 @@ err_page_ptr_cleared:
 	}
 err_no_vma:
 	if (mm) {
-		up_write(&mm->mmap_sem);
+		up_read(&mm->mmap_sem);
 		mmput(mm);
 	}
 	return vma ? -ENOMEM : -ESRCH;
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index 940ddbc59aa7..583e366be7e2 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -271,7 +271,7 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 	 * Fill in command table information.  First, the header,
 	 * a SATA Register - Host to Device command FIS.
 	 */
-	cmd_tbl = pp->cmd_tbl + qc->tag * AHCI_CMD_TBL_SZ;
+	cmd_tbl = pp->cmd_tbl + qc->hw_tag * AHCI_CMD_TBL_SZ;
 
 	ata_tf_to_fis(&qc->tf, qc->dev->link->pmp, 1, cmd_tbl);
 	if (is_atapi) {
@@ -294,7 +294,7 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 	if (is_atapi)
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
-	ahci_fill_cmd_slot(pp, qc->tag, opts);
+	ahci_fill_cmd_slot(pp, qc->hw_tag, opts);
 }
 
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 1ff17799769d..738fb22978dd 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -334,6 +334,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x9c07), board_ahci_mobile }, /* Lynx LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x9c0e), board_ahci_mobile }, /* Lynx LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x9c0f), board_ahci_mobile }, /* Lynx LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9dd3), board_ahci_mobile }, /* Cannon Lake PCH-LP AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1f22), board_ahci }, /* Avoton AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1f23), board_ahci }, /* Avoton AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1f24), board_ahci }, /* Avoton RAID */
@@ -698,7 +699,7 @@ static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
 
 	DPRINTK("ENTER\n");
 
-	ahci_stop_engine(ap);
+	hpriv->stop_engine(ap);
 
 	rc = sata_link_hardreset(link, sata_ehc_deb_timing(&link->eh_context),
 				 deadline, &online, NULL);
@@ -724,7 +725,7 @@ static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class,
 	bool online;
 	int rc;
 
-	ahci_stop_engine(ap);
+	hpriv->stop_engine(ap);
 
 	/* clear D2H reception area to properly wait for D2H FIS */
 	ata_tf_init(link->device, &tf);
@@ -788,7 +789,7 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
 
 	DPRINTK("ENTER\n");
 
-	ahci_stop_engine(ap);
+	hpriv->stop_engine(ap);
 
 	for (i = 0; i < 2; i++) {
 		u16 val;
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 4356ef1d28a8..1609ebab4e23 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -350,7 +350,6 @@ struct ahci_host_priv {
 	u32			em_msg_type;	/* EM message type */
 	bool			got_runtime_pm; /* Did we do pm_runtime_get? */
 	struct clk		*clks[AHCI_MAX_CLKS]; /* Optional */
-	struct reset_control	*rsts;		/* Optional */
 	struct regulator	**target_pwrs;	/* Optional */
 	/*
 	 * If platform uses PHYs. There is a 1:1 relation between the port number and
@@ -366,6 +365,13 @@ struct ahci_host_priv {
 	 * be overridden anytime before the host is activated.
 	 */
 	void			(*start_engine)(struct ata_port *ap);
+	/*
+	 * Optional ahci_stop_engine override, if not set this gets set to the
+	 * default ahci_stop_engine during ahci_save_initial_config, this can
+	 * be overridden anytime before the host is activated.
+	 */
+	int			(*stop_engine)(struct ata_port *ap);
+
 	irqreturn_t 		(*irq_handler)(int irq, void *dev_instance);
 
 	/* only required for per-port MSI(-X) support */
@@ -384,7 +390,7 @@ extern struct device_attribute *ahci_sdev_attrs[];
  */
 #define AHCI_SHT(drv_name)						\
 	ATA_NCQ_SHT(drv_name),						\
-	.can_queue		= AHCI_MAX_CMDS - 1,			\
+	.can_queue		= AHCI_MAX_CMDS,			\
 	.sg_tablesize		= AHCI_MAX_SG,				\
 	.dma_boundary		= AHCI_DMA_BOUNDARY,			\
 	.shost_attrs		= ahci_shost_attrs,			\
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index de7128d81e9c..0045dacd814b 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -62,6 +62,60 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv)
 	writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA);
 }
 
+/**
+ * ahci_mvebu_stop_engine
+ *
+ * @ap:	Target ata port
+ *
+ * Errata Ref#226 - SATA Disk HOT swap issue when connected through
+ * Port Multiplier in FIS-based Switching mode.
+ *
+ * To avoid the issue, according to design, the bits[11:8, 0] of
+ * register PxFBS are cleared when Port Command and Status (0x18) bit[0]
+ * changes its value from 1 to 0, i.e. falling edge of Port
+ * Command and Status bit[0] sends PULSE that resets PxFBS
+ * bits[11:8; 0].
+ *
+ * This function is used to override function of "ahci_stop_engine"
+ * from libahci.c by adding the mvebu work around(WA) to save PxFBS
+ * value before the PxCMD ST write of 0, then restore PxFBS value.
+ *
+ * Return: 0 on success; Error code otherwise.
+ */
+int ahci_mvebu_stop_engine(struct ata_port *ap)
+{
+	void __iomem *port_mmio = ahci_port_base(ap);
+	u32 tmp, port_fbs;
+
+	tmp = readl(port_mmio + PORT_CMD);
+
+	/* check if the HBA is idle */
+	if ((tmp & (PORT_CMD_START | PORT_CMD_LIST_ON)) == 0)
+		return 0;
+
+	/* save the port PxFBS register for later restore */
+	port_fbs = readl(port_mmio + PORT_FBS);
+
+	/* setting HBA to idle */
+	tmp &= ~PORT_CMD_START;
+	writel(tmp, port_mmio + PORT_CMD);
+
+	/*
+	 * bit #15 PxCMD signal doesn't clear PxFBS,
+	 * restore the PxFBS register right after clearing the PxCMD ST,
+	 * no need to wait for the PxCMD bit #15.
+	 */
+	writel(port_fbs, port_mmio + PORT_FBS);
+
+	/* wait for engine to stop. This could be as long as 500 msec */
+	tmp = ata_wait_register(ap, port_mmio + PORT_CMD,
+				PORT_CMD_LIST_ON, PORT_CMD_LIST_ON, 1, 500);
+	if (tmp & PORT_CMD_LIST_ON)
+		return -EIO;
+
+	return 0;
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state)
 {
@@ -112,6 +166,8 @@ static int ahci_mvebu_probe(struct platform_device *pdev)
 	if (rc)
 		return rc;
 
+	hpriv->stop_engine = ahci_mvebu_stop_engine;
+
 	if (of_device_is_compatible(pdev->dev.of_node,
 				    "marvell,armada-380-ahci")) {
 		dram = mv_mbus_dram_info();
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index 2685f28160f7..cfdef4d44ae9 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -96,7 +96,7 @@ static int ahci_qoriq_hardreset(struct ata_link *link, unsigned int *class,
 
 	DPRINTK("ENTER\n");
 
-	ahci_stop_engine(ap);
+	hpriv->stop_engine(ap);
 
 	/*
 	 * There is a errata on ls1021a Rev1.0 and Rev2.0 which is:
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index c2b5941d9184..ad58da7c9aff 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -165,7 +165,7 @@ static int xgene_ahci_restart_engine(struct ata_port *ap)
 				    PORT_CMD_ISSUE, 0x0, 1, 100))
 		  return -EBUSY;
 
-	ahci_stop_engine(ap);
+	hpriv->stop_engine(ap);
 	ahci_start_fis_rx(ap);
 
 	/*
@@ -421,7 +421,7 @@ static int xgene_ahci_hardreset(struct ata_link *link, unsigned int *class,
 	portrxfis_saved = readl(port_mmio + PORT_FIS_ADDR);
 	portrxfishi_saved = readl(port_mmio + PORT_FIS_ADDR_HI);
 
-	ahci_stop_engine(ap);
+	hpriv->stop_engine(ap);
 
 	rc = xgene_ahci_do_hardreset(link, deadline, &online);
 
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 7adcf3caabd0..965842a08743 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -560,6 +560,9 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 	if (!hpriv->start_engine)
 		hpriv->start_engine = ahci_start_engine;
 
+	if (!hpriv->stop_engine)
+		hpriv->stop_engine = ahci_stop_engine;
+
 	if (!hpriv->irq_handler)
 		hpriv->irq_handler = ahci_single_level_irq_intr;
 }
@@ -897,9 +900,10 @@ static void ahci_start_port(struct ata_port *ap)
 static int ahci_deinit_port(struct ata_port *ap, const char **emsg)
 {
 	int rc;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 
 	/* disable DMA */
-	rc = ahci_stop_engine(ap);
+	rc = hpriv->stop_engine(ap);
 	if (rc) {
 		*emsg = "failed to stop engine";
 		return rc;
@@ -1310,7 +1314,7 @@ int ahci_kick_engine(struct ata_port *ap)
 	int busy, rc;
 
 	/* stop engine */
-	rc = ahci_stop_engine(ap);
+	rc = hpriv->stop_engine(ap);
 	if (rc)
 		goto out_restart;
 
@@ -1549,7 +1553,7 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class,
 
 	DPRINTK("ENTER\n");
 
-	ahci_stop_engine(ap);
+	hpriv->stop_engine(ap);
 
 	/* clear D2H reception area to properly wait for D2H FIS */
 	ata_tf_init(link->device, &tf);
@@ -1645,7 +1649,7 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc)
 	 * Fill in command table information.  First, the header,
 	 * a SATA Register - Host to Device command FIS.
 	 */
-	cmd_tbl = pp->cmd_tbl + qc->tag * AHCI_CMD_TBL_SZ;
+	cmd_tbl = pp->cmd_tbl + qc->hw_tag * AHCI_CMD_TBL_SZ;
 
 	ata_tf_to_fis(&qc->tf, qc->dev->link->pmp, 1, cmd_tbl);
 	if (is_atapi) {
@@ -1666,7 +1670,7 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc)
 	if (is_atapi)
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
-	ahci_fill_cmd_slot(pp, qc->tag, opts);
+	ahci_fill_cmd_slot(pp, qc->hw_tag, opts);
 }
 
 static void ahci_fbs_dec_intr(struct ata_port *ap)
@@ -2002,7 +2006,7 @@ unsigned int ahci_qc_issue(struct ata_queued_cmd *qc)
 	pp->active_link = qc->dev->link;
 
 	if (ata_is_ncq(qc->tf.protocol))
-		writel(1 << qc->tag, port_mmio + PORT_SCR_ACT);
+		writel(1 << qc->hw_tag, port_mmio + PORT_SCR_ACT);
 
 	if (pp->fbs_enabled && pp->fbs_last_dev != qc->dev->link->pmp) {
 		u32 fbs = readl(port_mmio + PORT_FBS);
@@ -2012,7 +2016,7 @@ unsigned int ahci_qc_issue(struct ata_queued_cmd *qc)
 		pp->fbs_last_dev = qc->dev->link->pmp;
 	}
 
-	writel(1 << qc->tag, port_mmio + PORT_CMD_ISSUE);
+	writel(1 << qc->hw_tag, port_mmio + PORT_CMD_ISSUE);
 
 	ahci_sw_activity(qc->dev->link);
 
@@ -2075,14 +2079,14 @@ void ahci_error_handler(struct ata_port *ap)
 
 	if (!(ap->pflags & ATA_PFLAG_FROZEN)) {
 		/* restart engine */
-		ahci_stop_engine(ap);
+		hpriv->stop_engine(ap);
 		hpriv->start_engine(ap);
 	}
 
 	sata_pmp_error_handler(ap);
 
 	if (!ata_dev_enabled(ap->link.device))
-		ahci_stop_engine(ap);
+		hpriv->stop_engine(ap);
 }
 EXPORT_SYMBOL_GPL(ahci_error_handler);
 
@@ -2129,7 +2133,7 @@ static void ahci_set_aggressive_devslp(struct ata_port *ap, bool sleep)
 		return;
 
 	/* set DITO, MDAT, DETO and enable DevSlp, need to stop engine first */
-	rc = ahci_stop_engine(ap);
+	rc = hpriv->stop_engine(ap);
 	if (rc)
 		return;
 
@@ -2189,7 +2193,7 @@ static void ahci_enable_fbs(struct ata_port *ap)
 		return;
 	}
 
-	rc = ahci_stop_engine(ap);
+	rc = hpriv->stop_engine(ap);
 	if (rc)
 		return;
 
@@ -2222,7 +2226,7 @@ static void ahci_disable_fbs(struct ata_port *ap)
 		return;
 	}
 
-	rc = ahci_stop_engine(ap);
+	rc = hpriv->stop_engine(ap);
 	if (rc)
 		return;
 
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 46a762442dc5..30cc8f1a31e1 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -25,7 +25,6 @@
 #include <linux/phy/phy.h>
 #include <linux/pm_runtime.h>
 #include <linux/of_platform.h>
-#include <linux/reset.h>
 #include "ahci.h"
 
 static void ahci_host_stop(struct ata_host *host);
@@ -196,8 +195,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators);
  * following order:
  * 1) Regulator
  * 2) Clocks (through ahci_platform_enable_clks)
- * 3) Resets
- * 4) Phys
+ * 3) Phys
  *
  * If resource enabling fails at any point the previous enabled resources
  * are disabled in reverse order.
@@ -217,19 +215,12 @@ int ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
 	if (rc)
 		goto disable_regulator;
 
-	rc = reset_control_deassert(hpriv->rsts);
-	if (rc)
-		goto disable_clks;
-
 	rc = ahci_platform_enable_phys(hpriv);
 	if (rc)
-		goto disable_resets;
+		goto disable_clks;
 
 	return 0;
 
-disable_resets:
-	reset_control_assert(hpriv->rsts);
-
 disable_clks:
 	ahci_platform_disable_clks(hpriv);
 
@@ -248,15 +239,12 @@ EXPORT_SYMBOL_GPL(ahci_platform_enable_resources);
  * following order:
  * 1) Phys
  * 2) Clocks (through ahci_platform_disable_clks)
- * 3) Resets
- * 4) Regulator
+ * 3) Regulator
  */
 void ahci_platform_disable_resources(struct ahci_host_priv *hpriv)
 {
 	ahci_platform_disable_phys(hpriv);
 
-	reset_control_assert(hpriv->rsts);
-
 	ahci_platform_disable_clks(hpriv);
 
 	ahci_platform_disable_regulators(hpriv);
@@ -405,12 +393,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
 		hpriv->clks[i] = clk;
 	}
 
-	hpriv->rsts = devm_reset_control_array_get_optional_shared(dev);
-	if (IS_ERR(hpriv->rsts)) {
-		rc = PTR_ERR(hpriv->rsts);
-		goto err_out;
-	}
-
 	hpriv->nports = child_nodes = of_get_child_count(dev->of_node);
 
 	/*
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 8bc71ca61e7f..c41b9eeabe7c 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -759,7 +759,7 @@ int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
 	tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
 	tf->flags |= tf_flags;
 
-	if (ata_ncq_enabled(dev) && likely(tag != ATA_TAG_INTERNAL)) {
+	if (ata_ncq_enabled(dev) && !ata_tag_internal(tag)) {
 		/* yay, NCQ */
 		if (!lba_48_ok(block, n_block))
 			return -ERANGE;
@@ -1570,8 +1570,9 @@ unsigned ata_exec_internal_sg(struct ata_device *dev,
 	u8 command = tf->command;
 	int auto_timeout = 0;
 	struct ata_queued_cmd *qc;
-	unsigned int tag, preempted_tag;
-	u32 preempted_sactive, preempted_qc_active;
+	unsigned int preempted_tag;
+	u32 preempted_sactive;
+	u64 preempted_qc_active;
 	int preempted_nr_active_links;
 	DECLARE_COMPLETION_ONSTACK(wait);
 	unsigned long flags;
@@ -1587,20 +1588,10 @@ unsigned ata_exec_internal_sg(struct ata_device *dev,
 	}
 
 	/* initialize internal qc */
+	qc = __ata_qc_from_tag(ap, ATA_TAG_INTERNAL);
 
-	/* XXX: Tag 0 is used for drivers with legacy EH as some
-	 * drivers choke if any other tag is given.  This breaks
-	 * ata_tag_internal() test for those drivers.  Don't use new
-	 * EH stuff without converting to it.
-	 */
-	if (ap->ops->error_handler)
-		tag = ATA_TAG_INTERNAL;
-	else
-		tag = 0;
-
-	qc = __ata_qc_from_tag(ap, tag);
-
-	qc->tag = tag;
+	qc->tag = ATA_TAG_INTERNAL;
+	qc->hw_tag = 0;
 	qc->scsicmd = NULL;
 	qc->ap = ap;
 	qc->dev = dev;
@@ -2295,7 +2286,7 @@ static int ata_dev_config_ncq(struct ata_device *dev,
 		return 0;
 	}
 	if (ap->flags & ATA_FLAG_NCQ) {
-		hdepth = min(ap->scsi_host->can_queue, ATA_MAX_QUEUE - 1);
+		hdepth = min(ap->scsi_host->can_queue, ATA_MAX_QUEUE);
 		dev->flags |= ATA_DFLAG_NCQ;
 	}
 
@@ -3573,9 +3564,11 @@ static int ata_dev_set_mode(struct ata_device *dev)
 	DPRINTK("xfer_shift=%u, xfer_mode=0x%x\n",
 		dev->xfer_shift, (int)dev->xfer_mode);
 
-	ata_dev_info(dev, "configured for %s%s\n",
-		     ata_mode_string(ata_xfer_mode2mask(dev->xfer_mode)),
-		     dev_err_whine);
+	if (!(ehc->i.flags & ATA_EHI_QUIET) ||
+	    ehc->i.flags & ATA_EHI_DID_HARDRESET)
+		ata_dev_info(dev, "configured for %s%s\n",
+			     ata_mode_string(ata_xfer_mode2mask(dev->xfer_mode)),
+			     dev_err_whine);
 
 	return 0;
 
@@ -4493,6 +4486,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */
 	{ "C300-CTFDDAC128MAG",	"0001",		ATA_HORKAGE_NONCQ, },
 
+	/* Some Sandisk SSDs lock up hard with NCQ enabled.  Reported on
+	   SD7SN6S256G and SD8SN8U256G */
+	{ "SanDisk SD[78]SN*G",	NULL,		ATA_HORKAGE_NONCQ, },
+
 	/* devices which puke on READ_NATIVE_MAX */
 	{ "HDS724040KLSA80",	"KFAOA20N",	ATA_HORKAGE_BROKEN_HPA, },
 	{ "WDC WD3200JD-00KLB0", "WD-WCAMR1130137", ATA_HORKAGE_BROKEN_HPA },
@@ -4549,7 +4546,13 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 						ATA_HORKAGE_ZERO_AFTER_TRIM |
 						ATA_HORKAGE_NOLPM, },
 
+	/* These specific Samsung models/firmware-revs do not handle LPM well */
+	{ "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, },
+	{ "SAMSUNG SSD PM830 mSATA *",  "CXM13D1Q", ATA_HORKAGE_NOLPM, },
+
 	/* devices that don't properly handle queued TRIM commands */
+	{ "Micron_M500IT_*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
+						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Micron_M500_*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Crucial_CT*M500*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
@@ -5123,7 +5126,7 @@ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag)
 	}
 
 	qc = __ata_qc_from_tag(ap, tag);
-	qc->tag = tag;
+	qc->tag = qc->hw_tag = tag;
 	qc->scsicmd = NULL;
 	qc->ap = ap;
 	qc->dev = dev;
@@ -5153,7 +5156,7 @@ void ata_qc_free(struct ata_queued_cmd *qc)
 
 	qc->flags = 0;
 	tag = qc->tag;
-	if (likely(ata_tag_valid(tag))) {
+	if (ata_tag_valid(tag)) {
 		qc->tag = ATA_TAG_POISON;
 		if (ap->flags & ATA_FLAG_SAS_HOST)
 			ata_sas_free_tag(tag, ap);
@@ -5175,7 +5178,7 @@ void __ata_qc_complete(struct ata_queued_cmd *qc)
 
 	/* command should be marked inactive atomically with qc completion */
 	if (ata_is_ncq(qc->tf.protocol)) {
-		link->sactive &= ~(1 << qc->tag);
+		link->sactive &= ~(1 << qc->hw_tag);
 		if (!link->sactive)
 			ap->nr_active_links--;
 	} else {
@@ -5193,7 +5196,7 @@ void __ata_qc_complete(struct ata_queued_cmd *qc)
 	 * is called. (when rc != 0 and atapi request sense is needed)
 	 */
 	qc->flags &= ~ATA_QCFLAG_ACTIVE;
-	ap->qc_active &= ~(1 << qc->tag);
+	ap->qc_active &= ~(1ULL << qc->tag);
 
 	/* call completion callback */
 	qc->complete_fn(qc);
@@ -5350,29 +5353,29 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
  *	RETURNS:
  *	Number of completed commands on success, -errno otherwise.
  */
-int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active)
+int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active)
 {
 	int nr_done = 0;
-	u32 done_mask;
+	u64 done_mask;
 
 	done_mask = ap->qc_active ^ qc_active;
 
 	if (unlikely(done_mask & qc_active)) {
-		ata_port_err(ap, "illegal qc_active transition (%08x->%08x)\n",
+		ata_port_err(ap, "illegal qc_active transition (%08llx->%08llx)\n",
 			     ap->qc_active, qc_active);
 		return -EINVAL;
 	}
 
 	while (done_mask) {
 		struct ata_queued_cmd *qc;
-		unsigned int tag = __ffs(done_mask);
+		unsigned int tag = __ffs64(done_mask);
 
 		qc = ata_qc_from_tag(ap, tag);
 		if (qc) {
 			ata_qc_complete(qc);
 			nr_done++;
 		}
-		done_mask &= ~(1 << tag);
+		done_mask &= ~(1ULL << tag);
 	}
 
 	return nr_done;
@@ -5403,11 +5406,11 @@ void ata_qc_issue(struct ata_queued_cmd *qc)
 	WARN_ON_ONCE(ap->ops->error_handler && ata_tag_valid(link->active_tag));
 
 	if (ata_is_ncq(prot)) {
-		WARN_ON_ONCE(link->sactive & (1 << qc->tag));
+		WARN_ON_ONCE(link->sactive & (1 << qc->hw_tag));
 
 		if (!link->sactive)
 			ap->nr_active_links++;
-		link->sactive |= 1 << qc->tag;
+		link->sactive |= 1 << qc->hw_tag;
 	} else {
 		WARN_ON_ONCE(link->sactive);
 
@@ -5416,7 +5419,7 @@ void ata_qc_issue(struct ata_queued_cmd *qc)
 	}
 
 	qc->flags |= ATA_QCFLAG_ACTIVE;
-	ap->qc_active |= 1 << qc->tag;
+	ap->qc_active |= 1ULL << qc->tag;
 
 	/*
 	 * We guarantee to LLDs that they will have at least one
@@ -6415,7 +6418,7 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 {
 	spin_lock_init(&host->lock);
 	mutex_init(&host->eh_mutex);
-	host->n_tags = ATA_MAX_QUEUE - 1;
+	host->n_tags = ATA_MAX_QUEUE;
 	host->dev = dev;
 	host->ops = ops;
 }
@@ -6497,7 +6500,7 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 {
 	int i, rc;
 
-	host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1);
+	host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE);
 
 	/* host must have been started */
 	if (!(host->flags & ATA_HOST_STARTED)) {
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index c016829a38fd..d5412145d76d 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -175,8 +175,8 @@ static void ata_eh_handle_port_resume(struct ata_port *ap)
 { }
 #endif /* CONFIG_PM */
 
-static void __ata_ehi_pushv_desc(struct ata_eh_info *ehi, const char *fmt,
-				 va_list args)
+static __printf(2, 0) void __ata_ehi_pushv_desc(struct ata_eh_info *ehi,
+				 const char *fmt, va_list args)
 {
 	ehi->desc_len += vscnprintf(ehi->desc + ehi->desc_len,
 				     ATA_EH_DESC_LEN - ehi->desc_len,
@@ -500,57 +500,6 @@ void ata_eh_release(struct ata_port *ap)
 	mutex_unlock(&ap->host->eh_mutex);
 }
 
-/**
- *	ata_scsi_timed_out - SCSI layer time out callback
- *	@cmd: timed out SCSI command
- *
- *	Handles SCSI layer timeout.  We race with normal completion of
- *	the qc for @cmd.  If the qc is already gone, we lose and let
- *	the scsi command finish (EH_HANDLED).  Otherwise, the qc has
- *	timed out and EH should be invoked.  Prevent ata_qc_complete()
- *	from finishing it by setting EH_SCHEDULED and return
- *	EH_NOT_HANDLED.
- *
- *	TODO: kill this function once old EH is gone.
- *
- *	LOCKING:
- *	Called from timer context
- *
- *	RETURNS:
- *	EH_HANDLED or EH_NOT_HANDLED
- */
-enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd)
-{
-	struct Scsi_Host *host = cmd->device->host;
-	struct ata_port *ap = ata_shost_to_port(host);
-	unsigned long flags;
-	struct ata_queued_cmd *qc;
-	enum blk_eh_timer_return ret;
-
-	DPRINTK("ENTER\n");
-
-	if (ap->ops->error_handler) {
-		ret = BLK_EH_NOT_HANDLED;
-		goto out;
-	}
-
-	ret = BLK_EH_HANDLED;
-	spin_lock_irqsave(ap->lock, flags);
-	qc = ata_qc_from_tag(ap, ap->link.active_tag);
-	if (qc) {
-		WARN_ON(qc->scsicmd != cmd);
-		qc->flags |= ATA_QCFLAG_EH_SCHEDULED;
-		qc->err_mask |= AC_ERR_TIMEOUT;
-		ret = BLK_EH_NOT_HANDLED;
-	}
-	spin_unlock_irqrestore(ap->lock, flags);
-
- out:
-	DPRINTK("EXIT, ret=%d\n", ret);
-	return ret;
-}
-EXPORT_SYMBOL(ata_scsi_timed_out);
-
 static void ata_eh_unload(struct ata_port *ap)
 {
 	struct ata_link *link;
@@ -873,9 +822,12 @@ static int ata_eh_nr_in_flight(struct ata_port *ap)
 	int nr = 0;
 
 	/* count only non-internal commands */
-	for (tag = 0; tag < ATA_MAX_QUEUE - 1; tag++)
+	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
+		if (ata_tag_internal(tag))
+			continue;
 		if (ata_qc_from_tag(ap, tag))
 			nr++;
+	}
 
 	return nr;
 }
@@ -900,7 +852,7 @@ void ata_eh_fastdrain_timerfn(struct timer_list *t)
 		/* No progress during the last interval, tag all
 		 * in-flight qcs as timed out and freeze the port.
 		 */
-		for (tag = 0; tag < ATA_MAX_QUEUE - 1; tag++) {
+		for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
 			struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
 			if (qc)
 				qc->err_mask |= AC_ERR_TIMEOUT;
@@ -1054,7 +1006,8 @@ static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link)
 	/* we're gonna abort all commands, no need for fast drain */
 	ata_eh_set_pending(ap, 0);
 
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
+	/* include internal tag in iteration */
+	for (tag = 0; tag <= ATA_MAX_QUEUE; tag++) {
 		struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
 
 		if (qc && (!link || qc->dev->link == link)) {
@@ -1483,6 +1436,10 @@ static const char *ata_err_string(unsigned int err_mask)
 		return "invalid argument";
 	if (err_mask & AC_ERR_DEV)
 		return "device error";
+	if (err_mask & AC_ERR_NCQ)
+		return "NCQ error";
+	if (err_mask & AC_ERR_NODEV_HINT)
+		return "Polling detection error";
 	return "unknown error";
 }
 
@@ -1866,10 +1823,10 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
 	if (qc->flags & ATA_QCFLAG_SENSE_VALID) {
 		int ret = scsi_check_sense(qc->scsicmd);
 		/*
-		 * SUCCESS here means that the sense code could
+		 * SUCCESS here means that the sense code could be
 		 * evaluated and should be passed to the upper layers
 		 * for correct evaluation.
-		 * FAILED means the sense code could not interpreted
+		 * FAILED means the sense code could not be interpreted
 		 * and the device would need to be reset.
 		 * NEEDS_RETRY and ADD_TO_MLQUEUE means that the
 		 * command would need to be retried.
@@ -2150,6 +2107,21 @@ static inline int ata_eh_worth_retry(struct ata_queued_cmd *qc)
 }
 
 /**
+ *      ata_eh_quiet - check if we need to be quiet about a command error
+ *      @qc: qc to check
+ *
+ *      Look at the qc flags anbd its scsi command request flags to determine
+ *      if we need to be quiet about the command failure.
+ */
+static inline bool ata_eh_quiet(struct ata_queued_cmd *qc)
+{
+	if (qc->scsicmd &&
+	    qc->scsicmd->request->rq_flags & RQF_QUIET)
+		qc->flags |= ATA_QCFLAG_QUIET;
+	return qc->flags & ATA_QCFLAG_QUIET;
+}
+
+/**
  *	ata_eh_link_autopsy - analyze error and determine recovery action
  *	@link: host link to perform autopsy on
  *
@@ -2166,7 +2138,7 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 	struct ata_eh_context *ehc = &link->eh_context;
 	struct ata_device *dev;
 	unsigned int all_err_mask = 0, eflags = 0;
-	int tag;
+	int tag, nr_failed = 0, nr_quiet = 0;
 	u32 serror;
 	int rc;
 
@@ -2218,12 +2190,16 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 		if (qc->err_mask & ~AC_ERR_OTHER)
 			qc->err_mask &= ~AC_ERR_OTHER;
 
-		/* SENSE_VALID trumps dev/unknown error and revalidation */
+		/*
+		 * SENSE_VALID trumps dev/unknown error and revalidation. Upper
+		 * layers will determine whether the command is worth retrying
+		 * based on the sense data and device class/type. Otherwise,
+		 * determine directly if the command is worth retrying using its
+		 * error mask and flags.
+		 */
 		if (qc->flags & ATA_QCFLAG_SENSE_VALID)
 			qc->err_mask &= ~(AC_ERR_DEV | AC_ERR_OTHER);
-
-		/* determine whether the command is worth retrying */
-		if (ata_eh_worth_retry(qc))
+		else if (ata_eh_worth_retry(qc))
 			qc->flags |= ATA_QCFLAG_RETRY;
 
 		/* accumulate error info */
@@ -2232,8 +2208,17 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 		if (qc->flags & ATA_QCFLAG_IO)
 			eflags |= ATA_EFLAG_IS_IO;
 		trace_ata_eh_link_autopsy_qc(qc);
+
+		/* Count quiet errors */
+		if (ata_eh_quiet(qc))
+			nr_quiet++;
+		nr_failed++;
 	}
 
+	/* If all failed commands requested silence, then be quiet */
+	if (nr_quiet == nr_failed)
+		ehc->i.flags |= ATA_EHI_QUIET;
+
 	/* enforce default EH actions */
 	if (ap->pflags & ATA_PFLAG_FROZEN ||
 	    all_err_mask & (AC_ERR_HSM | AC_ERR_TIMEOUT))
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 89a9d4a2efc8..ce5019db50fd 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -872,6 +872,9 @@ static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev,
 
 		qc->sg = scsi_sglist(cmd);
 		qc->n_elem = scsi_sg_count(cmd);
+
+		if (cmd->request->rq_flags & RQF_QUIET)
+			qc->flags |= ATA_QCFLAG_QUIET;
 	} else {
 		cmd->result = (DID_OK << 16) | (QUEUE_FULL << 1);
 		cmd->scsi_done(cmd);
@@ -1316,7 +1319,7 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
 		int depth;
 
 		depth = min(sdev->host->can_queue, ata_id_queue_depth(dev->id));
-		depth = min(ATA_MAX_QUEUE - 1, depth);
+		depth = min(ATA_MAX_QUEUE, depth);
 		scsi_change_queue_depth(sdev, depth);
 	}
 
@@ -1429,7 +1432,7 @@ int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
 	/* limit and apply queue depth */
 	queue_depth = min(queue_depth, sdev->host->can_queue);
 	queue_depth = min(queue_depth, ata_id_queue_depth(dev->id));
-	queue_depth = min(queue_depth, ATA_MAX_QUEUE - 1);
+	queue_depth = min(queue_depth, ATA_MAX_QUEUE);
 
 	if (sdev->queue_depth == queue_depth)
 		return -EINVAL;
@@ -1895,7 +1898,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc)
 	qc->nbytes = n_block * scmd->device->sector_size;
 
 	rc = ata_build_rw_tf(&qc->tf, qc->dev, block, n_block, tf_flags,
-			     qc->tag, class);
+			     qc->hw_tag, class);
 
 	if (likely(rc == 0))
 		return 0;
@@ -3233,7 +3236,7 @@ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc)
 
 	/* For NCQ commands copy the tag value */
 	if (ata_is_ncq(tf->protocol))
-		tf->nsect = qc->tag << 3;
+		tf->nsect = qc->hw_tag << 3;
 
 	/* enforce correct master/slave bit */
 	tf->device = dev->devno ?
@@ -3513,7 +3516,7 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
 		tf->protocol = ATA_PROT_NCQ;
 		tf->command = ATA_CMD_FPDMA_SEND;
 		tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f;
-		tf->nsect = qc->tag << 3;
+		tf->nsect = qc->hw_tag << 3;
 		tf->hob_feature = (size / 512) >> 8;
 		tf->feature = size / 512;
 
@@ -3733,7 +3736,7 @@ static unsigned int ata_scsi_zbc_in_xlat(struct ata_queued_cmd *qc)
 		tf->protocol = ATA_PROT_NCQ;
 		tf->command = ATA_CMD_FPDMA_RECV;
 		tf->hob_nsect = ATA_SUBCMD_FPDMA_RECV_ZAC_MGMT_IN & 0x1f;
-		tf->nsect = qc->tag << 3;
+		tf->nsect = qc->hw_tag << 3;
 		tf->feature = sect & 0xff;
 		tf->hob_feature = (sect >> 8) & 0xff;
 		tf->auxiliary = ATA_SUBCMD_ZAC_MGMT_IN_REPORT_ZONES | (options << 8);
@@ -3812,7 +3815,7 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc)
 		tf->protocol = ATA_PROT_NCQ_NODATA;
 		tf->command = ATA_CMD_NCQ_NON_DATA;
 		tf->feature = ATA_SUBCMD_NCQ_NON_DATA_ZAC_MGMT_OUT;
-		tf->nsect = qc->tag << 3;
+		tf->nsect = qc->hw_tag << 3;
 		tf->auxiliary = sa | ((u16)all << 8);
 	} else {
 		tf->protocol = ATA_PROT_NODATA;
@@ -5117,7 +5120,7 @@ int ata_sas_allocate_tag(struct ata_port *ap)
 		tag = tag < max_queue ? tag : 0;
 
 		/* the last tag is reserved for internal command. */
-		if (tag == ATA_TAG_INTERNAL)
+		if (ata_tag_internal(tag))
 			continue;
 
 		if (!test_and_set_bit(tag, &ap->sas_tag_allocated)) {
diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c
index de4ddd0e8550..b3ed8f9953a8 100644
--- a/drivers/ata/libata-zpodd.c
+++ b/drivers/ata/libata-zpodd.c
@@ -35,7 +35,7 @@ struct zpodd {
 static int eject_tray(struct ata_device *dev)
 {
 	struct ata_taskfile tf;
-	static const char cdb[] = {  GPCMD_START_STOP_UNIT,
+	static const char cdb[ATAPI_CDB_LEN] = {  GPCMD_START_STOP_UNIT,
 		0, 0, 0,
 		0x02,     /* LoEj */
 		0, 0, 0, 0, 0, 0, 0,
diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c
index 3ba843f5cdc0..ef8aaeb0c575 100644
--- a/drivers/ata/pata_hpt37x.c
+++ b/drivers/ata/pata_hpt37x.c
@@ -224,17 +224,14 @@ static int hpt_dma_blacklisted(const struct ata_device *dev, char *modestr,
 			       const char * const list[])
 {
 	unsigned char model_num[ATA_ID_PROD_LEN + 1];
-	int i = 0;
+	int i;
 
 	ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num));
 
-	while (list[i] != NULL) {
-		if (!strcmp(list[i], model_num)) {
-			pr_warn("%s is not supported for %s\n",
-				modestr, list[i]);
-			return 1;
-		}
-		i++;
+	i = match_string(list, -1, model_num);
+	if (i >= 0) {
+		pr_warn("%s is not supported for %s\n", modestr, list[i]);
+		return 1;
 	}
 	return 0;
 }
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index ce3d6674ef80..6f142aa54f5f 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -761,7 +761,7 @@ static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status)
 	if (tag > 0) {
 		dev_info(ap->dev,
 			 "%s tag=%u cmd=0x%02x dma dir=%s proto=%s dmacr=0x%08x\n",
-			 __func__, qc->tag, qc->tf.command,
+			 __func__, qc->hw_tag, qc->tf.command,
 			 get_dma_dir_descript(qc->dma_dir),
 			 get_prot_descript(qc->tf.protocol),
 			 sata_dwc_readl(&hsdev->sata_dwc_regs->dmacr));
@@ -789,7 +789,7 @@ static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc,
 {
 	u8 status = 0;
 	u32 mask = 0x0;
-	u8 tag = qc->tag;
+	u8 tag = qc->hw_tag;
 	struct sata_dwc_device *hsdev = HSDEV_FROM_AP(ap);
 	struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap);
 	hsdev->sactive_queued = 0;
@@ -997,7 +997,7 @@ static void sata_dwc_bmdma_setup_by_tag(struct ata_queued_cmd *qc, u8 tag)
 
 static void sata_dwc_bmdma_setup(struct ata_queued_cmd *qc)
 {
-	u8 tag = qc->tag;
+	u8 tag = qc->hw_tag;
 
 	if (ata_is_ncq(qc->tf.protocol)) {
 		dev_dbg(qc->ap->dev, "%s: ap->link.sactive=0x%08x tag=%d\n",
@@ -1059,7 +1059,7 @@ static void sata_dwc_bmdma_start_by_tag(struct ata_queued_cmd *qc, u8 tag)
 
 static void sata_dwc_bmdma_start(struct ata_queued_cmd *qc)
 {
-	u8 tag = qc->tag;
+	u8 tag = qc->hw_tag;
 
 	if (ata_is_ncq(qc->tf.protocol)) {
 		dev_dbg(qc->ap->dev, "%s: ap->link.sactive=0x%08x tag=%d\n",
@@ -1074,17 +1074,17 @@ static void sata_dwc_bmdma_start(struct ata_queued_cmd *qc)
 static unsigned int sata_dwc_qc_issue(struct ata_queued_cmd *qc)
 {
 	u32 sactive;
-	u8 tag = qc->tag;
+	u8 tag = qc->hw_tag;
 	struct ata_port *ap = qc->ap;
 	struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap);
 
 #ifdef DEBUG_NCQ
-	if (qc->tag > 0 || ap->link.sactive > 1)
+	if (qc->hw_tag > 0 || ap->link.sactive > 1)
 		dev_info(ap->dev,
 			 "%s ap id=%d cmd(0x%02x)=%s qc tag=%d prot=%s ap active_tag=0x%08x ap sactive=0x%08x\n",
 			 __func__, ap->print_id, qc->tf.command,
 			 ata_get_cmd_descript(qc->tf.command),
-			 qc->tag, get_prot_descript(qc->tf.protocol),
+			 qc->hw_tag, get_prot_descript(qc->tf.protocol),
 			 ap->link.active_tag, ap->link.sactive);
 #endif
 
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 95bf3abda6f6..b8d9cfc60374 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -519,7 +519,7 @@ static void sata_fsl_qc_prep(struct ata_queued_cmd *qc)
 	struct sata_fsl_port_priv *pp = ap->private_data;
 	struct sata_fsl_host_priv *host_priv = ap->host->private_data;
 	void __iomem *hcr_base = host_priv->hcr_base;
-	unsigned int tag = sata_fsl_tag(qc->tag, hcr_base);
+	unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base);
 	struct command_desc *cd;
 	u32 desc_info = CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE;
 	u32 num_prde = 0;
@@ -566,7 +566,7 @@ static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc)
 	struct ata_port *ap = qc->ap;
 	struct sata_fsl_host_priv *host_priv = ap->host->private_data;
 	void __iomem *hcr_base = host_priv->hcr_base;
-	unsigned int tag = sata_fsl_tag(qc->tag, hcr_base);
+	unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base);
 
 	VPRINTK("xx_qc_issue called,CQ=0x%x,CA=0x%x,CE=0x%x,CC=0x%x\n",
 		ioread32(CQ + hcr_base),
@@ -595,7 +595,7 @@ static bool sata_fsl_qc_fill_rtf(struct ata_queued_cmd *qc)
 	struct sata_fsl_port_priv *pp = qc->ap->private_data;
 	struct sata_fsl_host_priv *host_priv = qc->ap->host->private_data;
 	void __iomem *hcr_base = host_priv->hcr_base;
-	unsigned int tag = sata_fsl_tag(qc->tag, hcr_base);
+	unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base);
 	struct command_desc *cd;
 
 	cd = pp->cmdentry + tag;
@@ -1266,7 +1266,7 @@ static void sata_fsl_host_intr(struct ata_port *ap)
 	}
 
 	VPRINTK("Status of all queues :\n");
-	VPRINTK("done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x,CQ=0x%x,apqa=0x%x\n",
+	VPRINTK("done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x,CQ=0x%x,apqa=0x%llx\n",
 		done_mask,
 		ioread32(hcr_base + CA),
 		ioread32(hcr_base + CE),
@@ -1293,7 +1293,7 @@ static void sata_fsl_host_intr(struct ata_port *ap)
 		ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
 		return;
 
-	} else if ((ap->qc_active & (1 << ATA_TAG_INTERNAL))) {
+	} else if ((ap->qc_active & (1ULL << ATA_TAG_INTERNAL))) {
 		iowrite32(1, hcr_base + CC);
 		qc = ata_qc_from_tag(ap, ATA_TAG_INTERNAL);
 
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index aafb8cc03523..e67815b896fc 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -410,7 +410,7 @@ static int ahci_highbank_hardreset(struct ata_link *link, unsigned int *class,
 	int rc;
 	int retry = 100;
 
-	ahci_stop_engine(ap);
+	hpriv->stop_engine(ap);
 
 	/* clear D2H reception area to properly wait for D2H FIS */
 	ata_tf_init(link->device, &tf);
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 42d4589b43d4..cddf96f6e431 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -1802,7 +1802,7 @@ static void mv_fill_sg(struct ata_queued_cmd *qc)
 	struct mv_sg *mv_sg, *last_sg = NULL;
 	unsigned int si;
 
-	mv_sg = pp->sg_tbl[qc->tag];
+	mv_sg = pp->sg_tbl[qc->hw_tag];
 	for_each_sg(qc->sg, sg, qc->n_elem, si) {
 		dma_addr_t addr = sg_dma_address(sg);
 		u32 sg_len = sg_dma_len(sg);
@@ -1903,9 +1903,9 @@ static void mv_bmdma_setup(struct ata_queued_cmd *qc)
 	writel(0, port_mmio + BMDMA_CMD);
 
 	/* load PRD table addr. */
-	writel((pp->sg_tbl_dma[qc->tag] >> 16) >> 16,
+	writel((pp->sg_tbl_dma[qc->hw_tag] >> 16) >> 16,
 		port_mmio + BMDMA_PRD_HIGH);
-	writelfl(pp->sg_tbl_dma[qc->tag],
+	writelfl(pp->sg_tbl_dma[qc->hw_tag],
 		port_mmio + BMDMA_PRD_LOW);
 
 	/* issue r/w command */
@@ -2071,17 +2071,17 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 	 */
 	if (!(tf->flags & ATA_TFLAG_WRITE))
 		flags |= CRQB_FLAG_READ;
-	WARN_ON(MV_MAX_Q_DEPTH <= qc->tag);
-	flags |= qc->tag << CRQB_TAG_SHIFT;
+	WARN_ON(MV_MAX_Q_DEPTH <= qc->hw_tag);
+	flags |= qc->hw_tag << CRQB_TAG_SHIFT;
 	flags |= (qc->dev->link->pmp & 0xf) << CRQB_PMP_SHIFT;
 
 	/* get current queue index from software */
 	in_index = pp->req_idx;
 
 	pp->crqb[in_index].sg_addr =
-		cpu_to_le32(pp->sg_tbl_dma[qc->tag] & 0xffffffff);
+		cpu_to_le32(pp->sg_tbl_dma[qc->hw_tag] & 0xffffffff);
 	pp->crqb[in_index].sg_addr_hi =
-		cpu_to_le32((pp->sg_tbl_dma[qc->tag] >> 16) >> 16);
+		cpu_to_le32((pp->sg_tbl_dma[qc->hw_tag] >> 16) >> 16);
 	pp->crqb[in_index].ctrl_flags = cpu_to_le16(flags);
 
 	cw = &pp->crqb[in_index].ata_cmd[0];
@@ -2164,17 +2164,17 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
 	if (!(tf->flags & ATA_TFLAG_WRITE))
 		flags |= CRQB_FLAG_READ;
 
-	WARN_ON(MV_MAX_Q_DEPTH <= qc->tag);
-	flags |= qc->tag << CRQB_TAG_SHIFT;
-	flags |= qc->tag << CRQB_HOSTQ_SHIFT;
+	WARN_ON(MV_MAX_Q_DEPTH <= qc->hw_tag);
+	flags |= qc->hw_tag << CRQB_TAG_SHIFT;
+	flags |= qc->hw_tag << CRQB_HOSTQ_SHIFT;
 	flags |= (qc->dev->link->pmp & 0xf) << CRQB_PMP_SHIFT;
 
 	/* get current queue index from software */
 	in_index = pp->req_idx;
 
 	crqb = (struct mv_crqb_iie *) &pp->crqb[in_index];
-	crqb->addr = cpu_to_le32(pp->sg_tbl_dma[qc->tag] & 0xffffffff);
-	crqb->addr_hi = cpu_to_le32((pp->sg_tbl_dma[qc->tag] >> 16) >> 16);
+	crqb->addr = cpu_to_le32(pp->sg_tbl_dma[qc->hw_tag] & 0xffffffff);
+	crqb->addr_hi = cpu_to_le32((pp->sg_tbl_dma[qc->hw_tag] >> 16) >> 16);
 	crqb->flags = cpu_to_le32(flags);
 
 	crqb->ata_cmd[0] = cpu_to_le32(
@@ -2539,7 +2539,7 @@ static int mv_handle_fbs_ncq_dev_err(struct ata_port *ap)
 	failed_links = hweight16(new_map);
 
 	ata_port_info(ap,
-		      "%s: pmp_map=%04x qc_map=%04x failed_links=%d nr_active_links=%d\n",
+		      "%s: pmp_map=%04x qc_map=%04llx failed_links=%d nr_active_links=%d\n",
 		      __func__, pp->delayed_eh_pmp_map,
 		      ap->qc_active, failed_links,
 		      ap->nr_active_links);
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 8c683ddd0f58..10ae11aa1926 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -400,7 +400,7 @@ static struct scsi_host_template nv_adma_sht = {
 
 static struct scsi_host_template nv_swncq_sht = {
 	ATA_NCQ_SHT(DRV_NAME),
-	.can_queue		= ATA_MAX_QUEUE,
+	.can_queue		= ATA_MAX_QUEUE - 1,
 	.sg_tablesize		= LIBATA_MAX_PRD,
 	.dma_boundary		= ATA_DMA_BOUNDARY,
 	.slave_configure	= nv_swncq_slave_config,
@@ -740,32 +740,16 @@ static int nv_adma_slave_config(struct scsi_device *sdev)
 	sdev1 = ap->host->ports[1]->link.device[0].sdev;
 	if ((port0->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) ||
 	    (port1->flags & NV_ADMA_ATAPI_SETUP_COMPLETE)) {
-		/** We have to set the DMA mask to 32-bit if either port is in
-		    ATAPI mode, since they are on the same PCI device which is
-		    used for DMA mapping. If we set the mask we also need to set
-		    the bounce limit on both ports to ensure that the block
-		    layer doesn't feed addresses that cause DMA mapping to
-		    choke. If either SCSI device is not allocated yet, it's OK
-		    since that port will discover its correct setting when it
-		    does get allocated.
-		    Note: Setting 32-bit mask should not fail. */
-		if (sdev0)
-			blk_queue_bounce_limit(sdev0->request_queue,
-					       ATA_DMA_MASK);
-		if (sdev1)
-			blk_queue_bounce_limit(sdev1->request_queue,
-					       ATA_DMA_MASK);
-
-		dma_set_mask(&pdev->dev, ATA_DMA_MASK);
+		/*
+		 * We have to set the DMA mask to 32-bit if either port is in
+		 * ATAPI mode, since they are on the same PCI device which is
+		 * used for DMA mapping.  If either SCSI device is not allocated
+		 * yet, it's OK since that port will discover its correct
+		 * setting when it does get allocated.
+		 */
+		rc = dma_set_mask(&pdev->dev, ATA_DMA_MASK);
 	} else {
-		/** This shouldn't fail as it was set to this value before */
-		dma_set_mask(&pdev->dev, pp->adma_dma_mask);
-		if (sdev0)
-			blk_queue_bounce_limit(sdev0->request_queue,
-					       pp->adma_dma_mask);
-		if (sdev1)
-			blk_queue_bounce_limit(sdev1->request_queue,
-					       pp->adma_dma_mask);
+		rc = dma_set_mask(&pdev->dev, pp->adma_dma_mask);
 	}
 
 	blk_queue_segment_boundary(sdev->request_queue, segment_boundary);
@@ -1131,12 +1115,11 @@ static int nv_adma_port_start(struct ata_port *ap)
 
 	VPRINTK("ENTER\n");
 
-	/* Ensure DMA mask is set to 32-bit before allocating legacy PRD and
-	   pad buffers */
-	rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
-	if (rc)
-		return rc;
-	rc = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+	/*
+	 * Ensure DMA mask is set to 32-bit before allocating legacy PRD and
+	 * pad buffers.
+	 */
+	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (rc)
 		return rc;
 
@@ -1156,13 +1139,16 @@ static int nv_adma_port_start(struct ata_port *ap)
 	pp->notifier_clear_block = pp->gen_block +
 	       NV_ADMA_NOTIFIER_CLEAR + (4 * ap->port_no);
 
-	/* Now that the legacy PRD and padding buffer are allocated we can
-	   safely raise the DMA mask to allocate the CPB/APRD table.
-	   These are allowed to fail since we store the value that ends up
-	   being used to set as the bounce limit in slave_config later if
-	   needed. */
-	dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
-	dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+	/*
+	 * Now that the legacy PRD and padding buffer are allocated we can
+	 * try to raise the DMA mask to allocate the CPB/APRD table.
+	 */
+	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (rc) {
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (rc)
+			return rc;
+	}
 	pp->adma_dma_mask = *dev->dma_mask;
 
 	mem = dmam_alloc_coherent(dev, NV_ADMA_PORT_PRIV_DMA_SZ,
@@ -1356,11 +1342,11 @@ static void nv_adma_fill_sg(struct ata_queued_cmd *qc, struct nv_adma_cpb *cpb)
 
 	for_each_sg(qc->sg, sg, qc->n_elem, si) {
 		aprd = (si < 5) ? &cpb->aprd[si] :
-			       &pp->aprd[NV_ADMA_SGTBL_LEN * qc->tag + (si-5)];
+			&pp->aprd[NV_ADMA_SGTBL_LEN * qc->hw_tag + (si-5)];
 		nv_adma_fill_aprd(qc, sg, si, aprd);
 	}
 	if (si > 5)
-		cpb->next_aprd = cpu_to_le64(((u64)(pp->aprd_dma + NV_ADMA_SGTBL_SZ * qc->tag)));
+		cpb->next_aprd = cpu_to_le64(((u64)(pp->aprd_dma + NV_ADMA_SGTBL_SZ * qc->hw_tag)));
 	else
 		cpb->next_aprd = cpu_to_le64(0);
 }
@@ -1385,7 +1371,7 @@ static int nv_adma_use_reg_mode(struct ata_queued_cmd *qc)
 static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct nv_adma_port_priv *pp = qc->ap->private_data;
-	struct nv_adma_cpb *cpb = &pp->cpb[qc->tag];
+	struct nv_adma_cpb *cpb = &pp->cpb[qc->hw_tag];
 	u8 ctl_flags = NV_CPB_CTL_CPB_VALID |
 		       NV_CPB_CTL_IEN;
 
@@ -1403,7 +1389,7 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
 	wmb();
 
 	cpb->len		= 3;
-	cpb->tag		= qc->tag;
+	cpb->tag		= qc->hw_tag;
 	cpb->next_cpb_idx	= 0;
 
 	/* turn on NCQ flags for NCQ commands */
@@ -1466,9 +1452,9 @@ static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
 		pp->last_issue_ncq = curr_ncq;
 	}
 
-	writew(qc->tag, mmio + NV_ADMA_APPEND);
+	writew(qc->hw_tag, mmio + NV_ADMA_APPEND);
 
-	DPRINTK("Issued tag %u\n", qc->tag);
+	DPRINTK("Issued tag %u\n", qc->hw_tag);
 
 	return 0;
 }
@@ -1730,8 +1716,8 @@ static void nv_swncq_qc_to_dq(struct ata_port *ap, struct ata_queued_cmd *qc)
 
 	/* queue is full */
 	WARN_ON(dq->tail - dq->head == ATA_MAX_QUEUE);
-	dq->defer_bits |= (1 << qc->tag);
-	dq->tag[dq->tail++ & (ATA_MAX_QUEUE - 1)] = qc->tag;
+	dq->defer_bits |= (1 << qc->hw_tag);
+	dq->tag[dq->tail++ & (ATA_MAX_QUEUE - 1)] = qc->hw_tag;
 }
 
 static struct ata_queued_cmd *nv_swncq_qc_from_dq(struct ata_port *ap)
@@ -1796,7 +1782,7 @@ static void nv_swncq_ncq_stop(struct ata_port *ap)
 	u32 sactive;
 	u32 done_mask;
 
-	ata_port_err(ap, "EH in SWNCQ mode,QC:qc_active 0x%X sactive 0x%X\n",
+	ata_port_err(ap, "EH in SWNCQ mode,QC:qc_active 0x%llX sactive 0x%X\n",
 		     ap->qc_active, ap->link.sactive);
 	ata_port_err(ap,
 		"SWNCQ:qc_active 0x%X defer_bits 0x%X last_issue_tag 0x%x\n  "
@@ -2010,7 +1996,7 @@ static void nv_swncq_fill_sg(struct ata_queued_cmd *qc)
 	struct ata_bmdma_prd *prd;
 	unsigned int si, idx;
 
-	prd = pp->prd + ATA_MAX_PRD * qc->tag;
+	prd = pp->prd + ATA_MAX_PRD * qc->hw_tag;
 
 	idx = 0;
 	for_each_sg(qc->sg, sg, qc->n_elem, si) {
@@ -2048,16 +2034,16 @@ static unsigned int nv_swncq_issue_atacmd(struct ata_port *ap,
 
 	DPRINTK("Enter\n");
 
-	writel((1 << qc->tag), pp->sactive_block);
-	pp->last_issue_tag = qc->tag;
-	pp->dhfis_bits &= ~(1 << qc->tag);
-	pp->dmafis_bits &= ~(1 << qc->tag);
-	pp->qc_active |= (0x1 << qc->tag);
+	writel((1 << qc->hw_tag), pp->sactive_block);
+	pp->last_issue_tag = qc->hw_tag;
+	pp->dhfis_bits &= ~(1 << qc->hw_tag);
+	pp->dmafis_bits &= ~(1 << qc->hw_tag);
+	pp->qc_active |= (0x1 << qc->hw_tag);
 
 	ap->ops->sff_tf_load(ap, &qc->tf);	 /* load tf registers */
 	ap->ops->sff_exec_command(ap, &qc->tf);
 
-	DPRINTK("Issued tag %u\n", qc->tag);
+	DPRINTK("Issued tag %u\n", qc->hw_tag);
 
 	return 0;
 }
@@ -2207,7 +2193,7 @@ static void nv_swncq_dmafis(struct ata_port *ap)
 	rw = qc->tf.flags & ATA_TFLAG_WRITE;
 
 	/* load PRD table addr. */
-	iowrite32(pp->prd_dma + ATA_PRD_TBL_SZ * qc->tag,
+	iowrite32(pp->prd_dma + ATA_PRD_TBL_SZ * qc->hw_tag,
 		  ap->ioaddr.bmdma_addr + ATA_DMA_TABLE_OFS);
 
 	/* specify data direction, triple-check start bit is clear */
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 4b1995e2d044..319f517137cd 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -285,13 +285,13 @@ static const struct sil24_cerr_info {
 	[PORT_CERR_INCONSISTENT] = { AC_ERR_HSM, ATA_EH_RESET,
 				     "protocol mismatch" },
 	[PORT_CERR_DIRECTION]	= { AC_ERR_HSM, ATA_EH_RESET,
-				    "data directon mismatch" },
+				    "data direction mismatch" },
 	[PORT_CERR_UNDERRUN]	= { AC_ERR_HSM, ATA_EH_RESET,
 				    "ran out of SGEs while writing" },
 	[PORT_CERR_OVERRUN]	= { AC_ERR_HSM, ATA_EH_RESET,
 				    "ran out of SGEs while reading" },
 	[PORT_CERR_PKT_PROT]	= { AC_ERR_HSM, ATA_EH_RESET,
-				    "invalid data directon for ATAPI CDB" },
+				    "invalid data direction for ATAPI CDB" },
 	[PORT_CERR_SGT_BOUNDARY] = { AC_ERR_SYSTEM, ATA_EH_RESET,
 				     "SGT not on qword boundary" },
 	[PORT_CERR_SGT_TGTABRT]	= { AC_ERR_HOST_BUS, ATA_EH_RESET,
@@ -849,7 +849,7 @@ static void sil24_qc_prep(struct ata_queued_cmd *qc)
 	struct sil24_sge *sge;
 	u16 ctrl = 0;
 
-	cb = &pp->cmd_block[sil24_tag(qc->tag)];
+	cb = &pp->cmd_block[sil24_tag(qc->hw_tag)];
 
 	if (!ata_is_atapi(qc->tf.protocol)) {
 		prb = &cb->ata.prb;
@@ -891,7 +891,7 @@ static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc)
 	struct ata_port *ap = qc->ap;
 	struct sil24_port_priv *pp = ap->private_data;
 	void __iomem *port = sil24_port_base(ap);
-	unsigned int tag = sil24_tag(qc->tag);
+	unsigned int tag = sil24_tag(qc->hw_tag);
 	dma_addr_t paddr;
 	void __iomem *activate;
 
@@ -911,7 +911,7 @@ static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc)
 
 static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc)
 {
-	sil24_read_tf(qc->ap, qc->tag, &qc->result_tf);
+	sil24_read_tf(qc->ap, qc->hw_tag, &qc->result_tf);
 	return true;
 }
 
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index d97c05690faa..4e46dc9e41ad 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -191,7 +191,7 @@ static char *res_strings[] = {
 	"reserved 37",
 	"reserved 38",
 	"reserved 39",
-	"reseverd 40",
+	"reserved 40",
 	"reserved 41", 
 	"reserved 42", 
 	"reserved 43", 
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 44abb8a0a5e5..be076606d30e 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -671,7 +671,7 @@ static void ia_tx_poll (IADEV *iadev) {
           if ((vcc->pop) && (skb1->len != 0))
           {
              vcc->pop(vcc, skb1);
-             IF_EVENT(printk("Tansmit Done - skb 0x%lx return\n",
+             IF_EVENT(printk("Transmit Done - skb 0x%lx return\n",
                                                           (long)skb1);)
           }
           else 
@@ -1665,7 +1665,7 @@ static void tx_intr(struct atm_dev *dev)
 	status = readl(iadev->seg_reg+SEG_INTR_STATUS_REG);  
         if (status & TRANSMIT_DONE){
 
-           IF_EVENT(printk("Tansmit Done Intr logic run\n");)
+           IF_EVENT(printk("Transmit Done Intr logic run\n");)
            spin_lock_irqsave(&iadev->tx_lock, flags);
            ia_tx_poll(iadev);
            spin_unlock_irqrestore(&iadev->tx_lock, flags);
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index 1ef67db03c8e..a8d2eb0ceb8d 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -28,6 +28,7 @@
 #include <asm/io.h>
 #include <linux/atomic.h>
 #include <linux/uaccess.h>
+#include <linux/nospec.h>
 
 #include "uPD98401.h"
 #include "uPD98402.h"
@@ -1150,8 +1151,8 @@ static void eprom_get_byte(struct zatm_dev *zatm_dev, unsigned char *byte,
 }
 
 
-static unsigned char eprom_try_esi(struct atm_dev *dev, unsigned short cmd,
-				   int offset, int swap)
+static int eprom_try_esi(struct atm_dev *dev, unsigned short cmd, int offset,
+			 int swap)
 {
 	unsigned char buf[ZEPROM_SIZE];
 	struct zatm_dev *zatm_dev;
@@ -1458,6 +1459,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 					return -EFAULT;
 				if (pool < 0 || pool > ZATM_LAST_POOL)
 					return -EINVAL;
+				pool = array_index_nospec(pool,
+							  ZATM_LAST_POOL + 1);
 				spin_lock_irqsave(&zatm_dev->lock, flags);
 				info = zatm_dev->pool_info[pool];
 				if (cmd == ZATM_GETPOOLZ) {
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 29b0eb452b3a..3e63a900b330 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -70,81 +70,25 @@ config STANDALONE
 	  If unsure, say Y.
 
 config PREVENT_FIRMWARE_BUILD
-	bool "Prevent firmware from being built"
+	bool "Disable drivers features which enable custom firmware building"
 	default y
 	help
-	  Say yes to avoid building firmware. Firmware is usually shipped
-	  with the driver and only when updating the firmware should a
-	  rebuild be made.
-	  If unsure, say Y here.
-
-config FW_LOADER
-	tristate "Userspace firmware loading support" if EXPERT
-	default y
-	---help---
-	  This option is provided for the case where none of the in-tree modules
-	  require userspace firmware loading support, but a module built
-	  out-of-tree does.
-
-config EXTRA_FIRMWARE
-	string "External firmware blobs to build into the kernel binary"
-	depends on FW_LOADER
-	help
-	  Various drivers in the kernel source tree may require firmware,
-	  which is generally available in your distribution's linux-firmware
-	  package.
-
-	  The linux-firmware package should install firmware into
-	  /lib/firmware/ on your system, so they can be loaded by userspace
-	  helpers on request.
-
-	  This option allows firmware to be built into the kernel for the case
-	  where the user either cannot or doesn't want to provide it from
-	  userspace at runtime (for example, when the firmware in question is
-	  required for accessing the boot device, and the user doesn't want to
-	  use an initrd).
-
-	  This option is a string and takes the (space-separated) names of the
-	  firmware files -- the same names that appear in MODULE_FIRMWARE()
-	  and request_firmware() in the source. These files should exist under
-	  the directory specified by the EXTRA_FIRMWARE_DIR option, which is
-	  /lib/firmware by default.
-
-	  For example, you might set CONFIG_EXTRA_FIRMWARE="usb8388.bin", copy
-	  the usb8388.bin file into /lib/firmware, and build the kernel. Then
-	  any request_firmware("usb8388.bin") will be satisfied internally
-	  without needing to call out to userspace.
-
-	  WARNING: If you include additional firmware files into your binary
-	  kernel image that are not available under the terms of the GPL,
-	  then it may be a violation of the GPL to distribute the resulting
-	  image since it combines both GPL and non-GPL work. You should
-	  consult a lawyer of your own before distributing such an image.
-
-config EXTRA_FIRMWARE_DIR
-	string "Firmware blobs root directory"
-	depends on EXTRA_FIRMWARE != ""
-	default "/lib/firmware"
-	help
-	  This option controls the directory in which the kernel build system
-	  looks for the firmware files listed in the EXTRA_FIRMWARE option.
-
-config FW_LOADER_USER_HELPER
-	bool
-
-config FW_LOADER_USER_HELPER_FALLBACK
-	bool "Fallback user-helper invocation for firmware loading"
-	depends on FW_LOADER
-	select FW_LOADER_USER_HELPER
-	help
-	  This option enables / disables the invocation of user-helper
-	  (e.g. udev) for loading firmware files as a fallback after the
-	  direct file loading in kernel fails.  The user-mode helper is
-	  no longer required unless you have a special firmware file that
-	  resides in a non-standard path. Moreover, the udev support has
-	  been deprecated upstream.
-
-	  If you are unsure about this, say N here.
+	  Say yes to disable driver features which enable building a custom
+	  driver firmware at kernel build time. These drivers do not use the
+	  kernel firmware API to load firmware (CONFIG_FW_LOADER), instead they
+	  use their own custom loading mechanism. The required firmware is
+	  usually shipped with the driver, building the driver firmware
+	  should only be needed if you have an updated firmware source.
+
+	  Firmware should not be being built as part of kernel, these days
+	  you should always prevent this and say Y here. There are only two
+	  old drivers which enable building of its firmware at kernel build
+	  time:
+
+	    o CONFIG_WANXL through CONFIG_WANXL_BUILD_FIRMWARE
+	    o CONFIG_SCSI_AIC79XX through CONFIG_AIC79XX_BUILD_FIRMWARE
+
+source "drivers/base/firmware_loader/Kconfig"
 
 config WANT_DEV_COREDUMP
 	bool
diff --git a/drivers/base/base.h b/drivers/base/base.h
index d800de650fa5..a75c3025fb78 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -161,3 +161,6 @@ extern void device_links_driver_cleanup(struct device *dev);
 extern void device_links_no_driver(struct device *dev);
 extern bool device_links_busy(struct device *dev);
 extern void device_links_unbind_consumers(struct device *dev);
+
+/* device pm support */
+void device_pm_move_to_tail(struct device *dev);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index ef6183306b40..8bfd27ec73d6 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -184,10 +184,10 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf,
 
 	dev = bus_find_device_by_name(bus, NULL, buf);
 	if (dev && dev->driver == drv) {
-		if (dev->parent)	/* Needed for USB */
+		if (dev->parent && dev->bus->need_parent_lock)
 			device_lock(dev->parent);
 		device_release_driver(dev);
-		if (dev->parent)
+		if (dev->parent && dev->bus->need_parent_lock)
 			device_unlock(dev->parent);
 		err = count;
 	}
@@ -211,12 +211,12 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf,
 
 	dev = bus_find_device_by_name(bus, NULL, buf);
 	if (dev && dev->driver == NULL && driver_match_device(drv, dev)) {
-		if (dev->parent)	/* Needed for USB */
+		if (dev->parent && bus->need_parent_lock)
 			device_lock(dev->parent);
 		device_lock(dev);
 		err = driver_probe_device(drv, dev);
 		device_unlock(dev);
-		if (dev->parent)
+		if (dev->parent && bus->need_parent_lock)
 			device_unlock(dev->parent);
 
 		if (err > 0) {
@@ -735,10 +735,10 @@ static int __must_check bus_rescan_devices_helper(struct device *dev,
 	int ret = 0;
 
 	if (!dev->driver) {
-		if (dev->parent)	/* Needed for USB */
+		if (dev->parent && dev->bus->need_parent_lock)
 			device_lock(dev->parent);
 		ret = device_attach(dev);
-		if (dev->parent)
+		if (dev->parent && dev->bus->need_parent_lock)
 			device_unlock(dev->parent);
 	}
 	return ret < 0 ? ret : 0;
@@ -770,10 +770,10 @@ EXPORT_SYMBOL_GPL(bus_rescan_devices);
 int device_reprobe(struct device *dev)
 {
 	if (dev->driver) {
-		if (dev->parent)        /* Needed for USB */
+		if (dev->parent && dev->bus->need_parent_lock)
 			device_lock(dev->parent);
 		device_release_driver(dev);
-		if (dev->parent)
+		if (dev->parent && dev->bus->need_parent_lock)
 			device_unlock(dev->parent);
 	}
 	return bus_rescan_devices_helper(dev, NULL);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b610816eb887..36622b52e419 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -145,6 +145,26 @@ static int device_reorder_to_tail(struct device *dev, void *not_used)
 }
 
 /**
+ * device_pm_move_to_tail - Move set of devices to the end of device lists
+ * @dev: Device to move
+ *
+ * This is a device_reorder_to_tail() wrapper taking the requisite locks.
+ *
+ * It moves the @dev along with all of its children and all of its consumers
+ * to the ends of the device_kset and dpm_list, recursively.
+ */
+void device_pm_move_to_tail(struct device *dev)
+{
+	int idx;
+
+	idx = device_links_read_lock();
+	device_pm_lock();
+	device_reorder_to_tail(dev, NULL);
+	device_pm_unlock();
+	device_links_read_unlock(idx);
+}
+
+/**
  * device_link_add - Create a link between two devices.
  * @consumer: Consumer end of the link.
  * @supplier: Supplier end of the link.
@@ -1467,7 +1487,7 @@ class_dir_create_and_add(struct class *class, struct kobject *parent_kobj)
 
 	dir = kzalloc(sizeof(*dir), GFP_KERNEL);
 	if (!dir)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	dir->class = class;
 	kobject_init(&dir->kobj, &class_dir_ktype);
@@ -1477,7 +1497,7 @@ class_dir_create_and_add(struct class *class, struct kobject *parent_kobj)
 	retval = kobject_add(&dir->kobj, parent_kobj, "%s", class->name);
 	if (retval < 0) {
 		kobject_put(&dir->kobj);
-		return NULL;
+		return ERR_PTR(retval);
 	}
 	return &dir->kobj;
 }
@@ -1784,6 +1804,10 @@ int device_add(struct device *dev)
 
 	parent = get_device(dev->parent);
 	kobj = get_device_parent(dev, parent);
+	if (IS_ERR(kobj)) {
+		error = PTR_ERR(kobj);
+		goto parent_error;
+	}
 	if (kobj)
 		dev->kobj.parent = kobj;
 
@@ -1882,6 +1906,7 @@ done:
 	kobject_del(&dev->kobj);
  Error:
 	cleanup_glue_dir(dev, glue_dir);
+parent_error:
 	put_device(parent);
 name_error:
 	kfree(dev->p);
@@ -2406,7 +2431,7 @@ static void device_create_release(struct device *dev)
 	kfree(dev);
 }
 
-static struct device *
+static __printf(6, 0) struct device *
 device_create_groups_vargs(struct class *class, struct device *parent,
 			   dev_t devt, void *drvdata,
 			   const struct attribute_group **groups,
@@ -2684,7 +2709,7 @@ static int device_move_class_links(struct device *dev,
 /**
  * device_move - moves a device to a new parent
  * @dev: the pointer to the struct device to be moved
- * @new_parent: the new parent of the device (can by NULL)
+ * @new_parent: the new parent of the device (can be NULL)
  * @dpm_order: how to reorder the dpm_list
  */
 int device_move(struct device *dev, struct device *new_parent,
@@ -2701,6 +2726,11 @@ int device_move(struct device *dev, struct device *new_parent,
 	device_pm_lock();
 	new_parent = get_device(new_parent);
 	new_parent_kobj = get_device_parent(dev, new_parent);
+	if (IS_ERR(new_parent_kobj)) {
+		error = PTR_ERR(new_parent_kobj);
+		put_device(new_parent);
+		goto out;
+	}
 
 	pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev),
 		 __func__, new_parent ? dev_name(new_parent) : "<NULL>");
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 2da998baa75c..30cc9c877ebb 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -534,14 +534,22 @@ ssize_t __weak cpu_show_spectre_v2(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
+					  struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
+static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
 	&dev_attr_spectre_v1.attr,
 	&dev_attr_spectre_v2.attr,
+	&dev_attr_spec_store_bypass.attr,
 	NULL
 };
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index c9f54089429b..fb4e2df68d95 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -122,9 +122,7 @@ static void deferred_probe_work_func(struct work_struct *work)
 		 * the list is a good order for suspend but deferred
 		 * probe makes that very unsafe.
 		 */
-		device_pm_lock();
-		device_pm_move_last(dev);
-		device_pm_unlock();
+		device_pm_move_to_tail(dev);
 
 		dev_dbg(dev, "Retrying from deferred list\n");
 		if (initcall_debug && !initcalls_done)
@@ -582,7 +580,7 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
 	pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
 		 drv->bus->name, __func__, dev_name(dev), drv->name);
 
-	pm_runtime_get_suppliers(dev);
+	pm_runtime_resume_suppliers(dev);
 	if (dev->parent)
 		pm_runtime_get_sync(dev->parent);
 
@@ -593,7 +591,6 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
 	if (dev->parent)
 		pm_runtime_put(dev->parent);
 
-	pm_runtime_put_suppliers(dev);
 	return ret;
 }
 
@@ -817,13 +814,13 @@ static int __driver_attach(struct device *dev, void *data)
 		return ret;
 	} /* ret > 0 means positive match */
 
-	if (dev->parent)	/* Needed for USB */
+	if (dev->parent && dev->bus->need_parent_lock)
 		device_lock(dev->parent);
 	device_lock(dev);
 	if (!dev->driver)
 		driver_probe_device(drv, dev);
 	device_unlock(dev);
-	if (dev->parent)
+	if (dev->parent && dev->bus->need_parent_lock)
 		device_unlock(dev->parent);
 
 	return 0;
@@ -919,7 +916,7 @@ void device_release_driver_internal(struct device *dev,
 				    struct device_driver *drv,
 				    struct device *parent)
 {
-	if (parent)
+	if (parent && dev->bus->need_parent_lock)
 		device_lock(parent);
 
 	device_lock(dev);
@@ -927,7 +924,7 @@ void device_release_driver_internal(struct device *dev,
 		__device_release_driver(dev, parent);
 
 	device_unlock(dev);
-	if (parent)
+	if (parent && dev->bus->need_parent_lock)
 		device_unlock(parent);
 }
 
diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c
index 1e6396bb807b..597d40893862 100644
--- a/drivers/base/dma-coherent.c
+++ b/drivers/base/dma-coherent.c
@@ -312,8 +312,9 @@ static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
  * This checks whether the memory was allocated from the per-device
  * coherent memory pool and if so, maps that memory to the provided vma.
  *
- * Returns 1 if we correctly mapped the memory, or 0 if the caller should
- * proceed with mapping memory from generic pools.
+ * Returns 1 if @vaddr belongs to the device coherent pool and the caller
+ * should return @ret, or 0 if they should proceed with mapping memory from
+ * generic areas.
  */
 int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
 			   void *vaddr, size_t size, int *ret)
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index 3b118353ea17..f831a582209c 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -226,7 +226,6 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 #ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
 	unsigned long user_count = vma_pages(vma);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
 	unsigned long off = vma->vm_pgoff;
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -234,12 +233,11 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
-	if (off < count && user_count <= (count - off)) {
+	if (off < count && user_count <= (count - off))
 		ret = remap_pfn_range(vma, vma->vm_start,
-				      pfn + off,
+				      page_to_pfn(virt_to_page(cpu_addr)) + off,
 				      user_count << PAGE_SHIFT,
 				      vma->vm_page_prot);
-	}
 #endif	/* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
 
 	return ret;
@@ -331,36 +329,13 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
 #endif
 
 /*
- * Common configuration to enable DMA API use for a device
+ * enables DMA API use for a device
  */
-#include <linux/pci.h>
-
 int dma_configure(struct device *dev)
 {
-	struct device *bridge = NULL, *dma_dev = dev;
-	enum dev_dma_attr attr;
-	int ret = 0;
-
-	if (dev_is_pci(dev)) {
-		bridge = pci_get_host_bridge_device(to_pci_dev(dev));
-		dma_dev = bridge;
-		if (IS_ENABLED(CONFIG_OF) && dma_dev->parent &&
-		    dma_dev->parent->of_node)
-			dma_dev = dma_dev->parent;
-	}
-
-	if (dma_dev->of_node) {
-		ret = of_dma_configure(dev, dma_dev->of_node);
-	} else if (has_acpi_companion(dma_dev)) {
-		attr = acpi_get_dma_attr(to_acpi_device_node(dma_dev->fwnode));
-		if (attr != DEV_DMA_NOT_SUPPORTED)
-			ret = acpi_dma_configure(dev, attr);
-	}
-
-	if (bridge)
-		pci_put_host_bridge_device(bridge);
-
-	return ret;
+	if (dev->bus->dma_configure)
+		return dev->bus->dma_configure(dev);
+	return 0;
 }
 
 void dma_deconfigure(struct device *dev)
diff --git a/drivers/base/driver.c b/drivers/base/driver.c
index ba912558a510..857c8f1b876e 100644
--- a/drivers/base/driver.c
+++ b/drivers/base/driver.c
@@ -148,7 +148,11 @@ int driver_register(struct device_driver *drv)
 	int ret;
 	struct device_driver *other;
 
-	BUG_ON(!drv->bus->p);
+	if (!drv->bus->p) {
+		pr_err("Driver '%s' was unable to register with bus_type '%s' because the bus was not initialized.\n",
+			   drv->name, drv->bus->name);
+		return -EINVAL;
+	}
 
 	if ((drv->bus->probe && drv->probe) ||
 	    (drv->bus->remove && drv->remove) ||
diff --git a/drivers/base/firmware_loader/Kconfig b/drivers/base/firmware_loader/Kconfig
new file mode 100644
index 000000000000..eb15d976a9ea
--- /dev/null
+++ b/drivers/base/firmware_loader/Kconfig
@@ -0,0 +1,154 @@
+menu "Firmware loader"
+
+config FW_LOADER
+	tristate "Firmware loading facility" if EXPERT
+	default y
+	help
+	  This enables the firmware loading facility in the kernel. The kernel
+	  will first look for built-in firmware, if it has any. Next, it will
+	  look for the requested firmware in a series of filesystem paths:
+
+		o firmware_class path module parameter or kernel boot param
+		o /lib/firmware/updates/UTS_RELEASE
+		o /lib/firmware/updates
+		o /lib/firmware/UTS_RELEASE
+		o /lib/firmware
+
+	  Enabling this feature only increases your kernel image by about
+	  828 bytes, enable this option unless you are certain you don't
+	  need firmware.
+
+	  You typically want this built-in (=y) but you can also enable this
+	  as a module, in which case the firmware_class module will be built.
+	  You also want to be sure to enable this built-in if you are going to
+	  enable built-in firmware (CONFIG_EXTRA_FIRMWARE).
+
+if FW_LOADER
+
+config EXTRA_FIRMWARE
+	string "Build named firmware blobs into the kernel binary"
+	help
+	  Device drivers which require firmware can typically deal with
+	  having the kernel load firmware from the various supported
+	  /lib/firmware/ paths. This option enables you to build into the
+	  kernel firmware files. Built-in firmware searches are preceded
+	  over firmware lookups using your filesystem over the supported
+	  /lib/firmware paths documented on CONFIG_FW_LOADER.
+
+	  This may be useful for testing or if the firmware is required early on
+	  in boot and cannot rely on the firmware being placed in an initrd or
+	  initramfs.
+
+	  This option is a string and takes the (space-separated) names of the
+	  firmware files -- the same names that appear in MODULE_FIRMWARE()
+	  and request_firmware() in the source. These files should exist under
+	  the directory specified by the EXTRA_FIRMWARE_DIR option, which is
+	  /lib/firmware by default.
+
+	  For example, you might set CONFIG_EXTRA_FIRMWARE="usb8388.bin", copy
+	  the usb8388.bin file into /lib/firmware, and build the kernel. Then
+	  any request_firmware("usb8388.bin") will be satisfied internally
+	  inside the kernel without ever looking at your filesystem at runtime.
+
+	  WARNING: If you include additional firmware files into your binary
+	  kernel image that are not available under the terms of the GPL,
+	  then it may be a violation of the GPL to distribute the resulting
+	  image since it combines both GPL and non-GPL work. You should
+	  consult a lawyer of your own before distributing such an image.
+
+config EXTRA_FIRMWARE_DIR
+	string "Firmware blobs root directory"
+	depends on EXTRA_FIRMWARE != ""
+	default "/lib/firmware"
+	help
+	  This option controls the directory in which the kernel build system
+	  looks for the firmware files listed in the EXTRA_FIRMWARE option.
+
+config FW_LOADER_USER_HELPER
+	bool "Enable the firmware sysfs fallback mechanism"
+	help
+	  This option enables a sysfs loading facility to enable firmware
+	  loading to the kernel through userspace as a fallback mechanism
+	  if and only if the kernel's direct filesystem lookup for the
+	  firmware failed using the different /lib/firmware/ paths, or the
+	  path specified in the firmware_class path module parameter, or the
+	  firmware_class path kernel boot parameter if the firmware_class is
+	  built-in. For details on how to work with the sysfs fallback mechanism
+	  refer to Documentation/driver-api/firmware/fallback-mechanisms.rst.
+
+	  The direct filesystem lookup for firmware is always used first now.
+
+	  If the kernel's direct filesystem lookup for firmware fails to find
+	  the requested firmware a sysfs fallback loading facility is made
+	  available and userspace is informed about this through uevents.
+	  The uevent can be suppressed if the driver explicitly requested it,
+	  this is known as the driver using the custom fallback mechanism.
+	  If the custom fallback mechanism is used userspace must always
+	  acknowledge failure to find firmware as the timeout for the fallback
+	  mechanism is disabled, and failed requests will linger forever.
+
+	  This used to be the default firmware loading facility, and udev used
+	  to listen for uvents to load firmware for the kernel. The firmware
+	  loading facility functionality in udev has been removed, as such it
+	  can no longer be relied upon as a fallback mechanism. Linux no longer
+	  relies on or uses a fallback mechanism in userspace. If you need to
+	  rely on one refer to the permissively licensed firmwared:
+
+	  https://github.com/teg/firmwared
+
+	  Since this was the default firmware loading facility at one point,
+	  old userspace may exist which relies upon it, and as such this
+	  mechanism can never be removed from the kernel.
+
+	  You should only enable this functionality if you are certain you
+	  require a fallback mechanism and have a userspace mechanism ready to
+	  load firmware in case it is not found. One main reason for this may
+	  be if you have drivers which require firmware built-in and for
+	  whatever reason cannot place the required firmware in initramfs.
+	  Another reason kernels may have this feature enabled is to support a
+	  driver which explicitly relies on this fallback mechanism. Only two
+	  drivers need this today:
+
+	    o CONFIG_LEDS_LP55XX_COMMON
+	    o CONFIG_DELL_RBU
+
+	  Outside of supporting the above drivers, another reason for needing
+	  this may be that your firmware resides outside of the paths the kernel
+	  looks for and cannot possibly be specified using the firmware_class
+	  path module parameter or kernel firmware_class path boot parameter
+	  if firmware_class is built-in.
+
+	  A modern use case may be to temporarily mount a custom partition
+	  during provisioning which is only accessible to userspace, and then
+	  to use it to look for and fetch the required firmware. Such type of
+	  driver functionality may not even ever be desirable upstream by
+	  vendors, and as such is only required to be supported as an interface
+	  for provisioning. Since udev's firmware loading facility has been
+	  removed you can use firmwared or a fork of it to customize how you
+	  want to load firmware based on uevents issued.
+
+	  Enabling this option will increase your kernel image size by about
+	  13436 bytes.
+
+	  If you are unsure about this, say N here, unless you are Linux
+	  distribution and need to support the above two drivers, or you are
+	  certain you need to support some really custom firmware loading
+	  facility in userspace.
+
+config FW_LOADER_USER_HELPER_FALLBACK
+	bool "Force the firmware sysfs fallback mechanism when possible"
+	depends on FW_LOADER_USER_HELPER
+	help
+	  Enabling this option forces a sysfs userspace fallback mechanism
+	  to be used for all firmware requests which explicitly do not disable a
+	  a fallback mechanism. Firmware calls which do prohibit a fallback
+	  mechanism is request_firmware_direct(). This option is kept for
+          backward compatibility purposes given this precise mechanism can also
+	  be enabled by setting the proc sysctl value to true:
+
+	       /proc/sys/kernel/firmware_config/force_sysfs_fallback
+
+	  If you are unsure about this, say N here.
+
+endif # FW_LOADER
+endmenu
diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 31b5015b59fe..b676a99c469c 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -125,7 +125,7 @@ static ssize_t timeout_show(struct class *class, struct class_attribute *attr,
 }
 
 /**
- * firmware_timeout_store - set number of seconds to wait for firmware
+ * firmware_timeout_store() - set number of seconds to wait for firmware
  * @class: device class pointer
  * @attr: device attribute pointer
  * @buf: buffer to scan for timeout value
@@ -239,7 +239,7 @@ static int map_fw_priv_pages(struct fw_priv *fw_priv)
 }
 
 /**
- * firmware_loading_store - set value in the 'loading' control file
+ * firmware_loading_store() - set value in the 'loading' control file
  * @dev: device pointer
  * @attr: device attribute pointer
  * @buf: buffer to scan for loading control value
@@ -431,7 +431,7 @@ static int fw_realloc_pages(struct fw_sysfs *fw_sysfs, int min_size)
 }
 
 /**
- * firmware_data_write - write method for firmware
+ * firmware_data_write() - write method for firmware
  * @filp: open sysfs file
  * @kobj: kobject for the device
  * @bin_attr: bin_attr structure
@@ -512,7 +512,7 @@ static const struct attribute_group *fw_dev_attr_groups[] = {
 
 static struct fw_sysfs *
 fw_create_instance(struct firmware *firmware, const char *fw_name,
-		   struct device *device, unsigned int opt_flags)
+		   struct device *device, enum fw_opt opt_flags)
 {
 	struct fw_sysfs *fw_sysfs;
 	struct device *f_dev;
@@ -537,15 +537,15 @@ exit:
 }
 
 /**
- * fw_load_sysfs_fallback - load a firmware via the syfs fallback mechanism
- * @fw_sysfs: firmware syfs information for the firmware to load
+ * fw_load_sysfs_fallback() - load a firmware via the sysfs fallback mechanism
+ * @fw_sysfs: firmware sysfs information for the firmware to load
  * @opt_flags: flags of options, FW_OPT_*
  * @timeout: timeout to wait for the load
  *
  * In charge of constructing a sysfs fallback interface for firmware loading.
  **/
 static int fw_load_sysfs_fallback(struct fw_sysfs *fw_sysfs,
-				  unsigned int opt_flags, long timeout)
+				  enum fw_opt opt_flags, long timeout)
 {
 	int retval = 0;
 	struct device *f_dev = &fw_sysfs->dev;
@@ -599,7 +599,7 @@ err_put_dev:
 
 static int fw_load_from_user_helper(struct firmware *firmware,
 				    const char *name, struct device *device,
-				    unsigned int opt_flags)
+				    enum fw_opt opt_flags)
 {
 	struct fw_sysfs *fw_sysfs;
 	long timeout;
@@ -640,7 +640,7 @@ out_unlock:
 	return ret;
 }
 
-static bool fw_force_sysfs_fallback(unsigned int opt_flags)
+static bool fw_force_sysfs_fallback(enum fw_opt opt_flags)
 {
 	if (fw_fallback_config.force_sysfs_fallback)
 		return true;
@@ -649,7 +649,7 @@ static bool fw_force_sysfs_fallback(unsigned int opt_flags)
 	return true;
 }
 
-static bool fw_run_sysfs_fallback(unsigned int opt_flags)
+static bool fw_run_sysfs_fallback(enum fw_opt opt_flags)
 {
 	if (fw_fallback_config.ignore_sysfs_fallback) {
 		pr_info_once("Ignoring firmware sysfs fallback due to sysctl knob\n");
@@ -662,14 +662,39 @@ static bool fw_run_sysfs_fallback(unsigned int opt_flags)
 	return fw_force_sysfs_fallback(opt_flags);
 }
 
-int fw_sysfs_fallback(struct firmware *fw, const char *name,
-		      struct device *device,
-		      unsigned int opt_flags,
-		      int ret)
+/**
+ * firmware_fallback_sysfs() - use the fallback mechanism to find firmware
+ * @fw: pointer to firmware image
+ * @name: name of firmware file to look for
+ * @device: device for which firmware is being loaded
+ * @opt_flags: options to control firmware loading behaviour
+ * @ret: return value from direct lookup which triggered the fallback mechanism
+ *
+ * This function is called if direct lookup for the firmware failed, it enables
+ * a fallback mechanism through userspace by exposing a sysfs loading
+ * interface. Userspace is in charge of loading the firmware through the syfs
+ * loading interface. This syfs fallback mechanism may be disabled completely
+ * on a system by setting the proc sysctl value ignore_sysfs_fallback to true.
+ * If this false we check if the internal API caller set the @FW_OPT_NOFALLBACK
+ * flag, if so it would also disable the fallback mechanism. A system may want
+ * to enfoce the sysfs fallback mechanism at all times, it can do this by
+ * setting ignore_sysfs_fallback to false and force_sysfs_fallback to true.
+ * Enabling force_sysfs_fallback is functionally equivalent to build a kernel
+ * with CONFIG_FW_LOADER_USER_HELPER_FALLBACK.
+ **/
+int firmware_fallback_sysfs(struct firmware *fw, const char *name,
+			    struct device *device,
+			    enum fw_opt opt_flags,
+			    int ret)
 {
 	if (!fw_run_sysfs_fallback(opt_flags))
 		return ret;
 
-	dev_warn(device, "Falling back to user helper\n");
+	if (!(opt_flags & FW_OPT_NO_WARN))
+		dev_warn(device, "Falling back to syfs fallback for: %s\n",
+				 name);
+	else
+		dev_dbg(device, "Falling back to sysfs fallback for: %s\n",
+				name);
 	return fw_load_from_user_helper(fw, name, device, opt_flags);
 }
diff --git a/drivers/base/firmware_loader/fallback.h b/drivers/base/firmware_loader/fallback.h
index dfebc644ed35..21063503e4ea 100644
--- a/drivers/base/firmware_loader/fallback.h
+++ b/drivers/base/firmware_loader/fallback.h
@@ -5,8 +5,10 @@
 #include <linux/firmware.h>
 #include <linux/device.h>
 
+#include "firmware.h"
+
 /**
- * struct firmware_fallback_config - firmware fallback configuratioon settings
+ * struct firmware_fallback_config - firmware fallback configuration settings
  *
  * Helps describe and fine tune the fallback mechanism.
  *
@@ -29,10 +31,10 @@ struct firmware_fallback_config {
 };
 
 #ifdef CONFIG_FW_LOADER_USER_HELPER
-int fw_sysfs_fallback(struct firmware *fw, const char *name,
-		      struct device *device,
-		      unsigned int opt_flags,
-		      int ret);
+int firmware_fallback_sysfs(struct firmware *fw, const char *name,
+			    struct device *device,
+			    enum fw_opt opt_flags,
+			    int ret);
 void kill_pending_fw_fallback_reqs(bool only_kill_custom);
 
 void fw_fallback_set_cache_timeout(void);
@@ -41,10 +43,10 @@ void fw_fallback_set_default_timeout(void);
 int register_sysfs_loader(void);
 void unregister_sysfs_loader(void);
 #else /* CONFIG_FW_LOADER_USER_HELPER */
-static inline int fw_sysfs_fallback(struct firmware *fw, const char *name,
-				    struct device *device,
-				    unsigned int opt_flags,
-				    int ret)
+static inline int firmware_fallback_sysfs(struct firmware *fw, const char *name,
+					  struct device *device,
+					  enum fw_opt opt_flags,
+					  int ret)
 {
 	/* Keep carrying over the same error */
 	return ret;
diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h
index 64acbb1a392c..4c1395f8e7ed 100644
--- a/drivers/base/firmware_loader/firmware.h
+++ b/drivers/base/firmware_loader/firmware.h
@@ -2,6 +2,7 @@
 #ifndef __FIRMWARE_LOADER_H
 #define __FIRMWARE_LOADER_H
 
+#include <linux/bitops.h>
 #include <linux/firmware.h>
 #include <linux/types.h>
 #include <linux/kref.h>
@@ -10,13 +11,33 @@
 
 #include <generated/utsrelease.h>
 
-/* firmware behavior options */
-#define FW_OPT_UEVENT			(1U << 0)
-#define FW_OPT_NOWAIT			(1U << 1)
-#define FW_OPT_USERHELPER		(1U << 2)
-#define FW_OPT_NO_WARN			(1U << 3)
-#define FW_OPT_NOCACHE			(1U << 4)
-#define FW_OPT_NOFALLBACK		(1U << 5)
+/**
+ * enum fw_opt - options to control firmware loading behaviour
+ *
+ * @FW_OPT_UEVENT: Enables the fallback mechanism to send a kobject uevent
+ *	when the firmware is not found. Userspace is in charge to load the
+ *	firmware using the sysfs loading facility.
+ * @FW_OPT_NOWAIT: Used to describe the firmware request is asynchronous.
+ * @FW_OPT_USERHELPER: Enable the fallback mechanism, in case the direct
+ *	filesystem lookup fails at finding the firmware.  For details refer to
+ *	firmware_fallback_sysfs().
+ * @FW_OPT_NO_WARN: Quiet, avoid printing warning messages.
+ * @FW_OPT_NOCACHE: Disables firmware caching. Firmware caching is used to
+ *	cache the firmware upon suspend, so that upon resume races against the
+ *	firmware file lookup on storage is avoided. Used for calls where the
+ *	file may be too big, or where the driver takes charge of its own
+ *	firmware caching mechanism.
+ * @FW_OPT_NOFALLBACK: Disable the fallback mechanism. Takes precedence over
+ *	&FW_OPT_UEVENT and &FW_OPT_USERHELPER.
+ */
+enum fw_opt {
+	FW_OPT_UEVENT =         BIT(0),
+	FW_OPT_NOWAIT =         BIT(1),
+	FW_OPT_USERHELPER =     BIT(2),
+	FW_OPT_NO_WARN =        BIT(3),
+	FW_OPT_NOCACHE =        BIT(4),
+	FW_OPT_NOFALLBACK =     BIT(5),
+};
 
 enum fw_status {
 	FW_STATUS_UNKNOWN,
@@ -110,6 +131,6 @@ static inline void fw_state_done(struct fw_priv *fw_priv)
 }
 
 int assign_fw(struct firmware *fw, struct device *device,
-	      unsigned int opt_flags);
+	      enum fw_opt opt_flags);
 
 #endif /* __FIRMWARE_LOADER_H */
diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index eb34089e4299..0943e7065e0e 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -443,7 +443,7 @@ static int fw_add_devm_name(struct device *dev, const char *name)
 #endif
 
 int assign_fw(struct firmware *fw, struct device *device,
-	      unsigned int opt_flags)
+	      enum fw_opt opt_flags)
 {
 	struct fw_priv *fw_priv = fw->priv;
 	int ret;
@@ -558,7 +558,7 @@ static void fw_abort_batch_reqs(struct firmware *fw)
 static int
 _request_firmware(const struct firmware **firmware_p, const char *name,
 		  struct device *device, void *buf, size_t size,
-		  unsigned int opt_flags)
+		  enum fw_opt opt_flags)
 {
 	struct firmware *fw = NULL;
 	int ret;
@@ -581,7 +581,7 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 			dev_warn(device,
 				 "Direct firmware load for %s failed with error %d\n",
 				 name, ret);
-		ret = fw_sysfs_fallback(fw, name, device, opt_flags, ret);
+		ret = firmware_fallback_sysfs(fw, name, device, opt_flags, ret);
 	} else
 		ret = assign_fw(fw, device, opt_flags);
 
@@ -597,7 +597,7 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 }
 
 /**
- * request_firmware: - send firmware request and wait for it
+ * request_firmware() - send firmware request and wait for it
  * @firmware_p: pointer to firmware image
  * @name: name of firmware file
  * @device: device for which firmware is being loaded
@@ -632,7 +632,34 @@ request_firmware(const struct firmware **firmware_p, const char *name,
 EXPORT_SYMBOL(request_firmware);
 
 /**
- * request_firmware_direct: - load firmware directly without usermode helper
+ * firmware_request_nowarn() - request for an optional fw module
+ * @firmware: pointer to firmware image
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded
+ *
+ * This function is similar in behaviour to request_firmware(), except
+ * it doesn't produce warning messages when the file is not found.
+ * The sysfs fallback mechanism is enabled if direct filesystem lookup fails,
+ * however, however failures to find the firmware file with it are still
+ * suppressed. It is therefore up to the driver to check for the return value
+ * of this call and to decide when to inform the users of errors.
+ **/
+int firmware_request_nowarn(const struct firmware **firmware, const char *name,
+			    struct device *device)
+{
+	int ret;
+
+	/* Need to pin this module until return */
+	__module_get(THIS_MODULE);
+	ret = _request_firmware(firmware, name, device, NULL, 0,
+				FW_OPT_UEVENT | FW_OPT_NO_WARN);
+	module_put(THIS_MODULE);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(firmware_request_nowarn);
+
+/**
+ * request_firmware_direct() - load firmware directly without usermode helper
  * @firmware_p: pointer to firmware image
  * @name: name of firmware file
  * @device: device for which firmware is being loaded
@@ -657,7 +684,7 @@ int request_firmware_direct(const struct firmware **firmware_p,
 EXPORT_SYMBOL_GPL(request_firmware_direct);
 
 /**
- * firmware_request_cache: - cache firmware for suspend so resume can use it
+ * firmware_request_cache() - cache firmware for suspend so resume can use it
  * @name: name of firmware file
  * @device: device for which firmware should be cached for
  *
@@ -681,7 +708,7 @@ int firmware_request_cache(struct device *device, const char *name)
 EXPORT_SYMBOL_GPL(firmware_request_cache);
 
 /**
- * request_firmware_into_buf - load firmware into a previously allocated buffer
+ * request_firmware_into_buf() - load firmware into a previously allocated buffer
  * @firmware_p: pointer to firmware image
  * @name: name of firmware file
  * @device: device for which firmware is being loaded and DMA region allocated
@@ -713,7 +740,7 @@ request_firmware_into_buf(const struct firmware **firmware_p, const char *name,
 EXPORT_SYMBOL(request_firmware_into_buf);
 
 /**
- * release_firmware: - release the resource associated with a firmware image
+ * release_firmware() - release the resource associated with a firmware image
  * @fw: firmware resource to release
  **/
 void release_firmware(const struct firmware *fw)
@@ -734,7 +761,7 @@ struct firmware_work {
 	struct device *device;
 	void *context;
 	void (*cont)(const struct firmware *fw, void *context);
-	unsigned int opt_flags;
+	enum fw_opt opt_flags;
 };
 
 static void request_firmware_work_func(struct work_struct *work)
@@ -755,7 +782,7 @@ static void request_firmware_work_func(struct work_struct *work)
 }
 
 /**
- * request_firmware_nowait - asynchronous version of request_firmware
+ * request_firmware_nowait() - asynchronous version of request_firmware
  * @module: module requesting the firmware
  * @uevent: sends uevent to copy the firmware image if this flag
  *	is non-zero else the firmware copy must be done manually.
@@ -824,7 +851,7 @@ EXPORT_SYMBOL(request_firmware_nowait);
 static ASYNC_DOMAIN_EXCLUSIVE(fw_cache_domain);
 
 /**
- * cache_firmware - cache one firmware image in kernel memory space
+ * cache_firmware() - cache one firmware image in kernel memory space
  * @fw_name: the firmware image name
  *
  * Cache firmware in kernel memory so that drivers can use it when
@@ -866,7 +893,7 @@ static struct fw_priv *lookup_fw_priv(const char *fw_name)
 }
 
 /**
- * uncache_firmware - remove one cached firmware image
+ * uncache_firmware() - remove one cached firmware image
  * @fw_name: the firmware image name
  *
  * Uncache one firmware image which has been cached successfully
@@ -1042,7 +1069,7 @@ static void __device_uncache_fw_images(void)
 }
 
 /**
- * device_cache_fw_images - cache devices' firmware
+ * device_cache_fw_images() - cache devices' firmware
  *
  * If one device called request_firmware or its nowait version
  * successfully before, the firmware names are recored into the
@@ -1075,7 +1102,7 @@ static void device_cache_fw_images(void)
 }
 
 /**
- * device_uncache_fw_images - uncache devices' firmware
+ * device_uncache_fw_images() - uncache devices' firmware
  *
  * uncache all firmwares which have been cached successfully
  * by device_uncache_fw_images earlier
@@ -1092,7 +1119,7 @@ static void device_uncache_fw_images_work(struct work_struct *work)
 }
 
 /**
- * device_uncache_fw_images_delay - uncache devices firmwares
+ * device_uncache_fw_images_delay() - uncache devices firmwares
  * @delay: number of milliseconds to delay uncache device firmwares
  *
  * uncache all devices's firmwares which has been cached successfully
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index bffe8616bd55..f5e560188a18 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -649,13 +649,19 @@ static const struct attribute_group *memory_memblk_attr_groups[] = {
 static
 int register_memory(struct memory_block *memory)
 {
+	int ret;
+
 	memory->dev.bus = &memory_subsys;
 	memory->dev.id = memory->start_section_nr / sections_per_block;
 	memory->dev.release = memory_block_release;
 	memory->dev.groups = memory_memblk_attr_groups;
 	memory->dev.offline = memory->state == MEM_OFFLINE;
 
-	return device_register(&memory->dev);
+	ret = device_register(&memory->dev);
+	if (ret)
+		put_device(&memory->dev);
+
+	return ret;
 }
 
 static int init_memory_block(struct memory_block **memory,
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 7a3a580821e0..a5e821d09656 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -490,7 +490,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
 	return 0;
 }
 
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages,
+		      bool check_nid)
 {
 	unsigned long end_pfn = start_pfn + nr_pages;
 	unsigned long pfn;
@@ -514,7 +515,7 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
 
 		mem_blk = find_memory_block_hinted(mem_sect, mem_blk);
 
-		ret = register_mem_sect_under_node(mem_blk, nid, true);
+		ret = register_mem_sect_under_node(mem_blk, nid, check_nid);
 		if (!err)
 			err = ret;
 
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index 8e22073aeeed..60d6cc618f1c 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -101,6 +101,9 @@ static void platform_msi_update_chip_ops(struct msi_domain_info *info)
 		chip->irq_set_affinity = msi_domain_set_affinity;
 	if (!chip->irq_write_msi_msg)
 		chip->irq_write_msi_msg = platform_msi_write_msg;
+	if (WARN_ON((info->flags & MSI_FLAG_LEVEL_CAPABLE) &&
+		    !(chip->flags & IRQCHIP_SUPPORTS_LEVEL_MSI)))
+		info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
 }
 
 static void platform_msi_free_descs(struct device *dev, int base, int nvec)
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 8075ddc70a17..dff82a3c2caa 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -572,17 +572,16 @@ static int platform_drv_probe(struct device *_dev)
 		return ret;
 
 	ret = dev_pm_domain_attach(_dev, true);
-	if (ret != -EPROBE_DEFER) {
-		if (drv->probe) {
-			ret = drv->probe(dev);
-			if (ret)
-				dev_pm_domain_detach(_dev, true);
-		} else {
-			/* don't fail if just dev_pm_domain_attach failed */
-			ret = 0;
-		}
+	if (ret)
+		goto out;
+
+	if (drv->probe) {
+		ret = drv->probe(dev);
+		if (ret)
+			dev_pm_domain_detach(_dev, true);
 	}
 
+out:
 	if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) {
 		dev_warn(_dev, "probe deferral not supported\n");
 		ret = -ENXIO;
@@ -1130,6 +1129,22 @@ int platform_pm_restore(struct device *dev)
 
 #endif /* CONFIG_HIBERNATE_CALLBACKS */
 
+int platform_dma_configure(struct device *dev)
+{
+	enum dev_dma_attr attr;
+	int ret = 0;
+
+	if (dev->of_node) {
+		ret = of_dma_configure(dev, dev->of_node, true);
+	} else if (has_acpi_companion(dev)) {
+		attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode));
+		if (attr != DEV_DMA_NOT_SUPPORTED)
+			ret = acpi_dma_configure(dev, attr);
+	}
+
+	return ret;
+}
+
 static const struct dev_pm_ops platform_dev_pm_ops = {
 	.runtime_suspend = pm_generic_runtime_suspend,
 	.runtime_resume = pm_generic_runtime_resume,
@@ -1141,8 +1156,8 @@ struct bus_type platform_bus_type = {
 	.dev_groups	= platform_dev_groups,
 	.match		= platform_match,
 	.uevent		= platform_uevent,
+	.dma_configure	= platform_dma_configure,
 	.pm		= &platform_dev_pm_ops,
-	.force_dma	= true,
 };
 EXPORT_SYMBOL_GPL(platform_bus_type);
 
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index f6a9ad52cbbf..7ae62b6355b8 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -98,17 +98,21 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
  * Callers must ensure proper synchronization of this function with power
  * management callbacks.
  *
- * Returns 0 on successfully attached PM domain or negative error code.
+ * Returns 0 on successfully attached PM domain, or when it is found that the
+ * device doesn't need a PM domain, else a negative error code.
  */
 int dev_pm_domain_attach(struct device *dev, bool power_on)
 {
 	int ret;
 
+	if (dev->pm_domain)
+		return 0;
+
 	ret = acpi_dev_pm_attach(dev, power_on);
-	if (ret)
+	if (!ret)
 		ret = genpd_dev_pm_attach(dev);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 1ea0e2502e8e..6f403d6fccb2 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
@@ -1315,7 +1316,6 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 #endif /* CONFIG_PM_SLEEP */
 
 static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
-					struct generic_pm_domain *genpd,
 					struct gpd_timing_data *td)
 {
 	struct generic_pm_domain_data *gpd_data;
@@ -1377,24 +1377,19 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 			    struct gpd_timing_data *td)
 {
 	struct generic_pm_domain_data *gpd_data;
-	int ret = 0;
+	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
 		return -EINVAL;
 
-	gpd_data = genpd_alloc_dev_data(dev, genpd, td);
+	gpd_data = genpd_alloc_dev_data(dev, td);
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
 	genpd_lock(genpd);
 
-	if (genpd->prepared_count > 0) {
-		ret = -EAGAIN;
-		goto out;
-	}
-
 	ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0;
 	if (ret)
 		goto out;
@@ -1418,23 +1413,21 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 }
 
 /**
- * __pm_genpd_add_device - Add a device to an I/O PM domain.
+ * pm_genpd_add_device - Add a device to an I/O PM domain.
  * @genpd: PM domain to add the device to.
  * @dev: Device to be added.
- * @td: Set of PM QoS timing parameters to attach to the device.
  */
-int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
-			  struct gpd_timing_data *td)
+int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
 {
 	int ret;
 
 	mutex_lock(&gpd_list_lock);
-	ret = genpd_add_device(genpd, dev, td);
+	ret = genpd_add_device(genpd, dev, NULL);
 	mutex_unlock(&gpd_list_lock);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__pm_genpd_add_device);
+EXPORT_SYMBOL_GPL(pm_genpd_add_device);
 
 static int genpd_remove_device(struct generic_pm_domain *genpd,
 			       struct device *dev)
@@ -1481,13 +1474,13 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 
 /**
  * pm_genpd_remove_device - Remove a device from an I/O PM domain.
- * @genpd: PM domain to remove the device from.
  * @dev: Device to be removed.
  */
-int pm_genpd_remove_device(struct generic_pm_domain *genpd,
-			   struct device *dev)
+int pm_genpd_remove_device(struct device *dev)
 {
-	if (!genpd || genpd != genpd_lookup_dev(dev))
+	struct generic_pm_domain *genpd = genpd_lookup_dev(dev);
+
+	if (!genpd)
 		return -EINVAL;
 
 	return genpd_remove_device(genpd, dev);
@@ -1696,6 +1689,9 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 			return ret;
 	}
 
+	device_initialize(&genpd->dev);
+	dev_set_name(&genpd->dev, "%s", genpd->name);
+
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
@@ -1892,14 +1888,33 @@ int of_genpd_add_provider_simple(struct device_node *np,
 
 	mutex_lock(&gpd_list_lock);
 
-	if (genpd_present(genpd)) {
-		ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
-		if (!ret) {
-			genpd->provider = &np->fwnode;
-			genpd->has_provider = true;
+	if (!genpd_present(genpd))
+		goto unlock;
+
+	genpd->dev.of_node = np;
+
+	/* Parse genpd OPP table */
+	if (genpd->set_performance_state) {
+		ret = dev_pm_opp_of_add_table(&genpd->dev);
+		if (ret) {
+			dev_err(&genpd->dev, "Failed to add OPP table: %d\n",
+				ret);
+			goto unlock;
 		}
 	}
 
+	ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
+	if (ret) {
+		if (genpd->set_performance_state)
+			dev_pm_opp_of_remove_table(&genpd->dev);
+
+		goto unlock;
+	}
+
+	genpd->provider = &np->fwnode;
+	genpd->has_provider = true;
+
+unlock:
 	mutex_unlock(&gpd_list_lock);
 
 	return ret;
@@ -1914,6 +1929,7 @@ EXPORT_SYMBOL_GPL(of_genpd_add_provider_simple);
 int of_genpd_add_provider_onecell(struct device_node *np,
 				  struct genpd_onecell_data *data)
 {
+	struct generic_pm_domain *genpd;
 	unsigned int i;
 	int ret = -EINVAL;
 
@@ -1926,13 +1942,27 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 		data->xlate = genpd_xlate_onecell;
 
 	for (i = 0; i < data->num_domains; i++) {
-		if (!data->domains[i])
+		genpd = data->domains[i];
+
+		if (!genpd)
 			continue;
-		if (!genpd_present(data->domains[i]))
+		if (!genpd_present(genpd))
 			goto error;
 
-		data->domains[i]->provider = &np->fwnode;
-		data->domains[i]->has_provider = true;
+		genpd->dev.of_node = np;
+
+		/* Parse genpd OPP table */
+		if (genpd->set_performance_state) {
+			ret = dev_pm_opp_of_add_table_indexed(&genpd->dev, i);
+			if (ret) {
+				dev_err(&genpd->dev, "Failed to add OPP table for index %d: %d\n",
+					i, ret);
+				goto error;
+			}
+		}
+
+		genpd->provider = &np->fwnode;
+		genpd->has_provider = true;
 	}
 
 	ret = genpd_add_provider(np, data->xlate, data);
@@ -1945,10 +1975,16 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 
 error:
 	while (i--) {
-		if (!data->domains[i])
+		genpd = data->domains[i];
+
+		if (!genpd)
 			continue;
-		data->domains[i]->provider = NULL;
-		data->domains[i]->has_provider = false;
+
+		genpd->provider = NULL;
+		genpd->has_provider = false;
+
+		if (genpd->set_performance_state)
+			dev_pm_opp_of_remove_table(&genpd->dev);
 	}
 
 	mutex_unlock(&gpd_list_lock);
@@ -1975,10 +2011,17 @@ void of_genpd_del_provider(struct device_node *np)
 			 * provider, set the 'has_provider' to false
 			 * so that the PM domain can be safely removed.
 			 */
-			list_for_each_entry(gpd, &gpd_list, gpd_list_node)
-				if (gpd->provider == &np->fwnode)
+			list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+				if (gpd->provider == &np->fwnode) {
 					gpd->has_provider = false;
 
+					if (!gpd->set_performance_state)
+						continue;
+
+					dev_pm_opp_of_remove_table(&gpd->dev);
+				}
+			}
+
 			list_del(&cp->link);
 			of_node_put(cp->node);
 			kfree(cp);
@@ -2185,31 +2228,25 @@ static void genpd_dev_pm_sync(struct device *dev)
  * Parse device's OF node to find a PM domain specifier. If such is found,
  * attaches the device to retrieved pm_domain ops.
  *
- * Both generic and legacy Samsung-specific DT bindings are supported to keep
- * backwards compatibility with existing DTBs.
- *
- * Returns 0 on successfully attached PM domain or negative error code. Note
- * that if a power-domain exists for the device, but it cannot be found or
- * turned on, then return -EPROBE_DEFER to ensure that the device is not
- * probed and to re-try again later.
+ * Returns 1 on successfully attached PM domain, 0 when the device don't need a
+ * PM domain or a negative error code in case of failures. Note that if a
+ * power-domain exists for the device, but it cannot be found or turned on,
+ * then return -EPROBE_DEFER to ensure that the device is not probed and to
+ * re-try again later.
  */
 int genpd_dev_pm_attach(struct device *dev)
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
-	unsigned int i;
 	int ret;
 
 	if (!dev->of_node)
-		return -ENODEV;
-
-	if (dev->pm_domain)
-		return -EEXIST;
+		return 0;
 
 	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
 					"#power-domain-cells", 0, &pd_args);
 	if (ret < 0)
-		return ret;
+		return 0;
 
 	mutex_lock(&gpd_list_lock);
 	pd = genpd_get_from_provider(&pd_args);
@@ -2223,21 +2260,14 @@ int genpd_dev_pm_attach(struct device *dev)
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
 
-	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
-		ret = genpd_add_device(pd, dev, NULL);
-		if (ret != -EAGAIN)
-			break;
-
-		mdelay(i);
-		cond_resched();
-	}
+	ret = genpd_add_device(pd, dev, NULL);
 	mutex_unlock(&gpd_list_lock);
 
 	if (ret < 0) {
 		if (ret != -EPROBE_DEFER)
 			dev_err(dev, "failed to add to PM domain %s: %d",
 				pd->name, ret);
-		goto out;
+		return ret;
 	}
 
 	dev->pm_domain->detach = genpd_dev_pm_detach;
@@ -2246,8 +2276,11 @@ int genpd_dev_pm_attach(struct device *dev)
 	genpd_lock(pd);
 	ret = genpd_power_on(pd, 0);
 	genpd_unlock(pd);
-out:
-	return ret ? -EPROBE_DEFER : 0;
+
+	if (ret)
+		genpd_remove_device(pd, dev);
+
+	return ret ? -EPROBE_DEFER : 1;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 
@@ -2361,6 +2394,55 @@ int of_genpd_parse_idle_states(struct device_node *dn,
 }
 EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
 
+/**
+ * of_genpd_opp_to_performance_state- Gets performance state of device's
+ * power domain corresponding to a DT node's "required-opps" property.
+ *
+ * @dev: Device for which the performance-state needs to be found.
+ * @opp_node: DT node where the "required-opps" property is present. This can be
+ *	the device node itself (if it doesn't have an OPP table) or a node
+ *	within the OPP table of a device (if device has an OPP table).
+ * @state: Pointer to return performance state.
+ *
+ * Returns performance state corresponding to the "required-opps" property of
+ * a DT node. This calls platform specific genpd->opp_to_performance_state()
+ * callback to translate power domain OPP to performance state.
+ *
+ * Returns performance state on success and 0 on failure.
+ */
+unsigned int of_genpd_opp_to_performance_state(struct device *dev,
+					       struct device_node *opp_node)
+{
+	struct generic_pm_domain *genpd;
+	struct dev_pm_opp *opp;
+	int state = 0;
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return 0;
+
+	if (unlikely(!genpd->set_performance_state))
+		return 0;
+
+	genpd_lock(genpd);
+
+	opp = of_dev_pm_opp_find_required_opp(&genpd->dev, opp_node);
+	if (IS_ERR(opp)) {
+		dev_err(dev, "Failed to find required OPP: %ld\n",
+			PTR_ERR(opp));
+		goto unlock;
+	}
+
+	state = genpd->opp_to_performance_state(genpd, opp);
+	dev_pm_opp_put(opp);
+
+unlock:
+	genpd_unlock(genpd);
+
+	return state;
+}
+EXPORT_SYMBOL_GPL(of_genpd_opp_to_performance_state);
+
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
 
 
@@ -2628,6 +2710,19 @@ static int genpd_devices_show(struct seq_file *s, void *data)
 	return ret;
 }
 
+static int genpd_perf_state_show(struct seq_file *s, void *data)
+{
+	struct generic_pm_domain *genpd = s->private;
+
+	if (genpd_lock_interruptible(genpd))
+		return -ERESTARTSYS;
+
+	seq_printf(s, "%u\n", genpd->performance_state);
+
+	genpd_unlock(genpd);
+	return 0;
+}
+
 #define define_genpd_open_function(name) \
 static int genpd_##name##_open(struct inode *inode, struct file *file) \
 { \
@@ -2641,6 +2736,7 @@ define_genpd_open_function(idle_states);
 define_genpd_open_function(active_time);
 define_genpd_open_function(total_idle_time);
 define_genpd_open_function(devices);
+define_genpd_open_function(perf_state);
 
 #define define_genpd_debugfs_fops(name) \
 static const struct file_operations genpd_##name##_fops = { \
@@ -2657,6 +2753,7 @@ define_genpd_debugfs_fops(idle_states);
 define_genpd_debugfs_fops(active_time);
 define_genpd_debugfs_fops(total_idle_time);
 define_genpd_debugfs_fops(devices);
+define_genpd_debugfs_fops(perf_state);
 
 static int __init genpd_debug_init(void)
 {
@@ -2690,6 +2787,9 @@ static int __init genpd_debug_init(void)
 				d, genpd, &genpd_total_idle_time_fops);
 		debugfs_create_file("devices", 0444,
 				d, genpd, &genpd_devices_fops);
+		if (genpd->set_performance_state)
+			debugfs_create_file("perf_state", 0444,
+					    d, genpd, &genpd_perf_state_fops);
 	}
 
 	return 0;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 02a497e7c785..3f68e2919dc5 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -192,34 +192,31 @@ void device_pm_move_last(struct device *dev)
 	list_move_tail(&dev->power.entry, &dpm_list);
 }
 
-static ktime_t initcall_debug_start(struct device *dev)
+static ktime_t initcall_debug_start(struct device *dev, void *cb)
 {
-	ktime_t calltime = 0;
-
-	if (pm_print_times_enabled) {
-		pr_info("calling  %s+ @ %i, parent: %s\n",
-			dev_name(dev), task_pid_nr(current),
-			dev->parent ? dev_name(dev->parent) : "none");
-		calltime = ktime_get();
-	}
+	if (!pm_print_times_enabled)
+		return 0;
 
-	return calltime;
+	dev_info(dev, "calling %pF @ %i, parent: %s\n", cb,
+		 task_pid_nr(current),
+		 dev->parent ? dev_name(dev->parent) : "none");
+	return ktime_get();
 }
 
 static void initcall_debug_report(struct device *dev, ktime_t calltime,
-				  int error, pm_message_t state,
-				  const char *info)
+				  void *cb, int error)
 {
 	ktime_t rettime;
 	s64 nsecs;
 
+	if (!pm_print_times_enabled)
+		return;
+
 	rettime = ktime_get();
 	nsecs = (s64) ktime_to_ns(ktime_sub(rettime, calltime));
 
-	if (pm_print_times_enabled) {
-		pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
-			error, (unsigned long long)nsecs >> 10);
-	}
+	dev_info(dev, "%pF returned %d after %Ld usecs\n", cb, error,
+		 (unsigned long long)nsecs >> 10);
 }
 
 /**
@@ -446,7 +443,7 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
 	if (!cb)
 		return 0;
 
-	calltime = initcall_debug_start(dev);
+	calltime = initcall_debug_start(dev, cb);
 
 	pm_dev_dbg(dev, state, info);
 	trace_device_pm_callback_start(dev, info, state.event);
@@ -454,7 +451,7 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
 	trace_device_pm_callback_end(dev, error);
 	suspend_report_result(cb, error);
 
-	initcall_debug_report(dev, calltime, error, state, info);
+	initcall_debug_report(dev, calltime, cb, error);
 
 	return error;
 }
@@ -1664,14 +1661,14 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
 	int error;
 	ktime_t calltime;
 
-	calltime = initcall_debug_start(dev);
+	calltime = initcall_debug_start(dev, cb);
 
 	trace_device_pm_callback_start(dev, info, state.event);
 	error = cb(dev, state);
 	trace_device_pm_callback_end(dev, error);
 	suspend_report_result(cb, error);
 
-	initcall_debug_report(dev, calltime, error, state, info);
+	initcall_debug_report(dev, calltime, cb, error);
 
 	return error;
 }
@@ -1923,10 +1920,8 @@ static int device_prepare(struct device *dev, pm_message_t state)
 
 	dev->power.wakeup_path = false;
 
-	if (dev->power.no_pm_callbacks) {
-		ret = 1;	/* Let device go direct_complete */
+	if (dev->power.no_pm_callbacks)
 		goto unlock;
-	}
 
 	if (dev->pm_domain)
 		callback = dev->pm_domain->ops.prepare;
@@ -1960,7 +1955,8 @@ unlock:
 	 */
 	spin_lock_irq(&dev->power.lock);
 	dev->power.direct_complete = state.event == PM_EVENT_SUSPEND &&
-		pm_runtime_suspended(dev) && ret > 0 &&
+		((pm_runtime_suspended(dev) && ret > 0) ||
+		 dev->power.no_pm_callbacks) &&
 		!dev_pm_test_driver_flags(dev, DPM_FLAG_NEVER_SKIP);
 	spin_unlock_irq(&dev->power.lock);
 	return 0;
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 86e67e70b509..c511def48b48 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -56,14 +56,6 @@ static inline void device_wakeup_detach_irq(struct device *dev)
 {
 }
 
-static inline void device_wakeup_arm_wake_irqs(void)
-{
-}
-
-static inline void device_wakeup_disarm_wake_irqs(void)
-{
-}
-
 #endif /* CONFIG_PM_SLEEP */
 
 /*
@@ -95,28 +87,6 @@ static inline void pm_runtime_remove(struct device *dev) {}
 
 static inline int dpm_sysfs_add(struct device *dev) { return 0; }
 static inline void dpm_sysfs_remove(struct device *dev) {}
-static inline void rpm_sysfs_remove(struct device *dev) {}
-static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
-static inline void wakeup_sysfs_remove(struct device *dev) {}
-static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
-static inline void pm_qos_sysfs_remove(struct device *dev) {}
-
-static inline void dev_pm_arm_wake_irq(struct wake_irq *wirq)
-{
-}
-
-static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
-{
-}
-
-static inline void dev_pm_enable_wake_irq_check(struct device *dev,
-						bool can_change_status)
-{
-}
-
-static inline void dev_pm_disable_wake_irq_check(struct device *dev)
-{
-}
 
 #endif
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 8bef3cb2424d..c6030f100c08 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1563,37 +1563,16 @@ void pm_runtime_clean_up_links(struct device *dev)
 }
 
 /**
- * pm_runtime_get_suppliers - Resume and reference-count supplier devices.
+ * pm_runtime_resume_suppliers - Resume supplier devices.
  * @dev: Consumer device.
  */
-void pm_runtime_get_suppliers(struct device *dev)
+void pm_runtime_resume_suppliers(struct device *dev)
 {
-	struct device_link *link;
-	int idx;
-
-	idx = device_links_read_lock();
-
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
-		if (link->flags & DL_FLAG_PM_RUNTIME)
-			pm_runtime_get_sync(link->supplier);
-
-	device_links_read_unlock(idx);
-}
-
-/**
- * pm_runtime_put_suppliers - Drop references to supplier devices.
- * @dev: Consumer device.
- */
-void pm_runtime_put_suppliers(struct device *dev)
-{
-	struct device_link *link;
 	int idx;
 
 	idx = device_links_read_lock();
 
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
-		if (link->flags & DL_FLAG_PM_RUNTIME)
-			pm_runtime_put(link->supplier);
+	rpm_get_suppliers(dev);
 
 	device_links_read_unlock(idx);
 }
@@ -1607,6 +1586,8 @@ void pm_runtime_new_link(struct device *dev)
 
 void pm_runtime_drop_link(struct device *dev)
 {
+	rpm_put_suppliers(dev);
+
 	spin_lock_irq(&dev->power.lock);
 	WARN_ON(dev->power.links_count == 0);
 	dev->power.links_count--;
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index ea01621ed769..5fa1898755a3 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -57,7 +57,7 @@ static void split_counters(unsigned int *cnt, unsigned int *inpr)
 /* A preserved old value of the events counter. */
 static unsigned int saved_count;
 
-static DEFINE_SPINLOCK(events_lock);
+static DEFINE_RAW_SPINLOCK(events_lock);
 
 static void pm_wakeup_timer_fn(struct timer_list *t);
 
@@ -183,11 +183,10 @@ void wakeup_source_add(struct wakeup_source *ws)
 	spin_lock_init(&ws->lock);
 	timer_setup(&ws->timer, pm_wakeup_timer_fn, 0);
 	ws->active = false;
-	ws->last_time = ktime_get();
 
-	spin_lock_irqsave(&events_lock, flags);
+	raw_spin_lock_irqsave(&events_lock, flags);
 	list_add_rcu(&ws->entry, &wakeup_sources);
-	spin_unlock_irqrestore(&events_lock, flags);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_add);
 
@@ -202,9 +201,9 @@ void wakeup_source_remove(struct wakeup_source *ws)
 	if (WARN_ON(!ws))
 		return;
 
-	spin_lock_irqsave(&events_lock, flags);
+	raw_spin_lock_irqsave(&events_lock, flags);
 	list_del_rcu(&ws->entry);
-	spin_unlock_irqrestore(&events_lock, flags);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
 	synchronize_srcu(&wakeup_srcu);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_remove);
@@ -843,7 +842,7 @@ bool pm_wakeup_pending(void)
 	unsigned long flags;
 	bool ret = false;
 
-	spin_lock_irqsave(&events_lock, flags);
+	raw_spin_lock_irqsave(&events_lock, flags);
 	if (events_check_enabled) {
 		unsigned int cnt, inpr;
 
@@ -851,10 +850,10 @@ bool pm_wakeup_pending(void)
 		ret = (cnt != saved_count || inpr > 0);
 		events_check_enabled = !ret;
 	}
-	spin_unlock_irqrestore(&events_lock, flags);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
 
 	if (ret) {
-		pr_info("PM: Wakeup pending, aborting suspend\n");
+		pr_debug("PM: Wakeup pending, aborting suspend\n");
 		pm_print_active_wakeup_sources();
 	}
 
@@ -940,13 +939,13 @@ bool pm_save_wakeup_count(unsigned int count)
 	unsigned long flags;
 
 	events_check_enabled = false;
-	spin_lock_irqsave(&events_lock, flags);
+	raw_spin_lock_irqsave(&events_lock, flags);
 	split_counters(&cnt, &inpr);
 	if (cnt == count && inpr == 0) {
 		saved_count = count;
 		events_check_enabled = true;
 	}
-	spin_unlock_irqrestore(&events_lock, flags);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
 	return events_check_enabled;
 }
 
@@ -1029,32 +1028,75 @@ static int print_wakeup_source_stats(struct seq_file *m,
 	return 0;
 }
 
-/**
- * wakeup_sources_stats_show - Print wakeup sources statistics information.
- * @m: seq_file to print the statistics into.
- */
-static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
+static void *wakeup_sources_stats_seq_start(struct seq_file *m,
+					loff_t *pos)
 {
 	struct wakeup_source *ws;
-	int srcuidx;
+	loff_t n = *pos;
+	int *srcuidx = m->private;
 
-	seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
-		"expire_count\tactive_since\ttotal_time\tmax_time\t"
-		"last_change\tprevent_suspend_time\n");
+	if (n == 0) {
+		seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
+			"expire_count\tactive_since\ttotal_time\tmax_time\t"
+			"last_change\tprevent_suspend_time\n");
+	}
 
-	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
-		print_wakeup_source_stats(m, ws);
-	srcu_read_unlock(&wakeup_srcu, srcuidx);
+	*srcuidx = srcu_read_lock(&wakeup_srcu);
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (n-- <= 0)
+			return ws;
+	}
+
+	return NULL;
+}
+
+static void *wakeup_sources_stats_seq_next(struct seq_file *m,
+					void *v, loff_t *pos)
+{
+	struct wakeup_source *ws = v;
+	struct wakeup_source *next_ws = NULL;
 
-	print_wakeup_source_stats(m, &deleted_ws);
+	++(*pos);
+
+	list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) {
+		next_ws = ws;
+		break;
+	}
+
+	return next_ws;
+}
+
+static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v)
+{
+	int *srcuidx = m->private;
+
+	srcu_read_unlock(&wakeup_srcu, *srcuidx);
+}
+
+/**
+ * wakeup_sources_stats_seq_show - Print wakeup sources statistics information.
+ * @m: seq_file to print the statistics into.
+ * @v: wakeup_source of each iteration
+ */
+static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v)
+{
+	struct wakeup_source *ws = v;
+
+	print_wakeup_source_stats(m, ws);
 
 	return 0;
 }
 
+static const struct seq_operations wakeup_sources_stats_seq_ops = {
+	.start = wakeup_sources_stats_seq_start,
+	.next  = wakeup_sources_stats_seq_next,
+	.stop  = wakeup_sources_stats_seq_stop,
+	.show  = wakeup_sources_stats_seq_show,
+};
+
 static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, wakeup_sources_stats_show, NULL);
+	return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int));
 }
 
 static const struct file_operations wakeup_sources_stats_fops = {
@@ -1062,7 +1104,7 @@ static const struct file_operations wakeup_sources_stats_fops = {
 	.open = wakeup_sources_stats_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = single_release,
+	.release = seq_release_private,
 };
 
 static int __init wakeup_sources_debugfs_init(void)
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 8f205f6461ed..240ab5230ff6 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -56,6 +56,72 @@ pset_prop_get(const struct property_set *pset, const char *name)
 	return NULL;
 }
 
+static const void *property_get_pointer(const struct property_entry *prop)
+{
+	switch (prop->type) {
+	case DEV_PROP_U8:
+		if (prop->is_array)
+			return prop->pointer.u8_data;
+		return &prop->value.u8_data;
+	case DEV_PROP_U16:
+		if (prop->is_array)
+			return prop->pointer.u16_data;
+		return &prop->value.u16_data;
+	case DEV_PROP_U32:
+		if (prop->is_array)
+			return prop->pointer.u32_data;
+		return &prop->value.u32_data;
+	case DEV_PROP_U64:
+		if (prop->is_array)
+			return prop->pointer.u64_data;
+		return &prop->value.u64_data;
+	case DEV_PROP_STRING:
+		if (prop->is_array)
+			return prop->pointer.str;
+		return &prop->value.str;
+	default:
+		return NULL;
+	}
+}
+
+static void property_set_pointer(struct property_entry *prop, const void *pointer)
+{
+	switch (prop->type) {
+	case DEV_PROP_U8:
+		if (prop->is_array)
+			prop->pointer.u8_data = pointer;
+		else
+			prop->value.u8_data = *((u8 *)pointer);
+		break;
+	case DEV_PROP_U16:
+		if (prop->is_array)
+			prop->pointer.u16_data = pointer;
+		else
+			prop->value.u16_data = *((u16 *)pointer);
+		break;
+	case DEV_PROP_U32:
+		if (prop->is_array)
+			prop->pointer.u32_data = pointer;
+		else
+			prop->value.u32_data = *((u32 *)pointer);
+		break;
+	case DEV_PROP_U64:
+		if (prop->is_array)
+			prop->pointer.u64_data = pointer;
+		else
+			prop->value.u64_data = *((u64 *)pointer);
+		break;
+	case DEV_PROP_STRING:
+		if (prop->is_array)
+			prop->pointer.str = pointer;
+		else
+			prop->value.str = pointer;
+		break;
+	default:
+		break;
+	}
+}
+
 static const void *pset_prop_find(const struct property_set *pset,
 				  const char *propname, size_t length)
 {
@@ -65,10 +131,7 @@ static const void *pset_prop_find(const struct property_set *pset,
 	prop = pset_prop_get(pset, propname);
 	if (!prop)
 		return ERR_PTR(-EINVAL);
-	if (prop->is_array)
-		pointer = prop->pointer.raw_data;
-	else
-		pointer = &prop->value.raw_data;
+	pointer = property_get_pointer(prop);
 	if (!pointer)
 		return ERR_PTR(-ENODATA);
 	if (length > prop->length)
@@ -698,16 +761,17 @@ EXPORT_SYMBOL_GPL(fwnode_property_get_reference_args);
 
 static void property_entry_free_data(const struct property_entry *p)
 {
+	const void *pointer = property_get_pointer(p);
 	size_t i, nval;
 
 	if (p->is_array) {
-		if (p->is_string && p->pointer.str) {
+		if (p->type == DEV_PROP_STRING && p->pointer.str) {
 			nval = p->length / sizeof(const char *);
 			for (i = 0; i < nval; i++)
 				kfree(p->pointer.str[i]);
 		}
-		kfree(p->pointer.raw_data);
-	} else if (p->is_string) {
+		kfree(pointer);
+	} else if (p->type == DEV_PROP_STRING) {
 		kfree(p->value.str);
 	}
 	kfree(p->name);
@@ -716,7 +780,7 @@ static void property_entry_free_data(const struct property_entry *p)
 static int property_copy_string_array(struct property_entry *dst,
 				      const struct property_entry *src)
 {
-	char **d;
+	const char **d;
 	size_t nval = src->length / sizeof(*d);
 	int i;
 
@@ -734,40 +798,44 @@ static int property_copy_string_array(struct property_entry *dst,
 		}
 	}
 
-	dst->pointer.raw_data = d;
+	dst->pointer.str = d;
 	return 0;
 }
 
 static int property_entry_copy_data(struct property_entry *dst,
 				    const struct property_entry *src)
 {
+	const void *pointer = property_get_pointer(src);
+	const void *new;
 	int error;
 
 	if (src->is_array) {
 		if (!src->length)
 			return -ENODATA;
 
-		if (src->is_string) {
+		if (src->type == DEV_PROP_STRING) {
 			error = property_copy_string_array(dst, src);
 			if (error)
 				return error;
+			new = dst->pointer.str;
 		} else {
-			dst->pointer.raw_data = kmemdup(src->pointer.raw_data,
-							src->length, GFP_KERNEL);
-			if (!dst->pointer.raw_data)
+			new = kmemdup(pointer, src->length, GFP_KERNEL);
+			if (!new)
 				return -ENOMEM;
 		}
-	} else if (src->is_string) {
-		dst->value.str = kstrdup(src->value.str, GFP_KERNEL);
-		if (!dst->value.str && src->value.str)
+	} else if (src->type == DEV_PROP_STRING) {
+		new = kstrdup(src->value.str, GFP_KERNEL);
+		if (!new && src->value.str)
 			return -ENOMEM;
 	} else {
-		dst->value.raw_data = src->value.raw_data;
+		new = pointer;
 	}
 
 	dst->length = src->length;
 	dst->is_array = src->is_array;
-	dst->is_string = src->is_string;
+	dst->type = src->type;
+
+	property_set_pointer(dst, new);
 
 	dst->name = kstrdup(src->name, GFP_KERNEL);
 	if (!dst->name)
diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c
index 5cadfd3394d8..8741fb5f8f54 100644
--- a/drivers/base/regmap/regmap-mmio.c
+++ b/drivers/base/regmap/regmap-mmio.c
@@ -206,7 +206,8 @@ static void regmap_mmio_free_context(void *context)
 
 	if (!IS_ERR(ctx->clk)) {
 		clk_unprepare(ctx->clk);
-		clk_put(ctx->clk);
+		if (!ctx->attached_clk)
+			clk_put(ctx->clk);
 	}
 	kfree(context);
 }
diff --git a/drivers/base/regmap/regmap-slimbus.c b/drivers/base/regmap/regmap-slimbus.c
index c90bee81d954..91d501eda8a9 100644
--- a/drivers/base/regmap/regmap-slimbus.c
+++ b/drivers/base/regmap/regmap-slimbus.c
@@ -41,7 +41,7 @@ static struct regmap_bus regmap_slimbus_bus = {
 static const struct regmap_bus *regmap_get_slimbus(struct slim_device *slim,
 					const struct regmap_config *config)
 {
-	if (config->val_bits == 8 && config->reg_bits == 8)
+	if (config->val_bits == 8 && config->reg_bits == 16)
 		return &regmap_slimbus_bus;
 
 	return ERR_PTR(-ENOTSUPP);
diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index f040aba48d50..27e9686b6d3a 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -184,7 +184,7 @@ static void bcma_core_mips_print_irq(struct bcma_device *dev, unsigned int irq)
 {
 	int i;
 	static const char *irq_name[] = {"2(S)", "3", "4", "5", "6", "D", "I"};
-	char interrupts[20];
+	char interrupts[25];
 	char *ints = interrupts;
 
 	for (i = 0; i < ARRAY_SIZE(irq_name); i++)
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index e6986c7608f1..fc1f4acdd189 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -207,7 +207,7 @@ static void bcma_of_fill_device(struct device *parent,
 
 	core->irq = bcma_of_get_irq(parent, core, 0);
 
-	of_dma_configure(&core->dev, node);
+	of_dma_configure(&core->dev, node, false);
 }
 
 unsigned int bcma_core_irq(struct bcma_device *core, int num)
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index f781eff7d23e..6ca77d6047d6 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -1179,7 +1179,6 @@ static bool DAC960_V1_EnableMemoryMailboxInterface(DAC960_Controller_T
 
   if (pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32)))
 	return DAC960_Failure(Controller, "DMA mask out of range");
-  Controller->BounceBufferLimit = DMA_BIT_MASK(32);
 
   if ((hw_type == DAC960_PD_Controller) || (hw_type == DAC960_P_Controller)) {
     CommandMailboxesSize =  0;
@@ -1380,11 +1379,8 @@ static bool DAC960_V2_EnableMemoryMailboxInterface(DAC960_Controller_T
   dma_addr_t	CommandMailboxDMA;
   DAC960_V2_CommandStatus_T CommandStatus;
 
-	if (!pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(64)))
-		Controller->BounceBufferLimit = DMA_BIT_MASK(64);
-	else if (!pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32)))
-		Controller->BounceBufferLimit = DMA_BIT_MASK(32);
-	else
+	if (pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(64)) &&
+	    pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32)))
 		return DAC960_Failure(Controller, "DMA mask out of range");
 
   /* This is a temporary dma mapping, used only in the scope of this function */
@@ -2540,7 +2536,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller)
 		continue;
   	}
   	Controller->RequestQueue[n] = RequestQueue;
-  	blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit);
   	RequestQueue->queuedata = Controller;
 	blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit);
 	blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand);
@@ -6451,19 +6446,6 @@ static int dac960_proc_show(struct seq_file *m, void *v)
   return 0;
 }
 
-static int dac960_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, dac960_proc_show, NULL);
-}
-
-static const struct file_operations dac960_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= dac960_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
 {
 	DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
@@ -6471,19 +6453,6 @@ static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int dac960_initial_status_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, dac960_initial_status_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations dac960_initial_status_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= dac960_initial_status_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int dac960_current_status_proc_show(struct seq_file *m, void *v)
 {
   DAC960_Controller_T *Controller = (DAC960_Controller_T *) m->private;
@@ -6517,19 +6486,6 @@ static int dac960_current_status_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int dac960_current_status_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, dac960_current_status_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations dac960_current_status_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= dac960_current_status_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int dac960_user_command_proc_show(struct seq_file *m, void *v)
 {
 	DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
@@ -6584,17 +6540,19 @@ static void DAC960_CreateProcEntries(DAC960_Controller_T *Controller)
 
 	if (DAC960_ProcDirectoryEntry == NULL) {
 		DAC960_ProcDirectoryEntry = proc_mkdir("rd", NULL);
-		proc_create("status", 0, DAC960_ProcDirectoryEntry,
-			    &dac960_proc_fops);
+		proc_create_single("status", 0, DAC960_ProcDirectoryEntry,
+				dac960_proc_show);
 	}
 
 	snprintf(Controller->ControllerName, sizeof(Controller->ControllerName),
 		 "c%d", Controller->ControllerNumber);
 	ControllerProcEntry = proc_mkdir(Controller->ControllerName,
 					 DAC960_ProcDirectoryEntry);
-	proc_create_data("initial_status", 0, ControllerProcEntry, &dac960_initial_status_proc_fops, Controller);
-	proc_create_data("current_status", 0, ControllerProcEntry, &dac960_current_status_proc_fops, Controller);
-	proc_create_data("user_command", S_IWUSR | S_IRUSR, ControllerProcEntry, &dac960_user_command_proc_fops, Controller);
+	proc_create_single_data("initial_status", 0, ControllerProcEntry,
+			dac960_initial_status_proc_show, Controller);
+	proc_create_single_data("current_status", 0, ControllerProcEntry,
+			dac960_current_status_proc_show, Controller);
+	proc_create_data("user_command", 0600, ControllerProcEntry, &dac960_user_command_proc_fops, Controller);
 	Controller->ControllerProcEntry = ControllerProcEntry;
 }
 
diff --git a/drivers/block/DAC960.h b/drivers/block/DAC960.h
index 21aff470d268..1439e651928b 100644
--- a/drivers/block/DAC960.h
+++ b/drivers/block/DAC960.h
@@ -2295,7 +2295,6 @@ typedef struct DAC960_Controller
   unsigned short MaxBlocksPerCommand;
   unsigned short ControllerScatterGatherLimit;
   unsigned short DriverScatterGatherLimit;
-  u64		BounceBufferLimit;
   unsigned int CombinedStatusBufferLength;
   unsigned int InitialStatusLength;
   unsigned int CurrentStatusLength;
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 6797e6c23c8a..429ebb84b592 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -159,14 +159,14 @@ static int aoe_debugfs_open(struct inode *inode, struct file *file)
 	return single_open(file, aoedisk_debugfs_show, inode->i_private);
 }
 
-static DEVICE_ATTR(state, S_IRUGO, aoedisk_show_state, NULL);
-static DEVICE_ATTR(mac, S_IRUGO, aoedisk_show_mac, NULL);
-static DEVICE_ATTR(netif, S_IRUGO, aoedisk_show_netif, NULL);
+static DEVICE_ATTR(state, 0444, aoedisk_show_state, NULL);
+static DEVICE_ATTR(mac, 0444, aoedisk_show_mac, NULL);
+static DEVICE_ATTR(netif, 0444, aoedisk_show_netif, NULL);
 static struct device_attribute dev_attr_firmware_version = {
-	.attr = { .name = "firmware-version", .mode = S_IRUGO },
+	.attr = { .name = "firmware-version", .mode = 0444 },
 	.show = aoedisk_show_fwver,
 };
-static DEVICE_ATTR(payload, S_IRUGO, aoedisk_show_payload, NULL);
+static DEVICE_ATTR(payload, 0444, aoedisk_show_payload, NULL);
 
 static struct attribute *aoe_attrs[] = {
 	&dev_attr_state.attr,
@@ -388,7 +388,6 @@ aoeblk_gdalloc(void *vp)
 			d->aoemajor, d->aoeminor);
 		goto err_mempool;
 	}
-	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
 
 	spin_lock_irqsave(&d->lock, flags);
 	WARN_ON(!(d->flags & DEVFL_GD_NOW));
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 540bb60cd071..096882e54095 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1032,8 +1032,9 @@ bvcpy(struct sk_buff *skb, struct bio *bio, struct bvec_iter iter, long cnt)
 	iter.bi_size = cnt;
 
 	__bio_for_each_segment(bv, bio, iter, iter) {
-		char *p = page_address(bv.bv_page) + bv.bv_offset;
+		char *p = kmap_atomic(bv.bv_page) + bv.bv_offset;
 		skb_copy_bits(skb, soff, p, bv.bv_len);
+		kunmap_atomic(p);
 		soff += bv.bv_len;
 	}
 }
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 66cb0f857f64..bb976598ee43 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -331,15 +331,15 @@ static const struct block_device_operations brd_fops = {
  * And now the modules code and kernel interface.
  */
 static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT;
-module_param(rd_nr, int, S_IRUGO);
+module_param(rd_nr, int, 0444);
 MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
 
 unsigned long rd_size = CONFIG_BLK_DEV_RAM_SIZE;
-module_param(rd_size, ulong, S_IRUGO);
+module_param(rd_size, ulong, 0444);
 MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
 
 static int max_part = 1;
-module_param(max_part, int, S_IRUGO);
+module_param(max_part, int, 0444);
 MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
 
 MODULE_LICENSE("GPL");
@@ -402,6 +402,10 @@ static struct brd_device *brd_alloc(int i)
 	set_capacity(disk, rd_size * 2);
 	disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
 
+	/* Tell the block layer that this is not a rotational device */
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
+	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
+
 	return brd;
 
 out_free_queue:
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 9f4e6f502b84..11a85b740327 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -977,7 +977,7 @@ static void drbd_bm_endio(struct bio *bio)
 	bm_page_unlock_io(device, idx);
 
 	if (ctx->flags & BM_AIO_COPY_PAGES)
-		mempool_free(bio->bi_io_vec[0].bv_page, drbd_md_io_page_pool);
+		mempool_free(bio->bi_io_vec[0].bv_page, &drbd_md_io_page_pool);
 
 	bio_put(bio);
 
@@ -1014,7 +1014,8 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 	bm_set_page_unchanged(b->bm_pages[page_nr]);
 
 	if (ctx->flags & BM_AIO_COPY_PAGES) {
-		page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_RECLAIM);
+		page = mempool_alloc(&drbd_md_io_page_pool,
+				GFP_NOIO | __GFP_HIGHMEM);
 		copy_highpage(page, b->bm_pages[page_nr]);
 		bm_store_page_idx(page, page_nr);
 	} else
diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index ab21976a87b2..5d5e8d6a8a56 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -481,9 +481,9 @@ void drbd_debugfs_resource_add(struct drbd_resource *resource)
 		goto fail;
 	resource->debugfs_res_connections = dentry;
 
-	dentry = debugfs_create_file("in_flight_summary", S_IRUSR|S_IRGRP,
-			resource->debugfs_res, resource,
-			&in_flight_summary_fops);
+	dentry = debugfs_create_file("in_flight_summary", 0440,
+				     resource->debugfs_res, resource,
+				     &in_flight_summary_fops);
 	if (IS_ERR_OR_NULL(dentry))
 		goto fail;
 	resource->debugfs_res_in_flight_summary = dentry;
@@ -645,16 +645,16 @@ void drbd_debugfs_connection_add(struct drbd_connection *connection)
 		goto fail;
 	connection->debugfs_conn = dentry;
 
-	dentry = debugfs_create_file("callback_history", S_IRUSR|S_IRGRP,
-			connection->debugfs_conn, connection,
-			&connection_callback_history_fops);
+	dentry = debugfs_create_file("callback_history", 0440,
+				     connection->debugfs_conn, connection,
+				     &connection_callback_history_fops);
 	if (IS_ERR_OR_NULL(dentry))
 		goto fail;
 	connection->debugfs_conn_callback_history = dentry;
 
-	dentry = debugfs_create_file("oldest_requests", S_IRUSR|S_IRGRP,
-			connection->debugfs_conn, connection,
-			&connection_oldest_requests_fops);
+	dentry = debugfs_create_file("oldest_requests", 0440,
+				     connection->debugfs_conn, connection,
+				     &connection_oldest_requests_fops);
 	if (IS_ERR_OR_NULL(dentry))
 		goto fail;
 	connection->debugfs_conn_oldest_requests = dentry;
@@ -824,7 +824,7 @@ void drbd_debugfs_device_add(struct drbd_device *device)
 	device->debugfs_minor = dentry;
 
 #define DCF(name)	do {					\
-	dentry = debugfs_create_file(#name, S_IRUSR|S_IRGRP,	\
+	dentry = debugfs_create_file(#name, 0440,	\
 			device->debugfs_vol, device,		\
 			&device_ ## name ## _fops);		\
 	if (IS_ERR_OR_NULL(dentry))				\
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 06ecee1b528e..bc4ed2ed40a2 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1405,8 +1405,8 @@ extern struct kmem_cache *drbd_request_cache;
 extern struct kmem_cache *drbd_ee_cache;	/* peer requests */
 extern struct kmem_cache *drbd_bm_ext_cache;	/* bitmap extents */
 extern struct kmem_cache *drbd_al_ext_cache;	/* activity log extents */
-extern mempool_t *drbd_request_mempool;
-extern mempool_t *drbd_ee_mempool;
+extern mempool_t drbd_request_mempool;
+extern mempool_t drbd_ee_mempool;
 
 /* drbd's page pool, used to buffer data received from the peer,
  * or data requested by the peer.
@@ -1432,16 +1432,16 @@ extern wait_queue_head_t drbd_pp_wait;
  * 128 should be plenty, currently we probably can get away with as few as 1.
  */
 #define DRBD_MIN_POOL_PAGES	128
-extern mempool_t *drbd_md_io_page_pool;
+extern mempool_t drbd_md_io_page_pool;
 
 /* We also need to make sure we get a bio
  * when we need it for housekeeping purposes */
-extern struct bio_set *drbd_md_io_bio_set;
+extern struct bio_set drbd_md_io_bio_set;
 /* to allocate from that set */
 extern struct bio *bio_alloc_drbd(gfp_t gfp_mask);
 
 /* And a bio_set for cloning */
-extern struct bio_set *drbd_io_bio_set;
+extern struct bio_set drbd_io_bio_set;
 
 extern struct mutex resources_mutex;
 
@@ -1643,7 +1643,7 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
 
 /* drbd_proc.c */
 extern struct proc_dir_entry *drbd_proc;
-extern const struct file_operations drbd_proc_fops;
+int drbd_seq_show(struct seq_file *seq, void *v);
 
 /* drbd_actlog.c */
 extern bool drbd_al_begin_io_prepare(struct drbd_device *device, struct drbd_interval *i);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 185f1ef00a7c..7655d6133139 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -124,11 +124,11 @@ struct kmem_cache *drbd_request_cache;
 struct kmem_cache *drbd_ee_cache;	/* peer requests */
 struct kmem_cache *drbd_bm_ext_cache;	/* bitmap extents */
 struct kmem_cache *drbd_al_ext_cache;	/* activity log extents */
-mempool_t *drbd_request_mempool;
-mempool_t *drbd_ee_mempool;
-mempool_t *drbd_md_io_page_pool;
-struct bio_set *drbd_md_io_bio_set;
-struct bio_set *drbd_io_bio_set;
+mempool_t drbd_request_mempool;
+mempool_t drbd_ee_mempool;
+mempool_t drbd_md_io_page_pool;
+struct bio_set drbd_md_io_bio_set;
+struct bio_set drbd_io_bio_set;
 
 /* I do not use a standard mempool, because:
    1) I want to hand out the pre-allocated objects first.
@@ -153,10 +153,10 @@ struct bio *bio_alloc_drbd(gfp_t gfp_mask)
 {
 	struct bio *bio;
 
-	if (!drbd_md_io_bio_set)
+	if (!bioset_initialized(&drbd_md_io_bio_set))
 		return bio_alloc(gfp_mask, 1);
 
-	bio = bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set);
+	bio = bio_alloc_bioset(gfp_mask, 1, &drbd_md_io_bio_set);
 	if (!bio)
 		return NULL;
 	return bio;
@@ -2097,16 +2097,11 @@ static void drbd_destroy_mempools(void)
 
 	/* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */
 
-	if (drbd_io_bio_set)
-		bioset_free(drbd_io_bio_set);
-	if (drbd_md_io_bio_set)
-		bioset_free(drbd_md_io_bio_set);
-	if (drbd_md_io_page_pool)
-		mempool_destroy(drbd_md_io_page_pool);
-	if (drbd_ee_mempool)
-		mempool_destroy(drbd_ee_mempool);
-	if (drbd_request_mempool)
-		mempool_destroy(drbd_request_mempool);
+	bioset_exit(&drbd_io_bio_set);
+	bioset_exit(&drbd_md_io_bio_set);
+	mempool_exit(&drbd_md_io_page_pool);
+	mempool_exit(&drbd_ee_mempool);
+	mempool_exit(&drbd_request_mempool);
 	if (drbd_ee_cache)
 		kmem_cache_destroy(drbd_ee_cache);
 	if (drbd_request_cache)
@@ -2116,11 +2111,6 @@ static void drbd_destroy_mempools(void)
 	if (drbd_al_ext_cache)
 		kmem_cache_destroy(drbd_al_ext_cache);
 
-	drbd_io_bio_set      = NULL;
-	drbd_md_io_bio_set   = NULL;
-	drbd_md_io_page_pool = NULL;
-	drbd_ee_mempool      = NULL;
-	drbd_request_mempool = NULL;
 	drbd_ee_cache        = NULL;
 	drbd_request_cache   = NULL;
 	drbd_bm_ext_cache    = NULL;
@@ -2133,18 +2123,7 @@ static int drbd_create_mempools(void)
 {
 	struct page *page;
 	const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count;
-	int i;
-
-	/* prepare our caches and mempools */
-	drbd_request_mempool = NULL;
-	drbd_ee_cache        = NULL;
-	drbd_request_cache   = NULL;
-	drbd_bm_ext_cache    = NULL;
-	drbd_al_ext_cache    = NULL;
-	drbd_pp_pool         = NULL;
-	drbd_md_io_page_pool = NULL;
-	drbd_md_io_bio_set   = NULL;
-	drbd_io_bio_set      = NULL;
+	int i, ret;
 
 	/* caches */
 	drbd_request_cache = kmem_cache_create(
@@ -2168,26 +2147,26 @@ static int drbd_create_mempools(void)
 		goto Enomem;
 
 	/* mempools */
-	drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
-	if (drbd_io_bio_set == NULL)
+	ret = bioset_init(&drbd_io_bio_set, BIO_POOL_SIZE, 0, 0);
+	if (ret)
 		goto Enomem;
 
-	drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0,
-					   BIOSET_NEED_BVECS);
-	if (drbd_md_io_bio_set == NULL)
+	ret = bioset_init(&drbd_md_io_bio_set, DRBD_MIN_POOL_PAGES, 0,
+			  BIOSET_NEED_BVECS);
+	if (ret)
 		goto Enomem;
 
-	drbd_md_io_page_pool = mempool_create_page_pool(DRBD_MIN_POOL_PAGES, 0);
-	if (drbd_md_io_page_pool == NULL)
+	ret = mempool_init_page_pool(&drbd_md_io_page_pool, DRBD_MIN_POOL_PAGES, 0);
+	if (ret)
 		goto Enomem;
 
-	drbd_request_mempool = mempool_create_slab_pool(number,
-		drbd_request_cache);
-	if (drbd_request_mempool == NULL)
+	ret = mempool_init_slab_pool(&drbd_request_mempool, number,
+				     drbd_request_cache);
+	if (ret)
 		goto Enomem;
 
-	drbd_ee_mempool = mempool_create_slab_pool(number, drbd_ee_cache);
-	if (drbd_ee_mempool == NULL)
+	ret = mempool_init_slab_pool(&drbd_ee_mempool, number, drbd_ee_cache);
+	if (ret)
 		goto Enomem;
 
 	/* drbd's page pool */
@@ -3010,7 +2989,7 @@ static int __init drbd_init(void)
 		goto fail;
 
 	err = -ENOMEM;
-	drbd_proc = proc_create_data("drbd", S_IFREG | S_IRUGO , NULL, &drbd_proc_fops, NULL);
+	drbd_proc = proc_create_single("drbd", S_IFREG | 0444 , NULL, drbd_seq_show);
 	if (!drbd_proc)	{
 		pr_err("unable to register proc file\n");
 		goto fail;
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index 582caeb0de86..74ef29247bb5 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -33,18 +33,7 @@
 #include <linux/drbd.h>
 #include "drbd_int.h"
 
-static int drbd_proc_open(struct inode *inode, struct file *file);
-static int drbd_proc_release(struct inode *inode, struct file *file);
-
-
 struct proc_dir_entry *drbd_proc;
-const struct file_operations drbd_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= drbd_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= drbd_proc_release,
-};
 
 static void seq_printf_with_thousands_grouping(struct seq_file *seq, long v)
 {
@@ -235,7 +224,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 	}
 }
 
-static int drbd_seq_show(struct seq_file *seq, void *v)
+int drbd_seq_show(struct seq_file *seq, void *v)
 {
 	int i, prev_i = -1;
 	const char *sn;
@@ -345,24 +334,3 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int drbd_proc_open(struct inode *inode, struct file *file)
-{
-	int err;
-
-	if (try_module_get(THIS_MODULE)) {
-		err = single_open(file, drbd_seq_show, NULL);
-		if (err)
-			module_put(THIS_MODULE);
-		return err;
-	}
-	return -ENODEV;
-}
-
-static int drbd_proc_release(struct inode *inode, struct file *file)
-{
-	module_put(THIS_MODULE);
-	return single_release(inode, file);
-}
-
-/* PROC FS stuff end */
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c72dee0ef083..be9450f5ad1c 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -378,7 +378,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
 	if (drbd_insert_fault(device, DRBD_FAULT_AL_EE))
 		return NULL;
 
-	peer_req = mempool_alloc(drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM);
+	peer_req = mempool_alloc(&drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM);
 	if (!peer_req) {
 		if (!(gfp_mask & __GFP_NOWARN))
 			drbd_err(device, "%s: allocation failed\n", __func__);
@@ -409,7 +409,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
 	return peer_req;
 
  fail:
-	mempool_free(peer_req, drbd_ee_mempool);
+	mempool_free(peer_req, &drbd_ee_mempool);
 	return NULL;
 }
 
@@ -426,7 +426,7 @@ void __drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *
 		peer_req->flags &= ~EE_CALL_AL_COMPLETE_IO;
 		drbd_al_complete_io(device, &peer_req->i);
 	}
-	mempool_free(peer_req, drbd_ee_mempool);
+	mempool_free(peer_req, &drbd_ee_mempool);
 }
 
 int drbd_free_peer_reqs(struct drbd_device *device, struct list_head *list)
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index a500e738d929..a47e4987ee46 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -55,7 +55,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
 {
 	struct drbd_request *req;
 
-	req = mempool_alloc(drbd_request_mempool, GFP_NOIO);
+	req = mempool_alloc(&drbd_request_mempool, GFP_NOIO);
 	if (!req)
 		return NULL;
 	memset(req, 0, sizeof(*req));
@@ -184,7 +184,7 @@ void drbd_req_destroy(struct kref *kref)
 		}
 	}
 
-	mempool_free(req, drbd_request_mempool);
+	mempool_free(req, &drbd_request_mempool);
 }
 
 static void wake_all_senders(struct drbd_connection *connection)
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index cb97b3b30962..94c654020f0f 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -269,7 +269,7 @@ enum drbd_req_state_bits {
 static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
 {
 	struct bio *bio;
-	bio = bio_clone_fast(bio_src, GFP_NOIO, drbd_io_bio_set);
+	bio = bio_clone_fast(bio_src, GFP_NOIO, &drbd_io_bio_set);
 
 	req->private_bio = bio;
 
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 8ec7235fc93b..8871b5044d9e 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4450,7 +4450,7 @@ static ssize_t floppy_cmos_show(struct device *dev,
 	return sprintf(buf, "%X\n", UDP->cmos);
 }
 
-static DEVICE_ATTR(cmos, S_IRUGO, floppy_cmos_show, NULL);
+static DEVICE_ATTR(cmos, 0444, floppy_cmos_show, NULL);
 
 static struct attribute *floppy_dev_attrs[] = {
 	&dev_attr_cmos.attr,
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index c9d04497a415..4838b0dbaad3 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -451,25 +451,47 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq)
 static void lo_complete_rq(struct request *rq)
 {
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	blk_status_t ret = BLK_STS_OK;
 
-	if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
-		     cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
-		struct bio *bio = cmd->rq->bio;
-
-		bio_advance(bio, cmd->ret);
-		zero_fill_bio(bio);
+	if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
+	    req_op(rq) != REQ_OP_READ) {
+		if (cmd->ret < 0)
+			ret = BLK_STS_IOERR;
+		goto end_io;
 	}
 
-	blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
+	/*
+	 * Short READ - if we got some data, advance our request and
+	 * retry it. If we got no data, end the rest with EIO.
+	 */
+	if (cmd->ret) {
+		blk_update_request(rq, BLK_STS_OK, cmd->ret);
+		cmd->ret = 0;
+		blk_mq_requeue_request(rq, true);
+	} else {
+		if (cmd->use_aio) {
+			struct bio *bio = rq->bio;
+
+			while (bio) {
+				zero_fill_bio(bio);
+				bio = bio->bi_next;
+			}
+		}
+		ret = BLK_STS_IOERR;
+end_io:
+		blk_mq_end_request(rq, ret);
+	}
 }
 
 static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
 {
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
+
 	if (!atomic_dec_and_test(&cmd->ref))
 		return;
 	kfree(cmd->bvec);
 	cmd->bvec = NULL;
-	blk_mq_complete_request(cmd->rq);
+	blk_mq_complete_request(rq);
 }
 
 static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
@@ -487,7 +509,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 {
 	struct iov_iter iter;
 	struct bio_vec *bvec;
-	struct request *rq = cmd->rq;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct bio *bio = rq->bio;
 	struct file *file = lo->lo_backing_file;
 	unsigned int offset;
@@ -710,7 +732,7 @@ static ssize_t loop_attr_do_show_##_name(struct device *d,		\
 	return loop_attr_show(d, b, loop_attr_##_name##_show);		\
 }									\
 static struct device_attribute loop_attr_##_name =			\
-	__ATTR(_name, S_IRUGO, loop_attr_do_show_##_name, NULL);
+	__ATTR(_name, 0444, loop_attr_do_show_##_name, NULL);
 
 static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
 {
@@ -787,16 +809,17 @@ static struct attribute_group loop_attribute_group = {
 	.attrs= loop_attrs,
 };
 
-static int loop_sysfs_init(struct loop_device *lo)
+static void loop_sysfs_init(struct loop_device *lo)
 {
-	return sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
-				  &loop_attribute_group);
+	lo->sysfs_inited = !sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
+						&loop_attribute_group);
 }
 
 static void loop_sysfs_exit(struct loop_device *lo)
 {
-	sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
-			   &loop_attribute_group);
+	if (lo->sysfs_inited)
+		sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
+				   &loop_attribute_group);
 }
 
 static void loop_config_discard(struct loop_device *lo)
@@ -1046,6 +1069,7 @@ static int loop_clr_fd(struct loop_device *lo)
 	if (bdev) {
 		bdput(bdev);
 		invalidate_bdev(bdev);
+		bdev->bd_inode->i_mapping->wb_err = 0;
 	}
 	set_capacity(lo->lo_disk, 0);
 	loop_sysfs_exit(lo);
@@ -1654,9 +1678,9 @@ static const struct block_device_operations lo_fops = {
  * And now the modules code and kernel interface.
  */
 static int max_loop;
-module_param(max_loop, int, S_IRUGO);
+module_param(max_loop, int, 0444);
 MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
-module_param(max_part, int, S_IRUGO);
+module_param(max_part, int, 0444);
 MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
@@ -1702,15 +1726,16 @@ EXPORT_SYMBOL(loop_unregister_transfer);
 static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
-	struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
-	struct loop_device *lo = cmd->rq->q->queuedata;
+	struct request *rq = bd->rq;
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	struct loop_device *lo = rq->q->queuedata;
 
-	blk_mq_start_request(bd->rq);
+	blk_mq_start_request(rq);
 
 	if (lo->lo_state != Lo_bound)
 		return BLK_STS_IOERR;
 
-	switch (req_op(cmd->rq)) {
+	switch (req_op(rq)) {
 	case REQ_OP_FLUSH:
 	case REQ_OP_DISCARD:
 	case REQ_OP_WRITE_ZEROES:
@@ -1723,8 +1748,8 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	/* always use the first bio's css */
 #ifdef CONFIG_BLK_CGROUP
-	if (cmd->use_aio && cmd->rq->bio && cmd->rq->bio->bi_css) {
-		cmd->css = cmd->rq->bio->bi_css;
+	if (cmd->use_aio && rq->bio && rq->bio->bi_css) {
+		cmd->css = rq->bio->bi_css;
 		css_get(cmd->css);
 	} else
 #endif
@@ -1736,8 +1761,9 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 static void loop_handle_cmd(struct loop_cmd *cmd)
 {
-	const bool write = op_is_write(req_op(cmd->rq));
-	struct loop_device *lo = cmd->rq->q->queuedata;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
+	const bool write = op_is_write(req_op(rq));
+	struct loop_device *lo = rq->q->queuedata;
 	int ret = 0;
 
 	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
@@ -1745,12 +1771,12 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 		goto failed;
 	}
 
-	ret = do_req_filebacked(lo, cmd->rq);
+	ret = do_req_filebacked(lo, rq);
  failed:
 	/* complete non-aio request */
 	if (!cmd->use_aio || ret) {
 		cmd->ret = ret ? -EIO : 0;
-		blk_mq_complete_request(cmd->rq);
+		blk_mq_complete_request(rq);
 	}
 }
 
@@ -1767,9 +1793,7 @@ static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq,
 {
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
-	cmd->rq = rq;
 	kthread_init_work(&cmd->work, loop_queue_work);
-
 	return 0;
 }
 
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 0f45416e4fcf..4d42c7af7de7 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -58,6 +58,7 @@ struct loop_device {
 	struct kthread_worker	worker;
 	struct task_struct	*worker_task;
 	bool			use_dio;
+	bool			sysfs_inited;
 
 	struct request_queue	*lo_queue;
 	struct blk_mq_tag_set	tag_set;
@@ -66,7 +67,6 @@ struct loop_device {
 
 struct loop_cmd {
 	struct kthread_work work;
-	struct request *rq;
 	bool use_aio; /* use AIO interface to handle I/O */
 	atomic_t ref; /* only for aio */
 	long ret;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 769c551e3d71..c73626decb46 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2285,7 +2285,7 @@ static ssize_t mtip_hw_show_status(struct device *dev,
 	return size;
 }
 
-static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL);
+static DEVICE_ATTR(status, 0444, mtip_hw_show_status, NULL);
 
 /* debugsfs entries */
 
@@ -2566,10 +2566,9 @@ static int mtip_hw_debugfs_init(struct driver_data *dd)
 		return -1;
 	}
 
-	debugfs_create_file("flags", S_IRUGO, dd->dfs_node, dd,
-							&mtip_flags_fops);
-	debugfs_create_file("registers", S_IRUGO, dd->dfs_node, dd,
-							&mtip_regs_fops);
+	debugfs_create_file("flags", 0444, dd->dfs_node, dd, &mtip_flags_fops);
+	debugfs_create_file("registers", 0444, dd->dfs_node, dd,
+			    &mtip_regs_fops);
 
 	return 0;
 }
@@ -2726,15 +2725,11 @@ static void mtip_softirq_done_fn(struct request *rq)
 	blk_mq_end_request(rq, cmd->status);
 }
 
-static void mtip_abort_cmd(struct request *req, void *data,
-							bool reserved)
+static void mtip_abort_cmd(struct request *req, void *data, bool reserved)
 {
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
 	struct driver_data *dd = data;
 
-	if (!blk_mq_request_started(req))
-		return;
-
 	dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
 
 	clear_bit(req->tag, dd->port->cmds_to_issue);
@@ -2742,14 +2737,10 @@ static void mtip_abort_cmd(struct request *req, void *data,
 	mtip_softirq_done_fn(req);
 }
 
-static void mtip_queue_cmd(struct request *req, void *data,
-							bool reserved)
+static void mtip_queue_cmd(struct request *req, void *data, bool reserved)
 {
 	struct driver_data *dd = data;
 
-	if (!blk_mq_request_started(req))
-		return;
-
 	set_bit(req->tag, dd->port->cmds_to_issue);
 	blk_abort_request(req);
 }
@@ -3720,7 +3711,8 @@ static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req,
 		struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
 
 		cmd->status = BLK_STS_TIMEOUT;
-		return BLK_EH_HANDLED;
+		blk_mq_complete_request(req);
+		return BLK_EH_DONE;
 	}
 
 	if (test_bit(req->tag, dd->port->cmds_to_issue))
@@ -3862,7 +3854,6 @@ skip_create_disk:
 	blk_queue_max_hw_sectors(dd->queue, 0xffff);
 	blk_queue_max_segment_size(dd->queue, 0x400000);
 	blk_queue_io_min(dd->queue, 4096);
-	blk_queue_bounce_limit(dd->queue, dd->pdev->dma_mask);
 
 	/* Signal trim support */
 	if (dd->trim_supp == true) {
@@ -4273,7 +4264,7 @@ static int mtip_pci_probe(struct pci_dev *pdev,
 	if (!dd->isr_workq) {
 		dev_warn(&pdev->dev, "Can't create wq %d\n", dd->instance);
 		rv = -ENOMEM;
-		goto block_initialize_err;
+		goto setmask_err;
 	}
 
 	memset(cpu_list, 0, sizeof(cpu_list));
@@ -4614,7 +4605,7 @@ static int __init mtip_init(void)
 	}
 	if (dfs_parent) {
 		dfs_device_status = debugfs_create_file("device_status",
-					S_IRUGO, dfs_parent, NULL,
+					0444, dfs_parent, NULL,
 					&mtip_device_status_fops);
 		if (IS_ERR_OR_NULL(dfs_device_status)) {
 			pr_err("Error creating device_status node\n");
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index afbc202ca6fd..3ed1ef8ee528 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -166,16 +166,19 @@ static ssize_t pid_show(struct device *dev,
 }
 
 static const struct device_attribute pid_attr = {
-	.attr = { .name = "pid", .mode = S_IRUGO},
+	.attr = { .name = "pid", .mode = 0444},
 	.show = pid_show,
 };
 
 static void nbd_dev_remove(struct nbd_device *nbd)
 {
 	struct gendisk *disk = nbd->disk;
+	struct request_queue *q;
+
 	if (disk) {
+		q = disk->queue;
 		del_gendisk(disk);
-		blk_cleanup_queue(disk->queue);
+		blk_cleanup_queue(q);
 		blk_mq_free_tag_set(&nbd->tag_set);
 		disk->private_data = NULL;
 		put_disk(disk);
@@ -213,7 +216,15 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
 	}
 	if (!nsock->dead) {
 		kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
-		atomic_dec(&nbd->config->live_connections);
+		if (atomic_dec_return(&nbd->config->live_connections) == 0) {
+			if (test_and_clear_bit(NBD_DISCONNECT_REQUESTED,
+					       &nbd->config->runtime_flags)) {
+				set_bit(NBD_DISCONNECTED,
+					&nbd->config->runtime_flags);
+				dev_info(nbd_to_dev(nbd),
+					"Disconnected due to user request.\n");
+			}
+		}
 	}
 	nsock->dead = true;
 	nsock->pending = NULL;
@@ -231,9 +242,22 @@ static void nbd_size_clear(struct nbd_device *nbd)
 static void nbd_size_update(struct nbd_device *nbd)
 {
 	struct nbd_config *config = nbd->config;
+	struct block_device *bdev = bdget_disk(nbd->disk, 0);
+
+	if (config->flags & NBD_FLAG_SEND_TRIM) {
+		nbd->disk->queue->limits.discard_granularity = config->blksize;
+		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
+	}
 	blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
 	blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
 	set_capacity(nbd->disk, config->bytesize >> 9);
+	if (bdev) {
+		if (bdev->bd_disk)
+			bd_set_size(bdev, config->bytesize);
+		else
+			bdev->bd_invalidated = 1;
+		bdput(bdev);
+	}
 	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
 }
 
@@ -243,6 +267,8 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize,
 	struct nbd_config *config = nbd->config;
 	config->blksize = blocksize;
 	config->bytesize = blocksize * nr_blocks;
+	if (nbd->task_recv != NULL)
+		nbd_size_update(nbd);
 }
 
 static void nbd_complete_rq(struct request *req)
@@ -286,13 +312,15 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 
 	if (!refcount_inc_not_zero(&nbd->config_refs)) {
 		cmd->status = BLK_STS_TIMEOUT;
-		return BLK_EH_HANDLED;
+		goto done;
 	}
 	config = nbd->config;
 
 	if (config->num_connections > 1) {
 		dev_err_ratelimited(nbd_to_dev(nbd),
-				    "Connection timed out, retrying\n");
+				    "Connection timed out, retrying (%d/%d alive)\n",
+				    atomic_read(&config->live_connections),
+				    config->num_connections);
 		/*
 		 * Hooray we have more connections, requeue this IO, the submit
 		 * path will put it on a real connection.
@@ -314,7 +342,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 			}
 			blk_mq_requeue_request(req, true);
 			nbd_config_put(nbd);
-			return BLK_EH_NOT_HANDLED;
+			return BLK_EH_DONE;
 		}
 	} else {
 		dev_err_ratelimited(nbd_to_dev(nbd),
@@ -324,8 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	cmd->status = BLK_STS_IOERR;
 	sock_shutdown(nbd);
 	nbd_config_put(nbd);
-
-	return BLK_EH_HANDLED;
+done:
+	blk_mq_complete_request(req);
+	return BLK_EH_DONE;
 }
 
 /*
@@ -647,11 +676,8 @@ static void recv_work(struct work_struct *work)
 
 static void nbd_clear_req(struct request *req, void *data, bool reserved)
 {
-	struct nbd_cmd *cmd;
+	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
-	if (!blk_mq_request_started(req))
-		return;
-	cmd = blk_mq_rq_to_pdu(req);
 	cmd->status = BLK_STS_IOERR;
 	blk_mq_complete_request(req);
 }
@@ -714,10 +740,9 @@ static int wait_for_reconnect(struct nbd_device *nbd)
 		return 0;
 	if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
 		return 0;
-	wait_event_timeout(config->conn_wait,
-			   atomic_read(&config->live_connections),
-			   config->dead_conn_timeout);
-	return atomic_read(&config->live_connections);
+	return wait_event_timeout(config->conn_wait,
+				  atomic_read(&config->live_connections) > 0,
+				  config->dead_conn_timeout) > 0;
 }
 
 static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
@@ -950,10 +975,6 @@ static void nbd_bdev_reset(struct block_device *bdev)
 	if (bdev->bd_openers > 1)
 		return;
 	bd_set_size(bdev, 0);
-	if (max_part > 0) {
-		blkdev_reread_part(bdev);
-		bdev->bd_invalidated = 1;
-	}
 }
 
 static void nbd_parse_flags(struct nbd_device *nbd)
@@ -1040,6 +1061,8 @@ static void nbd_config_put(struct nbd_device *nbd)
 		nbd->config = NULL;
 
 		nbd->tag_set.timeout = 0;
+		nbd->disk->queue->limits.discard_granularity = 0;
+		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 
 		mutex_unlock(&nbd->config_lock);
@@ -1109,7 +1132,6 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 	if (ret)
 		return ret;
 
-	bd_set_size(bdev, config->bytesize);
 	if (max_part)
 		bdev->bd_invalidated = 1;
 	mutex_unlock(&nbd->config_lock);
@@ -1118,7 +1140,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 	if (ret)
 		sock_shutdown(nbd);
 	mutex_lock(&nbd->config_lock);
-	bd_set_size(bdev, 0);
+	nbd_bdev_reset(bdev);
 	/* user requested, ignore socket errors */
 	if (test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags))
 		ret = 0;
@@ -1269,6 +1291,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
+		bdev->bd_invalidated = 1;
+	} else if (nbd_disconnected(nbd->config)) {
+		bdev->bd_invalidated = 1;
 	}
 out:
 	mutex_unlock(&nbd_index_mutex);
@@ -1490,8 +1515,8 @@ static int nbd_dev_add(int index)
 	 */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
-	disk->queue->limits.discard_granularity = 512;
-	blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
+	disk->queue->limits.discard_granularity = 0;
+	blk_queue_max_discard_sectors(disk->queue, 0);
 	blk_queue_max_segment_size(disk->queue, UINT_MAX);
 	blk_queue_max_segments(disk->queue, USHRT_MAX);
 	blk_queue_max_hw_sectors(disk->queue, 65536);
@@ -1755,6 +1780,7 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
 	}
 	mutex_lock(&nbd->config_lock);
 	nbd_disconnect(nbd);
+	nbd_clear_sock(nbd);
 	mutex_unlock(&nbd->config_lock);
 	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
 			       &nbd->config->runtime_flags))
@@ -2093,7 +2119,8 @@ static int __init nbd_init(void)
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 	recv_workqueue = alloc_workqueue("knbd-recv",
-					 WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+					 WQ_MEM_RECLAIM | WQ_HIGHPRI |
+					 WQ_UNBOUND, 0);
 	if (!recv_workqueue)
 		return -ENOMEM;
 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index a76553293a31..2bdadd7f1454 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -157,23 +157,23 @@ enum {
 };
 
 static int g_no_sched;
-module_param_named(no_sched, g_no_sched, int, S_IRUGO);
+module_param_named(no_sched, g_no_sched, int, 0444);
 MODULE_PARM_DESC(no_sched, "No io scheduler");
 
 static int g_submit_queues = 1;
-module_param_named(submit_queues, g_submit_queues, int, S_IRUGO);
+module_param_named(submit_queues, g_submit_queues, int, 0444);
 MODULE_PARM_DESC(submit_queues, "Number of submission queues");
 
 static int g_home_node = NUMA_NO_NODE;
-module_param_named(home_node, g_home_node, int, S_IRUGO);
+module_param_named(home_node, g_home_node, int, 0444);
 MODULE_PARM_DESC(home_node, "Home node for the device");
 
 #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
 static char g_timeout_str[80];
-module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), S_IRUGO);
+module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444);
 
 static char g_requeue_str[80];
-module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), S_IRUGO);
+module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444);
 #endif
 
 static int g_queue_mode = NULL_Q_MQ;
@@ -203,27 +203,27 @@ static const struct kernel_param_ops null_queue_mode_param_ops = {
 	.get	= param_get_int,
 };
 
-device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, S_IRUGO);
+device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, 0444);
 MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
 
 static int g_gb = 250;
-module_param_named(gb, g_gb, int, S_IRUGO);
+module_param_named(gb, g_gb, int, 0444);
 MODULE_PARM_DESC(gb, "Size in GB");
 
 static int g_bs = 512;
-module_param_named(bs, g_bs, int, S_IRUGO);
+module_param_named(bs, g_bs, int, 0444);
 MODULE_PARM_DESC(bs, "Block size (in bytes)");
 
 static int nr_devices = 1;
-module_param(nr_devices, int, S_IRUGO);
+module_param(nr_devices, int, 0444);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
 
 static bool g_blocking;
-module_param_named(blocking, g_blocking, bool, S_IRUGO);
+module_param_named(blocking, g_blocking, bool, 0444);
 MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
 
 static bool shared_tags;
-module_param(shared_tags, bool, S_IRUGO);
+module_param(shared_tags, bool, 0444);
 MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
 
 static int g_irqmode = NULL_IRQ_SOFTIRQ;
@@ -239,19 +239,19 @@ static const struct kernel_param_ops null_irqmode_param_ops = {
 	.get	= param_get_int,
 };
 
-device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, S_IRUGO);
+device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, 0444);
 MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
 
 static unsigned long g_completion_nsec = 10000;
-module_param_named(completion_nsec, g_completion_nsec, ulong, S_IRUGO);
+module_param_named(completion_nsec, g_completion_nsec, ulong, 0444);
 MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");
 
 static int g_hw_queue_depth = 64;
-module_param_named(hw_queue_depth, g_hw_queue_depth, int, S_IRUGO);
+module_param_named(hw_queue_depth, g_hw_queue_depth, int, 0444);
 MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64");
 
 static bool g_use_per_node_hctx;
-module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, S_IRUGO);
+module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
 MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
 
 static struct nullb_device *null_alloc_dev(void);
@@ -1365,7 +1365,8 @@ static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
 static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
 {
 	pr_info("null: rq %p timed out\n", rq);
-	return BLK_EH_HANDLED;
+	blk_mq_complete_request(rq);
+	return BLK_EH_DONE;
 }
 
 static int null_rq_prep_fn(struct request_queue *q, struct request *req)
@@ -1427,7 +1428,8 @@ static void null_request_fn(struct request_queue *q)
 static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
 {
 	pr_info("null: rq %p timed out\n", rq);
-	return BLK_EH_HANDLED;
+	blk_mq_complete_request(rq);
+	return BLK_EH_DONE;
 }
 
 static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 27a44b97393a..8961b190e256 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -740,7 +740,7 @@ static int pd_special_command(struct pd_unit *disk,
 {
 	struct request *rq;
 
-	rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, 0);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index c61d20c9f3f8..b3f83cd96f33 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -97,8 +97,8 @@ static int pktdev_major;
 static int write_congestion_on  = PKT_WRITE_CONGESTION_ON;
 static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
 static struct mutex ctl_mutex;	/* Serialize open/close/setup/teardown */
-static mempool_t *psd_pool;
-static struct bio_set *pkt_bio_set;
+static mempool_t psd_pool;
+static struct bio_set pkt_bio_set;
 
 static struct class	*class_pktcdvd = NULL;    /* /sys/class/pktcdvd */
 static struct dentry	*pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
@@ -478,8 +478,8 @@ static void pkt_debugfs_dev_new(struct pktcdvd_device *pd)
 	if (!pd->dfs_d_root)
 		return;
 
-	pd->dfs_f_info = debugfs_create_file("info", S_IRUGO,
-				pd->dfs_d_root, pd, &debug_fops);
+	pd->dfs_f_info = debugfs_create_file("info", 0444,
+					     pd->dfs_d_root, pd, &debug_fops);
 }
 
 static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd)
@@ -631,7 +631,7 @@ static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
 static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
 {
 	rb_erase(&node->rb_node, &pd->bio_queue);
-	mempool_free(node, pd->rb_pool);
+	mempool_free(node, &pd->rb_pool);
 	pd->bio_queue_size--;
 	BUG_ON(pd->bio_queue_size < 0);
 }
@@ -704,13 +704,13 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 	int ret = 0;
 
 	rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
-			     REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM);
+			     REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
 	if (cgc->buflen) {
 		ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
-				      __GFP_RECLAIM);
+				      GFP_NOIO);
 		if (ret)
 			goto out;
 	}
@@ -1285,7 +1285,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 	 * Fill-in bvec with data from orig_bios.
 	 */
 	spin_lock(&pkt->lock);
-	bio_copy_data(pkt->w_bio, pkt->orig_bios.head);
+	bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head);
 
 	pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
 	spin_unlock(&pkt->lock);
@@ -2303,14 +2303,14 @@ static void pkt_end_io_read_cloned(struct bio *bio)
 	psd->bio->bi_status = bio->bi_status;
 	bio_put(bio);
 	bio_endio(psd->bio);
-	mempool_free(psd, psd_pool);
+	mempool_free(psd, &psd_pool);
 	pkt_bio_finished(pd);
 }
 
 static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
 {
-	struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, pkt_bio_set);
-	struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO);
+	struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, &pkt_bio_set);
+	struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
 
 	psd->pd = pd;
 	psd->bio = bio;
@@ -2381,7 +2381,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
 	/*
 	 * No matching packet found. Store the bio in the work queue.
 	 */
-	node = mempool_alloc(pd->rb_pool, GFP_NOIO);
+	node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
 	node->bio = bio;
 	spin_lock(&pd->lock);
 	BUG_ON(pd->bio_queue_size < 0);
@@ -2451,7 +2451,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
 
 			split = bio_split(bio, last_zone -
 					  bio->bi_iter.bi_sector,
-					  GFP_NOIO, pkt_bio_set);
+					  GFP_NOIO, &pkt_bio_set);
 			bio_chain(split, bio);
 		} else {
 			split = bio;
@@ -2538,18 +2538,6 @@ static int pkt_seq_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-static int pkt_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pkt_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations pkt_proc_fops = {
-	.open	= pkt_seq_open,
-	.read	= seq_read,
-	.llseek	= seq_lseek,
-	.release = single_release
-};
-
 static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 {
 	int i;
@@ -2604,7 +2592,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		goto out_mem;
 	}
 
-	proc_create_data(pd->name, 0, pkt_proc, &pkt_proc_fops, pd);
+	proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd);
 	pkt_dbg(1, pd, "writer mapped to %s\n", bdevname(bdev, b));
 	return 0;
 
@@ -2707,9 +2695,9 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	if (!pd)
 		goto out_mutex;
 
-	pd->rb_pool = mempool_create_kmalloc_pool(PKT_RB_POOL_SIZE,
-						  sizeof(struct pkt_rb_node));
-	if (!pd->rb_pool)
+	ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
+					sizeof(struct pkt_rb_node));
+	if (ret)
 		goto out_mem;
 
 	INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
@@ -2766,7 +2754,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 out_mem2:
 	put_disk(disk);
 out_mem:
-	mempool_destroy(pd->rb_pool);
+	mempool_exit(&pd->rb_pool);
 	kfree(pd);
 out_mutex:
 	mutex_unlock(&ctl_mutex);
@@ -2817,7 +2805,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
 	blk_cleanup_queue(pd->disk->queue);
 	put_disk(pd->disk);
 
-	mempool_destroy(pd->rb_pool);
+	mempool_exit(&pd->rb_pool);
 	kfree(pd);
 
 	/* This is safe: open() is still holding a reference. */
@@ -2914,14 +2902,14 @@ static int __init pkt_init(void)
 
 	mutex_init(&ctl_mutex);
 
-	psd_pool = mempool_create_kmalloc_pool(PSD_POOL_SIZE,
-					sizeof(struct packet_stacked_data));
-	if (!psd_pool)
-		return -ENOMEM;
-	pkt_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
-	if (!pkt_bio_set) {
-		mempool_destroy(psd_pool);
-		return -ENOMEM;
+	ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
+				    sizeof(struct packet_stacked_data));
+	if (ret)
+		return ret;
+	ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
+	if (ret) {
+		mempool_exit(&psd_pool);
+		return ret;
 	}
 
 	ret = register_blkdev(pktdev_major, DRIVER_NAME);
@@ -2954,8 +2942,8 @@ out_misc:
 out:
 	unregister_blkdev(pktdev_major, DRIVER_NAME);
 out2:
-	mempool_destroy(psd_pool);
-	bioset_free(pkt_bio_set);
+	mempool_exit(&psd_pool);
+	bioset_exit(&pkt_bio_set);
 	return ret;
 }
 
@@ -2968,8 +2956,8 @@ static void __exit pkt_exit(void)
 	pkt_sysfs_cleanup();
 
 	unregister_blkdev(pktdev_major, DRIVER_NAME);
-	mempool_destroy(psd_pool);
-	bioset_free(pkt_bio_set);
+	mempool_exit(&psd_pool);
+	bioset_exit(&pkt_bio_set);
 }
 
 MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 075662f2cf46..afe1508d82c6 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -465,8 +465,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	priv->queue = queue;
 	queue->queuedata = dev;
 
-	blk_queue_bounce_limit(queue, BLK_BOUNCE_HIGH);
-
 	blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9);
 	blk_queue_segment_boundary(queue, -1UL);
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 6a55959cbf78..8fa4533a1249 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -521,26 +521,13 @@ static int ps3vram_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ps3vram_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ps3vram_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ps3vram_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ps3vram_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static void ps3vram_proc_init(struct ps3_system_bus_device *dev)
 {
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
 	struct proc_dir_entry *pde;
 
-	pde = proc_create_data(DEVICE_NAME, 0444, NULL, &ps3vram_proc_fops,
-			       priv);
+	pde = proc_create_single_data(DEVICE_NAME, 0444, NULL,
+			ps3vram_proc_show, priv);
 	if (!pde)
 		dev_warn(&dev->core, "failed to create /proc entry\n");
 }
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 07dc5419bd63..af354047ac4b 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -424,7 +424,7 @@ static struct workqueue_struct *rbd_wq;
  * single-major requires >= 0.75 version of userspace rbd utility.
  */
 static bool single_major = true;
-module_param(single_major, bool, S_IRUGO);
+module_param(single_major, bool, 0444);
 MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (default: true)");
 
 static ssize_t rbd_add(struct bus_type *bus, const char *buf,
@@ -468,11 +468,11 @@ static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf)
 	return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED);
 }
 
-static BUS_ATTR(add, S_IWUSR, NULL, rbd_add);
-static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove);
-static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major);
-static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major);
-static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL);
+static BUS_ATTR(add, 0200, NULL, rbd_add);
+static BUS_ATTR(remove, 0200, NULL, rbd_remove);
+static BUS_ATTR(add_single_major, 0200, NULL, rbd_add_single_major);
+static BUS_ATTR(remove_single_major, 0200, NULL, rbd_remove_single_major);
+static BUS_ATTR(supported_features, 0444, rbd_supported_features_show, NULL);
 
 static struct attribute *rbd_bus_attrs[] = {
 	&bus_attr_add.attr,
@@ -732,6 +732,7 @@ static struct rbd_client *rbd_client_find(struct ceph_options *ceph_opts)
  */
 enum {
 	Opt_queue_depth,
+	Opt_lock_timeout,
 	Opt_last_int,
 	/* int args above */
 	Opt_last_string,
@@ -740,11 +741,13 @@ enum {
 	Opt_read_write,
 	Opt_lock_on_read,
 	Opt_exclusive,
+	Opt_notrim,
 	Opt_err
 };
 
 static match_table_t rbd_opts_tokens = {
 	{Opt_queue_depth, "queue_depth=%d"},
+	{Opt_lock_timeout, "lock_timeout=%d"},
 	/* int args above */
 	/* string args above */
 	{Opt_read_only, "read_only"},
@@ -753,20 +756,25 @@ static match_table_t rbd_opts_tokens = {
 	{Opt_read_write, "rw"},		/* Alternate spelling */
 	{Opt_lock_on_read, "lock_on_read"},
 	{Opt_exclusive, "exclusive"},
+	{Opt_notrim, "notrim"},
 	{Opt_err, NULL}
 };
 
 struct rbd_options {
 	int	queue_depth;
+	unsigned long	lock_timeout;
 	bool	read_only;
 	bool	lock_on_read;
 	bool	exclusive;
+	bool	trim;
 };
 
 #define RBD_QUEUE_DEPTH_DEFAULT	BLKDEV_MAX_RQ
+#define RBD_LOCK_TIMEOUT_DEFAULT 0  /* no timeout */
 #define RBD_READ_ONLY_DEFAULT	false
 #define RBD_LOCK_ON_READ_DEFAULT false
 #define RBD_EXCLUSIVE_DEFAULT	false
+#define RBD_TRIM_DEFAULT	true
 
 static int parse_rbd_opts_token(char *c, void *private)
 {
@@ -796,6 +804,14 @@ static int parse_rbd_opts_token(char *c, void *private)
 		}
 		rbd_opts->queue_depth = intval;
 		break;
+	case Opt_lock_timeout:
+		/* 0 is "wait forever" (i.e. infinite timeout) */
+		if (intval < 0 || intval > INT_MAX / 1000) {
+			pr_err("lock_timeout out of range\n");
+			return -EINVAL;
+		}
+		rbd_opts->lock_timeout = msecs_to_jiffies(intval * 1000);
+		break;
 	case Opt_read_only:
 		rbd_opts->read_only = true;
 		break;
@@ -808,6 +824,9 @@ static int parse_rbd_opts_token(char *c, void *private)
 	case Opt_exclusive:
 		rbd_opts->exclusive = true;
 		break;
+	case Opt_notrim:
+		rbd_opts->trim = false;
+		break;
 	default:
 		/* libceph prints "bad option" msg */
 		return -EINVAL;
@@ -1392,7 +1411,7 @@ static bool rbd_img_is_write(struct rbd_img_request *img_req)
 	case OBJ_OP_DISCARD:
 		return true;
 	default:
-		rbd_assert(0);
+		BUG();
 	}
 }
 
@@ -2347,7 +2366,9 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes)
 	osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd",
 			    "copyup");
 	osd_req_op_cls_request_data_bvecs(obj_req->osd_req, 0,
-					  obj_req->copyup_bvecs, bytes);
+					  obj_req->copyup_bvecs,
+					  obj_req->copyup_bvec_count,
+					  bytes);
 
 	switch (obj_req->img_request->op_type) {
 	case OBJ_OP_WRITE:
@@ -2466,7 +2487,7 @@ again:
 		}
 		return false;
 	default:
-		rbd_assert(0);
+		BUG();
 	}
 }
 
@@ -2494,7 +2515,7 @@ static bool __rbd_obj_handle_request(struct rbd_obj_request *obj_req)
 		}
 		return false;
 	default:
-		rbd_assert(0);
+		BUG();
 	}
 }
 
@@ -3533,9 +3554,22 @@ static int rbd_obj_method_sync(struct rbd_device *rbd_dev,
 /*
  * lock_rwsem must be held for read
  */
-static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
+static int rbd_wait_state_locked(struct rbd_device *rbd_dev, bool may_acquire)
 {
 	DEFINE_WAIT(wait);
+	unsigned long timeout;
+	int ret = 0;
+
+	if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
+		return -EBLACKLISTED;
+
+	if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED)
+		return 0;
+
+	if (!may_acquire) {
+		rbd_warn(rbd_dev, "exclusive lock required");
+		return -EROFS;
+	}
 
 	do {
 		/*
@@ -3547,12 +3581,22 @@ static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
 		prepare_to_wait_exclusive(&rbd_dev->lock_waitq, &wait,
 					  TASK_UNINTERRUPTIBLE);
 		up_read(&rbd_dev->lock_rwsem);
-		schedule();
+		timeout = schedule_timeout(ceph_timeout_jiffies(
+						rbd_dev->opts->lock_timeout));
 		down_read(&rbd_dev->lock_rwsem);
-	} while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
-		 !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+		if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+			ret = -EBLACKLISTED;
+			break;
+		}
+		if (!timeout) {
+			rbd_warn(rbd_dev, "timed out waiting for lock");
+			ret = -ETIMEDOUT;
+			break;
+		}
+	} while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
 
 	finish_wait(&rbd_dev->lock_waitq, &wait);
+	return ret;
 }
 
 static void rbd_queue_workfn(struct work_struct *work)
@@ -3638,19 +3682,10 @@ static void rbd_queue_workfn(struct work_struct *work)
 	    (op_type != OBJ_OP_READ || rbd_dev->opts->lock_on_read);
 	if (must_be_locked) {
 		down_read(&rbd_dev->lock_rwsem);
-		if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
-		    !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
-			if (rbd_dev->opts->exclusive) {
-				rbd_warn(rbd_dev, "exclusive lock required");
-				result = -EROFS;
-				goto err_unlock;
-			}
-			rbd_wait_state_locked(rbd_dev);
-		}
-		if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
-			result = -EBLACKLISTED;
+		result = rbd_wait_state_locked(rbd_dev,
+					       !rbd_dev->opts->exclusive);
+		if (result)
 			goto err_unlock;
-		}
 	}
 
 	img_request = rbd_img_request_create(rbd_dev, op_type, snapc);
@@ -3902,7 +3937,8 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 {
 	struct gendisk *disk;
 	struct request_queue *q;
-	u64 segment_size;
+	unsigned int objset_bytes =
+	    rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
 	int err;
 
 	/* create gendisk info */
@@ -3942,20 +3978,19 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 	/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
 
-	/* set io sizes to object size */
-	segment_size = rbd_obj_bytes(&rbd_dev->header);
-	blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+	blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT);
 	q->limits.max_sectors = queue_max_hw_sectors(q);
 	blk_queue_max_segments(q, USHRT_MAX);
 	blk_queue_max_segment_size(q, UINT_MAX);
-	blk_queue_io_min(q, segment_size);
-	blk_queue_io_opt(q, segment_size);
+	blk_queue_io_min(q, objset_bytes);
+	blk_queue_io_opt(q, objset_bytes);
 
-	/* enable the discard support */
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
-	q->limits.discard_granularity = segment_size;
-	blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
-	blk_queue_max_write_zeroes_sectors(q, segment_size / SECTOR_SIZE);
+	if (rbd_dev->opts->trim) {
+		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+		q->limits.discard_granularity = objset_bytes;
+		blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
+		blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
+	}
 
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
 		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
@@ -4169,22 +4204,22 @@ static ssize_t rbd_image_refresh(struct device *dev,
 	return size;
 }
 
-static DEVICE_ATTR(size, S_IRUGO, rbd_size_show, NULL);
-static DEVICE_ATTR(features, S_IRUGO, rbd_features_show, NULL);
-static DEVICE_ATTR(major, S_IRUGO, rbd_major_show, NULL);
-static DEVICE_ATTR(minor, S_IRUGO, rbd_minor_show, NULL);
-static DEVICE_ATTR(client_addr, S_IRUGO, rbd_client_addr_show, NULL);
-static DEVICE_ATTR(client_id, S_IRUGO, rbd_client_id_show, NULL);
-static DEVICE_ATTR(cluster_fsid, S_IRUGO, rbd_cluster_fsid_show, NULL);
-static DEVICE_ATTR(config_info, S_IRUSR, rbd_config_info_show, NULL);
-static DEVICE_ATTR(pool, S_IRUGO, rbd_pool_show, NULL);
-static DEVICE_ATTR(pool_id, S_IRUGO, rbd_pool_id_show, NULL);
-static DEVICE_ATTR(name, S_IRUGO, rbd_name_show, NULL);
-static DEVICE_ATTR(image_id, S_IRUGO, rbd_image_id_show, NULL);
-static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh);
-static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL);
-static DEVICE_ATTR(snap_id, S_IRUGO, rbd_snap_id_show, NULL);
-static DEVICE_ATTR(parent, S_IRUGO, rbd_parent_show, NULL);
+static DEVICE_ATTR(size, 0444, rbd_size_show, NULL);
+static DEVICE_ATTR(features, 0444, rbd_features_show, NULL);
+static DEVICE_ATTR(major, 0444, rbd_major_show, NULL);
+static DEVICE_ATTR(minor, 0444, rbd_minor_show, NULL);
+static DEVICE_ATTR(client_addr, 0444, rbd_client_addr_show, NULL);
+static DEVICE_ATTR(client_id, 0444, rbd_client_id_show, NULL);
+static DEVICE_ATTR(cluster_fsid, 0444, rbd_cluster_fsid_show, NULL);
+static DEVICE_ATTR(config_info, 0400, rbd_config_info_show, NULL);
+static DEVICE_ATTR(pool, 0444, rbd_pool_show, NULL);
+static DEVICE_ATTR(pool_id, 0444, rbd_pool_id_show, NULL);
+static DEVICE_ATTR(name, 0444, rbd_name_show, NULL);
+static DEVICE_ATTR(image_id, 0444, rbd_image_id_show, NULL);
+static DEVICE_ATTR(refresh, 0200, NULL, rbd_image_refresh);
+static DEVICE_ATTR(current_snap, 0444, rbd_snap_show, NULL);
+static DEVICE_ATTR(snap_id, 0444, rbd_snap_id_show, NULL);
+static DEVICE_ATTR(parent, 0444, rbd_parent_show, NULL);
 
 static struct attribute *rbd_attrs[] = {
 	&dev_attr_size.attr,
@@ -5179,8 +5214,10 @@ static int rbd_add_parse_args(const char *buf,
 
 	rbd_opts->read_only = RBD_READ_ONLY_DEFAULT;
 	rbd_opts->queue_depth = RBD_QUEUE_DEPTH_DEFAULT;
+	rbd_opts->lock_timeout = RBD_LOCK_TIMEOUT_DEFAULT;
 	rbd_opts->lock_on_read = RBD_LOCK_ON_READ_DEFAULT;
 	rbd_opts->exclusive = RBD_EXCLUSIVE_DEFAULT;
+	rbd_opts->trim = RBD_TRIM_DEFAULT;
 
 	copts = ceph_parse_options(options, mon_addrs,
 					mon_addrs + mon_addrs_size - 1,
@@ -5216,6 +5253,8 @@ static void rbd_dev_image_unlock(struct rbd_device *rbd_dev)
 
 static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
 {
+	int ret;
+
 	if (!(rbd_dev->header.features & RBD_FEATURE_EXCLUSIVE_LOCK)) {
 		rbd_warn(rbd_dev, "exclusive-lock feature is not enabled");
 		return -EINVAL;
@@ -5223,9 +5262,9 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
 
 	/* FIXME: "rbd map --exclusive" should be in interruptible */
 	down_read(&rbd_dev->lock_rwsem);
-	rbd_wait_state_locked(rbd_dev);
+	ret = rbd_wait_state_locked(rbd_dev, true);
 	up_read(&rbd_dev->lock_rwsem);
-	if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+	if (ret) {
 		rbd_warn(rbd_dev, "failed to acquire exclusive lock");
 		return -EROFS;
 	}
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 34997df132e2..09537bee387f 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -247,19 +247,19 @@ static void rsxx_debugfs_dev_new(struct rsxx_cardinfo *card)
 	if (IS_ERR_OR_NULL(card->debugfs_dir))
 		goto failed_debugfs_dir;
 
-	debugfs_stats = debugfs_create_file("stats", S_IRUGO,
+	debugfs_stats = debugfs_create_file("stats", 0444,
 					    card->debugfs_dir, card,
 					    &debugfs_stats_fops);
 	if (IS_ERR_OR_NULL(debugfs_stats))
 		goto failed_debugfs_stats;
 
-	debugfs_pci_regs = debugfs_create_file("pci_regs", S_IRUGO,
+	debugfs_pci_regs = debugfs_create_file("pci_regs", 0444,
 					       card->debugfs_dir, card,
 					       &debugfs_pci_regs_fops);
 	if (IS_ERR_OR_NULL(debugfs_pci_regs))
 		goto failed_debugfs_pci_regs;
 
-	debugfs_cram = debugfs_create_file("cram", S_IRUGO | S_IWUSR,
+	debugfs_cram = debugfs_create_file("cram", 0644,
 					   card->debugfs_dir, card,
 					   &debugfs_cram_fops);
 	if (IS_ERR_OR_NULL(debugfs_cram))
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 64e066eba72e..0e31884a9519 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -110,7 +110,7 @@ struct iwm {
 /* Select values for swim_select and swim_readbit */
 
 #define READ_DATA_0	0x074
-#define TWOMEG_DRIVE	0x075
+#define ONEMEG_DRIVE	0x075
 #define SINGLE_SIDED	0x076
 #define DRIVE_PRESENT	0x077
 #define DISK_IN		0x170
@@ -118,9 +118,9 @@ struct iwm {
 #define TRACK_ZERO	0x172
 #define TACHO		0x173
 #define READ_DATA_1	0x174
-#define MFM_MODE	0x175
+#define GCR_MODE	0x175
 #define SEEK_COMPLETE	0x176
-#define ONEMEG_MEDIA	0x177
+#define TWOMEG_MEDIA	0x177
 
 /* Bits in handshake register */
 
@@ -612,7 +612,6 @@ static void setup_medium(struct floppy_state *fs)
 		struct floppy_struct *g;
 		fs->disk_in = 1;
 		fs->write_protected = swim_readbit(base, WRITE_PROT);
-		fs->type = swim_readbit(base, ONEMEG_MEDIA);
 
 		if (swim_track00(base))
 			printk(KERN_ERR
@@ -620,6 +619,9 @@ static void setup_medium(struct floppy_state *fs)
 
 		swim_track00(base);
 
+		fs->type = swim_readbit(base, TWOMEG_MEDIA) ?
+			HD_MEDIA : DD_MEDIA;
+		fs->head_number = swim_readbit(base, SINGLE_SIDED) ? 1 : 2;
 		get_floppy_geometry(fs, 0, &g);
 		fs->total_secs = g->size;
 		fs->secpercyl = g->head * g->sect;
@@ -646,7 +648,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 
 	swim_write(base, setup, S_IBM_DRIVE  | S_FCLK_DIV2);
 	udelay(10);
-	swim_drive(base, INTERNAL_DRIVE);
+	swim_drive(base, fs->location);
 	swim_motor(base, ON);
 	swim_action(base, SETMFM);
 	if (fs->ejected)
@@ -656,6 +658,8 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 		goto out;
 	}
 
+	set_capacity(fs->disk, fs->total_secs);
+
 	if (mode & FMODE_NDELAY)
 		return 0;
 
@@ -727,14 +731,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode,
 		if (copy_to_user((void __user *) param, (void *) &floppy_type,
 				 sizeof(struct floppy_struct)))
 			return -EFAULT;
-		break;
-
-	default:
-		printk(KERN_DEBUG "SWIM floppy_ioctl: unknown cmd %d\n",
-		       cmd);
-		return -ENOSYS;
+		return 0;
 	}
-	return 0;
+	return -ENOTTY;
 }
 
 static int floppy_getgeo(struct block_device *bdev, struct hd_geometry *geo)
@@ -795,7 +794,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data)
 	struct swim_priv *swd = data;
 	int drive = (*part & 3);
 
-	if (drive > swd->floppy_count)
+	if (drive >= swd->floppy_count)
 		return NULL;
 
 	*part = 0;
@@ -813,10 +812,9 @@ static int swim_add_floppy(struct swim_priv *swd, enum drive_location location)
 
 	swim_motor(base, OFF);
 
-	if (swim_readbit(base, SINGLE_SIDED))
-		fs->head_number = 1;
-	else
-		fs->head_number = 2;
+	fs->type = HD_MEDIA;
+	fs->head_number = 2;
+
 	fs->ref_count = 0;
 	fs->ejected = 1;
 
@@ -834,10 +832,12 @@ static int swim_floppy_init(struct swim_priv *swd)
 	/* scan floppy drives */
 
 	swim_drive(base, INTERNAL_DRIVE);
-	if (swim_readbit(base, DRIVE_PRESENT))
+	if (swim_readbit(base, DRIVE_PRESENT) &&
+	    !swim_readbit(base, ONEMEG_DRIVE))
 		swim_add_floppy(swd, INTERNAL_DRIVE);
 	swim_drive(base, EXTERNAL_DRIVE);
-	if (swim_readbit(base, DRIVE_PRESENT))
+	if (swim_readbit(base, DRIVE_PRESENT) &&
+	    !swim_readbit(base, ONEMEG_DRIVE))
 		swim_add_floppy(swd, EXTERNAL_DRIVE);
 
 	/* register floppy drives */
@@ -861,7 +861,6 @@ static int swim_floppy_init(struct swim_priv *swd)
 							      &swd->lock);
 		if (!swd->unit[drive].disk->queue) {
 			err = -ENOMEM;
-			put_disk(swd->unit[drive].disk);
 			goto exit_put_disks;
 		}
 		blk_queue_bounce_limit(swd->unit[drive].disk->queue,
@@ -911,7 +910,7 @@ static int swim_probe(struct platform_device *dev)
 		goto out;
 	}
 
-	swim_base = ioremap(res->start, resource_size(res));
+	swim_base = (struct swim __iomem *)res->start;
 	if (!swim_base) {
 		ret = -ENOMEM;
 		goto out_release_io;
@@ -923,7 +922,7 @@ static int swim_probe(struct platform_device *dev)
 	if (!get_swim_mode(swim_base)) {
 		printk(KERN_INFO "SWIM device not found !\n");
 		ret = -ENODEV;
-		goto out_iounmap;
+		goto out_release_io;
 	}
 
 	/* set platform driver data */
@@ -931,7 +930,7 @@ static int swim_probe(struct platform_device *dev)
 	swd = kzalloc(sizeof(struct swim_priv), GFP_KERNEL);
 	if (!swd) {
 		ret = -ENOMEM;
-		goto out_iounmap;
+		goto out_release_io;
 	}
 	platform_set_drvdata(dev, swd);
 
@@ -945,8 +944,6 @@ static int swim_probe(struct platform_device *dev)
 
 out_kfree:
 	kfree(swd);
-out_iounmap:
-	iounmap(swim_base);
 out_release_io:
 	release_mem_region(res->start, resource_size(res));
 out:
@@ -974,8 +971,6 @@ static int swim_remove(struct platform_device *dev)
 	for (drive = 0; drive < swd->floppy_count; drive++)
 		floppy_eject(&swd->unit[drive]);
 
-	iounmap(swd->base);
-
 	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
 	if (res)
 		release_mem_region(res->start, resource_size(res));
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index af51015d056e..469541c1e51e 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -148,7 +148,7 @@ struct swim3 {
 #define MOTOR_ON	2
 #define RELAX		3	/* also eject in progress */
 #define READ_DATA_0	4
-#define TWOMEG_DRIVE	5
+#define ONEMEG_DRIVE	5
 #define SINGLE_SIDED	6	/* drive or diskette is 4MB type? */
 #define DRIVE_PRESENT	7
 #define DISK_IN		8
@@ -156,9 +156,9 @@ struct swim3 {
 #define TRACK_ZERO	10
 #define TACHO		11
 #define READ_DATA_1	12
-#define MFM_MODE	13
+#define GCR_MODE	13
 #define SEEK_COMPLETE	14
-#define ONEMEG_MEDIA	15
+#define TWOMEG_MEDIA	15
 
 /* Definitions of values used in writing and formatting */
 #define DATA_ESCAPE	0x99
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index 08586dc14e85..4d90e5eba2f5 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -567,7 +567,7 @@ static struct carm_request *carm_get_special(struct carm_host *host)
 	if (!crq)
 		return NULL;
 
-	rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, GFP_KERNEL);
+	rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, 0);
 	if (IS_ERR(rq)) {
 		spin_lock_irqsave(&host->lock, flags);
 		carm_put_request(host, crq);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 4a07593c2efd..23752dc99b00 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -298,7 +298,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	struct request *req;
 	int err;
 
-	req = blk_get_request(q, REQ_OP_DRV_IN, GFP_KERNEL);
+	req = blk_get_request(q, REQ_OP_DRV_IN, 0);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -371,7 +371,7 @@ static ssize_t virtblk_serial_show(struct device *dev,
 	return err;
 }
 
-static DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
+static DEVICE_ATTR(serial, 0444, virtblk_serial_show, NULL);
 
 /* The queue's logical block size must be set before calling this */
 static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize)
@@ -576,10 +576,10 @@ virtblk_cache_type_show(struct device *dev, struct device_attribute *attr,
 }
 
 static const struct device_attribute dev_attr_cache_type_ro =
-	__ATTR(cache_type, S_IRUGO,
+	__ATTR(cache_type, 0444,
 	       virtblk_cache_type_show, NULL);
 static const struct device_attribute dev_attr_cache_type_rw =
-	__ATTR(cache_type, S_IRUGO|S_IWUSR,
+	__ATTR(cache_type, 0644,
 	       virtblk_cache_type_show, virtblk_cache_type_store);
 
 static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq,
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 987d665e82de..b55b245e8052 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -98,7 +98,7 @@ MODULE_PARM_DESC(max_queues,
  * backend, 4KB page granularity is used.
  */
 unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER;
-module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
+module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444);
 MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
 /*
  * The LRU mechanism to clean the lists of persistent grants needs to
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 21c1be1eb226..66412eededda 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -367,7 +367,7 @@ int __init xen_blkif_interface_init(void)
 out:									\
 		return sprintf(buf, format, result);			\
 	}								\
-	static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
+	static DEVICE_ATTR(name, 0444, show_##name, NULL)
 
 VBD_SHOW_ALLRING(oo_req,  "%llu\n");
 VBD_SHOW_ALLRING(rd_req,  "%llu\n");
@@ -403,7 +403,7 @@ static const struct attribute_group xen_vbdstat_group = {
 									\
 		return sprintf(buf, format, ##args);			\
 	}								\
-	static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
+	static DEVICE_ATTR(name, 0444, show_##name, NULL)
 
 VBD_SHOW(physical_device, "%x:%x\n", be->major, be->minor);
 VBD_SHOW(mode, "%s\n", be->mode);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 2a8e7813bd1a..ae00a82f350b 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -129,13 +129,12 @@ static const struct block_device_operations xlvbd_block_fops;
  */
 
 static unsigned int xen_blkif_max_segments = 32;
-module_param_named(max_indirect_segments, xen_blkif_max_segments, uint,
-		   S_IRUGO);
+module_param_named(max_indirect_segments, xen_blkif_max_segments, uint, 0444);
 MODULE_PARM_DESC(max_indirect_segments,
 		 "Maximum amount of segments in indirect requests (default is 32)");
 
 static unsigned int xen_blkif_max_queues = 4;
-module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
+module_param_named(max_queues, xen_blkif_max_queues, uint, 0444);
 MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used per virtual disk");
 
 /*
@@ -143,7 +142,7 @@ MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used per v
  * backend, 4KB page granularity is used.
  */
 static unsigned int xen_blkif_max_ring_order;
-module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
+module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444);
 MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
 
 #define BLK_RING_SIZE(info)	\
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index c8c8b0b8d333..b937cc1e2c07 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -231,6 +231,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 },
@@ -263,7 +264,6 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 },
 
 	/* QCA ROME chipset */
-	{ USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME },
@@ -399,6 +399,13 @@ static const struct dmi_system_id btusb_needs_reset_resume_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 3060"),
 		},
 	},
+	{
+		/* Dell XPS 9360 (QCA ROME device 0cf3:e300) */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
+		},
+	},
 	{}
 };
 
@@ -2852,6 +2859,12 @@ static int btusb_config_oob_wake(struct hci_dev *hdev)
 }
 #endif
 
+static void btusb_check_needs_reset_resume(struct usb_interface *intf)
+{
+	if (dmi_check_system(btusb_needs_reset_resume_table))
+		interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
+}
+
 static int btusb_probe(struct usb_interface *intf,
 		       const struct usb_device_id *id)
 {
@@ -2974,9 +2987,6 @@ static int btusb_probe(struct usb_interface *intf,
 	hdev->send   = btusb_send_frame;
 	hdev->notify = btusb_notify;
 
-	if (dmi_check_system(btusb_needs_reset_resume_table))
-		interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
-
 #ifdef CONFIG_PM
 	err = btusb_config_oob_wake(hdev);
 	if (err)
@@ -3064,6 +3074,7 @@ static int btusb_probe(struct usb_interface *intf,
 		data->setup_on_usb = btusb_setup_qca;
 		hdev->set_bdaddr = btusb_set_bdaddr_ath3012;
 		set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks);
+		btusb_check_needs_reset_resume(intf);
 	}
 
 #ifdef CONFIG_BT_HCIBTUSB_RTL
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index d1c0b60e9326..6dc177bf4c42 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -33,6 +33,7 @@ config HISILICON_LPC
 	bool "Support for ISA I/O space on HiSilicon Hip06/7"
 	depends on ARM64 && (ARCH_HISI || COMPILE_TEST)
 	select INDIRECT_PIO
+	select MFD_CORE if ACPI
 	help
 	  Driver to enable I/O access to devices attached to the Low Pin
 	  Count bus on the HiSilicon Hip06/7 SoC.
diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c
index ec35e255b496..8b9c66d7c4ff 100644
--- a/drivers/bus/fsl-mc/fsl-mc-msi.c
+++ b/drivers/bus/fsl-mc/fsl-mc-msi.c
@@ -163,6 +163,8 @@ struct irq_domain *fsl_mc_msi_create_irq_domain(struct fwnode_handle *fwnode,
 {
 	struct irq_domain *domain;
 
+	if (WARN_ON((info->flags & MSI_FLAG_LEVEL_CAPABLE)))
+		info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
 	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
 		fsl_mc_msi_update_dom_ops(info);
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 8327478effd0..9adc8c3eb0fa 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2192,7 +2192,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 
 		len = nr * CD_FRAMESIZE_RAW;
 
-		rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
+		rq = blk_get_request(q, REQ_OP_SCSI_IN, 0);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
 			break;
@@ -2371,7 +2371,7 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi,
 	if (!CDROM_CAN(CDC_SELECT_DISC) || arg == CDSL_CURRENT)
 		return media_changed(cdi, 1);
 
-	if ((unsigned int)arg >= cdi->capacity)
+	if (arg >= cdi->capacity)
 		return -EINVAL;
 
 	info = kmalloc(sizeof(*info), GFP_KERNEL);
diff --git a/drivers/char/agp/uninorth-agp.c b/drivers/char/agp/uninorth-agp.c
index c381c8e396fc..79d8c84693a1 100644
--- a/drivers/char/agp/uninorth-agp.c
+++ b/drivers/char/agp/uninorth-agp.c
@@ -195,7 +195,7 @@ static int uninorth_insert_memory(struct agp_memory *mem, off_t pg_start, int ty
 	return 0;
 }
 
-int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
+static int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
 {
 	size_t i;
 	u32 *gp;
@@ -470,7 +470,7 @@ static int uninorth_free_gatt_table(struct agp_bridge_data *bridge)
 	return 0;
 }
 
-void null_cache_flush(void)
+static void null_cache_flush(void)
 {
 	mb();
 }
diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c
index a5e2f9e557ea..53436c03dbce 100644
--- a/drivers/char/apm-emulation.c
+++ b/drivers/char/apm-emulation.c
@@ -461,19 +461,6 @@ static int proc_apm_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int proc_apm_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_apm_show, NULL);
-}
-
-static const struct file_operations apm_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_apm_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 static int kapmd(void *arg)
@@ -657,7 +644,7 @@ static int __init apm_init(void)
 	wake_up_process(kapmd_tsk);
 
 #ifdef CONFIG_PROC_FS
-	proc_create("apm", 0, NULL, &apm_proc_fops);
+	proc_create_single("apm", 0, NULL, proc_apm_show);
 #endif
 
 	ret = misc_register(&apm_device);
diff --git a/drivers/char/ds1620.c b/drivers/char/ds1620.c
index eb53cbadb68f..a5ecf6dae02e 100644
--- a/drivers/char/ds1620.c
+++ b/drivers/char/ds1620.c
@@ -345,18 +345,6 @@ static int ds1620_proc_therm_show(struct seq_file *m, void *v)
 		   fan_state[netwinder_get_fan()]);
 	return 0;
 }
-
-static int ds1620_proc_therm_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ds1620_proc_therm_show, NULL);
-}
-
-static const struct file_operations ds1620_proc_therm_fops = {
-	.open		= ds1620_proc_therm_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 static const struct file_operations ds1620_fops = {
@@ -404,7 +392,7 @@ static int __init ds1620_init(void)
 		return ret;
 
 #ifdef THERM_USE_PROC
-	if (!proc_create("therm", 0, NULL, &ds1620_proc_therm_fops))
+	if (!proc_create_single("therm", 0, NULL, ds1620_proc_therm_show))
 		printk(KERN_ERR "therm: unable to register /proc/therm\n");
 #endif
 
diff --git a/drivers/char/efirtc.c b/drivers/char/efirtc.c
index dc62568b7dde..d9aab643997e 100644
--- a/drivers/char/efirtc.c
+++ b/drivers/char/efirtc.c
@@ -358,19 +358,6 @@ static int efi_rtc_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int efi_rtc_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, efi_rtc_proc_show, NULL);
-}
-
-static const struct file_operations efi_rtc_proc_fops = {
-	.open		= efi_rtc_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init 
 efi_rtc_init(void)
 {
@@ -386,7 +373,7 @@ efi_rtc_init(void)
 		return ret;
 	}
 
-	dir = proc_create("driver/efirtc", 0, NULL, &efi_rtc_proc_fops);
+	dir = proc_create_single("driver/efirtc", 0, NULL, efi_rtc_proc_show);
 	if (dir == NULL) {
 		printk(KERN_ERR "efirtc: can't create /proc/driver/efirtc.\n");
 		misc_deregister(&efi_rtc_dev);
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index d53541e96bee..c34b257d852d 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -347,6 +347,7 @@ config HW_RANDOM_STM32
 	tristate "STMicroelectronics STM32 random number generator"
 	depends on HW_RANDOM && (ARCH_STM32 || COMPILE_TEST)
 	depends on HAS_IOMEM
+	default HW_RANDOM
 	help
 	  This driver provides kernel-side support for the Random Number
 	  Generator hardware found on STM32 microcontrollers.
diff --git a/drivers/char/hw_random/n2-drv.c b/drivers/char/hw_random/n2-drv.c
index 92dd4e925315..f8411515fe1c 100644
--- a/drivers/char/hw_random/n2-drv.c
+++ b/drivers/char/hw_random/n2-drv.c
@@ -435,7 +435,7 @@ static int n2rng_data_read(struct hwrng *rng, u32 *data)
 			*data = np->test_data & 0xffffffff;
 			len = 4;
 		} else {
-			dev_err(&np->op->dev, "RNG error, restesting\n");
+			dev_err(&np->op->dev, "RNG error, retesting\n");
 			np->flags &= ~N2RNG_FLAG_READY;
 			if (!(np->flags & N2RNG_FLAG_SHUTDOWN))
 				schedule_delayed_work(&np->work, 0);
diff --git a/drivers/char/hw_random/stm32-rng.c b/drivers/char/hw_random/stm32-rng.c
index 0d2328da3b76..042860d97b15 100644
--- a/drivers/char/hw_random/stm32-rng.c
+++ b/drivers/char/hw_random/stm32-rng.c
@@ -187,8 +187,13 @@ static int stm32_rng_runtime_resume(struct device *dev)
 }
 #endif
 
-static UNIVERSAL_DEV_PM_OPS(stm32_rng_pm_ops, stm32_rng_runtime_suspend,
-			    stm32_rng_runtime_resume, NULL);
+static const struct dev_pm_ops stm32_rng_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_rng_runtime_suspend,
+			   stm32_rng_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
 
 static const struct of_device_id stm32_rng_match[] = {
 	{
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index 6e9df558325b..ffe9b0c6c647 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -135,7 +135,7 @@ static int via_rng_init(struct hwrng *rng)
 	 * is always enabled if CPUID rng_en is set.  There is no
 	 * RNG configuration like it used to be the case in this
 	 * register */
-	if ((c->x86 == 6) && (c->x86_model >= 0x0f)) {
+	if (((c->x86 == 6) && (c->x86_model >= 0x0f))  || (c->x86 > 6)){
 		if (!boot_cpu_has(X86_FEATURE_XSTORE_EN)) {
 			pr_err(PFX "can't enable hardware RNG "
 				"if XSTORE is not enabled\n");
diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig
index 3bda116c8aa0..c108441882cc 100644
--- a/drivers/char/ipmi/Kconfig
+++ b/drivers/char/ipmi/Kconfig
@@ -22,14 +22,6 @@ config IPMI_DMI_DECODE
 
 if IPMI_HANDLER
 
-config IPMI_PROC_INTERFACE
-       bool 'Provide an interface for IPMI stats in /proc (deprecated)'
-       depends on PROC_FS
-       default y
-       help
-         Do not use this any more, use sysfs for this info.  It will be
-	 removed in future kernel versions.
-
 config IPMI_PANIC_EVENT
        bool 'Generate a panic event to all BMCs on a panic'
        help
@@ -111,6 +103,21 @@ config ASPEED_KCS_IPMI_BMC
 	  The driver implements the BMC side of the KCS contorller, it
 	  provides the access of KCS IO space for BMC side.
 
+config NPCM7XX_KCS_IPMI_BMC
+	depends on ARCH_NPCM7XX || COMPILE_TEST
+	select IPMI_KCS_BMC
+	select REGMAP_MMIO
+	tristate "NPCM7xx KCS IPMI BMC driver"
+	help
+	  Provides a driver for the KCS (Keyboard Controller Style) IPMI
+	  interface found on Nuvoton NPCM7xx SOCs.
+
+	  The driver implements the BMC side of the KCS contorller, it
+	  provides the access of KCS IO space for BMC side.
+
+	  This support is also available as a module.  If so, the module
+	  will be called kcs_bmc_npcm7xx.
+
 config ASPEED_BT_IPMI_BMC
 	depends on ARCH_ASPEED || COMPILE_TEST
        depends on REGMAP && REGMAP_MMIO && MFD_SYSCON
diff --git a/drivers/char/ipmi/Makefile b/drivers/char/ipmi/Makefile
index 21e9e872d973..7a3baf301a8f 100644
--- a/drivers/char/ipmi/Makefile
+++ b/drivers/char/ipmi/Makefile
@@ -24,3 +24,4 @@ obj-$(CONFIG_IPMI_POWEROFF) += ipmi_poweroff.o
 obj-$(CONFIG_IPMI_KCS_BMC) += kcs_bmc.o
 obj-$(CONFIG_ASPEED_BT_IPMI_BMC) += bt-bmc.o
 obj-$(CONFIG_ASPEED_KCS_IPMI_BMC) += kcs_bmc_aspeed.o
+obj-$(CONFIG_NPCM7XX_KCS_IPMI_BMC) += kcs_bmc_npcm7xx.o
diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c
index fd4ea8d87d4b..a3397664f800 100644
--- a/drivers/char/ipmi/ipmi_bt_sm.c
+++ b/drivers/char/ipmi/ipmi_bt_sm.c
@@ -504,11 +504,12 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time)
 		if (status & BT_H_BUSY)		/* clear a leftover H_BUSY */
 			BT_CONTROL(BT_H_BUSY);
 
+		bt->timeout = bt->BT_CAP_req2rsp;
+
 		/* Read BT capabilities if it hasn't been done yet */
 		if (!bt->BT_CAP_outreqs)
 			BT_STATE_CHANGE(BT_STATE_CAPABILITIES_BEGIN,
 					SI_SM_CALL_WITHOUT_DELAY);
-		bt->timeout = bt->BT_CAP_req2rsp;
 		BT_SI_SM_RETURN(SI_SM_IDLE);
 
 	case BT_STATE_XACTION_START:
diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c
index 8ecfd47806fa..1a486aec99b6 100644
--- a/drivers/char/ipmi/ipmi_devintf.c
+++ b/drivers/char/ipmi/ipmi_devintf.c
@@ -26,7 +26,7 @@
 
 struct ipmi_file_private
 {
-	ipmi_user_t          user;
+	struct ipmi_user     *user;
 	spinlock_t           recv_msg_lock;
 	struct list_head     recv_msgs;
 	struct file          *file;
@@ -37,7 +37,6 @@ struct ipmi_file_private
 	unsigned int         default_retry_time_ms;
 };
 
-static DEFINE_MUTEX(ipmi_mutex);
 static void file_receive_handler(struct ipmi_recv_msg *msg,
 				 void                 *handler_data)
 {
@@ -45,17 +44,15 @@ static void file_receive_handler(struct ipmi_recv_msg *msg,
 	int                      was_empty;
 	unsigned long            flags;
 
-	spin_lock_irqsave(&(priv->recv_msg_lock), flags);
-
-	was_empty = list_empty(&(priv->recv_msgs));
-	list_add_tail(&(msg->link), &(priv->recv_msgs));
+	spin_lock_irqsave(&priv->recv_msg_lock, flags);
+	was_empty = list_empty(&priv->recv_msgs);
+	list_add_tail(&msg->link, &priv->recv_msgs);
+	spin_unlock_irqrestore(&priv->recv_msg_lock, flags);
 
 	if (was_empty) {
 		wake_up_interruptible(&priv->wait);
 		kill_fasync(&priv->fasync_queue, SIGIO, POLL_IN);
 	}
-
-	spin_unlock_irqrestore(&(priv->recv_msg_lock), flags);
 }
 
 static __poll_t ipmi_poll(struct file *file, poll_table *wait)
@@ -68,7 +65,7 @@ static __poll_t ipmi_poll(struct file *file, poll_table *wait)
 
 	spin_lock_irqsave(&priv->recv_msg_lock, flags);
 
-	if (!list_empty(&(priv->recv_msgs)))
+	if (!list_empty(&priv->recv_msgs))
 		mask |= (EPOLLIN | EPOLLRDNORM);
 
 	spin_unlock_irqrestore(&priv->recv_msg_lock, flags);
@@ -79,13 +76,8 @@ static __poll_t ipmi_poll(struct file *file, poll_table *wait)
 static int ipmi_fasync(int fd, struct file *file, int on)
 {
 	struct ipmi_file_private *priv = file->private_data;
-	int                      result;
 
-	mutex_lock(&ipmi_mutex); /* could race against open() otherwise */
-	result = fasync_helper(fd, file, on, &priv->fasync_queue);
-	mutex_unlock(&ipmi_mutex);
-
-	return (result);
+	return fasync_helper(fd, file, on, &priv->fasync_queue);
 }
 
 static const struct ipmi_user_hndl ipmi_hndlrs =
@@ -99,18 +91,16 @@ static int ipmi_open(struct inode *inode, struct file *file)
 	int                      rv;
 	struct ipmi_file_private *priv;
 
-
 	priv = kmalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
-	mutex_lock(&ipmi_mutex);
 	priv->file = file;
 
 	rv = ipmi_create_user(if_num,
 			      &ipmi_hndlrs,
 			      priv,
-			      &(priv->user));
+			      &priv->user);
 	if (rv) {
 		kfree(priv);
 		goto out;
@@ -118,8 +108,8 @@ static int ipmi_open(struct inode *inode, struct file *file)
 
 	file->private_data = priv;
 
-	spin_lock_init(&(priv->recv_msg_lock));
-	INIT_LIST_HEAD(&(priv->recv_msgs));
+	spin_lock_init(&priv->recv_msg_lock);
+	INIT_LIST_HEAD(&priv->recv_msgs);
 	init_waitqueue_head(&priv->wait);
 	priv->fasync_queue = NULL;
 	mutex_init(&priv->recv_mutex);
@@ -129,7 +119,6 @@ static int ipmi_open(struct inode *inode, struct file *file)
 	priv->default_retry_time_ms = 0;
 
 out:
-	mutex_unlock(&ipmi_mutex);
 	return rv;
 }
 
@@ -137,7 +126,7 @@ static int ipmi_release(struct inode *inode, struct file *file)
 {
 	struct ipmi_file_private *priv = file->private_data;
 	int                      rv;
-	struct  ipmi_recv_msg *msg, *next;
+	struct ipmi_recv_msg *msg, *next;
 
 	rv = ipmi_destroy_user(priv->user);
 	if (rv)
@@ -146,13 +135,12 @@ static int ipmi_release(struct inode *inode, struct file *file)
 	list_for_each_entry_safe(msg, next, &priv->recv_msgs, link)
 		ipmi_free_recv_msg(msg);
 
-
 	kfree(priv);
 
 	return 0;
 }
 
-static int handle_send_req(ipmi_user_t     user,
+static int handle_send_req(struct ipmi_user *user,
 			   struct ipmi_req *req,
 			   int             retries,
 			   unsigned int    retry_time_ms)
@@ -189,8 +177,7 @@ static int handle_send_req(ipmi_user_t     user,
 
 		if (copy_from_user(msg.data,
 				   req->msg.data,
-				   req->msg.data_len))
-		{
+				   req->msg.data_len)) {
 			rv = -EFAULT;
 			goto out;
 		}
@@ -233,25 +220,24 @@ static int handle_recv(struct ipmi_file_private *priv,
 	mutex_lock(&priv->recv_mutex);
 
 	/* Grab the message off the list. */
-	spin_lock_irqsave(&(priv->recv_msg_lock), flags);
+	spin_lock_irqsave(&priv->recv_msg_lock, flags);
 	if (list_empty(&(priv->recv_msgs))) {
-		spin_unlock_irqrestore(&(priv->recv_msg_lock), flags);
+		spin_unlock_irqrestore(&priv->recv_msg_lock, flags);
 		rv = -EAGAIN;
 		goto recv_err;
 	}
 	entry = priv->recv_msgs.next;
 	msg = list_entry(entry, struct ipmi_recv_msg, link);
 	list_del(entry);
-	spin_unlock_irqrestore(&(priv->recv_msg_lock), flags);
+	spin_unlock_irqrestore(&priv->recv_msg_lock, flags);
 
 	addr_len = ipmi_addr_length(msg->addr.addr_type);
-	if (rsp->addr_len < addr_len)
-	{
+	if (rsp->addr_len < addr_len) {
 		rv = -EINVAL;
 		goto recv_putback_on_err;
 	}
 
-	if (copy_to_user(rsp->addr, &(msg->addr), addr_len)) {
+	if (copy_to_user(rsp->addr, &msg->addr, addr_len)) {
 		rv = -EFAULT;
 		goto recv_putback_on_err;
 	}
@@ -273,8 +259,7 @@ static int handle_recv(struct ipmi_file_private *priv,
 
 		if (copy_to_user(rsp->msg.data,
 				 msg->msg.data,
-				 msg->msg.data_len))
-		{
+				 msg->msg.data_len)) {
 			rv = -EFAULT;
 			goto recv_putback_on_err;
 		}
@@ -294,9 +279,9 @@ static int handle_recv(struct ipmi_file_private *priv,
 recv_putback_on_err:
 	/* If we got an error, put the message back onto
 	   the head of the queue. */
-	spin_lock_irqsave(&(priv->recv_msg_lock), flags);
-	list_add(entry, &(priv->recv_msgs));
-	spin_unlock_irqrestore(&(priv->recv_msg_lock), flags);
+	spin_lock_irqsave(&priv->recv_msg_lock, flags);
+	list_add(entry, &priv->recv_msgs);
+	spin_unlock_irqrestore(&priv->recv_msg_lock, flags);
 recv_err:
 	mutex_unlock(&priv->recv_mutex);
 	return rv;
@@ -307,9 +292,9 @@ static int copyout_recv(struct ipmi_recv *rsp, void __user *to)
 	return copy_to_user(to, rsp, sizeof(struct ipmi_recv)) ? -EFAULT : 0;
 }
 
-static int ipmi_ioctl(struct file   *file,
-		      unsigned int  cmd,
-		      unsigned long data)
+static long ipmi_ioctl(struct file   *file,
+		       unsigned int  cmd,
+		       unsigned long data)
 {
 	int                      rv = -EINVAL;
 	struct ipmi_file_private *priv = file->private_data;
@@ -320,16 +305,20 @@ static int ipmi_ioctl(struct file   *file,
 	case IPMICTL_SEND_COMMAND:
 	{
 		struct ipmi_req req;
+		int retries;
+		unsigned int retry_time_ms;
 
 		if (copy_from_user(&req, arg, sizeof(req))) {
 			rv = -EFAULT;
 			break;
 		}
 
-		rv = handle_send_req(priv->user,
-				     &req,
-				     priv->default_retries,
-				     priv->default_retry_time_ms);
+		mutex_lock(&priv->recv_mutex);
+		retries = priv->default_retries;
+		retry_time_ms = priv->default_retry_time_ms;
+		mutex_unlock(&priv->recv_mutex);
+
+		rv = handle_send_req(priv->user, &req, retries, retry_time_ms);
 		break;
 	}
 
@@ -569,8 +558,10 @@ static int ipmi_ioctl(struct file   *file,
 			break;
 		}
 
+		mutex_lock(&priv->recv_mutex);
 		priv->default_retries = parms.retries;
 		priv->default_retry_time_ms = parms.retry_time_ms;
+		mutex_unlock(&priv->recv_mutex);
 		rv = 0;
 		break;
 	}
@@ -579,8 +570,10 @@ static int ipmi_ioctl(struct file   *file,
 	{
 		struct ipmi_timing_parms parms;
 
+		mutex_lock(&priv->recv_mutex);
 		parms.retries = priv->default_retries;
 		parms.retry_time_ms = priv->default_retry_time_ms;
+		mutex_unlock(&priv->recv_mutex);
 
 		if (copy_to_user(arg, &parms, sizeof(parms))) {
 			rv = -EFAULT;
@@ -615,30 +608,16 @@ static int ipmi_ioctl(struct file   *file,
 		rv = ipmi_set_maintenance_mode(priv->user, mode);
 		break;
 	}
+
+	default:
+		rv = -ENOTTY;
+		break;
 	}
   
 	return rv;
 }
 
-/*
- * Note: it doesn't make sense to take the BKL here but
- *       not in compat_ipmi_ioctl. -arnd
- */
-static long ipmi_unlocked_ioctl(struct file   *file,
-			        unsigned int  cmd,
-			        unsigned long data)
-{
-	int ret;
-
-	mutex_lock(&ipmi_mutex);
-	ret = ipmi_ioctl(file, cmd, data);
-	mutex_unlock(&ipmi_mutex);
-
-	return ret;
-}
-
 #ifdef CONFIG_COMPAT
-
 /*
  * The following code contains code for supporting 32-bit compatible
  * ioctls on 64-bit kernels.  This allows running 32-bit apps on the
@@ -749,15 +728,21 @@ static long compat_ipmi_ioctl(struct file *filep, unsigned int cmd,
 	{
 		struct ipmi_req	rp;
 		struct compat_ipmi_req r32;
+		int retries;
+		unsigned int retry_time_ms;
 
 		if (copy_from_user(&r32, compat_ptr(arg), sizeof(r32)))
 			return -EFAULT;
 
 		get_compat_ipmi_req(&rp, &r32);
 
+		mutex_lock(&priv->recv_mutex);
+		retries = priv->default_retries;
+		retry_time_ms = priv->default_retry_time_ms;
+		mutex_unlock(&priv->recv_mutex);
+
 		return handle_send_req(priv->user, &rp,
-				priv->default_retries,
-				priv->default_retry_time_ms);
+				       retries, retry_time_ms);
 	}
 	case COMPAT_IPMICTL_SEND_COMMAND_SETTIME:
 	{
@@ -791,25 +776,13 @@ static long compat_ipmi_ioctl(struct file *filep, unsigned int cmd,
 		return ipmi_ioctl(filep, cmd, arg);
 	}
 }
-
-static long unlocked_compat_ipmi_ioctl(struct file *filep, unsigned int cmd,
-				       unsigned long arg)
-{
-	int ret;
-
-	mutex_lock(&ipmi_mutex);
-	ret = compat_ipmi_ioctl(filep, cmd, arg);
-	mutex_unlock(&ipmi_mutex);
-
-	return ret;
-}
 #endif
 
 static const struct file_operations ipmi_fops = {
 	.owner		= THIS_MODULE,
-	.unlocked_ioctl	= ipmi_unlocked_ioctl,
+	.unlocked_ioctl	= ipmi_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl   = unlocked_compat_ipmi_ioctl,
+	.compat_ioctl   = compat_ipmi_ioctl,
 #endif
 	.open		= ipmi_open,
 	.release	= ipmi_release,
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 361148938801..51832b8a2c62 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -37,11 +37,30 @@
 static struct ipmi_recv_msg *ipmi_alloc_recv_msg(void);
 static int ipmi_init_msghandler(void);
 static void smi_recv_tasklet(unsigned long);
-static void handle_new_recv_msgs(ipmi_smi_t intf);
-static void need_waiter(ipmi_smi_t intf);
-static int handle_one_recv_msg(ipmi_smi_t          intf,
+static void handle_new_recv_msgs(struct ipmi_smi *intf);
+static void need_waiter(struct ipmi_smi *intf);
+static int handle_one_recv_msg(struct ipmi_smi *intf,
 			       struct ipmi_smi_msg *msg);
 
+#ifdef DEBUG
+static void ipmi_debug_msg(const char *title, unsigned char *data,
+			   unsigned int len)
+{
+	int i, pos;
+	char buf[100];
+
+	pos = snprintf(buf, sizeof(buf), "%s: ", title);
+	for (i = 0; i < len; i++)
+		pos += snprintf(buf + pos, sizeof(buf) - pos,
+				" %2.2x", data[i]);
+	pr_debug("%s\n", buf);
+}
+#else
+static void ipmi_debug_msg(const char *title, unsigned char *data,
+			   unsigned int len)
+{ }
+#endif
+
 static int initialized;
 
 enum ipmi_panic_event_op {
@@ -112,14 +131,13 @@ module_param_cb(panic_op, &panic_op_ops, NULL, 0600);
 MODULE_PARM_DESC(panic_op, "Sets if the IPMI driver will attempt to store panic information in the event log in the event of a panic.  Set to 'none' for no, 'event' for a single event, or 'string' for a generic event and the panic string in IPMI OEM events.");
 
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-static struct proc_dir_entry *proc_ipmi_root;
-#endif /* CONFIG_IPMI_PROC_INTERFACE */
+#define MAX_EVENTS_IN_QUEUE	25
 
 /* Remain in auto-maintenance mode for this amount of time (in ms). */
-#define IPMI_MAINTENANCE_MODE_TIMEOUT 30000
-
-#define MAX_EVENTS_IN_QUEUE	25
+static unsigned long maintenance_mode_timeout_ms = 30000;
+module_param(maintenance_mode_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(maintenance_mode_timeout_ms,
+		 "The time (milliseconds) after the last maintenance message that the connection stays in maintenance mode.");
 
 /*
  * Don't let a message sit in a queue forever, always time it with at lest
@@ -127,6 +145,31 @@ static struct proc_dir_entry *proc_ipmi_root;
  */
 #define MAX_MSG_TIMEOUT		60000
 
+/*
+ * Timeout times below are in milliseconds, and are done off a 1
+ * second timer.  So setting the value to 1000 would mean anything
+ * between 0 and 1000ms.  So really the only reasonable minimum
+ * setting it 2000ms, which is between 1 and 2 seconds.
+ */
+
+/* The default timeout for message retries. */
+static unsigned long default_retry_ms = 2000;
+module_param(default_retry_ms, ulong, 0644);
+MODULE_PARM_DESC(default_retry_ms,
+		 "The time (milliseconds) between retry sends");
+
+/* The default timeout for maintenance mode message retries. */
+static unsigned long default_maintenance_retry_ms = 3000;
+module_param(default_maintenance_retry_ms, ulong, 0644);
+MODULE_PARM_DESC(default_maintenance_retry_ms,
+		 "The time (milliseconds) between retry sends in maintenance mode");
+
+/* The default maximum number of retries */
+static unsigned int default_max_retries = 4;
+module_param(default_max_retries, uint, 0644);
+MODULE_PARM_DESC(default_max_retries,
+		 "The time (milliseconds) between retry sends in maintenance mode");
+
 /* Call every ~1000 ms. */
 #define IPMI_TIMEOUT_TIME	1000
 
@@ -150,8 +193,12 @@ static struct proc_dir_entry *proc_ipmi_root;
 struct ipmi_user {
 	struct list_head link;
 
-	/* Set to false when the user is destroyed. */
-	bool valid;
+	/*
+	 * Set to NULL when the user is destroyed, a pointer to myself
+	 * so srcu_dereference can be used on it.
+	 */
+	struct ipmi_user *self;
+	struct srcu_struct release_barrier;
 
 	struct kref refcount;
 
@@ -160,16 +207,33 @@ struct ipmi_user {
 	void             *handler_data;
 
 	/* The interface this user is bound to. */
-	ipmi_smi_t intf;
+	struct ipmi_smi *intf;
 
 	/* Does this interface receive IPMI events? */
 	bool gets_events;
 };
 
+static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
+	__acquires(user->release_barrier)
+{
+	struct ipmi_user *ruser;
+
+	*index = srcu_read_lock(&user->release_barrier);
+	ruser = srcu_dereference(user->self, &user->release_barrier);
+	if (!ruser)
+		srcu_read_unlock(&user->release_barrier, *index);
+	return ruser;
+}
+
+static void release_ipmi_user(struct ipmi_user *user, int index)
+{
+	srcu_read_unlock(&user->release_barrier, index);
+}
+
 struct cmd_rcvr {
 	struct list_head link;
 
-	ipmi_user_t   user;
+	struct ipmi_user *user;
 	unsigned char netfn;
 	unsigned char cmd;
 	unsigned int  chans;
@@ -247,13 +311,6 @@ struct ipmi_my_addrinfo {
 	unsigned char lun;
 };
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-struct ipmi_proc_entry {
-	char                   *name;
-	struct ipmi_proc_entry *next;
-};
-#endif
-
 /*
  * Note that the product id, manufacturer id, guid, and device id are
  * immutable in this structure, so dyn_mutex is not required for
@@ -275,7 +332,7 @@ struct bmc_device {
 };
 #define to_bmc_device(x) container_of((x), struct bmc_device, pdev.dev)
 
-static int bmc_get_device_id(ipmi_smi_t intf, struct bmc_device *bmc,
+static int bmc_get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc,
 			     struct ipmi_device_id *id,
 			     bool *guid_set, guid_t *guid);
 
@@ -397,10 +454,11 @@ struct ipmi_smi {
 	struct list_head link;
 
 	/*
-	 * The list of upper layers that are using me.  seq_lock
-	 * protects this.
+	 * The list of upper layers that are using me.  seq_lock write
+	 * protects this.  Read protection is with srcu.
 	 */
 	struct list_head users;
+	struct srcu_struct users_srcu;
 
 	/* Used for wake ups at startup. */
 	wait_queue_head_t waitq;
@@ -420,24 +478,9 @@ struct ipmi_smi {
 	bool in_bmc_register;  /* Handle recursive situations.  Yuck. */
 	struct work_struct bmc_reg_work;
 
-	/*
-	 * This is the lower-layer's sender routine.  Note that you
-	 * must either be holding the ipmi_interfaces_mutex or be in
-	 * an umpreemptible region to use this.  You must fetch the
-	 * value into a local variable and make sure it is not NULL.
-	 */
 	const struct ipmi_smi_handlers *handlers;
 	void                     *send_info;
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	/* A list of proc entries for this interface. */
-	struct mutex           proc_entry_lock;
-	struct ipmi_proc_entry *proc_entries;
-
-	struct proc_dir_entry *proc_dir;
-	char                  proc_dir_name[10];
-#endif
-
 	/* Driver-model device for the system interface. */
 	struct device          *si_dev;
 
@@ -503,6 +546,13 @@ struct ipmi_smi {
 	spinlock_t maintenance_mode_lock; /* Used in a timer... */
 
 	/*
+	 * If we are doing maintenance on something on IPMB, extend
+	 * the timeout time to avoid timeouts writing firmware and
+	 * such.
+	 */
+	int ipmb_maintenance_mode_timeout;
+
+	/*
 	 * A cheap hack, if this is non-null and a message to an
 	 * interface comes in with a NULL user, call this routine with
 	 * it.  Note that the message will still be freed by the
@@ -510,7 +560,8 @@ struct ipmi_smi {
 	 *
 	 * Protected by bmc_reg_mutex.
 	 */
-	void (*null_user_handler)(ipmi_smi_t intf, struct ipmi_recv_msg *msg);
+	void (*null_user_handler)(struct ipmi_smi *intf,
+				  struct ipmi_recv_msg *msg);
 
 	/*
 	 * When we are scanning the channels for an SMI, this will
@@ -536,12 +587,12 @@ struct ipmi_smi {
 };
 #define to_si_intf_from_dev(device) container_of(device, struct ipmi_smi, dev)
 
-static void __get_guid(ipmi_smi_t intf);
-static void __ipmi_bmc_unregister(ipmi_smi_t intf);
-static int __ipmi_bmc_register(ipmi_smi_t intf,
+static void __get_guid(struct ipmi_smi *intf);
+static void __ipmi_bmc_unregister(struct ipmi_smi *intf);
+static int __ipmi_bmc_register(struct ipmi_smi *intf,
 			       struct ipmi_device_id *id,
 			       bool guid_set, guid_t *guid, int intf_num);
-static int __scan_channels(ipmi_smi_t intf, struct ipmi_device_id *id);
+static int __scan_channels(struct ipmi_smi *intf, struct ipmi_device_id *id);
 
 
 /**
@@ -560,6 +611,7 @@ static DEFINE_MUTEX(ipmidriver_mutex);
 
 static LIST_HEAD(ipmi_interfaces);
 static DEFINE_MUTEX(ipmi_interfaces_mutex);
+DEFINE_STATIC_SRCU(ipmi_interfaces_srcu);
 
 /*
  * List of watchers that want to know when smi's are added and deleted.
@@ -620,7 +672,7 @@ static void free_smi_msg_list(struct list_head *q)
 	}
 }
 
-static void clean_up_interface_data(ipmi_smi_t intf)
+static void clean_up_interface_data(struct ipmi_smi *intf)
 {
 	int              i;
 	struct cmd_rcvr  *rcvr, *rcvr2;
@@ -652,7 +704,7 @@ static void clean_up_interface_data(ipmi_smi_t intf)
 
 static void intf_free(struct kref *ref)
 {
-	ipmi_smi_t intf = container_of(ref, struct ipmi_smi, refcount);
+	struct ipmi_smi *intf = container_of(ref, struct ipmi_smi, refcount);
 
 	clean_up_interface_data(intf);
 	kfree(intf);
@@ -660,65 +712,39 @@ static void intf_free(struct kref *ref)
 
 struct watcher_entry {
 	int              intf_num;
-	ipmi_smi_t       intf;
+	struct ipmi_smi  *intf;
 	struct list_head link;
 };
 
 int ipmi_smi_watcher_register(struct ipmi_smi_watcher *watcher)
 {
-	ipmi_smi_t intf;
-	LIST_HEAD(to_deliver);
-	struct watcher_entry *e, *e2;
+	struct ipmi_smi *intf;
+	int index;
 
 	mutex_lock(&smi_watchers_mutex);
 
-	mutex_lock(&ipmi_interfaces_mutex);
-
-	/* Build a list of things to deliver. */
-	list_for_each_entry(intf, &ipmi_interfaces, link) {
-		if (intf->intf_num == -1)
-			continue;
-		e = kmalloc(sizeof(*e), GFP_KERNEL);
-		if (!e)
-			goto out_err;
-		kref_get(&intf->refcount);
-		e->intf = intf;
-		e->intf_num = intf->intf_num;
-		list_add_tail(&e->link, &to_deliver);
-	}
-
-	/* We will succeed, so add it to the list. */
 	list_add(&watcher->link, &smi_watchers);
 
-	mutex_unlock(&ipmi_interfaces_mutex);
+	index = srcu_read_lock(&ipmi_interfaces_srcu);
+	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
+		int intf_num = READ_ONCE(intf->intf_num);
 
-	list_for_each_entry_safe(e, e2, &to_deliver, link) {
-		list_del(&e->link);
-		watcher->new_smi(e->intf_num, e->intf->si_dev);
-		kref_put(&e->intf->refcount, intf_free);
-		kfree(e);
+		if (intf_num == -1)
+			continue;
+		watcher->new_smi(intf_num, intf->si_dev);
 	}
+	srcu_read_unlock(&ipmi_interfaces_srcu, index);
 
 	mutex_unlock(&smi_watchers_mutex);
 
 	return 0;
-
- out_err:
-	mutex_unlock(&ipmi_interfaces_mutex);
-	mutex_unlock(&smi_watchers_mutex);
-	list_for_each_entry_safe(e, e2, &to_deliver, link) {
-		list_del(&e->link);
-		kref_put(&e->intf->refcount, intf_free);
-		kfree(e);
-	}
-	return -ENOMEM;
 }
 EXPORT_SYMBOL(ipmi_smi_watcher_register);
 
 int ipmi_smi_watcher_unregister(struct ipmi_smi_watcher *watcher)
 {
 	mutex_lock(&smi_watchers_mutex);
-	list_del(&(watcher->link));
+	list_del(&watcher->link);
 	mutex_unlock(&smi_watchers_mutex);
 	return 0;
 }
@@ -732,12 +758,14 @@ call_smi_watchers(int i, struct device *dev)
 {
 	struct ipmi_smi_watcher *w;
 
+	mutex_lock(&smi_watchers_mutex);
 	list_for_each_entry(w, &smi_watchers, link) {
 		if (try_module_get(w->owner)) {
 			w->new_smi(i, dev);
 			module_put(w->owner);
 		}
 	}
+	mutex_unlock(&smi_watchers_mutex);
 }
 
 static int
@@ -831,18 +859,17 @@ unsigned int ipmi_addr_length(int addr_type)
 }
 EXPORT_SYMBOL(ipmi_addr_length);
 
-static void deliver_response(struct ipmi_recv_msg *msg)
+static int deliver_response(struct ipmi_smi *intf, struct ipmi_recv_msg *msg)
 {
-	if (!msg->user) {
-		ipmi_smi_t    intf = msg->user_msg_data;
+	int rv = 0;
 
+	if (!msg->user) {
 		/* Special handling for NULL users. */
 		if (intf->null_user_handler) {
 			intf->null_user_handler(intf, msg);
-			ipmi_inc_stat(intf, handled_local_responses);
 		} else {
 			/* No handler, so give up. */
-			ipmi_inc_stat(intf, unhandled_local_responses);
+			rv = -EINVAL;
 		}
 		ipmi_free_recv_msg(msg);
 	} else if (!oops_in_progress) {
@@ -851,21 +878,40 @@ static void deliver_response(struct ipmi_recv_msg *msg)
 		 * receive handler doesn't much meaning and has a deadlock
 		 * risk.  At this moment, simply skip it in that case.
 		 */
+		int index;
+		struct ipmi_user *user = acquire_ipmi_user(msg->user, &index);
 
-		ipmi_user_t user = msg->user;
-		user->handler->ipmi_recv_hndl(msg, user->handler_data);
+		if (user) {
+			user->handler->ipmi_recv_hndl(msg, user->handler_data);
+			release_ipmi_user(msg->user, index);
+		} else {
+			/* User went away, give up. */
+			ipmi_free_recv_msg(msg);
+			rv = -EINVAL;
+		}
 	}
+
+	return rv;
 }
 
-static void
-deliver_err_response(struct ipmi_recv_msg *msg, int err)
+static void deliver_local_response(struct ipmi_smi *intf,
+				   struct ipmi_recv_msg *msg)
+{
+	if (deliver_response(intf, msg))
+		ipmi_inc_stat(intf, unhandled_local_responses);
+	else
+		ipmi_inc_stat(intf, handled_local_responses);
+}
+
+static void deliver_err_response(struct ipmi_smi *intf,
+				 struct ipmi_recv_msg *msg, int err)
 {
 	msg->recv_type = IPMI_RESPONSE_RECV_TYPE;
 	msg->msg_data[0] = err;
 	msg->msg.netfn |= 1; /* Convert to a response. */
 	msg->msg.data_len = 1;
 	msg->msg.data = msg->msg_data;
-	deliver_response(msg);
+	deliver_local_response(intf, msg);
 }
 
 /*
@@ -873,7 +919,7 @@ deliver_err_response(struct ipmi_recv_msg *msg, int err)
  * message with the given timeout to the sequence table.  This must be
  * called with the interface's seq_lock held.
  */
-static int intf_next_seq(ipmi_smi_t           intf,
+static int intf_next_seq(struct ipmi_smi      *intf,
 			 struct ipmi_recv_msg *recv_msg,
 			 unsigned long        timeout,
 			 int                  retries,
@@ -884,6 +930,11 @@ static int intf_next_seq(ipmi_smi_t           intf,
 	int          rv = 0;
 	unsigned int i;
 
+	if (timeout == 0)
+		timeout = default_retry_ms;
+	if (retries < 0)
+		retries = default_max_retries;
+
 	for (i = intf->curr_seq; (i+1)%IPMI_IPMB_NUM_SEQ != intf->curr_seq;
 					i = (i+1)%IPMI_IPMB_NUM_SEQ) {
 		if (!intf->seq_table[i].inuse)
@@ -921,7 +972,7 @@ static int intf_next_seq(ipmi_smi_t           intf,
  * guard against message coming in after their timeout and the
  * sequence number being reused).
  */
-static int intf_find_seq(ipmi_smi_t           intf,
+static int intf_find_seq(struct ipmi_smi      *intf,
 			 unsigned char        seq,
 			 short                channel,
 			 unsigned char        cmd,
@@ -935,26 +986,26 @@ static int intf_find_seq(ipmi_smi_t           intf,
 	if (seq >= IPMI_IPMB_NUM_SEQ)
 		return -EINVAL;
 
-	spin_lock_irqsave(&(intf->seq_lock), flags);
+	spin_lock_irqsave(&intf->seq_lock, flags);
 	if (intf->seq_table[seq].inuse) {
 		struct ipmi_recv_msg *msg = intf->seq_table[seq].recv_msg;
 
 		if ((msg->addr.channel == channel) && (msg->msg.cmd == cmd)
 				&& (msg->msg.netfn == netfn)
-				&& (ipmi_addr_equal(addr, &(msg->addr)))) {
+				&& (ipmi_addr_equal(addr, &msg->addr))) {
 			*recv_msg = msg;
 			intf->seq_table[seq].inuse = 0;
 			rv = 0;
 		}
 	}
-	spin_unlock_irqrestore(&(intf->seq_lock), flags);
+	spin_unlock_irqrestore(&intf->seq_lock, flags);
 
 	return rv;
 }
 
 
 /* Start the timer for a specific sequence table entry. */
-static int intf_start_seq_timer(ipmi_smi_t intf,
+static int intf_start_seq_timer(struct ipmi_smi *intf,
 				long       msgid)
 {
 	int           rv = -ENODEV;
@@ -965,24 +1016,24 @@ static int intf_start_seq_timer(ipmi_smi_t intf,
 
 	GET_SEQ_FROM_MSGID(msgid, seq, seqid);
 
-	spin_lock_irqsave(&(intf->seq_lock), flags);
+	spin_lock_irqsave(&intf->seq_lock, flags);
 	/*
 	 * We do this verification because the user can be deleted
 	 * while a message is outstanding.
 	 */
 	if ((intf->seq_table[seq].inuse)
 				&& (intf->seq_table[seq].seqid == seqid)) {
-		struct seq_table *ent = &(intf->seq_table[seq]);
+		struct seq_table *ent = &intf->seq_table[seq];
 		ent->timeout = ent->orig_timeout;
 		rv = 0;
 	}
-	spin_unlock_irqrestore(&(intf->seq_lock), flags);
+	spin_unlock_irqrestore(&intf->seq_lock, flags);
 
 	return rv;
 }
 
 /* Got an error for the send message for a specific sequence number. */
-static int intf_err_seq(ipmi_smi_t   intf,
+static int intf_err_seq(struct ipmi_smi *intf,
 			long         msgid,
 			unsigned int err)
 {
@@ -995,23 +1046,23 @@ static int intf_err_seq(ipmi_smi_t   intf,
 
 	GET_SEQ_FROM_MSGID(msgid, seq, seqid);
 
-	spin_lock_irqsave(&(intf->seq_lock), flags);
+	spin_lock_irqsave(&intf->seq_lock, flags);
 	/*
 	 * We do this verification because the user can be deleted
 	 * while a message is outstanding.
 	 */
 	if ((intf->seq_table[seq].inuse)
 				&& (intf->seq_table[seq].seqid == seqid)) {
-		struct seq_table *ent = &(intf->seq_table[seq]);
+		struct seq_table *ent = &intf->seq_table[seq];
 
 		ent->inuse = 0;
 		msg = ent->recv_msg;
 		rv = 0;
 	}
-	spin_unlock_irqrestore(&(intf->seq_lock), flags);
+	spin_unlock_irqrestore(&intf->seq_lock, flags);
 
 	if (msg)
-		deliver_err_response(msg, err);
+		deliver_err_response(intf, msg, err);
 
 	return rv;
 }
@@ -1020,12 +1071,12 @@ static int intf_err_seq(ipmi_smi_t   intf,
 int ipmi_create_user(unsigned int          if_num,
 		     const struct ipmi_user_hndl *handler,
 		     void                  *handler_data,
-		     ipmi_user_t           *user)
+		     struct ipmi_user      **user)
 {
 	unsigned long flags;
-	ipmi_user_t   new_user;
-	int           rv = 0;
-	ipmi_smi_t    intf;
+	struct ipmi_user *new_user;
+	int           rv = 0, index;
+	struct ipmi_smi *intf;
 
 	/*
 	 * There is no module usecount here, because it's not
@@ -1059,7 +1110,7 @@ int ipmi_create_user(unsigned int          if_num,
 	if (!new_user)
 		return -ENOMEM;
 
-	mutex_lock(&ipmi_interfaces_mutex);
+	index = srcu_read_lock(&ipmi_interfaces_srcu);
 	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
 		if (intf->intf_num == if_num)
 			goto found;
@@ -1069,6 +1120,10 @@ int ipmi_create_user(unsigned int          if_num,
 	goto out_kfree;
 
  found:
+	rv = init_srcu_struct(&new_user->release_barrier);
+	if (rv)
+		goto out_kfree;
+
 	/* Note that each existing user holds a refcount to the interface. */
 	kref_get(&intf->refcount);
 
@@ -1078,26 +1133,7 @@ int ipmi_create_user(unsigned int          if_num,
 	new_user->intf = intf;
 	new_user->gets_events = false;
 
-	if (!try_module_get(intf->handlers->owner)) {
-		rv = -ENODEV;
-		goto out_kref;
-	}
-
-	if (intf->handlers->inc_usecount) {
-		rv = intf->handlers->inc_usecount(intf->send_info);
-		if (rv) {
-			module_put(intf->handlers->owner);
-			goto out_kref;
-		}
-	}
-
-	/*
-	 * Hold the lock so intf->handlers is guaranteed to be good
-	 * until now
-	 */
-	mutex_unlock(&ipmi_interfaces_mutex);
-
-	new_user->valid = true;
+	rcu_assign_pointer(new_user->self, new_user);
 	spin_lock_irqsave(&intf->seq_lock, flags);
 	list_add_rcu(&new_user->link, &intf->users);
 	spin_unlock_irqrestore(&intf->seq_lock, flags);
@@ -1106,13 +1142,12 @@ int ipmi_create_user(unsigned int          if_num,
 		if (atomic_inc_return(&intf->event_waiters) == 1)
 			need_waiter(intf);
 	}
+	srcu_read_unlock(&ipmi_interfaces_srcu, index);
 	*user = new_user;
 	return 0;
 
-out_kref:
-	kref_put(&intf->refcount, intf_free);
 out_kfree:
-	mutex_unlock(&ipmi_interfaces_mutex);
+	srcu_read_unlock(&ipmi_interfaces_srcu, index);
 	kfree(new_user);
 	return rv;
 }
@@ -1120,26 +1155,25 @@ EXPORT_SYMBOL(ipmi_create_user);
 
 int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data)
 {
-	int           rv = 0;
-	ipmi_smi_t    intf;
-	const struct ipmi_smi_handlers *handlers;
+	int rv, index;
+	struct ipmi_smi *intf;
 
-	mutex_lock(&ipmi_interfaces_mutex);
+	index = srcu_read_lock(&ipmi_interfaces_srcu);
 	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
 		if (intf->intf_num == if_num)
 			goto found;
 	}
+	srcu_read_unlock(&ipmi_interfaces_srcu, index);
+
 	/* Not found, return an error */
-	rv = -EINVAL;
-	mutex_unlock(&ipmi_interfaces_mutex);
-	return rv;
+	return -EINVAL;
 
 found:
-	handlers = intf->handlers;
-	rv = -ENOSYS;
-	if (handlers->get_smi_info)
-		rv = handlers->get_smi_info(intf->send_info, data);
-	mutex_unlock(&ipmi_interfaces_mutex);
+	if (!intf->handlers->get_smi_info)
+		rv = -ENOTTY;
+	else
+		rv = intf->handlers->get_smi_info(intf->send_info, data);
+	srcu_read_unlock(&ipmi_interfaces_srcu, index);
 
 	return rv;
 }
@@ -1147,19 +1181,34 @@ EXPORT_SYMBOL(ipmi_get_smi_info);
 
 static void free_user(struct kref *ref)
 {
-	ipmi_user_t user = container_of(ref, struct ipmi_user, refcount);
+	struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
 	kfree(user);
 }
 
-int ipmi_destroy_user(ipmi_user_t user)
+static void _ipmi_destroy_user(struct ipmi_user *user)
 {
-	ipmi_smi_t       intf = user->intf;
+	struct ipmi_smi  *intf = user->intf;
 	int              i;
 	unsigned long    flags;
 	struct cmd_rcvr  *rcvr;
 	struct cmd_rcvr  *rcvrs = NULL;
 
-	user->valid = false;
+	if (!acquire_ipmi_user(user, &i)) {
+		/*
+		 * The user has already been cleaned up, just make sure
+		 * nothing is using it and return.
+		 */
+		synchronize_srcu(&user->release_barrier);
+		return;
+	}
+
+	rcu_assign_pointer(user->self, NULL);
+	release_ipmi_user(user, i);
+
+	synchronize_srcu(&user->release_barrier);
+
+	if (user->handler->shutdown)
+		user->handler->shutdown(user->handler_data);
 
 	if (user->handler->ipmi_watchdog_pretimeout)
 		atomic_dec(&intf->event_waiters);
@@ -1184,7 +1233,7 @@ int ipmi_destroy_user(ipmi_user_t user)
 	 * Remove the user from the command receiver's table.  First
 	 * we build a list of everything (not using the standard link,
 	 * since other things may be using it till we do
-	 * synchronize_rcu()) then free everything in that list.
+	 * synchronize_srcu()) then free everything in that list.
 	 */
 	mutex_lock(&intf->cmd_rcvrs_mutex);
 	list_for_each_entry_rcu(rcvr, &intf->cmd_rcvrs, link) {
@@ -1202,109 +1251,156 @@ int ipmi_destroy_user(ipmi_user_t user)
 		kfree(rcvr);
 	}
 
-	mutex_lock(&ipmi_interfaces_mutex);
-	if (intf->handlers) {
-		module_put(intf->handlers->owner);
-		if (intf->handlers->dec_usecount)
-			intf->handlers->dec_usecount(intf->send_info);
-	}
-	mutex_unlock(&ipmi_interfaces_mutex);
-
 	kref_put(&intf->refcount, intf_free);
+}
 
+int ipmi_destroy_user(struct ipmi_user *user)
+{
+	_ipmi_destroy_user(user);
+
+	cleanup_srcu_struct(&user->release_barrier);
 	kref_put(&user->refcount, free_user);
 
 	return 0;
 }
 EXPORT_SYMBOL(ipmi_destroy_user);
 
-int ipmi_get_version(ipmi_user_t   user,
+int ipmi_get_version(struct ipmi_user *user,
 		     unsigned char *major,
 		     unsigned char *minor)
 {
 	struct ipmi_device_id id;
-	int rv;
+	int rv, index;
 
-	rv = bmc_get_device_id(user->intf, NULL, &id, NULL, NULL);
-	if (rv)
-		return rv;
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
 
-	*major = ipmi_version_major(&id);
-	*minor = ipmi_version_minor(&id);
+	rv = bmc_get_device_id(user->intf, NULL, &id, NULL, NULL);
+	if (!rv) {
+		*major = ipmi_version_major(&id);
+		*minor = ipmi_version_minor(&id);
+	}
+	release_ipmi_user(user, index);
 
-	return 0;
+	return rv;
 }
 EXPORT_SYMBOL(ipmi_get_version);
 
-int ipmi_set_my_address(ipmi_user_t   user,
+int ipmi_set_my_address(struct ipmi_user *user,
 			unsigned int  channel,
 			unsigned char address)
 {
+	int index, rv = 0;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
+
 	if (channel >= IPMI_MAX_CHANNELS)
-		return -EINVAL;
-	user->intf->addrinfo[channel].address = address;
-	return 0;
+		rv = -EINVAL;
+	else
+		user->intf->addrinfo[channel].address = address;
+	release_ipmi_user(user, index);
+
+	return rv;
 }
 EXPORT_SYMBOL(ipmi_set_my_address);
 
-int ipmi_get_my_address(ipmi_user_t   user,
+int ipmi_get_my_address(struct ipmi_user *user,
 			unsigned int  channel,
 			unsigned char *address)
 {
+	int index, rv = 0;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
+
 	if (channel >= IPMI_MAX_CHANNELS)
-		return -EINVAL;
-	*address = user->intf->addrinfo[channel].address;
-	return 0;
+		rv = -EINVAL;
+	else
+		*address = user->intf->addrinfo[channel].address;
+	release_ipmi_user(user, index);
+
+	return rv;
 }
 EXPORT_SYMBOL(ipmi_get_my_address);
 
-int ipmi_set_my_LUN(ipmi_user_t   user,
+int ipmi_set_my_LUN(struct ipmi_user *user,
 		    unsigned int  channel,
 		    unsigned char LUN)
 {
+	int index, rv = 0;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
+
 	if (channel >= IPMI_MAX_CHANNELS)
-		return -EINVAL;
-	user->intf->addrinfo[channel].lun = LUN & 0x3;
+		rv = -EINVAL;
+	else
+		user->intf->addrinfo[channel].lun = LUN & 0x3;
+	release_ipmi_user(user, index);
+
 	return 0;
 }
 EXPORT_SYMBOL(ipmi_set_my_LUN);
 
-int ipmi_get_my_LUN(ipmi_user_t   user,
+int ipmi_get_my_LUN(struct ipmi_user *user,
 		    unsigned int  channel,
 		    unsigned char *address)
 {
+	int index, rv = 0;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
+
 	if (channel >= IPMI_MAX_CHANNELS)
-		return -EINVAL;
-	*address = user->intf->addrinfo[channel].lun;
-	return 0;
+		rv = -EINVAL;
+	else
+		*address = user->intf->addrinfo[channel].lun;
+	release_ipmi_user(user, index);
+
+	return rv;
 }
 EXPORT_SYMBOL(ipmi_get_my_LUN);
 
-int ipmi_get_maintenance_mode(ipmi_user_t user)
+int ipmi_get_maintenance_mode(struct ipmi_user *user)
 {
-	int           mode;
+	int mode, index;
 	unsigned long flags;
 
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
+
 	spin_lock_irqsave(&user->intf->maintenance_mode_lock, flags);
 	mode = user->intf->maintenance_mode;
 	spin_unlock_irqrestore(&user->intf->maintenance_mode_lock, flags);
+	release_ipmi_user(user, index);
 
 	return mode;
 }
 EXPORT_SYMBOL(ipmi_get_maintenance_mode);
 
-static void maintenance_mode_update(ipmi_smi_t intf)
+static void maintenance_mode_update(struct ipmi_smi *intf)
 {
 	if (intf->handlers->set_maintenance_mode)
 		intf->handlers->set_maintenance_mode(
 			intf->send_info, intf->maintenance_mode_enable);
 }
 
-int ipmi_set_maintenance_mode(ipmi_user_t user, int mode)
+int ipmi_set_maintenance_mode(struct ipmi_user *user, int mode)
 {
-	int           rv = 0;
+	int rv = 0, index;
 	unsigned long flags;
-	ipmi_smi_t    intf = user->intf;
+	struct ipmi_smi *intf = user->intf;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
 
 	spin_lock_irqsave(&intf->maintenance_mode_lock, flags);
 	if (intf->maintenance_mode != mode) {
@@ -1332,17 +1428,23 @@ int ipmi_set_maintenance_mode(ipmi_user_t user, int mode)
 	}
  out_unlock:
 	spin_unlock_irqrestore(&intf->maintenance_mode_lock, flags);
+	release_ipmi_user(user, index);
 
 	return rv;
 }
 EXPORT_SYMBOL(ipmi_set_maintenance_mode);
 
-int ipmi_set_gets_events(ipmi_user_t user, bool val)
+int ipmi_set_gets_events(struct ipmi_user *user, bool val)
 {
 	unsigned long        flags;
-	ipmi_smi_t           intf = user->intf;
+	struct ipmi_smi      *intf = user->intf;
 	struct ipmi_recv_msg *msg, *msg2;
 	struct list_head     msgs;
+	int index;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
 
 	INIT_LIST_HEAD(&msgs);
 
@@ -1383,7 +1485,7 @@ int ipmi_set_gets_events(ipmi_user_t user, bool val)
 		list_for_each_entry_safe(msg, msg2, &msgs, link) {
 			msg->user = user;
 			kref_get(&user->refcount);
-			deliver_response(msg);
+			deliver_local_response(intf, msg);
 		}
 
 		spin_lock_irqsave(&intf->events_lock, flags);
@@ -1392,12 +1494,13 @@ int ipmi_set_gets_events(ipmi_user_t user, bool val)
 
  out:
 	spin_unlock_irqrestore(&intf->events_lock, flags);
+	release_ipmi_user(user, index);
 
 	return 0;
 }
 EXPORT_SYMBOL(ipmi_set_gets_events);
 
-static struct cmd_rcvr *find_cmd_rcvr(ipmi_smi_t    intf,
+static struct cmd_rcvr *find_cmd_rcvr(struct ipmi_smi *intf,
 				      unsigned char netfn,
 				      unsigned char cmd,
 				      unsigned char chan)
@@ -1412,7 +1515,7 @@ static struct cmd_rcvr *find_cmd_rcvr(ipmi_smi_t    intf,
 	return NULL;
 }
 
-static int is_cmd_rcvr_exclusive(ipmi_smi_t    intf,
+static int is_cmd_rcvr_exclusive(struct ipmi_smi *intf,
 				 unsigned char netfn,
 				 unsigned char cmd,
 				 unsigned int  chans)
@@ -1427,19 +1530,24 @@ static int is_cmd_rcvr_exclusive(ipmi_smi_t    intf,
 	return 1;
 }
 
-int ipmi_register_for_cmd(ipmi_user_t   user,
+int ipmi_register_for_cmd(struct ipmi_user *user,
 			  unsigned char netfn,
 			  unsigned char cmd,
 			  unsigned int  chans)
 {
-	ipmi_smi_t      intf = user->intf;
+	struct ipmi_smi *intf = user->intf;
 	struct cmd_rcvr *rcvr;
-	int             rv = 0;
+	int rv = 0, index;
 
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
 
 	rcvr = kmalloc(sizeof(*rcvr), GFP_KERNEL);
-	if (!rcvr)
-		return -ENOMEM;
+	if (!rcvr) {
+		rv = -ENOMEM;
+		goto out_release;
+	}
 	rcvr->cmd = cmd;
 	rcvr->netfn = netfn;
 	rcvr->chans = chans;
@@ -1457,24 +1565,30 @@ int ipmi_register_for_cmd(ipmi_user_t   user,
 
 	list_add_rcu(&rcvr->link, &intf->cmd_rcvrs);
 
- out_unlock:
+out_unlock:
 	mutex_unlock(&intf->cmd_rcvrs_mutex);
 	if (rv)
 		kfree(rcvr);
+out_release:
+	release_ipmi_user(user, index);
 
 	return rv;
 }
 EXPORT_SYMBOL(ipmi_register_for_cmd);
 
-int ipmi_unregister_for_cmd(ipmi_user_t   user,
+int ipmi_unregister_for_cmd(struct ipmi_user *user,
 			    unsigned char netfn,
 			    unsigned char cmd,
 			    unsigned int  chans)
 {
-	ipmi_smi_t      intf = user->intf;
+	struct ipmi_smi *intf = user->intf;
 	struct cmd_rcvr *rcvr;
 	struct cmd_rcvr *rcvrs = NULL;
-	int i, rv = -ENOENT;
+	int i, rv = -ENOENT, index;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
 
 	mutex_lock(&intf->cmd_rcvrs_mutex);
 	for (i = 0; i < IPMI_NUM_CHANNELS; i++) {
@@ -1495,12 +1609,14 @@ int ipmi_unregister_for_cmd(ipmi_user_t   user,
 	}
 	mutex_unlock(&intf->cmd_rcvrs_mutex);
 	synchronize_rcu();
+	release_ipmi_user(user, index);
 	while (rcvrs) {
 		atomic_dec(&intf->event_waiters);
 		rcvr = rcvrs;
 		rcvrs = rcvr->next;
 		kfree(rcvr);
 	}
+
 	return rv;
 }
 EXPORT_SYMBOL(ipmi_unregister_for_cmd);
@@ -1535,21 +1651,19 @@ static inline void format_ipmb_msg(struct ipmi_smi_msg   *smi_msg,
 		smi_msg->data[3] = 0;
 	smi_msg->data[i+3] = ipmb_addr->slave_addr;
 	smi_msg->data[i+4] = (msg->netfn << 2) | (ipmb_addr->lun & 0x3);
-	smi_msg->data[i+5] = ipmb_checksum(&(smi_msg->data[i+3]), 2);
+	smi_msg->data[i+5] = ipmb_checksum(&smi_msg->data[i + 3], 2);
 	smi_msg->data[i+6] = source_address;
 	smi_msg->data[i+7] = (ipmb_seq << 2) | source_lun;
 	smi_msg->data[i+8] = msg->cmd;
 
 	/* Now tack on the data to the message. */
 	if (msg->data_len > 0)
-		memcpy(&(smi_msg->data[i+9]), msg->data,
-		       msg->data_len);
+		memcpy(&smi_msg->data[i + 9], msg->data, msg->data_len);
 	smi_msg->data_size = msg->data_len + 9;
 
 	/* Now calculate the checksum and tack it on. */
 	smi_msg->data[i+smi_msg->data_size]
-		= ipmb_checksum(&(smi_msg->data[i+6]),
-				smi_msg->data_size-6);
+		= ipmb_checksum(&smi_msg->data[i + 6], smi_msg->data_size - 6);
 
 	/*
 	 * Add on the checksum size and the offset from the
@@ -1574,21 +1688,19 @@ static inline void format_lan_msg(struct ipmi_smi_msg   *smi_msg,
 	smi_msg->data[3] = lan_addr->session_handle;
 	smi_msg->data[4] = lan_addr->remote_SWID;
 	smi_msg->data[5] = (msg->netfn << 2) | (lan_addr->lun & 0x3);
-	smi_msg->data[6] = ipmb_checksum(&(smi_msg->data[4]), 2);
+	smi_msg->data[6] = ipmb_checksum(&smi_msg->data[4], 2);
 	smi_msg->data[7] = lan_addr->local_SWID;
 	smi_msg->data[8] = (ipmb_seq << 2) | source_lun;
 	smi_msg->data[9] = msg->cmd;
 
 	/* Now tack on the data to the message. */
 	if (msg->data_len > 0)
-		memcpy(&(smi_msg->data[10]), msg->data,
-		       msg->data_len);
+		memcpy(&smi_msg->data[10], msg->data, msg->data_len);
 	smi_msg->data_size = msg->data_len + 10;
 
 	/* Now calculate the checksum and tack it on. */
 	smi_msg->data[smi_msg->data_size]
-		= ipmb_checksum(&(smi_msg->data[7]),
-				smi_msg->data_size-7);
+		= ipmb_checksum(&smi_msg->data[7], smi_msg->data_size - 7);
 
 	/*
 	 * Add on the checksum size and the offset from the
@@ -1599,7 +1711,7 @@ static inline void format_lan_msg(struct ipmi_smi_msg   *smi_msg,
 	smi_msg->msgid = msgid;
 }
 
-static struct ipmi_smi_msg *smi_add_send_msg(ipmi_smi_t intf,
+static struct ipmi_smi_msg *smi_add_send_msg(struct ipmi_smi *intf,
 					     struct ipmi_smi_msg *smi_msg,
 					     int priority)
 {
@@ -1617,7 +1729,8 @@ static struct ipmi_smi_msg *smi_add_send_msg(ipmi_smi_t intf,
 }
 
 
-static void smi_send(ipmi_smi_t intf, const struct ipmi_smi_handlers *handlers,
+static void smi_send(struct ipmi_smi *intf,
+		     const struct ipmi_smi_handlers *handlers,
 		     struct ipmi_smi_msg *smi_msg, int priority)
 {
 	int run_to_completion = intf->run_to_completion;
@@ -1636,405 +1749,435 @@ static void smi_send(ipmi_smi_t intf, const struct ipmi_smi_handlers *handlers,
 		handlers->sender(intf->send_info, smi_msg);
 }
 
-/*
- * Separate from ipmi_request so that the user does not have to be
- * supplied in certain circumstances (mainly at panic time).  If
- * messages are supplied, they will be freed, even if an error
- * occurs.
- */
-static int i_ipmi_request(ipmi_user_t          user,
-			  ipmi_smi_t           intf,
-			  struct ipmi_addr     *addr,
-			  long                 msgid,
-			  struct kernel_ipmi_msg *msg,
-			  void                 *user_msg_data,
-			  void                 *supplied_smi,
-			  struct ipmi_recv_msg *supplied_recv,
-			  int                  priority,
-			  unsigned char        source_address,
-			  unsigned char        source_lun,
-			  int                  retries,
-			  unsigned int         retry_time_ms)
+static bool is_maintenance_mode_cmd(struct kernel_ipmi_msg *msg)
 {
-	int                      rv = 0;
-	struct ipmi_smi_msg      *smi_msg;
-	struct ipmi_recv_msg     *recv_msg;
-	unsigned long            flags;
+	return (((msg->netfn == IPMI_NETFN_APP_REQUEST)
+		 && ((msg->cmd == IPMI_COLD_RESET_CMD)
+		     || (msg->cmd == IPMI_WARM_RESET_CMD)))
+		|| (msg->netfn == IPMI_NETFN_FIRMWARE_REQUEST));
+}
 
+static int i_ipmi_req_sysintf(struct ipmi_smi        *intf,
+			      struct ipmi_addr       *addr,
+			      long                   msgid,
+			      struct kernel_ipmi_msg *msg,
+			      struct ipmi_smi_msg    *smi_msg,
+			      struct ipmi_recv_msg   *recv_msg,
+			      int                    retries,
+			      unsigned int           retry_time_ms)
+{
+	struct ipmi_system_interface_addr *smi_addr;
 
-	if (supplied_recv)
-		recv_msg = supplied_recv;
-	else {
-		recv_msg = ipmi_alloc_recv_msg();
-		if (recv_msg == NULL)
-			return -ENOMEM;
-	}
-	recv_msg->user_msg_data = user_msg_data;
+	if (msg->netfn & 1)
+		/* Responses are not allowed to the SMI. */
+		return -EINVAL;
 
-	if (supplied_smi)
-		smi_msg = (struct ipmi_smi_msg *) supplied_smi;
-	else {
-		smi_msg = ipmi_alloc_smi_msg();
-		if (smi_msg == NULL) {
-			ipmi_free_recv_msg(recv_msg);
-			return -ENOMEM;
-		}
+	smi_addr = (struct ipmi_system_interface_addr *) addr;
+	if (smi_addr->lun > 3) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EINVAL;
 	}
 
-	rcu_read_lock();
-	if (intf->in_shutdown) {
-		rv = -ENODEV;
-		goto out_err;
-	}
+	memcpy(&recv_msg->addr, smi_addr, sizeof(*smi_addr));
 
-	recv_msg->user = user;
-	if (user)
-		kref_get(&user->refcount);
-	recv_msg->msgid = msgid;
-	/*
-	 * Store the message to send in the receive message so timeout
-	 * responses can get the proper response data.
-	 */
-	recv_msg->msg = *msg;
+	if ((msg->netfn == IPMI_NETFN_APP_REQUEST)
+	    && ((msg->cmd == IPMI_SEND_MSG_CMD)
+		|| (msg->cmd == IPMI_GET_MSG_CMD)
+		|| (msg->cmd == IPMI_READ_EVENT_MSG_BUFFER_CMD))) {
+		/*
+		 * We don't let the user do these, since we manage
+		 * the sequence numbers.
+		 */
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EINVAL;
+	}
 
-	if (addr->addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE) {
-		struct ipmi_system_interface_addr *smi_addr;
+	if (is_maintenance_mode_cmd(msg)) {
+		unsigned long flags;
 
-		if (msg->netfn & 1) {
-			/* Responses are not allowed to the SMI. */
-			rv = -EINVAL;
-			goto out_err;
+		spin_lock_irqsave(&intf->maintenance_mode_lock, flags);
+		intf->auto_maintenance_timeout
+			= maintenance_mode_timeout_ms;
+		if (!intf->maintenance_mode
+		    && !intf->maintenance_mode_enable) {
+			intf->maintenance_mode_enable = true;
+			maintenance_mode_update(intf);
 		}
+		spin_unlock_irqrestore(&intf->maintenance_mode_lock,
+				       flags);
+	}
 
-		smi_addr = (struct ipmi_system_interface_addr *) addr;
-		if (smi_addr->lun > 3) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EINVAL;
-			goto out_err;
-		}
+	if (msg->data_len + 2 > IPMI_MAX_MSG_LENGTH) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EMSGSIZE;
+	}
 
-		memcpy(&recv_msg->addr, smi_addr, sizeof(*smi_addr));
+	smi_msg->data[0] = (msg->netfn << 2) | (smi_addr->lun & 0x3);
+	smi_msg->data[1] = msg->cmd;
+	smi_msg->msgid = msgid;
+	smi_msg->user_data = recv_msg;
+	if (msg->data_len > 0)
+		memcpy(&smi_msg->data[2], msg->data, msg->data_len);
+	smi_msg->data_size = msg->data_len + 2;
+	ipmi_inc_stat(intf, sent_local_commands);
 
-		if ((msg->netfn == IPMI_NETFN_APP_REQUEST)
-		    && ((msg->cmd == IPMI_SEND_MSG_CMD)
-			|| (msg->cmd == IPMI_GET_MSG_CMD)
-			|| (msg->cmd == IPMI_READ_EVENT_MSG_BUFFER_CMD))) {
-			/*
-			 * We don't let the user do these, since we manage
-			 * the sequence numbers.
-			 */
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EINVAL;
-			goto out_err;
-		}
+	return 0;
+}
 
-		if (((msg->netfn == IPMI_NETFN_APP_REQUEST)
-		      && ((msg->cmd == IPMI_COLD_RESET_CMD)
-			  || (msg->cmd == IPMI_WARM_RESET_CMD)))
-		     || (msg->netfn == IPMI_NETFN_FIRMWARE_REQUEST)) {
-			spin_lock_irqsave(&intf->maintenance_mode_lock, flags);
-			intf->auto_maintenance_timeout
-				= IPMI_MAINTENANCE_MODE_TIMEOUT;
-			if (!intf->maintenance_mode
-			    && !intf->maintenance_mode_enable) {
-				intf->maintenance_mode_enable = true;
-				maintenance_mode_update(intf);
-			}
-			spin_unlock_irqrestore(&intf->maintenance_mode_lock,
-					       flags);
-		}
+static int i_ipmi_req_ipmb(struct ipmi_smi        *intf,
+			   struct ipmi_addr       *addr,
+			   long                   msgid,
+			   struct kernel_ipmi_msg *msg,
+			   struct ipmi_smi_msg    *smi_msg,
+			   struct ipmi_recv_msg   *recv_msg,
+			   unsigned char          source_address,
+			   unsigned char          source_lun,
+			   int                    retries,
+			   unsigned int           retry_time_ms)
+{
+	struct ipmi_ipmb_addr *ipmb_addr;
+	unsigned char ipmb_seq;
+	long seqid;
+	int broadcast = 0;
+	struct ipmi_channel *chans;
+	int rv = 0;
 
-		if ((msg->data_len + 2) > IPMI_MAX_MSG_LENGTH) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EMSGSIZE;
-			goto out_err;
-		}
+	if (addr->channel >= IPMI_MAX_CHANNELS) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EINVAL;
+	}
 
-		smi_msg->data[0] = (msg->netfn << 2) | (smi_addr->lun & 0x3);
-		smi_msg->data[1] = msg->cmd;
-		smi_msg->msgid = msgid;
-		smi_msg->user_data = recv_msg;
-		if (msg->data_len > 0)
-			memcpy(&(smi_msg->data[2]), msg->data, msg->data_len);
-		smi_msg->data_size = msg->data_len + 2;
-		ipmi_inc_stat(intf, sent_local_commands);
-	} else if (is_ipmb_addr(addr) || is_ipmb_bcast_addr(addr)) {
-		struct ipmi_ipmb_addr *ipmb_addr;
-		unsigned char         ipmb_seq;
-		long                  seqid;
-		int                   broadcast = 0;
-		struct ipmi_channel   *chans;
+	chans = READ_ONCE(intf->channel_list)->c;
 
-		if (addr->channel >= IPMI_MAX_CHANNELS) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EINVAL;
-			goto out_err;
-		}
+	if (chans[addr->channel].medium != IPMI_CHANNEL_MEDIUM_IPMB) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EINVAL;
+	}
 
-		chans = READ_ONCE(intf->channel_list)->c;
+	if (addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE) {
+		/*
+		 * Broadcasts add a zero at the beginning of the
+		 * message, but otherwise is the same as an IPMB
+		 * address.
+		 */
+		addr->addr_type = IPMI_IPMB_ADDR_TYPE;
+		broadcast = 1;
+		retries = 0; /* Don't retry broadcasts. */
+	}
 
-		if (chans[addr->channel].medium != IPMI_CHANNEL_MEDIUM_IPMB) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EINVAL;
-			goto out_err;
-		}
+	/*
+	 * 9 for the header and 1 for the checksum, plus
+	 * possibly one for the broadcast.
+	 */
+	if ((msg->data_len + 10 + broadcast) > IPMI_MAX_MSG_LENGTH) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EMSGSIZE;
+	}
 
-		if (retries < 0) {
-		    if (addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE)
-			retries = 0; /* Don't retry broadcasts. */
-		    else
-			retries = 4;
-		}
-		if (addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE) {
-		    /*
-		     * Broadcasts add a zero at the beginning of the
-		     * message, but otherwise is the same as an IPMB
-		     * address.
-		     */
-		    addr->addr_type = IPMI_IPMB_ADDR_TYPE;
-		    broadcast = 1;
-		}
+	ipmb_addr = (struct ipmi_ipmb_addr *) addr;
+	if (ipmb_addr->lun > 3) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EINVAL;
+	}
 
+	memcpy(&recv_msg->addr, ipmb_addr, sizeof(*ipmb_addr));
 
-		/* Default to 1 second retries. */
-		if (retry_time_ms == 0)
-		    retry_time_ms = 1000;
+	if (recv_msg->msg.netfn & 0x1) {
+		/*
+		 * It's a response, so use the user's sequence
+		 * from msgid.
+		 */
+		ipmi_inc_stat(intf, sent_ipmb_responses);
+		format_ipmb_msg(smi_msg, msg, ipmb_addr, msgid,
+				msgid, broadcast,
+				source_address, source_lun);
 
 		/*
-		 * 9 for the header and 1 for the checksum, plus
-		 * possibly one for the broadcast.
+		 * Save the receive message so we can use it
+		 * to deliver the response.
 		 */
-		if ((msg->data_len + 10 + broadcast) > IPMI_MAX_MSG_LENGTH) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EMSGSIZE;
-			goto out_err;
-		}
+		smi_msg->user_data = recv_msg;
+	} else {
+		/* It's a command, so get a sequence for it. */
+		unsigned long flags;
 
-		ipmb_addr = (struct ipmi_ipmb_addr *) addr;
-		if (ipmb_addr->lun > 3) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EINVAL;
-			goto out_err;
-		}
+		spin_lock_irqsave(&intf->seq_lock, flags);
 
-		memcpy(&recv_msg->addr, ipmb_addr, sizeof(*ipmb_addr));
+		if (is_maintenance_mode_cmd(msg))
+			intf->ipmb_maintenance_mode_timeout =
+				maintenance_mode_timeout_ms;
 
-		if (recv_msg->msg.netfn & 0x1) {
-			/*
-			 * It's a response, so use the user's sequence
-			 * from msgid.
-			 */
-			ipmi_inc_stat(intf, sent_ipmb_responses);
-			format_ipmb_msg(smi_msg, msg, ipmb_addr, msgid,
-					msgid, broadcast,
-					source_address, source_lun);
+		if (intf->ipmb_maintenance_mode_timeout && retry_time_ms == 0)
+			/* Different default in maintenance mode */
+			retry_time_ms = default_maintenance_retry_ms;
 
+		/*
+		 * Create a sequence number with a 1 second
+		 * timeout and 4 retries.
+		 */
+		rv = intf_next_seq(intf,
+				   recv_msg,
+				   retry_time_ms,
+				   retries,
+				   broadcast,
+				   &ipmb_seq,
+				   &seqid);
+		if (rv)
 			/*
-			 * Save the receive message so we can use it
-			 * to deliver the response.
+			 * We have used up all the sequence numbers,
+			 * probably, so abort.
 			 */
-			smi_msg->user_data = recv_msg;
-		} else {
-			/* It's a command, so get a sequence for it. */
+			goto out_err;
 
-			spin_lock_irqsave(&(intf->seq_lock), flags);
+		ipmi_inc_stat(intf, sent_ipmb_commands);
 
-			/*
-			 * Create a sequence number with a 1 second
-			 * timeout and 4 retries.
-			 */
-			rv = intf_next_seq(intf,
-					   recv_msg,
-					   retry_time_ms,
-					   retries,
-					   broadcast,
-					   &ipmb_seq,
-					   &seqid);
-			if (rv) {
-				/*
-				 * We have used up all the sequence numbers,
-				 * probably, so abort.
-				 */
-				spin_unlock_irqrestore(&(intf->seq_lock),
-						       flags);
-				goto out_err;
-			}
+		/*
+		 * Store the sequence number in the message,
+		 * so that when the send message response
+		 * comes back we can start the timer.
+		 */
+		format_ipmb_msg(smi_msg, msg, ipmb_addr,
+				STORE_SEQ_IN_MSGID(ipmb_seq, seqid),
+				ipmb_seq, broadcast,
+				source_address, source_lun);
 
-			ipmi_inc_stat(intf, sent_ipmb_commands);
+		/*
+		 * Copy the message into the recv message data, so we
+		 * can retransmit it later if necessary.
+		 */
+		memcpy(recv_msg->msg_data, smi_msg->data,
+		       smi_msg->data_size);
+		recv_msg->msg.data = recv_msg->msg_data;
+		recv_msg->msg.data_len = smi_msg->data_size;
 
-			/*
-			 * Store the sequence number in the message,
-			 * so that when the send message response
-			 * comes back we can start the timer.
-			 */
-			format_ipmb_msg(smi_msg, msg, ipmb_addr,
-					STORE_SEQ_IN_MSGID(ipmb_seq, seqid),
-					ipmb_seq, broadcast,
-					source_address, source_lun);
+		/*
+		 * We don't unlock until here, because we need
+		 * to copy the completed message into the
+		 * recv_msg before we release the lock.
+		 * Otherwise, race conditions may bite us.  I
+		 * know that's pretty paranoid, but I prefer
+		 * to be correct.
+		 */
+out_err:
+		spin_unlock_irqrestore(&intf->seq_lock, flags);
+	}
 
-			/*
-			 * Copy the message into the recv message data, so we
-			 * can retransmit it later if necessary.
-			 */
-			memcpy(recv_msg->msg_data, smi_msg->data,
-			       smi_msg->data_size);
-			recv_msg->msg.data = recv_msg->msg_data;
-			recv_msg->msg.data_len = smi_msg->data_size;
+	return rv;
+}
 
-			/*
-			 * We don't unlock until here, because we need
-			 * to copy the completed message into the
-			 * recv_msg before we release the lock.
-			 * Otherwise, race conditions may bite us.  I
-			 * know that's pretty paranoid, but I prefer
-			 * to be correct.
-			 */
-			spin_unlock_irqrestore(&(intf->seq_lock), flags);
-		}
-	} else if (is_lan_addr(addr)) {
-		struct ipmi_lan_addr  *lan_addr;
-		unsigned char         ipmb_seq;
-		long                  seqid;
-		struct ipmi_channel   *chans;
+static int i_ipmi_req_lan(struct ipmi_smi        *intf,
+			  struct ipmi_addr       *addr,
+			  long                   msgid,
+			  struct kernel_ipmi_msg *msg,
+			  struct ipmi_smi_msg    *smi_msg,
+			  struct ipmi_recv_msg   *recv_msg,
+			  unsigned char          source_lun,
+			  int                    retries,
+			  unsigned int           retry_time_ms)
+{
+	struct ipmi_lan_addr  *lan_addr;
+	unsigned char ipmb_seq;
+	long seqid;
+	struct ipmi_channel *chans;
+	int rv = 0;
 
-		if (addr->channel >= IPMI_MAX_CHANNELS) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EINVAL;
-			goto out_err;
-		}
+	if (addr->channel >= IPMI_MAX_CHANNELS) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EINVAL;
+	}
 
-		chans = READ_ONCE(intf->channel_list)->c;
+	chans = READ_ONCE(intf->channel_list)->c;
 
-		if ((chans[addr->channel].medium
+	if ((chans[addr->channel].medium
 				!= IPMI_CHANNEL_MEDIUM_8023LAN)
-		    && (chans[addr->channel].medium
-				!= IPMI_CHANNEL_MEDIUM_ASYNC)) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EINVAL;
-			goto out_err;
-		}
+			&& (chans[addr->channel].medium
+			    != IPMI_CHANNEL_MEDIUM_ASYNC)) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EINVAL;
+	}
 
-		retries = 4;
+	/* 11 for the header and 1 for the checksum. */
+	if ((msg->data_len + 12) > IPMI_MAX_MSG_LENGTH) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EMSGSIZE;
+	}
 
-		/* Default to 1 second retries. */
-		if (retry_time_ms == 0)
-		    retry_time_ms = 1000;
+	lan_addr = (struct ipmi_lan_addr *) addr;
+	if (lan_addr->lun > 3) {
+		ipmi_inc_stat(intf, sent_invalid_commands);
+		return -EINVAL;
+	}
 
-		/* 11 for the header and 1 for the checksum. */
-		if ((msg->data_len + 12) > IPMI_MAX_MSG_LENGTH) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EMSGSIZE;
-			goto out_err;
-		}
+	memcpy(&recv_msg->addr, lan_addr, sizeof(*lan_addr));
 
-		lan_addr = (struct ipmi_lan_addr *) addr;
-		if (lan_addr->lun > 3) {
-			ipmi_inc_stat(intf, sent_invalid_commands);
-			rv = -EINVAL;
-			goto out_err;
-		}
+	if (recv_msg->msg.netfn & 0x1) {
+		/*
+		 * It's a response, so use the user's sequence
+		 * from msgid.
+		 */
+		ipmi_inc_stat(intf, sent_lan_responses);
+		format_lan_msg(smi_msg, msg, lan_addr, msgid,
+			       msgid, source_lun);
 
-		memcpy(&recv_msg->addr, lan_addr, sizeof(*lan_addr));
+		/*
+		 * Save the receive message so we can use it
+		 * to deliver the response.
+		 */
+		smi_msg->user_data = recv_msg;
+	} else {
+		/* It's a command, so get a sequence for it. */
+		unsigned long flags;
 
-		if (recv_msg->msg.netfn & 0x1) {
-			/*
-			 * It's a response, so use the user's sequence
-			 * from msgid.
-			 */
-			ipmi_inc_stat(intf, sent_lan_responses);
-			format_lan_msg(smi_msg, msg, lan_addr, msgid,
-				       msgid, source_lun);
+		spin_lock_irqsave(&intf->seq_lock, flags);
 
+		/*
+		 * Create a sequence number with a 1 second
+		 * timeout and 4 retries.
+		 */
+		rv = intf_next_seq(intf,
+				   recv_msg,
+				   retry_time_ms,
+				   retries,
+				   0,
+				   &ipmb_seq,
+				   &seqid);
+		if (rv)
 			/*
-			 * Save the receive message so we can use it
-			 * to deliver the response.
+			 * We have used up all the sequence numbers,
+			 * probably, so abort.
 			 */
-			smi_msg->user_data = recv_msg;
-		} else {
-			/* It's a command, so get a sequence for it. */
+			goto out_err;
 
-			spin_lock_irqsave(&(intf->seq_lock), flags);
+		ipmi_inc_stat(intf, sent_lan_commands);
 
-			/*
-			 * Create a sequence number with a 1 second
-			 * timeout and 4 retries.
-			 */
-			rv = intf_next_seq(intf,
-					   recv_msg,
-					   retry_time_ms,
-					   retries,
-					   0,
-					   &ipmb_seq,
-					   &seqid);
-			if (rv) {
-				/*
-				 * We have used up all the sequence numbers,
-				 * probably, so abort.
-				 */
-				spin_unlock_irqrestore(&(intf->seq_lock),
-						       flags);
-				goto out_err;
-			}
+		/*
+		 * Store the sequence number in the message,
+		 * so that when the send message response
+		 * comes back we can start the timer.
+		 */
+		format_lan_msg(smi_msg, msg, lan_addr,
+			       STORE_SEQ_IN_MSGID(ipmb_seq, seqid),
+			       ipmb_seq, source_lun);
 
-			ipmi_inc_stat(intf, sent_lan_commands);
+		/*
+		 * Copy the message into the recv message data, so we
+		 * can retransmit it later if necessary.
+		 */
+		memcpy(recv_msg->msg_data, smi_msg->data,
+		       smi_msg->data_size);
+		recv_msg->msg.data = recv_msg->msg_data;
+		recv_msg->msg.data_len = smi_msg->data_size;
 
-			/*
-			 * Store the sequence number in the message,
-			 * so that when the send message response
-			 * comes back we can start the timer.
-			 */
-			format_lan_msg(smi_msg, msg, lan_addr,
-				       STORE_SEQ_IN_MSGID(ipmb_seq, seqid),
-				       ipmb_seq, source_lun);
+		/*
+		 * We don't unlock until here, because we need
+		 * to copy the completed message into the
+		 * recv_msg before we release the lock.
+		 * Otherwise, race conditions may bite us.  I
+		 * know that's pretty paranoid, but I prefer
+		 * to be correct.
+		 */
+out_err:
+		spin_unlock_irqrestore(&intf->seq_lock, flags);
+	}
 
-			/*
-			 * Copy the message into the recv message data, so we
-			 * can retransmit it later if necessary.
-			 */
-			memcpy(recv_msg->msg_data, smi_msg->data,
-			       smi_msg->data_size);
-			recv_msg->msg.data = recv_msg->msg_data;
-			recv_msg->msg.data_len = smi_msg->data_size;
+	return rv;
+}
 
-			/*
-			 * We don't unlock until here, because we need
-			 * to copy the completed message into the
-			 * recv_msg before we release the lock.
-			 * Otherwise, race conditions may bite us.  I
-			 * know that's pretty paranoid, but I prefer
-			 * to be correct.
-			 */
-			spin_unlock_irqrestore(&(intf->seq_lock), flags);
+/*
+ * Separate from ipmi_request so that the user does not have to be
+ * supplied in certain circumstances (mainly at panic time).  If
+ * messages are supplied, they will be freed, even if an error
+ * occurs.
+ */
+static int i_ipmi_request(struct ipmi_user     *user,
+			  struct ipmi_smi      *intf,
+			  struct ipmi_addr     *addr,
+			  long                 msgid,
+			  struct kernel_ipmi_msg *msg,
+			  void                 *user_msg_data,
+			  void                 *supplied_smi,
+			  struct ipmi_recv_msg *supplied_recv,
+			  int                  priority,
+			  unsigned char        source_address,
+			  unsigned char        source_lun,
+			  int                  retries,
+			  unsigned int         retry_time_ms)
+{
+	struct ipmi_smi_msg *smi_msg;
+	struct ipmi_recv_msg *recv_msg;
+	int rv = 0;
+
+	if (supplied_recv)
+		recv_msg = supplied_recv;
+	else {
+		recv_msg = ipmi_alloc_recv_msg();
+		if (recv_msg == NULL) {
+			rv = -ENOMEM;
+			goto out;
 		}
+	}
+	recv_msg->user_msg_data = user_msg_data;
+
+	if (supplied_smi)
+		smi_msg = (struct ipmi_smi_msg *) supplied_smi;
+	else {
+		smi_msg = ipmi_alloc_smi_msg();
+		if (smi_msg == NULL) {
+			ipmi_free_recv_msg(recv_msg);
+			rv = -ENOMEM;
+			goto out;
+		}
+	}
+
+	rcu_read_lock();
+	if (intf->in_shutdown) {
+		rv = -ENODEV;
+		goto out_err;
+	}
+
+	recv_msg->user = user;
+	if (user)
+		/* The put happens when the message is freed. */
+		kref_get(&user->refcount);
+	recv_msg->msgid = msgid;
+	/*
+	 * Store the message to send in the receive message so timeout
+	 * responses can get the proper response data.
+	 */
+	recv_msg->msg = *msg;
+
+	if (addr->addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE) {
+		rv = i_ipmi_req_sysintf(intf, addr, msgid, msg, smi_msg,
+					recv_msg, retries, retry_time_ms);
+	} else if (is_ipmb_addr(addr) || is_ipmb_bcast_addr(addr)) {
+		rv = i_ipmi_req_ipmb(intf, addr, msgid, msg, smi_msg, recv_msg,
+				     source_address, source_lun,
+				     retries, retry_time_ms);
+	} else if (is_lan_addr(addr)) {
+		rv = i_ipmi_req_lan(intf, addr, msgid, msg, smi_msg, recv_msg,
+				    source_lun, retries, retry_time_ms);
 	} else {
 	    /* Unknown address type. */
 		ipmi_inc_stat(intf, sent_invalid_commands);
 		rv = -EINVAL;
-		goto out_err;
 	}
 
-#ifdef DEBUG_MSGING
-	{
-		int m;
-		for (m = 0; m < smi_msg->data_size; m++)
-			printk(" %2.2x", smi_msg->data[m]);
-		printk("\n");
-	}
-#endif
+	if (rv) {
+out_err:
+		ipmi_free_smi_msg(smi_msg);
+		ipmi_free_recv_msg(recv_msg);
+	} else {
+		ipmi_debug_msg("Send", smi_msg->data, smi_msg->data_size);
 
-	smi_send(intf, intf->handlers, smi_msg, priority);
+		smi_send(intf, intf->handlers, smi_msg, priority);
+	}
 	rcu_read_unlock();
 
-	return 0;
-
- out_err:
-	rcu_read_unlock();
-	ipmi_free_smi_msg(smi_msg);
-	ipmi_free_recv_msg(recv_msg);
+out:
 	return rv;
 }
 
-static int check_addr(ipmi_smi_t       intf,
+static int check_addr(struct ipmi_smi  *intf,
 		      struct ipmi_addr *addr,
 		      unsigned char    *saddr,
 		      unsigned char    *lun)
@@ -2046,7 +2189,7 @@ static int check_addr(ipmi_smi_t       intf,
 	return 0;
 }
 
-int ipmi_request_settime(ipmi_user_t      user,
+int ipmi_request_settime(struct ipmi_user *user,
 			 struct ipmi_addr *addr,
 			 long             msgid,
 			 struct kernel_ipmi_msg  *msg,
@@ -2056,29 +2199,36 @@ int ipmi_request_settime(ipmi_user_t      user,
 			 unsigned int     retry_time_ms)
 {
 	unsigned char saddr = 0, lun = 0;
-	int           rv;
+	int rv, index;
 
 	if (!user)
 		return -EINVAL;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
+
 	rv = check_addr(user->intf, addr, &saddr, &lun);
-	if (rv)
-		return rv;
-	return i_ipmi_request(user,
-			      user->intf,
-			      addr,
-			      msgid,
-			      msg,
-			      user_msg_data,
-			      NULL, NULL,
-			      priority,
-			      saddr,
-			      lun,
-			      retries,
-			      retry_time_ms);
+	if (!rv)
+		rv = i_ipmi_request(user,
+				    user->intf,
+				    addr,
+				    msgid,
+				    msg,
+				    user_msg_data,
+				    NULL, NULL,
+				    priority,
+				    saddr,
+				    lun,
+				    retries,
+				    retry_time_ms);
+
+	release_ipmi_user(user, index);
+	return rv;
 }
 EXPORT_SYMBOL(ipmi_request_settime);
 
-int ipmi_request_supply_msgs(ipmi_user_t          user,
+int ipmi_request_supply_msgs(struct ipmi_user     *user,
 			     struct ipmi_addr     *addr,
 			     long                 msgid,
 			     struct kernel_ipmi_msg *msg,
@@ -2088,29 +2238,37 @@ int ipmi_request_supply_msgs(ipmi_user_t          user,
 			     int                  priority)
 {
 	unsigned char saddr = 0, lun = 0;
-	int           rv;
+	int rv, index;
 
 	if (!user)
 		return -EINVAL;
+
+	user = acquire_ipmi_user(user, &index);
+	if (!user)
+		return -ENODEV;
+
 	rv = check_addr(user->intf, addr, &saddr, &lun);
-	if (rv)
-		return rv;
-	return i_ipmi_request(user,
-			      user->intf,
-			      addr,
-			      msgid,
-			      msg,
-			      user_msg_data,
-			      supplied_smi,
-			      supplied_recv,
-			      priority,
-			      saddr,
-			      lun,
-			      -1, 0);
+	if (!rv)
+		rv = i_ipmi_request(user,
+				    user->intf,
+				    addr,
+				    msgid,
+				    msg,
+				    user_msg_data,
+				    supplied_smi,
+				    supplied_recv,
+				    priority,
+				    saddr,
+				    lun,
+				    -1, 0);
+
+	release_ipmi_user(user, index);
+	return rv;
 }
 EXPORT_SYMBOL(ipmi_request_supply_msgs);
 
-static void bmc_device_id_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
+static void bmc_device_id_handler(struct ipmi_smi *intf,
+				  struct ipmi_recv_msg *msg)
 {
 	int rv;
 
@@ -2142,7 +2300,7 @@ static void bmc_device_id_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 }
 
 static int
-send_get_device_id_cmd(ipmi_smi_t intf)
+send_get_device_id_cmd(struct ipmi_smi *intf)
 {
 	struct ipmi_system_interface_addr si;
 	struct kernel_ipmi_msg msg;
@@ -2170,7 +2328,7 @@ send_get_device_id_cmd(ipmi_smi_t intf)
 			      -1, 0);
 }
 
-static int __get_device_id(ipmi_smi_t intf, struct bmc_device *bmc)
+static int __get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc)
 {
 	int rv;
 
@@ -2204,7 +2362,7 @@ static int __get_device_id(ipmi_smi_t intf, struct bmc_device *bmc)
  * Except for the first time this is called (in ipmi_register_smi()),
  * this will always return good data;
  */
-static int __bmc_get_device_id(ipmi_smi_t intf, struct bmc_device *bmc,
+static int __bmc_get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc,
 			       struct ipmi_device_id *id,
 			       bool *guid_set, guid_t *guid, int intf_num)
 {
@@ -2337,223 +2495,13 @@ out_noprocessing:
 	return rv;
 }
 
-static int bmc_get_device_id(ipmi_smi_t intf, struct bmc_device *bmc,
+static int bmc_get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc,
 			     struct ipmi_device_id *id,
 			     bool *guid_set, guid_t *guid)
 {
 	return __bmc_get_device_id(intf, bmc, id, guid_set, guid, -1);
 }
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-static int smi_ipmb_proc_show(struct seq_file *m, void *v)
-{
-	ipmi_smi_t intf = m->private;
-	int        i;
-
-	seq_printf(m, "%x", intf->addrinfo[0].address);
-	for (i = 1; i < IPMI_MAX_CHANNELS; i++)
-		seq_printf(m, " %x", intf->addrinfo[i].address);
-	seq_putc(m, '\n');
-
-	return 0;
-}
-
-static int smi_ipmb_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smi_ipmb_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations smi_ipmb_proc_ops = {
-	.open		= smi_ipmb_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int smi_version_proc_show(struct seq_file *m, void *v)
-{
-	ipmi_smi_t intf = m->private;
-	struct ipmi_device_id id;
-	int rv;
-
-	rv = bmc_get_device_id(intf, NULL, &id, NULL, NULL);
-	if (rv)
-		return rv;
-
-	seq_printf(m, "%u.%u\n",
-		   ipmi_version_major(&id),
-		   ipmi_version_minor(&id));
-
-	return 0;
-}
-
-static int smi_version_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smi_version_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations smi_version_proc_ops = {
-	.open		= smi_version_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int smi_stats_proc_show(struct seq_file *m, void *v)
-{
-	ipmi_smi_t intf = m->private;
-
-	seq_printf(m, "sent_invalid_commands:       %u\n",
-		       ipmi_get_stat(intf, sent_invalid_commands));
-	seq_printf(m, "sent_local_commands:         %u\n",
-		       ipmi_get_stat(intf, sent_local_commands));
-	seq_printf(m, "handled_local_responses:     %u\n",
-		       ipmi_get_stat(intf, handled_local_responses));
-	seq_printf(m, "unhandled_local_responses:   %u\n",
-		       ipmi_get_stat(intf, unhandled_local_responses));
-	seq_printf(m, "sent_ipmb_commands:          %u\n",
-		       ipmi_get_stat(intf, sent_ipmb_commands));
-	seq_printf(m, "sent_ipmb_command_errs:      %u\n",
-		       ipmi_get_stat(intf, sent_ipmb_command_errs));
-	seq_printf(m, "retransmitted_ipmb_commands: %u\n",
-		       ipmi_get_stat(intf, retransmitted_ipmb_commands));
-	seq_printf(m, "timed_out_ipmb_commands:     %u\n",
-		       ipmi_get_stat(intf, timed_out_ipmb_commands));
-	seq_printf(m, "timed_out_ipmb_broadcasts:   %u\n",
-		       ipmi_get_stat(intf, timed_out_ipmb_broadcasts));
-	seq_printf(m, "sent_ipmb_responses:         %u\n",
-		       ipmi_get_stat(intf, sent_ipmb_responses));
-	seq_printf(m, "handled_ipmb_responses:      %u\n",
-		       ipmi_get_stat(intf, handled_ipmb_responses));
-	seq_printf(m, "invalid_ipmb_responses:      %u\n",
-		       ipmi_get_stat(intf, invalid_ipmb_responses));
-	seq_printf(m, "unhandled_ipmb_responses:    %u\n",
-		       ipmi_get_stat(intf, unhandled_ipmb_responses));
-	seq_printf(m, "sent_lan_commands:           %u\n",
-		       ipmi_get_stat(intf, sent_lan_commands));
-	seq_printf(m, "sent_lan_command_errs:       %u\n",
-		       ipmi_get_stat(intf, sent_lan_command_errs));
-	seq_printf(m, "retransmitted_lan_commands:  %u\n",
-		       ipmi_get_stat(intf, retransmitted_lan_commands));
-	seq_printf(m, "timed_out_lan_commands:      %u\n",
-		       ipmi_get_stat(intf, timed_out_lan_commands));
-	seq_printf(m, "sent_lan_responses:          %u\n",
-		       ipmi_get_stat(intf, sent_lan_responses));
-	seq_printf(m, "handled_lan_responses:       %u\n",
-		       ipmi_get_stat(intf, handled_lan_responses));
-	seq_printf(m, "invalid_lan_responses:       %u\n",
-		       ipmi_get_stat(intf, invalid_lan_responses));
-	seq_printf(m, "unhandled_lan_responses:     %u\n",
-		       ipmi_get_stat(intf, unhandled_lan_responses));
-	seq_printf(m, "handled_commands:            %u\n",
-		       ipmi_get_stat(intf, handled_commands));
-	seq_printf(m, "invalid_commands:            %u\n",
-		       ipmi_get_stat(intf, invalid_commands));
-	seq_printf(m, "unhandled_commands:          %u\n",
-		       ipmi_get_stat(intf, unhandled_commands));
-	seq_printf(m, "invalid_events:              %u\n",
-		       ipmi_get_stat(intf, invalid_events));
-	seq_printf(m, "events:                      %u\n",
-		       ipmi_get_stat(intf, events));
-	seq_printf(m, "failed rexmit LAN msgs:      %u\n",
-		       ipmi_get_stat(intf, dropped_rexmit_lan_commands));
-	seq_printf(m, "failed rexmit IPMB msgs:     %u\n",
-		       ipmi_get_stat(intf, dropped_rexmit_ipmb_commands));
-	return 0;
-}
-
-static int smi_stats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smi_stats_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations smi_stats_proc_ops = {
-	.open		= smi_stats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name,
-			    const struct file_operations *proc_ops,
-			    void *data)
-{
-	int                    rv = 0;
-	struct proc_dir_entry  *file;
-	struct ipmi_proc_entry *entry;
-
-	/* Create a list element. */
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		return -ENOMEM;
-	entry->name = kstrdup(name, GFP_KERNEL);
-	if (!entry->name) {
-		kfree(entry);
-		return -ENOMEM;
-	}
-
-	file = proc_create_data(name, 0, smi->proc_dir, proc_ops, data);
-	if (!file) {
-		kfree(entry->name);
-		kfree(entry);
-		rv = -ENOMEM;
-	} else {
-		mutex_lock(&smi->proc_entry_lock);
-		/* Stick it on the list. */
-		entry->next = smi->proc_entries;
-		smi->proc_entries = entry;
-		mutex_unlock(&smi->proc_entry_lock);
-	}
-
-	return rv;
-}
-EXPORT_SYMBOL(ipmi_smi_add_proc_entry);
-
-static int add_proc_entries(ipmi_smi_t smi, int num)
-{
-	int rv = 0;
-
-	sprintf(smi->proc_dir_name, "%d", num);
-	smi->proc_dir = proc_mkdir(smi->proc_dir_name, proc_ipmi_root);
-	if (!smi->proc_dir)
-		rv = -ENOMEM;
-
-	if (rv == 0)
-		rv = ipmi_smi_add_proc_entry(smi, "stats",
-					     &smi_stats_proc_ops,
-					     smi);
-
-	if (rv == 0)
-		rv = ipmi_smi_add_proc_entry(smi, "ipmb",
-					     &smi_ipmb_proc_ops,
-					     smi);
-
-	if (rv == 0)
-		rv = ipmi_smi_add_proc_entry(smi, "version",
-					     &smi_version_proc_ops,
-					     smi);
-
-	return rv;
-}
-
-static void remove_proc_entries(ipmi_smi_t smi)
-{
-	struct ipmi_proc_entry *entry;
-
-	mutex_lock(&smi->proc_entry_lock);
-	while (smi->proc_entries) {
-		entry = smi->proc_entries;
-		smi->proc_entries = entry->next;
-
-		remove_proc_entry(entry->name, smi->proc_dir);
-		kfree(entry->name);
-		kfree(entry);
-	}
-	mutex_unlock(&smi->proc_entry_lock);
-	remove_proc_entry(smi->proc_dir_name, proc_ipmi_root);
-}
-#endif /* CONFIG_IPMI_PROC_INTERFACE */
-
 static ssize_t device_id_show(struct device *dev,
 			      struct device_attribute *attr,
 			      char *buf)
@@ -2885,7 +2833,7 @@ cleanup_bmc_device(struct kref *ref)
 /*
  * Must be called with intf->bmc_reg_mutex held.
  */
-static void __ipmi_bmc_unregister(ipmi_smi_t intf)
+static void __ipmi_bmc_unregister(struct ipmi_smi *intf)
 {
 	struct bmc_device *bmc = intf->bmc;
 
@@ -2905,7 +2853,7 @@ static void __ipmi_bmc_unregister(ipmi_smi_t intf)
 	intf->bmc_registered = false;
 }
 
-static void ipmi_bmc_unregister(ipmi_smi_t intf)
+static void ipmi_bmc_unregister(struct ipmi_smi *intf)
 {
 	mutex_lock(&intf->bmc_reg_mutex);
 	__ipmi_bmc_unregister(intf);
@@ -2915,7 +2863,7 @@ static void ipmi_bmc_unregister(ipmi_smi_t intf)
 /*
  * Must be called with intf->bmc_reg_mutex held.
  */
-static int __ipmi_bmc_register(ipmi_smi_t intf,
+static int __ipmi_bmc_register(struct ipmi_smi *intf,
 			       struct ipmi_device_id *id,
 			       bool guid_set, guid_t *guid, int intf_num)
 {
@@ -3077,7 +3025,7 @@ out_list_del:
 }
 
 static int
-send_guid_cmd(ipmi_smi_t intf, int chan)
+send_guid_cmd(struct ipmi_smi *intf, int chan)
 {
 	struct kernel_ipmi_msg            msg;
 	struct ipmi_system_interface_addr si;
@@ -3104,7 +3052,7 @@ send_guid_cmd(ipmi_smi_t intf, int chan)
 			      -1, 0);
 }
 
-static void guid_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
+static void guid_handler(struct ipmi_smi *intf, struct ipmi_recv_msg *msg)
 {
 	struct bmc_device *bmc = intf->bmc;
 
@@ -3139,7 +3087,7 @@ static void guid_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 	wake_up(&intf->waitq);
 }
 
-static void __get_guid(ipmi_smi_t intf)
+static void __get_guid(struct ipmi_smi *intf)
 {
 	int rv;
 	struct bmc_device *bmc = intf->bmc;
@@ -3160,7 +3108,7 @@ static void __get_guid(ipmi_smi_t intf)
 }
 
 static int
-send_channel_info_cmd(ipmi_smi_t intf, int chan)
+send_channel_info_cmd(struct ipmi_smi *intf, int chan)
 {
 	struct kernel_ipmi_msg            msg;
 	unsigned char                     data[1];
@@ -3190,7 +3138,7 @@ send_channel_info_cmd(ipmi_smi_t intf, int chan)
 }
 
 static void
-channel_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
+channel_handler(struct ipmi_smi *intf, struct ipmi_recv_msg *msg)
 {
 	int rv = 0;
 	int ch;
@@ -3262,7 +3210,7 @@ channel_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 /*
  * Must be holding intf->bmc_reg_mutex to call this.
  */
-static int __scan_channels(ipmi_smi_t intf, struct ipmi_device_id *id)
+static int __scan_channels(struct ipmi_smi *intf, struct ipmi_device_id *id)
 {
 	int rv;
 
@@ -3306,7 +3254,7 @@ static int __scan_channels(ipmi_smi_t intf, struct ipmi_device_id *id)
 	return 0;
 }
 
-static void ipmi_poll(ipmi_smi_t intf)
+static void ipmi_poll(struct ipmi_smi *intf)
 {
 	if (intf->handlers->poll)
 		intf->handlers->poll(intf->send_info);
@@ -3314,7 +3262,7 @@ static void ipmi_poll(ipmi_smi_t intf)
 	handle_new_recv_msgs(intf);
 }
 
-void ipmi_poll_interface(ipmi_user_t user)
+void ipmi_poll_interface(struct ipmi_user *user)
 {
 	ipmi_poll(user->intf);
 }
@@ -3322,7 +3270,8 @@ EXPORT_SYMBOL(ipmi_poll_interface);
 
 static void redo_bmc_reg(struct work_struct *work)
 {
-	ipmi_smi_t intf = container_of(work, struct ipmi_smi, bmc_reg_work);
+	struct ipmi_smi *intf = container_of(work, struct ipmi_smi,
+					     bmc_reg_work);
 
 	if (!intf->in_shutdown)
 		bmc_get_device_id(intf, NULL, NULL, NULL, NULL);
@@ -3337,8 +3286,7 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
 {
 	int              i, j;
 	int              rv;
-	ipmi_smi_t       intf;
-	ipmi_smi_t       tintf;
+	struct ipmi_smi *intf, *tintf;
 	struct list_head *link;
 	struct ipmi_device_id id;
 
@@ -3362,6 +3310,13 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
 	if (!intf)
 		return -ENOMEM;
 
+	rv = init_srcu_struct(&intf->users_srcu);
+	if (rv) {
+		kfree(intf);
+		return rv;
+	}
+
+
 	intf->bmc = &intf->tmp_bmc;
 	INIT_LIST_HEAD(&intf->bmc->intfs);
 	mutex_init(&intf->bmc->dyn_mutex);
@@ -3386,9 +3341,6 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
 		intf->seq_table[j].seqid = 0;
 	}
 	intf->curr_seq = 0;
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	mutex_init(&intf->proc_entry_lock);
-#endif
 	spin_lock_init(&intf->waiting_rcv_msgs_lock);
 	INIT_LIST_HEAD(&intf->waiting_rcv_msgs);
 	tasklet_init(&intf->recv_tasklet,
@@ -3410,11 +3362,6 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
 	for (i = 0; i < IPMI_NUM_STATS; i++)
 		atomic_set(&intf->stats[i], 0);
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	intf->proc_dir = NULL;
-#endif
-
-	mutex_lock(&smi_watchers_mutex);
 	mutex_lock(&ipmi_interfaces_mutex);
 	/* Look for a hole in the numbers. */
 	i = 0;
@@ -3445,25 +3392,14 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
 	mutex_lock(&intf->bmc_reg_mutex);
 	rv = __scan_channels(intf, &id);
 	mutex_unlock(&intf->bmc_reg_mutex);
-	if (rv)
-		goto out;
-
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	rv = add_proc_entries(intf, i);
-#endif
 
  out:
 	if (rv) {
 		ipmi_bmc_unregister(intf);
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-		if (intf->proc_dir)
-			remove_proc_entries(intf);
-#endif
-		intf->handlers = NULL;
 		list_del_rcu(&intf->link);
 		mutex_unlock(&ipmi_interfaces_mutex);
-		mutex_unlock(&smi_watchers_mutex);
-		synchronize_rcu();
+		synchronize_srcu(&ipmi_interfaces_srcu);
+		cleanup_srcu_struct(&intf->users_srcu);
 		kref_put(&intf->refcount, intf_free);
 	} else {
 		/*
@@ -3474,16 +3410,16 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
 		smp_wmb();
 		intf->intf_num = i;
 		mutex_unlock(&ipmi_interfaces_mutex);
+
 		/* After this point the interface is legal to use. */
 		call_smi_watchers(i, intf->si_dev);
-		mutex_unlock(&smi_watchers_mutex);
 	}
 
 	return rv;
 }
 EXPORT_SYMBOL(ipmi_register_smi);
 
-static void deliver_smi_err_response(ipmi_smi_t intf,
+static void deliver_smi_err_response(struct ipmi_smi *intf,
 				     struct ipmi_smi_msg *msg,
 				     unsigned char err)
 {
@@ -3495,7 +3431,7 @@ static void deliver_smi_err_response(ipmi_smi_t intf,
 	handle_one_recv_msg(intf, msg);
 }
 
-static void cleanup_smi_msgs(ipmi_smi_t intf)
+static void cleanup_smi_msgs(struct ipmi_smi *intf)
 {
 	int              i;
 	struct seq_table *ent;
@@ -3528,60 +3464,58 @@ static void cleanup_smi_msgs(ipmi_smi_t intf)
 	}
 
 	for (i = 0; i < IPMI_IPMB_NUM_SEQ; i++) {
-		ent = &(intf->seq_table[i]);
+		ent = &intf->seq_table[i];
 		if (!ent->inuse)
 			continue;
-		deliver_err_response(ent->recv_msg, IPMI_ERR_UNSPECIFIED);
+		deliver_err_response(intf, ent->recv_msg, IPMI_ERR_UNSPECIFIED);
 	}
 }
 
-int ipmi_unregister_smi(ipmi_smi_t intf)
+void ipmi_unregister_smi(struct ipmi_smi *intf)
 {
 	struct ipmi_smi_watcher *w;
-	int intf_num = intf->intf_num;
-	ipmi_user_t user;
+	int intf_num = intf->intf_num, index;
 
-	mutex_lock(&smi_watchers_mutex);
 	mutex_lock(&ipmi_interfaces_mutex);
 	intf->intf_num = -1;
 	intf->in_shutdown = true;
 	list_del_rcu(&intf->link);
 	mutex_unlock(&ipmi_interfaces_mutex);
-	synchronize_rcu();
+	synchronize_srcu(&ipmi_interfaces_srcu);
 
-	cleanup_smi_msgs(intf);
-
-	/* Clean up the effects of users on the lower-level software. */
-	mutex_lock(&ipmi_interfaces_mutex);
-	rcu_read_lock();
-	list_for_each_entry_rcu(user, &intf->users, link) {
-		module_put(intf->handlers->owner);
-		if (intf->handlers->dec_usecount)
-			intf->handlers->dec_usecount(intf->send_info);
-	}
-	rcu_read_unlock();
-	intf->handlers = NULL;
-	mutex_unlock(&ipmi_interfaces_mutex);
-
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	remove_proc_entries(intf);
-#endif
-	ipmi_bmc_unregister(intf);
+	/* At this point no users can be added to the interface. */
 
 	/*
 	 * Call all the watcher interfaces to tell them that
-	 * an interface is gone.
+	 * an interface is going away.
 	 */
+	mutex_lock(&smi_watchers_mutex);
 	list_for_each_entry(w, &smi_watchers, link)
 		w->smi_gone(intf_num);
 	mutex_unlock(&smi_watchers_mutex);
 
+	index = srcu_read_lock(&intf->users_srcu);
+	while (!list_empty(&intf->users)) {
+		struct ipmi_user *user =
+			container_of(list_next_rcu(&intf->users),
+				     struct ipmi_user, link);
+
+		_ipmi_destroy_user(user);
+	}
+	srcu_read_unlock(&intf->users_srcu, index);
+
+	intf->handlers->shutdown(intf->send_info);
+
+	cleanup_smi_msgs(intf);
+
+	ipmi_bmc_unregister(intf);
+
+	cleanup_srcu_struct(&intf->users_srcu);
 	kref_put(&intf->refcount, intf_free);
-	return 0;
 }
 EXPORT_SYMBOL(ipmi_unregister_smi);
 
-static int handle_ipmb_get_msg_rsp(ipmi_smi_t          intf,
+static int handle_ipmb_get_msg_rsp(struct ipmi_smi *intf,
 				   struct ipmi_smi_msg *msg)
 {
 	struct ipmi_ipmb_addr ipmb_addr;
@@ -3616,7 +3550,7 @@ static int handle_ipmb_get_msg_rsp(ipmi_smi_t          intf,
 			  msg->rsp[3] & 0x0f,
 			  msg->rsp[8],
 			  (msg->rsp[4] >> 2) & (~1),
-			  (struct ipmi_addr *) &(ipmb_addr),
+			  (struct ipmi_addr *) &ipmb_addr,
 			  &recv_msg)) {
 		/*
 		 * We were unable to find the sequence number,
@@ -3626,9 +3560,7 @@ static int handle_ipmb_get_msg_rsp(ipmi_smi_t          intf,
 		return 0;
 	}
 
-	memcpy(recv_msg->msg_data,
-	       &(msg->rsp[9]),
-	       msg->rsp_size - 9);
+	memcpy(recv_msg->msg_data, &msg->rsp[9], msg->rsp_size - 9);
 	/*
 	 * The other fields matched, so no need to set them, except
 	 * for netfn, which needs to be the response that was
@@ -3638,13 +3570,15 @@ static int handle_ipmb_get_msg_rsp(ipmi_smi_t          intf,
 	recv_msg->msg.data = recv_msg->msg_data;
 	recv_msg->msg.data_len = msg->rsp_size - 10;
 	recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE;
-	ipmi_inc_stat(intf, handled_ipmb_responses);
-	deliver_response(recv_msg);
+	if (deliver_response(intf, recv_msg))
+		ipmi_inc_stat(intf, unhandled_ipmb_responses);
+	else
+		ipmi_inc_stat(intf, handled_ipmb_responses);
 
 	return 0;
 }
 
-static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
+static int handle_ipmb_get_msg_cmd(struct ipmi_smi *intf,
 				   struct ipmi_smi_msg *msg)
 {
 	struct cmd_rcvr          *rcvr;
@@ -3652,7 +3586,7 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 	unsigned char            netfn;
 	unsigned char            cmd;
 	unsigned char            chan;
-	ipmi_user_t              user = NULL;
+	struct ipmi_user         *user = NULL;
 	struct ipmi_ipmb_addr    *ipmb_addr;
 	struct ipmi_recv_msg     *recv_msg;
 
@@ -3689,24 +3623,17 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 		msg->data[2] = msg->rsp[3];
 		msg->data[3] = msg->rsp[6];
 		msg->data[4] = ((netfn + 1) << 2) | (msg->rsp[7] & 0x3);
-		msg->data[5] = ipmb_checksum(&(msg->data[3]), 2);
+		msg->data[5] = ipmb_checksum(&msg->data[3], 2);
 		msg->data[6] = intf->addrinfo[msg->rsp[3] & 0xf].address;
 		/* rqseq/lun */
 		msg->data[7] = (msg->rsp[7] & 0xfc) | (msg->rsp[4] & 0x3);
 		msg->data[8] = msg->rsp[8]; /* cmd */
 		msg->data[9] = IPMI_INVALID_CMD_COMPLETION_CODE;
-		msg->data[10] = ipmb_checksum(&(msg->data[6]), 4);
+		msg->data[10] = ipmb_checksum(&msg->data[6], 4);
 		msg->data_size = 11;
 
-#ifdef DEBUG_MSGING
-	{
-		int m;
-		printk("Invalid command:");
-		for (m = 0; m < msg->data_size; m++)
-			printk(" %2.2x", msg->data[m]);
-		printk("\n");
-	}
-#endif
+		ipmi_debug_msg("Invalid command:", msg->data, msg->data_size);
+
 		rcu_read_lock();
 		if (!intf->in_shutdown) {
 			smi_send(intf, intf->handlers, msg, 0);
@@ -3719,9 +3646,6 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 		}
 		rcu_read_unlock();
 	} else {
-		/* Deliver the message to the user. */
-		ipmi_inc_stat(intf, handled_commands);
-
 		recv_msg = ipmi_alloc_recv_msg();
 		if (!recv_msg) {
 			/*
@@ -3755,17 +3679,19 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 			 * at the end also needs to be removed.
 			 */
 			recv_msg->msg.data_len = msg->rsp_size - 10;
-			memcpy(recv_msg->msg_data,
-			       &(msg->rsp[9]),
+			memcpy(recv_msg->msg_data, &msg->rsp[9],
 			       msg->rsp_size - 10);
-			deliver_response(recv_msg);
+			if (deliver_response(intf, recv_msg))
+				ipmi_inc_stat(intf, unhandled_commands);
+			else
+				ipmi_inc_stat(intf, handled_commands);
 		}
 	}
 
 	return rv;
 }
 
-static int handle_lan_get_msg_rsp(ipmi_smi_t          intf,
+static int handle_lan_get_msg_rsp(struct ipmi_smi *intf,
 				  struct ipmi_smi_msg *msg)
 {
 	struct ipmi_lan_addr  lan_addr;
@@ -3804,7 +3730,7 @@ static int handle_lan_get_msg_rsp(ipmi_smi_t          intf,
 			  msg->rsp[3] & 0x0f,
 			  msg->rsp[10],
 			  (msg->rsp[6] >> 2) & (~1),
-			  (struct ipmi_addr *) &(lan_addr),
+			  (struct ipmi_addr *) &lan_addr,
 			  &recv_msg)) {
 		/*
 		 * We were unable to find the sequence number,
@@ -3814,9 +3740,7 @@ static int handle_lan_get_msg_rsp(ipmi_smi_t          intf,
 		return 0;
 	}
 
-	memcpy(recv_msg->msg_data,
-	       &(msg->rsp[11]),
-	       msg->rsp_size - 11);
+	memcpy(recv_msg->msg_data, &msg->rsp[11], msg->rsp_size - 11);
 	/*
 	 * The other fields matched, so no need to set them, except
 	 * for netfn, which needs to be the response that was
@@ -3826,13 +3750,15 @@ static int handle_lan_get_msg_rsp(ipmi_smi_t          intf,
 	recv_msg->msg.data = recv_msg->msg_data;
 	recv_msg->msg.data_len = msg->rsp_size - 12;
 	recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE;
-	ipmi_inc_stat(intf, handled_lan_responses);
-	deliver_response(recv_msg);
+	if (deliver_response(intf, recv_msg))
+		ipmi_inc_stat(intf, unhandled_lan_responses);
+	else
+		ipmi_inc_stat(intf, handled_lan_responses);
 
 	return 0;
 }
 
-static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
+static int handle_lan_get_msg_cmd(struct ipmi_smi *intf,
 				  struct ipmi_smi_msg *msg)
 {
 	struct cmd_rcvr          *rcvr;
@@ -3840,7 +3766,7 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
 	unsigned char            netfn;
 	unsigned char            cmd;
 	unsigned char            chan;
-	ipmi_user_t              user = NULL;
+	struct ipmi_user         *user = NULL;
 	struct ipmi_lan_addr     *lan_addr;
 	struct ipmi_recv_msg     *recv_msg;
 
@@ -3878,9 +3804,6 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
 		 */
 		rv = 0;
 	} else {
-		/* Deliver the message to the user. */
-		ipmi_inc_stat(intf, handled_commands);
-
 		recv_msg = ipmi_alloc_recv_msg();
 		if (!recv_msg) {
 			/*
@@ -3916,10 +3839,12 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
 			 * at the end also needs to be removed.
 			 */
 			recv_msg->msg.data_len = msg->rsp_size - 12;
-			memcpy(recv_msg->msg_data,
-			       &(msg->rsp[11]),
+			memcpy(recv_msg->msg_data, &msg->rsp[11],
 			       msg->rsp_size - 12);
-			deliver_response(recv_msg);
+			if (deliver_response(intf, recv_msg))
+				ipmi_inc_stat(intf, unhandled_commands);
+			else
+				ipmi_inc_stat(intf, handled_commands);
 		}
 	}
 
@@ -3932,7 +3857,7 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
  * the OEM.  See IPMI 2.0 specification, Chapter 6 and
  * Chapter 22, sections 22.6 and 22.24 for more details.
  */
-static int handle_oem_get_msg_cmd(ipmi_smi_t          intf,
+static int handle_oem_get_msg_cmd(struct ipmi_smi *intf,
 				  struct ipmi_smi_msg *msg)
 {
 	struct cmd_rcvr       *rcvr;
@@ -3940,7 +3865,7 @@ static int handle_oem_get_msg_cmd(ipmi_smi_t          intf,
 	unsigned char         netfn;
 	unsigned char         cmd;
 	unsigned char         chan;
-	ipmi_user_t           user = NULL;
+	struct ipmi_user *user = NULL;
 	struct ipmi_system_interface_addr *smi_addr;
 	struct ipmi_recv_msg  *recv_msg;
 
@@ -3987,9 +3912,6 @@ static int handle_oem_get_msg_cmd(ipmi_smi_t          intf,
 
 		rv = 0;
 	} else {
-		/* Deliver the message to the user. */
-		ipmi_inc_stat(intf, handled_commands);
-
 		recv_msg = ipmi_alloc_recv_msg();
 		if (!recv_msg) {
 			/*
@@ -4007,7 +3929,7 @@ static int handle_oem_get_msg_cmd(ipmi_smi_t          intf,
 			 * requirements
 			 */
 			smi_addr = ((struct ipmi_system_interface_addr *)
-				    &(recv_msg->addr));
+				    &recv_msg->addr);
 			smi_addr->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
 			smi_addr->channel = IPMI_BMC_CHANNEL;
 			smi_addr->lun = msg->rsp[0] & 3;
@@ -4024,10 +3946,12 @@ static int handle_oem_get_msg_cmd(ipmi_smi_t          intf,
 			 * the Channel Byte in the "GET MESSAGE" command
 			 */
 			recv_msg->msg.data_len = msg->rsp_size - 4;
-			memcpy(recv_msg->msg_data,
-			       &(msg->rsp[4]),
+			memcpy(recv_msg->msg_data, &msg->rsp[4],
 			       msg->rsp_size - 4);
-			deliver_response(recv_msg);
+			if (deliver_response(intf, recv_msg))
+				ipmi_inc_stat(intf, unhandled_commands);
+			else
+				ipmi_inc_stat(intf, handled_commands);
 		}
 	}
 
@@ -4040,26 +3964,25 @@ static void copy_event_into_recv_msg(struct ipmi_recv_msg *recv_msg,
 	struct ipmi_system_interface_addr *smi_addr;
 
 	recv_msg->msgid = 0;
-	smi_addr = (struct ipmi_system_interface_addr *) &(recv_msg->addr);
+	smi_addr = (struct ipmi_system_interface_addr *) &recv_msg->addr;
 	smi_addr->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
 	smi_addr->channel = IPMI_BMC_CHANNEL;
 	smi_addr->lun = msg->rsp[0] & 3;
 	recv_msg->recv_type = IPMI_ASYNC_EVENT_RECV_TYPE;
 	recv_msg->msg.netfn = msg->rsp[0] >> 2;
 	recv_msg->msg.cmd = msg->rsp[1];
-	memcpy(recv_msg->msg_data, &(msg->rsp[3]), msg->rsp_size - 3);
+	memcpy(recv_msg->msg_data, &msg->rsp[3], msg->rsp_size - 3);
 	recv_msg->msg.data = recv_msg->msg_data;
 	recv_msg->msg.data_len = msg->rsp_size - 3;
 }
 
-static int handle_read_event_rsp(ipmi_smi_t          intf,
+static int handle_read_event_rsp(struct ipmi_smi *intf,
 				 struct ipmi_smi_msg *msg)
 {
 	struct ipmi_recv_msg *recv_msg, *recv_msg2;
 	struct list_head     msgs;
-	ipmi_user_t          user;
-	int                  rv = 0;
-	int                  deliver_count = 0;
+	struct ipmi_user     *user;
+	int rv = 0, deliver_count = 0, index;
 	unsigned long        flags;
 
 	if (msg->rsp_size < 19) {
@@ -4083,7 +4006,7 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 	 * Allocate and fill in one message for every user that is
 	 * getting events.
 	 */
-	rcu_read_lock();
+	index = srcu_read_lock(&intf->users_srcu);
 	list_for_each_entry_rcu(user, &intf->users, link) {
 		if (!user->gets_events)
 			continue;
@@ -4110,15 +4033,15 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 		copy_event_into_recv_msg(recv_msg, msg);
 		recv_msg->user = user;
 		kref_get(&user->refcount);
-		list_add_tail(&(recv_msg->link), &msgs);
+		list_add_tail(&recv_msg->link, &msgs);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&intf->users_srcu, index);
 
 	if (deliver_count) {
 		/* Now deliver all the messages. */
 		list_for_each_entry_safe(recv_msg, recv_msg2, &msgs, link) {
 			list_del(&recv_msg->link);
-			deliver_response(recv_msg);
+			deliver_local_response(intf, recv_msg);
 		}
 	} else if (intf->waiting_events_count < MAX_EVENTS_IN_QUEUE) {
 		/*
@@ -4137,7 +4060,7 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 		}
 
 		copy_event_into_recv_msg(recv_msg, msg);
-		list_add_tail(&(recv_msg->link), &(intf->waiting_events));
+		list_add_tail(&recv_msg->link, &intf->waiting_events);
 		intf->waiting_events_count++;
 	} else if (!intf->event_msg_printed) {
 		/*
@@ -4150,16 +4073,16 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 	}
 
  out:
-	spin_unlock_irqrestore(&(intf->events_lock), flags);
+	spin_unlock_irqrestore(&intf->events_lock, flags);
 
 	return rv;
 }
 
-static int handle_bmc_rsp(ipmi_smi_t          intf,
+static int handle_bmc_rsp(struct ipmi_smi *intf,
 			  struct ipmi_smi_msg *msg)
 {
 	struct ipmi_recv_msg *recv_msg;
-	struct ipmi_user     *user;
+	struct ipmi_system_interface_addr *smi_addr;
 
 	recv_msg = (struct ipmi_recv_msg *) msg->user_data;
 	if (recv_msg == NULL) {
@@ -4168,32 +4091,19 @@ static int handle_bmc_rsp(ipmi_smi_t          intf,
 		return 0;
 	}
 
-	user = recv_msg->user;
-	/* Make sure the user still exists. */
-	if (user && !user->valid) {
-		/* The user for the message went away, so give up. */
-		ipmi_inc_stat(intf, unhandled_local_responses);
-		ipmi_free_recv_msg(recv_msg);
-	} else {
-		struct ipmi_system_interface_addr *smi_addr;
-
-		ipmi_inc_stat(intf, handled_local_responses);
-		recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE;
-		recv_msg->msgid = msg->msgid;
-		smi_addr = ((struct ipmi_system_interface_addr *)
-			    &(recv_msg->addr));
-		smi_addr->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-		smi_addr->channel = IPMI_BMC_CHANNEL;
-		smi_addr->lun = msg->rsp[0] & 3;
-		recv_msg->msg.netfn = msg->rsp[0] >> 2;
-		recv_msg->msg.cmd = msg->rsp[1];
-		memcpy(recv_msg->msg_data,
-		       &(msg->rsp[2]),
-		       msg->rsp_size - 2);
-		recv_msg->msg.data = recv_msg->msg_data;
-		recv_msg->msg.data_len = msg->rsp_size - 2;
-		deliver_response(recv_msg);
-	}
+	recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE;
+	recv_msg->msgid = msg->msgid;
+	smi_addr = ((struct ipmi_system_interface_addr *)
+		    &recv_msg->addr);
+	smi_addr->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+	smi_addr->channel = IPMI_BMC_CHANNEL;
+	smi_addr->lun = msg->rsp[0] & 3;
+	recv_msg->msg.netfn = msg->rsp[0] >> 2;
+	recv_msg->msg.cmd = msg->rsp[1];
+	memcpy(recv_msg->msg_data, &msg->rsp[2], msg->rsp_size - 2);
+	recv_msg->msg.data = recv_msg->msg_data;
+	recv_msg->msg.data_len = msg->rsp_size - 2;
+	deliver_local_response(intf, recv_msg);
 
 	return 0;
 }
@@ -4203,19 +4113,13 @@ static int handle_bmc_rsp(ipmi_smi_t          intf,
  * 0 if the message should be freed, or -1 if the message should not
  * be freed or requeued.
  */
-static int handle_one_recv_msg(ipmi_smi_t          intf,
+static int handle_one_recv_msg(struct ipmi_smi *intf,
 			       struct ipmi_smi_msg *msg)
 {
 	int requeue;
 	int chan;
 
-#ifdef DEBUG_MSGING
-	int m;
-	printk("Recv:");
-	for (m = 0; m < msg->rsp_size; m++)
-		printk(" %2.2x", msg->rsp[m]);
-	printk("\n");
-#endif
+	ipmi_debug_msg("Recv:", msg->rsp, msg->rsp_size);
 	if (msg->rsp_size < 2) {
 		/* Message is too small to be correct. */
 		dev_warn(intf->si_dev,
@@ -4252,7 +4156,7 @@ static int handle_one_recv_msg(ipmi_smi_t          intf,
 		 * It's a response to a response we sent.  For this we
 		 * deliver a send message response to the user.
 		 */
-		struct ipmi_recv_msg     *recv_msg = msg->user_data;
+		struct ipmi_recv_msg *recv_msg = msg->user_data;
 
 		requeue = 0;
 		if (msg->rsp_size < 2)
@@ -4267,15 +4171,11 @@ static int handle_one_recv_msg(ipmi_smi_t          intf,
 		if (!recv_msg)
 			goto out;
 
-		/* Make sure the user still exists. */
-		if (!recv_msg->user || !recv_msg->user->valid)
-			goto out;
-
 		recv_msg->recv_type = IPMI_RESPONSE_RESPONSE_TYPE;
 		recv_msg->msg.data = recv_msg->msg_data;
 		recv_msg->msg.data_len = 1;
 		recv_msg->msg_data[0] = msg->rsp[2];
-		deliver_response(recv_msg);
+		deliver_local_response(intf, recv_msg);
 	} else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2))
 		   && (msg->rsp[1] == IPMI_GET_MSG_CMD)) {
 		struct ipmi_channel   *chans;
@@ -4367,7 +4267,7 @@ static int handle_one_recv_msg(ipmi_smi_t          intf,
 /*
  * If there are messages in the queue or pretimeouts, handle them.
  */
-static void handle_new_recv_msgs(ipmi_smi_t intf)
+static void handle_new_recv_msgs(struct ipmi_smi *intf)
 {
 	struct ipmi_smi_msg  *smi_msg;
 	unsigned long        flags = 0;
@@ -4412,22 +4312,23 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
 	 * deliver pretimeouts to all the users.
 	 */
 	if (atomic_add_unless(&intf->watchdog_pretimeouts_to_deliver, -1, 0)) {
-		ipmi_user_t user;
+		struct ipmi_user *user;
+		int index;
 
-		rcu_read_lock();
+		index = srcu_read_lock(&intf->users_srcu);
 		list_for_each_entry_rcu(user, &intf->users, link) {
 			if (user->handler->ipmi_watchdog_pretimeout)
 				user->handler->ipmi_watchdog_pretimeout(
 					user->handler_data);
 		}
-		rcu_read_unlock();
+		srcu_read_unlock(&intf->users_srcu, index);
 	}
 }
 
 static void smi_recv_tasklet(unsigned long val)
 {
 	unsigned long flags = 0; /* keep us warning-free. */
-	ipmi_smi_t intf = (ipmi_smi_t) val;
+	struct ipmi_smi *intf = (struct ipmi_smi *) val;
 	int run_to_completion = intf->run_to_completion;
 	struct ipmi_smi_msg *newmsg = NULL;
 
@@ -4469,7 +4370,7 @@ static void smi_recv_tasklet(unsigned long val)
 }
 
 /* Handle a new message from the lower layer. */
-void ipmi_smi_msg_received(ipmi_smi_t          intf,
+void ipmi_smi_msg_received(struct ipmi_smi *intf,
 			   struct ipmi_smi_msg *msg)
 {
 	unsigned long flags = 0; /* keep us warning-free. */
@@ -4550,7 +4451,7 @@ free_msg:
 }
 EXPORT_SYMBOL(ipmi_smi_msg_received);
 
-void ipmi_smi_watchdog_pretimeout(ipmi_smi_t intf)
+void ipmi_smi_watchdog_pretimeout(struct ipmi_smi *intf)
 {
 	if (intf->in_shutdown)
 		return;
@@ -4561,7 +4462,7 @@ void ipmi_smi_watchdog_pretimeout(ipmi_smi_t intf)
 EXPORT_SYMBOL(ipmi_smi_watchdog_pretimeout);
 
 static struct ipmi_smi_msg *
-smi_from_recv_msg(ipmi_smi_t intf, struct ipmi_recv_msg *recv_msg,
+smi_from_recv_msg(struct ipmi_smi *intf, struct ipmi_recv_msg *recv_msg,
 		  unsigned char seq, long seqid)
 {
 	struct ipmi_smi_msg *smi_msg = ipmi_alloc_smi_msg();
@@ -4576,26 +4477,18 @@ smi_from_recv_msg(ipmi_smi_t intf, struct ipmi_recv_msg *recv_msg,
 	smi_msg->data_size = recv_msg->msg.data_len;
 	smi_msg->msgid = STORE_SEQ_IN_MSGID(seq, seqid);
 
-#ifdef DEBUG_MSGING
-	{
-		int m;
-		printk("Resend: ");
-		for (m = 0; m < smi_msg->data_size; m++)
-			printk(" %2.2x", smi_msg->data[m]);
-		printk("\n");
-	}
-#endif
+	ipmi_debug_msg("Resend: ", smi_msg->data, smi_msg->data_size);
+
 	return smi_msg;
 }
 
-static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
+static void check_msg_timeout(struct ipmi_smi *intf, struct seq_table *ent,
 			      struct list_head *timeouts,
 			      unsigned long timeout_period,
 			      int slot, unsigned long *flags,
 			      unsigned int *waiting_msgs)
 {
-	struct ipmi_recv_msg     *msg;
-	const struct ipmi_smi_handlers *handlers;
+	struct ipmi_recv_msg *msg;
 
 	if (intf->in_shutdown)
 		return;
@@ -4653,8 +4546,7 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
 		 * only for messages to the local MC, which don't get
 		 * resent.
 		 */
-		handlers = intf->handlers;
-		if (handlers) {
+		if (intf->handlers) {
 			if (is_lan_addr(&ent->recv_msg->addr))
 				ipmi_inc_stat(intf,
 					      retransmitted_lan_commands);
@@ -4662,7 +4554,7 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
 				ipmi_inc_stat(intf,
 					      retransmitted_ipmb_commands);
 
-			smi_send(intf, handlers, smi_msg, 0);
+			smi_send(intf, intf->handlers, smi_msg, 0);
 		} else
 			ipmi_free_smi_msg(smi_msg);
 
@@ -4670,7 +4562,7 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
 	}
 }
 
-static unsigned int ipmi_timeout_handler(ipmi_smi_t intf,
+static unsigned int ipmi_timeout_handler(struct ipmi_smi *intf,
 					 unsigned long timeout_period)
 {
 	struct list_head     timeouts;
@@ -4694,14 +4586,20 @@ static unsigned int ipmi_timeout_handler(ipmi_smi_t intf,
 	 */
 	INIT_LIST_HEAD(&timeouts);
 	spin_lock_irqsave(&intf->seq_lock, flags);
+	if (intf->ipmb_maintenance_mode_timeout) {
+		if (intf->ipmb_maintenance_mode_timeout <= timeout_period)
+			intf->ipmb_maintenance_mode_timeout = 0;
+		else
+			intf->ipmb_maintenance_mode_timeout -= timeout_period;
+	}
 	for (i = 0; i < IPMI_IPMB_NUM_SEQ; i++)
-		check_msg_timeout(intf, &(intf->seq_table[i]),
+		check_msg_timeout(intf, &intf->seq_table[i],
 				  &timeouts, timeout_period, i,
 				  &flags, &waiting_msgs);
 	spin_unlock_irqrestore(&intf->seq_lock, flags);
 
 	list_for_each_entry_safe(msg, msg2, &timeouts, link)
-		deliver_err_response(msg, IPMI_TIMEOUT_COMPLETION_CODE);
+		deliver_err_response(intf, msg, IPMI_TIMEOUT_COMPLETION_CODE);
 
 	/*
 	 * Maintenance mode handling.  Check the timeout
@@ -4731,7 +4629,7 @@ static unsigned int ipmi_timeout_handler(ipmi_smi_t intf,
 	return waiting_msgs;
 }
 
-static void ipmi_request_event(ipmi_smi_t intf)
+static void ipmi_request_event(struct ipmi_smi *intf)
 {
 	/* No event requests when in maintenance mode. */
 	if (intf->maintenance_mode_enable)
@@ -4747,13 +4645,13 @@ static atomic_t stop_operation;
 
 static void ipmi_timeout(struct timer_list *unused)
 {
-	ipmi_smi_t intf;
-	int nt = 0;
+	struct ipmi_smi *intf;
+	int nt = 0, index;
 
 	if (atomic_read(&stop_operation))
 		return;
 
-	rcu_read_lock();
+	index = srcu_read_lock(&ipmi_interfaces_srcu);
 	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
 		int lnt = 0;
 
@@ -4776,13 +4674,13 @@ static void ipmi_timeout(struct timer_list *unused)
 
 		nt += lnt;
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&ipmi_interfaces_srcu, index);
 
 	if (nt)
 		mod_timer(&ipmi_timer, jiffies + IPMI_TIMEOUT_JIFFIES);
 }
 
-static void need_waiter(ipmi_smi_t intf)
+static void need_waiter(struct ipmi_smi *intf)
 {
 	/* Racy, but worst case we start the timer twice. */
 	if (!timer_pending(&ipmi_timer))
@@ -4853,8 +4751,8 @@ static void dummy_recv_done_handler(struct ipmi_recv_msg *msg)
 /*
  * Inside a panic, send a message and wait for a response.
  */
-static void ipmi_panic_request_and_wait(ipmi_smi_t           intf,
-					struct ipmi_addr     *addr,
+static void ipmi_panic_request_and_wait(struct ipmi_smi *intf,
+					struct ipmi_addr *addr,
 					struct kernel_ipmi_msg *msg)
 {
 	struct ipmi_smi_msg  smi_msg;
@@ -4885,7 +4783,8 @@ static void ipmi_panic_request_and_wait(ipmi_smi_t           intf,
 		ipmi_poll(intf);
 }
 
-static void event_receiver_fetcher(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
+static void event_receiver_fetcher(struct ipmi_smi *intf,
+				   struct ipmi_recv_msg *msg)
 {
 	if ((msg->addr.addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE)
 	    && (msg->msg.netfn == IPMI_NETFN_SENSOR_EVENT_RESPONSE)
@@ -4897,7 +4796,7 @@ static void event_receiver_fetcher(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 	}
 }
 
-static void device_id_fetcher(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
+static void device_id_fetcher(struct ipmi_smi *intf, struct ipmi_recv_msg *msg)
 {
 	if ((msg->addr.addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE)
 	    && (msg->msg.netfn == IPMI_NETFN_APP_RESPONSE)
@@ -4912,13 +4811,15 @@ static void device_id_fetcher(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 	}
 }
 
-static void send_panic_events(char *str)
+static void send_panic_events(struct ipmi_smi *intf, char *str)
 {
-	struct kernel_ipmi_msg            msg;
-	ipmi_smi_t                        intf;
-	unsigned char                     data[16];
+	struct kernel_ipmi_msg msg;
+	unsigned char data[16];
 	struct ipmi_system_interface_addr *si;
-	struct ipmi_addr                  addr;
+	struct ipmi_addr addr;
+	char *p = str;
+	struct ipmi_ipmb_addr *ipmb;
+	int j;
 
 	if (ipmi_send_panic_event == IPMI_SEND_PANIC_EVENT_NONE)
 		return;
@@ -4949,15 +4850,8 @@ static void send_panic_events(char *str)
 		data[7] = str[2];
 	}
 
-	/* For every registered interface, send the event. */
-	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
-		if (!intf->handlers || !intf->handlers->poll)
-			/* Interface is not ready or can't run at panic time. */
-			continue;
-
-		/* Send the event announcing the panic. */
-		ipmi_panic_request_and_wait(intf, &addr, &msg);
-	}
+	/* Send the event announcing the panic. */
+	ipmi_panic_request_and_wait(intf, &addr, &msg);
 
 	/*
 	 * On every interface, dump a bunch of OEM event holding the
@@ -4966,111 +4860,100 @@ static void send_panic_events(char *str)
 	if (ipmi_send_panic_event != IPMI_SEND_PANIC_EVENT_STRING || !str)
 		return;
 
-	/* For every registered interface, send the event. */
-	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
-		char                  *p = str;
-		struct ipmi_ipmb_addr *ipmb;
-		int                   j;
-
-		if (intf->intf_num == -1)
-			/* Interface was not ready yet. */
-			continue;
+	/*
+	 * intf_num is used as an marker to tell if the
+	 * interface is valid.  Thus we need a read barrier to
+	 * make sure data fetched before checking intf_num
+	 * won't be used.
+	 */
+	smp_rmb();
 
-		/*
-		 * intf_num is used as an marker to tell if the
-		 * interface is valid.  Thus we need a read barrier to
-		 * make sure data fetched before checking intf_num
-		 * won't be used.
-		 */
-		smp_rmb();
+	/*
+	 * First job here is to figure out where to send the
+	 * OEM events.  There's no way in IPMI to send OEM
+	 * events using an event send command, so we have to
+	 * find the SEL to put them in and stick them in
+	 * there.
+	 */
 
-		/*
-		 * First job here is to figure out where to send the
-		 * OEM events.  There's no way in IPMI to send OEM
-		 * events using an event send command, so we have to
-		 * find the SEL to put them in and stick them in
-		 * there.
-		 */
+	/* Get capabilities from the get device id. */
+	intf->local_sel_device = 0;
+	intf->local_event_generator = 0;
+	intf->event_receiver = 0;
 
-		/* Get capabilities from the get device id. */
-		intf->local_sel_device = 0;
-		intf->local_event_generator = 0;
-		intf->event_receiver = 0;
+	/* Request the device info from the local MC. */
+	msg.netfn = IPMI_NETFN_APP_REQUEST;
+	msg.cmd = IPMI_GET_DEVICE_ID_CMD;
+	msg.data = NULL;
+	msg.data_len = 0;
+	intf->null_user_handler = device_id_fetcher;
+	ipmi_panic_request_and_wait(intf, &addr, &msg);
 
-		/* Request the device info from the local MC. */
-		msg.netfn = IPMI_NETFN_APP_REQUEST;
-		msg.cmd = IPMI_GET_DEVICE_ID_CMD;
+	if (intf->local_event_generator) {
+		/* Request the event receiver from the local MC. */
+		msg.netfn = IPMI_NETFN_SENSOR_EVENT_REQUEST;
+		msg.cmd = IPMI_GET_EVENT_RECEIVER_CMD;
 		msg.data = NULL;
 		msg.data_len = 0;
-		intf->null_user_handler = device_id_fetcher;
+		intf->null_user_handler = event_receiver_fetcher;
 		ipmi_panic_request_and_wait(intf, &addr, &msg);
+	}
+	intf->null_user_handler = NULL;
 
-		if (intf->local_event_generator) {
-			/* Request the event receiver from the local MC. */
-			msg.netfn = IPMI_NETFN_SENSOR_EVENT_REQUEST;
-			msg.cmd = IPMI_GET_EVENT_RECEIVER_CMD;
-			msg.data = NULL;
-			msg.data_len = 0;
-			intf->null_user_handler = event_receiver_fetcher;
-			ipmi_panic_request_and_wait(intf, &addr, &msg);
-		}
-		intf->null_user_handler = NULL;
+	/*
+	 * Validate the event receiver.  The low bit must not
+	 * be 1 (it must be a valid IPMB address), it cannot
+	 * be zero, and it must not be my address.
+	 */
+	if (((intf->event_receiver & 1) == 0)
+	    && (intf->event_receiver != 0)
+	    && (intf->event_receiver != intf->addrinfo[0].address)) {
+		/*
+		 * The event receiver is valid, send an IPMB
+		 * message.
+		 */
+		ipmb = (struct ipmi_ipmb_addr *) &addr;
+		ipmb->addr_type = IPMI_IPMB_ADDR_TYPE;
+		ipmb->channel = 0; /* FIXME - is this right? */
+		ipmb->lun = intf->event_receiver_lun;
+		ipmb->slave_addr = intf->event_receiver;
+	} else if (intf->local_sel_device) {
+		/*
+		 * The event receiver was not valid (or was
+		 * me), but I am an SEL device, just dump it
+		 * in my SEL.
+		 */
+		si = (struct ipmi_system_interface_addr *) &addr;
+		si->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+		si->channel = IPMI_BMC_CHANNEL;
+		si->lun = 0;
+	} else
+		return; /* No where to send the event. */
 
+	msg.netfn = IPMI_NETFN_STORAGE_REQUEST; /* Storage. */
+	msg.cmd = IPMI_ADD_SEL_ENTRY_CMD;
+	msg.data = data;
+	msg.data_len = 16;
+
+	j = 0;
+	while (*p) {
+		int size = strlen(p);
+
+		if (size > 11)
+			size = 11;
+		data[0] = 0;
+		data[1] = 0;
+		data[2] = 0xf0; /* OEM event without timestamp. */
+		data[3] = intf->addrinfo[0].address;
+		data[4] = j++; /* sequence # */
 		/*
-		 * Validate the event receiver.  The low bit must not
-		 * be 1 (it must be a valid IPMB address), it cannot
-		 * be zero, and it must not be my address.
+		 * Always give 11 bytes, so strncpy will fill
+		 * it with zeroes for me.
 		 */
-		if (((intf->event_receiver & 1) == 0)
-		    && (intf->event_receiver != 0)
-		    && (intf->event_receiver != intf->addrinfo[0].address)) {
-			/*
-			 * The event receiver is valid, send an IPMB
-			 * message.
-			 */
-			ipmb = (struct ipmi_ipmb_addr *) &addr;
-			ipmb->addr_type = IPMI_IPMB_ADDR_TYPE;
-			ipmb->channel = 0; /* FIXME - is this right? */
-			ipmb->lun = intf->event_receiver_lun;
-			ipmb->slave_addr = intf->event_receiver;
-		} else if (intf->local_sel_device) {
-			/*
-			 * The event receiver was not valid (or was
-			 * me), but I am an SEL device, just dump it
-			 * in my SEL.
-			 */
-			si = (struct ipmi_system_interface_addr *) &addr;
-			si->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-			si->channel = IPMI_BMC_CHANNEL;
-			si->lun = 0;
-		} else
-			continue; /* No where to send the event. */
-
-		msg.netfn = IPMI_NETFN_STORAGE_REQUEST; /* Storage. */
-		msg.cmd = IPMI_ADD_SEL_ENTRY_CMD;
-		msg.data = data;
-		msg.data_len = 16;
-
-		j = 0;
-		while (*p) {
-			int size = strlen(p);
-
-			if (size > 11)
-				size = 11;
-			data[0] = 0;
-			data[1] = 0;
-			data[2] = 0xf0; /* OEM event without timestamp. */
-			data[3] = intf->addrinfo[0].address;
-			data[4] = j++; /* sequence # */
-			/*
-			 * Always give 11 bytes, so strncpy will fill
-			 * it with zeroes for me.
-			 */
-			strncpy(data+5, p, 11);
-			p += size;
+		strncpy(data+5, p, 11);
+		p += size;
 
-			ipmi_panic_request_and_wait(intf, &addr, &msg);
-		}
+		ipmi_panic_request_and_wait(intf, &addr, &msg);
 	}
 }
 
@@ -5080,7 +4963,8 @@ static int panic_event(struct notifier_block *this,
 		       unsigned long         event,
 		       void                  *ptr)
 {
-	ipmi_smi_t intf;
+	struct ipmi_smi *intf;
+	struct ipmi_user *user;
 
 	if (has_panicked)
 		return NOTIFY_DONE;
@@ -5088,10 +4972,13 @@ static int panic_event(struct notifier_block *this,
 
 	/* For every registered interface, set it to run to completion. */
 	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
-		if (!intf->handlers)
+		if (!intf->handlers || intf->intf_num == -1)
 			/* Interface is not ready. */
 			continue;
 
+		if (!intf->handlers->poll)
+			continue;
+
 		/*
 		 * If we were interrupted while locking xmit_msgs_lock or
 		 * waiting_rcv_msgs_lock, the corresponding list may be
@@ -5113,9 +5000,15 @@ static int panic_event(struct notifier_block *this,
 		if (intf->handlers->set_run_to_completion)
 			intf->handlers->set_run_to_completion(intf->send_info,
 							      1);
-	}
 
-	send_panic_events(ptr);
+		list_for_each_entry_rcu(user, &intf->users, link) {
+			if (user->handler->ipmi_panic_handler)
+				user->handler->ipmi_panic_handler(
+					user->handler_data);
+		}
+
+		send_panic_events(intf, ptr);
+	}
 
 	return NOTIFY_DONE;
 }
@@ -5141,16 +5034,6 @@ static int ipmi_init_msghandler(void)
 
 	pr_info("ipmi message handler version " IPMI_DRIVER_VERSION "\n");
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	proc_ipmi_root = proc_mkdir("ipmi", NULL);
-	if (!proc_ipmi_root) {
-	    pr_err(PFX "Unable to create IPMI proc dir");
-	    driver_unregister(&ipmidriver.driver);
-	    return -ENOMEM;
-	}
-
-#endif /* CONFIG_IPMI_PROC_INTERFACE */
-
 	timer_setup(&ipmi_timer, ipmi_timeout, 0);
 	mod_timer(&ipmi_timer, jiffies + IPMI_TIMEOUT_JIFFIES);
 
@@ -5189,10 +5072,6 @@ static void __exit cleanup_ipmi(void)
 	atomic_inc(&stop_operation);
 	del_timer_sync(&ipmi_timer);
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	proc_remove(proc_ipmi_root);
-#endif /* CONFIG_IPMI_PROC_INTERFACE */
-
 	driver_unregister(&ipmidriver.driver);
 
 	initialized = 0;
diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c
index 7996337852f2..f6e19410dc57 100644
--- a/drivers/char/ipmi/ipmi_poweroff.c
+++ b/drivers/char/ipmi/ipmi_poweroff.c
@@ -39,9 +39,9 @@ static int ifnum_to_use = -1;
 
 /* Our local state. */
 static int ready;
-static ipmi_user_t ipmi_user;
+static struct ipmi_user *ipmi_user;
 static int ipmi_ifnum;
-static void (*specific_poweroff_func)(ipmi_user_t user);
+static void (*specific_poweroff_func)(struct ipmi_user *user);
 
 /* Holds the old poweroff function so we can restore it on removal. */
 static void (*old_poweroff_func)(void);
@@ -118,7 +118,7 @@ static const struct ipmi_user_hndl ipmi_poweroff_handler = {
 };
 
 
-static int ipmi_request_wait_for_response(ipmi_user_t            user,
+static int ipmi_request_wait_for_response(struct ipmi_user       *user,
 					  struct ipmi_addr       *addr,
 					  struct kernel_ipmi_msg *send_msg)
 {
@@ -138,7 +138,7 @@ static int ipmi_request_wait_for_response(ipmi_user_t            user,
 }
 
 /* Wait for message to complete, spinning. */
-static int ipmi_request_in_rc_mode(ipmi_user_t            user,
+static int ipmi_request_in_rc_mode(struct ipmi_user       *user,
 				   struct ipmi_addr       *addr,
 				   struct kernel_ipmi_msg *send_msg)
 {
@@ -178,9 +178,9 @@ static int ipmi_request_in_rc_mode(ipmi_user_t            user,
 #define IPMI_MOTOROLA_MANUFACTURER_ID		0x0000A1
 #define IPMI_MOTOROLA_PPS_IPMC_PRODUCT_ID	0x0051
 
-static void (*atca_oem_poweroff_hook)(ipmi_user_t user);
+static void (*atca_oem_poweroff_hook)(struct ipmi_user *user);
 
-static void pps_poweroff_atca(ipmi_user_t user)
+static void pps_poweroff_atca(struct ipmi_user *user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct kernel_ipmi_msg            send_msg;
@@ -208,7 +208,7 @@ static void pps_poweroff_atca(ipmi_user_t user)
 	return;
 }
 
-static int ipmi_atca_detect(ipmi_user_t user)
+static int ipmi_atca_detect(struct ipmi_user *user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct kernel_ipmi_msg            send_msg;
@@ -245,7 +245,7 @@ static int ipmi_atca_detect(ipmi_user_t user)
 	return !rv;
 }
 
-static void ipmi_poweroff_atca(ipmi_user_t user)
+static void ipmi_poweroff_atca(struct ipmi_user *user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct kernel_ipmi_msg            send_msg;
@@ -309,13 +309,13 @@ static void ipmi_poweroff_atca(ipmi_user_t user)
 #define IPMI_CPI1_PRODUCT_ID		0x000157
 #define IPMI_CPI1_MANUFACTURER_ID	0x0108
 
-static int ipmi_cpi1_detect(ipmi_user_t user)
+static int ipmi_cpi1_detect(struct ipmi_user *user)
 {
 	return ((mfg_id == IPMI_CPI1_MANUFACTURER_ID)
 		&& (prod_id == IPMI_CPI1_PRODUCT_ID));
 }
 
-static void ipmi_poweroff_cpi1(ipmi_user_t user)
+static void ipmi_poweroff_cpi1(struct ipmi_user *user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct ipmi_ipmb_addr             ipmb_addr;
@@ -424,7 +424,7 @@ static void ipmi_poweroff_cpi1(ipmi_user_t user)
  */
 
 #define DELL_IANA_MFR_ID {0xA2, 0x02, 0x00}
-static int ipmi_dell_chassis_detect(ipmi_user_t user)
+static int ipmi_dell_chassis_detect(struct ipmi_user *user)
 {
 	const char ipmi_version_major = ipmi_version & 0xF;
 	const char ipmi_version_minor = (ipmi_version >> 4) & 0xF;
@@ -445,7 +445,7 @@ static int ipmi_dell_chassis_detect(ipmi_user_t user)
 
 #define HP_IANA_MFR_ID 0x0b
 #define HP_BMC_PROD_ID 0x8201
-static int ipmi_hp_chassis_detect(ipmi_user_t user)
+static int ipmi_hp_chassis_detect(struct ipmi_user *user)
 {
 	if (mfg_id == HP_IANA_MFR_ID
 		&& prod_id == HP_BMC_PROD_ID
@@ -461,13 +461,13 @@ static int ipmi_hp_chassis_detect(ipmi_user_t user)
 #define IPMI_NETFN_CHASSIS_REQUEST	0
 #define IPMI_CHASSIS_CONTROL_CMD	0x02
 
-static int ipmi_chassis_detect(ipmi_user_t user)
+static int ipmi_chassis_detect(struct ipmi_user *user)
 {
 	/* Chassis support, use it. */
 	return (capabilities & 0x80);
 }
 
-static void ipmi_poweroff_chassis(ipmi_user_t user)
+static void ipmi_poweroff_chassis(struct ipmi_user *user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct kernel_ipmi_msg            send_msg;
@@ -517,8 +517,8 @@ static void ipmi_poweroff_chassis(ipmi_user_t user)
 /* Table of possible power off functions. */
 struct poweroff_function {
 	char *platform_type;
-	int  (*detect)(ipmi_user_t user);
-	void (*poweroff_func)(ipmi_user_t user);
+	int  (*detect)(struct ipmi_user *user);
+	void (*poweroff_func)(struct ipmi_user *user);
 };
 
 static struct poweroff_function poweroff_functions[] = {
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index ff870aa91cfe..ad353be871bf 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -122,8 +122,8 @@ enum si_stat_indexes {
 };
 
 struct smi_info {
-	int                    intf_num;
-	ipmi_smi_t             intf;
+	int                    si_num;
+	struct ipmi_smi        *intf;
 	struct si_sm_data      *si_sm;
 	const struct si_sm_handlers *handlers;
 	spinlock_t             si_lock;
@@ -261,7 +261,6 @@ static int num_max_busy_us;
 static bool unload_when_empty = true;
 
 static int try_smi_init(struct smi_info *smi);
-static void shutdown_one_si(struct smi_info *smi_info);
 static void cleanup_one_si(struct smi_info *smi_info);
 static void cleanup_ipmi_si(void);
 
@@ -287,10 +286,7 @@ static void deliver_recv_msg(struct smi_info *smi_info,
 			     struct ipmi_smi_msg *msg)
 {
 	/* Deliver the message to the upper layer. */
-	if (smi_info->intf)
-		ipmi_smi_msg_received(smi_info->intf, msg);
-	else
-		ipmi_free_smi_msg(msg);
+	ipmi_smi_msg_received(smi_info->intf, msg);
 }
 
 static void return_hosed_msg(struct smi_info *smi_info, int cCode)
@@ -471,8 +467,7 @@ retry:
 
 		start_clear_flags(smi_info);
 		smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT;
-		if (smi_info->intf)
-			ipmi_smi_watchdog_pretimeout(smi_info->intf);
+		ipmi_smi_watchdog_pretimeout(smi_info->intf);
 	} else if (smi_info->msg_flags & RECEIVE_MSG_AVAIL) {
 		/* Messages available. */
 		smi_info->curr_msg = alloc_msg_handle_irq(smi_info);
@@ -798,8 +793,7 @@ restart:
 	 * We prefer handling attn over new messages.  But don't do
 	 * this if there is not yet an upper layer to handle anything.
 	 */
-	if (likely(smi_info->intf) &&
-	    (si_sm_result == SI_SM_ATTN || smi_info->got_attn)) {
+	if (si_sm_result == SI_SM_ATTN || smi_info->got_attn) {
 		unsigned char msg[2];
 
 		if (smi_info->si_state != SI_NORMAL) {
@@ -962,8 +956,8 @@ static inline int ipmi_thread_busy_wait(enum si_sm_result smi_result,
 {
 	unsigned int max_busy_us = 0;
 
-	if (smi_info->intf_num < num_max_busy_us)
-		max_busy_us = kipmid_max_busy_us[smi_info->intf_num];
+	if (smi_info->si_num < num_max_busy_us)
+		max_busy_us = kipmid_max_busy_us[smi_info->si_num];
 	if (max_busy_us == 0 || smi_result != SI_SM_CALL_WITH_DELAY)
 		ipmi_si_set_not_busy(busy_until);
 	else if (!ipmi_si_is_busy(busy_until)) {
@@ -1143,8 +1137,8 @@ irqreturn_t ipmi_si_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int smi_start_processing(void       *send_info,
-				ipmi_smi_t intf)
+static int smi_start_processing(void            *send_info,
+				struct ipmi_smi *intf)
 {
 	struct smi_info *new_smi = send_info;
 	int             enable = 0;
@@ -1165,8 +1159,8 @@ static int smi_start_processing(void       *send_info,
 	/*
 	 * Check if the user forcefully enabled the daemon.
 	 */
-	if (new_smi->intf_num < num_force_kipmid)
-		enable = force_kipmid[new_smi->intf_num];
+	if (new_smi->si_num < num_force_kipmid)
+		enable = force_kipmid[new_smi->si_num];
 	/*
 	 * The BT interface is efficient enough to not need a thread,
 	 * and there is no need for a thread if we have interrupts.
@@ -1176,7 +1170,7 @@ static int smi_start_processing(void       *send_info,
 
 	if (enable) {
 		new_smi->thread = kthread_run(ipmi_thread, new_smi,
-					      "kipmi%d", new_smi->intf_num);
+					      "kipmi%d", new_smi->si_num);
 		if (IS_ERR(new_smi->thread)) {
 			dev_notice(new_smi->io.dev, "Could not start"
 				   " kernel thread due to error %ld, only using"
@@ -1209,9 +1203,11 @@ static void set_maintenance_mode(void *send_info, bool enable)
 		atomic_set(&smi_info->req_events, 0);
 }
 
+static void shutdown_smi(void *send_info);
 static const struct ipmi_smi_handlers handlers = {
 	.owner                  = THIS_MODULE,
 	.start_processing       = smi_start_processing,
+	.shutdown               = shutdown_smi,
 	.get_smi_info		= get_smi_info,
 	.sender			= sender,
 	.request_events		= request_events,
@@ -1592,102 +1588,6 @@ out:
 	return rv;
 }
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-static int smi_type_proc_show(struct seq_file *m, void *v)
-{
-	struct smi_info *smi = m->private;
-
-	seq_printf(m, "%s\n", si_to_str[smi->io.si_type]);
-
-	return 0;
-}
-
-static int smi_type_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smi_type_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations smi_type_proc_ops = {
-	.open		= smi_type_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int smi_si_stats_proc_show(struct seq_file *m, void *v)
-{
-	struct smi_info *smi = m->private;
-
-	seq_printf(m, "interrupts_enabled:    %d\n",
-		       smi->io.irq && !smi->interrupt_disabled);
-	seq_printf(m, "short_timeouts:        %u\n",
-		       smi_get_stat(smi, short_timeouts));
-	seq_printf(m, "long_timeouts:         %u\n",
-		       smi_get_stat(smi, long_timeouts));
-	seq_printf(m, "idles:                 %u\n",
-		       smi_get_stat(smi, idles));
-	seq_printf(m, "interrupts:            %u\n",
-		       smi_get_stat(smi, interrupts));
-	seq_printf(m, "attentions:            %u\n",
-		       smi_get_stat(smi, attentions));
-	seq_printf(m, "flag_fetches:          %u\n",
-		       smi_get_stat(smi, flag_fetches));
-	seq_printf(m, "hosed_count:           %u\n",
-		       smi_get_stat(smi, hosed_count));
-	seq_printf(m, "complete_transactions: %u\n",
-		       smi_get_stat(smi, complete_transactions));
-	seq_printf(m, "events:                %u\n",
-		       smi_get_stat(smi, events));
-	seq_printf(m, "watchdog_pretimeouts:  %u\n",
-		       smi_get_stat(smi, watchdog_pretimeouts));
-	seq_printf(m, "incoming_messages:     %u\n",
-		       smi_get_stat(smi, incoming_messages));
-	return 0;
-}
-
-static int smi_si_stats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smi_si_stats_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations smi_si_stats_proc_ops = {
-	.open		= smi_si_stats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int smi_params_proc_show(struct seq_file *m, void *v)
-{
-	struct smi_info *smi = m->private;
-
-	seq_printf(m,
-		   "%s,%s,0x%lx,rsp=%d,rsi=%d,rsh=%d,irq=%d,ipmb=%d\n",
-		   si_to_str[smi->io.si_type],
-		   addr_space_to_str[smi->io.addr_type],
-		   smi->io.addr_data,
-		   smi->io.regspacing,
-		   smi->io.regsize,
-		   smi->io.regshift,
-		   smi->io.irq,
-		   smi->io.slave_addr);
-
-	return 0;
-}
-
-static int smi_params_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smi_params_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations smi_params_proc_ops = {
-	.open		= smi_params_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
 #define IPMI_SI_ATTR(name) \
 static ssize_t ipmi_##name##_show(struct device *dev,			\
 				  struct device_attribute *attr,	\
@@ -2006,14 +1906,8 @@ int ipmi_si_add_smi(struct si_sm_io *io)
 
 	list_add_tail(&new_smi->link, &smi_infos);
 
-	if (initialized) {
+	if (initialized)
 		rv = try_smi_init(new_smi);
-		if (rv) {
-			cleanup_one_si(new_smi);
-			mutex_unlock(&smi_infos_lock);
-			return rv;
-		}
-	}
 out_err:
 	mutex_unlock(&smi_infos_lock);
 	return rv;
@@ -2056,19 +1950,19 @@ static int try_smi_init(struct smi_info *new_smi)
 		goto out_err;
 	}
 
-	new_smi->intf_num = smi_num;
+	new_smi->si_num = smi_num;
 
 	/* Do this early so it's available for logs. */
 	if (!new_smi->io.dev) {
 		init_name = kasprintf(GFP_KERNEL, "ipmi_si.%d",
-				      new_smi->intf_num);
+				      new_smi->si_num);
 
 		/*
 		 * If we don't already have a device from something
 		 * else (like PCI), then register a new one.
 		 */
 		new_smi->pdev = platform_device_alloc("ipmi_si",
-						      new_smi->intf_num);
+						      new_smi->si_num);
 		if (!new_smi->pdev) {
 			pr_err(PFX "Unable to allocate platform device\n");
 			rv = -ENOMEM;
@@ -2182,35 +2076,6 @@ static int try_smi_init(struct smi_info *new_smi)
 		goto out_err;
 	}
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	rv = ipmi_smi_add_proc_entry(new_smi->intf, "type",
-				     &smi_type_proc_ops,
-				     new_smi);
-	if (rv) {
-		dev_err(new_smi->io.dev,
-			"Unable to create proc entry: %d\n", rv);
-		goto out_err;
-	}
-
-	rv = ipmi_smi_add_proc_entry(new_smi->intf, "si_stats",
-				     &smi_si_stats_proc_ops,
-				     new_smi);
-	if (rv) {
-		dev_err(new_smi->io.dev,
-			"Unable to create proc entry: %d\n", rv);
-		goto out_err;
-	}
-
-	rv = ipmi_smi_add_proc_entry(new_smi->intf, "params",
-				     &smi_params_proc_ops,
-				     new_smi);
-	if (rv) {
-		dev_err(new_smi->io.dev,
-			"Unable to create proc entry: %d\n", rv);
-		goto out_err;
-	}
-#endif
-
 	/* Don't increment till we know we have succeeded. */
 	smi_num++;
 
@@ -2223,7 +2088,8 @@ static int try_smi_init(struct smi_info *new_smi)
 	return 0;
 
 out_err:
-	shutdown_one_si(new_smi);
+	ipmi_unregister_smi(new_smi->intf);
+	new_smi->intf = NULL;
 
 	kfree(init_name);
 
@@ -2301,20 +2167,9 @@ skip_fallback_noirq:
 }
 module_init(init_ipmi_si);
 
-static void shutdown_one_si(struct smi_info *smi_info)
+static void shutdown_smi(void *send_info)
 {
-	int           rv = 0;
-
-	if (smi_info->intf) {
-		ipmi_smi_t intf = smi_info->intf;
-
-		smi_info->intf = NULL;
-		rv = ipmi_unregister_smi(intf);
-		if (rv) {
-			pr_err(PFX "Unable to unregister device: errno=%d\n",
-			       rv);
-		}
-	}
+	struct smi_info *smi_info = send_info;
 
 	if (smi_info->dev_group_added) {
 		device_remove_group(smi_info->io.dev, &ipmi_si_dev_attr_group);
@@ -2372,6 +2227,10 @@ static void shutdown_one_si(struct smi_info *smi_info)
 	smi_info->si_sm = NULL;
 }
 
+/*
+ * Must be called with smi_infos_lock held, to serialize the
+ * smi_info->intf check.
+ */
 static void cleanup_one_si(struct smi_info *smi_info)
 {
 	if (!smi_info)
@@ -2379,7 +2238,10 @@ static void cleanup_one_si(struct smi_info *smi_info)
 
 	list_del(&smi_info->link);
 
-	shutdown_one_si(smi_info);
+	if (smi_info->intf) {
+		ipmi_unregister_smi(smi_info->intf);
+		smi_info->intf = NULL;
+	}
 
 	if (smi_info->pdev) {
 		if (smi_info->pdev_registered)
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index 35a82f4bfd78..22f634eb09fd 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -193,8 +193,7 @@ typedef void (*ssif_i2c_done)(struct ssif_info *ssif_info, int result,
 			     unsigned char *data, unsigned int len);
 
 struct ssif_info {
-	ipmi_smi_t          intf;
-	int                 intf_num;
+	struct ipmi_smi     *intf;
 	spinlock_t	    lock;
 	struct ipmi_smi_msg *waiting_msg;
 	struct ipmi_smi_msg *curr_msg;
@@ -290,8 +289,6 @@ struct ssif_info {
 
 static bool initialized;
 
-static atomic_t next_intf = ATOMIC_INIT(0);
-
 static void return_hosed_msg(struct ssif_info *ssif_info,
 			     struct ipmi_smi_msg *msg);
 static void start_next_msg(struct ssif_info *ssif_info, unsigned long *flags);
@@ -315,17 +312,13 @@ static void ipmi_ssif_unlock_cond(struct ssif_info *ssif_info,
 static void deliver_recv_msg(struct ssif_info *ssif_info,
 			     struct ipmi_smi_msg *msg)
 {
-	ipmi_smi_t    intf = ssif_info->intf;
-
-	if (!intf) {
-		ipmi_free_smi_msg(msg);
-	} else if (msg->rsp_size < 0) {
+	if (msg->rsp_size < 0) {
 		return_hosed_msg(ssif_info, msg);
 		pr_err(PFX
 		       "Malformed message in deliver_recv_msg: rsp_size = %d\n",
 		       msg->rsp_size);
 	} else {
-		ipmi_smi_msg_received(intf, msg);
+		ipmi_smi_msg_received(ssif_info->intf, msg);
 	}
 }
 
@@ -452,12 +445,10 @@ static void start_recv_msg_fetch(struct ssif_info *ssif_info,
 static void handle_flags(struct ssif_info *ssif_info, unsigned long *flags)
 {
 	if (ssif_info->msg_flags & WDT_PRE_TIMEOUT_INT) {
-		ipmi_smi_t intf = ssif_info->intf;
 		/* Watchdog pre-timeout */
 		ssif_inc_stat(ssif_info, watchdog_pretimeouts);
 		start_clear_flags(ssif_info, flags);
-		if (intf)
-			ipmi_smi_watchdog_pretimeout(intf);
+		ipmi_smi_watchdog_pretimeout(ssif_info->intf);
 	} else if (ssif_info->msg_flags & RECEIVE_MSG_AVAIL)
 		/* Messages available. */
 		start_recv_msg_fetch(ssif_info, flags);
@@ -1094,27 +1085,8 @@ static void request_events(void *send_info)
 	}
 }
 
-static int inc_usecount(void *send_info)
-{
-	struct ssif_info *ssif_info = send_info;
-
-	if (!i2c_get_adapter(i2c_adapter_id(ssif_info->client->adapter)))
-		return -ENODEV;
-
-	i2c_use_client(ssif_info->client);
-	return 0;
-}
-
-static void dec_usecount(void *send_info)
-{
-	struct ssif_info *ssif_info = send_info;
-
-	i2c_release_client(ssif_info->client);
-	i2c_put_adapter(ssif_info->client->adapter);
-}
-
-static int ssif_start_processing(void *send_info,
-				 ipmi_smi_t intf)
+static int ssif_start_processing(void            *send_info,
+				 struct ipmi_smi *intf)
 {
 	struct ssif_info *ssif_info = send_info;
 
@@ -1225,25 +1197,9 @@ static const struct attribute_group ipmi_ssif_dev_attr_group = {
 	.attrs		= ipmi_ssif_dev_attrs,
 };
 
-static int ssif_remove(struct i2c_client *client)
+static void shutdown_ssif(void *send_info)
 {
-	struct ssif_info *ssif_info = i2c_get_clientdata(client);
-	struct ssif_addr_info *addr_info;
-	int rv;
-
-	if (!ssif_info)
-		return 0;
-
-	/*
-	 * After this point, we won't deliver anything asychronously
-	 * to the message handler.  We can unregister ourself.
-	 */
-	rv = ipmi_unregister_smi(ssif_info->intf);
-	if (rv) {
-		pr_err(PFX "Unable to unregister device: errno=%d\n", rv);
-		return rv;
-	}
-	ssif_info->intf = NULL;
+	struct ssif_info *ssif_info = send_info;
 
 	device_remove_group(&ssif_info->client->dev, &ipmi_ssif_dev_attr_group);
 	dev_set_drvdata(&ssif_info->client->dev, NULL);
@@ -1259,6 +1215,30 @@ static int ssif_remove(struct i2c_client *client)
 		kthread_stop(ssif_info->thread);
 	}
 
+	/*
+	 * No message can be outstanding now, we have removed the
+	 * upper layer and it permitted us to do so.
+	 */
+	kfree(ssif_info);
+}
+
+static int ssif_remove(struct i2c_client *client)
+{
+	struct ssif_info *ssif_info = i2c_get_clientdata(client);
+	struct ipmi_smi *intf;
+	struct ssif_addr_info *addr_info;
+
+	if (!ssif_info)
+		return 0;
+
+	/*
+	 * After this point, we won't deliver anything asychronously
+	 * to the message handler.  We can unregister ourself.
+	 */
+	intf = ssif_info->intf;
+	ssif_info->intf = NULL;
+	ipmi_unregister_smi(intf);
+
 	list_for_each_entry(addr_info, &ssif_infos, link) {
 		if (addr_info->client == client) {
 			addr_info->client = NULL;
@@ -1266,11 +1246,6 @@ static int ssif_remove(struct i2c_client *client)
 		}
 	}
 
-	/*
-	 * No message can be outstanding now, we have removed the
-	 * upper layer and it permitted us to do so.
-	 */
-	kfree(ssif_info);
 	return 0;
 }
 
@@ -1341,72 +1316,6 @@ static int ssif_detect(struct i2c_client *client, struct i2c_board_info *info)
 	return rv;
 }
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-static int smi_type_proc_show(struct seq_file *m, void *v)
-{
-	seq_puts(m, "ssif\n");
-
-	return 0;
-}
-
-static int smi_type_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smi_type_proc_show, inode->i_private);
-}
-
-static const struct file_operations smi_type_proc_ops = {
-	.open		= smi_type_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int smi_stats_proc_show(struct seq_file *m, void *v)
-{
-	struct ssif_info *ssif_info = m->private;
-
-	seq_printf(m, "sent_messages:          %u\n",
-		   ssif_get_stat(ssif_info, sent_messages));
-	seq_printf(m, "sent_messages_parts:    %u\n",
-		   ssif_get_stat(ssif_info, sent_messages_parts));
-	seq_printf(m, "send_retries:           %u\n",
-		   ssif_get_stat(ssif_info, send_retries));
-	seq_printf(m, "send_errors:            %u\n",
-		   ssif_get_stat(ssif_info, send_errors));
-	seq_printf(m, "received_messages:      %u\n",
-		   ssif_get_stat(ssif_info, received_messages));
-	seq_printf(m, "received_message_parts: %u\n",
-		   ssif_get_stat(ssif_info, received_message_parts));
-	seq_printf(m, "receive_retries:        %u\n",
-		   ssif_get_stat(ssif_info, receive_retries));
-	seq_printf(m, "receive_errors:         %u\n",
-		   ssif_get_stat(ssif_info, receive_errors));
-	seq_printf(m, "flag_fetches:           %u\n",
-		   ssif_get_stat(ssif_info, flag_fetches));
-	seq_printf(m, "hosed:                  %u\n",
-		   ssif_get_stat(ssif_info, hosed));
-	seq_printf(m, "events:                 %u\n",
-		   ssif_get_stat(ssif_info, events));
-	seq_printf(m, "watchdog_pretimeouts:   %u\n",
-		   ssif_get_stat(ssif_info, watchdog_pretimeouts));
-	seq_printf(m, "alerts:                 %u\n",
-		   ssif_get_stat(ssif_info, alerts));
-	return 0;
-}
-
-static int smi_stats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smi_stats_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations smi_stats_proc_ops = {
-	.open		= smi_stats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
 static int strcmp_nospace(char *s1, char *s2)
 {
 	while (*s1 && *s2) {
@@ -1678,8 +1587,6 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	}
 
  found:
-	ssif_info->intf_num = atomic_inc_return(&next_intf);
-
 	if (ssif_dbg_probe) {
 		pr_info("ssif_probe: i2c_probe found device at i2c address %x\n",
 			client->addr);
@@ -1697,11 +1604,10 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 
 	ssif_info->handlers.owner = THIS_MODULE;
 	ssif_info->handlers.start_processing = ssif_start_processing;
+	ssif_info->handlers.shutdown = shutdown_ssif;
 	ssif_info->handlers.get_smi_info = get_smi_info;
 	ssif_info->handlers.sender = sender;
 	ssif_info->handlers.request_events = request_events;
-	ssif_info->handlers.inc_usecount = inc_usecount;
-	ssif_info->handlers.dec_usecount = dec_usecount;
 
 	{
 		unsigned int thread_num;
@@ -1740,24 +1646,6 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		goto out_remove_attr;
 	}
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-	rv = ipmi_smi_add_proc_entry(ssif_info->intf, "type",
-				     &smi_type_proc_ops,
-				     ssif_info);
-	if (rv) {
-		pr_err(PFX "Unable to create proc entry: %d\n", rv);
-		goto out_err_unreg;
-	}
-
-	rv = ipmi_smi_add_proc_entry(ssif_info->intf, "ssif_stats",
-				     &smi_stats_proc_ops,
-				     ssif_info);
-	if (rv) {
-		pr_err(PFX "Unable to create proc entry: %d\n", rv);
-		goto out_err_unreg;
-	}
-#endif
-
  out:
 	if (rv) {
 		/*
@@ -1775,11 +1663,6 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	kfree(resp);
 	return rv;
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-out_err_unreg:
-	ipmi_unregister_smi(ssif_info->intf);
-#endif
-
 out_remove_attr:
 	device_remove_group(&ssif_info->client->dev, &ipmi_ssif_dev_attr_group);
 	dev_set_drvdata(&ssif_info->client->dev, NULL);
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 22bc287eac2d..ca1c5c5109f0 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -125,7 +125,7 @@
 static DEFINE_MUTEX(ipmi_watchdog_mutex);
 static bool nowayout = WATCHDOG_NOWAYOUT;
 
-static ipmi_user_t watchdog_user;
+static struct ipmi_user *watchdog_user;
 static int watchdog_ifnum;
 
 /* Default the timeout to 10 seconds. */
@@ -153,7 +153,7 @@ static DEFINE_SPINLOCK(ipmi_read_lock);
 static char data_to_read;
 static DECLARE_WAIT_QUEUE_HEAD(read_q);
 static struct fasync_struct *fasync_q;
-static char pretimeout_since_last_heartbeat;
+static atomic_t pretimeout_since_last_heartbeat;
 static char expect_close;
 
 static int ifnum_to_use = -1;
@@ -303,9 +303,6 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 /* Default state of the timer. */
 static unsigned char ipmi_watchdog_state = WDOG_TIMEOUT_NONE;
 
-/* If shutting down via IPMI, we ignore the heartbeat. */
-static int ipmi_ignore_heartbeat;
-
 /* Is someone using the watchdog?  Only one user is allowed. */
 static unsigned long ipmi_wdog_open;
 
@@ -329,35 +326,33 @@ static int testing_nmi;
 static int nmi_handler_registered;
 #endif
 
-static int ipmi_heartbeat(void);
+static int __ipmi_heartbeat(void);
 
 /*
- * We use a mutex to make sure that only one thing can send a set
- * timeout at one time, because we only have one copy of the data.
- * The mutex is claimed when the set_timeout is sent and freed
- * when both messages are free.
+ * We use a mutex to make sure that only one thing can send a set a
+ * message at one time.  The mutex is claimed when a message is sent
+ * and freed when both the send and receive messages are free.
  */
-static atomic_t set_timeout_tofree = ATOMIC_INIT(0);
-static DEFINE_MUTEX(set_timeout_lock);
-static DECLARE_COMPLETION(set_timeout_wait);
-static void set_timeout_free_smi(struct ipmi_smi_msg *msg)
+static atomic_t msg_tofree = ATOMIC_INIT(0);
+static DECLARE_COMPLETION(msg_wait);
+static void msg_free_smi(struct ipmi_smi_msg *msg)
 {
-    if (atomic_dec_and_test(&set_timeout_tofree))
-	    complete(&set_timeout_wait);
+	if (atomic_dec_and_test(&msg_tofree))
+		complete(&msg_wait);
 }
-static void set_timeout_free_recv(struct ipmi_recv_msg *msg)
+static void msg_free_recv(struct ipmi_recv_msg *msg)
 {
-    if (atomic_dec_and_test(&set_timeout_tofree))
-	    complete(&set_timeout_wait);
+	if (atomic_dec_and_test(&msg_tofree))
+		complete(&msg_wait);
 }
-static struct ipmi_smi_msg set_timeout_smi_msg = {
-	.done = set_timeout_free_smi
+static struct ipmi_smi_msg smi_msg = {
+	.done = msg_free_smi
 };
-static struct ipmi_recv_msg set_timeout_recv_msg = {
-	.done = set_timeout_free_recv
+static struct ipmi_recv_msg recv_msg = {
+	.done = msg_free_recv
 };
 
-static int i_ipmi_set_timeout(struct ipmi_smi_msg  *smi_msg,
+static int __ipmi_set_timeout(struct ipmi_smi_msg  *smi_msg,
 			      struct ipmi_recv_msg *recv_msg,
 			      int                  *send_heartbeat_now)
 {
@@ -368,9 +363,6 @@ static int i_ipmi_set_timeout(struct ipmi_smi_msg  *smi_msg,
 	int                               hbnow = 0;
 
 
-	/* These can be cleared as we are setting the timeout. */
-	pretimeout_since_last_heartbeat = 0;
-
 	data[0] = 0;
 	WDOG_SET_TIMER_USE(data[0], WDOG_TIMER_USE_SMS_OS);
 
@@ -414,46 +406,48 @@ static int i_ipmi_set_timeout(struct ipmi_smi_msg  *smi_msg,
 				      smi_msg,
 				      recv_msg,
 				      1);
-	if (rv) {
-		printk(KERN_WARNING PFX "set timeout error: %d\n",
-		       rv);
-	}
-
-	if (send_heartbeat_now)
-	    *send_heartbeat_now = hbnow;
+	if (rv)
+		pr_warn(PFX "set timeout error: %d\n", rv);
+	else if (send_heartbeat_now)
+		*send_heartbeat_now = hbnow;
 
 	return rv;
 }
 
-static int ipmi_set_timeout(int do_heartbeat)
+static int _ipmi_set_timeout(int do_heartbeat)
 {
 	int send_heartbeat_now;
 	int rv;
 
+	if (!watchdog_user)
+		return -ENODEV;
 
-	/* We can only send one of these at a time. */
-	mutex_lock(&set_timeout_lock);
-
-	atomic_set(&set_timeout_tofree, 2);
+	atomic_set(&msg_tofree, 2);
 
-	rv = i_ipmi_set_timeout(&set_timeout_smi_msg,
-				&set_timeout_recv_msg,
+	rv = __ipmi_set_timeout(&smi_msg,
+				&recv_msg,
 				&send_heartbeat_now);
-	if (rv) {
-		mutex_unlock(&set_timeout_lock);
-		goto out;
-	}
-
-	wait_for_completion(&set_timeout_wait);
+	if (rv)
+		return rv;
 
-	mutex_unlock(&set_timeout_lock);
+	wait_for_completion(&msg_wait);
 
 	if ((do_heartbeat == IPMI_SET_TIMEOUT_FORCE_HB)
-	    || ((send_heartbeat_now)
-		&& (do_heartbeat == IPMI_SET_TIMEOUT_HB_IF_NECESSARY)))
-		rv = ipmi_heartbeat();
+		|| ((send_heartbeat_now)
+		    && (do_heartbeat == IPMI_SET_TIMEOUT_HB_IF_NECESSARY)))
+		rv = __ipmi_heartbeat();
+
+	return rv;
+}
+
+static int ipmi_set_timeout(int do_heartbeat)
+{
+	int rv;
+
+	mutex_lock(&ipmi_watchdog_mutex);
+	rv = _ipmi_set_timeout(do_heartbeat);
+	mutex_unlock(&ipmi_watchdog_mutex);
 
-out:
 	return rv;
 }
 
@@ -531,13 +525,12 @@ static void panic_halt_ipmi_set_timeout(void)
 	while (atomic_read(&panic_done_count) != 0)
 		ipmi_poll_interface(watchdog_user);
 	atomic_add(1, &panic_done_count);
-	rv = i_ipmi_set_timeout(&panic_halt_smi_msg,
+	rv = __ipmi_set_timeout(&panic_halt_smi_msg,
 				&panic_halt_recv_msg,
 				&send_heartbeat_now);
 	if (rv) {
 		atomic_sub(1, &panic_done_count);
-		printk(KERN_WARNING PFX
-		       "Unable to extend the watchdog timeout.");
+		pr_warn(PFX "Unable to extend the watchdog timeout.");
 	} else {
 		if (send_heartbeat_now)
 			panic_halt_ipmi_heartbeat();
@@ -546,69 +539,22 @@ static void panic_halt_ipmi_set_timeout(void)
 		ipmi_poll_interface(watchdog_user);
 }
 
-/*
- * We use a mutex to make sure that only one thing can send a
- * heartbeat at one time, because we only have one copy of the data.
- * The semaphore is claimed when the set_timeout is sent and freed
- * when both messages are free.
- */
-static atomic_t heartbeat_tofree = ATOMIC_INIT(0);
-static DEFINE_MUTEX(heartbeat_lock);
-static DECLARE_COMPLETION(heartbeat_wait);
-static void heartbeat_free_smi(struct ipmi_smi_msg *msg)
-{
-    if (atomic_dec_and_test(&heartbeat_tofree))
-	    complete(&heartbeat_wait);
-}
-static void heartbeat_free_recv(struct ipmi_recv_msg *msg)
-{
-    if (atomic_dec_and_test(&heartbeat_tofree))
-	    complete(&heartbeat_wait);
-}
-static struct ipmi_smi_msg heartbeat_smi_msg = {
-	.done = heartbeat_free_smi
-};
-static struct ipmi_recv_msg heartbeat_recv_msg = {
-	.done = heartbeat_free_recv
-};
-
-static int ipmi_heartbeat(void)
+static int __ipmi_heartbeat(void)
 {
-	struct kernel_ipmi_msg            msg;
-	int                               rv;
+	struct kernel_ipmi_msg msg;
+	int rv;
 	struct ipmi_system_interface_addr addr;
-	int				  timeout_retries = 0;
-
-	if (ipmi_ignore_heartbeat)
-		return 0;
-
-	if (ipmi_start_timer_on_heartbeat) {
-		ipmi_start_timer_on_heartbeat = 0;
-		ipmi_watchdog_state = action_val;
-		return ipmi_set_timeout(IPMI_SET_TIMEOUT_FORCE_HB);
-	} else if (pretimeout_since_last_heartbeat) {
-		/*
-		 * A pretimeout occurred, make sure we set the timeout.
-		 * We don't want to set the action, though, we want to
-		 * leave that alone (thus it can't be combined with the
-		 * above operation.
-		 */
-		return ipmi_set_timeout(IPMI_SET_TIMEOUT_HB_IF_NECESSARY);
-	}
-
-	mutex_lock(&heartbeat_lock);
+	int timeout_retries = 0;
 
 restart:
-	atomic_set(&heartbeat_tofree, 2);
-
 	/*
 	 * Don't reset the timer if we have the timer turned off, that
 	 * re-enables the watchdog.
 	 */
-	if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE) {
-		mutex_unlock(&heartbeat_lock);
+	if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE)
 		return 0;
-	}
+
+	atomic_set(&msg_tofree, 2);
 
 	addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
 	addr.channel = IPMI_BMC_CHANNEL;
@@ -623,26 +569,23 @@ restart:
 				      0,
 				      &msg,
 				      NULL,
-				      &heartbeat_smi_msg,
-				      &heartbeat_recv_msg,
+				      &smi_msg,
+				      &recv_msg,
 				      1);
 	if (rv) {
-		mutex_unlock(&heartbeat_lock);
-		printk(KERN_WARNING PFX "heartbeat failure: %d\n",
-		       rv);
+		pr_warn(PFX "heartbeat send failure: %d\n", rv);
 		return rv;
 	}
 
 	/* Wait for the heartbeat to be sent. */
-	wait_for_completion(&heartbeat_wait);
+	wait_for_completion(&msg_wait);
 
-	if (heartbeat_recv_msg.msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP)  {
+	if (recv_msg.msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP)  {
 		timeout_retries++;
 		if (timeout_retries > 3) {
-			printk(KERN_ERR PFX ": Unable to restore the IPMI"
-			       " watchdog's settings, giving up.\n");
+			pr_err(PFX ": Unable to restore the IPMI watchdog's settings, giving up.\n");
 			rv = -EIO;
-			goto out_unlock;
+			goto out;
 		}
 
 		/*
@@ -651,18 +594,17 @@ restart:
 		 * to restore the timer's info.  Note that we still hold
 		 * the heartbeat lock, to keep a heartbeat from happening
 		 * in this process, so must say no heartbeat to avoid a
-		 * deadlock on this mutex.
+		 * deadlock on this mutex
 		 */
-		rv = ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
+		rv = _ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
 		if (rv) {
-			printk(KERN_ERR PFX ": Unable to send the command to"
-			       " set the watchdog's settings, giving up.\n");
-			goto out_unlock;
+			pr_err(PFX ": Unable to send the command to set the watchdog's settings, giving up.\n");
+			goto out;
 		}
 
-		/* We might need a new heartbeat, so do it now */
+		/* Might need a heartbeat send, go ahead and do it. */
 		goto restart;
-	} else if (heartbeat_recv_msg.msg.data[0] != 0) {
+	} else if (recv_msg.msg.data[0] != 0) {
 		/*
 		 * Got an error in the heartbeat response.  It was already
 		 * reported in ipmi_wdog_msg_handler, but we should return
@@ -671,8 +613,43 @@ restart:
 		rv = -EINVAL;
 	}
 
-out_unlock:
-	mutex_unlock(&heartbeat_lock);
+out:
+	return rv;
+}
+
+static int _ipmi_heartbeat(void)
+{
+	int rv;
+
+	if (!watchdog_user)
+		return -ENODEV;
+
+	if (ipmi_start_timer_on_heartbeat) {
+		ipmi_start_timer_on_heartbeat = 0;
+		ipmi_watchdog_state = action_val;
+		rv = _ipmi_set_timeout(IPMI_SET_TIMEOUT_FORCE_HB);
+	} else if (atomic_cmpxchg(&pretimeout_since_last_heartbeat, 1, 0)) {
+		/*
+		 * A pretimeout occurred, make sure we set the timeout.
+		 * We don't want to set the action, though, we want to
+		 * leave that alone (thus it can't be combined with the
+		 * above operation.
+		 */
+		rv = _ipmi_set_timeout(IPMI_SET_TIMEOUT_HB_IF_NECESSARY);
+	} else {
+		rv = __ipmi_heartbeat();
+	}
+
+	return rv;
+}
+
+static int ipmi_heartbeat(void)
+{
+	int rv;
+
+	mutex_lock(&ipmi_watchdog_mutex);
+	rv = _ipmi_heartbeat();
+	mutex_unlock(&ipmi_watchdog_mutex);
 
 	return rv;
 }
@@ -700,7 +677,7 @@ static int ipmi_ioctl(struct file *file,
 		if (i)
 			return -EFAULT;
 		timeout = val;
-		return ipmi_set_timeout(IPMI_SET_TIMEOUT_HB_IF_NECESSARY);
+		return _ipmi_set_timeout(IPMI_SET_TIMEOUT_HB_IF_NECESSARY);
 
 	case WDIOC_GETTIMEOUT:
 		i = copy_to_user(argp, &timeout, sizeof(timeout));
@@ -713,7 +690,7 @@ static int ipmi_ioctl(struct file *file,
 		if (i)
 			return -EFAULT;
 		pretimeout = val;
-		return ipmi_set_timeout(IPMI_SET_TIMEOUT_HB_IF_NECESSARY);
+		return _ipmi_set_timeout(IPMI_SET_TIMEOUT_HB_IF_NECESSARY);
 
 	case WDIOC_GETPRETIMEOUT:
 		i = copy_to_user(argp, &pretimeout, sizeof(pretimeout));
@@ -722,7 +699,7 @@ static int ipmi_ioctl(struct file *file,
 		return 0;
 
 	case WDIOC_KEEPALIVE:
-		return ipmi_heartbeat();
+		return _ipmi_heartbeat();
 
 	case WDIOC_SETOPTIONS:
 		i = copy_from_user(&val, argp, sizeof(int));
@@ -730,13 +707,13 @@ static int ipmi_ioctl(struct file *file,
 			return -EFAULT;
 		if (val & WDIOS_DISABLECARD) {
 			ipmi_watchdog_state = WDOG_TIMEOUT_NONE;
-			ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
+			_ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
 			ipmi_start_timer_on_heartbeat = 0;
 		}
 
 		if (val & WDIOS_ENABLECARD) {
 			ipmi_watchdog_state = action_val;
-			ipmi_set_timeout(IPMI_SET_TIMEOUT_FORCE_HB);
+			_ipmi_set_timeout(IPMI_SET_TIMEOUT_FORCE_HB);
 		}
 		return 0;
 
@@ -810,7 +787,7 @@ static ssize_t ipmi_read(struct file *file,
 	 * Reading returns if the pretimeout has gone off, and it only does
 	 * it once per pretimeout.
 	 */
-	spin_lock(&ipmi_read_lock);
+	spin_lock_irq(&ipmi_read_lock);
 	if (!data_to_read) {
 		if (file->f_flags & O_NONBLOCK) {
 			rv = -EAGAIN;
@@ -821,9 +798,9 @@ static ssize_t ipmi_read(struct file *file,
 		add_wait_queue(&read_q, &wait);
 		while (!data_to_read) {
 			set_current_state(TASK_INTERRUPTIBLE);
-			spin_unlock(&ipmi_read_lock);
+			spin_unlock_irq(&ipmi_read_lock);
 			schedule();
-			spin_lock(&ipmi_read_lock);
+			spin_lock_irq(&ipmi_read_lock);
 		}
 		remove_wait_queue(&read_q, &wait);
 
@@ -835,7 +812,7 @@ static ssize_t ipmi_read(struct file *file,
 	data_to_read = 0;
 
  out:
-	spin_unlock(&ipmi_read_lock);
+	spin_unlock_irq(&ipmi_read_lock);
 
 	if (rv == 0) {
 		if (copy_to_user(buf, &data_to_read, 1))
@@ -873,10 +850,10 @@ static __poll_t ipmi_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &read_q, wait);
 
-	spin_lock(&ipmi_read_lock);
+	spin_lock_irq(&ipmi_read_lock);
 	if (data_to_read)
 		mask |= (EPOLLIN | EPOLLRDNORM);
-	spin_unlock(&ipmi_read_lock);
+	spin_unlock_irq(&ipmi_read_lock);
 
 	return mask;
 }
@@ -894,11 +871,13 @@ static int ipmi_close(struct inode *ino, struct file *filep)
 {
 	if (iminor(ino) == WATCHDOG_MINOR) {
 		if (expect_close == 42) {
+			mutex_lock(&ipmi_watchdog_mutex);
 			ipmi_watchdog_state = WDOG_TIMEOUT_NONE;
-			ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
+			_ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
+			mutex_unlock(&ipmi_watchdog_mutex);
 		} else {
-			printk(KERN_CRIT PFX
-			       "Unexpected close, not stopping watchdog!\n");
+			pr_crit(PFX
+				"Unexpected close, not stopping watchdog!\n");
 			ipmi_heartbeat();
 		}
 		clear_bit(0, &ipmi_wdog_open);
@@ -932,11 +911,9 @@ static void ipmi_wdog_msg_handler(struct ipmi_recv_msg *msg,
 {
 	if (msg->msg.cmd == IPMI_WDOG_RESET_TIMER &&
 			msg->msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP)
-		printk(KERN_INFO PFX "response: The IPMI controller appears"
-		       " to have been reset, will attempt to reinitialize"
-		       " the watchdog timer\n");
+		pr_info(PFX "response: The IPMI controller appears to have been reset, will attempt to reinitialize the watchdog timer\n");
 	else if (msg->msg.data[0] != 0)
-		printk(KERN_ERR PFX "response: Error %x on cmd %x\n",
+		pr_err(PFX "response: Error %x on cmd %x\n",
 		       msg->msg.data[0],
 		       msg->msg.cmd);
 
@@ -950,12 +927,13 @@ static void ipmi_wdog_pretimeout_handler(void *handler_data)
 			if (atomic_inc_and_test(&preop_panic_excl))
 				panic("Watchdog pre-timeout");
 		} else if (preop_val == WDOG_PREOP_GIVE_DATA) {
-			spin_lock(&ipmi_read_lock);
+			unsigned long flags;
+
+			spin_lock_irqsave(&ipmi_read_lock, flags);
 			data_to_read = 1;
 			wake_up_interruptible(&read_q);
 			kill_fasync(&fasync_q, SIGIO, POLL_IN);
-
-			spin_unlock(&ipmi_read_lock);
+			spin_unlock_irqrestore(&ipmi_read_lock, flags);
 		}
 	}
 
@@ -963,12 +941,34 @@ static void ipmi_wdog_pretimeout_handler(void *handler_data)
 	 * On some machines, the heartbeat will give an error and not
 	 * work unless we re-enable the timer.  So do so.
 	 */
-	pretimeout_since_last_heartbeat = 1;
+	atomic_set(&pretimeout_since_last_heartbeat, 1);
+}
+
+static void ipmi_wdog_panic_handler(void *user_data)
+{
+	static int panic_event_handled;
+
+	/*
+	 * On a panic, if we have a panic timeout, make sure to extend
+	 * the watchdog timer to a reasonable value to complete the
+	 * panic, if the watchdog timer is running.  Plus the
+	 * pretimeout is meaningless at panic time.
+	 */
+	if (watchdog_user && !panic_event_handled &&
+	    ipmi_watchdog_state != WDOG_TIMEOUT_NONE) {
+		/* Make sure we do this only once. */
+		panic_event_handled = 1;
+
+		timeout = panic_wdt_timeout;
+		pretimeout = 0;
+		panic_halt_ipmi_set_timeout();
+	}
 }
 
 static const struct ipmi_user_hndl ipmi_hndlrs = {
 	.ipmi_recv_hndl           = ipmi_wdog_msg_handler,
-	.ipmi_watchdog_pretimeout = ipmi_wdog_pretimeout_handler
+	.ipmi_watchdog_pretimeout = ipmi_wdog_pretimeout_handler,
+	.ipmi_panic_handler       = ipmi_wdog_panic_handler
 };
 
 static void ipmi_register_watchdog(int ipmi_intf)
@@ -985,7 +985,7 @@ static void ipmi_register_watchdog(int ipmi_intf)
 
 	rv = ipmi_create_user(ipmi_intf, &ipmi_hndlrs, NULL, &watchdog_user);
 	if (rv < 0) {
-		printk(KERN_CRIT PFX "Unable to register with ipmi\n");
+		pr_crit(PFX "Unable to register with ipmi\n");
 		goto out;
 	}
 
@@ -1002,7 +1002,7 @@ static void ipmi_register_watchdog(int ipmi_intf)
 	if (rv < 0) {
 		ipmi_destroy_user(watchdog_user);
 		watchdog_user = NULL;
-		printk(KERN_CRIT PFX "Unable to register misc device\n");
+		pr_crit(PFX "Unable to register misc device\n");
 	}
 
 #ifdef HAVE_DIE_NMI
@@ -1024,9 +1024,8 @@ static void ipmi_register_watchdog(int ipmi_intf)
 
 		rv = ipmi_set_timeout(IPMI_SET_TIMEOUT_FORCE_HB);
 		if (rv) {
-			printk(KERN_WARNING PFX "Error starting timer to"
-			       " test NMI: 0x%x.  The NMI pretimeout will"
-			       " likely not work\n", rv);
+			pr_warn(PFX "Error starting timer to test NMI: 0x%x.  The NMI pretimeout will likely not work\n",
+				rv);
 			rv = 0;
 			goto out_restore;
 		}
@@ -1034,9 +1033,7 @@ static void ipmi_register_watchdog(int ipmi_intf)
 		msleep(1500);
 
 		if (testing_nmi != 2) {
-			printk(KERN_WARNING PFX "IPMI NMI didn't seem to"
-			       " occur.  The NMI pretimeout will"
-			       " likely not work\n");
+			pr_warn(PFX "IPMI NMI didn't seem to occur.  The NMI pretimeout will likely not work\n");
 		}
  out_restore:
 		testing_nmi = 0;
@@ -1052,7 +1049,7 @@ static void ipmi_register_watchdog(int ipmi_intf)
 		start_now = 0; /* Disable this function after first startup. */
 		ipmi_watchdog_state = action_val;
 		ipmi_set_timeout(IPMI_SET_TIMEOUT_FORCE_HB);
-		printk(KERN_INFO PFX "Starting now!\n");
+		pr_info(PFX "Starting now!\n");
 	} else {
 		/* Stop the timer now. */
 		ipmi_watchdog_state = WDOG_TIMEOUT_NONE;
@@ -1063,34 +1060,38 @@ static void ipmi_register_watchdog(int ipmi_intf)
 static void ipmi_unregister_watchdog(int ipmi_intf)
 {
 	int rv;
+	struct ipmi_user *loc_user = watchdog_user;
 
-	if (!watchdog_user)
-		goto out;
+	if (!loc_user)
+		return;
 
 	if (watchdog_ifnum != ipmi_intf)
-		goto out;
+		return;
 
 	/* Make sure no one can call us any more. */
 	misc_deregister(&ipmi_wdog_miscdev);
 
+	watchdog_user = NULL;
+
 	/*
 	 * Wait to make sure the message makes it out.  The lower layer has
 	 * pointers to our buffers, we want to make sure they are done before
 	 * we release our memory.
 	 */
-	while (atomic_read(&set_timeout_tofree))
-		schedule_timeout_uninterruptible(1);
+	while (atomic_read(&msg_tofree))
+		msg_free_smi(NULL);
+
+	mutex_lock(&ipmi_watchdog_mutex);
 
 	/* Disconnect from IPMI. */
-	rv = ipmi_destroy_user(watchdog_user);
-	if (rv) {
-		printk(KERN_WARNING PFX "error unlinking from IPMI: %d\n",
-		       rv);
-	}
-	watchdog_user = NULL;
+	rv = ipmi_destroy_user(loc_user);
+	if (rv)
+		pr_warn(PFX "error unlinking from IPMI: %d\n",  rv);
 
- out:
-	return;
+	/* If it comes back, restart it properly. */
+	ipmi_start_timer_on_heartbeat = 1;
+
+	mutex_unlock(&ipmi_watchdog_mutex);
 }
 
 #ifdef HAVE_DIE_NMI
@@ -1124,7 +1125,7 @@ ipmi_nmi(unsigned int val, struct pt_regs *regs)
 		/* On some machines, the heartbeat will give
 		   an error and not work unless we re-enable
 		   the timer.   So do so. */
-		pretimeout_since_last_heartbeat = 1;
+		atomic_set(&pretimeout_since_last_heartbeat, 1);
 		if (atomic_inc_and_test(&preop_panic_excl))
 			nmi_panic(regs, PFX "pre-timeout");
 	}
@@ -1167,36 +1168,6 @@ static struct notifier_block wdog_reboot_notifier = {
 	.priority	= 0
 };
 
-static int wdog_panic_handler(struct notifier_block *this,
-			      unsigned long         event,
-			      void                  *unused)
-{
-	static int panic_event_handled;
-
-	/* On a panic, if we have a panic timeout, make sure to extend
-	   the watchdog timer to a reasonable value to complete the
-	   panic, if the watchdog timer is running.  Plus the
-	   pretimeout is meaningless at panic time. */
-	if (watchdog_user && !panic_event_handled &&
-	    ipmi_watchdog_state != WDOG_TIMEOUT_NONE) {
-		/* Make sure we do this only once. */
-		panic_event_handled = 1;
-
-		timeout = panic_wdt_timeout;
-		pretimeout = 0;
-		panic_halt_ipmi_set_timeout();
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block wdog_panic_notifier = {
-	.notifier_call	= wdog_panic_handler,
-	.next		= NULL,
-	.priority	= 150	/* priority: INT_MAX >= x >= 0 */
-};
-
-
 static void ipmi_new_smi(int if_num, struct device *device)
 {
 	ipmi_register_watchdog(if_num);
@@ -1288,9 +1259,7 @@ static void check_parms(void)
 	if (preaction_val == WDOG_PRETIMEOUT_NMI) {
 		do_nmi = 1;
 		if (preop_val == WDOG_PREOP_GIVE_DATA) {
-			printk(KERN_WARNING PFX "Pretimeout op is to give data"
-			       " but NMI pretimeout is enabled, setting"
-			       " pretimeout op to none\n");
+			pr_warn(PFX "Pretimeout op is to give data but NMI pretimeout is enabled, setting pretimeout op to none\n");
 			preop_op("preop_none", NULL);
 			do_nmi = 0;
 		}
@@ -1299,8 +1268,7 @@ static void check_parms(void)
 		rv = register_nmi_handler(NMI_UNKNOWN, ipmi_nmi, 0,
 						"ipmi");
 		if (rv) {
-			printk(KERN_WARNING PFX
-			       "Can't register nmi handler\n");
+			pr_warn(PFX "Can't register nmi handler\n");
 			return;
 		} else
 			nmi_handler_registered = 1;
@@ -1317,27 +1285,24 @@ static int __init ipmi_wdog_init(void)
 
 	if (action_op(action, NULL)) {
 		action_op("reset", NULL);
-		printk(KERN_INFO PFX "Unknown action '%s', defaulting to"
-		       " reset\n", action);
+		pr_info(PFX "Unknown action '%s', defaulting to reset\n",
+			action);
 	}
 
 	if (preaction_op(preaction, NULL)) {
 		preaction_op("pre_none", NULL);
-		printk(KERN_INFO PFX "Unknown preaction '%s', defaulting to"
-		       " none\n", preaction);
+		pr_info(PFX "Unknown preaction '%s', defaulting to none\n",
+			preaction);
 	}
 
 	if (preop_op(preop, NULL)) {
 		preop_op("preop_none", NULL);
-		printk(KERN_INFO PFX "Unknown preop '%s', defaulting to"
-		       " none\n", preop);
+		pr_info(PFX "Unknown preop '%s', defaulting to none\n", preop);
 	}
 
 	check_parms();
 
 	register_reboot_notifier(&wdog_reboot_notifier);
-	atomic_notifier_chain_register(&panic_notifier_list,
-			&wdog_panic_notifier);
 
 	rv = ipmi_smi_watcher_register(&smi_watcher);
 	if (rv) {
@@ -1345,14 +1310,12 @@ static int __init ipmi_wdog_init(void)
 		if (nmi_handler_registered)
 			unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
 #endif
-		atomic_notifier_chain_unregister(&panic_notifier_list,
-						 &wdog_panic_notifier);
 		unregister_reboot_notifier(&wdog_reboot_notifier);
-		printk(KERN_WARNING PFX "can't register smi watcher\n");
+		pr_warn(PFX "can't register smi watcher\n");
 		return rv;
 	}
 
-	printk(KERN_INFO PFX "driver initialized\n");
+	pr_info(PFX "driver initialized\n");
 
 	return 0;
 }
@@ -1367,8 +1330,6 @@ static void __exit ipmi_wdog_exit(void)
 		unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
 #endif
 
-	atomic_notifier_chain_unregister(&panic_notifier_list,
-					 &wdog_panic_notifier);
 	unregister_reboot_notifier(&wdog_reboot_notifier);
 }
 module_exit(ipmi_wdog_exit);
diff --git a/drivers/char/ipmi/kcs_bmc_npcm7xx.c b/drivers/char/ipmi/kcs_bmc_npcm7xx.c
new file mode 100644
index 000000000000..722f7391fe1f
--- /dev/null
+++ b/drivers/char/ipmi/kcs_bmc_npcm7xx.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, Nuvoton Corporation.
+ * Copyright (c) 2018, Intel Corporation.
+ */
+
+#define pr_fmt(fmt) "nuvoton-kcs-bmc: " fmt
+
+#include <linux/atomic.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include "kcs_bmc.h"
+
+#define DEVICE_NAME	"npcm-kcs-bmc"
+#define KCS_CHANNEL_MAX	3
+
+#define KCS1ST		0x0C
+#define KCS2ST		0x1E
+#define KCS3ST		0x30
+
+#define KCS1DO		0x0E
+#define KCS2DO		0x20
+#define KCS3DO		0x32
+
+#define KCS1DI		0x10
+#define KCS2DI		0x22
+#define KCS3DI		0x34
+
+#define KCS1CTL		0x18
+#define KCS2CTL		0x2A
+#define KCS3CTL		0x3C
+#define    KCS_CTL_IBFIE	BIT(0)
+
+#define KCS1IE		0x1C
+#define KCS2IE		0x2E
+#define KCS3IE		0x40
+#define    KCS_IE_IRQE          BIT(0)
+#define    KCS_IE_HIRQE         BIT(3)
+
+/*
+ * 7.2.4 Core KCS Registers
+ * Registers in this module are 8 bits. An 8-bit register must be accessed
+ * by an 8-bit read or write.
+ *
+ * sts: KCS Channel n Status Register (KCSnST).
+ * dob: KCS Channel n Data Out Buffer Register (KCSnDO).
+ * dib: KCS Channel n Data In Buffer Register (KCSnDI).
+ * ctl: KCS Channel n Control Register (KCSnCTL).
+ * ie : KCS Channel n  Interrupt Enable Register (KCSnIE).
+ */
+struct npcm7xx_kcs_reg {
+	u32 sts;
+	u32 dob;
+	u32 dib;
+	u32 ctl;
+	u32 ie;
+};
+
+struct npcm7xx_kcs_bmc {
+	struct regmap *map;
+
+	const struct npcm7xx_kcs_reg *reg;
+};
+
+static const struct npcm7xx_kcs_reg npcm7xx_kcs_reg_tbl[KCS_CHANNEL_MAX] = {
+	{ .sts = KCS1ST, .dob = KCS1DO, .dib = KCS1DI, .ctl = KCS1CTL, .ie = KCS1IE },
+	{ .sts = KCS2ST, .dob = KCS2DO, .dib = KCS2DI, .ctl = KCS2CTL, .ie = KCS2IE },
+	{ .sts = KCS3ST, .dob = KCS3DO, .dib = KCS3DI, .ctl = KCS3CTL, .ie = KCS3IE },
+};
+
+static u8 npcm7xx_kcs_inb(struct kcs_bmc *kcs_bmc, u32 reg)
+{
+	struct npcm7xx_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc);
+	u32 val = 0;
+	int rc;
+
+	rc = regmap_read(priv->map, reg, &val);
+	WARN(rc != 0, "regmap_read() failed: %d\n", rc);
+
+	return rc == 0 ? (u8)val : 0;
+}
+
+static void npcm7xx_kcs_outb(struct kcs_bmc *kcs_bmc, u32 reg, u8 data)
+{
+	struct npcm7xx_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc);
+	int rc;
+
+	rc = regmap_write(priv->map, reg, data);
+	WARN(rc != 0, "regmap_write() failed: %d\n", rc);
+}
+
+static void npcm7xx_kcs_enable_channel(struct kcs_bmc *kcs_bmc, bool enable)
+{
+	struct npcm7xx_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc);
+
+	regmap_update_bits(priv->map, priv->reg->ctl, KCS_CTL_IBFIE,
+			   enable ? KCS_CTL_IBFIE : 0);
+
+	regmap_update_bits(priv->map, priv->reg->ie, KCS_IE_IRQE | KCS_IE_HIRQE,
+			   enable ? KCS_IE_IRQE | KCS_IE_HIRQE : 0);
+}
+
+static irqreturn_t npcm7xx_kcs_irq(int irq, void *arg)
+{
+	struct kcs_bmc *kcs_bmc = arg;
+
+	if (!kcs_bmc_handle_event(kcs_bmc))
+		return IRQ_HANDLED;
+
+	return IRQ_NONE;
+}
+
+static int npcm7xx_kcs_config_irq(struct kcs_bmc *kcs_bmc,
+				  struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	int irq;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	return devm_request_irq(dev, irq, npcm7xx_kcs_irq, IRQF_SHARED,
+				dev_name(dev), kcs_bmc);
+}
+
+static int npcm7xx_kcs_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct npcm7xx_kcs_bmc *priv;
+	struct kcs_bmc *kcs_bmc;
+	u32 chan;
+	int rc;
+
+	rc = of_property_read_u32(dev->of_node, "kcs_chan", &chan);
+	if (rc != 0 || chan == 0 || chan > KCS_CHANNEL_MAX) {
+		dev_err(dev, "no valid 'kcs_chan' configured\n");
+		return -ENODEV;
+	}
+
+	kcs_bmc = kcs_bmc_alloc(dev, sizeof(*priv), chan);
+	if (!kcs_bmc)
+		return -ENOMEM;
+
+	priv = kcs_bmc_priv(kcs_bmc);
+	priv->map = syscon_node_to_regmap(dev->parent->of_node);
+	if (IS_ERR(priv->map)) {
+		dev_err(dev, "Couldn't get regmap\n");
+		return -ENODEV;
+	}
+	priv->reg = &npcm7xx_kcs_reg_tbl[chan - 1];
+
+	kcs_bmc->ioreg.idr = priv->reg->dib;
+	kcs_bmc->ioreg.odr = priv->reg->dob;
+	kcs_bmc->ioreg.str = priv->reg->sts;
+	kcs_bmc->io_inputb = npcm7xx_kcs_inb;
+	kcs_bmc->io_outputb = npcm7xx_kcs_outb;
+
+	dev_set_drvdata(dev, kcs_bmc);
+
+	npcm7xx_kcs_enable_channel(kcs_bmc, true);
+	rc = npcm7xx_kcs_config_irq(kcs_bmc, pdev);
+	if (rc)
+		return rc;
+
+	rc = misc_register(&kcs_bmc->miscdev);
+	if (rc) {
+		dev_err(dev, "Unable to register device\n");
+		return rc;
+	}
+
+	pr_info("channel=%u idr=0x%x odr=0x%x str=0x%x\n",
+		chan,
+		kcs_bmc->ioreg.idr, kcs_bmc->ioreg.odr, kcs_bmc->ioreg.str);
+
+	return 0;
+}
+
+static int npcm7xx_kcs_remove(struct platform_device *pdev)
+{
+	struct kcs_bmc *kcs_bmc = dev_get_drvdata(&pdev->dev);
+
+	misc_deregister(&kcs_bmc->miscdev);
+
+	return 0;
+}
+
+static const struct of_device_id npcm_kcs_bmc_match[] = {
+	{ .compatible = "nuvoton,npcm750-kcs-bmc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, npcm_kcs_bmc_match);
+
+static struct platform_driver npcm_kcs_bmc_driver = {
+	.driver = {
+		.name		= DEVICE_NAME,
+		.of_match_table	= npcm_kcs_bmc_match,
+	},
+	.probe	= npcm7xx_kcs_probe,
+	.remove	= npcm7xx_kcs_remove,
+};
+module_platform_driver(npcm_kcs_bmc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Avi Fishman <avifishman70@gmail.com>");
+MODULE_AUTHOR("Haiyue Wang <haiyue.wang@linux.intel.com>");
+MODULE_DESCRIPTION("NPCM7xx device interface to the KCS BMC device");
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index 1bb9e7cc82e3..53cfe574d8d4 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -95,19 +95,6 @@ static const struct seq_operations misc_seq_ops = {
 	.stop  = misc_seq_stop,
 	.show  = misc_seq_show,
 };
-
-static int misc_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &misc_seq_ops);
-}
-
-static const struct file_operations misc_proc_fops = {
-	.owner	 = THIS_MODULE,
-	.open    = misc_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-};
 #endif
 
 static int misc_open(struct inode *inode, struct file *file)
@@ -282,7 +269,7 @@ static int __init misc_init(void)
 	int err;
 	struct proc_dir_entry *ret;
 
-	ret = proc_create("misc", 0, NULL, &misc_proc_fops);
+	ret = proc_create_seq("misc", 0, NULL, &misc_seq_ops);
 	misc_class = class_create(THIS_MODULE, "misc");
 	err = PTR_ERR(misc_class);
 	if (IS_ERR(misc_class))
diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c
index 7b75669d3670..058876b55b09 100644
--- a/drivers/char/mspec.c
+++ b/drivers/char/mspec.c
@@ -191,7 +191,7 @@ mspec_close(struct vm_area_struct *vma)
  *
  * Creates a mspec page and maps it to user space.
  */
-static int
+static vm_fault_t
 mspec_fault(struct vm_fault *vmf)
 {
 	unsigned long paddr, maddr;
@@ -223,14 +223,7 @@ mspec_fault(struct vm_fault *vmf)
 
 	pfn = paddr >> PAGE_SHIFT;
 
-	/*
-	 * vm_insert_pfn can fail with -EBUSY, but in that case it will
-	 * be because another thread has installed the pte first, so it
-	 * is no problem.
-	 */
-	vm_insert_pfn(vmf->vma, vmf->address, pfn);
-
-	return VM_FAULT_NOPAGE;
+	return vmf_insert_pfn(vmf->vma, vmf->address, pfn);
 }
 
 static const struct vm_operations_struct mspec_vm_ops = {
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index 678fa97e41fb..25264d65e716 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -389,22 +389,9 @@ static int nvram_proc_read(struct seq_file *seq, void *offset)
 	return 0;
 }
 
-static int nvram_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, nvram_proc_read, NULL);
-}
-
-static const struct file_operations nvram_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= nvram_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int nvram_add_proc_fs(void)
 {
-	if (!proc_create("driver/nvram", 0, NULL, &nvram_proc_fops))
+	if (!proc_create_single("driver/nvram", 0, NULL, nvram_proc_read))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index aa502e9fb7fa..66b04194aa9f 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -2616,19 +2616,6 @@ static int mgslpc_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int mgslpc_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mgslpc_proc_show, NULL);
-}
-
-static const struct file_operations mgslpc_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= mgslpc_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int rx_alloc_buffers(MGSLPC_INFO *info)
 {
 	/* each buffer has header and data */
@@ -2815,7 +2802,7 @@ static const struct tty_operations mgslpc_ops = {
 	.tiocmget = tiocmget,
 	.tiocmset = tiocmset,
 	.get_icount = mgslpc_get_icount,
-	.proc_fops = &mgslpc_proc_fops,
+	.proc_show = mgslpc_proc_show,
 };
 
 static int __init synclink_cs_init(void)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index e027e7fa1472..a8fb0020ba5c 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -261,6 +261,7 @@
 #include <linux/ptrace.h>
 #include <linux/workqueue.h>
 #include <linux/irq.h>
+#include <linux/ratelimit.h>
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
@@ -401,8 +402,7 @@ static struct poolinfo {
 /*
  * Static global variables
  */
-static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
-static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_wait);
 static struct fasync_struct *fasync;
 
 static DEFINE_SPINLOCK(random_ready_list_lock);
@@ -427,8 +427,9 @@ struct crng_state primary_crng = {
  * its value (from 0->1->2).
  */
 static int crng_init = 0;
-#define crng_ready() (likely(crng_init > 0))
+#define crng_ready() (likely(crng_init > 1))
 static int crng_init_cnt = 0;
+static unsigned long crng_global_init_time = 0;
 #define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
 static void _extract_crng(struct crng_state *crng,
 			  __u32 out[CHACHA20_BLOCK_WORDS]);
@@ -437,6 +438,16 @@ static void _crng_backtrack_protect(struct crng_state *crng,
 static void process_random_ready_list(void);
 static void _get_random_bytes(void *buf, int nbytes);
 
+static struct ratelimit_state unseeded_warning =
+	RATELIMIT_STATE_INIT("warn_unseeded_randomness", HZ, 3);
+static struct ratelimit_state urandom_warning =
+	RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3);
+
+static int ratelimit_disable __read_mostly;
+
+module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
+MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
+
 /**********************************************************************
  *
  * OS independent entropy store.   Here are the functions which handle
@@ -710,8 +721,8 @@ retry:
 
 		/* should we wake readers? */
 		if (entropy_bits >= random_read_wakeup_bits &&
-		    wq_has_sleeper(&random_read_wait)) {
-			wake_up_interruptible(&random_read_wait);
+		    wq_has_sleeper(&random_wait)) {
+			wake_up_interruptible_poll(&random_wait, POLLIN);
 			kill_fasync(&fasync, SIGIO, POLL_IN);
 		}
 		/* If the input pool is getting full, send some
@@ -787,6 +798,43 @@ static void crng_initialize(struct crng_state *crng)
 	crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
 }
 
+#ifdef CONFIG_NUMA
+static void do_numa_crng_init(struct work_struct *work)
+{
+	int i;
+	struct crng_state *crng;
+	struct crng_state **pool;
+
+	pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
+	for_each_online_node(i) {
+		crng = kmalloc_node(sizeof(struct crng_state),
+				    GFP_KERNEL | __GFP_NOFAIL, i);
+		spin_lock_init(&crng->lock);
+		crng_initialize(crng);
+		pool[i] = crng;
+	}
+	mb();
+	if (cmpxchg(&crng_node_pool, NULL, pool)) {
+		for_each_node(i)
+			kfree(pool[i]);
+		kfree(pool);
+	}
+}
+
+static DECLARE_WORK(numa_crng_init_work, do_numa_crng_init);
+
+static void numa_crng_init(void)
+{
+	schedule_work(&numa_crng_init_work);
+}
+#else
+static void numa_crng_init(void) {}
+#endif
+
+/*
+ * crng_fast_load() can be called by code in the interrupt service
+ * path.  So we can't afford to dilly-dally.
+ */
 static int crng_fast_load(const char *cp, size_t len)
 {
 	unsigned long flags;
@@ -794,7 +842,7 @@ static int crng_fast_load(const char *cp, size_t len)
 
 	if (!spin_trylock_irqsave(&primary_crng.lock, flags))
 		return 0;
-	if (crng_ready()) {
+	if (crng_init != 0) {
 		spin_unlock_irqrestore(&primary_crng.lock, flags);
 		return 0;
 	}
@@ -813,6 +861,51 @@ static int crng_fast_load(const char *cp, size_t len)
 	return 1;
 }
 
+/*
+ * crng_slow_load() is called by add_device_randomness, which has two
+ * attributes.  (1) We can't trust the buffer passed to it is
+ * guaranteed to be unpredictable (so it might not have any entropy at
+ * all), and (2) it doesn't have the performance constraints of
+ * crng_fast_load().
+ *
+ * So we do something more comprehensive which is guaranteed to touch
+ * all of the primary_crng's state, and which uses a LFSR with a
+ * period of 255 as part of the mixing algorithm.  Finally, we do
+ * *not* advance crng_init_cnt since buffer we may get may be something
+ * like a fixed DMI table (for example), which might very well be
+ * unique to the machine, but is otherwise unvarying.
+ */
+static int crng_slow_load(const char *cp, size_t len)
+{
+	unsigned long		flags;
+	static unsigned char	lfsr = 1;
+	unsigned char		tmp;
+	unsigned		i, max = CHACHA20_KEY_SIZE;
+	const char *		src_buf = cp;
+	char *			dest_buf = (char *) &primary_crng.state[4];
+
+	if (!spin_trylock_irqsave(&primary_crng.lock, flags))
+		return 0;
+	if (crng_init != 0) {
+		spin_unlock_irqrestore(&primary_crng.lock, flags);
+		return 0;
+	}
+	if (len > max)
+		max = len;
+
+	for (i = 0; i < max ; i++) {
+		tmp = lfsr;
+		lfsr >>= 1;
+		if (tmp & 1)
+			lfsr ^= 0xE1;
+		tmp = dest_buf[i % CHACHA20_KEY_SIZE];
+		dest_buf[i % CHACHA20_KEY_SIZE] ^= src_buf[i % len] ^ lfsr;
+		lfsr += (tmp << 3) | (tmp >> 5);
+	}
+	spin_unlock_irqrestore(&primary_crng.lock, flags);
+	return 1;
+}
+
 static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 {
 	unsigned long	flags;
@@ -831,7 +924,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 		_crng_backtrack_protect(&primary_crng, buf.block,
 					CHACHA20_KEY_SIZE);
 	}
-	spin_lock_irqsave(&primary_crng.lock, flags);
+	spin_lock_irqsave(&crng->lock, flags);
 	for (i = 0; i < 8; i++) {
 		unsigned long	rv;
 		if (!arch_get_random_seed_long(&rv) &&
@@ -841,13 +934,26 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 	}
 	memzero_explicit(&buf, sizeof(buf));
 	crng->init_time = jiffies;
-	spin_unlock_irqrestore(&primary_crng.lock, flags);
+	spin_unlock_irqrestore(&crng->lock, flags);
 	if (crng == &primary_crng && crng_init < 2) {
 		invalidate_batched_entropy();
+		numa_crng_init();
 		crng_init = 2;
 		process_random_ready_list();
 		wake_up_interruptible(&crng_init_wait);
 		pr_notice("random: crng init done\n");
+		if (unseeded_warning.missed) {
+			pr_notice("random: %d get_random_xx warning(s) missed "
+				  "due to ratelimiting\n",
+				  unseeded_warning.missed);
+			unseeded_warning.missed = 0;
+		}
+		if (urandom_warning.missed) {
+			pr_notice("random: %d urandom warning(s) missed "
+				  "due to ratelimiting\n",
+				  urandom_warning.missed);
+			urandom_warning.missed = 0;
+		}
 	}
 }
 
@@ -856,8 +962,9 @@ static void _extract_crng(struct crng_state *crng,
 {
 	unsigned long v, flags;
 
-	if (crng_init > 1 &&
-	    time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL))
+	if (crng_ready() &&
+	    (time_after(crng_global_init_time, crng->init_time) ||
+	     time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL)))
 		crng_reseed(crng, crng == &primary_crng ? &input_pool : NULL);
 	spin_lock_irqsave(&crng->lock, flags);
 	if (arch_get_random_long(&v))
@@ -981,10 +1088,8 @@ void add_device_randomness(const void *buf, unsigned int size)
 	unsigned long time = random_get_entropy() ^ jiffies;
 	unsigned long flags;
 
-	if (!crng_ready()) {
-		crng_fast_load(buf, size);
-		return;
-	}
+	if (!crng_ready() && size)
+		crng_slow_load(buf, size);
 
 	trace_add_device_randomness(size, _RET_IP_);
 	spin_lock_irqsave(&input_pool.lock, flags);
@@ -1139,7 +1244,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
 
-	if (!crng_ready()) {
+	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
 		    crng_fast_load((char *) fast_pool->pool,
 				   sizeof(fast_pool->pool))) {
@@ -1291,7 +1396,7 @@ retry:
 	trace_debit_entropy(r->name, 8 * ibytes);
 	if (ibytes &&
 	    (r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
-		wake_up_interruptible(&random_write_wait);
+		wake_up_interruptible_poll(&random_wait, POLLOUT);
 		kill_fasync(&fasync, SIGIO, POLL_OUT);
 	}
 
@@ -1489,8 +1594,9 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
 #ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM
 	print_once = true;
 #endif
-	pr_notice("random: %s called from %pS with crng_init=%d\n",
-		  func_name, caller, crng_init);
+	if (__ratelimit(&unseeded_warning))
+		pr_notice("random: %s called from %pS with crng_init=%d\n",
+			  func_name, caller, crng_init);
 }
 
 /*
@@ -1680,28 +1786,14 @@ static void init_std_data(struct entropy_store *r)
  */
 static int rand_initialize(void)
 {
-#ifdef CONFIG_NUMA
-	int i;
-	struct crng_state *crng;
-	struct crng_state **pool;
-#endif
-
 	init_std_data(&input_pool);
 	init_std_data(&blocking_pool);
 	crng_initialize(&primary_crng);
-
-#ifdef CONFIG_NUMA
-	pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
-	for_each_online_node(i) {
-		crng = kmalloc_node(sizeof(struct crng_state),
-				    GFP_KERNEL | __GFP_NOFAIL, i);
-		spin_lock_init(&crng->lock);
-		crng_initialize(crng);
-		pool[i] = crng;
+	crng_global_init_time = jiffies;
+	if (ratelimit_disable) {
+		urandom_warning.interval = 0;
+		unseeded_warning.interval = 0;
 	}
-	mb();
-	crng_node_pool = pool;
-#endif
 	return 0;
 }
 early_initcall(rand_initialize);
@@ -1746,7 +1838,7 @@ _random_read(int nonblock, char __user *buf, size_t nbytes)
 		if (nonblock)
 			return -EAGAIN;
 
-		wait_event_interruptible(random_read_wait,
+		wait_event_interruptible(random_wait,
 			ENTROPY_BITS(&input_pool) >=
 			random_read_wakeup_bits);
 		if (signal_pending(current))
@@ -1769,9 +1861,10 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 
 	if (!crng_ready() && maxwarn > 0) {
 		maxwarn--;
-		printk(KERN_NOTICE "random: %s: uninitialized urandom read "
-		       "(%zd bytes read)\n",
-		       current->comm, nbytes);
+		if (__ratelimit(&urandom_warning))
+			printk(KERN_NOTICE "random: %s: uninitialized "
+			       "urandom read (%zd bytes read)\n",
+			       current->comm, nbytes);
 		spin_lock_irqsave(&primary_crng.lock, flags);
 		crng_init_cnt = 0;
 		spin_unlock_irqrestore(&primary_crng.lock, flags);
@@ -1782,14 +1875,17 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 	return ret;
 }
 
+static struct wait_queue_head *
+random_get_poll_head(struct file *file, __poll_t events)
+{
+	return &random_wait;
+}
+
 static __poll_t
-random_poll(struct file *file, poll_table * wait)
+random_poll_mask(struct file *file, __poll_t events)
 {
-	__poll_t mask;
+	__poll_t mask = 0;
 
-	poll_wait(file, &random_read_wait, wait);
-	poll_wait(file, &random_write_wait, wait);
-	mask = 0;
 	if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
@@ -1875,6 +1971,14 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 		input_pool.entropy_count = 0;
 		blocking_pool.entropy_count = 0;
 		return 0;
+	case RNDRESEEDCRNG:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (crng_init < 2)
+			return -ENODATA;
+		crng_reseed(&primary_crng, NULL);
+		crng_global_init_time = jiffies - 1;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -1888,7 +1992,8 @@ static int random_fasync(int fd, struct file *filp, int on)
 const struct file_operations random_fops = {
 	.read  = random_read,
 	.write = random_write,
-	.poll  = random_poll,
+	.get_poll_head  = random_get_poll_head,
+	.poll_mask  = random_poll_mask,
 	.unlocked_ioctl = random_ioctl,
 	.fasync = random_fasync,
 	.llseek = noop_llseek,
@@ -2212,7 +2317,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
 {
 	struct entropy_store *poolp = &input_pool;
 
-	if (!crng_ready()) {
+	if (unlikely(crng_init == 0)) {
 		crng_fast_load(buffer, count);
 		return;
 	}
@@ -2221,7 +2326,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
 	 * We'll be woken up again once below random_write_wakeup_thresh,
 	 * or when the calling thread is about to terminate.
 	 */
-	wait_event_interruptible(random_write_wait, kthread_should_stop() ||
+	wait_event_interruptible(random_wait, kthread_should_stop() ||
 			ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
 	mix_pool_bytes(poolp, buffer, count);
 	credit_entropy_bits(poolp, entropy);
diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c
index 57dc546628b5..94fedeeec035 100644
--- a/drivers/char/rtc.c
+++ b/drivers/char/rtc.c
@@ -171,7 +171,7 @@ static void mask_rtc_irq_bit(unsigned char bit)
 #endif
 
 #ifdef CONFIG_PROC_FS
-static int rtc_proc_open(struct inode *inode, struct file *file);
+static int rtc_proc_show(struct seq_file *seq, void *v);
 #endif
 
 /*
@@ -832,16 +832,6 @@ static struct miscdevice rtc_dev = {
 	.fops		= &rtc_fops,
 };
 
-#ifdef CONFIG_PROC_FS
-static const struct file_operations rtc_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= rtc_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
 static resource_size_t rtc_size;
 
 static struct resource * __init rtc_request_region(resource_size_t size)
@@ -982,7 +972,7 @@ no_irq:
 	}
 
 #ifdef CONFIG_PROC_FS
-	ent = proc_create("driver/rtc", 0, NULL, &rtc_proc_fops);
+	ent = proc_create_single("driver/rtc", 0, NULL, rtc_proc_show);
 	if (!ent)
 		printk(KERN_WARNING "rtc: Failed to register with procfs.\n");
 #endif
@@ -1201,11 +1191,6 @@ static int rtc_proc_show(struct seq_file *seq, void *v)
 #undef YN
 #undef NY
 }
-
-static int rtc_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, rtc_proc_show, NULL);
-}
 #endif
 
 static void rtc_get_rtc_time(struct rtc_time *rtc_tm)
diff --git a/drivers/char/toshiba.c b/drivers/char/toshiba.c
index 5488516da8ea..802376fe851a 100644
--- a/drivers/char/toshiba.c
+++ b/drivers/char/toshiba.c
@@ -326,19 +326,6 @@ static int proc_toshiba_show(struct seq_file *m, void *v)
 		key);
 	return 0;
 }
-
-static int proc_toshiba_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_toshiba_show, NULL);
-}
-
-static const struct file_operations proc_toshiba_fops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_toshiba_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 
@@ -524,7 +511,7 @@ static int __init toshiba_init(void)
 	{
 		struct proc_dir_entry *pde;
 
-		pde = proc_create("toshiba", 0, NULL, &proc_toshiba_fops);
+		pde = proc_create_single("toshiba", 0, NULL, proc_toshiba_show);
 		if (!pde) {
 			misc_deregister(&tosh_device);
 			return -ENOMEM;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 468f06134012..21085515814f 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -422,7 +422,7 @@ static void reclaim_dma_bufs(void)
 	}
 }
 
-static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
+static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size,
 				     int pages)
 {
 	struct port_buffer *buf;
@@ -445,16 +445,16 @@ static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
 		return buf;
 	}
 
-	if (is_rproc_serial(vq->vdev)) {
+	if (is_rproc_serial(vdev)) {
 		/*
 		 * Allocate DMA memory from ancestor. When a virtio
 		 * device is created by remoteproc, the DMA memory is
 		 * associated with the grandparent device:
 		 * vdev => rproc => platform-dev.
 		 */
-		if (!vq->vdev->dev.parent || !vq->vdev->dev.parent->parent)
+		if (!vdev->dev.parent || !vdev->dev.parent->parent)
 			goto free_buf;
-		buf->dev = vq->vdev->dev.parent->parent;
+		buf->dev = vdev->dev.parent->parent;
 
 		/* Increase device refcnt to avoid freeing it */
 		get_device(buf->dev);
@@ -838,7 +838,7 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 
 	count = min((size_t)(32 * 1024), count);
 
-	buf = alloc_buf(port->out_vq, count, 0);
+	buf = alloc_buf(port->portdev->vdev, count, 0);
 	if (!buf)
 		return -ENOMEM;
 
@@ -957,7 +957,7 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 	if (ret < 0)
 		goto error_out;
 
-	buf = alloc_buf(port->out_vq, 0, pipe->nrbufs);
+	buf = alloc_buf(port->portdev->vdev, 0, pipe->nrbufs);
 	if (!buf) {
 		ret = -ENOMEM;
 		goto error_out;
@@ -1374,7 +1374,7 @@ static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
 
 	nr_added_bufs = 0;
 	do {
-		buf = alloc_buf(vq, PAGE_SIZE, 0);
+		buf = alloc_buf(vq->vdev, PAGE_SIZE, 0);
 		if (!buf)
 			break;
 
@@ -1402,7 +1402,6 @@ static int add_port(struct ports_device *portdev, u32 id)
 {
 	char debugfs_name[16];
 	struct port *port;
-	struct port_buffer *buf;
 	dev_t devt;
 	unsigned int nr_added_bufs;
 	int err;
@@ -1513,8 +1512,6 @@ static int add_port(struct ports_device *portdev, u32 id)
 	return 0;
 
 free_inbufs:
-	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf, true);
 free_device:
 	device_destroy(pdrvdata.class, port->dev->devt);
 free_cdev:
@@ -1539,34 +1536,14 @@ static void remove_port(struct kref *kref)
 
 static void remove_port_data(struct port *port)
 {
-	struct port_buffer *buf;
-
 	spin_lock_irq(&port->inbuf_lock);
 	/* Remove unused data this port might have received. */
 	discard_port_data(port);
 	spin_unlock_irq(&port->inbuf_lock);
 
-	/* Remove buffers we queued up for the Host to send us data in. */
-	do {
-		spin_lock_irq(&port->inbuf_lock);
-		buf = virtqueue_detach_unused_buf(port->in_vq);
-		spin_unlock_irq(&port->inbuf_lock);
-		if (buf)
-			free_buf(buf, true);
-	} while (buf);
-
 	spin_lock_irq(&port->outvq_lock);
 	reclaim_consumed_buffers(port);
 	spin_unlock_irq(&port->outvq_lock);
-
-	/* Free pending buffers from the out-queue. */
-	do {
-		spin_lock_irq(&port->outvq_lock);
-		buf = virtqueue_detach_unused_buf(port->out_vq);
-		spin_unlock_irq(&port->outvq_lock);
-		if (buf)
-			free_buf(buf, true);
-	} while (buf);
 }
 
 /*
@@ -1791,13 +1768,24 @@ static void control_work_handler(struct work_struct *work)
 	spin_unlock(&portdev->c_ivq_lock);
 }
 
+static void flush_bufs(struct virtqueue *vq, bool can_sleep)
+{
+	struct port_buffer *buf;
+	unsigned int len;
+
+	while ((buf = virtqueue_get_buf(vq, &len)))
+		free_buf(buf, can_sleep);
+}
+
 static void out_intr(struct virtqueue *vq)
 {
 	struct port *port;
 
 	port = find_port_by_vq(vq->vdev->priv, vq);
-	if (!port)
+	if (!port) {
+		flush_bufs(vq, false);
 		return;
+	}
 
 	wake_up_interruptible(&port->waitqueue);
 }
@@ -1808,8 +1796,10 @@ static void in_intr(struct virtqueue *vq)
 	unsigned long flags;
 
 	port = find_port_by_vq(vq->vdev->priv, vq);
-	if (!port)
+	if (!port) {
+		flush_bufs(vq, false);
 		return;
+	}
 
 	spin_lock_irqsave(&port->inbuf_lock, flags);
 	port->inbuf = get_inbuf(port);
@@ -1984,24 +1974,54 @@ static const struct file_operations portdev_fops = {
 
 static void remove_vqs(struct ports_device *portdev)
 {
+	struct virtqueue *vq;
+
+	virtio_device_for_each_vq(portdev->vdev, vq) {
+		struct port_buffer *buf;
+
+		flush_bufs(vq, true);
+		while ((buf = virtqueue_detach_unused_buf(vq)))
+			free_buf(buf, true);
+	}
 	portdev->vdev->config->del_vqs(portdev->vdev);
 	kfree(portdev->in_vqs);
 	kfree(portdev->out_vqs);
 }
 
-static void remove_controlq_data(struct ports_device *portdev)
+static void virtcons_remove(struct virtio_device *vdev)
 {
-	struct port_buffer *buf;
-	unsigned int len;
+	struct ports_device *portdev;
+	struct port *port, *port2;
 
-	if (!use_multiport(portdev))
-		return;
+	portdev = vdev->priv;
 
-	while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
-		free_buf(buf, true);
+	spin_lock_irq(&pdrvdata_lock);
+	list_del(&portdev->list);
+	spin_unlock_irq(&pdrvdata_lock);
 
-	while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
-		free_buf(buf, true);
+	/* Disable interrupts for vqs */
+	vdev->config->reset(vdev);
+	/* Finish up work that's lined up */
+	if (use_multiport(portdev))
+		cancel_work_sync(&portdev->control_work);
+	else
+		cancel_work_sync(&portdev->config_work);
+
+	list_for_each_entry_safe(port, port2, &portdev->ports, list)
+		unplug_port(port);
+
+	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
+
+	/*
+	 * When yanking out a device, we immediately lose the
+	 * (device-side) queues.  So there's no point in keeping the
+	 * guest side around till we drop our final reference.  This
+	 * also means that any ports which are in an open state will
+	 * have to just stop using the port, as the vqs are going
+	 * away.
+	 */
+	remove_vqs(portdev);
+	kfree(portdev);
 }
 
 /*
@@ -2070,6 +2090,7 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	spin_lock_init(&portdev->ports_lock);
 	INIT_LIST_HEAD(&portdev->ports);
+	INIT_LIST_HEAD(&portdev->list);
 
 	virtio_device_ready(portdev->vdev);
 
@@ -2087,8 +2108,15 @@ static int virtcons_probe(struct virtio_device *vdev)
 		if (!nr_added_bufs) {
 			dev_err(&vdev->dev,
 				"Error allocating buffers for control queue\n");
-			err = -ENOMEM;
-			goto free_vqs;
+			/*
+			 * The host might want to notify mgmt sw about device
+			 * add failure.
+			 */
+			__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
+					   VIRTIO_CONSOLE_DEVICE_READY, 0);
+			/* Device was functional: we need full cleanup. */
+			virtcons_remove(vdev);
+			return -ENOMEM;
 		}
 	} else {
 		/*
@@ -2119,11 +2147,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	return 0;
 
-free_vqs:
-	/* The host might want to notify mgmt sw about device add failure */
-	__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
-			   VIRTIO_CONSOLE_DEVICE_READY, 0);
-	remove_vqs(portdev);
 free_chrdev:
 	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
 free:
@@ -2132,43 +2155,6 @@ fail:
 	return err;
 }
 
-static void virtcons_remove(struct virtio_device *vdev)
-{
-	struct ports_device *portdev;
-	struct port *port, *port2;
-
-	portdev = vdev->priv;
-
-	spin_lock_irq(&pdrvdata_lock);
-	list_del(&portdev->list);
-	spin_unlock_irq(&pdrvdata_lock);
-
-	/* Disable interrupts for vqs */
-	vdev->config->reset(vdev);
-	/* Finish up work that's lined up */
-	if (use_multiport(portdev))
-		cancel_work_sync(&portdev->control_work);
-	else
-		cancel_work_sync(&portdev->config_work);
-
-	list_for_each_entry_safe(port, port2, &portdev->ports, list)
-		unplug_port(port);
-
-	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
-
-	/*
-	 * When yanking out a device, we immediately lose the
-	 * (device-side) queues.  So there's no point in keeping the
-	 * guest side around till we drop our final reference.  This
-	 * also means that any ports which are in an open state will
-	 * have to just stop using the port, as the vqs are going
-	 * away.
-	 */
-	remove_controlq_data(portdev);
-	remove_vqs(portdev);
-	kfree(portdev);
-}
-
 static struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
 	{ 0 },
@@ -2209,7 +2195,6 @@ static int virtcons_freeze(struct virtio_device *vdev)
 	 */
 	if (use_multiport(portdev))
 		virtqueue_disable_cb(portdev->c_ivq);
-	remove_controlq_data(portdev);
 
 	list_for_each_entry(port, &portdev->ports, list) {
 		virtqueue_disable_cb(port->in_vq);
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 41492e980ef4..34968a381d0f 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -266,15 +266,13 @@ config COMMON_CLK_STM32MP157
 	  Support for stm32mp157 SoC family clocks
 
 config COMMON_CLK_STM32F
-	bool "Clock driver for stm32f4 and stm32f7 SoC families"
-	depends on MACH_STM32F429 || MACH_STM32F469 || MACH_STM32F746
+	def_bool COMMON_CLK && (MACH_STM32F429 || MACH_STM32F469 || MACH_STM32F746)
 	help
 	---help---
 	  Support for stm32f4 and stm32f7 SoC families clocks
 
 config COMMON_CLK_STM32H7
-	bool "Clock driver for stm32h7 SoC family"
-	depends on MACH_STM32H743
+	def_bool COMMON_CLK && MACH_STM32H743
 	help
 	---help---
 	  Support for stm32h7 SoC family clocks
diff --git a/drivers/clk/clk-cs2000-cp.c b/drivers/clk/clk-cs2000-cp.c
index c58019750b7e..a2f8c42e527a 100644
--- a/drivers/clk/clk-cs2000-cp.c
+++ b/drivers/clk/clk-cs2000-cp.c
@@ -541,7 +541,7 @@ probe_err:
 	return ret;
 }
 
-static int cs2000_resume(struct device *dev)
+static int __maybe_unused cs2000_resume(struct device *dev)
 {
 	struct cs2000_priv *priv = dev_get_drvdata(dev);
 
diff --git a/drivers/clk/clk-mux.c b/drivers/clk/clk-mux.c
index ac4a042f8658..1628b93655ed 100644
--- a/drivers/clk/clk-mux.c
+++ b/drivers/clk/clk-mux.c
@@ -112,10 +112,18 @@ static int clk_mux_set_parent(struct clk_hw *hw, u8 index)
 	return 0;
 }
 
+static int clk_mux_determine_rate(struct clk_hw *hw,
+				  struct clk_rate_request *req)
+{
+	struct clk_mux *mux = to_clk_mux(hw);
+
+	return clk_mux_determine_rate_flags(hw, req, mux->flags);
+}
+
 const struct clk_ops clk_mux_ops = {
 	.get_parent = clk_mux_get_parent,
 	.set_parent = clk_mux_set_parent,
-	.determine_rate = __clk_mux_determine_rate,
+	.determine_rate = clk_mux_determine_rate,
 };
 EXPORT_SYMBOL_GPL(clk_mux_ops);
 
diff --git a/drivers/clk/clk-stm32mp1.c b/drivers/clk/clk-stm32mp1.c
index f1d5967b4b39..edd3cf451401 100644
--- a/drivers/clk/clk-stm32mp1.c
+++ b/drivers/clk/clk-stm32mp1.c
@@ -216,7 +216,7 @@ static const char * const usart1_src[] = {
 	"pclk5", "pll3_q", "ck_hsi", "ck_csi", "pll4_q", "ck_hse"
 };
 
-const char * const usart234578_src[] = {
+static const char * const usart234578_src[] = {
 	"pclk1", "pll4_q", "ck_hsi", "ck_csi", "ck_hse"
 };
 
@@ -224,10 +224,6 @@ static const char * const usart6_src[] = {
 	"pclk2", "pll4_q", "ck_hsi", "ck_csi", "ck_hse"
 };
 
-static const char * const dfsdm_src[] = {
-	"pclk2", "ck_mcu"
-};
-
 static const char * const fdcan_src[] = {
 	"ck_hse", "pll3_q", "pll4_q"
 };
@@ -316,10 +312,8 @@ struct stm32_clk_mgate {
 struct clock_config {
 	u32 id;
 	const char *name;
-	union {
-		const char *parent_name;
-		const char * const *parent_names;
-	};
+	const char *parent_name;
+	const char * const *parent_names;
 	int num_parents;
 	unsigned long flags;
 	void *cfg;
@@ -469,7 +463,7 @@ static void mp1_gate_clk_disable(struct clk_hw *hw)
 	}
 }
 
-const struct clk_ops mp1_gate_clk_ops = {
+static const struct clk_ops mp1_gate_clk_ops = {
 	.enable		= mp1_gate_clk_enable,
 	.disable	= mp1_gate_clk_disable,
 	.is_enabled	= clk_gate_is_enabled,
@@ -698,7 +692,7 @@ static void mp1_mgate_clk_disable(struct clk_hw *hw)
 		mp1_gate_clk_disable(hw);
 }
 
-const struct clk_ops mp1_mgate_clk_ops = {
+static const struct clk_ops mp1_mgate_clk_ops = {
 	.enable		= mp1_mgate_clk_enable,
 	.disable	= mp1_mgate_clk_disable,
 	.is_enabled	= clk_gate_is_enabled,
@@ -732,7 +726,7 @@ static int clk_mmux_set_parent(struct clk_hw *hw, u8 index)
 	return 0;
 }
 
-const struct clk_ops clk_mmux_ops = {
+static const struct clk_ops clk_mmux_ops = {
 	.get_parent	= clk_mmux_get_parent,
 	.set_parent	= clk_mmux_set_parent,
 	.determine_rate	= __clk_mux_determine_rate,
@@ -1048,10 +1042,10 @@ struct stm32_pll_cfg {
 	u32 offset;
 };
 
-struct clk_hw *_clk_register_pll(struct device *dev,
-				 struct clk_hw_onecell_data *clk_data,
-				 void __iomem *base, spinlock_t *lock,
-				 const struct clock_config *cfg)
+static struct clk_hw *_clk_register_pll(struct device *dev,
+					struct clk_hw_onecell_data *clk_data,
+					void __iomem *base, spinlock_t *lock,
+					const struct clock_config *cfg)
 {
 	struct stm32_pll_cfg *stm_pll_cfg = cfg->cfg;
 
@@ -1405,7 +1399,8 @@ enum {
 	G_USBH,
 	G_ETHSTP,
 	G_RTCAPB,
-	G_TZC,
+	G_TZC1,
+	G_TZC2,
 	G_TZPC,
 	G_IWDG1,
 	G_BSEC,
@@ -1417,7 +1412,7 @@ enum {
 	G_LAST
 };
 
-struct stm32_mgate mp1_mgate[G_LAST];
+static struct stm32_mgate mp1_mgate[G_LAST];
 
 #define _K_GATE(_id, _gate_offset, _gate_bit_idx, _gate_flags,\
 	       _mgate, _ops)\
@@ -1440,7 +1435,7 @@ struct stm32_mgate mp1_mgate[G_LAST];
 	       &mp1_mgate[_id], &mp1_mgate_clk_ops)
 
 /* Peripheral gates */
-struct stm32_gate_cfg per_gate_cfg[G_LAST] = {
+static struct stm32_gate_cfg per_gate_cfg[G_LAST] = {
 	/* Multi gates */
 	K_GATE(G_MDIO,		RCC_APB1ENSETR, 31, 0),
 	K_MGATE(G_DAC12,	RCC_APB1ENSETR, 29, 0),
@@ -1506,7 +1501,8 @@ struct stm32_gate_cfg per_gate_cfg[G_LAST] = {
 	K_GATE(G_BSEC,		RCC_APB5ENSETR, 16, 0),
 	K_GATE(G_IWDG1,		RCC_APB5ENSETR, 15, 0),
 	K_GATE(G_TZPC,		RCC_APB5ENSETR, 13, 0),
-	K_GATE(G_TZC,		RCC_APB5ENSETR, 12, 0),
+	K_GATE(G_TZC2,		RCC_APB5ENSETR, 12, 0),
+	K_GATE(G_TZC1,		RCC_APB5ENSETR, 11, 0),
 	K_GATE(G_RTCAPB,	RCC_APB5ENSETR, 8, 0),
 	K_MGATE(G_USART1,	RCC_APB5ENSETR, 4, 0),
 	K_MGATE(G_I2C6,		RCC_APB5ENSETR, 3, 0),
@@ -1600,7 +1596,7 @@ enum {
 	M_LAST
 };
 
-struct stm32_mmux ker_mux[M_LAST];
+static struct stm32_mmux ker_mux[M_LAST];
 
 #define _K_MUX(_id, _offset, _shift, _width, _mux_flags, _mmux, _ops)\
 	[_id] = {\
@@ -1623,7 +1619,7 @@ struct stm32_mmux ker_mux[M_LAST];
 	_K_MUX(_id, _offset, _shift, _width, _mux_flags,\
 			&ker_mux[_id], &clk_mmux_ops)
 
-const struct stm32_mux_cfg ker_mux_cfg[M_LAST] = {
+static const struct stm32_mux_cfg ker_mux_cfg[M_LAST] = {
 	/* Kernel multi mux */
 	K_MMUX(M_SDMMC12, RCC_SDMMC12CKSELR, 0, 3, 0),
 	K_MMUX(M_SPI23, RCC_SPI2S23CKSELR, 0, 3, 0),
@@ -1860,7 +1856,8 @@ static const struct clock_config stm32mp1_clock_cfg[] = {
 	PCLK(USART1, "usart1", "pclk5", 0, G_USART1),
 	PCLK(RTCAPB, "rtcapb", "pclk5", CLK_IGNORE_UNUSED |
 	     CLK_IS_CRITICAL, G_RTCAPB),
-	PCLK(TZC, "tzc", "pclk5", CLK_IGNORE_UNUSED, G_TZC),
+	PCLK(TZC1, "tzc1", "ck_axi", CLK_IGNORE_UNUSED, G_TZC1),
+	PCLK(TZC2, "tzc2", "ck_axi", CLK_IGNORE_UNUSED, G_TZC2),
 	PCLK(TZPC, "tzpc", "pclk5", CLK_IGNORE_UNUSED, G_TZPC),
 	PCLK(IWDG1, "iwdg1", "pclk5", 0, G_IWDG1),
 	PCLK(BSEC, "bsec", "pclk5", CLK_IGNORE_UNUSED, G_BSEC),
@@ -1916,8 +1913,7 @@ static const struct clock_config stm32mp1_clock_cfg[] = {
 	KCLK(RNG1_K, "rng1_k", rng_src, 0, G_RNG1, M_RNG1),
 	KCLK(RNG2_K, "rng2_k", rng_src, 0, G_RNG2, M_RNG2),
 	KCLK(USBPHY_K, "usbphy_k", usbphy_src, 0, G_USBPHY, M_USBPHY),
-	KCLK(STGEN_K, "stgen_k",  stgen_src, CLK_IGNORE_UNUSED,
-	     G_STGEN, M_STGEN),
+	KCLK(STGEN_K, "stgen_k", stgen_src, CLK_IS_CRITICAL, G_STGEN, M_STGEN),
 	KCLK(SPDIF_K, "spdif_k", spdif_src, 0, G_SPDIF, M_SPDIF),
 	KCLK(SPI1_K, "spi1_k", spi123_src, 0, G_SPI1, M_SPI1),
 	KCLK(SPI2_K, "spi2_k", spi123_src, 0, G_SPI2, M_SPI23),
@@ -1948,8 +1944,8 @@ static const struct clock_config stm32mp1_clock_cfg[] = {
 	KCLK(FDCAN_K, "fdcan_k", fdcan_src, 0, G_FDCAN, M_FDCAN),
 	KCLK(SAI1_K, "sai1_k", sai_src, 0, G_SAI1, M_SAI1),
 	KCLK(SAI2_K, "sai2_k", sai2_src, 0, G_SAI2, M_SAI2),
-	KCLK(SAI3_K, "sai3_k", sai_src, 0, G_SAI2, M_SAI3),
-	KCLK(SAI4_K, "sai4_k", sai_src, 0, G_SAI2, M_SAI4),
+	KCLK(SAI3_K, "sai3_k", sai_src, 0, G_SAI3, M_SAI3),
+	KCLK(SAI4_K, "sai4_k", sai_src, 0, G_SAI4, M_SAI4),
 	KCLK(ADC12_K, "adc12_k", adc12_src, 0, G_ADC12, M_ADC12),
 	KCLK(DSI_K, "dsi_k", dsi_src, 0, G_DSI, M_DSI),
 	KCLK(ADFSDM_K, "adfsdm_k", sai_src, 0, G_ADFSDM, M_SAI1),
@@ -1992,10 +1988,6 @@ static const struct clock_config stm32mp1_clock_cfg[] = {
 		  _DIV(RCC_MCO2CFGR, 4, 4, 0, NULL)),
 
 	/* Debug clocks */
-	FIXED_FACTOR(NO_ID, "ck_axi_div2", "ck_axi", 0, 1, 2),
-
-	GATE(DBG, "ck_apb_dbg", "ck_axi_div2", 0, RCC_DBGCFGR, 8, 0),
-
 	GATE(CK_DBG, "ck_sys_dbg", "ck_axi", 0, RCC_DBGCFGR, 8, 0),
 
 	COMPOSITE(CK_TRACE, "ck_trace", ck_trace_src, CLK_OPS_PARENT_ENABLE,
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index ea67ac81c6f9..7af555f0e60c 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -426,9 +426,9 @@ static bool mux_is_better_rate(unsigned long rate, unsigned long now,
 	return now <= rate && now > best;
 }
 
-static int
-clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req,
-			     unsigned long flags)
+int clk_mux_determine_rate_flags(struct clk_hw *hw,
+				 struct clk_rate_request *req,
+				 unsigned long flags)
 {
 	struct clk_core *core = hw->core, *parent, *best_parent = NULL;
 	int i, num_parents, ret;
@@ -488,6 +488,7 @@ out:
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(clk_mux_determine_rate_flags);
 
 struct clk *__clk_lookup(const char *name)
 {
diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
index 114ecbb94ec5..12320118f8de 100644
--- a/drivers/clk/imx/clk-imx6ul.c
+++ b/drivers/clk/imx/clk-imx6ul.c
@@ -464,7 +464,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clk_set_rate(clks[IMX6UL_CLK_AHB], 99000000);
 
 	/* Change periph_pre clock to pll2_bus to adjust AXI rate to 264MHz */
-	clk_set_parent(clks[IMX6UL_CLK_PERIPH_CLK2_SEL], clks[IMX6UL_CLK_PLL3_USB_OTG]);
+	clk_set_parent(clks[IMX6UL_CLK_PERIPH_CLK2_SEL], clks[IMX6UL_CLK_OSC]);
 	clk_set_parent(clks[IMX6UL_CLK_PERIPH], clks[IMX6UL_CLK_PERIPH_CLK2]);
 	clk_set_parent(clks[IMX6UL_CLK_PERIPH_PRE], clks[IMX6UL_CLK_PLL2_BUS]);
 	clk_set_parent(clks[IMX6UL_CLK_PERIPH], clks[IMX6UL_CLK_PERIPH_PRE]);
diff --git a/drivers/clk/meson/clk-regmap.c b/drivers/clk/meson/clk-regmap.c
index 3645fdb62343..ab7a3556f5b2 100644
--- a/drivers/clk/meson/clk-regmap.c
+++ b/drivers/clk/meson/clk-regmap.c
@@ -153,10 +153,19 @@ static int clk_regmap_mux_set_parent(struct clk_hw *hw, u8 index)
 				  val << mux->shift);
 }
 
+static int clk_regmap_mux_determine_rate(struct clk_hw *hw,
+					 struct clk_rate_request *req)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct clk_regmap_mux_data *mux = clk_get_regmap_mux_data(clk);
+
+	return clk_mux_determine_rate_flags(hw, req, mux->flags);
+}
+
 const struct clk_ops clk_regmap_mux_ops = {
 	.get_parent = clk_regmap_mux_get_parent,
 	.set_parent = clk_regmap_mux_set_parent,
-	.determine_rate = __clk_mux_determine_rate,
+	.determine_rate = clk_regmap_mux_determine_rate,
 };
 EXPORT_SYMBOL_GPL(clk_regmap_mux_ops);
 
diff --git a/drivers/clk/meson/gxbb-aoclk.h b/drivers/clk/meson/gxbb-aoclk.h
index 0be78383f257..badc4c22b4ee 100644
--- a/drivers/clk/meson/gxbb-aoclk.h
+++ b/drivers/clk/meson/gxbb-aoclk.h
@@ -17,8 +17,6 @@
 #define AO_RTC_ALT_CLK_CNTL0	0x94
 #define AO_RTC_ALT_CLK_CNTL1	0x98
 
-extern const struct clk_ops meson_aoclk_gate_regmap_ops;
-
 struct aoclk_cec_32k {
 	struct clk_hw hw;
 	struct regmap *regmap;
diff --git a/drivers/clk/meson/meson8b.c b/drivers/clk/meson/meson8b.c
index cc2992493e0b..d0524ec71aad 100644
--- a/drivers/clk/meson/meson8b.c
+++ b/drivers/clk/meson/meson8b.c
@@ -253,7 +253,7 @@ static struct clk_fixed_factor meson8b_fclk_div3_div = {
 	.mult = 1,
 	.div = 3,
 	.hw.init = &(struct clk_init_data){
-		.name = "fclk_div_div3",
+		.name = "fclk_div3_div",
 		.ops = &clk_fixed_factor_ops,
 		.parent_names = (const char *[]){ "fixed_pll" },
 		.num_parents = 1,
@@ -632,7 +632,8 @@ static struct clk_regmap meson8b_cpu_clk = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk",
 		.ops = &clk_regmap_mux_ro_ops,
-		.parent_names = (const char *[]){ "xtal", "cpu_out_sel" },
+		.parent_names = (const char *[]){ "xtal",
+						  "cpu_scale_out_sel" },
 		.num_parents = 2,
 		.flags = (CLK_SET_RATE_PARENT |
 			  CLK_SET_RATE_NO_REPARENT),
diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c
index 4e88e980fb76..69a7c756658b 100644
--- a/drivers/clk/renesas/renesas-cpg-mssr.c
+++ b/drivers/clk/renesas/renesas-cpg-mssr.c
@@ -258,8 +258,9 @@ struct clk *cpg_mssr_clk_src_twocell_get(struct of_phandle_args *clkspec,
 		dev_err(dev, "Cannot get %s clock %u: %ld", type, clkidx,
 		       PTR_ERR(clk));
 	else
-		dev_dbg(dev, "clock (%u, %u) is %pC at %pCr Hz\n",
-			clkspec->args[0], clkspec->args[1], clk, clk);
+		dev_dbg(dev, "clock (%u, %u) is %pC at %lu Hz\n",
+			clkspec->args[0], clkspec->args[1], clk,
+			clk_get_rate(clk));
 	return clk;
 }
 
@@ -326,7 +327,7 @@ static void __init cpg_mssr_register_core_clk(const struct cpg_core_clk *core,
 	if (IS_ERR_OR_NULL(clk))
 		goto fail;
 
-	dev_dbg(dev, "Core clock %pC at %pCr Hz\n", clk, clk);
+	dev_dbg(dev, "Core clock %pC at %lu Hz\n", clk, clk_get_rate(clk));
 	priv->clks[id] = clk;
 	return;
 
@@ -392,7 +393,7 @@ static void __init cpg_mssr_register_mod_clk(const struct mssr_mod_clk *mod,
 	if (IS_ERR(clk))
 		goto fail;
 
-	dev_dbg(dev, "Module clock %pC at %pCr Hz\n", clk, clk);
+	dev_dbg(dev, "Module clock %pC at %lu Hz\n", clk, clk_get_rate(clk));
 	priv->clks[id] = clk;
 	priv->smstpcr_saved[clock->index / 32].mask |= BIT(clock->index % 32);
 	return;
diff --git a/drivers/clk/x86/Makefile b/drivers/clk/x86/Makefile
index 1367afb03858..00303bc05415 100644
--- a/drivers/clk/x86/Makefile
+++ b/drivers/clk/x86/Makefile
@@ -1,3 +1,4 @@
+obj-$(CONFIG_PMC_ATOM)		+= clk-pmc-atom.o
+obj-$(CONFIG_X86_AMD_PLATFORM_DEVICE)	+= clk-st.o
 clk-x86-lpss-objs		:= clk-lpt.o
 obj-$(CONFIG_X86_INTEL_LPSS)	+= clk-x86-lpss.o
-obj-$(CONFIG_PMC_ATOM)		+= clk-pmc-atom.o
diff --git a/drivers/clk/x86/clk-st.c b/drivers/clk/x86/clk-st.c
new file mode 100644
index 000000000000..fb62f3938008
--- /dev/null
+++ b/drivers/clk/x86/clk-st.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: MIT
+/*
+ * clock framework for AMD Stoney based clocks
+ *
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/platform_data/clk-st.h>
+#include <linux/platform_device.h>
+
+/* Clock Driving Strength 2 register */
+#define CLKDRVSTR2	0x28
+/* Clock Control 1 register */
+#define MISCCLKCNTL1	0x40
+/* Auxiliary clock1 enable bit */
+#define OSCCLKENB	2
+/* 25Mhz auxiliary output clock freq bit */
+#define OSCOUT1CLK25MHZ	16
+
+#define ST_CLK_48M	0
+#define ST_CLK_25M	1
+#define ST_CLK_MUX	2
+#define ST_CLK_GATE	3
+#define ST_MAX_CLKS	4
+
+static const char * const clk_oscout1_parents[] = { "clk48MHz", "clk25MHz" };
+static struct clk_hw *hws[ST_MAX_CLKS];
+
+static int st_clk_probe(struct platform_device *pdev)
+{
+	struct st_clk_data *st_data;
+
+	st_data = dev_get_platdata(&pdev->dev);
+	if (!st_data || !st_data->base)
+		return -EINVAL;
+
+	hws[ST_CLK_48M] = clk_hw_register_fixed_rate(NULL, "clk48MHz", NULL, 0,
+						     48000000);
+	hws[ST_CLK_25M] = clk_hw_register_fixed_rate(NULL, "clk25MHz", NULL, 0,
+						     25000000);
+
+	hws[ST_CLK_MUX] = clk_hw_register_mux(NULL, "oscout1_mux",
+		clk_oscout1_parents, ARRAY_SIZE(clk_oscout1_parents),
+		0, st_data->base + CLKDRVSTR2, OSCOUT1CLK25MHZ, 3, 0, NULL);
+
+	clk_set_parent(hws[ST_CLK_MUX]->clk, hws[ST_CLK_25M]->clk);
+
+	hws[ST_CLK_GATE] = clk_hw_register_gate(NULL, "oscout1", "oscout1_mux",
+		0, st_data->base + MISCCLKCNTL1, OSCCLKENB,
+		CLK_GATE_SET_TO_DISABLE, NULL);
+
+	clk_hw_register_clkdev(hws[ST_CLK_GATE], "oscout1", NULL);
+
+	return 0;
+}
+
+static int st_clk_remove(struct platform_device *pdev)
+{
+	int i;
+
+	for (i = 0; i < ST_MAX_CLKS; i++)
+		clk_hw_unregister(hws[i]);
+	return 0;
+}
+
+static struct platform_driver st_clk_driver = {
+	.driver = {
+		.name = "clk-st",
+		.suppress_bind_attrs = true,
+	},
+	.probe = st_clk_probe,
+	.remove = st_clk_remove,
+};
+builtin_platform_driver(st_clk_driver);
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 9ee2888275c1..dec0dd88ec15 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -133,6 +133,14 @@ config VT8500_TIMER
 	help
 	  Enables support for the VT8500 driver.
 
+config NPCM7XX_TIMER
+	bool "NPCM7xx timer driver" if COMPILE_TEST
+	depends on HAS_IOMEM
+	select CLKSRC_MMIO
+	help
+	  Enable 24-bit TIMER0 and TIMER1 counters in the NPCM7xx architecture,
+	  While TIMER0 serves as clockevent and TIMER1 serves as clocksource.
+
 config CADENCE_TTC_TIMER
 	bool "Cadence TTC timer driver" if COMPILE_TEST
 	depends on COMMON_CLK
@@ -442,8 +450,10 @@ config MTK_TIMER
 	  Support for Mediatek timer driver.
 
 config SPRD_TIMER
-	bool "Spreadtrum timer driver" if COMPILE_TEST
+	bool "Spreadtrum timer driver" if EXPERT
 	depends on HAS_IOMEM
+	depends on (ARCH_SPRD || COMPILE_TEST)
+	default ARCH_SPRD
 	select TIMER_OF
 	help
 	  Enables support for the Spreadtrum timer driver.
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index e8e76dfef00b..00caf37e52f9 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_CLKSRC_NPS)	+= timer-nps.o
 obj-$(CONFIG_OXNAS_RPS_TIMER)	+= timer-oxnas-rps.o
 obj-$(CONFIG_OWL_TIMER)		+= owl-timer.o
 obj-$(CONFIG_SPRD_TIMER)	+= timer-sprd.o
+obj-$(CONFIG_NPCM7XX_TIMER)	+= timer-npcm7xx.o
 
 obj-$(CONFIG_ARC_TIMERS)		+= arc_timer.o
 obj-$(CONFIG_ARM_ARCH_TIMER)		+= arm_arch_timer.o
diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c
index 471b428d8034..20da9b1d7f7d 100644
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -61,6 +61,20 @@ static u64 arc_read_gfrc(struct clocksource *cs)
 	unsigned long flags;
 	u32 l, h;
 
+	/*
+	 * From a programming model pov, there seems to be just one instance of
+	 * MCIP_CMD/MCIP_READBACK however micro-architecturally there's
+	 * an instance PER ARC CORE (not per cluster), and there are dedicated
+	 * hardware decode logic (per core) inside ARConnect to handle
+	 * simultaneous read/write accesses from cores via those two registers.
+	 * So several concurrent commands to ARConnect are OK if they are
+	 * trying to access two different sub-components (like GFRC,
+	 * inter-core interrupt, etc...). HW also supports simultaneously
+	 * accessing GFRC by multiple cores.
+	 * That's why it is safe to disable hard interrupts on the local CPU
+	 * before access to GFRC instead of taking global MCIP spinlock
+	 * defined in arch/arc/kernel/mcip.c
+	 */
 	local_irq_save(flags);
 
 	__mcip_cmd(CMD_GFRC_READ_LO, 0);
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 986b6796b631..54f8a331b53a 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -5,6 +5,9 @@
  *
  * Copyright (C) 2012 MIPS Technologies, Inc.  All rights reserved.
  */
+
+#define pr_fmt(fmt) "mips-gic-timer: " fmt
+
 #include <linux/clk.h>
 #include <linux/clockchips.h>
 #include <linux/cpu.h>
@@ -136,8 +139,7 @@ static int gic_clockevent_init(void)
 
 	ret = setup_percpu_irq(gic_timer_irq, &gic_compare_irqaction);
 	if (ret < 0) {
-		pr_err("GIC timer IRQ %d setup failed: %d\n",
-		       gic_timer_irq, ret);
+		pr_err("IRQ %d setup failed (%d)\n", gic_timer_irq, ret);
 		return ret;
 	}
 
@@ -176,7 +178,7 @@ static int __init __gic_clocksource_init(void)
 
 	ret = clocksource_register_hz(&gic_clocksource, gic_frequency);
 	if (ret < 0)
-		pr_warn("GIC: Unable to register clocksource\n");
+		pr_warn("Unable to register clocksource\n");
 
 	return ret;
 }
@@ -188,7 +190,7 @@ static int __init gic_clocksource_of_init(struct device_node *node)
 
 	if (!mips_gic_present() || !node->parent ||
 	    !of_device_is_compatible(node->parent, "mti,gic")) {
-		pr_warn("No DT definition for the mips gic driver\n");
+		pr_warn("No DT definition\n");
 		return -ENXIO;
 	}
 
@@ -196,7 +198,7 @@ static int __init gic_clocksource_of_init(struct device_node *node)
 	if (!IS_ERR(clk)) {
 		ret = clk_prepare_enable(clk);
 		if (ret < 0) {
-			pr_err("GIC failed to enable clock\n");
+			pr_err("Failed to enable clock\n");
 			clk_put(clk);
 			return ret;
 		}
@@ -204,12 +206,12 @@ static int __init gic_clocksource_of_init(struct device_node *node)
 		gic_frequency = clk_get_rate(clk);
 	} else if (of_property_read_u32(node, "clock-frequency",
 					&gic_frequency)) {
-		pr_err("GIC frequency not specified.\n");
+		pr_err("Frequency not specified\n");
 		return -EINVAL;
 	}
 	gic_timer_irq = irq_of_parse_and_map(node, 0);
 	if (!gic_timer_irq) {
-		pr_err("GIC timer IRQ not specified.\n");
+		pr_err("IRQ not specified\n");
 		return -EINVAL;
 	}
 
@@ -220,7 +222,7 @@ static int __init gic_clocksource_of_init(struct device_node *node)
 	ret = gic_clockevent_init();
 	if (!ret && !IS_ERR(clk)) {
 		if (clk_notifier_register(clk, &gic_clk_nb) < 0)
-			pr_warn("GIC: Unable to register clock notifier\n");
+			pr_warn("Unable to register clock notifier\n");
 	}
 
 	/* And finally start the counter */
diff --git a/drivers/clocksource/mxs_timer.c b/drivers/clocksource/mxs_timer.c
index a03434e9fe8f..f6ddae30933f 100644
--- a/drivers/clocksource/mxs_timer.c
+++ b/drivers/clocksource/mxs_timer.c
@@ -1,24 +1,10 @@
-/*
- *  Copyright (C) 2000-2001 Deep Blue Solutions
- *  Copyright (C) 2002 Shane Nay (shane@minirl.com)
- *  Copyright (C) 2006-2007 Pavel Pisa (ppisa@pikron.com)
- *  Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
- *  Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+//  Copyright (C) 2000-2001 Deep Blue Solutions
+//  Copyright (C) 2002 Shane Nay (shane@minirl.com)
+//  Copyright (C) 2006-2007 Pavel Pisa (ppisa@pikron.com)
+//  Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
+//  Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved.
 
 #include <linux/err.h>
 #include <linux/interrupt.h>
diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c
index 6ec6d79b237c..165fbbb1c9a0 100644
--- a/drivers/clocksource/timer-imx-gpt.c
+++ b/drivers/clocksource/timer-imx-gpt.c
@@ -1,25 +1,9 @@
-/*
- *  linux/arch/arm/plat-mxc/time.c
- *
- *  Copyright (C) 2000-2001 Deep Blue Solutions
- *  Copyright (C) 2002 Shane Nay (shane@minirl.com)
- *  Copyright (C) 2006-2007 Pavel Pisa (ppisa@pikron.com)
- *  Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+//  Copyright (C) 2000-2001 Deep Blue Solutions
+//  Copyright (C) 2002 Shane Nay (shane@minirl.com)
+//  Copyright (C) 2006-2007 Pavel Pisa (ppisa@pikron.com)
+//  Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
 
 #include <linux/interrupt.h>
 #include <linux/irq.h>
diff --git a/drivers/clocksource/timer-imx-tpm.c b/drivers/clocksource/timer-imx-tpm.c
index 21bffdcb2f20..b7aa2b817078 100644
--- a/drivers/clocksource/timer-imx-tpm.c
+++ b/drivers/clocksource/timer-imx-tpm.c
@@ -1,12 +1,7 @@
-/*
- * Copyright 2016 Freescale Semiconductor, Inc.
- * Copyright 2017 NXP
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2016 Freescale Semiconductor, Inc.
+// Copyright 2017 NXP
 
 #include <linux/clk.h>
 #include <linux/clockchips.h>
@@ -17,9 +12,14 @@
 #include <linux/of_irq.h>
 #include <linux/sched_clock.h>
 
+#define TPM_PARAM			0x4
+#define TPM_PARAM_WIDTH_SHIFT		16
+#define TPM_PARAM_WIDTH_MASK		(0xff << 16)
 #define TPM_SC				0x10
 #define TPM_SC_CMOD_INC_PER_CNT		(0x1 << 3)
 #define TPM_SC_CMOD_DIV_DEFAULT		0x3
+#define TPM_SC_CMOD_DIV_MAX		0x7
+#define TPM_SC_TOF_MASK			(0x1 << 7)
 #define TPM_CNT				0x14
 #define TPM_MOD				0x18
 #define TPM_STATUS			0x1c
@@ -29,8 +29,11 @@
 #define TPM_C0SC_MODE_SHIFT		2
 #define TPM_C0SC_MODE_MASK		0x3c
 #define TPM_C0SC_MODE_SW_COMPARE	0x4
+#define TPM_C0SC_CHF_MASK		(0x1 << 7)
 #define TPM_C0V				0x24
 
+static int counter_width;
+static int rating;
 static void __iomem *timer_base;
 static struct clock_event_device clockevent_tpm;
 
@@ -83,10 +86,11 @@ static int __init tpm_clocksource_init(unsigned long rate)
 	tpm_delay_timer.freq = rate;
 	register_current_timer_delay(&tpm_delay_timer);
 
-	sched_clock_register(tpm_read_sched_clock, 32, rate);
+	sched_clock_register(tpm_read_sched_clock, counter_width, rate);
 
 	return clocksource_mmio_init(timer_base + TPM_CNT, "imx-tpm",
-				     rate, 200, 32, clocksource_mmio_readl_up);
+				     rate, rating, counter_width,
+				     clocksource_mmio_readl_up);
 }
 
 static int tpm_set_next_event(unsigned long delta,
@@ -105,7 +109,7 @@ static int tpm_set_next_event(unsigned long delta,
 	 * of writing CNT registers which may cause the min_delta event got
 	 * missed, so we need add a ETIME check here in case it happened.
 	 */
-	return (int)((next - now) <= 0) ? -ETIME : 0;
+	return (int)(next - now) <= 0 ? -ETIME : 0;
 }
 
 static int tpm_set_state_oneshot(struct clock_event_device *evt)
@@ -139,7 +143,6 @@ static struct clock_event_device clockevent_tpm = {
 	.set_state_oneshot	= tpm_set_state_oneshot,
 	.set_next_event		= tpm_set_next_event,
 	.set_state_shutdown	= tpm_set_state_shutdown,
-	.rating			= 200,
 };
 
 static int __init tpm_clockevent_init(unsigned long rate, int irq)
@@ -149,10 +152,11 @@ static int __init tpm_clockevent_init(unsigned long rate, int irq)
 	ret = request_irq(irq, tpm_timer_interrupt, IRQF_TIMER | IRQF_IRQPOLL,
 			  "i.MX7ULP TPM Timer", &clockevent_tpm);
 
+	clockevent_tpm.rating = rating;
 	clockevent_tpm.cpumask = cpumask_of(0);
 	clockevent_tpm.irq = irq;
-	clockevents_config_and_register(&clockevent_tpm,
-					rate, 300, 0xfffffffe);
+	clockevents_config_and_register(&clockevent_tpm, rate, 300,
+					GENMASK(counter_width - 1, 1));
 
 	return ret;
 }
@@ -179,7 +183,7 @@ static int __init tpm_timer_init(struct device_node *np)
 	ipg = of_clk_get_by_name(np, "ipg");
 	per = of_clk_get_by_name(np, "per");
 	if (IS_ERR(ipg) || IS_ERR(per)) {
-		pr_err("tpm: failed to get igp or per clk\n");
+		pr_err("tpm: failed to get ipg or per clk\n");
 		ret = -ENODEV;
 		goto err_clk_get;
 	}
@@ -197,6 +201,11 @@ static int __init tpm_timer_init(struct device_node *np)
 		goto err_per_clk_enable;
 	}
 
+	counter_width = (readl(timer_base + TPM_PARAM) & TPM_PARAM_WIDTH_MASK)
+		>> TPM_PARAM_WIDTH_SHIFT;
+	/* use rating 200 for 32-bit counter and 150 for 16-bit counter */
+	rating = counter_width == 0x20 ? 200 : 150;
+
 	/*
 	 * Initialize tpm module to a known state
 	 * 1) Counter disabled
@@ -205,16 +214,25 @@ static int __init tpm_timer_init(struct device_node *np)
 	 * 4) Channel0 disabled
 	 * 5) DMA transfers disabled
 	 */
+	/* make sure counter is disabled */
 	writel(0, timer_base + TPM_SC);
+	/* TOF is W1C */
+	writel(TPM_SC_TOF_MASK, timer_base + TPM_SC);
 	writel(0, timer_base + TPM_CNT);
-	writel(0, timer_base + TPM_C0SC);
+	/* CHF is W1C */
+	writel(TPM_C0SC_CHF_MASK, timer_base + TPM_C0SC);
 
-	/* increase per cnt, div 8 by default */
-	writel(TPM_SC_CMOD_INC_PER_CNT | TPM_SC_CMOD_DIV_DEFAULT,
+	/*
+	 * increase per cnt,
+	 * div 8 for 32-bit counter and div 128 for 16-bit counter
+	 */
+	writel(TPM_SC_CMOD_INC_PER_CNT |
+		(counter_width == 0x20 ?
+		TPM_SC_CMOD_DIV_DEFAULT : TPM_SC_CMOD_DIV_MAX),
 		     timer_base + TPM_SC);
 
 	/* set MOD register to maximum for free running mode */
-	writel(0xffffffff, timer_base + TPM_MOD);
+	writel(GENMASK(counter_width - 1, 0), timer_base + TPM_MOD);
 
 	rate = clk_get_rate(per) >> 3;
 	ret = tpm_clocksource_init(rate);
diff --git a/drivers/clocksource/timer-npcm7xx.c b/drivers/clocksource/timer-npcm7xx.c
new file mode 100644
index 000000000000..7a9bb5532d99
--- /dev/null
+++ b/drivers/clocksource/timer-npcm7xx.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2014-2018 Nuvoton Technologies tomer.maimon@nuvoton.com
+ * All rights reserved.
+ *
+ * Copyright 2017 Google, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/clockchips.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include "timer-of.h"
+
+/* Timers registers */
+#define NPCM7XX_REG_TCSR0	0x0 /* Timer 0 Control and Status Register */
+#define NPCM7XX_REG_TICR0	0x8 /* Timer 0 Initial Count Register */
+#define NPCM7XX_REG_TCSR1	0x4 /* Timer 1 Control and Status Register */
+#define NPCM7XX_REG_TICR1	0xc /* Timer 1 Initial Count Register */
+#define NPCM7XX_REG_TDR1	0x14 /* Timer 1 Data Register */
+#define NPCM7XX_REG_TISR	0x18 /* Timer Interrupt Status Register */
+
+/* Timers control */
+#define NPCM7XX_Tx_RESETINT		0x1f
+#define NPCM7XX_Tx_PERIOD		BIT(27)
+#define NPCM7XX_Tx_INTEN		BIT(29)
+#define NPCM7XX_Tx_COUNTEN		BIT(30)
+#define NPCM7XX_Tx_ONESHOT		0x0
+#define NPCM7XX_Tx_OPER			GENMASK(3, 27)
+#define NPCM7XX_Tx_MIN_PRESCALE		0x1
+#define NPCM7XX_Tx_TDR_MASK_BITS	24
+#define NPCM7XX_Tx_MAX_CNT		0xFFFFFF
+#define NPCM7XX_T0_CLR_INT		0x1
+#define NPCM7XX_Tx_CLR_CSR		0x0
+
+/* Timers operating mode */
+#define NPCM7XX_START_PERIODIC_Tx (NPCM7XX_Tx_PERIOD | NPCM7XX_Tx_COUNTEN | \
+					NPCM7XX_Tx_INTEN | \
+					NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_START_ONESHOT_Tx (NPCM7XX_Tx_ONESHOT | NPCM7XX_Tx_COUNTEN | \
+					NPCM7XX_Tx_INTEN | \
+					NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_START_Tx (NPCM7XX_Tx_COUNTEN | NPCM7XX_Tx_PERIOD | \
+				NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_DEFAULT_CSR (NPCM7XX_Tx_CLR_CSR | NPCM7XX_Tx_MIN_PRESCALE)
+
+static int npcm7xx_timer_resume(struct clock_event_device *evt)
+{
+	struct timer_of *to = to_timer_of(evt);
+	u32 val;
+
+	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+	val |= NPCM7XX_Tx_COUNTEN;
+	writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+	return 0;
+}
+
+static int npcm7xx_timer_shutdown(struct clock_event_device *evt)
+{
+	struct timer_of *to = to_timer_of(evt);
+	u32 val;
+
+	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+	val &= ~NPCM7XX_Tx_COUNTEN;
+	writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+	return 0;
+}
+
+static int npcm7xx_timer_oneshot(struct clock_event_device *evt)
+{
+	struct timer_of *to = to_timer_of(evt);
+	u32 val;
+
+	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+	val &= ~NPCM7XX_Tx_OPER;
+
+	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+	val |= NPCM7XX_START_ONESHOT_Tx;
+	writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+	return 0;
+}
+
+static int npcm7xx_timer_periodic(struct clock_event_device *evt)
+{
+	struct timer_of *to = to_timer_of(evt);
+	u32 val;
+
+	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+	val &= ~NPCM7XX_Tx_OPER;
+
+	writel(timer_of_period(to), timer_of_base(to) + NPCM7XX_REG_TICR0);
+	val |= NPCM7XX_START_PERIODIC_Tx;
+
+	writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+	return 0;
+}
+
+static int npcm7xx_clockevent_set_next_event(unsigned long evt,
+		struct clock_event_device *clk)
+{
+	struct timer_of *to = to_timer_of(clk);
+	u32 val;
+
+	writel(evt, timer_of_base(to) + NPCM7XX_REG_TICR0);
+	val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+	val |= NPCM7XX_START_Tx;
+	writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+	return 0;
+}
+
+static irqreturn_t npcm7xx_timer0_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = (struct clock_event_device *)dev_id;
+	struct timer_of *to = to_timer_of(evt);
+
+	writel(NPCM7XX_T0_CLR_INT, timer_of_base(to) + NPCM7XX_REG_TISR);
+
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static struct timer_of npcm7xx_to = {
+	.flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+	.clkevt = {
+		.name		    = "npcm7xx-timer0",
+		.features	    = CLOCK_EVT_FEAT_PERIODIC |
+				      CLOCK_EVT_FEAT_ONESHOT,
+		.set_next_event	    = npcm7xx_clockevent_set_next_event,
+		.set_state_shutdown = npcm7xx_timer_shutdown,
+		.set_state_periodic = npcm7xx_timer_periodic,
+		.set_state_oneshot  = npcm7xx_timer_oneshot,
+		.tick_resume	    = npcm7xx_timer_resume,
+		.rating		    = 300,
+	},
+
+	.of_irq = {
+		.handler = npcm7xx_timer0_interrupt,
+		.flags = IRQF_TIMER | IRQF_IRQPOLL,
+	},
+};
+
+static void __init npcm7xx_clockevents_init(void)
+{
+	writel(NPCM7XX_DEFAULT_CSR,
+		timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR0);
+
+	writel(NPCM7XX_Tx_RESETINT,
+		timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TISR);
+
+	npcm7xx_to.clkevt.cpumask = cpumask_of(0);
+	clockevents_config_and_register(&npcm7xx_to.clkevt,
+					timer_of_rate(&npcm7xx_to),
+					0x1, NPCM7XX_Tx_MAX_CNT);
+}
+
+static void __init npcm7xx_clocksource_init(void)
+{
+	u32 val;
+
+	writel(NPCM7XX_DEFAULT_CSR,
+		timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+	writel(NPCM7XX_Tx_MAX_CNT,
+		timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TICR1);
+
+	val = readl(timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+	val |= NPCM7XX_START_Tx;
+	writel(val, timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+
+	clocksource_mmio_init(timer_of_base(&npcm7xx_to) +
+				NPCM7XX_REG_TDR1,
+				"npcm7xx-timer1", timer_of_rate(&npcm7xx_to),
+				200, (unsigned int)NPCM7XX_Tx_TDR_MASK_BITS,
+				clocksource_mmio_readl_down);
+}
+
+static int __init npcm7xx_timer_init(struct device_node *np)
+{
+	int ret;
+
+	ret = timer_of_init(np, &npcm7xx_to);
+	if (ret)
+		return ret;
+
+	/* Clock input is divided by PRESCALE + 1 before it is fed */
+	/* to the counter */
+	npcm7xx_to.of_clk.rate = npcm7xx_to.of_clk.rate /
+		(NPCM7XX_Tx_MIN_PRESCALE + 1);
+
+	npcm7xx_clocksource_init();
+	npcm7xx_clockevents_init();
+
+	pr_info("Enabling NPCM7xx clocksource timer base: %px, IRQ: %d ",
+		timer_of_base(&npcm7xx_to), timer_of_irq(&npcm7xx_to));
+
+	return 0;
+}
+
+TIMER_OF_DECLARE(npcm7xx, "nuvoton,npcm750-timer", npcm7xx_timer_init);
+
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 8615594bd065..e718b8c69a56 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -260,19 +260,6 @@ static int cn_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int cn_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, cn_proc_show, NULL);
-}
-
-static const struct file_operations cn_file_ops = {
-	.owner   = THIS_MODULE,
-	.open    = cn_proc_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release
-};
-
 static struct cn_dev cdev = {
 	.input   = cn_rx_skb,
 };
@@ -297,7 +284,7 @@ static int cn_init(void)
 
 	cn_already_initialized = 1;
 
-	proc_create("connector", S_IRUGO, init_net.proc_net, &cn_file_ops);
+	proc_create_single("connector", S_IRUGO, init_net.proc_net, cn_proc_show);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 7f56fe5183f2..c7ce928fbf1f 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -20,7 +20,7 @@ config ACPI_CPPC_CPUFREQ
 
 config ARM_ARMADA_37XX_CPUFREQ
 	tristate "Armada 37xx CPUFreq support"
-	depends on ARCH_MVEBU
+	depends on ARCH_MVEBU && CPUFREQ_DT
 	help
 	  This adds the CPUFreq driver support for Marvell Armada 37xx SoCs.
 	  The Armada 37xx PMU supports 4 frequency and VDD levels.
@@ -71,16 +71,6 @@ config ARM_BRCMSTB_AVS_CPUFREQ
 
 	  Say Y, if you have a Broadcom SoC with AVS support for DFS or DVFS.
 
-config ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-	bool "Broadcom STB AVS CPUfreq driver sysfs debug capability"
-	depends on ARM_BRCMSTB_AVS_CPUFREQ
-	help
-	  Enabling this option turns on debug support via sysfs under
-	  /sys/kernel/debug/brcmstb-avs-cpufreq. It is possible to read all and
-	  write some AVS mailbox registers through sysfs entries.
-
-	  If in doubt, say N.
-
 config ARM_EXYNOS5440_CPUFREQ
 	tristate "SAMSUNG EXYNOS5440"
 	depends on SOC_EXYNOS5440
@@ -134,6 +124,17 @@ config ARM_OMAP2PLUS_CPUFREQ
 	depends on ARCH_OMAP2PLUS
 	default ARCH_OMAP2PLUS
 
+config ARM_QCOM_CPUFREQ_KRYO
+	bool "Qualcomm Kryo based CPUFreq"
+	depends on ARM64
+	depends on QCOM_QFPROM
+	depends on QCOM_SMEM
+	select PM_OPP
+	help
+	  This adds the CPUFreq driver for Qualcomm Kryo SoC based boards.
+
+	  If in doubt, say N.
+
 config ARM_S3C_CPUFREQ
 	bool
 	help
@@ -274,7 +275,7 @@ config ARM_TANGO_CPUFREQ
 	default y
 
 config ARM_TEGRA20_CPUFREQ
-	bool "Tegra20 CPUFreq support"
+	tristate "Tegra20 CPUFreq support"
 	depends on ARCH_TEGRA
 	default y
 	help
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 8d24ade3bd02..fb4a2ecac43b 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_MACH_MVEBU_V7)		+= mvebu-cpufreq.o
 obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)	+= omap-cpufreq.o
 obj-$(CONFIG_ARM_PXA2xx_CPUFREQ)	+= pxa2xx-cpufreq.o
 obj-$(CONFIG_PXA3xx)			+= pxa3xx-cpufreq.o
+obj-$(CONFIG_ARM_QCOM_CPUFREQ_KRYO)	+= qcom-cpufreq-kryo.o
 obj-$(CONFIG_ARM_S3C2410_CPUFREQ)	+= s3c2410-cpufreq.o
 obj-$(CONFIG_ARM_S3C2412_CPUFREQ)	+= s3c2412-cpufreq.o
 obj-$(CONFIG_ARM_S3C2416_CPUFREQ)	+= s3c2416-cpufreq.o
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 72a2975499db..739da90ff3f6 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -23,6 +23,8 @@
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
+#include "cpufreq-dt.h"
+
 /* Power management in North Bridge register set */
 #define ARMADA_37XX_NB_L0L1	0x18
 #define ARMADA_37XX_NB_L2L3	0x1C
@@ -56,6 +58,16 @@
  */
 #define LOAD_LEVEL_NR	4
 
+struct armada37xx_cpufreq_state {
+	struct regmap *regmap;
+	u32 nb_l0l1;
+	u32 nb_l2l3;
+	u32 nb_dyn_mod;
+	u32 nb_cpu_load;
+};
+
+static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state;
+
 struct armada_37xx_dvfs {
 	u32 cpu_freq_max;
 	u8 divider[LOAD_LEVEL_NR];
@@ -136,7 +148,7 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 	clk_set_parent(clk, parent);
 }
 
-static void __init armada37xx_cpufreq_disable_dvfs(struct regmap *base)
+static void armada37xx_cpufreq_disable_dvfs(struct regmap *base)
 {
 	unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
 		mask = ARMADA_37XX_NB_DFS_EN;
@@ -162,10 +174,47 @@ static void __init armada37xx_cpufreq_enable_dvfs(struct regmap *base)
 	regmap_update_bits(base, reg, mask, mask);
 }
 
+static int armada37xx_cpufreq_suspend(struct cpufreq_policy *policy)
+{
+	struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state;
+
+	regmap_read(state->regmap, ARMADA_37XX_NB_L0L1, &state->nb_l0l1);
+	regmap_read(state->regmap, ARMADA_37XX_NB_L2L3, &state->nb_l2l3);
+	regmap_read(state->regmap, ARMADA_37XX_NB_CPU_LOAD,
+		    &state->nb_cpu_load);
+	regmap_read(state->regmap, ARMADA_37XX_NB_DYN_MOD, &state->nb_dyn_mod);
+
+	return 0;
+}
+
+static int armada37xx_cpufreq_resume(struct cpufreq_policy *policy)
+{
+	struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state;
+
+	/* Ensure DVFS is disabled otherwise the following registers are RO */
+	armada37xx_cpufreq_disable_dvfs(state->regmap);
+
+	regmap_write(state->regmap, ARMADA_37XX_NB_L0L1, state->nb_l0l1);
+	regmap_write(state->regmap, ARMADA_37XX_NB_L2L3, state->nb_l2l3);
+	regmap_write(state->regmap, ARMADA_37XX_NB_CPU_LOAD,
+		     state->nb_cpu_load);
+
+	/*
+	 * NB_DYN_MOD register is the one that actually enable back DVFS if it
+	 * was enabled before the suspend operation. This must be done last
+	 * otherwise other registers are not writable.
+	 */
+	regmap_write(state->regmap, ARMADA_37XX_NB_DYN_MOD, state->nb_dyn_mod);
+
+	return 0;
+}
+
 static int __init armada37xx_cpufreq_driver_init(void)
 {
+	struct cpufreq_dt_platform_data pdata;
 	struct armada_37xx_dvfs *dvfs;
 	struct platform_device *pdev;
+	unsigned long freq;
 	unsigned int cur_frequency;
 	struct regmap *nb_pm_base;
 	struct device *cpu_dev;
@@ -207,33 +256,58 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	}
 
 	dvfs = armada_37xx_cpu_freq_info_get(cur_frequency);
-	if (!dvfs)
+	if (!dvfs) {
+		clk_put(clk);
 		return -EINVAL;
+	}
+
+	armada37xx_cpufreq_state = kmalloc(sizeof(*armada37xx_cpufreq_state),
+					   GFP_KERNEL);
+	if (!armada37xx_cpufreq_state) {
+		clk_put(clk);
+		return -ENOMEM;
+	}
+
+	armada37xx_cpufreq_state->regmap = nb_pm_base;
 
 	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
 	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {
-		unsigned long freq = cur_frequency / dvfs->divider[load_lvl];
+		freq = cur_frequency / dvfs->divider[load_lvl];
 
 		ret = dev_pm_opp_add(cpu_dev, freq, 0);
-		if (ret) {
-			/* clean-up the already added opp before leaving */
-			while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
-				freq = cur_frequency / dvfs->divider[load_lvl];
-				dev_pm_opp_remove(cpu_dev, freq);
-			}
-			return ret;
-		}
+		if (ret)
+			goto remove_opp;
 	}
 
 	/* Now that everything is setup, enable the DVFS at hardware level */
 	armada37xx_cpufreq_enable_dvfs(nb_pm_base);
 
-	pdev = platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+	pdata.suspend = armada37xx_cpufreq_suspend;
+	pdata.resume = armada37xx_cpufreq_resume;
+
+	pdev = platform_device_register_data(NULL, "cpufreq-dt", -1, &pdata,
+					     sizeof(pdata));
+	ret = PTR_ERR_OR_ZERO(pdev);
+	if (ret)
+		goto disable_dvfs;
+
+	return 0;
+
+disable_dvfs:
+	armada37xx_cpufreq_disable_dvfs(nb_pm_base);
+remove_opp:
+	/* clean-up the already added opp before leaving */
+	while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
+		freq = cur_frequency / dvfs->divider[load_lvl];
+		dev_pm_opp_remove(cpu_dev, freq);
+	}
+
+	kfree(armada37xx_cpufreq_state);
 
-	return PTR_ERR_OR_ZERO(pdev);
+	return ret;
 }
 /* late_initcall, to guarantee the driver is loaded after A37xx clock driver */
 late_initcall(armada37xx_cpufreq_driver_init);
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index 6cdac1aaf23c..b07559b9ed99 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -49,13 +49,6 @@
 #include <linux/platform_device.h>
 #include <linux/semaphore.h>
 
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-#include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#endif
-
 /* Max number of arguments AVS calls take */
 #define AVS_MAX_CMD_ARGS	4
 /*
@@ -182,88 +175,11 @@ struct private_data {
 	void __iomem *base;
 	void __iomem *avs_intr_base;
 	struct device *dev;
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-	struct dentry *debugfs;
-#endif
 	struct completion done;
 	struct semaphore sem;
 	struct pmap pmap;
 };
 
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-
-enum debugfs_format {
-	DEBUGFS_NORMAL,
-	DEBUGFS_FLOAT,
-	DEBUGFS_REV,
-};
-
-struct debugfs_data {
-	struct debugfs_entry *entry;
-	struct private_data *priv;
-};
-
-struct debugfs_entry {
-	char *name;
-	u32 offset;
-	fmode_t mode;
-	enum debugfs_format format;
-};
-
-#define DEBUGFS_ENTRY(name, mode, format)	{ \
-	#name, AVS_MBOX_##name, mode, format \
-}
-
-/*
- * These are used for debugfs only. Otherwise we use AVS_MBOX_PARAM() directly.
- */
-#define AVS_MBOX_PARAM1		AVS_MBOX_PARAM(0)
-#define AVS_MBOX_PARAM2		AVS_MBOX_PARAM(1)
-#define AVS_MBOX_PARAM3		AVS_MBOX_PARAM(2)
-#define AVS_MBOX_PARAM4		AVS_MBOX_PARAM(3)
-
-/*
- * This table stores the name, access permissions and offset for each hardware
- * register and is used to generate debugfs entries.
- */
-static struct debugfs_entry debugfs_entries[] = {
-	DEBUGFS_ENTRY(COMMAND, S_IWUSR, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(STATUS, S_IWUSR, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(VOLTAGE0, 0, DEBUGFS_FLOAT),
-	DEBUGFS_ENTRY(TEMP0, 0, DEBUGFS_FLOAT),
-	DEBUGFS_ENTRY(PV0, 0, DEBUGFS_FLOAT),
-	DEBUGFS_ENTRY(MV0, 0, DEBUGFS_FLOAT),
-	DEBUGFS_ENTRY(PARAM1, S_IWUSR, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(PARAM2, S_IWUSR, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(PARAM3, S_IWUSR, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(PARAM4, S_IWUSR, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(REVISION, 0, DEBUGFS_REV),
-	DEBUGFS_ENTRY(PSTATE, 0, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(HEARTBEAT, 0, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(MAGIC, S_IWUSR, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(SIGMA_HVT, 0, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(SIGMA_SVT, 0, DEBUGFS_NORMAL),
-	DEBUGFS_ENTRY(VOLTAGE1, 0, DEBUGFS_FLOAT),
-	DEBUGFS_ENTRY(TEMP1, 0, DEBUGFS_FLOAT),
-	DEBUGFS_ENTRY(PV1, 0, DEBUGFS_FLOAT),
-	DEBUGFS_ENTRY(MV1, 0, DEBUGFS_FLOAT),
-	DEBUGFS_ENTRY(FREQUENCY, 0, DEBUGFS_NORMAL),
-};
-
-static int brcm_avs_target_index(struct cpufreq_policy *, unsigned int);
-
-static char *__strtolower(char *s)
-{
-	char *p;
-
-	for (p = s; *p; p++)
-		*p = tolower(*p);
-
-	return s;
-}
-
-#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */
-
 static void __iomem *__map_region(const char *name)
 {
 	struct device_node *np;
@@ -516,238 +432,6 @@ brcm_avs_get_freq_table(struct device *dev, struct private_data *priv)
 	return table;
 }
 
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-
-#define MANT(x)	(unsigned int)(abs((x)) / 1000)
-#define FRAC(x)	(unsigned int)(abs((x)) - abs((x)) / 1000 * 1000)
-
-static int brcm_avs_debug_show(struct seq_file *s, void *data)
-{
-	struct debugfs_data *dbgfs = s->private;
-	void __iomem *base;
-	u32 val, offset;
-
-	if (!dbgfs) {
-		seq_puts(s, "No device pointer\n");
-		return 0;
-	}
-
-	base = dbgfs->priv->base;
-	offset = dbgfs->entry->offset;
-	val = readl(base + offset);
-	switch (dbgfs->entry->format) {
-	case DEBUGFS_NORMAL:
-		seq_printf(s, "%u\n", val);
-		break;
-	case DEBUGFS_FLOAT:
-		seq_printf(s, "%d.%03d\n", MANT(val), FRAC(val));
-		break;
-	case DEBUGFS_REV:
-		seq_printf(s, "%c.%c.%c.%c\n", (val >> 24 & 0xff),
-			   (val >> 16 & 0xff), (val >> 8 & 0xff),
-			   val & 0xff);
-		break;
-	}
-	seq_printf(s, "0x%08x\n", val);
-
-	return 0;
-}
-
-#undef MANT
-#undef FRAC
-
-static ssize_t brcm_avs_seq_write(struct file *file, const char __user *buf,
-				  size_t size, loff_t *ppos)
-{
-	struct seq_file *s = file->private_data;
-	struct debugfs_data *dbgfs = s->private;
-	struct private_data *priv = dbgfs->priv;
-	void __iomem *base, *avs_intr_base;
-	bool use_issue_command = false;
-	unsigned long val, offset;
-	char str[128];
-	int ret;
-	char *str_ptr = str;
-
-	if (size >= sizeof(str))
-		return -E2BIG;
-
-	memset(str, 0, sizeof(str));
-	ret = copy_from_user(str, buf, size);
-	if (ret)
-		return ret;
-
-	base = priv->base;
-	avs_intr_base = priv->avs_intr_base;
-	offset = dbgfs->entry->offset;
-	/*
-	 * Special case writing to "command" entry only: if the string starts
-	 * with a 'c', we use the driver's __issue_avs_command() function.
-	 * Otherwise, we perform a raw write. This should allow testing of raw
-	 * access as well as using the higher level function. (Raw access
-	 * doesn't clear the firmware return status after issuing the command.)
-	 */
-	if (str_ptr[0] == 'c' && offset == AVS_MBOX_COMMAND) {
-		use_issue_command = true;
-		str_ptr++;
-	}
-	if (kstrtoul(str_ptr, 0, &val) != 0)
-		return -EINVAL;
-
-	/*
-	 * Setting the P-state is a special case. We need to update the CPU
-	 * frequency we report.
-	 */
-	if (val == AVS_CMD_SET_PSTATE) {
-		struct cpufreq_policy *policy;
-		unsigned int pstate;
-
-		policy = cpufreq_cpu_get(smp_processor_id());
-		/* Read back the P-state we are about to set */
-		pstate = readl(base + AVS_MBOX_PARAM(0));
-		if (use_issue_command) {
-			ret = brcm_avs_target_index(policy, pstate);
-			return ret ? ret : size;
-		}
-		policy->cur = policy->freq_table[pstate].frequency;
-	}
-
-	if (use_issue_command) {
-		ret = __issue_avs_command(priv, val, false, NULL);
-	} else {
-		/* Locking here is not perfect, but is only for debug. */
-		ret = down_interruptible(&priv->sem);
-		if (ret)
-			return ret;
-
-		writel(val, base + offset);
-		/* We have to wake up the firmware to process a command. */
-		if (offset == AVS_MBOX_COMMAND)
-			writel(AVS_CPU_L2_INT_MASK,
-			       avs_intr_base + AVS_CPU_L2_SET0);
-		up(&priv->sem);
-	}
-
-	return ret ? ret : size;
-}
-
-static struct debugfs_entry *__find_debugfs_entry(const char *name)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++)
-		if (strcasecmp(debugfs_entries[i].name, name) == 0)
-			return &debugfs_entries[i];
-
-	return NULL;
-}
-
-static int brcm_avs_debug_open(struct inode *inode, struct file *file)
-{
-	struct debugfs_data *data;
-	fmode_t fmode;
-	int ret;
-
-	/*
-	 * seq_open(), which is called by single_open(), clears "write" access.
-	 * We need write access to some files, so we preserve our access mode
-	 * and restore it.
-	 */
-	fmode = file->f_mode;
-	/*
-	 * Check access permissions even for root. We don't want to be writing
-	 * to read-only registers. Access for regular users has already been
-	 * checked by the VFS layer.
-	 */
-	if ((fmode & FMODE_WRITER) && !(inode->i_mode & S_IWUSR))
-		return -EACCES;
-
-	data = kmalloc(sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-	/*
-	 * We use the same file system operations for all our debug files. To
-	 * produce specific output, we look up the file name upon opening a
-	 * debugfs entry and map it to a memory offset. This offset is then used
-	 * in the generic "show" function to read a specific register.
-	 */
-	data->entry = __find_debugfs_entry(file->f_path.dentry->d_iname);
-	data->priv = inode->i_private;
-
-	ret = single_open(file, brcm_avs_debug_show, data);
-	if (ret)
-		kfree(data);
-	file->f_mode = fmode;
-
-	return ret;
-}
-
-static int brcm_avs_debug_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq_priv = file->private_data;
-	struct debugfs_data *data = seq_priv->private;
-
-	kfree(data);
-	return single_release(inode, file);
-}
-
-static const struct file_operations brcm_avs_debug_ops = {
-	.open		= brcm_avs_debug_open,
-	.read		= seq_read,
-	.write		= brcm_avs_seq_write,
-	.llseek		= seq_lseek,
-	.release	= brcm_avs_debug_release,
-};
-
-static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev)
-{
-	struct private_data *priv = platform_get_drvdata(pdev);
-	struct dentry *dir;
-	int i;
-
-	if (!priv)
-		return;
-
-	dir = debugfs_create_dir(BRCM_AVS_CPUFREQ_NAME, NULL);
-	if (IS_ERR_OR_NULL(dir))
-		return;
-	priv->debugfs = dir;
-
-	for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++) {
-		/*
-		 * The DEBUGFS_ENTRY macro generates uppercase strings. We
-		 * convert them to lowercase before creating the debugfs
-		 * entries.
-		 */
-		char *entry = __strtolower(debugfs_entries[i].name);
-		fmode_t mode = debugfs_entries[i].mode;
-
-		if (!debugfs_create_file(entry, S_IFREG | S_IRUGO | mode,
-					 dir, priv, &brcm_avs_debug_ops)) {
-			priv->debugfs = NULL;
-			debugfs_remove_recursive(dir);
-			break;
-		}
-	}
-}
-
-static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev)
-{
-	struct private_data *priv = platform_get_drvdata(pdev);
-
-	if (priv && priv->debugfs) {
-		debugfs_remove_recursive(priv->debugfs);
-		priv->debugfs = NULL;
-	}
-}
-
-#else
-
-static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev) {}
-static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev) {}
-
-#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */
-
 /*
  * To ensure the right firmware is running we need to
  *    - check the MAGIC matches what we expect
@@ -1016,11 +700,8 @@ static int brcm_avs_cpufreq_probe(struct platform_device *pdev)
 		return ret;
 
 	brcm_avs_driver.driver_data = pdev;
-	ret = cpufreq_register_driver(&brcm_avs_driver);
-	if (!ret)
-		brcm_avs_cpufreq_debug_init(pdev);
 
-	return ret;
+	return cpufreq_register_driver(&brcm_avs_driver);
 }
 
 static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
@@ -1032,8 +713,6 @@ static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	brcm_avs_cpufreq_debug_exit(pdev);
-
 	priv = platform_get_drvdata(pdev);
 	iounmap(priv->base);
 	iounmap(priv->avs_intr_base);
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index bc5fc1630876..3464580ac3ca 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -42,9 +42,6 @@
  */
 static struct cppc_cpudata **all_cpu_data;
 
-/* Capture the max KHz from DMI */
-static u64 cppc_dmi_max_khz;
-
 /* Callback function used to retrieve the max frequency from DMI */
 static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
 {
@@ -75,6 +72,64 @@ static u64 cppc_get_dmi_max_khz(void)
 	return (1000 * mhz);
 }
 
+/*
+ * If CPPC lowest_freq and nominal_freq registers are exposed then we can
+ * use them to convert perf to freq and vice versa
+ *
+ * If the perf/freq point lies between Nominal and Lowest, we can treat
+ * (Low perf, Low freq) and (Nom Perf, Nom freq) as 2D co-ordinates of a line
+ * and extrapolate the rest
+ * For perf/freq > Nominal, we use the ratio perf:freq at Nominal for conversion
+ */
+static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu,
+					unsigned int perf)
+{
+	static u64 max_khz;
+	struct cppc_perf_caps *caps = &cpu->perf_caps;
+	u64 mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		if (perf >= caps->nominal_perf) {
+			mul = caps->nominal_freq;
+			div = caps->nominal_perf;
+		} else {
+			mul = caps->nominal_freq - caps->lowest_freq;
+			div = caps->nominal_perf - caps->lowest_perf;
+		}
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = max_khz;
+		div = cpu->perf_caps.highest_perf;
+	}
+	return (u64)perf * mul / div;
+}
+
+static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu,
+					unsigned int freq)
+{
+	static u64 max_khz;
+	struct cppc_perf_caps *caps = &cpu->perf_caps;
+	u64  mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		if (freq >= caps->nominal_freq) {
+			mul = caps->nominal_perf;
+			div = caps->nominal_freq;
+		} else {
+			mul = caps->lowest_perf;
+			div = caps->lowest_freq;
+		}
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = cpu->perf_caps.highest_perf;
+		div = max_khz;
+	}
+
+	return (u64)freq * mul / div;
+}
+
 static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 		unsigned int target_freq,
 		unsigned int relation)
@@ -86,7 +141,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 
 	cpu = all_cpu_data[policy->cpu];
 
-	desired_perf = (u64)target_freq * cpu->perf_caps.highest_perf / cppc_dmi_max_khz;
+	desired_perf = cppc_cpufreq_khz_to_perf(cpu, target_freq);
 	/* Return if it is exactly the same perf */
 	if (desired_perf == cpu->perf_ctrls.desired_perf)
 		return ret;
@@ -126,6 +181,49 @@ static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 				cpu->perf_caps.lowest_perf, cpu_num, ret);
 }
 
+/*
+ * The PCC subspace describes the rate at which platform can accept commands
+ * on the shared PCC channel (including READs which do not count towards freq
+ * trasition requests), so ideally we need to use the PCC values as a fallback
+ * if we don't have a platform specific transition_delay_us
+ */
+#ifdef CONFIG_ARM64
+#include <asm/cputype.h>
+
+static unsigned int cppc_cpufreq_get_transition_delay_us(int cpu)
+{
+	unsigned long implementor = read_cpuid_implementor();
+	unsigned long part_num = read_cpuid_part_number();
+	unsigned int delay_us = 0;
+
+	switch (implementor) {
+	case ARM_CPU_IMP_QCOM:
+		switch (part_num) {
+		case QCOM_CPU_PART_FALKOR_V1:
+		case QCOM_CPU_PART_FALKOR:
+			delay_us = 10000;
+			break;
+		default:
+			delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+			break;
+		}
+		break;
+	default:
+		delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+		break;
+	}
+
+	return delay_us;
+}
+
+#else
+
+static unsigned int cppc_cpufreq_get_transition_delay_us(int cpu)
+{
+	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+}
+#endif
+
 static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
 	struct cppc_cpudata *cpu;
@@ -143,27 +241,26 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		return ret;
 	}
 
-	cppc_dmi_max_khz = cppc_get_dmi_max_khz();
+	/* Convert the lowest and nominal freq from MHz to KHz */
+	cpu->perf_caps.lowest_freq *= 1000;
+	cpu->perf_caps.nominal_freq *= 1000;
 
 	/*
 	 * Set min to lowest nonlinear perf to avoid any efficiency penalty (see
 	 * Section 8.4.7.1.1.5 of ACPI 6.1 spec)
 	 */
-	policy->min = cpu->perf_caps.lowest_nonlinear_perf * cppc_dmi_max_khz /
-		cpu->perf_caps.highest_perf;
-	policy->max = cppc_dmi_max_khz;
+	policy->min = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.lowest_nonlinear_perf);
+	policy->max = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf);
 
 	/*
 	 * Set cpuinfo.min_freq to Lowest to make the full range of performance
 	 * available if userspace wants to use any perf between lowest & lowest
 	 * nonlinear perf
 	 */
-	policy->cpuinfo.min_freq = cpu->perf_caps.lowest_perf * cppc_dmi_max_khz /
-		cpu->perf_caps.highest_perf;
-	policy->cpuinfo.max_freq = cppc_dmi_max_khz;
+	policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.lowest_perf);
+	policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf);
 
-	policy->transition_delay_us = cppc_get_transition_latency(cpu_num) /
-		NSEC_PER_USEC;
+	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu_num);
 	policy->shared_type = cpu->shared_type;
 
 	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
@@ -187,7 +284,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	cpu->cur_policy = policy;
 
 	/* Set policy->cur to max now. The governors will adjust later. */
-	policy->cur = cppc_dmi_max_khz;
+	policy->cur = cppc_cpufreq_perf_to_khz(cpu,
+					cpu->perf_caps.highest_perf);
 	cpu->perf_ctrls.desired_perf = cpu->perf_caps.highest_perf;
 
 	ret = cppc_set_perf(cpu_num, &cpu->perf_ctrls);
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 3b585e4bfac5..fe14c57de6ca 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -66,8 +66,6 @@ static const struct of_device_id whitelist[] __initconst = {
 	{ .compatible = "renesas,r8a7792", },
 	{ .compatible = "renesas,r8a7793", },
 	{ .compatible = "renesas,r8a7794", },
-	{ .compatible = "renesas,r8a7795", },
-	{ .compatible = "renesas,r8a7796", },
 	{ .compatible = "renesas,sh73a0", },
 
 	{ .compatible = "rockchip,rk2928", },
@@ -118,6 +116,9 @@ static const struct of_device_id blacklist[] __initconst = {
 
 	{ .compatible = "nvidia,tegra124", },
 
+	{ .compatible = "qcom,apq8096", },
+	{ .compatible = "qcom,msm8996", },
+
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },
 
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 190ea0dccb79..0a9ebf00be46 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -346,8 +346,14 @@ static int dt_cpufreq_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	if (data && data->have_governor_per_policy)
-		dt_cpufreq_driver.flags |= CPUFREQ_HAVE_GOVERNOR_PER_POLICY;
+	if (data) {
+		if (data->have_governor_per_policy)
+			dt_cpufreq_driver.flags |= CPUFREQ_HAVE_GOVERNOR_PER_POLICY;
+
+		dt_cpufreq_driver.resume = data->resume;
+		if (data->suspend)
+			dt_cpufreq_driver.suspend = data->suspend;
+	}
 
 	ret = cpufreq_register_driver(&dt_cpufreq_driver);
 	if (ret)
diff --git a/drivers/cpufreq/cpufreq-dt.h b/drivers/cpufreq/cpufreq-dt.h
index 54d774e46c43..d5aeea13433e 100644
--- a/drivers/cpufreq/cpufreq-dt.h
+++ b/drivers/cpufreq/cpufreq-dt.h
@@ -12,8 +12,13 @@
 
 #include <linux/types.h>
 
+struct cpufreq_policy;
+
 struct cpufreq_dt_platform_data {
 	bool have_governor_per_policy;
+
+	int (*suspend)(struct cpufreq_policy *policy);
+	int (*resume)(struct cpufreq_policy *policy);
 };
 
 #endif /* __CPUFREQ_DT_H__ */
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 075d18f6ba7a..b0dfd3222013 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -89,16 +89,7 @@ static void cpufreq_governor_limits(struct cpufreq_policy *policy);
  * The mutex locks both lists.
  */
 static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
-static struct srcu_notifier_head cpufreq_transition_notifier_list;
-
-static bool init_cpufreq_transition_notifier_list_called;
-static int __init init_cpufreq_transition_notifier_list(void)
-{
-	srcu_init_notifier_head(&cpufreq_transition_notifier_list);
-	init_cpufreq_transition_notifier_list_called = true;
-	return 0;
-}
-pure_initcall(init_cpufreq_transition_notifier_list);
+SRCU_NOTIFIER_HEAD_STATIC(cpufreq_transition_notifier_list);
 
 static int off __read_mostly;
 static int cpufreq_disabled(void)
@@ -300,8 +291,19 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
 #endif
 }
 
-static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
-		struct cpufreq_freqs *freqs, unsigned int state)
+/**
+ * cpufreq_notify_transition - Notify frequency transition and adjust_jiffies.
+ * @policy: cpufreq policy to enable fast frequency switching for.
+ * @freqs: contain details of the frequency update.
+ * @state: set to CPUFREQ_PRECHANGE or CPUFREQ_POSTCHANGE.
+ *
+ * This function calls the transition notifiers and the "adjust_jiffies"
+ * function. It is called twice on all CPU frequency changes that have
+ * external effects.
+ */
+static void cpufreq_notify_transition(struct cpufreq_policy *policy,
+				      struct cpufreq_freqs *freqs,
+				      unsigned int state)
 {
 	BUG_ON(irqs_disabled());
 
@@ -313,54 +315,44 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 		 state, freqs->new);
 
 	switch (state) {
-
 	case CPUFREQ_PRECHANGE:
-		/* detect if the driver reported a value as "old frequency"
+		/*
+		 * Detect if the driver reported a value as "old frequency"
 		 * which is not equal to what the cpufreq core thinks is
 		 * "old frequency".
 		 */
 		if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
-			if ((policy) && (policy->cpu == freqs->cpu) &&
-			    (policy->cur) && (policy->cur != freqs->old)) {
+			if (policy->cur && (policy->cur != freqs->old)) {
 				pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
 					 freqs->old, policy->cur);
 				freqs->old = policy->cur;
 			}
 		}
-		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
-				CPUFREQ_PRECHANGE, freqs);
+
+		for_each_cpu(freqs->cpu, policy->cpus) {
+			srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
+						 CPUFREQ_PRECHANGE, freqs);
+		}
+
 		adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
 		break;
 
 	case CPUFREQ_POSTCHANGE:
 		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
-		pr_debug("FREQ: %lu - CPU: %lu\n",
-			 (unsigned long)freqs->new, (unsigned long)freqs->cpu);
-		trace_cpu_frequency(freqs->new, freqs->cpu);
+		pr_debug("FREQ: %u - CPUs: %*pbl\n", freqs->new,
+			 cpumask_pr_args(policy->cpus));
+
+		for_each_cpu(freqs->cpu, policy->cpus) {
+			trace_cpu_frequency(freqs->new, freqs->cpu);
+			srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
+						 CPUFREQ_POSTCHANGE, freqs);
+		}
+
 		cpufreq_stats_record_transition(policy, freqs->new);
-		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
-				CPUFREQ_POSTCHANGE, freqs);
-		if (likely(policy) && likely(policy->cpu == freqs->cpu))
-			policy->cur = freqs->new;
-		break;
+		policy->cur = freqs->new;
 	}
 }
 
-/**
- * cpufreq_notify_transition - call notifier chain and adjust_jiffies
- * on frequency transition.
- *
- * This function calls the transition notifiers and the "adjust_jiffies"
- * function. It is called twice on all CPU frequency changes that have
- * external effects.
- */
-static void cpufreq_notify_transition(struct cpufreq_policy *policy,
-		struct cpufreq_freqs *freqs, unsigned int state)
-{
-	for_each_cpu(freqs->cpu, policy->cpus)
-		__cpufreq_notify_transition(policy, freqs, state);
-}
-
 /* Do post notifications when there are chances that transition has failed */
 static void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs, int transition_failed)
@@ -696,6 +688,8 @@ static ssize_t store_##file_name					\
 	struct cpufreq_policy new_policy;				\
 									\
 	memcpy(&new_policy, policy, sizeof(*policy));			\
+	new_policy.min = policy->user_policy.min;			\
+	new_policy.max = policy->user_policy.max;			\
 									\
 	ret = sscanf(buf, "%u", &new_policy.object);			\
 	if (ret != 1)							\
@@ -1764,8 +1758,6 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
 	if (cpufreq_disabled())
 		return -EINVAL;
 
-	WARN_ON(!init_cpufreq_transition_notifier_list_called);
-
 	switch (list) {
 	case CPUFREQ_TRANSITION_NOTIFIER:
 		mutex_lock(&cpufreq_fast_switch_lock);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index ca38229b045a..871bf9cf55cf 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -278,7 +278,7 @@ static void dbs_update_util_handler(struct update_util_data *data, u64 time,
 	struct policy_dbs_info *policy_dbs = cdbs->policy_dbs;
 	u64 delta_ns, lst;
 
-	if (!cpufreq_can_do_remote_dvfs(policy_dbs->policy))
+	if (!cpufreq_this_cpu_can_update(policy_dbs->policy))
 		return;
 
 	/*
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 17e566afbb41..08960a55eb27 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1939,13 +1939,51 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
 	return 0;
 }
 
+/* Use of trace in passive mode:
+ *
+ * In passive mode the trace core_busy field (also known as the
+ * performance field, and lablelled as such on the graphs; also known as
+ * core_avg_perf) is not needed and so is re-assigned to indicate if the
+ * driver call was via the normal or fast switch path. Various graphs
+ * output from the intel_pstate_tracer.py utility that include core_busy
+ * (or performance or core_avg_perf) have a fixed y-axis from 0 to 100%,
+ * so we use 10 to indicate the the normal path through the driver, and
+ * 90 to indicate the fast switch path through the driver.
+ * The scaled_busy field is not used, and is set to 0.
+ */
+
+#define	INTEL_PSTATE_TRACE_TARGET 10
+#define	INTEL_PSTATE_TRACE_FAST_SWITCH 90
+
+static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, int old_pstate)
+{
+	struct sample *sample;
+
+	if (!trace_pstate_sample_enabled())
+		return;
+
+	if (!intel_pstate_sample(cpu, ktime_get()))
+		return;
+
+	sample = &cpu->sample;
+	trace_pstate_sample(trace_type,
+		0,
+		old_pstate,
+		cpu->pstate.current_pstate,
+		sample->mperf,
+		sample->aperf,
+		sample->tsc,
+		get_avg_frequency(cpu),
+		fp_toint(cpu->iowait_boost * 100));
+}
+
 static int intel_cpufreq_target(struct cpufreq_policy *policy,
 				unsigned int target_freq,
 				unsigned int relation)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
 	struct cpufreq_freqs freqs;
-	int target_pstate;
+	int target_pstate, old_pstate;
 
 	update_turbo_state();
 
@@ -1965,12 +2003,14 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 		break;
 	}
 	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+	old_pstate = cpu->pstate.current_pstate;
 	if (target_pstate != cpu->pstate.current_pstate) {
 		cpu->pstate.current_pstate = target_pstate;
 		wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL,
 			      pstate_funcs.get_val(cpu, target_pstate));
 	}
 	freqs.new = target_pstate * cpu->pstate.scaling;
+	intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_TARGET, old_pstate);
 	cpufreq_freq_transition_end(policy, &freqs, false);
 
 	return 0;
@@ -1980,13 +2020,15 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
-	int target_pstate;
+	int target_pstate, old_pstate;
 
 	update_turbo_state();
 
 	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
 	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+	old_pstate = cpu->pstate.current_pstate;
 	intel_pstate_update_pstate(cpu, target_pstate);
+	intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_FAST_SWITCH, old_pstate);
 	return target_pstate * cpu->pstate.scaling;
 }
 
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 0591874856d3..54edaec1e608 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -679,6 +679,16 @@ void gpstate_timer_handler(struct timer_list *t)
 
 	if (!spin_trylock(&gpstates->gpstate_lock))
 		return;
+	/*
+	 * If the timer has migrated to the different cpu then bring
+	 * it back to one of the policy->cpus
+	 */
+	if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) {
+		gpstates->timer.expires = jiffies + msecs_to_jiffies(1);
+		add_timer_on(&gpstates->timer, cpumask_first(policy->cpus));
+		spin_unlock(&gpstates->gpstate_lock);
+		return;
+	}
 
 	/*
 	 * If PMCR was last updated was using fast_swtich then
@@ -718,10 +728,8 @@ void gpstate_timer_handler(struct timer_list *t)
 	if (gpstate_idx != gpstates->last_lpstate_idx)
 		queue_gpstate_timer(gpstates);
 
+	set_pstate(&freq_data);
 	spin_unlock(&gpstates->gpstate_lock);
-
-	/* Timer may get migrated to a different cpu on cpu hot unplug */
-	smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
 }
 
 /*
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
new file mode 100644
index 000000000000..d049fe4b80c4
--- /dev/null
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+/*
+ * In Certain QCOM SoCs like apq8096 and msm8996 that have KRYO processors,
+ * the CPU frequency subset and voltage value of each OPP varies
+ * based on the silicon variant in use. Qualcomm Process Voltage Scaling Tables
+ * defines the voltage and frequency value based on the msm-id in SMEM
+ * and speedbin blown in the efuse combination.
+ * The qcom-cpufreq-kryo driver reads the msm-id and efuse value from the SoC
+ * to provide the OPP framework with required information.
+ * This is used to determine the voltage and frequency value for each OPP of
+ * operating-points-v2 table when it is parsed by the OPP framework.
+ */
+
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/smem.h>
+
+#define MSM_ID_SMEM	137
+
+enum _msm_id {
+	MSM8996V3 = 0xF6ul,
+	APQ8096V3 = 0x123ul,
+	MSM8996SG = 0x131ul,
+	APQ8096SG = 0x138ul,
+};
+
+enum _msm8996_version {
+	MSM8996_V3,
+	MSM8996_SG,
+	NUM_OF_MSM8996_VERSIONS,
+};
+
+static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
+{
+	size_t len;
+	u32 *msm_id;
+	enum _msm8996_version version;
+
+	msm_id = qcom_smem_get(QCOM_SMEM_HOST_ANY, MSM_ID_SMEM, &len);
+	if (IS_ERR(msm_id))
+		return NUM_OF_MSM8996_VERSIONS;
+
+	/* The first 4 bytes are format, next to them is the actual msm-id */
+	msm_id++;
+
+	switch ((enum _msm_id)*msm_id) {
+	case MSM8996V3:
+	case APQ8096V3:
+		version = MSM8996_V3;
+		break;
+	case MSM8996SG:
+	case APQ8096SG:
+		version = MSM8996_SG;
+		break;
+	default:
+		version = NUM_OF_MSM8996_VERSIONS;
+	}
+
+	return version;
+}
+
+static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
+{
+	struct opp_table *opp_tables[NR_CPUS] = {0};
+	struct platform_device *cpufreq_dt_pdev;
+	enum _msm8996_version msm8996_version;
+	struct nvmem_cell *speedbin_nvmem;
+	struct device_node *np;
+	struct device *cpu_dev;
+	unsigned cpu;
+	u8 *speedbin;
+	u32 versions;
+	size_t len;
+	int ret;
+
+	cpu_dev = get_cpu_device(0);
+	if (NULL == cpu_dev)
+		ret = -ENODEV;
+
+	msm8996_version = qcom_cpufreq_kryo_get_msm_id();
+	if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
+		dev_err(cpu_dev, "Not Snapdragon 820/821!");
+		return -ENODEV;
+	}
+
+	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
+	if (IS_ERR(np))
+		return PTR_ERR(np);
+
+	ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
+	if (!ret) {
+		of_node_put(np);
+		return -ENOENT;
+	}
+
+	speedbin_nvmem = of_nvmem_cell_get(np, NULL);
+	of_node_put(np);
+	if (IS_ERR(speedbin_nvmem)) {
+		dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
+			PTR_ERR(speedbin_nvmem));
+		return PTR_ERR(speedbin_nvmem);
+	}
+
+	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
+	nvmem_cell_put(speedbin_nvmem);
+
+	switch (msm8996_version) {
+	case MSM8996_V3:
+		versions = 1 << (unsigned int)(*speedbin);
+		break;
+	case MSM8996_SG:
+		versions = 1 << ((unsigned int)(*speedbin) + 4);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	for_each_possible_cpu(cpu) {
+		cpu_dev = get_cpu_device(cpu);
+		if (NULL == cpu_dev) {
+			ret = -ENODEV;
+			goto free_opp;
+		}
+
+		opp_tables[cpu] = dev_pm_opp_set_supported_hw(cpu_dev,
+							      &versions, 1);
+		if (IS_ERR(opp_tables[cpu])) {
+			ret = PTR_ERR(opp_tables[cpu]);
+			dev_err(cpu_dev, "Failed to set supported hardware\n");
+			goto free_opp;
+		}
+	}
+
+	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
+							  NULL, 0);
+	if (!IS_ERR(cpufreq_dt_pdev))
+		return 0;
+
+	ret = PTR_ERR(cpufreq_dt_pdev);
+	dev_err(cpu_dev, "Failed to register platform device\n");
+
+free_opp:
+	for_each_possible_cpu(cpu) {
+		if (IS_ERR_OR_NULL(opp_tables[cpu]))
+			break;
+		dev_pm_opp_put_supported_hw(opp_tables[cpu]);
+	}
+
+	return ret;
+}
+
+static struct platform_driver qcom_cpufreq_kryo_driver = {
+	.probe = qcom_cpufreq_kryo_probe,
+	.driver = {
+		.name = "qcom-cpufreq-kryo",
+	},
+};
+
+static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = {
+	{ .compatible = "qcom,apq8096", },
+	{ .compatible = "qcom,msm8996", },
+};
+
+/*
+ * Since the driver depends on smem and nvmem drivers, which may
+ * return EPROBE_DEFER, all the real activity is done in the probe,
+ * which may be defered as well. The init here is only registering
+ * the driver and the platform device.
+ */
+static int __init qcom_cpufreq_kryo_init(void)
+{
+	struct device_node *np = of_find_node_by_path("/");
+	const struct of_device_id *match;
+	int ret;
+
+	if (!np)
+		return -ENODEV;
+
+	match = of_match_node(qcom_cpufreq_kryo_match_list, np);
+	of_node_put(np);
+	if (!match)
+		return -ENODEV;
+
+	ret = platform_driver_register(&qcom_cpufreq_kryo_driver);
+	if (unlikely(ret < 0))
+		return ret;
+
+	ret = PTR_ERR_OR_ZERO(platform_device_register_simple(
+		"qcom-cpufreq-kryo", -1, NULL, 0));
+	if (0 == ret)
+		return 0;
+
+	platform_driver_unregister(&qcom_cpufreq_kryo_driver);
+	return ret;
+}
+module_init(qcom_cpufreq_kryo_init);
+
+MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/s3c2440-cpufreq.c b/drivers/cpufreq/s3c2440-cpufreq.c
index d0d75b65ddd6..d2f67b7a20dd 100644
--- a/drivers/cpufreq/s3c2440-cpufreq.c
+++ b/drivers/cpufreq/s3c2440-cpufreq.c
@@ -143,7 +143,7 @@ static void s3c2440_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
 {
 	unsigned long clkdiv, camdiv;
 
-	s3c_freq_dbg("%s: divsiors: h=%d, p=%d\n", __func__,
+	s3c_freq_dbg("%s: divisors: h=%d, p=%d\n", __func__,
 		     cfg->divs.h_divisor, cfg->divs.p_divisor);
 
 	clkdiv = __raw_readl(S3C2410_CLKDIVN);
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index e3a9962ee410..cabb6f48eb77 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -252,7 +252,7 @@ EXPORT_SYMBOL_GPL(speedstep_get_frequency);
  *********************************************************************/
 
 /* Keep in sync with the x86_cpu_id tables in the different modules */
-unsigned int speedstep_detect_processor(void)
+enum speedstep_processor speedstep_detect_processor(void)
 {
 	struct cpuinfo_x86 *c = &cpu_data(0);
 	u32 ebx, msr_lo, msr_hi;
diff --git a/drivers/cpufreq/tegra20-cpufreq.c b/drivers/cpufreq/tegra20-cpufreq.c
index 2bd62845e9d5..05f57dcd5215 100644
--- a/drivers/cpufreq/tegra20-cpufreq.c
+++ b/drivers/cpufreq/tegra20-cpufreq.c
@@ -16,16 +16,13 @@
  *
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/clk.h>
 #include <linux/cpufreq.h>
-#include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
 
 static struct cpufreq_frequency_table freq_table[] = {
 	{ .frequency = 216000 },
@@ -39,25 +36,27 @@ static struct cpufreq_frequency_table freq_table[] = {
 	{ .frequency = CPUFREQ_TABLE_END },
 };
 
-#define NUM_CPUS	2
-
-static struct clk *cpu_clk;
-static struct clk *pll_x_clk;
-static struct clk *pll_p_clk;
-static struct clk *emc_clk;
-static bool pll_x_prepared;
+struct tegra20_cpufreq {
+	struct device *dev;
+	struct cpufreq_driver driver;
+	struct clk *cpu_clk;
+	struct clk *pll_x_clk;
+	struct clk *pll_p_clk;
+	bool pll_x_prepared;
+};
 
 static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy,
 					   unsigned int index)
 {
-	unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
+	unsigned int ifreq = clk_get_rate(cpufreq->pll_p_clk) / 1000;
 
 	/*
 	 * Don't switch to intermediate freq if:
 	 * - we are already at it, i.e. policy->cur == ifreq
 	 * - index corresponds to ifreq
 	 */
-	if ((freq_table[index].frequency == ifreq) || (policy->cur == ifreq))
+	if (freq_table[index].frequency == ifreq || policy->cur == ifreq)
 		return 0;
 
 	return ifreq;
@@ -66,6 +65,7 @@ static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy,
 static int tegra_target_intermediate(struct cpufreq_policy *policy,
 				     unsigned int index)
 {
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
 	int ret;
 
 	/*
@@ -78,47 +78,37 @@ static int tegra_target_intermediate(struct cpufreq_policy *policy,
 	 * Also, we wouldn't be using pll_x anymore and must not take extra
 	 * reference to it, as it can be disabled now to save some power.
 	 */
-	clk_prepare_enable(pll_x_clk);
+	clk_prepare_enable(cpufreq->pll_x_clk);
 
-	ret = clk_set_parent(cpu_clk, pll_p_clk);
+	ret = clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_p_clk);
 	if (ret)
-		clk_disable_unprepare(pll_x_clk);
+		clk_disable_unprepare(cpufreq->pll_x_clk);
 	else
-		pll_x_prepared = true;
+		cpufreq->pll_x_prepared = true;
 
 	return ret;
 }
 
 static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 {
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
 	unsigned long rate = freq_table[index].frequency;
-	unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
-	int ret = 0;
-
-	/*
-	 * Vote on memory bus frequency based on cpu frequency
-	 * This sets the minimum frequency, display or avp may request higher
-	 */
-	if (rate >= 816000)
-		clk_set_rate(emc_clk, 600000000); /* cpu 816 MHz, emc max */
-	else if (rate >= 456000)
-		clk_set_rate(emc_clk, 300000000); /* cpu 456 MHz, emc 150Mhz */
-	else
-		clk_set_rate(emc_clk, 100000000);  /* emc 50Mhz */
+	unsigned int ifreq = clk_get_rate(cpufreq->pll_p_clk) / 1000;
+	int ret;
 
 	/*
 	 * target freq == pll_p, don't need to take extra reference to pll_x_clk
 	 * as it isn't used anymore.
 	 */
 	if (rate == ifreq)
-		return clk_set_parent(cpu_clk, pll_p_clk);
+		return clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_p_clk);
 
-	ret = clk_set_rate(pll_x_clk, rate * 1000);
+	ret = clk_set_rate(cpufreq->pll_x_clk, rate * 1000);
 	/* Restore to earlier frequency on error, i.e. pll_x */
 	if (ret)
-		pr_err("Failed to change pll_x to %lu\n", rate);
+		dev_err(cpufreq->dev, "Failed to change pll_x to %lu\n", rate);
 
-	ret = clk_set_parent(cpu_clk, pll_x_clk);
+	ret = clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_x_clk);
 	/* This shouldn't fail while changing or restoring */
 	WARN_ON(ret);
 
@@ -126,9 +116,9 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 	 * Drop count to pll_x clock only if we switched to intermediate freq
 	 * earlier while transitioning to a target frequency.
 	 */
-	if (pll_x_prepared) {
-		clk_disable_unprepare(pll_x_clk);
-		pll_x_prepared = false;
+	if (cpufreq->pll_x_prepared) {
+		clk_disable_unprepare(cpufreq->pll_x_clk);
+		cpufreq->pll_x_prepared = false;
 	}
 
 	return ret;
@@ -136,81 +126,111 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 
 static int tegra_cpu_init(struct cpufreq_policy *policy)
 {
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
 	int ret;
 
-	if (policy->cpu >= NUM_CPUS)
-		return -EINVAL;
-
-	clk_prepare_enable(emc_clk);
-	clk_prepare_enable(cpu_clk);
+	clk_prepare_enable(cpufreq->cpu_clk);
 
 	/* FIXME: what's the actual transition time? */
 	ret = cpufreq_generic_init(policy, freq_table, 300 * 1000);
 	if (ret) {
-		clk_disable_unprepare(cpu_clk);
-		clk_disable_unprepare(emc_clk);
+		clk_disable_unprepare(cpufreq->cpu_clk);
 		return ret;
 	}
 
-	policy->clk = cpu_clk;
+	policy->clk = cpufreq->cpu_clk;
 	policy->suspend_freq = freq_table[0].frequency;
 	return 0;
 }
 
 static int tegra_cpu_exit(struct cpufreq_policy *policy)
 {
-	clk_disable_unprepare(cpu_clk);
-	clk_disable_unprepare(emc_clk);
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
+
+	clk_disable_unprepare(cpufreq->cpu_clk);
 	return 0;
 }
 
-static struct cpufreq_driver tegra_cpufreq_driver = {
-	.flags			= CPUFREQ_NEED_INITIAL_FREQ_CHECK,
-	.verify			= cpufreq_generic_frequency_table_verify,
-	.get_intermediate	= tegra_get_intermediate,
-	.target_intermediate	= tegra_target_intermediate,
-	.target_index		= tegra_target,
-	.get			= cpufreq_generic_get,
-	.init			= tegra_cpu_init,
-	.exit			= tegra_cpu_exit,
-	.name			= "tegra",
-	.attr			= cpufreq_generic_attr,
-	.suspend		= cpufreq_generic_suspend,
-};
-
-static int __init tegra_cpufreq_init(void)
+static int tegra20_cpufreq_probe(struct platform_device *pdev)
 {
-	cpu_clk = clk_get_sys(NULL, "cclk");
-	if (IS_ERR(cpu_clk))
-		return PTR_ERR(cpu_clk);
-
-	pll_x_clk = clk_get_sys(NULL, "pll_x");
-	if (IS_ERR(pll_x_clk))
-		return PTR_ERR(pll_x_clk);
-
-	pll_p_clk = clk_get_sys(NULL, "pll_p");
-	if (IS_ERR(pll_p_clk))
-		return PTR_ERR(pll_p_clk);
-
-	emc_clk = clk_get_sys("cpu", "emc");
-	if (IS_ERR(emc_clk)) {
-		clk_put(cpu_clk);
-		return PTR_ERR(emc_clk);
+	struct tegra20_cpufreq *cpufreq;
+	int err;
+
+	cpufreq = devm_kzalloc(&pdev->dev, sizeof(*cpufreq), GFP_KERNEL);
+	if (!cpufreq)
+		return -ENOMEM;
+
+	cpufreq->cpu_clk = clk_get_sys(NULL, "cclk");
+	if (IS_ERR(cpufreq->cpu_clk))
+		return PTR_ERR(cpufreq->cpu_clk);
+
+	cpufreq->pll_x_clk = clk_get_sys(NULL, "pll_x");
+	if (IS_ERR(cpufreq->pll_x_clk)) {
+		err = PTR_ERR(cpufreq->pll_x_clk);
+		goto put_cpu;
+	}
+
+	cpufreq->pll_p_clk = clk_get_sys(NULL, "pll_p");
+	if (IS_ERR(cpufreq->pll_p_clk)) {
+		err = PTR_ERR(cpufreq->pll_p_clk);
+		goto put_pll_x;
 	}
 
-	return cpufreq_register_driver(&tegra_cpufreq_driver);
+	cpufreq->dev = &pdev->dev;
+	cpufreq->driver.get = cpufreq_generic_get;
+	cpufreq->driver.attr = cpufreq_generic_attr;
+	cpufreq->driver.init = tegra_cpu_init;
+	cpufreq->driver.exit = tegra_cpu_exit;
+	cpufreq->driver.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK;
+	cpufreq->driver.verify = cpufreq_generic_frequency_table_verify;
+	cpufreq->driver.suspend = cpufreq_generic_suspend;
+	cpufreq->driver.driver_data = cpufreq;
+	cpufreq->driver.target_index = tegra_target;
+	cpufreq->driver.get_intermediate = tegra_get_intermediate;
+	cpufreq->driver.target_intermediate = tegra_target_intermediate;
+	snprintf(cpufreq->driver.name, CPUFREQ_NAME_LEN, "tegra");
+
+	err = cpufreq_register_driver(&cpufreq->driver);
+	if (err)
+		goto put_pll_p;
+
+	platform_set_drvdata(pdev, cpufreq);
+
+	return 0;
+
+put_pll_p:
+	clk_put(cpufreq->pll_p_clk);
+put_pll_x:
+	clk_put(cpufreq->pll_x_clk);
+put_cpu:
+	clk_put(cpufreq->cpu_clk);
+
+	return err;
 }
 
-static void __exit tegra_cpufreq_exit(void)
+static int tegra20_cpufreq_remove(struct platform_device *pdev)
 {
-        cpufreq_unregister_driver(&tegra_cpufreq_driver);
-	clk_put(emc_clk);
-	clk_put(cpu_clk);
+	struct tegra20_cpufreq *cpufreq = platform_get_drvdata(pdev);
+
+	cpufreq_unregister_driver(&cpufreq->driver);
+
+	clk_put(cpufreq->pll_p_clk);
+	clk_put(cpufreq->pll_x_clk);
+	clk_put(cpufreq->cpu_clk);
+
+	return 0;
 }
 
+static struct platform_driver tegra20_cpufreq_driver = {
+	.probe		= tegra20_cpufreq_probe,
+	.remove		= tegra20_cpufreq_remove,
+	.driver		= {
+		.name	= "tegra20-cpufreq",
+	},
+};
+module_platform_driver(tegra20_cpufreq_driver);
 
+MODULE_ALIAS("platform:tegra20-cpufreq");
 MODULE_AUTHOR("Colin Cross <ccross@android.com>");
-MODULE_DESCRIPTION("cpufreq driver for Nvidia Tegra2");
+MODULE_DESCRIPTION("NVIDIA Tegra20 cpufreq driver");
 MODULE_LICENSE("GPL");
-module_init(tegra_cpufreq_init);
-module_exit(tegra_cpufreq_exit);
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index 5d359aff3cc5..9fed1b829292 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -8,8 +8,10 @@
  * This code is licenced under the GPL.
  */
 
-#include <linux/mutex.h>
+#include <linux/cpu.h>
 #include <linux/cpuidle.h>
+#include <linux/mutex.h>
+#include <linux/pm_qos.h>
 
 #include "cpuidle.h"
 
@@ -93,3 +95,16 @@ int cpuidle_register_governor(struct cpuidle_governor *gov)
 
 	return ret;
 }
+
+/**
+ * cpuidle_governor_latency_req - Compute a latency constraint for CPU
+ * @cpu: Target CPU
+ */
+int cpuidle_governor_latency_req(unsigned int cpu)
+{
+	int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+	struct device *device = get_cpu_device(cpu);
+	int device_req = dev_pm_qos_raw_read_value(device);
+
+	return device_req < global_req ? device_req : global_req;
+}
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index b24883f85c99..704880a6612a 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -14,10 +14,8 @@
 
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
-#include <linux/pm_qos.h>
 #include <linux/jiffies.h>
 #include <linux/tick.h>
-#include <linux/cpu.h>
 
 #include <asm/io.h>
 #include <linux/uaccess.h>
@@ -69,16 +67,10 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 			       struct cpuidle_device *dev, bool *dummy)
 {
 	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
-	struct device *device = get_cpu_device(dev->cpu);
 	struct ladder_device_state *last_state;
 	int last_residency, last_idx = ldev->last_state_idx;
 	int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0;
-	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
-	int resume_latency = dev_pm_qos_raw_read_value(device);
-
-	if (resume_latency < latency_req &&
-	    resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
-		latency_req = resume_latency;
+	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 1bfe03ceb236..1aef60d160eb 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -12,7 +12,6 @@
 
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
-#include <linux/pm_qos.h>
 #include <linux/time.h>
 #include <linux/ktime.h>
 #include <linux/hrtimer.h>
@@ -21,7 +20,6 @@
 #include <linux/sched/loadavg.h>
 #include <linux/sched/stat.h>
 #include <linux/math64.h>
-#include <linux/cpu.h>
 
 /*
  * Please note when changing the tuning values:
@@ -286,15 +284,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		       bool *stop_tick)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
-	struct device *device = get_cpu_device(dev->cpu);
-	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 	int i;
 	int first_idx;
 	int idx;
 	unsigned int interactivity_req;
 	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
-	int resume_latency = dev_pm_qos_raw_read_value(device);
 	ktime_t delta_next;
 
 	if (data->needs_update) {
@@ -302,10 +298,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		data->needs_update = 0;
 	}
 
-	if (resume_latency < latency_req &&
-	    resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
-		latency_req = resume_latency;
-
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
 		*stop_tick = false;
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index d1ea1a07cecb..43cccf6aff61 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -302,6 +302,7 @@ config CRYPTO_DEV_PPC4XX
 	select CRYPTO_AEAD
 	select CRYPTO_AES
 	select CRYPTO_CCM
+	select CRYPTO_CTR
 	select CRYPTO_GCM
 	select CRYPTO_BLKCIPHER
 	help
@@ -419,7 +420,7 @@ config CRYPTO_DEV_EXYNOS_RNG
 config CRYPTO_DEV_S5P
 	tristate "Support for Samsung S5PV210/Exynos crypto accelerator"
 	depends on ARCH_S5PV210 || ARCH_EXYNOS || COMPILE_TEST
-	depends on HAS_IOMEM && HAS_DMA
+	depends on HAS_IOMEM
 	select CRYPTO_AES
 	select CRYPTO_BLKCIPHER
 	help
@@ -466,7 +467,6 @@ endif # if CRYPTO_DEV_UX500
 
 config CRYPTO_DEV_ATMEL_AUTHENC
 	tristate "Support for Atmel IPSEC/SSL hw accelerator"
-	depends on HAS_DMA
 	depends on ARCH_AT91 || COMPILE_TEST
 	select CRYPTO_AUTHENC
 	select CRYPTO_DEV_ATMEL_AES
@@ -479,7 +479,6 @@ config CRYPTO_DEV_ATMEL_AUTHENC
 
 config CRYPTO_DEV_ATMEL_AES
 	tristate "Support for Atmel AES hw accelerator"
-	depends on HAS_DMA
 	depends on ARCH_AT91 || COMPILE_TEST
 	select CRYPTO_AES
 	select CRYPTO_AEAD
@@ -494,7 +493,6 @@ config CRYPTO_DEV_ATMEL_AES
 
 config CRYPTO_DEV_ATMEL_TDES
 	tristate "Support for Atmel DES/TDES hw accelerator"
-	depends on HAS_DMA
 	depends on ARCH_AT91 || COMPILE_TEST
 	select CRYPTO_DES
 	select CRYPTO_BLKCIPHER
@@ -508,7 +506,6 @@ config CRYPTO_DEV_ATMEL_TDES
 
 config CRYPTO_DEV_ATMEL_SHA
 	tristate "Support for Atmel SHA hw accelerator"
-	depends on HAS_DMA
 	depends on ARCH_AT91 || COMPILE_TEST
 	select CRYPTO_HASH
 	help
@@ -574,7 +571,8 @@ config CRYPTO_DEV_CAVIUM_ZIP
 
 config CRYPTO_DEV_QCE
 	tristate "Qualcomm crypto engine accelerator"
-	depends on (ARCH_QCOM || COMPILE_TEST) && HAS_DMA && HAS_IOMEM
+	depends on ARCH_QCOM || COMPILE_TEST
+	depends on HAS_IOMEM
 	select CRYPTO_AES
 	select CRYPTO_DES
 	select CRYPTO_ECB
@@ -598,7 +596,6 @@ source "drivers/crypto/vmx/Kconfig"
 config CRYPTO_DEV_IMGTEC_HASH
 	tristate "Imagination Technologies hardware hash accelerator"
 	depends on MIPS || COMPILE_TEST
-	depends on HAS_DMA
 	select CRYPTO_MD5
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
@@ -650,7 +647,6 @@ config CRYPTO_DEV_ROCKCHIP
 
 config CRYPTO_DEV_MEDIATEK
 	tristate "MediaTek's EIP97 Cryptographic Engine driver"
-	depends on HAS_DMA
 	depends on (ARM && ARCH_MEDIATEK) || COMPILE_TEST
 	select CRYPTO_AES
 	select CRYPTO_AEAD
@@ -688,9 +684,10 @@ source "drivers/crypto/stm32/Kconfig"
 
 config CRYPTO_DEV_SAFEXCEL
 	tristate "Inside Secure's SafeXcel cryptographic engine driver"
-	depends on HAS_DMA && OF
+	depends on OF
 	depends on (ARM64 && ARCH_MVEBU) || (COMPILE_TEST && 64BIT)
 	select CRYPTO_AES
+	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_HASH
 	select CRYPTO_HMAC
@@ -706,7 +703,6 @@ config CRYPTO_DEV_SAFEXCEL
 config CRYPTO_DEV_ARTPEC6
 	tristate "Support for Axis ARTPEC-6/7 hardware crypto acceleration."
 	depends on ARM && (ARCH_ARTPEC || COMPILE_TEST)
-	depends on HAS_DMA
 	depends on OF
 	select CRYPTO_AEAD
 	select CRYPTO_AES
diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c
index ea83d0bff0e9..f5c07498ea4f 100644
--- a/drivers/crypto/amcc/crypto4xx_alg.c
+++ b/drivers/crypto/amcc/crypto4xx_alg.c
@@ -31,6 +31,7 @@
 #include <crypto/gcm.h>
 #include <crypto/sha.h>
 #include <crypto/ctr.h>
+#include <crypto/skcipher.h>
 #include "crypto4xx_reg_def.h"
 #include "crypto4xx_core.h"
 #include "crypto4xx_sa.h"
@@ -74,51 +75,57 @@ static void set_dynamic_sa_command_1(struct dynamic_sa_ctl *sa, u32 cm,
 	sa->sa_command_1.bf.copy_hdr = cp_hdr;
 }
 
-int crypto4xx_encrypt(struct ablkcipher_request *req)
+static inline int crypto4xx_crypt(struct skcipher_request *req,
+				  const unsigned int ivlen, bool decrypt)
 {
-	struct crypto4xx_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	unsigned int ivlen = crypto_ablkcipher_ivsize(
-		crypto_ablkcipher_reqtfm(req));
-	__le32 iv[ivlen];
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
+	struct crypto4xx_ctx *ctx = crypto_skcipher_ctx(cipher);
+	__le32 iv[AES_IV_SIZE];
 
 	if (ivlen)
-		crypto4xx_memcpy_to_le32(iv, req->info, ivlen);
+		crypto4xx_memcpy_to_le32(iv, req->iv, ivlen);
 
 	return crypto4xx_build_pd(&req->base, ctx, req->src, req->dst,
-		req->nbytes, iv, ivlen, ctx->sa_out, ctx->sa_len, 0);
+		req->cryptlen, iv, ivlen, decrypt ? ctx->sa_in : ctx->sa_out,
+		ctx->sa_len, 0, NULL);
 }
 
-int crypto4xx_decrypt(struct ablkcipher_request *req)
+int crypto4xx_encrypt_noiv(struct skcipher_request *req)
 {
-	struct crypto4xx_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	unsigned int ivlen = crypto_ablkcipher_ivsize(
-		crypto_ablkcipher_reqtfm(req));
-	__le32 iv[ivlen];
+	return crypto4xx_crypt(req, 0, false);
+}
 
-	if (ivlen)
-		crypto4xx_memcpy_to_le32(iv, req->info, ivlen);
+int crypto4xx_encrypt_iv(struct skcipher_request *req)
+{
+	return crypto4xx_crypt(req, AES_IV_SIZE, false);
+}
 
-	return crypto4xx_build_pd(&req->base, ctx, req->src, req->dst,
-		req->nbytes, iv, ivlen, ctx->sa_in, ctx->sa_len, 0);
+int crypto4xx_decrypt_noiv(struct skcipher_request *req)
+{
+	return crypto4xx_crypt(req, 0, true);
+}
+
+int crypto4xx_decrypt_iv(struct skcipher_request *req)
+{
+	return crypto4xx_crypt(req, AES_IV_SIZE, true);
 }
 
 /**
  * AES Functions
  */
-static int crypto4xx_setkey_aes(struct crypto_ablkcipher *cipher,
+static int crypto4xx_setkey_aes(struct crypto_skcipher *cipher,
 				const u8 *key,
 				unsigned int keylen,
 				unsigned char cm,
 				u8 fb)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct crypto4xx_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto4xx_ctx *ctx = crypto_skcipher_ctx(cipher);
 	struct dynamic_sa_ctl *sa;
 	int    rc;
 
 	if (keylen != AES_KEYSIZE_256 &&
 		keylen != AES_KEYSIZE_192 && keylen != AES_KEYSIZE_128) {
-		crypto_ablkcipher_set_flags(cipher,
+		crypto_skcipher_set_flags(cipher,
 				CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
@@ -134,7 +141,8 @@ static int crypto4xx_setkey_aes(struct crypto_ablkcipher *cipher,
 	/* Setup SA */
 	sa = ctx->sa_in;
 
-	set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, SA_NOT_SAVE_IV,
+	set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, (cm == CRYPTO_MODE_CBC ?
+				 SA_SAVE_IV : SA_NOT_SAVE_IV),
 				 SA_LOAD_HASH_FROM_SA, SA_LOAD_IV_FROM_STATE,
 				 SA_NO_HEADER_PROC, SA_HASH_ALG_NULL,
 				 SA_CIPHER_ALG_AES, SA_PAD_TYPE_ZERO,
@@ -158,39 +166,38 @@ static int crypto4xx_setkey_aes(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-int crypto4xx_setkey_aes_cbc(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_aes_cbc(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen)
 {
 	return crypto4xx_setkey_aes(cipher, key, keylen, CRYPTO_MODE_CBC,
 				    CRYPTO_FEEDBACK_MODE_NO_FB);
 }
 
-int crypto4xx_setkey_aes_cfb(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_aes_cfb(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen)
 {
 	return crypto4xx_setkey_aes(cipher, key, keylen, CRYPTO_MODE_CFB,
 				    CRYPTO_FEEDBACK_MODE_128BIT_CFB);
 }
 
-int crypto4xx_setkey_aes_ecb(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_aes_ecb(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen)
 {
 	return crypto4xx_setkey_aes(cipher, key, keylen, CRYPTO_MODE_ECB,
 				    CRYPTO_FEEDBACK_MODE_NO_FB);
 }
 
-int crypto4xx_setkey_aes_ofb(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_aes_ofb(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen)
 {
 	return crypto4xx_setkey_aes(cipher, key, keylen, CRYPTO_MODE_OFB,
 				    CRYPTO_FEEDBACK_MODE_64BIT_OFB);
 }
 
-int crypto4xx_setkey_rfc3686(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_rfc3686(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
-	struct crypto4xx_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto4xx_ctx *ctx = crypto_skcipher_ctx(cipher);
 	int rc;
 
 	rc = crypto4xx_setkey_aes(cipher, key, keylen - CTR_RFC3686_NONCE_SIZE,
@@ -204,35 +211,117 @@ int crypto4xx_setkey_rfc3686(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-int crypto4xx_rfc3686_encrypt(struct ablkcipher_request *req)
+int crypto4xx_rfc3686_encrypt(struct skcipher_request *req)
 {
-	struct crypto4xx_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
+	struct crypto4xx_ctx *ctx = crypto_skcipher_ctx(cipher);
 	__le32 iv[AES_IV_SIZE / 4] = {
 		ctx->iv_nonce,
-		cpu_to_le32p((u32 *) req->info),
-		cpu_to_le32p((u32 *) (req->info + 4)),
+		cpu_to_le32p((u32 *) req->iv),
+		cpu_to_le32p((u32 *) (req->iv + 4)),
 		cpu_to_le32(1) };
 
 	return crypto4xx_build_pd(&req->base, ctx, req->src, req->dst,
-				  req->nbytes, iv, AES_IV_SIZE,
-				  ctx->sa_out, ctx->sa_len, 0);
+				  req->cryptlen, iv, AES_IV_SIZE,
+				  ctx->sa_out, ctx->sa_len, 0, NULL);
 }
 
-int crypto4xx_rfc3686_decrypt(struct ablkcipher_request *req)
+int crypto4xx_rfc3686_decrypt(struct skcipher_request *req)
 {
-	struct crypto4xx_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
+	struct crypto4xx_ctx *ctx = crypto_skcipher_ctx(cipher);
 	__le32 iv[AES_IV_SIZE / 4] = {
 		ctx->iv_nonce,
-		cpu_to_le32p((u32 *) req->info),
-		cpu_to_le32p((u32 *) (req->info + 4)),
+		cpu_to_le32p((u32 *) req->iv),
+		cpu_to_le32p((u32 *) (req->iv + 4)),
 		cpu_to_le32(1) };
 
 	return crypto4xx_build_pd(&req->base, ctx, req->src, req->dst,
-				  req->nbytes, iv, AES_IV_SIZE,
-				  ctx->sa_out, ctx->sa_len, 0);
+				  req->cryptlen, iv, AES_IV_SIZE,
+				  ctx->sa_out, ctx->sa_len, 0, NULL);
+}
+
+static int
+crypto4xx_ctr_crypt(struct skcipher_request *req, bool encrypt)
+{
+	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
+	struct crypto4xx_ctx *ctx = crypto_skcipher_ctx(cipher);
+	size_t iv_len = crypto_skcipher_ivsize(cipher);
+	unsigned int counter = be32_to_cpup((__be32 *)(req->iv + iv_len - 4));
+	unsigned int nblks = ALIGN(req->cryptlen, AES_BLOCK_SIZE) /
+			AES_BLOCK_SIZE;
+
+	/*
+	 * The hardware uses only the last 32-bits as the counter while the
+	 * kernel tests (aes_ctr_enc_tv_template[4] for example) expect that
+	 * the whole IV is a counter.  So fallback if the counter is going to
+	 * overlow.
+	 */
+	if (counter + nblks < counter) {
+		struct skcipher_request *subreq = skcipher_request_ctx(req);
+		int ret;
+
+		skcipher_request_set_tfm(subreq, ctx->sw_cipher.cipher);
+		skcipher_request_set_callback(subreq, req->base.flags,
+			NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+			req->cryptlen, req->iv);
+		ret = encrypt ? crypto_skcipher_encrypt(subreq)
+			: crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
+		return ret;
+	}
+
+	return encrypt ? crypto4xx_encrypt_iv(req)
+		       : crypto4xx_decrypt_iv(req);
+}
+
+static int crypto4xx_sk_setup_fallback(struct crypto4xx_ctx *ctx,
+				       struct crypto_skcipher *cipher,
+				       const u8 *key,
+				       unsigned int keylen)
+{
+	int rc;
+
+	crypto_skcipher_clear_flags(ctx->sw_cipher.cipher,
+				    CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctx->sw_cipher.cipher,
+		crypto_skcipher_get_flags(cipher) & CRYPTO_TFM_REQ_MASK);
+	rc = crypto_skcipher_setkey(ctx->sw_cipher.cipher, key, keylen);
+	crypto_skcipher_clear_flags(cipher, CRYPTO_TFM_RES_MASK);
+	crypto_skcipher_set_flags(cipher,
+		crypto_skcipher_get_flags(ctx->sw_cipher.cipher) &
+			CRYPTO_TFM_RES_MASK);
+
+	return rc;
+}
+
+int crypto4xx_setkey_aes_ctr(struct crypto_skcipher *cipher,
+			     const u8 *key, unsigned int keylen)
+{
+	struct crypto4xx_ctx *ctx = crypto_skcipher_ctx(cipher);
+	int rc;
+
+	rc = crypto4xx_sk_setup_fallback(ctx, cipher, key, keylen);
+	if (rc)
+		return rc;
+
+	return crypto4xx_setkey_aes(cipher, key, keylen,
+		CRYPTO_MODE_CTR, CRYPTO_FEEDBACK_MODE_NO_FB);
+}
+
+int crypto4xx_encrypt_ctr(struct skcipher_request *req)
+{
+	return crypto4xx_ctr_crypt(req, true);
+}
+
+int crypto4xx_decrypt_ctr(struct skcipher_request *req)
+{
+	return crypto4xx_ctr_crypt(req, false);
 }
 
 static inline bool crypto4xx_aead_need_fallback(struct aead_request *req,
+						unsigned int len,
 						bool is_ccm, bool decrypt)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -242,14 +331,14 @@ static inline bool crypto4xx_aead_need_fallback(struct aead_request *req,
 		return true;
 
 	/*
-	 * hardware does not handle cases where cryptlen
-	 * is less than a block
+	 * hardware does not handle cases where plaintext
+	 * is less than a block.
 	 */
-	if (req->cryptlen < AES_BLOCK_SIZE)
+	if (len < AES_BLOCK_SIZE)
 		return true;
 
-	/* assoc len needs to be a multiple of 4 */
-	if (req->assoclen & 0x3)
+	/* assoc len needs to be a multiple of 4 and <= 1020 */
+	if (req->assoclen & 0x3 || req->assoclen > 1020)
 		return true;
 
 	/* CCM supports only counter field length of 2 and 4 bytes */
@@ -262,13 +351,7 @@ static inline bool crypto4xx_aead_need_fallback(struct aead_request *req,
 static int crypto4xx_aead_fallback(struct aead_request *req,
 	struct crypto4xx_ctx *ctx, bool do_decrypt)
 {
-	char aead_req_data[sizeof(struct aead_request) +
-			   crypto_aead_reqsize(ctx->sw_cipher.aead)]
-		__aligned(__alignof__(struct aead_request));
-
-	struct aead_request *subreq = (void *) aead_req_data;
-
-	memset(subreq, 0, sizeof(aead_req_data));
+	struct aead_request *subreq = aead_request_ctx(req);
 
 	aead_request_set_tfm(subreq, ctx->sw_cipher.aead);
 	aead_request_set_callback(subreq, req->base.flags,
@@ -280,10 +363,10 @@ static int crypto4xx_aead_fallback(struct aead_request *req,
 			    crypto_aead_encrypt(subreq);
 }
 
-static int crypto4xx_setup_fallback(struct crypto4xx_ctx *ctx,
-				    struct crypto_aead *cipher,
-				    const u8 *key,
-				    unsigned int keylen)
+static int crypto4xx_aead_setup_fallback(struct crypto4xx_ctx *ctx,
+					 struct crypto_aead *cipher,
+					 const u8 *key,
+					 unsigned int keylen)
 {
 	int rc;
 
@@ -311,7 +394,7 @@ int crypto4xx_setkey_aes_ccm(struct crypto_aead *cipher, const u8 *key,
 	struct dynamic_sa_ctl *sa;
 	int rc = 0;
 
-	rc = crypto4xx_setup_fallback(ctx, cipher, key, keylen);
+	rc = crypto4xx_aead_setup_fallback(ctx, cipher, key, keylen);
 	if (rc)
 		return rc;
 
@@ -366,19 +449,20 @@ int crypto4xx_setkey_aes_ccm(struct crypto_aead *cipher, const u8 *key,
 static int crypto4xx_crypt_aes_ccm(struct aead_request *req, bool decrypt)
 {
 	struct crypto4xx_ctx *ctx  = crypto_tfm_ctx(req->base.tfm);
+	struct crypto4xx_aead_reqctx *rctx = aead_request_ctx(req);
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	unsigned int len = req->cryptlen;
 	__le32 iv[16];
-	u32 tmp_sa[ctx->sa_len * 4];
+	u32 tmp_sa[SA_AES128_CCM_LEN + 4];
 	struct dynamic_sa_ctl *sa = (struct dynamic_sa_ctl *)tmp_sa;
-
-	if (crypto4xx_aead_need_fallback(req, true, decrypt))
-		return crypto4xx_aead_fallback(req, ctx, decrypt);
+	unsigned int len = req->cryptlen;
 
 	if (decrypt)
 		len -= crypto_aead_authsize(aead);
 
-	memcpy(tmp_sa, decrypt ? ctx->sa_in : ctx->sa_out, sizeof(tmp_sa));
+	if (crypto4xx_aead_need_fallback(req, len, true, decrypt))
+		return crypto4xx_aead_fallback(req, ctx, decrypt);
+
+	memcpy(tmp_sa, decrypt ? ctx->sa_in : ctx->sa_out, ctx->sa_len * 4);
 	sa->sa_command_0.bf.digest_len = crypto_aead_authsize(aead) >> 2;
 
 	if (req->iv[0] == 1) {
@@ -391,7 +475,7 @@ static int crypto4xx_crypt_aes_ccm(struct aead_request *req, bool decrypt)
 
 	return crypto4xx_build_pd(&req->base, ctx, req->src, req->dst,
 				  len, iv, sizeof(iv),
-				  sa, ctx->sa_len, req->assoclen);
+				  sa, ctx->sa_len, req->assoclen, rctx->dst);
 }
 
 int crypto4xx_encrypt_aes_ccm(struct aead_request *req)
@@ -470,7 +554,7 @@ int crypto4xx_setkey_aes_gcm(struct crypto_aead *cipher,
 		return -EINVAL;
 	}
 
-	rc = crypto4xx_setup_fallback(ctx, cipher, key, keylen);
+	rc = crypto4xx_aead_setup_fallback(ctx, cipher, key, keylen);
 	if (rc)
 		return rc;
 
@@ -523,22 +607,23 @@ static inline int crypto4xx_crypt_aes_gcm(struct aead_request *req,
 					  bool decrypt)
 {
 	struct crypto4xx_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	unsigned int len = req->cryptlen;
+	struct crypto4xx_aead_reqctx *rctx = aead_request_ctx(req);
 	__le32 iv[4];
+	unsigned int len = req->cryptlen;
+
+	if (decrypt)
+		len -= crypto_aead_authsize(crypto_aead_reqtfm(req));
 
-	if (crypto4xx_aead_need_fallback(req, false, decrypt))
+	if (crypto4xx_aead_need_fallback(req, len, false, decrypt))
 		return crypto4xx_aead_fallback(req, ctx, decrypt);
 
 	crypto4xx_memcpy_to_le32(iv, req->iv, GCM_AES_IV_SIZE);
 	iv[3] = cpu_to_le32(1);
 
-	if (decrypt)
-		len -= crypto_aead_authsize(crypto_aead_reqtfm(req));
-
 	return crypto4xx_build_pd(&req->base, ctx, req->src, req->dst,
 				  len, iv, sizeof(iv),
 				  decrypt ? ctx->sa_in : ctx->sa_out,
-				  ctx->sa_len, req->assoclen);
+				  ctx->sa_len, req->assoclen, rctx->dst);
 }
 
 int crypto4xx_encrypt_aes_gcm(struct aead_request *req)
@@ -623,7 +708,7 @@ int crypto4xx_hash_update(struct ahash_request *req)
 
 	return crypto4xx_build_pd(&req->base, ctx, req->src, &dst,
 				  req->nbytes, NULL, 0, ctx->sa_in,
-				  ctx->sa_len, 0);
+				  ctx->sa_len, 0, NULL);
 }
 
 int crypto4xx_hash_final(struct ahash_request *req)
@@ -642,7 +727,7 @@ int crypto4xx_hash_digest(struct ahash_request *req)
 
 	return crypto4xx_build_pd(&req->base, ctx, req->src, &dst,
 				  req->nbytes, NULL, 0, ctx->sa_in,
-				  ctx->sa_len, 0);
+				  ctx->sa_len, 0, NULL);
 }
 
 /**
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 76f459ad2821..9cb234c72549 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -41,6 +41,7 @@
 #include <crypto/gcm.h>
 #include <crypto/sha.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/skcipher.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include "crypto4xx_reg_def.h"
@@ -526,31 +527,38 @@ static void crypto4xx_ret_sg_desc(struct crypto4xx_device *dev,
 	}
 }
 
-static void crypto4xx_ablkcipher_done(struct crypto4xx_device *dev,
+static void crypto4xx_cipher_done(struct crypto4xx_device *dev,
 				     struct pd_uinfo *pd_uinfo,
 				     struct ce_pd *pd)
 {
-	struct crypto4xx_ctx *ctx;
-	struct ablkcipher_request *ablk_req;
+	struct skcipher_request *req;
 	struct scatterlist *dst;
 	dma_addr_t addr;
 
-	ablk_req = ablkcipher_request_cast(pd_uinfo->async_req);
-	ctx  = crypto_tfm_ctx(ablk_req->base.tfm);
+	req = skcipher_request_cast(pd_uinfo->async_req);
 
 	if (pd_uinfo->using_sd) {
-		crypto4xx_copy_pkt_to_dst(dev, pd, pd_uinfo, ablk_req->nbytes,
-					  ablk_req->dst);
+		crypto4xx_copy_pkt_to_dst(dev, pd, pd_uinfo,
+					  req->cryptlen, req->dst);
 	} else {
 		dst = pd_uinfo->dest_va;
 		addr = dma_map_page(dev->core_dev->device, sg_page(dst),
 				    dst->offset, dst->length, DMA_FROM_DEVICE);
 	}
+
+	if (pd_uinfo->sa_va->sa_command_0.bf.save_iv == SA_SAVE_IV) {
+		struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+
+		crypto4xx_memcpy_from_le32((u32 *)req->iv,
+			pd_uinfo->sr_va->save_iv,
+			crypto_skcipher_ivsize(skcipher));
+	}
+
 	crypto4xx_ret_sg_desc(dev, pd_uinfo);
 
 	if (pd_uinfo->state & PD_ENTRY_BUSY)
-		ablkcipher_request_complete(ablk_req, -EINPROGRESS);
-	ablkcipher_request_complete(ablk_req, 0);
+		skcipher_request_complete(req, -EINPROGRESS);
+	skcipher_request_complete(req, 0);
 }
 
 static void crypto4xx_ahash_done(struct crypto4xx_device *dev,
@@ -580,7 +588,7 @@ static void crypto4xx_aead_done(struct crypto4xx_device *dev,
 	struct scatterlist *dst = pd_uinfo->dest_va;
 	size_t cp_len = crypto_aead_authsize(
 		crypto_aead_reqtfm(aead_req));
-	u32 icv[cp_len];
+	u32 icv[AES_BLOCK_SIZE];
 	int err = 0;
 
 	if (pd_uinfo->using_sd) {
@@ -595,7 +603,7 @@ static void crypto4xx_aead_done(struct crypto4xx_device *dev,
 	if (pd_uinfo->sa_va->sa_command_0.bf.dir == DIR_OUTBOUND) {
 		/* append icv at the end */
 		crypto4xx_memcpy_from_le32(icv, pd_uinfo->sr_va->save_digest,
-					   cp_len);
+					   sizeof(icv));
 
 		scatterwalk_map_and_copy(icv, dst, aead_req->cryptlen,
 					 cp_len, 1);
@@ -605,7 +613,7 @@ static void crypto4xx_aead_done(struct crypto4xx_device *dev,
 			aead_req->assoclen + aead_req->cryptlen -
 			cp_len, cp_len, 0);
 
-		crypto4xx_memcpy_from_le32(icv, icv, cp_len);
+		crypto4xx_memcpy_from_le32(icv, icv, sizeof(icv));
 
 		if (crypto_memneq(icv, pd_uinfo->sr_va->save_digest, cp_len))
 			err = -EBADMSG;
@@ -641,8 +649,8 @@ static void crypto4xx_pd_done(struct crypto4xx_device *dev, u32 idx)
 	struct pd_uinfo *pd_uinfo = &dev->pdr_uinfo[idx];
 
 	switch (crypto_tfm_alg_type(pd_uinfo->async_req->tfm)) {
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		crypto4xx_ablkcipher_done(dev, pd_uinfo, pd);
+	case CRYPTO_ALG_TYPE_SKCIPHER:
+		crypto4xx_cipher_done(dev, pd_uinfo, pd);
 		break;
 	case CRYPTO_ALG_TYPE_AEAD:
 		crypto4xx_aead_done(dev, pd_uinfo, pd);
@@ -687,9 +695,9 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		       const __le32 *iv, const u32 iv_len,
 		       const struct dynamic_sa_ctl *req_sa,
 		       const unsigned int sa_len,
-		       const unsigned int assoclen)
+		       const unsigned int assoclen,
+		       struct scatterlist *_dst)
 {
-	struct scatterlist _dst[2];
 	struct crypto4xx_device *dev = ctx->dev;
 	struct dynamic_sa_ctl *sa;
 	struct ce_gd *gd;
@@ -936,15 +944,27 @@ static void crypto4xx_ctx_init(struct crypto4xx_alg *amcc_alg,
 	ctx->sa_len = 0;
 }
 
-static int crypto4xx_ablk_init(struct crypto_tfm *tfm)
+static int crypto4xx_sk_init(struct crypto_skcipher *sk)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
+	struct skcipher_alg *alg = crypto_skcipher_alg(sk);
 	struct crypto4xx_alg *amcc_alg;
-	struct crypto4xx_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto4xx_ctx *ctx =  crypto_skcipher_ctx(sk);
+
+	if (alg->base.cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
+		ctx->sw_cipher.cipher =
+			crypto_alloc_skcipher(alg->base.cra_name, 0,
+					      CRYPTO_ALG_NEED_FALLBACK |
+					      CRYPTO_ALG_ASYNC);
+		if (IS_ERR(ctx->sw_cipher.cipher))
+			return PTR_ERR(ctx->sw_cipher.cipher);
+
+		crypto_skcipher_set_reqsize(sk,
+			sizeof(struct skcipher_request) + 32 +
+			crypto_skcipher_reqsize(ctx->sw_cipher.cipher));
+	}
 
 	amcc_alg = container_of(alg, struct crypto4xx_alg, alg.u.cipher);
 	crypto4xx_ctx_init(amcc_alg, ctx);
-	tfm->crt_ablkcipher.reqsize = sizeof(struct crypto4xx_ctx);
 	return 0;
 }
 
@@ -953,9 +973,13 @@ static void crypto4xx_common_exit(struct crypto4xx_ctx *ctx)
 	crypto4xx_free_sa(ctx);
 }
 
-static void crypto4xx_ablk_exit(struct crypto_tfm *tfm)
+static void crypto4xx_sk_exit(struct crypto_skcipher *sk)
 {
-	crypto4xx_common_exit(crypto_tfm_ctx(tfm));
+	struct crypto4xx_ctx *ctx =  crypto_skcipher_ctx(sk);
+
+	crypto4xx_common_exit(ctx);
+	if (ctx->sw_cipher.cipher)
+		crypto_free_skcipher(ctx->sw_cipher.cipher);
 }
 
 static int crypto4xx_aead_init(struct crypto_aead *tfm)
@@ -972,9 +996,9 @@ static int crypto4xx_aead_init(struct crypto_aead *tfm)
 
 	amcc_alg = container_of(alg, struct crypto4xx_alg, alg.u.aead);
 	crypto4xx_ctx_init(amcc_alg, ctx);
-	crypto_aead_set_reqsize(tfm, sizeof(struct aead_request) +
-				max(sizeof(struct crypto4xx_ctx), 32 +
-				crypto_aead_reqsize(ctx->sw_cipher.aead)));
+	crypto_aead_set_reqsize(tfm, max(sizeof(struct aead_request) + 32 +
+				crypto_aead_reqsize(ctx->sw_cipher.aead),
+				sizeof(struct crypto4xx_aead_reqctx)));
 	return 0;
 }
 
@@ -1012,7 +1036,7 @@ static int crypto4xx_register_alg(struct crypto4xx_device *sec_dev,
 			break;
 
 		default:
-			rc = crypto_register_alg(&alg->alg.u.cipher);
+			rc = crypto_register_skcipher(&alg->alg.u.cipher);
 			break;
 		}
 
@@ -1041,7 +1065,7 @@ static void crypto4xx_unregister_alg(struct crypto4xx_device *sec_dev)
 			break;
 
 		default:
-			crypto_unregister_alg(&alg->alg.u.cipher);
+			crypto_unregister_skcipher(&alg->alg.u.cipher);
 		}
 		kfree(alg);
 	}
@@ -1103,126 +1127,131 @@ static irqreturn_t crypto4xx_ce_interrupt_handler_revb(int irq, void *data)
  */
 static struct crypto4xx_alg_common crypto4xx_alg[] = {
 	/* Crypto AES modes */
-	{ .type = CRYPTO_ALG_TYPE_ABLKCIPHER, .u.cipher = {
-		.cra_name 	= "cbc(aes)",
-		.cra_driver_name = "cbc-aes-ppc4xx",
-		.cra_priority 	= CRYPTO4XX_CRYPTO_PRIORITY,
-		.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY,
-		.cra_blocksize 	= AES_BLOCK_SIZE,
-		.cra_ctxsize 	= sizeof(struct crypto4xx_ctx),
-		.cra_type 	= &crypto_ablkcipher_type,
-		.cra_init	= crypto4xx_ablk_init,
-		.cra_exit	= crypto4xx_ablk_exit,
-		.cra_module 	= THIS_MODULE,
-		.cra_u 		= {
-			.ablkcipher = {
-				.min_keysize 	= AES_MIN_KEY_SIZE,
-				.max_keysize 	= AES_MAX_KEY_SIZE,
-				.ivsize		= AES_IV_SIZE,
-				.setkey 	= crypto4xx_setkey_aes_cbc,
-				.encrypt 	= crypto4xx_encrypt,
-				.decrypt 	= crypto4xx_decrypt,
-			}
-		}
-	}},
-	{ .type = CRYPTO_ALG_TYPE_ABLKCIPHER, .u.cipher = {
-		.cra_name	= "cfb(aes)",
-		.cra_driver_name = "cfb-aes-ppc4xx",
-		.cra_priority	= CRYPTO4XX_CRYPTO_PRIORITY,
-		.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY,
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_ctxsize	= sizeof(struct crypto4xx_ctx),
-		.cra_type	= &crypto_ablkcipher_type,
-		.cra_init	= crypto4xx_ablk_init,
-		.cra_exit	= crypto4xx_ablk_exit,
-		.cra_module	= THIS_MODULE,
-		.cra_u		= {
-			.ablkcipher = {
-				.min_keysize	= AES_MIN_KEY_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE,
-				.ivsize		= AES_IV_SIZE,
-				.setkey		= crypto4xx_setkey_aes_cfb,
-				.encrypt	= crypto4xx_encrypt,
-				.decrypt	= crypto4xx_decrypt,
-			}
-		}
+	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
+		.base = {
+			.cra_name = "cbc(aes)",
+			.cra_driver_name = "cbc-aes-ppc4xx",
+			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC |
+				CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
+			.cra_module = THIS_MODULE,
+		},
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize	= AES_IV_SIZE,
+		.setkey = crypto4xx_setkey_aes_cbc,
+		.encrypt = crypto4xx_encrypt_iv,
+		.decrypt = crypto4xx_decrypt_iv,
+		.init = crypto4xx_sk_init,
+		.exit = crypto4xx_sk_exit,
 	} },
-	{ .type = CRYPTO_ALG_TYPE_ABLKCIPHER, .u.cipher = {
-		.cra_name	= "rfc3686(ctr(aes))",
-		.cra_driver_name = "rfc3686-ctr-aes-ppc4xx",
-		.cra_priority	= CRYPTO4XX_CRYPTO_PRIORITY,
-		.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY,
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_ctxsize	= sizeof(struct crypto4xx_ctx),
-		.cra_type	= &crypto_ablkcipher_type,
-		.cra_init	= crypto4xx_ablk_init,
-		.cra_exit	= crypto4xx_ablk_exit,
-		.cra_module	= THIS_MODULE,
-		.cra_u		= {
-			.ablkcipher = {
-				.min_keysize	= AES_MIN_KEY_SIZE +
-						  CTR_RFC3686_NONCE_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE +
-						  CTR_RFC3686_NONCE_SIZE,
-				.ivsize		= CTR_RFC3686_IV_SIZE,
-				.setkey		= crypto4xx_setkey_rfc3686,
-				.encrypt	= crypto4xx_rfc3686_encrypt,
-				.decrypt	= crypto4xx_rfc3686_decrypt,
-			}
-		}
+	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
+		.base = {
+			.cra_name = "cfb(aes)",
+			.cra_driver_name = "cfb-aes-ppc4xx",
+			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC |
+				CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
+			.cra_module = THIS_MODULE,
+		},
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize	= AES_IV_SIZE,
+		.setkey	= crypto4xx_setkey_aes_cfb,
+		.encrypt = crypto4xx_encrypt_iv,
+		.decrypt = crypto4xx_decrypt_iv,
+		.init = crypto4xx_sk_init,
+		.exit = crypto4xx_sk_exit,
 	} },
-	{ .type = CRYPTO_ALG_TYPE_ABLKCIPHER, .u.cipher = {
-		.cra_name	= "ecb(aes)",
-		.cra_driver_name = "ecb-aes-ppc4xx",
-		.cra_priority	= CRYPTO4XX_CRYPTO_PRIORITY,
-		.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY,
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_ctxsize	= sizeof(struct crypto4xx_ctx),
-		.cra_type	= &crypto_ablkcipher_type,
-		.cra_init	= crypto4xx_ablk_init,
-		.cra_exit	= crypto4xx_ablk_exit,
-		.cra_module	= THIS_MODULE,
-		.cra_u		= {
-			.ablkcipher = {
-				.min_keysize	= AES_MIN_KEY_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE,
-				.setkey		= crypto4xx_setkey_aes_ecb,
-				.encrypt	= crypto4xx_encrypt,
-				.decrypt	= crypto4xx_decrypt,
-			}
-		}
+	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
+		.base = {
+			.cra_name = "ctr(aes)",
+			.cra_driver_name = "ctr-aes-ppc4xx",
+			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_NEED_FALLBACK |
+				CRYPTO_ALG_ASYNC |
+				CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
+			.cra_module = THIS_MODULE,
+		},
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize	= AES_IV_SIZE,
+		.setkey	= crypto4xx_setkey_aes_ctr,
+		.encrypt = crypto4xx_encrypt_ctr,
+		.decrypt = crypto4xx_decrypt_ctr,
+		.init = crypto4xx_sk_init,
+		.exit = crypto4xx_sk_exit,
 	} },
-	{ .type = CRYPTO_ALG_TYPE_ABLKCIPHER, .u.cipher = {
-		.cra_name	= "ofb(aes)",
-		.cra_driver_name = "ofb-aes-ppc4xx",
-		.cra_priority	= CRYPTO4XX_CRYPTO_PRIORITY,
-		.cra_flags	= CRYPTO_ALG_TYPE_ABLKCIPHER |
-				  CRYPTO_ALG_ASYNC |
-				  CRYPTO_ALG_KERN_DRIVER_ONLY,
-		.cra_blocksize	= AES_BLOCK_SIZE,
-		.cra_ctxsize	= sizeof(struct crypto4xx_ctx),
-		.cra_type	= &crypto_ablkcipher_type,
-		.cra_init	= crypto4xx_ablk_init,
-		.cra_exit	= crypto4xx_ablk_exit,
-		.cra_module	= THIS_MODULE,
-		.cra_u		= {
-			.ablkcipher = {
-				.min_keysize	= AES_MIN_KEY_SIZE,
-				.max_keysize	= AES_MAX_KEY_SIZE,
-				.ivsize		= AES_IV_SIZE,
-				.setkey		= crypto4xx_setkey_aes_ofb,
-				.encrypt	= crypto4xx_encrypt,
-				.decrypt	= crypto4xx_decrypt,
-			}
-		}
+	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
+		.base = {
+			.cra_name = "rfc3686(ctr(aes))",
+			.cra_driver_name = "rfc3686-ctr-aes-ppc4xx",
+			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC |
+				CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
+			.cra_module = THIS_MODULE,
+		},
+		.min_keysize = AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE + CTR_RFC3686_NONCE_SIZE,
+		.ivsize	= CTR_RFC3686_IV_SIZE,
+		.setkey = crypto4xx_setkey_rfc3686,
+		.encrypt = crypto4xx_rfc3686_encrypt,
+		.decrypt = crypto4xx_rfc3686_decrypt,
+		.init = crypto4xx_sk_init,
+		.exit = crypto4xx_sk_exit,
+	} },
+	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
+		.base = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "ecb-aes-ppc4xx",
+			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC |
+				CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
+			.cra_module = THIS_MODULE,
+		},
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.setkey	= crypto4xx_setkey_aes_ecb,
+		.encrypt = crypto4xx_encrypt_noiv,
+		.decrypt = crypto4xx_decrypt_noiv,
+		.init = crypto4xx_sk_init,
+		.exit = crypto4xx_sk_exit,
+	} },
+	{ .type = CRYPTO_ALG_TYPE_SKCIPHER, .u.cipher = {
+		.base = {
+			.cra_name = "ofb(aes)",
+			.cra_driver_name = "ofb-aes-ppc4xx",
+			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
+				CRYPTO_ALG_ASYNC |
+				CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
+			.cra_module = THIS_MODULE,
+		},
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize	= AES_IV_SIZE,
+		.setkey	= crypto4xx_setkey_aes_ofb,
+		.encrypt = crypto4xx_encrypt_iv,
+		.decrypt = crypto4xx_decrypt_iv,
+		.init = crypto4xx_sk_init,
+		.exit = crypto4xx_sk_exit,
 	} },
 
 	/* AEAD */
diff --git a/drivers/crypto/amcc/crypto4xx_core.h b/drivers/crypto/amcc/crypto4xx_core.h
index 23b726da6534..e2ca56722f07 100644
--- a/drivers/crypto/amcc/crypto4xx_core.h
+++ b/drivers/crypto/amcc/crypto4xx_core.h
@@ -25,6 +25,7 @@
 #include <linux/ratelimit.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/skcipher.h>
 #include "crypto4xx_reg_def.h"
 #include "crypto4xx_sa.h"
 
@@ -127,14 +128,19 @@ struct crypto4xx_ctx {
 	__le32 iv_nonce;
 	u32 sa_len;
 	union {
+		struct crypto_skcipher *cipher;
 		struct crypto_aead *aead;
 	} sw_cipher;
 };
 
+struct crypto4xx_aead_reqctx {
+	struct scatterlist dst[2];
+};
+
 struct crypto4xx_alg_common {
 	u32 type;
 	union {
-		struct crypto_alg cipher;
+		struct skcipher_alg cipher;
 		struct ahash_alg hash;
 		struct aead_alg aead;
 	} u;
@@ -157,21 +163,28 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		       const __le32 *iv, const u32 iv_len,
 		       const struct dynamic_sa_ctl *sa,
 		       const unsigned int sa_len,
-		       const unsigned int assoclen);
-int crypto4xx_setkey_aes_cbc(struct crypto_ablkcipher *cipher,
+		       const unsigned int assoclen,
+		       struct scatterlist *dst_tmp);
+int crypto4xx_setkey_aes_cbc(struct crypto_skcipher *cipher,
+			     const u8 *key, unsigned int keylen);
+int crypto4xx_setkey_aes_cfb(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
-int crypto4xx_setkey_aes_cfb(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_aes_ctr(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
-int crypto4xx_setkey_aes_ecb(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_aes_ecb(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
-int crypto4xx_setkey_aes_ofb(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_aes_ofb(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
-int crypto4xx_setkey_rfc3686(struct crypto_ablkcipher *cipher,
+int crypto4xx_setkey_rfc3686(struct crypto_skcipher *cipher,
 			     const u8 *key, unsigned int keylen);
-int crypto4xx_encrypt(struct ablkcipher_request *req);
-int crypto4xx_decrypt(struct ablkcipher_request *req);
-int crypto4xx_rfc3686_encrypt(struct ablkcipher_request *req);
-int crypto4xx_rfc3686_decrypt(struct ablkcipher_request *req);
+int crypto4xx_encrypt_ctr(struct skcipher_request *req);
+int crypto4xx_decrypt_ctr(struct skcipher_request *req);
+int crypto4xx_encrypt_iv(struct skcipher_request *req);
+int crypto4xx_decrypt_iv(struct skcipher_request *req);
+int crypto4xx_encrypt_noiv(struct skcipher_request *req);
+int crypto4xx_decrypt_noiv(struct skcipher_request *req);
+int crypto4xx_rfc3686_encrypt(struct skcipher_request *req);
+int crypto4xx_rfc3686_decrypt(struct skcipher_request *req);
 int crypto4xx_sha1_alg_init(struct crypto_tfm *tfm);
 int crypto4xx_hash_digest(struct ahash_request *req);
 int crypto4xx_hash_final(struct ahash_request *req);
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 7207a535942d..d67667970f7e 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -769,15 +769,18 @@ struct aead_edesc {
  * @src_nents: number of segments in input s/w scatterlist
  * @dst_nents: number of segments in output s/w scatterlist
  * @iv_dma: dma address of iv for checking continuity and link table
+ * @iv_dir: DMA mapping direction for IV
  * @sec4_sg_bytes: length of dma mapped sec4_sg space
  * @sec4_sg_dma: bus physical mapped address of h/w link table
  * @sec4_sg: pointer to h/w link table
  * @hw_desc: the h/w job descriptor followed by any referenced link tables
+ *	     and IV
  */
 struct ablkcipher_edesc {
 	int src_nents;
 	int dst_nents;
 	dma_addr_t iv_dma;
+	enum dma_data_direction iv_dir;
 	int sec4_sg_bytes;
 	dma_addr_t sec4_sg_dma;
 	struct sec4_sg_entry *sec4_sg;
@@ -787,7 +790,8 @@ struct ablkcipher_edesc {
 static void caam_unmap(struct device *dev, struct scatterlist *src,
 		       struct scatterlist *dst, int src_nents,
 		       int dst_nents,
-		       dma_addr_t iv_dma, int ivsize, dma_addr_t sec4_sg_dma,
+		       dma_addr_t iv_dma, int ivsize,
+		       enum dma_data_direction iv_dir, dma_addr_t sec4_sg_dma,
 		       int sec4_sg_bytes)
 {
 	if (dst != src) {
@@ -799,7 +803,7 @@ static void caam_unmap(struct device *dev, struct scatterlist *src,
 	}
 
 	if (iv_dma)
-		dma_unmap_single(dev, iv_dma, ivsize, DMA_TO_DEVICE);
+		dma_unmap_single(dev, iv_dma, ivsize, iv_dir);
 	if (sec4_sg_bytes)
 		dma_unmap_single(dev, sec4_sg_dma, sec4_sg_bytes,
 				 DMA_TO_DEVICE);
@@ -810,7 +814,7 @@ static void aead_unmap(struct device *dev,
 		       struct aead_request *req)
 {
 	caam_unmap(dev, req->src, req->dst,
-		   edesc->src_nents, edesc->dst_nents, 0, 0,
+		   edesc->src_nents, edesc->dst_nents, 0, 0, DMA_NONE,
 		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
 }
 
@@ -823,7 +827,7 @@ static void ablkcipher_unmap(struct device *dev,
 
 	caam_unmap(dev, req->src, req->dst,
 		   edesc->src_nents, edesc->dst_nents,
-		   edesc->iv_dma, ivsize,
+		   edesc->iv_dma, ivsize, edesc->iv_dir,
 		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
 }
 
@@ -912,6 +916,18 @@ static void ablkcipher_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	scatterwalk_map_and_copy(req->info, req->dst, req->nbytes - ivsize,
 				 ivsize, 0);
 
+	/* In case initial IV was generated, copy it in GIVCIPHER request */
+	if (edesc->iv_dir == DMA_FROM_DEVICE) {
+		u8 *iv;
+		struct skcipher_givcrypt_request *greq;
+
+		greq = container_of(req, struct skcipher_givcrypt_request,
+				    creq);
+		iv = (u8 *)edesc->hw_desc + desc_bytes(edesc->hw_desc) +
+		     edesc->sec4_sg_bytes;
+		memcpy(greq->giv, iv, ivsize);
+	}
+
 	kfree(edesc);
 
 	ablkcipher_request_complete(req, err);
@@ -922,10 +938,10 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 {
 	struct ablkcipher_request *req = context;
 	struct ablkcipher_edesc *edesc;
+#ifdef DEBUG
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 
-#ifdef DEBUG
 	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
 #endif
 
@@ -943,14 +959,6 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 		     edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
 
 	ablkcipher_unmap(jrdev, edesc, req);
-
-	/*
-	 * The crypto API expects us to set the IV (req->info) to the last
-	 * ciphertext block.
-	 */
-	scatterwalk_map_and_copy(req->info, req->src, req->nbytes - ivsize,
-				 ivsize, 0);
-
 	kfree(edesc);
 
 	ablkcipher_request_complete(req, err);
@@ -1099,15 +1107,14 @@ static void init_authenc_job(struct aead_request *req,
  */
 static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
 				struct ablkcipher_edesc *edesc,
-				struct ablkcipher_request *req,
-				bool iv_contig)
+				struct ablkcipher_request *req)
 {
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 	u32 *desc = edesc->hw_desc;
-	u32 out_options = 0, in_options;
-	dma_addr_t dst_dma, src_dma;
-	int len, sec4_sg_index = 0;
+	u32 out_options = 0;
+	dma_addr_t dst_dma;
+	int len;
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "presciv@"__stringify(__LINE__)": ",
@@ -1123,30 +1130,18 @@ static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
 	len = desc_len(sh_desc);
 	init_job_desc_shared(desc, ptr, len, HDR_SHARE_DEFER | HDR_REVERSE);
 
-	if (iv_contig) {
-		src_dma = edesc->iv_dma;
-		in_options = 0;
-	} else {
-		src_dma = edesc->sec4_sg_dma;
-		sec4_sg_index += edesc->src_nents + 1;
-		in_options = LDST_SGF;
-	}
-	append_seq_in_ptr(desc, src_dma, req->nbytes + ivsize, in_options);
+	append_seq_in_ptr(desc, edesc->sec4_sg_dma, req->nbytes + ivsize,
+			  LDST_SGF);
 
 	if (likely(req->src == req->dst)) {
-		if (edesc->src_nents == 1 && iv_contig) {
-			dst_dma = sg_dma_address(req->src);
-		} else {
-			dst_dma = edesc->sec4_sg_dma +
-				sizeof(struct sec4_sg_entry);
-			out_options = LDST_SGF;
-		}
+		dst_dma = edesc->sec4_sg_dma + sizeof(struct sec4_sg_entry);
+		out_options = LDST_SGF;
 	} else {
 		if (edesc->dst_nents == 1) {
 			dst_dma = sg_dma_address(req->dst);
 		} else {
-			dst_dma = edesc->sec4_sg_dma +
-				sec4_sg_index * sizeof(struct sec4_sg_entry);
+			dst_dma = edesc->sec4_sg_dma + (edesc->src_nents + 1) *
+				  sizeof(struct sec4_sg_entry);
 			out_options = LDST_SGF;
 		}
 	}
@@ -1158,13 +1153,12 @@ static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
  */
 static void init_ablkcipher_giv_job(u32 *sh_desc, dma_addr_t ptr,
 				    struct ablkcipher_edesc *edesc,
-				    struct ablkcipher_request *req,
-				    bool iv_contig)
+				    struct ablkcipher_request *req)
 {
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 	u32 *desc = edesc->hw_desc;
-	u32 out_options, in_options;
+	u32 in_options;
 	dma_addr_t dst_dma, src_dma;
 	int len, sec4_sg_index = 0;
 
@@ -1190,15 +1184,9 @@ static void init_ablkcipher_giv_job(u32 *sh_desc, dma_addr_t ptr,
 	}
 	append_seq_in_ptr(desc, src_dma, req->nbytes, in_options);
 
-	if (iv_contig) {
-		dst_dma = edesc->iv_dma;
-		out_options = 0;
-	} else {
-		dst_dma = edesc->sec4_sg_dma +
-			  sec4_sg_index * sizeof(struct sec4_sg_entry);
-		out_options = LDST_SGF;
-	}
-	append_seq_out_ptr(desc, dst_dma, req->nbytes + ivsize, out_options);
+	dst_dma = edesc->sec4_sg_dma + sec4_sg_index *
+		  sizeof(struct sec4_sg_entry);
+	append_seq_out_ptr(desc, dst_dma, req->nbytes + ivsize, LDST_SGF);
 }
 
 /*
@@ -1287,7 +1275,7 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 			GFP_DMA | flags);
 	if (!edesc) {
 		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents, 0,
-			   0, 0, 0);
+			   0, DMA_NONE, 0, 0);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1491,8 +1479,7 @@ static int aead_decrypt(struct aead_request *req)
  * allocate and map the ablkcipher extended descriptor for ablkcipher
  */
 static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
-						       *req, int desc_bytes,
-						       bool *iv_contig_out)
+						       *req, int desc_bytes)
 {
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
@@ -1501,8 +1488,8 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 		       GFP_KERNEL : GFP_ATOMIC;
 	int src_nents, mapped_src_nents, dst_nents = 0, mapped_dst_nents = 0;
 	struct ablkcipher_edesc *edesc;
-	dma_addr_t iv_dma = 0;
-	bool in_contig;
+	dma_addr_t iv_dma;
+	u8 *iv;
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 	int dst_sg_idx, sec4_sg_ents, sec4_sg_bytes;
 
@@ -1546,33 +1533,20 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 		}
 	}
 
-	iv_dma = dma_map_single(jrdev, req->info, ivsize, DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, iv_dma)) {
-		dev_err(jrdev, "unable to map IV\n");
-		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents, 0,
-			   0, 0, 0);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	if (mapped_src_nents == 1 &&
-	    iv_dma + ivsize == sg_dma_address(req->src)) {
-		in_contig = true;
-		sec4_sg_ents = 0;
-	} else {
-		in_contig = false;
-		sec4_sg_ents = 1 + mapped_src_nents;
-	}
+	sec4_sg_ents = 1 + mapped_src_nents;
 	dst_sg_idx = sec4_sg_ents;
 	sec4_sg_ents += mapped_dst_nents > 1 ? mapped_dst_nents : 0;
 	sec4_sg_bytes = sec4_sg_ents * sizeof(struct sec4_sg_entry);
 
-	/* allocate space for base edesc and hw desc commands, link tables */
-	edesc = kzalloc(sizeof(*edesc) + desc_bytes + sec4_sg_bytes,
+	/*
+	 * allocate space for base edesc and hw desc commands, link tables, IV
+	 */
+	edesc = kzalloc(sizeof(*edesc) + desc_bytes + sec4_sg_bytes + ivsize,
 			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
-		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, 0, 0);
+		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, DMA_NONE, 0, 0);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1581,13 +1555,24 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) +
 			 desc_bytes;
+	edesc->iv_dir = DMA_TO_DEVICE;
 
-	if (!in_contig) {
-		dma_to_sec4_sg_one(edesc->sec4_sg, iv_dma, ivsize, 0);
-		sg_to_sec4_sg_last(req->src, mapped_src_nents,
-				   edesc->sec4_sg + 1, 0);
+	/* Make sure IV is located in a DMAable area */
+	iv = (u8 *)edesc->hw_desc + desc_bytes + sec4_sg_bytes;
+	memcpy(iv, req->info, ivsize);
+
+	iv_dma = dma_map_single(jrdev, iv, ivsize, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, iv_dma)) {
+		dev_err(jrdev, "unable to map IV\n");
+		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, DMA_NONE, 0, 0);
+		kfree(edesc);
+		return ERR_PTR(-ENOMEM);
 	}
 
+	dma_to_sec4_sg_one(edesc->sec4_sg, iv_dma, ivsize, 0);
+	sg_to_sec4_sg_last(req->src, mapped_src_nents, edesc->sec4_sg + 1, 0);
+
 	if (mapped_dst_nents > 1) {
 		sg_to_sec4_sg_last(req->dst, mapped_dst_nents,
 				   edesc->sec4_sg + dst_sg_idx, 0);
@@ -1598,7 +1583,7 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
 		dev_err(jrdev, "unable to map S/G table\n");
 		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, 0, 0);
+			   iv_dma, ivsize, DMA_TO_DEVICE, 0, 0);
 		kfree(edesc);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -1611,7 +1596,6 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 		       sec4_sg_bytes, 1);
 #endif
 
-	*iv_contig_out = in_contig;
 	return edesc;
 }
 
@@ -1621,19 +1605,16 @@ static int ablkcipher_encrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
 	struct device *jrdev = ctx->jrdev;
-	bool iv_contig;
 	u32 *desc;
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = ablkcipher_edesc_alloc(req, DESC_JOB_IO_LEN *
-				       CAAM_CMD_SZ, &iv_contig);
+	edesc = ablkcipher_edesc_alloc(req, DESC_JOB_IO_LEN * CAAM_CMD_SZ);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
 	/* Create and submit job descriptor*/
-	init_ablkcipher_job(ctx->sh_desc_enc,
-		ctx->sh_desc_enc_dma, edesc, req, iv_contig);
+	init_ablkcipher_job(ctx->sh_desc_enc, ctx->sh_desc_enc_dma, edesc, req);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "ablkcipher jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
@@ -1657,20 +1638,25 @@ static int ablkcipher_decrypt(struct ablkcipher_request *req)
 	struct ablkcipher_edesc *edesc;
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 	struct device *jrdev = ctx->jrdev;
-	bool iv_contig;
 	u32 *desc;
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = ablkcipher_edesc_alloc(req, DESC_JOB_IO_LEN *
-				       CAAM_CMD_SZ, &iv_contig);
+	edesc = ablkcipher_edesc_alloc(req, DESC_JOB_IO_LEN * CAAM_CMD_SZ);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
+	/*
+	 * The crypto API expects us to set the IV (req->info) to the last
+	 * ciphertext block.
+	 */
+	scatterwalk_map_and_copy(req->info, req->src, req->nbytes - ivsize,
+				 ivsize, 0);
+
 	/* Create and submit job descriptor*/
-	init_ablkcipher_job(ctx->sh_desc_dec,
-		ctx->sh_desc_dec_dma, edesc, req, iv_contig);
+	init_ablkcipher_job(ctx->sh_desc_dec, ctx->sh_desc_dec_dma, edesc, req);
 	desc = edesc->hw_desc;
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "ablkcipher jobdesc@"__stringify(__LINE__)": ",
@@ -1695,8 +1681,7 @@ static int ablkcipher_decrypt(struct ablkcipher_request *req)
  */
 static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 				struct skcipher_givcrypt_request *greq,
-				int desc_bytes,
-				bool *iv_contig_out)
+				int desc_bytes)
 {
 	struct ablkcipher_request *req = &greq->creq;
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
@@ -1706,8 +1691,8 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 		       GFP_KERNEL : GFP_ATOMIC;
 	int src_nents, mapped_src_nents, dst_nents, mapped_dst_nents;
 	struct ablkcipher_edesc *edesc;
-	dma_addr_t iv_dma = 0;
-	bool out_contig;
+	dma_addr_t iv_dma;
+	u8 *iv;
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 	int dst_sg_idx, sec4_sg_ents, sec4_sg_bytes;
 
@@ -1752,36 +1737,20 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 		}
 	}
 
-	/*
-	 * Check if iv can be contiguous with source and destination.
-	 * If so, include it. If not, create scatterlist.
-	 */
-	iv_dma = dma_map_single(jrdev, greq->giv, ivsize, DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, iv_dma)) {
-		dev_err(jrdev, "unable to map IV\n");
-		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents, 0,
-			   0, 0, 0);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	sec4_sg_ents = mapped_src_nents > 1 ? mapped_src_nents : 0;
 	dst_sg_idx = sec4_sg_ents;
-	if (mapped_dst_nents == 1 &&
-	    iv_dma + ivsize == sg_dma_address(req->dst)) {
-		out_contig = true;
-	} else {
-		out_contig = false;
-		sec4_sg_ents += 1 + mapped_dst_nents;
-	}
+	sec4_sg_ents += 1 + mapped_dst_nents;
 
-	/* allocate space for base edesc and hw desc commands, link tables */
+	/*
+	 * allocate space for base edesc and hw desc commands, link tables, IV
+	 */
 	sec4_sg_bytes = sec4_sg_ents * sizeof(struct sec4_sg_entry);
-	edesc = kzalloc(sizeof(*edesc) + desc_bytes + sec4_sg_bytes,
+	edesc = kzalloc(sizeof(*edesc) + desc_bytes + sec4_sg_bytes + ivsize,
 			GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
-		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, 0, 0);
+		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, DMA_NONE, 0, 0);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1790,24 +1759,33 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) +
 			 desc_bytes;
+	edesc->iv_dir = DMA_FROM_DEVICE;
+
+	/* Make sure IV is located in a DMAable area */
+	iv = (u8 *)edesc->hw_desc + desc_bytes + sec4_sg_bytes;
+	iv_dma = dma_map_single(jrdev, iv, ivsize, DMA_FROM_DEVICE);
+	if (dma_mapping_error(jrdev, iv_dma)) {
+		dev_err(jrdev, "unable to map IV\n");
+		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, DMA_NONE, 0, 0);
+		kfree(edesc);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	if (mapped_src_nents > 1)
 		sg_to_sec4_sg_last(req->src, mapped_src_nents, edesc->sec4_sg,
 				   0);
 
-	if (!out_contig) {
-		dma_to_sec4_sg_one(edesc->sec4_sg + dst_sg_idx,
-				   iv_dma, ivsize, 0);
-		sg_to_sec4_sg_last(req->dst, mapped_dst_nents,
-				   edesc->sec4_sg + dst_sg_idx + 1, 0);
-	}
+	dma_to_sec4_sg_one(edesc->sec4_sg + dst_sg_idx, iv_dma, ivsize, 0);
+	sg_to_sec4_sg_last(req->dst, mapped_dst_nents, edesc->sec4_sg +
+			   dst_sg_idx + 1, 0);
 
 	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
 					    sec4_sg_bytes, DMA_TO_DEVICE);
 	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
 		dev_err(jrdev, "unable to map S/G table\n");
 		caam_unmap(jrdev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, 0, 0);
+			   iv_dma, ivsize, DMA_FROM_DEVICE, 0, 0);
 		kfree(edesc);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -1820,7 +1798,6 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 		       sec4_sg_bytes, 1);
 #endif
 
-	*iv_contig_out = out_contig;
 	return edesc;
 }
 
@@ -1831,19 +1808,17 @@ static int ablkcipher_givencrypt(struct skcipher_givcrypt_request *creq)
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
 	struct device *jrdev = ctx->jrdev;
-	bool iv_contig = false;
 	u32 *desc;
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = ablkcipher_giv_edesc_alloc(creq, DESC_JOB_IO_LEN *
-				       CAAM_CMD_SZ, &iv_contig);
+	edesc = ablkcipher_giv_edesc_alloc(creq, DESC_JOB_IO_LEN * CAAM_CMD_SZ);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
 	/* Create and submit job descriptor*/
 	init_ablkcipher_giv_job(ctx->sh_desc_givenc, ctx->sh_desc_givenc_dma,
-				edesc, req, iv_contig);
+				edesc, req);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR,
 		       "ablkcipher jobdesc@" __stringify(__LINE__) ": ",
diff --git a/drivers/crypto/caam/caamalg_desc.c b/drivers/crypto/caam/caamalg_desc.c
index 8ae7a1be7dfd..a408edd84f34 100644
--- a/drivers/crypto/caam/caamalg_desc.c
+++ b/drivers/crypto/caam/caamalg_desc.c
@@ -1093,7 +1093,7 @@ void cnstr_shdsc_rfc4543_encap(u32 * const desc, struct alginfo *cdata,
 	read_move_cmd = append_move(desc, MOVE_SRC_DESCBUF | MOVE_DEST_MATH3 |
 				    (0x6 << MOVE_LEN_SHIFT));
 	write_move_cmd = append_move(desc, MOVE_SRC_MATH3 | MOVE_DEST_DESCBUF |
-				     (0x8 << MOVE_LEN_SHIFT));
+				     (0x8 << MOVE_LEN_SHIFT) | MOVE_WAITCOMP);
 
 	/* Will read assoclen + cryptlen bytes */
 	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
@@ -1178,7 +1178,7 @@ void cnstr_shdsc_rfc4543_decap(u32 * const desc, struct alginfo *cdata,
 	read_move_cmd = append_move(desc, MOVE_SRC_DESCBUF | MOVE_DEST_MATH3 |
 				    (0x6 << MOVE_LEN_SHIFT));
 	write_move_cmd = append_move(desc, MOVE_SRC_MATH3 | MOVE_DEST_DESCBUF |
-				     (0x8 << MOVE_LEN_SHIFT));
+				     (0x8 << MOVE_LEN_SHIFT) | MOVE_WAITCOMP);
 
 	/* Will read assoclen + cryptlen bytes */
 	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c
index cacda0831390..6e61cc93c2b0 100644
--- a/drivers/crypto/caam/caamalg_qi.c
+++ b/drivers/crypto/caam/caamalg_qi.c
@@ -728,7 +728,7 @@ badkey:
  * @assoclen: associated data length, in CAAM endianness
  * @assoclen_dma: bus physical mapped address of req->assoclen
  * @drv_req: driver-specific request structure
- * @sgt: the h/w link table
+ * @sgt: the h/w link table, followed by IV
  */
 struct aead_edesc {
 	int src_nents;
@@ -739,9 +739,6 @@ struct aead_edesc {
 	unsigned int assoclen;
 	dma_addr_t assoclen_dma;
 	struct caam_drv_req drv_req;
-#define CAAM_QI_MAX_AEAD_SG						\
-	((CAAM_QI_MEMCACHE_SIZE - offsetof(struct aead_edesc, sgt)) /	\
-	 sizeof(struct qm_sg_entry))
 	struct qm_sg_entry sgt[0];
 };
 
@@ -753,7 +750,7 @@ struct aead_edesc {
  * @qm_sg_bytes: length of dma mapped h/w link table
  * @qm_sg_dma: bus physical mapped address of h/w link table
  * @drv_req: driver-specific request structure
- * @sgt: the h/w link table
+ * @sgt: the h/w link table, followed by IV
  */
 struct ablkcipher_edesc {
 	int src_nents;
@@ -762,9 +759,6 @@ struct ablkcipher_edesc {
 	int qm_sg_bytes;
 	dma_addr_t qm_sg_dma;
 	struct caam_drv_req drv_req;
-#define CAAM_QI_MAX_ABLKCIPHER_SG					    \
-	((CAAM_QI_MEMCACHE_SIZE - offsetof(struct ablkcipher_edesc, sgt)) / \
-	 sizeof(struct qm_sg_entry))
 	struct qm_sg_entry sgt[0];
 };
 
@@ -986,17 +980,8 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 		}
 	}
 
-	if ((alg->caam.rfc3686 && encrypt) || !alg->caam.geniv) {
+	if ((alg->caam.rfc3686 && encrypt) || !alg->caam.geniv)
 		ivsize = crypto_aead_ivsize(aead);
-		iv_dma = dma_map_single(qidev, req->iv, ivsize, DMA_TO_DEVICE);
-		if (dma_mapping_error(qidev, iv_dma)) {
-			dev_err(qidev, "unable to map IV\n");
-			caam_unmap(qidev, req->src, req->dst, src_nents,
-				   dst_nents, 0, 0, op_type, 0, 0);
-			qi_cache_free(edesc);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
 
 	/*
 	 * Create S/G table: req->assoclen, [IV,] req->src [, req->dst].
@@ -1004,16 +989,33 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	 */
 	qm_sg_ents = 1 + !!ivsize + mapped_src_nents +
 		     (mapped_dst_nents > 1 ? mapped_dst_nents : 0);
-	if (unlikely(qm_sg_ents > CAAM_QI_MAX_AEAD_SG)) {
-		dev_err(qidev, "Insufficient S/G entries: %d > %zu\n",
-			qm_sg_ents, CAAM_QI_MAX_AEAD_SG);
-		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, op_type, 0, 0);
+	sg_table = &edesc->sgt[0];
+	qm_sg_bytes = qm_sg_ents * sizeof(*sg_table);
+	if (unlikely(offsetof(struct aead_edesc, sgt) + qm_sg_bytes + ivsize >
+		     CAAM_QI_MEMCACHE_SIZE)) {
+		dev_err(qidev, "No space for %d S/G entries and/or %dB IV\n",
+			qm_sg_ents, ivsize);
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
 		qi_cache_free(edesc);
 		return ERR_PTR(-ENOMEM);
 	}
-	sg_table = &edesc->sgt[0];
-	qm_sg_bytes = qm_sg_ents * sizeof(*sg_table);
+
+	if (ivsize) {
+		u8 *iv = (u8 *)(sg_table + qm_sg_ents);
+
+		/* Make sure IV is located in a DMAable area */
+		memcpy(iv, req->iv, ivsize);
+
+		iv_dma = dma_map_single(qidev, iv, ivsize, DMA_TO_DEVICE);
+		if (dma_mapping_error(qidev, iv_dma)) {
+			dev_err(qidev, "unable to map IV\n");
+			caam_unmap(qidev, req->src, req->dst, src_nents,
+				   dst_nents, 0, 0, 0, 0, 0);
+			qi_cache_free(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
 
 	edesc->src_nents = src_nents;
 	edesc->dst_nents = dst_nents;
@@ -1166,15 +1168,27 @@ static void ablkcipher_done(struct caam_drv_req *drv_req, u32 status)
 #endif
 
 	ablkcipher_unmap(qidev, edesc, req);
-	qi_cache_free(edesc);
+
+	/* In case initial IV was generated, copy it in GIVCIPHER request */
+	if (edesc->drv_req.drv_ctx->op_type == GIVENCRYPT) {
+		u8 *iv;
+		struct skcipher_givcrypt_request *greq;
+
+		greq = container_of(req, struct skcipher_givcrypt_request,
+				    creq);
+		iv = (u8 *)edesc->sgt + edesc->qm_sg_bytes;
+		memcpy(greq->giv, iv, ivsize);
+	}
 
 	/*
 	 * The crypto API expects us to set the IV (req->info) to the last
 	 * ciphertext block. This is used e.g. by the CTS mode.
 	 */
-	scatterwalk_map_and_copy(req->info, req->dst, req->nbytes - ivsize,
-				 ivsize, 0);
+	if (edesc->drv_req.drv_ctx->op_type != DECRYPT)
+		scatterwalk_map_and_copy(req->info, req->dst, req->nbytes -
+					 ivsize, ivsize, 0);
 
+	qi_cache_free(edesc);
 	ablkcipher_request_complete(req, status);
 }
 
@@ -1189,9 +1203,9 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	int src_nents, mapped_src_nents, dst_nents = 0, mapped_dst_nents = 0;
 	struct ablkcipher_edesc *edesc;
 	dma_addr_t iv_dma;
-	bool in_contig;
+	u8 *iv;
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
-	int dst_sg_idx, qm_sg_ents;
+	int dst_sg_idx, qm_sg_ents, qm_sg_bytes;
 	struct qm_sg_entry *sg_table, *fd_sgt;
 	struct caam_drv_ctx *drv_ctx;
 	enum optype op_type = encrypt ? ENCRYPT : DECRYPT;
@@ -1238,55 +1252,53 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 		}
 	}
 
-	iv_dma = dma_map_single(qidev, req->info, ivsize, DMA_TO_DEVICE);
-	if (dma_mapping_error(qidev, iv_dma)) {
-		dev_err(qidev, "unable to map IV\n");
-		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
-			   0, 0, 0, 0);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	if (mapped_src_nents == 1 &&
-	    iv_dma + ivsize == sg_dma_address(req->src)) {
-		in_contig = true;
-		qm_sg_ents = 0;
-	} else {
-		in_contig = false;
-		qm_sg_ents = 1 + mapped_src_nents;
-	}
+	qm_sg_ents = 1 + mapped_src_nents;
 	dst_sg_idx = qm_sg_ents;
 
 	qm_sg_ents += mapped_dst_nents > 1 ? mapped_dst_nents : 0;
-	if (unlikely(qm_sg_ents > CAAM_QI_MAX_ABLKCIPHER_SG)) {
-		dev_err(qidev, "Insufficient S/G entries: %d > %zu\n",
-			qm_sg_ents, CAAM_QI_MAX_ABLKCIPHER_SG);
-		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, op_type, 0, 0);
+	qm_sg_bytes = qm_sg_ents * sizeof(struct qm_sg_entry);
+	if (unlikely(offsetof(struct ablkcipher_edesc, sgt) + qm_sg_bytes +
+		     ivsize > CAAM_QI_MEMCACHE_SIZE)) {
+		dev_err(qidev, "No space for %d S/G entries and/or %dB IV\n",
+			qm_sg_ents, ivsize);
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	/* allocate space for base edesc and link tables */
+	/* allocate space for base edesc, link tables and IV */
 	edesc = qi_cache_alloc(GFP_DMA | flags);
 	if (unlikely(!edesc)) {
 		dev_err(qidev, "could not allocate extended descriptor\n");
-		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, op_type, 0, 0);
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* Make sure IV is located in a DMAable area */
+	sg_table = &edesc->sgt[0];
+	iv = (u8 *)(sg_table + qm_sg_ents);
+	memcpy(iv, req->info, ivsize);
+
+	iv_dma = dma_map_single(qidev, iv, ivsize, DMA_TO_DEVICE);
+	if (dma_mapping_error(qidev, iv_dma)) {
+		dev_err(qidev, "unable to map IV\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
+		qi_cache_free(edesc);
 		return ERR_PTR(-ENOMEM);
 	}
 
 	edesc->src_nents = src_nents;
 	edesc->dst_nents = dst_nents;
 	edesc->iv_dma = iv_dma;
-	sg_table = &edesc->sgt[0];
-	edesc->qm_sg_bytes = qm_sg_ents * sizeof(*sg_table);
+	edesc->qm_sg_bytes = qm_sg_bytes;
 	edesc->drv_req.app_ctx = req;
 	edesc->drv_req.cbk = ablkcipher_done;
 	edesc->drv_req.drv_ctx = drv_ctx;
 
-	if (!in_contig) {
-		dma_to_qm_sg_one(sg_table, iv_dma, ivsize, 0);
-		sg_to_qm_sg_last(req->src, mapped_src_nents, sg_table + 1, 0);
-	}
+	dma_to_qm_sg_one(sg_table, iv_dma, ivsize, 0);
+	sg_to_qm_sg_last(req->src, mapped_src_nents, sg_table + 1, 0);
 
 	if (mapped_dst_nents > 1)
 		sg_to_qm_sg_last(req->dst, mapped_dst_nents, sg_table +
@@ -1304,20 +1316,12 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 
 	fd_sgt = &edesc->drv_req.fd_sgt[0];
 
-	if (!in_contig)
-		dma_to_qm_sg_one_last_ext(&fd_sgt[1], edesc->qm_sg_dma,
-					  ivsize + req->nbytes, 0);
-	else
-		dma_to_qm_sg_one_last(&fd_sgt[1], iv_dma, ivsize + req->nbytes,
-				      0);
+	dma_to_qm_sg_one_last_ext(&fd_sgt[1], edesc->qm_sg_dma,
+				  ivsize + req->nbytes, 0);
 
 	if (req->src == req->dst) {
-		if (!in_contig)
-			dma_to_qm_sg_one_ext(&fd_sgt[0], edesc->qm_sg_dma +
-					     sizeof(*sg_table), req->nbytes, 0);
-		else
-			dma_to_qm_sg_one(&fd_sgt[0], sg_dma_address(req->src),
-					 req->nbytes, 0);
+		dma_to_qm_sg_one_ext(&fd_sgt[0], edesc->qm_sg_dma +
+				     sizeof(*sg_table), req->nbytes, 0);
 	} else if (mapped_dst_nents > 1) {
 		dma_to_qm_sg_one_ext(&fd_sgt[0], edesc->qm_sg_dma + dst_sg_idx *
 				     sizeof(*sg_table), req->nbytes, 0);
@@ -1341,10 +1345,10 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 	int src_nents, mapped_src_nents, dst_nents, mapped_dst_nents;
 	struct ablkcipher_edesc *edesc;
 	dma_addr_t iv_dma;
-	bool out_contig;
+	u8 *iv;
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 	struct qm_sg_entry *sg_table, *fd_sgt;
-	int dst_sg_idx, qm_sg_ents;
+	int dst_sg_idx, qm_sg_ents, qm_sg_bytes;
 	struct caam_drv_ctx *drv_ctx;
 
 	drv_ctx = get_drv_ctx(ctx, GIVENCRYPT);
@@ -1392,46 +1396,45 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 		mapped_dst_nents = src_nents;
 	}
 
-	iv_dma = dma_map_single(qidev, creq->giv, ivsize, DMA_FROM_DEVICE);
-	if (dma_mapping_error(qidev, iv_dma)) {
-		dev_err(qidev, "unable to map IV\n");
-		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
-			   0, 0, 0, 0);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	qm_sg_ents = mapped_src_nents > 1 ? mapped_src_nents : 0;
 	dst_sg_idx = qm_sg_ents;
-	if (mapped_dst_nents == 1 &&
-	    iv_dma + ivsize == sg_dma_address(req->dst)) {
-		out_contig = true;
-	} else {
-		out_contig = false;
-		qm_sg_ents += 1 + mapped_dst_nents;
-	}
 
-	if (unlikely(qm_sg_ents > CAAM_QI_MAX_ABLKCIPHER_SG)) {
-		dev_err(qidev, "Insufficient S/G entries: %d > %zu\n",
-			qm_sg_ents, CAAM_QI_MAX_ABLKCIPHER_SG);
-		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, GIVENCRYPT, 0, 0);
+	qm_sg_ents += 1 + mapped_dst_nents;
+	qm_sg_bytes = qm_sg_ents * sizeof(struct qm_sg_entry);
+	if (unlikely(offsetof(struct ablkcipher_edesc, sgt) + qm_sg_bytes +
+		     ivsize > CAAM_QI_MEMCACHE_SIZE)) {
+		dev_err(qidev, "No space for %d S/G entries and/or %dB IV\n",
+			qm_sg_ents, ivsize);
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	/* allocate space for base edesc and link tables */
+	/* allocate space for base edesc, link tables and IV */
 	edesc = qi_cache_alloc(GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(qidev, "could not allocate extended descriptor\n");
-		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents,
-			   iv_dma, ivsize, GIVENCRYPT, 0, 0);
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* Make sure IV is located in a DMAable area */
+	sg_table = &edesc->sgt[0];
+	iv = (u8 *)(sg_table + qm_sg_ents);
+	iv_dma = dma_map_single(qidev, iv, ivsize, DMA_FROM_DEVICE);
+	if (dma_mapping_error(qidev, iv_dma)) {
+		dev_err(qidev, "unable to map IV\n");
+		caam_unmap(qidev, req->src, req->dst, src_nents, dst_nents, 0,
+			   0, 0, 0, 0);
+		qi_cache_free(edesc);
 		return ERR_PTR(-ENOMEM);
 	}
 
 	edesc->src_nents = src_nents;
 	edesc->dst_nents = dst_nents;
 	edesc->iv_dma = iv_dma;
-	sg_table = &edesc->sgt[0];
-	edesc->qm_sg_bytes = qm_sg_ents * sizeof(*sg_table);
+	edesc->qm_sg_bytes = qm_sg_bytes;
 	edesc->drv_req.app_ctx = req;
 	edesc->drv_req.cbk = ablkcipher_done;
 	edesc->drv_req.drv_ctx = drv_ctx;
@@ -1439,11 +1442,9 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 	if (mapped_src_nents > 1)
 		sg_to_qm_sg_last(req->src, mapped_src_nents, sg_table, 0);
 
-	if (!out_contig) {
-		dma_to_qm_sg_one(sg_table + dst_sg_idx, iv_dma, ivsize, 0);
-		sg_to_qm_sg_last(req->dst, mapped_dst_nents, sg_table +
-				 dst_sg_idx + 1, 0);
-	}
+	dma_to_qm_sg_one(sg_table + dst_sg_idx, iv_dma, ivsize, 0);
+	sg_to_qm_sg_last(req->dst, mapped_dst_nents, sg_table + dst_sg_idx + 1,
+			 0);
 
 	edesc->qm_sg_dma = dma_map_single(qidev, sg_table, edesc->qm_sg_bytes,
 					  DMA_TO_DEVICE);
@@ -1464,13 +1465,8 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 		dma_to_qm_sg_one(&fd_sgt[1], sg_dma_address(req->src),
 				 req->nbytes, 0);
 
-	if (!out_contig)
-		dma_to_qm_sg_one_ext(&fd_sgt[0], edesc->qm_sg_dma + dst_sg_idx *
-				     sizeof(*sg_table), ivsize + req->nbytes,
-				     0);
-	else
-		dma_to_qm_sg_one(&fd_sgt[0], sg_dma_address(req->dst),
-				 ivsize + req->nbytes, 0);
+	dma_to_qm_sg_one_ext(&fd_sgt[0], edesc->qm_sg_dma + dst_sg_idx *
+			     sizeof(*sg_table), ivsize + req->nbytes, 0);
 
 	return edesc;
 }
@@ -1480,6 +1476,7 @@ static inline int ablkcipher_crypt(struct ablkcipher_request *req, bool encrypt)
 	struct ablkcipher_edesc *edesc;
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
+	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 	int ret;
 
 	if (unlikely(caam_congested))
@@ -1490,6 +1487,14 @@ static inline int ablkcipher_crypt(struct ablkcipher_request *req, bool encrypt)
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
+	/*
+	 * The crypto API expects us to set the IV (req->info) to the last
+	 * ciphertext block.
+	 */
+	if (!encrypt)
+		scatterwalk_map_and_copy(req->info, req->src, req->nbytes -
+					 ivsize, ivsize, 0);
+
 	ret = caam_qi_enqueue(ctx->qidev, &edesc->drv_req);
 	if (!ret) {
 		ret = -EINPROGRESS;
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
index 7a897209f181..578ea63a3109 100644
--- a/drivers/crypto/caam/caampkc.c
+++ b/drivers/crypto/caam/caampkc.c
@@ -66,7 +66,7 @@ static void rsa_priv_f2_unmap(struct device *dev, struct rsa_edesc *edesc,
 	struct caam_rsa_key *key = &ctx->key;
 	struct rsa_priv_f2_pdb *pdb = &edesc->pdb.priv_f2;
 	size_t p_sz = key->p_sz;
-	size_t q_sz = key->p_sz;
+	size_t q_sz = key->q_sz;
 
 	dma_unmap_single(dev, pdb->d_dma, key->d_sz, DMA_TO_DEVICE);
 	dma_unmap_single(dev, pdb->p_dma, p_sz, DMA_TO_DEVICE);
@@ -83,7 +83,7 @@ static void rsa_priv_f3_unmap(struct device *dev, struct rsa_edesc *edesc,
 	struct caam_rsa_key *key = &ctx->key;
 	struct rsa_priv_f3_pdb *pdb = &edesc->pdb.priv_f3;
 	size_t p_sz = key->p_sz;
-	size_t q_sz = key->p_sz;
+	size_t q_sz = key->q_sz;
 
 	dma_unmap_single(dev, pdb->p_dma, p_sz, DMA_TO_DEVICE);
 	dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE);
@@ -166,18 +166,71 @@ static void rsa_priv_f3_done(struct device *dev, u32 *desc, u32 err,
 	akcipher_request_complete(req, err);
 }
 
+static int caam_rsa_count_leading_zeros(struct scatterlist *sgl,
+					unsigned int nbytes,
+					unsigned int flags)
+{
+	struct sg_mapping_iter miter;
+	int lzeros, ents;
+	unsigned int len;
+	unsigned int tbytes = nbytes;
+	const u8 *buff;
+
+	ents = sg_nents_for_len(sgl, nbytes);
+	if (ents < 0)
+		return ents;
+
+	sg_miter_start(&miter, sgl, ents, SG_MITER_FROM_SG | flags);
+
+	lzeros = 0;
+	len = 0;
+	while (nbytes > 0) {
+		while (len && !*buff) {
+			lzeros++;
+			len--;
+			buff++;
+		}
+
+		if (len && *buff)
+			break;
+
+		sg_miter_next(&miter);
+		buff = miter.addr;
+		len = miter.length;
+
+		nbytes -= lzeros;
+		lzeros = 0;
+	}
+
+	miter.consumed = lzeros;
+	sg_miter_stop(&miter);
+	nbytes -= lzeros;
+
+	return tbytes - nbytes;
+}
+
 static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 					 size_t desclen)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct device *dev = ctx->dev;
+	struct caam_rsa_req_ctx *req_ctx = akcipher_request_ctx(req);
 	struct rsa_edesc *edesc;
 	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 		       GFP_KERNEL : GFP_ATOMIC;
+	int sg_flags = (flags == GFP_ATOMIC) ? SG_MITER_ATOMIC : 0;
 	int sgc;
 	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
 	int src_nents, dst_nents;
+	int lzeros;
+
+	lzeros = caam_rsa_count_leading_zeros(req->src, req->src_len, sg_flags);
+	if (lzeros < 0)
+		return ERR_PTR(lzeros);
+
+	req->src_len -= lzeros;
+	req->src = scatterwalk_ffwd(req_ctx->src, req->src, lzeros);
 
 	src_nents = sg_nents_for_len(req->src, req->src_len);
 	dst_nents = sg_nents_for_len(req->dst, req->dst_len);
@@ -344,7 +397,7 @@ static int set_rsa_priv_f2_pdb(struct akcipher_request *req,
 	struct rsa_priv_f2_pdb *pdb = &edesc->pdb.priv_f2;
 	int sec4_sg_index = 0;
 	size_t p_sz = key->p_sz;
-	size_t q_sz = key->p_sz;
+	size_t q_sz = key->q_sz;
 
 	pdb->d_dma = dma_map_single(dev, key->d, key->d_sz, DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, pdb->d_dma)) {
@@ -419,7 +472,7 @@ static int set_rsa_priv_f3_pdb(struct akcipher_request *req,
 	struct rsa_priv_f3_pdb *pdb = &edesc->pdb.priv_f3;
 	int sec4_sg_index = 0;
 	size_t p_sz = key->p_sz;
-	size_t q_sz = key->p_sz;
+	size_t q_sz = key->q_sz;
 
 	pdb->p_dma = dma_map_single(dev, key->p, p_sz, DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, pdb->p_dma)) {
@@ -730,19 +783,12 @@ static u8 *caam_read_rsa_crt(const u8 *ptr, size_t nbytes, size_t dstlen)
  */
 static inline u8 *caam_read_raw_data(const u8 *buf, size_t *nbytes)
 {
-	u8 *val;
 
 	caam_rsa_drop_leading_zeros(&buf, nbytes);
 	if (!*nbytes)
 		return NULL;
 
-	val = kzalloc(*nbytes, GFP_DMA | GFP_KERNEL);
-	if (!val)
-		return NULL;
-
-	memcpy(val, buf, *nbytes);
-
-	return val;
+	return kmemdup(buf, *nbytes, GFP_DMA | GFP_KERNEL);
 }
 
 static int caam_rsa_check_key_length(unsigned int len)
@@ -953,6 +999,7 @@ static struct akcipher_alg caam_rsa = {
 	.max_size = caam_rsa_max_size,
 	.init = caam_rsa_init_tfm,
 	.exit = caam_rsa_exit_tfm,
+	.reqsize = sizeof(struct caam_rsa_req_ctx),
 	.base = {
 		.cra_name = "rsa",
 		.cra_driver_name = "rsa-caam",
diff --git a/drivers/crypto/caam/caampkc.h b/drivers/crypto/caam/caampkc.h
index fd145c46eae1..82645bcf8b27 100644
--- a/drivers/crypto/caam/caampkc.h
+++ b/drivers/crypto/caam/caampkc.h
@@ -96,6 +96,14 @@ struct caam_rsa_ctx {
 };
 
 /**
+ * caam_rsa_req_ctx - per request context.
+ * @src: input scatterlist (stripped of leading zeros)
+ */
+struct caam_rsa_req_ctx {
+	struct scatterlist src[2];
+};
+
+/**
  * rsa_edesc - s/w-extended rsa descriptor
  * @src_nents     : number of segments in input scatterlist
  * @dst_nents     : number of segments in output scatterlist
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index e4cc636e1104..538c01f428c1 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -322,9 +322,9 @@ static int caam_remove(struct platform_device *pdev)
 
 	/*
 	 * De-initialize RNG state handles initialized by this driver.
-	 * In case of DPAA 2.x, RNG is managed by MC firmware.
+	 * In case of SoCs with Management Complex, RNG is managed by MC f/w.
 	 */
-	if (!caam_dpaa2 && ctrlpriv->rng4_sh_init)
+	if (!ctrlpriv->mc_en && ctrlpriv->rng4_sh_init)
 		deinstantiate_rng(ctrldev, ctrlpriv->rng4_sh_init);
 
 	/* Shut down debug views */
@@ -396,11 +396,56 @@ start_rng:
 	clrsetbits_32(&r4tst->rtmctl, RTMCTL_PRGM, RTMCTL_SAMP_MODE_RAW_ES_SC);
 }
 
+static int caam_get_era_from_hw(struct caam_ctrl __iomem *ctrl)
+{
+	static const struct {
+		u16 ip_id;
+		u8 maj_rev;
+		u8 era;
+	} id[] = {
+		{0x0A10, 1, 1},
+		{0x0A10, 2, 2},
+		{0x0A12, 1, 3},
+		{0x0A14, 1, 3},
+		{0x0A14, 2, 4},
+		{0x0A16, 1, 4},
+		{0x0A10, 3, 4},
+		{0x0A11, 1, 4},
+		{0x0A18, 1, 4},
+		{0x0A11, 2, 5},
+		{0x0A12, 2, 5},
+		{0x0A13, 1, 5},
+		{0x0A1C, 1, 5}
+	};
+	u32 ccbvid, id_ms;
+	u8 maj_rev, era;
+	u16 ip_id;
+	int i;
+
+	ccbvid = rd_reg32(&ctrl->perfmon.ccb_id);
+	era = (ccbvid & CCBVID_ERA_MASK) >> CCBVID_ERA_SHIFT;
+	if (era)	/* This is '0' prior to CAAM ERA-6 */
+		return era;
+
+	id_ms = rd_reg32(&ctrl->perfmon.caam_id_ms);
+	ip_id = (id_ms & SECVID_MS_IPID_MASK) >> SECVID_MS_IPID_SHIFT;
+	maj_rev = (id_ms & SECVID_MS_MAJ_REV_MASK) >> SECVID_MS_MAJ_REV_SHIFT;
+
+	for (i = 0; i < ARRAY_SIZE(id); i++)
+		if (id[i].ip_id == ip_id && id[i].maj_rev == maj_rev)
+			return id[i].era;
+
+	return -ENOTSUPP;
+}
+
 /**
  * caam_get_era() - Return the ERA of the SEC on SoC, based
- * on "sec-era" propery in the DTS. This property is updated by u-boot.
+ * on "sec-era" optional property in the DTS. This property is updated
+ * by u-boot.
+ * In case this property is not passed an attempt to retrieve the CAAM
+ * era via register reads will be made.
  **/
-int caam_get_era(void)
+static int caam_get_era(struct caam_ctrl __iomem *ctrl)
 {
 	struct device_node *caam_node;
 	int ret;
@@ -410,9 +455,11 @@ int caam_get_era(void)
 	ret = of_property_read_u32(caam_node, "fsl,sec-era", &prop);
 	of_node_put(caam_node);
 
-	return ret ? -ENOTSUPP : prop;
+	if (!ret)
+		return prop;
+	else
+		return caam_get_era_from_hw(ctrl);
 }
-EXPORT_SYMBOL(caam_get_era);
 
 static const struct of_device_id caam_match[] = {
 	{
@@ -571,11 +618,15 @@ static int caam_probe(struct platform_device *pdev)
 	/*
 	 * Enable DECO watchdogs and, if this is a PHYS_ADDR_T_64BIT kernel,
 	 * long pointers in master configuration register.
-	 * In case of DPAA 2.x, Management Complex firmware performs
+	 * In case of SoCs with Management Complex, MC f/w performs
 	 * the configuration.
 	 */
 	caam_dpaa2 = !!(comp_params & CTPR_MS_DPAA2);
-	if (!caam_dpaa2)
+	np = of_find_compatible_node(NULL, NULL, "fsl,qoriq-mc");
+	ctrlpriv->mc_en = !!np;
+	of_node_put(np);
+
+	if (!ctrlpriv->mc_en)
 		clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK | MCFGR_LONG_PTR,
 			      MCFGR_AWCACHE_CACH | MCFGR_AWCACHE_BUFF |
 			      MCFGR_WDENABLE | MCFGR_LARGE_BURST |
@@ -623,7 +674,7 @@ static int caam_probe(struct platform_device *pdev)
 		goto iounmap_ctrl;
 	}
 
-	ctrlpriv->era = caam_get_era();
+	ctrlpriv->era = caam_get_era(ctrl);
 
 	ret = of_platform_populate(nprop, caam_match, NULL, dev);
 	if (ret) {
@@ -686,9 +737,9 @@ static int caam_probe(struct platform_device *pdev)
 	/*
 	 * If SEC has RNG version >= 4 and RNG state handle has not been
 	 * already instantiated, do RNG instantiation
-	 * In case of DPAA 2.x, RNG is managed by MC firmware.
+	 * In case of SoCs with Management Complex, RNG is managed by MC f/w.
 	 */
-	if (!caam_dpaa2 &&
+	if (!ctrlpriv->mc_en &&
 	    (cha_vid_ls & CHA_ID_LS_RNG_MASK) >> CHA_ID_LS_RNG_SHIFT >= 4) {
 		ctrlpriv->rng4_sh_init =
 			rd_reg32(&ctrl->r4tst[0].rdsta);
@@ -757,9 +808,8 @@ static int caam_probe(struct platform_device *pdev)
 	/* Report "alive" for developer to see */
 	dev_info(dev, "device ID = 0x%016llx (Era %d)\n", caam_id,
 		 ctrlpriv->era);
-	dev_info(dev, "job rings = %d, qi = %d, dpaa2 = %s\n",
-		 ctrlpriv->total_jobrs, ctrlpriv->qi_present,
-		 caam_dpaa2 ? "yes" : "no");
+	dev_info(dev, "job rings = %d, qi = %d\n",
+		 ctrlpriv->total_jobrs, ctrlpriv->qi_present);
 
 #ifdef CONFIG_DEBUG_FS
 	debugfs_create_file("rq_dequeued", S_IRUSR | S_IRGRP | S_IROTH,
diff --git a/drivers/crypto/caam/ctrl.h b/drivers/crypto/caam/ctrl.h
index be693a2cc25e..f3ecd67922a7 100644
--- a/drivers/crypto/caam/ctrl.h
+++ b/drivers/crypto/caam/ctrl.h
@@ -9,8 +9,6 @@
 #define CTRL_H
 
 /* Prototypes for backend-level services exposed to APIs */
-int caam_get_era(void);
-
 extern bool caam_dpaa2;
 
 #endif /* CTRL_H */
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index 7696a774a362..babc78abd155 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -82,6 +82,7 @@ struct caam_drv_private {
 	 */
 	u8 total_jobrs;		/* Total Job Rings in device */
 	u8 qi_present;		/* Nonzero if QI present in device */
+	u8 mc_en;		/* Nonzero if MC f/w is active */
 	int secvio_irq;		/* Security violation interrupt number */
 	int virt_en;		/* Virtualization enabled in CAAM */
 	int era;		/* CAAM Era (internal HW revision) */
diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c
index b9480828da38..67f7f8c42c93 100644
--- a/drivers/crypto/caam/qi.c
+++ b/drivers/crypto/caam/qi.c
@@ -657,9 +657,8 @@ static int init_cgr(struct device *qidev)
 {
 	int ret;
 	struct qm_mcc_initcgr opts;
-	const u64 cpus = *(u64 *)qman_affine_cpus();
-	const int num_cpus = hweight64(cpus);
-	const u64 val = num_cpus * MAX_RSP_FQ_BACKLOG_PER_CPU;
+	const u64 val = (u64)cpumask_weight(qman_affine_cpus()) *
+			MAX_RSP_FQ_BACKLOG_PER_CPU;
 
 	ret = qman_alloc_cgrid(&qipriv.cgr.cgrid);
 	if (ret) {
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index fee363865d88..4fb91ba39c36 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -312,11 +312,17 @@ struct caam_perfmon {
 
 	/* Component Instantiation Parameters			fe0-fff */
 	u32 rtic_id;		/* RVID - RTIC Version ID	*/
+#define CCBVID_ERA_MASK		0xff000000
+#define CCBVID_ERA_SHIFT	24
 	u32 ccb_id;		/* CCBVID - CCB Version ID	*/
 	u32 cha_id_ms;		/* CHAVID - CHA Version ID Most Significant*/
 	u32 cha_id_ls;		/* CHAVID - CHA Version ID Least Significant*/
 	u32 cha_num_ms;		/* CHANUM - CHA Number Most Significant	*/
 	u32 cha_num_ls;		/* CHANUM - CHA Number Least Significant*/
+#define SECVID_MS_IPID_MASK	0xffff0000
+#define SECVID_MS_IPID_SHIFT	16
+#define SECVID_MS_MAJ_REV_MASK	0x0000ff00
+#define SECVID_MS_MAJ_REV_SHIFT	8
 	u32 caam_id_ms;		/* CAAMVID - CAAM Version ID MS	*/
 	u32 caam_id_ls;		/* CAAMVID - CAAM Version ID LS	*/
 };
diff --git a/drivers/crypto/cavium/zip/common.h b/drivers/crypto/cavium/zip/common.h
index dc451e0a43c5..58fb3ed6e644 100644
--- a/drivers/crypto/cavium/zip/common.h
+++ b/drivers/crypto/cavium/zip/common.h
@@ -46,8 +46,10 @@
 #ifndef __COMMON_H__
 #define __COMMON_H__
 
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
@@ -149,6 +151,25 @@ struct zip_operation {
 	u32   sizeofzops;
 };
 
+static inline int zip_poll_result(union zip_zres_s *result)
+{
+	int retries = 1000;
+
+	while (!result->s.compcode) {
+		if (!--retries) {
+			pr_err("ZIP ERR: request timed out");
+			return -ETIMEDOUT;
+		}
+		udelay(10);
+		/*
+		 * Force re-reading of compcode which is updated
+		 * by the ZIP coprocessor.
+		 */
+		rmb();
+	}
+	return 0;
+}
+
 /* error messages */
 #define zip_err(fmt, args...) pr_err("ZIP ERR:%s():%d: " \
 			      fmt "\n", __func__, __LINE__, ## args)
diff --git a/drivers/crypto/cavium/zip/zip_crypto.c b/drivers/crypto/cavium/zip/zip_crypto.c
index 8df4d26cf9d4..b92b6e7e100f 100644
--- a/drivers/crypto/cavium/zip/zip_crypto.c
+++ b/drivers/crypto/cavium/zip/zip_crypto.c
@@ -124,7 +124,7 @@ int zip_compress(const u8 *src, unsigned int slen,
 		 struct zip_kernel_ctx *zip_ctx)
 {
 	struct zip_operation  *zip_ops   = NULL;
-	struct zip_state      zip_state;
+	struct zip_state      *zip_state;
 	struct zip_device     *zip = NULL;
 	int ret;
 
@@ -135,20 +135,23 @@ int zip_compress(const u8 *src, unsigned int slen,
 	if (!zip)
 		return -ENODEV;
 
-	memset(&zip_state, 0, sizeof(struct zip_state));
+	zip_state = kzalloc(sizeof(*zip_state), GFP_ATOMIC);
+	if (!zip_state)
+		return -ENOMEM;
+
 	zip_ops = &zip_ctx->zip_comp;
 
 	zip_ops->input_len  = slen;
 	zip_ops->output_len = *dlen;
 	memcpy(zip_ops->input, src, slen);
 
-	ret = zip_deflate(zip_ops, &zip_state, zip);
+	ret = zip_deflate(zip_ops, zip_state, zip);
 
 	if (!ret) {
 		*dlen = zip_ops->output_len;
 		memcpy(dst, zip_ops->output, *dlen);
 	}
-
+	kfree(zip_state);
 	return ret;
 }
 
@@ -157,7 +160,7 @@ int zip_decompress(const u8 *src, unsigned int slen,
 		   struct zip_kernel_ctx *zip_ctx)
 {
 	struct zip_operation  *zip_ops   = NULL;
-	struct zip_state      zip_state;
+	struct zip_state      *zip_state;
 	struct zip_device     *zip = NULL;
 	int ret;
 
@@ -168,7 +171,10 @@ int zip_decompress(const u8 *src, unsigned int slen,
 	if (!zip)
 		return -ENODEV;
 
-	memset(&zip_state, 0, sizeof(struct zip_state));
+	zip_state = kzalloc(sizeof(*zip_state), GFP_ATOMIC);
+	if (!zip_state)
+		return -ENOMEM;
+
 	zip_ops = &zip_ctx->zip_decomp;
 	memcpy(zip_ops->input, src, slen);
 
@@ -179,13 +185,13 @@ int zip_decompress(const u8 *src, unsigned int slen,
 	zip_ops->input_len  = slen;
 	zip_ops->output_len = *dlen;
 
-	ret = zip_inflate(zip_ops, &zip_state, zip);
+	ret = zip_inflate(zip_ops, zip_state, zip);
 
 	if (!ret) {
 		*dlen = zip_ops->output_len;
 		memcpy(dst, zip_ops->output, *dlen);
 	}
-
+	kfree(zip_state);
 	return ret;
 }
 
diff --git a/drivers/crypto/cavium/zip/zip_deflate.c b/drivers/crypto/cavium/zip/zip_deflate.c
index 9a944b8c1e29..d7133f857d67 100644
--- a/drivers/crypto/cavium/zip/zip_deflate.c
+++ b/drivers/crypto/cavium/zip/zip_deflate.c
@@ -129,8 +129,8 @@ int zip_deflate(struct zip_operation *zip_ops, struct zip_state *s,
 	/* Stats update for compression requests submitted */
 	atomic64_inc(&zip_dev->stats.comp_req_submit);
 
-	while (!result_ptr->s.compcode)
-		continue;
+	/* Wait for completion or error */
+	zip_poll_result(result_ptr);
 
 	/* Stats update for compression requests completed */
 	atomic64_inc(&zip_dev->stats.comp_req_complete);
diff --git a/drivers/crypto/cavium/zip/zip_device.c b/drivers/crypto/cavium/zip/zip_device.c
index ccf21fb91513..f174ec29ed69 100644
--- a/drivers/crypto/cavium/zip/zip_device.c
+++ b/drivers/crypto/cavium/zip/zip_device.c
@@ -87,12 +87,12 @@ u32 zip_load_instr(union zip_inst_s *instr,
 	 * Distribute the instructions between the enabled queues based on
 	 * the CPU id.
 	 */
-	if (smp_processor_id() % 2 == 0)
+	if (raw_smp_processor_id() % 2 == 0)
 		queue = 0;
 	else
 		queue = 1;
 
-	zip_dbg("CPU Core: %d Queue number:%d", smp_processor_id(), queue);
+	zip_dbg("CPU Core: %d Queue number:%d", raw_smp_processor_id(), queue);
 
 	/* Take cmd buffer lock */
 	spin_lock(&zip_dev->iq[queue].lock);
diff --git a/drivers/crypto/cavium/zip/zip_inflate.c b/drivers/crypto/cavium/zip/zip_inflate.c
index 50cbdd83dbf2..7e0d73e2f89e 100644
--- a/drivers/crypto/cavium/zip/zip_inflate.c
+++ b/drivers/crypto/cavium/zip/zip_inflate.c
@@ -143,8 +143,8 @@ int zip_inflate(struct zip_operation *zip_ops, struct zip_state *s,
 	/* Decompression requests submitted stats update */
 	atomic64_inc(&zip_dev->stats.decomp_req_submit);
 
-	while (!result_ptr->s.compcode)
-		continue;
+	/* Wait for completion or error */
+	zip_poll_result(result_ptr);
 
 	/* Decompression requests completed stats update */
 	atomic64_inc(&zip_dev->stats.decomp_req_complete);
diff --git a/drivers/crypto/cavium/zip/zip_main.c b/drivers/crypto/cavium/zip/zip_main.c
index 1cd8aa488185..be055b9547f6 100644
--- a/drivers/crypto/cavium/zip/zip_main.c
+++ b/drivers/crypto/cavium/zip/zip_main.c
@@ -113,7 +113,7 @@ struct zip_device *zip_get_device(int node)
  */
 int zip_get_node_id(void)
 {
-	return cpu_to_node(smp_processor_id());
+	return cpu_to_node(raw_smp_processor_id());
 }
 
 /* Initializes the ZIP h/w sub-system */
@@ -469,6 +469,8 @@ static int zip_show_stats(struct seq_file *s, void *unused)
 	struct zip_stats  *st;
 
 	for (index = 0; index < MAX_ZIP_DEVICES; index++) {
+		u64 pending = 0;
+
 		if (zip_dev[index]) {
 			zip = zip_dev[index];
 			st  = &zip->stats;
@@ -476,16 +478,15 @@ static int zip_show_stats(struct seq_file *s, void *unused)
 			/* Get all the pending requests */
 			for (q = 0; q < ZIP_NUM_QUEUES; q++) {
 				val = zip_reg_read((zip->reg_base +
-						    ZIP_DBG_COREX_STA(q)));
-				val = (val >> 32);
-				val = val & 0xffffff;
-				atomic64_add(val, &st->pending_req);
+						    ZIP_DBG_QUEX_STA(q)));
+				pending += val >> 32 & 0xffffff;
 			}
 
-			avg_chunk = (atomic64_read(&st->comp_in_bytes) /
-				     atomic64_read(&st->comp_req_complete));
-			avg_cr = (atomic64_read(&st->comp_in_bytes) /
-				  atomic64_read(&st->comp_out_bytes));
+			val = atomic64_read(&st->comp_req_complete);
+			avg_chunk = (val) ? atomic64_read(&st->comp_in_bytes) / val : 0;
+
+			val = atomic64_read(&st->comp_out_bytes);
+			avg_cr = (val) ? atomic64_read(&st->comp_in_bytes) / val : 0;
 			seq_printf(s, "        ZIP Device %d Stats\n"
 				      "-----------------------------------\n"
 				      "Comp Req Submitted        : \t%lld\n"
@@ -513,10 +514,7 @@ static int zip_show_stats(struct seq_file *s, void *unused)
 				       (u64)atomic64_read(&st->decomp_in_bytes),
 				       (u64)atomic64_read(&st->decomp_out_bytes),
 				       (u64)atomic64_read(&st->decomp_bad_reqs),
-				       (u64)atomic64_read(&st->pending_req));
-
-			/* Reset pending requests  count */
-			atomic64_set(&st->pending_req, 0);
+				       pending);
 		}
 	}
 	return 0;
diff --git a/drivers/crypto/cavium/zip/zip_main.h b/drivers/crypto/cavium/zip/zip_main.h
index 64e051f60784..e1e4fa92ce80 100644
--- a/drivers/crypto/cavium/zip/zip_main.h
+++ b/drivers/crypto/cavium/zip/zip_main.h
@@ -74,7 +74,6 @@ struct zip_stats {
 	atomic64_t    comp_req_complete;
 	atomic64_t    decomp_req_submit;
 	atomic64_t    decomp_req_complete;
-	atomic64_t    pending_req;
 	atomic64_t    comp_in_bytes;
 	atomic64_t    comp_out_bytes;
 	atomic64_t    decomp_in_bytes;
diff --git a/drivers/crypto/cavium/zip/zip_regs.h b/drivers/crypto/cavium/zip/zip_regs.h
index d0be682305c1..874e0236c87e 100644
--- a/drivers/crypto/cavium/zip/zip_regs.h
+++ b/drivers/crypto/cavium/zip/zip_regs.h
@@ -443,7 +443,7 @@ union zip_corex_bist_status {
 
 static inline u64 ZIP_COREX_BIST_STATUS(u64 param1)
 {
-	if (((param1 <= 1)))
+	if (param1 <= 1)
 		return 0x0520ull + (param1 & 1) * 0x8ull;
 	pr_err("ZIP_COREX_BIST_STATUS: %llu\n", param1);
 	return 0;
@@ -537,7 +537,7 @@ union zip_dbg_corex_inst {
 
 static inline u64 ZIP_DBG_COREX_INST(u64 param1)
 {
-	if (((param1 <= 1)))
+	if (param1 <= 1)
 		return 0x0640ull + (param1 & 1) * 0x8ull;
 	pr_err("ZIP_DBG_COREX_INST: %llu\n", param1);
 	return 0;
@@ -568,7 +568,7 @@ union zip_dbg_corex_sta {
 
 static inline u64 ZIP_DBG_COREX_STA(u64 param1)
 {
-	if (((param1 <= 1)))
+	if (param1 <= 1)
 		return 0x0680ull + (param1 & 1) * 0x8ull;
 	pr_err("ZIP_DBG_COREX_STA: %llu\n", param1);
 	return 0;
@@ -599,7 +599,7 @@ union zip_dbg_quex_sta {
 
 static inline u64 ZIP_DBG_QUEX_STA(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x1800ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_DBG_QUEX_STA: %llu\n", param1);
 	return 0;
@@ -817,7 +817,7 @@ union zip_msix_pbax {
 
 static inline u64 ZIP_MSIX_PBAX(u64 param1)
 {
-	if (((param1 == 0)))
+	if (param1 == 0)
 		return 0x0000838000FF0000ull;
 	pr_err("ZIP_MSIX_PBAX: %llu\n", param1);
 	return 0;
@@ -846,7 +846,7 @@ union zip_msix_vecx_addr {
 
 static inline u64 ZIP_MSIX_VECX_ADDR(u64 param1)
 {
-	if (((param1 <= 17)))
+	if (param1 <= 17)
 		return 0x0000838000F00000ull + (param1 & 31) * 0x10ull;
 	pr_err("ZIP_MSIX_VECX_ADDR: %llu\n", param1);
 	return 0;
@@ -875,7 +875,7 @@ union zip_msix_vecx_ctl {
 
 static inline u64 ZIP_MSIX_VECX_CTL(u64 param1)
 {
-	if (((param1 <= 17)))
+	if (param1 <= 17)
 		return 0x0000838000F00008ull + (param1 & 31) * 0x10ull;
 	pr_err("ZIP_MSIX_VECX_CTL: %llu\n", param1);
 	return 0;
@@ -900,7 +900,7 @@ union zip_quex_done {
 
 static inline u64 ZIP_QUEX_DONE(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x2000ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_DONE: %llu\n", param1);
 	return 0;
@@ -925,7 +925,7 @@ union zip_quex_done_ack {
 
 static inline u64 ZIP_QUEX_DONE_ACK(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x2200ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_DONE_ACK: %llu\n", param1);
 	return 0;
@@ -950,7 +950,7 @@ union zip_quex_done_ena_w1c {
 
 static inline u64 ZIP_QUEX_DONE_ENA_W1C(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x2600ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_DONE_ENA_W1C: %llu\n", param1);
 	return 0;
@@ -975,7 +975,7 @@ union zip_quex_done_ena_w1s {
 
 static inline u64 ZIP_QUEX_DONE_ENA_W1S(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x2400ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_DONE_ENA_W1S: %llu\n", param1);
 	return 0;
@@ -1004,7 +1004,7 @@ union zip_quex_done_wait {
 
 static inline u64 ZIP_QUEX_DONE_WAIT(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x2800ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_DONE_WAIT: %llu\n", param1);
 	return 0;
@@ -1029,7 +1029,7 @@ union zip_quex_doorbell {
 
 static inline u64 ZIP_QUEX_DOORBELL(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x4000ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_DOORBELL: %llu\n", param1);
 	return 0;
@@ -1058,7 +1058,7 @@ union zip_quex_err_ena_w1c {
 
 static inline u64 ZIP_QUEX_ERR_ENA_W1C(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x3600ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_ERR_ENA_W1C: %llu\n", param1);
 	return 0;
@@ -1087,7 +1087,7 @@ union zip_quex_err_ena_w1s {
 
 static inline u64 ZIP_QUEX_ERR_ENA_W1S(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x3400ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_ERR_ENA_W1S: %llu\n", param1);
 	return 0;
@@ -1120,7 +1120,7 @@ union zip_quex_err_int {
 
 static inline u64 ZIP_QUEX_ERR_INT(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x3000ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_ERR_INT: %llu\n", param1);
 	return 0;
@@ -1150,7 +1150,7 @@ union zip_quex_err_int_w1s {
 
 static inline u64 ZIP_QUEX_ERR_INT_W1S(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x3200ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_ERR_INT_W1S: %llu\n", param1);
 	return 0;
@@ -1179,7 +1179,7 @@ union zip_quex_gcfg {
 
 static inline u64 ZIP_QUEX_GCFG(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x1A00ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_GCFG: %llu\n", param1);
 	return 0;
@@ -1204,7 +1204,7 @@ union zip_quex_map {
 
 static inline u64 ZIP_QUEX_MAP(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x1400ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_MAP: %llu\n", param1);
 	return 0;
@@ -1236,7 +1236,7 @@ union zip_quex_sbuf_addr {
 
 static inline u64 ZIP_QUEX_SBUF_ADDR(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x1000ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_SBUF_ADDR: %llu\n", param1);
 	return 0;
@@ -1276,7 +1276,7 @@ union zip_quex_sbuf_ctl {
 
 static inline u64 ZIP_QUEX_SBUF_CTL(u64 param1)
 {
-	if (((param1 <= 7)))
+	if (param1 <= 7)
 		return 0x1200ull + (param1 & 7) * 0x8ull;
 	pr_err("ZIP_QUEX_SBUF_CTL: %llu\n", param1);
 	return 0;
diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index d95ec526587a..ff478d826d7d 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -22,11 +22,17 @@
 #include <linux/delay.h>
 #include <linux/hw_random.h>
 #include <linux/ccp.h>
+#include <linux/firmware.h>
 
 #include "sp-dev.h"
 #include "psp-dev.h"
 
+#define SEV_VERSION_GREATER_OR_EQUAL(_maj, _min)	\
+		((psp_master->api_major) >= _maj &&	\
+		 (psp_master->api_minor) >= _min)
+
 #define DEVICE_NAME	"sev"
+#define SEV_FW_FILE	"amd/sev.fw"
 
 static DEFINE_MUTEX(sev_cmd_mutex);
 static struct sev_misc_dev *misc_dev;
@@ -112,6 +118,8 @@ static int sev_cmd_buffer_len(int cmd)
 	case SEV_CMD_RECEIVE_UPDATE_DATA:	return sizeof(struct sev_data_receive_update_data);
 	case SEV_CMD_RECEIVE_UPDATE_VMSA:	return sizeof(struct sev_data_receive_update_vmsa);
 	case SEV_CMD_LAUNCH_UPDATE_SECRET:	return sizeof(struct sev_data_launch_secret);
+	case SEV_CMD_DOWNLOAD_FIRMWARE:		return sizeof(struct sev_data_download_firmware);
+	case SEV_CMD_GET_ID:			return sizeof(struct sev_data_get_id);
 	default:				return 0;
 	}
 
@@ -378,6 +386,79 @@ void *psp_copy_user_blob(u64 __user uaddr, u32 len)
 }
 EXPORT_SYMBOL_GPL(psp_copy_user_blob);
 
+static int sev_get_api_version(void)
+{
+	struct sev_user_data_status *status;
+	int error, ret;
+
+	status = &psp_master->status_cmd_buf;
+	ret = sev_platform_status(status, &error);
+	if (ret) {
+		dev_err(psp_master->dev,
+			"SEV: failed to get status. Error: %#x\n", error);
+		return 1;
+	}
+
+	psp_master->api_major = status->api_major;
+	psp_master->api_minor = status->api_minor;
+	psp_master->build = status->build;
+
+	return 0;
+}
+
+/* Don't fail if SEV FW couldn't be updated. Continue with existing SEV FW */
+static int sev_update_firmware(struct device *dev)
+{
+	struct sev_data_download_firmware *data;
+	const struct firmware *firmware;
+	int ret, error, order;
+	struct page *p;
+	u64 data_size;
+
+	ret = request_firmware(&firmware, SEV_FW_FILE, dev);
+	if (ret < 0)
+		return -1;
+
+	/*
+	 * SEV FW expects the physical address given to it to be 32
+	 * byte aligned. Memory allocated has structure placed at the
+	 * beginning followed by the firmware being passed to the SEV
+	 * FW. Allocate enough memory for data structure + alignment
+	 * padding + SEV FW.
+	 */
+	data_size = ALIGN(sizeof(struct sev_data_download_firmware), 32);
+
+	order = get_order(firmware->size + data_size);
+	p = alloc_pages(GFP_KERNEL, order);
+	if (!p) {
+		ret = -1;
+		goto fw_err;
+	}
+
+	/*
+	 * Copy firmware data to a kernel allocated contiguous
+	 * memory region.
+	 */
+	data = page_address(p);
+	memcpy(page_address(p) + data_size, firmware->data, firmware->size);
+
+	data->address = __psp_pa(page_address(p) + data_size);
+	data->len = firmware->size;
+
+	ret = sev_do_cmd(SEV_CMD_DOWNLOAD_FIRMWARE, data, &error);
+	if (ret)
+		dev_dbg(dev, "Failed to update SEV firmware: %#x\n", error);
+	else
+		dev_info(dev, "SEV firmware update successful\n");
+
+	__free_pages(p, order);
+
+fw_err:
+	release_firmware(firmware);
+
+	return ret;
+}
+
 static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp)
 {
 	struct sev_user_data_pek_cert_import input;
@@ -430,6 +511,46 @@ e_free:
 	return ret;
 }
 
+static int sev_ioctl_do_get_id(struct sev_issue_cmd *argp)
+{
+	struct sev_data_get_id *data;
+	u64 data_size, user_size;
+	void *id_blob, *mem;
+	int ret;
+
+	/* SEV GET_ID available from SEV API v0.16 and up */
+	if (!SEV_VERSION_GREATER_OR_EQUAL(0, 16))
+		return -ENOTSUPP;
+
+	/* SEV FW expects the buffer it fills with the ID to be
+	 * 8-byte aligned. Memory allocated should be enough to
+	 * hold data structure + alignment padding + memory
+	 * where SEV FW writes the ID.
+	 */
+	data_size = ALIGN(sizeof(struct sev_data_get_id), 8);
+	user_size = sizeof(struct sev_user_data_get_id);
+
+	mem = kzalloc(data_size + user_size, GFP_KERNEL);
+	if (!mem)
+		return -ENOMEM;
+
+	data = mem;
+	id_blob = mem + data_size;
+
+	data->address = __psp_pa(id_blob);
+	data->len = user_size;
+
+	ret = __sev_do_cmd_locked(SEV_CMD_GET_ID, data, &argp->error);
+	if (!ret) {
+		if (copy_to_user((void __user *)argp->data, id_blob, data->len))
+			ret = -EFAULT;
+	}
+
+	kfree(mem);
+
+	return ret;
+}
+
 static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp)
 {
 	struct sev_user_data_pdh_cert_export input;
@@ -567,6 +688,9 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg)
 	case SEV_PDH_CERT_EXPORT:
 		ret = sev_ioctl_do_pdh_export(&input);
 		break;
+	case SEV_GET_ID:
+		ret = sev_ioctl_do_get_id(&input);
+		break;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -750,7 +874,6 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user);
 
 void psp_pci_init(void)
 {
-	struct sev_user_data_status *status;
 	struct sp_device *sp;
 	int error, rc;
 
@@ -760,6 +883,13 @@ void psp_pci_init(void)
 
 	psp_master = sp->psp_data;
 
+	if (sev_get_api_version())
+		goto err;
+
+	if (SEV_VERSION_GREATER_OR_EQUAL(0, 15) &&
+	    sev_update_firmware(psp_master->dev) == 0)
+		sev_get_api_version();
+
 	/* Initialize the platform */
 	rc = sev_platform_init(&error);
 	if (rc) {
@@ -767,16 +897,9 @@ void psp_pci_init(void)
 		goto err;
 	}
 
-	/* Display SEV firmware version */
-	status = &psp_master->status_cmd_buf;
-	rc = sev_platform_status(status, &error);
-	if (rc) {
-		dev_err(sp->dev, "SEV: failed to get status error %#x\n", error);
-		goto err;
-	}
+	dev_info(sp->dev, "SEV API:%d.%d build:%d\n", psp_master->api_major,
+		 psp_master->api_minor, psp_master->build);
 
-	dev_info(sp->dev, "SEV API:%d.%d build:%d\n", status->api_major,
-		 status->api_minor, status->build);
 	return;
 
 err:
diff --git a/drivers/crypto/ccp/psp-dev.h b/drivers/crypto/ccp/psp-dev.h
index c81f0b11287a..c7e9098a233c 100644
--- a/drivers/crypto/ccp/psp-dev.h
+++ b/drivers/crypto/ccp/psp-dev.h
@@ -78,6 +78,10 @@ struct psp_device {
 	struct sev_misc_dev *sev_misc;
 	struct sev_user_data_status status_cmd_buf;
 	struct sev_data_init init_cmd_buf;
+
+	u8 api_major;
+	u8 api_minor;
+	u8 build;
 };
 
 #endif /* __PSP_DEV_H */
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index df98f7afe645..d2810c183b73 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -42,6 +42,7 @@ struct cc_cipher_ctx {
 	int cipher_mode;
 	int flow_mode;
 	unsigned int flags;
+	bool hw_key;
 	struct cc_user_key_info user;
 	struct cc_hw_key_info hw;
 	struct crypto_shash *shash_tfm;
@@ -49,6 +50,13 @@ struct cc_cipher_ctx {
 
 static void cc_cipher_complete(struct device *dev, void *cc_req, int err);
 
+static inline bool cc_is_hw_key(struct crypto_tfm *tfm)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+
+	return ctx_p->hw_key;
+}
+
 static int validate_keys_sizes(struct cc_cipher_ctx *ctx_p, u32 size)
 {
 	switch (ctx_p->flow_mode) {
@@ -211,7 +219,7 @@ struct tdes_keys {
 	u8	key3[DES_KEY_SIZE];
 };
 
-static enum cc_hw_crypto_key hw_key_to_cc_hw_key(int slot_num)
+static enum cc_hw_crypto_key cc_slot_to_hw_key(int slot_num)
 {
 	switch (slot_num) {
 	case 0:
@@ -226,69 +234,100 @@ static enum cc_hw_crypto_key hw_key_to_cc_hw_key(int slot_num)
 	return END_OF_KEYS;
 }
 
-static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key,
-			    unsigned int keylen)
+static int cc_cipher_sethkey(struct crypto_skcipher *sktfm, const u8 *key,
+			     unsigned int keylen)
 {
 	struct crypto_tfm *tfm = crypto_skcipher_tfm(sktfm);
 	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
 	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
-	u32 tmp[DES3_EDE_EXPKEY_WORDS];
-	struct cc_crypto_alg *cc_alg =
-			container_of(tfm->__crt_alg, struct cc_crypto_alg,
-				     skcipher_alg.base);
-	unsigned int max_key_buf_size = cc_alg->skcipher_alg.max_keysize;
+	struct cc_hkey_info hki;
 
-	dev_dbg(dev, "Setting key in context @%p for %s. keylen=%u\n",
+	dev_dbg(dev, "Setting HW key in context @%p for %s. keylen=%u\n",
 		ctx_p, crypto_tfm_alg_name(tfm), keylen);
 	dump_byte_array("key", (u8 *)key, keylen);
 
 	/* STAT_PHASE_0: Init and sanity checks */
 
+	/* This check the size of the hardware key token */
+	if (keylen != sizeof(hki)) {
+		dev_err(dev, "Unsupported HW key size %d.\n", keylen);
+		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	if (ctx_p->flow_mode != S_DIN_to_AES) {
+		dev_err(dev, "HW key not supported for non-AES flows\n");
+		return -EINVAL;
+	}
+
+	memcpy(&hki, key, keylen);
+
+	/* The real key len for crypto op is the size of the HW key
+	 * referenced by the HW key slot, not the hardware key token
+	 */
+	keylen = hki.keylen;
+
 	if (validate_keys_sizes(ctx_p, keylen)) {
 		dev_err(dev, "Unsupported key size %d.\n", keylen);
 		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
-	if (cc_is_hw_key(tfm)) {
-		/* setting HW key slots */
-		struct arm_hw_key_info *hki = (struct arm_hw_key_info *)key;
+	ctx_p->hw.key1_slot = cc_slot_to_hw_key(hki.hw_key1);
+	if (ctx_p->hw.key1_slot == END_OF_KEYS) {
+		dev_err(dev, "Unsupported hw key1 number (%d)\n", hki.hw_key1);
+		return -EINVAL;
+	}
 
-		if (ctx_p->flow_mode != S_DIN_to_AES) {
-			dev_err(dev, "HW key not supported for non-AES flows\n");
+	if (ctx_p->cipher_mode == DRV_CIPHER_XTS ||
+	    ctx_p->cipher_mode == DRV_CIPHER_ESSIV ||
+	    ctx_p->cipher_mode == DRV_CIPHER_BITLOCKER) {
+		if (hki.hw_key1 == hki.hw_key2) {
+			dev_err(dev, "Illegal hw key numbers (%d,%d)\n",
+				hki.hw_key1, hki.hw_key2);
 			return -EINVAL;
 		}
-
-		ctx_p->hw.key1_slot = hw_key_to_cc_hw_key(hki->hw_key1);
-		if (ctx_p->hw.key1_slot == END_OF_KEYS) {
-			dev_err(dev, "Unsupported hw key1 number (%d)\n",
-				hki->hw_key1);
+		ctx_p->hw.key2_slot = cc_slot_to_hw_key(hki.hw_key2);
+		if (ctx_p->hw.key2_slot == END_OF_KEYS) {
+			dev_err(dev, "Unsupported hw key2 number (%d)\n",
+				hki.hw_key2);
 			return -EINVAL;
 		}
+	}
 
-		if (ctx_p->cipher_mode == DRV_CIPHER_XTS ||
-		    ctx_p->cipher_mode == DRV_CIPHER_ESSIV ||
-		    ctx_p->cipher_mode == DRV_CIPHER_BITLOCKER) {
-			if (hki->hw_key1 == hki->hw_key2) {
-				dev_err(dev, "Illegal hw key numbers (%d,%d)\n",
-					hki->hw_key1, hki->hw_key2);
-				return -EINVAL;
-			}
-			ctx_p->hw.key2_slot =
-				hw_key_to_cc_hw_key(hki->hw_key2);
-			if (ctx_p->hw.key2_slot == END_OF_KEYS) {
-				dev_err(dev, "Unsupported hw key2 number (%d)\n",
-					hki->hw_key2);
-				return -EINVAL;
-			}
-		}
+	ctx_p->keylen = keylen;
+	ctx_p->hw_key = true;
+	dev_dbg(dev, "cc_is_hw_key ret 0");
+
+	return 0;
+}
+
+static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key,
+			    unsigned int keylen)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(sktfm);
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	u32 tmp[DES3_EDE_EXPKEY_WORDS];
+	struct cc_crypto_alg *cc_alg =
+			container_of(tfm->__crt_alg, struct cc_crypto_alg,
+				     skcipher_alg.base);
+	unsigned int max_key_buf_size = cc_alg->skcipher_alg.max_keysize;
+
+	dev_dbg(dev, "Setting key in context @%p for %s. keylen=%u\n",
+		ctx_p, crypto_tfm_alg_name(tfm), keylen);
+	dump_byte_array("key", (u8 *)key, keylen);
 
-		ctx_p->keylen = keylen;
-		dev_dbg(dev, "cc_is_hw_key ret 0");
+	/* STAT_PHASE_0: Init and sanity checks */
 
-		return 0;
+	if (validate_keys_sizes(ctx_p, keylen)) {
+		dev_err(dev, "Unsupported key size %d.\n", keylen);
+		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
 	}
 
+	ctx_p->hw_key = false;
+
 	/*
 	 * Verify DES weak keys
 	 * Note that we're dropping the expanded key since the
@@ -735,6 +774,241 @@ static int cc_cipher_decrypt(struct skcipher_request *req)
 /* Block cipher alg */
 static const struct cc_alg_template skcipher_algs[] = {
 	{
+		.name = "xts(paes)",
+		.driver_name = "xts-paes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_XTS,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "xts512(paes)",
+		.driver_name = "xts-paes-du512-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_XTS,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 512,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "xts4096(paes)",
+		.driver_name = "xts-paes-du4096-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_XTS,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 4096,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "essiv(paes)",
+		.driver_name = "essiv-paes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_ESSIV,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "essiv512(paes)",
+		.driver_name = "essiv-paes-du512-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_ESSIV,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 512,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "essiv4096(paes)",
+		.driver_name = "essiv-paes-du4096-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_ESSIV,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 4096,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "bitlocker(paes)",
+		.driver_name = "bitlocker-paes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_BITLOCKER,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "bitlocker512(paes)",
+		.driver_name = "bitlocker-paes-du512-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_BITLOCKER,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 512,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "bitlocker4096(paes)",
+		.driver_name = "bitlocker-paes-du4096-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize =  CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_BITLOCKER,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 4096,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "ecb(paes)",
+		.driver_name = "ecb-paes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = 0,
+			},
+		.cipher_mode = DRV_CIPHER_ECB,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "cbc(paes)",
+		.driver_name = "cbc-paes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "ofb(paes)",
+		.driver_name = "ofb-paes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_OFB,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "cts1(cbc(paes))",
+		.driver_name = "cts1-cbc-paes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_CBC_CTS,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "ctr(paes)",
+		.driver_name = "ctr-paes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_CTR,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
 		.name = "xts(aes)",
 		.driver_name = "xts-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
diff --git a/drivers/crypto/ccree/cc_cipher.h b/drivers/crypto/ccree/cc_cipher.h
index 2a2a6f46c515..68444cfa936b 100644
--- a/drivers/crypto/ccree/cc_cipher.h
+++ b/drivers/crypto/ccree/cc_cipher.h
@@ -13,18 +13,6 @@
 #include "cc_driver.h"
 #include "cc_buffer_mgr.h"
 
-/* Crypto cipher flags */
-#define CC_CRYPTO_CIPHER_KEY_KFDE0	BIT(0)
-#define CC_CRYPTO_CIPHER_KEY_KFDE1	BIT(1)
-#define CC_CRYPTO_CIPHER_KEY_KFDE2	BIT(2)
-#define CC_CRYPTO_CIPHER_KEY_KFDE3	BIT(3)
-#define CC_CRYPTO_CIPHER_DU_SIZE_512B	BIT(4)
-
-#define CC_CRYPTO_CIPHER_KEY_KFDE_MASK (CC_CRYPTO_CIPHER_KEY_KFDE0 | \
-					CC_CRYPTO_CIPHER_KEY_KFDE1 | \
-					CC_CRYPTO_CIPHER_KEY_KFDE2 | \
-					CC_CRYPTO_CIPHER_KEY_KFDE3)
-
 struct cipher_req_ctx {
 	struct async_gen_req_ctx gen_ctx;
 	enum cc_req_dma_buf_type dma_buf_type;
@@ -42,18 +30,12 @@ int cc_cipher_alloc(struct cc_drvdata *drvdata);
 
 int cc_cipher_free(struct cc_drvdata *drvdata);
 
-struct arm_hw_key_info {
-	int hw_key1;
-	int hw_key2;
-};
+struct cc_hkey_info {
+	u16 keylen;
+	u8 hw_key1;
+	u8 hw_key2;
+} __packed;
 
-/*
- * This is a stub function that will replaced when we
- * implement secure keys
- */
-static inline bool cc_is_hw_key(struct crypto_tfm *tfm)
-{
-	return false;
-}
+#define CC_HW_KEY_SIZE sizeof(struct cc_hkey_info)
 
 #endif /*__CC_CIPHER_H__*/
diff --git a/drivers/crypto/ccree/cc_debugfs.c b/drivers/crypto/ccree/cc_debugfs.c
index 08f8db489cf0..5ca184e42483 100644
--- a/drivers/crypto/ccree/cc_debugfs.c
+++ b/drivers/crypto/ccree/cc_debugfs.c
@@ -26,7 +26,8 @@ struct cc_debugfs_ctx {
 static struct dentry *cc_debugfs_dir;
 
 static struct debugfs_reg32 debug_regs[] = {
-	CC_DEBUG_REG(HOST_SIGNATURE),
+	{ .name = "SIGNATURE" }, /* Must be 0th */
+	{ .name = "VERSION" }, /* Must be 1st */
 	CC_DEBUG_REG(HOST_IRR),
 	CC_DEBUG_REG(HOST_POWER_DOWN_EN),
 	CC_DEBUG_REG(AXIM_MON_ERR),
@@ -34,7 +35,6 @@ static struct debugfs_reg32 debug_regs[] = {
 	CC_DEBUG_REG(HOST_IMR),
 	CC_DEBUG_REG(AXIM_CFG),
 	CC_DEBUG_REG(AXIM_CACHE_PARAMS),
-	CC_DEBUG_REG(HOST_VERSION),
 	CC_DEBUG_REG(GPR_HOST),
 	CC_DEBUG_REG(AXIM_MON_COMP),
 };
@@ -58,6 +58,9 @@ int cc_debugfs_init(struct cc_drvdata *drvdata)
 	struct debugfs_regset32 *regset;
 	struct dentry *file;
 
+	debug_regs[0].offset = drvdata->sig_offset;
+	debug_regs[1].offset = drvdata->ver_offset;
+
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c
index 89ce013ae093..bd974fef05e4 100644
--- a/drivers/crypto/ccree/cc_driver.c
+++ b/drivers/crypto/ccree/cc_driver.c
@@ -168,14 +168,14 @@ int init_cc_regs(struct cc_drvdata *drvdata, bool is_probe)
 	val = cc_ioread(drvdata, CC_REG(AXIM_CACHE_PARAMS));
 
 	if (is_probe)
-		dev_info(dev, "Cache params previous: 0x%08X\n", val);
+		dev_dbg(dev, "Cache params previous: 0x%08X\n", val);
 
 	cc_iowrite(drvdata, CC_REG(AXIM_CACHE_PARAMS), cache_params);
 	val = cc_ioread(drvdata, CC_REG(AXIM_CACHE_PARAMS));
 
 	if (is_probe)
-		dev_info(dev, "Cache params current: 0x%08X (expect: 0x%08X)\n",
-			 val, cache_params);
+		dev_dbg(dev, "Cache params current: 0x%08X (expect: 0x%08X)\n",
+			val, cache_params);
 
 	return 0;
 }
@@ -190,6 +190,7 @@ static int init_cc_resources(struct platform_device *plat_dev)
 	u64 dma_mask;
 	const struct cc_hw_data *hw_rev;
 	const struct of_device_id *dev_id;
+	struct clk *clk;
 	int rc = 0;
 
 	new_drvdata = devm_kzalloc(dev, sizeof(*new_drvdata), GFP_KERNEL);
@@ -207,15 +208,36 @@ static int init_cc_resources(struct platform_device *plat_dev)
 	if (hw_rev->rev >= CC_HW_REV_712) {
 		new_drvdata->hash_len_sz = HASH_LEN_SIZE_712;
 		new_drvdata->axim_mon_offset = CC_REG(AXIM_MON_COMP);
+		new_drvdata->sig_offset = CC_REG(HOST_SIGNATURE_712);
+		new_drvdata->ver_offset = CC_REG(HOST_VERSION_712);
 	} else {
 		new_drvdata->hash_len_sz = HASH_LEN_SIZE_630;
 		new_drvdata->axim_mon_offset = CC_REG(AXIM_MON_COMP8);
+		new_drvdata->sig_offset = CC_REG(HOST_SIGNATURE_630);
+		new_drvdata->ver_offset = CC_REG(HOST_VERSION_630);
 	}
 
 	platform_set_drvdata(plat_dev, new_drvdata);
 	new_drvdata->plat_dev = plat_dev;
 
-	new_drvdata->clk = of_clk_get(np, 0);
+	clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(clk))
+		switch (PTR_ERR(clk)) {
+		/* Clock is optional so this might be fine */
+		case -ENOENT:
+			break;
+
+		/* Clock not available, let's try again soon */
+		case -EPROBE_DEFER:
+			return -EPROBE_DEFER;
+
+		default:
+			dev_err(dev, "Error getting clock: %ld\n",
+				PTR_ERR(clk));
+			return PTR_ERR(clk);
+		}
+	new_drvdata->clk = clk;
+
 	new_drvdata->coherent = of_dma_is_coherent(np);
 
 	/* Get device resources */
@@ -265,7 +287,7 @@ static int init_cc_resources(struct platform_device *plat_dev)
 	}
 
 	if (rc) {
-		dev_err(dev, "Failed in dma_set_mask, mask=%pad\n", &dma_mask);
+		dev_err(dev, "Failed in dma_set_mask, mask=%llx\n", dma_mask);
 		return rc;
 	}
 
@@ -276,7 +298,7 @@ static int init_cc_resources(struct platform_device *plat_dev)
 	}
 
 	/* Verify correct mapping */
-	signature_val = cc_ioread(new_drvdata, CC_REG(HOST_SIGNATURE));
+	signature_val = cc_ioread(new_drvdata, new_drvdata->sig_offset);
 	if (signature_val != hw_rev->sig) {
 		dev_err(dev, "Invalid CC signature: SIGNATURE=0x%08X != expected=0x%08X\n",
 			signature_val, hw_rev->sig);
@@ -287,7 +309,7 @@ static int init_cc_resources(struct platform_device *plat_dev)
 
 	/* Display HW versions */
 	dev_info(dev, "ARM CryptoCell %s Driver: HW version 0x%08X, Driver version %s\n",
-		 hw_rev->name, cc_ioread(new_drvdata, CC_REG(HOST_VERSION)),
+		 hw_rev->name, cc_ioread(new_drvdata, new_drvdata->ver_offset),
 		 DRV_MODULE_VERSION);
 
 	rc = init_cc_regs(new_drvdata, true);
diff --git a/drivers/crypto/ccree/cc_driver.h b/drivers/crypto/ccree/cc_driver.h
index 2048fdeb9579..95f82b2d1e70 100644
--- a/drivers/crypto/ccree/cc_driver.h
+++ b/drivers/crypto/ccree/cc_driver.h
@@ -129,6 +129,8 @@ struct cc_drvdata {
 	enum cc_hw_rev hw_rev;
 	u32 hash_len_sz;
 	u32 axim_mon_offset;
+	u32 sig_offset;
+	u32 ver_offset;
 };
 
 struct cc_crypto_alg {
diff --git a/drivers/crypto/ccree/cc_host_regs.h b/drivers/crypto/ccree/cc_host_regs.h
index f51001898ca1..616b2e1c41ba 100644
--- a/drivers/crypto/ccree/cc_host_regs.h
+++ b/drivers/crypto/ccree/cc_host_regs.h
@@ -45,7 +45,8 @@
 #define CC_HOST_ICR_DSCRPTR_WATERMARK_QUEUE0_CLEAR_BIT_SIZE	0x1UL
 #define CC_HOST_ICR_AXIM_COMP_INT_CLEAR_BIT_SHIFT	0x17UL
 #define CC_HOST_ICR_AXIM_COMP_INT_CLEAR_BIT_SIZE	0x1UL
-#define CC_HOST_SIGNATURE_REG_OFFSET	0xA24UL
+#define CC_HOST_SIGNATURE_712_REG_OFFSET	0xA24UL
+#define CC_HOST_SIGNATURE_630_REG_OFFSET	0xAC8UL
 #define CC_HOST_SIGNATURE_VALUE_BIT_SHIFT	0x0UL
 #define CC_HOST_SIGNATURE_VALUE_BIT_SIZE	0x20UL
 #define CC_HOST_BOOT_REG_OFFSET	0xA28UL
@@ -105,7 +106,8 @@
 #define CC_HOST_BOOT_ONLY_ENCRYPT_LOCAL_BIT_SIZE	0x1UL
 #define CC_HOST_BOOT_AES_EXISTS_LOCAL_BIT_SHIFT	0x1EUL
 #define CC_HOST_BOOT_AES_EXISTS_LOCAL_BIT_SIZE	0x1UL
-#define CC_HOST_VERSION_REG_OFFSET	0xA40UL
+#define CC_HOST_VERSION_712_REG_OFFSET	0xA40UL
+#define CC_HOST_VERSION_630_REG_OFFSET	0xAD8UL
 #define CC_HOST_VERSION_VALUE_BIT_SHIFT	0x0UL
 #define CC_HOST_VERSION_VALUE_BIT_SIZE	0x20UL
 #define CC_HOST_KFDE0_VALID_REG_OFFSET	0xA60UL
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 59fe6631e73e..b916c4eb608c 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -203,13 +203,8 @@ static inline void chcr_handle_aead_resp(struct aead_request *req,
 					 int err)
 {
 	struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct uld_ctx *u_ctx = ULD_CTX(a_ctx(tfm));
 
-	chcr_aead_dma_unmap(&u_ctx->lldi.pdev->dev, req, reqctx->op);
-	if (reqctx->b0_dma)
-		dma_unmap_single(&u_ctx->lldi.pdev->dev, reqctx->b0_dma,
-				 reqctx->b0_len, DMA_BIDIRECTIONAL);
+	chcr_aead_common_exit(req);
 	if (reqctx->verify == VERIFY_SW) {
 		chcr_verify_tag(req, input, &err);
 		reqctx->verify = VERIFY_HW;
@@ -638,7 +633,6 @@ static int chcr_sg_ent_in_wr(struct scatterlist *src,
 		src = sg_next(src);
 		srcskip = 0;
 	}
-
 	if (sg_dma_len(dst) == dstskip) {
 		dst = sg_next(dst);
 		dstskip = 0;
@@ -688,6 +682,7 @@ static int chcr_cipher_fallback(struct crypto_skcipher *cipher,
 	int err;
 
 	SKCIPHER_REQUEST_ON_STACK(subreq, cipher);
+
 	skcipher_request_set_tfm(subreq, cipher);
 	skcipher_request_set_callback(subreq, flags, NULL, NULL);
 	skcipher_request_set_crypt(subreq, src, dst,
@@ -760,13 +755,13 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
 
 	nents = sg_nents_xlen(reqctx->dstsg,  wrparam->bytes, CHCR_DST_SG_SIZE,
 			      reqctx->dst_ofst);
-	dst_size = get_space_for_phys_dsgl(nents + 1);
+	dst_size = get_space_for_phys_dsgl(nents);
 	kctx_len = roundup(ablkctx->enckey_len, 16);
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
 	nents = sg_nents_xlen(reqctx->srcsg, wrparam->bytes,
 				  CHCR_SRC_SG_SIZE, reqctx->src_ofst);
-	temp = reqctx->imm ? roundup(IV + wrparam->req->nbytes, 16) :
-				     (sgl_len(nents + MIN_CIPHER_SG) * 8);
+	temp = reqctx->imm ? roundup(wrparam->bytes, 16) :
+				     (sgl_len(nents) * 8);
 	transhdr_len += temp;
 	transhdr_len = roundup(transhdr_len, 16);
 	skb = alloc_skb(SGE_MAX_WR_LEN, flags);
@@ -788,7 +783,7 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
 							 ablkctx->ciph_mode,
 							 0, 0, IV >> 1);
 	chcr_req->sec_cpl.ivgen_hdrlen = FILL_SEC_CPL_IVGEN_HDRLEN(0, 0, 0,
-							  0, 0, dst_size);
+							  0, 1, dst_size);
 
 	chcr_req->key_ctx.ctx_hdr = ablkctx->key_ctx_hdr;
 	if ((reqctx->op == CHCR_DECRYPT_OP) &&
@@ -818,8 +813,8 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
 	chcr_add_cipher_dst_ent(wrparam->req, phys_cpl, wrparam, wrparam->qid);
 
 	atomic_inc(&adap->chcr_stats.cipher_rqst);
-	temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size + kctx_len
-		+(reqctx->imm ? (IV + wrparam->bytes) : 0);
+	temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size + kctx_len + IV
+		+ (reqctx->imm ? (wrparam->bytes) : 0);
 	create_wreq(c_ctx(tfm), chcr_req, &(wrparam->req->base), reqctx->imm, 0,
 		    transhdr_len, temp,
 			ablkctx->ciph_mode == CHCR_SCMD_CIPHER_MODE_AES_CBC);
@@ -1022,7 +1017,7 @@ static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv,
 	ret = crypto_cipher_setkey(cipher, key, keylen);
 	if (ret)
 		goto out;
-	/*H/W sends the encrypted IV in dsgl when AADIVDROP bit is 0*/
+	crypto_cipher_encrypt_one(cipher, iv, iv);
 	for (i = 0; i < round8; i++)
 		gf128mul_x8_ble((le128 *)iv, (le128 *)iv);
 
@@ -1113,16 +1108,8 @@ static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
 		goto complete;
 	}
 
-	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-					    c_ctx(tfm)->tx_qidx))) {
-		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) {
-			err = -EBUSY;
-			goto unmap;
-		}
-
-	}
 	if (!reqctx->imm) {
-		bytes = chcr_sg_ent_in_wr(reqctx->srcsg, reqctx->dstsg, 1,
+		bytes = chcr_sg_ent_in_wr(reqctx->srcsg, reqctx->dstsg, 0,
 					  CIP_SPACE_LEFT(ablkctx->enckey_len),
 					  reqctx->src_ofst, reqctx->dst_ofst);
 		if ((bytes + reqctx->processed) >= req->nbytes)
@@ -1133,11 +1120,7 @@ static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
 		/*CTR mode counter overfloa*/
 		bytes  = req->nbytes - reqctx->processed;
 	}
-	dma_sync_single_for_cpu(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev,
-				reqctx->iv_dma, IV, DMA_BIDIRECTIONAL);
 	err = chcr_update_cipher_iv(req, fw6_pld, reqctx->iv);
-	dma_sync_single_for_device(&ULD_CTX(c_ctx(tfm))->lldi.pdev->dev,
-				   reqctx->iv_dma, IV, DMA_BIDIRECTIONAL);
 	if (err)
 		goto unmap;
 
@@ -1212,7 +1195,6 @@ static int process_cipher(struct ablkcipher_request *req,
 
 		dnents = sg_nents_xlen(req->dst, req->nbytes,
 				       CHCR_DST_SG_SIZE, 0);
-		dnents += 1; // IV
 		phys_dsgl = get_space_for_phys_dsgl(dnents);
 		kctx_len = roundup(ablkctx->enckey_len, 16);
 		transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, phys_dsgl);
@@ -1225,8 +1207,7 @@ static int process_cipher(struct ablkcipher_request *req,
 	}
 
 	if (!reqctx->imm) {
-		bytes = chcr_sg_ent_in_wr(req->src, req->dst,
-					  MIN_CIPHER_SG,
+		bytes = chcr_sg_ent_in_wr(req->src, req->dst, 0,
 					  CIP_SPACE_LEFT(ablkctx->enckey_len),
 					  0, 0);
 		if ((bytes + reqctx->processed) >= req->nbytes)
@@ -1293,13 +1274,14 @@ static int chcr_aes_encrypt(struct ablkcipher_request *req)
 {
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct sk_buff *skb = NULL;
-	int err;
+	int err, isfull = 0;
 	struct uld_ctx *u_ctx = ULD_CTX(c_ctx(tfm));
 
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
 					    c_ctx(tfm)->tx_qidx))) {
+		isfull = 1;
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
-			return -EBUSY;
+			return -ENOSPC;
 	}
 
 	err = process_cipher(req, u_ctx->lldi.rxq_ids[c_ctx(tfm)->rx_qidx],
@@ -1309,7 +1291,7 @@ static int chcr_aes_encrypt(struct ablkcipher_request *req)
 	skb->dev = u_ctx->lldi.ports[0];
 	set_wr_txq(skb, CPL_PRIORITY_DATA, c_ctx(tfm)->tx_qidx);
 	chcr_send_wr(skb);
-	return -EINPROGRESS;
+	return isfull ? -EBUSY : -EINPROGRESS;
 }
 
 static int chcr_aes_decrypt(struct ablkcipher_request *req)
@@ -1317,12 +1299,13 @@ static int chcr_aes_decrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct uld_ctx *u_ctx = ULD_CTX(c_ctx(tfm));
 	struct sk_buff *skb = NULL;
-	int err;
+	int err, isfull = 0;
 
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
 					    c_ctx(tfm)->tx_qidx))) {
+		isfull = 1;
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
-			return -EBUSY;
+			return -ENOSPC;
 	}
 
 	 err = process_cipher(req, u_ctx->lldi.rxq_ids[c_ctx(tfm)->rx_qidx],
@@ -1332,7 +1315,7 @@ static int chcr_aes_decrypt(struct ablkcipher_request *req)
 	skb->dev = u_ctx->lldi.ports[0];
 	set_wr_txq(skb, CPL_PRIORITY_DATA, c_ctx(tfm)->tx_qidx);
 	chcr_send_wr(skb);
-	return -EINPROGRESS;
+	return isfull ? -EBUSY : -EINPROGRESS;
 }
 
 static int chcr_device_init(struct chcr_context *ctx)
@@ -1574,14 +1557,15 @@ static int chcr_ahash_update(struct ahash_request *req)
 	u8 remainder = 0, bs;
 	unsigned int nbytes = req->nbytes;
 	struct hash_wr_param params;
-	int error;
+	int error, isfull = 0;
 
 	bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm));
 	u_ctx = ULD_CTX(h_ctx(rtfm));
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
 					    h_ctx(rtfm)->tx_qidx))) {
+		isfull = 1;
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
-			return -EBUSY;
+			return -ENOSPC;
 	}
 
 	if (nbytes + req_ctx->reqlen >= bs) {
@@ -1633,7 +1617,7 @@ static int chcr_ahash_update(struct ahash_request *req)
 	set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx);
 	chcr_send_wr(skb);
 
-	return -EINPROGRESS;
+	return isfull ? -EBUSY : -EINPROGRESS;
 unmap:
 	chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req);
 	return error;
@@ -1710,15 +1694,16 @@ static int chcr_ahash_finup(struct ahash_request *req)
 	struct sk_buff *skb;
 	struct hash_wr_param params;
 	u8  bs;
-	int error;
+	int error, isfull = 0;
 
 	bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm));
 	u_ctx = ULD_CTX(h_ctx(rtfm));
 
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
 					    h_ctx(rtfm)->tx_qidx))) {
+		isfull = 1;
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
-			return -EBUSY;
+			return -ENOSPC;
 	}
 	chcr_init_hctx_per_wr(req_ctx);
 	error = chcr_hash_dma_map(&u_ctx->lldi.pdev->dev, req);
@@ -1777,7 +1762,7 @@ static int chcr_ahash_finup(struct ahash_request *req)
 	set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx);
 	chcr_send_wr(skb);
 
-	return -EINPROGRESS;
+	return isfull ? -EBUSY : -EINPROGRESS;
 unmap:
 	chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req);
 	return error;
@@ -1791,7 +1776,7 @@ static int chcr_ahash_digest(struct ahash_request *req)
 	struct sk_buff *skb;
 	struct hash_wr_param params;
 	u8  bs;
-	int error;
+	int error, isfull = 0;
 
 	rtfm->init(req);
 	bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm));
@@ -1799,8 +1784,9 @@ static int chcr_ahash_digest(struct ahash_request *req)
 	u_ctx = ULD_CTX(h_ctx(rtfm));
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
 					    h_ctx(rtfm)->tx_qidx))) {
+		isfull = 1;
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
-			return -EBUSY;
+			return -ENOSPC;
 	}
 
 	chcr_init_hctx_per_wr(req_ctx);
@@ -1856,7 +1842,7 @@ static int chcr_ahash_digest(struct ahash_request *req)
 	skb->dev = u_ctx->lldi.ports[0];
 	set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx);
 	chcr_send_wr(skb);
-	return -EINPROGRESS;
+	return isfull ? -EBUSY : -EINPROGRESS;
 unmap:
 	chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req);
 	return error;
@@ -1875,11 +1861,6 @@ static int chcr_ahash_continue(struct ahash_request *req)
 
 	bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm));
 	u_ctx = ULD_CTX(h_ctx(rtfm));
-	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
-					    h_ctx(rtfm)->tx_qidx))) {
-		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
-			return -EBUSY;
-	}
 	get_alg_config(&params.alg_prm, crypto_ahash_digestsize(rtfm));
 	params.kctx_len = roundup(params.alg_prm.result_size, 16);
 	if (is_hmac(crypto_ahash_tfm(rtfm))) {
@@ -2192,22 +2173,35 @@ static void chcr_hmac_cra_exit(struct crypto_tfm *tfm)
 	}
 }
 
-static int chcr_aead_common_init(struct aead_request *req,
-				 unsigned short op_type)
+inline void chcr_aead_common_exit(struct aead_request *req)
+{
+	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct uld_ctx *u_ctx = ULD_CTX(a_ctx(tfm));
+
+	chcr_aead_dma_unmap(&u_ctx->lldi.pdev->dev, req, reqctx->op);
+}
+
+static int chcr_aead_common_init(struct aead_request *req)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm));
 	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
-	int error = -EINVAL;
 	unsigned int authsize = crypto_aead_authsize(tfm);
+	int error = -EINVAL;
 
 	/* validate key size */
 	if (aeadctx->enckey_len == 0)
 		goto err;
-	if (op_type && req->cryptlen < authsize)
+	if (reqctx->op && req->cryptlen < authsize)
 		goto err;
+	if (reqctx->b0_len)
+		reqctx->scratch_pad = reqctx->iv + IV;
+	else
+		reqctx->scratch_pad = NULL;
+
 	error = chcr_aead_dma_map(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev, req,
-				  op_type);
+				  reqctx->op);
 	if (error) {
 		error = -ENOMEM;
 		goto err;
@@ -2244,7 +2238,7 @@ static int chcr_aead_fallback(struct aead_request *req, unsigned short op_type)
 	aead_request_set_tfm(subreq, aeadctx->sw_cipher);
 	aead_request_set_callback(subreq, req->base.flags,
 				  req->base.complete, req->base.data);
-	 aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
+	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
 				 req->iv);
 	 aead_request_set_ad(subreq, req->assoclen);
 	return op_type ? crypto_aead_decrypt(subreq) :
@@ -2253,8 +2247,7 @@ static int chcr_aead_fallback(struct aead_request *req, unsigned short op_type)
 
 static struct sk_buff *create_authenc_wr(struct aead_request *req,
 					 unsigned short qid,
-					 int size,
-					 unsigned short op_type)
+					 int size)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm));
@@ -2278,18 +2271,20 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	if (req->cryptlen == 0)
 		return NULL;
 
-	reqctx->b0_dma = 0;
+	reqctx->b0_len = 0;
+	error = chcr_aead_common_init(req);
+	if (error)
+		return ERR_PTR(error);
+
 	if (subtype == CRYPTO_ALG_SUB_TYPE_CBC_NULL ||
-	subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) {
+		subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) {
 		null = 1;
 		assoclen = 0;
+		reqctx->aad_nents = 0;
 	}
-	error = chcr_aead_common_init(req, op_type);
-	if (error)
-		return ERR_PTR(error);
 	dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
 	dnents += sg_nents_xlen(req->dst, req->cryptlen +
-		(op_type ? -authsize : authsize), CHCR_DST_SG_SIZE,
+		(reqctx->op ? -authsize : authsize), CHCR_DST_SG_SIZE,
 		req->assoclen);
 	dnents += MIN_AUTH_SG; // For IV
 
@@ -2306,11 +2301,10 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	transhdr_len = roundup(transhdr_len, 16);
 
 	if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE,
-				    transhdr_len, op_type)) {
+				    transhdr_len, reqctx->op)) {
 		atomic_inc(&adap->chcr_stats.fallback);
-		chcr_aead_dma_unmap(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev, req,
-				    op_type);
-		return ERR_PTR(chcr_aead_fallback(req, op_type));
+		chcr_aead_common_exit(req);
+		return ERR_PTR(chcr_aead_fallback(req, reqctx->op));
 	}
 	skb = alloc_skb(SGE_MAX_WR_LEN, flags);
 	if (!skb) {
@@ -2320,7 +2314,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 
 	chcr_req = __skb_put_zero(skb, transhdr_len);
 
-	temp  = (op_type == CHCR_ENCRYPT_OP) ? 0 : authsize;
+	temp  = (reqctx->op == CHCR_ENCRYPT_OP) ? 0 : authsize;
 
 	/*
 	 * Input order	is AAD,IV and Payload. where IV should be included as
@@ -2344,8 +2338,8 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 		temp = CHCR_SCMD_CIPHER_MODE_AES_CTR;
 	else
 		temp = CHCR_SCMD_CIPHER_MODE_AES_CBC;
-	chcr_req->sec_cpl.seqno_numivs = FILL_SEC_CPL_SCMD0_SEQNO(op_type,
-					(op_type == CHCR_ENCRYPT_OP) ? 1 : 0,
+	chcr_req->sec_cpl.seqno_numivs = FILL_SEC_CPL_SCMD0_SEQNO(reqctx->op,
+					(reqctx->op == CHCR_ENCRYPT_OP) ? 1 : 0,
 					temp,
 					actx->auth_mode, aeadctx->hmac_ctrl,
 					IV >> 1);
@@ -2353,7 +2347,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 					 0, 0, dst_size);
 
 	chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr;
-	if (op_type == CHCR_ENCRYPT_OP ||
+	if (reqctx->op == CHCR_ENCRYPT_OP ||
 		subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA ||
 		subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL)
 		memcpy(chcr_req->key_ctx.key, aeadctx->key,
@@ -2376,20 +2370,18 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	}
 	phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len);
 	ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size);
-	chcr_add_aead_dst_ent(req, phys_cpl, assoclen, op_type, qid);
-	chcr_add_aead_src_ent(req, ulptx, assoclen, op_type);
+	chcr_add_aead_dst_ent(req, phys_cpl, assoclen, qid);
+	chcr_add_aead_src_ent(req, ulptx, assoclen);
 	atomic_inc(&adap->chcr_stats.cipher_rqst);
 	temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size +
 		kctx_len + (reqctx->imm ? (assoclen + IV + req->cryptlen) : 0);
 	create_wreq(a_ctx(tfm), chcr_req, &req->base, reqctx->imm, size,
 		   transhdr_len, temp, 0);
 	reqctx->skb = skb;
-	reqctx->op = op_type;
 
 	return skb;
 err:
-	chcr_aead_dma_unmap(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev, req,
-			    op_type);
+	chcr_aead_common_exit(req);
 
 	return ERR_PTR(error);
 }
@@ -2408,11 +2400,14 @@ int chcr_aead_dma_map(struct device *dev,
 				-authsize : authsize);
 	if (!req->cryptlen || !dst_size)
 		return 0;
-	reqctx->iv_dma = dma_map_single(dev, reqctx->iv, IV,
+	reqctx->iv_dma = dma_map_single(dev, reqctx->iv, (IV + reqctx->b0_len),
 					DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, reqctx->iv_dma))
 		return -ENOMEM;
-
+	if (reqctx->b0_len)
+		reqctx->b0_dma = reqctx->iv_dma + IV;
+	else
+		reqctx->b0_dma = 0;
 	if (req->src == req->dst) {
 		error = dma_map_sg(dev, req->src, sg_nents(req->src),
 				   DMA_BIDIRECTIONAL);
@@ -2452,7 +2447,7 @@ void chcr_aead_dma_unmap(struct device *dev,
 	if (!req->cryptlen || !dst_size)
 		return;
 
-	dma_unmap_single(dev, reqctx->iv_dma, IV,
+	dma_unmap_single(dev, reqctx->iv_dma, (IV + reqctx->b0_len),
 					DMA_BIDIRECTIONAL);
 	if (req->src == req->dst) {
 		dma_unmap_sg(dev, req->src, sg_nents(req->src),
@@ -2467,8 +2462,7 @@ void chcr_aead_dma_unmap(struct device *dev,
 
 void chcr_add_aead_src_ent(struct aead_request *req,
 			   struct ulptx_sgl *ulptx,
-			   unsigned int assoclen,
-			   unsigned short op_type)
+			   unsigned int assoclen)
 {
 	struct ulptx_walk ulp_walk;
 	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
@@ -2476,7 +2470,7 @@ void chcr_add_aead_src_ent(struct aead_request *req,
 	if (reqctx->imm) {
 		u8 *buf = (u8 *)ulptx;
 
-		if (reqctx->b0_dma) {
+		if (reqctx->b0_len) {
 			memcpy(buf, reqctx->scratch_pad, reqctx->b0_len);
 			buf += reqctx->b0_len;
 		}
@@ -2489,7 +2483,7 @@ void chcr_add_aead_src_ent(struct aead_request *req,
 				   buf, req->cryptlen, req->assoclen);
 	} else {
 		ulptx_walk_init(&ulp_walk, ulptx);
-		if (reqctx->b0_dma)
+		if (reqctx->b0_len)
 			ulptx_walk_add_page(&ulp_walk, reqctx->b0_len,
 					    &reqctx->b0_dma);
 		ulptx_walk_add_sg(&ulp_walk, req->src, assoclen, 0);
@@ -2503,7 +2497,6 @@ void chcr_add_aead_src_ent(struct aead_request *req,
 void chcr_add_aead_dst_ent(struct aead_request *req,
 			   struct cpl_rx_phys_dsgl *phys_cpl,
 			   unsigned int assoclen,
-			   unsigned short op_type,
 			   unsigned short qid)
 {
 	struct chcr_aead_reqctx  *reqctx = aead_request_ctx(req);
@@ -2513,32 +2506,30 @@ void chcr_add_aead_dst_ent(struct aead_request *req,
 	u32 temp;
 
 	dsgl_walk_init(&dsgl_walk, phys_cpl);
-	if (reqctx->b0_dma)
+	if (reqctx->b0_len)
 		dsgl_walk_add_page(&dsgl_walk, reqctx->b0_len, &reqctx->b0_dma);
 	dsgl_walk_add_sg(&dsgl_walk, req->dst, assoclen, 0);
 	dsgl_walk_add_page(&dsgl_walk, IV, &reqctx->iv_dma);
-	temp = req->cryptlen + (op_type ? -authsize : authsize);
+	temp = req->cryptlen + (reqctx->op ? -authsize : authsize);
 	dsgl_walk_add_sg(&dsgl_walk, req->dst, temp, req->assoclen);
 	dsgl_walk_end(&dsgl_walk, qid);
 }
 
 void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
-			     struct ulptx_sgl *ulptx,
+			     void *ulptx,
 			     struct  cipher_wr_param *wrparam)
 {
 	struct ulptx_walk ulp_walk;
 	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
+	u8 *buf = ulptx;
 
+	memcpy(buf, reqctx->iv, IV);
+	buf += IV;
 	if (reqctx->imm) {
-		u8 *buf = (u8 *)ulptx;
-
-		memcpy(buf, reqctx->iv, IV);
-		buf += IV;
 		sg_pcopy_to_buffer(req->src, sg_nents(req->src),
 				   buf, wrparam->bytes, reqctx->processed);
 	} else {
-		ulptx_walk_init(&ulp_walk, ulptx);
-		ulptx_walk_add_page(&ulp_walk, IV, &reqctx->iv_dma);
+		ulptx_walk_init(&ulp_walk, (struct ulptx_sgl *)buf);
 		ulptx_walk_add_sg(&ulp_walk, reqctx->srcsg, wrparam->bytes,
 				  reqctx->src_ofst);
 		reqctx->srcsg = ulp_walk.last_sg;
@@ -2556,7 +2547,6 @@ void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
 	struct dsgl_walk dsgl_walk;
 
 	dsgl_walk_init(&dsgl_walk, phys_cpl);
-	dsgl_walk_add_page(&dsgl_walk, IV, &reqctx->iv_dma);
 	dsgl_walk_add_sg(&dsgl_walk, reqctx->dstsg, wrparam->bytes,
 			 reqctx->dst_ofst);
 	reqctx->dstsg = dsgl_walk.last_sg;
@@ -2630,12 +2620,6 @@ int chcr_cipher_dma_map(struct device *dev,
 			struct ablkcipher_request *req)
 {
 	int error;
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
-
-	reqctx->iv_dma = dma_map_single(dev, reqctx->iv, IV,
-					DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, reqctx->iv_dma))
-		return -ENOMEM;
 
 	if (req->src == req->dst) {
 		error = dma_map_sg(dev, req->src, sg_nents(req->src),
@@ -2658,17 +2642,12 @@ int chcr_cipher_dma_map(struct device *dev,
 
 	return 0;
 err:
-	dma_unmap_single(dev, reqctx->iv_dma, IV, DMA_BIDIRECTIONAL);
 	return -ENOMEM;
 }
 
 void chcr_cipher_dma_unmap(struct device *dev,
 			   struct ablkcipher_request *req)
 {
-	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
-
-	dma_unmap_single(dev, reqctx->iv_dma, IV,
-					DMA_BIDIRECTIONAL);
 	if (req->src == req->dst) {
 		dma_unmap_sg(dev, req->src, sg_nents(req->src),
 				   DMA_BIDIRECTIONAL);
@@ -2738,7 +2717,8 @@ static inline int crypto_ccm_check_iv(const u8 *iv)
 static int ccm_format_packet(struct aead_request *req,
 			     struct chcr_aead_ctx *aeadctx,
 			     unsigned int sub_type,
-			     unsigned short op_type)
+			     unsigned short op_type,
+			     unsigned int assoclen)
 {
 	struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
 	int rc = 0;
@@ -2748,13 +2728,13 @@ static int ccm_format_packet(struct aead_request *req,
 		memcpy(reqctx->iv + 1, &aeadctx->salt[0], 3);
 		memcpy(reqctx->iv + 4, req->iv, 8);
 		memset(reqctx->iv + 12, 0, 4);
-		*((unsigned short *)(reqctx->scratch_pad + 16)) =
-			htons(req->assoclen - 8);
 	} else {
 		memcpy(reqctx->iv, req->iv, 16);
-		*((unsigned short *)(reqctx->scratch_pad + 16)) =
-			htons(req->assoclen);
 	}
+	if (assoclen)
+		*((unsigned short *)(reqctx->scratch_pad + 16)) =
+				htons(assoclen);
+
 	generate_b0(req, aeadctx, op_type);
 	/* zero the ctr value */
 	memset(reqctx->iv + 15 - reqctx->iv[0], 0, reqctx->iv[0] + 1);
@@ -2836,8 +2816,7 @@ static int aead_ccm_validate_input(unsigned short op_type,
 
 static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 					  unsigned short qid,
-					  int size,
-					  unsigned short op_type)
+					  int size)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm));
@@ -2855,22 +2834,20 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 		GFP_ATOMIC;
 	struct adapter *adap = padap(a_ctx(tfm)->dev);
 
-	reqctx->b0_dma = 0;
 	sub_type = get_aead_subtype(tfm);
 	if (sub_type == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309)
 		assoclen -= 8;
-	error = chcr_aead_common_init(req, op_type);
+	reqctx->b0_len = CCM_B0_SIZE + (assoclen ? CCM_AAD_FIELD_SIZE : 0);
+	error = chcr_aead_common_init(req);
 	if (error)
 		return ERR_PTR(error);
 
-
-	reqctx->b0_len = CCM_B0_SIZE + (assoclen ? CCM_AAD_FIELD_SIZE : 0);
-	error = aead_ccm_validate_input(op_type, req, aeadctx, sub_type);
+	error = aead_ccm_validate_input(reqctx->op, req, aeadctx, sub_type);
 	if (error)
 		goto err;
 	dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
 	dnents += sg_nents_xlen(req->dst, req->cryptlen
-			+ (op_type ? -authsize : authsize),
+			+ (reqctx->op ? -authsize : authsize),
 			CHCR_DST_SG_SIZE, req->assoclen);
 	dnents += MIN_CCM_SG; // For IV and B0
 	dst_size = get_space_for_phys_dsgl(dnents);
@@ -2886,11 +2863,10 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	transhdr_len = roundup(transhdr_len, 16);
 
 	if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE -
-				    reqctx->b0_len, transhdr_len, op_type)) {
+				    reqctx->b0_len, transhdr_len, reqctx->op)) {
 		atomic_inc(&adap->chcr_stats.fallback);
-		chcr_aead_dma_unmap(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev, req,
-				    op_type);
-		return ERR_PTR(chcr_aead_fallback(req, op_type));
+		chcr_aead_common_exit(req);
+		return ERR_PTR(chcr_aead_fallback(req, reqctx->op));
 	}
 	skb = alloc_skb(SGE_MAX_WR_LEN,  flags);
 
@@ -2901,7 +2877,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 
 	chcr_req = (struct chcr_wr *) __skb_put_zero(skb, transhdr_len);
 
-	fill_sec_cpl_for_aead(&chcr_req->sec_cpl, dst_size, req, op_type);
+	fill_sec_cpl_for_aead(&chcr_req->sec_cpl, dst_size, req, reqctx->op);
 
 	chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr;
 	memcpy(chcr_req->key_ctx.key, aeadctx->key, aeadctx->enckey_len);
@@ -2910,21 +2886,11 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 
 	phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len);
 	ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size);
-	error = ccm_format_packet(req, aeadctx, sub_type, op_type);
+	error = ccm_format_packet(req, aeadctx, sub_type, reqctx->op, assoclen);
 	if (error)
 		goto dstmap_fail;
-
-	reqctx->b0_dma = dma_map_single(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev,
-					&reqctx->scratch_pad, reqctx->b0_len,
-					DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev,
-			      reqctx->b0_dma)) {
-		error = -ENOMEM;
-		goto dstmap_fail;
-	}
-
-	chcr_add_aead_dst_ent(req, phys_cpl, assoclen, op_type, qid);
-	chcr_add_aead_src_ent(req, ulptx, assoclen, op_type);
+	chcr_add_aead_dst_ent(req, phys_cpl, assoclen, qid);
+	chcr_add_aead_src_ent(req, ulptx, assoclen);
 
 	atomic_inc(&adap->chcr_stats.aead_rqst);
 	temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size +
@@ -2933,20 +2899,18 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	create_wreq(a_ctx(tfm), chcr_req, &req->base, reqctx->imm, 0,
 		    transhdr_len, temp, 0);
 	reqctx->skb = skb;
-	reqctx->op = op_type;
 
 	return skb;
 dstmap_fail:
 	kfree_skb(skb);
 err:
-	chcr_aead_dma_unmap(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev, req, op_type);
+	chcr_aead_common_exit(req);
 	return ERR_PTR(error);
 }
 
 static struct sk_buff *create_gcm_wr(struct aead_request *req,
 				     unsigned short qid,
-				     int size,
-				     unsigned short op_type)
+				     int size)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct chcr_aead_ctx *aeadctx = AEAD_CTX(a_ctx(tfm));
@@ -2966,13 +2930,13 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106)
 		assoclen = req->assoclen - 8;
 
-	reqctx->b0_dma = 0;
-	error = chcr_aead_common_init(req, op_type);
+	reqctx->b0_len = 0;
+	error = chcr_aead_common_init(req);
 	if (error)
 		return ERR_PTR(error);
 	dnents = sg_nents_xlen(req->dst, assoclen, CHCR_DST_SG_SIZE, 0);
 	dnents += sg_nents_xlen(req->dst, req->cryptlen +
-				(op_type ? -authsize : authsize),
+				(reqctx->op ? -authsize : authsize),
 				CHCR_DST_SG_SIZE, req->assoclen);
 	dnents += MIN_GCM_SG; // For IV
 	dst_size = get_space_for_phys_dsgl(dnents);
@@ -2986,11 +2950,11 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	transhdr_len += temp;
 	transhdr_len = roundup(transhdr_len, 16);
 	if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE,
-			    transhdr_len, op_type)) {
+			    transhdr_len, reqctx->op)) {
+
 		atomic_inc(&adap->chcr_stats.fallback);
-		chcr_aead_dma_unmap(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev, req,
-				    op_type);
-		return ERR_PTR(chcr_aead_fallback(req, op_type));
+		chcr_aead_common_exit(req);
+		return ERR_PTR(chcr_aead_fallback(req, reqctx->op));
 	}
 	skb = alloc_skb(SGE_MAX_WR_LEN, flags);
 	if (!skb) {
@@ -3001,7 +2965,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	chcr_req = __skb_put_zero(skb, transhdr_len);
 
 	//Offset of tag from end
-	temp = (op_type == CHCR_ENCRYPT_OP) ? 0 : authsize;
+	temp = (reqctx->op == CHCR_ENCRYPT_OP) ? 0 : authsize;
 	chcr_req->sec_cpl.op_ivinsrtofst = FILL_SEC_CPL_OP_IVINSR(
 					a_ctx(tfm)->dev->rx_channel_id, 2,
 					(assoclen + 1));
@@ -3014,7 +2978,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 			FILL_SEC_CPL_AUTHINSERT(0, assoclen + IV + 1,
 						temp, temp);
 	chcr_req->sec_cpl.seqno_numivs =
-			FILL_SEC_CPL_SCMD0_SEQNO(op_type, (op_type ==
+			FILL_SEC_CPL_SCMD0_SEQNO(reqctx->op, (reqctx->op ==
 					CHCR_ENCRYPT_OP) ? 1 : 0,
 					CHCR_SCMD_CIPHER_MODE_AES_GCM,
 					CHCR_SCMD_AUTH_MODE_GHASH,
@@ -3040,19 +3004,18 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len);
 	ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size);
 
-	chcr_add_aead_dst_ent(req, phys_cpl, assoclen, op_type, qid);
-	chcr_add_aead_src_ent(req, ulptx, assoclen, op_type);
+	chcr_add_aead_dst_ent(req, phys_cpl, assoclen, qid);
+	chcr_add_aead_src_ent(req, ulptx, assoclen);
 	atomic_inc(&adap->chcr_stats.aead_rqst);
 	temp = sizeof(struct cpl_rx_phys_dsgl) + dst_size +
 		kctx_len + (reqctx->imm ? (assoclen + IV + req->cryptlen) : 0);
 	create_wreq(a_ctx(tfm), chcr_req, &req->base, reqctx->imm, size,
 		    transhdr_len, temp, reqctx->verify);
 	reqctx->skb = skb;
-	reqctx->op = op_type;
 	return skb;
 
 err:
-	chcr_aead_dma_unmap(&ULD_CTX(a_ctx(tfm))->lldi.pdev->dev, req, op_type);
+	chcr_aead_common_exit(req);
 	return ERR_PTR(error);
 }
 
@@ -3461,6 +3424,7 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 	}
 	{
 		SHASH_DESC_ON_STACK(shash, base_hash);
+
 		shash->tfm = base_hash;
 		shash->flags = crypto_shash_get_flags(base_hash);
 		bs = crypto_shash_blocksize(base_hash);
@@ -3585,13 +3549,13 @@ out:
 }
 
 static int chcr_aead_op(struct aead_request *req,
-			unsigned short op_type,
 			int size,
 			create_wr_t create_wr_fn)
 {
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct uld_ctx *u_ctx;
 	struct sk_buff *skb;
+	int isfull = 0;
 
 	if (!a_ctx(tfm)->dev) {
 		pr_err("chcr : %s : No crypto device.\n", __func__);
@@ -3600,13 +3564,13 @@ static int chcr_aead_op(struct aead_request *req,
 	u_ctx = ULD_CTX(a_ctx(tfm));
 	if (cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
 				   a_ctx(tfm)->tx_qidx)) {
+		isfull = 1;
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
-			return -EBUSY;
+			return -ENOSPC;
 	}
 
 	/* Form a WR from req */
-	skb = create_wr_fn(req, u_ctx->lldi.rxq_ids[a_ctx(tfm)->rx_qidx], size,
-			   op_type);
+	skb = create_wr_fn(req, u_ctx->lldi.rxq_ids[a_ctx(tfm)->rx_qidx], size);
 
 	if (IS_ERR(skb) || !skb)
 		return PTR_ERR(skb);
@@ -3614,7 +3578,7 @@ static int chcr_aead_op(struct aead_request *req,
 	skb->dev = u_ctx->lldi.ports[0];
 	set_wr_txq(skb, CPL_PRIORITY_DATA, a_ctx(tfm)->tx_qidx);
 	chcr_send_wr(skb);
-	return -EINPROGRESS;
+	return isfull ? -EBUSY : -EINPROGRESS;
 }
 
 static int chcr_aead_encrypt(struct aead_request *req)
@@ -3623,21 +3587,19 @@ static int chcr_aead_encrypt(struct aead_request *req)
 	struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
 
 	reqctx->verify = VERIFY_HW;
+	reqctx->op = CHCR_ENCRYPT_OP;
 
 	switch (get_aead_subtype(tfm)) {
 	case CRYPTO_ALG_SUB_TYPE_CTR_SHA:
 	case CRYPTO_ALG_SUB_TYPE_CBC_SHA:
 	case CRYPTO_ALG_SUB_TYPE_CBC_NULL:
 	case CRYPTO_ALG_SUB_TYPE_CTR_NULL:
-		return chcr_aead_op(req, CHCR_ENCRYPT_OP, 0,
-				    create_authenc_wr);
+		return chcr_aead_op(req, 0, create_authenc_wr);
 	case CRYPTO_ALG_SUB_TYPE_AEAD_CCM:
 	case CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309:
-		return chcr_aead_op(req, CHCR_ENCRYPT_OP, 0,
-				    create_aead_ccm_wr);
+		return chcr_aead_op(req, 0, create_aead_ccm_wr);
 	default:
-		return chcr_aead_op(req, CHCR_ENCRYPT_OP, 0,
-				    create_gcm_wr);
+		return chcr_aead_op(req, 0, create_gcm_wr);
 	}
 }
 
@@ -3655,21 +3617,18 @@ static int chcr_aead_decrypt(struct aead_request *req)
 		size = 0;
 		reqctx->verify = VERIFY_HW;
 	}
-
+	reqctx->op = CHCR_DECRYPT_OP;
 	switch (get_aead_subtype(tfm)) {
 	case CRYPTO_ALG_SUB_TYPE_CBC_SHA:
 	case CRYPTO_ALG_SUB_TYPE_CTR_SHA:
 	case CRYPTO_ALG_SUB_TYPE_CBC_NULL:
 	case CRYPTO_ALG_SUB_TYPE_CTR_NULL:
-		return chcr_aead_op(req, CHCR_DECRYPT_OP, size,
-				    create_authenc_wr);
+		return chcr_aead_op(req, size, create_authenc_wr);
 	case CRYPTO_ALG_SUB_TYPE_AEAD_CCM:
 	case CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309:
-		return chcr_aead_op(req, CHCR_DECRYPT_OP, size,
-				    create_aead_ccm_wr);
+		return chcr_aead_op(req, size, create_aead_ccm_wr);
 	default:
-		return chcr_aead_op(req, CHCR_DECRYPT_OP, size,
-				    create_gcm_wr);
+		return chcr_aead_op(req, size, create_gcm_wr);
 	}
 }
 
diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h
index dba3dff1e209..1871500309e2 100644
--- a/drivers/crypto/chelsio/chcr_algo.h
+++ b/drivers/crypto/chelsio/chcr_algo.h
@@ -146,7 +146,7 @@
 	 kctx_len)
 #define CIPHER_TRANSHDR_SIZE(kctx_len, sge_pairs) \
 	(TRANSHDR_SIZE((kctx_len)) + (sge_pairs) +\
-	 sizeof(struct cpl_rx_phys_dsgl))
+	 sizeof(struct cpl_rx_phys_dsgl) + AES_BLOCK_SIZE)
 #define HASH_TRANSHDR_SIZE(kctx_len)\
 	(TRANSHDR_SIZE(kctx_len) + DUMMY_BYTES)
 
@@ -259,7 +259,6 @@
 					ULP_TX_SC_MORE_V((immdatalen)))
 #define MAX_NK 8
 #define MAX_DSGL_ENT			32
-#define MIN_CIPHER_SG			1 /* IV */
 #define MIN_AUTH_SG			1 /* IV */
 #define MIN_GCM_SG			1 /* IV */
 #define MIN_DIGEST_SG			1 /*Partial Buffer*/
diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h
index 1a20424e18c6..de3a9c085daf 100644
--- a/drivers/crypto/chelsio/chcr_core.h
+++ b/drivers/crypto/chelsio/chcr_core.h
@@ -56,7 +56,7 @@
 #define MAX_SALT                4
 #define CIP_WR_MIN_LEN (sizeof(struct chcr_wr) + \
 		    sizeof(struct cpl_rx_phys_dsgl) + \
-		    sizeof(struct ulptx_sgl))
+		    sizeof(struct ulptx_sgl) + 16) //IV
 
 #define HASH_WR_MIN_LEN (sizeof(struct chcr_wr) + \
 			DUMMY_BYTES + \
diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h
index c8e8972af283..54835cb109e5 100644
--- a/drivers/crypto/chelsio/chcr_crypto.h
+++ b/drivers/crypto/chelsio/chcr_crypto.h
@@ -190,8 +190,8 @@ struct chcr_aead_reqctx {
 	short int dst_nents;
 	u16 imm;
 	u16 verify;
-	u8 iv[CHCR_MAX_CRYPTO_IV_LEN];
-	unsigned char scratch_pad[MAX_SCRATCH_PAD_SIZE];
+	u8 iv[CHCR_MAX_CRYPTO_IV_LEN + MAX_SCRATCH_PAD_SIZE];
+	u8 *scratch_pad;
 };
 
 struct ulptx_walk {
@@ -295,7 +295,6 @@ struct chcr_blkcipher_req_ctx {
 	unsigned int src_ofst;
 	unsigned int dst_ofst;
 	unsigned int op;
-	dma_addr_t iv_dma;
 	u16 imm;
 	u8 iv[CHCR_MAX_CRYPTO_IV_LEN];
 };
@@ -312,8 +311,7 @@ struct chcr_alg_template {
 
 typedef struct sk_buff *(*create_wr_t)(struct aead_request *req,
 				       unsigned short qid,
-				       int size,
-				       unsigned short op_type);
+				       int size);
 
 void chcr_verify_tag(struct aead_request *req, u8 *input, int *err);
 int chcr_aead_dma_map(struct device *dev, struct aead_request *req,
@@ -322,12 +320,12 @@ void chcr_aead_dma_unmap(struct device *dev, struct aead_request *req,
 			 unsigned short op_type);
 void chcr_add_aead_dst_ent(struct aead_request *req,
 			   struct cpl_rx_phys_dsgl *phys_cpl,
-			   unsigned int assoclen, unsigned short op_type,
+			   unsigned int assoclen,
 			   unsigned short qid);
 void chcr_add_aead_src_ent(struct aead_request *req, struct ulptx_sgl *ulptx,
-			   unsigned int assoclen, unsigned short op_type);
+			   unsigned int assoclen);
 void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
-			     struct ulptx_sgl *ulptx,
+			     void *ulptx,
 			     struct  cipher_wr_param *wrparam);
 int chcr_cipher_dma_map(struct device *dev, struct ablkcipher_request *req);
 void chcr_cipher_dma_unmap(struct device *dev, struct ablkcipher_request *req);
@@ -340,4 +338,5 @@ void chcr_add_hash_src_ent(struct ahash_request *req, struct ulptx_sgl *ulptx,
 			   struct hash_wr_param *param);
 int chcr_hash_dma_map(struct device *dev, struct ahash_request *req);
 void chcr_hash_dma_unmap(struct device *dev, struct ahash_request *req);
+void chcr_aead_common_exit(struct aead_request *req);
 #endif /* __CHCR_CRYPTO_H__ */
diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/crypto/chelsio/chcr_ipsec.c
index 8e0aa3f175c9..461b97e2f1fd 100644
--- a/drivers/crypto/chelsio/chcr_ipsec.c
+++ b/drivers/crypto/chelsio/chcr_ipsec.c
@@ -346,18 +346,23 @@ inline void *copy_cpltx_pktxt(struct sk_buff *skb,
 				struct net_device *dev,
 				void *pos)
 {
+	struct cpl_tx_pkt_core *cpl;
+	struct sge_eth_txq *q;
 	struct adapter *adap;
 	struct port_info *pi;
-	struct sge_eth_txq *q;
-	struct cpl_tx_pkt_core *cpl;
-	u64 cntrl = 0;
 	u32 ctrl0, qidx;
+	u64 cntrl = 0;
+	int left;
 
 	pi = netdev_priv(dev);
 	adap = pi->adapter;
 	qidx = skb->queue_mapping;
 	q = &adap->sge.ethtxq[qidx + pi->first_qset];
 
+	left = (void *)q->q.stat - pos;
+	if (!left)
+		pos = q->q.desc;
+
 	cpl = (struct cpl_tx_pkt_core *)pos;
 
 	cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
@@ -382,18 +387,17 @@ inline void *copy_key_cpltx_pktxt(struct sk_buff *skb,
 				void *pos,
 				struct ipsec_sa_entry *sa_entry)
 {
-	struct adapter *adap;
-	struct port_info *pi;
-	struct sge_eth_txq *q;
-	unsigned int len, qidx;
 	struct _key_ctx *key_ctx;
 	int left, eoq, key_len;
+	struct sge_eth_txq *q;
+	struct adapter *adap;
+	struct port_info *pi;
+	unsigned int qidx;
 
 	pi = netdev_priv(dev);
 	adap = pi->adapter;
 	qidx = skb->queue_mapping;
 	q = &adap->sge.ethtxq[qidx + pi->first_qset];
-	len = sa_entry->enckey_len + sizeof(struct cpl_tx_pkt_core);
 	key_len = sa_entry->kctx_len;
 
 	/* end of queue, reset pos to start of queue */
@@ -411,19 +415,14 @@ inline void *copy_key_cpltx_pktxt(struct sk_buff *skb,
 	pos += sizeof(struct _key_ctx);
 	left -= sizeof(struct _key_ctx);
 
-	if (likely(len <= left)) {
+	if (likely(key_len <= left)) {
 		memcpy(key_ctx->key, sa_entry->key, key_len);
 		pos += key_len;
 	} else {
-		if (key_len <= left) {
-			memcpy(pos, sa_entry->key, key_len);
-			pos += key_len;
-		} else {
-			memcpy(pos, sa_entry->key, left);
-			memcpy(q->q.desc, sa_entry->key + left,
-			       key_len - left);
-			pos = (u8 *)q->q.desc + (key_len - left);
-		}
+		memcpy(pos, sa_entry->key, left);
+		memcpy(q->q.desc, sa_entry->key + left,
+		       key_len - left);
+		pos = (u8 *)q->q.desc + (key_len - left);
 	}
 	/* Copy CPL TX PKT XT */
 	pos = copy_cpltx_pktxt(skb, dev, pos);
diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h
index f4b8f1ec0061..a53a0e6ba024 100644
--- a/drivers/crypto/chelsio/chtls/chtls.h
+++ b/drivers/crypto/chelsio/chtls/chtls.h
@@ -67,11 +67,6 @@ enum {
 	CPL_RET_UNKNOWN_TID = 4    /* unexpected unknown TID */
 };
 
-#define TLS_RCV_ST_READ_HEADER		0xF0
-#define TLS_RCV_ST_READ_BODY		0xF1
-#define TLS_RCV_ST_READ_DONE		0xF2
-#define TLS_RCV_ST_READ_NB		0xF3
-
 #define LISTEN_INFO_HASH_SIZE 32
 #define RSPQ_HASH_BITS 5
 struct listen_info {
@@ -149,6 +144,7 @@ struct chtls_dev {
 	struct list_head rcu_node;
 	struct list_head na_node;
 	unsigned int send_page_order;
+	int max_host_sndbuf;
 	struct key_map kmap;
 };
 
@@ -278,6 +274,7 @@ struct tlsrx_cmp_hdr {
 #define TLSRX_HDR_PKT_MAC_ERROR_F        TLSRX_HDR_PKT_MAC_ERROR_V(1U)
 
 #define TLSRX_HDR_PKT_ERROR_M           0x1F
+#define CONTENT_TYPE_ERROR		0x7F
 
 struct ulp_mem_rw {
 	__be32 cmd;
@@ -347,8 +344,8 @@ enum {
 	ULPCB_FLAG_HOLD      = 1 << 3,	/* skb not ready for Tx yet */
 	ULPCB_FLAG_COMPL     = 1 << 4,	/* request WR completion */
 	ULPCB_FLAG_URG       = 1 << 5,	/* urgent data */
-	ULPCB_FLAG_TLS_ND    = 1 << 6, /* payload of zero length */
-	ULPCB_FLAG_NO_HDR    = 1 << 7, /* not a ofld wr */
+	ULPCB_FLAG_TLS_HDR   = 1 << 6,  /* payload with tls hdr */
+	ULPCB_FLAG_NO_HDR    = 1 << 7,  /* not a ofld wr */
 };
 
 /* The ULP mode/submode of an skbuff */
diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index 82a473a0cefa..2bb6f0380758 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -1537,6 +1537,10 @@ static int chtls_rx_data(struct chtls_dev *cdev, struct sk_buff *skb)
 	struct sock *sk;
 
 	sk = lookup_tid(cdev->tids, hwtid);
+	if (unlikely(!sk)) {
+		pr_err("can't find conn. for hwtid %u.\n", hwtid);
+		return -EINVAL;
+	}
 	skb_dst_set(skb, NULL);
 	process_cpl_msg(chtls_recv_data, sk, skb);
 	return 0;
@@ -1585,6 +1589,10 @@ static int chtls_rx_pdu(struct chtls_dev *cdev, struct sk_buff *skb)
 	struct sock *sk;
 
 	sk = lookup_tid(cdev->tids, hwtid);
+	if (unlikely(!sk)) {
+		pr_err("can't find conn. for hwtid %u.\n", hwtid);
+		return -EINVAL;
+	}
 	skb_dst_set(skb, NULL);
 	process_cpl_msg(chtls_recv_pdu, sk, skb);
 	return 0;
@@ -1600,12 +1608,14 @@ static void chtls_set_hdrlen(struct sk_buff *skb, unsigned int nlen)
 
 static void chtls_rx_hdr(struct sock *sk, struct sk_buff *skb)
 {
-	struct cpl_rx_tls_cmp *cmp_cpl = cplhdr(skb);
+	struct tlsrx_cmp_hdr *tls_hdr_pkt;
+	struct cpl_rx_tls_cmp *cmp_cpl;
 	struct sk_buff *skb_rec;
 	struct chtls_sock *csk;
 	struct chtls_hws *tlsk;
 	struct tcp_sock *tp;
 
+	cmp_cpl = cplhdr(skb);
 	csk = rcu_dereference_sk_user_data(sk);
 	tlsk = &csk->tlshws;
 	tp = tcp_sk(sk);
@@ -1615,16 +1625,18 @@ static void chtls_rx_hdr(struct sock *sk, struct sk_buff *skb)
 
 	skb_reset_transport_header(skb);
 	__skb_pull(skb, sizeof(*cmp_cpl));
+	tls_hdr_pkt = (struct tlsrx_cmp_hdr *)skb->data;
+	if (tls_hdr_pkt->res_to_mac_error & TLSRX_HDR_PKT_ERROR_M)
+		tls_hdr_pkt->type = CONTENT_TYPE_ERROR;
 	if (!skb->data_len)
-		__skb_trim(skb, CPL_RX_TLS_CMP_LENGTH_G
-				(ntohl(cmp_cpl->pdulength_length)));
+		__skb_trim(skb, TLS_HEADER_LENGTH);
 
 	tp->rcv_nxt +=
 		CPL_RX_TLS_CMP_PDULENGTH_G(ntohl(cmp_cpl->pdulength_length));
 
+	ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_TLS_HDR;
 	skb_rec = __skb_dequeue(&tlsk->sk_recv_queue);
 	if (!skb_rec) {
-		ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_TLS_ND;
 		__skb_queue_tail(&sk->sk_receive_queue, skb);
 	} else {
 		chtls_set_hdrlen(skb, tlsk->pldlen);
@@ -1646,6 +1658,10 @@ static int chtls_rx_cmp(struct chtls_dev *cdev, struct sk_buff *skb)
 	struct sock *sk;
 
 	sk = lookup_tid(cdev->tids, hwtid);
+	if (unlikely(!sk)) {
+		pr_err("can't find conn. for hwtid %u.\n", hwtid);
+		return -EINVAL;
+	}
 	skb_dst_set(skb, NULL);
 	process_cpl_msg(chtls_rx_hdr, sk, skb);
 
@@ -2105,6 +2121,10 @@ static int chtls_wr_ack(struct chtls_dev *cdev, struct sk_buff *skb)
 	struct sock *sk;
 
 	sk = lookup_tid(cdev->tids, hwtid);
+	if (unlikely(!sk)) {
+		pr_err("can't find conn. for hwtid %u.\n", hwtid);
+		return -EINVAL;
+	}
 	process_cpl_msg(chtls_rx_ack, sk, skb);
 
 	return 0;
diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/crypto/chelsio/chtls/chtls_hw.c
index 54a13aa99121..55d50140f9e5 100644
--- a/drivers/crypto/chelsio/chtls/chtls_hw.c
+++ b/drivers/crypto/chelsio/chtls/chtls_hw.c
@@ -213,7 +213,7 @@ static int chtls_key_info(struct chtls_sock *csk,
 			  struct _key_ctx *kctx,
 			  u32 keylen, u32 optname)
 {
-	unsigned char key[CHCR_KEYCTX_CIPHER_KEY_SIZE_256];
+	unsigned char key[AES_KEYSIZE_128];
 	struct tls12_crypto_info_aes_gcm_128 *gcm_ctx;
 	unsigned char ghash_h[AEAD_H_SIZE];
 	struct crypto_cipher *cipher;
@@ -228,10 +228,6 @@ static int chtls_key_info(struct chtls_sock *csk,
 
 	if (keylen == AES_KEYSIZE_128) {
 		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128;
-	} else if (keylen == AES_KEYSIZE_192) {
-		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192;
-	} else if (keylen == AES_KEYSIZE_256) {
-		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256;
 	} else {
 		pr_err("GCM: Invalid key length %d\n", keylen);
 		return -EINVAL;
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 5a75be43950f..51fc6821cbbf 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -907,11 +907,83 @@ static int chtls_skb_copy_to_page_nocache(struct sock *sk,
 }
 
 /* Read TLS header to find content type and data length */
-static u16 tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
+static int tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
 {
 	if (copy_from_iter(thdr, sizeof(*thdr), from) != sizeof(*thdr))
 		return -EFAULT;
-	return (__force u16)cpu_to_be16(thdr->length);
+	return (__force int)cpu_to_be16(thdr->length);
+}
+
+static int csk_mem_free(struct chtls_dev *cdev, struct sock *sk)
+{
+	return (cdev->max_host_sndbuf - sk->sk_wmem_queued);
+}
+
+static int csk_wait_memory(struct chtls_dev *cdev,
+			   struct sock *sk, long *timeo_p)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	int sndbuf, err = 0;
+	long current_timeo;
+	long vm_wait = 0;
+	bool noblock;
+
+	current_timeo = *timeo_p;
+	noblock = (*timeo_p ? false : true);
+	sndbuf = cdev->max_host_sndbuf;
+	if (csk_mem_free(cdev, sk)) {
+		current_timeo = (prandom_u32() % (HZ / 5)) + 2;
+		vm_wait = (prandom_u32() % (HZ / 5)) + 2;
+	}
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	while (1) {
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+
+		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+			goto do_error;
+		if (!*timeo_p) {
+			if (noblock)
+				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+			goto do_nonblock;
+		}
+		if (signal_pending(current))
+			goto do_interrupted;
+		sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+		if (csk_mem_free(cdev, sk) && !vm_wait)
+			break;
+
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		sk->sk_write_pending++;
+		sk_wait_event(sk, &current_timeo, sk->sk_err ||
+			      (sk->sk_shutdown & SEND_SHUTDOWN) ||
+			      (csk_mem_free(cdev, sk) && !vm_wait), &wait);
+		sk->sk_write_pending--;
+
+		if (vm_wait) {
+			vm_wait -= current_timeo;
+			current_timeo = *timeo_p;
+			if (current_timeo != MAX_SCHEDULE_TIMEOUT) {
+				current_timeo -= vm_wait;
+				if (current_timeo < 0)
+					current_timeo = 0;
+			}
+			vm_wait = 0;
+		}
+		*timeo_p = current_timeo;
+	}
+do_rm_wq:
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return err;
+do_error:
+	err = -EPIPE;
+	goto do_rm_wq;
+do_nonblock:
+	err = -EAGAIN;
+	goto do_rm_wq;
+do_interrupted:
+	err = sock_intr_errno(*timeo_p);
+	goto do_rm_wq;
 }
 
 int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
@@ -952,6 +1024,8 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			copy = mss - skb->len;
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		}
+		if (!csk_mem_free(cdev, sk))
+			goto wait_for_sndbuf;
 
 		if (is_tls_tx(csk) && !csk->tlshws.txleft) {
 			struct tls_hdr hdr;
@@ -1009,9 +1083,10 @@ new_buf:
 			int off = TCP_OFF(sk);
 			bool merge;
 
-			if (page)
-				pg_size <<= compound_order(page);
+			if (!page)
+				goto wait_for_memory;
 
+			pg_size <<= compound_order(page);
 			if (off < pg_size &&
 			    skb_can_coalesce(skb, i, page, off)) {
 				merge = 1;
@@ -1099,8 +1174,10 @@ copy:
 		if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND)
 			push_frames_if_head(sk);
 		continue;
+wait_for_sndbuf:
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-		err = sk_stream_wait_memory(sk, &timeo);
+		err = csk_wait_memory(cdev, sk, &timeo);
 		if (err)
 			goto do_error;
 	}
@@ -1131,6 +1208,7 @@ int chtls_sendpage(struct sock *sk, struct page *page,
 		   int offset, size_t size, int flags)
 {
 	struct chtls_sock *csk;
+	struct chtls_dev *cdev;
 	int mss, err, copied;
 	struct tcp_sock *tp;
 	long timeo;
@@ -1138,6 +1216,7 @@ int chtls_sendpage(struct sock *sk, struct page *page,
 	tp = tcp_sk(sk);
 	copied = 0;
 	csk = rcu_dereference_sk_user_data(sk);
+	cdev = csk->cdev;
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 
 	err = sk_stream_wait_connect(sk, &timeo);
@@ -1152,10 +1231,11 @@ int chtls_sendpage(struct sock *sk, struct page *page,
 		struct sk_buff *skb = skb_peek_tail(&csk->txq);
 		int copy, i;
 
-		copy = mss - skb->len;
 		if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) ||
-		    copy <= 0) {
+		    (copy = mss - skb->len) <= 0) {
 new_buf:
+			if (!csk_mem_free(cdev, sk))
+				goto wait_for_sndbuf;
 
 			if (is_tls_tx(csk)) {
 				skb = get_record_skb(sk,
@@ -1167,7 +1247,7 @@ new_buf:
 				skb = get_tx_skb(sk, 0);
 			}
 			if (!skb)
-				goto do_error;
+				goto wait_for_memory;
 			copy = mss;
 		}
 		if (copy > size)
@@ -1206,8 +1286,12 @@ new_buf:
 		if (unlikely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND))
 			push_frames_if_head(sk);
 		continue;
-
+wait_for_sndbuf:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+wait_for_memory:
+		err = csk_wait_memory(cdev, sk, &timeo);
+		if (err)
+			goto do_error;
 	}
 out:
 	csk_reset_flag(csk, CSK_TX_MORE_DATA);
@@ -1409,7 +1493,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			break;
 		chtls_cleanup_rbuf(sk, copied);
 		sk_wait_data(sk, &timeo, NULL);
-			continue;
+		continue;
 found_ok_skb:
 		if (!skb->len) {
 			skb_dst_set(skb, NULL);
@@ -1449,31 +1533,13 @@ found_ok_skb:
 				}
 			}
 		}
-		if (hws->rstate == TLS_RCV_ST_READ_BODY) {
-			if (skb_copy_datagram_msg(skb, offset,
-						  msg, avail)) {
-				if (!copied) {
-					copied = -EFAULT;
-					break;
-				}
-			}
-		} else {
-			struct tlsrx_cmp_hdr *tls_hdr_pkt =
-				(struct tlsrx_cmp_hdr *)skb->data;
-
-			if ((tls_hdr_pkt->res_to_mac_error &
-			    TLSRX_HDR_PKT_ERROR_M))
-				tls_hdr_pkt->type = 0x7F;
-
-			/* CMP pld len is for recv seq */
-			hws->rcvpld = skb->hdr_len;
-			if (skb_copy_datagram_msg(skb, offset, msg, avail)) {
-				if (!copied) {
-					copied = -EFAULT;
-					break;
-				}
+		if (skb_copy_datagram_msg(skb, offset, msg, avail)) {
+			if (!copied) {
+				copied = -EFAULT;
+				break;
 			}
 		}
+
 		copied += avail;
 		len -= avail;
 		hws->copied_seq += avail;
@@ -1481,32 +1547,20 @@ skip_copy:
 		if (tp->urg_data && after(tp->copied_seq, tp->urg_seq))
 			tp->urg_data = 0;
 
-		if (hws->rstate == TLS_RCV_ST_READ_BODY &&
-		    (avail + offset) >= skb->len) {
+		if ((avail + offset) >= skb->len) {
 			if (likely(skb))
 				chtls_free_skb(sk, skb);
 			buffers_freed++;
-			hws->rstate = TLS_RCV_ST_READ_HEADER;
-			atomic_inc(&adap->chcr_stats.tls_pdu_rx);
-			tp->copied_seq += hws->rcvpld;
+			if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) {
+				tp->copied_seq += skb->len;
+				hws->rcvpld = skb->hdr_len;
+			} else {
+				tp->copied_seq += hws->rcvpld;
+			}
 			hws->copied_seq = 0;
 			if (copied >= target &&
 			    !skb_peek(&sk->sk_receive_queue))
 				break;
-		} else {
-			if (likely(skb)) {
-				if (ULP_SKB_CB(skb)->flags &
-				    ULPCB_FLAG_TLS_ND)
-					hws->rstate =
-						TLS_RCV_ST_READ_HEADER;
-				else
-					hws->rstate =
-						TLS_RCV_ST_READ_BODY;
-				chtls_free_skb(sk, skb);
-			}
-			buffers_freed++;
-			tp->copied_seq += avail;
-			hws->copied_seq = 0;
 		}
 	} while (len > 0);
 
diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c
index 007c45c38fc7..9b07f9165658 100644
--- a/drivers/crypto/chelsio/chtls/chtls_main.c
+++ b/drivers/crypto/chelsio/chtls/chtls_main.c
@@ -216,7 +216,6 @@ static void *chtls_uld_add(const struct cxgb4_lld_info *info)
 	cdev->lldi = lldi;
 	cdev->pdev = lldi->pdev;
 	cdev->tids = lldi->tids;
-	cdev->ports = (struct net_device **)(cdev + 1);
 	cdev->ports = lldi->ports;
 	cdev->mtus = lldi->mtus;
 	cdev->tids = lldi->tids;
@@ -239,6 +238,7 @@ static void *chtls_uld_add(const struct cxgb4_lld_info *info)
 	spin_lock_init(&cdev->idr_lock);
 	cdev->send_page_order = min_t(uint, get_order(32768),
 				      send_page_order);
+	cdev->max_host_sndbuf = 48 * 1024;
 
 	if (lldi->vr->key.size)
 		if (chtls_init_kmap(cdev, lldi))
@@ -250,7 +250,7 @@ static void *chtls_uld_add(const struct cxgb4_lld_info *info)
 
 	return cdev;
 out_rspq_skb:
-	for (j = 0; j <= i; j++)
+	for (j = 0; j < i; j++)
 		kfree_skb(cdev->rspq_skb_cache[j]);
 	kfree_skb(cdev->askb);
 out_skb:
@@ -441,7 +441,7 @@ nomem:
 static int do_chtls_getsockopt(struct sock *sk, char __user *optval,
 			       int __user *optlen)
 {
-	struct tls_crypto_info crypto_info;
+	struct tls_crypto_info crypto_info = { 0 };
 
 	crypto_info.version = TLS_1_2_VERSION;
 	if (copy_to_user(optval, &crypto_info, sizeof(struct tls_crypto_info)))
@@ -491,9 +491,13 @@ static int do_chtls_setsockopt(struct sock *sk, int optname,
 
 	switch (tmp_crypto_info.cipher_type) {
 	case TLS_CIPHER_AES_GCM_128: {
-		rc = copy_from_user(crypto_info, optval,
-				    sizeof(struct
-					   tls12_crypto_info_aes_gcm_128));
+		/* Obtain version and type from previous copy */
+		crypto_info[0] = tmp_crypto_info;
+		/* Now copy the following data */
+		rc = copy_from_user((char *)crypto_info + sizeof(*crypto_info),
+				optval + sizeof(*crypto_info),
+				sizeof(struct tls12_crypto_info_aes_gcm_128)
+				- sizeof(*crypto_info));
 
 		if (rc) {
 			rc = -EFAULT;
diff --git a/drivers/crypto/exynos-rng.c b/drivers/crypto/exynos-rng.c
index 86f5f459762e..2cfabb99cb6e 100644
--- a/drivers/crypto/exynos-rng.c
+++ b/drivers/crypto/exynos-rng.c
@@ -319,8 +319,7 @@ static int exynos_rng_remove(struct platform_device *pdev)
 
 static int __maybe_unused exynos_rng_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct exynos_rng_dev *rng = platform_get_drvdata(pdev);
+	struct exynos_rng_dev *rng = dev_get_drvdata(dev);
 	int ret;
 
 	/* If we were never seeded then after resume it will be the same */
@@ -350,8 +349,7 @@ static int __maybe_unused exynos_rng_suspend(struct device *dev)
 
 static int __maybe_unused exynos_rng_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct exynos_rng_dev *rng = platform_get_drvdata(pdev);
+	struct exynos_rng_dev *rng = dev_get_drvdata(dev);
 	int ret;
 
 	/* Never seeded so nothing to do */
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index d4a81be0d7d2..4e86f864a952 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -20,6 +20,7 @@
 #include <linux/platform_device.h>
 #include <linux/workqueue.h>
 
+#include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 
@@ -152,8 +153,8 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
 	       EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
 	writel(val, EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
 
-	memset(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
-	       EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
+	memset_io(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
+		  EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
 
 	eip197_write_firmware(priv, fw[FW_IFPP], EIP197_PE_ICE_FPP_CTRL,
 			      EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN);
@@ -352,6 +353,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	/* H/W capabilities selection */
 	val = EIP197_FUNCTION_RSVD;
 	val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
+	val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
 	val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
 	val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
 	val |= EIP197_ALG_SHA2 | EIP197_ALG_HMAC_SHA2;
@@ -537,6 +539,27 @@ finalize:
 	       EIP197_HIA_CDR(priv, ring) + EIP197_HIA_xDR_PREP_COUNT);
 }
 
+inline int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
+				       struct safexcel_result_desc *rdesc)
+{
+	if (likely(!rdesc->result_data.error_code))
+		return 0;
+
+	if (rdesc->result_data.error_code & 0x407f) {
+		/* Fatal error (bits 0-7, 14) */
+		dev_err(priv->dev,
+			"cipher: result: result descriptor error (%d)\n",
+			rdesc->result_data.error_code);
+		return -EIO;
+	} else if (rdesc->result_data.error_code == BIT(9)) {
+		/* Authentication failed */
+		return -EBADMSG;
+	}
+
+	/* All other non-fatal errors */
+	return -EINVAL;
+}
+
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring)
 {
 	struct safexcel_command_desc *cdesc;
@@ -770,6 +793,9 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_hmac_sha1,
 	&safexcel_alg_hmac_sha224,
 	&safexcel_alg_hmac_sha256,
+	&safexcel_alg_authenc_hmac_sha1_cbc_aes,
+	&safexcel_alg_authenc_hmac_sha224_cbc_aes,
+	&safexcel_alg_authenc_hmac_sha256_cbc_aes,
 };
 
 static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
@@ -781,6 +807,8 @@ static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
 
 		if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			ret = crypto_register_skcipher(&safexcel_algs[i]->alg.skcipher);
+		else if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_AEAD)
+			ret = crypto_register_aead(&safexcel_algs[i]->alg.aead);
 		else
 			ret = crypto_register_ahash(&safexcel_algs[i]->alg.ahash);
 
@@ -794,6 +822,8 @@ fail:
 	for (j = 0; j < i; j++) {
 		if (safexcel_algs[j]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			crypto_unregister_skcipher(&safexcel_algs[j]->alg.skcipher);
+		else if (safexcel_algs[j]->type == SAFEXCEL_ALG_TYPE_AEAD)
+			crypto_unregister_aead(&safexcel_algs[j]->alg.aead);
 		else
 			crypto_unregister_ahash(&safexcel_algs[j]->alg.ahash);
 	}
@@ -808,6 +838,8 @@ static void safexcel_unregister_algorithms(struct safexcel_crypto_priv *priv)
 	for (i = 0; i < ARRAY_SIZE(safexcel_algs); i++) {
 		if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			crypto_unregister_skcipher(&safexcel_algs[i]->alg.skcipher);
+		else if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_AEAD)
+			crypto_unregister_aead(&safexcel_algs[i]->alg.aead);
 		else
 			crypto_unregister_ahash(&safexcel_algs[i]->alg.ahash);
 	}
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index b470a849721f..8b3ee9b59f53 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -11,8 +11,10 @@
 #ifndef __SAFEXCEL_H__
 #define __SAFEXCEL_H__
 
+#include <crypto/aead.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
+#include <crypto/sha.h>
 #include <crypto/skcipher.h>
 
 #define EIP197_HIA_VERSION_LE			0xca35
@@ -20,7 +22,7 @@
 
 /* Static configuration */
 #define EIP197_DEFAULT_RING_SIZE		400
-#define EIP197_MAX_TOKENS			5
+#define EIP197_MAX_TOKENS			8
 #define EIP197_MAX_RINGS			4
 #define EIP197_FETCH_COUNT			1
 #define EIP197_MAX_BATCH_SZ			64
@@ -28,6 +30,17 @@
 #define EIP197_GFP_FLAGS(base)	((base).flags & CRYPTO_TFM_REQ_MAY_SLEEP ? \
 				 GFP_KERNEL : GFP_ATOMIC)
 
+/* Custom on-stack requests (for invalidation) */
+#define EIP197_SKCIPHER_REQ_SIZE	sizeof(struct skcipher_request) + \
+					sizeof(struct safexcel_cipher_req)
+#define EIP197_AHASH_REQ_SIZE		sizeof(struct ahash_request) + \
+					sizeof(struct safexcel_ahash_req)
+#define EIP197_AEAD_REQ_SIZE		sizeof(struct aead_request) + \
+					sizeof(struct safexcel_cipher_req)
+#define EIP197_REQUEST_ON_STACK(name, type, size) \
+	char __##name##_desc[size] CRYPTO_MINALIGN_ATTR; \
+	struct type##_request *name = (void *)__##name##_desc
+
 /* Register base offsets */
 #define EIP197_HIA_AIC(priv)		((priv)->base + (priv)->offsets.hia_aic)
 #define EIP197_HIA_AIC_G(priv)		((priv)->base + (priv)->offsets.hia_aic_g)
@@ -274,7 +287,7 @@ struct safexcel_context_record {
 	u32 control0;
 	u32 control1;
 
-	__le32 data[12];
+	__le32 data[24];
 } __packed;
 
 /* control0 */
@@ -286,8 +299,8 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_TYPE_CRYPTO_IN		0x5
 #define CONTEXT_CONTROL_TYPE_ENCRYPT_HASH_OUT	0x6
 #define CONTEXT_CONTROL_TYPE_DECRYPT_HASH_IN	0x7
-#define CONTEXT_CONTROL_TYPE_HASH_ENCRYPT_OUT	0x14
-#define CONTEXT_CONTROL_TYPE_HASH_DECRYPT_OUT	0x15
+#define CONTEXT_CONTROL_TYPE_HASH_ENCRYPT_OUT	0xe
+#define CONTEXT_CONTROL_TYPE_HASH_DECRYPT_IN	0xf
 #define CONTEXT_CONTROL_RESTART_HASH		BIT(4)
 #define CONTEXT_CONTROL_NO_FINISH_HASH		BIT(5)
 #define CONTEXT_CONTROL_SIZE(n)			((n) << 8)
@@ -391,11 +404,15 @@ struct safexcel_token {
 	u8 opcode:4;
 } __packed;
 
+#define EIP197_TOKEN_HASH_RESULT_VERIFY		BIT(16)
+
 #define EIP197_TOKEN_STAT_LAST_HASH		BIT(0)
 #define EIP197_TOKEN_STAT_LAST_PACKET		BIT(1)
 #define EIP197_TOKEN_OPCODE_DIRECTION		0x0
 #define EIP197_TOKEN_OPCODE_INSERT		0x2
 #define EIP197_TOKEN_OPCODE_NOOP		EIP197_TOKEN_OPCODE_INSERT
+#define EIP197_TOKEN_OPCODE_RETRIEVE		0x4
+#define EIP197_TOKEN_OPCODE_VERIFY		0xd
 #define EIP197_TOKEN_OPCODE_BYPASS		GENMASK(3, 0)
 
 static inline void eip197_noop_token(struct safexcel_token *token)
@@ -479,6 +496,7 @@ struct safexcel_ring {
 
 enum safexcel_alg_type {
 	SAFEXCEL_ALG_TYPE_SKCIPHER,
+	SAFEXCEL_ALG_TYPE_AEAD,
 	SAFEXCEL_ALG_TYPE_AHASH,
 };
 
@@ -581,6 +599,16 @@ struct safexcel_context {
 	bool exit_inv;
 };
 
+struct safexcel_ahash_export_state {
+	u64 len;
+	u64 processed;
+
+	u32 digest;
+
+	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u8 cache[SHA256_BLOCK_SIZE];
+};
+
 /*
  * Template structure to describe the algorithms in order to register them.
  * It also has the purpose to contain our private structure and is actually
@@ -591,6 +619,7 @@ struct safexcel_alg_template {
 	enum safexcel_alg_type type;
 	union {
 		struct skcipher_alg skcipher;
+		struct aead_alg aead;
 		struct ahash_alg ahash;
 	} alg;
 };
@@ -601,6 +630,8 @@ struct safexcel_inv_result {
 };
 
 void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring);
+int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
+				struct safexcel_result_desc *rdesc);
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring);
 int safexcel_invalidate_cache(struct crypto_async_request *async,
 			      struct safexcel_crypto_priv *priv,
@@ -625,6 +656,8 @@ struct safexcel_result_desc *safexcel_add_rdesc(struct safexcel_crypto_priv *pri
 						bool first, bool last,
 						dma_addr_t data, u32 len);
 void safexcel_inv_complete(struct crypto_async_request *req, int error);
+int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
+			 void *istate, void *ostate);
 
 /* available algorithms */
 extern struct safexcel_alg_template safexcel_alg_ecb_aes;
@@ -635,5 +668,8 @@ extern struct safexcel_alg_template safexcel_alg_sha256;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha224;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha256;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes;
 
 #endif
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index bafb60505fab..6bb60fda2043 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -12,8 +12,12 @@
 #include <linux/dma-mapping.h>
 #include <linux/dmapool.h>
 
+#include <crypto/aead.h>
 #include <crypto/aes.h>
+#include <crypto/authenc.h>
+#include <crypto/sha.h>
 #include <crypto/skcipher.h>
+#include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 
 #include "safexcel.h"
@@ -28,9 +32,16 @@ struct safexcel_cipher_ctx {
 	struct safexcel_crypto_priv *priv;
 
 	u32 mode;
+	bool aead;
 
 	__le32 key[8];
 	unsigned int key_len;
+
+	/* All the below is AEAD specific */
+	u32 alg;
+	u32 state_sz;
+	u32 ipad[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u32 opad[SHA256_DIGEST_SIZE / sizeof(u32)];
 };
 
 struct safexcel_cipher_req {
@@ -38,18 +49,16 @@ struct safexcel_cipher_req {
 	bool needs_inv;
 };
 
-static void safexcel_cipher_token(struct safexcel_cipher_ctx *ctx,
-				  struct crypto_async_request *async,
-				  struct safexcel_command_desc *cdesc,
-				  u32 length)
+static void safexcel_skcipher_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
+				    struct safexcel_command_desc *cdesc,
+				    u32 length)
 {
-	struct skcipher_request *req = skcipher_request_cast(async);
 	struct safexcel_token *token;
 	unsigned offset = 0;
 
 	if (ctx->mode == CONTEXT_CONTROL_CRYPTO_MODE_CBC) {
 		offset = AES_BLOCK_SIZE / sizeof(u32);
-		memcpy(cdesc->control_data.token, req->iv, AES_BLOCK_SIZE);
+		memcpy(cdesc->control_data.token, iv, AES_BLOCK_SIZE);
 
 		cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
 	}
@@ -65,8 +74,64 @@ static void safexcel_cipher_token(struct safexcel_cipher_ctx *ctx,
 				EIP197_TOKEN_INS_TYPE_OUTPUT;
 }
 
-static int safexcel_aes_setkey(struct crypto_skcipher *ctfm, const u8 *key,
-			       unsigned int len)
+static void safexcel_aead_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
+				struct safexcel_command_desc *cdesc,
+				enum safexcel_cipher_direction direction,
+				u32 cryptlen, u32 assoclen, u32 digestsize)
+{
+	struct safexcel_token *token;
+	unsigned offset = 0;
+
+	if (ctx->mode == CONTEXT_CONTROL_CRYPTO_MODE_CBC) {
+		offset = AES_BLOCK_SIZE / sizeof(u32);
+		memcpy(cdesc->control_data.token, iv, AES_BLOCK_SIZE);
+
+		cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
+	}
+
+	token = (struct safexcel_token *)(cdesc->control_data.token + offset);
+
+	if (direction == SAFEXCEL_DECRYPT)
+		cryptlen -= digestsize;
+
+	token[0].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
+	token[0].packet_length = assoclen;
+	token[0].instructions = EIP197_TOKEN_INS_TYPE_HASH |
+				EIP197_TOKEN_INS_TYPE_OUTPUT;
+
+	token[1].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
+	token[1].packet_length = cryptlen;
+	token[1].stat = EIP197_TOKEN_STAT_LAST_HASH;
+	token[1].instructions = EIP197_TOKEN_INS_LAST |
+				EIP197_TOKEN_INS_TYPE_CRYTO |
+				EIP197_TOKEN_INS_TYPE_HASH |
+				EIP197_TOKEN_INS_TYPE_OUTPUT;
+
+	if (direction == SAFEXCEL_ENCRYPT) {
+		token[2].opcode = EIP197_TOKEN_OPCODE_INSERT;
+		token[2].packet_length = digestsize;
+		token[2].stat = EIP197_TOKEN_STAT_LAST_HASH |
+				EIP197_TOKEN_STAT_LAST_PACKET;
+		token[2].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT |
+					EIP197_TOKEN_INS_INSERT_HASH_DIGEST;
+	} else {
+		token[2].opcode = EIP197_TOKEN_OPCODE_RETRIEVE;
+		token[2].packet_length = digestsize;
+		token[2].stat = EIP197_TOKEN_STAT_LAST_HASH |
+				EIP197_TOKEN_STAT_LAST_PACKET;
+		token[2].instructions = EIP197_TOKEN_INS_INSERT_HASH_DIGEST;
+
+		token[3].opcode = EIP197_TOKEN_OPCODE_VERIFY;
+		token[3].packet_length = digestsize |
+					 EIP197_TOKEN_HASH_RESULT_VERIFY;
+		token[3].stat = EIP197_TOKEN_STAT_LAST_HASH |
+				EIP197_TOKEN_STAT_LAST_PACKET;
+		token[3].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT;
+	}
+}
+
+static int safexcel_skcipher_aes_setkey(struct crypto_skcipher *ctfm,
+					const u8 *key, unsigned int len)
 {
 	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -98,41 +163,123 @@ static int safexcel_aes_setkey(struct crypto_skcipher *ctfm, const u8 *key,
 	return 0;
 }
 
+static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
+				    unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_aead_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_ahash_export_state istate, ostate;
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	struct crypto_authenc_keys keys;
+
+	if (crypto_authenc_extractkeys(&keys, key, len) != 0)
+		goto badkey;
+
+	if (keys.enckeylen > sizeof(ctx->key))
+		goto badkey;
+
+	/* Encryption key */
+	if (priv->version == EIP197 && ctx->base.ctxr_dma &&
+	    memcmp(ctx->key, keys.enckey, keys.enckeylen))
+		ctx->base.needs_inv = true;
+
+	/* Auth key */
+	switch (ctx->alg) {
+	case CONTEXT_CONTROL_CRYPTO_ALG_SHA1:
+		if (safexcel_hmac_setkey("safexcel-sha1", keys.authkey,
+					 keys.authkeylen, &istate, &ostate))
+			goto badkey;
+		break;
+	case CONTEXT_CONTROL_CRYPTO_ALG_SHA224:
+		if (safexcel_hmac_setkey("safexcel-sha224", keys.authkey,
+					 keys.authkeylen, &istate, &ostate))
+			goto badkey;
+		break;
+	case CONTEXT_CONTROL_CRYPTO_ALG_SHA256:
+		if (safexcel_hmac_setkey("safexcel-sha256", keys.authkey,
+					 keys.authkeylen, &istate, &ostate))
+			goto badkey;
+		break;
+	default:
+		dev_err(priv->dev, "aead: unsupported hash algorithm\n");
+		goto badkey;
+	}
+
+	crypto_aead_set_flags(ctfm, crypto_aead_get_flags(ctfm) &
+				    CRYPTO_TFM_RES_MASK);
+
+	if (priv->version == EIP197 && ctx->base.ctxr_dma &&
+	    (memcmp(ctx->ipad, istate.state, ctx->state_sz) ||
+	     memcmp(ctx->opad, ostate.state, ctx->state_sz)))
+		ctx->base.needs_inv = true;
+
+	/* Now copy the keys into the context */
+	memcpy(ctx->key, keys.enckey, keys.enckeylen);
+	ctx->key_len = keys.enckeylen;
+
+	memcpy(ctx->ipad, &istate.state, ctx->state_sz);
+	memcpy(ctx->opad, &ostate.state, ctx->state_sz);
+
+	memzero_explicit(&keys, sizeof(keys));
+	return 0;
+
+badkey:
+	crypto_aead_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	memzero_explicit(&keys, sizeof(keys));
+	return -EINVAL;
+}
+
 static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 				    struct crypto_async_request *async,
+				    struct safexcel_cipher_req *sreq,
 				    struct safexcel_command_desc *cdesc)
 {
 	struct safexcel_crypto_priv *priv = ctx->priv;
-	struct skcipher_request *req = skcipher_request_cast(async);
-	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
 	int ctrl_size;
 
-	if (sreq->direction == SAFEXCEL_ENCRYPT)
+	if (ctx->aead) {
+		if (sreq->direction == SAFEXCEL_ENCRYPT)
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_ENCRYPT_HASH_OUT;
+		else
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_HASH_DECRYPT_IN;
+	} else {
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_CRYPTO_OUT;
-	else
-		cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_CRYPTO_IN;
+
+		/* The decryption control type is a combination of the
+		 * encryption type and CONTEXT_CONTROL_TYPE_NULL_IN, for all
+		 * types.
+		 */
+		if (sreq->direction == SAFEXCEL_DECRYPT)
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_NULL_IN;
+	}
 
 	cdesc->control_data.control0 |= CONTEXT_CONTROL_KEY_EN;
 	cdesc->control_data.control1 |= ctx->mode;
 
+	if (ctx->aead)
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_DIGEST_HMAC |
+						ctx->alg;
+
 	switch (ctx->key_len) {
 	case AES_KEYSIZE_128:
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES128;
-		ctrl_size = 4;
 		break;
 	case AES_KEYSIZE_192:
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES192;
-		ctrl_size = 6;
 		break;
 	case AES_KEYSIZE_256:
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES256;
-		ctrl_size = 8;
 		break;
 	default:
 		dev_err(priv->dev, "aes keysize not supported: %u\n",
 			ctx->key_len);
 		return -EINVAL;
 	}
+
+	ctrl_size = ctx->key_len / sizeof(u32);
+	if (ctx->aead)
+		/* Take in account the ipad+opad digests */
+		ctrl_size += ctx->state_sz / sizeof(u32) * 2;
 	cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(ctrl_size);
 
 	return 0;
@@ -140,9 +287,12 @@ static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 
 static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int ring,
 				      struct crypto_async_request *async,
+				      struct scatterlist *src,
+				      struct scatterlist *dst,
+				      unsigned int cryptlen,
+				      struct safexcel_cipher_req *sreq,
 				      bool *should_complete, int *ret)
 {
-	struct skcipher_request *req = skcipher_request_cast(async);
 	struct safexcel_result_desc *rdesc;
 	int ndesc = 0;
 
@@ -158,12 +308,8 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 			break;
 		}
 
-		if (rdesc->result_data.error_code) {
-			dev_err(priv->dev,
-				"cipher: result: result descriptor error (%d)\n",
-				rdesc->result_data.error_code);
-			*ret = -EIO;
-		}
+		if (likely(!*ret))
+			*ret = safexcel_rdesc_check_errors(priv, rdesc);
 
 		ndesc++;
 	} while (!rdesc->last_seg);
@@ -171,16 +317,16 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	safexcel_complete(priv, ring);
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
-	if (req->src == req->dst) {
-		dma_unmap_sg(priv->dev, req->src,
-			     sg_nents_for_len(req->src, req->cryptlen),
+	if (src == dst) {
+		dma_unmap_sg(priv->dev, src,
+			     sg_nents_for_len(src, cryptlen),
 			     DMA_BIDIRECTIONAL);
 	} else {
-		dma_unmap_sg(priv->dev, req->src,
-			     sg_nents_for_len(req->src, req->cryptlen),
+		dma_unmap_sg(priv->dev, src,
+			     sg_nents_for_len(src, cryptlen),
 			     DMA_TO_DEVICE);
-		dma_unmap_sg(priv->dev, req->dst,
-			     sg_nents_for_len(req->dst, req->cryptlen),
+		dma_unmap_sg(priv->dev, dst,
+			     sg_nents_for_len(dst, cryptlen),
 			     DMA_FROM_DEVICE);
 	}
 
@@ -189,39 +335,43 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	return ndesc;
 }
 
-static int safexcel_aes_send(struct crypto_async_request *async,
-			     int ring, struct safexcel_request *request,
-			     int *commands, int *results)
+static int safexcel_aes_send(struct crypto_async_request *base, int ring,
+			     struct safexcel_request *request,
+			     struct safexcel_cipher_req *sreq,
+			     struct scatterlist *src, struct scatterlist *dst,
+			     unsigned int cryptlen, unsigned int assoclen,
+			     unsigned int digestsize, u8 *iv, int *commands,
+			     int *results)
 {
-	struct skcipher_request *req = skcipher_request_cast(async);
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct safexcel_command_desc *cdesc;
 	struct safexcel_result_desc *rdesc;
 	struct scatterlist *sg;
-	int nr_src, nr_dst, n_cdesc = 0, n_rdesc = 0, queued = req->cryptlen;
+	unsigned int totlen = cryptlen + assoclen;
+	int nr_src, nr_dst, n_cdesc = 0, n_rdesc = 0, queued = totlen;
 	int i, ret = 0;
 
-	if (req->src == req->dst) {
-		nr_src = dma_map_sg(priv->dev, req->src,
-				    sg_nents_for_len(req->src, req->cryptlen),
+	if (src == dst) {
+		nr_src = dma_map_sg(priv->dev, src,
+				    sg_nents_for_len(src, totlen),
 				    DMA_BIDIRECTIONAL);
 		nr_dst = nr_src;
 		if (!nr_src)
 			return -EINVAL;
 	} else {
-		nr_src = dma_map_sg(priv->dev, req->src,
-				    sg_nents_for_len(req->src, req->cryptlen),
+		nr_src = dma_map_sg(priv->dev, src,
+				    sg_nents_for_len(src, totlen),
 				    DMA_TO_DEVICE);
 		if (!nr_src)
 			return -EINVAL;
 
-		nr_dst = dma_map_sg(priv->dev, req->dst,
-				    sg_nents_for_len(req->dst, req->cryptlen),
+		nr_dst = dma_map_sg(priv->dev, dst,
+				    sg_nents_for_len(dst, totlen),
 				    DMA_FROM_DEVICE);
 		if (!nr_dst) {
-			dma_unmap_sg(priv->dev, req->src,
-				     sg_nents_for_len(req->src, req->cryptlen),
+			dma_unmap_sg(priv->dev, src,
+				     sg_nents_for_len(src, totlen),
 				     DMA_TO_DEVICE);
 			return -EINVAL;
 		}
@@ -229,10 +379,17 @@ static int safexcel_aes_send(struct crypto_async_request *async,
 
 	memcpy(ctx->base.ctxr->data, ctx->key, ctx->key_len);
 
+	if (ctx->aead) {
+		memcpy(ctx->base.ctxr->data + ctx->key_len / sizeof(u32),
+		       ctx->ipad, ctx->state_sz);
+		memcpy(ctx->base.ctxr->data + (ctx->key_len + ctx->state_sz) / sizeof(u32),
+		       ctx->opad, ctx->state_sz);
+	}
+
 	spin_lock_bh(&priv->ring[ring].egress_lock);
 
 	/* command descriptors */
-	for_each_sg(req->src, sg, nr_src, i) {
+	for_each_sg(src, sg, nr_src, i) {
 		int len = sg_dma_len(sg);
 
 		/* Do not overflow the request */
@@ -240,7 +397,7 @@ static int safexcel_aes_send(struct crypto_async_request *async,
 			len = queued;
 
 		cdesc = safexcel_add_cdesc(priv, ring, !n_cdesc, !(queued - len),
-					   sg_dma_address(sg), len, req->cryptlen,
+					   sg_dma_address(sg), len, totlen,
 					   ctx->base.ctxr_dma);
 		if (IS_ERR(cdesc)) {
 			/* No space left in the command descriptor ring */
@@ -250,8 +407,14 @@ static int safexcel_aes_send(struct crypto_async_request *async,
 		n_cdesc++;
 
 		if (n_cdesc == 1) {
-			safexcel_context_control(ctx, async, cdesc);
-			safexcel_cipher_token(ctx, async, cdesc, req->cryptlen);
+			safexcel_context_control(ctx, base, sreq, cdesc);
+			if (ctx->aead)
+				safexcel_aead_token(ctx, iv, cdesc,
+						    sreq->direction, cryptlen,
+						    assoclen, digestsize);
+			else
+				safexcel_skcipher_token(ctx, iv, cdesc,
+							cryptlen);
 		}
 
 		queued -= len;
@@ -260,7 +423,7 @@ static int safexcel_aes_send(struct crypto_async_request *async,
 	}
 
 	/* result descriptors */
-	for_each_sg(req->dst, sg, nr_dst, i) {
+	for_each_sg(dst, sg, nr_dst, i) {
 		bool first = !i, last = (i == nr_dst - 1);
 		u32 len = sg_dma_len(sg);
 
@@ -276,7 +439,7 @@ static int safexcel_aes_send(struct crypto_async_request *async,
 
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
-	request->req = &req->base;
+	request->req = base;
 
 	*commands = n_cdesc;
 	*results = n_rdesc;
@@ -291,16 +454,16 @@ cdesc_rollback:
 
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
-	if (req->src == req->dst) {
-		dma_unmap_sg(priv->dev, req->src,
-			     sg_nents_for_len(req->src, req->cryptlen),
+	if (src == dst) {
+		dma_unmap_sg(priv->dev, src,
+			     sg_nents_for_len(src, totlen),
 			     DMA_BIDIRECTIONAL);
 	} else {
-		dma_unmap_sg(priv->dev, req->src,
-			     sg_nents_for_len(req->src, req->cryptlen),
+		dma_unmap_sg(priv->dev, src,
+			     sg_nents_for_len(src, totlen),
 			     DMA_TO_DEVICE);
-		dma_unmap_sg(priv->dev, req->dst,
-			     sg_nents_for_len(req->dst, req->cryptlen),
+		dma_unmap_sg(priv->dev, dst,
+			     sg_nents_for_len(dst, totlen),
 			     DMA_FROM_DEVICE);
 	}
 
@@ -309,11 +472,10 @@ cdesc_rollback:
 
 static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 				      int ring,
-				      struct crypto_async_request *async,
+				      struct crypto_async_request *base,
 				      bool *should_complete, int *ret)
 {
-	struct skcipher_request *req = skcipher_request_cast(async);
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_result_desc *rdesc;
 	int ndesc = 0, enq_ret;
 
@@ -354,7 +516,7 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 	ctx->base.ring = ring;
 
 	spin_lock_bh(&priv->ring[ring].queue_lock);
-	enq_ret = crypto_enqueue_request(&priv->ring[ring].queue, async);
+	enq_ret = crypto_enqueue_request(&priv->ring[ring].queue, base);
 	spin_unlock_bh(&priv->ring[ring].queue_lock);
 
 	if (enq_ret != -EINPROGRESS)
@@ -368,9 +530,10 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 	return ndesc;
 }
 
-static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
-				  struct crypto_async_request *async,
-				  bool *should_complete, int *ret)
+static int safexcel_skcipher_handle_result(struct safexcel_crypto_priv *priv,
+					   int ring,
+					   struct crypto_async_request *async,
+					   bool *should_complete, int *ret)
 {
 	struct skcipher_request *req = skcipher_request_cast(async);
 	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
@@ -381,24 +544,48 @@ static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
 		err = safexcel_handle_inv_result(priv, ring, async,
 						 should_complete, ret);
 	} else {
-		err = safexcel_handle_req_result(priv, ring, async,
+		err = safexcel_handle_req_result(priv, ring, async, req->src,
+						 req->dst, req->cryptlen, sreq,
 						 should_complete, ret);
 	}
 
 	return err;
 }
 
-static int safexcel_cipher_send_inv(struct crypto_async_request *async,
+static int safexcel_aead_handle_result(struct safexcel_crypto_priv *priv,
+				       int ring,
+				       struct crypto_async_request *async,
+				       bool *should_complete, int *ret)
+{
+	struct aead_request *req = aead_request_cast(async);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct safexcel_cipher_req *sreq = aead_request_ctx(req);
+	int err;
+
+	if (sreq->needs_inv) {
+		sreq->needs_inv = false;
+		err = safexcel_handle_inv_result(priv, ring, async,
+						 should_complete, ret);
+	} else {
+		err = safexcel_handle_req_result(priv, ring, async, req->src,
+						 req->dst,
+						 req->cryptlen + crypto_aead_authsize(tfm),
+						 sreq, should_complete, ret);
+	}
+
+	return err;
+}
+
+static int safexcel_cipher_send_inv(struct crypto_async_request *base,
 				    int ring, struct safexcel_request *request,
 				    int *commands, int *results)
 {
-	struct skcipher_request *req = skcipher_request_cast(async);
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	ret = safexcel_invalidate_cache(async, priv,
-					ctx->base.ctxr_dma, ring, request);
+	ret = safexcel_invalidate_cache(base, priv, ctx->base.ctxr_dma, ring,
+					request);
 	if (unlikely(ret))
 		return ret;
 
@@ -408,9 +595,9 @@ static int safexcel_cipher_send_inv(struct crypto_async_request *async,
 	return 0;
 }
 
-static int safexcel_send(struct crypto_async_request *async,
-			 int ring, struct safexcel_request *request,
-			 int *commands, int *results)
+static int safexcel_skcipher_send(struct crypto_async_request *async, int ring,
+				  struct safexcel_request *request,
+				  int *commands, int *results)
 {
 	struct skcipher_request *req = skcipher_request_cast(async);
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
@@ -421,59 +608,108 @@ static int safexcel_send(struct crypto_async_request *async,
 	BUG_ON(priv->version == EIP97 && sreq->needs_inv);
 
 	if (sreq->needs_inv)
-		ret = safexcel_cipher_send_inv(async, ring, request,
-					       commands, results);
+		ret = safexcel_cipher_send_inv(async, ring, request, commands,
+					       results);
+	else
+		ret = safexcel_aes_send(async, ring, request, sreq, req->src,
+					req->dst, req->cryptlen, 0, 0, req->iv,
+					commands, results);
+	return ret;
+}
+
+static int safexcel_aead_send(struct crypto_async_request *async, int ring,
+			      struct safexcel_request *request, int *commands,
+			      int *results)
+{
+	struct aead_request *req = aead_request_cast(async);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_cipher_req *sreq = aead_request_ctx(req);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	BUG_ON(priv->version == EIP97 && sreq->needs_inv);
+
+	if (sreq->needs_inv)
+		ret = safexcel_cipher_send_inv(async, ring, request, commands,
+					       results);
 	else
-		ret = safexcel_aes_send(async, ring, request,
+		ret = safexcel_aes_send(async, ring, request, sreq, req->src,
+					req->dst, req->cryptlen, req->assoclen,
+					crypto_aead_authsize(tfm), req->iv,
 					commands, results);
 	return ret;
 }
 
-static int safexcel_cipher_exit_inv(struct crypto_tfm *tfm)
+static int safexcel_cipher_exit_inv(struct crypto_tfm *tfm,
+				    struct crypto_async_request *base,
+				    struct safexcel_cipher_req *sreq,
+				    struct safexcel_inv_result *result)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
-	SKCIPHER_REQUEST_ON_STACK(req, __crypto_skcipher_cast(tfm));
-	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
-	struct safexcel_inv_result result = {};
 	int ring = ctx->base.ring;
 
-	memset(req, 0, sizeof(struct skcipher_request));
+	init_completion(&result->completion);
 
-	/* create invalidation request */
-	init_completion(&result.completion);
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-				      safexcel_inv_complete, &result);
-
-	skcipher_request_set_tfm(req, __crypto_skcipher_cast(tfm));
-	ctx = crypto_tfm_ctx(req->base.tfm);
+	ctx = crypto_tfm_ctx(base->tfm);
 	ctx->base.exit_inv = true;
 	sreq->needs_inv = true;
 
 	spin_lock_bh(&priv->ring[ring].queue_lock);
-	crypto_enqueue_request(&priv->ring[ring].queue, &req->base);
+	crypto_enqueue_request(&priv->ring[ring].queue, base);
 	spin_unlock_bh(&priv->ring[ring].queue_lock);
 
 	queue_work(priv->ring[ring].workqueue,
 		   &priv->ring[ring].work_data.work);
 
-	wait_for_completion(&result.completion);
+	wait_for_completion(&result->completion);
 
-	if (result.error) {
+	if (result->error) {
 		dev_warn(priv->dev,
 			"cipher: sync: invalidate: completion error %d\n",
-			 result.error);
-		return result.error;
+			 result->error);
+		return result->error;
 	}
 
 	return 0;
 }
 
-static int safexcel_aes(struct skcipher_request *req,
-			enum safexcel_cipher_direction dir, u32 mode)
+static int safexcel_skcipher_exit_inv(struct crypto_tfm *tfm)
 {
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	EIP197_REQUEST_ON_STACK(req, skcipher, EIP197_SKCIPHER_REQ_SIZE);
 	struct safexcel_cipher_req *sreq = skcipher_request_ctx(req);
+	struct safexcel_inv_result result = {};
+
+	memset(req, 0, sizeof(struct skcipher_request));
+
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      safexcel_inv_complete, &result);
+	skcipher_request_set_tfm(req, __crypto_skcipher_cast(tfm));
+
+	return safexcel_cipher_exit_inv(tfm, &req->base, sreq, &result);
+}
+
+static int safexcel_aead_exit_inv(struct crypto_tfm *tfm)
+{
+	EIP197_REQUEST_ON_STACK(req, aead, EIP197_AEAD_REQ_SIZE);
+	struct safexcel_cipher_req *sreq = aead_request_ctx(req);
+	struct safexcel_inv_result result = {};
+
+	memset(req, 0, sizeof(struct aead_request));
+
+	aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				  safexcel_inv_complete, &result);
+	aead_request_set_tfm(req, __crypto_aead_cast(tfm));
+
+	return safexcel_cipher_exit_inv(tfm, &req->base, sreq, &result);
+}
+
+static int safexcel_aes(struct crypto_async_request *base,
+			struct safexcel_cipher_req *sreq,
+			enum safexcel_cipher_direction dir, u32 mode)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret, ring;
 
@@ -489,7 +725,7 @@ static int safexcel_aes(struct skcipher_request *req,
 	} else {
 		ctx->base.ring = safexcel_select_ring(priv);
 		ctx->base.ctxr = dma_pool_zalloc(priv->context_pool,
-						 EIP197_GFP_FLAGS(req->base),
+						 EIP197_GFP_FLAGS(*base),
 						 &ctx->base.ctxr_dma);
 		if (!ctx->base.ctxr)
 			return -ENOMEM;
@@ -498,7 +734,7 @@ static int safexcel_aes(struct skcipher_request *req,
 	ring = ctx->base.ring;
 
 	spin_lock_bh(&priv->ring[ring].queue_lock);
-	ret = crypto_enqueue_request(&priv->ring[ring].queue, &req->base);
+	ret = crypto_enqueue_request(&priv->ring[ring].queue, base);
 	spin_unlock_bh(&priv->ring[ring].queue_lock);
 
 	queue_work(priv->ring[ring].workqueue,
@@ -509,14 +745,14 @@ static int safexcel_aes(struct skcipher_request *req,
 
 static int safexcel_ecb_aes_encrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(req, SAFEXCEL_ENCRYPT,
-			    CONTEXT_CONTROL_CRYPTO_MODE_ECB);
+	return safexcel_aes(&req->base, skcipher_request_ctx(req),
+			    SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB);
 }
 
 static int safexcel_ecb_aes_decrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(req, SAFEXCEL_DECRYPT,
-			    CONTEXT_CONTROL_CRYPTO_MODE_ECB);
+	return safexcel_aes(&req->base, skcipher_request_ctx(req),
+			    SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB);
 }
 
 static int safexcel_skcipher_cra_init(struct crypto_tfm *tfm)
@@ -526,34 +762,64 @@ static int safexcel_skcipher_cra_init(struct crypto_tfm *tfm)
 		container_of(tfm->__crt_alg, struct safexcel_alg_template,
 			     alg.skcipher.base);
 
-	ctx->priv = tmpl->priv;
-	ctx->base.send = safexcel_send;
-	ctx->base.handle_result = safexcel_handle_result;
-
 	crypto_skcipher_set_reqsize(__crypto_skcipher_cast(tfm),
 				    sizeof(struct safexcel_cipher_req));
 
+	ctx->priv = tmpl->priv;
+
+	ctx->base.send = safexcel_skcipher_send;
+	ctx->base.handle_result = safexcel_skcipher_handle_result;
 	return 0;
 }
 
-static void safexcel_skcipher_cra_exit(struct crypto_tfm *tfm)
+static int safexcel_cipher_cra_exit(struct crypto_tfm *tfm)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct safexcel_crypto_priv *priv = ctx->priv;
-	int ret;
 
-	memzero_explicit(ctx->key, 8 * sizeof(u32));
+	memzero_explicit(ctx->key, sizeof(ctx->key));
 
 	/* context not allocated, skip invalidation */
 	if (!ctx->base.ctxr)
+		return -ENOMEM;
+
+	memzero_explicit(ctx->base.ctxr->data, sizeof(ctx->base.ctxr->data));
+	return 0;
+}
+
+static void safexcel_skcipher_cra_exit(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	if (safexcel_cipher_cra_exit(tfm))
 		return;
 
-	memzero_explicit(ctx->base.ctxr->data, 8 * sizeof(u32));
+	if (priv->version == EIP197) {
+		ret = safexcel_skcipher_exit_inv(tfm);
+		if (ret)
+			dev_warn(priv->dev, "skcipher: invalidation error %d\n",
+				 ret);
+	} else {
+		dma_pool_free(priv->context_pool, ctx->base.ctxr,
+			      ctx->base.ctxr_dma);
+	}
+}
+
+static void safexcel_aead_cra_exit(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	if (safexcel_cipher_cra_exit(tfm))
+		return;
 
 	if (priv->version == EIP197) {
-		ret = safexcel_cipher_exit_inv(tfm);
+		ret = safexcel_aead_exit_inv(tfm);
 		if (ret)
-			dev_warn(priv->dev, "cipher: invalidation error %d\n", ret);
+			dev_warn(priv->dev, "aead: invalidation error %d\n",
+				 ret);
 	} else {
 		dma_pool_free(priv->context_pool, ctx->base.ctxr,
 			      ctx->base.ctxr_dma);
@@ -563,7 +829,7 @@ static void safexcel_skcipher_cra_exit(struct crypto_tfm *tfm)
 struct safexcel_alg_template safexcel_alg_ecb_aes = {
 	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
 	.alg.skcipher = {
-		.setkey = safexcel_aes_setkey,
+		.setkey = safexcel_skcipher_aes_setkey,
 		.encrypt = safexcel_ecb_aes_encrypt,
 		.decrypt = safexcel_ecb_aes_decrypt,
 		.min_keysize = AES_MIN_KEY_SIZE,
@@ -586,20 +852,20 @@ struct safexcel_alg_template safexcel_alg_ecb_aes = {
 
 static int safexcel_cbc_aes_encrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(req, SAFEXCEL_ENCRYPT,
-			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_aes(&req->base, skcipher_request_ctx(req),
+			    SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC);
 }
 
 static int safexcel_cbc_aes_decrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(req, SAFEXCEL_DECRYPT,
-			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_aes(&req->base, skcipher_request_ctx(req),
+			    SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC);
 }
 
 struct safexcel_alg_template safexcel_alg_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
 	.alg.skcipher = {
-		.setkey = safexcel_aes_setkey,
+		.setkey = safexcel_skcipher_aes_setkey,
 		.encrypt = safexcel_cbc_aes_encrypt,
 		.decrypt = safexcel_cbc_aes_decrypt,
 		.min_keysize = AES_MIN_KEY_SIZE,
@@ -620,3 +886,139 @@ struct safexcel_alg_template safexcel_alg_cbc_aes = {
 		},
 	},
 };
+
+static int safexcel_aead_encrypt(struct aead_request *req)
+{
+	struct safexcel_cipher_req *creq = aead_request_ctx(req);
+
+	return safexcel_aes(&req->base, creq, SAFEXCEL_ENCRYPT,
+			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+}
+
+static int safexcel_aead_decrypt(struct aead_request *req)
+{
+	struct safexcel_cipher_req *creq = aead_request_ctx(req);
+
+	return safexcel_aes(&req->base, creq, SAFEXCEL_DECRYPT,
+			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+}
+
+static int safexcel_aead_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_alg_template *tmpl =
+		container_of(tfm->__crt_alg, struct safexcel_alg_template,
+			     alg.aead.base);
+
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct safexcel_cipher_req));
+
+	ctx->priv = tmpl->priv;
+
+	ctx->aead = true;
+	ctx->base.send = safexcel_aead_send;
+	ctx->base.handle_result = safexcel_aead_handle_result;
+	return 0;
+}
+
+static int safexcel_aead_sha1_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
+	ctx->state_sz = SHA1_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.alg.aead = {
+		.setkey = safexcel_aead_aes_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = AES_BLOCK_SIZE,
+		.maxauthsize = SHA1_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha1),cbc(aes))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha1-cbc-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha1_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha256_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
+	ctx->state_sz = SHA256_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.alg.aead = {
+		.setkey = safexcel_aead_aes_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = AES_BLOCK_SIZE,
+		.maxauthsize = SHA256_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha256),cbc(aes))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha256-cbc-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha256_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha224_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
+	ctx->state_sz = SHA256_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.alg.aead = {
+		.setkey = safexcel_aead_aes_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = AES_BLOCK_SIZE,
+		.maxauthsize = SHA224_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha224),cbc(aes))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha224-cbc-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha224_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 317b9e480312..d138d6b8fec5 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -50,16 +50,6 @@ struct safexcel_ahash_req {
 	u8 cache_next[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
 };
 
-struct safexcel_ahash_export_state {
-	u64 len;
-	u64 processed;
-
-	u32 digest;
-
-	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)];
-	u8 cache[SHA256_BLOCK_SIZE];
-};
-
 static void safexcel_hash_token(struct safexcel_command_desc *cdesc,
 				u32 input_length, u32 result_length)
 {
@@ -146,11 +136,8 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 		dev_err(priv->dev,
 			"hash: result: could not retrieve the result descriptor\n");
 		*ret = PTR_ERR(rdesc);
-	} else if (rdesc->result_data.error_code) {
-		dev_err(priv->dev,
-			"hash: result: result descriptor error (%d)\n",
-			rdesc->result_data.error_code);
-		*ret = -EINVAL;
+	} else {
+		*ret = safexcel_rdesc_check_errors(priv, rdesc);
 	}
 
 	safexcel_complete(priv, ring);
@@ -480,7 +467,7 @@ static int safexcel_ahash_exit_inv(struct crypto_tfm *tfm)
 {
 	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
-	AHASH_REQUEST_ON_STACK(req, __crypto_ahash_cast(tfm));
+	EIP197_REQUEST_ON_STACK(req, ahash, EIP197_AHASH_REQ_SIZE);
 	struct safexcel_ahash_req *rctx = ahash_request_ctx(req);
 	struct safexcel_inv_result result = {};
 	int ring = ctx->base.ring;
@@ -912,8 +899,8 @@ static int safexcel_hmac_init_iv(struct ahash_request *areq,
 	return crypto_ahash_export(areq, state);
 }
 
-static int safexcel_hmac_setkey(const char *alg, const u8 *key,
-				unsigned int keylen, void *istate, void *ostate)
+int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
+			 void *istate, void *ostate)
 {
 	struct ahash_request *areq;
 	struct crypto_ahash *tfm;
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index 1e87637c412d..36afd6d8753c 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -334,7 +334,7 @@ static int wait_for_csb(struct nx842_workmem *wmem,
 		return -EPROTO;
 	case CSB_CC_SEQUENCE:
 		/* should not happen, we don't use chained CRBs */
-		CSB_ERR(csb, "CRB seqeunce number error");
+		CSB_ERR(csb, "CRB sequence number error");
 		return -EPROTO;
 	case CSB_CC_UNKNOWN_CODE:
 		CSB_ERR(csb, "Unknown subfunction code");
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index ad02aa63b519..d1a1c74fb56a 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -1087,7 +1087,7 @@ static void omap_sham_finish_req(struct ahash_request *req, int err)
 
 	if (test_bit(FLAGS_SGS_COPIED, &dd->flags))
 		free_pages((unsigned long)sg_virt(ctx->sg),
-			   get_order(ctx->sg->length));
+			   get_order(ctx->sg->length + ctx->bufcnt));
 
 	if (test_bit(FLAGS_SGS_ALLOCED, &dd->flags))
 		kfree(ctx->sg);
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index a4df966adbf6..321d5e2ac833 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -1169,8 +1169,7 @@ static void spacc_spacc_complete(unsigned long data)
 #ifdef CONFIG_PM
 static int spacc_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct spacc_engine *engine = platform_get_drvdata(pdev);
+	struct spacc_engine *engine = dev_get_drvdata(dev);
 
 	/*
 	 * We only support standby mode. All we have to do is gate the clock to
@@ -1184,8 +1183,7 @@ static int spacc_suspend(struct device *dev)
 
 static int spacc_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct spacc_engine *engine = platform_get_drvdata(pdev);
+	struct spacc_engine *engine = dev_get_drvdata(dev);
 
 	return clk_enable(engine->clk);
 }
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_drv.c b/drivers/crypto/qat/qat_c3xxx/adf_drv.c
index f172171668ee..ba197f34c252 100644
--- a/drivers/crypto/qat/qat_c3xxx/adf_drv.c
+++ b/drivers/crypto/qat/qat_c3xxx/adf_drv.c
@@ -329,5 +329,7 @@ module_exit(adfdrv_release);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
+MODULE_FIRMWARE(ADF_C3XXX_FW);
+MODULE_FIRMWARE(ADF_C3XXX_MMP);
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
 MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c
index 58a984c9c3ec..59a5a0df50b6 100644
--- a/drivers/crypto/qat/qat_c62x/adf_drv.c
+++ b/drivers/crypto/qat/qat_c62x/adf_drv.c
@@ -329,5 +329,7 @@ module_exit(adfdrv_release);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
+MODULE_FIRMWARE(ADF_C62X_FW);
+MODULE_FIRMWARE(ADF_C62X_MMP);
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
 MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
index 2ce01f010c74..be5c5a988ca5 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
@@ -332,5 +332,6 @@ module_exit(adfdrv_release);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
 MODULE_FIRMWARE(ADF_DH895XCC_FW);
+MODULE_FIRMWARE(ADF_DH895XCC_MMP);
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
 MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c
index 96072b9b55c4..d7316f7a3a69 100644
--- a/drivers/crypto/vmx/aes.c
+++ b/drivers/crypto/vmx/aes.c
@@ -48,8 +48,6 @@ static int p8_aes_init(struct crypto_tfm *tfm)
 		       alg, PTR_ERR(fallback));
 		return PTR_ERR(fallback);
 	}
-	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-	       crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
 
 	crypto_cipher_set_flags(fallback,
 				crypto_cipher_get_flags((struct
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 7394d35d5936..5285ece4f33a 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -52,9 +52,6 @@ static int p8_aes_cbc_init(struct crypto_tfm *tfm)
 		       alg, PTR_ERR(fallback));
 		return PTR_ERR(fallback);
 	}
-	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-		crypto_skcipher_driver_name(fallback));
-
 
 	crypto_skcipher_set_flags(
 		fallback,
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index fc60d00a2e84..cd777c75291d 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -50,8 +50,6 @@ static int p8_aes_ctr_init(struct crypto_tfm *tfm)
 		       alg, PTR_ERR(fallback));
 		return PTR_ERR(fallback);
 	}
-	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-		crypto_skcipher_driver_name(fallback));
 
 	crypto_skcipher_set_flags(
 		fallback,
diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c
index 8cd6e62e4c90..8bd9aff0f55f 100644
--- a/drivers/crypto/vmx/aes_xts.c
+++ b/drivers/crypto/vmx/aes_xts.c
@@ -53,8 +53,6 @@ static int p8_aes_xts_init(struct crypto_tfm *tfm)
 			alg, PTR_ERR(fallback));
 		return PTR_ERR(fallback);
 	}
-	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-		crypto_skcipher_driver_name(fallback));
 
 	crypto_skcipher_set_flags(
 		fallback,
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index 0b4a293b8a1e..d6a9f63d65ba 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -1,12 +1,51 @@
 #! /usr/bin/env perl
-# Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from CRYPTOGAMs[1] and is included here using the option
+# in the license to distribute the code under the GPL. Therefore this program
+# is free software; you can redistribute it and/or modify it under the terms of
+# the GNU General Public License version 2 as published by the Free Software
+# Foundation.
 #
-# Licensed under the OpenSSL license (the "License").  You may not use
-# this file except in compliance with the License.  You can obtain a copy
-# in the file LICENSE in the source distribution or at
-# https://www.openssl.org/source/license.html
+# [1] https://www.openssl.org/~appro/cryptogams/
 
+# Copyright (c) 2006-2017, CRYPTOGAMS by <appro@openssl.org>
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+#       * Redistributions of source code must retain copyright notices,
+#         this list of conditions and the following disclaimer.
+#
+#       * Redistributions in binary form must reproduce the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer in the documentation and/or other materials
+#         provided with the distribution.
 #
+#       * Neither the name of the CRYPTOGAMS nor the names of its
+#         copyright holder and contributors may be used to endorse or
+#         promote products derived from this software without specific
+#         prior written permission.
+#
+# ALTERNATIVELY, provided that this notice is retained in full, this
+# product may be distributed under the terms of the GNU General Public
+# License (GPL), in which case the provisions of the GPL apply INSTEAD OF
+# those given above.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
 # ====================================================================
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index 27a94a119009..1c4b5b889fba 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -64,8 +64,6 @@ static int p8_ghash_init_tfm(struct crypto_tfm *tfm)
 		       alg, PTR_ERR(fallback));
 		return PTR_ERR(fallback);
 	}
-	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-	       crypto_tfm_alg_driver_name(crypto_shash_tfm(fallback)));
 
 	crypto_shash_set_flags(fallback,
 			       crypto_shash_get_flags((struct crypto_shash
diff --git a/drivers/crypto/vmx/ghashp8-ppc.pl b/drivers/crypto/vmx/ghashp8-ppc.pl
index d8429cb71f02..f746af271460 100644
--- a/drivers/crypto/vmx/ghashp8-ppc.pl
+++ b/drivers/crypto/vmx/ghashp8-ppc.pl
@@ -1,5 +1,14 @@
 #!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore this program is free software;
+# you can redistribute it and/or modify it under the terms of the GNU General
+# Public License version 2 as published by the Free Software Foundation.
 #
+# The original headers, including the original license headers, are
+# included below for completeness.
+
 # ====================================================================
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index be8606457f27..aff2c1594220 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -19,6 +19,7 @@
 #include <linux/dax.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/mman.h>
 #include "dax-private.h"
 #include "dax.h"
 
@@ -540,6 +541,7 @@ static const struct file_operations dax_fops = {
 	.release = dax_release,
 	.get_unmapped_area = dax_get_unmapped_area,
 	.mmap = dax_mmap,
+	.mmap_supported_flags = MAP_SYNC,
 };
 
 static void dev_dax_release(struct device *dev)
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 2b2332b605e4..1d7bd96511f0 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -74,42 +74,42 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
 
 /**
  * __bdev_dax_supported() - Check if the device supports dax for filesystem
- * @sb: The superblock of the device
+ * @bdev: block device to check
  * @blocksize: The block size of the device
  *
  * This is a library function for filesystems to check if the block device
  * can be mounted with dax option.
  *
- * Return: negative errno if unsupported, 0 if supported.
+ * Return: true if supported, false if unsupported
  */
-int __bdev_dax_supported(struct super_block *sb, int blocksize)
+bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 {
-	struct block_device *bdev = sb->s_bdev;
 	struct dax_device *dax_dev;
 	pgoff_t pgoff;
 	int err, id;
 	void *kaddr;
 	pfn_t pfn;
 	long len;
+	char buf[BDEVNAME_SIZE];
 
 	if (blocksize != PAGE_SIZE) {
-		pr_debug("VFS (%s): error: unsupported blocksize for dax\n",
-				sb->s_id);
-		return -EINVAL;
+		pr_debug("%s: error: unsupported blocksize for dax\n",
+				bdevname(bdev, buf));
+		return false;
 	}
 
 	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
 	if (err) {
-		pr_debug("VFS (%s): error: unaligned partition for dax\n",
-				sb->s_id);
-		return err;
+		pr_debug("%s: error: unaligned partition for dax\n",
+				bdevname(bdev, buf));
+		return false;
 	}
 
 	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
 	if (!dax_dev) {
-		pr_debug("VFS (%s): error: device does not support dax\n",
-				sb->s_id);
-		return -EOPNOTSUPP;
+		pr_debug("%s: error: device does not support dax\n",
+				bdevname(bdev, buf));
+		return false;
 	}
 
 	id = dax_read_lock();
@@ -119,9 +119,9 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 	put_dax(dax_dev);
 
 	if (len < 1) {
-		pr_debug("VFS (%s): error: dax access failed (%ld)\n",
-				sb->s_id, len);
-		return len < 0 ? len : -EIO;
+		pr_debug("%s: error: dax access failed (%ld)\n",
+				bdevname(bdev, buf), len);
+		return false;
 	}
 
 	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) {
@@ -137,12 +137,12 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 	} else if (pfn_t_devmap(pfn)) {
 		/* pass */;
 	} else {
-		pr_debug("VFS (%s): error: dax support not enabled\n",
-				sb->s_id);
-		return -EOPNOTSUPP;
+		pr_debug("%s: error: dax support not enabled\n",
+				bdevname(bdev, buf));
+		return false;
 	}
 
-	return 0;
+	return true;
 }
 EXPORT_SYMBOL_GPL(__bdev_dax_supported);
 #endif
diff --git a/drivers/dma-buf/sync_debug.h b/drivers/dma-buf/sync_debug.h
index d615a89f774c..05e33f937ad0 100644
--- a/drivers/dma-buf/sync_debug.h
+++ b/drivers/dma-buf/sync_debug.h
@@ -62,8 +62,6 @@ struct sync_pt {
 	struct rb_node node;
 };
 
-#ifdef CONFIG_SW_SYNC
-
 extern const struct file_operations sw_sync_debugfs_fops;
 
 void sync_timeline_debug_add(struct sync_timeline *obj);
@@ -72,12 +70,4 @@ void sync_file_debug_add(struct sync_file *fence);
 void sync_file_debug_remove(struct sync_file *fence);
 void sync_dump(void);
 
-#else
-# define sync_timeline_debug_add(obj)
-# define sync_timeline_debug_remove(obj)
-# define sync_file_debug_add(fence)
-# define sync_file_debug_remove(fence)
-# define sync_dump()
-#endif
-
 #endif /* _LINUX_SYNC_H */
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index d29275b97e84..4a828c18099a 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -524,6 +524,14 @@ static int bam_alloc_chan(struct dma_chan *chan)
 	return 0;
 }
 
+static int bam_pm_runtime_get_sync(struct device *dev)
+{
+	if (pm_runtime_enabled(dev))
+		return pm_runtime_get_sync(dev);
+
+	return 0;
+}
+
 /**
  * bam_free_chan - Frees dma resources associated with specific channel
  * @chan: specified channel
@@ -539,7 +547,7 @@ static void bam_free_chan(struct dma_chan *chan)
 	unsigned long flags;
 	int ret;
 
-	ret = pm_runtime_get_sync(bdev->dev);
+	ret = bam_pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return;
 
@@ -720,7 +728,7 @@ static int bam_pause(struct dma_chan *chan)
 	unsigned long flag;
 	int ret;
 
-	ret = pm_runtime_get_sync(bdev->dev);
+	ret = bam_pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return ret;
 
@@ -746,7 +754,7 @@ static int bam_resume(struct dma_chan *chan)
 	unsigned long flag;
 	int ret;
 
-	ret = pm_runtime_get_sync(bdev->dev);
+	ret = bam_pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return ret;
 
@@ -852,7 +860,7 @@ static irqreturn_t bam_dma_irq(int irq, void *data)
 	if (srcs & P_IRQ)
 		tasklet_schedule(&bdev->task);
 
-	ret = pm_runtime_get_sync(bdev->dev);
+	ret = bam_pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return ret;
 
@@ -969,7 +977,7 @@ static void bam_start_dma(struct bam_chan *bchan)
 	if (!vd)
 		return;
 
-	ret = pm_runtime_get_sync(bdev->dev);
+	ret = bam_pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
 		return;
 
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index 000c7019ca7d..d64edeb6771a 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -398,7 +398,7 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 		}
 		of_node_get(child);
 		new_pdev->dev.of_node = child;
-		of_dma_configure(&new_pdev->dev, child);
+		of_dma_configure(&new_pdev->dev, child, true);
 		/*
 		 * It is assumed that calling of_msi_configure is safe on
 		 * platforms with or without MSI support.
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index da2da53bca6d..57304b2e989f 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -232,6 +232,7 @@ config EDAC_SBRIDGE
 config EDAC_SKX
 	tristate "Intel Skylake server Integrated MC"
 	depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG
+	depends on ACPI_NFIT || !ACPI_NFIT # if ACPI_NFIT=m, EDAC_SKX can't be y
 	select DMI
 	help
 	  Support for error detection and correction the Intel
@@ -374,7 +375,7 @@ config EDAC_THUNDERX
 
 config EDAC_ALTERA
 	bool "Altera SOCFPGA ECC"
-	depends on EDAC=y && ARCH_SOCFPGA
+	depends on EDAC=y && (ARCH_SOCFPGA || ARCH_STRATIX10)
 	help
 	  Support for error detection and correction on the
 	  Altera SOCs. This must be selected for SDRAM ECC.
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 11d6419788c2..d0d5c4dbe097 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
+ *  Copyright (C) 2017-2018, Intel Corporation. All rights reserved
  *  Copyright Altera Corporation (C) 2014-2016. All rights reserved.
  *  Copyright 2011-2012 Calxeda, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * Adapted from the highbank_mc_edac driver.
  */
 
 #include <asm/cacheflush.h>
@@ -26,6 +14,7 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/kernel.h>
 #include <linux/mfd/syscon.h>
+#include <linux/notifier.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
@@ -80,6 +69,25 @@ static const struct altr_sdram_prv_data a10_data = {
 	.ue_set_mask        = A10_DIAGINT_TDERRA_MASK,
 };
 
+static const struct altr_sdram_prv_data s10_data = {
+	.ecc_ctrl_offset    = S10_ECCCTRL1_OFST,
+	.ecc_ctl_en_mask    = A10_ECCCTRL1_ECC_EN,
+	.ecc_stat_offset    = S10_INTSTAT_OFST,
+	.ecc_stat_ce_mask   = A10_INTSTAT_SBEERR,
+	.ecc_stat_ue_mask   = A10_INTSTAT_DBEERR,
+	.ecc_saddr_offset   = S10_SERRADDR_OFST,
+	.ecc_daddr_offset   = S10_DERRADDR_OFST,
+	.ecc_irq_en_offset  = S10_ERRINTEN_OFST,
+	.ecc_irq_en_mask    = A10_ECC_IRQ_EN_MASK,
+	.ecc_irq_clr_offset = S10_INTSTAT_OFST,
+	.ecc_irq_clr_mask   = (A10_INTSTAT_SBEERR | A10_INTSTAT_DBEERR),
+	.ecc_cnt_rst_offset = S10_ECCCTRL1_OFST,
+	.ecc_cnt_rst_mask   = A10_ECC_CNT_RESET_MASK,
+	.ce_ue_trgr_offset  = S10_DIAGINTTEST_OFST,
+	.ce_set_mask        = A10_DIAGINT_TSERRA_MASK,
+	.ue_set_mask        = A10_DIAGINT_TDERRA_MASK,
+};
+
 /*********************** EDAC Memory Controller Functions ****************/
 
 /* The SDRAM controller uses the EDAC Memory Controller framework.       */
@@ -231,6 +239,7 @@ static unsigned long get_total_mem(void)
 static const struct of_device_id altr_sdram_ctrl_of_match[] = {
 	{ .compatible = "altr,sdram-edac", .data = &c5_data},
 	{ .compatible = "altr,sdram-edac-a10", .data = &a10_data},
+	{ .compatible = "altr,sdram-edac-s10", .data = &s10_data},
 	{},
 };
 MODULE_DEVICE_TABLE(of, altr_sdram_ctrl_of_match);
@@ -477,6 +486,292 @@ static int altr_sdram_remove(struct platform_device *pdev)
 	return 0;
 }
 
+/**************** Stratix 10 EDAC Memory Controller Functions ************/
+
+/**
+ * s10_protected_reg_write
+ * Write to a protected SMC register.
+ * @context: Not used.
+ * @reg: Address of register
+ * @value: Value to write
+ * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
+ *	   INTEL_SIP_SMC_REG_ERROR on error
+ *	   INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
+ */
+static int s10_protected_reg_write(void *context, unsigned int reg,
+				   unsigned int val)
+{
+	struct arm_smccc_res result;
+
+	arm_smccc_smc(INTEL_SIP_SMC_REG_WRITE, reg, val, 0, 0,
+		      0, 0, 0, &result);
+
+	return (int)result.a0;
+}
+
+/**
+ * s10_protected_reg_read
+ * Read the status of a protected SMC register
+ * @context: Not used.
+ * @reg: Address of register
+ * @value: Value read.
+ * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
+ *	   INTEL_SIP_SMC_REG_ERROR on error
+ *	   INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
+ */
+static int s10_protected_reg_read(void *context, unsigned int reg,
+				  unsigned int *val)
+{
+	struct arm_smccc_res result;
+
+	arm_smccc_smc(INTEL_SIP_SMC_REG_READ, reg, 0, 0, 0,
+		      0, 0, 0, &result);
+
+	*val = (unsigned int)result.a1;
+
+	return (int)result.a0;
+}
+
+static bool s10_sdram_writeable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case S10_ECCCTRL1_OFST:
+	case S10_ERRINTEN_OFST:
+	case S10_INTMODE_OFST:
+	case S10_INTSTAT_OFST:
+	case S10_DIAGINTTEST_OFST:
+	case S10_SYSMGR_ECC_INTMASK_VAL_OFST:
+	case S10_SYSMGR_ECC_INTMASK_SET_OFST:
+	case S10_SYSMGR_ECC_INTMASK_CLR_OFST:
+		return true;
+	}
+	return false;
+}
+
+static bool s10_sdram_readable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case S10_ECCCTRL1_OFST:
+	case S10_ERRINTEN_OFST:
+	case S10_INTMODE_OFST:
+	case S10_INTSTAT_OFST:
+	case S10_DERRADDR_OFST:
+	case S10_SERRADDR_OFST:
+	case S10_DIAGINTTEST_OFST:
+	case S10_SYSMGR_ECC_INTMASK_VAL_OFST:
+	case S10_SYSMGR_ECC_INTMASK_SET_OFST:
+	case S10_SYSMGR_ECC_INTMASK_CLR_OFST:
+	case S10_SYSMGR_ECC_INTSTAT_SERR_OFST:
+	case S10_SYSMGR_ECC_INTSTAT_DERR_OFST:
+		return true;
+	}
+	return false;
+}
+
+static bool s10_sdram_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case S10_ECCCTRL1_OFST:
+	case S10_ERRINTEN_OFST:
+	case S10_INTMODE_OFST:
+	case S10_INTSTAT_OFST:
+	case S10_DERRADDR_OFST:
+	case S10_SERRADDR_OFST:
+	case S10_DIAGINTTEST_OFST:
+	case S10_SYSMGR_ECC_INTMASK_VAL_OFST:
+	case S10_SYSMGR_ECC_INTMASK_SET_OFST:
+	case S10_SYSMGR_ECC_INTMASK_CLR_OFST:
+	case S10_SYSMGR_ECC_INTSTAT_SERR_OFST:
+	case S10_SYSMGR_ECC_INTSTAT_DERR_OFST:
+		return true;
+	}
+	return false;
+}
+
+static const struct regmap_config s10_sdram_regmap_cfg = {
+	.name = "s10_ddr",
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = 0xffffffff,
+	.writeable_reg = s10_sdram_writeable_reg,
+	.readable_reg = s10_sdram_readable_reg,
+	.volatile_reg = s10_sdram_volatile_reg,
+	.reg_read = s10_protected_reg_read,
+	.reg_write = s10_protected_reg_write,
+	.use_single_rw = true,
+};
+
+static int altr_s10_sdram_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *id;
+	struct edac_mc_layer layers[2];
+	struct mem_ctl_info *mci;
+	struct altr_sdram_mc_data *drvdata;
+	const struct altr_sdram_prv_data *priv;
+	struct regmap *regmap;
+	struct dimm_info *dimm;
+	u32 read_reg;
+	int irq, ret = 0;
+	unsigned long mem_size;
+
+	id = of_match_device(altr_sdram_ctrl_of_match, &pdev->dev);
+	if (!id)
+		return -ENODEV;
+
+	/* Grab specific offsets and masks for Stratix10 */
+	priv = of_match_node(altr_sdram_ctrl_of_match,
+			     pdev->dev.of_node)->data;
+
+	regmap = devm_regmap_init(&pdev->dev, NULL, (void *)priv,
+				  &s10_sdram_regmap_cfg);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/* Validate the SDRAM controller has ECC enabled */
+	if (regmap_read(regmap, priv->ecc_ctrl_offset, &read_reg) ||
+	    ((read_reg & priv->ecc_ctl_en_mask) != priv->ecc_ctl_en_mask)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "No ECC/ECC disabled [0x%08X]\n", read_reg);
+		return -ENODEV;
+	}
+
+	/* Grab memory size from device tree. */
+	mem_size = get_total_mem();
+	if (!mem_size) {
+		edac_printk(KERN_ERR, EDAC_MC, "Unable to calculate memory size\n");
+		return -ENODEV;
+	}
+
+	/* Ensure the SDRAM Interrupt is disabled */
+	if (regmap_update_bits(regmap, priv->ecc_irq_en_offset,
+			       priv->ecc_irq_en_mask, 0)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Error disabling SDRAM ECC IRQ\n");
+		return -ENODEV;
+	}
+
+	/* Toggle to clear the SDRAM Error count */
+	if (regmap_update_bits(regmap, priv->ecc_cnt_rst_offset,
+			       priv->ecc_cnt_rst_mask,
+			       priv->ecc_cnt_rst_mask)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Error clearing SDRAM ECC count\n");
+		return -ENODEV;
+	}
+
+	if (regmap_update_bits(regmap, priv->ecc_cnt_rst_offset,
+			       priv->ecc_cnt_rst_mask, 0)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Error clearing SDRAM ECC count\n");
+		return -ENODEV;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "No irq %d in DT\n", irq);
+		return -ENODEV;
+	}
+
+	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
+	layers[0].size = 1;
+	layers[0].is_virt_csrow = true;
+	layers[1].type = EDAC_MC_LAYER_CHANNEL;
+	layers[1].size = 1;
+	layers[1].is_virt_csrow = false;
+	mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers,
+			    sizeof(struct altr_sdram_mc_data));
+	if (!mci)
+		return -ENOMEM;
+
+	mci->pdev = &pdev->dev;
+	drvdata = mci->pvt_info;
+	drvdata->mc_vbase = regmap;
+	drvdata->data = priv;
+	platform_set_drvdata(pdev, mci);
+
+	if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Unable to get managed device resource\n");
+		ret = -ENOMEM;
+		goto free;
+	}
+
+	mci->mtype_cap = MEM_FLAG_DDR3;
+	mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
+	mci->edac_cap = EDAC_FLAG_SECDED;
+	mci->mod_name = EDAC_MOD_STR;
+	mci->ctl_name = dev_name(&pdev->dev);
+	mci->scrub_mode = SCRUB_SW_SRC;
+	mci->dev_name = dev_name(&pdev->dev);
+
+	dimm = *mci->dimms;
+	dimm->nr_pages = ((mem_size - 1) >> PAGE_SHIFT) + 1;
+	dimm->grain = 8;
+	dimm->dtype = DEV_X8;
+	dimm->mtype = MEM_DDR3;
+	dimm->edac_mode = EDAC_SECDED;
+
+	ret = edac_mc_add_mc(mci);
+	if (ret < 0)
+		goto err;
+
+	ret = devm_request_irq(&pdev->dev, irq, altr_sdram_mc_err_handler,
+			       IRQF_SHARED, dev_name(&pdev->dev), mci);
+	if (ret < 0) {
+		edac_mc_printk(mci, KERN_ERR,
+			       "Unable to request irq %d\n", irq);
+		ret = -ENODEV;
+		goto err2;
+	}
+
+	if (regmap_write(regmap, S10_SYSMGR_ECC_INTMASK_CLR_OFST,
+			 S10_DDR0_IRQ_MASK)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Error clearing SDRAM ECC count\n");
+		return -ENODEV;
+	}
+
+	if (regmap_update_bits(drvdata->mc_vbase, priv->ecc_irq_en_offset,
+			       priv->ecc_irq_en_mask, priv->ecc_irq_en_mask)) {
+		edac_mc_printk(mci, KERN_ERR,
+			       "Error enabling SDRAM ECC IRQ\n");
+		ret = -ENODEV;
+		goto err2;
+	}
+
+	altr_sdr_mc_create_debugfs_nodes(mci);
+
+	devres_close_group(&pdev->dev, NULL);
+
+	return 0;
+
+err2:
+	edac_mc_del_mc(&pdev->dev);
+err:
+	devres_release_group(&pdev->dev, NULL);
+free:
+	edac_mc_free(mci);
+	edac_printk(KERN_ERR, EDAC_MC,
+		    "EDAC Probe Failed; Error %d\n", ret);
+
+	return ret;
+}
+
+static int altr_s10_sdram_remove(struct platform_device *pdev)
+{
+	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
+
+	edac_mc_del_mc(&pdev->dev);
+	edac_mc_free(mci);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+/************** </Stratix10 EDAC Memory Controller Functions> ***********/
+
 /*
  * If you want to suspend, need to disable EDAC by removing it
  * from the device tree or defconfig.
@@ -508,6 +803,20 @@ static struct platform_driver altr_sdram_edac_driver = {
 
 module_platform_driver(altr_sdram_edac_driver);
 
+static struct platform_driver altr_s10_sdram_edac_driver = {
+	.probe = altr_s10_sdram_probe,
+	.remove = altr_s10_sdram_remove,
+	.driver = {
+		.name = "altr_s10_sdram_edac",
+#ifdef CONFIG_PM
+		.pm = &altr_sdram_pm_ops,
+#endif
+		.of_match_table = altr_sdram_ctrl_of_match,
+	},
+};
+
+module_platform_driver(altr_s10_sdram_edac_driver);
+
 /************************* EDAC Parent Probe *************************/
 
 static const struct of_device_id altr_edac_device_of_match[];
@@ -1106,7 +1415,7 @@ static void *ocram_alloc_mem(size_t size, void **other)
 
 static void ocram_free_mem(void *p, size_t size, void *other)
 {
-	gen_pool_free((struct gen_pool *)other, (u32)p, size);
+	gen_pool_free((struct gen_pool *)other, (unsigned long)p, size);
 }
 
 static const struct edac_device_prv_data ocramecc_data = {
@@ -1925,6 +2234,171 @@ static struct platform_driver altr_edac_a10_driver = {
 };
 module_platform_driver(altr_edac_a10_driver);
 
+/************** Stratix 10 EDAC Device Controller Functions> ************/
+
+#define to_s10edac(p, m) container_of(p, struct altr_stratix10_edac, m)
+
+/*
+ * The double bit error is handled through SError which is fatal. This is
+ * called as a panic notifier to printout ECC error info as part of the panic.
+ */
+static int s10_edac_dberr_handler(struct notifier_block *this,
+				  unsigned long event, void *ptr)
+{
+	struct altr_stratix10_edac *edac = to_s10edac(this, panic_notifier);
+	int err_addr, dberror;
+
+	s10_protected_reg_read(edac, S10_SYSMGR_ECC_INTSTAT_DERR_OFST,
+			       &dberror);
+	/* Remember the UE Errors for a reboot */
+	s10_protected_reg_write(edac, S10_SYSMGR_UE_VAL_OFST, dberror);
+	if (dberror & S10_DDR0_IRQ_MASK) {
+		s10_protected_reg_read(edac, S10_DERRADDR_OFST, &err_addr);
+		/* Remember the UE Error address */
+		s10_protected_reg_write(edac, S10_SYSMGR_UE_ADDR_OFST,
+					err_addr);
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "EDAC: [Uncorrectable errors @ 0x%08X]\n\n",
+			    err_addr);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static void altr_edac_s10_irq_handler(struct irq_desc *desc)
+{
+	struct altr_stratix10_edac *edac = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	int irq = irq_desc_get_irq(desc);
+	int bit, sm_offset, irq_status;
+
+	sm_offset = S10_SYSMGR_ECC_INTSTAT_SERR_OFST;
+
+	chained_irq_enter(chip, desc);
+
+	s10_protected_reg_read(NULL, sm_offset, &irq_status);
+
+	for_each_set_bit(bit, (unsigned long *)&irq_status, 32) {
+		irq = irq_linear_revmap(edac->domain, bit);
+		if (irq)
+			generic_handle_irq(irq);
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void s10_eccmgr_irq_mask(struct irq_data *d)
+{
+	struct altr_stratix10_edac *edac = irq_data_get_irq_chip_data(d);
+
+	s10_protected_reg_write(edac, S10_SYSMGR_ECC_INTMASK_SET_OFST,
+				BIT(d->hwirq));
+}
+
+static void s10_eccmgr_irq_unmask(struct irq_data *d)
+{
+	struct altr_stratix10_edac *edac = irq_data_get_irq_chip_data(d);
+
+	s10_protected_reg_write(edac, S10_SYSMGR_ECC_INTMASK_CLR_OFST,
+				BIT(d->hwirq));
+}
+
+static int s10_eccmgr_irqdomain_map(struct irq_domain *d, unsigned int irq,
+				    irq_hw_number_t hwirq)
+{
+	struct altr_stratix10_edac *edac = d->host_data;
+
+	irq_set_chip_and_handler(irq, &edac->irq_chip, handle_simple_irq);
+	irq_set_chip_data(irq, edac);
+	irq_set_noprobe(irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops s10_eccmgr_ic_ops = {
+	.map = s10_eccmgr_irqdomain_map,
+	.xlate = irq_domain_xlate_twocell,
+};
+
+static int altr_edac_s10_probe(struct platform_device *pdev)
+{
+	struct altr_stratix10_edac *edac;
+	struct device_node *child;
+	int dberror, err_addr;
+
+	edac = devm_kzalloc(&pdev->dev, sizeof(*edac), GFP_KERNEL);
+	if (!edac)
+		return -ENOMEM;
+
+	edac->dev = &pdev->dev;
+	platform_set_drvdata(pdev, edac);
+	INIT_LIST_HEAD(&edac->s10_ecc_devices);
+
+	edac->irq_chip.name = pdev->dev.of_node->name;
+	edac->irq_chip.irq_mask = s10_eccmgr_irq_mask;
+	edac->irq_chip.irq_unmask = s10_eccmgr_irq_unmask;
+	edac->domain = irq_domain_add_linear(pdev->dev.of_node, 64,
+					     &s10_eccmgr_ic_ops, edac);
+	if (!edac->domain) {
+		dev_err(&pdev->dev, "Error adding IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	edac->sb_irq = platform_get_irq(pdev, 0);
+	if (edac->sb_irq < 0) {
+		dev_err(&pdev->dev, "No SBERR IRQ resource\n");
+		return edac->sb_irq;
+	}
+
+	irq_set_chained_handler_and_data(edac->sb_irq,
+					 altr_edac_s10_irq_handler,
+					 edac);
+
+	edac->panic_notifier.notifier_call = s10_edac_dberr_handler;
+	atomic_notifier_chain_register(&panic_notifier_list,
+				       &edac->panic_notifier);
+
+	/* Printout a message if uncorrectable error previously. */
+	s10_protected_reg_read(edac, S10_SYSMGR_UE_VAL_OFST, &dberror);
+	if (dberror) {
+		s10_protected_reg_read(edac, S10_SYSMGR_UE_ADDR_OFST,
+				       &err_addr);
+		edac_printk(KERN_ERR, EDAC_DEVICE,
+			    "Previous Boot UE detected[0x%X] @ 0x%X\n",
+			    dberror, err_addr);
+		/* Reset the sticky registers */
+		s10_protected_reg_write(edac, S10_SYSMGR_UE_VAL_OFST, 0);
+		s10_protected_reg_write(edac, S10_SYSMGR_UE_ADDR_OFST, 0);
+	}
+
+	for_each_child_of_node(pdev->dev.of_node, child) {
+		if (!of_device_is_available(child))
+			continue;
+
+		if (of_device_is_compatible(child, "altr,sdram-edac-s10"))
+			of_platform_populate(pdev->dev.of_node,
+					     altr_sdram_ctrl_of_match,
+					     NULL, &pdev->dev);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id altr_edac_s10_of_match[] = {
+	{ .compatible = "altr,socfpga-s10-ecc-manager" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, altr_edac_s10_of_match);
+
+static struct platform_driver altr_edac_s10_driver = {
+	.probe =  altr_edac_s10_probe,
+	.driver = {
+		.name = "socfpga_s10_ecc_manager",
+		.of_match_table = altr_edac_s10_of_match,
+	},
+};
+module_platform_driver(altr_edac_s10_driver);
+
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Thor Thayer");
 MODULE_DESCRIPTION("EDAC Driver for Altera Memories");
diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h
index cbc96290f743..81f0554e09de 100644
--- a/drivers/edac/altera_edac.h
+++ b/drivers/edac/altera_edac.h
@@ -1,23 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- *
+ * Copyright (C) 2017-2018, Intel Corporation
  * Copyright (C) 2015 Altera Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _ALTERA_EDAC_H
 #define _ALTERA_EDAC_H
 
+#include <linux/arm-smccc.h>
 #include <linux/edac.h>
 #include <linux/types.h>
 
@@ -94,6 +84,7 @@
 /* SDRAM Controller Address Width Register */
 #define CV_DRAMADDRW               0xFFC2502C
 #define A10_DRAMADDRW              0xFFCFA0A8
+#define S10_DRAMADDRW              0xF80110E0
 
 /* SDRAM Controller Address Widths Field Register */
 #define DRAMADDRW_COLBIT_MASK      0x001F
@@ -115,6 +106,7 @@
 /* SDRAM Controller Interface Data Width Register */
 #define CV_DRAMIFWIDTH             0xFFC25030
 #define A10_DRAMIFWIDTH            0xFFCFB008
+#define S10_DRAMIFWIDTH            0xF8011008
 
 /* SDRAM Controller Interface Data Width Defines */
 #define CV_DRAMIFWIDTH_16B_ECC     24
@@ -164,6 +156,34 @@
 #define A10_INTMASK_CLR_OFST       0x10
 #define A10_DDR0_IRQ_MASK          BIT(17)
 
+/************* Stratix10 Defines **************/
+
+/* SDRAM Controller EccCtrl Register */
+#define S10_ECCCTRL1_OFST          0xF8011100
+
+/* SDRAM Controller DRAM IRQ Register */
+#define S10_ERRINTEN_OFST          0xF8011110
+
+/* SDRAM Interrupt Mode Register */
+#define S10_INTMODE_OFST           0xF801111C
+
+/* SDRAM Controller Error Status Register */
+#define S10_INTSTAT_OFST           0xF8011120
+
+/* SDRAM Controller ECC Error Address Register */
+#define S10_DERRADDR_OFST          0xF801112C
+#define S10_SERRADDR_OFST          0xF8011130
+
+/* SDRAM Controller ECC Diagnostic Register */
+#define S10_DIAGINTTEST_OFST       0xF8011124
+
+/* SDRAM Single Bit Error Count Compare Set Register */
+#define S10_SERRCNTREG_OFST        0xF801113C
+
+/* Sticky registers for Uncorrected Errors */
+#define S10_SYSMGR_UE_VAL_OFST     0xFFD12220
+#define S10_SYSMGR_UE_ADDR_OFST    0xFFD12224
+
 struct altr_sdram_prv_data {
 	int ecc_ctrl_offset;
 	int ecc_ctl_en_mask;
@@ -296,6 +316,18 @@ struct altr_sdram_mc_data {
 /* A10 ECC Controller memory initialization timeout */
 #define ALTR_A10_ECC_INIT_WATCHDOG_10US      10000
 
+/************* Stratix10 Defines **************/
+
+/* Stratix10 ECC Manager Defines */
+#define S10_SYSMGR_ECC_INTMASK_VAL_OFST   0xFFD12090
+#define S10_SYSMGR_ECC_INTMASK_SET_OFST   0xFFD12094
+#define S10_SYSMGR_ECC_INTMASK_CLR_OFST   0xFFD12098
+
+#define S10_SYSMGR_ECC_INTSTAT_SERR_OFST  0xFFD1209C
+#define S10_SYSMGR_ECC_INTSTAT_DERR_OFST  0xFFD120A0
+
+#define S10_DDR0_IRQ_MASK                 BIT(16)
+
 struct altr_edac_device_dev;
 
 struct edac_device_prv_data {
@@ -340,4 +372,78 @@ struct altr_arria10_edac {
 	struct list_head	a10_ecc_devices;
 };
 
+/*
+ * Functions specified by ARM SMC Calling convention:
+ *
+ * FAST call executes atomic operations, returns when the requested operation
+ * has completed.
+ * STD call starts a operation which can be preempted by a non-secure
+ * interrupt. The call can return before the requested operation has
+ * completed.
+ *
+ * a0..a7 is used as register names in the descriptions below, on arm32
+ * that translates to r0..r7 and on arm64 to w0..w7.
+ */
+
+#define INTEL_SIP_SMC_STD_CALL_VAL(func_num) \
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_64, \
+	ARM_SMCCC_OWNER_SIP, (func_num))
+
+#define INTEL_SIP_SMC_FAST_CALL_VAL(func_num) \
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, \
+	ARM_SMCCC_OWNER_SIP, (func_num))
+
+#define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION		0xFFFFFFFF
+#define INTEL_SIP_SMC_STATUS_OK				0x0
+#define INTEL_SIP_SMC_REG_ERROR				0x5
+
+/*
+ * Request INTEL_SIP_SMC_REG_READ
+ *
+ * Read a protected register using SMCCC
+ *
+ * Call register usage:
+ * a0: INTEL_SIP_SMC_REG_READ.
+ * a1: register address.
+ * a2-7: not used.
+ *
+ * Return status:
+ * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or
+ *     INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION
+ * a1: Value in the register
+ * a2-3: not used.
+ */
+#define INTEL_SIP_SMC_FUNCID_REG_READ 7
+#define INTEL_SIP_SMC_REG_READ \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_READ)
+
+/*
+ * Request INTEL_SIP_SMC_REG_WRITE
+ *
+ * Write a protected register using SMCCC
+ *
+ * Call register usage:
+ * a0: INTEL_SIP_SMC_REG_WRITE.
+ * a1: register address
+ * a2: value to program into register.
+ * a3-7: not used.
+ *
+ * Return status:
+ * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or
+ *     INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION
+ * a1-3: not used.
+ */
+#define INTEL_SIP_SMC_FUNCID_REG_WRITE 8
+#define INTEL_SIP_SMC_REG_WRITE \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_WRITE)
+
+struct altr_stratix10_edac {
+	struct device		*dev;
+	int sb_irq;
+	struct irq_domain	*domain;
+	struct irq_chip		irq_chip;
+	struct list_head	s10_ecc_devices;
+	struct notifier_block	panic_notifier;
+};
+
 #endif	/* #ifndef _ALTERA_EDAC_H */
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 68b6ee18bea6..473aeec4b1da 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -91,6 +91,7 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
 		struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
 						       mci->n_layers,
 						       dimm_fill->count, 0, 0);
+		u16 rdr_mask = BIT(7) | BIT(13);
 
 		if (entry->size == 0xffff) {
 			pr_info("Can't get DIMM%i size\n",
@@ -99,22 +100,21 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
 		} else if (entry->size == 0x7fff) {
 			dimm->nr_pages = MiB_TO_PAGES(entry->extended_size);
 		} else {
-			if (entry->size & 1 << 15)
-				dimm->nr_pages = MiB_TO_PAGES((entry->size &
-							       0x7fff) << 10);
+			if (entry->size & BIT(15))
+				dimm->nr_pages = MiB_TO_PAGES((entry->size & 0x7fff) << 10);
 			else
 				dimm->nr_pages = MiB_TO_PAGES(entry->size);
 		}
 
 		switch (entry->memory_type) {
 		case 0x12:
-			if (entry->type_detail & 1 << 13)
+			if (entry->type_detail & BIT(13))
 				dimm->mtype = MEM_RDDR;
 			else
 				dimm->mtype = MEM_DDR;
 			break;
 		case 0x13:
-			if (entry->type_detail & 1 << 13)
+			if (entry->type_detail & BIT(13))
 				dimm->mtype = MEM_RDDR2;
 			else
 				dimm->mtype = MEM_DDR2;
@@ -123,20 +123,29 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
 			dimm->mtype = MEM_FB_DDR2;
 			break;
 		case 0x18:
-			if (entry->type_detail & 1 << 13)
+			if (entry->type_detail & BIT(12))
+				dimm->mtype = MEM_NVDIMM;
+			else if (entry->type_detail & BIT(13))
 				dimm->mtype = MEM_RDDR3;
 			else
 				dimm->mtype = MEM_DDR3;
 			break;
+		case 0x1a:
+			if (entry->type_detail & BIT(12))
+				dimm->mtype = MEM_NVDIMM;
+			else if (entry->type_detail & BIT(13))
+				dimm->mtype = MEM_RDDR4;
+			else
+				dimm->mtype = MEM_DDR4;
+			break;
 		default:
-			if (entry->type_detail & 1 << 6)
+			if (entry->type_detail & BIT(6))
 				dimm->mtype = MEM_RMBS;
-			else if ((entry->type_detail & ((1 << 7) | (1 << 13)))
-				 == ((1 << 7) | (1 << 13)))
+			else if ((entry->type_detail & rdr_mask) == rdr_mask)
 				dimm->mtype = MEM_RDR;
-			else if (entry->type_detail & 1 << 7)
+			else if (entry->type_detail & BIT(7))
 				dimm->mtype = MEM_SDR;
-			else if (entry->type_detail & 1 << 9)
+			else if (entry->type_detail & BIT(9))
 				dimm->mtype = MEM_EDO;
 			else
 				dimm->mtype = MEM_UNKNOWN;
@@ -172,8 +181,7 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
 	}
 }
 
-void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
-				struct cper_sec_mem_err *mem_err)
+void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 {
 	enum hw_event_mc_err_type type;
 	struct edac_raw_error_desc *e;
@@ -183,10 +191,8 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
 	char *p;
 	u8 grain_bits;
 
-	if (!pvt) {
-		pr_err("Internal error: Can't find EDAC structure\n");
+	if (!pvt)
 		return;
-	}
 
 	/*
 	 * We can do the locking below because GHES defers error processing
@@ -434,12 +440,16 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 	struct mem_ctl_info *mci;
 	struct edac_mc_layer layers[1];
 	struct ghes_edac_dimm_fill dimm_fill;
-	int idx;
+	int idx = -1;
 
-	/* Check if safe to enable on this system */
-	idx = acpi_match_platform_list(plat_list);
-	if (!force_load && idx < 0)
-		return 0;
+	if (IS_ENABLED(CONFIG_X86)) {
+		/* Check if safe to enable on this system */
+		idx = acpi_match_platform_list(plat_list);
+		if (!force_load && idx < 0)
+			return -ENODEV;
+	} else {
+		idx = 0;
+	}
 
 	/*
 	 * We have only one logical memory controller to which all DIMMs belong.
@@ -519,6 +529,9 @@ void ghes_edac_unregister(struct ghes *ghes)
 {
 	struct mem_ctl_info *mci;
 
+	if (!ghes_pvt)
+		return;
+
 	mci = ghes_pvt->mci;
 	edac_mc_del_mc(mci->pdev);
 	edac_mc_free(mci);
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 8c5540160a23..4d0ea3563d47 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1743,7 +1743,7 @@ static void i7core_mce_output_error(struct mem_ctl_info *mci,
 		err = "write parity error";
 		break;
 	case 19:
-		err = "redundacy loss";
+		err = "redundancy loss";
 		break;
 	case 20:
 		err = "reserved";
diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index e6f17825db79..2b90606452a2 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -284,7 +284,7 @@ scmi_clock_info_get(const struct scmi_handle *handle, u32 clk_id)
 	struct clock_info *ci = handle->clk_priv;
 	struct scmi_clock_info *clk = ci->clk + clk_id;
 
-	if (!clk->name || !clk->name[0])
+	if (!clk->name[0])
 		return NULL;
 
 	return clk;
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 14b147135a0c..2455be8cbc4f 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -778,6 +778,7 @@ scmi_create_protocol_device(struct device_node *np, struct scmi_info *info,
 	if (scmi_mbox_chan_setup(info, &sdev->dev, prot_id)) {
 		dev_err(&sdev->dev, "failed to setup transport\n");
 		scmi_device_destroy(sdev);
+		return;
 	}
 
 	/* setup handle now as the transport is ready */
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 3098410abad8..781a4a337557 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -174,6 +174,11 @@ config UEFI_CPER_ARM
 	depends on UEFI_CPER && ( ARM || ARM64 )
 	default y
 
+config UEFI_CPER_X86
+	bool
+	depends on UEFI_CPER && X86
+	default y
+
 config EFI_DEV_PATH_PARSER
 	bool
 	depends on ACPI
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index cb805374f4bc..5f9f5039de50 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -31,3 +31,4 @@ obj-$(CONFIG_ARM)			+= $(arm-obj-y)
 obj-$(CONFIG_ARM64)			+= $(arm-obj-y)
 obj-$(CONFIG_EFI_CAPSULE_LOADER)	+= capsule-loader.o
 obj-$(CONFIG_UEFI_CPER_ARM)		+= cper-arm.o
+obj-$(CONFIG_UEFI_CPER_X86)		+= cper-x86.o
diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c
index adaa9a3714b9..60a95719ecb8 100644
--- a/drivers/firmware/efi/apple-properties.c
+++ b/drivers/firmware/efi/apple-properties.c
@@ -13,6 +13,9 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Note, all properties are considered as u8 arrays.
+ * To get a value of any of them the caller must use device_property_read_u8_array().
  */
 
 #define pr_fmt(fmt) "apple-properties: " fmt
@@ -96,12 +99,13 @@ static void __init unmarshal_key_value_pairs(struct dev_header *dev_header,
 		entry[i].name = key;
 		entry[i].length = val_len - sizeof(val_len);
 		entry[i].is_array = !!entry[i].length;
-		entry[i].pointer.raw_data = ptr + key_len + sizeof(val_len);
+		entry[i].type = DEV_PROP_U8;
+		entry[i].pointer.u8_data = ptr + key_len + sizeof(val_len);
 
 		if (dump_properties) {
 			dev_info(dev, "property: %s\n", entry[i].name);
 			print_hex_dump(KERN_INFO, pr_fmt(), DUMP_PREFIX_OFFSET,
-				16, 1, entry[i].pointer.raw_data,
+				16, 1, entry[i].pointer.u8_data,
 				entry[i].length, true);
 		}
 
diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c
index e456f4602df1..96688986da56 100644
--- a/drivers/firmware/efi/capsule-loader.c
+++ b/drivers/firmware/efi/capsule-loader.c
@@ -134,10 +134,16 @@ static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info)
 
 	/* Indicate capsule binary uploading is done */
 	cap_info->index = NO_FURTHER_WRITE_ACTION;
-	pr_info("Successfully upload capsule file with reboot type '%s'\n",
-		!cap_info->reset_type ? "RESET_COLD" :
-		cap_info->reset_type == 1 ? "RESET_WARM" :
-		"RESET_SHUTDOWN");
+
+	if (cap_info->header.flags & EFI_CAPSULE_PERSIST_ACROSS_RESET) {
+		pr_info("Successfully uploaded capsule file with reboot type '%s'\n",
+			!cap_info->reset_type ? "RESET_COLD" :
+			cap_info->reset_type == 1 ? "RESET_WARM" :
+			"RESET_SHUTDOWN");
+	} else {
+		pr_info("Successfully processed capsule file\n");
+	}
+
 	return 0;
 }
 
diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c
index 698e5c8e0c8d..502811344e81 100644
--- a/drivers/firmware/efi/cper-arm.c
+++ b/drivers/firmware/efi/cper-arm.c
@@ -30,8 +30,6 @@
 #include <acpi/ghes.h>
 #include <ras/ras_event.h>
 
-#define INDENT_SP	" "
-
 static const char * const arm_reg_ctx_strs[] = {
 	"AArch32 general purpose registers",
 	"AArch32 EL1 context registers",
@@ -283,7 +281,7 @@ void cper_print_proc_arm(const char *pfx,
 			pfx, proc->psci_state);
 	}
 
-	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+	snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
 
 	err_info = (struct cper_arm_err_info *)(proc + 1);
 	for (i = 0; i < proc->err_info_num; i++) {
@@ -310,7 +308,7 @@ void cper_print_proc_arm(const char *pfx,
 		if (err_info->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO) {
 			printk("%serror_info: 0x%016llx\n", newpfx,
 			       err_info->error_info);
-			snprintf(infopfx, sizeof(infopfx), "%s%s", newpfx, INDENT_SP);
+			snprintf(infopfx, sizeof(infopfx), "%s ", newpfx);
 			cper_print_arm_err_info(infopfx, err_info->type,
 						err_info->error_info);
 		}
diff --git a/drivers/firmware/efi/cper-x86.c b/drivers/firmware/efi/cper-x86.c
new file mode 100644
index 000000000000..2531de49f56c
--- /dev/null
+++ b/drivers/firmware/efi/cper-x86.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Advanced Micro Devices, Inc.
+
+#include <linux/cper.h>
+
+/*
+ * We don't need a "CPER_IA" prefix since these are all locally defined.
+ * This will save us a lot of line space.
+ */
+#define VALID_LAPIC_ID			BIT_ULL(0)
+#define VALID_CPUID_INFO		BIT_ULL(1)
+#define VALID_PROC_ERR_INFO_NUM(bits)	(((bits) & GENMASK_ULL(7, 2)) >> 2)
+#define VALID_PROC_CXT_INFO_NUM(bits)	(((bits) & GENMASK_ULL(13, 8)) >> 8)
+
+#define INFO_ERR_STRUCT_TYPE_CACHE					\
+	GUID_INIT(0xA55701F5, 0xE3EF, 0x43DE, 0xAC, 0x72, 0x24, 0x9B,	\
+		  0x57, 0x3F, 0xAD, 0x2C)
+#define INFO_ERR_STRUCT_TYPE_TLB					\
+	GUID_INIT(0xFC06B535, 0x5E1F, 0x4562, 0x9F, 0x25, 0x0A, 0x3B,	\
+		  0x9A, 0xDB, 0x63, 0xC3)
+#define INFO_ERR_STRUCT_TYPE_BUS					\
+	GUID_INIT(0x1CF3F8B3, 0xC5B1, 0x49a2, 0xAA, 0x59, 0x5E, 0xEF,	\
+		  0x92, 0xFF, 0xA6, 0x3C)
+#define INFO_ERR_STRUCT_TYPE_MS						\
+	GUID_INIT(0x48AB7F57, 0xDC34, 0x4f6c, 0xA7, 0xD3, 0xB0, 0xB5,	\
+		  0xB0, 0xA7, 0x43, 0x14)
+
+#define INFO_VALID_CHECK_INFO		BIT_ULL(0)
+#define INFO_VALID_TARGET_ID		BIT_ULL(1)
+#define INFO_VALID_REQUESTOR_ID		BIT_ULL(2)
+#define INFO_VALID_RESPONDER_ID		BIT_ULL(3)
+#define INFO_VALID_IP			BIT_ULL(4)
+
+#define CHECK_VALID_TRANS_TYPE		BIT_ULL(0)
+#define CHECK_VALID_OPERATION		BIT_ULL(1)
+#define CHECK_VALID_LEVEL		BIT_ULL(2)
+#define CHECK_VALID_PCC			BIT_ULL(3)
+#define CHECK_VALID_UNCORRECTED		BIT_ULL(4)
+#define CHECK_VALID_PRECISE_IP		BIT_ULL(5)
+#define CHECK_VALID_RESTARTABLE_IP	BIT_ULL(6)
+#define CHECK_VALID_OVERFLOW		BIT_ULL(7)
+
+#define CHECK_VALID_BUS_PART_TYPE	BIT_ULL(8)
+#define CHECK_VALID_BUS_TIME_OUT	BIT_ULL(9)
+#define CHECK_VALID_BUS_ADDR_SPACE	BIT_ULL(10)
+
+#define CHECK_VALID_BITS(check)		(((check) & GENMASK_ULL(15, 0)))
+#define CHECK_TRANS_TYPE(check)		(((check) & GENMASK_ULL(17, 16)) >> 16)
+#define CHECK_OPERATION(check)		(((check) & GENMASK_ULL(21, 18)) >> 18)
+#define CHECK_LEVEL(check)		(((check) & GENMASK_ULL(24, 22)) >> 22)
+#define CHECK_PCC			BIT_ULL(25)
+#define CHECK_UNCORRECTED		BIT_ULL(26)
+#define CHECK_PRECISE_IP		BIT_ULL(27)
+#define CHECK_RESTARTABLE_IP		BIT_ULL(28)
+#define CHECK_OVERFLOW			BIT_ULL(29)
+
+#define CHECK_BUS_PART_TYPE(check)	(((check) & GENMASK_ULL(31, 30)) >> 30)
+#define CHECK_BUS_TIME_OUT		BIT_ULL(32)
+#define CHECK_BUS_ADDR_SPACE(check)	(((check) & GENMASK_ULL(34, 33)) >> 33)
+
+#define CHECK_VALID_MS_ERR_TYPE		BIT_ULL(0)
+#define CHECK_VALID_MS_PCC		BIT_ULL(1)
+#define CHECK_VALID_MS_UNCORRECTED	BIT_ULL(2)
+#define CHECK_VALID_MS_PRECISE_IP	BIT_ULL(3)
+#define CHECK_VALID_MS_RESTARTABLE_IP	BIT_ULL(4)
+#define CHECK_VALID_MS_OVERFLOW		BIT_ULL(5)
+
+#define CHECK_MS_ERR_TYPE(check)	(((check) & GENMASK_ULL(18, 16)) >> 16)
+#define CHECK_MS_PCC			BIT_ULL(19)
+#define CHECK_MS_UNCORRECTED		BIT_ULL(20)
+#define CHECK_MS_PRECISE_IP		BIT_ULL(21)
+#define CHECK_MS_RESTARTABLE_IP		BIT_ULL(22)
+#define CHECK_MS_OVERFLOW		BIT_ULL(23)
+
+#define CTX_TYPE_MSR			1
+#define CTX_TYPE_MMREG			7
+
+enum err_types {
+	ERR_TYPE_CACHE = 0,
+	ERR_TYPE_TLB,
+	ERR_TYPE_BUS,
+	ERR_TYPE_MS,
+	N_ERR_TYPES
+};
+
+static enum err_types cper_get_err_type(const guid_t *err_type)
+{
+	if (guid_equal(err_type, &INFO_ERR_STRUCT_TYPE_CACHE))
+		return ERR_TYPE_CACHE;
+	else if (guid_equal(err_type, &INFO_ERR_STRUCT_TYPE_TLB))
+		return ERR_TYPE_TLB;
+	else if (guid_equal(err_type, &INFO_ERR_STRUCT_TYPE_BUS))
+		return ERR_TYPE_BUS;
+	else if (guid_equal(err_type, &INFO_ERR_STRUCT_TYPE_MS))
+		return ERR_TYPE_MS;
+	else
+		return N_ERR_TYPES;
+}
+
+static const char * const ia_check_trans_type_strs[] = {
+	"Instruction",
+	"Data Access",
+	"Generic",
+};
+
+static const char * const ia_check_op_strs[] = {
+	"generic error",
+	"generic read",
+	"generic write",
+	"data read",
+	"data write",
+	"instruction fetch",
+	"prefetch",
+	"eviction",
+	"snoop",
+};
+
+static const char * const ia_check_bus_part_type_strs[] = {
+	"Local Processor originated request",
+	"Local Processor responded to request",
+	"Local Processor observed",
+	"Generic",
+};
+
+static const char * const ia_check_bus_addr_space_strs[] = {
+	"Memory Access",
+	"Reserved",
+	"I/O",
+	"Other Transaction",
+};
+
+static const char * const ia_check_ms_error_type_strs[] = {
+	"No Error",
+	"Unclassified",
+	"Microcode ROM Parity Error",
+	"External Error",
+	"FRC Error",
+	"Internal Unclassified",
+};
+
+static const char * const ia_reg_ctx_strs[] = {
+	"Unclassified Data",
+	"MSR Registers (Machine Check and other MSRs)",
+	"32-bit Mode Execution Context",
+	"64-bit Mode Execution Context",
+	"FXSAVE Context",
+	"32-bit Mode Debug Registers (DR0-DR7)",
+	"64-bit Mode Debug Registers (DR0-DR7)",
+	"Memory Mapped Registers",
+};
+
+static inline void print_bool(char *str, const char *pfx, u64 check, u64 bit)
+{
+	printk("%s%s: %s\n", pfx, str, (check & bit) ? "true" : "false");
+}
+
+static void print_err_info_ms(const char *pfx, u16 validation_bits, u64 check)
+{
+	if (validation_bits & CHECK_VALID_MS_ERR_TYPE) {
+		u8 err_type = CHECK_MS_ERR_TYPE(check);
+
+		printk("%sError Type: %u, %s\n", pfx, err_type,
+		       err_type < ARRAY_SIZE(ia_check_ms_error_type_strs) ?
+		       ia_check_ms_error_type_strs[err_type] : "unknown");
+	}
+
+	if (validation_bits & CHECK_VALID_MS_PCC)
+		print_bool("Processor Context Corrupt", pfx, check, CHECK_MS_PCC);
+
+	if (validation_bits & CHECK_VALID_MS_UNCORRECTED)
+		print_bool("Uncorrected", pfx, check, CHECK_MS_UNCORRECTED);
+
+	if (validation_bits & CHECK_VALID_MS_PRECISE_IP)
+		print_bool("Precise IP", pfx, check, CHECK_MS_PRECISE_IP);
+
+	if (validation_bits & CHECK_VALID_MS_RESTARTABLE_IP)
+		print_bool("Restartable IP", pfx, check, CHECK_MS_RESTARTABLE_IP);
+
+	if (validation_bits & CHECK_VALID_MS_OVERFLOW)
+		print_bool("Overflow", pfx, check, CHECK_MS_OVERFLOW);
+}
+
+static void print_err_info(const char *pfx, u8 err_type, u64 check)
+{
+	u16 validation_bits = CHECK_VALID_BITS(check);
+
+	/*
+	 * The MS Check structure varies a lot from the others, so use a
+	 * separate function for decoding.
+	 */
+	if (err_type == ERR_TYPE_MS)
+		return print_err_info_ms(pfx, validation_bits, check);
+
+	if (validation_bits & CHECK_VALID_TRANS_TYPE) {
+		u8 trans_type = CHECK_TRANS_TYPE(check);
+
+		printk("%sTransaction Type: %u, %s\n", pfx, trans_type,
+		       trans_type < ARRAY_SIZE(ia_check_trans_type_strs) ?
+		       ia_check_trans_type_strs[trans_type] : "unknown");
+	}
+
+	if (validation_bits & CHECK_VALID_OPERATION) {
+		u8 op = CHECK_OPERATION(check);
+
+		/*
+		 * CACHE has more operation types than TLB or BUS, though the
+		 * name and the order are the same.
+		 */
+		u8 max_ops = (err_type == ERR_TYPE_CACHE) ? 9 : 7;
+
+		printk("%sOperation: %u, %s\n", pfx, op,
+		       op < max_ops ? ia_check_op_strs[op] : "unknown");
+	}
+
+	if (validation_bits & CHECK_VALID_LEVEL)
+		printk("%sLevel: %llu\n", pfx, CHECK_LEVEL(check));
+
+	if (validation_bits & CHECK_VALID_PCC)
+		print_bool("Processor Context Corrupt", pfx, check, CHECK_PCC);
+
+	if (validation_bits & CHECK_VALID_UNCORRECTED)
+		print_bool("Uncorrected", pfx, check, CHECK_UNCORRECTED);
+
+	if (validation_bits & CHECK_VALID_PRECISE_IP)
+		print_bool("Precise IP", pfx, check, CHECK_PRECISE_IP);
+
+	if (validation_bits & CHECK_VALID_RESTARTABLE_IP)
+		print_bool("Restartable IP", pfx, check, CHECK_RESTARTABLE_IP);
+
+	if (validation_bits & CHECK_VALID_OVERFLOW)
+		print_bool("Overflow", pfx, check, CHECK_OVERFLOW);
+
+	if (err_type != ERR_TYPE_BUS)
+		return;
+
+	if (validation_bits & CHECK_VALID_BUS_PART_TYPE) {
+		u8 part_type = CHECK_BUS_PART_TYPE(check);
+
+		printk("%sParticipation Type: %u, %s\n", pfx, part_type,
+		       part_type < ARRAY_SIZE(ia_check_bus_part_type_strs) ?
+		       ia_check_bus_part_type_strs[part_type] : "unknown");
+	}
+
+	if (validation_bits & CHECK_VALID_BUS_TIME_OUT)
+		print_bool("Time Out", pfx, check, CHECK_BUS_TIME_OUT);
+
+	if (validation_bits & CHECK_VALID_BUS_ADDR_SPACE) {
+		u8 addr_space = CHECK_BUS_ADDR_SPACE(check);
+
+		printk("%sAddress Space: %u, %s\n", pfx, addr_space,
+		       addr_space < ARRAY_SIZE(ia_check_bus_addr_space_strs) ?
+		       ia_check_bus_addr_space_strs[addr_space] : "unknown");
+	}
+}
+
+void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc)
+{
+	int i;
+	struct cper_ia_err_info *err_info;
+	struct cper_ia_proc_ctx *ctx_info;
+	char newpfx[64], infopfx[64];
+	u8 err_type;
+
+	if (proc->validation_bits & VALID_LAPIC_ID)
+		printk("%sLocal APIC_ID: 0x%llx\n", pfx, proc->lapic_id);
+
+	if (proc->validation_bits & VALID_CPUID_INFO) {
+		printk("%sCPUID Info:\n", pfx);
+		print_hex_dump(pfx, "", DUMP_PREFIX_OFFSET, 16, 4, proc->cpuid,
+			       sizeof(proc->cpuid), 0);
+	}
+
+	snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
+
+	err_info = (struct cper_ia_err_info *)(proc + 1);
+	for (i = 0; i < VALID_PROC_ERR_INFO_NUM(proc->validation_bits); i++) {
+		printk("%sError Information Structure %d:\n", pfx, i);
+
+		err_type = cper_get_err_type(&err_info->err_type);
+		printk("%sError Structure Type: %s\n", newpfx,
+		       err_type < ARRAY_SIZE(cper_proc_error_type_strs) ?
+		       cper_proc_error_type_strs[err_type] : "unknown");
+
+		if (err_type >= N_ERR_TYPES) {
+			printk("%sError Structure Type: %pUl\n", newpfx,
+			       &err_info->err_type);
+		}
+
+		if (err_info->validation_bits & INFO_VALID_CHECK_INFO) {
+			printk("%sCheck Information: 0x%016llx\n", newpfx,
+			       err_info->check_info);
+
+			if (err_type < N_ERR_TYPES) {
+				snprintf(infopfx, sizeof(infopfx), "%s ",
+					 newpfx);
+
+				print_err_info(infopfx, err_type,
+					       err_info->check_info);
+			}
+		}
+
+		if (err_info->validation_bits & INFO_VALID_TARGET_ID) {
+			printk("%sTarget Identifier: 0x%016llx\n",
+			       newpfx, err_info->target_id);
+		}
+
+		if (err_info->validation_bits & INFO_VALID_REQUESTOR_ID) {
+			printk("%sRequestor Identifier: 0x%016llx\n",
+			       newpfx, err_info->requestor_id);
+		}
+
+		if (err_info->validation_bits & INFO_VALID_RESPONDER_ID) {
+			printk("%sResponder Identifier: 0x%016llx\n",
+			       newpfx, err_info->responder_id);
+		}
+
+		if (err_info->validation_bits & INFO_VALID_IP) {
+			printk("%sInstruction Pointer: 0x%016llx\n",
+			       newpfx, err_info->ip);
+		}
+
+		err_info++;
+	}
+
+	ctx_info = (struct cper_ia_proc_ctx *)err_info;
+	for (i = 0; i < VALID_PROC_CXT_INFO_NUM(proc->validation_bits); i++) {
+		int size = sizeof(*ctx_info) + ctx_info->reg_arr_size;
+		int groupsize = 4;
+
+		printk("%sContext Information Structure %d:\n", pfx, i);
+
+		printk("%sRegister Context Type: %s\n", newpfx,
+		       ctx_info->reg_ctx_type < ARRAY_SIZE(ia_reg_ctx_strs) ?
+		       ia_reg_ctx_strs[ctx_info->reg_ctx_type] : "unknown");
+
+		printk("%sRegister Array Size: 0x%04x\n", newpfx,
+		       ctx_info->reg_arr_size);
+
+		if (ctx_info->reg_ctx_type == CTX_TYPE_MSR) {
+			groupsize = 8; /* MSRs are 8 bytes wide. */
+			printk("%sMSR Address: 0x%08x\n", newpfx,
+			       ctx_info->msr_addr);
+		}
+
+		if (ctx_info->reg_ctx_type == CTX_TYPE_MMREG) {
+			printk("%sMM Register Address: 0x%016llx\n", newpfx,
+			       ctx_info->mm_reg_addr);
+		}
+
+		printk("%sRegister Array:\n", newpfx);
+		print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, groupsize,
+			       (ctx_info + 1), ctx_info->reg_arr_size, 0);
+
+		ctx_info = (struct cper_ia_proc_ctx *)((long)ctx_info + size);
+	}
+}
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index c165933ebf38..3bf0dca378a6 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -37,8 +37,6 @@
 #include <acpi/ghes.h>
 #include <ras/ras_event.h>
 
-#define INDENT_SP	" "
-
 static char rcd_decode_str[CPER_REC_LEN];
 
 /*
@@ -433,7 +431,7 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
 		printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
 
-	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+	snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
 	if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) {
 		struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata);
 
@@ -470,6 +468,16 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		else
 			goto err_section_too_small;
 #endif
+#if defined(CONFIG_UEFI_CPER_X86)
+	} else if (guid_equal(sec_type, &CPER_SEC_PROC_IA)) {
+		struct cper_sec_proc_ia *ia_err = acpi_hest_get_payload(gdata);
+
+		printk("%ssection_type: IA32/X64 processor error\n", newpfx);
+		if (gdata->error_data_length >= sizeof(*ia_err))
+			cper_print_proc_ia(newpfx, ia_err);
+		else
+			goto err_section_too_small;
+#endif
 	} else {
 		const void *err = acpi_hest_get_payload(gdata);
 
@@ -500,7 +508,7 @@ void cper_estatus_print(const char *pfx,
 		       "It has been corrected by h/w "
 		       "and requires no further action");
 	printk("%s""event severity: %s\n", pfx, cper_severity_str(severity));
-	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+	snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
 
 	apei_estatus_for_each_section(estatus, gdata) {
 		cper_estatus_print_section(newpfx, gdata, sec_no);
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index b9bd827caa22..1b4d465cc5d9 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -98,6 +98,16 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
 			     (phys_seed >> 32) & mask : TEXT_OFFSET;
 
 		/*
+		 * With CONFIG_RANDOMIZE_TEXT_OFFSET=y, TEXT_OFFSET may not
+		 * be a multiple of EFI_KIMG_ALIGN, and we must ensure that
+		 * we preserve the misalignment of 'offset' relative to
+		 * EFI_KIMG_ALIGN so that statically allocated objects whose
+		 * alignment exceeds PAGE_SIZE appear correctly aligned in
+		 * memory.
+		 */
+		offset |= TEXT_OFFSET % EFI_KIMG_ALIGN;
+
+		/*
 		 * If KASLR is enabled, and we have some randomness available,
 		 * locate the kernel at a randomized offset in physical memory.
 		 */
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 8f07eb414c00..72d9dfbebf08 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -30,6 +30,9 @@ static const efi_char16_t shim_MokSBState_name[] = L"MokSBState";
 
 /*
  * Determine whether we're in secure boot mode.
+ *
+ * Please keep the logic in sync with
+ * arch/x86/xen/efi.c:xen_efi_get_secureboot().
  */
 enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
 {
diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c
index 9d08cea3f1b0..caa37a6dd9d4 100644
--- a/drivers/firmware/efi/libstub/tpm.c
+++ b/drivers/firmware/efi/libstub/tpm.c
@@ -59,7 +59,7 @@ void efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg)
 
 #endif
 
-void efi_retrieve_tpm2_eventlog_1_2(efi_system_table_t *sys_table_arg)
+static void efi_retrieve_tpm2_eventlog_1_2(efi_system_table_t *sys_table_arg)
 {
 	efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID;
 	efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID;
diff --git a/drivers/firmware/google/Kconfig b/drivers/firmware/google/Kconfig
index f16b381a569c..a456a000048b 100644
--- a/drivers/firmware/google/Kconfig
+++ b/drivers/firmware/google/Kconfig
@@ -55,6 +55,14 @@ config GOOGLE_MEMCONSOLE_X86_LEGACY
 	  the EBDA on Google servers.  If found, this log is exported to
 	  userland in the file /sys/firmware/log.
 
+config GOOGLE_FRAMEBUFFER_COREBOOT
+	tristate "Coreboot Framebuffer"
+	depends on FB_SIMPLE
+	depends on GOOGLE_COREBOOT_TABLE
+	help
+	  This option enables the kernel to search for a framebuffer in
+	  the coreboot table.  If found, it is registered with simplefb.
+
 config GOOGLE_MEMCONSOLE_COREBOOT
 	tristate "Firmware Memory Console"
 	depends on GOOGLE_COREBOOT_TABLE
diff --git a/drivers/firmware/google/Makefile b/drivers/firmware/google/Makefile
index dcd3675efcfc..d0b3fba96194 100644
--- a/drivers/firmware/google/Makefile
+++ b/drivers/firmware/google/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_GOOGLE_SMI)		+= gsmi.o
 obj-$(CONFIG_GOOGLE_COREBOOT_TABLE)        += coreboot_table.o
 obj-$(CONFIG_GOOGLE_COREBOOT_TABLE_ACPI)   += coreboot_table-acpi.o
 obj-$(CONFIG_GOOGLE_COREBOOT_TABLE_OF)     += coreboot_table-of.o
+obj-$(CONFIG_GOOGLE_FRAMEBUFFER_COREBOOT)  += framebuffer-coreboot.o
 obj-$(CONFIG_GOOGLE_MEMCONSOLE)            += memconsole.o
 obj-$(CONFIG_GOOGLE_MEMCONSOLE_COREBOOT)   += memconsole-coreboot.o
 obj-$(CONFIG_GOOGLE_MEMCONSOLE_X86_LEGACY) += memconsole-x86-legacy.o
diff --git a/drivers/firmware/google/coreboot_table-acpi.c b/drivers/firmware/google/coreboot_table-acpi.c
index fb98db2d20e2..77197fe3d42f 100644
--- a/drivers/firmware/google/coreboot_table-acpi.c
+++ b/drivers/firmware/google/coreboot_table-acpi.c
@@ -53,7 +53,7 @@ static int coreboot_table_acpi_probe(struct platform_device *pdev)
 	if (!ptr)
 		return -ENOMEM;
 
-	return coreboot_table_init(ptr);
+	return coreboot_table_init(&pdev->dev, ptr);
 }
 
 static int coreboot_table_acpi_remove(struct platform_device *pdev)
diff --git a/drivers/firmware/google/coreboot_table-of.c b/drivers/firmware/google/coreboot_table-of.c
index 727acdc83e83..f15bf404c579 100644
--- a/drivers/firmware/google/coreboot_table-of.c
+++ b/drivers/firmware/google/coreboot_table-of.c
@@ -34,7 +34,7 @@ static int coreboot_table_of_probe(struct platform_device *pdev)
 	if (!ptr)
 		return -ENOMEM;
 
-	return coreboot_table_init(ptr);
+	return coreboot_table_init(&pdev->dev, ptr);
 }
 
 static int coreboot_table_of_remove(struct platform_device *pdev)
diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c
index 0019d3ec18dd..19db5709ae28 100644
--- a/drivers/firmware/google/coreboot_table.c
+++ b/drivers/firmware/google/coreboot_table.c
@@ -4,6 +4,7 @@
  * Module providing coreboot table access.
  *
  * Copyright 2017 Google Inc.
+ * Copyright 2017 Samuel Holland <samuel@sholland.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License v2.0 as published by
@@ -15,37 +16,96 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 
 #include "coreboot_table.h"
 
-struct coreboot_table_entry {
-	u32 tag;
-	u32 size;
-};
+#define CB_DEV(d) container_of(d, struct coreboot_device, dev)
+#define CB_DRV(d) container_of(d, struct coreboot_driver, drv)
 
 static struct coreboot_table_header __iomem *ptr_header;
 
-/*
- * This function parses the coreboot table for an entry that contains the base
- * address of the given entry tag. The coreboot table consists of a header
- * directly followed by a number of small, variable-sized entries, which each
- * contain an identifying tag and their length as the first two fields.
- */
-int coreboot_table_find(int tag, void *data, size_t data_size)
+static int coreboot_bus_match(struct device *dev, struct device_driver *drv)
 {
-	struct coreboot_table_header header;
-	struct coreboot_table_entry entry;
-	void *ptr_entry;
-	int i;
+	struct coreboot_device *device = CB_DEV(dev);
+	struct coreboot_driver *driver = CB_DRV(drv);
 
-	if (!ptr_header)
-		return -EPROBE_DEFER;
+	return device->entry.tag == driver->tag;
+}
 
+static int coreboot_bus_probe(struct device *dev)
+{
+	int ret = -ENODEV;
+	struct coreboot_device *device = CB_DEV(dev);
+	struct coreboot_driver *driver = CB_DRV(dev->driver);
+
+	if (driver->probe)
+		ret = driver->probe(device);
+
+	return ret;
+}
+
+static int coreboot_bus_remove(struct device *dev)
+{
+	int ret = 0;
+	struct coreboot_device *device = CB_DEV(dev);
+	struct coreboot_driver *driver = CB_DRV(dev->driver);
+
+	if (driver->remove)
+		ret = driver->remove(device);
+
+	return ret;
+}
+
+static struct bus_type coreboot_bus_type = {
+	.name		= "coreboot",
+	.match		= coreboot_bus_match,
+	.probe		= coreboot_bus_probe,
+	.remove		= coreboot_bus_remove,
+};
+
+static int __init coreboot_bus_init(void)
+{
+	return bus_register(&coreboot_bus_type);
+}
+module_init(coreboot_bus_init);
+
+static void coreboot_device_release(struct device *dev)
+{
+	struct coreboot_device *device = CB_DEV(dev);
+
+	kfree(device);
+}
+
+int coreboot_driver_register(struct coreboot_driver *driver)
+{
+	driver->drv.bus = &coreboot_bus_type;
+
+	return driver_register(&driver->drv);
+}
+EXPORT_SYMBOL(coreboot_driver_register);
+
+void coreboot_driver_unregister(struct coreboot_driver *driver)
+{
+	driver_unregister(&driver->drv);
+}
+EXPORT_SYMBOL(coreboot_driver_unregister);
+
+int coreboot_table_init(struct device *dev, void __iomem *ptr)
+{
+	int i, ret;
+	void *ptr_entry;
+	struct coreboot_device *device;
+	struct coreboot_table_entry entry;
+	struct coreboot_table_header header;
+
+	ptr_header = ptr;
 	memcpy_fromio(&header, ptr_header, sizeof(header));
 
 	if (strncmp(header.signature, "LBIO", sizeof(header.signature))) {
@@ -54,37 +114,41 @@ int coreboot_table_find(int tag, void *data, size_t data_size)
 	}
 
 	ptr_entry = (void *)ptr_header + header.header_bytes;
-
 	for (i = 0; i < header.table_entries; i++) {
 		memcpy_fromio(&entry, ptr_entry, sizeof(entry));
-		if (entry.tag == tag) {
-			if (data_size < entry.size)
-				return -EINVAL;
 
-			memcpy_fromio(data, ptr_entry, entry.size);
+		device = kzalloc(sizeof(struct device) + entry.size, GFP_KERNEL);
+		if (!device) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		dev_set_name(&device->dev, "coreboot%d", i);
+		device->dev.parent = dev;
+		device->dev.bus = &coreboot_bus_type;
+		device->dev.release = coreboot_device_release;
+		memcpy_fromio(&device->entry, ptr_entry, entry.size);
 
-			return 0;
+		ret = device_register(&device->dev);
+		if (ret) {
+			put_device(&device->dev);
+			break;
 		}
 
 		ptr_entry += entry.size;
 	}
 
-	return -ENOENT;
-}
-EXPORT_SYMBOL(coreboot_table_find);
-
-int coreboot_table_init(void __iomem *ptr)
-{
-	ptr_header = ptr;
-
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(coreboot_table_init);
 
 int coreboot_table_exit(void)
 {
-	if (ptr_header)
+	if (ptr_header) {
+		bus_unregister(&coreboot_bus_type);
 		iounmap(ptr_header);
+		ptr_header = NULL;
+	}
 
 	return 0;
 }
diff --git a/drivers/firmware/google/coreboot_table.h b/drivers/firmware/google/coreboot_table.h
index 6eff1ae0c5d3..8ad95a94481b 100644
--- a/drivers/firmware/google/coreboot_table.h
+++ b/drivers/firmware/google/coreboot_table.h
@@ -3,7 +3,9 @@
  *
  * Internal header for coreboot table access.
  *
+ * Copyright 2014 Gerd Hoffmann <kraxel@redhat.com>
  * Copyright 2017 Google Inc.
+ * Copyright 2017 Samuel Holland <samuel@sholland.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License v2.0 as published by
@@ -20,14 +22,6 @@
 
 #include <linux/io.h>
 
-/* List of coreboot entry structures that is used */
-struct lb_cbmem_ref {
-	uint32_t tag;
-	uint32_t size;
-
-	uint64_t cbmem_addr;
-};
-
 /* Coreboot table header structure */
 struct coreboot_table_header {
 	char signature[4];
@@ -38,11 +32,67 @@ struct coreboot_table_header {
 	u32 table_entries;
 };
 
-/* Retrieve coreboot table entry with tag *tag* and copy it to data */
-int coreboot_table_find(int tag, void *data, size_t data_size);
+/* List of coreboot entry structures that is used */
+/* Generic */
+struct coreboot_table_entry {
+	u32 tag;
+	u32 size;
+};
+
+/* Points to a CBMEM entry */
+struct lb_cbmem_ref {
+	u32 tag;
+	u32 size;
+
+	u64 cbmem_addr;
+};
+
+/* Describes framebuffer setup by coreboot */
+struct lb_framebuffer {
+	u32 tag;
+	u32 size;
+
+	u64 physical_address;
+	u32 x_resolution;
+	u32 y_resolution;
+	u32 bytes_per_line;
+	u8  bits_per_pixel;
+	u8  red_mask_pos;
+	u8  red_mask_size;
+	u8  green_mask_pos;
+	u8  green_mask_size;
+	u8  blue_mask_pos;
+	u8  blue_mask_size;
+	u8  reserved_mask_pos;
+	u8  reserved_mask_size;
+};
+
+/* A device, additionally with information from coreboot. */
+struct coreboot_device {
+	struct device dev;
+	union {
+		struct coreboot_table_entry entry;
+		struct lb_cbmem_ref cbmem_ref;
+		struct lb_framebuffer framebuffer;
+	};
+};
+
+/* A driver for handling devices described in coreboot tables. */
+struct coreboot_driver {
+	int (*probe)(struct coreboot_device *);
+	int (*remove)(struct coreboot_device *);
+	struct device_driver drv;
+	u32 tag;
+};
+
+/* Register a driver that uses the data from a coreboot table. */
+int coreboot_driver_register(struct coreboot_driver *driver);
+
+/* Unregister a driver that uses the data from a coreboot table. */
+void coreboot_driver_unregister(struct coreboot_driver *driver);
 
 /* Initialize coreboot table module given a pointer to iomem */
-int coreboot_table_init(void __iomem *ptr);
+int coreboot_table_init(struct device *dev, void __iomem *ptr);
 
 /* Cleanup coreboot table module */
 int coreboot_table_exit(void);
diff --git a/drivers/firmware/google/framebuffer-coreboot.c b/drivers/firmware/google/framebuffer-coreboot.c
new file mode 100644
index 000000000000..b8b49c067157
--- /dev/null
+++ b/drivers/firmware/google/framebuffer-coreboot.c
@@ -0,0 +1,115 @@
+/*
+ * framebuffer-coreboot.c
+ *
+ * Memory based framebuffer accessed through coreboot table.
+ *
+ * Copyright 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ * Copyright 2017 Google Inc.
+ * Copyright 2017 Samuel Holland <samuel@sholland.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License v2.0 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+
+#include "coreboot_table.h"
+
+#define CB_TAG_FRAMEBUFFER 0x12
+
+static const struct simplefb_format formats[] = SIMPLEFB_FORMATS;
+
+static int framebuffer_probe(struct coreboot_device *dev)
+{
+	int i;
+	u32 length;
+	struct lb_framebuffer *fb = &dev->framebuffer;
+	struct platform_device *pdev;
+	struct resource res;
+	struct simplefb_platform_data pdata = {
+		.width = fb->x_resolution,
+		.height = fb->y_resolution,
+		.stride = fb->bytes_per_line,
+		.format = NULL,
+	};
+
+	for (i = 0; i < ARRAY_SIZE(formats); ++i) {
+		if (fb->bits_per_pixel     == formats[i].bits_per_pixel &&
+		    fb->red_mask_pos       == formats[i].red.offset &&
+		    fb->red_mask_size      == formats[i].red.length &&
+		    fb->green_mask_pos     == formats[i].green.offset &&
+		    fb->green_mask_size    == formats[i].green.length &&
+		    fb->blue_mask_pos      == formats[i].blue.offset &&
+		    fb->blue_mask_size     == formats[i].blue.length &&
+		    fb->reserved_mask_pos  == formats[i].transp.offset &&
+		    fb->reserved_mask_size == formats[i].transp.length)
+			pdata.format = formats[i].name;
+	}
+	if (!pdata.format)
+		return -ENODEV;
+
+	memset(&res, 0, sizeof(res));
+	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res.name = "Coreboot Framebuffer";
+	res.start = fb->physical_address;
+	length = PAGE_ALIGN(fb->y_resolution * fb->bytes_per_line);
+	res.end = res.start + length - 1;
+	if (res.end <= res.start)
+		return -EINVAL;
+
+	pdev = platform_device_register_resndata(&dev->dev,
+						 "simple-framebuffer", 0,
+						 &res, 1, &pdata,
+						 sizeof(pdata));
+	if (IS_ERR(pdev))
+		pr_warn("coreboot: could not register framebuffer\n");
+	else
+		dev_set_drvdata(&dev->dev, pdev);
+
+	return PTR_ERR_OR_ZERO(pdev);
+}
+
+static int framebuffer_remove(struct coreboot_device *dev)
+{
+	struct platform_device *pdev = dev_get_drvdata(&dev->dev);
+
+	platform_device_unregister(pdev);
+
+	return 0;
+}
+
+static struct coreboot_driver framebuffer_driver = {
+	.probe = framebuffer_probe,
+	.remove = framebuffer_remove,
+	.drv = {
+		.name = "framebuffer",
+	},
+	.tag = CB_TAG_FRAMEBUFFER,
+};
+
+static int __init coreboot_framebuffer_init(void)
+{
+	return coreboot_driver_register(&framebuffer_driver);
+}
+
+static void coreboot_framebuffer_exit(void)
+{
+	coreboot_driver_unregister(&framebuffer_driver);
+}
+
+module_init(coreboot_framebuffer_init);
+module_exit(coreboot_framebuffer_exit);
+
+MODULE_AUTHOR("Samuel Holland <samuel@sholland.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/google/memconsole-coreboot.c b/drivers/firmware/google/memconsole-coreboot.c
index 52738887735c..b29e10757bfb 100644
--- a/drivers/firmware/google/memconsole-coreboot.c
+++ b/drivers/firmware/google/memconsole-coreboot.c
@@ -15,9 +15,9 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/platform_device.h>
 
 #include "memconsole.h"
 #include "coreboot_table.h"
@@ -73,18 +73,19 @@ static ssize_t memconsole_coreboot_read(char *buf, loff_t pos, size_t count)
 	return done;
 }
 
-static int memconsole_coreboot_init(phys_addr_t physaddr)
+static int memconsole_probe(struct coreboot_device *dev)
 {
 	struct cbmem_cons __iomem *tmp_cbmc;
 
-	tmp_cbmc = memremap(physaddr, sizeof(*tmp_cbmc), MEMREMAP_WB);
+	tmp_cbmc = memremap(dev->cbmem_ref.cbmem_addr,
+			    sizeof(*tmp_cbmc), MEMREMAP_WB);
 
 	if (!tmp_cbmc)
 		return -ENOMEM;
 
 	/* Read size only once to prevent overrun attack through /dev/mem. */
 	cbmem_console_size = tmp_cbmc->size_dont_access_after_boot;
-	cbmem_console = memremap(physaddr,
+	cbmem_console = memremap(dev->cbmem_ref.cbmem_addr,
 				 cbmem_console_size + sizeof(*cbmem_console),
 				 MEMREMAP_WB);
 	memunmap(tmp_cbmc);
@@ -93,26 +94,11 @@ static int memconsole_coreboot_init(phys_addr_t physaddr)
 		return -ENOMEM;
 
 	memconsole_setup(memconsole_coreboot_read);
-	return 0;
-}
-
-static int memconsole_probe(struct platform_device *pdev)
-{
-	int ret;
-	struct lb_cbmem_ref entry;
-
-	ret = coreboot_table_find(CB_TAG_CBMEM_CONSOLE, &entry, sizeof(entry));
-	if (ret)
-		return ret;
-
-	ret = memconsole_coreboot_init(entry.cbmem_addr);
-	if (ret)
-		return ret;
 
 	return memconsole_sysfs_init();
 }
 
-static int memconsole_remove(struct platform_device *pdev)
+static int memconsole_remove(struct coreboot_device *dev)
 {
 	memconsole_exit();
 
@@ -122,28 +108,27 @@ static int memconsole_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_driver memconsole_driver = {
+static struct coreboot_driver memconsole_driver = {
 	.probe = memconsole_probe,
 	.remove = memconsole_remove,
-	.driver = {
+	.drv = {
 		.name = "memconsole",
 	},
+	.tag = CB_TAG_CBMEM_CONSOLE,
 };
 
-static int __init platform_memconsole_init(void)
+static void coreboot_memconsole_exit(void)
 {
-	struct platform_device *pdev;
-
-	pdev = platform_device_register_simple("memconsole", -1, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
-
-	platform_driver_register(&memconsole_driver);
+	coreboot_driver_unregister(&memconsole_driver);
+}
 
-	return 0;
+static int __init coreboot_memconsole_init(void)
+{
+	return coreboot_driver_register(&memconsole_driver);
 }
 
-module_init(platform_memconsole_init);
+module_exit(coreboot_memconsole_exit);
+module_init(coreboot_memconsole_init);
 
 MODULE_AUTHOR("Google, Inc.");
 MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c
index e4b40f2b4627..e9db895916c3 100644
--- a/drivers/firmware/google/vpd.c
+++ b/drivers/firmware/google/vpd.c
@@ -286,20 +286,15 @@ static int vpd_sections_init(phys_addr_t physaddr)
 	return 0;
 }
 
-static int vpd_probe(struct platform_device *pdev)
+static int vpd_probe(struct coreboot_device *dev)
 {
 	int ret;
-	struct lb_cbmem_ref entry;
-
-	ret = coreboot_table_find(CB_TAG_VPD, &entry, sizeof(entry));
-	if (ret)
-		return ret;
 
 	vpd_kobj = kobject_create_and_add("vpd", firmware_kobj);
 	if (!vpd_kobj)
 		return -ENOMEM;
 
-	ret = vpd_sections_init(entry.cbmem_addr);
+	ret = vpd_sections_init(dev->cbmem_ref.cbmem_addr);
 	if (ret) {
 		kobject_put(vpd_kobj);
 		return ret;
@@ -308,7 +303,7 @@ static int vpd_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int vpd_remove(struct platform_device *pdev)
+static int vpd_remove(struct coreboot_device *dev)
 {
 	vpd_section_destroy(&ro_vpd);
 	vpd_section_destroy(&rw_vpd);
@@ -318,41 +313,27 @@ static int vpd_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_driver vpd_driver = {
+static struct coreboot_driver vpd_driver = {
 	.probe = vpd_probe,
 	.remove = vpd_remove,
-	.driver = {
+	.drv = {
 		.name = "vpd",
 	},
+	.tag = CB_TAG_VPD,
 };
 
-static struct platform_device *vpd_pdev;
-
-static int __init vpd_platform_init(void)
+static int __init coreboot_vpd_init(void)
 {
-	int ret;
-
-	ret = platform_driver_register(&vpd_driver);
-	if (ret)
-		return ret;
-
-	vpd_pdev = platform_device_register_simple("vpd", -1, NULL, 0);
-	if (IS_ERR(vpd_pdev)) {
-		platform_driver_unregister(&vpd_driver);
-		return PTR_ERR(vpd_pdev);
-	}
-
-	return 0;
+	return coreboot_driver_register(&vpd_driver);
 }
 
-static void __exit vpd_platform_exit(void)
+static void __exit coreboot_vpd_exit(void)
 {
-	platform_device_unregister(vpd_pdev);
-	platform_driver_unregister(&vpd_driver);
+	coreboot_driver_unregister(&vpd_driver);
 }
 
-module_init(vpd_platform_init);
-module_exit(vpd_platform_exit);
+module_init(coreboot_vpd_init);
+module_exit(coreboot_vpd_exit);
 
 MODULE_AUTHOR("Google, Inc.");
 MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index dfbd894d5bb7..4e24e591ae74 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -147,7 +147,7 @@ static u32 smc(u32 cmd_addr)
 			"smc	#0	@ switch to secure world\n"
 			: "=r" (r0)
 			: "r" (r0), "r" (r1), "r" (r2)
-			: "r3");
+			: "r3", "r12");
 	} while (r0 == QCOM_SCM_INTERRUPTED);
 
 	return r0;
@@ -263,7 +263,7 @@ static s32 qcom_scm_call_atomic1(u32 svc, u32 cmd, u32 arg1)
 			"smc    #0      @ switch to secure world\n"
 			: "=r" (r0)
 			: "r" (r0), "r" (r1), "r" (r2)
-			: "r3");
+			: "r3", "r12");
 	return r0;
 }
 
@@ -298,7 +298,7 @@ static s32 qcom_scm_call_atomic2(u32 svc, u32 cmd, u32 arg1, u32 arg2)
 			"smc    #0      @ switch to secure world\n"
 			: "=r" (r0)
 			: "r" (r0), "r" (r1), "r" (r2), "r" (r3)
-			);
+			: "r12");
 	return r0;
 }
 
@@ -328,7 +328,7 @@ u32 qcom_scm_get_version(void)
 			"smc	#0	@ switch to secure world\n"
 			: "=r" (r0), "=r" (r1)
 			: "r" (r0), "r" (r1)
-			: "r2", "r3");
+			: "r2", "r3", "r12");
 	} while (r0 == QCOM_SCM_INTERRUPTED);
 
 	version = r1;
diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig
index f47ef848bcd0..ee9c5420c47f 100644
--- a/drivers/fpga/Kconfig
+++ b/drivers/fpga/Kconfig
@@ -53,7 +53,6 @@ config FPGA_MGR_ALTERA_CVP
 config FPGA_MGR_ZYNQ_FPGA
 	tristate "Xilinx Zynq FPGA"
 	depends on ARCH_ZYNQ || COMPILE_TEST
-	depends on HAS_DMA
 	help
 	  FPGA manager driver support for Xilinx Zynq FPGAs.
 
@@ -70,6 +69,13 @@ config FPGA_MGR_ICE40_SPI
 	help
 	  FPGA manager driver support for Lattice iCE40 FPGAs over SPI.
 
+config FPGA_MGR_MACHXO2_SPI
+	tristate "Lattice MachXO2 SPI"
+	depends on SPI
+	help
+	  FPGA manager driver support for Lattice MachXO2 configuration
+	  over slave SPI interface.
+
 config FPGA_MGR_TS73XX
 	tristate "Technologic Systems TS-73xx SBC FPGA Manager"
 	depends on ARCH_EP93XX && MACH_TS72XX
diff --git a/drivers/fpga/Makefile b/drivers/fpga/Makefile
index 3cb276a0f88d..f9803dad6919 100644
--- a/drivers/fpga/Makefile
+++ b/drivers/fpga/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_FPGA)			+= fpga-mgr.o
 obj-$(CONFIG_FPGA_MGR_ALTERA_CVP)	+= altera-cvp.o
 obj-$(CONFIG_FPGA_MGR_ALTERA_PS_SPI)	+= altera-ps-spi.o
 obj-$(CONFIG_FPGA_MGR_ICE40_SPI)	+= ice40-spi.o
+obj-$(CONFIG_FPGA_MGR_MACHXO2_SPI)	+= machxo2-spi.o
 obj-$(CONFIG_FPGA_MGR_SOCFPGA)		+= socfpga.o
 obj-$(CONFIG_FPGA_MGR_SOCFPGA_A10)	+= socfpga-a10.o
 obj-$(CONFIG_FPGA_MGR_TS73XX)		+= ts73xx-fpga.o
diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c
index 77b04e4b3254..dd4edd8f22ce 100644
--- a/drivers/fpga/altera-cvp.c
+++ b/drivers/fpga/altera-cvp.c
@@ -401,6 +401,7 @@ static int altera_cvp_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *dev_id)
 {
 	struct altera_cvp_conf *conf;
+	struct fpga_manager *mgr;
 	u16 cmd, val;
 	int ret;
 
@@ -452,16 +453,24 @@ static int altera_cvp_probe(struct pci_dev *pdev,
 	snprintf(conf->mgr_name, sizeof(conf->mgr_name), "%s @%s",
 		 ALTERA_CVP_MGR_NAME, pci_name(pdev));
 
-	ret = fpga_mgr_register(&pdev->dev, conf->mgr_name,
-				&altera_cvp_ops, conf);
-	if (ret)
+	mgr = fpga_mgr_create(&pdev->dev, conf->mgr_name,
+			      &altera_cvp_ops, conf);
+	if (!mgr)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, mgr);
+
+	ret = fpga_mgr_register(mgr);
+	if (ret) {
+		fpga_mgr_free(mgr);
 		goto err_unmap;
+	}
 
 	ret = driver_create_file(&altera_cvp_driver.driver,
 				 &driver_attr_chkcfg);
 	if (ret) {
 		dev_err(&pdev->dev, "Can't create sysfs chkcfg file\n");
-		fpga_mgr_unregister(&pdev->dev);
+		fpga_mgr_unregister(mgr);
 		goto err_unmap;
 	}
 
@@ -483,7 +492,7 @@ static void altera_cvp_remove(struct pci_dev *pdev)
 	u16 cmd;
 
 	driver_remove_file(&altera_cvp_driver.driver, &driver_attr_chkcfg);
-	fpga_mgr_unregister(&pdev->dev);
+	fpga_mgr_unregister(mgr);
 	pci_iounmap(pdev, conf->map);
 	pci_release_region(pdev, CVP_BAR);
 	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
diff --git a/drivers/fpga/altera-fpga2sdram.c b/drivers/fpga/altera-fpga2sdram.c
index d4eeb74388da..23660ccd634b 100644
--- a/drivers/fpga/altera-fpga2sdram.c
+++ b/drivers/fpga/altera-fpga2sdram.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA to SDRAM Bridge Driver for Altera SoCFPGA Devices
  *
  *  Copyright (C) 2013-2016 Altera Corporation, All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
@@ -106,6 +95,7 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct alt_fpga2sdram_data *priv;
+	struct fpga_bridge *br;
 	u32 enable;
 	struct regmap *sysmgr;
 	int ret = 0;
@@ -131,10 +121,18 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 	/* Get f2s bridge configuration saved in handoff register */
 	regmap_read(sysmgr, SYSMGR_ISWGRP_HANDOFF3, &priv->mask);
 
-	ret = fpga_bridge_register(dev, F2S_BRIDGE_NAME,
-				   &altera_fpga2sdram_br_ops, priv);
-	if (ret)
+	br = fpga_bridge_create(dev, F2S_BRIDGE_NAME,
+				&altera_fpga2sdram_br_ops, priv);
+	if (!br)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, br);
+
+	ret = fpga_bridge_register(br);
+	if (ret) {
+		fpga_bridge_free(br);
 		return ret;
+	}
 
 	dev_info(dev, "driver initialized with handoff %08x\n", priv->mask);
 
@@ -146,7 +144,7 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 				 (enable ? "enabling" : "disabling"));
 			ret = _alt_fpga2sdram_enable_set(priv, enable);
 			if (ret) {
-				fpga_bridge_unregister(&pdev->dev);
+				fpga_bridge_unregister(br);
 				return ret;
 			}
 		}
@@ -157,7 +155,9 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 
 static int alt_fpga_bridge_remove(struct platform_device *pdev)
 {
-	fpga_bridge_unregister(&pdev->dev);
+	struct fpga_bridge *br = platform_get_drvdata(pdev);
+
+	fpga_bridge_unregister(br);
 
 	return 0;
 }
diff --git a/drivers/fpga/altera-freeze-bridge.c b/drivers/fpga/altera-freeze-bridge.c
index 6159cfcf78a2..ffd586c48ecf 100644
--- a/drivers/fpga/altera-freeze-bridge.c
+++ b/drivers/fpga/altera-freeze-bridge.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA Freeze Bridge Controller
  *
  *  Copyright (C) 2016 Altera Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -221,8 +210,10 @@ static int altera_freeze_br_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	void __iomem *base_addr;
 	struct altera_freeze_br_data *priv;
+	struct fpga_bridge *br;
 	struct resource *res;
 	u32 status, revision;
+	int ret;
 
 	if (!np)
 		return -ENODEV;
@@ -254,13 +245,27 @@ static int altera_freeze_br_probe(struct platform_device *pdev)
 
 	priv->base_addr = base_addr;
 
-	return fpga_bridge_register(dev, FREEZE_BRIDGE_NAME,
-				    &altera_freeze_br_br_ops, priv);
+	br = fpga_bridge_create(dev, FREEZE_BRIDGE_NAME,
+				&altera_freeze_br_br_ops, priv);
+	if (!br)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, br);
+
+	ret = fpga_bridge_register(br);
+	if (ret) {
+		fpga_bridge_free(br);
+		return ret;
+	}
+
+	return 0;
 }
 
 static int altera_freeze_br_remove(struct platform_device *pdev)
 {
-	fpga_bridge_unregister(&pdev->dev);
+	struct fpga_bridge *br = platform_get_drvdata(pdev);
+
+	fpga_bridge_unregister(br);
 
 	return 0;
 }
diff --git a/drivers/fpga/altera-hps2fpga.c b/drivers/fpga/altera-hps2fpga.c
index 406d2f10741f..a974d3f60321 100644
--- a/drivers/fpga/altera-hps2fpga.c
+++ b/drivers/fpga/altera-hps2fpga.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA to/from HPS Bridge Driver for Altera SoCFPGA Devices
  *
@@ -6,18 +7,6 @@
  * Includes this patch from the mailing list:
  *   fpga: altera-hps2fpga: fix HPS2FPGA bridge visibility to L3 masters
  *   Signed-off-by: Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
@@ -139,6 +128,7 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct altera_hps2fpga_data *priv;
 	const struct of_device_id *of_id;
+	struct fpga_bridge *br;
 	u32 enable;
 	int ret;
 
@@ -190,11 +180,24 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev)
 		}
 	}
 
-	ret = fpga_bridge_register(dev, priv->name, &altera_hps2fpga_br_ops,
-				   priv);
-err:
+	br = fpga_bridge_create(dev, priv->name, &altera_hps2fpga_br_ops, priv);
+	if (!br) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	platform_set_drvdata(pdev, br);
+
+	ret = fpga_bridge_register(br);
 	if (ret)
-		clk_disable_unprepare(priv->clk);
+		goto err_free;
+
+	return 0;
+
+err_free:
+	fpga_bridge_free(br);
+err:
+	clk_disable_unprepare(priv->clk);
 
 	return ret;
 }
@@ -204,7 +207,7 @@ static int alt_fpga_bridge_remove(struct platform_device *pdev)
 	struct fpga_bridge *bridge = platform_get_drvdata(pdev);
 	struct altera_hps2fpga_data *priv = bridge->priv;
 
-	fpga_bridge_unregister(&pdev->dev);
+	fpga_bridge_unregister(bridge);
 
 	clk_disable_unprepare(priv->clk);
 
diff --git a/drivers/fpga/altera-pr-ip-core-plat.c b/drivers/fpga/altera-pr-ip-core-plat.c
index 8fb36b8b4648..b293d83143f1 100644
--- a/drivers/fpga/altera-pr-ip-core-plat.c
+++ b/drivers/fpga/altera-pr-ip-core-plat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Driver for Altera Partial Reconfiguration IP Core
  *
@@ -5,18 +6,6 @@
  *
  * Based on socfpga-a10.c Copyright (C) 2015-2016 Altera Corporation
  *  by Alan Tull <atull@opensource.altera.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/fpga/altera-pr-ip-core.h>
 #include <linux/module.h>
diff --git a/drivers/fpga/altera-pr-ip-core.c b/drivers/fpga/altera-pr-ip-core.c
index a7b31f9797ce..65e0b6a2c031 100644
--- a/drivers/fpga/altera-pr-ip-core.c
+++ b/drivers/fpga/altera-pr-ip-core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Driver for Altera Partial Reconfiguration IP Core
  *
@@ -5,18 +6,6 @@
  *
  * Based on socfpga-a10.c Copyright (C) 2015-2016 Altera Corporation
  *  by Alan Tull <atull@opensource.altera.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/delay.h>
 #include <linux/fpga/altera-pr-ip-core.h>
@@ -187,6 +176,8 @@ static const struct fpga_manager_ops alt_pr_ops = {
 int alt_pr_register(struct device *dev, void __iomem *reg_base)
 {
 	struct alt_pr_priv *priv;
+	struct fpga_manager *mgr;
+	int ret;
 	u32 val;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -201,15 +192,27 @@ int alt_pr_register(struct device *dev, void __iomem *reg_base)
 		(val & ALT_PR_CSR_STATUS_MSK) >> ALT_PR_CSR_STATUS_SFT,
 		(int)(val & ALT_PR_CSR_PR_START));
 
-	return fpga_mgr_register(dev, dev_name(dev), &alt_pr_ops, priv);
+	mgr = fpga_mgr_create(dev, dev_name(dev), &alt_pr_ops, priv);
+	if (!mgr)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, mgr);
+
+	ret = fpga_mgr_register(mgr);
+	if (ret)
+		fpga_mgr_free(mgr);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(alt_pr_register);
 
 int alt_pr_unregister(struct device *dev)
 {
+	struct fpga_manager *mgr = dev_get_drvdata(dev);
+
 	dev_dbg(dev, "%s\n", __func__);
 
-	fpga_mgr_unregister(dev);
+	fpga_mgr_unregister(mgr);
 
 	return 0;
 }
diff --git a/drivers/fpga/altera-ps-spi.c b/drivers/fpga/altera-ps-spi.c
index 14f14efdf0d5..24b25c626036 100644
--- a/drivers/fpga/altera-ps-spi.c
+++ b/drivers/fpga/altera-ps-spi.c
@@ -238,6 +238,8 @@ static int altera_ps_probe(struct spi_device *spi)
 {
 	struct altera_ps_conf *conf;
 	const struct of_device_id *of_id;
+	struct fpga_manager *mgr;
+	int ret;
 
 	conf = devm_kzalloc(&spi->dev, sizeof(*conf), GFP_KERNEL);
 	if (!conf)
@@ -249,7 +251,7 @@ static int altera_ps_probe(struct spi_device *spi)
 
 	conf->data = of_id->data;
 	conf->spi = spi;
-	conf->config = devm_gpiod_get(&spi->dev, "nconfig", GPIOD_OUT_HIGH);
+	conf->config = devm_gpiod_get(&spi->dev, "nconfig", GPIOD_OUT_LOW);
 	if (IS_ERR(conf->config)) {
 		dev_err(&spi->dev, "Failed to get config gpio: %ld\n",
 			PTR_ERR(conf->config));
@@ -273,13 +275,25 @@ static int altera_ps_probe(struct spi_device *spi)
 	snprintf(conf->mgr_name, sizeof(conf->mgr_name), "%s %s",
 		 dev_driver_string(&spi->dev), dev_name(&spi->dev));
 
-	return fpga_mgr_register(&spi->dev, conf->mgr_name,
-				 &altera_ps_ops, conf);
+	mgr = fpga_mgr_create(&spi->dev, conf->mgr_name,
+			      &altera_ps_ops, conf);
+	if (!mgr)
+		return -ENOMEM;
+
+	spi_set_drvdata(spi, mgr);
+
+	ret = fpga_mgr_register(mgr);
+	if (ret)
+		fpga_mgr_free(mgr);
+
+	return ret;
 }
 
 static int altera_ps_remove(struct spi_device *spi)
 {
-	fpga_mgr_unregister(&spi->dev);
+	struct fpga_manager *mgr = spi_get_drvdata(spi);
+
+	fpga_mgr_unregister(mgr);
 
 	return 0;
 }
diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c
index 31bd2c59c305..24b8f98b73ec 100644
--- a/drivers/fpga/fpga-bridge.c
+++ b/drivers/fpga/fpga-bridge.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA Bridge Framework Driver
  *
  *  Copyright (C) 2013-2016 Altera Corporation, All Rights Reserved.
  *  Copyright (C) 2017 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/fpga/fpga-bridge.h>
 #include <linux/idr.h>
@@ -132,6 +121,7 @@ static int fpga_bridge_dev_match(struct device *dev, const void *data)
 /**
  * fpga_bridge_get - get an exclusive reference to a fpga bridge
  * @dev:	parent device that fpga bridge was registered with
+ * @info:	fpga manager info
  *
  * Given a device, get an exclusive reference to a fpga bridge.
  *
@@ -328,28 +318,29 @@ static struct attribute *fpga_bridge_attrs[] = {
 ATTRIBUTE_GROUPS(fpga_bridge);
 
 /**
- * fpga_bridge_register - register a fpga bridge driver
+ * fpga_bridge_create - create and initialize a struct fpga_bridge
  * @dev:	FPGA bridge device from pdev
  * @name:	FPGA bridge name
  * @br_ops:	pointer to structure of fpga bridge ops
  * @priv:	FPGA bridge private data
  *
- * Return: 0 for success, error code otherwise.
+ * Return: struct fpga_bridge or NULL
  */
-int fpga_bridge_register(struct device *dev, const char *name,
-			 const struct fpga_bridge_ops *br_ops, void *priv)
+struct fpga_bridge *fpga_bridge_create(struct device *dev, const char *name,
+				       const struct fpga_bridge_ops *br_ops,
+				       void *priv)
 {
 	struct fpga_bridge *bridge;
 	int id, ret = 0;
 
 	if (!name || !strlen(name)) {
 		dev_err(dev, "Attempt to register with no name!\n");
-		return -EINVAL;
+		return NULL;
 	}
 
 	bridge = kzalloc(sizeof(*bridge), GFP_KERNEL);
 	if (!bridge)
-		return -ENOMEM;
+		return NULL;
 
 	id = ida_simple_get(&fpga_bridge_ida, 0, 0, GFP_KERNEL);
 	if (id < 0) {
@@ -370,40 +361,62 @@ int fpga_bridge_register(struct device *dev, const char *name,
 	bridge->dev.parent = dev;
 	bridge->dev.of_node = dev->of_node;
 	bridge->dev.id = id;
-	dev_set_drvdata(dev, bridge);
 
 	ret = dev_set_name(&bridge->dev, "br%d", id);
 	if (ret)
 		goto error_device;
 
-	ret = device_add(&bridge->dev);
-	if (ret)
-		goto error_device;
-
-	of_platform_populate(dev->of_node, NULL, NULL, dev);
-
-	dev_info(bridge->dev.parent, "fpga bridge [%s] registered\n",
-		 bridge->name);
-
-	return 0;
+	return bridge;
 
 error_device:
 	ida_simple_remove(&fpga_bridge_ida, id);
 error_kfree:
 	kfree(bridge);
 
-	return ret;
+	return NULL;
 }
-EXPORT_SYMBOL_GPL(fpga_bridge_register);
+EXPORT_SYMBOL_GPL(fpga_bridge_create);
 
 /**
- * fpga_bridge_unregister - unregister a fpga bridge driver
- * @dev: FPGA bridge device from pdev
+ * fpga_bridge_free - free a fpga bridge and its id
+ * @bridge:	FPGA bridge struct created by fpga_bridge_create
  */
-void fpga_bridge_unregister(struct device *dev)
+void fpga_bridge_free(struct fpga_bridge *bridge)
 {
-	struct fpga_bridge *bridge = dev_get_drvdata(dev);
+	ida_simple_remove(&fpga_bridge_ida, bridge->dev.id);
+	kfree(bridge);
+}
+EXPORT_SYMBOL_GPL(fpga_bridge_free);
 
+/**
+ * fpga_bridge_register - register a fpga bridge
+ * @bridge:	FPGA bridge struct created by fpga_bridge_create
+ *
+ * Return: 0 for success, error code otherwise.
+ */
+int fpga_bridge_register(struct fpga_bridge *bridge)
+{
+	struct device *dev = &bridge->dev;
+	int ret;
+
+	ret = device_add(dev);
+	if (ret)
+		return ret;
+
+	of_platform_populate(dev->of_node, NULL, NULL, dev);
+
+	dev_info(dev->parent, "fpga bridge [%s] registered\n", bridge->name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fpga_bridge_register);
+
+/**
+ * fpga_bridge_unregister - unregister and free a fpga bridge
+ * @bridge:	FPGA bridge struct created by fpga_bridge_create
+ */
+void fpga_bridge_unregister(struct fpga_bridge *bridge)
+{
 	/*
 	 * If the low level driver provides a method for putting bridge into
 	 * a desired state upon unregister, do it.
@@ -419,8 +432,7 @@ static void fpga_bridge_dev_release(struct device *dev)
 {
 	struct fpga_bridge *bridge = to_fpga_bridge(dev);
 
-	ida_simple_remove(&fpga_bridge_ida, bridge->dev.id);
-	kfree(bridge);
+	fpga_bridge_free(bridge);
 }
 
 static int __init fpga_bridge_dev_init(void)
diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c
index 9939d2cbc9a6..c1564cf827fe 100644
--- a/drivers/fpga/fpga-mgr.c
+++ b/drivers/fpga/fpga-mgr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA Manager Core
  *
@@ -6,18 +7,6 @@
  *
  * With code from the mailing list:
  * Copyright (C) 2013 Xilinx, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/firmware.h>
 #include <linux/fpga/fpga-mgr.h>
@@ -32,6 +21,12 @@
 static DEFINE_IDA(fpga_mgr_ida);
 static struct class *fpga_mgr_class;
 
+/**
+ * fpga_image_info_alloc - Allocate a FPGA image info struct
+ * @dev: owning device
+ *
+ * Return: struct fpga_image_info or NULL
+ */
 struct fpga_image_info *fpga_image_info_alloc(struct device *dev)
 {
 	struct fpga_image_info *info;
@@ -50,6 +45,10 @@ struct fpga_image_info *fpga_image_info_alloc(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(fpga_image_info_alloc);
 
+/**
+ * fpga_image_info_free - Free a FPGA image info struct
+ * @info: FPGA image info struct to free
+ */
 void fpga_image_info_free(struct fpga_image_info *info)
 {
 	struct device *dev;
@@ -234,7 +233,7 @@ static int fpga_mgr_buf_load_mapped(struct fpga_manager *mgr,
 /**
  * fpga_mgr_buf_load - load fpga from image in buffer
  * @mgr:	fpga manager
- * @flags:	flags setting fpga confuration modes
+ * @info:	fpga image info
  * @buf:	buffer contain fpga image
  * @count:	byte count of buf
  *
@@ -343,6 +342,16 @@ static int fpga_mgr_firmware_load(struct fpga_manager *mgr,
 	return ret;
 }
 
+/**
+ * fpga_mgr_load - load FPGA from scatter/gather table, buffer, or firmware
+ * @mgr:	fpga manager
+ * @info:	fpga image information.
+ *
+ * Load the FPGA from an image which is indicated in @info.  If successful, the
+ * FPGA ends up in operating mode.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
 int fpga_mgr_load(struct fpga_manager *mgr, struct fpga_image_info *info)
 {
 	if (info->sgt)
@@ -429,11 +438,9 @@ static int fpga_mgr_dev_match(struct device *dev, const void *data)
 }
 
 /**
- * fpga_mgr_get - get a reference to a fpga mgr
+ * fpga_mgr_get - Given a device, get a reference to a fpga mgr.
  * @dev:	parent device that fpga mgr was registered with
  *
- * Given a device, get a reference to a fpga mgr.
- *
  * Return: fpga manager struct or IS_ERR() condition containing error code.
  */
 struct fpga_manager *fpga_mgr_get(struct device *dev)
@@ -453,10 +460,9 @@ static int fpga_mgr_of_node_match(struct device *dev, const void *data)
 }
 
 /**
- * of_fpga_mgr_get - get a reference to a fpga mgr
- * @node:	device node
+ * of_fpga_mgr_get - Given a device node, get a reference to a fpga mgr.
  *
- * Given a device node, get a reference to a fpga mgr.
+ * @node:	device node
  *
  * Return: fpga manager struct or IS_ERR() condition containing error code.
  */
@@ -489,7 +495,10 @@ EXPORT_SYMBOL_GPL(fpga_mgr_put);
  * @mgr:	fpga manager
  *
  * Given a pointer to FPGA Manager (from fpga_mgr_get() or
- * of_fpga_mgr_put()) attempt to get the mutex.
+ * of_fpga_mgr_put()) attempt to get the mutex. The user should call
+ * fpga_mgr_lock() and verify that it returns 0 before attempting to
+ * program the FPGA.  Likewise, the user should call fpga_mgr_unlock
+ * when done programming the FPGA.
  *
  * Return: 0 for success or -EBUSY
  */
@@ -505,7 +514,7 @@ int fpga_mgr_lock(struct fpga_manager *mgr)
 EXPORT_SYMBOL_GPL(fpga_mgr_lock);
 
 /**
- * fpga_mgr_unlock - Unlock FPGA manager
+ * fpga_mgr_unlock - Unlock FPGA manager after done programming
  * @mgr:	fpga manager
  */
 void fpga_mgr_unlock(struct fpga_manager *mgr)
@@ -515,17 +524,17 @@ void fpga_mgr_unlock(struct fpga_manager *mgr)
 EXPORT_SYMBOL_GPL(fpga_mgr_unlock);
 
 /**
- * fpga_mgr_register - register a low level fpga manager driver
+ * fpga_mgr_create - create and initialize a FPGA manager struct
  * @dev:	fpga manager device from pdev
  * @name:	fpga manager name
  * @mops:	pointer to structure of fpga manager ops
  * @priv:	fpga manager private data
  *
- * Return: 0 on success, negative error code otherwise.
+ * Return: pointer to struct fpga_manager or NULL
  */
-int fpga_mgr_register(struct device *dev, const char *name,
-		      const struct fpga_manager_ops *mops,
-		      void *priv)
+struct fpga_manager *fpga_mgr_create(struct device *dev, const char *name,
+				     const struct fpga_manager_ops *mops,
+				     void *priv)
 {
 	struct fpga_manager *mgr;
 	int id, ret;
@@ -534,17 +543,17 @@ int fpga_mgr_register(struct device *dev, const char *name,
 	    !mops->write_init || (!mops->write && !mops->write_sg) ||
 	    (mops->write && mops->write_sg)) {
 		dev_err(dev, "Attempt to register without fpga_manager_ops\n");
-		return -EINVAL;
+		return NULL;
 	}
 
 	if (!name || !strlen(name)) {
 		dev_err(dev, "Attempt to register with no name!\n");
-		return -EINVAL;
+		return NULL;
 	}
 
 	mgr = kzalloc(sizeof(*mgr), GFP_KERNEL);
 	if (!mgr)
-		return -ENOMEM;
+		return NULL;
 
 	id = ida_simple_get(&fpga_mgr_ida, 0, 0, GFP_KERNEL);
 	if (id < 0) {
@@ -558,25 +567,56 @@ int fpga_mgr_register(struct device *dev, const char *name,
 	mgr->mops = mops;
 	mgr->priv = priv;
 
-	/*
-	 * Initialize framework state by requesting low level driver read state
-	 * from device.  FPGA may be in reset mode or may have been programmed
-	 * by bootloader or EEPROM.
-	 */
-	mgr->state = mgr->mops->state(mgr);
-
 	device_initialize(&mgr->dev);
 	mgr->dev.class = fpga_mgr_class;
 	mgr->dev.groups = mops->groups;
 	mgr->dev.parent = dev;
 	mgr->dev.of_node = dev->of_node;
 	mgr->dev.id = id;
-	dev_set_drvdata(dev, mgr);
 
 	ret = dev_set_name(&mgr->dev, "fpga%d", id);
 	if (ret)
 		goto error_device;
 
+	return mgr;
+
+error_device:
+	ida_simple_remove(&fpga_mgr_ida, id);
+error_kfree:
+	kfree(mgr);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(fpga_mgr_create);
+
+/**
+ * fpga_mgr_free - deallocate a FPGA manager
+ * @mgr:	fpga manager struct created by fpga_mgr_create
+ */
+void fpga_mgr_free(struct fpga_manager *mgr)
+{
+	ida_simple_remove(&fpga_mgr_ida, mgr->dev.id);
+	kfree(mgr);
+}
+EXPORT_SYMBOL_GPL(fpga_mgr_free);
+
+/**
+ * fpga_mgr_register - register a FPGA manager
+ * @mgr:	fpga manager struct created by fpga_mgr_create
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int fpga_mgr_register(struct fpga_manager *mgr)
+{
+	int ret;
+
+	/*
+	 * Initialize framework state by requesting low level driver read state
+	 * from device.  FPGA may be in reset mode or may have been programmed
+	 * by bootloader or EEPROM.
+	 */
+	mgr->state = mgr->mops->state(mgr);
+
 	ret = device_add(&mgr->dev);
 	if (ret)
 		goto error_device;
@@ -586,22 +626,18 @@ int fpga_mgr_register(struct device *dev, const char *name,
 	return 0;
 
 error_device:
-	ida_simple_remove(&fpga_mgr_ida, id);
-error_kfree:
-	kfree(mgr);
+	ida_simple_remove(&fpga_mgr_ida, mgr->dev.id);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(fpga_mgr_register);
 
 /**
- * fpga_mgr_unregister - unregister a low level fpga manager driver
- * @dev:	fpga manager device from pdev
+ * fpga_mgr_unregister - unregister and free a FPGA manager
+ * @mgr:	fpga manager struct
  */
-void fpga_mgr_unregister(struct device *dev)
+void fpga_mgr_unregister(struct fpga_manager *mgr)
 {
-	struct fpga_manager *mgr = dev_get_drvdata(dev);
-
 	dev_info(&mgr->dev, "%s %s\n", __func__, mgr->name);
 
 	/*
@@ -619,8 +655,7 @@ static void fpga_mgr_dev_release(struct device *dev)
 {
 	struct fpga_manager *mgr = to_fpga_manager(dev);
 
-	ida_simple_remove(&fpga_mgr_ida, mgr->dev.id);
-	kfree(mgr);
+	fpga_mgr_free(mgr);
 }
 
 static int __init fpga_mgr_class_init(void)
diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c
index edab2a2e03ef..6d214d75c7be 100644
--- a/drivers/fpga/fpga-region.c
+++ b/drivers/fpga/fpga-region.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA Region - Device Tree support for FPGA programming under Linux
  *
  *  Copyright (C) 2013-2016 Altera Corporation
  *  Copyright (C) 2017 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-
 #include <linux/fpga/fpga-bridge.h>
 #include <linux/fpga/fpga-mgr.h>
 #include <linux/fpga/fpga-region.h>
@@ -93,8 +81,16 @@ static void fpga_region_put(struct fpga_region *region)
 
 /**
  * fpga_region_program_fpga - program FPGA
+ *
  * @region: FPGA region
+ *
  * Program an FPGA using fpga image info (region->info).
+ * If the region has a get_bridges function, the exclusive reference for the
+ * bridges will be held if programming succeeds.  This is intended to prevent
+ * reprogramming the region until the caller considers it safe to do so.
+ * The caller will need to call fpga_bridges_put() before attempting to
+ * reprogram the region.
+ *
  * Return 0 for success or negative error code.
  */
 int fpga_region_program_fpga(struct fpga_region *region)
@@ -162,45 +158,86 @@ err_put_region:
 }
 EXPORT_SYMBOL_GPL(fpga_region_program_fpga);
 
-int fpga_region_register(struct device *dev, struct fpga_region *region)
+/**
+ * fpga_region_create - alloc and init a struct fpga_region
+ * @dev: device parent
+ * @mgr: manager that programs this region
+ * @get_bridges: optional function to get bridges to a list
+ *
+ * Return: struct fpga_region or NULL
+ */
+struct fpga_region
+*fpga_region_create(struct device *dev,
+		    struct fpga_manager *mgr,
+		    int (*get_bridges)(struct fpga_region *))
 {
+	struct fpga_region *region;
 	int id, ret = 0;
 
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region)
+		return NULL;
+
 	id = ida_simple_get(&fpga_region_ida, 0, 0, GFP_KERNEL);
 	if (id < 0)
-		return id;
+		goto err_free;
 
+	region->mgr = mgr;
+	region->get_bridges = get_bridges;
 	mutex_init(&region->mutex);
 	INIT_LIST_HEAD(&region->bridge_list);
+
 	device_initialize(&region->dev);
-	region->dev.groups = region->groups;
 	region->dev.class = fpga_region_class;
 	region->dev.parent = dev;
 	region->dev.of_node = dev->of_node;
 	region->dev.id = id;
-	dev_set_drvdata(dev, region);
 
 	ret = dev_set_name(&region->dev, "region%d", id);
 	if (ret)
 		goto err_remove;
 
-	ret = device_add(&region->dev);
-	if (ret)
-		goto err_remove;
-
-	return 0;
+	return region;
 
 err_remove:
 	ida_simple_remove(&fpga_region_ida, id);
-	return ret;
+err_free:
+	kfree(region);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(fpga_region_create);
+
+/**
+ * fpga_region_free - free a struct fpga_region
+ * @region: FPGA region created by fpga_region_create
+ */
+void fpga_region_free(struct fpga_region *region)
+{
+	ida_simple_remove(&fpga_region_ida, region->dev.id);
+	kfree(region);
+}
+EXPORT_SYMBOL_GPL(fpga_region_free);
+
+/**
+ * fpga_region_register - register a FPGA region
+ * @region: FPGA region created by fpga_region_create
+ * Return: 0 or -errno
+ */
+int fpga_region_register(struct fpga_region *region)
+{
+	return device_add(&region->dev);
+
 }
 EXPORT_SYMBOL_GPL(fpga_region_register);
 
-int fpga_region_unregister(struct fpga_region *region)
+/**
+ * fpga_region_unregister - unregister and free a FPGA region
+ * @region: FPGA region
+ */
+void fpga_region_unregister(struct fpga_region *region)
 {
 	device_unregister(&region->dev);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(fpga_region_unregister);
 
@@ -208,7 +245,7 @@ static void fpga_region_dev_release(struct device *dev)
 {
 	struct fpga_region *region = to_fpga_region(dev);
 
-	ida_simple_remove(&fpga_region_ida, region->dev.id);
+	fpga_region_free(region);
 }
 
 /**
diff --git a/drivers/fpga/ice40-spi.c b/drivers/fpga/ice40-spi.c
index 7fca82023062..5981c7ee7a7d 100644
--- a/drivers/fpga/ice40-spi.c
+++ b/drivers/fpga/ice40-spi.c
@@ -133,6 +133,7 @@ static int ice40_fpga_probe(struct spi_device *spi)
 {
 	struct device *dev = &spi->dev;
 	struct ice40_fpga_priv *priv;
+	struct fpga_manager *mgr;
 	int ret;
 
 	priv = devm_kzalloc(&spi->dev, sizeof(*priv), GFP_KERNEL);
@@ -174,14 +175,26 @@ static int ice40_fpga_probe(struct spi_device *spi)
 		return ret;
 	}
 
-	/* Register with the FPGA manager */
-	return fpga_mgr_register(dev, "Lattice iCE40 FPGA Manager",
-				 &ice40_fpga_ops, priv);
+	mgr = fpga_mgr_create(dev, "Lattice iCE40 FPGA Manager",
+			      &ice40_fpga_ops, priv);
+	if (!mgr)
+		return -ENOMEM;
+
+	spi_set_drvdata(spi, mgr);
+
+	ret = fpga_mgr_register(mgr);
+	if (ret)
+		fpga_mgr_free(mgr);
+
+	return ret;
 }
 
 static int ice40_fpga_remove(struct spi_device *spi)
 {
-	fpga_mgr_unregister(&spi->dev);
+	struct fpga_manager *mgr = spi_get_drvdata(spi);
+
+	fpga_mgr_unregister(mgr);
+
 	return 0;
 }
 
diff --git a/drivers/fpga/machxo2-spi.c b/drivers/fpga/machxo2-spi.c
new file mode 100644
index 000000000000..a582e0000c97
--- /dev/null
+++ b/drivers/fpga/machxo2-spi.c
@@ -0,0 +1,415 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Lattice MachXO2 Slave SPI Driver
+ *
+ * Manage Lattice FPGA firmware that is loaded over SPI using
+ * the slave serial configuration interface.
+ *
+ * Copyright (C) 2018 Paolo Pisati <p.pisati@gmail.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/fpga/fpga-mgr.h>
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+
+/* MachXO2 Programming Guide - sysCONFIG Programming Commands */
+#define IDCODE_PUB		{0xe0, 0x00, 0x00, 0x00}
+#define ISC_ENABLE		{0xc6, 0x08, 0x00, 0x00}
+#define ISC_ERASE		{0x0e, 0x04, 0x00, 0x00}
+#define ISC_PROGRAMDONE		{0x5e, 0x00, 0x00, 0x00}
+#define LSC_INITADDRESS		{0x46, 0x00, 0x00, 0x00}
+#define LSC_PROGINCRNV		{0x70, 0x00, 0x00, 0x01}
+#define LSC_READ_STATUS		{0x3c, 0x00, 0x00, 0x00}
+#define LSC_REFRESH		{0x79, 0x00, 0x00, 0x00}
+
+/*
+ * Max CCLK in Slave SPI mode according to 'MachXO2 Family Data
+ * Sheet' sysCONFIG Port Timing Specifications (3-36)
+ */
+#define MACHXO2_MAX_SPEED		66000000
+
+#define MACHXO2_LOW_DELAY_USEC		5
+#define MACHXO2_HIGH_DELAY_USEC		200
+#define MACHXO2_REFRESH_USEC		4800
+#define MACHXO2_MAX_BUSY_LOOP		128
+#define MACHXO2_MAX_REFRESH_LOOP	16
+
+#define MACHXO2_PAGE_SIZE		16
+#define MACHXO2_BUF_SIZE		(MACHXO2_PAGE_SIZE + 4)
+
+/* Status register bits, errors and error mask */
+#define BUSY	12
+#define DONE	8
+#define DVER	27
+#define ENAB	9
+#define ERRBITS	23
+#define ERRMASK	7
+#define FAIL	13
+
+#define ENOERR	0 /* no error */
+#define EID	1
+#define ECMD	2
+#define ECRC	3
+#define EPREAM	4 /* preamble error */
+#define EABRT	5 /* abort error */
+#define EOVERFL	6 /* overflow error */
+#define ESDMEOF	7 /* SDM EOF */
+
+static inline u8 get_err(unsigned long *status)
+{
+	return (*status >> ERRBITS) & ERRMASK;
+}
+
+static int get_status(struct spi_device *spi, unsigned long *status)
+{
+	struct spi_message msg;
+	struct spi_transfer rx, tx;
+	static const u8 cmd[] = LSC_READ_STATUS;
+	int ret;
+
+	memset(&rx, 0, sizeof(rx));
+	memset(&tx, 0, sizeof(tx));
+	tx.tx_buf = cmd;
+	tx.len = sizeof(cmd);
+	rx.rx_buf = status;
+	rx.len = 4;
+	spi_message_init(&msg);
+	spi_message_add_tail(&tx, &msg);
+	spi_message_add_tail(&rx, &msg);
+	ret = spi_sync(spi, &msg);
+	if (ret)
+		return ret;
+
+	*status = be32_to_cpu(*status);
+
+	return 0;
+}
+
+#ifdef DEBUG
+static const char *get_err_string(u8 err)
+{
+	switch (err) {
+	case ENOERR:	return "No Error";
+	case EID:	return "ID ERR";
+	case ECMD:	return "CMD ERR";
+	case ECRC:	return "CRC ERR";
+	case EPREAM:	return "Preamble ERR";
+	case EABRT:	return "Abort ERR";
+	case EOVERFL:	return "Overflow ERR";
+	case ESDMEOF:	return "SDM EOF";
+	}
+
+	return "Default switch case";
+}
+#endif
+
+static void dump_status_reg(unsigned long *status)
+{
+#ifdef DEBUG
+	pr_debug("machxo2 status: 0x%08lX - done=%d, cfgena=%d, busy=%d, fail=%d, devver=%d, err=%s\n",
+		 *status, test_bit(DONE, status), test_bit(ENAB, status),
+		 test_bit(BUSY, status), test_bit(FAIL, status),
+		 test_bit(DVER, status), get_err_string(get_err(status)));
+#endif
+}
+
+static int wait_until_not_busy(struct spi_device *spi)
+{
+	unsigned long status;
+	int ret, loop = 0;
+
+	do {
+		ret = get_status(spi, &status);
+		if (ret)
+			return ret;
+		if (++loop >= MACHXO2_MAX_BUSY_LOOP)
+			return -EBUSY;
+	} while (test_bit(BUSY, &status));
+
+	return 0;
+}
+
+static int machxo2_cleanup(struct fpga_manager *mgr)
+{
+	struct spi_device *spi = mgr->priv;
+	struct spi_message msg;
+	struct spi_transfer tx[2];
+	static const u8 erase[] = ISC_ERASE;
+	static const u8 refresh[] = LSC_REFRESH;
+	int ret;
+
+	memset(tx, 0, sizeof(tx));
+	spi_message_init(&msg);
+	tx[0].tx_buf = &erase;
+	tx[0].len = sizeof(erase);
+	spi_message_add_tail(&tx[0], &msg);
+	ret = spi_sync(spi, &msg);
+	if (ret)
+		goto fail;
+
+	ret = wait_until_not_busy(spi);
+	if (ret)
+		goto fail;
+
+	spi_message_init(&msg);
+	tx[1].tx_buf = &refresh;
+	tx[1].len = sizeof(refresh);
+	tx[1].delay_usecs = MACHXO2_REFRESH_USEC;
+	spi_message_add_tail(&tx[1], &msg);
+	ret = spi_sync(spi, &msg);
+	if (ret)
+		goto fail;
+
+	return 0;
+fail:
+	dev_err(&mgr->dev, "Cleanup failed\n");
+
+	return ret;
+}
+
+static enum fpga_mgr_states machxo2_spi_state(struct fpga_manager *mgr)
+{
+	struct spi_device *spi = mgr->priv;
+	unsigned long status;
+
+	get_status(spi, &status);
+	if (!test_bit(BUSY, &status) && test_bit(DONE, &status) &&
+	    get_err(&status) == ENOERR)
+		return FPGA_MGR_STATE_OPERATING;
+
+	return FPGA_MGR_STATE_UNKNOWN;
+}
+
+static int machxo2_write_init(struct fpga_manager *mgr,
+			      struct fpga_image_info *info,
+			      const char *buf, size_t count)
+{
+	struct spi_device *spi = mgr->priv;
+	struct spi_message msg;
+	struct spi_transfer tx[3];
+	static const u8 enable[] = ISC_ENABLE;
+	static const u8 erase[] = ISC_ERASE;
+	static const u8 initaddr[] = LSC_INITADDRESS;
+	unsigned long status;
+	int ret;
+
+	if ((info->flags & FPGA_MGR_PARTIAL_RECONFIG)) {
+		dev_err(&mgr->dev,
+			"Partial reconfiguration is not supported\n");
+		return -ENOTSUPP;
+	}
+
+	get_status(spi, &status);
+	dump_status_reg(&status);
+	memset(tx, 0, sizeof(tx));
+	spi_message_init(&msg);
+	tx[0].tx_buf = &enable;
+	tx[0].len = sizeof(enable);
+	tx[0].delay_usecs = MACHXO2_LOW_DELAY_USEC;
+	spi_message_add_tail(&tx[0], &msg);
+
+	tx[1].tx_buf = &erase;
+	tx[1].len = sizeof(erase);
+	spi_message_add_tail(&tx[1], &msg);
+	ret = spi_sync(spi, &msg);
+	if (ret)
+		goto fail;
+
+	ret = wait_until_not_busy(spi);
+	if (ret)
+		goto fail;
+
+	get_status(spi, &status);
+	if (test_bit(FAIL, &status))
+		goto fail;
+	dump_status_reg(&status);
+
+	spi_message_init(&msg);
+	tx[2].tx_buf = &initaddr;
+	tx[2].len = sizeof(initaddr);
+	spi_message_add_tail(&tx[2], &msg);
+	ret = spi_sync(spi, &msg);
+	if (ret)
+		goto fail;
+
+	get_status(spi, &status);
+	dump_status_reg(&status);
+
+	return 0;
+fail:
+	dev_err(&mgr->dev, "Error during FPGA init.\n");
+
+	return ret;
+}
+
+static int machxo2_write(struct fpga_manager *mgr, const char *buf,
+			 size_t count)
+{
+	struct spi_device *spi = mgr->priv;
+	struct spi_message msg;
+	struct spi_transfer tx;
+	static const u8 progincr[] = LSC_PROGINCRNV;
+	u8 payload[MACHXO2_BUF_SIZE];
+	unsigned long status;
+	int i, ret;
+
+	if (count % MACHXO2_PAGE_SIZE != 0) {
+		dev_err(&mgr->dev, "Malformed payload.\n");
+		return -EINVAL;
+	}
+	get_status(spi, &status);
+	dump_status_reg(&status);
+	memcpy(payload, &progincr, sizeof(progincr));
+	for (i = 0; i < count; i += MACHXO2_PAGE_SIZE) {
+		memcpy(&payload[sizeof(progincr)], &buf[i], MACHXO2_PAGE_SIZE);
+		memset(&tx, 0, sizeof(tx));
+		spi_message_init(&msg);
+		tx.tx_buf = payload;
+		tx.len = MACHXO2_BUF_SIZE;
+		tx.delay_usecs = MACHXO2_HIGH_DELAY_USEC;
+		spi_message_add_tail(&tx, &msg);
+		ret = spi_sync(spi, &msg);
+		if (ret) {
+			dev_err(&mgr->dev, "Error loading the bitstream.\n");
+			return ret;
+		}
+	}
+	get_status(spi, &status);
+	dump_status_reg(&status);
+
+	return 0;
+}
+
+static int machxo2_write_complete(struct fpga_manager *mgr,
+				  struct fpga_image_info *info)
+{
+	struct spi_device *spi = mgr->priv;
+	struct spi_message msg;
+	struct spi_transfer tx[2];
+	static const u8 progdone[] = ISC_PROGRAMDONE;
+	static const u8 refresh[] = LSC_REFRESH;
+	unsigned long status;
+	int ret, refreshloop = 0;
+
+	memset(tx, 0, sizeof(tx));
+	spi_message_init(&msg);
+	tx[0].tx_buf = &progdone;
+	tx[0].len = sizeof(progdone);
+	spi_message_add_tail(&tx[0], &msg);
+	ret = spi_sync(spi, &msg);
+	if (ret)
+		goto fail;
+	ret = wait_until_not_busy(spi);
+	if (ret)
+		goto fail;
+
+	get_status(spi, &status);
+	dump_status_reg(&status);
+	if (!test_bit(DONE, &status)) {
+		machxo2_cleanup(mgr);
+		goto fail;
+	}
+
+	do {
+		spi_message_init(&msg);
+		tx[1].tx_buf = &refresh;
+		tx[1].len = sizeof(refresh);
+		tx[1].delay_usecs = MACHXO2_REFRESH_USEC;
+		spi_message_add_tail(&tx[1], &msg);
+		ret = spi_sync(spi, &msg);
+		if (ret)
+			goto fail;
+
+		/* check refresh status */
+		get_status(spi, &status);
+		dump_status_reg(&status);
+		if (!test_bit(BUSY, &status) && test_bit(DONE, &status) &&
+		    get_err(&status) == ENOERR)
+			break;
+		if (++refreshloop == MACHXO2_MAX_REFRESH_LOOP) {
+			machxo2_cleanup(mgr);
+			goto fail;
+		}
+	} while (1);
+
+	get_status(spi, &status);
+	dump_status_reg(&status);
+
+	return 0;
+fail:
+	dev_err(&mgr->dev, "Refresh failed.\n");
+
+	return ret;
+}
+
+static const struct fpga_manager_ops machxo2_ops = {
+	.state = machxo2_spi_state,
+	.write_init = machxo2_write_init,
+	.write = machxo2_write,
+	.write_complete = machxo2_write_complete,
+};
+
+static int machxo2_spi_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct fpga_manager *mgr;
+	int ret;
+
+	if (spi->max_speed_hz > MACHXO2_MAX_SPEED) {
+		dev_err(dev, "Speed is too high\n");
+		return -EINVAL;
+	}
+
+	mgr = fpga_mgr_create(dev, "Lattice MachXO2 SPI FPGA Manager",
+			      &machxo2_ops, spi);
+	if (!mgr)
+		return -ENOMEM;
+
+	spi_set_drvdata(spi, mgr);
+
+	ret = fpga_mgr_register(mgr);
+	if (ret)
+		fpga_mgr_free(mgr);
+
+	return ret;
+}
+
+static int machxo2_spi_remove(struct spi_device *spi)
+{
+	struct fpga_manager *mgr = spi_get_drvdata(spi);
+
+	fpga_mgr_unregister(mgr);
+
+	return 0;
+}
+
+static const struct of_device_id of_match[] = {
+	{ .compatible = "lattice,machxo2-slave-spi", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, of_match);
+
+static const struct spi_device_id lattice_ids[] = {
+	{ "machxo2-slave-spi", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(spi, lattice_ids);
+
+static struct spi_driver machxo2_spi_driver = {
+	.driver = {
+		.name = "machxo2-slave-spi",
+		.of_match_table = of_match_ptr(of_match),
+	},
+	.probe = machxo2_spi_probe,
+	.remove = machxo2_spi_remove,
+	.id_table = lattice_ids,
+};
+
+module_spi_driver(machxo2_spi_driver)
+
+MODULE_AUTHOR("Paolo Pisati <p.pisati@gmail.com>");
+MODULE_DESCRIPTION("Load Lattice FPGA firmware over SPI");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c
index 119ff75522f1..35fabb8083fb 100644
--- a/drivers/fpga/of-fpga-region.c
+++ b/drivers/fpga/of-fpga-region.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA Region - Device Tree support for FPGA programming under Linux
  *
  *  Copyright (C) 2013-2016 Altera Corporation
  *  Copyright (C) 2017 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-
 #include <linux/fpga/fpga-bridge.h>
 #include <linux/fpga/fpga-mgr.h>
 #include <linux/fpga/fpga-region.h>
@@ -422,27 +410,25 @@ static int of_fpga_region_probe(struct platform_device *pdev)
 	if (IS_ERR(mgr))
 		return -EPROBE_DEFER;
 
-	region = devm_kzalloc(dev, sizeof(*region), GFP_KERNEL);
+	region = fpga_region_create(dev, mgr, of_fpga_region_get_bridges);
 	if (!region) {
 		ret = -ENOMEM;
 		goto eprobe_mgr_put;
 	}
 
-	region->mgr = mgr;
-
-	/* Specify how to get bridges for this type of region. */
-	region->get_bridges = of_fpga_region_get_bridges;
-
-	ret = fpga_region_register(dev, region);
+	ret = fpga_region_register(region);
 	if (ret)
-		goto eprobe_mgr_put;
+		goto eprobe_free;
 
 	of_platform_populate(np, fpga_region_of_match, NULL, &region->dev);
+	dev_set_drvdata(dev, region);
 
 	dev_info(dev, "FPGA Region probed\n");
 
 	return 0;
 
+eprobe_free:
+	fpga_region_free(region);
 eprobe_mgr_put:
 	fpga_mgr_put(mgr);
 	return ret;
diff --git a/drivers/fpga/socfpga-a10.c b/drivers/fpga/socfpga-a10.c
index a46e343a5b72..be30c48eb6e4 100644
--- a/drivers/fpga/socfpga-a10.c
+++ b/drivers/fpga/socfpga-a10.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA Manager Driver for Altera Arria10 SoCFPGA
  *
  * Copyright (C) 2015-2016 Altera Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/delay.h>
@@ -482,6 +470,7 @@ static int socfpga_a10_fpga_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct a10_fpga_priv *priv;
 	void __iomem *reg_base;
+	struct fpga_manager *mgr;
 	struct resource *res;
 	int ret;
 
@@ -519,9 +508,16 @@ static int socfpga_a10_fpga_probe(struct platform_device *pdev)
 		return -EBUSY;
 	}
 
-	ret = fpga_mgr_register(dev, "SoCFPGA Arria10 FPGA Manager",
-				 &socfpga_a10_fpga_mgr_ops, priv);
+	mgr = fpga_mgr_create(dev, "SoCFPGA Arria10 FPGA Manager",
+			      &socfpga_a10_fpga_mgr_ops, priv);
+	if (!mgr)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, mgr);
+
+	ret = fpga_mgr_register(mgr);
 	if (ret) {
+		fpga_mgr_free(mgr);
 		clk_disable_unprepare(priv->clk);
 		return ret;
 	}
@@ -534,7 +530,7 @@ static int socfpga_a10_fpga_remove(struct platform_device *pdev)
 	struct fpga_manager *mgr = platform_get_drvdata(pdev);
 	struct a10_fpga_priv *priv = mgr->priv;
 
-	fpga_mgr_unregister(&pdev->dev);
+	fpga_mgr_unregister(mgr);
 	clk_disable_unprepare(priv->clk);
 
 	return 0;
diff --git a/drivers/fpga/socfpga.c b/drivers/fpga/socfpga.c
index b6672e66cda6..959d71f26896 100644
--- a/drivers/fpga/socfpga.c
+++ b/drivers/fpga/socfpga.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * FPGA Manager Driver for Altera SOCFPGA
  *
  *  Copyright (C) 2013-2015 Altera Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/completion.h>
 #include <linux/delay.h>
@@ -555,6 +544,7 @@ static int socfpga_fpga_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct socfpga_fpga_priv *priv;
+	struct fpga_manager *mgr;
 	struct resource *res;
 	int ret;
 
@@ -581,13 +571,25 @@ static int socfpga_fpga_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return fpga_mgr_register(dev, "Altera SOCFPGA FPGA Manager",
-				 &socfpga_fpga_ops, priv);
+	mgr = fpga_mgr_create(dev, "Altera SOCFPGA FPGA Manager",
+			      &socfpga_fpga_ops, priv);
+	if (!mgr)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, mgr);
+
+	ret = fpga_mgr_register(mgr);
+	if (ret)
+		fpga_mgr_free(mgr);
+
+	return ret;
 }
 
 static int socfpga_fpga_remove(struct platform_device *pdev)
 {
-	fpga_mgr_unregister(&pdev->dev);
+	struct fpga_manager *mgr = platform_get_drvdata(pdev);
+
+	fpga_mgr_unregister(mgr);
 
 	return 0;
 }
diff --git a/drivers/fpga/ts73xx-fpga.c b/drivers/fpga/ts73xx-fpga.c
index f6a96b42e2ca..08efd1895b1b 100644
--- a/drivers/fpga/ts73xx-fpga.c
+++ b/drivers/fpga/ts73xx-fpga.c
@@ -116,7 +116,9 @@ static int ts73xx_fpga_probe(struct platform_device *pdev)
 {
 	struct device *kdev = &pdev->dev;
 	struct ts73xx_fpga_priv *priv;
+	struct fpga_manager *mgr;
 	struct resource *res;
+	int ret;
 
 	priv = devm_kzalloc(kdev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -131,13 +133,25 @@ static int ts73xx_fpga_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->io_base);
 	}
 
-	return fpga_mgr_register(kdev, "TS-73xx FPGA Manager",
-				 &ts73xx_fpga_ops, priv);
+	mgr = fpga_mgr_create(kdev, "TS-73xx FPGA Manager",
+			      &ts73xx_fpga_ops, priv);
+	if (!mgr)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, mgr);
+
+	ret = fpga_mgr_register(mgr);
+	if (ret)
+		fpga_mgr_free(mgr);
+
+	return ret;
 }
 
 static int ts73xx_fpga_remove(struct platform_device *pdev)
 {
-	fpga_mgr_unregister(&pdev->dev);
+	struct fpga_manager *mgr = platform_get_drvdata(pdev);
+
+	fpga_mgr_unregister(mgr);
 
 	return 0;
 }
diff --git a/drivers/fpga/xilinx-pr-decoupler.c b/drivers/fpga/xilinx-pr-decoupler.c
index 0d7743089414..07ba1539e82c 100644
--- a/drivers/fpga/xilinx-pr-decoupler.c
+++ b/drivers/fpga/xilinx-pr-decoupler.c
@@ -94,6 +94,7 @@ MODULE_DEVICE_TABLE(of, xlnx_pr_decoupler_of_match);
 static int xlnx_pr_decoupler_probe(struct platform_device *pdev)
 {
 	struct xlnx_pr_decoupler_data *priv;
+	struct fpga_bridge *br;
 	int err;
 	struct resource *res;
 
@@ -120,16 +121,27 @@ static int xlnx_pr_decoupler_probe(struct platform_device *pdev)
 
 	clk_disable(priv->clk);
 
-	err = fpga_bridge_register(&pdev->dev, "Xilinx PR Decoupler",
-				   &xlnx_pr_decoupler_br_ops, priv);
+	br = fpga_bridge_create(&pdev->dev, "Xilinx PR Decoupler",
+				&xlnx_pr_decoupler_br_ops, priv);
+	if (!br) {
+		err = -ENOMEM;
+		goto err_clk;
+	}
+
+	platform_set_drvdata(pdev, br);
 
+	err = fpga_bridge_register(br);
 	if (err) {
 		dev_err(&pdev->dev, "unable to register Xilinx PR Decoupler");
-		clk_unprepare(priv->clk);
-		return err;
+		goto err_clk;
 	}
 
 	return 0;
+
+err_clk:
+	clk_unprepare(priv->clk);
+
+	return err;
 }
 
 static int xlnx_pr_decoupler_remove(struct platform_device *pdev)
@@ -137,7 +149,7 @@ static int xlnx_pr_decoupler_remove(struct platform_device *pdev)
 	struct fpga_bridge *bridge = platform_get_drvdata(pdev);
 	struct xlnx_pr_decoupler_data *p = bridge->priv;
 
-	fpga_bridge_unregister(&pdev->dev);
+	fpga_bridge_unregister(bridge);
 
 	clk_unprepare(p->clk);
 
diff --git a/drivers/fpga/xilinx-spi.c b/drivers/fpga/xilinx-spi.c
index 9b62a4c2a3df..8d1945966533 100644
--- a/drivers/fpga/xilinx-spi.c
+++ b/drivers/fpga/xilinx-spi.c
@@ -143,6 +143,8 @@ static const struct fpga_manager_ops xilinx_spi_ops = {
 static int xilinx_spi_probe(struct spi_device *spi)
 {
 	struct xilinx_spi_conf *conf;
+	struct fpga_manager *mgr;
+	int ret;
 
 	conf = devm_kzalloc(&spi->dev, sizeof(*conf), GFP_KERNEL);
 	if (!conf)
@@ -165,13 +167,25 @@ static int xilinx_spi_probe(struct spi_device *spi)
 		return PTR_ERR(conf->done);
 	}
 
-	return fpga_mgr_register(&spi->dev, "Xilinx Slave Serial FPGA Manager",
-				 &xilinx_spi_ops, conf);
+	mgr = fpga_mgr_create(&spi->dev, "Xilinx Slave Serial FPGA Manager",
+			      &xilinx_spi_ops, conf);
+	if (!mgr)
+		return -ENOMEM;
+
+	spi_set_drvdata(spi, mgr);
+
+	ret = fpga_mgr_register(mgr);
+	if (ret)
+		fpga_mgr_free(mgr);
+
+	return ret;
 }
 
 static int xilinx_spi_remove(struct spi_device *spi)
 {
-	fpga_mgr_unregister(&spi->dev);
+	struct fpga_manager *mgr = spi_get_drvdata(spi);
+
+	fpga_mgr_unregister(mgr);
 
 	return 0;
 }
diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c
index 70b15b303471..3110e00121ca 100644
--- a/drivers/fpga/zynq-fpga.c
+++ b/drivers/fpga/zynq-fpga.c
@@ -558,6 +558,7 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct zynq_fpga_priv *priv;
+	struct fpga_manager *mgr;
 	struct resource *res;
 	int err;
 
@@ -613,10 +614,17 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 
 	clk_disable(priv->clk);
 
-	err = fpga_mgr_register(dev, "Xilinx Zynq FPGA Manager",
-				&zynq_fpga_ops, priv);
+	mgr = fpga_mgr_create(dev, "Xilinx Zynq FPGA Manager",
+			      &zynq_fpga_ops, priv);
+	if (!mgr)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, mgr);
+
+	err = fpga_mgr_register(mgr);
 	if (err) {
 		dev_err(dev, "unable to register FPGA manager\n");
+		fpga_mgr_free(mgr);
 		clk_unprepare(priv->clk);
 		return err;
 	}
@@ -632,7 +640,7 @@ static int zynq_fpga_remove(struct platform_device *pdev)
 	mgr = platform_get_drvdata(pdev);
 	priv = mgr->priv;
 
-	fpga_mgr_unregister(&pdev->dev);
+	fpga_mgr_unregister(mgr);
 
 	clk_unprepare(priv->clk);
 
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index 77e485557498..6f693b7d5220 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -384,7 +384,7 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set)
 	if (set)
 		reg |= bit;
 	else
-		reg &= bit;
+		reg &= ~bit;
 	iowrite32(reg, addr);
 
 	spin_unlock_irqrestore(&gpio->lock, flags);
diff --git a/drivers/gpio/gpio-pci-idio-16.c b/drivers/gpio/gpio-pci-idio-16.c
index 1948724d8c36..25d16b2af1c3 100644
--- a/drivers/gpio/gpio-pci-idio-16.c
+++ b/drivers/gpio/gpio-pci-idio-16.c
@@ -116,9 +116,9 @@ static int idio_16_gpio_get_multiple(struct gpio_chip *chip,
 	unsigned long word_mask;
 	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
 	unsigned long port_state;
-	u8 __iomem ports[] = {
-		idio16gpio->reg->out0_7, idio16gpio->reg->out8_15,
-		idio16gpio->reg->in0_7, idio16gpio->reg->in8_15,
+	void __iomem *ports[] = {
+		&idio16gpio->reg->out0_7, &idio16gpio->reg->out8_15,
+		&idio16gpio->reg->in0_7, &idio16gpio->reg->in8_15,
 	};
 
 	/* clear bits array to a clean slate */
@@ -143,7 +143,7 @@ static int idio_16_gpio_get_multiple(struct gpio_chip *chip,
 		}
 
 		/* read bits from current gpio port */
-		port_state = ioread8(ports + i);
+		port_state = ioread8(ports[i]);
 
 		/* store acquired bits at respective bits array offset */
 		bits[word_index] |= port_state << word_offset;
diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c
index 835607ecf658..f953541e7890 100644
--- a/drivers/gpio/gpio-pcie-idio-24.c
+++ b/drivers/gpio/gpio-pcie-idio-24.c
@@ -206,10 +206,10 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip,
 	unsigned long word_mask;
 	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
 	unsigned long port_state;
-	u8 __iomem ports[] = {
-		idio24gpio->reg->out0_7, idio24gpio->reg->out8_15,
-		idio24gpio->reg->out16_23, idio24gpio->reg->in0_7,
-		idio24gpio->reg->in8_15, idio24gpio->reg->in16_23,
+	void __iomem *ports[] = {
+		&idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
+		&idio24gpio->reg->out16_23, &idio24gpio->reg->in0_7,
+		&idio24gpio->reg->in8_15, &idio24gpio->reg->in16_23,
 	};
 	const unsigned long out_mode_mask = BIT(1);
 
@@ -217,7 +217,7 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip,
 	bitmap_zero(bits, chip->ngpio);
 
 	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
+	for (i = 0; i < ARRAY_SIZE(ports) + 1; i++) {
 		/* gpio offset in bits array */
 		bits_offset = i * gpio_reg_size;
 
@@ -236,7 +236,7 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip,
 
 		/* read bits from current gpio port (port 6 is TTL GPIO) */
 		if (i < 6)
-			port_state = ioread8(ports + i);
+			port_state = ioread8(ports[i]);
 		else if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask)
 			port_state = ioread8(&idio24gpio->reg->ttl_out0_7);
 		else
@@ -301,9 +301,9 @@ static void idio_24_gpio_set_multiple(struct gpio_chip *chip,
 	const unsigned long port_mask = GENMASK(gpio_reg_size, 0);
 	unsigned long flags;
 	unsigned int out_state;
-	u8 __iomem ports[] = {
-		idio24gpio->reg->out0_7, idio24gpio->reg->out8_15,
-		idio24gpio->reg->out16_23
+	void __iomem *ports[] = {
+		&idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
+		&idio24gpio->reg->out16_23
 	};
 	const unsigned long out_mode_mask = BIT(1);
 	const unsigned int ttl_offset = 48;
@@ -327,9 +327,9 @@ static void idio_24_gpio_set_multiple(struct gpio_chip *chip,
 		raw_spin_lock_irqsave(&idio24gpio->lock, flags);
 
 		/* process output lines */
-		out_state = ioread8(ports + i) & ~gpio_mask;
+		out_state = ioread8(ports[i]) & ~gpio_mask;
 		out_state |= (*bits >> bits_offset) & gpio_mask;
-		iowrite8(out_state, ports + i);
+		iowrite8(out_state, ports[i]);
 
 		raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
 	}
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 43aeb07343ec..d8ccb500872f 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -497,7 +497,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 	struct gpiohandle_request handlereq;
 	struct linehandle_state *lh;
 	struct file *file;
-	int fd, i, ret;
+	int fd, i, count = 0, ret;
 	u32 lflags;
 
 	if (copy_from_user(&handlereq, ip, sizeof(handlereq)))
@@ -558,6 +558,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 		if (ret)
 			goto out_free_descs;
 		lh->descs[i] = desc;
+		count = i;
 
 		if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW)
 			set_bit(FLAG_ACTIVE_LOW, &desc->flags);
@@ -628,7 +629,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 out_put_unused_fd:
 	put_unused_fd(fd);
 out_free_descs:
-	for (; i >= 0; i--)
+	for (i = 0; i < count; i++)
 		gpiod_free(lh->descs[i]);
 	kfree(lh->label);
 out_free_lh:
@@ -902,7 +903,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 	desc = &gdev->descs[offset];
 	ret = gpiod_request(desc, le->label);
 	if (ret)
-		goto out_free_desc;
+		goto out_free_label;
 	le->desc = desc;
 	le->eflags = eflags;
 
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index deeefa7a1773..2a72d2feb76d 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -49,16 +49,17 @@ config DRM_DEBUG_MM
 
 	  If in doubt, say "N".
 
-config DRM_DEBUG_MM_SELFTEST
-	tristate "kselftests for DRM range manager (struct drm_mm)"
+config DRM_DEBUG_SELFTEST
+	tristate "kselftests for DRM"
 	depends on DRM
 	depends on DEBUG_KERNEL
 	select PRIME_NUMBERS
 	select DRM_LIB_RANDOM
+	select DRM_KMS_HELPER
 	default n
 	help
-	  This option provides a kernel module that can be used to test
-	  the DRM range manager (drm_mm) and its API. This option is not
+	  This option provides kernel modules that can be used to run
+	  various selftests on parts of the DRM api. This option is not
 	  useful for distributions or general kernels, but only for kernel
 	  developers working on DRM and associated drivers.
 
@@ -267,6 +268,8 @@ source "drivers/gpu/drm/amd/amdkfd/Kconfig"
 
 source "drivers/gpu/drm/imx/Kconfig"
 
+source "drivers/gpu/drm/v3d/Kconfig"
+
 source "drivers/gpu/drm/vc4/Kconfig"
 
 source "drivers/gpu/drm/etnaviv/Kconfig"
@@ -289,6 +292,8 @@ source "drivers/gpu/drm/pl111/Kconfig"
 
 source "drivers/gpu/drm/tve200/Kconfig"
 
+source "drivers/gpu/drm/xen/Kconfig"
+
 # Keep legacy drivers last
 
 menuconfig DRM_LEGACY
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 50093ff4479b..ef9f3dab287f 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -43,7 +43,7 @@ drm_kms_helper-$(CONFIG_DRM_KMS_CMA_HELPER) += drm_fb_cma_helper.o
 drm_kms_helper-$(CONFIG_DRM_DP_AUX_CHARDEV) += drm_dp_aux_dev.o
 
 obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o
-obj-$(CONFIG_DRM_DEBUG_MM_SELFTEST) += selftests/
+obj-$(CONFIG_DRM_DEBUG_SELFTEST) += selftests/
 
 obj-$(CONFIG_DRM)	+= drm.o
 obj-$(CONFIG_DRM_MIPI_DSI) += drm_mipi_dsi.o
@@ -61,6 +61,7 @@ obj-$(CONFIG_DRM_MGA)	+= mga/
 obj-$(CONFIG_DRM_I810)	+= i810/
 obj-$(CONFIG_DRM_I915)	+= i915/
 obj-$(CONFIG_DRM_MGAG200) += mgag200/
+obj-$(CONFIG_DRM_V3D)  += v3d/
 obj-$(CONFIG_DRM_VC4)  += vc4/
 obj-$(CONFIG_DRM_CIRRUS_QEMU) += cirrus/
 obj-$(CONFIG_DRM_SIS)   += sis/
@@ -103,3 +104,4 @@ obj-$(CONFIG_DRM_MXSFB)	+= mxsfb/
 obj-$(CONFIG_DRM_TINYDRM) += tinydrm/
 obj-$(CONFIG_DRM_PL111) += pl111/
 obj-$(CONFIG_DRM_TVE200) += tve200/
+obj-$(CONFIG_DRM_XEN) += xen/
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 2ca2b5154d52..bfd332c95b61 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -56,13 +56,18 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 
 # add asic specific block
 amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \
-	ci_smc.o ci_dpm.o dce_v8_0.o gfx_v7_0.o cik_sdma.o uvd_v4_2.o vce_v2_0.o \
-	amdgpu_amdkfd_gfx_v7.o
+	ci_smc.o ci_dpm.o dce_v8_0.o gfx_v7_0.o cik_sdma.o uvd_v4_2.o vce_v2_0.o
 
 amdgpu-$(CONFIG_DRM_AMDGPU_SI)+= si.o gmc_v6_0.o gfx_v6_0.o si_ih.o si_dma.o dce_v6_0.o si_dpm.o si_smc.o
 
 amdgpu-y += \
-	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o emu_soc.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o
+	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o emu_soc.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o \
+	vega20_reg_init.o
+
+# add DF block
+amdgpu-y += \
+	df_v1_7.o \
+	df_v3_6.o
 
 # add GMC block
 amdgpu-y += \
@@ -126,11 +131,20 @@ amdgpu-y += \
 	vcn_v1_0.o
 
 # add amdkfd interfaces
+amdgpu-y += amdgpu_amdkfd.o
+
+ifneq ($(CONFIG_HSA_AMD),)
 amdgpu-y += \
-	 amdgpu_amdkfd.o \
 	 amdgpu_amdkfd_fence.o \
 	 amdgpu_amdkfd_gpuvm.o \
-	 amdgpu_amdkfd_gfx_v8.o
+	 amdgpu_amdkfd_gfx_v8.o \
+	 amdgpu_amdkfd_gfx_v9.o
+
+ifneq ($(CONFIG_DRM_AMDGPU_CIK),)
+amdgpu-y += amdgpu_amdkfd_gfx_v7.o
+endif
+
+endif
 
 # add cgs
 amdgpu-y += amdgpu_cgs.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index c8b605f3dc05..a59c07590cee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -129,6 +129,7 @@ extern int amdgpu_lbpw;
 extern int amdgpu_compute_multipipe;
 extern int amdgpu_gpu_recovery;
 extern int amdgpu_emu_mode;
+extern uint amdgpu_smu_memory_pool_size;
 
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;
@@ -137,6 +138,7 @@ extern int amdgpu_si_support;
 extern int amdgpu_cik_support;
 #endif
 
+#define AMDGPU_SG_THRESHOLD			(256*1024*1024)
 #define AMDGPU_DEFAULT_GTT_SIZE_MB		3072ULL /* 3GB by default */
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
@@ -222,10 +224,10 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
 
-int amdgpu_device_ip_set_clockgating_state(struct amdgpu_device *adev,
+int amdgpu_device_ip_set_clockgating_state(void *dev,
 					   enum amd_ip_block_type block_type,
 					   enum amd_clockgating_state state);
-int amdgpu_device_ip_set_powergating_state(struct amdgpu_device *adev,
+int amdgpu_device_ip_set_powergating_state(void *dev,
 					   enum amd_ip_block_type block_type,
 					   enum amd_powergating_state state);
 void amdgpu_device_ip_get_clockgating_state(struct amdgpu_device *adev,
@@ -681,6 +683,8 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id);
 
 void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr);
+void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr);
+void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr);
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
 
 
@@ -771,9 +775,18 @@ struct amdgpu_rlc {
 	u32 starting_offsets_start;
 	u32 reg_list_format_size_bytes;
 	u32 reg_list_size_bytes;
+	u32 reg_list_format_direct_reg_list_length;
+	u32 save_restore_list_cntl_size_bytes;
+	u32 save_restore_list_gpm_size_bytes;
+	u32 save_restore_list_srm_size_bytes;
 
 	u32 *register_list_format;
 	u32 *register_restore;
+	u8 *save_restore_list_cntl;
+	u8 *save_restore_list_gpm;
+	u8 *save_restore_list_srm;
+
+	bool is_rlc_v2_1;
 };
 
 #define AMDGPU_MAX_COMPUTE_QUEUES KGD_MAX_QUEUES
@@ -867,6 +880,8 @@ struct amdgpu_gfx_config {
 
 	/* gfx configure feature */
 	uint32_t double_offchip_lds_buf;
+	/* cached value of DB_DEBUG2 */
+	uint32_t db_debug2;
 };
 
 struct amdgpu_cu_info {
@@ -938,6 +953,12 @@ struct amdgpu_gfx {
 	uint32_t			ce_feature_version;
 	uint32_t			pfp_feature_version;
 	uint32_t			rlc_feature_version;
+	uint32_t			rlc_srlc_fw_version;
+	uint32_t			rlc_srlc_feature_version;
+	uint32_t			rlc_srlg_fw_version;
+	uint32_t			rlc_srlg_feature_version;
+	uint32_t			rlc_srls_fw_version;
+	uint32_t			rlc_srls_feature_version;
 	uint32_t			mec_feature_version;
 	uint32_t			mec2_feature_version;
 	struct amdgpu_ring		gfx_ring[AMDGPU_MAX_GFX_RINGS];
@@ -1204,6 +1225,8 @@ struct amdgpu_asic_funcs {
 	/* invalidate hdp read cache */
 	void (*invalidate_hdp)(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring);
+	/* check if the asic needs a full reset of if soft reset will work */
+	bool (*need_full_reset)(struct amdgpu_device *adev);
 };
 
 /*
@@ -1368,7 +1391,19 @@ struct amdgpu_nbio_funcs {
 	void (*detect_hw_virt)(struct amdgpu_device *adev);
 };
 
-
+struct amdgpu_df_funcs {
+	void (*init)(struct amdgpu_device *adev);
+	void (*enable_broadcast_mode)(struct amdgpu_device *adev,
+				      bool enable);
+	u32 (*get_fb_channel_number)(struct amdgpu_device *adev);
+	u32 (*get_hbm_channel_number)(struct amdgpu_device *adev);
+	void (*update_medium_grain_clock_gating)(struct amdgpu_device *adev,
+						 bool enable);
+	void (*get_clockgating_state)(struct amdgpu_device *adev,
+				      u32 *flags);
+	void (*enable_ecc_force_par_wr_rmw)(struct amdgpu_device *adev,
+					    bool enable);
+};
 /* Define the HW IP blocks will be used in driver , add more if necessary */
 enum amd_hw_ip_block_type {
 	GC_HWIP = 1,
@@ -1398,6 +1433,7 @@ enum amd_hw_ip_block_type {
 struct amd_powerplay {
 	void *pp_handle;
 	const struct amd_pm_funcs *pp_funcs;
+	uint32_t pp_feature;
 };
 
 #define AMDGPU_RESET_MAGIC_NUM 64
@@ -1590,6 +1626,7 @@ struct amdgpu_device {
 	uint32_t 		*reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
 
 	const struct amdgpu_nbio_funcs	*nbio_funcs;
+	const struct amdgpu_df_funcs	*df_funcs;
 
 	/* delayed work_func for deferring clockgating during resume */
 	struct delayed_work     late_init_work;
@@ -1764,6 +1801,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_asic_get_config_memsize(adev) (adev)->asic_funcs->get_config_memsize((adev))
 #define amdgpu_asic_flush_hdp(adev, r) (adev)->asic_funcs->flush_hdp((adev), (r))
 #define amdgpu_asic_invalidate_hdp(adev, r) (adev)->asic_funcs->invalidate_hdp((adev), (r))
+#define amdgpu_asic_need_full_reset(adev) (adev)->asic_funcs->need_full_reset((adev))
 #define amdgpu_gmc_flush_gpu_tlb(adev, vmid) (adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid))
 #define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (addr))
 #define amdgpu_gmc_emit_pasid_mapping(r, vmid, pasid) (r)->adev->gmc.gmc_funcs->emit_pasid_mapping((r), (vmid), (pasid))
@@ -1790,6 +1828,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_ring_emit_rreg(r, d) (r)->funcs->emit_rreg((r), (d))
 #define amdgpu_ring_emit_wreg(r, d, v) (r)->funcs->emit_wreg((r), (d), (v))
 #define amdgpu_ring_emit_reg_wait(r, d, v, m) (r)->funcs->emit_reg_wait((r), (d), (v), (m))
+#define amdgpu_ring_emit_reg_write_reg_wait(r, d0, d1, v, m) (r)->funcs->emit_reg_write_reg_wait((r), (d0), (d1), (v), (m))
 #define amdgpu_ring_emit_tmz(r, b) (r)->funcs->emit_tmz((r), (b))
 #define amdgpu_ring_pad_ib(r, ib) ((r)->funcs->pad_ib((r), (ib)))
 #define amdgpu_ring_init_cond_exec(r) (r)->funcs->init_cond_exec((r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index a29362f9ef41..428e5eb3444f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -290,12 +290,11 @@ static int acp_hw_init(void *handle)
 	else if (r)
 		return r;
 
-	r = cgs_get_pci_resource(adev->acp.cgs_device, CGS_RESOURCE_TYPE_MMIO,
-			0x5289, 0, &acp_base);
-	if (r == -ENODEV)
-		return 0;
-	else if (r)
-		return r;
+	if (adev->rmmio_size == 0 || adev->rmmio_size < 0x5289)
+		return -EINVAL;
+
+	acp_base = adev->rmmio_base;
+
 	if (adev->asic_type != CHIP_STONEY) {
 		adev->acp.acp_genpd = kzalloc(sizeof(struct acp_pm_domain), GFP_KERNEL);
 		if (adev->acp.acp_genpd == NULL)
@@ -513,7 +512,7 @@ static int acp_hw_fini(void *handle)
 	if (adev->acp.acp_genpd) {
 		for (i = 0; i < ACP_DEVS ; i++) {
 			dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
-			ret = pm_genpd_remove_device(&adev->acp.acp_genpd->gpd, dev);
+			ret = pm_genpd_remove_device(dev);
 			/* If removal fails, dont giveup and try rest */
 			if (ret)
 				dev_err(dev, "remove dev from genpd failed\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 4d36203ffb11..8f6f45567bfa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -50,15 +50,21 @@ int amdgpu_amdkfd_init(void)
 		kgd2kfd = NULL;
 	}
 
+
 #elif defined(CONFIG_HSA_AMD)
+
 	ret = kgd2kfd_init(KFD_INTERFACE_VERSION, &kgd2kfd);
 	if (ret)
 		kgd2kfd = NULL;
 
 #else
+	kgd2kfd = NULL;
 	ret = -ENOENT;
 #endif
+
+#if defined(CONFIG_HSA_AMD_MODULE) || defined(CONFIG_HSA_AMD)
 	amdgpu_amdkfd_gpuvm_init_mem_limits();
+#endif
 
 	return ret;
 }
@@ -92,8 +98,12 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 	case CHIP_POLARIS11:
 		kfd2kgd = amdgpu_amdkfd_gfx_8_0_get_functions();
 		break;
+	case CHIP_VEGA10:
+	case CHIP_RAVEN:
+		kfd2kgd = amdgpu_amdkfd_gfx_9_0_get_functions();
+		break;
 	default:
-		dev_dbg(adev->dev, "kfd not supported on this ASIC\n");
+		dev_info(adev->dev, "kfd not supported on this ASIC\n");
 		return;
 	}
 
@@ -175,6 +185,28 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 				&gpu_resources.doorbell_physical_address,
 				&gpu_resources.doorbell_aperture_size,
 				&gpu_resources.doorbell_start_offset);
+		if (adev->asic_type >= CHIP_VEGA10) {
+			/* On SOC15 the BIF is involved in routing
+			 * doorbells using the low 12 bits of the
+			 * address. Communicate the assignments to
+			 * KFD. KFD uses two doorbell pages per
+			 * process in case of 64-bit doorbells so we
+			 * can use each doorbell assignment twice.
+			 */
+			gpu_resources.sdma_doorbell[0][0] =
+				AMDGPU_DOORBELL64_sDMA_ENGINE0;
+			gpu_resources.sdma_doorbell[0][1] =
+				AMDGPU_DOORBELL64_sDMA_ENGINE0 + 0x200;
+			gpu_resources.sdma_doorbell[1][0] =
+				AMDGPU_DOORBELL64_sDMA_ENGINE1;
+			gpu_resources.sdma_doorbell[1][1] =
+				AMDGPU_DOORBELL64_sDMA_ENGINE1 + 0x200;
+			/* Doorbells 0x0f0-0ff and 0x2f0-2ff are reserved for
+			 * SDMA, IH and VCN. So don't use them for the CP.
+			 */
+			gpu_resources.reserved_doorbell_mask = 0x1f0;
+			gpu_resources.reserved_doorbell_val  = 0x0f0;
+		}
 
 		kgd2kfd->device_init(adev->kfd, &gpu_resources);
 	}
@@ -217,13 +249,19 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 	struct amdgpu_bo *bo = NULL;
+	struct amdgpu_bo_param bp;
 	int r;
 	uint64_t gpu_addr_tmp = 0;
 	void *cpu_ptr_tmp = NULL;
 
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
-			     AMDGPU_GEM_CREATE_CPU_GTT_USWC, ttm_bo_type_kernel,
-			     NULL, &bo);
+	memset(&bp, 0, sizeof(bp));
+	bp.size = size;
+	bp.byte_align = PAGE_SIZE;
+	bp.domain = AMDGPU_GEM_DOMAIN_GTT;
+	bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+	bp.type = ttm_bo_type_kernel;
+	bp.resv = NULL;
+	r = amdgpu_bo_create(adev, &bp, &bo);
 	if (r) {
 		dev_err(adev->dev,
 			"failed to allocate BO for amdkfd (%d)\n", r);
@@ -432,3 +470,44 @@ bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 
 	return false;
 }
+
+#if !defined(CONFIG_HSA_AMD_MODULE) && !defined(CONFIG_HSA_AMD)
+bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm)
+{
+	return false;
+}
+
+void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo)
+{
+}
+
+void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
+					struct amdgpu_vm *vm)
+{
+}
+
+struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
+{
+	return NULL;
+}
+
+int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm)
+{
+	return 0;
+}
+
+struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
+{
+	return NULL;
+}
+
+struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
+{
+	return NULL;
+}
+
+struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
+{
+	return NULL;
+}
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index c2c2bea731e0..a8418a3f4e9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -28,6 +28,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/mmu_context.h>
+#include <linux/workqueue.h>
 #include <kgd_kfd_interface.h>
 #include <drm/ttm/ttm_execbuf_util.h>
 #include "amdgpu_sync.h"
@@ -59,7 +60,9 @@ struct kgd_mem {
 
 	uint32_t mapping_flags;
 
+	atomic_t invalid;
 	struct amdkfd_process_info *process_info;
+	struct page **user_pages;
 
 	struct amdgpu_sync sync;
 
@@ -84,6 +87,9 @@ struct amdkfd_process_info {
 	struct list_head vm_list_head;
 	/* List head for all KFD BOs that belong to a KFD process. */
 	struct list_head kfd_bo_list;
+	/* List of userptr BOs that are valid or invalid */
+	struct list_head userptr_valid_list;
+	struct list_head userptr_inval_list;
 	/* Lock to protect kfd_bo_list */
 	struct mutex lock;
 
@@ -91,6 +97,11 @@ struct amdkfd_process_info {
 	unsigned int n_vms;
 	/* Eviction Fence */
 	struct amdgpu_amdkfd_fence *eviction_fence;
+
+	/* MMU-notifier related fields */
+	atomic_t evicted_bos;
+	struct delayed_work restore_userptr_work;
+	struct pid *pid;
 };
 
 int amdgpu_amdkfd_init(void);
@@ -104,12 +115,14 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev);
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev);
 void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev);
 
+int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm);
 int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t vmid, uint64_t gpu_addr,
 				uint32_t *ib_cmd, uint32_t ib_len);
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void);
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void);
+struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
@@ -143,14 +156,14 @@ uint64_t amdgpu_amdkfd_get_vram_usage(struct kgd_dev *kgd);
 
 /* GPUVM API */
 int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, void **vm,
-					  void **process_info,
-					  struct dma_fence **ef);
+					void **process_info,
+					struct dma_fence **ef);
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
-					   struct file *filp,
-					   void **vm, void **process_info,
-					   struct dma_fence **ef);
+					struct file *filp,
+					void **vm, void **process_info,
+					struct dma_fence **ef);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
-				    struct amdgpu_vm *vm);
+				struct amdgpu_vm *vm);
 void amdgpu_amdkfd_gpuvm_destroy_process_vm(struct kgd_dev *kgd, void *vm);
 uint32_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *vm);
 int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index ea54e53172b9..0ff36d45a597 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -98,8 +98,6 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 					unsigned int vmid);
 
-static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
-				uint32_t hpd_size, uint64_t hpd_gpu_addr);
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
 static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr,
@@ -183,7 +181,6 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.free_pasid = amdgpu_pasid_free,
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
-	.init_pipeline = kgd_init_pipeline,
 	.init_interrupts = kgd_init_interrupts,
 	.hqd_load = kgd_hqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
@@ -309,13 +306,6 @@ static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 	return 0;
 }
 
-static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
-				uint32_t hpd_size, uint64_t hpd_gpu_addr)
-{
-	/* amdgpu owns the per-pipe state */
-	return 0;
-}
-
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 89264c9a5e9f..6ef9762b4b00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -57,8 +57,6 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t sh_mem_bases);
 static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 		unsigned int vmid);
-static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
-		uint32_t hpd_size, uint64_t hpd_gpu_addr);
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
 static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr,
@@ -141,7 +139,6 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.free_pasid = amdgpu_pasid_free,
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
-	.init_pipeline = kgd_init_pipeline,
 	.init_interrupts = kgd_init_interrupts,
 	.hqd_load = kgd_hqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
@@ -270,13 +267,6 @@ static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 	return 0;
 }
 
-static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
-				uint32_t hpd_size, uint64_t hpd_gpu_addr)
-{
-	/* amdgpu owns the per-pipe state */
-	return 0;
-}
-
 static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
new file mode 100644
index 000000000000..f0c0d3953f69
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -0,0 +1,1043 @@
+/*
+ * Copyright 2014-2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#define pr_fmt(fmt) "kfd2kgd: " fmt
+
+#include <linux/module.h>
+#include <linux/fdtable.h>
+#include <linux/uaccess.h>
+#include <linux/firmware.h>
+#include <drm/drmP.h>
+#include "amdgpu.h"
+#include "amdgpu_amdkfd.h"
+#include "amdgpu_ucode.h"
+#include "soc15_hw_ip.h"
+#include "gc/gc_9_0_offset.h"
+#include "gc/gc_9_0_sh_mask.h"
+#include "vega10_enum.h"
+#include "sdma0/sdma0_4_0_offset.h"
+#include "sdma0/sdma0_4_0_sh_mask.h"
+#include "sdma1/sdma1_4_0_offset.h"
+#include "sdma1/sdma1_4_0_sh_mask.h"
+#include "athub/athub_1_0_offset.h"
+#include "athub/athub_1_0_sh_mask.h"
+#include "oss/osssys_4_0_offset.h"
+#include "oss/osssys_4_0_sh_mask.h"
+#include "soc15_common.h"
+#include "v9_structs.h"
+#include "soc15.h"
+#include "soc15d.h"
+
+/* HACK: MMHUB and GC both have VM-related register with the same
+ * names but different offsets. Define the MMHUB register we need here
+ * with a prefix. A proper solution would be to move the functions
+ * programming these registers into gfx_v9_0.c and mmhub_v1_0.c
+ * respectively.
+ */
+#define mmMMHUB_VM_INVALIDATE_ENG16_REQ				0x06f3
+#define mmMMHUB_VM_INVALIDATE_ENG16_REQ_BASE_IDX		0
+
+#define mmMMHUB_VM_INVALIDATE_ENG16_ACK				0x0705
+#define mmMMHUB_VM_INVALIDATE_ENG16_ACK_BASE_IDX		0
+
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32		0x072b
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32_BASE_IDX	0
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32		0x072c
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32_BASE_IDX	0
+
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32		0x074b
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32_BASE_IDX	0
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32		0x074c
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32_BASE_IDX	0
+
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32		0x076b
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32_BASE_IDX	0
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32		0x076c
+#define mmMMHUB_VM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32_BASE_IDX	0
+
+#define mmMMHUB_VM_INVALIDATE_ENG16_ADDR_RANGE_LO32		0x0727
+#define mmMMHUB_VM_INVALIDATE_ENG16_ADDR_RANGE_LO32_BASE_IDX	0
+#define mmMMHUB_VM_INVALIDATE_ENG16_ADDR_RANGE_HI32		0x0728
+#define mmMMHUB_VM_INVALIDATE_ENG16_ADDR_RANGE_HI32_BASE_IDX	0
+
+#define V9_PIPE_PER_MEC		(4)
+#define V9_QUEUES_PER_PIPE_MEC	(8)
+
+enum hqd_dequeue_request_type {
+	NO_ACTION = 0,
+	DRAIN_PIPE,
+	RESET_WAVES
+};
+
+/*
+ * Register access functions
+ */
+
+static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
+		uint32_t sh_mem_config,
+		uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit,
+		uint32_t sh_mem_bases);
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+		unsigned int vmid);
+static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
+static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
+			uint32_t queue_id, uint32_t __user *wptr,
+			uint32_t wptr_shift, uint32_t wptr_mask,
+			struct mm_struct *mm);
+static int kgd_hqd_dump(struct kgd_dev *kgd,
+			uint32_t pipe_id, uint32_t queue_id,
+			uint32_t (**dump)[2], uint32_t *n_regs);
+static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
+			     uint32_t __user *wptr, struct mm_struct *mm);
+static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
+			     uint32_t engine_id, uint32_t queue_id,
+			     uint32_t (**dump)[2], uint32_t *n_regs);
+static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
+		uint32_t pipe_id, uint32_t queue_id);
+static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd);
+static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
+				enum kfd_preempt_type reset_type,
+				unsigned int utimeout, uint32_t pipe_id,
+				uint32_t queue_id);
+static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
+				unsigned int utimeout);
+static int kgd_address_watch_disable(struct kgd_dev *kgd);
+static int kgd_address_watch_execute(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					uint32_t cntl_val,
+					uint32_t addr_hi,
+					uint32_t addr_lo);
+static int kgd_wave_control_execute(struct kgd_dev *kgd,
+					uint32_t gfx_index_val,
+					uint32_t sq_cmd);
+static uint32_t kgd_address_watch_get_offset(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					unsigned int reg_offset);
+
+static bool get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
+		uint8_t vmid);
+static uint16_t get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
+		uint8_t vmid);
+static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
+		uint32_t page_table_base);
+static uint16_t get_fw_version(struct kgd_dev *kgd, enum kgd_engine_type type);
+static void set_scratch_backing_va(struct kgd_dev *kgd,
+					uint64_t va, uint32_t vmid);
+static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid);
+static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid);
+
+/* Because of REG_GET_FIELD() being used, we put this function in the
+ * asic specific file.
+ */
+static int amdgpu_amdkfd_get_tile_config(struct kgd_dev *kgd,
+		struct tile_config *config)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	config->gb_addr_config = adev->gfx.config.gb_addr_config;
+
+	config->tile_config_ptr = adev->gfx.config.tile_mode_array;
+	config->num_tile_configs =
+			ARRAY_SIZE(adev->gfx.config.tile_mode_array);
+	config->macro_tile_config_ptr =
+			adev->gfx.config.macrotile_mode_array;
+	config->num_macro_tile_configs =
+			ARRAY_SIZE(adev->gfx.config.macrotile_mode_array);
+
+	return 0;
+}
+
+static const struct kfd2kgd_calls kfd2kgd = {
+	.init_gtt_mem_allocation = alloc_gtt_mem,
+	.free_gtt_mem = free_gtt_mem,
+	.get_local_mem_info = get_local_mem_info,
+	.get_gpu_clock_counter = get_gpu_clock_counter,
+	.get_max_engine_clock_in_mhz = get_max_engine_clock_in_mhz,
+	.alloc_pasid = amdgpu_pasid_alloc,
+	.free_pasid = amdgpu_pasid_free,
+	.program_sh_mem_settings = kgd_program_sh_mem_settings,
+	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
+	.init_interrupts = kgd_init_interrupts,
+	.hqd_load = kgd_hqd_load,
+	.hqd_sdma_load = kgd_hqd_sdma_load,
+	.hqd_dump = kgd_hqd_dump,
+	.hqd_sdma_dump = kgd_hqd_sdma_dump,
+	.hqd_is_occupied = kgd_hqd_is_occupied,
+	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
+	.hqd_destroy = kgd_hqd_destroy,
+	.hqd_sdma_destroy = kgd_hqd_sdma_destroy,
+	.address_watch_disable = kgd_address_watch_disable,
+	.address_watch_execute = kgd_address_watch_execute,
+	.wave_control_execute = kgd_wave_control_execute,
+	.address_watch_get_offset = kgd_address_watch_get_offset,
+	.get_atc_vmid_pasid_mapping_pasid =
+			get_atc_vmid_pasid_mapping_pasid,
+	.get_atc_vmid_pasid_mapping_valid =
+			get_atc_vmid_pasid_mapping_valid,
+	.get_fw_version = get_fw_version,
+	.set_scratch_backing_va = set_scratch_backing_va,
+	.get_tile_config = amdgpu_amdkfd_get_tile_config,
+	.get_cu_info = get_cu_info,
+	.get_vram_usage = amdgpu_amdkfd_get_vram_usage,
+	.create_process_vm = amdgpu_amdkfd_gpuvm_create_process_vm,
+	.acquire_process_vm = amdgpu_amdkfd_gpuvm_acquire_process_vm,
+	.destroy_process_vm = amdgpu_amdkfd_gpuvm_destroy_process_vm,
+	.get_process_page_dir = amdgpu_amdkfd_gpuvm_get_process_page_dir,
+	.set_vm_context_page_table_base = set_vm_context_page_table_base,
+	.alloc_memory_of_gpu = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu,
+	.free_memory_of_gpu = amdgpu_amdkfd_gpuvm_free_memory_of_gpu,
+	.map_memory_to_gpu = amdgpu_amdkfd_gpuvm_map_memory_to_gpu,
+	.unmap_memory_to_gpu = amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu,
+	.sync_memory = amdgpu_amdkfd_gpuvm_sync_memory,
+	.map_gtt_bo_to_kernel = amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel,
+	.restore_process_bos = amdgpu_amdkfd_gpuvm_restore_process_bos,
+	.invalidate_tlbs = invalidate_tlbs,
+	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
+	.submit_ib = amdgpu_amdkfd_submit_ib,
+};
+
+struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
+{
+	return (struct kfd2kgd_calls *)&kfd2kgd;
+}
+
+static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
+{
+	return (struct amdgpu_device *)kgd;
+}
+
+static void lock_srbm(struct kgd_dev *kgd, uint32_t mec, uint32_t pipe,
+			uint32_t queue, uint32_t vmid)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	mutex_lock(&adev->srbm_mutex);
+	soc15_grbm_select(adev, mec, pipe, queue, vmid);
+}
+
+static void unlock_srbm(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	soc15_grbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+}
+
+static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
+				uint32_t queue_id)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	uint32_t mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	uint32_t pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
+
+	lock_srbm(kgd, mec, pipe, queue_id, 0);
+}
+
+static uint32_t get_queue_mask(struct amdgpu_device *adev,
+			       uint32_t pipe_id, uint32_t queue_id)
+{
+	unsigned int bit = (pipe_id * adev->gfx.mec.num_queue_per_pipe +
+			    queue_id) & 31;
+
+	return ((uint32_t)1) << bit;
+}
+
+static void release_queue(struct kgd_dev *kgd)
+{
+	unlock_srbm(kgd);
+}
+
+static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
+					uint32_t sh_mem_config,
+					uint32_t sh_mem_ape1_base,
+					uint32_t sh_mem_ape1_limit,
+					uint32_t sh_mem_bases)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	lock_srbm(kgd, 0, 0, 0, vmid);
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), sh_mem_config);
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), sh_mem_bases);
+	/* APE1 no longer exists on GFX9 */
+
+	unlock_srbm(kgd);
+}
+
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+					unsigned int vmid)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	/*
+	 * We have to assume that there is no outstanding mapping.
+	 * The ATC_VMID_PASID_MAPPING_UPDATE_STATUS bit could be 0 because
+	 * a mapping is in progress or because a mapping finished
+	 * and the SW cleared it.
+	 * So the protocol is to always wait & clear.
+	 */
+	uint32_t pasid_mapping = (pasid == 0) ? 0 : (uint32_t)pasid |
+			ATC_VMID0_PASID_MAPPING__VALID_MASK;
+
+	/*
+	 * need to do this twice, once for gfx and once for mmhub
+	 * for ATC add 16 to VMID for mmhub, for IH different registers.
+	 * ATC_VMID0..15 registers are separate from ATC_VMID16..31.
+	 */
+
+	WREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING) + vmid,
+	       pasid_mapping);
+
+	while (!(RREG32(SOC15_REG_OFFSET(
+				ATHUB, 0,
+				mmATC_VMID_PASID_MAPPING_UPDATE_STATUS)) &
+		 (1U << vmid)))
+		cpu_relax();
+
+	WREG32(SOC15_REG_OFFSET(ATHUB, 0,
+				mmATC_VMID_PASID_MAPPING_UPDATE_STATUS),
+	       1U << vmid);
+
+	/* Mapping vmid to pasid also for IH block */
+	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT) + vmid,
+	       pasid_mapping);
+
+	WREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID16_PASID_MAPPING) + vmid,
+	       pasid_mapping);
+
+	while (!(RREG32(SOC15_REG_OFFSET(
+				ATHUB, 0,
+				mmATC_VMID_PASID_MAPPING_UPDATE_STATUS)) &
+		 (1U << (vmid + 16))))
+		cpu_relax();
+
+	WREG32(SOC15_REG_OFFSET(ATHUB, 0,
+				mmATC_VMID_PASID_MAPPING_UPDATE_STATUS),
+	       1U << (vmid + 16));
+
+	/* Mapping vmid to pasid also for IH block */
+	WREG32(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT_MM) + vmid,
+	       pasid_mapping);
+	return 0;
+}
+
+/* TODO - RING0 form of field is obsolete, seems to date back to SI
+ * but still works
+ */
+
+static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t mec;
+	uint32_t pipe;
+
+	mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
+
+	lock_srbm(kgd, mec, pipe, 0, 0);
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmCPC_INT_CNTL),
+		CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK |
+		CP_INT_CNTL_RING0__OPCODE_ERROR_INT_ENABLE_MASK);
+
+	unlock_srbm(kgd);
+
+	return 0;
+}
+
+static uint32_t get_sdma_base_addr(struct amdgpu_device *adev,
+				unsigned int engine_id,
+				unsigned int queue_id)
+{
+	uint32_t base[2] = {
+		SOC15_REG_OFFSET(SDMA0, 0,
+				 mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL,
+		SOC15_REG_OFFSET(SDMA1, 0,
+				 mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL
+	};
+	uint32_t retval;
+
+	retval = base[engine_id] + queue_id * (mmSDMA0_RLC1_RB_CNTL -
+					       mmSDMA0_RLC0_RB_CNTL);
+
+	pr_debug("sdma base address: 0x%x\n", retval);
+
+	return retval;
+}
+
+static inline struct v9_mqd *get_mqd(void *mqd)
+{
+	return (struct v9_mqd *)mqd;
+}
+
+static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
+{
+	return (struct v9_sdma_mqd *)mqd;
+}
+
+static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
+			uint32_t queue_id, uint32_t __user *wptr,
+			uint32_t wptr_shift, uint32_t wptr_mask,
+			struct mm_struct *mm)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct v9_mqd *m;
+	uint32_t *mqd_hqd;
+	uint32_t reg, hqd_base, data;
+
+	m = get_mqd(mqd);
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	/* HIQ is set during driver init period with vmid set to 0*/
+	if (m->cp_hqd_vmid == 0) {
+		uint32_t value, mec, pipe;
+
+		mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+		pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
+
+		pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
+			mec, pipe, queue_id);
+		value = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS));
+		value = REG_SET_FIELD(value, RLC_CP_SCHEDULERS, scheduler1,
+			((mec << 5) | (pipe << 3) | queue_id | 0x80));
+		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), value);
+	}
+
+	/* HQD registers extend from CP_MQD_BASE_ADDR to CP_HQD_EOP_WPTR_MEM. */
+	mqd_hqd = &m->cp_mqd_base_addr_lo;
+	hqd_base = SOC15_REG_OFFSET(GC, 0, mmCP_MQD_BASE_ADDR);
+
+	for (reg = hqd_base;
+	     reg <= SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_HI); reg++)
+		WREG32(reg, mqd_hqd[reg - hqd_base]);
+
+
+	/* Activate doorbell logic before triggering WPTR poll. */
+	data = REG_SET_FIELD(m->cp_hqd_pq_doorbell_control,
+			     CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL), data);
+
+	if (wptr) {
+		/* Don't read wptr with get_user because the user
+		 * context may not be accessible (if this function
+		 * runs in a work queue). Instead trigger a one-shot
+		 * polling read from memory in the CP. This assumes
+		 * that wptr is GPU-accessible in the queue's VMID via
+		 * ATC or SVM. WPTR==RPTR before starting the poll so
+		 * the CP starts fetching new commands from the right
+		 * place.
+		 *
+		 * Guessing a 64-bit WPTR from a 32-bit RPTR is a bit
+		 * tricky. Assume that the queue didn't overflow. The
+		 * number of valid bits in the 32-bit RPTR depends on
+		 * the queue size. The remaining bits are taken from
+		 * the saved 64-bit WPTR. If the WPTR wrapped, add the
+		 * queue size.
+		 */
+		uint32_t queue_size =
+			2 << REG_GET_FIELD(m->cp_hqd_pq_control,
+					   CP_HQD_PQ_CONTROL, QUEUE_SIZE);
+		uint64_t guessed_wptr = m->cp_hqd_pq_rptr & (queue_size - 1);
+
+		if ((m->cp_hqd_pq_wptr_lo & (queue_size - 1)) < guessed_wptr)
+			guessed_wptr += queue_size;
+		guessed_wptr += m->cp_hqd_pq_wptr_lo & ~(queue_size - 1);
+		guessed_wptr += (uint64_t)m->cp_hqd_pq_wptr_hi << 32;
+
+		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_LO),
+		       lower_32_bits(guessed_wptr));
+		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_HI),
+		       upper_32_bits(guessed_wptr));
+		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR),
+		       lower_32_bits((uintptr_t)wptr));
+		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
+		       upper_32_bits((uintptr_t)wptr));
+		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
+		       get_queue_mask(adev, pipe_id, queue_id));
+	}
+
+	/* Start the EOP fetcher */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_EOP_RPTR),
+	       REG_SET_FIELD(m->cp_hqd_eop_rptr,
+			     CP_HQD_EOP_RPTR, INIT_FETCHER, 1));
+
+	data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1);
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE), data);
+
+	release_queue(kgd);
+
+	return 0;
+}
+
+static int kgd_hqd_dump(struct kgd_dev *kgd,
+			uint32_t pipe_id, uint32_t queue_id,
+			uint32_t (**dump)[2], uint32_t *n_regs)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t i = 0, reg;
+#define HQD_N_REGS 56
+#define DUMP_REG(addr) do {				\
+		if (WARN_ON_ONCE(i >= HQD_N_REGS))	\
+			break;				\
+		(*dump)[i][0] = (addr) << 2;		\
+		(*dump)[i++][1] = RREG32(addr);		\
+	} while (0)
+
+	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	if (*dump == NULL)
+		return -ENOMEM;
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	for (reg = SOC15_REG_OFFSET(GC, 0, mmCP_MQD_BASE_ADDR);
+	     reg <= SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_HI); reg++)
+		DUMP_REG(reg);
+
+	release_queue(kgd);
+
+	WARN_ON_ONCE(i != HQD_N_REGS);
+	*n_regs = i;
+
+	return 0;
+}
+
+static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
+			     uint32_t __user *wptr, struct mm_struct *mm)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct v9_sdma_mqd *m;
+	uint32_t sdma_base_addr, sdmax_gfx_context_cntl;
+	unsigned long end_jiffies;
+	uint32_t data;
+	uint64_t data64;
+	uint64_t __user *wptr64 = (uint64_t __user *)wptr;
+
+	m = get_sdma_mqd(mqd);
+	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+					    m->sdma_queue_id);
+	sdmax_gfx_context_cntl = m->sdma_engine_id ?
+		SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_GFX_CONTEXT_CNTL) :
+		SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GFX_CONTEXT_CNTL);
+
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		m->sdmax_rlcx_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
+
+	end_jiffies = msecs_to_jiffies(2000) + jiffies;
+	while (true) {
+		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
+			break;
+		if (time_after(jiffies, end_jiffies))
+			return -ETIME;
+		usleep_range(500, 1000);
+	}
+	data = RREG32(sdmax_gfx_context_cntl);
+	data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
+			     RESUME_CTX, 0);
+	WREG32(sdmax_gfx_context_cntl, data);
+
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL_OFFSET,
+	       m->sdmax_rlcx_doorbell_offset);
+
+	data = REG_SET_FIELD(m->sdmax_rlcx_doorbell, SDMA0_RLC0_DOORBELL,
+			     ENABLE, 1);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, data);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, m->sdmax_rlcx_rb_rptr);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_HI,
+				m->sdmax_rlcx_rb_rptr_hi);
+
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 1);
+	if (read_user_wptr(mm, wptr64, data64)) {
+		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		       lower_32_bits(data64));
+		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR_HI,
+		       upper_32_bits(data64));
+	} else {
+		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		       m->sdmax_rlcx_rb_rptr);
+		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR_HI,
+		       m->sdmax_rlcx_rb_rptr_hi);
+	}
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 0);
+
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
+			m->sdmax_rlcx_rb_base_hi);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
+			m->sdmax_rlcx_rb_rptr_addr_lo);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
+			m->sdmax_rlcx_rb_rptr_addr_hi);
+
+	data = REG_SET_FIELD(m->sdmax_rlcx_rb_cntl, SDMA0_RLC0_RB_CNTL,
+			     RB_ENABLE, 1);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, data);
+
+	return 0;
+}
+
+static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
+			     uint32_t engine_id, uint32_t queue_id,
+			     uint32_t (**dump)[2], uint32_t *n_regs)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t sdma_base_addr = get_sdma_base_addr(adev, engine_id, queue_id);
+	uint32_t i = 0, reg;
+#undef HQD_N_REGS
+#define HQD_N_REGS (19+6+7+10)
+
+	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	if (*dump == NULL)
+		return -ENOMEM;
+
+	for (reg = mmSDMA0_RLC0_RB_CNTL; reg <= mmSDMA0_RLC0_DOORBELL; reg++)
+		DUMP_REG(sdma_base_addr + reg);
+	for (reg = mmSDMA0_RLC0_STATUS; reg <= mmSDMA0_RLC0_CSA_ADDR_HI; reg++)
+		DUMP_REG(sdma_base_addr + reg);
+	for (reg = mmSDMA0_RLC0_IB_SUB_REMAIN;
+	     reg <= mmSDMA0_RLC0_MINOR_PTR_UPDATE; reg++)
+		DUMP_REG(sdma_base_addr + reg);
+	for (reg = mmSDMA0_RLC0_MIDCMD_DATA0;
+	     reg <= mmSDMA0_RLC0_MIDCMD_CNTL; reg++)
+		DUMP_REG(sdma_base_addr + reg);
+
+	WARN_ON_ONCE(i != HQD_N_REGS);
+	*n_regs = i;
+
+	return 0;
+}
+
+static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
+				uint32_t pipe_id, uint32_t queue_id)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t act;
+	bool retval = false;
+	uint32_t low, high;
+
+	acquire_queue(kgd, pipe_id, queue_id);
+	act = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE));
+	if (act) {
+		low = lower_32_bits(queue_address >> 8);
+		high = upper_32_bits(queue_address >> 8);
+
+		if (low == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE)) &&
+		   high == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE_HI)))
+			retval = true;
+	}
+	release_queue(kgd);
+	return retval;
+}
+
+static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct v9_sdma_mqd *m;
+	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_rb_cntl;
+
+	m = get_sdma_mqd(mqd);
+	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+					    m->sdma_queue_id);
+
+	sdma_rlc_rb_cntl = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+
+	if (sdma_rlc_rb_cntl & SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK)
+		return true;
+
+	return false;
+}
+
+static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
+				enum kfd_preempt_type reset_type,
+				unsigned int utimeout, uint32_t pipe_id,
+				uint32_t queue_id)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	enum hqd_dequeue_request_type type;
+	unsigned long end_jiffies;
+	uint32_t temp;
+	struct v9_mqd *m = get_mqd(mqd);
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	if (m->cp_hqd_vmid == 0)
+		WREG32_FIELD15(GC, 0, RLC_CP_SCHEDULERS, scheduler1, 0);
+
+	switch (reset_type) {
+	case KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN:
+		type = DRAIN_PIPE;
+		break;
+	case KFD_PREEMPT_TYPE_WAVEFRONT_RESET:
+		type = RESET_WAVES;
+		break;
+	default:
+		type = DRAIN_PIPE;
+		break;
+	}
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_DEQUEUE_REQUEST), type);
+
+	end_jiffies = (utimeout * HZ / 1000) + jiffies;
+	while (true) {
+		temp = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE));
+		if (!(temp & CP_HQD_ACTIVE__ACTIVE_MASK))
+			break;
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("cp queue preemption time out.\n");
+			release_queue(kgd);
+			return -ETIME;
+		}
+		usleep_range(500, 1000);
+	}
+
+	release_queue(kgd);
+	return 0;
+}
+
+static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
+				unsigned int utimeout)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct v9_sdma_mqd *m;
+	uint32_t sdma_base_addr;
+	uint32_t temp;
+	unsigned long end_jiffies = (utimeout * HZ / 1000) + jiffies;
+
+	m = get_sdma_mqd(mqd);
+	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+					    m->sdma_queue_id);
+
+	temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	temp = temp & ~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK;
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, temp);
+
+	while (true) {
+		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
+			break;
+		if (time_after(jiffies, end_jiffies))
+			return -ETIME;
+		usleep_range(500, 1000);
+	}
+
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
+	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
+
+	m->sdmax_rlcx_rb_rptr = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR);
+	m->sdmax_rlcx_rb_rptr_hi =
+		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_HI);
+
+	return 0;
+}
+
+static bool get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
+							uint8_t vmid)
+{
+	uint32_t reg;
+	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+
+	reg = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
+		     + vmid);
+	return reg & ATC_VMID0_PASID_MAPPING__VALID_MASK;
+}
+
+static uint16_t get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
+								uint8_t vmid)
+{
+	uint32_t reg;
+	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+
+	reg = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
+		     + vmid);
+	return reg & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+}
+
+static void write_vmid_invalidate_request(struct kgd_dev *kgd, uint8_t vmid)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+	uint32_t req = (1 << vmid) |
+		(0 << VM_INVALIDATE_ENG16_REQ__FLUSH_TYPE__SHIFT) | /* legacy */
+		VM_INVALIDATE_ENG16_REQ__INVALIDATE_L2_PTES_MASK |
+		VM_INVALIDATE_ENG16_REQ__INVALIDATE_L2_PDE0_MASK |
+		VM_INVALIDATE_ENG16_REQ__INVALIDATE_L2_PDE1_MASK |
+		VM_INVALIDATE_ENG16_REQ__INVALIDATE_L2_PDE2_MASK |
+		VM_INVALIDATE_ENG16_REQ__INVALIDATE_L1_PTES_MASK;
+
+	mutex_lock(&adev->srbm_mutex);
+
+	/* Use legacy mode tlb invalidation.
+	 *
+	 * Currently on Raven the code below is broken for anything but
+	 * legacy mode due to a MMHUB power gating problem. A workaround
+	 * is for MMHUB to wait until the condition PER_VMID_INVALIDATE_REQ
+	 * == PER_VMID_INVALIDATE_ACK instead of simply waiting for the ack
+	 * bit.
+	 *
+	 * TODO 1: agree on the right set of invalidation registers for
+	 * KFD use. Use the last one for now. Invalidate both GC and
+	 * MMHUB.
+	 *
+	 * TODO 2: support range-based invalidation, requires kfg2kgd
+	 * interface change
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG16_ADDR_RANGE_LO32),
+				0xffffffff);
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG16_ADDR_RANGE_HI32),
+				0x0000001f);
+
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0,
+				mmMMHUB_VM_INVALIDATE_ENG16_ADDR_RANGE_LO32),
+				0xffffffff);
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0,
+				mmMMHUB_VM_INVALIDATE_ENG16_ADDR_RANGE_HI32),
+				0x0000001f);
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG16_REQ), req);
+
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0, mmMMHUB_VM_INVALIDATE_ENG16_REQ),
+				req);
+
+	while (!(RREG32(SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG16_ACK)) &
+					(1 << vmid)))
+		cpu_relax();
+
+	while (!(RREG32(SOC15_REG_OFFSET(MMHUB, 0,
+					mmMMHUB_VM_INVALIDATE_ENG16_ACK)) &
+					(1 << vmid)))
+		cpu_relax();
+
+	mutex_unlock(&adev->srbm_mutex);
+
+}
+
+static int invalidate_tlbs_with_kiq(struct amdgpu_device *adev, uint16_t pasid)
+{
+	signed long r;
+	uint32_t seq;
+	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
+
+	spin_lock(&adev->gfx.kiq.ring_lock);
+	amdgpu_ring_alloc(ring, 12); /* fence + invalidate_tlbs package*/
+	amdgpu_ring_write(ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
+	amdgpu_ring_write(ring,
+			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
+			PACKET3_INVALIDATE_TLBS_ALL_HUB(1) |
+			PACKET3_INVALIDATE_TLBS_PASID(pasid) |
+			PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(0)); /* legacy */
+	amdgpu_fence_emit_polling(ring, &seq);
+	amdgpu_ring_commit(ring);
+	spin_unlock(&adev->gfx.kiq.ring_lock);
+
+	r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+	if (r < 1) {
+		DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+		return -ETIME;
+	}
+
+	return 0;
+}
+
+static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+	int vmid;
+	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
+
+	if (ring->ready)
+		return invalidate_tlbs_with_kiq(adev, pasid);
+
+	for (vmid = 0; vmid < 16; vmid++) {
+		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
+			continue;
+		if (get_atc_vmid_pasid_mapping_valid(kgd, vmid)) {
+			if (get_atc_vmid_pasid_mapping_pasid(kgd, vmid)
+				== pasid) {
+				write_vmid_invalidate_request(kgd, vmid);
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+
+	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
+		pr_err("non kfd vmid %d\n", vmid);
+		return 0;
+	}
+
+	write_vmid_invalidate_request(kgd, vmid);
+	return 0;
+}
+
+static int kgd_address_watch_disable(struct kgd_dev *kgd)
+{
+	return 0;
+}
+
+static int kgd_address_watch_execute(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					uint32_t cntl_val,
+					uint32_t addr_hi,
+					uint32_t addr_lo)
+{
+	return 0;
+}
+
+static int kgd_wave_control_execute(struct kgd_dev *kgd,
+					uint32_t gfx_index_val,
+					uint32_t sq_cmd)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint32_t data = 0;
+
+	mutex_lock(&adev->grbm_idx_mutex);
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX), gfx_index_val);
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CMD), sq_cmd);
+
+	data = REG_SET_FIELD(data, GRBM_GFX_INDEX,
+		INSTANCE_BROADCAST_WRITES, 1);
+	data = REG_SET_FIELD(data, GRBM_GFX_INDEX,
+		SH_BROADCAST_WRITES, 1);
+	data = REG_SET_FIELD(data, GRBM_GFX_INDEX,
+		SE_BROADCAST_WRITES, 1);
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX), data);
+	mutex_unlock(&adev->grbm_idx_mutex);
+
+	return 0;
+}
+
+static uint32_t kgd_address_watch_get_offset(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					unsigned int reg_offset)
+{
+	return 0;
+}
+
+static void set_scratch_backing_va(struct kgd_dev *kgd,
+					uint64_t va, uint32_t vmid)
+{
+	/* No longer needed on GFXv9. The scratch base address is
+	 * passed to the shader by the CP. It's the user mode driver's
+	 * responsibility.
+	 */
+}
+
+/* FIXME: Does this need to be ASIC-specific code? */
+static uint16_t get_fw_version(struct kgd_dev *kgd, enum kgd_engine_type type)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+	const union amdgpu_firmware_header *hdr;
+
+	switch (type) {
+	case KGD_ENGINE_PFP:
+		hdr = (const union amdgpu_firmware_header *)adev->gfx.pfp_fw->data;
+		break;
+
+	case KGD_ENGINE_ME:
+		hdr = (const union amdgpu_firmware_header *)adev->gfx.me_fw->data;
+		break;
+
+	case KGD_ENGINE_CE:
+		hdr = (const union amdgpu_firmware_header *)adev->gfx.ce_fw->data;
+		break;
+
+	case KGD_ENGINE_MEC1:
+		hdr = (const union amdgpu_firmware_header *)adev->gfx.mec_fw->data;
+		break;
+
+	case KGD_ENGINE_MEC2:
+		hdr = (const union amdgpu_firmware_header *)adev->gfx.mec2_fw->data;
+		break;
+
+	case KGD_ENGINE_RLC:
+		hdr = (const union amdgpu_firmware_header *)adev->gfx.rlc_fw->data;
+		break;
+
+	case KGD_ENGINE_SDMA1:
+		hdr = (const union amdgpu_firmware_header *)adev->sdma.instance[0].fw->data;
+		break;
+
+	case KGD_ENGINE_SDMA2:
+		hdr = (const union amdgpu_firmware_header *)adev->sdma.instance[1].fw->data;
+		break;
+
+	default:
+		return 0;
+	}
+
+	if (hdr == NULL)
+		return 0;
+
+	/* Only 12 bit in use*/
+	return hdr->common.ucode_version;
+}
+
+static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
+		uint32_t page_table_base)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	uint64_t base = (uint64_t)page_table_base << PAGE_SHIFT |
+		AMDGPU_PTE_VALID;
+
+	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
+		pr_err("trying to set page table base for wrong VMID %u\n",
+		       vmid);
+		return;
+	}
+
+	/* TODO: take advantage of per-process address space size. For
+	 * now, all processes share the same address space size, like
+	 * on GFX8 and older.
+	 */
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0, mmMMHUB_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32) + (vmid*2), 0);
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0, mmMMHUB_VM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32) + (vmid*2), 0);
+
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0, mmMMHUB_VM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32) + (vmid*2),
+			lower_32_bits(adev->vm_manager.max_pfn - 1));
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0, mmMMHUB_VM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32) + (vmid*2),
+			upper_32_bits(adev->vm_manager.max_pfn - 1));
+
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0, mmMMHUB_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32) + (vmid*2), lower_32_bits(base));
+	WREG32(SOC15_REG_OFFSET(MMHUB, 0, mmMMHUB_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32) + (vmid*2), upper_32_bits(base));
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32) + (vmid*2), 0);
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32) + (vmid*2), 0);
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32) + (vmid*2),
+			lower_32_bits(adev->vm_manager.max_pfn - 1));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32) + (vmid*2),
+			upper_32_bits(adev->vm_manager.max_pfn - 1));
+
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32) + (vmid*2), lower_32_bits(base));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32) + (vmid*2), upper_32_bits(base));
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 1d6e1479da38..ff8fd75f7ca5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -23,6 +23,8 @@
 #define pr_fmt(fmt) "kfd2kgd: " fmt
 
 #include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/sched/mm.h>
 #include <drm/drmP.h>
 #include "amdgpu_object.h"
 #include "amdgpu_vm.h"
@@ -33,10 +35,20 @@
  */
 #define VI_BO_SIZE_ALIGN (0x8000)
 
+/* BO flag to indicate a KFD userptr BO */
+#define AMDGPU_AMDKFD_USERPTR_BO (1ULL << 63)
+
+/* Userptr restore delay, just long enough to allow consecutive VM
+ * changes to accumulate
+ */
+#define AMDGPU_USERPTR_RESTORE_DELAY_MS 1
+
 /* Impose limit on how much memory KFD can use */
 static struct {
 	uint64_t max_system_mem_limit;
+	uint64_t max_userptr_mem_limit;
 	int64_t system_mem_used;
+	int64_t userptr_mem_used;
 	spinlock_t mem_limit_lock;
 } kfd_mem_limit;
 
@@ -57,6 +69,7 @@ static const char * const domain_bit_to_string[] = {
 
 #define domain_string(domain) domain_bit_to_string[ffs(domain)-1]
 
+static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work);
 
 
 static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
@@ -78,6 +91,7 @@ static bool check_if_add_bo_to_vm(struct amdgpu_vm *avm,
 
 /* Set memory usage limits. Current, limits are
  *  System (kernel) memory - 3/8th System RAM
+ *  Userptr memory - 3/4th System RAM
  */
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
 {
@@ -90,8 +104,10 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
 
 	spin_lock_init(&kfd_mem_limit.mem_limit_lock);
 	kfd_mem_limit.max_system_mem_limit = (mem >> 1) - (mem >> 3);
-	pr_debug("Kernel memory limit %lluM\n",
-		(kfd_mem_limit.max_system_mem_limit >> 20));
+	kfd_mem_limit.max_userptr_mem_limit = mem - (mem >> 2);
+	pr_debug("Kernel memory limit %lluM, userptr limit %lluM\n",
+		(kfd_mem_limit.max_system_mem_limit >> 20),
+		(kfd_mem_limit.max_userptr_mem_limit >> 20));
 }
 
 static int amdgpu_amdkfd_reserve_system_mem_limit(struct amdgpu_device *adev,
@@ -111,6 +127,16 @@ static int amdgpu_amdkfd_reserve_system_mem_limit(struct amdgpu_device *adev,
 			goto err_no_mem;
 		}
 		kfd_mem_limit.system_mem_used += (acc_size + size);
+	} else if (domain == AMDGPU_GEM_DOMAIN_CPU) {
+		if ((kfd_mem_limit.system_mem_used + acc_size >
+			kfd_mem_limit.max_system_mem_limit) ||
+			(kfd_mem_limit.userptr_mem_used + (size + acc_size) >
+			kfd_mem_limit.max_userptr_mem_limit)) {
+			ret = -ENOMEM;
+			goto err_no_mem;
+		}
+		kfd_mem_limit.system_mem_used += acc_size;
+		kfd_mem_limit.userptr_mem_used += size;
 	}
 err_no_mem:
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
@@ -126,10 +152,16 @@ static void unreserve_system_mem_limit(struct amdgpu_device *adev,
 				       sizeof(struct amdgpu_bo));
 
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
-	if (domain == AMDGPU_GEM_DOMAIN_GTT)
+	if (domain == AMDGPU_GEM_DOMAIN_GTT) {
 		kfd_mem_limit.system_mem_used -= (acc_size + size);
+	} else if (domain == AMDGPU_GEM_DOMAIN_CPU) {
+		kfd_mem_limit.system_mem_used -= acc_size;
+		kfd_mem_limit.userptr_mem_used -= size;
+	}
 	WARN_ONCE(kfd_mem_limit.system_mem_used < 0,
 		  "kfd system memory accounting unbalanced");
+	WARN_ONCE(kfd_mem_limit.userptr_mem_used < 0,
+		  "kfd userptr memory accounting unbalanced");
 
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
 }
@@ -138,12 +170,17 @@ void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo)
 {
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
 
-	if (bo->preferred_domains == AMDGPU_GEM_DOMAIN_GTT) {
+	if (bo->flags & AMDGPU_AMDKFD_USERPTR_BO) {
+		kfd_mem_limit.system_mem_used -= bo->tbo.acc_size;
+		kfd_mem_limit.userptr_mem_used -= amdgpu_bo_size(bo);
+	} else if (bo->preferred_domains == AMDGPU_GEM_DOMAIN_GTT) {
 		kfd_mem_limit.system_mem_used -=
 			(bo->tbo.acc_size + amdgpu_bo_size(bo));
 	}
 	WARN_ONCE(kfd_mem_limit.system_mem_used < 0,
 		  "kfd system memory accounting unbalanced");
+	WARN_ONCE(kfd_mem_limit.userptr_mem_used < 0,
+		  "kfd userptr memory accounting unbalanced");
 
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
 }
@@ -506,7 +543,8 @@ static void remove_bo_from_vm(struct amdgpu_device *adev,
 }
 
 static void add_kgd_mem_to_kfd_bo_list(struct kgd_mem *mem,
-				struct amdkfd_process_info *process_info)
+				struct amdkfd_process_info *process_info,
+				bool userptr)
 {
 	struct ttm_validate_buffer *entry = &mem->validate_list;
 	struct amdgpu_bo *bo = mem->bo;
@@ -515,10 +553,95 @@ static void add_kgd_mem_to_kfd_bo_list(struct kgd_mem *mem,
 	entry->shared = true;
 	entry->bo = &bo->tbo;
 	mutex_lock(&process_info->lock);
-	list_add_tail(&entry->head, &process_info->kfd_bo_list);
+	if (userptr)
+		list_add_tail(&entry->head, &process_info->userptr_valid_list);
+	else
+		list_add_tail(&entry->head, &process_info->kfd_bo_list);
 	mutex_unlock(&process_info->lock);
 }
 
+/* Initializes user pages. It registers the MMU notifier and validates
+ * the userptr BO in the GTT domain.
+ *
+ * The BO must already be on the userptr_valid_list. Otherwise an
+ * eviction and restore may happen that leaves the new BO unmapped
+ * with the user mode queues running.
+ *
+ * Takes the process_info->lock to protect against concurrent restore
+ * workers.
+ *
+ * Returns 0 for success, negative errno for errors.
+ */
+static int init_user_pages(struct kgd_mem *mem, struct mm_struct *mm,
+			   uint64_t user_addr)
+{
+	struct amdkfd_process_info *process_info = mem->process_info;
+	struct amdgpu_bo *bo = mem->bo;
+	struct ttm_operation_ctx ctx = { true, false };
+	int ret = 0;
+
+	mutex_lock(&process_info->lock);
+
+	ret = amdgpu_ttm_tt_set_userptr(bo->tbo.ttm, user_addr, 0);
+	if (ret) {
+		pr_err("%s: Failed to set userptr: %d\n", __func__, ret);
+		goto out;
+	}
+
+	ret = amdgpu_mn_register(bo, user_addr);
+	if (ret) {
+		pr_err("%s: Failed to register MMU notifier: %d\n",
+		       __func__, ret);
+		goto out;
+	}
+
+	/* If no restore worker is running concurrently, user_pages
+	 * should not be allocated
+	 */
+	WARN(mem->user_pages, "Leaking user_pages array");
+
+	mem->user_pages = kvmalloc_array(bo->tbo.ttm->num_pages,
+					   sizeof(struct page *),
+					   GFP_KERNEL | __GFP_ZERO);
+	if (!mem->user_pages) {
+		pr_err("%s: Failed to allocate pages array\n", __func__);
+		ret = -ENOMEM;
+		goto unregister_out;
+	}
+
+	ret = amdgpu_ttm_tt_get_user_pages(bo->tbo.ttm, mem->user_pages);
+	if (ret) {
+		pr_err("%s: Failed to get user pages: %d\n", __func__, ret);
+		goto free_out;
+	}
+
+	amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm, mem->user_pages);
+
+	ret = amdgpu_bo_reserve(bo, true);
+	if (ret) {
+		pr_err("%s: Failed to reserve BO\n", __func__);
+		goto release_out;
+	}
+	amdgpu_ttm_placement_from_domain(bo, mem->domain);
+	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+	if (ret)
+		pr_err("%s: failed to validate BO\n", __func__);
+	amdgpu_bo_unreserve(bo);
+
+release_out:
+	if (ret)
+		release_pages(mem->user_pages, bo->tbo.ttm->num_pages);
+free_out:
+	kvfree(mem->user_pages);
+	mem->user_pages = NULL;
+unregister_out:
+	if (ret)
+		amdgpu_mn_unregister(bo);
+out:
+	mutex_unlock(&process_info->lock);
+	return ret;
+}
+
 /* Reserving a BO and its page table BOs must happen atomically to
  * avoid deadlocks. Some operations update multiple VMs at once. Track
  * all the reservation info in a context structure. Optionally a sync
@@ -748,7 +871,8 @@ static int update_gpuvm_pte(struct amdgpu_device *adev,
 }
 
 static int map_bo_to_gpuvm(struct amdgpu_device *adev,
-		struct kfd_bo_va_list *entry, struct amdgpu_sync *sync)
+		struct kfd_bo_va_list *entry, struct amdgpu_sync *sync,
+		bool no_update_pte)
 {
 	int ret;
 
@@ -762,6 +886,9 @@ static int map_bo_to_gpuvm(struct amdgpu_device *adev,
 		return ret;
 	}
 
+	if (no_update_pte)
+		return 0;
+
 	ret = update_gpuvm_pte(adev, entry, sync);
 	if (ret) {
 		pr_err("update_gpuvm_pte() failed\n");
@@ -820,6 +947,8 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 		mutex_init(&info->lock);
 		INIT_LIST_HEAD(&info->vm_list_head);
 		INIT_LIST_HEAD(&info->kfd_bo_list);
+		INIT_LIST_HEAD(&info->userptr_valid_list);
+		INIT_LIST_HEAD(&info->userptr_inval_list);
 
 		info->eviction_fence =
 			amdgpu_amdkfd_fence_create(dma_fence_context_alloc(1),
@@ -830,6 +959,11 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 			goto create_evict_fence_fail;
 		}
 
+		info->pid = get_task_pid(current->group_leader, PIDTYPE_PID);
+		atomic_set(&info->evicted_bos, 0);
+		INIT_DELAYED_WORK(&info->restore_userptr_work,
+				  amdgpu_amdkfd_restore_userptr_worker);
+
 		*process_info = info;
 		*ef = dma_fence_get(&info->eviction_fence->base);
 	}
@@ -872,6 +1006,7 @@ reserve_pd_fail:
 		dma_fence_put(*ef);
 		*ef = NULL;
 		*process_info = NULL;
+		put_pid(info->pid);
 create_evict_fence_fail:
 		mutex_destroy(&info->lock);
 		kfree(info);
@@ -967,8 +1102,12 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 	/* Release per-process resources when last compute VM is destroyed */
 	if (!process_info->n_vms) {
 		WARN_ON(!list_empty(&process_info->kfd_bo_list));
+		WARN_ON(!list_empty(&process_info->userptr_valid_list));
+		WARN_ON(!list_empty(&process_info->userptr_inval_list));
 
 		dma_fence_put(&process_info->eviction_fence->base);
+		cancel_delayed_work_sync(&process_info->restore_userptr_work);
+		put_pid(process_info->pid);
 		mutex_destroy(&process_info->lock);
 		kfree(process_info);
 	}
@@ -1003,9 +1142,11 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;
+	uint64_t user_addr = 0;
 	struct amdgpu_bo *bo;
+	struct amdgpu_bo_param bp;
 	int byte_align;
-	u32 alloc_domain;
+	u32 domain, alloc_domain;
 	u64 alloc_flags;
 	uint32_t mapping_flags;
 	int ret;
@@ -1014,14 +1155,21 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	 * Check on which domain to allocate BO
 	 */
 	if (flags & ALLOC_MEM_FLAGS_VRAM) {
-		alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
+		domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
 		alloc_flags = AMDGPU_GEM_CREATE_VRAM_CLEARED;
 		alloc_flags |= (flags & ALLOC_MEM_FLAGS_PUBLIC) ?
 			AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED :
 			AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
 	} else if (flags & ALLOC_MEM_FLAGS_GTT) {
-		alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
+		domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
+		alloc_flags = 0;
+	} else if (flags & ALLOC_MEM_FLAGS_USERPTR) {
+		domain = AMDGPU_GEM_DOMAIN_GTT;
+		alloc_domain = AMDGPU_GEM_DOMAIN_CPU;
 		alloc_flags = 0;
+		if (!offset || !*offset)
+			return -EINVAL;
+		user_addr = *offset;
 	} else {
 		return -EINVAL;
 	}
@@ -1069,8 +1217,14 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s\n",
 			va, size, domain_string(alloc_domain));
 
-	ret = amdgpu_bo_create(adev, size, byte_align,
-				alloc_domain, alloc_flags, ttm_bo_type_device, NULL, &bo);
+	memset(&bp, 0, sizeof(bp));
+	bp.size = size;
+	bp.byte_align = byte_align;
+	bp.domain = alloc_domain;
+	bp.flags = alloc_flags;
+	bp.type = ttm_bo_type_device;
+	bp.resv = NULL;
+	ret = amdgpu_bo_create(adev, &bp, &bo);
 	if (ret) {
 		pr_debug("Failed to create BO on domain %s. ret %d\n",
 				domain_string(alloc_domain), ret);
@@ -1078,18 +1232,34 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	}
 	bo->kfd_bo = *mem;
 	(*mem)->bo = bo;
+	if (user_addr)
+		bo->flags |= AMDGPU_AMDKFD_USERPTR_BO;
 
 	(*mem)->va = va;
-	(*mem)->domain = alloc_domain;
+	(*mem)->domain = domain;
 	(*mem)->mapped_to_gpu_memory = 0;
 	(*mem)->process_info = avm->process_info;
-	add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info);
+	add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr);
+
+	if (user_addr) {
+		ret = init_user_pages(*mem, current->mm, user_addr);
+		if (ret) {
+			mutex_lock(&avm->process_info->lock);
+			list_del(&(*mem)->validate_list.head);
+			mutex_unlock(&avm->process_info->lock);
+			goto allocate_init_user_pages_failed;
+		}
+	}
 
 	if (offset)
 		*offset = amdgpu_bo_mmap_offset(bo);
 
 	return 0;
 
+allocate_init_user_pages_failed:
+	amdgpu_bo_unref(&bo);
+	/* Don't unreserve system mem limit twice */
+	goto err_reserve_system_mem;
 err_bo_create:
 	unreserve_system_mem_limit(adev, size, alloc_domain);
 err_reserve_system_mem:
@@ -1122,12 +1292,24 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	 * be freed anyway
 	 */
 
+	/* No more MMU notifiers */
+	amdgpu_mn_unregister(mem->bo);
+
 	/* Make sure restore workers don't access the BO any more */
 	bo_list_entry = &mem->validate_list;
 	mutex_lock(&process_info->lock);
 	list_del(&bo_list_entry->head);
 	mutex_unlock(&process_info->lock);
 
+	/* Free user pages if necessary */
+	if (mem->user_pages) {
+		pr_debug("%s: Freeing user_pages array\n", __func__);
+		if (mem->user_pages[0])
+			release_pages(mem->user_pages,
+					mem->bo->tbo.ttm->num_pages);
+		kvfree(mem->user_pages);
+	}
+
 	ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx);
 	if (unlikely(ret))
 		return ret;
@@ -1173,21 +1355,32 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 	struct kfd_bo_va_list *bo_va_entry = NULL;
 	struct kfd_bo_va_list *bo_va_entry_aql = NULL;
 	unsigned long bo_size;
-
-	/* Make sure restore is not running concurrently.
-	 */
-	mutex_lock(&mem->process_info->lock);
-
-	mutex_lock(&mem->lock);
+	bool is_invalid_userptr = false;
 
 	bo = mem->bo;
-
 	if (!bo) {
 		pr_err("Invalid BO when mapping memory to GPU\n");
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
+	/* Make sure restore is not running concurrently. Since we
+	 * don't map invalid userptr BOs, we rely on the next restore
+	 * worker to do the mapping
+	 */
+	mutex_lock(&mem->process_info->lock);
+
+	/* Lock mmap-sem. If we find an invalid userptr BO, we can be
+	 * sure that the MMU notifier is no longer running
+	 * concurrently and the queues are actually stopped
+	 */
+	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) {
+		down_write(&current->mm->mmap_sem);
+		is_invalid_userptr = atomic_read(&mem->invalid);
+		up_write(&current->mm->mmap_sem);
+	}
+
+	mutex_lock(&mem->lock);
+
 	domain = mem->domain;
 	bo_size = bo->tbo.mem.size;
 
@@ -1200,6 +1393,14 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 	if (unlikely(ret))
 		goto out;
 
+	/* Userptr can be marked as "not invalid", but not actually be
+	 * validated yet (still in the system domain). In that case
+	 * the queues are still stopped and we can leave mapping for
+	 * the next restore worker
+	 */
+	if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM)
+		is_invalid_userptr = true;
+
 	if (check_if_add_bo_to_vm(avm, mem)) {
 		ret = add_bo_to_vm(adev, mem, avm, false,
 				&bo_va_entry);
@@ -1217,7 +1418,8 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 			goto add_bo_to_vm_failed;
 	}
 
-	if (mem->mapped_to_gpu_memory == 0) {
+	if (mem->mapped_to_gpu_memory == 0 &&
+	    !amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) {
 		/* Validate BO only once. The eviction fence gets added to BO
 		 * the first time it is mapped. Validate will wait for all
 		 * background evictions to complete.
@@ -1235,7 +1437,8 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 					entry->va, entry->va + bo_size,
 					entry);
 
-			ret = map_bo_to_gpuvm(adev, entry, ctx.sync);
+			ret = map_bo_to_gpuvm(adev, entry, ctx.sync,
+					      is_invalid_userptr);
 			if (ret) {
 				pr_err("Failed to map radeon bo to gpuvm\n");
 				goto map_bo_to_gpuvm_failed;
@@ -1418,6 +1621,337 @@ bo_reserve_failed:
 	return ret;
 }
 
+/* Evict a userptr BO by stopping the queues if necessary
+ *
+ * Runs in MMU notifier, may be in RECLAIM_FS context. This means it
+ * cannot do any memory allocations, and cannot take any locks that
+ * are held elsewhere while allocating memory. Therefore this is as
+ * simple as possible, using atomic counters.
+ *
+ * It doesn't do anything to the BO itself. The real work happens in
+ * restore, where we get updated page addresses. This function only
+ * ensures that GPU access to the BO is stopped.
+ */
+int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem,
+				struct mm_struct *mm)
+{
+	struct amdkfd_process_info *process_info = mem->process_info;
+	int invalid, evicted_bos;
+	int r = 0;
+
+	invalid = atomic_inc_return(&mem->invalid);
+	evicted_bos = atomic_inc_return(&process_info->evicted_bos);
+	if (evicted_bos == 1) {
+		/* First eviction, stop the queues */
+		r = kgd2kfd->quiesce_mm(mm);
+		if (r)
+			pr_err("Failed to quiesce KFD\n");
+		schedule_delayed_work(&process_info->restore_userptr_work,
+			msecs_to_jiffies(AMDGPU_USERPTR_RESTORE_DELAY_MS));
+	}
+
+	return r;
+}
+
+/* Update invalid userptr BOs
+ *
+ * Moves invalidated (evicted) userptr BOs from userptr_valid_list to
+ * userptr_inval_list and updates user pages for all BOs that have
+ * been invalidated since their last update.
+ */
+static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
+				     struct mm_struct *mm)
+{
+	struct kgd_mem *mem, *tmp_mem;
+	struct amdgpu_bo *bo;
+	struct ttm_operation_ctx ctx = { false, false };
+	int invalid, ret;
+
+	/* Move all invalidated BOs to the userptr_inval_list and
+	 * release their user pages by migration to the CPU domain
+	 */
+	list_for_each_entry_safe(mem, tmp_mem,
+				 &process_info->userptr_valid_list,
+				 validate_list.head) {
+		if (!atomic_read(&mem->invalid))
+			continue; /* BO is still valid */
+
+		bo = mem->bo;
+
+		if (amdgpu_bo_reserve(bo, true))
+			return -EAGAIN;
+		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
+		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+		amdgpu_bo_unreserve(bo);
+		if (ret) {
+			pr_err("%s: Failed to invalidate userptr BO\n",
+			       __func__);
+			return -EAGAIN;
+		}
+
+		list_move_tail(&mem->validate_list.head,
+			       &process_info->userptr_inval_list);
+	}
+
+	if (list_empty(&process_info->userptr_inval_list))
+		return 0; /* All evicted userptr BOs were freed */
+
+	/* Go through userptr_inval_list and update any invalid user_pages */
+	list_for_each_entry(mem, &process_info->userptr_inval_list,
+			    validate_list.head) {
+		invalid = atomic_read(&mem->invalid);
+		if (!invalid)
+			/* BO hasn't been invalidated since the last
+			 * revalidation attempt. Keep its BO list.
+			 */
+			continue;
+
+		bo = mem->bo;
+
+		if (!mem->user_pages) {
+			mem->user_pages =
+				kvmalloc_array(bo->tbo.ttm->num_pages,
+						 sizeof(struct page *),
+						 GFP_KERNEL | __GFP_ZERO);
+			if (!mem->user_pages) {
+				pr_err("%s: Failed to allocate pages array\n",
+				       __func__);
+				return -ENOMEM;
+			}
+		} else if (mem->user_pages[0]) {
+			release_pages(mem->user_pages, bo->tbo.ttm->num_pages);
+		}
+
+		/* Get updated user pages */
+		ret = amdgpu_ttm_tt_get_user_pages(bo->tbo.ttm,
+						   mem->user_pages);
+		if (ret) {
+			mem->user_pages[0] = NULL;
+			pr_info("%s: Failed to get user pages: %d\n",
+				__func__, ret);
+			/* Pretend it succeeded. It will fail later
+			 * with a VM fault if the GPU tries to access
+			 * it. Better than hanging indefinitely with
+			 * stalled user mode queues.
+			 */
+		}
+
+		/* Mark the BO as valid unless it was invalidated
+		 * again concurrently
+		 */
+		if (atomic_cmpxchg(&mem->invalid, invalid, 0) != invalid)
+			return -EAGAIN;
+	}
+
+	return 0;
+}
+
+/* Validate invalid userptr BOs
+ *
+ * Validates BOs on the userptr_inval_list, and moves them back to the
+ * userptr_valid_list. Also updates GPUVM page tables with new page
+ * addresses and waits for the page table updates to complete.
+ */
+static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
+{
+	struct amdgpu_bo_list_entry *pd_bo_list_entries;
+	struct list_head resv_list, duplicates;
+	struct ww_acquire_ctx ticket;
+	struct amdgpu_sync sync;
+
+	struct amdgpu_vm *peer_vm;
+	struct kgd_mem *mem, *tmp_mem;
+	struct amdgpu_bo *bo;
+	struct ttm_operation_ctx ctx = { false, false };
+	int i, ret;
+
+	pd_bo_list_entries = kcalloc(process_info->n_vms,
+				     sizeof(struct amdgpu_bo_list_entry),
+				     GFP_KERNEL);
+	if (!pd_bo_list_entries) {
+		pr_err("%s: Failed to allocate PD BO list entries\n", __func__);
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&resv_list);
+	INIT_LIST_HEAD(&duplicates);
+
+	/* Get all the page directory BOs that need to be reserved */
+	i = 0;
+	list_for_each_entry(peer_vm, &process_info->vm_list_head,
+			    vm_list_node)
+		amdgpu_vm_get_pd_bo(peer_vm, &resv_list,
+				    &pd_bo_list_entries[i++]);
+	/* Add the userptr_inval_list entries to resv_list */
+	list_for_each_entry(mem, &process_info->userptr_inval_list,
+			    validate_list.head) {
+		list_add_tail(&mem->resv_list.head, &resv_list);
+		mem->resv_list.bo = mem->validate_list.bo;
+		mem->resv_list.shared = mem->validate_list.shared;
+	}
+
+	/* Reserve all BOs and page tables for validation */
+	ret = ttm_eu_reserve_buffers(&ticket, &resv_list, false, &duplicates);
+	WARN(!list_empty(&duplicates), "Duplicates should be empty");
+	if (ret)
+		goto out;
+
+	amdgpu_sync_create(&sync);
+
+	/* Avoid triggering eviction fences when unmapping invalid
+	 * userptr BOs (waits for all fences, doesn't use
+	 * FENCE_OWNER_VM)
+	 */
+	list_for_each_entry(peer_vm, &process_info->vm_list_head,
+			    vm_list_node)
+		amdgpu_amdkfd_remove_eviction_fence(peer_vm->root.base.bo,
+						process_info->eviction_fence,
+						NULL, NULL);
+
+	ret = process_validate_vms(process_info);
+	if (ret)
+		goto unreserve_out;
+
+	/* Validate BOs and update GPUVM page tables */
+	list_for_each_entry_safe(mem, tmp_mem,
+				 &process_info->userptr_inval_list,
+				 validate_list.head) {
+		struct kfd_bo_va_list *bo_va_entry;
+
+		bo = mem->bo;
+
+		/* Copy pages array and validate the BO if we got user pages */
+		if (mem->user_pages[0]) {
+			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
+						     mem->user_pages);
+			amdgpu_ttm_placement_from_domain(bo, mem->domain);
+			ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+			if (ret) {
+				pr_err("%s: failed to validate BO\n", __func__);
+				goto unreserve_out;
+			}
+		}
+
+		/* Validate succeeded, now the BO owns the pages, free
+		 * our copy of the pointer array. Put this BO back on
+		 * the userptr_valid_list. If we need to revalidate
+		 * it, we need to start from scratch.
+		 */
+		kvfree(mem->user_pages);
+		mem->user_pages = NULL;
+		list_move_tail(&mem->validate_list.head,
+			       &process_info->userptr_valid_list);
+
+		/* Update mapping. If the BO was not validated
+		 * (because we couldn't get user pages), this will
+		 * clear the page table entries, which will result in
+		 * VM faults if the GPU tries to access the invalid
+		 * memory.
+		 */
+		list_for_each_entry(bo_va_entry, &mem->bo_va_list, bo_list) {
+			if (!bo_va_entry->is_mapped)
+				continue;
+
+			ret = update_gpuvm_pte((struct amdgpu_device *)
+					       bo_va_entry->kgd_dev,
+					       bo_va_entry, &sync);
+			if (ret) {
+				pr_err("%s: update PTE failed\n", __func__);
+				/* make sure this gets validated again */
+				atomic_inc(&mem->invalid);
+				goto unreserve_out;
+			}
+		}
+	}
+
+	/* Update page directories */
+	ret = process_update_pds(process_info, &sync);
+
+unreserve_out:
+	list_for_each_entry(peer_vm, &process_info->vm_list_head,
+			    vm_list_node)
+		amdgpu_bo_fence(peer_vm->root.base.bo,
+				&process_info->eviction_fence->base, true);
+	ttm_eu_backoff_reservation(&ticket, &resv_list);
+	amdgpu_sync_wait(&sync, false);
+	amdgpu_sync_free(&sync);
+out:
+	kfree(pd_bo_list_entries);
+
+	return ret;
+}
+
+/* Worker callback to restore evicted userptr BOs
+ *
+ * Tries to update and validate all userptr BOs. If successful and no
+ * concurrent evictions happened, the queues are restarted. Otherwise,
+ * reschedule for another attempt later.
+ */
+static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct amdkfd_process_info *process_info =
+		container_of(dwork, struct amdkfd_process_info,
+			     restore_userptr_work);
+	struct task_struct *usertask;
+	struct mm_struct *mm;
+	int evicted_bos;
+
+	evicted_bos = atomic_read(&process_info->evicted_bos);
+	if (!evicted_bos)
+		return;
+
+	/* Reference task and mm in case of concurrent process termination */
+	usertask = get_pid_task(process_info->pid, PIDTYPE_PID);
+	if (!usertask)
+		return;
+	mm = get_task_mm(usertask);
+	if (!mm) {
+		put_task_struct(usertask);
+		return;
+	}
+
+	mutex_lock(&process_info->lock);
+
+	if (update_invalid_user_pages(process_info, mm))
+		goto unlock_out;
+	/* userptr_inval_list can be empty if all evicted userptr BOs
+	 * have been freed. In that case there is nothing to validate
+	 * and we can just restart the queues.
+	 */
+	if (!list_empty(&process_info->userptr_inval_list)) {
+		if (atomic_read(&process_info->evicted_bos) != evicted_bos)
+			goto unlock_out; /* Concurrent eviction, try again */
+
+		if (validate_invalid_user_pages(process_info))
+			goto unlock_out;
+	}
+	/* Final check for concurrent evicton and atomic update. If
+	 * another eviction happens after successful update, it will
+	 * be a first eviction that calls quiesce_mm. The eviction
+	 * reference counting inside KFD will handle this case.
+	 */
+	if (atomic_cmpxchg(&process_info->evicted_bos, evicted_bos, 0) !=
+	    evicted_bos)
+		goto unlock_out;
+	evicted_bos = 0;
+	if (kgd2kfd->resume_mm(mm)) {
+		pr_err("%s: Failed to resume KFD\n", __func__);
+		/* No recovery from this failure. Probably the CP is
+		 * hanging. No point trying again.
+		 */
+	}
+unlock_out:
+	mutex_unlock(&process_info->lock);
+	mmput(mm);
+	put_task_struct(usertask);
+
+	/* If validation failed, reschedule another attempt */
+	if (evicted_bos)
+		schedule_delayed_work(&process_info->restore_userptr_work,
+			msecs_to_jiffies(AMDGPU_USERPTR_RESTORE_DELAY_MS));
+}
+
 /** amdgpu_amdkfd_gpuvm_restore_process_bos - Restore all BOs for the given
  *   KFD process identified by process_info
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index a0f48cb9b8f0..236915849cfe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -322,3 +322,47 @@ int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev)
 
 	return ret;
 }
+
+union gfx_info {
+	struct  atom_gfx_info_v2_4 v24;
+};
+
+int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev)
+{
+	struct amdgpu_mode_info *mode_info = &adev->mode_info;
+	int index;
+	uint8_t frev, crev;
+	uint16_t data_offset;
+
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+					    gfx_info);
+	if (amdgpu_atom_parse_data_header(mode_info->atom_context, index, NULL,
+				   &frev, &crev, &data_offset)) {
+		union gfx_info *gfx_info = (union gfx_info *)
+			(mode_info->atom_context->bios + data_offset);
+		switch (crev) {
+		case 4:
+			adev->gfx.config.max_shader_engines = gfx_info->v24.gc_num_se;
+			adev->gfx.config.max_cu_per_sh = gfx_info->v24.gc_num_cu_per_sh;
+			adev->gfx.config.max_sh_per_se = gfx_info->v24.gc_num_sh_per_se;
+			adev->gfx.config.max_backends_per_se = gfx_info->v24.gc_num_rb_per_se;
+			adev->gfx.config.max_texture_channel_caches = gfx_info->v24.gc_num_tccs;
+			adev->gfx.config.max_gprs = le16_to_cpu(gfx_info->v24.gc_num_gprs);
+			adev->gfx.config.max_gs_threads = gfx_info->v24.gc_num_max_gs_thds;
+			adev->gfx.config.gs_vgt_table_depth = gfx_info->v24.gc_gs_table_depth;
+			adev->gfx.config.gs_prim_buffer_depth =
+				le16_to_cpu(gfx_info->v24.gc_gsprim_buff_depth);
+			adev->gfx.config.double_offchip_lds_buf =
+				gfx_info->v24.gc_double_offchip_lds_buffer;
+			adev->gfx.cu_info.wave_front_size = le16_to_cpu(gfx_info->v24.gc_wave_size);
+			adev->gfx.cu_info.max_waves_per_simd = le16_to_cpu(gfx_info->v24.gc_max_waves_per_simd);
+			adev->gfx.cu_info.max_scratch_slots_per_cu = gfx_info->v24.gc_max_scratch_slots_per_cu;
+			adev->gfx.cu_info.lds_size = le16_to_cpu(gfx_info->v24.gc_lds_size);
+			return 0;
+		default:
+			return -EINVAL;
+		}
+
+	}
+	return -EINVAL;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
index 7689c961c4ef..20f158fd3b76 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
@@ -30,5 +30,6 @@ int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_vram_width(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_vram_type(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev);
+int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 1ae5ae8c45a4..1bcb2b247335 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -550,7 +550,7 @@ static int amdgpu_atpx_init(void)
  * look up whether we are the integrated or discrete GPU (all asics).
  * Returns the client id.
  */
-static int amdgpu_atpx_get_client_id(struct pci_dev *pdev)
+static enum vga_switcheroo_client_id amdgpu_atpx_get_client_id(struct pci_dev *pdev)
 {
 	if (amdgpu_atpx_priv.dhandle == ACPI_HANDLE(&pdev->dev))
 		return VGA_SWITCHEROO_IGD;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 02b849be083b..19cfff31f2e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -75,13 +75,20 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 {
 	struct amdgpu_bo *dobj = NULL;
 	struct amdgpu_bo *sobj = NULL;
+	struct amdgpu_bo_param bp;
 	uint64_t saddr, daddr;
 	int r, n;
 	int time;
 
+	memset(&bp, 0, sizeof(bp));
+	bp.size = size;
+	bp.byte_align = PAGE_SIZE;
+	bp.domain = sdomain;
+	bp.flags = 0;
+	bp.type = ttm_bo_type_kernel;
+	bp.resv = NULL;
 	n = AMDGPU_BENCHMARK_ITERATIONS;
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE,sdomain, 0,
-			     ttm_bo_type_kernel, NULL, &sobj);
+	r = amdgpu_bo_create(adev, &bp, &sobj);
 	if (r) {
 		goto out_cleanup;
 	}
@@ -93,8 +100,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	if (r) {
 		goto out_cleanup;
 	}
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, ddomain, 0,
-			     ttm_bo_type_kernel, NULL, &dobj);
+	bp.domain = ddomain;
+	r = amdgpu_bo_create(adev, &bp, &dobj);
 	if (r) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 71a57b2f7f04..e950730f1933 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -23,7 +23,6 @@
  */
 #include <linux/list.h>
 #include <linux/slab.h>
-#include <linux/pci.h>
 #include <drm/drmP.h>
 #include <linux/firmware.h>
 #include <drm/amdgpu_drm.h>
@@ -109,121 +108,6 @@ static void amdgpu_cgs_write_ind_register(struct cgs_device *cgs_device,
 	WARN(1, "Invalid indirect register space");
 }
 
-static int amdgpu_cgs_get_pci_resource(struct cgs_device *cgs_device,
-				       enum cgs_resource_type resource_type,
-				       uint64_t size,
-				       uint64_t offset,
-				       uint64_t *resource_base)
-{
-	CGS_FUNC_ADEV;
-
-	if (resource_base == NULL)
-		return -EINVAL;
-
-	switch (resource_type) {
-	case CGS_RESOURCE_TYPE_MMIO:
-		if (adev->rmmio_size == 0)
-			return -ENOENT;
-		if ((offset + size) > adev->rmmio_size)
-			return -EINVAL;
-		*resource_base = adev->rmmio_base;
-		return 0;
-	case CGS_RESOURCE_TYPE_DOORBELL:
-		if (adev->doorbell.size == 0)
-			return -ENOENT;
-		if ((offset + size) > adev->doorbell.size)
-			return -EINVAL;
-		*resource_base = adev->doorbell.base;
-		return 0;
-	case CGS_RESOURCE_TYPE_FB:
-	case CGS_RESOURCE_TYPE_IO:
-	case CGS_RESOURCE_TYPE_ROM:
-	default:
-		return -EINVAL;
-	}
-}
-
-static const void *amdgpu_cgs_atom_get_data_table(struct cgs_device *cgs_device,
-						  unsigned table, uint16_t *size,
-						  uint8_t *frev, uint8_t *crev)
-{
-	CGS_FUNC_ADEV;
-	uint16_t data_start;
-
-	if (amdgpu_atom_parse_data_header(
-		    adev->mode_info.atom_context, table, size,
-		    frev, crev, &data_start))
-		return (uint8_t*)adev->mode_info.atom_context->bios +
-			data_start;
-
-	return NULL;
-}
-
-static int amdgpu_cgs_atom_get_cmd_table_revs(struct cgs_device *cgs_device, unsigned table,
-					      uint8_t *frev, uint8_t *crev)
-{
-	CGS_FUNC_ADEV;
-
-	if (amdgpu_atom_parse_cmd_header(
-		    adev->mode_info.atom_context, table,
-		    frev, crev))
-		return 0;
-
-	return -EINVAL;
-}
-
-static int amdgpu_cgs_atom_exec_cmd_table(struct cgs_device *cgs_device, unsigned table,
-					  void *args)
-{
-	CGS_FUNC_ADEV;
-
-	return amdgpu_atom_execute_table(
-		adev->mode_info.atom_context, table, args);
-}
-
-static int amdgpu_cgs_set_clockgating_state(struct cgs_device *cgs_device,
-				  enum amd_ip_block_type block_type,
-				  enum amd_clockgating_state state)
-{
-	CGS_FUNC_ADEV;
-	int i, r = -1;
-
-	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_blocks[i].status.valid)
-			continue;
-
-		if (adev->ip_blocks[i].version->type == block_type) {
-			r = adev->ip_blocks[i].version->funcs->set_clockgating_state(
-								(void *)adev,
-									state);
-			break;
-		}
-	}
-	return r;
-}
-
-static int amdgpu_cgs_set_powergating_state(struct cgs_device *cgs_device,
-				  enum amd_ip_block_type block_type,
-				  enum amd_powergating_state state)
-{
-	CGS_FUNC_ADEV;
-	int i, r = -1;
-
-	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_blocks[i].status.valid)
-			continue;
-
-		if (adev->ip_blocks[i].version->type == block_type) {
-			r = adev->ip_blocks[i].version->funcs->set_powergating_state(
-								(void *)adev,
-									state);
-			break;
-		}
-	}
-	return r;
-}
-
-
 static uint32_t fw_type_convert(struct cgs_device *cgs_device, uint32_t fw_type)
 {
 	CGS_FUNC_ADEV;
@@ -271,18 +155,6 @@ static uint32_t fw_type_convert(struct cgs_device *cgs_device, uint32_t fw_type)
 	return result;
 }
 
-static int amdgpu_cgs_rel_firmware(struct cgs_device *cgs_device, enum cgs_ucode_id type)
-{
-	CGS_FUNC_ADEV;
-	if ((CGS_UCODE_ID_SMU == type) || (CGS_UCODE_ID_SMU_SK == type)) {
-		release_firmware(adev->pm.fw);
-		adev->pm.fw = NULL;
-		return 0;
-	}
-	/* cannot release other firmware because they are not created by cgs */
-	return -EINVAL;
-}
-
 static uint16_t amdgpu_get_firmware_version(struct cgs_device *cgs_device,
 					enum cgs_ucode_id type)
 {
@@ -326,34 +198,6 @@ static uint16_t amdgpu_get_firmware_version(struct cgs_device *cgs_device,
 	return fw_version;
 }
 
-static int amdgpu_cgs_enter_safe_mode(struct cgs_device *cgs_device,
-					bool en)
-{
-	CGS_FUNC_ADEV;
-
-	if (adev->gfx.rlc.funcs->enter_safe_mode == NULL ||
-		adev->gfx.rlc.funcs->exit_safe_mode == NULL)
-		return 0;
-
-	if (en)
-		adev->gfx.rlc.funcs->enter_safe_mode(adev);
-	else
-		adev->gfx.rlc.funcs->exit_safe_mode(adev);
-
-	return 0;
-}
-
-static void amdgpu_cgs_lock_grbm_idx(struct cgs_device *cgs_device,
-					bool lock)
-{
-	CGS_FUNC_ADEV;
-
-	if (lock)
-		mutex_lock(&adev->grbm_idx_mutex);
-	else
-		mutex_unlock(&adev->grbm_idx_mutex);
-}
-
 static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 					enum cgs_ucode_id type,
 					struct cgs_firmware_info *info)
@@ -541,6 +385,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 			case CHIP_POLARIS12:
 				strcpy(fw_name, "amdgpu/polaris12_smc.bin");
 				break;
+			case CHIP_VEGAM:
+				strcpy(fw_name, "amdgpu/vegam_smc.bin");
+				break;
 			case CHIP_VEGA10:
 				if ((adev->pdev->device == 0x687f) &&
 					((adev->pdev->revision == 0xc0) ||
@@ -553,6 +400,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 			case CHIP_VEGA12:
 				strcpy(fw_name, "amdgpu/vega12_smc.bin");
 				break;
+			case CHIP_VEGA20:
+				strcpy(fw_name, "amdgpu/vega20_smc.bin");
+				break;
 			default:
 				DRM_ERROR("SMC firmware not supported\n");
 				return -EINVAL;
@@ -598,97 +448,12 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 	return 0;
 }
 
-static int amdgpu_cgs_is_virtualization_enabled(void *cgs_device)
-{
-	CGS_FUNC_ADEV;
-	return amdgpu_sriov_vf(adev);
-}
-
-static int amdgpu_cgs_get_active_displays_info(struct cgs_device *cgs_device,
-					  struct cgs_display_info *info)
-{
-	CGS_FUNC_ADEV;
-	struct cgs_mode_info *mode_info;
-
-	if (info == NULL)
-		return -EINVAL;
-
-	mode_info = info->mode_info;
-	if (mode_info)
-		/* if the displays are off, vblank time is max */
-		mode_info->vblank_time_us = 0xffffffff;
-
-	if (!amdgpu_device_has_dc_support(adev)) {
-		struct amdgpu_crtc *amdgpu_crtc;
-		struct drm_device *ddev = adev->ddev;
-		struct drm_crtc *crtc;
-		uint32_t line_time_us, vblank_lines;
-
-		if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) {
-			list_for_each_entry(crtc,
-					&ddev->mode_config.crtc_list, head) {
-				amdgpu_crtc = to_amdgpu_crtc(crtc);
-				if (crtc->enabled) {
-					info->active_display_mask |= (1 << amdgpu_crtc->crtc_id);
-					info->display_count++;
-				}
-				if (mode_info != NULL &&
-					crtc->enabled && amdgpu_crtc->enabled &&
-					amdgpu_crtc->hw_mode.clock) {
-					line_time_us = (amdgpu_crtc->hw_mode.crtc_htotal * 1000) /
-								amdgpu_crtc->hw_mode.clock;
-					vblank_lines = amdgpu_crtc->hw_mode.crtc_vblank_end -
-								amdgpu_crtc->hw_mode.crtc_vdisplay +
-								(amdgpu_crtc->v_border * 2);
-					mode_info->vblank_time_us = vblank_lines * line_time_us;
-					mode_info->refresh_rate = drm_mode_vrefresh(&amdgpu_crtc->hw_mode);
-					/* we have issues with mclk switching with refresh rates
-					 * over 120 hz on the non-DC code.
-					 */
-					if (mode_info->refresh_rate > 120)
-						mode_info->vblank_time_us = 0;
-					mode_info = NULL;
-				}
-			}
-		}
-	} else {
-		info->display_count = adev->pm.pm_display_cfg.num_display;
-		if (mode_info != NULL) {
-			mode_info->vblank_time_us = adev->pm.pm_display_cfg.min_vblank_time;
-			mode_info->refresh_rate = adev->pm.pm_display_cfg.vrefresh;
-		}
-	}
-	return 0;
-}
-
-
-static int amdgpu_cgs_notify_dpm_enabled(struct cgs_device *cgs_device, bool enabled)
-{
-	CGS_FUNC_ADEV;
-
-	adev->pm.dpm_enabled = enabled;
-
-	return 0;
-}
-
 static const struct cgs_ops amdgpu_cgs_ops = {
 	.read_register = amdgpu_cgs_read_register,
 	.write_register = amdgpu_cgs_write_register,
 	.read_ind_register = amdgpu_cgs_read_ind_register,
 	.write_ind_register = amdgpu_cgs_write_ind_register,
-	.get_pci_resource = amdgpu_cgs_get_pci_resource,
-	.atom_get_data_table = amdgpu_cgs_atom_get_data_table,
-	.atom_get_cmd_table_revs = amdgpu_cgs_atom_get_cmd_table_revs,
-	.atom_exec_cmd_table = amdgpu_cgs_atom_exec_cmd_table,
 	.get_firmware_info = amdgpu_cgs_get_firmware_info,
-	.rel_firmware = amdgpu_cgs_rel_firmware,
-	.set_powergating_state = amdgpu_cgs_set_powergating_state,
-	.set_clockgating_state = amdgpu_cgs_set_clockgating_state,
-	.get_active_displays_info = amdgpu_cgs_get_active_displays_info,
-	.notify_dpm_enabled = amdgpu_cgs_notify_dpm_enabled,
-	.is_virtualization_enabled = amdgpu_cgs_is_virtualization_enabled,
-	.enter_safe_mode = amdgpu_cgs_enter_safe_mode,
-	.lock_grbm_idx = amdgpu_cgs_lock_grbm_idx,
 };
 
 struct cgs_device *amdgpu_cgs_create_device(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 96501ff0e55b..8e66851eb427 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -691,7 +691,7 @@ static int amdgpu_connector_lvds_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static int amdgpu_connector_lvds_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status amdgpu_connector_lvds_mode_valid(struct drm_connector *connector,
 					     struct drm_display_mode *mode)
 {
 	struct drm_encoder *encoder = amdgpu_connector_best_single_encoder(connector);
@@ -843,7 +843,7 @@ static int amdgpu_connector_vga_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static int amdgpu_connector_vga_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status amdgpu_connector_vga_mode_valid(struct drm_connector *connector,
 					    struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
@@ -1172,7 +1172,7 @@ static void amdgpu_connector_dvi_force(struct drm_connector *connector)
 		amdgpu_connector->use_digital = true;
 }
 
-static int amdgpu_connector_dvi_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status amdgpu_connector_dvi_mode_valid(struct drm_connector *connector,
 					    struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
@@ -1448,7 +1448,7 @@ out:
 	return ret;
 }
 
-static int amdgpu_connector_dp_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status amdgpu_connector_dp_mode_valid(struct drm_connector *connector,
 					   struct drm_display_mode *mode)
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index dc34b50e6b29..9c1d491d742e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -382,8 +382,7 @@ retry:
 
 	p->bytes_moved += ctx.bytes_moved;
 	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
-	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
-	    bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT)
+	    amdgpu_bo_in_cpu_visible_vram(bo))
 		p->bytes_moved_vis += ctx.bytes_moved;
 
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
@@ -411,7 +410,6 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 		struct amdgpu_bo_list_entry *candidate = p->evictable;
 		struct amdgpu_bo *bo = candidate->robj;
 		struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-		u64 initial_bytes_moved, bytes_moved;
 		bool update_bytes_moved_vis;
 		uint32_t other;
 
@@ -435,18 +433,14 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 			continue;
 
 		/* Good we can try to move this BO somewhere else */
-		amdgpu_ttm_placement_from_domain(bo, other);
 		update_bytes_moved_vis =
 			adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
-			bo->tbo.mem.mem_type == TTM_PL_VRAM &&
-			bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT;
-		initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
+			amdgpu_bo_in_cpu_visible_vram(bo);
+		amdgpu_ttm_placement_from_domain(bo, other);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
-		bytes_moved = atomic64_read(&adev->num_bytes_moved) -
-			initial_bytes_moved;
-		p->bytes_moved += bytes_moved;
+		p->bytes_moved += ctx.bytes_moved;
 		if (update_bytes_moved_vis)
-			p->bytes_moved_vis += bytes_moved;
+			p->bytes_moved_vis += ctx.bytes_moved;
 
 		if (unlikely(r))
 			break;
@@ -536,7 +530,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	if (p->bo_list) {
 		amdgpu_bo_list_get_list(p->bo_list, &p->validated);
 		if (p->bo_list->first_userptr != p->bo_list->num_entries)
-			p->mn = amdgpu_mn_get(p->adev);
+			p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);
 	}
 
 	INIT_LIST_HEAD(&duplicates);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 09d35051fdd6..c5bb36275e93 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -91,7 +91,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 			continue;
 
 		r = drm_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
-					  rq, amdgpu_sched_jobs, &ctx->guilty);
+					  rq, &ctx->guilty);
 		if (r)
 			goto failed;
 	}
@@ -111,8 +111,9 @@ failed:
 	return r;
 }
 
-static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
+static void amdgpu_ctx_fini(struct kref *ref)
 {
+	struct amdgpu_ctx *ctx = container_of(ref, struct amdgpu_ctx, refcount);
 	struct amdgpu_device *adev = ctx->adev;
 	unsigned i, j;
 
@@ -125,13 +126,11 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
 	kfree(ctx->fences);
 	ctx->fences = NULL;
 
-	for (i = 0; i < adev->num_rings; i++)
-		drm_sched_entity_fini(&adev->rings[i]->sched,
-				      &ctx->rings[i].entity);
-
 	amdgpu_queue_mgr_fini(adev, &ctx->queue_mgr);
 
 	mutex_destroy(&ctx->lock);
+
+	kfree(ctx);
 }
 
 static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
@@ -170,12 +169,20 @@ static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
 static void amdgpu_ctx_do_release(struct kref *ref)
 {
 	struct amdgpu_ctx *ctx;
+	u32 i;
 
 	ctx = container_of(ref, struct amdgpu_ctx, refcount);
 
-	amdgpu_ctx_fini(ctx);
+	for (i = 0; i < ctx->adev->num_rings; i++) {
 
-	kfree(ctx);
+		if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
+			continue;
+
+		drm_sched_entity_fini(&ctx->adev->rings[i]->sched,
+			&ctx->rings[i].entity);
+	}
+
+	amdgpu_ctx_fini(ref);
 }
 
 static int amdgpu_ctx_free(struct amdgpu_fpriv *fpriv, uint32_t id)
@@ -419,9 +426,11 @@ int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id)
 
 	if (other) {
 		signed long r;
-		r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT);
+		r = dma_fence_wait(other, true);
 		if (r < 0) {
-			DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+			if (r != -ERESTARTSYS)
+				DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+
 			return r;
 		}
 	}
@@ -435,16 +444,72 @@ void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr)
 	idr_init(&mgr->ctx_handles);
 }
 
+void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
+{
+	struct amdgpu_ctx *ctx;
+	struct idr *idp;
+	uint32_t id, i;
+
+	idp = &mgr->ctx_handles;
+
+	idr_for_each_entry(idp, ctx, id) {
+
+		if (!ctx->adev)
+			return;
+
+		for (i = 0; i < ctx->adev->num_rings; i++) {
+
+			if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
+				continue;
+
+			if (kref_read(&ctx->refcount) == 1)
+				drm_sched_entity_do_release(&ctx->adev->rings[i]->sched,
+						  &ctx->rings[i].entity);
+			else
+				DRM_ERROR("ctx %p is still alive\n", ctx);
+		}
+	}
+}
+
+void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr)
+{
+	struct amdgpu_ctx *ctx;
+	struct idr *idp;
+	uint32_t id, i;
+
+	idp = &mgr->ctx_handles;
+
+	idr_for_each_entry(idp, ctx, id) {
+
+		if (!ctx->adev)
+			return;
+
+		for (i = 0; i < ctx->adev->num_rings; i++) {
+
+			if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
+				continue;
+
+			if (kref_read(&ctx->refcount) == 1)
+				drm_sched_entity_cleanup(&ctx->adev->rings[i]->sched,
+					&ctx->rings[i].entity);
+			else
+				DRM_ERROR("ctx %p is still alive\n", ctx);
+		}
+	}
+}
+
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
 {
 	struct amdgpu_ctx *ctx;
 	struct idr *idp;
 	uint32_t id;
 
+	amdgpu_ctx_mgr_entity_cleanup(mgr);
+
 	idp = &mgr->ctx_handles;
 
 	idr_for_each_entry(idp, ctx, id) {
-		if (kref_put(&ctx->refcount, amdgpu_ctx_do_release) != 1)
+		if (kref_put(&ctx->refcount, amdgpu_ctx_fini) != 1)
 			DRM_ERROR("ctx %p is still alive\n", ctx);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 448d69fe3756..f5fb93795a69 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -28,8 +28,13 @@
 #include <linux/debugfs.h>
 #include "amdgpu.h"
 
-/*
- * Debugfs
+/**
+ * amdgpu_debugfs_add_files - Add simple debugfs entries
+ *
+ * @adev:  Device to attach debugfs entries to
+ * @files:  Array of function callbacks that respond to reads
+ * @nfiles: Number of callbacks to register
+ *
  */
 int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
 			     const struct drm_info_list *files,
@@ -64,7 +69,33 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
 
 #if defined(CONFIG_DEBUG_FS)
 
-
+/**
+ * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes
+ *
+ * @read: True if reading
+ * @f: open file handle
+ * @buf: User buffer to write/read to
+ * @size: Number of bytes to write/read
+ * @pos:  Offset to seek to
+ *
+ * This debugfs entry has special meaning on the offset being sought.
+ * Various bits have different meanings:
+ *
+ * Bit 62:  Indicates a GRBM bank switch is needed
+ * Bit 61:  Indicates a SRBM bank switch is needed (implies bit 62 is
+ * 			zero)
+ * Bits 24..33: The SE or ME selector if needed
+ * Bits 34..43: The SH (or SA) or PIPE selector if needed
+ * Bits 44..53: The INSTANCE (or CU/WGP) or QUEUE selector if needed
+ *
+ * Bit 23:  Indicates that the PM power gating lock should be held
+ * 			This is necessary to read registers that might be
+ * 			unreliable during a power gating transistion.
+ *
+ * The lower bits are the BYTE offset of the register to read.  This
+ * allows reading multiple registers in a single call and having
+ * the returned size reflect that.
+ */
 static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 		char __user *buf, size_t size, loff_t *pos)
 {
@@ -164,19 +195,37 @@ end:
 	return result;
 }
 
-
+/**
+ * amdgpu_debugfs_regs_read - Callback for reading MMIO registers
+ */
 static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
 	return amdgpu_debugfs_process_reg_op(true, f, buf, size, pos);
 }
 
+/**
+ * amdgpu_debugfs_regs_write - Callback for writing MMIO registers
+ */
 static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
 					 size_t size, loff_t *pos)
 {
 	return amdgpu_debugfs_process_reg_op(false, f, (char __user *)buf, size, pos);
 }
 
+
+/**
+ * amdgpu_debugfs_regs_pcie_read - Read from a PCIE register
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ *
+ * The lower bits are the BYTE offset of the register to read.  This
+ * allows reading multiple registers in a single call and having
+ * the returned size reflect that.
+ */
 static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -204,6 +253,18 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/**
+ * amdgpu_debugfs_regs_pcie_write - Write to a PCIE register
+ *
+ * @f: open file handle
+ * @buf: User buffer to write data from
+ * @size: Number of bytes to write
+ * @pos:  Offset to seek to
+ *
+ * The lower bits are the BYTE offset of the register to write.  This
+ * allows writing multiple registers in a single call and having
+ * the returned size reflect that.
+ */
 static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user *buf,
 					 size_t size, loff_t *pos)
 {
@@ -232,6 +293,18 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 	return result;
 }
 
+/**
+ * amdgpu_debugfs_regs_didt_read - Read from a DIDT register
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ *
+ * The lower bits are the BYTE offset of the register to read.  This
+ * allows reading multiple registers in a single call and having
+ * the returned size reflect that.
+ */
 static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -259,6 +332,18 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/**
+ * amdgpu_debugfs_regs_didt_write - Write to a DIDT register
+ *
+ * @f: open file handle
+ * @buf: User buffer to write data from
+ * @size: Number of bytes to write
+ * @pos:  Offset to seek to
+ *
+ * The lower bits are the BYTE offset of the register to write.  This
+ * allows writing multiple registers in a single call and having
+ * the returned size reflect that.
+ */
 static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user *buf,
 					 size_t size, loff_t *pos)
 {
@@ -287,6 +372,18 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 	return result;
 }
 
+/**
+ * amdgpu_debugfs_regs_smc_read - Read from a SMC register
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ *
+ * The lower bits are the BYTE offset of the register to read.  This
+ * allows reading multiple registers in a single call and having
+ * the returned size reflect that.
+ */
 static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -314,6 +411,18 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/**
+ * amdgpu_debugfs_regs_smc_write - Write to a SMC register
+ *
+ * @f: open file handle
+ * @buf: User buffer to write data from
+ * @size: Number of bytes to write
+ * @pos:  Offset to seek to
+ *
+ * The lower bits are the BYTE offset of the register to write.  This
+ * allows writing multiple registers in a single call and having
+ * the returned size reflect that.
+ */
 static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *buf,
 					 size_t size, loff_t *pos)
 {
@@ -342,6 +451,20 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 	return result;
 }
 
+/**
+ * amdgpu_debugfs_gca_config_read - Read from gfx config data
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ *
+ * This file is used to access configuration data in a somewhat
+ * stable fashion.  The format is a series of DWORDs with the first
+ * indicating which revision it is.  New content is appended to the
+ * end so that older software can still read the data.
+ */
+
 static ssize_t amdgpu_debugfs_gca_config_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -418,6 +541,19 @@ static ssize_t amdgpu_debugfs_gca_config_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/**
+ * amdgpu_debugfs_sensor_read - Read from the powerplay sensors
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ *
+ * The offset is treated as the BYTE address of one of the sensors
+ * enumerated in amd/include/kgd_pp_interface.h under the
+ * 'amd_pp_sensors' enumeration.  For instance to read the UVD VCLK
+ * you would use the offset 3 * 4 = 12.
+ */
 static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -428,7 +564,7 @@ static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
 	if (size & 3 || *pos & 0x3)
 		return -EINVAL;
 
-	if (amdgpu_dpm == 0)
+	if (!adev->pm.dpm_enabled)
 		return -EINVAL;
 
 	/* convert offset to sensor number */
@@ -457,6 +593,27 @@ static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
 	return !r ? outsize : r;
 }
 
+/** amdgpu_debugfs_wave_read - Read WAVE STATUS data
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ *
+ * The offset being sought changes which wave that the status data
+ * will be returned for.  The bits are used as follows:
+ *
+ * Bits 0..6: 	Byte offset into data
+ * Bits 7..14:	SE selector
+ * Bits 15..22:	SH/SA selector
+ * Bits 23..30: CU/{WGP+SIMD} selector
+ * Bits 31..36: WAVE ID selector
+ * Bits 37..44: SIMD ID selector
+ *
+ * The returned data begins with one DWORD of version information
+ * Followed by WAVE STATUS registers relevant to the GFX IP version
+ * being used.  See gfx_v8_0_read_wave_data() for an example output.
+ */
 static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -507,6 +664,28 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/** amdgpu_debugfs_gpr_read - Read wave gprs
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ *
+ * The offset being sought changes which wave that the status data
+ * will be returned for.  The bits are used as follows:
+ *
+ * Bits 0..11:	Byte offset into data
+ * Bits 12..19:	SE selector
+ * Bits 20..27:	SH/SA selector
+ * Bits 28..35: CU/{WGP+SIMD} selector
+ * Bits 36..43: WAVE ID selector
+ * Bits 37..44: SIMD ID selector
+ * Bits 52..59: Thread selector
+ * Bits 60..61: Bank selector (VGPR=0,SGPR=1)
+ *
+ * The return data comes from the SGPR or VGPR register bank for
+ * the selected operational unit.
+ */
 static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -637,6 +816,12 @@ static const char *debugfs_regs_names[] = {
 	"amdgpu_gpr",
 };
 
+/**
+ * amdgpu_debugfs_regs_init -	Initialize debugfs entries that provide
+ * 								register access.
+ *
+ * @adev: The device to attach the debugfs entries to
+ */
 int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
 {
 	struct drm_minor *minor = adev->ddev->primary;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 34af664b9f93..290e279abf0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -83,8 +83,10 @@ static const char *amdgpu_asic_name[] = {
 	"POLARIS10",
 	"POLARIS11",
 	"POLARIS12",
+	"VEGAM",
 	"VEGA10",
 	"VEGA12",
+	"VEGA20",
 	"RAVEN",
 	"LAST",
 };
@@ -690,6 +692,8 @@ void amdgpu_device_gart_location(struct amdgpu_device *adev,
 {
 	u64 size_af, size_bf;
 
+	mc->gart_size += adev->pm.smu_prv_buffer_size;
+
 	size_af = adev->gmc.mc_mask - mc->vram_end;
 	size_bf = mc->vram_start;
 	if (size_bf > size_af) {
@@ -907,6 +911,46 @@ static void amdgpu_device_check_vm_size(struct amdgpu_device *adev)
 	}
 }
 
+static void amdgpu_device_check_smu_prv_buffer_size(struct amdgpu_device *adev)
+{
+	struct sysinfo si;
+	bool is_os_64 = (sizeof(void *) == 8) ? true : false;
+	uint64_t total_memory;
+	uint64_t dram_size_seven_GB = 0x1B8000000;
+	uint64_t dram_size_three_GB = 0xB8000000;
+
+	if (amdgpu_smu_memory_pool_size == 0)
+		return;
+
+	if (!is_os_64) {
+		DRM_WARN("Not 64-bit OS, feature not supported\n");
+		goto def_value;
+	}
+	si_meminfo(&si);
+	total_memory = (uint64_t)si.totalram * si.mem_unit;
+
+	if ((amdgpu_smu_memory_pool_size == 1) ||
+		(amdgpu_smu_memory_pool_size == 2)) {
+		if (total_memory < dram_size_three_GB)
+			goto def_value1;
+	} else if ((amdgpu_smu_memory_pool_size == 4) ||
+		(amdgpu_smu_memory_pool_size == 8)) {
+		if (total_memory < dram_size_seven_GB)
+			goto def_value1;
+	} else {
+		DRM_WARN("Smu memory pool size not supported\n");
+		goto def_value;
+	}
+	adev->pm.smu_prv_buffer_size = amdgpu_smu_memory_pool_size << 28;
+
+	return;
+
+def_value1:
+	DRM_WARN("No enough system memory\n");
+def_value:
+	adev->pm.smu_prv_buffer_size = 0;
+}
+
 /**
  * amdgpu_device_check_arguments - validate module params
  *
@@ -948,6 +992,8 @@ static void amdgpu_device_check_arguments(struct amdgpu_device *adev)
 		amdgpu_vm_fragment_size = -1;
 	}
 
+	amdgpu_device_check_smu_prv_buffer_size(adev);
+
 	amdgpu_device_check_vm_size(adev);
 
 	amdgpu_device_check_block_size(adev);
@@ -1039,10 +1085,11 @@ static const struct vga_switcheroo_client_ops amdgpu_switcheroo_ops = {
  * the hardware IP specified.
  * Returns the error code from the last instance.
  */
-int amdgpu_device_ip_set_clockgating_state(struct amdgpu_device *adev,
+int amdgpu_device_ip_set_clockgating_state(void *dev,
 					   enum amd_ip_block_type block_type,
 					   enum amd_clockgating_state state)
 {
+	struct amdgpu_device *adev = dev;
 	int i, r = 0;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
@@ -1072,10 +1119,11 @@ int amdgpu_device_ip_set_clockgating_state(struct amdgpu_device *adev,
  * the hardware IP specified.
  * Returns the error code from the last instance.
  */
-int amdgpu_device_ip_set_powergating_state(struct amdgpu_device *adev,
+int amdgpu_device_ip_set_powergating_state(void *dev,
 					   enum amd_ip_block_type block_type,
 					   enum amd_powergating_state state)
 {
+	struct amdgpu_device *adev = dev;
 	int i, r = 0;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
@@ -1320,9 +1368,10 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 	case CHIP_TOPAZ:
 	case CHIP_TONGA:
 	case CHIP_FIJI:
-	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
 #ifdef CONFIG_DRM_AMDGPU_SI
@@ -1339,6 +1388,7 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 	case CHIP_KABINI:
 	case CHIP_MULLINS:
 #endif
+	case CHIP_VEGA20:
 	default:
 		return 0;
 	case CHIP_VEGA10:
@@ -1428,9 +1478,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	case CHIP_TOPAZ:
 	case CHIP_TONGA:
 	case CHIP_FIJI:
-	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
 		if (adev->asic_type == CHIP_CARRIZO || adev->asic_type == CHIP_STONEY)
@@ -1472,6 +1523,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 #endif
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 	case CHIP_RAVEN:
 		if (adev->asic_type == CHIP_RAVEN)
 			adev->family = AMDGPU_FAMILY_RV;
@@ -1499,6 +1551,8 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 			return -EAGAIN;
 	}
 
+	adev->powerplay.pp_feature = amdgpu_pp_feature_mask;
+
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if ((amdgpu_ip_block_mask & (1 << i)) == 0) {
 			DRM_ERROR("disabled ip block: %d <%s>\n",
@@ -1654,12 +1708,17 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 	if (amdgpu_emu_mode == 1)
 		return 0;
 
+	r = amdgpu_ib_ring_tests(adev);
+	if (r)
+		DRM_ERROR("ib ring test failed (%d).\n", r);
+
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
 		/* skip CG for VCE/UVD, it's handled specially */
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN &&
 		    adev->ip_blocks[i].version->funcs->set_clockgating_state) {
 			/* enable clockgating to save power */
 			r = adev->ip_blocks[i].version->funcs->set_clockgating_state((void *)adev,
@@ -1704,8 +1763,8 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 		}
 	}
 
-	mod_delayed_work(system_wq, &adev->late_init_work,
-			msecs_to_jiffies(AMDGPU_RESUME_MS));
+	queue_delayed_work(system_wq, &adev->late_init_work,
+			   msecs_to_jiffies(AMDGPU_RESUME_MS));
 
 	amdgpu_device_fill_reset_magic(adev);
 
@@ -1759,6 +1818,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 			adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
+			adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN &&
 			adev->ip_blocks[i].version->funcs->set_clockgating_state) {
 			/* ungate blocks before hw fini so that we can shutdown the blocks safely */
 			r = adev->ip_blocks[i].version->funcs->set_clockgating_state((void *)adev,
@@ -1850,6 +1910,12 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_request_full_gpu(adev, false);
 
+	/* ungate SMC block powergating */
+	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK)
+		amdgpu_device_ip_set_powergating_state(adev,
+						       AMD_IP_BLOCK_TYPE_SMC,
+						       AMD_CG_STATE_UNGATE);
+
 	/* ungate SMC block first */
 	r = amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_SMC,
 						   AMD_CG_STATE_UNGATE);
@@ -2086,16 +2152,15 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_MULLINS:
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
-	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 	case CHIP_TONGA:
 	case CHIP_FIJI:
-#if defined(CONFIG_DRM_AMD_DC_PRE_VEGA)
-		return amdgpu_dc != 0;
-#endif
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 	case CHIP_RAVEN:
 #endif
@@ -2375,10 +2440,6 @@ fence_driver_init:
 		goto failed;
 	}
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
-
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_init_data_exchange(adev);
 
@@ -2539,7 +2600,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	/* unpin the front buffers and cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-		struct amdgpu_framebuffer *rfb = to_amdgpu_framebuffer(crtc->primary->fb);
+		struct drm_framebuffer *fb = crtc->primary->fb;
 		struct amdgpu_bo *robj;
 
 		if (amdgpu_crtc->cursor_bo) {
@@ -2551,10 +2612,10 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 			}
 		}
 
-		if (rfb == NULL || rfb->obj == NULL) {
+		if (fb == NULL || fb->obj[0] == NULL) {
 			continue;
 		}
-		robj = gem_to_amdgpu_bo(rfb->obj);
+		robj = gem_to_amdgpu_bo(fb->obj[0]);
 		/* don't unpin kernel fb objects */
 		if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
 			r = amdgpu_bo_reserve(robj, true);
@@ -2640,11 +2701,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	}
 	amdgpu_fence_driver_resume(adev);
 
-	if (resume) {
-		r = amdgpu_ib_ring_tests(adev);
-		if (r)
-			DRM_ERROR("ib ring test failed (%d).\n", r);
-	}
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
@@ -2736,6 +2792,9 @@ static bool amdgpu_device_ip_check_soft_reset(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		return true;
 
+	if (amdgpu_asic_need_full_reset(adev))
+		return true;
+
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -2792,6 +2851,9 @@ static bool amdgpu_device_ip_need_full_reset(struct amdgpu_device *adev)
 {
 	int i;
 
+	if (amdgpu_asic_need_full_reset(adev))
+		return true;
+
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -3087,20 +3149,19 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 
 	/* now we are okay to resume SMC/CP/SDMA */
 	r = amdgpu_device_ip_reinit_late_sriov(adev);
-	amdgpu_virt_release_full_gpu(adev, true);
 	if (r)
 		goto error;
 
 	amdgpu_irq_gpu_reset_resume_helper(adev);
 	r = amdgpu_ib_ring_tests(adev);
 
+error:
+	amdgpu_virt_release_full_gpu(adev, true);
 	if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
 		atomic_inc(&adev->vram_lost_counter);
 		r = amdgpu_device_handle_vram_lost(adev);
 	}
 
-error:
-
 	return r;
 }
 
@@ -3117,7 +3178,6 @@ error:
 int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			      struct amdgpu_job *job, bool force)
 {
-	struct drm_atomic_state *state = NULL;
 	int i, r, resched;
 
 	if (!force && !amdgpu_device_ip_check_soft_reset(adev)) {
@@ -3140,10 +3200,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
 
-	/* store modesetting */
-	if (amdgpu_device_has_dc_support(adev))
-		state = drm_atomic_helper_suspend(adev->ddev);
-
 	/* block all schedulers and reset given job's ring */
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -3183,10 +3239,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		kthread_unpark(ring->sched.thread);
 	}
 
-	if (amdgpu_device_has_dc_support(adev)) {
-		if (drm_atomic_helper_resume(adev->ddev, state))
-			dev_info(adev->dev, "drm resume failed:%d\n", r);
-	} else {
+	if (!amdgpu_device_has_dc_support(adev)) {
 		drm_helper_resume_force_mode(adev->ddev);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 93f700ab1bfb..76ee8e04ff11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -35,6 +35,7 @@
 #include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_fb_helper.h>
 
 static void amdgpu_display_flip_callback(struct dma_fence *f,
@@ -151,8 +152,6 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_framebuffer *old_amdgpu_fb;
-	struct amdgpu_framebuffer *new_amdgpu_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_flip_work *work;
 	struct amdgpu_bo *new_abo;
@@ -174,15 +173,13 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 	work->async = (page_flip_flags & DRM_MODE_PAGE_FLIP_ASYNC) != 0;
 
 	/* schedule unpin of the old buffer */
-	old_amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
-	obj = old_amdgpu_fb->obj;
+	obj = crtc->primary->fb->obj[0];
 
 	/* take a reference to the old object */
 	work->old_abo = gem_to_amdgpu_bo(obj);
 	amdgpu_bo_ref(work->old_abo);
 
-	new_amdgpu_fb = to_amdgpu_framebuffer(fb);
-	obj = new_amdgpu_fb->obj;
+	obj = fb->obj[0];
 	new_abo = gem_to_amdgpu_bo(obj);
 
 	/* pin the new buffer */
@@ -192,7 +189,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 		goto cleanup;
 	}
 
-	r = amdgpu_bo_pin(new_abo, amdgpu_display_framebuffer_domains(adev), &base);
+	r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev), &base);
 	if (unlikely(r != 0)) {
 		DRM_ERROR("failed to pin new abo buffer before flip\n");
 		goto unreserve;
@@ -482,31 +479,12 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector,
 	return true;
 }
 
-static void amdgpu_display_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct amdgpu_framebuffer *amdgpu_fb = to_amdgpu_framebuffer(fb);
-
-	drm_gem_object_put_unlocked(amdgpu_fb->obj);
-	drm_framebuffer_cleanup(fb);
-	kfree(amdgpu_fb);
-}
-
-static int amdgpu_display_user_framebuffer_create_handle(
-			struct drm_framebuffer *fb,
-			struct drm_file *file_priv,
-			unsigned int *handle)
-{
-	struct amdgpu_framebuffer *amdgpu_fb = to_amdgpu_framebuffer(fb);
-
-	return drm_gem_handle_create(file_priv, amdgpu_fb->obj, handle);
-}
-
 static const struct drm_framebuffer_funcs amdgpu_fb_funcs = {
-	.destroy = amdgpu_display_user_framebuffer_destroy,
-	.create_handle = amdgpu_display_user_framebuffer_create_handle,
+	.destroy = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
 };
 
-uint32_t amdgpu_display_framebuffer_domains(struct amdgpu_device *adev)
+uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev)
 {
 	uint32_t domain = AMDGPU_GEM_DOMAIN_VRAM;
 
@@ -526,11 +504,11 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 				    struct drm_gem_object *obj)
 {
 	int ret;
-	rfb->obj = obj;
+	rfb->base.obj[0] = obj;
 	drm_helper_mode_fill_fb_struct(dev, &rfb->base, mode_cmd);
 	ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
 	if (ret) {
-		rfb->obj = NULL;
+		rfb->base.obj[0] = NULL;
 		return ret;
 	}
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
index 2b11d808f297..f66e3e3fef0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h
@@ -23,7 +23,7 @@
 #ifndef __AMDGPU_DISPLAY_H__
 #define __AMDGPU_DISPLAY_H__
 
-uint32_t amdgpu_display_framebuffer_domains(struct amdgpu_device *adev);
+uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev);
 struct drm_framebuffer *
 amdgpu_display_user_framebuffer_create(struct drm_device *dev,
 				       struct drm_file *file_priv,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index e997ebbe43ea..def1010ac05e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -115,6 +115,26 @@ void amdgpu_dpm_print_ps_status(struct amdgpu_device *adev,
 	pr_cont("\n");
 }
 
+void amdgpu_dpm_get_active_displays(struct amdgpu_device *adev)
+{
+	struct drm_device *ddev = adev->ddev;
+	struct drm_crtc *crtc;
+	struct amdgpu_crtc *amdgpu_crtc;
+
+	adev->pm.dpm.new_active_crtcs = 0;
+	adev->pm.dpm.new_active_crtc_count = 0;
+	if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc,
+				    &ddev->mode_config.crtc_list, head) {
+			amdgpu_crtc = to_amdgpu_crtc(crtc);
+			if (amdgpu_crtc->enabled) {
+				adev->pm.dpm.new_active_crtcs |= (1 << amdgpu_crtc->crtc_id);
+				adev->pm.dpm.new_active_crtc_count++;
+			}
+		}
+	}
+}
+
 
 u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index 643d008410c6..dd6203a0a6b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -52,8 +52,6 @@ enum amdgpu_dpm_event_src {
 	AMDGPU_DPM_EVENT_SRC_DIGIAL_OR_EXTERNAL = 4
 };
 
-#define SCLK_DEEP_SLEEP_MASK 0x8
-
 struct amdgpu_ps {
 	u32 caps; /* vbios flags */
 	u32 class; /* vbios flags */
@@ -349,12 +347,6 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
 			(adev)->powerplay.pp_handle, msg_id))
 
-#define amdgpu_dpm_notify_smu_memory_info(adev, virtual_addr_low, \
-			virtual_addr_hi, mc_addr_low, mc_addr_hi, size) \
-		((adev)->powerplay.pp_funcs->notify_smu_memory_info)( \
-			(adev)->powerplay.pp_handle, virtual_addr_low, \
-			virtual_addr_hi, mc_addr_low, mc_addr_hi, size)
-
 #define amdgpu_dpm_get_power_profile_mode(adev, buf) \
 		((adev)->powerplay.pp_funcs->get_power_profile_mode(\
 			(adev)->powerplay.pp_handle, buf))
@@ -445,6 +437,8 @@ struct amdgpu_pm {
 	uint32_t                pcie_gen_mask;
 	uint32_t                pcie_mlw_mask;
 	struct amd_pp_display_configuration pm_display_cfg;/* set by dc */
+	uint32_t                smu_prv_buffer_size;
+	struct amdgpu_bo        *smu_prv_buffer;
 };
 
 #define R600_SSTU_DFLT                               0
@@ -482,6 +476,7 @@ void amdgpu_dpm_print_ps_status(struct amdgpu_device *adev,
 				struct amdgpu_ps *rps);
 u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev);
 u32 amdgpu_dpm_get_vrefresh(struct amdgpu_device *adev);
+void amdgpu_dpm_get_active_displays(struct amdgpu_device *adev);
 bool amdgpu_is_uvd_state(u32 class, u32 class2);
 void amdgpu_calculate_u_and_p(u32 i, u32 r_c, u32 p_b,
 			      u32 *p, u32 *u);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0b19482b36b8..b0bf2f24da48 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -75,9 +75,10 @@
  * - 3.23.0 - Add query for VRAM lost counter
  * - 3.24.0 - Add high priority compute support for gfx9
  * - 3.25.0 - Add support for sensor query info (stable pstate sclk/mclk).
+ * - 3.26.0 - GFX9: Process AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE.
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	25
+#define KMS_DRIVER_MINOR	26
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -121,7 +122,7 @@ uint amdgpu_pg_mask = 0xffffffff;
 uint amdgpu_sdma_phase_quantum = 32;
 char *amdgpu_disable_cu = NULL;
 char *amdgpu_virtual_display = NULL;
-uint amdgpu_pp_feature_mask = 0xffffbfff;
+uint amdgpu_pp_feature_mask = 0xffff3fff; /* gfxoff (bit 15) disabled by default */
 int amdgpu_ngg = 0;
 int amdgpu_prim_buf_per_se = 0;
 int amdgpu_pos_buf_per_se = 0;
@@ -132,6 +133,7 @@ int amdgpu_lbpw = -1;
 int amdgpu_compute_multipipe = -1;
 int amdgpu_gpu_recovery = -1; /* auto */
 int amdgpu_emu_mode = 0;
+uint amdgpu_smu_memory_pool_size = 0;
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -316,6 +318,11 @@ MODULE_PARM_DESC(cik_support, "CIK support (1 = enabled (default), 0 = disabled)
 module_param_named(cik_support, amdgpu_cik_support, int, 0444);
 #endif
 
+MODULE_PARM_DESC(smu_memory_pool_size,
+	"reserve gtt for smu debug usage, 0 = disable,"
+		"0x1 = 256Mbyte, 0x2 = 512Mbyte, 0x4 = 1 Gbyte, 0x8 = 2GByte");
+module_param_named(smu_memory_pool_size, amdgpu_smu_memory_pool_size, uint, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
@@ -534,6 +541,9 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x6995, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
 	{0x1002, 0x6997, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
 	{0x1002, 0x699F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
+	/* VEGAM */
+	{0x1002, 0x694C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGAM},
+	{0x1002, 0x694E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGAM},
 	/* Vega 10 */
 	{0x1002, 0x6860, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
 	{0x1002, 0x6861, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10},
@@ -550,6 +560,13 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x69A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA12},
 	{0x1002, 0x69A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA12},
 	{0x1002, 0x69AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA12},
+	/* Vega 20 */
+	{0x1002, 0x66A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x66A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x66A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x66A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x66A7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x66AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20|AMD_EXP_HW_SUPPORT},
 	/* Raven */
 	{0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 12063019751b..bc5fd8ebab5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -137,7 +137,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	/* need to align pitch with crtc limits */
 	mode_cmd->pitches[0] = amdgpu_align_pitch(adev, mode_cmd->width, cpp,
 						  fb_tiled);
-	domain = amdgpu_display_framebuffer_domains(adev);
+	domain = amdgpu_display_supported_domains(adev);
 
 	height = ALIGN(mode_cmd->height, 8);
 	size = mode_cmd->pitches[0] * height;
@@ -292,9 +292,9 @@ static int amdgpu_fbdev_destroy(struct drm_device *dev, struct amdgpu_fbdev *rfb
 
 	drm_fb_helper_unregister_fbi(&rfbdev->helper);
 
-	if (rfb->obj) {
-		amdgpufb_destroy_pinned_object(rfb->obj);
-		rfb->obj = NULL;
+	if (rfb->base.obj[0]) {
+		amdgpufb_destroy_pinned_object(rfb->base.obj[0]);
+		rfb->base.obj[0] = NULL;
 		drm_framebuffer_unregister_private(&rfb->base);
 		drm_framebuffer_cleanup(&rfb->base);
 	}
@@ -377,7 +377,7 @@ int amdgpu_fbdev_total_size(struct amdgpu_device *adev)
 	if (!adev->mode_info.rfbdev)
 		return 0;
 
-	robj = gem_to_amdgpu_bo(adev->mode_info.rfbdev->rfb.obj);
+	robj = gem_to_amdgpu_bo(adev->mode_info.rfbdev->rfb.base.obj[0]);
 	size += amdgpu_bo_size(robj);
 	return size;
 }
@@ -386,7 +386,7 @@ bool amdgpu_fbdev_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj)
 {
 	if (!adev->mode_info.rfbdev)
 		return false;
-	if (robj == gem_to_amdgpu_bo(adev->mode_info.rfbdev->rfb.obj))
+	if (robj == gem_to_amdgpu_bo(adev->mode_info.rfbdev->rfb.base.obj[0]))
 		return true;
 	return false;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 97449e06a242..39ec6b8890a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -131,7 +131,8 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring)
  * Emits a fence command on the requested ring (all asics).
  * Returns 0 on success, -ENOMEM on failure.
  */
-int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f)
+int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
+		      unsigned flags)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_fence *fence;
@@ -149,7 +150,7 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f)
 		       adev->fence_context + ring->idx,
 		       seq);
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
-			       seq, AMDGPU_FENCE_FLAG_INT);
+			       seq, flags | AMDGPU_FENCE_FLAG_INT);
 
 	ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask];
 	/* This function can't be called concurrently anyway, otherwise
@@ -375,14 +376,14 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 	uint64_t index;
 
-	if (ring != &adev->uvd.ring) {
+	if (ring != &adev->uvd.inst[ring->me].ring) {
 		ring->fence_drv.cpu_addr = &adev->wb.wb[ring->fence_offs];
 		ring->fence_drv.gpu_addr = adev->wb.gpu_addr + (ring->fence_offs * 4);
 	} else {
 		/* put fence directly behind firmware */
 		index = ALIGN(adev->uvd.fw->size, 8);
-		ring->fence_drv.cpu_addr = adev->uvd.cpu_addr + index;
-		ring->fence_drv.gpu_addr = adev->uvd.gpu_addr + index;
+		ring->fence_drv.cpu_addr = adev->uvd.inst[ring->me].cpu_addr + index;
+		ring->fence_drv.gpu_addr = adev->uvd.inst[ring->me].gpu_addr + index;
 	}
 	amdgpu_fence_write(ring, atomic_read(&ring->fence_drv.last_seq));
 	amdgpu_irq_get(adev, irq_src, irq_type);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index cf0f186c6092..17d6b9fb6d77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -113,12 +113,17 @@ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
 	int r;
 
 	if (adev->gart.robj == NULL) {
-		r = amdgpu_bo_create(adev, adev->gart.table_size, PAGE_SIZE,
-				     AMDGPU_GEM_DOMAIN_VRAM,
-				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-				     AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
-				     ttm_bo_type_kernel, NULL,
-				     &adev->gart.robj);
+		struct amdgpu_bo_param bp;
+
+		memset(&bp, 0, sizeof(bp));
+		bp.size = adev->gart.table_size;
+		bp.byte_align = PAGE_SIZE;
+		bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
+		bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
+			AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+		bp.type = ttm_bo_type_kernel;
+		bp.resv = NULL;
+		r = amdgpu_bo_create(adev, &bp, &adev->gart.robj);
 		if (r) {
 			return r;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 46b9ea4e6103..2c8e27370284 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -48,17 +48,25 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 			     struct drm_gem_object **obj)
 {
 	struct amdgpu_bo *bo;
+	struct amdgpu_bo_param bp;
 	int r;
 
+	memset(&bp, 0, sizeof(bp));
 	*obj = NULL;
 	/* At least align on page size */
 	if (alignment < PAGE_SIZE) {
 		alignment = PAGE_SIZE;
 	}
 
+	bp.size = size;
+	bp.byte_align = alignment;
+	bp.type = type;
+	bp.resv = resv;
+	bp.preferred_domain = initial_domain;
 retry:
-	r = amdgpu_bo_create(adev, size, alignment, initial_domain,
-			     flags, type, resv, &bo);
+	bp.flags = flags;
+	bp.domain = initial_domain;
+	r = amdgpu_bo_create(adev, &bp, &bo);
 	if (r) {
 		if (r != -ERESTARTSYS) {
 			if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
@@ -221,12 +229,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 
 	/* reject invalid gem domains */
-	if (args->in.domains & ~(AMDGPU_GEM_DOMAIN_CPU |
-				 AMDGPU_GEM_DOMAIN_GTT |
-				 AMDGPU_GEM_DOMAIN_VRAM |
-				 AMDGPU_GEM_DOMAIN_GDS |
-				 AMDGPU_GEM_DOMAIN_GWS |
-				 AMDGPU_GEM_DOMAIN_OA))
+	if (args->in.domains & ~AMDGPU_GEM_DOMAIN_MASK)
 		return -EINVAL;
 
 	/* create a gem object to contain this object in */
@@ -771,16 +774,23 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 }
 
 #if defined(CONFIG_DEBUG_FS)
+
+#define amdgpu_debugfs_gem_bo_print_flag(m, bo, flag)	\
+	if (bo->flags & (AMDGPU_GEM_CREATE_ ## flag)) {	\
+		seq_printf((m), " " #flag);		\
+	}
+
 static int amdgpu_debugfs_gem_bo_info(int id, void *ptr, void *data)
 {
 	struct drm_gem_object *gobj = ptr;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj);
 	struct seq_file *m = data;
 
+	struct dma_buf_attachment *attachment;
+	struct dma_buf *dma_buf;
 	unsigned domain;
 	const char *placement;
 	unsigned pin_count;
-	uint64_t offset;
 
 	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 	switch (domain) {
@@ -798,13 +808,27 @@ static int amdgpu_debugfs_gem_bo_info(int id, void *ptr, void *data)
 	seq_printf(m, "\t0x%08x: %12ld byte %s",
 		   id, amdgpu_bo_size(bo), placement);
 
-	offset = READ_ONCE(bo->tbo.mem.start);
-	if (offset != AMDGPU_BO_INVALID_OFFSET)
-		seq_printf(m, " @ 0x%010Lx", offset);
-
 	pin_count = READ_ONCE(bo->pin_count);
 	if (pin_count)
 		seq_printf(m, " pin count %d", pin_count);
+
+	dma_buf = READ_ONCE(bo->gem_base.dma_buf);
+	attachment = READ_ONCE(bo->gem_base.import_attach);
+
+	if (attachment)
+		seq_printf(m, " imported from %p", dma_buf);
+	else if (dma_buf)
+		seq_printf(m, " exported as %p", dma_buf);
+
+	amdgpu_debugfs_gem_bo_print_flag(m, bo, CPU_ACCESS_REQUIRED);
+	amdgpu_debugfs_gem_bo_print_flag(m, bo, NO_CPU_ACCESS);
+	amdgpu_debugfs_gem_bo_print_flag(m, bo, CPU_GTT_USWC);
+	amdgpu_debugfs_gem_bo_print_flag(m, bo, VRAM_CLEARED);
+	amdgpu_debugfs_gem_bo_print_flag(m, bo, SHADOW);
+	amdgpu_debugfs_gem_bo_print_flag(m, bo, VRAM_CONTIGUOUS);
+	amdgpu_debugfs_gem_bo_print_flag(m, bo, VM_ALWAYS_VALID);
+	amdgpu_debugfs_gem_bo_print_flag(m, bo, EXPLICIT_SYNC);
+
 	seq_printf(m, "\n");
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 311589e02d17..f70eeed9ed76 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -127,6 +127,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	struct amdgpu_vm *vm;
 	uint64_t fence_ctx;
 	uint32_t status = 0, alloc_size;
+	unsigned fence_flags = 0;
 
 	unsigned i;
 	int r = 0;
@@ -227,7 +228,10 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 #endif
 		amdgpu_asic_invalidate_hdp(adev, ring);
 
-	r = amdgpu_fence_emit(ring, f);
+	if (ib->flags & AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE)
+		fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
+
+	r = amdgpu_fence_emit(ring, f, fence_flags);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
 		if (job && job->vmid)
@@ -242,7 +246,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	/* wrap the last IB with fence */
 	if (job && job->uf_addr) {
 		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
-				       AMDGPU_FENCE_FLAG_64BIT);
+				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
 	}
 
 	if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 4b7824d30e73..91517b166a3b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -31,6 +31,7 @@
 #include "amdgpu_sched.h"
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
+#include "atom.h"
 
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
@@ -214,6 +215,18 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->ver = adev->gfx.rlc_fw_version;
 		fw_info->feature = adev->gfx.rlc_feature_version;
 		break;
+	case AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_CNTL:
+		fw_info->ver = adev->gfx.rlc_srlc_fw_version;
+		fw_info->feature = adev->gfx.rlc_srlc_feature_version;
+		break;
+	case AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_GPM_MEM:
+		fw_info->ver = adev->gfx.rlc_srlg_fw_version;
+		fw_info->feature = adev->gfx.rlc_srlg_feature_version;
+		break;
+	case AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_SRM_MEM:
+		fw_info->ver = adev->gfx.rlc_srls_fw_version;
+		fw_info->feature = adev->gfx.rlc_srls_feature_version;
+		break;
 	case AMDGPU_INFO_FW_GFX_MEC:
 		if (query_fw->index == 0) {
 			fw_info->ver = adev->gfx.mec_fw_version;
@@ -273,12 +286,15 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	struct drm_crtc *crtc;
 	uint32_t ui32 = 0;
 	uint64_t ui64 = 0;
-	int i, found;
+	int i, j, found;
 	int ui32_size = sizeof(ui32);
 
 	if (!info->return_size || !info->return_pointer)
 		return -EINVAL;
 
+	/* Ensure IB tests are run on ring */
+	flush_delayed_work(&adev->late_init_work);
+
 	switch (info->query) {
 	case AMDGPU_INFO_ACCEL_WORKING:
 		ui32 = adev->accel_working;
@@ -332,7 +348,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_UVD:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			ring_mask = adev->uvd.ring.ready ? 1 : 0;
+			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
+				ring_mask |= ((adev->uvd.inst[i].ring.ready ? 1 : 0) << i);
 			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
 			ib_size_alignment = 16;
 			break;
@@ -345,8 +362,11 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_UVD_ENC:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			for (i = 0; i < adev->uvd.num_enc_rings; i++)
-				ring_mask |= ((adev->uvd.ring_enc[i].ready ? 1 : 0) << i);
+			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
+				for (j = 0; j < adev->uvd.num_enc_rings; j++)
+					ring_mask |=
+					((adev->uvd.inst[i].ring_enc[j].ready ? 1 : 0) <<
+					(j + i * adev->uvd.num_enc_rings));
 			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
 			ib_size_alignment = 1;
 			break;
@@ -701,10 +721,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		}
 	}
 	case AMDGPU_INFO_SENSOR: {
-		struct pp_gpu_power query = {0};
-		int query_size = sizeof(query);
-
-		if (amdgpu_dpm == 0)
+		if (!adev->pm.dpm_enabled)
 			return -ENOENT;
 
 		switch (info->sensor_info.type) {
@@ -746,10 +763,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			/* get average GPU power */
 			if (amdgpu_dpm_read_sensor(adev,
 						   AMDGPU_PP_SENSOR_GPU_POWER,
-						   (void *)&query, &query_size)) {
+						   (void *)&ui32, &ui32_size)) {
 				return -EINVAL;
 			}
-			ui32 = query.average_gpu_power >> 8;
+			ui32 >>= 8;
 			break;
 		case AMDGPU_INFO_SENSOR_VDDNB:
 			/* get VDDNB in millivolts */
@@ -913,8 +930,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 		return;
 
 	pm_runtime_get_sync(dev->dev);
-
-	amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
+	amdgpu_ctx_mgr_entity_fini(&fpriv->ctx_mgr);
 
 	if (adev->asic_type != CHIP_RAVEN) {
 		amdgpu_uvd_free_handles(adev, file_priv);
@@ -935,6 +951,8 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 	pd = amdgpu_bo_ref(fpriv->vm.root.base.bo);
 
 	amdgpu_vm_fini(adev, &fpriv->vm);
+	amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
+
 	if (pasid)
 		amdgpu_pasid_free_delayed(pd->tbo.resv, pasid);
 	amdgpu_bo_unref(&pd);
@@ -1088,6 +1106,7 @@ static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data)
 	struct amdgpu_device *adev = dev->dev_private;
 	struct drm_amdgpu_info_firmware fw_info;
 	struct drm_amdgpu_query_fw query_fw;
+	struct atom_context *ctx = adev->mode_info.atom_context;
 	int ret, i;
 
 	/* VCE */
@@ -1146,6 +1165,30 @@ static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data)
 	seq_printf(m, "RLC feature version: %u, firmware version: 0x%08x\n",
 		   fw_info.feature, fw_info.ver);
 
+	/* RLC SAVE RESTORE LIST CNTL */
+	query_fw.fw_type = AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_CNTL;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "RLC SRLC feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* RLC SAVE RESTORE LIST GPM MEM */
+	query_fw.fw_type = AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_GPM_MEM;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "RLC SRLG feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* RLC SAVE RESTORE LIST SRM MEM */
+	query_fw.fw_type = AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_SRM_MEM;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "RLC SRLS feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
 	/* MEC */
 	query_fw.fw_type = AMDGPU_INFO_FW_GFX_MEC;
 	query_fw.index = 0;
@@ -1210,6 +1253,9 @@ static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data)
 	seq_printf(m, "VCN feature version: %u, firmware version: 0x%08x\n",
 		   fw_info.feature, fw_info.ver);
 
+
+	seq_printf(m, "VBIOS version: %s\n", ctx->vbios_version);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index bd67f4cb8e6c..83e344fbb50a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -36,12 +36,14 @@
 #include <drm/drm.h>
 
 #include "amdgpu.h"
+#include "amdgpu_amdkfd.h"
 
 struct amdgpu_mn {
 	/* constant after initialisation */
 	struct amdgpu_device	*adev;
 	struct mm_struct	*mm;
 	struct mmu_notifier	mn;
+	enum amdgpu_mn_type	type;
 
 	/* only used on destruction */
 	struct work_struct	work;
@@ -185,7 +187,7 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
 }
 
 /**
- * amdgpu_mn_invalidate_range_start - callback to notify about mm change
+ * amdgpu_mn_invalidate_range_start_gfx - callback to notify about mm change
  *
  * @mn: our notifier
  * @mn: the mm this callback is about
@@ -195,10 +197,10 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
  * We block for all BOs between start and end to be idle and
  * unmap them by move them into system domain again.
  */
-static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
-					     struct mm_struct *mm,
-					     unsigned long start,
-					     unsigned long end)
+static void amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
+						 struct mm_struct *mm,
+						 unsigned long start,
+						 unsigned long end)
 {
 	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
 	struct interval_tree_node *it;
@@ -220,6 +222,49 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
 }
 
 /**
+ * amdgpu_mn_invalidate_range_start_hsa - callback to notify about mm change
+ *
+ * @mn: our notifier
+ * @mn: the mm this callback is about
+ * @start: start of updated range
+ * @end: end of updated range
+ *
+ * We temporarily evict all BOs between start and end. This
+ * necessitates evicting all user-mode queues of the process. The BOs
+ * are restorted in amdgpu_mn_invalidate_range_end_hsa.
+ */
+static void amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
+						 struct mm_struct *mm,
+						 unsigned long start,
+						 unsigned long end)
+{
+	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+	struct interval_tree_node *it;
+
+	/* notification is exclusive, but interval is inclusive */
+	end -= 1;
+
+	amdgpu_mn_read_lock(rmn);
+
+	it = interval_tree_iter_first(&rmn->objects, start, end);
+	while (it) {
+		struct amdgpu_mn_node *node;
+		struct amdgpu_bo *bo;
+
+		node = container_of(it, struct amdgpu_mn_node, it);
+		it = interval_tree_iter_next(it, start, end);
+
+		list_for_each_entry(bo, &node->bos, mn_list) {
+			struct kgd_mem *mem = bo->kfd_bo;
+
+			if (amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm,
+							 start, end))
+				amdgpu_amdkfd_evict_userptr(mem, mm);
+		}
+	}
+}
+
+/**
  * amdgpu_mn_invalidate_range_end - callback to notify about mm change
  *
  * @mn: our notifier
@@ -239,23 +284,39 @@ static void amdgpu_mn_invalidate_range_end(struct mmu_notifier *mn,
 	amdgpu_mn_read_unlock(rmn);
 }
 
-static const struct mmu_notifier_ops amdgpu_mn_ops = {
-	.release = amdgpu_mn_release,
-	.invalidate_range_start = amdgpu_mn_invalidate_range_start,
-	.invalidate_range_end = amdgpu_mn_invalidate_range_end,
+static const struct mmu_notifier_ops amdgpu_mn_ops[] = {
+	[AMDGPU_MN_TYPE_GFX] = {
+		.release = amdgpu_mn_release,
+		.invalidate_range_start = amdgpu_mn_invalidate_range_start_gfx,
+		.invalidate_range_end = amdgpu_mn_invalidate_range_end,
+	},
+	[AMDGPU_MN_TYPE_HSA] = {
+		.release = amdgpu_mn_release,
+		.invalidate_range_start = amdgpu_mn_invalidate_range_start_hsa,
+		.invalidate_range_end = amdgpu_mn_invalidate_range_end,
+	},
 };
 
+/* Low bits of any reasonable mm pointer will be unused due to struct
+ * alignment. Use these bits to make a unique key from the mm pointer
+ * and notifier type.
+ */
+#define AMDGPU_MN_KEY(mm, type) ((unsigned long)(mm) + (type))
+
 /**
  * amdgpu_mn_get - create notifier context
  *
  * @adev: amdgpu device pointer
+ * @type: type of MMU notifier context
  *
  * Creates a notifier context for current->mm.
  */
-struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
+struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
+				enum amdgpu_mn_type type)
 {
 	struct mm_struct *mm = current->mm;
 	struct amdgpu_mn *rmn;
+	unsigned long key = AMDGPU_MN_KEY(mm, type);
 	int r;
 
 	mutex_lock(&adev->mn_lock);
@@ -264,8 +325,8 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
 		return ERR_PTR(-EINTR);
 	}
 
-	hash_for_each_possible(adev->mn_hash, rmn, node, (unsigned long)mm)
-		if (rmn->mm == mm)
+	hash_for_each_possible(adev->mn_hash, rmn, node, key)
+		if (AMDGPU_MN_KEY(rmn->mm, rmn->type) == key)
 			goto release_locks;
 
 	rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
@@ -276,8 +337,9 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
 
 	rmn->adev = adev;
 	rmn->mm = mm;
-	rmn->mn.ops = &amdgpu_mn_ops;
 	init_rwsem(&rmn->lock);
+	rmn->type = type;
+	rmn->mn.ops = &amdgpu_mn_ops[type];
 	rmn->objects = RB_ROOT_CACHED;
 	mutex_init(&rmn->read_lock);
 	atomic_set(&rmn->recursion, 0);
@@ -286,7 +348,7 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
 	if (r)
 		goto free_rmn;
 
-	hash_add(adev->mn_hash, &rmn->node, (unsigned long)mm);
+	hash_add(adev->mn_hash, &rmn->node, AMDGPU_MN_KEY(mm, type));
 
 release_locks:
 	up_write(&mm->mmap_sem);
@@ -315,15 +377,21 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 {
 	unsigned long end = addr + amdgpu_bo_size(bo) - 1;
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	enum amdgpu_mn_type type =
+		bo->kfd_bo ? AMDGPU_MN_TYPE_HSA : AMDGPU_MN_TYPE_GFX;
 	struct amdgpu_mn *rmn;
-	struct amdgpu_mn_node *node = NULL;
+	struct amdgpu_mn_node *node = NULL, *new_node;
 	struct list_head bos;
 	struct interval_tree_node *it;
 
-	rmn = amdgpu_mn_get(adev);
+	rmn = amdgpu_mn_get(adev, type);
 	if (IS_ERR(rmn))
 		return PTR_ERR(rmn);
 
+	new_node = kmalloc(sizeof(*new_node), GFP_KERNEL);
+	if (!new_node)
+		return -ENOMEM;
+
 	INIT_LIST_HEAD(&bos);
 
 	down_write(&rmn->lock);
@@ -337,13 +405,10 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 		list_splice(&node->bos, &bos);
 	}
 
-	if (!node) {
-		node = kmalloc(sizeof(struct amdgpu_mn_node), GFP_KERNEL);
-		if (!node) {
-			up_write(&rmn->lock);
-			return -ENOMEM;
-		}
-	}
+	if (!node)
+		node = new_node;
+	else
+		kfree(new_node);
 
 	bo->mn = rmn;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
index d0095a3793b8..eb0f432f78fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
@@ -29,16 +29,23 @@
  */
 struct amdgpu_mn;
 
+enum amdgpu_mn_type {
+	AMDGPU_MN_TYPE_GFX,
+	AMDGPU_MN_TYPE_HSA,
+};
+
 #if defined(CONFIG_MMU_NOTIFIER)
 void amdgpu_mn_lock(struct amdgpu_mn *mn);
 void amdgpu_mn_unlock(struct amdgpu_mn *mn);
-struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev);
+struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
+				enum amdgpu_mn_type type);
 int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr);
 void amdgpu_mn_unregister(struct amdgpu_bo *bo);
 #else
 static inline void amdgpu_mn_lock(struct amdgpu_mn *mn) {}
 static inline void amdgpu_mn_unlock(struct amdgpu_mn *mn) {}
-static inline struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
+static inline struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
+					      enum amdgpu_mn_type type)
 {
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index d6416ee52e32..b9e9e8b02fb7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -308,7 +308,6 @@ struct amdgpu_display_funcs {
 
 struct amdgpu_framebuffer {
 	struct drm_framebuffer base;
-	struct drm_gem_object *obj;
 
 	/* caching for later use */
 	uint64_t address;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 6d08cde8443c..6a9e46ae7f0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -191,14 +191,21 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 			      u32 domain, struct amdgpu_bo **bo_ptr,
 			      u64 *gpu_addr, void **cpu_addr)
 {
+	struct amdgpu_bo_param bp;
 	bool free = false;
 	int r;
 
+	memset(&bp, 0, sizeof(bp));
+	bp.size = size;
+	bp.byte_align = align;
+	bp.domain = domain;
+	bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
+		AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+	bp.type = ttm_bo_type_kernel;
+	bp.resv = NULL;
+
 	if (!*bo_ptr) {
-		r = amdgpu_bo_create(adev, size, align, domain,
-				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-				     AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
-				     ttm_bo_type_kernel, NULL, bo_ptr);
+		r = amdgpu_bo_create(adev, &bp, bo_ptr);
 		if (r) {
 			dev_err(adev->dev, "(%d) failed to allocate kernel bo\n",
 				r);
@@ -341,27 +348,25 @@ fail:
 	return false;
 }
 
-static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size,
-			       int byte_align, u32 domain,
-			       u64 flags, enum ttm_bo_type type,
-			       struct reservation_object *resv,
+static int amdgpu_bo_do_create(struct amdgpu_device *adev,
+			       struct amdgpu_bo_param *bp,
 			       struct amdgpu_bo **bo_ptr)
 {
 	struct ttm_operation_ctx ctx = {
-		.interruptible = (type != ttm_bo_type_kernel),
+		.interruptible = (bp->type != ttm_bo_type_kernel),
 		.no_wait_gpu = false,
-		.resv = resv,
+		.resv = bp->resv,
 		.flags = TTM_OPT_FLAG_ALLOW_RES_EVICT
 	};
 	struct amdgpu_bo *bo;
-	unsigned long page_align;
+	unsigned long page_align, size = bp->size;
 	size_t acc_size;
 	int r;
 
-	page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
+	page_align = roundup(bp->byte_align, PAGE_SIZE) >> PAGE_SHIFT;
 	size = ALIGN(size, PAGE_SIZE);
 
-	if (!amdgpu_bo_validate_size(adev, size, domain))
+	if (!amdgpu_bo_validate_size(adev, size, bp->domain))
 		return -ENOMEM;
 
 	*bo_ptr = NULL;
@@ -375,18 +380,14 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size,
 	drm_gem_private_object_init(adev->ddev, &bo->gem_base, size);
 	INIT_LIST_HEAD(&bo->shadow_list);
 	INIT_LIST_HEAD(&bo->va);
-	bo->preferred_domains = domain & (AMDGPU_GEM_DOMAIN_VRAM |
-					 AMDGPU_GEM_DOMAIN_GTT |
-					 AMDGPU_GEM_DOMAIN_CPU |
-					 AMDGPU_GEM_DOMAIN_GDS |
-					 AMDGPU_GEM_DOMAIN_GWS |
-					 AMDGPU_GEM_DOMAIN_OA);
+	bo->preferred_domains = bp->preferred_domain ? bp->preferred_domain :
+		bp->domain;
 	bo->allowed_domains = bo->preferred_domains;
-	if (type != ttm_bo_type_kernel &&
+	if (bp->type != ttm_bo_type_kernel &&
 	    bo->allowed_domains == AMDGPU_GEM_DOMAIN_VRAM)
 		bo->allowed_domains |= AMDGPU_GEM_DOMAIN_GTT;
 
-	bo->flags = flags;
+	bo->flags = bp->flags;
 
 #ifdef CONFIG_X86_32
 	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
@@ -417,11 +418,13 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size,
 #endif
 
 	bo->tbo.bdev = &adev->mman.bdev;
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_ttm_placement_from_domain(bo, bp->domain);
+	if (bp->type == ttm_bo_type_kernel)
+		bo->tbo.priority = 1;
 
-	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
+	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, bp->type,
 				 &bo->placement, page_align, &ctx, acc_size,
-				 NULL, resv, &amdgpu_ttm_bo_destroy);
+				 NULL, bp->resv, &amdgpu_ttm_bo_destroy);
 	if (unlikely(r != 0))
 		return r;
 
@@ -433,10 +436,7 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size,
 	else
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0);
 
-	if (type == ttm_bo_type_kernel)
-		bo->tbo.priority = 1;
-
-	if (flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
+	if (bp->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
 	    bo->tbo.mem.placement & TTM_PL_FLAG_VRAM) {
 		struct dma_fence *fence;
 
@@ -449,20 +449,20 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size,
 		bo->tbo.moving = dma_fence_get(fence);
 		dma_fence_put(fence);
 	}
-	if (!resv)
+	if (!bp->resv)
 		amdgpu_bo_unreserve(bo);
 	*bo_ptr = bo;
 
 	trace_amdgpu_bo_create(bo);
 
 	/* Treat CPU_ACCESS_REQUIRED only as a hint if given by UMD */
-	if (type == ttm_bo_type_device)
+	if (bp->type == ttm_bo_type_device)
 		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 
 	return 0;
 
 fail_unreserve:
-	if (!resv)
+	if (!bp->resv)
 		ww_mutex_unlock(&bo->tbo.resv->lock);
 	amdgpu_bo_unref(&bo);
 	return r;
@@ -472,16 +472,22 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
 				   unsigned long size, int byte_align,
 				   struct amdgpu_bo *bo)
 {
+	struct amdgpu_bo_param bp;
 	int r;
 
 	if (bo->shadow)
 		return 0;
 
-	r = amdgpu_bo_do_create(adev, size, byte_align, AMDGPU_GEM_DOMAIN_GTT,
-				AMDGPU_GEM_CREATE_CPU_GTT_USWC |
-				AMDGPU_GEM_CREATE_SHADOW,
-				ttm_bo_type_kernel,
-				bo->tbo.resv, &bo->shadow);
+	memset(&bp, 0, sizeof(bp));
+	bp.size = size;
+	bp.byte_align = byte_align;
+	bp.domain = AMDGPU_GEM_DOMAIN_GTT;
+	bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC |
+		AMDGPU_GEM_CREATE_SHADOW;
+	bp.type = ttm_bo_type_kernel;
+	bp.resv = bo->tbo.resv;
+
+	r = amdgpu_bo_do_create(adev, &bp, &bo->shadow);
 	if (!r) {
 		bo->shadow->parent = amdgpu_bo_ref(bo);
 		mutex_lock(&adev->shadow_list_lock);
@@ -492,28 +498,26 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
 	return r;
 }
 
-int amdgpu_bo_create(struct amdgpu_device *adev, unsigned long size,
-		     int byte_align, u32 domain,
-		     u64 flags, enum ttm_bo_type type,
-		     struct reservation_object *resv,
+int amdgpu_bo_create(struct amdgpu_device *adev,
+		     struct amdgpu_bo_param *bp,
 		     struct amdgpu_bo **bo_ptr)
 {
-	uint64_t parent_flags = flags & ~AMDGPU_GEM_CREATE_SHADOW;
+	u64 flags = bp->flags;
 	int r;
 
-	r = amdgpu_bo_do_create(adev, size, byte_align, domain,
-				parent_flags, type, resv, bo_ptr);
+	bp->flags = bp->flags & ~AMDGPU_GEM_CREATE_SHADOW;
+	r = amdgpu_bo_do_create(adev, bp, bo_ptr);
 	if (r)
 		return r;
 
 	if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_need_backup(adev)) {
-		if (!resv)
+		if (!bp->resv)
 			WARN_ON(reservation_object_lock((*bo_ptr)->tbo.resv,
 							NULL));
 
-		r = amdgpu_bo_create_shadow(adev, size, byte_align, (*bo_ptr));
+		r = amdgpu_bo_create_shadow(adev, bp->size, bp->byte_align, (*bo_ptr));
 
-		if (!resv)
+		if (!bp->resv)
 			reservation_object_unlock((*bo_ptr)->tbo.resv);
 
 		if (r)
@@ -689,8 +693,21 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		return -EINVAL;
 
 	/* A shared bo cannot be migrated to VRAM */
-	if (bo->prime_shared_count && (domain == AMDGPU_GEM_DOMAIN_VRAM))
-		return -EINVAL;
+	if (bo->prime_shared_count) {
+		if (domain & AMDGPU_GEM_DOMAIN_GTT)
+			domain = AMDGPU_GEM_DOMAIN_GTT;
+		else
+			return -EINVAL;
+	}
+
+	/* This assumes only APU display buffers are pinned with (VRAM|GTT).
+	 * See function amdgpu_display_supported_domains()
+	 */
+	if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) {
+		domain = AMDGPU_GEM_DOMAIN_VRAM;
+		if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD)
+			domain = AMDGPU_GEM_DOMAIN_GTT;
+	}
 
 	if (bo->pin_count) {
 		uint32_t mem_type = bo->tbo.mem.mem_type;
@@ -838,6 +855,13 @@ int amdgpu_bo_init(struct amdgpu_device *adev)
 	return amdgpu_ttm_init(adev);
 }
 
+int amdgpu_bo_late_init(struct amdgpu_device *adev)
+{
+	amdgpu_ttm_late_init(adev);
+
+	return 0;
+}
+
 void amdgpu_bo_fini(struct amdgpu_device *adev)
 {
 	amdgpu_ttm_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 546f77cb7882..540e03fa159f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -33,6 +33,16 @@
 
 #define AMDGPU_BO_INVALID_OFFSET	LONG_MAX
 
+struct amdgpu_bo_param {
+	unsigned long			size;
+	int				byte_align;
+	u32				domain;
+	u32				preferred_domain;
+	u64				flags;
+	enum ttm_bo_type		type;
+	struct reservation_object	*resv;
+};
+
 /* bo virtual addresses in a vm */
 struct amdgpu_bo_va_mapping {
 	struct amdgpu_bo_va		*bo_va;
@@ -196,6 +206,27 @@ static inline bool amdgpu_bo_gpu_accessible(struct amdgpu_bo *bo)
 }
 
 /**
+ * amdgpu_bo_in_cpu_visible_vram - check if BO is (partly) in visible VRAM
+ */
+static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo)
+{
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	unsigned fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
+	struct drm_mm_node *node = bo->tbo.mem.mm_node;
+	unsigned long pages_left;
+
+	if (bo->tbo.mem.mem_type != TTM_PL_VRAM)
+		return false;
+
+	for (pages_left = bo->tbo.mem.num_pages; pages_left;
+	     pages_left -= node->size, node++)
+		if (node->start < fpfn)
+			return true;
+
+	return false;
+}
+
+/**
  * amdgpu_bo_explicit_sync - return whether the bo is explicitly synced
  */
 static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
@@ -203,10 +234,8 @@ static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
 	return bo->flags & AMDGPU_GEM_CREATE_EXPLICIT_SYNC;
 }
 
-int amdgpu_bo_create(struct amdgpu_device *adev, unsigned long size,
-		     int byte_align, u32 domain,
-		     u64 flags, enum ttm_bo_type type,
-		     struct reservation_object *resv,
+int amdgpu_bo_create(struct amdgpu_device *adev,
+		     struct amdgpu_bo_param *bp,
 		     struct amdgpu_bo **bo_ptr);
 int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 			      unsigned long size, int align,
@@ -230,6 +259,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 int amdgpu_bo_unpin(struct amdgpu_bo *bo);
 int amdgpu_bo_evict_vram(struct amdgpu_device *adev);
 int amdgpu_bo_init(struct amdgpu_device *adev);
+int amdgpu_bo_late_init(struct amdgpu_device *adev);
 void amdgpu_bo_fini(struct amdgpu_device *adev);
 int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
 				struct vm_area_struct *vma);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 361975cf45a9..b455da487782 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -77,6 +77,37 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
 	}
 }
 
+/**
+ * DOC: power_dpm_state
+ *
+ * This is a legacy interface and is only provided for backwards compatibility.
+ * The amdgpu driver provides a sysfs API for adjusting certain power
+ * related parameters.  The file power_dpm_state is used for this.
+ * It accepts the following arguments:
+ * - battery
+ * - balanced
+ * - performance
+ *
+ * battery
+ *
+ * On older GPUs, the vbios provided a special power state for battery
+ * operation.  Selecting battery switched to this state.  This is no
+ * longer provided on newer GPUs so the option does nothing in that case.
+ *
+ * balanced
+ *
+ * On older GPUs, the vbios provided a special power state for balanced
+ * operation.  Selecting balanced switched to this state.  This is no
+ * longer provided on newer GPUs so the option does nothing in that case.
+ *
+ * performance
+ *
+ * On older GPUs, the vbios provided a special power state for performance
+ * operation.  Selecting performance switched to this state.  This is no
+ * longer provided on newer GPUs so the option does nothing in that case.
+ *
+ */
+
 static ssize_t amdgpu_get_dpm_state(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
@@ -131,6 +162,59 @@ fail:
 	return count;
 }
 
+
+/**
+ * DOC: power_dpm_force_performance_level
+ *
+ * The amdgpu driver provides a sysfs API for adjusting certain power
+ * related parameters.  The file power_dpm_force_performance_level is
+ * used for this.  It accepts the following arguments:
+ * - auto
+ * - low
+ * - high
+ * - manual
+ * - GPU fan
+ * - profile_standard
+ * - profile_min_sclk
+ * - profile_min_mclk
+ * - profile_peak
+ *
+ * auto
+ *
+ * When auto is selected, the driver will attempt to dynamically select
+ * the optimal power profile for current conditions in the driver.
+ *
+ * low
+ *
+ * When low is selected, the clocks are forced to the lowest power state.
+ *
+ * high
+ *
+ * When high is selected, the clocks are forced to the highest power state.
+ *
+ * manual
+ *
+ * When manual is selected, the user can manually adjust which power states
+ * are enabled for each clock domain via the sysfs pp_dpm_mclk, pp_dpm_sclk,
+ * and pp_dpm_pcie files and adjust the power state transition heuristics
+ * via the pp_power_profile_mode sysfs file.
+ *
+ * profile_standard
+ * profile_min_sclk
+ * profile_min_mclk
+ * profile_peak
+ *
+ * When the profiling modes are selected, clock and power gating are
+ * disabled and the clocks are set for different profiling cases. This
+ * mode is recommended for profiling specific work loads where you do
+ * not want clock or power gating for clock fluctuation to interfere
+ * with your results. profile_standard sets the clocks to a fixed clock
+ * level which varies from asic to asic.  profile_min_sclk forces the sclk
+ * to the lowest level.  profile_min_mclk forces the mclk to the lowest level.
+ * profile_peak sets all clocks (mclk, sclk, pcie) to the highest levels.
+ *
+ */
+
 static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev,
 						struct device_attribute *attr,
 								char *buf)
@@ -324,6 +408,17 @@ fail:
 	return count;
 }
 
+/**
+ * DOC: pp_table
+ *
+ * The amdgpu driver provides a sysfs API for uploading new powerplay
+ * tables.  The file pp_table is used for this.  Reading the file
+ * will dump the current power play table.  Writing to the file
+ * will attempt to upload a new powerplay table and re-initialize
+ * powerplay using that new table.
+ *
+ */
+
 static ssize_t amdgpu_get_pp_table(struct device *dev,
 		struct device_attribute *attr,
 		char *buf)
@@ -360,6 +455,29 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
 	return count;
 }
 
+/**
+ * DOC: pp_od_clk_voltage
+ *
+ * The amdgpu driver provides a sysfs API for adjusting the clocks and voltages
+ * in each power level within a power state.  The pp_od_clk_voltage is used for
+ * this.
+ *
+ * Reading the file will display:
+ * - a list of engine clock levels and voltages labeled OD_SCLK
+ * - a list of memory clock levels and voltages labeled OD_MCLK
+ * - a list of valid ranges for sclk, mclk, and voltage labeled OD_RANGE
+ *
+ * To manually adjust these settings, first select manual using
+ * power_dpm_force_performance_level. Enter a new value for each
+ * level by writing a string that contains "s/m level clock voltage" to
+ * the file.  E.g., "s 1 500 820" will update sclk level 1 to be 500 MHz
+ * at 820 mV; "m 0 350 810" will update mclk level 0 to be 350 MHz at
+ * 810 mV.  When you have edited all of the states as needed, write
+ * "c" (commit) to the file to commit your changes.  If you want to reset to the
+ * default power levels, write "r" (reset) to the file to reset them.
+ *
+ */
+
 static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 		struct device_attribute *attr,
 		const char *buf,
@@ -437,6 +555,7 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev,
 	if (adev->powerplay.pp_funcs->print_clock_levels) {
 		size = amdgpu_dpm_print_clock_levels(adev, OD_SCLK, buf);
 		size += amdgpu_dpm_print_clock_levels(adev, OD_MCLK, buf+size);
+		size += amdgpu_dpm_print_clock_levels(adev, OD_RANGE, buf+size);
 		return size;
 	} else {
 		return snprintf(buf, PAGE_SIZE, "\n");
@@ -444,6 +563,23 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev,
 
 }
 
+/**
+ * DOC: pp_dpm_sclk pp_dpm_mclk pp_dpm_pcie
+ *
+ * The amdgpu driver provides a sysfs API for adjusting what power levels
+ * are enabled for a given power state.  The files pp_dpm_sclk, pp_dpm_mclk,
+ * and pp_dpm_pcie are used for this.
+ *
+ * Reading back the files will show you the available power levels within
+ * the power state and the clock information for those levels.
+ *
+ * To manually adjust these states, first select manual using
+ * power_dpm_force_performance_level.
+ * Secondly,Enter a new value for each level by inputing a string that
+ * contains " echo xx xx xx > pp_dpm_sclk/mclk/pcie"
+ * E.g., echo 4 5 6 to > pp_dpm_sclk will enable sclk levels 4, 5, and 6.
+ */
+
 static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev,
 		struct device_attribute *attr,
 		char *buf)
@@ -466,23 +602,27 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
 	long level;
-	uint32_t i, mask = 0;
-	char sub_str[2];
+	uint32_t mask = 0;
+	char *sub_str = NULL;
+	char *tmp;
+	char buf_cpy[count];
+	const char delimiter[3] = {' ', '\n', '\0'};
 
-	for (i = 0; i < strlen(buf); i++) {
-		if (*(buf + i) == '\n')
-			continue;
-		sub_str[0] = *(buf + i);
-		sub_str[1] = '\0';
-		ret = kstrtol(sub_str, 0, &level);
+	memcpy(buf_cpy, buf, count+1);
+	tmp = buf_cpy;
+	while (tmp[0]) {
+		sub_str =  strsep(&tmp, delimiter);
+		if (strlen(sub_str)) {
+			ret = kstrtol(sub_str, 0, &level);
 
-		if (ret) {
-			count = -EINVAL;
-			goto fail;
-		}
-		mask |= 1 << level;
+			if (ret) {
+				count = -EINVAL;
+				goto fail;
+			}
+			mask |= 1 << level;
+		} else
+			break;
 	}
-
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
 
@@ -512,21 +652,26 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
 	long level;
-	uint32_t i, mask = 0;
-	char sub_str[2];
+	uint32_t mask = 0;
+	char *sub_str = NULL;
+	char *tmp;
+	char buf_cpy[count];
+	const char delimiter[3] = {' ', '\n', '\0'};
 
-	for (i = 0; i < strlen(buf); i++) {
-		if (*(buf + i) == '\n')
-			continue;
-		sub_str[0] = *(buf + i);
-		sub_str[1] = '\0';
-		ret = kstrtol(sub_str, 0, &level);
+	memcpy(buf_cpy, buf, count+1);
+	tmp = buf_cpy;
+	while (tmp[0]) {
+		sub_str =  strsep(&tmp, delimiter);
+		if (strlen(sub_str)) {
+			ret = kstrtol(sub_str, 0, &level);
 
-		if (ret) {
-			count = -EINVAL;
-			goto fail;
-		}
-		mask |= 1 << level;
+			if (ret) {
+				count = -EINVAL;
+				goto fail;
+			}
+			mask |= 1 << level;
+		} else
+			break;
 	}
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
@@ -557,21 +702,27 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
 	long level;
-	uint32_t i, mask = 0;
-	char sub_str[2];
+	uint32_t mask = 0;
+	char *sub_str = NULL;
+	char *tmp;
+	char buf_cpy[count];
+	const char delimiter[3] = {' ', '\n', '\0'};
 
-	for (i = 0; i < strlen(buf); i++) {
-		if (*(buf + i) == '\n')
-			continue;
-		sub_str[0] = *(buf + i);
-		sub_str[1] = '\0';
-		ret = kstrtol(sub_str, 0, &level);
+	memcpy(buf_cpy, buf, count+1);
+	tmp = buf_cpy;
 
-		if (ret) {
-			count = -EINVAL;
-			goto fail;
-		}
-		mask |= 1 << level;
+	while (tmp[0]) {
+		sub_str =  strsep(&tmp, delimiter);
+		if (strlen(sub_str)) {
+			ret = kstrtol(sub_str, 0, &level);
+
+			if (ret) {
+				count = -EINVAL;
+				goto fail;
+			}
+			mask |= 1 << level;
+		} else
+			break;
 	}
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
@@ -668,6 +819,26 @@ fail:
 	return count;
 }
 
+/**
+ * DOC: pp_power_profile_mode
+ *
+ * The amdgpu driver provides a sysfs API for adjusting the heuristics
+ * related to switching between power levels in a power state.  The file
+ * pp_power_profile_mode is used for this.
+ *
+ * Reading this file outputs a list of all of the predefined power profiles
+ * and the relevant heuristics settings for that profile.
+ *
+ * To select a profile or create a custom profile, first select manual using
+ * power_dpm_force_performance_level.  Writing the number of a predefined
+ * profile to pp_power_profile_mode will enable those heuristics.  To
+ * create a custom set of heuristics, write a string of numbers to the file
+ * starting with the number of the custom profile along with a setting
+ * for each heuristic parameter.  Due to differences across asic families
+ * the heuristic parameters vary from family to family.
+ *
+ */
+
 static ssize_t amdgpu_get_pp_power_profile_mode(struct device *dev,
 		struct device_attribute *attr,
 		char *buf)
@@ -1020,8 +1191,8 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	struct drm_device *ddev = adev->ddev;
-	struct pp_gpu_power query = {0};
-	int r, size = sizeof(query);
+	u32 query = 0;
+	int r, size = sizeof(u32);
 	unsigned uw;
 
 	/* Can't get power when the card is off */
@@ -1041,7 +1212,7 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev,
 		return r;
 
 	/* convert to microwatts */
-	uw = (query.average_gpu_power >> 8) * 1000000;
+	uw = (query >> 8) * 1000000 + (query & 0xff) * 1000;
 
 	return snprintf(buf, PAGE_SIZE, "%u\n", uw);
 }
@@ -1109,6 +1280,46 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
 	return count;
 }
 
+
+/**
+ * DOC: hwmon
+ *
+ * The amdgpu driver exposes the following sensor interfaces:
+ * - GPU temperature (via the on-die sensor)
+ * - GPU voltage
+ * - Northbridge voltage (APUs only)
+ * - GPU power
+ * - GPU fan
+ *
+ * hwmon interfaces for GPU temperature:
+ * - temp1_input: the on die GPU temperature in millidegrees Celsius
+ * - temp1_crit: temperature critical max value in millidegrees Celsius
+ * - temp1_crit_hyst: temperature hysteresis for critical limit in millidegrees Celsius
+ *
+ * hwmon interfaces for GPU voltage:
+ * - in0_input: the voltage on the GPU in millivolts
+ * - in1_input: the voltage on the Northbridge in millivolts
+ *
+ * hwmon interfaces for GPU power:
+ * - power1_average: average power used by the GPU in microWatts
+ * - power1_cap_min: minimum cap supported in microWatts
+ * - power1_cap_max: maximum cap supported in microWatts
+ * - power1_cap: selected power cap in microWatts
+ *
+ * hwmon interfaces for GPU fan:
+ * - pwm1: pulse width modulation fan level (0-255)
+ * - pwm1_enable: pulse width modulation fan control method
+ *                0: no fan speed control
+ *                1: manual fan speed control using pwm interface
+ *                2: automatic fan speed control
+ * - pwm1_min: pulse width modulation fan control minimum level (0)
+ * - pwm1_max: pulse width modulation fan control maximum level (255)
+ * - fan1_input: fan speed in RPM
+ *
+ * You can use hwmon tools like sensors to view this information on your system.
+ *
+ */
+
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, amdgpu_hwmon_show_temp, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, amdgpu_hwmon_show_temp_thresh, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, amdgpu_hwmon_show_temp_thresh, NULL, 1);
@@ -1153,19 +1364,14 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	umode_t effective_mode = attr->mode;
 
-	/* handle non-powerplay limitations */
-	if (!adev->powerplay.pp_handle) {
-		/* Skip fan attributes if fan is not present */
-		if (adev->pm.no_fan &&
-		    (attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
-		     attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr ||
-		     attr == &sensor_dev_attr_pwm1_max.dev_attr.attr ||
-		     attr == &sensor_dev_attr_pwm1_min.dev_attr.attr))
-			return 0;
-		/* requires powerplay */
-		if (attr == &sensor_dev_attr_fan1_input.dev_attr.attr)
-			return 0;
-	}
+
+	/* Skip fan attributes if fan is not present */
+	if (adev->pm.no_fan && (attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
+	    attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr ||
+	    attr == &sensor_dev_attr_pwm1_max.dev_attr.attr ||
+	    attr == &sensor_dev_attr_pwm1_min.dev_attr.attr ||
+	    attr == &sensor_dev_attr_fan1_input.dev_attr.attr))
+		return 0;
 
 	/* Skip limit attributes if DPM is not enabled */
 	if (!adev->pm.dpm_enabled &&
@@ -1658,9 +1864,6 @@ void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev)
 
 void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 {
-	struct drm_device *ddev = adev->ddev;
-	struct drm_crtc *crtc;
-	struct amdgpu_crtc *amdgpu_crtc;
 	int i = 0;
 
 	if (!adev->pm.dpm_enabled)
@@ -1676,21 +1879,25 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 	}
 
 	if (adev->powerplay.pp_funcs->dispatch_tasks) {
+		if (!amdgpu_device_has_dc_support(adev)) {
+			mutex_lock(&adev->pm.mutex);
+			amdgpu_dpm_get_active_displays(adev);
+			adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtcs;
+			adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev);
+			adev->pm.pm_display_cfg.min_vblank_time = amdgpu_dpm_get_vblank_time(adev);
+			/* we have issues with mclk switching with refresh rates over 120 hz on the non-DC code. */
+			if (adev->pm.pm_display_cfg.vrefresh > 120)
+				adev->pm.pm_display_cfg.min_vblank_time = 0;
+			if (adev->powerplay.pp_funcs->display_configuration_change)
+				adev->powerplay.pp_funcs->display_configuration_change(
+								adev->powerplay.pp_handle,
+								&adev->pm.pm_display_cfg);
+			mutex_unlock(&adev->pm.mutex);
+		}
 		amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_DISPLAY_CONFIG_CHANGE, NULL);
 	} else {
 		mutex_lock(&adev->pm.mutex);
-		adev->pm.dpm.new_active_crtcs = 0;
-		adev->pm.dpm.new_active_crtc_count = 0;
-		if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) {
-			list_for_each_entry(crtc,
-					    &ddev->mode_config.crtc_list, head) {
-				amdgpu_crtc = to_amdgpu_crtc(crtc);
-				if (amdgpu_crtc->enabled) {
-					adev->pm.dpm.new_active_crtcs |= (1 << amdgpu_crtc->crtc_id);
-					adev->pm.dpm.new_active_crtc_count++;
-				}
-			}
-		}
+		amdgpu_dpm_get_active_displays(adev);
 		/* update battery/ac status */
 		if (power_supply_is_system_supplied() > 0)
 			adev->pm.dpm.ac_power = true;
@@ -1711,7 +1918,7 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *adev)
 {
 	uint32_t value;
-	struct pp_gpu_power query = {0};
+	uint32_t query = 0;
 	int size;
 
 	/* sanity check PP is enabled */
@@ -1734,17 +1941,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 		seq_printf(m, "\t%u mV (VDDGFX)\n", value);
 	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDNB, (void *)&value, &size))
 		seq_printf(m, "\t%u mV (VDDNB)\n", value);
-	size = sizeof(query);
-	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_POWER, (void *)&query, &size)) {
-		seq_printf(m, "\t%u.%u W (VDDC)\n", query.vddc_power >> 8,
-				query.vddc_power & 0xff);
-		seq_printf(m, "\t%u.%u W (VDDCI)\n", query.vddci_power >> 8,
-				query.vddci_power & 0xff);
-		seq_printf(m, "\t%u.%u W (max GPU)\n", query.max_gpu_power >> 8,
-				query.max_gpu_power & 0xff);
-		seq_printf(m, "\t%u.%u W (average GPU)\n", query.average_gpu_power >> 8,
-				query.average_gpu_power & 0xff);
-	}
+	size = sizeof(uint32_t);
+	if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_POWER, (void *)&query, &size))
+		seq_printf(m, "\t%u.%u W (average GPU)\n", query >> 8, query & 0xff);
 	size = sizeof(value);
 	seq_printf(m, "\n");
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 4b584cb75bf4..4683626b065f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -102,12 +102,18 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 	struct reservation_object *resv = attach->dmabuf->resv;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_bo *bo;
+	struct amdgpu_bo_param bp;
 	int ret;
 
+	memset(&bp, 0, sizeof(bp));
+	bp.size = attach->dmabuf->size;
+	bp.byte_align = PAGE_SIZE;
+	bp.domain = AMDGPU_GEM_DOMAIN_CPU;
+	bp.flags = 0;
+	bp.type = ttm_bo_type_sg;
+	bp.resv = resv;
 	ww_mutex_lock(&resv->lock, NULL);
-	ret = amdgpu_bo_create(adev, attach->dmabuf->size, PAGE_SIZE,
-			       AMDGPU_GEM_DOMAIN_CPU, 0, ttm_bo_type_sg,
-			       resv, &bo);
+	ret = amdgpu_bo_create(adev, &bp, &bo);
 	if (ret)
 		goto error;
 
@@ -209,7 +215,7 @@ static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(dma_buf->priv);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct ttm_operation_ctx ctx = { true, false };
-	u32 domain = amdgpu_display_framebuffer_domains(adev);
+	u32 domain = amdgpu_display_supported_domains(adev);
 	int ret;
 	bool reads = (direction == DMA_BIDIRECTIONAL ||
 		      direction == DMA_FROM_DEVICE);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index c7d43e064fc7..9f1a5bd39ae8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -52,6 +52,7 @@ static int psp_sw_init(void *handle)
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 		psp_v3_1_set_psp_funcs(psp);
 		break;
 	case CHIP_RAVEN:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index 262c1267249e..8af16e81c7d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -66,6 +66,8 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 			       u32 ring,
 			       struct amdgpu_ring **out_ring)
 {
+	u32 instance;
+
 	switch (mapper->hw_ip) {
 	case AMDGPU_HW_IP_GFX:
 		*out_ring = &adev->gfx.gfx_ring[ring];
@@ -77,13 +79,16 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 		*out_ring = &adev->sdma.instance[ring].ring;
 		break;
 	case AMDGPU_HW_IP_UVD:
-		*out_ring = &adev->uvd.ring;
+		instance = ring;
+		*out_ring = &adev->uvd.inst[instance].ring;
 		break;
 	case AMDGPU_HW_IP_VCE:
 		*out_ring = &adev->vce.ring[ring];
 		break;
 	case AMDGPU_HW_IP_UVD_ENC:
-		*out_ring = &adev->uvd.ring_enc[ring];
+		instance = ring / adev->uvd.num_enc_rings;
+		*out_ring =
+		&adev->uvd.inst[instance].ring_enc[ring%adev->uvd.num_enc_rings];
 		break;
 	case AMDGPU_HW_IP_VCN_DEC:
 		*out_ring = &adev->vcn.ring_dec;
@@ -240,13 +245,14 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 		ip_num_rings = adev->sdma.num_instances;
 		break;
 	case AMDGPU_HW_IP_UVD:
-		ip_num_rings = 1;
+		ip_num_rings = adev->uvd.num_uvd_inst;
 		break;
 	case AMDGPU_HW_IP_VCE:
 		ip_num_rings = adev->vce.num_rings;
 		break;
 	case AMDGPU_HW_IP_UVD_ENC:
-		ip_num_rings = adev->uvd.num_enc_rings;
+		ip_num_rings =
+			adev->uvd.num_enc_rings * adev->uvd.num_uvd_inst;
 		break;
 	case AMDGPU_HW_IP_VCN_DEC:
 		ip_num_rings = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index d5f526f38e50..c6850b629d0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -362,6 +362,7 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 
 	dma_fence_put(ring->vmid_wait);
 	ring->vmid_wait = NULL;
+	ring->me = 0;
 
 	ring->adev->rings[ring->idx] = NULL;
 }
@@ -459,6 +460,26 @@ void amdgpu_ring_lru_touch(struct amdgpu_device *adev, struct amdgpu_ring *ring)
 	spin_unlock(&adev->ring_lru_list_lock);
 }
 
+/**
+ * amdgpu_ring_emit_reg_write_reg_wait_helper - ring helper
+ *
+ * @adev: amdgpu_device pointer
+ * @reg0: register to write
+ * @reg1: register to wait on
+ * @ref: reference value to write/wait on
+ * @mask: mask to wait on
+ *
+ * Helper for rings that don't support write and wait in a
+ * single oneshot packet.
+ */
+void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring,
+						uint32_t reg0, uint32_t reg1,
+						uint32_t ref, uint32_t mask)
+{
+	amdgpu_ring_emit_wreg(ring, reg0, ref);
+	amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask);
+}
+
 /*
  * Debugfs info
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 1a5911882657..1513124c5659 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -29,7 +29,7 @@
 #include <drm/drm_print.h>
 
 /* max number of rings */
-#define AMDGPU_MAX_RINGS		18
+#define AMDGPU_MAX_RINGS		21
 #define AMDGPU_MAX_GFX_RINGS		1
 #define AMDGPU_MAX_COMPUTE_RINGS	8
 #define AMDGPU_MAX_VCE_RINGS		3
@@ -42,6 +42,7 @@
 
 #define AMDGPU_FENCE_FLAG_64BIT         (1 << 0)
 #define AMDGPU_FENCE_FLAG_INT           (1 << 1)
+#define AMDGPU_FENCE_FLAG_TC_WB_ONLY    (1 << 2)
 
 enum amdgpu_ring_type {
 	AMDGPU_RING_TYPE_GFX,
@@ -90,7 +91,8 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 				   unsigned irq_type);
 void amdgpu_fence_driver_suspend(struct amdgpu_device *adev);
 void amdgpu_fence_driver_resume(struct amdgpu_device *adev);
-int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence);
+int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence,
+		      unsigned flags);
 int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s);
 void amdgpu_fence_process(struct amdgpu_ring *ring);
 int amdgpu_fence_wait_empty(struct amdgpu_ring *ring);
@@ -154,6 +156,9 @@ struct amdgpu_ring_funcs {
 	void (*emit_wreg)(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
 	void (*emit_reg_wait)(struct amdgpu_ring *ring, uint32_t reg,
 			      uint32_t val, uint32_t mask);
+	void (*emit_reg_write_reg_wait)(struct amdgpu_ring *ring,
+					uint32_t reg0, uint32_t reg1,
+					uint32_t ref, uint32_t mask);
 	void (*emit_tmz)(struct amdgpu_ring *ring, bool start);
 	/* priority functions */
 	void (*set_priority) (struct amdgpu_ring *ring,
@@ -228,6 +233,10 @@ int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type,
 			int *blacklist, int num_blacklist,
 			bool lru_pipe_order, struct amdgpu_ring **ring);
 void amdgpu_ring_lru_touch(struct amdgpu_device *adev, struct amdgpu_ring *ring);
+void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring,
+						uint32_t reg0, uint32_t val0,
+						uint32_t reg1, uint32_t val1);
+
 static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
 {
 	int i = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index 2dbe87591f81..d167e8ab76d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -33,6 +33,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 	struct amdgpu_bo *vram_obj = NULL;
 	struct amdgpu_bo **gtt_obj = NULL;
+	struct amdgpu_bo_param bp;
 	uint64_t gart_addr, vram_addr;
 	unsigned n, size;
 	int i, r;
@@ -58,9 +59,15 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		r = 1;
 		goto out_cleanup;
 	}
-
-	r = amdgpu_bo_create(adev, size, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, 0,
-			     ttm_bo_type_kernel, NULL, &vram_obj);
+	memset(&bp, 0, sizeof(bp));
+	bp.size = size;
+	bp.byte_align = PAGE_SIZE;
+	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
+	bp.flags = 0;
+	bp.type = ttm_bo_type_kernel;
+	bp.resv = NULL;
+
+	r = amdgpu_bo_create(adev, &bp, &vram_obj);
 	if (r) {
 		DRM_ERROR("Failed to create VRAM object\n");
 		goto out_cleanup;
@@ -79,9 +86,8 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		void **vram_start, **vram_end;
 		struct dma_fence *fence = NULL;
 
-		r = amdgpu_bo_create(adev, size, PAGE_SIZE,
-				     AMDGPU_GEM_DOMAIN_GTT, 0,
-				     ttm_bo_type_kernel, NULL, gtt_obj + i);
+		bp.domain = AMDGPU_GEM_DOMAIN_GTT;
+		r = amdgpu_bo_create(adev, &bp, gtt_obj + i);
 		if (r) {
 			DRM_ERROR("Failed to create GTT object %d\n", i);
 			goto out_lclean;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 532263ab6e16..e96e26d3f3b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -275,7 +275,7 @@ TRACE_EVENT(amdgpu_vm_bo_unmap,
 			     ),
 
 	    TP_fast_assign(
-			   __entry->bo = bo_va->base.bo;
+			   __entry->bo = bo_va ? bo_va->base.bo : NULL;
 			   __entry->start = mapping->start;
 			   __entry->last = mapping->last;
 			   __entry->offset = mapping->offset;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 205da3ff9cd0..e93a0a237dc3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -63,16 +63,44 @@ static void amdgpu_ttm_debugfs_fini(struct amdgpu_device *adev);
 /*
  * Global memory.
  */
+
+/**
+ * amdgpu_ttm_mem_global_init - Initialize and acquire reference to
+ * memory object
+ *
+ * @ref: Object for initialization.
+ *
+ * This is called by drm_global_item_ref() when an object is being
+ * initialized.
+ */
 static int amdgpu_ttm_mem_global_init(struct drm_global_reference *ref)
 {
 	return ttm_mem_global_init(ref->object);
 }
 
+/**
+ * amdgpu_ttm_mem_global_release - Drop reference to a memory object
+ *
+ * @ref: Object being removed
+ *
+ * This is called by drm_global_item_unref() when an object is being
+ * released.
+ */
 static void amdgpu_ttm_mem_global_release(struct drm_global_reference *ref)
 {
 	ttm_mem_global_release(ref->object);
 }
 
+/**
+ * amdgpu_ttm_global_init - Initialize global TTM memory reference
+ * 							structures.
+ *
+ * @adev:  	AMDGPU device for which the global structures need to be
+ *			registered.
+ *
+ * This is called as part of the AMDGPU ttm init from amdgpu_ttm_init()
+ * during bring up.
+ */
 static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 {
 	struct drm_global_reference *global_ref;
@@ -80,7 +108,9 @@ static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 	struct drm_sched_rq *rq;
 	int r;
 
+	/* ensure reference is false in case init fails */
 	adev->mman.mem_global_referenced = false;
+
 	global_ref = &adev->mman.mem_global_ref;
 	global_ref->global_type = DRM_GLOBAL_TTM_MEM;
 	global_ref->size = sizeof(struct ttm_mem_global);
@@ -111,7 +141,7 @@ static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 	ring = adev->mman.buffer_funcs_ring;
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
 	r = drm_sched_entity_init(&ring->sched, &adev->mman.entity,
-				  rq, amdgpu_sched_jobs, NULL);
+				  rq, NULL);
 	if (r) {
 		DRM_ERROR("Failed setting up TTM BO move run queue.\n");
 		goto error_entity;
@@ -146,6 +176,18 @@ static int amdgpu_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
 	return 0;
 }
 
+/**
+ * amdgpu_init_mem_type - 	Initialize a memory manager for a specific
+ * 							type of memory request.
+ *
+ * @bdev:	The TTM BO device object (contains a reference to
+ * 			amdgpu_device)
+ * @type:	The type of memory requested
+ * @man:
+ *
+ * This is called by ttm_bo_init_mm() when a buffer object is being
+ * initialized.
+ */
 static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 				struct ttm_mem_type_manager *man)
 {
@@ -161,6 +203,7 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 		man->default_caching = TTM_PL_FLAG_CACHED;
 		break;
 	case TTM_PL_TT:
+		/* GTT memory  */
 		man->func = &amdgpu_gtt_mgr_func;
 		man->gpu_offset = adev->gmc.gart_start;
 		man->available_caching = TTM_PL_MASK_CACHING;
@@ -193,6 +236,14 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 	return 0;
 }
 
+/**
+ * amdgpu_evict_flags - Compute placement flags
+ *
+ * @bo: The buffer object to evict
+ * @placement: Possible destination(s) for evicted BO
+ *
+ * Fill in placement data when ttm_bo_evict() is called
+ */
 static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 				struct ttm_placement *placement)
 {
@@ -204,12 +255,14 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 		.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM
 	};
 
+	/* Don't handle scatter gather BOs */
 	if (bo->type == ttm_bo_type_sg) {
 		placement->num_placement = 0;
 		placement->num_busy_placement = 0;
 		return;
 	}
 
+	/* Object isn't an AMDGPU object so ignore */
 	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo)) {
 		placement->placement = &placements;
 		placement->busy_placement = &placements;
@@ -217,26 +270,16 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 		placement->num_busy_placement = 1;
 		return;
 	}
+
 	abo = ttm_to_amdgpu_bo(bo);
 	switch (bo->mem.mem_type) {
 	case TTM_PL_VRAM:
 		if (!adev->mman.buffer_funcs_enabled) {
+			/* Move to system memory */
 			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
 		} else if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
-			   !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)) {
-			unsigned fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
-			struct drm_mm_node *node = bo->mem.mm_node;
-			unsigned long pages_left;
-
-			for (pages_left = bo->mem.num_pages;
-			     pages_left;
-			     pages_left -= node->size, node++) {
-				if (node->start < fpfn)
-					break;
-			}
-
-			if (!pages_left)
-				goto gtt;
+			   !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) &&
+			   amdgpu_bo_in_cpu_visible_vram(abo)) {
 
 			/* Try evicting to the CPU inaccessible part of VRAM
 			 * first, but only set GTT as busy placement, so this
@@ -245,12 +288,12 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			 */
 			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
 							 AMDGPU_GEM_DOMAIN_GTT);
-			abo->placements[0].fpfn = fpfn;
+			abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 			abo->placements[0].lpfn = 0;
 			abo->placement.busy_placement = &abo->placements[1];
 			abo->placement.num_busy_placement = 1;
 		} else {
-gtt:
+			/* Move to GTT memory */
 			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
 		}
 		break;
@@ -261,6 +304,15 @@ gtt:
 	*placement = abo->placement;
 }
 
+/**
+ * amdgpu_verify_access - Verify access for a mmap call
+ *
+ * @bo:		The buffer object to map
+ * @filp:	The file pointer from the process performing the mmap
+ *
+ * This is called by ttm_bo_mmap() to verify whether a process
+ * has the right to mmap a BO to their process space.
+ */
 static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
@@ -278,6 +330,15 @@ static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 					  filp->private_data);
 }
 
+/**
+ * amdgpu_move_null - Register memory for a buffer object
+ *
+ * @bo:			The bo to assign the memory to
+ * @new_mem:	The memory to be assigned.
+ *
+ * Assign the memory from new_mem to the memory of the buffer object
+ * bo.
+ */
 static void amdgpu_move_null(struct ttm_buffer_object *bo,
 			     struct ttm_mem_reg *new_mem)
 {
@@ -288,6 +349,10 @@ static void amdgpu_move_null(struct ttm_buffer_object *bo,
 	new_mem->mm_node = NULL;
 }
 
+/**
+ * amdgpu_mm_node_addr -	Compute the GPU relative offset of a GTT
+ * 							buffer.
+ */
 static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
 				    struct drm_mm_node *mm_node,
 				    struct ttm_mem_reg *mem)
@@ -302,9 +367,10 @@ static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
 }
 
 /**
- * amdgpu_find_mm_node - Helper function finds the drm_mm_node
- *  corresponding to @offset. It also modifies the offset to be
- *  within the drm_mm_node returned
+ * amdgpu_find_mm_node -	Helper function finds the drm_mm_node
+ *  						corresponding to @offset. It also modifies
+ * 							the offset to be within the drm_mm_node
+ * 							returned
  */
 static struct drm_mm_node *amdgpu_find_mm_node(struct ttm_mem_reg *mem,
 					       unsigned long *offset)
@@ -443,7 +509,12 @@ error:
 	return r;
 }
 
-
+/**
+ * amdgpu_move_blit - Copy an entire buffer to another buffer
+ *
+ * This is a helper called by amdgpu_bo_move() and
+ * amdgpu_move_vram_ram() to help move buffers to and from VRAM.
+ */
 static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 			    bool evict, bool no_wait_gpu,
 			    struct ttm_mem_reg *new_mem,
@@ -478,6 +549,11 @@ error:
 	return r;
 }
 
+/**
+ * amdgpu_move_vram_ram - Copy VRAM buffer to RAM buffer
+ *
+ * Called by amdgpu_bo_move().
+ */
 static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 				struct ttm_operation_ctx *ctx,
 				struct ttm_mem_reg *new_mem)
@@ -490,6 +566,8 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 	int r;
 
 	adev = amdgpu_ttm_adev(bo->bdev);
+
+	/* create space/pages for new_mem in GTT space */
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
 	placement.num_placement = 1;
@@ -504,25 +582,36 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 		return r;
 	}
 
+	/* set caching flags */
 	r = ttm_tt_set_placement_caching(bo->ttm, tmp_mem.placement);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
 
+	/* Bind the memory to the GTT space */
 	r = ttm_tt_bind(bo->ttm, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
+
+	/* blit VRAM to GTT */
 	r = amdgpu_move_blit(bo, true, ctx->no_wait_gpu, &tmp_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
+
+	/* move BO (in tmp_mem) to new_mem */
 	r = ttm_bo_move_ttm(bo, ctx, new_mem);
 out_cleanup:
 	ttm_bo_mem_put(bo, &tmp_mem);
 	return r;
 }
 
+/**
+ * amdgpu_move_ram_vram - Copy buffer from RAM to VRAM
+ *
+ * Called by amdgpu_bo_move().
+ */
 static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 				struct ttm_operation_ctx *ctx,
 				struct ttm_mem_reg *new_mem)
@@ -535,6 +624,8 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 	int r;
 
 	adev = amdgpu_ttm_adev(bo->bdev);
+
+	/* make space in GTT for old_mem buffer */
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
 	placement.num_placement = 1;
@@ -548,10 +639,14 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 	if (unlikely(r)) {
 		return r;
 	}
+
+	/* move/bind old memory to GTT space */
 	r = ttm_bo_move_ttm(bo, ctx, &tmp_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
+
+	/* copy to VRAM */
 	r = amdgpu_move_blit(bo, true, ctx->no_wait_gpu, new_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
@@ -561,6 +656,11 @@ out_cleanup:
 	return r;
 }
 
+/**
+ * amdgpu_bo_move - Move a buffer object to a new memory location
+ *
+ * Called by ttm_bo_handle_move_mem()
+ */
 static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			  struct ttm_operation_ctx *ctx,
 			  struct ttm_mem_reg *new_mem)
@@ -626,6 +726,11 @@ memcpy:
 	return 0;
 }
 
+/**
+ * amdgpu_ttm_io_mem_reserve - Reserve a block of memory during a fault
+ *
+ * Called by ttm_mem_io_reserve() ultimately via ttm_bo_vm_fault()
+ */
 static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
 {
 	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
@@ -695,7 +800,7 @@ struct amdgpu_ttm_tt {
 	struct ttm_dma_tt	ttm;
 	u64			offset;
 	uint64_t		userptr;
-	struct mm_struct	*usermm;
+	struct task_struct	*usertask;
 	uint32_t		userflags;
 	spinlock_t              guptasklock;
 	struct list_head        guptasks;
@@ -703,17 +808,29 @@ struct amdgpu_ttm_tt {
 	uint32_t		last_set_pages;
 };
 
+/**
+ * amdgpu_ttm_tt_get_user_pages - 	Pin pages of memory pointed to
+ * 									by a USERPTR pointer to memory
+ *
+ * Called by amdgpu_gem_userptr_ioctl() and amdgpu_cs_parser_bos().
+ * This provides a wrapper around the get_user_pages() call to provide
+ * device accessible pages that back user memory.
+ */
 int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct mm_struct *mm = gtt->usertask->mm;
 	unsigned int flags = 0;
 	unsigned pinned = 0;
 	int r;
 
+	if (!mm) /* Happens during process shutdown */
+		return -ESRCH;
+
 	if (!(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY))
 		flags |= FOLL_WRITE;
 
-	down_read(&current->mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 
 	if (gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) {
 		/* check that we only use anonymous memory
@@ -721,13 +838,14 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 		unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE;
 		struct vm_area_struct *vma;
 
-		vma = find_vma(gtt->usermm, gtt->userptr);
+		vma = find_vma(mm, gtt->userptr);
 		if (!vma || vma->vm_file || vma->vm_end < end) {
-			up_read(&current->mm->mmap_sem);
+			up_read(&mm->mmap_sem);
 			return -EPERM;
 		}
 	}
 
+	/* loop enough times using contiguous pages of memory */
 	do {
 		unsigned num_pages = ttm->num_pages - pinned;
 		uint64_t userptr = gtt->userptr + pinned * PAGE_SIZE;
@@ -739,7 +857,12 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 		list_add(&guptask.list, &gtt->guptasks);
 		spin_unlock(&gtt->guptasklock);
 
-		r = get_user_pages(userptr, num_pages, flags, p, NULL);
+		if (mm == current->mm)
+			r = get_user_pages(userptr, num_pages, flags, p, NULL);
+		else
+			r = get_user_pages_remote(gtt->usertask,
+					mm, userptr, num_pages,
+					flags, p, NULL, NULL);
 
 		spin_lock(&gtt->guptasklock);
 		list_del(&guptask.list);
@@ -752,15 +875,23 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 
 	} while (pinned < ttm->num_pages);
 
-	up_read(&current->mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 	return 0;
 
 release_pages:
 	release_pages(pages, pinned);
-	up_read(&current->mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 	return r;
 }
 
+/**
+ * amdgpu_ttm_tt_set_user_pages - 	Copy pages in, putting old pages
+ * 									as necessary.
+ *
+ * Called by amdgpu_cs_list_validate().  This creates the page list
+ * that backs user memory and will ultimately be mapped into the device
+ * address space.
+ */
 void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
@@ -775,6 +906,11 @@ void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages)
 	}
 }
 
+/**
+ * amdgpu_ttm_tt_mark_user_page - Mark pages as dirty
+ *
+ * Called while unpinning userptr pages
+ */
 void amdgpu_ttm_tt_mark_user_pages(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
@@ -793,7 +929,12 @@ void amdgpu_ttm_tt_mark_user_pages(struct ttm_tt *ttm)
 	}
 }
 
-/* prepare the sg table with the user pages */
+/**
+ * amdgpu_ttm_tt_pin_userptr - 	prepare the sg table with the
+ * 								user pages
+ *
+ * Called by amdgpu_ttm_backend_bind()
+ **/
 static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
@@ -805,17 +946,20 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm)
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
 
+	/* Allocate an SG array and squash pages into it */
 	r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0,
 				      ttm->num_pages << PAGE_SHIFT,
 				      GFP_KERNEL);
 	if (r)
 		goto release_sg;
 
+	/* Map SG to device */
 	r = -ENOMEM;
 	nents = dma_map_sg(adev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
 	if (nents != ttm->sg->nents)
 		goto release_sg;
 
+	/* convert SG to linear array of pages and dma addresses */
 	drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 					 gtt->ttm.dma_address, ttm->num_pages);
 
@@ -826,6 +970,9 @@ release_sg:
 	return r;
 }
 
+/**
+ * amdgpu_ttm_tt_unpin_userptr - Unpin and unmap userptr pages
+ */
 static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
@@ -839,14 +986,60 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 	if (!ttm->sg->sgl)
 		return;
 
-	/* free the sg table and pages again */
+	/* unmap the pages mapped to the device */
 	dma_unmap_sg(adev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
 
+	/* mark the pages as dirty */
 	amdgpu_ttm_tt_mark_user_pages(ttm);
 
 	sg_free_table(ttm->sg);
 }
 
+int amdgpu_ttm_gart_bind(struct amdgpu_device *adev,
+				struct ttm_buffer_object *tbo,
+				uint64_t flags)
+{
+	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(tbo);
+	struct ttm_tt *ttm = tbo->ttm;
+	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	int r;
+
+	if (abo->flags & AMDGPU_GEM_CREATE_MQD_GFX9) {
+		uint64_t page_idx = 1;
+
+		r = amdgpu_gart_bind(adev, gtt->offset, page_idx,
+				ttm->pages, gtt->ttm.dma_address, flags);
+		if (r)
+			goto gart_bind_fail;
+
+		/* Patch mtype of the second part BO */
+		flags &=  ~AMDGPU_PTE_MTYPE_MASK;
+		flags |= AMDGPU_PTE_MTYPE(AMDGPU_MTYPE_NC);
+
+		r = amdgpu_gart_bind(adev,
+				gtt->offset + (page_idx << PAGE_SHIFT),
+				ttm->num_pages - page_idx,
+				&ttm->pages[page_idx],
+				&(gtt->ttm.dma_address[page_idx]), flags);
+	} else {
+		r = amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages,
+				     ttm->pages, gtt->ttm.dma_address, flags);
+	}
+
+gart_bind_fail:
+	if (r)
+		DRM_ERROR("failed to bind %lu pages at 0x%08llX\n",
+			  ttm->num_pages, gtt->offset);
+
+	return r;
+}
+
+/**
+ * amdgpu_ttm_backend_bind - Bind GTT memory
+ *
+ * Called by ttm_tt_bind() on behalf of ttm_bo_handle_move_mem().
+ * This handles binding GTT memory to the device address space.
+ */
 static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
 				   struct ttm_mem_reg *bo_mem)
 {
@@ -877,7 +1070,10 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
 		return 0;
 	}
 
+	/* compute PTE flags relevant to this BO memory */
 	flags = amdgpu_ttm_tt_pte_flags(adev, ttm, bo_mem);
+
+	/* bind pages into GART page tables */
 	gtt->offset = (u64)bo_mem->start << PAGE_SHIFT;
 	r = amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages,
 		ttm->pages, gtt->ttm.dma_address, flags);
@@ -888,6 +1084,9 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
 	return r;
 }
 
+/**
+ * amdgpu_ttm_alloc_gart - Allocate GART memory for buffer object
+ */
 int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
@@ -903,6 +1102,7 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 	    amdgpu_gtt_mgr_has_gart_addr(&bo->mem))
 		return 0;
 
+	/* allocate GTT space */
 	tmp = bo->mem;
 	tmp.mm_node = NULL;
 	placement.num_placement = 1;
@@ -918,10 +1118,12 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 	if (unlikely(r))
 		return r;
 
+	/* compute PTE flags for this buffer object */
 	flags = amdgpu_ttm_tt_pte_flags(adev, bo->ttm, &tmp);
+
+	/* Bind pages */
 	gtt->offset = (u64)tmp.start << PAGE_SHIFT;
-	r = amdgpu_gart_bind(adev, gtt->offset, bo->ttm->num_pages,
-			     bo->ttm->pages, gtt->ttm.dma_address, flags);
+	r = amdgpu_ttm_gart_bind(adev, bo, flags);
 	if (unlikely(r)) {
 		ttm_bo_mem_put(bo, &tmp);
 		return r;
@@ -935,31 +1137,40 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 	return 0;
 }
 
+/**
+ * amdgpu_ttm_recover_gart - Rebind GTT pages
+ *
+ * Called by amdgpu_gtt_mgr_recover() from amdgpu_device_reset() to
+ * rebind GTT pages during a GPU reset.
+ */
 int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)tbo->ttm;
 	uint64_t flags;
 	int r;
 
-	if (!gtt)
+	if (!tbo->ttm)
 		return 0;
 
-	flags = amdgpu_ttm_tt_pte_flags(adev, &gtt->ttm.ttm, &tbo->mem);
-	r = amdgpu_gart_bind(adev, gtt->offset, gtt->ttm.ttm.num_pages,
-			     gtt->ttm.ttm.pages, gtt->ttm.dma_address, flags);
-	if (r)
-		DRM_ERROR("failed to bind %lu pages at 0x%08llX\n",
-			  gtt->ttm.ttm.num_pages, gtt->offset);
+	flags = amdgpu_ttm_tt_pte_flags(adev, tbo->ttm, &tbo->mem);
+	r = amdgpu_ttm_gart_bind(adev, tbo, flags);
+
 	return r;
 }
 
+/**
+ * amdgpu_ttm_backend_unbind - Unbind GTT mapped pages
+ *
+ * Called by ttm_tt_unbind() on behalf of ttm_bo_move_ttm() and
+ * ttm_tt_destroy().
+ */
 static int amdgpu_ttm_backend_unbind(struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	int r;
 
+	/* if the pages have userptr pinning then clear that first */
 	if (gtt->userptr)
 		amdgpu_ttm_tt_unpin_userptr(ttm);
 
@@ -978,6 +1189,9 @@ static void amdgpu_ttm_backend_destroy(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 
+	if (gtt->usertask)
+		put_task_struct(gtt->usertask);
+
 	ttm_dma_tt_fini(&gtt->ttm);
 	kfree(gtt);
 }
@@ -988,6 +1202,13 @@ static struct ttm_backend_func amdgpu_backend_func = {
 	.destroy = &amdgpu_ttm_backend_destroy,
 };
 
+/**
+ * amdgpu_ttm_tt_create - Create a ttm_tt object for a given BO
+ *
+ * @bo: The buffer object to create a GTT ttm_tt object around
+ *
+ * Called by ttm_tt_create().
+ */
 static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
 					   uint32_t page_flags)
 {
@@ -1001,6 +1222,8 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
 		return NULL;
 	}
 	gtt->ttm.ttm.func = &amdgpu_backend_func;
+
+	/* allocate space for the uninitialized page entries */
 	if (ttm_sg_tt_init(&gtt->ttm, bo, page_flags)) {
 		kfree(gtt);
 		return NULL;
@@ -1008,6 +1231,12 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
 	return &gtt->ttm.ttm;
 }
 
+/**
+ * amdgpu_ttm_tt_populate - Map GTT pages visible to the device
+ *
+ * Map the pages of a ttm_tt object to an address space visible
+ * to the underlying device.
+ */
 static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
 			struct ttm_operation_ctx *ctx)
 {
@@ -1015,6 +1244,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
 
+	/* user pages are bound by amdgpu_ttm_tt_pin_userptr() */
 	if (gtt && gtt->userptr) {
 		ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
 		if (!ttm->sg)
@@ -1039,9 +1269,17 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
 	}
 #endif
 
+	/* fall back to generic helper to populate the page array
+	 * and map them to the device */
 	return ttm_populate_and_map_pages(adev->dev, &gtt->ttm, ctx);
 }
 
+/**
+ * amdgpu_ttm_tt_unpopulate - unmap GTT pages and unpopulate page arrays
+ *
+ * Unmaps pages of a ttm_tt object from the device address space and
+ * unpopulates the page array backing it.
+ */
 static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev;
@@ -1067,9 +1305,21 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	}
 #endif
 
+	/* fall back to generic helper to unmap and unpopulate array */
 	ttm_unmap_and_unpopulate_pages(adev->dev, &gtt->ttm);
 }
 
+/**
+ * amdgpu_ttm_tt_set_userptr -	Initialize userptr GTT ttm_tt
+ * 								for the current task
+ *
+ * @ttm: The ttm_tt object to bind this userptr object to
+ * @addr:  The address in the current tasks VM space to use
+ * @flags: Requirements of userptr object.
+ *
+ * Called by amdgpu_gem_userptr_ioctl() to bind userptr pages
+ * to current task
+ */
 int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
 			      uint32_t flags)
 {
@@ -1079,8 +1329,13 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
 		return -EINVAL;
 
 	gtt->userptr = addr;
-	gtt->usermm = current->mm;
 	gtt->userflags = flags;
+
+	if (gtt->usertask)
+		put_task_struct(gtt->usertask);
+	gtt->usertask = current->group_leader;
+	get_task_struct(gtt->usertask);
+
 	spin_lock_init(&gtt->guptasklock);
 	INIT_LIST_HEAD(&gtt->guptasks);
 	atomic_set(&gtt->mmu_invalidations, 0);
@@ -1089,6 +1344,9 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
 	return 0;
 }
 
+/**
+ * amdgpu_ttm_tt_get_usermm - Return memory manager for ttm_tt object
+ */
 struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
@@ -1096,9 +1354,18 @@ struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 	if (gtt == NULL)
 		return NULL;
 
-	return gtt->usermm;
+	if (gtt->usertask == NULL)
+		return NULL;
+
+	return gtt->usertask->mm;
 }
 
+/**
+ * amdgpu_ttm_tt_affect_userptr -	Determine if a ttm_tt object lays
+ * 									inside an address range for the
+ * 									current task.
+ *
+ */
 bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 				  unsigned long end)
 {
@@ -1109,10 +1376,16 @@ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 	if (gtt == NULL || !gtt->userptr)
 		return false;
 
+	/* Return false if no part of the ttm_tt object lies within
+	 * the range
+	 */
 	size = (unsigned long)gtt->ttm.ttm.num_pages * PAGE_SIZE;
 	if (gtt->userptr > end || gtt->userptr + size <= start)
 		return false;
 
+	/* Search the lists of tasks that hold this mapping and see
+	 * if current is one of them.  If it is return false.
+	 */
 	spin_lock(&gtt->guptasklock);
 	list_for_each_entry(entry, &gtt->guptasks, list) {
 		if (entry->task == current) {
@@ -1127,6 +1400,10 @@ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 	return true;
 }
 
+/**
+ * amdgpu_ttm_tt_userptr_invalidated -	Has the ttm_tt object been
+ * 										invalidated?
+ */
 bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
 				       int *last_invalidated)
 {
@@ -1137,6 +1414,12 @@ bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
 	return prev_invalidated != *last_invalidated;
 }
 
+/**
+ * amdgpu_ttm_tt_userptr_needs_pages -	Have the pages backing this
+ * 										ttm_tt object been invalidated
+ * 										since the last time they've
+ * 										been set?
+ */
 bool amdgpu_ttm_tt_userptr_needs_pages(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
@@ -1147,6 +1430,9 @@ bool amdgpu_ttm_tt_userptr_needs_pages(struct ttm_tt *ttm)
 	return atomic_read(&gtt->mmu_invalidations) != gtt->last_set_pages;
 }
 
+/**
+ * amdgpu_ttm_tt_is_readonly - Is the ttm_tt object read only?
+ */
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
@@ -1157,6 +1443,12 @@ bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 	return !!(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
 }
 
+/**
+ * amdgpu_ttm_tt_pte_flags - Compute PTE flags for ttm_tt object
+ *
+ * @ttm: The ttm_tt object to compute the flags for
+ * @mem: The memory registry backing this ttm_tt object
+ */
 uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 				 struct ttm_mem_reg *mem)
 {
@@ -1181,6 +1473,16 @@ uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 	return flags;
 }
 
+/**
+ * amdgpu_ttm_bo_eviction_valuable -	Check to see if we can evict
+ * 										a buffer object.
+ *
+ * Return true if eviction is sensible.  Called by
+ * ttm_mem_evict_first() on behalf of ttm_bo_mem_force_space()
+ * which tries to evict buffer objects until it can find space
+ * for a new object and by ttm_bo_force_list_clean() which is
+ * used to clean out a memory space.
+ */
 static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 					    const struct ttm_place *place)
 {
@@ -1227,6 +1529,19 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 	return ttm_bo_eviction_valuable(bo, place);
 }
 
+/**
+ * amdgpu_ttm_access_memory -	Read or Write memory that backs a
+ * 								buffer object.
+ *
+ * @bo:  The buffer object to read/write
+ * @offset:  Offset into buffer object
+ * @buf:  Secondary buffer to write/read from
+ * @len: Length in bytes of access
+ * @write:  true if writing
+ *
+ * This is used to access VRAM that backs a buffer object via MMIO
+ * access for debugging purposes.
+ */
 static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 				    unsigned long offset,
 				    void *buf, int len, int write)
@@ -1329,6 +1644,7 @@ static void amdgpu_ttm_fw_reserve_vram_fini(struct amdgpu_device *adev)
 static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
 {
 	struct ttm_operation_ctx ctx = { false, false };
+	struct amdgpu_bo_param bp;
 	int r = 0;
 	int i;
 	u64 vram_size = adev->gmc.visible_vram_size;
@@ -1336,17 +1652,21 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
 	u64 size = adev->fw_vram_usage.size;
 	struct amdgpu_bo *bo;
 
+	memset(&bp, 0, sizeof(bp));
+	bp.size = adev->fw_vram_usage.size;
+	bp.byte_align = PAGE_SIZE;
+	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
+	bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
+		AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+	bp.type = ttm_bo_type_kernel;
+	bp.resv = NULL;
 	adev->fw_vram_usage.va = NULL;
 	adev->fw_vram_usage.reserved_bo = NULL;
 
 	if (adev->fw_vram_usage.size > 0 &&
 		adev->fw_vram_usage.size <= vram_size) {
 
-		r = amdgpu_bo_create(adev, adev->fw_vram_usage.size, PAGE_SIZE,
-				     AMDGPU_GEM_DOMAIN_VRAM,
-				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-				     AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
-				     ttm_bo_type_kernel, NULL,
+		r = amdgpu_bo_create(adev, &bp,
 				     &adev->fw_vram_usage.reserved_bo);
 		if (r)
 			goto error_create;
@@ -1398,13 +1718,22 @@ error_create:
 	adev->fw_vram_usage.reserved_bo = NULL;
 	return r;
 }
-
+/**
+ * amdgpu_ttm_init -	Init the memory management (ttm) as well as
+ * 						various gtt/vram related fields.
+ *
+ * This initializes all of the memory space pools that the TTM layer
+ * will need such as the GTT space (system memory mapped to the device),
+ * VRAM (on-board memory), and on-chip memories (GDS, GWS, OA) which
+ * can be mapped per VMID.
+ */
 int amdgpu_ttm_init(struct amdgpu_device *adev)
 {
 	uint64_t gtt_size;
 	int r;
 	u64 vis_vram_limit;
 
+	/* initialize global references for vram/gtt */
 	r = amdgpu_ttm_global_init(adev);
 	if (r) {
 		return r;
@@ -1425,6 +1754,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	/* We opt to avoid OOM on system pages allocations */
 	adev->mman.bdev.no_retry = true;
 
+	/* Initialize VRAM pool with all of VRAM divided into pages */
 	r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_VRAM,
 				adev->gmc.real_vram_size >> PAGE_SHIFT);
 	if (r) {
@@ -1454,15 +1784,23 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	r = amdgpu_bo_create_kernel(adev, adev->gmc.stolen_size, PAGE_SIZE,
-				    AMDGPU_GEM_DOMAIN_VRAM,
-				    &adev->stolen_vga_memory,
-				    NULL, NULL);
-	if (r)
-		return r;
+	/* allocate memory as required for VGA
+	 * This is used for VGA emulation and pre-OS scanout buffers to
+	 * avoid display artifacts while transitioning between pre-OS
+	 * and driver.  */
+	if (adev->gmc.stolen_size) {
+		r = amdgpu_bo_create_kernel(adev, adev->gmc.stolen_size, PAGE_SIZE,
+					    AMDGPU_GEM_DOMAIN_VRAM,
+					    &adev->stolen_vga_memory,
+					    NULL, NULL);
+		if (r)
+			return r;
+	}
 	DRM_INFO("amdgpu: %uM of VRAM memory ready\n",
 		 (unsigned) (adev->gmc.real_vram_size / (1024 * 1024)));
 
+	/* Compute GTT size, either bsaed on 3/4th the size of RAM size
+	 * or whatever the user passed on module init */
 	if (amdgpu_gtt_size == -1) {
 		struct sysinfo si;
 
@@ -1473,6 +1811,8 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	}
 	else
 		gtt_size = (uint64_t)amdgpu_gtt_size << 20;
+
+	/* Initialize GTT memory pool */
 	r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_TT, gtt_size >> PAGE_SHIFT);
 	if (r) {
 		DRM_ERROR("Failed initializing GTT heap.\n");
@@ -1481,6 +1821,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	DRM_INFO("amdgpu: %uM of GTT memory ready.\n",
 		 (unsigned)(gtt_size / (1024 * 1024)));
 
+	/* Initialize various on-chip memory pools */
 	adev->gds.mem.total_size = adev->gds.mem.total_size << AMDGPU_GDS_SHIFT;
 	adev->gds.mem.gfx_partition_size = adev->gds.mem.gfx_partition_size << AMDGPU_GDS_SHIFT;
 	adev->gds.mem.cs_partition_size = adev->gds.mem.cs_partition_size << AMDGPU_GDS_SHIFT;
@@ -1520,6 +1861,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 		}
 	}
 
+	/* Register debugfs entries for amdgpu_ttm */
 	r = amdgpu_ttm_debugfs_init(adev);
 	if (r) {
 		DRM_ERROR("Failed to init debugfs\n");
@@ -1528,13 +1870,25 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_ttm_late_init -	Handle any late initialization for
+ * 							amdgpu_ttm
+ */
+void amdgpu_ttm_late_init(struct amdgpu_device *adev)
+{
+	/* return the VGA stolen memory (if any) back to VRAM */
+	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL);
+}
+
+/**
+ * amdgpu_ttm_fini - De-initialize the TTM memory pools
+ */
 void amdgpu_ttm_fini(struct amdgpu_device *adev)
 {
 	if (!adev->mman.initialized)
 		return;
 
 	amdgpu_ttm_debugfs_fini(adev);
-	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL);
 	amdgpu_ttm_fw_reserve_vram_fini(adev);
 	if (adev->mman.aper_base_kaddr)
 		iounmap(adev->mman.aper_base_kaddr);
@@ -1856,6 +2210,11 @@ static const struct drm_info_list amdgpu_ttm_debugfs_list[] = {
 #endif
 };
 
+/**
+ * amdgpu_ttm_vram_read - Linear read access to VRAM
+ *
+ * Accesses VRAM via MMIO for debugging purposes.
+ */
 static ssize_t amdgpu_ttm_vram_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1895,6 +2254,11 @@ static ssize_t amdgpu_ttm_vram_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/**
+ * amdgpu_ttm_vram_write - Linear write access to VRAM
+ *
+ * Accesses VRAM via MMIO for debugging purposes.
+ */
 static ssize_t amdgpu_ttm_vram_write(struct file *f, const char __user *buf,
 				    size_t size, loff_t *pos)
 {
@@ -1943,6 +2307,9 @@ static const struct file_operations amdgpu_ttm_vram_fops = {
 
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 
+/**
+ * amdgpu_ttm_gtt_read - Linear read access to GTT memory
+ */
 static ssize_t amdgpu_ttm_gtt_read(struct file *f, char __user *buf,
 				   size_t size, loff_t *pos)
 {
@@ -1990,6 +2357,13 @@ static const struct file_operations amdgpu_ttm_gtt_fops = {
 
 #endif
 
+/**
+ * amdgpu_iomem_read - Virtual read access to GPU mapped memory
+ *
+ * This function is used to read memory that has been mapped to the
+ * GPU and the known addresses are not physical addresses but instead
+ * bus addresses (e.g., what you'd put in an IB or ring buffer).
+ */
 static ssize_t amdgpu_iomem_read(struct file *f, char __user *buf,
 				 size_t size, loff_t *pos)
 {
@@ -1998,6 +2372,7 @@ static ssize_t amdgpu_iomem_read(struct file *f, char __user *buf,
 	ssize_t result = 0;
 	int r;
 
+	/* retrieve the IOMMU domain if any for this device */
 	dom = iommu_get_domain_for_dev(adev->dev);
 
 	while (size) {
@@ -2010,6 +2385,10 @@ static ssize_t amdgpu_iomem_read(struct file *f, char __user *buf,
 
 		bytes = bytes < size ? bytes : size;
 
+		/* Translate the bus address to a physical address.  If
+		 * the domain is NULL it means there is no IOMMU active
+		 * and the address translation is the identity
+		 */
 		addr = dom ? iommu_iova_to_phys(dom, addr) : addr;
 
 		pfn = addr >> PAGE_SHIFT;
@@ -2034,6 +2413,13 @@ static ssize_t amdgpu_iomem_read(struct file *f, char __user *buf,
 	return result;
 }
 
+/**
+ * amdgpu_iomem_write - Virtual write access to GPU mapped memory
+ *
+ * This function is used to write memory that has been mapped to the
+ * GPU and the known addresses are not physical addresses but instead
+ * bus addresses (e.g., what you'd put in an IB or ring buffer).
+ */
 static ssize_t amdgpu_iomem_write(struct file *f, const char __user *buf,
 				 size_t size, loff_t *pos)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 6ea7de863041..e969c879d87e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -77,6 +77,7 @@ uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
 uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
 
 int amdgpu_ttm_init(struct amdgpu_device *adev);
+void amdgpu_ttm_late_init(struct amdgpu_device *adev);
 void amdgpu_ttm_fini(struct amdgpu_device *adev);
 void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev,
 					bool enable);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 5916cc25e28b..f55f72a37ca8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -161,8 +161,38 @@ void amdgpu_ucode_print_rlc_hdr(const struct common_firmware_header *hdr)
 			  le32_to_cpu(rlc_hdr->reg_list_format_separate_array_offset_bytes));
 		DRM_DEBUG("reg_list_separate_size_bytes: %u\n",
 			  le32_to_cpu(rlc_hdr->reg_list_separate_size_bytes));
-		DRM_DEBUG("reg_list_separate_size_bytes: %u\n",
-			  le32_to_cpu(rlc_hdr->reg_list_separate_size_bytes));
+		DRM_DEBUG("reg_list_separate_array_offset_bytes: %u\n",
+			  le32_to_cpu(rlc_hdr->reg_list_separate_array_offset_bytes));
+		if (version_minor == 1) {
+			const struct rlc_firmware_header_v2_1 *v2_1 =
+				container_of(rlc_hdr, struct rlc_firmware_header_v2_1, v2_0);
+			DRM_DEBUG("reg_list_format_direct_reg_list_length: %u\n",
+				  le32_to_cpu(v2_1->reg_list_format_direct_reg_list_length));
+			DRM_DEBUG("save_restore_list_cntl_ucode_ver: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_cntl_ucode_ver));
+			DRM_DEBUG("save_restore_list_cntl_feature_ver: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_cntl_feature_ver));
+			DRM_DEBUG("save_restore_list_cntl_size_bytes %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_cntl_size_bytes));
+			DRM_DEBUG("save_restore_list_cntl_offset_bytes: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_cntl_offset_bytes));
+			DRM_DEBUG("save_restore_list_gpm_ucode_ver: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_gpm_ucode_ver));
+			DRM_DEBUG("save_restore_list_gpm_feature_ver: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_gpm_feature_ver));
+			DRM_DEBUG("save_restore_list_gpm_size_bytes %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_gpm_size_bytes));
+			DRM_DEBUG("save_restore_list_gpm_offset_bytes: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_gpm_offset_bytes));
+			DRM_DEBUG("save_restore_list_srm_ucode_ver: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_srm_ucode_ver));
+			DRM_DEBUG("save_restore_list_srm_feature_ver: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_srm_feature_ver));
+			DRM_DEBUG("save_restore_list_srm_size_bytes %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_srm_size_bytes));
+			DRM_DEBUG("save_restore_list_srm_offset_bytes: %u\n",
+				  le32_to_cpu(v2_1->save_restore_list_srm_offset_bytes));
+		}
 	} else {
 		DRM_ERROR("Unknown RLC ucode version: %u.%u\n", version_major, version_minor);
 	}
@@ -265,6 +295,7 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type)
 	case CHIP_POLARIS10:
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 		if (!load_type)
 			return AMDGPU_FW_LOAD_DIRECT;
 		else
@@ -276,6 +307,8 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type)
 			return AMDGPU_FW_LOAD_DIRECT;
 		else
 			return AMDGPU_FW_LOAD_PSP;
+	case CHIP_VEGA20:
+		return AMDGPU_FW_LOAD_DIRECT;
 	default:
 		DRM_ERROR("Unknown firmware load type\n");
 	}
@@ -307,7 +340,10 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 	    (ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC1 &&
 	     ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC2 &&
 	     ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC1_JT &&
-	     ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC2_JT)) {
+	     ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC2_JT &&
+	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL &&
+	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM &&
+	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM)) {
 		ucode->ucode_size = le32_to_cpu(header->ucode_size_bytes);
 
 		memcpy(ucode->kaddr, (void *)((uint8_t *)ucode->fw->data +
@@ -329,6 +365,18 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 					      le32_to_cpu(header->ucode_array_offset_bytes) +
 					      le32_to_cpu(cp_hdr->jt_offset) * 4),
 		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL) {
+		ucode->ucode_size = adev->gfx.rlc.save_restore_list_cntl_size_bytes;
+		memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_cntl,
+		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM) {
+		ucode->ucode_size = adev->gfx.rlc.save_restore_list_gpm_size_bytes;
+		memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_gpm,
+		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM) {
+		ucode->ucode_size = adev->gfx.rlc.save_restore_list_srm_size_bytes;
+		memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_srm,
+		       ucode->ucode_size);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 30b5500dc152..08e38579af24 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -98,6 +98,24 @@ struct rlc_firmware_header_v2_0 {
 	uint32_t reg_list_separate_array_offset_bytes; /* payload offset from the start of the header */
 };
 
+/* version_major=2, version_minor=1 */
+struct rlc_firmware_header_v2_1 {
+	struct rlc_firmware_header_v2_0 v2_0;
+	uint32_t reg_list_format_direct_reg_list_length; /* length of direct reg list format array */
+	uint32_t save_restore_list_cntl_ucode_ver;
+	uint32_t save_restore_list_cntl_feature_ver;
+	uint32_t save_restore_list_cntl_size_bytes;
+	uint32_t save_restore_list_cntl_offset_bytes;
+	uint32_t save_restore_list_gpm_ucode_ver;
+	uint32_t save_restore_list_gpm_feature_ver;
+	uint32_t save_restore_list_gpm_size_bytes;
+	uint32_t save_restore_list_gpm_offset_bytes;
+	uint32_t save_restore_list_srm_ucode_ver;
+	uint32_t save_restore_list_srm_feature_ver;
+	uint32_t save_restore_list_srm_size_bytes;
+	uint32_t save_restore_list_srm_offset_bytes;
+};
+
 /* version_major=1, version_minor=0 */
 struct sdma_firmware_header_v1_0 {
 	struct common_firmware_header header;
@@ -148,6 +166,7 @@ union amdgpu_firmware_header {
 	struct gfx_firmware_header_v1_0 gfx;
 	struct rlc_firmware_header_v1_0 rlc;
 	struct rlc_firmware_header_v2_0 rlc_v2_0;
+	struct rlc_firmware_header_v2_1 rlc_v2_1;
 	struct sdma_firmware_header_v1_0 sdma;
 	struct sdma_firmware_header_v1_1 sdma_v1_1;
 	struct gpu_info_firmware_header_v1_0 gpu_info;
@@ -168,6 +187,9 @@ enum AMDGPU_UCODE_ID {
 	AMDGPU_UCODE_ID_CP_MEC2,
 	AMDGPU_UCODE_ID_CP_MEC2_JT,
 	AMDGPU_UCODE_ID_RLC_G,
+	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL,
+	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM,
+	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM,
 	AMDGPU_UCODE_ID_STORAGE,
 	AMDGPU_UCODE_ID_SMC,
 	AMDGPU_UCODE_ID_UVD,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 627542b22ae4..bcf68f80bbf0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -66,15 +66,18 @@
 #define FIRMWARE_POLARIS10	"amdgpu/polaris10_uvd.bin"
 #define FIRMWARE_POLARIS11	"amdgpu/polaris11_uvd.bin"
 #define FIRMWARE_POLARIS12	"amdgpu/polaris12_uvd.bin"
+#define FIRMWARE_VEGAM		"amdgpu/vegam_uvd.bin"
 
 #define FIRMWARE_VEGA10		"amdgpu/vega10_uvd.bin"
 #define FIRMWARE_VEGA12		"amdgpu/vega12_uvd.bin"
+#define FIRMWARE_VEGA20		"amdgpu/vega20_uvd.bin"
 
-#define mmUVD_GPCOM_VCPU_DATA0_VEGA10 (0x03c4 + 0x7e00)
-#define mmUVD_GPCOM_VCPU_DATA1_VEGA10 (0x03c5 + 0x7e00)
-#define mmUVD_GPCOM_VCPU_CMD_VEGA10 (0x03c3 + 0x7e00)
-#define mmUVD_NO_OP_VEGA10 (0x03ff + 0x7e00)
-#define mmUVD_ENGINE_CNTL_VEGA10 (0x03c6 + 0x7e00)
+/* These are common relative offsets for all asics, from uvd_7_0_offset.h,  */
+#define UVD_GPCOM_VCPU_CMD		0x03c3
+#define UVD_GPCOM_VCPU_DATA0	0x03c4
+#define UVD_GPCOM_VCPU_DATA1	0x03c5
+#define UVD_NO_OP				0x03ff
+#define UVD_BASE_SI				0x3800
 
 /**
  * amdgpu_uvd_cs_ctx - Command submission parser context
@@ -109,9 +112,11 @@ MODULE_FIRMWARE(FIRMWARE_STONEY);
 MODULE_FIRMWARE(FIRMWARE_POLARIS10);
 MODULE_FIRMWARE(FIRMWARE_POLARIS11);
 MODULE_FIRMWARE(FIRMWARE_POLARIS12);
+MODULE_FIRMWARE(FIRMWARE_VEGAM);
 
 MODULE_FIRMWARE(FIRMWARE_VEGA10);
 MODULE_FIRMWARE(FIRMWARE_VEGA12);
+MODULE_FIRMWARE(FIRMWARE_VEGA20);
 
 static void amdgpu_uvd_idle_work_handler(struct work_struct *work);
 
@@ -123,9 +128,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	const char *fw_name;
 	const struct common_firmware_header *hdr;
 	unsigned version_major, version_minor, family_id;
-	int i, r;
+	int i, j, r;
 
-	INIT_DELAYED_WORK(&adev->uvd.idle_work, amdgpu_uvd_idle_work_handler);
+	INIT_DELAYED_WORK(&adev->uvd.inst->idle_work, amdgpu_uvd_idle_work_handler);
 
 	switch (adev->asic_type) {
 #ifdef CONFIG_DRM_AMDGPU_CIK
@@ -172,6 +177,12 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	case CHIP_VEGA12:
 		fw_name = FIRMWARE_VEGA12;
 		break;
+	case CHIP_VEGAM:
+		fw_name = FIRMWARE_VEGAM;
+		break;
+	case CHIP_VEGA20:
+		fw_name = FIRMWARE_VEGA20;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -226,28 +237,30 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
 		bo_size += AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
-	r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
-				    AMDGPU_GEM_DOMAIN_VRAM, &adev->uvd.vcpu_bo,
-				    &adev->uvd.gpu_addr, &adev->uvd.cpu_addr);
-	if (r) {
-		dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r);
-		return r;
-	}
+	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
 
-	ring = &adev->uvd.ring;
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&ring->sched, &adev->uvd.entity,
-				  rq, amdgpu_sched_jobs, NULL);
-	if (r != 0) {
-		DRM_ERROR("Failed setting up UVD run queue.\n");
-		return r;
-	}
+		r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
+					    AMDGPU_GEM_DOMAIN_VRAM, &adev->uvd.inst[j].vcpu_bo,
+					    &adev->uvd.inst[j].gpu_addr, &adev->uvd.inst[j].cpu_addr);
+		if (r) {
+			dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r);
+			return r;
+		}
 
-	for (i = 0; i < adev->uvd.max_handles; ++i) {
-		atomic_set(&adev->uvd.handles[i], 0);
-		adev->uvd.filp[i] = NULL;
-	}
+		ring = &adev->uvd.inst[j].ring;
+		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity,
+					  rq, NULL);
+		if (r != 0) {
+			DRM_ERROR("Failed setting up UVD(%d) run queue.\n", j);
+			return r;
+		}
 
+		for (i = 0; i < adev->uvd.max_handles; ++i) {
+			atomic_set(&adev->uvd.inst[j].handles[i], 0);
+			adev->uvd.inst[j].filp[i] = NULL;
+		}
+	}
 	/* from uvd v5.0 HW addressing capacity increased to 64 bits */
 	if (!amdgpu_device_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0))
 		adev->uvd.address_64_bit = true;
@@ -274,20 +287,22 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 
 int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
-	int i;
-	kfree(adev->uvd.saved_bo);
+	int i, j;
 
-	drm_sched_entity_fini(&adev->uvd.ring.sched, &adev->uvd.entity);
+	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		kfree(adev->uvd.inst[j].saved_bo);
 
-	amdgpu_bo_free_kernel(&adev->uvd.vcpu_bo,
-			      &adev->uvd.gpu_addr,
-			      (void **)&adev->uvd.cpu_addr);
+		drm_sched_entity_fini(&adev->uvd.inst[j].ring.sched, &adev->uvd.inst[j].entity);
 
-	amdgpu_ring_fini(&adev->uvd.ring);
+		amdgpu_bo_free_kernel(&adev->uvd.inst[j].vcpu_bo,
+				      &adev->uvd.inst[j].gpu_addr,
+				      (void **)&adev->uvd.inst[j].cpu_addr);
 
-	for (i = 0; i < AMDGPU_MAX_UVD_ENC_RINGS; ++i)
-		amdgpu_ring_fini(&adev->uvd.ring_enc[i]);
+		amdgpu_ring_fini(&adev->uvd.inst[j].ring);
 
+		for (i = 0; i < AMDGPU_MAX_UVD_ENC_RINGS; ++i)
+			amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]);
+	}
 	release_firmware(adev->uvd.fw);
 
 	return 0;
@@ -297,32 +312,33 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 {
 	unsigned size;
 	void *ptr;
-	int i;
-
-	if (adev->uvd.vcpu_bo == NULL)
-		return 0;
+	int i, j;
 
-	cancel_delayed_work_sync(&adev->uvd.idle_work);
+	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		if (adev->uvd.inst[j].vcpu_bo == NULL)
+			continue;
 
-	/* only valid for physical mode */
-	if (adev->asic_type < CHIP_POLARIS10) {
-		for (i = 0; i < adev->uvd.max_handles; ++i)
-			if (atomic_read(&adev->uvd.handles[i]))
-				break;
+		cancel_delayed_work_sync(&adev->uvd.inst[j].idle_work);
 
-		if (i == adev->uvd.max_handles)
-			return 0;
-	}
+		/* only valid for physical mode */
+		if (adev->asic_type < CHIP_POLARIS10) {
+			for (i = 0; i < adev->uvd.max_handles; ++i)
+				if (atomic_read(&adev->uvd.inst[j].handles[i]))
+					break;
 
-	size = amdgpu_bo_size(adev->uvd.vcpu_bo);
-	ptr = adev->uvd.cpu_addr;
+			if (i == adev->uvd.max_handles)
+				continue;
+		}
 
-	adev->uvd.saved_bo = kmalloc(size, GFP_KERNEL);
-	if (!adev->uvd.saved_bo)
-		return -ENOMEM;
+		size = amdgpu_bo_size(adev->uvd.inst[j].vcpu_bo);
+		ptr = adev->uvd.inst[j].cpu_addr;
 
-	memcpy_fromio(adev->uvd.saved_bo, ptr, size);
+		adev->uvd.inst[j].saved_bo = kmalloc(size, GFP_KERNEL);
+		if (!adev->uvd.inst[j].saved_bo)
+			return -ENOMEM;
 
+		memcpy_fromio(adev->uvd.inst[j].saved_bo, ptr, size);
+	}
 	return 0;
 }
 
@@ -330,59 +346,65 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 {
 	unsigned size;
 	void *ptr;
+	int i;
 
-	if (adev->uvd.vcpu_bo == NULL)
-		return -EINVAL;
+	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		if (adev->uvd.inst[i].vcpu_bo == NULL)
+			return -EINVAL;
 
-	size = amdgpu_bo_size(adev->uvd.vcpu_bo);
-	ptr = adev->uvd.cpu_addr;
+		size = amdgpu_bo_size(adev->uvd.inst[i].vcpu_bo);
+		ptr = adev->uvd.inst[i].cpu_addr;
 
-	if (adev->uvd.saved_bo != NULL) {
-		memcpy_toio(ptr, adev->uvd.saved_bo, size);
-		kfree(adev->uvd.saved_bo);
-		adev->uvd.saved_bo = NULL;
-	} else {
-		const struct common_firmware_header *hdr;
-		unsigned offset;
-
-		hdr = (const struct common_firmware_header *)adev->uvd.fw->data;
-		if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
-			offset = le32_to_cpu(hdr->ucode_array_offset_bytes);
-			memcpy_toio(adev->uvd.cpu_addr, adev->uvd.fw->data + offset,
-				    le32_to_cpu(hdr->ucode_size_bytes));
-			size -= le32_to_cpu(hdr->ucode_size_bytes);
-			ptr += le32_to_cpu(hdr->ucode_size_bytes);
+		if (adev->uvd.inst[i].saved_bo != NULL) {
+			memcpy_toio(ptr, adev->uvd.inst[i].saved_bo, size);
+			kfree(adev->uvd.inst[i].saved_bo);
+			adev->uvd.inst[i].saved_bo = NULL;
+		} else {
+			const struct common_firmware_header *hdr;
+			unsigned offset;
+
+			hdr = (const struct common_firmware_header *)adev->uvd.fw->data;
+			if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
+				offset = le32_to_cpu(hdr->ucode_array_offset_bytes);
+				memcpy_toio(adev->uvd.inst[i].cpu_addr, adev->uvd.fw->data + offset,
+					    le32_to_cpu(hdr->ucode_size_bytes));
+				size -= le32_to_cpu(hdr->ucode_size_bytes);
+				ptr += le32_to_cpu(hdr->ucode_size_bytes);
+			}
+			memset_io(ptr, 0, size);
+			/* to restore uvd fence seq */
+			amdgpu_fence_driver_force_completion(&adev->uvd.inst[i].ring);
 		}
-		memset_io(ptr, 0, size);
-		/* to restore uvd fence seq */
-		amdgpu_fence_driver_force_completion(&adev->uvd.ring);
 	}
-
 	return 0;
 }
 
 void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 {
-	struct amdgpu_ring *ring = &adev->uvd.ring;
-	int i, r;
+	struct amdgpu_ring *ring;
+	int i, j, r;
 
-	for (i = 0; i < adev->uvd.max_handles; ++i) {
-		uint32_t handle = atomic_read(&adev->uvd.handles[i]);
-		if (handle != 0 && adev->uvd.filp[i] == filp) {
-			struct dma_fence *fence;
-
-			r = amdgpu_uvd_get_destroy_msg(ring, handle,
-						       false, &fence);
-			if (r) {
-				DRM_ERROR("Error destroying UVD (%d)!\n", r);
-				continue;
-			}
+	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		ring = &adev->uvd.inst[j].ring;
+
+		for (i = 0; i < adev->uvd.max_handles; ++i) {
+			uint32_t handle = atomic_read(&adev->uvd.inst[j].handles[i]);
+			if (handle != 0 && adev->uvd.inst[j].filp[i] == filp) {
+				struct dma_fence *fence;
+
+				r = amdgpu_uvd_get_destroy_msg(ring, handle,
+							       false, &fence);
+				if (r) {
+					DRM_ERROR("Error destroying UVD(%d) %d!\n", j, r);
+					continue;
+				}
 
-			dma_fence_wait(fence, false);
-			dma_fence_put(fence);
+				dma_fence_wait(fence, false);
+				dma_fence_put(fence);
 
-			adev->uvd.filp[i] = NULL;
-			atomic_set(&adev->uvd.handles[i], 0);
+				adev->uvd.inst[j].filp[i] = NULL;
+				atomic_set(&adev->uvd.inst[j].handles[i], 0);
+			}
 		}
 	}
 }
@@ -657,15 +679,16 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 	void *ptr;
 	long r;
 	int i;
+	uint32_t ip_instance = ctx->parser->job->ring->me;
 
 	if (offset & 0x3F) {
-		DRM_ERROR("UVD messages must be 64 byte aligned!\n");
+		DRM_ERROR("UVD(%d) messages must be 64 byte aligned!\n", ip_instance);
 		return -EINVAL;
 	}
 
 	r = amdgpu_bo_kmap(bo, &ptr);
 	if (r) {
-		DRM_ERROR("Failed mapping the UVD message (%ld)!\n", r);
+		DRM_ERROR("Failed mapping the UVD(%d) message (%ld)!\n", ip_instance, r);
 		return r;
 	}
 
@@ -675,7 +698,7 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 	handle = msg[2];
 
 	if (handle == 0) {
-		DRM_ERROR("Invalid UVD handle!\n");
+		DRM_ERROR("Invalid UVD(%d) handle!\n", ip_instance);
 		return -EINVAL;
 	}
 
@@ -686,18 +709,18 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 		/* try to alloc a new handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			if (atomic_read(&adev->uvd.handles[i]) == handle) {
-				DRM_ERROR("Handle 0x%x already in use!\n", handle);
+			if (atomic_read(&adev->uvd.inst[ip_instance].handles[i]) == handle) {
+				DRM_ERROR("(%d)Handle 0x%x already in use!\n", ip_instance, handle);
 				return -EINVAL;
 			}
 
-			if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
-				adev->uvd.filp[i] = ctx->parser->filp;
+			if (!atomic_cmpxchg(&adev->uvd.inst[ip_instance].handles[i], 0, handle)) {
+				adev->uvd.inst[ip_instance].filp[i] = ctx->parser->filp;
 				return 0;
 			}
 		}
 
-		DRM_ERROR("No more free UVD handles!\n");
+		DRM_ERROR("No more free UVD(%d) handles!\n", ip_instance);
 		return -ENOSPC;
 
 	case 1:
@@ -709,27 +732,27 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 		/* validate the handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			if (atomic_read(&adev->uvd.handles[i]) == handle) {
-				if (adev->uvd.filp[i] != ctx->parser->filp) {
-					DRM_ERROR("UVD handle collision detected!\n");
+			if (atomic_read(&adev->uvd.inst[ip_instance].handles[i]) == handle) {
+				if (adev->uvd.inst[ip_instance].filp[i] != ctx->parser->filp) {
+					DRM_ERROR("UVD(%d) handle collision detected!\n", ip_instance);
 					return -EINVAL;
 				}
 				return 0;
 			}
 		}
 
-		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
+		DRM_ERROR("Invalid UVD(%d) handle 0x%x!\n", ip_instance, handle);
 		return -ENOENT;
 
 	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i)
-			atomic_cmpxchg(&adev->uvd.handles[i], handle, 0);
+			atomic_cmpxchg(&adev->uvd.inst[ip_instance].handles[i], handle, 0);
 		amdgpu_bo_kunmap(bo);
 		return 0;
 
 	default:
-		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+		DRM_ERROR("Illegal UVD(%d) message type (%d)!\n", ip_instance, msg_type);
 		return -EINVAL;
 	}
 	BUG();
@@ -800,7 +823,7 @@ static int amdgpu_uvd_cs_pass2(struct amdgpu_uvd_cs_ctx *ctx)
 		}
 
 		if ((cmd == 0 || cmd == 0x3) &&
-		    (start >> 28) != (ctx->parser->adev->uvd.gpu_addr >> 28)) {
+		    (start >> 28) != (ctx->parser->adev->uvd.inst->gpu_addr >> 28)) {
 			DRM_ERROR("msg/fb buffer %LX-%LX out of 256MB segment!\n",
 				  start, end);
 			return -EINVAL;
@@ -968,6 +991,8 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 	uint64_t addr;
 	long r;
 	int i;
+	unsigned offset_idx = 0;
+	unsigned offset[3] = { UVD_BASE_SI, 0, 0 };
 
 	amdgpu_bo_kunmap(bo);
 	amdgpu_bo_unpin(bo);
@@ -987,17 +1012,16 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 		goto err;
 
 	if (adev->asic_type >= CHIP_VEGA10) {
-		data[0] = PACKET0(mmUVD_GPCOM_VCPU_DATA0_VEGA10, 0);
-		data[1] = PACKET0(mmUVD_GPCOM_VCPU_DATA1_VEGA10, 0);
-		data[2] = PACKET0(mmUVD_GPCOM_VCPU_CMD_VEGA10, 0);
-		data[3] = PACKET0(mmUVD_NO_OP_VEGA10, 0);
-	} else {
-		data[0] = PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0);
-		data[1] = PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0);
-		data[2] = PACKET0(mmUVD_GPCOM_VCPU_CMD, 0);
-		data[3] = PACKET0(mmUVD_NO_OP, 0);
+		offset_idx = 1 + ring->me;
+		offset[1] = adev->reg_offset[UVD_HWIP][0][1];
+		offset[2] = adev->reg_offset[UVD_HWIP][1][1];
 	}
 
+	data[0] = PACKET0(offset[offset_idx] + UVD_GPCOM_VCPU_DATA0, 0);
+	data[1] = PACKET0(offset[offset_idx] + UVD_GPCOM_VCPU_DATA1, 0);
+	data[2] = PACKET0(offset[offset_idx] + UVD_GPCOM_VCPU_CMD, 0);
+	data[3] = PACKET0(offset[offset_idx] + UVD_NO_OP, 0);
+
 	ib = &job->ibs[0];
 	addr = amdgpu_bo_gpu_offset(bo);
 	ib->ptr[0] = data[0];
@@ -1033,7 +1057,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 		if (r)
 			goto err_free;
 
-		r = amdgpu_job_submit(job, ring, &adev->uvd.entity,
+		r = amdgpu_job_submit(job, ring, &adev->uvd.inst[ring->me].entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err_free;
@@ -1121,8 +1145,15 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
-		container_of(work, struct amdgpu_device, uvd.idle_work.work);
-	unsigned fences = amdgpu_fence_count_emitted(&adev->uvd.ring);
+		container_of(work, struct amdgpu_device, uvd.inst->idle_work.work);
+	unsigned fences = 0, i, j;
+
+	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		fences += amdgpu_fence_count_emitted(&adev->uvd.inst[i].ring);
+		for (j = 0; j < adev->uvd.num_enc_rings; ++j) {
+			fences += amdgpu_fence_count_emitted(&adev->uvd.inst[i].ring_enc[j]);
+		}
+	}
 
 	if (fences == 0) {
 		if (adev->pm.dpm_enabled) {
@@ -1136,7 +1167,7 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 							       AMD_CG_STATE_GATE);
 		}
 	} else {
-		schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
+		schedule_delayed_work(&adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT);
 	}
 }
 
@@ -1148,7 +1179,7 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring)
 	if (amdgpu_sriov_vf(adev))
 		return;
 
-	set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work);
+	set_clocks = !cancel_delayed_work_sync(&adev->uvd.inst->idle_work);
 	if (set_clocks) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_uvd(adev, true);
@@ -1165,7 +1196,7 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring)
 void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring)
 {
 	if (!amdgpu_sriov_vf(ring->adev))
-		schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
+		schedule_delayed_work(&ring->adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT);
 }
 
 /**
@@ -1179,27 +1210,28 @@ int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence;
 	long r;
+	uint32_t ip_instance = ring->me;
 
 	r = amdgpu_uvd_get_create_msg(ring, 1, NULL);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get create msg (%ld).\n", r);
+		DRM_ERROR("amdgpu: (%d)failed to get create msg (%ld).\n", ip_instance, r);
 		goto error;
 	}
 
 	r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r);
+		DRM_ERROR("amdgpu: (%d)failed to get destroy ib (%ld).\n", ip_instance, r);
 		goto error;
 	}
 
 	r = dma_fence_wait_timeout(fence, false, timeout);
 	if (r == 0) {
-		DRM_ERROR("amdgpu: IB test timed out.\n");
+		DRM_ERROR("amdgpu: (%d)IB test timed out.\n", ip_instance);
 		r = -ETIMEDOUT;
 	} else if (r < 0) {
-		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
+		DRM_ERROR("amdgpu: (%d)fence wait failed (%ld).\n", ip_instance, r);
 	} else {
-		DRM_DEBUG("ib test on ring %d succeeded\n",  ring->idx);
+		DRM_DEBUG("ib test on (%d)ring %d succeeded\n", ip_instance, ring->idx);
 		r = 0;
 	}
 
@@ -1227,7 +1259,7 @@ uint32_t amdgpu_uvd_used_handles(struct amdgpu_device *adev)
 		 * necessarily linear. So we need to count
 		 * all non-zero handles.
 		 */
-		if (atomic_read(&adev->uvd.handles[i]))
+		if (atomic_read(&adev->uvd.inst->handles[i]))
 			used_handles++;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index 32ea20b99e53..b1579fba134c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -31,30 +31,37 @@
 #define AMDGPU_UVD_SESSION_SIZE		(50*1024)
 #define AMDGPU_UVD_FIRMWARE_OFFSET	256
 
+#define AMDGPU_MAX_UVD_INSTANCES			2
+
 #define AMDGPU_UVD_FIRMWARE_SIZE(adev)    \
 	(AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(((const struct common_firmware_header *)(adev)->uvd.fw->data)->ucode_size_bytes) + \
 			       8) - AMDGPU_UVD_FIRMWARE_OFFSET)
 
-struct amdgpu_uvd {
+struct amdgpu_uvd_inst {
 	struct amdgpu_bo	*vcpu_bo;
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
-	unsigned		fw_version;
 	void			*saved_bo;
-	unsigned		max_handles;
 	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
 	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
 	struct delayed_work	idle_work;
-	const struct firmware	*fw;	/* UVD firmware */
 	struct amdgpu_ring	ring;
 	struct amdgpu_ring	ring_enc[AMDGPU_MAX_UVD_ENC_RINGS];
 	struct amdgpu_irq_src	irq;
-	bool			address_64_bit;
-	bool			use_ctx_buf;
 	struct drm_sched_entity entity;
 	struct drm_sched_entity entity_enc;
 	uint32_t                srbm_soft_reset;
+};
+
+struct amdgpu_uvd {
+	const struct firmware	*fw;	/* UVD firmware */
+	unsigned		fw_version;
+	unsigned		max_handles;
 	unsigned		num_enc_rings;
+	uint8_t		num_uvd_inst;
+	bool			address_64_bit;
+	bool			use_ctx_buf;
+	struct amdgpu_uvd_inst		inst[AMDGPU_MAX_UVD_INSTANCES];
 };
 
 int amdgpu_uvd_sw_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index a33804bd3314..23d960ec1cf2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -51,11 +51,13 @@
 #define FIRMWARE_FIJI		"amdgpu/fiji_vce.bin"
 #define FIRMWARE_STONEY		"amdgpu/stoney_vce.bin"
 #define FIRMWARE_POLARIS10	"amdgpu/polaris10_vce.bin"
-#define FIRMWARE_POLARIS11         "amdgpu/polaris11_vce.bin"
-#define FIRMWARE_POLARIS12         "amdgpu/polaris12_vce.bin"
+#define FIRMWARE_POLARIS11	"amdgpu/polaris11_vce.bin"
+#define FIRMWARE_POLARIS12	"amdgpu/polaris12_vce.bin"
+#define FIRMWARE_VEGAM		"amdgpu/vegam_vce.bin"
 
 #define FIRMWARE_VEGA10		"amdgpu/vega10_vce.bin"
 #define FIRMWARE_VEGA12		"amdgpu/vega12_vce.bin"
+#define FIRMWARE_VEGA20		"amdgpu/vega20_vce.bin"
 
 #ifdef CONFIG_DRM_AMDGPU_CIK
 MODULE_FIRMWARE(FIRMWARE_BONAIRE);
@@ -71,9 +73,11 @@ MODULE_FIRMWARE(FIRMWARE_STONEY);
 MODULE_FIRMWARE(FIRMWARE_POLARIS10);
 MODULE_FIRMWARE(FIRMWARE_POLARIS11);
 MODULE_FIRMWARE(FIRMWARE_POLARIS12);
+MODULE_FIRMWARE(FIRMWARE_VEGAM);
 
 MODULE_FIRMWARE(FIRMWARE_VEGA10);
 MODULE_FIRMWARE(FIRMWARE_VEGA12);
+MODULE_FIRMWARE(FIRMWARE_VEGA20);
 
 static void amdgpu_vce_idle_work_handler(struct work_struct *work);
 
@@ -132,12 +136,18 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 	case CHIP_POLARIS12:
 		fw_name = FIRMWARE_POLARIS12;
 		break;
+	case CHIP_VEGAM:
+		fw_name = FIRMWARE_VEGAM;
+		break;
 	case CHIP_VEGA10:
 		fw_name = FIRMWARE_VEGA10;
 		break;
 	case CHIP_VEGA12:
 		fw_name = FIRMWARE_VEGA12;
 		break;
+	case CHIP_VEGA20:
+		fw_name = FIRMWARE_VEGA20;
+		break;
 
 	default:
 		return -EINVAL;
@@ -181,7 +191,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 	ring = &adev->vce.ring[0];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
 	r = drm_sched_entity_init(&ring->sched, &adev->vce.entity,
-				  rq, amdgpu_sched_jobs, NULL);
+				  rq, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCE run queue.\n");
 		return r;
@@ -755,6 +765,18 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 			if (r)
 				goto out;
 			break;
+
+		case 0x0500000d: /* MV buffer */
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3,
+							idx + 2, 0, 0);
+			if (r)
+				goto out;
+
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 8,
+							idx + 7, 0, 0);
+			if (r)
+				goto out;
+			break;
 		}
 
 		idx += len / 4;
@@ -860,6 +882,18 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 				goto out;
 			break;
 
+		case 0x0500000d: /* MV buffer */
+			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3,
+							idx + 2, *size, 0);
+			if (r)
+				goto out;
+
+			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 8,
+							idx + 7, *size / 12, 0);
+			if (r)
+				goto out;
+			break;
+
 		default:
 			DRM_ERROR("invalid VCE command (0x%x)!\n", cmd);
 			r = -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 58e495330b38..8851bcdfc260 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -105,7 +105,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	ring = &adev->vcn.ring_dec;
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
 	r = drm_sched_entity_init(&ring->sched, &adev->vcn.entity_dec,
-				  rq, amdgpu_sched_jobs, NULL);
+				  rq, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCN dec run queue.\n");
 		return r;
@@ -114,7 +114,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	ring = &adev->vcn.ring_enc[0];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
 	r = drm_sched_entity_init(&ring->sched, &adev->vcn.entity_enc,
-				  rq, amdgpu_sched_jobs, NULL);
+				  rq, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCN enc run queue.\n");
 		return r;
@@ -205,13 +205,18 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, vcn.idle_work.work);
 	unsigned fences = amdgpu_fence_count_emitted(&adev->vcn.ring_dec);
+	unsigned i;
+
+	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+		fences += amdgpu_fence_count_emitted(&adev->vcn.ring_enc[i]);
+	}
 
 	if (fences == 0) {
-		if (adev->pm.dpm_enabled) {
-			/* might be used when with pg/cg
+		if (adev->pm.dpm_enabled)
 			amdgpu_dpm_enable_uvd(adev, false);
-			*/
-		}
+		else
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+							       AMD_PG_STATE_GATE);
 	} else {
 		schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
 	}
@@ -223,9 +228,11 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
 
 	if (set_clocks && adev->pm.dpm_enabled) {
-		/* might be used when with pg/cg
-		amdgpu_dpm_enable_uvd(adev, true);
-		*/
+		if (adev->pm.dpm_enabled)
+			amdgpu_dpm_enable_uvd(adev, true);
+		else
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+							       AMD_PG_STATE_UNGATE);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 2fd7db891689..181e6afa9847 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -45,6 +45,17 @@
 #define VCN_ENC_CMD_REG_WRITE		0x0000000b
 #define VCN_ENC_CMD_REG_WAIT		0x0000000c
 
+enum engine_status_constants {
+	UVD_PGFSM_STATUS__UVDM_UVDU_PWR_ON = 0x2AAAA0,
+	UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON = 0x00000002,
+	UVD_STATUS__UVD_BUSY = 0x00000004,
+	GB_ADDR_CONFIG_DEFAULT = 0x26010011,
+	UVD_STATUS__IDLE = 0x2,
+	UVD_STATUS__BUSY = 0x5,
+	UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF = 0x1,
+	UVD_STATUS__RBC_BUSY = 0x1,
+};
+
 struct amdgpu_vcn {
 	struct amdgpu_bo	*vcpu_bo;
 	void			*cpu_addr;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index da55a78d7380..ccba88cc8c54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -94,6 +94,34 @@ struct amdgpu_prt_cb {
 	struct dma_fence_cb cb;
 };
 
+static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
+				   struct amdgpu_vm *vm,
+				   struct amdgpu_bo *bo)
+{
+	base->vm = vm;
+	base->bo = bo;
+	INIT_LIST_HEAD(&base->bo_list);
+	INIT_LIST_HEAD(&base->vm_status);
+
+	if (!bo)
+		return;
+	list_add_tail(&base->bo_list, &bo->va);
+
+	if (bo->tbo.resv != vm->root.base.bo->tbo.resv)
+		return;
+
+	if (bo->preferred_domains &
+	    amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type))
+		return;
+
+	/*
+	 * we checked all the prerequisites, but it looks like this per vm bo
+	 * is currently evicted. add the bo to the evicted list to make sure it
+	 * is validated on next vm use to avoid fault.
+	 * */
+	list_move_tail(&base->vm_status, &vm->evicted);
+}
+
 /**
  * amdgpu_vm_level_shift - return the addr shift for each level
  *
@@ -196,24 +224,16 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      void *param)
 {
 	struct ttm_bo_global *glob = adev->mman.bdev.glob;
-	int r;
+	struct amdgpu_vm_bo_base *bo_base, *tmp;
+	int r = 0;
 
-	spin_lock(&vm->status_lock);
-	while (!list_empty(&vm->evicted)) {
-		struct amdgpu_vm_bo_base *bo_base;
-		struct amdgpu_bo *bo;
+	list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
+		struct amdgpu_bo *bo = bo_base->bo;
 
-		bo_base = list_first_entry(&vm->evicted,
-					   struct amdgpu_vm_bo_base,
-					   vm_status);
-		spin_unlock(&vm->status_lock);
-
-		bo = bo_base->bo;
-		BUG_ON(!bo);
 		if (bo->parent) {
 			r = validate(param, bo);
 			if (r)
-				return r;
+				break;
 
 			spin_lock(&glob->lru_lock);
 			ttm_bo_move_to_lru_tail(&bo->tbo);
@@ -222,22 +242,29 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			spin_unlock(&glob->lru_lock);
 		}
 
-		if (bo->tbo.type == ttm_bo_type_kernel &&
-		    vm->use_cpu_for_update) {
-			r = amdgpu_bo_kmap(bo, NULL);
-			if (r)
-				return r;
-		}
-
-		spin_lock(&vm->status_lock);
-		if (bo->tbo.type != ttm_bo_type_kernel)
+		if (bo->tbo.type != ttm_bo_type_kernel) {
+			spin_lock(&vm->moved_lock);
 			list_move(&bo_base->vm_status, &vm->moved);
-		else
+			spin_unlock(&vm->moved_lock);
+		} else {
 			list_move(&bo_base->vm_status, &vm->relocated);
+		}
 	}
-	spin_unlock(&vm->status_lock);
 
-	return 0;
+	spin_lock(&glob->lru_lock);
+	list_for_each_entry(bo_base, &vm->idle, vm_status) {
+		struct amdgpu_bo *bo = bo_base->bo;
+
+		if (!bo->parent)
+			continue;
+
+		ttm_bo_move_to_lru_tail(&bo->tbo);
+		if (bo->shadow)
+			ttm_bo_move_to_lru_tail(&bo->shadow->tbo);
+	}
+	spin_unlock(&glob->lru_lock);
+
+	return r;
 }
 
 /**
@@ -249,13 +276,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  */
 bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 {
-	bool ready;
-
-	spin_lock(&vm->status_lock);
-	ready = list_empty(&vm->evicted);
-	spin_unlock(&vm->status_lock);
-
-	return ready;
+	return list_empty(&vm->evicted);
 }
 
 /**
@@ -412,11 +433,16 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 		struct amdgpu_bo *pt;
 
 		if (!entry->base.bo) {
-			r = amdgpu_bo_create(adev,
-					     amdgpu_vm_bo_size(adev, level),
-					     AMDGPU_GPU_PAGE_SIZE,
-					     AMDGPU_GEM_DOMAIN_VRAM, flags,
-					     ttm_bo_type_kernel, resv, &pt);
+			struct amdgpu_bo_param bp;
+
+			memset(&bp, 0, sizeof(bp));
+			bp.size = amdgpu_vm_bo_size(adev, level);
+			bp.byte_align = AMDGPU_GPU_PAGE_SIZE;
+			bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
+			bp.flags = flags;
+			bp.type = ttm_bo_type_kernel;
+			bp.resv = resv;
+			r = amdgpu_bo_create(adev, &bp, &pt);
 			if (r)
 				return r;
 
@@ -441,12 +467,8 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 			*/
 			pt->parent = amdgpu_bo_ref(parent->base.bo);
 
-			entry->base.vm = vm;
-			entry->base.bo = pt;
-			list_add_tail(&entry->base.bo_list, &pt->va);
-			spin_lock(&vm->status_lock);
-			list_add(&entry->base.vm_status, &vm->relocated);
-			spin_unlock(&vm->status_lock);
+			amdgpu_vm_bo_base_init(&entry->base, vm, pt);
+			list_move(&entry->base.vm_status, &vm->relocated);
 		}
 
 		if (level < AMDGPU_VM_PTB) {
@@ -628,7 +650,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 		amdgpu_gmc_emit_pasid_mapping(ring, job->vmid, job->pasid);
 
 	if (vm_flush_needed || pasid_mapping_needed) {
-		r = amdgpu_fence_emit(ring, &fence);
+		r = amdgpu_fence_emit(ring, &fence, 0);
 		if (r)
 			return r;
 	}
@@ -893,10 +915,8 @@ static void amdgpu_vm_invalidate_level(struct amdgpu_device *adev,
 		if (!entry->base.bo)
 			continue;
 
-		spin_lock(&vm->status_lock);
-		if (list_empty(&entry->base.vm_status))
-			list_add(&entry->base.vm_status, &vm->relocated);
-		spin_unlock(&vm->status_lock);
+		if (!entry->base.moved)
+			list_move(&entry->base.vm_status, &vm->relocated);
 		amdgpu_vm_invalidate_level(adev, vm, entry, level + 1);
 	}
 }
@@ -926,6 +946,14 @@ restart:
 	params.adev = adev;
 
 	if (vm->use_cpu_for_update) {
+		struct amdgpu_vm_bo_base *bo_base;
+
+		list_for_each_entry(bo_base, &vm->relocated, vm_status) {
+			r = amdgpu_bo_kmap(bo_base->bo, NULL);
+			if (unlikely(r))
+				return r;
+		}
+
 		r = amdgpu_vm_wait_pd(adev, vm, AMDGPU_FENCE_OWNER_VM);
 		if (unlikely(r))
 			return r;
@@ -941,7 +969,6 @@ restart:
 		params.func = amdgpu_vm_do_set_ptes;
 	}
 
-	spin_lock(&vm->status_lock);
 	while (!list_empty(&vm->relocated)) {
 		struct amdgpu_vm_bo_base *bo_base, *parent;
 		struct amdgpu_vm_pt *pt, *entry;
@@ -950,14 +977,12 @@ restart:
 		bo_base = list_first_entry(&vm->relocated,
 					   struct amdgpu_vm_bo_base,
 					   vm_status);
-		list_del_init(&bo_base->vm_status);
-		spin_unlock(&vm->status_lock);
+		bo_base->moved = false;
+		list_move(&bo_base->vm_status, &vm->idle);
 
 		bo = bo_base->bo->parent;
-		if (!bo) {
-			spin_lock(&vm->status_lock);
+		if (!bo)
 			continue;
-		}
 
 		parent = list_first_entry(&bo->va, struct amdgpu_vm_bo_base,
 					  bo_list);
@@ -966,12 +991,10 @@ restart:
 
 		amdgpu_vm_update_pde(&params, vm, pt, entry);
 
-		spin_lock(&vm->status_lock);
 		if (!vm->use_cpu_for_update &&
 		    (ndw - params.ib->length_dw) < 32)
 			break;
 	}
-	spin_unlock(&vm->status_lock);
 
 	if (vm->use_cpu_for_update) {
 		/* Flush HDP */
@@ -1074,9 +1097,7 @@ static void amdgpu_vm_handle_huge_pages(struct amdgpu_pte_update_params *p,
 		if (entry->huge) {
 			/* Add the entry to the relocated list to update it. */
 			entry->huge = false;
-			spin_lock(&p->vm->status_lock);
 			list_move(&entry->base.vm_status, &p->vm->relocated);
-			spin_unlock(&p->vm->status_lock);
 		}
 		return;
 	}
@@ -1555,9 +1576,22 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 		amdgpu_asic_flush_hdp(adev, NULL);
 	}
 
-	spin_lock(&vm->status_lock);
+	spin_lock(&vm->moved_lock);
 	list_del_init(&bo_va->base.vm_status);
-	spin_unlock(&vm->status_lock);
+	spin_unlock(&vm->moved_lock);
+
+	/* If the BO is not in its preferred location add it back to
+	 * the evicted list so that it gets validated again on the
+	 * next command submission.
+	 */
+	if (bo && bo->tbo.resv == vm->root.base.bo->tbo.resv) {
+		uint32_t mem_type = bo->tbo.mem.mem_type;
+
+		if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(mem_type)))
+			list_add_tail(&bo_va->base.vm_status, &vm->evicted);
+		else
+			list_add(&bo_va->base.vm_status, &vm->idle);
+	}
 
 	list_splice_init(&bo_va->invalids, &bo_va->valids);
 	bo_va->cleared = clear;
@@ -1766,19 +1800,18 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 			   struct amdgpu_vm *vm)
 {
+	struct amdgpu_bo_va *bo_va, *tmp;
+	struct list_head moved;
 	bool clear;
-	int r = 0;
-
-	spin_lock(&vm->status_lock);
-	while (!list_empty(&vm->moved)) {
-		struct amdgpu_bo_va *bo_va;
-		struct reservation_object *resv;
+	int r;
 
-		bo_va = list_first_entry(&vm->moved,
-			struct amdgpu_bo_va, base.vm_status);
-		spin_unlock(&vm->status_lock);
+	INIT_LIST_HEAD(&moved);
+	spin_lock(&vm->moved_lock);
+	list_splice_init(&vm->moved, &moved);
+	spin_unlock(&vm->moved_lock);
 
-		resv = bo_va->base.bo->tbo.resv;
+	list_for_each_entry_safe(bo_va, tmp, &moved, base.vm_status) {
+		struct reservation_object *resv = bo_va->base.bo->tbo.resv;
 
 		/* Per VM BOs never need to bo cleared in the page tables */
 		if (resv == vm->root.base.bo->tbo.resv)
@@ -1791,17 +1824,19 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 			clear = true;
 
 		r = amdgpu_vm_bo_update(adev, bo_va, clear);
-		if (r)
+		if (r) {
+			spin_lock(&vm->moved_lock);
+			list_splice(&moved, &vm->moved);
+			spin_unlock(&vm->moved_lock);
 			return r;
+		}
 
 		if (!clear && resv != vm->root.base.bo->tbo.resv)
 			reservation_object_unlock(resv);
 
-		spin_lock(&vm->status_lock);
 	}
-	spin_unlock(&vm->status_lock);
 
-	return r;
+	return 0;
 }
 
 /**
@@ -1827,36 +1862,12 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
 	if (bo_va == NULL) {
 		return NULL;
 	}
-	bo_va->base.vm = vm;
-	bo_va->base.bo = bo;
-	INIT_LIST_HEAD(&bo_va->base.bo_list);
-	INIT_LIST_HEAD(&bo_va->base.vm_status);
+	amdgpu_vm_bo_base_init(&bo_va->base, vm, bo);
 
 	bo_va->ref_count = 1;
 	INIT_LIST_HEAD(&bo_va->valids);
 	INIT_LIST_HEAD(&bo_va->invalids);
 
-	if (!bo)
-		return bo_va;
-
-	list_add_tail(&bo_va->base.bo_list, &bo->va);
-
-	if (bo->tbo.resv != vm->root.base.bo->tbo.resv)
-		return bo_va;
-
-	if (bo->preferred_domains &
-	    amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type))
-		return bo_va;
-
-	/*
-	 * We checked all the prerequisites, but it looks like this per VM BO
-	 * is currently evicted. add the BO to the evicted list to make sure it
-	 * is validated on next VM use to avoid fault.
-	 * */
-	spin_lock(&vm->status_lock);
-	list_move_tail(&bo_va->base.vm_status, &vm->evicted);
-	spin_unlock(&vm->status_lock);
-
 	return bo_va;
 }
 
@@ -1884,11 +1895,11 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
 	if (mapping->flags & AMDGPU_PTE_PRT)
 		amdgpu_vm_prt_get(adev);
 
-	if (bo && bo->tbo.resv == vm->root.base.bo->tbo.resv) {
-		spin_lock(&vm->status_lock);
-		if (list_empty(&bo_va->base.vm_status))
-			list_add(&bo_va->base.vm_status, &vm->moved);
-		spin_unlock(&vm->status_lock);
+	if (bo && bo->tbo.resv == vm->root.base.bo->tbo.resv &&
+	    !bo_va->base.moved) {
+		spin_lock(&vm->moved_lock);
+		list_move(&bo_va->base.vm_status, &vm->moved);
+		spin_unlock(&vm->moved_lock);
 	}
 	trace_amdgpu_vm_bo_map(bo_va, mapping);
 }
@@ -2198,9 +2209,9 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 
 	list_del(&bo_va->base.bo_list);
 
-	spin_lock(&vm->status_lock);
+	spin_lock(&vm->moved_lock);
 	list_del(&bo_va->base.vm_status);
-	spin_unlock(&vm->status_lock);
+	spin_unlock(&vm->moved_lock);
 
 	list_for_each_entry_safe(mapping, next, &bo_va->valids, list) {
 		list_del(&mapping->list);
@@ -2234,33 +2245,34 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 {
 	struct amdgpu_vm_bo_base *bo_base;
 
+	/* shadow bo doesn't have bo base, its validation needs its parent */
+	if (bo->parent && bo->parent->shadow == bo)
+		bo = bo->parent;
+
 	list_for_each_entry(bo_base, &bo->va, bo_list) {
 		struct amdgpu_vm *vm = bo_base->vm;
+		bool was_moved = bo_base->moved;
 
 		bo_base->moved = true;
 		if (evicted && bo->tbo.resv == vm->root.base.bo->tbo.resv) {
-			spin_lock(&bo_base->vm->status_lock);
 			if (bo->tbo.type == ttm_bo_type_kernel)
 				list_move(&bo_base->vm_status, &vm->evicted);
 			else
 				list_move_tail(&bo_base->vm_status,
 					       &vm->evicted);
-			spin_unlock(&bo_base->vm->status_lock);
 			continue;
 		}
 
-		if (bo->tbo.type == ttm_bo_type_kernel) {
-			spin_lock(&bo_base->vm->status_lock);
-			if (list_empty(&bo_base->vm_status))
-				list_add(&bo_base->vm_status, &vm->relocated);
-			spin_unlock(&bo_base->vm->status_lock);
+		if (was_moved)
 			continue;
-		}
 
-		spin_lock(&bo_base->vm->status_lock);
-		if (list_empty(&bo_base->vm_status))
-			list_add(&bo_base->vm_status, &vm->moved);
-		spin_unlock(&bo_base->vm->status_lock);
+		if (bo->tbo.type == ttm_bo_type_kernel) {
+			list_move(&bo_base->vm_status, &vm->relocated);
+		} else {
+			spin_lock(&bo_base->vm->moved_lock);
+			list_move(&bo_base->vm_status, &vm->moved);
+			spin_unlock(&bo_base->vm->moved_lock);
+		}
 	}
 }
 
@@ -2355,6 +2367,8 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		   int vm_context, unsigned int pasid)
 {
+	struct amdgpu_bo_param bp;
+	struct amdgpu_bo *root;
 	const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE,
 		AMDGPU_VM_PTE_COUNT(adev) * 8);
 	unsigned ring_instance;
@@ -2367,10 +2381,11 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	vm->va = RB_ROOT_CACHED;
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
 		vm->reserved_vmid[i] = NULL;
-	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->evicted);
 	INIT_LIST_HEAD(&vm->relocated);
+	spin_lock_init(&vm->moved_lock);
 	INIT_LIST_HEAD(&vm->moved);
+	INIT_LIST_HEAD(&vm->idle);
 	INIT_LIST_HEAD(&vm->freed);
 
 	/* create scheduler entity for page table updates */
@@ -2380,7 +2395,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	ring = adev->vm_manager.vm_pte_rings[ring_instance];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
 	r = drm_sched_entity_init(&ring->sched, &vm->entity,
-				  rq, amdgpu_sched_jobs, NULL);
+				  rq, NULL);
 	if (r)
 		return r;
 
@@ -2409,24 +2424,28 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		flags |= AMDGPU_GEM_CREATE_SHADOW;
 
 	size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
-	r = amdgpu_bo_create(adev, size, align, AMDGPU_GEM_DOMAIN_VRAM, flags,
-			     ttm_bo_type_kernel, NULL, &vm->root.base.bo);
+	memset(&bp, 0, sizeof(bp));
+	bp.size = size;
+	bp.byte_align = align;
+	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
+	bp.flags = flags;
+	bp.type = ttm_bo_type_kernel;
+	bp.resv = NULL;
+	r = amdgpu_bo_create(adev, &bp, &root);
 	if (r)
 		goto error_free_sched_entity;
 
-	r = amdgpu_bo_reserve(vm->root.base.bo, true);
+	r = amdgpu_bo_reserve(root, true);
 	if (r)
 		goto error_free_root;
 
-	r = amdgpu_vm_clear_bo(adev, vm, vm->root.base.bo,
+	r = amdgpu_vm_clear_bo(adev, vm, root,
 			       adev->vm_manager.root_level,
 			       vm->pte_support_ats);
 	if (r)
 		goto error_unreserve;
 
-	vm->root.base.vm = vm;
-	list_add_tail(&vm->root.base.bo_list, &vm->root.base.bo->va);
-	list_add_tail(&vm->root.base.vm_status, &vm->evicted);
+	amdgpu_vm_bo_base_init(&vm->root.base, vm, root);
 	amdgpu_bo_unreserve(vm->root.base.bo);
 
 	if (pasid) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 30f080364c97..061b99a18cb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -75,11 +75,12 @@ struct amdgpu_bo_list_entry;
 /* PDE Block Fragment Size for VEGA10 */
 #define AMDGPU_PDE_BFS(a)	((uint64_t)a << 59)
 
-/* VEGA10 only */
+
+/* For GFX9 */
 #define AMDGPU_PTE_MTYPE(a)    ((uint64_t)a << 57)
 #define AMDGPU_PTE_MTYPE_MASK	AMDGPU_PTE_MTYPE(3ULL)
 
-/* For Raven */
+#define AMDGPU_MTYPE_NC 0
 #define AMDGPU_MTYPE_CC 2
 
 #define AMDGPU_PTE_DEFAULT_ATC  (AMDGPU_PTE_SYSTEM      \
@@ -167,9 +168,6 @@ struct amdgpu_vm {
 	/* tree of virtual addresses mapped */
 	struct rb_root_cached	va;
 
-	/* protecting invalidated */
-	spinlock_t		status_lock;
-
 	/* BOs who needs a validation */
 	struct list_head	evicted;
 
@@ -178,6 +176,10 @@ struct amdgpu_vm {
 
 	/* BOs moved, but not yet updated in the PT */
 	struct list_head	moved;
+	spinlock_t		moved_lock;
+
+	/* All BOs of this VM not currently in the state machine */
+	struct list_head	idle;
 
 	/* BO mappings freed, but not yet updated in the PT */
 	struct list_head	freed;
@@ -186,9 +188,6 @@ struct amdgpu_vm {
 	struct amdgpu_vm_pt     root;
 	struct dma_fence	*last_update;
 
-	/* protecting freed */
-	spinlock_t		freed_lock;
-
 	/* Scheduler entity for page table updates */
 	struct drm_sched_entity	entity;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 47ef3e6e7178..a266dcf5daed 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -5903,7 +5903,7 @@ static int ci_dpm_init(struct amdgpu_device *adev)
 	pi->pcie_dpm_key_disabled = 0;
 	pi->thermal_sclk_dpm_enabled = 0;
 
-	if (amdgpu_pp_feature_mask & SCLK_DEEP_SLEEP_MASK)
+	if (adev->powerplay.pp_feature & PP_SCLK_DEEP_SLEEP_MASK)
 		pi->caps_sclk_ds = true;
 	else
 		pi->caps_sclk_ds = false;
@@ -6255,7 +6255,7 @@ static int ci_dpm_late_init(void *handle)
 	int ret;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!amdgpu_dpm)
+	if (!adev->pm.dpm_enabled)
 		return 0;
 
 	/* init the sysfs and debugfs files late */
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 0df22030e713..8ff4c60d1b59 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1735,6 +1735,12 @@ static void cik_invalidate_hdp(struct amdgpu_device *adev,
 	}
 }
 
+static bool cik_need_full_reset(struct amdgpu_device *adev)
+{
+	/* change this when we support soft reset */
+	return true;
+}
+
 static const struct amdgpu_asic_funcs cik_asic_funcs =
 {
 	.read_disabled_bios = &cik_read_disabled_bios,
@@ -1748,6 +1754,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.get_config_memsize = &cik_get_config_memsize,
 	.flush_hdp = &cik_flush_hdp,
 	.invalidate_hdp = &cik_invalidate_hdp,
+	.need_full_reset = &cik_need_full_reset,
 };
 
 static int cik_common_early_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 452f88ea46a2..ada241bfeee9 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1823,7 +1823,6 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_framebuffer *amdgpu_fb;
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *abo;
@@ -1842,18 +1841,15 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 		return 0;
 	}
 
-	if (atomic) {
-		amdgpu_fb = to_amdgpu_framebuffer(fb);
+	if (atomic)
 		target_fb = fb;
-	} else {
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
+	else
 		target_fb = crtc->primary->fb;
-	}
 
 	/* If atomic, assume fb object is pinned & idle & fenced and
 	 * just update base pointers
 	 */
-	obj = amdgpu_fb->obj;
+	obj = target_fb->obj[0];
 	abo = gem_to_amdgpu_bo(obj);
 	r = amdgpu_bo_reserve(abo, false);
 	if (unlikely(r != 0))
@@ -2043,8 +2039,7 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(mmMASTER_UPDATE_MODE + amdgpu_crtc->crtc_offset, 0);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
-		amdgpu_fb = to_amdgpu_framebuffer(fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r != 0))
 			return r;
@@ -2526,11 +2521,9 @@ static void dce_v10_0_crtc_disable(struct drm_crtc *crtc)
 	dce_v10_0_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 	if (crtc->primary->fb) {
 		int r;
-		struct amdgpu_framebuffer *amdgpu_fb;
 		struct amdgpu_bo *abo;
 
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(crtc->primary->fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r))
 			DRM_ERROR("failed to reserve abo before unpin\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index a7c1c584a191..a5b96eac3033 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -173,6 +173,7 @@ static void dce_v11_0_init_golden_registers(struct amdgpu_device *adev)
 							ARRAY_SIZE(polaris11_golden_settings_a11));
 		break;
 	case CHIP_POLARIS10:
+	case CHIP_VEGAM:
 		amdgpu_device_program_register_sequence(adev,
 							polaris10_golden_settings_a11,
 							ARRAY_SIZE(polaris10_golden_settings_a11));
@@ -473,6 +474,7 @@ static int dce_v11_0_get_num_crtc (struct amdgpu_device *adev)
 		num_crtc = 2;
 		break;
 	case CHIP_POLARIS10:
+	case CHIP_VEGAM:
 		num_crtc = 6;
 		break;
 	case CHIP_POLARIS11:
@@ -1445,6 +1447,7 @@ static int dce_v11_0_audio_init(struct amdgpu_device *adev)
 		adev->mode_info.audio.num_pins = 7;
 		break;
 	case CHIP_POLARIS10:
+	case CHIP_VEGAM:
 		adev->mode_info.audio.num_pins = 8;
 		break;
 	case CHIP_POLARIS11:
@@ -1862,7 +1865,6 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_framebuffer *amdgpu_fb;
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *abo;
@@ -1881,18 +1883,15 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 		return 0;
 	}
 
-	if (atomic) {
-		amdgpu_fb = to_amdgpu_framebuffer(fb);
+	if (atomic)
 		target_fb = fb;
-	} else {
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
+	else
 		target_fb = crtc->primary->fb;
-	}
 
 	/* If atomic, assume fb object is pinned & idle & fenced and
 	 * just update base pointers
 	 */
-	obj = amdgpu_fb->obj;
+	obj = target_fb->obj[0];
 	abo = gem_to_amdgpu_bo(obj);
 	r = amdgpu_bo_reserve(abo, false);
 	if (unlikely(r != 0))
@@ -2082,8 +2081,7 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(mmCRTC_MASTER_UPDATE_MODE + amdgpu_crtc->crtc_offset, 0);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
-		amdgpu_fb = to_amdgpu_framebuffer(fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r != 0))
 			return r;
@@ -2253,7 +2251,8 @@ static u32 dce_v11_0_pick_pll(struct drm_crtc *crtc)
 
 	if ((adev->asic_type == CHIP_POLARIS10) ||
 	    (adev->asic_type == CHIP_POLARIS11) ||
-	    (adev->asic_type == CHIP_POLARIS12)) {
+	    (adev->asic_type == CHIP_POLARIS12) ||
+	    (adev->asic_type == CHIP_VEGAM)) {
 		struct amdgpu_encoder *amdgpu_encoder =
 			to_amdgpu_encoder(amdgpu_crtc->encoder);
 		struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
@@ -2601,11 +2600,9 @@ static void dce_v11_0_crtc_disable(struct drm_crtc *crtc)
 	dce_v11_0_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 	if (crtc->primary->fb) {
 		int r;
-		struct amdgpu_framebuffer *amdgpu_fb;
 		struct amdgpu_bo *abo;
 
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(crtc->primary->fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r))
 			DRM_ERROR("failed to reserve abo before unpin\n");
@@ -2673,7 +2670,8 @@ static int dce_v11_0_crtc_mode_set(struct drm_crtc *crtc,
 
 	if ((adev->asic_type == CHIP_POLARIS10) ||
 	    (adev->asic_type == CHIP_POLARIS11) ||
-	    (adev->asic_type == CHIP_POLARIS12)) {
+	    (adev->asic_type == CHIP_POLARIS12) ||
+	    (adev->asic_type == CHIP_VEGAM)) {
 		struct amdgpu_encoder *amdgpu_encoder =
 			to_amdgpu_encoder(amdgpu_crtc->encoder);
 		int encoder_mode =
@@ -2830,6 +2828,7 @@ static int dce_v11_0_early_init(void *handle)
 		adev->mode_info.num_dig = 9;
 		break;
 	case CHIP_POLARIS10:
+	case CHIP_VEGAM:
 		adev->mode_info.num_hpd = 6;
 		adev->mode_info.num_dig = 6;
 		break;
@@ -2949,7 +2948,8 @@ static int dce_v11_0_hw_init(void *handle)
 	amdgpu_atombios_encoder_init_dig(adev);
 	if ((adev->asic_type == CHIP_POLARIS10) ||
 	    (adev->asic_type == CHIP_POLARIS11) ||
-	    (adev->asic_type == CHIP_POLARIS12)) {
+	    (adev->asic_type == CHIP_POLARIS12) ||
+	    (adev->asic_type == CHIP_VEGAM)) {
 		amdgpu_atombios_crtc_set_dce_clock(adev, adev->clock.default_dispclk,
 						   DCE_CLOCK_TYPE_DISPCLK, ATOM_GCK_DFS);
 		amdgpu_atombios_crtc_set_dce_clock(adev, 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 9f67b7fd3487..394cc1e8fe20 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1780,7 +1780,6 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc,
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_framebuffer *amdgpu_fb;
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *abo;
@@ -1798,18 +1797,15 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc,
 		return 0;
 	}
 
-	if (atomic) {
-		amdgpu_fb = to_amdgpu_framebuffer(fb);
+	if (atomic)
 		target_fb = fb;
-	} else {
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
+	else
 		target_fb = crtc->primary->fb;
-	}
 
 	/* If atomic, assume fb object is pinned & idle & fenced and
 	 * just update base pointers
 	 */
-	obj = amdgpu_fb->obj;
+	obj = target_fb->obj[0];
 	abo = gem_to_amdgpu_bo(obj);
 	r = amdgpu_bo_reserve(abo, false);
 	if (unlikely(r != 0))
@@ -1978,8 +1974,7 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(mmMASTER_UPDATE_MODE + amdgpu_crtc->crtc_offset, 0);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
-		amdgpu_fb = to_amdgpu_framebuffer(fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r != 0))
 			return r;
@@ -2414,11 +2409,9 @@ static void dce_v6_0_crtc_disable(struct drm_crtc *crtc)
 	dce_v6_0_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 	if (crtc->primary->fb) {
 		int r;
-		struct amdgpu_framebuffer *amdgpu_fb;
 		struct amdgpu_bo *abo;
 
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(crtc->primary->fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r))
 			DRM_ERROR("failed to reserve abo before unpin\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index f55422cbd77a..c9b9ab8f1b05 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1754,7 +1754,6 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_framebuffer *amdgpu_fb;
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *abo;
@@ -1773,18 +1772,15 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 		return 0;
 	}
 
-	if (atomic) {
-		amdgpu_fb = to_amdgpu_framebuffer(fb);
+	if (atomic)
 		target_fb = fb;
-	} else {
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
+	else
 		target_fb = crtc->primary->fb;
-	}
 
 	/* If atomic, assume fb object is pinned & idle & fenced and
 	 * just update base pointers
 	 */
-	obj = amdgpu_fb->obj;
+	obj = target_fb->obj[0];
 	abo = gem_to_amdgpu_bo(obj);
 	r = amdgpu_bo_reserve(abo, false);
 	if (unlikely(r != 0))
@@ -1955,8 +1951,7 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(mmMASTER_UPDATE_MODE + amdgpu_crtc->crtc_offset, 0);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
-		amdgpu_fb = to_amdgpu_framebuffer(fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r != 0))
 			return r;
@@ -2430,11 +2425,9 @@ static void dce_v8_0_crtc_disable(struct drm_crtc *crtc)
 	dce_v8_0_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 	if (crtc->primary->fb) {
 		int r;
-		struct amdgpu_framebuffer *amdgpu_fb;
 		struct amdgpu_bo *abo;
 
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(crtc->primary->fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r))
 			DRM_ERROR("failed to reserve abo before unpin\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index b51f05dc9582..dbf2ccd0c744 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -168,11 +168,9 @@ static void dce_virtual_crtc_disable(struct drm_crtc *crtc)
 	dce_virtual_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 	if (crtc->primary->fb) {
 		int r;
-		struct amdgpu_framebuffer *amdgpu_fb;
 		struct amdgpu_bo *abo;
 
-		amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
-		abo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+		abo = gem_to_amdgpu_bo(crtc->primary->fb->obj[0]);
 		r = amdgpu_bo_reserve(abo, true);
 		if (unlikely(r))
 			DRM_ERROR("failed to reserve abo before unpin\n");
@@ -329,7 +327,7 @@ static int dce_virtual_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static int dce_virtual_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status dce_virtual_mode_valid(struct drm_connector *connector,
 				  struct drm_display_mode *mode)
 {
 	return MODE_OK;
@@ -462,8 +460,9 @@ static int dce_virtual_hw_init(void *handle)
 		break;
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
-	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_VEGAM:
 		dce_v11_0_disable_dce(adev);
 		break;
 	case CHIP_TOPAZ:
@@ -474,6 +473,7 @@ static int dce_virtual_hw_init(void *handle)
 		break;
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 		break;
 	default:
 		DRM_ERROR("Virtual display unsupported ASIC type: 0x%X\n", adev->asic_type);
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
new file mode 100644
index 000000000000..9935371db7ce
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
@@ -0,0 +1,120 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "df_v1_7.h"
+
+#include "df/df_1_7_default.h"
+#include "df/df_1_7_offset.h"
+#include "df/df_1_7_sh_mask.h"
+
+static u32 df_v1_7_channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
+
+static void df_v1_7_init (struct amdgpu_device *adev)
+{
+}
+
+static void df_v1_7_enable_broadcast_mode(struct amdgpu_device *adev,
+                                          bool enable)
+{
+	u32 tmp;
+
+	if (enable) {
+		tmp = RREG32_SOC15(DF, 0, mmFabricConfigAccessControl);
+		tmp &= ~FabricConfigAccessControl__CfgRegInstAccEn_MASK;
+		WREG32_SOC15(DF, 0, mmFabricConfigAccessControl, tmp);
+	} else
+		WREG32_SOC15(DF, 0, mmFabricConfigAccessControl,
+			     mmFabricConfigAccessControl_DEFAULT);
+}
+
+static u32 df_v1_7_get_fb_channel_number(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	tmp = RREG32_SOC15(DF, 0, mmDF_CS_AON0_DramBaseAddress0);
+	tmp &= DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK;
+	tmp >>= DF_CS_AON0_DramBaseAddress0__IntLvNumChan__SHIFT;
+
+	return tmp;
+}
+
+static u32 df_v1_7_get_hbm_channel_number(struct amdgpu_device *adev)
+{
+	int fb_channel_number;
+
+	fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
+
+	return df_v1_7_channel_number[fb_channel_number];
+}
+
+static void df_v1_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						     bool enable)
+{
+	u32 tmp;
+
+	/* Put DF on broadcast mode */
+	adev->df_funcs->enable_broadcast_mode(adev, true);
+
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) {
+		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
+		tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
+		tmp |= DF_V1_7_MGCG_ENABLE_15_CYCLE_DELAY;
+		WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+	} else {
+		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
+		tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
+		tmp |= DF_V1_7_MGCG_DISABLE;
+		WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+	}
+
+	/* Exit boradcast mode */
+	adev->df_funcs->enable_broadcast_mode(adev, false);
+}
+
+static void df_v1_7_get_clockgating_state(struct amdgpu_device *adev,
+					  u32 *flags)
+{
+	u32 tmp;
+
+	/* AMD_CG_SUPPORT_DF_MGCG */
+	tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
+	if (tmp & DF_V1_7_MGCG_ENABLE_15_CYCLE_DELAY)
+		*flags |= AMD_CG_SUPPORT_DF_MGCG;
+}
+
+static void df_v1_7_enable_ecc_force_par_wr_rmw(struct amdgpu_device *adev,
+						bool enable)
+{
+	WREG32_FIELD15(DF, 0, DF_CS_AON0_CoherentSlaveModeCtrlA0,
+		       ForceParWrRMW, enable);
+}
+
+const struct amdgpu_df_funcs df_v1_7_funcs = {
+	.init = df_v1_7_init,
+	.enable_broadcast_mode = df_v1_7_enable_broadcast_mode,
+	.get_fb_channel_number = df_v1_7_get_fb_channel_number,
+	.get_hbm_channel_number = df_v1_7_get_hbm_channel_number,
+	.update_medium_grain_clock_gating = df_v1_7_update_medium_grain_clock_gating,
+	.get_clockgating_state = df_v1_7_get_clockgating_state,
+	.enable_ecc_force_par_wr_rmw = df_v1_7_enable_ecc_force_par_wr_rmw,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegk104.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.h
index 780a1d973634..74621104c487 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegk104.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Red Hat Inc.
+ * Copyright 2018 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -19,20 +19,22 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
 
-#include <nvif/class.h>
+#ifndef __DF_V1_7_H__
+#define __DF_V1_7_H__
 
-const struct nv50_disp_dmac_oclass
-gk104_disp_base_oclass = {
-	.base.oclass = GK104_DISP_BASE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_base_new,
-	.func = &gf119_disp_dmac_func,
-	.mthd = &gf119_disp_base_chan_mthd,
-	.chid = 1,
+#include "soc15_common.h"
+enum DF_V1_7_MGCG
+{
+	DF_V1_7_MGCG_DISABLE = 0,
+	DF_V1_7_MGCG_ENABLE_00_CYCLE_DELAY =1,
+	DF_V1_7_MGCG_ENABLE_01_CYCLE_DELAY =2,
+	DF_V1_7_MGCG_ENABLE_15_CYCLE_DELAY =13,
+	DF_V1_7_MGCG_ENABLE_31_CYCLE_DELAY =14,
+	DF_V1_7_MGCG_ENABLE_63_CYCLE_DELAY =15
 };
+
+extern const struct amdgpu_df_funcs df_v1_7_funcs;
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
new file mode 100644
index 000000000000..60608b3df881
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "df_v3_6.h"
+
+#include "df/df_3_6_default.h"
+#include "df/df_3_6_offset.h"
+#include "df/df_3_6_sh_mask.h"
+
+static u32 df_v3_6_channel_number[] = {1, 2, 0, 4, 0, 8, 0,
+				       16, 32, 0, 0, 0, 2, 4, 8};
+
+static void df_v3_6_init(struct amdgpu_device *adev)
+{
+}
+
+static void df_v3_6_enable_broadcast_mode(struct amdgpu_device *adev,
+					  bool enable)
+{
+	u32 tmp;
+
+	if (enable) {
+		tmp = RREG32_SOC15(DF, 0, mmFabricConfigAccessControl);
+		tmp &= ~FabricConfigAccessControl__CfgRegInstAccEn_MASK;
+		WREG32_SOC15(DF, 0, mmFabricConfigAccessControl, tmp);
+	} else
+		WREG32_SOC15(DF, 0, mmFabricConfigAccessControl,
+			     mmFabricConfigAccessControl_DEFAULT);
+}
+
+static u32 df_v3_6_get_fb_channel_number(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	tmp = RREG32_SOC15(DF, 0, mmDF_CS_UMC_AON0_DramBaseAddress0);
+	tmp &= DF_CS_UMC_AON0_DramBaseAddress0__IntLvNumChan_MASK;
+	tmp >>= DF_CS_UMC_AON0_DramBaseAddress0__IntLvNumChan__SHIFT;
+
+	return tmp;
+}
+
+static u32 df_v3_6_get_hbm_channel_number(struct amdgpu_device *adev)
+{
+	int fb_channel_number;
+
+	fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
+	if (fb_channel_number > ARRAY_SIZE(df_v3_6_channel_number))
+		fb_channel_number = 0;
+
+	return df_v3_6_channel_number[fb_channel_number];
+}
+
+static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						     bool enable)
+{
+	u32 tmp;
+
+	/* Put DF on broadcast mode */
+	adev->df_funcs->enable_broadcast_mode(adev, true);
+
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) {
+		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
+		tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
+		tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY;
+		WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+	} else {
+		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
+		tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
+		tmp |= DF_V3_6_MGCG_DISABLE;
+		WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+	}
+
+	/* Exit broadcast mode */
+	adev->df_funcs->enable_broadcast_mode(adev, false);
+}
+
+static void df_v3_6_get_clockgating_state(struct amdgpu_device *adev,
+					  u32 *flags)
+{
+	u32 tmp;
+
+	/* AMD_CG_SUPPORT_DF_MGCG */
+	tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
+	if (tmp & DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY)
+		*flags |= AMD_CG_SUPPORT_DF_MGCG;
+}
+
+const struct amdgpu_df_funcs df_v3_6_funcs = {
+	.init = df_v3_6_init,
+	.enable_broadcast_mode = df_v3_6_enable_broadcast_mode,
+	.get_fb_channel_number = df_v3_6_get_fb_channel_number,
+	.get_hbm_channel_number = df_v3_6_get_hbm_channel_number,
+	.update_medium_grain_clock_gating =
+			df_v3_6_update_medium_grain_clock_gating,
+	.get_clockgating_state = df_v3_6_get_clockgating_state,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegt200.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.h
index 93451e46570c..e79c58e5efcb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegt200.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Red Hat Inc.
+ * Copyright 2018 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -19,20 +19,22 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
 
-#include <nvif/class.h>
+#ifndef __DF_V3_6_H__
+#define __DF_V3_6_H__
 
-const struct nv50_disp_dmac_oclass
-gt200_disp_base_oclass = {
-	.base.oclass = GT200_DISP_BASE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_base_new,
-	.func = &nv50_disp_dmac_func,
-	.mthd = &g84_disp_base_chan_mthd,
-	.chid = 1,
+#include "soc15_common.h"
+
+enum DF_V3_6_MGCG {
+	DF_V3_6_MGCG_DISABLE = 0,
+	DF_V3_6_MGCG_ENABLE_00_CYCLE_DELAY = 1,
+	DF_V3_6_MGCG_ENABLE_01_CYCLE_DELAY = 2,
+	DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY = 13,
+	DF_V3_6_MGCG_ENABLE_31_CYCLE_DELAY = 14,
+	DF_V3_6_MGCG_ENABLE_63_CYCLE_DELAY = 15
 };
+
+extern const struct amdgpu_df_funcs df_v3_6_funcs;
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index b0e591eaa71a..818874b13c99 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -125,18 +125,6 @@ MODULE_FIRMWARE("amdgpu/fiji_mec.bin");
 MODULE_FIRMWARE("amdgpu/fiji_mec2.bin");
 MODULE_FIRMWARE("amdgpu/fiji_rlc.bin");
 
-MODULE_FIRMWARE("amdgpu/polaris11_ce.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_ce_2.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_pfp.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_pfp_2.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_me.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_me_2.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_mec.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_mec_2.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_mec2.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_mec2_2.bin");
-MODULE_FIRMWARE("amdgpu/polaris11_rlc.bin");
-
 MODULE_FIRMWARE("amdgpu/polaris10_ce.bin");
 MODULE_FIRMWARE("amdgpu/polaris10_ce_2.bin");
 MODULE_FIRMWARE("amdgpu/polaris10_pfp.bin");
@@ -149,6 +137,18 @@ MODULE_FIRMWARE("amdgpu/polaris10_mec2.bin");
 MODULE_FIRMWARE("amdgpu/polaris10_mec2_2.bin");
 MODULE_FIRMWARE("amdgpu/polaris10_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/polaris11_ce.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_ce_2.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_pfp.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_pfp_2.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_me.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_me_2.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_mec.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_mec_2.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_mec2.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_mec2_2.bin");
+MODULE_FIRMWARE("amdgpu/polaris11_rlc.bin");
+
 MODULE_FIRMWARE("amdgpu/polaris12_ce.bin");
 MODULE_FIRMWARE("amdgpu/polaris12_ce_2.bin");
 MODULE_FIRMWARE("amdgpu/polaris12_pfp.bin");
@@ -161,6 +161,13 @@ MODULE_FIRMWARE("amdgpu/polaris12_mec2.bin");
 MODULE_FIRMWARE("amdgpu/polaris12_mec2_2.bin");
 MODULE_FIRMWARE("amdgpu/polaris12_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/vegam_ce.bin");
+MODULE_FIRMWARE("amdgpu/vegam_pfp.bin");
+MODULE_FIRMWARE("amdgpu/vegam_me.bin");
+MODULE_FIRMWARE("amdgpu/vegam_mec.bin");
+MODULE_FIRMWARE("amdgpu/vegam_mec2.bin");
+MODULE_FIRMWARE("amdgpu/vegam_rlc.bin");
+
 static const struct amdgpu_gds_reg_offset amdgpu_gds_reg_offset[] =
 {
 	{mmGDS_VMID0_BASE, mmGDS_VMID0_SIZE, mmGDS_GWS_VMID0, mmGDS_OA_VMID0},
@@ -292,6 +299,37 @@ static const u32 tonga_mgcg_cgcg_init[] =
 	mmCP_MEM_SLP_CNTL, 0x00000001, 0x00000001,
 };
 
+static const u32 golden_settings_vegam_a11[] =
+{
+	mmCB_HW_CONTROL, 0x0001f3cf, 0x00007208,
+	mmCB_HW_CONTROL_2, 0x0f000000, 0x0d000000,
+	mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
+	mmDB_DEBUG2, 0xf00fffff, 0x00000400,
+	mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
+	mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000,
+	mmPA_SC_RASTER_CONFIG, 0x3f3fffff, 0x3a00161a,
+	mmPA_SC_RASTER_CONFIG_1, 0x0000003f, 0x0000002e,
+	mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0001003c,
+	mmRLC_CGCG_CGLS_CTRL_3D, 0xffffffff, 0x0001003c,
+	mmSQ_CONFIG, 0x07f80000, 0x01180000,
+	mmTA_CNTL_AUX, 0x000f000f, 0x000b0000,
+	mmTCC_CTRL, 0x00100000, 0xf31fff7f,
+	mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f7,
+	mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000,
+	mmTCP_CHAN_STEER_LO, 0xffffffff, 0x32761054,
+	mmVGT_RESET_DEBUG, 0x00000004, 0x00000004,
+};
+
+static const u32 vegam_golden_common_all[] =
+{
+	mmGRBM_GFX_INDEX, 0xffffffff, 0xe0000000,
+	mmGB_ADDR_CONFIG, 0xffffffff, 0x22011003,
+	mmSPI_RESOURCE_RESERVE_CU_0, 0xffffffff, 0x00000800,
+	mmSPI_RESOURCE_RESERVE_CU_1, 0xffffffff, 0x00000800,
+	mmSPI_RESOURCE_RESERVE_EN_CU_0, 0xffffffff, 0x00FF7FBF,
+	mmSPI_RESOURCE_RESERVE_EN_CU_1, 0xffffffff, 0x00FF7FAF,
+};
+
 static const u32 golden_settings_polaris11_a11[] =
 {
 	mmCB_HW_CONTROL, 0x0000f3cf, 0x00007208,
@@ -712,6 +750,14 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev)
 							tonga_golden_common_all,
 							ARRAY_SIZE(tonga_golden_common_all));
 		break;
+	case CHIP_VEGAM:
+		amdgpu_device_program_register_sequence(adev,
+							golden_settings_vegam_a11,
+							ARRAY_SIZE(golden_settings_vegam_a11));
+		amdgpu_device_program_register_sequence(adev,
+							vegam_golden_common_all,
+							ARRAY_SIZE(vegam_golden_common_all));
+		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
 		amdgpu_device_program_register_sequence(adev,
@@ -918,17 +964,20 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev)
 	case CHIP_FIJI:
 		chip_name = "fiji";
 		break;
-	case CHIP_POLARIS11:
-		chip_name = "polaris11";
+	case CHIP_STONEY:
+		chip_name = "stoney";
 		break;
 	case CHIP_POLARIS10:
 		chip_name = "polaris10";
 		break;
+	case CHIP_POLARIS11:
+		chip_name = "polaris11";
+		break;
 	case CHIP_POLARIS12:
 		chip_name = "polaris12";
 		break;
-	case CHIP_STONEY:
-		chip_name = "stoney";
+	case CHIP_VEGAM:
+		chip_name = "vegam";
 		break;
 	default:
 		BUG();
@@ -1459,10 +1508,11 @@ static const u32 sgpr_init_compute_shader[] =
 static const u32 vgpr_init_regs[] =
 {
 	mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0xffffffff,
-	mmCOMPUTE_RESOURCE_LIMITS, 0,
+	mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */
 	mmCOMPUTE_NUM_THREAD_X, 256*4,
 	mmCOMPUTE_NUM_THREAD_Y, 1,
 	mmCOMPUTE_NUM_THREAD_Z, 1,
+	mmCOMPUTE_PGM_RSRC1, 0x100004f, /* VGPRS=15 (64 logical VGPRs), SGPRS=1 (16 SGPRs), BULKY=1 */
 	mmCOMPUTE_PGM_RSRC2, 20,
 	mmCOMPUTE_USER_DATA_0, 0xedcedc00,
 	mmCOMPUTE_USER_DATA_1, 0xedcedc01,
@@ -1479,10 +1529,11 @@ static const u32 vgpr_init_regs[] =
 static const u32 sgpr1_init_regs[] =
 {
 	mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0x0f,
-	mmCOMPUTE_RESOURCE_LIMITS, 0x1000000,
+	mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */
 	mmCOMPUTE_NUM_THREAD_X, 256*5,
 	mmCOMPUTE_NUM_THREAD_Y, 1,
 	mmCOMPUTE_NUM_THREAD_Z, 1,
+	mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */
 	mmCOMPUTE_PGM_RSRC2, 20,
 	mmCOMPUTE_USER_DATA_0, 0xedcedc00,
 	mmCOMPUTE_USER_DATA_1, 0xedcedc01,
@@ -1503,6 +1554,7 @@ static const u32 sgpr2_init_regs[] =
 	mmCOMPUTE_NUM_THREAD_X, 256*5,
 	mmCOMPUTE_NUM_THREAD_Y, 1,
 	mmCOMPUTE_NUM_THREAD_Z, 1,
+	mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */
 	mmCOMPUTE_PGM_RSRC2, 20,
 	mmCOMPUTE_USER_DATA_0, 0xedcedc00,
 	mmCOMPUTE_USER_DATA_1, 0xedcedc01,
@@ -1767,6 +1819,7 @@ static int gfx_v8_0_gpu_early_init(struct amdgpu_device *adev)
 		gb_addr_config = POLARIS11_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	case CHIP_POLARIS10:
+	case CHIP_VEGAM:
 		ret = amdgpu_atombios_get_gfx_info(adev);
 		if (ret)
 			return ret;
@@ -1954,12 +2007,13 @@ static int gfx_v8_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	switch (adev->asic_type) {
-	case CHIP_FIJI:
 	case CHIP_TONGA:
+	case CHIP_CARRIZO:
+	case CHIP_FIJI:
+	case CHIP_POLARIS10:
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
-	case CHIP_POLARIS10:
-	case CHIP_CARRIZO:
+	case CHIP_VEGAM:
 		adev->gfx.mec.num_mec = 2;
 		break;
 	case CHIP_TOPAZ:
@@ -2320,6 +2374,7 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev)
 
 		break;
 	case CHIP_FIJI:
+	case CHIP_VEGAM:
 		modearray[0] = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 				PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
 				TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
@@ -3501,6 +3556,7 @@ gfx_v8_0_raster_config(struct amdgpu_device *adev, u32 *rconf, u32 *rconf1)
 {
 	switch (adev->asic_type) {
 	case CHIP_FIJI:
+	case CHIP_VEGAM:
 		*rconf |= RB_MAP_PKR0(2) | RB_MAP_PKR1(2) |
 			  RB_XSEL2(1) | PKR_MAP(2) |
 			  PKR_XSEL(1) | PKR_YSEL(1) |
@@ -4068,7 +4124,8 @@ static void gfx_v8_0_init_pg(struct amdgpu_device *adev)
 		gfx_v8_0_init_power_gating(adev);
 		WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, adev->gfx.cu_info.ao_cu_mask);
 	} else if ((adev->asic_type == CHIP_POLARIS11) ||
-		   (adev->asic_type == CHIP_POLARIS12)) {
+		   (adev->asic_type == CHIP_POLARIS12) ||
+		   (adev->asic_type == CHIP_VEGAM)) {
 		gfx_v8_0_init_csb(adev);
 		gfx_v8_0_init_save_restore_list(adev);
 		gfx_v8_0_enable_save_restore_machine(adev);
@@ -4143,7 +4200,8 @@ static int gfx_v8_0_rlc_resume(struct amdgpu_device *adev)
 	WREG32(mmRLC_CGCG_CGLS_CTRL, tmp);
 	if (adev->asic_type == CHIP_POLARIS11 ||
 	    adev->asic_type == CHIP_POLARIS10 ||
-	    adev->asic_type == CHIP_POLARIS12) {
+	    adev->asic_type == CHIP_POLARIS12 ||
+	    adev->asic_type == CHIP_VEGAM) {
 		tmp = RREG32(mmRLC_CGCG_CGLS_CTRL_3D);
 		tmp &= ~0x3;
 		WREG32(mmRLC_CGCG_CGLS_CTRL_3D, tmp);
@@ -5495,7 +5553,8 @@ static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *ade
 						       bool enable)
 {
 	if ((adev->asic_type == CHIP_POLARIS11) ||
-	    (adev->asic_type == CHIP_POLARIS12))
+	    (adev->asic_type == CHIP_POLARIS12) ||
+	    (adev->asic_type == CHIP_VEGAM))
 		/* Send msg to SMU via Powerplay */
 		amdgpu_device_ip_set_powergating_state(adev,
 						       AMD_IP_BLOCK_TYPE_SMC,
@@ -5585,6 +5644,7 @@ static int gfx_v8_0_set_powergating_state(void *handle,
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 		if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) && enable)
 			gfx_v8_0_enable_gfx_static_mg_power_gating(adev, true);
 		else
@@ -6151,6 +6211,7 @@ static int gfx_v8_0_set_clockgating_state(void *handle,
 	case CHIP_POLARIS10:
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 		gfx_v8_0_polaris_update_gfx_clock_gating(adev, state);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 9d39fd5b1822..d7530fdfaad5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -27,6 +27,7 @@
 #include "amdgpu_gfx.h"
 #include "soc15.h"
 #include "soc15d.h"
+#include "amdgpu_atomfirmware.h"
 
 #include "gc/gc_9_0_offset.h"
 #include "gc/gc_9_0_sh_mask.h"
@@ -41,7 +42,6 @@
 #define GFX9_MEC_HPD_SIZE 2048
 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L
 #define RLC_SAVE_RESTORE_ADDR_STARTING_OFFSET 0x00000000L
-#define GFX9_RLC_FORMAT_DIRECT_REG_LIST_LENGTH 34
 
 #define mmPWR_MISC_CNTL_STATUS					0x0183
 #define mmPWR_MISC_CNTL_STATUS_BASE_IDX				0
@@ -64,6 +64,13 @@ MODULE_FIRMWARE("amdgpu/vega12_mec.bin");
 MODULE_FIRMWARE("amdgpu/vega12_mec2.bin");
 MODULE_FIRMWARE("amdgpu/vega12_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/vega20_ce.bin");
+MODULE_FIRMWARE("amdgpu/vega20_pfp.bin");
+MODULE_FIRMWARE("amdgpu/vega20_me.bin");
+MODULE_FIRMWARE("amdgpu/vega20_mec.bin");
+MODULE_FIRMWARE("amdgpu/vega20_mec2.bin");
+MODULE_FIRMWARE("amdgpu/vega20_rlc.bin");
+
 MODULE_FIRMWARE("amdgpu/raven_ce.bin");
 MODULE_FIRMWARE("amdgpu/raven_pfp.bin");
 MODULE_FIRMWARE("amdgpu/raven_me.bin");
@@ -73,29 +80,22 @@ MODULE_FIRMWARE("amdgpu/raven_rlc.bin");
 
 static const struct soc15_reg_golden golden_settings_gc_9_0[] =
 {
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPC_UTCL1_CNTL, 0x08000000, 0x08000080),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_UTCL1_CNTL, 0x08000000, 0x08000080),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPG_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG2, 0xf00fffff, 0x00000420),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_GPU_ID, 0x0000000f, 0x00000000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmIA_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_EVENT_CNTL_3, 0x00000003, 0x82400024),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE, 0x3fffffff, 0x00000001),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_0, 0x08000000, 0x08000080),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_1, 0x08000000, 0x08000080),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_2, 0x08000000, 0x08000080),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_PREWALKER_UTCL1_CNTL, 0x08000000, 0x08000080),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_SPM_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSH_MEM_CONFIG, 0x00001000, 0x00001000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x0000000f, 0x01000107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_RESOURCE_RESERVE_CU_0, 0x0007ffff, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_RESOURCE_RESERVE_CU_1, 0x0007ffff, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_RESOURCE_RESERVE_EN_CU_0, 0x01ffffff, 0x0000ff87),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_RESOURCE_RESERVE_EN_CU_1, 0x01ffffff, 0x0000ff8f),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQC_CONFIG, 0x03000000, 0x020a2000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfffffeef, 0x010b0000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x4a2c0e68),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_LO, 0xffffffff, 0xb5d3f197),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_CACHE_INVALIDATION, 0x3fff3af3, 0x19200000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000003ff),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000003ff)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
@@ -109,6 +109,20 @@ static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800)
 };
 
+static const struct soc15_reg_golden golden_settings_gc_9_0_vg20[] =
+{
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_2, 0x0f000000, 0x0a000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0x30000000, 0x10000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0xf3e777ff, 0x22014042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG_READ, 0xf3e777ff, 0x22014042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG2, 0x00003e00, 0x00000400),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0xff840000, 0x04040000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_UTCL1_CNTL2, 0x00030000, 0x00030000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0xffff010f, 0x01000107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0x000b0000, 0x000b0000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x01000000, 0x01000000)
+};
+
 static const struct soc15_reg_golden golden_settings_gc_9_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL, 0xfffdf3cf, 0x00014104),
@@ -185,6 +199,30 @@ static const struct soc15_reg_golden golden_settings_gc_9_2_1_vg12[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x01bd9f33, 0x01000000)
 };
 
+static const u32 GFX_RLC_SRM_INDEX_CNTL_ADDR_OFFSETS[] =
+{
+	mmRLC_SRM_INDEX_CNTL_ADDR_0 - mmRLC_SRM_INDEX_CNTL_ADDR_0,
+	mmRLC_SRM_INDEX_CNTL_ADDR_1 - mmRLC_SRM_INDEX_CNTL_ADDR_0,
+	mmRLC_SRM_INDEX_CNTL_ADDR_2 - mmRLC_SRM_INDEX_CNTL_ADDR_0,
+	mmRLC_SRM_INDEX_CNTL_ADDR_3 - mmRLC_SRM_INDEX_CNTL_ADDR_0,
+	mmRLC_SRM_INDEX_CNTL_ADDR_4 - mmRLC_SRM_INDEX_CNTL_ADDR_0,
+	mmRLC_SRM_INDEX_CNTL_ADDR_5 - mmRLC_SRM_INDEX_CNTL_ADDR_0,
+	mmRLC_SRM_INDEX_CNTL_ADDR_6 - mmRLC_SRM_INDEX_CNTL_ADDR_0,
+	mmRLC_SRM_INDEX_CNTL_ADDR_7 - mmRLC_SRM_INDEX_CNTL_ADDR_0,
+};
+
+static const u32 GFX_RLC_SRM_INDEX_CNTL_DATA_OFFSETS[] =
+{
+	mmRLC_SRM_INDEX_CNTL_DATA_0 - mmRLC_SRM_INDEX_CNTL_DATA_0,
+	mmRLC_SRM_INDEX_CNTL_DATA_1 - mmRLC_SRM_INDEX_CNTL_DATA_0,
+	mmRLC_SRM_INDEX_CNTL_DATA_2 - mmRLC_SRM_INDEX_CNTL_DATA_0,
+	mmRLC_SRM_INDEX_CNTL_DATA_3 - mmRLC_SRM_INDEX_CNTL_DATA_0,
+	mmRLC_SRM_INDEX_CNTL_DATA_4 - mmRLC_SRM_INDEX_CNTL_DATA_0,
+	mmRLC_SRM_INDEX_CNTL_DATA_5 - mmRLC_SRM_INDEX_CNTL_DATA_0,
+	mmRLC_SRM_INDEX_CNTL_DATA_6 - mmRLC_SRM_INDEX_CNTL_DATA_0,
+	mmRLC_SRM_INDEX_CNTL_DATA_7 - mmRLC_SRM_INDEX_CNTL_DATA_0,
+};
+
 #define VEGA10_GB_ADDR_CONFIG_GOLDEN 0x2a114042
 #define VEGA12_GB_ADDR_CONFIG_GOLDEN 0x24104041
 #define RAVEN_GB_ADDR_CONFIG_GOLDEN 0x24000042
@@ -218,6 +256,14 @@ static void gfx_v9_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_gc_9_2_1_vg12,
 						ARRAY_SIZE(golden_settings_gc_9_2_1_vg12));
 		break;
+	case CHIP_VEGA20:
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_9_0,
+						ARRAY_SIZE(golden_settings_gc_9_0));
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_9_0_vg20,
+						ARRAY_SIZE(golden_settings_gc_9_0_vg20));
+		break;
 	case CHIP_RAVEN:
 		soc15_program_register_sequence(adev,
 						 golden_settings_gc_9_1,
@@ -401,6 +447,27 @@ static void gfx_v9_0_free_microcode(struct amdgpu_device *adev)
 	kfree(adev->gfx.rlc.register_list_format);
 }
 
+static void gfx_v9_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
+{
+	const struct rlc_firmware_header_v2_1 *rlc_hdr;
+
+	rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data;
+	adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver);
+	adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver);
+	adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes);
+	adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes);
+	adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver);
+	adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver);
+	adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes);
+	adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes);
+	adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver);
+	adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver);
+	adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes);
+	adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes);
+	adev->gfx.rlc.reg_list_format_direct_reg_list_length =
+			le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
+}
+
 static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 {
 	const char *chip_name;
@@ -412,6 +479,8 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 	const struct rlc_firmware_header_v2_0 *rlc_hdr;
 	unsigned int *tmp = NULL;
 	unsigned int i = 0;
+	uint16_t version_major;
+	uint16_t version_minor;
 
 	DRM_DEBUG("\n");
 
@@ -422,6 +491,9 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 	case CHIP_VEGA12:
 		chip_name = "vega12";
 		break;
+	case CHIP_VEGA20:
+		chip_name = "vega20";
+		break;
 	case CHIP_RAVEN:
 		chip_name = "raven";
 		break;
@@ -468,6 +540,12 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 		goto out;
 	err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
 	rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
+
+	version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
+	version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
+	if (version_major == 2 && version_minor == 1)
+		adev->gfx.rlc.is_rlc_v2_1 = true;
+
 	adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
 	adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
 	adev->gfx.rlc.save_and_restore_offset =
@@ -508,6 +586,9 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 	for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
 		adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
 
+	if (adev->gfx.rlc.is_rlc_v2_1)
+		gfx_v9_0_init_rlc_ext_microcode(adev);
+
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
 	if (err)
@@ -566,6 +647,26 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 
+		if (adev->gfx.rlc.is_rlc_v2_1) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.save_restore_list_cntl_size_bytes, PAGE_SIZE);
+
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE);
+
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE);
+		}
+
 		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1];
 		info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1;
 		info->fw = adev->gfx.mec_fw;
@@ -1013,9 +1114,10 @@ static const struct amdgpu_gfx_funcs gfx_v9_0_gfx_funcs = {
 	.select_me_pipe_q = &gfx_v9_0_select_me_pipe_q
 };
 
-static void gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
+static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 {
 	u32 gb_addr_config;
+	int err;
 
 	adev->gfx.funcs = &gfx_v9_0_gfx_funcs;
 
@@ -1037,6 +1139,20 @@ static void gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 		gb_addr_config = VEGA12_GB_ADDR_CONFIG_GOLDEN;
 		DRM_INFO("fix gfx.config for vega12\n");
 		break;
+	case CHIP_VEGA20:
+		adev->gfx.config.max_hw_contexts = 8;
+		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+		adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
+		adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0;
+		gb_addr_config = RREG32_SOC15(GC, 0, mmGB_ADDR_CONFIG);
+		gb_addr_config &= ~0xf3e777ff;
+		gb_addr_config |= 0x22014042;
+		/* check vbios table if gpu info is not available */
+		err = amdgpu_atomfirmware_get_gfx_info(adev);
+		if (err)
+			return err;
+		break;
 	case CHIP_RAVEN:
 		adev->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
@@ -1086,6 +1202,8 @@ static void gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 					adev->gfx.config.gb_addr_config,
 					GB_ADDR_CONFIG,
 					PIPE_INTERLEAVE_SIZE));
+
+	return 0;
 }
 
 static int gfx_v9_0_ngg_create_buf(struct amdgpu_device *adev,
@@ -1319,6 +1437,7 @@ static int gfx_v9_0_sw_init(void *handle)
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 	case CHIP_RAVEN:
 		adev->gfx.mec.num_mec = 2;
 		break;
@@ -1446,7 +1565,9 @@ static int gfx_v9_0_sw_init(void *handle)
 
 	adev->gfx.ce_ram_size = 0x8000;
 
-	gfx_v9_0_gpu_early_init(adev);
+	r = gfx_v9_0_gpu_early_init(adev);
+	if (r)
+		return r;
 
 	r = gfx_v9_0_ngg_init(adev);
 	if (r)
@@ -1600,6 +1721,7 @@ static void gfx_v9_0_gpu_init(struct amdgpu_device *adev)
 
 	gfx_v9_0_setup_rb(adev);
 	gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info);
+	adev->gfx.config.db_debug2 = RREG32_SOC15(GC, 0, mmDB_DEBUG2);
 
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
@@ -1616,7 +1738,10 @@ static void gfx_v9_0_gpu_init(struct amdgpu_device *adev)
 			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
 					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
 			WREG32_SOC15(GC, 0, mmSH_MEM_CONFIG, tmp);
-			tmp = adev->gmc.shared_aperture_start >> 48;
+			tmp = REG_SET_FIELD(0, SH_MEM_BASES, PRIVATE_BASE,
+				(adev->gmc.private_aperture_start >> 48));
+			tmp = REG_SET_FIELD(tmp, SH_MEM_BASES, SHARED_BASE,
+				(adev->gmc.shared_aperture_start >> 48));
 			WREG32_SOC15(GC, 0, mmSH_MEM_BASES, tmp);
 		}
 	}
@@ -1708,55 +1833,42 @@ static void gfx_v9_0_init_csb(struct amdgpu_device *adev)
 			adev->gfx.rlc.clear_state_size);
 }
 
-static void gfx_v9_0_parse_ind_reg_list(int *register_list_format,
+static void gfx_v9_1_parse_ind_reg_list(int *register_list_format,
 				int indirect_offset,
 				int list_size,
 				int *unique_indirect_regs,
 				int *unique_indirect_reg_count,
-				int max_indirect_reg_count,
 				int *indirect_start_offsets,
-				int *indirect_start_offsets_count,
-				int max_indirect_start_offsets_count)
+				int *indirect_start_offsets_count)
 {
 	int idx;
-	bool new_entry = true;
 
 	for (; indirect_offset < list_size; indirect_offset++) {
+		indirect_start_offsets[*indirect_start_offsets_count] = indirect_offset;
+		*indirect_start_offsets_count = *indirect_start_offsets_count + 1;
 
-		if (new_entry) {
-			new_entry = false;
-			indirect_start_offsets[*indirect_start_offsets_count] = indirect_offset;
-			*indirect_start_offsets_count = *indirect_start_offsets_count + 1;
-			BUG_ON(*indirect_start_offsets_count >= max_indirect_start_offsets_count);
-		}
+		while (register_list_format[indirect_offset] != 0xFFFFFFFF) {
+			indirect_offset += 2;
 
-		if (register_list_format[indirect_offset] == 0xFFFFFFFF) {
-			new_entry = true;
-			continue;
-		}
+			/* look for the matching indice */
+			for (idx = 0; idx < *unique_indirect_reg_count; idx++) {
+				if (unique_indirect_regs[idx] ==
+					register_list_format[indirect_offset] ||
+					!unique_indirect_regs[idx])
+					break;
+			}
 
-		indirect_offset += 2;
+			BUG_ON(idx >= *unique_indirect_reg_count);
 
-		/* look for the matching indice */
-		for (idx = 0; idx < *unique_indirect_reg_count; idx++) {
-			if (unique_indirect_regs[idx] ==
-				register_list_format[indirect_offset])
-				break;
-		}
+			if (!unique_indirect_regs[idx])
+				unique_indirect_regs[idx] = register_list_format[indirect_offset];
 
-		if (idx >= *unique_indirect_reg_count) {
-			unique_indirect_regs[*unique_indirect_reg_count] =
-				register_list_format[indirect_offset];
-			idx = *unique_indirect_reg_count;
-			*unique_indirect_reg_count = *unique_indirect_reg_count + 1;
-			BUG_ON(*unique_indirect_reg_count >= max_indirect_reg_count);
+			indirect_offset++;
 		}
-
-		register_list_format[indirect_offset] = idx;
 	}
 }
 
-static int gfx_v9_0_init_rlc_save_restore_list(struct amdgpu_device *adev)
+static int gfx_v9_1_init_rlc_save_restore_list(struct amdgpu_device *adev)
 {
 	int unique_indirect_regs[] = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0};
 	int unique_indirect_reg_count = 0;
@@ -1765,7 +1877,7 @@ static int gfx_v9_0_init_rlc_save_restore_list(struct amdgpu_device *adev)
 	int indirect_start_offsets_count = 0;
 
 	int list_size = 0;
-	int i = 0;
+	int i = 0, j = 0;
 	u32 tmp = 0;
 
 	u32 *register_list_format =
@@ -1776,15 +1888,14 @@ static int gfx_v9_0_init_rlc_save_restore_list(struct amdgpu_device *adev)
 		adev->gfx.rlc.reg_list_format_size_bytes);
 
 	/* setup unique_indirect_regs array and indirect_start_offsets array */
-	gfx_v9_0_parse_ind_reg_list(register_list_format,
-				GFX9_RLC_FORMAT_DIRECT_REG_LIST_LENGTH,
-				adev->gfx.rlc.reg_list_format_size_bytes >> 2,
-				unique_indirect_regs,
-				&unique_indirect_reg_count,
-				ARRAY_SIZE(unique_indirect_regs),
-				indirect_start_offsets,
-				&indirect_start_offsets_count,
-				ARRAY_SIZE(indirect_start_offsets));
+	unique_indirect_reg_count = ARRAY_SIZE(unique_indirect_regs);
+	gfx_v9_1_parse_ind_reg_list(register_list_format,
+				    adev->gfx.rlc.reg_list_format_direct_reg_list_length,
+				    adev->gfx.rlc.reg_list_format_size_bytes >> 2,
+				    unique_indirect_regs,
+				    &unique_indirect_reg_count,
+				    indirect_start_offsets,
+				    &indirect_start_offsets_count);
 
 	/* enable auto inc in case it is disabled */
 	tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_CNTL));
@@ -1798,19 +1909,37 @@ static int gfx_v9_0_init_rlc_save_restore_list(struct amdgpu_device *adev)
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_ARAM_DATA),
 			adev->gfx.rlc.register_restore[i]);
 
-	/* load direct register */
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_ARAM_ADDR), 0);
-	for (i = 0; i < adev->gfx.rlc.reg_list_size_bytes >> 2; i++)
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_ARAM_DATA),
-			adev->gfx.rlc.register_restore[i]);
-
 	/* load indirect register */
 	WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_SCRATCH_ADDR),
 		adev->gfx.rlc.reg_list_format_start);
-	for (i = 0; i < adev->gfx.rlc.reg_list_format_size_bytes >> 2; i++)
+
+	/* direct register portion */
+	for (i = 0; i < adev->gfx.rlc.reg_list_format_direct_reg_list_length; i++)
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_SCRATCH_DATA),
 			register_list_format[i]);
 
+	/* indirect register portion */
+	while (i < (adev->gfx.rlc.reg_list_format_size_bytes >> 2)) {
+		if (register_list_format[i] == 0xFFFFFFFF) {
+			WREG32_SOC15(GC, 0, mmRLC_GPM_SCRATCH_DATA, register_list_format[i++]);
+			continue;
+		}
+
+		WREG32_SOC15(GC, 0, mmRLC_GPM_SCRATCH_DATA, register_list_format[i++]);
+		WREG32_SOC15(GC, 0, mmRLC_GPM_SCRATCH_DATA, register_list_format[i++]);
+
+		for (j = 0; j < unique_indirect_reg_count; j++) {
+			if (register_list_format[i] == unique_indirect_regs[j]) {
+				WREG32_SOC15(GC, 0, mmRLC_GPM_SCRATCH_DATA, j);
+				break;
+			}
+		}
+
+		BUG_ON(j >= unique_indirect_reg_count);
+
+		i++;
+	}
+
 	/* set save/restore list size */
 	list_size = adev->gfx.rlc.reg_list_size_bytes >> 2;
 	list_size = list_size >> 1;
@@ -1823,14 +1952,19 @@ static int gfx_v9_0_init_rlc_save_restore_list(struct amdgpu_device *adev)
 		adev->gfx.rlc.starting_offsets_start);
 	for (i = 0; i < ARRAY_SIZE(indirect_start_offsets); i++)
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_GPM_SCRATCH_DATA),
-			indirect_start_offsets[i]);
+		       indirect_start_offsets[i]);
 
 	/* load unique indirect regs*/
 	for (i = 0; i < ARRAY_SIZE(unique_indirect_regs); i++) {
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_INDEX_CNTL_ADDR_0) + i,
-			unique_indirect_regs[i] & 0x3FFFF);
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_INDEX_CNTL_DATA_0) + i,
-			unique_indirect_regs[i] >> 20);
+		if (unique_indirect_regs[i] != 0) {
+			WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_INDEX_CNTL_ADDR_0)
+			       + GFX_RLC_SRM_INDEX_CNTL_ADDR_OFFSETS[i],
+			       unique_indirect_regs[i] & 0x3FFFF);
+
+			WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_INDEX_CNTL_DATA_0)
+			       + GFX_RLC_SRM_INDEX_CNTL_DATA_OFFSETS[i],
+			       unique_indirect_regs[i] >> 20);
+		}
 	}
 
 	kfree(register_list_format);
@@ -2010,6 +2144,9 @@ static void gfx_v9_0_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *ad
 
 static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 {
+	if (!adev->gfx.rlc.is_rlc_v2_1)
+		return;
+
 	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
 			      AMD_PG_SUPPORT_GFX_SMG |
 			      AMD_PG_SUPPORT_GFX_DMG |
@@ -2017,27 +2154,12 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 			      AMD_PG_SUPPORT_GDS |
 			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v9_0_init_csb(adev);
-		gfx_v9_0_init_rlc_save_restore_list(adev);
+		gfx_v9_1_init_rlc_save_restore_list(adev);
 		gfx_v9_0_enable_save_restore_machine(adev);
 
-		if (adev->asic_type == CHIP_RAVEN) {
-			WREG32(mmRLC_JUMP_TABLE_RESTORE,
-				adev->gfx.rlc.cp_table_gpu_addr >> 8);
-			gfx_v9_0_init_gfx_power_gating(adev);
-
-			if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
-				gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true);
-				gfx_v9_0_enable_sck_slow_down_on_power_down(adev, true);
-			} else {
-				gfx_v9_0_enable_sck_slow_down_on_power_up(adev, false);
-				gfx_v9_0_enable_sck_slow_down_on_power_down(adev, false);
-			}
-
-			if (adev->pg_flags & AMD_PG_SUPPORT_CP)
-				gfx_v9_0_enable_cp_power_gating(adev, true);
-			else
-				gfx_v9_0_enable_cp_power_gating(adev, false);
-		}
+		WREG32(mmRLC_JUMP_TABLE_RESTORE,
+		       adev->gfx.rlc.cp_table_gpu_addr >> 8);
+		gfx_v9_0_init_gfx_power_gating(adev);
 	}
 }
 
@@ -3061,6 +3183,9 @@ static int gfx_v9_0_hw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int i;
 
+	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_GFX,
+					       AMD_PG_STATE_UNGATE);
+
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
@@ -3279,6 +3404,11 @@ static int gfx_v9_0_late_init(void *handle)
 	if (r)
 		return r;
 
+	r = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_GFX,
+						   AMD_PG_STATE_GATE);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -3339,8 +3469,7 @@ static void gfx_v9_0_exit_rlc_safe_mode(struct amdgpu_device *adev)
 static void gfx_v9_0_update_gfx_cg_power_gating(struct amdgpu_device *adev,
 						bool enable)
 {
-	/* TODO: double check if we need to perform under safe mdoe */
-	/* gfx_v9_0_enter_rlc_safe_mode(adev); */
+	gfx_v9_0_enter_rlc_safe_mode(adev);
 
 	if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) && enable) {
 		gfx_v9_0_enable_gfx_cg_power_gating(adev, true);
@@ -3351,7 +3480,7 @@ static void gfx_v9_0_update_gfx_cg_power_gating(struct amdgpu_device *adev,
 		gfx_v9_0_enable_gfx_pipeline_powergating(adev, false);
 	}
 
-	/* gfx_v9_0_exit_rlc_safe_mode(adev); */
+	gfx_v9_0_exit_rlc_safe_mode(adev);
 }
 
 static void gfx_v9_0_update_gfx_mg_power_gating(struct amdgpu_device *adev,
@@ -3605,6 +3734,7 @@ static int gfx_v9_0_set_clockgating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 	case CHIP_RAVEN:
 		gfx_v9_0_update_gfx_clock_gating(adev,
 						 state == AMD_CG_STATE_GATE ? true : false);
@@ -3742,7 +3872,7 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	}
 
 	amdgpu_ring_write(ring, header);
-BUG_ON(ib->gpu_addr & 0x3); /* Dword align */
+	BUG_ON(ib->gpu_addr & 0x3); /* Dword align */
 	amdgpu_ring_write(ring,
 #ifdef __BIG_ENDIAN
 		(2 << 0) |
@@ -3774,13 +3904,16 @@ static void gfx_v9_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
 {
 	bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT;
 	bool int_sel = flags & AMDGPU_FENCE_FLAG_INT;
+	bool writeback = flags & AMDGPU_FENCE_FLAG_TC_WB_ONLY;
 
 	/* RELEASE_MEM - flush caches, send int */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_RELEASE_MEM, 6));
-	amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
-				 EOP_TC_ACTION_EN |
-				 EOP_TC_WB_ACTION_EN |
-				 EOP_TC_MD_ACTION_EN |
+	amdgpu_ring_write(ring, ((writeback ? (EOP_TC_WB_ACTION_EN |
+					       EOP_TC_NC_ACTION_EN) :
+					      (EOP_TCL1_ACTION_EN |
+					       EOP_TC_ACTION_EN |
+					       EOP_TC_WB_ACTION_EN |
+					       EOP_TC_MD_ACTION_EN)) |
 				 EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) |
 				 EVENT_INDEX(5)));
 	amdgpu_ring_write(ring, DATA_SEL(write64bit ? 2 : 1) | INT_SEL(int_sel ? 2 : 0));
@@ -4137,6 +4270,20 @@ static void gfx_v9_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 	gfx_v9_0_wait_reg_mem(ring, 0, 0, 0, reg, 0, val, mask, 0x20);
 }
 
+static void gfx_v9_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
+						  uint32_t reg0, uint32_t reg1,
+						  uint32_t ref, uint32_t mask)
+{
+	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
+
+	if (amdgpu_sriov_vf(ring->adev))
+		gfx_v9_0_wait_reg_mem(ring, usepfp, 0, 1, reg0, reg1,
+				      ref, mask, 0x20);
+	else
+		amdgpu_ring_emit_reg_write_reg_wait_helper(ring, reg0, reg1,
+							   ref, mask);
+}
+
 static void gfx_v9_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 						 enum amdgpu_interrupt_state state)
 {
@@ -4458,6 +4605,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = {
 	.emit_tmz = gfx_v9_0_ring_emit_tmz,
 	.emit_wreg = gfx_v9_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v9_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait,
 };
 
 static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
@@ -4492,6 +4640,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
 	.set_priority = gfx_v9_0_ring_set_priority_compute,
 	.emit_wreg = gfx_v9_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v9_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait,
 };
 
 static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = {
@@ -4522,6 +4671,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = {
 	.emit_rreg = gfx_v9_0_ring_emit_rreg,
 	.emit_wreg = gfx_v9_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v9_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait,
 };
 
 static void gfx_v9_0_set_ring_funcs(struct amdgpu_device *adev)
@@ -4577,6 +4727,7 @@ static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev)
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 	case CHIP_RAVEN:
 		adev->gfx.rlc.funcs = &gfx_v9_0_rlc_funcs;
 		break;
@@ -4686,6 +4837,7 @@ static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 
 	cu_info->number = active_cu_number;
 	cu_info->ao_cu_mask = ao_cu_mask;
+	cu_info->simd_per_cu = NUM_SIMD_PER_CU;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 5617cf62c566..79f9ac29019b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -819,12 +819,33 @@ static int gmc_v6_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	amdgpu_bo_late_init(adev);
+
 	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
 		return amdgpu_irq_get(adev, &adev->gmc.vm_fault, 0);
 	else
 		return 0;
 }
 
+static unsigned gmc_v6_0_get_vbios_fb_size(struct amdgpu_device *adev)
+{
+	u32 d1vga_control = RREG32(mmD1VGA_CONTROL);
+	unsigned size;
+
+	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
+		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
+	} else {
+		u32 viewport = RREG32(mmVIEWPORT_SIZE);
+		size = (REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
+			REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_WIDTH) *
+			4);
+	}
+	/* return 0 if the pre-OS buffer uses up most of vram */
+	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
+		return 0;
+	return size;
+}
+
 static int gmc_v6_0_sw_init(void *handle)
 {
 	int r;
@@ -851,8 +872,6 @@ static int gmc_v6_0_sw_init(void *handle)
 
 	adev->gmc.mc_mask = 0xffffffffffULL;
 
-	adev->gmc.stolen_size = 256 * 1024;
-
 	adev->need_dma32 = false;
 	dma_bits = adev->need_dma32 ? 32 : 40;
 	r = pci_set_dma_mask(adev->pdev, DMA_BIT_MASK(dma_bits));
@@ -878,6 +897,8 @@ static int gmc_v6_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	adev->gmc.stolen_size = gmc_v6_0_get_vbios_fb_size(adev);
+
 	r = amdgpu_bo_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 80054f36e487..7147bfe25a23 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -958,12 +958,33 @@ static int gmc_v7_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	amdgpu_bo_late_init(adev);
+
 	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
 		return amdgpu_irq_get(adev, &adev->gmc.vm_fault, 0);
 	else
 		return 0;
 }
 
+static unsigned gmc_v7_0_get_vbios_fb_size(struct amdgpu_device *adev)
+{
+	u32 d1vga_control = RREG32(mmD1VGA_CONTROL);
+	unsigned size;
+
+	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
+		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
+	} else {
+		u32 viewport = RREG32(mmVIEWPORT_SIZE);
+		size = (REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
+			REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_WIDTH) *
+			4);
+	}
+	/* return 0 if the pre-OS buffer uses up most of vram */
+	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
+		return 0;
+	return size;
+}
+
 static int gmc_v7_0_sw_init(void *handle)
 {
 	int r;
@@ -998,8 +1019,6 @@ static int gmc_v7_0_sw_init(void *handle)
 	 */
 	adev->gmc.mc_mask = 0xffffffffffULL; /* 40 bit MC */
 
-	adev->gmc.stolen_size = 256 * 1024;
-
 	/* set DMA mask + need_dma32 flags.
 	 * PCIE - can handle 40-bits.
 	 * IGP - can handle 40-bits
@@ -1030,6 +1049,8 @@ static int gmc_v7_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	adev->gmc.stolen_size = gmc_v7_0_get_vbios_fb_size(adev);
+
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index d71d4cb68f9c..1edbe6b477b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -138,6 +138,7 @@ static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev)
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 		amdgpu_device_program_register_sequence(adev,
 							golden_settings_polaris11_a11,
 							ARRAY_SIZE(golden_settings_polaris11_a11));
@@ -231,6 +232,7 @@ static int gmc_v8_0_init_microcode(struct amdgpu_device *adev)
 	case CHIP_FIJI:
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
+	case CHIP_VEGAM:
 		return 0;
 	default: BUG();
 	}
@@ -567,9 +569,10 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
 	/* set the gart size */
 	if (amdgpu_gart_size == -1) {
 		switch (adev->asic_type) {
-		case CHIP_POLARIS11: /* all engines support GPUVM */
 		case CHIP_POLARIS10: /* all engines support GPUVM */
+		case CHIP_POLARIS11: /* all engines support GPUVM */
 		case CHIP_POLARIS12: /* all engines support GPUVM */
+		case CHIP_VEGAM:     /* all engines support GPUVM */
 		default:
 			adev->gmc.gart_size = 256ULL << 20;
 			break;
@@ -1049,12 +1052,33 @@ static int gmc_v8_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	amdgpu_bo_late_init(adev);
+
 	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
 		return amdgpu_irq_get(adev, &adev->gmc.vm_fault, 0);
 	else
 		return 0;
 }
 
+static unsigned gmc_v8_0_get_vbios_fb_size(struct amdgpu_device *adev)
+{
+	u32 d1vga_control = RREG32(mmD1VGA_CONTROL);
+	unsigned size;
+
+	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
+		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
+	} else {
+		u32 viewport = RREG32(mmVIEWPORT_SIZE);
+		size = (REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
+			REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_WIDTH) *
+			4);
+	}
+	/* return 0 if the pre-OS buffer uses up most of vram */
+	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
+		return 0;
+	return size;
+}
+
 #define mmMC_SEQ_MISC0_FIJI 0xA71
 
 static int gmc_v8_0_sw_init(void *handle)
@@ -1068,7 +1092,8 @@ static int gmc_v8_0_sw_init(void *handle)
 	} else {
 		u32 tmp;
 
-		if (adev->asic_type == CHIP_FIJI)
+		if ((adev->asic_type == CHIP_FIJI) ||
+		    (adev->asic_type == CHIP_VEGAM))
 			tmp = RREG32(mmMC_SEQ_MISC0_FIJI);
 		else
 			tmp = RREG32(mmMC_SEQ_MISC0);
@@ -1096,8 +1121,6 @@ static int gmc_v8_0_sw_init(void *handle)
 	 */
 	adev->gmc.mc_mask = 0xffffffffffULL; /* 40 bit MC */
 
-	adev->gmc.stolen_size = 256 * 1024;
-
 	/* set DMA mask + need_dma32 flags.
 	 * PCIE - can handle 40-bits.
 	 * IGP - can handle 40-bits
@@ -1128,6 +1151,8 @@ static int gmc_v8_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	adev->gmc.stolen_size = gmc_v8_0_get_vbios_fb_size(adev);
+
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index e687363900bb..3c0a85d4e4ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -43,19 +43,13 @@
 #include "gfxhub_v1_0.h"
 #include "mmhub_v1_0.h"
 
-#define mmDF_CS_AON0_DramBaseAddress0                                                                  0x0044
-#define mmDF_CS_AON0_DramBaseAddress0_BASE_IDX                                                         0
-//DF_CS_AON0_DramBaseAddress0
-#define DF_CS_AON0_DramBaseAddress0__AddrRngVal__SHIFT                                                        0x0
-#define DF_CS_AON0_DramBaseAddress0__LgcyMmioHoleEn__SHIFT                                                    0x1
-#define DF_CS_AON0_DramBaseAddress0__IntLvNumChan__SHIFT                                                      0x4
-#define DF_CS_AON0_DramBaseAddress0__IntLvAddrSel__SHIFT                                                      0x8
-#define DF_CS_AON0_DramBaseAddress0__DramBaseAddr__SHIFT                                                      0xc
-#define DF_CS_AON0_DramBaseAddress0__AddrRngVal_MASK                                                          0x00000001L
-#define DF_CS_AON0_DramBaseAddress0__LgcyMmioHoleEn_MASK                                                      0x00000002L
-#define DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK                                                        0x000000F0L
-#define DF_CS_AON0_DramBaseAddress0__IntLvAddrSel_MASK                                                        0x00000700L
-#define DF_CS_AON0_DramBaseAddress0__DramBaseAddr_MASK                                                        0xFFFFF000L
+/* add these here since we already include dce12 headers and these are for DCN */
+#define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION                                                          0x055d
+#define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_BASE_IDX                                                 2
+#define HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION__PRI_VIEWPORT_WIDTH__SHIFT                                        0x0
+#define HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION__PRI_VIEWPORT_HEIGHT__SHIFT                                       0x10
+#define HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION__PRI_VIEWPORT_WIDTH_MASK                                          0x00003FFFL
+#define HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION__PRI_VIEWPORT_HEIGHT_MASK                                         0x3FFF0000L
 
 /* XXX Move this macro to VEGA10 header file, which is like vid.h for VI.*/
 #define AMDGPU_NUM_OF_VMIDS			8
@@ -385,11 +379,9 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid),
 			      upper_32_bits(pd_addr));
 
-	amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req);
-
-	/* wait for the invalidate to complete */
-	amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_ack + eng,
-				  1 << vmid, 1 << vmid);
+	amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng,
+					    hub->vm_inv_eng0_ack + eng,
+					    req, 1 << vmid);
 
 	return pd_addr;
 }
@@ -556,8 +548,7 @@ static int gmc_v9_0_early_init(void *handle)
 	adev->gmc.shared_aperture_start = 0x2000000000000000ULL;
 	adev->gmc.shared_aperture_end =
 		adev->gmc.shared_aperture_start + (4ULL << 30) - 1;
-	adev->gmc.private_aperture_start =
-		adev->gmc.shared_aperture_end + 1;
+	adev->gmc.private_aperture_start = 0x1000000000000000ULL;
 	adev->gmc.private_aperture_end =
 		adev->gmc.private_aperture_start + (4ULL << 30) - 1;
 
@@ -659,6 +650,11 @@ static int gmc_v9_0_late_init(void *handle)
 	unsigned i;
 	int r;
 
+	/*
+	 * TODO - Uncomment once GART corruption issue is fixed.
+	 */
+	/* amdgpu_bo_late_init(adev); */
+
 	for(i = 0; i < adev->num_rings; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 		unsigned vmhub = ring->funcs->vmhub;
@@ -679,6 +675,7 @@ static int gmc_v9_0_late_init(void *handle)
 			DRM_INFO("ECC is active.\n");
 		} else if (r == 0) {
 			DRM_INFO("ECC is not present.\n");
+			adev->df_funcs->enable_ecc_force_par_wr_rmw(adev, false);
 		} else {
 			DRM_ERROR("gmc_v9_0_ecc_available() failed. r: %d\n", r);
 			return r;
@@ -697,10 +694,7 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 	amdgpu_device_vram_location(adev, &adev->gmc, base);
 	amdgpu_device_gart_location(adev, mc);
 	/* base offset of vram pages */
-	if (adev->flags & AMD_IS_APU)
-		adev->vm_manager.vram_base_offset = gfxhub_v1_0_get_mc_fb_offset(adev);
-	else
-		adev->vm_manager.vram_base_offset = 0;
+	adev->vm_manager.vram_base_offset = gfxhub_v1_0_get_mc_fb_offset(adev);
 }
 
 /**
@@ -714,7 +708,6 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
  */
 static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 {
-	u32 tmp;
 	int chansize, numchan;
 	int r;
 
@@ -727,39 +720,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 		else
 			chansize = 128;
 
-		tmp = RREG32_SOC15(DF, 0, mmDF_CS_AON0_DramBaseAddress0);
-		tmp &= DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK;
-		tmp >>= DF_CS_AON0_DramBaseAddress0__IntLvNumChan__SHIFT;
-		switch (tmp) {
-		case 0:
-		default:
-			numchan = 1;
-			break;
-		case 1:
-			numchan = 2;
-			break;
-		case 2:
-			numchan = 0;
-			break;
-		case 3:
-			numchan = 4;
-			break;
-		case 4:
-			numchan = 0;
-			break;
-		case 5:
-			numchan = 8;
-			break;
-		case 6:
-			numchan = 0;
-			break;
-		case 7:
-			numchan = 16;
-			break;
-		case 8:
-			numchan = 2;
-			break;
-		}
+		numchan = adev->df_funcs->get_hbm_channel_number(adev);
 		adev->gmc.vram_width = numchan * chansize;
 	}
 
@@ -792,6 +753,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 		switch (adev->asic_type) {
 		case CHIP_VEGA10:  /* all engines support GPUVM */
 		case CHIP_VEGA12:  /* all engines support GPUVM */
+		case CHIP_VEGA20:
 		default:
 			adev->gmc.gart_size = 512ULL << 20;
 			break;
@@ -826,6 +788,52 @@ static int gmc_v9_0_gart_init(struct amdgpu_device *adev)
 	return amdgpu_gart_table_vram_alloc(adev);
 }
 
+static unsigned gmc_v9_0_get_vbios_fb_size(struct amdgpu_device *adev)
+{
+#if 0
+	u32 d1vga_control = RREG32_SOC15(DCE, 0, mmD1VGA_CONTROL);
+#endif
+	unsigned size;
+
+	/*
+	 * TODO Remove once GART corruption is resolved
+	 * Check related code in gmc_v9_0_sw_fini
+	 * */
+	size = 9 * 1024 * 1024;
+
+#if 0
+	if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
+		size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
+	} else {
+		u32 viewport;
+
+		switch (adev->asic_type) {
+		case CHIP_RAVEN:
+			viewport = RREG32_SOC15(DCE, 0, mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION);
+			size = (REG_GET_FIELD(viewport,
+					      HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) *
+				REG_GET_FIELD(viewport,
+					      HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_WIDTH) *
+				4);
+			break;
+		case CHIP_VEGA10:
+		case CHIP_VEGA12:
+		default:
+			viewport = RREG32_SOC15(DCE, 0, mmSCL0_VIEWPORT_SIZE);
+			size = (REG_GET_FIELD(viewport, SCL0_VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
+				REG_GET_FIELD(viewport, SCL0_VIEWPORT_SIZE, VIEWPORT_WIDTH) *
+				4);
+			break;
+		}
+	}
+	/* return 0 if the pre-OS buffer uses up most of vram */
+	if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
+		return 0;
+
+#endif
+	return size;
+}
+
 static int gmc_v9_0_sw_init(void *handle)
 {
 	int r;
@@ -851,6 +859,7 @@ static int gmc_v9_0_sw_init(void *handle)
 		break;
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 		/*
 		 * To fulfill 4-level page support,
 		 * vm size is 256TB (48bit), maximum size of Vega10,
@@ -877,12 +886,6 @@ static int gmc_v9_0_sw_init(void *handle)
 	 */
 	adev->gmc.mc_mask = 0xffffffffffffULL; /* 48 bit MC */
 
-	/*
-	 * It needs to reserve 8M stolen memory for vega10
-	 * TODO: Figure out how to avoid that...
-	 */
-	adev->gmc.stolen_size = 8 * 1024 * 1024;
-
 	/* set DMA mask + need_dma32 flags.
 	 * PCIE - can handle 44-bits.
 	 * IGP - can handle 44-bits
@@ -907,6 +910,8 @@ static int gmc_v9_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	adev->gmc.stolen_size = gmc_v9_0_get_vbios_fb_size(adev);
+
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
 	if (r)
@@ -950,6 +955,18 @@ static int gmc_v9_0_sw_fini(void *handle)
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
 	gmc_v9_0_gart_fini(adev);
+
+	/*
+	* TODO:
+	* Currently there is a bug where some memory client outside
+	* of the driver writes to first 8M of VRAM on S3 resume,
+	* this overrides GART which by default gets placed in first 8M and
+	* causes VM_FAULTS once GTT is accessed.
+	* Keep the stolen memory reservation until the while this is not solved.
+	* Also check code in gmc_v9_0_get_vbios_fb_size and gmc_v9_0_late_init
+	*/
+	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL);
+
 	amdgpu_bo_fini(adev);
 
 	return 0;
@@ -960,6 +977,7 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
+	case CHIP_VEGA20:
 		soc15_program_register_sequence(adev,
 						golden_settings_mmhub_1_0_0,
 						ARRAY_SIZE(golden_settings_mmhub_1_0_0));
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 26ba984ab2b7..17f7f074cedc 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -2817,7 +2817,7 @@ static int kv_dpm_init(struct amdgpu_device *adev)
 		pi->caps_tcp_ramping = true;
 	}
 
-	if (amdgpu_pp_feature_mask & SCLK_DEEP_SLEEP_MASK)
+	if (adev->powerplay.pp_feature & PP_SCLK_DEEP_SLEEP_MASK)
 		pi->caps_sclk_ds = true;
 	else
 		pi->caps_sclk_ds = false;
@@ -2974,7 +2974,7 @@ static int kv_dpm_late_init(void *handle)
 	/* powerdown unused blocks for now */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!amdgpu_dpm)
+	if (!adev->pm.dpm_enabled)
 		return 0;
 
 	kv_dpm_powergate_acp(adev, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 43f925773b57..3d53c4413f13 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -734,6 +734,7 @@ int mmhub_v1_0_set_clockgating(struct amdgpu_device *adev,
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 	case CHIP_RAVEN:
 		mmhub_v1_0_update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 493348672475..078f70faedcb 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -260,8 +260,10 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	} while (timeout > 1);
 
 flr_done:
-	if (locked)
+	if (locked) {
+		adev->in_gpu_reset = 0;
 		mutex_unlock(&adev->lock_reset);
+	}
 
 	/* Trigger recovery for world switch failure if no TDR */
 	if (amdgpu_lockup_timeout == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
index df34dc79d444..365517c0121e 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
@@ -34,10 +34,19 @@
 #define smnCPM_CONTROL                                                                                  0x11180460
 #define smnPCIE_CNTL2                                                                                   0x11180070
 
+/* vega20 */
+#define mmRCC_DEV0_EPF0_STRAP0_VG20                                                                         0x0011
+#define mmRCC_DEV0_EPF0_STRAP0_VG20_BASE_IDX                                                                2
+
 static u32 nbio_v7_0_get_rev_id(struct amdgpu_device *adev)
 {
         u32 tmp = RREG32_SOC15(NBIO, 0, mmRCC_DEV0_EPF0_STRAP0);
 
+	if (adev->asic_type == CHIP_VEGA20)
+		tmp = RREG32_SOC15(NBIO, 0, mmRCC_DEV0_EPF0_STRAP0_VG20);
+	else
+		tmp = RREG32_SOC15(NBIO, 0, mmRCC_DEV0_EPF0_STRAP0);
+
 	tmp &= RCC_DEV0_EPF0_STRAP0__STRAP_ATI_REV_ID_DEV0_F0_MASK;
 	tmp >>= RCC_DEV0_EPF0_STRAP0__STRAP_ATI_REV_ID_DEV0_F0__SHIFT;
 
@@ -75,10 +84,14 @@ static void nbio_v7_0_sdma_doorbell_range(struct amdgpu_device *adev, int instan
 			SOC15_REG_OFFSET(NBIO, 0, mmBIF_SDMA1_DOORBELL_RANGE);
 
 	u32 doorbell_range = RREG32(reg);
+	u32 range = 2;
+
+	if (adev->asic_type == CHIP_VEGA20)
+		range = 8;
 
 	if (use_doorbell) {
 		doorbell_range = REG_SET_FIELD(doorbell_range, BIF_SDMA0_DOORBELL_RANGE, OFFSET, doorbell_index);
-		doorbell_range = REG_SET_FIELD(doorbell_range, BIF_SDMA0_DOORBELL_RANGE, SIZE, 2);
+		doorbell_range = REG_SET_FIELD(doorbell_range, BIF_SDMA0_DOORBELL_RANGE, SIZE, range);
 	} else
 		doorbell_range = REG_SET_FIELD(doorbell_range, BIF_SDMA0_DOORBELL_RANGE, SIZE, 0);
 
@@ -133,6 +146,9 @@ static void nbio_v7_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 {
 	uint32_t def, data;
 
+	if (adev->asic_type == CHIP_VEGA20)
+		return;
+
 	/* NBIF_MGCG_CTRL_LCLK */
 	def = data = RREG32_PCIE(smnNBIF_MGCG_CTRL_LCLK);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index 8da6da90b1c9..0cf48d26c676 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -40,11 +40,20 @@ enum psp_gfx_crtl_cmd_id
     GFX_CTRL_CMD_ID_INIT_GPCOM_RING = 0x00020000,   /* initialize GPCOM ring */
     GFX_CTRL_CMD_ID_DESTROY_RINGS   = 0x00030000,   /* destroy rings */
     GFX_CTRL_CMD_ID_CAN_INIT_RINGS  = 0x00040000,   /* is it allowed to initialized the rings */
+    GFX_CTRL_CMD_ID_ENABLE_INT      = 0x00050000,   /* enable PSP-to-Gfx interrupt */
+    GFX_CTRL_CMD_ID_DISABLE_INT     = 0x00060000,   /* disable PSP-to-Gfx interrupt */
+    GFX_CTRL_CMD_ID_MODE1_RST       = 0x00070000,   /* trigger the Mode 1 reset */
 
     GFX_CTRL_CMD_ID_MAX             = 0x000F0000,   /* max command ID */
 };
 
 
+/*-----------------------------------------------------------------------------
+    NOTE:   All physical addresses used in this interface are actually
+            GPU Virtual Addresses.
+*/
+
+
 /* Control registers of the TEE Gfx interface. These are located in
 *  SRBM-to-PSP mailbox registers (total 8 registers).
 */
@@ -55,8 +64,8 @@ struct psp_gfx_ctrl
     volatile uint32_t   rbi_rptr;         /* +8   Read pointer (index) of RBI ring */
     volatile uint32_t   gpcom_wptr;       /* +12  Write pointer (index) of GPCOM ring */
     volatile uint32_t   gpcom_rptr;       /* +16  Read pointer (index) of GPCOM ring */
-    volatile uint32_t   ring_addr_lo;     /* +20  bits [31:0] of physical address of ring buffer */
-    volatile uint32_t   ring_addr_hi;     /* +24  bits [63:32] of physical address of ring buffer */
+    volatile uint32_t   ring_addr_lo;     /* +20  bits [31:0] of GPU Virtual of ring buffer (VMID=0)*/
+    volatile uint32_t   ring_addr_hi;     /* +24  bits [63:32] of GPU Virtual of ring buffer (VMID=0) */
     volatile uint32_t   ring_buf_size;    /* +28  Ring buffer size (in bytes) */
 
 };
@@ -78,6 +87,8 @@ enum psp_gfx_cmd_id
     GFX_CMD_ID_LOAD_ASD     = 0x00000004,   /* load ASD Driver */
     GFX_CMD_ID_SETUP_TMR    = 0x00000005,   /* setup TMR region */
     GFX_CMD_ID_LOAD_IP_FW   = 0x00000006,   /* load HW IP FW */
+    GFX_CMD_ID_DESTROY_TMR  = 0x00000007,   /* destroy TMR region */
+    GFX_CMD_ID_SAVE_RESTORE = 0x00000008,   /* save/restore HW IP FW */
 
 };
 
@@ -85,11 +96,11 @@ enum psp_gfx_cmd_id
 /* Command to load Trusted Application binary into PSP OS. */
 struct psp_gfx_cmd_load_ta
 {
-    uint32_t        app_phy_addr_lo;        /* bits [31:0] of the physical address of the TA binary (must be 4 KB aligned) */
-    uint32_t        app_phy_addr_hi;        /* bits [63:32] of the physical address of the TA binary */
+    uint32_t        app_phy_addr_lo;        /* bits [31:0] of the GPU Virtual address of the TA binary (must be 4 KB aligned) */
+    uint32_t        app_phy_addr_hi;        /* bits [63:32] of the GPU Virtual address of the TA binary */
     uint32_t        app_len;                /* length of the TA binary in bytes */
-    uint32_t        cmd_buf_phy_addr_lo;    /* bits [31:0] of the physical address of CMD buffer (must be 4 KB aligned) */
-    uint32_t        cmd_buf_phy_addr_hi;    /* bits [63:32] of the physical address of CMD buffer */
+    uint32_t        cmd_buf_phy_addr_lo;    /* bits [31:0] of the GPU Virtual address of CMD buffer (must be 4 KB aligned) */
+    uint32_t        cmd_buf_phy_addr_hi;    /* bits [63:32] of the GPU Virtual address of CMD buffer */
     uint32_t        cmd_buf_len;            /* length of the CMD buffer in bytes; must be multiple of 4 KB */
 
     /* Note: CmdBufLen can be set to 0. In this case no persistent CMD buffer is provided
@@ -111,8 +122,8 @@ struct psp_gfx_cmd_unload_ta
 */
 struct psp_gfx_buf_desc
 {
-    uint32_t        buf_phy_addr_lo;       /* bits [31:0] of physical address of the buffer (must be 4 KB aligned) */
-    uint32_t        buf_phy_addr_hi;       /* bits [63:32] of physical address of the buffer */
+    uint32_t        buf_phy_addr_lo;       /* bits [31:0] of GPU Virtual address of the buffer (must be 4 KB aligned) */
+    uint32_t        buf_phy_addr_hi;       /* bits [63:32] of GPU Virtual address of the buffer */
     uint32_t        buf_size;              /* buffer size in bytes (must be multiple of 4 KB and no bigger than 64 MB) */
 
 };
@@ -145,8 +156,8 @@ struct psp_gfx_cmd_invoke_cmd
 /* Command to setup TMR region. */
 struct psp_gfx_cmd_setup_tmr
 {
-    uint32_t        buf_phy_addr_lo;       /* bits [31:0] of physical address of TMR buffer (must be 4 KB aligned) */
-    uint32_t        buf_phy_addr_hi;       /* bits [63:32] of physical address of TMR buffer */
+    uint32_t        buf_phy_addr_lo;       /* bits [31:0] of GPU Virtual address of TMR buffer (must be 4 KB aligned) */
+    uint32_t        buf_phy_addr_hi;       /* bits [63:32] of GPU Virtual address of TMR buffer */
     uint32_t        buf_size;              /* buffer size in bytes (must be multiple of 4 KB) */
 
 };
@@ -174,18 +185,32 @@ enum psp_gfx_fw_type
     GFX_FW_TYPE_ISP         = 16,
     GFX_FW_TYPE_ACP         = 17,
     GFX_FW_TYPE_SMU         = 18,
+    GFX_FW_TYPE_MMSCH       = 19,
+    GFX_FW_TYPE_RLC_RESTORE_LIST_GPM_MEM        = 20,
+    GFX_FW_TYPE_RLC_RESTORE_LIST_SRM_MEM        = 21,
+    GFX_FW_TYPE_RLC_RESTORE_LIST_CNTL           = 22,
+    GFX_FW_TYPE_MAX         = 23
 };
 
 /* Command to load HW IP FW. */
 struct psp_gfx_cmd_load_ip_fw
 {
-    uint32_t                fw_phy_addr_lo;    /* bits [31:0] of physical address of FW location (must be 4 KB aligned) */
-    uint32_t                fw_phy_addr_hi;    /* bits [63:32] of physical address of FW location */
+    uint32_t                fw_phy_addr_lo;    /* bits [31:0] of GPU Virtual address of FW location (must be 4 KB aligned) */
+    uint32_t                fw_phy_addr_hi;    /* bits [63:32] of GPU Virtual address of FW location */
     uint32_t                fw_size;           /* FW buffer size in bytes */
     enum psp_gfx_fw_type    fw_type;           /* FW type */
 
 };
 
+/* Command to save/restore HW IP FW. */
+struct psp_gfx_cmd_save_restore_ip_fw
+{
+    uint32_t                save_fw;              /* if set, command is used for saving fw otherwise for resetoring*/
+    uint32_t                save_restore_addr_lo; /* bits [31:0] of FB address of GART memory used as save/restore buffer (must be 4 KB aligned) */
+    uint32_t                save_restore_addr_hi; /* bits [63:32] of FB address of GART memory used as save/restore buffer */
+    uint32_t                buf_size;             /* Size of the save/restore buffer in bytes */
+    enum psp_gfx_fw_type    fw_type;              /* FW type */
+};
 
 /* All GFX ring buffer commands. */
 union psp_gfx_commands
@@ -195,7 +220,7 @@ union psp_gfx_commands
     struct psp_gfx_cmd_invoke_cmd       cmd_invoke_cmd;
     struct psp_gfx_cmd_setup_tmr        cmd_setup_tmr;
     struct psp_gfx_cmd_load_ip_fw       cmd_load_ip_fw;
-
+    struct psp_gfx_cmd_save_restore_ip_fw cmd_save_restore_ip_fw;
 };
 
 
@@ -226,8 +251,8 @@ struct psp_gfx_cmd_resp
 
     /* These fields are used for RBI only. They are all 0 in GPCOM commands
     */
-    uint32_t        resp_buf_addr_lo;   /* +12 bits [31:0] of physical address of response buffer (must be 4 KB aligned) */
-    uint32_t        resp_buf_addr_hi;   /* +16 bits [63:32] of physical address of response buffer */
+    uint32_t        resp_buf_addr_lo;   /* +12 bits [31:0] of GPU Virtual address of response buffer (must be 4 KB aligned) */
+    uint32_t        resp_buf_addr_hi;   /* +16 bits [63:32] of GPU Virtual address of response buffer */
     uint32_t        resp_offset;        /* +20 offset within response buffer */
     uint32_t        resp_buf_size;      /* +24 total size of the response buffer in bytes */
 
@@ -251,19 +276,19 @@ struct psp_gfx_cmd_resp
 /* Structure of the Ring Buffer Frame */
 struct psp_gfx_rb_frame
 {
-    uint32_t    cmd_buf_addr_lo;    /* +0  bits [31:0] of physical address of command buffer (must be 4 KB aligned) */
-    uint32_t    cmd_buf_addr_hi;    /* +4  bits [63:32] of physical address of command buffer */
+    uint32_t    cmd_buf_addr_lo;    /* +0  bits [31:0] of GPU Virtual address of command buffer (must be 4 KB aligned) */
+    uint32_t    cmd_buf_addr_hi;    /* +4  bits [63:32] of GPU Virtual address of command buffer */
     uint32_t    cmd_buf_size;       /* +8  command buffer size in bytes */
-    uint32_t    fence_addr_lo;      /* +12 bits [31:0] of physical address of Fence for this frame */
-    uint32_t    fence_addr_hi;      /* +16 bits [63:32] of physical address of Fence for this frame */
+    uint32_t    fence_addr_lo;      /* +12 bits [31:0] of GPU Virtual address of Fence for this frame */
+    uint32_t    fence_addr_hi;      /* +16 bits [63:32] of GPU Virtual address of Fence for this frame */
     uint32_t    fence_value;        /* +20 Fence value */
     uint32_t    sid_lo;             /* +24 bits [31:0] of SID value (used only for RBI frames) */
     uint32_t    sid_hi;             /* +28 bits [63:32] of SID value (used only for RBI frames) */
     uint8_t     vmid;               /* +32 VMID value used for mapping of all addresses for this frame */
     uint8_t     frame_type;         /* +33 1: destory context frame, 0: all other frames; used only for RBI frames */
     uint8_t     reserved1[2];       /* +34 reserved, must be 0 */
-    uint32_t    reserved2[7];       /* +40 reserved, must be 0 */
-    /* total 64 bytes */
+    uint32_t    reserved2[7];       /* +36 reserved, must be 0 */
+                /* total 64 bytes */
 };
 
 #endif /* _PSP_TEE_GFX_IF_H_ */
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index 8873d833a7f7..0ff136d02d9b 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
@@ -70,6 +70,15 @@ psp_v10_0_get_fw_type(struct amdgpu_firmware_info *ucode, enum psp_gfx_fw_type *
 	case AMDGPU_UCODE_ID_RLC_G:
 		*type = GFX_FW_TYPE_RLC_G;
 		break;
+	case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL:
+		*type = GFX_FW_TYPE_RLC_RESTORE_LIST_CNTL;
+		break;
+	case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM:
+		*type = GFX_FW_TYPE_RLC_RESTORE_LIST_GPM_MEM;
+		break;
+	case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM:
+		*type = GFX_FW_TYPE_RLC_RESTORE_LIST_SRM_MEM;
+		break;
 	case AMDGPU_UCODE_ID_SMC:
 		*type = GFX_FW_TYPE_SMU;
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index 196e75def1f2..0c768e388ace 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -41,6 +41,9 @@ MODULE_FIRMWARE("amdgpu/vega10_sos.bin");
 MODULE_FIRMWARE("amdgpu/vega10_asd.bin");
 MODULE_FIRMWARE("amdgpu/vega12_sos.bin");
 MODULE_FIRMWARE("amdgpu/vega12_asd.bin");
+MODULE_FIRMWARE("amdgpu/vega20_sos.bin");
+MODULE_FIRMWARE("amdgpu/vega20_asd.bin");
+
 
 #define smnMP1_FIRMWARE_FLAGS 0x3010028
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index be20a387d961..aa9ab299fd32 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -62,6 +62,8 @@ MODULE_FIRMWARE("amdgpu/polaris11_sdma.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_sdma1.bin");
 MODULE_FIRMWARE("amdgpu/polaris12_sdma.bin");
 MODULE_FIRMWARE("amdgpu/polaris12_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/vegam_sdma.bin");
+MODULE_FIRMWARE("amdgpu/vegam_sdma1.bin");
 
 
 static const u32 sdma_offsets[SDMA_MAX_INSTANCE] =
@@ -209,6 +211,7 @@ static void sdma_v3_0_init_golden_registers(struct amdgpu_device *adev)
 		break;
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 		amdgpu_device_program_register_sequence(adev,
 							golden_settings_polaris11_a11,
 							ARRAY_SIZE(golden_settings_polaris11_a11));
@@ -275,15 +278,18 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev)
 	case CHIP_FIJI:
 		chip_name = "fiji";
 		break;
-	case CHIP_POLARIS11:
-		chip_name = "polaris11";
-		break;
 	case CHIP_POLARIS10:
 		chip_name = "polaris10";
 		break;
+	case CHIP_POLARIS11:
+		chip_name = "polaris11";
+		break;
 	case CHIP_POLARIS12:
 		chip_name = "polaris12";
 		break;
+	case CHIP_VEGAM:
+		chip_name = "vegam";
+		break;
 	case CHIP_CARRIZO:
 		chip_name = "carrizo";
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 399f876f9cad..ca53b3fba422 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -42,6 +42,8 @@ MODULE_FIRMWARE("amdgpu/vega10_sdma.bin");
 MODULE_FIRMWARE("amdgpu/vega10_sdma1.bin");
 MODULE_FIRMWARE("amdgpu/vega12_sdma.bin");
 MODULE_FIRMWARE("amdgpu/vega12_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/vega20_sdma.bin");
+MODULE_FIRMWARE("amdgpu/vega20_sdma1.bin");
 MODULE_FIRMWARE("amdgpu/raven_sdma.bin");
 
 #define SDMA0_POWER_CNTL__ON_OFF_CONDITION_HOLD_TIME_MASK  0x000000F8L
@@ -107,6 +109,28 @@ static const struct soc15_reg_golden golden_settings_sdma_4_1[] =
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0)
 };
 
+static const struct soc15_reg_golden golden_settings_sdma_4_2[] =
+{
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831d07),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CLK_CTRL, 0xffffffff, 0x3f000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG, 0x0000773f, 0x00004002),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG_READ, 0x0000773f, 0x00004002),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GFX_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_PAGE_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff0, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831d07),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CLK_CTRL, 0xffffffff, 0x3f000100),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG, 0x0000773f, 0x00004002),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG_READ, 0x0000773f, 0x00004002),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GFX_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_PAGE_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_PAGE, 0x000003ff, 0x000003c0)
+};
+
 static const struct soc15_reg_golden golden_settings_sdma_rv1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG, 0x0018773f, 0x00000002),
@@ -139,6 +163,11 @@ static void sdma_v4_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_sdma_vg12,
 						ARRAY_SIZE(golden_settings_sdma_vg12));
 		break;
+	case CHIP_VEGA20:
+		soc15_program_register_sequence(adev,
+						golden_settings_sdma_4_2,
+						ARRAY_SIZE(golden_settings_sdma_4_2));
+		break;
 	case CHIP_RAVEN:
 		soc15_program_register_sequence(adev,
 						 golden_settings_sdma_4_1,
@@ -182,6 +211,9 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev)
 	case CHIP_VEGA12:
 		chip_name = "vega12";
 		break;
+	case CHIP_VEGA20:
+		chip_name = "vega20";
+		break;
 	case CHIP_RAVEN:
 		chip_name = "raven";
 		break;
@@ -360,6 +392,31 @@ static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
 
 }
 
+static void sdma_v4_0_wait_reg_mem(struct amdgpu_ring *ring,
+				   int mem_space, int hdp,
+				   uint32_t addr0, uint32_t addr1,
+				   uint32_t ref, uint32_t mask,
+				   uint32_t inv)
+{
+	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
+			  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(hdp) |
+			  SDMA_PKT_POLL_REGMEM_HEADER_MEM_POLL(mem_space) |
+			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */
+	if (mem_space) {
+		/* memory */
+		amdgpu_ring_write(ring, addr0);
+		amdgpu_ring_write(ring, addr1);
+	} else {
+		/* registers */
+		amdgpu_ring_write(ring, addr0 << 2);
+		amdgpu_ring_write(ring, addr1 << 2);
+	}
+	amdgpu_ring_write(ring, ref); /* reference */
+	amdgpu_ring_write(ring, mask); /* mask */
+	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
+			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(inv)); /* retry count, poll interval */
+}
+
 /**
  * sdma_v4_0_ring_emit_hdp_flush - emit an hdp flush on the DMA ring
  *
@@ -378,15 +435,10 @@ static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	else
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma1;
 
-	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
-			  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) |
-			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */
-	amdgpu_ring_write(ring, (adev->nbio_funcs->get_hdp_flush_done_offset(adev)) << 2);
-	amdgpu_ring_write(ring, (adev->nbio_funcs->get_hdp_flush_req_offset(adev)) << 2);
-	amdgpu_ring_write(ring, ref_and_mask); /* reference */
-	amdgpu_ring_write(ring, ref_and_mask); /* mask */
-	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
-			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */
+	sdma_v4_0_wait_reg_mem(ring, 0, 1,
+			       adev->nbio_funcs->get_hdp_flush_done_offset(adev),
+			       adev->nbio_funcs->get_hdp_flush_req_offset(adev),
+			       ref_and_mask, ref_and_mask, 10);
 }
 
 /**
@@ -1114,16 +1166,10 @@ static void sdma_v4_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 	uint64_t addr = ring->fence_drv.gpu_addr;
 
 	/* wait for idle */
-	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
-			  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(0) |
-			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3) | /* equal */
-			  SDMA_PKT_POLL_REGMEM_HEADER_MEM_POLL(1));
-	amdgpu_ring_write(ring, addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
-	amdgpu_ring_write(ring, seq); /* reference */
-	amdgpu_ring_write(ring, 0xffffffff); /* mask */
-	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
-			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */
+	sdma_v4_0_wait_reg_mem(ring, 1, 0,
+			       addr & 0xfffffffc,
+			       upper_32_bits(addr) & 0xffffffff,
+			       seq, 0xffffffff, 4);
 }
 
 
@@ -1154,15 +1200,7 @@ static void sdma_v4_0_ring_emit_wreg(struct amdgpu_ring *ring,
 static void sdma_v4_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 					 uint32_t val, uint32_t mask)
 {
-	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
-			  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(0) |
-			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* equal */
-	amdgpu_ring_write(ring, reg << 2);
-	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, val); /* reference */
-	amdgpu_ring_write(ring, mask); /* mask */
-	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
-			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10));
+	sdma_v4_0_wait_reg_mem(ring, 0, 0, reg, 0, val, mask, 10);
 }
 
 static int sdma_v4_0_early_init(void *handle)
@@ -1510,6 +1548,7 @@ static int sdma_v4_0_set_clockgating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 	case CHIP_RAVEN:
 		sdma_v4_0_update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
@@ -1605,6 +1644,7 @@ static const struct amdgpu_ring_funcs sdma_v4_0_ring_funcs = {
 	.pad_ib = sdma_v4_0_ring_pad_ib,
 	.emit_wreg = sdma_v4_0_ring_emit_wreg,
 	.emit_reg_wait = sdma_v4_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
 static void sdma_v4_0_set_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index a675ec6d2811..c364ef94cc36 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -1252,6 +1252,12 @@ static void si_invalidate_hdp(struct amdgpu_device *adev,
 	}
 }
 
+static bool si_need_full_reset(struct amdgpu_device *adev)
+{
+	/* change this when we support soft reset */
+	return true;
+}
+
 static int si_get_pcie_lanes(struct amdgpu_device *adev)
 {
 	u32 link_width_cntl;
@@ -1332,6 +1338,7 @@ static const struct amdgpu_asic_funcs si_asic_funcs =
 	.get_config_memsize = &si_get_config_memsize,
 	.flush_hdp = &si_flush_hdp,
 	.invalidate_hdp = &si_invalidate_hdp,
+	.need_full_reset = &si_need_full_reset,
 };
 
 static uint32_t si_get_rev_id(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 797d505bf9ee..b12d7c9d42a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -7580,7 +7580,7 @@ static int si_dpm_late_init(void *handle)
 	int ret;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!amdgpu_dpm)
+	if (!adev->pm.dpm_enabled)
 		return 0;
 
 	ret = si_set_temperature_range(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 51cf8a30f6c2..68b4a22a8892 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -41,8 +41,6 @@
 #include "sdma1/sdma1_4_0_offset.h"
 #include "hdp/hdp_4_0_offset.h"
 #include "hdp/hdp_4_0_sh_mask.h"
-#include "mp/mp_9_0_offset.h"
-#include "mp/mp_9_0_sh_mask.h"
 #include "smuio/smuio_9_0_offset.h"
 #include "smuio/smuio_9_0_sh_mask.h"
 
@@ -52,6 +50,8 @@
 #include "gmc_v9_0.h"
 #include "gfxhub_v1_0.h"
 #include "mmhub_v1_0.h"
+#include "df_v1_7.h"
+#include "df_v3_6.h"
 #include "vega10_ih.h"
 #include "sdma_v4_0.h"
 #include "uvd_v7_0.h"
@@ -60,33 +60,6 @@
 #include "dce_virtual.h"
 #include "mxgpu_ai.h"
 
-#define mmFabricConfigAccessControl                                                                    0x0410
-#define mmFabricConfigAccessControl_BASE_IDX                                                           0
-#define mmFabricConfigAccessControl_DEFAULT                                      0x00000000
-//FabricConfigAccessControl
-#define FabricConfigAccessControl__CfgRegInstAccEn__SHIFT                                                     0x0
-#define FabricConfigAccessControl__CfgRegInstAccRegLock__SHIFT                                                0x1
-#define FabricConfigAccessControl__CfgRegInstID__SHIFT                                                        0x10
-#define FabricConfigAccessControl__CfgRegInstAccEn_MASK                                                       0x00000001L
-#define FabricConfigAccessControl__CfgRegInstAccRegLock_MASK                                                  0x00000002L
-#define FabricConfigAccessControl__CfgRegInstID_MASK                                                          0x00FF0000L
-
-
-#define mmDF_PIE_AON0_DfGlobalClkGater                                                                 0x00fc
-#define mmDF_PIE_AON0_DfGlobalClkGater_BASE_IDX                                                        0
-//DF_PIE_AON0_DfGlobalClkGater
-#define DF_PIE_AON0_DfGlobalClkGater__MGCGMode__SHIFT                                                         0x0
-#define DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK                                                           0x0000000FL
-
-enum {
-	DF_MGCG_DISABLE = 0,
-	DF_MGCG_ENABLE_00_CYCLE_DELAY =1,
-	DF_MGCG_ENABLE_01_CYCLE_DELAY =2,
-	DF_MGCG_ENABLE_15_CYCLE_DELAY =13,
-	DF_MGCG_ENABLE_31_CYCLE_DELAY =14,
-	DF_MGCG_ENABLE_63_CYCLE_DELAY =15
-};
-
 #define mmMP0_MISC_CGTT_CTRL0                                                                   0x01b9
 #define mmMP0_MISC_CGTT_CTRL0_BASE_IDX                                                          0
 #define mmMP0_MISC_LIGHT_SLEEP_CTRL                                                             0x01ba
@@ -313,6 +286,7 @@ static struct soc15_allowed_register_entry soc15_allowed_read_registers[] = {
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STATUS)},
 	{ SOC15_REG_ENTRY(GC, 0, mmGB_ADDR_CONFIG)},
+	{ SOC15_REG_ENTRY(GC, 0, mmDB_DEBUG2)},
 };
 
 static uint32_t soc15_read_indexed_register(struct amdgpu_device *adev, u32 se_num,
@@ -341,6 +315,8 @@ static uint32_t soc15_get_register_value(struct amdgpu_device *adev,
 	} else {
 		if (reg_offset == SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG))
 			return adev->gfx.config.gb_addr_config;
+		else if (reg_offset == SOC15_REG_OFFSET(GC, 0, mmDB_DEBUG2))
+			return adev->gfx.config.db_debug2;
 		return RREG32(reg_offset);
 	}
 }
@@ -512,15 +488,24 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 	case CHIP_RAVEN:
 		vega10_reg_base_init(adev);
 		break;
+	case CHIP_VEGA20:
+		vega20_reg_base_init(adev);
+		break;
 	default:
 		return -EINVAL;
 	}
 
 	if (adev->flags & AMD_IS_APU)
 		adev->nbio_funcs = &nbio_v7_0_funcs;
+	else if (adev->asic_type == CHIP_VEGA20)
+		adev->nbio_funcs = &nbio_v7_0_funcs;
 	else
 		adev->nbio_funcs = &nbio_v6_1_funcs;
 
+	if (adev->asic_type == CHIP_VEGA20)
+		adev->df_funcs = &df_v3_6_funcs;
+	else
+		adev->df_funcs = &df_v1_7_funcs;
 	adev->nbio_funcs->detect_hw_virt(adev);
 
 	if (amdgpu_sriov_vf(adev))
@@ -529,12 +514,15 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 		amdgpu_device_ip_block_add(adev, &vega10_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
-		amdgpu_device_ip_block_add(adev, &psp_v3_1_ip_block);
-		if (!amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		if (adev->asic_type != CHIP_VEGA20) {
+			amdgpu_device_ip_block_add(adev, &psp_v3_1_ip_block);
+			if (!amdgpu_sriov_vf(adev))
+				amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		}
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
@@ -593,6 +581,12 @@ static void soc15_invalidate_hdp(struct amdgpu_device *adev,
 			HDP, 0, mmHDP_READ_CACHE_INVALIDATE), 1);
 }
 
+static bool soc15_need_full_reset(struct amdgpu_device *adev)
+{
+	/* change this when we implement soft reset */
+	return true;
+}
+
 static const struct amdgpu_asic_funcs soc15_asic_funcs =
 {
 	.read_disabled_bios = &soc15_read_disabled_bios,
@@ -606,6 +600,7 @@ static const struct amdgpu_asic_funcs soc15_asic_funcs =
 	.get_config_memsize = &soc15_get_config_memsize,
 	.flush_hdp = &soc15_flush_hdp,
 	.invalidate_hdp = &soc15_invalidate_hdp,
+	.need_full_reset = &soc15_need_full_reset,
 };
 
 static int soc15_common_early_init(void *handle)
@@ -675,6 +670,27 @@ static int soc15_common_early_init(void *handle)
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x14;
 		break;
+	case CHIP_VEGA20:
+		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_3D_CGCG |
+			AMD_CG_SUPPORT_GFX_3D_CGLS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_MGCG |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_ROM_MGCG |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG;
+		adev->pg_flags = 0;
+		adev->external_rev_id = adev->rev_id + 0x28;
+		break;
 	case CHIP_RAVEN:
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_GFX_MGLS |
@@ -694,8 +710,15 @@ static int soc15_common_early_init(void *handle)
 			AMD_CG_SUPPORT_MC_MGCG |
 			AMD_CG_SUPPORT_MC_LS |
 			AMD_CG_SUPPORT_SDMA_MGCG |
-			AMD_CG_SUPPORT_SDMA_LS;
-		adev->pg_flags = AMD_PG_SUPPORT_SDMA;
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_VCN_MGCG;
+
+		adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
+
+		if (adev->powerplay.pp_feature & PP_GFXOFF_MASK)
+			adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+				AMD_PG_SUPPORT_CP |
+				AMD_PG_SUPPORT_RLC_SMU_HS;
 
 		adev->external_rev_id = 0x1;
 		break;
@@ -871,32 +894,6 @@ static void soc15_update_rom_medium_grain_clock_gating(struct amdgpu_device *ade
 		WREG32(SOC15_REG_OFFSET(SMUIO, 0, mmCGTT_ROM_CLK_CTRL0), data);
 }
 
-static void soc15_update_df_medium_grain_clock_gating(struct amdgpu_device *adev,
-						       bool enable)
-{
-	uint32_t data;
-
-	/* Put DF on broadcast mode */
-	data = RREG32(SOC15_REG_OFFSET(DF, 0, mmFabricConfigAccessControl));
-	data &= ~FabricConfigAccessControl__CfgRegInstAccEn_MASK;
-	WREG32(SOC15_REG_OFFSET(DF, 0, mmFabricConfigAccessControl), data);
-
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) {
-		data = RREG32(SOC15_REG_OFFSET(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater));
-		data &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
-		data |= DF_MGCG_ENABLE_15_CYCLE_DELAY;
-		WREG32(SOC15_REG_OFFSET(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater), data);
-	} else {
-		data = RREG32(SOC15_REG_OFFSET(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater));
-		data &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
-		data |= DF_MGCG_DISABLE;
-		WREG32(SOC15_REG_OFFSET(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater), data);
-	}
-
-	WREG32(SOC15_REG_OFFSET(DF, 0, mmFabricConfigAccessControl),
-	       mmFabricConfigAccessControl_DEFAULT);
-}
-
 static int soc15_common_set_clockgating_state(void *handle,
 					    enum amd_clockgating_state state)
 {
@@ -908,6 +905,7 @@ static int soc15_common_set_clockgating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 		adev->nbio_funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		adev->nbio_funcs->update_medium_grain_light_sleep(adev,
@@ -920,7 +918,7 @@ static int soc15_common_set_clockgating_state(void *handle,
 				state == AMD_CG_STATE_GATE ? true : false);
 		soc15_update_rom_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
-		soc15_update_df_medium_grain_clock_gating(adev,
+		adev->df_funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		break;
 	case CHIP_RAVEN:
@@ -973,10 +971,7 @@ static void soc15_common_get_clockgating_state(void *handle, u32 *flags)
 	if (!(data & CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE0_MASK))
 		*flags |= AMD_CG_SUPPORT_ROM_MGCG;
 
-	/* AMD_CG_SUPPORT_DF_MGCG */
-	data = RREG32(SOC15_REG_OFFSET(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater));
-	if (data & DF_MGCG_ENABLE_15_CYCLE_DELAY)
-		*flags |= AMD_CG_SUPPORT_DF_MGCG;
+	adev->df_funcs->get_clockgating_state(adev, flags);
 }
 
 static int soc15_common_set_powergating_state(void *handle,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h
index f70da8a29f86..1f714b7af520 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.h
@@ -55,5 +55,6 @@ void soc15_program_register_sequence(struct amdgpu_device *adev,
 					     const u32 array_size);
 
 int vega10_reg_base_init(struct amdgpu_device *adev);
+int vega20_reg_base_init(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index def865067edd..0942f492d2e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -47,6 +47,21 @@
 #define WREG32_SOC15_OFFSET(ip, inst, reg, offset, value) \
 	WREG32((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, value)
 
+#define SOC15_WAIT_ON_RREG(ip, inst, reg, expected_value, mask, ret) \
+	do {							\
+		uint32_t tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
+		uint32_t loop = adev->usec_timeout;		\
+		while ((tmp_ & (mask)) != (expected_value)) {	\
+			udelay(2);				\
+			tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
+			loop--;					\
+			if (!loop) {				\
+				ret = -ETIMEDOUT;		\
+				break;				\
+			}					\
+		}						\
+	} while (0)
+
 #endif
 
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h
index 7f408f85fdb6..8dc29107228f 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15d.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h
@@ -159,6 +159,7 @@
 #define		EOP_TC_WB_ACTION_EN                     (1 << 15) /* L2 */
 #define		EOP_TCL1_ACTION_EN                      (1 << 16)
 #define		EOP_TC_ACTION_EN                        (1 << 17) /* L2 */
+#define		EOP_TC_NC_ACTION_EN			(1 << 19)
 #define		EOP_TC_MD_ACTION_EN			(1 << 21) /* L2 metadata */
 
 #define		DATA_SEL(x)                             ((x) << 29)
@@ -268,6 +269,11 @@
 			 * x=1: tmz_end
 			 */
 
+#define	PACKET3_INVALIDATE_TLBS				0x98
+#              define PACKET3_INVALIDATE_TLBS_DST_SEL(x)     ((x) << 0)
+#              define PACKET3_INVALIDATE_TLBS_ALL_HUB(x)     ((x) << 4)
+#              define PACKET3_INVALIDATE_TLBS_PASID(x)       ((x) << 5)
+#              define PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(x)  ((x) << 29)
 #define PACKET3_SET_RESOURCES				0xA0
 /* 1. header
  * 2. CONTROL
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 948bb9437757..6fed3d7797a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -93,6 +93,7 @@ static void uvd_v4_2_ring_set_wptr(struct amdgpu_ring *ring)
 static int uvd_v4_2_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	adev->uvd.num_uvd_inst = 1;
 
 	uvd_v4_2_set_ring_funcs(adev);
 	uvd_v4_2_set_irq_funcs(adev);
@@ -107,7 +108,7 @@ static int uvd_v4_2_sw_init(void *handle)
 	int r;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
@@ -119,9 +120,9 @@ static int uvd_v4_2_sw_init(void *handle)
 	if (r)
 		return r;
 
-	ring = &adev->uvd.ring;
+	ring = &adev->uvd.inst->ring;
 	sprintf(ring->name, "uvd");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
+	r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0);
 
 	return r;
 }
@@ -150,7 +151,7 @@ static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
 static int uvd_v4_2_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 	uint32_t tmp;
 	int r;
 
@@ -208,7 +209,7 @@ done:
 static int uvd_v4_2_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 
 	if (RREG32(mmUVD_STATUS) != 0)
 		uvd_v4_2_stop(adev);
@@ -251,7 +252,7 @@ static int uvd_v4_2_resume(void *handle)
  */
 static int uvd_v4_2_start(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 	uint32_t rb_bufsz;
 	int i, j, r;
 	u32 tmp;
@@ -523,6 +524,18 @@ static void uvd_v4_2_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
+static void uvd_v4_2_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKET0(mmUVD_NO_OP, 0));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
 /**
  * uvd_v4_2_mc_resume - memory controller programming
  *
@@ -536,7 +549,7 @@ static void uvd_v4_2_mc_resume(struct amdgpu_device *adev)
 	uint32_t size;
 
 	/* programm the VCPU memory controller bits 0-27 */
-	addr = (adev->uvd.gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3;
+	addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3;
 	size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3;
 	WREG32(mmUVD_VCPU_CACHE_OFFSET0, addr);
 	WREG32(mmUVD_VCPU_CACHE_SIZE0, size);
@@ -553,11 +566,11 @@ static void uvd_v4_2_mc_resume(struct amdgpu_device *adev)
 	WREG32(mmUVD_VCPU_CACHE_SIZE2, size);
 
 	/* bits 28-31 */
-	addr = (adev->uvd.gpu_addr >> 28) & 0xF;
+	addr = (adev->uvd.inst->gpu_addr >> 28) & 0xF;
 	WREG32(mmUVD_LMI_ADDR_EXT, (addr << 12) | (addr << 0));
 
 	/* bits 32-39 */
-	addr = (adev->uvd.gpu_addr >> 32) & 0xFF;
+	addr = (adev->uvd.inst->gpu_addr >> 32) & 0xFF;
 	WREG32(mmUVD_LMI_EXT40_ADDR, addr | (0x9 << 16) | (0x1 << 31));
 
 	WREG32(mmUVD_UDEC_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
@@ -664,7 +677,7 @@ static int uvd_v4_2_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_iv_entry *entry)
 {
 	DRM_DEBUG("IH: UVD TRAP\n");
-	amdgpu_fence_process(&adev->uvd.ring);
+	amdgpu_fence_process(&adev->uvd.inst->ring);
 	return 0;
 }
 
@@ -688,7 +701,7 @@ static int uvd_v4_2_set_powergating_state(void *handle,
 
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v4_2_stop(adev);
-		if (adev->pg_flags & AMD_PG_SUPPORT_UVD && amdgpu_dpm == 0) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_UVD && !adev->pm.dpm_enabled) {
 			if (!(RREG32_SMC(ixCURRENT_PG_STATUS) &
 				CURRENT_PG_STATUS__UVD_PG_STATUS_MASK)) {
 				WREG32(mmUVD_PGFSM_CONFIG, (UVD_PGFSM_CONFIG__UVD_PGFSM_FSM_ADDR_MASK   |
@@ -699,7 +712,7 @@ static int uvd_v4_2_set_powergating_state(void *handle,
 		}
 		return 0;
 	} else {
-		if (adev->pg_flags & AMD_PG_SUPPORT_UVD && amdgpu_dpm == 0) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_UVD && !adev->pm.dpm_enabled) {
 			if (RREG32_SMC(ixCURRENT_PG_STATUS) &
 				CURRENT_PG_STATUS__UVD_PG_STATUS_MASK) {
 				WREG32(mmUVD_PGFSM_CONFIG, (UVD_PGFSM_CONFIG__UVD_PGFSM_FSM_ADDR_MASK   |
@@ -732,7 +745,6 @@ static const struct amd_ip_funcs uvd_v4_2_ip_funcs = {
 static const struct amdgpu_ring_funcs uvd_v4_2_ring_funcs = {
 	.type = AMDGPU_RING_TYPE_UVD,
 	.align_mask = 0xf,
-	.nop = PACKET0(mmUVD_NO_OP, 0),
 	.support_64bit_ptrs = false,
 	.get_rptr = uvd_v4_2_ring_get_rptr,
 	.get_wptr = uvd_v4_2_ring_get_wptr,
@@ -745,7 +757,7 @@ static const struct amdgpu_ring_funcs uvd_v4_2_ring_funcs = {
 	.emit_fence = uvd_v4_2_ring_emit_fence,
 	.test_ring = uvd_v4_2_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = uvd_v4_2_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_uvd_ring_begin_use,
 	.end_use = amdgpu_uvd_ring_end_use,
@@ -753,7 +765,7 @@ static const struct amdgpu_ring_funcs uvd_v4_2_ring_funcs = {
 
 static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.ring.funcs = &uvd_v4_2_ring_funcs;
+	adev->uvd.inst->ring.funcs = &uvd_v4_2_ring_funcs;
 }
 
 static const struct amdgpu_irq_src_funcs uvd_v4_2_irq_funcs = {
@@ -763,8 +775,8 @@ static const struct amdgpu_irq_src_funcs uvd_v4_2_irq_funcs = {
 
 static void uvd_v4_2_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.irq.num_types = 1;
-	adev->uvd.irq.funcs = &uvd_v4_2_irq_funcs;
+	adev->uvd.inst->irq.num_types = 1;
+	adev->uvd.inst->irq.funcs = &uvd_v4_2_irq_funcs;
 }
 
 const struct amdgpu_ip_block_version uvd_v4_2_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 6445d55e7d5a..341ee6d55ce8 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -89,6 +89,7 @@ static void uvd_v5_0_ring_set_wptr(struct amdgpu_ring *ring)
 static int uvd_v5_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	adev->uvd.num_uvd_inst = 1;
 
 	uvd_v5_0_set_ring_funcs(adev);
 	uvd_v5_0_set_irq_funcs(adev);
@@ -103,7 +104,7 @@ static int uvd_v5_0_sw_init(void *handle)
 	int r;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
@@ -115,9 +116,9 @@ static int uvd_v5_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	ring = &adev->uvd.ring;
+	ring = &adev->uvd.inst->ring;
 	sprintf(ring->name, "uvd");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
+	r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0);
 
 	return r;
 }
@@ -144,7 +145,7 @@ static int uvd_v5_0_sw_fini(void *handle)
 static int uvd_v5_0_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 	uint32_t tmp;
 	int r;
 
@@ -204,7 +205,7 @@ done:
 static int uvd_v5_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 
 	if (RREG32(mmUVD_STATUS) != 0)
 		uvd_v5_0_stop(adev);
@@ -253,9 +254,9 @@ static void uvd_v5_0_mc_resume(struct amdgpu_device *adev)
 
 	/* programm memory controller bits 0-27 */
 	WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-			lower_32_bits(adev->uvd.gpu_addr));
+			lower_32_bits(adev->uvd.inst->gpu_addr));
 	WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-			upper_32_bits(adev->uvd.gpu_addr));
+			upper_32_bits(adev->uvd.inst->gpu_addr));
 
 	offset = AMDGPU_UVD_FIRMWARE_OFFSET;
 	size = AMDGPU_UVD_FIRMWARE_SIZE(adev);
@@ -287,7 +288,7 @@ static void uvd_v5_0_mc_resume(struct amdgpu_device *adev)
  */
 static int uvd_v5_0_start(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 	uint32_t rb_bufsz, tmp;
 	uint32_t lmi_swap_cntl;
 	uint32_t mp_swap_cntl;
@@ -540,6 +541,18 @@ static void uvd_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
+static void uvd_v5_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKET0(mmUVD_NO_OP, 0));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
 static bool uvd_v5_0_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -586,7 +599,7 @@ static int uvd_v5_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_iv_entry *entry)
 {
 	DRM_DEBUG("IH: UVD TRAP\n");
-	amdgpu_fence_process(&adev->uvd.ring);
+	amdgpu_fence_process(&adev->uvd.inst->ring);
 	return 0;
 }
 
@@ -840,7 +853,6 @@ static const struct amd_ip_funcs uvd_v5_0_ip_funcs = {
 static const struct amdgpu_ring_funcs uvd_v5_0_ring_funcs = {
 	.type = AMDGPU_RING_TYPE_UVD,
 	.align_mask = 0xf,
-	.nop = PACKET0(mmUVD_NO_OP, 0),
 	.support_64bit_ptrs = false,
 	.get_rptr = uvd_v5_0_ring_get_rptr,
 	.get_wptr = uvd_v5_0_ring_get_wptr,
@@ -853,7 +865,7 @@ static const struct amdgpu_ring_funcs uvd_v5_0_ring_funcs = {
 	.emit_fence = uvd_v5_0_ring_emit_fence,
 	.test_ring = uvd_v5_0_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = uvd_v5_0_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_uvd_ring_begin_use,
 	.end_use = amdgpu_uvd_ring_end_use,
@@ -861,7 +873,7 @@ static const struct amdgpu_ring_funcs uvd_v5_0_ring_funcs = {
 
 static void uvd_v5_0_set_ring_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.ring.funcs = &uvd_v5_0_ring_funcs;
+	adev->uvd.inst->ring.funcs = &uvd_v5_0_ring_funcs;
 }
 
 static const struct amdgpu_irq_src_funcs uvd_v5_0_irq_funcs = {
@@ -871,8 +883,8 @@ static const struct amdgpu_irq_src_funcs uvd_v5_0_irq_funcs = {
 
 static void uvd_v5_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.irq.num_types = 1;
-	adev->uvd.irq.funcs = &uvd_v5_0_irq_funcs;
+	adev->uvd.inst->irq.num_types = 1;
+	adev->uvd.inst->irq.funcs = &uvd_v5_0_irq_funcs;
 }
 
 const struct amdgpu_ip_block_version uvd_v5_0_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index f26f515db2fb..bfddf97dd13e 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -62,7 +62,7 @@ static void uvd_v6_0_enable_mgcg(struct amdgpu_device *adev,
 static inline bool uvd_v6_0_enc_support(struct amdgpu_device *adev)
 {
 	return ((adev->asic_type >= CHIP_POLARIS10) &&
-			(adev->asic_type <= CHIP_POLARIS12) &&
+			(adev->asic_type <= CHIP_VEGAM) &&
 			(!adev->uvd.fw_version || adev->uvd.fw_version >= FW_1_130_16));
 }
 
@@ -91,7 +91,7 @@ static uint64_t uvd_v6_0_enc_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->uvd.ring_enc[0])
+	if (ring == &adev->uvd.inst->ring_enc[0])
 		return RREG32(mmUVD_RB_RPTR);
 	else
 		return RREG32(mmUVD_RB_RPTR2);
@@ -121,7 +121,7 @@ static uint64_t uvd_v6_0_enc_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->uvd.ring_enc[0])
+	if (ring == &adev->uvd.inst->ring_enc[0])
 		return RREG32(mmUVD_RB_WPTR);
 	else
 		return RREG32(mmUVD_RB_WPTR2);
@@ -152,7 +152,7 @@ static void uvd_v6_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->uvd.ring_enc[0])
+	if (ring == &adev->uvd.inst->ring_enc[0])
 		WREG32(mmUVD_RB_WPTR,
 			lower_32_bits(ring->wptr));
 	else
@@ -375,6 +375,7 @@ error:
 static int uvd_v6_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	adev->uvd.num_uvd_inst = 1;
 
 	if (!(adev->flags & AMD_IS_APU) &&
 	    (RREG32_SMC(ixCC_HARVEST_FUSES) & CC_HARVEST_FUSES__UVD_DISABLE_MASK))
@@ -399,14 +400,14 @@ static int uvd_v6_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
 	/* UVD ENC TRAP */
 	if (uvd_v6_0_enc_support(adev)) {
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + 119, &adev->uvd.irq);
+			r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + 119, &adev->uvd.inst->irq);
 			if (r)
 				return r;
 		}
@@ -418,18 +419,18 @@ static int uvd_v6_0_sw_init(void *handle)
 
 	if (!uvd_v6_0_enc_support(adev)) {
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
-			adev->uvd.ring_enc[i].funcs = NULL;
+			adev->uvd.inst->ring_enc[i].funcs = NULL;
 
-		adev->uvd.irq.num_types = 1;
+		adev->uvd.inst->irq.num_types = 1;
 		adev->uvd.num_enc_rings = 0;
 
 		DRM_INFO("UVD ENC is disabled\n");
 	} else {
 		struct drm_sched_rq *rq;
-		ring = &adev->uvd.ring_enc[0];
+		ring = &adev->uvd.inst->ring_enc[0];
 		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
-					  rq, amdgpu_sched_jobs, NULL);
+		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst->entity_enc,
+					  rq, NULL);
 		if (r) {
 			DRM_ERROR("Failed setting up UVD ENC run queue.\n");
 			return r;
@@ -440,17 +441,17 @@ static int uvd_v6_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	ring = &adev->uvd.ring;
+	ring = &adev->uvd.inst->ring;
 	sprintf(ring->name, "uvd");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
+	r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0);
 	if (r)
 		return r;
 
 	if (uvd_v6_0_enc_support(adev)) {
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			ring = &adev->uvd.ring_enc[i];
+			ring = &adev->uvd.inst->ring_enc[i];
 			sprintf(ring->name, "uvd_enc%d", i);
-			r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
+			r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0);
 			if (r)
 				return r;
 		}
@@ -469,10 +470,10 @@ static int uvd_v6_0_sw_fini(void *handle)
 		return r;
 
 	if (uvd_v6_0_enc_support(adev)) {
-		drm_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
+		drm_sched_entity_fini(&adev->uvd.inst->ring_enc[0].sched, &adev->uvd.inst->entity_enc);
 
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
-			amdgpu_ring_fini(&adev->uvd.ring_enc[i]);
+			amdgpu_ring_fini(&adev->uvd.inst->ring_enc[i]);
 	}
 
 	return amdgpu_uvd_sw_fini(adev);
@@ -488,7 +489,7 @@ static int uvd_v6_0_sw_fini(void *handle)
 static int uvd_v6_0_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 	uint32_t tmp;
 	int i, r;
 
@@ -532,7 +533,7 @@ static int uvd_v6_0_hw_init(void *handle)
 
 	if (uvd_v6_0_enc_support(adev)) {
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			ring = &adev->uvd.ring_enc[i];
+			ring = &adev->uvd.inst->ring_enc[i];
 			ring->ready = true;
 			r = amdgpu_ring_test_ring(ring);
 			if (r) {
@@ -563,7 +564,7 @@ done:
 static int uvd_v6_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 
 	if (RREG32(mmUVD_STATUS) != 0)
 		uvd_v6_0_stop(adev);
@@ -611,9 +612,9 @@ static void uvd_v6_0_mc_resume(struct amdgpu_device *adev)
 
 	/* programm memory controller bits 0-27 */
 	WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-			lower_32_bits(adev->uvd.gpu_addr));
+			lower_32_bits(adev->uvd.inst->gpu_addr));
 	WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-			upper_32_bits(adev->uvd.gpu_addr));
+			upper_32_bits(adev->uvd.inst->gpu_addr));
 
 	offset = AMDGPU_UVD_FIRMWARE_OFFSET;
 	size = AMDGPU_UVD_FIRMWARE_SIZE(adev);
@@ -726,7 +727,7 @@ static void cz_set_uvd_clock_gating_branches(struct amdgpu_device *adev,
  */
 static int uvd_v6_0_start(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst->ring;
 	uint32_t rb_bufsz, tmp;
 	uint32_t lmi_swap_cntl;
 	uint32_t mp_swap_cntl;
@@ -866,14 +867,14 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	WREG32_FIELD(UVD_RBC_RB_CNTL, RB_NO_FETCH, 0);
 
 	if (uvd_v6_0_enc_support(adev)) {
-		ring = &adev->uvd.ring_enc[0];
+		ring = &adev->uvd.inst->ring_enc[0];
 		WREG32(mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
 		WREG32(mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
 		WREG32(mmUVD_RB_BASE_LO, ring->gpu_addr);
 		WREG32(mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
 		WREG32(mmUVD_RB_SIZE, ring->ring_size / 4);
 
-		ring = &adev->uvd.ring_enc[1];
+		ring = &adev->uvd.inst->ring_enc[1];
 		WREG32(mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
 		WREG32(mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
 		WREG32(mmUVD_RB_BASE_LO2, ring->gpu_addr);
@@ -964,6 +965,16 @@ static void uvd_v6_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
 }
 
 /**
+ * uvd_v6_0_ring_emit_hdp_flush - skip HDP flushing
+ *
+ * @ring: amdgpu_ring pointer
+ */
+static void uvd_v6_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+{
+	/* The firmware doesn't seem to like touching registers at this point. */
+}
+
+/**
  * uvd_v6_0_ring_test_ring - register write test
  *
  * @ring: amdgpu_ring pointer
@@ -1089,6 +1100,18 @@ static void uvd_v6_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, 0xE);
 }
 
+static void uvd_v6_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKET0(mmUVD_NO_OP, 0));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
 static void uvd_v6_0_enc_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 {
 	uint32_t seq = ring->fence_drv.sync_seq;
@@ -1148,10 +1171,10 @@ static bool uvd_v6_0_check_soft_reset(void *handle)
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_UVD, 1);
 
 	if (srbm_soft_reset) {
-		adev->uvd.srbm_soft_reset = srbm_soft_reset;
+		adev->uvd.inst->srbm_soft_reset = srbm_soft_reset;
 		return true;
 	} else {
-		adev->uvd.srbm_soft_reset = 0;
+		adev->uvd.inst->srbm_soft_reset = 0;
 		return false;
 	}
 }
@@ -1160,7 +1183,7 @@ static int uvd_v6_0_pre_soft_reset(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!adev->uvd.srbm_soft_reset)
+	if (!adev->uvd.inst->srbm_soft_reset)
 		return 0;
 
 	uvd_v6_0_stop(adev);
@@ -1172,9 +1195,9 @@ static int uvd_v6_0_soft_reset(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	u32 srbm_soft_reset;
 
-	if (!adev->uvd.srbm_soft_reset)
+	if (!adev->uvd.inst->srbm_soft_reset)
 		return 0;
-	srbm_soft_reset = adev->uvd.srbm_soft_reset;
+	srbm_soft_reset = adev->uvd.inst->srbm_soft_reset;
 
 	if (srbm_soft_reset) {
 		u32 tmp;
@@ -1202,7 +1225,7 @@ static int uvd_v6_0_post_soft_reset(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!adev->uvd.srbm_soft_reset)
+	if (!adev->uvd.inst->srbm_soft_reset)
 		return 0;
 
 	mdelay(5);
@@ -1228,17 +1251,17 @@ static int uvd_v6_0_process_interrupt(struct amdgpu_device *adev,
 
 	switch (entry->src_id) {
 	case 124:
-		amdgpu_fence_process(&adev->uvd.ring);
+		amdgpu_fence_process(&adev->uvd.inst->ring);
 		break;
 	case 119:
 		if (likely(uvd_v6_0_enc_support(adev)))
-			amdgpu_fence_process(&adev->uvd.ring_enc[0]);
+			amdgpu_fence_process(&adev->uvd.inst->ring_enc[0]);
 		else
 			int_handled = false;
 		break;
 	case 120:
 		if (likely(uvd_v6_0_enc_support(adev)))
-			amdgpu_fence_process(&adev->uvd.ring_enc[1]);
+			amdgpu_fence_process(&adev->uvd.inst->ring_enc[1]);
 		else
 			int_handled = false;
 		break;
@@ -1521,22 +1544,22 @@ static const struct amd_ip_funcs uvd_v6_0_ip_funcs = {
 static const struct amdgpu_ring_funcs uvd_v6_0_ring_phys_funcs = {
 	.type = AMDGPU_RING_TYPE_UVD,
 	.align_mask = 0xf,
-	.nop = PACKET0(mmUVD_NO_OP, 0),
 	.support_64bit_ptrs = false,
 	.get_rptr = uvd_v6_0_ring_get_rptr,
 	.get_wptr = uvd_v6_0_ring_get_wptr,
 	.set_wptr = uvd_v6_0_ring_set_wptr,
 	.parse_cs = amdgpu_uvd_ring_parse_cs,
 	.emit_frame_size =
-		6 + 6 + /* hdp flush / invalidate */
+		6 + /* hdp invalidate */
 		10 + /* uvd_v6_0_ring_emit_pipeline_sync */
 		14, /* uvd_v6_0_ring_emit_fence x1 no user fence */
 	.emit_ib_size = 8, /* uvd_v6_0_ring_emit_ib */
 	.emit_ib = uvd_v6_0_ring_emit_ib,
 	.emit_fence = uvd_v6_0_ring_emit_fence,
+	.emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush,
 	.test_ring = uvd_v6_0_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = uvd_v6_0_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_uvd_ring_begin_use,
 	.end_use = amdgpu_uvd_ring_end_use,
@@ -1552,7 +1575,7 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
 	.get_wptr = uvd_v6_0_ring_get_wptr,
 	.set_wptr = uvd_v6_0_ring_set_wptr,
 	.emit_frame_size =
-		6 + 6 + /* hdp flush / invalidate */
+		6 + /* hdp invalidate */
 		10 + /* uvd_v6_0_ring_emit_pipeline_sync */
 		VI_FLUSH_GPU_TLB_NUM_WREG * 6 + 8 + /* uvd_v6_0_ring_emit_vm_flush */
 		14 + 14, /* uvd_v6_0_ring_emit_fence x2 vm fence */
@@ -1561,6 +1584,7 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
 	.emit_fence = uvd_v6_0_ring_emit_fence,
 	.emit_vm_flush = uvd_v6_0_ring_emit_vm_flush,
 	.emit_pipeline_sync = uvd_v6_0_ring_emit_pipeline_sync,
+	.emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush,
 	.test_ring = uvd_v6_0_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
@@ -1600,10 +1624,10 @@ static const struct amdgpu_ring_funcs uvd_v6_0_enc_ring_vm_funcs = {
 static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	if (adev->asic_type >= CHIP_POLARIS10) {
-		adev->uvd.ring.funcs = &uvd_v6_0_ring_vm_funcs;
+		adev->uvd.inst->ring.funcs = &uvd_v6_0_ring_vm_funcs;
 		DRM_INFO("UVD is enabled in VM mode\n");
 	} else {
-		adev->uvd.ring.funcs = &uvd_v6_0_ring_phys_funcs;
+		adev->uvd.inst->ring.funcs = &uvd_v6_0_ring_phys_funcs;
 		DRM_INFO("UVD is enabled in physical mode\n");
 	}
 }
@@ -1613,7 +1637,7 @@ static void uvd_v6_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_enc_rings; ++i)
-		adev->uvd.ring_enc[i].funcs = &uvd_v6_0_enc_ring_vm_funcs;
+		adev->uvd.inst->ring_enc[i].funcs = &uvd_v6_0_enc_ring_vm_funcs;
 
 	DRM_INFO("UVD ENC is enabled in VM mode\n");
 }
@@ -1626,11 +1650,11 @@ static const struct amdgpu_irq_src_funcs uvd_v6_0_irq_funcs = {
 static void uvd_v6_0_set_irq_funcs(struct amdgpu_device *adev)
 {
 	if (uvd_v6_0_enc_support(adev))
-		adev->uvd.irq.num_types = adev->uvd.num_enc_rings + 1;
+		adev->uvd.inst->irq.num_types = adev->uvd.num_enc_rings + 1;
 	else
-		adev->uvd.irq.num_types = 1;
+		adev->uvd.inst->irq.num_types = 1;
 
-	adev->uvd.irq.funcs = &uvd_v6_0_irq_funcs;
+	adev->uvd.inst->irq.funcs = &uvd_v6_0_irq_funcs;
 }
 
 const struct amdgpu_ip_block_version uvd_v6_0_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index eddc57f3b72a..57d32f21b3a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -40,6 +40,8 @@
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
 
+#define UVD7_MAX_HW_INSTANCES_VEGA20			2
+
 static void uvd_v7_0_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v7_0_set_enc_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v7_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -47,6 +49,11 @@ static int uvd_v7_0_start(struct amdgpu_device *adev);
 static void uvd_v7_0_stop(struct amdgpu_device *adev);
 static int uvd_v7_0_sriov_start(struct amdgpu_device *adev);
 
+static int amdgpu_ih_clientid_uvds[] = {
+	SOC15_IH_CLIENTID_UVD,
+	SOC15_IH_CLIENTID_UVD1
+};
+
 /**
  * uvd_v7_0_ring_get_rptr - get read pointer
  *
@@ -58,7 +65,7 @@ static uint64_t uvd_v7_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	return RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR);
+	return RREG32_SOC15(UVD, ring->me, mmUVD_RBC_RB_RPTR);
 }
 
 /**
@@ -72,10 +79,10 @@ static uint64_t uvd_v7_0_enc_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->uvd.ring_enc[0])
-		return RREG32_SOC15(UVD, 0, mmUVD_RB_RPTR);
+	if (ring == &adev->uvd.inst[ring->me].ring_enc[0])
+		return RREG32_SOC15(UVD, ring->me, mmUVD_RB_RPTR);
 	else
-		return RREG32_SOC15(UVD, 0, mmUVD_RB_RPTR2);
+		return RREG32_SOC15(UVD, ring->me, mmUVD_RB_RPTR2);
 }
 
 /**
@@ -89,7 +96,7 @@ static uint64_t uvd_v7_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	return RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR);
+	return RREG32_SOC15(UVD, ring->me, mmUVD_RBC_RB_WPTR);
 }
 
 /**
@@ -106,10 +113,10 @@ static uint64_t uvd_v7_0_enc_ring_get_wptr(struct amdgpu_ring *ring)
 	if (ring->use_doorbell)
 		return adev->wb.wb[ring->wptr_offs];
 
-	if (ring == &adev->uvd.ring_enc[0])
-		return RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR);
+	if (ring == &adev->uvd.inst[ring->me].ring_enc[0])
+		return RREG32_SOC15(UVD, ring->me, mmUVD_RB_WPTR);
 	else
-		return RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2);
+		return RREG32_SOC15(UVD, ring->me, mmUVD_RB_WPTR2);
 }
 
 /**
@@ -123,7 +130,7 @@ static void uvd_v7_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
+	WREG32_SOC15(UVD, ring->me, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
 }
 
 /**
@@ -144,11 +151,11 @@ static void uvd_v7_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
 		return;
 	}
 
-	if (ring == &adev->uvd.ring_enc[0])
-		WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR,
+	if (ring == &adev->uvd.inst[ring->me].ring_enc[0])
+		WREG32_SOC15(UVD, ring->me, mmUVD_RB_WPTR,
 			lower_32_bits(ring->wptr));
 	else
-		WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2,
+		WREG32_SOC15(UVD, ring->me, mmUVD_RB_WPTR2,
 			lower_32_bits(ring->wptr));
 }
 
@@ -170,8 +177,8 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring)
 
 	r = amdgpu_ring_alloc(ring, 16);
 	if (r) {
-		DRM_ERROR("amdgpu: uvd enc failed to lock ring %d (%d).\n",
-			  ring->idx, r);
+		DRM_ERROR("amdgpu: uvd enc failed to lock (%d)ring %d (%d).\n",
+			  ring->me, ring->idx, r);
 		return r;
 	}
 	amdgpu_ring_write(ring, HEVC_ENC_CMD_END);
@@ -184,11 +191,11 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
-			 ring->idx, i);
+		DRM_DEBUG("(%d)ring test on %d succeeded in %d usecs\n",
+			 ring->me, ring->idx, i);
 	} else {
-		DRM_ERROR("amdgpu: ring %d test failed\n",
-			  ring->idx);
+		DRM_ERROR("amdgpu: (%d)ring %d test failed\n",
+			  ring->me, ring->idx);
 		r = -ETIMEDOUT;
 	}
 
@@ -342,24 +349,24 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 	r = uvd_v7_0_enc_get_create_msg(ring, 1, NULL);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get create msg (%ld).\n", r);
+		DRM_ERROR("amdgpu: (%d)failed to get create msg (%ld).\n", ring->me, r);
 		goto error;
 	}
 
 	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, true, &fence);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r);
+		DRM_ERROR("amdgpu: (%d)failed to get destroy ib (%ld).\n", ring->me, r);
 		goto error;
 	}
 
 	r = dma_fence_wait_timeout(fence, false, timeout);
 	if (r == 0) {
-		DRM_ERROR("amdgpu: IB test timed out.\n");
+		DRM_ERROR("amdgpu: (%d)IB test timed out.\n", ring->me);
 		r = -ETIMEDOUT;
 	} else if (r < 0) {
-		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
+		DRM_ERROR("amdgpu: (%d)fence wait failed (%ld).\n", ring->me, r);
 	} else {
-		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on (%d)ring %d succeeded\n", ring->me, ring->idx);
 		r = 0;
 	}
 error:
@@ -370,6 +377,10 @@ error:
 static int uvd_v7_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	if (adev->asic_type == CHIP_VEGA20)
+		adev->uvd.num_uvd_inst = UVD7_MAX_HW_INSTANCES_VEGA20;
+	else
+		adev->uvd.num_uvd_inst = 1;
 
 	if (amdgpu_sriov_vf(adev))
 		adev->uvd.num_enc_rings = 1;
@@ -386,19 +397,21 @@ static int uvd_v7_0_sw_init(void *handle)
 {
 	struct amdgpu_ring *ring;
 	struct drm_sched_rq *rq;
-	int i, r;
+	int i, j, r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UVD, 124, &adev->uvd.irq);
-	if (r)
-		return r;
-
-	/* UVD ENC TRAP */
-	for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UVD, i + 119, &adev->uvd.irq);
+	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		/* UVD TRAP */
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], 124, &adev->uvd.inst[j].irq);
 		if (r)
 			return r;
+
+		/* UVD ENC TRAP */
+		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
+			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], i + 119, &adev->uvd.inst[j].irq);
+			if (r)
+				return r;
+		}
 	}
 
 	r = amdgpu_uvd_sw_init(adev);
@@ -415,43 +428,48 @@ static int uvd_v7_0_sw_init(void *handle)
 		DRM_INFO("PSP loading UVD firmware\n");
 	}
 
-	ring = &adev->uvd.ring_enc[0];
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
-				  rq, amdgpu_sched_jobs, NULL);
-	if (r) {
-		DRM_ERROR("Failed setting up UVD ENC run queue.\n");
-		return r;
+	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		ring = &adev->uvd.inst[j].ring_enc[0];
+		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity_enc,
+					  rq, NULL);
+		if (r) {
+			DRM_ERROR("(%d)Failed setting up UVD ENC run queue.\n", j);
+			return r;
+		}
 	}
 
 	r = amdgpu_uvd_resume(adev);
 	if (r)
 		return r;
-	if (!amdgpu_sriov_vf(adev)) {
-		ring = &adev->uvd.ring;
-		sprintf(ring->name, "uvd");
-		r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
-		if (r)
-			return r;
-	}
 
-	for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-		ring = &adev->uvd.ring_enc[i];
-		sprintf(ring->name, "uvd_enc%d", i);
-		if (amdgpu_sriov_vf(adev)) {
-			ring->use_doorbell = true;
-
-			/* currently only use the first enconding ring for
-			 * sriov, so set unused location for other unused rings.
-			 */
-			if (i == 0)
-				ring->doorbell_index = AMDGPU_DOORBELL64_UVD_RING0_1 * 2;
-			else
-				ring->doorbell_index = AMDGPU_DOORBELL64_UVD_RING2_3 * 2 + 1;
+	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		if (!amdgpu_sriov_vf(adev)) {
+			ring = &adev->uvd.inst[j].ring;
+			sprintf(ring->name, "uvd<%d>", j);
+			r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst[j].irq, 0);
+			if (r)
+				return r;
+		}
+
+		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
+			ring = &adev->uvd.inst[j].ring_enc[i];
+			sprintf(ring->name, "uvd_enc%d<%d>", i, j);
+			if (amdgpu_sriov_vf(adev)) {
+				ring->use_doorbell = true;
+
+				/* currently only use the first enconding ring for
+				 * sriov, so set unused location for other unused rings.
+				 */
+				if (i == 0)
+					ring->doorbell_index = AMDGPU_DOORBELL64_UVD_RING0_1 * 2;
+				else
+					ring->doorbell_index = AMDGPU_DOORBELL64_UVD_RING2_3 * 2 + 1;
+			}
+			r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst[j].irq, 0);
+			if (r)
+				return r;
 		}
-		r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
-		if (r)
-			return r;
 	}
 
 	r = amdgpu_virt_alloc_mm_table(adev);
@@ -463,7 +481,7 @@ static int uvd_v7_0_sw_init(void *handle)
 
 static int uvd_v7_0_sw_fini(void *handle)
 {
-	int i, r;
+	int i, j, r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_virt_free_mm_table(adev);
@@ -472,11 +490,12 @@ static int uvd_v7_0_sw_fini(void *handle)
 	if (r)
 		return r;
 
-	drm_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
-
-	for (i = 0; i < adev->uvd.num_enc_rings; ++i)
-		amdgpu_ring_fini(&adev->uvd.ring_enc[i]);
+	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		drm_sched_entity_fini(&adev->uvd.inst[j].ring_enc[0].sched, &adev->uvd.inst[j].entity_enc);
 
+		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
+			amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]);
+	}
 	return amdgpu_uvd_sw_fini(adev);
 }
 
@@ -490,9 +509,9 @@ static int uvd_v7_0_sw_fini(void *handle)
 static int uvd_v7_0_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring;
 	uint32_t tmp;
-	int i, r;
+	int i, j, r;
 
 	if (amdgpu_sriov_vf(adev))
 		r = uvd_v7_0_sriov_start(adev);
@@ -501,57 +520,60 @@ static int uvd_v7_0_hw_init(void *handle)
 	if (r)
 		goto done;
 
-	if (!amdgpu_sriov_vf(adev)) {
-		ring->ready = true;
-		r = amdgpu_ring_test_ring(ring);
-		if (r) {
-			ring->ready = false;
-			goto done;
+	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		ring = &adev->uvd.inst[j].ring;
+
+		if (!amdgpu_sriov_vf(adev)) {
+			ring->ready = true;
+			r = amdgpu_ring_test_ring(ring);
+			if (r) {
+				ring->ready = false;
+				goto done;
+			}
+
+			r = amdgpu_ring_alloc(ring, 10);
+			if (r) {
+				DRM_ERROR("amdgpu: (%d)ring failed to lock UVD ring (%d).\n", j, r);
+				goto done;
+			}
+
+			tmp = PACKET0(SOC15_REG_OFFSET(UVD, j,
+				mmUVD_SEMA_WAIT_FAULT_TIMEOUT_CNTL), 0);
+			amdgpu_ring_write(ring, tmp);
+			amdgpu_ring_write(ring, 0xFFFFF);
+
+			tmp = PACKET0(SOC15_REG_OFFSET(UVD, j,
+				mmUVD_SEMA_WAIT_INCOMPLETE_TIMEOUT_CNTL), 0);
+			amdgpu_ring_write(ring, tmp);
+			amdgpu_ring_write(ring, 0xFFFFF);
+
+			tmp = PACKET0(SOC15_REG_OFFSET(UVD, j,
+				mmUVD_SEMA_SIGNAL_INCOMPLETE_TIMEOUT_CNTL), 0);
+			amdgpu_ring_write(ring, tmp);
+			amdgpu_ring_write(ring, 0xFFFFF);
+
+			/* Clear timeout status bits */
+			amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, j,
+				mmUVD_SEMA_TIMEOUT_STATUS), 0));
+			amdgpu_ring_write(ring, 0x8);
+
+			amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, j,
+				mmUVD_SEMA_CNTL), 0));
+			amdgpu_ring_write(ring, 3);
+
+			amdgpu_ring_commit(ring);
 		}
 
-		r = amdgpu_ring_alloc(ring, 10);
-		if (r) {
-			DRM_ERROR("amdgpu: ring failed to lock UVD ring (%d).\n", r);
-			goto done;
+		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
+			ring = &adev->uvd.inst[j].ring_enc[i];
+			ring->ready = true;
+			r = amdgpu_ring_test_ring(ring);
+			if (r) {
+				ring->ready = false;
+				goto done;
+			}
 		}
-
-		tmp = PACKET0(SOC15_REG_OFFSET(UVD, 0,
-			mmUVD_SEMA_WAIT_FAULT_TIMEOUT_CNTL), 0);
-		amdgpu_ring_write(ring, tmp);
-		amdgpu_ring_write(ring, 0xFFFFF);
-
-		tmp = PACKET0(SOC15_REG_OFFSET(UVD, 0,
-			mmUVD_SEMA_WAIT_INCOMPLETE_TIMEOUT_CNTL), 0);
-		amdgpu_ring_write(ring, tmp);
-		amdgpu_ring_write(ring, 0xFFFFF);
-
-		tmp = PACKET0(SOC15_REG_OFFSET(UVD, 0,
-			mmUVD_SEMA_SIGNAL_INCOMPLETE_TIMEOUT_CNTL), 0);
-		amdgpu_ring_write(ring, tmp);
-		amdgpu_ring_write(ring, 0xFFFFF);
-
-		/* Clear timeout status bits */
-		amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, 0,
-			mmUVD_SEMA_TIMEOUT_STATUS), 0));
-		amdgpu_ring_write(ring, 0x8);
-
-		amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, 0,
-			mmUVD_SEMA_CNTL), 0));
-		amdgpu_ring_write(ring, 3);
-
-		amdgpu_ring_commit(ring);
 	}
-
-	for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-		ring = &adev->uvd.ring_enc[i];
-		ring->ready = true;
-		r = amdgpu_ring_test_ring(ring);
-		if (r) {
-			ring->ready = false;
-			goto done;
-		}
-	}
-
 done:
 	if (!r)
 		DRM_INFO("UVD and UVD ENC initialized successfully.\n");
@@ -569,7 +591,7 @@ done:
 static int uvd_v7_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	int i;
 
 	if (!amdgpu_sriov_vf(adev))
 		uvd_v7_0_stop(adev);
@@ -578,7 +600,8 @@ static int uvd_v7_0_hw_fini(void *handle)
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
 	}
 
-	ring->ready = false;
+	for (i = 0; i < adev->uvd.num_uvd_inst; ++i)
+		adev->uvd.inst[i].ring.ready = false;
 
 	return 0;
 }
@@ -618,48 +641,51 @@ static void uvd_v7_0_mc_resume(struct amdgpu_device *adev)
 {
 	uint32_t size = AMDGPU_UVD_FIRMWARE_SIZE(adev);
 	uint32_t offset;
+	int i;
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
-		WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-			lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
-		WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-			upper_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
-		offset = 0;
-	} else {
-		WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-			lower_32_bits(adev->uvd.gpu_addr));
-		WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-			upper_32_bits(adev->uvd.gpu_addr));
-		offset = size;
-	}
+	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+				lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
+			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+				upper_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
+			offset = 0;
+		} else {
+			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+				lower_32_bits(adev->uvd.inst[i].gpu_addr));
+			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+				upper_32_bits(adev->uvd.inst[i].gpu_addr));
+			offset = size;
+		}
 
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0,
-				AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size);
-
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
-			lower_32_bits(adev->uvd.gpu_addr + offset));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
-			upper_32_bits(adev->uvd.gpu_addr + offset));
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1, (1 << 21));
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_UVD_HEAP_SIZE);
-
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
-			lower_32_bits(adev->uvd.gpu_addr + offset + AMDGPU_UVD_HEAP_SIZE));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
-			upper_32_bits(adev->uvd.gpu_addr + offset + AMDGPU_UVD_HEAP_SIZE));
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2, (2 << 21));
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE2,
-			AMDGPU_UVD_STACK_SIZE + (AMDGPU_UVD_SESSION_SIZE * 40));
-
-	WREG32_SOC15(UVD, 0, mmUVD_UDEC_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-	WREG32_SOC15(UVD, 0, mmUVD_UDEC_DB_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-	WREG32_SOC15(UVD, 0, mmUVD_UDEC_DBW_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-
-	WREG32_SOC15(UVD, 0, mmUVD_GP_SCRATCH4, adev->uvd.max_handles);
+		WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_OFFSET0,
+					AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+		WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_SIZE0, size);
+
+		WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
+				lower_32_bits(adev->uvd.inst[i].gpu_addr + offset));
+		WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
+				upper_32_bits(adev->uvd.inst[i].gpu_addr + offset));
+		WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_OFFSET1, (1 << 21));
+		WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_UVD_HEAP_SIZE);
+
+		WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
+				lower_32_bits(adev->uvd.inst[i].gpu_addr + offset + AMDGPU_UVD_HEAP_SIZE));
+		WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
+				upper_32_bits(adev->uvd.inst[i].gpu_addr + offset + AMDGPU_UVD_HEAP_SIZE));
+		WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_OFFSET2, (2 << 21));
+		WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_SIZE2,
+				AMDGPU_UVD_STACK_SIZE + (AMDGPU_UVD_SESSION_SIZE * 40));
+
+		WREG32_SOC15(UVD, i, mmUVD_UDEC_ADDR_CONFIG,
+				adev->gfx.config.gb_addr_config);
+		WREG32_SOC15(UVD, i, mmUVD_UDEC_DB_ADDR_CONFIG,
+				adev->gfx.config.gb_addr_config);
+		WREG32_SOC15(UVD, i, mmUVD_UDEC_DBW_ADDR_CONFIG,
+				adev->gfx.config.gb_addr_config);
+
+		WREG32_SOC15(UVD, i, mmUVD_GP_SCRATCH4, adev->uvd.max_handles);
+	}
 }
 
 static int uvd_v7_0_mmsch_start(struct amdgpu_device *adev,
@@ -669,6 +695,7 @@ static int uvd_v7_0_mmsch_start(struct amdgpu_device *adev,
 	uint64_t addr = table->gpu_addr;
 	struct mmsch_v1_0_init_header *header = (struct mmsch_v1_0_init_header *)table->cpu_addr;
 	uint32_t size;
+	int i;
 
 	size = header->header_size + header->vce_table_size + header->uvd_table_size;
 
@@ -688,11 +715,12 @@ static int uvd_v7_0_mmsch_start(struct amdgpu_device *adev,
 	/* 4, set resp to zero */
 	WREG32_SOC15(VCE, 0, mmVCE_MMSCH_VF_MAILBOX_RESP, 0);
 
-	WDOORBELL32(adev->uvd.ring_enc[0].doorbell_index, 0);
-	adev->wb.wb[adev->uvd.ring_enc[0].wptr_offs] = 0;
-	adev->uvd.ring_enc[0].wptr = 0;
-	adev->uvd.ring_enc[0].wptr_old = 0;
-
+	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		WDOORBELL32(adev->uvd.inst[i].ring_enc[0].doorbell_index, 0);
+		adev->wb.wb[adev->uvd.inst[i].ring_enc[0].wptr_offs] = 0;
+		adev->uvd.inst[i].ring_enc[0].wptr = 0;
+		adev->uvd.inst[i].ring_enc[0].wptr_old = 0;
+	}
 	/* 5, kick off the initialization and wait until VCE_MMSCH_VF_MAILBOX_RESP becomes non-zero */
 	WREG32_SOC15(VCE, 0, mmVCE_MMSCH_VF_MAILBOX_HOST, 0x10000001);
 
@@ -725,6 +753,7 @@ static int uvd_v7_0_sriov_start(struct amdgpu_device *adev)
 	struct mmsch_v1_0_cmd_end end = { {0} };
 	uint32_t *init_table = adev->virt.mm_table.cpu_addr;
 	struct mmsch_v1_0_init_header *header = (struct mmsch_v1_0_init_header *)init_table;
+	uint8_t i = 0;
 
 	direct_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_WRITE;
 	direct_rd_mod_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_READ_MODIFY_WRITE;
@@ -742,120 +771,121 @@ static int uvd_v7_0_sriov_start(struct amdgpu_device *adev)
 
 		init_table += header->uvd_table_offset;
 
-		ring = &adev->uvd.ring;
-		ring->wptr = 0;
-		size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4);
-
-		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_STATUS),
-						   0xFFFFFFFF, 0x00000004);
-		/* mc resume*/
-		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
-			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
-						    lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
-			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
-						    upper_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
-			offset = 0;
-		} else {
-			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
-						    lower_32_bits(adev->uvd.gpu_addr));
-			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
-						    upper_32_bits(adev->uvd.gpu_addr));
-			offset = size;
+		for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+			ring = &adev->uvd.inst[i].ring;
+			ring->wptr = 0;
+			size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4);
+
+			MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_STATUS),
+							   0xFFFFFFFF, 0x00000004);
+			/* mc resume*/
+			if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+							    lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
+				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+							    upper_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
+				offset = 0;
+			} else {
+				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+							    lower_32_bits(adev->uvd.inst[i].gpu_addr));
+				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+							    upper_32_bits(adev->uvd.inst[i].gpu_addr));
+				offset = size;
+			}
+
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET0),
+						    AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE0), size);
+
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
+						    lower_32_bits(adev->uvd.inst[i].gpu_addr + offset));
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
+						    upper_32_bits(adev->uvd.inst[i].gpu_addr + offset));
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET1), (1 << 21));
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE1), AMDGPU_UVD_HEAP_SIZE);
+
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
+						    lower_32_bits(adev->uvd.inst[i].gpu_addr + offset + AMDGPU_UVD_HEAP_SIZE));
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
+						    upper_32_bits(adev->uvd.inst[i].gpu_addr + offset + AMDGPU_UVD_HEAP_SIZE));
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET2), (2 << 21));
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE2),
+						    AMDGPU_UVD_STACK_SIZE + (AMDGPU_UVD_SESSION_SIZE * 40));
+
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_GP_SCRATCH4), adev->uvd.max_handles);
+			/* mc resume end*/
+
+			/* disable clock gating */
+			MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_CGC_CTRL),
+							   ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK, 0);
+
+			/* disable interupt */
+			MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_MASTINT_EN),
+							   ~UVD_MASTINT_EN__VCPU_EN_MASK, 0);
+
+			/* stall UMC and register bus before resetting VCPU */
+			MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_CTRL2),
+							   ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK,
+							   UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+			/* put LMI, VCPU, RBC etc... into reset */
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_SOFT_RESET),
+						    (uint32_t)(UVD_SOFT_RESET__LMI_SOFT_RESET_MASK |
+							       UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK |
+							       UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK |
+							       UVD_SOFT_RESET__RBC_SOFT_RESET_MASK |
+							       UVD_SOFT_RESET__CSM_SOFT_RESET_MASK |
+							       UVD_SOFT_RESET__CXW_SOFT_RESET_MASK |
+							       UVD_SOFT_RESET__TAP_SOFT_RESET_MASK |
+							       UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK));
+
+			/* initialize UVD memory controller */
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_CTRL),
+						    (uint32_t)((0x40 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
+							       UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+							       UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+							       UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
+							       UVD_LMI_CTRL__REQ_MODE_MASK |
+							       0x00100000L));
+
+			/* take all subblocks out of reset, except VCPU */
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_SOFT_RESET),
+						    UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+
+			/* enable VCPU clock */
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CNTL),
+						    UVD_VCPU_CNTL__CLK_EN_MASK);
+
+			/* enable master interrupt */
+			MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_MASTINT_EN),
+							   ~(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK),
+							   (UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK));
+
+			/* clear the bit 4 of UVD_STATUS */
+			MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_STATUS),
+							   ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT), 0);
+
+			/* force RBC into idle state */
+			size = order_base_2(ring->ring_size);
+			tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, size);
+			tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_RBC_RB_CNTL), tmp);
+
+			ring = &adev->uvd.inst[i].ring_enc[0];
+			ring->wptr = 0;
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_RB_BASE_LO), ring->gpu_addr);
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_RB_BASE_HI), upper_32_bits(ring->gpu_addr));
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_RB_SIZE), ring->ring_size / 4);
+
+			/* boot up the VCPU */
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_SOFT_RESET), 0);
+
+			/* enable UMC */
+			MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_CTRL2),
+											   ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK, 0);
+
+			MMSCH_V1_0_INSERT_DIRECT_POLL(SOC15_REG_OFFSET(UVD, i, mmUVD_STATUS), 0x02, 0x02);
 		}
-
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0),
-					    AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_SIZE0), size);
-
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
-					    lower_32_bits(adev->uvd.gpu_addr + offset));
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
-					    upper_32_bits(adev->uvd.gpu_addr + offset));
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1), (1 << 21));
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_SIZE1), AMDGPU_UVD_HEAP_SIZE);
-
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
-					    lower_32_bits(adev->uvd.gpu_addr + offset + AMDGPU_UVD_HEAP_SIZE));
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
-					    upper_32_bits(adev->uvd.gpu_addr + offset + AMDGPU_UVD_HEAP_SIZE));
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2), (2 << 21));
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_SIZE2),
-					    AMDGPU_UVD_STACK_SIZE + (AMDGPU_UVD_SESSION_SIZE * 40));
-
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_GP_SCRATCH4), adev->uvd.max_handles);
-		/* mc resume end*/
-
-		/* disable clock gating */
-		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_CGC_CTRL),
-						   ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK, 0);
-
-		/* disable interupt */
-		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN),
-						   ~UVD_MASTINT_EN__VCPU_EN_MASK, 0);
-
-		/* stall UMC and register bus before resetting VCPU */
-		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2),
-						   ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK,
-						   UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		/* put LMI, VCPU, RBC etc... into reset */
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET),
-					    (uint32_t)(UVD_SOFT_RESET__LMI_SOFT_RESET_MASK |
-						       UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK |
-						       UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK |
-						       UVD_SOFT_RESET__RBC_SOFT_RESET_MASK |
-						       UVD_SOFT_RESET__CSM_SOFT_RESET_MASK |
-						       UVD_SOFT_RESET__CXW_SOFT_RESET_MASK |
-						       UVD_SOFT_RESET__TAP_SOFT_RESET_MASK |
-						       UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK));
-
-		/* initialize UVD memory controller */
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL),
-					    (uint32_t)((0x40 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
-						       UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
-						       UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-						       UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
-						       UVD_LMI_CTRL__REQ_MODE_MASK |
-						       0x00100000L));
-
-		/* take all subblocks out of reset, except VCPU */
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET),
-					    UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
-
-		/* enable VCPU clock */
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CNTL),
-					    UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* enable master interrupt */
-		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN),
-						   ~(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK),
-						   (UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK));
-
-		/* clear the bit 4 of UVD_STATUS */
-		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_STATUS),
-						   ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT), 0);
-
-		/* force RBC into idle state */
-		size = order_base_2(ring->ring_size);
-		tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, size);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_RB_CNTL), tmp);
-
-		ring = &adev->uvd.ring_enc[0];
-		ring->wptr = 0;
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_RB_BASE_LO), ring->gpu_addr);
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_RB_BASE_HI), upper_32_bits(ring->gpu_addr));
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_RB_SIZE), ring->ring_size / 4);
-
-		/* boot up the VCPU */
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), 0);
-
-		/* enable UMC */
-		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2),
-										   ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK, 0);
-
-		MMSCH_V1_0_INSERT_DIRECT_POLL(SOC15_REG_OFFSET(UVD, 0, mmUVD_STATUS), 0x02, 0x02);
-
 		/* add end packet */
 		memcpy((void *)init_table, &end, sizeof(struct mmsch_v1_0_cmd_end));
 		table_size += sizeof(struct mmsch_v1_0_cmd_end) / 4;
@@ -874,15 +904,17 @@ static int uvd_v7_0_sriov_start(struct amdgpu_device *adev)
  */
 static int uvd_v7_0_start(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring = &adev->uvd.ring;
+	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
 	uint32_t lmi_swap_cntl;
 	uint32_t mp_swap_cntl;
-	int i, j, r;
+	int i, j, k, r;
 
-	/* disable DPG */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), 0,
-			~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
+	for (k = 0; k < adev->uvd.num_uvd_inst; ++k) {
+		/* disable DPG */
+		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_POWER_STATUS), 0,
+				~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
+	}
 
 	/* disable byte swapping */
 	lmi_swap_cntl = 0;
@@ -890,157 +922,159 @@ static int uvd_v7_0_start(struct amdgpu_device *adev)
 
 	uvd_v7_0_mc_resume(adev);
 
-	/* disable clock gating */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_CGC_CTRL), 0,
-			~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK);
-
-	/* disable interupt */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN), 0,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-	/* stall UMC and register bus before resetting VCPU */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2),
-			UVD_LMI_CTRL2__STALL_ARB_UMC_MASK,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-	mdelay(1);
-
-	/* put LMI, VCPU, RBC etc... into reset */
-	WREG32_SOC15(UVD, 0, mmUVD_SOFT_RESET,
-		UVD_SOFT_RESET__LMI_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__RBC_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__CSM_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__CXW_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__TAP_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK);
-	mdelay(5);
+	for (k = 0; k < adev->uvd.num_uvd_inst; ++k) {
+		ring = &adev->uvd.inst[k].ring;
+		/* disable clock gating */
+		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_CGC_CTRL), 0,
+				~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK);
 
-	/* initialize UVD memory controller */
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_CTRL,
-		(0x40 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
-		UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
-		UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-		UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
-		UVD_LMI_CTRL__REQ_MODE_MASK |
-		0x00100000L);
+		/* disable interupt */
+		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_MASTINT_EN), 0,
+				~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+		/* stall UMC and register bus before resetting VCPU */
+		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_LMI_CTRL2),
+				UVD_LMI_CTRL2__STALL_ARB_UMC_MASK,
+				~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+		mdelay(1);
+
+		/* put LMI, VCPU, RBC etc... into reset */
+		WREG32_SOC15(UVD, k, mmUVD_SOFT_RESET,
+			UVD_SOFT_RESET__LMI_SOFT_RESET_MASK |
+			UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK |
+			UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK |
+			UVD_SOFT_RESET__RBC_SOFT_RESET_MASK |
+			UVD_SOFT_RESET__CSM_SOFT_RESET_MASK |
+			UVD_SOFT_RESET__CXW_SOFT_RESET_MASK |
+			UVD_SOFT_RESET__TAP_SOFT_RESET_MASK |
+			UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK);
+		mdelay(5);
+
+		/* initialize UVD memory controller */
+		WREG32_SOC15(UVD, k, mmUVD_LMI_CTRL,
+			(0x40 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
+			UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+			UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+			UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
+			UVD_LMI_CTRL__REQ_MODE_MASK |
+			0x00100000L);
 
 #ifdef __BIG_ENDIAN
-	/* swap (8 in 32) RB and IB */
-	lmi_swap_cntl = 0xa;
-	mp_swap_cntl = 0;
+		/* swap (8 in 32) RB and IB */
+		lmi_swap_cntl = 0xa;
+		mp_swap_cntl = 0;
 #endif
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_SWAP_CNTL, lmi_swap_cntl);
-	WREG32_SOC15(UVD, 0, mmUVD_MP_SWAP_CNTL, mp_swap_cntl);
-
-	WREG32_SOC15(UVD, 0, mmUVD_MPC_SET_MUXA0, 0x40c2040);
-	WREG32_SOC15(UVD, 0, mmUVD_MPC_SET_MUXA1, 0x0);
-	WREG32_SOC15(UVD, 0, mmUVD_MPC_SET_MUXB0, 0x40c2040);
-	WREG32_SOC15(UVD, 0, mmUVD_MPC_SET_MUXB1, 0x0);
-	WREG32_SOC15(UVD, 0, mmUVD_MPC_SET_ALU, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_MPC_SET_MUX, 0x88);
-
-	/* take all subblocks out of reset, except VCPU */
-	WREG32_SOC15(UVD, 0, mmUVD_SOFT_RESET,
-			UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
-	mdelay(5);
+		WREG32_SOC15(UVD, k, mmUVD_LMI_SWAP_CNTL, lmi_swap_cntl);
+		WREG32_SOC15(UVD, k, mmUVD_MP_SWAP_CNTL, mp_swap_cntl);
 
-	/* enable VCPU clock */
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CNTL,
-			UVD_VCPU_CNTL__CLK_EN_MASK);
+		WREG32_SOC15(UVD, k, mmUVD_MPC_SET_MUXA0, 0x40c2040);
+		WREG32_SOC15(UVD, k, mmUVD_MPC_SET_MUXA1, 0x0);
+		WREG32_SOC15(UVD, k, mmUVD_MPC_SET_MUXB0, 0x40c2040);
+		WREG32_SOC15(UVD, k, mmUVD_MPC_SET_MUXB1, 0x0);
+		WREG32_SOC15(UVD, k, mmUVD_MPC_SET_ALU, 0);
+		WREG32_SOC15(UVD, k, mmUVD_MPC_SET_MUX, 0x88);
 
-	/* enable UMC */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+		/* take all subblocks out of reset, except VCPU */
+		WREG32_SOC15(UVD, k, mmUVD_SOFT_RESET,
+				UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+		mdelay(5);
 
-	/* boot up the VCPU */
-	WREG32_SOC15(UVD, 0, mmUVD_SOFT_RESET, 0);
-	mdelay(10);
+		/* enable VCPU clock */
+		WREG32_SOC15(UVD, k, mmUVD_VCPU_CNTL,
+				UVD_VCPU_CNTL__CLK_EN_MASK);
 
-	for (i = 0; i < 10; ++i) {
-		uint32_t status;
+		/* enable UMC */
+		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_LMI_CTRL2), 0,
+				~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
 
-		for (j = 0; j < 100; ++j) {
-			status = RREG32_SOC15(UVD, 0, mmUVD_STATUS);
+		/* boot up the VCPU */
+		WREG32_SOC15(UVD, k, mmUVD_SOFT_RESET, 0);
+		mdelay(10);
+
+		for (i = 0; i < 10; ++i) {
+			uint32_t status;
+
+			for (j = 0; j < 100; ++j) {
+				status = RREG32_SOC15(UVD, k, mmUVD_STATUS);
+				if (status & 2)
+					break;
+				mdelay(10);
+			}
+			r = 0;
 			if (status & 2)
 				break;
+
+			DRM_ERROR("UVD(%d) not responding, trying to reset the VCPU!!!\n", k);
+			WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_SOFT_RESET),
+					UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK,
+					~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
 			mdelay(10);
+			WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_SOFT_RESET), 0,
+					~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+			mdelay(10);
+			r = -1;
 		}
-		r = 0;
-		if (status & 2)
-			break;
-
-		DRM_ERROR("UVD not responding, trying to reset the VCPU!!!\n");
-		WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET),
-				UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK,
-				~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
-		mdelay(10);
-		WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), 0,
-				~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
-		mdelay(10);
-		r = -1;
-	}
-
-	if (r) {
-		DRM_ERROR("UVD not responding, giving up!!!\n");
-		return r;
-	}
-	/* enable master interrupt */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN),
-		(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK),
-		~(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK));
-
-	/* clear the bit 4 of UVD_STATUS */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_STATUS), 0,
-			~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
-
-	/* force RBC into idle state */
-	rb_bufsz = order_base_2(ring->ring_size);
-	tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
-	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
-	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
-	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_WPTR_POLL_EN, 0);
-	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
-	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_CNTL, tmp);
-
-	/* set the write pointer delay */
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR_CNTL, 0);
-
-	/* set the wb address */
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR,
-			(upper_32_bits(ring->gpu_addr) >> 2));
-
-	/* programm the RB_BASE for ring buffer */
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
-			lower_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
-			upper_32_bits(ring->gpu_addr));
-
-	/* Initialize the ring buffer's read and write pointers */
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR, 0);
-
-	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR);
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
-			lower_32_bits(ring->wptr));
 
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_RB_CNTL), 0,
-			~UVD_RBC_RB_CNTL__RB_NO_FETCH_MASK);
-
-	ring = &adev->uvd.ring_enc[0];
-	WREG32_SOC15(UVD, 0, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
-	WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
-	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO, ring->gpu_addr);
-	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE, ring->ring_size / 4);
+		if (r) {
+			DRM_ERROR("UVD(%d) not responding, giving up!!!\n", k);
+			return r;
+		}
+		/* enable master interrupt */
+		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_MASTINT_EN),
+			(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK),
+			~(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK));
 
-	ring = &adev->uvd.ring_enc[1];
-	WREG32_SOC15(UVD, 0, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
-	WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
-	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO2, ring->gpu_addr);
-	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
+		/* clear the bit 4 of UVD_STATUS */
+		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_STATUS), 0,
+				~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
+		/* force RBC into idle state */
+		rb_bufsz = order_base_2(ring->ring_size);
+		tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_WPTR_POLL_EN, 0);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
+		WREG32_SOC15(UVD, k, mmUVD_RBC_RB_CNTL, tmp);
+
+		/* set the write pointer delay */
+		WREG32_SOC15(UVD, k, mmUVD_RBC_RB_WPTR_CNTL, 0);
+
+		/* set the wb address */
+		WREG32_SOC15(UVD, k, mmUVD_RBC_RB_RPTR_ADDR,
+				(upper_32_bits(ring->gpu_addr) >> 2));
+
+		/* programm the RB_BASE for ring buffer */
+		WREG32_SOC15(UVD, k, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
+				lower_32_bits(ring->gpu_addr));
+		WREG32_SOC15(UVD, k, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
+				upper_32_bits(ring->gpu_addr));
+
+		/* Initialize the ring buffer's read and write pointers */
+		WREG32_SOC15(UVD, k, mmUVD_RBC_RB_RPTR, 0);
+
+		ring->wptr = RREG32_SOC15(UVD, k, mmUVD_RBC_RB_RPTR);
+		WREG32_SOC15(UVD, k, mmUVD_RBC_RB_WPTR,
+				lower_32_bits(ring->wptr));
+
+		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_RBC_RB_CNTL), 0,
+				~UVD_RBC_RB_CNTL__RB_NO_FETCH_MASK);
+
+		ring = &adev->uvd.inst[k].ring_enc[0];
+		WREG32_SOC15(UVD, k, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+		WREG32_SOC15(UVD, k, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+		WREG32_SOC15(UVD, k, mmUVD_RB_BASE_LO, ring->gpu_addr);
+		WREG32_SOC15(UVD, k, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(UVD, k, mmUVD_RB_SIZE, ring->ring_size / 4);
+
+		ring = &adev->uvd.inst[k].ring_enc[1];
+		WREG32_SOC15(UVD, k, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+		WREG32_SOC15(UVD, k, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+		WREG32_SOC15(UVD, k, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+		WREG32_SOC15(UVD, k, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(UVD, k, mmUVD_RB_SIZE2, ring->ring_size / 4);
+	}
 	return 0;
 }
 
@@ -1053,26 +1087,30 @@ static int uvd_v7_0_start(struct amdgpu_device *adev)
  */
 static void uvd_v7_0_stop(struct amdgpu_device *adev)
 {
-	/* force RBC into idle state */
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_CNTL, 0x11010101);
-
-	/* Stall UMC and register bus before resetting VCPU */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2),
-			UVD_LMI_CTRL2__STALL_ARB_UMC_MASK,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-	mdelay(1);
-
-	/* put VCPU into reset */
-	WREG32_SOC15(UVD, 0, mmUVD_SOFT_RESET,
-			UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
-	mdelay(5);
+	uint8_t i = 0;
 
-	/* disable VCPU clock */
-	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CNTL, 0x0);
+	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		/* force RBC into idle state */
+		WREG32_SOC15(UVD, i, mmUVD_RBC_RB_CNTL, 0x11010101);
 
-	/* Unstall UMC and register bus */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+		/* Stall UMC and register bus before resetting VCPU */
+		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_CTRL2),
+				UVD_LMI_CTRL2__STALL_ARB_UMC_MASK,
+				~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+		mdelay(1);
+
+		/* put VCPU into reset */
+		WREG32_SOC15(UVD, i, mmUVD_SOFT_RESET,
+				UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+		mdelay(5);
+
+		/* disable VCPU clock */
+		WREG32_SOC15(UVD, i, mmUVD_VCPU_CNTL, 0x0);
+
+		/* Unstall UMC and register bus */
+		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_CTRL2), 0,
+				~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+	}
 }
 
 /**
@@ -1091,26 +1129,26 @@ static void uvd_v7_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
 	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
 
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_CONTEXT_ID), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_CONTEXT_ID), 0));
 	amdgpu_ring_write(ring, seq);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, addr & 0xffffffff);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_DATA1), 0));
 	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xff);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_CMD), 0));
 	amdgpu_ring_write(ring, 0);
 
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_DATA1), 0));
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_CMD), 0));
 	amdgpu_ring_write(ring, 2);
 }
 
@@ -1136,6 +1174,16 @@ static void uvd_v7_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
 }
 
 /**
+ * uvd_v7_0_ring_emit_hdp_flush - skip HDP flushing
+ *
+ * @ring: amdgpu_ring pointer
+ */
+static void uvd_v7_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+{
+	/* The firmware doesn't seem to like touching registers at this point. */
+}
+
+/**
  * uvd_v7_0_ring_test_ring - register write test
  *
  * @ring: amdgpu_ring pointer
@@ -1149,30 +1197,30 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring)
 	unsigned i;
 	int r;
 
-	WREG32_SOC15(UVD, 0, mmUVD_CONTEXT_ID, 0xCAFEDEAD);
+	WREG32_SOC15(UVD, ring->me, mmUVD_CONTEXT_ID, 0xCAFEDEAD);
 	r = amdgpu_ring_alloc(ring, 3);
 	if (r) {
-		DRM_ERROR("amdgpu: cp failed to lock ring %d (%d).\n",
-			  ring->idx, r);
+		DRM_ERROR("amdgpu: (%d)cp failed to lock ring %d (%d).\n",
+			  ring->me, ring->idx, r);
 		return r;
 	}
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_CONTEXT_ID), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_CONTEXT_ID), 0));
 	amdgpu_ring_write(ring, 0xDEADBEEF);
 	amdgpu_ring_commit(ring);
 	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32_SOC15(UVD, 0, mmUVD_CONTEXT_ID);
+		tmp = RREG32_SOC15(UVD, ring->me, mmUVD_CONTEXT_ID);
 		if (tmp == 0xDEADBEEF)
 			break;
 		DRM_UDELAY(1);
 	}
 
 	if (i < adev->usec_timeout) {
-		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
-			 ring->idx, i);
+		DRM_DEBUG("(%d)ring test on %d succeeded in %d usecs\n",
+			 ring->me, ring->idx, i);
 	} else {
-		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
-			  ring->idx, tmp);
+		DRM_ERROR("(%d)amdgpu: ring %d test failed (0x%08X)\n",
+			  ring->me, ring->idx, tmp);
 		r = -EINVAL;
 	}
 	return r;
@@ -1193,17 +1241,17 @@ static void uvd_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_VMID), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_LMI_RBC_IB_VMID), 0));
 	amdgpu_ring_write(ring, vmid);
 
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_64BIT_BAR_LOW), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_LMI_RBC_IB_64BIT_BAR_LOW), 0));
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH), 0));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_IB_SIZE), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_RBC_IB_SIZE), 0));
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
@@ -1231,13 +1279,13 @@ static void uvd_v7_0_ring_emit_wreg(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, reg << 2);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_DATA1), 0));
 	amdgpu_ring_write(ring, val);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_CMD), 0));
 	amdgpu_ring_write(ring, 8);
 }
 
@@ -1247,16 +1295,16 @@ static void uvd_v7_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 	struct amdgpu_device *adev = ring->adev;
 
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_DATA0), 0));
 	amdgpu_ring_write(ring, reg << 2);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_DATA1), 0));
 	amdgpu_ring_write(ring, val);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GP_SCRATCH8), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GP_SCRATCH8), 0));
 	amdgpu_ring_write(ring, mask);
 	amdgpu_ring_write(ring,
-		PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD), 0));
+		PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_GPCOM_VCPU_CMD), 0));
 	amdgpu_ring_write(ring, 12);
 }
 
@@ -1277,12 +1325,15 @@ static void uvd_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 static void uvd_v7_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
 {
-	int i;
 	struct amdgpu_device *adev = ring->adev;
+	int i;
 
-	for (i = 0; i < count; i++)
-		amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0));
+	WARN_ON(ring->wptr % 2 || count % 2);
 
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_NO_OP), 0));
+		amdgpu_ring_write(ring, 0);
+	}
 }
 
 static void uvd_v7_0_enc_ring_insert_end(struct amdgpu_ring *ring)
@@ -1349,16 +1400,16 @@ static bool uvd_v7_0_check_soft_reset(void *handle)
 
 	if (REG_GET_FIELD(tmp, SRBM_STATUS, UVD_RQ_PENDING) ||
 	    REG_GET_FIELD(tmp, SRBM_STATUS, UVD_BUSY) ||
-	    (RREG32_SOC15(UVD, 0, mmUVD_STATUS) &
+	    (RREG32_SOC15(UVD, ring->me, mmUVD_STATUS) &
 		    AMDGPU_UVD_STATUS_BUSY_MASK))
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset,
 				SRBM_SOFT_RESET, SOFT_RESET_UVD, 1);
 
 	if (srbm_soft_reset) {
-		adev->uvd.srbm_soft_reset = srbm_soft_reset;
+		adev->uvd.inst[ring->me].srbm_soft_reset = srbm_soft_reset;
 		return true;
 	} else {
-		adev->uvd.srbm_soft_reset = 0;
+		adev->uvd.inst[ring->me].srbm_soft_reset = 0;
 		return false;
 	}
 }
@@ -1367,7 +1418,7 @@ static int uvd_v7_0_pre_soft_reset(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!adev->uvd.srbm_soft_reset)
+	if (!adev->uvd.inst[ring->me].srbm_soft_reset)
 		return 0;
 
 	uvd_v7_0_stop(adev);
@@ -1379,9 +1430,9 @@ static int uvd_v7_0_soft_reset(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	u32 srbm_soft_reset;
 
-	if (!adev->uvd.srbm_soft_reset)
+	if (!adev->uvd.inst[ring->me].srbm_soft_reset)
 		return 0;
-	srbm_soft_reset = adev->uvd.srbm_soft_reset;
+	srbm_soft_reset = adev->uvd.inst[ring->me].srbm_soft_reset;
 
 	if (srbm_soft_reset) {
 		u32 tmp;
@@ -1409,7 +1460,7 @@ static int uvd_v7_0_post_soft_reset(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!adev->uvd.srbm_soft_reset)
+	if (!adev->uvd.inst[ring->me].srbm_soft_reset)
 		return 0;
 
 	mdelay(5);
@@ -1431,17 +1482,32 @@ static int uvd_v7_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
+	uint32_t ip_instance;
+
+	switch (entry->client_id) {
+	case SOC15_IH_CLIENTID_UVD:
+		ip_instance = 0;
+		break;
+	case SOC15_IH_CLIENTID_UVD1:
+		ip_instance = 1;
+		break;
+	default:
+		DRM_ERROR("Unhandled client id: %d\n", entry->client_id);
+		return 0;
+	}
+
 	DRM_DEBUG("IH: UVD TRAP\n");
+
 	switch (entry->src_id) {
 	case 124:
-		amdgpu_fence_process(&adev->uvd.ring);
+		amdgpu_fence_process(&adev->uvd.inst[ip_instance].ring);
 		break;
 	case 119:
-		amdgpu_fence_process(&adev->uvd.ring_enc[0]);
+		amdgpu_fence_process(&adev->uvd.inst[ip_instance].ring_enc[0]);
 		break;
 	case 120:
 		if (!amdgpu_sriov_vf(adev))
-			amdgpu_fence_process(&adev->uvd.ring_enc[1]);
+			amdgpu_fence_process(&adev->uvd.inst[ip_instance].ring_enc[1]);
 		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
@@ -1457,9 +1523,9 @@ static void uvd_v7_0_set_sw_clock_gating(struct amdgpu_device *adev)
 {
 	uint32_t data, data1, data2, suvd_flags;
 
-	data = RREG32_SOC15(UVD, 0, mmUVD_CGC_CTRL);
-	data1 = RREG32_SOC15(UVD, 0, mmUVD_SUVD_CGC_GATE);
-	data2 = RREG32_SOC15(UVD, 0, mmUVD_SUVD_CGC_CTRL);
+	data = RREG32_SOC15(UVD, ring->me, mmUVD_CGC_CTRL);
+	data1 = RREG32_SOC15(UVD, ring->me, mmUVD_SUVD_CGC_GATE);
+	data2 = RREG32_SOC15(UVD, ring->me, mmUVD_SUVD_CGC_CTRL);
 
 	data &= ~(UVD_CGC_CTRL__CLK_OFF_DELAY_MASK |
 		  UVD_CGC_CTRL__CLK_GATE_DLY_TIMER_MASK);
@@ -1503,18 +1569,18 @@ static void uvd_v7_0_set_sw_clock_gating(struct amdgpu_device *adev)
 			UVD_SUVD_CGC_CTRL__SDB_MODE_MASK);
 	data1 |= suvd_flags;
 
-	WREG32_SOC15(UVD, 0, mmUVD_CGC_CTRL, data);
-	WREG32_SOC15(UVD, 0, mmUVD_CGC_GATE, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_SUVD_CGC_GATE, data1);
-	WREG32_SOC15(UVD, 0, mmUVD_SUVD_CGC_CTRL, data2);
+	WREG32_SOC15(UVD, ring->me, mmUVD_CGC_CTRL, data);
+	WREG32_SOC15(UVD, ring->me, mmUVD_CGC_GATE, 0);
+	WREG32_SOC15(UVD, ring->me, mmUVD_SUVD_CGC_GATE, data1);
+	WREG32_SOC15(UVD, ring->me, mmUVD_SUVD_CGC_CTRL, data2);
 }
 
 static void uvd_v7_0_set_hw_clock_gating(struct amdgpu_device *adev)
 {
 	uint32_t data, data1, cgc_flags, suvd_flags;
 
-	data = RREG32_SOC15(UVD, 0, mmUVD_CGC_GATE);
-	data1 = RREG32_SOC15(UVD, 0, mmUVD_SUVD_CGC_GATE);
+	data = RREG32_SOC15(UVD, ring->me, mmUVD_CGC_GATE);
+	data1 = RREG32_SOC15(UVD, ring->me, mmUVD_SUVD_CGC_GATE);
 
 	cgc_flags = UVD_CGC_GATE__SYS_MASK |
 		UVD_CGC_GATE__UDEC_MASK |
@@ -1546,8 +1612,8 @@ static void uvd_v7_0_set_hw_clock_gating(struct amdgpu_device *adev)
 	data |= cgc_flags;
 	data1 |= suvd_flags;
 
-	WREG32_SOC15(UVD, 0, mmUVD_CGC_GATE, data);
-	WREG32_SOC15(UVD, 0, mmUVD_SUVD_CGC_GATE, data1);
+	WREG32_SOC15(UVD, ring->me, mmUVD_CGC_GATE, data);
+	WREG32_SOC15(UVD, ring->me, mmUVD_SUVD_CGC_GATE, data1);
 }
 
 static void uvd_v7_0_set_bypass_mode(struct amdgpu_device *adev, bool enable)
@@ -1606,7 +1672,7 @@ static int uvd_v7_0_set_powergating_state(void *handle,
 	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
 		return 0;
 
-	WREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS, UVD_POWER_STATUS__UVD_PG_EN_MASK);
+	WREG32_SOC15(UVD, ring->me, mmUVD_POWER_STATUS, UVD_POWER_STATUS__UVD_PG_EN_MASK);
 
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v7_0_stop(adev);
@@ -1647,14 +1713,13 @@ const struct amd_ip_funcs uvd_v7_0_ip_funcs = {
 static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_UVD,
 	.align_mask = 0xf,
-	.nop = PACKET0(0x81ff, 0),
 	.support_64bit_ptrs = false,
 	.vmhub = AMDGPU_MMHUB,
 	.get_rptr = uvd_v7_0_ring_get_rptr,
 	.get_wptr = uvd_v7_0_ring_get_wptr,
 	.set_wptr = uvd_v7_0_ring_set_wptr,
 	.emit_frame_size =
-		6 + 6 + /* hdp flush / invalidate */
+		6 + /* hdp invalidate */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
 		8 + /* uvd_v7_0_ring_emit_vm_flush */
@@ -1663,6 +1728,7 @@ static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
 	.emit_ib = uvd_v7_0_ring_emit_ib,
 	.emit_fence = uvd_v7_0_ring_emit_fence,
 	.emit_vm_flush = uvd_v7_0_ring_emit_vm_flush,
+	.emit_hdp_flush = uvd_v7_0_ring_emit_hdp_flush,
 	.test_ring = uvd_v7_0_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
 	.insert_nop = uvd_v7_0_ring_insert_nop,
@@ -1671,6 +1737,7 @@ static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
 	.end_use = amdgpu_uvd_ring_end_use,
 	.emit_wreg = uvd_v7_0_ring_emit_wreg,
 	.emit_reg_wait = uvd_v7_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
 static const struct amdgpu_ring_funcs uvd_v7_0_enc_ring_vm_funcs = {
@@ -1702,22 +1769,32 @@ static const struct amdgpu_ring_funcs uvd_v7_0_enc_ring_vm_funcs = {
 	.end_use = amdgpu_uvd_ring_end_use,
 	.emit_wreg = uvd_v7_0_enc_ring_emit_wreg,
 	.emit_reg_wait = uvd_v7_0_enc_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
 static void uvd_v7_0_set_ring_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.ring.funcs = &uvd_v7_0_ring_vm_funcs;
-	DRM_INFO("UVD is enabled in VM mode\n");
+	int i;
+
+	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		adev->uvd.inst[i].ring.funcs = &uvd_v7_0_ring_vm_funcs;
+		adev->uvd.inst[i].ring.me = i;
+		DRM_INFO("UVD(%d) is enabled in VM mode\n", i);
+	}
 }
 
 static void uvd_v7_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 {
-	int i;
+	int i, j;
 
-	for (i = 0; i < adev->uvd.num_enc_rings; ++i)
-		adev->uvd.ring_enc[i].funcs = &uvd_v7_0_enc_ring_vm_funcs;
+	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
+			adev->uvd.inst[j].ring_enc[i].funcs = &uvd_v7_0_enc_ring_vm_funcs;
+			adev->uvd.inst[j].ring_enc[i].me = j;
+		}
 
-	DRM_INFO("UVD ENC is enabled in VM mode\n");
+		DRM_INFO("UVD(%d) ENC is enabled in VM mode\n", j);
+	}
 }
 
 static const struct amdgpu_irq_src_funcs uvd_v7_0_irq_funcs = {
@@ -1727,8 +1804,12 @@ static const struct amdgpu_irq_src_funcs uvd_v7_0_irq_funcs = {
 
 static void uvd_v7_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.irq.num_types = adev->uvd.num_enc_rings + 1;
-	adev->uvd.irq.funcs = &uvd_v7_0_irq_funcs;
+	int i;
+
+	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		adev->uvd.inst[i].irq.num_types = adev->uvd.num_enc_rings + 1;
+		adev->uvd.inst[i].irq.funcs = &uvd_v7_0_irq_funcs;
+	}
 }
 
 const struct amdgpu_ip_block_version uvd_v7_0_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 428d1928e44e..0999c843f623 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -388,7 +388,8 @@ static unsigned vce_v3_0_get_harvest_config(struct amdgpu_device *adev)
 	default:
 		if ((adev->asic_type == CHIP_POLARIS10) ||
 		    (adev->asic_type == CHIP_POLARIS11) ||
-		    (adev->asic_type == CHIP_POLARIS12))
+		    (adev->asic_type == CHIP_POLARIS12) ||
+		    (adev->asic_type == CHIP_VEGAM))
 			return AMDGPU_VCE_HARVEST_VCE1;
 
 		return 0;
@@ -467,8 +468,8 @@ static int vce_v3_0_hw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	vce_v3_0_override_vce_clock_gating(adev, true);
-	if (!(adev->flags & AMD_IS_APU))
-		amdgpu_asic_set_vce_clocks(adev, 10000, 10000);
+
+	amdgpu_asic_set_vce_clocks(adev, 10000, 10000);
 
 	for (i = 0; i < adev->vce.num_rings; i++)
 		adev->vce.ring[i].ready = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index 73fd48d6c756..8fd1b742985a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -1081,6 +1081,7 @@ static const struct amdgpu_ring_funcs vce_v4_0_ring_vm_funcs = {
 	.end_use = amdgpu_vce_ring_end_use,
 	.emit_wreg = vce_v4_0_emit_wreg,
 	.emit_reg_wait = vce_v4_0_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
 static void vce_v4_0_set_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 8c132673bc79..110b294ebed3 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -35,7 +35,6 @@
 #include "mmhub/mmhub_9_1_offset.h"
 #include "mmhub/mmhub_9_1_sh_mask.h"
 
-static int vcn_v1_0_start(struct amdgpu_device *adev);
 static int vcn_v1_0_stop(struct amdgpu_device *adev);
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
@@ -146,10 +145,6 @@ static int vcn_v1_0_hw_init(void *handle)
 	struct amdgpu_ring *ring = &adev->vcn.ring_dec;
 	int i, r;
 
-	r = vcn_v1_0_start(adev);
-	if (r)
-		goto done;
-
 	ring->ready = true;
 	r = amdgpu_ring_test_ring(ring);
 	if (r) {
@@ -185,11 +180,9 @@ static int vcn_v1_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct amdgpu_ring *ring = &adev->vcn.ring_dec;
-	int r;
 
-	r = vcn_v1_0_stop(adev);
-	if (r)
-		return r;
+	if (RREG32_SOC15(VCN, 0, mmUVD_STATUS))
+		vcn_v1_0_stop(adev);
 
 	ring->ready = false;
 
@@ -288,14 +281,14 @@ static void vcn_v1_0_mc_resume(struct amdgpu_device *adev)
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev, bool sw)
+static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev)
 {
 	uint32_t data;
 
 	/* JPEG disable CGC */
 	data = RREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL);
 
-	if (sw)
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
 		data |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
 	else
 		data &= ~JPEG_CGC_CTRL__DYN_CLOCK_MODE_MASK;
@@ -310,7 +303,7 @@ static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev, bool sw)
 
 	/* UVD disable CGC */
 	data = RREG32_SOC15(VCN, 0, mmUVD_CGC_CTRL);
-	if (sw)
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
 		data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
 	else
 		data &= ~ UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
@@ -415,13 +408,13 @@ static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev, bool sw)
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev, bool sw)
+static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev)
 {
 	uint32_t data = 0;
 
 	/* enable JPEG CGC */
 	data = RREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL);
-	if (sw)
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
 		data |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
 	else
 		data |= 0 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
@@ -435,7 +428,7 @@ static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev, bool sw)
 
 	/* enable UVD CGC */
 	data = RREG32_SOC15(VCN, 0, mmUVD_CGC_CTRL);
-	if (sw)
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
 		data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
 	else
 		data |= 0 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
@@ -480,6 +473,94 @@ static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev, bool sw)
 	WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data);
 }
 
+static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev)
+{
+	uint32_t data = 0;
+	int ret;
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
+		data = (1 << UVD_PGFSM_CONFIG__UVDM_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDU_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDF_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDC_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDB_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDIL_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDIR_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDTD_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDTE_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDE_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDW_PWR_CONFIG__SHIFT);
+
+		WREG32_SOC15(VCN, 0, mmUVD_PGFSM_CONFIG, data);
+		SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, UVD_PGFSM_STATUS__UVDM_UVDU_PWR_ON, 0xFFFFFF, ret);
+	} else {
+		data = (1 << UVD_PGFSM_CONFIG__UVDM_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDU_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDF_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDC_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDB_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDIL_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDIR_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDTD_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDTE_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDE_PWR_CONFIG__SHIFT
+			| 1 << UVD_PGFSM_CONFIG__UVDW_PWR_CONFIG__SHIFT);
+		WREG32_SOC15(VCN, 0, mmUVD_PGFSM_CONFIG, data);
+		SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, 0,  0xFFFFFFFF, ret);
+	}
+
+	/* polling UVD_PGFSM_STATUS to confirm UVDM_PWR_STATUS , UVDU_PWR_STATUS are 0 (power on) */
+
+	data = RREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS);
+	data &= ~0x103;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN)
+		data |= UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON | UVD_POWER_STATUS__UVD_PG_EN_MASK;
+
+	WREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS, data);
+}
+
+static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev)
+{
+	uint32_t data = 0;
+	int ret;
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
+		/* Before power off, this indicator has to be turned on */
+		data = RREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS);
+		data &= ~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK;
+		data |= UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF;
+		WREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS, data);
+
+
+		data = (2 << UVD_PGFSM_CONFIG__UVDM_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDU_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDF_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDC_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDB_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDIL_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDIR_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDTD_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDTE_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDE_PWR_CONFIG__SHIFT
+			| 2 << UVD_PGFSM_CONFIG__UVDW_PWR_CONFIG__SHIFT);
+
+		WREG32_SOC15(VCN, 0, mmUVD_PGFSM_CONFIG, data);
+
+		data = (2 << UVD_PGFSM_STATUS__UVDM_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDU_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDF_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDC_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDB_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDIL_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDIR_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDTD_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDTE_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDE_PWR_STATUS__SHIFT
+			| 2 << UVD_PGFSM_STATUS__UVDW_PWR_STATUS__SHIFT);
+		SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, data, 0xFFFFFFFF, ret);
+	}
+}
+
 /**
  * vcn_v1_0_start - start VCN block
  *
@@ -499,8 +580,9 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
 
 	vcn_v1_0_mc_resume(adev);
 
+	vcn_1_0_disable_static_power_gating(adev);
 	/* disable clock gating */
-	vcn_v1_0_disable_clock_gating(adev, true);
+	vcn_v1_0_disable_clock_gating(adev);
 
 	/* disable interupt */
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN), 0,
@@ -680,16 +762,45 @@ static int vcn_v1_0_stop(struct amdgpu_device *adev)
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2), 0,
 			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
 
-	/* enable clock gating */
-	vcn_v1_0_enable_clock_gating(adev, true);
+	WREG32_SOC15(VCN, 0, mmUVD_STATUS, 0);
 
+	vcn_v1_0_enable_clock_gating(adev);
+	vcn_1_0_enable_static_power_gating(adev);
 	return 0;
 }
 
+bool vcn_v1_0_is_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == 0x2);
+}
+
+int vcn_v1_0_wait_for_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int ret = 0;
+
+	SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_STATUS, 0x2, 0x2, ret);
+
+	return ret;
+}
+
 static int vcn_v1_0_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
-	/* needed for driver unload*/
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+
+	if (enable) {
+		/* wait for STATUS to clear */
+		if (vcn_v1_0_is_idle(handle))
+			return -EBUSY;
+		vcn_v1_0_enable_clock_gating(adev);
+	} else {
+		/* disable HW gating and enable Sw gating */
+		vcn_v1_0_disable_clock_gating(adev);
+	}
 	return 0;
 }
 
@@ -1048,16 +1159,36 @@ static int vcn_v1_0_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
-static void vcn_v1_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+static void vcn_v1_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
 {
-	int i;
 	struct amdgpu_device *adev = ring->adev;
+	int i;
 
-	for (i = 0; i < count; i++)
-		amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0));
+	WARN_ON(ring->wptr % 2 || count % 2);
 
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0));
+		amdgpu_ring_write(ring, 0);
+	}
 }
 
+static int vcn_v1_0_set_powergating_state(void *handle,
+					  enum amd_powergating_state state)
+{
+	/* This doesn't actually powergate the VCN block.
+	 * That's done in the dpm code via the SMC.  This
+	 * just re-inits the block as necessary.  The actual
+	 * gating still happens in the dpm code.  We should
+	 * revisit this when there is a cleaner line between
+	 * the smc and the hw blocks
+	 */
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (state == AMD_PG_STATE_GATE)
+		return vcn_v1_0_stop(adev);
+	else
+		return vcn_v1_0_start(adev);
+}
 
 static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 	.name = "vcn_v1_0",
@@ -1069,20 +1200,19 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 	.hw_fini = vcn_v1_0_hw_fini,
 	.suspend = vcn_v1_0_suspend,
 	.resume = vcn_v1_0_resume,
-	.is_idle = NULL /* vcn_v1_0_is_idle */,
-	.wait_for_idle = NULL /* vcn_v1_0_wait_for_idle */,
+	.is_idle = vcn_v1_0_is_idle,
+	.wait_for_idle = vcn_v1_0_wait_for_idle,
 	.check_soft_reset = NULL /* vcn_v1_0_check_soft_reset */,
 	.pre_soft_reset = NULL /* vcn_v1_0_pre_soft_reset */,
 	.soft_reset = NULL /* vcn_v1_0_soft_reset */,
 	.post_soft_reset = NULL /* vcn_v1_0_post_soft_reset */,
 	.set_clockgating_state = vcn_v1_0_set_clockgating_state,
-	.set_powergating_state = NULL /* vcn_v1_0_set_powergating_state */,
+	.set_powergating_state = vcn_v1_0_set_powergating_state,
 };
 
 static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_DEC,
 	.align_mask = 0xf,
-	.nop = PACKET0(0x81ff, 0),
 	.support_64bit_ptrs = false,
 	.vmhub = AMDGPU_MMHUB,
 	.get_rptr = vcn_v1_0_dec_ring_get_rptr,
@@ -1101,7 +1231,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.emit_vm_flush = vcn_v1_0_dec_ring_emit_vm_flush,
 	.test_ring = amdgpu_vcn_dec_ring_test_ring,
 	.test_ib = amdgpu_vcn_dec_ring_test_ib,
-	.insert_nop = vcn_v1_0_ring_insert_nop,
+	.insert_nop = vcn_v1_0_dec_ring_insert_nop,
 	.insert_start = vcn_v1_0_dec_ring_insert_start,
 	.insert_end = vcn_v1_0_dec_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
@@ -1109,6 +1239,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.end_use = amdgpu_vcn_ring_end_use,
 	.emit_wreg = vcn_v1_0_dec_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_dec_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
 static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
@@ -1139,6 +1270,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
 	.end_use = amdgpu_vcn_ring_end_use,
 	.emit_wreg = vcn_v1_0_enc_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_enc_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c
new file mode 100644
index 000000000000..52778de93ab0
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c
@@ -0,0 +1,53 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "soc15.h"
+
+#include "soc15_common.h"
+#include "soc15_hw_ip.h"
+#include "vega20_ip_offset.h"
+
+int vega20_reg_base_init(struct amdgpu_device *adev)
+{
+	/* HW has more IP blocks,  only initialized the blocke beend by our driver  */
+	uint32_t i;
+	for (i = 0 ; i < MAX_INSTANCE ; ++i) {
+		adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i]));
+		adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i]));
+		adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i]));
+		adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i]));
+		adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i]));
+		adev->reg_offset[UVD_HWIP][i] = (uint32_t *)(&(UVD_BASE.instance[i]));
+		adev->reg_offset[VCE_HWIP][i] = (uint32_t *)(&(VCE_BASE.instance[i]));
+		adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i]));
+		adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DCE_BASE.instance[i]));
+		adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i]));
+		adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(SDMA0_BASE.instance[i]));
+		adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(SDMA1_BASE.instance[i]));
+		adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i]));
+	}
+	return 0;
+}
+
+
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 126f1276d347..4ac1288ab7df 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -305,9 +305,10 @@ static void vi_init_golden_registers(struct amdgpu_device *adev)
 							stoney_mgcg_cgcg_init,
 							ARRAY_SIZE(stoney_mgcg_cgcg_init));
 		break;
-	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 	default:
 		break;
 	}
@@ -728,33 +729,59 @@ static int vi_set_uvd_clock(struct amdgpu_device *adev, u32 clock,
 		return r;
 
 	tmp = RREG32_SMC(cntl_reg);
-	tmp &= ~(CG_DCLK_CNTL__DCLK_DIR_CNTL_EN_MASK |
-		CG_DCLK_CNTL__DCLK_DIVIDER_MASK);
+
+	if (adev->flags & AMD_IS_APU)
+		tmp &= ~CG_DCLK_CNTL__DCLK_DIVIDER_MASK;
+	else
+		tmp &= ~(CG_DCLK_CNTL__DCLK_DIR_CNTL_EN_MASK |
+				CG_DCLK_CNTL__DCLK_DIVIDER_MASK);
 	tmp |= dividers.post_divider;
 	WREG32_SMC(cntl_reg, tmp);
 
 	for (i = 0; i < 100; i++) {
-		if (RREG32_SMC(status_reg) & CG_DCLK_STATUS__DCLK_STATUS_MASK)
-			break;
+		tmp = RREG32_SMC(status_reg);
+		if (adev->flags & AMD_IS_APU) {
+			if (tmp & 0x10000)
+				break;
+		} else {
+			if (tmp & CG_DCLK_STATUS__DCLK_STATUS_MASK)
+				break;
+		}
 		mdelay(10);
 	}
 	if (i == 100)
 		return -ETIMEDOUT;
-
 	return 0;
 }
 
+#define ixGNB_CLK1_DFS_CNTL 0xD82200F0
+#define ixGNB_CLK1_STATUS   0xD822010C
+#define ixGNB_CLK2_DFS_CNTL 0xD8220110
+#define ixGNB_CLK2_STATUS   0xD822012C
+#define ixGNB_CLK3_DFS_CNTL 0xD8220130
+#define ixGNB_CLK3_STATUS   0xD822014C
+
 static int vi_set_uvd_clocks(struct amdgpu_device *adev, u32 vclk, u32 dclk)
 {
 	int r;
 
-	r = vi_set_uvd_clock(adev, vclk, ixCG_VCLK_CNTL, ixCG_VCLK_STATUS);
-	if (r)
-		return r;
+	if (adev->flags & AMD_IS_APU) {
+		r = vi_set_uvd_clock(adev, vclk, ixGNB_CLK2_DFS_CNTL, ixGNB_CLK2_STATUS);
+		if (r)
+			return r;
 
-	r = vi_set_uvd_clock(adev, dclk, ixCG_DCLK_CNTL, ixCG_DCLK_STATUS);
-	if (r)
-		return r;
+		r = vi_set_uvd_clock(adev, dclk, ixGNB_CLK1_DFS_CNTL, ixGNB_CLK1_STATUS);
+		if (r)
+			return r;
+	} else {
+		r = vi_set_uvd_clock(adev, vclk, ixCG_VCLK_CNTL, ixCG_VCLK_STATUS);
+		if (r)
+			return r;
+
+		r = vi_set_uvd_clock(adev, dclk, ixCG_DCLK_CNTL, ixCG_DCLK_STATUS);
+		if (r)
+			return r;
+	}
 
 	return 0;
 }
@@ -764,6 +791,22 @@ static int vi_set_vce_clocks(struct amdgpu_device *adev, u32 evclk, u32 ecclk)
 	int r, i;
 	struct atom_clock_dividers dividers;
 	u32 tmp;
+	u32 reg_ctrl;
+	u32 reg_status;
+	u32 status_mask;
+	u32 reg_mask;
+
+	if (adev->flags & AMD_IS_APU) {
+		reg_ctrl = ixGNB_CLK3_DFS_CNTL;
+		reg_status = ixGNB_CLK3_STATUS;
+		status_mask = 0x00010000;
+		reg_mask = CG_ECLK_CNTL__ECLK_DIVIDER_MASK;
+	} else {
+		reg_ctrl = ixCG_ECLK_CNTL;
+		reg_status = ixCG_ECLK_STATUS;
+		status_mask = CG_ECLK_STATUS__ECLK_STATUS_MASK;
+		reg_mask = CG_ECLK_CNTL__ECLK_DIR_CNTL_EN_MASK | CG_ECLK_CNTL__ECLK_DIVIDER_MASK;
+	}
 
 	r = amdgpu_atombios_get_clock_dividers(adev,
 					       COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK,
@@ -772,24 +815,25 @@ static int vi_set_vce_clocks(struct amdgpu_device *adev, u32 evclk, u32 ecclk)
 		return r;
 
 	for (i = 0; i < 100; i++) {
-		if (RREG32_SMC(ixCG_ECLK_STATUS) & CG_ECLK_STATUS__ECLK_STATUS_MASK)
+		if (RREG32_SMC(reg_status) & status_mask)
 			break;
 		mdelay(10);
 	}
+
 	if (i == 100)
 		return -ETIMEDOUT;
 
-	tmp = RREG32_SMC(ixCG_ECLK_CNTL);
-	tmp &= ~(CG_ECLK_CNTL__ECLK_DIR_CNTL_EN_MASK |
-		CG_ECLK_CNTL__ECLK_DIVIDER_MASK);
+	tmp = RREG32_SMC(reg_ctrl);
+	tmp &= ~reg_mask;
 	tmp |= dividers.post_divider;
-	WREG32_SMC(ixCG_ECLK_CNTL, tmp);
+	WREG32_SMC(reg_ctrl, tmp);
 
 	for (i = 0; i < 100; i++) {
-		if (RREG32_SMC(ixCG_ECLK_STATUS) & CG_ECLK_STATUS__ECLK_STATUS_MASK)
+		if (RREG32_SMC(reg_status) & status_mask)
 			break;
 		mdelay(10);
 	}
+
 	if (i == 100)
 		return -ETIMEDOUT;
 
@@ -876,6 +920,27 @@ static void vi_invalidate_hdp(struct amdgpu_device *adev,
 	}
 }
 
+static bool vi_need_full_reset(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_CARRIZO:
+	case CHIP_STONEY:
+		/* CZ has hang issues with full reset at the moment */
+		return false;
+	case CHIP_FIJI:
+	case CHIP_TONGA:
+		/* XXX: soft reset should work on fiji and tonga */
+		return true;
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+	case CHIP_TOPAZ:
+	default:
+		/* change this when we support soft reset */
+		return true;
+	}
+}
+
 static const struct amdgpu_asic_funcs vi_asic_funcs =
 {
 	.read_disabled_bios = &vi_read_disabled_bios,
@@ -889,6 +954,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.get_config_memsize = &vi_get_config_memsize,
 	.flush_hdp = &vi_flush_hdp,
 	.invalidate_hdp = &vi_invalidate_hdp,
+	.need_full_reset = &vi_need_full_reset,
 };
 
 #define CZ_REV_BRISTOL(rev)	 \
@@ -1031,6 +1097,30 @@ static int vi_common_early_init(void *handle)
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x64;
 		break;
+	case CHIP_VEGAM:
+		adev->cg_flags = 0;
+			/*AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_RLC_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_3D_CGCG |
+			AMD_CG_SUPPORT_GFX_3D_CGLS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_MGCG |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_ROM_MGCG |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_DRM_LS |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_VCE_MGCG;*/
+		adev->pg_flags = 0;
+		adev->external_rev_id = adev->rev_id + 0x6E;
+		break;
 	case CHIP_CARRIZO:
 		adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG |
 			AMD_CG_SUPPORT_GFX_MGCG |
@@ -1422,6 +1512,7 @@ static int vi_common_set_clockgating_state(void *handle,
 	case CHIP_POLARIS10:
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 		vi_common_set_clockgating_state_by_smu(adev, state);
 	default:
 		break;
@@ -1551,9 +1642,10 @@ int vi_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &vce_v3_0_ip_block);
 		}
 		break;
-	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 		amdgpu_device_ip_block_add(adev, &vi_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v8_1_ip_block);
 		amdgpu_device_ip_block_add(adev, &tonga_ih_ip_block);
diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig
index ed2f06c9f346..3858820a0055 100644
--- a/drivers/gpu/drm/amd/amdkfd/Kconfig
+++ b/drivers/gpu/drm/amd/amdkfd/Kconfig
@@ -6,5 +6,6 @@ config HSA_AMD
 	tristate "HSA kernel driver for AMD GPU devices"
 	depends on DRM_AMDGPU && X86_64
 	imply AMD_IOMMU_V2
+	select MMU_NOTIFIER
 	help
 	  Enable this if you want to use HSA features on AMD GPU devices.
diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile
index 0d0242240c47..ffd096fffc1c 100644
--- a/drivers/gpu/drm/amd/amdkfd/Makefile
+++ b/drivers/gpu/drm/amd/amdkfd/Makefile
@@ -30,12 +30,14 @@ amdkfd-y	:= kfd_module.o kfd_device.o kfd_chardev.o kfd_topology.o \
 		kfd_pasid.o kfd_doorbell.o kfd_flat_memory.o \
 		kfd_process.o kfd_queue.o kfd_mqd_manager.o \
 		kfd_mqd_manager_cik.o kfd_mqd_manager_vi.o \
+		kfd_mqd_manager_v9.o \
 		kfd_kernel_queue.o kfd_kernel_queue_cik.o \
-		kfd_kernel_queue_vi.o kfd_packet_manager.o \
-		kfd_process_queue_manager.o kfd_device_queue_manager.o \
-		kfd_device_queue_manager_cik.o kfd_device_queue_manager_vi.o \
+		kfd_kernel_queue_vi.o kfd_kernel_queue_v9.o \
+		kfd_packet_manager.o kfd_process_queue_manager.o \
+		kfd_device_queue_manager.o kfd_device_queue_manager_cik.o \
+		kfd_device_queue_manager_vi.o kfd_device_queue_manager_v9.o \
 		kfd_interrupt.o kfd_events.o cik_event_interrupt.o \
-		kfd_dbgdev.o kfd_dbgmgr.o kfd_crat.o
+		kfd_int_process_v9.o kfd_dbgdev.o kfd_dbgmgr.o kfd_crat.o
 
 ifneq ($(CONFIG_AMD_IOMMU_V2),)
 amdkfd-y += kfd_iommu.o
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 3d5ccb3755d4..49df6c791cfc 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -27,18 +27,28 @@
 static bool cik_event_interrupt_isr(struct kfd_dev *dev,
 					const uint32_t *ih_ring_entry)
 {
-	unsigned int pasid;
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
+	unsigned int vmid, pasid;
+
+	/* Only handle interrupts from KFD VMIDs */
+	vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
+	if (vmid < dev->vm_info.first_vmid_kfd ||
+	    vmid > dev->vm_info.last_vmid_kfd)
+		return 0;
 
+	/* If there is no valid PASID, it's likely a firmware bug */
 	pasid = (ihre->ring_id & 0xffff0000) >> 16;
+	if (WARN_ONCE(pasid == 0, "FW bug: No PASID in KFD interrupt"))
+		return 0;
 
-	/* Do not process in ISR, just request it to be forwarded to WQ. */
-	return (pasid != 0) &&
-		(ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE ||
+	/* Interrupt types we care about: various signals and faults.
+	 * They will be forwarded to a work queue (see below).
+	 */
+	return ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE ||
 		ihre->source_id == CIK_INTSRC_SDMA_TRAP ||
 		ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG ||
-		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE);
+		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE;
 }
 
 static void cik_event_interrupt_wq(struct kfd_dev *dev,
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_regs.h b/drivers/gpu/drm/amd/amdkfd/cik_regs.h
index 48769d12dd7b..37ce6dd65391 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_regs.h
+++ b/drivers/gpu/drm/amd/amdkfd/cik_regs.h
@@ -33,7 +33,8 @@
 #define	APE1_MTYPE(x)					((x) << 7)
 
 /* valid for both DEFAULT_MTYPE and APE1_MTYPE */
-#define	MTYPE_CACHED					0
+#define	MTYPE_CACHED_NV					0
+#define	MTYPE_CACHED					1
 #define	MTYPE_NONCACHED					3
 
 #define	DEFAULT_CP_HQD_PERSISTENT_STATE			(0x33U << 8)
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
new file mode 100644
index 000000000000..f68aef02fc1f
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -0,0 +1,560 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+static const uint32_t cwsr_trap_gfx8_hex[] = {
+	0xbf820001, 0xbf820125,
+	0xb8f4f802, 0x89748674,
+	0xb8f5f803, 0x8675ff75,
+	0x00000400, 0xbf850011,
+	0xc00a1e37, 0x00000000,
+	0xbf8c007f, 0x87777978,
+	0xbf840002, 0xb974f802,
+	0xbe801d78, 0xb8f5f803,
+	0x8675ff75, 0x000001ff,
+	0xbf850002, 0x80708470,
+	0x82718071, 0x8671ff71,
+	0x0000ffff, 0xb974f802,
+	0xbe801f70, 0xb8f5f803,
+	0x8675ff75, 0x00000100,
+	0xbf840006, 0xbefa0080,
+	0xb97a0203, 0x8671ff71,
+	0x0000ffff, 0x80f08870,
+	0x82f18071, 0xbefa0080,
+	0xb97a0283, 0xbef60068,
+	0xbef70069, 0xb8fa1c07,
+	0x8e7a9c7a, 0x87717a71,
+	0xb8fa03c7, 0x8e7a9b7a,
+	0x87717a71, 0xb8faf807,
+	0x867aff7a, 0x00007fff,
+	0xb97af807, 0xbef2007e,
+	0xbef3007f, 0xbefe0180,
+	0xbf900004, 0x877a8474,
+	0xb97af802, 0xbf8e0002,
+	0xbf88fffe, 0xbef8007e,
+	0x8679ff7f, 0x0000ffff,
+	0x8779ff79, 0x00040000,
+	0xbefa0080, 0xbefb00ff,
+	0x00807fac, 0x867aff7f,
+	0x08000000, 0x8f7a837a,
+	0x877b7a7b, 0x867aff7f,
+	0x70000000, 0x8f7a817a,
+	0x877b7a7b, 0xbeef007c,
+	0xbeee0080, 0xb8ee2a05,
+	0x806e816e, 0x8e6e8a6e,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x806e7a6e,
+	0xbefa0084, 0xbefa00ff,
+	0x01000000, 0xbefe007c,
+	0xbefc006e, 0xc0611bfc,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611c3c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611c7c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611cbc,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611cfc,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611d3c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xb8f5f803,
+	0xbefe007c, 0xbefc006e,
+	0xc0611d7c, 0x0000007c,
+	0x806e846e, 0xbefc007e,
+	0xbefe007c, 0xbefc006e,
+	0xc0611dbc, 0x0000007c,
+	0x806e846e, 0xbefc007e,
+	0xbefe007c, 0xbefc006e,
+	0xc0611dfc, 0x0000007c,
+	0x806e846e, 0xbefc007e,
+	0xb8eff801, 0xbefe007c,
+	0xbefc006e, 0xc0611bfc,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611b3c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0xbefe007c,
+	0xbefc006e, 0xc0611b7c,
+	0x0000007c, 0x806e846e,
+	0xbefc007e, 0x867aff7f,
+	0x04000000, 0xbef30080,
+	0x8773737a, 0xb8ee2a05,
+	0x806e816e, 0x8e6e8a6e,
+	0xb8f51605, 0x80758175,
+	0x8e758475, 0x8e7a8275,
+	0xbefa00ff, 0x01000000,
+	0xbef60178, 0x80786e78,
+	0x82798079, 0xbefc0080,
+	0xbe802b00, 0xbe822b02,
+	0xbe842b04, 0xbe862b06,
+	0xbe882b08, 0xbe8a2b0a,
+	0xbe8c2b0c, 0xbe8e2b0e,
+	0xc06b003c, 0x00000000,
+	0xc06b013c, 0x00000010,
+	0xc06b023c, 0x00000020,
+	0xc06b033c, 0x00000030,
+	0x8078c078, 0x82798079,
+	0x807c907c, 0xbf0a757c,
+	0xbf85ffeb, 0xbef80176,
+	0xbeee0080, 0xbefe00c1,
+	0xbeff00c1, 0xbefa00ff,
+	0x01000000, 0xe0724000,
+	0x6e1e0000, 0xe0724100,
+	0x6e1e0100, 0xe0724200,
+	0x6e1e0200, 0xe0724300,
+	0x6e1e0300, 0xbefe00c1,
+	0xbeff00c1, 0xb8f54306,
+	0x8675c175, 0xbf84002c,
+	0xbf8a0000, 0x867aff73,
+	0x04000000, 0xbf840028,
+	0x8e758675, 0x8e758275,
+	0xbefa0075, 0xb8ee2a05,
+	0x806e816e, 0x8e6e8a6e,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x806e7a6e,
+	0x806eff6e, 0x00000080,
+	0xbefa00ff, 0x01000000,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0xd1060002,
+	0x00011103, 0x7e0602ff,
+	0x00000200, 0xbefc00ff,
+	0x00010000, 0xbe80007b,
+	0x867bff7b, 0xff7fffff,
+	0x877bff7b, 0x00058000,
+	0xd8ec0000, 0x00000002,
+	0xbf8c007f, 0xe0765000,
+	0x6e1e0002, 0x32040702,
+	0xd0c9006a, 0x0000eb02,
+	0xbf87fff7, 0xbefb0000,
+	0xbeee00ff, 0x00000400,
+	0xbefe00c1, 0xbeff00c1,
+	0xb8f52a05, 0x80758175,
+	0x8e758275, 0x8e7a8875,
+	0xbefa00ff, 0x01000000,
+	0xbefc0084, 0xbf0a757c,
+	0xbf840015, 0xbf11017c,
+	0x8075ff75, 0x00001000,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
+	0xe0724000, 0x6e1e0000,
+	0xe0724100, 0x6e1e0100,
+	0xe0724200, 0x6e1e0200,
+	0xe0724300, 0x6e1e0300,
+	0x807c847c, 0x806eff6e,
+	0x00000400, 0xbf0a757c,
+	0xbf85ffef, 0xbf9c0000,
+	0xbf8200ca, 0xbef8007e,
+	0x8679ff7f, 0x0000ffff,
+	0x8779ff79, 0x00040000,
+	0xbefa0080, 0xbefb00ff,
+	0x00807fac, 0x8676ff7f,
+	0x08000000, 0x8f768376,
+	0x877b767b, 0x8676ff7f,
+	0x70000000, 0x8f768176,
+	0x877b767b, 0x8676ff7f,
+	0x04000000, 0xbf84001e,
+	0xbefe00c1, 0xbeff00c1,
+	0xb8f34306, 0x8673c173,
+	0xbf840019, 0x8e738673,
+	0x8e738273, 0xbefa0073,
+	0xb8f22a05, 0x80728172,
+	0x8e728a72, 0xb8f61605,
+	0x80768176, 0x8e768676,
+	0x80727672, 0x8072ff72,
+	0x00000080, 0xbefa00ff,
+	0x01000000, 0xbefc0080,
+	0xe0510000, 0x721e0000,
+	0xe0510100, 0x721e0000,
+	0x807cff7c, 0x00000200,
+	0x8072ff72, 0x00000200,
+	0xbf0a737c, 0xbf85fff6,
+	0xbef20080, 0xbefe00c1,
+	0xbeff00c1, 0xb8f32a05,
+	0x80738173, 0x8e738273,
+	0x8e7a8873, 0xbefa00ff,
+	0x01000000, 0xbef60072,
+	0x8072ff72, 0x00000400,
+	0xbefc0084, 0xbf11087c,
+	0x8073ff73, 0x00008000,
+	0xe0524000, 0x721e0000,
+	0xe0524100, 0x721e0100,
+	0xe0524200, 0x721e0200,
+	0xe0524300, 0x721e0300,
+	0xbf8c0f70, 0x7e000300,
+	0x7e020301, 0x7e040302,
+	0x7e060303, 0x807c847c,
+	0x8072ff72, 0x00000400,
+	0xbf0a737c, 0xbf85ffee,
+	0xbf9c0000, 0xe0524000,
+	0x761e0000, 0xe0524100,
+	0x761e0100, 0xe0524200,
+	0x761e0200, 0xe0524300,
+	0x761e0300, 0xb8f22a05,
+	0x80728172, 0x8e728a72,
+	0xb8f61605, 0x80768176,
+	0x8e768676, 0x80727672,
+	0x80f2c072, 0xb8f31605,
+	0x80738173, 0x8e738473,
+	0x8e7a8273, 0xbefa00ff,
+	0x01000000, 0xbefc0073,
+	0xc031003c, 0x00000072,
+	0x80f2c072, 0xbf8c007f,
+	0x80fc907c, 0xbe802d00,
+	0xbe822d02, 0xbe842d04,
+	0xbe862d06, 0xbe882d08,
+	0xbe8a2d0a, 0xbe8c2d0c,
+	0xbe8e2d0e, 0xbf06807c,
+	0xbf84fff1, 0xb8f22a05,
+	0x80728172, 0x8e728a72,
+	0xb8f61605, 0x80768176,
+	0x8e768676, 0x80727672,
+	0xbefa0084, 0xbefa00ff,
+	0x01000000, 0xc0211cfc,
+	0x00000072, 0x80728472,
+	0xc0211c3c, 0x00000072,
+	0x80728472, 0xc0211c7c,
+	0x00000072, 0x80728472,
+	0xc0211bbc, 0x00000072,
+	0x80728472, 0xc0211bfc,
+	0x00000072, 0x80728472,
+	0xc0211d3c, 0x00000072,
+	0x80728472, 0xc0211d7c,
+	0x00000072, 0x80728472,
+	0xc0211a3c, 0x00000072,
+	0x80728472, 0xc0211a7c,
+	0x00000072, 0x80728472,
+	0xc0211dfc, 0x00000072,
+	0x80728472, 0xc0211b3c,
+	0x00000072, 0x80728472,
+	0xc0211b7c, 0x00000072,
+	0x80728472, 0xbf8c007f,
+	0xbefc0073, 0xbefe006e,
+	0xbeff006f, 0x867375ff,
+	0x000003ff, 0xb9734803,
+	0x867375ff, 0xfffff800,
+	0x8f738b73, 0xb973a2c3,
+	0xb977f801, 0x8673ff71,
+	0xf0000000, 0x8f739c73,
+	0x8e739073, 0xbef60080,
+	0x87767376, 0x8673ff71,
+	0x08000000, 0x8f739b73,
+	0x8e738f73, 0x87767376,
+	0x8673ff74, 0x00800000,
+	0x8f739773, 0xb976f807,
+	0x8671ff71, 0x0000ffff,
+	0x86fe7e7e, 0x86ea6a6a,
+	0xb974f802, 0xbf8a0000,
+	0x95807370, 0xbf810000,
+};
+
+
+static const uint32_t cwsr_trap_gfx9_hex[] = {
+	0xbf820001, 0xbf82015a,
+	0xb8f8f802, 0x89788678,
+	0xb8f1f803, 0x866eff71,
+	0x00000400, 0xbf850034,
+	0x866eff71, 0x00000800,
+	0xbf850003, 0x866eff71,
+	0x00000100, 0xbf840008,
+	0x866eff78, 0x00002000,
+	0xbf840001, 0xbf810000,
+	0x8778ff78, 0x00002000,
+	0x80ec886c, 0x82ed806d,
+	0xb8eef807, 0x866fff6e,
+	0x001f8000, 0x8e6f8b6f,
+	0x8977ff77, 0xfc000000,
+	0x87776f77, 0x896eff6e,
+	0x001f8000, 0xb96ef807,
+	0xb8f0f812, 0xb8f1f813,
+	0x8ef08870, 0xc0071bb8,
+	0x00000000, 0xbf8cc07f,
+	0xc0071c38, 0x00000008,
+	0xbf8cc07f, 0x86ee6e6e,
+	0xbf840001, 0xbe801d6e,
+	0xb8f1f803, 0x8671ff71,
+	0x000001ff, 0xbf850002,
+	0x806c846c, 0x826d806d,
+	0x866dff6d, 0x0000ffff,
+	0x8f6e8b77, 0x866eff6e,
+	0x001f8000, 0xb96ef807,
+	0x86fe7e7e, 0x86ea6a6a,
+	0xb978f802, 0xbe801f6c,
+	0x866dff6d, 0x0000ffff,
+	0xbef00080, 0xb9700283,
+	0xb8f02407, 0x8e709c70,
+	0x876d706d, 0xb8f003c7,
+	0x8e709b70, 0x876d706d,
+	0xb8f0f807, 0x8670ff70,
+	0x00007fff, 0xb970f807,
+	0xbeee007e, 0xbeef007f,
+	0xbefe0180, 0xbf900004,
+	0x87708478, 0xb970f802,
+	0xbf8e0002, 0xbf88fffe,
+	0xb8f02a05, 0x80708170,
+	0x8e708a70, 0xb8f11605,
+	0x80718171, 0x8e718671,
+	0x80707170, 0x80707e70,
+	0x8271807f, 0x8671ff71,
+	0x0000ffff, 0xc0471cb8,
+	0x00000040, 0xbf8cc07f,
+	0xc04b1d38, 0x00000048,
+	0xbf8cc07f, 0xc0431e78,
+	0x00000058, 0xbf8cc07f,
+	0xc0471eb8, 0x0000005c,
+	0xbf8cc07f, 0xbef4007e,
+	0x8675ff7f, 0x0000ffff,
+	0x8775ff75, 0x00040000,
+	0xbef60080, 0xbef700ff,
+	0x00807fac, 0x8670ff7f,
+	0x08000000, 0x8f708370,
+	0x87777077, 0x8670ff7f,
+	0x70000000, 0x8f708170,
+	0x87777077, 0xbefb007c,
+	0xbefa0080, 0xb8fa2a05,
+	0x807a817a, 0x8e7a8a7a,
+	0xb8f01605, 0x80708170,
+	0x8e708670, 0x807a707a,
+	0xbef60084, 0xbef600ff,
+	0x01000000, 0xbefe007c,
+	0xbefc007a, 0xc0611efa,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xbefe007c, 0xbefc007a,
+	0xc0611b3a, 0x0000007c,
+	0xbf8cc07f, 0x807a847a,
+	0xbefc007e, 0xbefe007c,
+	0xbefc007a, 0xc0611b7a,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xbefe007c, 0xbefc007a,
+	0xc0611bba, 0x0000007c,
+	0xbf8cc07f, 0x807a847a,
+	0xbefc007e, 0xbefe007c,
+	0xbefc007a, 0xc0611bfa,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xbefe007c, 0xbefc007a,
+	0xc0611e3a, 0x0000007c,
+	0xbf8cc07f, 0x807a847a,
+	0xbefc007e, 0xb8f1f803,
+	0xbefe007c, 0xbefc007a,
+	0xc0611c7a, 0x0000007c,
+	0xbf8cc07f, 0x807a847a,
+	0xbefc007e, 0xbefe007c,
+	0xbefc007a, 0xc0611a3a,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xbefe007c, 0xbefc007a,
+	0xc0611a7a, 0x0000007c,
+	0xbf8cc07f, 0x807a847a,
+	0xbefc007e, 0xb8fbf801,
+	0xbefe007c, 0xbefc007a,
+	0xc0611efa, 0x0000007c,
+	0xbf8cc07f, 0x807a847a,
+	0xbefc007e, 0x8670ff7f,
+	0x04000000, 0xbeef0080,
+	0x876f6f70, 0xb8fa2a05,
+	0x807a817a, 0x8e7a8a7a,
+	0xb8f11605, 0x80718171,
+	0x8e718471, 0x8e768271,
+	0xbef600ff, 0x01000000,
+	0xbef20174, 0x80747a74,
+	0x82758075, 0xbefc0080,
+	0xbf800000, 0xbe802b00,
+	0xbe822b02, 0xbe842b04,
+	0xbe862b06, 0xbe882b08,
+	0xbe8a2b0a, 0xbe8c2b0c,
+	0xbe8e2b0e, 0xc06b003a,
+	0x00000000, 0xbf8cc07f,
+	0xc06b013a, 0x00000010,
+	0xbf8cc07f, 0xc06b023a,
+	0x00000020, 0xbf8cc07f,
+	0xc06b033a, 0x00000030,
+	0xbf8cc07f, 0x8074c074,
+	0x82758075, 0x807c907c,
+	0xbf0a717c, 0xbf85ffe7,
+	0xbef40172, 0xbefa0080,
+	0xbefe00c1, 0xbeff00c1,
+	0xbee80080, 0xbee90080,
+	0xbef600ff, 0x01000000,
+	0xe0724000, 0x7a1d0000,
+	0xe0724100, 0x7a1d0100,
+	0xe0724200, 0x7a1d0200,
+	0xe0724300, 0x7a1d0300,
+	0xbefe00c1, 0xbeff00c1,
+	0xb8f14306, 0x8671c171,
+	0xbf84002c, 0xbf8a0000,
+	0x8670ff6f, 0x04000000,
+	0xbf840028, 0x8e718671,
+	0x8e718271, 0xbef60071,
+	0xb8fa2a05, 0x807a817a,
+	0x8e7a8a7a, 0xb8f01605,
+	0x80708170, 0x8e708670,
+	0x807a707a, 0x807aff7a,
+	0x00000080, 0xbef600ff,
+	0x01000000, 0xbefc0080,
+	0xd28c0002, 0x000100c1,
+	0xd28d0003, 0x000204c1,
+	0xd1060002, 0x00011103,
+	0x7e0602ff, 0x00000200,
+	0xbefc00ff, 0x00010000,
+	0xbe800077, 0x8677ff77,
+	0xff7fffff, 0x8777ff77,
+	0x00058000, 0xd8ec0000,
+	0x00000002, 0xbf8cc07f,
+	0xe0765000, 0x7a1d0002,
+	0x68040702, 0xd0c9006a,
+	0x0000e302, 0xbf87fff7,
+	0xbef70000, 0xbefa00ff,
+	0x00000400, 0xbefe00c1,
+	0xbeff00c1, 0xb8f12a05,
+	0x80718171, 0x8e718271,
+	0x8e768871, 0xbef600ff,
+	0x01000000, 0xbefc0084,
+	0xbf0a717c, 0xbf840015,
+	0xbf11017c, 0x8071ff71,
+	0x00001000, 0x7e000300,
+	0x7e020301, 0x7e040302,
+	0x7e060303, 0xe0724000,
+	0x7a1d0000, 0xe0724100,
+	0x7a1d0100, 0xe0724200,
+	0x7a1d0200, 0xe0724300,
+	0x7a1d0300, 0x807c847c,
+	0x807aff7a, 0x00000400,
+	0xbf0a717c, 0xbf85ffef,
+	0xbf9c0000, 0xbf8200d9,
+	0xbef4007e, 0x8675ff7f,
+	0x0000ffff, 0x8775ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x00807fac,
+	0x866eff7f, 0x08000000,
+	0x8f6e836e, 0x87776e77,
+	0x866eff7f, 0x70000000,
+	0x8f6e816e, 0x87776e77,
+	0x866eff7f, 0x04000000,
+	0xbf84001e, 0xbefe00c1,
+	0xbeff00c1, 0xb8ef4306,
+	0x866fc16f, 0xbf840019,
+	0x8e6f866f, 0x8e6f826f,
+	0xbef6006f, 0xb8f82a05,
+	0x80788178, 0x8e788a78,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0x8078ff78, 0x00000080,
+	0xbef600ff, 0x01000000,
+	0xbefc0080, 0xe0510000,
+	0x781d0000, 0xe0510100,
+	0x781d0000, 0x807cff7c,
+	0x00000200, 0x8078ff78,
+	0x00000200, 0xbf0a6f7c,
+	0xbf85fff6, 0xbef80080,
+	0xbefe00c1, 0xbeff00c1,
+	0xb8ef2a05, 0x806f816f,
+	0x8e6f826f, 0x8e76886f,
+	0xbef600ff, 0x01000000,
+	0xbeee0078, 0x8078ff78,
+	0x00000400, 0xbefc0084,
+	0xbf11087c, 0x806fff6f,
+	0x00008000, 0xe0524000,
+	0x781d0000, 0xe0524100,
+	0x781d0100, 0xe0524200,
+	0x781d0200, 0xe0524300,
+	0x781d0300, 0xbf8c0f70,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
+	0x807c847c, 0x8078ff78,
+	0x00000400, 0xbf0a6f7c,
+	0xbf85ffee, 0xbf9c0000,
+	0xe0524000, 0x6e1d0000,
+	0xe0524100, 0x6e1d0100,
+	0xe0524200, 0x6e1d0200,
+	0xe0524300, 0x6e1d0300,
+	0xb8f82a05, 0x80788178,
+	0x8e788a78, 0xb8ee1605,
+	0x806e816e, 0x8e6e866e,
+	0x80786e78, 0x80f8c078,
+	0xb8ef1605, 0x806f816f,
+	0x8e6f846f, 0x8e76826f,
+	0xbef600ff, 0x01000000,
+	0xbefc006f, 0xc031003a,
+	0x00000078, 0x80f8c078,
+	0xbf8cc07f, 0x80fc907c,
+	0xbf800000, 0xbe802d00,
+	0xbe822d02, 0xbe842d04,
+	0xbe862d06, 0xbe882d08,
+	0xbe8a2d0a, 0xbe8c2d0c,
+	0xbe8e2d0e, 0xbf06807c,
+	0xbf84fff0, 0xb8f82a05,
+	0x80788178, 0x8e788a78,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0xbef60084, 0xbef600ff,
+	0x01000000, 0xc0211bfa,
+	0x00000078, 0x80788478,
+	0xc0211b3a, 0x00000078,
+	0x80788478, 0xc0211b7a,
+	0x00000078, 0x80788478,
+	0xc0211eba, 0x00000078,
+	0x80788478, 0xc0211efa,
+	0x00000078, 0x80788478,
+	0xc0211c3a, 0x00000078,
+	0x80788478, 0xc0211c7a,
+	0x00000078, 0x80788478,
+	0xc0211a3a, 0x00000078,
+	0x80788478, 0xc0211a7a,
+	0x00000078, 0x80788478,
+	0xc0211cfa, 0x00000078,
+	0x80788478, 0xbf8cc07f,
+	0xbefc006f, 0xbefe007a,
+	0xbeff007b, 0x866f71ff,
+	0x000003ff, 0xb96f4803,
+	0x866f71ff, 0xfffff800,
+	0x8f6f8b6f, 0xb96fa2c3,
+	0xb973f801, 0xb8ee2a05,
+	0x806e816e, 0x8e6e8a6e,
+	0xb8ef1605, 0x806f816f,
+	0x8e6f866f, 0x806e6f6e,
+	0x806e746e, 0x826f8075,
+	0x866fff6f, 0x0000ffff,
+	0xc0071cb7, 0x00000040,
+	0xc00b1d37, 0x00000048,
+	0xc0031e77, 0x00000058,
+	0xc0071eb7, 0x0000005c,
+	0xbf8cc07f, 0x866fff6d,
+	0xf0000000, 0x8f6f9c6f,
+	0x8e6f906f, 0xbeee0080,
+	0x876e6f6e, 0x866fff6d,
+	0x08000000, 0x8f6f9b6f,
+	0x8e6f8f6f, 0x876e6f6e,
+	0x866fff70, 0x00800000,
+	0x8f6f976f, 0xb96ef807,
+	0x866dff6d, 0x0000ffff,
+	0x86fe7e7e, 0x86ea6a6a,
+	0xb970f802, 0xbf8a0000,
+	0x95806f6c, 0xbf810000,
+};
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
index 997a383dcb8b..a2a04bb64096 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
@@ -20,9 +20,12 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#if 0
-HW (VI) source code for CWSR trap handler
-#Version 18 + multiple trap handler
+/* To compile this assembly code:
+ * PROJECT=vi ./sp3 cwsr_trap_handler_gfx8.asm -hex tmp.hex
+ */
+
+/* HW (VI) source code for CWSR trap handler */
+/* Version 18 + multiple trap handler */
 
 // this performance-optimal version was originally from Seven Xu at SRDC
 
@@ -98,6 +101,7 @@ var SWIZZLE_EN                      =   0                   //whether we use swi
 /**************************************************************************/
 var SQ_WAVE_STATUS_INST_ATC_SHIFT  = 23
 var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
+var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT    = 12
@@ -149,7 +153,7 @@ var s_save_spi_init_lo              =   exec_lo
 var s_save_spi_init_hi              =   exec_hi
 
                                                 //tba_lo and tba_hi need to be saved/restored
-var s_save_pc_lo            =   ttmp0           //{TTMP1, TTMP0} = {3??h0,pc_rewind[3:0], HT[0],trapID[7:0], PC[47:0]}
+var s_save_pc_lo            =   ttmp0           //{TTMP1, TTMP0} = {3'h0,pc_rewind[3:0], HT[0],trapID[7:0], PC[47:0]}
 var s_save_pc_hi            =   ttmp1
 var s_save_exec_lo          =   ttmp2
 var s_save_exec_hi          =   ttmp3
@@ -319,6 +323,10 @@ end
         s_sendmsg   sendmsg(MSG_SAVEWAVE)  //send SPI a message and wait for SPI's write to EXEC
     end
 
+    // Set SPI_PRIO=2 to avoid starving instruction fetch in the waves we're waiting for.
+    s_or_b32 s_save_tmp, s_save_status, (2 << SQ_WAVE_STATUS_SPI_PRIO_SHIFT)
+    s_setreg_b32 hwreg(HW_REG_STATUS), s_save_tmp
+
   L_SLEEP:
     s_sleep 0x2                // sleep 1 (64clk) is not enough for 8 waves per SIMD, which will cause SQ hang, since the 7,8th wave could not get arbit to exec inst, while other waves are stuck into the sleep-loop and waiting for wrexec!=0
 
@@ -1007,8 +1015,6 @@ end
 
     s_waitcnt       lgkmcnt(0)                                                                                      //from now on, it is safe to restore STATUS and IB_STS
 
-    s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff      //pc[47:32]        //Do it here in order not to affect STATUS
-
     //for normal save & restore, the saved PC points to the next inst to execute, no adjustment needs to be made, otherwise:
     if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_RESTORE_NORMAL))
         s_add_u32 s_restore_pc_lo, s_restore_pc_lo, 8            //pc[31:0]+8     //two back-to-back s_trap are used (first for save and second for restore)
@@ -1044,6 +1050,7 @@ end
     s_lshr_b32      s_restore_m0, s_restore_m0, SQ_WAVE_STATUS_INST_ATC_SHIFT
     s_setreg_b32    hwreg(HW_REG_IB_STS),   s_restore_tmp
 
+    s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff      //pc[47:32]        //Do it here in order not to affect STATUS
     s_and_b64    exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64    vcc, vcc, vcc  // Restore STATUS.VCCZ, not writable by s_setreg_b32
     s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status     // SCC is included, which is changed by previous salu
@@ -1127,258 +1134,3 @@ end
 function get_hwreg_size_bytes
     return 128 //HWREG size 128 bytes
 end
-
-
-#endif
-
-static const uint32_t cwsr_trap_gfx8_hex[] = {
-	0xbf820001, 0xbf820123,
-	0xb8f4f802, 0x89748674,
-	0xb8f5f803, 0x8675ff75,
-	0x00000400, 0xbf850011,
-	0xc00a1e37, 0x00000000,
-	0xbf8c007f, 0x87777978,
-	0xbf840002, 0xb974f802,
-	0xbe801d78, 0xb8f5f803,
-	0x8675ff75, 0x000001ff,
-	0xbf850002, 0x80708470,
-	0x82718071, 0x8671ff71,
-	0x0000ffff, 0xb974f802,
-	0xbe801f70, 0xb8f5f803,
-	0x8675ff75, 0x00000100,
-	0xbf840006, 0xbefa0080,
-	0xb97a0203, 0x8671ff71,
-	0x0000ffff, 0x80f08870,
-	0x82f18071, 0xbefa0080,
-	0xb97a0283, 0xbef60068,
-	0xbef70069, 0xb8fa1c07,
-	0x8e7a9c7a, 0x87717a71,
-	0xb8fa03c7, 0x8e7a9b7a,
-	0x87717a71, 0xb8faf807,
-	0x867aff7a, 0x00007fff,
-	0xb97af807, 0xbef2007e,
-	0xbef3007f, 0xbefe0180,
-	0xbf900004, 0xbf8e0002,
-	0xbf88fffe, 0xbef8007e,
-	0x8679ff7f, 0x0000ffff,
-	0x8779ff79, 0x00040000,
-	0xbefa0080, 0xbefb00ff,
-	0x00807fac, 0x867aff7f,
-	0x08000000, 0x8f7a837a,
-	0x877b7a7b, 0x867aff7f,
-	0x70000000, 0x8f7a817a,
-	0x877b7a7b, 0xbeef007c,
-	0xbeee0080, 0xb8ee2a05,
-	0x806e816e, 0x8e6e8a6e,
-	0xb8fa1605, 0x807a817a,
-	0x8e7a867a, 0x806e7a6e,
-	0xbefa0084, 0xbefa00ff,
-	0x01000000, 0xbefe007c,
-	0xbefc006e, 0xc0611bfc,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0xbefe007c,
-	0xbefc006e, 0xc0611c3c,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0xbefe007c,
-	0xbefc006e, 0xc0611c7c,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0xbefe007c,
-	0xbefc006e, 0xc0611cbc,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0xbefe007c,
-	0xbefc006e, 0xc0611cfc,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0xbefe007c,
-	0xbefc006e, 0xc0611d3c,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0xb8f5f803,
-	0xbefe007c, 0xbefc006e,
-	0xc0611d7c, 0x0000007c,
-	0x806e846e, 0xbefc007e,
-	0xbefe007c, 0xbefc006e,
-	0xc0611dbc, 0x0000007c,
-	0x806e846e, 0xbefc007e,
-	0xbefe007c, 0xbefc006e,
-	0xc0611dfc, 0x0000007c,
-	0x806e846e, 0xbefc007e,
-	0xb8eff801, 0xbefe007c,
-	0xbefc006e, 0xc0611bfc,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0xbefe007c,
-	0xbefc006e, 0xc0611b3c,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0xbefe007c,
-	0xbefc006e, 0xc0611b7c,
-	0x0000007c, 0x806e846e,
-	0xbefc007e, 0x867aff7f,
-	0x04000000, 0xbef30080,
-	0x8773737a, 0xb8ee2a05,
-	0x806e816e, 0x8e6e8a6e,
-	0xb8f51605, 0x80758175,
-	0x8e758475, 0x8e7a8275,
-	0xbefa00ff, 0x01000000,
-	0xbef60178, 0x80786e78,
-	0x82798079, 0xbefc0080,
-	0xbe802b00, 0xbe822b02,
-	0xbe842b04, 0xbe862b06,
-	0xbe882b08, 0xbe8a2b0a,
-	0xbe8c2b0c, 0xbe8e2b0e,
-	0xc06b003c, 0x00000000,
-	0xc06b013c, 0x00000010,
-	0xc06b023c, 0x00000020,
-	0xc06b033c, 0x00000030,
-	0x8078c078, 0x82798079,
-	0x807c907c, 0xbf0a757c,
-	0xbf85ffeb, 0xbef80176,
-	0xbeee0080, 0xbefe00c1,
-	0xbeff00c1, 0xbefa00ff,
-	0x01000000, 0xe0724000,
-	0x6e1e0000, 0xe0724100,
-	0x6e1e0100, 0xe0724200,
-	0x6e1e0200, 0xe0724300,
-	0x6e1e0300, 0xbefe00c1,
-	0xbeff00c1, 0xb8f54306,
-	0x8675c175, 0xbf84002c,
-	0xbf8a0000, 0x867aff73,
-	0x04000000, 0xbf840028,
-	0x8e758675, 0x8e758275,
-	0xbefa0075, 0xb8ee2a05,
-	0x806e816e, 0x8e6e8a6e,
-	0xb8fa1605, 0x807a817a,
-	0x8e7a867a, 0x806e7a6e,
-	0x806eff6e, 0x00000080,
-	0xbefa00ff, 0x01000000,
-	0xbefc0080, 0xd28c0002,
-	0x000100c1, 0xd28d0003,
-	0x000204c1, 0xd1060002,
-	0x00011103, 0x7e0602ff,
-	0x00000200, 0xbefc00ff,
-	0x00010000, 0xbe80007b,
-	0x867bff7b, 0xff7fffff,
-	0x877bff7b, 0x00058000,
-	0xd8ec0000, 0x00000002,
-	0xbf8c007f, 0xe0765000,
-	0x6e1e0002, 0x32040702,
-	0xd0c9006a, 0x0000eb02,
-	0xbf87fff7, 0xbefb0000,
-	0xbeee00ff, 0x00000400,
-	0xbefe00c1, 0xbeff00c1,
-	0xb8f52a05, 0x80758175,
-	0x8e758275, 0x8e7a8875,
-	0xbefa00ff, 0x01000000,
-	0xbefc0084, 0xbf0a757c,
-	0xbf840015, 0xbf11017c,
-	0x8075ff75, 0x00001000,
-	0x7e000300, 0x7e020301,
-	0x7e040302, 0x7e060303,
-	0xe0724000, 0x6e1e0000,
-	0xe0724100, 0x6e1e0100,
-	0xe0724200, 0x6e1e0200,
-	0xe0724300, 0x6e1e0300,
-	0x807c847c, 0x806eff6e,
-	0x00000400, 0xbf0a757c,
-	0xbf85ffef, 0xbf9c0000,
-	0xbf8200ca, 0xbef8007e,
-	0x8679ff7f, 0x0000ffff,
-	0x8779ff79, 0x00040000,
-	0xbefa0080, 0xbefb00ff,
-	0x00807fac, 0x8676ff7f,
-	0x08000000, 0x8f768376,
-	0x877b767b, 0x8676ff7f,
-	0x70000000, 0x8f768176,
-	0x877b767b, 0x8676ff7f,
-	0x04000000, 0xbf84001e,
-	0xbefe00c1, 0xbeff00c1,
-	0xb8f34306, 0x8673c173,
-	0xbf840019, 0x8e738673,
-	0x8e738273, 0xbefa0073,
-	0xb8f22a05, 0x80728172,
-	0x8e728a72, 0xb8f61605,
-	0x80768176, 0x8e768676,
-	0x80727672, 0x8072ff72,
-	0x00000080, 0xbefa00ff,
-	0x01000000, 0xbefc0080,
-	0xe0510000, 0x721e0000,
-	0xe0510100, 0x721e0000,
-	0x807cff7c, 0x00000200,
-	0x8072ff72, 0x00000200,
-	0xbf0a737c, 0xbf85fff6,
-	0xbef20080, 0xbefe00c1,
-	0xbeff00c1, 0xb8f32a05,
-	0x80738173, 0x8e738273,
-	0x8e7a8873, 0xbefa00ff,
-	0x01000000, 0xbef60072,
-	0x8072ff72, 0x00000400,
-	0xbefc0084, 0xbf11087c,
-	0x8073ff73, 0x00008000,
-	0xe0524000, 0x721e0000,
-	0xe0524100, 0x721e0100,
-	0xe0524200, 0x721e0200,
-	0xe0524300, 0x721e0300,
-	0xbf8c0f70, 0x7e000300,
-	0x7e020301, 0x7e040302,
-	0x7e060303, 0x807c847c,
-	0x8072ff72, 0x00000400,
-	0xbf0a737c, 0xbf85ffee,
-	0xbf9c0000, 0xe0524000,
-	0x761e0000, 0xe0524100,
-	0x761e0100, 0xe0524200,
-	0x761e0200, 0xe0524300,
-	0x761e0300, 0xb8f22a05,
-	0x80728172, 0x8e728a72,
-	0xb8f61605, 0x80768176,
-	0x8e768676, 0x80727672,
-	0x80f2c072, 0xb8f31605,
-	0x80738173, 0x8e738473,
-	0x8e7a8273, 0xbefa00ff,
-	0x01000000, 0xbefc0073,
-	0xc031003c, 0x00000072,
-	0x80f2c072, 0xbf8c007f,
-	0x80fc907c, 0xbe802d00,
-	0xbe822d02, 0xbe842d04,
-	0xbe862d06, 0xbe882d08,
-	0xbe8a2d0a, 0xbe8c2d0c,
-	0xbe8e2d0e, 0xbf06807c,
-	0xbf84fff1, 0xb8f22a05,
-	0x80728172, 0x8e728a72,
-	0xb8f61605, 0x80768176,
-	0x8e768676, 0x80727672,
-	0xbefa0084, 0xbefa00ff,
-	0x01000000, 0xc0211cfc,
-	0x00000072, 0x80728472,
-	0xc0211c3c, 0x00000072,
-	0x80728472, 0xc0211c7c,
-	0x00000072, 0x80728472,
-	0xc0211bbc, 0x00000072,
-	0x80728472, 0xc0211bfc,
-	0x00000072, 0x80728472,
-	0xc0211d3c, 0x00000072,
-	0x80728472, 0xc0211d7c,
-	0x00000072, 0x80728472,
-	0xc0211a3c, 0x00000072,
-	0x80728472, 0xc0211a7c,
-	0x00000072, 0x80728472,
-	0xc0211dfc, 0x00000072,
-	0x80728472, 0xc0211b3c,
-	0x00000072, 0x80728472,
-	0xc0211b7c, 0x00000072,
-	0x80728472, 0xbf8c007f,
-	0x8671ff71, 0x0000ffff,
-	0xbefc0073, 0xbefe006e,
-	0xbeff006f, 0x867375ff,
-	0x000003ff, 0xb9734803,
-	0x867375ff, 0xfffff800,
-	0x8f738b73, 0xb973a2c3,
-	0xb977f801, 0x8673ff71,
-	0xf0000000, 0x8f739c73,
-	0x8e739073, 0xbef60080,
-	0x87767376, 0x8673ff71,
-	0x08000000, 0x8f739b73,
-	0x8e738f73, 0x87767376,
-	0x8673ff74, 0x00800000,
-	0x8f739773, 0xb976f807,
-	0x86fe7e7e, 0x86ea6a6a,
-	0xb974f802, 0xbf8a0000,
-	0x95807370, 0xbf810000,
-};
-
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
new file mode 100644
index 000000000000..998be96be736
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -0,0 +1,1214 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/* To compile this assembly code:
+ * PROJECT=greenland ./sp3 cwsr_trap_handler_gfx9.asm -hex tmp.hex
+ */
+
+/* HW (GFX9) source code for CWSR trap handler */
+/* Version 18 + multiple trap handler */
+
+// this performance-optimal version was originally from Seven Xu at SRDC
+
+// Revison #18	 --...
+/* Rev History
+** #1. Branch from gc dv.   //gfxip/gfx9/main/src/test/suites/block/cs/sr/cs_trap_handler.sp3#1,#50, #51, #52-53(Skip, Already Fixed by PV), #54-56(merged),#57-58(mergerd, skiped-already fixed by PV)
+** #4. SR Memory Layout:
+**			 1. VGPR-SGPR-HWREG-{LDS}
+**			 2. tba_hi.bits.26 - reconfigured as the first wave in tg bits, for defer Save LDS for a threadgroup.. performance concern..
+** #5. Update: 1. Accurate g8sr_ts_save_d timestamp
+** #6. Update: 1. Fix s_barrier usage; 2. VGPR s/r using swizzle buffer?(NoNeed, already matched the swizzle pattern, more investigation)
+** #7. Update: 1. don't barrier if noLDS
+** #8. Branch: 1. Branch to ver#0, which is very similar to gc dv version
+**	       2. Fix SQ issue by s_sleep 2
+** #9. Update: 1. Fix scc restore failed issue, restore wave_status at last
+**	       2. optimize s_buffer save by burst 16sgprs...
+** #10. Update 1. Optimize restore sgpr by busrt 16 sgprs.
+** #11. Update 1. Add 2 more timestamp for debug version
+** #12. Update 1. Add VGPR SR using DWx4, some case improve and some case drop performance
+** #13. Integ  1. Always use MUBUF for PV trap shader...
+** #14. Update 1. s_buffer_store soft clause...
+** #15. Update 1. PERF - sclar write with glc:0/mtype0 to allow L2 combine. perf improvement a lot.
+** #16. Update 1. PRRF - UNROLL LDS_DMA got 2500cycle save in IP tree
+** #17. Update 1. FUNC - LDS_DMA has issues while ATC, replace with ds_read/buffer_store for save part[TODO restore part]
+**	       2. PERF - Save LDS before save VGPR to cover LDS save long latency...
+** #18. Update 1. FUNC - Implicitly estore STATUS.VCCZ, which is not writable by s_setreg_b32
+**	       2. FUNC - Handle non-CWSR traps
+*/
+
+var G8SR_WDMEM_HWREG_OFFSET = 0
+var G8SR_WDMEM_SGPR_OFFSET  = 128  // in bytes
+
+// Keep definition same as the app shader, These 2 time stamps are part of the app shader... Should before any Save and after restore.
+
+var G8SR_DEBUG_TIMESTAMP = 0
+var G8SR_DEBUG_TS_SAVE_D_OFFSET = 40*4	// ts_save_d timestamp offset relative to SGPR_SR_memory_offset
+var s_g8sr_ts_save_s	= s[34:35]   // save start
+var s_g8sr_ts_sq_save_msg  = s[36:37]	// The save shader send SAVEWAVE msg to spi
+var s_g8sr_ts_spi_wrexec   = s[38:39]	// the SPI write the sr address to SQ
+var s_g8sr_ts_save_d	= s[40:41]   // save end
+var s_g8sr_ts_restore_s = s[42:43]   // restore start
+var s_g8sr_ts_restore_d = s[44:45]   // restore end
+
+var G8SR_VGPR_SR_IN_DWX4 = 0
+var G8SR_SAVE_BUF_RSRC_WORD1_STRIDE_DWx4 = 0x00100000	 // DWx4 stride is 4*4Bytes
+var G8SR_RESTORE_BUF_RSRC_WORD1_STRIDE_DWx4  = G8SR_SAVE_BUF_RSRC_WORD1_STRIDE_DWx4
+
+
+/*************************************************************************/
+/*		    control on how to run the shader			 */
+/*************************************************************************/
+//any hack that needs to be made to run this code in EMU (either because various EMU code are not ready or no compute save & restore in EMU run)
+var EMU_RUN_HACK		    =	0
+var EMU_RUN_HACK_RESTORE_NORMAL	    =	0
+var EMU_RUN_HACK_SAVE_NORMAL_EXIT   =	0
+var EMU_RUN_HACK_SAVE_SINGLE_WAVE   =	0
+var EMU_RUN_HACK_SAVE_FIRST_TIME    =	0		    //for interrupted restore in which the first save is through EMU_RUN_HACK
+var SAVE_LDS			    =	1
+var WG_BASE_ADDR_LO		    =	0x9000a000
+var WG_BASE_ADDR_HI		    =	0x0
+var WAVE_SPACE			    =	0x5000		    //memory size that each wave occupies in workgroup state mem
+var CTX_SAVE_CONTROL		    =	0x0
+var CTX_RESTORE_CONTROL		    =	CTX_SAVE_CONTROL
+var SIM_RUN_HACK		    =	0		    //any hack that needs to be made to run this code in SIM (either because various RTL code are not ready or no compute save & restore in RTL run)
+var SGPR_SAVE_USE_SQC		    =	1		    //use SQC D$ to do the write
+var USE_MTBUF_INSTEAD_OF_MUBUF	    =	0		    //because TC EMU currently asserts on 0 of // overload DFMT field to carry 4 more bits of stride for MUBUF opcodes
+var SWIZZLE_EN			    =	0		    //whether we use swizzled buffer addressing
+var ACK_SQC_STORE		    =	1		    //workaround for suspected SQC store bug causing incorrect stores under concurrency
+
+/**************************************************************************/
+/*			variables					  */
+/**************************************************************************/
+var SQ_WAVE_STATUS_INST_ATC_SHIFT  = 23
+var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
+var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
+var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
+var SQ_WAVE_STATUS_HALT_MASK       = 0x2000
+
+var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT	= 12
+var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE	= 9
+var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT	= 8
+var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE	= 6
+var SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SHIFT	= 24
+var SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SIZE	= 3			//FIXME	 sq.blk still has 4 bits at this time while SQ programming guide has 3 bits
+
+var SQ_WAVE_TRAPSTS_SAVECTX_MASK    =	0x400
+var SQ_WAVE_TRAPSTS_EXCE_MASK	    =	0x1FF			// Exception mask
+var SQ_WAVE_TRAPSTS_SAVECTX_SHIFT   =	10
+var SQ_WAVE_TRAPSTS_MEM_VIOL_MASK   =	0x100
+var SQ_WAVE_TRAPSTS_MEM_VIOL_SHIFT  =	8
+var SQ_WAVE_TRAPSTS_PRE_SAVECTX_MASK	=   0x3FF
+var SQ_WAVE_TRAPSTS_PRE_SAVECTX_SHIFT	=   0x0
+var SQ_WAVE_TRAPSTS_PRE_SAVECTX_SIZE	=   10
+var SQ_WAVE_TRAPSTS_POST_SAVECTX_MASK	=   0xFFFFF800
+var SQ_WAVE_TRAPSTS_POST_SAVECTX_SHIFT	=   11
+var SQ_WAVE_TRAPSTS_POST_SAVECTX_SIZE	=   21
+var SQ_WAVE_TRAPSTS_ILLEGAL_INST_MASK	=   0x800
+
+var SQ_WAVE_IB_STS_RCNT_SHIFT		=   16			//FIXME
+var SQ_WAVE_IB_STS_FIRST_REPLAY_SHIFT	=   15			//FIXME
+var SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK	= 0x1F8000
+var SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK_NEG	= 0x00007FFF	//FIXME
+
+var SQ_BUF_RSRC_WORD1_ATC_SHIFT	    =	24
+var SQ_BUF_RSRC_WORD3_MTYPE_SHIFT   =	27
+
+var TTMP11_SAVE_RCNT_FIRST_REPLAY_SHIFT	=   26			// bits [31:26] unused by SPI debug data
+var TTMP11_SAVE_RCNT_FIRST_REPLAY_MASK	=   0xFC000000
+
+/*	Save	    */
+var S_SAVE_BUF_RSRC_WORD1_STRIDE	=   0x00040000		//stride is 4 bytes
+var S_SAVE_BUF_RSRC_WORD3_MISC		=   0x00807FAC		//SQ_SEL_X/Y/Z/W, BUF_NUM_FORMAT_FLOAT, (0 for MUBUF stride[17:14] when ADD_TID_ENABLE and BUF_DATA_FORMAT_32 for MTBUF), ADD_TID_ENABLE
+
+var S_SAVE_SPI_INIT_ATC_MASK		=   0x08000000		//bit[27]: ATC bit
+var S_SAVE_SPI_INIT_ATC_SHIFT		=   27
+var S_SAVE_SPI_INIT_MTYPE_MASK		=   0x70000000		//bit[30:28]: Mtype
+var S_SAVE_SPI_INIT_MTYPE_SHIFT		=   28
+var S_SAVE_SPI_INIT_FIRST_WAVE_MASK	=   0x04000000		//bit[26]: FirstWaveInTG
+var S_SAVE_SPI_INIT_FIRST_WAVE_SHIFT	=   26
+
+var S_SAVE_PC_HI_RCNT_SHIFT		=   28			//FIXME	 check with Brian to ensure all fields other than PC[47:0] can be used
+var S_SAVE_PC_HI_RCNT_MASK		=   0xF0000000		//FIXME
+var S_SAVE_PC_HI_FIRST_REPLAY_SHIFT	=   27			//FIXME
+var S_SAVE_PC_HI_FIRST_REPLAY_MASK	=   0x08000000		//FIXME
+
+var s_save_spi_init_lo		    =	exec_lo
+var s_save_spi_init_hi		    =	exec_hi
+
+var s_save_pc_lo	    =	ttmp0		//{TTMP1, TTMP0} = {3'h0,pc_rewind[3:0], HT[0],trapID[7:0], PC[47:0]}
+var s_save_pc_hi	    =	ttmp1
+var s_save_exec_lo	    =	ttmp2
+var s_save_exec_hi	    =	ttmp3
+var s_save_tmp		    =	ttmp4
+var s_save_trapsts	    =	ttmp5		//not really used until the end of the SAVE routine
+var s_save_xnack_mask_lo    =	ttmp6
+var s_save_xnack_mask_hi    =	ttmp7
+var s_save_buf_rsrc0	    =	ttmp8
+var s_save_buf_rsrc1	    =	ttmp9
+var s_save_buf_rsrc2	    =	ttmp10
+var s_save_buf_rsrc3	    =	ttmp11
+var s_save_status	    =	ttmp12
+var s_save_mem_offset	    =	ttmp14
+var s_save_alloc_size	    =	s_save_trapsts		//conflict
+var s_save_m0		    =	ttmp15
+var s_save_ttmps_lo	    =	s_save_tmp		//no conflict
+var s_save_ttmps_hi	    =	s_save_trapsts		//no conflict
+
+/*	Restore	    */
+var S_RESTORE_BUF_RSRC_WORD1_STRIDE	    =	S_SAVE_BUF_RSRC_WORD1_STRIDE
+var S_RESTORE_BUF_RSRC_WORD3_MISC	    =	S_SAVE_BUF_RSRC_WORD3_MISC
+
+var S_RESTORE_SPI_INIT_ATC_MASK		    =	0x08000000	    //bit[27]: ATC bit
+var S_RESTORE_SPI_INIT_ATC_SHIFT	    =	27
+var S_RESTORE_SPI_INIT_MTYPE_MASK	    =	0x70000000	    //bit[30:28]: Mtype
+var S_RESTORE_SPI_INIT_MTYPE_SHIFT	    =	28
+var S_RESTORE_SPI_INIT_FIRST_WAVE_MASK	    =	0x04000000	    //bit[26]: FirstWaveInTG
+var S_RESTORE_SPI_INIT_FIRST_WAVE_SHIFT	    =	26
+
+var S_RESTORE_PC_HI_RCNT_SHIFT		    =	S_SAVE_PC_HI_RCNT_SHIFT
+var S_RESTORE_PC_HI_RCNT_MASK		    =	S_SAVE_PC_HI_RCNT_MASK
+var S_RESTORE_PC_HI_FIRST_REPLAY_SHIFT	    =	S_SAVE_PC_HI_FIRST_REPLAY_SHIFT
+var S_RESTORE_PC_HI_FIRST_REPLAY_MASK	    =	S_SAVE_PC_HI_FIRST_REPLAY_MASK
+
+var s_restore_spi_init_lo		    =	exec_lo
+var s_restore_spi_init_hi		    =	exec_hi
+
+var s_restore_mem_offset	=   ttmp12
+var s_restore_alloc_size	=   ttmp3
+var s_restore_tmp		=   ttmp2
+var s_restore_mem_offset_save	=   s_restore_tmp	//no conflict
+
+var s_restore_m0	    =	s_restore_alloc_size	//no conflict
+
+var s_restore_mode	    =	ttmp7
+
+var s_restore_pc_lo	    =	ttmp0
+var s_restore_pc_hi	    =	ttmp1
+var s_restore_exec_lo	    =	ttmp14
+var s_restore_exec_hi	    = 	ttmp15
+var s_restore_status	    =	ttmp4
+var s_restore_trapsts	    =	ttmp5
+var s_restore_xnack_mask_lo =	xnack_mask_lo
+var s_restore_xnack_mask_hi =	xnack_mask_hi
+var s_restore_buf_rsrc0	    =	ttmp8
+var s_restore_buf_rsrc1	    =	ttmp9
+var s_restore_buf_rsrc2	    =	ttmp10
+var s_restore_buf_rsrc3	    =	ttmp11
+var s_restore_ttmps_lo	    =	s_restore_tmp		//no conflict
+var s_restore_ttmps_hi	    =	s_restore_alloc_size	//no conflict
+
+/**************************************************************************/
+/*			trap handler entry points			  */
+/**************************************************************************/
+/* Shader Main*/
+
+shader main
+  asic(GFX9)
+  type(CS)
+
+
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_RESTORE_NORMAL))		    //hack to use trap_id for determining save/restore
+	//FIXME VCCZ un-init assertion s_getreg_b32	s_save_status, hwreg(HW_REG_STATUS)	    //save STATUS since we will change SCC
+	s_and_b32 s_save_tmp, s_save_pc_hi, 0xffff0000		    //change SCC
+	s_cmp_eq_u32 s_save_tmp, 0x007e0000			    //Save: trap_id = 0x7e. Restore: trap_id = 0x7f.
+	s_cbranch_scc0 L_JUMP_TO_RESTORE			    //do not need to recover STATUS here  since we are going to RESTORE
+	//FIXME	 s_setreg_b32	hwreg(HW_REG_STATUS),	s_save_status	    //need to recover STATUS since we are going to SAVE
+	s_branch L_SKIP_RESTORE					    //NOT restore, SAVE actually
+    else
+	s_branch L_SKIP_RESTORE					    //NOT restore. might be a regular trap or save
+    end
+
+L_JUMP_TO_RESTORE:
+    s_branch L_RESTORE						    //restore
+
+L_SKIP_RESTORE:
+
+    s_getreg_b32    s_save_status, hwreg(HW_REG_STATUS)				    //save STATUS since we will change SCC
+    s_andn2_b32	    s_save_status, s_save_status, SQ_WAVE_STATUS_SPI_PRIO_MASK	    //check whether this is for save
+    s_getreg_b32    s_save_trapsts, hwreg(HW_REG_TRAPSTS)
+    s_and_b32       ttmp2, s_save_trapsts, SQ_WAVE_TRAPSTS_SAVECTX_MASK    //check whether this is for save
+    s_cbranch_scc1  L_SAVE					//this is the operation for save
+
+    // *********    Handle non-CWSR traps	*******************
+if (!EMU_RUN_HACK)
+    // Illegal instruction is a non-maskable exception which blocks context save.
+    // Halt the wavefront and return from the trap.
+    s_and_b32       ttmp2, s_save_trapsts, SQ_WAVE_TRAPSTS_ILLEGAL_INST_MASK
+    s_cbranch_scc1  L_HALT_WAVE
+
+    // If STATUS.MEM_VIOL is asserted then we cannot fetch from the TMA.
+    // Instead, halt the wavefront and return from the trap.
+    s_and_b32       ttmp2, s_save_trapsts, SQ_WAVE_TRAPSTS_MEM_VIOL_MASK
+    s_cbranch_scc0  L_FETCH_2ND_TRAP
+
+L_HALT_WAVE:
+    // If STATUS.HALT is set then this fault must come from SQC instruction fetch.
+    // We cannot prevent further faults so just terminate the wavefront.
+    s_and_b32       ttmp2, s_save_status, SQ_WAVE_STATUS_HALT_MASK
+    s_cbranch_scc0  L_NOT_ALREADY_HALTED
+    s_endpgm
+L_NOT_ALREADY_HALTED:
+    s_or_b32        s_save_status, s_save_status, SQ_WAVE_STATUS_HALT_MASK
+
+    // If the PC points to S_ENDPGM then context save will fail if STATUS.HALT is set.
+    // Rewind the PC to prevent this from occurring. The debugger compensates for this.
+    s_sub_u32       ttmp0, ttmp0, 0x8
+    s_subb_u32      ttmp1, ttmp1, 0x0
+
+L_FETCH_2ND_TRAP:
+    // Preserve and clear scalar XNACK state before issuing scalar reads.
+    // Save IB_STS.FIRST_REPLAY[15] and IB_STS.RCNT[20:16] into unused space ttmp11[31:26].
+    s_getreg_b32    ttmp2, hwreg(HW_REG_IB_STS)
+    s_and_b32       ttmp3, ttmp2, SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK
+    s_lshl_b32      ttmp3, ttmp3, (TTMP11_SAVE_RCNT_FIRST_REPLAY_SHIFT - SQ_WAVE_IB_STS_FIRST_REPLAY_SHIFT)
+    s_andn2_b32     ttmp11, ttmp11, TTMP11_SAVE_RCNT_FIRST_REPLAY_MASK
+    s_or_b32        ttmp11, ttmp11, ttmp3
+
+    s_andn2_b32     ttmp2, ttmp2, SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK
+    s_setreg_b32    hwreg(HW_REG_IB_STS), ttmp2
+
+    // Read second-level TBA/TMA from first-level TMA and jump if available.
+    // ttmp[2:5] and ttmp12 can be used (others hold SPI-initialized debug data)
+    // ttmp12 holds SQ_WAVE_STATUS
+    s_getreg_b32    ttmp4, hwreg(HW_REG_SQ_SHADER_TMA_LO)
+    s_getreg_b32    ttmp5, hwreg(HW_REG_SQ_SHADER_TMA_HI)
+    s_lshl_b64      [ttmp4, ttmp5], [ttmp4, ttmp5], 0x8
+    s_load_dwordx2  [ttmp2, ttmp3], [ttmp4, ttmp5], 0x0 glc:1 // second-level TBA
+    s_waitcnt       lgkmcnt(0)
+    s_load_dwordx2  [ttmp4, ttmp5], [ttmp4, ttmp5], 0x8 glc:1 // second-level TMA
+    s_waitcnt       lgkmcnt(0)
+    s_and_b64       [ttmp2, ttmp3], [ttmp2, ttmp3], [ttmp2, ttmp3]
+    s_cbranch_scc0  L_NO_NEXT_TRAP // second-level trap handler not been set
+    s_setpc_b64     [ttmp2, ttmp3] // jump to second-level trap handler
+
+L_NO_NEXT_TRAP:
+    s_getreg_b32    s_save_trapsts, hwreg(HW_REG_TRAPSTS)
+    s_and_b32	    s_save_trapsts, s_save_trapsts, SQ_WAVE_TRAPSTS_EXCE_MASK // Check whether it is an exception
+    s_cbranch_scc1  L_EXCP_CASE	  // Exception, jump back to the shader program directly.
+    s_add_u32	    ttmp0, ttmp0, 4   // S_TRAP case, add 4 to ttmp0
+    s_addc_u32	ttmp1, ttmp1, 0
+L_EXCP_CASE:
+    s_and_b32	ttmp1, ttmp1, 0xFFFF
+
+    // Restore SQ_WAVE_IB_STS.
+    s_lshr_b32      ttmp2, ttmp11, (TTMP11_SAVE_RCNT_FIRST_REPLAY_SHIFT - SQ_WAVE_IB_STS_FIRST_REPLAY_SHIFT)
+    s_and_b32       ttmp2, ttmp2, SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK
+    s_setreg_b32    hwreg(HW_REG_IB_STS), ttmp2
+
+    // Restore SQ_WAVE_STATUS.
+    s_and_b64       exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32
+    s_and_b64       vcc, vcc, vcc    // Restore STATUS.VCCZ, not writable by s_setreg_b32
+    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status
+
+    s_rfe_b64       [ttmp0, ttmp1]
+end
+    // *********	End handling of non-CWSR traps	 *******************
+
+/**************************************************************************/
+/*			save routine					  */
+/**************************************************************************/
+
+L_SAVE:
+
+if G8SR_DEBUG_TIMESTAMP
+	s_memrealtime	s_g8sr_ts_save_s
+	s_waitcnt lgkmcnt(0)	     //FIXME, will cause xnack??
+end
+
+    s_and_b32	    s_save_pc_hi, s_save_pc_hi, 0x0000ffff    //pc[47:32]
+
+    s_mov_b32	    s_save_tmp, 0							    //clear saveCtx bit
+    s_setreg_b32    hwreg(HW_REG_TRAPSTS, SQ_WAVE_TRAPSTS_SAVECTX_SHIFT, 1), s_save_tmp	    //clear saveCtx bit
+
+    s_getreg_b32    s_save_tmp, hwreg(HW_REG_IB_STS, SQ_WAVE_IB_STS_RCNT_SHIFT, SQ_WAVE_IB_STS_RCNT_SIZE)		    //save RCNT
+    s_lshl_b32	    s_save_tmp, s_save_tmp, S_SAVE_PC_HI_RCNT_SHIFT
+    s_or_b32	    s_save_pc_hi, s_save_pc_hi, s_save_tmp
+    s_getreg_b32    s_save_tmp, hwreg(HW_REG_IB_STS, SQ_WAVE_IB_STS_FIRST_REPLAY_SHIFT, SQ_WAVE_IB_STS_FIRST_REPLAY_SIZE)   //save FIRST_REPLAY
+    s_lshl_b32	    s_save_tmp, s_save_tmp, S_SAVE_PC_HI_FIRST_REPLAY_SHIFT
+    s_or_b32	    s_save_pc_hi, s_save_pc_hi, s_save_tmp
+    s_getreg_b32    s_save_tmp, hwreg(HW_REG_IB_STS)					    //clear RCNT and FIRST_REPLAY in IB_STS
+    s_and_b32	    s_save_tmp, s_save_tmp, SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK_NEG
+
+    s_setreg_b32    hwreg(HW_REG_IB_STS), s_save_tmp
+
+    /*	    inform SPI the readiness and wait for SPI's go signal */
+    s_mov_b32	    s_save_exec_lo, exec_lo						    //save EXEC and use EXEC for the go signal from SPI
+    s_mov_b32	    s_save_exec_hi, exec_hi
+    s_mov_b64	    exec,   0x0								    //clear EXEC to get ready to receive
+
+if G8SR_DEBUG_TIMESTAMP
+	s_memrealtime  s_g8sr_ts_sq_save_msg
+	s_waitcnt lgkmcnt(0)
+end
+
+    if (EMU_RUN_HACK)
+
+    else
+	s_sendmsg   sendmsg(MSG_SAVEWAVE)  //send SPI a message and wait for SPI's write to EXEC
+    end
+
+    // Set SPI_PRIO=2 to avoid starving instruction fetch in the waves we're waiting for.
+    s_or_b32 s_save_tmp, s_save_status, (2 << SQ_WAVE_STATUS_SPI_PRIO_SHIFT)
+    s_setreg_b32 hwreg(HW_REG_STATUS), s_save_tmp
+
+  L_SLEEP:
+    s_sleep 0x2		       // sleep 1 (64clk) is not enough for 8 waves per SIMD, which will cause SQ hang, since the 7,8th wave could not get arbit to exec inst, while other waves are stuck into the sleep-loop and waiting for wrexec!=0
+
+    if (EMU_RUN_HACK)
+
+    else
+	s_cbranch_execz L_SLEEP
+    end
+
+if G8SR_DEBUG_TIMESTAMP
+	s_memrealtime  s_g8sr_ts_spi_wrexec
+	s_waitcnt lgkmcnt(0)
+end
+
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_SAVE_SINGLE_WAVE))
+	//calculate wd_addr using absolute thread id
+	v_readlane_b32 s_save_tmp, v9, 0
+	s_lshr_b32 s_save_tmp, s_save_tmp, 6
+	s_mul_i32 s_save_tmp, s_save_tmp, WAVE_SPACE
+	s_add_i32 s_save_spi_init_lo, s_save_tmp, WG_BASE_ADDR_LO
+	s_mov_b32 s_save_spi_init_hi, WG_BASE_ADDR_HI
+	s_and_b32 s_save_spi_init_hi, s_save_spi_init_hi, CTX_SAVE_CONTROL
+    else
+    end
+    if ((EMU_RUN_HACK) && (EMU_RUN_HACK_SAVE_SINGLE_WAVE))
+	s_add_i32 s_save_spi_init_lo, s_save_tmp, WG_BASE_ADDR_LO
+	s_mov_b32 s_save_spi_init_hi, WG_BASE_ADDR_HI
+	s_and_b32 s_save_spi_init_hi, s_save_spi_init_hi, CTX_SAVE_CONTROL
+    else
+    end
+
+    // Save trap temporaries 6-11, 13-15 initialized by SPI debug dispatch logic
+    // ttmp SR memory offset : size(VGPR)+size(SGPR)+0x40
+    get_vgpr_size_bytes(s_save_ttmps_lo)
+    get_sgpr_size_bytes(s_save_ttmps_hi)
+    s_add_u32	    s_save_ttmps_lo, s_save_ttmps_lo, s_save_ttmps_hi
+    s_add_u32	    s_save_ttmps_lo, s_save_ttmps_lo, s_save_spi_init_lo
+    s_addc_u32	    s_save_ttmps_hi, s_save_spi_init_hi, 0x0
+    s_and_b32	    s_save_ttmps_hi, s_save_ttmps_hi, 0xFFFF
+    s_store_dwordx2 [ttmp6, ttmp7], [s_save_ttmps_lo, s_save_ttmps_hi], 0x40 glc:1
+    ack_sqc_store_workaround()
+    s_store_dwordx4 [ttmp8, ttmp9, ttmp10, ttmp11], [s_save_ttmps_lo, s_save_ttmps_hi], 0x48 glc:1
+    ack_sqc_store_workaround()
+    s_store_dword   ttmp13, [s_save_ttmps_lo, s_save_ttmps_hi], 0x58 glc:1
+    ack_sqc_store_workaround()
+    s_store_dwordx2 [ttmp14, ttmp15], [s_save_ttmps_lo, s_save_ttmps_hi], 0x5C glc:1
+    ack_sqc_store_workaround()
+
+    /*	    setup Resource Contants    */
+    s_mov_b32	    s_save_buf_rsrc0,	s_save_spi_init_lo							//base_addr_lo
+    s_and_b32	    s_save_buf_rsrc1,	s_save_spi_init_hi, 0x0000FFFF						//base_addr_hi
+    s_or_b32	    s_save_buf_rsrc1,	s_save_buf_rsrc1,  S_SAVE_BUF_RSRC_WORD1_STRIDE
+    s_mov_b32	    s_save_buf_rsrc2,	0									//NUM_RECORDS initial value = 0 (in bytes) although not neccessarily inited
+    s_mov_b32	    s_save_buf_rsrc3,	S_SAVE_BUF_RSRC_WORD3_MISC
+    s_and_b32	    s_save_tmp,		s_save_spi_init_hi, S_SAVE_SPI_INIT_ATC_MASK
+    s_lshr_b32	    s_save_tmp,		s_save_tmp, (S_SAVE_SPI_INIT_ATC_SHIFT-SQ_BUF_RSRC_WORD1_ATC_SHIFT)	    //get ATC bit into position
+    s_or_b32	    s_save_buf_rsrc3,	s_save_buf_rsrc3,  s_save_tmp						//or ATC
+    s_and_b32	    s_save_tmp,		s_save_spi_init_hi, S_SAVE_SPI_INIT_MTYPE_MASK
+    s_lshr_b32	    s_save_tmp,		s_save_tmp, (S_SAVE_SPI_INIT_MTYPE_SHIFT-SQ_BUF_RSRC_WORD3_MTYPE_SHIFT)	    //get MTYPE bits into position
+    s_or_b32	    s_save_buf_rsrc3,	s_save_buf_rsrc3,  s_save_tmp						//or MTYPE
+
+    //FIXME  right now s_save_m0/s_save_mem_offset use tma_lo/tma_hi  (might need to save them before using them?)
+    s_mov_b32	    s_save_m0,		m0								    //save M0
+
+    /*	    global mem offset		*/
+    s_mov_b32	    s_save_mem_offset,	0x0									//mem offset initial value = 0
+
+
+
+
+    /*	    save HW registers	*/
+    //////////////////////////////
+
+  L_SAVE_HWREG:
+	// HWREG SR memory offset : size(VGPR)+size(SGPR)
+       get_vgpr_size_bytes(s_save_mem_offset)
+       get_sgpr_size_bytes(s_save_tmp)
+       s_add_u32 s_save_mem_offset, s_save_mem_offset, s_save_tmp
+
+
+    s_mov_b32	    s_save_buf_rsrc2, 0x4				//NUM_RECORDS	in bytes
+    if (SWIZZLE_EN)
+	s_add_u32	s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0			    //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_save_buf_rsrc2,  0x1000000				    //NUM_RECORDS in bytes
+    end
+
+
+    write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)			//M0
+
+    if ((EMU_RUN_HACK) && (EMU_RUN_HACK_SAVE_FIRST_TIME))
+	s_add_u32 s_save_pc_lo, s_save_pc_lo, 4		    //pc[31:0]+4
+	s_addc_u32 s_save_pc_hi, s_save_pc_hi, 0x0	    //carry bit over
+    end
+
+    write_hwreg_to_mem(s_save_pc_lo, s_save_buf_rsrc0, s_save_mem_offset)		    //PC
+    write_hwreg_to_mem(s_save_pc_hi, s_save_buf_rsrc0, s_save_mem_offset)
+    write_hwreg_to_mem(s_save_exec_lo, s_save_buf_rsrc0, s_save_mem_offset)		//EXEC
+    write_hwreg_to_mem(s_save_exec_hi, s_save_buf_rsrc0, s_save_mem_offset)
+    write_hwreg_to_mem(s_save_status, s_save_buf_rsrc0, s_save_mem_offset)		//STATUS
+
+    //s_save_trapsts conflicts with s_save_alloc_size
+    s_getreg_b32    s_save_trapsts, hwreg(HW_REG_TRAPSTS)
+    write_hwreg_to_mem(s_save_trapsts, s_save_buf_rsrc0, s_save_mem_offset)		//TRAPSTS
+
+    write_hwreg_to_mem(xnack_mask_lo, s_save_buf_rsrc0, s_save_mem_offset)	    //XNACK_MASK_LO
+    write_hwreg_to_mem(xnack_mask_hi, s_save_buf_rsrc0, s_save_mem_offset)	    //XNACK_MASK_HI
+
+    //use s_save_tmp would introduce conflict here between s_save_tmp and s_save_buf_rsrc2
+    s_getreg_b32    s_save_m0, hwreg(HW_REG_MODE)						    //MODE
+    write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)
+
+
+
+    /*	    the first wave in the threadgroup	 */
+    s_and_b32	    s_save_tmp, s_save_spi_init_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK	// extract fisrt wave bit
+    s_mov_b32	     s_save_exec_hi, 0x0
+    s_or_b32	     s_save_exec_hi, s_save_tmp, s_save_exec_hi				 // save first wave bit to s_save_exec_hi.bits[26]
+
+
+    /*		save SGPRs	*/
+	// Save SGPR before LDS save, then the s0 to s4 can be used during LDS save...
+    //////////////////////////////
+
+    // SGPR SR memory offset : size(VGPR)
+    get_vgpr_size_bytes(s_save_mem_offset)
+    // TODO, change RSRC word to rearrange memory layout for SGPRS
+
+    s_getreg_b32    s_save_alloc_size, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SIZE)		//spgr_size
+    s_add_u32	    s_save_alloc_size, s_save_alloc_size, 1
+    s_lshl_b32	    s_save_alloc_size, s_save_alloc_size, 4			    //Number of SGPRs = (sgpr_size + 1) * 16   (non-zero value)
+
+    if (SGPR_SAVE_USE_SQC)
+	s_lshl_b32	s_save_buf_rsrc2,   s_save_alloc_size, 2		    //NUM_RECORDS in bytes
+    else
+	s_lshl_b32	s_save_buf_rsrc2,   s_save_alloc_size, 8		    //NUM_RECORDS in bytes (64 threads)
+    end
+
+    if (SWIZZLE_EN)
+	s_add_u32	s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0			    //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_save_buf_rsrc2,  0x1000000				    //NUM_RECORDS in bytes
+    end
+
+
+    // backup s_save_buf_rsrc0,1 to s_save_pc_lo/hi, since write_16sgpr_to_mem function will change the rsrc0
+    //s_mov_b64 s_save_pc_lo, s_save_buf_rsrc0
+    s_mov_b64 s_save_xnack_mask_lo, s_save_buf_rsrc0
+    s_add_u32 s_save_buf_rsrc0, s_save_buf_rsrc0, s_save_mem_offset
+    s_addc_u32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0
+
+    s_mov_b32	    m0, 0x0			    //SGPR initial index value =0
+    s_nop	    0x0				    //Manually inserted wait states
+  L_SAVE_SGPR_LOOP:
+    // SGPR is allocated in 16 SGPR granularity
+    s_movrels_b64   s0, s0     //s0 = s[0+m0], s1 = s[1+m0]
+    s_movrels_b64   s2, s2     //s2 = s[2+m0], s3 = s[3+m0]
+    s_movrels_b64   s4, s4     //s4 = s[4+m0], s5 = s[5+m0]
+    s_movrels_b64   s6, s6     //s6 = s[6+m0], s7 = s[7+m0]
+    s_movrels_b64   s8, s8     //s8 = s[8+m0], s9 = s[9+m0]
+    s_movrels_b64   s10, s10   //s10 = s[10+m0], s11 = s[11+m0]
+    s_movrels_b64   s12, s12   //s12 = s[12+m0], s13 = s[13+m0]
+    s_movrels_b64   s14, s14   //s14 = s[14+m0], s15 = s[15+m0]
+
+    write_16sgpr_to_mem(s0, s_save_buf_rsrc0, s_save_mem_offset) //PV: the best performance should be using s_buffer_store_dwordx4
+    s_add_u32	    m0, m0, 16							    //next sgpr index
+    s_cmp_lt_u32    m0, s_save_alloc_size					    //scc = (m0 < s_save_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_SAVE_SGPR_LOOP					//SGPR save is complete?
+    // restore s_save_buf_rsrc0,1
+    //s_mov_b64 s_save_buf_rsrc0, s_save_pc_lo
+    s_mov_b64 s_save_buf_rsrc0, s_save_xnack_mask_lo
+
+
+
+
+    /*		save first 4 VGPR, then LDS save could use   */
+	// each wave will alloc 4 vgprs at least...
+    /////////////////////////////////////////////////////////////////////////////////////
+
+    s_mov_b32	    s_save_mem_offset, 0
+    s_mov_b32	    exec_lo, 0xFFFFFFFF						    //need every thread from now on
+    s_mov_b32	    exec_hi, 0xFFFFFFFF
+    s_mov_b32	    xnack_mask_lo, 0x0
+    s_mov_b32	    xnack_mask_hi, 0x0
+
+    if (SWIZZLE_EN)
+	s_add_u32	s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0			    //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_save_buf_rsrc2,  0x1000000				    //NUM_RECORDS in bytes
+    end
+
+
+    // VGPR Allocated in 4-GPR granularity
+
+if G8SR_VGPR_SR_IN_DWX4
+	// the const stride for DWx4 is 4*4 bytes
+	s_and_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+	s_or_b32  s_save_buf_rsrc1, s_save_buf_rsrc1, G8SR_SAVE_BUF_RSRC_WORD1_STRIDE_DWx4  // const stride to 4*4 bytes
+
+	buffer_store_dwordx4 v0, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1
+
+	s_and_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+	s_or_b32  s_save_buf_rsrc1, s_save_buf_rsrc1, S_SAVE_BUF_RSRC_WORD1_STRIDE  // reset const stride to 4 bytes
+else
+	buffer_store_dword v0, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1
+	buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256
+	buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256*2
+	buffer_store_dword v3, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256*3
+end
+
+
+
+    /*		save LDS	*/
+    //////////////////////////////
+
+  L_SAVE_LDS:
+
+	// Change EXEC to all threads...
+    s_mov_b32	    exec_lo, 0xFFFFFFFF	  //need every thread from now on
+    s_mov_b32	    exec_hi, 0xFFFFFFFF
+
+    s_getreg_b32    s_save_alloc_size, hwreg(HW_REG_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE)		    //lds_size
+    s_and_b32	    s_save_alloc_size, s_save_alloc_size, 0xFFFFFFFF		    //lds_size is zero?
+    s_cbranch_scc0  L_SAVE_LDS_DONE									       //no lds used? jump to L_SAVE_DONE
+
+    s_barrier		    //LDS is used? wait for other waves in the same TG
+    s_and_b32	    s_save_tmp, s_save_exec_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK		       //exec is still used here
+    s_cbranch_scc0  L_SAVE_LDS_DONE
+
+	// first wave do LDS save;
+
+    s_lshl_b32	    s_save_alloc_size, s_save_alloc_size, 6			    //LDS size in dwords = lds_size * 64dw
+    s_lshl_b32	    s_save_alloc_size, s_save_alloc_size, 2			    //LDS size in bytes
+    s_mov_b32	    s_save_buf_rsrc2,  s_save_alloc_size			    //NUM_RECORDS in bytes
+
+    // LDS at offset: size(VGPR)+SIZE(SGPR)+SIZE(HWREG)
+    //
+    get_vgpr_size_bytes(s_save_mem_offset)
+    get_sgpr_size_bytes(s_save_tmp)
+    s_add_u32  s_save_mem_offset, s_save_mem_offset, s_save_tmp
+    s_add_u32 s_save_mem_offset, s_save_mem_offset, get_hwreg_size_bytes()
+
+
+    if (SWIZZLE_EN)
+	s_add_u32	s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0	      //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_save_buf_rsrc2,  0x1000000		      //NUM_RECORDS in bytes
+    end
+
+    s_mov_b32	    m0, 0x0						  //lds_offset initial value = 0
+
+
+var LDS_DMA_ENABLE = 0
+var UNROLL = 0
+if UNROLL==0 && LDS_DMA_ENABLE==1
+	s_mov_b32  s3, 256*2
+	s_nop 0
+	s_nop 0
+	s_nop 0
+  L_SAVE_LDS_LOOP:
+	//TODO: looks the 2 buffer_store/load clause for s/r will hurt performance.???
+    if (SAVE_LDS)     //SPI always alloc LDS space in 128DW granularity
+	    buffer_store_lds_dword s_save_buf_rsrc0, s_save_mem_offset lds:1		// first 64DW
+	    buffer_store_lds_dword s_save_buf_rsrc0, s_save_mem_offset lds:1 offset:256 // second 64DW
+    end
+
+    s_add_u32	    m0, m0, s3						//every buffer_store_lds does 256 bytes
+    s_add_u32	    s_save_mem_offset, s_save_mem_offset, s3				//mem offset increased by 256 bytes
+    s_cmp_lt_u32    m0, s_save_alloc_size						//scc=(m0 < s_save_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_SAVE_LDS_LOOP							//LDS save is complete?
+
+elsif LDS_DMA_ENABLE==1 && UNROLL==1 // UNROOL	, has ichace miss
+      // store from higest LDS address to lowest
+      s_mov_b32	 s3, 256*2
+      s_sub_u32	 m0, s_save_alloc_size, s3
+      s_add_u32 s_save_mem_offset, s_save_mem_offset, m0
+      s_lshr_b32 s_save_alloc_size, s_save_alloc_size, 9   // how many 128 trunks...
+      s_sub_u32 s_save_alloc_size, 128, s_save_alloc_size   // store from higheset addr to lowest
+      s_mul_i32 s_save_alloc_size, s_save_alloc_size, 6*4   // PC offset increment,  each LDS save block cost 6*4 Bytes instruction
+      s_add_u32 s_save_alloc_size, s_save_alloc_size, 3*4   //2is the below 2 inst...//s_addc and s_setpc
+      s_nop 0
+      s_nop 0
+      s_nop 0	//pad 3 dw to let LDS_DMA align with 64Bytes
+      s_getpc_b64 s[0:1]			      // reuse s[0:1], since s[0:1] already saved
+      s_add_u32	  s0, s0,s_save_alloc_size
+      s_addc_u32  s1, s1, 0
+      s_setpc_b64 s[0:1]
+
+
+       for var i =0; i< 128; i++
+	    // be careful to make here a 64Byte aligned address, which could improve performance...
+	    buffer_store_lds_dword s_save_buf_rsrc0, s_save_mem_offset lds:1 offset:0		// first 64DW
+	    buffer_store_lds_dword s_save_buf_rsrc0, s_save_mem_offset lds:1 offset:256		  // second 64DW
+
+	if i!=127
+	s_sub_u32  m0, m0, s3	   // use a sgpr to shrink 2DW-inst to 1DW inst to improve performance , i.e.  pack more LDS_DMA inst to one Cacheline
+	    s_sub_u32  s_save_mem_offset, s_save_mem_offset,  s3
+	    end
+       end
+
+else   // BUFFER_STORE
+      v_mbcnt_lo_u32_b32 v2, 0xffffffff, 0x0
+      v_mbcnt_hi_u32_b32 v3, 0xffffffff, v2	// tid
+      v_mul_i32_i24 v2, v3, 8	// tid*8
+      v_mov_b32 v3, 256*2
+      s_mov_b32 m0, 0x10000
+      s_mov_b32 s0, s_save_buf_rsrc3
+      s_and_b32 s_save_buf_rsrc3, s_save_buf_rsrc3, 0xFF7FFFFF	  // disable add_tid
+      s_or_b32 s_save_buf_rsrc3, s_save_buf_rsrc3, 0x58000   //DFMT
+
+L_SAVE_LDS_LOOP_VECTOR:
+      ds_read_b64 v[0:1], v2	//x =LDS[a], byte address
+      s_waitcnt lgkmcnt(0)
+      buffer_store_dwordx2  v[0:1], v2, s_save_buf_rsrc0, s_save_mem_offset offen:1  glc:1  slc:1
+//	s_waitcnt vmcnt(0)
+//	v_add_u32 v2, vcc[0:1], v2, v3
+      v_add_u32 v2, v2, v3
+      v_cmp_lt_u32 vcc[0:1], v2, s_save_alloc_size
+      s_cbranch_vccnz L_SAVE_LDS_LOOP_VECTOR
+
+      // restore rsrc3
+      s_mov_b32 s_save_buf_rsrc3, s0
+
+end
+
+L_SAVE_LDS_DONE:
+
+
+    /*		save VGPRs  - set the Rest VGPRs	*/
+    //////////////////////////////////////////////////////////////////////////////////////
+  L_SAVE_VGPR:
+    // VGPR SR memory offset: 0
+    // TODO rearrange the RSRC words to use swizzle for VGPR save...
+
+    s_mov_b32	    s_save_mem_offset, (0+256*4)				    // for the rest VGPRs
+    s_mov_b32	    exec_lo, 0xFFFFFFFF						    //need every thread from now on
+    s_mov_b32	    exec_hi, 0xFFFFFFFF
+
+    s_getreg_b32    s_save_alloc_size, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)		    //vpgr_size
+    s_add_u32	    s_save_alloc_size, s_save_alloc_size, 1
+    s_lshl_b32	    s_save_alloc_size, s_save_alloc_size, 2			    //Number of VGPRs = (vgpr_size + 1) * 4    (non-zero value)	  //FIXME for GFX, zero is possible
+    s_lshl_b32	    s_save_buf_rsrc2,  s_save_alloc_size, 8			    //NUM_RECORDS in bytes (64 threads*4)
+    if (SWIZZLE_EN)
+	s_add_u32	s_save_buf_rsrc2, s_save_buf_rsrc2, 0x0			    //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_save_buf_rsrc2,  0x1000000				    //NUM_RECORDS in bytes
+    end
+
+
+    // VGPR Allocated in 4-GPR granularity
+
+if G8SR_VGPR_SR_IN_DWX4
+	// the const stride for DWx4 is 4*4 bytes
+	s_and_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+	s_or_b32  s_save_buf_rsrc1, s_save_buf_rsrc1, G8SR_SAVE_BUF_RSRC_WORD1_STRIDE_DWx4  // const stride to 4*4 bytes
+
+	s_mov_b32	  m0, 4	    // skip first 4 VGPRs
+	s_cmp_lt_u32	  m0, s_save_alloc_size
+	s_cbranch_scc0	  L_SAVE_VGPR_LOOP_END	    // no more vgprs
+
+	s_set_gpr_idx_on  m0, 0x1   // This will change M0
+	s_add_u32	  s_save_alloc_size, s_save_alloc_size, 0x1000	// because above inst change m0
+L_SAVE_VGPR_LOOP:
+	v_mov_b32	  v0, v0   // v0 = v[0+m0]
+	v_mov_b32	  v1, v1
+	v_mov_b32	  v2, v2
+	v_mov_b32	  v3, v3
+
+
+	buffer_store_dwordx4 v0, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1
+	s_add_u32	  m0, m0, 4
+	s_add_u32	  s_save_mem_offset, s_save_mem_offset, 256*4
+	s_cmp_lt_u32	  m0, s_save_alloc_size
+    s_cbranch_scc1  L_SAVE_VGPR_LOOP						    //VGPR save is complete?
+    s_set_gpr_idx_off
+L_SAVE_VGPR_LOOP_END:
+
+	s_and_b32 s_save_buf_rsrc1, s_save_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+	s_or_b32  s_save_buf_rsrc1, s_save_buf_rsrc1, S_SAVE_BUF_RSRC_WORD1_STRIDE  // reset const stride to 4 bytes
+else
+    // VGPR store using dw burst
+    s_mov_b32	      m0, 0x4	//VGPR initial index value =0
+    s_cmp_lt_u32      m0, s_save_alloc_size
+    s_cbranch_scc0    L_SAVE_VGPR_END
+
+
+    s_set_gpr_idx_on	m0, 0x1 //M0[7:0] = M0[7:0] and M0[15:12] = 0x1
+    s_add_u32	    s_save_alloc_size, s_save_alloc_size, 0x1000		    //add 0x1000 since we compare m0 against it later
+
+  L_SAVE_VGPR_LOOP:
+    v_mov_b32	    v0, v0		//v0 = v[0+m0]
+    v_mov_b32	    v1, v1		//v0 = v[0+m0]
+    v_mov_b32	    v2, v2		//v0 = v[0+m0]
+    v_mov_b32	    v3, v3		//v0 = v[0+m0]
+
+    if(USE_MTBUF_INSTEAD_OF_MUBUF)
+	tbuffer_store_format_x v0, v0, s_save_buf_rsrc0, s_save_mem_offset format:BUF_NUM_FORMAT_FLOAT format: BUF_DATA_FORMAT_32 slc:1 glc:1
+    else
+	buffer_store_dword v0, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1
+	buffer_store_dword v1, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256
+	buffer_store_dword v2, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256*2
+	buffer_store_dword v3, v0, s_save_buf_rsrc0, s_save_mem_offset slc:1 glc:1  offset:256*3
+    end
+
+    s_add_u32	    m0, m0, 4							    //next vgpr index
+    s_add_u32	    s_save_mem_offset, s_save_mem_offset, 256*4			    //every buffer_store_dword does 256 bytes
+    s_cmp_lt_u32    m0, s_save_alloc_size					    //scc = (m0 < s_save_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_SAVE_VGPR_LOOP						    //VGPR save is complete?
+    s_set_gpr_idx_off
+end
+
+L_SAVE_VGPR_END:
+
+
+
+
+
+
+    /*	   S_PGM_END_SAVED  */				    //FIXME  graphics ONLY
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_SAVE_NORMAL_EXIT))
+	s_and_b32 s_save_pc_hi, s_save_pc_hi, 0x0000ffff    //pc[47:32]
+	s_add_u32 s_save_pc_lo, s_save_pc_lo, 4		    //pc[31:0]+4
+	s_addc_u32 s_save_pc_hi, s_save_pc_hi, 0x0	    //carry bit over
+	s_rfe_b64 s_save_pc_lo				    //Return to the main shader program
+    else
+    end
+
+// Save Done timestamp
+if G8SR_DEBUG_TIMESTAMP
+	s_memrealtime	s_g8sr_ts_save_d
+	// SGPR SR memory offset : size(VGPR)
+	get_vgpr_size_bytes(s_save_mem_offset)
+	s_add_u32 s_save_mem_offset, s_save_mem_offset, G8SR_DEBUG_TS_SAVE_D_OFFSET
+	s_waitcnt lgkmcnt(0)	     //FIXME, will cause xnack??
+	// Need reset rsrc2??
+	s_mov_b32 m0, s_save_mem_offset
+	s_mov_b32 s_save_buf_rsrc2,  0x1000000					//NUM_RECORDS in bytes
+	s_buffer_store_dwordx2 s_g8sr_ts_save_d, s_save_buf_rsrc0, m0	    glc:1
+end
+
+
+    s_branch	L_END_PGM
+
+
+
+/**************************************************************************/
+/*			restore routine					  */
+/**************************************************************************/
+
+L_RESTORE:
+    /*	    Setup Resource Contants    */
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_RESTORE_NORMAL))
+	//calculate wd_addr using absolute thread id
+	v_readlane_b32 s_restore_tmp, v9, 0
+	s_lshr_b32 s_restore_tmp, s_restore_tmp, 6
+	s_mul_i32 s_restore_tmp, s_restore_tmp, WAVE_SPACE
+	s_add_i32 s_restore_spi_init_lo, s_restore_tmp, WG_BASE_ADDR_LO
+	s_mov_b32 s_restore_spi_init_hi, WG_BASE_ADDR_HI
+	s_and_b32 s_restore_spi_init_hi, s_restore_spi_init_hi, CTX_RESTORE_CONTROL
+    else
+    end
+
+if G8SR_DEBUG_TIMESTAMP
+	s_memrealtime	s_g8sr_ts_restore_s
+	s_waitcnt lgkmcnt(0)	     //FIXME, will cause xnack??
+	// tma_lo/hi are sgpr 110, 111, which will not used for 112 SGPR allocated case...
+	s_mov_b32 s_restore_pc_lo, s_g8sr_ts_restore_s[0]
+	s_mov_b32 s_restore_pc_hi, s_g8sr_ts_restore_s[1]   //backup ts to ttmp0/1, sicne exec will be finally restored..
+end
+
+
+
+    s_mov_b32	    s_restore_buf_rsrc0,    s_restore_spi_init_lo							    //base_addr_lo
+    s_and_b32	    s_restore_buf_rsrc1,    s_restore_spi_init_hi, 0x0000FFFF						    //base_addr_hi
+    s_or_b32	    s_restore_buf_rsrc1,    s_restore_buf_rsrc1,  S_RESTORE_BUF_RSRC_WORD1_STRIDE
+    s_mov_b32	    s_restore_buf_rsrc2,    0										    //NUM_RECORDS initial value = 0 (in bytes)
+    s_mov_b32	    s_restore_buf_rsrc3,    S_RESTORE_BUF_RSRC_WORD3_MISC
+    s_and_b32	    s_restore_tmp,	    s_restore_spi_init_hi, S_RESTORE_SPI_INIT_ATC_MASK
+    s_lshr_b32	    s_restore_tmp,	    s_restore_tmp, (S_RESTORE_SPI_INIT_ATC_SHIFT-SQ_BUF_RSRC_WORD1_ATC_SHIFT)	    //get ATC bit into position
+    s_or_b32	    s_restore_buf_rsrc3,    s_restore_buf_rsrc3,  s_restore_tmp						    //or ATC
+    s_and_b32	    s_restore_tmp,	    s_restore_spi_init_hi, S_RESTORE_SPI_INIT_MTYPE_MASK
+    s_lshr_b32	    s_restore_tmp,	    s_restore_tmp, (S_RESTORE_SPI_INIT_MTYPE_SHIFT-SQ_BUF_RSRC_WORD3_MTYPE_SHIFT)   //get MTYPE bits into position
+    s_or_b32	    s_restore_buf_rsrc3,    s_restore_buf_rsrc3,  s_restore_tmp						    //or MTYPE
+
+    /*	    global mem offset		*/
+//  s_mov_b32	    s_restore_mem_offset, 0x0				    //mem offset initial value = 0
+
+    /*	    the first wave in the threadgroup	 */
+    s_and_b32	    s_restore_tmp, s_restore_spi_init_hi, S_RESTORE_SPI_INIT_FIRST_WAVE_MASK
+    s_cbranch_scc0  L_RESTORE_VGPR
+
+    /*		restore LDS	*/
+    //////////////////////////////
+  L_RESTORE_LDS:
+
+    s_mov_b32	    exec_lo, 0xFFFFFFFF							    //need every thread from now on   //be consistent with SAVE although can be moved ahead
+    s_mov_b32	    exec_hi, 0xFFFFFFFF
+
+    s_getreg_b32    s_restore_alloc_size, hwreg(HW_REG_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE)		//lds_size
+    s_and_b32	    s_restore_alloc_size, s_restore_alloc_size, 0xFFFFFFFF		    //lds_size is zero?
+    s_cbranch_scc0  L_RESTORE_VGPR							    //no lds used? jump to L_RESTORE_VGPR
+    s_lshl_b32	    s_restore_alloc_size, s_restore_alloc_size, 6			    //LDS size in dwords = lds_size * 64dw
+    s_lshl_b32	    s_restore_alloc_size, s_restore_alloc_size, 2			    //LDS size in bytes
+    s_mov_b32	    s_restore_buf_rsrc2,    s_restore_alloc_size			    //NUM_RECORDS in bytes
+
+    // LDS at offset: size(VGPR)+SIZE(SGPR)+SIZE(HWREG)
+    //
+    get_vgpr_size_bytes(s_restore_mem_offset)
+    get_sgpr_size_bytes(s_restore_tmp)
+    s_add_u32  s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+    s_add_u32  s_restore_mem_offset, s_restore_mem_offset, get_hwreg_size_bytes()	     //FIXME, Check if offset overflow???
+
+
+    if (SWIZZLE_EN)
+	s_add_u32	s_restore_buf_rsrc2, s_restore_buf_rsrc2, 0x0			    //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_restore_buf_rsrc2,  0x1000000					    //NUM_RECORDS in bytes
+    end
+    s_mov_b32	    m0, 0x0								    //lds_offset initial value = 0
+
+  L_RESTORE_LDS_LOOP:
+    if (SAVE_LDS)
+	buffer_load_dword   v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset lds:1		       // first 64DW
+	buffer_load_dword   v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset lds:1 offset:256	       // second 64DW
+    end
+    s_add_u32	    m0, m0, 256*2						// 128 DW
+    s_add_u32	    s_restore_mem_offset, s_restore_mem_offset, 256*2		//mem offset increased by 128DW
+    s_cmp_lt_u32    m0, s_restore_alloc_size					//scc=(m0 < s_restore_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_RESTORE_LDS_LOOP							    //LDS restore is complete?
+
+
+    /*		restore VGPRs	    */
+    //////////////////////////////
+  L_RESTORE_VGPR:
+	// VGPR SR memory offset : 0
+    s_mov_b32	    s_restore_mem_offset, 0x0
+    s_mov_b32	    exec_lo, 0xFFFFFFFF							    //need every thread from now on   //be consistent with SAVE although can be moved ahead
+    s_mov_b32	    exec_hi, 0xFFFFFFFF
+
+    s_getreg_b32    s_restore_alloc_size, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)	//vpgr_size
+    s_add_u32	    s_restore_alloc_size, s_restore_alloc_size, 1
+    s_lshl_b32	    s_restore_alloc_size, s_restore_alloc_size, 2			    //Number of VGPRs = (vgpr_size + 1) * 4    (non-zero value)
+    s_lshl_b32	    s_restore_buf_rsrc2,  s_restore_alloc_size, 8			    //NUM_RECORDS in bytes (64 threads*4)
+    if (SWIZZLE_EN)
+	s_add_u32	s_restore_buf_rsrc2, s_restore_buf_rsrc2, 0x0			    //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_restore_buf_rsrc2,  0x1000000					    //NUM_RECORDS in bytes
+    end
+
+if G8SR_VGPR_SR_IN_DWX4
+     get_vgpr_size_bytes(s_restore_mem_offset)
+     s_sub_u32	       s_restore_mem_offset, s_restore_mem_offset, 256*4
+
+     // the const stride for DWx4 is 4*4 bytes
+     s_and_b32 s_restore_buf_rsrc1, s_restore_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+     s_or_b32  s_restore_buf_rsrc1, s_restore_buf_rsrc1, G8SR_RESTORE_BUF_RSRC_WORD1_STRIDE_DWx4  // const stride to 4*4 bytes
+
+     s_mov_b32	       m0, s_restore_alloc_size
+     s_set_gpr_idx_on  m0, 0x8	  // Note.. This will change m0
+
+L_RESTORE_VGPR_LOOP:
+     buffer_load_dwordx4 v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1
+     s_waitcnt vmcnt(0)
+     s_sub_u32	       m0, m0, 4
+     v_mov_b32	       v0, v0	// v[0+m0] = v0
+     v_mov_b32	       v1, v1
+     v_mov_b32	       v2, v2
+     v_mov_b32	       v3, v3
+     s_sub_u32	       s_restore_mem_offset, s_restore_mem_offset, 256*4
+     s_cmp_eq_u32      m0, 0x8000
+     s_cbranch_scc0    L_RESTORE_VGPR_LOOP
+     s_set_gpr_idx_off
+
+     s_and_b32 s_restore_buf_rsrc1, s_restore_buf_rsrc1, 0x0000FFFF   // reset const stride to 0
+     s_or_b32  s_restore_buf_rsrc1, s_restore_buf_rsrc1, S_RESTORE_BUF_RSRC_WORD1_STRIDE  // const stride to 4*4 bytes
+
+else
+    // VGPR load using dw burst
+    s_mov_b32	    s_restore_mem_offset_save, s_restore_mem_offset	// restore start with v1, v0 will be the last
+    s_add_u32	    s_restore_mem_offset, s_restore_mem_offset, 256*4
+    s_mov_b32	    m0, 4				//VGPR initial index value = 1
+    s_set_gpr_idx_on  m0, 0x8			    //M0[7:0] = M0[7:0] and M0[15:12] = 0x8
+    s_add_u32	    s_restore_alloc_size, s_restore_alloc_size, 0x8000			    //add 0x8000 since we compare m0 against it later
+
+  L_RESTORE_VGPR_LOOP:
+    if(USE_MTBUF_INSTEAD_OF_MUBUF)
+	tbuffer_load_format_x v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset format:BUF_NUM_FORMAT_FLOAT format: BUF_DATA_FORMAT_32 slc:1 glc:1
+    else
+	buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1
+	buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1 offset:256
+	buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1 offset:256*2
+	buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset slc:1 glc:1 offset:256*3
+    end
+    s_waitcnt	    vmcnt(0)								    //ensure data ready
+    v_mov_b32	    v0, v0								    //v[0+m0] = v0
+    v_mov_b32	    v1, v1
+    v_mov_b32	    v2, v2
+    v_mov_b32	    v3, v3
+    s_add_u32	    m0, m0, 4								    //next vgpr index
+    s_add_u32	    s_restore_mem_offset, s_restore_mem_offset, 256*4				//every buffer_load_dword does 256 bytes
+    s_cmp_lt_u32    m0, s_restore_alloc_size						    //scc = (m0 < s_restore_alloc_size) ? 1 : 0
+    s_cbranch_scc1  L_RESTORE_VGPR_LOOP							    //VGPR restore (except v0) is complete?
+    s_set_gpr_idx_off
+											    /* VGPR restore on v0 */
+    if(USE_MTBUF_INSTEAD_OF_MUBUF)
+	tbuffer_load_format_x v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save format:BUF_NUM_FORMAT_FLOAT format: BUF_DATA_FORMAT_32 slc:1 glc:1
+    else
+	buffer_load_dword v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save    slc:1 glc:1
+	buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save    slc:1 glc:1 offset:256
+	buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save    slc:1 glc:1 offset:256*2
+	buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save    slc:1 glc:1 offset:256*3
+    end
+
+end
+
+    /*		restore SGPRs	    */
+    //////////////////////////////
+
+    // SGPR SR memory offset : size(VGPR)
+    get_vgpr_size_bytes(s_restore_mem_offset)
+    get_sgpr_size_bytes(s_restore_tmp)
+    s_add_u32 s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+    s_sub_u32 s_restore_mem_offset, s_restore_mem_offset, 16*4	   // restore SGPR from S[n] to S[0], by 16 sgprs group
+    // TODO, change RSRC word to rearrange memory layout for SGPRS
+
+    s_getreg_b32    s_restore_alloc_size, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SIZE)		    //spgr_size
+    s_add_u32	    s_restore_alloc_size, s_restore_alloc_size, 1
+    s_lshl_b32	    s_restore_alloc_size, s_restore_alloc_size, 4			    //Number of SGPRs = (sgpr_size + 1) * 16   (non-zero value)
+
+    if (SGPR_SAVE_USE_SQC)
+	s_lshl_b32	s_restore_buf_rsrc2,	s_restore_alloc_size, 2			    //NUM_RECORDS in bytes
+    else
+	s_lshl_b32	s_restore_buf_rsrc2,	s_restore_alloc_size, 8			    //NUM_RECORDS in bytes (64 threads)
+    end
+    if (SWIZZLE_EN)
+	s_add_u32	s_restore_buf_rsrc2, s_restore_buf_rsrc2, 0x0			    //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_restore_buf_rsrc2,  0x1000000					    //NUM_RECORDS in bytes
+    end
+
+    s_mov_b32 m0, s_restore_alloc_size
+
+ L_RESTORE_SGPR_LOOP:
+    read_16sgpr_from_mem(s0, s_restore_buf_rsrc0, s_restore_mem_offset)	 //PV: further performance improvement can be made
+    s_waitcnt	    lgkmcnt(0)								    //ensure data ready
+
+    s_sub_u32 m0, m0, 16    // Restore from S[n] to S[0]
+    s_nop 0 // hazard SALU M0=> S_MOVREL
+
+    s_movreld_b64   s0, s0	//s[0+m0] = s0
+    s_movreld_b64   s2, s2
+    s_movreld_b64   s4, s4
+    s_movreld_b64   s6, s6
+    s_movreld_b64   s8, s8
+    s_movreld_b64   s10, s10
+    s_movreld_b64   s12, s12
+    s_movreld_b64   s14, s14
+
+    s_cmp_eq_u32    m0, 0		//scc = (m0 < s_restore_alloc_size) ? 1 : 0
+    s_cbranch_scc0  L_RESTORE_SGPR_LOOP		    //SGPR restore (except s0) is complete?
+
+    /*	    restore HW registers    */
+    //////////////////////////////
+  L_RESTORE_HWREG:
+
+
+if G8SR_DEBUG_TIMESTAMP
+      s_mov_b32 s_g8sr_ts_restore_s[0], s_restore_pc_lo
+      s_mov_b32 s_g8sr_ts_restore_s[1], s_restore_pc_hi
+end
+
+    // HWREG SR memory offset : size(VGPR)+size(SGPR)
+    get_vgpr_size_bytes(s_restore_mem_offset)
+    get_sgpr_size_bytes(s_restore_tmp)
+    s_add_u32 s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+
+
+    s_mov_b32	    s_restore_buf_rsrc2, 0x4						    //NUM_RECORDS   in bytes
+    if (SWIZZLE_EN)
+	s_add_u32	s_restore_buf_rsrc2, s_restore_buf_rsrc2, 0x0			    //FIXME need to use swizzle to enable bounds checking?
+    else
+	s_mov_b32	s_restore_buf_rsrc2,  0x1000000					    //NUM_RECORDS in bytes
+    end
+
+    read_hwreg_from_mem(s_restore_m0, s_restore_buf_rsrc0, s_restore_mem_offset)		    //M0
+    read_hwreg_from_mem(s_restore_pc_lo, s_restore_buf_rsrc0, s_restore_mem_offset)		//PC
+    read_hwreg_from_mem(s_restore_pc_hi, s_restore_buf_rsrc0, s_restore_mem_offset)
+    read_hwreg_from_mem(s_restore_exec_lo, s_restore_buf_rsrc0, s_restore_mem_offset)		    //EXEC
+    read_hwreg_from_mem(s_restore_exec_hi, s_restore_buf_rsrc0, s_restore_mem_offset)
+    read_hwreg_from_mem(s_restore_status, s_restore_buf_rsrc0, s_restore_mem_offset)		    //STATUS
+    read_hwreg_from_mem(s_restore_trapsts, s_restore_buf_rsrc0, s_restore_mem_offset)		    //TRAPSTS
+    read_hwreg_from_mem(xnack_mask_lo, s_restore_buf_rsrc0, s_restore_mem_offset)		    //XNACK_MASK_LO
+    read_hwreg_from_mem(xnack_mask_hi, s_restore_buf_rsrc0, s_restore_mem_offset)		    //XNACK_MASK_HI
+    read_hwreg_from_mem(s_restore_mode, s_restore_buf_rsrc0, s_restore_mem_offset)		//MODE
+
+    s_waitcnt	    lgkmcnt(0)											    //from now on, it is safe to restore STATUS and IB_STS
+
+    //for normal save & restore, the saved PC points to the next inst to execute, no adjustment needs to be made, otherwise:
+    if ((EMU_RUN_HACK) && (!EMU_RUN_HACK_RESTORE_NORMAL))
+	s_add_u32 s_restore_pc_lo, s_restore_pc_lo, 8		 //pc[31:0]+8	  //two back-to-back s_trap are used (first for save and second for restore)
+	s_addc_u32  s_restore_pc_hi, s_restore_pc_hi, 0x0	 //carry bit over
+    end
+    if ((EMU_RUN_HACK) && (EMU_RUN_HACK_RESTORE_NORMAL))
+	s_add_u32 s_restore_pc_lo, s_restore_pc_lo, 4		 //pc[31:0]+4	  // save is hack through s_trap but restore is normal
+	s_addc_u32  s_restore_pc_hi, s_restore_pc_hi, 0x0	 //carry bit over
+    end
+
+    s_mov_b32	    m0,		s_restore_m0
+    s_mov_b32	    exec_lo,	s_restore_exec_lo
+    s_mov_b32	    exec_hi,	s_restore_exec_hi
+
+    s_and_b32	    s_restore_m0, SQ_WAVE_TRAPSTS_PRE_SAVECTX_MASK, s_restore_trapsts
+    s_setreg_b32    hwreg(HW_REG_TRAPSTS, SQ_WAVE_TRAPSTS_PRE_SAVECTX_SHIFT, SQ_WAVE_TRAPSTS_PRE_SAVECTX_SIZE), s_restore_m0
+    s_and_b32	    s_restore_m0, SQ_WAVE_TRAPSTS_POST_SAVECTX_MASK, s_restore_trapsts
+    s_lshr_b32	    s_restore_m0, s_restore_m0, SQ_WAVE_TRAPSTS_POST_SAVECTX_SHIFT
+    s_setreg_b32    hwreg(HW_REG_TRAPSTS, SQ_WAVE_TRAPSTS_POST_SAVECTX_SHIFT, SQ_WAVE_TRAPSTS_POST_SAVECTX_SIZE), s_restore_m0
+    //s_setreg_b32  hwreg(HW_REG_TRAPSTS),  s_restore_trapsts	   //don't overwrite SAVECTX bit as it may be set through external SAVECTX during restore
+    s_setreg_b32    hwreg(HW_REG_MODE),	    s_restore_mode
+
+    // Restore trap temporaries 6-11, 13-15 initialized by SPI debug dispatch logic
+    // ttmp SR memory offset : size(VGPR)+size(SGPR)+0x40
+    get_vgpr_size_bytes(s_restore_ttmps_lo)
+    get_sgpr_size_bytes(s_restore_ttmps_hi)
+    s_add_u32	    s_restore_ttmps_lo, s_restore_ttmps_lo, s_restore_ttmps_hi
+    s_add_u32	    s_restore_ttmps_lo, s_restore_ttmps_lo, s_restore_buf_rsrc0
+    s_addc_u32	    s_restore_ttmps_hi, s_restore_buf_rsrc1, 0x0
+    s_and_b32	    s_restore_ttmps_hi, s_restore_ttmps_hi, 0xFFFF
+    s_load_dwordx2  [ttmp6, ttmp7], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x40 glc:1
+    s_load_dwordx4  [ttmp8, ttmp9, ttmp10, ttmp11], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x48 glc:1
+    s_load_dword    ttmp13, [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x58 glc:1
+    s_load_dwordx2  [ttmp14, ttmp15], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x5C glc:1
+    s_waitcnt	    lgkmcnt(0)
+
+    //reuse s_restore_m0 as a temp register
+    s_and_b32	    s_restore_m0, s_restore_pc_hi, S_SAVE_PC_HI_RCNT_MASK
+    s_lshr_b32	    s_restore_m0, s_restore_m0, S_SAVE_PC_HI_RCNT_SHIFT
+    s_lshl_b32	    s_restore_m0, s_restore_m0, SQ_WAVE_IB_STS_RCNT_SHIFT
+    s_mov_b32	    s_restore_tmp, 0x0										    //IB_STS is zero
+    s_or_b32	    s_restore_tmp, s_restore_tmp, s_restore_m0
+    s_and_b32	    s_restore_m0, s_restore_pc_hi, S_SAVE_PC_HI_FIRST_REPLAY_MASK
+    s_lshr_b32	    s_restore_m0, s_restore_m0, S_SAVE_PC_HI_FIRST_REPLAY_SHIFT
+    s_lshl_b32	    s_restore_m0, s_restore_m0, SQ_WAVE_IB_STS_FIRST_REPLAY_SHIFT
+    s_or_b32	    s_restore_tmp, s_restore_tmp, s_restore_m0
+    s_and_b32	    s_restore_m0, s_restore_status, SQ_WAVE_STATUS_INST_ATC_MASK
+    s_lshr_b32	    s_restore_m0, s_restore_m0, SQ_WAVE_STATUS_INST_ATC_SHIFT
+    s_setreg_b32    hwreg(HW_REG_IB_STS),   s_restore_tmp
+
+    s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff	//pc[47:32]	   //Do it here in order not to affect STATUS
+    s_and_b64	 exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
+    s_and_b64	 vcc, vcc, vcc	// Restore STATUS.VCCZ, not writable by s_setreg_b32
+    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status	 // SCC is included, which is changed by previous salu
+
+    s_barrier							//barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
+
+if G8SR_DEBUG_TIMESTAMP
+    s_memrealtime s_g8sr_ts_restore_d
+    s_waitcnt lgkmcnt(0)
+end
+
+//  s_rfe_b64 s_restore_pc_lo					//Return to the main shader program and resume execution
+    s_rfe_restore_b64  s_restore_pc_lo, s_restore_m0		// s_restore_m0[0] is used to set STATUS.inst_atc
+
+
+/**************************************************************************/
+/*			the END						  */
+/**************************************************************************/
+L_END_PGM:
+    s_endpgm
+
+end
+
+
+/**************************************************************************/
+/*			the helper functions				  */
+/**************************************************************************/
+
+//Only for save hwreg to mem
+function write_hwreg_to_mem(s, s_rsrc, s_mem_offset)
+	s_mov_b32 exec_lo, m0			//assuming exec_lo is not needed anymore from this point on
+	s_mov_b32 m0, s_mem_offset
+	s_buffer_store_dword s, s_rsrc, m0	glc:1
+	ack_sqc_store_workaround()
+	s_add_u32	s_mem_offset, s_mem_offset, 4
+	s_mov_b32   m0, exec_lo
+end
+
+
+// HWREG are saved before SGPRs, so all HWREG could be use.
+function write_16sgpr_to_mem(s, s_rsrc, s_mem_offset)
+
+	s_buffer_store_dwordx4 s[0], s_rsrc, 0	glc:1
+	ack_sqc_store_workaround()
+	s_buffer_store_dwordx4 s[4], s_rsrc, 16	 glc:1
+	ack_sqc_store_workaround()
+	s_buffer_store_dwordx4 s[8], s_rsrc, 32	 glc:1
+	ack_sqc_store_workaround()
+	s_buffer_store_dwordx4 s[12], s_rsrc, 48 glc:1
+	ack_sqc_store_workaround()
+	s_add_u32	s_rsrc[0], s_rsrc[0], 4*16
+	s_addc_u32	s_rsrc[1], s_rsrc[1], 0x0	      // +scc
+end
+
+
+function read_hwreg_from_mem(s, s_rsrc, s_mem_offset)
+    s_buffer_load_dword s, s_rsrc, s_mem_offset	    glc:1
+    s_add_u32	    s_mem_offset, s_mem_offset, 4
+end
+
+function read_16sgpr_from_mem(s, s_rsrc, s_mem_offset)
+    s_buffer_load_dwordx16 s, s_rsrc, s_mem_offset	glc:1
+    s_sub_u32	    s_mem_offset, s_mem_offset, 4*16
+end
+
+
+
+function get_lds_size_bytes(s_lds_size_byte)
+    // SQ LDS granularity is 64DW, while PGM_RSRC2.lds_size is in granularity 128DW
+    s_getreg_b32   s_lds_size_byte, hwreg(HW_REG_LDS_ALLOC, SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT, SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE)		// lds_size
+    s_lshl_b32	   s_lds_size_byte, s_lds_size_byte, 8			    //LDS size in dwords = lds_size * 64 *4Bytes    // granularity 64DW
+end
+
+function get_vgpr_size_bytes(s_vgpr_size_byte)
+    s_getreg_b32   s_vgpr_size_byte, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)	 //vpgr_size
+    s_add_u32	   s_vgpr_size_byte, s_vgpr_size_byte, 1
+    s_lshl_b32	   s_vgpr_size_byte, s_vgpr_size_byte, (2+8) //Number of VGPRs = (vgpr_size + 1) * 4 * 64 * 4	(non-zero value)   //FIXME for GFX, zero is possible
+end
+
+function get_sgpr_size_bytes(s_sgpr_size_byte)
+    s_getreg_b32   s_sgpr_size_byte, hwreg(HW_REG_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_SGPR_SIZE_SIZE)	 //spgr_size
+    s_add_u32	   s_sgpr_size_byte, s_sgpr_size_byte, 1
+    s_lshl_b32	   s_sgpr_size_byte, s_sgpr_size_byte, 6 //Number of SGPRs = (sgpr_size + 1) * 16 *4   (non-zero value)
+end
+
+function get_hwreg_size_bytes
+    return 128 //HWREG size 128 bytes
+end
+
+function ack_sqc_store_workaround
+    if ACK_SQC_STORE
+        s_waitcnt lgkmcnt(0)
+    end
+end
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index cd679cf1fd30..f64c5551cdba 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -233,7 +233,7 @@ static int set_queue_properties_from_user(struct queue_properties *q_properties,
 	pr_debug("Queue Size: 0x%llX, %u\n",
 			q_properties->queue_size, args->ring_size);
 
-	pr_debug("Queue r/w Pointers: %p, %p\n",
+	pr_debug("Queue r/w Pointers: %px, %px\n",
 			q_properties->read_ptr,
 			q_properties->write_ptr);
 
@@ -292,8 +292,16 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 
 
 	/* Return gpu_id as doorbell offset for mmap usage */
-	args->doorbell_offset = (KFD_MMAP_DOORBELL_MASK | args->gpu_id);
+	args->doorbell_offset = KFD_MMAP_TYPE_DOORBELL;
+	args->doorbell_offset |= KFD_MMAP_GPU_ID(args->gpu_id);
 	args->doorbell_offset <<= PAGE_SHIFT;
+	if (KFD_IS_SOC15(dev->device_info->asic_family))
+		/* On SOC15 ASICs, doorbell allocation must be
+		 * per-device, and independent from the per-process
+		 * queue_id. Return the doorbell offset within the
+		 * doorbell aperture to user mode.
+		 */
+		args->doorbell_offset |= q_properties.doorbell_off;
 
 	mutex_unlock(&p->mutex);
 
@@ -749,12 +757,13 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 	struct timespec64 time;
 
 	dev = kfd_device_by_id(args->gpu_id);
-	if (dev == NULL)
-		return -EINVAL;
-
-	/* Reading GPU clock counter from KGD */
-	args->gpu_clock_counter =
-		dev->kfd2kgd->get_gpu_clock_counter(dev->kgd);
+	if (dev)
+		/* Reading GPU clock counter from KGD */
+		args->gpu_clock_counter =
+			dev->kfd2kgd->get_gpu_clock_counter(dev->kgd);
+	else
+		/* Node without GPU resource */
+		args->gpu_clock_counter = 0;
 
 	/* No access to rdtsc. Using raw monotonic time */
 	getrawmonotonic64(&time);
@@ -1147,7 +1156,7 @@ err_unlock:
 	return ret;
 }
 
-bool kfd_dev_is_large_bar(struct kfd_dev *dev)
+static bool kfd_dev_is_large_bar(struct kfd_dev *dev)
 {
 	struct kfd_local_mem_info mem_info;
 
@@ -1295,8 +1304,8 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 		return -EINVAL;
 	}
 
-	devices_arr = kmalloc(args->n_devices * sizeof(*devices_arr),
-			      GFP_KERNEL);
+	devices_arr = kmalloc_array(args->n_devices, sizeof(*devices_arr),
+				    GFP_KERNEL);
 	if (!devices_arr)
 		return -ENOMEM;
 
@@ -1404,8 +1413,8 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 		return -EINVAL;
 	}
 
-	devices_arr = kmalloc(args->n_devices * sizeof(*devices_arr),
-			      GFP_KERNEL);
+	devices_arr = kmalloc_array(args->n_devices, sizeof(*devices_arr),
+				    GFP_KERNEL);
 	if (!devices_arr)
 		return -ENOMEM;
 
@@ -1421,7 +1430,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 
 	pdd = kfd_get_process_device_data(dev, p);
 	if (!pdd) {
-		err = PTR_ERR(pdd);
+		err = -EINVAL;
 		goto bind_process_to_device_failed;
 	}
 
@@ -1644,23 +1653,33 @@ err_i1:
 static int kfd_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct kfd_process *process;
+	struct kfd_dev *dev = NULL;
+	unsigned long vm_pgoff;
+	unsigned int gpu_id;
 
 	process = kfd_get_process(current);
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
-	if ((vma->vm_pgoff & KFD_MMAP_DOORBELL_MASK) ==
-			KFD_MMAP_DOORBELL_MASK) {
-		vma->vm_pgoff = vma->vm_pgoff ^ KFD_MMAP_DOORBELL_MASK;
-		return kfd_doorbell_mmap(process, vma);
-	} else if ((vma->vm_pgoff & KFD_MMAP_EVENTS_MASK) ==
-			KFD_MMAP_EVENTS_MASK) {
-		vma->vm_pgoff = vma->vm_pgoff ^ KFD_MMAP_EVENTS_MASK;
+	vm_pgoff = vma->vm_pgoff;
+	vma->vm_pgoff = KFD_MMAP_OFFSET_VALUE_GET(vm_pgoff);
+	gpu_id = KFD_MMAP_GPU_ID_GET(vm_pgoff);
+	if (gpu_id)
+		dev = kfd_device_by_id(gpu_id);
+
+	switch (vm_pgoff & KFD_MMAP_TYPE_MASK) {
+	case KFD_MMAP_TYPE_DOORBELL:
+		if (!dev)
+			return -ENODEV;
+		return kfd_doorbell_mmap(dev, process, vma);
+
+	case KFD_MMAP_TYPE_EVENTS:
 		return kfd_event_mmap(process, vma);
-	} else if ((vma->vm_pgoff & KFD_MMAP_RESERVED_MEM_MASK) ==
-			KFD_MMAP_RESERVED_MEM_MASK) {
-		vma->vm_pgoff = vma->vm_pgoff ^ KFD_MMAP_RESERVED_MEM_MASK;
-		return kfd_reserved_mem_mmap(process, vma);
+
+	case KFD_MMAP_TYPE_RESERVED_MEM:
+		if (!dev)
+			return -ENODEV;
+		return kfd_reserved_mem_mmap(dev, process, vma);
 	}
 
 	return -EFAULT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 4f126ef6139b..296b3f230280 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -132,6 +132,9 @@ static struct kfd_gpu_cache_info carrizo_cache_info[] = {
 #define fiji_cache_info  carrizo_cache_info
 #define polaris10_cache_info carrizo_cache_info
 #define polaris11_cache_info carrizo_cache_info
+/* TODO - check & update Vega10 cache details */
+#define vega10_cache_info carrizo_cache_info
+#define raven_cache_info carrizo_cache_info
 
 static void kfd_populated_cu_info_cpu(struct kfd_topology_device *dev,
 		struct crat_subtype_computeunit *cu)
@@ -603,6 +606,14 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 		pcache_info = polaris11_cache_info;
 		num_of_cache_types = ARRAY_SIZE(polaris11_cache_info);
 		break;
+	case CHIP_VEGA10:
+		pcache_info = vega10_cache_info;
+		num_of_cache_types = ARRAY_SIZE(vega10_cache_info);
+		break;
+	case CHIP_RAVEN:
+		pcache_info = raven_cache_info;
+		num_of_cache_types = ARRAY_SIZE(raven_cache_info);
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 3346699960dd..7ee6cec2c060 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -20,16 +20,13 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#if defined(CONFIG_AMD_IOMMU_V2_MODULE) || defined(CONFIG_AMD_IOMMU_V2)
-#include <linux/amd-iommu.h>
-#endif
 #include <linux/bsearch.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
 #include "kfd_pm4_headers_vi.h"
-#include "cwsr_trap_handler_gfx8.asm"
+#include "cwsr_trap_handler.h"
 #include "kfd_iommu.h"
 
 #define MQD_SIZE_ALIGNED 768
@@ -41,6 +38,7 @@ static const struct kfd_device_info kaveri_device_info = {
 	.max_pasid_bits = 16,
 	/* max num of queues for KV.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -55,6 +53,7 @@ static const struct kfd_device_info carrizo_device_info = {
 	.max_pasid_bits = 16,
 	/* max num of queues for CZ.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -70,6 +69,7 @@ static const struct kfd_device_info hawaii_device_info = {
 	.max_pasid_bits = 16,
 	/* max num of queues for KV.TODO should be a dynamic value */
 	.max_no_of_hqd	= 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -83,6 +83,7 @@ static const struct kfd_device_info tonga_device_info = {
 	.asic_family = CHIP_TONGA,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -96,6 +97,7 @@ static const struct kfd_device_info tonga_vf_device_info = {
 	.asic_family = CHIP_TONGA,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -109,6 +111,7 @@ static const struct kfd_device_info fiji_device_info = {
 	.asic_family = CHIP_FIJI,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -122,6 +125,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 	.asic_family = CHIP_FIJI,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -136,6 +140,7 @@ static const struct kfd_device_info polaris10_device_info = {
 	.asic_family = CHIP_POLARIS10,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -149,6 +154,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 	.asic_family = CHIP_POLARIS10,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -162,6 +168,7 @@ static const struct kfd_device_info polaris11_device_info = {
 	.asic_family = CHIP_POLARIS11,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
+	.doorbell_size  = 4,
 	.ih_ring_entry_size = 4 * sizeof(uint32_t),
 	.event_interrupt_class = &event_interrupt_class_cik,
 	.num_of_watch_points = 4,
@@ -171,6 +178,34 @@ static const struct kfd_device_info polaris11_device_info = {
 	.needs_pci_atomics = true,
 };
 
+static const struct kfd_device_info vega10_device_info = {
+	.asic_family = CHIP_VEGA10,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.doorbell_size  = 8,
+	.ih_ring_entry_size = 8 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_v9,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = true,
+	.needs_iommu_device = false,
+	.needs_pci_atomics = false,
+};
+
+static const struct kfd_device_info vega10_vf_device_info = {
+	.asic_family = CHIP_VEGA10,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.doorbell_size  = 8,
+	.ih_ring_entry_size = 8 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_v9,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = true,
+	.needs_iommu_device = false,
+	.needs_pci_atomics = false,
+};
+
 
 struct kfd_deviceid {
 	unsigned short did;
@@ -250,6 +285,15 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x67EB, &polaris11_device_info },	/* Polaris11 */
 	{ 0x67EF, &polaris11_device_info },	/* Polaris11 */
 	{ 0x67FF, &polaris11_device_info },	/* Polaris11 */
+	{ 0x6860, &vega10_device_info },	/* Vega10 */
+	{ 0x6861, &vega10_device_info },	/* Vega10 */
+	{ 0x6862, &vega10_device_info },	/* Vega10 */
+	{ 0x6863, &vega10_device_info },	/* Vega10 */
+	{ 0x6864, &vega10_device_info },	/* Vega10 */
+	{ 0x6867, &vega10_device_info },	/* Vega10 */
+	{ 0x6868, &vega10_device_info },	/* Vega10 */
+	{ 0x686C, &vega10_vf_device_info },	/* Vega10  vf*/
+	{ 0x687F, &vega10_device_info },	/* Vega10 */
 };
 
 static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
@@ -279,7 +323,7 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 	struct pci_dev *pdev, const struct kfd2kgd_calls *f2g)
 {
 	struct kfd_dev *kfd;
-
+	int ret;
 	const struct kfd_device_info *device_info =
 					lookup_device_info(pdev->device);
 
@@ -288,19 +332,18 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 		return NULL;
 	}
 
-	if (device_info->needs_pci_atomics) {
-		/* Allow BIF to recode atomics to PCIe 3.0
-		 * AtomicOps. 32 and 64-bit requests are possible and
-		 * must be supported.
-		 */
-		if (pci_enable_atomic_ops_to_root(pdev,
-				PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
-				PCI_EXP_DEVCAP2_ATOMIC_COMP64) < 0) {
-			dev_info(kfd_device,
-				"skipped device %x:%x, PCI rejects atomics",
-				 pdev->vendor, pdev->device);
-			return NULL;
-		}
+	/* Allow BIF to recode atomics to PCIe 3.0 AtomicOps.
+	 * 32 and 64-bit requests are possible and must be
+	 * supported.
+	 */
+	ret = pci_enable_atomic_ops_to_root(pdev,
+			PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
+			PCI_EXP_DEVCAP2_ATOMIC_COMP64);
+	if (device_info->needs_pci_atomics && ret < 0) {
+		dev_info(kfd_device,
+			 "skipped device %x:%x, PCI rejects atomics\n",
+			 pdev->vendor, pdev->device);
+		return NULL;
 	}
 
 	kfd = kzalloc(sizeof(*kfd), GFP_KERNEL);
@@ -323,10 +366,16 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 static void kfd_cwsr_init(struct kfd_dev *kfd)
 {
 	if (cwsr_enable && kfd->device_info->supports_cwsr) {
-		BUILD_BUG_ON(sizeof(cwsr_trap_gfx8_hex) > PAGE_SIZE);
+		if (kfd->device_info->asic_family < CHIP_VEGA10) {
+			BUILD_BUG_ON(sizeof(cwsr_trap_gfx8_hex) > PAGE_SIZE);
+			kfd->cwsr_isa = cwsr_trap_gfx8_hex;
+			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx8_hex);
+		} else {
+			BUILD_BUG_ON(sizeof(cwsr_trap_gfx9_hex) > PAGE_SIZE);
+			kfd->cwsr_isa = cwsr_trap_gfx9_hex;
+			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx9_hex);
+		}
 
-		kfd->cwsr_isa = cwsr_trap_gfx8_hex;
-		kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx8_hex);
 		kfd->cwsr_enabled = true;
 	}
 }
@@ -541,6 +590,44 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 	spin_unlock(&kfd->interrupt_lock);
 }
 
+int kgd2kfd_quiesce_mm(struct mm_struct *mm)
+{
+	struct kfd_process *p;
+	int r;
+
+	/* Because we are called from arbitrary context (workqueue) as opposed
+	 * to process context, kfd_process could attempt to exit while we are
+	 * running so the lookup function increments the process ref count.
+	 */
+	p = kfd_lookup_process_by_mm(mm);
+	if (!p)
+		return -ESRCH;
+
+	r = kfd_process_evict_queues(p);
+
+	kfd_unref_process(p);
+	return r;
+}
+
+int kgd2kfd_resume_mm(struct mm_struct *mm)
+{
+	struct kfd_process *p;
+	int r;
+
+	/* Because we are called from arbitrary context (workqueue) as opposed
+	 * to process context, kfd_process could attempt to exit while we are
+	 * running so the lookup function increments the process ref count.
+	 */
+	p = kfd_lookup_process_by_mm(mm);
+	if (!p)
+		return -ESRCH;
+
+	r = kfd_process_restore_queues(p);
+
+	kfd_unref_process(p);
+	return r;
+}
+
 /** kgd2kfd_schedule_evict_and_restore_process - Schedules work queue that will
  *   prepare for safe eviction of KFD BOs that belong to the specified
  *   process.
@@ -652,7 +739,7 @@ int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size,
 	if (size > kfd->gtt_sa_num_of_chunks * kfd->gtt_sa_chunk_size)
 		return -ENOMEM;
 
-	*mem_obj = kmalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
+	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
 	if ((*mem_obj) == NULL)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index d55d29d31da4..668ad07ebe1f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -110,6 +110,57 @@ void program_sh_mem_settings(struct device_queue_manager *dqm,
 						qpd->sh_mem_bases);
 }
 
+static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
+{
+	struct kfd_dev *dev = qpd->dqm->dev;
+
+	if (!KFD_IS_SOC15(dev->device_info->asic_family)) {
+		/* On pre-SOC15 chips we need to use the queue ID to
+		 * preserve the user mode ABI.
+		 */
+		q->doorbell_id = q->properties.queue_id;
+	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
+		/* For SDMA queues on SOC15, use static doorbell
+		 * assignments based on the engine and queue.
+		 */
+		q->doorbell_id = dev->shared_resources.sdma_doorbell
+			[q->properties.sdma_engine_id]
+			[q->properties.sdma_queue_id];
+	} else {
+		/* For CP queues on SOC15 reserve a free doorbell ID */
+		unsigned int found;
+
+		found = find_first_zero_bit(qpd->doorbell_bitmap,
+					    KFD_MAX_NUM_OF_QUEUES_PER_PROCESS);
+		if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
+			pr_debug("No doorbells available");
+			return -EBUSY;
+		}
+		set_bit(found, qpd->doorbell_bitmap);
+		q->doorbell_id = found;
+	}
+
+	q->properties.doorbell_off =
+		kfd_doorbell_id_to_offset(dev, q->process,
+					  q->doorbell_id);
+
+	return 0;
+}
+
+static void deallocate_doorbell(struct qcm_process_device *qpd,
+				struct queue *q)
+{
+	unsigned int old;
+	struct kfd_dev *dev = qpd->dqm->dev;
+
+	if (!KFD_IS_SOC15(dev->device_info->asic_family) ||
+	    q->properties.type == KFD_QUEUE_TYPE_SDMA)
+		return;
+
+	old = test_and_clear_bit(q->doorbell_id, qpd->doorbell_bitmap);
+	WARN_ON(!old);
+}
+
 static int allocate_vmid(struct device_queue_manager *dqm,
 			struct qcm_process_device *qpd,
 			struct queue *q)
@@ -145,15 +196,19 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 static int flush_texture_cache_nocpsch(struct kfd_dev *kdev,
 				struct qcm_process_device *qpd)
 {
-	uint32_t len;
+	const struct packet_manager_funcs *pmf = qpd->dqm->packets.pmf;
+	int ret;
 
 	if (!qpd->ib_kaddr)
 		return -ENOMEM;
 
-	len = pm_create_release_mem(qpd->ib_base, (uint32_t *)qpd->ib_kaddr);
+	ret = pmf->release_mem(qpd->ib_base, (uint32_t *)qpd->ib_kaddr);
+	if (ret)
+		return ret;
 
 	return kdev->kfd2kgd->submit_ib(kdev->kgd, KGD_ENGINE_MEC1, qpd->vmid,
-				qpd->ib_base, (uint32_t *)qpd->ib_kaddr, len);
+				qpd->ib_base, (uint32_t *)qpd->ib_kaddr,
+				pmf->release_mem_size / sizeof(uint32_t));
 }
 
 static void deallocate_vmid(struct device_queue_manager *dqm,
@@ -301,10 +356,14 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		return retval;
 
+	retval = allocate_doorbell(qpd, q);
+	if (retval)
+		goto out_deallocate_hqd;
+
 	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
-		goto out_deallocate_hqd;
+		goto out_deallocate_doorbell;
 
 	pr_debug("Loading mqd to hqd on pipe %d, queue %d\n",
 			q->pipe, q->queue);
@@ -324,6 +383,8 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 
 out_uninit_mqd:
 	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+out_deallocate_doorbell:
+	deallocate_doorbell(qpd, q);
 out_deallocate_hqd:
 	deallocate_hqd(dqm, q);
 
@@ -357,6 +418,8 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 	}
 	dqm->total_queue_count--;
 
+	deallocate_doorbell(qpd, q);
+
 	retval = mqd->destroy_mqd(mqd, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 				KFD_UNMAP_LATENCY_MS,
@@ -861,6 +924,10 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
 	q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
 
+	retval = allocate_doorbell(qpd, q);
+	if (retval)
+		goto out_deallocate_sdma_queue;
+
 	pr_debug("SDMA id is:    %d\n", q->sdma_id);
 	pr_debug("SDMA queue id: %d\n", q->properties.sdma_queue_id);
 	pr_debug("SDMA engine id: %d\n", q->properties.sdma_engine_id);
@@ -869,7 +936,7 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
-		goto out_deallocate_sdma_queue;
+		goto out_deallocate_doorbell;
 
 	retval = mqd->load_mqd(mqd, q->mqd, 0, 0, &q->properties, NULL);
 	if (retval)
@@ -879,6 +946,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 
 out_uninit_mqd:
 	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+out_deallocate_doorbell:
+	deallocate_doorbell(qpd, q);
 out_deallocate_sdma_queue:
 	deallocate_sdma_queue(dqm, q->sdma_id);
 
@@ -1070,12 +1139,17 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		q->properties.sdma_engine_id =
 			q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
 	}
+
+	retval = allocate_doorbell(qpd, q);
+	if (retval)
+		goto out_deallocate_sdma_queue;
+
 	mqd = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
 
 	if (!mqd) {
 		retval = -ENOMEM;
-		goto out_deallocate_sdma_queue;
+		goto out_deallocate_doorbell;
 	}
 	/*
 	 * Eviction state logic: we only mark active queues as evicted
@@ -1093,7 +1167,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
-		goto out_deallocate_sdma_queue;
+		goto out_deallocate_doorbell;
 
 	list_add(&q->list, &qpd->queues_list);
 	qpd->queue_count++;
@@ -1117,6 +1191,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	mutex_unlock(&dqm->lock);
 	return retval;
 
+out_deallocate_doorbell:
+	deallocate_doorbell(qpd, q);
 out_deallocate_sdma_queue:
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
 		deallocate_sdma_queue(dqm, q->sdma_id);
@@ -1257,6 +1333,8 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 		goto failed;
 	}
 
+	deallocate_doorbell(qpd, q);
+
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
 		dqm->sdma_queue_count--;
 		deallocate_sdma_queue(dqm, q->sdma_id);
@@ -1308,7 +1386,10 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 				   void __user *alternate_aperture_base,
 				   uint64_t alternate_aperture_size)
 {
-	bool retval;
+	bool retval = true;
+
+	if (!dqm->asic_ops.set_cache_memory_policy)
+		return retval;
 
 	mutex_lock(&dqm->lock);
 
@@ -1577,6 +1658,11 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 	case CHIP_POLARIS11:
 		device_queue_manager_init_vi_tonga(&dqm->asic_ops);
 		break;
+
+	case CHIP_VEGA10:
+	case CHIP_RAVEN:
+		device_queue_manager_init_v9(&dqm->asic_ops);
+		break;
 	default:
 		WARN(1, "Unexpected ASIC family %u",
 		     dev->device_info->asic_family);
@@ -1627,6 +1713,18 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 	int pipe, queue;
 	int r = 0;
 
+	r = dqm->dev->kfd2kgd->hqd_dump(dqm->dev->kgd,
+		KFD_CIK_HIQ_PIPE, KFD_CIK_HIQ_QUEUE, &dump, &n_regs);
+	if (!r) {
+		seq_printf(m, "  HIQ on MEC %d Pipe %d Queue %d\n",
+				KFD_CIK_HIQ_PIPE/get_pipes_per_mec(dqm)+1,
+				KFD_CIK_HIQ_PIPE%get_pipes_per_mec(dqm),
+				KFD_CIK_HIQ_QUEUE);
+		seq_reg_dump(m, dump, n_regs);
+
+		kfree(dump);
+	}
+
 	for (pipe = 0; pipe < get_pipes_per_mec(dqm); pipe++) {
 		int pipe_offset = pipe * get_queues_per_pipe(dqm);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 412beff3281d..59a6b1956932 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -200,6 +200,8 @@ void device_queue_manager_init_vi(
 		struct device_queue_manager_asic_ops *asic_ops);
 void device_queue_manager_init_vi_tonga(
 		struct device_queue_manager_asic_ops *asic_ops);
+void device_queue_manager_init_v9(
+		struct device_queue_manager_asic_ops *asic_ops);
 void program_sh_mem_settings(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd);
 unsigned int get_queues_num(struct device_queue_manager *dqm);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
new file mode 100644
index 000000000000..79e5bcf6367c
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
@@ -0,0 +1,84 @@
+/*
+ * Copyright 2016-2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "kfd_device_queue_manager.h"
+#include "vega10_enum.h"
+#include "gc/gc_9_0_offset.h"
+#include "gc/gc_9_0_sh_mask.h"
+#include "sdma0/sdma0_4_0_sh_mask.h"
+
+static int update_qpd_v9(struct device_queue_manager *dqm,
+			 struct qcm_process_device *qpd);
+static void init_sdma_vm_v9(struct device_queue_manager *dqm, struct queue *q,
+			    struct qcm_process_device *qpd);
+
+void device_queue_manager_init_v9(
+	struct device_queue_manager_asic_ops *asic_ops)
+{
+	asic_ops->update_qpd = update_qpd_v9;
+	asic_ops->init_sdma_vm = init_sdma_vm_v9;
+}
+
+static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd)
+{
+	uint32_t shared_base = pdd->lds_base >> 48;
+	uint32_t private_base = pdd->scratch_base >> 48;
+
+	return (shared_base << SH_MEM_BASES__SHARED_BASE__SHIFT) |
+		private_base;
+}
+
+static int update_qpd_v9(struct device_queue_manager *dqm,
+			 struct qcm_process_device *qpd)
+{
+	struct kfd_process_device *pdd;
+
+	pdd = qpd_to_pdd(qpd);
+
+	/* check if sh_mem_config register already configured */
+	if (qpd->sh_mem_config == 0) {
+		qpd->sh_mem_config =
+				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
+		if (vega10_noretry &&
+		    !dqm->dev->device_info->needs_iommu_device)
+			qpd->sh_mem_config |=
+				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
+
+		qpd->sh_mem_ape1_limit = 0;
+		qpd->sh_mem_ape1_base = 0;
+	}
+
+	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd);
+
+	pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases);
+
+	return 0;
+}
+
+static void init_sdma_vm_v9(struct device_queue_manager *dqm, struct queue *q,
+			    struct qcm_process_device *qpd)
+{
+	/* Not needed on SDMAv4 any more */
+	q->properties.sdma_vm_addr = 0;
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index ebb4da14e3df..c3744d89352c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -33,7 +33,6 @@
 
 static DEFINE_IDA(doorbell_ida);
 static unsigned int max_doorbell_slices;
-#define KFD_SIZE_OF_DOORBELL_IN_BYTES 4
 
 /*
  * Each device exposes a doorbell aperture, a PCI MMIO aperture that
@@ -50,9 +49,9 @@ static unsigned int max_doorbell_slices;
  */
 
 /* # of doorbell bytes allocated for each process. */
-static inline size_t doorbell_process_allocation(void)
+size_t kfd_doorbell_process_slice(struct kfd_dev *kfd)
 {
-	return roundup(KFD_SIZE_OF_DOORBELL_IN_BYTES *
+	return roundup(kfd->device_info->doorbell_size *
 			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS,
 			PAGE_SIZE);
 }
@@ -72,16 +71,16 @@ int kfd_doorbell_init(struct kfd_dev *kfd)
 
 	doorbell_start_offset =
 			roundup(kfd->shared_resources.doorbell_start_offset,
-					doorbell_process_allocation());
+					kfd_doorbell_process_slice(kfd));
 
 	doorbell_aperture_size =
 			rounddown(kfd->shared_resources.doorbell_aperture_size,
-					doorbell_process_allocation());
+					kfd_doorbell_process_slice(kfd));
 
 	if (doorbell_aperture_size > doorbell_start_offset)
 		doorbell_process_limit =
 			(doorbell_aperture_size - doorbell_start_offset) /
-						doorbell_process_allocation();
+						kfd_doorbell_process_slice(kfd);
 	else
 		return -ENOSPC;
 
@@ -95,7 +94,7 @@ int kfd_doorbell_init(struct kfd_dev *kfd)
 	kfd->doorbell_id_offset = doorbell_start_offset / sizeof(u32);
 
 	kfd->doorbell_kernel_ptr = ioremap(kfd->doorbell_base,
-						doorbell_process_allocation());
+					   kfd_doorbell_process_slice(kfd));
 
 	if (!kfd->doorbell_kernel_ptr)
 		return -ENOMEM;
@@ -127,21 +126,16 @@ void kfd_doorbell_fini(struct kfd_dev *kfd)
 		iounmap(kfd->doorbell_kernel_ptr);
 }
 
-int kfd_doorbell_mmap(struct kfd_process *process, struct vm_area_struct *vma)
+int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process,
+		      struct vm_area_struct *vma)
 {
 	phys_addr_t address;
-	struct kfd_dev *dev;
 
 	/*
 	 * For simplicitly we only allow mapping of the entire doorbell
 	 * allocation of a single device & process.
 	 */
-	if (vma->vm_end - vma->vm_start != doorbell_process_allocation())
-		return -EINVAL;
-
-	/* Find kfd device according to gpu id */
-	dev = kfd_device_by_id(vma->vm_pgoff);
-	if (!dev)
+	if (vma->vm_end - vma->vm_start != kfd_doorbell_process_slice(dev))
 		return -EINVAL;
 
 	/* Calculate physical address of doorbell */
@@ -158,19 +152,19 @@ int kfd_doorbell_mmap(struct kfd_process *process, struct vm_area_struct *vma)
 		 "     vm_flags            == 0x%04lX\n"
 		 "     size                == 0x%04lX\n",
 		 (unsigned long long) vma->vm_start, address, vma->vm_flags,
-		 doorbell_process_allocation());
+		 kfd_doorbell_process_slice(dev));
 
 
 	return io_remap_pfn_range(vma,
 				vma->vm_start,
 				address >> PAGE_SHIFT,
-				doorbell_process_allocation(),
+				kfd_doorbell_process_slice(dev),
 				vma->vm_page_prot);
 }
 
 
 /* get kernel iomem pointer for a doorbell */
-u32 __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
+void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 					unsigned int *doorbell_off)
 {
 	u32 inx;
@@ -185,6 +179,8 @@ u32 __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 	if (inx >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)
 		return NULL;
 
+	inx *= kfd->device_info->doorbell_size / sizeof(u32);
+
 	/*
 	 * Calculating the kernel doorbell offset using the first
 	 * doorbell page.
@@ -210,7 +206,7 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr)
 	mutex_unlock(&kfd->doorbell_mutex);
 }
 
-inline void write_kernel_doorbell(u32 __iomem *db, u32 value)
+void write_kernel_doorbell(void __iomem *db, u32 value)
 {
 	if (db) {
 		writel(value, db);
@@ -218,30 +214,37 @@ inline void write_kernel_doorbell(u32 __iomem *db, u32 value)
 	}
 }
 
-/*
- * queue_ids are in the range [0,MAX_PROCESS_QUEUES) and are mapped 1:1
- * to doorbells with the process's doorbell page
- */
-unsigned int kfd_queue_id_to_doorbell(struct kfd_dev *kfd,
+void write_kernel_doorbell64(void __iomem *db, u64 value)
+{
+	if (db) {
+		WARN(((unsigned long)db & 7) != 0,
+		     "Unaligned 64-bit doorbell");
+		writeq(value, (u64 __iomem *)db);
+		pr_debug("writing %llu to doorbell address %p\n", value, db);
+	}
+}
+
+unsigned int kfd_doorbell_id_to_offset(struct kfd_dev *kfd,
 					struct kfd_process *process,
-					unsigned int queue_id)
+					unsigned int doorbell_id)
 {
 	/*
 	 * doorbell_id_offset accounts for doorbells taken by KGD.
-	 * index * doorbell_process_allocation/sizeof(u32) adjusts to
-	 * the process's doorbells.
+	 * index * kfd_doorbell_process_slice/sizeof(u32) adjusts to
+	 * the process's doorbells. The offset returned is in dword
+	 * units regardless of the ASIC-dependent doorbell size.
 	 */
 	return kfd->doorbell_id_offset +
 		process->doorbell_index
-		* doorbell_process_allocation() / sizeof(u32) +
-		queue_id;
+		* kfd_doorbell_process_slice(kfd) / sizeof(u32) +
+		doorbell_id * kfd->device_info->doorbell_size / sizeof(u32);
 }
 
 uint64_t kfd_get_number_elems(struct kfd_dev *kfd)
 {
 	uint64_t num_of_elems = (kfd->shared_resources.doorbell_aperture_size -
 				kfd->shared_resources.doorbell_start_offset) /
-					doorbell_process_allocation() + 1;
+					kfd_doorbell_process_slice(kfd) + 1;
 
 	return num_of_elems;
 
@@ -251,7 +254,7 @@ phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev,
 					struct kfd_process *process)
 {
 	return dev->doorbell_base +
-		process->doorbell_index * doorbell_process_allocation();
+		process->doorbell_index * kfd_doorbell_process_slice(dev);
 }
 
 int kfd_alloc_process_doorbells(struct kfd_process *process)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 4890a90f1e44..5562e94e786a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -345,7 +345,7 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 	case KFD_EVENT_TYPE_DEBUG:
 		ret = create_signal_event(devkfd, p, ev);
 		if (!ret) {
-			*event_page_offset = KFD_MMAP_EVENTS_MASK;
+			*event_page_offset = KFD_MMAP_TYPE_EVENTS;
 			*event_page_offset <<= PAGE_SHIFT;
 			*event_slot_index = ev->event_id;
 		}
@@ -496,7 +496,7 @@ void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
 			pr_debug_ratelimited("Partial ID invalid: %u (%u valid bits)\n",
 					     partial_id, valid_id_bits);
 
-		if (p->signal_event_count < KFD_SIGNAL_EVENT_LIMIT/2) {
+		if (p->signal_event_count < KFD_SIGNAL_EVENT_LIMIT / 64) {
 			/* With relatively few events, it's faster to
 			 * iterate over the event IDR
 			 */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
index 66852de410c8..97d5423c5673 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
@@ -275,23 +275,35 @@
  * for FLAT_* / S_LOAD operations.
  */
 
-#define MAKE_GPUVM_APP_BASE(gpu_num) \
+#define MAKE_GPUVM_APP_BASE_VI(gpu_num) \
 	(((uint64_t)(gpu_num) << 61) + 0x1000000000000L)
 
 #define MAKE_GPUVM_APP_LIMIT(base, size) \
 	(((uint64_t)(base) & 0xFFFFFF0000000000UL) + (size) - 1)
 
-#define MAKE_SCRATCH_APP_BASE() \
+#define MAKE_SCRATCH_APP_BASE_VI() \
 	(((uint64_t)(0x1UL) << 61) + 0x100000000L)
 
 #define MAKE_SCRATCH_APP_LIMIT(base) \
 	(((uint64_t)base & 0xFFFFFFFF00000000UL) | 0xFFFFFFFF)
 
-#define MAKE_LDS_APP_BASE() \
+#define MAKE_LDS_APP_BASE_VI() \
 	(((uint64_t)(0x1UL) << 61) + 0x0)
 #define MAKE_LDS_APP_LIMIT(base) \
 	(((uint64_t)(base) & 0xFFFFFFFF00000000UL) | 0xFFFFFFFF)
 
+/* On GFXv9 the LDS and scratch apertures are programmed independently
+ * using the high 16 bits of the 64-bit virtual address. They must be
+ * in the hole, which will be the case as long as the high 16 bits are
+ * not 0.
+ *
+ * The aperture sizes are still 4GB implicitly.
+ *
+ * A GPUVM aperture is not applicable on GFXv9.
+ */
+#define MAKE_LDS_APP_BASE_V9() ((uint64_t)(0x1UL) << 48)
+#define MAKE_SCRATCH_APP_BASE_V9() ((uint64_t)(0x2UL) << 48)
+
 /* User mode manages most of the SVM aperture address space. The low
  * 16MB are reserved for kernel use (CWSR trap handler and kernel IB
  * for now).
@@ -300,6 +312,55 @@
 #define SVM_CWSR_BASE (SVM_USER_BASE - KFD_CWSR_TBA_TMA_SIZE)
 #define SVM_IB_BASE   (SVM_CWSR_BASE - PAGE_SIZE)
 
+static void kfd_init_apertures_vi(struct kfd_process_device *pdd, uint8_t id)
+{
+	/*
+	 * node id couldn't be 0 - the three MSB bits of
+	 * aperture shoudn't be 0
+	 */
+	pdd->lds_base = MAKE_LDS_APP_BASE_VI();
+	pdd->lds_limit = MAKE_LDS_APP_LIMIT(pdd->lds_base);
+
+	if (!pdd->dev->device_info->needs_iommu_device) {
+		/* dGPUs: SVM aperture starting at 0
+		 * with small reserved space for kernel.
+		 * Set them to CANONICAL addresses.
+		 */
+		pdd->gpuvm_base = SVM_USER_BASE;
+		pdd->gpuvm_limit =
+			pdd->dev->shared_resources.gpuvm_size - 1;
+	} else {
+		/* set them to non CANONICAL addresses, and no SVM is
+		 * allocated.
+		 */
+		pdd->gpuvm_base = MAKE_GPUVM_APP_BASE_VI(id + 1);
+		pdd->gpuvm_limit = MAKE_GPUVM_APP_LIMIT(pdd->gpuvm_base,
+				pdd->dev->shared_resources.gpuvm_size);
+	}
+
+	pdd->scratch_base = MAKE_SCRATCH_APP_BASE_VI();
+	pdd->scratch_limit = MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base);
+}
+
+static void kfd_init_apertures_v9(struct kfd_process_device *pdd, uint8_t id)
+{
+	pdd->lds_base = MAKE_LDS_APP_BASE_V9();
+	pdd->lds_limit = MAKE_LDS_APP_LIMIT(pdd->lds_base);
+
+	/* Raven needs SVM to support graphic handle, etc. Leave the small
+	 * reserved space before SVM on Raven as well, even though we don't
+	 * have to.
+	 * Set gpuvm_base and gpuvm_limit to CANONICAL addresses so that they
+	 * are used in Thunk to reserve SVM.
+	 */
+	pdd->gpuvm_base = SVM_USER_BASE;
+	pdd->gpuvm_limit =
+		pdd->dev->shared_resources.gpuvm_size - 1;
+
+	pdd->scratch_base = MAKE_SCRATCH_APP_BASE_V9();
+	pdd->scratch_limit = MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base);
+}
+
 int kfd_init_apertures(struct kfd_process *process)
 {
 	uint8_t id  = 0;
@@ -307,9 +368,7 @@ int kfd_init_apertures(struct kfd_process *process)
 	struct kfd_process_device *pdd;
 
 	/*Iterating over all devices*/
-	while (kfd_topology_enum_kfd_devices(id, &dev) == 0 &&
-		id < NUM_OF_SUPPORTED_GPUS) {
-
+	while (kfd_topology_enum_kfd_devices(id, &dev) == 0) {
 		if (!dev) {
 			id++; /* Skip non GPU devices */
 			continue;
@@ -318,7 +377,7 @@ int kfd_init_apertures(struct kfd_process *process)
 		pdd = kfd_create_process_device_data(dev, process);
 		if (!pdd) {
 			pr_err("Failed to create process device data\n");
-			return -1;
+			return -ENOMEM;
 		}
 		/*
 		 * For 64 bit process apertures will be statically reserved in
@@ -330,32 +389,30 @@ int kfd_init_apertures(struct kfd_process *process)
 			pdd->gpuvm_base = pdd->gpuvm_limit = 0;
 			pdd->scratch_base = pdd->scratch_limit = 0;
 		} else {
-			/* Same LDS and scratch apertures can be used
-			 * on all GPUs. This allows using more dGPUs
-			 * than placement options for apertures.
-			 */
-			pdd->lds_base = MAKE_LDS_APP_BASE();
-			pdd->lds_limit = MAKE_LDS_APP_LIMIT(pdd->lds_base);
-
-			pdd->scratch_base = MAKE_SCRATCH_APP_BASE();
-			pdd->scratch_limit =
-				MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base);
+			switch (dev->device_info->asic_family) {
+			case CHIP_KAVERI:
+			case CHIP_HAWAII:
+			case CHIP_CARRIZO:
+			case CHIP_TONGA:
+			case CHIP_FIJI:
+			case CHIP_POLARIS10:
+			case CHIP_POLARIS11:
+				kfd_init_apertures_vi(pdd, id);
+				break;
+			case CHIP_VEGA10:
+			case CHIP_RAVEN:
+				kfd_init_apertures_v9(pdd, id);
+				break;
+			default:
+				WARN(1, "Unexpected ASIC family %u",
+				     dev->device_info->asic_family);
+				return -EINVAL;
+			}
 
-			if (dev->device_info->needs_iommu_device) {
-				/* APUs: GPUVM aperture in
-				 * non-canonical address space
-				 */
-				pdd->gpuvm_base = MAKE_GPUVM_APP_BASE(id + 1);
-				pdd->gpuvm_limit = MAKE_GPUVM_APP_LIMIT(
-					pdd->gpuvm_base,
-					dev->shared_resources.gpuvm_size);
-			} else {
-				/* dGPUs: SVM aperture starting at 0
-				 * with small reserved space for kernel
+			if (!dev->device_info->needs_iommu_device) {
+				/* dGPUs: the reserved space for kernel
+				 * before SVM
 				 */
-				pdd->gpuvm_base = SVM_USER_BASE;
-				pdd->gpuvm_limit =
-					dev->shared_resources.gpuvm_size - 1;
 				pdd->qpd.cwsr_base = SVM_CWSR_BASE;
 				pdd->qpd.ib_base = SVM_IB_BASE;
 			}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
new file mode 100644
index 000000000000..37029baa3346
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -0,0 +1,92 @@
+/*
+ * Copyright 2016-2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "kfd_priv.h"
+#include "kfd_events.h"
+#include "soc15_int.h"
+
+
+static bool event_interrupt_isr_v9(struct kfd_dev *dev,
+					const uint32_t *ih_ring_entry)
+{
+	uint16_t source_id, client_id, pasid, vmid;
+	const uint32_t *data = ih_ring_entry;
+
+	/* Only handle interrupts from KFD VMIDs */
+	vmid = SOC15_VMID_FROM_IH_ENTRY(ih_ring_entry);
+	if (vmid < dev->vm_info.first_vmid_kfd ||
+	    vmid > dev->vm_info.last_vmid_kfd)
+		return 0;
+
+	/* If there is no valid PASID, it's likely a firmware bug */
+	pasid = SOC15_PASID_FROM_IH_ENTRY(ih_ring_entry);
+	if (WARN_ONCE(pasid == 0, "FW bug: No PASID in KFD interrupt"))
+		return 0;
+
+	source_id = SOC15_SOURCE_ID_FROM_IH_ENTRY(ih_ring_entry);
+	client_id = SOC15_CLIENT_ID_FROM_IH_ENTRY(ih_ring_entry);
+
+	pr_debug("client id 0x%x, source id %d, pasid 0x%x. raw data:\n",
+		 client_id, source_id, pasid);
+	pr_debug("%8X, %8X, %8X, %8X, %8X, %8X, %8X, %8X.\n",
+		 data[0], data[1], data[2], data[3],
+		 data[4], data[5], data[6], data[7]);
+
+	/* Interrupt types we care about: various signals and faults.
+	 * They will be forwarded to a work queue (see below).
+	 */
+	return source_id == SOC15_INTSRC_CP_END_OF_PIPE ||
+		source_id == SOC15_INTSRC_SDMA_TRAP ||
+		source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG ||
+		source_id == SOC15_INTSRC_CP_BAD_OPCODE;
+}
+
+static void event_interrupt_wq_v9(struct kfd_dev *dev,
+					const uint32_t *ih_ring_entry)
+{
+	uint16_t source_id, client_id, pasid, vmid;
+	uint32_t context_id;
+
+	source_id = SOC15_SOURCE_ID_FROM_IH_ENTRY(ih_ring_entry);
+	client_id = SOC15_CLIENT_ID_FROM_IH_ENTRY(ih_ring_entry);
+	pasid = SOC15_PASID_FROM_IH_ENTRY(ih_ring_entry);
+	vmid = SOC15_VMID_FROM_IH_ENTRY(ih_ring_entry);
+	context_id = SOC15_CONTEXT_ID0_FROM_IH_ENTRY(ih_ring_entry);
+
+	if (source_id == SOC15_INTSRC_CP_END_OF_PIPE)
+		kfd_signal_event_interrupt(pasid, context_id, 32);
+	else if (source_id == SOC15_INTSRC_SDMA_TRAP)
+		kfd_signal_event_interrupt(pasid, context_id & 0xfffffff, 28);
+	else if (source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG)
+		kfd_signal_event_interrupt(pasid, context_id & 0xffffff, 24);
+	else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE)
+		kfd_signal_hw_exception_event(pasid);
+	else if (client_id == SOC15_IH_CLIENTID_VMC ||
+		 client_id == SOC15_IH_CLIENTID_UTCL2) {
+		/* TODO */
+	}
+}
+
+const struct kfd_event_interrupt_class event_interrupt_class_v9 = {
+	.interrupt_isr = event_interrupt_isr_v9,
+	.interrupt_wq = event_interrupt_wq_v9,
+};
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
index 035c351f47c5..db6d9336b80d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
@@ -139,10 +139,12 @@ static void interrupt_wq(struct work_struct *work)
 {
 	struct kfd_dev *dev = container_of(work, struct kfd_dev,
 						interrupt_work);
+	uint32_t ih_ring_entry[KFD_MAX_RING_ENTRY_SIZE];
 
-	uint32_t ih_ring_entry[DIV_ROUND_UP(
-				dev->device_info->ih_ring_entry_size,
-				sizeof(uint32_t))];
+	if (dev->device_info->ih_ring_entry_size > sizeof(ih_ring_entry)) {
+		dev_err_once(kfd_chardev(), "Ring entry too small\n");
+		return;
+	}
 
 	while (dequeue_ih_ring_entry(dev, ih_ring_entry))
 		dev->device_info->event_interrupt_class->interrupt_wq(dev,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 69f496485331..476951d8c91c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -99,7 +99,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	kq->rptr_kernel = kq->rptr_mem->cpu_ptr;
 	kq->rptr_gpu_addr = kq->rptr_mem->gpu_addr;
 
-	retval = kfd_gtt_sa_allocate(dev, sizeof(*kq->wptr_kernel),
+	retval = kfd_gtt_sa_allocate(dev, dev->device_info->doorbell_size,
 					&kq->wptr_mem);
 
 	if (retval != 0)
@@ -208,6 +208,7 @@ static int acquire_packet_buffer(struct kernel_queue *kq,
 	size_t available_size;
 	size_t queue_size_dwords;
 	uint32_t wptr, rptr;
+	uint64_t wptr64;
 	unsigned int *queue_address;
 
 	/* When rptr == wptr, the buffer is empty.
@@ -216,7 +217,8 @@ static int acquire_packet_buffer(struct kernel_queue *kq,
 	 * the opposite. So we can only use up to queue_size_dwords - 1 dwords.
 	 */
 	rptr = *kq->rptr_kernel;
-	wptr = *kq->wptr_kernel;
+	wptr = kq->pending_wptr;
+	wptr64 = kq->pending_wptr64;
 	queue_address = (unsigned int *)kq->pq_kernel_addr;
 	queue_size_dwords = kq->queue->properties.queue_size / 4;
 
@@ -232,29 +234,33 @@ static int acquire_packet_buffer(struct kernel_queue *kq,
 		 * make sure calling functions know
 		 * acquire_packet_buffer() failed
 		 */
-		*buffer_ptr = NULL;
-		return -ENOMEM;
+		goto err_no_space;
 	}
 
 	if (wptr + packet_size_in_dwords >= queue_size_dwords) {
 		/* make sure after rolling back to position 0, there is
 		 * still enough space.
 		 */
-		if (packet_size_in_dwords >= rptr) {
-			*buffer_ptr = NULL;
-			return -ENOMEM;
-		}
+		if (packet_size_in_dwords >= rptr)
+			goto err_no_space;
+
 		/* fill nops, roll back and start at position 0 */
 		while (wptr > 0) {
 			queue_address[wptr] = kq->nop_packet;
 			wptr = (wptr + 1) % queue_size_dwords;
+			wptr64++;
 		}
 	}
 
 	*buffer_ptr = &queue_address[wptr];
 	kq->pending_wptr = wptr + packet_size_in_dwords;
+	kq->pending_wptr64 = wptr64 + packet_size_in_dwords;
 
 	return 0;
+
+err_no_space:
+	*buffer_ptr = NULL;
+	return -ENOMEM;
 }
 
 static void submit_packet(struct kernel_queue *kq)
@@ -270,14 +276,18 @@ static void submit_packet(struct kernel_queue *kq)
 	pr_debug("\n");
 #endif
 
-	*kq->wptr_kernel = kq->pending_wptr;
-	write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
-				kq->pending_wptr);
+	kq->ops_asic_specific.submit_packet(kq);
 }
 
 static void rollback_packet(struct kernel_queue *kq)
 {
-	kq->pending_wptr = *kq->queue->properties.write_ptr;
+	if (kq->dev->device_info->doorbell_size == 8) {
+		kq->pending_wptr64 = *kq->wptr64_kernel;
+		kq->pending_wptr = *kq->wptr_kernel %
+			(kq->queue->properties.queue_size / 4);
+	} else {
+		kq->pending_wptr = *kq->wptr_kernel;
+	}
 }
 
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
@@ -308,6 +318,11 @@ struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 	case CHIP_HAWAII:
 		kernel_queue_init_cik(&kq->ops_asic_specific);
 		break;
+
+	case CHIP_VEGA10:
+	case CHIP_RAVEN:
+		kernel_queue_init_v9(&kq->ops_asic_specific);
+		break;
 	default:
 		WARN(1, "Unexpected ASIC family %u",
 		     dev->device_info->asic_family);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
index 594053136ee4..97aff2041a5d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
@@ -72,6 +72,7 @@ struct kernel_queue {
 	struct kfd_dev		*dev;
 	struct mqd_manager	*mqd;
 	struct queue		*queue;
+	uint64_t		pending_wptr64;
 	uint32_t		pending_wptr;
 	unsigned int		nop_packet;
 
@@ -79,7 +80,10 @@ struct kernel_queue {
 	uint32_t		*rptr_kernel;
 	uint64_t		rptr_gpu_addr;
 	struct kfd_mem_obj	*wptr_mem;
-	uint32_t		*wptr_kernel;
+	union {
+		uint64_t	*wptr64_kernel;
+		uint32_t	*wptr_kernel;
+	};
 	uint64_t		wptr_gpu_addr;
 	struct kfd_mem_obj	*pq;
 	uint64_t		pq_gpu_addr;
@@ -97,5 +101,6 @@ struct kernel_queue {
 
 void kernel_queue_init_cik(struct kernel_queue_ops *ops);
 void kernel_queue_init_vi(struct kernel_queue_ops *ops);
+void kernel_queue_init_v9(struct kernel_queue_ops *ops);
 
 #endif /* KFD_KERNEL_QUEUE_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_cik.c
index a90eb440b1fb..19e54acb4125 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_cik.c
@@ -26,11 +26,13 @@
 static bool initialize_cik(struct kernel_queue *kq, struct kfd_dev *dev,
 			enum kfd_queue_type type, unsigned int queue_size);
 static void uninitialize_cik(struct kernel_queue *kq);
+static void submit_packet_cik(struct kernel_queue *kq);
 
 void kernel_queue_init_cik(struct kernel_queue_ops *ops)
 {
 	ops->initialize = initialize_cik;
 	ops->uninitialize = uninitialize_cik;
+	ops->submit_packet = submit_packet_cik;
 }
 
 static bool initialize_cik(struct kernel_queue *kq, struct kfd_dev *dev,
@@ -42,3 +44,10 @@ static bool initialize_cik(struct kernel_queue *kq, struct kfd_dev *dev,
 static void uninitialize_cik(struct kernel_queue *kq)
 {
 }
+
+static void submit_packet_cik(struct kernel_queue *kq)
+{
+	*kq->wptr_kernel = kq->pending_wptr;
+	write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
+				kq->pending_wptr);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c
new file mode 100644
index 000000000000..684a3bf07efd
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c
@@ -0,0 +1,340 @@
+/*
+ * Copyright 2016-2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "kfd_kernel_queue.h"
+#include "kfd_device_queue_manager.h"
+#include "kfd_pm4_headers_ai.h"
+#include "kfd_pm4_opcodes.h"
+
+static bool initialize_v9(struct kernel_queue *kq, struct kfd_dev *dev,
+			enum kfd_queue_type type, unsigned int queue_size);
+static void uninitialize_v9(struct kernel_queue *kq);
+static void submit_packet_v9(struct kernel_queue *kq);
+
+void kernel_queue_init_v9(struct kernel_queue_ops *ops)
+{
+	ops->initialize = initialize_v9;
+	ops->uninitialize = uninitialize_v9;
+	ops->submit_packet = submit_packet_v9;
+}
+
+static bool initialize_v9(struct kernel_queue *kq, struct kfd_dev *dev,
+			enum kfd_queue_type type, unsigned int queue_size)
+{
+	int retval;
+
+	retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
+	if (retval)
+		return false;
+
+	kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
+	kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
+
+	memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
+
+	return true;
+}
+
+static void uninitialize_v9(struct kernel_queue *kq)
+{
+	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
+}
+
+static void submit_packet_v9(struct kernel_queue *kq)
+{
+	*kq->wptr64_kernel = kq->pending_wptr64;
+	write_kernel_doorbell64(kq->queue->properties.doorbell_ptr,
+				kq->pending_wptr64);
+}
+
+static int pm_map_process_v9(struct packet_manager *pm,
+		uint32_t *buffer, struct qcm_process_device *qpd)
+{
+	struct pm4_mes_map_process *packet;
+	uint64_t vm_page_table_base_addr =
+		(uint64_t)(qpd->page_table_base) << 12;
+
+	packet = (struct pm4_mes_map_process *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mes_map_process));
+
+	packet->header.u32All = pm_build_pm4_header(IT_MAP_PROCESS,
+					sizeof(struct pm4_mes_map_process));
+	packet->bitfields2.diq_enable = (qpd->is_debug) ? 1 : 0;
+	packet->bitfields2.process_quantum = 1;
+	packet->bitfields2.pasid = qpd->pqm->process->pasid;
+	packet->bitfields14.gds_size = qpd->gds_size;
+	packet->bitfields14.num_gws = qpd->num_gws;
+	packet->bitfields14.num_oac = qpd->num_oac;
+	packet->bitfields14.sdma_enable = 1;
+	packet->bitfields14.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
+
+	packet->sh_mem_config = qpd->sh_mem_config;
+	packet->sh_mem_bases = qpd->sh_mem_bases;
+	packet->sq_shader_tba_lo = lower_32_bits(qpd->tba_addr >> 8);
+	packet->sq_shader_tba_hi = upper_32_bits(qpd->tba_addr >> 8);
+	packet->sq_shader_tma_lo = lower_32_bits(qpd->tma_addr >> 8);
+	packet->sq_shader_tma_hi = upper_32_bits(qpd->tma_addr >> 8);
+
+	packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
+	packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
+
+	packet->vm_context_page_table_base_addr_lo32 =
+			lower_32_bits(vm_page_table_base_addr);
+	packet->vm_context_page_table_base_addr_hi32 =
+			upper_32_bits(vm_page_table_base_addr);
+
+	return 0;
+}
+
+static int pm_runlist_v9(struct packet_manager *pm, uint32_t *buffer,
+			uint64_t ib, size_t ib_size_in_dwords, bool chain)
+{
+	struct pm4_mes_runlist *packet;
+
+	int concurrent_proc_cnt = 0;
+	struct kfd_dev *kfd = pm->dqm->dev;
+
+	/* Determine the number of processes to map together to HW:
+	 * it can not exceed the number of VMIDs available to the
+	 * scheduler, and it is determined by the smaller of the number
+	 * of processes in the runlist and kfd module parameter
+	 * hws_max_conc_proc.
+	 * Note: the arbitration between the number of VMIDs and
+	 * hws_max_conc_proc has been done in
+	 * kgd2kfd_device_init().
+	 */
+	concurrent_proc_cnt = min(pm->dqm->processes_count,
+			kfd->max_proc_per_quantum);
+
+	packet = (struct pm4_mes_runlist *)buffer;
+
+	memset(buffer, 0, sizeof(struct pm4_mes_runlist));
+	packet->header.u32All = pm_build_pm4_header(IT_RUN_LIST,
+						sizeof(struct pm4_mes_runlist));
+
+	packet->bitfields4.ib_size = ib_size_in_dwords;
+	packet->bitfields4.chain = chain ? 1 : 0;
+	packet->bitfields4.offload_polling = 0;
+	packet->bitfields4.valid = 1;
+	packet->bitfields4.process_cnt = concurrent_proc_cnt;
+	packet->ordinal2 = lower_32_bits(ib);
+	packet->ib_base_hi = upper_32_bits(ib);
+
+	return 0;
+}
+
+static int pm_map_queues_v9(struct packet_manager *pm, uint32_t *buffer,
+		struct queue *q, bool is_static)
+{
+	struct pm4_mes_map_queues *packet;
+	bool use_static = is_static;
+
+	packet = (struct pm4_mes_map_queues *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mes_map_queues));
+
+	packet->header.u32All = pm_build_pm4_header(IT_MAP_QUEUES,
+					sizeof(struct pm4_mes_map_queues));
+	packet->bitfields2.alloc_format =
+		alloc_format__mes_map_queues__one_per_pipe_vi;
+	packet->bitfields2.num_queues = 1;
+	packet->bitfields2.queue_sel =
+		queue_sel__mes_map_queues__map_to_hws_determined_queue_slots_vi;
+
+	packet->bitfields2.engine_sel =
+		engine_sel__mes_map_queues__compute_vi;
+	packet->bitfields2.queue_type =
+		queue_type__mes_map_queues__normal_compute_vi;
+
+	switch (q->properties.type) {
+	case KFD_QUEUE_TYPE_COMPUTE:
+		if (use_static)
+			packet->bitfields2.queue_type =
+		queue_type__mes_map_queues__normal_latency_static_queue_vi;
+		break;
+	case KFD_QUEUE_TYPE_DIQ:
+		packet->bitfields2.queue_type =
+			queue_type__mes_map_queues__debug_interface_queue_vi;
+		break;
+	case KFD_QUEUE_TYPE_SDMA:
+		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
+				engine_sel__mes_map_queues__sdma0_vi;
+		use_static = false; /* no static queues under SDMA */
+		break;
+	default:
+		WARN(1, "queue type %d", q->properties.type);
+		return -EINVAL;
+	}
+	packet->bitfields3.doorbell_offset =
+			q->properties.doorbell_off;
+
+	packet->mqd_addr_lo =
+			lower_32_bits(q->gart_mqd_addr);
+
+	packet->mqd_addr_hi =
+			upper_32_bits(q->gart_mqd_addr);
+
+	packet->wptr_addr_lo =
+			lower_32_bits((uint64_t)q->properties.write_ptr);
+
+	packet->wptr_addr_hi =
+			upper_32_bits((uint64_t)q->properties.write_ptr);
+
+	return 0;
+}
+
+static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer,
+			enum kfd_queue_type type,
+			enum kfd_unmap_queues_filter filter,
+			uint32_t filter_param, bool reset,
+			unsigned int sdma_engine)
+{
+	struct pm4_mes_unmap_queues *packet;
+
+	packet = (struct pm4_mes_unmap_queues *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues));
+
+	packet->header.u32All = pm_build_pm4_header(IT_UNMAP_QUEUES,
+					sizeof(struct pm4_mes_unmap_queues));
+	switch (type) {
+	case KFD_QUEUE_TYPE_COMPUTE:
+	case KFD_QUEUE_TYPE_DIQ:
+		packet->bitfields2.engine_sel =
+			engine_sel__mes_unmap_queues__compute;
+		break;
+	case KFD_QUEUE_TYPE_SDMA:
+		packet->bitfields2.engine_sel =
+			engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
+		break;
+	default:
+		WARN(1, "queue type %d", type);
+		return -EINVAL;
+	}
+
+	if (reset)
+		packet->bitfields2.action =
+			action__mes_unmap_queues__reset_queues;
+	else
+		packet->bitfields2.action =
+			action__mes_unmap_queues__preempt_queues;
+
+	switch (filter) {
+	case KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE:
+		packet->bitfields2.queue_sel =
+			queue_sel__mes_unmap_queues__perform_request_on_specified_queues;
+		packet->bitfields2.num_queues = 1;
+		packet->bitfields3b.doorbell_offset0 = filter_param;
+		break;
+	case KFD_UNMAP_QUEUES_FILTER_BY_PASID:
+		packet->bitfields2.queue_sel =
+			queue_sel__mes_unmap_queues__perform_request_on_pasid_queues;
+		packet->bitfields3a.pasid = filter_param;
+		break;
+	case KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES:
+		packet->bitfields2.queue_sel =
+			queue_sel__mes_unmap_queues__unmap_all_queues;
+		break;
+	case KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES:
+		/* in this case, we do not preempt static queues */
+		packet->bitfields2.queue_sel =
+			queue_sel__mes_unmap_queues__unmap_all_non_static_queues;
+		break;
+	default:
+		WARN(1, "filter %d", filter);
+		return -EINVAL;
+	}
+
+	return 0;
+
+}
+
+static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer,
+			uint64_t fence_address,	uint32_t fence_value)
+{
+	struct pm4_mes_query_status *packet;
+
+	packet = (struct pm4_mes_query_status *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mes_query_status));
+
+
+	packet->header.u32All = pm_build_pm4_header(IT_QUERY_STATUS,
+					sizeof(struct pm4_mes_query_status));
+
+	packet->bitfields2.context_id = 0;
+	packet->bitfields2.interrupt_sel =
+			interrupt_sel__mes_query_status__completion_status;
+	packet->bitfields2.command =
+			command__mes_query_status__fence_only_after_write_ack;
+
+	packet->addr_hi = upper_32_bits((uint64_t)fence_address);
+	packet->addr_lo = lower_32_bits((uint64_t)fence_address);
+	packet->data_hi = upper_32_bits((uint64_t)fence_value);
+	packet->data_lo = lower_32_bits((uint64_t)fence_value);
+
+	return 0;
+}
+
+
+static int pm_release_mem_v9(uint64_t gpu_addr, uint32_t *buffer)
+{
+	struct pm4_mec_release_mem *packet;
+
+	packet = (struct pm4_mec_release_mem *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mec_release_mem));
+
+	packet->header.u32All = pm_build_pm4_header(IT_RELEASE_MEM,
+					sizeof(struct pm4_mec_release_mem));
+
+	packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
+	packet->bitfields2.event_index = event_index__mec_release_mem__end_of_pipe;
+	packet->bitfields2.tcl1_action_ena = 1;
+	packet->bitfields2.tc_action_ena = 1;
+	packet->bitfields2.cache_policy = cache_policy__mec_release_mem__lru;
+
+	packet->bitfields3.data_sel = data_sel__mec_release_mem__send_32_bit_low;
+	packet->bitfields3.int_sel =
+		int_sel__mec_release_mem__send_interrupt_after_write_confirm;
+
+	packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
+	packet->address_hi = upper_32_bits(gpu_addr);
+
+	packet->data_lo = 0;
+
+	return 0;
+}
+
+const struct packet_manager_funcs kfd_v9_pm_funcs = {
+	.map_process		= pm_map_process_v9,
+	.runlist		= pm_runlist_v9,
+	.set_resources		= pm_set_resources_vi,
+	.map_queues		= pm_map_queues_v9,
+	.unmap_queues		= pm_unmap_queues_v9,
+	.query_status		= pm_query_status_v9,
+	.release_mem		= pm_release_mem_v9,
+	.map_process_size	= sizeof(struct pm4_mes_map_process),
+	.runlist_size		= sizeof(struct pm4_mes_runlist),
+	.set_resources_size	= sizeof(struct pm4_mes_set_resources),
+	.map_queues_size	= sizeof(struct pm4_mes_map_queues),
+	.unmap_queues_size	= sizeof(struct pm4_mes_unmap_queues),
+	.query_status_size	= sizeof(struct pm4_mes_query_status),
+	.release_mem_size	= sizeof(struct pm4_mec_release_mem)
+};
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c
index f1d48281e322..bf20c6d32ef3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c
@@ -22,15 +22,20 @@
  */
 
 #include "kfd_kernel_queue.h"
+#include "kfd_device_queue_manager.h"
+#include "kfd_pm4_headers_vi.h"
+#include "kfd_pm4_opcodes.h"
 
 static bool initialize_vi(struct kernel_queue *kq, struct kfd_dev *dev,
 			enum kfd_queue_type type, unsigned int queue_size);
 static void uninitialize_vi(struct kernel_queue *kq);
+static void submit_packet_vi(struct kernel_queue *kq);
 
 void kernel_queue_init_vi(struct kernel_queue_ops *ops)
 {
 	ops->initialize = initialize_vi;
 	ops->uninitialize = uninitialize_vi;
+	ops->submit_packet = submit_packet_vi;
 }
 
 static bool initialize_vi(struct kernel_queue *kq, struct kfd_dev *dev,
@@ -54,3 +59,317 @@ static void uninitialize_vi(struct kernel_queue *kq)
 {
 	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
 }
+
+static void submit_packet_vi(struct kernel_queue *kq)
+{
+	*kq->wptr_kernel = kq->pending_wptr;
+	write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
+				kq->pending_wptr);
+}
+
+unsigned int pm_build_pm4_header(unsigned int opcode, size_t packet_size)
+{
+	union PM4_MES_TYPE_3_HEADER header;
+
+	header.u32All = 0;
+	header.opcode = opcode;
+	header.count = packet_size / 4 - 2;
+	header.type = PM4_TYPE_3;
+
+	return header.u32All;
+}
+
+static int pm_map_process_vi(struct packet_manager *pm, uint32_t *buffer,
+				struct qcm_process_device *qpd)
+{
+	struct pm4_mes_map_process *packet;
+
+	packet = (struct pm4_mes_map_process *)buffer;
+
+	memset(buffer, 0, sizeof(struct pm4_mes_map_process));
+
+	packet->header.u32All = pm_build_pm4_header(IT_MAP_PROCESS,
+					sizeof(struct pm4_mes_map_process));
+	packet->bitfields2.diq_enable = (qpd->is_debug) ? 1 : 0;
+	packet->bitfields2.process_quantum = 1;
+	packet->bitfields2.pasid = qpd->pqm->process->pasid;
+	packet->bitfields3.page_table_base = qpd->page_table_base;
+	packet->bitfields10.gds_size = qpd->gds_size;
+	packet->bitfields10.num_gws = qpd->num_gws;
+	packet->bitfields10.num_oac = qpd->num_oac;
+	packet->bitfields10.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
+
+	packet->sh_mem_config = qpd->sh_mem_config;
+	packet->sh_mem_bases = qpd->sh_mem_bases;
+	packet->sh_mem_ape1_base = qpd->sh_mem_ape1_base;
+	packet->sh_mem_ape1_limit = qpd->sh_mem_ape1_limit;
+
+	packet->sh_hidden_private_base_vmid = qpd->sh_hidden_private_base;
+
+	packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
+	packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
+
+	return 0;
+}
+
+static int pm_runlist_vi(struct packet_manager *pm, uint32_t *buffer,
+			uint64_t ib, size_t ib_size_in_dwords, bool chain)
+{
+	struct pm4_mes_runlist *packet;
+	int concurrent_proc_cnt = 0;
+	struct kfd_dev *kfd = pm->dqm->dev;
+
+	if (WARN_ON(!ib))
+		return -EFAULT;
+
+	/* Determine the number of processes to map together to HW:
+	 * it can not exceed the number of VMIDs available to the
+	 * scheduler, and it is determined by the smaller of the number
+	 * of processes in the runlist and kfd module parameter
+	 * hws_max_conc_proc.
+	 * Note: the arbitration between the number of VMIDs and
+	 * hws_max_conc_proc has been done in
+	 * kgd2kfd_device_init().
+	 */
+	concurrent_proc_cnt = min(pm->dqm->processes_count,
+			kfd->max_proc_per_quantum);
+
+	packet = (struct pm4_mes_runlist *)buffer;
+
+	memset(buffer, 0, sizeof(struct pm4_mes_runlist));
+	packet->header.u32All = pm_build_pm4_header(IT_RUN_LIST,
+						sizeof(struct pm4_mes_runlist));
+
+	packet->bitfields4.ib_size = ib_size_in_dwords;
+	packet->bitfields4.chain = chain ? 1 : 0;
+	packet->bitfields4.offload_polling = 0;
+	packet->bitfields4.valid = 1;
+	packet->bitfields4.process_cnt = concurrent_proc_cnt;
+	packet->ordinal2 = lower_32_bits(ib);
+	packet->bitfields3.ib_base_hi = upper_32_bits(ib);
+
+	return 0;
+}
+
+int pm_set_resources_vi(struct packet_manager *pm, uint32_t *buffer,
+				struct scheduling_resources *res)
+{
+	struct pm4_mes_set_resources *packet;
+
+	packet = (struct pm4_mes_set_resources *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mes_set_resources));
+
+	packet->header.u32All = pm_build_pm4_header(IT_SET_RESOURCES,
+					sizeof(struct pm4_mes_set_resources));
+
+	packet->bitfields2.queue_type =
+			queue_type__mes_set_resources__hsa_interface_queue_hiq;
+	packet->bitfields2.vmid_mask = res->vmid_mask;
+	packet->bitfields2.unmap_latency = KFD_UNMAP_LATENCY_MS / 100;
+	packet->bitfields7.oac_mask = res->oac_mask;
+	packet->bitfields8.gds_heap_base = res->gds_heap_base;
+	packet->bitfields8.gds_heap_size = res->gds_heap_size;
+
+	packet->gws_mask_lo = lower_32_bits(res->gws_mask);
+	packet->gws_mask_hi = upper_32_bits(res->gws_mask);
+
+	packet->queue_mask_lo = lower_32_bits(res->queue_mask);
+	packet->queue_mask_hi = upper_32_bits(res->queue_mask);
+
+	return 0;
+}
+
+static int pm_map_queues_vi(struct packet_manager *pm, uint32_t *buffer,
+		struct queue *q, bool is_static)
+{
+	struct pm4_mes_map_queues *packet;
+	bool use_static = is_static;
+
+	packet = (struct pm4_mes_map_queues *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mes_map_queues));
+
+	packet->header.u32All = pm_build_pm4_header(IT_MAP_QUEUES,
+					sizeof(struct pm4_mes_map_queues));
+	packet->bitfields2.alloc_format =
+		alloc_format__mes_map_queues__one_per_pipe_vi;
+	packet->bitfields2.num_queues = 1;
+	packet->bitfields2.queue_sel =
+		queue_sel__mes_map_queues__map_to_hws_determined_queue_slots_vi;
+
+	packet->bitfields2.engine_sel =
+		engine_sel__mes_map_queues__compute_vi;
+	packet->bitfields2.queue_type =
+		queue_type__mes_map_queues__normal_compute_vi;
+
+	switch (q->properties.type) {
+	case KFD_QUEUE_TYPE_COMPUTE:
+		if (use_static)
+			packet->bitfields2.queue_type =
+		queue_type__mes_map_queues__normal_latency_static_queue_vi;
+		break;
+	case KFD_QUEUE_TYPE_DIQ:
+		packet->bitfields2.queue_type =
+			queue_type__mes_map_queues__debug_interface_queue_vi;
+		break;
+	case KFD_QUEUE_TYPE_SDMA:
+		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
+				engine_sel__mes_map_queues__sdma0_vi;
+		use_static = false; /* no static queues under SDMA */
+		break;
+	default:
+		WARN(1, "queue type %d", q->properties.type);
+		return -EINVAL;
+	}
+	packet->bitfields3.doorbell_offset =
+			q->properties.doorbell_off;
+
+	packet->mqd_addr_lo =
+			lower_32_bits(q->gart_mqd_addr);
+
+	packet->mqd_addr_hi =
+			upper_32_bits(q->gart_mqd_addr);
+
+	packet->wptr_addr_lo =
+			lower_32_bits((uint64_t)q->properties.write_ptr);
+
+	packet->wptr_addr_hi =
+			upper_32_bits((uint64_t)q->properties.write_ptr);
+
+	return 0;
+}
+
+static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer,
+			enum kfd_queue_type type,
+			enum kfd_unmap_queues_filter filter,
+			uint32_t filter_param, bool reset,
+			unsigned int sdma_engine)
+{
+	struct pm4_mes_unmap_queues *packet;
+
+	packet = (struct pm4_mes_unmap_queues *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues));
+
+	packet->header.u32All = pm_build_pm4_header(IT_UNMAP_QUEUES,
+					sizeof(struct pm4_mes_unmap_queues));
+	switch (type) {
+	case KFD_QUEUE_TYPE_COMPUTE:
+	case KFD_QUEUE_TYPE_DIQ:
+		packet->bitfields2.engine_sel =
+			engine_sel__mes_unmap_queues__compute;
+		break;
+	case KFD_QUEUE_TYPE_SDMA:
+		packet->bitfields2.engine_sel =
+			engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
+		break;
+	default:
+		WARN(1, "queue type %d", type);
+		return -EINVAL;
+	}
+
+	if (reset)
+		packet->bitfields2.action =
+			action__mes_unmap_queues__reset_queues;
+	else
+		packet->bitfields2.action =
+			action__mes_unmap_queues__preempt_queues;
+
+	switch (filter) {
+	case KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE:
+		packet->bitfields2.queue_sel =
+			queue_sel__mes_unmap_queues__perform_request_on_specified_queues;
+		packet->bitfields2.num_queues = 1;
+		packet->bitfields3b.doorbell_offset0 = filter_param;
+		break;
+	case KFD_UNMAP_QUEUES_FILTER_BY_PASID:
+		packet->bitfields2.queue_sel =
+			queue_sel__mes_unmap_queues__perform_request_on_pasid_queues;
+		packet->bitfields3a.pasid = filter_param;
+		break;
+	case KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES:
+		packet->bitfields2.queue_sel =
+			queue_sel__mes_unmap_queues__unmap_all_queues;
+		break;
+	case KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES:
+		/* in this case, we do not preempt static queues */
+		packet->bitfields2.queue_sel =
+			queue_sel__mes_unmap_queues__unmap_all_non_static_queues;
+		break;
+	default:
+		WARN(1, "filter %d", filter);
+		return -EINVAL;
+	}
+
+	return 0;
+
+}
+
+static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer,
+			uint64_t fence_address,	uint32_t fence_value)
+{
+	struct pm4_mes_query_status *packet;
+
+	packet = (struct pm4_mes_query_status *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mes_query_status));
+
+	packet->header.u32All = pm_build_pm4_header(IT_QUERY_STATUS,
+					sizeof(struct pm4_mes_query_status));
+
+	packet->bitfields2.context_id = 0;
+	packet->bitfields2.interrupt_sel =
+			interrupt_sel__mes_query_status__completion_status;
+	packet->bitfields2.command =
+			command__mes_query_status__fence_only_after_write_ack;
+
+	packet->addr_hi = upper_32_bits((uint64_t)fence_address);
+	packet->addr_lo = lower_32_bits((uint64_t)fence_address);
+	packet->data_hi = upper_32_bits((uint64_t)fence_value);
+	packet->data_lo = lower_32_bits((uint64_t)fence_value);
+
+	return 0;
+}
+
+static int pm_release_mem_vi(uint64_t gpu_addr, uint32_t *buffer)
+{
+	struct pm4_mec_release_mem *packet;
+
+	packet = (struct pm4_mec_release_mem *)buffer;
+	memset(buffer, 0, sizeof(*packet));
+
+	packet->header.u32All = pm_build_pm4_header(IT_RELEASE_MEM,
+						 sizeof(*packet));
+
+	packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
+	packet->bitfields2.event_index = event_index___release_mem__end_of_pipe;
+	packet->bitfields2.tcl1_action_ena = 1;
+	packet->bitfields2.tc_action_ena = 1;
+	packet->bitfields2.cache_policy = cache_policy___release_mem__lru;
+	packet->bitfields2.atc = 0;
+
+	packet->bitfields3.data_sel = data_sel___release_mem__send_32_bit_low;
+	packet->bitfields3.int_sel =
+		int_sel___release_mem__send_interrupt_after_write_confirm;
+
+	packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
+	packet->address_hi = upper_32_bits(gpu_addr);
+
+	packet->data_lo = 0;
+
+	return 0;
+}
+
+const struct packet_manager_funcs kfd_vi_pm_funcs = {
+	.map_process		= pm_map_process_vi,
+	.runlist		= pm_runlist_vi,
+	.set_resources		= pm_set_resources_vi,
+	.map_queues		= pm_map_queues_vi,
+	.unmap_queues		= pm_unmap_queues_vi,
+	.query_status		= pm_query_status_vi,
+	.release_mem		= pm_release_mem_vi,
+	.map_process_size	= sizeof(struct pm4_mes_map_process),
+	.runlist_size		= sizeof(struct pm4_mes_runlist),
+	.set_resources_size	= sizeof(struct pm4_mes_set_resources),
+	.map_queues_size	= sizeof(struct pm4_mes_map_queues),
+	.unmap_queues_size	= sizeof(struct pm4_mes_unmap_queues),
+	.query_status_size	= sizeof(struct pm4_mes_query_status),
+	.release_mem_size	= sizeof(struct pm4_mec_release_mem)
+};
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index e0c07d24d251..76bf2dc8aec4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -43,6 +43,8 @@ static const struct kgd2kfd_calls kgd2kfd = {
 	.interrupt	= kgd2kfd_interrupt,
 	.suspend	= kgd2kfd_suspend,
 	.resume		= kgd2kfd_resume,
+	.quiesce_mm	= kgd2kfd_quiesce_mm,
+	.resume_mm	= kgd2kfd_resume_mm,
 	.schedule_evict_and_restore_process =
 			  kgd2kfd_schedule_evict_and_restore_process,
 };
@@ -81,6 +83,11 @@ module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
 	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
 
+int vega10_noretry;
+module_param_named(noretry, vega10_noretry, int, 0644);
+MODULE_PARM_DESC(noretry,
+	"Set sh_mem_config.retry_disable on Vega10 (0 = retry enabled (default), 1 = retry disabled)");
+
 static int amdkfd_init_completed;
 
 int kgd2kfd_init(unsigned int interface_version,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index ee7061e1c466..4b8eb506642b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -38,6 +38,9 @@ struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 	case CHIP_POLARIS10:
 	case CHIP_POLARIS11:
 		return mqd_manager_init_vi_tonga(type, dev);
+	case CHIP_VEGA10:
+	case CHIP_RAVEN:
+		return mqd_manager_init_v9(type, dev);
 	default:
 		WARN(1, "Unexpected ASIC family %u",
 		     dev->device_info->asic_family);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index c00c325ed3c9..06eaa218eba6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -79,10 +79,6 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
 	m->cp_mqd_base_addr_hi        = upper_32_bits(addr);
 
-	m->cp_hqd_ib_control = DEFAULT_MIN_IB_AVAIL_SIZE | IB_ATC_EN;
-	/* Although WinKFD writes this, I suspect it should not be necessary */
-	m->cp_hqd_ib_control = IB_ATC_EN | DEFAULT_MIN_IB_AVAIL_SIZE;
-
 	m->cp_hqd_quantum = QUANTUM_EN | QUANTUM_SCALE_1MS |
 				QUANTUM_DURATION(10);
 
@@ -412,7 +408,7 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
+	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
 	if (!mqd)
 		return NULL;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
new file mode 100644
index 000000000000..684054ff02cd
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -0,0 +1,443 @@
+/*
+ * Copyright 2016-2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include "kfd_priv.h"
+#include "kfd_mqd_manager.h"
+#include "v9_structs.h"
+#include "gc/gc_9_0_offset.h"
+#include "gc/gc_9_0_sh_mask.h"
+#include "sdma0/sdma0_4_0_sh_mask.h"
+
+static inline struct v9_mqd *get_mqd(void *mqd)
+{
+	return (struct v9_mqd *)mqd;
+}
+
+static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
+{
+	return (struct v9_sdma_mqd *)mqd;
+}
+
+static int init_mqd(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *q)
+{
+	int retval;
+	uint64_t addr;
+	struct v9_mqd *m;
+	struct kfd_dev *kfd = mm->dev;
+
+	/* From V9,  for CWSR, the control stack is located on the next page
+	 * boundary after the mqd, we will use the gtt allocation function
+	 * instead of sub-allocation function.
+	 */
+	if (kfd->cwsr_enabled && (q->type == KFD_QUEUE_TYPE_COMPUTE)) {
+		*mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
+		if (!*mqd_mem_obj)
+			return -ENOMEM;
+		retval = kfd->kfd2kgd->init_gtt_mem_allocation(kfd->kgd,
+			ALIGN(q->ctl_stack_size, PAGE_SIZE) +
+				ALIGN(sizeof(struct v9_mqd), PAGE_SIZE),
+			&((*mqd_mem_obj)->gtt_mem),
+			&((*mqd_mem_obj)->gpu_addr),
+			(void *)&((*mqd_mem_obj)->cpu_ptr));
+	} else
+		retval = kfd_gtt_sa_allocate(mm->dev, sizeof(struct v9_mqd),
+				mqd_mem_obj);
+	if (retval != 0)
+		return -ENOMEM;
+
+	m = (struct v9_mqd *) (*mqd_mem_obj)->cpu_ptr;
+	addr = (*mqd_mem_obj)->gpu_addr;
+
+	memset(m, 0, sizeof(struct v9_mqd));
+
+	m->header = 0xC0310800;
+	m->compute_pipelinestat_enable = 1;
+	m->compute_static_thread_mgmt_se0 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se1 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se2 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se3 = 0xFFFFFFFF;
+
+	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
+			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
+
+	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
+
+	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
+	m->cp_mqd_base_addr_hi        = upper_32_bits(addr);
+
+	m->cp_hqd_quantum = 1 << CP_HQD_QUANTUM__QUANTUM_EN__SHIFT |
+			1 << CP_HQD_QUANTUM__QUANTUM_SCALE__SHIFT |
+			10 << CP_HQD_QUANTUM__QUANTUM_DURATION__SHIFT;
+
+	m->cp_hqd_pipe_priority = 1;
+	m->cp_hqd_queue_priority = 15;
+
+	if (q->format == KFD_QUEUE_FORMAT_AQL) {
+		m->cp_hqd_aql_control =
+			1 << CP_HQD_AQL_CONTROL__CONTROL0__SHIFT;
+	}
+
+	if (q->tba_addr) {
+		m->compute_pgm_rsrc2 |=
+			(1 << COMPUTE_PGM_RSRC2__TRAP_PRESENT__SHIFT);
+	}
+
+	if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address) {
+		m->cp_hqd_persistent_state |=
+			(1 << CP_HQD_PERSISTENT_STATE__QSWITCH_MODE__SHIFT);
+		m->cp_hqd_ctx_save_base_addr_lo =
+			lower_32_bits(q->ctx_save_restore_area_address);
+		m->cp_hqd_ctx_save_base_addr_hi =
+			upper_32_bits(q->ctx_save_restore_area_address);
+		m->cp_hqd_ctx_save_size = q->ctx_save_restore_area_size;
+		m->cp_hqd_cntl_stack_size = q->ctl_stack_size;
+		m->cp_hqd_cntl_stack_offset = q->ctl_stack_size;
+		m->cp_hqd_wg_state_offset = q->ctl_stack_size;
+	}
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+	retval = mm->update_mqd(mm, m, q);
+
+	return retval;
+}
+
+static int load_mqd(struct mqd_manager *mm, void *mqd,
+			uint32_t pipe_id, uint32_t queue_id,
+			struct queue_properties *p, struct mm_struct *mms)
+{
+	/* AQL write pointer counts in 64B packets, PM4/CP counts in dwords. */
+	uint32_t wptr_shift = (p->format == KFD_QUEUE_FORMAT_AQL ? 4 : 0);
+
+	return mm->dev->kfd2kgd->hqd_load(mm->dev->kgd, mqd, pipe_id, queue_id,
+					  (uint32_t __user *)p->write_ptr,
+					  wptr_shift, 0, mms);
+}
+
+static int update_mqd(struct mqd_manager *mm, void *mqd,
+		      struct queue_properties *q)
+{
+	struct v9_mqd *m;
+
+	m = get_mqd(mqd);
+
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
+	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
+
+	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
+	m->cp_hqd_pq_base_hi = upper_32_bits((uint64_t)q->queue_address >> 8);
+
+	m->cp_hqd_pq_rptr_report_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
+	m->cp_hqd_pq_rptr_report_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
+	m->cp_hqd_pq_wptr_poll_addr_lo = lower_32_bits((uint64_t)q->write_ptr);
+	m->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits((uint64_t)q->write_ptr);
+
+	m->cp_hqd_pq_doorbell_control =
+		q->doorbell_off <<
+			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+			m->cp_hqd_pq_doorbell_control);
+
+	m->cp_hqd_ib_control =
+		3 << CP_HQD_IB_CONTROL__MIN_IB_AVAIL_SIZE__SHIFT |
+		1 << CP_HQD_IB_CONTROL__IB_EXE_DISABLE__SHIFT;
+
+	/*
+	 * HW does not clamp this field correctly. Maximum EOP queue size
+	 * is constrained by per-SE EOP done signal count, which is 8-bit.
+	 * Limit is 0xFF EOP entries (= 0x7F8 dwords). CP will not submit
+	 * more than (EOP entry count - 1) so a queue size of 0x800 dwords
+	 * is safe, giving a maximum field value of 0xA.
+	 */
+	m->cp_hqd_eop_control = min(0xA,
+		order_base_2(q->eop_ring_buffer_size / 4) - 1);
+	m->cp_hqd_eop_base_addr_lo =
+			lower_32_bits(q->eop_ring_buffer_address >> 8);
+	m->cp_hqd_eop_base_addr_hi =
+			upper_32_bits(q->eop_ring_buffer_address >> 8);
+
+	m->cp_hqd_iq_timer = 0;
+
+	m->cp_hqd_vmid = q->vmid;
+
+	if (q->format == KFD_QUEUE_FORMAT_AQL) {
+		m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__NO_UPDATE_RPTR_MASK |
+				2 << CP_HQD_PQ_CONTROL__SLOT_BASED_WPTR__SHIFT |
+				1 << CP_HQD_PQ_CONTROL__QUEUE_FULL_EN__SHIFT |
+				1 << CP_HQD_PQ_CONTROL__WPP_CLAMP_EN__SHIFT;
+		m->cp_hqd_pq_doorbell_control |= 1 <<
+			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_BIF_DROP__SHIFT;
+	}
+	if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address)
+		m->cp_hqd_ctx_save_control = 0;
+
+	q->is_active = (q->queue_size > 0 &&
+			q->queue_address != 0 &&
+			q->queue_percent > 0 &&
+			!q->is_evicted);
+
+	return 0;
+}
+
+
+static int destroy_mqd(struct mqd_manager *mm, void *mqd,
+			enum kfd_preempt_type type,
+			unsigned int timeout, uint32_t pipe_id,
+			uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_destroy
+		(mm->dev->kgd, mqd, type, timeout,
+		pipe_id, queue_id);
+}
+
+static void uninit_mqd(struct mqd_manager *mm, void *mqd,
+			struct kfd_mem_obj *mqd_mem_obj)
+{
+	struct kfd_dev *kfd = mm->dev;
+
+	if (mqd_mem_obj->gtt_mem) {
+		kfd->kfd2kgd->free_gtt_mem(kfd->kgd, mqd_mem_obj->gtt_mem);
+		kfree(mqd_mem_obj);
+	} else {
+		kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
+	}
+}
+
+static bool is_occupied(struct mqd_manager *mm, void *mqd,
+			uint64_t queue_address,	uint32_t pipe_id,
+			uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_is_occupied(
+		mm->dev->kgd, queue_address,
+		pipe_id, queue_id);
+}
+
+static int init_mqd_hiq(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *q)
+{
+	struct v9_mqd *m;
+	int retval = init_mqd(mm, mqd, mqd_mem_obj, gart_addr, q);
+
+	if (retval != 0)
+		return retval;
+
+	m = get_mqd(*mqd);
+
+	m->cp_hqd_pq_control |= 1 << CP_HQD_PQ_CONTROL__PRIV_STATE__SHIFT |
+			1 << CP_HQD_PQ_CONTROL__KMD_QUEUE__SHIFT;
+
+	return retval;
+}
+
+static int update_mqd_hiq(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct v9_mqd *m;
+	int retval = update_mqd(mm, mqd, q);
+
+	if (retval != 0)
+		return retval;
+
+	/* TODO: what's the point? update_mqd already does this. */
+	m = get_mqd(mqd);
+	m->cp_hqd_vmid = q->vmid;
+	return retval;
+}
+
+static int init_mqd_sdma(struct mqd_manager *mm, void **mqd,
+		struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
+		struct queue_properties *q)
+{
+	int retval;
+	struct v9_sdma_mqd *m;
+
+
+	retval = kfd_gtt_sa_allocate(mm->dev,
+			sizeof(struct v9_sdma_mqd),
+			mqd_mem_obj);
+
+	if (retval != 0)
+		return -ENOMEM;
+
+	m = (struct v9_sdma_mqd *) (*mqd_mem_obj)->cpu_ptr;
+
+	memset(m, 0, sizeof(struct v9_sdma_mqd));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = (*mqd_mem_obj)->gpu_addr;
+
+	retval = mm->update_mqd(mm, m, q);
+
+	return retval;
+}
+
+static void uninit_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		struct kfd_mem_obj *mqd_mem_obj)
+{
+	kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
+}
+
+static int load_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		uint32_t pipe_id, uint32_t queue_id,
+		struct queue_properties *p, struct mm_struct *mms)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->kgd, mqd,
+					       (uint32_t __user *)p->write_ptr,
+					       mms);
+}
+
+#define SDMA_RLC_DUMMY_DEFAULT 0xf
+
+static int update_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		struct queue_properties *q)
+{
+	struct v9_sdma_mqd *m;
+
+	m = get_sdma_mqd(mqd);
+	m->sdmax_rlcx_rb_cntl = order_base_2(q->queue_size / 4)
+		<< SDMA0_RLC0_RB_CNTL__RB_SIZE__SHIFT |
+		q->vmid << SDMA0_RLC0_RB_CNTL__RB_VMID__SHIFT |
+		1 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
+		6 << SDMA0_RLC0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT;
+
+	m->sdmax_rlcx_rb_base = lower_32_bits(q->queue_address >> 8);
+	m->sdmax_rlcx_rb_base_hi = upper_32_bits(q->queue_address >> 8);
+	m->sdmax_rlcx_rb_rptr_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
+	m->sdmax_rlcx_rb_rptr_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
+	m->sdmax_rlcx_doorbell_offset =
+		q->doorbell_off << SDMA0_RLC0_DOORBELL_OFFSET__OFFSET__SHIFT;
+
+	m->sdma_engine_id = q->sdma_engine_id;
+	m->sdma_queue_id = q->sdma_queue_id;
+	m->sdmax_rlcx_dummy_reg = SDMA_RLC_DUMMY_DEFAULT;
+
+	q->is_active = (q->queue_size > 0 &&
+			q->queue_address != 0 &&
+			q->queue_percent > 0 &&
+			!q->is_evicted);
+
+	return 0;
+}
+
+/*
+ *  * preempt type here is ignored because there is only one way
+ *  * to preempt sdma queue
+ */
+static int destroy_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		enum kfd_preempt_type type,
+		unsigned int timeout, uint32_t pipe_id,
+		uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_destroy(mm->dev->kgd, mqd, timeout);
+}
+
+static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
+		uint64_t queue_address, uint32_t pipe_id,
+		uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->kgd, mqd);
+}
+
+#if defined(CONFIG_DEBUG_FS)
+
+static int debugfs_show_mqd(struct seq_file *m, void *data)
+{
+	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
+		     data, sizeof(struct v9_mqd), false);
+	return 0;
+}
+
+static int debugfs_show_mqd_sdma(struct seq_file *m, void *data)
+{
+	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
+		     data, sizeof(struct v9_sdma_mqd), false);
+	return 0;
+}
+
+#endif
+
+struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
+		struct kfd_dev *dev)
+{
+	struct mqd_manager *mqd;
+
+	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
+		return NULL;
+
+	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	if (!mqd)
+		return NULL;
+
+	mqd->dev = dev;
+
+	switch (type) {
+	case KFD_MQD_TYPE_CP:
+	case KFD_MQD_TYPE_COMPUTE:
+		mqd->init_mqd = init_mqd;
+		mqd->uninit_mqd = uninit_mqd;
+		mqd->load_mqd = load_mqd;
+		mqd->update_mqd = update_mqd;
+		mqd->destroy_mqd = destroy_mqd;
+		mqd->is_occupied = is_occupied;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
+		break;
+	case KFD_MQD_TYPE_HIQ:
+		mqd->init_mqd = init_mqd_hiq;
+		mqd->uninit_mqd = uninit_mqd;
+		mqd->load_mqd = load_mqd;
+		mqd->update_mqd = update_mqd_hiq;
+		mqd->destroy_mqd = destroy_mqd;
+		mqd->is_occupied = is_occupied;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd;
+#endif
+		break;
+	case KFD_MQD_TYPE_SDMA:
+		mqd->init_mqd = init_mqd_sdma;
+		mqd->uninit_mqd = uninit_mqd_sdma;
+		mqd->load_mqd = load_mqd_sdma;
+		mqd->update_mqd = update_mqd_sdma;
+		mqd->destroy_mqd = destroy_mqd_sdma;
+		mqd->is_occupied = is_occupied_sdma;
+#if defined(CONFIG_DEBUG_FS)
+		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
+#endif
+		break;
+	default:
+		kfree(mqd);
+		return NULL;
+	}
+
+	return mqd;
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index 89e4242e43e7..481307b8b4db 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -394,7 +394,7 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
+	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
 	if (!mqd)
 		return NULL;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 89ba4c670ec5..c317feb43f69 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -26,8 +26,6 @@
 #include "kfd_device_queue_manager.h"
 #include "kfd_kernel_queue.h"
 #include "kfd_priv.h"
-#include "kfd_pm4_headers_vi.h"
-#include "kfd_pm4_opcodes.h"
 
 static inline void inc_wptr(unsigned int *wptr, unsigned int increment_bytes,
 				unsigned int buffer_size_bytes)
@@ -39,18 +37,6 @@ static inline void inc_wptr(unsigned int *wptr, unsigned int increment_bytes,
 	*wptr = temp;
 }
 
-static unsigned int build_pm4_header(unsigned int opcode, size_t packet_size)
-{
-	union PM4_MES_TYPE_3_HEADER header;
-
-	header.u32All = 0;
-	header.opcode = opcode;
-	header.count = packet_size / 4 - 2;
-	header.type = PM4_TYPE_3;
-
-	return header.u32All;
-}
-
 static void pm_calc_rlib_size(struct packet_manager *pm,
 				unsigned int *rlib_size,
 				bool *over_subscription)
@@ -80,9 +66,9 @@ static void pm_calc_rlib_size(struct packet_manager *pm,
 		pr_debug("Over subscribed runlist\n");
 	}
 
-	map_queue_size = sizeof(struct pm4_mes_map_queues);
+	map_queue_size = pm->pmf->map_queues_size;
 	/* calculate run list ib allocation size */
-	*rlib_size = process_count * sizeof(struct pm4_mes_map_process) +
+	*rlib_size = process_count * pm->pmf->map_process_size +
 		     queue_count * map_queue_size;
 
 	/*
@@ -90,7 +76,7 @@ static void pm_calc_rlib_size(struct packet_manager *pm,
 	 * when over subscription
 	 */
 	if (*over_subscription)
-		*rlib_size += sizeof(struct pm4_mes_runlist);
+		*rlib_size += pm->pmf->runlist_size;
 
 	pr_debug("runlist ib size %d\n", *rlib_size);
 }
@@ -108,12 +94,14 @@ static int pm_allocate_runlist_ib(struct packet_manager *pm,
 
 	pm_calc_rlib_size(pm, rl_buffer_size, is_over_subscription);
 
+	mutex_lock(&pm->lock);
+
 	retval = kfd_gtt_sa_allocate(pm->dqm->dev, *rl_buffer_size,
 					&pm->ib_buffer_obj);
 
 	if (retval) {
 		pr_err("Failed to allocate runlist IB\n");
-		return retval;
+		goto out;
 	}
 
 	*(void **)rl_buffer = pm->ib_buffer_obj->cpu_ptr;
@@ -121,138 +109,10 @@ static int pm_allocate_runlist_ib(struct packet_manager *pm,
 
 	memset(*rl_buffer, 0, *rl_buffer_size);
 	pm->allocated = true;
-	return retval;
-}
-
-static int pm_create_runlist(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t ib, size_t ib_size_in_dwords, bool chain)
-{
-	struct pm4_mes_runlist *packet;
-	int concurrent_proc_cnt = 0;
-	struct kfd_dev *kfd = pm->dqm->dev;
-
-	if (WARN_ON(!ib))
-		return -EFAULT;
-
-	/* Determine the number of processes to map together to HW:
-	 * it can not exceed the number of VMIDs available to the
-	 * scheduler, and it is determined by the smaller of the number
-	 * of processes in the runlist and kfd module parameter
-	 * hws_max_conc_proc.
-	 * Note: the arbitration between the number of VMIDs and
-	 * hws_max_conc_proc has been done in
-	 * kgd2kfd_device_init().
-	 */
-	concurrent_proc_cnt = min(pm->dqm->processes_count,
-			kfd->max_proc_per_quantum);
-
-	packet = (struct pm4_mes_runlist *)buffer;
-
-	memset(buffer, 0, sizeof(struct pm4_mes_runlist));
-	packet->header.u32All = build_pm4_header(IT_RUN_LIST,
-						sizeof(struct pm4_mes_runlist));
-
-	packet->bitfields4.ib_size = ib_size_in_dwords;
-	packet->bitfields4.chain = chain ? 1 : 0;
-	packet->bitfields4.offload_polling = 0;
-	packet->bitfields4.valid = 1;
-	packet->bitfields4.process_cnt = concurrent_proc_cnt;
-	packet->ordinal2 = lower_32_bits(ib);
-	packet->bitfields3.ib_base_hi = upper_32_bits(ib);
-
-	return 0;
-}
-
-static int pm_create_map_process(struct packet_manager *pm, uint32_t *buffer,
-				struct qcm_process_device *qpd)
-{
-	struct pm4_mes_map_process *packet;
-
-	packet = (struct pm4_mes_map_process *)buffer;
 
-	memset(buffer, 0, sizeof(struct pm4_mes_map_process));
-
-	packet->header.u32All = build_pm4_header(IT_MAP_PROCESS,
-					sizeof(struct pm4_mes_map_process));
-	packet->bitfields2.diq_enable = (qpd->is_debug) ? 1 : 0;
-	packet->bitfields2.process_quantum = 1;
-	packet->bitfields2.pasid = qpd->pqm->process->pasid;
-	packet->bitfields3.page_table_base = qpd->page_table_base;
-	packet->bitfields10.gds_size = qpd->gds_size;
-	packet->bitfields10.num_gws = qpd->num_gws;
-	packet->bitfields10.num_oac = qpd->num_oac;
-	packet->bitfields10.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
-
-	packet->sh_mem_config = qpd->sh_mem_config;
-	packet->sh_mem_bases = qpd->sh_mem_bases;
-	packet->sh_mem_ape1_base = qpd->sh_mem_ape1_base;
-	packet->sh_mem_ape1_limit = qpd->sh_mem_ape1_limit;
-
-	packet->sh_hidden_private_base_vmid = qpd->sh_hidden_private_base;
-
-	packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
-	packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
-
-	return 0;
-}
-
-static int pm_create_map_queue(struct packet_manager *pm, uint32_t *buffer,
-		struct queue *q, bool is_static)
-{
-	struct pm4_mes_map_queues *packet;
-	bool use_static = is_static;
-
-	packet = (struct pm4_mes_map_queues *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_map_queues));
-
-	packet->header.u32All = build_pm4_header(IT_MAP_QUEUES,
-						sizeof(struct pm4_mes_map_queues));
-	packet->bitfields2.alloc_format =
-		alloc_format__mes_map_queues__one_per_pipe_vi;
-	packet->bitfields2.num_queues = 1;
-	packet->bitfields2.queue_sel =
-		queue_sel__mes_map_queues__map_to_hws_determined_queue_slots_vi;
-
-	packet->bitfields2.engine_sel =
-		engine_sel__mes_map_queues__compute_vi;
-	packet->bitfields2.queue_type =
-		queue_type__mes_map_queues__normal_compute_vi;
-
-	switch (q->properties.type) {
-	case KFD_QUEUE_TYPE_COMPUTE:
-		if (use_static)
-			packet->bitfields2.queue_type =
-		queue_type__mes_map_queues__normal_latency_static_queue_vi;
-		break;
-	case KFD_QUEUE_TYPE_DIQ:
-		packet->bitfields2.queue_type =
-			queue_type__mes_map_queues__debug_interface_queue_vi;
-		break;
-	case KFD_QUEUE_TYPE_SDMA:
-		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
-				engine_sel__mes_map_queues__sdma0_vi;
-		use_static = false; /* no static queues under SDMA */
-		break;
-	default:
-		WARN(1, "queue type %d", q->properties.type);
-		return -EINVAL;
-	}
-	packet->bitfields3.doorbell_offset =
-			q->properties.doorbell_off;
-
-	packet->mqd_addr_lo =
-			lower_32_bits(q->gart_mqd_addr);
-
-	packet->mqd_addr_hi =
-			upper_32_bits(q->gart_mqd_addr);
-
-	packet->wptr_addr_lo =
-			lower_32_bits((uint64_t)q->properties.write_ptr);
-
-	packet->wptr_addr_hi =
-			upper_32_bits((uint64_t)q->properties.write_ptr);
-
-	return 0;
+out:
+	mutex_unlock(&pm->lock);
+	return retval;
 }
 
 static int pm_create_runlist_ib(struct packet_manager *pm,
@@ -292,12 +152,12 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 			return -ENOMEM;
 		}
 
-		retval = pm_create_map_process(pm, &rl_buffer[rl_wptr], qpd);
+		retval = pm->pmf->map_process(pm, &rl_buffer[rl_wptr], qpd);
 		if (retval)
 			return retval;
 
 		proccesses_mapped++;
-		inc_wptr(&rl_wptr, sizeof(struct pm4_mes_map_process),
+		inc_wptr(&rl_wptr, pm->pmf->map_process_size,
 				alloc_size_bytes);
 
 		list_for_each_entry(kq, &qpd->priv_queue_list, list) {
@@ -307,7 +167,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 			pr_debug("static_queue, mapping kernel q %d, is debug status %d\n",
 				kq->queue->queue, qpd->is_debug);
 
-			retval = pm_create_map_queue(pm,
+			retval = pm->pmf->map_queues(pm,
 						&rl_buffer[rl_wptr],
 						kq->queue,
 						qpd->is_debug);
@@ -315,7 +175,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 				return retval;
 
 			inc_wptr(&rl_wptr,
-				sizeof(struct pm4_mes_map_queues),
+				pm->pmf->map_queues_size,
 				alloc_size_bytes);
 		}
 
@@ -326,7 +186,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 			pr_debug("static_queue, mapping user queue %d, is debug status %d\n",
 				q->queue, qpd->is_debug);
 
-			retval = pm_create_map_queue(pm,
+			retval = pm->pmf->map_queues(pm,
 						&rl_buffer[rl_wptr],
 						q,
 						qpd->is_debug);
@@ -335,7 +195,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 				return retval;
 
 			inc_wptr(&rl_wptr,
-				sizeof(struct pm4_mes_map_queues),
+				pm->pmf->map_queues_size,
 				alloc_size_bytes);
 		}
 	}
@@ -343,7 +203,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 	pr_debug("Finished map process and queues to runlist\n");
 
 	if (is_over_subscription)
-		retval = pm_create_runlist(pm, &rl_buffer[rl_wptr],
+		retval = pm->pmf->runlist(pm, &rl_buffer[rl_wptr],
 					*rl_gpu_addr,
 					alloc_size_bytes / sizeof(uint32_t),
 					true);
@@ -355,45 +215,29 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
 	return retval;
 }
 
-/* pm_create_release_mem - Create a RELEASE_MEM packet and return the size
- *     of this packet
- *     @gpu_addr - GPU address of the packet. It's a virtual address.
- *     @buffer - buffer to fill up with the packet. It's a CPU kernel pointer
- *     Return - length of the packet
- */
-uint32_t pm_create_release_mem(uint64_t gpu_addr, uint32_t *buffer)
-{
-	struct pm4_mec_release_mem *packet;
-
-	WARN_ON(!buffer);
-
-	packet = (struct pm4_mec_release_mem *)buffer;
-	memset(buffer, 0, sizeof(*packet));
-
-	packet->header.u32All = build_pm4_header(IT_RELEASE_MEM,
-						 sizeof(*packet));
-
-	packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
-	packet->bitfields2.event_index = event_index___release_mem__end_of_pipe;
-	packet->bitfields2.tcl1_action_ena = 1;
-	packet->bitfields2.tc_action_ena = 1;
-	packet->bitfields2.cache_policy = cache_policy___release_mem__lru;
-	packet->bitfields2.atc = 0;
-
-	packet->bitfields3.data_sel = data_sel___release_mem__send_32_bit_low;
-	packet->bitfields3.int_sel =
-		int_sel___release_mem__send_interrupt_after_write_confirm;
-
-	packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
-	packet->address_hi = upper_32_bits(gpu_addr);
-
-	packet->data_lo = 0;
-
-	return sizeof(*packet) / sizeof(unsigned int);
-}
-
 int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
 {
+	switch (dqm->dev->device_info->asic_family) {
+	case CHIP_KAVERI:
+	case CHIP_HAWAII:
+		/* PM4 packet structures on CIK are the same as on VI */
+	case CHIP_CARRIZO:
+	case CHIP_TONGA:
+	case CHIP_FIJI:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+		pm->pmf = &kfd_vi_pm_funcs;
+		break;
+	case CHIP_VEGA10:
+	case CHIP_RAVEN:
+		pm->pmf = &kfd_v9_pm_funcs;
+		break;
+	default:
+		WARN(1, "Unexpected ASIC family %u",
+		     dqm->dev->device_info->asic_family);
+		return -EINVAL;
+	}
+
 	pm->dqm = dqm;
 	mutex_init(&pm->lock);
 	pm->priv_queue = kernel_queue_init(dqm->dev, KFD_QUEUE_TYPE_HIQ);
@@ -415,38 +259,25 @@ void pm_uninit(struct packet_manager *pm)
 int pm_send_set_resources(struct packet_manager *pm,
 				struct scheduling_resources *res)
 {
-	struct pm4_mes_set_resources *packet;
+	uint32_t *buffer, size;
 	int retval = 0;
 
+	size = pm->pmf->set_resources_size;
 	mutex_lock(&pm->lock);
 	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
-					sizeof(*packet) / sizeof(uint32_t),
-					(unsigned int **)&packet);
-	if (!packet) {
+					size / sizeof(uint32_t),
+					(unsigned int **)&buffer);
+	if (!buffer) {
 		pr_err("Failed to allocate buffer on kernel queue\n");
 		retval = -ENOMEM;
 		goto out;
 	}
 
-	memset(packet, 0, sizeof(struct pm4_mes_set_resources));
-	packet->header.u32All = build_pm4_header(IT_SET_RESOURCES,
-					sizeof(struct pm4_mes_set_resources));
-
-	packet->bitfields2.queue_type =
-			queue_type__mes_set_resources__hsa_interface_queue_hiq;
-	packet->bitfields2.vmid_mask = res->vmid_mask;
-	packet->bitfields2.unmap_latency = KFD_UNMAP_LATENCY_MS / 100;
-	packet->bitfields7.oac_mask = res->oac_mask;
-	packet->bitfields8.gds_heap_base = res->gds_heap_base;
-	packet->bitfields8.gds_heap_size = res->gds_heap_size;
-
-	packet->gws_mask_lo = lower_32_bits(res->gws_mask);
-	packet->gws_mask_hi = upper_32_bits(res->gws_mask);
-
-	packet->queue_mask_lo = lower_32_bits(res->queue_mask);
-	packet->queue_mask_hi = upper_32_bits(res->queue_mask);
-
-	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+	retval = pm->pmf->set_resources(pm, buffer, res);
+	if (!retval)
+		pm->priv_queue->ops.submit_packet(pm->priv_queue);
+	else
+		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
 
 out:
 	mutex_unlock(&pm->lock);
@@ -468,7 +299,7 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
 
 	pr_debug("runlist IB address: 0x%llX\n", rl_gpu_ib_addr);
 
-	packet_size_dwords = sizeof(struct pm4_mes_runlist) / sizeof(uint32_t);
+	packet_size_dwords = pm->pmf->runlist_size / sizeof(uint32_t);
 	mutex_lock(&pm->lock);
 
 	retval = pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
@@ -476,7 +307,7 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
 	if (retval)
 		goto fail_acquire_packet_buffer;
 
-	retval = pm_create_runlist(pm, rl_buffer, rl_gpu_ib_addr,
+	retval = pm->pmf->runlist(pm, rl_buffer, rl_gpu_ib_addr,
 					rl_ib_size / sizeof(uint32_t), false);
 	if (retval)
 		goto fail_create_runlist;
@@ -499,37 +330,29 @@ fail_create_runlist_ib:
 int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
 			uint32_t fence_value)
 {
-	int retval;
-	struct pm4_mes_query_status *packet;
+	uint32_t *buffer, size;
+	int retval = 0;
 
 	if (WARN_ON(!fence_address))
 		return -EFAULT;
 
+	size = pm->pmf->query_status_size;
 	mutex_lock(&pm->lock);
-	retval = pm->priv_queue->ops.acquire_packet_buffer(
-			pm->priv_queue,
-			sizeof(struct pm4_mes_query_status) / sizeof(uint32_t),
-			(unsigned int **)&packet);
-	if (retval)
-		goto fail_acquire_packet_buffer;
-
-	packet->header.u32All = build_pm4_header(IT_QUERY_STATUS,
-					sizeof(struct pm4_mes_query_status));
-
-	packet->bitfields2.context_id = 0;
-	packet->bitfields2.interrupt_sel =
-			interrupt_sel__mes_query_status__completion_status;
-	packet->bitfields2.command =
-			command__mes_query_status__fence_only_after_write_ack;
-
-	packet->addr_hi = upper_32_bits((uint64_t)fence_address);
-	packet->addr_lo = lower_32_bits((uint64_t)fence_address);
-	packet->data_hi = upper_32_bits((uint64_t)fence_value);
-	packet->data_lo = lower_32_bits((uint64_t)fence_value);
+	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		retval = -ENOMEM;
+		goto out;
+	}
 
-	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+	retval = pm->pmf->query_status(pm, buffer, fence_address, fence_value);
+	if (!retval)
+		pm->priv_queue->ops.submit_packet(pm->priv_queue);
+	else
+		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
 
-fail_acquire_packet_buffer:
+out:
 	mutex_unlock(&pm->lock);
 	return retval;
 }
@@ -539,82 +362,27 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 			uint32_t filter_param, bool reset,
 			unsigned int sdma_engine)
 {
-	int retval;
-	uint32_t *buffer;
-	struct pm4_mes_unmap_queues *packet;
+	uint32_t *buffer, size;
+	int retval = 0;
 
+	size = pm->pmf->unmap_queues_size;
 	mutex_lock(&pm->lock);
-	retval = pm->priv_queue->ops.acquire_packet_buffer(
-			pm->priv_queue,
-			sizeof(struct pm4_mes_unmap_queues) / sizeof(uint32_t),
-			&buffer);
-	if (retval)
-		goto err_acquire_packet_buffer;
-
-	packet = (struct pm4_mes_unmap_queues *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues));
-	pr_debug("static_queue: unmapping queues: filter is %d , reset is %d , type is %d\n",
-		filter, reset, type);
-	packet->header.u32All = build_pm4_header(IT_UNMAP_QUEUES,
-					sizeof(struct pm4_mes_unmap_queues));
-	switch (type) {
-	case KFD_QUEUE_TYPE_COMPUTE:
-	case KFD_QUEUE_TYPE_DIQ:
-		packet->bitfields2.engine_sel =
-			engine_sel__mes_unmap_queues__compute;
-		break;
-	case KFD_QUEUE_TYPE_SDMA:
-		packet->bitfields2.engine_sel =
-			engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
-		break;
-	default:
-		WARN(1, "queue type %d", type);
-		retval = -EINVAL;
-		goto err_invalid;
+	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		retval = -ENOMEM;
+		goto out;
 	}
 
-	if (reset)
-		packet->bitfields2.action =
-				action__mes_unmap_queues__reset_queues;
+	retval = pm->pmf->unmap_queues(pm, buffer, type, filter, filter_param,
+				       reset, sdma_engine);
+	if (!retval)
+		pm->priv_queue->ops.submit_packet(pm->priv_queue);
 	else
-		packet->bitfields2.action =
-				action__mes_unmap_queues__preempt_queues;
-
-	switch (filter) {
-	case KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE:
-		packet->bitfields2.queue_sel =
-				queue_sel__mes_unmap_queues__perform_request_on_specified_queues;
-		packet->bitfields2.num_queues = 1;
-		packet->bitfields3b.doorbell_offset0 = filter_param;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_BY_PASID:
-		packet->bitfields2.queue_sel =
-				queue_sel__mes_unmap_queues__perform_request_on_pasid_queues;
-		packet->bitfields3a.pasid = filter_param;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES:
-		packet->bitfields2.queue_sel =
-				queue_sel__mes_unmap_queues__unmap_all_queues;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES:
-		/* in this case, we do not preempt static queues */
-		packet->bitfields2.queue_sel =
-				queue_sel__mes_unmap_queues__unmap_all_non_static_queues;
-		break;
-	default:
-		WARN(1, "filter %d", filter);
-		retval = -EINVAL;
-		goto err_invalid;
-	}
+		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
 
-	pm->priv_queue->ops.submit_packet(pm->priv_queue);
-
-	mutex_unlock(&pm->lock);
-	return 0;
-
-err_invalid:
-	pm->priv_queue->ops.rollback_packet(pm->priv_queue);
-err_acquire_packet_buffer:
+out:
 	mutex_unlock(&pm->lock);
 	return retval;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h b/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h
new file mode 100644
index 000000000000..f2bcf5c092ea
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h
@@ -0,0 +1,583 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef F32_MES_PM4_PACKETS_H
+#define F32_MES_PM4_PACKETS_H
+
+#ifndef PM4_MES_HEADER_DEFINED
+#define PM4_MES_HEADER_DEFINED
+union PM4_MES_TYPE_3_HEADER {
+	struct {
+		uint32_t reserved1 : 8; /* < reserved */
+		uint32_t opcode    : 8; /* < IT opcode */
+		uint32_t count     : 14;/* < number of DWORDs - 1 in the
+					 *   information body.
+					 */
+		uint32_t type      : 2; /* < packet identifier.
+					 *   It should be 3 for type 3 packets
+					 */
+	};
+	uint32_t u32All;
+};
+#endif /* PM4_MES_HEADER_DEFINED */
+
+/*--------------------MES_SET_RESOURCES--------------------*/
+
+#ifndef PM4_MES_SET_RESOURCES_DEFINED
+#define PM4_MES_SET_RESOURCES_DEFINED
+enum mes_set_resources_queue_type_enum {
+	queue_type__mes_set_resources__kernel_interface_queue_kiq = 0,
+	queue_type__mes_set_resources__hsa_interface_queue_hiq = 1,
+	queue_type__mes_set_resources__hsa_debug_interface_queue = 4
+};
+
+
+struct pm4_mes_set_resources {
+	union {
+		union PM4_MES_TYPE_3_HEADER	header;		/* header */
+		uint32_t			ordinal1;
+	};
+
+	union {
+		struct {
+			uint32_t vmid_mask:16;
+			uint32_t unmap_latency:8;
+			uint32_t reserved1:5;
+			enum mes_set_resources_queue_type_enum queue_type:3;
+		} bitfields2;
+		uint32_t ordinal2;
+	};
+
+	uint32_t queue_mask_lo;
+	uint32_t queue_mask_hi;
+	uint32_t gws_mask_lo;
+	uint32_t gws_mask_hi;
+
+	union {
+		struct {
+			uint32_t oac_mask:16;
+			uint32_t reserved2:16;
+		} bitfields7;
+		uint32_t ordinal7;
+	};
+
+	union {
+		struct {
+		uint32_t gds_heap_base:6;
+		uint32_t reserved3:5;
+		uint32_t gds_heap_size:6;
+		uint32_t reserved4:15;
+		} bitfields8;
+		uint32_t ordinal8;
+	};
+
+};
+#endif
+
+/*--------------------MES_RUN_LIST--------------------*/
+
+#ifndef PM4_MES_RUN_LIST_DEFINED
+#define PM4_MES_RUN_LIST_DEFINED
+
+struct pm4_mes_runlist {
+	union {
+		union PM4_MES_TYPE_3_HEADER header; /* header */
+		uint32_t ordinal1;
+	};
+
+	union {
+		struct {
+			uint32_t reserved1:2;
+			uint32_t ib_base_lo:30;
+		} bitfields2;
+		uint32_t ordinal2;
+	};
+
+	uint32_t ib_base_hi;
+
+	union {
+		struct {
+			uint32_t ib_size:20;
+			uint32_t chain:1;
+			uint32_t offload_polling:1;
+			uint32_t reserved2:1;
+			uint32_t valid:1;
+			uint32_t process_cnt:4;
+			uint32_t reserved3:4;
+		} bitfields4;
+		uint32_t ordinal4;
+	};
+
+};
+#endif
+
+/*--------------------MES_MAP_PROCESS--------------------*/
+
+#ifndef PM4_MES_MAP_PROCESS_DEFINED
+#define PM4_MES_MAP_PROCESS_DEFINED
+
+struct pm4_mes_map_process {
+	union {
+		union PM4_MES_TYPE_3_HEADER header;	/* header */
+		uint32_t ordinal1;
+	};
+
+	union {
+		struct {
+			uint32_t pasid:16;
+			uint32_t reserved1:8;
+			uint32_t diq_enable:1;
+			uint32_t process_quantum:7;
+		} bitfields2;
+		uint32_t ordinal2;
+	};
+
+	uint32_t vm_context_page_table_base_addr_lo32;
+
+	uint32_t vm_context_page_table_base_addr_hi32;
+
+	uint32_t sh_mem_bases;
+
+	uint32_t sh_mem_config;
+
+	uint32_t sq_shader_tba_lo;
+
+	uint32_t sq_shader_tba_hi;
+
+	uint32_t sq_shader_tma_lo;
+
+	uint32_t sq_shader_tma_hi;
+
+	uint32_t reserved6;
+
+	uint32_t gds_addr_lo;
+
+	uint32_t gds_addr_hi;
+
+	union {
+		struct {
+			uint32_t num_gws:6;
+			uint32_t reserved7:1;
+			uint32_t sdma_enable:1;
+			uint32_t num_oac:4;
+			uint32_t reserved8:4;
+			uint32_t gds_size:6;
+			uint32_t num_queues:10;
+		} bitfields14;
+		uint32_t ordinal14;
+	};
+
+	uint32_t completion_signal_lo;
+
+	uint32_t completion_signal_hi;
+
+};
+
+#endif
+
+/*--------------------MES_MAP_PROCESS_VM--------------------*/
+
+#ifndef PM4_MES_MAP_PROCESS_VM_DEFINED
+#define PM4_MES_MAP_PROCESS_VM_DEFINED
+
+struct PM4_MES_MAP_PROCESS_VM {
+	union {
+		union PM4_MES_TYPE_3_HEADER header;	/* header */
+		uint32_t ordinal1;
+	};
+
+	uint32_t reserved1;
+
+	uint32_t vm_context_cntl;
+
+	uint32_t reserved2;
+
+	uint32_t vm_context_page_table_end_addr_lo32;
+
+	uint32_t vm_context_page_table_end_addr_hi32;
+
+	uint32_t vm_context_page_table_start_addr_lo32;
+
+	uint32_t vm_context_page_table_start_addr_hi32;
+
+	uint32_t reserved3;
+
+	uint32_t reserved4;
+
+	uint32_t reserved5;
+
+	uint32_t reserved6;
+
+	uint32_t reserved7;
+
+	uint32_t reserved8;
+
+	uint32_t completion_signal_lo32;
+
+	uint32_t completion_signal_hi32;
+
+};
+#endif
+
+/*--------------------MES_MAP_QUEUES--------------------*/
+
+#ifndef PM4_MES_MAP_QUEUES_VI_DEFINED
+#define PM4_MES_MAP_QUEUES_VI_DEFINED
+enum mes_map_queues_queue_sel_enum {
+	queue_sel__mes_map_queues__map_to_specified_queue_slots_vi = 0,
+queue_sel__mes_map_queues__map_to_hws_determined_queue_slots_vi = 1
+};
+
+enum mes_map_queues_queue_type_enum {
+	queue_type__mes_map_queues__normal_compute_vi = 0,
+	queue_type__mes_map_queues__debug_interface_queue_vi = 1,
+	queue_type__mes_map_queues__normal_latency_static_queue_vi = 2,
+queue_type__mes_map_queues__low_latency_static_queue_vi = 3
+};
+
+enum mes_map_queues_alloc_format_enum {
+	alloc_format__mes_map_queues__one_per_pipe_vi = 0,
+alloc_format__mes_map_queues__all_on_one_pipe_vi = 1
+};
+
+enum mes_map_queues_engine_sel_enum {
+	engine_sel__mes_map_queues__compute_vi = 0,
+	engine_sel__mes_map_queues__sdma0_vi = 2,
+	engine_sel__mes_map_queues__sdma1_vi = 3
+};
+
+
+struct pm4_mes_map_queues {
+	union {
+		union PM4_MES_TYPE_3_HEADER   header;            /* header */
+		uint32_t            ordinal1;
+	};
+
+	union {
+		struct {
+			uint32_t reserved1:4;
+			enum mes_map_queues_queue_sel_enum queue_sel:2;
+			uint32_t reserved2:15;
+			enum mes_map_queues_queue_type_enum queue_type:3;
+			enum mes_map_queues_alloc_format_enum alloc_format:2;
+			enum mes_map_queues_engine_sel_enum engine_sel:3;
+			uint32_t num_queues:3;
+		} bitfields2;
+		uint32_t ordinal2;
+	};
+
+	union {
+		struct {
+			uint32_t reserved3:1;
+			uint32_t check_disable:1;
+			uint32_t doorbell_offset:26;
+			uint32_t reserved4:4;
+		} bitfields3;
+		uint32_t ordinal3;
+	};
+
+	uint32_t mqd_addr_lo;
+	uint32_t mqd_addr_hi;
+	uint32_t wptr_addr_lo;
+	uint32_t wptr_addr_hi;
+};
+#endif
+
+/*--------------------MES_QUERY_STATUS--------------------*/
+
+#ifndef PM4_MES_QUERY_STATUS_DEFINED
+#define PM4_MES_QUERY_STATUS_DEFINED
+enum mes_query_status_interrupt_sel_enum {
+	interrupt_sel__mes_query_status__completion_status = 0,
+	interrupt_sel__mes_query_status__process_status = 1,
+	interrupt_sel__mes_query_status__queue_status = 2
+};
+
+enum mes_query_status_command_enum {
+	command__mes_query_status__interrupt_only = 0,
+	command__mes_query_status__fence_only_immediate = 1,
+	command__mes_query_status__fence_only_after_write_ack = 2,
+	command__mes_query_status__fence_wait_for_write_ack_send_interrupt = 3
+};
+
+enum mes_query_status_engine_sel_enum {
+	engine_sel__mes_query_status__compute = 0,
+	engine_sel__mes_query_status__sdma0_queue = 2,
+	engine_sel__mes_query_status__sdma1_queue = 3
+};
+
+struct pm4_mes_query_status {
+	union {
+		union PM4_MES_TYPE_3_HEADER   header;            /* header */
+		uint32_t            ordinal1;
+	};
+
+	union {
+		struct {
+			uint32_t context_id:28;
+			enum mes_query_status_interrupt_sel_enum	interrupt_sel:2;
+			enum mes_query_status_command_enum command:2;
+		} bitfields2;
+		uint32_t ordinal2;
+	};
+
+	union {
+		struct {
+			uint32_t pasid:16;
+			uint32_t reserved1:16;
+		} bitfields3a;
+		struct {
+			uint32_t reserved2:2;
+			uint32_t doorbell_offset:26;
+			enum mes_query_status_engine_sel_enum engine_sel:3;
+			uint32_t reserved3:1;
+		} bitfields3b;
+		uint32_t ordinal3;
+	};
+
+	uint32_t addr_lo;
+	uint32_t addr_hi;
+	uint32_t data_lo;
+	uint32_t data_hi;
+};
+#endif
+
+/*--------------------MES_UNMAP_QUEUES--------------------*/
+
+#ifndef PM4_MES_UNMAP_QUEUES_DEFINED
+#define PM4_MES_UNMAP_QUEUES_DEFINED
+enum mes_unmap_queues_action_enum {
+	action__mes_unmap_queues__preempt_queues = 0,
+	action__mes_unmap_queues__reset_queues = 1,
+	action__mes_unmap_queues__disable_process_queues = 2,
+	action__mes_unmap_queues__reserved = 3
+};
+
+enum mes_unmap_queues_queue_sel_enum {
+	queue_sel__mes_unmap_queues__perform_request_on_specified_queues = 0,
+	queue_sel__mes_unmap_queues__perform_request_on_pasid_queues = 1,
+	queue_sel__mes_unmap_queues__unmap_all_queues = 2,
+	queue_sel__mes_unmap_queues__unmap_all_non_static_queues = 3
+};
+
+enum mes_unmap_queues_engine_sel_enum {
+	engine_sel__mes_unmap_queues__compute = 0,
+	engine_sel__mes_unmap_queues__sdma0 = 2,
+	engine_sel__mes_unmap_queues__sdmal = 3
+};
+
+struct pm4_mes_unmap_queues {
+	union {
+		union PM4_MES_TYPE_3_HEADER   header;            /* header */
+		uint32_t            ordinal1;
+	};
+
+	union {
+		struct {
+			enum mes_unmap_queues_action_enum action:2;
+			uint32_t reserved1:2;
+			enum mes_unmap_queues_queue_sel_enum queue_sel:2;
+			uint32_t reserved2:20;
+			enum mes_unmap_queues_engine_sel_enum engine_sel:3;
+			uint32_t num_queues:3;
+		} bitfields2;
+		uint32_t ordinal2;
+	};
+
+	union {
+		struct {
+			uint32_t pasid:16;
+			uint32_t reserved3:16;
+		} bitfields3a;
+		struct {
+			uint32_t reserved4:2;
+			uint32_t doorbell_offset0:26;
+			int32_t reserved5:4;
+		} bitfields3b;
+		uint32_t ordinal3;
+	};
+
+	union {
+	struct {
+			uint32_t reserved6:2;
+			uint32_t doorbell_offset1:26;
+			uint32_t reserved7:4;
+		} bitfields4;
+		uint32_t ordinal4;
+	};
+
+	union {
+		struct {
+			uint32_t reserved8:2;
+			uint32_t doorbell_offset2:26;
+			uint32_t reserved9:4;
+		} bitfields5;
+		uint32_t ordinal5;
+	};
+
+	union {
+		struct {
+			uint32_t reserved10:2;
+			uint32_t doorbell_offset3:26;
+			uint32_t reserved11:4;
+		} bitfields6;
+		uint32_t ordinal6;
+	};
+};
+#endif
+
+#ifndef PM4_MEC_RELEASE_MEM_DEFINED
+#define PM4_MEC_RELEASE_MEM_DEFINED
+
+enum mec_release_mem_event_index_enum {
+	event_index__mec_release_mem__end_of_pipe = 5,
+	event_index__mec_release_mem__shader_done = 6
+};
+
+enum mec_release_mem_cache_policy_enum {
+	cache_policy__mec_release_mem__lru = 0,
+	cache_policy__mec_release_mem__stream = 1
+};
+
+enum mec_release_mem_pq_exe_status_enum {
+	pq_exe_status__mec_release_mem__default = 0,
+	pq_exe_status__mec_release_mem__phase_update = 1
+};
+
+enum mec_release_mem_dst_sel_enum {
+	dst_sel__mec_release_mem__memory_controller = 0,
+	dst_sel__mec_release_mem__tc_l2 = 1,
+	dst_sel__mec_release_mem__queue_write_pointer_register = 2,
+	dst_sel__mec_release_mem__queue_write_pointer_poll_mask_bit = 3
+};
+
+enum mec_release_mem_int_sel_enum {
+	int_sel__mec_release_mem__none = 0,
+	int_sel__mec_release_mem__send_interrupt_only = 1,
+	int_sel__mec_release_mem__send_interrupt_after_write_confirm = 2,
+	int_sel__mec_release_mem__send_data_after_write_confirm = 3,
+	int_sel__mec_release_mem__unconditionally_send_int_ctxid = 4,
+	int_sel__mec_release_mem__conditionally_send_int_ctxid_based_on_32_bit_compare = 5,
+	int_sel__mec_release_mem__conditionally_send_int_ctxid_based_on_64_bit_compare = 6
+};
+
+enum mec_release_mem_data_sel_enum {
+	data_sel__mec_release_mem__none = 0,
+	data_sel__mec_release_mem__send_32_bit_low = 1,
+	data_sel__mec_release_mem__send_64_bit_data = 2,
+	data_sel__mec_release_mem__send_gpu_clock_counter = 3,
+	data_sel__mec_release_mem__send_cp_perfcounter_hi_lo = 4,
+	data_sel__mec_release_mem__store_gds_data_to_memory = 5
+};
+
+struct pm4_mec_release_mem {
+	union {
+		union PM4_MES_TYPE_3_HEADER header;     /*header */
+		unsigned int ordinal1;
+	};
+
+	union {
+		struct {
+			unsigned int event_type:6;
+			unsigned int reserved1:2;
+			enum mec_release_mem_event_index_enum event_index:4;
+			unsigned int tcl1_vol_action_ena:1;
+			unsigned int tc_vol_action_ena:1;
+			unsigned int reserved2:1;
+			unsigned int tc_wb_action_ena:1;
+			unsigned int tcl1_action_ena:1;
+			unsigned int tc_action_ena:1;
+			uint32_t reserved3:1;
+			uint32_t tc_nc_action_ena:1;
+			uint32_t tc_wc_action_ena:1;
+			uint32_t tc_md_action_ena:1;
+			uint32_t reserved4:3;
+			enum mec_release_mem_cache_policy_enum cache_policy:2;
+			uint32_t reserved5:2;
+			enum mec_release_mem_pq_exe_status_enum pq_exe_status:1;
+			uint32_t reserved6:2;
+		} bitfields2;
+		unsigned int ordinal2;
+	};
+
+	union {
+		struct {
+			uint32_t reserved7:16;
+			enum mec_release_mem_dst_sel_enum dst_sel:2;
+			uint32_t reserved8:6;
+			enum mec_release_mem_int_sel_enum int_sel:3;
+			uint32_t reserved9:2;
+			enum mec_release_mem_data_sel_enum data_sel:3;
+		} bitfields3;
+		unsigned int ordinal3;
+	};
+
+	union {
+		struct {
+			uint32_t reserved10:2;
+			unsigned int address_lo_32b:30;
+		} bitfields4;
+		struct {
+			uint32_t reserved11:3;
+			uint32_t address_lo_64b:29;
+		} bitfields4b;
+		uint32_t reserved12;
+		unsigned int ordinal4;
+	};
+
+	union {
+		uint32_t address_hi;
+		uint32_t reserved13;
+		uint32_t ordinal5;
+	};
+
+	union {
+		uint32_t data_lo;
+		uint32_t cmp_data_lo;
+		struct {
+			uint32_t dw_offset:16;
+			uint32_t num_dwords:16;
+		} bitfields6c;
+		uint32_t reserved14;
+		uint32_t ordinal6;
+	};
+
+	union {
+		uint32_t data_hi;
+		uint32_t cmp_data_hi;
+		uint32_t reserved15;
+		uint32_t reserved16;
+		uint32_t ordinal7;
+	};
+
+	uint32_t int_ctxid;
+
+};
+
+#endif
+
+enum {
+	CACHE_FLUSH_AND_INV_TS_EVENT = 0x00000014
+};
+#endif
+
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 96a9cc0f02c9..5e3990bb4c4b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -39,11 +39,37 @@
 
 #include "amd_shared.h"
 
+#define KFD_MAX_RING_ENTRY_SIZE	8
+
 #define KFD_SYSFS_FILE_MODE 0444
 
-#define KFD_MMAP_DOORBELL_MASK 0x8000000000000ull
-#define KFD_MMAP_EVENTS_MASK 0x4000000000000ull
-#define KFD_MMAP_RESERVED_MEM_MASK 0x2000000000000ull
+/* GPU ID hash width in bits */
+#define KFD_GPU_ID_HASH_WIDTH 16
+
+/* Use upper bits of mmap offset to store KFD driver specific information.
+ * BITS[63:62] - Encode MMAP type
+ * BITS[61:46] - Encode gpu_id. To identify to which GPU the offset belongs to
+ * BITS[45:0]  - MMAP offset value
+ *
+ * NOTE: struct vm_area_struct.vm_pgoff uses offset in pages. Hence, these
+ *  defines are w.r.t to PAGE_SIZE
+ */
+#define KFD_MMAP_TYPE_SHIFT	(62 - PAGE_SHIFT)
+#define KFD_MMAP_TYPE_MASK	(0x3ULL << KFD_MMAP_TYPE_SHIFT)
+#define KFD_MMAP_TYPE_DOORBELL	(0x3ULL << KFD_MMAP_TYPE_SHIFT)
+#define KFD_MMAP_TYPE_EVENTS	(0x2ULL << KFD_MMAP_TYPE_SHIFT)
+#define KFD_MMAP_TYPE_RESERVED_MEM	(0x1ULL << KFD_MMAP_TYPE_SHIFT)
+
+#define KFD_MMAP_GPU_ID_SHIFT (46 - PAGE_SHIFT)
+#define KFD_MMAP_GPU_ID_MASK (((1ULL << KFD_GPU_ID_HASH_WIDTH) - 1) \
+				<< KFD_MMAP_GPU_ID_SHIFT)
+#define KFD_MMAP_GPU_ID(gpu_id) ((((uint64_t)gpu_id) << KFD_MMAP_GPU_ID_SHIFT)\
+				& KFD_MMAP_GPU_ID_MASK)
+#define KFD_MMAP_GPU_ID_GET(offset)    ((offset & KFD_MMAP_GPU_ID_MASK) \
+				>> KFD_MMAP_GPU_ID_SHIFT)
+
+#define KFD_MMAP_OFFSET_VALUE_MASK	(0x3FFFFFFFFFFFULL >> PAGE_SHIFT)
+#define KFD_MMAP_OFFSET_VALUE_GET(offset) (offset & KFD_MMAP_OFFSET_VALUE_MASK)
 
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
@@ -55,9 +81,6 @@
 #define KFD_CIK_HIQ_PIPE 4
 #define KFD_CIK_HIQ_QUEUE 0
 
-/* GPU ID hash width in bits */
-#define KFD_GPU_ID_HASH_WIDTH 16
-
 /* Macro for allocating structures */
 #define kfd_alloc_struct(ptr_to_struct)	\
 	((typeof(ptr_to_struct)) kzalloc(sizeof(*ptr_to_struct), GFP_KERNEL))
@@ -116,6 +139,11 @@ extern int debug_largebar;
  */
 extern int ignore_crat;
 
+/*
+ * Set sh_mem_config.retry_disable on Vega10
+ */
+extern int vega10_noretry;
+
 /**
  * enum kfd_sched_policy
  *
@@ -148,6 +176,8 @@ enum cache_policy {
 	cache_policy_noncoherent
 };
 
+#define KFD_IS_SOC15(chip) ((chip) >= CHIP_VEGA10)
+
 struct kfd_event_interrupt_class {
 	bool (*interrupt_isr)(struct kfd_dev *dev,
 				const uint32_t *ih_ring_entry);
@@ -160,6 +190,7 @@ struct kfd_device_info {
 	const struct kfd_event_interrupt_class *event_interrupt_class;
 	unsigned int max_pasid_bits;
 	unsigned int max_no_of_hqd;
+	unsigned int doorbell_size;
 	size_t ih_ring_entry_size;
 	uint8_t num_of_watch_points;
 	uint16_t mqd_size_aligned;
@@ -173,6 +204,7 @@ struct kfd_mem_obj {
 	uint32_t range_end;
 	uint64_t gpu_addr;
 	uint32_t *cpu_ptr;
+	void *gtt_mem;
 };
 
 struct kfd_vmid_info {
@@ -364,7 +396,7 @@ struct queue_properties {
 	uint32_t queue_percent;
 	uint32_t *read_ptr;
 	uint32_t *write_ptr;
-	uint32_t __iomem *doorbell_ptr;
+	void __iomem *doorbell_ptr;
 	uint32_t doorbell_off;
 	bool is_interop;
 	bool is_evicted;
@@ -427,6 +459,7 @@ struct queue {
 	uint32_t queue;
 
 	unsigned int sdma_id;
+	unsigned int doorbell_id;
 
 	struct kfd_process	*process;
 	struct kfd_dev		*device;
@@ -501,6 +534,9 @@ struct qcm_process_device {
 	/* IB memory */
 	uint64_t ib_base;
 	void *ib_kaddr;
+
+	/* doorbell resources per process per device */
+	unsigned long *doorbell_bitmap;
 };
 
 /* KFD Memory Eviction */
@@ -512,6 +548,8 @@ struct qcm_process_device {
 /* Approx. time before evicting the process again */
 #define PROCESS_ACTIVE_TIME_MS 10
 
+int kgd2kfd_quiesce_mm(struct mm_struct *mm);
+int kgd2kfd_resume_mm(struct mm_struct *mm);
 int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
 					       struct dma_fence *fence);
 
@@ -681,6 +719,8 @@ struct kfd_process *kfd_get_process(const struct task_struct *);
 struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid);
 struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm);
 void kfd_unref_process(struct kfd_process *p);
+int kfd_process_evict_queues(struct kfd_process *p);
+int kfd_process_restore_queues(struct kfd_process *p);
 void kfd_suspend_all_processes(void);
 int kfd_resume_all_processes(void);
 
@@ -693,7 +733,7 @@ struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev,
 struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 							struct kfd_process *p);
 
-int kfd_reserved_mem_mmap(struct kfd_process *process,
+int kfd_reserved_mem_mmap(struct kfd_dev *dev, struct kfd_process *process,
 			  struct vm_area_struct *vma);
 
 /* KFD process API for creating and translating handles */
@@ -721,17 +761,20 @@ unsigned int kfd_pasid_alloc(void);
 void kfd_pasid_free(unsigned int pasid);
 
 /* Doorbells */
+size_t kfd_doorbell_process_slice(struct kfd_dev *kfd);
 int kfd_doorbell_init(struct kfd_dev *kfd);
 void kfd_doorbell_fini(struct kfd_dev *kfd);
-int kfd_doorbell_mmap(struct kfd_process *process, struct vm_area_struct *vma);
-u32 __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
+int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process,
+		      struct vm_area_struct *vma);
+void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 					unsigned int *doorbell_off);
 void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr);
 u32 read_kernel_doorbell(u32 __iomem *db);
-void write_kernel_doorbell(u32 __iomem *db, u32 value);
-unsigned int kfd_queue_id_to_doorbell(struct kfd_dev *kfd,
+void write_kernel_doorbell(void __iomem *db, u32 value);
+void write_kernel_doorbell64(void __iomem *db, u64 value);
+unsigned int kfd_doorbell_id_to_offset(struct kfd_dev *kfd,
 					struct kfd_process *process,
-					unsigned int queue_id);
+					unsigned int doorbell_id);
 phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev,
 					struct kfd_process *process);
 int kfd_alloc_process_doorbells(struct kfd_process *process);
@@ -788,6 +831,8 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 		struct kfd_dev *dev);
 struct mqd_manager *mqd_manager_init_vi_tonga(enum KFD_MQD_TYPE type,
 		struct kfd_dev *dev);
+struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
+		struct kfd_dev *dev);
 struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev);
 void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
@@ -832,8 +877,42 @@ struct packet_manager {
 	bool allocated;
 	struct kfd_mem_obj *ib_buffer_obj;
 	unsigned int ib_size_bytes;
+
+	const struct packet_manager_funcs *pmf;
+};
+
+struct packet_manager_funcs {
+	/* Support ASIC-specific packet formats for PM4 packets */
+	int (*map_process)(struct packet_manager *pm, uint32_t *buffer,
+			struct qcm_process_device *qpd);
+	int (*runlist)(struct packet_manager *pm, uint32_t *buffer,
+			uint64_t ib, size_t ib_size_in_dwords, bool chain);
+	int (*set_resources)(struct packet_manager *pm, uint32_t *buffer,
+			struct scheduling_resources *res);
+	int (*map_queues)(struct packet_manager *pm, uint32_t *buffer,
+			struct queue *q, bool is_static);
+	int (*unmap_queues)(struct packet_manager *pm, uint32_t *buffer,
+			enum kfd_queue_type type,
+			enum kfd_unmap_queues_filter mode,
+			uint32_t filter_param, bool reset,
+			unsigned int sdma_engine);
+	int (*query_status)(struct packet_manager *pm, uint32_t *buffer,
+			uint64_t fence_address,	uint32_t fence_value);
+	int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer);
+
+	/* Packet sizes */
+	int map_process_size;
+	int runlist_size;
+	int set_resources_size;
+	int map_queues_size;
+	int unmap_queues_size;
+	int query_status_size;
+	int release_mem_size;
 };
 
+extern const struct packet_manager_funcs kfd_vi_pm_funcs;
+extern const struct packet_manager_funcs kfd_v9_pm_funcs;
+
 int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm);
 void pm_uninit(struct packet_manager *pm);
 int pm_send_set_resources(struct packet_manager *pm,
@@ -849,12 +928,17 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 
 void pm_release_ib(struct packet_manager *pm);
 
-uint32_t pm_create_release_mem(uint64_t gpu_addr, uint32_t *buffer);
+/* Following PM funcs can be shared among VI and AI */
+unsigned int pm_build_pm4_header(unsigned int opcode, size_t packet_size);
+int pm_set_resources_vi(struct packet_manager *pm, uint32_t *buffer,
+				struct scheduling_resources *res);
 
 uint64_t kfd_get_number_elems(struct kfd_dev *kfd);
 
 /* Events */
 extern const struct kfd_event_interrupt_class event_interrupt_class_cik;
+extern const struct kfd_event_interrupt_class event_interrupt_class_v9;
+
 extern const struct kfd_device_global_init_class device_global_init_class_cik;
 
 void kfd_event_init_process(struct kfd_process *p);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 1711ad0642f7..1d80b4f7c681 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -332,6 +332,7 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
 			free_pages((unsigned long)pdd->qpd.cwsr_kaddr,
 				get_order(KFD_CWSR_TBA_TMA_SIZE));
 
+		kfree(pdd->qpd.doorbell_bitmap);
 		idr_destroy(&pdd->alloc_idr);
 
 		kfree(pdd);
@@ -451,7 +452,8 @@ static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep)
 		if (!dev->cwsr_enabled || qpd->cwsr_kaddr || qpd->cwsr_base)
 			continue;
 
-		offset = (dev->id | KFD_MMAP_RESERVED_MEM_MASK) << PAGE_SHIFT;
+		offset = (KFD_MMAP_TYPE_RESERVED_MEM | KFD_MMAP_GPU_ID(dev->id))
+			<< PAGE_SHIFT;
 		qpd->tba_addr = (int64_t)vm_mmap(filep, 0,
 			KFD_CWSR_TBA_TMA_SIZE, PROT_READ | PROT_EXEC,
 			MAP_SHARED, offset);
@@ -585,6 +587,31 @@ err_alloc_process:
 	return ERR_PTR(err);
 }
 
+static int init_doorbell_bitmap(struct qcm_process_device *qpd,
+			struct kfd_dev *dev)
+{
+	unsigned int i;
+
+	if (!KFD_IS_SOC15(dev->device_info->asic_family))
+		return 0;
+
+	qpd->doorbell_bitmap =
+		kzalloc(DIV_ROUND_UP(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS,
+				     BITS_PER_BYTE), GFP_KERNEL);
+	if (!qpd->doorbell_bitmap)
+		return -ENOMEM;
+
+	/* Mask out any reserved doorbells */
+	for (i = 0; i < KFD_MAX_NUM_OF_QUEUES_PER_PROCESS; i++)
+		if ((dev->shared_resources.reserved_doorbell_mask & i) ==
+		    dev->shared_resources.reserved_doorbell_val) {
+			set_bit(i, qpd->doorbell_bitmap);
+			pr_debug("reserved doorbell 0x%03x\n", i);
+		}
+
+	return 0;
+}
+
 struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev,
 							struct kfd_process *p)
 {
@@ -606,6 +633,12 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 	if (!pdd)
 		return NULL;
 
+	if (init_doorbell_bitmap(&pdd->qpd, dev)) {
+		pr_err("Failed to init doorbell for process\n");
+		kfree(pdd);
+		return NULL;
+	}
+
 	pdd->dev = dev;
 	INIT_LIST_HEAD(&pdd->qpd.queues_list);
 	INIT_LIST_HEAD(&pdd->qpd.priv_queue_list);
@@ -808,7 +841,7 @@ struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm)
  * Eviction is reference-counted per process-device. This means multiple
  * evictions from different sources can be nested safely.
  */
-static int process_evict_queues(struct kfd_process *p)
+int kfd_process_evict_queues(struct kfd_process *p)
 {
 	struct kfd_process_device *pdd;
 	int r = 0;
@@ -844,7 +877,7 @@ fail:
 }
 
 /* process_restore_queues - Restore all user queues of a process */
-static  int process_restore_queues(struct kfd_process *p)
+int kfd_process_restore_queues(struct kfd_process *p)
 {
 	struct kfd_process_device *pdd;
 	int r, ret = 0;
@@ -886,7 +919,7 @@ static void evict_process_worker(struct work_struct *work)
 	flush_delayed_work(&p->restore_work);
 
 	pr_debug("Started evicting pasid %d\n", p->pasid);
-	ret = process_evict_queues(p);
+	ret = kfd_process_evict_queues(p);
 	if (!ret) {
 		dma_fence_signal(p->ef);
 		dma_fence_put(p->ef);
@@ -946,7 +979,7 @@ static void restore_process_worker(struct work_struct *work)
 		return;
 	}
 
-	ret = process_restore_queues(p);
+	ret = kfd_process_restore_queues(p);
 	if (!ret)
 		pr_debug("Finished restoring pasid %d\n", p->pasid);
 	else
@@ -963,7 +996,7 @@ void kfd_suspend_all_processes(void)
 		cancel_delayed_work_sync(&p->eviction_work);
 		cancel_delayed_work_sync(&p->restore_work);
 
-		if (process_evict_queues(p))
+		if (kfd_process_evict_queues(p))
 			pr_err("Failed to suspend process %d\n", p->pasid);
 		dma_fence_signal(p->ef);
 		dma_fence_put(p->ef);
@@ -989,15 +1022,12 @@ int kfd_resume_all_processes(void)
 	return ret;
 }
 
-int kfd_reserved_mem_mmap(struct kfd_process *process,
+int kfd_reserved_mem_mmap(struct kfd_dev *dev, struct kfd_process *process,
 			  struct vm_area_struct *vma)
 {
-	struct kfd_dev *dev = kfd_device_by_id(vma->vm_pgoff);
 	struct kfd_process_device *pdd;
 	struct qcm_process_device *qpd;
 
-	if (!dev)
-		return -EINVAL;
 	if ((vma->vm_end - vma->vm_start) != KFD_CWSR_TBA_TMA_SIZE) {
 		pr_err("Incorrect CWSR mapping size.\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 7817e327ea6d..d65ce0436b31 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -119,9 +119,6 @@ static int create_cp_queue(struct process_queue_manager *pqm,
 	/* Doorbell initialized in user space*/
 	q_properties->doorbell_ptr = NULL;
 
-	q_properties->doorbell_off =
-			kfd_queue_id_to_doorbell(dev, pqm->process, qid);
-
 	/* let DQM handle it*/
 	q_properties->vmid = 0;
 	q_properties->queue_id = qid;
@@ -244,10 +241,20 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 	}
 
 	if (retval != 0) {
-		pr_err("DQM create queue failed\n");
+		pr_err("Pasid %d DQM create queue %d failed. ret %d\n",
+			pqm->process->pasid, type, retval);
 		goto err_create_queue;
 	}
 
+	if (q)
+		/* Return the doorbell offset within the doorbell page
+		 * to the caller so it can be passed up to user mode
+		 * (in bytes).
+		 */
+		properties->doorbell_off =
+			(q->properties.doorbell_off * sizeof(uint32_t)) &
+			(kfd_doorbell_process_slice(dev) - 1);
+
 	pr_debug("PQM After DQM create queue\n");
 
 	list_add(&pqn->process_queue_list, &pqm->queues);
@@ -313,8 +320,11 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 		dqm = pqn->q->device->dqm;
 		retval = dqm->ops.destroy_queue(dqm, &pdd->qpd, pqn->q);
 		if (retval) {
-			pr_debug("Destroy queue failed, returned %d\n", retval);
-			goto err_destroy_queue;
+			pr_err("Pasid %d destroy queue %d failed, ret %d\n",
+				pqm->process->pasid,
+				pqn->q->properties.queue_id, retval);
+			if (retval != -ETIME)
+				goto err_destroy_queue;
 		}
 		uninit_queue(pqn->q);
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index a5315d4f1c95..6dcd621e5b71 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -36,8 +36,8 @@ void print_queue_properties(struct queue_properties *q)
 	pr_debug("Queue Address: 0x%llX\n", q->queue_address);
 	pr_debug("Queue Id: %u\n", q->queue_id);
 	pr_debug("Queue Process Vmid: %u\n", q->vmid);
-	pr_debug("Queue Read Pointer: 0x%p\n", q->read_ptr);
-	pr_debug("Queue Write Pointer: 0x%p\n", q->write_ptr);
+	pr_debug("Queue Read Pointer: 0x%px\n", q->read_ptr);
+	pr_debug("Queue Write Pointer: 0x%px\n", q->write_ptr);
 	pr_debug("Queue Doorbell Pointer: 0x%p\n", q->doorbell_ptr);
 	pr_debug("Queue Doorbell Offset: %u\n", q->doorbell_off);
 }
@@ -53,8 +53,8 @@ void print_queue(struct queue *q)
 	pr_debug("Queue Address: 0x%llX\n", q->properties.queue_address);
 	pr_debug("Queue Id: %u\n", q->properties.queue_id);
 	pr_debug("Queue Process Vmid: %u\n", q->properties.vmid);
-	pr_debug("Queue Read Pointer: 0x%p\n", q->properties.read_ptr);
-	pr_debug("Queue Write Pointer: 0x%p\n", q->properties.write_ptr);
+	pr_debug("Queue Read Pointer: 0x%px\n", q->properties.read_ptr);
+	pr_debug("Queue Write Pointer: 0x%px\n", q->properties.write_ptr);
 	pr_debug("Queue Doorbell Pointer: 0x%p\n", q->properties.doorbell_ptr);
 	pr_debug("Queue Doorbell Offset: %u\n", q->properties.doorbell_off);
 	pr_debug("Queue MQD Address: 0x%p\n", q->mqd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index ac28abc94e57..bc95d4dfee2e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1239,6 +1239,12 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 			HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) &
 			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
 		break;
+	case CHIP_VEGA10:
+	case CHIP_RAVEN:
+		dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 <<
+			HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) &
+			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
+		break;
 	default:
 		WARN(1, "Unexpected ASIC family %u",
 		     dev->gpu->device_info->asic_family);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index eb54cfcaf039..7d9c3f948dff 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -45,6 +45,7 @@
 
 #define HSA_CAP_DOORBELL_TYPE_PRE_1_0		0x0
 #define HSA_CAP_DOORBELL_TYPE_1_0		0x1
+#define HSA_CAP_DOORBELL_TYPE_2_0		0x2
 #define HSA_CAP_AQL_QUEUE_DOUBLE_MAP		0x00004000
 
 struct kfd_node_properties {
diff --git a/drivers/gpu/drm/amd/amdkfd/soc15_int.h b/drivers/gpu/drm/amd/amdkfd/soc15_int.h
new file mode 100644
index 000000000000..0bc0b25cb410
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/soc15_int.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright 2016-2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef HSA_SOC15_INT_H_INCLUDED
+#define HSA_SOC15_INT_H_INCLUDED
+
+#include "soc15_ih_clientid.h"
+
+#define SOC15_INTSRC_CP_END_OF_PIPE	181
+#define SOC15_INTSRC_CP_BAD_OPCODE	183
+#define SOC15_INTSRC_SQ_INTERRUPT_MSG	239
+#define SOC15_INTSRC_VMC_FAULT		0
+#define SOC15_INTSRC_SDMA_TRAP		224
+
+
+#define SOC15_CLIENT_ID_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[0]) & 0xff)
+#define SOC15_SOURCE_ID_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[0]) >> 8 & 0xff)
+#define SOC15_RING_ID_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[0]) >> 16 & 0xff)
+#define SOC15_VMID_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[0]) >> 24 & 0xf)
+#define SOC15_VMID_TYPE_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[0]) >> 31 & 0x1)
+#define SOC15_PASID_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[3]) & 0xffff)
+#define SOC15_CONTEXT_ID0_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[4]))
+#define SOC15_CONTEXT_ID1_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[5]))
+#define SOC15_CONTEXT_ID2_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[6]))
+#define SOC15_CONTEXT_ID3_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[7]))
+
+#endif
+
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 5b124a67404c..d5d4586e6176 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -9,14 +9,6 @@ config DRM_AMD_DC
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
-config DRM_AMD_DC_PRE_VEGA
-	bool "DC support for Polaris and older ASICs"
-	default y
-	help
-	  Choose this option to enable the new DC support for older asics
-	  by default. This includes Polaris, Carrizo, Tonga, Bonaire,
-	  and Hawaii.
-
 config DRM_AMD_DC_FBC
 	bool "AMD FBC - Enable Frame Buffer Compression"
 	depends on DRM_AMD_DC
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 4e2f379ce217..f9b9ab90558c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -433,11 +433,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.dce_environment = DCE_ENV_PRODUCTION_DRV;
 
-	if (amdgpu_dc_log)
-		init_data.log_mask = DC_DEFAULT_LOG_MASK;
-	else
-		init_data.log_mask = DC_MIN_LOG_MASK;
-
 	/*
 	 * TODO debug why this doesn't work on Raven
 	 */
@@ -649,18 +644,6 @@ amdgpu_dm_find_first_crtc_matching_connector(struct drm_atomic_state *state,
 static int dm_resume(void *handle)
 {
 	struct amdgpu_device *adev = handle;
-	struct amdgpu_display_manager *dm = &adev->dm;
-	int ret = 0;
-
-	/* power on hardware */
-	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0);
-
-	ret = amdgpu_dm_display_resume(adev);
-	return ret;
-}
-
-int amdgpu_dm_display_resume(struct amdgpu_device *adev)
-{
 	struct drm_device *ddev = adev->ddev;
 	struct amdgpu_display_manager *dm = &adev->dm;
 	struct amdgpu_dm_connector *aconnector;
@@ -671,10 +654,12 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev)
 	struct drm_plane *plane;
 	struct drm_plane_state *new_plane_state;
 	struct dm_plane_state *dm_new_plane_state;
-
-	int ret = 0;
+	int ret;
 	int i;
 
+	/* power on hardware */
+	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0);
+
 	/* program HPD filter */
 	dc_resume(dm->dc);
 
@@ -688,8 +673,7 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev)
 	amdgpu_dm_irq_resume_early(adev);
 
 	/* Do detection*/
-	list_for_each_entry(connector,
-			&ddev->mode_config.connector_list, head) {
+	list_for_each_entry(connector, &ddev->mode_config.connector_list, head) {
 		aconnector = to_amdgpu_dm_connector(connector);
 
 		/*
@@ -711,7 +695,7 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev)
 	}
 
 	/* Force mode set in atomic comit */
-	for_each_new_crtc_in_state(adev->dm.cached_state, crtc, new_crtc_state, i)
+	for_each_new_crtc_in_state(dm->cached_state, crtc, new_crtc_state, i)
 		new_crtc_state->active_changed = true;
 
 	/*
@@ -719,7 +703,7 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev)
 	 * them here, since they were duplicated as part of the suspend
 	 * procedure.
 	 */
-	for_each_new_crtc_in_state(adev->dm.cached_state, crtc, new_crtc_state, i) {
+	for_each_new_crtc_in_state(dm->cached_state, crtc, new_crtc_state, i) {
 		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
 		if (dm_new_crtc_state->stream) {
 			WARN_ON(kref_read(&dm_new_crtc_state->stream->refcount) > 1);
@@ -728,7 +712,7 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev)
 		}
 	}
 
-	for_each_new_plane_in_state(adev->dm.cached_state, plane, new_plane_state, i) {
+	for_each_new_plane_in_state(dm->cached_state, plane, new_plane_state, i) {
 		dm_new_plane_state = to_dm_plane_state(new_plane_state);
 		if (dm_new_plane_state->dc_state) {
 			WARN_ON(kref_read(&dm_new_plane_state->dc_state->refcount) > 1);
@@ -737,9 +721,9 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev)
 		}
 	}
 
-	ret = drm_atomic_helper_resume(ddev, adev->dm.cached_state);
+	ret = drm_atomic_helper_resume(ddev, dm->cached_state);
 
-	adev->dm.cached_state = NULL;
+	dm->cached_state = NULL;
 
 	amdgpu_dm_irq_resume_late(adev);
 
@@ -927,6 +911,7 @@ amdgpu_dm_update_connector_after_detect(struct amdgpu_dm_connector *aconnector)
 		drm_mode_connector_update_edid_property(connector, NULL);
 		aconnector->num_modes = 0;
 		aconnector->dc_sink = NULL;
+		aconnector->edid = NULL;
 	}
 
 	mutex_unlock(&dev->mode_config.mutex);
@@ -1131,6 +1116,7 @@ static int dce110_register_irq_handlers(struct amdgpu_device *adev)
 
 	if (adev->asic_type == CHIP_VEGA10 ||
 	    adev->asic_type == CHIP_VEGA12 ||
+	    adev->asic_type == CHIP_VEGA20 ||
 	    adev->asic_type == CHIP_RAVEN)
 		client_id = SOC15_IH_CLIENTID_DCE;
 
@@ -1529,8 +1515,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS10:
 	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 		if (dce110_register_irq_handlers(dm->adev)) {
 			DRM_ERROR("DM: Failed to initialize IRQ\n");
 			goto fail;
@@ -1549,7 +1537,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		break;
 #endif
 	default:
-		DRM_ERROR("Usupported ASIC type: 0x%X\n", adev->asic_type);
+		DRM_ERROR("Unsupported ASIC type: 0x%X\n", adev->asic_type);
 		goto fail;
 	}
 
@@ -1657,7 +1645,6 @@ static ssize_t s3_debug_store(struct device *device,
 	if (ret == 0) {
 		if (s3_state) {
 			dm_resume(adev);
-			amdgpu_dm_display_resume(adev);
 			drm_kms_helper_hotplug_event(adev->ddev);
 		} else
 			dm_suspend(adev);
@@ -1722,6 +1709,7 @@ static int dm_early_init(void *handle)
 		adev->mode_info.plane_type = dm_plane_type_default;
 		break;
 	case CHIP_POLARIS10:
+	case CHIP_VEGAM:
 		adev->mode_info.num_crtc = 6;
 		adev->mode_info.num_hpd = 6;
 		adev->mode_info.num_dig = 6;
@@ -1729,6 +1717,7 @@ static int dm_early_init(void *handle)
 		break;
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
+	case CHIP_VEGA20:
 		adev->mode_info.num_crtc = 6;
 		adev->mode_info.num_hpd = 6;
 		adev->mode_info.num_dig = 6;
@@ -1743,7 +1732,7 @@ static int dm_early_init(void *handle)
 		break;
 #endif
 	default:
-		DRM_ERROR("Usupported ASIC type: 0x%X\n", adev->asic_type);
+		DRM_ERROR("Unsupported ASIC type: 0x%X\n", adev->asic_type);
 		return -EINVAL;
 	}
 
@@ -1848,7 +1837,7 @@ static bool fill_rects_from_plane_state(const struct drm_plane_state *state,
 static int get_fb_info(const struct amdgpu_framebuffer *amdgpu_fb,
 		       uint64_t *tiling_flags)
 {
-	struct amdgpu_bo *rbo = gem_to_amdgpu_bo(amdgpu_fb->obj);
+	struct amdgpu_bo *rbo = gem_to_amdgpu_bo(amdgpu_fb->base.obj[0]);
 	int r = amdgpu_bo_reserve(rbo, false);
 
 	if (unlikely(r)) {
@@ -1977,6 +1966,7 @@ static int fill_plane_attributes_from_fb(struct amdgpu_device *adev,
 
 	if (adev->asic_type == CHIP_VEGA10 ||
 	    adev->asic_type == CHIP_VEGA12 ||
+	    adev->asic_type == CHIP_VEGA20 ||
 	    adev->asic_type == CHIP_RAVEN) {
 		/* Fill GFX9 params */
 		plane_state->tiling_info.gfx9.num_pipes =
@@ -2017,7 +2007,6 @@ static int fill_plane_attributes(struct amdgpu_device *adev,
 	const struct amdgpu_framebuffer *amdgpu_fb =
 		to_amdgpu_framebuffer(plane_state->fb);
 	const struct drm_crtc *crtc = plane_state->crtc;
-	struct dc_transfer_func *input_tf;
 	int ret = 0;
 
 	if (!fill_rects_from_plane_state(plane_state, dc_plane_state))
@@ -2031,13 +2020,6 @@ static int fill_plane_attributes(struct amdgpu_device *adev,
 	if (ret)
 		return ret;
 
-	input_tf = dc_create_transfer_func();
-
-	if (input_tf == NULL)
-		return -ENOMEM;
-
-	dc_plane_state->in_transfer_func = input_tf;
-
 	/*
 	 * Always set input transfer function, since plane state is refreshed
 	 * every time.
@@ -2206,7 +2188,6 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 					     const struct drm_connector *connector)
 {
 	struct dc_crtc_timing *timing_out = &stream->timing;
-	struct dc_transfer_func *tf = dc_create_transfer_func();
 
 	memset(timing_out, 0, sizeof(struct dc_crtc_timing));
 
@@ -2250,9 +2231,8 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 
 	stream->output_color_space = get_output_color_space(timing_out);
 
-	tf->type = TF_TYPE_PREDEFINED;
-	tf->tf = TRANSFER_FUNCTION_SRGB;
-	stream->out_transfer_func = tf;
+	stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
+	stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
 }
 
 static void fill_audio_info(struct audio_info *audio_info,
@@ -2488,6 +2468,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 
 	update_stream_signal(stream);
 
+	if (dm_state && dm_state->freesync_capable)
+		stream->ignore_msa_timing_param = true;
+
 	return stream;
 }
 
@@ -2710,18 +2693,15 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector)
 	const struct dc_link *link = aconnector->dc_link;
 	struct amdgpu_device *adev = connector->dev->dev_private;
 	struct amdgpu_display_manager *dm = &adev->dm;
+
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\
 	defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
 
 	if ((link->connector_signal & (SIGNAL_TYPE_EDP | SIGNAL_TYPE_LVDS)) &&
-	    link->type != dc_connection_none) {
-		amdgpu_dm_register_backlight_device(dm);
-
-		if (dm->backlight_dev) {
-			backlight_device_unregister(dm->backlight_dev);
-			dm->backlight_dev = NULL;
-		}
-
+	    link->type != dc_connection_none &&
+	    dm->backlight_dev) {
+		backlight_device_unregister(dm->backlight_dev);
+		dm->backlight_dev = NULL;
 	}
 #endif
 	drm_connector_unregister(connector);
@@ -2855,7 +2835,7 @@ static void handle_edid_mgmt(struct amdgpu_dm_connector *aconnector)
 	create_eml_sink(aconnector);
 }
 
-int amdgpu_dm_connector_mode_valid(struct drm_connector *connector,
+enum drm_mode_status amdgpu_dm_connector_mode_valid(struct drm_connector *connector,
 				   struct drm_display_mode *mode)
 {
 	int result = MODE_ERROR;
@@ -3058,8 +3038,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	}
 
 	afb = to_amdgpu_framebuffer(new_state->fb);
-
-	obj = afb->obj;
+	obj = new_state->fb->obj[0];
 	rbo = gem_to_amdgpu_bo(obj);
 	adev = amdgpu_ttm_adev(rbo->tbo.bdev);
 	r = amdgpu_bo_reserve(rbo, false);
@@ -3067,12 +3046,11 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 		return r;
 
 	if (plane->type != DRM_PLANE_TYPE_CURSOR)
-		domain = amdgpu_display_framebuffer_domains(adev);
+		domain = amdgpu_display_supported_domains(adev);
 	else
 		domain = AMDGPU_GEM_DOMAIN_VRAM;
 
 	r = amdgpu_bo_pin(rbo, domain, &afb->address);
-
 	amdgpu_bo_unreserve(rbo);
 
 	if (unlikely(r != 0)) {
@@ -3123,14 +3101,12 @@ static void dm_plane_helper_cleanup_fb(struct drm_plane *plane,
 				       struct drm_plane_state *old_state)
 {
 	struct amdgpu_bo *rbo;
-	struct amdgpu_framebuffer *afb;
 	int r;
 
 	if (!old_state->fb)
 		return;
 
-	afb = to_amdgpu_framebuffer(old_state->fb);
-	rbo = gem_to_amdgpu_bo(afb->obj);
+	rbo = gem_to_amdgpu_bo(old_state->fb->obj[0]);
 	r = amdgpu_bo_reserve(rbo, false);
 	if (unlikely(r)) {
 		DRM_ERROR("failed to reserve rbo before unpin\n");
@@ -3773,7 +3749,7 @@ static void remove_stream(struct amdgpu_device *adev,
 static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc,
 			       struct dc_cursor_position *position)
 {
-	struct amdgpu_crtc *amdgpu_crtc = amdgpu_crtc = to_amdgpu_crtc(crtc);
+	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	int x, y;
 	int xorigin = 0, yorigin = 0;
 
@@ -3905,7 +3881,7 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 	int r, vpos, hpos;
 	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
 	struct amdgpu_framebuffer *afb = to_amdgpu_framebuffer(fb);
-	struct amdgpu_bo *abo = gem_to_amdgpu_bo(afb->obj);
+	struct amdgpu_bo *abo = gem_to_amdgpu_bo(fb->obj[0]);
 	struct amdgpu_device *adev = crtc->dev->dev_private;
 	bool async_flip = (crtc->state->pageflip_flags & DRM_MODE_PAGE_FLIP_ASYNC) != 0;
 	struct dc_flip_addrs addr = { {0} };
@@ -3986,6 +3962,96 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 	spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 }
 
+/*
+ * TODO this whole function needs to go
+ *
+ * dc_surface_update is needlessly complex. See if we can just replace this
+ * with a dc_plane_state and follow the atomic model a bit more closely here.
+ */
+static bool commit_planes_to_stream(
+		struct dc *dc,
+		struct dc_plane_state **plane_states,
+		uint8_t new_plane_count,
+		struct dm_crtc_state *dm_new_crtc_state,
+		struct dm_crtc_state *dm_old_crtc_state,
+		struct dc_state *state)
+{
+	/* no need to dynamically allocate this. it's pretty small */
+	struct dc_surface_update updates[MAX_SURFACES];
+	struct dc_flip_addrs *flip_addr;
+	struct dc_plane_info *plane_info;
+	struct dc_scaling_info *scaling_info;
+	int i;
+	struct dc_stream_state *dc_stream = dm_new_crtc_state->stream;
+	struct dc_stream_update *stream_update =
+			kzalloc(sizeof(struct dc_stream_update), GFP_KERNEL);
+
+	if (!stream_update) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	flip_addr = kcalloc(MAX_SURFACES, sizeof(struct dc_flip_addrs),
+			    GFP_KERNEL);
+	plane_info = kcalloc(MAX_SURFACES, sizeof(struct dc_plane_info),
+			     GFP_KERNEL);
+	scaling_info = kcalloc(MAX_SURFACES, sizeof(struct dc_scaling_info),
+			       GFP_KERNEL);
+
+	if (!flip_addr || !plane_info || !scaling_info) {
+		kfree(flip_addr);
+		kfree(plane_info);
+		kfree(scaling_info);
+		kfree(stream_update);
+		return false;
+	}
+
+	memset(updates, 0, sizeof(updates));
+
+	stream_update->src = dc_stream->src;
+	stream_update->dst = dc_stream->dst;
+	stream_update->out_transfer_func = dc_stream->out_transfer_func;
+
+	for (i = 0; i < new_plane_count; i++) {
+		updates[i].surface = plane_states[i];
+		updates[i].gamma =
+			(struct dc_gamma *)plane_states[i]->gamma_correction;
+		updates[i].in_transfer_func = plane_states[i]->in_transfer_func;
+		flip_addr[i].address = plane_states[i]->address;
+		flip_addr[i].flip_immediate = plane_states[i]->flip_immediate;
+		plane_info[i].color_space = plane_states[i]->color_space;
+		plane_info[i].format = plane_states[i]->format;
+		plane_info[i].plane_size = plane_states[i]->plane_size;
+		plane_info[i].rotation = plane_states[i]->rotation;
+		plane_info[i].horizontal_mirror = plane_states[i]->horizontal_mirror;
+		plane_info[i].stereo_format = plane_states[i]->stereo_format;
+		plane_info[i].tiling_info = plane_states[i]->tiling_info;
+		plane_info[i].visible = plane_states[i]->visible;
+		plane_info[i].per_pixel_alpha = plane_states[i]->per_pixel_alpha;
+		plane_info[i].dcc = plane_states[i]->dcc;
+		scaling_info[i].scaling_quality = plane_states[i]->scaling_quality;
+		scaling_info[i].src_rect = plane_states[i]->src_rect;
+		scaling_info[i].dst_rect = plane_states[i]->dst_rect;
+		scaling_info[i].clip_rect = plane_states[i]->clip_rect;
+
+		updates[i].flip_addr = &flip_addr[i];
+		updates[i].plane_info = &plane_info[i];
+		updates[i].scaling_info = &scaling_info[i];
+	}
+
+	dc_commit_updates_for_stream(
+			dc,
+			updates,
+			new_plane_count,
+			dc_stream, stream_update, plane_states, state);
+
+	kfree(flip_addr);
+	kfree(plane_info);
+	kfree(scaling_info);
+	kfree(stream_update);
+	return true;
+}
+
 static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct drm_device *dev,
 				    struct amdgpu_display_manager *dm,
@@ -4001,6 +4067,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	struct drm_crtc_state *new_pcrtc_state =
 			drm_atomic_get_new_crtc_state(state, pcrtc);
 	struct dm_crtc_state *acrtc_state = to_dm_crtc_state(new_pcrtc_state);
+	struct dm_crtc_state *dm_old_crtc_state =
+			to_dm_crtc_state(drm_atomic_get_old_crtc_state(state, pcrtc));
 	struct dm_atomic_state *dm_state = to_dm_atomic_state(state);
 	int planes_count = 0;
 	unsigned long flags;
@@ -4037,7 +4105,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		}
 		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 
-		if (!pflip_needed) {
+		if (!pflip_needed || plane->type == DRM_PLANE_TYPE_OVERLAY) {
 			WARN_ON(!dm_new_plane_state->dc_state);
 
 			plane_states_constructed[planes_count] = dm_new_plane_state->dc_state;
@@ -4079,10 +4147,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags);
 		}
 
-		if (false == dc_commit_planes_to_stream(dm->dc,
+
+		if (false == commit_planes_to_stream(dm->dc,
 							plane_states_constructed,
 							planes_count,
-							dc_stream_attach,
+							acrtc_state,
+							dm_old_crtc_state,
 							dm_state->context))
 			dm_error("%s: Failed to attach plane!\n", __func__);
 	} else {
@@ -4307,8 +4377,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
 		struct dc_stream_status *status = NULL;
 
-		if (acrtc)
+		if (acrtc) {
 			new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
+			old_crtc_state = drm_atomic_get_old_crtc_state(state, &acrtc->base);
+		}
 
 		/* Skip any modesets/resets */
 		if (!acrtc || drm_atomic_crtc_needs_modeset(new_crtc_state))
@@ -4331,11 +4403,12 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		WARN_ON(!status->plane_count);
 
 		/*TODO How it works with MPO ?*/
-		if (!dc_commit_planes_to_stream(
+		if (!commit_planes_to_stream(
 				dm->dc,
 				status->plane_states,
 				status->plane_count,
-				dm_new_crtc_state->stream,
+				dm_new_crtc_state,
+				to_dm_crtc_state(old_crtc_state),
 				dm_state->context))
 			dm_error("%s: Failed to update stream scaling!\n", __func__);
 	}
@@ -4555,8 +4628,9 @@ static int dm_update_crtcs_state(struct dc *dc,
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		struct amdgpu_crtc *acrtc = NULL;
 		struct amdgpu_dm_connector *aconnector = NULL;
-		struct drm_connector_state *new_con_state = NULL;
-		struct dm_connector_state *dm_conn_state = NULL;
+		struct drm_connector_state *drm_new_conn_state = NULL, *drm_old_conn_state = NULL;
+		struct dm_connector_state *dm_new_conn_state = NULL, *dm_old_conn_state = NULL;
+		struct drm_plane_state *new_plane_state = NULL;
 
 		new_stream = NULL;
 
@@ -4564,24 +4638,34 @@ static int dm_update_crtcs_state(struct dc *dc,
 		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
 		acrtc = to_amdgpu_crtc(crtc);
 
+		new_plane_state = drm_atomic_get_new_plane_state(state, new_crtc_state->crtc->primary);
+
+		if (new_crtc_state->enable && new_plane_state && !new_plane_state->fb) {
+			ret = -EINVAL;
+			goto fail;
+		}
+
 		aconnector = amdgpu_dm_find_first_crtc_matching_connector(state, crtc);
 
 		/* TODO This hack should go away */
 		if (aconnector && enable) {
 			// Make sure fake sink is created in plug-in scenario
-			new_con_state = drm_atomic_get_connector_state(state,
+			drm_new_conn_state = drm_atomic_get_new_connector_state(state,
  								    &aconnector->base);
+			drm_old_conn_state = drm_atomic_get_old_connector_state(state,
+								    &aconnector->base);
 
-			if (IS_ERR(new_con_state)) {
-				ret = PTR_ERR_OR_ZERO(new_con_state);
+			if (IS_ERR(drm_new_conn_state)) {
+				ret = PTR_ERR_OR_ZERO(drm_new_conn_state);
 				break;
 			}
 
-			dm_conn_state = to_dm_connector_state(new_con_state);
+			dm_new_conn_state = to_dm_connector_state(drm_new_conn_state);
+			dm_old_conn_state = to_dm_connector_state(drm_old_conn_state);
 
 			new_stream = create_stream_for_sink(aconnector,
 							     &new_crtc_state->mode,
-							    dm_conn_state);
+							    dm_new_conn_state);
 
 			/*
 			 * we can have no stream on ACTION_SET if a display
@@ -4687,20 +4771,30 @@ next_crtc:
 		 * We want to do dc stream updates that do not require a
 		 * full modeset below.
 		 */
-		if (!enable || !aconnector || modereset_required(new_crtc_state))
+		if (!(enable && aconnector && new_crtc_state->enable &&
+		      new_crtc_state->active))
 			continue;
 		/*
 		 * Given above conditions, the dc state cannot be NULL because:
-		 * 1. We're attempting to enable a CRTC. Which has a...
-		 * 2. Valid connector attached, and
-		 * 3. User does not want to reset it (disable or mark inactive,
-		 *    which can happen on a CRTC that's already disabled).
-		 * => It currently exists.
+		 * 1. We're in the process of enabling CRTCs (just been added
+		 *    to the dc context, or already is on the context)
+		 * 2. Has a valid connector attached, and
+		 * 3. Is currently active and enabled.
+		 * => The dc stream state currently exists.
 		 */
 		BUG_ON(dm_new_crtc_state->stream == NULL);
 
-		/* Color managment settings */
-		if (dm_new_crtc_state->base.color_mgmt_changed) {
+		/* Scaling or underscan settings */
+		if (is_scaling_state_different(dm_old_conn_state, dm_new_conn_state))
+			update_stream_scaling_settings(
+				&new_crtc_state->mode, dm_new_conn_state, dm_new_crtc_state->stream);
+
+		/*
+		 * Color management settings. We also update color properties
+		 * when a modeset is needed, to ensure it gets reprogrammed.
+		 */
+		if (dm_new_crtc_state->base.color_mgmt_changed ||
+		    drm_atomic_crtc_needs_modeset(new_crtc_state)) {
 			ret = amdgpu_dm_set_regamma_lut(dm_new_crtc_state);
 			if (ret)
 				goto fail;
@@ -4747,7 +4841,8 @@ static int dm_update_planes_state(struct dc *dc,
 
 		/* Remove any changed/removed planes */
 		if (!enable) {
-			if (pflip_needed)
+			if (pflip_needed &&
+			    plane->type != DRM_PLANE_TYPE_OVERLAY)
 				continue;
 
 			if (!old_plane_crtc)
@@ -4760,7 +4855,7 @@ static int dm_update_planes_state(struct dc *dc,
 			if (!dm_old_crtc_state->stream)
 				continue;
 
-			DRM_DEBUG_DRIVER("Disabling DRM plane: %d on DRM crtc %d\n",
+			DRM_DEBUG_ATOMIC("Disabling DRM plane: %d on DRM crtc %d\n",
 					plane->base.id, old_plane_crtc->base.id);
 
 			if (!dc_remove_plane_from_context(
@@ -4794,7 +4889,8 @@ static int dm_update_planes_state(struct dc *dc,
 			if (!dm_new_crtc_state->stream)
 				continue;
 
-			if (pflip_needed)
+			if (pflip_needed &&
+			    plane->type != DRM_PLANE_TYPE_OVERLAY)
 				continue;
 
 			WARN_ON(dm_new_plane_state->dc_state);
@@ -5001,17 +5097,24 @@ void amdgpu_dm_add_sink_to_freesync_module(struct drm_connector *connector,
 					   struct edid *edid)
 {
 	int i;
-	uint64_t val_capable;
 	bool edid_check_required;
 	struct detailed_timing *timing;
 	struct detailed_non_pixel *data;
 	struct detailed_data_monitor_range *range;
 	struct amdgpu_dm_connector *amdgpu_dm_connector =
 			to_amdgpu_dm_connector(connector);
+	struct dm_connector_state *dm_con_state;
 
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 
+	if (!connector->state) {
+		DRM_ERROR("%s - Connector has no state", __func__);
+		return;
+	}
+
+	dm_con_state = to_dm_connector_state(connector->state);
+
 	edid_check_required = false;
 	if (!amdgpu_dm_connector->dc_sink) {
 		DRM_ERROR("dc_sink NULL, could not add free_sync module.\n");
@@ -5030,7 +5133,7 @@ void amdgpu_dm_add_sink_to_freesync_module(struct drm_connector *connector,
 						amdgpu_dm_connector);
 		}
 	}
-	val_capable = 0;
+	dm_con_state->freesync_capable = false;
 	if (edid_check_required == true && (edid->version > 1 ||
 	   (edid->version == 1 && edid->revision > 1))) {
 		for (i = 0; i < 4; i++) {
@@ -5066,7 +5169,7 @@ void amdgpu_dm_add_sink_to_freesync_module(struct drm_connector *connector,
 					amdgpu_dm_connector->min_vfreq * 1000000;
 			amdgpu_dm_connector->caps.max_refresh_in_micro_hz =
 					amdgpu_dm_connector->max_vfreq * 1000000;
-				val_capable = 1;
+			dm_con_state->freesync_capable = true;
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index b68400c1154b..d5aa89ad5571 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -28,7 +28,6 @@
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
-#include "dc.h"
 
 /*
  * This file contains the definition for amdgpu_display_manager
@@ -53,6 +52,7 @@
 struct amdgpu_device;
 struct drm_device;
 struct amdgpu_dm_irq_handler_data;
+struct dc;
 
 struct amdgpu_dm_prev_state {
 	struct drm_framebuffer *fb;
@@ -220,6 +220,7 @@ struct dm_connector_state {
 	uint8_t underscan_hborder;
 	bool underscan_enable;
 	struct mod_freesync_user_enable user_enable;
+	bool freesync_capable;
 };
 
 #define to_dm_connector_state(x)\
@@ -246,7 +247,7 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 				     struct dc_link *link,
 				     int link_index);
 
-int amdgpu_dm_connector_mode_valid(struct drm_connector *connector,
+enum drm_mode_status amdgpu_dm_connector_mode_valid(struct drm_connector *connector,
 				   struct drm_display_mode *mode);
 
 void dm_restore_drm_connector_state(struct drm_device *dev,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index f6cb502c303f..b329393307e5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -25,6 +25,7 @@
 
 #include "amdgpu_mode.h"
 #include "amdgpu_dm.h"
+#include "dc.h"
 #include "modules/color/color_gamma.h"
 
 #define MAX_DRM_LUT_VALUE 0xFFFF
@@ -87,9 +88,9 @@ static void __drm_lut_to_dc_gamma(struct drm_color_lut *lut,
 			g = drm_color_lut_extract(lut[i].green, 16);
 			b = drm_color_lut_extract(lut[i].blue, 16);
 
-			gamma->entries.red[i] = dal_fixed31_32_from_int(r);
-			gamma->entries.green[i] = dal_fixed31_32_from_int(g);
-			gamma->entries.blue[i] = dal_fixed31_32_from_int(b);
+			gamma->entries.red[i] = dc_fixpt_from_int(r);
+			gamma->entries.green[i] = dc_fixpt_from_int(g);
+			gamma->entries.blue[i] = dc_fixpt_from_int(b);
 		}
 		return;
 	}
@@ -100,9 +101,9 @@ static void __drm_lut_to_dc_gamma(struct drm_color_lut *lut,
 		g = drm_color_lut_extract(lut[i].green, 16);
 		b = drm_color_lut_extract(lut[i].blue, 16);
 
-		gamma->entries.red[i] = dal_fixed31_32_from_fraction(r, MAX_DRM_LUT_VALUE);
-		gamma->entries.green[i] = dal_fixed31_32_from_fraction(g, MAX_DRM_LUT_VALUE);
-		gamma->entries.blue[i] = dal_fixed31_32_from_fraction(b, MAX_DRM_LUT_VALUE);
+		gamma->entries.red[i] = dc_fixpt_from_fraction(r, MAX_DRM_LUT_VALUE);
+		gamma->entries.green[i] = dc_fixpt_from_fraction(g, MAX_DRM_LUT_VALUE);
+		gamma->entries.blue[i] = dc_fixpt_from_fraction(b, MAX_DRM_LUT_VALUE);
 	}
 }
 
@@ -138,13 +139,6 @@ int amdgpu_dm_set_regamma_lut(struct dm_crtc_state *crtc)
 	lut = (struct drm_color_lut *)blob->data;
 	lut_size = blob->length / sizeof(struct drm_color_lut);
 
-	if (__is_lut_linear(lut, lut_size)) {
-		/* Set to bypass if lut is set to linear */
-		stream->out_transfer_func->type = TF_TYPE_BYPASS;
-		stream->out_transfer_func->tf = TRANSFER_FUNCTION_LINEAR;
-		return 0;
-	}
-
 	gamma = dc_create_gamma();
 	if (!gamma)
 		return -ENOMEM;
@@ -214,7 +208,7 @@ void amdgpu_dm_set_ctm(struct dm_crtc_state *crtc)
 	for (i = 0; i < 12; i++) {
 		/* Skip 4th element */
 		if (i % 4 == 3) {
-			stream->gamut_remap_matrix.matrix[i] = dal_fixed31_32_zero;
+			stream->gamut_remap_matrix.matrix[i] = dc_fixpt_zero;
 			continue;
 		}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index ca0b08bfa2cf..bd449351803f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -330,11 +330,6 @@ bool dm_helpers_dp_mst_send_payload_allocation(
 	return true;
 }
 
-bool dm_helpers_dc_conn_log(struct dc_context *ctx, struct log_entry *entry, enum dc_log_type event)
-{
-	return true;
-}
-
 void dm_dtn_log_begin(struct dc_context *ctx)
 {}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 490017df371d..4be21bf54749 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -329,14 +329,15 @@ void amdgpu_dm_irq_fini(struct amdgpu_device *adev)
 {
 	int src;
 	struct irq_list_head *lh;
+	unsigned long irq_table_flags;
 	DRM_DEBUG_KMS("DM_IRQ: releasing resources.\n");
-
 	for (src = 0; src < DAL_IRQ_SOURCES_NUMBER; src++) {
-
+		DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
 		/* The handler was removed from the table,
 		 * it means it is safe to flush all the 'work'
 		 * (because no code can schedule a new one). */
 		lh = &adev->dm.irq_handler_list_low_tab[src];
+		DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags);
 		flush_work(&lh->work);
 	}
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 8291d74f26bc..4304d9e408b8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -83,21 +83,22 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
 		I2C_MOT_TRUE : I2C_MOT_FALSE;
 	enum ddc_result res;
-	ssize_t read_bytes;
+	uint32_t read_bytes = msg->size;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
 
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_READ:
-		read_bytes = dal_ddc_service_read_dpcd_data(
+		res = dal_ddc_service_read_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
 				false,
 				I2C_MOT_UNDEF,
 				msg->address,
 				msg->buffer,
-				msg->size);
-		return read_bytes;
+				msg->size,
+				&read_bytes);
+		break;
 	case DP_AUX_NATIVE_WRITE:
 		res = dal_ddc_service_write_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
@@ -108,14 +109,15 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				msg->size);
 		break;
 	case DP_AUX_I2C_READ:
-		read_bytes = dal_ddc_service_read_dpcd_data(
+		res = dal_ddc_service_read_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
 				true,
 				mot,
 				msg->address,
 				msg->buffer,
-				msg->size);
-		return read_bytes;
+				msg->size,
+				&read_bytes);
+		break;
 	case DP_AUX_I2C_WRITE:
 		res = dal_ddc_service_write_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
@@ -137,7 +139,9 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 		 r == DDC_RESULT_SUCESSFULL);
 #endif
 
-	return msg->size;
+	if (res != DDC_RESULT_SUCESSFULL)
+		return -EIO;
+	return read_bytes;
 }
 
 static enum drm_connector_status
@@ -161,6 +165,11 @@ dm_dp_mst_connector_destroy(struct drm_connector *connector)
 	struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector);
 	struct amdgpu_encoder *amdgpu_encoder = amdgpu_dm_connector->mst_encoder;
 
+	if (amdgpu_dm_connector->edid) {
+		kfree(amdgpu_dm_connector->edid);
+		amdgpu_dm_connector->edid = NULL;
+	}
+
 	drm_encoder_cleanup(&amdgpu_encoder->base);
 	kfree(amdgpu_encoder);
 	drm_connector_cleanup(connector);
@@ -181,28 +190,22 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
 void dm_dp_mst_dc_sink_create(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-	struct edid *edid;
 	struct dc_sink *dc_sink;
 	struct dc_sink_init_data init_params = {
 			.link = aconnector->dc_link,
 			.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
 
+	/* FIXME none of this is safe. we shouldn't touch aconnector here in
+	 * atomic_check
+	 */
+
 	/*
 	 * TODO: Need to further figure out why ddc.algo is NULL while MST port exists
 	 */
 	if (!aconnector->port || !aconnector->port->aux.ddc.algo)
 		return;
 
-	edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
-
-	if (!edid) {
-		drm_mode_connector_update_edid_property(
-			&aconnector->base,
-			NULL);
-		return;
-	}
-
-	aconnector->edid = edid;
+	ASSERT(aconnector->edid);
 
 	dc_sink = dc_link_add_remote_sink(
 		aconnector->dc_link,
@@ -215,9 +218,6 @@ void dm_dp_mst_dc_sink_create(struct drm_connector *connector)
 
 	amdgpu_dm_add_sink_to_freesync_module(
 			connector, aconnector->edid);
-
-	drm_mode_connector_update_edid_property(
-					&aconnector->base, aconnector->edid);
 }
 
 static int dm_dp_mst_get_modes(struct drm_connector *connector)
@@ -230,10 +230,6 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 
 	if (!aconnector->edid) {
 		struct edid *edid;
-		struct dc_sink *dc_sink;
-		struct dc_sink_init_data init_params = {
-				.link = aconnector->dc_link,
-				.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
 		edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
 
 		if (!edid) {
@@ -244,11 +240,17 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 		}
 
 		aconnector->edid = edid;
+	}
 
+	if (!aconnector->dc_sink) {
+		struct dc_sink *dc_sink;
+		struct dc_sink_init_data init_params = {
+				.link = aconnector->dc_link,
+				.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
 		dc_sink = dc_link_add_remote_sink(
 			aconnector->dc_link,
-			(uint8_t *)edid,
-			(edid->extensions + 1) * EDID_LENGTH,
+			(uint8_t *)aconnector->edid,
+			(aconnector->edid->extensions + 1) * EDID_LENGTH,
 			&init_params);
 
 		dc_sink->priv = aconnector;
@@ -256,12 +258,12 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 
 		if (aconnector->dc_sink)
 			amdgpu_dm_add_sink_to_freesync_module(
-					connector, edid);
-
-		drm_mode_connector_update_edid_property(
-						&aconnector->base, edid);
+					connector, aconnector->edid);
 	}
 
+	drm_mode_connector_update_edid_property(
+					&aconnector->base, aconnector->edid);
+
 	ret = drm_add_edid_modes(connector, aconnector->edid);
 
 	return ret;
@@ -424,14 +426,6 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		dc_sink_release(aconnector->dc_sink);
 		aconnector->dc_sink = NULL;
 	}
-	if (aconnector->edid) {
-		kfree(aconnector->edid);
-		aconnector->edid = NULL;
-	}
-
-	drm_mode_connector_update_edid_property(
-			&aconnector->base,
-			NULL);
 
 	aconnector->mst_connected = false;
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 89342b48be6b..0229c7edb8ad 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -37,8 +37,17 @@
 
 unsigned long long dm_get_timestamp(struct dc_context *ctx)
 {
-	/* TODO: return actual timestamp */
-	return 0;
+	struct timespec64 time;
+
+	getrawmonotonic64(&time);
+	return timespec64_to_ns(&time);
+}
+
+unsigned long long dm_get_elapse_time_in_ns(struct dc_context *ctx,
+		unsigned long long current_time_stamp,
+		unsigned long long last_time_stamp)
+{
+	return current_time_stamp - last_time_stamp;
 }
 
 void dm_perf_trace_timestamp(const char *func_name, unsigned int line)
diff --git a/drivers/gpu/drm/amd/display/dc/basics/Makefile b/drivers/gpu/drm/amd/display/dc/basics/Makefile
index bca33bd9a0d2..b49ea96b5dae 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/basics/Makefile
@@ -24,7 +24,7 @@
 # It provides the general basic services required by other DAL
 # subcomponents.
 
-BASICS = conversion.o fixpt31_32.o fixpt32_32.o \
+BASICS = conversion.o fixpt31_32.o \
 	logger.o log_helpers.o vector.o
 
 AMD_DAL_BASICS = $(addprefix $(AMDDALPATH)/dc/basics/,$(BASICS))
diff --git a/drivers/gpu/drm/amd/display/dc/basics/conversion.c b/drivers/gpu/drm/amd/display/dc/basics/conversion.c
index 310964915a83..50b47f11875c 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/conversion.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/conversion.c
@@ -41,22 +41,22 @@ uint16_t fixed_point_to_int_frac(
 
 	uint16_t result;
 
-	uint16_t d = (uint16_t)dal_fixed31_32_floor(
-		dal_fixed31_32_abs(
+	uint16_t d = (uint16_t)dc_fixpt_floor(
+		dc_fixpt_abs(
 			arg));
 
 	if (d <= (uint16_t)(1 << integer_bits) - (1 / (uint16_t)divisor))
-		numerator = (uint16_t)dal_fixed31_32_round(
-			dal_fixed31_32_mul_int(
+		numerator = (uint16_t)dc_fixpt_round(
+			dc_fixpt_mul_int(
 				arg,
 				divisor));
 	else {
-		numerator = dal_fixed31_32_floor(
-			dal_fixed31_32_sub(
-				dal_fixed31_32_from_int(
+		numerator = dc_fixpt_floor(
+			dc_fixpt_sub(
+				dc_fixpt_from_int(
 					1LL << integer_bits),
-				dal_fixed31_32_recip(
-					dal_fixed31_32_from_int(
+				dc_fixpt_recip(
+					dc_fixpt_from_int(
 						divisor))));
 	}
 
@@ -66,8 +66,8 @@ uint16_t fixed_point_to_int_frac(
 		result = (uint16_t)(
 		(1 << (integer_bits + fractional_bits + 1)) + numerator);
 
-	if ((result != 0) && dal_fixed31_32_lt(
-		arg, dal_fixed31_32_zero))
+	if ((result != 0) && dc_fixpt_lt(
+		arg, dc_fixpt_zero))
 		result |= 1 << (integer_bits + fractional_bits);
 
 	return result;
@@ -84,15 +84,15 @@ void convert_float_matrix(
 	uint32_t buffer_size)
 {
 	const struct fixed31_32 min_2_13 =
-		dal_fixed31_32_from_fraction(S2D13_MIN, DIVIDER);
+		dc_fixpt_from_fraction(S2D13_MIN, DIVIDER);
 	const struct fixed31_32 max_2_13 =
-		dal_fixed31_32_from_fraction(S2D13_MAX, DIVIDER);
+		dc_fixpt_from_fraction(S2D13_MAX, DIVIDER);
 	uint32_t i;
 
 	for (i = 0; i < buffer_size; ++i) {
 		uint32_t reg_value =
 				fixed_point_to_int_frac(
-					dal_fixed31_32_clamp(
+					dc_fixpt_clamp(
 						flt[i],
 						min_2_13,
 						max_2_13),
diff --git a/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c b/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
index 8a9bba879207..e61dd97d0928 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
@@ -26,13 +26,13 @@
 #include "dm_services.h"
 #include "include/fixed31_32.h"
 
-static inline uint64_t abs_i64(
-	int64_t arg)
+static inline unsigned long long abs_i64(
+	long long arg)
 {
 	if (arg > 0)
-		return (uint64_t)arg;
+		return (unsigned long long)arg;
 	else
-		return (uint64_t)(-arg);
+		return (unsigned long long)(-arg);
 }
 
 /*
@@ -40,12 +40,12 @@ static inline uint64_t abs_i64(
  * result = dividend / divisor
  * *remainder = dividend % divisor
  */
-static inline uint64_t complete_integer_division_u64(
-	uint64_t dividend,
-	uint64_t divisor,
-	uint64_t *remainder)
+static inline unsigned long long complete_integer_division_u64(
+	unsigned long long dividend,
+	unsigned long long divisor,
+	unsigned long long *remainder)
 {
-	uint64_t result;
+	unsigned long long result;
 
 	ASSERT(divisor);
 
@@ -64,30 +64,28 @@ static inline uint64_t complete_integer_division_u64(
 #define GET_FRACTIONAL_PART(x) \
 	(FRACTIONAL_PART_MASK & (x))
 
-struct fixed31_32 dal_fixed31_32_from_fraction(
-	int64_t numerator,
-	int64_t denominator)
+struct fixed31_32 dc_fixpt_from_fraction(long long numerator, long long denominator)
 {
 	struct fixed31_32 res;
 
 	bool arg1_negative = numerator < 0;
 	bool arg2_negative = denominator < 0;
 
-	uint64_t arg1_value = arg1_negative ? -numerator : numerator;
-	uint64_t arg2_value = arg2_negative ? -denominator : denominator;
+	unsigned long long arg1_value = arg1_negative ? -numerator : numerator;
+	unsigned long long arg2_value = arg2_negative ? -denominator : denominator;
 
-	uint64_t remainder;
+	unsigned long long remainder;
 
 	/* determine integer part */
 
-	uint64_t res_value = complete_integer_division_u64(
+	unsigned long long res_value = complete_integer_division_u64(
 		arg1_value, arg2_value, &remainder);
 
 	ASSERT(res_value <= LONG_MAX);
 
 	/* determine fractional part */
 	{
-		uint32_t i = FIXED31_32_BITS_PER_FRACTIONAL_PART;
+		unsigned int i = FIXED31_32_BITS_PER_FRACTIONAL_PART;
 
 		do {
 			remainder <<= 1;
@@ -103,14 +101,14 @@ struct fixed31_32 dal_fixed31_32_from_fraction(
 
 	/* round up LSB */
 	{
-		uint64_t summand = (remainder << 1) >= arg2_value;
+		unsigned long long summand = (remainder << 1) >= arg2_value;
 
 		ASSERT(res_value <= LLONG_MAX - summand);
 
 		res_value += summand;
 	}
 
-	res.value = (int64_t)res_value;
+	res.value = (long long)res_value;
 
 	if (arg1_negative ^ arg2_negative)
 		res.value = -res.value;
@@ -118,79 +116,23 @@ struct fixed31_32 dal_fixed31_32_from_fraction(
 	return res;
 }
 
-struct fixed31_32 dal_fixed31_32_from_int_nonconst(
-	int64_t arg)
-{
-	struct fixed31_32 res;
-
-	ASSERT((LONG_MIN <= arg) && (arg <= LONG_MAX));
-
-	res.value = arg << FIXED31_32_BITS_PER_FRACTIONAL_PART;
-
-	return res;
-}
-
-struct fixed31_32 dal_fixed31_32_shl(
-	struct fixed31_32 arg,
-	uint8_t shift)
-{
-	struct fixed31_32 res;
-
-	ASSERT(((arg.value >= 0) && (arg.value <= LLONG_MAX >> shift)) ||
-		((arg.value < 0) && (arg.value >= LLONG_MIN >> shift)));
-
-	res.value = arg.value << shift;
-
-	return res;
-}
-
-struct fixed31_32 dal_fixed31_32_add(
-	struct fixed31_32 arg1,
-	struct fixed31_32 arg2)
-{
-	struct fixed31_32 res;
-
-	ASSERT(((arg1.value >= 0) && (LLONG_MAX - arg1.value >= arg2.value)) ||
-		((arg1.value < 0) && (LLONG_MIN - arg1.value <= arg2.value)));
-
-	res.value = arg1.value + arg2.value;
-
-	return res;
-}
-
-struct fixed31_32 dal_fixed31_32_sub(
-	struct fixed31_32 arg1,
-	struct fixed31_32 arg2)
-{
-	struct fixed31_32 res;
-
-	ASSERT(((arg2.value >= 0) && (LLONG_MIN + arg2.value <= arg1.value)) ||
-		((arg2.value < 0) && (LLONG_MAX + arg2.value >= arg1.value)));
-
-	res.value = arg1.value - arg2.value;
-
-	return res;
-}
-
-struct fixed31_32 dal_fixed31_32_mul(
-	struct fixed31_32 arg1,
-	struct fixed31_32 arg2)
+struct fixed31_32 dc_fixpt_mul(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
 	struct fixed31_32 res;
 
 	bool arg1_negative = arg1.value < 0;
 	bool arg2_negative = arg2.value < 0;
 
-	uint64_t arg1_value = arg1_negative ? -arg1.value : arg1.value;
-	uint64_t arg2_value = arg2_negative ? -arg2.value : arg2.value;
+	unsigned long long arg1_value = arg1_negative ? -arg1.value : arg1.value;
+	unsigned long long arg2_value = arg2_negative ? -arg2.value : arg2.value;
 
-	uint64_t arg1_int = GET_INTEGER_PART(arg1_value);
-	uint64_t arg2_int = GET_INTEGER_PART(arg2_value);
+	unsigned long long arg1_int = GET_INTEGER_PART(arg1_value);
+	unsigned long long arg2_int = GET_INTEGER_PART(arg2_value);
 
-	uint64_t arg1_fra = GET_FRACTIONAL_PART(arg1_value);
-	uint64_t arg2_fra = GET_FRACTIONAL_PART(arg2_value);
+	unsigned long long arg1_fra = GET_FRACTIONAL_PART(arg1_value);
+	unsigned long long arg2_fra = GET_FRACTIONAL_PART(arg2_value);
 
-	uint64_t tmp;
+	unsigned long long tmp;
 
 	res.value = arg1_int * arg2_int;
 
@@ -200,22 +142,22 @@ struct fixed31_32 dal_fixed31_32_mul(
 
 	tmp = arg1_int * arg2_fra;
 
-	ASSERT(tmp <= (uint64_t)(LLONG_MAX - res.value));
+	ASSERT(tmp <= (unsigned long long)(LLONG_MAX - res.value));
 
 	res.value += tmp;
 
 	tmp = arg2_int * arg1_fra;
 
-	ASSERT(tmp <= (uint64_t)(LLONG_MAX - res.value));
+	ASSERT(tmp <= (unsigned long long)(LLONG_MAX - res.value));
 
 	res.value += tmp;
 
 	tmp = arg1_fra * arg2_fra;
 
 	tmp = (tmp >> FIXED31_32_BITS_PER_FRACTIONAL_PART) +
-		(tmp >= (uint64_t)dal_fixed31_32_half.value);
+		(tmp >= (unsigned long long)dc_fixpt_half.value);
 
-	ASSERT(tmp <= (uint64_t)(LLONG_MAX - res.value));
+	ASSERT(tmp <= (unsigned long long)(LLONG_MAX - res.value));
 
 	res.value += tmp;
 
@@ -225,18 +167,17 @@ struct fixed31_32 dal_fixed31_32_mul(
 	return res;
 }
 
-struct fixed31_32 dal_fixed31_32_sqr(
-	struct fixed31_32 arg)
+struct fixed31_32 dc_fixpt_sqr(struct fixed31_32 arg)
 {
 	struct fixed31_32 res;
 
-	uint64_t arg_value = abs_i64(arg.value);
+	unsigned long long arg_value = abs_i64(arg.value);
 
-	uint64_t arg_int = GET_INTEGER_PART(arg_value);
+	unsigned long long arg_int = GET_INTEGER_PART(arg_value);
 
-	uint64_t arg_fra = GET_FRACTIONAL_PART(arg_value);
+	unsigned long long arg_fra = GET_FRACTIONAL_PART(arg_value);
 
-	uint64_t tmp;
+	unsigned long long tmp;
 
 	res.value = arg_int * arg_int;
 
@@ -246,28 +187,27 @@ struct fixed31_32 dal_fixed31_32_sqr(
 
 	tmp = arg_int * arg_fra;
 
-	ASSERT(tmp <= (uint64_t)(LLONG_MAX - res.value));
+	ASSERT(tmp <= (unsigned long long)(LLONG_MAX - res.value));
 
 	res.value += tmp;
 
-	ASSERT(tmp <= (uint64_t)(LLONG_MAX - res.value));
+	ASSERT(tmp <= (unsigned long long)(LLONG_MAX - res.value));
 
 	res.value += tmp;
 
 	tmp = arg_fra * arg_fra;
 
 	tmp = (tmp >> FIXED31_32_BITS_PER_FRACTIONAL_PART) +
-		(tmp >= (uint64_t)dal_fixed31_32_half.value);
+		(tmp >= (unsigned long long)dc_fixpt_half.value);
 
-	ASSERT(tmp <= (uint64_t)(LLONG_MAX - res.value));
+	ASSERT(tmp <= (unsigned long long)(LLONG_MAX - res.value));
 
 	res.value += tmp;
 
 	return res;
 }
 
-struct fixed31_32 dal_fixed31_32_recip(
-	struct fixed31_32 arg)
+struct fixed31_32 dc_fixpt_recip(struct fixed31_32 arg)
 {
 	/*
 	 * @note
@@ -276,41 +216,40 @@ struct fixed31_32 dal_fixed31_32_recip(
 
 	ASSERT(arg.value);
 
-	return dal_fixed31_32_from_fraction(
-		dal_fixed31_32_one.value,
+	return dc_fixpt_from_fraction(
+		dc_fixpt_one.value,
 		arg.value);
 }
 
-struct fixed31_32 dal_fixed31_32_sinc(
-	struct fixed31_32 arg)
+struct fixed31_32 dc_fixpt_sinc(struct fixed31_32 arg)
 {
 	struct fixed31_32 square;
 
-	struct fixed31_32 res = dal_fixed31_32_one;
+	struct fixed31_32 res = dc_fixpt_one;
 
-	int32_t n = 27;
+	int n = 27;
 
 	struct fixed31_32 arg_norm = arg;
 
-	if (dal_fixed31_32_le(
-		dal_fixed31_32_two_pi,
-		dal_fixed31_32_abs(arg))) {
-		arg_norm = dal_fixed31_32_sub(
+	if (dc_fixpt_le(
+		dc_fixpt_two_pi,
+		dc_fixpt_abs(arg))) {
+		arg_norm = dc_fixpt_sub(
 			arg_norm,
-			dal_fixed31_32_mul_int(
-				dal_fixed31_32_two_pi,
-				(int32_t)div64_s64(
+			dc_fixpt_mul_int(
+				dc_fixpt_two_pi,
+				(int)div64_s64(
 					arg_norm.value,
-					dal_fixed31_32_two_pi.value)));
+					dc_fixpt_two_pi.value)));
 	}
 
-	square = dal_fixed31_32_sqr(arg_norm);
+	square = dc_fixpt_sqr(arg_norm);
 
 	do {
-		res = dal_fixed31_32_sub(
-			dal_fixed31_32_one,
-			dal_fixed31_32_div_int(
-				dal_fixed31_32_mul(
+		res = dc_fixpt_sub(
+			dc_fixpt_one,
+			dc_fixpt_div_int(
+				dc_fixpt_mul(
 					square,
 					res),
 				n * (n - 1)));
@@ -319,37 +258,35 @@ struct fixed31_32 dal_fixed31_32_sinc(
 	} while (n > 2);
 
 	if (arg.value != arg_norm.value)
-		res = dal_fixed31_32_div(
-			dal_fixed31_32_mul(res, arg_norm),
+		res = dc_fixpt_div(
+			dc_fixpt_mul(res, arg_norm),
 			arg);
 
 	return res;
 }
 
-struct fixed31_32 dal_fixed31_32_sin(
-	struct fixed31_32 arg)
+struct fixed31_32 dc_fixpt_sin(struct fixed31_32 arg)
 {
-	return dal_fixed31_32_mul(
+	return dc_fixpt_mul(
 		arg,
-		dal_fixed31_32_sinc(arg));
+		dc_fixpt_sinc(arg));
 }
 
-struct fixed31_32 dal_fixed31_32_cos(
-	struct fixed31_32 arg)
+struct fixed31_32 dc_fixpt_cos(struct fixed31_32 arg)
 {
 	/* TODO implement argument normalization */
 
-	const struct fixed31_32 square = dal_fixed31_32_sqr(arg);
+	const struct fixed31_32 square = dc_fixpt_sqr(arg);
 
-	struct fixed31_32 res = dal_fixed31_32_one;
+	struct fixed31_32 res = dc_fixpt_one;
 
-	int32_t n = 26;
+	int n = 26;
 
 	do {
-		res = dal_fixed31_32_sub(
-			dal_fixed31_32_one,
-			dal_fixed31_32_div_int(
-				dal_fixed31_32_mul(
+		res = dc_fixpt_sub(
+			dc_fixpt_one,
+			dc_fixpt_div_int(
+				dc_fixpt_mul(
 					square,
 					res),
 				n * (n - 1)));
@@ -367,37 +304,35 @@ struct fixed31_32 dal_fixed31_32_cos(
  *
  * Calculated as Taylor series.
  */
-static struct fixed31_32 fixed31_32_exp_from_taylor_series(
-	struct fixed31_32 arg)
+static struct fixed31_32 fixed31_32_exp_from_taylor_series(struct fixed31_32 arg)
 {
-	uint32_t n = 9;
+	unsigned int n = 9;
 
-	struct fixed31_32 res = dal_fixed31_32_from_fraction(
+	struct fixed31_32 res = dc_fixpt_from_fraction(
 		n + 2,
 		n + 1);
 	/* TODO find correct res */
 
-	ASSERT(dal_fixed31_32_lt(arg, dal_fixed31_32_one));
+	ASSERT(dc_fixpt_lt(arg, dc_fixpt_one));
 
 	do
-		res = dal_fixed31_32_add(
-			dal_fixed31_32_one,
-			dal_fixed31_32_div_int(
-				dal_fixed31_32_mul(
+		res = dc_fixpt_add(
+			dc_fixpt_one,
+			dc_fixpt_div_int(
+				dc_fixpt_mul(
 					arg,
 					res),
 				n));
 	while (--n != 1);
 
-	return dal_fixed31_32_add(
-		dal_fixed31_32_one,
-		dal_fixed31_32_mul(
+	return dc_fixpt_add(
+		dc_fixpt_one,
+		dc_fixpt_mul(
 			arg,
 			res));
 }
 
-struct fixed31_32 dal_fixed31_32_exp(
-	struct fixed31_32 arg)
+struct fixed31_32 dc_fixpt_exp(struct fixed31_32 arg)
 {
 	/*
 	 * @brief
@@ -406,44 +341,43 @@ struct fixed31_32 dal_fixed31_32_exp(
 	 * where m = round(x / ln(2)), r = x - m * ln(2)
 	 */
 
-	if (dal_fixed31_32_le(
-		dal_fixed31_32_ln2_div_2,
-		dal_fixed31_32_abs(arg))) {
-		int32_t m = dal_fixed31_32_round(
-			dal_fixed31_32_div(
+	if (dc_fixpt_le(
+		dc_fixpt_ln2_div_2,
+		dc_fixpt_abs(arg))) {
+		int m = dc_fixpt_round(
+			dc_fixpt_div(
 				arg,
-				dal_fixed31_32_ln2));
+				dc_fixpt_ln2));
 
-		struct fixed31_32 r = dal_fixed31_32_sub(
+		struct fixed31_32 r = dc_fixpt_sub(
 			arg,
-			dal_fixed31_32_mul_int(
-				dal_fixed31_32_ln2,
+			dc_fixpt_mul_int(
+				dc_fixpt_ln2,
 				m));
 
 		ASSERT(m != 0);
 
-		ASSERT(dal_fixed31_32_lt(
-			dal_fixed31_32_abs(r),
-			dal_fixed31_32_one));
+		ASSERT(dc_fixpt_lt(
+			dc_fixpt_abs(r),
+			dc_fixpt_one));
 
 		if (m > 0)
-			return dal_fixed31_32_shl(
+			return dc_fixpt_shl(
 				fixed31_32_exp_from_taylor_series(r),
-				(uint8_t)m);
+				(unsigned char)m);
 		else
-			return dal_fixed31_32_div_int(
+			return dc_fixpt_div_int(
 				fixed31_32_exp_from_taylor_series(r),
 				1LL << -m);
 	} else if (arg.value != 0)
 		return fixed31_32_exp_from_taylor_series(arg);
 	else
-		return dal_fixed31_32_one;
+		return dc_fixpt_one;
 }
 
-struct fixed31_32 dal_fixed31_32_log(
-	struct fixed31_32 arg)
+struct fixed31_32 dc_fixpt_log(struct fixed31_32 arg)
 {
-	struct fixed31_32 res = dal_fixed31_32_neg(dal_fixed31_32_one);
+	struct fixed31_32 res = dc_fixpt_neg(dc_fixpt_one);
 	/* TODO improve 1st estimation */
 
 	struct fixed31_32 error;
@@ -453,15 +387,15 @@ struct fixed31_32 dal_fixed31_32_log(
 	/* TODO if arg is zero, return -INF */
 
 	do {
-		struct fixed31_32 res1 = dal_fixed31_32_add(
-			dal_fixed31_32_sub(
+		struct fixed31_32 res1 = dc_fixpt_add(
+			dc_fixpt_sub(
 				res,
-				dal_fixed31_32_one),
-			dal_fixed31_32_div(
+				dc_fixpt_one),
+			dc_fixpt_div(
 				arg,
-				dal_fixed31_32_exp(res)));
+				dc_fixpt_exp(res)));
 
-		error = dal_fixed31_32_sub(
+		error = dc_fixpt_sub(
 			res,
 			res1);
 
@@ -472,78 +406,23 @@ struct fixed31_32 dal_fixed31_32_log(
 	return res;
 }
 
-struct fixed31_32 dal_fixed31_32_pow(
-	struct fixed31_32 arg1,
-	struct fixed31_32 arg2)
-{
-	return dal_fixed31_32_exp(
-		dal_fixed31_32_mul(
-			dal_fixed31_32_log(arg1),
-			arg2));
-}
-
-int32_t dal_fixed31_32_floor(
-	struct fixed31_32 arg)
-{
-	uint64_t arg_value = abs_i64(arg.value);
-
-	if (arg.value >= 0)
-		return (int32_t)GET_INTEGER_PART(arg_value);
-	else
-		return -(int32_t)GET_INTEGER_PART(arg_value);
-}
-
-int32_t dal_fixed31_32_round(
-	struct fixed31_32 arg)
-{
-	uint64_t arg_value = abs_i64(arg.value);
-
-	const int64_t summand = dal_fixed31_32_half.value;
-
-	ASSERT(LLONG_MAX - (int64_t)arg_value >= summand);
-
-	arg_value += summand;
-
-	if (arg.value >= 0)
-		return (int32_t)GET_INTEGER_PART(arg_value);
-	else
-		return -(int32_t)GET_INTEGER_PART(arg_value);
-}
-
-int32_t dal_fixed31_32_ceil(
-	struct fixed31_32 arg)
-{
-	uint64_t arg_value = abs_i64(arg.value);
-
-	const int64_t summand = dal_fixed31_32_one.value -
-		dal_fixed31_32_epsilon.value;
-
-	ASSERT(LLONG_MAX - (int64_t)arg_value >= summand);
-
-	arg_value += summand;
-
-	if (arg.value >= 0)
-		return (int32_t)GET_INTEGER_PART(arg_value);
-	else
-		return -(int32_t)GET_INTEGER_PART(arg_value);
-}
 
 /* this function is a generic helper to translate fixed point value to
  * specified integer format that will consist of integer_bits integer part and
  * fractional_bits fractional part. For example it is used in
- * dal_fixed31_32_u2d19 to receive 2 bits integer part and 19 bits fractional
+ * dc_fixpt_u2d19 to receive 2 bits integer part and 19 bits fractional
  * part in 32 bits. It is used in hw programming (scaler)
  */
 
-static inline uint32_t ux_dy(
-	int64_t value,
-	uint32_t integer_bits,
-	uint32_t fractional_bits)
+static inline unsigned int ux_dy(
+	long long value,
+	unsigned int integer_bits,
+	unsigned int fractional_bits)
 {
 	/* 1. create mask of integer part */
-	uint32_t result = (1 << integer_bits) - 1;
+	unsigned int result = (1 << integer_bits) - 1;
 	/* 2. mask out fractional part */
-	uint32_t fractional_part = FRACTIONAL_PART_MASK & value;
+	unsigned int fractional_part = FRACTIONAL_PART_MASK & value;
 	/* 3. shrink fixed point integer part to be of integer_bits width*/
 	result &= GET_INTEGER_PART(value);
 	/* 4. make space for fractional part to be filled in after integer */
@@ -554,13 +433,13 @@ static inline uint32_t ux_dy(
 	return result | fractional_part;
 }
 
-static inline uint32_t clamp_ux_dy(
-	int64_t value,
-	uint32_t integer_bits,
-	uint32_t fractional_bits,
-	uint32_t min_clamp)
+static inline unsigned int clamp_ux_dy(
+	long long value,
+	unsigned int integer_bits,
+	unsigned int fractional_bits,
+	unsigned int min_clamp)
 {
-	uint32_t truncated_val = ux_dy(value, integer_bits, fractional_bits);
+	unsigned int truncated_val = ux_dy(value, integer_bits, fractional_bits);
 
 	if (value >= (1LL << (integer_bits + FIXED31_32_BITS_PER_FRACTIONAL_PART)))
 		return (1 << (integer_bits + fractional_bits)) - 1;
@@ -570,35 +449,30 @@ static inline uint32_t clamp_ux_dy(
 		return min_clamp;
 }
 
-uint32_t dal_fixed31_32_u2d19(
-	struct fixed31_32 arg)
+unsigned int dc_fixpt_u2d19(struct fixed31_32 arg)
 {
 	return ux_dy(arg.value, 2, 19);
 }
 
-uint32_t dal_fixed31_32_u0d19(
-	struct fixed31_32 arg)
+unsigned int dc_fixpt_u0d19(struct fixed31_32 arg)
 {
 	return ux_dy(arg.value, 0, 19);
 }
 
-uint32_t dal_fixed31_32_clamp_u0d14(
-	struct fixed31_32 arg)
+unsigned int dc_fixpt_clamp_u0d14(struct fixed31_32 arg)
 {
 	return clamp_ux_dy(arg.value, 0, 14, 1);
 }
 
-uint32_t dal_fixed31_32_clamp_u0d10(
-	struct fixed31_32 arg)
+unsigned int dc_fixpt_clamp_u0d10(struct fixed31_32 arg)
 {
 	return clamp_ux_dy(arg.value, 0, 10, 1);
 }
 
-int32_t dal_fixed31_32_s4d19(
-	struct fixed31_32 arg)
+int dc_fixpt_s4d19(struct fixed31_32 arg)
 {
 	if (arg.value < 0)
-		return -(int32_t)ux_dy(dal_fixed31_32_abs(arg).value, 4, 19);
+		return -(int)ux_dy(dc_fixpt_abs(arg).value, 4, 19);
 	else
 		return ux_dy(arg.value, 4, 19);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/basics/fixpt32_32.c b/drivers/gpu/drm/amd/display/dc/basics/fixpt32_32.c
deleted file mode 100644
index 4d3aaa82a07b..000000000000
--- a/drivers/gpu/drm/amd/display/dc/basics/fixpt32_32.c
+++ /dev/null
@@ -1,161 +0,0 @@
-/*
- * Copyright 2012-15 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-
-#include "dm_services.h"
-#include "include/fixed32_32.h"
-
-static uint64_t u64_div(uint64_t n, uint64_t d)
-{
-	uint32_t i = 0;
-	uint64_t r;
-	uint64_t q = div64_u64_rem(n, d, &r);
-
-	for (i = 0; i < 32; ++i) {
-		uint64_t sbit = q & (1ULL<<63);
-
-		r <<= 1;
-		r |= sbit ? 1 : 0;
-		q <<= 1;
-		if (r >= d) {
-			r -= d;
-			q |= 1;
-		}
-	}
-
-	if (2*r >= d)
-		q += 1;
-	return q;
-}
-
-struct fixed32_32 dal_fixed32_32_from_fraction(uint32_t n, uint32_t d)
-{
-	struct fixed32_32 fx;
-
-	fx.value = u64_div((uint64_t)n << 32, (uint64_t)d << 32);
-	return fx;
-}
-
-struct fixed32_32 dal_fixed32_32_add(
-	struct fixed32_32 lhs,
-	struct fixed32_32 rhs)
-{
-	struct fixed32_32 fx = {lhs.value + rhs.value};
-
-	ASSERT(fx.value >= rhs.value);
-	return fx;
-}
-
-struct fixed32_32 dal_fixed32_32_add_int(struct fixed32_32 lhs, uint32_t rhs)
-{
-	struct fixed32_32 fx = {lhs.value + ((uint64_t)rhs << 32)};
-
-	ASSERT(fx.value >= (uint64_t)rhs << 32);
-	return fx;
-
-}
-struct fixed32_32 dal_fixed32_32_sub(
-	struct fixed32_32 lhs,
-	struct fixed32_32 rhs)
-{
-	struct fixed32_32 fx;
-
-	ASSERT(lhs.value >= rhs.value);
-	fx.value = lhs.value - rhs.value;
-	return fx;
-}
-
-struct fixed32_32 dal_fixed32_32_sub_int(struct fixed32_32 lhs, uint32_t rhs)
-{
-	struct fixed32_32 fx;
-
-	ASSERT(lhs.value >= ((uint64_t)rhs<<32));
-	fx.value = lhs.value - ((uint64_t)rhs<<32);
-	return fx;
-}
-
-struct fixed32_32 dal_fixed32_32_mul(
-	struct fixed32_32 lhs,
-	struct fixed32_32 rhs)
-{
-	struct fixed32_32 fx;
-	uint64_t lhs_int = lhs.value>>32;
-	uint64_t lhs_frac = (uint32_t)lhs.value;
-	uint64_t rhs_int = rhs.value>>32;
-	uint64_t rhs_frac = (uint32_t)rhs.value;
-	uint64_t ahbh = lhs_int * rhs_int;
-	uint64_t ahbl = lhs_int * rhs_frac;
-	uint64_t albh = lhs_frac * rhs_int;
-	uint64_t albl = lhs_frac * rhs_frac;
-
-	ASSERT((ahbh>>32) == 0);
-
-	fx.value = (ahbh<<32) + ahbl + albh + (albl>>32);
-	return fx;
-
-}
-
-struct fixed32_32 dal_fixed32_32_mul_int(struct fixed32_32 lhs, uint32_t rhs)
-{
-	struct fixed32_32 fx;
-	uint64_t lhsi = (lhs.value>>32) * (uint64_t)rhs;
-	uint64_t lhsf;
-
-	ASSERT((lhsi>>32) == 0);
-	lhsf = ((uint32_t)lhs.value) * (uint64_t)rhs;
-	ASSERT((lhsi<<32) + lhsf >= lhsf);
-	fx.value = (lhsi<<32) + lhsf;
-	return fx;
-}
-
-struct fixed32_32 dal_fixed32_32_div(
-	struct fixed32_32 lhs,
-	struct fixed32_32 rhs)
-{
-	struct fixed32_32 fx;
-
-	fx.value = u64_div(lhs.value, rhs.value);
-	return fx;
-}
-
-struct fixed32_32 dal_fixed32_32_div_int(struct fixed32_32 lhs, uint32_t rhs)
-{
-	struct fixed32_32 fx;
-
-	fx.value = u64_div(lhs.value, (uint64_t)rhs << 32);
-	return fx;
-}
-
-uint32_t dal_fixed32_32_ceil(struct fixed32_32 v)
-{
-	ASSERT((uint32_t)v.value ? (v.value >> 32) + 1 >= 1 : true);
-	return (v.value>>32) + ((uint32_t)v.value ? 1 : 0);
-}
-
-uint32_t dal_fixed32_32_round(struct fixed32_32 v)
-{
-	ASSERT(v.value + (1ULL<<31) >= (1ULL<<31));
-	return (v.value + (1ULL<<31))>>32;
-}
-
diff --git a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
index 854678a0c54b..021451549ff7 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
@@ -94,7 +94,6 @@ void dc_conn_log(struct dc_context *ctx,
 			dm_logger_append(&entry, "%2.2X ", hex_data[i]);
 
 	dm_logger_append(&entry, "^\n");
-	dm_helpers_dc_conn_log(ctx, &entry, event);
 
 fail:
 	dm_logger_close(&entry);
diff --git a/drivers/gpu/drm/amd/display/dc/basics/logger.c b/drivers/gpu/drm/amd/display/dc/basics/logger.c
index 31bee054f43a..738a818d58d1 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/logger.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/logger.c
@@ -61,7 +61,7 @@ static const struct dc_log_type_info log_type_info_tbl[] = {
 		{LOG_EVENT_UNDERFLOW,       "Underflow"},
 		{LOG_IF_TRACE,              "InterfaceTrace"},
 		{LOG_DTN,                   "DTN"},
-		{LOG_PROFILING,             "Profiling"}
+		{LOG_DISPLAYSTATS,          "DisplayStats"}
 };
 
 
@@ -402,3 +402,4 @@ cleanup:
 		entry->max_buf_bytes = 0;
 	}
 }
+
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 985fe8c22875..b8cef7af3c4a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -70,6 +70,10 @@ static enum bp_result get_firmware_info_v3_1(
 	struct bios_parser *bp,
 	struct dc_firmware_info *info);
 
+static enum bp_result get_firmware_info_v3_2(
+	struct bios_parser *bp,
+	struct dc_firmware_info *info);
+
 static struct atom_hpd_int_record *get_hpd_record(struct bios_parser *bp,
 		struct atom_display_object_path_v2 *object);
 
@@ -1321,9 +1325,14 @@ static enum bp_result bios_parser_get_firmware_info(
 		case 3:
 			switch (revision.minor) {
 			case 1:
-			case 2:
 				result = get_firmware_info_v3_1(bp, info);
 				break;
+			case 2:
+				result = get_firmware_info_v3_2(bp, info);
+				break;
+			case 3:
+				result = get_firmware_info_v3_2(bp, info);
+				break;
 			default:
 				break;
 			}
@@ -1383,6 +1392,84 @@ static enum bp_result get_firmware_info_v3_1(
 	return BP_RESULT_OK;
 }
 
+static enum bp_result get_firmware_info_v3_2(
+	struct bios_parser *bp,
+	struct dc_firmware_info *info)
+{
+	struct atom_firmware_info_v3_2 *firmware_info;
+	struct atom_display_controller_info_v4_1 *dce_info = NULL;
+	struct atom_common_table_header *header;
+	struct atom_data_revision revision;
+	struct atom_smu_info_v3_2 *smu_info_v3_2 = NULL;
+	struct atom_smu_info_v3_3 *smu_info_v3_3 = NULL;
+
+	if (!info)
+		return BP_RESULT_BADINPUT;
+
+	firmware_info = GET_IMAGE(struct atom_firmware_info_v3_2,
+			DATA_TABLES(firmwareinfo));
+
+	dce_info = GET_IMAGE(struct atom_display_controller_info_v4_1,
+			DATA_TABLES(dce_info));
+
+	if (!firmware_info || !dce_info)
+		return BP_RESULT_BADBIOSTABLE;
+
+	memset(info, 0, sizeof(*info));
+
+	header = GET_IMAGE(struct atom_common_table_header,
+					DATA_TABLES(smu_info));
+	get_atom_data_table_revision(header, &revision);
+
+	if (revision.minor == 2) {
+		/* Vega12 */
+		smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2,
+							DATA_TABLES(smu_info));
+
+		if (!smu_info_v3_2)
+			return BP_RESULT_BADBIOSTABLE;
+
+		info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10;
+	} else if (revision.minor == 3) {
+		/* Vega20 */
+		smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3,
+							DATA_TABLES(smu_info));
+
+		if (!smu_info_v3_3)
+			return BP_RESULT_BADBIOSTABLE;
+
+		info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10;
+	}
+
+	 // We need to convert from 10KHz units into KHz units.
+	info->default_memory_clk = firmware_info->bootup_mclk_in10khz * 10;
+
+	 /* 27MHz for Vega10 & Vega12; 100MHz for Vega20 */
+	info->pll_info.crystal_frequency = dce_info->dce_refclk_10khz * 10;
+	/* Hardcode frequency if BIOS gives no DCE Ref Clk */
+	if (info->pll_info.crystal_frequency == 0) {
+		if (revision.minor == 2)
+			info->pll_info.crystal_frequency = 27000;
+		else if (revision.minor == 3)
+			info->pll_info.crystal_frequency = 100000;
+	}
+	/*dp_phy_ref_clk is not correct for atom_display_controller_info_v4_2, but we don't use it*/
+	info->dp_phy_ref_clk     = dce_info->dpphy_refclk_10khz * 10;
+	info->i2c_engine_ref_clk = dce_info->i2c_engine_refclk_10khz * 10;
+
+	/* Get GPU PLL VCO Clock */
+	if (bp->cmd_tbl.get_smu_clock_info != NULL) {
+		if (revision.minor == 2)
+			info->smu_gpu_pll_output_freq =
+					bp->cmd_tbl.get_smu_clock_info(bp, SMU9_SYSPLL0_ID) * 10;
+		else if (revision.minor == 3)
+			info->smu_gpu_pll_output_freq =
+					bp->cmd_tbl.get_smu_clock_info(bp, SMU11_SYSPLL3_0_ID) * 10;
+	}
+
+	return BP_RESULT_OK;
+}
+
 static enum bp_result bios_parser_get_encoder_cap_info(
 	struct dc_bios *dcb,
 	struct graphics_object_id object_id,
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 4b5fdd577848..651e1fd4622f 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -24,7 +24,7 @@
  */
 
 #include "dm_services.h"
-
+#include "amdgpu.h"
 #include "atom.h"
 
 #include "include/bios_parser_interface.h"
@@ -35,16 +35,16 @@
 #include "bios_parser_types_internal.h"
 
 #define EXEC_BIOS_CMD_TABLE(command, params)\
-	(cgs_atom_exec_cmd_table(bp->base.ctx->cgs_device, \
+	(amdgpu_atom_execute_table(((struct amdgpu_device *)bp->base.ctx->driver_context)->mode_info.atom_context, \
 		GetIndexIntoMasterTable(COMMAND, command), \
-		&params) == 0)
+		(uint32_t *)&params) == 0)
 
 #define BIOS_CMD_TABLE_REVISION(command, frev, crev)\
-	cgs_atom_get_cmd_table_revs(bp->base.ctx->cgs_device, \
+	amdgpu_atom_parse_cmd_header(((struct amdgpu_device *)bp->base.ctx->driver_context)->mode_info.atom_context, \
 		GetIndexIntoMasterTable(COMMAND, command), &frev, &crev)
 
 #define BIOS_CMD_TABLE_PARA_REVISION(command)\
-	bios_cmd_table_para_revision(bp->base.ctx->cgs_device, \
+	bios_cmd_table_para_revision(bp->base.ctx->driver_context, \
 		GetIndexIntoMasterTable(COMMAND, command))
 
 static void init_dig_encoder_control(struct bios_parser *bp);
@@ -82,16 +82,18 @@ void dal_bios_parser_init_cmd_tbl(struct bios_parser *bp)
 	init_set_dce_clock(bp);
 }
 
-static uint32_t bios_cmd_table_para_revision(void *cgs_device,
+static uint32_t bios_cmd_table_para_revision(void *dev,
 					     uint32_t index)
 {
+	struct amdgpu_device *adev = dev;
 	uint8_t frev, crev;
 
-	if (cgs_atom_get_cmd_table_revs(cgs_device,
+	if (amdgpu_atom_parse_cmd_header(adev->mode_info.atom_context,
 					index,
-					&frev, &crev) != 0)
+					&frev, &crev))
+		return crev;
+	else
 		return 0;
-	return crev;
 }
 
 /*******************************************************************************
@@ -368,7 +370,7 @@ static void init_transmitter_control(struct bios_parser *bp)
 	uint8_t crev;
 
 	if (BIOS_CMD_TABLE_REVISION(UNIPHYTransmitterControl,
-			frev, crev) != 0)
+			frev, crev) == false)
 		BREAK_TO_DEBUGGER();
 	switch (crev) {
 	case 2:
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index 3f63f712c8a4..752b08a42d3e 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -26,14 +26,18 @@
 #include "dm_services.h"
 
 #include "ObjectID.h"
-#include "atomfirmware.h"
 
+#include "atomfirmware.h"
+#include "atom.h"
 #include "include/bios_parser_interface.h"
 
 #include "command_table2.h"
 #include "command_table_helper2.h"
 #include "bios_parser_helper.h"
 #include "bios_parser_types_internal2.h"
+#include "amdgpu.h"
+
+
 #define DC_LOGGER \
 	bp->base.ctx->logger
 
@@ -43,16 +47,16 @@
 		->FieldName)-(char *)0)/sizeof(uint16_t))
 
 #define EXEC_BIOS_CMD_TABLE(fname, params)\
-	(cgs_atom_exec_cmd_table(bp->base.ctx->cgs_device, \
+	(amdgpu_atom_execute_table(((struct amdgpu_device *)bp->base.ctx->driver_context)->mode_info.atom_context, \
 		GET_INDEX_INTO_MASTER_TABLE(command, fname), \
-		&params) == 0)
+		(uint32_t *)&params) == 0)
 
 #define BIOS_CMD_TABLE_REVISION(fname, frev, crev)\
-	cgs_atom_get_cmd_table_revs(bp->base.ctx->cgs_device, \
+	amdgpu_atom_parse_cmd_header(((struct amdgpu_device *)bp->base.ctx->driver_context)->mode_info.atom_context, \
 		GET_INDEX_INTO_MASTER_TABLE(command, fname), &frev, &crev)
 
 #define BIOS_CMD_TABLE_PARA_REVISION(fname)\
-	bios_cmd_table_para_revision(bp->base.ctx->cgs_device, \
+	bios_cmd_table_para_revision(bp->base.ctx->driver_context, \
 			GET_INDEX_INTO_MASTER_TABLE(command, fname))
 
 static void init_dig_encoder_control(struct bios_parser *bp);
@@ -86,16 +90,18 @@ void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
 	init_get_smu_clock_info(bp);
 }
 
-static uint32_t bios_cmd_table_para_revision(void *cgs_device,
+static uint32_t bios_cmd_table_para_revision(void *dev,
 					     uint32_t index)
 {
+	struct amdgpu_device *adev = dev;
 	uint8_t frev, crev;
 
-	if (cgs_atom_get_cmd_table_revs(cgs_device,
+	if (amdgpu_atom_parse_cmd_header(adev->mode_info.atom_context,
 					index,
-					&frev, &crev) != 0)
+					&frev, &crev))
+		return crev;
+	else
 		return 0;
-	return crev;
 }
 
 /******************************************************************************
@@ -201,7 +207,7 @@ static void init_transmitter_control(struct bios_parser *bp)
 	uint8_t frev;
 	uint8_t crev;
 
-	if (BIOS_CMD_TABLE_REVISION(dig1transmittercontrol, frev, crev) != 0)
+	if (BIOS_CMD_TABLE_REVISION(dig1transmittercontrol, frev, crev) == false)
 		BREAK_TO_DEBUGGER();
 	switch (crev) {
 	case 6:
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c
index 2979358c6a55..253bbb1eea60 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c
@@ -51,6 +51,7 @@ bool dal_bios_parser_init_cmd_tbl_helper(
 		return true;
 
 	case DCE_VERSION_11_2:
+	case DCE_VERSION_11_22:
 		*h = dal_cmd_tbl_helper_dce112_get_table();
 		return true;
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
index 9a4d30dd4969..bbbcef566c55 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
@@ -52,6 +52,7 @@ bool dal_bios_parser_init_cmd_tbl_helper2(
 		return true;
 
 	case DCE_VERSION_11_2:
+	case DCE_VERSION_11_22:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h b/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
new file mode 100644
index 000000000000..fc3f98fb09ea
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
@@ -0,0 +1,579 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _CALCS_CALCS_LOGGER_H_
+#define _CALCS_CALCS_LOGGER_H_
+#define DC_LOGGER \
+	logger
+
+static void print_bw_calcs_dceip(struct dal_logger *logger, const struct bw_calcs_dceip *dceip)
+{
+
+	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
+	DC_LOG_BANDWIDTH_CALCS("struct bw_calcs_dceip");
+	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
+	DC_LOG_BANDWIDTH_CALCS("	[enum]   bw_calcs_version version %d", dceip->version);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] large_cursor: %d", dceip->large_cursor);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] dmif_pipe_en_fbc_chunk_tracker: %d", dceip->dmif_pipe_en_fbc_chunk_tracker);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] display_write_back_supported: %d", dceip->display_write_back_supported);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] argb_compression_support: %d", dceip->argb_compression_support);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] pre_downscaler_enabled: %d", dceip->pre_downscaler_enabled);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] underlay_downscale_prefetch_enabled: %d",
+				dceip->underlay_downscale_prefetch_enabled);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] graphics_lb_nodownscaling_multi_line_prefetching: %d",
+				dceip->graphics_lb_nodownscaling_multi_line_prefetching);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] limit_excessive_outstanding_dmif_requests: %d",
+				dceip->limit_excessive_outstanding_dmif_requests);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] cursor_max_outstanding_group_num: %d",
+				dceip->cursor_max_outstanding_group_num);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] lines_interleaved_into_lb: %d", dceip->lines_interleaved_into_lb);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] low_power_tiling_mode: %d", dceip->low_power_tiling_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] chunk_width: %d", dceip->chunk_width);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_graphics_pipes: %d", dceip->number_of_graphics_pipes);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_underlay_pipes: %d", dceip->number_of_underlay_pipes);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] max_dmif_buffer_allocated: %d", dceip->max_dmif_buffer_allocated);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] graphics_dmif_size: %d", dceip->graphics_dmif_size);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] underlay_luma_dmif_size: %d", dceip->underlay_luma_dmif_size);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] underlay_chroma_dmif_size: %d", dceip->underlay_chroma_dmif_size);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] scatter_gather_lines_of_pte_prefetching_in_linear_mode: %d",
+				dceip->scatter_gather_lines_of_pte_prefetching_in_linear_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] display_write_back420_luma_mcifwr_buffer_size: %d",
+				dceip->display_write_back420_luma_mcifwr_buffer_size);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] display_write_back420_chroma_mcifwr_buffer_size: %d",
+				dceip->display_write_back420_chroma_mcifwr_buffer_size);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] scatter_gather_pte_request_rows_in_tiling_mode: %d",
+				dceip->scatter_gather_pte_request_rows_in_tiling_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] underlay_vscaler_efficiency10_bit_per_component: %d",
+				bw_fixed_to_int(dceip->underlay_vscaler_efficiency10_bit_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] underlay_vscaler_efficiency12_bit_per_component: %d",
+				bw_fixed_to_int(dceip->underlay_vscaler_efficiency12_bit_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] graphics_vscaler_efficiency6_bit_per_component: %d",
+				bw_fixed_to_int(dceip->graphics_vscaler_efficiency6_bit_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] graphics_vscaler_efficiency8_bit_per_component: %d",
+				bw_fixed_to_int(dceip->graphics_vscaler_efficiency8_bit_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] graphics_vscaler_efficiency10_bit_per_component: %d",
+				bw_fixed_to_int(dceip->graphics_vscaler_efficiency10_bit_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] graphics_vscaler_efficiency12_bit_per_component: %d",
+				bw_fixed_to_int(dceip->graphics_vscaler_efficiency12_bit_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] alpha_vscaler_efficiency: %d",
+				bw_fixed_to_int(dceip->alpha_vscaler_efficiency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lb_write_pixels_per_dispclk: %d",
+				bw_fixed_to_int(dceip->lb_write_pixels_per_dispclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lb_size_per_component444: %d",
+				bw_fixed_to_int(dceip->lb_size_per_component444));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_and_dram_clock_state_change_gated_before_cursor: %d",
+				bw_fixed_to_int(dceip->stutter_and_dram_clock_state_change_gated_before_cursor));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] underlay420_luma_lb_size_per_component: %d",
+				bw_fixed_to_int(dceip->underlay420_luma_lb_size_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] underlay420_chroma_lb_size_per_component: %d",
+				bw_fixed_to_int(dceip->underlay420_chroma_lb_size_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] underlay422_lb_size_per_component: %d",
+				bw_fixed_to_int(dceip->underlay422_lb_size_per_component));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] cursor_chunk_width: %d", bw_fixed_to_int(dceip->cursor_chunk_width));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] cursor_dcp_buffer_lines: %d",
+				bw_fixed_to_int(dceip->cursor_dcp_buffer_lines));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] underlay_maximum_width_efficient_for_tiling: %d",
+				bw_fixed_to_int(dceip->underlay_maximum_width_efficient_for_tiling));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] underlay_maximum_height_efficient_for_tiling: %d",
+				bw_fixed_to_int(dceip->underlay_maximum_height_efficient_for_tiling));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display: %d",
+				bw_fixed_to_int(dceip->peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation: %d",
+				bw_fixed_to_int(dceip->peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] minimum_outstanding_pte_request_limit: %d",
+				bw_fixed_to_int(dceip->minimum_outstanding_pte_request_limit));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] maximum_total_outstanding_pte_requests_allowed_by_saw: %d",
+				bw_fixed_to_int(dceip->maximum_total_outstanding_pte_requests_allowed_by_saw));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] linear_mode_line_request_alternation_slice: %d",
+				bw_fixed_to_int(dceip->linear_mode_line_request_alternation_slice));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] request_efficiency: %d", bw_fixed_to_int(dceip->request_efficiency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk_per_request: %d", bw_fixed_to_int(dceip->dispclk_per_request));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk_ramping_factor: %d",
+				bw_fixed_to_int(dceip->dispclk_ramping_factor));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] display_pipe_throughput_factor: %d",
+				bw_fixed_to_int(dceip->display_pipe_throughput_factor));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mcifwr_all_surfaces_burst_time: %d",
+				bw_fixed_to_int(dceip->mcifwr_all_surfaces_burst_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmif_request_buffer_size: %d",
+				bw_fixed_to_int(dceip->dmif_request_buffer_size));
+
+
+}
+
+static void print_bw_calcs_vbios(struct dal_logger *logger, const struct bw_calcs_vbios *vbios)
+{
+
+	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
+	DC_LOG_BANDWIDTH_CALCS("struct bw_calcs_vbios vbios");
+	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines memory_type: %d", vbios->memory_type);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines memory_type: %d", vbios->memory_type);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] dram_channel_width_in_bits: %d", vbios->dram_channel_width_in_bits);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_dram_channels: %d", vbios->number_of_dram_channels);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_dram_banks: %d", vbios->number_of_dram_banks);
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] low_yclk: %d", bw_fixed_to_int(vbios->low_yclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid_yclk: %d", bw_fixed_to_int(vbios->mid_yclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] high_yclk: %d", bw_fixed_to_int(vbios->high_yclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] low_sclk: %d", bw_fixed_to_int(vbios->low_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid1_sclk: %d", bw_fixed_to_int(vbios->mid1_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid2_sclk: %d", bw_fixed_to_int(vbios->mid2_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid3_sclk: %d", bw_fixed_to_int(vbios->mid3_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid4_sclk: %d", bw_fixed_to_int(vbios->mid4_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid5_sclk: %d", bw_fixed_to_int(vbios->mid5_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid6_sclk: %d", bw_fixed_to_int(vbios->mid6_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] high_sclk: %d", bw_fixed_to_int(vbios->high_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] low_voltage_max_dispclk: %d",
+				bw_fixed_to_int(vbios->low_voltage_max_dispclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid_voltage_max_dispclk;: %d",
+				bw_fixed_to_int(vbios->mid_voltage_max_dispclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] high_voltage_max_dispclk;: %d",
+				bw_fixed_to_int(vbios->high_voltage_max_dispclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] low_voltage_max_phyclk: %d",
+				bw_fixed_to_int(vbios->low_voltage_max_phyclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mid_voltage_max_phyclk: %d",
+				bw_fixed_to_int(vbios->mid_voltage_max_phyclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] high_voltage_max_phyclk: %d",
+				bw_fixed_to_int(vbios->high_voltage_max_phyclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] data_return_bus_width: %d", bw_fixed_to_int(vbios->data_return_bus_width));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] trc: %d", bw_fixed_to_int(vbios->trc));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmifmc_urgent_latency: %d", bw_fixed_to_int(vbios->dmifmc_urgent_latency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_self_refresh_exit_latency: %d",
+				bw_fixed_to_int(vbios->stutter_self_refresh_exit_latency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_self_refresh_entry_latency: %d",
+				bw_fixed_to_int(vbios->stutter_self_refresh_entry_latency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] nbp_state_change_latency: %d",
+				bw_fixed_to_int(vbios->nbp_state_change_latency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mcifwrmc_urgent_latency: %d",
+				bw_fixed_to_int(vbios->mcifwrmc_urgent_latency));
+	DC_LOG_BANDWIDTH_CALCS("	[bool] scatter_gather_enable: %d", vbios->scatter_gather_enable);
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] down_spread_percentage: %d",
+				bw_fixed_to_int(vbios->down_spread_percentage));
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] cursor_width: %d", vbios->cursor_width);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] average_compression_rate: %d", vbios->average_compression_rate);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_request_slots_gmc_reserves_for_dmif_per_channel: %d",
+				vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel);
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] blackout_duration: %d", bw_fixed_to_int(vbios->blackout_duration));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] maximum_blackout_recovery_time: %d",
+				bw_fixed_to_int(vbios->maximum_blackout_recovery_time));
+
+
+}
+
+static void print_bw_calcs_data(struct dal_logger *logger, struct bw_calcs_data *data)
+{
+
+	int i, j, k;
+
+	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
+	DC_LOG_BANDWIDTH_CALCS("struct bw_calcs_data data");
+	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_displays: %d", data->number_of_displays);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines underlay_surface_type: %d", data->underlay_surface_type);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines panning_and_bezel_adjustment: %d",
+				data->panning_and_bezel_adjustment);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines graphics_tiling_mode: %d", data->graphics_tiling_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] graphics_lb_bpc: %d", data->graphics_lb_bpc);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] underlay_lb_bpc: %d", data->underlay_lb_bpc);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines underlay_tiling_mode: %d", data->underlay_tiling_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines d0_underlay_mode: %d", data->d0_underlay_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] d1_display_write_back_dwb_enable: %d", data->d1_display_write_back_dwb_enable);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines d1_underlay_mode: %d", data->d1_underlay_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] cpup_state_change_enable: %d", data->cpup_state_change_enable);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] cpuc_state_change_enable: %d", data->cpuc_state_change_enable);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] nbp_state_change_enable: %d", data->nbp_state_change_enable);
+	DC_LOG_BANDWIDTH_CALCS("	[bool] stutter_mode_enable: %d", data->stutter_mode_enable);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] y_clk_level: %d", data->y_clk_level);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] sclk_level: %d", data->sclk_level);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_underlay_surfaces: %d", data->number_of_underlay_surfaces);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_dram_wrchannels: %d", data->number_of_dram_wrchannels);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] chunk_request_delay: %d", data->chunk_request_delay);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] number_of_dram_channels: %d", data->number_of_dram_channels);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines underlay_micro_tile_mode: %d", data->underlay_micro_tile_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines graphics_micro_tile_mode: %d", data->graphics_micro_tile_mode);
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] max_phyclk: %d", bw_fixed_to_int(data->max_phyclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dram_efficiency: %d", bw_fixed_to_int(data->dram_efficiency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_width_after_surface_type: %d",
+				bw_fixed_to_int(data->src_width_after_surface_type));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_height_after_surface_type: %d",
+				bw_fixed_to_int(data->src_height_after_surface_type));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] hsr_after_surface_type: %d",
+				bw_fixed_to_int(data->hsr_after_surface_type));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] vsr_after_surface_type: %d", bw_fixed_to_int(data->vsr_after_surface_type));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_width_after_rotation: %d",
+				bw_fixed_to_int(data->src_width_after_rotation));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_height_after_rotation: %d",
+				bw_fixed_to_int(data->src_height_after_rotation));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] hsr_after_rotation: %d", bw_fixed_to_int(data->hsr_after_rotation));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] vsr_after_rotation: %d", bw_fixed_to_int(data->vsr_after_rotation));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] source_height_pixels: %d", bw_fixed_to_int(data->source_height_pixels));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] hsr_after_stereo: %d", bw_fixed_to_int(data->hsr_after_stereo));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] vsr_after_stereo: %d", bw_fixed_to_int(data->vsr_after_stereo));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] source_width_in_lb: %d", bw_fixed_to_int(data->source_width_in_lb));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lb_line_pitch: %d", bw_fixed_to_int(data->lb_line_pitch));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] underlay_maximum_source_efficient_for_tiling: %d",
+				bw_fixed_to_int(data->underlay_maximum_source_efficient_for_tiling));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] num_lines_at_frame_start: %d",
+				bw_fixed_to_int(data->num_lines_at_frame_start));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] min_dmif_size_in_time: %d", bw_fixed_to_int(data->min_dmif_size_in_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] min_mcifwr_size_in_time: %d",
+				bw_fixed_to_int(data->min_mcifwr_size_in_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_requests_for_dmif_size: %d",
+				bw_fixed_to_int(data->total_requests_for_dmif_size));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] peak_pte_request_to_eviction_ratio_limiting: %d",
+				bw_fixed_to_int(data->peak_pte_request_to_eviction_ratio_limiting));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] useful_pte_per_pte_request: %d",
+				bw_fixed_to_int(data->useful_pte_per_pte_request));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_pte_request_rows: %d",
+				bw_fixed_to_int(data->scatter_gather_pte_request_rows));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_row_height: %d",
+				bw_fixed_to_int(data->scatter_gather_row_height));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_pte_requests_in_vblank: %d",
+				bw_fixed_to_int(data->scatter_gather_pte_requests_in_vblank));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] inefficient_linear_pitch_in_bytes: %d",
+				bw_fixed_to_int(data->inefficient_linear_pitch_in_bytes));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] cursor_total_data: %d", bw_fixed_to_int(data->cursor_total_data));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] cursor_total_request_groups: %d",
+				bw_fixed_to_int(data->cursor_total_request_groups));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_total_pte_requests: %d",
+				bw_fixed_to_int(data->scatter_gather_total_pte_requests));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_total_pte_request_groups: %d",
+				bw_fixed_to_int(data->scatter_gather_total_pte_request_groups));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] tile_width_in_pixels: %d", bw_fixed_to_int(data->tile_width_in_pixels));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmif_total_number_of_data_request_page_close_open: %d",
+				bw_fixed_to_int(data->dmif_total_number_of_data_request_page_close_open));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mcifwr_total_number_of_data_request_page_close_open: %d",
+				bw_fixed_to_int(data->mcifwr_total_number_of_data_request_page_close_open));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] bytes_per_page_close_open: %d",
+				bw_fixed_to_int(data->bytes_per_page_close_open));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mcifwr_total_page_close_open_time: %d",
+				bw_fixed_to_int(data->mcifwr_total_page_close_open_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_requests_for_adjusted_dmif_size: %d",
+				bw_fixed_to_int(data->total_requests_for_adjusted_dmif_size));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_dmifmc_urgent_trips: %d",
+				bw_fixed_to_int(data->total_dmifmc_urgent_trips));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_dmifmc_urgent_latency: %d",
+				bw_fixed_to_int(data->total_dmifmc_urgent_latency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_display_reads_required_data: %d",
+				bw_fixed_to_int(data->total_display_reads_required_data));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_display_reads_required_dram_access_data: %d",
+				bw_fixed_to_int(data->total_display_reads_required_dram_access_data));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_display_writes_required_data: %d",
+				bw_fixed_to_int(data->total_display_writes_required_data));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_display_writes_required_dram_access_data: %d",
+				bw_fixed_to_int(data->total_display_writes_required_dram_access_data));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] display_reads_required_data: %d",
+				bw_fixed_to_int(data->display_reads_required_data));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] display_reads_required_dram_access_data: %d",
+				bw_fixed_to_int(data->display_reads_required_dram_access_data));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmif_total_page_close_open_time: %d",
+				bw_fixed_to_int(data->dmif_total_page_close_open_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] min_cursor_memory_interface_buffer_size_in_time: %d",
+				bw_fixed_to_int(data->min_cursor_memory_interface_buffer_size_in_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] min_read_buffer_size_in_time: %d",
+				bw_fixed_to_int(data->min_read_buffer_size_in_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] display_reads_time_for_data_transfer: %d",
+				bw_fixed_to_int(data->display_reads_time_for_data_transfer));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] display_writes_time_for_data_transfer: %d",
+				bw_fixed_to_int(data->display_writes_time_for_data_transfer));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmif_required_dram_bandwidth: %d",
+				bw_fixed_to_int(data->dmif_required_dram_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mcifwr_required_dram_bandwidth: %d",
+				bw_fixed_to_int(data->mcifwr_required_dram_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] required_dmifmc_urgent_latency_for_page_close_open: %d",
+				bw_fixed_to_int(data->required_dmifmc_urgent_latency_for_page_close_open));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] required_mcifmcwr_urgent_latency: %d",
+				bw_fixed_to_int(data->required_mcifmcwr_urgent_latency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] required_dram_bandwidth_gbyte_per_second: %d",
+				bw_fixed_to_int(data->required_dram_bandwidth_gbyte_per_second));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dram_bandwidth: %d", bw_fixed_to_int(data->dram_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmif_required_sclk: %d", bw_fixed_to_int(data->dmif_required_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mcifwr_required_sclk: %d", bw_fixed_to_int(data->mcifwr_required_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] required_sclk: %d", bw_fixed_to_int(data->required_sclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] downspread_factor: %d", bw_fixed_to_int(data->downspread_factor));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] v_scaler_efficiency: %d", bw_fixed_to_int(data->v_scaler_efficiency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scaler_limits_factor: %d", bw_fixed_to_int(data->scaler_limits_factor));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] display_pipe_pixel_throughput: %d",
+				bw_fixed_to_int(data->display_pipe_pixel_throughput));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_dispclk_required_with_ramping: %d",
+				bw_fixed_to_int(data->total_dispclk_required_with_ramping));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_dispclk_required_without_ramping: %d",
+				bw_fixed_to_int(data->total_dispclk_required_without_ramping));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_read_request_bandwidth: %d",
+				bw_fixed_to_int(data->total_read_request_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_write_request_bandwidth: %d",
+				bw_fixed_to_int(data->total_write_request_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk_required_for_total_read_request_bandwidth: %d",
+				bw_fixed_to_int(data->dispclk_required_for_total_read_request_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_dispclk_required_with_ramping_with_request_bandwidth: %d",
+				bw_fixed_to_int(data->total_dispclk_required_with_ramping_with_request_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_dispclk_required_without_ramping_with_request_bandwidth: %d",
+				bw_fixed_to_int(data->total_dispclk_required_without_ramping_with_request_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk: %d", bw_fixed_to_int(data->dispclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] blackout_recovery_time: %d", bw_fixed_to_int(data->blackout_recovery_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] min_pixels_per_data_fifo_entry: %d",
+				bw_fixed_to_int(data->min_pixels_per_data_fifo_entry));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] sclk_deep_sleep: %d", bw_fixed_to_int(data->sclk_deep_sleep));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] chunk_request_time: %d", bw_fixed_to_int(data->chunk_request_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] cursor_request_time: %d", bw_fixed_to_int(data->cursor_request_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] line_source_pixels_transfer_time: %d",
+				bw_fixed_to_int(data->line_source_pixels_transfer_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmifdram_access_efficiency: %d",
+				bw_fixed_to_int(data->dmifdram_access_efficiency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mcifwrdram_access_efficiency: %d",
+				bw_fixed_to_int(data->mcifwrdram_access_efficiency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_average_bandwidth_no_compression: %d",
+				bw_fixed_to_int(data->total_average_bandwidth_no_compression));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_average_bandwidth: %d",
+				bw_fixed_to_int(data->total_average_bandwidth));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] total_stutter_cycle_duration: %d",
+				bw_fixed_to_int(data->total_stutter_cycle_duration));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_burst_time: %d", bw_fixed_to_int(data->stutter_burst_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] time_in_self_refresh: %d", bw_fixed_to_int(data->time_in_self_refresh));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_efficiency: %d", bw_fixed_to_int(data->stutter_efficiency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] worst_number_of_trips_to_memory: %d",
+				bw_fixed_to_int(data->worst_number_of_trips_to_memory));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] immediate_flip_time: %d", bw_fixed_to_int(data->immediate_flip_time));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] latency_for_non_dmif_clients: %d",
+				bw_fixed_to_int(data->latency_for_non_dmif_clients));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] latency_for_non_mcifwr_clients: %d",
+				bw_fixed_to_int(data->latency_for_non_mcifwr_clients));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmifmc_urgent_latency_supported_in_high_sclk_and_yclk: %d",
+				bw_fixed_to_int(data->dmifmc_urgent_latency_supported_in_high_sclk_and_yclk));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] nbp_state_dram_speed_change_margin: %d",
+				bw_fixed_to_int(data->nbp_state_dram_speed_change_margin));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] display_reads_time_for_data_transfer_and_urgent_latency: %d",
+				bw_fixed_to_int(data->display_reads_time_for_data_transfer_and_urgent_latency));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dram_speed_change_margin: %d",
+				bw_fixed_to_int(data->dram_speed_change_margin));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] min_vblank_dram_speed_change_margin: %d",
+				bw_fixed_to_int(data->min_vblank_dram_speed_change_margin));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] min_stutter_refresh_duration: %d",
+				bw_fixed_to_int(data->min_stutter_refresh_duration));
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] total_stutter_dmif_buffer_size: %d", data->total_stutter_dmif_buffer_size);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] total_bytes_requested: %d", data->total_bytes_requested);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] min_stutter_dmif_buffer_size: %d", data->min_stutter_dmif_buffer_size);
+	DC_LOG_BANDWIDTH_CALCS("	[uint32_t] num_stutter_bursts: %d", data->num_stutter_bursts);
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] v_blank_nbp_state_dram_speed_change_latency_supported: %d",
+				bw_fixed_to_int(data->v_blank_nbp_state_dram_speed_change_latency_supported));
+	DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] nbp_state_dram_speed_change_latency_supported: %d",
+				bw_fixed_to_int(data->nbp_state_dram_speed_change_latency_supported));
+
+	for (i = 0; i < maximum_number_of_surfaces; i++) {
+		DC_LOG_BANDWIDTH_CALCS("	[bool] fbc_en[%d]:%d\n", i, data->fbc_en[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] lpt_en[%d]:%d", i, data->lpt_en[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] displays_match_flag[%d]:%d", i, data->displays_match_flag[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] use_alpha[%d]:%d", i, data->use_alpha[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] orthogonal_rotation[%d]:%d", i, data->orthogonal_rotation[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] enable[%d]:%d", i, data->enable[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] access_one_channel_only[%d]:%d", i, data->access_one_channel_only[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] scatter_gather_enable_for_pipe[%d]:%d",
+					i, data->scatter_gather_enable_for_pipe[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] interlace_mode[%d]:%d",
+					i, data->interlace_mode[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] display_pstate_change_enable[%d]:%d",
+					i, data->display_pstate_change_enable[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bool] line_buffer_prefetch[%d]:%d", i, data->line_buffer_prefetch[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[uint32_t] bytes_per_pixel[%d]:%d", i, data->bytes_per_pixel[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[uint32_t] max_chunks_non_fbc_mode[%d]:%d",
+					i, data->max_chunks_non_fbc_mode[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[uint32_t] lb_bpc[%d]:%d", i, data->lb_bpc[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[uint32_t] output_bpphdmi[%d]:%d", i, data->output_bpphdmi[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[uint32_t] output_bppdp4_lane_hbr[%d]:%d", i, data->output_bppdp4_lane_hbr[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[uint32_t] output_bppdp4_lane_hbr2[%d]:%d",
+					i, data->output_bppdp4_lane_hbr2[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[uint32_t] output_bppdp4_lane_hbr3[%d]:%d",
+					i, data->output_bppdp4_lane_hbr3[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[enum] bw_defines stereo_mode[%d]:%d", i, data->stereo_mode[i]);
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmif_buffer_transfer_time[%d]:%d",
+					i, bw_fixed_to_int(data->dmif_buffer_transfer_time[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] displays_with_same_mode[%d]:%d",
+					i, bw_fixed_to_int(data->displays_with_same_mode[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_dmif_buffer_size[%d]:%d",
+					i, bw_fixed_to_int(data->stutter_dmif_buffer_size[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_refresh_duration[%d]:%d",
+					i, bw_fixed_to_int(data->stutter_refresh_duration[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_exit_watermark[%d]:%d",
+					i, bw_fixed_to_int(data->stutter_exit_watermark[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_entry_watermark[%d]:%d",
+					i, bw_fixed_to_int(data->stutter_entry_watermark[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] h_total[%d]:%d", i, bw_fixed_to_int(data->h_total[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] v_total[%d]:%d", i, bw_fixed_to_int(data->v_total[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] pixel_rate[%d]:%d", i, bw_fixed_to_int(data->pixel_rate[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_width[%d]:%d", i, bw_fixed_to_int(data->src_width[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] pitch_in_pixels[%d]:%d",
+					i, bw_fixed_to_int(data->pitch_in_pixels[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] pitch_in_pixels_after_surface_type[%d]:%d",
+					i, bw_fixed_to_int(data->pitch_in_pixels_after_surface_type[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_height[%d]:%d", i, bw_fixed_to_int(data->src_height[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scale_ratio[%d]:%d", i, bw_fixed_to_int(data->scale_ratio[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] h_taps[%d]:%d", i, bw_fixed_to_int(data->h_taps[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] v_taps[%d]:%d", i, bw_fixed_to_int(data->v_taps[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] h_scale_ratio[%d]:%d", i, bw_fixed_to_int(data->h_scale_ratio[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] v_scale_ratio[%d]:%d", i, bw_fixed_to_int(data->v_scale_ratio[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] rotation_angle[%d]:%d",
+					i, bw_fixed_to_int(data->rotation_angle[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] compression_rate[%d]:%d",
+					i, bw_fixed_to_int(data->compression_rate[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] hsr[%d]:%d", i, bw_fixed_to_int(data->hsr[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] vsr[%d]:%d", i, bw_fixed_to_int(data->vsr[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] source_width_rounded_up_to_chunks[%d]:%d",
+					i, bw_fixed_to_int(data->source_width_rounded_up_to_chunks[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] source_width_pixels[%d]:%d",
+					i, bw_fixed_to_int(data->source_width_pixels[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] source_height_rounded_up_to_chunks[%d]:%d",
+					i, bw_fixed_to_int(data->source_height_rounded_up_to_chunks[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] display_bandwidth[%d]:%d",
+					i, bw_fixed_to_int(data->display_bandwidth[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] request_bandwidth[%d]:%d",
+					i, bw_fixed_to_int(data->request_bandwidth[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] bytes_per_request[%d]:%d",
+					i, bw_fixed_to_int(data->bytes_per_request[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] useful_bytes_per_request[%d]:%d",
+					i, bw_fixed_to_int(data->useful_bytes_per_request[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lines_interleaved_in_mem_access[%d]:%d",
+					i, bw_fixed_to_int(data->lines_interleaved_in_mem_access[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] latency_hiding_lines[%d]:%d",
+					i, bw_fixed_to_int(data->latency_hiding_lines[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lb_partitions[%d]:%d",
+					i, bw_fixed_to_int(data->lb_partitions[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lb_partitions_max[%d]:%d",
+					i, bw_fixed_to_int(data->lb_partitions_max[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk_required_with_ramping[%d]:%d",
+					i, bw_fixed_to_int(data->dispclk_required_with_ramping[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk_required_without_ramping[%d]:%d",
+					i, bw_fixed_to_int(data->dispclk_required_without_ramping[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] data_buffer_size[%d]:%d",
+					i, bw_fixed_to_int(data->data_buffer_size[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] outstanding_chunk_request_limit[%d]:%d",
+					i, bw_fixed_to_int(data->outstanding_chunk_request_limit[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] urgent_watermark[%d]:%d",
+					i, bw_fixed_to_int(data->urgent_watermark[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] nbp_state_change_watermark[%d]:%d",
+					i, bw_fixed_to_int(data->nbp_state_change_watermark[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] v_filter_init[%d]:%d", i, bw_fixed_to_int(data->v_filter_init[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] stutter_cycle_duration[%d]:%d",
+					i, bw_fixed_to_int(data->stutter_cycle_duration[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] average_bandwidth[%d]:%d",
+					i, bw_fixed_to_int(data->average_bandwidth[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] average_bandwidth_no_compression[%d]:%d",
+					i, bw_fixed_to_int(data->average_bandwidth_no_compression[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_pte_request_limit[%d]:%d",
+					i, bw_fixed_to_int(data->scatter_gather_pte_request_limit[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lb_size_per_component[%d]:%d",
+					i, bw_fixed_to_int(data->lb_size_per_component[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] memory_chunk_size_in_bytes[%d]:%d",
+					i, bw_fixed_to_int(data->memory_chunk_size_in_bytes[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] pipe_chunk_size_in_bytes[%d]:%d",
+					i, bw_fixed_to_int(data->pipe_chunk_size_in_bytes[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] number_of_trips_to_memory_for_getting_apte_row[%d]:%d",
+					i, bw_fixed_to_int(data->number_of_trips_to_memory_for_getting_apte_row[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] adjusted_data_buffer_size[%d]:%d",
+					i, bw_fixed_to_int(data->adjusted_data_buffer_size[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] adjusted_data_buffer_size_in_memory[%d]:%d",
+					i, bw_fixed_to_int(data->adjusted_data_buffer_size_in_memory[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] pixels_per_data_fifo_entry[%d]:%d",
+					i, bw_fixed_to_int(data->pixels_per_data_fifo_entry[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_pte_requests_in_row[%d]:%d",
+					i, bw_fixed_to_int(data->scatter_gather_pte_requests_in_row[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] pte_request_per_chunk[%d]:%d",
+					i, bw_fixed_to_int(data->pte_request_per_chunk[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_page_width[%d]:%d",
+					i, bw_fixed_to_int(data->scatter_gather_page_width[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] scatter_gather_page_height[%d]:%d",
+					i, bw_fixed_to_int(data->scatter_gather_page_height[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lb_lines_in_per_line_out_in_beginning_of_frame[%d]:%d",
+					i, bw_fixed_to_int(data->lb_lines_in_per_line_out_in_beginning_of_frame[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] lb_lines_in_per_line_out_in_middle_of_frame[%d]:%d",
+					i, bw_fixed_to_int(data->lb_lines_in_per_line_out_in_middle_of_frame[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] cursor_width_pixels[%d]:%d",
+					i, bw_fixed_to_int(data->cursor_width_pixels[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] minimum_latency_hiding[%d]:%d",
+					i, bw_fixed_to_int(data->minimum_latency_hiding[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] maximum_latency_hiding[%d]:%d",
+					i, bw_fixed_to_int(data->maximum_latency_hiding[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] minimum_latency_hiding_with_cursor[%d]:%d",
+					i, bw_fixed_to_int(data->minimum_latency_hiding_with_cursor[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] maximum_latency_hiding_with_cursor[%d]:%d",
+					i, bw_fixed_to_int(data->maximum_latency_hiding_with_cursor[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_pixels_for_first_output_pixel[%d]:%d",
+					i, bw_fixed_to_int(data->src_pixels_for_first_output_pixel[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_pixels_for_last_output_pixel[%d]:%d",
+					i, bw_fixed_to_int(data->src_pixels_for_last_output_pixel[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_data_for_first_output_pixel[%d]:%d",
+					i, bw_fixed_to_int(data->src_data_for_first_output_pixel[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] src_data_for_last_output_pixel[%d]:%d",
+					i, bw_fixed_to_int(data->src_data_for_last_output_pixel[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] active_time[%d]:%d", i, bw_fixed_to_int(data->active_time[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] horizontal_blank_and_chunk_granularity_factor[%d]:%d",
+					i, bw_fixed_to_int(data->horizontal_blank_and_chunk_granularity_factor[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] cursor_latency_hiding[%d]:%d",
+					i, bw_fixed_to_int(data->cursor_latency_hiding[i]));
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] v_blank_dram_speed_change_margin[%d]:%d",
+					i, bw_fixed_to_int(data->v_blank_dram_speed_change_margin[i]));
+		}
+
+	for (i = 0; i < maximum_number_of_surfaces; i++) {
+		for (j = 0; j < 3; j++) {
+			for (k = 0; k < 8; k++) {
+
+				DC_LOG_BANDWIDTH_CALCS("\n	[bw_fixed] line_source_transfer_time[%d][%d][%d]:%d",
+					i, j, k, bw_fixed_to_int(data->line_source_transfer_time[i][j][k]));
+				DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dram_speed_change_line_source_transfer_time[%d][%d][%d]:%d",
+					i, j, k,
+					bw_fixed_to_int(data->dram_speed_change_line_source_transfer_time[i][j][k]));
+			}
+		}
+	}
+
+	for (i = 0; i < 3; i++) {
+		for (j = 0; j < 8; j++) {
+
+			DC_LOG_BANDWIDTH_CALCS("\n	[uint32_t] num_displays_with_margin[%d][%d]:%d",
+					i, j, data->num_displays_with_margin[i][j]);
+			DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmif_burst_time[%d][%d]:%d",
+					i, j, bw_fixed_to_int(data->dmif_burst_time[i][j]));
+			DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] mcifwr_burst_time[%d][%d]:%d",
+					i, j, bw_fixed_to_int(data->mcifwr_burst_time[i][j]));
+			DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] min_dram_speed_change_margin[%d][%d]:%d",
+					i, j, bw_fixed_to_int(data->min_dram_speed_change_margin[i][j]));
+			DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk_required_for_dram_speed_change[%d][%d]:%d",
+					i, j, bw_fixed_to_int(data->dispclk_required_for_dram_speed_change[i][j]));
+			DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] blackout_duration_margin[%d][%d]:%d",
+					i, j, bw_fixed_to_int(data->blackout_duration_margin[i][j]));
+			DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk_required_for_blackout_duration[%d][%d]:%d",
+					i, j, bw_fixed_to_int(data->dispclk_required_for_blackout_duration[i][j]));
+			DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dispclk_required_for_blackout_recovery[%d][%d]:%d",
+					i, j, bw_fixed_to_int(data->dispclk_required_for_blackout_recovery[i][j]));
+		}
+	}
+
+	for (i = 0; i < 6; i++) {
+		DC_LOG_BANDWIDTH_CALCS("	[bw_fixed] dmif_required_sclk_for_urgent_latency[%d]:%d",
+					i, bw_fixed_to_int(data->dmif_required_sclk_for_urgent_latency[i]));
+	}
+}
+;
+
+#endif /* _CALCS_CALCS_LOGGER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/custom_float.c b/drivers/gpu/drm/amd/display/dc/calcs/custom_float.c
index 7243c37f569e..31d167bc548f 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/custom_float.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/custom_float.c
@@ -36,41 +36,41 @@ static bool build_custom_float(
 	uint32_t exp_offset = (1 << (format->exponenta_bits - 1)) - 1;
 
 	const struct fixed31_32 mantissa_constant_plus_max_fraction =
-		dal_fixed31_32_from_fraction(
+		dc_fixpt_from_fraction(
 			(1LL << (format->mantissa_bits + 1)) - 1,
 			1LL << format->mantissa_bits);
 
 	struct fixed31_32 mantiss;
 
-	if (dal_fixed31_32_eq(
+	if (dc_fixpt_eq(
 		value,
-		dal_fixed31_32_zero)) {
+		dc_fixpt_zero)) {
 		*negative = false;
 		*mantissa = 0;
 		*exponenta = 0;
 		return true;
 	}
 
-	if (dal_fixed31_32_lt(
+	if (dc_fixpt_lt(
 		value,
-		dal_fixed31_32_zero)) {
+		dc_fixpt_zero)) {
 		*negative = format->sign;
-		value = dal_fixed31_32_neg(value);
+		value = dc_fixpt_neg(value);
 	} else {
 		*negative = false;
 	}
 
-	if (dal_fixed31_32_lt(
+	if (dc_fixpt_lt(
 		value,
-		dal_fixed31_32_one)) {
+		dc_fixpt_one)) {
 		uint32_t i = 1;
 
 		do {
-			value = dal_fixed31_32_shl(value, 1);
+			value = dc_fixpt_shl(value, 1);
 			++i;
-		} while (dal_fixed31_32_lt(
+		} while (dc_fixpt_lt(
 			value,
-			dal_fixed31_32_one));
+			dc_fixpt_one));
 
 		--i;
 
@@ -81,15 +81,15 @@ static bool build_custom_float(
 		}
 
 		*exponenta = exp_offset - i;
-	} else if (dal_fixed31_32_le(
+	} else if (dc_fixpt_le(
 		mantissa_constant_plus_max_fraction,
 		value)) {
 		uint32_t i = 1;
 
 		do {
-			value = dal_fixed31_32_shr(value, 1);
+			value = dc_fixpt_shr(value, 1);
 			++i;
-		} while (dal_fixed31_32_lt(
+		} while (dc_fixpt_lt(
 			mantissa_constant_plus_max_fraction,
 			value));
 
@@ -98,23 +98,23 @@ static bool build_custom_float(
 		*exponenta = exp_offset;
 	}
 
-	mantiss = dal_fixed31_32_sub(
+	mantiss = dc_fixpt_sub(
 		value,
-		dal_fixed31_32_one);
+		dc_fixpt_one);
 
-	if (dal_fixed31_32_lt(
+	if (dc_fixpt_lt(
 			mantiss,
-			dal_fixed31_32_zero) ||
-		dal_fixed31_32_lt(
-			dal_fixed31_32_one,
+			dc_fixpt_zero) ||
+		dc_fixpt_lt(
+			dc_fixpt_one,
 			mantiss))
-		mantiss = dal_fixed31_32_zero;
+		mantiss = dc_fixpt_zero;
 	else
-		mantiss = dal_fixed31_32_shl(
+		mantiss = dc_fixpt_shl(
 			mantiss,
 			format->mantissa_bits);
 
-	*mantissa = dal_fixed31_32_floor(mantiss);
+	*mantissa = dc_fixpt_floor(mantiss);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
index 0cbab81ab304..2c4e8f0cb2dc 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
@@ -28,6 +28,7 @@
 #include "dc.h"
 #include "core_types.h"
 #include "dal_asic_id.h"
+#include "calcs_logger.h"
 
 /*
  * NOTE:
@@ -52,11 +53,14 @@ static enum bw_calcs_version bw_calcs_version_from_asic_id(struct hw_asic_id asi
 		return BW_CALCS_VERSION_CARRIZO;
 
 	case FAMILY_VI:
+		if (ASIC_REV_IS_POLARIS12_V(asic_id.hw_internal_rev))
+			return BW_CALCS_VERSION_POLARIS12;
 		if (ASIC_REV_IS_POLARIS10_P(asic_id.hw_internal_rev))
 			return BW_CALCS_VERSION_POLARIS10;
-		if (ASIC_REV_IS_POLARIS11_M(asic_id.hw_internal_rev) ||
-				ASIC_REV_IS_POLARIS12_V(asic_id.hw_internal_rev))
+		if (ASIC_REV_IS_POLARIS11_M(asic_id.hw_internal_rev))
 			return BW_CALCS_VERSION_POLARIS11;
+		if (ASIC_REV_IS_VEGAM(asic_id.hw_internal_rev))
+			return BW_CALCS_VERSION_VEGAM;
 		return BW_CALCS_VERSION_INVALID;
 
 	case FAMILY_AI:
@@ -2145,6 +2149,9 @@ void bw_calcs_init(struct bw_calcs_dceip *bw_dceip,
 		dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); /* todo: this is a bug*/
 		break;
 	case BW_CALCS_VERSION_POLARIS10:
+		/* TODO: Treat VEGAM the same as P10 for now
+		 * Need to tune the para for VEGAM if needed */
+	case BW_CALCS_VERSION_VEGAM:
 		vbios.memory_type = bw_def_gddr5;
 		vbios.dram_channel_width_in_bits = 32;
 		vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits;
@@ -2373,6 +2380,122 @@ void bw_calcs_init(struct bw_calcs_dceip *bw_dceip,
 		dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2;
 		dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0);
 		break;
+	case BW_CALCS_VERSION_POLARIS12:
+		vbios.memory_type = bw_def_gddr5;
+		vbios.dram_channel_width_in_bits = 32;
+		vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits;
+		vbios.number_of_dram_banks = 8;
+		vbios.high_yclk = bw_int_to_fixed(6000);
+		vbios.mid_yclk = bw_int_to_fixed(3200);
+		vbios.low_yclk = bw_int_to_fixed(1000);
+		vbios.low_sclk = bw_int_to_fixed(678);
+		vbios.mid1_sclk = bw_int_to_fixed(864);
+		vbios.mid2_sclk = bw_int_to_fixed(900);
+		vbios.mid3_sclk = bw_int_to_fixed(920);
+		vbios.mid4_sclk = bw_int_to_fixed(940);
+		vbios.mid5_sclk = bw_int_to_fixed(960);
+		vbios.mid6_sclk = bw_int_to_fixed(980);
+		vbios.high_sclk = bw_int_to_fixed(1049);
+		vbios.low_voltage_max_dispclk = bw_int_to_fixed(459);
+		vbios.mid_voltage_max_dispclk = bw_int_to_fixed(654);
+		vbios.high_voltage_max_dispclk = bw_int_to_fixed(1108);
+		vbios.low_voltage_max_phyclk = bw_int_to_fixed(540);
+		vbios.mid_voltage_max_phyclk = bw_int_to_fixed(810);
+		vbios.high_voltage_max_phyclk = bw_int_to_fixed(810);
+		vbios.data_return_bus_width = bw_int_to_fixed(32);
+		vbios.trc = bw_int_to_fixed(48);
+		if (vbios.number_of_dram_channels == 2) // 64-bit
+			vbios.dmifmc_urgent_latency = bw_int_to_fixed(4);
+		else
+			vbios.dmifmc_urgent_latency = bw_int_to_fixed(3);
+		vbios.stutter_self_refresh_exit_latency = bw_int_to_fixed(5);
+		vbios.stutter_self_refresh_entry_latency = bw_int_to_fixed(0);
+		vbios.nbp_state_change_latency = bw_int_to_fixed(250);
+		vbios.mcifwrmc_urgent_latency = bw_int_to_fixed(10);
+		vbios.scatter_gather_enable = false;
+		vbios.down_spread_percentage = bw_frc_to_fixed(5, 10);
+		vbios.cursor_width = 32;
+		vbios.average_compression_rate = 4;
+		vbios.number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256;
+		vbios.blackout_duration = bw_int_to_fixed(0); /* us */
+		vbios.maximum_blackout_recovery_time = bw_int_to_fixed(0);
+
+		dceip.max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100;
+		dceip.max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100;
+		dceip.percent_of_ideal_port_bw_received_after_urgent_latency = 100;
+		dceip.large_cursor = false;
+		dceip.dmif_request_buffer_size = bw_int_to_fixed(768);
+		dceip.dmif_pipe_en_fbc_chunk_tracker = false;
+		dceip.cursor_max_outstanding_group_num = 1;
+		dceip.lines_interleaved_into_lb = 2;
+		dceip.chunk_width = 256;
+		dceip.number_of_graphics_pipes = 5;
+		dceip.number_of_underlay_pipes = 0;
+		dceip.low_power_tiling_mode = 0;
+		dceip.display_write_back_supported = true;
+		dceip.argb_compression_support = true;
+		dceip.underlay_vscaler_efficiency6_bit_per_component =
+			bw_frc_to_fixed(35556, 10000);
+		dceip.underlay_vscaler_efficiency8_bit_per_component =
+			bw_frc_to_fixed(34286, 10000);
+		dceip.underlay_vscaler_efficiency10_bit_per_component =
+			bw_frc_to_fixed(32, 10);
+		dceip.underlay_vscaler_efficiency12_bit_per_component =
+			bw_int_to_fixed(3);
+		dceip.graphics_vscaler_efficiency6_bit_per_component =
+			bw_frc_to_fixed(35, 10);
+		dceip.graphics_vscaler_efficiency8_bit_per_component =
+			bw_frc_to_fixed(34286, 10000);
+		dceip.graphics_vscaler_efficiency10_bit_per_component =
+			bw_frc_to_fixed(32, 10);
+		dceip.graphics_vscaler_efficiency12_bit_per_component =
+			bw_int_to_fixed(3);
+		dceip.alpha_vscaler_efficiency = bw_int_to_fixed(3);
+		dceip.max_dmif_buffer_allocated = 4;
+		dceip.graphics_dmif_size = 12288;
+		dceip.underlay_luma_dmif_size = 19456;
+		dceip.underlay_chroma_dmif_size = 23552;
+		dceip.pre_downscaler_enabled = true;
+		dceip.underlay_downscale_prefetch_enabled = true;
+		dceip.lb_write_pixels_per_dispclk = bw_int_to_fixed(1);
+		dceip.lb_size_per_component444 = bw_int_to_fixed(245952);
+		dceip.graphics_lb_nodownscaling_multi_line_prefetching = true;
+		dceip.stutter_and_dram_clock_state_change_gated_before_cursor =
+			bw_int_to_fixed(1);
+		dceip.underlay420_luma_lb_size_per_component = bw_int_to_fixed(
+			82176);
+		dceip.underlay420_chroma_lb_size_per_component =
+			bw_int_to_fixed(164352);
+		dceip.underlay422_lb_size_per_component = bw_int_to_fixed(
+			82176);
+		dceip.cursor_chunk_width = bw_int_to_fixed(64);
+		dceip.cursor_dcp_buffer_lines = bw_int_to_fixed(4);
+		dceip.underlay_maximum_width_efficient_for_tiling =
+			bw_int_to_fixed(1920);
+		dceip.underlay_maximum_height_efficient_for_tiling =
+			bw_int_to_fixed(1080);
+		dceip.peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display =
+			bw_frc_to_fixed(3, 10);
+		dceip.peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation =
+			bw_int_to_fixed(25);
+		dceip.minimum_outstanding_pte_request_limit = bw_int_to_fixed(
+			2);
+		dceip.maximum_total_outstanding_pte_requests_allowed_by_saw =
+			bw_int_to_fixed(128);
+		dceip.limit_excessive_outstanding_dmif_requests = true;
+		dceip.linear_mode_line_request_alternation_slice =
+			bw_int_to_fixed(64);
+		dceip.scatter_gather_lines_of_pte_prefetching_in_linear_mode =
+			32;
+		dceip.display_write_back420_luma_mcifwr_buffer_size = 12288;
+		dceip.display_write_back420_chroma_mcifwr_buffer_size = 8192;
+		dceip.request_efficiency = bw_frc_to_fixed(8, 10);
+		dceip.dispclk_per_request = bw_int_to_fixed(2);
+		dceip.dispclk_ramping_factor = bw_frc_to_fixed(105, 100);
+		dceip.display_pipe_throughput_factor = bw_frc_to_fixed(105, 100);
+		dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2;
+		dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0);
+		break;
 	case BW_CALCS_VERSION_STONEY:
 		vbios.memory_type = bw_def_gddr5;
 		vbios.dram_channel_width_in_bits = 64;
@@ -2815,6 +2938,19 @@ static void populate_initial_data(
 				data->bytes_per_pixel[num_displays + 4] = 4;
 				break;
 			}
+		} else if (pipe[i].stream->dst.width != 0 &&
+					pipe[i].stream->dst.height != 0 &&
+					pipe[i].stream->src.width != 0 &&
+					pipe[i].stream->src.height != 0) {
+			data->src_width[num_displays + 4] = bw_int_to_fixed(pipe[i].stream->src.width);
+			data->pitch_in_pixels[num_displays + 4] = data->src_width[num_displays + 4];
+			data->src_height[num_displays + 4] = bw_int_to_fixed(pipe[i].stream->src.height);
+			data->h_taps[num_displays + 4] = pipe[i].stream->src.width == pipe[i].stream->dst.width ? bw_int_to_fixed(1) : bw_int_to_fixed(2);
+			data->v_taps[num_displays + 4] = pipe[i].stream->src.height == pipe[i].stream->dst.height ? bw_int_to_fixed(1) : bw_int_to_fixed(2);
+			data->h_scale_ratio[num_displays + 4] = bw_frc_to_fixed(pipe[i].stream->src.width, pipe[i].stream->dst.width);
+			data->v_scale_ratio[num_displays + 4] = bw_frc_to_fixed(pipe[i].stream->src.height, pipe[i].stream->dst.height);
+			data->rotation_angle[num_displays + 4] = bw_int_to_fixed(0);
+			data->bytes_per_pixel[num_displays + 4] = 4;
 		} else {
 			data->src_width[num_displays + 4] = bw_int_to_fixed(pipe[i].stream->timing.h_addressable);
 			data->pitch_in_pixels[num_displays + 4] = data->src_width[num_displays + 4];
@@ -2873,6 +3009,11 @@ bool bw_calcs(struct dc_context *ctx,
 		struct bw_fixed mid_yclk = vbios->mid_yclk;
 		struct bw_fixed low_yclk = vbios->low_yclk;
 
+		if (ctx->dc->debug.bandwidth_calcs_trace) {
+			print_bw_calcs_dceip(ctx->logger, dceip);
+			print_bw_calcs_vbios(ctx->logger, vbios);
+			print_bw_calcs_data(ctx->logger, data);
+		}
 		calculate_bandwidth(dceip, vbios, data);
 
 		yclk_lvl = data->y_clk_level;
@@ -2968,7 +3109,33 @@ bool bw_calcs(struct dc_context *ctx,
 			bw_fixed_to_int(bw_mul(data->
 				stutter_exit_watermark[9], bw_int_to_fixed(1000)));
 
-
+		calcs_output->stutter_entry_wm_ns[0].a_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[4], bw_int_to_fixed(1000)));
+		calcs_output->stutter_entry_wm_ns[1].a_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[5], bw_int_to_fixed(1000)));
+		calcs_output->stutter_entry_wm_ns[2].a_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[6], bw_int_to_fixed(1000)));
+		if (ctx->dc->caps.max_slave_planes) {
+			calcs_output->stutter_entry_wm_ns[3].a_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[0], bw_int_to_fixed(1000)));
+			calcs_output->stutter_entry_wm_ns[4].a_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[1], bw_int_to_fixed(1000)));
+		} else {
+			calcs_output->stutter_entry_wm_ns[3].a_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[7], bw_int_to_fixed(1000)));
+			calcs_output->stutter_entry_wm_ns[4].a_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[8], bw_int_to_fixed(1000)));
+		}
+		calcs_output->stutter_entry_wm_ns[5].a_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[9], bw_int_to_fixed(1000)));
 
 		calcs_output->urgent_wm_ns[0].a_mark =
 			bw_fixed_to_int(bw_mul(data->
@@ -3063,7 +3230,33 @@ bool bw_calcs(struct dc_context *ctx,
 				bw_fixed_to_int(bw_mul(data->
 					stutter_exit_watermark[9], bw_int_to_fixed(1000)));
 
-
+		calcs_output->stutter_entry_wm_ns[0].b_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[4], bw_int_to_fixed(1000)));
+		calcs_output->stutter_entry_wm_ns[1].b_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[5], bw_int_to_fixed(1000)));
+		calcs_output->stutter_entry_wm_ns[2].b_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[6], bw_int_to_fixed(1000)));
+		if (ctx->dc->caps.max_slave_planes) {
+			calcs_output->stutter_entry_wm_ns[3].b_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[0], bw_int_to_fixed(1000)));
+			calcs_output->stutter_entry_wm_ns[4].b_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[1], bw_int_to_fixed(1000)));
+		} else {
+			calcs_output->stutter_entry_wm_ns[3].b_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[7], bw_int_to_fixed(1000)));
+			calcs_output->stutter_entry_wm_ns[4].b_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[8], bw_int_to_fixed(1000)));
+		}
+		calcs_output->stutter_entry_wm_ns[5].b_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[9], bw_int_to_fixed(1000)));
 
 			calcs_output->urgent_wm_ns[0].b_mark =
 				bw_fixed_to_int(bw_mul(data->
@@ -3156,6 +3349,34 @@ bool bw_calcs(struct dc_context *ctx,
 				bw_fixed_to_int(bw_mul(data->
 					stutter_exit_watermark[9], bw_int_to_fixed(1000)));
 
+		calcs_output->stutter_entry_wm_ns[0].c_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[4], bw_int_to_fixed(1000)));
+		calcs_output->stutter_entry_wm_ns[1].c_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[5], bw_int_to_fixed(1000)));
+		calcs_output->stutter_entry_wm_ns[2].c_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[6], bw_int_to_fixed(1000)));
+		if (ctx->dc->caps.max_slave_planes) {
+			calcs_output->stutter_entry_wm_ns[3].c_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[0], bw_int_to_fixed(1000)));
+			calcs_output->stutter_entry_wm_ns[4].c_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[1], bw_int_to_fixed(1000)));
+		} else {
+			calcs_output->stutter_entry_wm_ns[3].c_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[7], bw_int_to_fixed(1000)));
+			calcs_output->stutter_entry_wm_ns[4].c_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[8], bw_int_to_fixed(1000)));
+		}
+		calcs_output->stutter_entry_wm_ns[5].c_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[9], bw_int_to_fixed(1000)));
+
 			calcs_output->urgent_wm_ns[0].c_mark =
 				bw_fixed_to_int(bw_mul(data->
 					urgent_watermark[4], bw_int_to_fixed(1000)));
@@ -3260,6 +3481,33 @@ bool bw_calcs(struct dc_context *ctx,
 			bw_fixed_to_int(bw_mul(data->
 				stutter_exit_watermark[9], bw_int_to_fixed(1000)));
 
+		calcs_output->stutter_entry_wm_ns[0].d_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[4], bw_int_to_fixed(1000)));
+		calcs_output->stutter_entry_wm_ns[1].d_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[5], bw_int_to_fixed(1000)));
+		calcs_output->stutter_entry_wm_ns[2].d_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[6], bw_int_to_fixed(1000)));
+		if (ctx->dc->caps.max_slave_planes) {
+			calcs_output->stutter_entry_wm_ns[3].d_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[0], bw_int_to_fixed(1000)));
+			calcs_output->stutter_entry_wm_ns[4].d_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[1], bw_int_to_fixed(1000)));
+		} else {
+			calcs_output->stutter_entry_wm_ns[3].d_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[7], bw_int_to_fixed(1000)));
+			calcs_output->stutter_entry_wm_ns[4].d_mark =
+				bw_fixed_to_int(bw_mul(data->
+					stutter_entry_watermark[8], bw_int_to_fixed(1000)));
+		}
+		calcs_output->stutter_entry_wm_ns[5].d_mark =
+			bw_fixed_to_int(bw_mul(data->
+				stutter_entry_watermark[9], bw_int_to_fixed(1000)));
 
 		calcs_output->urgent_wm_ns[0].d_mark =
 			bw_fixed_to_int(bw_mul(data->
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 4bb43a371292..49a4ea45466d 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -873,14 +873,14 @@ bool dcn_validate_bandwidth(
 			}
 
 			if (pipe->plane_state->rotation % 2 == 0) {
-				ASSERT(pipe->plane_res.scl_data.ratios.horz.value != dal_fixed31_32_one.value
+				ASSERT(pipe->plane_res.scl_data.ratios.horz.value != dc_fixpt_one.value
 					|| v->scaler_rec_out_width[input_idx] == v->viewport_width[input_idx]);
-				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dal_fixed31_32_one.value
+				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dc_fixpt_one.value
 					|| v->scaler_recout_height[input_idx] == v->viewport_height[input_idx]);
 			} else {
-				ASSERT(pipe->plane_res.scl_data.ratios.horz.value != dal_fixed31_32_one.value
+				ASSERT(pipe->plane_res.scl_data.ratios.horz.value != dc_fixpt_one.value
 					|| v->scaler_recout_height[input_idx] == v->viewport_width[input_idx]);
-				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dal_fixed31_32_one.value
+				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dc_fixpt_one.value
 					|| v->scaler_rec_out_width[input_idx] == v->viewport_height[input_idx]);
 			}
 			v->dcc_enable[input_idx] = pipe->plane_state->dcc.enable ? dcn_bw_yes : dcn_bw_no;
@@ -1459,39 +1459,39 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 void dcn_bw_sync_calcs_and_dml(struct dc *dc)
 {
 	kernel_fpu_begin();
-	DC_LOG_BANDWIDTH_CALCS("sr_exit_time: %d ns\n"
-			"sr_enter_plus_exit_time: %d ns\n"
-			"urgent_latency: %d ns\n"
-			"write_back_latency: %d ns\n"
-			"percent_of_ideal_drambw_received_after_urg_latency: %d %\n"
+	DC_LOG_BANDWIDTH_CALCS("sr_exit_time: %f ns\n"
+			"sr_enter_plus_exit_time: %f ns\n"
+			"urgent_latency: %f ns\n"
+			"write_back_latency: %f ns\n"
+			"percent_of_ideal_drambw_received_after_urg_latency: %f %%\n"
 			"max_request_size: %d bytes\n"
-			"dcfclkv_max0p9: %d kHz\n"
-			"dcfclkv_nom0p8: %d kHz\n"
-			"dcfclkv_mid0p72: %d kHz\n"
-			"dcfclkv_min0p65: %d kHz\n"
-			"max_dispclk_vmax0p9: %d kHz\n"
-			"max_dispclk_vnom0p8: %d kHz\n"
-			"max_dispclk_vmid0p72: %d kHz\n"
-			"max_dispclk_vmin0p65: %d kHz\n"
-			"max_dppclk_vmax0p9: %d kHz\n"
-			"max_dppclk_vnom0p8: %d kHz\n"
-			"max_dppclk_vmid0p72: %d kHz\n"
-			"max_dppclk_vmin0p65: %d kHz\n"
-			"socclk: %d kHz\n"
-			"fabric_and_dram_bandwidth_vmax0p9: %d MB/s\n"
-			"fabric_and_dram_bandwidth_vnom0p8: %d MB/s\n"
-			"fabric_and_dram_bandwidth_vmid0p72: %d MB/s\n"
-			"fabric_and_dram_bandwidth_vmin0p65: %d MB/s\n"
-			"phyclkv_max0p9: %d kHz\n"
-			"phyclkv_nom0p8: %d kHz\n"
-			"phyclkv_mid0p72: %d kHz\n"
-			"phyclkv_min0p65: %d kHz\n"
-			"downspreading: %d %\n"
+			"dcfclkv_max0p9: %f kHz\n"
+			"dcfclkv_nom0p8: %f kHz\n"
+			"dcfclkv_mid0p72: %f kHz\n"
+			"dcfclkv_min0p65: %f kHz\n"
+			"max_dispclk_vmax0p9: %f kHz\n"
+			"max_dispclk_vnom0p8: %f kHz\n"
+			"max_dispclk_vmid0p72: %f kHz\n"
+			"max_dispclk_vmin0p65: %f kHz\n"
+			"max_dppclk_vmax0p9: %f kHz\n"
+			"max_dppclk_vnom0p8: %f kHz\n"
+			"max_dppclk_vmid0p72: %f kHz\n"
+			"max_dppclk_vmin0p65: %f kHz\n"
+			"socclk: %f kHz\n"
+			"fabric_and_dram_bandwidth_vmax0p9: %f MB/s\n"
+			"fabric_and_dram_bandwidth_vnom0p8: %f MB/s\n"
+			"fabric_and_dram_bandwidth_vmid0p72: %f MB/s\n"
+			"fabric_and_dram_bandwidth_vmin0p65: %f MB/s\n"
+			"phyclkv_max0p9: %f kHz\n"
+			"phyclkv_nom0p8: %f kHz\n"
+			"phyclkv_mid0p72: %f kHz\n"
+			"phyclkv_min0p65: %f kHz\n"
+			"downspreading: %f %%\n"
 			"round_trip_ping_latency_cycles: %d DCFCLK Cycles\n"
 			"urgent_out_of_order_return_per_channel: %d Bytes\n"
 			"number_of_channels: %d\n"
 			"vmm_page_size: %d Bytes\n"
-			"dram_clock_change_latency: %d ns\n"
+			"dram_clock_change_latency: %f ns\n"
 			"return_bus_width: %d Bytes\n",
 			dc->dcn_soc->sr_exit_time * 1000,
 			dc->dcn_soc->sr_enter_plus_exit_time * 1000,
@@ -1527,11 +1527,11 @@ void dcn_bw_sync_calcs_and_dml(struct dc *dc)
 			dc->dcn_soc->vmm_page_size,
 			dc->dcn_soc->dram_clock_change_latency * 1000,
 			dc->dcn_soc->return_bus_width);
-	DC_LOG_BANDWIDTH_CALCS("rob_buffer_size_in_kbyte: %d\n"
-			"det_buffer_size_in_kbyte: %d\n"
-			"dpp_output_buffer_pixels: %d\n"
-			"opp_output_buffer_lines: %d\n"
-			"pixel_chunk_size_in_kbyte: %d\n"
+	DC_LOG_BANDWIDTH_CALCS("rob_buffer_size_in_kbyte: %f\n"
+			"det_buffer_size_in_kbyte: %f\n"
+			"dpp_output_buffer_pixels: %f\n"
+			"opp_output_buffer_lines: %f\n"
+			"pixel_chunk_size_in_kbyte: %f\n"
 			"pte_enable: %d\n"
 			"pte_chunk_size: %d kbytes\n"
 			"meta_chunk_size: %d kbytes\n"
@@ -1550,13 +1550,13 @@ void dcn_bw_sync_calcs_and_dml(struct dc *dc)
 			"max_pscl_tolb_throughput: %d pixels/dppclk\n"
 			"max_lb_tovscl_throughput: %d pixels/dppclk\n"
 			"max_vscl_tohscl_throughput: %d pixels/dppclk\n"
-			"max_hscl_ratio: %d\n"
-			"max_vscl_ratio: %d\n"
+			"max_hscl_ratio: %f\n"
+			"max_vscl_ratio: %f\n"
 			"max_hscl_taps: %d\n"
 			"max_vscl_taps: %d\n"
 			"pte_buffer_size_in_requests: %d\n"
-			"dispclk_ramping_margin: %d %\n"
-			"under_scan_factor: %d %\n"
+			"dispclk_ramping_margin: %f %%\n"
+			"under_scan_factor: %f %%\n"
 			"max_inter_dcn_tile_repeaters: %d\n"
 			"can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one: %d\n"
 			"bug_forcing_luma_and_chroma_request_to_same_size_fixed: %d\n"
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 9cd3566def8d..644b2187507b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -936,95 +936,6 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 	return true;
 }
 
-/*
- * TODO this whole function needs to go
- *
- * dc_surface_update is needlessly complex. See if we can just replace this
- * with a dc_plane_state and follow the atomic model a bit more closely here.
- */
-bool dc_commit_planes_to_stream(
-		struct dc *dc,
-		struct dc_plane_state **plane_states,
-		uint8_t new_plane_count,
-		struct dc_stream_state *dc_stream,
-		struct dc_state *state)
-{
-	/* no need to dynamically allocate this. it's pretty small */
-	struct dc_surface_update updates[MAX_SURFACES];
-	struct dc_flip_addrs *flip_addr;
-	struct dc_plane_info *plane_info;
-	struct dc_scaling_info *scaling_info;
-	int i;
-	struct dc_stream_update *stream_update =
-			kzalloc(sizeof(struct dc_stream_update), GFP_KERNEL);
-
-	if (!stream_update) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-
-	flip_addr = kcalloc(MAX_SURFACES, sizeof(struct dc_flip_addrs),
-			    GFP_KERNEL);
-	plane_info = kcalloc(MAX_SURFACES, sizeof(struct dc_plane_info),
-			     GFP_KERNEL);
-	scaling_info = kcalloc(MAX_SURFACES, sizeof(struct dc_scaling_info),
-			       GFP_KERNEL);
-
-	if (!flip_addr || !plane_info || !scaling_info) {
-		kfree(flip_addr);
-		kfree(plane_info);
-		kfree(scaling_info);
-		kfree(stream_update);
-		return false;
-	}
-
-	memset(updates, 0, sizeof(updates));
-
-	stream_update->src = dc_stream->src;
-	stream_update->dst = dc_stream->dst;
-	stream_update->out_transfer_func = dc_stream->out_transfer_func;
-
-	for (i = 0; i < new_plane_count; i++) {
-		updates[i].surface = plane_states[i];
-		updates[i].gamma =
-			(struct dc_gamma *)plane_states[i]->gamma_correction;
-		updates[i].in_transfer_func = plane_states[i]->in_transfer_func;
-		flip_addr[i].address = plane_states[i]->address;
-		flip_addr[i].flip_immediate = plane_states[i]->flip_immediate;
-		plane_info[i].color_space = plane_states[i]->color_space;
-		plane_info[i].input_tf = plane_states[i]->input_tf;
-		plane_info[i].format = plane_states[i]->format;
-		plane_info[i].plane_size = plane_states[i]->plane_size;
-		plane_info[i].rotation = plane_states[i]->rotation;
-		plane_info[i].horizontal_mirror = plane_states[i]->horizontal_mirror;
-		plane_info[i].stereo_format = plane_states[i]->stereo_format;
-		plane_info[i].tiling_info = plane_states[i]->tiling_info;
-		plane_info[i].visible = plane_states[i]->visible;
-		plane_info[i].per_pixel_alpha = plane_states[i]->per_pixel_alpha;
-		plane_info[i].dcc = plane_states[i]->dcc;
-		scaling_info[i].scaling_quality = plane_states[i]->scaling_quality;
-		scaling_info[i].src_rect = plane_states[i]->src_rect;
-		scaling_info[i].dst_rect = plane_states[i]->dst_rect;
-		scaling_info[i].clip_rect = plane_states[i]->clip_rect;
-
-		updates[i].flip_addr = &flip_addr[i];
-		updates[i].plane_info = &plane_info[i];
-		updates[i].scaling_info = &scaling_info[i];
-	}
-
-	dc_commit_updates_for_stream(
-			dc,
-			updates,
-			new_plane_count,
-			dc_stream, stream_update, plane_states, state);
-
-	kfree(flip_addr);
-	kfree(plane_info);
-	kfree(scaling_info);
-	kfree(stream_update);
-	return true;
-}
-
 struct dc_state *dc_create_state(void)
 {
 	struct dc_state *context = kzalloc(sizeof(struct dc_state),
@@ -1107,9 +1018,6 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa
 	if (u->plane_info->color_space != u->surface->color_space)
 		update_flags->bits.color_space_change = 1;
 
-	if (u->plane_info->input_tf != u->surface->input_tf)
-		update_flags->bits.input_tf_change = 1;
-
 	if (u->plane_info->horizontal_mirror != u->surface->horizontal_mirror)
 		update_flags->bits.horizontal_mirror_change = 1;
 
@@ -1243,12 +1151,20 @@ static enum surface_update_type det_surface_update(const struct dc *dc,
 	if (u->input_csc_color_matrix)
 		update_flags->bits.input_csc_change = 1;
 
-	if (update_flags->bits.in_transfer_func_change
-			|| update_flags->bits.input_csc_change) {
+	if (u->coeff_reduction_factor)
+		update_flags->bits.coeff_reduction_change = 1;
+
+	if (update_flags->bits.in_transfer_func_change) {
 		type = UPDATE_TYPE_MED;
 		elevate_update_type(&overall_type, type);
 	}
 
+	if (update_flags->bits.input_csc_change
+			|| update_flags->bits.coeff_reduction_change) {
+		type = UPDATE_TYPE_FULL;
+		elevate_update_type(&overall_type, type);
+	}
+
 	return overall_type;
 }
 
@@ -1297,7 +1213,7 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
 	type = check_update_surfaces_for_stream(dc, updates, surface_count, stream_update, stream_status);
 	if (type == UPDATE_TYPE_FULL)
 		for (i = 0; i < surface_count; i++)
-			updates[i].surface->update_flags.bits.full_update = 1;
+			updates[i].surface->update_flags.raw = 0xFFFFFFFF;
 
 	return type;
 }
@@ -1375,6 +1291,12 @@ static void commit_planes_for_stream(struct dc *dc,
 					pipe_ctx->stream_res.abm->funcs->set_abm_level(
 							pipe_ctx->stream_res.abm, stream->abm_level);
 			}
+
+			if (stream_update && stream_update->periodic_fn_vsync_delta &&
+					pipe_ctx->stream_res.tg->funcs->program_vline_interrupt)
+				pipe_ctx->stream_res.tg->funcs->program_vline_interrupt(
+						pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing,
+						pipe_ctx->stream->periodic_fn_vsync_delta);
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
index 5a552cb3f8a7..267c76766dea 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
@@ -36,8 +36,9 @@
 #include "hw_sequencer.h"
 
 #include "resource.h"
-#define DC_LOGGER \
-	logger
+
+#define DC_LOGGER_INIT(logger)
+
 
 #define SURFACE_TRACE(...) do {\
 		if (dc->debug.surface_trace) \
@@ -60,8 +61,7 @@ void pre_surface_trace(
 		int surface_count)
 {
 	int i;
-	struct dc  *core_dc = dc;
-	struct dal_logger *logger =  core_dc->ctx->logger;
+	DC_LOGGER_INIT(dc->ctx->logger);
 
 	for (i = 0; i < surface_count; i++) {
 		const struct dc_plane_state *plane_state = plane_states[i];
@@ -72,8 +72,8 @@ void pre_surface_trace(
 				"plane_state->visible = %d;\n"
 				"plane_state->flip_immediate = %d;\n"
 				"plane_state->address.type = %d;\n"
-				"plane_state->address.grph.addr.quad_part = 0x%X;\n"
-				"plane_state->address.grph.meta_addr.quad_part = 0x%X;\n"
+				"plane_state->address.grph.addr.quad_part = 0x%llX;\n"
+				"plane_state->address.grph.meta_addr.quad_part = 0x%llX;\n"
 				"plane_state->scaling_quality.h_taps = %d;\n"
 				"plane_state->scaling_quality.v_taps = %d;\n"
 				"plane_state->scaling_quality.h_taps_c = %d;\n"
@@ -155,7 +155,6 @@ void pre_surface_trace(
 				"plane_state->tiling_info.gfx8.pipe_config = %d;\n"
 				"plane_state->tiling_info.gfx8.array_mode = %d;\n"
 				"plane_state->color_space = %d;\n"
-				"plane_state->input_tf = %d;\n"
 				"plane_state->dcc.enable = %d;\n"
 				"plane_state->format = %d;\n"
 				"plane_state->rotation = %d;\n"
@@ -163,7 +162,6 @@ void pre_surface_trace(
 				plane_state->tiling_info.gfx8.pipe_config,
 				plane_state->tiling_info.gfx8.array_mode,
 				plane_state->color_space,
-				plane_state->input_tf,
 				plane_state->dcc.enable,
 				plane_state->format,
 				plane_state->rotation,
@@ -183,8 +181,7 @@ void update_surface_trace(
 		int surface_count)
 {
 	int i;
-	struct dc  *core_dc = dc;
-	struct dal_logger *logger =  core_dc->ctx->logger;
+	DC_LOGGER_INIT(dc->ctx->logger);
 
 	for (i = 0; i < surface_count; i++) {
 		const struct dc_surface_update *update = &updates[i];
@@ -192,8 +189,8 @@ void update_surface_trace(
 		SURFACE_TRACE("Update %d\n", i);
 		if (update->flip_addr) {
 			SURFACE_TRACE("flip_addr->address.type = %d;\n"
-					"flip_addr->address.grph.addr.quad_part = 0x%X;\n"
-					"flip_addr->address.grph.meta_addr.quad_part = 0x%X;\n"
+					"flip_addr->address.grph.addr.quad_part = 0x%llX;\n"
+					"flip_addr->address.grph.meta_addr.quad_part = 0x%llX;\n"
 					"flip_addr->flip_immediate = %d;\n",
 					update->flip_addr->address.type,
 					update->flip_addr->address.grph.addr.quad_part,
@@ -204,16 +201,15 @@ void update_surface_trace(
 		if (update->plane_info) {
 			SURFACE_TRACE(
 					"plane_info->color_space = %d;\n"
-					"plane_info->input_tf = %d;\n"
 					"plane_info->format = %d;\n"
 					"plane_info->plane_size.grph.surface_pitch = %d;\n"
 					"plane_info->plane_size.grph.surface_size.height = %d;\n"
 					"plane_info->plane_size.grph.surface_size.width = %d;\n"
 					"plane_info->plane_size.grph.surface_size.x = %d;\n"
 					"plane_info->plane_size.grph.surface_size.y = %d;\n"
-					"plane_info->rotation = %d;\n",
+					"plane_info->rotation = %d;\n"
+					"plane_info->stereo_format = %d;\n",
 					update->plane_info->color_space,
-					update->plane_info->input_tf,
 					update->plane_info->format,
 					update->plane_info->plane_size.grph.surface_pitch,
 					update->plane_info->plane_size.grph.surface_size.height,
@@ -303,8 +299,7 @@ void update_surface_trace(
 
 void post_surface_trace(struct dc *dc)
 {
-	struct dc  *core_dc = dc;
-	struct dal_logger *logger =  core_dc->ctx->logger;
+	DC_LOGGER_INIT(dc->ctx->logger);
 
 	SURFACE_TRACE("post surface process.\n");
 
@@ -316,10 +311,10 @@ void context_timing_trace(
 {
 	int i;
 	struct dc  *core_dc = dc;
-	struct dal_logger *logger =  core_dc->ctx->logger;
 	int h_pos[MAX_PIPES], v_pos[MAX_PIPES];
 	struct crtc_position position;
 	unsigned int underlay_idx = core_dc->res_pool->underlay_pipe_index;
+	DC_LOGGER_INIT(dc->ctx->logger);
 
 
 	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
@@ -354,9 +349,7 @@ void context_clock_trace(
 		struct dc_state *context)
 {
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	struct dc  *core_dc = dc;
-	struct dal_logger *logger =  core_dc->ctx->logger;
-
+	DC_LOGGER_INIT(dc->ctx->logger);
 	CLOCK_TRACE("Current: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
 			context->bw.dcn.calc_clk.dispclk_khz,
@@ -371,6 +364,7 @@ void context_clock_trace(
 			context->bw.dcn.calc_clk.dppclk_khz,
 			context->bw.dcn.calc_clk.dcfclk_khz,
 			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			context->bw.dcn.calc_clk.fclk_khz);
+			context->bw.dcn.calc_clk.fclk_khz,
+			context->bw.dcn.calc_clk.socclk_khz);
 #endif
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
index ebc96b720083..83d121510ef5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
@@ -208,6 +208,7 @@ void color_space_to_black_color(
 	case COLOR_SPACE_YCBCR709:
 	case COLOR_SPACE_YCBCR601_LIMITED:
 	case COLOR_SPACE_YCBCR709_LIMITED:
+	case COLOR_SPACE_2020_YCBCR:
 		*black_color = black_color_format[BLACK_COLOR_FORMAT_YUV_CV];
 		break;
 
@@ -216,7 +217,25 @@ void color_space_to_black_color(
 			black_color_format[BLACK_COLOR_FORMAT_RGB_LIMITED];
 		break;
 
-	default:
+	/**
+	 * Remove default and add case for all color space
+	 * so when we forget to add new color space
+	 * compiler will give a warning
+	 */
+	case COLOR_SPACE_UNKNOWN:
+	case COLOR_SPACE_SRGB:
+	case COLOR_SPACE_XR_RGB:
+	case COLOR_SPACE_MSREF_SCRGB:
+	case COLOR_SPACE_XV_YCC_709:
+	case COLOR_SPACE_XV_YCC_601:
+	case COLOR_SPACE_2020_RGB_FULLRANGE:
+	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
+	case COLOR_SPACE_ADOBERGB:
+	case COLOR_SPACE_DCIP3:
+	case COLOR_SPACE_DISPLAYNATIVE:
+	case COLOR_SPACE_DOLBYVISION:
+	case COLOR_SPACE_APPCTRL:
+	case COLOR_SPACE_CUSTOMPOINTS:
 		/* fefault is sRGB black (full range). */
 		*black_color =
 			black_color_format[BLACK_COLOR_FORMAT_RGB_FULLRANGE];
@@ -230,6 +249,9 @@ bool hwss_wait_for_blank_complete(
 {
 	int counter;
 
+	/* Not applicable if the pipe is not primary, save 300ms of boot time */
+	if (!tg->funcs->is_blanked)
+		return true;
 	for (counter = 0; counter < 100; counter++) {
 		if (tg->funcs->is_blanked(tg))
 			break;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 6d1c4981a185..2fa521812d23 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -45,8 +45,9 @@
 #include "dce/dce_11_0_d.h"
 #include "dce/dce_11_0_enum.h"
 #include "dce/dce_11_0_sh_mask.h"
-#define DC_LOGGER \
-	dc_ctx->logger
+
+#define DC_LOGGER_INIT(logger)
+
 
 #define LINK_INFO(...) \
 	DC_LOG_HW_HOTPLUG(  \
@@ -468,6 +469,13 @@ static void link_disconnect_sink(struct dc_link *link)
 	link->dpcd_sink_count = 0;
 }
 
+static void link_disconnect_remap(struct dc_sink *prev_sink, struct dc_link *link)
+{
+	dc_sink_release(link->local_sink);
+	link->local_sink = prev_sink;
+}
+
+
 static bool detect_dp(
 	struct dc_link *link,
 	struct display_sink_capability *sink_caps,
@@ -550,6 +558,17 @@ static bool detect_dp(
 	return true;
 }
 
+static bool is_same_edid(struct dc_edid *old_edid, struct dc_edid *new_edid)
+{
+	if (old_edid->length != new_edid->length)
+		return false;
+
+	if (new_edid->length == 0)
+		return false;
+
+	return (memcmp(old_edid->raw_edid, new_edid->raw_edid, new_edid->length) == 0);
+}
+
 bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 {
 	struct dc_sink_init_data sink_init_data = { 0 };
@@ -557,11 +576,15 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 	uint8_t i;
 	bool converter_disable_audio = false;
 	struct audio_support *aud_support = &link->dc->res_pool->audio_support;
+	bool same_edid = false;
 	enum dc_edid_status edid_status;
 	struct dc_context *dc_ctx = link->ctx;
 	struct dc_sink *sink = NULL;
+	struct dc_sink *prev_sink = NULL;
+	struct dpcd_caps prev_dpcd_caps;
+	bool same_dpcd = true;
 	enum dc_connection_type new_connection_type = dc_connection_none;
-
+	DC_LOGGER_INIT(link->ctx->logger);
 	if (link->connector_signal == SIGNAL_TYPE_VIRTUAL)
 		return false;
 
@@ -574,6 +597,11 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 			link->local_sink)
 		return true;
 
+	prev_sink = link->local_sink;
+	if (prev_sink != NULL) {
+		dc_sink_retain(prev_sink);
+		memcpy(&prev_dpcd_caps, &link->dpcd_caps, sizeof(struct dpcd_caps));
+	}
 	link_disconnect_sink(link);
 
 	if (new_connection_type != dc_connection_none) {
@@ -615,14 +643,25 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 				link,
 				&sink_caps,
 				&converter_disable_audio,
-				aud_support, reason))
+				aud_support, reason)) {
+				if (prev_sink != NULL)
+					dc_sink_release(prev_sink);
 				return false;
+			}
 
+			// Check if dpcp block is the same
+			if (prev_sink != NULL) {
+				if (memcmp(&link->dpcd_caps, &prev_dpcd_caps, sizeof(struct dpcd_caps)))
+					same_dpcd = false;
+			}
 			/* Active dongle downstream unplug */
 			if (link->type == dc_connection_active_dongle
 					&& link->dpcd_caps.sink_count.
-					bits.SINK_COUNT == 0)
+					bits.SINK_COUNT == 0) {
+				if (prev_sink != NULL)
+					dc_sink_release(prev_sink);
 				return true;
+			}
 
 			if (link->type == dc_connection_mst_branch) {
 				LINK_INFO("link=%d, mst branch is now Connected\n",
@@ -630,9 +669,11 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 				/* Need to setup mst link_cap struct here
 				 * otherwise dc_link_detect() will leave mst link_cap
 				 * empty which leads to allocate_mst_payload() has "0"
-				 * pbn_per_slot value leading to exception on dal_fixed31_32_div()
+				 * pbn_per_slot value leading to exception on dc_fixpt_div()
 				 */
 				link->verified_link_cap = link->reported_link_cap;
+				if (prev_sink != NULL)
+					dc_sink_release(prev_sink);
 				return false;
 			}
 
@@ -642,6 +683,8 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 		default:
 			DC_ERROR("Invalid connector type! signal:%d\n",
 				link->connector_signal);
+			if (prev_sink != NULL)
+				dc_sink_release(prev_sink);
 			return false;
 		} /* switch() */
 
@@ -664,6 +707,8 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 		sink = dc_sink_create(&sink_init_data);
 		if (!sink) {
 			DC_ERROR("Failed to create sink!\n");
+			if (prev_sink != NULL)
+				dc_sink_release(prev_sink);
 			return false;
 		}
 
@@ -687,22 +732,33 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 			break;
 		}
 
-		if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
-			sink_caps.transaction_type ==
-			DDC_TRANSACTION_TYPE_I2C_OVER_AUX) {
-			/*
-			 * TODO debug why Dell 2413 doesn't like
-			 *  two link trainings
-			 */
+		// Check if edid is the same
+		if ((prev_sink != NULL) && ((edid_status == EDID_THE_SAME) || (edid_status == EDID_OK)))
+			same_edid = is_same_edid(&prev_sink->dc_edid, &sink->dc_edid);
 
-			/* deal with non-mst cases */
-			dp_hbr_verify_link_cap(link, &link->reported_link_cap);
-		}
+		// If both edid and dpcd are the same, then discard new sink and revert back to original sink
+		if ((same_edid) && (same_dpcd)) {
+			link_disconnect_remap(prev_sink, link);
+			sink = prev_sink;
+			prev_sink = NULL;
+		} else {
+			if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
+					sink_caps.transaction_type ==
+						DDC_TRANSACTION_TYPE_I2C_OVER_AUX) {
+				/*
+				 * TODO debug why Dell 2413 doesn't like
+				 *  two link trainings
+				 */
 
-		/* HDMI-DVI Dongle */
-		if (sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A &&
-				!sink->edid_caps.edid_hdmi)
-			sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
+				/* deal with non-mst cases */
+				dp_hbr_verify_link_cap(link, &link->reported_link_cap);
+			}
+
+			/* HDMI-DVI Dongle */
+			if (sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A &&
+					!sink->edid_caps.edid_hdmi)
+				sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
+		}
 
 		/* Connectivity log: detection */
 		for (i = 0; i < sink->dc_edid.length / EDID_BLOCK_SIZE; i++) {
@@ -761,10 +817,14 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 		sink_caps.signal = SIGNAL_TYPE_NONE;
 	}
 
-	LINK_INFO("link=%d, dc_sink_in=%p is now %s\n",
+	LINK_INFO("link=%d, dc_sink_in=%p is now %s prev_sink=%p dpcd same=%d edid same=%d\n",
 		link->link_index, sink,
 		(sink_caps.signal == SIGNAL_TYPE_NONE ?
-			"Disconnected":"Connected"));
+			"Disconnected":"Connected"), prev_sink,
+			same_dpcd, same_edid);
+
+	if (prev_sink != NULL)
+		dc_sink_release(prev_sink);
 
 	return true;
 }
@@ -927,6 +987,7 @@ static bool construct(
 	struct integrated_info info = {{{ 0 }}};
 	struct dc_bios *bios = init_params->dc->ctx->dc_bios;
 	const struct dc_vbios_funcs *bp_funcs = bios->funcs;
+	DC_LOGGER_INIT(dc_ctx->logger);
 
 	link->irq_source_hpd = DC_IRQ_SOURCE_INVALID;
 	link->irq_source_hpd_rx = DC_IRQ_SOURCE_INVALID;
@@ -1135,7 +1196,8 @@ static void dpcd_configure_panel_mode(
 {
 	union dpcd_edp_config edp_config_set;
 	bool panel_mode_edp = false;
-	struct dc_context *dc_ctx = link->ctx;
+	DC_LOGGER_INIT(link->ctx->logger);
+
 	memset(&edp_config_set, '\0', sizeof(union dpcd_edp_config));
 
 	if (DP_PANEL_MODE_DEFAULT != panel_mode) {
@@ -1183,16 +1245,21 @@ static void enable_stream_features(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->sink->link;
-	union down_spread_ctrl downspread;
+	union down_spread_ctrl old_downspread;
+	union down_spread_ctrl new_downspread;
 
 	core_link_read_dpcd(link, DP_DOWNSPREAD_CTRL,
-			&downspread.raw, sizeof(downspread));
+			&old_downspread.raw, sizeof(old_downspread));
 
-	downspread.bits.IGNORE_MSA_TIMING_PARAM =
+	new_downspread.raw = old_downspread.raw;
+
+	new_downspread.bits.IGNORE_MSA_TIMING_PARAM =
 			(stream->ignore_msa_timing_param) ? 1 : 0;
 
-	core_link_write_dpcd(link, DP_DOWNSPREAD_CTRL,
-			&downspread.raw, sizeof(downspread));
+	if (new_downspread.raw != old_downspread.raw) {
+		core_link_write_dpcd(link, DP_DOWNSPREAD_CTRL,
+			&new_downspread.raw, sizeof(new_downspread));
+	}
 }
 
 static enum dc_status enable_link_dp(
@@ -1843,9 +1910,22 @@ static void disable_link(struct dc_link *link, enum signal_type signal)
 
 static bool dp_active_dongle_validate_timing(
 		const struct dc_crtc_timing *timing,
-		const struct dc_dongle_caps *dongle_caps)
+		const struct dpcd_caps *dpcd_caps)
 {
 	unsigned int required_pix_clk = timing->pix_clk_khz;
+	const struct dc_dongle_caps *dongle_caps = &dpcd_caps->dongle_caps;
+
+	switch (dpcd_caps->dongle_type) {
+	case DISPLAY_DONGLE_DP_VGA_CONVERTER:
+	case DISPLAY_DONGLE_DP_DVI_CONVERTER:
+	case DISPLAY_DONGLE_DP_DVI_DONGLE:
+		if (timing->pixel_encoding == PIXEL_ENCODING_RGB)
+			return true;
+		else
+			return false;
+	default:
+		break;
+	}
 
 	if (dongle_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER ||
 		dongle_caps->extendedCapValid == false)
@@ -1911,7 +1991,7 @@ enum dc_status dc_link_validate_mode_timing(
 		const struct dc_crtc_timing *timing)
 {
 	uint32_t max_pix_clk = stream->sink->dongle_max_pix_clk;
-	struct dc_dongle_caps *dongle_caps = &link->dpcd_caps.dongle_caps;
+	struct dpcd_caps *dpcd_caps = &link->dpcd_caps;
 
 	/* A hack to avoid failing any modes for EDID override feature on
 	 * topology change such as lower quality cable for DP or different dongle
@@ -1924,7 +2004,7 @@ enum dc_status dc_link_validate_mode_timing(
 		return DC_EXCEED_DONGLE_CAP;
 
 	/* Active Dongle*/
-	if (!dp_active_dongle_validate_timing(timing, dongle_caps))
+	if (!dp_active_dongle_validate_timing(timing, dpcd_caps))
 		return DC_EXCEED_DONGLE_CAP;
 
 	switch (stream->signal) {
@@ -1950,10 +2030,10 @@ bool dc_link_set_backlight_level(const struct dc_link *link, uint32_t level,
 	struct dc  *core_dc = link->ctx->dc;
 	struct abm *abm = core_dc->res_pool->abm;
 	struct dmcu *dmcu = core_dc->res_pool->dmcu;
-	struct dc_context *dc_ctx = link->ctx;
 	unsigned int controller_id = 0;
 	bool use_smooth_brightness = true;
 	int i;
+	DC_LOGGER_INIT(link->ctx->logger);
 
 	if ((dmcu == NULL) ||
 		(abm == NULL) ||
@@ -1961,7 +2041,7 @@ bool dc_link_set_backlight_level(const struct dc_link *link, uint32_t level,
 		return false;
 
 	if (stream) {
-		if (stream->bl_pwm_level == 0)
+		if (stream->bl_pwm_level == EDP_BACKLIGHT_RAMP_DISABLE_LEVEL)
 			frame_ramp = 0;
 
 		((struct dc_stream_state *)stream)->bl_pwm_level = level;
@@ -2038,10 +2118,10 @@ static struct fixed31_32 get_pbn_per_slot(struct dc_stream_state *stream)
 			&stream->sink->link->cur_link_settings;
 	uint32_t link_rate_in_mbps =
 			link_settings->link_rate * LINK_RATE_REF_FREQ_IN_MHZ;
-	struct fixed31_32 mbps = dal_fixed31_32_from_int(
+	struct fixed31_32 mbps = dc_fixpt_from_int(
 			link_rate_in_mbps * link_settings->lane_count);
 
-	return dal_fixed31_32_div_int(mbps, 54);
+	return dc_fixpt_div_int(mbps, 54);
 }
 
 static int get_color_depth(enum dc_color_depth color_depth)
@@ -2082,7 +2162,7 @@ static struct fixed31_32 get_pbn_from_timing(struct pipe_ctx *pipe_ctx)
 	numerator = 64 * PEAK_FACTOR_X1000;
 	denominator = 54 * 8 * 1000 * 1000;
 	kbps *= numerator;
-	peak_kbps = dal_fixed31_32_from_fraction(kbps, denominator);
+	peak_kbps = dc_fixpt_from_fraction(kbps, denominator);
 
 	return peak_kbps;
 }
@@ -2149,8 +2229,8 @@ static enum dc_status allocate_mst_payload(struct pipe_ctx *pipe_ctx)
 	struct fixed31_32 avg_time_slots_per_mtp;
 	struct fixed31_32 pbn;
 	struct fixed31_32 pbn_per_slot;
-	struct dc_context *dc_ctx = link->ctx;
 	uint8_t i;
+	DC_LOGGER_INIT(link->ctx->logger);
 
 	/* enable_link_dp_mst already check link->enabled_stream_count
 	 * and stream is in link->stream[]. This is called during set mode,
@@ -2178,11 +2258,11 @@ static enum dc_status allocate_mst_payload(struct pipe_ctx *pipe_ctx)
 			link->mst_stream_alloc_table.stream_count);
 
 	for (i = 0; i < MAX_CONTROLLER_NUM; i++) {
-		DC_LOG_MST("stream_enc[%d]: 0x%x      "
+		DC_LOG_MST("stream_enc[%d]: %p      "
 		"stream[%d].vcp_id: %d      "
 		"stream[%d].slot_count: %d\n",
 		i,
-		link->mst_stream_alloc_table.stream_allocations[i].stream_enc,
+		(void *) link->mst_stream_alloc_table.stream_allocations[i].stream_enc,
 		i,
 		link->mst_stream_alloc_table.stream_allocations[i].vcp_id,
 		i,
@@ -2209,7 +2289,7 @@ static enum dc_status allocate_mst_payload(struct pipe_ctx *pipe_ctx)
 	/* slot X.Y for only current stream */
 	pbn_per_slot = get_pbn_per_slot(stream);
 	pbn = get_pbn_from_timing(pipe_ctx);
-	avg_time_slots_per_mtp = dal_fixed31_32_div(pbn, pbn_per_slot);
+	avg_time_slots_per_mtp = dc_fixpt_div(pbn, pbn_per_slot);
 
 	stream_encoder->funcs->set_mst_bandwidth(
 		stream_encoder,
@@ -2226,10 +2306,10 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
 	struct link_encoder *link_encoder = link->link_enc;
 	struct stream_encoder *stream_encoder = pipe_ctx->stream_res.stream_enc;
 	struct dp_mst_stream_allocation_table proposed_table = {0};
-	struct fixed31_32 avg_time_slots_per_mtp = dal_fixed31_32_from_int(0);
+	struct fixed31_32 avg_time_slots_per_mtp = dc_fixpt_from_int(0);
 	uint8_t i;
 	bool mst_mode = (link->type == dc_connection_mst_branch);
-	struct dc_context *dc_ctx = link->ctx;
+	DC_LOGGER_INIT(link->ctx->logger);
 
 	/* deallocate_mst_payload is called before disable link. When mode or
 	 * disable/enable monitor, new stream is created which is not in link
@@ -2268,11 +2348,11 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
 			link->mst_stream_alloc_table.stream_count);
 
 	for (i = 0; i < MAX_CONTROLLER_NUM; i++) {
-		DC_LOG_MST("stream_enc[%d]: 0x%x      "
+		DC_LOG_MST("stream_enc[%d]: %p      "
 		"stream[%d].vcp_id: %d      "
 		"stream[%d].slot_count: %d\n",
 		i,
-		link->mst_stream_alloc_table.stream_allocations[i].stream_enc,
+		(void *) link->mst_stream_alloc_table.stream_allocations[i].stream_enc,
 		i,
 		link->mst_stream_alloc_table.stream_allocations[i].vcp_id,
 		i,
@@ -2302,8 +2382,8 @@ void core_link_enable_stream(
 		struct pipe_ctx *pipe_ctx)
 {
 	struct dc  *core_dc = pipe_ctx->stream->ctx->dc;
-	struct dc_context *dc_ctx = pipe_ctx->stream->ctx;
 	enum dc_status status;
+	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
 	/* eDP lit up by bios already, no need to enable again. */
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_EDP &&
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 49c2face1e7a..ae48d603ebd6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -629,13 +629,14 @@ bool dal_ddc_service_query_ddc_data(
 	return ret;
 }
 
-ssize_t dal_ddc_service_read_dpcd_data(
+enum ddc_result dal_ddc_service_read_dpcd_data(
 	struct ddc_service *ddc,
 	bool i2c,
 	enum i2c_mot_mode mot,
 	uint32_t address,
 	uint8_t *data,
-	uint32_t len)
+	uint32_t len,
+	uint32_t *read)
 {
 	struct aux_payload read_payload = {
 		.i2c_over_aux = i2c,
@@ -652,6 +653,8 @@ ssize_t dal_ddc_service_read_dpcd_data(
 		.mot = mot
 	};
 
+	*read = 0;
+
 	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
 		BREAK_TO_DEBUGGER();
 		return DDC_RESULT_FAILED_INVALID_OPERATION;
@@ -661,7 +664,8 @@ ssize_t dal_ddc_service_read_dpcd_data(
 		ddc->ctx->i2caux,
 		ddc->ddc_pin,
 		&command)) {
-		return (ssize_t)command.payloads->length;
+		*read = command.payloads->length;
+		return DDC_RESULT_SUCESSFULL;
 	}
 
 	return DDC_RESULT_FAILED_OPERATION;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 3b5053570229..7d609c71394b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1378,8 +1378,8 @@ static uint32_t bandwidth_in_kbps_from_timing(
 {
 	uint32_t bits_per_channel = 0;
 	uint32_t kbps;
-	switch (timing->display_color_depth) {
 
+	switch (timing->display_color_depth) {
 	case COLOR_DEPTH_666:
 		bits_per_channel = 6;
 		break;
@@ -1401,14 +1401,20 @@ static uint32_t bandwidth_in_kbps_from_timing(
 	default:
 		break;
 	}
+
 	ASSERT(bits_per_channel != 0);
 
 	kbps = timing->pix_clk_khz;
 	kbps *= bits_per_channel;
 
-	if (timing->flags.Y_ONLY != 1)
+	if (timing->flags.Y_ONLY != 1) {
 		/*Only YOnly make reduce bandwidth by 1/3 compares to RGB*/
 		kbps *= 3;
+		if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			kbps /= 2;
+		else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
+			kbps = kbps * 2 / 3;
+	}
 
 	return kbps;
 
@@ -2278,6 +2284,8 @@ static bool retrieve_link_cap(struct dc_link *link)
 	union edp_configuration_cap edp_config_cap;
 	union dp_downstream_port_present ds_port = { 0 };
 	enum dc_status status = DC_ERROR_UNEXPECTED;
+	uint32_t read_dpcd_retry_cnt = 3;
+	int i;
 
 	memset(dpcd_data, '\0', sizeof(dpcd_data));
 	memset(&down_strm_port_count,
@@ -2285,11 +2293,15 @@ static bool retrieve_link_cap(struct dc_link *link)
 	memset(&edp_config_cap, '\0',
 		sizeof(union edp_configuration_cap));
 
-	status = core_link_read_dpcd(
-			link,
-			DP_DPCD_REV,
-			dpcd_data,
-			sizeof(dpcd_data));
+	for (i = 0; i < read_dpcd_retry_cnt; i++) {
+		status = core_link_read_dpcd(
+				link,
+				DP_DPCD_REV,
+				dpcd_data,
+				sizeof(dpcd_data));
+		if (status == DC_OK)
+			break;
+	}
 
 	if (status != DC_OK) {
 		dm_error("%s: Read dpcd data failed.\n", __func__);
@@ -2376,6 +2388,10 @@ bool detect_dp_sink_caps(struct dc_link *link)
 void detect_edp_sink_caps(struct dc_link *link)
 {
 	retrieve_link_cap(link);
+
+	if (link->reported_link_cap.link_rate == LINK_RATE_UNKNOWN)
+		link->reported_link_cap.link_rate = LINK_RATE_HIGH2;
+
 	link->verified_link_cap = link->reported_link_cap;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
index 7c866a7d5e77..82cd1d6e6e59 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
@@ -11,8 +11,6 @@
 #include "dc_link_dp.h"
 #include "dc_link_ddc.h"
 #include "dm_helpers.h"
-#include "dce/dce_link_encoder.h"
-#include "dce/dce_stream_encoder.h"
 #include "dpcd_defs.h"
 
 enum dc_status core_link_read_dpcd(
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index ba3487e97361..751f3ac9d921 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -45,8 +45,9 @@
 #include "dcn10/dcn10_resource.h"
 #endif
 #include "dce120/dce120_resource.h"
-#define DC_LOGGER \
-	ctx->logger
+
+#define DC_LOGGER_INIT(logger)
+
 enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 {
 	enum dce_version dc_version = DCE_VERSION_UNKNOWN;
@@ -78,6 +79,8 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 				ASIC_REV_IS_POLARIS12_V(asic_id.hw_internal_rev)) {
 			dc_version = DCE_VERSION_11_2;
 		}
+		if (ASIC_REV_IS_VEGAM(asic_id.hw_internal_rev))
+			dc_version = DCE_VERSION_11_22;
 		break;
 	case FAMILY_AI:
 		dc_version = DCE_VERSION_12_0;
@@ -124,6 +127,7 @@ struct resource_pool *dc_create_resource_pool(
 			num_virtual_links, dc, asic_id);
 		break;
 	case DCE_VERSION_11_2:
+	case DCE_VERSION_11_22:
 		res_pool = dce112_create_resource_pool(
 			num_virtual_links, dc);
 		break;
@@ -492,9 +496,9 @@ static void calculate_viewport(struct pipe_ctx *pipe_ctx)
 	data->viewport_c.x = data->viewport.x / vpc_div;
 	data->viewport_c.y = data->viewport.y / vpc_div;
 	data->inits.h_c = (data->viewport.x % vpc_div) != 0 ?
-			dal_fixed31_32_half : dal_fixed31_32_zero;
+			dc_fixpt_half : dc_fixpt_zero;
 	data->inits.v_c = (data->viewport.y % vpc_div) != 0 ?
-			dal_fixed31_32_half : dal_fixed31_32_zero;
+			dc_fixpt_half : dc_fixpt_zero;
 	/* Round up, assume original video size always even dimensions */
 	data->viewport_c.width = (data->viewport.width + vpc_div - 1) / vpc_div;
 	data->viewport_c.height = (data->viewport.height + vpc_div - 1) / vpc_div;
@@ -623,10 +627,10 @@ static void calculate_scaling_ratios(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270)
 		rect_swap_helper(&surf_src);
 
-	pipe_ctx->plane_res.scl_data.ratios.horz = dal_fixed31_32_from_fraction(
+	pipe_ctx->plane_res.scl_data.ratios.horz = dc_fixpt_from_fraction(
 					surf_src.width,
 					plane_state->dst_rect.width);
-	pipe_ctx->plane_res.scl_data.ratios.vert = dal_fixed31_32_from_fraction(
+	pipe_ctx->plane_res.scl_data.ratios.vert = dc_fixpt_from_fraction(
 					surf_src.height,
 					plane_state->dst_rect.height);
 
@@ -648,6 +652,14 @@ static void calculate_scaling_ratios(struct pipe_ctx *pipe_ctx)
 		pipe_ctx->plane_res.scl_data.ratios.horz_c.value /= 2;
 		pipe_ctx->plane_res.scl_data.ratios.vert_c.value /= 2;
 	}
+	pipe_ctx->plane_res.scl_data.ratios.horz = dc_fixpt_truncate(
+			pipe_ctx->plane_res.scl_data.ratios.horz, 19);
+	pipe_ctx->plane_res.scl_data.ratios.vert = dc_fixpt_truncate(
+			pipe_ctx->plane_res.scl_data.ratios.vert, 19);
+	pipe_ctx->plane_res.scl_data.ratios.horz_c = dc_fixpt_truncate(
+			pipe_ctx->plane_res.scl_data.ratios.horz_c, 19);
+	pipe_ctx->plane_res.scl_data.ratios.vert_c = dc_fixpt_truncate(
+			pipe_ctx->plane_res.scl_data.ratios.vert_c, 19);
 }
 
 static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *recout_skip)
@@ -684,32 +696,33 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 	 * 	init_bot = init + scaling_ratio
 	 * 	init_c = init + truncated_vp_c_offset(from calculate viewport)
 	 */
-	data->inits.h = dal_fixed31_32_div_int(
-			dal_fixed31_32_add_int(data->ratios.horz, data->taps.h_taps + 1), 2);
+	data->inits.h = dc_fixpt_truncate(dc_fixpt_div_int(
+			dc_fixpt_add_int(data->ratios.horz, data->taps.h_taps + 1), 2), 19);
 
-	data->inits.h_c = dal_fixed31_32_add(data->inits.h_c, dal_fixed31_32_div_int(
-			dal_fixed31_32_add_int(data->ratios.horz_c, data->taps.h_taps_c + 1), 2));
+	data->inits.h_c = dc_fixpt_truncate(dc_fixpt_add(data->inits.h_c, dc_fixpt_div_int(
+			dc_fixpt_add_int(data->ratios.horz_c, data->taps.h_taps_c + 1), 2)), 19);
 
-	data->inits.v = dal_fixed31_32_div_int(
-			dal_fixed31_32_add_int(data->ratios.vert, data->taps.v_taps + 1), 2);
+	data->inits.v = dc_fixpt_truncate(dc_fixpt_div_int(
+			dc_fixpt_add_int(data->ratios.vert, data->taps.v_taps + 1), 2), 19);
+
+	data->inits.v_c = dc_fixpt_truncate(dc_fixpt_add(data->inits.v_c, dc_fixpt_div_int(
+			dc_fixpt_add_int(data->ratios.vert_c, data->taps.v_taps_c + 1), 2)), 19);
 
-	data->inits.v_c = dal_fixed31_32_add(data->inits.v_c, dal_fixed31_32_div_int(
-			dal_fixed31_32_add_int(data->ratios.vert_c, data->taps.v_taps_c + 1), 2));
 
 
 	/* Adjust for viewport end clip-off */
 	if ((data->viewport.x + data->viewport.width) < (src.x + src.width) && !flip_horz_scan_dir) {
 		int vp_clip = src.x + src.width - data->viewport.width - data->viewport.x;
-		int int_part = dal_fixed31_32_floor(
-				dal_fixed31_32_sub(data->inits.h, data->ratios.horz));
+		int int_part = dc_fixpt_floor(
+				dc_fixpt_sub(data->inits.h, data->ratios.horz));
 
 		int_part = int_part > 0 ? int_part : 0;
 		data->viewport.width += int_part < vp_clip ? int_part : vp_clip;
 	}
 	if ((data->viewport.y + data->viewport.height) < (src.y + src.height) && !flip_vert_scan_dir) {
 		int vp_clip = src.y + src.height - data->viewport.height - data->viewport.y;
-		int int_part = dal_fixed31_32_floor(
-				dal_fixed31_32_sub(data->inits.v, data->ratios.vert));
+		int int_part = dc_fixpt_floor(
+				dc_fixpt_sub(data->inits.v, data->ratios.vert));
 
 		int_part = int_part > 0 ? int_part : 0;
 		data->viewport.height += int_part < vp_clip ? int_part : vp_clip;
@@ -717,8 +730,8 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 	if ((data->viewport_c.x + data->viewport_c.width) < (src.x + src.width) / vpc_div && !flip_horz_scan_dir) {
 		int vp_clip = (src.x + src.width) / vpc_div -
 				data->viewport_c.width - data->viewport_c.x;
-		int int_part = dal_fixed31_32_floor(
-				dal_fixed31_32_sub(data->inits.h_c, data->ratios.horz_c));
+		int int_part = dc_fixpt_floor(
+				dc_fixpt_sub(data->inits.h_c, data->ratios.horz_c));
 
 		int_part = int_part > 0 ? int_part : 0;
 		data->viewport_c.width += int_part < vp_clip ? int_part : vp_clip;
@@ -726,8 +739,8 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 	if ((data->viewport_c.y + data->viewport_c.height) < (src.y + src.height) / vpc_div && !flip_vert_scan_dir) {
 		int vp_clip = (src.y + src.height) / vpc_div -
 				data->viewport_c.height - data->viewport_c.y;
-		int int_part = dal_fixed31_32_floor(
-				dal_fixed31_32_sub(data->inits.v_c, data->ratios.vert_c));
+		int int_part = dc_fixpt_floor(
+				dc_fixpt_sub(data->inits.v_c, data->ratios.vert_c));
 
 		int_part = int_part > 0 ? int_part : 0;
 		data->viewport_c.height += int_part < vp_clip ? int_part : vp_clip;
@@ -737,9 +750,9 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 	if (data->viewport.x && !flip_horz_scan_dir) {
 		int int_part;
 
-		data->inits.h = dal_fixed31_32_add(data->inits.h, dal_fixed31_32_mul_int(
+		data->inits.h = dc_fixpt_add(data->inits.h, dc_fixpt_mul_int(
 				data->ratios.horz, recout_skip->width));
-		int_part = dal_fixed31_32_floor(data->inits.h) - data->viewport.x;
+		int_part = dc_fixpt_floor(data->inits.h) - data->viewport.x;
 		if (int_part < data->taps.h_taps) {
 			int int_adj = data->viewport.x >= (data->taps.h_taps - int_part) ?
 						(data->taps.h_taps - int_part) : data->viewport.x;
@@ -752,15 +765,15 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 			int_part = data->taps.h_taps;
 		}
 		data->inits.h.value &= 0xffffffff;
-		data->inits.h = dal_fixed31_32_add_int(data->inits.h, int_part);
+		data->inits.h = dc_fixpt_add_int(data->inits.h, int_part);
 	}
 
 	if (data->viewport_c.x && !flip_horz_scan_dir) {
 		int int_part;
 
-		data->inits.h_c = dal_fixed31_32_add(data->inits.h_c, dal_fixed31_32_mul_int(
+		data->inits.h_c = dc_fixpt_add(data->inits.h_c, dc_fixpt_mul_int(
 				data->ratios.horz_c, recout_skip->width));
-		int_part = dal_fixed31_32_floor(data->inits.h_c) - data->viewport_c.x;
+		int_part = dc_fixpt_floor(data->inits.h_c) - data->viewport_c.x;
 		if (int_part < data->taps.h_taps_c) {
 			int int_adj = data->viewport_c.x >= (data->taps.h_taps_c - int_part) ?
 					(data->taps.h_taps_c - int_part) : data->viewport_c.x;
@@ -773,15 +786,15 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 			int_part = data->taps.h_taps_c;
 		}
 		data->inits.h_c.value &= 0xffffffff;
-		data->inits.h_c = dal_fixed31_32_add_int(data->inits.h_c, int_part);
+		data->inits.h_c = dc_fixpt_add_int(data->inits.h_c, int_part);
 	}
 
 	if (data->viewport.y && !flip_vert_scan_dir) {
 		int int_part;
 
-		data->inits.v = dal_fixed31_32_add(data->inits.v, dal_fixed31_32_mul_int(
+		data->inits.v = dc_fixpt_add(data->inits.v, dc_fixpt_mul_int(
 				data->ratios.vert, recout_skip->height));
-		int_part = dal_fixed31_32_floor(data->inits.v) - data->viewport.y;
+		int_part = dc_fixpt_floor(data->inits.v) - data->viewport.y;
 		if (int_part < data->taps.v_taps) {
 			int int_adj = data->viewport.y >= (data->taps.v_taps - int_part) ?
 						(data->taps.v_taps - int_part) : data->viewport.y;
@@ -794,15 +807,15 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 			int_part = data->taps.v_taps;
 		}
 		data->inits.v.value &= 0xffffffff;
-		data->inits.v = dal_fixed31_32_add_int(data->inits.v, int_part);
+		data->inits.v = dc_fixpt_add_int(data->inits.v, int_part);
 	}
 
 	if (data->viewport_c.y && !flip_vert_scan_dir) {
 		int int_part;
 
-		data->inits.v_c = dal_fixed31_32_add(data->inits.v_c, dal_fixed31_32_mul_int(
+		data->inits.v_c = dc_fixpt_add(data->inits.v_c, dc_fixpt_mul_int(
 				data->ratios.vert_c, recout_skip->height));
-		int_part = dal_fixed31_32_floor(data->inits.v_c) - data->viewport_c.y;
+		int_part = dc_fixpt_floor(data->inits.v_c) - data->viewport_c.y;
 		if (int_part < data->taps.v_taps_c) {
 			int int_adj = data->viewport_c.y >= (data->taps.v_taps_c - int_part) ?
 					(data->taps.v_taps_c - int_part) : data->viewport_c.y;
@@ -815,12 +828,12 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 			int_part = data->taps.v_taps_c;
 		}
 		data->inits.v_c.value &= 0xffffffff;
-		data->inits.v_c = dal_fixed31_32_add_int(data->inits.v_c, int_part);
+		data->inits.v_c = dc_fixpt_add_int(data->inits.v_c, int_part);
 	}
 
 	/* Interlaced inits based on final vert inits */
-	data->inits.v_bot = dal_fixed31_32_add(data->inits.v, data->ratios.vert);
-	data->inits.v_c_bot = dal_fixed31_32_add(data->inits.v_c, data->ratios.vert_c);
+	data->inits.v_bot = dc_fixpt_add(data->inits.v, data->ratios.vert);
+	data->inits.v_c_bot = dc_fixpt_add(data->inits.v_c, data->ratios.vert_c);
 
 	if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_90 ||
 			pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270) {
@@ -835,7 +848,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	struct dc_crtc_timing *timing = &pipe_ctx->stream->timing;
 	struct view recout_skip = { 0 };
 	bool res = false;
-	struct dc_context *ctx = pipe_ctx->stream->ctx;
+	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 	/* Important: scaling ratio calculation requires pixel format,
 	 * lb depth calculation requires recout and taps require scaling ratios.
 	 * Inits require viewport, taps, ratios and recout of split pipe
@@ -843,6 +856,9 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_res.scl_data.format = convert_pixel_format_to_dalsurface(
 			pipe_ctx->plane_state->format);
 
+	if (pipe_ctx->stream->timing.flags.INTERLACE)
+		pipe_ctx->stream->dst.height *= 2;
+
 	calculate_scaling_ratios(pipe_ctx);
 
 	calculate_viewport(pipe_ctx);
@@ -863,6 +879,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 
 	pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable + timing->h_border_left + timing->h_border_right;
 	pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
+	if (pipe_ctx->stream->timing.flags.INTERLACE)
+		pipe_ctx->plane_res.scl_data.v_active *= 2;
 
 
 	/* Taps calculations */
@@ -908,6 +926,9 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 				plane_state->dst_rect.x,
 				plane_state->dst_rect.y);
 
+	if (pipe_ctx->stream->timing.flags.INTERLACE)
+		pipe_ctx->stream->dst.height /= 2;
+
 	return res;
 }
 
@@ -1294,6 +1315,19 @@ bool dc_add_all_planes_for_stream(
 }
 
 
+static bool is_hdr_static_meta_changed(struct dc_stream_state *cur_stream,
+	struct dc_stream_state *new_stream)
+{
+	if (cur_stream == NULL)
+		return true;
+
+	if (memcmp(&cur_stream->hdr_static_metadata,
+			&new_stream->hdr_static_metadata,
+			sizeof(struct dc_info_packet)) != 0)
+		return true;
+
+	return false;
+}
 
 static bool is_timing_changed(struct dc_stream_state *cur_stream,
 		struct dc_stream_state *new_stream)
@@ -1329,6 +1363,9 @@ static bool are_stream_backends_same(
 	if (is_timing_changed(stream_a, stream_b))
 		return false;
 
+	if (is_hdr_static_meta_changed(stream_a, stream_b))
+		return false;
+
 	return true;
 }
 
@@ -1599,18 +1636,6 @@ enum dc_status dc_remove_stream_from_ctx(
 	return DC_OK;
 }
 
-static void copy_pipe_ctx(
-	const struct pipe_ctx *from_pipe_ctx, struct pipe_ctx *to_pipe_ctx)
-{
-	struct dc_plane_state *plane_state = to_pipe_ctx->plane_state;
-	struct dc_stream_state *stream = to_pipe_ctx->stream;
-
-	*to_pipe_ctx = *from_pipe_ctx;
-	to_pipe_ctx->stream = stream;
-	if (plane_state != NULL)
-		to_pipe_ctx->plane_state = plane_state;
-}
-
 static struct dc_stream_state *find_pll_sharable_stream(
 		struct dc_stream_state *stream_needs_pll,
 		struct dc_state *context)
@@ -1703,7 +1728,7 @@ enum dc_status resource_map_pool_resources(
 		pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 #endif
 
-	if (pipe_idx < 0)
+	if (pipe_idx < 0 || context->res_ctx.pipe_ctx[pipe_idx].stream_res.tg == NULL)
 		return DC_NO_CONTROLLER_RESOURCE;
 
 	pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx];
@@ -1752,26 +1777,6 @@ enum dc_status resource_map_pool_resources(
 	return DC_ERROR_UNEXPECTED;
 }
 
-/* first stream in the context is used to populate the rest */
-void validate_guaranteed_copy_streams(
-		struct dc_state *context,
-		int max_streams)
-{
-	int i;
-
-	for (i = 1; i < max_streams; i++) {
-		context->streams[i] = context->streams[0];
-
-		copy_pipe_ctx(&context->res_ctx.pipe_ctx[0],
-			      &context->res_ctx.pipe_ctx[i]);
-		context->res_ctx.pipe_ctx[i].stream =
-				context->res_ctx.pipe_ctx[0].stream;
-
-		dc_stream_retain(context->streams[i]);
-		context->stream_count++;
-	}
-}
-
 void dc_resource_state_copy_construct_current(
 		const struct dc *dc,
 		struct dc_state *dst_ctx)
@@ -1798,9 +1803,9 @@ enum dc_status dc_validate_global_state(
 		return DC_ERROR_UNEXPECTED;
 
 	if (dc->res_pool->funcs->validate_global) {
-			result = dc->res_pool->funcs->validate_global(dc, new_ctx);
-			if (result != DC_OK)
-				return result;
+		result = dc->res_pool->funcs->validate_global(dc, new_ctx);
+		if (result != DC_OK)
+			return result;
 	}
 
 	for (i = 0; i < new_ctx->stream_count; i++) {
@@ -1843,7 +1848,7 @@ enum dc_status dc_validate_global_state(
 }
 
 static void patch_gamut_packet_checksum(
-		struct encoder_info_packet *gamut_packet)
+		struct dc_info_packet *gamut_packet)
 {
 	/* For gamut we recalc checksum */
 	if (gamut_packet->valid) {
@@ -1862,12 +1867,11 @@ static void patch_gamut_packet_checksum(
 }
 
 static void set_avi_info_frame(
-		struct encoder_info_packet *info_packet,
+		struct dc_info_packet *info_packet,
 		struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	enum dc_color_space color_space = COLOR_SPACE_UNKNOWN;
-	struct info_frame info_frame = { {0} };
 	uint32_t pixel_encoding = 0;
 	enum scanning_type scan_type = SCANNING_TYPE_NODATA;
 	enum dc_aspect_ratio aspect = ASPECT_RATIO_NO_DATA;
@@ -1877,22 +1881,24 @@ static void set_avi_info_frame(
 	unsigned int cn0_cn1_value = 0;
 	uint8_t *check_sum = NULL;
 	uint8_t byte_index = 0;
-	union hdmi_info_packet *hdmi_info = &info_frame.avi_info_packet.info_packet_hdmi;
+	union hdmi_info_packet hdmi_info;
 	union display_content_support support = {0};
 	unsigned int vic = pipe_ctx->stream->timing.vic;
 	enum dc_timing_3d_format format;
 
+	memset(&hdmi_info, 0, sizeof(union hdmi_info_packet));
+
 	color_space = pipe_ctx->stream->output_color_space;
 	if (color_space == COLOR_SPACE_UNKNOWN)
 		color_space = (stream->timing.pixel_encoding == PIXEL_ENCODING_RGB) ?
 			COLOR_SPACE_SRGB:COLOR_SPACE_YCBCR709;
 
 	/* Initialize header */
-	hdmi_info->bits.header.info_frame_type = HDMI_INFOFRAME_TYPE_AVI;
+	hdmi_info.bits.header.info_frame_type = HDMI_INFOFRAME_TYPE_AVI;
 	/* InfoFrameVersion_3 is defined by CEA861F (Section 6.4), but shall
 	* not be used in HDMI 2.0 (Section 10.1) */
-	hdmi_info->bits.header.version = 2;
-	hdmi_info->bits.header.length = HDMI_AVI_INFOFRAME_SIZE;
+	hdmi_info.bits.header.version = 2;
+	hdmi_info.bits.header.length = HDMI_AVI_INFOFRAME_SIZE;
 
 	/*
 	 * IDO-defined (Y2,Y1,Y0 = 1,1,1) shall not be used by devices built
@@ -1918,39 +1924,39 @@ static void set_avi_info_frame(
 
 	/* Y0_Y1_Y2 : The pixel encoding */
 	/* H14b AVI InfoFrame has extension on Y-field from 2 bits to 3 bits */
-	hdmi_info->bits.Y0_Y1_Y2 = pixel_encoding;
+	hdmi_info.bits.Y0_Y1_Y2 = pixel_encoding;
 
 	/* A0 = 1 Active Format Information valid */
-	hdmi_info->bits.A0 = ACTIVE_FORMAT_VALID;
+	hdmi_info.bits.A0 = ACTIVE_FORMAT_VALID;
 
 	/* B0, B1 = 3; Bar info data is valid */
-	hdmi_info->bits.B0_B1 = BAR_INFO_BOTH_VALID;
+	hdmi_info.bits.B0_B1 = BAR_INFO_BOTH_VALID;
 
-	hdmi_info->bits.SC0_SC1 = PICTURE_SCALING_UNIFORM;
+	hdmi_info.bits.SC0_SC1 = PICTURE_SCALING_UNIFORM;
 
 	/* S0, S1 : Underscan / Overscan */
 	/* TODO: un-hardcode scan type */
 	scan_type = SCANNING_TYPE_UNDERSCAN;
-	hdmi_info->bits.S0_S1 = scan_type;
+	hdmi_info.bits.S0_S1 = scan_type;
 
 	/* C0, C1 : Colorimetry */
 	if (color_space == COLOR_SPACE_YCBCR709 ||
 			color_space == COLOR_SPACE_YCBCR709_LIMITED)
-		hdmi_info->bits.C0_C1 = COLORIMETRY_ITU709;
+		hdmi_info.bits.C0_C1 = COLORIMETRY_ITU709;
 	else if (color_space == COLOR_SPACE_YCBCR601 ||
 			color_space == COLOR_SPACE_YCBCR601_LIMITED)
-		hdmi_info->bits.C0_C1 = COLORIMETRY_ITU601;
+		hdmi_info.bits.C0_C1 = COLORIMETRY_ITU601;
 	else {
-		hdmi_info->bits.C0_C1 = COLORIMETRY_NO_DATA;
+		hdmi_info.bits.C0_C1 = COLORIMETRY_NO_DATA;
 	}
 	if (color_space == COLOR_SPACE_2020_RGB_FULLRANGE ||
 			color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE ||
 			color_space == COLOR_SPACE_2020_YCBCR) {
-		hdmi_info->bits.EC0_EC2 = COLORIMETRYEX_BT2020RGBYCBCR;
-		hdmi_info->bits.C0_C1   = COLORIMETRY_EXTENDED;
+		hdmi_info.bits.EC0_EC2 = COLORIMETRYEX_BT2020RGBYCBCR;
+		hdmi_info.bits.C0_C1   = COLORIMETRY_EXTENDED;
 	} else if (color_space == COLOR_SPACE_ADOBERGB) {
-		hdmi_info->bits.EC0_EC2 = COLORIMETRYEX_ADOBERGB;
-		hdmi_info->bits.C0_C1   = COLORIMETRY_EXTENDED;
+		hdmi_info.bits.EC0_EC2 = COLORIMETRYEX_ADOBERGB;
+		hdmi_info.bits.C0_C1   = COLORIMETRY_EXTENDED;
 	}
 
 	/* TODO: un-hardcode aspect ratio */
@@ -1959,18 +1965,18 @@ static void set_avi_info_frame(
 	switch (aspect) {
 	case ASPECT_RATIO_4_3:
 	case ASPECT_RATIO_16_9:
-		hdmi_info->bits.M0_M1 = aspect;
+		hdmi_info.bits.M0_M1 = aspect;
 		break;
 
 	case ASPECT_RATIO_NO_DATA:
 	case ASPECT_RATIO_64_27:
 	case ASPECT_RATIO_256_135:
 	default:
-		hdmi_info->bits.M0_M1 = 0;
+		hdmi_info.bits.M0_M1 = 0;
 	}
 
 	/* Active Format Aspect ratio - same as Picture Aspect Ratio. */
-	hdmi_info->bits.R0_R3 = ACTIVE_FORMAT_ASPECT_RATIO_SAME_AS_PICTURE;
+	hdmi_info.bits.R0_R3 = ACTIVE_FORMAT_ASPECT_RATIO_SAME_AS_PICTURE;
 
 	/* TODO: un-hardcode cn0_cn1 and itc */
 
@@ -2013,8 +2019,8 @@ static void set_avi_info_frame(
 				}
 			}
 		}
-		hdmi_info->bits.CN0_CN1 = cn0_cn1_value;
-		hdmi_info->bits.ITC = itc_value;
+		hdmi_info.bits.CN0_CN1 = cn0_cn1_value;
+		hdmi_info.bits.ITC = itc_value;
 	}
 
 	/* TODO : We should handle YCC quantization */
@@ -2023,19 +2029,19 @@ static void set_avi_info_frame(
 			stream->sink->edid_caps.qy_bit == 1) {
 		if (color_space == COLOR_SPACE_SRGB ||
 			color_space == COLOR_SPACE_2020_RGB_FULLRANGE) {
-			hdmi_info->bits.Q0_Q1   = RGB_QUANTIZATION_FULL_RANGE;
-			hdmi_info->bits.YQ0_YQ1 = YYC_QUANTIZATION_FULL_RANGE;
+			hdmi_info.bits.Q0_Q1   = RGB_QUANTIZATION_FULL_RANGE;
+			hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_FULL_RANGE;
 		} else if (color_space == COLOR_SPACE_SRGB_LIMITED ||
 					color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE) {
-			hdmi_info->bits.Q0_Q1   = RGB_QUANTIZATION_LIMITED_RANGE;
-			hdmi_info->bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE;
+			hdmi_info.bits.Q0_Q1   = RGB_QUANTIZATION_LIMITED_RANGE;
+			hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE;
 		} else {
-			hdmi_info->bits.Q0_Q1   = RGB_QUANTIZATION_DEFAULT_RANGE;
-			hdmi_info->bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE;
+			hdmi_info.bits.Q0_Q1   = RGB_QUANTIZATION_DEFAULT_RANGE;
+			hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE;
 		}
 	} else {
-		hdmi_info->bits.Q0_Q1   = RGB_QUANTIZATION_DEFAULT_RANGE;
-		hdmi_info->bits.YQ0_YQ1   = YYC_QUANTIZATION_LIMITED_RANGE;
+		hdmi_info.bits.Q0_Q1   = RGB_QUANTIZATION_DEFAULT_RANGE;
+		hdmi_info.bits.YQ0_YQ1   = YYC_QUANTIZATION_LIMITED_RANGE;
 	}
 
 	///VIC
@@ -2060,51 +2066,49 @@ static void set_avi_info_frame(
 			break;
 		}
 	}
-	hdmi_info->bits.VIC0_VIC7 = vic;
+	hdmi_info.bits.VIC0_VIC7 = vic;
 
 	/* pixel repetition
 	 * PR0 - PR3 start from 0 whereas pHwPathMode->mode.timing.flags.pixel
 	 * repetition start from 1 */
-	hdmi_info->bits.PR0_PR3 = 0;
+	hdmi_info.bits.PR0_PR3 = 0;
 
 	/* Bar Info
 	 * barTop:    Line Number of End of Top Bar.
 	 * barBottom: Line Number of Start of Bottom Bar.
 	 * barLeft:   Pixel Number of End of Left Bar.
 	 * barRight:  Pixel Number of Start of Right Bar. */
-	hdmi_info->bits.bar_top = stream->timing.v_border_top;
-	hdmi_info->bits.bar_bottom = (stream->timing.v_total
+	hdmi_info.bits.bar_top = stream->timing.v_border_top;
+	hdmi_info.bits.bar_bottom = (stream->timing.v_total
 			- stream->timing.v_border_bottom + 1);
-	hdmi_info->bits.bar_left  = stream->timing.h_border_left;
-	hdmi_info->bits.bar_right = (stream->timing.h_total
+	hdmi_info.bits.bar_left  = stream->timing.h_border_left;
+	hdmi_info.bits.bar_right = (stream->timing.h_total
 			- stream->timing.h_border_right + 1);
 
 	/* check_sum - Calculate AFMT_AVI_INFO0 ~ AFMT_AVI_INFO3 */
-	check_sum = &info_frame.avi_info_packet.info_packet_hdmi.packet_raw_data.sb[0];
+	check_sum = &hdmi_info.packet_raw_data.sb[0];
 
 	*check_sum = HDMI_INFOFRAME_TYPE_AVI + HDMI_AVI_INFOFRAME_SIZE + 2;
 
 	for (byte_index = 1; byte_index <= HDMI_AVI_INFOFRAME_SIZE; byte_index++)
-		*check_sum += hdmi_info->packet_raw_data.sb[byte_index];
+		*check_sum += hdmi_info.packet_raw_data.sb[byte_index];
 
 	/* one byte complement */
 	*check_sum = (uint8_t) (0x100 - *check_sum);
 
 	/* Store in hw_path_mode */
-	info_packet->hb0 = hdmi_info->packet_raw_data.hb0;
-	info_packet->hb1 = hdmi_info->packet_raw_data.hb1;
-	info_packet->hb2 = hdmi_info->packet_raw_data.hb2;
+	info_packet->hb0 = hdmi_info.packet_raw_data.hb0;
+	info_packet->hb1 = hdmi_info.packet_raw_data.hb1;
+	info_packet->hb2 = hdmi_info.packet_raw_data.hb2;
 
-	for (byte_index = 0; byte_index < sizeof(info_frame.avi_info_packet.
-				info_packet_hdmi.packet_raw_data.sb); byte_index++)
-		info_packet->sb[byte_index] = info_frame.avi_info_packet.
-				info_packet_hdmi.packet_raw_data.sb[byte_index];
+	for (byte_index = 0; byte_index < sizeof(hdmi_info.packet_raw_data.sb); byte_index++)
+		info_packet->sb[byte_index] = hdmi_info.packet_raw_data.sb[byte_index];
 
 	info_packet->valid = true;
 }
 
 static void set_vendor_info_packet(
-		struct encoder_info_packet *info_packet,
+		struct dc_info_packet *info_packet,
 		struct dc_stream_state *stream)
 {
 	uint32_t length = 0;
@@ -2217,7 +2221,7 @@ static void set_vendor_info_packet(
 }
 
 static void set_spd_info_packet(
-		struct encoder_info_packet *info_packet,
+		struct dc_info_packet *info_packet,
 		struct dc_stream_state *stream)
 {
 	/* SPD info packet for FreeSync */
@@ -2338,104 +2342,19 @@ static void set_spd_info_packet(
 }
 
 static void set_hdr_static_info_packet(
-		struct encoder_info_packet *info_packet,
+		struct dc_info_packet *info_packet,
 		struct dc_stream_state *stream)
 {
-	uint16_t i = 0;
-	enum signal_type signal = stream->signal;
-	uint32_t data;
+	/* HDR Static Metadata info packet for HDR10 */
 
-	if (!stream->hdr_static_metadata.hdr_supported)
+	if (!stream->hdr_static_metadata.valid)
 		return;
 
-	if (dc_is_hdmi_signal(signal)) {
-		info_packet->valid = true;
-
-		info_packet->hb0 = 0x87;
-		info_packet->hb1 = 0x01;
-		info_packet->hb2 = 0x1A;
-		i = 1;
-	} else if (dc_is_dp_signal(signal)) {
-		info_packet->valid = true;
-
-		info_packet->hb0 = 0x00;
-		info_packet->hb1 = 0x87;
-		info_packet->hb2 = 0x1D;
-		info_packet->hb3 = (0x13 << 2);
-		i = 2;
-	}
-
-	data = stream->hdr_static_metadata.is_hdr;
-	info_packet->sb[i++] = data ? 0x02 : 0x00;
-	info_packet->sb[i++] = 0x00;
-
-	data = stream->hdr_static_metadata.chromaticity_green_x / 2;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.chromaticity_green_y / 2;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.chromaticity_blue_x / 2;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.chromaticity_blue_y / 2;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.chromaticity_red_x / 2;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.chromaticity_red_y / 2;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.chromaticity_white_point_x / 2;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.chromaticity_white_point_y / 2;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.max_luminance;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.min_luminance;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.maximum_content_light_level;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	data = stream->hdr_static_metadata.maximum_frame_average_light_level;
-	info_packet->sb[i++] = data & 0xFF;
-	info_packet->sb[i++] = (data & 0xFF00) >> 8;
-
-	if (dc_is_hdmi_signal(signal)) {
-		uint32_t checksum = 0;
-
-		checksum += info_packet->hb0;
-		checksum += info_packet->hb1;
-		checksum += info_packet->hb2;
-
-		for (i = 1; i <= info_packet->hb2; i++)
-			checksum += info_packet->sb[i];
-
-		info_packet->sb[0] = 0x100 - checksum;
-	} else if (dc_is_dp_signal(signal)) {
-		info_packet->sb[0] = 0x01;
-		info_packet->sb[1] = 0x1A;
-	}
+	*info_packet = stream->hdr_static_metadata;
 }
 
 static void set_vsc_info_packet(
-		struct encoder_info_packet *info_packet,
+		struct dc_info_packet *info_packet,
 		struct dc_stream_state *stream)
 {
 	unsigned int vscPacketRevision = 0;
@@ -2650,6 +2569,8 @@ bool pipe_need_reprogram(
 	if (is_timing_changed(pipe_ctx_old->stream, pipe_ctx->stream))
 		return true;
 
+	if (is_hdr_static_meta_changed(pipe_ctx_old->stream, pipe_ctx->stream))
+		return true;
 
 	return false;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index ce0747ed0f00..3732a1de9d6c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -101,14 +101,16 @@ static void construct(struct dc_stream_state *stream,
 	stream->status.link = stream->sink->link;
 
 	update_stream_signal(stream);
+
+	stream->out_transfer_func = dc_create_transfer_func();
+	stream->out_transfer_func->type = TF_TYPE_BYPASS;
 }
 
 static void destruct(struct dc_stream_state *stream)
 {
 	dc_sink_release(stream->sink);
 	if (stream->out_transfer_func != NULL) {
-		dc_transfer_func_release(
-				stream->out_transfer_func);
+		dc_transfer_func_release(stream->out_transfer_func);
 		stream->out_transfer_func = NULL;
 	}
 }
@@ -176,6 +178,7 @@ bool dc_stream_set_cursor_attributes(
 	int i;
 	struct dc  *core_dc;
 	struct resource_context *res_ctx;
+	struct pipe_ctx *pipe_to_program = NULL;
 
 	if (NULL == stream) {
 		dm_error("DC: dc_stream is NULL!\n");
@@ -203,9 +206,17 @@ bool dc_stream_set_cursor_attributes(
 		if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state)
 			continue;
 
+		if (!pipe_to_program) {
+			pipe_to_program = pipe_ctx;
+			core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, true);
+		}
 
 		core_dc->hwss.set_cursor_attribute(pipe_ctx);
 	}
+
+	if (pipe_to_program)
+		core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, false);
+
 	return true;
 }
 
@@ -216,6 +227,7 @@ bool dc_stream_set_cursor_position(
 	int i;
 	struct dc  *core_dc;
 	struct resource_context *res_ctx;
+	struct pipe_ctx *pipe_to_program = NULL;
 
 	if (NULL == stream) {
 		dm_error("DC: dc_stream is NULL!\n");
@@ -241,9 +253,17 @@ bool dc_stream_set_cursor_position(
 				!pipe_ctx->plane_res.ipp)
 			continue;
 
+		if (!pipe_to_program) {
+			pipe_to_program = pipe_ctx;
+			core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, true);
+		}
+
 		core_dc->hwss.set_cursor_position(pipe_ctx);
 	}
 
+	if (pipe_to_program)
+		core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, false);
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index ade5b8ee9c3c..68a71adeb12e 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -38,6 +38,12 @@
 static void construct(struct dc_context *ctx, struct dc_plane_state *plane_state)
 {
 	plane_state->ctx = ctx;
+
+	plane_state->gamma_correction = dc_create_gamma();
+	plane_state->gamma_correction->is_identity = true;
+
+	plane_state->in_transfer_func = dc_create_transfer_func();
+	plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
 }
 
 static void destruct(struct dc_plane_state *plane_state)
@@ -66,8 +72,8 @@ struct dc_plane_state *dc_create_plane_state(struct dc *dc)
 {
 	struct dc *core_dc = dc;
 
-	struct dc_plane_state *plane_state = kzalloc(sizeof(*plane_state),
-						     GFP_KERNEL);
+	struct dc_plane_state *plane_state = kvzalloc(sizeof(*plane_state),
+						      GFP_KERNEL);
 
 	if (NULL == plane_state)
 		return NULL;
@@ -120,7 +126,7 @@ static void dc_plane_state_free(struct kref *kref)
 {
 	struct dc_plane_state *plane_state = container_of(kref, struct dc_plane_state, refcount);
 	destruct(plane_state);
-	kfree(plane_state);
+	kvfree(plane_state);
 }
 
 void dc_plane_state_release(struct dc_plane_state *plane_state)
@@ -136,7 +142,7 @@ void dc_gamma_retain(struct dc_gamma *gamma)
 static void dc_gamma_free(struct kref *kref)
 {
 	struct dc_gamma *gamma = container_of(kref, struct dc_gamma, refcount);
-	kfree(gamma);
+	kvfree(gamma);
 }
 
 void dc_gamma_release(struct dc_gamma **gamma)
@@ -147,7 +153,7 @@ void dc_gamma_release(struct dc_gamma **gamma)
 
 struct dc_gamma *dc_create_gamma(void)
 {
-	struct dc_gamma *gamma = kzalloc(sizeof(*gamma), GFP_KERNEL);
+	struct dc_gamma *gamma = kvzalloc(sizeof(*gamma), GFP_KERNEL);
 
 	if (gamma == NULL)
 		goto alloc_fail;
@@ -167,7 +173,7 @@ void dc_transfer_func_retain(struct dc_transfer_func *tf)
 static void dc_transfer_func_free(struct kref *kref)
 {
 	struct dc_transfer_func *tf = container_of(kref, struct dc_transfer_func, refcount);
-	kfree(tf);
+	kvfree(tf);
 }
 
 void dc_transfer_func_release(struct dc_transfer_func *tf)
@@ -175,9 +181,9 @@ void dc_transfer_func_release(struct dc_transfer_func *tf)
 	kref_put(&tf->refcount, dc_transfer_func_free);
 }
 
-struct dc_transfer_func *dc_create_transfer_func(void)
+struct dc_transfer_func *dc_create_transfer_func()
 {
-	struct dc_transfer_func *tf = kzalloc(sizeof(*tf), GFP_KERNEL);
+	struct dc_transfer_func *tf = kvzalloc(sizeof(*tf), GFP_KERNEL);
 
 	if (tf == NULL)
 		goto alloc_fail;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index fa4b3c8b3bb7..9cfde0ccf4e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.38"
+#define DC_VER "3.1.44"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
@@ -75,6 +75,7 @@ struct dc_caps {
 	bool dynamic_audio;
 	bool is_apu;
 	bool dual_link_dvi;
+	bool post_blend_color_processing;
 };
 
 struct dc_dcc_surface_param {
@@ -202,6 +203,8 @@ struct dc_debug {
 	bool timing_trace;
 	bool clock_trace;
 	bool validation_trace;
+	bool bandwidth_calcs_trace;
+	int max_downscale_src_width;
 
 	/* stutter efficiency related */
 	bool disable_stutter;
@@ -238,6 +241,8 @@ struct dc_debug {
 	bool az_endpoint_mute_only;
 	bool always_use_regamma;
 	bool p010_mpo_support;
+	bool recovery_enabled;
+
 };
 struct dc_state;
 struct resource_pool;
@@ -332,20 +337,6 @@ enum {
 	TRANSFER_FUNC_POINTS = 1025
 };
 
-// Moved here from color module for linux
-enum color_transfer_func {
-	transfer_func_unknown,
-	transfer_func_srgb,
-	transfer_func_bt709,
-	transfer_func_pq2084,
-	transfer_func_pq2084_interim,
-	transfer_func_linear_0_1,
-	transfer_func_linear_0_125,
-	transfer_func_dolbyvision,
-	transfer_func_gamma_22,
-	transfer_func_gamma_26
-};
-
 struct dc_hdr_static_metadata {
 	/* display chromaticities and white point in units of 0.00001 */
 	unsigned int chromaticity_green_x;
@@ -361,9 +352,6 @@ struct dc_hdr_static_metadata {
 	uint32_t max_luminance;
 	uint32_t maximum_content_light_level;
 	uint32_t maximum_frame_average_light_level;
-
-	bool hdr_supported;
-	bool is_hdr;
 };
 
 enum dc_transfer_func_type {
@@ -419,7 +407,6 @@ union surface_update_flags {
 		/* Medium updates */
 		uint32_t dcc_change:1;
 		uint32_t color_space_change:1;
-		uint32_t input_tf_change:1;
 		uint32_t horizontal_mirror_change:1;
 		uint32_t per_pixel_alpha_change:1;
 		uint32_t rotation_change:1;
@@ -428,6 +415,7 @@ union surface_update_flags {
 		uint32_t position_change:1;
 		uint32_t in_transfer_func_change:1;
 		uint32_t input_csc_change:1;
+		uint32_t coeff_reduction_change:1;
 		uint32_t output_tf_change:1;
 		uint32_t pixel_format_change:1;
 
@@ -460,7 +448,7 @@ struct dc_plane_state {
 	struct dc_gamma *gamma_correction;
 	struct dc_transfer_func *in_transfer_func;
 	struct dc_bias_and_scale *bias_and_scale;
-	struct csc_transform input_csc_color_matrix;
+	struct dc_csc_transform input_csc_color_matrix;
 	struct fixed31_32 coeff_reduction_factor;
 	uint32_t sdr_white_level;
 
@@ -468,7 +456,6 @@ struct dc_plane_state {
 	struct dc_hdr_static_metadata hdr_static_ctx;
 
 	enum dc_color_space color_space;
-	enum color_transfer_func input_tf;
 
 	enum surface_pixel_format format;
 	enum dc_rotation_angle rotation;
@@ -498,7 +485,6 @@ struct dc_plane_info {
 	enum dc_rotation_angle rotation;
 	enum plane_stereo_format stereo_format;
 	enum dc_color_space color_space;
-	enum color_transfer_func input_tf;
 	unsigned int sdr_white_level;
 	bool horizontal_mirror;
 	bool visible;
@@ -517,19 +503,18 @@ struct dc_surface_update {
 	struct dc_plane_state *surface;
 
 	/* isr safe update parameters.  null means no updates */
-	struct dc_flip_addrs *flip_addr;
-	struct dc_plane_info *plane_info;
-	struct dc_scaling_info *scaling_info;
+	const struct dc_flip_addrs *flip_addr;
+	const struct dc_plane_info *plane_info;
+	const struct dc_scaling_info *scaling_info;
 
 	/* following updates require alloc/sleep/spin that is not isr safe,
 	 * null means no updates
 	 */
-	struct dc_gamma *gamma;
-	enum color_transfer_func color_input_tf;
-	struct dc_transfer_func *in_transfer_func;
+	const struct dc_gamma *gamma;
+	const struct dc_transfer_func *in_transfer_func;
 
-	struct csc_transform *input_csc_color_matrix;
-	struct fixed31_32 *coeff_reduction_factor;
+	const struct dc_csc_transform *input_csc_color_matrix;
+	const struct fixed31_32 *coeff_reduction_factor;
 };
 
 /*
@@ -699,6 +684,7 @@ struct dc_cursor {
 	struct dc_cursor_attributes attributes;
 };
 
+
 /*******************************************************************************
  * Interrupt interfaces
  ******************************************************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 2726b02e006b..90bccd5ccaa2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -26,6 +26,8 @@
 #ifndef DC_DP_TYPES_H
 #define DC_DP_TYPES_H
 
+#include "os_types.h"
+
 enum dc_lane_count {
 	LANE_COUNT_UNKNOWN = 0,
 	LANE_COUNT_ONE = 1,
diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index 48e1fcf53d43..bd0fda0ceb91 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -117,6 +117,65 @@ uint32_t generic_reg_get5(const struct dc_context *ctx, uint32_t addr,
 	return reg_val;
 }
 
+uint32_t generic_reg_get6(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	*field_value4 = get_reg_field_value_ex(reg_val, mask4, shift4);
+	*field_value5 = get_reg_field_value_ex(reg_val, mask5, shift5);
+	*field_value6 = get_reg_field_value_ex(reg_val, mask6, shift6);
+	return reg_val;
+}
+
+uint32_t generic_reg_get7(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
+		uint8_t shift7, uint32_t mask7, uint32_t *field_value7)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	*field_value4 = get_reg_field_value_ex(reg_val, mask4, shift4);
+	*field_value5 = get_reg_field_value_ex(reg_val, mask5, shift5);
+	*field_value6 = get_reg_field_value_ex(reg_val, mask6, shift6);
+	*field_value7 = get_reg_field_value_ex(reg_val, mask7, shift7);
+	return reg_val;
+}
+
+uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
+		uint8_t shift7, uint32_t mask7, uint32_t *field_value7,
+		uint8_t shift8, uint32_t mask8, uint32_t *field_value8)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	*field_value4 = get_reg_field_value_ex(reg_val, mask4, shift4);
+	*field_value5 = get_reg_field_value_ex(reg_val, mask5, shift5);
+	*field_value6 = get_reg_field_value_ex(reg_val, mask6, shift6);
+	*field_value7 = get_reg_field_value_ex(reg_val, mask7, shift7);
+	*field_value8 = get_reg_field_value_ex(reg_val, mask8, shift8);
+	return reg_val;
+}
 /* note:  va version of this is pretty bad idea, since there is a output parameter pass by pointer
  * compiler won't be able to check for size match and is prone to stack corruption type of bugs
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index b83a7dc2f5a9..b1f70579d61b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -423,6 +423,11 @@ enum dc_gamma_type {
 	GAMMA_CS_TFM_1D = 3,
 };
 
+struct dc_csc_transform {
+	uint16_t matrix[12];
+	bool enable_adjustment;
+};
+
 struct dc_gamma {
 	struct kref refcount;
 	enum dc_gamma_type type;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index dc34515ef01f..8a716baa1203 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -51,6 +51,14 @@ struct link_mst_stream_allocation_table {
 	struct link_mst_stream_allocation stream_allocations[MAX_CONTROLLER_NUM];
 };
 
+struct time_stamp {
+	uint64_t edp_poweroff;
+	uint64_t edp_poweron;
+};
+
+struct link_trace {
+	struct time_stamp time_stamp;
+};
 /*
  * A link contains one or more sinks and their connected status.
  * The currently active signal type (HDMI, DP-SST, DP-MST) is also reported.
@@ -114,6 +122,7 @@ struct dc_link {
 
 	struct dc_link_status link_status;
 
+	struct link_trace link_trace;
 };
 
 const struct dc_link_status *dc_link_get_status(const struct dc_link *dc_link);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index d017df56b2ba..d7e6d53bb383 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -58,18 +58,20 @@ struct dc_stream_state {
 
 	struct freesync_context freesync_ctx;
 
-	struct dc_hdr_static_metadata hdr_static_metadata;
+	struct dc_info_packet hdr_static_metadata;
 	struct dc_transfer_func *out_transfer_func;
 	struct colorspace_transform gamut_remap_matrix;
-	struct csc_transform csc_color_matrix;
+	struct dc_csc_transform csc_color_matrix;
 
 	enum dc_color_space output_color_space;
 	enum dc_dither_option dither_option;
 
 	enum view_3d_format view_format;
-	enum color_transfer_func output_tf;
 
 	bool ignore_msa_timing_param;
+
+	unsigned long long periodic_fn_vsync_delta;
+
 	/* TODO: custom INFO packets */
 	/* TODO: ABM info (DMCU) */
 	/* PSR info */
@@ -110,9 +112,10 @@ struct dc_stream_update {
 	struct rect src;
 	struct rect dst;
 	struct dc_transfer_func *out_transfer_func;
-	struct dc_hdr_static_metadata *hdr_static_metadata;
-	enum color_transfer_func color_output_tf;
+	struct dc_info_packet *hdr_static_metadata;
 	unsigned int *abm_level;
+
+	unsigned long long *periodic_fn_vsync_delta;
 };
 
 bool dc_is_stream_unchanged(
@@ -131,13 +134,6 @@ bool dc_is_stream_scaling_unchanged(
  *   This does not trigger a flip.  No surface address is programmed.
  */
 
-bool dc_commit_planes_to_stream(
-		struct dc *dc,
-		struct dc_plane_state **plane_states,
-		uint8_t new_plane_count,
-		struct dc_stream_state *dc_stream,
-		struct dc_state *state);
-
 void dc_commit_updates_for_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates,
 		int surface_count,
@@ -209,14 +205,6 @@ bool dc_add_all_planes_for_stream(
 enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream);
 
 /*
- * This function takes a stream and checks if it is guaranteed to be supported.
- * Guaranteed means that MAX_COFUNC similar streams are supported.
- *
- * After this call:
- *   No hardware is programmed for call.  Only validation is done.
- */
-
-/*
  * Set up streams and links associated to drive sinks
  * The streams parameter is an absolute set of all active streams.
  *
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 9441305d3ab5..76df2534c4a4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -25,7 +25,7 @@
 #ifndef DC_TYPES_H_
 #define DC_TYPES_H_
 
-#include "fixed32_32.h"
+#include "os_types.h"
 #include "fixed31_32.h"
 #include "irq_types.h"
 #include "dc_dp_types.h"
@@ -370,12 +370,6 @@ struct dc_csc_adjustments {
 	struct fixed31_32 hue;
 };
 
-enum {
-	MAX_LANES = 2,
-	MAX_COFUNC_PATH = 6,
-	LAYER_INDEX_PRIMARY = -1,
-};
-
 enum dpcd_downstream_port_max_bpc {
 	DOWN_STREAM_MAX_8BPC = 0,
 	DOWN_STREAM_MAX_10BPC,
@@ -530,6 +524,15 @@ struct vrr_params {
 	uint32_t frame_counter;
 };
 
+struct dc_info_packet {
+	bool valid;
+	uint8_t hb0;
+	uint8_t hb1;
+	uint8_t hb2;
+	uint8_t hb3;
+	uint8_t sb[32];
+};
+
 #define DC_PLANE_UPDATE_TIMES_MAX 10
 
 struct dc_plane_flip_time {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
index fe92a1222803..29294db1a96b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
@@ -26,7 +26,7 @@
 #include "dce_abm.h"
 #include "dm_services.h"
 #include "reg_helper.h"
-#include "fixed32_32.h"
+#include "fixed31_32.h"
 #include "dc.h"
 
 #include "atom.h"
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
index 6d5cdcdc8ec9..7f6d724686f1 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c
@@ -33,8 +33,9 @@
 
 #define CTX \
 	aud->base.ctx
-#define DC_LOGGER \
-	aud->base.ctx->logger
+
+#define DC_LOGGER_INIT()
+
 #define REG(reg)\
 	(aud->regs->reg)
 
@@ -348,8 +349,8 @@ static void set_audio_latency(
 
 void dce_aud_az_enable(struct audio *audio)
 {
-	struct dce_audio *aud = DCE_AUD(audio);
 	uint32_t value = AZ_REG_READ(AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL);
+	DC_LOGGER_INIT();
 
 	set_reg_field_value(value, 1,
 			    AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
@@ -371,7 +372,7 @@ void dce_aud_az_enable(struct audio *audio)
 void dce_aud_az_disable(struct audio *audio)
 {
 	uint32_t value;
-	struct dce_audio *aud = DCE_AUD(audio);
+	DC_LOGGER_INIT();
 
 	value = AZ_REG_READ(AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL);
 	set_reg_field_value(value, 1,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 0aa2cda60890..599c7ab6befe 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -41,8 +41,9 @@
 
 #define CTX \
 	clk_src->base.ctx
-#define DC_LOGGER \
-	calc_pll_cs->ctx->logger
+
+#define DC_LOGGER_INIT()
+
 #undef FN
 #define FN(reg_name, field_name) \
 	clk_src->cs_shift->field_name, clk_src->cs_mask->field_name
@@ -467,7 +468,7 @@ static uint32_t dce110_get_pix_clk_dividers_helper (
 {
 	uint32_t field = 0;
 	uint32_t pll_calc_error = MAX_PLL_CALC_ERROR;
-	struct calc_pll_clock_source *calc_pll_cs = &clk_src->calc_pll;
+	DC_LOGGER_INIT();
 	/* Check if reference clock is external (not pcie/xtalin)
 	* HW Dce80 spec:
 	* 00 - PCIE_REFCLK, 01 - XTALIN,    02 - GENERICA,    03 - GENERICB
@@ -557,8 +558,8 @@ static uint32_t dce110_get_pix_clk_dividers(
 		struct pll_settings *pll_settings)
 {
 	struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(cs);
-	struct calc_pll_clock_source *calc_pll_cs = &clk_src->calc_pll;
 	uint32_t pll_calc_error = MAX_PLL_CALC_ERROR;
+	DC_LOGGER_INIT();
 
 	if (pix_clk_params == NULL || pll_settings == NULL
 			|| pix_clk_params->requested_pix_clk == 0) {
@@ -589,6 +590,7 @@ static uint32_t dce110_get_pix_clk_dividers(
 			pll_settings, pix_clk_params);
 		break;
 	case DCE_VERSION_11_2:
+	case DCE_VERSION_11_22:
 	case DCE_VERSION_12_0:
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 	case DCN_VERSION_1_0:
@@ -655,12 +657,12 @@ static uint32_t dce110_get_d_to_pixel_rate_in_hz(
 			return 0;
 		}
 
-		pix_rate = dal_fixed31_32_from_int(clk_src->ref_freq_khz);
-		pix_rate = dal_fixed31_32_mul_int(pix_rate, 1000);
-		pix_rate = dal_fixed31_32_mul_int(pix_rate, phase);
-		pix_rate = dal_fixed31_32_div_int(pix_rate, modulo);
+		pix_rate = dc_fixpt_from_int(clk_src->ref_freq_khz);
+		pix_rate = dc_fixpt_mul_int(pix_rate, 1000);
+		pix_rate = dc_fixpt_mul_int(pix_rate, phase);
+		pix_rate = dc_fixpt_div_int(pix_rate, modulo);
 
-		return dal_fixed31_32_round(pix_rate);
+		return dc_fixpt_round(pix_rate);
 	} else {
 		return dce110_get_dp_pixel_rate_from_combo_phy_pll(cs, pix_clk_params, pll_settings);
 	}
@@ -709,12 +711,12 @@ static bool calculate_ss(
 		const struct spread_spectrum_data *ss_data,
 		struct delta_sigma_data *ds_data)
 {
-	struct fixed32_32 fb_div;
-	struct fixed32_32 ss_amount;
-	struct fixed32_32 ss_nslip_amount;
-	struct fixed32_32 ss_ds_frac_amount;
-	struct fixed32_32 ss_step_size;
-	struct fixed32_32 modulation_time;
+	struct fixed31_32 fb_div;
+	struct fixed31_32 ss_amount;
+	struct fixed31_32 ss_nslip_amount;
+	struct fixed31_32 ss_ds_frac_amount;
+	struct fixed31_32 ss_step_size;
+	struct fixed31_32 modulation_time;
 
 	if (ds_data == NULL)
 		return false;
@@ -729,42 +731,42 @@ static bool calculate_ss(
 
 	/* compute SS_AMOUNT_FBDIV & SS_AMOUNT_NFRAC_SLIP & SS_AMOUNT_DSFRAC*/
 	/* 6 decimal point support in fractional feedback divider */
-	fb_div  = dal_fixed32_32_from_fraction(
+	fb_div  = dc_fixpt_from_fraction(
 		pll_settings->fract_feedback_divider, 1000000);
-	fb_div = dal_fixed32_32_add_int(fb_div, pll_settings->feedback_divider);
+	fb_div = dc_fixpt_add_int(fb_div, pll_settings->feedback_divider);
 
 	ds_data->ds_frac_amount = 0;
 	/*spreadSpectrumPercentage is in the unit of .01%,
 	 * so have to divided by 100 * 100*/
-	ss_amount = dal_fixed32_32_mul(
-		fb_div, dal_fixed32_32_from_fraction(ss_data->percentage,
+	ss_amount = dc_fixpt_mul(
+		fb_div, dc_fixpt_from_fraction(ss_data->percentage,
 					100 * ss_data->percentage_divider));
-	ds_data->feedback_amount = dal_fixed32_32_floor(ss_amount);
+	ds_data->feedback_amount = dc_fixpt_floor(ss_amount);
 
-	ss_nslip_amount = dal_fixed32_32_sub(ss_amount,
-		dal_fixed32_32_from_int(ds_data->feedback_amount));
-	ss_nslip_amount = dal_fixed32_32_mul_int(ss_nslip_amount, 10);
-	ds_data->nfrac_amount = dal_fixed32_32_floor(ss_nslip_amount);
+	ss_nslip_amount = dc_fixpt_sub(ss_amount,
+		dc_fixpt_from_int(ds_data->feedback_amount));
+	ss_nslip_amount = dc_fixpt_mul_int(ss_nslip_amount, 10);
+	ds_data->nfrac_amount = dc_fixpt_floor(ss_nslip_amount);
 
-	ss_ds_frac_amount = dal_fixed32_32_sub(ss_nslip_amount,
-		dal_fixed32_32_from_int(ds_data->nfrac_amount));
-	ss_ds_frac_amount = dal_fixed32_32_mul_int(ss_ds_frac_amount, 65536);
-	ds_data->ds_frac_amount = dal_fixed32_32_floor(ss_ds_frac_amount);
+	ss_ds_frac_amount = dc_fixpt_sub(ss_nslip_amount,
+		dc_fixpt_from_int(ds_data->nfrac_amount));
+	ss_ds_frac_amount = dc_fixpt_mul_int(ss_ds_frac_amount, 65536);
+	ds_data->ds_frac_amount = dc_fixpt_floor(ss_ds_frac_amount);
 
 	/* compute SS_STEP_SIZE_DSFRAC */
-	modulation_time = dal_fixed32_32_from_fraction(
+	modulation_time = dc_fixpt_from_fraction(
 		pll_settings->reference_freq * 1000,
 		pll_settings->reference_divider * ss_data->modulation_freq_hz);
 
 	if (ss_data->flags.CENTER_SPREAD)
-		modulation_time = dal_fixed32_32_div_int(modulation_time, 4);
+		modulation_time = dc_fixpt_div_int(modulation_time, 4);
 	else
-		modulation_time = dal_fixed32_32_div_int(modulation_time, 2);
+		modulation_time = dc_fixpt_div_int(modulation_time, 2);
 
-	ss_step_size = dal_fixed32_32_div(ss_amount, modulation_time);
+	ss_step_size = dc_fixpt_div(ss_amount, modulation_time);
 	/* SS_STEP_SIZE_DSFRAC_DEC = Int(SS_STEP_SIZE * 2 ^ 16 * 10)*/
-	ss_step_size = dal_fixed32_32_mul_int(ss_step_size, 65536 * 10);
-	ds_data->ds_frac_size =  dal_fixed32_32_floor(ss_step_size);
+	ss_step_size = dc_fixpt_mul_int(ss_step_size, 65536 * 10);
+	ds_data->ds_frac_size =  dc_fixpt_floor(ss_step_size);
 
 	return true;
 }
@@ -978,6 +980,7 @@ static bool dce110_program_pix_clk(
 
 		break;
 	case DCE_VERSION_11_2:
+	case DCE_VERSION_11_22:
 	case DCE_VERSION_12_0:
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 	case DCN_VERSION_1_0:
@@ -1054,7 +1057,7 @@ static void get_ss_info_from_atombios(
 	struct spread_spectrum_info *ss_info_cur;
 	struct spread_spectrum_data *ss_data_cur;
 	uint32_t i;
-	struct calc_pll_clock_source *calc_pll_cs = &clk_src->calc_pll;
+	DC_LOGGER_INIT();
 	if (ss_entries_num == NULL) {
 		DC_LOG_SYNC(
 			"Invalid entry !!!\n");
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 78e6beb6cf26..8a581c67bf2d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -26,7 +26,7 @@
 #include "dce_clocks.h"
 #include "dm_services.h"
 #include "reg_helper.h"
-#include "fixed32_32.h"
+#include "fixed31_32.h"
 #include "bios_parser_interface.h"
 #include "dc.h"
 #include "dmcu.h"
@@ -35,7 +35,7 @@
 #endif
 #include "core_types.h"
 #include "dc_types.h"
-
+#include "dal_asic_id.h"
 
 #define TO_DCE_CLOCKS(clocks)\
 	container_of(clocks, struct dce_disp_clk, base)
@@ -228,19 +228,19 @@ static int dce_clocks_get_dp_ref_freq(struct display_clock *clk)
 	 generated according to average value (case as with previous ASICs)
 	  */
 	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
-		struct fixed32_32 ss_percentage = dal_fixed32_32_div_int(
-				dal_fixed32_32_from_fraction(
+		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
+				dc_fixpt_from_fraction(
 						clk_dce->dprefclk_ss_percentage,
 						clk_dce->dprefclk_ss_divider), 200);
-		struct fixed32_32 adj_dp_ref_clk_khz;
+		struct fixed31_32 adj_dp_ref_clk_khz;
 
-		ss_percentage = dal_fixed32_32_sub(dal_fixed32_32_one,
+		ss_percentage = dc_fixpt_sub(dc_fixpt_one,
 								ss_percentage);
 		adj_dp_ref_clk_khz =
-			dal_fixed32_32_mul_int(
+			dc_fixpt_mul_int(
 				ss_percentage,
 				dp_ref_clk_khz);
-		dp_ref_clk_khz = dal_fixed32_32_floor(adj_dp_ref_clk_khz);
+		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
 	}
 
 	return dp_ref_clk_khz;
@@ -256,19 +256,19 @@ static int dce_clocks_get_dp_ref_freq_wrkaround(struct display_clock *clk)
 	int dp_ref_clk_khz = 600000;
 
 	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
-		struct fixed32_32 ss_percentage = dal_fixed32_32_div_int(
-				dal_fixed32_32_from_fraction(
+		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
+				dc_fixpt_from_fraction(
 						clk_dce->dprefclk_ss_percentage,
 						clk_dce->dprefclk_ss_divider), 200);
-		struct fixed32_32 adj_dp_ref_clk_khz;
+		struct fixed31_32 adj_dp_ref_clk_khz;
 
-		ss_percentage = dal_fixed32_32_sub(dal_fixed32_32_one,
+		ss_percentage = dc_fixpt_sub(dc_fixpt_one,
 								ss_percentage);
 		adj_dp_ref_clk_khz =
-			dal_fixed32_32_mul_int(
+			dc_fixpt_mul_int(
 				ss_percentage,
 				dp_ref_clk_khz);
-		dp_ref_clk_khz = dal_fixed32_32_floor(adj_dp_ref_clk_khz);
+		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
 	}
 
 	return dp_ref_clk_khz;
@@ -413,9 +413,12 @@ static int dce112_set_clock(
 	/*VBIOS will determine DPREFCLK frequency, so we don't set it*/
 	dce_clk_params.target_clock_frequency = 0;
 	dce_clk_params.clock_type = DCECLOCK_TYPE_DPREFCLK;
-	dce_clk_params.flags.USE_GENLOCK_AS_SOURCE_FOR_DPREFCLK =
+	if (!ASICREV_IS_VEGA20_P(clk->ctx->asic_id.hw_internal_rev))
+		dce_clk_params.flags.USE_GENLOCK_AS_SOURCE_FOR_DPREFCLK =
 			(dce_clk_params.pll_id ==
 					CLOCK_SOURCE_COMBO_DISPLAY_PLL0);
+	else
+		dce_clk_params.flags.USE_GENLOCK_AS_SOURCE_FOR_DPREFCLK = false;
 
 	bp->funcs->set_dce_clock(bp, &dce_clk_params);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
index 2ee3d9bf1062..a576b8bbb3cd 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -28,7 +28,7 @@
 #include "dce_dmcu.h"
 #include "dm_services.h"
 #include "reg_helper.h"
-#include "fixed32_32.h"
+#include "fixed31_32.h"
 #include "dc.h"
 
 #define TO_DCE_DMCU(dmcu)\
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
index 487724345d9d..0275d6d60da4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
@@ -53,7 +53,8 @@ void dce_pipe_control_lock(struct dc *dc,
 	struct dce_hwseq *hws = dc->hwseq;
 
 	/* Not lock pipe when blank */
-	if (lock && pipe->stream_res.tg->funcs->is_blanked(pipe->stream_res.tg))
+	if (lock && pipe->stream_res.tg->funcs->is_blanked &&
+	    pipe->stream_res.tg->funcs->is_blanked(pipe->stream_res.tg))
 		return;
 
 	val = REG_GET_4(BLND_V_UPDATE_LOCK[pipe->stream_res.tg->inst],
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c b/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
index d737e911971b..5d9506b3d46b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_ipp.c
@@ -195,13 +195,13 @@ static void dce_ipp_program_input_lut(
 
 	for (i = 0; i < gamma->num_entries; i++) {
 		REG_SET(DC_LUT_SEQ_COLOR, 0, DC_LUT_SEQ_COLOR,
-				dal_fixed31_32_round(
+				dc_fixpt_round(
 					gamma->entries.red[i]));
 		REG_SET(DC_LUT_SEQ_COLOR, 0, DC_LUT_SEQ_COLOR,
-				dal_fixed31_32_round(
+				dc_fixpt_round(
 					gamma->entries.green[i]));
 		REG_SET(DC_LUT_SEQ_COLOR, 0, DC_LUT_SEQ_COLOR,
-				dal_fixed31_32_round(
+				dc_fixpt_round(
 					gamma->entries.blue[i]));
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index 8167cad7bcf7..dbe3b26b6d9e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -113,6 +113,7 @@ static const struct link_encoder_funcs dce110_lnk_enc_funcs = {
 	.connect_dig_be_to_fe = dce110_link_encoder_connect_dig_be_to_fe,
 	.enable_hpd = dce110_link_encoder_enable_hpd,
 	.disable_hpd = dce110_link_encoder_disable_hpd,
+	.is_dig_enabled = dce110_is_dig_enabled,
 	.destroy = dce110_link_encoder_destroy
 };
 
@@ -535,8 +536,9 @@ void dce110_psr_program_secondary_packet(struct link_encoder *enc,
 		DP_SEC_GSP0_PRIORITY, 1);
 }
 
-static bool is_dig_enabled(const struct dce110_link_encoder *enc110)
+bool dce110_is_dig_enabled(struct link_encoder *enc)
 {
+	struct dce110_link_encoder *enc110 = TO_DCE110_LINK_ENC(enc);
 	uint32_t value;
 
 	REG_GET(DIG_BE_EN_CNTL, DIG_ENABLE, &value);
@@ -1031,7 +1033,7 @@ void dce110_link_encoder_disable_output(
 	struct bp_transmitter_control cntl = { 0 };
 	enum bp_result result;
 
-	if (!is_dig_enabled(enc110)) {
+	if (!dce110_is_dig_enabled(enc)) {
 		/* OF_SKIP_POWER_DOWN_INACTIVE_ENCODER */
 		return;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
index 0ec3433d34b6..347069461a22 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
@@ -263,4 +263,6 @@ void dce110_psr_program_dp_dphy_fast_training(struct link_encoder *enc,
 void dce110_psr_program_secondary_packet(struct link_encoder *enc,
 			unsigned int sdp_transmit_line_num_deadline);
 
+bool dce110_is_dig_enabled(struct link_encoder *enc);
+
 #endif /* __DC_LINK_ENCODER__DCE110_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index 0790f25c7b3b..b235a75355b8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -174,6 +174,25 @@ static void program_urgency_watermark(
 		URGENCY_HIGH_WATERMARK, urgency_high_wm);
 }
 
+static void dce120_program_urgency_watermark(
+	struct dce_mem_input *dce_mi,
+	uint32_t wm_select,
+	uint32_t urgency_low_wm,
+	uint32_t urgency_high_wm)
+{
+	REG_UPDATE(DPG_WATERMARK_MASK_CONTROL,
+		URGENCY_WATERMARK_MASK, wm_select);
+
+	REG_SET_2(DPG_PIPE_URGENCY_CONTROL, 0,
+		URGENCY_LOW_WATERMARK, urgency_low_wm,
+		URGENCY_HIGH_WATERMARK, urgency_high_wm);
+
+	REG_SET_2(DPG_PIPE_URGENT_LEVEL_CONTROL, 0,
+		URGENT_LEVEL_LOW_WATERMARK, urgency_low_wm,
+		URGENT_LEVEL_HIGH_WATERMARK, urgency_high_wm);
+
+}
+
 static void program_nbp_watermark(
 	struct dce_mem_input *dce_mi,
 	uint32_t wm_select,
@@ -206,6 +225,25 @@ static void program_nbp_watermark(
 	}
 }
 
+static void dce120_program_stutter_watermark(
+	struct dce_mem_input *dce_mi,
+	uint32_t wm_select,
+	uint32_t stutter_mark,
+	uint32_t stutter_entry)
+{
+	REG_UPDATE(DPG_WATERMARK_MASK_CONTROL,
+		STUTTER_EXIT_SELF_REFRESH_WATERMARK_MASK, wm_select);
+
+	if (REG(DPG_PIPE_STUTTER_CONTROL2))
+		REG_UPDATE_2(DPG_PIPE_STUTTER_CONTROL2,
+				STUTTER_EXIT_SELF_REFRESH_WATERMARK, stutter_mark,
+				STUTTER_ENTER_SELF_REFRESH_WATERMARK, stutter_entry);
+	else
+		REG_UPDATE_2(DPG_PIPE_STUTTER_CONTROL,
+				STUTTER_EXIT_SELF_REFRESH_WATERMARK, stutter_mark,
+				STUTTER_ENTER_SELF_REFRESH_WATERMARK, stutter_entry);
+}
+
 static void program_stutter_watermark(
 	struct dce_mem_input *dce_mi,
 	uint32_t wm_select,
@@ -225,7 +263,8 @@ static void program_stutter_watermark(
 static void dce_mi_program_display_marks(
 	struct mem_input *mi,
 	struct dce_watermarks nbp,
-	struct dce_watermarks stutter,
+	struct dce_watermarks stutter_exit,
+	struct dce_watermarks stutter_enter,
 	struct dce_watermarks urgent,
 	uint32_t total_dest_line_time_ns)
 {
@@ -243,13 +282,14 @@ static void dce_mi_program_display_marks(
 	program_nbp_watermark(dce_mi, 2, nbp.a_mark); /* set a */
 	program_nbp_watermark(dce_mi, 1, nbp.d_mark); /* set d */
 
-	program_stutter_watermark(dce_mi, 2, stutter.a_mark); /* set a */
-	program_stutter_watermark(dce_mi, 1, stutter.d_mark); /* set d */
+	program_stutter_watermark(dce_mi, 2, stutter_exit.a_mark); /* set a */
+	program_stutter_watermark(dce_mi, 1, stutter_exit.d_mark); /* set d */
 }
 
-static void dce120_mi_program_display_marks(struct mem_input *mi,
+static void dce112_mi_program_display_marks(struct mem_input *mi,
 	struct dce_watermarks nbp,
-	struct dce_watermarks stutter,
+	struct dce_watermarks stutter_exit,
+	struct dce_watermarks stutter_entry,
 	struct dce_watermarks urgent,
 	uint32_t total_dest_line_time_ns)
 {
@@ -273,10 +313,43 @@ static void dce120_mi_program_display_marks(struct mem_input *mi,
 	program_nbp_watermark(dce_mi, 2, nbp.c_mark); /* set c */
 	program_nbp_watermark(dce_mi, 3, nbp.d_mark); /* set d */
 
-	program_stutter_watermark(dce_mi, 0, stutter.a_mark); /* set a */
-	program_stutter_watermark(dce_mi, 1, stutter.b_mark); /* set b */
-	program_stutter_watermark(dce_mi, 2, stutter.c_mark); /* set c */
-	program_stutter_watermark(dce_mi, 3, stutter.d_mark); /* set d */
+	program_stutter_watermark(dce_mi, 0, stutter_exit.a_mark); /* set a */
+	program_stutter_watermark(dce_mi, 1, stutter_exit.b_mark); /* set b */
+	program_stutter_watermark(dce_mi, 2, stutter_exit.c_mark); /* set c */
+	program_stutter_watermark(dce_mi, 3, stutter_exit.d_mark); /* set d */
+}
+
+static void dce120_mi_program_display_marks(struct mem_input *mi,
+	struct dce_watermarks nbp,
+	struct dce_watermarks stutter_exit,
+	struct dce_watermarks stutter_entry,
+	struct dce_watermarks urgent,
+	uint32_t total_dest_line_time_ns)
+{
+	struct dce_mem_input *dce_mi = TO_DCE_MEM_INPUT(mi);
+	uint32_t stutter_en = mi->ctx->dc->debug.disable_stutter ? 0 : 1;
+
+	dce120_program_urgency_watermark(dce_mi, 0, /* set a */
+			urgent.a_mark, total_dest_line_time_ns);
+	dce120_program_urgency_watermark(dce_mi, 1, /* set b */
+			urgent.b_mark, total_dest_line_time_ns);
+	dce120_program_urgency_watermark(dce_mi, 2, /* set c */
+			urgent.c_mark, total_dest_line_time_ns);
+	dce120_program_urgency_watermark(dce_mi, 3, /* set d */
+			urgent.d_mark, total_dest_line_time_ns);
+
+	REG_UPDATE_2(DPG_PIPE_STUTTER_CONTROL,
+		STUTTER_ENABLE, stutter_en,
+		STUTTER_IGNORE_FBC, 1);
+	program_nbp_watermark(dce_mi, 0, nbp.a_mark); /* set a */
+	program_nbp_watermark(dce_mi, 1, nbp.b_mark); /* set b */
+	program_nbp_watermark(dce_mi, 2, nbp.c_mark); /* set c */
+	program_nbp_watermark(dce_mi, 3, nbp.d_mark); /* set d */
+
+	dce120_program_stutter_watermark(dce_mi, 0, stutter_exit.a_mark, stutter_entry.a_mark); /* set a */
+	dce120_program_stutter_watermark(dce_mi, 1, stutter_exit.b_mark, stutter_entry.b_mark); /* set b */
+	dce120_program_stutter_watermark(dce_mi, 2, stutter_exit.c_mark, stutter_entry.c_mark); /* set c */
+	dce120_program_stutter_watermark(dce_mi, 3, stutter_exit.d_mark, stutter_entry.d_mark); /* set d */
 }
 
 static void program_tiling(
@@ -696,5 +769,17 @@ void dce112_mem_input_construct(
 	const struct dce_mem_input_mask *mi_mask)
 {
 	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
+	dce_mi->base.funcs->mem_input_program_display_marks = dce112_mi_program_display_marks;
+}
+
+void dce120_mem_input_construct(
+	struct dce_mem_input *dce_mi,
+	struct dc_context *ctx,
+	int inst,
+	const struct dce_mem_input_registers *regs,
+	const struct dce_mem_input_shift *mi_shift,
+	const struct dce_mem_input_mask *mi_mask)
+{
+	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
 	dce_mi->base.funcs->mem_input_program_display_marks = dce120_mi_program_display_marks;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.h b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.h
index 05d39c0cbe87..d15b0d7f47fc 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.h
@@ -106,6 +106,7 @@ struct dce_mem_input_registers {
 	uint32_t DPG_PIPE_ARBITRATION_CONTROL1;
 	uint32_t DPG_WATERMARK_MASK_CONTROL;
 	uint32_t DPG_PIPE_URGENCY_CONTROL;
+	uint32_t DPG_PIPE_URGENT_LEVEL_CONTROL;
 	uint32_t DPG_PIPE_NB_PSTATE_CHANGE_CONTROL;
 	uint32_t DPG_PIPE_LOW_POWER_CONTROL;
 	uint32_t DPG_PIPE_STUTTER_CONTROL;
@@ -213,6 +214,11 @@ struct dce_mem_input_registers {
 
 #define MI_DCE12_DMIF_PG_MASK_SH_LIST(mask_sh, blk)\
 	SFB(blk, DPG_PIPE_STUTTER_CONTROL2, STUTTER_EXIT_SELF_REFRESH_WATERMARK, mask_sh),\
+	SFB(blk, DPG_PIPE_STUTTER_CONTROL2, STUTTER_ENTER_SELF_REFRESH_WATERMARK, mask_sh),\
+	SFB(blk, DPG_PIPE_URGENT_LEVEL_CONTROL, URGENT_LEVEL_LOW_WATERMARK, mask_sh),\
+	SFB(blk, DPG_PIPE_URGENT_LEVEL_CONTROL, URGENT_LEVEL_HIGH_WATERMARK, mask_sh),\
+	SFB(blk, DPG_PIPE_URGENCY_CONTROL, URGENCY_LOW_WATERMARK, mask_sh),\
+	SFB(blk, DPG_PIPE_URGENCY_CONTROL, URGENCY_HIGH_WATERMARK, mask_sh),\
 	SFB(blk, DPG_WATERMARK_MASK_CONTROL, PSTATE_CHANGE_WATERMARK_MASK, mask_sh),\
 	SFB(blk, DPG_PIPE_LOW_POWER_CONTROL, PSTATE_CHANGE_ENABLE, mask_sh),\
 	SFB(blk, DPG_PIPE_LOW_POWER_CONTROL, PSTATE_CHANGE_URGENT_DURING_REQUEST, mask_sh),\
@@ -286,6 +292,8 @@ struct dce_mem_input_registers {
 	type STUTTER_EXIT_SELF_REFRESH_WATERMARK_MASK; \
 	type URGENCY_LOW_WATERMARK; \
 	type URGENCY_HIGH_WATERMARK; \
+	type URGENT_LEVEL_LOW_WATERMARK;\
+	type URGENT_LEVEL_HIGH_WATERMARK;\
 	type NB_PSTATE_CHANGE_ENABLE; \
 	type NB_PSTATE_CHANGE_URGENT_DURING_REQUEST; \
 	type NB_PSTATE_CHANGE_NOT_SELF_REFRESH_DURING_REQUEST; \
@@ -297,6 +305,7 @@ struct dce_mem_input_registers {
 	type STUTTER_ENABLE; \
 	type STUTTER_IGNORE_FBC; \
 	type STUTTER_EXIT_SELF_REFRESH_WATERMARK; \
+	type STUTTER_ENTER_SELF_REFRESH_WATERMARK; \
 	type DMIF_BUFFERS_ALLOCATED; \
 	type DMIF_BUFFERS_ALLOCATION_COMPLETED; \
 	type ENABLE; /* MC_HUB_RDREQ_DMIF_LIMIT */\
@@ -344,4 +353,12 @@ void dce112_mem_input_construct(
 	const struct dce_mem_input_shift *mi_shift,
 	const struct dce_mem_input_mask *mi_mask);
 
+void dce120_mem_input_construct(
+	struct dce_mem_input *dce_mi,
+	struct dc_context *ctx,
+	int inst,
+	const struct dce_mem_input_registers *regs,
+	const struct dce_mem_input_shift *mi_shift,
+	const struct dce_mem_input_mask *mi_mask);
+
 #endif /*__DCE_MEM_INPUT_H__*/
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_scl_filters.c b/drivers/gpu/drm/amd/display/dc/dce/dce_scl_filters.c
index 6243450b41b7..48862bebf29e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_scl_filters.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_scl_filters.c
@@ -1014,11 +1014,11 @@ static const uint16_t filter_8tap_64p_183[264] = {
 
 const uint16_t *get_filter_3tap_16p(struct fixed31_32 ratio)
 {
-	if (ratio.value < dal_fixed31_32_one.value)
+	if (ratio.value < dc_fixpt_one.value)
 		return filter_3tap_16p_upscale;
-	else if (ratio.value < dal_fixed31_32_from_fraction(4, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(4, 3).value)
 		return filter_3tap_16p_117;
-	else if (ratio.value < dal_fixed31_32_from_fraction(5, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(5, 3).value)
 		return filter_3tap_16p_150;
 	else
 		return filter_3tap_16p_183;
@@ -1026,11 +1026,11 @@ const uint16_t *get_filter_3tap_16p(struct fixed31_32 ratio)
 
 const uint16_t *get_filter_3tap_64p(struct fixed31_32 ratio)
 {
-	if (ratio.value < dal_fixed31_32_one.value)
+	if (ratio.value < dc_fixpt_one.value)
 		return filter_3tap_64p_upscale;
-	else if (ratio.value < dal_fixed31_32_from_fraction(4, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(4, 3).value)
 		return filter_3tap_64p_117;
-	else if (ratio.value < dal_fixed31_32_from_fraction(5, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(5, 3).value)
 		return filter_3tap_64p_150;
 	else
 		return filter_3tap_64p_183;
@@ -1038,11 +1038,11 @@ const uint16_t *get_filter_3tap_64p(struct fixed31_32 ratio)
 
 const uint16_t *get_filter_4tap_16p(struct fixed31_32 ratio)
 {
-	if (ratio.value < dal_fixed31_32_one.value)
+	if (ratio.value < dc_fixpt_one.value)
 		return filter_4tap_16p_upscale;
-	else if (ratio.value < dal_fixed31_32_from_fraction(4, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(4, 3).value)
 		return filter_4tap_16p_117;
-	else if (ratio.value < dal_fixed31_32_from_fraction(5, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(5, 3).value)
 		return filter_4tap_16p_150;
 	else
 		return filter_4tap_16p_183;
@@ -1050,11 +1050,11 @@ const uint16_t *get_filter_4tap_16p(struct fixed31_32 ratio)
 
 const uint16_t *get_filter_4tap_64p(struct fixed31_32 ratio)
 {
-	if (ratio.value < dal_fixed31_32_one.value)
+	if (ratio.value < dc_fixpt_one.value)
 		return filter_4tap_64p_upscale;
-	else if (ratio.value < dal_fixed31_32_from_fraction(4, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(4, 3).value)
 		return filter_4tap_64p_117;
-	else if (ratio.value < dal_fixed31_32_from_fraction(5, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(5, 3).value)
 		return filter_4tap_64p_150;
 	else
 		return filter_4tap_64p_183;
@@ -1062,11 +1062,11 @@ const uint16_t *get_filter_4tap_64p(struct fixed31_32 ratio)
 
 const uint16_t *get_filter_5tap_64p(struct fixed31_32 ratio)
 {
-	if (ratio.value < dal_fixed31_32_one.value)
+	if (ratio.value < dc_fixpt_one.value)
 		return filter_5tap_64p_upscale;
-	else if (ratio.value < dal_fixed31_32_from_fraction(4, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(4, 3).value)
 		return filter_5tap_64p_117;
-	else if (ratio.value < dal_fixed31_32_from_fraction(5, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(5, 3).value)
 		return filter_5tap_64p_150;
 	else
 		return filter_5tap_64p_183;
@@ -1074,11 +1074,11 @@ const uint16_t *get_filter_5tap_64p(struct fixed31_32 ratio)
 
 const uint16_t *get_filter_6tap_64p(struct fixed31_32 ratio)
 {
-	if (ratio.value < dal_fixed31_32_one.value)
+	if (ratio.value < dc_fixpt_one.value)
 		return filter_6tap_64p_upscale;
-	else if (ratio.value < dal_fixed31_32_from_fraction(4, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(4, 3).value)
 		return filter_6tap_64p_117;
-	else if (ratio.value < dal_fixed31_32_from_fraction(5, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(5, 3).value)
 		return filter_6tap_64p_150;
 	else
 		return filter_6tap_64p_183;
@@ -1086,11 +1086,11 @@ const uint16_t *get_filter_6tap_64p(struct fixed31_32 ratio)
 
 const uint16_t *get_filter_7tap_64p(struct fixed31_32 ratio)
 {
-	if (ratio.value < dal_fixed31_32_one.value)
+	if (ratio.value < dc_fixpt_one.value)
 		return filter_7tap_64p_upscale;
-	else if (ratio.value < dal_fixed31_32_from_fraction(4, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(4, 3).value)
 		return filter_7tap_64p_117;
-	else if (ratio.value < dal_fixed31_32_from_fraction(5, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(5, 3).value)
 		return filter_7tap_64p_150;
 	else
 		return filter_7tap_64p_183;
@@ -1098,11 +1098,11 @@ const uint16_t *get_filter_7tap_64p(struct fixed31_32 ratio)
 
 const uint16_t *get_filter_8tap_64p(struct fixed31_32 ratio)
 {
-	if (ratio.value < dal_fixed31_32_one.value)
+	if (ratio.value < dc_fixpt_one.value)
 		return filter_8tap_64p_upscale;
-	else if (ratio.value < dal_fixed31_32_from_fraction(4, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(4, 3).value)
 		return filter_8tap_64p_117;
-	else if (ratio.value < dal_fixed31_32_from_fraction(5, 3).value)
+	else if (ratio.value < dc_fixpt_from_fraction(5, 3).value)
 		return filter_8tap_64p_150;
 	else
 		return filter_8tap_64p_183;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index 162f6a6c4208..0a6d483dc046 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -26,27 +26,10 @@
 #include "dc_bios_types.h"
 #include "dce_stream_encoder.h"
 #include "reg_helper.h"
+#include "hw_shared.h"
+
 #define DC_LOGGER \
 		enc110->base.ctx->logger
-enum DP_PIXEL_ENCODING {
-DP_PIXEL_ENCODING_RGB444                 = 0x00000000,
-DP_PIXEL_ENCODING_YCBCR422               = 0x00000001,
-DP_PIXEL_ENCODING_YCBCR444               = 0x00000002,
-DP_PIXEL_ENCODING_RGB_WIDE_GAMUT         = 0x00000003,
-DP_PIXEL_ENCODING_Y_ONLY                 = 0x00000004,
-DP_PIXEL_ENCODING_YCBCR420               = 0x00000005,
-DP_PIXEL_ENCODING_RESERVED               = 0x00000006,
-};
-
-
-enum DP_COMPONENT_DEPTH {
-DP_COMPONENT_DEPTH_6BPC                  = 0x00000000,
-DP_COMPONENT_DEPTH_8BPC                  = 0x00000001,
-DP_COMPONENT_DEPTH_10BPC                 = 0x00000002,
-DP_COMPONENT_DEPTH_12BPC                 = 0x00000003,
-DP_COMPONENT_DEPTH_16BPC                 = 0x00000004,
-DP_COMPONENT_DEPTH_RESERVED              = 0x00000005,
-};
 
 
 #define REG(reg)\
@@ -80,7 +63,7 @@ enum {
 static void dce110_update_generic_info_packet(
 	struct dce110_stream_encoder *enc110,
 	uint32_t packet_index,
-	const struct encoder_info_packet *info_packet)
+	const struct dc_info_packet *info_packet)
 {
 	uint32_t regval;
 	/* TODOFPGA Figure out a proper number for max_retries polling for lock
@@ -196,7 +179,7 @@ static void dce110_update_generic_info_packet(
 static void dce110_update_hdmi_info_packet(
 	struct dce110_stream_encoder *enc110,
 	uint32_t packet_index,
-	const struct encoder_info_packet *info_packet)
+	const struct dc_info_packet *info_packet)
 {
 	uint32_t cont, send, line;
 
@@ -314,11 +297,11 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	switch (crtc_timing->pixel_encoding) {
 	case PIXEL_ENCODING_YCBCR422:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_YCBCR422);
+				DP_PIXEL_ENCODING_TYPE_YCBCR422);
 		break;
 	case PIXEL_ENCODING_YCBCR444:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_YCBCR444);
+				DP_PIXEL_ENCODING_TYPE_YCBCR444);
 
 		if (crtc_timing->flags.Y_ONLY)
 			if (crtc_timing->display_color_depth != COLOR_DEPTH_666)
@@ -326,7 +309,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				 * Color depth of Y-only could be
 				 * 8, 10, 12, 16 bits */
 				REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-						DP_PIXEL_ENCODING_Y_ONLY);
+						DP_PIXEL_ENCODING_TYPE_Y_ONLY);
 		/* Note: DP_MSA_MISC1 bit 7 is the indicator
 		 * of Y-only mode.
 		 * This bit is set in HW if register
@@ -334,7 +317,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		break;
 	case PIXEL_ENCODING_YCBCR420:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_YCBCR420);
+				DP_PIXEL_ENCODING_TYPE_YCBCR420);
 		if (enc110->se_mask->DP_VID_M_DOUBLE_VALUE_EN)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_M_DOUBLE_VALUE_EN, 1);
 
@@ -345,7 +328,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		break;
 	default:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_RGB444);
+				DP_PIXEL_ENCODING_TYPE_RGB444);
 		break;
 	}
 
@@ -363,20 +346,20 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		break;
 	case COLOR_DEPTH_888:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_DEPTH_8BPC);
+				DP_COMPONENT_PIXEL_DEPTH_8BPC);
 		break;
 	case COLOR_DEPTH_101010:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_DEPTH_10BPC);
+				DP_COMPONENT_PIXEL_DEPTH_10BPC);
 
 		break;
 	case COLOR_DEPTH_121212:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_DEPTH_12BPC);
+				DP_COMPONENT_PIXEL_DEPTH_12BPC);
 		break;
 	default:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_DEPTH_6BPC);
+				DP_COMPONENT_PIXEL_DEPTH_6BPC);
 		break;
 	}
 
@@ -700,11 +683,11 @@ static void dce110_stream_encoder_set_mst_bandwidth(
 	struct fixed31_32 avg_time_slots_per_mtp)
 {
 	struct dce110_stream_encoder *enc110 = DCE110STRENC_FROM_STRENC(enc);
-	uint32_t x = dal_fixed31_32_floor(
+	uint32_t x = dc_fixpt_floor(
 		avg_time_slots_per_mtp);
-	uint32_t y = dal_fixed31_32_ceil(
-		dal_fixed31_32_shl(
-			dal_fixed31_32_sub_int(
+	uint32_t y = dc_fixpt_ceil(
+		dc_fixpt_shl(
+			dc_fixpt_sub_int(
 				avg_time_slots_per_mtp,
 				x),
 			26));
@@ -836,7 +819,7 @@ static void dce110_stream_encoder_update_dp_info_packets(
 	const struct encoder_info_frame *info_frame)
 {
 	struct dce110_stream_encoder *enc110 = DCE110STRENC_FROM_STRENC(enc);
-	uint32_t value = REG_READ(DP_SEC_CNTL);
+	uint32_t value = 0;
 
 	if (info_frame->vsc.valid)
 		dce110_update_generic_info_packet(
@@ -870,6 +853,7 @@ static void dce110_stream_encoder_update_dp_info_packets(
 	* Therefore we need to enable master bit
 	* if at least on of the fields is not 0
 	*/
+	value = REG_READ(DP_SEC_CNTL);
 	if (value)
 		REG_UPDATE(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, 1);
 }
@@ -879,7 +863,7 @@ static void dce110_stream_encoder_stop_dp_info_packets(
 {
 	/* stop generic packets on DP */
 	struct dce110_stream_encoder *enc110 = DCE110STRENC_FROM_STRENC(enc);
-	uint32_t value = REG_READ(DP_SEC_CNTL);
+	uint32_t value = 0;
 
 	if (enc110->se_mask->DP_SEC_AVI_ENABLE) {
 		REG_SET_7(DP_SEC_CNTL, 0,
@@ -892,25 +876,10 @@ static void dce110_stream_encoder_stop_dp_info_packets(
 			DP_SEC_STREAM_ENABLE, 0);
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	if (enc110->se_mask->DP_SEC_GSP7_ENABLE) {
-		REG_SET_10(DP_SEC_CNTL, 0,
-			DP_SEC_GSP0_ENABLE, 0,
-			DP_SEC_GSP1_ENABLE, 0,
-			DP_SEC_GSP2_ENABLE, 0,
-			DP_SEC_GSP3_ENABLE, 0,
-			DP_SEC_GSP4_ENABLE, 0,
-			DP_SEC_GSP5_ENABLE, 0,
-			DP_SEC_GSP6_ENABLE, 0,
-			DP_SEC_GSP7_ENABLE, 0,
-			DP_SEC_MPG_ENABLE, 0,
-			DP_SEC_STREAM_ENABLE, 0);
-	}
-#endif
 	/* this register shared with audio info frame.
 	 * therefore we need to keep master enabled
 	 * if at least one of the fields is not 0 */
-
+	value = REG_READ(DP_SEC_CNTL);
 	if (value)
 		REG_UPDATE(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, 1);
 
@@ -1513,7 +1482,7 @@ static void dce110_se_disable_dp_audio(
 	struct stream_encoder *enc)
 {
 	struct dce110_stream_encoder *enc110 = DCE110STRENC_FROM_STRENC(enc);
-	uint32_t value = REG_READ(DP_SEC_CNTL);
+	uint32_t value = 0;
 
 	/* Disable Audio packets */
 	REG_UPDATE_5(DP_SEC_CNTL,
@@ -1525,6 +1494,7 @@ static void dce110_se_disable_dp_audio(
 
 	/* This register shared with encoder info frame. Therefore we need to
 	keep master enabled if at least on of the fields is not 0 */
+	value = REG_READ(DP_SEC_CNTL);
 	if (value != 0)
 		REG_UPDATE(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, 1);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index 832c5daada35..a02e719d7794 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -41,7 +41,7 @@
 #define DC_LOGGER \
 	xfm_dce->base.ctx->logger
 
-#define IDENTITY_RATIO(ratio) (dal_fixed31_32_u2d19(ratio) == (1 << 19))
+#define IDENTITY_RATIO(ratio) (dc_fixpt_u2d19(ratio) == (1 << 19))
 #define GAMUT_MATRIX_SIZE 12
 #define SCL_PHASES 16
 
@@ -256,27 +256,27 @@ static void calculate_inits(
 	struct fixed31_32 v_init;
 
 	inits->h_int_scale_ratio =
-		dal_fixed31_32_u2d19(data->ratios.horz) << 5;
+		dc_fixpt_u2d19(data->ratios.horz) << 5;
 	inits->v_int_scale_ratio =
-		dal_fixed31_32_u2d19(data->ratios.vert) << 5;
+		dc_fixpt_u2d19(data->ratios.vert) << 5;
 
 	h_init =
-		dal_fixed31_32_div_int(
-			dal_fixed31_32_add(
+		dc_fixpt_div_int(
+			dc_fixpt_add(
 				data->ratios.horz,
-				dal_fixed31_32_from_int(data->taps.h_taps + 1)),
+				dc_fixpt_from_int(data->taps.h_taps + 1)),
 				2);
-	inits->h_init.integer = dal_fixed31_32_floor(h_init);
-	inits->h_init.fraction = dal_fixed31_32_u0d19(h_init) << 5;
+	inits->h_init.integer = dc_fixpt_floor(h_init);
+	inits->h_init.fraction = dc_fixpt_u0d19(h_init) << 5;
 
 	v_init =
-		dal_fixed31_32_div_int(
-			dal_fixed31_32_add(
+		dc_fixpt_div_int(
+			dc_fixpt_add(
 				data->ratios.vert,
-				dal_fixed31_32_from_int(data->taps.v_taps + 1)),
+				dc_fixpt_from_int(data->taps.v_taps + 1)),
 				2);
-	inits->v_init.integer = dal_fixed31_32_floor(v_init);
-	inits->v_init.fraction = dal_fixed31_32_u0d19(v_init) << 5;
+	inits->v_init.integer = dc_fixpt_floor(v_init);
+	inits->v_init.fraction = dc_fixpt_u0d19(v_init) << 5;
 }
 
 static void program_scl_ratios_inits(
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 3092f76bdb75..38ec0d609297 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -733,38 +733,6 @@ enum dc_status dce100_add_stream_to_ctx(
 	return result;
 }
 
-enum dc_status dce100_validate_guaranteed(
-		struct dc  *dc,
-		struct dc_stream_state *dc_stream,
-		struct dc_state *context)
-{
-	enum dc_status result = DC_ERROR_UNEXPECTED;
-
-	context->streams[0] = dc_stream;
-	dc_stream_retain(context->streams[0]);
-	context->stream_count++;
-
-	result = resource_map_pool_resources(dc, context, dc_stream);
-
-	if (result == DC_OK)
-		result = resource_map_clock_resources(dc, context, dc_stream);
-
-	if (result == DC_OK)
-		result = build_mapped_resource(dc, context, dc_stream);
-
-	if (result == DC_OK) {
-		validate_guaranteed_copy_streams(
-				context, dc->caps.max_streams);
-		result = resource_build_scaling_params_for_context(dc, context);
-	}
-
-	if (result == DC_OK)
-		if (!dce100_validate_bandwidth(dc, context))
-			result = DC_FAIL_BANDWIDTH_VALIDATE;
-
-	return result;
-}
-
 static void dce100_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
@@ -786,7 +754,6 @@ enum dc_status dce100_validate_plane(const struct dc_plane_state *plane_state, s
 static const struct resource_funcs dce100_res_pool_funcs = {
 	.destroy = dce100_destroy_resource_pool,
 	.link_enc_create = dce100_link_encoder_create,
-	.validate_guaranteed = dce100_validate_guaranteed,
 	.validate_bandwidth = dce100_validate_bandwidth,
 	.validate_plane = dce100_validate_plane,
 	.add_stream_to_ctx = dce100_add_stream_to_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index d0575999f172..a92fb0aa2ff3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -70,8 +70,9 @@
 
 #define CTX \
 	hws->ctx
-#define DC_LOGGER \
-	ctx->logger
+
+#define DC_LOGGER_INIT()
+
 #define REG(reg)\
 	hws->regs->reg
 
@@ -279,7 +280,9 @@ dce110_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 	build_prescale_params(&prescale_params, plane_state);
 	ipp->funcs->ipp_program_prescale(ipp, &prescale_params);
 
-	if (plane_state->gamma_correction && dce_use_lut(plane_state->format))
+	if (plane_state->gamma_correction &&
+			!plane_state->gamma_correction->is_identity &&
+			dce_use_lut(plane_state->format))
 		ipp->funcs->ipp_program_input_lut(ipp, plane_state->gamma_correction);
 
 	if (tf == NULL) {
@@ -506,19 +509,19 @@ dce110_translate_regamma_to_hw_format(const struct dc_transfer_func *output_tf,
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
-	arr_points[0].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-					     dal_fixed31_32_from_int(region_start));
-	arr_points[1].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-					     dal_fixed31_32_from_int(region_end));
+	arr_points[0].x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_start));
+	arr_points[1].x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_end));
 
 	y_r = rgb_resulted[0].red;
 	y_g = rgb_resulted[0].green;
 	y_b = rgb_resulted[0].blue;
 
-	y1_min = dal_fixed31_32_min(y_r, dal_fixed31_32_min(y_g, y_b));
+	y1_min = dc_fixpt_min(y_r, dc_fixpt_min(y_g, y_b));
 
 	arr_points[0].y = y1_min;
-	arr_points[0].slope = dal_fixed31_32_div(arr_points[0].y,
+	arr_points[0].slope = dc_fixpt_div(arr_points[0].y,
 						 arr_points[0].x);
 
 	y_r = rgb_resulted[hw_points - 1].red;
@@ -528,21 +531,21 @@ dce110_translate_regamma_to_hw_format(const struct dc_transfer_func *output_tf,
 	/* see comment above, m_arrPoints[1].y should be the Y value for the
 	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
 	 */
-	y3_max = dal_fixed31_32_max(y_r, dal_fixed31_32_max(y_g, y_b));
+	y3_max = dc_fixpt_max(y_r, dc_fixpt_max(y_g, y_b));
 
 	arr_points[1].y = y3_max;
 
-	arr_points[1].slope = dal_fixed31_32_zero;
+	arr_points[1].slope = dc_fixpt_zero;
 
 	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
 		/* for PQ, we want to have a straight line from last HW X point,
 		 * and the slope to be such that we hit 1.0 at 10000 nits.
 		 */
-		const struct fixed31_32 end_value = dal_fixed31_32_from_int(125);
+		const struct fixed31_32 end_value = dc_fixpt_from_int(125);
 
-		arr_points[1].slope = dal_fixed31_32_div(
-				dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
-				dal_fixed31_32_sub(end_value, arr_points[1].x));
+		arr_points[1].slope = dc_fixpt_div(
+				dc_fixpt_sub(dc_fixpt_one, arr_points[1].y),
+				dc_fixpt_sub(end_value, arr_points[1].x));
 	}
 
 	regamma_params->hw_points_num = hw_points;
@@ -566,16 +569,16 @@ dce110_translate_regamma_to_hw_format(const struct dc_transfer_func *output_tf,
 	i = 1;
 
 	while (i != hw_points + 1) {
-		if (dal_fixed31_32_lt(rgb_plus_1->red, rgb->red))
+		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
 			rgb_plus_1->red = rgb->red;
-		if (dal_fixed31_32_lt(rgb_plus_1->green, rgb->green))
+		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
 			rgb_plus_1->green = rgb->green;
-		if (dal_fixed31_32_lt(rgb_plus_1->blue, rgb->blue))
+		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
 			rgb_plus_1->blue = rgb->blue;
 
-		rgb->delta_red = dal_fixed31_32_sub(rgb_plus_1->red, rgb->red);
-		rgb->delta_green = dal_fixed31_32_sub(rgb_plus_1->green, rgb->green);
-		rgb->delta_blue = dal_fixed31_32_sub(rgb_plus_1->blue, rgb->blue);
+		rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red);
+		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
+		rgb->delta_blue = dc_fixpt_sub(rgb_plus_1->blue, rgb->blue);
 
 		++rgb_plus_1;
 		++rgb;
@@ -851,6 +854,28 @@ void hwss_edp_power_control(
 
 	if (power_up != is_panel_powered_on(hwseq)) {
 		/* Send VBIOS command to prompt eDP panel power */
+		if (power_up) {
+			unsigned long long current_ts = dm_get_timestamp(ctx);
+			unsigned long long duration_in_ms =
+					dm_get_elapse_time_in_ns(
+							ctx,
+							current_ts,
+							div64_u64(link->link_trace.time_stamp.edp_poweroff, 1000000));
+			unsigned long long wait_time_ms = 0;
+
+			/* max 500ms from LCDVDD off to on */
+			if (link->link_trace.time_stamp.edp_poweroff == 0)
+				wait_time_ms = 500;
+			else if (duration_in_ms < 500)
+				wait_time_ms = 500 - duration_in_ms;
+
+			if (wait_time_ms) {
+				msleep(wait_time_ms);
+				dm_output_to_console("%s: wait %lld ms to power on eDP.\n",
+						__func__, wait_time_ms);
+			}
+
+		}
 
 		DC_LOG_HW_RESUME_S3(
 				"%s: Panel Power action: %s\n",
@@ -864,9 +889,14 @@ void hwss_edp_power_control(
 		cntl.coherent = false;
 		cntl.lanes_number = LANE_COUNT_FOUR;
 		cntl.hpd_sel = link->link_enc->hpd_source;
-
 		bp_result = link_transmitter_control(ctx->dc_bios, &cntl);
 
+		if (!power_up)
+			/*save driver power off time stamp*/
+			link->link_trace.time_stamp.edp_poweroff = dm_get_timestamp(ctx);
+		else
+			link->link_trace.time_stamp.edp_poweron = dm_get_timestamp(ctx);
+
 		if (bp_result != BP_RESULT_OK)
 			DC_LOG_ERROR(
 					"%s: Panel Power bp_result: %d\n",
@@ -1011,7 +1041,7 @@ void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
 		link->dc->hwss.edp_backlight_control(link, true);
-		stream->bl_pwm_level = 0;
+		stream->bl_pwm_level = EDP_BACKLIGHT_RAMP_DISABLE_LEVEL;
 	}
 }
 void dce110_blank_stream(struct pipe_ctx *pipe_ctx)
@@ -1203,7 +1233,7 @@ static void program_scaler(const struct dc *dc,
 		&pipe_ctx->plane_res.scl_data);
 }
 
-static enum dc_status dce110_prog_pixclk_crtc_otg(
+static enum dc_status dce110_enable_stream_timing(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -1269,7 +1299,7 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 			pipe_ctx[pipe_ctx->pipe_idx];
 
 	/*  */
-	dc->hwss.prog_pixclk_crtc_otg(pipe_ctx, context, dc);
+	dc->hwss.enable_stream_timing(pipe_ctx, context, dc);
 
 	/* FPGA does not program backend */
 	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
@@ -1441,6 +1471,17 @@ static void disable_vga_and_power_gate_all_controllers(
 	}
 }
 
+static struct dc_link *get_link_for_edp(struct dc *dc)
+{
+	int i;
+
+	for (i = 0; i < dc->link_count; i++) {
+		if (dc->links[i]->connector_signal == SIGNAL_TYPE_EDP)
+			return dc->links[i];
+	}
+	return NULL;
+}
+
 static struct dc_link *get_link_for_edp_not_in_use(
 		struct dc *dc,
 		struct dc_state *context)
@@ -1475,20 +1516,21 @@ static struct dc_link *get_link_for_edp_not_in_use(
  */
 void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
 {
-	struct dc_bios *dcb = dc->ctx->dc_bios;
-
-	/* vbios already light up eDP, so we can leverage vbios and skip eDP
-	 * programming
-	 */
-	bool can_eDP_fast_boot_optimize =
-			(dcb->funcs->get_vga_enabled_displays(dc->ctx->dc_bios) == ATOM_DISPLAY_LCD1_ACTIVE);
-
-	/* if OS doesn't light up eDP and eDP link is available, we want to disable */
 	struct dc_link *edp_link_to_turnoff = NULL;
+	struct dc_link *edp_link = get_link_for_edp(dc);
+	bool can_eDP_fast_boot_optimize = false;
+
+	if (edp_link) {
+		can_eDP_fast_boot_optimize =
+				edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc);
+	}
 
 	if (can_eDP_fast_boot_optimize) {
 		edp_link_to_turnoff = get_link_for_edp_not_in_use(dc, context);
 
+		/* if OS doesn't light up eDP and eDP link is available, we want to disable
+		 * If resume from S4/S5, should optimization.
+		 */
 		if (!edp_link_to_turnoff)
 			dc->apply_edp_fast_boot_optimization = true;
 	}
@@ -1544,6 +1586,7 @@ static void dce110_set_displaymarks(
 			pipe_ctx->plane_res.mi,
 			context->bw.dce.nbp_state_change_wm_ns[num_pipes],
 			context->bw.dce.stutter_exit_wm_ns[num_pipes],
+			context->bw.dce.stutter_entry_wm_ns[num_pipes],
 			context->bw.dce.urgent_wm_ns[num_pipes],
 			total_dest_line_time_ns);
 		if (i == underlay_idx) {
@@ -1569,6 +1612,7 @@ static void set_safe_displaymarks(
 		MAX_WATERMARK, MAX_WATERMARK, MAX_WATERMARK, MAX_WATERMARK };
 	struct dce_watermarks nbp_marks = {
 		SAFE_NBP_MARK, SAFE_NBP_MARK, SAFE_NBP_MARK, SAFE_NBP_MARK };
+	struct dce_watermarks min_marks = { 0, 0, 0, 0};
 
 	for (i = 0; i < MAX_PIPES; i++) {
 		if (res_ctx->pipe_ctx[i].stream == NULL || res_ctx->pipe_ctx[i].plane_res.mi == NULL)
@@ -1578,6 +1622,7 @@ static void set_safe_displaymarks(
 				res_ctx->pipe_ctx[i].plane_res.mi,
 				nbp_marks,
 				max_marks,
+				min_marks,
 				max_marks,
 				MAX_WATERMARK);
 
@@ -1803,6 +1848,9 @@ static bool should_enable_fbc(struct dc *dc,
 		}
 	}
 
+	/* Pipe context should be found */
+	ASSERT(pipe_ctx);
+
 	/* Only supports eDP */
 	if (pipe_ctx->stream->sink->link->connector_signal != SIGNAL_TYPE_EDP)
 		return false;
@@ -2221,74 +2269,6 @@ static void program_gamut_remap(struct pipe_ctx *pipe_ctx)
 
 	pipe_ctx->plane_res.xfm->funcs->transform_set_gamut_remap(pipe_ctx->plane_res.xfm, &adjust);
 }
-
-/**
- * TODO REMOVE, USE UPDATE INSTEAD
- */
-static void set_plane_config(
-	const struct dc *dc,
-	struct pipe_ctx *pipe_ctx,
-	struct resource_context *res_ctx)
-{
-	struct mem_input *mi = pipe_ctx->plane_res.mi;
-	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
-	struct xfm_grph_csc_adjustment adjust;
-	struct out_csc_color_matrix tbl_entry;
-	unsigned int i;
-
-	memset(&adjust, 0, sizeof(adjust));
-	memset(&tbl_entry, 0, sizeof(tbl_entry));
-	adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS;
-
-	dce_enable_fe_clock(dc->hwseq, mi->inst, true);
-
-	set_default_colors(pipe_ctx);
-	if (pipe_ctx->stream->csc_color_matrix.enable_adjustment == true) {
-		tbl_entry.color_space =
-			pipe_ctx->stream->output_color_space;
-
-		for (i = 0; i < 12; i++)
-			tbl_entry.regval[i] =
-			pipe_ctx->stream->csc_color_matrix.matrix[i];
-
-		pipe_ctx->plane_res.xfm->funcs->opp_set_csc_adjustment
-				(pipe_ctx->plane_res.xfm, &tbl_entry);
-	}
-
-	if (pipe_ctx->stream->gamut_remap_matrix.enable_remap == true) {
-		adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW;
-
-		for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++)
-			adjust.temperature_matrix[i] =
-				pipe_ctx->stream->gamut_remap_matrix.matrix[i];
-	}
-
-	pipe_ctx->plane_res.xfm->funcs->transform_set_gamut_remap(pipe_ctx->plane_res.xfm, &adjust);
-
-	pipe_ctx->plane_res.scl_data.lb_params.alpha_en = pipe_ctx->bottom_pipe != 0;
-	program_scaler(dc, pipe_ctx);
-
-	program_surface_visibility(dc, pipe_ctx);
-
-	mi->funcs->mem_input_program_surface_config(
-			mi,
-			plane_state->format,
-			&plane_state->tiling_info,
-			&plane_state->plane_size,
-			plane_state->rotation,
-			NULL,
-			false);
-	if (mi->funcs->set_blank)
-		mi->funcs->set_blank(mi, pipe_ctx->plane_state->visible);
-
-	if (dc->config.gpu_vm_support)
-		mi->funcs->mem_input_program_pte_vm(
-				pipe_ctx->plane_res.mi,
-				plane_state->format,
-				&plane_state->tiling_info,
-				plane_state->rotation);
-}
-
 static void update_plane_addr(const struct dc *dc,
 		struct pipe_ctx *pipe_ctx)
 {
@@ -2699,8 +2679,11 @@ static void dce110_program_front_end_for_pipe(
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct xfm_grph_csc_adjustment adjust;
 	struct out_csc_color_matrix tbl_entry;
+#if defined(CONFIG_DRM_AMD_DC_FBC)
+	unsigned int underlay_idx = dc->res_pool->underlay_pipe_index;
+#endif
 	unsigned int i;
-	struct dc_context *ctx = dc->ctx;
+	DC_LOGGER_INIT();
 	memset(&tbl_entry, 0, sizeof(tbl_entry));
 
 	if (dc->current_state)
@@ -2740,7 +2723,9 @@ static void dce110_program_front_end_for_pipe(
 	program_scaler(dc, pipe_ctx);
 
 #if defined(CONFIG_DRM_AMD_DC_FBC)
-	if (dc->fbc_compressor && old_pipe->stream) {
+	/* fbc not applicable on Underlay pipe */
+	if (dc->fbc_compressor && old_pipe->stream &&
+	    pipe_ctx->pipe_idx != underlay_idx) {
 		if (plane_state->tiling_info.gfx8.array_mode == DC_ARRAY_LINEAR_GENERAL)
 			dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
 		else
@@ -2776,13 +2761,13 @@ static void dce110_program_front_end_for_pipe(
 		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
 
 	DC_LOG_SURFACE(
-			"Pipe:%d 0x%x: addr hi:0x%x, "
+			"Pipe:%d %p: addr hi:0x%x, "
 			"addr low:0x%x, "
 			"src: %d, %d, %d,"
 			" %d; dst: %d, %d, %d, %d;"
 			"clip: %d, %d, %d, %d\n",
 			pipe_ctx->pipe_idx,
-			pipe_ctx->plane_state,
+			(void *) pipe_ctx->plane_state,
 			pipe_ctx->plane_state->address.grph.addr.high_part,
 			pipe_ctx->plane_state->address.grph.addr.low_part,
 			pipe_ctx->plane_state->src_rect.x,
@@ -2970,7 +2955,6 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.init_hw = init_hw,
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = dce110_apply_ctx_for_surface,
-	.set_plane_config = set_plane_config,
 	.update_plane_addr = update_plane_addr,
 	.update_pending_status = dce110_update_pending_status,
 	.set_input_transfer_func = dce110_set_input_transfer_func,
@@ -2993,7 +2977,7 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.get_position = get_position,
 	.set_static_screen_control = set_static_screen_control,
 	.reset_hw_ctx_wrap = dce110_reset_hw_ctx_wrap,
-	.prog_pixclk_crtc_otg = dce110_prog_pixclk_crtc_otg,
+	.enable_stream_timing = dce110_enable_stream_timing,
 	.setup_stereo = NULL,
 	.set_avmute = dce110_set_avmute,
 	.wait_for_mpcc_disconnect = dce110_wait_for_mpcc_disconnect,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
index 7bab8c6d2a73..0564c8e31252 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
@@ -923,6 +923,7 @@ void dce_mem_input_v_program_display_marks(
 	struct mem_input *mem_input,
 	struct dce_watermarks nbp,
 	struct dce_watermarks stutter,
+	struct dce_watermarks stutter_enter,
 	struct dce_watermarks urgent,
 	uint32_t total_dest_line_time_ns)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index b1f14be20fdf..ee33786bdef6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -930,38 +930,6 @@ static enum dc_status dce110_add_stream_to_ctx(
 	return result;
 }
 
-static enum dc_status dce110_validate_guaranteed(
-		struct dc *dc,
-		struct dc_stream_state *dc_stream,
-		struct dc_state *context)
-{
-	enum dc_status result = DC_ERROR_UNEXPECTED;
-
-	context->streams[0] = dc_stream;
-	dc_stream_retain(context->streams[0]);
-	context->stream_count++;
-
-	result = resource_map_pool_resources(dc, context, dc_stream);
-
-	if (result == DC_OK)
-		result = resource_map_clock_resources(dc, context, dc_stream);
-
-	if (result == DC_OK)
-		result = build_mapped_resource(dc, context, dc_stream);
-
-	if (result == DC_OK) {
-		validate_guaranteed_copy_streams(
-				context, dc->caps.max_streams);
-		result = resource_build_scaling_params_for_context(dc, context);
-	}
-
-	if (result == DC_OK)
-		if (!dce110_validate_bandwidth(dc, context))
-			result = DC_FAIL_BANDWIDTH_VALIDATE;
-
-	return result;
-}
-
 static struct pipe_ctx *dce110_acquire_underlay(
 		struct dc_state *context,
 		const struct resource_pool *pool,
@@ -1036,7 +1004,6 @@ static void dce110_destroy_resource_pool(struct resource_pool **pool)
 static const struct resource_funcs dce110_res_pool_funcs = {
 	.destroy = dce110_destroy_resource_pool,
 	.link_enc_create = dce110_link_encoder_create,
-	.validate_guaranteed = dce110_validate_guaranteed,
 	.validate_bandwidth = dce110_validate_bandwidth,
 	.validate_plane = dce110_validate_plane,
 	.acquire_idle_pipe_for_layer = dce110_acquire_underlay,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
index be7153924a70..1b2fe0df347f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
@@ -431,14 +431,6 @@ void dce110_timing_generator_set_drr(
 			0,
 			CRTC_V_TOTAL_CONTROL,
 			CRTC_SET_V_TOTAL_MIN_MASK);
-		set_reg_field_value(v_total_min,
-				0,
-				CRTC_V_TOTAL_MIN,
-				CRTC_V_TOTAL_MIN);
-		set_reg_field_value(v_total_max,
-				0,
-				CRTC_V_TOTAL_MAX,
-				CRTC_V_TOTAL_MAX);
 		set_reg_field_value(v_total_cntl,
 				0,
 				CRTC_V_TOTAL_CONTROL,
@@ -447,6 +439,14 @@ void dce110_timing_generator_set_drr(
 				0,
 				CRTC_V_TOTAL_CONTROL,
 				CRTC_V_TOTAL_MAX_SEL);
+		set_reg_field_value(v_total_min,
+				0,
+				CRTC_V_TOTAL_MIN,
+				CRTC_V_TOTAL_MIN);
+		set_reg_field_value(v_total_max,
+				0,
+				CRTC_V_TOTAL_MAX,
+				CRTC_V_TOTAL_MAX);
 		set_reg_field_value(v_total_cntl,
 				0,
 				CRTC_V_TOTAL_CONTROL,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator_v.c
index 8ad04816e7d3..a3cef60380ed 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator_v.c
@@ -648,12 +648,6 @@ static void dce110_timing_generator_v_disable_vga(
 	return;
 }
 
-static bool dce110_tg_v_is_blanked(struct timing_generator *tg)
-{
-	/* Signal comes from the primary pipe, underlay is never blanked. */
-	return false;
-}
-
 /** ********************************************************************************************
  *
  * DCE11 Timing Generator Constructor / Destructor
@@ -670,7 +664,6 @@ static const struct timing_generator_funcs dce110_tg_v_funcs = {
 		.set_early_control = dce110_timing_generator_v_set_early_control,
 		.wait_for_state = dce110_timing_generator_v_wait_for_state,
 		.set_blank = dce110_timing_generator_v_set_blank,
-		.is_blanked = dce110_tg_v_is_blanked,
 		.set_colors = dce110_timing_generator_v_set_colors,
 		.set_overscan_blank_color =
 				dce110_timing_generator_v_set_overscan_color_black,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
index 8ba3c12fc608..a7dce060204f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
@@ -373,13 +373,13 @@ static void calculate_inits(
 	struct rect *chroma_viewport)
 {
 	inits->h_int_scale_ratio_luma =
-		dal_fixed31_32_u2d19(data->ratios.horz) << 5;
+		dc_fixpt_u2d19(data->ratios.horz) << 5;
 	inits->v_int_scale_ratio_luma =
-		dal_fixed31_32_u2d19(data->ratios.vert) << 5;
+		dc_fixpt_u2d19(data->ratios.vert) << 5;
 	inits->h_int_scale_ratio_chroma =
-		dal_fixed31_32_u2d19(data->ratios.horz_c) << 5;
+		dc_fixpt_u2d19(data->ratios.horz_c) << 5;
 	inits->v_int_scale_ratio_chroma =
-		dal_fixed31_32_u2d19(data->ratios.vert_c) << 5;
+		dc_fixpt_u2d19(data->ratios.vert_c) << 5;
 
 	inits->h_init_luma.integer = 1;
 	inits->v_init_luma.integer = 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index cd1e3f72c44e..00c0a1ef15eb 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -430,7 +430,7 @@ static struct stream_encoder *dce112_stream_encoder_create(
 
 	if (!enc110)
 		return NULL;
-	
+
 	dce110_stream_encoder_construct(enc110, ctx, ctx->dc_bios, eng_id,
 					&stream_enc_regs[eng_id],
 					&se_shift, &se_mask);
@@ -867,38 +867,6 @@ enum dc_status dce112_add_stream_to_ctx(
 	return result;
 }
 
-enum dc_status dce112_validate_guaranteed(
-		struct dc *dc,
-		struct dc_stream_state *stream,
-		struct dc_state *context)
-{
-	enum dc_status result = DC_ERROR_UNEXPECTED;
-
-	context->streams[0] = stream;
-	dc_stream_retain(context->streams[0]);
-	context->stream_count++;
-
-	result = resource_map_pool_resources(dc, context, stream);
-
-	if (result == DC_OK)
-		result = resource_map_phy_clock_resources(dc, context, stream);
-
-	if (result == DC_OK)
-		result = build_mapped_resource(dc, context, stream);
-
-	if (result == DC_OK) {
-		validate_guaranteed_copy_streams(
-				context, dc->caps.max_streams);
-		result = resource_build_scaling_params_for_context(dc, context);
-	}
-
-	if (result == DC_OK)
-		if (!dce112_validate_bandwidth(dc, context))
-			result = DC_FAIL_BANDWIDTH_VALIDATE;
-
-	return result;
-}
-
 enum dc_status dce112_validate_global(
 		struct dc *dc,
 		struct dc_state *context)
@@ -921,7 +889,6 @@ static void dce112_destroy_resource_pool(struct resource_pool **pool)
 static const struct resource_funcs dce112_res_pool_funcs = {
 	.destroy = dce112_destroy_resource_pool,
 	.link_enc_create = dce112_link_encoder_create,
-	.validate_guaranteed = dce112_validate_guaranteed,
 	.validate_bandwidth = dce112_validate_bandwidth,
 	.validate_plane = dce100_validate_plane,
 	.add_stream_to_ctx = dce112_add_stream_to_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.h b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.h
index d5c19d34eb0a..95a403396219 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.h
@@ -42,11 +42,6 @@ enum dc_status dce112_validate_with_context(
 		struct dc_state *context,
 		struct dc_state *old_context);
 
-enum dc_status dce112_validate_guaranteed(
-		struct dc *dc,
-		struct dc_stream_state *dc_stream,
-		struct dc_state *context);
-
 bool dce112_validate_bandwidth(
 	struct dc *dc,
 	struct dc_state *context);
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 4659a4bfabaa..2d58daccc005 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -652,7 +652,7 @@ static struct mem_input *dce120_mem_input_create(
 		return NULL;
 	}
 
-	dce112_mem_input_construct(dce_mi, ctx, inst, &mi_regs[inst], &mi_shifts, &mi_masks);
+	dce120_mem_input_construct(dce_mi, ctx, inst, &mi_regs[inst], &mi_shifts, &mi_masks);
 	return &dce_mi->base;
 }
 
@@ -684,7 +684,6 @@ static void dce120_destroy_resource_pool(struct resource_pool **pool)
 static const struct resource_funcs dce120_res_pool_funcs = {
 	.destroy = dce120_destroy_resource_pool,
 	.link_enc_create = dce120_link_encoder_create,
-	.validate_guaranteed = dce112_validate_guaranteed,
 	.validate_bandwidth = dce112_validate_bandwidth,
 	.validate_plane = dce100_validate_plane,
 	.add_stream_to_ctx = dce112_add_stream_to_ctx
@@ -815,14 +814,25 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	dm_pp_notify_wm_clock_changes(dc->ctx, &clk_ranges);
 }
 
+static uint32_t read_pipe_fuses(struct dc_context *ctx)
+{
+	uint32_t value = dm_read_reg_soc15(ctx, mmCC_DC_PIPE_DIS, 0);
+	/* VG20 support max 6 pipes */
+	value = value & 0x3f;
+	return value;
+}
+
 static bool construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dce110_resource_pool *pool)
 {
 	unsigned int i;
+	int j;
 	struct dc_context *ctx = dc->ctx;
 	struct irq_service_init_data irq_init_data;
+	bool harvest_enabled = ASICREV_IS_VEGA20_P(ctx->asic_id.hw_internal_rev);
+	uint32_t pipe_fuses;
 
 	ctx->dc_bios->regs = &bios_regs;
 
@@ -916,28 +926,41 @@ static bool construct(
 	if (!pool->base.irqs)
 		goto irqs_create_fail;
 
+	/* retrieve valid pipe fuses */
+	if (harvest_enabled)
+		pipe_fuses = read_pipe_fuses(ctx);
+
+	/* index to valid pipe resource */
+	j = 0;
 	for (i = 0; i < pool->base.pipe_count; i++) {
-		pool->base.timing_generators[i] =
+		if (harvest_enabled) {
+			if ((pipe_fuses & (1 << i)) != 0) {
+				dm_error("DC: skip invalid pipe %d!\n", i);
+				continue;
+			}
+		}
+
+		pool->base.timing_generators[j] =
 				dce120_timing_generator_create(
 					ctx,
 					i,
 					&dce120_tg_offsets[i]);
-		if (pool->base.timing_generators[i] == NULL) {
+		if (pool->base.timing_generators[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error("DC: failed to create tg!\n");
 			goto controller_create_fail;
 		}
 
-		pool->base.mis[i] = dce120_mem_input_create(ctx, i);
+		pool->base.mis[j] = dce120_mem_input_create(ctx, i);
 
-		if (pool->base.mis[i] == NULL) {
+		if (pool->base.mis[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create memory input!\n");
 			goto controller_create_fail;
 		}
 
-		pool->base.ipps[i] = dce120_ipp_create(ctx, i);
+		pool->base.ipps[j] = dce120_ipp_create(ctx, i);
 		if (pool->base.ipps[i] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
@@ -945,7 +968,7 @@ static bool construct(
 			goto controller_create_fail;
 		}
 
-		pool->base.transforms[i] = dce120_transform_create(ctx, i);
+		pool->base.transforms[j] = dce120_transform_create(ctx, i);
 		if (pool->base.transforms[i] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
@@ -953,16 +976,23 @@ static bool construct(
 			goto res_create_fail;
 		}
 
-		pool->base.opps[i] = dce120_opp_create(
+		pool->base.opps[j] = dce120_opp_create(
 			ctx,
 			i);
-		if (pool->base.opps[i] == NULL) {
+		if (pool->base.opps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create output pixel processor!\n");
 		}
+
+		/* check next valid pipe */
+		j++;
 	}
 
+	/* valid pipe num */
+	pool->base.pipe_count = j;
+	pool->base.timing_generator_count = j;
+
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			 &res_create_funcs))
 		goto res_create_fail;
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
index 7bee78172d85..2ea490f8482e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
@@ -570,12 +570,6 @@ void dce120_timing_generator_set_drr(
 				0x180);
 
 	} else {
-		CRTC_REG_UPDATE(
-				CRTC0_CRTC_V_TOTAL_MIN,
-				CRTC_V_TOTAL_MIN, 0);
-		CRTC_REG_UPDATE(
-				CRTC0_CRTC_V_TOTAL_MAX,
-				CRTC_V_TOTAL_MAX, 0);
 		CRTC_REG_SET_N(CRTC0_CRTC_V_TOTAL_CONTROL, 5,
 				FD(CRTC0_CRTC_V_TOTAL_CONTROL__CRTC_V_TOTAL_MIN_SEL), 0,
 				FD(CRTC0_CRTC_V_TOTAL_CONTROL__CRTC_V_TOTAL_MAX_SEL), 0,
@@ -583,6 +577,12 @@ void dce120_timing_generator_set_drr(
 				FD(CRTC0_CRTC_V_TOTAL_CONTROL__CRTC_FORCE_LOCK_TO_MASTER_VSYNC), 0,
 				FD(CRTC0_CRTC_V_TOTAL_CONTROL__CRTC_SET_V_TOTAL_MIN_MASK), 0);
 		CRTC_REG_UPDATE(
+				CRTC0_CRTC_V_TOTAL_MIN,
+				CRTC_V_TOTAL_MIN, 0);
+		CRTC_REG_UPDATE(
+				CRTC0_CRTC_V_TOTAL_MAX,
+				CRTC_V_TOTAL_MAX, 0);
+		CRTC_REG_UPDATE(
 				CRTC0_CRTC_STATIC_SCREEN_CONTROL,
 				CRTC_STATIC_SCREEN_EVENT_MASK,
 				0);
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 5d854a37a978..48a068964722 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -691,23 +691,6 @@ static void destruct(struct dce110_resource_pool *pool)
 	}
 }
 
-static enum dc_status build_mapped_resource(
-		const struct dc *dc,
-		struct dc_state *context,
-		struct dc_stream_state *stream)
-{
-	struct pipe_ctx *pipe_ctx = resource_get_head_pipe_for_stream(&context->res_ctx, stream);
-
-	if (!pipe_ctx)
-		return DC_ERROR_UNEXPECTED;
-
-	dce110_resource_build_pipe_hw_param(pipe_ctx);
-
-	resource_build_info_frame(pipe_ctx);
-
-	return DC_OK;
-}
-
 bool dce80_validate_bandwidth(
 	struct dc *dc,
 	struct dc_state *context)
@@ -749,37 +732,6 @@ enum dc_status dce80_validate_global(
 	return DC_OK;
 }
 
-enum dc_status dce80_validate_guaranteed(
-		struct dc *dc,
-		struct dc_stream_state *dc_stream,
-		struct dc_state *context)
-{
-	enum dc_status result = DC_ERROR_UNEXPECTED;
-
-	context->streams[0] = dc_stream;
-	dc_stream_retain(context->streams[0]);
-	context->stream_count++;
-
-	result = resource_map_pool_resources(dc, context, dc_stream);
-
-	if (result == DC_OK)
-		result = resource_map_clock_resources(dc, context, dc_stream);
-
-	if (result == DC_OK)
-		result = build_mapped_resource(dc, context, dc_stream);
-
-	if (result == DC_OK) {
-		validate_guaranteed_copy_streams(
-				context, dc->caps.max_streams);
-		result = resource_build_scaling_params_for_context(dc, context);
-	}
-
-	if (result == DC_OK)
-		result = dce80_validate_bandwidth(dc, context);
-
-	return result;
-}
-
 static void dce80_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
@@ -792,7 +744,6 @@ static void dce80_destroy_resource_pool(struct resource_pool **pool)
 static const struct resource_funcs dce80_res_pool_funcs = {
 	.destroy = dce80_destroy_resource_pool,
 	.link_enc_create = dce80_link_encoder_create,
-	.validate_guaranteed = dce80_validate_guaranteed,
 	.validate_bandwidth = dce80_validate_bandwidth,
 	.validate_plane = dce100_validate_plane,
 	.add_stream_to_ctx = dce100_add_stream_to_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
index 5469bdfe19f3..84f52c63d95c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
@@ -26,7 +26,7 @@ DCN10 = dcn10_resource.o dcn10_ipp.o dcn10_hw_sequencer.o \
 		dcn10_dpp.o dcn10_opp.o dcn10_optc.o \
 		dcn10_hubp.o dcn10_mpc.o \
 		dcn10_dpp_dscl.o dcn10_dpp_cm.o dcn10_cm_common.o \
-		dcn10_hubbub.o
+		dcn10_hubbub.o dcn10_stream_encoder.o dcn10_link_encoder.o
 
 AMD_DAL_DCN10 = $(addprefix $(AMDDALPATH)/dc/dcn10/,$(DCN10))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 881a1bff94d2..5d95a997fd9f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -169,7 +169,7 @@ bool cm_helper_convert_to_custom_float(
 	}
 
 	if (fixpoint == true)
-		arr_points[1].custom_float_y = dal_fixed31_32_clamp_u0d14(arr_points[1].y);
+		arr_points[1].custom_float_y = dc_fixpt_clamp_u0d14(arr_points[1].y);
 	else if (!convert_to_custom_float_format(arr_points[1].y, &fmt,
 		&arr_points[1].custom_float_y)) {
 		BREAK_TO_DEBUGGER();
@@ -327,19 +327,19 @@ bool cm_helper_translate_curve_to_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
-	arr_points[0].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-					     dal_fixed31_32_from_int(region_start));
-	arr_points[1].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-					     dal_fixed31_32_from_int(region_end));
+	arr_points[0].x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_start));
+	arr_points[1].x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_end));
 
 	y_r = rgb_resulted[0].red;
 	y_g = rgb_resulted[0].green;
 	y_b = rgb_resulted[0].blue;
 
-	y1_min = dal_fixed31_32_min(y_r, dal_fixed31_32_min(y_g, y_b));
+	y1_min = dc_fixpt_min(y_r, dc_fixpt_min(y_g, y_b));
 
 	arr_points[0].y = y1_min;
-	arr_points[0].slope = dal_fixed31_32_div(arr_points[0].y, arr_points[0].x);
+	arr_points[0].slope = dc_fixpt_div(arr_points[0].y, arr_points[0].x);
 	y_r = rgb_resulted[hw_points - 1].red;
 	y_g = rgb_resulted[hw_points - 1].green;
 	y_b = rgb_resulted[hw_points - 1].blue;
@@ -347,35 +347,35 @@ bool cm_helper_translate_curve_to_hw_format(
 	/* see comment above, m_arrPoints[1].y should be the Y value for the
 	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
 	 */
-	y3_max = dal_fixed31_32_max(y_r, dal_fixed31_32_max(y_g, y_b));
+	y3_max = dc_fixpt_max(y_r, dc_fixpt_max(y_g, y_b));
 
 	arr_points[1].y = y3_max;
 
-	arr_points[1].slope = dal_fixed31_32_zero;
+	arr_points[1].slope = dc_fixpt_zero;
 
 	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
 		/* for PQ, we want to have a straight line from last HW X point,
 		 * and the slope to be such that we hit 1.0 at 10000 nits.
 		 */
 		const struct fixed31_32 end_value =
-				dal_fixed31_32_from_int(125);
+				dc_fixpt_from_int(125);
 
-		arr_points[1].slope = dal_fixed31_32_div(
-			dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
-			dal_fixed31_32_sub(end_value, arr_points[1].x));
+		arr_points[1].slope = dc_fixpt_div(
+			dc_fixpt_sub(dc_fixpt_one, arr_points[1].y),
+			dc_fixpt_sub(end_value, arr_points[1].x));
 	}
 
 	lut_params->hw_points_num = hw_points;
 
-	i = 1;
-	for (k = 0; k < MAX_REGIONS_NUMBER && i < MAX_REGIONS_NUMBER; k++) {
+	k = 0;
+	for (i = 1; i < MAX_REGIONS_NUMBER; i++) {
 		if (seg_distr[k] != -1) {
 			lut_params->arr_curve_points[k].segments_num =
 					seg_distr[k];
 			lut_params->arr_curve_points[i].offset =
 					lut_params->arr_curve_points[k].offset + (1 << seg_distr[k]);
 		}
-		i++;
+		k++;
 	}
 
 	if (seg_distr[k] != -1)
@@ -386,24 +386,24 @@ bool cm_helper_translate_curve_to_hw_format(
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dal_fixed31_32_lt(rgb_plus_1->red, rgb->red))
+		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
 			rgb_plus_1->red = rgb->red;
-		if (dal_fixed31_32_lt(rgb_plus_1->green, rgb->green))
+		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
 			rgb_plus_1->green = rgb->green;
-		if (dal_fixed31_32_lt(rgb_plus_1->blue, rgb->blue))
+		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
 			rgb_plus_1->blue = rgb->blue;
 
-		rgb->delta_red   = dal_fixed31_32_sub(rgb_plus_1->red,   rgb->red);
-		rgb->delta_green = dal_fixed31_32_sub(rgb_plus_1->green, rgb->green);
-		rgb->delta_blue  = dal_fixed31_32_sub(rgb_plus_1->blue,  rgb->blue);
+		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
+		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
+		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
 
 		if (fixpoint == true) {
-			rgb->delta_red_reg   = dal_fixed31_32_clamp_u0d10(rgb->delta_red);
-			rgb->delta_green_reg = dal_fixed31_32_clamp_u0d10(rgb->delta_green);
-			rgb->delta_blue_reg  = dal_fixed31_32_clamp_u0d10(rgb->delta_blue);
-			rgb->red_reg         = dal_fixed31_32_clamp_u0d14(rgb->red);
-			rgb->green_reg       = dal_fixed31_32_clamp_u0d14(rgb->green);
-			rgb->blue_reg        = dal_fixed31_32_clamp_u0d14(rgb->blue);
+			rgb->delta_red_reg   = dc_fixpt_clamp_u0d10(rgb->delta_red);
+			rgb->delta_green_reg = dc_fixpt_clamp_u0d10(rgb->delta_green);
+			rgb->delta_blue_reg  = dc_fixpt_clamp_u0d10(rgb->delta_blue);
+			rgb->red_reg         = dc_fixpt_clamp_u0d14(rgb->red);
+			rgb->green_reg       = dc_fixpt_clamp_u0d14(rgb->green);
+			rgb->blue_reg        = dc_fixpt_clamp_u0d14(rgb->blue);
 		}
 
 		++rgb_plus_1;
@@ -489,19 +489,19 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
-	arr_points[0].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-					     dal_fixed31_32_from_int(region_start));
-	arr_points[1].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
-					     dal_fixed31_32_from_int(region_end));
+	arr_points[0].x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_start));
+	arr_points[1].x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_end));
 
 	y_r = rgb_resulted[0].red;
 	y_g = rgb_resulted[0].green;
 	y_b = rgb_resulted[0].blue;
 
-	y1_min = dal_fixed31_32_min(y_r, dal_fixed31_32_min(y_g, y_b));
+	y1_min = dc_fixpt_min(y_r, dc_fixpt_min(y_g, y_b));
 
 	arr_points[0].y = y1_min;
-	arr_points[0].slope = dal_fixed31_32_div(arr_points[0].y, arr_points[0].x);
+	arr_points[0].slope = dc_fixpt_div(arr_points[0].y, arr_points[0].x);
 	y_r = rgb_resulted[hw_points - 1].red;
 	y_g = rgb_resulted[hw_points - 1].green;
 	y_b = rgb_resulted[hw_points - 1].blue;
@@ -509,35 +509,35 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 	/* see comment above, m_arrPoints[1].y should be the Y value for the
 	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
 	 */
-	y3_max = dal_fixed31_32_max(y_r, dal_fixed31_32_max(y_g, y_b));
+	y3_max = dc_fixpt_max(y_r, dc_fixpt_max(y_g, y_b));
 
 	arr_points[1].y = y3_max;
 
-	arr_points[1].slope = dal_fixed31_32_zero;
+	arr_points[1].slope = dc_fixpt_zero;
 
 	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
 		/* for PQ, we want to have a straight line from last HW X point,
 		 * and the slope to be such that we hit 1.0 at 10000 nits.
 		 */
 		const struct fixed31_32 end_value =
-				dal_fixed31_32_from_int(125);
+				dc_fixpt_from_int(125);
 
-		arr_points[1].slope = dal_fixed31_32_div(
-			dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
-			dal_fixed31_32_sub(end_value, arr_points[1].x));
+		arr_points[1].slope = dc_fixpt_div(
+			dc_fixpt_sub(dc_fixpt_one, arr_points[1].y),
+			dc_fixpt_sub(end_value, arr_points[1].x));
 	}
 
 	lut_params->hw_points_num = hw_points;
 
-	i = 1;
-	for (k = 0; k < MAX_REGIONS_NUMBER && i < MAX_REGIONS_NUMBER; k++) {
+	k = 0;
+	for (i = 1; i < MAX_REGIONS_NUMBER; i++) {
 		if (seg_distr[k] != -1) {
 			lut_params->arr_curve_points[k].segments_num =
 					seg_distr[k];
 			lut_params->arr_curve_points[i].offset =
 					lut_params->arr_curve_points[k].offset + (1 << seg_distr[k]);
 		}
-		i++;
+		k++;
 	}
 
 	if (seg_distr[k] != -1)
@@ -548,16 +548,16 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dal_fixed31_32_lt(rgb_plus_1->red, rgb->red))
+		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
 			rgb_plus_1->red = rgb->red;
-		if (dal_fixed31_32_lt(rgb_plus_1->green, rgb->green))
+		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
 			rgb_plus_1->green = rgb->green;
-		if (dal_fixed31_32_lt(rgb_plus_1->blue, rgb->blue))
+		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
 			rgb_plus_1->blue = rgb->blue;
 
-		rgb->delta_red   = dal_fixed31_32_sub(rgb_plus_1->red,   rgb->red);
-		rgb->delta_green = dal_fixed31_32_sub(rgb_plus_1->green, rgb->green);
-		rgb->delta_blue  = dal_fixed31_32_sub(rgb_plus_1->blue,  rgb->blue);
+		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
+		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
+		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
 
 		++rgb_plus_1;
 		++rgb;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index e305c28c98de..46a35c7f01df 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -98,6 +98,30 @@ enum gamut_remap_select {
 	GAMUT_REMAP_COMB_COEFF
 };
 
+void dpp_read_state(struct dpp *dpp_base,
+		struct dcn_dpp_state *s)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	REG_GET(CM_IGAM_CONTROL,
+			CM_IGAM_LUT_MODE, &s->igam_lut_mode);
+	REG_GET(CM_IGAM_CONTROL,
+			CM_IGAM_INPUT_FORMAT, &s->igam_input_format);
+	REG_GET(CM_DGAM_CONTROL,
+			CM_DGAM_LUT_MODE, &s->dgam_lut_mode);
+	REG_GET(CM_RGAM_CONTROL,
+			CM_RGAM_LUT_MODE, &s->rgam_lut_mode);
+	REG_GET(CM_GAMUT_REMAP_CONTROL,
+			CM_GAMUT_REMAP_MODE, &s->gamut_remap_mode);
+
+	s->gamut_remap_c11_c12 = REG_READ(CM_GAMUT_REMAP_C11_C12);
+	s->gamut_remap_c13_c14 = REG_READ(CM_GAMUT_REMAP_C13_C14);
+	s->gamut_remap_c21_c22 = REG_READ(CM_GAMUT_REMAP_C21_C22);
+	s->gamut_remap_c23_c24 = REG_READ(CM_GAMUT_REMAP_C23_C24);
+	s->gamut_remap_c31_c32 = REG_READ(CM_GAMUT_REMAP_C31_C32);
+	s->gamut_remap_c33_c34 = REG_READ(CM_GAMUT_REMAP_C33_C34);
+}
+
 /* Program gamut remap in bypass mode */
 void dpp_set_gamut_remap_bypass(struct dcn10_dpp *dpp)
 {
@@ -106,7 +130,7 @@ void dpp_set_gamut_remap_bypass(struct dcn10_dpp *dpp)
 	/* Gamut remap in bypass */
 }
 
-#define IDENTITY_RATIO(ratio) (dal_fixed31_32_u2d19(ratio) == (1 << 19))
+#define IDENTITY_RATIO(ratio) (dc_fixpt_u2d19(ratio) == (1 << 19))
 
 
 bool dpp_get_optimal_number_of_taps(
@@ -121,6 +145,18 @@ bool dpp_get_optimal_number_of_taps(
 	else
 		pixel_width = scl_data->viewport.width;
 
+	/* Some ASICs does not support  FP16 scaling, so we reject modes require this*/
+	if (scl_data->viewport.width  != scl_data->h_active &&
+		scl_data->viewport.height != scl_data->v_active &&
+		dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
+		scl_data->format == PIXEL_FORMAT_FP16)
+		return false;
+
+	if (scl_data->viewport.width > scl_data->h_active &&
+		dpp->ctx->dc->debug.max_downscale_src_width != 0 &&
+		scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width)
+		return false;
+
 	/* TODO: add lb check */
 
 	/* No support for programming ratio of 4, drop to 3.99999.. */
@@ -257,7 +293,7 @@ void dpp1_cnv_setup (
 		struct dpp *dpp_base,
 		enum surface_pixel_format format,
 		enum expansion_mode mode,
-		struct csc_transform input_csc_color_matrix,
+		struct dc_csc_transform input_csc_color_matrix,
 		enum dc_color_space input_color_space)
 {
 	uint32_t pixel_format;
@@ -416,7 +452,7 @@ void dpp1_set_cursor_position(
 	if (src_x_offset >= (int)param->viewport_width)
 		cur_en = 0;  /* not visible beyond right edge*/
 
-	if (src_x_offset + (int)width < 0)
+	if (src_x_offset + (int)width <= 0)
 		cur_en = 0;  /* not visible beyond left edge*/
 
 	REG_UPDATE(CURSOR0_CONTROL,
@@ -443,6 +479,7 @@ void dpp1_dppclk_control(
 }
 
 static const struct dpp_funcs dcn10_dpp_funcs = {
+		.dpp_read_state = dpp_read_state,
 		.dpp_reset = dpp_reset,
 		.dpp_set_scaler = dpp1_dscl_set_scaler_manual_scale,
 		.dpp_get_optimal_number_of_taps = dpp_get_optimal_number_of_taps,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
index 17b062a8f88a..5944a3ba0409 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
@@ -44,6 +44,10 @@
 #define TF_REG_LIST_DCN(id) \
 	SRI(CM_GAMUT_REMAP_CONTROL, CM, id),\
 	SRI(CM_GAMUT_REMAP_C11_C12, CM, id),\
+	SRI(CM_GAMUT_REMAP_C13_C14, CM, id),\
+	SRI(CM_GAMUT_REMAP_C21_C22, CM, id),\
+	SRI(CM_GAMUT_REMAP_C23_C24, CM, id),\
+	SRI(CM_GAMUT_REMAP_C31_C32, CM, id),\
 	SRI(CM_GAMUT_REMAP_C33_C34, CM, id),\
 	SRI(DSCL_EXT_OVERSCAN_LEFT_RIGHT, DSCL, id), \
 	SRI(DSCL_EXT_OVERSCAN_TOP_BOTTOM, DSCL, id), \
@@ -108,6 +112,8 @@
 	SRI(CM_DGAM_LUT_DATA, CM, id), \
 	SRI(CM_CONTROL, CM, id), \
 	SRI(CM_DGAM_CONTROL, CM, id), \
+	SRI(CM_TEST_DEBUG_INDEX, CM, id), \
+	SRI(CM_TEST_DEBUG_DATA, CM, id), \
 	SRI(FORMAT_CONTROL, CNVC_CFG, id), \
 	SRI(CNVC_SURFACE_PIXEL_FORMAT, CNVC_CFG, id), \
 	SRI(CURSOR0_CONTROL, CNVC_CUR, id), \
@@ -175,6 +181,14 @@
 	TF_SF(CM0_CM_GAMUT_REMAP_CONTROL, CM_GAMUT_REMAP_MODE, mask_sh),\
 	TF_SF(CM0_CM_GAMUT_REMAP_C11_C12, CM_GAMUT_REMAP_C11, mask_sh),\
 	TF_SF(CM0_CM_GAMUT_REMAP_C11_C12, CM_GAMUT_REMAP_C12, mask_sh),\
+	TF_SF(CM0_CM_GAMUT_REMAP_C13_C14, CM_GAMUT_REMAP_C13, mask_sh),\
+	TF_SF(CM0_CM_GAMUT_REMAP_C13_C14, CM_GAMUT_REMAP_C14, mask_sh),\
+	TF_SF(CM0_CM_GAMUT_REMAP_C21_C22, CM_GAMUT_REMAP_C21, mask_sh),\
+	TF_SF(CM0_CM_GAMUT_REMAP_C21_C22, CM_GAMUT_REMAP_C22, mask_sh),\
+	TF_SF(CM0_CM_GAMUT_REMAP_C23_C24, CM_GAMUT_REMAP_C23, mask_sh),\
+	TF_SF(CM0_CM_GAMUT_REMAP_C23_C24, CM_GAMUT_REMAP_C24, mask_sh),\
+	TF_SF(CM0_CM_GAMUT_REMAP_C31_C32, CM_GAMUT_REMAP_C31, mask_sh),\
+	TF_SF(CM0_CM_GAMUT_REMAP_C31_C32, CM_GAMUT_REMAP_C32, mask_sh),\
 	TF_SF(CM0_CM_GAMUT_REMAP_C33_C34, CM_GAMUT_REMAP_C33, mask_sh),\
 	TF_SF(CM0_CM_GAMUT_REMAP_C33_C34, CM_GAMUT_REMAP_C34, mask_sh),\
 	TF_SF(DSCL0_DSCL_EXT_OVERSCAN_LEFT_RIGHT, EXT_OVERSCAN_LEFT, mask_sh),\
@@ -300,6 +314,7 @@
 	TF_SF(CM0_CM_DGAM_LUT_INDEX, CM_DGAM_LUT_INDEX, mask_sh), \
 	TF_SF(CM0_CM_DGAM_LUT_DATA, CM_DGAM_LUT_DATA, mask_sh), \
 	TF_SF(CM0_CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, mask_sh), \
+	TF_SF(CM0_CM_TEST_DEBUG_INDEX, CM_TEST_DEBUG_INDEX, mask_sh), \
 	TF_SF(CNVC_CFG0_FORMAT_CONTROL, CNVC_BYPASS, mask_sh), \
 	TF2_SF(CNVC_CFG0, FORMAT_CONTROL__ALPHA_EN, mask_sh), \
 	TF_SF(CNVC_CFG0_FORMAT_CONTROL, FORMAT_EXPANSION_MODE, mask_sh), \
@@ -417,6 +432,41 @@
 	TF_SF(CURSOR0_CURSOR_CONTROL, CURSOR_ENABLE, mask_sh), \
 	TF_SF(DPP_TOP0_DPP_CONTROL, DPPCLK_RATE_CONTROL, mask_sh)
 
+/*
+ *
+	DCN1 CM debug status register definition
+
+	register :ID9_CM_STATUS do
+	implement_ref :cm
+	map to:  :cmdebugind, at: j
+	width 32
+	disclosure   NEVER
+
+		field :ID9_VUPDATE_CFG, [0], R
+		field :ID9_IGAM_LUT_MODE, [2..1], R
+		field :ID9_BNS_BYPASS, [3], R
+		field :ID9_ICSC_MODE, [5..4], R
+		field :ID9_DGAM_LUT_MODE, [8..6], R
+		field :ID9_HDR_BYPASS, [9], R
+		field :ID9_GAMUT_REMAP_MODE, [11..10], R
+		field :ID9_RGAM_LUT_MODE, [14..12], R
+		#1 free bit
+		field :ID9_OCSC_MODE, [18..16], R
+		field :ID9_DENORM_MODE, [21..19], R
+		field :ID9_ROUND_TRUNC_MODE, [25..22], R
+		field :ID9_DITHER_EN, [26], R
+		field :ID9_DITHER_MODE, [28..27], R
+	end
+*/
+
+#define TF_DEBUG_REG_LIST_SH_DCN10 \
+	.CM_TEST_DEBUG_DATA_ID9_ICSC_MODE = 4, \
+	.CM_TEST_DEBUG_DATA_ID9_OCSC_MODE = 16
+
+#define TF_DEBUG_REG_LIST_MASK_DCN10 \
+	.CM_TEST_DEBUG_DATA_ID9_ICSC_MODE = 0x30, \
+	.CM_TEST_DEBUG_DATA_ID9_OCSC_MODE = 0x70000
+
 #define TF_REG_FIELD_LIST(type) \
 	type EXT_OVERSCAN_LEFT; \
 	type EXT_OVERSCAN_RIGHT; \
@@ -486,6 +536,14 @@
 	type CM_GAMUT_REMAP_MODE; \
 	type CM_GAMUT_REMAP_C11; \
 	type CM_GAMUT_REMAP_C12; \
+	type CM_GAMUT_REMAP_C13; \
+	type CM_GAMUT_REMAP_C14; \
+	type CM_GAMUT_REMAP_C21; \
+	type CM_GAMUT_REMAP_C22; \
+	type CM_GAMUT_REMAP_C23; \
+	type CM_GAMUT_REMAP_C24; \
+	type CM_GAMUT_REMAP_C31; \
+	type CM_GAMUT_REMAP_C32; \
 	type CM_GAMUT_REMAP_C33; \
 	type CM_GAMUT_REMAP_C34; \
 	type CM_COMA_C11; \
@@ -1010,6 +1068,9 @@
 	type CUR0_EXPANSION_MODE; \
 	type CUR0_ENABLE; \
 	type CM_BYPASS; \
+	type CM_TEST_DEBUG_INDEX; \
+	type CM_TEST_DEBUG_DATA_ID9_ICSC_MODE; \
+	type CM_TEST_DEBUG_DATA_ID9_OCSC_MODE;\
 	type FORMAT_CONTROL__ALPHA_EN; \
 	type CUR0_COLOR0; \
 	type CUR0_COLOR1; \
@@ -1054,6 +1115,10 @@ struct dcn_dpp_mask {
 	uint32_t RECOUT_SIZE; \
 	uint32_t CM_GAMUT_REMAP_CONTROL; \
 	uint32_t CM_GAMUT_REMAP_C11_C12; \
+	uint32_t CM_GAMUT_REMAP_C13_C14; \
+	uint32_t CM_GAMUT_REMAP_C21_C22; \
+	uint32_t CM_GAMUT_REMAP_C23_C24; \
+	uint32_t CM_GAMUT_REMAP_C31_C32; \
 	uint32_t CM_GAMUT_REMAP_C33_C34; \
 	uint32_t CM_COMA_C11_C12; \
 	uint32_t CM_COMA_C33_C34; \
@@ -1255,6 +1320,8 @@ struct dcn_dpp_mask {
 	uint32_t CM_IGAM_LUT_RW_CONTROL; \
 	uint32_t CM_IGAM_LUT_RW_INDEX; \
 	uint32_t CM_IGAM_LUT_SEQ_COLOR; \
+	uint32_t CM_TEST_DEBUG_INDEX; \
+	uint32_t CM_TEST_DEBUG_DATA; \
 	uint32_t FORMAT_CONTROL; \
 	uint32_t CNVC_SURFACE_PIXEL_FORMAT; \
 	uint32_t CURSOR_CONTROL; \
@@ -1289,8 +1356,8 @@ struct dcn10_dpp {
 
 enum dcn10_input_csc_select {
 	INPUT_CSC_SELECT_BYPASS = 0,
-	INPUT_CSC_SELECT_ICSC,
-	INPUT_CSC_SELECT_COMA
+	INPUT_CSC_SELECT_ICSC = 1,
+	INPUT_CSC_SELECT_COMA = 2
 };
 
 void dpp1_set_cursor_attributes(
@@ -1364,6 +1431,9 @@ bool dpp_get_optimal_number_of_taps(
 		struct scaler_data *scl_data,
 		const struct scaling_taps *in_taps);
 
+void dpp_read_state(struct dpp *dpp_base,
+		struct dcn_dpp_state *s);
+
 void dpp_reset(struct dpp *dpp_base);
 
 void dpp1_cm_program_regamma_lut(
@@ -1408,7 +1478,7 @@ void dpp1_cnv_setup (
 		struct dpp *dpp_base,
 		enum surface_pixel_format format,
 		enum expansion_mode mode,
-		struct csc_transform input_csc_color_matrix,
+		struct dc_csc_transform input_csc_color_matrix,
 		enum dc_color_space input_color_space);
 
 void dpp1_full_bypass(struct dpp *dpp_base);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
index fb32975e4b67..116977eb24e2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
@@ -216,41 +216,55 @@ static void dpp1_cm_program_color_matrix(
 		struct dcn10_dpp *dpp,
 		const uint16_t *regval)
 {
-	uint32_t mode;
+	uint32_t ocsc_mode;
+	uint32_t cur_mode;
 	struct color_matrices_reg gam_regs;
 
-	REG_GET(CM_OCSC_CONTROL, CM_OCSC_MODE, &mode);
-
 	if (regval == NULL) {
 		BREAK_TO_DEBUGGER();
 		return;
 	}
-	mode = 4;
+
+	/* determine which CSC matrix (ocsc or comb) we are using
+	 * currently.  select the alternate set to double buffer
+	 * the CSC update so CSC is updated on frame boundary
+	 */
+	REG_SET(CM_TEST_DEBUG_INDEX, 0,
+			CM_TEST_DEBUG_INDEX, 9);
+
+	REG_GET(CM_TEST_DEBUG_DATA,
+			CM_TEST_DEBUG_DATA_ID9_OCSC_MODE, &cur_mode);
+
+	if (cur_mode != 4)
+		ocsc_mode = 4;
+	else
+		ocsc_mode = 5;
+
+
 	gam_regs.shifts.csc_c11 = dpp->tf_shift->CM_OCSC_C11;
 	gam_regs.masks.csc_c11  = dpp->tf_mask->CM_OCSC_C11;
 	gam_regs.shifts.csc_c12 = dpp->tf_shift->CM_OCSC_C12;
 	gam_regs.masks.csc_c12 = dpp->tf_mask->CM_OCSC_C12;
 
-	if (mode == 4) {
+	if (ocsc_mode == 4) {
 
 		gam_regs.csc_c11_c12 = REG(CM_OCSC_C11_C12);
 		gam_regs.csc_c33_c34 = REG(CM_OCSC_C33_C34);
 
-		cm_helper_program_color_matrices(
-				dpp->base.ctx,
-				regval,
-				&gam_regs);
-
 	} else {
 
 		gam_regs.csc_c11_c12 = REG(CM_COMB_C11_C12);
 		gam_regs.csc_c33_c34 = REG(CM_COMB_C33_C34);
 
-		cm_helper_program_color_matrices(
-				dpp->base.ctx,
-				regval,
-				&gam_regs);
 	}
+
+	cm_helper_program_color_matrices(
+			dpp->base.ctx,
+			regval,
+			&gam_regs);
+
+	REG_SET(CM_OCSC_CONTROL, 0, CM_OCSC_MODE, ocsc_mode);
+
 }
 
 void dpp1_cm_set_output_csc_default(
@@ -260,15 +274,14 @@ void dpp1_cm_set_output_csc_default(
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
 	const uint16_t *regval = NULL;
 	int arr_size;
-	uint32_t ocsc_mode = 4;
 
 	regval = find_color_matrix(colorspace, &arr_size);
 	if (regval == NULL) {
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+
 	dpp1_cm_program_color_matrix(dpp, regval);
-	REG_SET(CM_OCSC_CONTROL, 0, CM_OCSC_MODE, ocsc_mode);
 }
 
 static void dpp1_cm_get_reg_field(
@@ -329,9 +342,8 @@ void dpp1_cm_set_output_csc_adjustment(
 		const uint16_t *regval)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
-	uint32_t ocsc_mode = 4;
+
 	dpp1_cm_program_color_matrix(dpp, regval);
-	REG_SET(CM_OCSC_CONTROL, 0, CM_OCSC_MODE, ocsc_mode);
 }
 
 void dpp1_cm_power_on_regamma_lut(struct dpp *dpp_base,
@@ -437,17 +449,18 @@ void dpp1_cm_program_regamma_lutb_settings(
 void dpp1_program_input_csc(
 		struct dpp *dpp_base,
 		enum dc_color_space color_space,
-		enum dcn10_input_csc_select select,
+		enum dcn10_input_csc_select input_select,
 		const struct out_csc_color_matrix *tbl_entry)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
 	int i;
 	int arr_size = sizeof(dcn10_input_csc_matrix)/sizeof(struct dcn10_input_csc_matrix);
 	const uint16_t *regval = NULL;
-	uint32_t selection = 1;
+	uint32_t cur_select = 0;
+	enum dcn10_input_csc_select select;
 	struct color_matrices_reg gam_regs;
 
-	if (select == INPUT_CSC_SELECT_BYPASS) {
+	if (input_select == INPUT_CSC_SELECT_BYPASS) {
 		REG_SET(CM_ICSC_CONTROL, 0, CM_ICSC_MODE, 0);
 		return;
 	}
@@ -467,36 +480,45 @@ void dpp1_program_input_csc(
 		regval = tbl_entry->regval;
 	}
 
-	if (select == INPUT_CSC_SELECT_COMA)
-		selection = 2;
-	REG_SET(CM_ICSC_CONTROL, 0,
-			CM_ICSC_MODE, selection);
+	/* determine which CSC matrix (icsc or coma) we are using
+	 * currently.  select the alternate set to double buffer
+	 * the CSC update so CSC is updated on frame boundary
+	 */
+	REG_SET(CM_TEST_DEBUG_INDEX, 0,
+			CM_TEST_DEBUG_INDEX, 9);
+
+	REG_GET(CM_TEST_DEBUG_DATA,
+			CM_TEST_DEBUG_DATA_ID9_ICSC_MODE, &cur_select);
+
+	if (cur_select != INPUT_CSC_SELECT_ICSC)
+		select = INPUT_CSC_SELECT_ICSC;
+	else
+		select = INPUT_CSC_SELECT_COMA;
 
 	gam_regs.shifts.csc_c11 = dpp->tf_shift->CM_ICSC_C11;
 	gam_regs.masks.csc_c11  = dpp->tf_mask->CM_ICSC_C11;
 	gam_regs.shifts.csc_c12 = dpp->tf_shift->CM_ICSC_C12;
 	gam_regs.masks.csc_c12 = dpp->tf_mask->CM_ICSC_C12;
 
-
 	if (select == INPUT_CSC_SELECT_ICSC) {
 
 		gam_regs.csc_c11_c12 = REG(CM_ICSC_C11_C12);
 		gam_regs.csc_c33_c34 = REG(CM_ICSC_C33_C34);
 
-		cm_helper_program_color_matrices(
-				dpp->base.ctx,
-				regval,
-				&gam_regs);
 	} else {
 
 		gam_regs.csc_c11_c12 = REG(CM_COMA_C11_C12);
 		gam_regs.csc_c33_c34 = REG(CM_COMA_C33_C34);
 
-		cm_helper_program_color_matrices(
-				dpp->base.ctx,
-				regval,
-				&gam_regs);
 	}
+
+	cm_helper_program_color_matrices(
+			dpp->base.ctx,
+			regval,
+			&gam_regs);
+
+	REG_SET(CM_ICSC_CONTROL, 0,
+				CM_ICSC_MODE, select);
 }
 
 //keep here for now, decide multi dce support later
@@ -789,13 +811,13 @@ void dpp1_program_input_lut(
 	REG_UPDATE(CM_IGAM_LUT_RW_INDEX, CM_IGAM_LUT_RW_INDEX, 0);
 	for (i = 0; i < gamma->num_entries; i++) {
 		REG_SET(CM_IGAM_LUT_SEQ_COLOR, 0, CM_IGAM_LUT_SEQ_COLOR,
-				dal_fixed31_32_round(
+				dc_fixpt_round(
 					gamma->entries.red[i]));
 		REG_SET(CM_IGAM_LUT_SEQ_COLOR, 0, CM_IGAM_LUT_SEQ_COLOR,
-				dal_fixed31_32_round(
+				dc_fixpt_round(
 					gamma->entries.green[i]));
 		REG_SET(CM_IGAM_LUT_SEQ_COLOR, 0, CM_IGAM_LUT_SEQ_COLOR,
-				dal_fixed31_32_round(
+				dc_fixpt_round(
 					gamma->entries.blue[i]));
 	}
 	// Power off LUT memory
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index 3eb824debf43..4ddd6273d5a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -169,7 +169,7 @@ static enum dscl_mode_sel dpp1_dscl_get_dscl_mode(
 		const struct scaler_data *data,
 		bool dbg_always_scale)
 {
-	const long long one = dal_fixed31_32_one.value;
+	const long long one = dc_fixpt_one.value;
 
 	if (dpp_base->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT) {
 		/* DSCL is processing data in fixed format */
@@ -464,8 +464,8 @@ static enum lb_memory_config dpp1_dscl_find_lb_memory_config(struct dcn10_dpp *d
 	int num_part_y, num_part_c;
 	int vtaps = scl_data->taps.v_taps;
 	int vtaps_c = scl_data->taps.v_taps_c;
-	int ceil_vratio = dal_fixed31_32_ceil(scl_data->ratios.vert);
-	int ceil_vratio_c = dal_fixed31_32_ceil(scl_data->ratios.vert_c);
+	int ceil_vratio = dc_fixpt_ceil(scl_data->ratios.vert);
+	int ceil_vratio_c = dc_fixpt_ceil(scl_data->ratios.vert_c);
 	enum lb_memory_config mem_cfg = LB_MEMORY_CONFIG_0;
 
 	if (dpp->base.ctx->dc->debug.use_max_lb)
@@ -565,52 +565,52 @@ static void dpp1_dscl_set_manual_ratio_init(
 	uint32_t init_int = 0;
 
 	REG_SET(SCL_HORZ_FILTER_SCALE_RATIO, 0,
-			SCL_H_SCALE_RATIO, dal_fixed31_32_u2d19(data->ratios.horz) << 5);
+			SCL_H_SCALE_RATIO, dc_fixpt_u2d19(data->ratios.horz) << 5);
 
 	REG_SET(SCL_VERT_FILTER_SCALE_RATIO, 0,
-			SCL_V_SCALE_RATIO, dal_fixed31_32_u2d19(data->ratios.vert) << 5);
+			SCL_V_SCALE_RATIO, dc_fixpt_u2d19(data->ratios.vert) << 5);
 
 	REG_SET(SCL_HORZ_FILTER_SCALE_RATIO_C, 0,
-			SCL_H_SCALE_RATIO_C, dal_fixed31_32_u2d19(data->ratios.horz_c) << 5);
+			SCL_H_SCALE_RATIO_C, dc_fixpt_u2d19(data->ratios.horz_c) << 5);
 
 	REG_SET(SCL_VERT_FILTER_SCALE_RATIO_C, 0,
-			SCL_V_SCALE_RATIO_C, dal_fixed31_32_u2d19(data->ratios.vert_c) << 5);
+			SCL_V_SCALE_RATIO_C, dc_fixpt_u2d19(data->ratios.vert_c) << 5);
 
 	/*
 	 * 0.24 format for fraction, first five bits zeroed
 	 */
-	init_frac = dal_fixed31_32_u0d19(data->inits.h) << 5;
-	init_int = dal_fixed31_32_floor(data->inits.h);
+	init_frac = dc_fixpt_u0d19(data->inits.h) << 5;
+	init_int = dc_fixpt_floor(data->inits.h);
 	REG_SET_2(SCL_HORZ_FILTER_INIT, 0,
 		SCL_H_INIT_FRAC, init_frac,
 		SCL_H_INIT_INT, init_int);
 
-	init_frac = dal_fixed31_32_u0d19(data->inits.h_c) << 5;
-	init_int = dal_fixed31_32_floor(data->inits.h_c);
+	init_frac = dc_fixpt_u0d19(data->inits.h_c) << 5;
+	init_int = dc_fixpt_floor(data->inits.h_c);
 	REG_SET_2(SCL_HORZ_FILTER_INIT_C, 0,
 		SCL_H_INIT_FRAC_C, init_frac,
 		SCL_H_INIT_INT_C, init_int);
 
-	init_frac = dal_fixed31_32_u0d19(data->inits.v) << 5;
-	init_int = dal_fixed31_32_floor(data->inits.v);
+	init_frac = dc_fixpt_u0d19(data->inits.v) << 5;
+	init_int = dc_fixpt_floor(data->inits.v);
 	REG_SET_2(SCL_VERT_FILTER_INIT, 0,
 		SCL_V_INIT_FRAC, init_frac,
 		SCL_V_INIT_INT, init_int);
 
-	init_frac = dal_fixed31_32_u0d19(data->inits.v_bot) << 5;
-	init_int = dal_fixed31_32_floor(data->inits.v_bot);
+	init_frac = dc_fixpt_u0d19(data->inits.v_bot) << 5;
+	init_int = dc_fixpt_floor(data->inits.v_bot);
 	REG_SET_2(SCL_VERT_FILTER_INIT_BOT, 0,
 		SCL_V_INIT_FRAC_BOT, init_frac,
 		SCL_V_INIT_INT_BOT, init_int);
 
-	init_frac = dal_fixed31_32_u0d19(data->inits.v_c) << 5;
-	init_int = dal_fixed31_32_floor(data->inits.v_c);
+	init_frac = dc_fixpt_u0d19(data->inits.v_c) << 5;
+	init_int = dc_fixpt_floor(data->inits.v_c);
 	REG_SET_2(SCL_VERT_FILTER_INIT_C, 0,
 		SCL_V_INIT_FRAC_C, init_frac,
 		SCL_V_INIT_INT_C, init_int);
 
-	init_frac = dal_fixed31_32_u0d19(data->inits.v_c_bot) << 5;
-	init_int = dal_fixed31_32_floor(data->inits.v_c_bot);
+	init_frac = dc_fixpt_u0d19(data->inits.v_c_bot) << 5;
+	init_int = dc_fixpt_floor(data->inits.v_c_bot);
 	REG_SET_2(SCL_VERT_FILTER_INIT_BOT_C, 0,
 		SCL_V_INIT_FRAC_BOT_C, init_frac,
 		SCL_V_INIT_INT_BOT_C, init_int);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index 738f67ffd1b4..943143efbb82 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -476,8 +476,235 @@ void hubbub1_toggle_watermark_change_req(struct hubbub *hubbub)
 			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, watermark_change_req);
 }
 
+void hubbub1_soft_reset(struct hubbub *hubbub, bool reset)
+{
+	uint32_t reset_en = reset ? 1 : 0;
+
+	REG_UPDATE(DCHUBBUB_SOFT_RESET,
+			DCHUBBUB_GLOBAL_SOFT_RESET, reset_en);
+}
+
+static bool hubbub1_dcc_support_swizzle(
+		enum swizzle_mode_values swizzle,
+		unsigned int bytes_per_element,
+		enum segment_order *segment_order_horz,
+		enum segment_order *segment_order_vert)
+{
+	bool standard_swizzle = false;
+	bool display_swizzle = false;
+
+	switch (swizzle) {
+	case DC_SW_4KB_S:
+	case DC_SW_64KB_S:
+	case DC_SW_VAR_S:
+	case DC_SW_4KB_S_X:
+	case DC_SW_64KB_S_X:
+	case DC_SW_VAR_S_X:
+		standard_swizzle = true;
+		break;
+	case DC_SW_4KB_D:
+	case DC_SW_64KB_D:
+	case DC_SW_VAR_D:
+	case DC_SW_4KB_D_X:
+	case DC_SW_64KB_D_X:
+	case DC_SW_VAR_D_X:
+		display_swizzle = true;
+		break;
+	default:
+		break;
+	}
+
+	if (bytes_per_element == 1 && standard_swizzle) {
+		*segment_order_horz = segment_order__contiguous;
+		*segment_order_vert = segment_order__na;
+		return true;
+	}
+	if (bytes_per_element == 2 && standard_swizzle) {
+		*segment_order_horz = segment_order__non_contiguous;
+		*segment_order_vert = segment_order__contiguous;
+		return true;
+	}
+	if (bytes_per_element == 4 && standard_swizzle) {
+		*segment_order_horz = segment_order__non_contiguous;
+		*segment_order_vert = segment_order__contiguous;
+		return true;
+	}
+	if (bytes_per_element == 8 && standard_swizzle) {
+		*segment_order_horz = segment_order__na;
+		*segment_order_vert = segment_order__contiguous;
+		return true;
+	}
+	if (bytes_per_element == 8 && display_swizzle) {
+		*segment_order_horz = segment_order__contiguous;
+		*segment_order_vert = segment_order__non_contiguous;
+		return true;
+	}
+
+	return false;
+}
+
+static bool hubbub1_dcc_support_pixel_format(
+		enum surface_pixel_format format,
+		unsigned int *bytes_per_element)
+{
+	/* DML: get_bytes_per_element */
+	switch (format) {
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555:
+	case SURFACE_PIXEL_FORMAT_GRPH_RGB565:
+		*bytes_per_element = 2;
+		return true;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB8888:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR8888:
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB2101010:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010:
+		*bytes_per_element = 4;
+		return true;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
+		*bytes_per_element = 8;
+		return true;
+	default:
+		return false;
+	}
+}
+
+static void hubbub1_get_blk256_size(unsigned int *blk256_width, unsigned int *blk256_height,
+		unsigned int bytes_per_element)
+{
+	/* copied from DML.  might want to refactor DML to leverage from DML */
+	/* DML : get_blk256_size */
+	if (bytes_per_element == 1) {
+		*blk256_width = 16;
+		*blk256_height = 16;
+	} else if (bytes_per_element == 2) {
+		*blk256_width = 16;
+		*blk256_height = 8;
+	} else if (bytes_per_element == 4) {
+		*blk256_width = 8;
+		*blk256_height = 8;
+	} else if (bytes_per_element == 8) {
+		*blk256_width = 8;
+		*blk256_height = 4;
+	}
+}
+
+static void hubbub1_det_request_size(
+		unsigned int height,
+		unsigned int width,
+		unsigned int bpe,
+		bool *req128_horz_wc,
+		bool *req128_vert_wc)
+{
+	unsigned int detile_buf_size = 164 * 1024;  /* 164KB for DCN1.0 */
+
+	unsigned int blk256_height = 0;
+	unsigned int blk256_width = 0;
+	unsigned int swath_bytes_horz_wc, swath_bytes_vert_wc;
+
+	hubbub1_get_blk256_size(&blk256_width, &blk256_height, bpe);
+
+	swath_bytes_horz_wc = height * blk256_height * bpe;
+	swath_bytes_vert_wc = width * blk256_width * bpe;
+
+	*req128_horz_wc = (2 * swath_bytes_horz_wc <= detile_buf_size) ?
+			false : /* full 256B request */
+			true; /* half 128b request */
+
+	*req128_vert_wc = (2 * swath_bytes_vert_wc <= detile_buf_size) ?
+			false : /* full 256B request */
+			true; /* half 128b request */
+}
+
+static bool hubbub1_get_dcc_compression_cap(struct hubbub *hubbub,
+		const struct dc_dcc_surface_param *input,
+		struct dc_surface_dcc_cap *output)
+{
+	struct dc *dc = hubbub->ctx->dc;
+	/* implement section 1.6.2.1 of DCN1_Programming_Guide.docx */
+	enum dcc_control dcc_control;
+	unsigned int bpe;
+	enum segment_order segment_order_horz, segment_order_vert;
+	bool req128_horz_wc, req128_vert_wc;
+
+	memset(output, 0, sizeof(*output));
+
+	if (dc->debug.disable_dcc == DCC_DISABLE)
+		return false;
+
+	if (!hubbub->funcs->dcc_support_pixel_format(input->format, &bpe))
+		return false;
+
+	if (!hubbub->funcs->dcc_support_swizzle(input->swizzle_mode, bpe,
+			&segment_order_horz, &segment_order_vert))
+		return false;
+
+	hubbub1_det_request_size(input->surface_size.height,  input->surface_size.width,
+			bpe, &req128_horz_wc, &req128_vert_wc);
+
+	if (!req128_horz_wc && !req128_vert_wc) {
+		dcc_control = dcc_control__256_256_xxx;
+	} else if (input->scan == SCAN_DIRECTION_HORIZONTAL) {
+		if (!req128_horz_wc)
+			dcc_control = dcc_control__256_256_xxx;
+		else if (segment_order_horz == segment_order__contiguous)
+			dcc_control = dcc_control__128_128_xxx;
+		else
+			dcc_control = dcc_control__256_64_64;
+	} else if (input->scan == SCAN_DIRECTION_VERTICAL) {
+		if (!req128_vert_wc)
+			dcc_control = dcc_control__256_256_xxx;
+		else if (segment_order_vert == segment_order__contiguous)
+			dcc_control = dcc_control__128_128_xxx;
+		else
+			dcc_control = dcc_control__256_64_64;
+	} else {
+		if ((req128_horz_wc &&
+			segment_order_horz == segment_order__non_contiguous) ||
+			(req128_vert_wc &&
+			segment_order_vert == segment_order__non_contiguous))
+			/* access_dir not known, must use most constraining */
+			dcc_control = dcc_control__256_64_64;
+		else
+			/* reg128 is true for either horz and vert
+			 * but segment_order is contiguous
+			 */
+			dcc_control = dcc_control__128_128_xxx;
+	}
+
+	if (dc->debug.disable_dcc == DCC_HALF_REQ_DISALBE &&
+		dcc_control != dcc_control__256_256_xxx)
+		return false;
+
+	switch (dcc_control) {
+	case dcc_control__256_256_xxx:
+		output->grph.rgb.max_uncompressed_blk_size = 256;
+		output->grph.rgb.max_compressed_blk_size = 256;
+		output->grph.rgb.independent_64b_blks = false;
+		break;
+	case dcc_control__128_128_xxx:
+		output->grph.rgb.max_uncompressed_blk_size = 128;
+		output->grph.rgb.max_compressed_blk_size = 128;
+		output->grph.rgb.independent_64b_blks = false;
+		break;
+	case dcc_control__256_64_64:
+		output->grph.rgb.max_uncompressed_blk_size = 256;
+		output->grph.rgb.max_compressed_blk_size = 64;
+		output->grph.rgb.independent_64b_blks = true;
+		break;
+	}
+
+	output->capable = true;
+	output->const_color_support = false;
+
+	return true;
+}
+
 static const struct hubbub_funcs hubbub1_funcs = {
-	.update_dchub = hubbub1_update_dchub
+	.update_dchub = hubbub1_update_dchub,
+	.dcc_support_swizzle = hubbub1_dcc_support_swizzle,
+	.dcc_support_pixel_format = hubbub1_dcc_support_pixel_format,
+	.get_dcc_compression_cap = hubbub1_get_dcc_compression_cap,
 };
 
 void hubbub1_construct(struct hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
index a16e908821a0..6315a0e6b0d6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -27,6 +27,7 @@
 #define __DC_HUBBUB_DCN10_H__
 
 #include "core_types.h"
+#include "dchubbub.h"
 
 #define HUBHUB_REG_LIST_DCN()\
 	SR(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A),\
@@ -47,7 +48,8 @@
 	SR(DCHUBBUB_ARB_DF_REQ_OUTSTAND),\
 	SR(DCHUBBUB_GLOBAL_TIMER_CNTL), \
 	SR(DCHUBBUB_TEST_DEBUG_INDEX), \
-	SR(DCHUBBUB_TEST_DEBUG_DATA)
+	SR(DCHUBBUB_TEST_DEBUG_DATA),\
+	SR(DCHUBBUB_SOFT_RESET)
 
 #define HUBBUB_SR_WATERMARK_REG_LIST()\
 	SR(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A),\
@@ -104,6 +106,7 @@ struct dcn_hubbub_registers {
 	uint32_t DCHUBBUB_SDPIF_AGP_BOT;
 	uint32_t DCHUBBUB_SDPIF_AGP_TOP;
 	uint32_t DCHUBBUB_CRC_CTRL;
+	uint32_t DCHUBBUB_SOFT_RESET;
 };
 
 /* set field name */
@@ -113,6 +116,7 @@ struct dcn_hubbub_registers {
 
 #define HUBBUB_MASK_SH_LIST_DCN(mask_sh)\
 		HUBBUB_SF(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, mask_sh), \
+		HUBBUB_SF(DCHUBBUB_SOFT_RESET, DCHUBBUB_GLOBAL_SOFT_RESET, mask_sh), \
 		HUBBUB_SF(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL, DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, mask_sh), \
 		HUBBUB_SF(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL, DCHUBBUB_ARB_WATERMARK_CHANGE_DONE_INTERRUPT_DISABLE, mask_sh), \
 		HUBBUB_SF(DCHUBBUB_ARB_DRAM_STATE_CNTL, DCHUBBUB_ARB_ALLOW_SELF_REFRESH_FORCE_VALUE, mask_sh), \
@@ -142,6 +146,7 @@ struct dcn_hubbub_registers {
 		type DCHUBBUB_ARB_SAT_LEVEL;\
 		type DCHUBBUB_ARB_MIN_REQ_OUTSTAND;\
 		type DCHUBBUB_GLOBAL_TIMER_REFDIV;\
+		type DCHUBBUB_GLOBAL_SOFT_RESET; \
 		type SDPIF_FB_TOP;\
 		type SDPIF_FB_BASE;\
 		type SDPIF_FB_OFFSET;\
@@ -173,12 +178,6 @@ struct dcn_hubbub_wm {
 	struct dcn_hubbub_wm_set sets[4];
 };
 
-struct hubbub_funcs {
-	void (*update_dchub)(
-			struct hubbub *hubbub,
-			struct dchub_init_data *dh_data);
-};
-
 struct hubbub {
 	const struct hubbub_funcs *funcs;
 	struct dc_context *ctx;
@@ -206,6 +205,7 @@ void hubbub1_toggle_watermark_change_req(
 void hubbub1_wm_read_state(struct hubbub *hubbub,
 		struct dcn_hubbub_wm *wm);
 
+void hubbub1_soft_reset(struct hubbub *hubbub, bool reset);
 void hubbub1_construct(struct hubbub *hubbub,
 	struct dc_context *ctx,
 	const struct dcn_hubbub_registers *hubbub_regs,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 39b72f696ae9..d2ab78b35a7a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -78,6 +78,27 @@ static void hubp1_disconnect(struct hubp *hubp)
 			CURSOR_ENABLE, 0);
 }
 
+static void hubp1_disable_control(struct hubp *hubp, bool disable_hubp)
+{
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+	uint32_t disable = disable_hubp ? 1 : 0;
+
+	REG_UPDATE(DCHUBP_CNTL,
+			HUBP_DISABLE, disable);
+}
+
+static unsigned int hubp1_get_underflow_status(struct hubp *hubp)
+{
+	uint32_t hubp_underflow = 0;
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+
+	REG_GET(DCHUBP_CNTL,
+		HUBP_UNDERFLOW_STATUS,
+		&hubp_underflow);
+
+	return hubp_underflow;
+}
+
 static void hubp1_set_hubp_blank_en(struct hubp *hubp, bool blank)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
@@ -146,6 +167,9 @@ void hubp1_program_size_and_rotation(
 	 * 444 or 420 luma
 	 */
 	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) {
+		ASSERT(plane_size->video.chroma_pitch != 0);
+		/* Chroma pitch zero can cause system hang! */
+
 		pitch = plane_size->video.luma_pitch - 1;
 		meta_pitch = dcc->video.meta_pitch_l - 1;
 		pitch_c = plane_size->video.chroma_pitch - 1;
@@ -535,11 +559,13 @@ void hubp1_program_deadline(
 	REG_SET(VBLANK_PARAMETERS_3, 0,
 		REFCYC_PER_META_CHUNK_VBLANK_L, dlg_attr->refcyc_per_meta_chunk_vblank_l);
 
-	REG_SET(NOM_PARAMETERS_0, 0,
-		DST_Y_PER_PTE_ROW_NOM_L, dlg_attr->dst_y_per_pte_row_nom_l);
+	if (REG(NOM_PARAMETERS_0))
+		REG_SET(NOM_PARAMETERS_0, 0,
+			DST_Y_PER_PTE_ROW_NOM_L, dlg_attr->dst_y_per_pte_row_nom_l);
 
-	REG_SET(NOM_PARAMETERS_1, 0,
-		REFCYC_PER_PTE_GROUP_NOM_L, dlg_attr->refcyc_per_pte_group_nom_l);
+	if (REG(NOM_PARAMETERS_1))
+		REG_SET(NOM_PARAMETERS_1, 0,
+			REFCYC_PER_PTE_GROUP_NOM_L, dlg_attr->refcyc_per_pte_group_nom_l);
 
 	REG_SET(NOM_PARAMETERS_4, 0,
 		DST_Y_PER_META_ROW_NOM_L, dlg_attr->dst_y_per_meta_row_nom_l);
@@ -568,11 +594,13 @@ void hubp1_program_deadline(
 	REG_SET(VBLANK_PARAMETERS_4, 0,
 		REFCYC_PER_META_CHUNK_VBLANK_C, dlg_attr->refcyc_per_meta_chunk_vblank_c);
 
-	REG_SET(NOM_PARAMETERS_2, 0,
-		DST_Y_PER_PTE_ROW_NOM_C, dlg_attr->dst_y_per_pte_row_nom_c);
+	if (REG(NOM_PARAMETERS_2))
+		REG_SET(NOM_PARAMETERS_2, 0,
+			DST_Y_PER_PTE_ROW_NOM_C, dlg_attr->dst_y_per_pte_row_nom_c);
 
-	REG_SET(NOM_PARAMETERS_3, 0,
-		REFCYC_PER_PTE_GROUP_NOM_C, dlg_attr->refcyc_per_pte_group_nom_c);
+	if (REG(NOM_PARAMETERS_3))
+		REG_SET(NOM_PARAMETERS_3, 0,
+			REFCYC_PER_PTE_GROUP_NOM_C, dlg_attr->refcyc_per_pte_group_nom_c);
 
 	REG_SET(NOM_PARAMETERS_6, 0,
 		DST_Y_PER_META_ROW_NOM_C, dlg_attr->dst_y_per_meta_row_nom_c);
@@ -609,6 +637,13 @@ void hubp1_program_deadline(
 	REG_SET(DCN_SURF1_TTU_CNTL1, 0,
 		REFCYC_PER_REQ_DELIVERY_PRE,
 		ttu_attr->refcyc_per_req_delivery_pre_c);
+
+	REG_SET_3(DCN_CUR0_TTU_CNTL0, 0,
+		REFCYC_PER_REQ_DELIVERY, ttu_attr->refcyc_per_req_delivery_cur0,
+		QoS_LEVEL_FIXED, ttu_attr->qos_level_fixed_cur0,
+		QoS_RAMP_DISABLE, ttu_attr->qos_ramp_disable_cur0);
+	REG_SET(DCN_CUR0_TTU_CNTL1, 0,
+		REFCYC_PER_REQ_DELIVERY_PRE, ttu_attr->refcyc_per_req_delivery_pre_cur0);
 }
 
 static void hubp1_setup(
@@ -752,9 +787,159 @@ void min_set_viewport(
 		  PRI_VIEWPORT_Y_START_C, viewport_c->y);
 }
 
-void hubp1_read_state(struct dcn10_hubp *hubp1,
-		struct dcn_hubp_state *s)
+void hubp1_read_state(struct hubp *hubp)
 {
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+	struct dcn_hubp_state *s = &hubp1->state;
+	struct _vcs_dpi_display_dlg_regs_st *dlg_attr = &s->dlg_attr;
+	struct _vcs_dpi_display_ttu_regs_st *ttu_attr = &s->ttu_attr;
+	struct _vcs_dpi_display_rq_regs_st *rq_regs = &s->rq_regs;
+
+	/* Requester */
+	REG_GET(HUBPRET_CONTROL,
+			DET_BUF_PLANE1_BASE_ADDRESS, &rq_regs->plane1_base_address);
+	REG_GET_4(DCN_EXPANSION_MODE,
+			DRQ_EXPANSION_MODE, &rq_regs->drq_expansion_mode,
+			PRQ_EXPANSION_MODE, &rq_regs->prq_expansion_mode,
+			MRQ_EXPANSION_MODE, &rq_regs->mrq_expansion_mode,
+			CRQ_EXPANSION_MODE, &rq_regs->crq_expansion_mode);
+	REG_GET_8(DCHUBP_REQ_SIZE_CONFIG,
+		CHUNK_SIZE, &rq_regs->rq_regs_l.chunk_size,
+		MIN_CHUNK_SIZE, &rq_regs->rq_regs_l.min_chunk_size,
+		META_CHUNK_SIZE, &rq_regs->rq_regs_l.meta_chunk_size,
+		MIN_META_CHUNK_SIZE, &rq_regs->rq_regs_l.min_meta_chunk_size,
+		DPTE_GROUP_SIZE, &rq_regs->rq_regs_l.dpte_group_size,
+		MPTE_GROUP_SIZE, &rq_regs->rq_regs_l.mpte_group_size,
+		SWATH_HEIGHT, &rq_regs->rq_regs_l.swath_height,
+		PTE_ROW_HEIGHT_LINEAR, &rq_regs->rq_regs_l.pte_row_height_linear);
+	REG_GET_8(DCHUBP_REQ_SIZE_CONFIG_C,
+		CHUNK_SIZE_C, &rq_regs->rq_regs_c.chunk_size,
+		MIN_CHUNK_SIZE_C, &rq_regs->rq_regs_c.min_chunk_size,
+		META_CHUNK_SIZE_C, &rq_regs->rq_regs_c.meta_chunk_size,
+		MIN_META_CHUNK_SIZE_C, &rq_regs->rq_regs_c.min_meta_chunk_size,
+		DPTE_GROUP_SIZE_C, &rq_regs->rq_regs_c.dpte_group_size,
+		MPTE_GROUP_SIZE_C, &rq_regs->rq_regs_c.mpte_group_size,
+		SWATH_HEIGHT_C, &rq_regs->rq_regs_c.swath_height,
+		PTE_ROW_HEIGHT_LINEAR_C, &rq_regs->rq_regs_c.pte_row_height_linear);
+
+	/* DLG - Per hubp */
+	REG_GET_2(BLANK_OFFSET_0,
+		REFCYC_H_BLANK_END, &dlg_attr->refcyc_h_blank_end,
+		DLG_V_BLANK_END, &dlg_attr->dlg_vblank_end);
+
+	REG_GET(BLANK_OFFSET_1,
+		MIN_DST_Y_NEXT_START, &dlg_attr->min_dst_y_next_start);
+
+	REG_GET(DST_DIMENSIONS,
+		REFCYC_PER_HTOTAL, &dlg_attr->refcyc_per_htotal);
+
+	REG_GET_2(DST_AFTER_SCALER,
+		REFCYC_X_AFTER_SCALER, &dlg_attr->refcyc_x_after_scaler,
+		DST_Y_AFTER_SCALER, &dlg_attr->dst_y_after_scaler);
+
+	if (REG(PREFETCH_SETTINS))
+		REG_GET_2(PREFETCH_SETTINS,
+			DST_Y_PREFETCH, &dlg_attr->dst_y_prefetch,
+			VRATIO_PREFETCH, &dlg_attr->vratio_prefetch);
+	else
+		REG_GET_2(PREFETCH_SETTINGS,
+			DST_Y_PREFETCH, &dlg_attr->dst_y_prefetch,
+			VRATIO_PREFETCH, &dlg_attr->vratio_prefetch);
+
+	REG_GET_2(VBLANK_PARAMETERS_0,
+		DST_Y_PER_VM_VBLANK, &dlg_attr->dst_y_per_vm_vblank,
+		DST_Y_PER_ROW_VBLANK, &dlg_attr->dst_y_per_row_vblank);
+
+	REG_GET(REF_FREQ_TO_PIX_FREQ,
+		REF_FREQ_TO_PIX_FREQ, &dlg_attr->ref_freq_to_pix_freq);
+
+	/* DLG - Per luma/chroma */
+	REG_GET(VBLANK_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_VBLANK_L, &dlg_attr->refcyc_per_pte_group_vblank_l);
+
+	REG_GET(VBLANK_PARAMETERS_3,
+		REFCYC_PER_META_CHUNK_VBLANK_L, &dlg_attr->refcyc_per_meta_chunk_vblank_l);
+
+	if (REG(NOM_PARAMETERS_0))
+		REG_GET(NOM_PARAMETERS_0,
+			DST_Y_PER_PTE_ROW_NOM_L, &dlg_attr->dst_y_per_pte_row_nom_l);
+
+	if (REG(NOM_PARAMETERS_1))
+		REG_GET(NOM_PARAMETERS_1,
+			REFCYC_PER_PTE_GROUP_NOM_L, &dlg_attr->refcyc_per_pte_group_nom_l);
+
+	REG_GET(NOM_PARAMETERS_4,
+		DST_Y_PER_META_ROW_NOM_L, &dlg_attr->dst_y_per_meta_row_nom_l);
+
+	REG_GET(NOM_PARAMETERS_5,
+		REFCYC_PER_META_CHUNK_NOM_L, &dlg_attr->refcyc_per_meta_chunk_nom_l);
+
+	REG_GET_2(PER_LINE_DELIVERY_PRE,
+		REFCYC_PER_LINE_DELIVERY_PRE_L, &dlg_attr->refcyc_per_line_delivery_pre_l,
+		REFCYC_PER_LINE_DELIVERY_PRE_C, &dlg_attr->refcyc_per_line_delivery_pre_c);
+
+	REG_GET_2(PER_LINE_DELIVERY,
+		REFCYC_PER_LINE_DELIVERY_L, &dlg_attr->refcyc_per_line_delivery_l,
+		REFCYC_PER_LINE_DELIVERY_C, &dlg_attr->refcyc_per_line_delivery_c);
+
+	if (REG(PREFETCH_SETTINS_C))
+		REG_GET(PREFETCH_SETTINS_C,
+			VRATIO_PREFETCH_C, &dlg_attr->vratio_prefetch_c);
+	else
+		REG_GET(PREFETCH_SETTINGS_C,
+			VRATIO_PREFETCH_C, &dlg_attr->vratio_prefetch_c);
+
+	REG_GET(VBLANK_PARAMETERS_2,
+		REFCYC_PER_PTE_GROUP_VBLANK_C, &dlg_attr->refcyc_per_pte_group_vblank_c);
+
+	REG_GET(VBLANK_PARAMETERS_4,
+		REFCYC_PER_META_CHUNK_VBLANK_C, &dlg_attr->refcyc_per_meta_chunk_vblank_c);
+
+	if (REG(NOM_PARAMETERS_2))
+		REG_GET(NOM_PARAMETERS_2,
+			DST_Y_PER_PTE_ROW_NOM_C, &dlg_attr->dst_y_per_pte_row_nom_c);
+
+	if (REG(NOM_PARAMETERS_3))
+		REG_GET(NOM_PARAMETERS_3,
+			REFCYC_PER_PTE_GROUP_NOM_C, &dlg_attr->refcyc_per_pte_group_nom_c);
+
+	REG_GET(NOM_PARAMETERS_6,
+		DST_Y_PER_META_ROW_NOM_C, &dlg_attr->dst_y_per_meta_row_nom_c);
+
+	REG_GET(NOM_PARAMETERS_7,
+		REFCYC_PER_META_CHUNK_NOM_C, &dlg_attr->refcyc_per_meta_chunk_nom_c);
+
+	/* TTU - per hubp */
+	REG_GET_2(DCN_TTU_QOS_WM,
+		QoS_LEVEL_LOW_WM, &ttu_attr->qos_level_low_wm,
+		QoS_LEVEL_HIGH_WM, &ttu_attr->qos_level_high_wm);
+
+	REG_GET_2(DCN_GLOBAL_TTU_CNTL,
+		MIN_TTU_VBLANK, &ttu_attr->min_ttu_vblank,
+		QoS_LEVEL_FLIP, &ttu_attr->qos_level_flip);
+
+	/* TTU - per luma/chroma */
+	/* Assumed surf0 is luma and 1 is chroma */
+
+	REG_GET_3(DCN_SURF0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr->refcyc_per_req_delivery_l,
+		QoS_LEVEL_FIXED, &ttu_attr->qos_level_fixed_l,
+		QoS_RAMP_DISABLE, &ttu_attr->qos_ramp_disable_l);
+
+	REG_GET(DCN_SURF0_TTU_CNTL1,
+		REFCYC_PER_REQ_DELIVERY_PRE,
+		&ttu_attr->refcyc_per_req_delivery_pre_l);
+
+	REG_GET_3(DCN_SURF1_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr->refcyc_per_req_delivery_c,
+		QoS_LEVEL_FIXED, &ttu_attr->qos_level_fixed_c,
+		QoS_RAMP_DISABLE, &ttu_attr->qos_ramp_disable_c);
+
+	REG_GET(DCN_SURF1_TTU_CNTL1,
+		REFCYC_PER_REQ_DELIVERY_PRE,
+		&ttu_attr->refcyc_per_req_delivery_pre_c);
+
+	/* Rest of hubp */
 	REG_GET(DCSURF_SURFACE_CONFIG,
 			SURFACE_PIXEL_FORMAT, &s->pixel_format);
 
@@ -890,14 +1075,14 @@ void hubp1_cursor_set_position(
 	ASSERT(param->h_scale_ratio.value);
 
 	if (param->h_scale_ratio.value)
-		dst_x_offset = dal_fixed31_32_floor(dal_fixed31_32_div(
-				dal_fixed31_32_from_int(dst_x_offset),
+		dst_x_offset = dc_fixpt_floor(dc_fixpt_div(
+				dc_fixpt_from_int(dst_x_offset),
 				param->h_scale_ratio));
 
 	if (src_x_offset >= (int)param->viewport_width)
 		cur_en = 0;  /* not visible beyond right edge*/
 
-	if (src_x_offset + (int)hubp->curs_attr.width < 0)
+	if (src_x_offset + (int)hubp->curs_attr.width <= 0)
 		cur_en = 0;  /* not visible beyond left edge*/
 
 	if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
@@ -952,6 +1137,10 @@ static struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_disconnect = hubp1_disconnect,
 	.hubp_clk_cntl = hubp1_clk_cntl,
 	.hubp_vtg_sel = hubp1_vtg_sel,
+	.hubp_read_state = hubp1_read_state,
+	.hubp_disable_control =  hubp1_disable_control,
+	.hubp_get_underflow_status = hubp1_get_underflow_status,
+
 };
 
 /*****************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index 4a3703e12ea1..af384034398f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -30,6 +30,7 @@
 #define TO_DCN10_HUBP(hubp)\
 	container_of(hubp, struct dcn10_hubp, base)
 
+/* Register address initialization macro for all ASICs (including those with reduced functionality) */
 #define HUBP_REG_LIST_DCN(id)\
 	SRI(DCHUBP_CNTL, HUBP, id),\
 	SRI(HUBPREQ_DEBUG_DB, HUBP, id),\
@@ -78,16 +79,12 @@
 	SRI(REF_FREQ_TO_PIX_FREQ, HUBPREQ, id),\
 	SRI(VBLANK_PARAMETERS_1, HUBPREQ, id),\
 	SRI(VBLANK_PARAMETERS_3, HUBPREQ, id),\
-	SRI(NOM_PARAMETERS_0, HUBPREQ, id),\
-	SRI(NOM_PARAMETERS_1, HUBPREQ, id),\
 	SRI(NOM_PARAMETERS_4, HUBPREQ, id),\
 	SRI(NOM_PARAMETERS_5, HUBPREQ, id),\
 	SRI(PER_LINE_DELIVERY_PRE, HUBPREQ, id),\
 	SRI(PER_LINE_DELIVERY, HUBPREQ, id),\
 	SRI(VBLANK_PARAMETERS_2, HUBPREQ, id),\
 	SRI(VBLANK_PARAMETERS_4, HUBPREQ, id),\
-	SRI(NOM_PARAMETERS_2, HUBPREQ, id),\
-	SRI(NOM_PARAMETERS_3, HUBPREQ, id),\
 	SRI(NOM_PARAMETERS_6, HUBPREQ, id),\
 	SRI(NOM_PARAMETERS_7, HUBPREQ, id),\
 	SRI(DCN_TTU_QOS_WM, HUBPREQ, id),\
@@ -96,11 +93,21 @@
 	SRI(DCN_SURF0_TTU_CNTL1, HUBPREQ, id),\
 	SRI(DCN_SURF1_TTU_CNTL0, HUBPREQ, id),\
 	SRI(DCN_SURF1_TTU_CNTL1, HUBPREQ, id),\
-	SRI(DCN_VM_MX_L1_TLB_CNTL, HUBPREQ, id),\
+	SRI(DCN_CUR0_TTU_CNTL0, HUBPREQ, id),\
+	SRI(DCN_CUR0_TTU_CNTL1, HUBPREQ, id),\
 	SRI(HUBP_CLK_CNTL, HUBP, id)
 
+/* Register address initialization macro for ASICs with VM */
+#define HUBP_REG_LIST_DCN_VM(id)\
+	SRI(NOM_PARAMETERS_0, HUBPREQ, id),\
+	SRI(NOM_PARAMETERS_1, HUBPREQ, id),\
+	SRI(NOM_PARAMETERS_2, HUBPREQ, id),\
+	SRI(NOM_PARAMETERS_3, HUBPREQ, id),\
+	SRI(DCN_VM_MX_L1_TLB_CNTL, HUBPREQ, id)
+
 #define HUBP_REG_LIST_DCN10(id)\
 	HUBP_REG_LIST_DCN(id),\
+	HUBP_REG_LIST_DCN_VM(id),\
 	SRI(PREFETCH_SETTINS, HUBPREQ, id),\
 	SRI(PREFETCH_SETTINS_C, HUBPREQ, id),\
 	SRI(DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB, HUBPREQ, id),\
@@ -198,6 +205,8 @@
 	uint32_t DCN_SURF0_TTU_CNTL1; \
 	uint32_t DCN_SURF1_TTU_CNTL0; \
 	uint32_t DCN_SURF1_TTU_CNTL1; \
+	uint32_t DCN_CUR0_TTU_CNTL0; \
+	uint32_t DCN_CUR0_TTU_CNTL1; \
 	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_MSB; \
 	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LSB; \
 	uint32_t DCN_VM_CONTEXT0_PAGE_TABLE_START_ADDR_MSB; \
@@ -237,12 +246,14 @@
 #define HUBP_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
+/* Mask/shift struct generation macro for all ASICs (including those with reduced functionality) */
 #define HUBP_MASK_SH_LIST_DCN(mask_sh)\
 	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_BLANK_EN, mask_sh),\
 	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_TTU_DISABLE, mask_sh),\
 	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_UNDERFLOW_STATUS, mask_sh),\
 	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_NO_OUTSTANDING_REQ, mask_sh),\
 	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_VTG_SEL, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_DISABLE, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_PIPES, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_BANKS, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, PIPE_INTERLEAVE, mask_sh),\
@@ -335,8 +346,6 @@
 	HUBP_SF(HUBPREQ0_REF_FREQ_TO_PIX_FREQ, REF_FREQ_TO_PIX_FREQ, mask_sh),\
 	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_1, REFCYC_PER_PTE_GROUP_VBLANK_L, mask_sh),\
 	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_3, REFCYC_PER_META_CHUNK_VBLANK_L, mask_sh),\
-	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_0, DST_Y_PER_PTE_ROW_NOM_L, mask_sh),\
-	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_1, REFCYC_PER_PTE_GROUP_NOM_L, mask_sh),\
 	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_4, DST_Y_PER_META_ROW_NOM_L, mask_sh),\
 	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_5, REFCYC_PER_META_CHUNK_NOM_L, mask_sh),\
 	HUBP_SF(HUBPREQ0_PER_LINE_DELIVERY_PRE, REFCYC_PER_LINE_DELIVERY_PRE_L, mask_sh),\
@@ -345,8 +354,6 @@
 	HUBP_SF(HUBPREQ0_PER_LINE_DELIVERY, REFCYC_PER_LINE_DELIVERY_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_2, REFCYC_PER_PTE_GROUP_VBLANK_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_4, REFCYC_PER_META_CHUNK_VBLANK_C, mask_sh),\
-	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_2, DST_Y_PER_PTE_ROW_NOM_C, mask_sh),\
-	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_3, REFCYC_PER_PTE_GROUP_NOM_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_6, DST_Y_PER_META_ROW_NOM_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_7, REFCYC_PER_META_CHUNK_NOM_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCN_TTU_QOS_WM, QoS_LEVEL_LOW_WM, mask_sh),\
@@ -357,12 +364,24 @@
 	HUBP_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL0, QoS_LEVEL_FIXED, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL0, QoS_RAMP_DISABLE, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCN_SURF0_TTU_CNTL1, REFCYC_PER_REQ_DELIVERY_PRE, mask_sh),\
+	HUBP_SF(HUBP0_HUBP_CLK_CNTL, HUBP_CLOCK_ENABLE, mask_sh)
+
+/* Mask/shift struct generation macro for ASICs with VM */
+#define HUBP_MASK_SH_LIST_DCN_VM(mask_sh)\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_0, DST_Y_PER_PTE_ROW_NOM_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_1, REFCYC_PER_PTE_GROUP_NOM_L, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_2, DST_Y_PER_PTE_ROW_NOM_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_NOM_PARAMETERS_3, REFCYC_PER_PTE_GROUP_NOM_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCN_VM_MX_L1_TLB_CNTL, ENABLE_L1_TLB, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCN_VM_MX_L1_TLB_CNTL, SYSTEM_ACCESS_MODE, mask_sh),\
-	HUBP_SF(HUBP0_HUBP_CLK_CNTL, HUBP_CLOCK_ENABLE, mask_sh)
+	HUBP_SF(HUBPREQ0_DCN_CUR0_TTU_CNTL0, REFCYC_PER_REQ_DELIVERY, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_CUR0_TTU_CNTL0, QoS_LEVEL_FIXED, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_CUR0_TTU_CNTL0, QoS_RAMP_DISABLE, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCN_CUR0_TTU_CNTL1, REFCYC_PER_REQ_DELIVERY_PRE, mask_sh)
 
 #define HUBP_MASK_SH_LIST_DCN10(mask_sh)\
 	HUBP_MASK_SH_LIST_DCN(mask_sh),\
+	HUBP_MASK_SH_LIST_DCN_VM(mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, DST_Y_PREFETCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, VRATIO_PREFETCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS_C, VRATIO_PREFETCH_C, mask_sh),\
@@ -403,6 +422,7 @@
 
 #define DCN_HUBP_REG_FIELD_LIST(type) \
 	type HUBP_BLANK_EN;\
+	type HUBP_DISABLE;\
 	type HUBP_TTU_DISABLE;\
 	type HUBP_NO_OUTSTANDING_REQ;\
 	type HUBP_VTG_SEL;\
@@ -601,8 +621,29 @@ struct dcn_mi_mask {
 	DCN_HUBP_REG_FIELD_LIST(uint32_t);
 };
 
+struct dcn_hubp_state {
+	struct _vcs_dpi_display_dlg_regs_st dlg_attr;
+	struct _vcs_dpi_display_ttu_regs_st ttu_attr;
+	struct _vcs_dpi_display_rq_regs_st rq_regs;
+	uint32_t pixel_format;
+	uint32_t inuse_addr_hi;
+	uint32_t viewport_width;
+	uint32_t viewport_height;
+	uint32_t rotation_angle;
+	uint32_t h_mirror_en;
+	uint32_t sw_mode;
+	uint32_t dcc_en;
+	uint32_t blank_en;
+	uint32_t underflow_status;
+	uint32_t ttu_disable;
+	uint32_t min_ttu_vblank;
+	uint32_t qos_level_low_wm;
+	uint32_t qos_level_high_wm;
+};
+
 struct dcn10_hubp {
 	struct hubp base;
+	struct dcn_hubp_state state;
 	const struct dcn_mi_registers *hubp_regs;
 	const struct dcn_mi_shift *hubp_shift;
 	const struct dcn_mi_mask *hubp_mask;
@@ -680,26 +721,9 @@ void dcn10_hubp_construct(
 	const struct dcn_mi_shift *hubp_shift,
 	const struct dcn_mi_mask *hubp_mask);
 
-
-struct dcn_hubp_state {
-	uint32_t pixel_format;
-	uint32_t inuse_addr_hi;
-	uint32_t viewport_width;
-	uint32_t viewport_height;
-	uint32_t rotation_angle;
-	uint32_t h_mirror_en;
-	uint32_t sw_mode;
-	uint32_t dcc_en;
-	uint32_t blank_en;
-	uint32_t underflow_status;
-	uint32_t ttu_disable;
-	uint32_t min_ttu_vblank;
-	uint32_t qos_level_low_wm;
-	uint32_t qos_level_high_wm;
-};
-void hubp1_read_state(struct dcn10_hubp *hubp1,
-		struct dcn_hubp_state *s);
+void hubp1_read_state(struct hubp *hubp);
 
 enum cursor_pitch hubp1_get_cursor_pitch(unsigned int pitch);
 
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 8b0f6b8a5627..f8e0576af6e0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -45,8 +45,8 @@
 #include "dcn10_hubbub.h"
 #include "dcn10_cm_common.h"
 
-#define DC_LOGGER \
-	ctx->logger
+#define DC_LOGGER_INIT(logger)
+
 #define CTX \
 	hws->ctx
 #define REG(reg)\
@@ -56,16 +56,17 @@
 #define FN(reg_name, field_name) \
 	hws->shifts->field_name, hws->masks->field_name
 
+/*print is 17 wide, first two characters are spaces*/
 #define DTN_INFO_MICRO_SEC(ref_cycle) \
 	print_microsec(dc_ctx, ref_cycle)
 
 void print_microsec(struct dc_context *dc_ctx, uint32_t ref_cycle)
 {
-	static const uint32_t ref_clk_mhz = 48;
-	static const unsigned int frac = 10;
+	const uint32_t ref_clk_mhz = dc_ctx->dc->res_pool->ref_clock_inKhz / 1000;
+	static const unsigned int frac = 1000;
 	uint32_t us_x10 = (ref_cycle * frac) / ref_clk_mhz;
 
-	DTN_INFO("%d.%d \t ",
+	DTN_INFO("  %11d.%03d",
 			us_x10 / frac,
 			us_x10 % frac);
 }
@@ -92,14 +93,14 @@ void dcn10_log_hubbub_state(struct dc *dc)
 
 	hubbub1_wm_read_state(dc->res_pool->hubbub, &wm);
 
-	DTN_INFO("HUBBUB WM: \t data_urgent \t pte_meta_urgent \t "
-			"sr_enter \t sr_exit \t dram_clk_change \n");
+	DTN_INFO("HUBBUB WM:      data_urgent  pte_meta_urgent"
+			"         sr_enter          sr_exit  dram_clk_change\n");
 
 	for (i = 0; i < 4; i++) {
 		struct dcn_hubbub_wm_set *s;
 
 		s = &wm.sets[i];
-		DTN_INFO("WM_Set[%d]:\t ", s->wm_set);
+		DTN_INFO("WM_Set[%d]:", s->wm_set);
 		DTN_INFO_MICRO_SEC(s->data_urgent);
 		DTN_INFO_MICRO_SEC(s->pte_meta_urgent);
 		DTN_INFO_MICRO_SEC(s->sr_enter);
@@ -111,6 +112,121 @@ void dcn10_log_hubbub_state(struct dc *dc)
 	DTN_INFO("\n");
 }
 
+static void dcn10_log_hubp_states(struct dc *dc)
+{
+	struct dc_context *dc_ctx = dc->ctx;
+	struct resource_pool *pool = dc->res_pool;
+	int i;
+
+	DTN_INFO("HUBP:  format  addr_hi  width  height"
+			"  rot  mir  sw_mode  dcc_en  blank_en  ttu_dis  underflow"
+			"   min_ttu_vblank       qos_low_wm      qos_high_wm\n");
+	for (i = 0; i < pool->pipe_count; i++) {
+		struct hubp *hubp = pool->hubps[i];
+		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(hubp)->state);
+
+		hubp->funcs->hubp_read_state(hubp);
+
+		if (!s->blank_en) {
+			DTN_INFO("[%2d]:  %5xh  %6xh  %5d  %6d  %2xh  %2xh  %6xh"
+					"  %6d  %8d  %7d  %8xh",
+					hubp->inst,
+					s->pixel_format,
+					s->inuse_addr_hi,
+					s->viewport_width,
+					s->viewport_height,
+					s->rotation_angle,
+					s->h_mirror_en,
+					s->sw_mode,
+					s->dcc_en,
+					s->blank_en,
+					s->ttu_disable,
+					s->underflow_status);
+			DTN_INFO_MICRO_SEC(s->min_ttu_vblank);
+			DTN_INFO_MICRO_SEC(s->qos_level_low_wm);
+			DTN_INFO_MICRO_SEC(s->qos_level_high_wm);
+			DTN_INFO("\n");
+		}
+	}
+
+	DTN_INFO("\n=========RQ========\n");
+	DTN_INFO("HUBP:  drq_exp_m  prq_exp_m  mrq_exp_m  crq_exp_m  plane1_ba  L:chunk_s  min_chu_s  meta_ch_s"
+		"  min_m_c_s  dpte_gr_s  mpte_gr_s  swath_hei  pte_row_h  C:chunk_s  min_chu_s  meta_ch_s"
+		"  min_m_c_s  dpte_gr_s  mpte_gr_s  swath_hei  pte_row_h\n");
+	for (i = 0; i < pool->pipe_count; i++) {
+		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(pool->hubps[i])->state);
+		struct _vcs_dpi_display_rq_regs_st *rq_regs = &s->rq_regs;
+
+		if (!s->blank_en)
+			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
+				pool->hubps[i]->inst, rq_regs->drq_expansion_mode, rq_regs->prq_expansion_mode, rq_regs->mrq_expansion_mode,
+				rq_regs->crq_expansion_mode, rq_regs->plane1_base_address, rq_regs->rq_regs_l.chunk_size,
+				rq_regs->rq_regs_l.min_chunk_size, rq_regs->rq_regs_l.meta_chunk_size,
+				rq_regs->rq_regs_l.min_meta_chunk_size, rq_regs->rq_regs_l.dpte_group_size,
+				rq_regs->rq_regs_l.mpte_group_size, rq_regs->rq_regs_l.swath_height,
+				rq_regs->rq_regs_l.pte_row_height_linear, rq_regs->rq_regs_c.chunk_size, rq_regs->rq_regs_c.min_chunk_size,
+				rq_regs->rq_regs_c.meta_chunk_size, rq_regs->rq_regs_c.min_meta_chunk_size,
+				rq_regs->rq_regs_c.dpte_group_size, rq_regs->rq_regs_c.mpte_group_size,
+				rq_regs->rq_regs_c.swath_height, rq_regs->rq_regs_c.pte_row_height_linear);
+	}
+
+	DTN_INFO("========DLG========\n");
+	DTN_INFO("HUBP:  rc_hbe     dlg_vbe    min_d_y_n  rc_per_ht  rc_x_a_s "
+			"  dst_y_a_s  dst_y_pf   dst_y_vvb  dst_y_rvb  dst_y_vfl  dst_y_rfl  rf_pix_fq"
+			"  vratio_pf  vrat_pf_c  rc_pg_vbl  rc_pg_vbc  rc_mc_vbl  rc_mc_vbc  rc_pg_fll"
+			"  rc_pg_flc  rc_mc_fll  rc_mc_flc  pr_nom_l   pr_nom_c   rc_pg_nl   rc_pg_nc "
+			"  mr_nom_l   mr_nom_c   rc_mc_nl   rc_mc_nc   rc_ld_pl   rc_ld_pc   rc_ld_l  "
+			"  rc_ld_c    cha_cur0   ofst_cur1  cha_cur1   vr_af_vc0  ddrq_limt  x_rt_dlay"
+			"  x_rp_dlay  x_rr_sfl\n");
+	for (i = 0; i < pool->pipe_count; i++) {
+		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(pool->hubps[i])->state);
+		struct _vcs_dpi_display_dlg_regs_st *dlg_regs = &s->dlg_attr;
+
+		if (!s->blank_en)
+			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh"
+				"%  8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh"
+				"  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
+				pool->hubps[i]->inst, dlg_regs->refcyc_h_blank_end, dlg_regs->dlg_vblank_end, dlg_regs->min_dst_y_next_start,
+				dlg_regs->refcyc_per_htotal, dlg_regs->refcyc_x_after_scaler, dlg_regs->dst_y_after_scaler,
+				dlg_regs->dst_y_prefetch, dlg_regs->dst_y_per_vm_vblank, dlg_regs->dst_y_per_row_vblank,
+				dlg_regs->dst_y_per_vm_flip, dlg_regs->dst_y_per_row_flip, dlg_regs->ref_freq_to_pix_freq,
+				dlg_regs->vratio_prefetch, dlg_regs->vratio_prefetch_c, dlg_regs->refcyc_per_pte_group_vblank_l,
+				dlg_regs->refcyc_per_pte_group_vblank_c, dlg_regs->refcyc_per_meta_chunk_vblank_l,
+				dlg_regs->refcyc_per_meta_chunk_vblank_c, dlg_regs->refcyc_per_pte_group_flip_l,
+				dlg_regs->refcyc_per_pte_group_flip_c, dlg_regs->refcyc_per_meta_chunk_flip_l,
+				dlg_regs->refcyc_per_meta_chunk_flip_c, dlg_regs->dst_y_per_pte_row_nom_l,
+				dlg_regs->dst_y_per_pte_row_nom_c, dlg_regs->refcyc_per_pte_group_nom_l,
+				dlg_regs->refcyc_per_pte_group_nom_c, dlg_regs->dst_y_per_meta_row_nom_l,
+				dlg_regs->dst_y_per_meta_row_nom_c, dlg_regs->refcyc_per_meta_chunk_nom_l,
+				dlg_regs->refcyc_per_meta_chunk_nom_c, dlg_regs->refcyc_per_line_delivery_pre_l,
+				dlg_regs->refcyc_per_line_delivery_pre_c, dlg_regs->refcyc_per_line_delivery_l,
+				dlg_regs->refcyc_per_line_delivery_c, dlg_regs->chunk_hdl_adjust_cur0, dlg_regs->dst_y_offset_cur1,
+				dlg_regs->chunk_hdl_adjust_cur1, dlg_regs->vready_after_vcount0, dlg_regs->dst_y_delta_drq_limit,
+				dlg_regs->xfc_reg_transfer_delay, dlg_regs->xfc_reg_precharge_delay,
+				dlg_regs->xfc_reg_remote_surface_flip_latency);
+	}
+
+	DTN_INFO("========TTU========\n");
+	DTN_INFO("HUBP:  qos_ll_wm  qos_lh_wm  mn_ttu_vb  qos_l_flp  rc_rd_p_l  rc_rd_l    rc_rd_p_c"
+			"  rc_rd_c    rc_rd_c0   rc_rd_pc0  rc_rd_c1   rc_rd_pc1  qos_lf_l   qos_rds_l"
+			"  qos_lf_c   qos_rds_c  qos_lf_c0  qos_rds_c0 qos_lf_c1  qos_rds_c1\n");
+	for (i = 0; i < pool->pipe_count; i++) {
+		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(pool->hubps[i])->state);
+		struct _vcs_dpi_display_ttu_regs_st *ttu_regs = &s->ttu_attr;
+
+		if (!s->blank_en)
+			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
+				pool->hubps[i]->inst, ttu_regs->qos_level_low_wm, ttu_regs->qos_level_high_wm, ttu_regs->min_ttu_vblank,
+				ttu_regs->qos_level_flip, ttu_regs->refcyc_per_req_delivery_pre_l, ttu_regs->refcyc_per_req_delivery_l,
+				ttu_regs->refcyc_per_req_delivery_pre_c, ttu_regs->refcyc_per_req_delivery_c, ttu_regs->refcyc_per_req_delivery_cur0,
+				ttu_regs->refcyc_per_req_delivery_pre_cur0, ttu_regs->refcyc_per_req_delivery_cur1,
+				ttu_regs->refcyc_per_req_delivery_pre_cur1, ttu_regs->qos_level_fixed_l, ttu_regs->qos_ramp_disable_l,
+				ttu_regs->qos_level_fixed_c, ttu_regs->qos_ramp_disable_c, ttu_regs->qos_level_fixed_cur0,
+				ttu_regs->qos_ramp_disable_cur0, ttu_regs->qos_level_fixed_cur1, ttu_regs->qos_ramp_disable_cur1);
+	}
+	DTN_INFO("\n");
+}
+
 void dcn10_log_hw_state(struct dc *dc)
 {
 	struct dc_context *dc_ctx = dc->ctx;
@@ -121,41 +237,64 @@ void dcn10_log_hw_state(struct dc *dc)
 
 	dcn10_log_hubbub_state(dc);
 
-	DTN_INFO("HUBP:\t format \t addr_hi \t width \t height \t "
-			"rotation \t mirror \t  sw_mode \t "
-			"dcc_en \t blank_en \t ttu_dis \t underflow \t "
-			"min_ttu_vblank \t qos_low_wm \t qos_high_wm \n");
+	dcn10_log_hubp_states(dc);
 
+	DTN_INFO("DPP:    IGAM format  IGAM mode    DGAM mode    RGAM mode"
+			"  GAMUT mode  C11 C12   C13 C14   C21 C22   C23 C24   "
+			"C31 C32   C33 C34\n");
 	for (i = 0; i < pool->pipe_count; i++) {
-		struct hubp *hubp = pool->hubps[i];
-		struct dcn_hubp_state s;
-
-		hubp1_read_state(TO_DCN10_HUBP(hubp), &s);
-
-		DTN_INFO("[%d]:\t %xh \t %xh \t %d \t %d \t "
-				"%xh \t %xh \t %xh \t "
-				"%d \t %d \t %d \t %xh \t",
-				hubp->inst,
-				s.pixel_format,
-				s.inuse_addr_hi,
-				s.viewport_width,
-				s.viewport_height,
-				s.rotation_angle,
-				s.h_mirror_en,
-				s.sw_mode,
-				s.dcc_en,
-				s.blank_en,
-				s.ttu_disable,
-				s.underflow_status);
-		DTN_INFO_MICRO_SEC(s.min_ttu_vblank);
-		DTN_INFO_MICRO_SEC(s.qos_level_low_wm);
-		DTN_INFO_MICRO_SEC(s.qos_level_high_wm);
+		struct dpp *dpp = pool->dpps[i];
+		struct dcn_dpp_state s;
+
+		dpp->funcs->dpp_read_state(dpp, &s);
+
+		DTN_INFO("[%2d]:  %11xh  %-11s  %-11s  %-11s"
+				"%8x    %08xh %08xh %08xh %08xh %08xh %08xh",
+				dpp->inst,
+				s.igam_input_format,
+				(s.igam_lut_mode == 0) ? "BypassFixed" :
+					((s.igam_lut_mode == 1) ? "BypassFloat" :
+					((s.igam_lut_mode == 2) ? "RAM" :
+					((s.igam_lut_mode == 3) ? "RAM" :
+								 "Unknown"))),
+				(s.dgam_lut_mode == 0) ? "Bypass" :
+					((s.dgam_lut_mode == 1) ? "sRGB" :
+					((s.dgam_lut_mode == 2) ? "Ycc" :
+					((s.dgam_lut_mode == 3) ? "RAM" :
+					((s.dgam_lut_mode == 4) ? "RAM" :
+								 "Unknown")))),
+				(s.rgam_lut_mode == 0) ? "Bypass" :
+					((s.rgam_lut_mode == 1) ? "sRGB" :
+					((s.rgam_lut_mode == 2) ? "Ycc" :
+					((s.rgam_lut_mode == 3) ? "RAM" :
+					((s.rgam_lut_mode == 4) ? "RAM" :
+								 "Unknown")))),
+				s.gamut_remap_mode,
+				s.gamut_remap_c11_c12,
+				s.gamut_remap_c13_c14,
+				s.gamut_remap_c21_c22,
+				s.gamut_remap_c23_c24,
+				s.gamut_remap_c31_c32,
+				s.gamut_remap_c33_c34);
 		DTN_INFO("\n");
 	}
 	DTN_INFO("\n");
 
-	DTN_INFO("OTG:\t v_bs \t v_be \t v_ss \t v_se \t vpol \t vmax \t vmin \t "
-			"h_bs \t h_be \t h_ss \t h_se \t hpol \t htot \t vtot \t underflow\n");
+	DTN_INFO("MPCC:  OPP  DPP  MPCCBOT  MODE  ALPHA_MODE  PREMULT  OVERLAP_ONLY  IDLE\n");
+	for (i = 0; i < pool->pipe_count; i++) {
+		struct mpcc_state s = {0};
+
+		pool->mpc->funcs->read_mpcc_state(pool->mpc, i, &s);
+		if (s.opp_id != 0xf)
+			DTN_INFO("[%2d]:  %2xh  %2xh  %6xh  %4d  %10d  %7d  %12d  %4d\n",
+				i, s.opp_id, s.dpp_id, s.bot_mpcc_id,
+				s.mode, s.alpha_mode, s.pre_multiplied_alpha, s.overlap_only,
+				s.idle);
+	}
+	DTN_INFO("\n");
+
+	DTN_INFO("OTG:  v_bs  v_be  v_ss  v_se  vpol  vmax  vmin  vmax_sel  vmin_sel"
+			"  h_bs  h_be  h_ss  h_se  hpol  htot  vtot  underflow\n");
 
 	for (i = 0; i < pool->timing_generator_count; i++) {
 		struct timing_generator *tg = pool->timing_generators[i];
@@ -167,9 +306,8 @@ void dcn10_log_hw_state(struct dc *dc)
 		if ((s.otg_enabled & 1) == 0)
 			continue;
 
-		DTN_INFO("[%d]:\t %d \t %d \t %d \t %d \t "
-				"%d \t %d \t %d \t %d \t %d \t %d \t "
-				"%d \t %d \t %d \t %d \t %d \t ",
+		DTN_INFO("[%d]: %5d %5d %5d %5d %5d %5d %5d %9d %9d %5d %5d %5d"
+				" %5d %5d %5d %5d  %9d\n",
 				tg->inst,
 				s.v_blank_start,
 				s.v_blank_end,
@@ -178,6 +316,8 @@ void dcn10_log_hw_state(struct dc *dc)
 				s.v_sync_a_pol,
 				s.v_total_max,
 				s.v_total_min,
+				s.v_total_max_sel,
+				s.v_total_min_sel,
 				s.h_blank_start,
 				s.h_blank_end,
 				s.h_sync_a_start,
@@ -186,10 +326,25 @@ void dcn10_log_hw_state(struct dc *dc)
 				s.h_total,
 				s.v_total,
 				s.underflow_occurred_status);
-		DTN_INFO("\n");
+
+		// Clear underflow for debug purposes
+		// We want to keep underflow sticky bit on for the longevity tests outside of test environment.
+		// This function is called only from Windows or Diags test environment, hence it's safe to clear
+		// it from here without affecting the original intent.
+		tg->funcs->clear_optc_underflow(tg);
 	}
 	DTN_INFO("\n");
 
+	DTN_INFO("\nCALCULATED Clocks: dcfclk_khz:%d  dcfclk_deep_sleep_khz:%d  dispclk_khz:%d\n"
+		"dppclk_khz:%d  max_supported_dppclk_khz:%d  fclk_khz:%d  socclk_khz:%d\n\n",
+			dc->current_state->bw.dcn.calc_clk.dcfclk_khz,
+			dc->current_state->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
+			dc->current_state->bw.dcn.calc_clk.dispclk_khz,
+			dc->current_state->bw.dcn.calc_clk.dppclk_khz,
+			dc->current_state->bw.dcn.calc_clk.max_supported_dppclk_khz,
+			dc->current_state->bw.dcn.calc_clk.fclk_khz,
+			dc->current_state->bw.dcn.calc_clk.socclk_khz);
+
 	log_mpc_crc(dc);
 
 	DTN_INFO_END();
@@ -354,7 +509,7 @@ static void power_on_plane(
 	struct dce_hwseq *hws,
 	int plane_id)
 {
-	struct dc_context *ctx = hws->ctx;
+	DC_LOGGER_INIT(hws->ctx->logger);
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
@@ -461,7 +616,7 @@ static void false_optc_underflow_wa(
 		tg->funcs->clear_optc_underflow(tg);
 }
 
-static enum dc_status dcn10_prog_pixclk_crtc_otg(
+static enum dc_status dcn10_enable_stream_timing(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -553,7 +708,7 @@ static void reset_back_end_for_pipe(
 		struct dc_state *context)
 {
 	int i;
-	struct dc_context *ctx = dc->ctx;
+	DC_LOGGER_INIT(dc->ctx->logger);
 	if (pipe_ctx->stream_res.stream_enc == NULL) {
 		pipe_ctx->stream = NULL;
 		return;
@@ -603,6 +758,90 @@ static void reset_back_end_for_pipe(
 					pipe_ctx->pipe_idx, pipe_ctx->stream_res.tg->inst);
 }
 
+static bool dcn10_hw_wa_force_recovery(struct dc *dc)
+{
+	struct hubp *hubp ;
+	unsigned int i;
+	bool need_recover = true;
+
+	if (!dc->debug.recovery_enabled)
+		return false;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx != NULL) {
+			hubp = pipe_ctx->plane_res.hubp;
+			if (hubp != NULL) {
+				if (hubp->funcs->hubp_get_underflow_status(hubp) != 0) {
+					/* one pipe underflow, we will reset all the pipes*/
+					need_recover = true;
+				}
+			}
+		}
+	}
+	if (!need_recover)
+		return false;
+	/*
+	DCHUBP_CNTL:HUBP_BLANK_EN=1
+	DCHUBBUB_SOFT_RESET:DCHUBBUB_GLOBAL_SOFT_RESET=1
+	DCHUBP_CNTL:HUBP_DISABLE=1
+	DCHUBP_CNTL:HUBP_DISABLE=0
+	DCHUBBUB_SOFT_RESET:DCHUBBUB_GLOBAL_SOFT_RESET=0
+	DCSURF_PRIMARY_SURFACE_ADDRESS
+	DCHUBP_CNTL:HUBP_BLANK_EN=0
+	*/
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx != NULL) {
+			hubp = pipe_ctx->plane_res.hubp;
+			/*DCHUBP_CNTL:HUBP_BLANK_EN=1*/
+			if (hubp != NULL)
+				hubp->funcs->set_hubp_blank_en(hubp, true);
+		}
+	}
+	/*DCHUBBUB_SOFT_RESET:DCHUBBUB_GLOBAL_SOFT_RESET=1*/
+	hubbub1_soft_reset(dc->res_pool->hubbub, true);
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx != NULL) {
+			hubp = pipe_ctx->plane_res.hubp;
+			/*DCHUBP_CNTL:HUBP_DISABLE=1*/
+			if (hubp != NULL)
+				hubp->funcs->hubp_disable_control(hubp, true);
+		}
+	}
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx != NULL) {
+			hubp = pipe_ctx->plane_res.hubp;
+			/*DCHUBP_CNTL:HUBP_DISABLE=0*/
+			if (hubp != NULL)
+				hubp->funcs->hubp_disable_control(hubp, true);
+		}
+	}
+	/*DCHUBBUB_SOFT_RESET:DCHUBBUB_GLOBAL_SOFT_RESET=0*/
+	hubbub1_soft_reset(dc->res_pool->hubbub, false);
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx != NULL) {
+			hubp = pipe_ctx->plane_res.hubp;
+			/*DCHUBP_CNTL:HUBP_BLANK_EN=0*/
+			if (hubp != NULL)
+				hubp->funcs->set_hubp_blank_en(hubp, true);
+		}
+	}
+	return true;
+
+}
+
+
 static void dcn10_verify_allow_pstate_change_high(struct dc *dc)
 {
 	static bool should_log_hw_state; /* prevent hw state log by default */
@@ -611,13 +850,17 @@ static void dcn10_verify_allow_pstate_change_high(struct dc *dc)
 		if (should_log_hw_state) {
 			dcn10_log_hw_state(dc);
 		}
-
 		BREAK_TO_DEBUGGER();
+		if (dcn10_hw_wa_force_recovery(dc)) {
+		/*check again*/
+			if (!hubbub1_verify_allow_pstate_change_high(dc->res_pool->hubbub))
+				BREAK_TO_DEBUGGER();
+		}
 	}
 }
 
 /* trigger HW to start disconnect plane from stream on the next vsync */
-static void plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	int dpp_id = pipe_ctx->plane_res.dpp->inst;
@@ -649,7 +892,7 @@ static void plane_atomic_power_down(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct dce_hwseq *hws = dc->hwseq;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
-	struct dc_context *ctx = dc->ctx;
+	DC_LOGGER_INIT(dc->ctx->logger);
 
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
@@ -699,7 +942,7 @@ static void plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 
 static void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
-	struct dc_context *ctx = dc->ctx;
+	DC_LOGGER_INIT(dc->ctx->logger);
 
 	if (!pipe_ctx->plane_res.hubp || pipe_ctx->plane_res.hubp->power_gated)
 		return;
@@ -800,7 +1043,7 @@ static void dcn10_init_hw(struct dc *dc)
 		dc->res_pool->opps[i]->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 		pipe_ctx->stream_res.opp = dc->res_pool->opps[i];
 
-		plane_atomic_disconnect(dc, pipe_ctx);
+		hwss1_plane_atomic_disconnect(dc, pipe_ctx);
 	}
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -945,9 +1188,8 @@ static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 		tf = plane_state->in_transfer_func;
 
 	if (plane_state->gamma_correction &&
-		plane_state->gamma_correction->is_identity)
-		dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
-	else if (plane_state->gamma_correction && dce_use_lut(plane_state->format))
+		!plane_state->gamma_correction->is_identity
+			&& dce_use_lut(plane_state->format))
 		dpp_base->funcs->dpp_program_input_lut(dpp_base, plane_state->gamma_correction);
 
 	if (tf == NULL)
@@ -1433,7 +1675,7 @@ static void program_csc_matrix(struct pipe_ctx *pipe_ctx,
 	}
 }
 
-static void program_output_csc(struct dc *dc,
+static void dcn10_program_output_csc(struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum dc_color_space colorspace,
 		uint16_t *matrix,
@@ -1542,22 +1784,22 @@ static uint16_t fixed_point_to_int_frac(
 
 	uint16_t result;
 
-	uint16_t d = (uint16_t)dal_fixed31_32_floor(
-		dal_fixed31_32_abs(
+	uint16_t d = (uint16_t)dc_fixpt_floor(
+		dc_fixpt_abs(
 			arg));
 
 	if (d <= (uint16_t)(1 << integer_bits) - (1 / (uint16_t)divisor))
-		numerator = (uint16_t)dal_fixed31_32_floor(
-			dal_fixed31_32_mul_int(
+		numerator = (uint16_t)dc_fixpt_floor(
+			dc_fixpt_mul_int(
 				arg,
 				divisor));
 	else {
-		numerator = dal_fixed31_32_floor(
-			dal_fixed31_32_sub(
-				dal_fixed31_32_from_int(
+		numerator = dc_fixpt_floor(
+			dc_fixpt_sub(
+				dc_fixpt_from_int(
 					1LL << integer_bits),
-				dal_fixed31_32_recip(
-					dal_fixed31_32_from_int(
+				dc_fixpt_recip(
+					dc_fixpt_from_int(
 						divisor))));
 	}
 
@@ -1567,8 +1809,8 @@ static uint16_t fixed_point_to_int_frac(
 		result = (uint16_t)(
 		(1 << (integer_bits + fractional_bits + 1)) + numerator);
 
-	if ((result != 0) && dal_fixed31_32_lt(
-		arg, dal_fixed31_32_zero))
+	if ((result != 0) && dc_fixpt_lt(
+		arg, dc_fixpt_zero))
 		result |= 1 << (integer_bits + fractional_bits);
 
 	return result;
@@ -1582,8 +1824,8 @@ void build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
 			&& plane_state->input_csc_color_matrix.enable_adjustment
 			&& plane_state->coeff_reduction_factor.value != 0) {
 		bias_and_scale->scale_blue = fixed_point_to_int_frac(
-			dal_fixed31_32_mul(plane_state->coeff_reduction_factor,
-					dal_fixed31_32_from_fraction(256, 255)),
+			dc_fixpt_mul(plane_state->coeff_reduction_factor,
+					dc_fixpt_from_fraction(256, 255)),
 				2,
 				13);
 		bias_and_scale->scale_red = bias_and_scale->scale_blue;
@@ -1623,6 +1865,8 @@ static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	struct mpc *mpc = dc->res_pool->mpc;
 	struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params);
 
+
+
 	/* TODO: proper fix once fpga works */
 
 	if (dc->debug.surface_visual_confirm)
@@ -1649,6 +1893,7 @@ static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 			pipe_ctx->stream->output_color_space)
 					&& per_pixel_alpha;
 
+
 	/*
 	 * TODO: remove hack
 	 * Note: currently there is a bug in init_hw such that
@@ -1659,6 +1904,12 @@ static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	 */
 	mpcc_id = hubp->inst;
 
+	/* If there is no full update, don't need to touch MPC tree*/
+	if (!pipe_ctx->plane_state->update_flags.bits.full_update) {
+		mpc->funcs->update_blending(mpc, &blnd_cfg, mpcc_id);
+		return;
+	}
+
 	/* check if this MPCC is already being used */
 	new_mpcc = mpc->funcs->get_mpcc_for_dpp(mpc_tree_params, mpcc_id);
 	/* remove MPCC if being used */
@@ -1777,7 +2028,7 @@ static void update_dchubp_dpp(
 		/*gamut remap*/
 		program_gamut_remap(pipe_ctx);
 
-		program_output_csc(dc,
+		dc->hwss.program_output_csc(dc,
 				pipe_ctx,
 				pipe_ctx->stream->output_color_space,
 				pipe_ctx->stream->csc_color_matrix.matrix,
@@ -1810,9 +2061,9 @@ static void update_dchubp_dpp(
 		hubp->funcs->set_blank(hubp, false);
 }
 
-static void dcn10_otg_blank(
+static void dcn10_blank_pixel_data(
 		struct dc *dc,
-		struct stream_resource stream_res,
+		struct stream_resource *stream_res,
 		struct dc_stream_state *stream,
 		bool blank)
 {
@@ -1823,27 +2074,27 @@ static void dcn10_otg_blank(
 	color_space = stream->output_color_space;
 	color_space_to_black_color(dc, color_space, &black_color);
 
-	if (stream_res.tg->funcs->set_blank_color)
-		stream_res.tg->funcs->set_blank_color(
-				stream_res.tg,
+	if (stream_res->tg->funcs->set_blank_color)
+		stream_res->tg->funcs->set_blank_color(
+				stream_res->tg,
 				&black_color);
 
 	if (!blank) {
-		if (stream_res.tg->funcs->set_blank)
-			stream_res.tg->funcs->set_blank(stream_res.tg, blank);
-		if (stream_res.abm)
-			stream_res.abm->funcs->set_abm_level(stream_res.abm, stream->abm_level);
+		if (stream_res->tg->funcs->set_blank)
+			stream_res->tg->funcs->set_blank(stream_res->tg, blank);
+		if (stream_res->abm)
+			stream_res->abm->funcs->set_abm_level(stream_res->abm, stream->abm_level);
 	} else if (blank) {
-		if (stream_res.abm)
-			stream_res.abm->funcs->set_abm_immediate_disable(stream_res.abm);
-		if (stream_res.tg->funcs->set_blank)
-			stream_res.tg->funcs->set_blank(stream_res.tg, blank);
+		if (stream_res->abm)
+			stream_res->abm->funcs->set_abm_immediate_disable(stream_res->abm);
+		if (stream_res->tg->funcs->set_blank)
+			stream_res->tg->funcs->set_blank(stream_res->tg, blank);
 	}
 }
 
 static void set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
 {
-	struct fixed31_32 multiplier = dal_fixed31_32_from_fraction(
+	struct fixed31_32 multiplier = dc_fixpt_from_fraction(
 			pipe_ctx->plane_state->sdr_white_level, 80);
 	uint32_t hw_mult = 0x1f000; // 1.0 default multiplier
 	struct custom_float_format fmt;
@@ -1876,7 +2127,7 @@ static void program_all_pipe_in_tree(
 		pipe_ctx->stream_res.tg->funcs->program_global_sync(
 				pipe_ctx->stream_res.tg);
 
-		dcn10_otg_blank(dc, pipe_ctx->stream_res,
+		dc->hwss.blank_pixel_data(dc, &pipe_ctx->stream_res,
 				pipe_ctx->stream, blank);
 	}
 
@@ -1983,9 +2234,9 @@ static void dcn10_apply_ctx_for_surface(
 	bool removed_pipe[4] = { false };
 	unsigned int ref_clk_mhz = dc->res_pool->ref_clock_inKhz/1000;
 	bool program_water_mark = false;
-	struct dc_context *ctx = dc->ctx;
 	struct pipe_ctx *top_pipe_to_program =
 			find_top_pipe_for_stream(dc, context, stream);
+	DC_LOGGER_INIT(dc->ctx->logger);
 
 	if (!top_pipe_to_program)
 		return;
@@ -1996,7 +2247,7 @@ static void dcn10_apply_ctx_for_surface(
 
 	if (num_planes == 0) {
 		/* OTG blank before remove all front end */
-		dcn10_otg_blank(dc, top_pipe_to_program->stream_res, top_pipe_to_program->stream, true);
+		dc->hwss.blank_pixel_data(dc, &top_pipe_to_program->stream_res, top_pipe_to_program->stream, true);
 	}
 
 	/* Disconnect unused mpcc */
@@ -2027,7 +2278,7 @@ static void dcn10_apply_ctx_for_surface(
 			old_pipe_ctx->plane_state &&
 			old_pipe_ctx->stream_res.tg == tg) {
 
-			plane_atomic_disconnect(dc, old_pipe_ctx);
+			hwss1_plane_atomic_disconnect(dc, old_pipe_ctx);
 			removed_pipe[i] = true;
 
 			DC_LOG_DC(
@@ -2335,15 +2586,6 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
 			set_static_screen_control(pipe_ctx[i]->stream_res.tg, value);
 }
 
-static void set_plane_config(
-	const struct dc *dc,
-	struct pipe_ctx *pipe_ctx,
-	struct resource_context *res_ctx)
-{
-	/* TODO */
-	program_gamut_remap(pipe_ctx);
-}
-
 static void dcn10_config_stereo_parameters(
 		struct dc_stream_state *stream, struct crtc_stereo_flags *flags)
 {
@@ -2521,12 +2763,12 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.init_hw = dcn10_init_hw,
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = dcn10_apply_ctx_for_surface,
-	.set_plane_config = set_plane_config,
 	.update_plane_addr = dcn10_update_plane_addr,
 	.update_dchub = dcn10_update_dchub,
 	.update_pending_status = dcn10_update_pending_status,
 	.set_input_transfer_func = dcn10_set_input_transfer_func,
 	.set_output_transfer_func = dcn10_set_output_transfer_func,
+	.program_output_csc = dcn10_program_output_csc,
 	.power_down = dce110_power_down,
 	.enable_accelerated_mode = dce110_enable_accelerated_mode,
 	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
@@ -2538,10 +2780,11 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.blank_stream = dce110_blank_stream,
 	.enable_display_power_gating = dcn10_dummy_display_power_gating,
 	.disable_plane = dcn10_disable_plane,
+	.blank_pixel_data = dcn10_blank_pixel_data,
 	.pipe_control_lock = dcn10_pipe_control_lock,
 	.set_bandwidth = dcn10_set_bandwidth,
 	.reset_hw_ctx_wrap = reset_hw_ctx_wrap,
-	.prog_pixclk_crtc_otg = dcn10_prog_pixclk_crtc_otg,
+	.enable_stream_timing = dcn10_enable_stream_timing,
 	.set_drr = set_drr,
 	.get_position = get_position,
 	.set_static_screen_control = set_static_screen_control,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index 6c526b5095d9..44f734b73f9e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -37,4 +37,6 @@ extern void fill_display_configs(
 
 bool is_rgb_cspace(enum dc_color_space output_color_space);
 
+void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx);
+
 #endif /* __DC_HWSS_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
new file mode 100644
index 000000000000..21fa40ac0786
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -0,0 +1,1362 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "reg_helper.h"
+
+#include "core_types.h"
+#include "link_encoder.h"
+#include "dcn10_link_encoder.h"
+#include "stream_encoder.h"
+#include "i2caux_interface.h"
+#include "dc_bios_types.h"
+
+#include "gpio_service_interface.h"
+
+#define CTX \
+	enc10->base.ctx
+#define DC_LOGGER \
+	enc10->base.ctx->logger
+
+#define REG(reg)\
+	(enc10->link_regs->reg)
+
+#undef FN
+#define FN(reg_name, field_name) \
+	enc10->link_shift->field_name, enc10->link_mask->field_name
+
+
+/*
+ * @brief
+ * Trigger Source Select
+ * ASIC-dependent, actual values for register programming
+ */
+#define DCN10_DIG_FE_SOURCE_SELECT_INVALID 0x0
+#define DCN10_DIG_FE_SOURCE_SELECT_DIGA 0x1
+#define DCN10_DIG_FE_SOURCE_SELECT_DIGB 0x2
+#define DCN10_DIG_FE_SOURCE_SELECT_DIGC 0x4
+#define DCN10_DIG_FE_SOURCE_SELECT_DIGD 0x08
+#define DCN10_DIG_FE_SOURCE_SELECT_DIGE 0x10
+#define DCN10_DIG_FE_SOURCE_SELECT_DIGF 0x20
+#define DCN10_DIG_FE_SOURCE_SELECT_DIGG 0x40
+
+enum {
+	DP_MST_UPDATE_MAX_RETRY = 50
+};
+
+
+
+static void aux_initialize(struct dcn10_link_encoder *enc10);
+
+
+static const struct link_encoder_funcs dcn10_lnk_enc_funcs = {
+	.validate_output_with_stream =
+		dcn10_link_encoder_validate_output_with_stream,
+	.hw_init = dcn10_link_encoder_hw_init,
+	.setup = dcn10_link_encoder_setup,
+	.enable_tmds_output = dcn10_link_encoder_enable_tmds_output,
+	.enable_dp_output = dcn10_link_encoder_enable_dp_output,
+	.enable_dp_mst_output = dcn10_link_encoder_enable_dp_mst_output,
+	.disable_output = dcn10_link_encoder_disable_output,
+	.dp_set_lane_settings = dcn10_link_encoder_dp_set_lane_settings,
+	.dp_set_phy_pattern = dcn10_link_encoder_dp_set_phy_pattern,
+	.update_mst_stream_allocation_table =
+		dcn10_link_encoder_update_mst_stream_allocation_table,
+	.psr_program_dp_dphy_fast_training =
+			dcn10_psr_program_dp_dphy_fast_training,
+	.psr_program_secondary_packet = dcn10_psr_program_secondary_packet,
+	.connect_dig_be_to_fe = dcn10_link_encoder_connect_dig_be_to_fe,
+	.enable_hpd = dcn10_link_encoder_enable_hpd,
+	.disable_hpd = dcn10_link_encoder_disable_hpd,
+	.is_dig_enabled = dcn10_is_dig_enabled,
+	.destroy = dcn10_link_encoder_destroy
+};
+
+static enum bp_result link_transmitter_control(
+	struct dcn10_link_encoder *enc10,
+	struct bp_transmitter_control *cntl)
+{
+	enum bp_result result;
+	struct dc_bios *bp = enc10->base.ctx->dc_bios;
+
+	result = bp->funcs->transmitter_control(bp, cntl);
+
+	return result;
+}
+
+static void enable_phy_bypass_mode(
+	struct dcn10_link_encoder *enc10,
+	bool enable)
+{
+	/* This register resides in DP back end block;
+	 * transmitter is used for the offset
+	 */
+	REG_UPDATE(DP_DPHY_CNTL, DPHY_BYPASS, enable);
+
+}
+
+static void disable_prbs_symbols(
+	struct dcn10_link_encoder *enc10,
+	bool disable)
+{
+	/* This register resides in DP back end block;
+	 * transmitter is used for the offset
+	 */
+	REG_UPDATE_4(DP_DPHY_CNTL,
+			DPHY_ATEST_SEL_LANE0, disable,
+			DPHY_ATEST_SEL_LANE1, disable,
+			DPHY_ATEST_SEL_LANE2, disable,
+			DPHY_ATEST_SEL_LANE3, disable);
+}
+
+static void disable_prbs_mode(
+	struct dcn10_link_encoder *enc10)
+{
+	REG_UPDATE(DP_DPHY_PRBS_CNTL, DPHY_PRBS_EN, 0);
+}
+
+static void program_pattern_symbols(
+	struct dcn10_link_encoder *enc10,
+	uint16_t pattern_symbols[8])
+{
+	/* This register resides in DP back end block;
+	 * transmitter is used for the offset
+	 */
+	REG_SET_3(DP_DPHY_SYM0, 0,
+			DPHY_SYM1, pattern_symbols[0],
+			DPHY_SYM2, pattern_symbols[1],
+			DPHY_SYM3, pattern_symbols[2]);
+
+	/* This register resides in DP back end block;
+	 * transmitter is used for the offset
+	 */
+	REG_SET_3(DP_DPHY_SYM1, 0,
+			DPHY_SYM4, pattern_symbols[3],
+			DPHY_SYM5, pattern_symbols[4],
+			DPHY_SYM6, pattern_symbols[5]);
+
+	/* This register resides in DP back end block;
+	 * transmitter is used for the offset
+	 */
+	REG_SET_2(DP_DPHY_SYM2, 0,
+			DPHY_SYM7, pattern_symbols[6],
+			DPHY_SYM8, pattern_symbols[7]);
+}
+
+static void set_dp_phy_pattern_d102(
+	struct dcn10_link_encoder *enc10)
+{
+	/* Disable PHY Bypass mode to setup the test pattern */
+	enable_phy_bypass_mode(enc10, false);
+
+	/* For 10-bit PRBS or debug symbols
+	 * please use the following sequence:
+	 *
+	 * Enable debug symbols on the lanes
+	 */
+	disable_prbs_symbols(enc10, true);
+
+	/* Disable PRBS mode */
+	disable_prbs_mode(enc10);
+
+	/* Program debug symbols to be output */
+	{
+		uint16_t pattern_symbols[8] = {
+			0x2AA, 0x2AA, 0x2AA, 0x2AA,
+			0x2AA, 0x2AA, 0x2AA, 0x2AA
+		};
+
+		program_pattern_symbols(enc10, pattern_symbols);
+	}
+
+	/* Enable phy bypass mode to enable the test pattern */
+
+	enable_phy_bypass_mode(enc10, true);
+}
+
+static void set_link_training_complete(
+	struct dcn10_link_encoder *enc10,
+	bool complete)
+{
+	/* This register resides in DP back end block;
+	 * transmitter is used for the offset
+	 */
+	REG_UPDATE(DP_LINK_CNTL, DP_LINK_TRAINING_COMPLETE, complete);
+
+}
+
+void dcn10_link_encoder_set_dp_phy_pattern_training_pattern(
+	struct link_encoder *enc,
+	uint32_t index)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	/* Write Training Pattern */
+
+	REG_WRITE(DP_DPHY_TRAINING_PATTERN_SEL, index);
+
+	/* Set HW Register Training Complete to false */
+
+	set_link_training_complete(enc10, false);
+
+	/* Disable PHY Bypass mode to output Training Pattern */
+
+	enable_phy_bypass_mode(enc10, false);
+
+	/* Disable PRBS mode */
+	disable_prbs_mode(enc10);
+}
+
+static void setup_panel_mode(
+	struct dcn10_link_encoder *enc10,
+	enum dp_panel_mode panel_mode)
+{
+	uint32_t value;
+
+	ASSERT(REG(DP_DPHY_INTERNAL_CTRL));
+	value = REG_READ(DP_DPHY_INTERNAL_CTRL);
+
+	switch (panel_mode) {
+	case DP_PANEL_MODE_EDP:
+		value = 0x1;
+		break;
+	case DP_PANEL_MODE_SPECIAL:
+		value = 0x11;
+		break;
+	default:
+		value = 0x0;
+		break;
+	}
+
+	REG_WRITE(DP_DPHY_INTERNAL_CTRL, value);
+}
+
+static void set_dp_phy_pattern_symbol_error(
+	struct dcn10_link_encoder *enc10)
+{
+	/* Disable PHY Bypass mode to setup the test pattern */
+	enable_phy_bypass_mode(enc10, false);
+
+	/* program correct panel mode*/
+	setup_panel_mode(enc10, DP_PANEL_MODE_DEFAULT);
+
+	/* A PRBS23 pattern is used for most DP electrical measurements. */
+
+	/* Enable PRBS symbols on the lanes */
+	disable_prbs_symbols(enc10, false);
+
+	/* For PRBS23 Set bit DPHY_PRBS_SEL=1 and Set bit DPHY_PRBS_EN=1 */
+	REG_UPDATE_2(DP_DPHY_PRBS_CNTL,
+			DPHY_PRBS_SEL, 1,
+			DPHY_PRBS_EN, 1);
+
+	/* Enable phy bypass mode to enable the test pattern */
+	enable_phy_bypass_mode(enc10, true);
+}
+
+static void set_dp_phy_pattern_prbs7(
+	struct dcn10_link_encoder *enc10)
+{
+	/* Disable PHY Bypass mode to setup the test pattern */
+	enable_phy_bypass_mode(enc10, false);
+
+	/* A PRBS7 pattern is used for most DP electrical measurements. */
+
+	/* Enable PRBS symbols on the lanes */
+	disable_prbs_symbols(enc10, false);
+
+	/* For PRBS7 Set bit DPHY_PRBS_SEL=0 and Set bit DPHY_PRBS_EN=1 */
+	REG_UPDATE_2(DP_DPHY_PRBS_CNTL,
+			DPHY_PRBS_SEL, 0,
+			DPHY_PRBS_EN, 1);
+
+	/* Enable phy bypass mode to enable the test pattern */
+	enable_phy_bypass_mode(enc10, true);
+}
+
+static void set_dp_phy_pattern_80bit_custom(
+	struct dcn10_link_encoder *enc10,
+	const uint8_t *pattern)
+{
+	/* Disable PHY Bypass mode to setup the test pattern */
+	enable_phy_bypass_mode(enc10, false);
+
+	/* Enable debug symbols on the lanes */
+
+	disable_prbs_symbols(enc10, true);
+
+	/* Enable PHY bypass mode to enable the test pattern */
+	/* TODO is it really needed ? */
+
+	enable_phy_bypass_mode(enc10, true);
+
+	/* Program 80 bit custom pattern */
+	{
+		uint16_t pattern_symbols[8];
+
+		pattern_symbols[0] =
+			((pattern[1] & 0x03) << 8) | pattern[0];
+		pattern_symbols[1] =
+			((pattern[2] & 0x0f) << 6) | ((pattern[1] >> 2) & 0x3f);
+		pattern_symbols[2] =
+			((pattern[3] & 0x3f) << 4) | ((pattern[2] >> 4) & 0x0f);
+		pattern_symbols[3] =
+			(pattern[4] << 2) | ((pattern[3] >> 6) & 0x03);
+		pattern_symbols[4] =
+			((pattern[6] & 0x03) << 8) | pattern[5];
+		pattern_symbols[5] =
+			((pattern[7] & 0x0f) << 6) | ((pattern[6] >> 2) & 0x3f);
+		pattern_symbols[6] =
+			((pattern[8] & 0x3f) << 4) | ((pattern[7] >> 4) & 0x0f);
+		pattern_symbols[7] =
+			(pattern[9] << 2) | ((pattern[8] >> 6) & 0x03);
+
+		program_pattern_symbols(enc10, pattern_symbols);
+	}
+
+	/* Enable phy bypass mode to enable the test pattern */
+
+	enable_phy_bypass_mode(enc10, true);
+}
+
+static void set_dp_phy_pattern_hbr2_compliance_cp2520_2(
+	struct dcn10_link_encoder *enc10,
+	unsigned int cp2520_pattern)
+{
+
+	/* previously there is a register DP_HBR2_EYE_PATTERN
+	 * that is enabled to get the pattern.
+	 * But it does not work with the latest spec change,
+	 * so we are programming the following registers manually.
+	 *
+	 * The following settings have been confirmed
+	 * by Nick Chorney and Sandra Liu
+	 */
+
+	/* Disable PHY Bypass mode to setup the test pattern */
+
+	enable_phy_bypass_mode(enc10, false);
+
+	/* Setup DIG encoder in DP SST mode */
+	enc10->base.funcs->setup(&enc10->base, SIGNAL_TYPE_DISPLAY_PORT);
+
+	/* ensure normal panel mode. */
+	setup_panel_mode(enc10, DP_PANEL_MODE_DEFAULT);
+
+	/* no vbid after BS (SR)
+	 * DP_LINK_FRAMING_CNTL changed history Sandra Liu
+	 * 11000260 / 11000104 / 110000FC
+	 */
+	REG_UPDATE_3(DP_LINK_FRAMING_CNTL,
+			DP_IDLE_BS_INTERVAL, 0xFC,
+			DP_VBID_DISABLE, 1,
+			DP_VID_ENHANCED_FRAME_MODE, 1);
+
+	/* swap every BS with SR */
+	REG_UPDATE(DP_DPHY_SCRAM_CNTL, DPHY_SCRAMBLER_BS_COUNT, 0);
+
+	/* select cp2520 patterns */
+	if (REG(DP_DPHY_HBR2_PATTERN_CONTROL))
+		REG_UPDATE(DP_DPHY_HBR2_PATTERN_CONTROL,
+				DP_DPHY_HBR2_PATTERN_CONTROL, cp2520_pattern);
+	else
+		/* pre-DCE11 can only generate CP2520 pattern 2 */
+		ASSERT(cp2520_pattern == 2);
+
+	/* set link training complete */
+	set_link_training_complete(enc10, true);
+
+	/* disable video stream */
+	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, 0);
+
+	/* Disable PHY Bypass mode to setup the test pattern */
+	enable_phy_bypass_mode(enc10, false);
+}
+
+static void set_dp_phy_pattern_passthrough_mode(
+	struct dcn10_link_encoder *enc10,
+	enum dp_panel_mode panel_mode)
+{
+	/* program correct panel mode */
+	setup_panel_mode(enc10, panel_mode);
+
+	/* restore LINK_FRAMING_CNTL and DPHY_SCRAMBLER_BS_COUNT
+	 * in case we were doing HBR2 compliance pattern before
+	 */
+	REG_UPDATE_3(DP_LINK_FRAMING_CNTL,
+			DP_IDLE_BS_INTERVAL, 0x2000,
+			DP_VBID_DISABLE, 0,
+			DP_VID_ENHANCED_FRAME_MODE, 1);
+
+	REG_UPDATE(DP_DPHY_SCRAM_CNTL, DPHY_SCRAMBLER_BS_COUNT, 0x1FF);
+
+	/* set link training complete */
+	set_link_training_complete(enc10, true);
+
+	/* Disable PHY Bypass mode to setup the test pattern */
+	enable_phy_bypass_mode(enc10, false);
+
+	/* Disable PRBS mode */
+	disable_prbs_mode(enc10);
+}
+
+/* return value is bit-vector */
+static uint8_t get_frontend_source(
+	enum engine_id engine)
+{
+	switch (engine) {
+	case ENGINE_ID_DIGA:
+		return DCN10_DIG_FE_SOURCE_SELECT_DIGA;
+	case ENGINE_ID_DIGB:
+		return DCN10_DIG_FE_SOURCE_SELECT_DIGB;
+	case ENGINE_ID_DIGC:
+		return DCN10_DIG_FE_SOURCE_SELECT_DIGC;
+	case ENGINE_ID_DIGD:
+		return DCN10_DIG_FE_SOURCE_SELECT_DIGD;
+	case ENGINE_ID_DIGE:
+		return DCN10_DIG_FE_SOURCE_SELECT_DIGE;
+	case ENGINE_ID_DIGF:
+		return DCN10_DIG_FE_SOURCE_SELECT_DIGF;
+	case ENGINE_ID_DIGG:
+		return DCN10_DIG_FE_SOURCE_SELECT_DIGG;
+	default:
+		ASSERT_CRITICAL(false);
+		return DCN10_DIG_FE_SOURCE_SELECT_INVALID;
+	}
+}
+
+static void configure_encoder(
+	struct dcn10_link_encoder *enc10,
+	const struct dc_link_settings *link_settings)
+{
+	/* set number of lanes */
+
+	REG_SET(DP_CONFIG, 0,
+			DP_UDI_LANES, link_settings->lane_count - LANE_COUNT_ONE);
+
+	/* setup scrambler */
+	REG_UPDATE(DP_DPHY_SCRAM_CNTL, DPHY_SCRAMBLER_ADVANCE, 1);
+}
+
+void dcn10_psr_program_dp_dphy_fast_training(struct link_encoder *enc,
+			bool exit_link_training_required)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+
+	if (exit_link_training_required)
+		REG_UPDATE(DP_DPHY_FAST_TRAINING,
+				DPHY_RX_FAST_TRAINING_CAPABLE, 1);
+	else {
+		REG_UPDATE(DP_DPHY_FAST_TRAINING,
+				DPHY_RX_FAST_TRAINING_CAPABLE, 0);
+		/*In DCE 11, we are able to pre-program a Force SR register
+		 * to be able to trigger SR symbol after 5 idle patterns
+		 * transmitted. Upon PSR Exit, DMCU can trigger
+		 * DPHY_LOAD_BS_COUNT_START = 1. Upon writing 1 to
+		 * DPHY_LOAD_BS_COUNT_START and the internal counter
+		 * reaches DPHY_LOAD_BS_COUNT, the next BS symbol will be
+		 * replaced by SR symbol once.
+		 */
+
+		REG_UPDATE(DP_DPHY_BS_SR_SWAP_CNTL, DPHY_LOAD_BS_COUNT, 0x5);
+	}
+}
+
+void dcn10_psr_program_secondary_packet(struct link_encoder *enc,
+			unsigned int sdp_transmit_line_num_deadline)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+
+	REG_UPDATE_2(DP_SEC_CNTL1,
+		DP_SEC_GSP0_LINE_NUM, sdp_transmit_line_num_deadline,
+		DP_SEC_GSP0_PRIORITY, 1);
+}
+
+bool dcn10_is_dig_enabled(struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	uint32_t value;
+
+	REG_GET(DIG_BE_EN_CNTL, DIG_ENABLE, &value);
+	return value;
+}
+
+static void link_encoder_disable(struct dcn10_link_encoder *enc10)
+{
+	/* reset training pattern */
+	REG_SET(DP_DPHY_TRAINING_PATTERN_SEL, 0,
+			DPHY_TRAINING_PATTERN_SEL, 0);
+
+	/* reset training complete */
+	REG_UPDATE(DP_LINK_CNTL, DP_LINK_TRAINING_COMPLETE, 0);
+
+	/* reset panel mode */
+	setup_panel_mode(enc10, DP_PANEL_MODE_DEFAULT);
+}
+
+static void hpd_initialize(
+	struct dcn10_link_encoder *enc10)
+{
+	/* Associate HPD with DIG_BE */
+	enum hpd_source_id hpd_source = enc10->base.hpd_source;
+
+	REG_UPDATE(DIG_BE_CNTL, DIG_HPD_SELECT, hpd_source);
+}
+
+bool dcn10_link_encoder_validate_dvi_output(
+	const struct dcn10_link_encoder *enc10,
+	enum signal_type connector_signal,
+	enum signal_type signal,
+	const struct dc_crtc_timing *crtc_timing)
+{
+	uint32_t max_pixel_clock = TMDS_MAX_PIXEL_CLOCK;
+
+	if (signal == SIGNAL_TYPE_DVI_DUAL_LINK)
+		max_pixel_clock *= 2;
+
+	/* This handles the case of HDMI downgrade to DVI we don't want to
+	 * we don't want to cap the pixel clock if the DDI is not DVI.
+	 */
+	if (connector_signal != SIGNAL_TYPE_DVI_DUAL_LINK &&
+			connector_signal != SIGNAL_TYPE_DVI_SINGLE_LINK)
+		max_pixel_clock = enc10->base.features.max_hdmi_pixel_clock;
+
+	/* DVI only support RGB pixel encoding */
+	if (crtc_timing->pixel_encoding != PIXEL_ENCODING_RGB)
+		return false;
+
+	/*connect DVI via adpater's HDMI connector*/
+	if ((connector_signal == SIGNAL_TYPE_DVI_SINGLE_LINK ||
+		connector_signal == SIGNAL_TYPE_HDMI_TYPE_A) &&
+		signal != SIGNAL_TYPE_HDMI_TYPE_A &&
+		crtc_timing->pix_clk_khz > TMDS_MAX_PIXEL_CLOCK)
+		return false;
+	if (crtc_timing->pix_clk_khz < TMDS_MIN_PIXEL_CLOCK)
+		return false;
+
+	if (crtc_timing->pix_clk_khz > max_pixel_clock)
+		return false;
+
+	/* DVI supports 6/8bpp single-link and 10/16bpp dual-link */
+	switch (crtc_timing->display_color_depth) {
+	case COLOR_DEPTH_666:
+	case COLOR_DEPTH_888:
+	break;
+	case COLOR_DEPTH_101010:
+	case COLOR_DEPTH_161616:
+		if (signal != SIGNAL_TYPE_DVI_DUAL_LINK)
+			return false;
+	break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static bool dcn10_link_encoder_validate_hdmi_output(
+	const struct dcn10_link_encoder *enc10,
+	const struct dc_crtc_timing *crtc_timing,
+	int adjusted_pix_clk_khz)
+{
+	enum dc_color_depth max_deep_color =
+			enc10->base.features.max_hdmi_deep_color;
+
+	if (max_deep_color < crtc_timing->display_color_depth)
+		return false;
+
+	if (crtc_timing->display_color_depth < COLOR_DEPTH_888)
+		return false;
+	if (adjusted_pix_clk_khz < TMDS_MIN_PIXEL_CLOCK)
+		return false;
+
+	if ((adjusted_pix_clk_khz == 0) ||
+		(adjusted_pix_clk_khz > enc10->base.features.max_hdmi_pixel_clock))
+		return false;
+
+	/* DCE11 HW does not support 420 */
+	if (!enc10->base.features.ycbcr420_supported &&
+			crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
+
+	if (!enc10->base.features.flags.bits.HDMI_6GB_EN &&
+		adjusted_pix_clk_khz >= 300000)
+		return false;
+	return true;
+}
+
+bool dcn10_link_encoder_validate_dp_output(
+	const struct dcn10_link_encoder *enc10,
+	const struct dc_crtc_timing *crtc_timing)
+{
+	/* default RGB only */
+	if (crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB)
+		return true;
+
+	if (enc10->base.features.flags.bits.IS_YCBCR_CAPABLE)
+		return true;
+
+	/* for DCE 8.x or later DP Y-only feature,
+	 * we need ASIC cap + FeatureSupportDPYonly, not support 666
+	 */
+	if (crtc_timing->flags.Y_ONLY &&
+		enc10->base.features.flags.bits.IS_YCBCR_CAPABLE &&
+		crtc_timing->display_color_depth != COLOR_DEPTH_666)
+		return true;
+
+	return false;
+}
+
+void dcn10_link_encoder_construct(
+	struct dcn10_link_encoder *enc10,
+	const struct encoder_init_data *init_data,
+	const struct encoder_feature_support *enc_features,
+	const struct dcn10_link_enc_registers *link_regs,
+	const struct dcn10_link_enc_aux_registers *aux_regs,
+	const struct dcn10_link_enc_hpd_registers *hpd_regs,
+	const struct dcn10_link_enc_shift *link_shift,
+	const struct dcn10_link_enc_mask *link_mask)
+{
+	struct bp_encoder_cap_info bp_cap_info = {0};
+	const struct dc_vbios_funcs *bp_funcs = init_data->ctx->dc_bios->funcs;
+	enum bp_result result = BP_RESULT_OK;
+
+	enc10->base.funcs = &dcn10_lnk_enc_funcs;
+	enc10->base.ctx = init_data->ctx;
+	enc10->base.id = init_data->encoder;
+
+	enc10->base.hpd_source = init_data->hpd_source;
+	enc10->base.connector = init_data->connector;
+
+	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
+
+	enc10->base.features = *enc_features;
+
+	enc10->base.transmitter = init_data->transmitter;
+
+	/* set the flag to indicate whether driver poll the I2C data pin
+	 * while doing the DP sink detect
+	 */
+
+/*	if (dal_adapter_service_is_feature_supported(as,
+		FEATURE_DP_SINK_DETECT_POLL_DATA_PIN))
+		enc10->base.features.flags.bits.
+			DP_SINK_DETECT_POLL_DATA_PIN = true;*/
+
+	enc10->base.output_signals =
+		SIGNAL_TYPE_DVI_SINGLE_LINK |
+		SIGNAL_TYPE_DVI_DUAL_LINK |
+		SIGNAL_TYPE_LVDS |
+		SIGNAL_TYPE_DISPLAY_PORT |
+		SIGNAL_TYPE_DISPLAY_PORT_MST |
+		SIGNAL_TYPE_EDP |
+		SIGNAL_TYPE_HDMI_TYPE_A;
+
+	/* For DCE 8.0 and 8.1, by design, UNIPHY is hardwired to DIG_BE.
+	 * SW always assign DIG_FE 1:1 mapped to DIG_FE for non-MST UNIPHY.
+	 * SW assign DIG_FE to non-MST UNIPHY first and MST last. So prefer
+	 * DIG is per UNIPHY and used by SST DP, eDP, HDMI, DVI and LVDS.
+	 * Prefer DIG assignment is decided by board design.
+	 * For DCE 8.0, there are only max 6 UNIPHYs, we assume board design
+	 * and VBIOS will filter out 7 UNIPHY for DCE 8.0.
+	 * By this, adding DIGG should not hurt DCE 8.0.
+	 * This will let DCE 8.1 share DCE 8.0 as much as possible
+	 */
+
+	enc10->link_regs = link_regs;
+	enc10->aux_regs = aux_regs;
+	enc10->hpd_regs = hpd_regs;
+	enc10->link_shift = link_shift;
+	enc10->link_mask = link_mask;
+
+	switch (enc10->base.transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		enc10->base.preferred_engine = ENGINE_ID_DIGA;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		enc10->base.preferred_engine = ENGINE_ID_DIGB;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		enc10->base.preferred_engine = ENGINE_ID_DIGC;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		enc10->base.preferred_engine = ENGINE_ID_DIGD;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		enc10->base.preferred_engine = ENGINE_ID_DIGE;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		enc10->base.preferred_engine = ENGINE_ID_DIGF;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		enc10->base.preferred_engine = ENGINE_ID_DIGG;
+	break;
+	default:
+		ASSERT_CRITICAL(false);
+		enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
+	}
+
+	/* default to one to mirror Windows behavior */
+	enc10->base.features.flags.bits.HDMI_6GB_EN = 1;
+
+	result = bp_funcs->get_encoder_cap_info(enc10->base.ctx->dc_bios,
+						enc10->base.id, &bp_cap_info);
+
+	/* Override features with DCE-specific values */
+	if (result == BP_RESULT_OK) {
+		enc10->base.features.flags.bits.IS_HBR2_CAPABLE =
+				bp_cap_info.DP_HBR2_EN;
+		enc10->base.features.flags.bits.IS_HBR3_CAPABLE =
+				bp_cap_info.DP_HBR3_EN;
+		enc10->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN;
+	} else {
+		DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n",
+				__func__,
+				result);
+	}
+}
+
+bool dcn10_link_encoder_validate_output_with_stream(
+	struct link_encoder *enc,
+	const struct dc_stream_state *stream)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	bool is_valid;
+
+	switch (stream->signal) {
+	case SIGNAL_TYPE_DVI_SINGLE_LINK:
+	case SIGNAL_TYPE_DVI_DUAL_LINK:
+		is_valid = dcn10_link_encoder_validate_dvi_output(
+			enc10,
+			stream->sink->link->connector_signal,
+			stream->signal,
+			&stream->timing);
+	break;
+	case SIGNAL_TYPE_HDMI_TYPE_A:
+		is_valid = dcn10_link_encoder_validate_hdmi_output(
+				enc10,
+				&stream->timing,
+				stream->phy_pix_clk);
+	break;
+	case SIGNAL_TYPE_DISPLAY_PORT:
+	case SIGNAL_TYPE_DISPLAY_PORT_MST:
+		is_valid = dcn10_link_encoder_validate_dp_output(
+					enc10, &stream->timing);
+	break;
+	case SIGNAL_TYPE_EDP:
+		is_valid = (stream->timing.pixel_encoding == PIXEL_ENCODING_RGB) ? true : false;
+	break;
+	case SIGNAL_TYPE_VIRTUAL:
+		is_valid = true;
+		break;
+	default:
+		is_valid = false;
+	break;
+	}
+
+	return is_valid;
+}
+
+void dcn10_link_encoder_hw_init(
+	struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	struct bp_transmitter_control cntl = { 0 };
+	enum bp_result result;
+
+	cntl.action = TRANSMITTER_CONTROL_INIT;
+	cntl.engine_id = ENGINE_ID_UNKNOWN;
+	cntl.transmitter = enc10->base.transmitter;
+	cntl.connector_obj_id = enc10->base.connector;
+	cntl.lanes_number = LANE_COUNT_FOUR;
+	cntl.coherent = false;
+	cntl.hpd_sel = enc10->base.hpd_source;
+
+	if (enc10->base.connector.id == CONNECTOR_ID_EDP)
+		cntl.signal = SIGNAL_TYPE_EDP;
+
+	result = link_transmitter_control(enc10, &cntl);
+
+	if (result != BP_RESULT_OK) {
+		DC_LOG_ERROR("%s: Failed to execute VBIOS command table!\n",
+			__func__);
+		BREAK_TO_DEBUGGER();
+		return;
+	}
+
+	if (enc10->base.connector.id == CONNECTOR_ID_LVDS) {
+		cntl.action = TRANSMITTER_CONTROL_BACKLIGHT_BRIGHTNESS;
+
+		result = link_transmitter_control(enc10, &cntl);
+
+		ASSERT(result == BP_RESULT_OK);
+
+	}
+	aux_initialize(enc10);
+
+	/* reinitialize HPD.
+	 * hpd_initialize() will pass DIG_FE id to HW context.
+	 * All other routine within HW context will use fe_engine_offset
+	 * as DIG_FE id even caller pass DIG_FE id.
+	 * So this routine must be called first.
+	 */
+	hpd_initialize(enc10);
+}
+
+void dcn10_link_encoder_destroy(struct link_encoder **enc)
+{
+	kfree(TO_DCN10_LINK_ENC(*enc));
+	*enc = NULL;
+}
+
+void dcn10_link_encoder_setup(
+	struct link_encoder *enc,
+	enum signal_type signal)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+
+	switch (signal) {
+	case SIGNAL_TYPE_EDP:
+	case SIGNAL_TYPE_DISPLAY_PORT:
+		/* DP SST */
+		REG_UPDATE(DIG_BE_CNTL, DIG_MODE, 0);
+		break;
+	case SIGNAL_TYPE_LVDS:
+		/* LVDS */
+		REG_UPDATE(DIG_BE_CNTL, DIG_MODE, 1);
+		break;
+	case SIGNAL_TYPE_DVI_SINGLE_LINK:
+	case SIGNAL_TYPE_DVI_DUAL_LINK:
+		/* TMDS-DVI */
+		REG_UPDATE(DIG_BE_CNTL, DIG_MODE, 2);
+		break;
+	case SIGNAL_TYPE_HDMI_TYPE_A:
+		/* TMDS-HDMI */
+		REG_UPDATE(DIG_BE_CNTL, DIG_MODE, 3);
+		break;
+	case SIGNAL_TYPE_DISPLAY_PORT_MST:
+		/* DP MST */
+		REG_UPDATE(DIG_BE_CNTL, DIG_MODE, 5);
+		break;
+	default:
+		ASSERT_CRITICAL(false);
+		/* invalid mode ! */
+		break;
+	}
+
+}
+
+/* TODO: still need depth or just pass in adjusted pixel clock? */
+void dcn10_link_encoder_enable_tmds_output(
+	struct link_encoder *enc,
+	enum clock_source_id clock_source,
+	enum dc_color_depth color_depth,
+	enum signal_type signal,
+	uint32_t pixel_clock)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	struct bp_transmitter_control cntl = { 0 };
+	enum bp_result result;
+
+	/* Enable the PHY */
+
+	cntl.action = TRANSMITTER_CONTROL_ENABLE;
+	cntl.engine_id = enc->preferred_engine;
+	cntl.transmitter = enc10->base.transmitter;
+	cntl.pll_id = clock_source;
+	cntl.signal = signal;
+	if (cntl.signal == SIGNAL_TYPE_DVI_DUAL_LINK)
+		cntl.lanes_number = 8;
+	else
+		cntl.lanes_number = 4;
+
+	cntl.hpd_sel = enc10->base.hpd_source;
+
+	cntl.pixel_clock = pixel_clock;
+	cntl.color_depth = color_depth;
+
+	result = link_transmitter_control(enc10, &cntl);
+
+	if (result != BP_RESULT_OK) {
+		DC_LOG_ERROR("%s: Failed to execute VBIOS command table!\n",
+			__func__);
+		BREAK_TO_DEBUGGER();
+	}
+}
+
+/* enables DP PHY output */
+void dcn10_link_encoder_enable_dp_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	struct bp_transmitter_control cntl = { 0 };
+	enum bp_result result;
+
+	/* Enable the PHY */
+
+	/* number_of_lanes is used for pixel clock adjust,
+	 * but it's not passed to asic_control.
+	 * We need to set number of lanes manually.
+	 */
+	configure_encoder(enc10, link_settings);
+
+	cntl.action = TRANSMITTER_CONTROL_ENABLE;
+	cntl.engine_id = enc->preferred_engine;
+	cntl.transmitter = enc10->base.transmitter;
+	cntl.pll_id = clock_source;
+	cntl.signal = SIGNAL_TYPE_DISPLAY_PORT;
+	cntl.lanes_number = link_settings->lane_count;
+	cntl.hpd_sel = enc10->base.hpd_source;
+	cntl.pixel_clock = link_settings->link_rate
+						* LINK_RATE_REF_FREQ_IN_KHZ;
+	/* TODO: check if undefined works */
+	cntl.color_depth = COLOR_DEPTH_UNDEFINED;
+
+	result = link_transmitter_control(enc10, &cntl);
+
+	if (result != BP_RESULT_OK) {
+		DC_LOG_ERROR("%s: Failed to execute VBIOS command table!\n",
+			__func__);
+		BREAK_TO_DEBUGGER();
+	}
+}
+
+/* enables DP PHY output in MST mode */
+void dcn10_link_encoder_enable_dp_mst_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	struct bp_transmitter_control cntl = { 0 };
+	enum bp_result result;
+
+	/* Enable the PHY */
+
+	/* number_of_lanes is used for pixel clock adjust,
+	 * but it's not passed to asic_control.
+	 * We need to set number of lanes manually.
+	 */
+	configure_encoder(enc10, link_settings);
+
+	cntl.action = TRANSMITTER_CONTROL_ENABLE;
+	cntl.engine_id = ENGINE_ID_UNKNOWN;
+	cntl.transmitter = enc10->base.transmitter;
+	cntl.pll_id = clock_source;
+	cntl.signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
+	cntl.lanes_number = link_settings->lane_count;
+	cntl.hpd_sel = enc10->base.hpd_source;
+	cntl.pixel_clock = link_settings->link_rate
+						* LINK_RATE_REF_FREQ_IN_KHZ;
+	/* TODO: check if undefined works */
+	cntl.color_depth = COLOR_DEPTH_UNDEFINED;
+
+	result = link_transmitter_control(enc10, &cntl);
+
+	if (result != BP_RESULT_OK) {
+		DC_LOG_ERROR("%s: Failed to execute VBIOS command table!\n",
+			__func__);
+		BREAK_TO_DEBUGGER();
+	}
+}
+/*
+ * @brief
+ * Disable transmitter and its encoder
+ */
+void dcn10_link_encoder_disable_output(
+	struct link_encoder *enc,
+	enum signal_type signal)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	struct bp_transmitter_control cntl = { 0 };
+	enum bp_result result;
+
+	if (!dcn10_is_dig_enabled(enc)) {
+		/* OF_SKIP_POWER_DOWN_INACTIVE_ENCODER */
+		return;
+	}
+	/* Power-down RX and disable GPU PHY should be paired.
+	 * Disabling PHY without powering down RX may cause
+	 * symbol lock loss, on which we will get DP Sink interrupt.
+	 */
+
+	/* There is a case for the DP active dongles
+	 * where we want to disable the PHY but keep RX powered,
+	 * for those we need to ignore DP Sink interrupt
+	 * by checking lane count that has been set
+	 * on the last do_enable_output().
+	 */
+
+	/* disable transmitter */
+	cntl.action = TRANSMITTER_CONTROL_DISABLE;
+	cntl.transmitter = enc10->base.transmitter;
+	cntl.hpd_sel = enc10->base.hpd_source;
+	cntl.signal = signal;
+	cntl.connector_obj_id = enc10->base.connector;
+
+	result = link_transmitter_control(enc10, &cntl);
+
+	if (result != BP_RESULT_OK) {
+		DC_LOG_ERROR("%s: Failed to execute VBIOS command table!\n",
+			__func__);
+		BREAK_TO_DEBUGGER();
+		return;
+	}
+
+	/* disable encoder */
+	if (dc_is_dp_signal(signal))
+		link_encoder_disable(enc10);
+}
+
+void dcn10_link_encoder_dp_set_lane_settings(
+	struct link_encoder *enc,
+	const struct link_training_settings *link_settings)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	union dpcd_training_lane_set training_lane_set = { { 0 } };
+	int32_t lane = 0;
+	struct bp_transmitter_control cntl = { 0 };
+
+	if (!link_settings) {
+		BREAK_TO_DEBUGGER();
+		return;
+	}
+
+	cntl.action = TRANSMITTER_CONTROL_SET_VOLTAGE_AND_PREEMPASIS;
+	cntl.transmitter = enc10->base.transmitter;
+	cntl.connector_obj_id = enc10->base.connector;
+	cntl.lanes_number = link_settings->link_settings.lane_count;
+	cntl.hpd_sel = enc10->base.hpd_source;
+	cntl.pixel_clock = link_settings->link_settings.link_rate *
+						LINK_RATE_REF_FREQ_IN_KHZ;
+
+	for (lane = 0; lane < link_settings->link_settings.lane_count; lane++) {
+		/* translate lane settings */
+
+		training_lane_set.bits.VOLTAGE_SWING_SET =
+			link_settings->lane_settings[lane].VOLTAGE_SWING;
+		training_lane_set.bits.PRE_EMPHASIS_SET =
+			link_settings->lane_settings[lane].PRE_EMPHASIS;
+
+		/* post cursor 2 setting only applies to HBR2 link rate */
+		if (link_settings->link_settings.link_rate == LINK_RATE_HIGH2) {
+			/* this is passed to VBIOS
+			 * to program post cursor 2 level
+			 */
+			training_lane_set.bits.POST_CURSOR2_SET =
+				link_settings->lane_settings[lane].POST_CURSOR2;
+		}
+
+		cntl.lane_select = lane;
+		cntl.lane_settings = training_lane_set.raw;
+
+		/* call VBIOS table to set voltage swing and pre-emphasis */
+		link_transmitter_control(enc10, &cntl);
+	}
+}
+
+/* set DP PHY test and training patterns */
+void dcn10_link_encoder_dp_set_phy_pattern(
+	struct link_encoder *enc,
+	const struct encoder_set_dp_phy_pattern_param *param)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+
+	switch (param->dp_phy_pattern) {
+	case DP_TEST_PATTERN_TRAINING_PATTERN1:
+		dcn10_link_encoder_set_dp_phy_pattern_training_pattern(enc, 0);
+		break;
+	case DP_TEST_PATTERN_TRAINING_PATTERN2:
+		dcn10_link_encoder_set_dp_phy_pattern_training_pattern(enc, 1);
+		break;
+	case DP_TEST_PATTERN_TRAINING_PATTERN3:
+		dcn10_link_encoder_set_dp_phy_pattern_training_pattern(enc, 2);
+		break;
+	case DP_TEST_PATTERN_TRAINING_PATTERN4:
+		dcn10_link_encoder_set_dp_phy_pattern_training_pattern(enc, 3);
+		break;
+	case DP_TEST_PATTERN_D102:
+		set_dp_phy_pattern_d102(enc10);
+		break;
+	case DP_TEST_PATTERN_SYMBOL_ERROR:
+		set_dp_phy_pattern_symbol_error(enc10);
+		break;
+	case DP_TEST_PATTERN_PRBS7:
+		set_dp_phy_pattern_prbs7(enc10);
+		break;
+	case DP_TEST_PATTERN_80BIT_CUSTOM:
+		set_dp_phy_pattern_80bit_custom(
+			enc10, param->custom_pattern);
+		break;
+	case DP_TEST_PATTERN_CP2520_1:
+		set_dp_phy_pattern_hbr2_compliance_cp2520_2(enc10, 1);
+		break;
+	case DP_TEST_PATTERN_CP2520_2:
+		set_dp_phy_pattern_hbr2_compliance_cp2520_2(enc10, 2);
+		break;
+	case DP_TEST_PATTERN_CP2520_3:
+		set_dp_phy_pattern_hbr2_compliance_cp2520_2(enc10, 3);
+		break;
+	case DP_TEST_PATTERN_VIDEO_MODE: {
+		set_dp_phy_pattern_passthrough_mode(
+			enc10, param->dp_panel_mode);
+		break;
+	}
+
+	default:
+		/* invalid phy pattern */
+		ASSERT_CRITICAL(false);
+		break;
+	}
+}
+
+static void fill_stream_allocation_row_info(
+	const struct link_mst_stream_allocation *stream_allocation,
+	uint32_t *src,
+	uint32_t *slots)
+{
+	const struct stream_encoder *stream_enc = stream_allocation->stream_enc;
+
+	if (stream_enc) {
+		*src = stream_enc->id;
+		*slots = stream_allocation->slot_count;
+	} else {
+		*src = 0;
+		*slots = 0;
+	}
+}
+
+/* programs DP MST VC payload allocation */
+void dcn10_link_encoder_update_mst_stream_allocation_table(
+	struct link_encoder *enc,
+	const struct link_mst_stream_allocation_table *table)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	uint32_t value0 = 0;
+	uint32_t value1 = 0;
+	uint32_t value2 = 0;
+	uint32_t slots = 0;
+	uint32_t src = 0;
+	uint32_t retries = 0;
+
+	/* For CZ, there are only 3 pipes. So Virtual channel is up 3.*/
+
+	/* --- Set MSE Stream Attribute -
+	 * Setup VC Payload Table on Tx Side,
+	 * Issue allocation change trigger
+	 * to commit payload on both tx and rx side
+	 */
+
+	/* we should clean-up table each time */
+
+	if (table->stream_count >= 1) {
+		fill_stream_allocation_row_info(
+			&table->stream_allocations[0],
+			&src,
+			&slots);
+	} else {
+		src = 0;
+		slots = 0;
+	}
+
+	REG_UPDATE_2(DP_MSE_SAT0,
+			DP_MSE_SAT_SRC0, src,
+			DP_MSE_SAT_SLOT_COUNT0, slots);
+
+	if (table->stream_count >= 2) {
+		fill_stream_allocation_row_info(
+			&table->stream_allocations[1],
+			&src,
+			&slots);
+	} else {
+		src = 0;
+		slots = 0;
+	}
+
+	REG_UPDATE_2(DP_MSE_SAT0,
+			DP_MSE_SAT_SRC1, src,
+			DP_MSE_SAT_SLOT_COUNT1, slots);
+
+	if (table->stream_count >= 3) {
+		fill_stream_allocation_row_info(
+			&table->stream_allocations[2],
+			&src,
+			&slots);
+	} else {
+		src = 0;
+		slots = 0;
+	}
+
+	REG_UPDATE_2(DP_MSE_SAT1,
+			DP_MSE_SAT_SRC2, src,
+			DP_MSE_SAT_SLOT_COUNT2, slots);
+
+	if (table->stream_count >= 4) {
+		fill_stream_allocation_row_info(
+			&table->stream_allocations[3],
+			&src,
+			&slots);
+	} else {
+		src = 0;
+		slots = 0;
+	}
+
+	REG_UPDATE_2(DP_MSE_SAT1,
+			DP_MSE_SAT_SRC3, src,
+			DP_MSE_SAT_SLOT_COUNT3, slots);
+
+	/* --- wait for transaction finish */
+
+	/* send allocation change trigger (ACT) ?
+	 * this step first sends the ACT,
+	 * then double buffers the SAT into the hardware
+	 * making the new allocation active on the DP MST mode link
+	 */
+
+	/* DP_MSE_SAT_UPDATE:
+	 * 0 - No Action
+	 * 1 - Update SAT with trigger
+	 * 2 - Update SAT without trigger
+	 */
+	REG_UPDATE(DP_MSE_SAT_UPDATE,
+			DP_MSE_SAT_UPDATE, 1);
+
+	/* wait for update to complete
+	 * (i.e. DP_MSE_SAT_UPDATE field is reset to 0)
+	 * then wait for the transmission
+	 * of at least 16 MTP headers on immediate local link.
+	 * i.e. DP_MSE_16_MTP_KEEPOUT field (read only) is reset to 0
+	 * a value of 1 indicates that DP MST mode
+	 * is in the 16 MTP keepout region after a VC has been added.
+	 * MST stream bandwidth (VC rate) can be configured
+	 * after this bit is cleared
+	 */
+	do {
+		udelay(10);
+
+		value0 = REG_READ(DP_MSE_SAT_UPDATE);
+
+		REG_GET(DP_MSE_SAT_UPDATE,
+				DP_MSE_SAT_UPDATE, &value1);
+
+		REG_GET(DP_MSE_SAT_UPDATE,
+				DP_MSE_16_MTP_KEEPOUT, &value2);
+
+		/* bit field DP_MSE_SAT_UPDATE is set to 1 already */
+		if (!value1 && !value2)
+			break;
+		++retries;
+	} while (retries < DP_MST_UPDATE_MAX_RETRY);
+}
+
+void dcn10_link_encoder_connect_dig_be_to_fe(
+	struct link_encoder *enc,
+	enum engine_id engine,
+	bool connect)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	uint32_t field;
+
+	if (engine != ENGINE_ID_UNKNOWN) {
+
+		REG_GET(DIG_BE_CNTL, DIG_FE_SOURCE_SELECT, &field);
+
+		if (connect)
+			field |= get_frontend_source(engine);
+		else
+			field &= ~get_frontend_source(engine);
+
+		REG_UPDATE(DIG_BE_CNTL, DIG_FE_SOURCE_SELECT, field);
+	}
+}
+
+
+#define HPD_REG(reg)\
+	(enc10->hpd_regs->reg)
+
+#define HPD_REG_READ(reg_name) \
+		dm_read_reg(CTX, HPD_REG(reg_name))
+
+#define HPD_REG_UPDATE_N(reg_name, n, ...)	\
+		generic_reg_update_ex(CTX, \
+				HPD_REG(reg_name), \
+				HPD_REG_READ(reg_name), \
+				n, __VA_ARGS__)
+
+#define HPD_REG_UPDATE(reg_name, field, val)	\
+		HPD_REG_UPDATE_N(reg_name, 1, \
+				FN(reg_name, field), val)
+
+void dcn10_link_encoder_enable_hpd(struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+
+	HPD_REG_UPDATE(DC_HPD_CONTROL,
+			DC_HPD_EN, 1);
+}
+
+void dcn10_link_encoder_disable_hpd(struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+
+	HPD_REG_UPDATE(DC_HPD_CONTROL,
+			DC_HPD_EN, 0);
+}
+
+
+#define AUX_REG(reg)\
+	(enc10->aux_regs->reg)
+
+#define AUX_REG_READ(reg_name) \
+		dm_read_reg(CTX, AUX_REG(reg_name))
+
+#define AUX_REG_UPDATE_N(reg_name, n, ...)	\
+		generic_reg_update_ex(CTX, \
+				AUX_REG(reg_name), \
+				AUX_REG_READ(reg_name), \
+				n, __VA_ARGS__)
+
+#define AUX_REG_UPDATE(reg_name, field, val)	\
+		AUX_REG_UPDATE_N(reg_name, 1, \
+				FN(reg_name, field), val)
+
+#define AUX_REG_UPDATE_2(reg, f1, v1, f2, v2)	\
+		AUX_REG_UPDATE_N(reg, 2,\
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+static void aux_initialize(
+	struct dcn10_link_encoder *enc10)
+{
+	enum hpd_source_id hpd_source = enc10->base.hpd_source;
+
+	AUX_REG_UPDATE_2(AUX_CONTROL,
+			AUX_HPD_SEL, hpd_source,
+			AUX_LS_READ_EN, 0);
+
+	/* 1/4 window (the maximum allowed) */
+	AUX_REG_UPDATE(AUX_DPHY_RX_CONTROL0,
+			AUX_RX_RECEIVE_WINDOW, 1);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
new file mode 100644
index 000000000000..2a97cdb2cfbb
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -0,0 +1,330 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ *  and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_LINK_ENCODER__DCN10_H__
+#define __DC_LINK_ENCODER__DCN10_H__
+
+#include "link_encoder.h"
+
+#define TO_DCN10_LINK_ENC(link_encoder)\
+	container_of(link_encoder, struct dcn10_link_encoder, base)
+
+
+#define AUX_REG_LIST(id)\
+	SRI(AUX_CONTROL, DP_AUX, id), \
+	SRI(AUX_DPHY_RX_CONTROL0, DP_AUX, id)
+
+#define HPD_REG_LIST(id)\
+	SRI(DC_HPD_CONTROL, HPD, id)
+
+#define LE_DCN_COMMON_REG_LIST(id) \
+	SRI(DIG_BE_CNTL, DIG, id), \
+	SRI(DIG_BE_EN_CNTL, DIG, id), \
+	SRI(DP_CONFIG, DP, id), \
+	SRI(DP_DPHY_CNTL, DP, id), \
+	SRI(DP_DPHY_PRBS_CNTL, DP, id), \
+	SRI(DP_DPHY_SCRAM_CNTL, DP, id),\
+	SRI(DP_DPHY_SYM0, DP, id), \
+	SRI(DP_DPHY_SYM1, DP, id), \
+	SRI(DP_DPHY_SYM2, DP, id), \
+	SRI(DP_DPHY_TRAINING_PATTERN_SEL, DP, id), \
+	SRI(DP_LINK_CNTL, DP, id), \
+	SRI(DP_LINK_FRAMING_CNTL, DP, id), \
+	SRI(DP_MSE_SAT0, DP, id), \
+	SRI(DP_MSE_SAT1, DP, id), \
+	SRI(DP_MSE_SAT2, DP, id), \
+	SRI(DP_MSE_SAT_UPDATE, DP, id), \
+	SRI(DP_SEC_CNTL, DP, id), \
+	SRI(DP_VID_STREAM_CNTL, DP, id), \
+	SRI(DP_DPHY_FAST_TRAINING, DP, id), \
+	SRI(DP_SEC_CNTL1, DP, id), \
+	SRI(DP_DPHY_BS_SR_SWAP_CNTL, DP, id), \
+	SRI(DP_DPHY_INTERNAL_CTRL, DP, id), \
+	SRI(DP_DPHY_HBR2_PATTERN_CONTROL, DP, id)
+
+#define LE_DCN10_REG_LIST(id)\
+	LE_DCN_COMMON_REG_LIST(id)
+
+struct dcn10_link_enc_aux_registers {
+	uint32_t AUX_CONTROL;
+	uint32_t AUX_DPHY_RX_CONTROL0;
+};
+
+struct dcn10_link_enc_hpd_registers {
+	uint32_t DC_HPD_CONTROL;
+};
+
+struct dcn10_link_enc_registers {
+	uint32_t DIG_BE_CNTL;
+	uint32_t DIG_BE_EN_CNTL;
+	uint32_t DP_CONFIG;
+	uint32_t DP_DPHY_CNTL;
+	uint32_t DP_DPHY_INTERNAL_CTRL;
+	uint32_t DP_DPHY_PRBS_CNTL;
+	uint32_t DP_DPHY_SCRAM_CNTL;
+	uint32_t DP_DPHY_SYM0;
+	uint32_t DP_DPHY_SYM1;
+	uint32_t DP_DPHY_SYM2;
+	uint32_t DP_DPHY_TRAINING_PATTERN_SEL;
+	uint32_t DP_LINK_CNTL;
+	uint32_t DP_LINK_FRAMING_CNTL;
+	uint32_t DP_MSE_SAT0;
+	uint32_t DP_MSE_SAT1;
+	uint32_t DP_MSE_SAT2;
+	uint32_t DP_MSE_SAT_UPDATE;
+	uint32_t DP_SEC_CNTL;
+	uint32_t DP_VID_STREAM_CNTL;
+	uint32_t DP_DPHY_FAST_TRAINING;
+	uint32_t DP_DPHY_BS_SR_SWAP_CNTL;
+	uint32_t DP_DPHY_HBR2_PATTERN_CONTROL;
+	uint32_t DP_SEC_CNTL1;
+};
+
+#define LE_SF(reg_name, field_name, post_fix)\
+	.field_name = reg_name ## __ ## field_name ## post_fix
+
+#define LINK_ENCODER_MASK_SH_LIST_DCN10(mask_sh)\
+	LE_SF(DIG0_DIG_BE_EN_CNTL, DIG_ENABLE, mask_sh),\
+	LE_SF(DIG0_DIG_BE_CNTL, DIG_HPD_SELECT, mask_sh),\
+	LE_SF(DIG0_DIG_BE_CNTL, DIG_MODE, mask_sh),\
+	LE_SF(DIG0_DIG_BE_CNTL, DIG_FE_SOURCE_SELECT, mask_sh),\
+	LE_SF(DP0_DP_DPHY_CNTL, DPHY_BYPASS, mask_sh),\
+	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE0, mask_sh),\
+	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE1, mask_sh),\
+	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE2, mask_sh),\
+	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE3, mask_sh),\
+	LE_SF(DP0_DP_DPHY_PRBS_CNTL, DPHY_PRBS_EN, mask_sh),\
+	LE_SF(DP0_DP_DPHY_PRBS_CNTL, DPHY_PRBS_SEL, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SYM0, DPHY_SYM1, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SYM0, DPHY_SYM2, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SYM0, DPHY_SYM3, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SYM1, DPHY_SYM4, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SYM1, DPHY_SYM5, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SYM1, DPHY_SYM6, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SYM2, DPHY_SYM7, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SYM2, DPHY_SYM8, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SCRAM_CNTL, DPHY_SCRAMBLER_BS_COUNT, mask_sh),\
+	LE_SF(DP0_DP_DPHY_SCRAM_CNTL, DPHY_SCRAMBLER_ADVANCE, mask_sh),\
+	LE_SF(DP0_DP_DPHY_FAST_TRAINING, DPHY_RX_FAST_TRAINING_CAPABLE, mask_sh),\
+	LE_SF(DP0_DP_DPHY_BS_SR_SWAP_CNTL, DPHY_LOAD_BS_COUNT, mask_sh),\
+	LE_SF(DP0_DP_DPHY_TRAINING_PATTERN_SEL, DPHY_TRAINING_PATTERN_SEL, mask_sh),\
+	LE_SF(DP0_DP_DPHY_HBR2_PATTERN_CONTROL, DP_DPHY_HBR2_PATTERN_CONTROL, mask_sh),\
+	LE_SF(DP0_DP_LINK_CNTL, DP_LINK_TRAINING_COMPLETE, mask_sh),\
+	LE_SF(DP0_DP_LINK_FRAMING_CNTL, DP_IDLE_BS_INTERVAL, mask_sh),\
+	LE_SF(DP0_DP_LINK_FRAMING_CNTL, DP_VBID_DISABLE, mask_sh),\
+	LE_SF(DP0_DP_LINK_FRAMING_CNTL, DP_VID_ENHANCED_FRAME_MODE, mask_sh),\
+	LE_SF(DP0_DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, mask_sh),\
+	LE_SF(DP0_DP_CONFIG, DP_UDI_LANES, mask_sh),\
+	LE_SF(DP0_DP_SEC_CNTL1, DP_SEC_GSP0_LINE_NUM, mask_sh),\
+	LE_SF(DP0_DP_SEC_CNTL1, DP_SEC_GSP0_PRIORITY, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT0, DP_MSE_SAT_SRC0, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT0, DP_MSE_SAT_SRC1, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT0, DP_MSE_SAT_SLOT_COUNT0, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT0, DP_MSE_SAT_SLOT_COUNT1, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT1, DP_MSE_SAT_SRC2, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT1, DP_MSE_SAT_SRC3, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT1, DP_MSE_SAT_SLOT_COUNT2, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT1, DP_MSE_SAT_SLOT_COUNT3, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT_UPDATE, DP_MSE_SAT_UPDATE, mask_sh),\
+	LE_SF(DP0_DP_MSE_SAT_UPDATE, DP_MSE_16_MTP_KEEPOUT, mask_sh),\
+	LE_SF(DP_AUX0_AUX_CONTROL, AUX_HPD_SEL, mask_sh),\
+	LE_SF(DP_AUX0_AUX_CONTROL, AUX_LS_READ_EN, mask_sh),\
+	LE_SF(DP_AUX0_AUX_DPHY_RX_CONTROL0, AUX_RX_RECEIVE_WINDOW, mask_sh),\
+	LE_SF(HPD0_DC_HPD_CONTROL, DC_HPD_EN, mask_sh)
+
+#define DCN_LINK_ENCODER_REG_FIELD_LIST(type) \
+	type DIG_ENABLE;\
+	type DIG_HPD_SELECT;\
+	type DIG_MODE;\
+	type DIG_FE_SOURCE_SELECT;\
+	type DPHY_BYPASS;\
+	type DPHY_ATEST_SEL_LANE0;\
+	type DPHY_ATEST_SEL_LANE1;\
+	type DPHY_ATEST_SEL_LANE2;\
+	type DPHY_ATEST_SEL_LANE3;\
+	type DPHY_PRBS_EN;\
+	type DPHY_PRBS_SEL;\
+	type DPHY_SYM1;\
+	type DPHY_SYM2;\
+	type DPHY_SYM3;\
+	type DPHY_SYM4;\
+	type DPHY_SYM5;\
+	type DPHY_SYM6;\
+	type DPHY_SYM7;\
+	type DPHY_SYM8;\
+	type DPHY_SCRAMBLER_BS_COUNT;\
+	type DPHY_SCRAMBLER_ADVANCE;\
+	type DPHY_RX_FAST_TRAINING_CAPABLE;\
+	type DPHY_LOAD_BS_COUNT;\
+	type DPHY_TRAINING_PATTERN_SEL;\
+	type DP_DPHY_HBR2_PATTERN_CONTROL;\
+	type DP_LINK_TRAINING_COMPLETE;\
+	type DP_IDLE_BS_INTERVAL;\
+	type DP_VBID_DISABLE;\
+	type DP_VID_ENHANCED_FRAME_MODE;\
+	type DP_VID_STREAM_ENABLE;\
+	type DP_UDI_LANES;\
+	type DP_SEC_GSP0_LINE_NUM;\
+	type DP_SEC_GSP0_PRIORITY;\
+	type DP_MSE_SAT_SRC0;\
+	type DP_MSE_SAT_SRC1;\
+	type DP_MSE_SAT_SRC2;\
+	type DP_MSE_SAT_SRC3;\
+	type DP_MSE_SAT_SLOT_COUNT0;\
+	type DP_MSE_SAT_SLOT_COUNT1;\
+	type DP_MSE_SAT_SLOT_COUNT2;\
+	type DP_MSE_SAT_SLOT_COUNT3;\
+	type DP_MSE_SAT_UPDATE;\
+	type DP_MSE_16_MTP_KEEPOUT;\
+	type AUX_HPD_SEL;\
+	type AUX_LS_READ_EN;\
+	type AUX_RX_RECEIVE_WINDOW;\
+	type DC_HPD_EN
+
+struct dcn10_link_enc_shift {
+	DCN_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
+};
+
+struct dcn10_link_enc_mask {
+	DCN_LINK_ENCODER_REG_FIELD_LIST(uint32_t);
+};
+
+struct dcn10_link_encoder {
+	struct link_encoder base;
+	const struct dcn10_link_enc_registers *link_regs;
+	const struct dcn10_link_enc_aux_registers *aux_regs;
+	const struct dcn10_link_enc_hpd_registers *hpd_regs;
+	const struct dcn10_link_enc_shift *link_shift;
+	const struct dcn10_link_enc_mask *link_mask;
+};
+
+
+void dcn10_link_encoder_construct(
+	struct dcn10_link_encoder *enc10,
+	const struct encoder_init_data *init_data,
+	const struct encoder_feature_support *enc_features,
+	const struct dcn10_link_enc_registers *link_regs,
+	const struct dcn10_link_enc_aux_registers *aux_regs,
+	const struct dcn10_link_enc_hpd_registers *hpd_regs,
+	const struct dcn10_link_enc_shift *link_shift,
+	const struct dcn10_link_enc_mask *link_mask);
+
+bool dcn10_link_encoder_validate_dvi_output(
+	const struct dcn10_link_encoder *enc10,
+	enum signal_type connector_signal,
+	enum signal_type signal,
+	const struct dc_crtc_timing *crtc_timing);
+
+bool dcn10_link_encoder_validate_rgb_output(
+	const struct dcn10_link_encoder *enc10,
+	const struct dc_crtc_timing *crtc_timing);
+
+bool dcn10_link_encoder_validate_dp_output(
+	const struct dcn10_link_encoder *enc10,
+	const struct dc_crtc_timing *crtc_timing);
+
+bool dcn10_link_encoder_validate_wireless_output(
+	const struct dcn10_link_encoder *enc10,
+	const struct dc_crtc_timing *crtc_timing);
+
+bool dcn10_link_encoder_validate_output_with_stream(
+	struct link_encoder *enc,
+	const struct dc_stream_state *stream);
+
+/****************** HW programming ************************/
+
+/* initialize HW */  /* why do we initialze aux in here? */
+void dcn10_link_encoder_hw_init(struct link_encoder *enc);
+
+void dcn10_link_encoder_destroy(struct link_encoder **enc);
+
+/* program DIG_MODE in DIG_BE */
+/* TODO can this be combined with enable_output? */
+void dcn10_link_encoder_setup(
+	struct link_encoder *enc,
+	enum signal_type signal);
+
+/* enables TMDS PHY output */
+/* TODO: still need depth or just pass in adjusted pixel clock? */
+void dcn10_link_encoder_enable_tmds_output(
+	struct link_encoder *enc,
+	enum clock_source_id clock_source,
+	enum dc_color_depth color_depth,
+	enum signal_type signal,
+	uint32_t pixel_clock);
+
+/* enables DP PHY output */
+void dcn10_link_encoder_enable_dp_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source);
+
+/* enables DP PHY output in MST mode */
+void dcn10_link_encoder_enable_dp_mst_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source);
+
+/* disable PHY output */
+void dcn10_link_encoder_disable_output(
+	struct link_encoder *enc,
+	enum signal_type signal);
+
+/* set DP lane settings */
+void dcn10_link_encoder_dp_set_lane_settings(
+	struct link_encoder *enc,
+	const struct link_training_settings *link_settings);
+
+void dcn10_link_encoder_dp_set_phy_pattern(
+	struct link_encoder *enc,
+	const struct encoder_set_dp_phy_pattern_param *param);
+
+/* programs DP MST VC payload allocation */
+void dcn10_link_encoder_update_mst_stream_allocation_table(
+	struct link_encoder *enc,
+	const struct link_mst_stream_allocation_table *table);
+
+void dcn10_link_encoder_connect_dig_be_to_fe(
+	struct link_encoder *enc,
+	enum engine_id engine,
+	bool connect);
+
+void dcn10_link_encoder_set_dp_phy_pattern_training_pattern(
+	struct link_encoder *enc,
+	uint32_t index);
+
+void dcn10_link_encoder_enable_hpd(struct link_encoder *enc);
+
+void dcn10_link_encoder_disable_hpd(struct link_encoder *enc);
+
+void dcn10_psr_program_dp_dphy_fast_training(struct link_encoder *enc,
+			bool exit_link_training_required);
+
+void dcn10_psr_program_secondary_packet(struct link_encoder *enc,
+			unsigned int sdp_transmit_line_num_deadline);
+
+bool dcn10_is_dig_enabled(struct link_encoder *enc);
+
+#endif /* __DC_LINK_ENCODER__DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 179890b1a8c4..9ca51ae46de7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -65,6 +65,7 @@ static void mpc1_update_blending(
 	int mpcc_id)
 {
 	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+	struct mpcc *mpcc = mpc1_get_mpcc(mpc, mpcc_id);
 
 	REG_UPDATE_5(MPCC_CONTROL[mpcc_id],
 			MPCC_ALPHA_BLND_MODE,		blnd_cfg->alpha_mode,
@@ -74,6 +75,7 @@ static void mpc1_update_blending(
 			MPCC_GLOBAL_GAIN,		blnd_cfg->global_gain);
 
 	mpc1_set_bg_color(mpc, &blnd_cfg->black_color, mpcc_id);
+	mpcc->blnd_cfg = *blnd_cfg;
 }
 
 void mpc1_update_stereo_mix(
@@ -235,8 +237,7 @@ struct mpcc *mpc1_insert_plane(
 	}
 
 	/* update the blending configuration */
-	new_mpcc->blnd_cfg = *blnd_cfg;
-	mpc->funcs->update_blending(mpc, &new_mpcc->blnd_cfg, mpcc_id);
+	mpc->funcs->update_blending(mpc, blnd_cfg, mpcc_id);
 
 	/* update the stereo mix settings, if provided */
 	if (sm_cfg != NULL) {
@@ -409,7 +410,26 @@ void mpc1_init_mpcc_list_from_hw(
 	}
 }
 
+void mpc1_read_mpcc_state(
+		struct mpc *mpc,
+		int mpcc_inst,
+		struct mpcc_state *s)
+{
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+
+	REG_GET(MPCC_OPP_ID[mpcc_inst], MPCC_OPP_ID, &s->opp_id);
+	REG_GET(MPCC_TOP_SEL[mpcc_inst], MPCC_TOP_SEL, &s->dpp_id);
+	REG_GET(MPCC_BOT_SEL[mpcc_inst], MPCC_BOT_SEL, &s->bot_mpcc_id);
+	REG_GET_4(MPCC_CONTROL[mpcc_inst], MPCC_MODE, &s->mode,
+			MPCC_ALPHA_BLND_MODE, &s->alpha_mode,
+			MPCC_ALPHA_MULTIPLIED_MODE, &s->pre_multiplied_alpha,
+			MPCC_BLND_ACTIVE_OVERLAP_ONLY, &s->overlap_only);
+	REG_GET_2(MPCC_STATUS[mpcc_inst], MPCC_IDLE, &s->idle,
+			MPCC_BUSY, &s->busy);
+}
+
 const struct mpc_funcs dcn10_mpc_funcs = {
+	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
 	.mpc_init = mpc1_mpc_init,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
index 267a2995ef6e..d3d16c4cbea3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
@@ -183,4 +183,9 @@ struct mpcc *mpc1_get_mpcc_for_dpp(
 	struct mpc_tree *tree,
 	int dpp_id);
 
+void mpc1_read_mpcc_state(
+		struct mpc *mpc,
+		int mpcc_inst,
+		struct mpcc_state *s);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index 4bf64d1b2c60..f2fbce0e3fc5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -93,6 +93,81 @@ static void optc1_disable_stereo(struct timing_generator *optc)
 		OTG_3D_STRUCTURE_STEREO_SEL_OVR, 0);
 }
 
+static uint32_t get_start_vline(struct timing_generator *optc, const struct dc_crtc_timing *dc_crtc_timing)
+{
+	struct dc_crtc_timing patched_crtc_timing;
+	int vesa_sync_start;
+	int asic_blank_end;
+	int interlace_factor;
+	int vertical_line_start;
+
+	patched_crtc_timing = *dc_crtc_timing;
+	optc1_apply_front_porch_workaround(optc, &patched_crtc_timing);
+
+	vesa_sync_start = patched_crtc_timing.h_addressable +
+			patched_crtc_timing.h_border_right +
+			patched_crtc_timing.h_front_porch;
+
+	asic_blank_end = patched_crtc_timing.h_total -
+			vesa_sync_start -
+			patched_crtc_timing.h_border_left;
+
+	interlace_factor = patched_crtc_timing.flags.INTERLACE ? 2 : 1;
+
+	vesa_sync_start = patched_crtc_timing.v_addressable +
+			patched_crtc_timing.v_border_bottom +
+			patched_crtc_timing.v_front_porch;
+
+	asic_blank_end = (patched_crtc_timing.v_total -
+			vesa_sync_start -
+			patched_crtc_timing.v_border_top)
+			* interlace_factor;
+
+	vertical_line_start = asic_blank_end - optc->dlg_otg_param.vstartup_start + 1;
+	if (vertical_line_start < 0) {
+		ASSERT(0);
+		vertical_line_start = 0;
+	}
+
+	return vertical_line_start;
+}
+
+void optc1_program_vline_interrupt(
+		struct timing_generator *optc,
+		const struct dc_crtc_timing *dc_crtc_timing,
+		unsigned long long vsync_delta)
+{
+
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	unsigned long long req_delta_tens_of_usec = div64_u64((vsync_delta + 9999), 10000);
+	unsigned long long pix_clk_hundreds_khz = div64_u64((dc_crtc_timing->pix_clk_khz + 99), 100);
+	uint32_t req_delta_lines = (uint32_t) div64_u64(
+			(req_delta_tens_of_usec * pix_clk_hundreds_khz + dc_crtc_timing->h_total - 1),
+								dc_crtc_timing->h_total);
+
+	uint32_t vsync_line = get_start_vline(optc, dc_crtc_timing);
+	uint32_t start_line = 0;
+	uint32_t endLine = 0;
+
+	if (req_delta_lines != 0)
+		req_delta_lines--;
+
+	if (req_delta_lines > vsync_line)
+		start_line = dc_crtc_timing->v_total - (req_delta_lines - vsync_line) - 1;
+	else
+		start_line = vsync_line - req_delta_lines;
+
+	endLine = start_line + 2;
+
+	if (endLine >= dc_crtc_timing->v_total)
+		endLine = 2;
+
+	REG_SET_2(OTG_VERTICAL_INTERRUPT0_POSITION, 0,
+			OTG_VERTICAL_INTERRUPT0_LINE_START, start_line,
+			OTG_VERTICAL_INTERRUPT0_LINE_END, endLine);
+}
+
 /**
  * program_timing_generator   used by mode timing set
  * Program CRTC Timing Registers - OTG_H_*, OTG_V_*, Pixel repetition.
@@ -285,7 +360,7 @@ void optc1_program_timing(
 
 }
 
-static void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable)
+void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
@@ -780,17 +855,17 @@ void optc1_set_drr(
 				OTG_SET_V_TOTAL_MIN_MASK_EN, 0,
 				OTG_SET_V_TOTAL_MIN_MASK, 0);
 	} else {
-		REG_SET(OTG_V_TOTAL_MIN, 0,
-			OTG_V_TOTAL_MIN, 0);
-
-		REG_SET(OTG_V_TOTAL_MAX, 0,
-			OTG_V_TOTAL_MAX, 0);
-
 		REG_UPDATE_4(OTG_V_TOTAL_CONTROL,
 				OTG_SET_V_TOTAL_MIN_MASK, 0,
 				OTG_V_TOTAL_MIN_SEL, 0,
 				OTG_V_TOTAL_MAX_SEL, 0,
 				OTG_FORCE_LOCK_ON_EVENT, 0);
+
+		REG_SET(OTG_V_TOTAL_MIN, 0,
+			OTG_V_TOTAL_MIN, 0);
+
+		REG_SET(OTG_V_TOTAL_MAX, 0,
+			OTG_V_TOTAL_MAX, 0);
 	}
 }
 
@@ -1154,6 +1229,12 @@ void optc1_read_otg_state(struct optc *optc1,
 	REG_GET(OTG_V_TOTAL_MIN,
 			OTG_V_TOTAL_MIN, &s->v_total_min);
 
+	REG_GET(OTG_V_TOTAL_CONTROL,
+			OTG_V_TOTAL_MAX_SEL, &s->v_total_max_sel);
+
+	REG_GET(OTG_V_TOTAL_CONTROL,
+			OTG_V_TOTAL_MIN_SEL, &s->v_total_min_sel);
+
 	REG_GET_2(OTG_V_SYNC_A,
 			OTG_V_SYNC_A_START, &s->v_sync_a_start,
 			OTG_V_SYNC_A_END, &s->v_sync_a_end);
@@ -1176,20 +1257,20 @@ void optc1_read_otg_state(struct optc *optc1,
 			OPTC_UNDERFLOW_OCCURRED_STATUS, &s->underflow_occurred_status);
 }
 
-static void optc1_clear_optc_underflow(struct timing_generator *optc)
+void optc1_clear_optc_underflow(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
 	REG_UPDATE(OPTC_INPUT_GLOBAL_CONTROL, OPTC_UNDERFLOW_CLEAR, 1);
 }
 
-static void optc1_tg_init(struct timing_generator *optc)
+void optc1_tg_init(struct timing_generator *optc)
 {
 	optc1_set_blank_data_double_buffer(optc, true);
 	optc1_clear_optc_underflow(optc);
 }
 
-static bool optc1_is_tg_enabled(struct timing_generator *optc)
+bool optc1_is_tg_enabled(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	uint32_t otg_enabled = 0;
@@ -1200,7 +1281,7 @@ static bool optc1_is_tg_enabled(struct timing_generator *optc)
 
 }
 
-static bool optc1_is_optc_underflow_occurred(struct timing_generator *optc)
+bool optc1_is_optc_underflow_occurred(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	uint32_t underflow_occurred = 0;
@@ -1215,6 +1296,7 @@ static bool optc1_is_optc_underflow_occurred(struct timing_generator *optc)
 static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.validate_timing = optc1_validate_timing,
 		.program_timing = optc1_program_timing,
+		.program_vline_interrupt = optc1_program_vline_interrupt,
 		.program_global_sync = optc1_program_global_sync,
 		.enable_crtc = optc1_enable_crtc,
 		.disable_crtc = optc1_disable_crtc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index d25e7bf0d0d7..c62052f46460 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -65,6 +65,8 @@
 	SRI(OTG_NOM_VERT_POSITION, OTG, inst),\
 	SRI(OTG_BLACK_COLOR, OTG, inst),\
 	SRI(OTG_CLOCK_CONTROL, OTG, inst),\
+	SRI(OTG_VERTICAL_INTERRUPT0_CONTROL, OTG, inst),\
+	SRI(OTG_VERTICAL_INTERRUPT0_POSITION, OTG, inst),\
 	SRI(OTG_VERTICAL_INTERRUPT2_CONTROL, OTG, inst),\
 	SRI(OTG_VERTICAL_INTERRUPT2_POSITION, OTG, inst),\
 	SRI(OPTC_INPUT_CLOCK_CONTROL, ODM, inst),\
@@ -124,6 +126,8 @@ struct dcn_optc_registers {
 	uint32_t OTG_TEST_PATTERN_CONTROL;
 	uint32_t OTG_TEST_PATTERN_COLOR;
 	uint32_t OTG_CLOCK_CONTROL;
+	uint32_t OTG_VERTICAL_INTERRUPT0_CONTROL;
+	uint32_t OTG_VERTICAL_INTERRUPT0_POSITION;
 	uint32_t OTG_VERTICAL_INTERRUPT2_CONTROL;
 	uint32_t OTG_VERTICAL_INTERRUPT2_POSITION;
 	uint32_t OPTC_INPUT_CLOCK_CONTROL;
@@ -206,6 +210,9 @@ struct dcn_optc_registers {
 	SF(OTG0_OTG_CLOCK_CONTROL, OTG_CLOCK_EN, mask_sh),\
 	SF(OTG0_OTG_CLOCK_CONTROL, OTG_CLOCK_ON, mask_sh),\
 	SF(OTG0_OTG_CLOCK_CONTROL, OTG_CLOCK_GATE_DIS, mask_sh),\
+	SF(OTG0_OTG_VERTICAL_INTERRUPT0_CONTROL, OTG_VERTICAL_INTERRUPT0_INT_ENABLE, mask_sh),\
+	SF(OTG0_OTG_VERTICAL_INTERRUPT0_POSITION, OTG_VERTICAL_INTERRUPT0_LINE_START, mask_sh),\
+	SF(OTG0_OTG_VERTICAL_INTERRUPT0_POSITION, OTG_VERTICAL_INTERRUPT0_LINE_END, mask_sh),\
 	SF(OTG0_OTG_VERTICAL_INTERRUPT2_CONTROL, OTG_VERTICAL_INTERRUPT2_INT_ENABLE, mask_sh),\
 	SF(OTG0_OTG_VERTICAL_INTERRUPT2_POSITION, OTG_VERTICAL_INTERRUPT2_LINE_START, mask_sh),\
 	SF(ODM0_OPTC_INPUT_CLOCK_CONTROL, OPTC_INPUT_CLK_EN, mask_sh),\
@@ -323,6 +330,9 @@ struct dcn_optc_registers {
 	type OTG_CLOCK_EN;\
 	type OTG_CLOCK_ON;\
 	type OTG_CLOCK_GATE_DIS;\
+	type OTG_VERTICAL_INTERRUPT0_INT_ENABLE;\
+	type OTG_VERTICAL_INTERRUPT0_LINE_START;\
+	type OTG_VERTICAL_INTERRUPT0_LINE_END;\
 	type OTG_VERTICAL_INTERRUPT2_INT_ENABLE;\
 	type OTG_VERTICAL_INTERRUPT2_LINE_START;\
 	type OPTC_INPUT_CLK_EN;\
@@ -396,6 +406,8 @@ struct dcn_otg_state {
 	uint32_t v_total;
 	uint32_t v_total_max;
 	uint32_t v_total_min;
+	uint32_t v_total_min_sel;
+	uint32_t v_total_max_sel;
 	uint32_t v_sync_a_start;
 	uint32_t v_sync_a_end;
 	uint32_t h_blank_start;
@@ -420,6 +432,10 @@ void optc1_program_timing(
 	const struct dc_crtc_timing *dc_crtc_timing,
 	bool use_vbios);
 
+void optc1_program_vline_interrupt(struct timing_generator *optc,
+		const struct dc_crtc_timing *dc_crtc_timing,
+		unsigned long long vsync_delta);
+
 void optc1_program_global_sync(
 		struct timing_generator *optc);
 
@@ -481,4 +497,14 @@ void optc1_program_stereo(struct timing_generator *optc,
 
 bool optc1_is_stereo_left_eye(struct timing_generator *optc);
 
+void optc1_clear_optc_underflow(struct timing_generator *optc);
+
+void optc1_tg_init(struct timing_generator *optc);
+
+bool optc1_is_tg_enabled(struct timing_generator *optc);
+
+bool optc1_is_optc_underflow_occurred(struct timing_generator *optc);
+
+void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable);
+
 #endif /* __DC_TIMING_GENERATOR_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 02bd664aed3e..df5cb2d1d164 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -38,8 +38,8 @@
 #include "dcn10/dcn10_hw_sequencer.h"
 #include "dce110/dce110_hw_sequencer.h"
 #include "dcn10/dcn10_opp.h"
-#include "dce/dce_link_encoder.h"
-#include "dce/dce_stream_encoder.h"
+#include "dcn10/dcn10_link_encoder.h"
+#include "dcn10/dcn10_stream_encoder.h"
 #include "dce/dce_clocks.h"
 #include "dce/dce_clock_source.h"
 #include "dce/dce_audio.h"
@@ -166,36 +166,22 @@ static const struct dce_abm_mask abm_mask = {
 
 #define stream_enc_regs(id)\
 [id] = {\
-	SE_DCN_REG_LIST(id),\
-	.TMDS_CNTL = 0,\
-	.AFMT_AVI_INFO0 = 0,\
-	.AFMT_AVI_INFO1 = 0,\
-	.AFMT_AVI_INFO2 = 0,\
-	.AFMT_AVI_INFO3 = 0,\
+	SE_DCN_REG_LIST(id)\
 }
 
-static const struct dce110_stream_enc_registers stream_enc_regs[] = {
+static const struct dcn10_stream_enc_registers stream_enc_regs[] = {
 	stream_enc_regs(0),
 	stream_enc_regs(1),
 	stream_enc_regs(2),
 	stream_enc_regs(3),
 };
 
-static const struct dce_stream_encoder_shift se_shift = {
+static const struct dcn10_stream_encoder_shift se_shift = {
 		SE_COMMON_MASK_SH_LIST_DCN10(__SHIFT)
 };
 
-static const struct dce_stream_encoder_mask se_mask = {
-		SE_COMMON_MASK_SH_LIST_DCN10(_MASK),
-		.AFMT_GENERIC0_UPDATE = 0,
-		.AFMT_GENERIC2_UPDATE = 0,
-		.DP_DYN_RANGE = 0,
-		.DP_YCBCR_RANGE = 0,
-		.HDMI_AVI_INFO_SEND = 0,
-		.HDMI_AVI_INFO_CONT = 0,
-		.HDMI_AVI_INFO_LINE = 0,
-		.DP_SEC_AVI_ENABLE = 0,
-		.AFMT_AVI_INFO_VERSION = 0
+static const struct dcn10_stream_encoder_mask se_mask = {
+		SE_COMMON_MASK_SH_LIST_DCN10(_MASK)
 };
 
 #define audio_regs(id)\
@@ -228,13 +214,11 @@ static const struct dce_aduio_mask audio_mask = {
 	AUX_REG_LIST(id)\
 }
 
-static const struct dce110_link_enc_aux_registers link_enc_aux_regs[] = {
+static const struct dcn10_link_enc_aux_registers link_enc_aux_regs[] = {
 		aux_regs(0),
 		aux_regs(1),
 		aux_regs(2),
-		aux_regs(3),
-		aux_regs(4),
-		aux_regs(5)
+		aux_regs(3)
 };
 
 #define hpd_regs(id)\
@@ -242,13 +226,11 @@ static const struct dce110_link_enc_aux_registers link_enc_aux_regs[] = {
 	HPD_REG_LIST(id)\
 }
 
-static const struct dce110_link_enc_hpd_registers link_enc_hpd_regs[] = {
+static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = {
 		hpd_regs(0),
 		hpd_regs(1),
 		hpd_regs(2),
-		hpd_regs(3),
-		hpd_regs(4),
-		hpd_regs(5)
+		hpd_regs(3)
 };
 
 #define link_regs(id)\
@@ -257,14 +239,19 @@ static const struct dce110_link_enc_hpd_registers link_enc_hpd_regs[] = {
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \
 }
 
-static const struct dce110_link_enc_registers link_enc_regs[] = {
+static const struct dcn10_link_enc_registers link_enc_regs[] = {
 	link_regs(0),
 	link_regs(1),
 	link_regs(2),
-	link_regs(3),
-	link_regs(4),
-	link_regs(5),
-	link_regs(6),
+	link_regs(3)
+};
+
+static const struct dcn10_link_enc_shift le_shift = {
+		LINK_ENCODER_MASK_SH_LIST_DCN10(__SHIFT)
+};
+
+static const struct dcn10_link_enc_mask le_mask = {
+		LINK_ENCODER_MASK_SH_LIST_DCN10(_MASK)
 };
 
 #define ipp_regs(id)\
@@ -320,11 +307,14 @@ static const struct dcn_dpp_registers tf_regs[] = {
 };
 
 static const struct dcn_dpp_shift tf_shift = {
-	TF_REG_LIST_SH_MASK_DCN10(__SHIFT)
+	TF_REG_LIST_SH_MASK_DCN10(__SHIFT),
+	TF_DEBUG_REG_LIST_SH_DCN10
+
 };
 
 static const struct dcn_dpp_mask tf_mask = {
 	TF_REG_LIST_SH_MASK_DCN10(_MASK),
+	TF_DEBUG_REG_LIST_MASK_DCN10
 };
 
 static const struct dcn_mpc_registers mpc_regs = {
@@ -457,6 +447,8 @@ static const struct dc_debug debug_defaults_drv = {
 		.vsr_support = true,
 		.performance_trace = false,
 		.az_endpoint_mute_only = true,
+		.recovery_enabled = false, /*enable this by default after testing.*/
+		.max_downscale_src_width = 3840,
 };
 
 static const struct dc_debug debug_defaults_diags = {
@@ -592,20 +584,22 @@ static const struct encoder_feature_support link_enc_feature = {
 struct link_encoder *dcn10_link_encoder_create(
 	const struct encoder_init_data *enc_init_data)
 {
-	struct dce110_link_encoder *enc110 =
-		kzalloc(sizeof(struct dce110_link_encoder), GFP_KERNEL);
+	struct dcn10_link_encoder *enc10 =
+		kzalloc(sizeof(struct dcn10_link_encoder), GFP_KERNEL);
 
-	if (!enc110)
+	if (!enc10)
 		return NULL;
 
-	dce110_link_encoder_construct(enc110,
+	dcn10_link_encoder_construct(enc10,
 				      enc_init_data,
 				      &link_enc_feature,
 				      &link_enc_regs[enc_init_data->transmitter],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      &link_enc_hpd_regs[enc_init_data->hpd_source],
+				      &le_shift,
+				      &le_mask);
 
-	return &enc110->base;
+	return &enc10->base;
 }
 
 struct clock_source *dcn10_clock_source_create(
@@ -650,16 +644,16 @@ static struct stream_encoder *dcn10_stream_encoder_create(
 	enum engine_id eng_id,
 	struct dc_context *ctx)
 {
-	struct dce110_stream_encoder *enc110 =
-		kzalloc(sizeof(struct dce110_stream_encoder), GFP_KERNEL);
+	struct dcn10_stream_encoder *enc1 =
+		kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL);
 
-	if (!enc110)
+	if (!enc1)
 		return NULL;
 
-	dce110_stream_encoder_construct(enc110, ctx, ctx->dc_bios, eng_id,
+	dcn10_stream_encoder_construct(enc1, ctx, ctx->dc_bios, eng_id,
 					&stream_enc_regs[eng_id],
 					&se_shift, &se_mask);
-	return &enc110->base;
+	return &enc1->base;
 }
 
 static const struct dce_hwseq_registers hwseq_reg = {
@@ -918,36 +912,6 @@ enum dc_status dcn10_add_stream_to_ctx(
 	return result;
 }
 
-enum dc_status dcn10_validate_guaranteed(
-		struct dc *dc,
-		struct dc_stream_state *dc_stream,
-		struct dc_state *context)
-{
-	enum dc_status result = DC_ERROR_UNEXPECTED;
-
-	context->streams[0] = dc_stream;
-	dc_stream_retain(context->streams[0]);
-	context->stream_count++;
-
-	result = resource_map_pool_resources(dc, context, dc_stream);
-
-	if (result == DC_OK)
-		result = resource_map_phy_clock_resources(dc, context, dc_stream);
-
-	if (result == DC_OK)
-		result = build_mapped_resource(dc, context, dc_stream);
-
-	if (result == DC_OK) {
-		validate_guaranteed_copy_streams(
-				context, dc->caps.max_streams);
-		result = resource_build_scaling_params_for_context(dc, context);
-	}
-	if (result == DC_OK && !dcn_validate_bandwidth(dc, context))
-		return DC_FAIL_BANDWIDTH_VALIDATE;
-
-	return result;
-}
-
 static struct pipe_ctx *dcn10_acquire_idle_pipe_for_layer(
 		struct dc_state *context,
 		const struct resource_pool *pool,
@@ -978,235 +942,16 @@ static struct pipe_ctx *dcn10_acquire_idle_pipe_for_layer(
 	return idle_pipe;
 }
 
-enum dcc_control {
-	dcc_control__256_256_xxx,
-	dcc_control__128_128_xxx,
-	dcc_control__256_64_64,
-};
-
-enum segment_order {
-	segment_order__na,
-	segment_order__contiguous,
-	segment_order__non_contiguous,
-};
-
-static bool dcc_support_pixel_format(
-		enum surface_pixel_format format,
-		unsigned int *bytes_per_element)
-{
-	/* DML: get_bytes_per_element */
-	switch (format) {
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555:
-	case SURFACE_PIXEL_FORMAT_GRPH_RGB565:
-		*bytes_per_element = 2;
-		return true;
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB8888:
-	case SURFACE_PIXEL_FORMAT_GRPH_ABGR8888:
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB2101010:
-	case SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010:
-		*bytes_per_element = 4;
-		return true;
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
-	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
-		*bytes_per_element = 8;
-		return true;
-	default:
-		return false;
-	}
-}
-
-static bool dcc_support_swizzle(
-		enum swizzle_mode_values swizzle,
-		unsigned int bytes_per_element,
-		enum segment_order *segment_order_horz,
-		enum segment_order *segment_order_vert)
-{
-	bool standard_swizzle = false;
-	bool display_swizzle = false;
-
-	switch (swizzle) {
-	case DC_SW_4KB_S:
-	case DC_SW_64KB_S:
-	case DC_SW_VAR_S:
-	case DC_SW_4KB_S_X:
-	case DC_SW_64KB_S_X:
-	case DC_SW_VAR_S_X:
-		standard_swizzle = true;
-		break;
-	case DC_SW_4KB_D:
-	case DC_SW_64KB_D:
-	case DC_SW_VAR_D:
-	case DC_SW_4KB_D_X:
-	case DC_SW_64KB_D_X:
-	case DC_SW_VAR_D_X:
-		display_swizzle = true;
-		break;
-	default:
-		break;
-	}
-
-	if (bytes_per_element == 1 && standard_swizzle) {
-		*segment_order_horz = segment_order__contiguous;
-		*segment_order_vert = segment_order__na;
-		return true;
-	}
-	if (bytes_per_element == 2 && standard_swizzle) {
-		*segment_order_horz = segment_order__non_contiguous;
-		*segment_order_vert = segment_order__contiguous;
-		return true;
-	}
-	if (bytes_per_element == 4 && standard_swizzle) {
-		*segment_order_horz = segment_order__non_contiguous;
-		*segment_order_vert = segment_order__contiguous;
-		return true;
-	}
-	if (bytes_per_element == 8 && standard_swizzle) {
-		*segment_order_horz = segment_order__na;
-		*segment_order_vert = segment_order__contiguous;
-		return true;
-	}
-	if (bytes_per_element == 8 && display_swizzle) {
-		*segment_order_horz = segment_order__contiguous;
-		*segment_order_vert = segment_order__non_contiguous;
-		return true;
-	}
-
-	return false;
-}
-
-static void get_blk256_size(unsigned int *blk256_width, unsigned int *blk256_height,
-		unsigned int bytes_per_element)
-{
-	/* copied from DML.  might want to refactor DML to leverage from DML */
-	/* DML : get_blk256_size */
-	if (bytes_per_element == 1) {
-		*blk256_width = 16;
-		*blk256_height = 16;
-	} else if (bytes_per_element == 2) {
-		*blk256_width = 16;
-		*blk256_height = 8;
-	} else if (bytes_per_element == 4) {
-		*blk256_width = 8;
-		*blk256_height = 8;
-	} else if (bytes_per_element == 8) {
-		*blk256_width = 8;
-		*blk256_height = 4;
-	}
-}
-
-static void det_request_size(
-		unsigned int height,
-		unsigned int width,
-		unsigned int bpe,
-		bool *req128_horz_wc,
-		bool *req128_vert_wc)
-{
-	unsigned int detile_buf_size = 164 * 1024;  /* 164KB for DCN1.0 */
-
-	unsigned int blk256_height = 0;
-	unsigned int blk256_width = 0;
-	unsigned int swath_bytes_horz_wc, swath_bytes_vert_wc;
-
-	get_blk256_size(&blk256_width, &blk256_height, bpe);
-
-	swath_bytes_horz_wc = height * blk256_height * bpe;
-	swath_bytes_vert_wc = width * blk256_width * bpe;
-
-	*req128_horz_wc = (2 * swath_bytes_horz_wc <= detile_buf_size) ?
-			false : /* full 256B request */
-			true; /* half 128b request */
-
-	*req128_vert_wc = (2 * swath_bytes_vert_wc <= detile_buf_size) ?
-			false : /* full 256B request */
-			true; /* half 128b request */
-}
-
-static bool get_dcc_compression_cap(const struct dc *dc,
+static bool dcn10_get_dcc_compression_cap(const struct dc *dc,
 		const struct dc_dcc_surface_param *input,
 		struct dc_surface_dcc_cap *output)
 {
-	/* implement section 1.6.2.1 of DCN1_Programming_Guide.docx */
-	enum dcc_control dcc_control;
-	unsigned int bpe;
-	enum segment_order segment_order_horz, segment_order_vert;
-	bool req128_horz_wc, req128_vert_wc;
-
-	memset(output, 0, sizeof(*output));
-
-	if (dc->debug.disable_dcc == DCC_DISABLE)
-		return false;
-
-	if (!dcc_support_pixel_format(input->format,
-			&bpe))
-		return false;
-
-	if (!dcc_support_swizzle(input->swizzle_mode, bpe,
-			&segment_order_horz, &segment_order_vert))
-		return false;
-
-	det_request_size(input->surface_size.height,  input->surface_size.width,
-			bpe, &req128_horz_wc, &req128_vert_wc);
-
-	if (!req128_horz_wc && !req128_vert_wc) {
-		dcc_control = dcc_control__256_256_xxx;
-	} else if (input->scan == SCAN_DIRECTION_HORIZONTAL) {
-		if (!req128_horz_wc)
-			dcc_control = dcc_control__256_256_xxx;
-		else if (segment_order_horz == segment_order__contiguous)
-			dcc_control = dcc_control__128_128_xxx;
-		else
-			dcc_control = dcc_control__256_64_64;
-	} else if (input->scan == SCAN_DIRECTION_VERTICAL) {
-		if (!req128_vert_wc)
-			dcc_control = dcc_control__256_256_xxx;
-		else if (segment_order_vert == segment_order__contiguous)
-			dcc_control = dcc_control__128_128_xxx;
-		else
-			dcc_control = dcc_control__256_64_64;
-	} else {
-		if ((req128_horz_wc &&
-			segment_order_horz == segment_order__non_contiguous) ||
-			(req128_vert_wc &&
-			segment_order_vert == segment_order__non_contiguous))
-			/* access_dir not known, must use most constraining */
-			dcc_control = dcc_control__256_64_64;
-		else
-			/* reg128 is true for either horz and vert
-			 * but segment_order is contiguous
-			 */
-			dcc_control = dcc_control__128_128_xxx;
-	}
-
-	if (dc->debug.disable_dcc == DCC_HALF_REQ_DISALBE &&
-		dcc_control != dcc_control__256_256_xxx)
-		return false;
-
-	switch (dcc_control) {
-	case dcc_control__256_256_xxx:
-		output->grph.rgb.max_uncompressed_blk_size = 256;
-		output->grph.rgb.max_compressed_blk_size = 256;
-		output->grph.rgb.independent_64b_blks = false;
-		break;
-	case dcc_control__128_128_xxx:
-		output->grph.rgb.max_uncompressed_blk_size = 128;
-		output->grph.rgb.max_compressed_blk_size = 128;
-		output->grph.rgb.independent_64b_blks = false;
-		break;
-	case dcc_control__256_64_64:
-		output->grph.rgb.max_uncompressed_blk_size = 256;
-		output->grph.rgb.max_compressed_blk_size = 64;
-		output->grph.rgb.independent_64b_blks = true;
-		break;
-	}
-
-	output->capable = true;
-	output->const_color_support = false;
-
-	return true;
+	return dc->res_pool->hubbub->funcs->get_dcc_compression_cap(
+			dc->res_pool->hubbub,
+			input,
+			output);
 }
 
-
 static void dcn10_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dcn10_resource_pool *dcn10_pool = TO_DCN10_RES_POOL(*pool);
@@ -1227,13 +972,12 @@ static enum dc_status dcn10_validate_plane(const struct dc_plane_state *plane_st
 }
 
 static struct dc_cap_funcs cap_funcs = {
-	.get_dcc_compression_cap = get_dcc_compression_cap
+	.get_dcc_compression_cap = dcn10_get_dcc_compression_cap
 };
 
 static struct resource_funcs dcn10_res_pool_funcs = {
 	.destroy = dcn10_destroy_resource_pool,
 	.link_enc_create = dcn10_link_encoder_create,
-	.validate_guaranteed = dcn10_validate_guaranteed,
 	.validate_bandwidth = dcn_validate_bandwidth,
 	.acquire_idle_pipe_for_layer = dcn10_acquire_idle_pipe_for_layer,
 	.validate_plane = dcn10_validate_plane,
@@ -1282,6 +1026,7 @@ static bool construct(
 	dc->caps.max_cursor_size = 256;
 	dc->caps.max_slave_planes = 1;
 	dc->caps.is_apu = true;
+	dc->caps.post_blend_color_processing = false;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
new file mode 100644
index 000000000000..653b7b2efe2e
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -0,0 +1,1490 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ *  and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+
+#include "dc_bios_types.h"
+#include "dcn10_stream_encoder.h"
+#include "reg_helper.h"
+#include "hw_shared.h"
+
+#define DC_LOGGER \
+		enc1->base.ctx->logger
+
+
+#define REG(reg)\
+	(enc1->regs->reg)
+
+#undef FN
+#define FN(reg_name, field_name) \
+	enc1->se_shift->field_name, enc1->se_mask->field_name
+
+#define VBI_LINE_0 0
+#define DP_BLANK_MAX_RETRY 20
+#define HDMI_CLOCK_CHANNEL_RATE_MORE_340M 340000
+
+
+enum {
+	DP_MST_UPDATE_MAX_RETRY = 50
+};
+
+#define CTX \
+	enc1->base.ctx
+
+void enc1_update_generic_info_packet(
+	struct dcn10_stream_encoder *enc1,
+	uint32_t packet_index,
+	const struct dc_info_packet *info_packet)
+{
+	uint32_t regval;
+	/* TODOFPGA Figure out a proper number for max_retries polling for lock
+	 * use 50 for now.
+	 */
+	uint32_t max_retries = 50;
+
+	/*we need turn on clock before programming AFMT block*/
+	REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, 1);
+
+	if (packet_index >= 8)
+		ASSERT(0);
+
+	/* poll dig_update_lock is not locked -> asic internal signal
+	 * assume otg master lock will unlock it
+	 */
+/*		REG_WAIT(AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_LOCK_STATUS,
+			0, 10, max_retries);*/
+
+	/* check if HW reading GSP memory */
+	REG_WAIT(AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_CONFLICT,
+			0, 10, max_retries);
+
+	/* HW does is not reading GSP memory not reading too long ->
+	 * something wrong. clear GPS memory access and notify?
+	 * hw SW is writing to GSP memory
+	 */
+	REG_UPDATE(AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_CONFLICT_CLR, 1);
+
+	/* choose which generic packet to use */
+	regval = REG_READ(AFMT_VBI_PACKET_CONTROL);
+	REG_UPDATE(AFMT_VBI_PACKET_CONTROL,
+			AFMT_GENERIC_INDEX, packet_index);
+
+	/* write generic packet header
+	 * (4th byte is for GENERIC0 only)
+	 */
+	REG_SET_4(AFMT_GENERIC_HDR, 0,
+			AFMT_GENERIC_HB0, info_packet->hb0,
+			AFMT_GENERIC_HB1, info_packet->hb1,
+			AFMT_GENERIC_HB2, info_packet->hb2,
+			AFMT_GENERIC_HB3, info_packet->hb3);
+
+	/* write generic packet contents
+	 * (we never use last 4 bytes)
+	 * there are 8 (0-7) mmDIG0_AFMT_GENERIC0_x registers
+	 */
+	{
+		const uint32_t *content =
+			(const uint32_t *) &info_packet->sb[0];
+
+		REG_WRITE(AFMT_GENERIC_0, *content++);
+		REG_WRITE(AFMT_GENERIC_1, *content++);
+		REG_WRITE(AFMT_GENERIC_2, *content++);
+		REG_WRITE(AFMT_GENERIC_3, *content++);
+		REG_WRITE(AFMT_GENERIC_4, *content++);
+		REG_WRITE(AFMT_GENERIC_5, *content++);
+		REG_WRITE(AFMT_GENERIC_6, *content++);
+		REG_WRITE(AFMT_GENERIC_7, *content);
+	}
+
+	switch (packet_index) {
+	case 0:
+		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
+				AFMT_GENERIC0_FRAME_UPDATE, 1);
+		break;
+	case 1:
+		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
+				AFMT_GENERIC1_FRAME_UPDATE, 1);
+		break;
+	case 2:
+		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
+				AFMT_GENERIC2_FRAME_UPDATE, 1);
+		break;
+	case 3:
+		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
+				AFMT_GENERIC3_FRAME_UPDATE, 1);
+		break;
+	case 4:
+		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
+				AFMT_GENERIC4_FRAME_UPDATE, 1);
+		break;
+	case 5:
+		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
+				AFMT_GENERIC5_FRAME_UPDATE, 1);
+		break;
+	case 6:
+		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
+				AFMT_GENERIC6_FRAME_UPDATE, 1);
+		break;
+	case 7:
+		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
+				AFMT_GENERIC7_FRAME_UPDATE, 1);
+		break;
+	default:
+		break;
+	}
+}
+
+static void enc1_update_hdmi_info_packet(
+	struct dcn10_stream_encoder *enc1,
+	uint32_t packet_index,
+	const struct dc_info_packet *info_packet)
+{
+	uint32_t cont, send, line;
+
+	if (info_packet->valid) {
+		enc1_update_generic_info_packet(
+			enc1,
+			packet_index,
+			info_packet);
+
+		/* enable transmission of packet(s) -
+		 * packet transmission begins on the next frame
+		 */
+		cont = 1;
+		/* send packet(s) every frame */
+		send = 1;
+		/* select line number to send packets on */
+		line = 2;
+	} else {
+		cont = 0;
+		send = 0;
+		line = 0;
+	}
+
+	/* choose which generic packet control to use */
+	switch (packet_index) {
+	case 0:
+		REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL0,
+				HDMI_GENERIC0_CONT, cont,
+				HDMI_GENERIC0_SEND, send,
+				HDMI_GENERIC0_LINE, line);
+		break;
+	case 1:
+		REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL0,
+				HDMI_GENERIC1_CONT, cont,
+				HDMI_GENERIC1_SEND, send,
+				HDMI_GENERIC1_LINE, line);
+		break;
+	case 2:
+		REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL1,
+				HDMI_GENERIC0_CONT, cont,
+				HDMI_GENERIC0_SEND, send,
+				HDMI_GENERIC0_LINE, line);
+		break;
+	case 3:
+		REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL1,
+				HDMI_GENERIC1_CONT, cont,
+				HDMI_GENERIC1_SEND, send,
+				HDMI_GENERIC1_LINE, line);
+		break;
+	case 4:
+		REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL2,
+				HDMI_GENERIC0_CONT, cont,
+				HDMI_GENERIC0_SEND, send,
+				HDMI_GENERIC0_LINE, line);
+		break;
+	case 5:
+		REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL2,
+				HDMI_GENERIC1_CONT, cont,
+				HDMI_GENERIC1_SEND, send,
+				HDMI_GENERIC1_LINE, line);
+		break;
+	case 6:
+		REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL3,
+				HDMI_GENERIC0_CONT, cont,
+				HDMI_GENERIC0_SEND, send,
+				HDMI_GENERIC0_LINE, line);
+		break;
+	case 7:
+		REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL3,
+				HDMI_GENERIC1_CONT, cont,
+				HDMI_GENERIC1_SEND, send,
+				HDMI_GENERIC1_LINE, line);
+		break;
+	default:
+		/* invalid HW packet index */
+		DC_LOG_WARNING(
+			"Invalid HW packet index: %s()\n",
+			__func__);
+		return;
+	}
+}
+
+/* setup stream encoder in dp mode */
+void enc1_stream_encoder_dp_set_stream_attribute(
+	struct stream_encoder *enc,
+	struct dc_crtc_timing *crtc_timing,
+	enum dc_color_space output_color_space)
+{
+	uint32_t h_active_start;
+	uint32_t v_active_start;
+	uint32_t misc0 = 0;
+	uint32_t misc1 = 0;
+	uint32_t h_blank;
+	uint32_t h_back_porch;
+	uint8_t synchronous_clock = 0; /* asynchronous mode */
+	uint8_t colorimetry_bpc;
+	uint8_t dynamic_range_rgb = 0; /*full range*/
+	uint8_t dynamic_range_ycbcr = 1; /*bt709*/
+
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	REG_UPDATE(DP_DB_CNTL, DP_DB_DISABLE, 1);
+
+	/* set pixel encoding */
+	switch (crtc_timing->pixel_encoding) {
+	case PIXEL_ENCODING_YCBCR422:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
+				DP_PIXEL_ENCODING_TYPE_YCBCR422);
+		break;
+	case PIXEL_ENCODING_YCBCR444:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
+				DP_PIXEL_ENCODING_TYPE_YCBCR444);
+
+		if (crtc_timing->flags.Y_ONLY)
+			if (crtc_timing->display_color_depth != COLOR_DEPTH_666)
+				/* HW testing only, no use case yet.
+				 * Color depth of Y-only could be
+				 * 8, 10, 12, 16 bits
+				 */
+				REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
+						DP_PIXEL_ENCODING_TYPE_Y_ONLY);
+		/* Note: DP_MSA_MISC1 bit 7 is the indicator
+		 * of Y-only mode.
+		 * This bit is set in HW if register
+		 * DP_PIXEL_ENCODING is programmed to 0x4
+		 */
+		break;
+	case PIXEL_ENCODING_YCBCR420:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
+				DP_PIXEL_ENCODING_TYPE_YCBCR420);
+		REG_UPDATE(DP_VID_TIMING, DP_VID_N_MUL, 1);
+		break;
+	default:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
+				DP_PIXEL_ENCODING_TYPE_RGB444);
+		break;
+	}
+
+	misc1 = REG_READ(DP_MSA_MISC);
+
+	/* set color depth */
+
+	switch (crtc_timing->display_color_depth) {
+	case COLOR_DEPTH_666:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
+				0);
+		break;
+	case COLOR_DEPTH_888:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
+				DP_COMPONENT_PIXEL_DEPTH_8BPC);
+		break;
+	case COLOR_DEPTH_101010:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
+				DP_COMPONENT_PIXEL_DEPTH_10BPC);
+
+		break;
+	case COLOR_DEPTH_121212:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
+				DP_COMPONENT_PIXEL_DEPTH_12BPC);
+		break;
+	default:
+		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
+				DP_COMPONENT_PIXEL_DEPTH_6BPC);
+		break;
+	}
+
+	/* set dynamic range and YCbCr range */
+
+	switch (crtc_timing->display_color_depth) {
+	case COLOR_DEPTH_666:
+		colorimetry_bpc = 0;
+		break;
+	case COLOR_DEPTH_888:
+		colorimetry_bpc = 1;
+		break;
+	case COLOR_DEPTH_101010:
+		colorimetry_bpc = 2;
+		break;
+	case COLOR_DEPTH_121212:
+		colorimetry_bpc = 3;
+		break;
+	default:
+		colorimetry_bpc = 0;
+		break;
+	}
+
+	misc0 = misc0 | synchronous_clock;
+	misc0 = colorimetry_bpc << 5;
+
+	switch (output_color_space) {
+	case COLOR_SPACE_SRGB:
+		misc0 = misc0 | 0x0;
+		misc1 = misc1 & ~0x80; /* bit7 = 0*/
+		dynamic_range_rgb = 0; /*full range*/
+		break;
+	case COLOR_SPACE_SRGB_LIMITED:
+		misc0 = misc0 | 0x8; /* bit3=1 */
+		misc1 = misc1 & ~0x80; /* bit7 = 0*/
+		dynamic_range_rgb = 1; /*limited range*/
+		break;
+	case COLOR_SPACE_YCBCR601:
+	case COLOR_SPACE_YCBCR601_LIMITED:
+		misc0 = misc0 | 0x8; /* bit3=1, bit4=0 */
+		misc1 = misc1 & ~0x80; /* bit7 = 0*/
+		dynamic_range_ycbcr = 0; /*bt601*/
+		if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
+			misc0 = misc0 | 0x2; /* bit2=0, bit1=1 */
+		else if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR444)
+			misc0 = misc0 | 0x4; /* bit2=1, bit1=0 */
+		break;
+	case COLOR_SPACE_YCBCR709:
+	case COLOR_SPACE_YCBCR709_LIMITED:
+		misc0 = misc0 | 0x18; /* bit3=1, bit4=1 */
+		misc1 = misc1 & ~0x80; /* bit7 = 0*/
+		dynamic_range_ycbcr = 1; /*bt709*/
+		if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
+			misc0 = misc0 | 0x2; /* bit2=0, bit1=1 */
+		else if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR444)
+			misc0 = misc0 | 0x4; /* bit2=1, bit1=0 */
+		break;
+	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
+		dynamic_range_rgb = 1; /*limited range*/
+		break;
+	case COLOR_SPACE_2020_RGB_FULLRANGE:
+	case COLOR_SPACE_2020_YCBCR:
+	case COLOR_SPACE_XR_RGB:
+	case COLOR_SPACE_MSREF_SCRGB:
+	case COLOR_SPACE_ADOBERGB:
+	case COLOR_SPACE_DCIP3:
+	case COLOR_SPACE_XV_YCC_709:
+	case COLOR_SPACE_XV_YCC_601:
+	case COLOR_SPACE_DISPLAYNATIVE:
+	case COLOR_SPACE_DOLBYVISION:
+	case COLOR_SPACE_APPCTRL:
+	case COLOR_SPACE_CUSTOMPOINTS:
+	case COLOR_SPACE_UNKNOWN:
+		/* do nothing */
+		break;
+	}
+
+	REG_SET(DP_MSA_COLORIMETRY, 0, DP_MSA_MISC0, misc0);
+	REG_WRITE(DP_MSA_MISC, misc1);   /* MSA_MISC1 */
+
+	/* dcn new register
+	 * dc_crtc_timing is vesa dmt struct. data from edid
+	 */
+	REG_SET_2(DP_MSA_TIMING_PARAM1, 0,
+			DP_MSA_HTOTAL, crtc_timing->h_total,
+			DP_MSA_VTOTAL, crtc_timing->v_total);
+
+	/* calculate from vesa timing parameters
+	 * h_active_start related to leading edge of sync
+	 */
+
+	h_blank = crtc_timing->h_total - crtc_timing->h_border_left -
+			crtc_timing->h_addressable - crtc_timing->h_border_right;
+
+	h_back_porch = h_blank - crtc_timing->h_front_porch -
+			crtc_timing->h_sync_width;
+
+	/* start at beginning of left border */
+	h_active_start = crtc_timing->h_sync_width + h_back_porch;
+
+
+	v_active_start = crtc_timing->v_total - crtc_timing->v_border_top -
+			crtc_timing->v_addressable - crtc_timing->v_border_bottom -
+			crtc_timing->v_front_porch;
+
+
+	/* start at beginning of left border */
+	REG_SET_2(DP_MSA_TIMING_PARAM2, 0,
+		DP_MSA_HSTART, h_active_start,
+		DP_MSA_VSTART, v_active_start);
+
+	REG_SET_4(DP_MSA_TIMING_PARAM3, 0,
+			DP_MSA_HSYNCWIDTH,
+			crtc_timing->h_sync_width,
+			DP_MSA_HSYNCPOLARITY,
+			!crtc_timing->flags.HSYNC_POSITIVE_POLARITY,
+			DP_MSA_VSYNCWIDTH,
+			crtc_timing->v_sync_width,
+			DP_MSA_VSYNCPOLARITY,
+			!crtc_timing->flags.VSYNC_POSITIVE_POLARITY);
+
+	/* HWDITH include border or overscan */
+	REG_SET_2(DP_MSA_TIMING_PARAM4, 0,
+		DP_MSA_HWIDTH, crtc_timing->h_border_left +
+		crtc_timing->h_addressable + crtc_timing->h_border_right,
+		DP_MSA_VHEIGHT, crtc_timing->v_border_top +
+		crtc_timing->v_addressable + crtc_timing->v_border_bottom);
+}
+
+static void enc1_stream_encoder_set_stream_attribute_helper(
+		struct dcn10_stream_encoder *enc1,
+		struct dc_crtc_timing *crtc_timing)
+{
+	switch (crtc_timing->pixel_encoding) {
+	case PIXEL_ENCODING_YCBCR422:
+		REG_UPDATE(DIG_FE_CNTL, TMDS_PIXEL_ENCODING, 1);
+		break;
+	default:
+		REG_UPDATE(DIG_FE_CNTL, TMDS_PIXEL_ENCODING, 0);
+		break;
+	}
+	REG_UPDATE(DIG_FE_CNTL, TMDS_COLOR_FORMAT, 0);
+}
+
+/* setup stream encoder in hdmi mode */
+void enc1_stream_encoder_hdmi_set_stream_attribute(
+	struct stream_encoder *enc,
+	struct dc_crtc_timing *crtc_timing,
+	int actual_pix_clk_khz,
+	bool enable_audio)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	struct bp_encoder_control cntl = {0};
+
+	cntl.action = ENCODER_CONTROL_SETUP;
+	cntl.engine_id = enc1->base.id;
+	cntl.signal = SIGNAL_TYPE_HDMI_TYPE_A;
+	cntl.enable_dp_audio = enable_audio;
+	cntl.pixel_clock = actual_pix_clk_khz;
+	cntl.lanes_number = LANE_COUNT_FOUR;
+
+	if (enc1->base.bp->funcs->encoder_control(
+			enc1->base.bp, &cntl) != BP_RESULT_OK)
+		return;
+
+	enc1_stream_encoder_set_stream_attribute_helper(enc1, crtc_timing);
+
+	/* setup HDMI engine */
+	REG_UPDATE_5(HDMI_CONTROL,
+		HDMI_PACKET_GEN_VERSION, 1,
+		HDMI_KEEPOUT_MODE, 1,
+		HDMI_DEEP_COLOR_ENABLE, 0,
+		HDMI_DATA_SCRAMBLE_EN, 0,
+		HDMI_CLOCK_CHANNEL_RATE, 0);
+
+
+	switch (crtc_timing->display_color_depth) {
+	case COLOR_DEPTH_888:
+		REG_UPDATE(HDMI_CONTROL, HDMI_DEEP_COLOR_DEPTH, 0);
+		break;
+	case COLOR_DEPTH_101010:
+		if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR422) {
+			REG_UPDATE_2(HDMI_CONTROL,
+					HDMI_DEEP_COLOR_DEPTH, 1,
+					HDMI_DEEP_COLOR_ENABLE, 0);
+		} else {
+			REG_UPDATE_2(HDMI_CONTROL,
+					HDMI_DEEP_COLOR_DEPTH, 1,
+					HDMI_DEEP_COLOR_ENABLE, 1);
+			}
+		break;
+	case COLOR_DEPTH_121212:
+		if (crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR422) {
+			REG_UPDATE_2(HDMI_CONTROL,
+					HDMI_DEEP_COLOR_DEPTH, 2,
+					HDMI_DEEP_COLOR_ENABLE, 0);
+		} else {
+			REG_UPDATE_2(HDMI_CONTROL,
+					HDMI_DEEP_COLOR_DEPTH, 2,
+					HDMI_DEEP_COLOR_ENABLE, 1);
+			}
+		break;
+	case COLOR_DEPTH_161616:
+		REG_UPDATE_2(HDMI_CONTROL,
+				HDMI_DEEP_COLOR_DEPTH, 3,
+				HDMI_DEEP_COLOR_ENABLE, 1);
+		break;
+	default:
+		break;
+	}
+
+	if (actual_pix_clk_khz >= HDMI_CLOCK_CHANNEL_RATE_MORE_340M) {
+		/* enable HDMI data scrambler
+		 * HDMI_CLOCK_CHANNEL_RATE_MORE_340M
+		 * Clock channel frequency is 1/4 of character rate.
+		 */
+		REG_UPDATE_2(HDMI_CONTROL,
+			HDMI_DATA_SCRAMBLE_EN, 1,
+			HDMI_CLOCK_CHANNEL_RATE, 1);
+	} else if (crtc_timing->flags.LTE_340MCSC_SCRAMBLE) {
+
+		/* TODO: New feature for DCE11, still need to implement */
+
+		/* enable HDMI data scrambler
+		 * HDMI_CLOCK_CHANNEL_FREQ_EQUAL_TO_CHAR_RATE
+		 * Clock channel frequency is the same
+		 * as character rate
+		 */
+		REG_UPDATE_2(HDMI_CONTROL,
+			HDMI_DATA_SCRAMBLE_EN, 1,
+			HDMI_CLOCK_CHANNEL_RATE, 0);
+	}
+
+
+	REG_UPDATE_3(HDMI_VBI_PACKET_CONTROL,
+		HDMI_GC_CONT, 1,
+		HDMI_GC_SEND, 1,
+		HDMI_NULL_SEND, 1);
+
+	/* following belongs to audio */
+	REG_UPDATE(HDMI_INFOFRAME_CONTROL0, HDMI_AUDIO_INFO_SEND, 1);
+
+	REG_UPDATE(AFMT_INFOFRAME_CONTROL0, AFMT_AUDIO_INFO_UPDATE, 1);
+
+	REG_UPDATE(HDMI_INFOFRAME_CONTROL1, HDMI_AUDIO_INFO_LINE,
+				VBI_LINE_0 + 2);
+
+	REG_UPDATE(HDMI_GC, HDMI_GC_AVMUTE, 0);
+}
+
+/* setup stream encoder in dvi mode */
+void enc1_stream_encoder_dvi_set_stream_attribute(
+	struct stream_encoder *enc,
+	struct dc_crtc_timing *crtc_timing,
+	bool is_dual_link)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	struct bp_encoder_control cntl = {0};
+
+	cntl.action = ENCODER_CONTROL_SETUP;
+	cntl.engine_id = enc1->base.id;
+	cntl.signal = is_dual_link ?
+			SIGNAL_TYPE_DVI_DUAL_LINK : SIGNAL_TYPE_DVI_SINGLE_LINK;
+	cntl.enable_dp_audio = false;
+	cntl.pixel_clock = crtc_timing->pix_clk_khz;
+	cntl.lanes_number = (is_dual_link) ? LANE_COUNT_EIGHT : LANE_COUNT_FOUR;
+
+	if (enc1->base.bp->funcs->encoder_control(
+			enc1->base.bp, &cntl) != BP_RESULT_OK)
+		return;
+
+	ASSERT(crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB);
+	ASSERT(crtc_timing->display_color_depth == COLOR_DEPTH_888);
+	enc1_stream_encoder_set_stream_attribute_helper(enc1, crtc_timing);
+}
+
+void enc1_stream_encoder_set_mst_bandwidth(
+	struct stream_encoder *enc,
+	struct fixed31_32 avg_time_slots_per_mtp)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	uint32_t x = dc_fixpt_floor(
+		avg_time_slots_per_mtp);
+	uint32_t y = dc_fixpt_ceil(
+		dc_fixpt_shl(
+			dc_fixpt_sub_int(
+				avg_time_slots_per_mtp,
+				x),
+			26));
+
+	REG_SET_2(DP_MSE_RATE_CNTL, 0,
+		DP_MSE_RATE_X, x,
+		DP_MSE_RATE_Y, y);
+
+	/* wait for update to be completed on the link */
+	/* i.e. DP_MSE_RATE_UPDATE_PENDING field (read only) */
+	/* is reset to 0 (not pending) */
+	REG_WAIT(DP_MSE_RATE_UPDATE, DP_MSE_RATE_UPDATE_PENDING,
+			0,
+			10, DP_MST_UPDATE_MAX_RETRY);
+}
+
+static void enc1_stream_encoder_update_hdmi_info_packets(
+	struct stream_encoder *enc,
+	const struct encoder_info_frame *info_frame)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	/* for bring up, disable dp double  TODO */
+	REG_UPDATE(HDMI_DB_CONTROL, HDMI_DB_DISABLE, 1);
+
+	enc1_update_hdmi_info_packet(enc1, 0, &info_frame->avi);
+	enc1_update_hdmi_info_packet(enc1, 1, &info_frame->vendor);
+	enc1_update_hdmi_info_packet(enc1, 2, &info_frame->gamut);
+	enc1_update_hdmi_info_packet(enc1, 3, &info_frame->spd);
+	enc1_update_hdmi_info_packet(enc1, 4, &info_frame->hdrsmd);
+}
+
+static void enc1_stream_encoder_stop_hdmi_info_packets(
+	struct stream_encoder *enc)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	/* stop generic packets 0 & 1 on HDMI */
+	REG_SET_6(HDMI_GENERIC_PACKET_CONTROL0, 0,
+		HDMI_GENERIC1_CONT, 0,
+		HDMI_GENERIC1_LINE, 0,
+		HDMI_GENERIC1_SEND, 0,
+		HDMI_GENERIC0_CONT, 0,
+		HDMI_GENERIC0_LINE, 0,
+		HDMI_GENERIC0_SEND, 0);
+
+	/* stop generic packets 2 & 3 on HDMI */
+	REG_SET_6(HDMI_GENERIC_PACKET_CONTROL1, 0,
+		HDMI_GENERIC0_CONT, 0,
+		HDMI_GENERIC0_LINE, 0,
+		HDMI_GENERIC0_SEND, 0,
+		HDMI_GENERIC1_CONT, 0,
+		HDMI_GENERIC1_LINE, 0,
+		HDMI_GENERIC1_SEND, 0);
+
+	/* stop generic packets 2 & 3 on HDMI */
+	REG_SET_6(HDMI_GENERIC_PACKET_CONTROL2, 0,
+		HDMI_GENERIC0_CONT, 0,
+		HDMI_GENERIC0_LINE, 0,
+		HDMI_GENERIC0_SEND, 0,
+		HDMI_GENERIC1_CONT, 0,
+		HDMI_GENERIC1_LINE, 0,
+		HDMI_GENERIC1_SEND, 0);
+
+	REG_SET_6(HDMI_GENERIC_PACKET_CONTROL3, 0,
+		HDMI_GENERIC0_CONT, 0,
+		HDMI_GENERIC0_LINE, 0,
+		HDMI_GENERIC0_SEND, 0,
+		HDMI_GENERIC1_CONT, 0,
+		HDMI_GENERIC1_LINE, 0,
+		HDMI_GENERIC1_SEND, 0);
+}
+
+void enc1_stream_encoder_update_dp_info_packets(
+	struct stream_encoder *enc,
+	const struct encoder_info_frame *info_frame)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	uint32_t value = 0;
+
+	if (info_frame->vsc.valid)
+		enc1_update_generic_info_packet(
+					enc1,
+					0,  /* packetIndex */
+					&info_frame->vsc);
+
+	if (info_frame->spd.valid)
+		enc1_update_generic_info_packet(
+				enc1,
+				2,  /* packetIndex */
+				&info_frame->spd);
+
+	if (info_frame->hdrsmd.valid)
+		enc1_update_generic_info_packet(
+				enc1,
+				3,  /* packetIndex */
+				&info_frame->hdrsmd);
+
+	/* enable/disable transmission of packet(s).
+	 * If enabled, packet transmission begins on the next frame
+	 */
+	REG_UPDATE(DP_SEC_CNTL, DP_SEC_GSP0_ENABLE, info_frame->vsc.valid);
+	REG_UPDATE(DP_SEC_CNTL, DP_SEC_GSP2_ENABLE, info_frame->spd.valid);
+	REG_UPDATE(DP_SEC_CNTL, DP_SEC_GSP3_ENABLE, info_frame->hdrsmd.valid);
+
+
+	/* This bit is the master enable bit.
+	 * When enabling secondary stream engine,
+	 * this master bit must also be set.
+	 * This register shared with audio info frame.
+	 * Therefore we need to enable master bit
+	 * if at least on of the fields is not 0
+	 */
+	value = REG_READ(DP_SEC_CNTL);
+	if (value)
+		REG_UPDATE(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, 1);
+}
+
+void enc1_stream_encoder_stop_dp_info_packets(
+	struct stream_encoder *enc)
+{
+	/* stop generic packets on DP */
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	uint32_t value = 0;
+
+	REG_SET_10(DP_SEC_CNTL, 0,
+		DP_SEC_GSP0_ENABLE, 0,
+		DP_SEC_GSP1_ENABLE, 0,
+		DP_SEC_GSP2_ENABLE, 0,
+		DP_SEC_GSP3_ENABLE, 0,
+		DP_SEC_GSP4_ENABLE, 0,
+		DP_SEC_GSP5_ENABLE, 0,
+		DP_SEC_GSP6_ENABLE, 0,
+		DP_SEC_GSP7_ENABLE, 0,
+		DP_SEC_MPG_ENABLE, 0,
+		DP_SEC_STREAM_ENABLE, 0);
+
+	/* this register shared with audio info frame.
+	 * therefore we need to keep master enabled
+	 * if at least one of the fields is not 0 */
+	value = REG_READ(DP_SEC_CNTL);
+	if (value)
+		REG_UPDATE(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, 1);
+
+}
+
+void enc1_stream_encoder_dp_blank(
+	struct stream_encoder *enc)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	uint32_t retries = 0;
+	uint32_t  reg1 = 0;
+	uint32_t max_retries = DP_BLANK_MAX_RETRY * 10;
+
+	/* Note: For CZ, we are changing driver default to disable
+	 * stream deferred to next VBLANK. If results are positive, we
+	 * will make the same change to all DCE versions. There are a
+	 * handful of panels that cannot handle disable stream at
+	 * HBLANK and will result in a white line flash across the
+	 * screen on stream disable.
+	 */
+	REG_GET(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, &reg1);
+	if ((reg1 & 0x1) == 0)
+		/*stream not enabled*/
+		return;
+	/* Specify the video stream disable point
+	 * (2 = start of the next vertical blank)
+	 */
+	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_DIS_DEFER, 2);
+	/* Larger delay to wait until VBLANK - use max retry of
+	 * 10us*3000=30ms. This covers 16.6ms of typical 60 Hz mode +
+	 * a little more because we may not trust delay accuracy.
+	 */
+	max_retries = DP_BLANK_MAX_RETRY * 150;
+
+	/* disable DP stream */
+	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, 0);
+
+	/* the encoder stops sending the video stream
+	 * at the start of the vertical blanking.
+	 * Poll for DP_VID_STREAM_STATUS == 0
+	 */
+
+	REG_WAIT(DP_VID_STREAM_CNTL, DP_VID_STREAM_STATUS,
+			0,
+			10, max_retries);
+
+	ASSERT(retries <= max_retries);
+
+	/* Tell the DP encoder to ignore timing from CRTC, must be done after
+	 * the polling. If we set DP_STEER_FIFO_RESET before DP stream blank is
+	 * complete, stream status will be stuck in video stream enabled state,
+	 * i.e. DP_VID_STREAM_STATUS stuck at 1.
+	 */
+
+	REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, true);
+}
+
+/* output video stream to link encoder */
+void enc1_stream_encoder_dp_unblank(
+	struct stream_encoder *enc,
+	const struct encoder_unblank_param *param)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	if (param->link_settings.link_rate != LINK_RATE_UNKNOWN) {
+		uint32_t n_vid = 0x8000;
+		uint32_t m_vid;
+
+		/* M / N = Fstream / Flink
+		 * m_vid / n_vid = pixel rate / link rate
+		 */
+
+		uint64_t m_vid_l = n_vid;
+
+		m_vid_l *= param->pixel_clk_khz;
+		m_vid_l = div_u64(m_vid_l,
+			param->link_settings.link_rate
+				* LINK_RATE_REF_FREQ_IN_KHZ);
+
+		m_vid = (uint32_t) m_vid_l;
+
+		/* enable auto measurement */
+
+		REG_UPDATE(DP_VID_TIMING, DP_VID_M_N_GEN_EN, 0);
+
+		/* auto measurement need 1 full 0x8000 symbol cycle to kick in,
+		 * therefore program initial value for Mvid and Nvid
+		 */
+
+		REG_UPDATE(DP_VID_N, DP_VID_N, n_vid);
+
+		REG_UPDATE(DP_VID_M, DP_VID_M, m_vid);
+
+		REG_UPDATE(DP_VID_TIMING, DP_VID_M_N_GEN_EN, 1);
+	}
+
+	/* set DIG_START to 0x1 to resync FIFO */
+
+	REG_UPDATE(DIG_FE_CNTL, DIG_START, 1);
+
+	/* switch DP encoder to CRTC data */
+
+	REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 0);
+
+	/* wait 100us for DIG/DP logic to prime
+	 * (i.e. a few video lines)
+	 */
+	udelay(100);
+
+	/* the hardware would start sending video at the start of the next DP
+	 * frame (i.e. rising edge of the vblank).
+	 * NOTE: We used to program DP_VID_STREAM_DIS_DEFER = 2 here, but this
+	 * register has no effect on enable transition! HW always guarantees
+	 * VID_STREAM enable at start of next frame, and this is not
+	 * programmable
+	 */
+
+	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, true);
+}
+
+void enc1_stream_encoder_set_avmute(
+	struct stream_encoder *enc,
+	bool enable)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	unsigned int value = enable ? 1 : 0;
+
+	REG_UPDATE(HDMI_GC, HDMI_GC_AVMUTE, value);
+}
+
+
+#define DP_SEC_AUD_N__DP_SEC_AUD_N__DEFAULT 0x8000
+#define DP_SEC_TIMESTAMP__DP_SEC_TIMESTAMP_MODE__AUTO_CALC 1
+
+#include "include/audio_types.h"
+
+/**
+* speakersToChannels
+*
+* @brief
+*  translate speakers to channels
+*
+*  FL  - Front Left
+*  FR  - Front Right
+*  RL  - Rear Left
+*  RR  - Rear Right
+*  RC  - Rear Center
+*  FC  - Front Center
+*  FLC - Front Left Center
+*  FRC - Front Right Center
+*  RLC - Rear Left Center
+*  RRC - Rear Right Center
+*  LFE - Low Freq Effect
+*
+*               FC
+*          FLC      FRC
+*    FL                    FR
+*
+*                    LFE
+*              ()
+*
+*
+*    RL                    RR
+*          RLC      RRC
+*               RC
+*
+*             ch  8   7   6   5   4   3   2   1
+* 0b00000011      -   -   -   -   -   -   FR  FL
+* 0b00000111      -   -   -   -   -   LFE FR  FL
+* 0b00001011      -   -   -   -   FC  -   FR  FL
+* 0b00001111      -   -   -   -   FC  LFE FR  FL
+* 0b00010011      -   -   -   RC  -   -   FR  FL
+* 0b00010111      -   -   -   RC  -   LFE FR  FL
+* 0b00011011      -   -   -   RC  FC  -   FR  FL
+* 0b00011111      -   -   -   RC  FC  LFE FR  FL
+* 0b00110011      -   -   RR  RL  -   -   FR  FL
+* 0b00110111      -   -   RR  RL  -   LFE FR  FL
+* 0b00111011      -   -   RR  RL  FC  -   FR  FL
+* 0b00111111      -   -   RR  RL  FC  LFE FR  FL
+* 0b01110011      -   RC  RR  RL  -   -   FR  FL
+* 0b01110111      -   RC  RR  RL  -   LFE FR  FL
+* 0b01111011      -   RC  RR  RL  FC  -   FR  FL
+* 0b01111111      -   RC  RR  RL  FC  LFE FR  FL
+* 0b11110011      RRC RLC RR  RL  -   -   FR  FL
+* 0b11110111      RRC RLC RR  RL  -   LFE FR  FL
+* 0b11111011      RRC RLC RR  RL  FC  -   FR  FL
+* 0b11111111      RRC RLC RR  RL  FC  LFE FR  FL
+* 0b11000011      FRC FLC -   -   -   -   FR  FL
+* 0b11000111      FRC FLC -   -   -   LFE FR  FL
+* 0b11001011      FRC FLC -   -   FC  -   FR  FL
+* 0b11001111      FRC FLC -   -   FC  LFE FR  FL
+* 0b11010011      FRC FLC -   RC  -   -   FR  FL
+* 0b11010111      FRC FLC -   RC  -   LFE FR  FL
+* 0b11011011      FRC FLC -   RC  FC  -   FR  FL
+* 0b11011111      FRC FLC -   RC  FC  LFE FR  FL
+* 0b11110011      FRC FLC RR  RL  -   -   FR  FL
+* 0b11110111      FRC FLC RR  RL  -   LFE FR  FL
+* 0b11111011      FRC FLC RR  RL  FC  -   FR  FL
+* 0b11111111      FRC FLC RR  RL  FC  LFE FR  FL
+*
+* @param
+*  speakers - speaker information as it comes from CEA audio block
+*/
+/* translate speakers to channels */
+
+union audio_cea_channels {
+	uint8_t all;
+	struct audio_cea_channels_bits {
+		uint32_t FL:1;
+		uint32_t FR:1;
+		uint32_t LFE:1;
+		uint32_t FC:1;
+		uint32_t RL_RC:1;
+		uint32_t RR:1;
+		uint32_t RC_RLC_FLC:1;
+		uint32_t RRC_FRC:1;
+	} channels;
+};
+
+struct audio_clock_info {
+	/* pixel clock frequency*/
+	uint32_t pixel_clock_in_10khz;
+	/* N - 32KHz audio */
+	uint32_t n_32khz;
+	/* CTS - 32KHz audio*/
+	uint32_t cts_32khz;
+	uint32_t n_44khz;
+	uint32_t cts_44khz;
+	uint32_t n_48khz;
+	uint32_t cts_48khz;
+};
+
+/* 25.2MHz/1.001*/
+/* 25.2MHz/1.001*/
+/* 25.2MHz*/
+/* 27MHz */
+/* 27MHz*1.001*/
+/* 27MHz*1.001*/
+/* 54MHz*/
+/* 54MHz*1.001*/
+/* 74.25MHz/1.001*/
+/* 74.25MHz*/
+/* 148.5MHz/1.001*/
+/* 148.5MHz*/
+
+static const struct audio_clock_info audio_clock_info_table[16] = {
+	{2517, 4576, 28125, 7007, 31250, 6864, 28125},
+	{2518, 4576, 28125, 7007, 31250, 6864, 28125},
+	{2520, 4096, 25200, 6272, 28000, 6144, 25200},
+	{2700, 4096, 27000, 6272, 30000, 6144, 27000},
+	{2702, 4096, 27027, 6272, 30030, 6144, 27027},
+	{2703, 4096, 27027, 6272, 30030, 6144, 27027},
+	{5400, 4096, 54000, 6272, 60000, 6144, 54000},
+	{5405, 4096, 54054, 6272, 60060, 6144, 54054},
+	{7417, 11648, 210937, 17836, 234375, 11648, 140625},
+	{7425, 4096, 74250, 6272, 82500, 6144, 74250},
+	{14835, 11648, 421875, 8918, 234375, 5824, 140625},
+	{14850, 4096, 148500, 6272, 165000, 6144, 148500},
+	{29670, 5824, 421875, 4459, 234375, 5824, 281250},
+	{29700, 3072, 222750, 4704, 247500, 5120, 247500},
+	{59340, 5824, 843750, 8918, 937500, 5824, 562500},
+	{59400, 3072, 445500, 9408, 990000, 6144, 594000}
+};
+
+static const struct audio_clock_info audio_clock_info_table_36bpc[14] = {
+	{2517,  9152,  84375,  7007,  48875,  9152,  56250},
+	{2518,  9152,  84375,  7007,  48875,  9152,  56250},
+	{2520,  4096,  37800,  6272,  42000,  6144,  37800},
+	{2700,  4096,  40500,  6272,  45000,  6144,  40500},
+	{2702,  8192,  81081,  6272,  45045,  8192,  54054},
+	{2703,  8192,  81081,  6272,  45045,  8192,  54054},
+	{5400,  4096,  81000,  6272,  90000,  6144,  81000},
+	{5405,  4096,  81081,  6272,  90090,  6144,  81081},
+	{7417, 11648, 316406, 17836, 351562, 11648, 210937},
+	{7425, 4096, 111375,  6272, 123750,  6144, 111375},
+	{14835, 11648, 632812, 17836, 703125, 11648, 421875},
+	{14850, 4096, 222750,  6272, 247500,  6144, 222750},
+	{29670, 5824, 632812,  8918, 703125,  5824, 421875},
+	{29700, 4096, 445500,  4704, 371250,  5120, 371250}
+};
+
+static const struct audio_clock_info audio_clock_info_table_48bpc[14] = {
+	{2517,  4576,  56250,  7007,  62500,  6864,  56250},
+	{2518,  4576,  56250,  7007,  62500,  6864,  56250},
+	{2520,  4096,  50400,  6272,  56000,  6144,  50400},
+	{2700,  4096,  54000,  6272,  60000,  6144,  54000},
+	{2702,  4096,  54054,  6267,  60060,  8192,  54054},
+	{2703,  4096,  54054,  6272,  60060,  8192,  54054},
+	{5400,  4096, 108000,  6272, 120000,  6144, 108000},
+	{5405,  4096, 108108,  6272, 120120,  6144, 108108},
+	{7417, 11648, 421875, 17836, 468750, 11648, 281250},
+	{7425,  4096, 148500,  6272, 165000,  6144, 148500},
+	{14835, 11648, 843750,  8918, 468750, 11648, 281250},
+	{14850, 4096, 297000,  6272, 330000,  6144, 297000},
+	{29670, 5824, 843750,  4459, 468750,  5824, 562500},
+	{29700, 3072, 445500,  4704, 495000,  5120, 495000}
+
+
+};
+
+static union audio_cea_channels speakers_to_channels(
+	struct audio_speaker_flags speaker_flags)
+{
+	union audio_cea_channels cea_channels = {0};
+
+	/* these are one to one */
+	cea_channels.channels.FL = speaker_flags.FL_FR;
+	cea_channels.channels.FR = speaker_flags.FL_FR;
+	cea_channels.channels.LFE = speaker_flags.LFE;
+	cea_channels.channels.FC = speaker_flags.FC;
+
+	/* if Rear Left and Right exist move RC speaker to channel 7
+	 * otherwise to channel 5
+	 */
+	if (speaker_flags.RL_RR) {
+		cea_channels.channels.RL_RC = speaker_flags.RL_RR;
+		cea_channels.channels.RR = speaker_flags.RL_RR;
+		cea_channels.channels.RC_RLC_FLC = speaker_flags.RC;
+	} else {
+		cea_channels.channels.RL_RC = speaker_flags.RC;
+	}
+
+	/* FRONT Left Right Center and REAR Left Right Center are exclusive */
+	if (speaker_flags.FLC_FRC) {
+		cea_channels.channels.RC_RLC_FLC = speaker_flags.FLC_FRC;
+		cea_channels.channels.RRC_FRC = speaker_flags.FLC_FRC;
+	} else {
+		cea_channels.channels.RC_RLC_FLC = speaker_flags.RLC_RRC;
+		cea_channels.channels.RRC_FRC = speaker_flags.RLC_RRC;
+	}
+
+	return cea_channels;
+}
+
+static uint32_t calc_max_audio_packets_per_line(
+	const struct audio_crtc_info *crtc_info)
+{
+	uint32_t max_packets_per_line;
+
+	max_packets_per_line =
+		crtc_info->h_total - crtc_info->h_active;
+
+	if (crtc_info->pixel_repetition)
+		max_packets_per_line *= crtc_info->pixel_repetition;
+
+	/* for other hdmi features */
+	max_packets_per_line -= 58;
+	/* for Control Period */
+	max_packets_per_line -= 16;
+	/* Number of Audio Packets per Line */
+	max_packets_per_line /= 32;
+
+	return max_packets_per_line;
+}
+
+static void get_audio_clock_info(
+	enum dc_color_depth color_depth,
+	uint32_t crtc_pixel_clock_in_khz,
+	uint32_t actual_pixel_clock_in_khz,
+	struct audio_clock_info *audio_clock_info)
+{
+	const struct audio_clock_info *clock_info;
+	uint32_t index;
+	uint32_t crtc_pixel_clock_in_10khz = crtc_pixel_clock_in_khz / 10;
+	uint32_t audio_array_size;
+
+	switch (color_depth) {
+	case COLOR_DEPTH_161616:
+		clock_info = audio_clock_info_table_48bpc;
+		audio_array_size = ARRAY_SIZE(
+				audio_clock_info_table_48bpc);
+		break;
+	case COLOR_DEPTH_121212:
+		clock_info = audio_clock_info_table_36bpc;
+		audio_array_size = ARRAY_SIZE(
+				audio_clock_info_table_36bpc);
+		break;
+	default:
+		clock_info = audio_clock_info_table;
+		audio_array_size = ARRAY_SIZE(
+				audio_clock_info_table);
+		break;
+	}
+
+	if (clock_info != NULL) {
+		/* search for exact pixel clock in table */
+		for (index = 0; index < audio_array_size; index++) {
+			if (clock_info[index].pixel_clock_in_10khz >
+				crtc_pixel_clock_in_10khz)
+				break;  /* not match */
+			else if (clock_info[index].pixel_clock_in_10khz ==
+					crtc_pixel_clock_in_10khz) {
+				/* match found */
+				*audio_clock_info = clock_info[index];
+				return;
+			}
+		}
+	}
+
+	/* not found */
+	if (actual_pixel_clock_in_khz == 0)
+		actual_pixel_clock_in_khz = crtc_pixel_clock_in_khz;
+
+	/* See HDMI spec  the table entry under
+	 *  pixel clock of "Other". */
+	audio_clock_info->pixel_clock_in_10khz =
+			actual_pixel_clock_in_khz / 10;
+	audio_clock_info->cts_32khz = actual_pixel_clock_in_khz;
+	audio_clock_info->cts_44khz = actual_pixel_clock_in_khz;
+	audio_clock_info->cts_48khz = actual_pixel_clock_in_khz;
+
+	audio_clock_info->n_32khz = 4096;
+	audio_clock_info->n_44khz = 6272;
+	audio_clock_info->n_48khz = 6144;
+}
+
+static void enc1_se_audio_setup(
+	struct stream_encoder *enc,
+	unsigned int az_inst,
+	struct audio_info *audio_info)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	uint32_t speakers = 0;
+	uint32_t channels = 0;
+
+	ASSERT(audio_info);
+	if (audio_info == NULL)
+		/* This should not happen.it does so we don't get BSOD*/
+		return;
+
+	speakers = audio_info->flags.info.ALLSPEAKERS;
+	channels = speakers_to_channels(audio_info->flags.speaker_flags).all;
+
+	/* setup the audio stream source select (audio -> dig mapping) */
+	REG_SET(AFMT_AUDIO_SRC_CONTROL, 0, AFMT_AUDIO_SRC_SELECT, az_inst);
+
+	/* Channel allocation */
+	REG_UPDATE(AFMT_AUDIO_PACKET_CONTROL2, AFMT_AUDIO_CHANNEL_ENABLE, channels);
+}
+
+static void enc1_se_setup_hdmi_audio(
+	struct stream_encoder *enc,
+	const struct audio_crtc_info *crtc_info)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	struct audio_clock_info audio_clock_info = {0};
+	uint32_t max_packets_per_line;
+
+	/* For now still do calculation, although this field is ignored when
+	 * above HDMI_PACKET_GEN_VERSION set to 1
+	 */
+	max_packets_per_line = calc_max_audio_packets_per_line(crtc_info);
+
+	/* HDMI_AUDIO_PACKET_CONTROL */
+	REG_UPDATE_2(HDMI_AUDIO_PACKET_CONTROL,
+			HDMI_AUDIO_PACKETS_PER_LINE, max_packets_per_line,
+			HDMI_AUDIO_DELAY_EN, 1);
+
+	/* AFMT_AUDIO_PACKET_CONTROL */
+	REG_UPDATE(AFMT_AUDIO_PACKET_CONTROL, AFMT_60958_CS_UPDATE, 1);
+
+	/* AFMT_AUDIO_PACKET_CONTROL2 */
+	REG_UPDATE_2(AFMT_AUDIO_PACKET_CONTROL2,
+			AFMT_AUDIO_LAYOUT_OVRD, 0,
+			AFMT_60958_OSF_OVRD, 0);
+
+	/* HDMI_ACR_PACKET_CONTROL */
+	REG_UPDATE_3(HDMI_ACR_PACKET_CONTROL,
+			HDMI_ACR_AUTO_SEND, 1,
+			HDMI_ACR_SOURCE, 0,
+			HDMI_ACR_AUDIO_PRIORITY, 0);
+
+	/* Program audio clock sample/regeneration parameters */
+	get_audio_clock_info(crtc_info->color_depth,
+			     crtc_info->requested_pixel_clock,
+			     crtc_info->calculated_pixel_clock,
+			     &audio_clock_info);
+	DC_LOG_HW_AUDIO(
+			"\n%s:Input::requested_pixel_clock = %d"	\
+			"calculated_pixel_clock = %d \n", __func__,	\
+			crtc_info->requested_pixel_clock,		\
+			crtc_info->calculated_pixel_clock);
+
+	/* HDMI_ACR_32_0__HDMI_ACR_CTS_32_MASK */
+	REG_UPDATE(HDMI_ACR_32_0, HDMI_ACR_CTS_32, audio_clock_info.cts_32khz);
+
+	/* HDMI_ACR_32_1__HDMI_ACR_N_32_MASK */
+	REG_UPDATE(HDMI_ACR_32_1, HDMI_ACR_N_32, audio_clock_info.n_32khz);
+
+	/* HDMI_ACR_44_0__HDMI_ACR_CTS_44_MASK */
+	REG_UPDATE(HDMI_ACR_44_0, HDMI_ACR_CTS_44, audio_clock_info.cts_44khz);
+
+	/* HDMI_ACR_44_1__HDMI_ACR_N_44_MASK */
+	REG_UPDATE(HDMI_ACR_44_1, HDMI_ACR_N_44, audio_clock_info.n_44khz);
+
+	/* HDMI_ACR_48_0__HDMI_ACR_CTS_48_MASK */
+	REG_UPDATE(HDMI_ACR_48_0, HDMI_ACR_CTS_48, audio_clock_info.cts_48khz);
+
+	/* HDMI_ACR_48_1__HDMI_ACR_N_48_MASK */
+	REG_UPDATE(HDMI_ACR_48_1, HDMI_ACR_N_48, audio_clock_info.n_48khz);
+
+	/* Video driver cannot know in advance which sample rate will
+	 * be used by HD Audio driver
+	 * HDMI_ACR_PACKET_CONTROL__HDMI_ACR_N_MULTIPLE field is
+	 * programmed below in interruppt callback
+	 */
+
+	/* AFMT_60958_0__AFMT_60958_CS_CHANNEL_NUMBER_L_MASK &
+	 * AFMT_60958_0__AFMT_60958_CS_CLOCK_ACCURACY_MASK
+	 */
+	REG_UPDATE_2(AFMT_60958_0,
+			AFMT_60958_CS_CHANNEL_NUMBER_L, 1,
+			AFMT_60958_CS_CLOCK_ACCURACY, 0);
+
+	/* AFMT_60958_1 AFMT_60958_CS_CHALNNEL_NUMBER_R */
+	REG_UPDATE(AFMT_60958_1, AFMT_60958_CS_CHANNEL_NUMBER_R, 2);
+
+	/* AFMT_60958_2 now keep this settings until
+	 * Programming guide comes out
+	 */
+	REG_UPDATE_6(AFMT_60958_2,
+			AFMT_60958_CS_CHANNEL_NUMBER_2, 3,
+			AFMT_60958_CS_CHANNEL_NUMBER_3, 4,
+			AFMT_60958_CS_CHANNEL_NUMBER_4, 5,
+			AFMT_60958_CS_CHANNEL_NUMBER_5, 6,
+			AFMT_60958_CS_CHANNEL_NUMBER_6, 7,
+			AFMT_60958_CS_CHANNEL_NUMBER_7, 8);
+}
+
+static void enc1_se_setup_dp_audio(
+	struct stream_encoder *enc)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	/* --- DP Audio packet configurations --- */
+
+	/* ATP Configuration */
+	REG_SET(DP_SEC_AUD_N, 0,
+			DP_SEC_AUD_N, DP_SEC_AUD_N__DP_SEC_AUD_N__DEFAULT);
+
+	/* Async/auto-calc timestamp mode */
+	REG_SET(DP_SEC_TIMESTAMP, 0, DP_SEC_TIMESTAMP_MODE,
+			DP_SEC_TIMESTAMP__DP_SEC_TIMESTAMP_MODE__AUTO_CALC);
+
+	/* --- The following are the registers
+	 *  copied from the SetupHDMI ---
+	 */
+
+	/* AFMT_AUDIO_PACKET_CONTROL */
+	REG_UPDATE(AFMT_AUDIO_PACKET_CONTROL, AFMT_60958_CS_UPDATE, 1);
+
+	/* AFMT_AUDIO_PACKET_CONTROL2 */
+	/* Program the ATP and AIP next */
+	REG_UPDATE_2(AFMT_AUDIO_PACKET_CONTROL2,
+			AFMT_AUDIO_LAYOUT_OVRD, 0,
+			AFMT_60958_OSF_OVRD, 0);
+
+	/* AFMT_INFOFRAME_CONTROL0 */
+	REG_UPDATE(AFMT_INFOFRAME_CONTROL0, AFMT_AUDIO_INFO_UPDATE, 1);
+
+	/* AFMT_60958_0__AFMT_60958_CS_CLOCK_ACCURACY_MASK */
+	REG_UPDATE(AFMT_60958_0, AFMT_60958_CS_CLOCK_ACCURACY, 0);
+}
+
+static void enc1_se_enable_audio_clock(
+	struct stream_encoder *enc,
+	bool enable)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	if (REG(AFMT_CNTL) == 0)
+		return;   /* DCE8/10 does not have this register */
+
+	REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, !!enable);
+
+	/* wait for AFMT clock to turn on,
+	 * expectation: this should complete in 1-2 reads
+	 *
+	 * REG_WAIT(AFMT_CNTL, AFMT_AUDIO_CLOCK_ON, !!enable, 1, 10);
+	 *
+	 * TODO: wait for clock_on does not work well. May need HW
+	 * program sequence. But audio seems work normally even without wait
+	 * for clock_on status change
+	 */
+}
+
+static void enc1_se_enable_dp_audio(
+	struct stream_encoder *enc)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	/* Enable Audio packets */
+	REG_UPDATE(DP_SEC_CNTL, DP_SEC_ASP_ENABLE, 1);
+
+	/* Program the ATP and AIP next */
+	REG_UPDATE_2(DP_SEC_CNTL,
+			DP_SEC_ATP_ENABLE, 1,
+			DP_SEC_AIP_ENABLE, 1);
+
+	/* Program STREAM_ENABLE after all the other enables. */
+	REG_UPDATE(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, 1);
+}
+
+static void enc1_se_disable_dp_audio(
+	struct stream_encoder *enc)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	uint32_t value = 0;
+
+	/* Disable Audio packets */
+	REG_UPDATE_5(DP_SEC_CNTL,
+			DP_SEC_ASP_ENABLE, 0,
+			DP_SEC_ATP_ENABLE, 0,
+			DP_SEC_AIP_ENABLE, 0,
+			DP_SEC_ACM_ENABLE, 0,
+			DP_SEC_STREAM_ENABLE, 0);
+
+	/* This register shared with encoder info frame. Therefore we need to
+	 * keep master enabled if at least on of the fields is not 0
+	 */
+	value = REG_READ(DP_SEC_CNTL);
+	if (value != 0)
+		REG_UPDATE(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, 1);
+
+}
+
+void enc1_se_audio_mute_control(
+	struct stream_encoder *enc,
+	bool mute)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	REG_UPDATE(AFMT_AUDIO_PACKET_CONTROL, AFMT_AUDIO_SAMPLE_SEND, !mute);
+}
+
+void enc1_se_dp_audio_setup(
+	struct stream_encoder *enc,
+	unsigned int az_inst,
+	struct audio_info *info)
+{
+	enc1_se_audio_setup(enc, az_inst, info);
+}
+
+void enc1_se_dp_audio_enable(
+	struct stream_encoder *enc)
+{
+	enc1_se_enable_audio_clock(enc, true);
+	enc1_se_setup_dp_audio(enc);
+	enc1_se_enable_dp_audio(enc);
+}
+
+void enc1_se_dp_audio_disable(
+	struct stream_encoder *enc)
+{
+	enc1_se_disable_dp_audio(enc);
+	enc1_se_enable_audio_clock(enc, false);
+}
+
+void enc1_se_hdmi_audio_setup(
+	struct stream_encoder *enc,
+	unsigned int az_inst,
+	struct audio_info *info,
+	struct audio_crtc_info *audio_crtc_info)
+{
+	enc1_se_enable_audio_clock(enc, true);
+	enc1_se_setup_hdmi_audio(enc, audio_crtc_info);
+	enc1_se_audio_setup(enc, az_inst, info);
+}
+
+void enc1_se_hdmi_audio_disable(
+	struct stream_encoder *enc)
+{
+	enc1_se_enable_audio_clock(enc, false);
+}
+
+
+void enc1_setup_stereo_sync(
+	struct stream_encoder *enc,
+	int tg_inst, bool enable)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	REG_UPDATE(DIG_FE_CNTL, DIG_STEREOSYNC_SELECT, tg_inst);
+	REG_UPDATE(DIG_FE_CNTL, DIG_STEREOSYNC_GATE_EN, !enable);
+}
+
+
+static const struct stream_encoder_funcs dcn10_str_enc_funcs = {
+	.dp_set_stream_attribute =
+		enc1_stream_encoder_dp_set_stream_attribute,
+	.hdmi_set_stream_attribute =
+		enc1_stream_encoder_hdmi_set_stream_attribute,
+	.dvi_set_stream_attribute =
+		enc1_stream_encoder_dvi_set_stream_attribute,
+	.set_mst_bandwidth =
+		enc1_stream_encoder_set_mst_bandwidth,
+	.update_hdmi_info_packets =
+		enc1_stream_encoder_update_hdmi_info_packets,
+	.stop_hdmi_info_packets =
+		enc1_stream_encoder_stop_hdmi_info_packets,
+	.update_dp_info_packets =
+		enc1_stream_encoder_update_dp_info_packets,
+	.stop_dp_info_packets =
+		enc1_stream_encoder_stop_dp_info_packets,
+	.dp_blank =
+		enc1_stream_encoder_dp_blank,
+	.dp_unblank =
+		enc1_stream_encoder_dp_unblank,
+	.audio_mute_control = enc1_se_audio_mute_control,
+
+	.dp_audio_setup = enc1_se_dp_audio_setup,
+	.dp_audio_enable = enc1_se_dp_audio_enable,
+	.dp_audio_disable = enc1_se_dp_audio_disable,
+
+	.hdmi_audio_setup = enc1_se_hdmi_audio_setup,
+	.hdmi_audio_disable = enc1_se_hdmi_audio_disable,
+	.setup_stereo_sync  = enc1_setup_stereo_sync,
+	.set_avmute = enc1_stream_encoder_set_avmute,
+};
+
+void dcn10_stream_encoder_construct(
+	struct dcn10_stream_encoder *enc1,
+	struct dc_context *ctx,
+	struct dc_bios *bp,
+	enum engine_id eng_id,
+	const struct dcn10_stream_enc_registers *regs,
+	const struct dcn10_stream_encoder_shift *se_shift,
+	const struct dcn10_stream_encoder_mask *se_mask)
+{
+	enc1->base.funcs = &dcn10_str_enc_funcs;
+	enc1->base.ctx = ctx;
+	enc1->base.id = eng_id;
+	enc1->base.bp = bp;
+	enc1->regs = regs;
+	enc1->se_shift = se_shift;
+	enc1->se_mask = se_mask;
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
new file mode 100644
index 000000000000..6b3e4ded155b
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
@@ -0,0 +1,524 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ *  and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_STREAM_ENCODER_DCN10_H__
+#define __DC_STREAM_ENCODER_DCN10_H__
+
+#include "stream_encoder.h"
+
+#define DCN10STRENC_FROM_STRENC(stream_encoder)\
+	container_of(stream_encoder, struct dcn10_stream_encoder, base)
+
+#define SE_COMMON_DCN_REG_LIST(id) \
+	SRI(AFMT_CNTL, DIG, id), \
+	SRI(AFMT_GENERIC_0, DIG, id), \
+	SRI(AFMT_GENERIC_1, DIG, id), \
+	SRI(AFMT_GENERIC_2, DIG, id), \
+	SRI(AFMT_GENERIC_3, DIG, id), \
+	SRI(AFMT_GENERIC_4, DIG, id), \
+	SRI(AFMT_GENERIC_5, DIG, id), \
+	SRI(AFMT_GENERIC_6, DIG, id), \
+	SRI(AFMT_GENERIC_7, DIG, id), \
+	SRI(AFMT_GENERIC_HDR, DIG, id), \
+	SRI(AFMT_INFOFRAME_CONTROL0, DIG, id), \
+	SRI(AFMT_VBI_PACKET_CONTROL, DIG, id), \
+	SRI(AFMT_VBI_PACKET_CONTROL1, DIG, id), \
+	SRI(AFMT_AUDIO_PACKET_CONTROL, DIG, id), \
+	SRI(AFMT_AUDIO_PACKET_CONTROL2, DIG, id), \
+	SRI(AFMT_AUDIO_SRC_CONTROL, DIG, id), \
+	SRI(AFMT_60958_0, DIG, id), \
+	SRI(AFMT_60958_1, DIG, id), \
+	SRI(AFMT_60958_2, DIG, id), \
+	SRI(DIG_FE_CNTL, DIG, id), \
+	SRI(HDMI_CONTROL, DIG, id), \
+	SRI(HDMI_DB_CONTROL, DIG, id), \
+	SRI(HDMI_GC, DIG, id), \
+	SRI(HDMI_GENERIC_PACKET_CONTROL0, DIG, id), \
+	SRI(HDMI_GENERIC_PACKET_CONTROL1, DIG, id), \
+	SRI(HDMI_GENERIC_PACKET_CONTROL2, DIG, id), \
+	SRI(HDMI_GENERIC_PACKET_CONTROL3, DIG, id), \
+	SRI(HDMI_INFOFRAME_CONTROL0, DIG, id), \
+	SRI(HDMI_INFOFRAME_CONTROL1, DIG, id), \
+	SRI(HDMI_VBI_PACKET_CONTROL, DIG, id), \
+	SRI(HDMI_AUDIO_PACKET_CONTROL, DIG, id),\
+	SRI(HDMI_ACR_PACKET_CONTROL, DIG, id),\
+	SRI(HDMI_ACR_32_0, DIG, id),\
+	SRI(HDMI_ACR_32_1, DIG, id),\
+	SRI(HDMI_ACR_44_0, DIG, id),\
+	SRI(HDMI_ACR_44_1, DIG, id),\
+	SRI(HDMI_ACR_48_0, DIG, id),\
+	SRI(HDMI_ACR_48_1, DIG, id),\
+	SRI(DP_DB_CNTL, DP, id), \
+	SRI(DP_MSA_MISC, DP, id), \
+	SRI(DP_MSA_COLORIMETRY, DP, id), \
+	SRI(DP_MSA_TIMING_PARAM1, DP, id), \
+	SRI(DP_MSA_TIMING_PARAM2, DP, id), \
+	SRI(DP_MSA_TIMING_PARAM3, DP, id), \
+	SRI(DP_MSA_TIMING_PARAM4, DP, id), \
+	SRI(DP_MSE_RATE_CNTL, DP, id), \
+	SRI(DP_MSE_RATE_UPDATE, DP, id), \
+	SRI(DP_PIXEL_FORMAT, DP, id), \
+	SRI(DP_SEC_CNTL, DP, id), \
+	SRI(DP_STEER_FIFO, DP, id), \
+	SRI(DP_VID_M, DP, id), \
+	SRI(DP_VID_N, DP, id), \
+	SRI(DP_VID_STREAM_CNTL, DP, id), \
+	SRI(DP_VID_TIMING, DP, id), \
+	SRI(DP_SEC_AUD_N, DP, id), \
+	SRI(DP_SEC_TIMESTAMP, DP, id)
+
+#define SE_DCN_REG_LIST(id)\
+	SE_COMMON_DCN_REG_LIST(id)
+
+
+struct dcn10_stream_enc_registers {
+	uint32_t AFMT_CNTL;
+	uint32_t AFMT_AVI_INFO0;
+	uint32_t AFMT_AVI_INFO1;
+	uint32_t AFMT_AVI_INFO2;
+	uint32_t AFMT_AVI_INFO3;
+	uint32_t AFMT_GENERIC_0;
+	uint32_t AFMT_GENERIC_1;
+	uint32_t AFMT_GENERIC_2;
+	uint32_t AFMT_GENERIC_3;
+	uint32_t AFMT_GENERIC_4;
+	uint32_t AFMT_GENERIC_5;
+	uint32_t AFMT_GENERIC_6;
+	uint32_t AFMT_GENERIC_7;
+	uint32_t AFMT_GENERIC_HDR;
+	uint32_t AFMT_INFOFRAME_CONTROL0;
+	uint32_t AFMT_VBI_PACKET_CONTROL;
+	uint32_t AFMT_VBI_PACKET_CONTROL1;
+	uint32_t AFMT_AUDIO_PACKET_CONTROL;
+	uint32_t AFMT_AUDIO_PACKET_CONTROL2;
+	uint32_t AFMT_AUDIO_SRC_CONTROL;
+	uint32_t AFMT_60958_0;
+	uint32_t AFMT_60958_1;
+	uint32_t AFMT_60958_2;
+	uint32_t DIG_FE_CNTL;
+	uint32_t DP_MSE_RATE_CNTL;
+	uint32_t DP_MSE_RATE_UPDATE;
+	uint32_t DP_PIXEL_FORMAT;
+	uint32_t DP_SEC_CNTL;
+	uint32_t DP_STEER_FIFO;
+	uint32_t DP_VID_M;
+	uint32_t DP_VID_N;
+	uint32_t DP_VID_STREAM_CNTL;
+	uint32_t DP_VID_TIMING;
+	uint32_t DP_SEC_AUD_N;
+	uint32_t DP_SEC_TIMESTAMP;
+	uint32_t HDMI_CONTROL;
+	uint32_t HDMI_GC;
+	uint32_t HDMI_GENERIC_PACKET_CONTROL0;
+	uint32_t HDMI_GENERIC_PACKET_CONTROL1;
+	uint32_t HDMI_GENERIC_PACKET_CONTROL2;
+	uint32_t HDMI_GENERIC_PACKET_CONTROL3;
+	uint32_t HDMI_GENERIC_PACKET_CONTROL4;
+	uint32_t HDMI_GENERIC_PACKET_CONTROL5;
+	uint32_t HDMI_INFOFRAME_CONTROL0;
+	uint32_t HDMI_INFOFRAME_CONTROL1;
+	uint32_t HDMI_VBI_PACKET_CONTROL;
+	uint32_t HDMI_AUDIO_PACKET_CONTROL;
+	uint32_t HDMI_ACR_PACKET_CONTROL;
+	uint32_t HDMI_ACR_32_0;
+	uint32_t HDMI_ACR_32_1;
+	uint32_t HDMI_ACR_44_0;
+	uint32_t HDMI_ACR_44_1;
+	uint32_t HDMI_ACR_48_0;
+	uint32_t HDMI_ACR_48_1;
+	uint32_t DP_DB_CNTL;
+	uint32_t DP_MSA_MISC;
+	uint32_t DP_MSA_COLORIMETRY;
+	uint32_t DP_MSA_TIMING_PARAM1;
+	uint32_t DP_MSA_TIMING_PARAM2;
+	uint32_t DP_MSA_TIMING_PARAM3;
+	uint32_t DP_MSA_TIMING_PARAM4;
+	uint32_t HDMI_DB_CONTROL;
+};
+
+
+#define SE_SF(reg_name, field_name, post_fix)\
+	.field_name = reg_name ## __ ## field_name ## post_fix
+
+#define SE_COMMON_MASK_SH_LIST_SOC_BASE(mask_sh)\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_INDEX, mask_sh),\
+	SE_SF(DIG0_AFMT_GENERIC_HDR, AFMT_GENERIC_HB0, mask_sh),\
+	SE_SF(DIG0_AFMT_GENERIC_HDR, AFMT_GENERIC_HB1, mask_sh),\
+	SE_SF(DIG0_AFMT_GENERIC_HDR, AFMT_GENERIC_HB2, mask_sh),\
+	SE_SF(DIG0_AFMT_GENERIC_HDR, AFMT_GENERIC_HB3, mask_sh),\
+	SE_SF(DP0_DP_PIXEL_FORMAT, DP_PIXEL_ENCODING, mask_sh),\
+	SE_SF(DP0_DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH, mask_sh),\
+	SE_SF(DIG0_HDMI_CONTROL, HDMI_PACKET_GEN_VERSION, mask_sh),\
+	SE_SF(DIG0_HDMI_CONTROL, HDMI_KEEPOUT_MODE, mask_sh),\
+	SE_SF(DIG0_HDMI_CONTROL, HDMI_DEEP_COLOR_ENABLE, mask_sh),\
+	SE_SF(DIG0_HDMI_CONTROL, HDMI_DEEP_COLOR_DEPTH, mask_sh),\
+	SE_SF(DIG0_HDMI_CONTROL, HDMI_DATA_SCRAMBLE_EN, mask_sh),\
+	SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_GC_CONT, mask_sh),\
+	SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_GC_SEND, mask_sh),\
+	SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_NULL_SEND, mask_sh),\
+	SE_SF(DIG0_HDMI_INFOFRAME_CONTROL0, HDMI_AUDIO_INFO_SEND, mask_sh),\
+	SE_SF(DIG0_AFMT_INFOFRAME_CONTROL0, AFMT_AUDIO_INFO_UPDATE, mask_sh),\
+	SE_SF(DIG0_HDMI_INFOFRAME_CONTROL1, HDMI_AUDIO_INFO_LINE, mask_sh),\
+	SE_SF(DIG0_HDMI_GC, HDMI_GC_AVMUTE, mask_sh),\
+	SE_SF(DP0_DP_MSE_RATE_CNTL, DP_MSE_RATE_X, mask_sh),\
+	SE_SF(DP0_DP_MSE_RATE_CNTL, DP_MSE_RATE_Y, mask_sh),\
+	SE_SF(DP0_DP_MSE_RATE_UPDATE, DP_MSE_RATE_UPDATE_PENDING, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP0_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP1_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP2_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP3_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_MPG_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_VID_STREAM_CNTL, DP_VID_STREAM_DIS_DEFER, mask_sh),\
+	SE_SF(DP0_DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_VID_STREAM_CNTL, DP_VID_STREAM_STATUS, mask_sh),\
+	SE_SF(DP0_DP_STEER_FIFO, DP_STEER_FIFO_RESET, mask_sh),\
+	SE_SF(DP0_DP_VID_TIMING, DP_VID_M_N_GEN_EN, mask_sh),\
+	SE_SF(DP0_DP_VID_N, DP_VID_N, mask_sh),\
+	SE_SF(DP0_DP_VID_M, DP_VID_M, mask_sh),\
+	SE_SF(DIG0_DIG_FE_CNTL, DIG_START, mask_sh),\
+	SE_SF(DIG0_AFMT_AUDIO_SRC_CONTROL, AFMT_AUDIO_SRC_SELECT, mask_sh),\
+	SE_SF(DIG0_AFMT_AUDIO_PACKET_CONTROL2, AFMT_AUDIO_CHANNEL_ENABLE, mask_sh),\
+	SE_SF(DIG0_HDMI_AUDIO_PACKET_CONTROL, HDMI_AUDIO_PACKETS_PER_LINE, mask_sh),\
+	SE_SF(DIG0_HDMI_AUDIO_PACKET_CONTROL, HDMI_AUDIO_DELAY_EN, mask_sh),\
+	SE_SF(DIG0_AFMT_AUDIO_PACKET_CONTROL, AFMT_60958_CS_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_AUDIO_PACKET_CONTROL2, AFMT_AUDIO_LAYOUT_OVRD, mask_sh),\
+	SE_SF(DIG0_AFMT_AUDIO_PACKET_CONTROL2, AFMT_60958_OSF_OVRD, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_PACKET_CONTROL, HDMI_ACR_AUTO_SEND, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_PACKET_CONTROL, HDMI_ACR_SOURCE, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_PACKET_CONTROL, HDMI_ACR_AUDIO_PRIORITY, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_32_0, HDMI_ACR_CTS_32, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_32_1, HDMI_ACR_N_32, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_44_0, HDMI_ACR_CTS_44, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_44_1, HDMI_ACR_N_44, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_48_0, HDMI_ACR_CTS_48, mask_sh),\
+	SE_SF(DIG0_HDMI_ACR_48_1, HDMI_ACR_N_48, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_0, AFMT_60958_CS_CHANNEL_NUMBER_L, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_0, AFMT_60958_CS_CLOCK_ACCURACY, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_1, AFMT_60958_CS_CHANNEL_NUMBER_R, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_2, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_3, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_4, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_5, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_6, mask_sh),\
+	SE_SF(DIG0_AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_7, mask_sh),\
+	SE_SF(DP0_DP_SEC_AUD_N, DP_SEC_AUD_N, mask_sh),\
+	SE_SF(DP0_DP_SEC_TIMESTAMP, DP_SEC_TIMESTAMP_MODE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_ASP_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_ATP_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_AIP_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_ACM_ENABLE, mask_sh),\
+	SE_SF(DIG0_AFMT_AUDIO_PACKET_CONTROL, AFMT_AUDIO_SAMPLE_SEND, mask_sh),\
+	SE_SF(DIG0_AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, mask_sh),\
+	SE_SF(DIG0_HDMI_CONTROL, HDMI_CLOCK_CHANNEL_RATE, mask_sh),\
+	SE_SF(DIG0_DIG_FE_CNTL, TMDS_PIXEL_ENCODING, mask_sh),\
+	SE_SF(DIG0_DIG_FE_CNTL, TMDS_COLOR_FORMAT, mask_sh),\
+	SE_SF(DIG0_DIG_FE_CNTL, DIG_STEREOSYNC_SELECT, mask_sh),\
+	SE_SF(DIG0_DIG_FE_CNTL, DIG_STEREOSYNC_GATE_EN, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_LOCK_STATUS, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_CONFLICT, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_CONFLICT_CLR, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC0_FRAME_UPDATE_PENDING, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC1_FRAME_UPDATE_PENDING, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_FRAME_UPDATE_PENDING, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_FRAME_UPDATE_PENDING, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_FRAME_UPDATE_PENDING, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_FRAME_UPDATE_PENDING, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_FRAME_UPDATE_PENDING, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_FRAME_UPDATE_PENDING, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC0_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC1_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_FRAME_UPDATE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP4_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP5_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP6_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP7_ENABLE, mask_sh),\
+	SE_SF(DP0_DP_DB_CNTL, DP_DB_DISABLE, mask_sh),\
+	SE_SF(DP0_DP_MSA_COLORIMETRY, DP_MSA_MISC0, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM1, DP_MSA_HTOTAL, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM1, DP_MSA_VTOTAL, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM2, DP_MSA_HSTART, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM2, DP_MSA_VSTART, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM3, DP_MSA_HSYNCWIDTH, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM3, DP_MSA_HSYNCPOLARITY, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM3, DP_MSA_VSYNCWIDTH, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM3, DP_MSA_VSYNCPOLARITY, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM4, DP_MSA_HWIDTH, mask_sh),\
+	SE_SF(DP0_DP_MSA_TIMING_PARAM4, DP_MSA_VHEIGHT, mask_sh),\
+	SE_SF(DIG0_HDMI_DB_CONTROL, HDMI_DB_DISABLE, mask_sh),\
+	SE_SF(DP0_DP_VID_TIMING, DP_VID_N_MUL, mask_sh)
+
+#define SE_COMMON_MASK_SH_LIST_SOC(mask_sh)\
+	SE_COMMON_MASK_SH_LIST_SOC_BASE(mask_sh)
+
+#define SE_COMMON_MASK_SH_LIST_DCN10(mask_sh)\
+	SE_COMMON_MASK_SH_LIST_SOC(mask_sh),\
+	SE_SF(DIG0_HDMI_GENERIC_PACKET_CONTROL0, HDMI_GENERIC0_CONT, mask_sh),\
+	SE_SF(DIG0_HDMI_GENERIC_PACKET_CONTROL0, HDMI_GENERIC0_SEND, mask_sh),\
+	SE_SF(DIG0_HDMI_GENERIC_PACKET_CONTROL0, HDMI_GENERIC0_LINE, mask_sh),\
+	SE_SF(DIG0_HDMI_GENERIC_PACKET_CONTROL0, HDMI_GENERIC1_CONT, mask_sh),\
+	SE_SF(DIG0_HDMI_GENERIC_PACKET_CONTROL0, HDMI_GENERIC1_SEND, mask_sh),\
+	SE_SF(DIG0_HDMI_GENERIC_PACKET_CONTROL0, HDMI_GENERIC1_LINE, mask_sh)
+
+
+#define SE_REG_FIELD_LIST_DCN1_0(type) \
+	type AFMT_GENERIC_INDEX;\
+	type AFMT_GENERIC_HB0;\
+	type AFMT_GENERIC_HB1;\
+	type AFMT_GENERIC_HB2;\
+	type AFMT_GENERIC_HB3;\
+	type AFMT_GENERIC_LOCK_STATUS;\
+	type AFMT_GENERIC_CONFLICT;\
+	type AFMT_GENERIC_CONFLICT_CLR;\
+	type AFMT_GENERIC0_FRAME_UPDATE_PENDING;\
+	type AFMT_GENERIC1_FRAME_UPDATE_PENDING;\
+	type AFMT_GENERIC2_FRAME_UPDATE_PENDING;\
+	type AFMT_GENERIC3_FRAME_UPDATE_PENDING;\
+	type AFMT_GENERIC4_FRAME_UPDATE_PENDING;\
+	type AFMT_GENERIC5_FRAME_UPDATE_PENDING;\
+	type AFMT_GENERIC6_FRAME_UPDATE_PENDING;\
+	type AFMT_GENERIC7_FRAME_UPDATE_PENDING;\
+	type AFMT_GENERIC0_FRAME_UPDATE;\
+	type AFMT_GENERIC1_FRAME_UPDATE;\
+	type AFMT_GENERIC2_FRAME_UPDATE;\
+	type AFMT_GENERIC3_FRAME_UPDATE;\
+	type AFMT_GENERIC4_FRAME_UPDATE;\
+	type AFMT_GENERIC5_FRAME_UPDATE;\
+	type AFMT_GENERIC6_FRAME_UPDATE;\
+	type AFMT_GENERIC7_FRAME_UPDATE;\
+	type HDMI_GENERIC0_CONT;\
+	type HDMI_GENERIC0_SEND;\
+	type HDMI_GENERIC0_LINE;\
+	type HDMI_GENERIC1_CONT;\
+	type HDMI_GENERIC1_SEND;\
+	type HDMI_GENERIC1_LINE;\
+	type HDMI_GENERIC2_CONT;\
+	type HDMI_GENERIC2_SEND;\
+	type HDMI_GENERIC2_LINE;\
+	type HDMI_GENERIC3_CONT;\
+	type HDMI_GENERIC3_SEND;\
+	type HDMI_GENERIC3_LINE;\
+	type HDMI_GENERIC4_CONT;\
+	type HDMI_GENERIC4_SEND;\
+	type HDMI_GENERIC4_LINE;\
+	type HDMI_GENERIC5_CONT;\
+	type HDMI_GENERIC5_SEND;\
+	type HDMI_GENERIC5_LINE;\
+	type HDMI_GENERIC6_CONT;\
+	type HDMI_GENERIC6_SEND;\
+	type HDMI_GENERIC6_LINE;\
+	type HDMI_GENERIC7_CONT;\
+	type HDMI_GENERIC7_SEND;\
+	type HDMI_GENERIC7_LINE;\
+	type DP_PIXEL_ENCODING;\
+	type DP_COMPONENT_DEPTH;\
+	type HDMI_PACKET_GEN_VERSION;\
+	type HDMI_KEEPOUT_MODE;\
+	type HDMI_DEEP_COLOR_ENABLE;\
+	type HDMI_CLOCK_CHANNEL_RATE;\
+	type HDMI_DEEP_COLOR_DEPTH;\
+	type HDMI_GC_CONT;\
+	type HDMI_GC_SEND;\
+	type HDMI_NULL_SEND;\
+	type HDMI_DATA_SCRAMBLE_EN;\
+	type HDMI_AUDIO_INFO_SEND;\
+	type AFMT_AUDIO_INFO_UPDATE;\
+	type HDMI_AUDIO_INFO_LINE;\
+	type HDMI_GC_AVMUTE;\
+	type DP_MSE_RATE_X;\
+	type DP_MSE_RATE_Y;\
+	type DP_MSE_RATE_UPDATE_PENDING;\
+	type DP_SEC_GSP0_ENABLE;\
+	type DP_SEC_STREAM_ENABLE;\
+	type DP_SEC_GSP1_ENABLE;\
+	type DP_SEC_GSP2_ENABLE;\
+	type DP_SEC_GSP3_ENABLE;\
+	type DP_SEC_GSP4_ENABLE;\
+	type DP_SEC_GSP5_ENABLE;\
+	type DP_SEC_GSP6_ENABLE;\
+	type DP_SEC_GSP7_ENABLE;\
+	type DP_SEC_MPG_ENABLE;\
+	type DP_VID_STREAM_DIS_DEFER;\
+	type DP_VID_STREAM_ENABLE;\
+	type DP_VID_STREAM_STATUS;\
+	type DP_STEER_FIFO_RESET;\
+	type DP_VID_M_N_GEN_EN;\
+	type DP_VID_N;\
+	type DP_VID_M;\
+	type DIG_START;\
+	type AFMT_AUDIO_SRC_SELECT;\
+	type AFMT_AUDIO_CHANNEL_ENABLE;\
+	type HDMI_AUDIO_PACKETS_PER_LINE;\
+	type HDMI_AUDIO_DELAY_EN;\
+	type AFMT_60958_CS_UPDATE;\
+	type AFMT_AUDIO_LAYOUT_OVRD;\
+	type AFMT_60958_OSF_OVRD;\
+	type HDMI_ACR_AUTO_SEND;\
+	type HDMI_ACR_SOURCE;\
+	type HDMI_ACR_AUDIO_PRIORITY;\
+	type HDMI_ACR_CTS_32;\
+	type HDMI_ACR_N_32;\
+	type HDMI_ACR_CTS_44;\
+	type HDMI_ACR_N_44;\
+	type HDMI_ACR_CTS_48;\
+	type HDMI_ACR_N_48;\
+	type AFMT_60958_CS_CHANNEL_NUMBER_L;\
+	type AFMT_60958_CS_CLOCK_ACCURACY;\
+	type AFMT_60958_CS_CHANNEL_NUMBER_R;\
+	type AFMT_60958_CS_CHANNEL_NUMBER_2;\
+	type AFMT_60958_CS_CHANNEL_NUMBER_3;\
+	type AFMT_60958_CS_CHANNEL_NUMBER_4;\
+	type AFMT_60958_CS_CHANNEL_NUMBER_5;\
+	type AFMT_60958_CS_CHANNEL_NUMBER_6;\
+	type AFMT_60958_CS_CHANNEL_NUMBER_7;\
+	type DP_SEC_AUD_N;\
+	type DP_SEC_TIMESTAMP_MODE;\
+	type DP_SEC_ASP_ENABLE;\
+	type DP_SEC_ATP_ENABLE;\
+	type DP_SEC_AIP_ENABLE;\
+	type DP_SEC_ACM_ENABLE;\
+	type AFMT_AUDIO_SAMPLE_SEND;\
+	type AFMT_AUDIO_CLOCK_EN;\
+	type TMDS_PIXEL_ENCODING;\
+	type TMDS_COLOR_FORMAT;\
+	type DIG_STEREOSYNC_SELECT;\
+	type DIG_STEREOSYNC_GATE_EN;\
+	type DP_DB_DISABLE;\
+	type DP_MSA_MISC0;\
+	type DP_MSA_HTOTAL;\
+	type DP_MSA_VTOTAL;\
+	type DP_MSA_HSTART;\
+	type DP_MSA_VSTART;\
+	type DP_MSA_HSYNCWIDTH;\
+	type DP_MSA_HSYNCPOLARITY;\
+	type DP_MSA_VSYNCWIDTH;\
+	type DP_MSA_VSYNCPOLARITY;\
+	type DP_MSA_HWIDTH;\
+	type DP_MSA_VHEIGHT;\
+	type HDMI_DB_DISABLE;\
+	type DP_VID_N_MUL;\
+	type DP_VID_M_DOUBLE_VALUE_EN
+
+struct dcn10_stream_encoder_shift {
+	SE_REG_FIELD_LIST_DCN1_0(uint8_t);
+};
+
+struct dcn10_stream_encoder_mask {
+	SE_REG_FIELD_LIST_DCN1_0(uint32_t);
+};
+
+struct dcn10_stream_encoder {
+	struct stream_encoder base;
+	const struct dcn10_stream_enc_registers *regs;
+	const struct dcn10_stream_encoder_shift *se_shift;
+	const struct dcn10_stream_encoder_mask *se_mask;
+};
+
+void dcn10_stream_encoder_construct(
+	struct dcn10_stream_encoder *enc1,
+	struct dc_context *ctx,
+	struct dc_bios *bp,
+	enum engine_id eng_id,
+	const struct dcn10_stream_enc_registers *regs,
+	const struct dcn10_stream_encoder_shift *se_shift,
+	const struct dcn10_stream_encoder_mask *se_mask);
+
+void enc1_update_generic_info_packet(
+	struct dcn10_stream_encoder *enc1,
+	uint32_t packet_index,
+	const struct dc_info_packet *info_packet);
+
+void enc1_stream_encoder_dp_set_stream_attribute(
+	struct stream_encoder *enc,
+	struct dc_crtc_timing *crtc_timing,
+	enum dc_color_space output_color_space);
+
+void enc1_stream_encoder_hdmi_set_stream_attribute(
+	struct stream_encoder *enc,
+	struct dc_crtc_timing *crtc_timing,
+	int actual_pix_clk_khz,
+	bool enable_audio);
+
+void enc1_stream_encoder_dvi_set_stream_attribute(
+	struct stream_encoder *enc,
+	struct dc_crtc_timing *crtc_timing,
+	bool is_dual_link);
+
+void enc1_stream_encoder_set_mst_bandwidth(
+	struct stream_encoder *enc,
+	struct fixed31_32 avg_time_slots_per_mtp);
+
+void enc1_stream_encoder_update_dp_info_packets(
+	struct stream_encoder *enc,
+	const struct encoder_info_frame *info_frame);
+
+void enc1_stream_encoder_stop_dp_info_packets(
+	struct stream_encoder *enc);
+
+void enc1_stream_encoder_dp_blank(
+	struct stream_encoder *enc);
+
+void enc1_stream_encoder_dp_unblank(
+	struct stream_encoder *enc,
+	const struct encoder_unblank_param *param);
+
+void enc1_setup_stereo_sync(
+	struct stream_encoder *enc,
+	int tg_inst, bool enable);
+
+void enc1_stream_encoder_set_avmute(
+	struct stream_encoder *enc,
+	bool enable);
+
+void enc1_se_audio_mute_control(
+	struct stream_encoder *enc,
+	bool mute);
+
+void enc1_se_dp_audio_setup(
+	struct stream_encoder *enc,
+	unsigned int az_inst,
+	struct audio_info *info);
+
+void enc1_se_dp_audio_enable(
+	struct stream_encoder *enc);
+
+void enc1_se_dp_audio_disable(
+	struct stream_encoder *enc);
+
+void enc1_se_hdmi_audio_setup(
+	struct stream_encoder *enc,
+	unsigned int az_inst,
+	struct audio_info *info,
+	struct audio_crtc_info *audio_crtc_info);
+
+void enc1_se_hdmi_audio_disable(
+	struct stream_encoder *enc);
+
+#endif /* __DC_STREAM_ENCODER_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index 22e7ee7dcd26..4ff9b2bba178 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -341,6 +341,10 @@ bool dm_dmcu_set_pipe(struct dc_context *ctx, unsigned int controller_id);
 
 unsigned long long dm_get_timestamp(struct dc_context *ctx);
 
+unsigned long long dm_get_elapse_time_in_ns(struct dc_context *ctx,
+		unsigned long long current_time_stamp,
+		unsigned long long last_time_stamp);
+
 /*
  * performance tracing
  */
@@ -351,10 +355,6 @@ void dm_perf_trace_timestamp(const char *func_name, unsigned int line);
 /*
  * Debug and verification hooks
  */
-bool dm_helpers_dc_conn_log(
-		struct dc_context *ctx,
-		struct log_entry *entry,
-		enum dc_log_type event);
 
 void dm_dtn_log_begin(struct dc_context *ctx);
 void dm_dtn_log_append_v(struct dc_context *ctx, const char *msg, ...);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
index b1ad3553f900..47c19f8fe7d1 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
@@ -108,4 +108,17 @@ enum output_standard {
 	dm_std_uninitialized = 0, dm_std_cvtr2, dm_std_cvt
 };
 
+enum mpc_combine_affinity {
+	dm_mpc_always_when_possible,
+	dm_mpc_reduce_voltage,
+	dm_mpc_reduce_voltage_and_clocks
+};
+
+enum self_refresh_affinity {
+	dm_try_to_allow_self_refresh_and_mclk_switch,
+	dm_allow_self_refresh_and_mclk_switch,
+	dm_allow_self_refresh,
+	dm_neither_self_refresh_nor_mclk_switch
+};
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
index c109b2c34c8f..fd9d97aab071 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
@@ -26,75 +26,89 @@
 #include "display_mode_lib.h"
 #include "dc_features.h"
 
+static const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
+	.rob_buffer_size_kbytes = 64,
+	.det_buffer_size_kbytes = 164,
+	.dpte_buffer_size_in_pte_reqs = 42,
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.pte_enable = 1,
+	.pte_chunk_size_kbytes = 2,
+	.meta_chunk_size_kbytes = 2,
+	.writeback_chunk_size_kbytes = 2,
+	.line_buffer_size_bits = 589824,
+	.max_line_buffer_lines = 12,
+	.IsLineBufferBppFixed = 0,
+	.LineBufferFixedBpp = -1,
+	.writeback_luma_buffer_size_kbytes = 12,
+	.writeback_chroma_buffer_size_kbytes = 8,
+	.max_num_dpp = 4,
+	.max_num_wb = 2,
+	.max_dchub_pscl_bw_pix_per_clk = 4,
+	.max_pscl_lb_bw_pix_per_clk = 2,
+	.max_lb_vscl_bw_pix_per_clk = 4,
+	.max_vscl_hscl_bw_pix_per_clk = 4,
+	.max_hscl_ratio = 4,
+	.max_vscl_ratio = 4,
+	.hscl_mults = 4,
+	.vscl_mults = 4,
+	.max_hscl_taps = 8,
+	.max_vscl_taps = 8,
+	.dispclk_ramp_margin_percent = 1,
+	.underscan_factor = 1.10,
+	.min_vblank_lines = 14,
+	.dppclk_delay_subtotal = 90,
+	.dispclk_delay_subtotal = 42,
+	.dcfclk_cstate_latency = 10,
+	.max_inter_dcn_tile_repeaters = 8,
+	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
+	.bug_forcing_LC_req_same_size_fixed = 0,
+};
+
+static const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
+	.sr_exit_time_us = 9.0,
+	.sr_enter_plus_exit_time_us = 11.0,
+	.urgent_latency_us = 4.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 80.0,
+	.max_request_size_bytes = 256,
+	.downspread_percent = 0.5,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 128,
+	.urgent_out_of_order_return_per_channel_bytes = 256,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 2,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 17.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+};
+
 static void set_soc_bounding_box(struct _vcs_dpi_soc_bounding_box_st *soc, enum dml_project project)
 {
-	if (project == DML_PROJECT_RAVEN1) {
-		soc->sr_exit_time_us = 9.0;
-		soc->sr_enter_plus_exit_time_us = 11.0;
-		soc->urgent_latency_us = 4.0;
-		soc->writeback_latency_us = 12.0;
-		soc->ideal_dram_bw_after_urgent_percent = 80.0;
-		soc->max_request_size_bytes = 256;
-		soc->downspread_percent = 0.5;
-		soc->dram_page_open_time_ns = 50.0;
-		soc->dram_rw_turnaround_time_ns = 17.5;
-		soc->dram_return_buffer_per_channel_bytes = 8192;
-		soc->round_trip_ping_latency_dcfclk_cycles = 128;
-		soc->urgent_out_of_order_return_per_channel_bytes = 256;
-		soc->channel_interleave_bytes = 256;
-		soc->num_banks = 8;
-		soc->num_chans = 2;
-		soc->vmm_page_size_bytes = 4096;
-		soc->dram_clock_change_latency_us = 17.0;
-		soc->writeback_dram_clock_change_latency_us = 23.0;
-		soc->return_bus_width_bytes = 64;
-	} else {
-		BREAK_TO_DEBUGGER(); /* Invalid Project Specified */
+	switch (project) {
+	case DML_PROJECT_RAVEN1:
+		*soc = dcn1_0_soc;
+		break;
+	default:
+		ASSERT(0);
+		break;
 	}
 }
 
 static void set_ip_params(struct _vcs_dpi_ip_params_st *ip, enum dml_project project)
 {
-	if (project == DML_PROJECT_RAVEN1) {
-		ip->rob_buffer_size_kbytes = 64;
-		ip->det_buffer_size_kbytes = 164;
-		ip->dpte_buffer_size_in_pte_reqs = 42;
-		ip->dpp_output_buffer_pixels = 2560;
-		ip->opp_output_buffer_lines = 1;
-		ip->pixel_chunk_size_kbytes = 8;
-		ip->pte_enable = 1;
-		ip->pte_chunk_size_kbytes = 2;
-		ip->meta_chunk_size_kbytes = 2;
-		ip->writeback_chunk_size_kbytes = 2;
-		ip->line_buffer_size_bits = 589824;
-		ip->max_line_buffer_lines = 12;
-		ip->IsLineBufferBppFixed = 0;
-		ip->LineBufferFixedBpp = -1;
-		ip->writeback_luma_buffer_size_kbytes = 12;
-		ip->writeback_chroma_buffer_size_kbytes = 8;
-		ip->max_num_dpp = 4;
-		ip->max_num_wb = 2;
-		ip->max_dchub_pscl_bw_pix_per_clk = 4;
-		ip->max_pscl_lb_bw_pix_per_clk = 2;
-		ip->max_lb_vscl_bw_pix_per_clk = 4;
-		ip->max_vscl_hscl_bw_pix_per_clk = 4;
-		ip->max_hscl_ratio = 4;
-		ip->max_vscl_ratio = 4;
-		ip->hscl_mults = 4;
-		ip->vscl_mults = 4;
-		ip->max_hscl_taps = 8;
-		ip->max_vscl_taps = 8;
-		ip->dispclk_ramp_margin_percent = 1;
-		ip->underscan_factor = 1.10;
-		ip->min_vblank_lines = 14;
-		ip->dppclk_delay_subtotal = 90;
-		ip->dispclk_delay_subtotal = 42;
-		ip->dcfclk_cstate_latency = 10;
-		ip->max_inter_dcn_tile_repeaters = 8;
-		ip->can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0;
-		ip->bug_forcing_LC_req_same_size_fixed = 0;
-	} else {
-		BREAK_TO_DEBUGGER(); /* Invalid Project Specified */
+	switch (project) {
+	case DML_PROJECT_RAVEN1:
+		*ip = dcn1_0_ip;
+		break;
+	default:
+		ASSERT(0);
+		break;
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index 09affa16cc43..7fa0375939ae 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -25,39 +25,39 @@
 #ifndef __DISPLAY_MODE_STRUCTS_H__
 #define __DISPLAY_MODE_STRUCTS_H__
 
-typedef struct _vcs_dpi_voltage_scaling_st	voltage_scaling_st;
-typedef struct _vcs_dpi_soc_bounding_box_st	soc_bounding_box_st;
-typedef struct _vcs_dpi_ip_params_st	ip_params_st;
-typedef struct _vcs_dpi_display_pipe_source_params_st	display_pipe_source_params_st;
-typedef struct _vcs_dpi_display_output_params_st	display_output_params_st;
-typedef struct _vcs_dpi_display_bandwidth_st	display_bandwidth_st;
-typedef struct _vcs_dpi_scaler_ratio_depth_st	scaler_ratio_depth_st;
-typedef struct _vcs_dpi_scaler_taps_st	scaler_taps_st;
-typedef struct _vcs_dpi_display_pipe_dest_params_st	display_pipe_dest_params_st;
-typedef struct _vcs_dpi_display_pipe_params_st	display_pipe_params_st;
-typedef struct _vcs_dpi_display_clocks_and_cfg_st	display_clocks_and_cfg_st;
-typedef struct _vcs_dpi_display_e2e_pipe_params_st	display_e2e_pipe_params_st;
-typedef struct _vcs_dpi_dchub_buffer_sizing_st	dchub_buffer_sizing_st;
-typedef struct _vcs_dpi_watermarks_perf_st	watermarks_perf_st;
-typedef struct _vcs_dpi_cstate_pstate_watermarks_st	cstate_pstate_watermarks_st;
-typedef struct _vcs_dpi_wm_calc_pipe_params_st	wm_calc_pipe_params_st;
-typedef struct _vcs_dpi_vratio_pre_st	vratio_pre_st;
-typedef struct _vcs_dpi_display_data_rq_misc_params_st	display_data_rq_misc_params_st;
-typedef struct _vcs_dpi_display_data_rq_sizing_params_st	display_data_rq_sizing_params_st;
-typedef struct _vcs_dpi_display_data_rq_dlg_params_st	display_data_rq_dlg_params_st;
-typedef struct _vcs_dpi_display_cur_rq_dlg_params_st	display_cur_rq_dlg_params_st;
-typedef struct _vcs_dpi_display_rq_dlg_params_st	display_rq_dlg_params_st;
-typedef struct _vcs_dpi_display_rq_sizing_params_st	display_rq_sizing_params_st;
-typedef struct _vcs_dpi_display_rq_misc_params_st	display_rq_misc_params_st;
-typedef struct _vcs_dpi_display_rq_params_st	display_rq_params_st;
-typedef struct _vcs_dpi_display_dlg_regs_st	display_dlg_regs_st;
-typedef struct _vcs_dpi_display_ttu_regs_st	display_ttu_regs_st;
-typedef struct _vcs_dpi_display_data_rq_regs_st	display_data_rq_regs_st;
-typedef struct _vcs_dpi_display_rq_regs_st	display_rq_regs_st;
-typedef struct _vcs_dpi_display_dlg_sys_params_st	display_dlg_sys_params_st;
-typedef struct _vcs_dpi_display_dlg_prefetch_param_st	display_dlg_prefetch_param_st;
-typedef struct _vcs_dpi_display_pipe_clock_st	display_pipe_clock_st;
-typedef struct _vcs_dpi_display_arb_params_st	display_arb_params_st;
+typedef struct _vcs_dpi_voltage_scaling_st voltage_scaling_st;
+typedef struct _vcs_dpi_soc_bounding_box_st soc_bounding_box_st;
+typedef struct _vcs_dpi_ip_params_st ip_params_st;
+typedef struct _vcs_dpi_display_pipe_source_params_st display_pipe_source_params_st;
+typedef struct _vcs_dpi_display_output_params_st display_output_params_st;
+typedef struct _vcs_dpi_display_bandwidth_st display_bandwidth_st;
+typedef struct _vcs_dpi_scaler_ratio_depth_st scaler_ratio_depth_st;
+typedef struct _vcs_dpi_scaler_taps_st scaler_taps_st;
+typedef struct _vcs_dpi_display_pipe_dest_params_st display_pipe_dest_params_st;
+typedef struct _vcs_dpi_display_pipe_params_st display_pipe_params_st;
+typedef struct _vcs_dpi_display_clocks_and_cfg_st display_clocks_and_cfg_st;
+typedef struct _vcs_dpi_display_e2e_pipe_params_st display_e2e_pipe_params_st;
+typedef struct _vcs_dpi_dchub_buffer_sizing_st dchub_buffer_sizing_st;
+typedef struct _vcs_dpi_watermarks_perf_st watermarks_perf_st;
+typedef struct _vcs_dpi_cstate_pstate_watermarks_st cstate_pstate_watermarks_st;
+typedef struct _vcs_dpi_wm_calc_pipe_params_st wm_calc_pipe_params_st;
+typedef struct _vcs_dpi_vratio_pre_st vratio_pre_st;
+typedef struct _vcs_dpi_display_data_rq_misc_params_st display_data_rq_misc_params_st;
+typedef struct _vcs_dpi_display_data_rq_sizing_params_st display_data_rq_sizing_params_st;
+typedef struct _vcs_dpi_display_data_rq_dlg_params_st display_data_rq_dlg_params_st;
+typedef struct _vcs_dpi_display_cur_rq_dlg_params_st display_cur_rq_dlg_params_st;
+typedef struct _vcs_dpi_display_rq_dlg_params_st display_rq_dlg_params_st;
+typedef struct _vcs_dpi_display_rq_sizing_params_st display_rq_sizing_params_st;
+typedef struct _vcs_dpi_display_rq_misc_params_st display_rq_misc_params_st;
+typedef struct _vcs_dpi_display_rq_params_st display_rq_params_st;
+typedef struct _vcs_dpi_display_dlg_regs_st display_dlg_regs_st;
+typedef struct _vcs_dpi_display_ttu_regs_st display_ttu_regs_st;
+typedef struct _vcs_dpi_display_data_rq_regs_st display_data_rq_regs_st;
+typedef struct _vcs_dpi_display_rq_regs_st display_rq_regs_st;
+typedef struct _vcs_dpi_display_dlg_sys_params_st display_dlg_sys_params_st;
+typedef struct _vcs_dpi_display_dlg_prefetch_param_st display_dlg_prefetch_param_st;
+typedef struct _vcs_dpi_display_pipe_clock_st display_pipe_clock_st;
+typedef struct _vcs_dpi_display_arb_params_st display_arb_params_st;
 
 struct _vcs_dpi_voltage_scaling_st {
 	int state;
@@ -72,89 +72,107 @@ struct _vcs_dpi_voltage_scaling_st {
 	double dppclk_mhz;
 };
 
-struct	_vcs_dpi_soc_bounding_box_st	{
-	double	sr_exit_time_us;
-	double	sr_enter_plus_exit_time_us;
-	double	urgent_latency_us;
-	double	writeback_latency_us;
-	double	ideal_dram_bw_after_urgent_percent;
-	unsigned int	max_request_size_bytes;
-	double	downspread_percent;
-	double	dram_page_open_time_ns;
-	double	dram_rw_turnaround_time_ns;
-	double	dram_return_buffer_per_channel_bytes;
-	double	dram_channel_width_bytes;
+struct _vcs_dpi_soc_bounding_box_st {
+	double sr_exit_time_us;
+	double sr_enter_plus_exit_time_us;
+	double urgent_latency_us;
+	double urgent_latency_pixel_data_only_us;
+	double urgent_latency_pixel_mixed_with_vm_data_us;
+	double urgent_latency_vm_data_only_us;
+	double writeback_latency_us;
+	double ideal_dram_bw_after_urgent_percent;
+	double pct_ideal_dram_sdp_bw_after_urgent_pixel_only; // PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly
+	double pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm;
+	double pct_ideal_dram_sdp_bw_after_urgent_vm_only;
+	double max_avg_sdp_bw_use_normal_percent;
+	double max_avg_dram_bw_use_normal_percent;
+	unsigned int max_request_size_bytes;
+	double downspread_percent;
+	double dram_page_open_time_ns;
+	double dram_rw_turnaround_time_ns;
+	double dram_return_buffer_per_channel_bytes;
+	double dram_channel_width_bytes;
 	double fabric_datapath_to_dcn_data_return_bytes;
 	double dcn_downspread_percent;
 	double dispclk_dppclk_vco_speed_mhz;
 	double dfs_vco_period_ps;
-	unsigned int	round_trip_ping_latency_dcfclk_cycles;
-	unsigned int	urgent_out_of_order_return_per_channel_bytes;
-	unsigned int	channel_interleave_bytes;
-	unsigned int	num_banks;
-	unsigned int	num_chans;
-	unsigned int	vmm_page_size_bytes;
-	double	dram_clock_change_latency_us;
-	double	writeback_dram_clock_change_latency_us;
-	unsigned int	return_bus_width_bytes;
-	unsigned int	voltage_override;
-	double	xfc_bus_transport_time_us;
-	double	xfc_xbuf_latency_tolerance_us;
+	unsigned int urgent_out_of_order_return_per_channel_pixel_only_bytes;
+	unsigned int urgent_out_of_order_return_per_channel_pixel_and_vm_bytes;
+	unsigned int urgent_out_of_order_return_per_channel_vm_only_bytes;
+	unsigned int round_trip_ping_latency_dcfclk_cycles;
+	unsigned int urgent_out_of_order_return_per_channel_bytes;
+	unsigned int channel_interleave_bytes;
+	unsigned int num_banks;
+	unsigned int num_chans;
+	unsigned int vmm_page_size_bytes;
+	double dram_clock_change_latency_us;
+	double writeback_dram_clock_change_latency_us;
+	unsigned int return_bus_width_bytes;
+	unsigned int voltage_override;
+	double xfc_bus_transport_time_us;
+	double xfc_xbuf_latency_tolerance_us;
+	int use_urgent_burst_bw;
 	struct _vcs_dpi_voltage_scaling_st clock_limits[7];
 };
 
-struct	_vcs_dpi_ip_params_st	{
-	unsigned int	max_inter_dcn_tile_repeaters;
-	unsigned int	num_dsc;
-	unsigned int	odm_capable;
-	unsigned int	rob_buffer_size_kbytes;
-	unsigned int	det_buffer_size_kbytes;
-	unsigned int	dpte_buffer_size_in_pte_reqs;
-	unsigned int	pde_proc_buffer_size_64k_reqs;
-	unsigned int	dpp_output_buffer_pixels;
-	unsigned int	opp_output_buffer_lines;
-	unsigned int	pixel_chunk_size_kbytes;
-	unsigned char	pte_enable;
-	unsigned int	pte_chunk_size_kbytes;
-	unsigned int	meta_chunk_size_kbytes;
-	unsigned int	writeback_chunk_size_kbytes;
-	unsigned int	line_buffer_size_bits;
-	unsigned int	max_line_buffer_lines;
-	unsigned int	writeback_luma_buffer_size_kbytes;
-	unsigned int	writeback_chroma_buffer_size_kbytes;
-	unsigned int	writeback_chroma_line_buffer_width_pixels;
-	unsigned int	max_page_table_levels;
-	unsigned int	max_num_dpp;
-	unsigned int	max_num_otg;
-	unsigned int	cursor_chunk_size;
-	unsigned int	cursor_buffer_size;
-	unsigned int	max_num_wb;
-	unsigned int	max_dchub_pscl_bw_pix_per_clk;
-	unsigned int	max_pscl_lb_bw_pix_per_clk;
-	unsigned int	max_lb_vscl_bw_pix_per_clk;
-	unsigned int	max_vscl_hscl_bw_pix_per_clk;
-	double	max_hscl_ratio;
-	double	max_vscl_ratio;
-	unsigned int	hscl_mults;
-	unsigned int	vscl_mults;
-	unsigned int	max_hscl_taps;
-	unsigned int	max_vscl_taps;
-	unsigned int	xfc_supported;
-	unsigned int	xfc_fill_constant_bytes;
-	double	dispclk_ramp_margin_percent;
-	double	xfc_fill_bw_overhead_percent;
-	double	underscan_factor;
-	unsigned int	min_vblank_lines;
-	unsigned int	dppclk_delay_subtotal;
-	unsigned int	dispclk_delay_subtotal;
-	unsigned int	dcfclk_cstate_latency;
-	unsigned int	dppclk_delay_scl;
-	unsigned int	dppclk_delay_scl_lb_only;
-	unsigned int	dppclk_delay_cnvc_formatter;
-	unsigned int	dppclk_delay_cnvc_cursor;
-	unsigned int	is_line_buffer_bpp_fixed;
-	unsigned int	line_buffer_fixed_bpp;
-	unsigned int	dcc_supported;
+struct _vcs_dpi_ip_params_st {
+	bool gpuvm_enable;
+	bool hostvm_enable;
+	unsigned int gpuvm_max_page_table_levels;
+	unsigned int hostvm_max_page_table_levels;
+	unsigned int hostvm_cached_page_table_levels;
+	unsigned int pte_group_size_bytes;
+	unsigned int max_inter_dcn_tile_repeaters;
+	unsigned int num_dsc;
+	unsigned int odm_capable;
+	unsigned int rob_buffer_size_kbytes;
+	unsigned int det_buffer_size_kbytes;
+	unsigned int dpte_buffer_size_in_pte_reqs;
+	unsigned int pde_proc_buffer_size_64k_reqs;
+	unsigned int dpp_output_buffer_pixels;
+	unsigned int opp_output_buffer_lines;
+	unsigned int pixel_chunk_size_kbytes;
+	unsigned char pte_enable;
+	unsigned int pte_chunk_size_kbytes;
+	unsigned int meta_chunk_size_kbytes;
+	unsigned int writeback_chunk_size_kbytes;
+	unsigned int line_buffer_size_bits;
+	unsigned int max_line_buffer_lines;
+	unsigned int writeback_luma_buffer_size_kbytes;
+	unsigned int writeback_chroma_buffer_size_kbytes;
+	unsigned int writeback_chroma_line_buffer_width_pixels;
+	unsigned int max_page_table_levels;
+	unsigned int max_num_dpp;
+	unsigned int max_num_otg;
+	unsigned int cursor_chunk_size;
+	unsigned int cursor_buffer_size;
+	unsigned int max_num_wb;
+	unsigned int max_dchub_pscl_bw_pix_per_clk;
+	unsigned int max_pscl_lb_bw_pix_per_clk;
+	unsigned int max_lb_vscl_bw_pix_per_clk;
+	unsigned int max_vscl_hscl_bw_pix_per_clk;
+	double max_hscl_ratio;
+	double max_vscl_ratio;
+	unsigned int hscl_mults;
+	unsigned int vscl_mults;
+	unsigned int max_hscl_taps;
+	unsigned int max_vscl_taps;
+	unsigned int xfc_supported;
+	unsigned int xfc_fill_constant_bytes;
+	double dispclk_ramp_margin_percent;
+	double xfc_fill_bw_overhead_percent;
+	double underscan_factor;
+	unsigned int min_vblank_lines;
+	unsigned int dppclk_delay_subtotal;
+	unsigned int dispclk_delay_subtotal;
+	unsigned int dcfclk_cstate_latency;
+	unsigned int dppclk_delay_scl;
+	unsigned int dppclk_delay_scl_lb_only;
+	unsigned int dppclk_delay_cnvc_formatter;
+	unsigned int dppclk_delay_cnvc_cursor;
+	unsigned int is_line_buffer_bpp_fixed;
+	unsigned int line_buffer_fixed_bpp;
+	unsigned int dcc_supported;
 
 	unsigned int IsLineBufferBppFixed;
 	unsigned int LineBufferFixedBpp;
@@ -169,41 +187,45 @@ struct _vcs_dpi_display_xfc_params_st {
 	int xfc_slv_chunk_size_bytes;
 };
 
-struct	_vcs_dpi_display_pipe_source_params_st	{
-	int	source_format;
-	unsigned char	dcc;
-	unsigned int	dcc_override;
-	unsigned int	dcc_rate;
-	unsigned char	dcc_use_global;
-	unsigned char	vm;
-	unsigned char	vm_levels_force_en;
-	unsigned int	vm_levels_force;
-	int	source_scan;
-	int	sw_mode;
-	int	macro_tile_size;
-	unsigned char	is_display_sw;
-	unsigned int	viewport_width;
-	unsigned int	viewport_height;
-	unsigned int	viewport_y_y;
-	unsigned int	viewport_y_c;
-	unsigned int	viewport_width_c;
-	unsigned int	viewport_height_c;
-	unsigned int	data_pitch;
-	unsigned int	data_pitch_c;
-	unsigned int	meta_pitch;
-	unsigned int	meta_pitch_c;
-	unsigned int	cur0_src_width;
-	int	cur0_bpp;
-	unsigned int	cur1_src_width;
-	int	cur1_bpp;
-	int	num_cursors;
-	unsigned char	is_hsplit;
-	unsigned char	dynamic_metadata_enable;
-	unsigned int	dynamic_metadata_lines_before_active;
-	unsigned int	dynamic_metadata_xmit_bytes;
-	unsigned int	hsplit_grp;
-	unsigned char	xfc_enable;
-	unsigned char	xfc_slave;
+struct _vcs_dpi_display_pipe_source_params_st {
+	int source_format;
+	unsigned char dcc;
+	unsigned int dcc_override;
+	unsigned int dcc_rate;
+	unsigned char dcc_use_global;
+	unsigned char vm;
+	bool gpuvm;    // gpuvm enabled
+	bool hostvm;    // hostvm enabled
+	bool gpuvm_levels_force_en;
+	unsigned int gpuvm_levels_force;
+	bool hostvm_levels_force_en;
+	unsigned int hostvm_levels_force;
+	int source_scan;
+	int sw_mode;
+	int macro_tile_size;
+	unsigned char is_display_sw;
+	unsigned int viewport_width;
+	unsigned int viewport_height;
+	unsigned int viewport_y_y;
+	unsigned int viewport_y_c;
+	unsigned int viewport_width_c;
+	unsigned int viewport_height_c;
+	unsigned int data_pitch;
+	unsigned int data_pitch_c;
+	unsigned int meta_pitch;
+	unsigned int meta_pitch_c;
+	unsigned int cur0_src_width;
+	int cur0_bpp;
+	unsigned int cur1_src_width;
+	int cur1_bpp;
+	int num_cursors;
+	unsigned char is_hsplit;
+	unsigned char dynamic_metadata_enable;
+	unsigned int dynamic_metadata_lines_before_active;
+	unsigned int dynamic_metadata_xmit_bytes;
+	unsigned int hsplit_grp;
+	unsigned char xfc_enable;
+	unsigned char xfc_slave;
 	struct _vcs_dpi_display_xfc_params_st xfc_params;
 };
 struct writeback_st {
@@ -215,338 +237,339 @@ struct writeback_st {
 	int wb_vtaps_luma;
 	int wb_htaps_chroma;
 	int wb_vtaps_chroma;
-	int wb_hratio;
-	int wb_vratio;
-};
-
-struct	_vcs_dpi_display_output_params_st	{
-	int	dp_lanes;
-	int	output_bpp;
-	int	dsc_enable;
-	int	wb_enable;
-	int	opp_input_bpc;
-	int	output_type;
-	int	output_format;
-	int	output_standard;
-	int	dsc_slices;
+	double wb_hratio;
+	double wb_vratio;
+};
+
+struct _vcs_dpi_display_output_params_st {
+	int dp_lanes;
+	int output_bpp;
+	int dsc_enable;
+	int wb_enable;
+	int num_active_wb;
+	int output_bpc;
+	int output_type;
+	int output_format;
+	int output_standard;
+	int dsc_slices;
 	struct writeback_st wb;
 };
 
-struct	_vcs_dpi_display_bandwidth_st	{
-	double	total_bw_consumed_gbps;
-	double	guaranteed_urgent_return_bw_gbps;
-};
-
-struct	_vcs_dpi_scaler_ratio_depth_st	{
-	double	hscl_ratio;
-	double	vscl_ratio;
-	double	hscl_ratio_c;
-	double	vscl_ratio_c;
-	double	vinit;
-	double	vinit_c;
-	double	vinit_bot;
-	double	vinit_bot_c;
-	int	lb_depth;
-	int	scl_enable;
-};
-
-struct	_vcs_dpi_scaler_taps_st	{
-	unsigned int	htaps;
-	unsigned int	vtaps;
-	unsigned int	htaps_c;
-	unsigned int	vtaps_c;
-};
-
-struct	_vcs_dpi_display_pipe_dest_params_st	{
-	unsigned int	recout_width;
-	unsigned int	recout_height;
-	unsigned int	full_recout_width;
-	unsigned int	full_recout_height;
-	unsigned int	hblank_start;
-	unsigned int	hblank_end;
-	unsigned int	vblank_start;
-	unsigned int	vblank_end;
-	unsigned int	htotal;
-	unsigned int	vtotal;
-	unsigned int	vactive;
-	unsigned int	hactive;
-	unsigned int	vstartup_start;
-	unsigned int	vupdate_offset;
-	unsigned int	vupdate_width;
-	unsigned int	vready_offset;
-	unsigned char	interlaced;
-	unsigned char	underscan;
-	double	pixel_rate_mhz;
-	unsigned char	synchronized_vblank_all_planes;
-	unsigned char	otg_inst;
-	unsigned char	odm_split_cnt;
-	unsigned char	odm_combine;
-};
-
-struct	_vcs_dpi_display_pipe_params_st	{
-	display_pipe_source_params_st	src;
-	display_pipe_dest_params_st	dest;
-	scaler_ratio_depth_st	scale_ratio_depth;
-	scaler_taps_st	scale_taps;
-};
-
-struct	_vcs_dpi_display_clocks_and_cfg_st	{
-	int	voltage;
-	double	dppclk_mhz;
-	double	refclk_mhz;
-	double	dispclk_mhz;
-	double	dcfclk_mhz;
-	double	socclk_mhz;
-};
-
-struct	_vcs_dpi_display_e2e_pipe_params_st	{
-	display_pipe_params_st	pipe;
-	display_output_params_st	dout;
-	display_clocks_and_cfg_st	clks_cfg;
-};
-
-struct	_vcs_dpi_dchub_buffer_sizing_st	{
-	unsigned int	swath_width_y;
-	unsigned int	swath_height_y;
-	unsigned int	swath_height_c;
-	unsigned int	detail_buffer_size_y;
-};
-
-struct	_vcs_dpi_watermarks_perf_st	{
-	double	stutter_eff_in_active_region_percent;
-	double	urgent_latency_supported_us;
-	double	non_urgent_latency_supported_us;
-	double	dram_clock_change_margin_us;
-	double	dram_access_eff_percent;
-};
-
-struct	_vcs_dpi_cstate_pstate_watermarks_st	{
-	double	cstate_exit_us;
-	double	cstate_enter_plus_exit_us;
-	double	pstate_change_us;
-};
-
-struct	_vcs_dpi_wm_calc_pipe_params_st	{
-	unsigned int	num_dpp;
-	int	voltage;
-	int	output_type;
-	double	dcfclk_mhz;
-	double	socclk_mhz;
-	double	dppclk_mhz;
-	double	pixclk_mhz;
-	unsigned char	interlace_en;
-	unsigned char	pte_enable;
-	unsigned char	dcc_enable;
-	double	dcc_rate;
-	double	bytes_per_pixel_c;
-	double	bytes_per_pixel_y;
-	unsigned int	swath_width_y;
-	unsigned int	swath_height_y;
-	unsigned int	swath_height_c;
-	unsigned int	det_buffer_size_y;
-	double	h_ratio;
-	double	v_ratio;
-	unsigned int	h_taps;
-	unsigned int	h_total;
-	unsigned int	v_total;
-	unsigned int	v_active;
-	unsigned int	e2e_index;
-	double	display_pipe_line_delivery_time;
-	double	read_bw;
-	unsigned int	lines_in_det_y;
-	unsigned int	lines_in_det_y_rounded_down_to_swath;
-	double	full_det_buffering_time;
-	double	dcfclk_deepsleep_mhz_per_plane;
-};
-
-struct	_vcs_dpi_vratio_pre_st	{
-	double	vratio_pre_l;
-	double	vratio_pre_c;
-};
-
-struct	_vcs_dpi_display_data_rq_misc_params_st	{
-	unsigned int	full_swath_bytes;
-	unsigned int	stored_swath_bytes;
-	unsigned int	blk256_height;
-	unsigned int	blk256_width;
-	unsigned int	req_height;
-	unsigned int	req_width;
-};
-
-struct	_vcs_dpi_display_data_rq_sizing_params_st	{
-	unsigned int	chunk_bytes;
-	unsigned int	min_chunk_bytes;
-	unsigned int	meta_chunk_bytes;
-	unsigned int	min_meta_chunk_bytes;
-	unsigned int	mpte_group_bytes;
-	unsigned int	dpte_group_bytes;
-};
-
-struct	_vcs_dpi_display_data_rq_dlg_params_st	{
-	unsigned int	swath_width_ub;
-	unsigned int	swath_height;
-	unsigned int	req_per_swath_ub;
-	unsigned int	meta_pte_bytes_per_frame_ub;
-	unsigned int	dpte_req_per_row_ub;
-	unsigned int	dpte_groups_per_row_ub;
-	unsigned int	dpte_row_height;
-	unsigned int	dpte_bytes_per_row_ub;
-	unsigned int	meta_chunks_per_row_ub;
-	unsigned int	meta_req_per_row_ub;
-	unsigned int	meta_row_height;
-	unsigned int	meta_bytes_per_row_ub;
-};
-
-struct	_vcs_dpi_display_cur_rq_dlg_params_st	{
-	unsigned char	enable;
-	unsigned int	swath_height;
-	unsigned int	req_per_line;
-};
-
-struct	_vcs_dpi_display_rq_dlg_params_st	{
-	display_data_rq_dlg_params_st	rq_l;
-	display_data_rq_dlg_params_st	rq_c;
-	display_cur_rq_dlg_params_st	rq_cur0;
-};
-
-struct	_vcs_dpi_display_rq_sizing_params_st	{
-	display_data_rq_sizing_params_st	rq_l;
-	display_data_rq_sizing_params_st	rq_c;
-};
-
-struct	_vcs_dpi_display_rq_misc_params_st	{
-	display_data_rq_misc_params_st	rq_l;
-	display_data_rq_misc_params_st	rq_c;
-};
-
-struct	_vcs_dpi_display_rq_params_st	{
-	unsigned char	yuv420;
-	unsigned char	yuv420_10bpc;
-	display_rq_misc_params_st	misc;
-	display_rq_sizing_params_st	sizing;
-	display_rq_dlg_params_st	dlg;
-};
-
-struct	_vcs_dpi_display_dlg_regs_st	{
-	unsigned int	refcyc_h_blank_end;
-	unsigned int	dlg_vblank_end;
-	unsigned int	min_dst_y_next_start;
-	unsigned int	refcyc_per_htotal;
-	unsigned int	refcyc_x_after_scaler;
-	unsigned int	dst_y_after_scaler;
-	unsigned int	dst_y_prefetch;
-	unsigned int	dst_y_per_vm_vblank;
-	unsigned int	dst_y_per_row_vblank;
-	unsigned int	dst_y_per_vm_flip;
-	unsigned int	dst_y_per_row_flip;
-	unsigned int	ref_freq_to_pix_freq;
-	unsigned int	vratio_prefetch;
-	unsigned int	vratio_prefetch_c;
-	unsigned int	refcyc_per_pte_group_vblank_l;
-	unsigned int	refcyc_per_pte_group_vblank_c;
-	unsigned int	refcyc_per_meta_chunk_vblank_l;
-	unsigned int	refcyc_per_meta_chunk_vblank_c;
-	unsigned int	refcyc_per_pte_group_flip_l;
-	unsigned int	refcyc_per_pte_group_flip_c;
-	unsigned int	refcyc_per_meta_chunk_flip_l;
-	unsigned int	refcyc_per_meta_chunk_flip_c;
-	unsigned int	dst_y_per_pte_row_nom_l;
-	unsigned int	dst_y_per_pte_row_nom_c;
-	unsigned int	refcyc_per_pte_group_nom_l;
-	unsigned int	refcyc_per_pte_group_nom_c;
-	unsigned int	dst_y_per_meta_row_nom_l;
-	unsigned int	dst_y_per_meta_row_nom_c;
-	unsigned int	refcyc_per_meta_chunk_nom_l;
-	unsigned int	refcyc_per_meta_chunk_nom_c;
-	unsigned int	refcyc_per_line_delivery_pre_l;
-	unsigned int	refcyc_per_line_delivery_pre_c;
-	unsigned int	refcyc_per_line_delivery_l;
-	unsigned int	refcyc_per_line_delivery_c;
-	unsigned int	chunk_hdl_adjust_cur0;
-	unsigned int	chunk_hdl_adjust_cur1;
-	unsigned int	vready_after_vcount0;
-	unsigned int	dst_y_offset_cur0;
-	unsigned int	dst_y_offset_cur1;
-	unsigned int	xfc_reg_transfer_delay;
-	unsigned int	xfc_reg_precharge_delay;
-	unsigned int	xfc_reg_remote_surface_flip_latency;
-	unsigned int	xfc_reg_prefetch_margin;
-	unsigned int	dst_y_delta_drq_limit;
-};
-
-struct	_vcs_dpi_display_ttu_regs_st	{
-	unsigned int	qos_level_low_wm;
-	unsigned int	qos_level_high_wm;
-	unsigned int	min_ttu_vblank;
-	unsigned int	qos_level_flip;
-	unsigned int	refcyc_per_req_delivery_l;
-	unsigned int	refcyc_per_req_delivery_c;
-	unsigned int	refcyc_per_req_delivery_cur0;
-	unsigned int	refcyc_per_req_delivery_cur1;
-	unsigned int	refcyc_per_req_delivery_pre_l;
-	unsigned int	refcyc_per_req_delivery_pre_c;
-	unsigned int	refcyc_per_req_delivery_pre_cur0;
-	unsigned int	refcyc_per_req_delivery_pre_cur1;
-	unsigned int	qos_level_fixed_l;
-	unsigned int	qos_level_fixed_c;
-	unsigned int	qos_level_fixed_cur0;
-	unsigned int	qos_level_fixed_cur1;
-	unsigned int	qos_ramp_disable_l;
-	unsigned int	qos_ramp_disable_c;
-	unsigned int	qos_ramp_disable_cur0;
-	unsigned int	qos_ramp_disable_cur1;
-};
-
-struct	_vcs_dpi_display_data_rq_regs_st	{
-	unsigned int	chunk_size;
-	unsigned int	min_chunk_size;
-	unsigned int	meta_chunk_size;
-	unsigned int	min_meta_chunk_size;
-	unsigned int	dpte_group_size;
-	unsigned int	mpte_group_size;
-	unsigned int	swath_height;
-	unsigned int	pte_row_height_linear;
-};
-
-struct	_vcs_dpi_display_rq_regs_st	{
-	display_data_rq_regs_st	rq_regs_l;
-	display_data_rq_regs_st	rq_regs_c;
-	unsigned int	drq_expansion_mode;
-	unsigned int	prq_expansion_mode;
-	unsigned int	mrq_expansion_mode;
-	unsigned int	crq_expansion_mode;
-	unsigned int	plane1_base_address;
-};
-
-struct	_vcs_dpi_display_dlg_sys_params_st	{
-	double	t_mclk_wm_us;
-	double	t_urg_wm_us;
-	double	t_sr_wm_us;
-	double	t_extra_us;
-	double	mem_trip_us;
-	double	t_srx_delay_us;
-	double	deepsleep_dcfclk_mhz;
-	double	total_flip_bw;
-	unsigned int	total_flip_bytes;
-};
-
-struct	_vcs_dpi_display_dlg_prefetch_param_st	{
-	double	prefetch_bw;
-	unsigned int	flip_bytes;
-};
-
-struct	_vcs_dpi_display_pipe_clock_st	{
-	double	dcfclk_mhz;
-	double	dispclk_mhz;
-	double	socclk_mhz;
-	double	dscclk_mhz[6];
-	double	dppclk_mhz[6];
-};
-
-struct	_vcs_dpi_display_arb_params_st	{
-	int	max_req_outstanding;
-	int	min_req_outstanding;
-	int	sat_level_us;
+struct _vcs_dpi_display_bandwidth_st {
+	double total_bw_consumed_gbps;
+	double guaranteed_urgent_return_bw_gbps;
+};
+
+struct _vcs_dpi_scaler_ratio_depth_st {
+	double hscl_ratio;
+	double vscl_ratio;
+	double hscl_ratio_c;
+	double vscl_ratio_c;
+	double vinit;
+	double vinit_c;
+	double vinit_bot;
+	double vinit_bot_c;
+	int lb_depth;
+	int scl_enable;
+};
+
+struct _vcs_dpi_scaler_taps_st {
+	unsigned int htaps;
+	unsigned int vtaps;
+	unsigned int htaps_c;
+	unsigned int vtaps_c;
+};
+
+struct _vcs_dpi_display_pipe_dest_params_st {
+	unsigned int recout_width;
+	unsigned int recout_height;
+	unsigned int full_recout_width;
+	unsigned int full_recout_height;
+	unsigned int hblank_start;
+	unsigned int hblank_end;
+	unsigned int vblank_start;
+	unsigned int vblank_end;
+	unsigned int htotal;
+	unsigned int vtotal;
+	unsigned int vactive;
+	unsigned int hactive;
+	unsigned int vstartup_start;
+	unsigned int vupdate_offset;
+	unsigned int vupdate_width;
+	unsigned int vready_offset;
+	unsigned char interlaced;
+	unsigned char underscan;
+	double pixel_rate_mhz;
+	unsigned char synchronized_vblank_all_planes;
+	unsigned char otg_inst;
+	unsigned char odm_split_cnt;
+	unsigned char odm_combine;
+};
+
+struct _vcs_dpi_display_pipe_params_st {
+	display_pipe_source_params_st src;
+	display_pipe_dest_params_st dest;
+	scaler_ratio_depth_st scale_ratio_depth;
+	scaler_taps_st scale_taps;
+};
+
+struct _vcs_dpi_display_clocks_and_cfg_st {
+	int voltage;
+	double dppclk_mhz;
+	double refclk_mhz;
+	double dispclk_mhz;
+	double dcfclk_mhz;
+	double socclk_mhz;
+};
+
+struct _vcs_dpi_display_e2e_pipe_params_st {
+	display_pipe_params_st pipe;
+	display_output_params_st dout;
+	display_clocks_and_cfg_st clks_cfg;
+};
+
+struct _vcs_dpi_dchub_buffer_sizing_st {
+	unsigned int swath_width_y;
+	unsigned int swath_height_y;
+	unsigned int swath_height_c;
+	unsigned int detail_buffer_size_y;
+};
+
+struct _vcs_dpi_watermarks_perf_st {
+	double stutter_eff_in_active_region_percent;
+	double urgent_latency_supported_us;
+	double non_urgent_latency_supported_us;
+	double dram_clock_change_margin_us;
+	double dram_access_eff_percent;
+};
+
+struct _vcs_dpi_cstate_pstate_watermarks_st {
+	double cstate_exit_us;
+	double cstate_enter_plus_exit_us;
+	double pstate_change_us;
+};
+
+struct _vcs_dpi_wm_calc_pipe_params_st {
+	unsigned int num_dpp;
+	int voltage;
+	int output_type;
+	double dcfclk_mhz;
+	double socclk_mhz;
+	double dppclk_mhz;
+	double pixclk_mhz;
+	unsigned char interlace_en;
+	unsigned char pte_enable;
+	unsigned char dcc_enable;
+	double dcc_rate;
+	double bytes_per_pixel_c;
+	double bytes_per_pixel_y;
+	unsigned int swath_width_y;
+	unsigned int swath_height_y;
+	unsigned int swath_height_c;
+	unsigned int det_buffer_size_y;
+	double h_ratio;
+	double v_ratio;
+	unsigned int h_taps;
+	unsigned int h_total;
+	unsigned int v_total;
+	unsigned int v_active;
+	unsigned int e2e_index;
+	double display_pipe_line_delivery_time;
+	double read_bw;
+	unsigned int lines_in_det_y;
+	unsigned int lines_in_det_y_rounded_down_to_swath;
+	double full_det_buffering_time;
+	double dcfclk_deepsleep_mhz_per_plane;
+};
+
+struct _vcs_dpi_vratio_pre_st {
+	double vratio_pre_l;
+	double vratio_pre_c;
+};
+
+struct _vcs_dpi_display_data_rq_misc_params_st {
+	unsigned int full_swath_bytes;
+	unsigned int stored_swath_bytes;
+	unsigned int blk256_height;
+	unsigned int blk256_width;
+	unsigned int req_height;
+	unsigned int req_width;
+};
+
+struct _vcs_dpi_display_data_rq_sizing_params_st {
+	unsigned int chunk_bytes;
+	unsigned int min_chunk_bytes;
+	unsigned int meta_chunk_bytes;
+	unsigned int min_meta_chunk_bytes;
+	unsigned int mpte_group_bytes;
+	unsigned int dpte_group_bytes;
+};
+
+struct _vcs_dpi_display_data_rq_dlg_params_st {
+	unsigned int swath_width_ub;
+	unsigned int swath_height;
+	unsigned int req_per_swath_ub;
+	unsigned int meta_pte_bytes_per_frame_ub;
+	unsigned int dpte_req_per_row_ub;
+	unsigned int dpte_groups_per_row_ub;
+	unsigned int dpte_row_height;
+	unsigned int dpte_bytes_per_row_ub;
+	unsigned int meta_chunks_per_row_ub;
+	unsigned int meta_req_per_row_ub;
+	unsigned int meta_row_height;
+	unsigned int meta_bytes_per_row_ub;
+};
+
+struct _vcs_dpi_display_cur_rq_dlg_params_st {
+	unsigned char enable;
+	unsigned int swath_height;
+	unsigned int req_per_line;
+};
+
+struct _vcs_dpi_display_rq_dlg_params_st {
+	display_data_rq_dlg_params_st rq_l;
+	display_data_rq_dlg_params_st rq_c;
+	display_cur_rq_dlg_params_st rq_cur0;
+};
+
+struct _vcs_dpi_display_rq_sizing_params_st {
+	display_data_rq_sizing_params_st rq_l;
+	display_data_rq_sizing_params_st rq_c;
+};
+
+struct _vcs_dpi_display_rq_misc_params_st {
+	display_data_rq_misc_params_st rq_l;
+	display_data_rq_misc_params_st rq_c;
+};
+
+struct _vcs_dpi_display_rq_params_st {
+	unsigned char yuv420;
+	unsigned char yuv420_10bpc;
+	display_rq_misc_params_st misc;
+	display_rq_sizing_params_st sizing;
+	display_rq_dlg_params_st dlg;
+};
+
+struct _vcs_dpi_display_dlg_regs_st {
+	unsigned int refcyc_h_blank_end;
+	unsigned int dlg_vblank_end;
+	unsigned int min_dst_y_next_start;
+	unsigned int refcyc_per_htotal;
+	unsigned int refcyc_x_after_scaler;
+	unsigned int dst_y_after_scaler;
+	unsigned int dst_y_prefetch;
+	unsigned int dst_y_per_vm_vblank;
+	unsigned int dst_y_per_row_vblank;
+	unsigned int dst_y_per_vm_flip;
+	unsigned int dst_y_per_row_flip;
+	unsigned int ref_freq_to_pix_freq;
+	unsigned int vratio_prefetch;
+	unsigned int vratio_prefetch_c;
+	unsigned int refcyc_per_pte_group_vblank_l;
+	unsigned int refcyc_per_pte_group_vblank_c;
+	unsigned int refcyc_per_meta_chunk_vblank_l;
+	unsigned int refcyc_per_meta_chunk_vblank_c;
+	unsigned int refcyc_per_pte_group_flip_l;
+	unsigned int refcyc_per_pte_group_flip_c;
+	unsigned int refcyc_per_meta_chunk_flip_l;
+	unsigned int refcyc_per_meta_chunk_flip_c;
+	unsigned int dst_y_per_pte_row_nom_l;
+	unsigned int dst_y_per_pte_row_nom_c;
+	unsigned int refcyc_per_pte_group_nom_l;
+	unsigned int refcyc_per_pte_group_nom_c;
+	unsigned int dst_y_per_meta_row_nom_l;
+	unsigned int dst_y_per_meta_row_nom_c;
+	unsigned int refcyc_per_meta_chunk_nom_l;
+	unsigned int refcyc_per_meta_chunk_nom_c;
+	unsigned int refcyc_per_line_delivery_pre_l;
+	unsigned int refcyc_per_line_delivery_pre_c;
+	unsigned int refcyc_per_line_delivery_l;
+	unsigned int refcyc_per_line_delivery_c;
+	unsigned int chunk_hdl_adjust_cur0;
+	unsigned int chunk_hdl_adjust_cur1;
+	unsigned int vready_after_vcount0;
+	unsigned int dst_y_offset_cur0;
+	unsigned int dst_y_offset_cur1;
+	unsigned int xfc_reg_transfer_delay;
+	unsigned int xfc_reg_precharge_delay;
+	unsigned int xfc_reg_remote_surface_flip_latency;
+	unsigned int xfc_reg_prefetch_margin;
+	unsigned int dst_y_delta_drq_limit;
+};
+
+struct _vcs_dpi_display_ttu_regs_st {
+	unsigned int qos_level_low_wm;
+	unsigned int qos_level_high_wm;
+	unsigned int min_ttu_vblank;
+	unsigned int qos_level_flip;
+	unsigned int refcyc_per_req_delivery_l;
+	unsigned int refcyc_per_req_delivery_c;
+	unsigned int refcyc_per_req_delivery_cur0;
+	unsigned int refcyc_per_req_delivery_cur1;
+	unsigned int refcyc_per_req_delivery_pre_l;
+	unsigned int refcyc_per_req_delivery_pre_c;
+	unsigned int refcyc_per_req_delivery_pre_cur0;
+	unsigned int refcyc_per_req_delivery_pre_cur1;
+	unsigned int qos_level_fixed_l;
+	unsigned int qos_level_fixed_c;
+	unsigned int qos_level_fixed_cur0;
+	unsigned int qos_level_fixed_cur1;
+	unsigned int qos_ramp_disable_l;
+	unsigned int qos_ramp_disable_c;
+	unsigned int qos_ramp_disable_cur0;
+	unsigned int qos_ramp_disable_cur1;
+};
+
+struct _vcs_dpi_display_data_rq_regs_st {
+	unsigned int chunk_size;
+	unsigned int min_chunk_size;
+	unsigned int meta_chunk_size;
+	unsigned int min_meta_chunk_size;
+	unsigned int dpte_group_size;
+	unsigned int mpte_group_size;
+	unsigned int swath_height;
+	unsigned int pte_row_height_linear;
+};
+
+struct _vcs_dpi_display_rq_regs_st {
+	display_data_rq_regs_st rq_regs_l;
+	display_data_rq_regs_st rq_regs_c;
+	unsigned int drq_expansion_mode;
+	unsigned int prq_expansion_mode;
+	unsigned int mrq_expansion_mode;
+	unsigned int crq_expansion_mode;
+	unsigned int plane1_base_address;
+};
+
+struct _vcs_dpi_display_dlg_sys_params_st {
+	double t_mclk_wm_us;
+	double t_urg_wm_us;
+	double t_sr_wm_us;
+	double t_extra_us;
+	double mem_trip_us;
+	double t_srx_delay_us;
+	double deepsleep_dcfclk_mhz;
+	double total_flip_bw;
+	unsigned int total_flip_bytes;
+};
+
+struct _vcs_dpi_display_dlg_prefetch_param_st {
+	double prefetch_bw;
+	unsigned int flip_bytes;
+};
+
+struct _vcs_dpi_display_pipe_clock_st {
+	double dcfclk_mhz;
+	double dispclk_mhz;
+	double socclk_mhz;
+	double dscclk_mhz[6];
+	double dppclk_mhz[6];
+};
+
+struct _vcs_dpi_display_arb_params_st {
+	int max_req_outstanding;
+	int min_req_outstanding;
+	int sat_level_us;
 };
 
 #endif /*__DISPLAY_MODE_STRUCTS_H__*/
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
index f9cf08357989..e8ce08567cd8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
@@ -35,6 +35,16 @@ static inline double dml_min(double a, double b)
 	return (double) dcn_bw_min2(a, b);
 }
 
+static inline double dml_min3(double a, double b, double c)
+{
+	return dml_min(dml_min(a, b), c);
+}
+
+static inline double dml_min4(double a, double b, double c, double d)
+{
+	return dml_min(dml_min(a, b), dml_min(c, d));
+}
+
 static inline double dml_max(double a, double b)
 {
 	return (double) dcn_bw_max2(a, b);
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
index 87b580fa4bc9..0caee3523017 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
@@ -75,6 +75,7 @@ bool dal_hw_factory_init(
 		return true;
 	case DCE_VERSION_11_0:
 	case DCE_VERSION_11_2:
+	case DCE_VERSION_11_22:
 		dal_hw_factory_dce110_init(factory);
 		return true;
 	case DCE_VERSION_12_0:
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
index 0ae8ace25739..55c707488541 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
@@ -72,6 +72,7 @@ bool dal_hw_translate_init(
 	case DCE_VERSION_10_0:
 	case DCE_VERSION_11_0:
 	case DCE_VERSION_11_2:
+	case DCE_VERSION_11_22:
 		dal_hw_translate_dce110_init(translate);
 		return true;
 	case DCE_VERSION_12_0:
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
index abd0095ced30..b7256f595052 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
@@ -527,7 +527,7 @@ static void construct(
 	REG_GET(MICROSECOND_TIME_BASE_DIV, XTAL_REF_DIV, &xtal_ref_div);
 
 	if (xtal_ref_div == 0) {
-		DC_LOG_WARNING("Invalid base timer divider\n",
+		DC_LOG_WARNING("Invalid base timer divider [%s]\n",
 				__func__);
 		xtal_ref_div = 2;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
index 5cbf6626b8d4..14dc8c94d862 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
@@ -83,6 +83,7 @@ struct i2caux *dal_i2caux_create(
 	case DCE_VERSION_8_3:
 		return dal_i2caux_dce80_create(ctx);
 	case DCE_VERSION_11_2:
+	case DCE_VERSION_11_22:
 		return dal_i2caux_dce112_create(ctx);
 	case DCE_VERSION_11_0:
 		return dal_i2caux_dce110_create(ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 8c51ad70cace..a94942d4e66b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -95,11 +95,6 @@ struct resource_funcs {
 	struct link_encoder *(*link_enc_create)(
 			const struct encoder_init_data *init);
 
-	enum dc_status (*validate_guaranteed)(
-					struct dc *dc,
-					struct dc_stream_state *stream,
-					struct dc_state *context);
-
 	bool (*validate_bandwidth)(
 					struct dc *dc,
 					struct dc_state *context);
@@ -250,6 +245,7 @@ struct dce_bw_output {
 	bool all_displays_in_sync;
 	struct dce_watermarks urgent_wm_ns[MAX_PIPES];
 	struct dce_watermarks stutter_exit_wm_ns[MAX_PIPES];
+	struct dce_watermarks stutter_entry_wm_ns[MAX_PIPES];
 	struct dce_watermarks nbp_state_change_wm_ns[MAX_PIPES];
 	int sclk_khz;
 	int sclk_deep_sleep_khz;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 090b7a8dd67b..30b3a08b91be 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -102,13 +102,14 @@ bool dal_ddc_service_query_ddc_data(
 		uint8_t *read_buf,
 		uint32_t read_size);
 
-ssize_t dal_ddc_service_read_dpcd_data(
+enum ddc_result dal_ddc_service_read_dpcd_data(
 		struct ddc_service *ddc,
 		bool i2c,
 		enum i2c_mot_mode mot,
 		uint32_t address,
 		uint8_t *data,
-		uint32_t len);
+		uint32_t len,
+		uint32_t *read);
 
 enum ddc_result dal_ddc_service_write_dpcd_data(
 		struct ddc_service *ddc,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dce_calcs.h b/drivers/gpu/drm/amd/display/dc/inc/dce_calcs.h
index a9bfe9ff8ce6..eece165206f9 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dce_calcs.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dce_calcs.h
@@ -42,6 +42,8 @@ enum bw_calcs_version {
 	BW_CALCS_VERSION_CARRIZO,
 	BW_CALCS_VERSION_POLARIS10,
 	BW_CALCS_VERSION_POLARIS11,
+	BW_CALCS_VERSION_POLARIS12,
+	BW_CALCS_VERSION_VEGAM,
 	BW_CALCS_VERSION_STONEY,
 	BW_CALCS_VERSION_VEGA10
 };
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
new file mode 100644
index 000000000000..02f757dd70d4
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_DCHUBBUB_H__
+#define __DAL_DCHUBBUB_H__
+
+
+enum dcc_control {
+	dcc_control__256_256_xxx,
+	dcc_control__128_128_xxx,
+	dcc_control__256_64_64,
+};
+
+enum segment_order {
+	segment_order__na,
+	segment_order__contiguous,
+	segment_order__non_contiguous,
+};
+
+
+struct hubbub_funcs {
+	void (*update_dchub)(
+			struct hubbub *hubbub,
+			struct dchub_init_data *dh_data);
+
+	bool (*get_dcc_compression_cap)(struct hubbub *hubbub,
+			const struct dc_dcc_surface_param *input,
+			struct dc_surface_dcc_cap *output);
+
+	bool (*dcc_support_swizzle)(
+			enum swizzle_mode_values swizzle,
+			unsigned int bytes_per_element,
+			enum segment_order *segment_order_horz,
+			enum segment_order *segment_order_vert);
+
+	bool (*dcc_support_pixel_format)(
+			enum surface_pixel_format format,
+			unsigned int *bytes_per_element);
+};
+
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 99995608b620..582458f028f8 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -44,7 +44,23 @@ struct dpp_grph_csc_adjustment {
 	enum graphics_gamut_adjust_type gamut_adjust_type;
 };
 
+struct dcn_dpp_state {
+	uint32_t igam_lut_mode;
+	uint32_t igam_input_format;
+	uint32_t dgam_lut_mode;
+	uint32_t rgam_lut_mode;
+	uint32_t gamut_remap_mode;
+	uint32_t gamut_remap_c11_c12;
+	uint32_t gamut_remap_c13_c14;
+	uint32_t gamut_remap_c21_c22;
+	uint32_t gamut_remap_c23_c24;
+	uint32_t gamut_remap_c31_c32;
+	uint32_t gamut_remap_c33_c34;
+};
+
 struct dpp_funcs {
+	void (*dpp_read_state)(struct dpp *dpp, struct dcn_dpp_state *s);
+
 	void (*dpp_reset)(struct dpp *dpp);
 
 	void (*dpp_set_scaler)(struct dpp *dpp,
@@ -117,7 +133,7 @@ struct dpp_funcs {
 			struct dpp *dpp_base,
 			enum surface_pixel_format format,
 			enum expansion_mode mode,
-			struct csc_transform input_csc_color_matrix,
+			struct dc_csc_transform input_csc_color_matrix,
 			enum dc_color_space input_color_space);
 
 	void (*dpp_full_bypass)(struct dpp *dpp_base);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 9ced254e652c..97df82cddf82 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -56,7 +56,6 @@ struct hubp {
 	bool power_gated;
 };
 
-
 struct hubp_funcs {
 	void (*hubp_setup)(
 			struct hubp *hubp,
@@ -121,6 +120,9 @@ struct hubp_funcs {
 
 	void (*hubp_clk_cntl)(struct hubp *hubp, bool enable);
 	void (*hubp_vtg_sel)(struct hubp *hubp, uint32_t otg_inst);
+	void (*hubp_read_state)(struct hubp *hubp);
+	void (*hubp_disable_control)(struct hubp *hubp, bool disable_hubp);
+	unsigned int (*hubp_get_underflow_status)(struct hubp *hubp);
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
index b22158190262..cf7433ebf91a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
@@ -140,11 +140,6 @@ enum opp_regamma {
 	OPP_REGAMMA_USER
 };
 
-struct csc_transform {
-	uint16_t matrix[12];
-	bool enable_adjustment;
-};
-
 struct dc_bias_and_scale {
 	uint16_t scale_red;
 	uint16_t bias_red;
@@ -191,4 +186,9 @@ enum controller_dp_test_pattern {
 	CONTROLLER_DP_TEST_PATTERN_COLORSQUARES_CEA
 };
 
+enum dc_lut_mode {
+	LUT_BYPASS,
+	LUT_RAM_A,
+	LUT_RAM_B
+};
 #endif /* __DAL_HW_SHARED_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/ipp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/ipp.h
index 2109eac20a3d..b2fa4c4cd920 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/ipp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/ipp.h
@@ -87,7 +87,7 @@ struct ipp_funcs {
 		struct input_pixel_processor *ipp,
 		enum surface_pixel_format format,
 		enum expansion_mode mode,
-		struct csc_transform input_csc_color_matrix,
+		struct dc_csc_transform input_csc_color_matrix,
 		enum dc_color_space input_color_space);
 
 	/* DCE function to setup IPP.  TODO: see if we can consolidate to setup */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
index 54d8a1386142..cf6df2e7beb2 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
@@ -149,6 +149,7 @@ struct link_encoder_funcs {
 		bool connect);
 	void (*enable_hpd)(struct link_encoder *enc);
 	void (*disable_hpd)(struct link_encoder *enc);
+	bool (*is_dig_enabled)(struct link_encoder *enc);
 	void (*destroy)(struct link_encoder **enc);
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
index 3e1e7e6a8792..47f1dc5a43b7 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
@@ -104,6 +104,7 @@ struct mem_input_funcs {
 		struct mem_input *mem_input,
 		struct dce_watermarks nbp,
 		struct dce_watermarks stutter,
+		struct dce_watermarks stutter_enter,
 		struct dce_watermarks urgent,
 		uint32_t total_dest_line_time_ns);
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 23a8d5e53a89..caf74e3c836f 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -105,7 +105,24 @@ struct mpc {
 	struct mpcc mpcc_array[MAX_MPCC];
 };
 
+struct mpcc_state {
+	uint32_t opp_id;
+	uint32_t dpp_id;
+	uint32_t bot_mpcc_id;
+	uint32_t mode;
+	uint32_t alpha_mode;
+	uint32_t pre_multiplied_alpha;
+	uint32_t overlap_only;
+	uint32_t idle;
+	uint32_t busy;
+};
+
 struct mpc_funcs {
+	void (*read_mpcc_state)(
+			struct mpc *mpc,
+			int mpcc_inst,
+			struct mpcc_state *s);
+
 	/*
 	 * Insert DPP into MPC tree based on specified blending position.
 	 * Only used for planes that are part of blending chain for OPP output
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
index b5db1692393c..cfa7ec9517ae 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
@@ -29,31 +29,40 @@
 #define STREAM_ENCODER_H_
 
 #include "audio_types.h"
+#include "hw_shared.h"
 
 struct dc_bios;
 struct dc_context;
 struct dc_crtc_timing;
 
-struct encoder_info_packet {
-	bool valid;
-	uint8_t hb0;
-	uint8_t hb1;
-	uint8_t hb2;
-	uint8_t hb3;
-	uint8_t sb[32];
+enum dp_pixel_encoding_type {
+	DP_PIXEL_ENCODING_TYPE_RGB444		= 0x00000000,
+	DP_PIXEL_ENCODING_TYPE_YCBCR422		= 0x00000001,
+	DP_PIXEL_ENCODING_TYPE_YCBCR444		= 0x00000002,
+	DP_PIXEL_ENCODING_TYPE_RGB_WIDE_GAMUT	= 0x00000003,
+	DP_PIXEL_ENCODING_TYPE_Y_ONLY		= 0x00000004,
+	DP_PIXEL_ENCODING_TYPE_YCBCR420		= 0x00000005
+};
+
+enum dp_component_depth {
+	DP_COMPONENT_PIXEL_DEPTH_6BPC		= 0x00000000,
+	DP_COMPONENT_PIXEL_DEPTH_8BPC		= 0x00000001,
+	DP_COMPONENT_PIXEL_DEPTH_10BPC		= 0x00000002,
+	DP_COMPONENT_PIXEL_DEPTH_12BPC		= 0x00000003,
+	DP_COMPONENT_PIXEL_DEPTH_16BPC		= 0x00000004
 };
 
 struct encoder_info_frame {
 	/* auxiliary video information */
-	struct encoder_info_packet avi;
-	struct encoder_info_packet gamut;
-	struct encoder_info_packet vendor;
+	struct dc_info_packet avi;
+	struct dc_info_packet gamut;
+	struct dc_info_packet vendor;
 	/* source product description */
-	struct encoder_info_packet spd;
+	struct dc_info_packet spd;
 	/* video stream configuration */
-	struct encoder_info_packet vsc;
+	struct dc_info_packet vsc;
 	/* HDR Static MetaData */
-	struct encoder_info_packet hdrsmd;
+	struct dc_info_packet hdrsmd;
 };
 
 struct encoder_unblank_param {
@@ -147,6 +156,7 @@ struct stream_encoder_funcs {
 
 	void (*set_avmute)(
 		struct stream_encoder *enc, bool enable);
+
 };
 
 #endif /* STREAM_ENCODER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index 3217b5bf6c7a..69cb0a105300 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -140,6 +140,9 @@ struct timing_generator_funcs {
 	void (*program_timing)(struct timing_generator *tg,
 							const struct dc_crtc_timing *timing,
 							bool use_vbios);
+	void (*program_vline_interrupt)(struct timing_generator *optc,
+			const struct dc_crtc_timing *dc_crtc_timing,
+			unsigned long long vsync_delta);
 	bool (*enable_crtc)(struct timing_generator *tg);
 	bool (*disable_crtc)(struct timing_generator *tg);
 	bool (*is_counter_moving)(struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
index c5b3623bcbd9..fecc80c47c26 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
@@ -252,7 +252,7 @@ struct transform_funcs {
 			struct transform *xfm_base,
 			enum surface_pixel_format format,
 			enum expansion_mode mode,
-			struct csc_transform input_csc_color_matrix,
+			struct dc_csc_transform input_csc_color_matrix,
 			enum dc_color_space input_color_space);
 
 	void (*ipp_full_bypass)(struct transform *xfm_base);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index e764cbad881b..63fc6c499789 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -32,6 +32,8 @@
 #include "inc/hw/link_encoder.h"
 #include "core_status.h"
 
+#define EDP_BACKLIGHT_RAMP_DISABLE_LEVEL 0xFFFFFFFF
+
 enum pipe_gating_control {
 	PIPE_GATING_CONTROL_DISABLE = 0,
 	PIPE_GATING_CONTROL_ENABLE,
@@ -63,6 +65,7 @@ struct dchub_init_data;
 struct dc_static_screen_events;
 struct resource_pool;
 struct resource_context;
+struct stream_resource;
 
 struct hw_sequencer_funcs {
 
@@ -80,11 +83,6 @@ struct hw_sequencer_funcs {
 			int num_planes,
 			struct dc_state *context);
 
-	void (*set_plane_config)(
-			const struct dc *dc,
-			struct pipe_ctx *pipe_ctx,
-			struct resource_context *res_ctx);
-
 	void (*program_gamut_remap)(
 			struct pipe_ctx *pipe_ctx);
 
@@ -93,6 +91,12 @@ struct hw_sequencer_funcs {
 			enum dc_color_space colorspace,
 			uint16_t *matrix);
 
+	void (*program_output_csc)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			enum dc_color_space colorspace,
+			uint16_t *matrix,
+			int opp_id);
+
 	void (*update_plane_addr)(
 		const struct dc *dc,
 		struct pipe_ctx *pipe_ctx);
@@ -154,6 +158,11 @@ struct hw_sequencer_funcs {
 				struct dc *dc,
 				struct pipe_ctx *pipe,
 				bool lock);
+	void (*blank_pixel_data)(
+			struct dc *dc,
+			struct stream_resource *stream_res,
+			struct dc_stream_state *stream,
+			bool blank);
 
 	void (*set_bandwidth)(
 			struct dc *dc,
@@ -169,7 +178,7 @@ struct hw_sequencer_funcs {
 	void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx,
 			int num_pipes, const struct dc_static_screen_events *events);
 
-	enum dc_status (*prog_pixclk_crtc_otg)(
+	enum dc_status (*enable_stream_timing)(
 			struct pipe_ctx *pipe_ctx,
 			struct dc_state *context,
 			struct dc *dc);
@@ -201,6 +210,7 @@ struct hw_sequencer_funcs {
 
 	void (*set_cursor_position)(struct pipe_ctx *pipe);
 	void (*set_cursor_attribute)(struct pipe_ctx *pipe);
+
 };
 
 void color_space_to_black_color(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
index 77eb72874e90..3306e7b0b3e3 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
@@ -183,6 +183,36 @@
 				FN(reg_name, f4), v4, \
 				FN(reg_name, f5), v5)
 
+#define REG_GET_6(reg_name, f1, v1, f2, v2, f3, v3, f4, v4, f5, v5, f6, v6)	\
+		generic_reg_get6(CTX, REG(reg_name), \
+				FN(reg_name, f1), v1, \
+				FN(reg_name, f2), v2, \
+				FN(reg_name, f3), v3, \
+				FN(reg_name, f4), v4, \
+				FN(reg_name, f5), v5, \
+				FN(reg_name, f6), v6)
+
+#define REG_GET_7(reg_name, f1, v1, f2, v2, f3, v3, f4, v4, f5, v5, f6, v6, f7, v7)	\
+		generic_reg_get7(CTX, REG(reg_name), \
+				FN(reg_name, f1), v1, \
+				FN(reg_name, f2), v2, \
+				FN(reg_name, f3), v3, \
+				FN(reg_name, f4), v4, \
+				FN(reg_name, f5), v5, \
+				FN(reg_name, f6), v6, \
+				FN(reg_name, f7), v7)
+
+#define REG_GET_8(reg_name, f1, v1, f2, v2, f3, v3, f4, v4, f5, v5, f6, v6, f7, v7, f8, v8)	\
+		generic_reg_get8(CTX, REG(reg_name), \
+				FN(reg_name, f1), v1, \
+				FN(reg_name, f2), v2, \
+				FN(reg_name, f3), v3, \
+				FN(reg_name, f4), v4, \
+				FN(reg_name, f5), v5, \
+				FN(reg_name, f6), v6, \
+				FN(reg_name, f7), v7, \
+				FN(reg_name, f8), v8)
+
 /* macro to poll and wait for a register field to read back given value */
 
 #define REG_WAIT(reg_name, field, val, delay_between_poll_us, max_try)	\
@@ -389,4 +419,30 @@ uint32_t generic_reg_get5(const struct dc_context *ctx, uint32_t addr,
 		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
 		uint8_t shift5, uint32_t mask5, uint32_t *field_value5);
 
+uint32_t generic_reg_get6(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6);
+
+uint32_t generic_reg_get7(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
+		uint8_t shift7, uint32_t mask7, uint32_t *field_value7);
+
+uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
+		uint8_t shift7, uint32_t mask7, uint32_t *field_value7,
+		uint8_t shift8, uint32_t mask8, uint32_t *field_value8);
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_REG_HELPER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 5467332faf7b..640a647f4611 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -139,10 +139,6 @@ bool resource_validate_attach_surfaces(
 		struct dc_state *context,
 		const struct resource_pool *pool);
 
-void validate_guaranteed_copy_streams(
-		struct dc_state *context,
-		int max_streams);
-
 void resource_validate_ctx_update_pointer_after_copy(
 		const struct dc_state *src_ctx,
 		struct dc_state *dst_ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/irq_types.h b/drivers/gpu/drm/amd/display/dc/irq_types.h
index a506c2e939f5..0b5f3a278c22 100644
--- a/drivers/gpu/drm/amd/display/dc/irq_types.h
+++ b/drivers/gpu/drm/amd/display/dc/irq_types.h
@@ -26,6 +26,8 @@
 #ifndef __DAL_IRQ_TYPES_H__
 #define __DAL_IRQ_TYPES_H__
 
+#include "os_types.h"
+
 struct dc_context;
 
 typedef void (*interrupt_handler)(void *);
@@ -135,6 +137,13 @@ enum dc_irq_source {
 	DC_IRQ_SOURCE_VBLANK5,
 	DC_IRQ_SOURCE_VBLANK6,
 
+	DC_IRQ_SOURCE_DC1_VLINE0,
+	DC_IRQ_SOURCE_DC2_VLINE0,
+	DC_IRQ_SOURCE_DC3_VLINE0,
+	DC_IRQ_SOURCE_DC4_VLINE0,
+	DC_IRQ_SOURCE_DC5_VLINE0,
+	DC_IRQ_SOURCE_DC6_VLINE0,
+
 	DAL_IRQ_SOURCES_NUMBER
 };
 
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 9831cb5eaa7c..25029ed42d89 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -86,6 +86,7 @@
 #define VI_POLARIS10_P_A0 80
 #define VI_POLARIS11_M_A0 90
 #define VI_POLARIS12_V_A0 100
+#define VI_VEGAM_A0 110
 
 #define VI_UNKNOWN 0xFF
 
@@ -98,7 +99,9 @@
 		(eChipRev < VI_POLARIS11_M_A0))
 #define ASIC_REV_IS_POLARIS11_M(eChipRev) ((eChipRev >= VI_POLARIS11_M_A0) &&  \
 		(eChipRev < VI_POLARIS12_V_A0))
-#define ASIC_REV_IS_POLARIS12_V(eChipRev) (eChipRev >= VI_POLARIS12_V_A0)
+#define ASIC_REV_IS_POLARIS12_V(eChipRev) ((eChipRev >= VI_POLARIS12_V_A0) && \
+		(eChipRev < VI_VEGAM_A0))
+#define ASIC_REV_IS_VEGAM(eChipRev) (eChipRev >= VI_VEGAM_A0)
 
 /* DCE11 */
 #define CZ_CARRIZO_A0 0x01
@@ -110,12 +113,19 @@
 	((rev >= STONEY_A0) && (rev < CZ_UNKNOWN))
 
 /* DCE12 */
+#define AI_UNKNOWN 0xFF
 
 #define AI_GREENLAND_P_A0 1
 #define AI_GREENLAND_P_A1 2
+#define AI_UNKNOWN 0xFF
 
-#define ASICREV_IS_GREENLAND_M(eChipRev)  (eChipRev < AI_UNKNOWN)
-#define ASICREV_IS_GREENLAND_P(eChipRev)  (eChipRev < AI_UNKNOWN)
+#define AI_VEGA12_P_A0 20
+#define AI_VEGA20_P_A0 40
+#define ASICREV_IS_GREENLAND_M(eChipRev)  (eChipRev < AI_VEGA12_P_A0)
+#define ASICREV_IS_GREENLAND_P(eChipRev)  (eChipRev < AI_VEGA12_P_A0)
+
+#define ASICREV_IS_VEGA12_P(eChipRev) ((eChipRev >= AI_VEGA12_P_A0) && (eChipRev < AI_VEGA20_P_A0))
+#define ASICREV_IS_VEGA20_P(eChipRev) ((eChipRev >= AI_VEGA20_P_A0) && (eChipRev < AI_UNKNOWN))
 
 /* DCN1_0 */
 #define INTERNAL_REV_RAVEN_A0             0x00    /* First spin of Raven */
diff --git a/drivers/gpu/drm/amd/display/include/dal_types.h b/drivers/gpu/drm/amd/display/include/dal_types.h
index fa543965feb5..840142b65f8b 100644
--- a/drivers/gpu/drm/amd/display/include/dal_types.h
+++ b/drivers/gpu/drm/amd/display/include/dal_types.h
@@ -40,6 +40,7 @@ enum dce_version {
 	DCE_VERSION_10_0,
 	DCE_VERSION_11_0,
 	DCE_VERSION_11_2,
+	DCE_VERSION_11_22,
 	DCE_VERSION_12_0,
 	DCE_VERSION_MAX,
 	DCN_VERSION_1_0,
diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h
index 0de258622c12..bb0d4ebba9f0 100644
--- a/drivers/gpu/drm/amd/display/include/fixed31_32.h
+++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h
@@ -26,9 +26,13 @@
 #ifndef __DAL_FIXED31_32_H__
 #define __DAL_FIXED31_32_H__
 
-#include "os_types.h"
-
 #define FIXED31_32_BITS_PER_FRACTIONAL_PART 32
+#ifndef LLONG_MIN
+#define LLONG_MIN (1LL<<63)
+#endif
+#ifndef LLONG_MAX
+#define LLONG_MAX (-1LL>>1)
+#endif
 
 /*
  * @brief
@@ -44,24 +48,25 @@
  */
 
 struct fixed31_32 {
-	int64_t value;
+	long long value;
 };
 
+
 /*
  * @brief
  * Useful constants
  */
 
-static const struct fixed31_32 dal_fixed31_32_zero = { 0 };
-static const struct fixed31_32 dal_fixed31_32_epsilon = { 1LL };
-static const struct fixed31_32 dal_fixed31_32_half = { 0x80000000LL };
-static const struct fixed31_32 dal_fixed31_32_one = { 0x100000000LL };
+static const struct fixed31_32 dc_fixpt_zero = { 0 };
+static const struct fixed31_32 dc_fixpt_epsilon = { 1LL };
+static const struct fixed31_32 dc_fixpt_half = { 0x80000000LL };
+static const struct fixed31_32 dc_fixpt_one = { 0x100000000LL };
 
-static const struct fixed31_32 dal_fixed31_32_pi = { 13493037705LL };
-static const struct fixed31_32 dal_fixed31_32_two_pi = { 26986075409LL };
-static const struct fixed31_32 dal_fixed31_32_e = { 11674931555LL };
-static const struct fixed31_32 dal_fixed31_32_ln2 = { 2977044471LL };
-static const struct fixed31_32 dal_fixed31_32_ln2_div_2 = { 1488522236LL };
+static const struct fixed31_32 dc_fixpt_pi = { 13493037705LL };
+static const struct fixed31_32 dc_fixpt_two_pi = { 26986075409LL };
+static const struct fixed31_32 dc_fixpt_e = { 11674931555LL };
+static const struct fixed31_32 dc_fixpt_ln2 = { 2977044471LL };
+static const struct fixed31_32 dc_fixpt_ln2_div_2 = { 1488522236LL };
 
 /*
  * @brief
@@ -72,24 +77,19 @@ static const struct fixed31_32 dal_fixed31_32_ln2_div_2 = { 1488522236LL };
  * @brief
  * result = numerator / denominator
  */
-struct fixed31_32 dal_fixed31_32_from_fraction(
-	int64_t numerator,
-	int64_t denominator);
+struct fixed31_32 dc_fixpt_from_fraction(long long numerator, long long denominator);
 
 /*
  * @brief
  * result = arg
  */
-struct fixed31_32 dal_fixed31_32_from_int_nonconst(int64_t arg);
-static inline struct fixed31_32 dal_fixed31_32_from_int(int64_t arg)
+static inline struct fixed31_32 dc_fixpt_from_int(int arg)
 {
-	if (__builtin_constant_p(arg)) {
-		struct fixed31_32 res;
-		BUILD_BUG_ON((LONG_MIN > arg) || (arg > LONG_MAX));
-		res.value = arg << FIXED31_32_BITS_PER_FRACTIONAL_PART;
-		return res;
-	} else
-		return dal_fixed31_32_from_int_nonconst(arg);
+	struct fixed31_32 res;
+
+	res.value = (long long) arg << FIXED31_32_BITS_PER_FRACTIONAL_PART;
+
+	return res;
 }
 
 /*
@@ -101,7 +101,7 @@ static inline struct fixed31_32 dal_fixed31_32_from_int(int64_t arg)
  * @brief
  * result = -arg
  */
-static inline struct fixed31_32 dal_fixed31_32_neg(struct fixed31_32 arg)
+static inline struct fixed31_32 dc_fixpt_neg(struct fixed31_32 arg)
 {
 	struct fixed31_32 res;
 
@@ -114,10 +114,10 @@ static inline struct fixed31_32 dal_fixed31_32_neg(struct fixed31_32 arg)
  * @brief
  * result = abs(arg) := (arg >= 0) ? arg : -arg
  */
-static inline struct fixed31_32 dal_fixed31_32_abs(struct fixed31_32 arg)
+static inline struct fixed31_32 dc_fixpt_abs(struct fixed31_32 arg)
 {
 	if (arg.value < 0)
-		return dal_fixed31_32_neg(arg);
+		return dc_fixpt_neg(arg);
 	else
 		return arg;
 }
@@ -131,8 +131,7 @@ static inline struct fixed31_32 dal_fixed31_32_abs(struct fixed31_32 arg)
  * @brief
  * result = arg1 < arg2
  */
-static inline bool dal_fixed31_32_lt(struct fixed31_32 arg1,
-				     struct fixed31_32 arg2)
+static inline bool dc_fixpt_lt(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
 	return arg1.value < arg2.value;
 }
@@ -141,8 +140,7 @@ static inline bool dal_fixed31_32_lt(struct fixed31_32 arg1,
  * @brief
  * result = arg1 <= arg2
  */
-static inline bool dal_fixed31_32_le(struct fixed31_32 arg1,
-				     struct fixed31_32 arg2)
+static inline bool dc_fixpt_le(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
 	return arg1.value <= arg2.value;
 }
@@ -151,8 +149,7 @@ static inline bool dal_fixed31_32_le(struct fixed31_32 arg1,
  * @brief
  * result = arg1 == arg2
  */
-static inline bool dal_fixed31_32_eq(struct fixed31_32 arg1,
-				     struct fixed31_32 arg2)
+static inline bool dc_fixpt_eq(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
 	return arg1.value == arg2.value;
 }
@@ -161,8 +158,7 @@ static inline bool dal_fixed31_32_eq(struct fixed31_32 arg1,
  * @brief
  * result = min(arg1, arg2) := (arg1 <= arg2) ? arg1 : arg2
  */
-static inline struct fixed31_32 dal_fixed31_32_min(struct fixed31_32 arg1,
-						   struct fixed31_32 arg2)
+static inline struct fixed31_32 dc_fixpt_min(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
 	if (arg1.value <= arg2.value)
 		return arg1;
@@ -174,8 +170,7 @@ static inline struct fixed31_32 dal_fixed31_32_min(struct fixed31_32 arg1,
  * @brief
  * result = max(arg1, arg2) := (arg1 <= arg2) ? arg2 : arg1
  */
-static inline struct fixed31_32 dal_fixed31_32_max(struct fixed31_32 arg1,
-						   struct fixed31_32 arg2)
+static inline struct fixed31_32 dc_fixpt_max(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
 	if (arg1.value <= arg2.value)
 		return arg2;
@@ -189,14 +184,14 @@ static inline struct fixed31_32 dal_fixed31_32_max(struct fixed31_32 arg1,
  * result = | arg, when min_value < arg < max_value
  *          | max_value, when arg >= max_value
  */
-static inline struct fixed31_32 dal_fixed31_32_clamp(
+static inline struct fixed31_32 dc_fixpt_clamp(
 	struct fixed31_32 arg,
 	struct fixed31_32 min_value,
 	struct fixed31_32 max_value)
 {
-	if (dal_fixed31_32_le(arg, min_value))
+	if (dc_fixpt_le(arg, min_value))
 		return min_value;
-	else if (dal_fixed31_32_le(max_value, arg))
+	else if (dc_fixpt_le(max_value, arg))
 		return max_value;
 	else
 		return arg;
@@ -211,21 +206,30 @@ static inline struct fixed31_32 dal_fixed31_32_clamp(
  * @brief
  * result = arg << shift
  */
-struct fixed31_32 dal_fixed31_32_shl(
-	struct fixed31_32 arg,
-	uint8_t shift);
+static inline struct fixed31_32 dc_fixpt_shl(struct fixed31_32 arg, unsigned char shift)
+{
+	ASSERT(((arg.value >= 0) && (arg.value <= LLONG_MAX >> shift)) ||
+		((arg.value < 0) && (arg.value >= ~(LLONG_MAX >> shift))));
+
+	arg.value = arg.value << shift;
+
+	return arg;
+}
 
 /*
  * @brief
  * result = arg >> shift
  */
-static inline struct fixed31_32 dal_fixed31_32_shr(
-	struct fixed31_32 arg,
-	uint8_t shift)
+static inline struct fixed31_32 dc_fixpt_shr(struct fixed31_32 arg, unsigned char shift)
 {
-	struct fixed31_32 res;
-	res.value = arg.value >> shift;
-	return res;
+	bool negative = arg.value < 0;
+
+	if (negative)
+		arg.value = -arg.value;
+	arg.value = arg.value >> shift;
+	if (negative)
+		arg.value = -arg.value;
+	return arg;
 }
 
 /*
@@ -237,38 +241,50 @@ static inline struct fixed31_32 dal_fixed31_32_shr(
  * @brief
  * result = arg1 + arg2
  */
-struct fixed31_32 dal_fixed31_32_add(
-	struct fixed31_32 arg1,
-	struct fixed31_32 arg2);
+static inline struct fixed31_32 dc_fixpt_add(struct fixed31_32 arg1, struct fixed31_32 arg2)
+{
+	struct fixed31_32 res;
+
+	ASSERT(((arg1.value >= 0) && (LLONG_MAX - arg1.value >= arg2.value)) ||
+		((arg1.value < 0) && (LLONG_MIN - arg1.value <= arg2.value)));
+
+	res.value = arg1.value + arg2.value;
+
+	return res;
+}
 
 /*
  * @brief
  * result = arg1 + arg2
  */
-static inline struct fixed31_32 dal_fixed31_32_add_int(struct fixed31_32 arg1,
-						       int32_t arg2)
+static inline struct fixed31_32 dc_fixpt_add_int(struct fixed31_32 arg1, int arg2)
 {
-	return dal_fixed31_32_add(arg1,
-				  dal_fixed31_32_from_int(arg2));
+	return dc_fixpt_add(arg1, dc_fixpt_from_int(arg2));
 }
 
 /*
  * @brief
  * result = arg1 - arg2
  */
-struct fixed31_32 dal_fixed31_32_sub(
-	struct fixed31_32 arg1,
-	struct fixed31_32 arg2);
+static inline struct fixed31_32 dc_fixpt_sub(struct fixed31_32 arg1, struct fixed31_32 arg2)
+{
+	struct fixed31_32 res;
+
+	ASSERT(((arg2.value >= 0) && (LLONG_MIN + arg2.value <= arg1.value)) ||
+		((arg2.value < 0) && (LLONG_MAX + arg2.value >= arg1.value)));
+
+	res.value = arg1.value - arg2.value;
+
+	return res;
+}
 
 /*
  * @brief
  * result = arg1 - arg2
  */
-static inline struct fixed31_32 dal_fixed31_32_sub_int(struct fixed31_32 arg1,
-						       int32_t arg2)
+static inline struct fixed31_32 dc_fixpt_sub_int(struct fixed31_32 arg1, int arg2)
 {
-	return dal_fixed31_32_sub(arg1,
-				  dal_fixed31_32_from_int(arg2));
+	return dc_fixpt_sub(arg1, dc_fixpt_from_int(arg2));
 }
 
 
@@ -281,49 +297,40 @@ static inline struct fixed31_32 dal_fixed31_32_sub_int(struct fixed31_32 arg1,
  * @brief
  * result = arg1 * arg2
  */
-struct fixed31_32 dal_fixed31_32_mul(
-	struct fixed31_32 arg1,
-	struct fixed31_32 arg2);
+struct fixed31_32 dc_fixpt_mul(struct fixed31_32 arg1, struct fixed31_32 arg2);
 
 
 /*
  * @brief
  * result = arg1 * arg2
  */
-static inline struct fixed31_32 dal_fixed31_32_mul_int(struct fixed31_32 arg1,
-						       int32_t arg2)
+static inline struct fixed31_32 dc_fixpt_mul_int(struct fixed31_32 arg1, int arg2)
 {
-	return dal_fixed31_32_mul(arg1,
-				  dal_fixed31_32_from_int(arg2));
+	return dc_fixpt_mul(arg1, dc_fixpt_from_int(arg2));
 }
 
 /*
  * @brief
  * result = square(arg) := arg * arg
  */
-struct fixed31_32 dal_fixed31_32_sqr(
-	struct fixed31_32 arg);
+struct fixed31_32 dc_fixpt_sqr(struct fixed31_32 arg);
 
 /*
  * @brief
  * result = arg1 / arg2
  */
-static inline struct fixed31_32 dal_fixed31_32_div_int(struct fixed31_32 arg1,
-						       int64_t arg2)
+static inline struct fixed31_32 dc_fixpt_div_int(struct fixed31_32 arg1, long long arg2)
 {
-	return dal_fixed31_32_from_fraction(arg1.value,
-					    dal_fixed31_32_from_int(arg2).value);
+	return dc_fixpt_from_fraction(arg1.value, dc_fixpt_from_int(arg2).value);
 }
 
 /*
  * @brief
  * result = arg1 / arg2
  */
-static inline struct fixed31_32 dal_fixed31_32_div(struct fixed31_32 arg1,
-						   struct fixed31_32 arg2)
+static inline struct fixed31_32 dc_fixpt_div(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
-	return dal_fixed31_32_from_fraction(arg1.value,
-					    arg2.value);
+	return dc_fixpt_from_fraction(arg1.value, arg2.value);
 }
 
 /*
@@ -338,8 +345,7 @@ static inline struct fixed31_32 dal_fixed31_32_div(struct fixed31_32 arg1,
  * @note
  * No special actions taken in case argument is zero.
  */
-struct fixed31_32 dal_fixed31_32_recip(
-	struct fixed31_32 arg);
+struct fixed31_32 dc_fixpt_recip(struct fixed31_32 arg);
 
 /*
  * @brief
@@ -354,8 +360,7 @@ struct fixed31_32 dal_fixed31_32_recip(
  * Argument specified in radians,
  * internally it's normalized to [-2pi...2pi] range.
  */
-struct fixed31_32 dal_fixed31_32_sinc(
-	struct fixed31_32 arg);
+struct fixed31_32 dc_fixpt_sinc(struct fixed31_32 arg);
 
 /*
  * @brief
@@ -365,8 +370,7 @@ struct fixed31_32 dal_fixed31_32_sinc(
  * Argument specified in radians,
  * internally it's normalized to [-2pi...2pi] range.
  */
-struct fixed31_32 dal_fixed31_32_sin(
-	struct fixed31_32 arg);
+struct fixed31_32 dc_fixpt_sin(struct fixed31_32 arg);
 
 /*
  * @brief
@@ -378,8 +382,7 @@ struct fixed31_32 dal_fixed31_32_sin(
  * passing arguments outside that range
  * will cause incorrect result!
  */
-struct fixed31_32 dal_fixed31_32_cos(
-	struct fixed31_32 arg);
+struct fixed31_32 dc_fixpt_cos(struct fixed31_32 arg);
 
 /*
  * @brief
@@ -393,8 +396,7 @@ struct fixed31_32 dal_fixed31_32_cos(
  * @note
  * Currently, function is verified for abs(arg) <= 1.
  */
-struct fixed31_32 dal_fixed31_32_exp(
-	struct fixed31_32 arg);
+struct fixed31_32 dc_fixpt_exp(struct fixed31_32 arg);
 
 /*
  * @brief
@@ -406,8 +408,7 @@ struct fixed31_32 dal_fixed31_32_exp(
  * Currently, no special actions taken
  * in case of invalid argument(s). Take care!
  */
-struct fixed31_32 dal_fixed31_32_log(
-	struct fixed31_32 arg);
+struct fixed31_32 dc_fixpt_log(struct fixed31_32 arg);
 
 /*
  * @brief
@@ -421,9 +422,13 @@ struct fixed31_32 dal_fixed31_32_log(
  * @note
  * Currently, abs(arg1) should be less than 1. Take care!
  */
-struct fixed31_32 dal_fixed31_32_pow(
-	struct fixed31_32 arg1,
-	struct fixed31_32 arg2);
+static inline struct fixed31_32 dc_fixpt_pow(struct fixed31_32 arg1, struct fixed31_32 arg2)
+{
+	return dc_fixpt_exp(
+		dc_fixpt_mul(
+			dc_fixpt_log(arg1),
+			arg2));
+}
 
 /*
  * @brief
@@ -434,22 +439,56 @@ struct fixed31_32 dal_fixed31_32_pow(
  * @brief
  * result = floor(arg) := greatest integer lower than or equal to arg
  */
-int32_t dal_fixed31_32_floor(
-	struct fixed31_32 arg);
+static inline int dc_fixpt_floor(struct fixed31_32 arg)
+{
+	unsigned long long arg_value = arg.value > 0 ? arg.value : -arg.value;
+
+	if (arg.value >= 0)
+		return (int)(arg_value >> FIXED31_32_BITS_PER_FRACTIONAL_PART);
+	else
+		return -(int)(arg_value >> FIXED31_32_BITS_PER_FRACTIONAL_PART);
+}
 
 /*
  * @brief
  * result = round(arg) := integer nearest to arg
  */
-int32_t dal_fixed31_32_round(
-	struct fixed31_32 arg);
+static inline int dc_fixpt_round(struct fixed31_32 arg)
+{
+	unsigned long long arg_value = arg.value > 0 ? arg.value : -arg.value;
+
+	const long long summand = dc_fixpt_half.value;
+
+	ASSERT(LLONG_MAX - (long long)arg_value >= summand);
+
+	arg_value += summand;
+
+	if (arg.value >= 0)
+		return (int)(arg_value >> FIXED31_32_BITS_PER_FRACTIONAL_PART);
+	else
+		return -(int)(arg_value >> FIXED31_32_BITS_PER_FRACTIONAL_PART);
+}
 
 /*
  * @brief
  * result = ceil(arg) := lowest integer greater than or equal to arg
  */
-int32_t dal_fixed31_32_ceil(
-	struct fixed31_32 arg);
+static inline int dc_fixpt_ceil(struct fixed31_32 arg)
+{
+	unsigned long long arg_value = arg.value > 0 ? arg.value : -arg.value;
+
+	const long long summand = dc_fixpt_one.value -
+		dc_fixpt_epsilon.value;
+
+	ASSERT(LLONG_MAX - (long long)arg_value >= summand);
+
+	arg_value += summand;
+
+	if (arg.value >= 0)
+		return (int)(arg_value >> FIXED31_32_BITS_PER_FRACTIONAL_PART);
+	else
+		return -(int)(arg_value >> FIXED31_32_BITS_PER_FRACTIONAL_PART);
+}
 
 /* the following two function are used in scaler hw programming to convert fixed
  * point value to format 2 bits from integer part and 19 bits from fractional
@@ -457,20 +496,31 @@ int32_t dal_fixed31_32_ceil(
  * fractional
  */
 
-uint32_t dal_fixed31_32_u2d19(
-	struct fixed31_32 arg);
+unsigned int dc_fixpt_u2d19(struct fixed31_32 arg);
+
+unsigned int dc_fixpt_u0d19(struct fixed31_32 arg);
 
-uint32_t dal_fixed31_32_u0d19(
-	struct fixed31_32 arg);
+unsigned int dc_fixpt_clamp_u0d14(struct fixed31_32 arg);
 
+unsigned int dc_fixpt_clamp_u0d10(struct fixed31_32 arg);
 
-uint32_t dal_fixed31_32_clamp_u0d14(
-	struct fixed31_32 arg);
+int dc_fixpt_s4d19(struct fixed31_32 arg);
 
-uint32_t dal_fixed31_32_clamp_u0d10(
-	struct fixed31_32 arg);
+static inline struct fixed31_32 dc_fixpt_truncate(struct fixed31_32 arg, unsigned int frac_bits)
+{
+	bool negative = arg.value < 0;
 
-int32_t dal_fixed31_32_s4d19(
-	struct fixed31_32 arg);
+	if (frac_bits >= FIXED31_32_BITS_PER_FRACTIONAL_PART) {
+		ASSERT(frac_bits == FIXED31_32_BITS_PER_FRACTIONAL_PART);
+		return arg;
+	}
+
+	if (negative)
+		arg.value = -arg.value;
+	arg.value &= (~0LL) << (FIXED31_32_BITS_PER_FRACTIONAL_PART - frac_bits);
+	if (negative)
+		arg.value = -arg.value;
+	return arg;
+}
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/include/fixed32_32.h b/drivers/gpu/drm/amd/display/include/fixed32_32.h
deleted file mode 100644
index 9c70341fe026..000000000000
--- a/drivers/gpu/drm/amd/display/include/fixed32_32.h
+++ /dev/null
@@ -1,129 +0,0 @@
-/*
- * Copyright 2012-15 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-
-
-#ifndef __DAL_FIXED32_32_H__
-#define __DAL_FIXED32_32_H__
-
-#include "os_types.h"
-
-struct fixed32_32 {
-	uint64_t value;
-};
-
-static const struct fixed32_32 dal_fixed32_32_zero = { 0 };
-static const struct fixed32_32 dal_fixed32_32_one = { 0x100000000LL };
-static const struct fixed32_32 dal_fixed32_32_half = { 0x80000000LL };
-
-struct fixed32_32 dal_fixed32_32_from_fraction(uint32_t n, uint32_t d);
-static inline struct fixed32_32 dal_fixed32_32_from_int(uint32_t value)
-{
-	struct fixed32_32 fx;
-
-	fx.value = (uint64_t)value<<32;
-	return fx;
-}
-
-struct fixed32_32 dal_fixed32_32_add(
-	struct fixed32_32 lhs,
-	struct fixed32_32 rhs);
-struct fixed32_32 dal_fixed32_32_add_int(
-	struct fixed32_32 lhs,
-	uint32_t rhs);
-struct fixed32_32 dal_fixed32_32_sub(
-	struct fixed32_32 lhs,
-	struct fixed32_32 rhs);
-struct fixed32_32 dal_fixed32_32_sub_int(
-	struct fixed32_32 lhs,
-	uint32_t rhs);
-struct fixed32_32 dal_fixed32_32_mul(
-	struct fixed32_32 lhs,
-	struct fixed32_32 rhs);
-struct fixed32_32 dal_fixed32_32_mul_int(
-	struct fixed32_32 lhs,
-	uint32_t rhs);
-struct fixed32_32 dal_fixed32_32_div(
-	struct fixed32_32 lhs,
-	struct fixed32_32 rhs);
-struct fixed32_32 dal_fixed32_32_div_int(
-	struct fixed32_32 lhs,
-	uint32_t rhs);
-
-static inline struct fixed32_32 dal_fixed32_32_min(struct fixed32_32 lhs,
-						   struct fixed32_32 rhs)
-{
-	return (lhs.value < rhs.value) ? lhs : rhs;
-}
-
-static inline struct fixed32_32 dal_fixed32_32_max(struct fixed32_32 lhs,
-						   struct fixed32_32 rhs)
-{
-	return (lhs.value > rhs.value) ? lhs : rhs;
-}
-
-static inline bool dal_fixed32_32_gt(struct fixed32_32 lhs, struct fixed32_32 rhs)
-{
-	return lhs.value > rhs.value;
-}
-
-static inline bool dal_fixed32_32_gt_int(struct fixed32_32 lhs, uint32_t rhs)
-{
-	return lhs.value > ((uint64_t)rhs<<32);
-}
-
-static inline bool dal_fixed32_32_lt(struct fixed32_32 lhs, struct fixed32_32 rhs)
-{
-	return lhs.value < rhs.value;
-}
-
-static inline bool dal_fixed32_32_lt_int(struct fixed32_32 lhs, uint32_t rhs)
-{
-	return lhs.value < ((uint64_t)rhs<<32);
-}
-
-static inline bool dal_fixed32_32_le(struct fixed32_32 lhs, struct fixed32_32 rhs)
-{
-	return lhs.value <= rhs.value;
-}
-
-static inline bool dal_fixed32_32_le_int(struct fixed32_32 lhs, uint32_t rhs)
-{
-	return lhs.value <= ((uint64_t)rhs<<32);
-}
-
-static inline bool dal_fixed32_32_eq(struct fixed32_32 lhs, struct fixed32_32 rhs)
-{
-	return lhs.value == rhs.value;
-}
-
-uint32_t dal_fixed32_32_ceil(struct fixed32_32 value);
-static inline uint32_t dal_fixed32_32_floor(struct fixed32_32 value)
-{
-	return value.value>>32;
-}
-
-uint32_t dal_fixed32_32_round(struct fixed32_32 value);
-
-#endif
diff --git a/drivers/gpu/drm/amd/display/include/logger_interface.h b/drivers/gpu/drm/amd/display/include/logger_interface.h
index 28dee960d509..dc98d6d4b2bd 100644
--- a/drivers/gpu/drm/amd/display/include/logger_interface.h
+++ b/drivers/gpu/drm/amd/display/include/logger_interface.h
@@ -190,4 +190,13 @@ void context_clock_trace(
 	} \
 } while (0)
 
+#define DISPLAY_STATS_BEGIN(entry) \
+	dm_logger_open(dc->ctx->logger, &entry, LOG_DISPLAYSTATS)
+
+#define DISPLAY_STATS(msg, ...) \
+	dm_logger_append(&log_entry, msg, ##__VA_ARGS__)
+
+#define DISPLAY_STATS_END(entry) \
+	dm_logger_close(&entry)
+
 #endif /* __DAL_LOGGER_INTERFACE_H__ */
diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h
index 427796bdc14a..0a540b9897a6 100644
--- a/drivers/gpu/drm/amd/display/include/logger_types.h
+++ b/drivers/gpu/drm/amd/display/include/logger_types.h
@@ -29,39 +29,39 @@
 #include "os_types.h"
 
 #define MAX_NAME_LEN 32
-#define DC_LOG_ERROR(a, ...) dm_logger_write(DC_LOGGER, LOG_ERROR, a, ## __VA_ARGS__)
-#define DC_LOG_WARNING(a, ...) dm_logger_write(DC_LOGGER, LOG_WARNING, a, ## __VA_ARGS__)
-#define DC_LOG_DEBUG(a, ...) dm_logger_write(DC_LOGGER, LOG_DEBUG, a, ## __VA_ARGS__)
-#define DC_LOG_DC(a, ...) dm_logger_write(DC_LOGGER, LOG_DC, a, ## __VA_ARGS__)
-#define DC_LOG_DTN(a, ...) dm_logger_write(DC_LOGGER, LOG_DTN, a, ## __VA_ARGS__)
-#define DC_LOG_SURFACE(a, ...) dm_logger_write(DC_LOGGER, LOG_SURFACE, a, ## __VA_ARGS__)
-#define DC_LOG_HW_HOTPLUG(a, ...) dm_logger_write(DC_LOGGER, LOG_HW_HOTPLUG, a, ## __VA_ARGS__)
-#define DC_LOG_HW_LINK_TRAINING(a, ...) dm_logger_write(DC_LOGGER, LOG_HW_LINK_TRAINING, a, ## __VA_ARGS__)
-#define DC_LOG_HW_SET_MODE(a, ...) dm_logger_write(DC_LOGGER, LOG_HW_SET_MODE, a, ## __VA_ARGS__)
-#define DC_LOG_HW_RESUME_S3(a, ...) dm_logger_write(DC_LOGGER, LOG_HW_RESUME_S3, a, ## __VA_ARGS__)
-#define DC_LOG_HW_AUDIO(a, ...) dm_logger_write(DC_LOGGER, LOG_HW_AUDIO, a, ## __VA_ARGS__)
-#define DC_LOG_HW_HPD_IRQ(a, ...) dm_logger_write(DC_LOGGER, LOG_HW_HPD_IRQ, a, ## __VA_ARGS__)
-#define DC_LOG_MST(a, ...) dm_logger_write(DC_LOGGER, LOG_MST, a, ## __VA_ARGS__)
-#define DC_LOG_SCALER(a, ...) dm_logger_write(DC_LOGGER, LOG_SCALER, a, ## __VA_ARGS__)
-#define DC_LOG_BIOS(a, ...) dm_logger_write(DC_LOGGER, LOG_BIOS, a, ## __VA_ARGS__)
-#define DC_LOG_BANDWIDTH_CALCS(a, ...) dm_logger_write(DC_LOGGER, LOG_BANDWIDTH_CALCS, a, ## __VA_ARGS__)
-#define DC_LOG_BANDWIDTH_VALIDATION(a, ...) dm_logger_write(DC_LOGGER, LOG_BANDWIDTH_VALIDATION, a, ## __VA_ARGS__)
-#define DC_LOG_I2C_AUX(a, ...) dm_logger_write(DC_LOGGER, LOG_I2C_AUX, a, ## __VA_ARGS__)
-#define DC_LOG_SYNC(a, ...) dm_logger_write(DC_LOGGER, LOG_SYNC, a, ## __VA_ARGS__)
-#define DC_LOG_BACKLIGHT(a, ...) dm_logger_write(DC_LOGGER, LOG_BACKLIGHT, a, ## __VA_ARGS__)
-#define DC_LOG_FEATURE_OVERRIDE(a, ...) dm_logger_write(DC_LOGGER, LOG_FEATURE_OVERRIDE, a, ## __VA_ARGS__)
-#define DC_LOG_DETECTION_EDID_PARSER(a, ...) dm_logger_write(DC_LOGGER, LOG_DETECTION_EDID_PARSER, a, ## __VA_ARGS__)
-#define DC_LOG_DETECTION_DP_CAPS(a, ...) dm_logger_write(DC_LOGGER, LOG_DETECTION_DP_CAPS, a, ## __VA_ARGS__)
-#define DC_LOG_RESOURCE(a, ...) dm_logger_write(DC_LOGGER, LOG_RESOURCE, a, ## __VA_ARGS__)
-#define DC_LOG_DML(a, ...) dm_logger_write(DC_LOGGER, LOG_DML, a, ## __VA_ARGS__)
-#define DC_LOG_EVENT_MODE_SET(a, ...) dm_logger_write(DC_LOGGER, LOG_EVENT_MODE_SET, a, ## __VA_ARGS__)
-#define DC_LOG_EVENT_DETECTION(a, ...) dm_logger_write(DC_LOGGER, LOG_EVENT_DETECTION, a, ## __VA_ARGS__)
-#define DC_LOG_EVENT_LINK_TRAINING(a, ...) dm_logger_write(DC_LOGGER, LOG_EVENT_LINK_TRAINING, a, ## __VA_ARGS__)
-#define DC_LOG_EVENT_LINK_LOSS(a, ...) dm_logger_write(DC_LOGGER, LOG_EVENT_LINK_LOSS, a, ## __VA_ARGS__)
-#define DC_LOG_EVENT_UNDERFLOW(a, ...) dm_logger_write(DC_LOGGER, LOG_EVENT_UNDERFLOW, a, ## __VA_ARGS__)
-#define DC_LOG_IF_TRACE(a, ...) dm_logger_write(DC_LOGGER, LOG_IF_TRACE, a, ## __VA_ARGS__)
-#define DC_LOG_PERF_TRACE(a, ...) dm_logger_write(DC_LOGGER, LOG_PERF_TRACE, a, ## __VA_ARGS__)
 
+#define DC_LOG_ERROR(...) DRM_ERROR(__VA_ARGS__)
+#define DC_LOG_WARNING(...) DRM_WARN(__VA_ARGS__)
+#define DC_LOG_DEBUG(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_DC(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_DTN(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_SURFACE(...) pr_debug("[SURFACE]:"__VA_ARGS__)
+#define DC_LOG_HW_HOTPLUG(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_HW_LINK_TRAINING(...) pr_debug("[HW_LINK_TRAINING]:"__VA_ARGS__)
+#define DC_LOG_HW_SET_MODE(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_HW_RESUME_S3(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_HW_AUDIO(...) pr_debug("[HW_AUDIO]:"__VA_ARGS__)
+#define DC_LOG_HW_HPD_IRQ(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_MST(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_SCALER(...) pr_debug("[SCALER]:"__VA_ARGS__)
+#define DC_LOG_BIOS(...) pr_debug("[BIOS]:"__VA_ARGS__)
+#define DC_LOG_BANDWIDTH_CALCS(...) pr_debug("[BANDWIDTH_CALCS]:"__VA_ARGS__)
+#define DC_LOG_BANDWIDTH_VALIDATION(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_I2C_AUX(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_SYNC(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_BACKLIGHT(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_FEATURE_OVERRIDE(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_DETECTION_EDID_PARSER(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_DETECTION_DP_CAPS(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_RESOURCE(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_DML(...) pr_debug("[DML]:"__VA_ARGS__)
+#define DC_LOG_EVENT_MODE_SET(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_EVENT_DETECTION(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_EVENT_LINK_TRAINING(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_EVENT_LINK_LOSS(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_EVENT_UNDERFLOW(...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define DC_LOG_IF_TRACE(...) pr_debug("[IF_TRACE]:"__VA_ARGS__)
+#define DC_LOG_PERF_TRACE(...) DRM_DEBUG_KMS(__VA_ARGS__)
 
 struct dal_logger;
 
@@ -98,7 +98,7 @@ enum dc_log_type {
 	LOG_EVENT_UNDERFLOW,
 	LOG_IF_TRACE,
 	LOG_PERF_TRACE,
-	LOG_PROFILING,
+	LOG_DISPLAYSTATS,
 
 	LOG_SECTION_TOTAL_COUNT
 };
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index e7e374f56864..0cd111d59018 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -43,7 +43,7 @@ static bool de_pq_initialized; /* = false; */
 /* one-time setup of X points */
 void setup_x_points_distribution(void)
 {
-	struct fixed31_32 region_size = dal_fixed31_32_from_int(128);
+	struct fixed31_32 region_size = dc_fixpt_from_int(128);
 	int32_t segment;
 	uint32_t seg_offset;
 	uint32_t index;
@@ -53,8 +53,8 @@ void setup_x_points_distribution(void)
 	coordinates_x[MAX_HW_POINTS + 1].x = region_size;
 
 	for (segment = 6; segment > (6 - NUM_REGIONS); segment--) {
-		region_size = dal_fixed31_32_div_int(region_size, 2);
-		increment = dal_fixed31_32_div_int(region_size,
+		region_size = dc_fixpt_div_int(region_size, 2);
+		increment = dc_fixpt_div_int(region_size,
 						NUM_PTS_IN_REGION);
 		seg_offset = (segment + (NUM_REGIONS - 7)) * NUM_PTS_IN_REGION;
 		coordinates_x[seg_offset].x = region_size;
@@ -62,7 +62,7 @@ void setup_x_points_distribution(void)
 		for (index = seg_offset + 1;
 				index < seg_offset + NUM_PTS_IN_REGION;
 				index++) {
-			coordinates_x[index].x = dal_fixed31_32_add
+			coordinates_x[index].x = dc_fixpt_add
 					(coordinates_x[index-1].x, increment);
 		}
 	}
@@ -72,63 +72,63 @@ static void compute_pq(struct fixed31_32 in_x, struct fixed31_32 *out_y)
 {
 	/* consts for PQ gamma formula. */
 	const struct fixed31_32 m1 =
-		dal_fixed31_32_from_fraction(159301758, 1000000000);
+		dc_fixpt_from_fraction(159301758, 1000000000);
 	const struct fixed31_32 m2 =
-		dal_fixed31_32_from_fraction(7884375, 100000);
+		dc_fixpt_from_fraction(7884375, 100000);
 	const struct fixed31_32 c1 =
-		dal_fixed31_32_from_fraction(8359375, 10000000);
+		dc_fixpt_from_fraction(8359375, 10000000);
 	const struct fixed31_32 c2 =
-		dal_fixed31_32_from_fraction(188515625, 10000000);
+		dc_fixpt_from_fraction(188515625, 10000000);
 	const struct fixed31_32 c3 =
-		dal_fixed31_32_from_fraction(186875, 10000);
+		dc_fixpt_from_fraction(186875, 10000);
 
 	struct fixed31_32 l_pow_m1;
 	struct fixed31_32 base;
 
-	if (dal_fixed31_32_lt(in_x, dal_fixed31_32_zero))
-		in_x = dal_fixed31_32_zero;
+	if (dc_fixpt_lt(in_x, dc_fixpt_zero))
+		in_x = dc_fixpt_zero;
 
-	l_pow_m1 = dal_fixed31_32_pow(in_x, m1);
-	base = dal_fixed31_32_div(
-			dal_fixed31_32_add(c1,
-					(dal_fixed31_32_mul(c2, l_pow_m1))),
-			dal_fixed31_32_add(dal_fixed31_32_one,
-					(dal_fixed31_32_mul(c3, l_pow_m1))));
-	*out_y = dal_fixed31_32_pow(base, m2);
+	l_pow_m1 = dc_fixpt_pow(in_x, m1);
+	base = dc_fixpt_div(
+			dc_fixpt_add(c1,
+					(dc_fixpt_mul(c2, l_pow_m1))),
+			dc_fixpt_add(dc_fixpt_one,
+					(dc_fixpt_mul(c3, l_pow_m1))));
+	*out_y = dc_fixpt_pow(base, m2);
 }
 
 static void compute_de_pq(struct fixed31_32 in_x, struct fixed31_32 *out_y)
 {
 	/* consts for dePQ gamma formula. */
 	const struct fixed31_32 m1 =
-		dal_fixed31_32_from_fraction(159301758, 1000000000);
+		dc_fixpt_from_fraction(159301758, 1000000000);
 	const struct fixed31_32 m2 =
-		dal_fixed31_32_from_fraction(7884375, 100000);
+		dc_fixpt_from_fraction(7884375, 100000);
 	const struct fixed31_32 c1 =
-		dal_fixed31_32_from_fraction(8359375, 10000000);
+		dc_fixpt_from_fraction(8359375, 10000000);
 	const struct fixed31_32 c2 =
-		dal_fixed31_32_from_fraction(188515625, 10000000);
+		dc_fixpt_from_fraction(188515625, 10000000);
 	const struct fixed31_32 c3 =
-		dal_fixed31_32_from_fraction(186875, 10000);
+		dc_fixpt_from_fraction(186875, 10000);
 
 	struct fixed31_32 l_pow_m1;
 	struct fixed31_32 base, div;
 
 
-	if (dal_fixed31_32_lt(in_x, dal_fixed31_32_zero))
-		in_x = dal_fixed31_32_zero;
+	if (dc_fixpt_lt(in_x, dc_fixpt_zero))
+		in_x = dc_fixpt_zero;
 
-	l_pow_m1 = dal_fixed31_32_pow(in_x,
-			dal_fixed31_32_div(dal_fixed31_32_one, m2));
-	base = dal_fixed31_32_sub(l_pow_m1, c1);
+	l_pow_m1 = dc_fixpt_pow(in_x,
+			dc_fixpt_div(dc_fixpt_one, m2));
+	base = dc_fixpt_sub(l_pow_m1, c1);
 
-	if (dal_fixed31_32_lt(base, dal_fixed31_32_zero))
-		base = dal_fixed31_32_zero;
+	if (dc_fixpt_lt(base, dc_fixpt_zero))
+		base = dc_fixpt_zero;
 
-	div = dal_fixed31_32_sub(c2, dal_fixed31_32_mul(c3, l_pow_m1));
+	div = dc_fixpt_sub(c2, dc_fixpt_mul(c3, l_pow_m1));
 
-	*out_y = dal_fixed31_32_pow(dal_fixed31_32_div(base, div),
-			dal_fixed31_32_div(dal_fixed31_32_one, m1));
+	*out_y = dc_fixpt_pow(dc_fixpt_div(base, div),
+			dc_fixpt_div(dc_fixpt_one, m1));
 
 }
 /* one-time pre-compute PQ values - only for sdr_white_level 80 */
@@ -138,14 +138,14 @@ void precompute_pq(void)
 	struct fixed31_32 x;
 	const struct hw_x_point *coord_x = coordinates_x + 32;
 	struct fixed31_32 scaling_factor =
-			dal_fixed31_32_from_fraction(80, 10000);
+			dc_fixpt_from_fraction(80, 10000);
 
 	/* pow function has problems with arguments too small */
 	for (i = 0; i < 32; i++)
-		pq_table[i] = dal_fixed31_32_zero;
+		pq_table[i] = dc_fixpt_zero;
 
 	for (i = 32; i <= MAX_HW_POINTS; i++) {
-		x = dal_fixed31_32_mul(coord_x->x, scaling_factor);
+		x = dc_fixpt_mul(coord_x->x, scaling_factor);
 		compute_pq(x, &pq_table[i]);
 		++coord_x;
 	}
@@ -158,7 +158,7 @@ void precompute_de_pq(void)
 	struct fixed31_32  y;
 	uint32_t begin_index, end_index;
 
-	struct fixed31_32 scaling_factor = dal_fixed31_32_from_int(125);
+	struct fixed31_32 scaling_factor = dc_fixpt_from_int(125);
 
 	/* X points is 2^-25 to 2^7
 	 * De-gamma X is 2^-12 to 2^0 – we are skipping first -12-(-25) = 13 regions
@@ -167,11 +167,11 @@ void precompute_de_pq(void)
 	end_index = begin_index + 12 * NUM_PTS_IN_REGION;
 
 	for (i = 0; i <= begin_index; i++)
-		de_pq_table[i] = dal_fixed31_32_zero;
+		de_pq_table[i] = dc_fixpt_zero;
 
 	for (; i <= end_index; i++) {
 		compute_de_pq(coordinates_x[i].x, &y);
-		de_pq_table[i] = dal_fixed31_32_mul(y, scaling_factor);
+		de_pq_table[i] = dc_fixpt_mul(y, scaling_factor);
 	}
 
 	for (; i <= MAX_HW_POINTS; i++)
@@ -185,25 +185,25 @@ struct dividers {
 
 static void build_coefficients(struct gamma_coefficients *coefficients, bool is_2_4)
 {
-		static const int32_t numerator01[] = { 31308, 180000};
-		static const int32_t numerator02[] = { 12920, 4500};
-		static const int32_t numerator03[] = { 55, 99};
-		static const int32_t numerator04[] = { 55, 99};
-		static const int32_t numerator05[] = { 2400, 2200};
+	static const int32_t numerator01[] = { 31308, 180000};
+	static const int32_t numerator02[] = { 12920, 4500};
+	static const int32_t numerator03[] = { 55, 99};
+	static const int32_t numerator04[] = { 55, 99};
+	static const int32_t numerator05[] = { 2400, 2200};
 
-		uint32_t i = 0;
-		uint32_t index = is_2_4 == true ? 0:1;
+	uint32_t i = 0;
+	uint32_t index = is_2_4 == true ? 0:1;
 
 	do {
-		coefficients->a0[i] = dal_fixed31_32_from_fraction(
+		coefficients->a0[i] = dc_fixpt_from_fraction(
 			numerator01[index], 10000000);
-		coefficients->a1[i] = dal_fixed31_32_from_fraction(
+		coefficients->a1[i] = dc_fixpt_from_fraction(
 			numerator02[index], 1000);
-		coefficients->a2[i] = dal_fixed31_32_from_fraction(
+		coefficients->a2[i] = dc_fixpt_from_fraction(
 			numerator03[index], 1000);
-		coefficients->a3[i] = dal_fixed31_32_from_fraction(
+		coefficients->a3[i] = dc_fixpt_from_fraction(
 			numerator04[index], 1000);
-		coefficients->user_gamma[i] = dal_fixed31_32_from_fraction(
+		coefficients->user_gamma[i] = dc_fixpt_from_fraction(
 			numerator05[index], 1000);
 
 		++i;
@@ -218,33 +218,33 @@ static struct fixed31_32 translate_from_linear_space(
 	struct fixed31_32 a3,
 	struct fixed31_32 gamma)
 {
-	const struct fixed31_32 one = dal_fixed31_32_from_int(1);
+	const struct fixed31_32 one = dc_fixpt_from_int(1);
 
-	if (dal_fixed31_32_lt(one, arg))
+	if (dc_fixpt_lt(one, arg))
 		return one;
 
-	if (dal_fixed31_32_le(arg, dal_fixed31_32_neg(a0)))
-		return dal_fixed31_32_sub(
+	if (dc_fixpt_le(arg, dc_fixpt_neg(a0)))
+		return dc_fixpt_sub(
 			a2,
-			dal_fixed31_32_mul(
-				dal_fixed31_32_add(
+			dc_fixpt_mul(
+				dc_fixpt_add(
 					one,
 					a3),
-				dal_fixed31_32_pow(
-					dal_fixed31_32_neg(arg),
-					dal_fixed31_32_recip(gamma))));
-	else if (dal_fixed31_32_le(a0, arg))
-		return dal_fixed31_32_sub(
-			dal_fixed31_32_mul(
-				dal_fixed31_32_add(
+				dc_fixpt_pow(
+					dc_fixpt_neg(arg),
+					dc_fixpt_recip(gamma))));
+	else if (dc_fixpt_le(a0, arg))
+		return dc_fixpt_sub(
+			dc_fixpt_mul(
+				dc_fixpt_add(
 					one,
 					a3),
-				dal_fixed31_32_pow(
+				dc_fixpt_pow(
 					arg,
-					dal_fixed31_32_recip(gamma))),
+					dc_fixpt_recip(gamma))),
 			a2);
 	else
-		return dal_fixed31_32_mul(
+		return dc_fixpt_mul(
 			arg,
 			a1);
 }
@@ -259,25 +259,25 @@ static struct fixed31_32 translate_to_linear_space(
 {
 	struct fixed31_32 linear;
 
-	a0 = dal_fixed31_32_mul(a0, a1);
-	if (dal_fixed31_32_le(arg, dal_fixed31_32_neg(a0)))
+	a0 = dc_fixpt_mul(a0, a1);
+	if (dc_fixpt_le(arg, dc_fixpt_neg(a0)))
 
-		linear = dal_fixed31_32_neg(
-				 dal_fixed31_32_pow(
-				 dal_fixed31_32_div(
-				 dal_fixed31_32_sub(a2, arg),
-				 dal_fixed31_32_add(
-				 dal_fixed31_32_one, a3)), gamma));
+		linear = dc_fixpt_neg(
+				 dc_fixpt_pow(
+				 dc_fixpt_div(
+				 dc_fixpt_sub(a2, arg),
+				 dc_fixpt_add(
+				 dc_fixpt_one, a3)), gamma));
 
-	else if (dal_fixed31_32_le(dal_fixed31_32_neg(a0), arg) &&
-			 dal_fixed31_32_le(arg, a0))
-		linear = dal_fixed31_32_div(arg, a1);
+	else if (dc_fixpt_le(dc_fixpt_neg(a0), arg) &&
+			 dc_fixpt_le(arg, a0))
+		linear = dc_fixpt_div(arg, a1);
 	else
-		linear =  dal_fixed31_32_pow(
-					dal_fixed31_32_div(
-					dal_fixed31_32_add(a2, arg),
-					dal_fixed31_32_add(
-					dal_fixed31_32_one, a3)), gamma);
+		linear =  dc_fixpt_pow(
+					dc_fixpt_div(
+					dc_fixpt_add(a2, arg),
+					dc_fixpt_add(
+					dc_fixpt_one, a3)), gamma);
 
 	return linear;
 }
@@ -352,8 +352,8 @@ static bool find_software_points(
 				right = axis_x[max_number - 1].b;
 		}
 
-		if (dal_fixed31_32_le(left, hw_point) &&
-			dal_fixed31_32_le(hw_point, right)) {
+		if (dc_fixpt_le(left, hw_point) &&
+			dc_fixpt_le(hw_point, right)) {
 			*index_to_start = i;
 			*index_left = i;
 
@@ -366,7 +366,7 @@ static bool find_software_points(
 
 			return true;
 		} else if ((i == *index_to_start) &&
-			dal_fixed31_32_le(hw_point, left)) {
+			dc_fixpt_le(hw_point, left)) {
 			*index_to_start = i;
 			*index_left = i;
 			*index_right = i;
@@ -375,7 +375,7 @@ static bool find_software_points(
 
 			return true;
 		} else if ((i == max_number - 1) &&
-			dal_fixed31_32_le(right, hw_point)) {
+			dc_fixpt_le(right, hw_point)) {
 			*index_to_start = i;
 			*index_left = i;
 			*index_right = i;
@@ -457,17 +457,17 @@ static bool build_custom_gamma_mapping_coefficients_worker(
 		}
 
 		if (hw_pos == HW_POINT_POSITION_MIDDLE)
-			point->coeff = dal_fixed31_32_div(
-				dal_fixed31_32_sub(
+			point->coeff = dc_fixpt_div(
+				dc_fixpt_sub(
 					coord_x,
 					left_pos),
-				dal_fixed31_32_sub(
+				dc_fixpt_sub(
 					right_pos,
 					left_pos));
 		else if (hw_pos == HW_POINT_POSITION_LEFT)
-			point->coeff = dal_fixed31_32_zero;
+			point->coeff = dc_fixpt_zero;
 		else if (hw_pos == HW_POINT_POSITION_RIGHT)
-			point->coeff = dal_fixed31_32_from_int(2);
+			point->coeff = dc_fixpt_from_int(2);
 		else {
 			BREAK_TO_DEBUGGER();
 			return false;
@@ -502,45 +502,45 @@ static struct fixed31_32 calculate_mapped_value(
 
 	if ((point->left_index < 0) || (point->left_index > max_index)) {
 		BREAK_TO_DEBUGGER();
-		return dal_fixed31_32_zero;
+		return dc_fixpt_zero;
 	}
 
 	if ((point->right_index < 0) || (point->right_index > max_index)) {
 		BREAK_TO_DEBUGGER();
-		return dal_fixed31_32_zero;
+		return dc_fixpt_zero;
 	}
 
 	if (point->pos == HW_POINT_POSITION_MIDDLE)
 		if (channel == CHANNEL_NAME_RED)
-			result = dal_fixed31_32_add(
-				dal_fixed31_32_mul(
+			result = dc_fixpt_add(
+				dc_fixpt_mul(
 					point->coeff,
-					dal_fixed31_32_sub(
+					dc_fixpt_sub(
 						rgb[point->right_index].r,
 						rgb[point->left_index].r)),
 				rgb[point->left_index].r);
 		else if (channel == CHANNEL_NAME_GREEN)
-			result = dal_fixed31_32_add(
-				dal_fixed31_32_mul(
+			result = dc_fixpt_add(
+				dc_fixpt_mul(
 					point->coeff,
-					dal_fixed31_32_sub(
+					dc_fixpt_sub(
 						rgb[point->right_index].g,
 						rgb[point->left_index].g)),
 				rgb[point->left_index].g);
 		else
-			result = dal_fixed31_32_add(
-				dal_fixed31_32_mul(
+			result = dc_fixpt_add(
+				dc_fixpt_mul(
 					point->coeff,
-					dal_fixed31_32_sub(
+					dc_fixpt_sub(
 						rgb[point->right_index].b,
 						rgb[point->left_index].b)),
 				rgb[point->left_index].b);
 	else if (point->pos == HW_POINT_POSITION_LEFT) {
 		BREAK_TO_DEBUGGER();
-		result = dal_fixed31_32_zero;
+		result = dc_fixpt_zero;
 	} else {
 		BREAK_TO_DEBUGGER();
-		result = dal_fixed31_32_one;
+		result = dc_fixpt_one;
 	}
 
 	return result;
@@ -558,7 +558,7 @@ static void build_pq(struct pwl_float_data_ex *rgb_regamma,
 	struct fixed31_32 x;
 	struct fixed31_32 output;
 	struct fixed31_32 scaling_factor =
-			dal_fixed31_32_from_fraction(sdr_white_level, 10000);
+			dc_fixpt_from_fraction(sdr_white_level, 10000);
 
 	if (!pq_initialized && sdr_white_level == 80) {
 		precompute_pq();
@@ -579,15 +579,15 @@ static void build_pq(struct pwl_float_data_ex *rgb_regamma,
 		if (sdr_white_level == 80) {
 			output = pq_table[i];
 		} else {
-			x = dal_fixed31_32_mul(coord_x->x, scaling_factor);
+			x = dc_fixpt_mul(coord_x->x, scaling_factor);
 			compute_pq(x, &output);
 		}
 
 		/* should really not happen? */
-		if (dal_fixed31_32_lt(output, dal_fixed31_32_zero))
-			output = dal_fixed31_32_zero;
-		else if (dal_fixed31_32_lt(dal_fixed31_32_one, output))
-			output = dal_fixed31_32_one;
+		if (dc_fixpt_lt(output, dc_fixpt_zero))
+			output = dc_fixpt_zero;
+		else if (dc_fixpt_lt(dc_fixpt_one, output))
+			output = dc_fixpt_one;
 
 		rgb->r = output;
 		rgb->g = output;
@@ -605,7 +605,7 @@ static void build_de_pq(struct pwl_float_data_ex *de_pq,
 	uint32_t i;
 	struct fixed31_32 output;
 
-	struct fixed31_32 scaling_factor = dal_fixed31_32_from_int(125);
+	struct fixed31_32 scaling_factor = dc_fixpt_from_int(125);
 
 	if (!de_pq_initialized) {
 		precompute_de_pq();
@@ -616,9 +616,9 @@ static void build_de_pq(struct pwl_float_data_ex *de_pq,
 	for (i = 0; i <= hw_points_num; i++) {
 		output = de_pq_table[i];
 		/* should really not happen? */
-		if (dal_fixed31_32_lt(output, dal_fixed31_32_zero))
-			output = dal_fixed31_32_zero;
-		else if (dal_fixed31_32_lt(scaling_factor, output))
+		if (dc_fixpt_lt(output, dc_fixpt_zero))
+			output = dc_fixpt_zero;
+		else if (dc_fixpt_lt(scaling_factor, output))
 			output = scaling_factor;
 		de_pq[i].r = output;
 		de_pq[i].g = output;
@@ -670,9 +670,9 @@ static void build_degamma(struct pwl_float_data_ex *curve,
 	end_index = begin_index + 12 * NUM_PTS_IN_REGION;
 
 	while (i != begin_index) {
-		curve[i].r = dal_fixed31_32_zero;
-		curve[i].g = dal_fixed31_32_zero;
-		curve[i].b = dal_fixed31_32_zero;
+		curve[i].r = dc_fixpt_zero;
+		curve[i].g = dc_fixpt_zero;
+		curve[i].b = dc_fixpt_zero;
 		i++;
 	}
 
@@ -684,19 +684,19 @@ static void build_degamma(struct pwl_float_data_ex *curve,
 		i++;
 	}
 	while (i != hw_points_num + 1) {
-		curve[i].r = dal_fixed31_32_one;
-		curve[i].g = dal_fixed31_32_one;
-		curve[i].b = dal_fixed31_32_one;
+		curve[i].r = dc_fixpt_one;
+		curve[i].g = dc_fixpt_one;
+		curve[i].b = dc_fixpt_one;
 		i++;
 	}
 }
 
-static bool scale_gamma(struct pwl_float_data *pwl_rgb,
+static void scale_gamma(struct pwl_float_data *pwl_rgb,
 		const struct dc_gamma *ramp,
 		struct dividers dividers)
 {
-	const struct fixed31_32 max_driver = dal_fixed31_32_from_int(0xFFFF);
-	const struct fixed31_32 max_os = dal_fixed31_32_from_int(0xFF00);
+	const struct fixed31_32 max_driver = dc_fixpt_from_int(0xFFFF);
+	const struct fixed31_32 max_os = dc_fixpt_from_int(0xFF00);
 	struct fixed31_32 scaler = max_os;
 	uint32_t i;
 	struct pwl_float_data *rgb = pwl_rgb;
@@ -705,9 +705,9 @@ static bool scale_gamma(struct pwl_float_data *pwl_rgb,
 	i = 0;
 
 	do {
-		if (dal_fixed31_32_lt(max_os, ramp->entries.red[i]) ||
-			dal_fixed31_32_lt(max_os, ramp->entries.green[i]) ||
-			dal_fixed31_32_lt(max_os, ramp->entries.blue[i])) {
+		if (dc_fixpt_lt(max_os, ramp->entries.red[i]) ||
+			dc_fixpt_lt(max_os, ramp->entries.green[i]) ||
+			dc_fixpt_lt(max_os, ramp->entries.blue[i])) {
 			scaler = max_driver;
 			break;
 		}
@@ -717,109 +717,170 @@ static bool scale_gamma(struct pwl_float_data *pwl_rgb,
 	i = 0;
 
 	do {
-		rgb->r = dal_fixed31_32_div(
+		rgb->r = dc_fixpt_div(
 			ramp->entries.red[i], scaler);
-		rgb->g = dal_fixed31_32_div(
+		rgb->g = dc_fixpt_div(
 			ramp->entries.green[i], scaler);
-		rgb->b = dal_fixed31_32_div(
+		rgb->b = dc_fixpt_div(
 			ramp->entries.blue[i], scaler);
 
 		++rgb;
 		++i;
 	} while (i != ramp->num_entries);
 
-	rgb->r = dal_fixed31_32_mul(rgb_last->r,
+	rgb->r = dc_fixpt_mul(rgb_last->r,
 			dividers.divider1);
-	rgb->g = dal_fixed31_32_mul(rgb_last->g,
+	rgb->g = dc_fixpt_mul(rgb_last->g,
 			dividers.divider1);
-	rgb->b = dal_fixed31_32_mul(rgb_last->b,
+	rgb->b = dc_fixpt_mul(rgb_last->b,
 			dividers.divider1);
 
 	++rgb;
 
-	rgb->r = dal_fixed31_32_mul(rgb_last->r,
+	rgb->r = dc_fixpt_mul(rgb_last->r,
 			dividers.divider2);
-	rgb->g = dal_fixed31_32_mul(rgb_last->g,
+	rgb->g = dc_fixpt_mul(rgb_last->g,
 			dividers.divider2);
-	rgb->b = dal_fixed31_32_mul(rgb_last->b,
+	rgb->b = dc_fixpt_mul(rgb_last->b,
 			dividers.divider2);
 
 	++rgb;
 
-	rgb->r = dal_fixed31_32_mul(rgb_last->r,
+	rgb->r = dc_fixpt_mul(rgb_last->r,
 			dividers.divider3);
-	rgb->g = dal_fixed31_32_mul(rgb_last->g,
+	rgb->g = dc_fixpt_mul(rgb_last->g,
 			dividers.divider3);
-	rgb->b = dal_fixed31_32_mul(rgb_last->b,
+	rgb->b = dc_fixpt_mul(rgb_last->b,
 			dividers.divider3);
-
-	return true;
 }
 
-static bool scale_gamma_dx(struct pwl_float_data *pwl_rgb,
+static void scale_gamma_dx(struct pwl_float_data *pwl_rgb,
 		const struct dc_gamma *ramp,
 		struct dividers dividers)
 {
 	uint32_t i;
-	struct fixed31_32 min = dal_fixed31_32_zero;
-	struct fixed31_32 max = dal_fixed31_32_one;
+	struct fixed31_32 min = dc_fixpt_zero;
+	struct fixed31_32 max = dc_fixpt_one;
 
-	struct fixed31_32 delta = dal_fixed31_32_zero;
-	struct fixed31_32 offset = dal_fixed31_32_zero;
+	struct fixed31_32 delta = dc_fixpt_zero;
+	struct fixed31_32 offset = dc_fixpt_zero;
 
 	for (i = 0 ; i < ramp->num_entries; i++) {
-		if (dal_fixed31_32_lt(ramp->entries.red[i], min))
+		if (dc_fixpt_lt(ramp->entries.red[i], min))
 			min = ramp->entries.red[i];
 
-		if (dal_fixed31_32_lt(ramp->entries.green[i], min))
+		if (dc_fixpt_lt(ramp->entries.green[i], min))
 			min = ramp->entries.green[i];
 
-		if (dal_fixed31_32_lt(ramp->entries.blue[i], min))
+		if (dc_fixpt_lt(ramp->entries.blue[i], min))
 			min = ramp->entries.blue[i];
 
-		if (dal_fixed31_32_lt(max, ramp->entries.red[i]))
+		if (dc_fixpt_lt(max, ramp->entries.red[i]))
 			max = ramp->entries.red[i];
 
-		if (dal_fixed31_32_lt(max, ramp->entries.green[i]))
+		if (dc_fixpt_lt(max, ramp->entries.green[i]))
 			max = ramp->entries.green[i];
 
-		if (dal_fixed31_32_lt(max, ramp->entries.blue[i]))
+		if (dc_fixpt_lt(max, ramp->entries.blue[i]))
 			max = ramp->entries.blue[i];
 	}
 
-	if (dal_fixed31_32_lt(min, dal_fixed31_32_zero))
-		delta = dal_fixed31_32_neg(min);
+	if (dc_fixpt_lt(min, dc_fixpt_zero))
+		delta = dc_fixpt_neg(min);
 
-	offset = dal_fixed31_32_add(min, max);
+	offset = dc_fixpt_add(min, max);
 
 	for (i = 0 ; i < ramp->num_entries; i++) {
-		pwl_rgb[i].r = dal_fixed31_32_div(
-			dal_fixed31_32_add(
+		pwl_rgb[i].r = dc_fixpt_div(
+			dc_fixpt_add(
 				ramp->entries.red[i], delta), offset);
-		pwl_rgb[i].g = dal_fixed31_32_div(
-			dal_fixed31_32_add(
+		pwl_rgb[i].g = dc_fixpt_div(
+			dc_fixpt_add(
 				ramp->entries.green[i], delta), offset);
-		pwl_rgb[i].b = dal_fixed31_32_div(
-			dal_fixed31_32_add(
+		pwl_rgb[i].b = dc_fixpt_div(
+			dc_fixpt_add(
 				ramp->entries.blue[i], delta), offset);
 
 	}
 
-	pwl_rgb[i].r =  dal_fixed31_32_sub(dal_fixed31_32_mul_int(
+	pwl_rgb[i].r =  dc_fixpt_sub(dc_fixpt_mul_int(
 				pwl_rgb[i-1].r, 2), pwl_rgb[i-2].r);
-	pwl_rgb[i].g =  dal_fixed31_32_sub(dal_fixed31_32_mul_int(
+	pwl_rgb[i].g =  dc_fixpt_sub(dc_fixpt_mul_int(
 				pwl_rgb[i-1].g, 2), pwl_rgb[i-2].g);
-	pwl_rgb[i].b =  dal_fixed31_32_sub(dal_fixed31_32_mul_int(
+	pwl_rgb[i].b =  dc_fixpt_sub(dc_fixpt_mul_int(
 				pwl_rgb[i-1].b, 2), pwl_rgb[i-2].b);
 	++i;
-	pwl_rgb[i].r =  dal_fixed31_32_sub(dal_fixed31_32_mul_int(
+	pwl_rgb[i].r =  dc_fixpt_sub(dc_fixpt_mul_int(
 				pwl_rgb[i-1].r, 2), pwl_rgb[i-2].r);
-	pwl_rgb[i].g =  dal_fixed31_32_sub(dal_fixed31_32_mul_int(
+	pwl_rgb[i].g =  dc_fixpt_sub(dc_fixpt_mul_int(
 				pwl_rgb[i-1].g, 2), pwl_rgb[i-2].g);
-	pwl_rgb[i].b =  dal_fixed31_32_sub(dal_fixed31_32_mul_int(
+	pwl_rgb[i].b =  dc_fixpt_sub(dc_fixpt_mul_int(
 				pwl_rgb[i-1].b, 2), pwl_rgb[i-2].b);
+}
 
-	return true;
+/* todo: all these scale_gamma functions are inherently the same but
+ *  take different structures as params or different format for ramp
+ *  values. We could probably implement it in a more generic fashion
+ */
+static void scale_user_regamma_ramp(struct pwl_float_data *pwl_rgb,
+		const struct regamma_ramp *ramp,
+		struct dividers dividers)
+{
+	unsigned short max_driver = 0xFFFF;
+	unsigned short max_os = 0xFF00;
+	unsigned short scaler = max_os;
+	uint32_t i;
+	struct pwl_float_data *rgb = pwl_rgb;
+	struct pwl_float_data *rgb_last = rgb + GAMMA_RGB_256_ENTRIES - 1;
+
+	i = 0;
+	do {
+		if (ramp->gamma[i] > max_os ||
+				ramp->gamma[i + 256] > max_os ||
+				ramp->gamma[i + 512] > max_os) {
+			scaler = max_driver;
+			break;
+		}
+		i++;
+	} while (i != GAMMA_RGB_256_ENTRIES);
+
+	i = 0;
+	do {
+		rgb->r = dc_fixpt_from_fraction(
+				ramp->gamma[i], scaler);
+		rgb->g = dc_fixpt_from_fraction(
+				ramp->gamma[i + 256], scaler);
+		rgb->b = dc_fixpt_from_fraction(
+				ramp->gamma[i + 512], scaler);
+
+		++rgb;
+		++i;
+	} while (i != GAMMA_RGB_256_ENTRIES);
+
+	rgb->r = dc_fixpt_mul(rgb_last->r,
+			dividers.divider1);
+	rgb->g = dc_fixpt_mul(rgb_last->g,
+			dividers.divider1);
+	rgb->b = dc_fixpt_mul(rgb_last->b,
+			dividers.divider1);
+
+	++rgb;
+
+	rgb->r = dc_fixpt_mul(rgb_last->r,
+			dividers.divider2);
+	rgb->g = dc_fixpt_mul(rgb_last->g,
+			dividers.divider2);
+	rgb->b = dc_fixpt_mul(rgb_last->b,
+			dividers.divider2);
+
+	++rgb;
+
+	rgb->r = dc_fixpt_mul(rgb_last->r,
+			dividers.divider3);
+	rgb->g = dc_fixpt_mul(rgb_last->g,
+			dividers.divider3);
+	rgb->b = dc_fixpt_mul(rgb_last->b,
+			dividers.divider3);
 }
 
 /*
@@ -852,7 +913,7 @@ static void apply_lut_1d(
 	struct fixed31_32 lut2;
 	const int max_lut_index = 4095;
 	const struct fixed31_32 max_lut_index_f =
-			dal_fixed31_32_from_int_nonconst(max_lut_index);
+			dc_fixpt_from_int(max_lut_index);
 	int32_t index = 0, index_next = 0;
 	struct fixed31_32 index_f;
 	struct fixed31_32 delta_lut;
@@ -870,10 +931,10 @@ static void apply_lut_1d(
 			else
 				regamma_y = &tf_pts->blue[i];
 
-			norm_y = dal_fixed31_32_mul(max_lut_index_f,
+			norm_y = dc_fixpt_mul(max_lut_index_f,
 						   *regamma_y);
-			index = dal_fixed31_32_floor(norm_y);
-			index_f = dal_fixed31_32_from_int_nonconst(index);
+			index = dc_fixpt_floor(norm_y);
+			index_f = dc_fixpt_from_int(index);
 
 			if (index < 0 || index > max_lut_index)
 				continue;
@@ -892,11 +953,11 @@ static void apply_lut_1d(
 			}
 
 			// we have everything now, so interpolate
-			delta_lut = dal_fixed31_32_sub(lut2, lut1);
-			delta_index = dal_fixed31_32_sub(norm_y, index_f);
+			delta_lut = dc_fixpt_sub(lut2, lut1);
+			delta_index = dc_fixpt_sub(norm_y, index_f);
 
-			*regamma_y = dal_fixed31_32_add(lut1,
-				dal_fixed31_32_mul(delta_index, delta_lut));
+			*regamma_y = dc_fixpt_add(lut1,
+				dc_fixpt_mul(delta_index, delta_lut));
 		}
 	}
 }
@@ -912,7 +973,7 @@ static void build_evenly_distributed_points(
 	uint32_t i = 0;
 
 	do {
-		struct fixed31_32 value = dal_fixed31_32_from_fraction(i,
+		struct fixed31_32 value = dc_fixpt_from_fraction(i,
 			numberof_points - 1);
 
 		p->r = value;
@@ -923,21 +984,21 @@ static void build_evenly_distributed_points(
 		++i;
 	} while (i != numberof_points);
 
-	p->r = dal_fixed31_32_div(p_last->r, dividers.divider1);
-	p->g = dal_fixed31_32_div(p_last->g, dividers.divider1);
-	p->b = dal_fixed31_32_div(p_last->b, dividers.divider1);
+	p->r = dc_fixpt_div(p_last->r, dividers.divider1);
+	p->g = dc_fixpt_div(p_last->g, dividers.divider1);
+	p->b = dc_fixpt_div(p_last->b, dividers.divider1);
 
 	++p;
 
-	p->r = dal_fixed31_32_div(p_last->r, dividers.divider2);
-	p->g = dal_fixed31_32_div(p_last->g, dividers.divider2);
-	p->b = dal_fixed31_32_div(p_last->b, dividers.divider2);
+	p->r = dc_fixpt_div(p_last->r, dividers.divider2);
+	p->g = dc_fixpt_div(p_last->g, dividers.divider2);
+	p->b = dc_fixpt_div(p_last->b, dividers.divider2);
 
 	++p;
 
-	p->r = dal_fixed31_32_div(p_last->r, dividers.divider3);
-	p->g = dal_fixed31_32_div(p_last->g, dividers.divider3);
-	p->b = dal_fixed31_32_div(p_last->b, dividers.divider3);
+	p->r = dc_fixpt_div(p_last->r, dividers.divider3);
+	p->g = dc_fixpt_div(p_last->g, dividers.divider3);
+	p->b = dc_fixpt_div(p_last->b, dividers.divider3);
 }
 
 static inline void copy_rgb_regamma_to_coordinates_x(
@@ -949,7 +1010,7 @@ static inline void copy_rgb_regamma_to_coordinates_x(
 	uint32_t i = 0;
 	const struct pwl_float_data_ex *rgb_regamma = rgb_ex;
 
-	while (i <= hw_points_num) {
+	while (i <= hw_points_num + 1) {
 		coords->regamma_y_red = rgb_regamma->r;
 		coords->regamma_y_green = rgb_regamma->g;
 		coords->regamma_y_blue = rgb_regamma->b;
@@ -1002,6 +1063,102 @@ static bool calculate_interpolated_hardware_curve(
 	return true;
 }
 
+/* The "old" interpolation uses a complicated scheme to build an array of
+ * coefficients while also using an array of 0-255 normalized to 0-1
+ * Then there's another loop using both of the above + new scaled user ramp
+ * and we concatenate them. It also searches for points of interpolation and
+ * uses enums for positions.
+ *
+ * This function uses a different approach:
+ * user ramp is always applied on X with 0/255, 1/255, 2/255, ..., 255/255
+ * To find index for hwX , we notice the following:
+ * i/255 <= hwX < (i+1)/255  <=> i <= 255*hwX < i+1
+ * See apply_lut_1d which is the same principle, but on 4K entry 1D LUT
+ *
+ * Once the index is known, combined Y is simply:
+ * user_ramp(index) + (hwX-index/255)*(user_ramp(index+1) - user_ramp(index)
+ *
+ * We should switch to this method in all cases, it's simpler and faster
+ * ToDo one day - for now this only applies to ADL regamma to avoid regression
+ * for regular use cases (sRGB and PQ)
+ */
+static void interpolate_user_regamma(uint32_t hw_points_num,
+		struct pwl_float_data *rgb_user,
+		bool apply_degamma,
+		struct dc_transfer_func_distributed_points *tf_pts)
+{
+	uint32_t i;
+	uint32_t color = 0;
+	int32_t index;
+	int32_t index_next;
+	struct fixed31_32 *tf_point;
+	struct fixed31_32 hw_x;
+	struct fixed31_32 norm_factor =
+			dc_fixpt_from_int(255);
+	struct fixed31_32 norm_x;
+	struct fixed31_32 index_f;
+	struct fixed31_32 lut1;
+	struct fixed31_32 lut2;
+	struct fixed31_32 delta_lut;
+	struct fixed31_32 delta_index;
+
+	i = 0;
+	/* fixed_pt library has problems handling too small values */
+	while (i != 32) {
+		tf_pts->red[i] = dc_fixpt_zero;
+		tf_pts->green[i] = dc_fixpt_zero;
+		tf_pts->blue[i] = dc_fixpt_zero;
+		++i;
+	}
+	while (i <= hw_points_num + 1) {
+		for (color = 0; color < 3; color++) {
+			if (color == 0)
+				tf_point = &tf_pts->red[i];
+			else if (color == 1)
+				tf_point = &tf_pts->green[i];
+			else
+				tf_point = &tf_pts->blue[i];
+
+			if (apply_degamma) {
+				if (color == 0)
+					hw_x = coordinates_x[i].regamma_y_red;
+				else if (color == 1)
+					hw_x = coordinates_x[i].regamma_y_green;
+				else
+					hw_x = coordinates_x[i].regamma_y_blue;
+			} else
+				hw_x = coordinates_x[i].x;
+
+			norm_x = dc_fixpt_mul(norm_factor, hw_x);
+			index = dc_fixpt_floor(norm_x);
+			if (index < 0 || index > 255)
+				continue;
+
+			index_f = dc_fixpt_from_int(index);
+			index_next = (index == 255) ? index : index + 1;
+
+			if (color == 0) {
+				lut1 = rgb_user[index].r;
+				lut2 = rgb_user[index_next].r;
+			} else if (color == 1) {
+				lut1 = rgb_user[index].g;
+				lut2 = rgb_user[index_next].g;
+			} else {
+				lut1 = rgb_user[index].b;
+				lut2 = rgb_user[index_next].b;
+			}
+
+			// we have everything now, so interpolate
+			delta_lut = dc_fixpt_sub(lut2, lut1);
+			delta_index = dc_fixpt_sub(norm_x, index_f);
+
+			*tf_point = dc_fixpt_add(lut1,
+				dc_fixpt_mul(delta_index, delta_lut));
+		}
+		++i;
+	}
+}
+
 static void build_new_custom_resulted_curve(
 	uint32_t hw_points_num,
 	struct dc_transfer_func_distributed_points *tf_pts)
@@ -1011,16 +1168,39 @@ static void build_new_custom_resulted_curve(
 	i = 0;
 
 	while (i != hw_points_num + 1) {
-		tf_pts->red[i] = dal_fixed31_32_clamp(
-			tf_pts->red[i], dal_fixed31_32_zero,
-			dal_fixed31_32_one);
-		tf_pts->green[i] = dal_fixed31_32_clamp(
-			tf_pts->green[i], dal_fixed31_32_zero,
-			dal_fixed31_32_one);
-		tf_pts->blue[i] = dal_fixed31_32_clamp(
-			tf_pts->blue[i], dal_fixed31_32_zero,
-			dal_fixed31_32_one);
+		tf_pts->red[i] = dc_fixpt_clamp(
+			tf_pts->red[i], dc_fixpt_zero,
+			dc_fixpt_one);
+		tf_pts->green[i] = dc_fixpt_clamp(
+			tf_pts->green[i], dc_fixpt_zero,
+			dc_fixpt_one);
+		tf_pts->blue[i] = dc_fixpt_clamp(
+			tf_pts->blue[i], dc_fixpt_zero,
+			dc_fixpt_one);
+
+		++i;
+	}
+}
+
+static void apply_degamma_for_user_regamma(struct pwl_float_data_ex *rgb_regamma,
+		uint32_t hw_points_num)
+{
+	uint32_t i;
+
+	struct gamma_coefficients coeff;
+	struct pwl_float_data_ex *rgb = rgb_regamma;
+	const struct hw_x_point *coord_x = coordinates_x;
 
+	build_coefficients(&coeff, true);
+
+	i = 0;
+	while (i != hw_points_num + 1) {
+		rgb->r = translate_from_linear_space_ex(
+				coord_x->x, &coeff, 0);
+		rgb->g = rgb->r;
+		rgb->b = rgb->r;
+		++coord_x;
+		++rgb;
 		++i;
 	}
 }
@@ -1062,6 +1242,7 @@ static bool map_regamma_hw_to_x_user(
 		}
 	}
 
+	/* this should be named differently, all it does is clamp to 0-1 */
 	build_new_custom_resulted_curve(hw_points_num, tf_pts);
 
 	return true;
@@ -1093,25 +1274,25 @@ bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf,
 
 	output_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
 
-	rgb_user = kzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
-			   GFP_KERNEL);
+	rgb_user = kvzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
+			    GFP_KERNEL);
 	if (!rgb_user)
 		goto rgb_user_alloc_fail;
-	rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS),
-			GFP_KERNEL);
+	rgb_regamma = kvzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS),
+			       GFP_KERNEL);
 	if (!rgb_regamma)
 		goto rgb_regamma_alloc_fail;
-	axix_x = kzalloc(sizeof(*axix_x) * (ramp->num_entries + 3),
-			 GFP_KERNEL);
+	axix_x = kvzalloc(sizeof(*axix_x) * (ramp->num_entries + 3),
+			  GFP_KERNEL);
 	if (!axix_x)
 		goto axix_x_alloc_fail;
-	coeff = kzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
+	coeff = kvzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
 	if (!coeff)
 		goto coeff_alloc_fail;
 
-	dividers.divider1 = dal_fixed31_32_from_fraction(3, 2);
-	dividers.divider2 = dal_fixed31_32_from_int(2);
-	dividers.divider3 = dal_fixed31_32_from_fraction(5, 2);
+	dividers.divider1 = dc_fixpt_from_fraction(3, 2);
+	dividers.divider2 = dc_fixpt_from_int(2);
+	dividers.divider3 = dc_fixpt_from_fraction(5, 2);
 
 	tf = output_tf->tf;
 
@@ -1157,13 +1338,120 @@ bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf,
 
 	ret = true;
 
-	kfree(coeff);
+	kvfree(coeff);
 coeff_alloc_fail:
-	kfree(axix_x);
+	kvfree(axix_x);
 axix_x_alloc_fail:
+	kvfree(rgb_regamma);
+rgb_regamma_alloc_fail:
+	kvfree(rgb_user);
+rgb_user_alloc_fail:
+	return ret;
+}
+
+bool calculate_user_regamma_coeff(struct dc_transfer_func *output_tf,
+		const struct regamma_lut *regamma)
+{
+	struct gamma_coefficients coeff;
+	const struct hw_x_point *coord_x = coordinates_x;
+	uint32_t i = 0;
+
+	do {
+		coeff.a0[i] = dc_fixpt_from_fraction(
+				regamma->coeff.A0[i], 10000000);
+		coeff.a1[i] = dc_fixpt_from_fraction(
+				regamma->coeff.A1[i], 1000);
+		coeff.a2[i] = dc_fixpt_from_fraction(
+				regamma->coeff.A2[i], 1000);
+		coeff.a3[i] = dc_fixpt_from_fraction(
+				regamma->coeff.A3[i], 1000);
+		coeff.user_gamma[i] = dc_fixpt_from_fraction(
+				regamma->coeff.gamma[i], 1000);
+
+		++i;
+	} while (i != 3);
+
+	i = 0;
+	/* fixed_pt library has problems handling too small values */
+	while (i != 32) {
+		output_tf->tf_pts.red[i] = dc_fixpt_zero;
+		output_tf->tf_pts.green[i] = dc_fixpt_zero;
+		output_tf->tf_pts.blue[i] = dc_fixpt_zero;
+		++coord_x;
+		++i;
+	}
+	while (i != MAX_HW_POINTS + 1) {
+		output_tf->tf_pts.red[i] = translate_from_linear_space_ex(
+				coord_x->x, &coeff, 0);
+		output_tf->tf_pts.green[i] = translate_from_linear_space_ex(
+				coord_x->x, &coeff, 1);
+		output_tf->tf_pts.blue[i] = translate_from_linear_space_ex(
+				coord_x->x, &coeff, 2);
+		++coord_x;
+		++i;
+	}
+
+	// this function just clamps output to 0-1
+	build_new_custom_resulted_curve(MAX_HW_POINTS, &output_tf->tf_pts);
+	output_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+
+	return true;
+}
+
+bool calculate_user_regamma_ramp(struct dc_transfer_func *output_tf,
+		const struct regamma_lut *regamma)
+{
+	struct dc_transfer_func_distributed_points *tf_pts = &output_tf->tf_pts;
+	struct dividers dividers;
+
+	struct pwl_float_data *rgb_user = NULL;
+	struct pwl_float_data_ex *rgb_regamma = NULL;
+	bool ret = false;
+
+	if (regamma == NULL)
+		return false;
+
+	output_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+
+	rgb_user = kzalloc(sizeof(*rgb_user) * (GAMMA_RGB_256_ENTRIES + _EXTRA_POINTS),
+			GFP_KERNEL);
+	if (!rgb_user)
+		goto rgb_user_alloc_fail;
+
+	rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS),
+			GFP_KERNEL);
+	if (!rgb_regamma)
+		goto rgb_regamma_alloc_fail;
+
+	dividers.divider1 = dc_fixpt_from_fraction(3, 2);
+	dividers.divider2 = dc_fixpt_from_int(2);
+	dividers.divider3 = dc_fixpt_from_fraction(5, 2);
+
+	scale_user_regamma_ramp(rgb_user, &regamma->ramp, dividers);
+
+	if (regamma->flags.bits.applyDegamma == 1) {
+		apply_degamma_for_user_regamma(rgb_regamma, MAX_HW_POINTS);
+		copy_rgb_regamma_to_coordinates_x(coordinates_x,
+				MAX_HW_POINTS, rgb_regamma);
+	}
+
+	interpolate_user_regamma(MAX_HW_POINTS, rgb_user,
+			regamma->flags.bits.applyDegamma, tf_pts);
+
+	// no custom HDR curves!
+	tf_pts->end_exponent = 0;
+	tf_pts->x_point_at_y1_red = 1;
+	tf_pts->x_point_at_y1_green = 1;
+	tf_pts->x_point_at_y1_blue = 1;
+
+	// this function just clamps output to 0-1
+	build_new_custom_resulted_curve(MAX_HW_POINTS, tf_pts);
+
+	ret = true;
+
 	kfree(rgb_regamma);
 rgb_regamma_alloc_fail:
-	kfree(rgb_user);
+	kvfree(rgb_user);
 rgb_user_alloc_fail:
 	return ret;
 }
@@ -1192,25 +1480,25 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf,
 
 	input_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
 
-	rgb_user = kzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
-			   GFP_KERNEL);
+	rgb_user = kvzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
+			    GFP_KERNEL);
 	if (!rgb_user)
 		goto rgb_user_alloc_fail;
-	curve = kzalloc(sizeof(*curve) * (MAX_HW_POINTS + _EXTRA_POINTS),
-			GFP_KERNEL);
+	curve = kvzalloc(sizeof(*curve) * (MAX_HW_POINTS + _EXTRA_POINTS),
+			 GFP_KERNEL);
 	if (!curve)
 		goto curve_alloc_fail;
-	axix_x = kzalloc(sizeof(*axix_x) * (ramp->num_entries + _EXTRA_POINTS),
-			 GFP_KERNEL);
+	axix_x = kvzalloc(sizeof(*axix_x) * (ramp->num_entries + _EXTRA_POINTS),
+			  GFP_KERNEL);
 	if (!axix_x)
 		goto axix_x_alloc_fail;
-	coeff = kzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
+	coeff = kvzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
 	if (!coeff)
 		goto coeff_alloc_fail;
 
-	dividers.divider1 = dal_fixed31_32_from_fraction(3, 2);
-	dividers.divider2 = dal_fixed31_32_from_int(2);
-	dividers.divider3 = dal_fixed31_32_from_fraction(5, 2);
+	dividers.divider1 = dc_fixpt_from_fraction(3, 2);
+	dividers.divider2 = dc_fixpt_from_int(2);
+	dividers.divider3 = dc_fixpt_from_fraction(5, 2);
 
 	tf = input_tf->tf;
 
@@ -1246,13 +1534,13 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf,
 
 	ret = true;
 
-	kfree(coeff);
+	kvfree(coeff);
 coeff_alloc_fail:
-	kfree(axix_x);
+	kvfree(axix_x);
 axix_x_alloc_fail:
-	kfree(curve);
+	kvfree(curve);
 curve_alloc_fail:
-	kfree(rgb_user);
+	kvfree(rgb_user);
 rgb_user_alloc_fail:
 
 	return ret;
@@ -1281,8 +1569,9 @@ bool  mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
 		}
 		ret = true;
 	} else if (trans == TRANSFER_FUNCTION_PQ) {
-		rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS +
-						_EXTRA_POINTS), GFP_KERNEL);
+		rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
+				       (MAX_HW_POINTS + _EXTRA_POINTS),
+				       GFP_KERNEL);
 		if (!rgb_regamma)
 			goto rgb_regamma_alloc_fail;
 		points->end_exponent = 7;
@@ -1302,11 +1591,12 @@ bool  mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
 		}
 		ret = true;
 
-		kfree(rgb_regamma);
+		kvfree(rgb_regamma);
 	} else if (trans == TRANSFER_FUNCTION_SRGB ||
 			  trans == TRANSFER_FUNCTION_BT709) {
-		rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS +
-						_EXTRA_POINTS), GFP_KERNEL);
+		rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
+				       (MAX_HW_POINTS + _EXTRA_POINTS),
+				       GFP_KERNEL);
 		if (!rgb_regamma)
 			goto rgb_regamma_alloc_fail;
 		points->end_exponent = 0;
@@ -1324,7 +1614,7 @@ bool  mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
 		}
 		ret = true;
 
-		kfree(rgb_regamma);
+		kvfree(rgb_regamma);
 	}
 rgb_regamma_alloc_fail:
 	return ret;
@@ -1348,8 +1638,9 @@ bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 		}
 		ret = true;
 	} else if (trans == TRANSFER_FUNCTION_PQ) {
-		rgb_degamma = kzalloc(sizeof(*rgb_degamma) * (MAX_HW_POINTS +
-						_EXTRA_POINTS), GFP_KERNEL);
+		rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
+				       (MAX_HW_POINTS +	_EXTRA_POINTS),
+				       GFP_KERNEL);
 		if (!rgb_degamma)
 			goto rgb_degamma_alloc_fail;
 
@@ -1364,11 +1655,12 @@ bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 		}
 		ret = true;
 
-		kfree(rgb_degamma);
+		kvfree(rgb_degamma);
 	} else if (trans == TRANSFER_FUNCTION_SRGB ||
 			  trans == TRANSFER_FUNCTION_BT709) {
-		rgb_degamma = kzalloc(sizeof(*rgb_degamma) * (MAX_HW_POINTS +
-						_EXTRA_POINTS), GFP_KERNEL);
+		rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
+				       (MAX_HW_POINTS + _EXTRA_POINTS),
+				       GFP_KERNEL);
 		if (!rgb_degamma)
 			goto rgb_degamma_alloc_fail;
 
@@ -1382,7 +1674,7 @@ bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 		}
 		ret = true;
 
-		kfree(rgb_degamma);
+		kvfree(rgb_degamma);
 	}
 	points->end_exponent = 0;
 	points->x_point_at_y1_red = 1;
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.h b/drivers/gpu/drm/amd/display/modules/color/color_gamma.h
index b7f9bc27d101..b64048991a95 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.h
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.h
@@ -32,6 +32,47 @@ struct dc_transfer_func_distributed_points;
 struct dc_rgb_fixed;
 enum dc_transfer_func_predefined;
 
+/* For SetRegamma ADL interface support
+ * Must match escape type
+ */
+union regamma_flags {
+	unsigned int raw;
+	struct {
+		unsigned int gammaRampArray       :1;    // RegammaRamp is in use
+		unsigned int gammaFromEdid        :1;    //gamma from edid is in use
+		unsigned int gammaFromEdidEx      :1;    //gamma from edid is in use , but only for Display Id 1.2
+		unsigned int gammaFromUser        :1;    //user custom gamma is used
+		unsigned int coeffFromUser        :1;    //coeff. A0-A3 from user is in use
+		unsigned int coeffFromEdid        :1;    //coeff. A0-A3 from edid is in use
+		unsigned int applyDegamma         :1;    //flag for additional degamma correction in driver
+		unsigned int gammaPredefinedSRGB  :1;    //flag for SRGB gamma
+		unsigned int gammaPredefinedPQ    :1;    //flag for PQ gamma
+		unsigned int gammaPredefinedPQ2084Interim :1;    //flag for PQ gamma, lower max nits
+		unsigned int gammaPredefined36    :1;    //flag for 3.6 gamma
+		unsigned int gammaPredefinedReset :1;    //flag to return to previous gamma
+	} bits;
+};
+
+struct regamma_ramp {
+	unsigned short gamma[256*3];  // gamma ramp packed  in same way as OS windows ,r , g & b
+};
+
+struct regamma_coeff {
+	int    gamma[3];
+	int    A0[3];
+	int    A1[3];
+	int    A2[3];
+	int    A3[3];
+};
+
+struct regamma_lut {
+	union regamma_flags flags;
+	union {
+		struct regamma_ramp ramp;
+		struct regamma_coeff coeff;
+	};
+};
+
 void setup_x_points_distribution(void);
 void precompute_pq(void);
 void precompute_de_pq(void);
@@ -45,9 +86,14 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *output_tf,
 bool mod_color_calculate_curve(enum dc_transfer_func_predefined  trans,
 		struct dc_transfer_func_distributed_points *points);
 
-bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
+bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 				struct dc_transfer_func_distributed_points *points);
 
+bool calculate_user_regamma_coeff(struct dc_transfer_func *output_tf,
+		const struct regamma_lut *regamma);
+
+bool calculate_user_regamma_ramp(struct dc_transfer_func *output_tf,
+		const struct regamma_lut *regamma);
 
 
 #endif /* COLOR_MOD_COLOR_GAMMA_H_ */
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h
index 3230e2adb870..3812094b52e8 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h
@@ -46,6 +46,10 @@ void mod_stats_dump(struct mod_stats *mod_stats);
 
 void mod_stats_reset_data(struct mod_stats *mod_stats);
 
+void mod_stats_update_event(struct mod_stats *mod_stats,
+		char *event_string,
+		unsigned int length);
+
 void mod_stats_update_flip(struct mod_stats *mod_stats,
 		unsigned long timestamp_in_ns);
 
diff --git a/drivers/gpu/drm/amd/display/modules/stats/stats.c b/drivers/gpu/drm/amd/display/modules/stats/stats.c
index 041f87b73d5f..3f7d47fdc367 100644
--- a/drivers/gpu/drm/amd/display/modules/stats/stats.c
+++ b/drivers/gpu/drm/amd/display/modules/stats/stats.c
@@ -36,9 +36,14 @@
 #define DAL_STATS_ENTRIES_REGKEY_DEFAULT	0x00350000
 #define DAL_STATS_ENTRIES_REGKEY_MAX		0x01000000
 
+#define DAL_STATS_EVENT_ENTRIES_DEFAULT		0x00000100
+
 #define MOD_STATS_NUM_VSYNCS			5
+#define MOD_STATS_EVENT_STRING_MAX		512
 
 struct stats_time_cache {
+	unsigned int entry_id;
+
 	unsigned long flip_timestamp_in_ns;
 	unsigned long vupdate_timestamp_in_ns;
 
@@ -63,15 +68,26 @@ struct stats_time_cache {
 	unsigned int flags;
 };
 
+struct stats_event_cache {
+	unsigned int entry_id;
+	char event_string[MOD_STATS_EVENT_STRING_MAX];
+};
+
 struct core_stats {
 	struct mod_stats public;
 	struct dc *dc;
 
+	bool enabled;
+	unsigned int entries;
+	unsigned int event_entries;
+	unsigned int entry_id;
+
 	struct stats_time_cache *time;
 	unsigned int index;
 
-	bool enabled;
-	unsigned int entries;
+	struct stats_event_cache *events;
+	unsigned int event_index;
+
 };
 
 #define MOD_STATS_TO_CORE(mod_stats)\
@@ -99,12 +115,12 @@ struct mod_stats *mod_stats_create(struct dc *dc)
 	unsigned int reg_data;
 	int i = 0;
 
+	if (dc == NULL)
+		goto fail_construct;
+
 	core_stats = kzalloc(sizeof(struct core_stats), GFP_KERNEL);
 
 	if (core_stats == NULL)
-		goto fail_alloc_context;
-
-	if (dc == NULL)
 		goto fail_construct;
 
 	core_stats->dc = dc;
@@ -115,33 +131,55 @@ struct mod_stats *mod_stats_create(struct dc *dc)
 			&reg_data, sizeof(unsigned int), &flag))
 		core_stats->enabled = reg_data;
 
-	core_stats->entries = DAL_STATS_ENTRIES_REGKEY_DEFAULT;
-	if (dm_read_persistent_data(dc->ctx, NULL, NULL,
-			DAL_STATS_ENTRIES_REGKEY,
-			&reg_data, sizeof(unsigned int), &flag)) {
-		if (reg_data > DAL_STATS_ENTRIES_REGKEY_MAX)
-			core_stats->entries = DAL_STATS_ENTRIES_REGKEY_MAX;
-		else
-			core_stats->entries = reg_data;
-	}
+	if (core_stats->enabled) {
+		core_stats->entries = DAL_STATS_ENTRIES_REGKEY_DEFAULT;
+		if (dm_read_persistent_data(dc->ctx, NULL, NULL,
+				DAL_STATS_ENTRIES_REGKEY,
+				&reg_data, sizeof(unsigned int), &flag)) {
+			if (reg_data > DAL_STATS_ENTRIES_REGKEY_MAX)
+				core_stats->entries = DAL_STATS_ENTRIES_REGKEY_MAX;
+			else
+				core_stats->entries = reg_data;
+		}
+		core_stats->time = kzalloc(
+			sizeof(struct stats_time_cache) *
+				core_stats->entries,
+						GFP_KERNEL);
 
-	core_stats->time = kzalloc(sizeof(struct stats_time_cache) * core_stats->entries,
-					GFP_KERNEL);
+		if (core_stats->time == NULL)
+			goto fail_construct_time;
 
-	if (core_stats->time == NULL)
-		goto fail_construct;
+		core_stats->event_entries = DAL_STATS_EVENT_ENTRIES_DEFAULT;
+		core_stats->events = kzalloc(
+			sizeof(struct stats_event_cache) *
+				core_stats->event_entries,
+						GFP_KERNEL);
+
+		if (core_stats->events == NULL)
+			goto fail_construct_events;
+
+	} else {
+		core_stats->entries = 0;
+	}
 
 	/* Purposely leave index 0 unused so we don't need special logic to
 	 * handle calculation cases that depend on previous flip data.
 	 */
 	core_stats->index = 1;
+	core_stats->event_index = 0;
+
+	// Keeps track of ordering within the different stats structures
+	core_stats->entry_id = 0;
 
 	return &core_stats->public;
 
-fail_construct:
+fail_construct_events:
+	kfree(core_stats->time);
+
+fail_construct_time:
 	kfree(core_stats);
 
-fail_alloc_context:
+fail_construct:
 	return NULL;
 }
 
@@ -153,6 +191,9 @@ void mod_stats_destroy(struct mod_stats *mod_stats)
 		if (core_stats->time != NULL)
 			kfree(core_stats->time);
 
+		if (core_stats->events != NULL)
+			kfree(core_stats->events);
+
 		kfree(core_stats);
 	}
 }
@@ -163,7 +204,11 @@ void mod_stats_dump(struct mod_stats *mod_stats)
 	struct dal_logger *logger = NULL;
 	struct core_stats *core_stats = NULL;
 	struct stats_time_cache *time = NULL;
+	struct stats_event_cache *events = NULL;
+	unsigned int time_index = 1;
+	unsigned int event_index = 0;
 	unsigned int index = 0;
+	struct log_entry log_entry;
 
 	if (mod_stats == NULL)
 		return;
@@ -172,45 +217,62 @@ void mod_stats_dump(struct mod_stats *mod_stats)
 	dc = core_stats->dc;
 	logger = dc->ctx->logger;
 	time = core_stats->time;
-
-	//LogEntry* pLog = GetLog()->Open(LogMajor_ISR, LogMinor_ISR_FreeSyncSW);
-
-	//if (!pLog->IsDummyEntry())
-	{
-		dm_logger_write(logger, LOG_PROFILING, "==Display Caps==\n");
-		dm_logger_write(logger, LOG_PROFILING, "\n");
-		dm_logger_write(logger, LOG_PROFILING, "\n");
-
-		dm_logger_write(logger, LOG_PROFILING, "==Stats==\n");
-		dm_logger_write(logger, LOG_PROFILING,
-			"render avgRender minWindow midPoint maxWindow vsyncToFlip flipToVsync #vsyncBetweenFlip #frame insertDuration vTotalMin vTotalMax eventTrigs vSyncTime1 vSyncTime2 vSyncTime3 vSyncTime4 vSyncTime5 flags\n");
-
-		for (int i = 0; i < core_stats->index && i < core_stats->entries; i++) {
-			dm_logger_write(logger, LOG_PROFILING,
-					"%u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u  %u\n",
-					time[i].render_time_in_us,
-					time[i].avg_render_time_in_us_last_ten,
-					time[i].min_window,
-					time[i].lfc_mid_point_in_us,
-					time[i].max_window,
-					time[i].vsync_to_flip_time_in_us,
-					time[i].flip_to_vsync_time_in_us,
-					time[i].num_vsync_between_flips,
-					time[i].num_frames_inserted,
-					time[i].inserted_duration_in_us,
-					time[i].v_total_min,
-					time[i].v_total_max,
-					time[i].event_triggers,
-					time[i].v_sync_time_in_us[0],
-					time[i].v_sync_time_in_us[1],
-					time[i].v_sync_time_in_us[2],
-					time[i].v_sync_time_in_us[3],
-					time[i].v_sync_time_in_us[4],
-					time[i].flags);
+	events = core_stats->events;
+
+	DISPLAY_STATS_BEGIN(log_entry);
+
+	DISPLAY_STATS("==Display Caps==\n");
+
+	DISPLAY_STATS("==Display Stats==\n");
+
+	DISPLAY_STATS("%10s %10s %10s %10s %10s"
+			" %11s %11s %17s %10s %14s"
+			" %10s %10s %10s %10s %10s"
+			" %10s %10s %10s %10s\n",
+		"render", "avgRender",
+		"minWindow", "midPoint", "maxWindow",
+		"vsyncToFlip", "flipToVsync", "vsyncsBetweenFlip",
+		"numFrame", "insertDuration",
+		"vTotalMin", "vTotalMax", "eventTrigs",
+		"vSyncTime1", "vSyncTime2", "vSyncTime3",
+		"vSyncTime4", "vSyncTime5", "flags");
+
+	for (int i = 0; i < core_stats->entry_id; i++) {
+		if (event_index < core_stats->event_index &&
+				i == events[event_index].entry_id) {
+			DISPLAY_STATS("%s\n", events[event_index].event_string);
+			event_index++;
+		} else if (time_index < core_stats->index &&
+				i == time[time_index].entry_id) {
+			DISPLAY_STATS("%10u %10u %10u %10u %10u"
+					" %11u %11u %17u %10u %14u"
+					" %10u %10u %10u %10u %10u"
+					" %10u %10u %10u %10u\n",
+				time[time_index].render_time_in_us,
+				time[time_index].avg_render_time_in_us_last_ten,
+				time[time_index].min_window,
+				time[time_index].lfc_mid_point_in_us,
+				time[time_index].max_window,
+				time[time_index].vsync_to_flip_time_in_us,
+				time[time_index].flip_to_vsync_time_in_us,
+				time[time_index].num_vsync_between_flips,
+				time[time_index].num_frames_inserted,
+				time[time_index].inserted_duration_in_us,
+				time[time_index].v_total_min,
+				time[time_index].v_total_max,
+				time[time_index].event_triggers,
+				time[time_index].v_sync_time_in_us[0],
+				time[time_index].v_sync_time_in_us[1],
+				time[time_index].v_sync_time_in_us[2],
+				time[time_index].v_sync_time_in_us[3],
+				time[time_index].v_sync_time_in_us[4],
+				time[time_index].flags);
+
+			time_index++;
 		}
 	}
-	//GetLog()->Close(pLog);
-	//GetLog()->UnSetLogMask(LogMajor_ISR, LogMinor_ISR_FreeSyncSW);
+
+	DISPLAY_STATS_END(log_entry);
 }
 
 void mod_stats_reset_data(struct mod_stats *mod_stats)
@@ -227,7 +289,46 @@ void mod_stats_reset_data(struct mod_stats *mod_stats)
 	memset(core_stats->time, 0,
 		sizeof(struct stats_time_cache) * core_stats->entries);
 
-	core_stats->index = 0;
+	memset(core_stats->events, 0,
+		sizeof(struct stats_event_cache) * core_stats->event_entries);
+
+	core_stats->index = 1;
+	core_stats->event_index = 0;
+
+	// Keeps track of ordering within the different stats structures
+	core_stats->entry_id = 0;
+}
+
+void mod_stats_update_event(struct mod_stats *mod_stats,
+		char *event_string,
+		unsigned int length)
+{
+	struct core_stats *core_stats = NULL;
+	struct stats_event_cache *events = NULL;
+	unsigned int index = 0;
+	unsigned int copy_length = 0;
+
+	if (mod_stats == NULL)
+		return;
+
+	core_stats = MOD_STATS_TO_CORE(mod_stats);
+
+	if (core_stats->event_index >= core_stats->event_entries)
+		return;
+
+	events = core_stats->events;
+	index = core_stats->event_index;
+
+	copy_length = length;
+	if (length > MOD_STATS_EVENT_STRING_MAX)
+		copy_length = MOD_STATS_EVENT_STRING_MAX;
+
+	memcpy(&events[index].event_string, event_string, copy_length);
+	events[index].event_string[copy_length - 1] = '\0';
+
+	events[index].entry_id = core_stats->entry_id;
+	core_stats->event_index++;
+	core_stats->entry_id++;
 }
 
 void mod_stats_update_flip(struct mod_stats *mod_stats,
@@ -250,7 +351,7 @@ void mod_stats_update_flip(struct mod_stats *mod_stats,
 
 	time[index].flip_timestamp_in_ns = timestamp_in_ns;
 	time[index].render_time_in_us =
-		timestamp_in_ns - time[index - 1].flip_timestamp_in_ns;
+		(timestamp_in_ns - time[index - 1].flip_timestamp_in_ns) / 1000;
 
 	if (index >= 10) {
 		for (unsigned int i = 0; i < 10; i++)
@@ -261,12 +362,16 @@ void mod_stats_update_flip(struct mod_stats *mod_stats,
 
 	if (time[index].num_vsync_between_flips > 0)
 		time[index].vsync_to_flip_time_in_us =
-			timestamp_in_ns - time[index].vupdate_timestamp_in_ns;
+			(timestamp_in_ns -
+				time[index].vupdate_timestamp_in_ns) / 1000;
 	else
 		time[index].vsync_to_flip_time_in_us =
-			timestamp_in_ns - time[index - 1].vupdate_timestamp_in_ns;
+			(timestamp_in_ns -
+				time[index - 1].vupdate_timestamp_in_ns) / 1000;
 
+	time[index].entry_id = core_stats->entry_id;
 	core_stats->index++;
+	core_stats->entry_id++;
 }
 
 void mod_stats_update_vupdate(struct mod_stats *mod_stats,
@@ -275,6 +380,8 @@ void mod_stats_update_vupdate(struct mod_stats *mod_stats,
 	struct core_stats *core_stats = NULL;
 	struct stats_time_cache *time = NULL;
 	unsigned int index = 0;
+	unsigned int num_vsyncs = 0;
+	unsigned int prev_vsync_in_ns = 0;
 
 	if (mod_stats == NULL)
 		return;
@@ -286,14 +393,27 @@ void mod_stats_update_vupdate(struct mod_stats *mod_stats,
 
 	time = core_stats->time;
 	index = core_stats->index;
+	num_vsyncs = time[index].num_vsync_between_flips;
+
+	if (num_vsyncs < MOD_STATS_NUM_VSYNCS) {
+		if (num_vsyncs == 0) {
+			prev_vsync_in_ns =
+				time[index - 1].vupdate_timestamp_in_ns;
+
+			time[index].flip_to_vsync_time_in_us =
+				(timestamp_in_ns -
+					time[index - 1].flip_timestamp_in_ns) /
+					1000;
+		} else {
+			prev_vsync_in_ns =
+				time[index].vupdate_timestamp_in_ns;
+		}
 
-	time[index].vupdate_timestamp_in_ns = timestamp_in_ns;
-	if (time[index].num_vsync_between_flips < MOD_STATS_NUM_VSYNCS)
-		time[index].v_sync_time_in_us[time[index].num_vsync_between_flips] =
-			timestamp_in_ns - time[index - 1].vupdate_timestamp_in_ns;
-	time[index].flip_to_vsync_time_in_us =
-		timestamp_in_ns - time[index - 1].flip_timestamp_in_ns;
+		time[index].v_sync_time_in_us[num_vsyncs] =
+			(timestamp_in_ns - prev_vsync_in_ns) / 1000;
+	}
 
+	time[index].vupdate_timestamp_in_ns = timestamp_in_ns;
 	time[index].num_vsync_between_flips++;
 }
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 9fa3aaef3f33..b178176b72ac 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -92,7 +92,7 @@ enum amd_powergating_state {
 #define AMD_CG_SUPPORT_GFX_3D_CGLS		(1 << 21)
 #define AMD_CG_SUPPORT_DRM_MGCG			(1 << 22)
 #define AMD_CG_SUPPORT_DF_MGCG			(1 << 23)
-
+#define AMD_CG_SUPPORT_VCN_MGCG			(1 << 24)
 /* PG flags */
 #define AMD_PG_SUPPORT_GFX_PG			(1 << 0)
 #define AMD_PG_SUPPORT_GFX_SMG			(1 << 1)
@@ -108,6 +108,27 @@ enum amd_powergating_state {
 #define AMD_PG_SUPPORT_GFX_QUICK_MG		(1 << 11)
 #define AMD_PG_SUPPORT_GFX_PIPELINE		(1 << 12)
 #define AMD_PG_SUPPORT_MMHUB			(1 << 13)
+#define AMD_PG_SUPPORT_VCN			(1 << 14)
+
+enum PP_FEATURE_MASK {
+	PP_SCLK_DPM_MASK = 0x1,
+	PP_MCLK_DPM_MASK = 0x2,
+	PP_PCIE_DPM_MASK = 0x4,
+	PP_SCLK_DEEP_SLEEP_MASK = 0x8,
+	PP_POWER_CONTAINMENT_MASK = 0x10,
+	PP_UVD_HANDSHAKE_MASK = 0x20,
+	PP_SMC_VOLTAGE_CONTROL_MASK = 0x40,
+	PP_VBI_TIME_SUPPORT_MASK = 0x80,
+	PP_ULV_MASK = 0x100,
+	PP_ENABLE_GFX_CG_THRU_SMU = 0x200,
+	PP_CLOCK_STRETCH_MASK = 0x400,
+	PP_OD_FUZZY_FAN_CONTROL_MASK = 0x800,
+	PP_SOCCLK_DPM_MASK = 0x1000,
+	PP_DCEFCLK_DPM_MASK = 0x2000,
+	PP_OVERDRIVE_MASK = 0x4000,
+	PP_GFXOFF_MASK = 0x8000,
+	PP_ACG_MASK = 0x10000,
+};
 
 struct amd_ip_funcs {
 	/* Name of IP block */
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
index f730d0629020..b6f74bf4af02 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
@@ -2095,6 +2095,18 @@
 #define mmDC_GPIO_AUX_CTRL_2_BASE_IDX                                                                  2
 #define mmDC_GPIO_RXEN                                                                                 0x212f
 #define mmDC_GPIO_RXEN_BASE_IDX                                                                        2
+#define mmDC_GPIO_AUX_CTRL_3                                                                           0x2130
+#define mmDC_GPIO_AUX_CTRL_3_BASE_IDX                                                                  2
+#define mmDC_GPIO_AUX_CTRL_4                                                                           0x2131
+#define mmDC_GPIO_AUX_CTRL_4_BASE_IDX                                                                  2
+#define mmDC_GPIO_AUX_CTRL_5                                                                           0x2132
+#define mmDC_GPIO_AUX_CTRL_5_BASE_IDX                                                                  2
+#define mmAUXI2C_PAD_ALL_PWR_OK                                                                        0x2133
+#define mmAUXI2C_PAD_ALL_PWR_OK_BASE_IDX                                                               2
+#define mmDC_GPIO_PULLUPEN                                                                             0x2134
+#define mmDC_GPIO_PULLUPEN_BASE_IDX                                                                    2
+#define mmDC_GPIO_AUX_CTRL_6                                                                           0x2135
+#define mmDC_GPIO_AUX_CTRL_6_BASE_IDX                                                                  2
 #define mmBPHYC_DAC_MACRO_CNTL                                                                         0x2136
 #define mmBPHYC_DAC_MACRO_CNTL_BASE_IDX                                                                2
 #define mmDAC_MACRO_CNTL_RESERVED0                                                                     0x2136
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_sh_mask.h
index 6d3162c42957..bcd190a3fcdd 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_sh_mask.h
@@ -10971,6 +10971,158 @@
 #define DC_GPIO_RXEN__DC_GPIO_BLON_RXEN_MASK                                                                  0x00100000L
 #define DC_GPIO_RXEN__DC_GPIO_DIGON_RXEN_MASK                                                                 0x00200000L
 #define DC_GPIO_RXEN__DC_GPIO_ENA_BL_RXEN_MASK                                                                0x00400000L
+//DC_GPIO_AUX_CTRL_3
+#define DC_GPIO_AUX_CTRL_3__AUX1_NEN_RTERM__SHIFT                                                             0x0
+#define DC_GPIO_AUX_CTRL_3__AUX2_NEN_RTERM__SHIFT                                                             0x1
+#define DC_GPIO_AUX_CTRL_3__AUX3_NEN_RTERM__SHIFT                                                             0x2
+#define DC_GPIO_AUX_CTRL_3__AUX4_NEN_RTERM__SHIFT                                                             0x3
+#define DC_GPIO_AUX_CTRL_3__AUX5_NEN_RTERM__SHIFT                                                             0x4
+#define DC_GPIO_AUX_CTRL_3__AUX6_NEN_RTERM__SHIFT                                                             0x5
+#define DC_GPIO_AUX_CTRL_3__AUX1_DP_DN_SWAP__SHIFT                                                            0x8
+#define DC_GPIO_AUX_CTRL_3__AUX2_DP_DN_SWAP__SHIFT                                                            0x9
+#define DC_GPIO_AUX_CTRL_3__AUX3_DP_DN_SWAP__SHIFT                                                            0xa
+#define DC_GPIO_AUX_CTRL_3__AUX4_DP_DN_SWAP__SHIFT                                                            0xb
+#define DC_GPIO_AUX_CTRL_3__AUX5_DP_DN_SWAP__SHIFT                                                            0xc
+#define DC_GPIO_AUX_CTRL_3__AUX6_DP_DN_SWAP__SHIFT                                                            0xd
+#define DC_GPIO_AUX_CTRL_3__AUX1_HYS_TUNE__SHIFT                                                              0x10
+#define DC_GPIO_AUX_CTRL_3__AUX2_HYS_TUNE__SHIFT                                                              0x12
+#define DC_GPIO_AUX_CTRL_3__AUX3_HYS_TUNE__SHIFT                                                              0x14
+#define DC_GPIO_AUX_CTRL_3__AUX4_HYS_TUNE__SHIFT                                                              0x16
+#define DC_GPIO_AUX_CTRL_3__AUX5_HYS_TUNE__SHIFT                                                              0x18
+#define DC_GPIO_AUX_CTRL_3__AUX6_HYS_TUNE__SHIFT                                                              0x1a
+#define DC_GPIO_AUX_CTRL_3__AUX1_NEN_RTERM_MASK                                                               0x00000001L
+#define DC_GPIO_AUX_CTRL_3__AUX2_NEN_RTERM_MASK                                                               0x00000002L
+#define DC_GPIO_AUX_CTRL_3__AUX3_NEN_RTERM_MASK                                                               0x00000004L
+#define DC_GPIO_AUX_CTRL_3__AUX4_NEN_RTERM_MASK                                                               0x00000008L
+#define DC_GPIO_AUX_CTRL_3__AUX5_NEN_RTERM_MASK                                                               0x00000010L
+#define DC_GPIO_AUX_CTRL_3__AUX6_NEN_RTERM_MASK                                                               0x00000020L
+#define DC_GPIO_AUX_CTRL_3__AUX1_DP_DN_SWAP_MASK                                                              0x00000100L
+#define DC_GPIO_AUX_CTRL_3__AUX2_DP_DN_SWAP_MASK                                                              0x00000200L
+#define DC_GPIO_AUX_CTRL_3__AUX3_DP_DN_SWAP_MASK                                                              0x00000400L
+#define DC_GPIO_AUX_CTRL_3__AUX4_DP_DN_SWAP_MASK                                                              0x00000800L
+#define DC_GPIO_AUX_CTRL_3__AUX5_DP_DN_SWAP_MASK                                                              0x00001000L
+#define DC_GPIO_AUX_CTRL_3__AUX6_DP_DN_SWAP_MASK                                                              0x00002000L
+#define DC_GPIO_AUX_CTRL_3__AUX1_HYS_TUNE_MASK                                                                0x00030000L
+#define DC_GPIO_AUX_CTRL_3__AUX2_HYS_TUNE_MASK                                                                0x000C0000L
+#define DC_GPIO_AUX_CTRL_3__AUX3_HYS_TUNE_MASK                                                                0x00300000L
+#define DC_GPIO_AUX_CTRL_3__AUX4_HYS_TUNE_MASK                                                                0x00C00000L
+#define DC_GPIO_AUX_CTRL_3__AUX5_HYS_TUNE_MASK                                                                0x03000000L
+#define DC_GPIO_AUX_CTRL_3__AUX6_HYS_TUNE_MASK                                                                0x0C000000L
+//DC_GPIO_AUX_CTRL_4
+#define DC_GPIO_AUX_CTRL_4__AUX1_AUX_CTRL__SHIFT                                                              0x0
+#define DC_GPIO_AUX_CTRL_4__AUX2_AUX_CTRL__SHIFT                                                              0x4
+#define DC_GPIO_AUX_CTRL_4__AUX3_AUX_CTRL__SHIFT                                                              0x8
+#define DC_GPIO_AUX_CTRL_4__AUX4_AUX_CTRL__SHIFT                                                              0xc
+#define DC_GPIO_AUX_CTRL_4__AUX5_AUX_CTRL__SHIFT                                                              0x10
+#define DC_GPIO_AUX_CTRL_4__AUX6_AUX_CTRL__SHIFT                                                              0x14
+#define DC_GPIO_AUX_CTRL_4__AUX1_AUX_CTRL_MASK                                                                0x0000000FL
+#define DC_GPIO_AUX_CTRL_4__AUX2_AUX_CTRL_MASK                                                                0x000000F0L
+#define DC_GPIO_AUX_CTRL_4__AUX3_AUX_CTRL_MASK                                                                0x00000F00L
+#define DC_GPIO_AUX_CTRL_4__AUX4_AUX_CTRL_MASK                                                                0x0000F000L
+#define DC_GPIO_AUX_CTRL_4__AUX5_AUX_CTRL_MASK                                                                0x000F0000L
+#define DC_GPIO_AUX_CTRL_4__AUX6_AUX_CTRL_MASK                                                                0x00F00000L
+//DC_GPIO_AUX_CTRL_5
+#define DC_GPIO_AUX_CTRL_5__AUX1_VOD_TUNE__SHIFT                                                              0x0
+#define DC_GPIO_AUX_CTRL_5__AUX2_VOD_TUNE__SHIFT                                                              0x2
+#define DC_GPIO_AUX_CTRL_5__AUX3_VOD_TUNE__SHIFT                                                              0x4
+#define DC_GPIO_AUX_CTRL_5__AUX4_VOD_TUNE__SHIFT                                                              0x6
+#define DC_GPIO_AUX_CTRL_5__AUX5_VOD_TUNE__SHIFT                                                              0x8
+#define DC_GPIO_AUX_CTRL_5__AUX6_VOD_TUNE__SHIFT                                                              0xa
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD1_I2CMODE__SHIFT                                                           0xc
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD2_I2CMODE__SHIFT                                                           0xd
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD3_I2CMODE__SHIFT                                                           0xe
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD4_I2CMODE__SHIFT                                                           0xf
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD5_I2CMODE__SHIFT                                                           0x10
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD6_I2CMODE__SHIFT                                                           0x11
+#define DC_GPIO_AUX_CTRL_5__DDC1_I2C_VPH_1V2_EN__SHIFT                                                        0x12
+#define DC_GPIO_AUX_CTRL_5__DDC2_I2C_VPH_1V2_EN__SHIFT                                                        0x13
+#define DC_GPIO_AUX_CTRL_5__DDC3_I2C_VPH_1V2_EN__SHIFT                                                        0x14
+#define DC_GPIO_AUX_CTRL_5__DDC4_I2C_VPH_1V2_EN__SHIFT                                                        0x15
+#define DC_GPIO_AUX_CTRL_5__DDC5_I2C_VPH_1V2_EN__SHIFT                                                        0x16
+#define DC_GPIO_AUX_CTRL_5__DDC6_I2C_VPH_1V2_EN__SHIFT                                                        0x17
+#define DC_GPIO_AUX_CTRL_5__DDC1_PAD_I2C_CTRL__SHIFT                                                          0x18
+#define DC_GPIO_AUX_CTRL_5__DDC2_PAD_I2C_CTRL__SHIFT                                                          0x19
+#define DC_GPIO_AUX_CTRL_5__DDC3_PAD_I2C_CTRL__SHIFT                                                          0x1a
+#define DC_GPIO_AUX_CTRL_5__DDC4_PAD_I2C_CTRL__SHIFT                                                          0x1b
+#define DC_GPIO_AUX_CTRL_5__DDC5_PAD_I2C_CTRL__SHIFT                                                          0x1c
+#define DC_GPIO_AUX_CTRL_5__DDC6_PAD_I2C_CTRL__SHIFT                                                          0x1d
+#define DC_GPIO_AUX_CTRL_5__AUX1_VOD_TUNE_MASK                                                                0x00000003L
+#define DC_GPIO_AUX_CTRL_5__AUX2_VOD_TUNE_MASK                                                                0x0000000CL
+#define DC_GPIO_AUX_CTRL_5__AUX3_VOD_TUNE_MASK                                                                0x00000030L
+#define DC_GPIO_AUX_CTRL_5__AUX4_VOD_TUNE_MASK                                                                0x000000C0L
+#define DC_GPIO_AUX_CTRL_5__AUX5_VOD_TUNE_MASK                                                                0x00000300L
+#define DC_GPIO_AUX_CTRL_5__AUX6_VOD_TUNE_MASK                                                                0x00000C00L
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD1_I2CMODE_MASK                                                             0x00001000L
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD2_I2CMODE_MASK                                                             0x00002000L
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD3_I2CMODE_MASK                                                             0x00004000L
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD4_I2CMODE_MASK                                                             0x00008000L
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD5_I2CMODE_MASK                                                             0x00010000L
+#define DC_GPIO_AUX_CTRL_5__DDC_PAD6_I2CMODE_MASK                                                             0x00020000L
+#define DC_GPIO_AUX_CTRL_5__DDC1_I2C_VPH_1V2_EN_MASK                                                          0x00040000L
+#define DC_GPIO_AUX_CTRL_5__DDC2_I2C_VPH_1V2_EN_MASK                                                          0x00080000L
+#define DC_GPIO_AUX_CTRL_5__DDC3_I2C_VPH_1V2_EN_MASK                                                          0x00100000L
+#define DC_GPIO_AUX_CTRL_5__DDC4_I2C_VPH_1V2_EN_MASK                                                          0x00200000L
+#define DC_GPIO_AUX_CTRL_5__DDC5_I2C_VPH_1V2_EN_MASK                                                          0x00400000L
+#define DC_GPIO_AUX_CTRL_5__DDC6_I2C_VPH_1V2_EN_MASK                                                          0x00800000L
+#define DC_GPIO_AUX_CTRL_5__DDC1_PAD_I2C_CTRL_MASK                                                            0x01000000L
+#define DC_GPIO_AUX_CTRL_5__DDC2_PAD_I2C_CTRL_MASK                                                            0x02000000L
+#define DC_GPIO_AUX_CTRL_5__DDC3_PAD_I2C_CTRL_MASK                                                            0x04000000L
+#define DC_GPIO_AUX_CTRL_5__DDC4_PAD_I2C_CTRL_MASK                                                            0x08000000L
+#define DC_GPIO_AUX_CTRL_5__DDC5_PAD_I2C_CTRL_MASK                                                            0x10000000L
+#define DC_GPIO_AUX_CTRL_5__DDC6_PAD_I2C_CTRL_MASK                                                            0x20000000L
+//AUXI2C_PAD_ALL_PWR_OK
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY1_ALL_PWR_OK__SHIFT                                                  0x0
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY2_ALL_PWR_OK__SHIFT                                                  0x1
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY3_ALL_PWR_OK__SHIFT                                                  0x2
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY4_ALL_PWR_OK__SHIFT                                                  0x3
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY5_ALL_PWR_OK__SHIFT                                                  0x4
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY6_ALL_PWR_OK__SHIFT                                                  0x5
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY1_ALL_PWR_OK_MASK                                                    0x00000001L
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY2_ALL_PWR_OK_MASK                                                    0x00000002L
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY3_ALL_PWR_OK_MASK                                                    0x00000004L
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY4_ALL_PWR_OK_MASK                                                    0x00000008L
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY5_ALL_PWR_OK_MASK                                                    0x00000010L
+#define AUXI2C_PAD_ALL_PWR_OK__AUXI2C_PHY6_ALL_PWR_OK_MASK                                                    0x00000020L
+//DC_GPIO_PULLUPEN
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICA_PU_EN__SHIFT                                                       0x0
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICB_PU_EN__SHIFT                                                       0x1
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICC_PU_EN__SHIFT                                                       0x2
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICD_PU_EN__SHIFT                                                       0x3
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICE_PU_EN__SHIFT                                                       0x4
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICF_PU_EN__SHIFT                                                       0x5
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICG_PU_EN__SHIFT                                                       0x6
+#define DC_GPIO_PULLUPEN__DC_GPIO_HSYNCA_PU_EN__SHIFT                                                         0x8
+#define DC_GPIO_PULLUPEN__DC_GPIO_VSYNCA_PU_EN__SHIFT                                                         0x9
+#define DC_GPIO_PULLUPEN__DC_GPIO_HPD1_PU_EN__SHIFT                                                           0xe
+#define DC_GPIO_PULLUPEN__DC_GPIO_BLON_PU_EN__SHIFT                                                           0x14
+#define DC_GPIO_PULLUPEN__DC_GPIO_DIGON_PU_EN__SHIFT                                                          0x15
+#define DC_GPIO_PULLUPEN__DC_GPIO_ENA_BL_PU_EN__SHIFT                                                         0x16
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICA_PU_EN_MASK                                                         0x00000001L
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICB_PU_EN_MASK                                                         0x00000002L
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICC_PU_EN_MASK                                                         0x00000004L
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICD_PU_EN_MASK                                                         0x00000008L
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICE_PU_EN_MASK                                                         0x00000010L
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICF_PU_EN_MASK                                                         0x00000020L
+#define DC_GPIO_PULLUPEN__DC_GPIO_GENERICG_PU_EN_MASK                                                         0x00000040L
+#define DC_GPIO_PULLUPEN__DC_GPIO_HSYNCA_PU_EN_MASK                                                           0x00000100L
+#define DC_GPIO_PULLUPEN__DC_GPIO_VSYNCA_PU_EN_MASK                                                           0x00000200L
+#define DC_GPIO_PULLUPEN__DC_GPIO_HPD1_PU_EN_MASK                                                             0x00004000L
+#define DC_GPIO_PULLUPEN__DC_GPIO_BLON_PU_EN_MASK                                                             0x00100000L
+#define DC_GPIO_PULLUPEN__DC_GPIO_DIGON_PU_EN_MASK                                                            0x00200000L
+#define DC_GPIO_PULLUPEN__DC_GPIO_ENA_BL_PU_EN_MASK                                                           0x00400000L
+//DC_GPIO_AUX_CTRL_6
+#define DC_GPIO_AUX_CTRL_6__AUX1_PAD_RXSEL__SHIFT                                                             0x0
+#define DC_GPIO_AUX_CTRL_6__AUX2_PAD_RXSEL__SHIFT                                                             0x2
+#define DC_GPIO_AUX_CTRL_6__AUX3_PAD_RXSEL__SHIFT                                                             0x4
+#define DC_GPIO_AUX_CTRL_6__AUX4_PAD_RXSEL__SHIFT                                                             0x6
+#define DC_GPIO_AUX_CTRL_6__AUX5_PAD_RXSEL__SHIFT                                                             0x8
+#define DC_GPIO_AUX_CTRL_6__AUX6_PAD_RXSEL__SHIFT                                                             0xa
+#define DC_GPIO_AUX_CTRL_6__AUX1_PAD_RXSEL_MASK                                                               0x00000003L
+#define DC_GPIO_AUX_CTRL_6__AUX2_PAD_RXSEL_MASK                                                               0x0000000CL
+#define DC_GPIO_AUX_CTRL_6__AUX3_PAD_RXSEL_MASK                                                               0x00000030L
+#define DC_GPIO_AUX_CTRL_6__AUX4_PAD_RXSEL_MASK                                                               0x000000C0L
+#define DC_GPIO_AUX_CTRL_6__AUX5_PAD_RXSEL_MASK                                                               0x00000300L
+#define DC_GPIO_AUX_CTRL_6__AUX6_PAD_RXSEL_MASK                                                               0x00000C00L
 //BPHYC_DAC_MACRO_CNTL
 #define BPHYC_DAC_MACRO_CNTL__BPHYC_DAC_WHITE_LEVEL__SHIFT                                                    0x0
 #define BPHYC_DAC_MACRO_CNTL__BPHYC_DAC_WHITE_FINE_CONTROL__SHIFT                                             0x8
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_offset.h
index 4ccf9681c45d..721c61171045 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_offset.h
@@ -3895,6 +3895,10 @@
 #define mmCM0_CM_MEM_PWR_CTRL_BASE_IDX                                                                 2
 #define mmCM0_CM_MEM_PWR_STATUS                                                                        0x0d33
 #define mmCM0_CM_MEM_PWR_STATUS_BASE_IDX                                                               2
+#define mmCM0_CM_TEST_DEBUG_INDEX                                                                      0x0d35
+#define mmCM0_CM_TEST_DEBUG_INDEX_BASE_IDX                                                             2
+#define mmCM0_CM_TEST_DEBUG_DATA                                                                       0x0d36
+#define mmCM0_CM_TEST_DEBUG_DATA_BASE_IDX                                                              2
 
 
 // addressBlock: dce_dc_dpp0_dispdec_dpp_dcperfmon_dc_perfmon_dispdec
@@ -4367,7 +4371,10 @@
 #define mmCM1_CM_MEM_PWR_CTRL_BASE_IDX                                                                 2
 #define mmCM1_CM_MEM_PWR_STATUS                                                                        0x0e4e
 #define mmCM1_CM_MEM_PWR_STATUS_BASE_IDX                                                               2
-
+#define mmCM1_CM_TEST_DEBUG_INDEX                                                                      0x0e50
+#define mmCM1_CM_TEST_DEBUG_INDEX_BASE_IDX                                                             2
+#define mmCM1_CM_TEST_DEBUG_DATA                                                                       0x0e51
+#define mmCM1_CM_TEST_DEBUG_DATA_BASE_IDX                                                              2
 
 // addressBlock: dce_dc_dpp1_dispdec_dpp_dcperfmon_dc_perfmon_dispdec
 // base address: 0x399c
@@ -4839,7 +4846,10 @@
 #define mmCM2_CM_MEM_PWR_CTRL_BASE_IDX                                                                 2
 #define mmCM2_CM_MEM_PWR_STATUS                                                                        0x0f69
 #define mmCM2_CM_MEM_PWR_STATUS_BASE_IDX                                                               2
-
+#define mmCM2_CM_TEST_DEBUG_INDEX                                                                      0x0f6b
+#define mmCM2_CM_TEST_DEBUG_INDEX_BASE_IDX                                                             2
+#define mmCM2_CM_TEST_DEBUG_DATA                                                                       0x0f6c
+#define mmCM2_CM_TEST_DEBUG_DATA_BASE_IDX                                                              2
 
 // addressBlock: dce_dc_dpp2_dispdec_dpp_dcperfmon_dc_perfmon_dispdec
 // base address: 0x3e08
@@ -5311,7 +5321,10 @@
 #define mmCM3_CM_MEM_PWR_CTRL_BASE_IDX                                                                 2
 #define mmCM3_CM_MEM_PWR_STATUS                                                                        0x1084
 #define mmCM3_CM_MEM_PWR_STATUS_BASE_IDX                                                               2
-
+#define mmCM3_CM_TEST_DEBUG_INDEX                                                                      0x1086
+#define mmCM3_CM_TEST_DEBUG_INDEX_BASE_IDX                                                             2
+#define mmCM3_CM_TEST_DEBUG_DATA                                                                       0x1087
+#define mmCM3_CM_TEST_DEBUG_DATA_BASE_IDX                                                              2
 
 // addressBlock: dce_dc_dpp3_dispdec_dpp_dcperfmon_dc_perfmon_dispdec
 // base address: 0x4274
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_sh_mask.h
index e2a2f114bd8e..e7c0cad41081 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_sh_mask.h
@@ -14049,6 +14049,14 @@
 #define CM0_CM_MEM_PWR_STATUS__RGAM_MEM_PWR_STATE__SHIFT                                                      0x2
 #define CM0_CM_MEM_PWR_STATUS__SHARED_MEM_PWR_STATE_MASK                                                      0x00000003L
 #define CM0_CM_MEM_PWR_STATUS__RGAM_MEM_PWR_STATE_MASK                                                        0x0000000CL
+//CM0_CM_TEST_DEBUG_INDEX
+#define CM0_CM_TEST_DEBUG_INDEX__CM_TEST_DEBUG_INDEX__SHIFT                                                   0x0
+#define CM0_CM_TEST_DEBUG_INDEX__CM_TEST_DEBUG_WRITE_EN__SHIFT                                                0x8
+#define CM0_CM_TEST_DEBUG_INDEX__CM_TEST_DEBUG_INDEX_MASK                                                     0x000000FFL
+#define CM0_CM_TEST_DEBUG_INDEX__CM_TEST_DEBUG_WRITE_EN_MASK                                                  0x00000100L
+//CM0_CM_TEST_DEBUG_DATA
+#define CM0_CM_TEST_DEBUG_DATA__CM_TEST_DEBUG_DATA__SHIFT                                                     0x0
+#define CM0_CM_TEST_DEBUG_DATA__CM_TEST_DEBUG_DATA_MASK                                                       0xFFFFFFFFL
 
 
 // addressBlock: dce_dc_dpp0_dispdec_dpp_dcperfmon_dc_perfmon_dispdec
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_default.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_default.h
new file mode 100644
index 000000000000..9e19e723081b
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_default.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2018  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _df_1_7_DEFAULT_HEADER
+#define _df_1_7_DEFAULT_HEADER
+
+#define mmFabricConfigAccessControl_DEFAULT						0x00000000
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_offset.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_offset.h
new file mode 100644
index 000000000000..e6044e27a913
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_offset.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2018  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _df_1_7_OFFSET_HEADER
+#define _df_1_7_OFFSET_HEADER
+
+#define mmFabricConfigAccessControl									0x0410
+#define mmFabricConfigAccessControl_BASE_IDX								0
+
+#define mmDF_PIE_AON0_DfGlobalClkGater									0x00fc
+#define mmDF_PIE_AON0_DfGlobalClkGater_BASE_IDX								0
+
+#define mmDF_CS_AON0_DramBaseAddress0									0x0044
+#define mmDF_CS_AON0_DramBaseAddress0_BASE_IDX								0
+
+#define mmDF_CS_AON0_CoherentSlaveModeCtrlA0								0x0214
+#define mmDF_CS_AON0_CoherentSlaveModeCtrlA0_BASE_IDX							0
+
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_sh_mask.h
new file mode 100644
index 000000000000..a78c99480e2d
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_1_7_sh_mask.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2018  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _df_1_7_SH_MASK_HEADER
+#define _df_1_7_SH_MASK_HEADER
+
+/* FabricConfigAccessControl */
+#define FabricConfigAccessControl__CfgRegInstAccEn__SHIFT						0x0
+#define FabricConfigAccessControl__CfgRegInstAccRegLock__SHIFT						0x1
+#define FabricConfigAccessControl__CfgRegInstID__SHIFT							0x10
+#define FabricConfigAccessControl__CfgRegInstAccEn_MASK							0x00000001L
+#define FabricConfigAccessControl__CfgRegInstAccRegLock_MASK						0x00000002L
+#define FabricConfigAccessControl__CfgRegInstID_MASK							0x00FF0000L
+
+/* DF_PIE_AON0_DfGlobalClkGater */
+#define DF_PIE_AON0_DfGlobalClkGater__MGCGMode__SHIFT							0x0
+#define DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK							0x0000000FL
+
+/* DF_CS_AON0_DramBaseAddress0 */
+#define DF_CS_AON0_DramBaseAddress0__AddrRngVal__SHIFT							0x0
+#define DF_CS_AON0_DramBaseAddress0__LgcyMmioHoleEn__SHIFT						0x1
+#define DF_CS_AON0_DramBaseAddress0__IntLvNumChan__SHIFT						0x4
+#define DF_CS_AON0_DramBaseAddress0__IntLvAddrSel__SHIFT						0x8
+#define DF_CS_AON0_DramBaseAddress0__DramBaseAddr__SHIFT						0xc
+#define DF_CS_AON0_DramBaseAddress0__AddrRngVal_MASK							0x00000001L
+#define DF_CS_AON0_DramBaseAddress0__LgcyMmioHoleEn_MASK						0x00000002L
+#define DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK							0x000000F0L
+#define DF_CS_AON0_DramBaseAddress0__IntLvAddrSel_MASK							0x00000700L
+#define DF_CS_AON0_DramBaseAddress0__DramBaseAddr_MASK							0xFFFFF000L
+
+//DF_CS_AON0_CoherentSlaveModeCtrlA0
+#define DF_CS_AON0_CoherentSlaveModeCtrlA0__ForceParWrRMW__SHIFT					0x3
+#define DF_CS_AON0_CoherentSlaveModeCtrlA0__ForceParWrRMW_MASK						0x00000008L
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_default.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_default.h
new file mode 100644
index 000000000000..e58c207ac980
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_default.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2018  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _df_3_6_DEFAULT_HEADER
+#define _df_3_6_DEFAULT_HEADER
+
+#define mmFabricConfigAccessControl_DEFAULT						0x00000000
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h
new file mode 100644
index 000000000000..a9575db8d7aa
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2018  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _df_3_6_OFFSET_HEADER
+#define _df_3_6_OFFSET_HEADER
+
+#define mmFabricConfigAccessControl									0x0410
+#define mmFabricConfigAccessControl_BASE_IDX								0
+
+#define mmDF_PIE_AON0_DfGlobalClkGater									0x00fc
+#define mmDF_PIE_AON0_DfGlobalClkGater_BASE_IDX								0
+
+#define mmDF_CS_UMC_AON0_DramBaseAddress0								0x0044
+#define mmDF_CS_UMC_AON0_DramBaseAddress0_BASE_IDX							0
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h
new file mode 100644
index 000000000000..88f7c69df6b9
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2018  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _df_3_6_SH_MASK_HEADER
+#define _df_3_6_SH_MASK_HEADER
+
+/* FabricConfigAccessControl */
+#define FabricConfigAccessControl__CfgRegInstAccEn__SHIFT						0x0
+#define FabricConfigAccessControl__CfgRegInstAccRegLock__SHIFT						0x1
+#define FabricConfigAccessControl__CfgRegInstID__SHIFT							0x10
+#define FabricConfigAccessControl__CfgRegInstAccEn_MASK							0x00000001L
+#define FabricConfigAccessControl__CfgRegInstAccRegLock_MASK						0x00000002L
+#define FabricConfigAccessControl__CfgRegInstID_MASK							0x00FF0000L
+
+/* DF_PIE_AON0_DfGlobalClkGater */
+#define DF_PIE_AON0_DfGlobalClkGater__MGCGMode__SHIFT							0x0
+#define DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK							0x0000000FL
+
+/* DF_CS_AON0_DramBaseAddress0 */
+#define DF_CS_UMC_AON0_DramBaseAddress0__AddrRngVal__SHIFT						0x0
+#define DF_CS_UMC_AON0_DramBaseAddress0__LgcyMmioHoleEn__SHIFT						0x1
+#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvNumChan__SHIFT						0x4
+#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvAddrSel__SHIFT						0x8
+#define DF_CS_UMC_AON0_DramBaseAddress0__DramBaseAddr__SHIFT						0xc
+#define DF_CS_UMC_AON0_DramBaseAddress0__AddrRngVal_MASK						0x00000001L
+#define DF_CS_UMC_AON0_DramBaseAddress0__LgcyMmioHoleEn_MASK						0x00000002L
+#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvNumChan_MASK						0x000000F0L
+#define DF_CS_UMC_AON0_DramBaseAddress0__IntLvAddrSel_MASK						0x00000700L
+#define DF_CS_UMC_AON0_DramBaseAddress0__DramBaseAddr_MASK						0xFFFFF000L
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h
index f696bbb643ef..7931502fa54f 100644
--- a/drivers/gpu/drm/amd/include/atombios.h
+++ b/drivers/gpu/drm/amd/include/atombios.h
@@ -632,6 +632,13 @@ typedef struct _COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_2
   ULONG ulReserved;
 }COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_2;
 
+typedef struct _COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_3
+{
+  COMPUTE_MEMORY_ENGINE_PLL_PARAMETERS_V4 ulClock;
+  USHORT  usMclk_fcw_frac;                  //fractional divider of fcw = usSclk_fcw_frac/65536
+  USHORT  usMclk_fcw_int;                   //integer divider of fcwc
+}COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_3;
+
 //Input parameter of DynamicMemorySettingsTable
 //when ATOM_COMPUTE_CLOCK_FREQ.ulComputeClockFlag = COMPUTE_MEMORY_PLL_PARAM
 typedef struct _DYNAMICE_MEMORY_SETTINGS_PARAMETER
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 0f5ad54d3fd3..c6c1666ac120 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -501,6 +501,32 @@ enum atom_cooling_solution_id{
   LIQUID_COOLING = 0x01
 };
 
+struct atom_firmware_info_v3_2 {
+  struct atom_common_table_header table_header;
+  uint32_t firmware_revision;
+  uint32_t bootup_sclk_in10khz;
+  uint32_t bootup_mclk_in10khz;
+  uint32_t firmware_capability;             // enum atombios_firmware_capability
+  uint32_t main_call_parser_entry;          /* direct address of main parser call in VBIOS binary. */
+  uint32_t bios_scratch_reg_startaddr;      // 1st bios scratch register dword address
+  uint16_t bootup_vddc_mv;
+  uint16_t bootup_vddci_mv;
+  uint16_t bootup_mvddc_mv;
+  uint16_t bootup_vddgfx_mv;
+  uint8_t  mem_module_id;
+  uint8_t  coolingsolution_id;              /*0: Air cooling; 1: Liquid cooling ... */
+  uint8_t  reserved1[2];
+  uint32_t mc_baseaddr_high;
+  uint32_t mc_baseaddr_low;
+  uint8_t  board_i2c_feature_id;            // enum of atom_board_i2c_feature_id_def
+  uint8_t  board_i2c_feature_gpio_id;       // i2c id find in gpio_lut data table gpio_id
+  uint8_t  board_i2c_feature_slave_addr;
+  uint8_t  reserved3;
+  uint16_t bootup_mvddq_mv;
+  uint16_t bootup_mvpp_mv;
+  uint32_t zfbstartaddrin16mb;
+  uint32_t reserved2[3];
+};
 
 /* 
   ***************************************************************************
@@ -1169,7 +1195,64 @@ struct  atom_gfx_info_v2_2
   uint32_t rlc_gpu_timer_refclk; 
 };
 
+struct  atom_gfx_info_v2_3 {
+  struct  atom_common_table_header  table_header;
+  uint8_t gfxip_min_ver;
+  uint8_t gfxip_max_ver;
+  uint8_t max_shader_engines;
+  uint8_t max_tile_pipes;
+  uint8_t max_cu_per_sh;
+  uint8_t max_sh_per_se;
+  uint8_t max_backends_per_se;
+  uint8_t max_texture_channel_caches;
+  uint32_t regaddr_cp_dma_src_addr;
+  uint32_t regaddr_cp_dma_src_addr_hi;
+  uint32_t regaddr_cp_dma_dst_addr;
+  uint32_t regaddr_cp_dma_dst_addr_hi;
+  uint32_t regaddr_cp_dma_command;
+  uint32_t regaddr_cp_status;
+  uint32_t regaddr_rlc_gpu_clock_32;
+  uint32_t rlc_gpu_timer_refclk;
+  uint8_t active_cu_per_sh;
+  uint8_t active_rb_per_se;
+  uint16_t gcgoldenoffset;
+  uint32_t rm21_sram_vmin_value;
+};
 
+struct  atom_gfx_info_v2_4 {
+  struct  atom_common_table_header  table_header;
+  uint8_t gfxip_min_ver;
+  uint8_t gfxip_max_ver;
+  uint8_t gc_num_se;
+  uint8_t max_tile_pipes;
+  uint8_t gc_num_cu_per_sh;
+  uint8_t gc_num_sh_per_se;
+  uint8_t gc_num_rb_per_se;
+  uint8_t gc_num_tccs;
+  uint32_t regaddr_cp_dma_src_addr;
+  uint32_t regaddr_cp_dma_src_addr_hi;
+  uint32_t regaddr_cp_dma_dst_addr;
+  uint32_t regaddr_cp_dma_dst_addr_hi;
+  uint32_t regaddr_cp_dma_command;
+  uint32_t regaddr_cp_status;
+  uint32_t regaddr_rlc_gpu_clock_32;
+  uint32_t rlc_gpu_timer_refclk;
+  uint8_t active_cu_per_sh;
+  uint8_t active_rb_per_se;
+  uint16_t gcgoldenoffset;
+  uint16_t gc_num_gprs;
+  uint16_t gc_gsprim_buff_depth;
+  uint16_t gc_parameter_cache_depth;
+  uint16_t gc_wave_size;
+  uint16_t gc_max_waves_per_simd;
+  uint16_t gc_lds_size;
+  uint8_t gc_num_max_gs_thds;
+  uint8_t gc_gs_table_depth;
+  uint8_t gc_double_offchip_lds_buffer;
+  uint8_t gc_max_scratch_slots_per_cu;
+  uint32_t sram_rm_fuses_val;
+  uint32_t sram_custom_rm_fuses_val;
+};
 
 /* 
   ***************************************************************************
@@ -1198,6 +1281,76 @@ struct atom_smu_info_v3_1
   uint8_t  fw_ctf_polarity;         // GPIO polarity for CTF
 };
 
+struct atom_smu_info_v3_2 {
+  struct   atom_common_table_header  table_header;
+  uint8_t  smuip_min_ver;
+  uint8_t  smuip_max_ver;
+  uint8_t  smu_rsd1;
+  uint8_t  gpuclk_ss_mode;
+  uint16_t sclk_ss_percentage;
+  uint16_t sclk_ss_rate_10hz;
+  uint16_t gpuclk_ss_percentage;    // in unit of 0.001%
+  uint16_t gpuclk_ss_rate_10hz;
+  uint32_t core_refclk_10khz;
+  uint8_t  ac_dc_gpio_bit;          // GPIO bit shift in SMU_GPIOPAD_A  configured for AC/DC switching, =0xff means invalid
+  uint8_t  ac_dc_polarity;          // GPIO polarity for AC/DC switching
+  uint8_t  vr0hot_gpio_bit;         // GPIO bit shift in SMU_GPIOPAD_A  configured for VR0 HOT event, =0xff means invalid
+  uint8_t  vr0hot_polarity;         // GPIO polarity for VR0 HOT event
+  uint8_t  vr1hot_gpio_bit;         // GPIO bit shift in SMU_GPIOPAD_A configured for VR1 HOT event , =0xff means invalid
+  uint8_t  vr1hot_polarity;         // GPIO polarity for VR1 HOT event
+  uint8_t  fw_ctf_gpio_bit;         // GPIO bit shift in SMU_GPIOPAD_A configured for CTF, =0xff means invalid
+  uint8_t  fw_ctf_polarity;         // GPIO polarity for CTF
+  uint8_t  pcc_gpio_bit;            // GPIO bit shift in SMU_GPIOPAD_A configured for PCC, =0xff means invalid
+  uint8_t  pcc_gpio_polarity;       // GPIO polarity for CTF
+  uint16_t smugoldenoffset;
+  uint32_t gpupll_vco_freq_10khz;
+  uint32_t bootup_smnclk_10khz;
+  uint32_t bootup_socclk_10khz;
+  uint32_t bootup_mp0clk_10khz;
+  uint32_t bootup_mp1clk_10khz;
+  uint32_t bootup_lclk_10khz;
+  uint32_t bootup_dcefclk_10khz;
+  uint32_t ctf_threshold_override_value;
+  uint32_t reserved[5];
+};
+
+struct atom_smu_info_v3_3 {
+  struct   atom_common_table_header  table_header;
+  uint8_t  smuip_min_ver;
+  uint8_t  smuip_max_ver;
+  uint8_t  smu_rsd1;
+  uint8_t  gpuclk_ss_mode;
+  uint16_t sclk_ss_percentage;
+  uint16_t sclk_ss_rate_10hz;
+  uint16_t gpuclk_ss_percentage;    // in unit of 0.001%
+  uint16_t gpuclk_ss_rate_10hz;
+  uint32_t core_refclk_10khz;
+  uint8_t  ac_dc_gpio_bit;          // GPIO bit shift in SMU_GPIOPAD_A  configured for AC/DC switching, =0xff means invalid
+  uint8_t  ac_dc_polarity;          // GPIO polarity for AC/DC switching
+  uint8_t  vr0hot_gpio_bit;         // GPIO bit shift in SMU_GPIOPAD_A  configured for VR0 HOT event, =0xff means invalid
+  uint8_t  vr0hot_polarity;         // GPIO polarity for VR0 HOT event
+  uint8_t  vr1hot_gpio_bit;         // GPIO bit shift in SMU_GPIOPAD_A configured for VR1 HOT event , =0xff means invalid
+  uint8_t  vr1hot_polarity;         // GPIO polarity for VR1 HOT event
+  uint8_t  fw_ctf_gpio_bit;         // GPIO bit shift in SMU_GPIOPAD_A configured for CTF, =0xff means invalid
+  uint8_t  fw_ctf_polarity;         // GPIO polarity for CTF
+  uint8_t  pcc_gpio_bit;            // GPIO bit shift in SMU_GPIOPAD_A configured for PCC, =0xff means invalid
+  uint8_t  pcc_gpio_polarity;       // GPIO polarity for CTF
+  uint16_t smugoldenoffset;
+  uint32_t gpupll_vco_freq_10khz;
+  uint32_t bootup_smnclk_10khz;
+  uint32_t bootup_socclk_10khz;
+  uint32_t bootup_mp0clk_10khz;
+  uint32_t bootup_mp1clk_10khz;
+  uint32_t bootup_lclk_10khz;
+  uint32_t bootup_dcefclk_10khz;
+  uint32_t ctf_threshold_override_value;
+  uint32_t syspll3_0_vco_freq_10khz;
+  uint32_t syspll3_1_vco_freq_10khz;
+  uint32_t bootup_fclk_10khz;
+  uint32_t bootup_waflclk_10khz;
+  uint32_t reserved[3];
+};
+
 /*
  ***************************************************************************
    Data Table smc_dpm_info  structure
@@ -1283,7 +1436,6 @@ struct atom_smc_dpm_info_v4_1
 	uint32_t boardreserved[10];
 };
 
-
 /* 
   ***************************************************************************
     Data Table asic_profiling_info  structure
@@ -1864,6 +2016,55 @@ enum atom_smu9_syspll0_clock_id
   SMU9_SYSPLL0_DISPCLK_ID  = 11,      //	DISPCLK
 };
 
+enum atom_smu11_syspll_id {
+  SMU11_SYSPLL0_ID            = 0,
+  SMU11_SYSPLL1_0_ID          = 1,
+  SMU11_SYSPLL1_1_ID          = 2,
+  SMU11_SYSPLL1_2_ID          = 3,
+  SMU11_SYSPLL2_ID            = 4,
+  SMU11_SYSPLL3_0_ID          = 5,
+  SMU11_SYSPLL3_1_ID          = 6,
+};
+
+
+enum atom_smu11_syspll0_clock_id {
+  SMU11_SYSPLL0_SOCCLK_ID   = 0,       //	SOCCLK
+  SMU11_SYSPLL0_MP0CLK_ID   = 1,       //	MP0CLK
+  SMU11_SYSPLL0_DCLK_ID     = 2,       //	DCLK
+  SMU11_SYSPLL0_VCLK_ID     = 3,       //	VCLK
+  SMU11_SYSPLL0_ECLK_ID     = 4,       //	ECLK
+  SMU11_SYSPLL0_DCEFCLK_ID  = 5,       //	DCEFCLK
+};
+
+
+enum atom_smu11_syspll1_0_clock_id {
+  SMU11_SYSPLL1_0_UCLKA_ID   = 0,       // UCLK_a
+};
+
+enum atom_smu11_syspll1_1_clock_id {
+  SMU11_SYSPLL1_0_UCLKB_ID   = 0,       // UCLK_b
+};
+
+enum atom_smu11_syspll1_2_clock_id {
+  SMU11_SYSPLL1_0_FCLK_ID   = 0,        // FCLK
+};
+
+enum atom_smu11_syspll2_clock_id {
+  SMU11_SYSPLL2_GFXCLK_ID   = 0,        // GFXCLK
+};
+
+enum atom_smu11_syspll3_0_clock_id {
+  SMU11_SYSPLL3_0_WAFCLK_ID = 0,       //	WAFCLK
+  SMU11_SYSPLL3_0_DISPCLK_ID = 1,      //	DISPCLK
+  SMU11_SYSPLL3_0_DPREFCLK_ID = 2,     //	DPREFCLK
+};
+
+enum atom_smu11_syspll3_1_clock_id {
+  SMU11_SYSPLL3_1_MP1CLK_ID = 0,       //	MP1CLK
+  SMU11_SYSPLL3_1_SMNCLK_ID = 1,       //	SMNCLK
+  SMU11_SYSPLL3_1_LCLK_ID = 2,         //	LCLK
+};
+
 struct  atom_get_smu_clock_info_output_parameters_v3_1
 {
   union {
diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h
index f2814ae7ecdd..a69deb3a2ac0 100644
--- a/drivers/gpu/drm/amd/include/cgs_common.h
+++ b/drivers/gpu/drm/amd/include/cgs_common.h
@@ -42,20 +42,6 @@ enum cgs_ind_reg {
 	CGS_IND_REG__AUDIO_ENDPT
 };
 
-/**
- * enum cgs_engine - Engines that can be statically power-gated
- */
-enum cgs_engine {
-	CGS_ENGINE__UVD,
-	CGS_ENGINE__VCE,
-	CGS_ENGINE__VP8,
-	CGS_ENGINE__ACP_DMA,
-	CGS_ENGINE__ACP_DSP0,
-	CGS_ENGINE__ACP_DSP1,
-	CGS_ENGINE__ISP,
-	/* ... */
-};
-
 /*
  * enum cgs_ucode_id - Firmware types for different IPs
  */
@@ -76,17 +62,6 @@ enum cgs_ucode_id {
 	CGS_UCODE_ID_MAXIMUM,
 };
 
-/*
- * enum cgs_resource_type - GPU resource type
- */
-enum cgs_resource_type {
-	CGS_RESOURCE_TYPE_MMIO = 0,
-	CGS_RESOURCE_TYPE_FB,
-	CGS_RESOURCE_TYPE_IO,
-	CGS_RESOURCE_TYPE_DOORBELL,
-	CGS_RESOURCE_TYPE_ROM,
-};
-
 /**
  * struct cgs_firmware_info - Firmware information
  */
@@ -104,17 +79,6 @@ struct cgs_firmware_info {
 	bool			is_kicker;
 };
 
-struct cgs_mode_info {
-	uint32_t		refresh_rate;
-	uint32_t		vblank_time_us;
-};
-
-struct cgs_display_info {
-	uint32_t		display_count;
-	uint32_t		active_display_mask;
-	struct cgs_mode_info *mode_info;
-};
-
 typedef unsigned long cgs_handle_t;
 
 /**
@@ -170,119 +134,18 @@ typedef void (*cgs_write_ind_register_t)(struct cgs_device *cgs_device, enum cgs
 #define CGS_WREG32_FIELD_IND(device, space, reg, field, val)	\
 	cgs_write_ind_register(device, space, ix##reg, (cgs_read_ind_register(device, space, ix##reg) & ~CGS_REG_FIELD_MASK(reg, field)) | (val) << CGS_REG_FIELD_SHIFT(reg, field))
 
-/**
- * cgs_get_pci_resource() - provide access to a device resource (PCI BAR)
- * @cgs_device:	opaque device handle
- * @resource_type:	Type of Resource (MMIO, IO, ROM, FB, DOORBELL)
- * @size:	size of the region
- * @offset:	offset from the start of the region
- * @resource_base:	base address (not including offset) returned
- *
- * Return: 0 on success, -errno otherwise
- */
-typedef int (*cgs_get_pci_resource_t)(struct cgs_device *cgs_device,
-				      enum cgs_resource_type resource_type,
-				      uint64_t size,
-				      uint64_t offset,
-				      uint64_t *resource_base);
-
-/**
- * cgs_atom_get_data_table() - Get a pointer to an ATOM BIOS data table
- * @cgs_device:	opaque device handle
- * @table:	data table index
- * @size:	size of the table (output, may be NULL)
- * @frev:	table format revision (output, may be NULL)
- * @crev:	table content revision (output, may be NULL)
- *
- * Return: Pointer to start of the table, or NULL on failure
- */
-typedef const void *(*cgs_atom_get_data_table_t)(
-	struct cgs_device *cgs_device, unsigned table,
-	uint16_t *size, uint8_t *frev, uint8_t *crev);
-
-/**
- * cgs_atom_get_cmd_table_revs() - Get ATOM BIOS command table revisions
- * @cgs_device:	opaque device handle
- * @table:	data table index
- * @frev:	table format revision (output, may be NULL)
- * @crev:	table content revision (output, may be NULL)
- *
- * Return: 0 on success, -errno otherwise
- */
-typedef int (*cgs_atom_get_cmd_table_revs_t)(struct cgs_device *cgs_device, unsigned table,
-					     uint8_t *frev, uint8_t *crev);
-
-/**
- * cgs_atom_exec_cmd_table() - Execute an ATOM BIOS command table
- * @cgs_device: opaque device handle
- * @table:	command table index
- * @args:	arguments
- *
- * Return: 0 on success, -errno otherwise
- */
-typedef int (*cgs_atom_exec_cmd_table_t)(struct cgs_device *cgs_device,
-					 unsigned table, void *args);
-
-/**
- * cgs_get_firmware_info - Get the firmware information from core driver
- * @cgs_device: opaque device handle
- * @type: the firmware type
- * @info: returend firmware information
- *
- * Return: 0 on success, -errno otherwise
- */
 typedef int (*cgs_get_firmware_info)(struct cgs_device *cgs_device,
 				     enum cgs_ucode_id type,
 				     struct cgs_firmware_info *info);
 
-typedef int (*cgs_rel_firmware)(struct cgs_device *cgs_device,
-					 enum cgs_ucode_id type);
-
-typedef int(*cgs_set_powergating_state)(struct cgs_device *cgs_device,
-				  enum amd_ip_block_type block_type,
-				  enum amd_powergating_state state);
-
-typedef int(*cgs_set_clockgating_state)(struct cgs_device *cgs_device,
-				  enum amd_ip_block_type block_type,
-				  enum amd_clockgating_state state);
-
-typedef int(*cgs_get_active_displays_info)(
-					struct cgs_device *cgs_device,
-					struct cgs_display_info *info);
-
-typedef int (*cgs_notify_dpm_enabled)(struct cgs_device *cgs_device, bool enabled);
-
-typedef int (*cgs_is_virtualization_enabled_t)(void *cgs_device);
-
-typedef int (*cgs_enter_safe_mode)(struct cgs_device *cgs_device, bool en);
-
-typedef void (*cgs_lock_grbm_idx)(struct cgs_device *cgs_device, bool lock);
-
 struct cgs_ops {
 	/* MMIO access */
 	cgs_read_register_t read_register;
 	cgs_write_register_t write_register;
 	cgs_read_ind_register_t read_ind_register;
 	cgs_write_ind_register_t write_ind_register;
-	/* PCI resources */
-	cgs_get_pci_resource_t get_pci_resource;
-	/* ATOM BIOS */
-	cgs_atom_get_data_table_t atom_get_data_table;
-	cgs_atom_get_cmd_table_revs_t atom_get_cmd_table_revs;
-	cgs_atom_exec_cmd_table_t atom_exec_cmd_table;
 	/* Firmware Info */
 	cgs_get_firmware_info get_firmware_info;
-	cgs_rel_firmware rel_firmware;
-	/* cg pg interface*/
-	cgs_set_powergating_state set_powergating_state;
-	cgs_set_clockgating_state set_clockgating_state;
-	/* display manager */
-	cgs_get_active_displays_info get_active_displays_info;
-	/* notify dpm enabled */
-	cgs_notify_dpm_enabled notify_dpm_enabled;
-	cgs_is_virtualization_enabled_t is_virtualization_enabled;
-	cgs_enter_safe_mode enter_safe_mode;
-	cgs_lock_grbm_idx lock_grbm_idx;
 };
 
 struct cgs_os_ops; /* To be define in OS-specific CGS header */
@@ -309,40 +172,7 @@ struct cgs_device
 #define cgs_write_ind_register(dev,space,index,value)		\
 	CGS_CALL(write_ind_register,dev,space,index,value)
 
-#define cgs_atom_get_data_table(dev,table,size,frev,crev)	\
-	CGS_CALL(atom_get_data_table,dev,table,size,frev,crev)
-#define cgs_atom_get_cmd_table_revs(dev,table,frev,crev)	\
-	CGS_CALL(atom_get_cmd_table_revs,dev,table,frev,crev)
-#define cgs_atom_exec_cmd_table(dev,table,args)		\
-	CGS_CALL(atom_exec_cmd_table,dev,table,args)
-
 #define cgs_get_firmware_info(dev, type, info)	\
 	CGS_CALL(get_firmware_info, dev, type, info)
-#define cgs_rel_firmware(dev, type)	\
-	CGS_CALL(rel_firmware, dev, type)
-#define cgs_set_powergating_state(dev, block_type, state)	\
-	CGS_CALL(set_powergating_state, dev, block_type, state)
-#define cgs_set_clockgating_state(dev, block_type, state)	\
-	CGS_CALL(set_clockgating_state, dev, block_type, state)
-#define cgs_notify_dpm_enabled(dev, enabled)	\
-	CGS_CALL(notify_dpm_enabled, dev, enabled)
-
-#define cgs_get_active_displays_info(dev, info)	\
-	CGS_CALL(get_active_displays_info, dev, info)
-
-#define cgs_get_pci_resource(cgs_device, resource_type, size, offset, \
-	resource_base) \
-	CGS_CALL(get_pci_resource, cgs_device, resource_type, size, offset, \
-	resource_base)
-
-#define cgs_is_virtualization_enabled(cgs_device) \
-		CGS_CALL(is_virtualization_enabled, cgs_device)
-
-#define cgs_enter_safe_mode(cgs_device, en) \
-		CGS_CALL(enter_safe_mode, cgs_device, en)
-
-#define cgs_lock_grbm_idx(cgs_device, lock) \
-		CGS_CALL(lock_grbm_idx, cgs_device, lock)
-
 
 #endif /* _CGS_COMMON_H */
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 237289a72bb7..5733fbee07f7 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -100,6 +100,21 @@ struct kgd2kfd_shared_resources {
 	/* Bit n == 1 means Queue n is available for KFD */
 	DECLARE_BITMAP(queue_bitmap, KGD_MAX_QUEUES);
 
+	/* Doorbell assignments (SOC15 and later chips only). Only
+	 * specific doorbells are routed to each SDMA engine. Others
+	 * are routed to IH and VCN. They are not usable by the CP.
+	 *
+	 * Any doorbell number D that satisfies the following condition
+	 * is reserved: (D & reserved_doorbell_mask) == reserved_doorbell_val
+	 *
+	 * KFD currently uses 1024 (= 0x3ff) doorbells per process. If
+	 * doorbells 0x0f0-0x0f7 and 0x2f-0x2f7 are reserved, that means
+	 * mask would be set to 0x1f8 and val set to 0x0f0.
+	 */
+	unsigned int sdma_doorbell[2][2];
+	unsigned int reserved_doorbell_mask;
+	unsigned int reserved_doorbell_val;
+
 	/* Base address of doorbell aperture. */
 	phys_addr_t doorbell_physical_address;
 
@@ -173,8 +188,6 @@ struct tile_config {
  * @set_pasid_vmid_mapping: Exposes pasid/vmid pair to the H/W for no cp
  * scheduling mode. Only used for no cp scheduling mode.
  *
- * @init_pipeline: Initialized the compute pipelines.
- *
  * @hqd_load: Loads the mqd structure to a H/W hqd slot. used only for no cp
  * sceduling mode.
  *
@@ -274,9 +287,6 @@ struct kfd2kgd_calls {
 	int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, unsigned int pasid,
 					unsigned int vmid);
 
-	int (*init_pipeline)(struct kgd_dev *kgd, uint32_t pipe_id,
-				uint32_t hpd_size, uint64_t hpd_gpu_addr);
-
 	int (*init_interrupts)(struct kgd_dev *kgd, uint32_t pipe_id);
 
 	int (*hqd_load)(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
@@ -382,6 +392,10 @@ struct kfd2kgd_calls {
  *
  * @resume: Notifies amdkfd about a resume action done to a kgd device
  *
+ * @quiesce_mm: Quiesce all user queue access to specified MM address space
+ *
+ * @resume_mm: Resume user queue access to specified MM address space
+ *
  * @schedule_evict_and_restore_process: Schedules work queue that will prepare
  * for safe eviction of KFD BOs that belong to the specified process.
  *
@@ -399,6 +413,8 @@ struct kgd2kfd_calls {
 	void (*interrupt)(struct kfd_dev *kfd, const void *ih_ring_entry);
 	void (*suspend)(struct kfd_dev *kfd);
 	int (*resume)(struct kfd_dev *kfd);
+	int (*quiesce_mm)(struct mm_struct *mm);
+	int (*resume_mm)(struct mm_struct *mm);
 	int (*schedule_evict_and_restore_process)(struct mm_struct *mm,
 			struct dma_fence *fence);
 };
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 5c840c022b52..06f08f34a110 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -94,6 +94,7 @@ enum pp_clock_type {
 	PP_PCIE,
 	OD_SCLK,
 	OD_MCLK,
+	OD_RANGE,
 };
 
 enum amd_pp_sensors {
@@ -149,13 +150,6 @@ struct pp_states_info {
 	uint32_t states[16];
 };
 
-struct pp_gpu_power {
-	uint32_t vddc_power;
-	uint32_t vddci_power;
-	uint32_t max_gpu_power;
-	uint32_t average_gpu_power;
-};
-
 #define PP_GROUP_MASK        0xF0000000
 #define PP_GROUP_SHIFT       28
 
@@ -246,11 +240,6 @@ struct amd_pm_funcs {
 	int (*load_firmware)(void *handle);
 	int (*wait_for_fw_loading_complete)(void *handle);
 	int (*set_clockgating_by_smu)(void *handle, uint32_t msg_id);
-	int (*notify_smu_memory_info)(void *handle, uint32_t virtual_addr_low,
-					uint32_t virtual_addr_hi,
-					uint32_t mc_addr_low,
-					uint32_t mc_addr_hi,
-					uint32_t size);
 	int (*set_power_limit)(void *handle, uint32_t n);
 	int (*get_power_limit)(void *handle, uint32_t *limit, bool default_limit);
 /* export to DC */
diff --git a/drivers/gpu/drm/amd/include/soc15_ih_clientid.h b/drivers/gpu/drm/amd/include/soc15_ih_clientid.h
index a12d4f27cfa4..12e196c15bbe 100644
--- a/drivers/gpu/drm/amd/include/soc15_ih_clientid.h
+++ b/drivers/gpu/drm/amd/include/soc15_ih_clientid.h
@@ -43,6 +43,7 @@ enum soc15_ih_clientid {
 	SOC15_IH_CLIENTID_SE2SH		= 0x0c,
 	SOC15_IH_CLIENTID_SE3SH		= 0x0d,
 	SOC15_IH_CLIENTID_SYSHUB	= 0x0e,
+	SOC15_IH_CLIENTID_UVD1		= 0x0e,
 	SOC15_IH_CLIENTID_THM		= 0x0f,
 	SOC15_IH_CLIENTID_UVD		= 0x10,
 	SOC15_IH_CLIENTID_VCE0		= 0x11,
diff --git a/drivers/gpu/drm/amd/include/v9_structs.h b/drivers/gpu/drm/amd/include/v9_structs.h
index 2fb25abaf7c8..ceaf4932258d 100644
--- a/drivers/gpu/drm/amd/include/v9_structs.h
+++ b/drivers/gpu/drm/amd/include/v9_structs.h
@@ -29,10 +29,10 @@ struct v9_sdma_mqd {
 	uint32_t sdmax_rlcx_rb_base;
 	uint32_t sdmax_rlcx_rb_base_hi;
 	uint32_t sdmax_rlcx_rb_rptr;
+	uint32_t sdmax_rlcx_rb_rptr_hi;
 	uint32_t sdmax_rlcx_rb_wptr;
+	uint32_t sdmax_rlcx_rb_wptr_hi;
 	uint32_t sdmax_rlcx_rb_wptr_poll_cntl;
-	uint32_t sdmax_rlcx_rb_wptr_poll_addr_hi;
-	uint32_t sdmax_rlcx_rb_wptr_poll_addr_lo;
 	uint32_t sdmax_rlcx_rb_rptr_addr_hi;
 	uint32_t sdmax_rlcx_rb_rptr_addr_lo;
 	uint32_t sdmax_rlcx_ib_cntl;
@@ -44,29 +44,29 @@ struct v9_sdma_mqd {
 	uint32_t sdmax_rlcx_skip_cntl;
 	uint32_t sdmax_rlcx_context_status;
 	uint32_t sdmax_rlcx_doorbell;
-	uint32_t sdmax_rlcx_virtual_addr;
-	uint32_t sdmax_rlcx_ape1_cntl;
+	uint32_t sdmax_rlcx_status;
 	uint32_t sdmax_rlcx_doorbell_log;
-	uint32_t reserved_22;
-	uint32_t reserved_23;
-	uint32_t reserved_24;
-	uint32_t reserved_25;
-	uint32_t reserved_26;
-	uint32_t reserved_27;
-	uint32_t reserved_28;
-	uint32_t reserved_29;
-	uint32_t reserved_30;
-	uint32_t reserved_31;
-	uint32_t reserved_32;
-	uint32_t reserved_33;
-	uint32_t reserved_34;
-	uint32_t reserved_35;
-	uint32_t reserved_36;
-	uint32_t reserved_37;
-	uint32_t reserved_38;
-	uint32_t reserved_39;
-	uint32_t reserved_40;
-	uint32_t reserved_41;
+	uint32_t sdmax_rlcx_watermark;
+	uint32_t sdmax_rlcx_doorbell_offset;
+	uint32_t sdmax_rlcx_csa_addr_lo;
+	uint32_t sdmax_rlcx_csa_addr_hi;
+	uint32_t sdmax_rlcx_ib_sub_remain;
+	uint32_t sdmax_rlcx_preempt;
+	uint32_t sdmax_rlcx_dummy_reg;
+	uint32_t sdmax_rlcx_rb_wptr_poll_addr_hi;
+	uint32_t sdmax_rlcx_rb_wptr_poll_addr_lo;
+	uint32_t sdmax_rlcx_rb_aql_cntl;
+	uint32_t sdmax_rlcx_minor_ptr_update;
+	uint32_t sdmax_rlcx_midcmd_data0;
+	uint32_t sdmax_rlcx_midcmd_data1;
+	uint32_t sdmax_rlcx_midcmd_data2;
+	uint32_t sdmax_rlcx_midcmd_data3;
+	uint32_t sdmax_rlcx_midcmd_data4;
+	uint32_t sdmax_rlcx_midcmd_data5;
+	uint32_t sdmax_rlcx_midcmd_data6;
+	uint32_t sdmax_rlcx_midcmd_data7;
+	uint32_t sdmax_rlcx_midcmd_data8;
+	uint32_t sdmax_rlcx_midcmd_cntl;
 	uint32_t reserved_42;
 	uint32_t reserved_43;
 	uint32_t reserved_44;
diff --git a/drivers/gpu/drm/amd/include/vega20_ip_offset.h b/drivers/gpu/drm/amd/include/vega20_ip_offset.h
new file mode 100644
index 000000000000..2a2a9cc8bedb
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/vega20_ip_offset.h
@@ -0,0 +1,1051 @@
+/*
+ * Copyright (C) 2018  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _vega20_ip_offset_HEADER
+#define _vega20_ip_offset_HEADER
+
+#define MAX_INSTANCE                                       6
+#define MAX_SEGMENT                                        6
+
+
+struct IP_BASE_INSTANCE
+{
+    unsigned int segment[MAX_SEGMENT];
+};
+
+struct IP_BASE
+{
+    struct IP_BASE_INSTANCE instance[MAX_INSTANCE];
+};
+
+
+static const struct IP_BASE ATHUB_BASE            ={ { { { 0x00000C20, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE CLK_BASE            ={ { { { 0x00016C00, 0x00016E00, 0x00017000, 0x00017200, 0x0001B000, 0x0001B200 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE DCE_BASE            ={ { { { 0x00000012, 0x000000C0, 0x000034C0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE DF_BASE            ={ { { { 0x00007000, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE FUSE_BASE            ={ { { { 0x00017400, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE GC_BASE            ={ { { { 0x00002000, 0x0000A000, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE HDP_BASE            ={ { { { 0x00000F20, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE MMHUB_BASE            ={ { { { 0x0001A000, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE MP0_BASE            ={ { { { 0x00016000, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE MP1_BASE            ={ { { { 0x00016000, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE NBIO_BASE            ={ { { { 0x00000000, 0x00000014, 0x00000D20, 0x00010400, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE OSSSYS_BASE            ={ { { { 0x000010A0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE SDMA0_BASE            ={ { { { 0x00001260, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE SDMA1_BASE            ={ { { { 0x00001860, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE SMUIO_BASE            ={ { { { 0x00016800, 0x00016A00, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE THM_BASE            ={ { { { 0x00016600, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE UMC_BASE            ={ { { { 0x00014000, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE UVD_BASE            ={ { { { 0x00007800, 0x00007E00, 0, 0, 0, 0 } },
+                                        { { 0, 0x00009000, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+/* Adjust VCE_BASE to make vce_4_1 use vce_4_0 offset header files*/
+static const struct IP_BASE VCE_BASE            ={ { { { 0x00007E00/* 0x00008800 */, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE XDMA_BASE            ={ { { { 0x00003400, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE RSMU_BASE            ={ { { { 0x00012000, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0, 0 } } } };
+
+
+#define ATHUB_BASE__INST0_SEG0                     0x00000C20
+#define ATHUB_BASE__INST0_SEG1                     0
+#define ATHUB_BASE__INST0_SEG2                     0
+#define ATHUB_BASE__INST0_SEG3                     0
+#define ATHUB_BASE__INST0_SEG4                     0
+#define ATHUB_BASE__INST0_SEG5                     0
+
+#define ATHUB_BASE__INST1_SEG0                     0
+#define ATHUB_BASE__INST1_SEG1                     0
+#define ATHUB_BASE__INST1_SEG2                     0
+#define ATHUB_BASE__INST1_SEG3                     0
+#define ATHUB_BASE__INST1_SEG4                     0
+#define ATHUB_BASE__INST1_SEG5                     0
+
+#define ATHUB_BASE__INST2_SEG0                     0
+#define ATHUB_BASE__INST2_SEG1                     0
+#define ATHUB_BASE__INST2_SEG2                     0
+#define ATHUB_BASE__INST2_SEG3                     0
+#define ATHUB_BASE__INST2_SEG4                     0
+#define ATHUB_BASE__INST2_SEG5                     0
+
+#define ATHUB_BASE__INST3_SEG0                     0
+#define ATHUB_BASE__INST3_SEG1                     0
+#define ATHUB_BASE__INST3_SEG2                     0
+#define ATHUB_BASE__INST3_SEG3                     0
+#define ATHUB_BASE__INST3_SEG4                     0
+#define ATHUB_BASE__INST3_SEG5                     0
+
+#define ATHUB_BASE__INST4_SEG0                     0
+#define ATHUB_BASE__INST4_SEG1                     0
+#define ATHUB_BASE__INST4_SEG2                     0
+#define ATHUB_BASE__INST4_SEG3                     0
+#define ATHUB_BASE__INST4_SEG4                     0
+#define ATHUB_BASE__INST4_SEG5                     0
+
+#define ATHUB_BASE__INST5_SEG0                     0
+#define ATHUB_BASE__INST5_SEG1                     0
+#define ATHUB_BASE__INST5_SEG2                     0
+#define ATHUB_BASE__INST5_SEG3                     0
+#define ATHUB_BASE__INST5_SEG4                     0
+#define ATHUB_BASE__INST5_SEG5                     0
+
+#define CLK_BASE__INST0_SEG0                       0x00016C00
+#define CLK_BASE__INST0_SEG1                       0x00016E00
+#define CLK_BASE__INST0_SEG2                       0x00017000
+#define CLK_BASE__INST0_SEG3                       0x00017200
+#define CLK_BASE__INST0_SEG4                       0x0001B000
+#define CLK_BASE__INST0_SEG5                       0x0001B200
+
+#define CLK_BASE__INST1_SEG0                       0
+#define CLK_BASE__INST1_SEG1                       0
+#define CLK_BASE__INST1_SEG2                       0
+#define CLK_BASE__INST1_SEG3                       0
+#define CLK_BASE__INST1_SEG4                       0
+#define CLK_BASE__INST1_SEG5                       0
+
+#define CLK_BASE__INST2_SEG0                       0
+#define CLK_BASE__INST2_SEG1                       0
+#define CLK_BASE__INST2_SEG2                       0
+#define CLK_BASE__INST2_SEG3                       0
+#define CLK_BASE__INST2_SEG4                       0
+#define CLK_BASE__INST2_SEG5                       0
+
+#define CLK_BASE__INST3_SEG0                       0
+#define CLK_BASE__INST3_SEG1                       0
+#define CLK_BASE__INST3_SEG2                       0
+#define CLK_BASE__INST3_SEG3                       0
+#define CLK_BASE__INST3_SEG4                       0
+#define CLK_BASE__INST3_SEG5                       0
+
+#define CLK_BASE__INST4_SEG0                       0
+#define CLK_BASE__INST4_SEG1                       0
+#define CLK_BASE__INST4_SEG2                       0
+#define CLK_BASE__INST4_SEG3                       0
+#define CLK_BASE__INST4_SEG4                       0
+#define CLK_BASE__INST4_SEG5                       0
+
+#define CLK_BASE__INST5_SEG0                       0
+#define CLK_BASE__INST5_SEG1                       0
+#define CLK_BASE__INST5_SEG2                       0
+#define CLK_BASE__INST5_SEG3                       0
+#define CLK_BASE__INST5_SEG4                       0
+#define CLK_BASE__INST5_SEG5                       0
+
+#define DCE_BASE__INST0_SEG0                       0x00000012
+#define DCE_BASE__INST0_SEG1                       0x000000C0
+#define DCE_BASE__INST0_SEG2                       0x000034C0
+#define DCE_BASE__INST0_SEG3                       0
+#define DCE_BASE__INST0_SEG4                       0
+#define DCE_BASE__INST0_SEG5                       0
+
+#define DCE_BASE__INST1_SEG0                       0
+#define DCE_BASE__INST1_SEG1                       0
+#define DCE_BASE__INST1_SEG2                       0
+#define DCE_BASE__INST1_SEG3                       0
+#define DCE_BASE__INST1_SEG4                       0
+#define DCE_BASE__INST1_SEG5                       0
+
+#define DCE_BASE__INST2_SEG0                       0
+#define DCE_BASE__INST2_SEG1                       0
+#define DCE_BASE__INST2_SEG2                       0
+#define DCE_BASE__INST2_SEG3                       0
+#define DCE_BASE__INST2_SEG4                       0
+#define DCE_BASE__INST2_SEG5                       0
+
+#define DCE_BASE__INST3_SEG0                       0
+#define DCE_BASE__INST3_SEG1                       0
+#define DCE_BASE__INST3_SEG2                       0
+#define DCE_BASE__INST3_SEG3                       0
+#define DCE_BASE__INST3_SEG4                       0
+#define DCE_BASE__INST3_SEG5                       0
+
+#define DCE_BASE__INST4_SEG0                       0
+#define DCE_BASE__INST4_SEG1                       0
+#define DCE_BASE__INST4_SEG2                       0
+#define DCE_BASE__INST4_SEG3                       0
+#define DCE_BASE__INST4_SEG4                       0
+#define DCE_BASE__INST4_SEG5                       0
+
+#define DCE_BASE__INST5_SEG0                       0
+#define DCE_BASE__INST5_SEG1                       0
+#define DCE_BASE__INST5_SEG2                       0
+#define DCE_BASE__INST5_SEG3                       0
+#define DCE_BASE__INST5_SEG4                       0
+#define DCE_BASE__INST5_SEG5                       0
+
+#define DF_BASE__INST0_SEG0                        0x00007000
+#define DF_BASE__INST0_SEG1                        0
+#define DF_BASE__INST0_SEG2                        0
+#define DF_BASE__INST0_SEG3                        0
+#define DF_BASE__INST0_SEG4                        0
+#define DF_BASE__INST0_SEG5                        0
+
+#define DF_BASE__INST1_SEG0                        0
+#define DF_BASE__INST1_SEG1                        0
+#define DF_BASE__INST1_SEG2                        0
+#define DF_BASE__INST1_SEG3                        0
+#define DF_BASE__INST1_SEG4                        0
+#define DF_BASE__INST1_SEG5                        0
+
+#define DF_BASE__INST2_SEG0                        0
+#define DF_BASE__INST2_SEG1                        0
+#define DF_BASE__INST2_SEG2                        0
+#define DF_BASE__INST2_SEG3                        0
+#define DF_BASE__INST2_SEG4                        0
+#define DF_BASE__INST2_SEG5                        0
+
+#define DF_BASE__INST3_SEG0                        0
+#define DF_BASE__INST3_SEG1                        0
+#define DF_BASE__INST3_SEG2                        0
+#define DF_BASE__INST3_SEG3                        0
+#define DF_BASE__INST3_SEG4                        0
+#define DF_BASE__INST3_SEG5                        0
+
+#define DF_BASE__INST4_SEG0                        0
+#define DF_BASE__INST4_SEG1                        0
+#define DF_BASE__INST4_SEG2                        0
+#define DF_BASE__INST4_SEG3                        0
+#define DF_BASE__INST4_SEG4                        0
+#define DF_BASE__INST4_SEG5                        0
+
+#define DF_BASE__INST5_SEG0                        0
+#define DF_BASE__INST5_SEG1                        0
+#define DF_BASE__INST5_SEG2                        0
+#define DF_BASE__INST5_SEG3                        0
+#define DF_BASE__INST5_SEG4                        0
+#define DF_BASE__INST5_SEG5                        0
+
+#define FUSE_BASE__INST0_SEG0                      0x00017400
+#define FUSE_BASE__INST0_SEG1                      0
+#define FUSE_BASE__INST0_SEG2                      0
+#define FUSE_BASE__INST0_SEG3                      0
+#define FUSE_BASE__INST0_SEG4                      0
+#define FUSE_BASE__INST0_SEG5                      0
+
+#define FUSE_BASE__INST1_SEG0                      0
+#define FUSE_BASE__INST1_SEG1                      0
+#define FUSE_BASE__INST1_SEG2                      0
+#define FUSE_BASE__INST1_SEG3                      0
+#define FUSE_BASE__INST1_SEG4                      0
+#define FUSE_BASE__INST1_SEG5                      0
+
+#define FUSE_BASE__INST2_SEG0                      0
+#define FUSE_BASE__INST2_SEG1                      0
+#define FUSE_BASE__INST2_SEG2                      0
+#define FUSE_BASE__INST2_SEG3                      0
+#define FUSE_BASE__INST2_SEG4                      0
+#define FUSE_BASE__INST2_SEG5                      0
+
+#define FUSE_BASE__INST3_SEG0                      0
+#define FUSE_BASE__INST3_SEG1                      0
+#define FUSE_BASE__INST3_SEG2                      0
+#define FUSE_BASE__INST3_SEG3                      0
+#define FUSE_BASE__INST3_SEG4                      0
+#define FUSE_BASE__INST3_SEG5                      0
+
+#define FUSE_BASE__INST4_SEG0                      0
+#define FUSE_BASE__INST4_SEG1                      0
+#define FUSE_BASE__INST4_SEG2                      0
+#define FUSE_BASE__INST4_SEG3                      0
+#define FUSE_BASE__INST4_SEG4                      0
+#define FUSE_BASE__INST4_SEG5                      0
+
+#define FUSE_BASE__INST5_SEG0                      0
+#define FUSE_BASE__INST5_SEG1                      0
+#define FUSE_BASE__INST5_SEG2                      0
+#define FUSE_BASE__INST5_SEG3                      0
+#define FUSE_BASE__INST5_SEG4                      0
+#define FUSE_BASE__INST5_SEG5                      0
+
+#define GC_BASE__INST0_SEG0                        0x00002000
+#define GC_BASE__INST0_SEG1                        0x0000A000
+#define GC_BASE__INST0_SEG2                        0
+#define GC_BASE__INST0_SEG3                        0
+#define GC_BASE__INST0_SEG4                        0
+#define GC_BASE__INST0_SEG5                        0
+
+#define GC_BASE__INST1_SEG0                        0
+#define GC_BASE__INST1_SEG1                        0
+#define GC_BASE__INST1_SEG2                        0
+#define GC_BASE__INST1_SEG3                        0
+#define GC_BASE__INST1_SEG4                        0
+#define GC_BASE__INST1_SEG5                        0
+
+#define GC_BASE__INST2_SEG0                        0
+#define GC_BASE__INST2_SEG1                        0
+#define GC_BASE__INST2_SEG2                        0
+#define GC_BASE__INST2_SEG3                        0
+#define GC_BASE__INST2_SEG4                        0
+#define GC_BASE__INST2_SEG5                        0
+
+#define GC_BASE__INST3_SEG0                        0
+#define GC_BASE__INST3_SEG1                        0
+#define GC_BASE__INST3_SEG2                        0
+#define GC_BASE__INST3_SEG3                        0
+#define GC_BASE__INST3_SEG4                        0
+#define GC_BASE__INST3_SEG5                        0
+
+#define GC_BASE__INST4_SEG0                        0
+#define GC_BASE__INST4_SEG1                        0
+#define GC_BASE__INST4_SEG2                        0
+#define GC_BASE__INST4_SEG3                        0
+#define GC_BASE__INST4_SEG4                        0
+#define GC_BASE__INST4_SEG5                        0
+
+#define GC_BASE__INST5_SEG0                        0
+#define GC_BASE__INST5_SEG1                        0
+#define GC_BASE__INST5_SEG2                        0
+#define GC_BASE__INST5_SEG3                        0
+#define GC_BASE__INST5_SEG4                        0
+#define GC_BASE__INST5_SEG5                        0
+
+#define HDP_BASE__INST0_SEG0                       0x00000F20
+#define HDP_BASE__INST0_SEG1                       0
+#define HDP_BASE__INST0_SEG2                       0
+#define HDP_BASE__INST0_SEG3                       0
+#define HDP_BASE__INST0_SEG4                       0
+#define HDP_BASE__INST0_SEG5                       0
+
+#define HDP_BASE__INST1_SEG0                       0
+#define HDP_BASE__INST1_SEG1                       0
+#define HDP_BASE__INST1_SEG2                       0
+#define HDP_BASE__INST1_SEG3                       0
+#define HDP_BASE__INST1_SEG4                       0
+#define HDP_BASE__INST1_SEG5                       0
+
+#define HDP_BASE__INST2_SEG0                       0
+#define HDP_BASE__INST2_SEG1                       0
+#define HDP_BASE__INST2_SEG2                       0
+#define HDP_BASE__INST2_SEG3                       0
+#define HDP_BASE__INST2_SEG4                       0
+#define HDP_BASE__INST2_SEG5                       0
+
+#define HDP_BASE__INST3_SEG0                       0
+#define HDP_BASE__INST3_SEG1                       0
+#define HDP_BASE__INST3_SEG2                       0
+#define HDP_BASE__INST3_SEG3                       0
+#define HDP_BASE__INST3_SEG4                       0
+#define HDP_BASE__INST3_SEG5                       0
+
+#define HDP_BASE__INST4_SEG0                       0
+#define HDP_BASE__INST4_SEG1                       0
+#define HDP_BASE__INST4_SEG2                       0
+#define HDP_BASE__INST4_SEG3                       0
+#define HDP_BASE__INST4_SEG4                       0
+#define HDP_BASE__INST4_SEG5                       0
+
+#define HDP_BASE__INST5_SEG0                       0
+#define HDP_BASE__INST5_SEG1                       0
+#define HDP_BASE__INST5_SEG2                       0
+#define HDP_BASE__INST5_SEG3                       0
+#define HDP_BASE__INST5_SEG4                       0
+#define HDP_BASE__INST5_SEG5                       0
+
+#define MMHUB_BASE__INST0_SEG0                     0x0001A000
+#define MMHUB_BASE__INST0_SEG1                     0
+#define MMHUB_BASE__INST0_SEG2                     0
+#define MMHUB_BASE__INST0_SEG3                     0
+#define MMHUB_BASE__INST0_SEG4                     0
+#define MMHUB_BASE__INST0_SEG5                     0
+
+#define MMHUB_BASE__INST1_SEG0                     0
+#define MMHUB_BASE__INST1_SEG1                     0
+#define MMHUB_BASE__INST1_SEG2                     0
+#define MMHUB_BASE__INST1_SEG3                     0
+#define MMHUB_BASE__INST1_SEG4                     0
+#define MMHUB_BASE__INST1_SEG5                     0
+
+#define MMHUB_BASE__INST2_SEG0                     0
+#define MMHUB_BASE__INST2_SEG1                     0
+#define MMHUB_BASE__INST2_SEG2                     0
+#define MMHUB_BASE__INST2_SEG3                     0
+#define MMHUB_BASE__INST2_SEG4                     0
+#define MMHUB_BASE__INST2_SEG5                     0
+
+#define MMHUB_BASE__INST3_SEG0                     0
+#define MMHUB_BASE__INST3_SEG1                     0
+#define MMHUB_BASE__INST3_SEG2                     0
+#define MMHUB_BASE__INST3_SEG3                     0
+#define MMHUB_BASE__INST3_SEG4                     0
+#define MMHUB_BASE__INST3_SEG5                     0
+
+#define MMHUB_BASE__INST4_SEG0                     0
+#define MMHUB_BASE__INST4_SEG1                     0
+#define MMHUB_BASE__INST4_SEG2                     0
+#define MMHUB_BASE__INST4_SEG3                     0
+#define MMHUB_BASE__INST4_SEG4                     0
+#define MMHUB_BASE__INST4_SEG5                     0
+
+#define MMHUB_BASE__INST5_SEG0                     0
+#define MMHUB_BASE__INST5_SEG1                     0
+#define MMHUB_BASE__INST5_SEG2                     0
+#define MMHUB_BASE__INST5_SEG3                     0
+#define MMHUB_BASE__INST5_SEG4                     0
+#define MMHUB_BASE__INST5_SEG5                     0
+
+#define MP0_BASE__INST0_SEG0                       0x00016000
+#define MP0_BASE__INST0_SEG1                       0
+#define MP0_BASE__INST0_SEG2                       0
+#define MP0_BASE__INST0_SEG3                       0
+#define MP0_BASE__INST0_SEG4                       0
+#define MP0_BASE__INST0_SEG5                       0
+
+#define MP0_BASE__INST1_SEG0                       0
+#define MP0_BASE__INST1_SEG1                       0
+#define MP0_BASE__INST1_SEG2                       0
+#define MP0_BASE__INST1_SEG3                       0
+#define MP0_BASE__INST1_SEG4                       0
+#define MP0_BASE__INST1_SEG5                       0
+
+#define MP0_BASE__INST2_SEG0                       0
+#define MP0_BASE__INST2_SEG1                       0
+#define MP0_BASE__INST2_SEG2                       0
+#define MP0_BASE__INST2_SEG3                       0
+#define MP0_BASE__INST2_SEG4                       0
+#define MP0_BASE__INST2_SEG5                       0
+
+#define MP0_BASE__INST3_SEG0                       0
+#define MP0_BASE__INST3_SEG1                       0
+#define MP0_BASE__INST3_SEG2                       0
+#define MP0_BASE__INST3_SEG3                       0
+#define MP0_BASE__INST3_SEG4                       0
+#define MP0_BASE__INST3_SEG5                       0
+
+#define MP0_BASE__INST4_SEG0                       0
+#define MP0_BASE__INST4_SEG1                       0
+#define MP0_BASE__INST4_SEG2                       0
+#define MP0_BASE__INST4_SEG3                       0
+#define MP0_BASE__INST4_SEG4                       0
+#define MP0_BASE__INST4_SEG5                       0
+
+#define MP0_BASE__INST5_SEG0                       0
+#define MP0_BASE__INST5_SEG1                       0
+#define MP0_BASE__INST5_SEG2                       0
+#define MP0_BASE__INST5_SEG3                       0
+#define MP0_BASE__INST5_SEG4                       0
+#define MP0_BASE__INST5_SEG5                       0
+
+#define MP1_BASE__INST0_SEG0                       0x00016000
+#define MP1_BASE__INST0_SEG1                       0
+#define MP1_BASE__INST0_SEG2                       0
+#define MP1_BASE__INST0_SEG3                       0
+#define MP1_BASE__INST0_SEG4                       0
+#define MP1_BASE__INST0_SEG5                       0
+
+#define MP1_BASE__INST1_SEG0                       0
+#define MP1_BASE__INST1_SEG1                       0
+#define MP1_BASE__INST1_SEG2                       0
+#define MP1_BASE__INST1_SEG3                       0
+#define MP1_BASE__INST1_SEG4                       0
+#define MP1_BASE__INST1_SEG5                       0
+
+#define MP1_BASE__INST2_SEG0                       0
+#define MP1_BASE__INST2_SEG1                       0
+#define MP1_BASE__INST2_SEG2                       0
+#define MP1_BASE__INST2_SEG3                       0
+#define MP1_BASE__INST2_SEG4                       0
+#define MP1_BASE__INST2_SEG5                       0
+
+#define MP1_BASE__INST3_SEG0                       0
+#define MP1_BASE__INST3_SEG1                       0
+#define MP1_BASE__INST3_SEG2                       0
+#define MP1_BASE__INST3_SEG3                       0
+#define MP1_BASE__INST3_SEG4                       0
+#define MP1_BASE__INST3_SEG5                       0
+
+#define MP1_BASE__INST4_SEG0                       0
+#define MP1_BASE__INST4_SEG1                       0
+#define MP1_BASE__INST4_SEG2                       0
+#define MP1_BASE__INST4_SEG3                       0
+#define MP1_BASE__INST4_SEG4                       0
+#define MP1_BASE__INST4_SEG5                       0
+
+#define MP1_BASE__INST5_SEG0                       0
+#define MP1_BASE__INST5_SEG1                       0
+#define MP1_BASE__INST5_SEG2                       0
+#define MP1_BASE__INST5_SEG3                       0
+#define MP1_BASE__INST5_SEG4                       0
+#define MP1_BASE__INST5_SEG5                       0
+
+#define NBIO_BASE__INST0_SEG0                      0x00000000
+#define NBIO_BASE__INST0_SEG1                      0x00000014
+#define NBIO_BASE__INST0_SEG2                      0x00000D20
+#define NBIO_BASE__INST0_SEG3                      0x00010400
+#define NBIO_BASE__INST0_SEG4                      0
+#define NBIO_BASE__INST0_SEG5                      0
+
+#define NBIO_BASE__INST1_SEG0                      0
+#define NBIO_BASE__INST1_SEG1                      0
+#define NBIO_BASE__INST1_SEG2                      0
+#define NBIO_BASE__INST1_SEG3                      0
+#define NBIO_BASE__INST1_SEG4                      0
+#define NBIO_BASE__INST1_SEG5                      0
+
+#define NBIO_BASE__INST2_SEG0                      0
+#define NBIO_BASE__INST2_SEG1                      0
+#define NBIO_BASE__INST2_SEG2                      0
+#define NBIO_BASE__INST2_SEG3                      0
+#define NBIO_BASE__INST2_SEG4                      0
+#define NBIO_BASE__INST2_SEG5                      0
+
+#define NBIO_BASE__INST3_SEG0                      0
+#define NBIO_BASE__INST3_SEG1                      0
+#define NBIO_BASE__INST3_SEG2                      0
+#define NBIO_BASE__INST3_SEG3                      0
+#define NBIO_BASE__INST3_SEG4                      0
+#define NBIO_BASE__INST3_SEG5                      0
+
+#define NBIO_BASE__INST4_SEG0                      0
+#define NBIO_BASE__INST4_SEG1                      0
+#define NBIO_BASE__INST4_SEG2                      0
+#define NBIO_BASE__INST4_SEG3                      0
+#define NBIO_BASE__INST4_SEG4                      0
+#define NBIO_BASE__INST4_SEG5                      0
+
+#define NBIO_BASE__INST5_SEG0                      0
+#define NBIO_BASE__INST5_SEG1                      0
+#define NBIO_BASE__INST5_SEG2                      0
+#define NBIO_BASE__INST5_SEG3                      0
+#define NBIO_BASE__INST5_SEG4                      0
+#define NBIO_BASE__INST5_SEG5                      0
+
+#define OSSSYS_BASE__INST0_SEG0                    0x000010A0
+#define OSSSYS_BASE__INST0_SEG1                    0
+#define OSSSYS_BASE__INST0_SEG2                    0
+#define OSSSYS_BASE__INST0_SEG3                    0
+#define OSSSYS_BASE__INST0_SEG4                    0
+#define OSSSYS_BASE__INST0_SEG5                    0
+
+#define OSSSYS_BASE__INST1_SEG0                    0
+#define OSSSYS_BASE__INST1_SEG1                    0
+#define OSSSYS_BASE__INST1_SEG2                    0
+#define OSSSYS_BASE__INST1_SEG3                    0
+#define OSSSYS_BASE__INST1_SEG4                    0
+#define OSSSYS_BASE__INST1_SEG5                    0
+
+#define OSSSYS_BASE__INST2_SEG0                    0
+#define OSSSYS_BASE__INST2_SEG1                    0
+#define OSSSYS_BASE__INST2_SEG2                    0
+#define OSSSYS_BASE__INST2_SEG3                    0
+#define OSSSYS_BASE__INST2_SEG4                    0
+#define OSSSYS_BASE__INST2_SEG5                    0
+
+#define OSSSYS_BASE__INST3_SEG0                    0
+#define OSSSYS_BASE__INST3_SEG1                    0
+#define OSSSYS_BASE__INST3_SEG2                    0
+#define OSSSYS_BASE__INST3_SEG3                    0
+#define OSSSYS_BASE__INST3_SEG4                    0
+#define OSSSYS_BASE__INST3_SEG5                    0
+
+#define OSSSYS_BASE__INST4_SEG0                    0
+#define OSSSYS_BASE__INST4_SEG1                    0
+#define OSSSYS_BASE__INST4_SEG2                    0
+#define OSSSYS_BASE__INST4_SEG3                    0
+#define OSSSYS_BASE__INST4_SEG4                    0
+#define OSSSYS_BASE__INST4_SEG5                    0
+
+#define OSSSYS_BASE__INST5_SEG0                    0
+#define OSSSYS_BASE__INST5_SEG1                    0
+#define OSSSYS_BASE__INST5_SEG2                    0
+#define OSSSYS_BASE__INST5_SEG3                    0
+#define OSSSYS_BASE__INST5_SEG4                    0
+#define OSSSYS_BASE__INST5_SEG5                    0
+
+#define SDMA0_BASE__INST0_SEG0                     0x00001260
+#define SDMA0_BASE__INST0_SEG1                     0
+#define SDMA0_BASE__INST0_SEG2                     0
+#define SDMA0_BASE__INST0_SEG3                     0
+#define SDMA0_BASE__INST0_SEG4                     0
+#define SDMA0_BASE__INST0_SEG5                     0
+
+#define SDMA0_BASE__INST1_SEG0                     0
+#define SDMA0_BASE__INST1_SEG1                     0
+#define SDMA0_BASE__INST1_SEG2                     0
+#define SDMA0_BASE__INST1_SEG3                     0
+#define SDMA0_BASE__INST1_SEG4                     0
+#define SDMA0_BASE__INST1_SEG5                     0
+
+#define SDMA0_BASE__INST2_SEG0                     0
+#define SDMA0_BASE__INST2_SEG1                     0
+#define SDMA0_BASE__INST2_SEG2                     0
+#define SDMA0_BASE__INST2_SEG3                     0
+#define SDMA0_BASE__INST2_SEG4                     0
+#define SDMA0_BASE__INST2_SEG5                     0
+
+#define SDMA0_BASE__INST3_SEG0                     0
+#define SDMA0_BASE__INST3_SEG1                     0
+#define SDMA0_BASE__INST3_SEG2                     0
+#define SDMA0_BASE__INST3_SEG3                     0
+#define SDMA0_BASE__INST3_SEG4                     0
+#define SDMA0_BASE__INST3_SEG5                     0
+
+#define SDMA0_BASE__INST4_SEG0                     0
+#define SDMA0_BASE__INST4_SEG1                     0
+#define SDMA0_BASE__INST4_SEG2                     0
+#define SDMA0_BASE__INST4_SEG3                     0
+#define SDMA0_BASE__INST4_SEG4                     0
+#define SDMA0_BASE__INST4_SEG5                     0
+
+#define SDMA0_BASE__INST5_SEG0                     0
+#define SDMA0_BASE__INST5_SEG1                     0
+#define SDMA0_BASE__INST5_SEG2                     0
+#define SDMA0_BASE__INST5_SEG3                     0
+#define SDMA0_BASE__INST5_SEG4                     0
+#define SDMA0_BASE__INST5_SEG5                     0
+
+#define SDMA1_BASE__INST0_SEG0                     0x00001860
+#define SDMA1_BASE__INST0_SEG1                     0
+#define SDMA1_BASE__INST0_SEG2                     0
+#define SDMA1_BASE__INST0_SEG3                     0
+#define SDMA1_BASE__INST0_SEG4                     0
+#define SDMA1_BASE__INST0_SEG5                     0
+
+#define SDMA1_BASE__INST1_SEG0                     0
+#define SDMA1_BASE__INST1_SEG1                     0
+#define SDMA1_BASE__INST1_SEG2                     0
+#define SDMA1_BASE__INST1_SEG3                     0
+#define SDMA1_BASE__INST1_SEG4                     0
+#define SDMA1_BASE__INST1_SEG5                     0
+
+#define SDMA1_BASE__INST2_SEG0                     0
+#define SDMA1_BASE__INST2_SEG1                     0
+#define SDMA1_BASE__INST2_SEG2                     0
+#define SDMA1_BASE__INST2_SEG3                     0
+#define SDMA1_BASE__INST2_SEG4                     0
+#define SDMA1_BASE__INST2_SEG5                     0
+
+#define SDMA1_BASE__INST3_SEG0                     0
+#define SDMA1_BASE__INST3_SEG1                     0
+#define SDMA1_BASE__INST3_SEG2                     0
+#define SDMA1_BASE__INST3_SEG3                     0
+#define SDMA1_BASE__INST3_SEG4                     0
+#define SDMA1_BASE__INST3_SEG5                     0
+
+#define SDMA1_BASE__INST4_SEG0                     0
+#define SDMA1_BASE__INST4_SEG1                     0
+#define SDMA1_BASE__INST4_SEG2                     0
+#define SDMA1_BASE__INST4_SEG3                     0
+#define SDMA1_BASE__INST4_SEG4                     0
+#define SDMA1_BASE__INST4_SEG5                     0
+
+#define SDMA1_BASE__INST5_SEG0                     0
+#define SDMA1_BASE__INST5_SEG1                     0
+#define SDMA1_BASE__INST5_SEG2                     0
+#define SDMA1_BASE__INST5_SEG3                     0
+#define SDMA1_BASE__INST5_SEG4                     0
+#define SDMA1_BASE__INST5_SEG5                     0
+
+#define SMUIO_BASE__INST0_SEG0                     0x00016800
+#define SMUIO_BASE__INST0_SEG1                     0x00016A00
+#define SMUIO_BASE__INST0_SEG2                     0
+#define SMUIO_BASE__INST0_SEG3                     0
+#define SMUIO_BASE__INST0_SEG4                     0
+#define SMUIO_BASE__INST0_SEG5                     0
+
+#define SMUIO_BASE__INST1_SEG0                     0
+#define SMUIO_BASE__INST1_SEG1                     0
+#define SMUIO_BASE__INST1_SEG2                     0
+#define SMUIO_BASE__INST1_SEG3                     0
+#define SMUIO_BASE__INST1_SEG4                     0
+#define SMUIO_BASE__INST1_SEG5                     0
+
+#define SMUIO_BASE__INST2_SEG0                     0
+#define SMUIO_BASE__INST2_SEG1                     0
+#define SMUIO_BASE__INST2_SEG2                     0
+#define SMUIO_BASE__INST2_SEG3                     0
+#define SMUIO_BASE__INST2_SEG4                     0
+#define SMUIO_BASE__INST2_SEG5                     0
+
+#define SMUIO_BASE__INST3_SEG0                     0
+#define SMUIO_BASE__INST3_SEG1                     0
+#define SMUIO_BASE__INST3_SEG2                     0
+#define SMUIO_BASE__INST3_SEG3                     0
+#define SMUIO_BASE__INST3_SEG4                     0
+#define SMUIO_BASE__INST3_SEG5                     0
+
+#define SMUIO_BASE__INST4_SEG0                     0
+#define SMUIO_BASE__INST4_SEG1                     0
+#define SMUIO_BASE__INST4_SEG2                     0
+#define SMUIO_BASE__INST4_SEG3                     0
+#define SMUIO_BASE__INST4_SEG4                     0
+#define SMUIO_BASE__INST4_SEG5                     0
+
+#define SMUIO_BASE__INST5_SEG0                     0
+#define SMUIO_BASE__INST5_SEG1                     0
+#define SMUIO_BASE__INST5_SEG2                     0
+#define SMUIO_BASE__INST5_SEG3                     0
+#define SMUIO_BASE__INST5_SEG4                     0
+#define SMUIO_BASE__INST5_SEG5                     0
+
+#define THM_BASE__INST0_SEG0                       0x00016600
+#define THM_BASE__INST0_SEG1                       0
+#define THM_BASE__INST0_SEG2                       0
+#define THM_BASE__INST0_SEG3                       0
+#define THM_BASE__INST0_SEG4                       0
+#define THM_BASE__INST0_SEG5                       0
+
+#define THM_BASE__INST1_SEG0                       0
+#define THM_BASE__INST1_SEG1                       0
+#define THM_BASE__INST1_SEG2                       0
+#define THM_BASE__INST1_SEG3                       0
+#define THM_BASE__INST1_SEG4                       0
+#define THM_BASE__INST1_SEG5                       0
+
+#define THM_BASE__INST2_SEG0                       0
+#define THM_BASE__INST2_SEG1                       0
+#define THM_BASE__INST2_SEG2                       0
+#define THM_BASE__INST2_SEG3                       0
+#define THM_BASE__INST2_SEG4                       0
+#define THM_BASE__INST2_SEG5                       0
+
+#define THM_BASE__INST3_SEG0                       0
+#define THM_BASE__INST3_SEG1                       0
+#define THM_BASE__INST3_SEG2                       0
+#define THM_BASE__INST3_SEG3                       0
+#define THM_BASE__INST3_SEG4                       0
+#define THM_BASE__INST3_SEG5                       0
+
+#define THM_BASE__INST4_SEG0                       0
+#define THM_BASE__INST4_SEG1                       0
+#define THM_BASE__INST4_SEG2                       0
+#define THM_BASE__INST4_SEG3                       0
+#define THM_BASE__INST4_SEG4                       0
+#define THM_BASE__INST4_SEG5                       0
+
+#define THM_BASE__INST5_SEG0                       0
+#define THM_BASE__INST5_SEG1                       0
+#define THM_BASE__INST5_SEG2                       0
+#define THM_BASE__INST5_SEG3                       0
+#define THM_BASE__INST5_SEG4                       0
+#define THM_BASE__INST5_SEG5                       0
+
+#define UMC_BASE__INST0_SEG0                       0x00014000
+#define UMC_BASE__INST0_SEG1                       0
+#define UMC_BASE__INST0_SEG2                       0
+#define UMC_BASE__INST0_SEG3                       0
+#define UMC_BASE__INST0_SEG4                       0
+#define UMC_BASE__INST0_SEG5                       0
+
+#define UMC_BASE__INST1_SEG0                       0
+#define UMC_BASE__INST1_SEG1                       0
+#define UMC_BASE__INST1_SEG2                       0
+#define UMC_BASE__INST1_SEG3                       0
+#define UMC_BASE__INST1_SEG4                       0
+#define UMC_BASE__INST1_SEG5                       0
+
+#define UMC_BASE__INST2_SEG0                       0
+#define UMC_BASE__INST2_SEG1                       0
+#define UMC_BASE__INST2_SEG2                       0
+#define UMC_BASE__INST2_SEG3                       0
+#define UMC_BASE__INST2_SEG4                       0
+#define UMC_BASE__INST2_SEG5                       0
+
+#define UMC_BASE__INST3_SEG0                       0
+#define UMC_BASE__INST3_SEG1                       0
+#define UMC_BASE__INST3_SEG2                       0
+#define UMC_BASE__INST3_SEG3                       0
+#define UMC_BASE__INST3_SEG4                       0
+#define UMC_BASE__INST3_SEG5                       0
+
+#define UMC_BASE__INST4_SEG0                       0
+#define UMC_BASE__INST4_SEG1                       0
+#define UMC_BASE__INST4_SEG2                       0
+#define UMC_BASE__INST4_SEG3                       0
+#define UMC_BASE__INST4_SEG4                       0
+#define UMC_BASE__INST4_SEG5                       0
+
+#define UMC_BASE__INST5_SEG0                       0
+#define UMC_BASE__INST5_SEG1                       0
+#define UMC_BASE__INST5_SEG2                       0
+#define UMC_BASE__INST5_SEG3                       0
+#define UMC_BASE__INST5_SEG4                       0
+#define UMC_BASE__INST5_SEG5                       0
+
+#define UVD_BASE__INST0_SEG0                       0x00007800
+#define UVD_BASE__INST0_SEG1                       0x00007E00
+#define UVD_BASE__INST0_SEG2                       0
+#define UVD_BASE__INST0_SEG3                       0
+#define UVD_BASE__INST0_SEG4                       0
+#define UVD_BASE__INST0_SEG5                       0
+
+#define UVD_BASE__INST1_SEG0                       0
+#define UVD_BASE__INST1_SEG1                       0x00009000
+#define UVD_BASE__INST1_SEG2                       0
+#define UVD_BASE__INST1_SEG3                       0
+#define UVD_BASE__INST1_SEG4                       0
+#define UVD_BASE__INST1_SEG5                       0
+
+#define UVD_BASE__INST2_SEG0                       0
+#define UVD_BASE__INST2_SEG1                       0
+#define UVD_BASE__INST2_SEG2                       0
+#define UVD_BASE__INST2_SEG3                       0
+#define UVD_BASE__INST2_SEG4                       0
+#define UVD_BASE__INST2_SEG5                       0
+
+#define UVD_BASE__INST3_SEG0                       0
+#define UVD_BASE__INST3_SEG1                       0
+#define UVD_BASE__INST3_SEG2                       0
+#define UVD_BASE__INST3_SEG3                       0
+#define UVD_BASE__INST3_SEG4                       0
+#define UVD_BASE__INST3_SEG5                       0
+
+#define UVD_BASE__INST4_SEG0                       0
+#define UVD_BASE__INST4_SEG1                       0
+#define UVD_BASE__INST4_SEG2                       0
+#define UVD_BASE__INST4_SEG3                       0
+#define UVD_BASE__INST4_SEG4                       0
+#define UVD_BASE__INST4_SEG5                       0
+
+#define UVD_BASE__INST5_SEG0                       0
+#define UVD_BASE__INST5_SEG1                       0
+#define UVD_BASE__INST5_SEG2                       0
+#define UVD_BASE__INST5_SEG3                       0
+#define UVD_BASE__INST5_SEG4                       0
+#define UVD_BASE__INST5_SEG5                       0
+
+#define VCE_BASE__INST0_SEG0                       0x00008800
+#define VCE_BASE__INST0_SEG1                       0
+#define VCE_BASE__INST0_SEG2                       0
+#define VCE_BASE__INST0_SEG3                       0
+#define VCE_BASE__INST0_SEG4                       0
+#define VCE_BASE__INST0_SEG5                       0
+
+#define VCE_BASE__INST1_SEG0                       0
+#define VCE_BASE__INST1_SEG1                       0
+#define VCE_BASE__INST1_SEG2                       0
+#define VCE_BASE__INST1_SEG3                       0
+#define VCE_BASE__INST1_SEG4                       0
+#define VCE_BASE__INST1_SEG5                       0
+
+#define VCE_BASE__INST2_SEG0                       0
+#define VCE_BASE__INST2_SEG1                       0
+#define VCE_BASE__INST2_SEG2                       0
+#define VCE_BASE__INST2_SEG3                       0
+#define VCE_BASE__INST2_SEG4                       0
+#define VCE_BASE__INST2_SEG5                       0
+
+#define VCE_BASE__INST3_SEG0                       0
+#define VCE_BASE__INST3_SEG1                       0
+#define VCE_BASE__INST3_SEG2                       0
+#define VCE_BASE__INST3_SEG3                       0
+#define VCE_BASE__INST3_SEG4                       0
+#define VCE_BASE__INST3_SEG5                       0
+
+#define VCE_BASE__INST4_SEG0                       0
+#define VCE_BASE__INST4_SEG1                       0
+#define VCE_BASE__INST4_SEG2                       0
+#define VCE_BASE__INST4_SEG3                       0
+#define VCE_BASE__INST4_SEG4                       0
+#define VCE_BASE__INST4_SEG5                       0
+
+#define VCE_BASE__INST5_SEG0                       0
+#define VCE_BASE__INST5_SEG1                       0
+#define VCE_BASE__INST5_SEG2                       0
+#define VCE_BASE__INST5_SEG3                       0
+#define VCE_BASE__INST5_SEG4                       0
+#define VCE_BASE__INST5_SEG5                       0
+
+#define XDMA_BASE__INST0_SEG0                      0x00003400
+#define XDMA_BASE__INST0_SEG1                      0
+#define XDMA_BASE__INST0_SEG2                      0
+#define XDMA_BASE__INST0_SEG3                      0
+#define XDMA_BASE__INST0_SEG4                      0
+#define XDMA_BASE__INST0_SEG5                      0
+
+#define XDMA_BASE__INST1_SEG0                      0
+#define XDMA_BASE__INST1_SEG1                      0
+#define XDMA_BASE__INST1_SEG2                      0
+#define XDMA_BASE__INST1_SEG3                      0
+#define XDMA_BASE__INST1_SEG4                      0
+#define XDMA_BASE__INST1_SEG5                      0
+
+#define XDMA_BASE__INST2_SEG0                      0
+#define XDMA_BASE__INST2_SEG1                      0
+#define XDMA_BASE__INST2_SEG2                      0
+#define XDMA_BASE__INST2_SEG3                      0
+#define XDMA_BASE__INST2_SEG4                      0
+#define XDMA_BASE__INST2_SEG5                      0
+
+#define XDMA_BASE__INST3_SEG0                      0
+#define XDMA_BASE__INST3_SEG1                      0
+#define XDMA_BASE__INST3_SEG2                      0
+#define XDMA_BASE__INST3_SEG3                      0
+#define XDMA_BASE__INST3_SEG4                      0
+#define XDMA_BASE__INST3_SEG5                      0
+
+#define XDMA_BASE__INST4_SEG0                      0
+#define XDMA_BASE__INST4_SEG1                      0
+#define XDMA_BASE__INST4_SEG2                      0
+#define XDMA_BASE__INST4_SEG3                      0
+#define XDMA_BASE__INST4_SEG4                      0
+#define XDMA_BASE__INST4_SEG5                      0
+
+#define XDMA_BASE__INST5_SEG0                      0
+#define XDMA_BASE__INST5_SEG1                      0
+#define XDMA_BASE__INST5_SEG2                      0
+#define XDMA_BASE__INST5_SEG3                      0
+#define XDMA_BASE__INST5_SEG4                      0
+#define XDMA_BASE__INST5_SEG5                      0
+
+#define RSMU_BASE__INST0_SEG0                      0x00012000
+#define RSMU_BASE__INST0_SEG1                      0
+#define RSMU_BASE__INST0_SEG2                      0
+#define RSMU_BASE__INST0_SEG3                      0
+#define RSMU_BASE__INST0_SEG4                      0
+#define RSMU_BASE__INST0_SEG5                      0
+
+#define RSMU_BASE__INST1_SEG0                      0
+#define RSMU_BASE__INST1_SEG1                      0
+#define RSMU_BASE__INST1_SEG2                      0
+#define RSMU_BASE__INST1_SEG3                      0
+#define RSMU_BASE__INST1_SEG4                      0
+#define RSMU_BASE__INST1_SEG5                      0
+
+#define RSMU_BASE__INST2_SEG0                      0
+#define RSMU_BASE__INST2_SEG1                      0
+#define RSMU_BASE__INST2_SEG2                      0
+#define RSMU_BASE__INST2_SEG3                      0
+#define RSMU_BASE__INST2_SEG4                      0
+#define RSMU_BASE__INST2_SEG5                      0
+
+#define RSMU_BASE__INST3_SEG0                      0
+#define RSMU_BASE__INST3_SEG1                      0
+#define RSMU_BASE__INST3_SEG2                      0
+#define RSMU_BASE__INST3_SEG3                      0
+#define RSMU_BASE__INST3_SEG4                      0
+#define RSMU_BASE__INST3_SEG5                      0
+
+#define RSMU_BASE__INST4_SEG0                      0
+#define RSMU_BASE__INST4_SEG1                      0
+#define RSMU_BASE__INST4_SEG2                      0
+#define RSMU_BASE__INST4_SEG3                      0
+#define RSMU_BASE__INST4_SEG4                      0
+#define RSMU_BASE__INST4_SEG5                      0
+
+#define RSMU_BASE__INST5_SEG0                      0
+#define RSMU_BASE__INST5_SEG1                      0
+#define RSMU_BASE__INST5_SEG2                      0
+#define RSMU_BASE__INST5_SEG3                      0
+#define RSMU_BASE__INST5_SEG4                      0
+#define RSMU_BASE__INST5_SEG5                      0
+
+#endif
+
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 7e8ad30d98e2..b493369e6d0f 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -25,30 +25,16 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/firmware.h>
 #include "amd_shared.h"
 #include "amd_powerplay.h"
 #include "power_state.h"
 #include "amdgpu.h"
 #include "hwmgr.h"
 
-#define PP_DPM_DISABLED 0xCCCC
-
-static int pp_dpm_dispatch_tasks(void *handle, enum amd_pp_task task_id,
-		enum amd_pm_state_type *user_state);
 
 static const struct amd_pm_funcs pp_dpm_funcs;
 
-static inline int pp_check(struct pp_hwmgr *hwmgr)
-{
-	if (hwmgr == NULL || hwmgr->smumgr_funcs == NULL)
-		return -EINVAL;
-
-	if (hwmgr->pm_en == 0 || hwmgr->hwmgr_func == NULL)
-		return PP_DPM_DISABLED;
-
-	return 0;
-}
-
 static int amd_powerplay_create(struct amdgpu_device *adev)
 {
 	struct pp_hwmgr *hwmgr;
@@ -61,19 +47,21 @@ static int amd_powerplay_create(struct amdgpu_device *adev)
 		return -ENOMEM;
 
 	hwmgr->adev = adev;
-	hwmgr->pm_en = (amdgpu_dpm != 0 && !amdgpu_sriov_vf(adev)) ? true : false;
+	hwmgr->not_vf = !amdgpu_sriov_vf(adev);
+	hwmgr->pm_en = (amdgpu_dpm && hwmgr->not_vf) ? true : false;
 	hwmgr->device = amdgpu_cgs_create_device(adev);
 	mutex_init(&hwmgr->smu_lock);
 	hwmgr->chip_family = adev->family;
 	hwmgr->chip_id = adev->asic_type;
-	hwmgr->feature_mask = amdgpu_pp_feature_mask;
+	hwmgr->feature_mask = adev->powerplay.pp_feature;
+	hwmgr->display_config = &adev->pm.pm_display_cfg;
 	adev->powerplay.pp_handle = hwmgr;
 	adev->powerplay.pp_funcs = &pp_dpm_funcs;
 	return 0;
 }
 
 
-static int amd_powerplay_destroy(struct amdgpu_device *adev)
+static void amd_powerplay_destroy(struct amdgpu_device *adev)
 {
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 
@@ -82,8 +70,6 @@ static int amd_powerplay_destroy(struct amdgpu_device *adev)
 
 	kfree(hwmgr);
 	hwmgr = NULL;
-
-	return 0;
 }
 
 static int pp_early_init(void *handle)
@@ -109,18 +95,9 @@ static int pp_sw_init(void *handle)
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret >= 0) {
-		if (hwmgr->smumgr_funcs->smu_init == NULL)
-			return -EINVAL;
-
-		ret = hwmgr->smumgr_funcs->smu_init(hwmgr);
+	ret = hwmgr_sw_init(hwmgr);
 
-		phm_register_irq_handlers(hwmgr);
-
-		pr_debug("amdgpu: powerplay sw initialized\n");
-	}
+	pr_debug("powerplay sw init %s\n", ret ? "failed" : "successfully");
 
 	return ret;
 }
@@ -129,16 +106,14 @@ static int pp_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret = 0;
 
-	ret = pp_check(hwmgr);
-	if (ret >= 0) {
-		if (hwmgr->smumgr_funcs->smu_fini != NULL)
-			hwmgr->smumgr_funcs->smu_fini(hwmgr);
-	}
+	hwmgr_sw_fini(hwmgr);
 
-	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU) {
+		release_firmware(adev->pm.fw);
+		adev->pm.fw = NULL;
 		amdgpu_ucode_fini_bo(adev);
+	}
 
 	return 0;
 }
@@ -152,55 +127,76 @@ static int pp_hw_init(void *handle)
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU)
 		amdgpu_ucode_init_bo(adev);
 
-	ret = pp_check(hwmgr);
+	ret = hwmgr_hw_init(hwmgr);
 
-	if (ret >= 0) {
-		if (hwmgr->smumgr_funcs->start_smu == NULL)
-			return -EINVAL;
+	if (ret)
+		pr_err("powerplay hw init failed\n");
 
-		if (hwmgr->smumgr_funcs->start_smu(hwmgr)) {
-			pr_err("smc start failed\n");
-			hwmgr->smumgr_funcs->smu_fini(hwmgr);
-			return -EINVAL;
-		}
-		if (ret == PP_DPM_DISABLED)
-			goto exit;
-		ret = hwmgr_hw_init(hwmgr);
-		if (ret)
-			goto exit;
-	}
 	return ret;
-exit:
-	hwmgr->pm_en = 0;
-	cgs_notify_dpm_enabled(hwmgr->device, false);
-	return 0;
-
 }
 
 static int pp_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret = 0;
 
-	ret = pp_check(hwmgr);
-	if (ret == 0)
-		hwmgr_hw_fini(hwmgr);
+	hwmgr_hw_fini(hwmgr);
 
 	return 0;
 }
 
+static void pp_reserve_vram_for_smu(struct amdgpu_device *adev)
+{
+	int r = -EINVAL;
+	void *cpu_ptr = NULL;
+	uint64_t gpu_addr;
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+
+	if (amdgpu_bo_create_kernel(adev, adev->pm.smu_prv_buffer_size,
+						PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
+						&adev->pm.smu_prv_buffer,
+						&gpu_addr,
+						&cpu_ptr)) {
+		DRM_ERROR("amdgpu: failed to create smu prv buffer\n");
+		return;
+	}
+
+	if (hwmgr->hwmgr_func->notify_cac_buffer_info)
+		r = hwmgr->hwmgr_func->notify_cac_buffer_info(hwmgr,
+					lower_32_bits((unsigned long)cpu_ptr),
+					upper_32_bits((unsigned long)cpu_ptr),
+					lower_32_bits(gpu_addr),
+					upper_32_bits(gpu_addr),
+					adev->pm.smu_prv_buffer_size);
+
+	if (r) {
+		amdgpu_bo_free_kernel(&adev->pm.smu_prv_buffer, NULL, NULL);
+		adev->pm.smu_prv_buffer = NULL;
+		DRM_ERROR("amdgpu: failed to notify SMU buffer address\n");
+	}
+}
+
 static int pp_late_init(void *handle)
 {
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret = 0;
-
-	ret = pp_check(hwmgr);
+	int ret;
 
-	if (ret == 0)
-		pp_dpm_dispatch_tasks(hwmgr,
+	if (hwmgr && hwmgr->pm_en) {
+		mutex_lock(&hwmgr->smu_lock);
+		hwmgr_handle_task(hwmgr,
 					AMD_PP_TASK_COMPLETE_INIT, NULL);
+		mutex_unlock(&hwmgr->smu_lock);
+	}
+	if (adev->pm.smu_prv_buffer_size != 0)
+		pp_reserve_vram_for_smu(adev);
+
+	if (hwmgr->hwmgr_func->gfx_off_control &&
+	    (hwmgr->feature_mask & PP_GFXOFF_MASK)) {
+		ret = hwmgr->hwmgr_func->gfx_off_control(hwmgr, true);
+		if (ret)
+			pr_err("gfx off enabling failed!\n");
+	}
 
 	return 0;
 }
@@ -209,6 +205,8 @@ static void pp_late_fini(void *handle)
 {
 	struct amdgpu_device *adev = handle;
 
+	if (adev->pm.smu_prv_buffer)
+		amdgpu_bo_free_kernel(&adev->pm.smu_prv_buffer, NULL, NULL);
 	amd_powerplay_destroy(adev);
 }
 
@@ -233,12 +231,18 @@ static int pp_set_powergating_state(void *handle,
 {
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret = 0;
+	int ret;
 
-	ret = pp_check(hwmgr);
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
 
-	if (ret)
-		return ret;
+	if (hwmgr->hwmgr_func->gfx_off_control) {
+		/* Enable/disable GFX off through SMU */
+		ret = hwmgr->hwmgr_func->gfx_off_control(hwmgr,
+							 state == AMD_PG_STATE_GATE);
+		if (ret)
+			pr_err("gfx off control failed!\n");
+	}
 
 	if (hwmgr->hwmgr_func->enable_per_cu_power_gating == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -254,38 +258,16 @@ static int pp_suspend(void *handle)
 {
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret = 0;
 
-	ret = pp_check(hwmgr);
-	if (ret == 0)
-		hwmgr_hw_suspend(hwmgr);
-	return 0;
+	return hwmgr_suspend(hwmgr);
 }
 
 static int pp_resume(void *handle)
 {
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret;
-
-	ret = pp_check(hwmgr);
-
-	if (ret < 0)
-		return ret;
-
-	if (hwmgr->smumgr_funcs->start_smu == NULL)
-		return -EINVAL;
-
-	if (hwmgr->smumgr_funcs->start_smu(hwmgr)) {
-		pr_err("smc start failed\n");
-		hwmgr->smumgr_funcs->smu_fini(hwmgr);
-		return -EINVAL;
-	}
-
-	if (ret == PP_DPM_DISABLED)
-		return 0;
 
-	return hwmgr_hw_resume(hwmgr);
+	return hwmgr_resume(hwmgr);
 }
 
 static int pp_set_clockgating_state(void *handle,
@@ -334,12 +316,9 @@ static int pp_dpm_fw_loading_complete(void *handle)
 static int pp_set_clockgating_by_smu(void *handle, uint32_t msg_id)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
-
-	ret = pp_check(hwmgr);
 
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->update_clock_gatings == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -362,10 +341,10 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr  *hwmgr,
 		if (*level & profile_mode_mask) {
 			hwmgr->saved_dpm_level = hwmgr->dpm_level;
 			hwmgr->en_umd_pstate = true;
-			cgs_set_clockgating_state(hwmgr->device,
+			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_GFX,
 						AMD_CG_STATE_UNGATE);
-			cgs_set_powergating_state(hwmgr->device,
+			amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_GFX,
 					AMD_PG_STATE_UNGATE);
 		}
@@ -375,10 +354,10 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr  *hwmgr,
 			if (*level == AMD_DPM_FORCED_LEVEL_PROFILE_EXIT)
 				*level = hwmgr->saved_dpm_level;
 			hwmgr->en_umd_pstate = false;
-			cgs_set_clockgating_state(hwmgr->device,
+			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_GFX,
 					AMD_CG_STATE_GATE);
-			cgs_set_powergating_state(hwmgr->device,
+			amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_GFX,
 					AMD_PG_STATE_GATE);
 		}
@@ -389,12 +368,9 @@ static int pp_dpm_force_performance_level(void *handle,
 					enum amd_dpm_forced_level level)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (level == hwmgr->dpm_level)
 		return 0;
@@ -412,13 +388,10 @@ static enum amd_dpm_forced_level pp_dpm_get_performance_level(
 								void *handle)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 	enum amd_dpm_forced_level level;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
 	level = hwmgr->dpm_level;
@@ -429,13 +402,10 @@ static enum amd_dpm_forced_level pp_dpm_get_performance_level(
 static uint32_t pp_dpm_get_sclk(void *handle, bool low)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 	uint32_t clk = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
 
 	if (hwmgr->hwmgr_func->get_sclk == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -450,13 +420,10 @@ static uint32_t pp_dpm_get_sclk(void *handle, bool low)
 static uint32_t pp_dpm_get_mclk(void *handle, bool low)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 	uint32_t clk = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
 
 	if (hwmgr->hwmgr_func->get_mclk == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -471,11 +438,8 @@ static uint32_t pp_dpm_get_mclk(void *handle, bool low)
 static void pp_dpm_powergate_vce(void *handle, bool gate)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
+	if (!hwmgr || !hwmgr->pm_en)
 		return;
 
 	if (hwmgr->hwmgr_func->powergate_vce == NULL) {
@@ -490,11 +454,8 @@ static void pp_dpm_powergate_vce(void *handle, bool gate)
 static void pp_dpm_powergate_uvd(void *handle, bool gate)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
-
-	ret = pp_check(hwmgr);
 
-	if (ret)
+	if (!hwmgr || !hwmgr->pm_en)
 		return;
 
 	if (hwmgr->hwmgr_func->powergate_uvd == NULL) {
@@ -512,10 +473,8 @@ static int pp_dpm_dispatch_tasks(void *handle, enum amd_pp_task task_id,
 	int ret = 0;
 	struct pp_hwmgr *hwmgr = handle;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
 	ret = hwmgr_handle_task(hwmgr, task_id, user_state);
@@ -528,15 +487,9 @@ static enum amd_pm_state_type pp_dpm_get_current_power_state(void *handle)
 {
 	struct pp_hwmgr *hwmgr = handle;
 	struct pp_power_state *state;
-	int ret = 0;
 	enum amd_pm_state_type pm_type;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
-
-	if (hwmgr->current_ps == NULL)
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->current_ps)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -568,11 +521,8 @@ static enum amd_pm_state_type pp_dpm_get_current_power_state(void *handle)
 static void pp_dpm_set_fan_control_mode(void *handle, uint32_t mode)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
-
-	ret = pp_check(hwmgr);
 
-	if (ret)
+	if (!hwmgr || !hwmgr->pm_en)
 		return;
 
 	if (hwmgr->hwmgr_func->set_fan_control_mode == NULL) {
@@ -587,13 +537,10 @@ static void pp_dpm_set_fan_control_mode(void *handle, uint32_t mode)
 static uint32_t pp_dpm_get_fan_control_mode(void *handle)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 	uint32_t mode = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
 
 	if (hwmgr->hwmgr_func->get_fan_control_mode == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -610,10 +557,8 @@ static int pp_dpm_set_fan_speed_percent(void *handle, uint32_t percent)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->set_fan_speed_percent == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -630,10 +575,8 @@ static int pp_dpm_get_fan_speed_percent(void *handle, uint32_t *speed)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->get_fan_speed_percent == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -651,10 +594,8 @@ static int pp_dpm_get_fan_speed_rpm(void *handle, uint32_t *rpm)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->get_fan_speed_rpm == NULL)
 		return -EINVAL;
@@ -670,16 +611,10 @@ static int pp_dpm_get_pp_num_states(void *handle,
 {
 	struct pp_hwmgr *hwmgr = handle;
 	int i;
-	int ret = 0;
 
 	memset(data, 0, sizeof(*data));
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
-
-	if (hwmgr->ps == NULL)
+	if (!hwmgr || !hwmgr->pm_en ||!hwmgr->ps)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -713,15 +648,9 @@ static int pp_dpm_get_pp_num_states(void *handle,
 static int pp_dpm_get_pp_table(void *handle, char **table)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 	int size = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
-
-	if (!hwmgr->soft_pp_table)
+	if (!hwmgr || !hwmgr->pm_en ||!hwmgr->soft_pp_table)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -736,10 +665,6 @@ static int amd_powerplay_reset(void *handle)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret;
 
-	ret = pp_check(hwmgr);
-	if (ret)
-		return ret;
-
 	ret = hwmgr_hw_fini(hwmgr);
 	if (ret)
 		return ret;
@@ -754,40 +679,38 @@ static int amd_powerplay_reset(void *handle)
 static int pp_dpm_set_pp_table(void *handle, const char *buf, size_t size)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
+	int ret = -ENOMEM;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
 	if (!hwmgr->hardcode_pp_table) {
 		hwmgr->hardcode_pp_table = kmemdup(hwmgr->soft_pp_table,
 						   hwmgr->soft_pp_table_size,
 						   GFP_KERNEL);
-		if (!hwmgr->hardcode_pp_table) {
-			mutex_unlock(&hwmgr->smu_lock);
-			return -ENOMEM;
-		}
+		if (!hwmgr->hardcode_pp_table)
+			goto err;
 	}
 
 	memcpy(hwmgr->hardcode_pp_table, buf, size);
 
 	hwmgr->soft_pp_table = hwmgr->hardcode_pp_table;
-	mutex_unlock(&hwmgr->smu_lock);
 
 	ret = amd_powerplay_reset(handle);
 	if (ret)
-		return ret;
+		goto err;
 
 	if (hwmgr->hwmgr_func->avfs_control) {
 		ret = hwmgr->hwmgr_func->avfs_control(hwmgr, false);
 		if (ret)
-			return ret;
+			goto err;
 	}
-
+	mutex_unlock(&hwmgr->smu_lock);
 	return 0;
+err:
+	mutex_unlock(&hwmgr->smu_lock);
+	return ret;
 }
 
 static int pp_dpm_force_clock_level(void *handle,
@@ -796,10 +719,8 @@ static int pp_dpm_force_clock_level(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->force_clock_level == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -820,10 +741,8 @@ static int pp_dpm_print_clock_levels(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->print_clock_levels == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -840,10 +759,8 @@ static int pp_dpm_get_sclk_od(void *handle)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->get_sclk_od == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -860,10 +777,8 @@ static int pp_dpm_set_sclk_od(void *handle, uint32_t value)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->set_sclk_od == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -881,10 +796,8 @@ static int pp_dpm_get_mclk_od(void *handle)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->get_mclk_od == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -901,10 +814,8 @@ static int pp_dpm_set_mclk_od(void *handle, uint32_t value)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->set_mclk_od == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -922,11 +833,7 @@ static int pp_dpm_read_sensor(void *handle, int idx,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-	if (ret)
-		return ret;
-
-	if (value == NULL)
+	if (!hwmgr || !hwmgr->pm_en || !value)
 		return -EINVAL;
 
 	switch (idx) {
@@ -948,14 +855,11 @@ static struct amd_vce_state*
 pp_dpm_get_vce_clock_state(void *handle, unsigned idx)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
-
-	ret = pp_check(hwmgr);
 
-	if (ret)
+	if (!hwmgr || !hwmgr->pm_en)
 		return NULL;
 
-	if (hwmgr && idx < hwmgr->num_vce_state_tables)
+	if (idx < hwmgr->num_vce_state_tables)
 		return &hwmgr->vce_states[idx];
 	return NULL;
 }
@@ -964,7 +868,7 @@ static int pp_get_power_profile_mode(void *handle, char *buf)
 {
 	struct pp_hwmgr *hwmgr = handle;
 
-	if (!buf || pp_check(hwmgr))
+	if (!hwmgr || !hwmgr->pm_en || !buf)
 		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->get_power_profile_mode == NULL) {
@@ -980,12 +884,12 @@ static int pp_set_power_profile_mode(void *handle, long *input, uint32_t size)
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = -EINVAL;
 
-	if (pp_check(hwmgr))
-		return -EINVAL;
+	if (!hwmgr || !hwmgr->pm_en)
+		return ret;
 
 	if (hwmgr->hwmgr_func->set_power_profile_mode == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
-		return -EINVAL;
+		return ret;
 	}
 	mutex_lock(&hwmgr->smu_lock);
 	if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL)
@@ -998,7 +902,7 @@ static int pp_odn_edit_dpm_table(void *handle, uint32_t type, long *input, uint3
 {
 	struct pp_hwmgr *hwmgr = handle;
 
-	if (pp_check(hwmgr))
+	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->odn_edit_dpm_table == NULL) {
@@ -1016,7 +920,7 @@ static int pp_dpm_switch_power_profile(void *handle,
 	long workload;
 	uint32_t index;
 
-	if (pp_check(hwmgr))
+	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->set_power_profile_mode == NULL) {
@@ -1048,46 +952,12 @@ static int pp_dpm_switch_power_profile(void *handle,
 	return 0;
 }
 
-static int pp_dpm_notify_smu_memory_info(void *handle,
-					uint32_t virtual_addr_low,
-					uint32_t virtual_addr_hi,
-					uint32_t mc_addr_low,
-					uint32_t mc_addr_hi,
-					uint32_t size)
-{
-	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
-
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
-
-	if (hwmgr->hwmgr_func->notify_cac_buffer_info == NULL) {
-		pr_info("%s was not implemented.\n", __func__);
-		return -EINVAL;
-	}
-
-	mutex_lock(&hwmgr->smu_lock);
-
-	ret = hwmgr->hwmgr_func->notify_cac_buffer_info(hwmgr, virtual_addr_low,
-					virtual_addr_hi, mc_addr_low, mc_addr_hi,
-					size);
-
-	mutex_unlock(&hwmgr->smu_lock);
-
-	return ret;
-}
-
 static int pp_set_power_limit(void *handle, uint32_t limit)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->set_power_limit == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -1104,20 +974,14 @@ static int pp_set_power_limit(void *handle, uint32_t limit)
 	hwmgr->hwmgr_func->set_power_limit(hwmgr, limit);
 	hwmgr->power_limit = limit;
 	mutex_unlock(&hwmgr->smu_lock);
-	return ret;
+	return 0;
 }
 
 static int pp_get_power_limit(void *handle, uint32_t *limit, bool default_limit)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
-
-	ret = pp_check(hwmgr);
 
-	if (ret)
-		return ret;
-
-	if (limit == NULL)
+	if (!hwmgr || !hwmgr->pm_en ||!limit)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1129,19 +993,16 @@ static int pp_get_power_limit(void *handle, uint32_t *limit, bool default_limit)
 
 	mutex_unlock(&hwmgr->smu_lock);
 
-	return ret;
+	return 0;
 }
 
 static int pp_display_configuration_change(void *handle,
 	const struct amd_pp_display_configuration *display_config)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
 	phm_store_dal_configuration_data(hwmgr, display_config);
@@ -1155,12 +1016,7 @@ static int pp_get_display_power_level(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
-
-	if (output == NULL)
+	if (!hwmgr || !hwmgr->pm_en ||!output)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1177,10 +1033,8 @@ static int pp_get_current_clocks(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
 
@@ -1225,10 +1079,8 @@ static int pp_get_clock_by_type(void *handle, enum amd_pp_clock_type type, struc
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (clocks == NULL)
 		return -EINVAL;
@@ -1246,11 +1098,7 @@ static int pp_get_clock_by_type_with_latency(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-	if (ret)
-		return ret;
-
-	if (!clocks)
+	if (!hwmgr || !hwmgr->pm_en ||!clocks)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1266,11 +1114,7 @@ static int pp_get_clock_by_type_with_voltage(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-	if (ret)
-		return ret;
-
-	if (!clocks)
+	if (!hwmgr || !hwmgr->pm_en ||!clocks)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1287,11 +1131,7 @@ static int pp_set_watermarks_for_clocks_ranges(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-	if (ret)
-		return ret;
-
-	if (!wm_with_clock_ranges)
+	if (!hwmgr || !hwmgr->pm_en ||!wm_with_clock_ranges)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1308,11 +1148,7 @@ static int pp_display_clock_voltage_request(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-	if (ret)
-		return ret;
-
-	if (!clock)
+	if (!hwmgr || !hwmgr->pm_en ||!clock)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1328,12 +1164,7 @@ static int pp_get_display_mode_validation_clocks(void *handle,
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
-
-	if (clocks == NULL)
+	if (!hwmgr || !hwmgr->pm_en ||!clocks)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1348,12 +1179,9 @@ static int pp_get_display_mode_validation_clocks(void *handle,
 static int pp_set_mmhub_powergating_by_smu(void *handle)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = 0;
 
-	ret = pp_check(hwmgr);
-
-	if (ret)
-		return ret;
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->set_mmhub_powergating_by_smu == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
@@ -1390,7 +1218,6 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.get_vce_clock_state = pp_dpm_get_vce_clock_state,
 	.switch_power_profile = pp_dpm_switch_power_profile,
 	.set_clockgating_by_smu = pp_set_clockgating_by_smu,
-	.notify_smu_memory_info = pp_dpm_notify_smu_memory_info,
 	.get_power_profile_mode = pp_get_power_profile_mode,
 	.set_power_profile_mode = pp_set_power_profile_mode,
 	.odn_edit_dpm_table = pp_odn_edit_dpm_table,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index ae2e9339dd6b..a0bb921fac22 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -75,8 +75,7 @@ int phm_set_power_state(struct pp_hwmgr *hwmgr,
 
 int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 {
-	int ret = 1;
-	bool enabled;
+	int ret = -EINVAL;;
 	PHM_FUNC_CHECK(hwmgr);
 
 	if (smum_is_dpm_running(hwmgr)) {
@@ -87,17 +86,12 @@ int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 	if (NULL != hwmgr->hwmgr_func->dynamic_state_management_enable)
 		ret = hwmgr->hwmgr_func->dynamic_state_management_enable(hwmgr);
 
-	enabled = ret == 0;
-
-	cgs_notify_dpm_enabled(hwmgr->device, enabled);
-
 	return ret;
 }
 
 int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 {
-	int ret = -1;
-	bool enabled;
+	int ret = -EINVAL;
 
 	PHM_FUNC_CHECK(hwmgr);
 
@@ -109,10 +103,6 @@ int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 	if (hwmgr->hwmgr_func->dynamic_state_management_disable)
 		ret = hwmgr->hwmgr_func->dynamic_state_management_disable(hwmgr);
 
-	enabled = ret == 0 ? false : true;
-
-	cgs_notify_dpm_enabled(hwmgr->device, enabled);
-
 	return ret;
 }
 
@@ -142,6 +132,15 @@ int phm_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+int phm_apply_clock_adjust_rules(struct pp_hwmgr *hwmgr)
+{
+	PHM_FUNC_CHECK(hwmgr);
+
+	if (hwmgr->hwmgr_func->apply_clocks_adjust_rules != NULL)
+		return hwmgr->hwmgr_func->apply_clocks_adjust_rules(hwmgr);
+	return 0;
+}
+
 int phm_powerdown_uvd(struct pp_hwmgr *hwmgr)
 {
 	PHM_FUNC_CHECK(hwmgr);
@@ -171,6 +170,16 @@ int phm_disable_clock_power_gatings(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+int phm_pre_display_configuration_changed(struct pp_hwmgr *hwmgr)
+{
+	PHM_FUNC_CHECK(hwmgr);
+
+	if (NULL != hwmgr->hwmgr_func->pre_display_config_changed)
+		hwmgr->hwmgr_func->pre_display_config_changed(hwmgr);
+
+	return 0;
+
+}
 
 int phm_display_configuration_changed(struct pp_hwmgr *hwmgr)
 {
@@ -275,13 +284,11 @@ int phm_store_dal_configuration_data(struct pp_hwmgr *hwmgr,
 	if (display_config == NULL)
 		return -EINVAL;
 
-	hwmgr->display_config = *display_config;
-
 	if (NULL != hwmgr->hwmgr_func->set_deep_sleep_dcefclk)
-		hwmgr->hwmgr_func->set_deep_sleep_dcefclk(hwmgr, hwmgr->display_config.min_dcef_deep_sleep_set_clk);
+		hwmgr->hwmgr_func->set_deep_sleep_dcefclk(hwmgr, display_config->min_dcef_deep_sleep_set_clk);
 
-	for (index = 0; index < hwmgr->display_config.num_path_including_non_display; index++) {
-		if (hwmgr->display_config.displays[index].controller_id != 0)
+	for (index = 0; index < display_config->num_path_including_non_display; index++) {
+		if (display_config->displays[index].controller_id != 0)
 			number_of_active_display++;
 	}
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 42982055b161..e63bc47dc715 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -40,6 +40,7 @@ extern const struct pp_smumgr_func iceland_smu_funcs;
 extern const struct pp_smumgr_func tonga_smu_funcs;
 extern const struct pp_smumgr_func fiji_smu_funcs;
 extern const struct pp_smumgr_func polaris10_smu_funcs;
+extern const struct pp_smumgr_func vegam_smu_funcs;
 extern const struct pp_smumgr_func vega10_smu_funcs;
 extern const struct pp_smumgr_func vega12_smu_funcs;
 extern const struct pp_smumgr_func smu10_smu_funcs;
@@ -76,7 +77,7 @@ static void hwmgr_init_workload_prority(struct pp_hwmgr *hwmgr)
 
 int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 {
-	if (hwmgr == NULL)
+	if (!hwmgr)
 		return -EINVAL;
 
 	hwmgr->usec_timeout = AMD_MAX_USEC_TIMEOUT;
@@ -95,7 +96,8 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 		hwmgr->smumgr_funcs = &ci_smu_funcs;
 		ci_set_asic_special_caps(hwmgr);
 		hwmgr->feature_mask &= ~(PP_VBI_TIME_SUPPORT_MASK |
-					PP_ENABLE_GFX_CG_THRU_SMU);
+					 PP_ENABLE_GFX_CG_THRU_SMU |
+					 PP_GFXOFF_MASK);
 		hwmgr->pp_table_version = PP_TABLE_V0;
 		hwmgr->od_enabled = false;
 		smu7_init_function_pointers(hwmgr);
@@ -103,9 +105,11 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 	case AMDGPU_FAMILY_CZ:
 		hwmgr->od_enabled = false;
 		hwmgr->smumgr_funcs = &smu8_smu_funcs;
+		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		smu8_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_VI:
+		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		switch (hwmgr->chip_id) {
 		case CHIP_TOPAZ:
 			hwmgr->smumgr_funcs = &iceland_smu_funcs;
@@ -133,14 +137,21 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 			polaris_set_asic_special_caps(hwmgr);
 			hwmgr->feature_mask &= ~(PP_UVD_HANDSHAKE_MASK);
 			break;
+		case CHIP_VEGAM:
+			hwmgr->smumgr_funcs = &vegam_smu_funcs;
+			polaris_set_asic_special_caps(hwmgr);
+			hwmgr->feature_mask &= ~(PP_UVD_HANDSHAKE_MASK);
+			break;
 		default:
 			return -EINVAL;
 		}
 		smu7_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_AI:
+		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		switch (hwmgr->chip_id) {
 		case CHIP_VEGA10:
+		case CHIP_VEGA20:
 			hwmgr->smumgr_funcs = &vega10_smu_funcs;
 			vega10_hwmgr_init(hwmgr);
 			break;
@@ -170,22 +181,58 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+int hwmgr_sw_init(struct pp_hwmgr *hwmgr)
+{
+	if (!hwmgr|| !hwmgr->smumgr_funcs || !hwmgr->smumgr_funcs->smu_init)
+		return -EINVAL;
+
+	phm_register_irq_handlers(hwmgr);
+
+	return hwmgr->smumgr_funcs->smu_init(hwmgr);
+}
+
+
+int hwmgr_sw_fini(struct pp_hwmgr *hwmgr)
+{
+	if (hwmgr && hwmgr->smumgr_funcs && hwmgr->smumgr_funcs->smu_fini)
+		hwmgr->smumgr_funcs->smu_fini(hwmgr);
+
+	return 0;
+}
+
 int hwmgr_hw_init(struct pp_hwmgr *hwmgr)
 {
 	int ret = 0;
 
-	if (hwmgr == NULL)
+	if (!hwmgr || !hwmgr->smumgr_funcs)
 		return -EINVAL;
 
-	if (hwmgr->pptable_func == NULL ||
-	    hwmgr->pptable_func->pptable_init == NULL ||
-	    hwmgr->hwmgr_func->backend_init == NULL)
-		return -EINVAL;
+	if (hwmgr->smumgr_funcs->start_smu) {
+		ret = hwmgr->smumgr_funcs->start_smu(hwmgr);
+		if (ret) {
+			pr_err("smc start failed\n");
+			return -EINVAL;
+		}
+	}
+
+	if (!hwmgr->pm_en)
+		return 0;
+
+	if (!hwmgr->pptable_func ||
+	    !hwmgr->pptable_func->pptable_init ||
+	    !hwmgr->hwmgr_func->backend_init) {
+		hwmgr->pm_en = false;
+		pr_info("dpm not supported \n");
+		return 0;
+	}
 
 	ret = hwmgr->pptable_func->pptable_init(hwmgr);
 	if (ret)
 		goto err;
 
+	((struct amdgpu_device *)hwmgr->adev)->pm.no_fan =
+				hwmgr->thermal_controller.fanInfo.bNoFan;
+
 	ret = hwmgr->hwmgr_func->backend_init(hwmgr);
 	if (ret)
 		goto err1;
@@ -206,6 +253,8 @@ int hwmgr_hw_init(struct pp_hwmgr *hwmgr)
 	if (ret)
 		goto err2;
 
+	((struct amdgpu_device *)hwmgr->adev)->pm.dpm_enabled = true;
+
 	return 0;
 err2:
 	if (hwmgr->hwmgr_func->backend_fini)
@@ -214,14 +263,13 @@ err1:
 	if (hwmgr->pptable_func->pptable_fini)
 		hwmgr->pptable_func->pptable_fini(hwmgr);
 err:
-	pr_err("amdgpu: powerplay initialization failed\n");
 	return ret;
 }
 
 int hwmgr_hw_fini(struct pp_hwmgr *hwmgr)
 {
-	if (hwmgr == NULL)
-		return -EINVAL;
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
 
 	phm_stop_thermal_controller(hwmgr);
 	psm_set_boot_states(hwmgr);
@@ -236,12 +284,12 @@ int hwmgr_hw_fini(struct pp_hwmgr *hwmgr)
 	return psm_fini_power_state_table(hwmgr);
 }
 
-int hwmgr_hw_suspend(struct pp_hwmgr *hwmgr)
+int hwmgr_suspend(struct pp_hwmgr *hwmgr)
 {
 	int ret = 0;
 
-	if (hwmgr == NULL)
-		return -EINVAL;
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
 
 	phm_disable_smc_firmware_ctf(hwmgr);
 	ret = psm_set_boot_states(hwmgr);
@@ -255,13 +303,23 @@ int hwmgr_hw_suspend(struct pp_hwmgr *hwmgr)
 	return ret;
 }
 
-int hwmgr_hw_resume(struct pp_hwmgr *hwmgr)
+int hwmgr_resume(struct pp_hwmgr *hwmgr)
 {
 	int ret = 0;
 
-	if (hwmgr == NULL)
+	if (!hwmgr)
 		return -EINVAL;
 
+	if (hwmgr->smumgr_funcs && hwmgr->smumgr_funcs->start_smu) {
+		if (hwmgr->smumgr_funcs->start_smu(hwmgr)) {
+			pr_err("smc start failed\n");
+			return -EINVAL;
+		}
+	}
+
+	if (!hwmgr->pm_en)
+		return 0;
+
 	ret = phm_setup_asic(hwmgr);
 	if (ret)
 		return ret;
@@ -270,9 +328,6 @@ int hwmgr_hw_resume(struct pp_hwmgr *hwmgr)
 	if (ret)
 		return ret;
 	ret = phm_start_thermal_controller(hwmgr);
-	if (ret)
-		return ret;
-
 	ret |= psm_set_performance_states(hwmgr);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
index 0f2851b5b368..0af13c154328 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
@@ -46,7 +46,7 @@ int psm_init_power_state_table(struct pp_hwmgr *hwmgr)
 					  sizeof(struct pp_power_state);
 
 	if (table_entries == 0 || size == 0) {
-		pr_warn("Please check whether power state management is suppported on this asic\n");
+		pr_warn("Please check whether power state management is supported on this asic\n");
 		return 0;
 	}
 
@@ -265,6 +265,15 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip,
 	if (skip)
 		return 0;
 
+	if (!hwmgr->ps)
+		/*
+		 * for vega12/vega20 which does not support power state manager
+		 * DAL clock limits should also be honoured
+		 */
+		phm_apply_clock_adjust_rules(hwmgr);
+
+	phm_pre_display_configuration_changed(hwmgr);
+
 	phm_display_configuration_changed(hwmgr);
 
 	if (hwmgr->ps)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index c6febbf0bf69..7047e29755c3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -23,7 +23,8 @@
 #include "pp_debug.h"
 #include <linux/module.h>
 #include <linux/slab.h>
-
+#include <linux/delay.h>
+#include "atom.h"
 #include "ppatomctrl.h"
 #include "atombios.h"
 #include "cgs_common.h"
@@ -128,7 +129,6 @@ static int atomctrl_set_mc_reg_address_table(
 	return 0;
 }
 
-
 int atomctrl_initialize_mc_reg_table(
 		struct pp_hwmgr *hwmgr,
 		uint8_t module_index,
@@ -141,7 +141,7 @@ int atomctrl_initialize_mc_reg_table(
 	u16 size;
 
 	vram_info = (ATOM_VRAM_INFO_HEADER_V2_1 *)
-		cgs_atom_get_data_table(hwmgr->device,
+		smu_atom_get_data_table(hwmgr->adev,
 				GetIndexIntoMasterTable(DATA, VRAM_Info), &size, &frev, &crev);
 
 	if (module_index >= vram_info->ucNumOfVRAMModule) {
@@ -174,6 +174,8 @@ int atomctrl_set_engine_dram_timings_rv770(
 		uint32_t engine_clock,
 		uint32_t memory_clock)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
+
 	SET_ENGINE_CLOCK_PS_ALLOCATION engine_clock_parameters;
 
 	/* They are both in 10KHz Units. */
@@ -184,9 +186,10 @@ int atomctrl_set_engine_dram_timings_rv770(
 	/* in 10 khz units.*/
 	engine_clock_parameters.sReserved.ulClock =
 		cpu_to_le32(memory_clock & SET_CLOCK_FREQ_MASK);
-	return cgs_atom_exec_cmd_table(hwmgr->device,
+
+	return amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, DynamicMemorySettings),
-			&engine_clock_parameters);
+			(uint32_t *)&engine_clock_parameters);
 }
 
 /**
@@ -203,7 +206,7 @@ static ATOM_VOLTAGE_OBJECT_INFO *get_voltage_info_table(void *device)
 	union voltage_object_info *voltage_info;
 
 	voltage_info = (union voltage_object_info *)
-		cgs_atom_get_data_table(device, index,
+		smu_atom_get_data_table(device, index,
 			&size, &frev, &crev);
 
 	if (voltage_info != NULL)
@@ -247,16 +250,16 @@ int atomctrl_get_memory_pll_dividers_si(
 		pp_atomctrl_memory_clock_param *mpll_param,
 		bool strobe_mode)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_1 mpll_parameters;
 	int result;
 
 	mpll_parameters.ulClock = cpu_to_le32(clock_value);
 	mpll_parameters.ucInputFlag = (uint8_t)((strobe_mode) ? 1 : 0);
 
-	result = cgs_atom_exec_cmd_table
-		(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam),
-		 &mpll_parameters);
+		(uint32_t *)&mpll_parameters);
 
 	if (0 == result) {
 		mpll_param->mpll_fb_divider.clk_frac =
@@ -295,14 +298,15 @@ int atomctrl_get_memory_pll_dividers_si(
 int atomctrl_get_memory_pll_dividers_vi(struct pp_hwmgr *hwmgr,
 		uint32_t clock_value, pp_atomctrl_memory_clock_param *mpll_param)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_2 mpll_parameters;
 	int result;
 
 	mpll_parameters.ulClock.ulClock = cpu_to_le32(clock_value);
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam),
-			&mpll_parameters);
+			(uint32_t *)&mpll_parameters);
 
 	if (!result)
 		mpll_param->mpll_post_divider =
@@ -311,19 +315,49 @@ int atomctrl_get_memory_pll_dividers_vi(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
+int atomctrl_get_memory_pll_dividers_ai(struct pp_hwmgr *hwmgr,
+					uint32_t clock_value,
+					pp_atomctrl_memory_clock_param_ai *mpll_param)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_3 mpll_parameters = {{0}, 0, 0};
+	int result;
+
+	mpll_parameters.ulClock.ulClock = cpu_to_le32(clock_value);
+
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
+			GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam),
+			(uint32_t *)&mpll_parameters);
+
+	/* VEGAM's mpll takes sometime to finish computing */
+	udelay(10);
+
+	if (!result) {
+		mpll_param->ulMclk_fcw_int =
+			le16_to_cpu(mpll_parameters.usMclk_fcw_int);
+		mpll_param->ulMclk_fcw_frac =
+			le16_to_cpu(mpll_parameters.usMclk_fcw_frac);
+		mpll_param->ulClock =
+			le32_to_cpu(mpll_parameters.ulClock.ulClock);
+		mpll_param->ulPostDiv = mpll_parameters.ulClock.ucPostDiv;
+	}
+
+	return result;
+}
+
 int atomctrl_get_engine_pll_dividers_kong(struct pp_hwmgr *hwmgr,
 					  uint32_t clock_value,
 					  pp_atomctrl_clock_dividers_kong *dividers)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	COMPUTE_MEMORY_ENGINE_PLL_PARAMETERS_V4 pll_parameters;
 	int result;
 
 	pll_parameters.ulClock = cpu_to_le32(clock_value);
 
-	result = cgs_atom_exec_cmd_table
-		(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL),
-		 &pll_parameters);
+		(uint32_t *)&pll_parameters);
 
 	if (0 == result) {
 		dividers->pll_post_divider = pll_parameters.ucPostDiv;
@@ -338,16 +372,16 @@ int atomctrl_get_engine_pll_dividers_vi(
 		uint32_t clock_value,
 		pp_atomctrl_clock_dividers_vi *dividers)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_6 pll_patameters;
 	int result;
 
 	pll_patameters.ulClock.ulClock = cpu_to_le32(clock_value);
 	pll_patameters.ulClock.ucPostDiv = COMPUTE_GPUCLK_INPUT_FLAG_SCLK;
 
-	result = cgs_atom_exec_cmd_table
-		(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL),
-		 &pll_patameters);
+		(uint32_t *)&pll_patameters);
 
 	if (0 == result) {
 		dividers->pll_post_divider =
@@ -375,16 +409,16 @@ int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr,
 		uint32_t clock_value,
 		pp_atomctrl_clock_dividers_ai *dividers)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_7 pll_patameters;
 	int result;
 
 	pll_patameters.ulClock.ulClock = cpu_to_le32(clock_value);
 	pll_patameters.ulClock.ucPostDiv = COMPUTE_GPUCLK_INPUT_FLAG_SCLK;
 
-	result = cgs_atom_exec_cmd_table
-		(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL),
-		 &pll_patameters);
+		(uint32_t *)&pll_patameters);
 
 	if (0 == result) {
 		dividers->usSclk_fcw_frac     = le16_to_cpu(pll_patameters.usSclk_fcw_frac);
@@ -407,6 +441,7 @@ int atomctrl_get_dfs_pll_dividers_vi(
 		uint32_t clock_value,
 		pp_atomctrl_clock_dividers_vi *dividers)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_6 pll_patameters;
 	int result;
 
@@ -414,10 +449,9 @@ int atomctrl_get_dfs_pll_dividers_vi(
 	pll_patameters.ulClock.ucPostDiv =
 		COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK;
 
-	result = cgs_atom_exec_cmd_table
-		(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL),
-		 &pll_patameters);
+		(uint32_t *)&pll_patameters);
 
 	if (0 == result) {
 		dividers->pll_post_divider =
@@ -452,7 +486,7 @@ uint32_t atomctrl_get_reference_clock(struct pp_hwmgr *hwmgr)
 	uint32_t clock;
 
 	fw_info = (ATOM_FIRMWARE_INFO *)
-		cgs_atom_get_data_table(hwmgr->device,
+		smu_atom_get_data_table(hwmgr->adev,
 			GetIndexIntoMasterTable(DATA, FirmwareInfo),
 			&size, &frev, &crev);
 
@@ -476,7 +510,7 @@ bool atomctrl_is_voltage_controlled_by_gpio_v3(
 		uint8_t voltage_mode)
 {
 	ATOM_VOLTAGE_OBJECT_INFO_V3_1 *voltage_info =
-		(ATOM_VOLTAGE_OBJECT_INFO_V3_1 *)get_voltage_info_table(hwmgr->device);
+		(ATOM_VOLTAGE_OBJECT_INFO_V3_1 *)get_voltage_info_table(hwmgr->adev);
 	bool ret;
 
 	PP_ASSERT_WITH_CODE((NULL != voltage_info),
@@ -495,7 +529,7 @@ int atomctrl_get_voltage_table_v3(
 		pp_atomctrl_voltage_table *voltage_table)
 {
 	ATOM_VOLTAGE_OBJECT_INFO_V3_1 *voltage_info =
-		(ATOM_VOLTAGE_OBJECT_INFO_V3_1 *)get_voltage_info_table(hwmgr->device);
+		(ATOM_VOLTAGE_OBJECT_INFO_V3_1 *)get_voltage_info_table(hwmgr->adev);
 	const ATOM_VOLTAGE_OBJECT_V3 *voltage_object;
 	unsigned int i;
 
@@ -572,7 +606,7 @@ static ATOM_GPIO_PIN_LUT *get_gpio_lookup_table(void *device)
 	void *table_address;
 
 	table_address = (ATOM_GPIO_PIN_LUT *)
-		cgs_atom_get_data_table(device,
+		smu_atom_get_data_table(device,
 				GetIndexIntoMasterTable(DATA, GPIO_Pin_LUT),
 				&size, &frev, &crev);
 
@@ -592,7 +626,7 @@ bool atomctrl_get_pp_assign_pin(
 {
 	bool bRet = false;
 	ATOM_GPIO_PIN_LUT *gpio_lookup_table =
-		get_gpio_lookup_table(hwmgr->device);
+		get_gpio_lookup_table(hwmgr->adev);
 
 	PP_ASSERT_WITH_CODE((NULL != gpio_lookup_table),
 			"Could not find GPIO lookup Table in BIOS.", return false);
@@ -613,7 +647,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 		bool debug)
 {
 	ATOM_ASIC_PROFILING_INFO_V3_4 *getASICProfilingInfo;
-
+	struct amdgpu_device *adev = hwmgr->adev;
 	EFUSE_LINEAR_FUNC_PARAM sRO_fuse;
 	EFUSE_LINEAR_FUNC_PARAM sCACm_fuse;
 	EFUSE_LINEAR_FUNC_PARAM sCACb_fuse;
@@ -640,7 +674,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	int result;
 
 	getASICProfilingInfo = (ATOM_ASIC_PROFILING_INFO_V3_4 *)
-			cgs_atom_get_data_table(hwmgr->device,
+			smu_atom_get_data_table(hwmgr->adev,
 					GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo),
 					NULL, NULL, NULL);
 
@@ -706,9 +740,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	sOutput_FuseValues.sEfuse = sInput_FuseValues;
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues);
 
 	if (result)
 		return result;
@@ -727,9 +761,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	sOutput_FuseValues.sEfuse = sInput_FuseValues;
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues);
 
 	if (result)
 		return result;
@@ -747,9 +781,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	sInput_FuseValues.ucBitLength = sCACb_fuse.ucEfuseLength;
 	sOutput_FuseValues.sEfuse = sInput_FuseValues;
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues);
 
 	if (result)
 		return result;
@@ -768,9 +802,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	sOutput_FuseValues.sEfuse = sInput_FuseValues;
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues);
 
 	if (result)
 		return result;
@@ -790,9 +824,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	sOutput_FuseValues.sEfuse = sInput_FuseValues;
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues);
 	if (result)
 		return result;
 
@@ -811,9 +845,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	sInput_FuseValues.ucBitLength = sKv_b_fuse.ucEfuseLength;
 	sOutput_FuseValues.sEfuse = sInput_FuseValues;
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues);
 
 	if (result)
 		return result;
@@ -842,9 +876,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	sOutput_FuseValues.sEfuse = sInput_FuseValues;
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			&sOutput_FuseValues);
+			(uint32_t *)&sOutput_FuseValues);
 
 	if (result)
 		return result;
@@ -1053,8 +1087,9 @@ int atomctrl_get_voltage_evv_on_sclk(
 		uint32_t sclk, uint16_t virtual_voltage_Id,
 		uint16_t *voltage)
 {
-	int result;
+	struct amdgpu_device *adev = hwmgr->adev;
 	GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 get_voltage_info_param_space;
+	int result;
 
 	get_voltage_info_param_space.ucVoltageType   =
 		voltage_type;
@@ -1065,14 +1100,12 @@ int atomctrl_get_voltage_evv_on_sclk(
 	get_voltage_info_param_space.ulSCLKFreq      =
 		cpu_to_le32(sclk);
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
-			&get_voltage_info_param_space);
-
-	if (0 != result)
-		return result;
+			(uint32_t *)&get_voltage_info_param_space);
 
-	*voltage = le16_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *)
+	*voltage = result ? 0 :
+			le16_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *)
 				(&get_voltage_info_param_space))->usVoltageLevel);
 
 	return result;
@@ -1088,9 +1121,10 @@ int atomctrl_get_voltage_evv(struct pp_hwmgr *hwmgr,
 			     uint16_t virtual_voltage_id,
 			     uint16_t *voltage)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
+	GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 get_voltage_info_param_space;
 	int result;
 	int entry_id;
-	GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 get_voltage_info_param_space;
 
 	/* search for leakage voltage ID 0xff01 ~ 0xff08 and sckl */
 	for (entry_id = 0; entry_id < hwmgr->dyn_state.vddc_dependency_on_sclk->count; entry_id++) {
@@ -1111,9 +1145,9 @@ int atomctrl_get_voltage_evv(struct pp_hwmgr *hwmgr,
 	get_voltage_info_param_space.ulSCLKFreq =
 		cpu_to_le32(hwmgr->dyn_state.vddc_dependency_on_sclk->entries[entry_id].clk);
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
-			&get_voltage_info_param_space);
+			(uint32_t *)&get_voltage_info_param_space);
 
 	if (0 != result)
 		return result;
@@ -1135,7 +1169,7 @@ uint32_t atomctrl_get_mpll_reference_clock(struct pp_hwmgr *hwmgr)
 	u16 size;
 
 	fw_info = (ATOM_COMMON_TABLE_HEADER *)
-		cgs_atom_get_data_table(hwmgr->device,
+		smu_atom_get_data_table(hwmgr->adev,
 				GetIndexIntoMasterTable(DATA, FirmwareInfo),
 				&size, &frev, &crev);
 
@@ -1167,7 +1201,7 @@ static ATOM_ASIC_INTERNAL_SS_INFO *asic_internal_ss_get_ss_table(void *device)
 	u16 size;
 
 	table = (ATOM_ASIC_INTERNAL_SS_INFO *)
-		cgs_atom_get_data_table(device,
+		smu_atom_get_data_table(device,
 			GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info),
 			&size, &frev, &crev);
 
@@ -1188,7 +1222,7 @@ static int asic_internal_ss_get_ss_asignment(struct pp_hwmgr *hwmgr,
 
 	memset(ssEntry, 0x00, sizeof(pp_atomctrl_internal_ss_info));
 
-	table = asic_internal_ss_get_ss_table(hwmgr->device);
+	table = asic_internal_ss_get_ss_table(hwmgr->adev);
 
 	if (NULL == table)
 		return -1;
@@ -1260,9 +1294,10 @@ int atomctrl_get_engine_clock_spread_spectrum(
 			ASIC_INTERNAL_ENGINE_SS, engine_clock, ssInfo);
 }
 
-int atomctrl_read_efuse(void *device, uint16_t start_index,
+int atomctrl_read_efuse(struct pp_hwmgr *hwmgr, uint16_t start_index,
 		uint16_t end_index, uint32_t mask, uint32_t *efuse)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int result;
 	READ_EFUSE_VALUE_PARAMETER efuse_param;
 
@@ -1272,11 +1307,10 @@ int atomctrl_read_efuse(void *device, uint16_t start_index,
 	efuse_param.sEfuse.ucBitLength  = (uint8_t)
 			((end_index - start_index) + 1);
 
-	result = cgs_atom_exec_cmd_table(device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
-			&efuse_param);
-	if (!result)
-		*efuse = le32_to_cpu(efuse_param.ulEfuseValue) & mask;
+			(uint32_t *)&efuse_param);
+	*efuse = result ? 0 : le32_to_cpu(efuse_param.ulEfuseValue) & mask;
 
 	return result;
 }
@@ -1284,6 +1318,7 @@ int atomctrl_read_efuse(void *device, uint16_t start_index,
 int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 			      uint8_t level)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	DYNAMICE_MEMORY_SETTINGS_PARAMETER_V2_1 memory_clock_parameters;
 	int result;
 
@@ -1293,10 +1328,9 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 		ADJUST_MC_SETTING_PARAM;
 	memory_clock_parameters.asDPMMCReg.ucMclkDPMState = level;
 
-	result = cgs_atom_exec_cmd_table
-		(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 		 GetIndexIntoMasterTable(COMMAND, DynamicMemorySettings),
-		 &memory_clock_parameters);
+		(uint32_t *)&memory_clock_parameters);
 
 	return result;
 }
@@ -1304,7 +1338,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
 				uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage)
 {
-
+	struct amdgpu_device *adev = hwmgr->adev;
 	int result;
 	GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_3 get_voltage_info_param_space;
 
@@ -1313,15 +1347,12 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
 	get_voltage_info_param_space.usVoltageLevel = cpu_to_le16(virtual_voltage_Id);
 	get_voltage_info_param_space.ulSCLKFreq = cpu_to_le32(sclk);
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
-			&get_voltage_info_param_space);
+			(uint32_t *)&get_voltage_info_param_space);
 
-	if (0 != result)
-		return result;
-
-	*voltage = le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)
-				(&get_voltage_info_param_space))->ulVoltageLevel);
+	*voltage = result ? 0 :
+		le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel);
 
 	return result;
 }
@@ -1334,7 +1365,7 @@ int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctr
 	u16 size;
 
 	ATOM_SMU_INFO_V2_1 *psmu_info =
-		(ATOM_SMU_INFO_V2_1 *)cgs_atom_get_data_table(hwmgr->device,
+		(ATOM_SMU_INFO_V2_1 *)smu_atom_get_data_table(hwmgr->adev,
 			GetIndexIntoMasterTable(DATA, SMU_Info),
 			&size, &frev, &crev);
 
@@ -1362,7 +1393,7 @@ int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 
 	profile = (ATOM_ASIC_PROFILING_INFO_V3_6 *)
-			cgs_atom_get_data_table(hwmgr->device,
+			smu_atom_get_data_table(hwmgr->adev,
 					GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo),
 					NULL, NULL, NULL);
 	if (!profile)
@@ -1402,7 +1433,7 @@ int  atomctrl_get_svi2_info(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
 				uint16_t *load_line)
 {
 	ATOM_VOLTAGE_OBJECT_INFO_V3_1 *voltage_info =
-		(ATOM_VOLTAGE_OBJECT_INFO_V3_1 *)get_voltage_info_table(hwmgr->device);
+		(ATOM_VOLTAGE_OBJECT_INFO_V3_1 *)get_voltage_info_table(hwmgr->adev);
 
 	const ATOM_VOLTAGE_OBJECT_V3 *voltage_object;
 
@@ -1421,16 +1452,17 @@ int  atomctrl_get_svi2_info(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
 
 int atomctrl_get_leakage_id_from_efuse(struct pp_hwmgr *hwmgr, uint16_t *virtual_voltage_id)
 {
-	int result;
+	struct amdgpu_device *adev = hwmgr->adev;
 	SET_VOLTAGE_PS_ALLOCATION allocation;
 	SET_VOLTAGE_PARAMETERS_V1_3 *voltage_parameters =
 			(SET_VOLTAGE_PARAMETERS_V1_3 *)&allocation.sASICSetVoltage;
+	int result;
 
 	voltage_parameters->ucVoltageMode = ATOM_GET_LEAKAGE_ID;
 
-	result = cgs_atom_exec_cmd_table(hwmgr->device,
+	result = amdgpu_atom_execute_table(adev->mode_info.atom_context,
 			GetIndexIntoMasterTable(COMMAND, SetVoltage),
-			voltage_parameters);
+			(uint32_t *)voltage_parameters);
 
 	*virtual_voltage_id = voltage_parameters->usVoltageLevel;
 
@@ -1453,7 +1485,7 @@ int atomctrl_get_leakage_vddc_base_on_leakage(struct pp_hwmgr *hwmgr,
 	ix = GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo);
 
 	profile = (ATOM_ASIC_PROFILING_INFO_V2_1 *)
-			cgs_atom_get_data_table(hwmgr->device,
+			smu_atom_get_data_table(hwmgr->adev,
 					ix,
 					NULL, NULL, NULL);
 	if (!profile)
@@ -1498,3 +1530,33 @@ int atomctrl_get_leakage_vddc_base_on_leakage(struct pp_hwmgr *hwmgr,
 
 	return 0;
 }
+
+void atomctrl_get_voltage_range(struct pp_hwmgr *hwmgr, uint32_t *max_vddc,
+							uint32_t *min_vddc)
+{
+	void *profile;
+
+	profile = smu_atom_get_data_table(hwmgr->adev,
+					GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo),
+					NULL, NULL, NULL);
+
+	if (profile) {
+		switch (hwmgr->chip_id) {
+		case CHIP_TONGA:
+		case CHIP_FIJI:
+			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMaxVddc/4);
+			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMinVddc/4);
+			return;
+		case CHIP_POLARIS11:
+		case CHIP_POLARIS10:
+		case CHIP_POLARIS12:
+			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMaxVddc/100);
+			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMinVddc/100);
+			return;
+		default:
+			break;
+		}
+	}
+	*max_vddc = 0;
+	*min_vddc = 0;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
index c44a92064cf1..3ee54f182943 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
@@ -146,6 +146,14 @@ struct pp_atomctrl_memory_clock_param {
 };
 typedef struct pp_atomctrl_memory_clock_param pp_atomctrl_memory_clock_param;
 
+struct pp_atomctrl_memory_clock_param_ai {
+	uint32_t ulClock;
+	uint32_t ulPostDiv;
+	uint16_t ulMclk_fcw_frac;
+	uint16_t ulMclk_fcw_int;
+};
+typedef struct pp_atomctrl_memory_clock_param_ai pp_atomctrl_memory_clock_param_ai;
+
 struct pp_atomctrl_internal_ss_info {
 	uint32_t speed_spectrum_percentage;                      /* in 1/100 percentage */
 	uint32_t speed_spectrum_rate;                            /* in KHz */
@@ -295,10 +303,12 @@ extern bool atomctrl_is_voltage_controlled_by_gpio_v3(struct pp_hwmgr *hwmgr, ui
 extern int atomctrl_get_voltage_table_v3(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint8_t voltage_mode, pp_atomctrl_voltage_table *voltage_table);
 extern int atomctrl_get_memory_pll_dividers_vi(struct pp_hwmgr *hwmgr,
 		uint32_t clock_value, pp_atomctrl_memory_clock_param *mpll_param);
+extern int atomctrl_get_memory_pll_dividers_ai(struct pp_hwmgr *hwmgr,
+		uint32_t clock_value, pp_atomctrl_memory_clock_param_ai *mpll_param);
 extern int atomctrl_get_engine_pll_dividers_kong(struct pp_hwmgr *hwmgr,
 						 uint32_t clock_value,
 						 pp_atomctrl_clock_dividers_kong *dividers);
-extern int atomctrl_read_efuse(void *device, uint16_t start_index,
+extern int atomctrl_read_efuse(struct pp_hwmgr *hwmgr, uint16_t start_index,
 		uint16_t end_index, uint32_t mask, uint32_t *efuse);
 extern int atomctrl_calculate_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
 		uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage, uint16_t dpm_level, bool debug);
@@ -320,5 +330,8 @@ extern int atomctrl_get_leakage_vddc_base_on_leakage(struct pp_hwmgr *hwmgr,
 					uint16_t virtual_voltage_id,
 					uint16_t efuse_voltage_id);
 extern int atomctrl_get_leakage_id_from_efuse(struct pp_hwmgr *hwmgr, uint16_t *virtual_voltage_id);
+
+extern void atomctrl_get_voltage_range(struct pp_hwmgr *hwmgr, uint32_t *max_vddc,
+							uint32_t *min_vddc);
 #endif
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
index ad42caac033e..c97b0e5ba43b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
@@ -23,9 +23,9 @@
 
 #include "ppatomfwctrl.h"
 #include "atomfirmware.h"
+#include "atom.h"
 #include "pp_debug.h"
 
-
 static const union atom_voltage_object_v4 *pp_atomfwctrl_lookup_voltage_type_v4(
 		const struct atom_voltage_objects_info_v4_1 *voltage_object_info_table,
 		uint8_t voltage_type, uint8_t voltage_mode)
@@ -38,35 +38,34 @@ static const union atom_voltage_object_v4 *pp_atomfwctrl_lookup_voltage_type_v4(
 
 	while (offset < size) {
 		const union atom_voltage_object_v4 *voltage_object =
-				(const union atom_voltage_object_v4 *)(start + offset);
+			(const union atom_voltage_object_v4 *)(start + offset);
 
-        if (voltage_type == voltage_object->gpio_voltage_obj.header.voltage_type &&
-            voltage_mode == voltage_object->gpio_voltage_obj.header.voltage_mode)
-            return voltage_object;
+		if (voltage_type == voltage_object->gpio_voltage_obj.header.voltage_type &&
+		    voltage_mode == voltage_object->gpio_voltage_obj.header.voltage_mode)
+			return voltage_object;
 
-        offset += le16_to_cpu(voltage_object->gpio_voltage_obj.header.object_size);
+		offset += le16_to_cpu(voltage_object->gpio_voltage_obj.header.object_size);
 
-    }
+	}
 
-    return NULL;
+	return NULL;
 }
 
 static struct atom_voltage_objects_info_v4_1 *pp_atomfwctrl_get_voltage_info_table(
 		struct pp_hwmgr *hwmgr)
 {
-    const void *table_address;
-    uint16_t idx;
+	const void *table_address;
+	uint16_t idx;
 
-    idx = GetIndexIntoMasterDataTable(voltageobject_info);
-    table_address =	cgs_atom_get_data_table(hwmgr->device,
-    		idx, NULL, NULL, NULL);
+	idx = GetIndexIntoMasterDataTable(voltageobject_info);
+	table_address = smu_atom_get_data_table(hwmgr->adev,
+						idx, NULL, NULL, NULL);
 
-    PP_ASSERT_WITH_CODE( 
-        table_address,
-        "Error retrieving BIOS Table Address!",
-        return NULL);
+	PP_ASSERT_WITH_CODE(table_address,
+			"Error retrieving BIOS Table Address!",
+			return NULL);
 
-    return (struct atom_voltage_objects_info_v4_1 *)table_address;
+	return (struct atom_voltage_objects_info_v4_1 *)table_address;
 }
 
 /**
@@ -167,7 +166,7 @@ static struct atom_gpio_pin_lut_v2_1 *pp_atomfwctrl_get_gpio_lookup_table(
 	uint16_t idx;
 
 	idx = GetIndexIntoMasterDataTable(gpio_pin_lut);
-	table_address =	cgs_atom_get_data_table(hwmgr->device,
+	table_address =	smu_atom_get_data_table(hwmgr->adev,
 			idx, NULL, NULL, NULL);
 	PP_ASSERT_WITH_CODE(table_address,
 			"Error retrieving BIOS Table Address!",
@@ -248,28 +247,30 @@ int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr,
 		uint32_t clock_type, uint32_t clock_value,
 		struct pp_atomfwctrl_clock_dividers_soc15 *dividers)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct compute_gpu_clock_input_parameter_v1_8 pll_parameters;
 	struct compute_gpu_clock_output_parameter_v1_8 *pll_output;
-	int result;
 	uint32_t idx;
 
 	pll_parameters.gpuclock_10khz = (uint32_t)clock_value;
 	pll_parameters.gpu_clock_type = clock_type;
 
 	idx = GetIndexIntoMasterCmdTable(computegpuclockparam);
-	result = cgs_atom_exec_cmd_table(hwmgr->device, idx, &pll_parameters);
-
-	if (!result) {
-		pll_output = (struct compute_gpu_clock_output_parameter_v1_8 *)
-				&pll_parameters;
-		dividers->ulClock = le32_to_cpu(pll_output->gpuclock_10khz);
-		dividers->ulDid = le32_to_cpu(pll_output->dfs_did);
-		dividers->ulPll_fb_mult = le32_to_cpu(pll_output->pll_fb_mult);
-		dividers->ulPll_ss_fbsmult = le32_to_cpu(pll_output->pll_ss_fbsmult);
-		dividers->usPll_ss_slew_frac = le16_to_cpu(pll_output->pll_ss_slew_frac);
-		dividers->ucPll_ss_enable = pll_output->pll_ss_enable;
-	}
-	return result;
+
+	if (amdgpu_atom_execute_table(
+		adev->mode_info.atom_context, idx, (uint32_t *)&pll_parameters))
+		return -EINVAL;
+
+	pll_output = (struct compute_gpu_clock_output_parameter_v1_8 *)
+			&pll_parameters;
+	dividers->ulClock = le32_to_cpu(pll_output->gpuclock_10khz);
+	dividers->ulDid = le32_to_cpu(pll_output->dfs_did);
+	dividers->ulPll_fb_mult = le32_to_cpu(pll_output->pll_fb_mult);
+	dividers->ulPll_ss_fbsmult = le32_to_cpu(pll_output->pll_ss_fbsmult);
+	dividers->usPll_ss_slew_frac = le16_to_cpu(pll_output->pll_ss_slew_frac);
+	dividers->ucPll_ss_enable = pll_output->pll_ss_enable;
+
+	return 0;
 }
 
 int pp_atomfwctrl_get_avfs_information(struct pp_hwmgr *hwmgr,
@@ -283,7 +284,7 @@ int pp_atomfwctrl_get_avfs_information(struct pp_hwmgr *hwmgr,
 
 	idx = GetIndexIntoMasterDataTable(asic_profiling_info);
 	profile = (struct atom_asic_profiling_info_v4_1 *)
-			cgs_atom_get_data_table(hwmgr->device,
+			smu_atom_get_data_table(hwmgr->adev,
 					idx, NULL, NULL, NULL);
 
 	if (!profile)
@@ -467,7 +468,7 @@ int pp_atomfwctrl_get_gpio_information(struct pp_hwmgr *hwmgr,
 
 	idx = GetIndexIntoMasterDataTable(smu_info);
 	info = (struct atom_smu_info_v3_1 *)
-		cgs_atom_get_data_table(hwmgr->device,
+		smu_atom_get_data_table(hwmgr->adev,
 				idx, NULL, NULL, NULL);
 
 	if (!info) {
@@ -487,8 +488,9 @@ int pp_atomfwctrl_get_gpio_information(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-int pp_atomfwctrl__get_clk_information_by_clkid(struct pp_hwmgr *hwmgr, BIOS_CLKID id, uint32_t *frequency)
+int pp_atomfwctrl_get_clk_information_by_clkid(struct pp_hwmgr *hwmgr, BIOS_CLKID id, uint32_t *frequency)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct atom_get_smu_clock_info_parameters_v3_1   parameters;
 	struct atom_get_smu_clock_info_output_parameters_v3_1 *output;
 	uint32_t ix;
@@ -497,13 +499,13 @@ int pp_atomfwctrl__get_clk_information_by_clkid(struct pp_hwmgr *hwmgr, BIOS_CLK
 	parameters.command = GET_SMU_CLOCK_INFO_V3_1_GET_CLOCK_FREQ;
 
 	ix = GetIndexIntoMasterCmdTable(getsmuclockinfo);
-	if (!cgs_atom_exec_cmd_table(hwmgr->device, ix, &parameters)) {
-		output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)&parameters;
-		*frequency = output->atom_smu_outputclkfreq.smu_clock_freq_hz / 10000;
-	} else {
-		pr_info("Error execute_table getsmuclockinfo!");
-		return -1;
-	}
+
+	if (amdgpu_atom_execute_table(
+		adev->mode_info.atom_context, ix, (uint32_t *)&parameters))
+		return -EINVAL;
+
+	output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)&parameters;
+	*frequency = output->atom_smu_outputclkfreq.smu_clock_freq_hz / 10000;
 
 	return 0;
 }
@@ -513,11 +515,10 @@ int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 {
 	struct atom_firmware_info_v3_1 *info = NULL;
 	uint16_t ix;
-	uint32_t frequency = 0;
 
 	ix = GetIndexIntoMasterDataTable(firmwareinfo);
 	info = (struct atom_firmware_info_v3_1 *)
-		cgs_atom_get_data_table(hwmgr->device,
+		smu_atom_get_data_table(hwmgr->adev,
 				ix, NULL, NULL, NULL);
 
 	if (!info) {
@@ -536,12 +537,6 @@ int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 	boot_values->ulSocClk   = 0;
 	boot_values->ulDCEFClk   = 0;
 
-	if (!pp_atomfwctrl__get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_SOCCLK_ID, &frequency))
-		boot_values->ulSocClk   = frequency;
-
-	if (!pp_atomfwctrl__get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCEFCLK_ID, &frequency))
-		boot_values->ulDCEFClk   = frequency;
-
 	return 0;
 }
 
@@ -553,7 +548,7 @@ int pp_atomfwctrl_get_smc_dpm_information(struct pp_hwmgr *hwmgr,
 
 	ix = GetIndexIntoMasterDataTable(smc_dpm_info);
 	info = (struct atom_smc_dpm_info_v4_1 *)
-		cgs_atom_get_data_table(hwmgr->device,
+		smu_atom_get_data_table(hwmgr->adev,
 				ix, NULL, NULL, NULL);
 	if (!info) {
 		pr_info("Error retrieving BIOS Table Address!");
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
index 8df1e84f27c9..fe10aa4db5e6 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
@@ -230,6 +230,8 @@ int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 			struct pp_atomfwctrl_bios_boot_up_values *boot_values);
 int pp_atomfwctrl_get_smc_dpm_information(struct pp_hwmgr *hwmgr,
 			struct pp_atomfwctrl_smc_dpm_parameters *param);
+int pp_atomfwctrl_get_clk_information_by_clkid(struct pp_hwmgr *hwmgr,
+					BIOS_CLKID id, uint32_t *frequency);
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
index c9eecce5683f..f0d48b183d22 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
@@ -141,7 +141,7 @@ static const void *get_powerplay_table(struct pp_hwmgr *hwmgr)
 
 	if (!table_address) {
 		table_address = (ATOM_Tonga_POWERPLAYTABLE *)
-				cgs_atom_get_data_table(hwmgr->device,
+				smu_atom_get_data_table(hwmgr->adev,
 						index, &size, &frev, &crev);
 		hwmgr->soft_pp_table = table_address;	/*Cache the result in RAM.*/
 		hwmgr->soft_pp_table_size = size;
@@ -728,6 +728,32 @@ static int get_mm_clock_voltage_table(
 	return 0;
 }
 
+static int get_gpio_table(struct pp_hwmgr *hwmgr,
+		struct phm_ppt_v1_gpio_table **pp_tonga_gpio_table,
+		const ATOM_Tonga_GPIO_Table *atom_gpio_table)
+{
+	uint32_t table_size;
+	struct phm_ppt_v1_gpio_table *pp_gpio_table;
+	struct phm_ppt_v1_information *pp_table_information =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+
+	table_size = sizeof(struct phm_ppt_v1_gpio_table);
+	pp_gpio_table = kzalloc(table_size, GFP_KERNEL);
+	if (!pp_gpio_table)
+		return -ENOMEM;
+
+	if (pp_table_information->vdd_dep_on_sclk->count <
+			atom_gpio_table->ucVRHotTriggeredSclkDpmIndex)
+		PP_ASSERT_WITH_CODE(false,
+				"SCLK DPM index for VRHot cannot exceed the total sclk level count!",);
+	else
+		pp_gpio_table->vrhot_triggered_sclk_dpm_index =
+				atom_gpio_table->ucVRHotTriggeredSclkDpmIndex;
+
+	*pp_tonga_gpio_table = pp_gpio_table;
+
+	return 0;
+}
 /**
  * Private Function used during initialization.
  * Initialize clock voltage dependency
@@ -761,11 +787,15 @@ static int init_clock_voltage_dependency(
 	const PPTable_Generic_SubTable_Header *pcie_table =
 		(const PPTable_Generic_SubTable_Header *)(((unsigned long) powerplay_table) +
 		le16_to_cpu(powerplay_table->usPCIETableOffset));
+	const ATOM_Tonga_GPIO_Table *gpio_table =
+		(const ATOM_Tonga_GPIO_Table *)(((unsigned long) powerplay_table) +
+		le16_to_cpu(powerplay_table->usGPIOTableOffset));
 
 	pp_table_information->vdd_dep_on_sclk = NULL;
 	pp_table_information->vdd_dep_on_mclk = NULL;
 	pp_table_information->mm_dep_table = NULL;
 	pp_table_information->pcie_table = NULL;
+	pp_table_information->gpio_table = NULL;
 
 	if (powerplay_table->usMMDependencyTableOffset != 0)
 		result = get_mm_clock_voltage_table(hwmgr,
@@ -810,6 +840,10 @@ static int init_clock_voltage_dependency(
 		result = get_valid_clk(hwmgr, &pp_table_information->valid_sclk_values,
 		pp_table_information->vdd_dep_on_sclk);
 
+	if (!result && gpio_table)
+		result = get_gpio_table(hwmgr, &pp_table_information->gpio_table,
+				gpio_table);
+
 	return result;
 }
 
@@ -1116,6 +1150,9 @@ static int pp_tables_v1_0_uninitialize(struct pp_hwmgr *hwmgr)
 	kfree(pp_table_information->pcie_table);
 	pp_table_information->pcie_table = NULL;
 
+	kfree(pp_table_information->gpio_table);
+	pp_table_information->gpio_table = NULL;
+
 	kfree(hwmgr->pptable);
 	hwmgr->pptable = NULL;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
index 36ca7c419c90..ce64dfabd34b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
@@ -837,7 +837,7 @@ static const ATOM_PPLIB_POWERPLAYTABLE *get_powerplay_table(
 			hwmgr->soft_pp_table = &soft_dummy_pp_table[0];
 			hwmgr->soft_pp_table_size = sizeof(soft_dummy_pp_table);
 		} else {
-			table_addr = cgs_atom_get_data_table(hwmgr->device,
+			table_addr = smu_atom_get_data_table(hwmgr->adev,
 					GetIndexIntoMasterTable(DATA, PowerPlayInfo),
 					&size, &frev, &crev);
 			hwmgr->soft_pp_table = table_addr;
@@ -1058,7 +1058,7 @@ static int init_overdrive_limits(struct pp_hwmgr *hwmgr,
 		return 0;
 
 	/* We assume here that fw_info is unchanged if this call fails.*/
-	fw_info = cgs_atom_get_data_table(hwmgr->device,
+	fw_info = smu_atom_get_data_table(hwmgr->adev,
 			 GetIndexIntoMasterTable(DATA, FirmwareInfo),
 			 &size, &frev, &crev);
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 10253b89b3d8..85f84f4d8be5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -34,7 +34,7 @@
 #include "rv_ppsmc.h"
 #include "smu10_hwmgr.h"
 #include "power_state.h"
-#include "pp_soc15.h"
+#include "soc15_common.h"
 
 #define SMU10_MAX_DEEPSLEEP_DIVIDER_ID     5
 #define SMU10_MINIMUM_ENGINE_CLOCK         800   /* 8Mhz, the low boundary of engine clock allowed on this chip */
@@ -42,6 +42,13 @@
 #define SMU10_DISPCLK_BYPASS_THRESHOLD     10000 /* 100Mhz */
 #define SMC_RAM_END                     0x40000
 
+#define mmPWR_MISC_CNTL_STATUS					0x0183
+#define mmPWR_MISC_CNTL_STATUS_BASE_IDX				0
+#define PWR_MISC_CNTL_STATUS__PWR_GFX_RLC_CGPG_EN__SHIFT	0x0
+#define PWR_MISC_CNTL_STATUS__PWR_GFXOFF_STATUS__SHIFT		0x1
+#define PWR_MISC_CNTL_STATUS__PWR_GFX_RLC_CGPG_EN_MASK		0x00000001L
+#define PWR_MISC_CNTL_STATUS__PWR_GFXOFF_STATUS_MASK		0x00000006L
+
 static const unsigned long SMU10_Magic = (unsigned long) PHM_Rv_Magic;
 
 
@@ -74,11 +81,15 @@ static int smu10_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 	smu10_data->thermal_auto_throttling_treshold = 0;
 	smu10_data->is_nb_dpm_enabled = 1;
 	smu10_data->dpm_flags = 1;
-	smu10_data->gfx_off_controled_by_driver = false;
 	smu10_data->need_min_deep_sleep_dcefclk = true;
 	smu10_data->num_active_display = 0;
 	smu10_data->deep_sleep_dcefclk = 0;
 
+	if (hwmgr->feature_mask & PP_GFXOFF_MASK)
+		smu10_data->gfx_off_controled_by_driver = true;
+	else
+		smu10_data->gfx_off_controled_by_driver = false;
+
 	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
 					PHM_PlatformCaps_SclkDeepSleep);
 
@@ -161,7 +172,7 @@ static int smu10_set_clock_limit(struct pp_hwmgr *hwmgr, const void *input)
 	struct PP_Clocks clocks = {0};
 	struct pp_display_clock_request clock_req;
 
-	clocks.dcefClock = hwmgr->display_config.min_dcef_set_clk;
+	clocks.dcefClock = hwmgr->display_config->min_dcef_set_clk;
 	clock_req.clock_type = amd_pp_dcf_clock;
 	clock_req.clock_freq_in_khz = clocks.dcefClock * 10;
 
@@ -206,12 +217,18 @@ static int smu10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input
 static int smu10_init_power_gate_state(struct pp_hwmgr *hwmgr)
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	smu10_data->vcn_power_gated = true;
 	smu10_data->isp_tileA_power_gated = true;
 	smu10_data->isp_tileB_power_gated = true;
 
-	return 0;
+	if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)
+		return smum_send_msg_to_smc_with_parameter(hwmgr,
+							   PPSMC_MSG_SetGfxCGPG,
+							   true);
+	else
+		return 0;
 }
 
 
@@ -237,13 +254,31 @@ static int smu10_power_off_asic(struct pp_hwmgr *hwmgr)
 	return smu10_reset_cc6_data(hwmgr);
 }
 
+static bool smu10_is_gfx_on(struct pp_hwmgr *hwmgr)
+{
+	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	reg = RREG32_SOC15(PWR, 0, mmPWR_MISC_CNTL_STATUS);
+	if ((reg & PWR_MISC_CNTL_STATUS__PWR_GFXOFF_STATUS_MASK) ==
+	    (0x2 << PWR_MISC_CNTL_STATUS__PWR_GFXOFF_STATUS__SHIFT))
+		return true;
+
+	return false;
+}
+
 static int smu10_disable_gfx_off(struct pp_hwmgr *hwmgr)
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
 
-	if (smu10_data->gfx_off_controled_by_driver)
+	if (smu10_data->gfx_off_controled_by_driver) {
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DisableGfxOff);
 
+		/* confirm gfx is back to "on" state */
+		while (!smu10_is_gfx_on(hwmgr))
+			msleep(1);
+	}
+
 	return 0;
 }
 
@@ -267,6 +302,14 @@ static int smu10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 	return smu10_enable_gfx_off(hwmgr);
 }
 
+static int smu10_gfx_off_control(struct pp_hwmgr *hwmgr, bool enable)
+{
+	if (enable)
+		return smu10_enable_gfx_off(hwmgr);
+	else
+		return smu10_disable_gfx_off(hwmgr);
+}
+
 static int smu10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				struct pp_power_state  *prequest_ps,
 			const struct pp_power_state *pcurrent_ps)
@@ -340,7 +383,7 @@ static int smu10_get_clock_voltage_dependency_table(struct pp_hwmgr *hwmgr,
 
 static int smu10_populate_clock_table(struct pp_hwmgr *hwmgr)
 {
-	int result;
+	uint32_t result;
 
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
 	DpmClocks_t  *table = &(smu10_data->clock_table);
@@ -386,11 +429,11 @@ static int smu10_populate_clock_table(struct pp_hwmgr *hwmgr)
 
 	smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency);
 	result = smum_get_argument(hwmgr);
-	smu10_data->gfx_min_freq_limit = result * 100;
+	smu10_data->gfx_min_freq_limit = result / 10 * 1000;
 
 	smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency);
 	result = smum_get_argument(hwmgr);
-	smu10_data->gfx_max_freq_limit = result * 100;
+	smu10_data->gfx_max_freq_limit = result / 10 * 1000;
 
 	return 0;
 }
@@ -436,8 +479,8 @@ static int smu10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 
 	hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50;
 
-	hwmgr->pstate_sclk = SMU10_UMD_PSTATE_GFXCLK;
-	hwmgr->pstate_mclk = SMU10_UMD_PSTATE_FCLK;
+	hwmgr->pstate_sclk = SMU10_UMD_PSTATE_GFXCLK * 100;
+	hwmgr->pstate_mclk = SMU10_UMD_PSTATE_FCLK * 100;
 
 	return result;
 }
@@ -472,6 +515,8 @@ static int smu10_hwmgr_backend_fini(struct pp_hwmgr *hwmgr)
 static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 				enum amd_dpm_forced_level level)
 {
+	struct smu10_hwmgr *data = hwmgr->backend;
+
 	if (hwmgr->smu_version < 0x1E3700) {
 		pr_info("smu firmware version too old, can not set dpm level\n");
 		return 0;
@@ -482,7 +527,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
-						SMU10_UMD_PSTATE_PEAK_GFXCLK);
+						data->gfx_max_freq_limit/100);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinFclkByFreq,
 						SMU10_UMD_PSTATE_PEAK_FCLK);
@@ -495,7 +540,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxGfxClk,
-						SMU10_UMD_PSTATE_PEAK_GFXCLK);
+						data->gfx_max_freq_limit/100);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxFclkByFreq,
 						SMU10_UMD_PSTATE_PEAK_FCLK);
@@ -509,10 +554,10 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
-						SMU10_UMD_PSTATE_MIN_GFXCLK);
+						data->gfx_min_freq_limit/100);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxGfxClk,
-						SMU10_UMD_PSTATE_MIN_GFXCLK);
+						data->gfx_min_freq_limit/100);
 		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
 		smum_send_msg_to_smc_with_parameter(hwmgr,
@@ -552,10 +597,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	case AMD_DPM_FORCED_LEVEL_AUTO:
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
-						SMU10_UMD_PSTATE_MIN_GFXCLK);
+						data->gfx_min_freq_limit/100);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinFclkByFreq,
+						hwmgr->display_config->num_display > 3 ?
+						SMU10_UMD_PSTATE_PEAK_FCLK :
 						SMU10_UMD_PSTATE_MIN_FCLK);
+
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinSocclkByFreq,
 						SMU10_UMD_PSTATE_MIN_SOCCLK);
@@ -565,7 +613,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxGfxClk,
-						SMU10_UMD_PSTATE_PEAK_GFXCLK);
+						data->gfx_max_freq_limit/100);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxFclkByFreq,
 						SMU10_UMD_PSTATE_PEAK_FCLK);
@@ -579,10 +627,10 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	case AMD_DPM_FORCED_LEVEL_LOW:
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
-						SMU10_UMD_PSTATE_MIN_GFXCLK);
+						data->gfx_min_freq_limit/100);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxGfxClk,
-						SMU10_UMD_PSTATE_MIN_GFXCLK);
+						data->gfx_min_freq_limit/100);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinFclkByFreq,
 						SMU10_UMD_PSTATE_MIN_FCLK);
@@ -699,6 +747,16 @@ static int smu10_set_cpu_power_state(struct pp_hwmgr *hwmgr)
 static int smu10_store_cc6_data(struct pp_hwmgr *hwmgr, uint32_t separation_time,
 			bool cc6_disable, bool pstate_disable, bool pstate_switch_disable)
 {
+	struct smu10_hwmgr *data = (struct smu10_hwmgr *)(hwmgr->backend);
+
+	if (separation_time != data->separation_time ||
+			cc6_disable != data->cc6_disable ||
+			pstate_disable != data->pstate_disable) {
+		data->separation_time = separation_time;
+		data->cc6_disable = cc6_disable;
+		data->pstate_disable = pstate_disable;
+		data->cc6_setting_changed = true;
+	}
 	return 0;
 }
 
@@ -711,6 +769,51 @@ static int smu10_get_dal_power_level(struct pp_hwmgr *hwmgr,
 static int smu10_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask)
 {
+	struct smu10_hwmgr *data = hwmgr->backend;
+	struct smu10_voltage_dependency_table *mclk_table =
+					data->clock_vol_info.vdd_dep_on_fclk;
+	uint32_t low, high;
+
+	low = mask ? (ffs(mask) - 1) : 0;
+	high = mask ? (fls(mask) - 1) : 0;
+
+	switch (type) {
+	case PP_SCLK:
+		if (low > 2 || high > 2) {
+			pr_info("Currently sclk only support 3 levels on RV\n");
+			return -EINVAL;
+		}
+
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+						PPSMC_MSG_SetHardMinGfxClk,
+						low == 2 ? data->gfx_max_freq_limit/100 :
+						low == 1 ? SMU10_UMD_PSTATE_GFXCLK :
+						data->gfx_min_freq_limit/100);
+
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+						PPSMC_MSG_SetSoftMaxGfxClk,
+						high == 0 ? data->gfx_min_freq_limit/100 :
+						high == 1 ? SMU10_UMD_PSTATE_GFXCLK :
+						data->gfx_max_freq_limit/100);
+		break;
+
+	case PP_MCLK:
+		if (low > mclk_table->count - 1 || high > mclk_table->count - 1)
+			return -EINVAL;
+
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+						PPSMC_MSG_SetHardMinFclkByFreq,
+						mclk_table->entries[low].clk/100);
+
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+						PPSMC_MSG_SetSoftMaxFclkByFreq,
+						mclk_table->entries[high].clk/100);
+		break;
+
+	case PP_PCIE:
+	default:
+		break;
+	}
 	return 0;
 }
 
@@ -720,21 +823,30 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct smu10_hwmgr *data = (struct smu10_hwmgr *)(hwmgr->backend);
 	struct smu10_voltage_dependency_table *mclk_table =
 			data->clock_vol_info.vdd_dep_on_fclk;
-	int i, now, size = 0;
+	uint32_t i, now, size = 0;
 
 	switch (type) {
 	case PP_SCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency);
 		now = smum_get_argument(hwmgr);
 
+	/* driver only know min/max gfx_clk, Add level 1 for all other gfx clks */
+		if (now == data->gfx_max_freq_limit/100)
+			i = 2;
+		else if (now == data->gfx_min_freq_limit/100)
+			i = 0;
+		else
+			i = 1;
+
 		size += sprintf(buf + size, "0: %uMhz %s\n",
-				data->gfx_min_freq_limit / 100,
-				((data->gfx_min_freq_limit / 100)
-				 == now) ? "*" : "");
+					data->gfx_min_freq_limit/100,
+					i == 0 ? "*" : "");
 		size += sprintf(buf + size, "1: %uMhz %s\n",
-				data->gfx_max_freq_limit / 100,
-				((data->gfx_max_freq_limit / 100)
-				 == now) ? "*" : "");
+					i == 1 ? now : SMU10_UMD_PSTATE_GFXCLK,
+					i == 1 ? "*" : "");
+		size += sprintf(buf + size, "2: %uMhz %s\n",
+					data->gfx_max_freq_limit/100,
+					i == 2 ? "*" : "");
 		break;
 	case PP_MCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency);
@@ -947,9 +1059,8 @@ static int smu10_get_max_high_clocks(struct pp_hwmgr *hwmgr, struct amd_pp_simpl
 
 static int smu10_thermal_get_temperature(struct pp_hwmgr *hwmgr)
 {
-	uint32_t reg_offset = soc15_get_register_offset(THM_HWID, 0,
-			mmTHM_TCON_CUR_TMP_BASE_IDX, mmTHM_TCON_CUR_TMP);
-	uint32_t reg_value = cgs_read_register(hwmgr->device, reg_offset);
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t reg_value = RREG32_SOC15(THM, 0, mmTHM_TCON_CUR_TMP);
 	int cur_temp =
 		(reg_value & THM_TCON_CUR_TMP__CUR_TEMP_MASK) >> THM_TCON_CUR_TMP__CUR_TEMP__SHIFT;
 
@@ -993,11 +1104,47 @@ static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 	return ret;
 }
 
+static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
+		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+{
+	struct smu10_hwmgr *data = hwmgr->backend;
+	Watermarks_t *table = &(data->water_marks_table);
+	int result = 0;
+
+	smu_set_watermarks_for_clocks_ranges(table,wm_with_clock_ranges);
+	smum_smc_table_manager(hwmgr, (uint8_t *)table, (uint16_t)SMU10_WMTABLE, false);
+	data->water_marks_exist = true;
+	return result;
+}
+
+static int smu10_smus_notify_pwe(struct pp_hwmgr *hwmgr)
+{
+
+	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_SetRccPfcPmeRestoreRegister);
+}
+
 static int smu10_set_mmhub_powergating_by_smu(struct pp_hwmgr *hwmgr)
 {
 	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PowerGateMmHub);
 }
 
+static void smu10_powergate_vcn(struct pp_hwmgr *hwmgr, bool bgate)
+{
+	if (bgate) {
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
+						AMD_IP_BLOCK_TYPE_VCN,
+						AMD_PG_STATE_GATE);
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_PowerDownVcn, 0);
+	} else {
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+						PPSMC_MSG_PowerUpVcn, 0);
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
+						AMD_IP_BLOCK_TYPE_VCN,
+						AMD_PG_STATE_UNGATE);
+	}
+}
+
 static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.backend_init = smu10_hwmgr_backend_init,
 	.backend_fini = smu10_hwmgr_backend_fini,
@@ -1006,7 +1153,7 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.force_dpm_level = smu10_dpm_force_dpm_level,
 	.get_power_state_size = smu10_get_power_state_size,
 	.powerdown_uvd = NULL,
-	.powergate_uvd = NULL,
+	.powergate_uvd = smu10_powergate_vcn,
 	.powergate_vce = NULL,
 	.get_mclk = smu10_dpm_get_mclk,
 	.get_sclk = smu10_dpm_get_sclk,
@@ -1022,6 +1169,7 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.get_current_shallow_sleep_clocks = smu10_get_current_shallow_sleep_clocks,
 	.get_clock_by_type_with_latency = smu10_get_clock_by_type_with_latency,
 	.get_clock_by_type_with_voltage = smu10_get_clock_by_type_with_voltage,
+	.set_watermarks_for_clocks_ranges = smu10_set_watermarks_for_clocks_ranges,
 	.get_max_high_clocks = smu10_get_max_high_clocks,
 	.read_sensor = smu10_read_sensor,
 	.set_active_display_count = smu10_set_active_display_count,
@@ -1032,6 +1180,8 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.power_state_set = smu10_set_power_state_tasks,
 	.dynamic_state_management_disable = smu10_disable_dpm_tasks,
 	.set_mmhub_powergating_by_smu = smu10_set_mmhub_powergating_by_smu,
+	.smus_notify_pwe = smu10_smus_notify_pwe,
+	.gfx_off_control = smu10_gfx_off_control,
 };
 
 int smu10_init_function_pointers(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.h
index 175c3a592b6c..1fb296a996f3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.h
@@ -290,6 +290,7 @@ struct smu10_hwmgr {
 	bool                           vcn_dpg_mode;
 
 	bool                           gfx_off_controled_by_driver;
+	bool                           water_marks_exist;
 	Watermarks_t                      water_marks_table;
 	struct smu10_clock_voltage_information   clock_vol_info;
 	DpmClocks_t                       clock_table;
@@ -310,11 +311,9 @@ int smu10_init_function_pointers(struct pp_hwmgr *hwmgr);
 #define SMU10_UMD_PSTATE_FCLK                   933
 #define SMU10_UMD_PSTATE_VCE                    0x03C00320
 
-#define SMU10_UMD_PSTATE_PEAK_GFXCLK            1100
 #define SMU10_UMD_PSTATE_PEAK_SOCCLK            757
 #define SMU10_UMD_PSTATE_PEAK_FCLK              1200
 
-#define SMU10_UMD_PSTATE_MIN_GFXCLK             200
 #define SMU10_UMD_PSTATE_MIN_FCLK               400
 #define SMU10_UMD_PSTATE_MIN_SOCCLK             200
 #define SMU10_UMD_PSTATE_MIN_VCE                0x0190012C
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
index f4cbaee4e2ca..6d72a5600917 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
@@ -147,20 +147,20 @@ void smu7_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate)
 	data->uvd_power_gated = bgate;
 
 	if (bgate) {
-		cgs_set_powergating_state(hwmgr->device,
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_UVD,
 						AMD_PG_STATE_GATE);
-		cgs_set_clockgating_state(hwmgr->device,
+		amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 				AMD_IP_BLOCK_TYPE_UVD,
 				AMD_CG_STATE_GATE);
 		smu7_update_uvd_dpm(hwmgr, true);
 		smu7_powerdown_uvd(hwmgr);
 	} else {
 		smu7_powerup_uvd(hwmgr);
-		cgs_set_clockgating_state(hwmgr->device,
+		amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 				AMD_IP_BLOCK_TYPE_UVD,
 				AMD_CG_STATE_UNGATE);
-		cgs_set_powergating_state(hwmgr->device,
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_UVD,
 						AMD_PG_STATE_UNGATE);
 		smu7_update_uvd_dpm(hwmgr, false);
@@ -175,20 +175,20 @@ void smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 	data->vce_power_gated = bgate;
 
 	if (bgate) {
-		cgs_set_powergating_state(hwmgr->device,
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_VCE,
 						AMD_PG_STATE_GATE);
-		cgs_set_clockgating_state(hwmgr->device,
+		amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 				AMD_IP_BLOCK_TYPE_VCE,
 				AMD_CG_STATE_GATE);
 		smu7_update_vce_dpm(hwmgr, true);
 		smu7_powerdown_vce(hwmgr);
 	} else {
 		smu7_powerup_vce(hwmgr);
-		cgs_set_clockgating_state(hwmgr->device,
+		amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 				AMD_IP_BLOCK_TYPE_VCE,
 				AMD_CG_STATE_UNGATE);
-		cgs_set_powergating_state(hwmgr->device,
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_VCE,
 						AMD_PG_STATE_UNGATE);
 		smu7_update_vce_dpm(hwmgr, false);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index add90675fd2a..45e9b8cb169d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -61,10 +61,6 @@
 #define SMC_CG_IND_START            0xc0030000
 #define SMC_CG_IND_END              0xc0040000
 
-#define VOLTAGE_SCALE               4
-#define VOLTAGE_VID_OFFSET_SCALE1   625
-#define VOLTAGE_VID_OFFSET_SCALE2   100
-
 #define MEM_FREQ_LOW_LATENCY        25000
 #define MEM_FREQ_HIGH_LATENCY       80000
 
@@ -79,14 +75,23 @@
 #define PCIE_BUS_CLK                10000
 #define TCLK                        (PCIE_BUS_CLK / 10)
 
-static const struct profile_mode_setting smu7_profiling[5] =
+static const struct profile_mode_setting smu7_profiling[6] =
 					{{1, 0, 100, 30, 1, 0, 100, 10},
 					 {1, 10, 0, 30, 0, 0, 0, 0},
 					 {0, 0, 0, 0, 1, 10, 16, 31},
 					 {1, 0, 11, 50, 1, 0, 100, 10},
 					 {1, 0, 5, 30, 0, 0, 0, 0},
+					 {0, 0, 0, 0, 0, 0, 0, 0},
 					};
 
+#define PPSMC_MSG_SetVBITimeout_VEGAM    ((uint16_t) 0x310)
+
+#define ixPWR_SVI2_PLANE1_LOAD                     0xC0200280
+#define PWR_SVI2_PLANE1_LOAD__PSI1_MASK                    0x00000020L
+#define PWR_SVI2_PLANE1_LOAD__PSI0_EN_MASK                 0x00000040L
+#define PWR_SVI2_PLANE1_LOAD__PSI1__SHIFT                  0x00000005
+#define PWR_SVI2_PLANE1_LOAD__PSI0_EN__SHIFT               0x00000006
+
 /** Values for the CG_THERMAL_CTRL::DPM_EVENT_SRC field. */
 enum DPM_EVENT_SRC {
 	DPM_EVENT_SRC_ANALOG = 0,
@@ -168,6 +173,13 @@ static int smu7_get_current_pcie_lane_number(struct pp_hwmgr *hwmgr)
 */
 static int smu7_enable_smc_voltage_controller(struct pp_hwmgr *hwmgr)
 {
+	if (hwmgr->chip_id == CHIP_VEGAM) {
+		PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device,
+				CGS_IND_REG__SMC, PWR_SVI2_PLANE1_LOAD, PSI1, 0);
+		PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device,
+				CGS_IND_REG__SMC, PWR_SVI2_PLANE1_LOAD, PSI0_EN, 0);
+	}
+
 	if (hwmgr->feature_mask & PP_SMC_VOLTAGE_CONTROL_MASK)
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_Voltage_Cntl_Enable);
 
@@ -797,32 +809,6 @@ static int smu7_setup_dpm_tables_v1(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int smu7_get_voltage_dependency_table(
-			const struct phm_ppt_v1_clock_voltage_dependency_table *allowed_dep_table,
-			struct phm_ppt_v1_clock_voltage_dependency_table *dep_table)
-{
-	uint8_t i = 0;
-	PP_ASSERT_WITH_CODE((0 != allowed_dep_table->count),
-				"Voltage Lookup Table empty",
-				return -EINVAL);
-
-	dep_table->count = allowed_dep_table->count;
-	for (i=0; i<dep_table->count; i++) {
-		dep_table->entries[i].clk = allowed_dep_table->entries[i].clk;
-		dep_table->entries[i].vddInd = allowed_dep_table->entries[i].vddInd;
-		dep_table->entries[i].vdd_offset = allowed_dep_table->entries[i].vdd_offset;
-		dep_table->entries[i].vddc = allowed_dep_table->entries[i].vddc;
-		dep_table->entries[i].vddgfx = allowed_dep_table->entries[i].vddgfx;
-		dep_table->entries[i].vddci = allowed_dep_table->entries[i].vddci;
-		dep_table->entries[i].mvdd = allowed_dep_table->entries[i].mvdd;
-		dep_table->entries[i].phases = allowed_dep_table->entries[i].phases;
-		dep_table->entries[i].cks_enable = allowed_dep_table->entries[i].cks_enable;
-		dep_table->entries[i].cks_voffset = allowed_dep_table->entries[i].cks_voffset;
-	}
-
-	return 0;
-}
-
 static int smu7_odn_initial_default_setting(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -850,7 +836,7 @@ static int smu7_odn_initial_default_setting(struct pp_hwmgr *hwmgr)
 		entries[i].vddc = dep_sclk_table->entries[i].vddc;
 	}
 
-	smu7_get_voltage_dependency_table(dep_sclk_table,
+	smu_get_voltage_dependency_table_ppt_v1(dep_sclk_table,
 		(struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk));
 
 	odn_table->odn_memory_clock_dpm_levels.num_of_pl =
@@ -862,12 +848,40 @@ static int smu7_odn_initial_default_setting(struct pp_hwmgr *hwmgr)
 		entries[i].vddc = dep_mclk_table->entries[i].vddc;
 	}
 
-	smu7_get_voltage_dependency_table(dep_mclk_table,
+	smu_get_voltage_dependency_table_ppt_v1(dep_mclk_table,
 		(struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_mclk));
 
 	return 0;
 }
 
+static void smu7_setup_voltage_range_from_vbios(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_sclk_table;
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	uint32_t min_vddc = 0;
+	uint32_t max_vddc = 0;
+
+	if (!table_info)
+		return;
+
+	dep_sclk_table = table_info->vdd_dep_on_sclk;
+
+	atomctrl_get_voltage_range(hwmgr, &max_vddc, &min_vddc);
+
+	if (min_vddc == 0 || min_vddc > 2000
+		|| min_vddc > dep_sclk_table->entries[0].vddc)
+		min_vddc = dep_sclk_table->entries[0].vddc;
+
+	if (max_vddc == 0 || max_vddc > 2000
+		|| max_vddc < dep_sclk_table->entries[dep_sclk_table->count-1].vddc)
+		max_vddc = dep_sclk_table->entries[dep_sclk_table->count-1].vddc;
+
+	data->odn_dpm_table.min_vddc = min_vddc;
+	data->odn_dpm_table.max_vddc = max_vddc;
+}
+
 static int smu7_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -886,8 +900,10 @@ static int smu7_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			sizeof(struct smu7_dpm_table));
 
 	/* initialize ODN table */
-	if (hwmgr->od_enabled)
+	if (hwmgr->od_enabled) {
+		smu7_setup_voltage_range_from_vbios(hwmgr);
 		smu7_odn_initial_default_setting(hwmgr);
+	}
 
 	return 0;
 }
@@ -965,6 +981,22 @@ static int smu7_disable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int smu7_disable_sclk_vce_handshake(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	uint32_t soft_register_value = 0;
+	uint32_t handshake_disables_offset = data->soft_regs_start
+				+ smum_get_offsetof(hwmgr,
+					SMU_SoftRegisters, HandshakeDisables);
+
+	soft_register_value = cgs_read_ind_register(hwmgr->device,
+				CGS_IND_REG__SMC, handshake_disables_offset);
+	soft_register_value |= SMU7_VCE_SCLK_HANDSHAKE_DISABLE;
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			handshake_disables_offset, soft_register_value);
+	return 0;
+}
+
 static int smu7_disable_handshake_uvd(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -987,23 +1019,29 @@ static int smu7_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
 	/* enable SCLK dpm */
-	if (!data->sclk_dpm_key_disabled)
+	if (!data->sclk_dpm_key_disabled) {
+		if (hwmgr->chip_id == CHIP_VEGAM)
+			smu7_disable_sclk_vce_handshake(hwmgr);
+
 		PP_ASSERT_WITH_CODE(
 		(0 == smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DPM_Enable)),
 		"Failed to enable SCLK DPM during DPM Start Function!",
 		return -EINVAL);
+	}
 
 	/* enable MCLK dpm */
 	if (0 == data->mclk_dpm_key_disabled) {
 		if (!(hwmgr->feature_mask & PP_UVD_HANDSHAKE_MASK))
 			smu7_disable_handshake_uvd(hwmgr);
+
 		PP_ASSERT_WITH_CODE(
 				(0 == smum_send_msg_to_smc(hwmgr,
 						PPSMC_MSG_MCLKDPM_Enable)),
 				"Failed to enable MCLK DPM during DPM Start Function!",
 				return -EINVAL);
 
-		PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1);
+		if (hwmgr->chip_family != CHIP_VEGAM)
+			PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1);
 
 
 		if (hwmgr->chip_family == AMDGPU_FAMILY_CI) {
@@ -1019,8 +1057,13 @@ static int smu7_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC1_CNTL, 0x5);
 			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_CPL_CNTL, 0x100005);
 			udelay(10);
-			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC0_CNTL, 0x400005);
-			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC1_CNTL, 0x400005);
+			if (hwmgr->chip_id == CHIP_VEGAM) {
+				cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC0_CNTL, 0x400009);
+				cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC1_CNTL, 0x400009);
+			} else {
+				cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC0_CNTL, 0x400005);
+				cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC1_CNTL, 0x400005);
+			}
 			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_CPL_CNTL, 0x500005);
 		}
 	}
@@ -1229,7 +1272,7 @@ static int smu7_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 
 		tmp_result = smu7_construct_voltage_tables(hwmgr);
 		PP_ASSERT_WITH_CODE((0 == tmp_result),
-				"Failed to contruct voltage tables!",
+				"Failed to construct voltage tables!",
 				result = tmp_result);
 	}
 	smum_initialize_mc_reg_table(hwmgr);
@@ -1261,10 +1304,12 @@ static int smu7_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to process firmware header!", result = tmp_result);
 
-	tmp_result = smu7_initial_switch_from_arbf0_to_f1(hwmgr);
-	PP_ASSERT_WITH_CODE((0 == tmp_result),
-			"Failed to initialize switch from ArbF0 to F1!",
-			result = tmp_result);
+	if (hwmgr->chip_id != CHIP_VEGAM) {
+		tmp_result = smu7_initial_switch_from_arbf0_to_f1(hwmgr);
+		PP_ASSERT_WITH_CODE((0 == tmp_result),
+				"Failed to initialize switch from ArbF0 to F1!",
+				result = tmp_result);
+	}
 
 	result = smu7_setup_default_dpm_tables(hwmgr);
 	PP_ASSERT_WITH_CODE(0 == result,
@@ -2754,6 +2799,9 @@ static int smu7_vblank_too_short(struct pp_hwmgr *hwmgr,
 	case CHIP_POLARIS12:
 		switch_limit_us = data->is_memory_gddr5 ? 190 : 150;
 		break;
+	case CHIP_VEGAM:
+		switch_limit_us = 30;
+		break;
 	default:
 		switch_limit_us = data->is_memory_gddr5 ? 450 : 150;
 		break;
@@ -2777,8 +2825,6 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	struct PP_Clocks minimum_clocks = {0};
 	bool disable_mclk_switching;
 	bool disable_mclk_switching_for_frame_lock;
-	struct cgs_display_info info = {0};
-	struct cgs_mode_info mode_info = {0};
 	const struct phm_clock_and_voltage_limits *max_limits;
 	uint32_t i;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -2787,7 +2833,6 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	int32_t count;
 	int32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0;
 
-	info.mode_info = &mode_info;
 	data->battery_state = (PP_StateUILabel_Battery ==
 			request_ps->classification.ui_label);
 
@@ -2809,10 +2854,8 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 		}
 	}
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
-
-	minimum_clocks.engineClock = hwmgr->display_config.min_core_set_clock;
-	minimum_clocks.memoryClock = hwmgr->display_config.min_mem_set_clock;
+	minimum_clocks.engineClock = hwmgr->display_config->min_core_set_clock;
+	minimum_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
 			PHM_PlatformCaps_StablePState)) {
@@ -2843,12 +2886,12 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				    PHM_PlatformCaps_DisableMclkSwitchingForFrameLock);
 
 
-	if (info.display_count == 0)
+	if (hwmgr->display_config->num_display == 0)
 		disable_mclk_switching = false;
 	else
-		disable_mclk_switching = ((1 < info.display_count) ||
+		disable_mclk_switching = ((1 < hwmgr->display_config->num_display) ||
 					  disable_mclk_switching_for_frame_lock ||
-					  smu7_vblank_too_short(hwmgr, mode_info.vblank_time_us));
+					  smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time));
 
 	sclk = smu7_ps->performance_levels[0].engine_clock;
 	mclk = smu7_ps->performance_levels[0].memory_clock;
@@ -2957,8 +3000,7 @@ static int smu7_dpm_patch_boot_state(struct pp_hwmgr *hwmgr,
 	/* First retrieve the Boot clocks and VDDC from the firmware info table.
 	 * We assume here that fw_info is unchanged if this call fails.
 	 */
-	fw_info = (ATOM_FIRMWARE_INFO_V2_2 *)cgs_atom_get_data_table(
-			hwmgr->device, index,
+	fw_info = (ATOM_FIRMWARE_INFO_V2_2 *)smu_atom_get_data_table(hwmgr->adev, index,
 			&size, &frev, &crev);
 	if (!fw_info)
 		/* During a test, there is no firmware info table. */
@@ -3366,34 +3408,35 @@ static int smu7_get_pp_table_entry(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr,
-		struct pp_gpu_power *query)
+static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query)
 {
-	PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr,
-			PPSMC_MSG_PmStatusLogStart),
-			"Failed to start pm status log!",
-			return -1);
+	int i;
+	u32 tmp = 0;
 
-	/* Sampling period from 50ms to 4sec */
-	msleep_interruptible(200);
+	if (!query)
+		return -EINVAL;
 
-	PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr,
-			PPSMC_MSG_PmStatusLogSample),
-			"Failed to sample pm status log!",
-			return -1);
+	smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0);
+	tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
+	*query = tmp;
 
-	query->vddc_power = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC,
-			ixSMU_PM_STATUS_40);
-	query->vddci_power = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC,
-			ixSMU_PM_STATUS_49);
-	query->max_gpu_power = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC,
-			ixSMU_PM_STATUS_94);
-	query->average_gpu_power = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC,
-			ixSMU_PM_STATUS_95);
+	if (tmp != 0)
+		return 0;
+
+	smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogStart);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+							ixSMU_PM_STATUS_94, 0);
+
+	for (i = 0; i < 10; i++) {
+		mdelay(1);
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogSample);
+		tmp = cgs_read_ind_register(hwmgr->device,
+						CGS_IND_REG__SMC,
+						ixSMU_PM_STATUS_94);
+		if (tmp != 0)
+			break;
+	}
+	*query = tmp;
 
 	return 0;
 }
@@ -3446,10 +3489,7 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		return 0;
 	case AMDGPU_PP_SENSOR_GPU_POWER:
-		if (*size < sizeof(struct pp_gpu_power))
-			return -EINVAL;
-		*size = sizeof(struct pp_gpu_power);
-		return smu7_get_gpu_power(hwmgr, (struct pp_gpu_power *)value);
+		return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
 	case AMDGPU_PP_SENSOR_VDDGFX:
 		if ((data->vr_config & 0xff) == 0x2)
 			val_vid = PHM_READ_INDIRECT_FIELD(hwmgr->device,
@@ -3480,7 +3520,6 @@ static int smu7_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, cons
 			[smu7_ps->performance_level_count - 1].memory_clock;
 	struct PP_Clocks min_clocks = {0};
 	uint32_t i;
-	struct cgs_display_info info = {0};
 
 	for (i = 0; i < sclk_table->count; i++) {
 		if (sclk == sclk_table->dpm_levels[i].value)
@@ -3507,9 +3546,8 @@ static int smu7_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, cons
 	if (i >= mclk_table->count)
 		data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
 
-	if (data->display_timing.num_existing_displays != info.display_count)
+	if (data->display_timing.num_existing_displays != hwmgr->display_config->num_display)
 		data->need_update_smu7_dpm_table |= DPMTABLE_UPDATE_MCLK;
 
 	return 0;
@@ -3812,9 +3850,14 @@ static int smu7_notify_smc_display(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
-	if (hwmgr->feature_mask & PP_VBI_TIME_SUPPORT_MASK)
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			(PPSMC_Msg)PPSMC_MSG_SetVBITimeout, data->frame_time_x2);
+	if (hwmgr->feature_mask & PP_VBI_TIME_SUPPORT_MASK) {
+		if (hwmgr->chip_id == CHIP_VEGAM)
+			smum_send_msg_to_smc_with_parameter(hwmgr,
+					(PPSMC_Msg)PPSMC_MSG_SetVBITimeout_VEGAM, data->frame_time_x2);
+		else
+			smum_send_msg_to_smc_with_parameter(hwmgr,
+					(PPSMC_Msg)PPSMC_MSG_SetVBITimeout, data->frame_time_x2);
+	}
 	return (smum_send_msg_to_smc(hwmgr, (PPSMC_Msg)PPSMC_HasDisplay) == 0) ?  0 : -EINVAL;
 }
 
@@ -3908,15 +3951,8 @@ smu7_notify_smc_display_change(struct pp_hwmgr *hwmgr, bool has_display)
 static int
 smu7_notify_smc_display_config_after_ps_adjustment(struct pp_hwmgr *hwmgr)
 {
-	uint32_t num_active_displays = 0;
-	struct cgs_display_info info = {0};
-
-	info.mode_info = NULL;
-	cgs_get_active_displays_info(hwmgr->device, &info);
-
-	num_active_displays = info.display_count;
-
-	if (num_active_displays > 1 && hwmgr->display_config.multi_monitor_in_sync != true)
+	if (hwmgr->display_config->num_display > 1 &&
+			!hwmgr->display_config->multi_monitor_in_sync)
 		smu7_notify_smc_display_change(hwmgr, false);
 
 	return 0;
@@ -3931,33 +3967,24 @@ smu7_notify_smc_display_config_after_ps_adjustment(struct pp_hwmgr *hwmgr)
 static int smu7_program_display_gap(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	uint32_t num_active_displays = 0;
 	uint32_t display_gap = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCG_DISPLAY_GAP_CNTL);
 	uint32_t display_gap2;
 	uint32_t pre_vbi_time_in_us;
 	uint32_t frame_time_in_us;
-	uint32_t ref_clock;
-	uint32_t refresh_rate = 0;
-	struct cgs_display_info info = {0};
-	struct cgs_mode_info mode_info = {0};
+	uint32_t ref_clock, refresh_rate;
 
-	info.mode_info = &mode_info;
-	cgs_get_active_displays_info(hwmgr->device, &info);
-	num_active_displays = info.display_count;
-
-	display_gap = PHM_SET_FIELD(display_gap, CG_DISPLAY_GAP_CNTL, DISP_GAP, (num_active_displays > 0) ? DISPLAY_GAP_VBLANK_OR_WM : DISPLAY_GAP_IGNORE);
+	display_gap = PHM_SET_FIELD(display_gap, CG_DISPLAY_GAP_CNTL, DISP_GAP, (hwmgr->display_config->num_display > 0) ? DISPLAY_GAP_VBLANK_OR_WM : DISPLAY_GAP_IGNORE);
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCG_DISPLAY_GAP_CNTL, display_gap);
 
 	ref_clock =  amdgpu_asic_get_xclk((struct amdgpu_device *)hwmgr->adev);
-
-	refresh_rate = mode_info.refresh_rate;
+	refresh_rate = hwmgr->display_config->vrefresh;
 
 	if (0 == refresh_rate)
 		refresh_rate = 60;
 
 	frame_time_in_us = 1000000 / refresh_rate;
 
-	pre_vbi_time_in_us = frame_time_in_us - 200 - mode_info.vblank_time_us;
+	pre_vbi_time_in_us = frame_time_in_us - 200 - hwmgr->display_config->min_vblank_time;
 
 	data->frame_time_x2 = frame_time_in_us * 2 / 100;
 
@@ -4037,17 +4064,14 @@ smu7_check_smc_update_required_for_display_configuration(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 	bool is_update_required = false;
-	struct cgs_display_info info = {0, 0, NULL};
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
-
-	if (data->display_timing.num_existing_displays != info.display_count)
+	if (data->display_timing.num_existing_displays != hwmgr->display_config->num_display)
 		is_update_required = true;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SclkDeepSleep)) {
-		if (data->display_timing.min_clock_in_sr != hwmgr->display_config.min_core_set_clock_in_sr &&
+		if (data->display_timing.min_clock_in_sr != hwmgr->display_config->min_core_set_clock_in_sr &&
 			(data->display_timing.min_clock_in_sr >= SMU7_MINIMUM_ENGINE_CLOCK ||
-			hwmgr->display_config.min_core_set_clock_in_sr >= SMU7_MINIMUM_ENGINE_CLOCK))
+			hwmgr->display_config->min_core_set_clock_in_sr >= SMU7_MINIMUM_ENGINE_CLOCK))
 			is_update_required = true;
 	}
 	return is_update_required;
@@ -4102,7 +4126,7 @@ static int smu7_check_states_equal(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static int smu7_upload_mc_firmware(struct pp_hwmgr *hwmgr)
+static int smu7_check_mc_firmware(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
@@ -4181,13 +4205,9 @@ static int smu7_read_clock_registers(struct pp_hwmgr *hwmgr)
 static int smu7_get_memory_type(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	uint32_t temp;
-
-	temp = cgs_read_register(hwmgr->device, mmMC_SEQ_MISC0);
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	data->is_memory_gddr5 = (MC_SEQ_MISC0_GDDR5_VALUE ==
-			((temp & MC_SEQ_MISC0_GDDR5_MASK) >>
-			 MC_SEQ_MISC0_GDDR5_SHIFT));
+	data->is_memory_gddr5 = (adev->gmc.vram_type == AMDGPU_VRAM_TYPE_GDDR5);
 
 	return 0;
 }
@@ -4235,7 +4255,7 @@ static int smu7_setup_asic_task(struct pp_hwmgr *hwmgr)
 {
 	int tmp_result, result = 0;
 
-	smu7_upload_mc_firmware(hwmgr);
+	smu7_check_mc_firmware(hwmgr);
 
 	tmp_result = smu7_read_clock_registers(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
@@ -4370,22 +4390,36 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s: \n", "OD_SCLK");
+			size = sprintf(buf, "%s:\n", "OD_SCLK");
 			for (i = 0; i < odn_sclk_table->num_of_pl; i++)
-				size += sprintf(buf + size, "%d: %10uMhz %10u mV\n",
-					i, odn_sclk_table->entries[i].clock / 100,
+				size += sprintf(buf + size, "%d: %10uMHz %10umV\n",
+					i, odn_sclk_table->entries[i].clock/100,
 					odn_sclk_table->entries[i].vddc);
 		}
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s: \n", "OD_MCLK");
+			size = sprintf(buf, "%s:\n", "OD_MCLK");
 			for (i = 0; i < odn_mclk_table->num_of_pl; i++)
-				size += sprintf(buf + size, "%d: %10uMhz %10u mV\n",
-					i, odn_mclk_table->entries[i].clock / 100,
+				size += sprintf(buf + size, "%d: %10uMHz %10umV\n",
+					i, odn_mclk_table->entries[i].clock/100,
 					odn_mclk_table->entries[i].vddc);
 		}
 		break;
+	case OD_RANGE:
+		if (hwmgr->od_enabled) {
+			size = sprintf(buf, "%s:\n", "OD_RANGE");
+			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
+				data->golden_dpm_table.sclk_table.dpm_levels[0].value/100,
+				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
+			size += sprintf(buf + size, "MCLK: %7uMHz %10uMHz\n",
+				data->golden_dpm_table.mclk_table.dpm_levels[0].value/100,
+				hwmgr->platform_descriptor.overdriveLimit.memoryClock/100);
+			size += sprintf(buf + size, "VDDC: %7umV %11umV\n",
+				data->odn_dpm_table.min_vddc,
+				data->odn_dpm_table.max_vddc);
+		}
+		break;
 	default:
 		break;
 	}
@@ -4669,36 +4703,27 @@ static bool smu7_check_clk_voltage_valid(struct pp_hwmgr *hwmgr,
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	uint32_t min_vddc;
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_sclk_table;
-
-	if (table_info == NULL)
-		return false;
-
-	dep_sclk_table = table_info->vdd_dep_on_sclk;
-	min_vddc = dep_sclk_table->entries[0].vddc;
-
-	if (voltage < min_vddc || voltage > 2000) {
-		pr_info("OD voltage is out of range [%d - 2000] mV\n", min_vddc);
+	if (voltage < data->odn_dpm_table.min_vddc || voltage > data->odn_dpm_table.max_vddc) {
+		pr_info("OD voltage is out of range [%d - %d] mV\n",
+						data->odn_dpm_table.min_vddc,
+						data->odn_dpm_table.max_vddc);
 		return false;
 	}
 
 	if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
-		if (data->vbios_boot_state.sclk_bootup_value > clk ||
+		if (data->golden_dpm_table.sclk_table.dpm_levels[0].value > clk ||
 			hwmgr->platform_descriptor.overdriveLimit.engineClock < clk) {
 			pr_info("OD engine clock is out of range [%d - %d] MHz\n",
-				data->vbios_boot_state.sclk_bootup_value,
-				hwmgr->platform_descriptor.overdriveLimit.engineClock / 100);
+				data->golden_dpm_table.sclk_table.dpm_levels[0].value/100,
+				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
 			return false;
 		}
 	} else if (type == PP_OD_EDIT_MCLK_VDDC_TABLE) {
-		if (data->vbios_boot_state.mclk_bootup_value > clk ||
+		if (data->golden_dpm_table.mclk_table.dpm_levels[0].value > clk ||
 			hwmgr->platform_descriptor.overdriveLimit.memoryClock < clk) {
 			pr_info("OD memory clock is out of range [%d - %d] MHz\n",
-				data->vbios_boot_state.mclk_bootup_value/100,
-				hwmgr->platform_descriptor.overdriveLimit.memoryClock / 100);
+				data->golden_dpm_table.mclk_table.dpm_levels[0].value/100,
+				hwmgr->platform_descriptor.overdriveLimit.memoryClock/100);
 			return false;
 		}
 	} else {
@@ -4743,23 +4768,23 @@ static void smu7_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
 
 	for (i=0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
-			break;
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
+			return;
 		}
 	}
-	if (i == dep_table->count)
-		data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
 
 	dep_table = table_info->vdd_dep_on_sclk;
 	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk);
 	for (i=0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
-			break;
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
+			return;
 		}
 	}
-	if (i == dep_table->count)
+	if (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
 		data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+		data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
+	}
 }
 
 static int smu7_odn_edit_dpm_table(struct pp_hwmgr *hwmgr,
@@ -4860,6 +4885,17 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	len = sizeof(smu7_profiling) / sizeof(struct profile_mode_setting);
 
 	for (i = 0; i < len; i++) {
+		if (i == hwmgr->power_profile_mode) {
+			size += sprintf(buf + size, "%3d %14s %s: %8d %16d %16d %16d %16d %16d\n",
+			i, profile_name[i], "*",
+			data->current_profile_setting.sclk_up_hyst,
+			data->current_profile_setting.sclk_down_hyst,
+			data->current_profile_setting.sclk_activity,
+			data->current_profile_setting.mclk_up_hyst,
+			data->current_profile_setting.mclk_down_hyst,
+			data->current_profile_setting.mclk_activity);
+			continue;
+		}
 		if (smu7_profiling[i].bupdate_sclk)
 			size += sprintf(buf + size, "%3d %16s: %8d %16d %16d ",
 			i, profile_name[i], smu7_profiling[i].sclk_up_hyst,
@@ -4879,24 +4915,6 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 			"-", "-", "-");
 	}
 
-	size += sprintf(buf + size, "%3d %16s: %8d %16d %16d %16d %16d %16d\n",
-			i, profile_name[i],
-			data->custom_profile_setting.sclk_up_hyst,
-			data->custom_profile_setting.sclk_down_hyst,
-			data->custom_profile_setting.sclk_activity,
-			data->custom_profile_setting.mclk_up_hyst,
-			data->custom_profile_setting.mclk_down_hyst,
-			data->custom_profile_setting.mclk_activity);
-
-	size += sprintf(buf + size, "%3s %16s: %8d %16d %16d %16d %16d %16d\n",
-			"*", "CURRENT",
-			data->current_profile_setting.sclk_up_hyst,
-			data->current_profile_setting.sclk_down_hyst,
-			data->current_profile_setting.sclk_activity,
-			data->current_profile_setting.mclk_up_hyst,
-			data->current_profile_setting.mclk_down_hyst,
-			data->current_profile_setting.mclk_activity);
-
 	return size;
 }
 
@@ -4935,16 +4953,16 @@ static int smu7_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, uint
 		if (size < 8)
 			return -EINVAL;
 
-		data->custom_profile_setting.bupdate_sclk = input[0];
-		data->custom_profile_setting.sclk_up_hyst = input[1];
-		data->custom_profile_setting.sclk_down_hyst = input[2];
-		data->custom_profile_setting.sclk_activity = input[3];
-		data->custom_profile_setting.bupdate_mclk = input[4];
-		data->custom_profile_setting.mclk_up_hyst = input[5];
-		data->custom_profile_setting.mclk_down_hyst = input[6];
-		data->custom_profile_setting.mclk_activity = input[7];
-		if (!smum_update_dpm_settings(hwmgr, &data->custom_profile_setting)) {
-			memcpy(&data->current_profile_setting, &data->custom_profile_setting, sizeof(struct profile_mode_setting));
+		tmp.bupdate_sclk = input[0];
+		tmp.sclk_up_hyst = input[1];
+		tmp.sclk_down_hyst = input[2];
+		tmp.sclk_activity = input[3];
+		tmp.bupdate_mclk = input[4];
+		tmp.mclk_up_hyst = input[5];
+		tmp.mclk_down_hyst = input[6];
+		tmp.mclk_activity = input[7];
+		if (!smum_update_dpm_settings(hwmgr, &tmp)) {
+			memcpy(&data->current_profile_setting, &tmp, sizeof(struct profile_mode_setting));
 			hwmgr->power_profile_mode = mode;
 		}
 		break;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
index f40179c9ca97..c91e75db6a8e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
@@ -184,6 +184,8 @@ struct smu7_odn_dpm_table {
 	struct smu7_odn_clock_voltage_dependency_table	vdd_dependency_on_sclk;
 	struct smu7_odn_clock_voltage_dependency_table	vdd_dependency_on_mclk;
 	uint32_t					odn_mclk_min_limit;
+	uint32_t min_vddc;
+	uint32_t max_vddc;
 };
 
 struct profile_mode_setting {
@@ -325,7 +327,6 @@ struct smu7_hwmgr {
 	uint16_t                              mem_latency_high;
 	uint16_t                              mem_latency_low;
 	uint32_t                              vr_config;
-	struct profile_mode_setting           custom_profile_setting;
 	struct profile_mode_setting           current_profile_setting;
 };
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
index 03bc7453f3b1..c952845833d7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
@@ -623,6 +623,190 @@ static const struct gpu_pt_config_reg DIDTConfig_Polaris11_Kicker[] =
 	{   0xFFFFFFFF  }  /* End of list */
 };
 
+static const struct gpu_pt_config_reg GCCACConfig_VegaM[] =
+{
+// ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+//      Offset                             Mask                                                Shift                                               Value       Type
+// ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+    // DIDT_SQ
+    //
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00060013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00860013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01060013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01860013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02060013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02860013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x03060013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x03860013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x04060013, GPU_CONFIGREG_GC_CAC_IND },
+
+    // DIDT_TD
+    //
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x000E0013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x008E0013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x010E0013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x018E0013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x020E0013, GPU_CONFIGREG_GC_CAC_IND },
+
+    // DIDT_TCP
+    //
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00100013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00900013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01100013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01900013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02100013, GPU_CONFIGREG_GC_CAC_IND },
+    {   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02900013, GPU_CONFIGREG_GC_CAC_IND },
+
+    {   0xFFFFFFFF  }  // End of list
+};
+
+static const struct gpu_pt_config_reg DIDTConfig_VegaM[] =
+{
+// ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+//      Offset                             Mask                                                Shift                                               Value       Type
+// ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+    // DIDT_SQ
+    //
+    {   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT0_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT0__SHIFT,                  0x0073,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT1_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT1__SHIFT,                  0x00ab,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT2_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT2__SHIFT,                  0x0084,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT3_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT3__SHIFT,                  0x005a,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT4_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT4__SHIFT,                  0x0067,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT5_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT5__SHIFT,                  0x0084,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT6_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT6__SHIFT,                  0x0027,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT7_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT7__SHIFT,                  0x0046,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT8_MASK,                   DIDT_SQ_WEIGHT8_11__WEIGHT8__SHIFT,                 0x00aa,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT9_MASK,                   DIDT_SQ_WEIGHT8_11__WEIGHT9__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT10_MASK,                  DIDT_SQ_WEIGHT8_11__WEIGHT10__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT11_MASK,                  DIDT_SQ_WEIGHT8_11__WEIGHT11__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_SQ_CTRL1,                   DIDT_SQ_CTRL1__MIN_POWER_MASK,                      DIDT_SQ_CTRL1__MIN_POWER__SHIFT,                    0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL1,                   DIDT_SQ_CTRL1__MAX_POWER_MASK,                      DIDT_SQ_CTRL1__MAX_POWER__SHIFT,                    0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__UNUSED_0_MASK,                    DIDT_SQ_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_SQ_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3853,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_0_MASK,                       DIDT_SQ_CTRL2__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,       DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,     0x005a,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_1_MASK,                       DIDT_SQ_CTRL2__UNUSED_1__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,       DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,     0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_2_MASK,                       DIDT_SQ_CTRL2__UNUSED_2__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,    DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT,  0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,   DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x0ebb,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__UNUSED_0_MASK,                  DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,       DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,     0x3853,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,     0x3153,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK,                 DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT,               0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_SQ_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__PHASE_OFFSET_MASK,                   DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0010,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0010,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__UNUSED_0_MASK,                       DIDT_SQ_CTRL0__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    // DIDT_TD
+    //
+    {   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT0_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT0__SHIFT,                  0x000a,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT1_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT1__SHIFT,                  0x0010,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT2_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT2__SHIFT,                  0x0017,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT3_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT3__SHIFT,                  0x002f,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT4_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT4__SHIFT,                  0x0046,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT5_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT5__SHIFT,                  0x005d,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT6_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT6__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT7_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT7__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MIN_POWER_MASK,                      DIDT_TD_CTRL1__MIN_POWER__SHIFT,                    0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MAX_POWER_MASK,                      DIDT_TD_CTRL1__MAX_POWER__SHIFT,                    0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__UNUSED_0_MASK,                    DIDT_TD_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_TD_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0x00ff,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3fff,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_0_MASK,                       DIDT_TD_CTRL2__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,       DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,     0x000f,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_1_MASK,                       DIDT_TD_CTRL2__UNUSED_1__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,       DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,     0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_2_MASK,                       DIDT_TD_CTRL2__UNUSED_2__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,    DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT,  0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,       DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,       DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,   DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__UNUSED_0_MASK,                  DIDT_TD_STALL_CTRL__UNUSED_0__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,       DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,     0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,       DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,     0x0dde,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,       DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,     0x0dde,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__UNUSED_0_MASK,                 DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT,               0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_TD_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__PHASE_OFFSET_MASK,                   DIDT_TD_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0009,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0009,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__UNUSED_0_MASK,                       DIDT_TD_CTRL0__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    // DIDT_TCP
+    //
+    {   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT0_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT0__SHIFT,                 0x0004,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT1_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT1__SHIFT,                 0x0037,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT2_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT2__SHIFT,                 0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT3_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT3__SHIFT,                 0x00ff,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT4_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT4__SHIFT,                 0x0054,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT5_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT5__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT6_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT6__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT7_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT7__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TCP_CTRL1,                  DIDT_TCP_CTRL1__MIN_POWER_MASK,                     DIDT_TCP_CTRL1__MIN_POWER__SHIFT,                   0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL1,                  DIDT_TCP_CTRL1__MAX_POWER_MASK,                     DIDT_TCP_CTRL1__MAX_POWER__SHIFT,                   0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TCP_CTRL_OCP,               DIDT_TCP_CTRL_OCP__UNUSED_0_MASK,                   DIDT_TCP_CTRL_OCP__UNUSED_0__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL_OCP,               DIDT_TCP_CTRL_OCP__OCP_MAX_POWER_MASK,              DIDT_TCP_CTRL_OCP__OCP_MAX_POWER__SHIFT,            0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__MAX_POWER_DELTA_MASK,               DIDT_TCP_CTRL2__MAX_POWER_DELTA__SHIFT,             0x3dde,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_0_MASK,                      DIDT_TCP_CTRL2__UNUSED_0__SHIFT,                    0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,      DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,    0x0032,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_1_MASK,                      DIDT_TCP_CTRL2__UNUSED_1__SHIFT,                    0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,      DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,    0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_2_MASK,                      DIDT_TCP_CTRL2__UNUSED_2__SHIFT,                    0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,   DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,      DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,    0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,      DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,    0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,  DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT,0x01aa,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__UNUSED_0_MASK,                 DIDT_TCP_STALL_CTRL__UNUSED_0__SHIFT,               0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,      DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,    0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,      DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,    0x3dde,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,      DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,    0x3dde,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK,                DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT,              0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_TCP_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__PHASE_OFFSET_MASK,                   DIDT_TCP_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0010,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0010,     GPU_CONFIGREG_DIDT_IND },
+    {   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__UNUSED_0_MASK,                       DIDT_TCP_CTRL0__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+    {   0xFFFFFFFF  }  // End of list
+};
 static int smu7_enable_didt(struct pp_hwmgr *hwmgr, const bool enable)
 {
 	uint32_t en = enable ? 1 : 0;
@@ -740,8 +924,8 @@ int smu7_enable_didt_config(struct pp_hwmgr *hwmgr)
 	    PP_CAP(PHM_PlatformCaps_TDRamping) ||
 	    PP_CAP(PHM_PlatformCaps_TCPRamping)) {
 
-		cgs_enter_safe_mode(hwmgr->device, true);
-		cgs_lock_grbm_idx(hwmgr->device, true);
+		adev->gfx.rlc.funcs->enter_safe_mode(adev);
+		mutex_lock(&adev->grbm_idx_mutex);
 		value = 0;
 		value2 = cgs_read_register(hwmgr->device, mmGRBM_GFX_INDEX);
 		for (count = 0; count < num_se; count++) {
@@ -752,67 +936,80 @@ int smu7_enable_didt_config(struct pp_hwmgr *hwmgr)
 
 			if (hwmgr->chip_id == CHIP_POLARIS10) {
 				result = smu7_program_pt_config_registers(hwmgr, GCCACConfig_Polaris10);
-				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", goto error);
 				result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris10);
-				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", goto error);
 			} else if (hwmgr->chip_id == CHIP_POLARIS11) {
 				result = smu7_program_pt_config_registers(hwmgr, GCCACConfig_Polaris11);
-				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", goto error);
 				if (hwmgr->is_kicker)
 					result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11_Kicker);
 				else
 					result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11);
-				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", goto error);
 			} else if (hwmgr->chip_id == CHIP_POLARIS12) {
 				result = smu7_program_pt_config_registers(hwmgr, GCCACConfig_Polaris11);
-				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", goto error);
 				result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris12);
-				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", goto error);
+			} else if (hwmgr->chip_id == CHIP_VEGAM) {
+				result = smu7_program_pt_config_registers(hwmgr, GCCACConfig_VegaM);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", goto error);
+				result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_VegaM);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", goto error);
 			}
 		}
 		cgs_write_register(hwmgr->device, mmGRBM_GFX_INDEX, value2);
 
 		result = smu7_enable_didt(hwmgr, true);
-		PP_ASSERT_WITH_CODE((result == 0), "EnableDiDt failed.", return result);
+		PP_ASSERT_WITH_CODE((result == 0), "EnableDiDt failed.", goto error);
 
 		if (hwmgr->chip_id == CHIP_POLARIS11) {
 			result = smum_send_msg_to_smc(hwmgr,
 						(uint16_t)(PPSMC_MSG_EnableDpmDidt));
 			PP_ASSERT_WITH_CODE((0 == result),
-					"Failed to enable DPM DIDT.", return result);
+					"Failed to enable DPM DIDT.", goto error);
 		}
-		cgs_lock_grbm_idx(hwmgr->device, false);
-		cgs_enter_safe_mode(hwmgr->device, false);
+		mutex_unlock(&adev->grbm_idx_mutex);
+		adev->gfx.rlc.funcs->exit_safe_mode(adev);
 	}
 
 	return 0;
+error:
+	mutex_unlock(&adev->grbm_idx_mutex);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
+	return result;
 }
 
 int smu7_disable_didt_config(struct pp_hwmgr *hwmgr)
 {
 	int result;
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	if (PP_CAP(PHM_PlatformCaps_SQRamping) ||
 	    PP_CAP(PHM_PlatformCaps_DBRamping) ||
 	    PP_CAP(PHM_PlatformCaps_TDRamping) ||
 	    PP_CAP(PHM_PlatformCaps_TCPRamping)) {
 
-		cgs_enter_safe_mode(hwmgr->device, true);
+		adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
 		result = smu7_enable_didt(hwmgr, false);
 		PP_ASSERT_WITH_CODE((result == 0),
 				"Post DIDT enable clock gating failed.",
-				return result);
+				goto error);
 		if (hwmgr->chip_id == CHIP_POLARIS11) {
 			result = smum_send_msg_to_smc(hwmgr,
 						(uint16_t)(PPSMC_MSG_DisableDpmDidt));
 			PP_ASSERT_WITH_CODE((0 == result),
-					"Failed to disable DPM DIDT.", return result);
+					"Failed to disable DPM DIDT.", goto error);
 		}
-		cgs_enter_safe_mode(hwmgr->device, false);
+		adev->gfx.rlc.funcs->exit_safe_mode(adev);
 	}
 
 	return 0;
+error:
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
+	return result;
 }
 
 int smu7_enable_smc_cac(struct pp_hwmgr *hwmgr)
@@ -852,12 +1049,10 @@ int smu7_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
-	n = (n & 0xff) << 8;
-
 	if (data->power_containment_features &
 			POWERCONTAINMENT_FEATURE_PkgPwrLimit)
 		return smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_PkgPwrSetLimit, n);
+				PPSMC_MSG_PkgPwrSetLimit, n<<8);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
index 7b26607c646a..50690c72b2ea 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
@@ -314,8 +314,7 @@ static int smu8_get_system_info_data(struct pp_hwmgr *hwmgr)
 	uint8_t frev, crev;
 	uint16_t size;
 
-	info = (ATOM_INTEGRATED_SYSTEM_INFO_V1_9 *) cgs_atom_get_data_table(
-			hwmgr->device,
+	info = (ATOM_INTEGRATED_SYSTEM_INFO_V1_9 *)smu_atom_get_data_table(hwmgr->adev,
 			GetIndexIntoMasterTable(DATA, IntegratedSystemInfo),
 			&size, &frev, &crev);
 
@@ -694,7 +693,7 @@ static int smu8_update_sclk_limit(struct pp_hwmgr *hwmgr)
 	else
 		data->sclk_dpm.soft_max_clk  = table->entries[table->count - 1].clk;
 
-	clock = hwmgr->display_config.min_core_set_clock;
+	clock = hwmgr->display_config->min_core_set_clock;
 	if (clock == 0)
 		pr_debug("min_core_set_clock not set\n");
 
@@ -749,7 +748,7 @@ static int smu8_set_deep_sleep_sclk_threshold(struct pp_hwmgr *hwmgr)
 {
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
 				PHM_PlatformCaps_SclkDeepSleep)) {
-		uint32_t clks = hwmgr->display_config.min_core_set_clock_in_sr;
+		uint32_t clks = hwmgr->display_config->min_core_set_clock_in_sr;
 		if (clks == 0)
 			clks = SMU8_MIN_DEEP_SLEEP_SCLK;
 
@@ -1041,25 +1040,21 @@ static int smu8_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	struct smu8_hwmgr *data = hwmgr->backend;
 	struct PP_Clocks clocks = {0, 0, 0, 0};
 	bool force_high;
-	uint32_t  num_of_active_displays = 0;
-	struct cgs_display_info info = {0};
 
 	smu8_ps->need_dfs_bypass = true;
 
 	data->battery_state = (PP_StateUILabel_Battery == prequest_ps->classification.ui_label);
 
-	clocks.memoryClock = hwmgr->display_config.min_mem_set_clock != 0 ?
-				hwmgr->display_config.min_mem_set_clock :
+	clocks.memoryClock = hwmgr->display_config->min_mem_set_clock != 0 ?
+				hwmgr->display_config->min_mem_set_clock :
 				data->sys_info.nbp_memory_clock[1];
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
-	num_of_active_displays = info.display_count;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_StablePState))
 		clocks.memoryClock = hwmgr->dyn_state.max_clock_voltage_on_ac.mclk;
 
 	force_high = (clocks.memoryClock > data->sys_info.nbp_memory_clock[SMU8_NUM_NBPMEMORYCLOCK - 1])
-			|| (num_of_active_displays >= 3);
+			|| (hwmgr->display_config->num_display >= 3);
 
 	smu8_ps->action = smu8_current_ps->action;
 
@@ -1897,20 +1892,20 @@ static void smu8_dpm_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate)
 	data->uvd_power_gated = bgate;
 
 	if (bgate) {
-		cgs_set_powergating_state(hwmgr->device,
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_UVD,
 						AMD_PG_STATE_GATE);
-		cgs_set_clockgating_state(hwmgr->device,
+		amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_UVD,
 						AMD_CG_STATE_GATE);
 		smu8_dpm_update_uvd_dpm(hwmgr, true);
 		smu8_dpm_powerdown_uvd(hwmgr);
 	} else {
 		smu8_dpm_powerup_uvd(hwmgr);
-		cgs_set_clockgating_state(hwmgr->device,
+		amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_UVD,
 						AMD_CG_STATE_UNGATE);
-		cgs_set_powergating_state(hwmgr->device,
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 						AMD_IP_BLOCK_TYPE_UVD,
 						AMD_PG_STATE_UNGATE);
 		smu8_dpm_update_uvd_dpm(hwmgr, false);
@@ -1923,12 +1918,10 @@ static void smu8_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 	struct smu8_hwmgr *data = hwmgr->backend;
 
 	if (bgate) {
-		cgs_set_powergating_state(
-					hwmgr->device,
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_VCE,
 					AMD_PG_STATE_GATE);
-		cgs_set_clockgating_state(
-					hwmgr->device,
+		amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_VCE,
 					AMD_CG_STATE_GATE);
 		smu8_enable_disable_vce_dpm(hwmgr, false);
@@ -1937,12 +1930,10 @@ static void smu8_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 	} else {
 		smu8_dpm_powerup_vce(hwmgr);
 		data->vce_power_gated = false;
-		cgs_set_clockgating_state(
-					hwmgr->device,
+		amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_VCE,
 					AMD_CG_STATE_UNGATE);
-		cgs_set_powergating_state(
-					hwmgr->device,
+		amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_VCE,
 					AMD_PG_STATE_UNGATE);
 		smu8_dpm_update_vce_dpm(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
index 598122854ab5..93a3d022ba47 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
@@ -24,6 +24,7 @@
 #include "pp_debug.h"
 #include "ppatomctrl.h"
 #include "ppsmc.h"
+#include "atom.h"
 
 uint8_t convert_to_vid(uint16_t vddc)
 {
@@ -608,3 +609,100 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
 
 	return 0;
 }
+
+void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
+						uint8_t *frev, uint8_t *crev)
+{
+	struct amdgpu_device *adev = dev;
+	uint16_t data_start;
+
+	if (amdgpu_atom_parse_data_header(
+		    adev->mode_info.atom_context, table, size,
+		    frev, crev, &data_start))
+		return (uint8_t *)adev->mode_info.atom_context->bios +
+			data_start;
+
+	return NULL;
+}
+
+int smu_get_voltage_dependency_table_ppt_v1(
+			const struct phm_ppt_v1_clock_voltage_dependency_table *allowed_dep_table,
+			struct phm_ppt_v1_clock_voltage_dependency_table *dep_table)
+{
+	uint8_t i = 0;
+	PP_ASSERT_WITH_CODE((0 != allowed_dep_table->count),
+				"Voltage Lookup Table empty",
+				return -EINVAL);
+
+	dep_table->count = allowed_dep_table->count;
+	for (i=0; i<dep_table->count; i++) {
+		dep_table->entries[i].clk = allowed_dep_table->entries[i].clk;
+		dep_table->entries[i].vddInd = allowed_dep_table->entries[i].vddInd;
+		dep_table->entries[i].vdd_offset = allowed_dep_table->entries[i].vdd_offset;
+		dep_table->entries[i].vddc = allowed_dep_table->entries[i].vddc;
+		dep_table->entries[i].vddgfx = allowed_dep_table->entries[i].vddgfx;
+		dep_table->entries[i].vddci = allowed_dep_table->entries[i].vddci;
+		dep_table->entries[i].mvdd = allowed_dep_table->entries[i].mvdd;
+		dep_table->entries[i].phases = allowed_dep_table->entries[i].phases;
+		dep_table->entries[i].cks_enable = allowed_dep_table->entries[i].cks_enable;
+		dep_table->entries[i].cks_voffset = allowed_dep_table->entries[i].cks_voffset;
+	}
+
+	return 0;
+}
+
+int smu_set_watermarks_for_clocks_ranges(void *wt_table,
+		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+{
+	uint32_t i;
+	struct watermarks *table = wt_table;
+
+	if (!table || !wm_with_clock_ranges)
+		return -EINVAL;
+
+	if (wm_with_clock_ranges->num_wm_sets_dmif > 4 || wm_with_clock_ranges->num_wm_sets_mcif > 4)
+		return -EINVAL;
+
+	for (i = 0; i < wm_with_clock_ranges->num_wm_sets_dmif; i++) {
+		table->WatermarkRow[1][i].MinClock =
+			cpu_to_le16((uint16_t)
+			(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_dcefclk_in_khz) /
+			100);
+		table->WatermarkRow[1][i].MaxClock =
+			cpu_to_le16((uint16_t)
+			(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_dcefclk_in_khz) /
+			100);
+		table->WatermarkRow[1][i].MinUclk =
+			cpu_to_le16((uint16_t)
+			(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_memclk_in_khz) /
+			100);
+		table->WatermarkRow[1][i].MaxUclk =
+			cpu_to_le16((uint16_t)
+			(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_memclk_in_khz) /
+			100);
+		table->WatermarkRow[1][i].WmSetting = (uint8_t)
+				wm_with_clock_ranges->wm_sets_dmif[i].wm_set_id;
+	}
+
+	for (i = 0; i < wm_with_clock_ranges->num_wm_sets_mcif; i++) {
+		table->WatermarkRow[0][i].MinClock =
+			cpu_to_le16((uint16_t)
+			(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_socclk_in_khz) /
+			100);
+		table->WatermarkRow[0][i].MaxClock =
+			cpu_to_le16((uint16_t)
+			(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_socclk_in_khz) /
+			100);
+		table->WatermarkRow[0][i].MinUclk =
+			cpu_to_le16((uint16_t)
+			(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_memclk_in_khz) /
+			100);
+		table->WatermarkRow[0][i].MaxUclk =
+			cpu_to_le16((uint16_t)
+			(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_memclk_in_khz) /
+			100);
+		table->WatermarkRow[0][i].WmSetting = (uint8_t)
+				wm_with_clock_ranges->wm_sets_mcif[i].wm_set_id;
+	}
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
index d37d16e4b613..916cc01e7652 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
@@ -26,10 +26,27 @@
 struct pp_atomctrl_voltage_table;
 struct pp_hwmgr;
 struct phm_ppt_v1_voltage_lookup_table;
+struct Watermarks_t;
+struct pp_wm_sets_with_clock_ranges_soc15;
 
 uint8_t convert_to_vid(uint16_t vddc);
 uint16_t convert_to_vddc(uint8_t vid);
 
+struct watermark_row_generic_t {
+	uint16_t MinClock;
+	uint16_t MaxClock;
+	uint16_t MinUclk;
+	uint16_t MaxUclk;
+
+	uint8_t  WmSetting;
+	uint8_t  Padding[3];
+};
+
+struct watermarks {
+	struct watermark_row_generic_t WatermarkRow[2][4];
+	uint32_t     padding[7];
+};
+
 extern int phm_wait_for_register_unequal(struct pp_hwmgr *hwmgr,
 					uint32_t index,
 					uint32_t value, uint32_t mask);
@@ -82,6 +99,16 @@ int phm_irq_process(struct amdgpu_device *adev,
 
 int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr);
 
+void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
+						uint8_t *frev, uint8_t *crev);
+
+int smu_get_voltage_dependency_table_ppt_v1(
+	const struct phm_ppt_v1_clock_voltage_dependency_table *allowed_dep_table,
+		struct phm_ppt_v1_clock_voltage_dependency_table *dep_table);
+
+int smu_set_watermarks_for_clocks_ranges(void *wt_table,
+		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+
 #define PHM_FIELD_SHIFT(reg, field) reg##__##field##__SHIFT
 #define PHM_FIELD_MASK(reg, field) reg##__##field##_MASK
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 7cbb56ba6fab..d156b7bb92ae 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -36,7 +36,7 @@
 #include "smu9.h"
 #include "smu9_driver_if.h"
 #include "vega10_inc.h"
-#include "pp_soc15.h"
+#include "soc15_common.h"
 #include "pppcielanes.h"
 #include "vega10_hwmgr.h"
 #include "vega10_processpptables.h"
@@ -51,10 +51,6 @@
 #include "smuio/smuio_9_0_offset.h"
 #include "smuio/smuio_9_0_sh_mask.h"
 
-#define VOLTAGE_SCALE  4
-#define VOLTAGE_VID_OFFSET_SCALE1   625
-#define VOLTAGE_VID_OFFSET_SCALE2   100
-
 #define HBM_MEMORY_CHANNEL_WIDTH    128
 
 static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
@@ -79,8 +75,6 @@ static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
 #define DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK                                                        0x000000F0L
 #define DF_CS_AON0_DramBaseAddress0__IntLvAddrSel_MASK                                                        0x00000700L
 #define DF_CS_AON0_DramBaseAddress0__DramBaseAddr_MASK                                                        0xFFFFF000L
-static int vega10_force_clock_level(struct pp_hwmgr *hwmgr,
-		enum pp_clock_type type, uint32_t mask);
 
 static const ULONG PhwVega10_Magic = (ULONG)(PHM_VIslands_Magic);
 
@@ -291,6 +285,48 @@ static int vega10_set_features_platform_caps(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int vega10_odn_initial_default_setting(struct pp_hwmgr *hwmgr)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	struct phm_ppt_v2_information *table_info =
+			(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
+	struct vega10_odn_vddc_lookup_table *od_lookup_table;
+	struct phm_ppt_v1_voltage_lookup_table *vddc_lookup_table;
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table[3];
+	struct phm_ppt_v1_clock_voltage_dependency_table *od_table[3];
+	uint32_t i;
+
+	od_lookup_table = &odn_table->vddc_lookup_table;
+	vddc_lookup_table = table_info->vddc_lookup_table;
+
+	for (i = 0; i < vddc_lookup_table->count; i++)
+		od_lookup_table->entries[i].us_vdd = vddc_lookup_table->entries[i].us_vdd;
+
+	od_lookup_table->count = vddc_lookup_table->count;
+
+	dep_table[0] = table_info->vdd_dep_on_sclk;
+	dep_table[1] = table_info->vdd_dep_on_mclk;
+	dep_table[2] = table_info->vdd_dep_on_socclk;
+	od_table[0] = (struct phm_ppt_v1_clock_voltage_dependency_table *)&odn_table->vdd_dep_on_sclk;
+	od_table[1] = (struct phm_ppt_v1_clock_voltage_dependency_table *)&odn_table->vdd_dep_on_mclk;
+	od_table[2] = (struct phm_ppt_v1_clock_voltage_dependency_table *)&odn_table->vdd_dep_on_socclk;
+
+	for (i = 0; i < 3; i++)
+		smu_get_voltage_dependency_table_ppt_v1(dep_table[i], od_table[i]);
+
+	if (odn_table->max_vddc == 0 || odn_table->max_vddc > 2000)
+		odn_table->max_vddc = dep_table[0]->entries[dep_table[0]->count - 1].vddc;
+	if (odn_table->min_vddc == 0 || odn_table->min_vddc > 2000)
+		odn_table->min_vddc = dep_table[0]->entries[0].vddc;
+
+	i = od_table[2]->count - 1;
+	od_table[2]->entries[i].clk = hwmgr->platform_descriptor.overdriveLimit.memoryClock;
+	od_table[2]->entries[i].vddc = odn_table->max_vddc;
+
+	return 0;
+}
+
 static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
@@ -427,7 +463,6 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 		/* ACG firmware has major version 5 */
 	if ((hwmgr->smu_version & 0xff000000) == 0x5000000)
 		data->smu_features[GNLD_ACG].supported = true;
-
 	if (data->registry_data.didt_support)
 		data->smu_features[GNLD_DIDT].supported = true;
 
@@ -754,7 +789,6 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	uint32_t config_telemetry = 0;
 	struct pp_atomfwctrl_voltage_table vol_table;
 	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
 
 	data = kzalloc(sizeof(struct vega10_hwmgr), GFP_KERNEL);
 	if (data == NULL)
@@ -860,10 +894,7 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 			advanceFanControlParameters.usFanPWMMinLimit *
 			hwmgr->thermal_controller.fanInfo.ulMaxRPM / 100;
 
-	reg = soc15_get_register_offset(DF_HWID, 0,
-			mmDF_CS_AON0_DramBaseAddress0_BASE_IDX,
-			mmDF_CS_AON0_DramBaseAddress0);
-	data->mem_channels = (cgs_read_register(hwmgr->device, reg) &
+	data->mem_channels = (RREG32_SOC15(DF, 0, mmDF_CS_AON0_DramBaseAddress0) &
 			DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK) >>
 			DF_CS_AON0_DramBaseAddress0__IntLvNumChan__SHIFT;
 	PP_ASSERT_WITH_CODE(data->mem_channels < ARRAY_SIZE(channel_number),
@@ -1370,48 +1401,6 @@ static int vega10_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 	memcpy(&(data->golden_dpm_table), &(data->dpm_table),
 			sizeof(struct vega10_dpm_table));
 
-	if (PP_CAP(PHM_PlatformCaps_ODNinACSupport) ||
-	    PP_CAP(PHM_PlatformCaps_ODNinDCSupport)) {
-		data->odn_dpm_table.odn_core_clock_dpm_levels.num_of_pl =
-						data->dpm_table.gfx_table.count;
-		for (i = 0; i < data->dpm_table.gfx_table.count; i++) {
-			data->odn_dpm_table.odn_core_clock_dpm_levels.entries[i].clock =
-					data->dpm_table.gfx_table.dpm_levels[i].value;
-			data->odn_dpm_table.odn_core_clock_dpm_levels.entries[i].enabled = true;
-		}
-
-		data->odn_dpm_table.vdd_dependency_on_sclk.count =
-				dep_gfx_table->count;
-		for (i = 0; i < dep_gfx_table->count; i++) {
-			data->odn_dpm_table.vdd_dependency_on_sclk.entries[i].clk =
-					dep_gfx_table->entries[i].clk;
-			data->odn_dpm_table.vdd_dependency_on_sclk.entries[i].vddInd =
-					dep_gfx_table->entries[i].vddInd;
-			data->odn_dpm_table.vdd_dependency_on_sclk.entries[i].cks_enable =
-					dep_gfx_table->entries[i].cks_enable;
-			data->odn_dpm_table.vdd_dependency_on_sclk.entries[i].cks_voffset =
-					dep_gfx_table->entries[i].cks_voffset;
-		}
-
-		data->odn_dpm_table.odn_memory_clock_dpm_levels.num_of_pl =
-						data->dpm_table.mem_table.count;
-		for (i = 0; i < data->dpm_table.mem_table.count; i++) {
-			data->odn_dpm_table.odn_memory_clock_dpm_levels.entries[i].clock =
-					data->dpm_table.mem_table.dpm_levels[i].value;
-			data->odn_dpm_table.odn_memory_clock_dpm_levels.entries[i].enabled = true;
-		}
-
-		data->odn_dpm_table.vdd_dependency_on_mclk.count = dep_mclk_table->count;
-		for (i = 0; i < dep_mclk_table->count; i++) {
-			data->odn_dpm_table.vdd_dependency_on_mclk.entries[i].clk =
-					dep_mclk_table->entries[i].clk;
-			data->odn_dpm_table.vdd_dependency_on_mclk.entries[i].vddInd =
-					dep_mclk_table->entries[i].vddInd;
-			data->odn_dpm_table.vdd_dependency_on_mclk.entries[i].vddci =
-					dep_mclk_table->entries[i].vddci;
-		}
-	}
-
 	return 0;
 }
 
@@ -1514,18 +1503,18 @@ static int vega10_populate_single_gfx_level(struct pp_hwmgr *hwmgr,
 {
 	struct phm_ppt_v2_information *table_info =
 			(struct phm_ppt_v2_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_on_sclk =
-			table_info->vdd_dep_on_sclk;
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_on_sclk;
 	struct vega10_hwmgr *data = hwmgr->backend;
 	struct pp_atomfwctrl_clock_dividers_soc15 dividers;
 	uint32_t gfx_max_clock =
 			hwmgr->platform_descriptor.overdriveLimit.engineClock;
 	uint32_t i = 0;
 
-	if (data->apply_overdrive_next_settings_mask &
-			DPMTABLE_OD_UPDATE_VDDC)
+	if (hwmgr->od_enabled)
 		dep_on_sclk = (struct phm_ppt_v1_clock_voltage_dependency_table *)
-						&(data->odn_dpm_table.vdd_dependency_on_sclk);
+						&(data->odn_dpm_table.vdd_dep_on_sclk);
+	else
+		dep_on_sclk = table_info->vdd_dep_on_sclk;
 
 	PP_ASSERT_WITH_CODE(dep_on_sclk,
 			"Invalid SOC_VDD-GFX_CLK Dependency Table!",
@@ -1577,23 +1566,32 @@ static int vega10_populate_single_soc_level(struct pp_hwmgr *hwmgr,
 		uint32_t soc_clock, uint8_t *current_soc_did,
 		uint8_t *current_vol_index)
 {
+	struct vega10_hwmgr *data = hwmgr->backend;
 	struct phm_ppt_v2_information *table_info =
 			(struct phm_ppt_v2_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_on_soc =
-			table_info->vdd_dep_on_socclk;
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_on_soc;
 	struct pp_atomfwctrl_clock_dividers_soc15 dividers;
 	uint32_t i;
 
-	PP_ASSERT_WITH_CODE(dep_on_soc,
-			"Invalid SOC_VDD-SOC_CLK Dependency Table!",
-			return -EINVAL);
-	for (i = 0; i < dep_on_soc->count; i++) {
-		if (dep_on_soc->entries[i].clk == soc_clock)
-			break;
+	if (hwmgr->od_enabled) {
+		dep_on_soc = (struct phm_ppt_v1_clock_voltage_dependency_table *)
+						&data->odn_dpm_table.vdd_dep_on_socclk;
+		for (i = 0; i < dep_on_soc->count; i++) {
+			if (dep_on_soc->entries[i].clk >= soc_clock)
+				break;
+		}
+	} else {
+		dep_on_soc = table_info->vdd_dep_on_socclk;
+		for (i = 0; i < dep_on_soc->count; i++) {
+			if (dep_on_soc->entries[i].clk == soc_clock)
+				break;
+		}
 	}
+
 	PP_ASSERT_WITH_CODE(dep_on_soc->count > i,
 			"Cannot find SOC_CLK in SOC_VDD-SOC_CLK Dependency Table",
 			return -EINVAL);
+
 	PP_ASSERT_WITH_CODE(!pp_atomfwctrl_get_gpu_pll_dividers_vega10(hwmgr,
 			COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK,
 			soc_clock, &dividers),
@@ -1602,22 +1600,6 @@ static int vega10_populate_single_soc_level(struct pp_hwmgr *hwmgr,
 
 	*current_soc_did = (uint8_t)dividers.ulDid;
 	*current_vol_index = (uint8_t)(dep_on_soc->entries[i].vddInd);
-
-	return 0;
-}
-
-uint16_t vega10_locate_vddc_given_clock(struct pp_hwmgr *hwmgr,
-		uint32_t clk,
-		struct phm_ppt_v1_clock_voltage_dependency_table *dep_table)
-{
-	uint16_t i;
-
-	for (i = 0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].clk == clk)
-			return dep_table->entries[i].vddc;
-	}
-
-	pr_info("[LocateVddcGivenClock] Cannot locate SOC Vddc for this clock!");
 	return 0;
 }
 
@@ -1631,8 +1613,6 @@ static int vega10_populate_all_graphic_levels(struct pp_hwmgr *hwmgr)
 	struct vega10_hwmgr *data = hwmgr->backend;
 	struct phm_ppt_v2_information *table_info =
 			(struct phm_ppt_v2_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table =
-			table_info->vdd_dep_on_socclk;
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
 	struct vega10_single_dpm_table *dpm_table = &(data->dpm_table.gfx_table);
 	int result = 0;
@@ -1663,11 +1643,6 @@ static int vega10_populate_all_graphic_levels(struct pp_hwmgr *hwmgr)
 
 	dpm_table = &(data->dpm_table.soc_table);
 	for (i = 0; i < dpm_table->count; i++) {
-		pp_table->SocVid[i] =
-				(uint8_t)convert_to_vid(
-				vega10_locate_vddc_given_clock(hwmgr,
-						dpm_table->dpm_levels[i].value,
-						dep_table));
 		result = vega10_populate_single_soc_level(hwmgr,
 				dpm_table->dpm_levels[i].value,
 				&(pp_table->SocclkDid[i]),
@@ -1678,7 +1653,6 @@ static int vega10_populate_all_graphic_levels(struct pp_hwmgr *hwmgr)
 
 	j = i - 1;
 	while (i < NUM_SOCCLK_DPM_LEVELS) {
-		pp_table->SocVid[i] = pp_table->SocVid[j];
 		result = vega10_populate_single_soc_level(hwmgr,
 				dpm_table->dpm_levels[j].value,
 				&(pp_table->SocclkDid[i]),
@@ -1691,6 +1665,32 @@ static int vega10_populate_all_graphic_levels(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+static void vega10_populate_vddc_soc_levels(struct pp_hwmgr *hwmgr)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+	struct phm_ppt_v2_information *table_info = hwmgr->pptable;
+	struct phm_ppt_v1_voltage_lookup_table *vddc_lookup_table;
+
+	uint8_t soc_vid = 0;
+	uint32_t i, max_vddc_level;
+
+	if (hwmgr->od_enabled)
+		vddc_lookup_table = (struct phm_ppt_v1_voltage_lookup_table *)&data->odn_dpm_table.vddc_lookup_table;
+	else
+		vddc_lookup_table = table_info->vddc_lookup_table;
+
+	max_vddc_level = vddc_lookup_table->count;
+	for (i = 0; i < max_vddc_level; i++) {
+		soc_vid = (uint8_t)convert_to_vid(vddc_lookup_table->entries[i].us_vdd);
+		pp_table->SocVid[i] = soc_vid;
+	}
+	while (i < MAX_REGULAR_DPM_NUMBER) {
+		pp_table->SocVid[i] = soc_vid;
+		i++;
+	}
+}
+
 /**
  * @brief Populates single SMC GFXCLK structure using the provided clock.
  *
@@ -1705,25 +1705,25 @@ static int vega10_populate_single_memory_level(struct pp_hwmgr *hwmgr,
 	struct vega10_hwmgr *data = hwmgr->backend;
 	struct phm_ppt_v2_information *table_info =
 			(struct phm_ppt_v2_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_on_mclk =
-			table_info->vdd_dep_on_mclk;
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_on_mclk;
 	struct pp_atomfwctrl_clock_dividers_soc15 dividers;
 	uint32_t mem_max_clock =
 			hwmgr->platform_descriptor.overdriveLimit.memoryClock;
 	uint32_t i = 0;
 
-	if (data->apply_overdrive_next_settings_mask &
-			DPMTABLE_OD_UPDATE_VDDC)
+	if (hwmgr->od_enabled)
 		dep_on_mclk = (struct phm_ppt_v1_clock_voltage_dependency_table *)
-					&data->odn_dpm_table.vdd_dependency_on_mclk;
+					&data->odn_dpm_table.vdd_dep_on_mclk;
+	else
+		dep_on_mclk = table_info->vdd_dep_on_mclk;
 
 	PP_ASSERT_WITH_CODE(dep_on_mclk,
 			"Invalid SOC_VDD-UCLK Dependency Table!",
 			return -EINVAL);
 
-	if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_MCLK)
+	if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_MCLK) {
 		mem_clock = mem_clock > mem_max_clock ? mem_max_clock : mem_clock;
-	else {
+	} else {
 		for (i = 0; i < dep_on_mclk->count; i++) {
 			if (dep_on_mclk->entries[i].clk == mem_clock)
 				break;
@@ -2067,6 +2067,9 @@ static int vega10_populate_avfs_parameters(struct pp_hwmgr *hwmgr)
 	if (data->smu_features[GNLD_AVFS].supported) {
 		result = pp_atomfwctrl_get_avfs_information(hwmgr, &avfs_params);
 		if (!result) {
+			data->odn_dpm_table.max_vddc = avfs_params.ulMaxVddc;
+			data->odn_dpm_table.min_vddc = avfs_params.ulMinVddc;
+
 			pp_table->MinVoltageVid = (uint8_t)
 					convert_to_vid((uint16_t)(avfs_params.ulMinVddc));
 			pp_table->MaxVoltageVid = (uint8_t)
@@ -2345,6 +2348,22 @@ static int vega10_avfs_enable(struct pp_hwmgr *hwmgr, bool enable)
 	return 0;
 }
 
+static int vega10_update_avfs(struct pp_hwmgr *hwmgr)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+
+	if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
+		vega10_avfs_enable(hwmgr, false);
+	} else if (data->need_update_dpm_table) {
+		vega10_avfs_enable(hwmgr, false);
+		vega10_avfs_enable(hwmgr, true);
+	} else {
+		vega10_avfs_enable(hwmgr, true);
+	}
+
+	return 0;
+}
+
 static int vega10_populate_and_upload_avfs_fuse_override(struct pp_hwmgr *hwmgr)
 {
 	int result = 0;
@@ -2406,6 +2425,10 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 			"Failed to setup default DPM tables!",
 			return result);
 
+	/* initialize ODN table */
+	if (hwmgr->od_enabled)
+		vega10_odn_initial_default_setting(hwmgr);
+
 	pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC,
 			VOLTAGE_OBJ_SVID2,  &voltage_table);
 	pp_table->MaxVidStep = voltage_table.max_vid_step;
@@ -2452,6 +2475,8 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 			"Failed to initialize Memory Level!",
 			return result);
 
+	vega10_populate_vddc_soc_levels(hwmgr);
+
 	result = vega10_populate_all_display_clock_levels(hwmgr);
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to initialize Display Level!",
@@ -2481,6 +2506,12 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 		data->vbios_boot_state.mvddc    = boot_up_values.usMvddc;
 		data->vbios_boot_state.gfx_clock = boot_up_values.ulGfxClk;
 		data->vbios_boot_state.mem_clock = boot_up_values.ulUClk;
+		pp_atomfwctrl_get_clk_information_by_clkid(hwmgr,
+				SMU9_SYSPLL0_SOCCLK_ID, &boot_up_values.ulSocClk);
+
+		pp_atomfwctrl_get_clk_information_by_clkid(hwmgr,
+				SMU9_SYSPLL0_DCEFCLK_ID, &boot_up_values.ulDCEFClk);
+
 		data->vbios_boot_state.soc_clock = boot_up_values.ulSocClk;
 		data->vbios_boot_state.dcef_clock = boot_up_values.ulDCEFClk;
 		if (0 != boot_up_values.usVddc) {
@@ -2829,7 +2860,7 @@ static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 
 	tmp_result = vega10_construct_voltage_tables(hwmgr);
 	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to contruct voltage tables!",
+			"Failed to construct voltage tables!",
 			result = tmp_result);
 
 	tmp_result = vega10_init_smc_table(hwmgr);
@@ -3028,7 +3059,6 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	bool disable_mclk_switching_for_frame_lock;
 	bool disable_mclk_switching_for_vr;
 	bool force_mclk_high;
-	struct cgs_display_info info = {0};
 	const struct phm_clock_and_voltage_limits *max_limits;
 	uint32_t i;
 	struct vega10_hwmgr *data = hwmgr->backend;
@@ -3063,11 +3093,9 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 		}
 	}
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
-
 	/* result = PHM_CheckVBlankTime(hwmgr, &vblankTooShort);*/
-	minimum_clocks.engineClock = hwmgr->display_config.min_core_set_clock;
-	minimum_clocks.memoryClock = hwmgr->display_config.min_mem_set_clock;
+	minimum_clocks.engineClock = hwmgr->display_config->min_core_set_clock;
+	minimum_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock;
 
 	if (PP_CAP(PHM_PlatformCaps_StablePState)) {
 		stable_pstate_sclk_dpm_percentage =
@@ -3107,10 +3135,10 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 		PP_CAP(PHM_PlatformCaps_DisableMclkSwitchForVR);
 	force_mclk_high = PP_CAP(PHM_PlatformCaps_ForceMclkHigh);
 
-	if (info.display_count == 0)
+	if (hwmgr->display_config->num_display == 0)
 		disable_mclk_switching = false;
 	else
-		disable_mclk_switching = (info.display_count > 1) ||
+		disable_mclk_switching = (hwmgr->display_config->num_display > 1) ||
 			disable_mclk_switching_for_frame_lock ||
 			disable_mclk_switching_for_vr ||
 			force_mclk_high;
@@ -3171,87 +3199,11 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 
 static int vega10_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, const void *input)
 {
-	const struct phm_set_power_state_input *states =
-			(const struct phm_set_power_state_input *)input;
-	const struct vega10_power_state *vega10_ps =
-			cast_const_phw_vega10_power_state(states->pnew_state);
 	struct vega10_hwmgr *data = hwmgr->backend;
-	struct vega10_single_dpm_table *sclk_table =
-			&(data->dpm_table.gfx_table);
-	uint32_t sclk = vega10_ps->performance_levels
-			[vega10_ps->performance_level_count - 1].gfx_clock;
-	struct vega10_single_dpm_table *mclk_table =
-			&(data->dpm_table.mem_table);
-	uint32_t mclk = vega10_ps->performance_levels
-			[vega10_ps->performance_level_count - 1].mem_clock;
-	struct PP_Clocks min_clocks = {0};
-	uint32_t i;
-	struct cgs_display_info info = {0};
-
-	data->need_update_dpm_table = 0;
-
-	if (PP_CAP(PHM_PlatformCaps_ODNinACSupport) ||
-	    PP_CAP(PHM_PlatformCaps_ODNinDCSupport)) {
-		for (i = 0; i < sclk_table->count; i++) {
-			if (sclk == sclk_table->dpm_levels[i].value)
-				break;
-		}
-
-		if (!(data->apply_overdrive_next_settings_mask &
-				DPMTABLE_OD_UPDATE_SCLK) && i >= sclk_table->count) {
-			/* Check SCLK in DAL's minimum clocks
-			 * in case DeepSleep divider update is required.
-			 */
-			if (data->display_timing.min_clock_in_sr !=
-					min_clocks.engineClockInSR &&
-				(min_clocks.engineClockInSR >=
-						VEGA10_MINIMUM_ENGINE_CLOCK ||
-					data->display_timing.min_clock_in_sr >=
-						VEGA10_MINIMUM_ENGINE_CLOCK))
-				data->need_update_dpm_table |= DPMTABLE_UPDATE_SCLK;
-		}
-
-		cgs_get_active_displays_info(hwmgr->device, &info);
-
-		if (data->display_timing.num_existing_displays !=
-				info.display_count)
-			data->need_update_dpm_table |= DPMTABLE_UPDATE_MCLK;
-	} else {
-		for (i = 0; i < sclk_table->count; i++) {
-			if (sclk == sclk_table->dpm_levels[i].value)
-				break;
-		}
-
-		if (i >= sclk_table->count)
-			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
-		else {
-			/* Check SCLK in DAL's minimum clocks
-			 * in case DeepSleep divider update is required.
-			 */
-			if (data->display_timing.min_clock_in_sr !=
-					min_clocks.engineClockInSR &&
-				(min_clocks.engineClockInSR >=
-						VEGA10_MINIMUM_ENGINE_CLOCK ||
-					data->display_timing.min_clock_in_sr >=
-						VEGA10_MINIMUM_ENGINE_CLOCK))
-				data->need_update_dpm_table |= DPMTABLE_UPDATE_SCLK;
-		}
 
-		for (i = 0; i < mclk_table->count; i++) {
-			if (mclk == mclk_table->dpm_levels[i].value)
-				break;
-		}
-
-		cgs_get_active_displays_info(hwmgr->device, &info);
+	if (data->display_timing.num_existing_displays != hwmgr->display_config->num_display)
+		data->need_update_dpm_table |= DPMTABLE_UPDATE_MCLK;
 
-		if (i >= mclk_table->count)
-			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
-
-		if (data->display_timing.num_existing_displays !=
-				info.display_count ||
-				i >= mclk_table->count)
-			data->need_update_dpm_table |= DPMTABLE_UPDATE_MCLK;
-	}
 	return 0;
 }
 
@@ -3259,194 +3211,29 @@ static int vega10_populate_and_upload_sclk_mclk_dpm_levels(
 		struct pp_hwmgr *hwmgr, const void *input)
 {
 	int result = 0;
-	const struct phm_set_power_state_input *states =
-			(const struct phm_set_power_state_input *)input;
-	const struct vega10_power_state *vega10_ps =
-			cast_const_phw_vega10_power_state(states->pnew_state);
 	struct vega10_hwmgr *data = hwmgr->backend;
-	uint32_t sclk = vega10_ps->performance_levels
-			[vega10_ps->performance_level_count - 1].gfx_clock;
-	uint32_t mclk = vega10_ps->performance_levels
-			[vega10_ps->performance_level_count - 1].mem_clock;
-	struct vega10_dpm_table *dpm_table = &data->dpm_table;
-	struct vega10_dpm_table *golden_dpm_table =
-			&data->golden_dpm_table;
-	uint32_t dpm_count, clock_percent;
-	uint32_t i;
 
-	if (PP_CAP(PHM_PlatformCaps_ODNinACSupport) ||
-	    PP_CAP(PHM_PlatformCaps_ODNinDCSupport)) {
-
-		if (!data->need_update_dpm_table &&
-			!data->apply_optimized_settings &&
-			!data->apply_overdrive_next_settings_mask)
-			return 0;
-
-		if (data->apply_overdrive_next_settings_mask &
-				DPMTABLE_OD_UPDATE_SCLK) {
-			for (dpm_count = 0;
-					dpm_count < dpm_table->gfx_table.count;
-					dpm_count++) {
-				dpm_table->gfx_table.dpm_levels[dpm_count].enabled =
-					data->odn_dpm_table.odn_core_clock_dpm_levels.entries[dpm_count].enabled;
-				dpm_table->gfx_table.dpm_levels[dpm_count].value =
-					data->odn_dpm_table.odn_core_clock_dpm_levels.entries[dpm_count].clock;
-			}
-		}
-
-		if (data->apply_overdrive_next_settings_mask &
-				DPMTABLE_OD_UPDATE_MCLK) {
-			for (dpm_count = 0;
-					dpm_count < dpm_table->mem_table.count;
-					dpm_count++) {
-				dpm_table->mem_table.dpm_levels[dpm_count].enabled =
-					data->odn_dpm_table.odn_memory_clock_dpm_levels.entries[dpm_count].enabled;
-				dpm_table->mem_table.dpm_levels[dpm_count].value =
-					data->odn_dpm_table.odn_memory_clock_dpm_levels.entries[dpm_count].clock;
-			}
-		}
-
-		if ((data->need_update_dpm_table & DPMTABLE_UPDATE_SCLK) ||
-			data->apply_optimized_settings ||
-			(data->apply_overdrive_next_settings_mask &
-					DPMTABLE_OD_UPDATE_SCLK)) {
-			result = vega10_populate_all_graphic_levels(hwmgr);
-			PP_ASSERT_WITH_CODE(!result,
-					"Failed to populate SCLK during PopulateNewDPMClocksStates Function!",
-					return result);
-		}
-
-		if ((data->need_update_dpm_table & DPMTABLE_UPDATE_MCLK) ||
-			(data->apply_overdrive_next_settings_mask &
-					DPMTABLE_OD_UPDATE_MCLK)){
-			result = vega10_populate_all_memory_levels(hwmgr);
-			PP_ASSERT_WITH_CODE(!result,
-					"Failed to populate MCLK during PopulateNewDPMClocksStates Function!",
-					return result);
-		}
-	} else {
-		if (!data->need_update_dpm_table &&
-				!data->apply_optimized_settings)
-			return 0;
-
-		if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_SCLK &&
-				data->smu_features[GNLD_DPM_GFXCLK].supported) {
-				dpm_table->
-				gfx_table.dpm_levels[dpm_table->gfx_table.count - 1].
-				value = sclk;
-				if (hwmgr->od_enabled) {
-					/* Need to do calculation based on the golden DPM table
-					 * as the Heatmap GPU Clock axis is also based on
-					 * the default values
-					 */
-					PP_ASSERT_WITH_CODE(
-							golden_dpm_table->gfx_table.dpm_levels
-							[golden_dpm_table->gfx_table.count - 1].value,
-							"Divide by 0!",
-							return -1);
-
-					dpm_count = dpm_table->gfx_table.count < 2 ?
-							0 : dpm_table->gfx_table.count - 2;
-					for (i = dpm_count; i > 1; i--) {
-						if (sclk > golden_dpm_table->gfx_table.dpm_levels
-							[golden_dpm_table->gfx_table.count - 1].value) {
-							clock_percent =
-								((sclk - golden_dpm_table->gfx_table.dpm_levels
-								[golden_dpm_table->gfx_table.count - 1].value) *
-								100) /
-								golden_dpm_table->gfx_table.dpm_levels
-								[golden_dpm_table->gfx_table.count - 1].value;
-
-							dpm_table->gfx_table.dpm_levels[i].value =
-								golden_dpm_table->gfx_table.dpm_levels[i].value +
-								(golden_dpm_table->gfx_table.dpm_levels[i].value *
-								clock_percent) / 100;
-						} else if (golden_dpm_table->
-								gfx_table.dpm_levels[dpm_table->gfx_table.count-1].value >
-								sclk) {
-							clock_percent =
-								((golden_dpm_table->gfx_table.dpm_levels
-								[golden_dpm_table->gfx_table.count - 1].value -
-								sclk) *	100) /
-								golden_dpm_table->gfx_table.dpm_levels
-								[golden_dpm_table->gfx_table.count-1].value;
-
-							dpm_table->gfx_table.dpm_levels[i].value =
-								golden_dpm_table->gfx_table.dpm_levels[i].value -
-								(golden_dpm_table->gfx_table.dpm_levels[i].value *
-								clock_percent) / 100;
-						} else
-							dpm_table->gfx_table.dpm_levels[i].value =
-								golden_dpm_table->gfx_table.dpm_levels[i].value;
-					}
-				}
-			}
+	if (!data->need_update_dpm_table)
+		return 0;
 
-		if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_MCLK &&
-				data->smu_features[GNLD_DPM_UCLK].supported) {
-			dpm_table->
-			mem_table.dpm_levels[dpm_table->mem_table.count - 1].
-			value = mclk;
+	if (data->need_update_dpm_table &
+			(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK + DPMTABLE_UPDATE_SOCCLK)) {
+		result = vega10_populate_all_graphic_levels(hwmgr);
+		PP_ASSERT_WITH_CODE((0 == result),
+				"Failed to populate SCLK during PopulateNewDPMClocksStates Function!",
+				return result);
+	}
 
-			if (hwmgr->od_enabled) {
-				PP_ASSERT_WITH_CODE(
-					golden_dpm_table->mem_table.dpm_levels
-					[golden_dpm_table->mem_table.count - 1].value,
-					"Divide by 0!",
-					return -1);
+	if (data->need_update_dpm_table &
+			(DPMTABLE_OD_UPDATE_MCLK + DPMTABLE_UPDATE_MCLK)) {
+		result = vega10_populate_all_memory_levels(hwmgr);
+		PP_ASSERT_WITH_CODE((0 == result),
+				"Failed to populate MCLK during PopulateNewDPMClocksStates Function!",
+				return result);
+	}
 
-				dpm_count = dpm_table->mem_table.count < 2 ?
-						0 : dpm_table->mem_table.count - 2;
-				for (i = dpm_count; i > 1; i--) {
-					if (mclk > golden_dpm_table->mem_table.dpm_levels
-						[golden_dpm_table->mem_table.count-1].value) {
-						clock_percent = ((mclk -
-							golden_dpm_table->mem_table.dpm_levels
-							[golden_dpm_table->mem_table.count-1].value) *
-							100) /
-							golden_dpm_table->mem_table.dpm_levels
-							[golden_dpm_table->mem_table.count-1].value;
-
-						dpm_table->mem_table.dpm_levels[i].value =
-							golden_dpm_table->mem_table.dpm_levels[i].value +
-							(golden_dpm_table->mem_table.dpm_levels[i].value *
-							clock_percent) / 100;
-					} else if (golden_dpm_table->mem_table.dpm_levels
-							[dpm_table->mem_table.count-1].value > mclk) {
-						clock_percent = ((golden_dpm_table->mem_table.dpm_levels
-							[golden_dpm_table->mem_table.count-1].value - mclk) *
-							100) /
-							golden_dpm_table->mem_table.dpm_levels
-							[golden_dpm_table->mem_table.count-1].value;
-
-						dpm_table->mem_table.dpm_levels[i].value =
-							golden_dpm_table->mem_table.dpm_levels[i].value -
-							(golden_dpm_table->mem_table.dpm_levels[i].value *
-							clock_percent) / 100;
-					} else
-						dpm_table->mem_table.dpm_levels[i].value =
-							golden_dpm_table->mem_table.dpm_levels[i].value;
-				}
-			}
-		}
+	vega10_populate_vddc_soc_levels(hwmgr);
 
-		if ((data->need_update_dpm_table &
-			(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK)) ||
-			data->apply_optimized_settings) {
-			result = vega10_populate_all_graphic_levels(hwmgr);
-			PP_ASSERT_WITH_CODE(!result,
-					"Failed to populate SCLK during PopulateNewDPMClocksStates Function!",
-					return result);
-		}
-
-		if (data->need_update_dpm_table &
-				(DPMTABLE_OD_UPDATE_MCLK + DPMTABLE_UPDATE_MCLK)) {
-			result = vega10_populate_all_memory_levels(hwmgr);
-			PP_ASSERT_WITH_CODE(!result,
-					"Failed to populate MCLK during PopulateNewDPMClocksStates Function!",
-					return result);
-		}
-	}
 	return result;
 }
 
@@ -3742,8 +3529,9 @@ static int vega10_set_power_state_tasks(struct pp_hwmgr *hwmgr,
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to upload PPtable!", return result);
 
-	data->apply_optimized_settings = false;
-	data->apply_overdrive_next_settings_mask = 0;
+	vega10_update_avfs(hwmgr);
+
+	data->need_update_dpm_table &= DPMTABLE_OD_UPDATE_VDDC;
 
 	return 0;
 }
@@ -3793,16 +3581,18 @@ static uint32_t vega10_dpm_get_mclk(struct pp_hwmgr *hwmgr, bool low)
 }
 
 static int vega10_get_gpu_power(struct pp_hwmgr *hwmgr,
-		struct pp_gpu_power *query)
+		uint32_t *query)
 {
 	uint32_t value;
 
+	if (!query)
+		return -EINVAL;
+
 	smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrPkgPwr);
 	value = smum_get_argument(hwmgr);
 
-	/* power value is an integer */
-	memset(query, 0, sizeof *query);
-	query->average_gpu_power = value << 8;
+	/* SMC returning actual watts, keep consistent with legacy asics, low 8 bit as 8 fractional bits */
+	*query = value << 8;
 
 	return 0;
 }
@@ -3810,22 +3600,18 @@ static int vega10_get_gpu_power(struct pp_hwmgr *hwmgr,
 static int vega10_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 			      void *value, int *size)
 {
-	uint32_t sclk_idx, mclk_idx, activity_percent = 0;
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t sclk_mhz, mclk_idx, activity_percent = 0;
 	struct vega10_hwmgr *data = hwmgr->backend;
 	struct vega10_dpm_table *dpm_table = &data->dpm_table;
 	int ret = 0;
-	uint32_t reg, val_vid;
+	uint32_t val_vid;
 
 	switch (idx) {
 	case AMDGPU_PP_SENSOR_GFX_SCLK:
-		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex);
-		sclk_idx = smum_get_argument(hwmgr);
-		if (sclk_idx <  dpm_table->gfx_table.count) {
-			*((uint32_t *)value) = dpm_table->gfx_table.dpm_levels[sclk_idx].value;
-			*size = 4;
-		} else {
-			ret = -EINVAL;
-		}
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetAverageGfxclkActualFrequency);
+		sclk_mhz = smum_get_argument(hwmgr);
+		*((uint32_t *)value) = sclk_mhz * 100;
 		break;
 	case AMDGPU_PP_SENSOR_GFX_MCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex);
@@ -3856,18 +3642,10 @@ static int vega10_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		break;
 	case AMDGPU_PP_SENSOR_GPU_POWER:
-		if (*size < sizeof(struct pp_gpu_power))
-			ret = -EINVAL;
-		else {
-			*size = sizeof(struct pp_gpu_power);
-			ret = vega10_get_gpu_power(hwmgr, (struct pp_gpu_power *)value);
-		}
+		ret = vega10_get_gpu_power(hwmgr, (uint32_t *)value);
 		break;
 	case AMDGPU_PP_SENSOR_VDDGFX:
-		reg = soc15_get_register_offset(SMUIO_HWID, 0,
-			mmSMUSVI0_PLANE0_CURRENTVID_BASE_IDX,
-			mmSMUSVI0_PLANE0_CURRENTVID);
-		val_vid = (cgs_read_register(hwmgr->device, reg) &
+		val_vid = (RREG32_SOC15(SMUIO, 0, mmSMUSVI0_PLANE0_CURRENTVID) &
 			SMUSVI0_PLANE0_CURRENTVID__CURRENT_SVI0_PLANE0_VID_MASK) >>
 			SMUSVI0_PLANE0_CURRENTVID__CURRENT_SVI0_PLANE0_VID__SHIFT;
 		*((uint32_t *)value) = (uint32_t)convert_to_vddc((uint8_t)val_vid);
@@ -3956,26 +3734,18 @@ static int vega10_notify_smc_display_config_after_ps_adjustment(
 			(struct phm_ppt_v2_information *)hwmgr->pptable;
 	struct phm_ppt_v1_clock_voltage_dependency_table *mclk_table = table_info->vdd_dep_on_mclk;
 	uint32_t idx;
-	uint32_t num_active_disps = 0;
-	struct cgs_display_info info = {0};
 	struct PP_Clocks min_clocks = {0};
 	uint32_t i;
 	struct pp_display_clock_request clock_req;
 
-	info.mode_info = NULL;
-
-	cgs_get_active_displays_info(hwmgr->device, &info);
-
-	num_active_disps = info.display_count;
-
-	if (num_active_disps > 1)
+	if (hwmgr->display_config->num_display > 1)
 		vega10_notify_smc_display_change(hwmgr, false);
 	else
 		vega10_notify_smc_display_change(hwmgr, true);
 
-	min_clocks.dcefClock = hwmgr->display_config.min_dcef_set_clk;
-	min_clocks.dcefClockInSR = hwmgr->display_config.min_dcef_deep_sleep_set_clk;
-	min_clocks.memoryClock = hwmgr->display_config.min_mem_set_clock;
+	min_clocks.dcefClock = hwmgr->display_config->min_dcef_set_clk;
+	min_clocks.dcefClockInSR = hwmgr->display_config->min_dcef_deep_sleep_set_clk;
+	min_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock;
 
 	for (i = 0; i < dpm_table->count; i++) {
 		if (dpm_table->dpm_levels[i].value == min_clocks.dcefClock)
@@ -4120,6 +3890,47 @@ static void vega10_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 	}
 }
 
+static int vega10_force_clock_level(struct pp_hwmgr *hwmgr,
+		enum pp_clock_type type, uint32_t mask)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+
+	switch (type) {
+	case PP_SCLK:
+		data->smc_state_table.gfx_boot_level = mask ? (ffs(mask) - 1) : 0;
+		data->smc_state_table.gfx_max_level = mask ? (fls(mask) - 1) : 0;
+
+		PP_ASSERT_WITH_CODE(!vega10_upload_dpm_bootup_level(hwmgr),
+			"Failed to upload boot level to lowest!",
+			return -EINVAL);
+
+		PP_ASSERT_WITH_CODE(!vega10_upload_dpm_max_level(hwmgr),
+			"Failed to upload dpm max level to highest!",
+			return -EINVAL);
+		break;
+
+	case PP_MCLK:
+		data->smc_state_table.mem_boot_level = mask ? (ffs(mask) - 1) : 0;
+		data->smc_state_table.mem_max_level = mask ? (fls(mask) - 1) : 0;
+
+		PP_ASSERT_WITH_CODE(!vega10_upload_dpm_bootup_level(hwmgr),
+			"Failed to upload boot level to lowest!",
+			return -EINVAL);
+
+		PP_ASSERT_WITH_CODE(!vega10_upload_dpm_max_level(hwmgr),
+			"Failed to upload dpm max level to highest!",
+			return -EINVAL);
+
+		break;
+
+	case PP_PCIE:
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int vega10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 				enum amd_dpm_forced_level level)
 {
@@ -4356,97 +4167,15 @@ static int vega10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 	struct vega10_hwmgr *data = hwmgr->backend;
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
 	int result = 0;
-	uint32_t i;
 
 	if (!data->registry_data.disable_water_mark) {
-		for (i = 0; i < wm_with_clock_ranges->num_wm_sets_dmif; i++) {
-			table->WatermarkRow[WM_DCEFCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_dcefclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_dcefclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].WmSetting = (uint8_t)
-					wm_with_clock_ranges->wm_sets_dmif[i].wm_set_id;
-		}
-
-		for (i = 0; i < wm_with_clock_ranges->num_wm_sets_mcif; i++) {
-			table->WatermarkRow[WM_SOCCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_socclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_socclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].WmSetting = (uint8_t)
-					wm_with_clock_ranges->wm_sets_mcif[i].wm_set_id;
-		}
+		smu_set_watermarks_for_clocks_ranges(table, wm_with_clock_ranges);
 		data->water_marks_bitmap = WaterMarksExist;
 	}
 
 	return result;
 }
 
-static int vega10_force_clock_level(struct pp_hwmgr *hwmgr,
-		enum pp_clock_type type, uint32_t mask)
-{
-	struct vega10_hwmgr *data = hwmgr->backend;
-
-	switch (type) {
-	case PP_SCLK:
-		data->smc_state_table.gfx_boot_level = mask ? (ffs(mask) - 1) : 0;
-		data->smc_state_table.gfx_max_level = mask ? (fls(mask) - 1) : 0;
-
-		PP_ASSERT_WITH_CODE(!vega10_upload_dpm_bootup_level(hwmgr),
-			"Failed to upload boot level to lowest!",
-			return -EINVAL);
-
-		PP_ASSERT_WITH_CODE(!vega10_upload_dpm_max_level(hwmgr),
-			"Failed to upload dpm max level to highest!",
-			return -EINVAL);
-		break;
-
-	case PP_MCLK:
-		data->smc_state_table.mem_boot_level = mask ? (ffs(mask) - 1) : 0;
-		data->smc_state_table.mem_max_level = mask ? (fls(mask) - 1) : 0;
-
-		PP_ASSERT_WITH_CODE(!vega10_upload_dpm_bootup_level(hwmgr),
-			"Failed to upload boot level to lowest!",
-			return -EINVAL);
-
-		PP_ASSERT_WITH_CODE(!vega10_upload_dpm_max_level(hwmgr),
-			"Failed to upload dpm max level to highest!",
-			return -EINVAL);
-
-		break;
-
-	case PP_PCIE:
-	default:
-		break;
-	}
-
-	return 0;
-}
-
 static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, char *buf)
 {
@@ -4454,6 +4183,8 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct vega10_single_dpm_table *sclk_table = &(data->dpm_table.gfx_table);
 	struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table);
 	struct vega10_pcie_table *pcie_table = &(data->dpm_table.pcie_table);
+	struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep = NULL;
+
 	int i, now, size = 0;
 
 	switch (type) {
@@ -4492,6 +4223,40 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 					(pcie_table->pcie_gen[i] == 2) ? "8.0GT/s, x16" : "",
 					(i == now) ? "*" : "");
 		break;
+	case OD_SCLK:
+		if (hwmgr->od_enabled) {
+			size = sprintf(buf, "%s:\n", "OD_SCLK");
+			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
+			for (i = 0; i < podn_vdd_dep->count; i++)
+				size += sprintf(buf + size, "%d: %10uMhz %10umV\n",
+					i, podn_vdd_dep->entries[i].clk / 100,
+						podn_vdd_dep->entries[i].vddc);
+		}
+		break;
+	case OD_MCLK:
+		if (hwmgr->od_enabled) {
+			size = sprintf(buf, "%s:\n", "OD_MCLK");
+			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
+			for (i = 0; i < podn_vdd_dep->count; i++)
+				size += sprintf(buf + size, "%d: %10uMhz %10umV\n",
+					i, podn_vdd_dep->entries[i].clk/100,
+						podn_vdd_dep->entries[i].vddc);
+		}
+		break;
+	case OD_RANGE:
+		if (hwmgr->od_enabled) {
+			size = sprintf(buf, "%s:\n", "OD_RANGE");
+			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
+				data->golden_dpm_table.gfx_table.dpm_levels[0].value/100,
+				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
+			size += sprintf(buf + size, "MCLK: %7uMHz %10uMHz\n",
+				data->golden_dpm_table.mem_table.dpm_levels[0].value/100,
+				hwmgr->platform_descriptor.overdriveLimit.memoryClock/100);
+			size += sprintf(buf + size, "VDDC: %7umV %11umV\n",
+				data->odn_dpm_table.min_vddc,
+				data->odn_dpm_table.max_vddc);
+		}
+		break;
 	default:
 		break;
 	}
@@ -4501,10 +4266,8 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 static int vega10_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
-	int result = 0;
-	uint32_t num_turned_on_displays = 1;
 	Watermarks_t *wm_table = &(data->smc_state_table.water_marks_table);
-	struct cgs_display_info info = {0};
+	int result = 0;
 
 	if ((data->water_marks_bitmap & WaterMarksExist) &&
 			!(data->water_marks_bitmap & WaterMarksLoaded)) {
@@ -4514,10 +4277,8 @@ static int vega10_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 	}
 
 	if (data->water_marks_bitmap & WaterMarksLoaded) {
-		cgs_get_active_displays_info(hwmgr->device, &info);
-		num_turned_on_displays = info.display_count;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_NumOfDisplays, num_turned_on_displays);
+			PPSMC_MSG_NumOfDisplays, hwmgr->display_config->num_display);
 	}
 
 	return result;
@@ -4603,15 +4364,12 @@ vega10_check_smc_update_required_for_display_configuration(struct pp_hwmgr *hwmg
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
 	bool is_update_required = false;
-	struct cgs_display_info info = {0, 0, NULL};
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
-
-	if (data->display_timing.num_existing_displays != info.display_count)
+	if (data->display_timing.num_existing_displays != hwmgr->display_config->num_display)
 		is_update_required = true;
 
 	if (PP_CAP(PHM_PlatformCaps_SclkDeepSleep)) {
-		if (data->display_timing.min_clock_in_sr != hwmgr->display_config.min_core_set_clock_in_sr)
+		if (data->display_timing.min_clock_in_sr != hwmgr->display_config->min_core_set_clock_in_sr)
 			is_update_required = true;
 	}
 
@@ -4886,6 +4644,200 @@ static int vega10_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui
 	return 0;
 }
 
+
+static bool vega10_check_clk_voltage_valid(struct pp_hwmgr *hwmgr,
+					enum PP_OD_DPM_TABLE_COMMAND type,
+					uint32_t clk,
+					uint32_t voltage)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
+	struct vega10_single_dpm_table *golden_table;
+
+	if (voltage < odn_table->min_vddc || voltage > odn_table->max_vddc) {
+		pr_info("OD voltage is out of range [%d - %d] mV\n", odn_table->min_vddc, odn_table->max_vddc);
+		return false;
+	}
+
+	if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
+		golden_table = &(data->golden_dpm_table.gfx_table);
+		if (golden_table->dpm_levels[0].value > clk ||
+			hwmgr->platform_descriptor.overdriveLimit.engineClock < clk) {
+			pr_info("OD engine clock is out of range [%d - %d] MHz\n",
+				golden_table->dpm_levels[0].value/100,
+				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
+			return false;
+		}
+	} else if (type == PP_OD_EDIT_MCLK_VDDC_TABLE) {
+		golden_table = &(data->golden_dpm_table.mem_table);
+		if (golden_table->dpm_levels[0].value > clk ||
+			hwmgr->platform_descriptor.overdriveLimit.memoryClock < clk) {
+			pr_info("OD memory clock is out of range [%d - %d] MHz\n",
+				golden_table->dpm_levels[0].value/100,
+				hwmgr->platform_descriptor.overdriveLimit.memoryClock/100);
+			return false;
+		}
+	} else {
+		return false;
+	}
+
+	return true;
+}
+
+static void vega10_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
+	struct phm_ppt_v2_information *table_info = hwmgr->pptable;
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
+	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
+	uint32_t i;
+
+	dep_table = table_info->vdd_dep_on_mclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_mclk);
+
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
+			return;
+		}
+	}
+
+	dep_table = table_info->vdd_dep_on_sclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_sclk);
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
+			return;
+		}
+	}
+
+	if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
+		data->need_update_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
+	}
+}
+
+static void vega10_odn_update_soc_table(struct pp_hwmgr *hwmgr,
+						enum PP_OD_DPM_TABLE_COMMAND type)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	struct phm_ppt_v2_information *table_info = hwmgr->pptable;
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table = table_info->vdd_dep_on_socclk;
+	struct vega10_single_dpm_table *dpm_table = &data->golden_dpm_table.soc_table;
+
+	struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep_on_socclk =
+							&data->odn_dpm_table.vdd_dep_on_socclk;
+	struct vega10_odn_vddc_lookup_table *od_vddc_lookup_table = &data->odn_dpm_table.vddc_lookup_table;
+
+	struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep;
+	uint8_t i, j;
+
+	if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
+		podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
+		for (i = 0; i < podn_vdd_dep->count - 1; i++)
+			od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
+		if (od_vddc_lookup_table->entries[i].us_vdd < podn_vdd_dep->entries[i].vddc)
+			od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
+	} else if (type == PP_OD_EDIT_MCLK_VDDC_TABLE) {
+		podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
+		for (i = 0; i < dpm_table->count; i++) {
+			for (j = 0; j < od_vddc_lookup_table->count; j++) {
+				if (od_vddc_lookup_table->entries[j].us_vdd >
+					podn_vdd_dep->entries[i].vddc)
+					break;
+			}
+			if (j == od_vddc_lookup_table->count) {
+				od_vddc_lookup_table->entries[j-1].us_vdd =
+					podn_vdd_dep->entries[i].vddc;
+				data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
+			}
+			podn_vdd_dep->entries[i].vddInd = j;
+		}
+		dpm_table = &data->dpm_table.soc_table;
+		for (i = 0; i < dep_table->count; i++) {
+			if (dep_table->entries[i].vddInd == podn_vdd_dep->entries[dep_table->count-1].vddInd &&
+					dep_table->entries[i].clk < podn_vdd_dep->entries[dep_table->count-1].clk) {
+				data->need_update_dpm_table |= DPMTABLE_UPDATE_SOCCLK;
+				podn_vdd_dep_on_socclk->entries[i].clk = podn_vdd_dep->entries[dep_table->count-1].clk;
+				dpm_table->dpm_levels[i].value = podn_vdd_dep_on_socclk->entries[i].clk;
+			}
+		}
+		if (podn_vdd_dep_on_socclk->entries[podn_vdd_dep_on_socclk->count - 1].clk <
+					podn_vdd_dep->entries[dep_table->count-1].clk) {
+			data->need_update_dpm_table |= DPMTABLE_UPDATE_SOCCLK;
+			podn_vdd_dep_on_socclk->entries[podn_vdd_dep_on_socclk->count - 1].clk = podn_vdd_dep->entries[dep_table->count-1].clk;
+			dpm_table->dpm_levels[podn_vdd_dep_on_socclk->count - 1].value = podn_vdd_dep->entries[dep_table->count-1].clk;
+		}
+		if (podn_vdd_dep_on_socclk->entries[podn_vdd_dep_on_socclk->count - 1].vddInd <
+					podn_vdd_dep->entries[dep_table->count-1].vddInd) {
+			data->need_update_dpm_table |= DPMTABLE_UPDATE_SOCCLK;
+			podn_vdd_dep_on_socclk->entries[podn_vdd_dep_on_socclk->count - 1].vddInd = podn_vdd_dep->entries[dep_table->count-1].vddInd;
+		}
+	}
+}
+
+static int vega10_odn_edit_dpm_table(struct pp_hwmgr *hwmgr,
+					enum PP_OD_DPM_TABLE_COMMAND type,
+					long *input, uint32_t size)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep_table;
+	struct vega10_single_dpm_table *dpm_table;
+
+	uint32_t input_clk;
+	uint32_t input_vol;
+	uint32_t input_level;
+	uint32_t i;
+
+	PP_ASSERT_WITH_CODE(input, "NULL user input for clock and voltage",
+				return -EINVAL);
+
+	if (!hwmgr->od_enabled) {
+		pr_info("OverDrive feature not enabled\n");
+		return -EINVAL;
+	}
+
+	if (PP_OD_EDIT_SCLK_VDDC_TABLE == type) {
+		dpm_table = &data->dpm_table.gfx_table;
+		podn_vdd_dep_table = &data->odn_dpm_table.vdd_dep_on_sclk;
+		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
+	} else if (PP_OD_EDIT_MCLK_VDDC_TABLE == type) {
+		dpm_table = &data->dpm_table.mem_table;
+		podn_vdd_dep_table = &data->odn_dpm_table.vdd_dep_on_mclk;
+		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
+	} else if (PP_OD_RESTORE_DEFAULT_TABLE == type) {
+		memcpy(&(data->dpm_table), &(data->golden_dpm_table), sizeof(struct vega10_dpm_table));
+		vega10_odn_initial_default_setting(hwmgr);
+		return 0;
+	} else if (PP_OD_COMMIT_DPM_TABLE == type) {
+		vega10_check_dpm_table_updated(hwmgr);
+		return 0;
+	} else {
+		return -EINVAL;
+	}
+
+	for (i = 0; i < size; i += 3) {
+		if (i + 3 > size || input[i] >= podn_vdd_dep_table->count) {
+			pr_info("invalid clock voltage input\n");
+			return 0;
+		}
+		input_level = input[i];
+		input_clk = input[i+1] * 100;
+		input_vol = input[i+2];
+
+		if (vega10_check_clk_voltage_valid(hwmgr, type, input_clk, input_vol)) {
+			dpm_table->dpm_levels[input_level].value = input_clk;
+			podn_vdd_dep_table->entries[input_level].clk = input_clk;
+			podn_vdd_dep_table->entries[input_level].vddc = input_vol;
+		} else {
+			return -EINVAL;
+		}
+	}
+	vega10_odn_update_soc_table(hwmgr, type);
+	return 0;
+}
+
 static const struct pp_hwmgr_func vega10_hwmgr_funcs = {
 	.backend_init = vega10_hwmgr_backend_init,
 	.backend_fini = vega10_hwmgr_backend_fini,
@@ -4944,6 +4896,7 @@ static const struct pp_hwmgr_func vega10_hwmgr_funcs = {
 	.get_power_profile_mode = vega10_get_power_profile_mode,
 	.set_power_profile_mode = vega10_set_power_profile_mode,
 	.set_power_limit = vega10_set_power_limit,
+	.odn_edit_dpm_table = vega10_odn_edit_dpm_table,
 };
 
 int vega10_enable_smc_features(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
index 5339ea1f3dce..aadd6cbc7e85 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
@@ -282,15 +282,21 @@ struct vega10_registry_data {
 
 struct vega10_odn_clock_voltage_dependency_table {
 	uint32_t count;
-	struct phm_ppt_v1_clock_voltage_dependency_record
-		entries[MAX_REGULAR_DPM_NUMBER];
+	struct phm_ppt_v1_clock_voltage_dependency_record entries[MAX_REGULAR_DPM_NUMBER];
+};
+
+struct vega10_odn_vddc_lookup_table {
+	uint32_t count;
+	struct phm_ppt_v1_voltage_lookup_record entries[MAX_REGULAR_DPM_NUMBER];
 };
 
 struct vega10_odn_dpm_table {
-	struct phm_odn_clock_levels		odn_core_clock_dpm_levels;
-	struct phm_odn_clock_levels		odn_memory_clock_dpm_levels;
-	struct vega10_odn_clock_voltage_dependency_table		vdd_dependency_on_sclk;
-	struct vega10_odn_clock_voltage_dependency_table		vdd_dependency_on_mclk;
+	struct vega10_odn_clock_voltage_dependency_table vdd_dep_on_sclk;
+	struct vega10_odn_clock_voltage_dependency_table vdd_dep_on_mclk;
+	struct vega10_odn_clock_voltage_dependency_table vdd_dep_on_socclk;
+	struct vega10_odn_vddc_lookup_table vddc_lookup_table;
+	uint32_t max_vddc;
+	uint32_t min_vddc;
 };
 
 struct vega10_odn_fan_table {
@@ -301,8 +307,8 @@ struct vega10_odn_fan_table {
 };
 
 struct vega10_hwmgr {
-	struct vega10_dpm_table			dpm_table;
-	struct vega10_dpm_table			golden_dpm_table;
+	struct vega10_dpm_table          dpm_table;
+	struct vega10_dpm_table          golden_dpm_table;
 	struct vega10_registry_data      registry_data;
 	struct vega10_vbios_boot_state   vbios_boot_state;
 	struct vega10_mclk_latency_table mclk_latency_table;
@@ -368,12 +374,8 @@ struct vega10_hwmgr {
 	bool                           need_long_memory_training;
 
 	/* Internal settings to apply the application power optimization parameters */
-	bool                           apply_optimized_settings;
 	uint32_t                       disable_dpm_mask;
 
-	/* ---- Overdrive next setting ---- */
-	uint32_t                       apply_overdrive_next_settings_mask;
-
 	/* ---- SMU9 ---- */
 	struct smu_features            smu_features[GNLD_FEATURES_MAX];
 	struct vega10_smc_state_table  smc_state_table;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
index ba63faefc61f..a9efd8554fbc 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
@@ -27,7 +27,7 @@
 #include "vega10_ppsmc.h"
 #include "vega10_inc.h"
 #include "pp_debug.h"
-#include "pp_soc15.h"
+#include "soc15_common.h"
 
 static const struct vega10_didt_config_reg SEDiDtTuningCtrlConfig_Vega10[] =
 {
@@ -888,36 +888,36 @@ static void vega10_didt_set_mask(struct pp_hwmgr *hwmgr, const bool enable)
 	if (PP_CAP(PHM_PlatformCaps_DiDtEDCEnable)) {
 		if (PP_CAP(PHM_PlatformCaps_SQRamping)) {
 			data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_SQ_EDC_CTRL);
-			data = CGS_REG_SET_FIELD(data, DIDT_SQ_EDC_CTRL, EDC_EN, en);
-			data = CGS_REG_SET_FIELD(data, DIDT_SQ_EDC_CTRL, EDC_SW_RST, ~en);
+			data = REG_SET_FIELD(data, DIDT_SQ_EDC_CTRL, EDC_EN, en);
+			data = REG_SET_FIELD(data, DIDT_SQ_EDC_CTRL, EDC_SW_RST, ~en);
 			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_SQ_EDC_CTRL, data);
 		}
 
 		if (PP_CAP(PHM_PlatformCaps_DBRamping)) {
 			data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DB_EDC_CTRL);
-			data = CGS_REG_SET_FIELD(data, DIDT_DB_EDC_CTRL, EDC_EN, en);
-			data = CGS_REG_SET_FIELD(data, DIDT_DB_EDC_CTRL, EDC_SW_RST, ~en);
+			data = REG_SET_FIELD(data, DIDT_DB_EDC_CTRL, EDC_EN, en);
+			data = REG_SET_FIELD(data, DIDT_DB_EDC_CTRL, EDC_SW_RST, ~en);
 			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DB_EDC_CTRL, data);
 		}
 
 		if (PP_CAP(PHM_PlatformCaps_TDRamping)) {
 			data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TD_EDC_CTRL);
-			data = CGS_REG_SET_FIELD(data, DIDT_TD_EDC_CTRL, EDC_EN, en);
-			data = CGS_REG_SET_FIELD(data, DIDT_TD_EDC_CTRL, EDC_SW_RST, ~en);
+			data = REG_SET_FIELD(data, DIDT_TD_EDC_CTRL, EDC_EN, en);
+			data = REG_SET_FIELD(data, DIDT_TD_EDC_CTRL, EDC_SW_RST, ~en);
 			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TD_EDC_CTRL, data);
 		}
 
 		if (PP_CAP(PHM_PlatformCaps_TCPRamping)) {
 			data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TCP_EDC_CTRL);
-			data = CGS_REG_SET_FIELD(data, DIDT_TCP_EDC_CTRL, EDC_EN, en);
-			data = CGS_REG_SET_FIELD(data, DIDT_TCP_EDC_CTRL, EDC_SW_RST, ~en);
+			data = REG_SET_FIELD(data, DIDT_TCP_EDC_CTRL, EDC_EN, en);
+			data = REG_SET_FIELD(data, DIDT_TCP_EDC_CTRL, EDC_SW_RST, ~en);
 			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TCP_EDC_CTRL, data);
 		}
 
 		if (PP_CAP(PHM_PlatformCaps_DBRRamping)) {
 			data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DBR_EDC_CTRL);
-			data = CGS_REG_SET_FIELD(data, DIDT_DBR_EDC_CTRL, EDC_EN, en);
-			data = CGS_REG_SET_FIELD(data, DIDT_DBR_EDC_CTRL, EDC_SW_RST, ~en);
+			data = REG_SET_FIELD(data, DIDT_DBR_EDC_CTRL, EDC_EN, en);
+			data = REG_SET_FIELD(data, DIDT_DBR_EDC_CTRL, EDC_SW_RST, ~en);
 			cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DBR_EDC_CTRL, data);
 		}
 	}
@@ -930,20 +930,18 @@ static void vega10_didt_set_mask(struct pp_hwmgr *hwmgr, const bool enable)
 
 static int vega10_enable_cac_driving_se_didt_config(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int result;
 	uint32_t num_se = 0, count, data;
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
 
 	num_se = adev->gfx.config.max_shader_engines;
 
-	cgs_enter_safe_mode(hwmgr->device, true);
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
-	cgs_lock_grbm_idx(hwmgr->device, true);
-	reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX);
+	mutex_lock(&adev->grbm_idx_mutex);
 	for (count = 0; count < num_se; count++) {
 		data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT);
-		cgs_write_register(hwmgr->device, reg, data);
+		WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, data);
 
 		result =  vega10_program_didt_config_registers(hwmgr, SEDiDtStallCtrlConfig_vega10, VEGA10_CONFIGREG_DIDT);
 		result |= vega10_program_didt_config_registers(hwmgr, SEDiDtStallPatternConfig_vega10, VEGA10_CONFIGREG_DIDT);
@@ -958,43 +956,43 @@ static int vega10_enable_cac_driving_se_didt_config(struct pp_hwmgr *hwmgr)
 		if (0 != result)
 			break;
 	}
-	cgs_write_register(hwmgr->device, reg, 0xE0000000);
-	cgs_lock_grbm_idx(hwmgr->device, false);
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xE0000000);
+	mutex_unlock(&adev->grbm_idx_mutex);
 
 	vega10_didt_set_mask(hwmgr, true);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	return 0;
 }
 
 static int vega10_disable_cac_driving_se_didt_config(struct pp_hwmgr *hwmgr)
 {
-	cgs_enter_safe_mode(hwmgr->device, true);
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
 	vega10_didt_set_mask(hwmgr, false);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	return 0;
 }
 
 static int vega10_enable_psm_gc_didt_config(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int result;
 	uint32_t num_se = 0, count, data;
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
 
 	num_se = adev->gfx.config.max_shader_engines;
 
-	cgs_enter_safe_mode(hwmgr->device, true);
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
-	cgs_lock_grbm_idx(hwmgr->device, true);
-	reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX);
+	mutex_lock(&adev->grbm_idx_mutex);
 	for (count = 0; count < num_se; count++) {
 		data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT);
-		cgs_write_register(hwmgr->device, reg, data);
+		WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, data);
 
 		result = vega10_program_didt_config_registers(hwmgr, SEDiDtStallCtrlConfig_vega10, VEGA10_CONFIGREG_DIDT);
 		result |= vega10_program_didt_config_registers(hwmgr, SEDiDtStallPatternConfig_vega10, VEGA10_CONFIGREG_DIDT);
@@ -1003,12 +1001,12 @@ static int vega10_enable_psm_gc_didt_config(struct pp_hwmgr *hwmgr)
 		if (0 != result)
 			break;
 	}
-	cgs_write_register(hwmgr->device, reg, 0xE0000000);
-	cgs_lock_grbm_idx(hwmgr->device, false);
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xE0000000);
+	mutex_unlock(&adev->grbm_idx_mutex);
 
 	vega10_didt_set_mask(hwmgr, true);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	vega10_program_gc_didt_config_registers(hwmgr, GCDiDtDroopCtrlConfig_vega10);
 	if (PP_CAP(PHM_PlatformCaps_GCEDC))
@@ -1022,13 +1020,14 @@ static int vega10_enable_psm_gc_didt_config(struct pp_hwmgr *hwmgr)
 
 static int vega10_disable_psm_gc_didt_config(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t data;
 
-	cgs_enter_safe_mode(hwmgr->device, true);
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
 	vega10_didt_set_mask(hwmgr, false);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	if (PP_CAP(PHM_PlatformCaps_GCEDC)) {
 		data = 0x00000000;
@@ -1043,20 +1042,18 @@ static int vega10_disable_psm_gc_didt_config(struct pp_hwmgr *hwmgr)
 
 static int vega10_enable_se_edc_config(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int result;
 	uint32_t num_se = 0, count, data;
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
 
 	num_se = adev->gfx.config.max_shader_engines;
 
-	cgs_enter_safe_mode(hwmgr->device, true);
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
-	cgs_lock_grbm_idx(hwmgr->device, true);
-	reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX);
+	mutex_lock(&adev->grbm_idx_mutex);
 	for (count = 0; count < num_se; count++) {
 		data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT);
-		cgs_write_register(hwmgr->device, reg, data);
+		WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, data);
 		result = vega10_program_didt_config_registers(hwmgr, SEDiDtWeightConfig_Vega10, VEGA10_CONFIGREG_DIDT);
 		result |= vega10_program_didt_config_registers(hwmgr, SEEDCStallPatternConfig_Vega10, VEGA10_CONFIGREG_DIDT);
 		result |= vega10_program_didt_config_registers(hwmgr, SEEDCStallDelayConfig_Vega10, VEGA10_CONFIGREG_DIDT);
@@ -1067,46 +1064,46 @@ static int vega10_enable_se_edc_config(struct pp_hwmgr *hwmgr)
 		if (0 != result)
 			break;
 	}
-	cgs_write_register(hwmgr->device, reg, 0xE0000000);
-	cgs_lock_grbm_idx(hwmgr->device, false);
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xE0000000);
+	mutex_unlock(&adev->grbm_idx_mutex);
 
 	vega10_didt_set_mask(hwmgr, true);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	return 0;
 }
 
 static int vega10_disable_se_edc_config(struct pp_hwmgr *hwmgr)
 {
-	cgs_enter_safe_mode(hwmgr->device, true);
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
 	vega10_didt_set_mask(hwmgr, false);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	return 0;
 }
 
 static int vega10_enable_psm_gc_edc_config(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int result;
 	uint32_t num_se = 0;
 	uint32_t count, data;
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
 
 	num_se = adev->gfx.config.max_shader_engines;
 
-	cgs_enter_safe_mode(hwmgr->device, true);
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
 	vega10_program_gc_didt_config_registers(hwmgr, AvfsPSMResetConfig_vega10);
 
-	cgs_lock_grbm_idx(hwmgr->device, true);
-	reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX);
+	mutex_lock(&adev->grbm_idx_mutex);
 	for (count = 0; count < num_se; count++) {
 		data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT);
-		cgs_write_register(hwmgr->device, reg, data);
+		WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, data);
 		result |= vega10_program_didt_config_registers(hwmgr, PSMSEEDCStallPatternConfig_Vega10, VEGA10_CONFIGREG_DIDT);
 		result |= vega10_program_didt_config_registers(hwmgr, PSMSEEDCStallDelayConfig_Vega10, VEGA10_CONFIGREG_DIDT);
 		result |= vega10_program_didt_config_registers(hwmgr, PSMSEEDCCtrlResetConfig_Vega10, VEGA10_CONFIGREG_DIDT);
@@ -1115,12 +1112,12 @@ static int vega10_enable_psm_gc_edc_config(struct pp_hwmgr *hwmgr)
 		if (0 != result)
 			break;
 	}
-	cgs_write_register(hwmgr->device, reg, 0xE0000000);
-	cgs_lock_grbm_idx(hwmgr->device, false);
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xE0000000);
+	mutex_unlock(&adev->grbm_idx_mutex);
 
 	vega10_didt_set_mask(hwmgr, true);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	vega10_program_gc_didt_config_registers(hwmgr, PSMGCEDCDroopCtrlConfig_vega10);
 
@@ -1137,13 +1134,14 @@ static int vega10_enable_psm_gc_edc_config(struct pp_hwmgr *hwmgr)
 
 static int vega10_disable_psm_gc_edc_config(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t data;
 
-	cgs_enter_safe_mode(hwmgr->device, true);
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
 	vega10_didt_set_mask(hwmgr, false);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	if (PP_CAP(PHM_PlatformCaps_GCEDC)) {
 		data = 0x00000000;
@@ -1158,15 +1156,14 @@ static int vega10_disable_psm_gc_edc_config(struct pp_hwmgr *hwmgr)
 
 static int vega10_enable_se_edc_force_stall_config(struct pp_hwmgr *hwmgr)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 	int result;
 
-	cgs_enter_safe_mode(hwmgr->device, true);
+	adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
-	cgs_lock_grbm_idx(hwmgr->device, true);
-	reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX);
-	cgs_write_register(hwmgr->device, reg, 0xE0000000);
-	cgs_lock_grbm_idx(hwmgr->device, false);
+	mutex_lock(&adev->grbm_idx_mutex);
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xE0000000);
+	mutex_unlock(&adev->grbm_idx_mutex);
 
 	result = vega10_program_didt_config_registers(hwmgr, SEEDCForceStallPatternConfig_Vega10, VEGA10_CONFIGREG_DIDT);
 	result |= vega10_program_didt_config_registers(hwmgr, SEEDCCtrlForceStallConfig_Vega10, VEGA10_CONFIGREG_DIDT);
@@ -1175,7 +1172,7 @@ static int vega10_enable_se_edc_force_stall_config(struct pp_hwmgr *hwmgr)
 
 	vega10_didt_set_mask(hwmgr, false);
 
-	cgs_enter_safe_mode(hwmgr->device, false);
+	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c
index c61d0744860d..0768d259c07c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_processpptables.c
@@ -52,7 +52,7 @@ static const void *get_powerplay_table(struct pp_hwmgr *hwmgr)
 
 	if (!table_address) {
 		table_address = (ATOM_Vega10_POWERPLAYTABLE *)
-				cgs_atom_get_data_table(hwmgr->device, index,
+				smu_atom_get_data_table(hwmgr->adev, index,
 						&size, &frev, &crev);
 
 		hwmgr->soft_pp_table = table_address;	/*Cache the result in RAM.*/
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
index 9f18226a56ea..aa044c1955fe 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
@@ -25,7 +25,7 @@
 #include "vega10_hwmgr.h"
 #include "vega10_ppsmc.h"
 #include "vega10_inc.h"
-#include "pp_soc15.h"
+#include "soc15_common.h"
 #include "pp_debug.h"
 
 static int vega10_get_current_rpm(struct pp_hwmgr *hwmgr, uint32_t *current_rpm)
@@ -89,6 +89,7 @@ int vega10_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
 
 int vega10_fan_ctrl_get_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t *speed)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct vega10_hwmgr *data = hwmgr->backend;
 	uint32_t tach_period;
 	uint32_t crystal_clock_freq;
@@ -100,10 +101,8 @@ int vega10_fan_ctrl_get_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t *speed)
 	if (data->smu_features[GNLD_FAN_CONTROL].supported) {
 		result = vega10_get_current_rpm(hwmgr, speed);
 	} else {
-		uint32_t reg = soc15_get_register_offset(THM_HWID, 0,
-				mmCG_TACH_STATUS_BASE_IDX, mmCG_TACH_STATUS);
 		tach_period =
-			CGS_REG_GET_FIELD(cgs_read_register(hwmgr->device, reg),
+			REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_STATUS),
 					  CG_TACH_STATUS,
 					  TACH_PERIOD);
 
@@ -127,26 +126,23 @@ int vega10_fan_ctrl_get_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t *speed)
 */
 int vega10_fan_ctrl_set_static_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 {
-	uint32_t reg;
-
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmCG_FDO_CTRL2_BASE_IDX, mmCG_FDO_CTRL2);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	if (hwmgr->fan_ctrl_is_in_default_mode) {
 		hwmgr->fan_ctrl_default_mode =
-			CGS_REG_GET_FIELD(cgs_read_register(hwmgr->device, reg),
+			REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
 				CG_FDO_CTRL2, FDO_PWM_MODE);
 		hwmgr->tmin =
-			CGS_REG_GET_FIELD(cgs_read_register(hwmgr->device, reg),
+			REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
 				CG_FDO_CTRL2, TMIN);
 		hwmgr->fan_ctrl_is_in_default_mode = false;
 	}
 
-	cgs_write_register(hwmgr->device, reg,
-			CGS_REG_SET_FIELD(cgs_read_register(hwmgr->device, reg),
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2,
+			REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
 				CG_FDO_CTRL2, TMIN, 0));
-	cgs_write_register(hwmgr->device, reg,
-			CGS_REG_SET_FIELD(cgs_read_register(hwmgr->device, reg),
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2,
+			REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
 				CG_FDO_CTRL2, FDO_PWM_MODE, mode));
 
 	return 0;
@@ -159,18 +155,15 @@ int vega10_fan_ctrl_set_static_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 */
 int vega10_fan_ctrl_set_default_mode(struct pp_hwmgr *hwmgr)
 {
-	uint32_t reg;
-
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmCG_FDO_CTRL2_BASE_IDX, mmCG_FDO_CTRL2);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	if (!hwmgr->fan_ctrl_is_in_default_mode) {
-		cgs_write_register(hwmgr->device, reg,
-			CGS_REG_SET_FIELD(cgs_read_register(hwmgr->device, reg),
+		WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2,
+			REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
 				CG_FDO_CTRL2, FDO_PWM_MODE,
 				hwmgr->fan_ctrl_default_mode));
-		cgs_write_register(hwmgr->device, reg,
-			CGS_REG_SET_FIELD(cgs_read_register(hwmgr->device, reg),
+		WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2,
+			REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
 				CG_FDO_CTRL2, TMIN,
 				hwmgr->tmin << CG_FDO_CTRL2__TMIN__SHIFT));
 		hwmgr->fan_ctrl_is_in_default_mode = true;
@@ -257,10 +250,10 @@ int vega10_fan_ctrl_stop_smc_fan_control(struct pp_hwmgr *hwmgr)
 int vega10_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 		uint32_t speed)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t duty100;
 	uint32_t duty;
 	uint64_t tmp64;
-	uint32_t reg;
 
 	if (hwmgr->thermal_controller.fanInfo.bNoFan)
 		return 0;
@@ -271,10 +264,7 @@ int vega10_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
 		vega10_fan_ctrl_stop_smc_fan_control(hwmgr);
 
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmCG_FDO_CTRL1_BASE_IDX, mmCG_FDO_CTRL1);
-
-	duty100 = CGS_REG_GET_FIELD(cgs_read_register(hwmgr->device, reg),
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
 				    CG_FDO_CTRL1, FMAX_DUTY100);
 
 	if (duty100 == 0)
@@ -284,10 +274,8 @@ int vega10_fan_ctrl_set_fan_speed_percent(struct pp_hwmgr *hwmgr,
 	do_div(tmp64, 100);
 	duty = (uint32_t)tmp64;
 
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmCG_FDO_CTRL0_BASE_IDX, mmCG_FDO_CTRL0);
-	cgs_write_register(hwmgr->device, reg,
-		CGS_REG_SET_FIELD(cgs_read_register(hwmgr->device, reg),
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0,
+		REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL0),
 			CG_FDO_CTRL0, FDO_STATIC_DUTY, duty));
 
 	return vega10_fan_ctrl_set_static_mode(hwmgr, FDO_PWM_MODE_STATIC);
@@ -317,10 +305,10 @@ int vega10_fan_ctrl_reset_fan_speed_to_default(struct pp_hwmgr *hwmgr)
 */
 int vega10_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t tach_period;
 	uint32_t crystal_clock_freq;
 	int result = 0;
-	uint32_t reg;
 
 	if (hwmgr->thermal_controller.fanInfo.bNoFan ||
 	    (speed < hwmgr->thermal_controller.fanInfo.ulMinRPM) ||
@@ -333,10 +321,8 @@ int vega10_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 	if (!result) {
 		crystal_clock_freq = amdgpu_asic_get_xclk((struct amdgpu_device *)hwmgr->adev);
 		tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
-		reg = soc15_get_register_offset(THM_HWID, 0,
-				mmCG_TACH_STATUS_BASE_IDX, mmCG_TACH_STATUS);
-		cgs_write_register(hwmgr->device, reg,
-				CGS_REG_SET_FIELD(cgs_read_register(hwmgr->device, reg),
+		WREG32_SOC15(THM, 0, mmCG_TACH_STATUS,
+				REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_STATUS),
 					CG_TACH_STATUS, TACH_PERIOD,
 					tach_period));
 	}
@@ -350,13 +336,10 @@ int vega10_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 */
 int vega10_thermal_get_temperature(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int temp;
-	uint32_t reg;
 
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmCG_MULT_THERMAL_STATUS_BASE_IDX,  mmCG_MULT_THERMAL_STATUS);
-
-	temp = cgs_read_register(hwmgr->device, reg);
+	temp = RREG32_SOC15(THM, 0, mmCG_MULT_THERMAL_STATUS);
 
 	temp = (temp & CG_MULT_THERMAL_STATUS__CTF_TEMP_MASK) >>
 			CG_MULT_THERMAL_STATUS__CTF_TEMP__SHIFT;
@@ -379,11 +362,12 @@ int vega10_thermal_get_temperature(struct pp_hwmgr *hwmgr)
 static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *range)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP *
 			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP *
 			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	uint32_t val, reg;
+	uint32_t val;
 
 	if (low < range->min)
 		low = range->min;
@@ -393,20 +377,17 @@ static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 	if (low > high)
 		return -EINVAL;
 
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmTHM_THERMAL_INT_CTRL_BASE_IDX, mmTHM_THERMAL_INT_CTRL);
-
-	val = cgs_read_register(hwmgr->device, reg);
+	val = RREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL);
 
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
 	val &= (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK) &
 			(~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK) &
 			(~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK);
 
-	cgs_write_register(hwmgr->device, reg, val);
+	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
 
 	return 0;
 }
@@ -418,21 +399,17 @@ static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 */
 static int vega10_thermal_initialize(struct pp_hwmgr *hwmgr)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	if (hwmgr->thermal_controller.fanInfo.ucTachometerPulsesPerRevolution) {
-		reg = soc15_get_register_offset(THM_HWID, 0,
-				mmCG_TACH_CTRL_BASE_IDX, mmCG_TACH_CTRL);
-		cgs_write_register(hwmgr->device, reg,
-			CGS_REG_SET_FIELD(cgs_read_register(hwmgr->device, reg),
+		WREG32_SOC15(THM, 0, mmCG_TACH_CTRL,
+			REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL),
 				CG_TACH_CTRL, EDGE_PER_REV,
 				hwmgr->thermal_controller.fanInfo.ucTachometerPulsesPerRevolution - 1));
 	}
 
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmCG_FDO_CTRL2_BASE_IDX, mmCG_FDO_CTRL2);
-	cgs_write_register(hwmgr->device, reg,
-		CGS_REG_SET_FIELD(cgs_read_register(hwmgr->device, reg),
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL2,
+		REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL2),
 			CG_FDO_CTRL2, TACH_PWM_RESP_RATE, 0x28));
 
 	return 0;
@@ -445,9 +422,9 @@ static int vega10_thermal_initialize(struct pp_hwmgr *hwmgr)
 */
 static int vega10_thermal_enable_alert(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct vega10_hwmgr *data = hwmgr->backend;
 	uint32_t val = 0;
-	uint32_t reg;
 
 	if (data->smu_features[GNLD_FW_CTF].supported) {
 		if (data->smu_features[GNLD_FW_CTF].enabled)
@@ -465,8 +442,7 @@ static int vega10_thermal_enable_alert(struct pp_hwmgr *hwmgr)
 	val |= (1 << THM_THERMAL_INT_ENA__THERM_INTL_CLR__SHIFT);
 	val |= (1 << THM_THERMAL_INT_ENA__THERM_TRIGGER_CLR__SHIFT);
 
-	reg = soc15_get_register_offset(THM_HWID, 0, mmTHM_THERMAL_INT_ENA_BASE_IDX, mmTHM_THERMAL_INT_ENA);
-	cgs_write_register(hwmgr->device, reg, val);
+	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_ENA, val);
 
 	return 0;
 }
@@ -477,8 +453,8 @@ static int vega10_thermal_enable_alert(struct pp_hwmgr *hwmgr)
 */
 int vega10_thermal_disable_alert(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct vega10_hwmgr *data = hwmgr->backend;
-	uint32_t reg;
 
 	if (data->smu_features[GNLD_FW_CTF].supported) {
 		if (!data->smu_features[GNLD_FW_CTF].enabled)
@@ -493,8 +469,7 @@ int vega10_thermal_disable_alert(struct pp_hwmgr *hwmgr)
 		data->smu_features[GNLD_FW_CTF].enabled = false;
 	}
 
-	reg = soc15_get_register_offset(THM_HWID, 0, mmTHM_THERMAL_INT_ENA_BASE_IDX, mmTHM_THERMAL_INT_ENA);
-	cgs_write_register(hwmgr->device, reg, 0);
+	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_ENA, 0);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 200de46bd06b..782e2098824d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -34,7 +34,6 @@
 #include "atomfirmware.h"
 #include "cgs_common.h"
 #include "vega12_inc.h"
-#include "pp_soc15.h"
 #include "pppcielanes.h"
 #include "vega12_hwmgr.h"
 #include "vega12_processpptables.h"
@@ -546,6 +545,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -565,6 +565,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -585,6 +586,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -605,6 +607,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 		return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -625,6 +628,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -645,6 +649,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 		return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -666,6 +671,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -686,6 +692,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -706,6 +713,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -726,6 +734,7 @@ static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			return -EINVAL);
 
 		dpm_table->dpm_levels[i].value = clock;
+		dpm_table->dpm_levels[i].enabled = true;
 	}
 
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
@@ -992,15 +1001,55 @@ static uint32_t vega12_find_highest_dpm_level(
 
 static int vega12_upload_dpm_min_level(struct pp_hwmgr *hwmgr)
 {
+	struct vega12_hwmgr *data = hwmgr->backend;
+	if (data->smc_state_table.gfx_boot_level !=
+			data->dpm_table.gfx_table.dpm_state.soft_min_level) {
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_SetSoftMinByFreq,
+			PPCLK_GFXCLK<<16 | data->dpm_table.gfx_table.dpm_levels[data->smc_state_table.gfx_boot_level].value);
+		data->dpm_table.gfx_table.dpm_state.soft_min_level =
+				data->smc_state_table.gfx_boot_level;
+	}
+
+	if (data->smc_state_table.mem_boot_level !=
+			data->dpm_table.mem_table.dpm_state.soft_min_level) {
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_SetSoftMinByFreq,
+			PPCLK_UCLK<<16 | data->dpm_table.mem_table.dpm_levels[data->smc_state_table.mem_boot_level].value);
+		data->dpm_table.mem_table.dpm_state.soft_min_level =
+				data->smc_state_table.mem_boot_level;
+	}
+
 	return 0;
+
 }
 
 static int vega12_upload_dpm_max_level(struct pp_hwmgr *hwmgr)
 {
+	struct vega12_hwmgr *data = hwmgr->backend;
+	if (data->smc_state_table.gfx_max_level !=
+		data->dpm_table.gfx_table.dpm_state.soft_max_level) {
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_SetSoftMaxByFreq,
+			/* plus the vale by 1 to align the resolution */
+			PPCLK_GFXCLK<<16 | (data->dpm_table.gfx_table.dpm_levels[data->smc_state_table.gfx_max_level].value + 1));
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+				data->smc_state_table.gfx_max_level;
+	}
+
+	if (data->smc_state_table.mem_max_level !=
+		data->dpm_table.mem_table.dpm_state.soft_max_level) {
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_SetSoftMaxByFreq,
+			/* plus the vale by 1 to align the resolution */
+			PPCLK_UCLK<<16 | (data->dpm_table.mem_table.dpm_levels[data->smc_state_table.mem_max_level].value + 1));
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+				data->smc_state_table.mem_max_level;
+	}
+
 	return 0;
 }
 
-
 int vega12_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable)
 {
 	struct vega12_hwmgr *data =
@@ -1064,8 +1113,7 @@ static uint32_t vega12_dpm_get_mclk(struct pp_hwmgr *hwmgr, bool low)
 	return (mem_clk * 100);
 }
 
-static int vega12_get_gpu_power(struct pp_hwmgr *hwmgr,
-		struct pp_gpu_power *query)
+static int vega12_get_gpu_power(struct pp_hwmgr *hwmgr, uint32_t *query)
 {
 #if 0
 	uint32_t value;
@@ -1077,7 +1125,7 @@ static int vega12_get_gpu_power(struct pp_hwmgr *hwmgr,
 
 	vega12_read_arg_from_smc(hwmgr, &value);
 	/* power value is an integer */
-	query->average_gpu_power = value << 8;
+	*query = value << 8;
 #endif
 	return 0;
 }
@@ -1186,12 +1234,8 @@ static int vega12_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 		*size = 4;
 		break;
 	case AMDGPU_PP_SENSOR_GPU_POWER:
-		if (*size < sizeof(struct pp_gpu_power))
-			ret = -EINVAL;
-		else {
-			*size = sizeof(struct pp_gpu_power);
-			ret = vega12_get_gpu_power(hwmgr, (struct pp_gpu_power *)value);
-		}
+		ret = vega12_get_gpu_power(hwmgr, (uint32_t *)value);
+
 		break;
 	default:
 		ret = -EINVAL;
@@ -1260,23 +1304,18 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 {
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
-	uint32_t num_active_disps = 0;
-	struct cgs_display_info info = {0};
 	struct PP_Clocks min_clocks = {0};
 	struct pp_display_clock_request clock_req;
 	uint32_t clk_request;
 
-	info.mode_info = NULL;
-	cgs_get_active_displays_info(hwmgr->device, &info);
-	num_active_disps = info.display_count;
-	if (num_active_disps > 1)
+	if (hwmgr->display_config->num_display > 1)
 		vega12_notify_smc_display_change(hwmgr, false);
 	else
 		vega12_notify_smc_display_change(hwmgr, true);
 
-	min_clocks.dcefClock = hwmgr->display_config.min_dcef_set_clk;
-	min_clocks.dcefClockInSR = hwmgr->display_config.min_dcef_deep_sleep_set_clk;
-	min_clocks.memoryClock = hwmgr->display_config.min_mem_set_clock;
+	min_clocks.dcefClock = hwmgr->display_config->min_dcef_set_clk;
+	min_clocks.dcefClockInSR = hwmgr->display_config->min_dcef_deep_sleep_set_clk;
+	min_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock;
 
 	if (data->smu_features[GNLD_DPM_DCEFCLK].supported) {
 		clock_req.clock_type = amd_pp_dcef_clock;
@@ -1832,9 +1871,7 @@ static int vega12_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 	int result = 0;
-	uint32_t num_turned_on_displays = 1;
 	Watermarks_t *wm_table = &(data->smc_state_table.water_marks_table);
-	struct cgs_display_info info = {0};
 
 	if ((data->water_marks_bitmap & WaterMarksExist) &&
 			!(data->water_marks_bitmap & WaterMarksLoaded)) {
@@ -1846,12 +1883,9 @@ static int vega12_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 
 	if ((data->water_marks_bitmap & WaterMarksExist) &&
 		data->smu_features[GNLD_DPM_DCEFCLK].supported &&
-		data->smu_features[GNLD_DPM_SOCCLK].supported) {
-		cgs_get_active_displays_info(hwmgr->device, &info);
-		num_turned_on_displays = info.display_count;
+		data->smu_features[GNLD_DPM_SOCCLK].supported)
 		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_NumOfDisplays, num_turned_on_displays);
-	}
+			PPSMC_MSG_NumOfDisplays, hwmgr->display_config->num_display);
 
 	return result;
 }
@@ -1894,15 +1928,12 @@ vega12_check_smc_update_required_for_display_configuration(struct pp_hwmgr *hwmg
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 	bool is_update_required = false;
-	struct cgs_display_info info = {0, 0, NULL};
-
-	cgs_get_active_displays_info(hwmgr->device, &info);
 
-	if (data->display_timing.num_existing_displays != info.display_count)
+	if (data->display_timing.num_existing_displays != hwmgr->display_config->num_display)
 		is_update_required = true;
 
 	if (data->registry_data.gfx_clk_deep_sleep_support) {
-		if (data->display_timing.min_clock_in_sr != hwmgr->display_config.min_core_set_clock_in_sr)
+		if (data->display_timing.min_clock_in_sr != hwmgr->display_config->min_core_set_clock_in_sr)
 			is_update_required = true;
 	}
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
index bc98b1df3b65..e81ded1ec198 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
@@ -33,7 +33,7 @@
 #define WaterMarksExist  1
 #define WaterMarksLoaded 2
 
-#define VG12_PSUEDO_NUM_GFXCLK_DPM_LEVELS   8
+#define VG12_PSUEDO_NUM_GFXCLK_DPM_LEVELS   16
 #define VG12_PSUEDO_NUM_SOCCLK_DPM_LEVELS   8
 #define VG12_PSUEDO_NUM_DCEFCLK_DPM_LEVELS  8
 #define VG12_PSUEDO_NUM_UCLK_DPM_LEVELS     4
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
index b34113f45904..888ddca902d8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
@@ -51,7 +51,7 @@ static const void *get_powerplay_table(struct pp_hwmgr *hwmgr)
 
 	if (!table_address) {
 		table_address = (ATOM_Vega12_POWERPLAYTABLE *)
-				cgs_atom_get_data_table(hwmgr->device, index,
+				smu_atom_get_data_table(hwmgr->adev, index,
 						&size, &frev, &crev);
 
 		hwmgr->soft_pp_table = table_address;	/*Cache the result in RAM.*/
@@ -224,6 +224,11 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable
 	ppsmc_pptable->AcgGfxclkSpreadPercent = smc_dpm_table.acggfxclkspreadpercent;
 	ppsmc_pptable->AcgGfxclkSpreadFreq = smc_dpm_table.acggfxclkspreadfreq;
 
+	/* 0xFFFF will disable the ACG feature */
+	if (!(hwmgr->feature_mask & PP_ACG_MASK)) {
+		ppsmc_pptable->AcgThresholdFreqHigh = 0xFFFF;
+		ppsmc_pptable->AcgThresholdFreqLow = 0xFFFF;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
index df0fa815cd6e..cfd9e6ccb790 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
@@ -26,7 +26,7 @@
 #include "vega12_smumgr.h"
 #include "vega12_ppsmc.h"
 #include "vega12_inc.h"
-#include "pp_soc15.h"
+#include "soc15_common.h"
 #include "pp_debug.h"
 
 static int vega12_get_current_rpm(struct pp_hwmgr *hwmgr, uint32_t *current_rpm)
@@ -147,13 +147,10 @@ int vega12_fan_ctrl_reset_fan_speed_to_default(struct pp_hwmgr *hwmgr)
 */
 int vega12_thermal_get_temperature(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int temp = 0;
-	uint32_t reg;
 
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmCG_MULT_THERMAL_STATUS_BASE_IDX,  mmCG_MULT_THERMAL_STATUS);
-
-	temp = cgs_read_register(hwmgr->device, reg);
+	temp = RREG32_SOC15(THM, 0, mmCG_MULT_THERMAL_STATUS);
 
 	temp = (temp & CG_MULT_THERMAL_STATUS__CTF_TEMP_MASK) >>
 			CG_MULT_THERMAL_STATUS__CTF_TEMP__SHIFT;
@@ -175,11 +172,12 @@ int vega12_thermal_get_temperature(struct pp_hwmgr *hwmgr)
 static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *range)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP *
 			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP *
 			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	uint32_t val, reg;
+	uint32_t val;
 
 	if (low < range->min)
 		low = range->min;
@@ -189,18 +187,15 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 	if (low > high)
 		return -EINVAL;
 
-	reg = soc15_get_register_offset(THM_HWID, 0,
-			mmTHM_THERMAL_INT_CTRL_BASE_IDX, mmTHM_THERMAL_INT_CTRL);
-
-	val = cgs_read_register(hwmgr->device, reg);
+	val = RREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL);
 
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
 	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
 
-	cgs_write_register(hwmgr->device, reg, val);
+	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
 
 	return 0;
 }
@@ -212,15 +207,14 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 */
 static int vega12_thermal_enable_alert(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t val = 0;
-	uint32_t reg;
 
 	val |= (1 << THM_THERMAL_INT_ENA__THERM_INTH_CLR__SHIFT);
 	val |= (1 << THM_THERMAL_INT_ENA__THERM_INTL_CLR__SHIFT);
 	val |= (1 << THM_THERMAL_INT_ENA__THERM_TRIGGER_CLR__SHIFT);
 
-	reg = soc15_get_register_offset(THM_HWID, 0, mmTHM_THERMAL_INT_ENA_BASE_IDX, mmTHM_THERMAL_INT_ENA);
-	cgs_write_register(hwmgr->device, reg, val);
+	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_ENA, val);
 
 	return 0;
 }
@@ -231,10 +225,9 @@ static int vega12_thermal_enable_alert(struct pp_hwmgr *hwmgr)
 */
 int vega12_thermal_disable_alert(struct pp_hwmgr *hwmgr)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	reg = soc15_get_register_offset(THM_HWID, 0, mmTHM_THERMAL_INT_ENA_BASE_IDX, mmTHM_THERMAL_INT_ENA);
-	cgs_write_register(hwmgr->device, reg, 0);
+	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_ENA, 0);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
index 8b78bbecd1bc..a202247c9894 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
@@ -377,11 +377,7 @@ struct phm_clocks {
 #define DPMTABLE_UPDATE_SCLK        0x00000004
 #define DPMTABLE_UPDATE_MCLK        0x00000008
 #define DPMTABLE_OD_UPDATE_VDDC     0x00000010
-
-/* To determine if sclk and mclk are in overdrive state */
-#define SCLK_OVERDRIVE_ENABLED           0x00000001
-#define MCLK_OVERDRIVE_ENABLED           0x00000002
-#define VDDC_OVERDRIVE_ENABLED           0x00000010
+#define DPMTABLE_UPDATE_SOCCLK      0x00000020
 
 struct phm_odn_performance_level {
 	uint32_t clock;
@@ -414,7 +410,10 @@ extern int phm_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				   struct pp_power_state *adjusted_ps,
 			     const struct pp_power_state *current_ps);
 
+extern int phm_apply_clock_adjust_rules(struct pp_hwmgr *hwmgr);
+
 extern int phm_force_dpm_levels(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_level level);
+extern int phm_pre_display_configuration_changed(struct pp_hwmgr *hwmgr);
 extern int phm_display_configuration_changed(struct pp_hwmgr *hwmgr);
 extern int phm_notify_smc_display_config_after_ps_adjustment(struct pp_hwmgr *hwmgr);
 extern int phm_register_irq_handlers(struct pp_hwmgr *hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 17f811d181c8..b99fb8ac822c 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -38,6 +38,8 @@ struct phm_fan_speed_info;
 struct pp_atomctrl_voltage_table;
 
 #define VOLTAGE_SCALE 4
+#define VOLTAGE_VID_OFFSET_SCALE1   625
+#define VOLTAGE_VID_OFFSET_SCALE2   100
 
 enum DISPLAY_GAP {
 	DISPLAY_GAP_VBLANK_OR_WM = 0,   /* Wait for vblank or MCHG watermark. */
@@ -64,24 +66,6 @@ struct vi_dpm_table {
 #define PCIE_PERF_REQ_GEN2         3
 #define PCIE_PERF_REQ_GEN3         4
 
-enum PP_FEATURE_MASK {
-	PP_SCLK_DPM_MASK = 0x1,
-	PP_MCLK_DPM_MASK = 0x2,
-	PP_PCIE_DPM_MASK = 0x4,
-	PP_SCLK_DEEP_SLEEP_MASK = 0x8,
-	PP_POWER_CONTAINMENT_MASK = 0x10,
-	PP_UVD_HANDSHAKE_MASK = 0x20,
-	PP_SMC_VOLTAGE_CONTROL_MASK = 0x40,
-	PP_VBI_TIME_SUPPORT_MASK = 0x80,
-	PP_ULV_MASK = 0x100,
-	PP_ENABLE_GFX_CG_THRU_SMU = 0x200,
-	PP_CLOCK_STRETCH_MASK = 0x400,
-	PP_OD_FUZZY_FAN_CONTROL_MASK = 0x800,
-	PP_SOCCLK_DPM_MASK = 0x1000,
-	PP_DCEFCLK_DPM_MASK = 0x2000,
-	PP_OVERDRIVE_MASK = 0x4000,
-};
-
 enum PHM_BackEnd_Magic {
 	PHM_Dummy_Magic       = 0xAA5555AA,
 	PHM_RV770_Magic       = 0xDCBAABCD,
@@ -245,6 +229,8 @@ struct pp_hwmgr_func {
 				struct pp_power_state  *prequest_ps,
 			const struct pp_power_state *pcurrent_ps);
 
+	int (*apply_clocks_adjust_rules)(struct pp_hwmgr *hwmgr);
+
 	int (*force_dpm_level)(struct pp_hwmgr *hw_mgr,
 					enum amd_dpm_forced_level level);
 
@@ -268,6 +254,7 @@ struct pp_hwmgr_func {
 						const void *state);
 	int (*enable_clock_power_gating)(struct pp_hwmgr *hwmgr);
 	int (*notify_smc_display_config_after_ps_adjustment)(struct pp_hwmgr *hwmgr);
+	int (*pre_display_config_changed)(struct pp_hwmgr *hwmgr);
 	int (*display_config_changed)(struct pp_hwmgr *hwmgr);
 	int (*disable_clock_power_gating)(struct pp_hwmgr *hwmgr);
 	int (*update_clock_gatings)(struct pp_hwmgr *hwmgr,
@@ -312,6 +299,7 @@ struct pp_hwmgr_func {
 	int (*display_clock_voltage_request)(struct pp_hwmgr *hwmgr,
 			struct pp_display_clock_request *clock);
 	int (*get_max_high_clocks)(struct pp_hwmgr *hwmgr, struct amd_pp_simple_clock_info *clocks);
+	int (*gfx_off_control)(struct pp_hwmgr *hwmgr, bool enable);
 	int (*power_off_asic)(struct pp_hwmgr *hwmgr);
 	int (*force_clock_level)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask);
 	int (*print_clock_levels)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, char *buf);
@@ -341,6 +329,7 @@ struct pp_hwmgr_func {
 					long *input, uint32_t size);
 	int (*set_power_limit)(struct pp_hwmgr *hwmgr, uint32_t n);
 	int (*set_mmhub_powergating_by_smu)(struct pp_hwmgr *hwmgr);
+	int (*smus_notify_pwe)(struct pp_hwmgr *hwmgr);
 };
 
 struct pp_table_func {
@@ -718,6 +707,7 @@ struct pp_hwmgr {
 	uint32_t chip_family;
 	uint32_t chip_id;
 	uint32_t smu_version;
+	bool not_vf;
 	bool pm_en;
 	struct mutex smu_lock;
 
@@ -764,7 +754,7 @@ struct pp_hwmgr {
 	struct pp_power_state    *request_ps;
 	struct pp_power_state    *boot_ps;
 	struct pp_power_state    *uvd_ps;
-	struct amd_pp_display_configuration display_config;
+	const struct amd_pp_display_configuration *display_config;
 	uint32_t feature_mask;
 	bool avfs_supported;
 	/* UMD Pstate */
@@ -782,10 +772,13 @@ struct pp_hwmgr {
 };
 
 int hwmgr_early_init(struct pp_hwmgr *hwmgr);
+int hwmgr_sw_init(struct pp_hwmgr *hwmgr);
+int hwmgr_sw_fini(struct pp_hwmgr *hwmgr);
 int hwmgr_hw_init(struct pp_hwmgr *hwmgr);
 int hwmgr_hw_fini(struct pp_hwmgr *hwmgr);
-int hwmgr_hw_suspend(struct pp_hwmgr *hwmgr);
-int hwmgr_hw_resume(struct pp_hwmgr *hwmgr);
+int hwmgr_suspend(struct pp_hwmgr *hwmgr);
+int hwmgr_resume(struct pp_hwmgr *hwmgr);
+
 int hwmgr_handle_task(struct pp_hwmgr *hwmgr,
 				enum amd_pp_task task_id,
 				enum amd_pm_state_type *user_state);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h
index 426bff2aad2b..a2991fa2e6f8 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h
@@ -75,13 +75,15 @@
 #define PPSMC_MSG_GetMinGfxclkFrequency         0x2C
 #define PPSMC_MSG_GetMaxGfxclkFrequency         0x2D
 #define PPSMC_MSG_SoftReset                     0x2E
+#define PPSMC_MSG_SetGfxCGPG			0x2F
 #define PPSMC_MSG_SetSoftMaxGfxClk              0x30
 #define PPSMC_MSG_SetHardMinGfxClk              0x31
 #define PPSMC_MSG_SetSoftMaxSocclkByFreq        0x32
 #define PPSMC_MSG_SetSoftMaxFclkByFreq          0x33
 #define PPSMC_MSG_SetSoftMaxVcn                 0x34
 #define PPSMC_MSG_PowerGateMmHub                0x35
-#define PPSMC_Message_Count                     0x36
+#define PPSMC_MSG_SetRccPfcPmeRestoreRegister   0x36
+#define PPSMC_Message_Count                     0x37
 
 
 typedef uint16_t PPSMC_Result;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu75.h b/drivers/gpu/drm/amd/powerplay/inc/smu75.h
new file mode 100644
index 000000000000..771523001533
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu75.h
@@ -0,0 +1,760 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef SMU75_H
+#define SMU75_H
+
+#pragma pack(push, 1)
+
+typedef struct {
+	uint32_t high;
+	uint32_t low;
+} data_64_t;
+
+typedef struct {
+	data_64_t high;
+	data_64_t low;
+} data_128_t;
+
+#define SMU__DGPU_ONLY
+
+#define SMU__NUM_SCLK_DPM_STATE  8
+#define SMU__NUM_MCLK_DPM_LEVELS 4
+#define SMU__NUM_LCLK_DPM_LEVELS 8
+#define SMU__NUM_PCIE_DPM_LEVELS 8
+
+#define SMU7_CONTEXT_ID_SMC        1
+#define SMU7_CONTEXT_ID_VBIOS      2
+
+#define SMU75_MAX_LEVELS_VDDC            16
+#define SMU75_MAX_LEVELS_VDDGFX          16
+#define SMU75_MAX_LEVELS_VDDCI           8
+#define SMU75_MAX_LEVELS_MVDD            4
+
+#define SMU_MAX_SMIO_LEVELS              4
+
+#define SMU75_MAX_LEVELS_GRAPHICS        SMU__NUM_SCLK_DPM_STATE
+#define SMU75_MAX_LEVELS_MEMORY          SMU__NUM_MCLK_DPM_LEVELS
+#define SMU75_MAX_LEVELS_GIO             SMU__NUM_LCLK_DPM_LEVELS
+#define SMU75_MAX_LEVELS_LINK            SMU__NUM_PCIE_DPM_LEVELS
+#define SMU75_MAX_LEVELS_UVD             8
+#define SMU75_MAX_LEVELS_VCE             8
+#define SMU75_MAX_LEVELS_ACP             8
+#define SMU75_MAX_LEVELS_SAMU            8
+#define SMU75_MAX_ENTRIES_SMIO           32
+
+#define DPM_NO_LIMIT 0
+#define DPM_NO_UP 1
+#define DPM_GO_DOWN 2
+#define DPM_GO_UP 3
+
+#define SMU7_FIRST_DPM_GRAPHICS_LEVEL    0
+#define SMU7_FIRST_DPM_MEMORY_LEVEL      0
+
+#define GPIO_CLAMP_MODE_VRHOT      1
+#define GPIO_CLAMP_MODE_THERM      2
+#define GPIO_CLAMP_MODE_DC         4
+
+#define SCRATCH_B_TARG_PCIE_INDEX_SHIFT 0
+#define SCRATCH_B_TARG_PCIE_INDEX_MASK  (0x7<<SCRATCH_B_TARG_PCIE_INDEX_SHIFT)
+#define SCRATCH_B_CURR_PCIE_INDEX_SHIFT 3
+#define SCRATCH_B_CURR_PCIE_INDEX_MASK  (0x7<<SCRATCH_B_CURR_PCIE_INDEX_SHIFT)
+#define SCRATCH_B_TARG_UVD_INDEX_SHIFT  6
+#define SCRATCH_B_TARG_UVD_INDEX_MASK   (0x7<<SCRATCH_B_TARG_UVD_INDEX_SHIFT)
+#define SCRATCH_B_CURR_UVD_INDEX_SHIFT  9
+#define SCRATCH_B_CURR_UVD_INDEX_MASK   (0x7<<SCRATCH_B_CURR_UVD_INDEX_SHIFT)
+#define SCRATCH_B_TARG_VCE_INDEX_SHIFT  12
+#define SCRATCH_B_TARG_VCE_INDEX_MASK   (0x7<<SCRATCH_B_TARG_VCE_INDEX_SHIFT)
+#define SCRATCH_B_CURR_VCE_INDEX_SHIFT  15
+#define SCRATCH_B_CURR_VCE_INDEX_MASK   (0x7<<SCRATCH_B_CURR_VCE_INDEX_SHIFT)
+#define SCRATCH_B_TARG_ACP_INDEX_SHIFT  18
+#define SCRATCH_B_TARG_ACP_INDEX_MASK   (0x7<<SCRATCH_B_TARG_ACP_INDEX_SHIFT)
+#define SCRATCH_B_CURR_ACP_INDEX_SHIFT  21
+#define SCRATCH_B_CURR_ACP_INDEX_MASK   (0x7<<SCRATCH_B_CURR_ACP_INDEX_SHIFT)
+#define SCRATCH_B_TARG_SAMU_INDEX_SHIFT 24
+#define SCRATCH_B_TARG_SAMU_INDEX_MASK  (0x7<<SCRATCH_B_TARG_SAMU_INDEX_SHIFT)
+#define SCRATCH_B_CURR_SAMU_INDEX_SHIFT 27
+#define SCRATCH_B_CURR_SAMU_INDEX_MASK  (0x7<<SCRATCH_B_CURR_SAMU_INDEX_SHIFT)
+
+/* Virtualization Defines */
+#define CG_XDMA_MASK  0x1
+#define CG_XDMA_SHIFT 0
+#define CG_UVD_MASK   0x2
+#define CG_UVD_SHIFT  1
+#define CG_VCE_MASK   0x4
+#define CG_VCE_SHIFT  2
+#define CG_SAMU_MASK  0x8
+#define CG_SAMU_SHIFT 3
+#define CG_GFX_MASK   0x10
+#define CG_GFX_SHIFT  4
+#define CG_SDMA_MASK  0x20
+#define CG_SDMA_SHIFT 5
+#define CG_HDP_MASK   0x40
+#define CG_HDP_SHIFT  6
+#define CG_MC_MASK    0x80
+#define CG_MC_SHIFT   7
+#define CG_DRM_MASK   0x100
+#define CG_DRM_SHIFT  8
+#define CG_ROM_MASK   0x200
+#define CG_ROM_SHIFT  9
+#define CG_BIF_MASK   0x400
+#define CG_BIF_SHIFT  10
+
+#if defined SMU__DGPU_ONLY
+#define SMU75_DTE_ITERATIONS 5
+#define SMU75_DTE_SOURCES 3
+#define SMU75_DTE_SINKS 1
+#define SMU75_NUM_CPU_TES 0
+#define SMU75_NUM_GPU_TES 1
+#define SMU75_NUM_NON_TES 2
+#define SMU75_DTE_FAN_SCALAR_MIN 0x100
+#define SMU75_DTE_FAN_SCALAR_MAX 0x166
+#define SMU75_DTE_FAN_TEMP_MAX 93
+#define SMU75_DTE_FAN_TEMP_MIN 83
+#endif
+#define SMU75_THERMAL_INPUT_LOOP_COUNT 2
+#define SMU75_THERMAL_CLAMP_MODE_COUNT 2
+
+#define EXP_M1_1  93
+#define EXP_M2_1  195759
+#define EXP_B_1   111176531
+
+#define EXP_M1_2  67
+#define EXP_M2_2  153720
+#define EXP_B_2   94415767
+
+#define EXP_M1_3  48
+#define EXP_M2_3  119796
+#define EXP_B_3   79195279
+
+#define EXP_M1_4  550
+#define EXP_M2_4  1484190
+#define EXP_B_4   1051432828
+
+#define EXP_M1_5  394
+#define EXP_M2_5  1143049
+#define EXP_B_5   864288432
+
+struct SMU7_HystController_Data {
+	uint16_t waterfall_up;
+	uint16_t waterfall_down;
+	uint16_t waterfall_limit;
+	uint16_t release_cnt;
+	uint16_t release_limit;
+	uint16_t spare;
+};
+
+typedef struct SMU7_HystController_Data SMU7_HystController_Data;
+
+struct SMU75_PIDController {
+	uint32_t Ki;
+	int32_t LFWindupUpperLim;
+	int32_t LFWindupLowerLim;
+	uint32_t StatePrecision;
+	uint32_t LfPrecision;
+	uint32_t LfOffset;
+	uint32_t MaxState;
+	uint32_t MaxLfFraction;
+	uint32_t StateShift;
+};
+
+typedef struct SMU75_PIDController SMU75_PIDController;
+
+struct SMU7_LocalDpmScoreboard {
+	uint32_t PercentageBusy;
+
+	int32_t  PIDError;
+	int32_t  PIDIntegral;
+	int32_t  PIDOutput;
+
+	uint32_t SigmaDeltaAccum;
+	uint32_t SigmaDeltaOutput;
+	uint32_t SigmaDeltaLevel;
+
+	uint32_t UtilizationSetpoint;
+
+	uint8_t  TdpClampMode;
+	uint8_t  TdcClampMode;
+	uint8_t  ThermClampMode;
+	uint8_t  VoltageBusy;
+
+	int8_t   CurrLevel;
+	int8_t   TargLevel;
+	uint8_t  LevelChangeInProgress;
+	uint8_t  UpHyst;
+
+	uint8_t  DownHyst;
+	uint8_t  VoltageDownHyst;
+	uint8_t  DpmEnable;
+	uint8_t  DpmRunning;
+
+	uint8_t  DpmForce;
+	uint8_t  DpmForceLevel;
+	uint8_t  DisplayWatermark;
+	uint8_t  McArbIndex;
+
+	uint32_t MinimumPerfSclk;
+
+	uint8_t  AcpiReq;
+	uint8_t  AcpiAck;
+	uint8_t  GfxClkSlow;
+	uint8_t  GpioClampMode;
+
+	uint8_t  EnableModeSwitchRLCNotification;
+	uint8_t  EnabledLevelsChange;
+	uint8_t  DteClampMode;
+	uint8_t  FpsClampMode;
+
+	uint16_t LevelResidencyCounters [SMU75_MAX_LEVELS_GRAPHICS];
+	uint16_t LevelSwitchCounters [SMU75_MAX_LEVELS_GRAPHICS];
+
+	void     (*TargetStateCalculator)(uint8_t);
+	void     (*SavedTargetStateCalculator)(uint8_t);
+
+	uint16_t AutoDpmInterval;
+	uint16_t AutoDpmRange;
+
+	uint8_t  FpsEnabled;
+	uint8_t  MaxPerfLevel;
+	uint8_t  AllowLowClkInterruptToHost;
+	uint8_t  FpsRunning;
+
+	uint32_t MaxAllowedFrequency;
+
+	uint32_t FilteredSclkFrequency;
+	uint32_t LastSclkFrequency;
+	uint32_t FilteredSclkFrequencyCnt;
+
+	uint8_t MinPerfLevel;
+#ifdef SMU__FIRMWARE_SCKS_PRESENT__1
+	uint8_t ScksClampMode;
+	uint8_t padding[2];
+#else
+	uint8_t padding[3];
+#endif
+
+	uint16_t FpsAlpha;
+	uint16_t DeltaTime;
+	uint32_t CurrentFps;
+	uint32_t FilteredFps;
+	uint32_t FrameCount;
+	uint32_t FrameCountLast;
+	uint16_t FpsTargetScalar;
+	uint16_t FpsWaterfallLimitScalar;
+	uint16_t FpsAlphaScalar;
+	uint16_t spare8;
+	SMU7_HystController_Data HystControllerData;
+};
+
+typedef struct SMU7_LocalDpmScoreboard SMU7_LocalDpmScoreboard;
+
+#define SMU7_MAX_VOLTAGE_CLIENTS 12
+
+typedef uint8_t (*VoltageChangeHandler_t)(uint16_t, uint8_t);
+
+#define VDDC_MASK    0x00007FFF
+#define VDDC_SHIFT   0
+#define VDDCI_MASK   0x3FFF8000
+#define VDDCI_SHIFT  15
+#define PHASES_MASK  0xC0000000
+#define PHASES_SHIFT 30
+
+typedef uint32_t SMU_VoltageLevel;
+
+struct SMU7_VoltageScoreboard {
+	SMU_VoltageLevel TargetVoltage;
+	uint16_t MaxVid;
+	uint8_t  HighestVidOffset;
+	uint8_t  CurrentVidOffset;
+
+	uint16_t CurrentVddc;
+	uint16_t CurrentVddci;
+
+	uint8_t  ControllerBusy;
+	uint8_t  CurrentVid;
+	uint8_t  CurrentVddciVid;
+	uint8_t  padding;
+
+	SMU_VoltageLevel RequestedVoltage[SMU7_MAX_VOLTAGE_CLIENTS];
+	SMU_VoltageLevel TargetVoltageState;
+	uint8_t  EnabledRequest[SMU7_MAX_VOLTAGE_CLIENTS];
+
+	uint8_t  padding2;
+	uint8_t  padding3;
+	uint8_t  ControllerEnable;
+	uint8_t  ControllerRunning;
+	uint16_t CurrentStdVoltageHiSidd;
+	uint16_t CurrentStdVoltageLoSidd;
+	uint8_t  OverrideVoltage;
+	uint8_t  padding4;
+	uint8_t  padding5;
+	uint8_t  CurrentPhases;
+
+	VoltageChangeHandler_t ChangeVddc;
+	VoltageChangeHandler_t ChangeVddci;
+	VoltageChangeHandler_t ChangePhase;
+	VoltageChangeHandler_t ChangeMvdd;
+
+	VoltageChangeHandler_t functionLinks[6];
+
+	uint16_t * VddcFollower1;
+	int16_t  Driver_OD_RequestedVidOffset1;
+	int16_t  Driver_OD_RequestedVidOffset2;
+};
+
+typedef struct SMU7_VoltageScoreboard SMU7_VoltageScoreboard;
+
+#define SMU7_MAX_PCIE_LINK_SPEEDS 3
+
+struct SMU7_PCIeLinkSpeedScoreboard {
+	uint8_t     DpmEnable;
+	uint8_t     DpmRunning;
+	uint8_t     DpmForce;
+	uint8_t     DpmForceLevel;
+
+	uint8_t     CurrentLinkSpeed;
+	uint8_t     EnabledLevelsChange;
+	uint16_t    AutoDpmInterval;
+
+	uint16_t    AutoDpmRange;
+	uint16_t    AutoDpmCount;
+
+	uint8_t     DpmMode;
+	uint8_t     AcpiReq;
+	uint8_t     AcpiAck;
+	uint8_t     CurrentLinkLevel;
+};
+
+typedef struct SMU7_PCIeLinkSpeedScoreboard SMU7_PCIeLinkSpeedScoreboard;
+
+#define SMU7_LKGE_LUT_NUM_OF_TEMP_ENTRIES 16
+#define SMU7_LKGE_LUT_NUM_OF_VOLT_ENTRIES 16
+
+#define SMU7_SCALE_I  7
+#define SMU7_SCALE_R 12
+
+struct SMU7_PowerScoreboard {
+	uint32_t GpuPower;
+
+	uint32_t VddcPower;
+	uint32_t VddcVoltage;
+	uint32_t VddcCurrent;
+
+	uint32_t VddciPower;
+	uint32_t VddciVoltage;
+	uint32_t VddciCurrent;
+
+	uint32_t RocPower;
+
+	uint16_t Telemetry_1_slope;
+	uint16_t Telemetry_2_slope;
+	int32_t  Telemetry_1_offset;
+	int32_t  Telemetry_2_offset;
+
+	uint8_t MCLK_patch_flag;
+	uint8_t reserved[3];
+};
+
+typedef struct SMU7_PowerScoreboard SMU7_PowerScoreboard;
+
+#define SMU7_SCLK_DPM_CONFIG_MASK                        0x01
+#define SMU7_VOLTAGE_CONTROLLER_CONFIG_MASK              0x02
+#define SMU7_THERMAL_CONTROLLER_CONFIG_MASK              0x04
+#define SMU7_MCLK_DPM_CONFIG_MASK                        0x08
+#define SMU7_UVD_DPM_CONFIG_MASK                         0x10
+#define SMU7_VCE_DPM_CONFIG_MASK                         0x20
+#define SMU7_ACP_DPM_CONFIG_MASK                         0x40
+#define SMU7_SAMU_DPM_CONFIG_MASK                        0x80
+#define SMU7_PCIEGEN_DPM_CONFIG_MASK                    0x100
+
+#define SMU7_ACP_MCLK_HANDSHAKE_DISABLE                  0x00000001
+#define SMU7_ACP_SCLK_HANDSHAKE_DISABLE                  0x00000002
+#define SMU7_UVD_MCLK_HANDSHAKE_DISABLE                  0x00000100
+#define SMU7_UVD_SCLK_HANDSHAKE_DISABLE                  0x00000200
+#define SMU7_VCE_MCLK_HANDSHAKE_DISABLE                  0x00010000
+#define SMU7_VCE_SCLK_HANDSHAKE_DISABLE                  0x00020000
+
+struct SMU75_SoftRegisters {
+	uint32_t        RefClockFrequency;
+	uint32_t        PmTimerPeriod;
+	uint32_t        FeatureEnables;
+#if defined (SMU__DGPU_ONLY)
+	uint32_t        PreVBlankGap;
+	uint32_t        VBlankTimeout;
+	uint32_t        TrainTimeGap;
+	uint32_t        MvddSwitchTime;
+	uint32_t        LongestAcpiTrainTime;
+	uint32_t        AcpiDelay;
+	uint32_t        G5TrainTime;
+	uint32_t        DelayMpllPwron;
+	uint32_t        VoltageChangeTimeout;
+#endif
+	uint32_t        HandshakeDisables;
+
+	uint8_t         DisplayPhy1Config;
+	uint8_t         DisplayPhy2Config;
+	uint8_t         DisplayPhy3Config;
+	uint8_t         DisplayPhy4Config;
+
+	uint8_t         DisplayPhy5Config;
+	uint8_t         DisplayPhy6Config;
+	uint8_t         DisplayPhy7Config;
+	uint8_t         DisplayPhy8Config;
+
+	uint32_t        AverageGraphicsActivity;
+	uint32_t        AverageMemoryActivity;
+	uint32_t        AverageGioActivity;
+
+	uint8_t         SClkDpmEnabledLevels;
+	uint8_t         MClkDpmEnabledLevels;
+	uint8_t         LClkDpmEnabledLevels;
+	uint8_t         PCIeDpmEnabledLevels;
+
+	uint8_t         UVDDpmEnabledLevels;
+	uint8_t         SAMUDpmEnabledLevels;
+	uint8_t         ACPDpmEnabledLevels;
+	uint8_t         VCEDpmEnabledLevels;
+
+	uint32_t        DRAM_LOG_ADDR_H;
+	uint32_t        DRAM_LOG_ADDR_L;
+	uint32_t        DRAM_LOG_PHY_ADDR_H;
+	uint32_t        DRAM_LOG_PHY_ADDR_L;
+	uint32_t        DRAM_LOG_BUFF_SIZE;
+	uint32_t        UlvEnterCount;
+	uint32_t        UlvTime;
+	uint32_t        UcodeLoadStatus;
+	uint32_t        AllowMvddSwitch;
+	uint8_t         Activity_Weight;
+	uint8_t         Reserved8[3];
+};
+
+typedef struct SMU75_SoftRegisters SMU75_SoftRegisters;
+
+struct SMU75_Firmware_Header {
+	uint32_t Digest[5];
+	uint32_t Version;
+	uint32_t HeaderSize;
+	uint32_t Flags;
+	uint32_t EntryPoint;
+	uint32_t CodeSize;
+	uint32_t ImageSize;
+
+	uint32_t Rtos;
+	uint32_t SoftRegisters;
+	uint32_t DpmTable;
+	uint32_t FanTable;
+	uint32_t CacConfigTable;
+	uint32_t CacStatusTable;
+	uint32_t mcRegisterTable;
+	uint32_t mcArbDramTimingTable;
+	uint32_t PmFuseTable;
+	uint32_t Globals;
+	uint32_t ClockStretcherTable;
+	uint32_t VftTable;
+	uint32_t Reserved1;
+	uint32_t AvfsCksOff_AvfsGbvTable;
+	uint32_t AvfsCksOff_BtcGbvTable;
+	uint32_t MM_AvfsTable;
+	uint32_t PowerSharingTable;
+	uint32_t AvfsTable;
+	uint32_t AvfsCksOffGbvTable;
+	uint32_t AvfsMeanNSigma;
+	uint32_t AvfsSclkOffsetTable;
+	uint32_t Reserved[12];
+	uint32_t Signature;
+};
+
+typedef struct SMU75_Firmware_Header SMU75_Firmware_Header;
+
+#define SMU7_FIRMWARE_HEADER_LOCATION 0x20000
+
+enum  DisplayConfig {
+	PowerDown = 1,
+	DP54x4,
+	DP54x2,
+	DP54x1,
+	DP27x4,
+	DP27x2,
+	DP27x1,
+	HDMI297,
+	HDMI162,
+	LVDS,
+	DP324x4,
+	DP324x2,
+	DP324x1
+};
+
+#define MC_BLOCK_COUNT 1
+#define CPL_BLOCK_COUNT 5
+#define SE_BLOCK_COUNT 15
+#define GC_BLOCK_COUNT 24
+
+struct SMU7_Local_Cac {
+	uint8_t BlockId;
+	uint8_t SignalId;
+	uint8_t Threshold;
+	uint8_t Padding;
+};
+
+typedef struct SMU7_Local_Cac SMU7_Local_Cac;
+
+struct SMU7_Local_Cac_Table {
+	SMU7_Local_Cac CplLocalCac[CPL_BLOCK_COUNT];
+	SMU7_Local_Cac McLocalCac[MC_BLOCK_COUNT];
+	SMU7_Local_Cac SeLocalCac[SE_BLOCK_COUNT];
+	SMU7_Local_Cac GcLocalCac[GC_BLOCK_COUNT];
+};
+
+typedef struct SMU7_Local_Cac_Table SMU7_Local_Cac_Table;
+
+#pragma pack(pop)
+
+#define CG_SYS_BITMASK_FIRST_BIT      0
+#define CG_SYS_BITMASK_LAST_BIT       10
+#define CG_SYS_BIF_MGLS_SHIFT         0
+#define CG_SYS_ROM_SHIFT              1
+#define CG_SYS_MC_MGCG_SHIFT          2
+#define CG_SYS_MC_MGLS_SHIFT          3
+#define CG_SYS_SDMA_MGCG_SHIFT        4
+#define CG_SYS_SDMA_MGLS_SHIFT        5
+#define CG_SYS_DRM_MGCG_SHIFT         6
+#define CG_SYS_HDP_MGCG_SHIFT         7
+#define CG_SYS_HDP_MGLS_SHIFT         8
+#define CG_SYS_DRM_MGLS_SHIFT         9
+#define CG_SYS_BIF_MGCG_SHIFT         10
+
+#define CG_SYS_BIF_MGLS_MASK          0x1
+#define CG_SYS_ROM_MASK               0x2
+#define CG_SYS_MC_MGCG_MASK           0x4
+#define CG_SYS_MC_MGLS_MASK           0x8
+#define CG_SYS_SDMA_MGCG_MASK         0x10
+#define CG_SYS_SDMA_MGLS_MASK         0x20
+#define CG_SYS_DRM_MGCG_MASK          0x40
+#define CG_SYS_HDP_MGCG_MASK          0x80
+#define CG_SYS_HDP_MGLS_MASK          0x100
+#define CG_SYS_DRM_MGLS_MASK          0x200
+#define CG_SYS_BIF_MGCG_MASK          0x400
+
+#define CG_GFX_BITMASK_FIRST_BIT      16
+#define CG_GFX_BITMASK_LAST_BIT       24
+
+#define CG_GFX_CGCG_SHIFT             16
+#define CG_GFX_CGLS_SHIFT             17
+#define CG_CPF_MGCG_SHIFT             18
+#define CG_RLC_MGCG_SHIFT             19
+#define CG_GFX_OTHERS_MGCG_SHIFT      20
+#define CG_GFX_3DCG_SHIFT             21
+#define CG_GFX_3DLS_SHIFT             22
+#define CG_GFX_RLC_LS_SHIFT           23
+#define CG_GFX_CP_LS_SHIFT            24
+
+#define CG_GFX_CGCG_MASK              0x00010000
+#define CG_GFX_CGLS_MASK              0x00020000
+#define CG_CPF_MGCG_MASK              0x00040000
+#define CG_RLC_MGCG_MASK              0x00080000
+#define CG_GFX_OTHERS_MGCG_MASK       0x00100000
+#define CG_GFX_3DCG_MASK              0x00200000
+#define CG_GFX_3DLS_MASK              0x00400000
+#define CG_GFX_RLC_LS_MASK            0x00800000
+#define CG_GFX_CP_LS_MASK             0x01000000
+
+
+#define VRCONF_VDDC_MASK         0x000000FF
+#define VRCONF_VDDC_SHIFT        0
+#define VRCONF_VDDGFX_MASK       0x0000FF00
+#define VRCONF_VDDGFX_SHIFT      8
+#define VRCONF_VDDCI_MASK        0x00FF0000
+#define VRCONF_VDDCI_SHIFT       16
+#define VRCONF_MVDD_MASK         0xFF000000
+#define VRCONF_MVDD_SHIFT        24
+
+#define VR_MERGED_WITH_VDDC      0
+#define VR_SVI2_PLANE_1          1
+#define VR_SVI2_PLANE_2          2
+#define VR_SMIO_PATTERN_1        3
+#define VR_SMIO_PATTERN_2        4
+#define VR_STATIC_VOLTAGE        5
+
+#define CLOCK_STRETCHER_MAX_ENTRIES 0x4
+#define CKS_LOOKUPTable_MAX_ENTRIES 0x4
+
+#define CLOCK_STRETCHER_SETTING_DDT_MASK             0x01
+#define CLOCK_STRETCHER_SETTING_DDT_SHIFT            0x0
+#define CLOCK_STRETCHER_SETTING_STRETCH_AMOUNT_MASK  0x1E
+#define CLOCK_STRETCHER_SETTING_STRETCH_AMOUNT_SHIFT 0x1
+#define CLOCK_STRETCHER_SETTING_ENABLE_MASK          0x80
+#define CLOCK_STRETCHER_SETTING_ENABLE_SHIFT         0x7
+
+struct SMU_ClockStretcherDataTableEntry {
+	uint8_t minVID;
+	uint8_t maxVID;
+
+	uint16_t setting;
+};
+typedef struct SMU_ClockStretcherDataTableEntry SMU_ClockStretcherDataTableEntry;
+
+struct SMU_ClockStretcherDataTable {
+	SMU_ClockStretcherDataTableEntry ClockStretcherDataTableEntry[CLOCK_STRETCHER_MAX_ENTRIES];
+};
+typedef struct SMU_ClockStretcherDataTable SMU_ClockStretcherDataTable;
+
+struct SMU_CKS_LOOKUPTableEntry {
+	uint16_t minFreq;
+	uint16_t maxFreq;
+
+	uint8_t setting;
+	uint8_t padding[3];
+};
+typedef struct SMU_CKS_LOOKUPTableEntry SMU_CKS_LOOKUPTableEntry;
+
+struct SMU_CKS_LOOKUPTable {
+	SMU_CKS_LOOKUPTableEntry CKS_LOOKUPTableEntry[CKS_LOOKUPTable_MAX_ENTRIES];
+};
+typedef struct SMU_CKS_LOOKUPTable SMU_CKS_LOOKUPTable;
+
+struct AgmAvfsData_t {
+	uint16_t avgPsmCount[28];
+	uint16_t minPsmCount[28];
+};
+typedef struct AgmAvfsData_t AgmAvfsData_t;
+
+enum VFT_COLUMNS {
+	SCLK0,
+	SCLK1,
+	SCLK2,
+	SCLK3,
+	SCLK4,
+	SCLK5,
+	SCLK6,
+	SCLK7,
+
+	NUM_VFT_COLUMNS
+};
+enum {
+  SCS_FUSE_T0,
+  SCS_FUSE_T1,
+  NUM_SCS_FUSE_TEMPERATURE
+};
+enum {
+  SCKS_ON,
+  SCKS_OFF,
+  NUM_SCKS_STATE_TYPES
+};
+
+#define VFT_TABLE_DEFINED
+
+#define TEMP_RANGE_MAXSTEPS 12
+struct VFT_CELL_t {
+	uint16_t Voltage;
+};
+
+typedef struct VFT_CELL_t VFT_CELL_t;
+#ifdef SMU__FIRMWARE_SCKS_PRESENT__1
+struct SCS_CELL_t {
+	uint16_t PsmCnt[NUM_SCKS_STATE_TYPES];
+};
+typedef struct SCS_CELL_t SCS_CELL_t;
+#endif
+
+struct VFT_TABLE_t {
+	VFT_CELL_t    Cell[TEMP_RANGE_MAXSTEPS][NUM_VFT_COLUMNS];
+	uint16_t      AvfsGbv [NUM_VFT_COLUMNS];
+	uint16_t      BtcGbv  [NUM_VFT_COLUMNS];
+	int16_t       Temperature [TEMP_RANGE_MAXSTEPS];
+
+#ifdef SMU__FIRMWARE_SCKS_PRESENT__1
+	SCS_CELL_t    ScksCell[TEMP_RANGE_MAXSTEPS][NUM_VFT_COLUMNS];
+#endif
+
+	uint8_t       NumTemperatureSteps;
+	uint8_t       padding[3];
+};
+typedef struct VFT_TABLE_t VFT_TABLE_t;
+
+#define BTCGB_VDROOP_TABLE_MAX_ENTRIES 2
+#define AVFSGB_VDROOP_TABLE_MAX_ENTRIES 2
+
+struct GB_VDROOP_TABLE_t {
+	int32_t a0;
+	int32_t a1;
+	int32_t a2;
+	uint32_t spare;
+};
+typedef struct GB_VDROOP_TABLE_t GB_VDROOP_TABLE_t;
+
+struct SMU_QuadraticCoeffs {
+	int32_t m1;
+	int32_t b;
+
+	int16_t m2;
+	uint8_t m1_shift;
+	uint8_t m2_shift;
+};
+typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs;
+
+struct AVFS_Margin_t {
+	VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_Margin_t AVFS_Margin_t;
+
+struct AVFS_CksOff_Gbv_t {
+	VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_CksOff_Gbv_t AVFS_CksOff_Gbv_t;
+
+struct AVFS_CksOff_AvfsGbv_t {
+	VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_CksOff_AvfsGbv_t AVFS_CksOff_AvfsGbv_t;
+
+struct AVFS_CksOff_BtcGbv_t {
+	VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_CksOff_BtcGbv_t AVFS_CksOff_BtcGbv_t;
+
+struct AVFS_meanNsigma_t {
+	uint32_t Aconstant[3];
+	uint16_t DC_tol_sigma;
+	uint16_t Platform_mean;
+	uint16_t Platform_sigma;
+	uint16_t PSM_Age_CompFactor;
+	uint8_t  Static_Voltage_Offset[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_meanNsigma_t AVFS_meanNsigma_t;
+
+struct AVFS_Sclk_Offset_t {
+	uint16_t Sclk_Offset[8];
+};
+typedef struct AVFS_Sclk_Offset_t AVFS_Sclk_Offset_t;
+
+struct Power_Sharing_t {
+	uint32_t EnergyCounter;
+	uint32_t EngeryThreshold;
+	uint64_t AM_SCLK_CNT;
+	uint64_t AM_0_BUSY_CNT;
+};
+typedef struct Power_Sharing_t  Power_Sharing_t;
+
+
+#endif
+
+
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu75_discrete.h b/drivers/gpu/drm/amd/powerplay/inc/smu75_discrete.h
new file mode 100644
index 000000000000..b64e58a22ddf
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu75_discrete.h
@@ -0,0 +1,886 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef SMU75_DISCRETE_H
+#define SMU75_DISCRETE_H
+
+#include "smu75.h"
+
+#pragma pack(push, 1)
+
+#define NUM_SCLK_RANGE 8
+
+#define VCO_3_6 1
+#define VCO_2_4 3
+
+#define POSTDIV_DIV_BY_1  0
+#define POSTDIV_DIV_BY_2  1
+#define POSTDIV_DIV_BY_4  2
+#define POSTDIV_DIV_BY_8  3
+#define POSTDIV_DIV_BY_16 4
+
+struct sclkFcwRange_t {
+	uint8_t  vco_setting; /* 1: 3-6GHz, 3: 2-4GHz */
+	uint8_t  postdiv;     /* divide by 2^n */
+	uint16_t fcw_pcc;
+	uint16_t fcw_trans_upper;
+	uint16_t fcw_trans_lower;
+};
+typedef struct sclkFcwRange_t sclkFcwRange_t;
+
+struct SMIO_Pattern {
+	uint16_t Voltage;
+	uint8_t  Smio;
+	uint8_t  padding;
+};
+
+typedef struct SMIO_Pattern SMIO_Pattern;
+
+struct SMIO_Table {
+	SMIO_Pattern Pattern[SMU_MAX_SMIO_LEVELS];
+};
+
+typedef struct SMIO_Table SMIO_Table;
+
+struct SMU_SclkSetting {
+	uint32_t    SclkFrequency;
+	uint16_t    Fcw_int;
+	uint16_t    Fcw_frac;
+	uint16_t    Pcc_fcw_int;
+	uint8_t     PllRange;
+	uint8_t     SSc_En;
+	uint16_t    Sclk_slew_rate;
+	uint16_t    Pcc_up_slew_rate;
+	uint16_t    Pcc_down_slew_rate;
+	uint16_t    Fcw1_int;
+	uint16_t    Fcw1_frac;
+	uint16_t    Sclk_ss_slew_rate;
+};
+typedef struct SMU_SclkSetting SMU_SclkSetting;
+
+struct SMU75_Discrete_GraphicsLevel {
+	SMU_VoltageLevel MinVoltage;
+
+	uint8_t     pcieDpmLevel;
+	uint8_t     DeepSleepDivId;
+	uint16_t    ActivityLevel;
+
+	uint32_t    CgSpllFuncCntl3;
+	uint32_t    CgSpllFuncCntl4;
+	uint32_t    CcPwrDynRm;
+	uint32_t    CcPwrDynRm1;
+
+	uint8_t     SclkDid;
+	uint8_t     padding;
+	uint8_t     EnabledForActivity;
+	uint8_t     EnabledForThrottle;
+	uint8_t     UpHyst;
+	uint8_t     DownHyst;
+	uint8_t     VoltageDownHyst;
+	uint8_t     PowerThrottle;
+
+	SMU_SclkSetting SclkSetting;
+
+	uint8_t  ScksStretchThreshVid[NUM_SCKS_STATE_TYPES];
+	uint16_t Padding;
+};
+
+typedef struct SMU75_Discrete_GraphicsLevel SMU75_Discrete_GraphicsLevel;
+
+struct SMU75_Discrete_ACPILevel {
+	uint32_t    Flags;
+	SMU_VoltageLevel MinVoltage;
+	uint32_t    SclkFrequency;
+	uint8_t     SclkDid;
+	uint8_t     DisplayWatermark;
+	uint8_t     DeepSleepDivId;
+	uint8_t     padding;
+	uint32_t    CcPwrDynRm;
+	uint32_t    CcPwrDynRm1;
+
+	SMU_SclkSetting SclkSetting;
+};
+
+typedef struct SMU75_Discrete_ACPILevel SMU75_Discrete_ACPILevel;
+
+struct SMU75_Discrete_Ulv {
+	uint32_t    CcPwrDynRm;
+	uint32_t    CcPwrDynRm1;
+	uint16_t    VddcOffset;
+	uint8_t     VddcOffsetVid;
+	uint8_t     VddcPhase;
+	uint16_t    BifSclkDfs;
+	uint16_t    Reserved;
+};
+
+typedef struct SMU75_Discrete_Ulv SMU75_Discrete_Ulv;
+
+struct SMU75_Discrete_MemoryLevel {
+	SMU_VoltageLevel MinVoltage;
+	uint32_t    MinMvdd;
+
+	uint32_t    MclkFrequency;
+
+	uint8_t     StutterEnable;
+	uint8_t     EnabledForThrottle;
+	uint8_t     EnabledForActivity;
+	uint8_t     padding_0;
+
+	uint8_t     UpHyst;
+	uint8_t     DownHyst;
+	uint8_t     VoltageDownHyst;
+	uint8_t     padding_1;
+
+	uint16_t    ActivityLevel;
+	uint8_t     DisplayWatermark;
+	uint8_t     padding_2;
+
+	uint16_t    Fcw_int;
+	uint16_t    Fcw_frac;
+	uint8_t     Postdiv;
+	uint8_t     padding_3[3];
+};
+
+typedef struct SMU75_Discrete_MemoryLevel SMU75_Discrete_MemoryLevel;
+
+struct SMU75_Discrete_LinkLevel {
+	uint8_t     PcieGenSpeed;
+	uint8_t     PcieLaneCount;
+	uint8_t     EnabledForActivity;
+	uint8_t     SPC;
+	uint32_t    DownThreshold;
+	uint32_t    UpThreshold;
+	uint16_t    BifSclkDfs;
+	uint16_t    Reserved;
+};
+
+typedef struct SMU75_Discrete_LinkLevel SMU75_Discrete_LinkLevel;
+
+
+/* MC ARB DRAM Timing registers. */
+struct SMU75_Discrete_MCArbDramTimingTableEntry {
+	uint32_t McArbDramTiming;
+	uint32_t McArbDramTiming2;
+	uint32_t McArbBurstTime;
+	uint32_t McArbRfshRate;
+	uint32_t McArbMisc3;
+};
+
+typedef struct SMU75_Discrete_MCArbDramTimingTableEntry SMU75_Discrete_MCArbDramTimingTableEntry;
+
+struct SMU75_Discrete_MCArbDramTimingTable {
+	SMU75_Discrete_MCArbDramTimingTableEntry entries[SMU__NUM_SCLK_DPM_STATE][SMU__NUM_MCLK_DPM_LEVELS];
+};
+
+typedef struct SMU75_Discrete_MCArbDramTimingTable SMU75_Discrete_MCArbDramTimingTable;
+
+/* UVD VCLK/DCLK state (level) definition. */
+struct SMU75_Discrete_UvdLevel {
+	uint32_t VclkFrequency;
+	uint32_t DclkFrequency;
+	SMU_VoltageLevel MinVoltage;
+	uint8_t  VclkDivider;
+	uint8_t  DclkDivider;
+	uint8_t  padding[2];
+};
+
+typedef struct SMU75_Discrete_UvdLevel SMU75_Discrete_UvdLevel;
+
+/* Clocks for other external blocks (VCE, ACP, SAMU). */
+struct SMU75_Discrete_ExtClkLevel {
+	uint32_t Frequency;
+	SMU_VoltageLevel MinVoltage;
+	uint8_t  Divider;
+	uint8_t  padding[3];
+};
+
+typedef struct SMU75_Discrete_ExtClkLevel SMU75_Discrete_ExtClkLevel;
+
+struct SMU75_Discrete_StateInfo {
+	uint32_t SclkFrequency;
+	uint32_t MclkFrequency;
+	uint32_t VclkFrequency;
+	uint32_t DclkFrequency;
+	uint32_t SamclkFrequency;
+	uint32_t AclkFrequency;
+	uint32_t EclkFrequency;
+	uint16_t MvddVoltage;
+	uint16_t padding16;
+	uint8_t  DisplayWatermark;
+	uint8_t  McArbIndex;
+	uint8_t  McRegIndex;
+	uint8_t  SeqIndex;
+	uint8_t  SclkDid;
+	int8_t   SclkIndex;
+	int8_t   MclkIndex;
+	uint8_t  PCIeGen;
+};
+
+typedef struct SMU75_Discrete_StateInfo SMU75_Discrete_StateInfo;
+
+struct SMU75_Discrete_DpmTable {
+	SMU75_PIDController                  GraphicsPIDController;
+	SMU75_PIDController                  MemoryPIDController;
+	SMU75_PIDController                  LinkPIDController;
+
+	uint32_t                            SystemFlags;
+
+	uint32_t                            VRConfig;
+	uint32_t                            SmioMask1;
+	uint32_t                            SmioMask2;
+	SMIO_Table                          SmioTable1;
+	SMIO_Table                          SmioTable2;
+
+	uint32_t                            MvddLevelCount;
+
+	uint8_t                             BapmVddcVidHiSidd        [SMU75_MAX_LEVELS_VDDC];
+	uint8_t                             BapmVddcVidLoSidd        [SMU75_MAX_LEVELS_VDDC];
+	uint8_t                             BapmVddcVidHiSidd2       [SMU75_MAX_LEVELS_VDDC];
+
+	uint8_t                             GraphicsDpmLevelCount;
+	uint8_t                             MemoryDpmLevelCount;
+	uint8_t                             LinkLevelCount;
+	uint8_t                             MasterDeepSleepControl;
+
+	uint8_t                             UvdLevelCount;
+	uint8_t                             VceLevelCount;
+	uint8_t                             AcpLevelCount;
+	uint8_t                             SamuLevelCount;
+
+	uint8_t                             ThermOutGpio;
+	uint8_t                             ThermOutPolarity;
+	uint8_t                             ThermOutMode;
+	uint8_t                             BootPhases;
+
+	uint8_t                             VRHotLevel;
+	uint8_t                             LdoRefSel;
+
+	uint8_t                             Reserved1[2];
+
+	uint16_t                            FanStartTemperature;
+	uint16_t                            FanStopTemperature;
+
+	uint16_t                            MaxVoltage;
+	uint16_t                            Reserved2;
+	uint32_t                            Reserved;
+
+	SMU75_Discrete_GraphicsLevel        GraphicsLevel           [SMU75_MAX_LEVELS_GRAPHICS];
+	SMU75_Discrete_MemoryLevel          MemoryACPILevel;
+	SMU75_Discrete_MemoryLevel          MemoryLevel             [SMU75_MAX_LEVELS_MEMORY];
+	SMU75_Discrete_LinkLevel            LinkLevel               [SMU75_MAX_LEVELS_LINK];
+	SMU75_Discrete_ACPILevel            ACPILevel;
+	SMU75_Discrete_UvdLevel             UvdLevel                [SMU75_MAX_LEVELS_UVD];
+	SMU75_Discrete_ExtClkLevel          VceLevel                [SMU75_MAX_LEVELS_VCE];
+	SMU75_Discrete_ExtClkLevel          AcpLevel                [SMU75_MAX_LEVELS_ACP];
+	SMU75_Discrete_ExtClkLevel          SamuLevel               [SMU75_MAX_LEVELS_SAMU];
+	SMU75_Discrete_Ulv                  Ulv;
+
+	uint8_t                             DisplayWatermark        [SMU75_MAX_LEVELS_MEMORY][SMU75_MAX_LEVELS_GRAPHICS];
+
+	uint32_t                            SclkStepSize;
+	uint32_t                            Smio                    [SMU75_MAX_ENTRIES_SMIO];
+
+	uint8_t                             UvdBootLevel;
+	uint8_t                             VceBootLevel;
+	uint8_t                             AcpBootLevel;
+	uint8_t                             SamuBootLevel;
+
+	uint8_t                             GraphicsBootLevel;
+	uint8_t                             GraphicsVoltageChangeEnable;
+	uint8_t                             GraphicsThermThrottleEnable;
+	uint8_t                             GraphicsInterval;
+
+	uint8_t                             VoltageInterval;
+	uint8_t                             ThermalInterval;
+	uint16_t                            TemperatureLimitHigh;
+
+	uint16_t                            TemperatureLimitLow;
+	uint8_t                             MemoryBootLevel;
+	uint8_t                             MemoryVoltageChangeEnable;
+
+	uint16_t                            BootMVdd;
+	uint8_t                             MemoryInterval;
+	uint8_t                             MemoryThermThrottleEnable;
+
+	uint16_t                            VoltageResponseTime;
+	uint16_t                            PhaseResponseTime;
+
+	uint8_t                             PCIeBootLinkLevel;
+	uint8_t                             PCIeGenInterval;
+	uint8_t                             DTEInterval;
+	uint8_t                             DTEMode;
+
+	uint8_t                             SVI2Enable;
+	uint8_t                             VRHotGpio;
+	uint8_t                             AcDcGpio;
+	uint8_t                             ThermGpio;
+
+	uint16_t                            PPM_PkgPwrLimit;
+	uint16_t                            PPM_TemperatureLimit;
+
+	uint16_t                            DefaultTdp;
+	uint16_t                            TargetTdp;
+
+	uint16_t                            FpsHighThreshold;
+	uint16_t                            FpsLowThreshold;
+
+	uint16_t                            BAPMTI_R  [SMU75_DTE_ITERATIONS][SMU75_DTE_SOURCES][SMU75_DTE_SINKS];
+	uint16_t                            BAPMTI_RC [SMU75_DTE_ITERATIONS][SMU75_DTE_SOURCES][SMU75_DTE_SINKS];
+
+	uint16_t                            TemperatureLimitEdge;
+	uint16_t                            TemperatureLimitHotspot;
+
+	uint16_t                            BootVddc;
+	uint16_t                            BootVddci;
+
+	uint16_t                            FanGainEdge;
+	uint16_t                            FanGainHotspot;
+
+	uint32_t                            LowSclkInterruptThreshold;
+	uint32_t                            VddGfxReChkWait;
+
+	uint8_t                             ClockStretcherAmount;
+	uint8_t                             Sclk_CKS_masterEn0_7;
+	uint8_t                             Sclk_CKS_masterEn8_15;
+	uint8_t                             DPMFreezeAndForced;
+
+	uint8_t                             Sclk_voltageOffset[8];
+
+	SMU_ClockStretcherDataTable         ClockStretcherDataTable;
+	SMU_CKS_LOOKUPTable                 CKS_LOOKUPTable;
+
+	uint32_t                            CurrSclkPllRange;
+	sclkFcwRange_t                      SclkFcwRangeTable[NUM_SCLK_RANGE];
+
+	GB_VDROOP_TABLE_t                   BTCGB_VDROOP_TABLE[BTCGB_VDROOP_TABLE_MAX_ENTRIES];
+	SMU_QuadraticCoeffs                 AVFSGB_FUSE_TABLE[AVFSGB_VDROOP_TABLE_MAX_ENTRIES];
+};
+
+typedef struct SMU75_Discrete_DpmTable SMU75_Discrete_DpmTable;
+
+struct SMU75_Discrete_FanTable {
+	uint16_t FdoMode;
+	int16_t  TempMin;
+	int16_t  TempMed;
+	int16_t  TempMax;
+	int16_t  Slope1;
+	int16_t  Slope2;
+	int16_t  FdoMin;
+	int16_t  HystUp;
+	int16_t  HystDown;
+	int16_t  HystSlope;
+	int16_t  TempRespLim;
+	int16_t  TempCurr;
+	int16_t  SlopeCurr;
+	int16_t  PwmCurr;
+	uint32_t RefreshPeriod;
+	int16_t  FdoMax;
+	uint8_t  TempSrc;
+	int8_t   Padding;
+};
+
+typedef struct SMU75_Discrete_FanTable SMU75_Discrete_FanTable;
+
+#define SMU7_DISCRETE_GPIO_SCLK_DEBUG             4
+#define SMU7_DISCRETE_GPIO_SCLK_DEBUG_BIT         (0x1 << SMU7_DISCRETE_GPIO_SCLK_DEBUG)
+
+
+
+struct SMU7_MclkDpmScoreboard {
+	uint32_t PercentageBusy;
+
+	int32_t  PIDError;
+	int32_t  PIDIntegral;
+	int32_t  PIDOutput;
+
+	uint32_t SigmaDeltaAccum;
+	uint32_t SigmaDeltaOutput;
+	uint32_t SigmaDeltaLevel;
+
+	uint32_t UtilizationSetpoint;
+
+	uint8_t  TdpClampMode;
+	uint8_t  TdcClampMode;
+	uint8_t  ThermClampMode;
+	uint8_t  VoltageBusy;
+
+	int8_t   CurrLevel;
+	int8_t   TargLevel;
+	uint8_t  LevelChangeInProgress;
+	uint8_t  UpHyst;
+
+	uint8_t  DownHyst;
+	uint8_t  VoltageDownHyst;
+	uint8_t  DpmEnable;
+	uint8_t  DpmRunning;
+
+	uint8_t  DpmForce;
+	uint8_t  DpmForceLevel;
+	uint8_t  padding2;
+	uint8_t  McArbIndex;
+
+	uint32_t MinimumPerfMclk;
+
+	uint8_t  AcpiReq;
+	uint8_t  AcpiAck;
+	uint8_t  MclkSwitchInProgress;
+	uint8_t  MclkSwitchCritical;
+
+	uint8_t  IgnoreVBlank;
+	uint8_t  TargetMclkIndex;
+	uint8_t  TargetMvddIndex;
+	uint8_t  MclkSwitchResult;
+
+	uint16_t VbiFailureCount;
+	uint8_t  VbiWaitCounter;
+	uint8_t  EnabledLevelsChange;
+
+	uint16_t LevelResidencyCounters [SMU75_MAX_LEVELS_MEMORY];
+	uint16_t LevelSwitchCounters [SMU75_MAX_LEVELS_MEMORY];
+
+	void     (*TargetStateCalculator)(uint8_t);
+	void     (*SavedTargetStateCalculator)(uint8_t);
+
+	uint16_t AutoDpmInterval;
+	uint16_t AutoDpmRange;
+
+	uint16_t VbiTimeoutCount;
+	uint16_t MclkSwitchingTime;
+
+	uint8_t  fastSwitch;
+	uint8_t  Save_PIC_VDDGFX_EXIT;
+	uint8_t  Save_PIC_VDDGFX_ENTER;
+	uint8_t  VbiTimeout;
+
+	uint32_t HbmTempRegBackup;
+};
+
+typedef struct SMU7_MclkDpmScoreboard SMU7_MclkDpmScoreboard;
+
+struct SMU7_UlvScoreboard {
+	uint8_t     EnterUlv;
+	uint8_t     ExitUlv;
+	uint8_t     UlvActive;
+	uint8_t     WaitingForUlv;
+	uint8_t     UlvEnable;
+	uint8_t     UlvRunning;
+	uint8_t     UlvMasterEnable;
+	uint8_t     padding;
+	uint32_t    UlvAbortedCount;
+	uint32_t    UlvTimeStamp;
+};
+
+typedef struct SMU7_UlvScoreboard SMU7_UlvScoreboard;
+
+struct VddgfxSavedRegisters {
+	uint32_t GPU_DBG[3];
+	uint32_t MEC_BaseAddress_Hi;
+	uint32_t MEC_BaseAddress_Lo;
+	uint32_t THM_TMON0_CTRL2__RDIR_PRESENT;
+	uint32_t THM_TMON1_CTRL2__RDIR_PRESENT;
+	uint32_t CP_INT_CNTL;
+};
+
+typedef struct VddgfxSavedRegisters VddgfxSavedRegisters;
+
+struct SMU7_VddGfxScoreboard {
+	uint8_t     VddGfxEnable;
+	uint8_t     VddGfxActive;
+	uint8_t     VPUResetOccured;
+	uint8_t     padding;
+
+	uint32_t    VddGfxEnteredCount;
+	uint32_t    VddGfxAbortedCount;
+
+	uint32_t    VddGfxVid;
+
+	VddgfxSavedRegisters SavedRegisters;
+};
+
+typedef struct SMU7_VddGfxScoreboard SMU7_VddGfxScoreboard;
+
+struct SMU7_TdcLimitScoreboard {
+	uint8_t  Enable;
+	uint8_t  Running;
+	uint16_t Alpha;
+	uint32_t FilteredIddc;
+	uint32_t IddcLimit;
+	uint32_t IddcHyst;
+	SMU7_HystController_Data HystControllerData;
+};
+
+typedef struct SMU7_TdcLimitScoreboard SMU7_TdcLimitScoreboard;
+
+struct SMU7_PkgPwrLimitScoreboard {
+	uint8_t  Enable;
+	uint8_t  Running;
+	uint16_t Alpha;
+	uint32_t FilteredPkgPwr;
+	uint32_t Limit;
+	uint32_t Hyst;
+	uint32_t LimitFromDriver;
+	uint8_t PowerSharingEnabled;
+	uint8_t PowerSharingCounter;
+	uint8_t PowerSharingINTEnabled;
+	uint8_t GFXActivityCounterEnabled;
+	uint32_t EnergyCount;
+	uint32_t PSACTCount;
+	uint8_t RollOverRequired;
+	uint8_t RollOverCount;
+	uint8_t padding[2];
+	SMU7_HystController_Data HystControllerData;
+};
+
+typedef struct SMU7_PkgPwrLimitScoreboard SMU7_PkgPwrLimitScoreboard;
+
+struct SMU7_BapmScoreboard {
+	uint32_t source_powers[SMU75_DTE_SOURCES];
+	uint32_t source_powers_last[SMU75_DTE_SOURCES];
+	int32_t entity_temperatures[SMU75_NUM_GPU_TES];
+	int32_t initial_entity_temperatures[SMU75_NUM_GPU_TES];
+	int32_t Limit;
+	int32_t Hyst;
+	int32_t therm_influence_coeff_table[SMU75_DTE_ITERATIONS * SMU75_DTE_SOURCES * SMU75_DTE_SINKS * 2];
+	int32_t therm_node_table[SMU75_DTE_ITERATIONS * SMU75_DTE_SOURCES * SMU75_DTE_SINKS];
+	uint16_t ConfigTDPPowerScalar;
+	uint16_t FanSpeedPowerScalar;
+	uint16_t OverDrivePowerScalar;
+	uint16_t OverDriveLimitScalar;
+	uint16_t FinalPowerScalar;
+	uint8_t VariantID;
+	uint8_t spare997;
+
+	SMU7_HystController_Data HystControllerData;
+
+	int32_t temperature_gradient_slope;
+	int32_t temperature_gradient;
+	uint32_t measured_temperature;
+};
+
+
+typedef struct SMU7_BapmScoreboard SMU7_BapmScoreboard;
+
+struct SMU7_AcpiScoreboard {
+	uint32_t SavedInterruptMask[2];
+	uint8_t LastACPIRequest;
+	uint8_t CgBifResp;
+	uint8_t RequestType;
+	uint8_t Padding;
+	SMU75_Discrete_ACPILevel D0Level;
+};
+
+typedef struct SMU7_AcpiScoreboard SMU7_AcpiScoreboard;
+
+struct SMU75_Discrete_PmFuses {
+	uint8_t BapmVddCVidHiSidd[8];
+
+	uint8_t BapmVddCVidLoSidd[8];
+
+	uint8_t VddCVid[8];
+
+	uint8_t SviLoadLineEn;
+	uint8_t SviLoadLineVddC;
+	uint8_t SviLoadLineTrimVddC;
+	uint8_t SviLoadLineOffsetVddC;
+
+	uint16_t TDC_VDDC_PkgLimit;
+	uint8_t TDC_VDDC_ThrottleReleaseLimitPerc;
+	uint8_t TDC_MAWt;
+
+	uint8_t TdcWaterfallCtl;
+	uint8_t LPMLTemperatureMin;
+	uint8_t LPMLTemperatureMax;
+	uint8_t Reserved;
+
+	uint8_t LPMLTemperatureScaler[16];
+
+	int16_t FuzzyFan_ErrorSetDelta;
+	int16_t FuzzyFan_ErrorRateSetDelta;
+	int16_t FuzzyFan_PwmSetDelta;
+	uint16_t Reserved6;
+
+	uint8_t GnbLPML[16];
+
+	uint8_t GnbLPMLMaxVid;
+	uint8_t GnbLPMLMinVid;
+	uint8_t Reserved1[2];
+
+	uint16_t BapmVddCBaseLeakageHiSidd;
+	uint16_t BapmVddCBaseLeakageLoSidd;
+
+	uint16_t  VFT_Temp[3];
+	uint8_t   Version;
+	uint8_t   padding;
+
+	SMU_QuadraticCoeffs VFT_ATE[3];
+
+	SMU_QuadraticCoeffs AVFS_GB;
+	SMU_QuadraticCoeffs ATE_ACBTC_GB;
+
+	SMU_QuadraticCoeffs P2V;
+
+	uint32_t PsmCharzFreq;
+
+	uint16_t InversionVoltage;
+	uint16_t PsmCharzTemp;
+
+	uint32_t EnabledAvfsModules;
+
+	SMU_QuadraticCoeffs BtcGbv_CksOff;
+};
+
+typedef struct SMU75_Discrete_PmFuses SMU75_Discrete_PmFuses;
+
+struct SMU7_Discrete_Log_Header_Table {
+	uint32_t    version;
+	uint32_t    asic_id;
+	uint16_t    flags;
+	uint16_t    entry_size;
+	uint32_t    total_size;
+	uint32_t    num_of_entries;
+	uint8_t     type;
+	uint8_t     mode;
+	uint8_t     filler_0[2];
+	uint32_t    filler_1[2];
+};
+
+typedef struct SMU7_Discrete_Log_Header_Table SMU7_Discrete_Log_Header_Table;
+
+struct SMU7_Discrete_Log_Cntl {
+	uint8_t             Enabled;
+	uint8_t             Type;
+	uint8_t             padding[2];
+	uint32_t            BufferSize;
+	uint32_t            SamplesLogged;
+	uint32_t            SampleSize;
+	uint32_t            AddrL;
+	uint32_t            AddrH;
+};
+
+typedef struct SMU7_Discrete_Log_Cntl SMU7_Discrete_Log_Cntl;
+
+#if defined SMU__DGPU_ONLY
+#define CAC_ACC_NW_NUM_OF_SIGNALS 87
+#endif
+
+
+struct SMU7_Discrete_Cac_Collection_Table {
+	uint32_t temperature;
+	uint32_t cac_acc_nw[CAC_ACC_NW_NUM_OF_SIGNALS];
+};
+
+typedef struct SMU7_Discrete_Cac_Collection_Table SMU7_Discrete_Cac_Collection_Table;
+
+struct SMU7_Discrete_Cac_Verification_Table {
+	uint32_t VddcTotalPower;
+	uint32_t VddcLeakagePower;
+	uint32_t VddcConstantPower;
+	uint32_t VddcGfxDynamicPower;
+	uint32_t VddcUvdDynamicPower;
+	uint32_t VddcVceDynamicPower;
+	uint32_t VddcAcpDynamicPower;
+	uint32_t VddcPcieDynamicPower;
+	uint32_t VddcDceDynamicPower;
+	uint32_t VddcCurrent;
+	uint32_t VddcVoltage;
+	uint32_t VddciTotalPower;
+	uint32_t VddciLeakagePower;
+	uint32_t VddciConstantPower;
+	uint32_t VddciDynamicPower;
+	uint32_t Vddr1TotalPower;
+	uint32_t Vddr1LeakagePower;
+	uint32_t Vddr1ConstantPower;
+	uint32_t Vddr1DynamicPower;
+	uint32_t spare[4];
+	uint32_t temperature;
+};
+
+typedef struct SMU7_Discrete_Cac_Verification_Table SMU7_Discrete_Cac_Verification_Table;
+
+struct SMU7_Discrete_Pm_Status_Table {
+	int32_t T_meas_max[SMU75_THERMAL_INPUT_LOOP_COUNT];
+	int32_t T_meas_acc[SMU75_THERMAL_INPUT_LOOP_COUNT];
+
+	uint32_t I_calc_max;
+	uint32_t I_calc_acc;
+	uint32_t P_meas_acc;
+	uint32_t V_meas_load_acc;
+	uint32_t I_meas_acc;
+	uint32_t P_meas_acc_vddci;
+	uint32_t V_meas_load_acc_vddci;
+	uint32_t I_meas_acc_vddci;
+
+	uint16_t Sclk_dpm_residency[8];
+	uint16_t Uvd_dpm_residency[8];
+	uint16_t Vce_dpm_residency[8];
+	uint16_t Mclk_dpm_residency[4];
+
+	uint32_t P_roc_acc;
+	uint32_t PkgPwr_max;
+	uint32_t PkgPwr_acc;
+	uint32_t MclkSwitchingTime_max;
+	uint32_t MclkSwitchingTime_acc;
+	uint32_t FanPwm_acc;
+	uint32_t FanRpm_acc;
+	uint32_t Gfx_busy_acc;
+	uint32_t Mc_busy_acc;
+	uint32_t Fps_acc;
+
+	uint32_t AccCnt;
+};
+
+typedef struct SMU7_Discrete_Pm_Status_Table SMU7_Discrete_Pm_Status_Table;
+
+struct SMU7_Discrete_AutoWattMan_Status_Table {
+	int32_t T_meas_acc[SMU75_THERMAL_INPUT_LOOP_COUNT];
+	uint16_t Sclk_dpm_residency[8];
+	uint16_t Mclk_dpm_residency[4];
+	uint32_t TgpPwr_acc;
+	uint32_t Gfx_busy_acc;
+	uint32_t Mc_busy_acc;
+	uint32_t AccCnt;
+};
+
+typedef struct SMU7_Discrete_AutoWattMan_Status_Table SMU7_Discrete_AutoWattMan_Status_Table;
+
+#define SMU7_MAX_GFX_CU_COUNT 24
+#define SMU7_MIN_GFX_CU_COUNT  8
+#define SMU7_GFX_CU_PG_ENABLE_DC_MAX_CU_SHIFT 0
+#define SMU7_GFX_CU_PG_ENABLE_DC_MAX_CU_MASK  (0xFFFF << SMU7_GFX_CU_PG_ENABLE_DC_MAX_CU_SHIFT)
+#define SMU7_GFX_CU_PG_ENABLE_AC_MAX_CU_SHIFT 16
+#define SMU7_GFX_CU_PG_ENABLE_AC_MAX_CU_MASK  (0xFFFF << SMU7_GFX_CU_PG_ENABLE_AC_MAX_CU_SHIFT)
+
+struct SMU7_GfxCuPgScoreboard {
+	uint8_t Enabled;
+	uint8_t WaterfallUp;
+	uint8_t WaterfallDown;
+	uint8_t WaterfallLimit;
+	uint8_t CurrMaxCu;
+	uint8_t TargMaxCu;
+	uint8_t ClampMode;
+	uint8_t Active;
+	uint8_t MaxSupportedCu;
+	uint8_t MinSupportedCu;
+	uint8_t PendingGfxCuHostInterrupt;
+	uint8_t LastFilteredMaxCuInteger;
+	uint16_t FilteredMaxCu;
+	uint16_t FilteredMaxCuAlpha;
+	uint16_t FilterResetCount;
+	uint16_t FilterResetCountLimit;
+	uint8_t ForceCu;
+	uint8_t ForceCuCount;
+	uint8_t AcModeMaxCu;
+	uint8_t DcModeMaxCu;
+};
+
+typedef struct SMU7_GfxCuPgScoreboard SMU7_GfxCuPgScoreboard;
+
+#define SMU7_SCLK_CAC 0x561
+#define SMU7_MCLK_CAC 0xF9
+#define SMU7_VCLK_CAC 0x2DE
+#define SMU7_DCLK_CAC 0x2DE
+#define SMU7_ECLK_CAC 0x25E
+#define SMU7_ACLK_CAC 0x25E
+#define SMU7_SAMCLK_CAC 0x25E
+#define SMU7_DISPCLK_CAC 0x100
+#define SMU7_CAC_CONSTANT 0x2EE3430
+#define SMU7_CAC_CONSTANT_SHIFT 18
+
+#define SMU7_VDDCI_MCLK_CONST        1765
+#define SMU7_VDDCI_MCLK_CONST_SHIFT  16
+#define SMU7_VDDCI_VDDCI_CONST       50958
+#define SMU7_VDDCI_VDDCI_CONST_SHIFT 14
+#define SMU7_VDDCI_CONST             11781
+#define SMU7_VDDCI_STROBE_PWR        1331
+
+#define SMU7_VDDR1_CONST            693
+#define SMU7_VDDR1_CAC_WEIGHT       20
+#define SMU7_VDDR1_CAC_WEIGHT_SHIFT 19
+#define SMU7_VDDR1_STROBE_PWR       512
+
+#define SMU7_AREA_COEFF_UVD 0xA78
+#define SMU7_AREA_COEFF_VCE 0x190A
+#define SMU7_AREA_COEFF_ACP 0x22D1
+#define SMU7_AREA_COEFF_SAMU 0x534
+
+#define SMU7_THERM_OUT_MODE_DISABLE       0x0
+#define SMU7_THERM_OUT_MODE_THERM_ONLY    0x1
+#define SMU7_THERM_OUT_MODE_THERM_VRHOT   0x2
+
+#define SQ_Enable_MASK 0x1
+#define SQ_IR_MASK 0x2
+#define SQ_PCC_MASK 0x4
+#define SQ_EDC_MASK 0x8
+
+#define TCP_Enable_MASK 0x100
+#define TCP_IR_MASK 0x200
+#define TCP_PCC_MASK 0x400
+#define TCP_EDC_MASK 0x800
+
+#define TD_Enable_MASK 0x10000
+#define TD_IR_MASK 0x20000
+#define TD_PCC_MASK 0x40000
+#define TD_EDC_MASK 0x80000
+
+#define DB_Enable_MASK 0x1000000
+#define DB_IR_MASK 0x2000000
+#define DB_PCC_MASK 0x4000000
+#define DB_EDC_MASK 0x8000000
+
+#define SQ_Enable_SHIFT 0
+#define SQ_IR_SHIFT 1
+#define SQ_PCC_SHIFT 2
+#define SQ_EDC_SHIFT 3
+
+#define TCP_Enable_SHIFT 8
+#define TCP_IR_SHIFT 9
+#define TCP_PCC_SHIFT 10
+#define TCP_EDC_SHIFT 11
+
+#define TD_Enable_SHIFT 16
+#define TD_IR_SHIFT 17
+#define TD_PCC_SHIFT 18
+#define TD_EDC_SHIFT 19
+
+#define DB_Enable_SHIFT 24
+#define DB_IR_SHIFT 25
+#define DB_PCC_SHIFT 26
+#define DB_EDC_SHIFT 27
+
+#define PMFUSES_AVFSSIZE 104
+
+#define BTCGB0_Vdroop_Enable_MASK  0x1
+#define BTCGB1_Vdroop_Enable_MASK  0x2
+#define AVFSGB0_Vdroop_Enable_MASK 0x4
+#define AVFSGB1_Vdroop_Enable_MASK 0x8
+
+#define BTCGB0_Vdroop_Enable_SHIFT  0
+#define BTCGB1_Vdroop_Enable_SHIFT  1
+#define AVFSGB0_Vdroop_Enable_SHIFT 2
+#define AVFSGB1_Vdroop_Enable_SHIFT 3
+
+#pragma pack(pop)
+
+
+#endif
+
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega10_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/vega10_ppsmc.h
index c3ed737ab951..715b5a168831 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega10_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega10_ppsmc.h
@@ -131,6 +131,7 @@ typedef uint16_t PPSMC_Result;
 #define PPSMC_MSG_RunAcgInOpenLoop               0x5E
 #define PPSMC_MSG_InitializeAcg                  0x5F
 #define PPSMC_MSG_GetCurrPkgPwr                  0x61
+#define PPSMC_MSG_GetAverageGfxclkActualFrequency 0x63
 #define PPSMC_MSG_SetPccThrottleLevel            0x67
 #define PPSMC_MSG_UpdatePkgPwrPidAlpha           0x68
 #define PPSMC_Message_Count                      0x69
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
index fb696e3d06cf..2f8a3b983cce 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
@@ -412,8 +412,10 @@ typedef struct {
   QuadraticInt_t    ReservedEquation2;
   QuadraticInt_t    ReservedEquation3;
 
+	uint16_t     MinVoltageUlvGfx;
+	uint16_t     MinVoltageUlvSoc;
 
-  uint32_t     Reserved[15];
+	uint32_t     Reserved[14];
 
 
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile b/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
index 958755075421..0a200406a1ec 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
@@ -26,7 +26,7 @@
 SMU_MGR = smumgr.o smu8_smumgr.o tonga_smumgr.o fiji_smumgr.o \
 	  polaris10_smumgr.o iceland_smumgr.o \
 	  smu7_smumgr.o vega10_smumgr.o smu10_smumgr.o ci_smumgr.o \
-	  vega12_smumgr.o
+	  vega12_smumgr.o vegam_smumgr.o
 
 AMD_PP_SMUMGR = $(addprefix $(AMD_PP_PATH)/smumgr/,$(SMU_MGR))
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 08d000140eca..2d4ec8ac3a08 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -61,9 +61,6 @@
 
 #define SMC_RAM_END 0x40000
 
-#define VOLTAGE_SCALE               4
-#define VOLTAGE_VID_OFFSET_SCALE1    625
-#define VOLTAGE_VID_OFFSET_SCALE2    100
 #define CISLAND_MINIMUM_ENGINE_CLOCK 800
 #define CISLAND_MAX_DEEPSLEEP_DIVIDER_ID 5
 
@@ -211,9 +208,7 @@ static int ci_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 {
 	int ret;
 
-	if (!ci_is_smc_ram_running(hwmgr))
-		return -EINVAL;
-
+	cgs_write_register(hwmgr->device, mmSMC_RESP_0, 0);
 	cgs_write_register(hwmgr->device, mmSMC_MESSAGE_0, msg);
 
 	PHM_WAIT_FIELD_UNEQUAL(hwmgr, SMC_RESP_0, SMC_RESP, 0);
@@ -1182,7 +1177,6 @@ static int ci_populate_single_memory_level(
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 	int result = 0;
 	bool dll_state_on;
-	struct cgs_display_info info = {0};
 	uint32_t mclk_edc_wr_enable_threshold = 40000;
 	uint32_t mclk_edc_enable_threshold = 40000;
 	uint32_t mclk_strobe_mode_threshold = 40000;
@@ -1236,8 +1230,7 @@ static int ci_populate_single_memory_level(
 	/* default set to low watermark. Highest level will be set to high later.*/
 	memory_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
-	data->display_timing.num_existing_displays = info.display_count;
+	data->display_timing.num_existing_displays = hwmgr->display_config->num_display;
 
 	/* stutter mode not support on ci */
 
@@ -2784,7 +2777,6 @@ static int ci_smu_fini(struct pp_hwmgr *hwmgr)
 {
 	kfree(hwmgr->smu_backend);
 	hwmgr->smu_backend = NULL;
-	cgs_rel_firmware(hwmgr->device, CGS_UCODE_ID_SMU);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index faef78321446..53df9405f43a 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -53,10 +53,7 @@
 
 #define FIJI_SMC_SIZE 0x20000
 
-#define VOLTAGE_SCALE 4
 #define POWERTUNE_DEFAULT_SET_MAX    1
-#define VOLTAGE_VID_OFFSET_SCALE1   625
-#define VOLTAGE_VID_OFFSET_SCALE2   100
 #define VDDC_VDDCI_DELTA            300
 #define MC_CG_ARB_FREQ_F1           0x0b
 
@@ -288,8 +285,7 @@ static int fiji_start_smu(struct pp_hwmgr *hwmgr)
 	struct fiji_smumgr *priv = (struct fiji_smumgr *)(hwmgr->smu_backend);
 
 	/* Only start SMC if SMC RAM is not running */
-	if (!(smu7_is_smc_ram_running(hwmgr)
-		|| cgs_is_virtualization_enabled(hwmgr->device))) {
+	if (!smu7_is_smc_ram_running(hwmgr) && hwmgr->not_vf) {
 		/* Check if SMU is running in protected mode */
 		if (0 == PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device,
 				CGS_IND_REG__SMC,
@@ -307,13 +303,13 @@ static int fiji_start_smu(struct pp_hwmgr *hwmgr)
 	}
 
 	/* To initialize all clock gating before RLC loaded and running.*/
-	cgs_set_clockgating_state(hwmgr->device,
+	amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 			AMD_IP_BLOCK_TYPE_GFX, AMD_CG_STATE_GATE);
-	cgs_set_clockgating_state(hwmgr->device,
+	amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 			AMD_IP_BLOCK_TYPE_GMC, AMD_CG_STATE_GATE);
-	cgs_set_clockgating_state(hwmgr->device,
+	amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 			AMD_IP_BLOCK_TYPE_SDMA, AMD_CG_STATE_GATE);
-	cgs_set_clockgating_state(hwmgr->device,
+	amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
 			AMD_IP_BLOCK_TYPE_COMMON, AMD_CG_STATE_GATE);
 
 	/* Setup SoftRegsStart here for register lookup in case
@@ -335,10 +331,10 @@ static bool fiji_is_hw_avfs_present(struct pp_hwmgr *hwmgr)
 	uint32_t efuse = 0;
 	uint32_t mask = (1 << ((AVFS_EN_MSB - AVFS_EN_LSB) + 1)) - 1;
 
-	if (cgs_is_virtualization_enabled(hwmgr->device))
-		return 0;
+	if (!hwmgr->not_vf)
+		return false;
 
-	if (!atomctrl_read_efuse(hwmgr->device, AVFS_EN_LSB, AVFS_EN_MSB,
+	if (!atomctrl_read_efuse(hwmgr, AVFS_EN_LSB, AVFS_EN_MSB,
 			mask, &efuse)) {
 		if (efuse)
 			return true;
@@ -989,11 +985,11 @@ static int fiji_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 
 	threshold = clock * data->fast_watermark_threshold / 100;
 
-	data->display_timing.min_clock_in_sr = hwmgr->display_config.min_core_set_clock_in_sr;
+	data->display_timing.min_clock_in_sr = hwmgr->display_config->min_core_set_clock_in_sr;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SclkDeepSleep))
 		level->DeepSleepDivId = smu7_get_sleep_divider_id_from_clock(clock,
-								hwmgr->display_config.min_core_set_clock_in_sr);
+								hwmgr->display_config->min_core_set_clock_in_sr);
 
 
 	/* Default to slow, highest DPM level will be
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
index d4bb934e7334..415f691c3fa9 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
@@ -60,10 +60,7 @@
 
 #define ICELAND_SMC_SIZE               0x20000
 
-#define VOLTAGE_SCALE 4
 #define POWERTUNE_DEFAULT_SET_MAX    1
-#define VOLTAGE_VID_OFFSET_SCALE1   625
-#define VOLTAGE_VID_OFFSET_SCALE2   100
 #define MC_CG_ARB_FREQ_F1           0x0b
 #define VDDC_VDDCI_DELTA            200
 
@@ -932,7 +929,7 @@ static int iceland_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 	graphic_level->PowerThrottle = 0;
 
 	data->display_timing.min_clock_in_sr =
-			hwmgr->display_config.min_core_set_clock_in_sr;
+			hwmgr->display_config->min_core_set_clock_in_sr;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
 			PHM_PlatformCaps_SclkDeepSleep))
@@ -1236,7 +1233,6 @@ static int iceland_populate_single_memory_level(
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 	int result = 0;
 	bool dll_state_on;
-	struct cgs_display_info info = {0};
 	uint32_t mclk_edc_wr_enable_threshold = 40000;
 	uint32_t mclk_edc_enable_threshold = 40000;
 	uint32_t mclk_strobe_mode_threshold = 40000;
@@ -1283,8 +1279,7 @@ static int iceland_populate_single_memory_level(
 	/* default set to low watermark. Highest level will be set to high later.*/
 	memory_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
-	data->display_timing.num_existing_displays = info.display_count;
+	data->display_timing.num_existing_displays = hwmgr->display_config->num_display;
 
 	/* stutter mode not support on iceland */
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index 997a777dd35b..a8c6524f07e4 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -52,8 +52,6 @@
 #include "dce/dce_10_0_sh_mask.h"
 
 #define POLARIS10_SMC_SIZE 0x20000
-#define VOLTAGE_VID_OFFSET_SCALE1   625
-#define VOLTAGE_VID_OFFSET_SCALE2   100
 #define POWERTUNE_DEFAULT_SET_MAX    1
 #define VDDC_VDDCI_DELTA            200
 #define MC_CG_ARB_FREQ_F1           0x0b
@@ -295,25 +293,16 @@ static int polaris10_start_smu(struct pp_hwmgr *hwmgr)
 	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smu_backend);
 
 	/* Only start SMC if SMC RAM is not running */
-	if (!(smu7_is_smc_ram_running(hwmgr)
-		|| cgs_is_virtualization_enabled(hwmgr->device))) {
+	if (!smu7_is_smc_ram_running(hwmgr) && hwmgr->not_vf) {
 		smu_data->protected_mode = (uint8_t) (PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, SMU_FIRMWARE, SMU_MODE));
 		smu_data->smu7_data.security_hard_key = (uint8_t) (PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, SMU_FIRMWARE, SMU_SEL));
 
 		/* Check if SMU is running in protected mode */
-		if (smu_data->protected_mode == 0) {
+		if (smu_data->protected_mode == 0)
 			result = polaris10_start_smu_in_non_protection_mode(hwmgr);
-		} else {
+		else
 			result = polaris10_start_smu_in_protection_mode(hwmgr);
 
-			/* If failed, try with different security Key. */
-			if (result != 0) {
-				smu_data->smu7_data.security_hard_key ^= 1;
-				cgs_rel_firmware(hwmgr->device, CGS_UCODE_ID_SMU);
-				result = polaris10_start_smu_in_protection_mode(hwmgr);
-			}
-		}
-
 		if (result != 0)
 			PP_ASSERT_WITH_CODE(0, "Failed to load SMU ucode.", return result);
 
@@ -951,11 +940,11 @@ static int polaris10_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 	level->DownHyst = data->current_profile_setting.sclk_down_hyst;
 	level->VoltageDownHyst = 0;
 	level->PowerThrottle = 0;
-	data->display_timing.min_clock_in_sr = hwmgr->display_config.min_core_set_clock_in_sr;
+	data->display_timing.min_clock_in_sr = hwmgr->display_config->min_core_set_clock_in_sr;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SclkDeepSleep))
 		level->DeepSleepDivId = smu7_get_sleep_divider_id_from_clock(clock,
-								hwmgr->display_config.min_core_set_clock_in_sr);
+								hwmgr->display_config->min_core_set_clock_in_sr);
 
 	/* Default to slow, highest DPM level will be
 	 * set to PPSMC_DISPLAY_WATERMARK_LOW later.
@@ -1085,11 +1074,9 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr,
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	int result = 0;
-	struct cgs_display_info info = {0, 0, NULL};
 	uint32_t mclk_stutter_mode_threshold = 40000;
 	phm_ppt_v1_clock_voltage_dependency_table *vdd_dep_table = NULL;
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
 
 	if (hwmgr->od_enabled)
 		vdd_dep_table = (phm_ppt_v1_clock_voltage_dependency_table *)&data->odn_dpm_table.vdd_dependency_on_mclk;
@@ -1115,7 +1102,7 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr,
 	mem_level->StutterEnable = false;
 	mem_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
 
-	data->display_timing.num_existing_displays = info.display_count;
+	data->display_timing.num_existing_displays = hwmgr->display_config->num_display;
 
 	if (mclk_stutter_mode_threshold &&
 		(clock <= mclk_stutter_mode_threshold) &&
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
index bc53f2beda30..0a563f6fe9ea 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
@@ -23,7 +23,7 @@
 
 #include "smumgr.h"
 #include "smu10_inc.h"
-#include "pp_soc15.h"
+#include "soc15_common.h"
 #include "smu10_smumgr.h"
 #include "ppatomctrl.h"
 #include "rv_ppsmc.h"
@@ -33,8 +33,6 @@
 #include "pp_debug.h"
 
 
-#define VOLTAGE_SCALE 4
-
 #define BUFFER_SIZE                 80000
 #define MAX_STRING_SIZE             15
 #define BUFFER_SIZETWO              131072
@@ -49,48 +47,41 @@
 
 static uint32_t smu10_wait_for_response(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t reg;
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
+	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
 
 	phm_wait_for_register_unequal(hwmgr, reg,
 			0, MP1_C2PMSG_90__CONTENT_MASK);
 
-	return cgs_read_register(hwmgr->device, reg);
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
 }
 
 static int smu10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
 		uint16_t msg)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_66_BASE_IDX, mmMP1_SMN_C2PMSG_66);
-	cgs_write_register(hwmgr->device, reg, msg);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
 
 	return 0;
 }
 
 static int smu10_read_arg_from_smc(struct pp_hwmgr *hwmgr)
 {
-	uint32_t reg;
-
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_82_BASE_IDX, mmMP1_SMN_C2PMSG_82);
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	return cgs_read_register(hwmgr->device, reg);
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
 }
 
 static int smu10_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	smu10_wait_for_response(hwmgr);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
-	cgs_write_register(hwmgr->device, reg, 0);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
 	smu10_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -104,17 +95,13 @@ static int smu10_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 static int smu10_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 		uint16_t msg, uint32_t parameter)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	smu10_wait_for_response(hwmgr);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
-	cgs_write_register(hwmgr->device, reg, 0);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_82_BASE_IDX, mmMP1_SMN_C2PMSG_82);
-	cgs_write_register(hwmgr->device, reg, parameter);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
 
 	smu10_send_msg_to_smc_without_waiting(hwmgr, msg);
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index 0399c10d2be0..d644a9bb9078 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -167,24 +167,25 @@ int smu7_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 {
 	int ret;
 
-	if (!smu7_is_smc_ram_running(hwmgr))
-		return -EINVAL;
-
-
 	PHM_WAIT_FIELD_UNEQUAL(hwmgr, SMC_RESP_0, SMC_RESP, 0);
 
 	ret = PHM_READ_FIELD(hwmgr->device, SMC_RESP_0, SMC_RESP);
 
-	if (ret != 1)
-		pr_info("\n failed to send pre message %x ret is %d \n",  msg, ret);
+	if (ret == 0xFE)
+		pr_debug("last message was not supported\n");
+	else if (ret != 1)
+		pr_info("\n last message was failed ret is %d\n", ret);
 
+	cgs_write_register(hwmgr->device, mmSMC_RESP_0, 0);
 	cgs_write_register(hwmgr->device, mmSMC_MESSAGE_0, msg);
 
 	PHM_WAIT_FIELD_UNEQUAL(hwmgr, SMC_RESP_0, SMC_RESP, 0);
 
 	ret = PHM_READ_FIELD(hwmgr->device, SMC_RESP_0, SMC_RESP);
 
-	if (ret != 1)
+	if (ret == 0xFE)
+		pr_debug("message %x was not supported\n", msg);
+	else if (ret != 1)
 		pr_info("\n failed to send message %x ret is %d \n",  msg, ret);
 
 	return 0;
@@ -199,10 +200,6 @@ int smu7_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr, uint16_t msg)
 
 int smu7_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr, uint16_t msg, uint32_t parameter)
 {
-	if (!smu7_is_smc_ram_running(hwmgr)) {
-		return -EINVAL;
-	}
-
 	PHM_WAIT_FIELD_UNEQUAL(hwmgr, SMC_RESP_0, SMC_RESP, 0);
 
 	cgs_write_register(hwmgr->device, mmSMC_MSG_ARG_0, parameter);
@@ -231,16 +228,6 @@ int smu7_send_msg_to_smc_offset(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-int smu7_wait_for_smc_inactive(struct pp_hwmgr *hwmgr)
-{
-	if (!smu7_is_smc_ram_running(hwmgr))
-		return -EINVAL;
-
-	PHM_WAIT_VFPF_INDIRECT_FIELD(hwmgr, SMC_IND, SMC_SYSCON_CLOCK_CNTL_0, cken, 0);
-	return 0;
-}
-
-
 enum cgs_ucode_id smu7_convert_fw_type_to_cgs(uint32_t fw_type)
 {
 	enum cgs_ucode_id result = CGS_UCODE_ID_MAXIMUM;
@@ -296,11 +283,9 @@ int smu7_read_smc_sram_dword(struct pp_hwmgr *hwmgr, uint32_t smc_addr, uint32_t
 
 	result = smu7_set_smc_sram_address(hwmgr, smc_addr, limit);
 
-	if (result)
-		return result;
+	*value = result ? 0 : cgs_read_register(hwmgr->device, mmSMC_IND_DATA_11);
 
-	*value = cgs_read_register(hwmgr->device, mmSMC_IND_DATA_11);
-	return 0;
+	return result;
 }
 
 int smu7_write_smc_sram_dword(struct pp_hwmgr *hwmgr, uint32_t smc_addr, uint32_t value, uint32_t limit)
@@ -375,7 +360,7 @@ static int smu7_populate_single_firmware_entry(struct pp_hwmgr *hwmgr,
 		entry->meta_data_addr_low = 0;
 
 		/* digest need be excluded out */
-		if (cgs_is_virtualization_enabled(hwmgr->device))
+		if (!hwmgr->not_vf)
 			info.image_size -= 20;
 		entry->data_size_byte = info.image_size;
 		entry->num_register_entries = 0;
@@ -409,7 +394,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 					0x0);
 
 	if (hwmgr->chip_id > CHIP_TOPAZ) { /* add support for Topaz */
-		if (!cgs_is_virtualization_enabled(hwmgr->device)) {
+		if (hwmgr->not_vf) {
 			smu7_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SMU_DRAM_ADDR_HI,
 						upper_32_bits(smu_data->smu_buffer.mc_addr));
@@ -467,7 +452,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
-	if (cgs_is_virtualization_enabled(hwmgr->device))
+	if (!hwmgr->not_vf)
 		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_MEC_STORAGE, &toc->entry[toc->num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
@@ -608,7 +593,7 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 	smu_data->header = smu_data->header_buffer.kaddr;
 	smu_data->header_buffer.mc_addr = mc_addr;
 
-	if (cgs_is_virtualization_enabled(hwmgr->device))
+	if (!hwmgr->not_vf)
 		return 0;
 
 	smu_data->smu_buffer.data_size = 200*4096;
@@ -643,13 +628,12 @@ int smu7_smu_fini(struct pp_hwmgr *hwmgr)
 					&smu_data->header_buffer.mc_addr,
 					&smu_data->header_buffer.kaddr);
 
-	if (!cgs_is_virtualization_enabled(hwmgr->device))
+	if (hwmgr->not_vf)
 		amdgpu_bo_free_kernel(&smu_data->smu_buffer.handle,
 					&smu_data->smu_buffer.mc_addr,
 					&smu_data->smu_buffer.kaddr);
 
 	kfree(hwmgr->smu_backend);
 	hwmgr->smu_backend = NULL;
-	cgs_rel_firmware(hwmgr->device, CGS_UCODE_ID_SMU);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
index 126d300259ba..39c9bfda0ab4 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
@@ -67,7 +67,6 @@ int smu7_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr, uint16_t msg,
 int smu7_send_msg_to_smc_with_parameter_without_waiting(struct pp_hwmgr *hwmgr,
 						uint16_t msg, uint32_t parameter);
 int smu7_send_msg_to_smc_offset(struct pp_hwmgr *hwmgr);
-int smu7_wait_for_smc_inactive(struct pp_hwmgr *hwmgr);
 
 enum cgs_ucode_id smu7_convert_fw_type_to_cgs(uint32_t fw_type);
 int smu7_read_smc_sram_dword(struct pp_hwmgr *hwmgr, uint32_t smc_addr,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index c28b60aae5f8..c9837935f0f5 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -41,9 +41,11 @@ MODULE_FIRMWARE("amdgpu/polaris11_smc.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_smc_sk.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_k_smc.bin");
 MODULE_FIRMWARE("amdgpu/polaris12_smc.bin");
+MODULE_FIRMWARE("amdgpu/vegam_smc.bin");
 MODULE_FIRMWARE("amdgpu/vega10_smc.bin");
 MODULE_FIRMWARE("amdgpu/vega10_acg_smc.bin");
 MODULE_FIRMWARE("amdgpu/vega12_smc.bin");
+MODULE_FIRMWARE("amdgpu/vega20_smc.bin");
 
 int smum_thermal_avfs_enable(struct pp_hwmgr *hwmgr)
 {
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
index b51d7468c3e7..782b19fc2e70 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
@@ -55,11 +55,7 @@
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
-
-#define VOLTAGE_SCALE 4
 #define POWERTUNE_DEFAULT_SET_MAX    1
-#define VOLTAGE_VID_OFFSET_SCALE1   625
-#define VOLTAGE_VID_OFFSET_SCALE2   100
 #define MC_CG_ARB_FREQ_F1           0x0b
 #define VDDC_VDDCI_DELTA            200
 
@@ -199,8 +195,7 @@ static int tonga_start_smu(struct pp_hwmgr *hwmgr)
 	int result;
 
 	/* Only start SMC if SMC RAM is not running */
-	if (!(smu7_is_smc_ram_running(hwmgr) ||
-		cgs_is_virtualization_enabled(hwmgr->device))) {
+	if (!smu7_is_smc_ram_running(hwmgr) && hwmgr->not_vf) {
 		/*Check if SMU is running in protected mode*/
 		if (0 == PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
 					SMU_FIRMWARE, SMU_MODE)) {
@@ -651,7 +646,7 @@ static int tonga_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 	graphic_level->PowerThrottle = 0;
 
 	data->display_timing.min_clock_in_sr =
-			hwmgr->display_config.min_core_set_clock_in_sr;
+			hwmgr->display_config->min_core_set_clock_in_sr;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
 			PHM_PlatformCaps_SclkDeepSleep))
@@ -957,18 +952,17 @@ static int tonga_populate_single_memory_level(
 		SMU72_Discrete_MemoryLevel *memory_level
 		)
 {
-	uint32_t mvdd = 0;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 	struct phm_ppt_v1_information *pptable_info =
 			  (struct phm_ppt_v1_information *)(hwmgr->pptable);
-	int result = 0;
-	bool dll_state_on;
-	struct cgs_display_info info = {0};
 	uint32_t mclk_edc_wr_enable_threshold = 40000;
 	uint32_t mclk_stutter_mode_threshold = 30000;
 	uint32_t mclk_edc_enable_threshold = 40000;
 	uint32_t mclk_strobe_mode_threshold = 40000;
 	phm_ppt_v1_clock_voltage_dependency_table *vdd_dep_table = NULL;
+	int result = 0;
+	bool dll_state_on;
+	uint32_t mvdd = 0;
 
 	if (hwmgr->od_enabled)
 		vdd_dep_table = (phm_ppt_v1_clock_voltage_dependency_table *)&data->odn_dpm_table.vdd_dependency_on_mclk;
@@ -1009,8 +1003,7 @@ static int tonga_populate_single_memory_level(
 	/* default set to low watermark. Highest level will be set to high later.*/
 	memory_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
 
-	cgs_get_active_displays_info(hwmgr->device, &info);
-	data->display_timing.num_existing_displays = info.display_count;
+	data->display_timing.num_existing_displays = hwmgr->display_config->num_display;
 
 	if ((mclk_stutter_mode_threshold != 0) &&
 	    (memory_clock <= mclk_stutter_mode_threshold) &&
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
index 4aafb043bcb0..e84669c448a3 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
@@ -23,7 +23,7 @@
 
 #include "smumgr.h"
 #include "vega10_inc.h"
-#include "pp_soc15.h"
+#include "soc15_common.h"
 #include "vega10_smumgr.h"
 #include "vega10_hwmgr.h"
 #include "vega10_ppsmc.h"
@@ -35,8 +35,6 @@
 #define AVFS_EN_MSB		1568
 #define AVFS_EN_LSB		1568
 
-#define VOLTAGE_SCALE	4
-
 /* Microcode file is stored in this buffer */
 #define BUFFER_SIZE                 80000
 #define MAX_STRING_SIZE             15
@@ -54,18 +52,13 @@
 
 static bool vega10_is_smc_ram_running(struct pp_hwmgr *hwmgr)
 {
-	uint32_t mp1_fw_flags, reg;
-
-	reg = soc15_get_register_offset(NBIF_HWID, 0,
-			mmPCIE_INDEX2_BASE_IDX, mmPCIE_INDEX2);
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t mp1_fw_flags;
 
-	cgs_write_register(hwmgr->device, reg,
+	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
 			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
 
-	reg = soc15_get_register_offset(NBIF_HWID, 0,
-			mmPCIE_DATA2_BASE_IDX, mmPCIE_DATA2);
-
-	mp1_fw_flags = cgs_read_register(hwmgr->device, reg);
+	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
 
 	if (mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK)
 		return true;
@@ -81,11 +74,11 @@ static bool vega10_is_smc_ram_running(struct pp_hwmgr *hwmgr)
  */
 static uint32_t vega10_wait_for_response(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t reg;
 	uint32_t ret;
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
+	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
 
 	ret = phm_wait_for_register_unequal(hwmgr, reg,
 			0, MP1_C2PMSG_90__CONTENT_MASK);
@@ -93,7 +86,7 @@ static uint32_t vega10_wait_for_response(struct pp_hwmgr *hwmgr)
 	if (ret)
 		pr_err("No response from smu\n");
 
-	return cgs_read_register(hwmgr->device, reg);
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
 }
 
 /*
@@ -105,11 +98,9 @@ static uint32_t vega10_wait_for_response(struct pp_hwmgr *hwmgr)
 static int vega10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
 		uint16_t msg)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_66_BASE_IDX, mmMP1_SMN_C2PMSG_66);
-	cgs_write_register(hwmgr->device, reg, msg);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
 
 	return 0;
 }
@@ -122,14 +113,12 @@ static int vega10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
  */
 static int vega10_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t ret;
 
 	vega10_wait_for_response(hwmgr);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
-	cgs_write_register(hwmgr->device, reg, 0);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
 	vega10_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -150,18 +139,14 @@ static int vega10_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 static int vega10_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 		uint16_t msg, uint32_t parameter)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t ret;
 
 	vega10_wait_for_response(hwmgr);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
-	cgs_write_register(hwmgr->device, reg, 0);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_82_BASE_IDX, mmMP1_SMN_C2PMSG_82);
-	cgs_write_register(hwmgr->device, reg, parameter);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
 
 	vega10_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -174,12 +159,9 @@ static int vega10_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 
 static int vega10_get_argument(struct pp_hwmgr *hwmgr)
 {
-	uint32_t reg;
-
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_82_BASE_IDX, mmMP1_SMN_C2PMSG_82);
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	return cgs_read_register(hwmgr->device, reg);
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
 }
 
 static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
index 651a3f28734b..7d9b40e8b1bf 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
@@ -23,7 +23,7 @@
 
 #include "smumgr.h"
 #include "vega12_inc.h"
-#include "pp_soc15.h"
+#include "soc15_common.h"
 #include "vega12_smumgr.h"
 #include "vega12_ppsmc.h"
 #include "vega12/smu9_driver_if.h"
@@ -44,18 +44,13 @@
 
 static bool vega12_is_smc_ram_running(struct pp_hwmgr *hwmgr)
 {
-	uint32_t mp1_fw_flags, reg;
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t mp1_fw_flags;
 
-	reg = soc15_get_register_offset(NBIF_HWID, 0,
-			mmPCIE_INDEX2_BASE_IDX, mmPCIE_INDEX2);
-
-	cgs_write_register(hwmgr->device, reg,
+	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
 			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
 
-	reg = soc15_get_register_offset(NBIF_HWID, 0,
-			mmPCIE_DATA2_BASE_IDX, mmPCIE_DATA2);
-
-	mp1_fw_flags = cgs_read_register(hwmgr->device, reg);
+	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
 
 	if ((mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) >>
 				MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT)
@@ -72,15 +67,15 @@ static bool vega12_is_smc_ram_running(struct pp_hwmgr *hwmgr)
  */
 static uint32_t vega12_wait_for_response(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	uint32_t reg;
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
+	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
 
 	phm_wait_for_register_unequal(hwmgr, reg,
 			0, MP1_C2PMSG_90__CONTENT_MASK);
 
-	return cgs_read_register(hwmgr->device, reg);
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
 }
 
 /*
@@ -92,11 +87,9 @@ static uint32_t vega12_wait_for_response(struct pp_hwmgr *hwmgr)
 int vega12_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
 		uint16_t msg)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_66_BASE_IDX, mmMP1_SMN_C2PMSG_66);
-	cgs_write_register(hwmgr->device, reg, msg);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
 
 	return 0;
 }
@@ -109,13 +102,11 @@ int vega12_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
  */
 int vega12_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	vega12_wait_for_response(hwmgr);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
-	cgs_write_register(hwmgr->device, reg, 0);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
 	vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -135,17 +126,13 @@ int vega12_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 int vega12_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 		uint16_t msg, uint32_t parameter)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	vega12_wait_for_response(hwmgr);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_90_BASE_IDX, mmMP1_SMN_C2PMSG_90);
-	cgs_write_register(hwmgr->device, reg, 0);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_82_BASE_IDX, mmMP1_SMN_C2PMSG_82);
-	cgs_write_register(hwmgr->device, reg, parameter);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
 
 	vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -166,11 +153,9 @@ int vega12_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 int vega12_send_msg_to_smc_with_parameter_without_waiting(
 		struct pp_hwmgr *hwmgr, uint16_t msg, uint32_t parameter)
 {
-	uint32_t reg;
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_66_BASE_IDX, mmMP1_SMN_C2PMSG_66);
-	cgs_write_register(hwmgr->device, reg, parameter);
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, parameter);
 
 	return vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
 }
@@ -183,12 +168,9 @@ int vega12_send_msg_to_smc_with_parameter_without_waiting(
  */
 int vega12_read_arg_from_smc(struct pp_hwmgr *hwmgr, uint32_t *arg)
 {
-	uint32_t reg;
-
-	reg = soc15_get_register_offset(MP1_HWID, 0,
-			mmMP1_SMN_C2PMSG_82_BASE_IDX, mmMP1_SMN_C2PMSG_82);
+	struct amdgpu_device *adev = hwmgr->adev;
 
-	*arg = cgs_read_register(hwmgr->device, reg);
+	*arg = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
new file mode 100644
index 000000000000..2de48959ac93
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -0,0 +1,2383 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "pp_debug.h"
+#include "smumgr.h"
+#include "smu_ucode_xfer_vi.h"
+#include "vegam_smumgr.h"
+#include "smu/smu_7_1_3_d.h"
+#include "smu/smu_7_1_3_sh_mask.h"
+#include "gmc/gmc_8_1_d.h"
+#include "gmc/gmc_8_1_sh_mask.h"
+#include "oss/oss_3_0_d.h"
+#include "gca/gfx_8_0_d.h"
+#include "bif/bif_5_0_d.h"
+#include "bif/bif_5_0_sh_mask.h"
+#include "ppatomctrl.h"
+#include "cgs_common.h"
+#include "smu7_ppsmc.h"
+
+#include "smu7_dyn_defaults.h"
+
+#include "smu7_hwmgr.h"
+#include "hardwaremanager.h"
+#include "ppatomctrl.h"
+#include "atombios.h"
+#include "pppcielanes.h"
+
+#include "dce/dce_11_2_d.h"
+#include "dce/dce_11_2_sh_mask.h"
+
+#define PPVEGAM_TARGETACTIVITY_DFLT                     50
+
+#define VOLTAGE_VID_OFFSET_SCALE1   625
+#define VOLTAGE_VID_OFFSET_SCALE2   100
+#define POWERTUNE_DEFAULT_SET_MAX    1
+#define VDDC_VDDCI_DELTA            200
+#define MC_CG_ARB_FREQ_F1           0x0b
+
+#define STRAP_ASIC_RO_LSB    2168
+#define STRAP_ASIC_RO_MSB    2175
+
+#define PPSMC_MSG_ApplyAvfsCksOffVoltage      ((uint16_t) 0x415)
+#define PPSMC_MSG_EnableModeSwitchRLCNotification  ((uint16_t) 0x305)
+
+static const struct vegam_pt_defaults
+vegam_power_tune_data_set_array[POWERTUNE_DEFAULT_SET_MAX] = {
+	/* sviLoadLIneEn, SviLoadLineVddC, TDC_VDDC_ThrottleReleaseLimitPerc, TDC_MAWt,
+	 * TdcWaterfallCtl, DTEAmbientTempBase, DisplayCac, BAPM_TEMP_GRADIENT */
+	{ 1, 0xF, 0xFD, 0x19, 5, 45, 0, 0xB0000,
+	{ 0x79, 0x253, 0x25D, 0xAE, 0x72, 0x80, 0x83, 0x86, 0x6F, 0xC8, 0xC9, 0xC9, 0x2F, 0x4D, 0x61},
+	{ 0x17C, 0x172, 0x180, 0x1BC, 0x1B3, 0x1BD, 0x206, 0x200, 0x203, 0x25D, 0x25A, 0x255, 0x2C3, 0x2C5, 0x2B4 } },
+};
+
+static const sclkFcwRange_t Range_Table[NUM_SCLK_RANGE] = {
+			{VCO_2_4, POSTDIV_DIV_BY_16,  75, 160, 112},
+			{VCO_3_6, POSTDIV_DIV_BY_16, 112, 224, 160},
+			{VCO_2_4, POSTDIV_DIV_BY_8,   75, 160, 112},
+			{VCO_3_6, POSTDIV_DIV_BY_8,  112, 224, 160},
+			{VCO_2_4, POSTDIV_DIV_BY_4,   75, 160, 112},
+			{VCO_3_6, POSTDIV_DIV_BY_4,  112, 216, 160},
+			{VCO_2_4, POSTDIV_DIV_BY_2,   75, 160, 108},
+			{VCO_3_6, POSTDIV_DIV_BY_2,  112, 216, 160} };
+
+static int vegam_smu_init(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data;
+
+	smu_data = kzalloc(sizeof(struct vegam_smumgr), GFP_KERNEL);
+	if (smu_data == NULL)
+		return -ENOMEM;
+
+	hwmgr->smu_backend = smu_data;
+
+	if (smu7_init(hwmgr)) {
+		kfree(smu_data);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int vegam_start_smu_in_protection_mode(struct pp_hwmgr *hwmgr)
+{
+	int result = 0;
+
+	/* Wait for smc boot up */
+	/* PHM_WAIT_VFPF_INDIRECT_FIELD_UNEQUAL(smumgr, SMC_IND, RCU_UC_EVENTS, boot_seq_done, 0) */
+
+	/* Assert reset */
+	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+					SMC_SYSCON_RESET_CNTL, rst_reg, 1);
+
+	result = smu7_upload_smu_firmware_image(hwmgr);
+	if (result != 0)
+		return result;
+
+	/* Clear status */
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixSMU_STATUS, 0);
+
+	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+					SMC_SYSCON_CLOCK_CNTL_0, ck_disable, 0);
+
+	/* De-assert reset */
+	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+					SMC_SYSCON_RESET_CNTL, rst_reg, 0);
+
+
+	PHM_WAIT_VFPF_INDIRECT_FIELD(hwmgr, SMC_IND, RCU_UC_EVENTS, INTERRUPTS_ENABLED, 1);
+
+
+	/* Call Test SMU message with 0x20000 offset to trigger SMU start */
+	smu7_send_msg_to_smc_offset(hwmgr);
+
+	/* Wait done bit to be set */
+	/* Check pass/failed indicator */
+
+	PHM_WAIT_VFPF_INDIRECT_FIELD_UNEQUAL(hwmgr, SMC_IND, SMU_STATUS, SMU_DONE, 0);
+
+	if (1 != PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+						SMU_STATUS, SMU_PASS))
+		PP_ASSERT_WITH_CODE(false, "SMU Firmware start failed!", return -1);
+
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixFIRMWARE_FLAGS, 0);
+
+	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+					SMC_SYSCON_RESET_CNTL, rst_reg, 1);
+
+	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+					SMC_SYSCON_RESET_CNTL, rst_reg, 0);
+
+	/* Wait for firmware to initialize */
+	PHM_WAIT_VFPF_INDIRECT_FIELD(hwmgr, SMC_IND, FIRMWARE_FLAGS, INTERRUPTS_ENABLED, 1);
+
+	return result;
+}
+
+static int vegam_start_smu_in_non_protection_mode(struct pp_hwmgr *hwmgr)
+{
+	int result = 0;
+
+	/* wait for smc boot up */
+	PHM_WAIT_VFPF_INDIRECT_FIELD_UNEQUAL(hwmgr, SMC_IND, RCU_UC_EVENTS, boot_seq_done, 0);
+
+	/* Clear firmware interrupt enable flag */
+	/* PHM_WRITE_VFPF_INDIRECT_FIELD(pSmuMgr, SMC_IND, SMC_SYSCON_MISC_CNTL, pre_fetcher_en, 1); */
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+				ixFIRMWARE_FLAGS, 0);
+
+	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+					SMC_SYSCON_RESET_CNTL,
+					rst_reg, 1);
+
+	result = smu7_upload_smu_firmware_image(hwmgr);
+	if (result != 0)
+		return result;
+
+	/* Set smc instruct start point at 0x0 */
+	smu7_program_jump_on_start(hwmgr);
+
+	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+					SMC_SYSCON_CLOCK_CNTL_0, ck_disable, 0);
+
+	PHM_WRITE_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+					SMC_SYSCON_RESET_CNTL, rst_reg, 0);
+
+	/* Wait for firmware to initialize */
+
+	PHM_WAIT_VFPF_INDIRECT_FIELD(hwmgr, SMC_IND,
+					FIRMWARE_FLAGS, INTERRUPTS_ENABLED, 1);
+
+	return result;
+}
+
+static int vegam_start_smu(struct pp_hwmgr *hwmgr)
+{
+	int result = 0;
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+
+	/* Only start SMC if SMC RAM is not running */
+	if (!smu7_is_smc_ram_running(hwmgr) && hwmgr->not_vf) {
+		smu_data->protected_mode = (uint8_t)(PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device,
+				CGS_IND_REG__SMC, SMU_FIRMWARE, SMU_MODE));
+		smu_data->smu7_data.security_hard_key = (uint8_t)(PHM_READ_VFPF_INDIRECT_FIELD(
+				hwmgr->device, CGS_IND_REG__SMC, SMU_FIRMWARE, SMU_SEL));
+
+		/* Check if SMU is running in protected mode */
+		if (smu_data->protected_mode == 0)
+			result = vegam_start_smu_in_non_protection_mode(hwmgr);
+		else
+			result = vegam_start_smu_in_protection_mode(hwmgr);
+
+		if (result != 0)
+			PP_ASSERT_WITH_CODE(0, "Failed to load SMU ucode.", return result);
+	}
+
+	/* Setup SoftRegsStart here for register lookup in case DummyBackEnd is used and ProcessFirmwareHeader is not executed */
+	smu7_read_smc_sram_dword(hwmgr,
+			SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU75_Firmware_Header, SoftRegisters),
+			&(smu_data->smu7_data.soft_regs_start),
+			0x40000);
+
+	result = smu7_request_smu_load_fw(hwmgr);
+
+	return result;
+}
+
+static int vegam_process_firmware_header(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	uint32_t tmp;
+	int result;
+	bool error = false;
+
+	result = smu7_read_smc_sram_dword(hwmgr,
+			SMU7_FIRMWARE_HEADER_LOCATION +
+			offsetof(SMU75_Firmware_Header, DpmTable),
+			&tmp, SMC_RAM_END);
+
+	if (0 == result)
+		smu_data->smu7_data.dpm_table_start = tmp;
+
+	error |= (0 != result);
+
+	result = smu7_read_smc_sram_dword(hwmgr,
+			SMU7_FIRMWARE_HEADER_LOCATION +
+			offsetof(SMU75_Firmware_Header, SoftRegisters),
+			&tmp, SMC_RAM_END);
+
+	if (!result) {
+		data->soft_regs_start = tmp;
+		smu_data->smu7_data.soft_regs_start = tmp;
+	}
+
+	error |= (0 != result);
+
+	result = smu7_read_smc_sram_dword(hwmgr,
+			SMU7_FIRMWARE_HEADER_LOCATION +
+			offsetof(SMU75_Firmware_Header, mcRegisterTable),
+			&tmp, SMC_RAM_END);
+
+	if (!result)
+		smu_data->smu7_data.mc_reg_table_start = tmp;
+
+	result = smu7_read_smc_sram_dword(hwmgr,
+			SMU7_FIRMWARE_HEADER_LOCATION +
+			offsetof(SMU75_Firmware_Header, FanTable),
+			&tmp, SMC_RAM_END);
+
+	if (!result)
+		smu_data->smu7_data.fan_table_start = tmp;
+
+	error |= (0 != result);
+
+	result = smu7_read_smc_sram_dword(hwmgr,
+			SMU7_FIRMWARE_HEADER_LOCATION +
+			offsetof(SMU75_Firmware_Header, mcArbDramTimingTable),
+			&tmp, SMC_RAM_END);
+
+	if (!result)
+		smu_data->smu7_data.arb_table_start = tmp;
+
+	error |= (0 != result);
+
+	result = smu7_read_smc_sram_dword(hwmgr,
+			SMU7_FIRMWARE_HEADER_LOCATION +
+			offsetof(SMU75_Firmware_Header, Version),
+			&tmp, SMC_RAM_END);
+
+	if (!result)
+		hwmgr->microcode_version_info.SMC = tmp;
+
+	error |= (0 != result);
+
+	return error ? -1 : 0;
+}
+
+static bool vegam_is_dpm_running(struct pp_hwmgr *hwmgr)
+{
+	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
+			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON))
+			? true : false;
+}
+
+static uint32_t vegam_get_mac_definition(uint32_t value)
+{
+	switch (value) {
+	case SMU_MAX_LEVELS_GRAPHICS:
+		return SMU75_MAX_LEVELS_GRAPHICS;
+	case SMU_MAX_LEVELS_MEMORY:
+		return SMU75_MAX_LEVELS_MEMORY;
+	case SMU_MAX_LEVELS_LINK:
+		return SMU75_MAX_LEVELS_LINK;
+	case SMU_MAX_ENTRIES_SMIO:
+		return SMU75_MAX_ENTRIES_SMIO;
+	case SMU_MAX_LEVELS_VDDC:
+		return SMU75_MAX_LEVELS_VDDC;
+	case SMU_MAX_LEVELS_VDDGFX:
+		return SMU75_MAX_LEVELS_VDDGFX;
+	case SMU_MAX_LEVELS_VDDCI:
+		return SMU75_MAX_LEVELS_VDDCI;
+	case SMU_MAX_LEVELS_MVDD:
+		return SMU75_MAX_LEVELS_MVDD;
+	case SMU_UVD_MCLK_HANDSHAKE_DISABLE:
+		return SMU7_UVD_MCLK_HANDSHAKE_DISABLE |
+				SMU7_VCE_MCLK_HANDSHAKE_DISABLE;
+	}
+
+	pr_warn("can't get the mac of %x\n", value);
+	return 0;
+}
+
+static int vegam_update_uvd_smc_table(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	uint32_t mm_boot_level_offset, mm_boot_level_value;
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+
+	smu_data->smc_state_table.UvdBootLevel = 0;
+	if (table_info->mm_dep_table->count > 0)
+		smu_data->smc_state_table.UvdBootLevel =
+				(uint8_t) (table_info->mm_dep_table->count - 1);
+	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start + offsetof(SMU75_Discrete_DpmTable,
+						UvdBootLevel);
+	mm_boot_level_offset /= 4;
+	mm_boot_level_offset *= 4;
+	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
+			CGS_IND_REG__SMC, mm_boot_level_offset);
+	mm_boot_level_value &= 0x00FFFFFF;
+	mm_boot_level_value |= smu_data->smc_state_table.UvdBootLevel << 24;
+	cgs_write_ind_register(hwmgr->device,
+			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
+
+	if (!phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_UVDDPM) ||
+		phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_StablePState))
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_UVDDPM_SetEnabledMask,
+				(uint32_t)(1 << smu_data->smc_state_table.UvdBootLevel));
+	return 0;
+}
+
+static int vegam_update_vce_smc_table(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	uint32_t mm_boot_level_offset, mm_boot_level_value;
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+					PHM_PlatformCaps_StablePState))
+		smu_data->smc_state_table.VceBootLevel =
+			(uint8_t) (table_info->mm_dep_table->count - 1);
+	else
+		smu_data->smc_state_table.VceBootLevel = 0;
+
+	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
+					offsetof(SMU75_Discrete_DpmTable, VceBootLevel);
+	mm_boot_level_offset /= 4;
+	mm_boot_level_offset *= 4;
+	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
+			CGS_IND_REG__SMC, mm_boot_level_offset);
+	mm_boot_level_value &= 0xFF00FFFF;
+	mm_boot_level_value |= smu_data->smc_state_table.VceBootLevel << 16;
+	cgs_write_ind_register(hwmgr->device,
+			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_StablePState))
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_VCEDPM_SetEnabledMask,
+				(uint32_t)1 << smu_data->smc_state_table.VceBootLevel);
+	return 0;
+}
+
+static int vegam_update_samu_smc_table(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	uint32_t mm_boot_level_offset, mm_boot_level_value;
+
+
+	smu_data->smc_state_table.SamuBootLevel = 0;
+	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
+				offsetof(SMU75_Discrete_DpmTable, SamuBootLevel);
+
+	mm_boot_level_offset /= 4;
+	mm_boot_level_offset *= 4;
+	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
+			CGS_IND_REG__SMC, mm_boot_level_offset);
+	mm_boot_level_value &= 0xFFFFFF00;
+	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
+	cgs_write_ind_register(hwmgr->device,
+			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_StablePState))
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_SAMUDPM_SetEnabledMask,
+				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
+	return 0;
+}
+
+
+static int vegam_update_bif_smc_table(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_pcie_table *pcie_table = table_info->pcie_table;
+	int max_entry, i;
+
+	max_entry = (SMU75_MAX_LEVELS_LINK < pcie_table->count) ?
+						SMU75_MAX_LEVELS_LINK :
+						pcie_table->count;
+	/* Setup BIF_SCLK levels */
+	for (i = 0; i < max_entry; i++)
+		smu_data->bif_sclk_table[i] = pcie_table->entries[i].pcie_sclk;
+	return 0;
+}
+
+static int vegam_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
+{
+	switch (type) {
+	case SMU_UVD_TABLE:
+		vegam_update_uvd_smc_table(hwmgr);
+		break;
+	case SMU_VCE_TABLE:
+		vegam_update_vce_smc_table(hwmgr);
+		break;
+	case SMU_SAMU_TABLE:
+		vegam_update_samu_smc_table(hwmgr);
+		break;
+	case SMU_BIF_TABLE:
+		vegam_update_bif_smc_table(hwmgr);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static void vegam_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct  phm_ppt_v1_information *table_info =
+			(struct  phm_ppt_v1_information *)(hwmgr->pptable);
+
+	if (table_info &&
+			table_info->cac_dtp_table->usPowerTuneDataSetID <= POWERTUNE_DEFAULT_SET_MAX &&
+			table_info->cac_dtp_table->usPowerTuneDataSetID)
+		smu_data->power_tune_defaults =
+				&vegam_power_tune_data_set_array
+				[table_info->cac_dtp_table->usPowerTuneDataSetID - 1];
+	else
+		smu_data->power_tune_defaults = &vegam_power_tune_data_set_array[0];
+
+}
+
+static int vegam_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
+			SMU75_Discrete_DpmTable *table)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	uint32_t count, level;
+
+	if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->mvdd_control) {
+		count = data->mvdd_voltage_table.count;
+		if (count > SMU_MAX_SMIO_LEVELS)
+			count = SMU_MAX_SMIO_LEVELS;
+		for (level = 0; level < count; level++) {
+			table->SmioTable2.Pattern[level].Voltage = PP_HOST_TO_SMC_US(
+					data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
+			table->SmioTable2.Pattern[level].Smio =
+				(uint8_t) level;
+			table->Smio[level] |=
+				data->mvdd_voltage_table.entries[level].smio_low;
+		}
+		table->SmioMask2 = data->mvdd_voltage_table.mask_low;
+
+		table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count);
+	}
+
+	return 0;
+}
+
+static int vegam_populate_smc_vddci_table(struct pp_hwmgr *hwmgr,
+					struct SMU75_Discrete_DpmTable *table)
+{
+	uint32_t count, level;
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+
+	count = data->vddci_voltage_table.count;
+
+	if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control) {
+		if (count > SMU_MAX_SMIO_LEVELS)
+			count = SMU_MAX_SMIO_LEVELS;
+		for (level = 0; level < count; ++level) {
+			table->SmioTable1.Pattern[level].Voltage = PP_HOST_TO_SMC_US(
+					data->vddci_voltage_table.entries[level].value * VOLTAGE_SCALE);
+			table->SmioTable1.Pattern[level].Smio = (uint8_t) level;
+
+			table->Smio[level] |= data->vddci_voltage_table.entries[level].smio_low;
+		}
+	}
+
+	table->SmioMask1 = data->vddci_voltage_table.mask_low;
+
+	return 0;
+}
+
+static int vegam_populate_cac_table(struct pp_hwmgr *hwmgr,
+		struct SMU75_Discrete_DpmTable *table)
+{
+	uint32_t count;
+	uint8_t index;
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_voltage_lookup_table *lookup_table =
+			table_info->vddc_lookup_table;
+	/* tables is already swapped, so in order to use the value from it,
+	 * we need to swap it back.
+	 * We are populating vddc CAC data to BapmVddc table
+	 * in split and merged mode
+	 */
+	for (count = 0; count < lookup_table->count; count++) {
+		index = phm_get_voltage_index(lookup_table,
+				data->vddc_voltage_table.entries[count].value);
+		table->BapmVddcVidLoSidd[count] =
+				convert_to_vid(lookup_table->entries[index].us_cac_low);
+		table->BapmVddcVidHiSidd[count] =
+				convert_to_vid(lookup_table->entries[index].us_cac_mid);
+		table->BapmVddcVidHiSidd2[count] =
+				convert_to_vid(lookup_table->entries[index].us_cac_high);
+	}
+
+	return 0;
+}
+
+static int vegam_populate_smc_voltage_tables(struct pp_hwmgr *hwmgr,
+		struct SMU75_Discrete_DpmTable *table)
+{
+	vegam_populate_smc_vddci_table(hwmgr, table);
+	vegam_populate_smc_mvdd_table(hwmgr, table);
+	vegam_populate_cac_table(hwmgr, table);
+
+	return 0;
+}
+
+static int vegam_populate_ulv_level(struct pp_hwmgr *hwmgr,
+		struct SMU75_Discrete_Ulv *state)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+
+	state->CcPwrDynRm = 0;
+	state->CcPwrDynRm1 = 0;
+
+	state->VddcOffset = (uint16_t) table_info->us_ulv_voltage_offset;
+	state->VddcOffsetVid = (uint8_t)(table_info->us_ulv_voltage_offset *
+			VOLTAGE_VID_OFFSET_SCALE2 / VOLTAGE_VID_OFFSET_SCALE1);
+
+	state->VddcPhase = data->vddc_phase_shed_control ^ 0x3;
+
+	CONVERT_FROM_HOST_TO_SMC_UL(state->CcPwrDynRm);
+	CONVERT_FROM_HOST_TO_SMC_UL(state->CcPwrDynRm1);
+	CONVERT_FROM_HOST_TO_SMC_US(state->VddcOffset);
+
+	return 0;
+}
+
+static int vegam_populate_ulv_state(struct pp_hwmgr *hwmgr,
+		struct SMU75_Discrete_DpmTable *table)
+{
+	return vegam_populate_ulv_level(hwmgr, &table->Ulv);
+}
+
+static int vegam_populate_smc_link_level(struct pp_hwmgr *hwmgr,
+		struct SMU75_Discrete_DpmTable *table)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data =
+			(struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct smu7_dpm_table *dpm_table = &data->dpm_table;
+	int i;
+
+	/* Index (dpm_table->pcie_speed_table.count)
+	 * is reserved for PCIE boot level. */
+	for (i = 0; i <= dpm_table->pcie_speed_table.count; i++) {
+		table->LinkLevel[i].PcieGenSpeed  =
+				(uint8_t)dpm_table->pcie_speed_table.dpm_levels[i].value;
+		table->LinkLevel[i].PcieLaneCount = (uint8_t)encode_pcie_lane_width(
+				dpm_table->pcie_speed_table.dpm_levels[i].param1);
+		table->LinkLevel[i].EnabledForActivity = 1;
+		table->LinkLevel[i].SPC = (uint8_t)(data->pcie_spc_cap & 0xff);
+		table->LinkLevel[i].DownThreshold = PP_HOST_TO_SMC_UL(5);
+		table->LinkLevel[i].UpThreshold = PP_HOST_TO_SMC_UL(30);
+	}
+
+	smu_data->smc_state_table.LinkLevelCount =
+			(uint8_t)dpm_table->pcie_speed_table.count;
+
+/* To Do move to hwmgr */
+	data->dpm_level_enable_mask.pcie_dpm_enable_mask =
+			phm_get_dpm_level_enable_mask_value(&dpm_table->pcie_speed_table);
+
+	return 0;
+}
+
+static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
+		struct phm_ppt_v1_clock_voltage_dependency_table *dep_table,
+		uint32_t clock, SMU_VoltageLevel *voltage, uint32_t *mvdd)
+{
+	uint32_t i;
+	uint16_t vddci;
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+
+	*voltage = *mvdd = 0;
+
+	/* clock - voltage dependency table is empty table */
+	if (dep_table->count == 0)
+		return -EINVAL;
+
+	for (i = 0; i < dep_table->count; i++) {
+		/* find first sclk bigger than request */
+		if (dep_table->entries[i].clk >= clock) {
+			*voltage |= (dep_table->entries[i].vddc *
+					VOLTAGE_SCALE) << VDDC_SHIFT;
+			if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control)
+				*voltage |= (data->vbios_boot_state.vddci_bootup_value *
+						VOLTAGE_SCALE) << VDDCI_SHIFT;
+			else if (dep_table->entries[i].vddci)
+				*voltage |= (dep_table->entries[i].vddci *
+						VOLTAGE_SCALE) << VDDCI_SHIFT;
+			else {
+				vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
+						(dep_table->entries[i].vddc -
+								(uint16_t)VDDC_VDDCI_DELTA));
+				*voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+			}
+
+			if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control)
+				*mvdd = data->vbios_boot_state.mvdd_bootup_value *
+					VOLTAGE_SCALE;
+			else if (dep_table->entries[i].mvdd)
+				*mvdd = (uint32_t) dep_table->entries[i].mvdd *
+					VOLTAGE_SCALE;
+
+			*voltage |= 1 << PHASES_SHIFT;
+			return 0;
+		}
+	}
+
+	/* sclk is bigger than max sclk in the dependence table */
+	*voltage |= (dep_table->entries[i - 1].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
+	vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
+			(dep_table->entries[i - 1].vddc -
+					(uint16_t)VDDC_VDDCI_DELTA));
+
+	if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control)
+		*voltage |= (data->vbios_boot_state.vddci_bootup_value *
+				VOLTAGE_SCALE) << VDDCI_SHIFT;
+	else if (dep_table->entries[i - 1].vddci)
+		*voltage |= (dep_table->entries[i - 1].vddci *
+				VOLTAGE_SCALE) << VDDC_SHIFT;
+	else
+		*voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+	if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control)
+		*mvdd = data->vbios_boot_state.mvdd_bootup_value * VOLTAGE_SCALE;
+	else if (dep_table->entries[i].mvdd)
+		*mvdd = (uint32_t) dep_table->entries[i - 1].mvdd * VOLTAGE_SCALE;
+
+	return 0;
+}
+
+static void vegam_get_sclk_range_table(struct pp_hwmgr *hwmgr,
+				   SMU75_Discrete_DpmTable  *table)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	uint32_t i, ref_clk;
+
+	struct pp_atom_ctrl_sclk_range_table range_table_from_vbios = { { {0} } };
+
+	ref_clk = amdgpu_asic_get_xclk((struct amdgpu_device *)hwmgr->adev);
+
+	if (0 == atomctrl_get_smc_sclk_range_table(hwmgr, &range_table_from_vbios)) {
+		for (i = 0; i < NUM_SCLK_RANGE; i++) {
+			table->SclkFcwRangeTable[i].vco_setting =
+					range_table_from_vbios.entry[i].ucVco_setting;
+			table->SclkFcwRangeTable[i].postdiv =
+					range_table_from_vbios.entry[i].ucPostdiv;
+			table->SclkFcwRangeTable[i].fcw_pcc =
+					range_table_from_vbios.entry[i].usFcw_pcc;
+
+			table->SclkFcwRangeTable[i].fcw_trans_upper =
+					range_table_from_vbios.entry[i].usFcw_trans_upper;
+			table->SclkFcwRangeTable[i].fcw_trans_lower =
+					range_table_from_vbios.entry[i].usRcw_trans_lower;
+
+			CONVERT_FROM_HOST_TO_SMC_US(table->SclkFcwRangeTable[i].fcw_pcc);
+			CONVERT_FROM_HOST_TO_SMC_US(table->SclkFcwRangeTable[i].fcw_trans_upper);
+			CONVERT_FROM_HOST_TO_SMC_US(table->SclkFcwRangeTable[i].fcw_trans_lower);
+		}
+		return;
+	}
+
+	for (i = 0; i < NUM_SCLK_RANGE; i++) {
+		smu_data->range_table[i].trans_lower_frequency =
+				(ref_clk * Range_Table[i].fcw_trans_lower) >> Range_Table[i].postdiv;
+		smu_data->range_table[i].trans_upper_frequency =
+				(ref_clk * Range_Table[i].fcw_trans_upper) >> Range_Table[i].postdiv;
+
+		table->SclkFcwRangeTable[i].vco_setting = Range_Table[i].vco_setting;
+		table->SclkFcwRangeTable[i].postdiv = Range_Table[i].postdiv;
+		table->SclkFcwRangeTable[i].fcw_pcc = Range_Table[i].fcw_pcc;
+
+		table->SclkFcwRangeTable[i].fcw_trans_upper = Range_Table[i].fcw_trans_upper;
+		table->SclkFcwRangeTable[i].fcw_trans_lower = Range_Table[i].fcw_trans_lower;
+
+		CONVERT_FROM_HOST_TO_SMC_US(table->SclkFcwRangeTable[i].fcw_pcc);
+		CONVERT_FROM_HOST_TO_SMC_US(table->SclkFcwRangeTable[i].fcw_trans_upper);
+		CONVERT_FROM_HOST_TO_SMC_US(table->SclkFcwRangeTable[i].fcw_trans_lower);
+	}
+}
+
+static int vegam_calculate_sclk_params(struct pp_hwmgr *hwmgr,
+		uint32_t clock, SMU_SclkSetting *sclk_setting)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	const SMU75_Discrete_DpmTable *table = &(smu_data->smc_state_table);
+	struct pp_atomctrl_clock_dividers_ai dividers;
+	uint32_t ref_clock;
+	uint32_t pcc_target_percent, pcc_target_freq, ss_target_percent, ss_target_freq;
+	uint8_t i;
+	int result;
+	uint64_t temp;
+
+	sclk_setting->SclkFrequency = clock;
+	/* get the engine clock dividers for this clock value */
+	result = atomctrl_get_engine_pll_dividers_ai(hwmgr, clock,  &dividers);
+	if (result == 0) {
+		sclk_setting->Fcw_int = dividers.usSclk_fcw_int;
+		sclk_setting->Fcw_frac = dividers.usSclk_fcw_frac;
+		sclk_setting->Pcc_fcw_int = dividers.usPcc_fcw_int;
+		sclk_setting->PllRange = dividers.ucSclkPllRange;
+		sclk_setting->Sclk_slew_rate = 0x400;
+		sclk_setting->Pcc_up_slew_rate = dividers.usPcc_fcw_slew_frac;
+		sclk_setting->Pcc_down_slew_rate = 0xffff;
+		sclk_setting->SSc_En = dividers.ucSscEnable;
+		sclk_setting->Fcw1_int = dividers.usSsc_fcw1_int;
+		sclk_setting->Fcw1_frac = dividers.usSsc_fcw1_frac;
+		sclk_setting->Sclk_ss_slew_rate = dividers.usSsc_fcw_slew_frac;
+		return result;
+	}
+
+	ref_clock = amdgpu_asic_get_xclk((struct amdgpu_device *)hwmgr->adev);
+
+	for (i = 0; i < NUM_SCLK_RANGE; i++) {
+		if (clock > smu_data->range_table[i].trans_lower_frequency
+		&& clock <= smu_data->range_table[i].trans_upper_frequency) {
+			sclk_setting->PllRange = i;
+			break;
+		}
+	}
+
+	sclk_setting->Fcw_int = (uint16_t)
+			((clock << table->SclkFcwRangeTable[sclk_setting->PllRange].postdiv) /
+					ref_clock);
+	temp = clock << table->SclkFcwRangeTable[sclk_setting->PllRange].postdiv;
+	temp <<= 0x10;
+	do_div(temp, ref_clock);
+	sclk_setting->Fcw_frac = temp & 0xffff;
+
+	pcc_target_percent = 10; /*  Hardcode 10% for now. */
+	pcc_target_freq = clock - (clock * pcc_target_percent / 100);
+	sclk_setting->Pcc_fcw_int = (uint16_t)
+			((pcc_target_freq << table->SclkFcwRangeTable[sclk_setting->PllRange].postdiv) /
+					ref_clock);
+
+	ss_target_percent = 2; /*  Hardcode 2% for now. */
+	sclk_setting->SSc_En = 0;
+	if (ss_target_percent) {
+		sclk_setting->SSc_En = 1;
+		ss_target_freq = clock - (clock * ss_target_percent / 100);
+		sclk_setting->Fcw1_int = (uint16_t)
+				((ss_target_freq << table->SclkFcwRangeTable[sclk_setting->PllRange].postdiv) /
+						ref_clock);
+		temp = ss_target_freq << table->SclkFcwRangeTable[sclk_setting->PllRange].postdiv;
+		temp <<= 0x10;
+		do_div(temp, ref_clock);
+		sclk_setting->Fcw1_frac = temp & 0xffff;
+	}
+
+	return 0;
+}
+
+static uint8_t vegam_get_sleep_divider_id_from_clock(uint32_t clock,
+		uint32_t clock_insr)
+{
+	uint8_t i;
+	uint32_t temp;
+	uint32_t min = max(clock_insr, (uint32_t)SMU7_MINIMUM_ENGINE_CLOCK);
+
+	PP_ASSERT_WITH_CODE((clock >= min),
+			"Engine clock can't satisfy stutter requirement!",
+			return 0);
+	for (i = 31;  ; i--) {
+		temp = clock / (i + 1);
+
+		if (temp >= min || i == 0)
+			break;
+	}
+	return i;
+}
+
+static int vegam_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
+		uint32_t clock, struct SMU75_Discrete_GraphicsLevel *level)
+{
+	int result;
+	/* PP_Clocks minClocks; */
+	uint32_t mvdd;
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	SMU_SclkSetting curr_sclk_setting = { 0 };
+
+	result = vegam_calculate_sclk_params(hwmgr, clock, &curr_sclk_setting);
+
+	/* populate graphics levels */
+	result = vegam_get_dependency_volt_by_clk(hwmgr,
+			table_info->vdd_dep_on_sclk, clock,
+			&level->MinVoltage, &mvdd);
+
+	PP_ASSERT_WITH_CODE((0 == result),
+			"can not find VDDC voltage value for "
+			"VDDC engine clock dependency table",
+			return result);
+	level->ActivityLevel = (uint16_t)(SclkDPMTuning_VEGAM >> DPMTuning_Activity_Shift);
+
+	level->CcPwrDynRm = 0;
+	level->CcPwrDynRm1 = 0;
+	level->EnabledForActivity = 0;
+	level->EnabledForThrottle = 1;
+	level->VoltageDownHyst = 0;
+	level->PowerThrottle = 0;
+	data->display_timing.min_clock_in_sr = hwmgr->display_config->min_core_set_clock_in_sr;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SclkDeepSleep))
+		level->DeepSleepDivId = vegam_get_sleep_divider_id_from_clock(clock,
+								hwmgr->display_config->min_core_set_clock_in_sr);
+
+	level->SclkSetting = curr_sclk_setting;
+
+	CONVERT_FROM_HOST_TO_SMC_UL(level->MinVoltage);
+	CONVERT_FROM_HOST_TO_SMC_UL(level->CcPwrDynRm);
+	CONVERT_FROM_HOST_TO_SMC_UL(level->CcPwrDynRm1);
+	CONVERT_FROM_HOST_TO_SMC_US(level->ActivityLevel);
+	CONVERT_FROM_HOST_TO_SMC_UL(level->SclkSetting.SclkFrequency);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Fcw_int);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Fcw_frac);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Pcc_fcw_int);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Sclk_slew_rate);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Pcc_up_slew_rate);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Pcc_down_slew_rate);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Fcw1_int);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Fcw1_frac);
+	CONVERT_FROM_HOST_TO_SMC_US(level->SclkSetting.Sclk_ss_slew_rate);
+	return 0;
+}
+
+static int vegam_populate_all_graphic_levels(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *hw_data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct smu7_dpm_table *dpm_table = &hw_data->dpm_table;
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_pcie_table *pcie_table = table_info->pcie_table;
+	uint8_t pcie_entry_cnt = (uint8_t) hw_data->dpm_table.pcie_speed_table.count;
+	int result = 0;
+	uint32_t array = smu_data->smu7_data.dpm_table_start +
+			offsetof(SMU75_Discrete_DpmTable, GraphicsLevel);
+	uint32_t array_size = sizeof(struct SMU75_Discrete_GraphicsLevel) *
+			SMU75_MAX_LEVELS_GRAPHICS;
+	struct SMU75_Discrete_GraphicsLevel *levels =
+			smu_data->smc_state_table.GraphicsLevel;
+	uint32_t i, max_entry;
+	uint8_t hightest_pcie_level_enabled = 0,
+		lowest_pcie_level_enabled = 0,
+		mid_pcie_level_enabled = 0,
+		count = 0;
+
+	vegam_get_sclk_range_table(hwmgr, &(smu_data->smc_state_table));
+
+	for (i = 0; i < dpm_table->sclk_table.count; i++) {
+
+		result = vegam_populate_single_graphic_level(hwmgr,
+				dpm_table->sclk_table.dpm_levels[i].value,
+				&(smu_data->smc_state_table.GraphicsLevel[i]));
+		if (result)
+			return result;
+
+		levels[i].UpHyst = (uint8_t)
+				(SclkDPMTuning_VEGAM >> DPMTuning_Uphyst_Shift);
+		levels[i].DownHyst = (uint8_t)
+				(SclkDPMTuning_VEGAM >> DPMTuning_Downhyst_Shift);
+		/* Making sure only DPM level 0-1 have Deep Sleep Div ID populated. */
+		if (i > 1)
+			levels[i].DeepSleepDivId = 0;
+	}
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+					PHM_PlatformCaps_SPLLShutdownSupport))
+		smu_data->smc_state_table.GraphicsLevel[0].SclkSetting.SSc_En = 0;
+
+	smu_data->smc_state_table.GraphicsDpmLevelCount =
+			(uint8_t)dpm_table->sclk_table.count;
+	hw_data->dpm_level_enable_mask.sclk_dpm_enable_mask =
+			phm_get_dpm_level_enable_mask_value(&dpm_table->sclk_table);
+
+	for (i = 0; i < dpm_table->sclk_table.count; i++)
+		levels[i].EnabledForActivity =
+				(hw_data->dpm_level_enable_mask.sclk_dpm_enable_mask >> i) & 0x1;
+
+	if (pcie_table != NULL) {
+		PP_ASSERT_WITH_CODE((1 <= pcie_entry_cnt),
+				"There must be 1 or more PCIE levels defined in PPTable.",
+				return -EINVAL);
+		max_entry = pcie_entry_cnt - 1;
+		for (i = 0; i < dpm_table->sclk_table.count; i++)
+			levels[i].pcieDpmLevel =
+					(uint8_t) ((i < max_entry) ? i : max_entry);
+	} else {
+		while (hw_data->dpm_level_enable_mask.pcie_dpm_enable_mask &&
+				((hw_data->dpm_level_enable_mask.pcie_dpm_enable_mask &
+						(1 << (hightest_pcie_level_enabled + 1))) != 0))
+			hightest_pcie_level_enabled++;
+
+		while (hw_data->dpm_level_enable_mask.pcie_dpm_enable_mask &&
+				((hw_data->dpm_level_enable_mask.pcie_dpm_enable_mask &
+						(1 << lowest_pcie_level_enabled)) == 0))
+			lowest_pcie_level_enabled++;
+
+		while ((count < hightest_pcie_level_enabled) &&
+				((hw_data->dpm_level_enable_mask.pcie_dpm_enable_mask &
+						(1 << (lowest_pcie_level_enabled + 1 + count))) == 0))
+			count++;
+
+		mid_pcie_level_enabled = (lowest_pcie_level_enabled + 1 + count) <
+				hightest_pcie_level_enabled ?
+						(lowest_pcie_level_enabled + 1 + count) :
+						hightest_pcie_level_enabled;
+
+		/* set pcieDpmLevel to hightest_pcie_level_enabled */
+		for (i = 2; i < dpm_table->sclk_table.count; i++)
+			levels[i].pcieDpmLevel = hightest_pcie_level_enabled;
+
+		/* set pcieDpmLevel to lowest_pcie_level_enabled */
+		levels[0].pcieDpmLevel = lowest_pcie_level_enabled;
+
+		/* set pcieDpmLevel to mid_pcie_level_enabled */
+		levels[1].pcieDpmLevel = mid_pcie_level_enabled;
+	}
+	/* level count will send to smc once at init smc table and never change */
+	result = smu7_copy_bytes_to_smc(hwmgr, array, (uint8_t *)levels,
+			(uint32_t)array_size, SMC_RAM_END);
+
+	return result;
+}
+
+static int vegam_calculate_mclk_params(struct pp_hwmgr *hwmgr,
+		uint32_t clock, struct SMU75_Discrete_MemoryLevel *mem_level)
+{
+	struct pp_atomctrl_memory_clock_param_ai mpll_param;
+
+	PP_ASSERT_WITH_CODE(!atomctrl_get_memory_pll_dividers_ai(hwmgr,
+			clock, &mpll_param),
+			"Failed to retrieve memory pll parameter.",
+			return -EINVAL);
+
+	mem_level->MclkFrequency = (uint32_t)mpll_param.ulClock;
+	mem_level->Fcw_int = (uint16_t)mpll_param.ulMclk_fcw_int;
+	mem_level->Fcw_frac = (uint16_t)mpll_param.ulMclk_fcw_frac;
+	mem_level->Postdiv = (uint8_t)mpll_param.ulPostDiv;
+
+	return 0;
+}
+
+static int vegam_populate_single_memory_level(struct pp_hwmgr *hwmgr,
+		uint32_t clock, struct SMU75_Discrete_MemoryLevel *mem_level)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	int result = 0;
+	uint32_t mclk_stutter_mode_threshold = 60000;
+
+
+	if (table_info->vdd_dep_on_mclk) {
+		result = vegam_get_dependency_volt_by_clk(hwmgr,
+				table_info->vdd_dep_on_mclk, clock,
+				&mem_level->MinVoltage, &mem_level->MinMvdd);
+		PP_ASSERT_WITH_CODE(!result,
+				"can not find MinVddc voltage value from memory "
+				"VDDC voltage dependency table", return result);
+	}
+
+	result = vegam_calculate_mclk_params(hwmgr, clock, mem_level);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to calculate mclk params.",
+			return -EINVAL);
+
+	mem_level->EnabledForThrottle = 1;
+	mem_level->EnabledForActivity = 0;
+	mem_level->VoltageDownHyst = 0;
+	mem_level->ActivityLevel = (uint16_t)
+			(MemoryDPMTuning_VEGAM >> DPMTuning_Activity_Shift);
+	mem_level->StutterEnable = false;
+	mem_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
+
+	data->display_timing.num_existing_displays = hwmgr->display_config->num_display;
+
+	if (mclk_stutter_mode_threshold &&
+		(clock <= mclk_stutter_mode_threshold) &&
+		(PHM_READ_FIELD(hwmgr->device, DPG_PIPE_STUTTER_CONTROL,
+				STUTTER_ENABLE) & 0x1))
+		mem_level->StutterEnable = true;
+
+	if (!result) {
+		CONVERT_FROM_HOST_TO_SMC_UL(mem_level->MinMvdd);
+		CONVERT_FROM_HOST_TO_SMC_UL(mem_level->MclkFrequency);
+		CONVERT_FROM_HOST_TO_SMC_US(mem_level->Fcw_int);
+		CONVERT_FROM_HOST_TO_SMC_US(mem_level->Fcw_frac);
+		CONVERT_FROM_HOST_TO_SMC_US(mem_level->ActivityLevel);
+		CONVERT_FROM_HOST_TO_SMC_UL(mem_level->MinVoltage);
+	}
+
+	return result;
+}
+
+static int vegam_populate_all_memory_levels(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *hw_data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct smu7_dpm_table *dpm_table = &hw_data->dpm_table;
+	int result;
+	/* populate MCLK dpm table to SMU7 */
+	uint32_t array = smu_data->smu7_data.dpm_table_start +
+			offsetof(SMU75_Discrete_DpmTable, MemoryLevel);
+	uint32_t array_size = sizeof(SMU75_Discrete_MemoryLevel) *
+			SMU75_MAX_LEVELS_MEMORY;
+	struct SMU75_Discrete_MemoryLevel *levels =
+			smu_data->smc_state_table.MemoryLevel;
+	uint32_t i;
+
+	for (i = 0; i < dpm_table->mclk_table.count; i++) {
+		PP_ASSERT_WITH_CODE((0 != dpm_table->mclk_table.dpm_levels[i].value),
+				"can not populate memory level as memory clock is zero",
+				return -EINVAL);
+		result = vegam_populate_single_memory_level(hwmgr,
+				dpm_table->mclk_table.dpm_levels[i].value,
+				&levels[i]);
+
+		if (result)
+			return result;
+
+		levels[i].UpHyst = (uint8_t)
+				(MemoryDPMTuning_VEGAM >> DPMTuning_Uphyst_Shift);
+		levels[i].DownHyst = (uint8_t)
+				(MemoryDPMTuning_VEGAM >> DPMTuning_Downhyst_Shift);
+	}
+
+	smu_data->smc_state_table.MemoryDpmLevelCount =
+			(uint8_t)dpm_table->mclk_table.count;
+	hw_data->dpm_level_enable_mask.mclk_dpm_enable_mask =
+			phm_get_dpm_level_enable_mask_value(&dpm_table->mclk_table);
+
+	for (i = 0; i < dpm_table->mclk_table.count; i++)
+		levels[i].EnabledForActivity =
+				(hw_data->dpm_level_enable_mask.mclk_dpm_enable_mask >> i) & 0x1;
+
+	levels[dpm_table->mclk_table.count - 1].DisplayWatermark =
+			PPSMC_DISPLAY_WATERMARK_HIGH;
+
+	/* level count will send to smc once at init smc table and never change */
+	result = smu7_copy_bytes_to_smc(hwmgr, array, (uint8_t *)levels,
+			(uint32_t)array_size, SMC_RAM_END);
+
+	return result;
+}
+
+static int vegam_populate_mvdd_value(struct pp_hwmgr *hwmgr,
+		uint32_t mclk, SMIO_Pattern *smio_pat)
+{
+	const struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	uint32_t i = 0;
+
+	if (SMU7_VOLTAGE_CONTROL_NONE != data->mvdd_control) {
+		/* find mvdd value which clock is more than request */
+		for (i = 0; i < table_info->vdd_dep_on_mclk->count; i++) {
+			if (mclk <= table_info->vdd_dep_on_mclk->entries[i].clk) {
+				smio_pat->Voltage = data->mvdd_voltage_table.entries[i].value;
+				break;
+			}
+		}
+		PP_ASSERT_WITH_CODE(i < table_info->vdd_dep_on_mclk->count,
+				"MVDD Voltage is outside the supported range.",
+				return -EINVAL);
+	} else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int vegam_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
+		SMU75_Discrete_DpmTable *table)
+{
+	int result = 0;
+	uint32_t sclk_frequency;
+	const struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	SMIO_Pattern vol_level;
+	uint32_t mvdd;
+	uint16_t us_mvdd;
+
+	table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
+
+	/* Get MinVoltage and Frequency from DPM0,
+	 * already converted to SMC_UL */
+	sclk_frequency = data->vbios_boot_state.sclk_bootup_value;
+	result = vegam_get_dependency_volt_by_clk(hwmgr,
+			table_info->vdd_dep_on_sclk,
+			sclk_frequency,
+			&table->ACPILevel.MinVoltage, &mvdd);
+	PP_ASSERT_WITH_CODE(!result,
+			"Cannot find ACPI VDDC voltage value "
+			"in Clock Dependency Table",
+			);
+
+	result = vegam_calculate_sclk_params(hwmgr, sclk_frequency,
+			&(table->ACPILevel.SclkSetting));
+	PP_ASSERT_WITH_CODE(!result,
+			"Error retrieving Engine Clock dividers from VBIOS.",
+			return result);
+
+	table->ACPILevel.DeepSleepDivId = 0;
+	table->ACPILevel.CcPwrDynRm = 0;
+	table->ACPILevel.CcPwrDynRm1 = 0;
+
+	CONVERT_FROM_HOST_TO_SMC_UL(table->ACPILevel.Flags);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->ACPILevel.MinVoltage);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->ACPILevel.CcPwrDynRm);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->ACPILevel.CcPwrDynRm1);
+
+	CONVERT_FROM_HOST_TO_SMC_UL(table->ACPILevel.SclkSetting.SclkFrequency);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw_int);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw_frac);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Pcc_fcw_int);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Sclk_slew_rate);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Pcc_up_slew_rate);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Pcc_down_slew_rate);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw1_int);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw1_frac);
+	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Sclk_ss_slew_rate);
+
+
+	/* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */
+	table->MemoryACPILevel.MclkFrequency = data->vbios_boot_state.mclk_bootup_value;
+	result = vegam_get_dependency_volt_by_clk(hwmgr,
+			table_info->vdd_dep_on_mclk,
+			table->MemoryACPILevel.MclkFrequency,
+			&table->MemoryACPILevel.MinVoltage, &mvdd);
+	PP_ASSERT_WITH_CODE((0 == result),
+			"Cannot find ACPI VDDCI voltage value "
+			"in Clock Dependency Table",
+			);
+
+	us_mvdd = 0;
+	if ((SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
+			(data->mclk_dpm_key_disabled))
+		us_mvdd = data->vbios_boot_state.mvdd_bootup_value;
+	else {
+		if (!vegam_populate_mvdd_value(hwmgr,
+				data->dpm_table.mclk_table.dpm_levels[0].value,
+				&vol_level))
+			us_mvdd = vol_level.Voltage;
+	}
+
+	if (!vegam_populate_mvdd_value(hwmgr, 0, &vol_level))
+		table->MemoryACPILevel.MinMvdd = PP_HOST_TO_SMC_UL(vol_level.Voltage);
+	else
+		table->MemoryACPILevel.MinMvdd = 0;
+
+	table->MemoryACPILevel.StutterEnable = false;
+
+	table->MemoryACPILevel.EnabledForThrottle = 0;
+	table->MemoryACPILevel.EnabledForActivity = 0;
+	table->MemoryACPILevel.UpHyst = 0;
+	table->MemoryACPILevel.DownHyst = 100;
+	table->MemoryACPILevel.VoltageDownHyst = 0;
+	table->MemoryACPILevel.ActivityLevel =
+		PP_HOST_TO_SMC_US(data->current_profile_setting.mclk_activity);
+
+	CONVERT_FROM_HOST_TO_SMC_UL(table->MemoryACPILevel.MclkFrequency);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->MemoryACPILevel.MinVoltage);
+
+	return result;
+}
+
+static int vegam_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
+		SMU75_Discrete_DpmTable *table)
+{
+	int result = -EINVAL;
+	uint8_t count;
+	struct pp_atomctrl_clock_dividers_vi dividers;
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
+			table_info->mm_dep_table;
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
+
+	table->VceLevelCount = (uint8_t)(mm_table->count);
+	table->VceBootLevel = 0;
+
+	for (count = 0; count < table->VceLevelCount; count++) {
+		table->VceLevel[count].Frequency = mm_table->entries[count].eclk;
+		table->VceLevel[count].MinVoltage = 0;
+		table->VceLevel[count].MinVoltage |=
+				(mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
+
+		if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+
+		table->VceLevel[count].MinVoltage |=
+				(vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+		table->VceLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
+
+		/*retrieve divider value for VBIOS */
+		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
+				table->VceLevel[count].Frequency, &dividers);
+		PP_ASSERT_WITH_CODE((0 == result),
+				"can not find divide id for VCE engine clock",
+				return result);
+
+		table->VceLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
+
+		CONVERT_FROM_HOST_TO_SMC_UL(table->VceLevel[count].Frequency);
+		CONVERT_FROM_HOST_TO_SMC_UL(table->VceLevel[count].MinVoltage);
+	}
+	return result;
+}
+
+static int vegam_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
+		SMU75_Discrete_DpmTable *table)
+{
+	int result = -EINVAL;
+	uint8_t count;
+	struct pp_atomctrl_clock_dividers_vi dividers;
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
+			table_info->mm_dep_table;
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
+
+	table->SamuBootLevel = 0;
+	table->SamuLevelCount = (uint8_t)(mm_table->count);
+
+	for (count = 0; count < table->SamuLevelCount; count++) {
+		/* not sure whether we need evclk or not */
+		table->SamuLevel[count].MinVoltage = 0;
+		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
+		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
+				VOLTAGE_SCALE) << VDDC_SHIFT;
+
+		if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
+
+		/* retrieve divider value for VBIOS */
+		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
+				table->SamuLevel[count].Frequency, &dividers);
+		PP_ASSERT_WITH_CODE((0 == result),
+				"can not find divide id for samu clock", return result);
+
+		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
+
+		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
+		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].MinVoltage);
+	}
+	return result;
+}
+
+static int vegam_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
+		int32_t eng_clock, int32_t mem_clock,
+		SMU75_Discrete_MCArbDramTimingTableEntry *arb_regs)
+{
+	uint32_t dram_timing;
+	uint32_t dram_timing2;
+	uint32_t burst_time;
+	uint32_t rfsh_rate;
+	uint32_t misc3;
+
+	int result;
+
+	result = atomctrl_set_engine_dram_timings_rv770(hwmgr,
+			eng_clock, mem_clock);
+	PP_ASSERT_WITH_CODE(result == 0,
+			"Error calling VBIOS to set DRAM_TIMING.",
+			return result);
+
+	dram_timing = cgs_read_register(hwmgr->device, mmMC_ARB_DRAM_TIMING);
+	dram_timing2 = cgs_read_register(hwmgr->device, mmMC_ARB_DRAM_TIMING2);
+	burst_time = cgs_read_register(hwmgr->device, mmMC_ARB_BURST_TIME);
+	rfsh_rate = cgs_read_register(hwmgr->device, mmMC_ARB_RFSH_RATE);
+	misc3 = cgs_read_register(hwmgr->device, mmMC_ARB_MISC3);
+
+	arb_regs->McArbDramTiming  = PP_HOST_TO_SMC_UL(dram_timing);
+	arb_regs->McArbDramTiming2 = PP_HOST_TO_SMC_UL(dram_timing2);
+	arb_regs->McArbBurstTime   = PP_HOST_TO_SMC_UL(burst_time);
+	arb_regs->McArbRfshRate = PP_HOST_TO_SMC_UL(rfsh_rate);
+	arb_regs->McArbMisc3 = PP_HOST_TO_SMC_UL(misc3);
+
+	return 0;
+}
+
+static int vegam_program_memory_timing_parameters(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *hw_data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct SMU75_Discrete_MCArbDramTimingTable arb_regs;
+	uint32_t i, j;
+	int result = 0;
+
+	memset(&arb_regs, 0, sizeof(SMU75_Discrete_MCArbDramTimingTable));
+
+	for (i = 0; i < hw_data->dpm_table.sclk_table.count; i++) {
+		for (j = 0; j < hw_data->dpm_table.mclk_table.count; j++) {
+			result = vegam_populate_memory_timing_parameters(hwmgr,
+					hw_data->dpm_table.sclk_table.dpm_levels[i].value,
+					hw_data->dpm_table.mclk_table.dpm_levels[j].value,
+					&arb_regs.entries[i][j]);
+			if (result)
+				return result;
+		}
+	}
+
+	result = smu7_copy_bytes_to_smc(
+			hwmgr,
+			smu_data->smu7_data.arb_table_start,
+			(uint8_t *)&arb_regs,
+			sizeof(SMU75_Discrete_MCArbDramTimingTable),
+			SMC_RAM_END);
+	return result;
+}
+
+static int vegam_populate_smc_uvd_level(struct pp_hwmgr *hwmgr,
+		struct SMU75_Discrete_DpmTable *table)
+{
+	int result = -EINVAL;
+	uint8_t count;
+	struct pp_atomctrl_clock_dividers_vi dividers;
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
+			table_info->mm_dep_table;
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
+
+	table->UvdLevelCount = (uint8_t)(mm_table->count);
+	table->UvdBootLevel = 0;
+
+	for (count = 0; count < table->UvdLevelCount; count++) {
+		table->UvdLevel[count].MinVoltage = 0;
+		table->UvdLevel[count].VclkFrequency = mm_table->entries[count].vclk;
+		table->UvdLevel[count].DclkFrequency = mm_table->entries[count].dclk;
+		table->UvdLevel[count].MinVoltage |=
+				(mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
+
+		if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		table->UvdLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+		table->UvdLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
+
+		/* retrieve divider value for VBIOS */
+		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
+				table->UvdLevel[count].VclkFrequency, &dividers);
+		PP_ASSERT_WITH_CODE((0 == result),
+				"can not find divide id for Vclk clock", return result);
+
+		table->UvdLevel[count].VclkDivider = (uint8_t)dividers.pll_post_divider;
+
+		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
+				table->UvdLevel[count].DclkFrequency, &dividers);
+		PP_ASSERT_WITH_CODE((0 == result),
+				"can not find divide id for Dclk clock", return result);
+
+		table->UvdLevel[count].DclkDivider = (uint8_t)dividers.pll_post_divider;
+
+		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].VclkFrequency);
+		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].DclkFrequency);
+		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].MinVoltage);
+	}
+
+	return result;
+}
+
+static int vegam_populate_smc_boot_level(struct pp_hwmgr *hwmgr,
+		struct SMU75_Discrete_DpmTable *table)
+{
+	int result = 0;
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+
+	table->GraphicsBootLevel = 0;
+	table->MemoryBootLevel = 0;
+
+	/* find boot level from dpm table */
+	result = phm_find_boot_level(&(data->dpm_table.sclk_table),
+			data->vbios_boot_state.sclk_bootup_value,
+			(uint32_t *)&(table->GraphicsBootLevel));
+
+	result = phm_find_boot_level(&(data->dpm_table.mclk_table),
+			data->vbios_boot_state.mclk_bootup_value,
+			(uint32_t *)&(table->MemoryBootLevel));
+
+	table->BootVddc  = data->vbios_boot_state.vddc_bootup_value *
+			VOLTAGE_SCALE;
+	table->BootVddci = data->vbios_boot_state.vddci_bootup_value *
+			VOLTAGE_SCALE;
+	table->BootMVdd  = data->vbios_boot_state.mvdd_bootup_value *
+			VOLTAGE_SCALE;
+
+	CONVERT_FROM_HOST_TO_SMC_US(table->BootVddc);
+	CONVERT_FROM_HOST_TO_SMC_US(table->BootVddci);
+	CONVERT_FROM_HOST_TO_SMC_US(table->BootMVdd);
+
+	return 0;
+}
+
+static int vegam_populate_smc_initial_state(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *hw_data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	uint8_t count, level;
+
+	count = (uint8_t)(table_info->vdd_dep_on_sclk->count);
+
+	for (level = 0; level < count; level++) {
+		if (table_info->vdd_dep_on_sclk->entries[level].clk >=
+				hw_data->vbios_boot_state.sclk_bootup_value) {
+			smu_data->smc_state_table.GraphicsBootLevel = level;
+			break;
+		}
+	}
+
+	count = (uint8_t)(table_info->vdd_dep_on_mclk->count);
+	for (level = 0; level < count; level++) {
+		if (table_info->vdd_dep_on_mclk->entries[level].clk >=
+				hw_data->vbios_boot_state.mclk_bootup_value) {
+			smu_data->smc_state_table.MemoryBootLevel = level;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static uint16_t scale_fan_gain_settings(uint16_t raw_setting)
+{
+	uint32_t tmp;
+	tmp = raw_setting * 4096 / 100;
+	return (uint16_t)tmp;
+}
+
+static int vegam_populate_bapm_parameters_in_dpm_table(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+
+	const struct vegam_pt_defaults *defaults = smu_data->power_tune_defaults;
+	SMU75_Discrete_DpmTable  *table = &(smu_data->smc_state_table);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_cac_tdp_table *cac_dtp_table = table_info->cac_dtp_table;
+	struct pp_advance_fan_control_parameters *fan_table =
+			&hwmgr->thermal_controller.advanceFanControlParameters;
+	int i, j, k;
+	const uint16_t *pdef1;
+	const uint16_t *pdef2;
+
+	table->DefaultTdp = PP_HOST_TO_SMC_US((uint16_t)(cac_dtp_table->usTDP * 128));
+	table->TargetTdp  = PP_HOST_TO_SMC_US((uint16_t)(cac_dtp_table->usTDP * 128));
+
+	PP_ASSERT_WITH_CODE(cac_dtp_table->usTargetOperatingTemp <= 255,
+				"Target Operating Temp is out of Range!",
+				);
+
+	table->TemperatureLimitEdge = PP_HOST_TO_SMC_US(
+			cac_dtp_table->usTargetOperatingTemp * 256);
+	table->TemperatureLimitHotspot = PP_HOST_TO_SMC_US(
+			cac_dtp_table->usTemperatureLimitHotspot * 256);
+	table->FanGainEdge = PP_HOST_TO_SMC_US(
+			scale_fan_gain_settings(fan_table->usFanGainEdge));
+	table->FanGainHotspot = PP_HOST_TO_SMC_US(
+			scale_fan_gain_settings(fan_table->usFanGainHotspot));
+
+	pdef1 = defaults->BAPMTI_R;
+	pdef2 = defaults->BAPMTI_RC;
+
+	for (i = 0; i < SMU75_DTE_ITERATIONS; i++) {
+		for (j = 0; j < SMU75_DTE_SOURCES; j++) {
+			for (k = 0; k < SMU75_DTE_SINKS; k++) {
+				table->BAPMTI_R[i][j][k] = PP_HOST_TO_SMC_US(*pdef1);
+				table->BAPMTI_RC[i][j][k] = PP_HOST_TO_SMC_US(*pdef2);
+				pdef1++;
+				pdef2++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int vegam_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
+{
+	uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min;
+	struct vegam_smumgr *smu_data =
+			(struct vegam_smumgr *)(hwmgr->smu_backend);
+
+	uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
+			table_info->vdd_dep_on_sclk;
+	uint32_t mask = (1 << ((STRAP_ASIC_RO_MSB - STRAP_ASIC_RO_LSB) + 1)) - 1;
+
+	stretch_amount = (uint8_t)table_info->cac_dtp_table->usClockStretchAmount;
+
+	atomctrl_read_efuse(hwmgr, STRAP_ASIC_RO_LSB, STRAP_ASIC_RO_MSB,
+			mask, &efuse);
+
+	min = 1200;
+	max = 2500;
+
+	ro = efuse * (max - min) / 255 + min;
+
+	/* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */
+	for (i = 0; i < sclk_table->count; i++) {
+		smu_data->smc_state_table.Sclk_CKS_masterEn0_7 |=
+				sclk_table->entries[i].cks_enable << i;
+		volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) *
+				136418 - (ro - 70) * 1000000) /
+				(2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000));
+		volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 *
+				3232 - (ro - 65) * 1000000) /
+				(2522480 - sclk_table->entries[i].clk/100 * 115764/100));
+
+		if (volt_without_cks >= volt_with_cks)
+			volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks +
+					sclk_table->entries[i].cks_voffset) * 100 + 624) / 625);
+
+		smu_data->smc_state_table.Sclk_voltageOffset[i] = volt_offset;
+	}
+
+	smu_data->smc_state_table.LdoRefSel =
+			(table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ?
+			table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 5;
+	/* Populate CKS Lookup Table */
+	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
+		stretch_amount2 = 0;
+	else if (stretch_amount == 3 || stretch_amount == 4)
+		stretch_amount2 = 1;
+	else {
+		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+				PHM_PlatformCaps_ClockStretcher);
+		PP_ASSERT_WITH_CODE(false,
+				"Stretch Amount in PPTable not supported\n",
+				return -EINVAL);
+	}
+
+	value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL);
+	value &= 0xFFFFFFFE;
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL, value);
+
+	return 0;
+}
+
+static bool vegam_is_hw_avfs_present(struct pp_hwmgr *hwmgr)
+{
+	uint32_t efuse;
+
+	efuse = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixSMU_EFUSE_0 + (49 * 4));
+	efuse &= 0x00000001;
+
+	if (efuse)
+		return true;
+
+	return false;
+}
+
+static int vegam_populate_avfs_parameters(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+
+	SMU75_Discrete_DpmTable  *table = &(smu_data->smc_state_table);
+	int result = 0;
+	struct pp_atom_ctrl__avfs_parameters avfs_params = {0};
+	AVFS_meanNsigma_t AVFS_meanNsigma = { {0} };
+	AVFS_Sclk_Offset_t AVFS_SclkOffset = { {0} };
+	uint32_t tmp, i;
+
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)hwmgr->pptable;
+	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
+			table_info->vdd_dep_on_sclk;
+
+	if (!hwmgr->avfs_supported)
+		return 0;
+
+	result = atomctrl_get_avfs_information(hwmgr, &avfs_params);
+
+	if (0 == result) {
+		table->BTCGB_VDROOP_TABLE[0].a0 =
+				PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a0);
+		table->BTCGB_VDROOP_TABLE[0].a1 =
+				PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a1);
+		table->BTCGB_VDROOP_TABLE[0].a2 =
+				PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a2);
+		table->BTCGB_VDROOP_TABLE[1].a0 =
+				PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a0);
+		table->BTCGB_VDROOP_TABLE[1].a1 =
+				PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a1);
+		table->BTCGB_VDROOP_TABLE[1].a2 =
+				PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a2);
+		table->AVFSGB_FUSE_TABLE[0].m1 =
+				PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_m1);
+		table->AVFSGB_FUSE_TABLE[0].m2 =
+				PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSON_m2);
+		table->AVFSGB_FUSE_TABLE[0].b =
+				PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_b);
+		table->AVFSGB_FUSE_TABLE[0].m1_shift = 24;
+		table->AVFSGB_FUSE_TABLE[0].m2_shift = 12;
+		table->AVFSGB_FUSE_TABLE[1].m1 =
+				PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_m1);
+		table->AVFSGB_FUSE_TABLE[1].m2 =
+				PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSOFF_m2);
+		table->AVFSGB_FUSE_TABLE[1].b =
+				PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_b);
+		table->AVFSGB_FUSE_TABLE[1].m1_shift = 24;
+		table->AVFSGB_FUSE_TABLE[1].m2_shift = 12;
+		table->MaxVoltage = PP_HOST_TO_SMC_US(avfs_params.usMaxVoltage_0_25mv);
+		AVFS_meanNsigma.Aconstant[0] =
+				PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant0);
+		AVFS_meanNsigma.Aconstant[1] =
+				PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant1);
+		AVFS_meanNsigma.Aconstant[2] =
+				PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant2);
+		AVFS_meanNsigma.DC_tol_sigma =
+				PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_DC_tol_sigma);
+		AVFS_meanNsigma.Platform_mean =
+				PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_mean);
+		AVFS_meanNsigma.PSM_Age_CompFactor =
+				PP_HOST_TO_SMC_US(avfs_params.usPSM_Age_ComFactor);
+		AVFS_meanNsigma.Platform_sigma =
+				PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_sigma);
+
+		for (i = 0; i < sclk_table->count; i++) {
+			AVFS_meanNsigma.Static_Voltage_Offset[i] =
+					(uint8_t)(sclk_table->entries[i].cks_voffset * 100 / 625);
+			AVFS_SclkOffset.Sclk_Offset[i] =
+					PP_HOST_TO_SMC_US((uint16_t)
+							(sclk_table->entries[i].sclk_offset) / 100);
+		}
+
+		result = smu7_read_smc_sram_dword(hwmgr,
+				SMU7_FIRMWARE_HEADER_LOCATION +
+				offsetof(SMU75_Firmware_Header, AvfsMeanNSigma),
+				&tmp, SMC_RAM_END);
+		smu7_copy_bytes_to_smc(hwmgr,
+					tmp,
+					(uint8_t *)&AVFS_meanNsigma,
+					sizeof(AVFS_meanNsigma_t),
+					SMC_RAM_END);
+
+		result = smu7_read_smc_sram_dword(hwmgr,
+				SMU7_FIRMWARE_HEADER_LOCATION +
+				offsetof(SMU75_Firmware_Header, AvfsSclkOffsetTable),
+				&tmp, SMC_RAM_END);
+		smu7_copy_bytes_to_smc(hwmgr,
+					tmp,
+					(uint8_t *)&AVFS_SclkOffset,
+					sizeof(AVFS_Sclk_Offset_t),
+					SMC_RAM_END);
+
+		data->avfs_vdroop_override_setting =
+				(avfs_params.ucEnableGB_VDROOP_TABLE_CKSON << BTCGB0_Vdroop_Enable_SHIFT) |
+				(avfs_params.ucEnableGB_VDROOP_TABLE_CKSOFF << BTCGB1_Vdroop_Enable_SHIFT) |
+				(avfs_params.ucEnableGB_FUSE_TABLE_CKSON << AVFSGB0_Vdroop_Enable_SHIFT) |
+				(avfs_params.ucEnableGB_FUSE_TABLE_CKSOFF << AVFSGB1_Vdroop_Enable_SHIFT);
+		data->apply_avfs_cks_off_voltage =
+				(avfs_params.ucEnableApplyAVFS_CKS_OFF_Voltage == 1) ? true : false;
+	}
+	return result;
+}
+
+static int vegam_populate_vr_config(struct pp_hwmgr *hwmgr,
+		struct SMU75_Discrete_DpmTable *table)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data =
+			(struct vegam_smumgr *)(hwmgr->smu_backend);
+	uint16_t config;
+
+	config = VR_MERGED_WITH_VDDC;
+	table->VRConfig |= (config << VRCONF_VDDGFX_SHIFT);
+
+	/* Set Vddc Voltage Controller */
+	if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->voltage_control) {
+		config = VR_SVI2_PLANE_1;
+		table->VRConfig |= config;
+	} else {
+		PP_ASSERT_WITH_CODE(false,
+				"VDDC should be on SVI2 control in merged mode!",
+				);
+	}
+	/* Set Vddci Voltage Controller */
+	if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control) {
+		config = VR_SVI2_PLANE_2;  /* only in merged mode */
+		table->VRConfig |= (config << VRCONF_VDDCI_SHIFT);
+	} else if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control) {
+		config = VR_SMIO_PATTERN_1;
+		table->VRConfig |= (config << VRCONF_VDDCI_SHIFT);
+	} else {
+		config = VR_STATIC_VOLTAGE;
+		table->VRConfig |= (config << VRCONF_VDDCI_SHIFT);
+	}
+	/* Set Mvdd Voltage Controller */
+	if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->mvdd_control) {
+		if (config != VR_SVI2_PLANE_2) {
+			config = VR_SVI2_PLANE_2;
+			table->VRConfig |= (config << VRCONF_MVDD_SHIFT);
+			cgs_write_ind_register(hwmgr->device,
+					CGS_IND_REG__SMC,
+					smu_data->smu7_data.soft_regs_start +
+					offsetof(SMU75_SoftRegisters, AllowMvddSwitch),
+					0x1);
+		} else {
+			PP_ASSERT_WITH_CODE(false,
+					"SVI2 Plane 2 is already taken, set MVDD as Static",);
+			config = VR_STATIC_VOLTAGE;
+			table->VRConfig = (config << VRCONF_MVDD_SHIFT);
+		}
+	} else if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->mvdd_control) {
+		config = VR_SMIO_PATTERN_2;
+		table->VRConfig = (config << VRCONF_MVDD_SHIFT);
+		cgs_write_ind_register(hwmgr->device,
+				CGS_IND_REG__SMC,
+				smu_data->smu7_data.soft_regs_start +
+				offsetof(SMU75_SoftRegisters, AllowMvddSwitch),
+				0x1);
+	} else {
+		config = VR_STATIC_VOLTAGE;
+		table->VRConfig |= (config << VRCONF_MVDD_SHIFT);
+	}
+
+	return 0;
+}
+
+static int vegam_populate_svi_load_line(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	const struct vegam_pt_defaults *defaults = smu_data->power_tune_defaults;
+
+	smu_data->power_tune_table.SviLoadLineEn = defaults->SviLoadLineEn;
+	smu_data->power_tune_table.SviLoadLineVddC = defaults->SviLoadLineVddC;
+	smu_data->power_tune_table.SviLoadLineTrimVddC = 3;
+	smu_data->power_tune_table.SviLoadLineOffsetVddC = 0;
+
+	return 0;
+}
+
+static int vegam_populate_tdc_limit(struct pp_hwmgr *hwmgr)
+{
+	uint16_t tdc_limit;
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	const struct vegam_pt_defaults *defaults = smu_data->power_tune_defaults;
+
+	tdc_limit = (uint16_t)(table_info->cac_dtp_table->usTDC * 128);
+	smu_data->power_tune_table.TDC_VDDC_PkgLimit =
+			CONVERT_FROM_HOST_TO_SMC_US(tdc_limit);
+	smu_data->power_tune_table.TDC_VDDC_ThrottleReleaseLimitPerc =
+			defaults->TDC_VDDC_ThrottleReleaseLimitPerc;
+	smu_data->power_tune_table.TDC_MAWt = defaults->TDC_MAWt;
+
+	return 0;
+}
+
+static int vegam_populate_dw8(struct pp_hwmgr *hwmgr, uint32_t fuse_table_offset)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	const struct vegam_pt_defaults *defaults = smu_data->power_tune_defaults;
+	uint32_t temp;
+
+	if (smu7_read_smc_sram_dword(hwmgr,
+			fuse_table_offset +
+			offsetof(SMU75_Discrete_PmFuses, TdcWaterfallCtl),
+			(uint32_t *)&temp, SMC_RAM_END))
+		PP_ASSERT_WITH_CODE(false,
+				"Attempt to read PmFuses.DW6 (SviLoadLineEn) from SMC Failed!",
+				return -EINVAL);
+	else {
+		smu_data->power_tune_table.TdcWaterfallCtl = defaults->TdcWaterfallCtl;
+		smu_data->power_tune_table.LPMLTemperatureMin =
+				(uint8_t)((temp >> 16) & 0xff);
+		smu_data->power_tune_table.LPMLTemperatureMax =
+				(uint8_t)((temp >> 8) & 0xff);
+		smu_data->power_tune_table.Reserved = (uint8_t)(temp & 0xff);
+	}
+	return 0;
+}
+
+static int vegam_populate_temperature_scaler(struct pp_hwmgr *hwmgr)
+{
+	int i;
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+
+	/* Currently not used. Set all to zero. */
+	for (i = 0; i < 16; i++)
+		smu_data->power_tune_table.LPMLTemperatureScaler[i] = 0;
+
+	return 0;
+}
+
+static int vegam_populate_fuzzy_fan(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+
+/* TO DO move to hwmgr */
+	if ((hwmgr->thermal_controller.advanceFanControlParameters.usFanOutputSensitivity & (1 << 15))
+		|| 0 == hwmgr->thermal_controller.advanceFanControlParameters.usFanOutputSensitivity)
+		hwmgr->thermal_controller.advanceFanControlParameters.usFanOutputSensitivity =
+			hwmgr->thermal_controller.advanceFanControlParameters.usDefaultFanOutputSensitivity;
+
+	smu_data->power_tune_table.FuzzyFan_PwmSetDelta = PP_HOST_TO_SMC_US(
+				hwmgr->thermal_controller.advanceFanControlParameters.usFanOutputSensitivity);
+	return 0;
+}
+
+static int vegam_populate_gnb_lpml(struct pp_hwmgr *hwmgr)
+{
+	int i;
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+
+	/* Currently not used. Set all to zero. */
+	for (i = 0; i < 16; i++)
+		smu_data->power_tune_table.GnbLPML[i] = 0;
+
+	return 0;
+}
+
+static int vegam_populate_bapm_vddc_base_leakage_sidd(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	uint16_t hi_sidd = smu_data->power_tune_table.BapmVddCBaseLeakageHiSidd;
+	uint16_t lo_sidd = smu_data->power_tune_table.BapmVddCBaseLeakageLoSidd;
+	struct phm_cac_tdp_table *cac_table = table_info->cac_dtp_table;
+
+	hi_sidd = (uint16_t)(cac_table->usHighCACLeakage / 100 * 256);
+	lo_sidd = (uint16_t)(cac_table->usLowCACLeakage / 100 * 256);
+
+	smu_data->power_tune_table.BapmVddCBaseLeakageHiSidd =
+			CONVERT_FROM_HOST_TO_SMC_US(hi_sidd);
+	smu_data->power_tune_table.BapmVddCBaseLeakageLoSidd =
+			CONVERT_FROM_HOST_TO_SMC_US(lo_sidd);
+
+	return 0;
+}
+
+static int vegam_populate_pm_fuses(struct pp_hwmgr *hwmgr)
+{
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+	uint32_t pm_fuse_table_offset;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_PowerContainment)) {
+		if (smu7_read_smc_sram_dword(hwmgr,
+				SMU7_FIRMWARE_HEADER_LOCATION +
+				offsetof(SMU75_Firmware_Header, PmFuseTable),
+				&pm_fuse_table_offset, SMC_RAM_END))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to get pm_fuse_table_offset Failed!",
+					return -EINVAL);
+
+		if (vegam_populate_svi_load_line(hwmgr))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to populate SviLoadLine Failed!",
+					return -EINVAL);
+
+		if (vegam_populate_tdc_limit(hwmgr))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to populate TDCLimit Failed!", return -EINVAL);
+
+		if (vegam_populate_dw8(hwmgr, pm_fuse_table_offset))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to populate TdcWaterfallCtl, "
+					"LPMLTemperature Min and Max Failed!",
+					return -EINVAL);
+
+		if (0 != vegam_populate_temperature_scaler(hwmgr))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to populate LPMLTemperatureScaler Failed!",
+					return -EINVAL);
+
+		if (vegam_populate_fuzzy_fan(hwmgr))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to populate Fuzzy Fan Control parameters Failed!",
+					return -EINVAL);
+
+		if (vegam_populate_gnb_lpml(hwmgr))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to populate GnbLPML Failed!",
+					return -EINVAL);
+
+		if (vegam_populate_bapm_vddc_base_leakage_sidd(hwmgr))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to populate BapmVddCBaseLeakage Hi and Lo "
+					"Sidd Failed!", return -EINVAL);
+
+		if (smu7_copy_bytes_to_smc(hwmgr, pm_fuse_table_offset,
+				(uint8_t *)&smu_data->power_tune_table,
+				(sizeof(struct SMU75_Discrete_PmFuses) - PMFUSES_AVFSSIZE),
+				SMC_RAM_END))
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to download PmFuseTable Failed!",
+					return -EINVAL);
+	}
+	return 0;
+}
+
+static int vegam_enable_reconfig_cus(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	smum_send_msg_to_smc_with_parameter(hwmgr,
+					    PPSMC_MSG_EnableModeSwitchRLCNotification,
+					    adev->gfx.cu_info.number);
+
+	return 0;
+}
+
+static int vegam_init_smc_table(struct pp_hwmgr *hwmgr)
+{
+	int result;
+	struct smu7_hwmgr *hw_data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
+
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct SMU75_Discrete_DpmTable *table = &(smu_data->smc_state_table);
+	uint8_t i;
+	struct pp_atomctrl_gpio_pin_assignment gpio_pin;
+	struct phm_ppt_v1_gpio_table *gpio_table =
+			(struct phm_ppt_v1_gpio_table *)table_info->gpio_table;
+	pp_atomctrl_clock_dividers_vi dividers;
+
+	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_AutomaticDCTransition);
+
+	vegam_initialize_power_tune_defaults(hwmgr);
+
+	if (SMU7_VOLTAGE_CONTROL_NONE != hw_data->voltage_control)
+		vegam_populate_smc_voltage_tables(hwmgr, table);
+
+	table->SystemFlags = 0;
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_AutomaticDCTransition))
+		table->SystemFlags |= PPSMC_SYSTEMFLAG_GPIO_DC;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_StepVddc))
+		table->SystemFlags |= PPSMC_SYSTEMFLAG_STEPVDDC;
+
+	if (hw_data->is_memory_gddr5)
+		table->SystemFlags |= PPSMC_SYSTEMFLAG_GDDR5;
+
+	if (hw_data->ulv_supported && table_info->us_ulv_voltage_offset) {
+		result = vegam_populate_ulv_state(hwmgr, table);
+		PP_ASSERT_WITH_CODE(!result,
+				"Failed to initialize ULV state!", return result);
+		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+				ixCG_ULV_PARAMETER, SMU7_CGULVPARAMETER_DFLT);
+	}
+
+	result = vegam_populate_smc_link_level(hwmgr, table);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize Link Level!", return result);
+
+	result = vegam_populate_all_graphic_levels(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize Graphics Level!", return result);
+
+	result = vegam_populate_all_memory_levels(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize Memory Level!", return result);
+
+	result = vegam_populate_smc_acpi_level(hwmgr, table);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize ACPI Level!", return result);
+
+	result = vegam_populate_smc_vce_level(hwmgr, table);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize VCE Level!", return result);
+
+	result = vegam_populate_smc_samu_level(hwmgr, table);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize SAMU Level!", return result);
+
+	/* Since only the initial state is completely set up at this point
+	 * (the other states are just copies of the boot state) we only
+	 * need to populate the  ARB settings for the initial state.
+	 */
+	result = vegam_program_memory_timing_parameters(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to Write ARB settings for the initial state.", return result);
+
+	result = vegam_populate_smc_uvd_level(hwmgr, table);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize UVD Level!", return result);
+
+	result = vegam_populate_smc_boot_level(hwmgr, table);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize Boot Level!", return result);
+
+	result = vegam_populate_smc_initial_state(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to initialize Boot State!", return result);
+
+	result = vegam_populate_bapm_parameters_in_dpm_table(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to populate BAPM Parameters!", return result);
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_ClockStretcher)) {
+		result = vegam_populate_clock_stretcher_data_table(hwmgr);
+		PP_ASSERT_WITH_CODE(!result,
+				"Failed to populate Clock Stretcher Data Table!",
+				return result);
+	}
+
+	result = vegam_populate_avfs_parameters(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to populate AVFS Parameters!", return result;);
+
+	table->CurrSclkPllRange = 0xff;
+	table->GraphicsVoltageChangeEnable  = 1;
+	table->GraphicsThermThrottleEnable  = 1;
+	table->GraphicsInterval = 1;
+	table->VoltageInterval  = 1;
+	table->ThermalInterval  = 1;
+	table->TemperatureLimitHigh =
+			table_info->cac_dtp_table->usTargetOperatingTemp *
+			SMU7_Q88_FORMAT_CONVERSION_UNIT;
+	table->TemperatureLimitLow  =
+			(table_info->cac_dtp_table->usTargetOperatingTemp - 1) *
+			SMU7_Q88_FORMAT_CONVERSION_UNIT;
+	table->MemoryVoltageChangeEnable = 1;
+	table->MemoryInterval = 1;
+	table->VoltageResponseTime = 0;
+	table->PhaseResponseTime = 0;
+	table->MemoryThermThrottleEnable = 1;
+
+	PP_ASSERT_WITH_CODE(hw_data->dpm_table.pcie_speed_table.count >= 1,
+			"There must be 1 or more PCIE levels defined in PPTable.",
+			return -EINVAL);
+	table->PCIeBootLinkLevel =
+			hw_data->dpm_table.pcie_speed_table.count;
+	table->PCIeGenInterval = 1;
+	table->VRConfig = 0;
+
+	result = vegam_populate_vr_config(hwmgr, table);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to populate VRConfig setting!", return result);
+
+	table->ThermGpio = 17;
+	table->SclkStepSize = 0x4000;
+
+	if (atomctrl_get_pp_assign_pin(hwmgr,
+			VDDC_VRHOT_GPIO_PINID, &gpio_pin)) {
+		table->VRHotGpio = gpio_pin.uc_gpio_pin_bit_shift;
+		if (gpio_table)
+			table->VRHotLevel =
+					table_info->gpio_table->vrhot_triggered_sclk_dpm_index;
+	} else {
+		table->VRHotGpio = SMU7_UNUSED_GPIO_PIN;
+		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+				PHM_PlatformCaps_RegulatorHot);
+	}
+
+	if (atomctrl_get_pp_assign_pin(hwmgr,
+			PP_AC_DC_SWITCH_GPIO_PINID,	&gpio_pin)) {
+		table->AcDcGpio = gpio_pin.uc_gpio_pin_bit_shift;
+		if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+				PHM_PlatformCaps_AutomaticDCTransition) &&
+				!smum_send_msg_to_smc(hwmgr, PPSMC_MSG_UseNewGPIOScheme))
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+					PHM_PlatformCaps_SMCtoPPLIBAcdcGpioScheme);
+	} else {
+		table->AcDcGpio = SMU7_UNUSED_GPIO_PIN;
+		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+				PHM_PlatformCaps_AutomaticDCTransition);
+	}
+
+	/* Thermal Output GPIO */
+	if (atomctrl_get_pp_assign_pin(hwmgr,
+			THERMAL_INT_OUTPUT_GPIO_PINID, &gpio_pin)) {
+		table->ThermOutGpio = gpio_pin.uc_gpio_pin_bit_shift;
+
+		/* For porlarity read GPIOPAD_A with assigned Gpio pin
+		 * since VBIOS will program this register to set 'inactive state',
+		 * driver can then determine 'active state' from this and
+		 * program SMU with correct polarity
+		 */
+		table->ThermOutPolarity =
+				(0 == (cgs_read_register(hwmgr->device, mmGPIOPAD_A) &
+				(1 << gpio_pin.uc_gpio_pin_bit_shift))) ? 1:0;
+		table->ThermOutMode = SMU7_THERM_OUT_MODE_THERM_ONLY;
+
+		/* if required, combine VRHot/PCC with thermal out GPIO */
+		if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+				PHM_PlatformCaps_RegulatorHot) &&
+			phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+				PHM_PlatformCaps_CombinePCCWithThermalSignal))
+			table->ThermOutMode = SMU7_THERM_OUT_MODE_THERM_VRHOT;
+	} else {
+		table->ThermOutGpio = 17;
+		table->ThermOutPolarity = 1;
+		table->ThermOutMode = SMU7_THERM_OUT_MODE_DISABLE;
+	}
+
+	/* Populate BIF_SCLK levels into SMC DPM table */
+	for (i = 0; i <= hw_data->dpm_table.pcie_speed_table.count; i++) {
+		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
+				smu_data->bif_sclk_table[i], &dividers);
+		PP_ASSERT_WITH_CODE(!result,
+				"Can not find DFS divide id for Sclk",
+				return result);
+
+		if (i == 0)
+			table->Ulv.BifSclkDfs =
+					PP_HOST_TO_SMC_US((uint16_t)(dividers.pll_post_divider));
+		else
+			table->LinkLevel[i - 1].BifSclkDfs =
+					PP_HOST_TO_SMC_US((uint16_t)(dividers.pll_post_divider));
+	}
+
+	for (i = 0; i < SMU75_MAX_ENTRIES_SMIO; i++)
+		table->Smio[i] = PP_HOST_TO_SMC_UL(table->Smio[i]);
+
+	CONVERT_FROM_HOST_TO_SMC_UL(table->SystemFlags);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->VRConfig);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->SmioMask1);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->SmioMask2);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->SclkStepSize);
+	CONVERT_FROM_HOST_TO_SMC_UL(table->CurrSclkPllRange);
+	CONVERT_FROM_HOST_TO_SMC_US(table->TemperatureLimitHigh);
+	CONVERT_FROM_HOST_TO_SMC_US(table->TemperatureLimitLow);
+	CONVERT_FROM_HOST_TO_SMC_US(table->VoltageResponseTime);
+	CONVERT_FROM_HOST_TO_SMC_US(table->PhaseResponseTime);
+
+	/* Upload all dpm data to SMC memory.(dpm level, dpm level count etc) */
+	result = smu7_copy_bytes_to_smc(hwmgr,
+			smu_data->smu7_data.dpm_table_start +
+			offsetof(SMU75_Discrete_DpmTable, SystemFlags),
+			(uint8_t *)&(table->SystemFlags),
+			sizeof(SMU75_Discrete_DpmTable) - 3 * sizeof(SMU75_PIDController),
+			SMC_RAM_END);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to upload dpm data to SMC memory!", return result);
+
+	result = vegam_populate_pm_fuses(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to  populate PM fuses to SMC memory!", return result);
+
+	result = vegam_enable_reconfig_cus(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to enable reconfigurable CUs!", return result);
+
+	return 0;
+}
+
+static uint32_t vegam_get_offsetof(uint32_t type, uint32_t member)
+{
+	switch (type) {
+	case SMU_SoftRegisters:
+		switch (member) {
+		case HandshakeDisables:
+			return offsetof(SMU75_SoftRegisters, HandshakeDisables);
+		case VoltageChangeTimeout:
+			return offsetof(SMU75_SoftRegisters, VoltageChangeTimeout);
+		case AverageGraphicsActivity:
+			return offsetof(SMU75_SoftRegisters, AverageGraphicsActivity);
+		case PreVBlankGap:
+			return offsetof(SMU75_SoftRegisters, PreVBlankGap);
+		case VBlankTimeout:
+			return offsetof(SMU75_SoftRegisters, VBlankTimeout);
+		case UcodeLoadStatus:
+			return offsetof(SMU75_SoftRegisters, UcodeLoadStatus);
+		case DRAM_LOG_ADDR_H:
+			return offsetof(SMU75_SoftRegisters, DRAM_LOG_ADDR_H);
+		case DRAM_LOG_ADDR_L:
+			return offsetof(SMU75_SoftRegisters, DRAM_LOG_ADDR_L);
+		case DRAM_LOG_PHY_ADDR_H:
+			return offsetof(SMU75_SoftRegisters, DRAM_LOG_PHY_ADDR_H);
+		case DRAM_LOG_PHY_ADDR_L:
+			return offsetof(SMU75_SoftRegisters, DRAM_LOG_PHY_ADDR_L);
+		case DRAM_LOG_BUFF_SIZE:
+			return offsetof(SMU75_SoftRegisters, DRAM_LOG_BUFF_SIZE);
+		}
+	case SMU_Discrete_DpmTable:
+		switch (member) {
+		case UvdBootLevel:
+			return offsetof(SMU75_Discrete_DpmTable, UvdBootLevel);
+		case VceBootLevel:
+			return offsetof(SMU75_Discrete_DpmTable, VceBootLevel);
+		case SamuBootLevel:
+			return offsetof(SMU75_Discrete_DpmTable, SamuBootLevel);
+		case LowSclkInterruptThreshold:
+			return offsetof(SMU75_Discrete_DpmTable, LowSclkInterruptThreshold);
+		}
+	}
+	pr_warn("can't get the offset of type %x member %x\n", type, member);
+	return 0;
+}
+
+static int vegam_program_mem_timing_parameters(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+
+	if (data->need_update_smu7_dpm_table &
+		(DPMTABLE_OD_UPDATE_SCLK +
+		DPMTABLE_UPDATE_SCLK +
+		DPMTABLE_UPDATE_MCLK))
+		return vegam_program_memory_timing_parameters(hwmgr);
+
+	return 0;
+}
+
+static int vegam_update_sclk_threshold(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct vegam_smumgr *smu_data =
+			(struct vegam_smumgr *)(hwmgr->smu_backend);
+	int result = 0;
+	uint32_t low_sclk_interrupt_threshold = 0;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_SclkThrottleLowNotification)
+	    && (data->low_sclk_interrupt_threshold != 0)) {
+		low_sclk_interrupt_threshold =
+				data->low_sclk_interrupt_threshold;
+
+		CONVERT_FROM_HOST_TO_SMC_UL(low_sclk_interrupt_threshold);
+
+		result = smu7_copy_bytes_to_smc(
+				hwmgr,
+				smu_data->smu7_data.dpm_table_start +
+				offsetof(SMU75_Discrete_DpmTable,
+					LowSclkInterruptThreshold),
+				(uint8_t *)&low_sclk_interrupt_threshold,
+				sizeof(uint32_t),
+				SMC_RAM_END);
+	}
+	PP_ASSERT_WITH_CODE((result == 0),
+			"Failed to update SCLK threshold!", return result);
+
+	result = vegam_program_mem_timing_parameters(hwmgr);
+	PP_ASSERT_WITH_CODE((result == 0),
+			"Failed to program memory timing parameters!",
+			);
+
+	return result;
+}
+
+int vegam_thermal_avfs_enable(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	int ret;
+
+	if (!hwmgr->avfs_supported)
+		return 0;
+
+	ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_EnableAvfs);
+	if (!ret) {
+		if (data->apply_avfs_cks_off_voltage)
+			ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ApplyAvfsCksOffVoltage);
+	}
+
+	return ret;
+}
+
+static int vegam_thermal_setup_fan_table(struct pp_hwmgr *hwmgr)
+{
+	PP_ASSERT_WITH_CODE(hwmgr->thermal_controller.fanInfo.bNoFan,
+			"VBIOS fan info is not correct!",
+			);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_MicrocodeFanControl);
+	return 0;
+}
+
+const struct pp_smumgr_func vegam_smu_funcs = {
+	.smu_init = vegam_smu_init,
+	.smu_fini = smu7_smu_fini,
+	.start_smu = vegam_start_smu,
+	.check_fw_load_finish = smu7_check_fw_load_finish,
+	.request_smu_load_fw = smu7_reload_firmware,
+	.request_smu_load_specific_fw = NULL,
+	.send_msg_to_smc = smu7_send_msg_to_smc,
+	.send_msg_to_smc_with_parameter = smu7_send_msg_to_smc_with_parameter,
+	.process_firmware_header = vegam_process_firmware_header,
+	.is_dpm_running = vegam_is_dpm_running,
+	.get_mac_definition = vegam_get_mac_definition,
+	.update_smc_table = vegam_update_smc_table,
+	.init_smc_table = vegam_init_smc_table,
+	.get_offsetof = vegam_get_offsetof,
+	.populate_all_graphic_levels = vegam_populate_all_graphic_levels,
+	.populate_all_memory_levels = vegam_populate_all_memory_levels,
+	.update_sclk_threshold = vegam_update_sclk_threshold,
+	.is_hw_avfs_present = vegam_is_hw_avfs_present,
+	.thermal_avfs_enable = vegam_thermal_avfs_enable,
+	.thermal_setup_fan_table = vegam_thermal_setup_fan_table,
+};
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.h
new file mode 100644
index 000000000000..2b6558238500
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.h
@@ -0,0 +1,75 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _VEGAM_SMUMANAGER_H
+#define _VEGAM_SMUMANAGER_H
+
+
+#include <pp_endian.h>
+#include "smu75_discrete.h"
+#include "smu7_smumgr.h"
+
+#define SMC_RAM_END 0x40000
+
+#define DPMTuning_Uphyst_Shift    0
+#define DPMTuning_Downhyst_Shift  8
+#define DPMTuning_Activity_Shift  16
+
+#define GraphicsDPMTuning_VEGAM    0x001e6400
+#define MemoryDPMTuning_VEGAM      0x000f3c0a
+#define SclkDPMTuning_VEGAM        0x002d000a
+#define MclkDPMTuning_VEGAM        0x001f100a
+
+
+struct vegam_pt_defaults {
+	uint8_t   SviLoadLineEn;
+	uint8_t   SviLoadLineVddC;
+	uint8_t   TDC_VDDC_ThrottleReleaseLimitPerc;
+	uint8_t   TDC_MAWt;
+	uint8_t   TdcWaterfallCtl;
+	uint8_t   DTEAmbientTempBase;
+
+	uint32_t  DisplayCac;
+	uint32_t  BAPM_TEMP_GRADIENT;
+	uint16_t  BAPMTI_R[SMU75_DTE_ITERATIONS * SMU75_DTE_SOURCES * SMU75_DTE_SINKS];
+	uint16_t  BAPMTI_RC[SMU75_DTE_ITERATIONS * SMU75_DTE_SOURCES * SMU75_DTE_SINKS];
+};
+
+struct vegam_range_table {
+	uint32_t trans_lower_frequency; /* in 10khz */
+	uint32_t trans_upper_frequency;
+};
+
+struct vegam_smumgr {
+	struct smu7_smumgr smu7_data;
+	uint8_t protected_mode;
+	SMU75_Discrete_DpmTable              smc_state_table;
+	struct SMU75_Discrete_Ulv            ulv_setting;
+	struct SMU75_Discrete_PmFuses  power_tune_table;
+	struct vegam_range_table                range_table[NUM_SCLK_RANGE];
+	const struct vegam_pt_defaults       *power_tune_defaults;
+	uint32_t               bif_sclk_table[SMU75_MAX_LEVELS_LINK];
+};
+
+
+#endif
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 831b73392d82..036dff8a1f33 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -799,7 +799,7 @@ static int ast_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static int ast_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status ast_mode_valid(struct drm_connector *connector,
 			  struct drm_display_mode *mode)
 {
 	struct ast_private *ast = connector->dev->dev_private;
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h
index ab32d5b268d2..60c937f42114 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h
@@ -299,7 +299,6 @@ struct atmel_hlcdc_layer {
 struct atmel_hlcdc_plane {
 	struct drm_plane base;
 	struct atmel_hlcdc_layer layer;
-	struct atmel_hlcdc_plane_properties *properties;
 };
 
 static inline struct atmel_hlcdc_plane *
@@ -346,18 +345,6 @@ struct atmel_hlcdc_dc_desc {
 };
 
 /**
- * Atmel HLCDC Plane properties.
- *
- * This structure stores plane property definitions.
- *
- * @alpha: alpha blending (or transparency) property
- * @rotation: rotation property
- */
-struct atmel_hlcdc_plane_properties {
-	struct drm_property *alpha;
-};
-
-/**
  * Atmel HLCDC Display Controller.
  *
  * @desc: HLCDC Display Controller description
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index e18800ed7cd1..73c875db45f4 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -31,7 +31,6 @@
  * @src_y: y buffer position
  * @src_w: buffer width
  * @src_h: buffer height
- * @alpha: alpha blending of the plane
  * @disc_x: x discard position
  * @disc_y: y discard position
  * @disc_w: discard width
@@ -54,8 +53,6 @@ struct atmel_hlcdc_plane_state {
 	uint32_t src_w;
 	uint32_t src_h;
 
-	u8 alpha;
-
 	int disc_x;
 	int disc_y;
 	int disc_w;
@@ -385,7 +382,7 @@ atmel_hlcdc_plane_update_general_settings(struct atmel_hlcdc_plane *plane,
 			cfg |= ATMEL_HLCDC_LAYER_LAEN;
 		else
 			cfg |= ATMEL_HLCDC_LAYER_GAEN |
-			       ATMEL_HLCDC_LAYER_GA(state->alpha);
+			       ATMEL_HLCDC_LAYER_GA(state->base.alpha >> 8);
 	}
 
 	if (state->disc_h && state->disc_w)
@@ -553,7 +550,7 @@ atmel_hlcdc_plane_prepare_disc_area(struct drm_crtc_state *c_state)
 
 		if (!ovl_s->fb ||
 		    ovl_s->fb->format->has_alpha ||
-		    ovl_state->alpha != 255)
+		    ovl_s->alpha != DRM_BLEND_ALPHA_OPAQUE)
 			continue;
 
 		/* TODO: implement a smarter hidden area detection */
@@ -829,51 +826,18 @@ static void atmel_hlcdc_plane_destroy(struct drm_plane *p)
 	drm_plane_cleanup(p);
 }
 
-static int atmel_hlcdc_plane_atomic_set_property(struct drm_plane *p,
-						 struct drm_plane_state *s,
-						 struct drm_property *property,
-						 uint64_t val)
-{
-	struct atmel_hlcdc_plane *plane = drm_plane_to_atmel_hlcdc_plane(p);
-	struct atmel_hlcdc_plane_properties *props = plane->properties;
-	struct atmel_hlcdc_plane_state *state =
-			drm_plane_state_to_atmel_hlcdc_plane_state(s);
-
-	if (property == props->alpha)
-		state->alpha = val;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-
-static int atmel_hlcdc_plane_atomic_get_property(struct drm_plane *p,
-					const struct drm_plane_state *s,
-					struct drm_property *property,
-					uint64_t *val)
-{
-	struct atmel_hlcdc_plane *plane = drm_plane_to_atmel_hlcdc_plane(p);
-	struct atmel_hlcdc_plane_properties *props = plane->properties;
-	const struct atmel_hlcdc_plane_state *state =
-		container_of(s, const struct atmel_hlcdc_plane_state, base);
-
-	if (property == props->alpha)
-		*val = state->alpha;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-
-static int atmel_hlcdc_plane_init_properties(struct atmel_hlcdc_plane *plane,
-				struct atmel_hlcdc_plane_properties *props)
+static int atmel_hlcdc_plane_init_properties(struct atmel_hlcdc_plane *plane)
 {
 	const struct atmel_hlcdc_layer_desc *desc = plane->layer.desc;
 
 	if (desc->type == ATMEL_HLCDC_OVERLAY_LAYER ||
-	    desc->type == ATMEL_HLCDC_CURSOR_LAYER)
-		drm_object_attach_property(&plane->base.base,
-					   props->alpha, 255);
+	    desc->type == ATMEL_HLCDC_CURSOR_LAYER) {
+		int ret;
+
+		ret = drm_plane_create_alpha_property(&plane->base);
+		if (ret)
+			return ret;
+	}
 
 	if (desc->layout.xstride && desc->layout.pstride) {
 		int ret;
@@ -988,8 +952,8 @@ static void atmel_hlcdc_plane_reset(struct drm_plane *p)
 			return;
 		}
 
-		state->alpha = 255;
 		p->state = &state->base;
+		p->state->alpha = DRM_BLEND_ALPHA_OPAQUE;
 		p->state->plane = p;
 	}
 }
@@ -1042,13 +1006,10 @@ static const struct drm_plane_funcs layer_plane_funcs = {
 	.reset = atmel_hlcdc_plane_reset,
 	.atomic_duplicate_state = atmel_hlcdc_plane_atomic_duplicate_state,
 	.atomic_destroy_state = atmel_hlcdc_plane_atomic_destroy_state,
-	.atomic_set_property = atmel_hlcdc_plane_atomic_set_property,
-	.atomic_get_property = atmel_hlcdc_plane_atomic_get_property,
 };
 
 static int atmel_hlcdc_plane_create(struct drm_device *dev,
-				    const struct atmel_hlcdc_layer_desc *desc,
-				    struct atmel_hlcdc_plane_properties *props)
+				    const struct atmel_hlcdc_layer_desc *desc)
 {
 	struct atmel_hlcdc_dc *dc = dev->dev_private;
 	struct atmel_hlcdc_plane *plane;
@@ -1060,7 +1021,6 @@ static int atmel_hlcdc_plane_create(struct drm_device *dev,
 		return -ENOMEM;
 
 	atmel_hlcdc_layer_init(&plane->layer, desc, dc->hlcdc->regmap);
-	plane->properties = props;
 
 	if (desc->type == ATMEL_HLCDC_BASE_LAYER)
 		type = DRM_PLANE_TYPE_PRIMARY;
@@ -1081,7 +1041,7 @@ static int atmel_hlcdc_plane_create(struct drm_device *dev,
 			     &atmel_hlcdc_layer_plane_helper_funcs);
 
 	/* Set default property values*/
-	ret = atmel_hlcdc_plane_init_properties(plane, props);
+	ret = atmel_hlcdc_plane_init_properties(plane);
 	if (ret)
 		return ret;
 
@@ -1090,34 +1050,13 @@ static int atmel_hlcdc_plane_create(struct drm_device *dev,
 	return 0;
 }
 
-static struct atmel_hlcdc_plane_properties *
-atmel_hlcdc_plane_create_properties(struct drm_device *dev)
-{
-	struct atmel_hlcdc_plane_properties *props;
-
-	props = devm_kzalloc(dev->dev, sizeof(*props), GFP_KERNEL);
-	if (!props)
-		return ERR_PTR(-ENOMEM);
-
-	props->alpha = drm_property_create_range(dev, 0, "alpha", 0, 255);
-	if (!props->alpha)
-		return ERR_PTR(-ENOMEM);
-
-	return props;
-}
-
 int atmel_hlcdc_create_planes(struct drm_device *dev)
 {
 	struct atmel_hlcdc_dc *dc = dev->dev_private;
-	struct atmel_hlcdc_plane_properties *props;
 	const struct atmel_hlcdc_layer_desc *descs = dc->desc->layers;
 	int nlayers = dc->desc->nlayers;
 	int i, ret;
 
-	props = atmel_hlcdc_plane_create_properties(dev);
-	if (IS_ERR(props))
-		return PTR_ERR(props);
-
 	dc->dscrpool = dmam_pool_create("atmel-hlcdc-dscr", dev->dev,
 				sizeof(struct atmel_hlcdc_dma_channel_dscr),
 				sizeof(u64), 0);
@@ -1130,7 +1069,7 @@ int atmel_hlcdc_create_planes(struct drm_device *dev)
 		    descs[i].type != ATMEL_HLCDC_CURSOR_LAYER)
 			continue;
 
-		ret = atmel_hlcdc_plane_create(dev, &descs[i], props);
+		ret = atmel_hlcdc_plane_create(dev, &descs[i]);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index a24a18fbd65a..233980a78591 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -188,7 +188,7 @@ static int bochs_connector_get_modes(struct drm_connector *connector)
 	return count;
 }
 
-static int bochs_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status bochs_connector_mode_valid(struct drm_connector *connector,
 				      struct drm_display_mode *mode)
 {
 	struct bochs_device *bochs =
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index 3aa65bdecb0e..fa2c7997e2fd 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -25,6 +25,16 @@ config DRM_ANALOGIX_ANX78XX
 	  the HDMI output of an application processor to MyDP
 	  or DisplayPort.
 
+config DRM_CDNS_DSI
+	tristate "Cadence DPI/DSI bridge"
+	select DRM_KMS_HELPER
+	select DRM_MIPI_DSI
+	select DRM_PANEL_BRIDGE
+	depends on OF
+	help
+	  Support Cadence DPI to DSI bridge. This is an internal
+	  bridge and is meant to be directly embedded in a SoC.
+
 config DRM_DUMB_VGA_DAC
 	tristate "Dumb VGA DAC Bridge support"
 	depends on OF
@@ -74,6 +84,7 @@ config DRM_SIL_SII8620
 	tristate "Silicon Image SII8620 HDMI/MHL bridge"
 	depends on OF && RC_CORE
 	select DRM_KMS_HELPER
+	imply EXTCON
 	help
 	  Silicon Image SII8620 HDMI/MHL bridge chip driver.
 
@@ -93,6 +104,12 @@ config DRM_SII9234
 	  It is an I2C driver, that detects connection of MHL bridge
 	  and starts encapsulation of HDMI signal.
 
+config DRM_THINE_THC63LVD1024
+	tristate "Thine THC63LVD1024 LVDS decoder bridge"
+	depends on OF
+	---help---
+	  Thine THC63LVD1024 LVDS/parallel converter driver.
+
 config DRM_TOSHIBA_TC358767
 	tristate "Toshiba TC358767 eDP bridge"
 	depends on OF
diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile
index 373eb28f31ed..35f88d48ec20 100644
--- a/drivers/gpu/drm/bridge/Makefile
+++ b/drivers/gpu/drm/bridge/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_DRM_ANALOGIX_ANX78XX) += analogix-anx78xx.o
+obj-$(CONFIG_DRM_CDNS_DSI) += cdns-dsi.o
 obj-$(CONFIG_DRM_DUMB_VGA_DAC) += dumb-vga-dac.o
 obj-$(CONFIG_DRM_LVDS_ENCODER) += lvds-encoder.o
 obj-$(CONFIG_DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW) += megachips-stdpxxxx-ge-b850v3-fw.o
@@ -8,6 +9,7 @@ obj-$(CONFIG_DRM_PARADE_PS8622) += parade-ps8622.o
 obj-$(CONFIG_DRM_SIL_SII8620) += sil-sii8620.o
 obj-$(CONFIG_DRM_SII902X) += sii902x.o
 obj-$(CONFIG_DRM_SII9234) += sii9234.o
+obj-$(CONFIG_DRM_THINE_THC63LVD1024) += thc63lvd1024.o
 obj-$(CONFIG_DRM_TOSHIBA_TC358767) += tc358767.o
 obj-$(CONFIG_DRM_ANALOGIX_DP) += analogix/
 obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/
diff --git a/drivers/gpu/drm/bridge/adv7511/Kconfig b/drivers/gpu/drm/bridge/adv7511/Kconfig
index 592b9d2ec034..944e440c4fde 100644
--- a/drivers/gpu/drm/bridge/adv7511/Kconfig
+++ b/drivers/gpu/drm/bridge/adv7511/Kconfig
@@ -1,5 +1,5 @@
 config DRM_I2C_ADV7511
-	tristate "AV7511 encoder"
+	tristate "ADV7511 encoder"
 	depends on OF
 	select DRM_KMS_HELPER
 	select REGMAP_I2C
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511.h b/drivers/gpu/drm/bridge/adv7511/adv7511.h
index d034b2cb5eee..73d8ccb97742 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511.h
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511.h
@@ -93,6 +93,11 @@
 #define ADV7511_REG_CHIP_ID_HIGH		0xf5
 #define ADV7511_REG_CHIP_ID_LOW			0xf6
 
+/* Hardware defined default addresses for I2C register maps */
+#define ADV7511_CEC_I2C_ADDR_DEFAULT		0x3c
+#define ADV7511_EDID_I2C_ADDR_DEFAULT		0x3f
+#define ADV7511_PACKET_I2C_ADDR_DEFAULT		0x38
+
 #define ADV7511_CSC_ENABLE			BIT(7)
 #define ADV7511_CSC_UPDATE_MODE			BIT(5)
 
@@ -321,6 +326,7 @@ enum adv7511_type {
 struct adv7511 {
 	struct i2c_client *i2c_main;
 	struct i2c_client *i2c_edid;
+	struct i2c_client *i2c_packet;
 	struct i2c_client *i2c_cec;
 
 	struct regmap *regmap;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index efa29db5fc2b..73021b388e12 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -586,7 +586,7 @@ static int adv7511_get_modes(struct adv7511 *adv7511,
 	/* Reading the EDID only works if the device is powered */
 	if (!adv7511->powered) {
 		unsigned int edid_i2c_addr =
-					(adv7511->i2c_main->addr << 1) + 4;
+					(adv7511->i2c_edid->addr << 1);
 
 		__adv7511_power_on(adv7511);
 
@@ -654,7 +654,7 @@ adv7511_detect(struct adv7511 *adv7511, struct drm_connector *connector)
 	return status;
 }
 
-static int adv7511_mode_valid(struct adv7511 *adv7511,
+static enum drm_mode_status adv7511_mode_valid(struct adv7511 *adv7511,
 			      struct drm_display_mode *mode)
 {
 	if (mode->clock > 165000)
@@ -969,10 +969,10 @@ static int adv7511_init_cec_regmap(struct adv7511 *adv)
 {
 	int ret;
 
-	adv->i2c_cec = i2c_new_dummy(adv->i2c_main->adapter,
-				     adv->i2c_main->addr - 1);
+	adv->i2c_cec = i2c_new_secondary_device(adv->i2c_main, "cec",
+						ADV7511_CEC_I2C_ADDR_DEFAULT);
 	if (!adv->i2c_cec)
-		return -ENOMEM;
+		return -EINVAL;
 	i2c_set_clientdata(adv->i2c_cec, adv);
 
 	adv->regmap_cec = devm_regmap_init_i2c(adv->i2c_cec,
@@ -1082,8 +1082,6 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	struct adv7511_link_config link_config;
 	struct adv7511 *adv7511;
 	struct device *dev = &i2c->dev;
-	unsigned int main_i2c_addr = i2c->addr << 1;
-	unsigned int edid_i2c_addr = main_i2c_addr + 4;
 	unsigned int val;
 	int ret;
 
@@ -1129,7 +1127,7 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	}
 
 	if (adv7511->gpio_pd) {
-		mdelay(5);
+		usleep_range(5000, 6000);
 		gpiod_set_value_cansleep(adv7511->gpio_pd, 0);
 	}
 
@@ -1153,23 +1151,34 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	if (ret)
 		goto uninit_regulators;
 
-	regmap_write(adv7511->regmap, ADV7511_REG_EDID_I2C_ADDR, edid_i2c_addr);
-	regmap_write(adv7511->regmap, ADV7511_REG_PACKET_I2C_ADDR,
-		     main_i2c_addr - 0xa);
-	regmap_write(adv7511->regmap, ADV7511_REG_CEC_I2C_ADDR,
-		     main_i2c_addr - 2);
-
 	adv7511_packet_disable(adv7511, 0xffff);
 
-	adv7511->i2c_edid = i2c_new_dummy(i2c->adapter, edid_i2c_addr >> 1);
+	adv7511->i2c_edid = i2c_new_secondary_device(i2c, "edid",
+					ADV7511_EDID_I2C_ADDR_DEFAULT);
 	if (!adv7511->i2c_edid) {
-		ret = -ENOMEM;
+		ret = -EINVAL;
 		goto uninit_regulators;
 	}
 
+	regmap_write(adv7511->regmap, ADV7511_REG_EDID_I2C_ADDR,
+		     adv7511->i2c_edid->addr << 1);
+
+	adv7511->i2c_packet = i2c_new_secondary_device(i2c, "packet",
+					ADV7511_PACKET_I2C_ADDR_DEFAULT);
+	if (!adv7511->i2c_packet) {
+		ret = -EINVAL;
+		goto err_i2c_unregister_edid;
+	}
+
+	regmap_write(adv7511->regmap, ADV7511_REG_PACKET_I2C_ADDR,
+		     adv7511->i2c_packet->addr << 1);
+
 	ret = adv7511_init_cec_regmap(adv7511);
 	if (ret)
-		goto err_i2c_unregister_edid;
+		goto err_i2c_unregister_packet;
+
+	regmap_write(adv7511->regmap, ADV7511_REG_CEC_I2C_ADDR,
+		     adv7511->i2c_cec->addr << 1);
 
 	INIT_WORK(&adv7511->hpd_work, adv7511_hpd_work);
 
@@ -1207,6 +1216,8 @@ err_unregister_cec:
 	i2c_unregister_device(adv7511->i2c_cec);
 	if (adv7511->cec_clk)
 		clk_disable_unprepare(adv7511->cec_clk);
+err_i2c_unregister_packet:
+	i2c_unregister_device(adv7511->i2c_packet);
 err_i2c_unregister_edid:
 	i2c_unregister_device(adv7511->i2c_edid);
 uninit_regulators:
@@ -1233,6 +1244,7 @@ static int adv7511_remove(struct i2c_client *i2c)
 
 	cec_unregister_adapter(adv7511->cec_adap);
 
+	i2c_unregister_device(adv7511->i2c_packet);
 	i2c_unregister_device(adv7511->i2c_edid);
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 5c52307146c7..2bcbfadb6ac5 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -43,8 +43,10 @@ struct bridge_init {
 	struct device_node *node;
 };
 
-static void analogix_dp_init_dp(struct analogix_dp_device *dp)
+static int analogix_dp_init_dp(struct analogix_dp_device *dp)
 {
+	int ret;
+
 	analogix_dp_reset(dp);
 
 	analogix_dp_swreset(dp);
@@ -56,10 +58,13 @@ static void analogix_dp_init_dp(struct analogix_dp_device *dp)
 	analogix_dp_enable_sw_function(dp);
 
 	analogix_dp_config_interrupt(dp);
-	analogix_dp_init_analog_func(dp);
+	ret = analogix_dp_init_analog_func(dp);
+	if (ret)
+		return ret;
 
 	analogix_dp_init_hpd(dp);
 	analogix_dp_init_aux(dp);
+	return 0;
 }
 
 static int analogix_dp_detect_hpd(struct analogix_dp_device *dp)
@@ -71,7 +76,7 @@ static int analogix_dp_detect_hpd(struct analogix_dp_device *dp)
 			return 0;
 
 		timeout_loop++;
-		usleep_range(10, 11);
+		usleep_range(1000, 1100);
 	}
 
 	/*
@@ -148,87 +153,146 @@ int analogix_dp_disable_psr(struct analogix_dp_device *dp)
 	psr_vsc.DB1 = 0;
 
 	ret = drm_dp_dpcd_writeb(&dp->aux, DP_SET_POWER, DP_SET_POWER_D0);
-	if (ret != 1)
+	if (ret != 1) {
 		dev_err(dp->dev, "Failed to set DP Power0 %d\n", ret);
+		return ret;
+	}
 
 	return analogix_dp_send_psr_spd(dp, &psr_vsc, false);
 }
 EXPORT_SYMBOL_GPL(analogix_dp_disable_psr);
 
-static bool analogix_dp_detect_sink_psr(struct analogix_dp_device *dp)
+static int analogix_dp_detect_sink_psr(struct analogix_dp_device *dp)
 {
 	unsigned char psr_version;
+	int ret;
+
+	ret = drm_dp_dpcd_readb(&dp->aux, DP_PSR_SUPPORT, &psr_version);
+	if (ret != 1) {
+		dev_err(dp->dev, "failed to get PSR version, disable it\n");
+		return ret;
+	}
 
-	drm_dp_dpcd_readb(&dp->aux, DP_PSR_SUPPORT, &psr_version);
 	dev_dbg(dp->dev, "Panel PSR version : %x\n", psr_version);
 
-	return (psr_version & DP_PSR_IS_SUPPORTED) ? true : false;
+	dp->psr_enable = (psr_version & DP_PSR_IS_SUPPORTED) ? true : false;
+
+	return 0;
 }
 
-static void analogix_dp_enable_sink_psr(struct analogix_dp_device *dp)
+static int analogix_dp_enable_sink_psr(struct analogix_dp_device *dp)
 {
 	unsigned char psr_en;
+	int ret;
 
 	/* Disable psr function */
-	drm_dp_dpcd_readb(&dp->aux, DP_PSR_EN_CFG, &psr_en);
+	ret = drm_dp_dpcd_readb(&dp->aux, DP_PSR_EN_CFG, &psr_en);
+	if (ret != 1) {
+		dev_err(dp->dev, "failed to get psr config\n");
+		goto end;
+	}
+
 	psr_en &= ~DP_PSR_ENABLE;
-	drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en);
+	ret = drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en);
+	if (ret != 1) {
+		dev_err(dp->dev, "failed to disable panel psr\n");
+		goto end;
+	}
 
 	/* Main-Link transmitter remains active during PSR active states */
 	psr_en = DP_PSR_MAIN_LINK_ACTIVE | DP_PSR_CRC_VERIFICATION;
-	drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en);
+	ret = drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en);
+	if (ret != 1) {
+		dev_err(dp->dev, "failed to set panel psr\n");
+		goto end;
+	}
 
 	/* Enable psr function */
 	psr_en = DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE |
 		 DP_PSR_CRC_VERIFICATION;
-	drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en);
+	ret = drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en);
+	if (ret != 1) {
+		dev_err(dp->dev, "failed to set panel psr\n");
+		goto end;
+	}
 
 	analogix_dp_enable_psr_crc(dp);
+
+	return 0;
+end:
+	dev_err(dp->dev, "enable psr fail, force to disable psr\n");
+	dp->psr_enable = false;
+
+	return ret;
 }
 
-static void
+static int
 analogix_dp_enable_rx_to_enhanced_mode(struct analogix_dp_device *dp,
 				       bool enable)
 {
 	u8 data;
+	int ret;
 
-	drm_dp_dpcd_readb(&dp->aux, DP_LANE_COUNT_SET, &data);
+	ret = drm_dp_dpcd_readb(&dp->aux, DP_LANE_COUNT_SET, &data);
+	if (ret != 1)
+		return ret;
 
 	if (enable)
-		drm_dp_dpcd_writeb(&dp->aux, DP_LANE_COUNT_SET,
-				   DP_LANE_COUNT_ENHANCED_FRAME_EN |
-					DPCD_LANE_COUNT_SET(data));
+		ret = drm_dp_dpcd_writeb(&dp->aux, DP_LANE_COUNT_SET,
+					 DP_LANE_COUNT_ENHANCED_FRAME_EN |
+					 DPCD_LANE_COUNT_SET(data));
 	else
-		drm_dp_dpcd_writeb(&dp->aux, DP_LANE_COUNT_SET,
-				   DPCD_LANE_COUNT_SET(data));
+		ret = drm_dp_dpcd_writeb(&dp->aux, DP_LANE_COUNT_SET,
+					 DPCD_LANE_COUNT_SET(data));
+
+	return ret < 0 ? ret : 0;
 }
 
-static int analogix_dp_is_enhanced_mode_available(struct analogix_dp_device *dp)
+static int analogix_dp_is_enhanced_mode_available(struct analogix_dp_device *dp,
+						  u8 *enhanced_mode_support)
 {
 	u8 data;
-	int retval;
+	int ret;
 
-	drm_dp_dpcd_readb(&dp->aux, DP_MAX_LANE_COUNT, &data);
-	retval = DPCD_ENHANCED_FRAME_CAP(data);
+	ret = drm_dp_dpcd_readb(&dp->aux, DP_MAX_LANE_COUNT, &data);
+	if (ret != 1) {
+		*enhanced_mode_support = 0;
+		return ret;
+	}
 
-	return retval;
+	*enhanced_mode_support = DPCD_ENHANCED_FRAME_CAP(data);
+
+	return 0;
 }
 
-static void analogix_dp_set_enhanced_mode(struct analogix_dp_device *dp)
+static int analogix_dp_set_enhanced_mode(struct analogix_dp_device *dp)
 {
 	u8 data;
+	int ret;
+
+	ret = analogix_dp_is_enhanced_mode_available(dp, &data);
+	if (ret < 0)
+		return ret;
+
+	ret = analogix_dp_enable_rx_to_enhanced_mode(dp, data);
+	if (ret < 0)
+		return ret;
 
-	data = analogix_dp_is_enhanced_mode_available(dp);
-	analogix_dp_enable_rx_to_enhanced_mode(dp, data);
 	analogix_dp_enable_enhanced_mode(dp, data);
+
+	return 0;
 }
 
-static void analogix_dp_training_pattern_dis(struct analogix_dp_device *dp)
+static int analogix_dp_training_pattern_dis(struct analogix_dp_device *dp)
 {
+	int ret;
+
 	analogix_dp_set_training_pattern(dp, DP_NONE);
 
-	drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET,
-			   DP_TRAINING_PATTERN_DISABLE);
+	ret = drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET,
+				 DP_TRAINING_PATTERN_DISABLE);
+
+	return ret < 0 ? ret : 0;
 }
 
 static void
@@ -276,6 +340,12 @@ static int analogix_dp_link_start(struct analogix_dp_device *dp)
 	retval = drm_dp_dpcd_write(&dp->aux, DP_LINK_BW_SET, buf, 2);
 	if (retval < 0)
 		return retval;
+	/* set enhanced mode if available */
+	retval = analogix_dp_set_enhanced_mode(dp);
+	if (retval < 0) {
+		dev_err(dp->dev, "failed to set enhance mode\n");
+		return retval;
+	}
 
 	/* Set TX pre-emphasis to minimum */
 	for (lane = 0; lane < lane_count; lane++)
@@ -531,7 +601,7 @@ static int analogix_dp_process_equalizer_training(struct analogix_dp_device *dp)
 {
 	int lane, lane_count, retval;
 	u32 reg;
-	u8 link_align, link_status[2], adjust_request[2], spread;
+	u8 link_align, link_status[2], adjust_request[2];
 
 	usleep_range(400, 401);
 
@@ -560,10 +630,11 @@ static int analogix_dp_process_equalizer_training(struct analogix_dp_device *dp)
 
 	if (!analogix_dp_channel_eq_ok(link_status, link_align, lane_count)) {
 		/* traing pattern Set to Normal */
-		analogix_dp_training_pattern_dis(dp);
+		retval = analogix_dp_training_pattern_dis(dp);
+		if (retval < 0)
+			return retval;
 
 		dev_info(dp->dev, "Link Training success!\n");
-
 		analogix_dp_get_link_bandwidth(dp, &reg);
 		dp->link_train.link_rate = reg;
 		dev_dbg(dp->dev, "final bandwidth = %.2x\n",
@@ -574,22 +645,6 @@ static int analogix_dp_process_equalizer_training(struct analogix_dp_device *dp)
 		dev_dbg(dp->dev, "final lane count = %.2x\n",
 			dp->link_train.lane_count);
 
-		retval = drm_dp_dpcd_readb(&dp->aux, DP_MAX_DOWNSPREAD,
-					   &spread);
-		if (retval != 1) {
-			dev_err(dp->dev, "failed to read downspread %d\n",
-				retval);
-			dp->fast_train_support = false;
-		} else {
-			dp->fast_train_support =
-				(spread & DP_NO_AUX_HANDSHAKE_LINK_TRAINING) ?
-					true : false;
-		}
-		dev_dbg(dp->dev, "fast link training %s\n",
-			dp->fast_train_support ? "supported" : "unsupported");
-
-		/* set enhanced mode if available */
-		analogix_dp_set_enhanced_mode(dp);
 		dp->link_train.lt_state = FINISHED;
 
 		return 0;
@@ -793,7 +848,7 @@ static int analogix_dp_fast_link_train(struct analogix_dp_device *dp)
 
 static int analogix_dp_train_link(struct analogix_dp_device *dp)
 {
-	if (dp->fast_train_support)
+	if (dp->fast_train_enable)
 		return analogix_dp_fast_link_train(dp);
 
 	return analogix_dp_full_link_train(dp, dp->video_info.max_lane_count,
@@ -819,11 +874,10 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp)
 		if (analogix_dp_is_slave_video_stream_clock_on(dp) == 0)
 			break;
 		if (timeout_loop > DP_TIMEOUT_LOOP_COUNT) {
-			dev_err(dp->dev, "Timeout of video streamclk ok\n");
+			dev_err(dp->dev, "Timeout of slave video streamclk ok\n");
 			return -ETIMEDOUT;
 		}
-
-		usleep_range(1, 2);
+		usleep_range(1000, 1001);
 	}
 
 	/* Set to use the register calculated M/N video */
@@ -838,6 +892,9 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp)
 	/* Configure video slave mode */
 	analogix_dp_enable_video_master(dp, 0);
 
+	/* Enable video */
+	analogix_dp_start_video(dp);
+
 	timeout_loop = 0;
 
 	for (;;) {
@@ -850,8 +907,9 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp)
 			done_count = 0;
 		}
 		if (timeout_loop > DP_TIMEOUT_LOOP_COUNT) {
-			dev_err(dp->dev, "Timeout of video streamclk ok\n");
-			return -ETIMEDOUT;
+			dev_warn(dp->dev,
+				 "Ignoring timeout of video streamclk ok\n");
+			break;
 		}
 
 		usleep_range(1000, 1001);
@@ -860,24 +918,32 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp)
 	return 0;
 }
 
-static void analogix_dp_enable_scramble(struct analogix_dp_device *dp,
-					bool enable)
+static int analogix_dp_enable_scramble(struct analogix_dp_device *dp,
+				       bool enable)
 {
 	u8 data;
+	int ret;
 
 	if (enable) {
 		analogix_dp_enable_scrambling(dp);
 
-		drm_dp_dpcd_readb(&dp->aux, DP_TRAINING_PATTERN_SET, &data);
-		drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET,
+		ret = drm_dp_dpcd_readb(&dp->aux, DP_TRAINING_PATTERN_SET,
+					&data);
+		if (ret != 1)
+			return ret;
+		ret = drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET,
 				   (u8)(data & ~DP_LINK_SCRAMBLING_DISABLE));
 	} else {
 		analogix_dp_disable_scrambling(dp);
 
-		drm_dp_dpcd_readb(&dp->aux, DP_TRAINING_PATTERN_SET, &data);
-		drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET,
+		ret = drm_dp_dpcd_readb(&dp->aux, DP_TRAINING_PATTERN_SET,
+					&data);
+		if (ret != 1)
+			return ret;
+		ret = drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET,
 				   (u8)(data | DP_LINK_SCRAMBLING_DISABLE));
 	}
+	return ret < 0 ? ret : 0;
 }
 
 static irqreturn_t analogix_dp_hardirq(int irq, void *arg)
@@ -916,7 +982,23 @@ static irqreturn_t analogix_dp_irq_thread(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static void analogix_dp_commit(struct analogix_dp_device *dp)
+static int analogix_dp_fast_link_train_detection(struct analogix_dp_device *dp)
+{
+	int ret;
+	u8 spread;
+
+	ret = drm_dp_dpcd_readb(&dp->aux, DP_MAX_DOWNSPREAD, &spread);
+	if (ret != 1) {
+		dev_err(dp->dev, "failed to read downspread %d\n", ret);
+		return ret;
+	}
+	dp->fast_train_enable = !!(spread & DP_NO_AUX_HANDSHAKE_LINK_TRAINING);
+	dev_dbg(dp->dev, "fast link training %s\n",
+		dp->fast_train_enable ? "supported" : "unsupported");
+	return 0;
+}
+
+static int analogix_dp_commit(struct analogix_dp_device *dp)
 {
 	int ret;
 
@@ -926,34 +1008,50 @@ static void analogix_dp_commit(struct analogix_dp_device *dp)
 			DRM_ERROR("failed to disable the panel\n");
 	}
 
-	ret = readx_poll_timeout(analogix_dp_train_link, dp, ret, !ret, 100,
-				 DP_TIMEOUT_TRAINING_US * 5);
+	ret = analogix_dp_train_link(dp);
 	if (ret) {
 		dev_err(dp->dev, "unable to do link train, ret=%d\n", ret);
-		return;
+		return ret;
 	}
 
-	analogix_dp_enable_scramble(dp, 1);
-	analogix_dp_enable_rx_to_enhanced_mode(dp, 1);
-	analogix_dp_enable_enhanced_mode(dp, 1);
+	ret = analogix_dp_enable_scramble(dp, 1);
+	if (ret < 0) {
+		dev_err(dp->dev, "can not enable scramble\n");
+		return ret;
+	}
 
 	analogix_dp_init_video(dp);
 	ret = analogix_dp_config_video(dp);
-	if (ret)
+	if (ret) {
 		dev_err(dp->dev, "unable to config video\n");
+		return ret;
+	}
 
 	/* Safe to enable the panel now */
 	if (dp->plat_data->panel) {
-		if (drm_panel_enable(dp->plat_data->panel))
+		ret = drm_panel_enable(dp->plat_data->panel);
+		if (ret) {
 			DRM_ERROR("failed to enable the panel\n");
+			return ret;
+		}
 	}
 
-	/* Enable video */
-	analogix_dp_start_video(dp);
+	ret = analogix_dp_detect_sink_psr(dp);
+	if (ret)
+		return ret;
 
-	dp->psr_enable = analogix_dp_detect_sink_psr(dp);
-	if (dp->psr_enable)
-		analogix_dp_enable_sink_psr(dp);
+	if (dp->psr_enable) {
+		ret = analogix_dp_enable_sink_psr(dp);
+		if (ret)
+			return ret;
+	}
+
+	/* Check whether panel supports fast training */
+	ret =  analogix_dp_fast_link_train_detection(dp);
+	if (ret)
+		dp->psr_enable = false;
+
+	return ret;
 }
 
 /*
@@ -1150,24 +1248,80 @@ static void analogix_dp_bridge_pre_enable(struct drm_bridge *bridge)
 		DRM_ERROR("failed to setup the panel ret = %d\n", ret);
 }
 
-static void analogix_dp_bridge_enable(struct drm_bridge *bridge)
+static int analogix_dp_set_bridge(struct analogix_dp_device *dp)
 {
-	struct analogix_dp_device *dp = bridge->driver_private;
-
-	if (dp->dpms_mode == DRM_MODE_DPMS_ON)
-		return;
+	int ret;
 
 	pm_runtime_get_sync(dp->dev);
 
-	if (dp->plat_data->power_on)
-		dp->plat_data->power_on(dp->plat_data);
+	ret = clk_prepare_enable(dp->clock);
+	if (ret < 0) {
+		DRM_ERROR("Failed to prepare_enable the clock clk [%d]\n", ret);
+		goto out_dp_clk_pre;
+	}
+
+	if (dp->plat_data->power_on_start)
+		dp->plat_data->power_on_start(dp->plat_data);
 
 	phy_power_on(dp->phy);
-	analogix_dp_init_dp(dp);
+
+	ret = analogix_dp_init_dp(dp);
+	if (ret)
+		goto out_dp_init;
+
+	/*
+	 * According to DP spec v1.3 chap 3.5.1.2 Link Training,
+	 * We should first make sure the HPD signal is asserted high by device
+	 * when we want to establish a link with it.
+	 */
+	ret = analogix_dp_detect_hpd(dp);
+	if (ret) {
+		DRM_ERROR("failed to get hpd single ret = %d\n", ret);
+		goto out_dp_init;
+	}
+
+	ret = analogix_dp_commit(dp);
+	if (ret) {
+		DRM_ERROR("dp commit error, ret = %d\n", ret);
+		goto out_dp_init;
+	}
+
+	if (dp->plat_data->power_on_end)
+		dp->plat_data->power_on_end(dp->plat_data);
+
 	enable_irq(dp->irq);
-	analogix_dp_commit(dp);
+	return 0;
 
-	dp->dpms_mode = DRM_MODE_DPMS_ON;
+out_dp_init:
+	phy_power_off(dp->phy);
+	if (dp->plat_data->power_off)
+		dp->plat_data->power_off(dp->plat_data);
+	clk_disable_unprepare(dp->clock);
+out_dp_clk_pre:
+	pm_runtime_put_sync(dp->dev);
+
+	return ret;
+}
+
+static void analogix_dp_bridge_enable(struct drm_bridge *bridge)
+{
+	struct analogix_dp_device *dp = bridge->driver_private;
+	int timeout_loop = 0;
+
+	if (dp->dpms_mode == DRM_MODE_DPMS_ON)
+		return;
+
+	while (timeout_loop < MAX_PLL_LOCK_LOOP) {
+		if (analogix_dp_set_bridge(dp) == 0) {
+			dp->dpms_mode = DRM_MODE_DPMS_ON;
+			return;
+		}
+		dev_err(dp->dev, "failed to set bridge, retry: %d\n",
+			timeout_loop);
+		timeout_loop++;
+		usleep_range(10, 11);
+	}
+	dev_err(dp->dev, "too many times retry set bridge, give it up\n");
 }
 
 static void analogix_dp_bridge_disable(struct drm_bridge *bridge)
@@ -1186,11 +1340,15 @@ static void analogix_dp_bridge_disable(struct drm_bridge *bridge)
 	}
 
 	disable_irq(dp->irq);
-	phy_power_off(dp->phy);
 
 	if (dp->plat_data->power_off)
 		dp->plat_data->power_off(dp->plat_data);
 
+	analogix_dp_set_analog_power_down(dp, POWER_ALL, 1);
+	phy_power_off(dp->phy);
+
+	clk_disable_unprepare(dp->clock);
+
 	pm_runtime_put_sync(dp->dev);
 
 	ret = analogix_dp_prepare_panel(dp, false, true);
@@ -1198,6 +1356,7 @@ static void analogix_dp_bridge_disable(struct drm_bridge *bridge)
 		DRM_ERROR("failed to setup the panel ret = %d\n", ret);
 
 	dp->psr_enable = false;
+	dp->fast_train_enable = false;
 	dp->dpms_mode = DRM_MODE_DPMS_OFF;
 }
 
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h
index 6a96ef7e6934..769255dc6e99 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h
@@ -19,6 +19,7 @@
 #define DP_TIMEOUT_LOOP_COUNT 100
 #define MAX_CR_LOOP 5
 #define MAX_EQ_LOOP 5
+#define MAX_PLL_LOCK_LOOP 5
 
 /* Training takes 22ms if AUX channel comm fails. Use this as retry interval */
 #define DP_TIMEOUT_TRAINING_US			22000
@@ -173,7 +174,7 @@ struct analogix_dp_device {
 	int			hpd_gpio;
 	bool                    force_hpd;
 	bool			psr_enable;
-	bool			fast_train_support;
+	bool			fast_train_enable;
 
 	struct mutex		panel_lock;
 	bool			panel_is_modeset;
@@ -197,7 +198,7 @@ void analogix_dp_set_pll_power_down(struct analogix_dp_device *dp, bool enable);
 void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp,
 				       enum analog_power_block block,
 				       bool enable);
-void analogix_dp_init_analog_func(struct analogix_dp_device *dp);
+int analogix_dp_init_analog_func(struct analogix_dp_device *dp);
 void analogix_dp_init_hpd(struct analogix_dp_device *dp);
 void analogix_dp_force_hpd(struct analogix_dp_device *dp);
 enum dp_irq_type analogix_dp_get_irq_type(struct analogix_dp_device *dp);
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
index 9df2f3ef000c..a5f2763d72e4 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
@@ -126,9 +126,14 @@ void analogix_dp_reset(struct analogix_dp_device *dp)
 	analogix_dp_stop_video(dp);
 	analogix_dp_enable_video_mute(dp, 0);
 
-	reg = MASTER_VID_FUNC_EN_N | SLAVE_VID_FUNC_EN_N |
-		AUD_FIFO_FUNC_EN_N | AUD_FUNC_EN_N |
-		HDCP_FUNC_EN_N | SW_FUNC_EN_N;
+	if (dp->plat_data && is_rockchip(dp->plat_data->dev_type))
+		reg = RK_VID_CAP_FUNC_EN_N | RK_VID_FIFO_FUNC_EN_N |
+			SW_FUNC_EN_N;
+	else
+		reg = MASTER_VID_FUNC_EN_N | SLAVE_VID_FUNC_EN_N |
+			AUD_FIFO_FUNC_EN_N | AUD_FUNC_EN_N |
+			HDCP_FUNC_EN_N | SW_FUNC_EN_N;
+
 	writel(reg, dp->reg_base + ANALOGIX_DP_FUNC_EN_1);
 
 	reg = SSC_FUNC_EN_N | AUX_FUNC_EN_N |
@@ -230,16 +235,20 @@ enum pll_status analogix_dp_get_pll_lock_status(struct analogix_dp_device *dp)
 void analogix_dp_set_pll_power_down(struct analogix_dp_device *dp, bool enable)
 {
 	u32 reg;
+	u32 mask = DP_PLL_PD;
+	u32 pd_addr = ANALOGIX_DP_PLL_CTL;
 
-	if (enable) {
-		reg = readl(dp->reg_base + ANALOGIX_DP_PLL_CTL);
-		reg |= DP_PLL_PD;
-		writel(reg, dp->reg_base + ANALOGIX_DP_PLL_CTL);
-	} else {
-		reg = readl(dp->reg_base + ANALOGIX_DP_PLL_CTL);
-		reg &= ~DP_PLL_PD;
-		writel(reg, dp->reg_base + ANALOGIX_DP_PLL_CTL);
+	if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) {
+		pd_addr = ANALOGIX_DP_PD;
+		mask = RK_PLL_PD;
 	}
+
+	reg = readl(dp->reg_base + pd_addr);
+	if (enable)
+		reg |= mask;
+	else
+		reg &= ~mask;
+	writel(reg, dp->reg_base + pd_addr);
 }
 
 void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp,
@@ -248,83 +257,98 @@ void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp,
 {
 	u32 reg;
 	u32 phy_pd_addr = ANALOGIX_DP_PHY_PD;
+	u32 mask;
 
 	if (dp->plat_data && is_rockchip(dp->plat_data->dev_type))
 		phy_pd_addr = ANALOGIX_DP_PD;
 
 	switch (block) {
 	case AUX_BLOCK:
-		if (enable) {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg |= AUX_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		} else {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg &= ~AUX_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		}
+		if (dp->plat_data && is_rockchip(dp->plat_data->dev_type))
+			mask = RK_AUX_PD;
+		else
+			mask = AUX_PD;
+
+		reg = readl(dp->reg_base + phy_pd_addr);
+		if (enable)
+			reg |= mask;
+		else
+			reg &= ~mask;
+		writel(reg, dp->reg_base + phy_pd_addr);
 		break;
 	case CH0_BLOCK:
-		if (enable) {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg |= CH0_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		} else {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg &= ~CH0_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		}
+		mask = CH0_PD;
+		reg = readl(dp->reg_base + phy_pd_addr);
+
+		if (enable)
+			reg |= mask;
+		else
+			reg &= ~mask;
+		writel(reg, dp->reg_base + phy_pd_addr);
 		break;
 	case CH1_BLOCK:
-		if (enable) {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg |= CH1_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		} else {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg &= ~CH1_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		}
+		mask = CH1_PD;
+		reg = readl(dp->reg_base + phy_pd_addr);
+
+		if (enable)
+			reg |= mask;
+		else
+			reg &= ~mask;
+		writel(reg, dp->reg_base + phy_pd_addr);
 		break;
 	case CH2_BLOCK:
-		if (enable) {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg |= CH2_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		} else {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg &= ~CH2_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		}
+		mask = CH2_PD;
+		reg = readl(dp->reg_base + phy_pd_addr);
+
+		if (enable)
+			reg |= mask;
+		else
+			reg &= ~mask;
+		writel(reg, dp->reg_base + phy_pd_addr);
 		break;
 	case CH3_BLOCK:
-		if (enable) {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg |= CH3_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		} else {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg &= ~CH3_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		}
+		mask = CH3_PD;
+		reg = readl(dp->reg_base + phy_pd_addr);
+
+		if (enable)
+			reg |= mask;
+		else
+			reg &= ~mask;
+		writel(reg, dp->reg_base + phy_pd_addr);
 		break;
 	case ANALOG_TOTAL:
-		if (enable) {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg |= DP_PHY_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		} else {
-			reg = readl(dp->reg_base + phy_pd_addr);
-			reg &= ~DP_PHY_PD;
-			writel(reg, dp->reg_base + phy_pd_addr);
-		}
+		/*
+		 * There is no bit named DP_PHY_PD, so We used DP_INC_BG
+		 * to power off everything instead of DP_PHY_PD in
+		 * Rockchip
+		 */
+		if (dp->plat_data && is_rockchip(dp->plat_data->dev_type))
+			mask = DP_INC_BG;
+		else
+			mask = DP_PHY_PD;
+
+		reg = readl(dp->reg_base + phy_pd_addr);
+		if (enable)
+			reg |= mask;
+		else
+			reg &= ~mask;
+
+		writel(reg, dp->reg_base + phy_pd_addr);
+		if (dp->plat_data && is_rockchip(dp->plat_data->dev_type))
+			usleep_range(10, 15);
 		break;
 	case POWER_ALL:
 		if (enable) {
-			reg = DP_PHY_PD | AUX_PD | CH3_PD | CH2_PD |
-				CH1_PD | CH0_PD;
+			reg = DP_ALL_PD;
 			writel(reg, dp->reg_base + phy_pd_addr);
 		} else {
+			reg = DP_ALL_PD;
+			writel(reg, dp->reg_base + phy_pd_addr);
+			usleep_range(10, 15);
+			reg &= ~DP_INC_BG;
+			writel(reg, dp->reg_base + phy_pd_addr);
+			usleep_range(10, 15);
+
 			writel(0x00, dp->reg_base + phy_pd_addr);
 		}
 		break;
@@ -333,7 +357,7 @@ void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp,
 	}
 }
 
-void analogix_dp_init_analog_func(struct analogix_dp_device *dp)
+int analogix_dp_init_analog_func(struct analogix_dp_device *dp)
 {
 	u32 reg;
 	int timeout_loop = 0;
@@ -355,7 +379,7 @@ void analogix_dp_init_analog_func(struct analogix_dp_device *dp)
 			timeout_loop++;
 			if (DP_TIMEOUT_LOOP_COUNT < timeout_loop) {
 				dev_err(dp->dev, "failed to get pll lock status\n");
-				return;
+				return -ETIMEDOUT;
 			}
 			usleep_range(10, 20);
 		}
@@ -366,6 +390,7 @@ void analogix_dp_init_analog_func(struct analogix_dp_device *dp)
 	reg &= ~(SERDES_FIFO_FUNC_EN_N | LS_CLK_DOMAIN_FUNC_EN_N
 		| AUX_FUNC_EN_N);
 	writel(reg, dp->reg_base + ANALOGIX_DP_FUNC_EN_2);
+	return 0;
 }
 
 void analogix_dp_clear_hotplug_interrupts(struct analogix_dp_device *dp)
@@ -450,17 +475,22 @@ void analogix_dp_init_aux(struct analogix_dp_device *dp)
 	reg = RPLY_RECEIV | AUX_ERR;
 	writel(reg, dp->reg_base + ANALOGIX_DP_INT_STA);
 
+	analogix_dp_set_analog_power_down(dp, AUX_BLOCK, true);
+	usleep_range(10, 11);
+	analogix_dp_set_analog_power_down(dp, AUX_BLOCK, false);
+
 	analogix_dp_reset_aux(dp);
 
-	/* Disable AUX transaction H/W retry */
+	/* AUX_BIT_PERIOD_EXPECTED_DELAY doesn't apply to Rockchip IP */
 	if (dp->plat_data && is_rockchip(dp->plat_data->dev_type))
-		reg = AUX_BIT_PERIOD_EXPECTED_DELAY(0) |
-		      AUX_HW_RETRY_COUNT_SEL(3) |
-		      AUX_HW_RETRY_INTERVAL_600_MICROSECONDS;
+		reg = 0;
 	else
-		reg = AUX_BIT_PERIOD_EXPECTED_DELAY(3) |
-		      AUX_HW_RETRY_COUNT_SEL(0) |
-		      AUX_HW_RETRY_INTERVAL_600_MICROSECONDS;
+		reg = AUX_BIT_PERIOD_EXPECTED_DELAY(3);
+
+	/* Disable AUX transaction H/W retry */
+	reg |= AUX_HW_RETRY_COUNT_SEL(0) |
+	       AUX_HW_RETRY_INTERVAL_600_MICROSECONDS;
+
 	writel(reg, dp->reg_base + ANALOGIX_DP_AUX_HW_RETRY_CTL);
 
 	/* Receive AUX Channel DEFER commands equal to DEFFER_COUNT*64 */
@@ -947,8 +977,12 @@ void analogix_dp_config_video_slave_mode(struct analogix_dp_device *dp)
 	u32 reg;
 
 	reg = readl(dp->reg_base + ANALOGIX_DP_FUNC_EN_1);
-	reg &= ~(MASTER_VID_FUNC_EN_N | SLAVE_VID_FUNC_EN_N);
-	reg |= MASTER_VID_FUNC_EN_N;
+	if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) {
+		reg &= ~(RK_VID_CAP_FUNC_EN_N | RK_VID_FIFO_FUNC_EN_N);
+	} else {
+		reg &= ~(MASTER_VID_FUNC_EN_N | SLAVE_VID_FUNC_EN_N);
+		reg |= MASTER_VID_FUNC_EN_N;
+	}
 	writel(reg, dp->reg_base + ANALOGIX_DP_FUNC_EN_1);
 
 	reg = readl(dp->reg_base + ANALOGIX_DP_VIDEO_CTL_10);
@@ -1072,10 +1106,11 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
 			     struct drm_dp_aux_msg *msg)
 {
 	u32 reg;
+	u32 status_reg;
 	u8 *buffer = msg->buffer;
-	int timeout_loop = 0;
 	unsigned int i;
 	int num_transferred = 0;
+	int ret;
 
 	/* Buffer size of AUX CH is 16 bytes */
 	if (WARN_ON(msg->size > 16))
@@ -1139,17 +1174,20 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
 
 	writel(reg, dp->reg_base + ANALOGIX_DP_AUX_CH_CTL_2);
 
-	/* Is AUX CH command reply received? */
+	ret = readx_poll_timeout(readl, dp->reg_base + ANALOGIX_DP_AUX_CH_CTL_2,
+				 reg, !(reg & AUX_EN), 25, 500 * 1000);
+	if (ret) {
+		dev_err(dp->dev, "AUX CH enable timeout!\n");
+		goto aux_error;
+	}
+
 	/* TODO: Wait for an interrupt instead of looping? */
-	reg = readl(dp->reg_base + ANALOGIX_DP_INT_STA);
-	while (!(reg & RPLY_RECEIV)) {
-		timeout_loop++;
-		if (timeout_loop > DP_TIMEOUT_LOOP_COUNT) {
-			dev_err(dp->dev, "AUX CH command reply failed!\n");
-			return -ETIMEDOUT;
-		}
-		reg = readl(dp->reg_base + ANALOGIX_DP_INT_STA);
-		usleep_range(10, 11);
+	/* Is AUX CH command reply received? */
+	ret = readx_poll_timeout(readl, dp->reg_base + ANALOGIX_DP_INT_STA,
+				 reg, reg & RPLY_RECEIV, 10, 20 * 1000);
+	if (ret) {
+		dev_err(dp->dev, "AUX CH cmd reply timeout!\n");
+		goto aux_error;
 	}
 
 	/* Clear interrupt source for AUX CH command reply */
@@ -1157,17 +1195,13 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
 
 	/* Clear interrupt source for AUX CH access error */
 	reg = readl(dp->reg_base + ANALOGIX_DP_INT_STA);
-	if (reg & AUX_ERR) {
+	status_reg = readl(dp->reg_base + ANALOGIX_DP_AUX_CH_STA);
+	if ((reg & AUX_ERR) || (status_reg & AUX_STATUS_MASK)) {
 		writel(AUX_ERR, dp->reg_base + ANALOGIX_DP_INT_STA);
-		return -EREMOTEIO;
-	}
 
-	/* Check AUX CH error access status */
-	reg = readl(dp->reg_base + ANALOGIX_DP_AUX_CH_STA);
-	if ((reg & AUX_STATUS_MASK)) {
-		dev_err(dp->dev, "AUX CH error happened: %d\n\n",
-			reg & AUX_STATUS_MASK);
-		return -EREMOTEIO;
+		dev_warn(dp->dev, "AUX CH error happened: %#x (%d)\n",
+			 status_reg & AUX_STATUS_MASK, !!(reg & AUX_ERR));
+		goto aux_error;
 	}
 
 	if (msg->request & DP_AUX_I2C_READ) {
@@ -1193,4 +1227,10 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
 		msg->reply = DP_AUX_NATIVE_REPLY_ACK;
 
 	return num_transferred > 0 ? num_transferred : -EBUSY;
+
+aux_error:
+	/* if aux err happen, reset aux */
+	analogix_dp_init_aux(dp);
+
+	return -EREMOTEIO;
 }
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h
index 40200c652533..0cf27c731727 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h
@@ -127,7 +127,9 @@
 
 /* ANALOGIX_DP_FUNC_EN_1 */
 #define MASTER_VID_FUNC_EN_N			(0x1 << 7)
+#define RK_VID_CAP_FUNC_EN_N			(0x1 << 6)
 #define SLAVE_VID_FUNC_EN_N			(0x1 << 5)
+#define RK_VID_FIFO_FUNC_EN_N			(0x1 << 5)
 #define AUD_FIFO_FUNC_EN_N			(0x1 << 4)
 #define AUD_FUNC_EN_N				(0x1 << 3)
 #define HDCP_FUNC_EN_N				(0x1 << 2)
@@ -342,12 +344,17 @@
 #define DP_PLL_REF_BIT_1_2500V			(0x7 << 0)
 
 /* ANALOGIX_DP_PHY_PD */
+#define DP_INC_BG				(0x1 << 7)
+#define DP_EXP_BG				(0x1 << 6)
 #define DP_PHY_PD				(0x1 << 5)
+#define RK_AUX_PD				(0x1 << 5)
 #define AUX_PD					(0x1 << 4)
+#define RK_PLL_PD				(0x1 << 4)
 #define CH3_PD					(0x1 << 3)
 #define CH2_PD					(0x1 << 2)
 #define CH1_PD					(0x1 << 1)
 #define CH0_PD					(0x1 << 0)
+#define DP_ALL_PD				(0xff)
 
 /* ANALOGIX_DP_PHY_TEST */
 #define MACRO_RST				(0x1 << 5)
diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
new file mode 100644
index 000000000000..c255fc3e1be5
--- /dev/null
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -0,0 +1,1623 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright: 2017 Cadence Design Systems, Inc.
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_bridge.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_panel.h>
+#include <video/mipi_display.h>
+
+#include <linux/clk.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_graph.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+
+#define IP_CONF				0x0
+#define SP_HS_FIFO_DEPTH(x)		(((x) & GENMASK(30, 26)) >> 26)
+#define SP_LP_FIFO_DEPTH(x)		(((x) & GENMASK(25, 21)) >> 21)
+#define VRS_FIFO_DEPTH(x)		(((x) & GENMASK(20, 16)) >> 16)
+#define DIRCMD_FIFO_DEPTH(x)		(((x) & GENMASK(15, 13)) >> 13)
+#define SDI_IFACE_32			BIT(12)
+#define INTERNAL_DATAPATH_32		(0 << 10)
+#define INTERNAL_DATAPATH_16		(1 << 10)
+#define INTERNAL_DATAPATH_8		(3 << 10)
+#define INTERNAL_DATAPATH_SIZE		((x) & GENMASK(11, 10))
+#define NUM_IFACE(x)			((((x) & GENMASK(9, 8)) >> 8) + 1)
+#define MAX_LANE_NB(x)			(((x) & GENMASK(7, 6)) >> 6)
+#define RX_FIFO_DEPTH(x)		((x) & GENMASK(5, 0))
+
+#define MCTL_MAIN_DATA_CTL		0x4
+#define TE_MIPI_POLLING_EN		BIT(25)
+#define TE_HW_POLLING_EN		BIT(24)
+#define DISP_EOT_GEN			BIT(18)
+#define HOST_EOT_GEN			BIT(17)
+#define DISP_GEN_CHECKSUM		BIT(16)
+#define DISP_GEN_ECC			BIT(15)
+#define BTA_EN				BIT(14)
+#define READ_EN				BIT(13)
+#define REG_TE_EN			BIT(12)
+#define IF_TE_EN(x)			BIT(8 + (x))
+#define TVG_SEL				BIT(6)
+#define VID_EN				BIT(5)
+#define IF_VID_SELECT(x)		((x) << 2)
+#define IF_VID_SELECT_MASK		GENMASK(3, 2)
+#define IF_VID_MODE			BIT(1)
+#define LINK_EN				BIT(0)
+
+#define MCTL_MAIN_PHY_CTL		0x8
+#define HS_INVERT_DAT(x)		BIT(19 + ((x) * 2))
+#define SWAP_PINS_DAT(x)		BIT(18 + ((x) * 2))
+#define HS_INVERT_CLK			BIT(17)
+#define SWAP_PINS_CLK			BIT(16)
+#define HS_SKEWCAL_EN			BIT(15)
+#define WAIT_BURST_TIME(x)		((x) << 10)
+#define DATA_ULPM_EN(x)			BIT(6 + (x))
+#define CLK_ULPM_EN			BIT(5)
+#define CLK_CONTINUOUS			BIT(4)
+#define DATA_LANE_EN(x)			BIT((x) - 1)
+
+#define MCTL_MAIN_EN			0xc
+#define DATA_FORCE_STOP			BIT(17)
+#define CLK_FORCE_STOP			BIT(16)
+#define IF_EN(x)			BIT(13 + (x))
+#define DATA_LANE_ULPM_REQ(l)		BIT(9 + (l))
+#define CLK_LANE_ULPM_REQ		BIT(8)
+#define DATA_LANE_START(x)		BIT(4 + (x))
+#define CLK_LANE_EN			BIT(3)
+#define PLL_START			BIT(0)
+
+#define MCTL_DPHY_CFG0			0x10
+#define DPHY_C_RSTB			BIT(20)
+#define DPHY_D_RSTB(x)			GENMASK(15 + (x), 16)
+#define DPHY_PLL_PDN			BIT(10)
+#define DPHY_CMN_PDN			BIT(9)
+#define DPHY_C_PDN			BIT(8)
+#define DPHY_D_PDN(x)			GENMASK(3 + (x), 4)
+#define DPHY_ALL_D_PDN			GENMASK(7, 4)
+#define DPHY_PLL_PSO			BIT(1)
+#define DPHY_CMN_PSO			BIT(0)
+
+#define MCTL_DPHY_TIMEOUT1		0x14
+#define HSTX_TIMEOUT(x)			((x) << 4)
+#define HSTX_TIMEOUT_MAX		GENMASK(17, 0)
+#define CLK_DIV(x)			(x)
+#define CLK_DIV_MAX			GENMASK(3, 0)
+
+#define MCTL_DPHY_TIMEOUT2		0x18
+#define LPRX_TIMEOUT(x)			(x)
+
+#define MCTL_ULPOUT_TIME		0x1c
+#define DATA_LANE_ULPOUT_TIME(x)	((x) << 9)
+#define CLK_LANE_ULPOUT_TIME(x)		(x)
+
+#define MCTL_3DVIDEO_CTL		0x20
+#define VID_VSYNC_3D_EN			BIT(7)
+#define VID_VSYNC_3D_LR			BIT(5)
+#define VID_VSYNC_3D_SECOND_EN		BIT(4)
+#define VID_VSYNC_3DFORMAT_LINE		(0 << 2)
+#define VID_VSYNC_3DFORMAT_FRAME	(1 << 2)
+#define VID_VSYNC_3DFORMAT_PIXEL	(2 << 2)
+#define VID_VSYNC_3DMODE_OFF		0
+#define VID_VSYNC_3DMODE_PORTRAIT	1
+#define VID_VSYNC_3DMODE_LANDSCAPE	2
+
+#define MCTL_MAIN_STS			0x24
+#define MCTL_MAIN_STS_CTL		0x130
+#define MCTL_MAIN_STS_CLR		0x150
+#define MCTL_MAIN_STS_FLAG		0x170
+#define HS_SKEWCAL_DONE			BIT(11)
+#define IF_UNTERM_PKT_ERR(x)		BIT(8 + (x))
+#define LPRX_TIMEOUT_ERR		BIT(7)
+#define HSTX_TIMEOUT_ERR		BIT(6)
+#define DATA_LANE_RDY(l)		BIT(2 + (l))
+#define CLK_LANE_RDY			BIT(1)
+#define PLL_LOCKED			BIT(0)
+
+#define MCTL_DPHY_ERR			0x28
+#define MCTL_DPHY_ERR_CTL1		0x148
+#define MCTL_DPHY_ERR_CLR		0x168
+#define MCTL_DPHY_ERR_FLAG		0x188
+#define ERR_CONT_LP(x, l)		BIT(18 + ((x) * 4) + (l))
+#define ERR_CONTROL(l)			BIT(14 + (l))
+#define ERR_SYNESC(l)			BIT(10 + (l))
+#define ERR_ESC(l)			BIT(6 + (l))
+
+#define MCTL_DPHY_ERR_CTL2		0x14c
+#define ERR_CONT_LP_EDGE(x, l)		BIT(12 + ((x) * 4) + (l))
+#define ERR_CONTROL_EDGE(l)		BIT(8 + (l))
+#define ERR_SYN_ESC_EDGE(l)		BIT(4 + (l))
+#define ERR_ESC_EDGE(l)			BIT(0 + (l))
+
+#define MCTL_LANE_STS			0x2c
+#define PPI_C_TX_READY_HS		BIT(18)
+#define DPHY_PLL_LOCK			BIT(17)
+#define PPI_D_RX_ULPS_ESC(x)		(((x) & GENMASK(15, 12)) >> 12)
+#define LANE_STATE_START		0
+#define LANE_STATE_IDLE			1
+#define LANE_STATE_WRITE		2
+#define LANE_STATE_ULPM			3
+#define LANE_STATE_READ			4
+#define DATA_LANE_STATE(l, val)		\
+	(((val) >> (2 + 2 * (l) + ((l) ? 1 : 0))) & GENMASK((l) ? 1 : 2, 0))
+#define CLK_LANE_STATE_HS		2
+#define CLK_LANE_STATE(val)		((val) & GENMASK(1, 0))
+
+#define DSC_MODE_CTL			0x30
+#define DSC_MODE_EN			BIT(0)
+
+#define DSC_CMD_SEND			0x34
+#define DSC_SEND_PPS			BIT(0)
+#define DSC_EXECUTE_QUEUE		BIT(1)
+
+#define DSC_PPS_WRDAT			0x38
+
+#define DSC_MODE_STS			0x3c
+#define DSC_PPS_DONE			BIT(1)
+#define DSC_EXEC_DONE			BIT(2)
+
+#define CMD_MODE_CTL			0x70
+#define IF_LP_EN(x)			BIT(9 + (x))
+#define IF_VCHAN_ID(x, c)		((c) << ((x) * 2))
+
+#define CMD_MODE_CTL2			0x74
+#define TE_TIMEOUT(x)			((x) << 11)
+#define FILL_VALUE(x)			((x) << 3)
+#define ARB_IF_WITH_HIGHEST_PRIORITY(x)	((x) << 1)
+#define ARB_ROUND_ROBIN_MODE		BIT(0)
+
+#define CMD_MODE_STS			0x78
+#define CMD_MODE_STS_CTL		0x134
+#define CMD_MODE_STS_CLR		0x154
+#define CMD_MODE_STS_FLAG		0x174
+#define ERR_IF_UNDERRUN(x)		BIT(4 + (x))
+#define ERR_UNWANTED_READ		BIT(3)
+#define ERR_TE_MISS			BIT(2)
+#define ERR_NO_TE			BIT(1)
+#define CSM_RUNNING			BIT(0)
+
+#define DIRECT_CMD_SEND			0x80
+
+#define DIRECT_CMD_MAIN_SETTINGS	0x84
+#define TRIGGER_VAL(x)			((x) << 25)
+#define CMD_LP_EN			BIT(24)
+#define CMD_SIZE(x)			((x) << 16)
+#define CMD_VCHAN_ID(x)			((x) << 14)
+#define CMD_DATATYPE(x)			((x) << 8)
+#define CMD_LONG			BIT(3)
+#define WRITE_CMD			0
+#define READ_CMD			1
+#define TE_REQ				4
+#define TRIGGER_REQ			5
+#define BTA_REQ				6
+
+#define DIRECT_CMD_STS			0x88
+#define DIRECT_CMD_STS_CTL		0x138
+#define DIRECT_CMD_STS_CLR		0x158
+#define DIRECT_CMD_STS_FLAG		0x178
+#define RCVD_ACK_VAL(val)		((val) >> 16)
+#define RCVD_TRIGGER_VAL(val)		(((val) & GENMASK(14, 11)) >> 11)
+#define READ_COMPLETED_WITH_ERR		BIT(10)
+#define BTA_FINISHED			BIT(9)
+#define BTA_COMPLETED			BIT(8)
+#define TE_RCVD				BIT(7)
+#define TRIGGER_RCVD			BIT(6)
+#define ACK_WITH_ERR_RCVD		BIT(5)
+#define ACK_RCVD			BIT(4)
+#define READ_COMPLETED			BIT(3)
+#define TRIGGER_COMPLETED		BIT(2)
+#define WRITE_COMPLETED			BIT(1)
+#define SENDING_CMD			BIT(0)
+
+#define DIRECT_CMD_STOP_READ		0x8c
+
+#define DIRECT_CMD_WRDATA		0x90
+
+#define DIRECT_CMD_FIFO_RST		0x94
+
+#define DIRECT_CMD_RDDATA		0xa0
+
+#define DIRECT_CMD_RD_PROPS		0xa4
+#define RD_DCS				BIT(18)
+#define RD_VCHAN_ID(val)		(((val) >> 16) & GENMASK(1, 0))
+#define RD_SIZE(val)			((val) & GENMASK(15, 0))
+
+#define DIRECT_CMD_RD_STS		0xa8
+#define DIRECT_CMD_RD_STS_CTL		0x13c
+#define DIRECT_CMD_RD_STS_CLR		0x15c
+#define DIRECT_CMD_RD_STS_FLAG		0x17c
+#define ERR_EOT_WITH_ERR		BIT(8)
+#define ERR_MISSING_EOT			BIT(7)
+#define ERR_WRONG_LENGTH		BIT(6)
+#define ERR_OVERSIZE			BIT(5)
+#define ERR_RECEIVE			BIT(4)
+#define ERR_UNDECODABLE			BIT(3)
+#define ERR_CHECKSUM			BIT(2)
+#define ERR_UNCORRECTABLE		BIT(1)
+#define ERR_FIXED			BIT(0)
+
+#define VID_MAIN_CTL			0xb0
+#define VID_IGNORE_MISS_VSYNC		BIT(31)
+#define VID_FIELD_SW			BIT(28)
+#define VID_INTERLACED_EN		BIT(27)
+#define RECOVERY_MODE(x)		((x) << 25)
+#define RECOVERY_MODE_NEXT_HSYNC	0
+#define RECOVERY_MODE_NEXT_STOP_POINT	2
+#define RECOVERY_MODE_NEXT_VSYNC	3
+#define REG_BLKEOL_MODE(x)		((x) << 23)
+#define REG_BLKLINE_MODE(x)		((x) << 21)
+#define REG_BLK_MODE_NULL_PKT		0
+#define REG_BLK_MODE_BLANKING_PKT	1
+#define REG_BLK_MODE_LP			2
+#define SYNC_PULSE_HORIZONTAL		BIT(20)
+#define SYNC_PULSE_ACTIVE		BIT(19)
+#define BURST_MODE			BIT(18)
+#define VID_PIXEL_MODE_MASK		GENMASK(17, 14)
+#define VID_PIXEL_MODE_RGB565		(0 << 14)
+#define VID_PIXEL_MODE_RGB666_PACKED	(1 << 14)
+#define VID_PIXEL_MODE_RGB666		(2 << 14)
+#define VID_PIXEL_MODE_RGB888		(3 << 14)
+#define VID_PIXEL_MODE_RGB101010	(4 << 14)
+#define VID_PIXEL_MODE_RGB121212	(5 << 14)
+#define VID_PIXEL_MODE_YUV420		(8 << 14)
+#define VID_PIXEL_MODE_YUV422_PACKED	(9 << 14)
+#define VID_PIXEL_MODE_YUV422		(10 << 14)
+#define VID_PIXEL_MODE_YUV422_24B	(11 << 14)
+#define VID_PIXEL_MODE_DSC_COMP		(12 << 14)
+#define VID_DATATYPE(x)			((x) << 8)
+#define VID_VIRTCHAN_ID(iface, x)	((x) << (4 + (iface) * 2))
+#define STOP_MODE(x)			((x) << 2)
+#define START_MODE(x)			(x)
+
+#define VID_VSIZE1			0xb4
+#define VFP_LEN(x)			((x) << 12)
+#define VBP_LEN(x)			((x) << 6)
+#define VSA_LEN(x)			(x)
+
+#define VID_VSIZE2			0xb8
+#define VACT_LEN(x)			(x)
+
+#define VID_HSIZE1			0xc0
+#define HBP_LEN(x)			((x) << 16)
+#define HSA_LEN(x)			(x)
+
+#define VID_HSIZE2			0xc4
+#define HFP_LEN(x)			((x) << 16)
+#define HACT_LEN(x)			(x)
+
+#define VID_BLKSIZE1			0xcc
+#define BLK_EOL_PKT_LEN(x)		((x) << 15)
+#define BLK_LINE_EVENT_PKT_LEN(x)	(x)
+
+#define VID_BLKSIZE2			0xd0
+#define BLK_LINE_PULSE_PKT_LEN(x)	(x)
+
+#define VID_PKT_TIME			0xd8
+#define BLK_EOL_DURATION(x)		(x)
+
+#define VID_DPHY_TIME			0xdc
+#define REG_WAKEUP_TIME(x)		((x) << 17)
+#define REG_LINE_DURATION(x)		(x)
+
+#define VID_ERR_COLOR1			0xe0
+#define COL_GREEN(x)			((x) << 12)
+#define COL_RED(x)			(x)
+
+#define VID_ERR_COLOR2			0xe4
+#define PAD_VAL(x)			((x) << 12)
+#define COL_BLUE(x)			(x)
+
+#define VID_VPOS			0xe8
+#define LINE_VAL(val)			(((val) & GENMASK(14, 2)) >> 2)
+#define LINE_POS(val)			((val) & GENMASK(1, 0))
+
+#define VID_HPOS			0xec
+#define HORIZ_VAL(val)			(((val) & GENMASK(17, 3)) >> 3)
+#define HORIZ_POS(val)			((val) & GENMASK(2, 0))
+
+#define VID_MODE_STS			0xf0
+#define VID_MODE_STS_CTL		0x140
+#define VID_MODE_STS_CLR		0x160
+#define VID_MODE_STS_FLAG		0x180
+#define VSG_RECOVERY			BIT(10)
+#define ERR_VRS_WRONG_LEN		BIT(9)
+#define ERR_LONG_READ			BIT(8)
+#define ERR_LINE_WRITE			BIT(7)
+#define ERR_BURST_WRITE			BIT(6)
+#define ERR_SMALL_HEIGHT		BIT(5)
+#define ERR_SMALL_LEN			BIT(4)
+#define ERR_MISSING_VSYNC		BIT(3)
+#define ERR_MISSING_HSYNC		BIT(2)
+#define ERR_MISSING_DATA		BIT(1)
+#define VSG_RUNNING			BIT(0)
+
+#define VID_VCA_SETTING1		0xf4
+#define BURST_LP			BIT(16)
+#define MAX_BURST_LIMIT(x)		(x)
+
+#define VID_VCA_SETTING2		0xf8
+#define MAX_LINE_LIMIT(x)		((x) << 16)
+#define EXACT_BURST_LIMIT(x)		(x)
+
+#define TVG_CTL				0xfc
+#define TVG_STRIPE_SIZE(x)		((x) << 5)
+#define TVG_MODE_MASK			GENMASK(4, 3)
+#define TVG_MODE_SINGLE_COLOR		(0 << 3)
+#define TVG_MODE_VSTRIPES		(2 << 3)
+#define TVG_MODE_HSTRIPES		(3 << 3)
+#define TVG_STOPMODE_MASK		GENMASK(2, 1)
+#define TVG_STOPMODE_EOF		(0 << 1)
+#define TVG_STOPMODE_EOL		(1 << 1)
+#define TVG_STOPMODE_NOW		(2 << 1)
+#define TVG_RUN				BIT(0)
+
+#define TVG_IMG_SIZE			0x100
+#define TVG_NBLINES(x)			((x) << 16)
+#define TVG_LINE_SIZE(x)		(x)
+
+#define TVG_COLOR1			0x104
+#define TVG_COL1_GREEN(x)		((x) << 12)
+#define TVG_COL1_RED(x)			(x)
+
+#define TVG_COLOR1_BIS			0x108
+#define TVG_COL1_BLUE(x)		(x)
+
+#define TVG_COLOR2			0x10c
+#define TVG_COL2_GREEN(x)		((x) << 12)
+#define TVG_COL2_RED(x)			(x)
+
+#define TVG_COLOR2_BIS			0x110
+#define TVG_COL2_BLUE(x)		(x)
+
+#define TVG_STS				0x114
+#define TVG_STS_CTL			0x144
+#define TVG_STS_CLR			0x164
+#define TVG_STS_FLAG			0x184
+#define TVG_STS_RUNNING			BIT(0)
+
+#define STS_CTL_EDGE(e)			((e) << 16)
+
+#define DPHY_LANES_MAP			0x198
+#define DAT_REMAP_CFG(b, l)		((l) << ((b) * 8))
+
+#define DPI_IRQ_EN			0x1a0
+#define DPI_IRQ_CLR			0x1a4
+#define DPI_IRQ_STS			0x1a8
+#define PIXEL_BUF_OVERFLOW		BIT(0)
+
+#define DPI_CFG				0x1ac
+#define DPI_CFG_FIFO_DEPTH(x)		((x) >> 16)
+#define DPI_CFG_FIFO_LEVEL(x)		((x) & GENMASK(15, 0))
+
+#define TEST_GENERIC			0x1f0
+#define TEST_STATUS(x)			((x) >> 16)
+#define TEST_CTRL(x)			(x)
+
+#define ID_REG				0x1fc
+#define REV_VENDOR_ID(x)		(((x) & GENMASK(31, 20)) >> 20)
+#define REV_PRODUCT_ID(x)		(((x) & GENMASK(19, 12)) >> 12)
+#define REV_HW(x)			(((x) & GENMASK(11, 8)) >> 8)
+#define REV_MAJOR(x)			(((x) & GENMASK(7, 4)) >> 4)
+#define REV_MINOR(x)			((x) & GENMASK(3, 0))
+
+#define DSI_OUTPUT_PORT			0
+#define DSI_INPUT_PORT(inputid)		(1 + (inputid))
+
+#define DSI_HBP_FRAME_OVERHEAD		12
+#define DSI_HSA_FRAME_OVERHEAD		14
+#define DSI_HFP_FRAME_OVERHEAD		6
+#define DSI_HSS_VSS_VSE_FRAME_OVERHEAD	4
+#define DSI_BLANKING_FRAME_OVERHEAD	6
+#define DSI_NULL_FRAME_OVERHEAD		6
+#define DSI_EOT_PKT_SIZE		4
+
+#define REG_WAKEUP_TIME_NS		800
+#define DPHY_PLL_RATE_HZ		108000000
+
+/* DPHY registers */
+#define DPHY_PMA_CMN(reg)		(reg)
+#define DPHY_PMA_LCLK(reg)		(0x100 + (reg))
+#define DPHY_PMA_LDATA(lane, reg)	(0x200 + ((lane) * 0x100) + (reg))
+#define DPHY_PMA_RCLK(reg)		(0x600 + (reg))
+#define DPHY_PMA_RDATA(lane, reg)	(0x700 + ((lane) * 0x100) + (reg))
+#define DPHY_PCS(reg)			(0xb00 + (reg))
+
+#define DPHY_CMN_SSM			DPHY_PMA_CMN(0x20)
+#define DPHY_CMN_SSM_EN			BIT(0)
+#define DPHY_CMN_TX_MODE_EN		BIT(9)
+
+#define DPHY_CMN_PWM			DPHY_PMA_CMN(0x40)
+#define DPHY_CMN_PWM_DIV(x)		((x) << 20)
+#define DPHY_CMN_PWM_LOW(x)		((x) << 10)
+#define DPHY_CMN_PWM_HIGH(x)		(x)
+
+#define DPHY_CMN_FBDIV			DPHY_PMA_CMN(0x4c)
+#define DPHY_CMN_FBDIV_VAL(low, high)	(((high) << 11) | ((low) << 22))
+#define DPHY_CMN_FBDIV_FROM_REG		(BIT(10) | BIT(21))
+
+#define DPHY_CMN_OPIPDIV		DPHY_PMA_CMN(0x50)
+#define DPHY_CMN_IPDIV_FROM_REG		BIT(0)
+#define DPHY_CMN_IPDIV(x)		((x) << 1)
+#define DPHY_CMN_OPDIV_FROM_REG		BIT(6)
+#define DPHY_CMN_OPDIV(x)		((x) << 7)
+
+#define DPHY_PSM_CFG			DPHY_PCS(0x4)
+#define DPHY_PSM_CFG_FROM_REG		BIT(0)
+#define DPHY_PSM_CLK_DIV(x)		((x) << 1)
+
+struct cdns_dsi_output {
+	struct mipi_dsi_device *dev;
+	struct drm_panel *panel;
+	struct drm_bridge *bridge;
+};
+
+enum cdns_dsi_input_id {
+	CDNS_SDI_INPUT,
+	CDNS_DPI_INPUT,
+	CDNS_DSC_INPUT,
+};
+
+struct cdns_dphy_cfg {
+	u8 pll_ipdiv;
+	u8 pll_opdiv;
+	u16 pll_fbdiv;
+	unsigned long lane_bps;
+	unsigned int nlanes;
+};
+
+struct cdns_dsi_cfg {
+	unsigned int hfp;
+	unsigned int hsa;
+	unsigned int hbp;
+	unsigned int hact;
+	unsigned int htotal;
+};
+
+struct cdns_dphy;
+
+enum cdns_dphy_clk_lane_cfg {
+	DPHY_CLK_CFG_LEFT_DRIVES_ALL = 0,
+	DPHY_CLK_CFG_LEFT_DRIVES_RIGHT = 1,
+	DPHY_CLK_CFG_LEFT_DRIVES_LEFT = 2,
+	DPHY_CLK_CFG_RIGHT_DRIVES_ALL = 3,
+};
+
+struct cdns_dphy_ops {
+	int (*probe)(struct cdns_dphy *dphy);
+	void (*remove)(struct cdns_dphy *dphy);
+	void (*set_psm_div)(struct cdns_dphy *dphy, u8 div);
+	void (*set_clk_lane_cfg)(struct cdns_dphy *dphy,
+				 enum cdns_dphy_clk_lane_cfg cfg);
+	void (*set_pll_cfg)(struct cdns_dphy *dphy,
+			    const struct cdns_dphy_cfg *cfg);
+	unsigned long (*get_wakeup_time_ns)(struct cdns_dphy *dphy);
+};
+
+struct cdns_dphy {
+	struct cdns_dphy_cfg cfg;
+	void __iomem *regs;
+	struct clk *psm_clk;
+	struct clk *pll_ref_clk;
+	const struct cdns_dphy_ops *ops;
+};
+
+struct cdns_dsi_input {
+	enum cdns_dsi_input_id id;
+	struct drm_bridge bridge;
+};
+
+struct cdns_dsi {
+	struct mipi_dsi_host base;
+	void __iomem *regs;
+	struct cdns_dsi_input input;
+	struct cdns_dsi_output output;
+	unsigned int direct_cmd_fifo_depth;
+	unsigned int rx_fifo_depth;
+	struct completion direct_cmd_comp;
+	struct clk *dsi_p_clk;
+	struct reset_control *dsi_p_rst;
+	struct clk *dsi_sys_clk;
+	bool link_initialized;
+	struct cdns_dphy *dphy;
+};
+
+static inline struct cdns_dsi *input_to_dsi(struct cdns_dsi_input *input)
+{
+	return container_of(input, struct cdns_dsi, input);
+}
+
+static inline struct cdns_dsi *to_cdns_dsi(struct mipi_dsi_host *host)
+{
+	return container_of(host, struct cdns_dsi, base);
+}
+
+static inline struct cdns_dsi_input *
+bridge_to_cdns_dsi_input(struct drm_bridge *bridge)
+{
+	return container_of(bridge, struct cdns_dsi_input, bridge);
+}
+
+static int cdns_dsi_get_dphy_pll_cfg(struct cdns_dphy *dphy,
+				     struct cdns_dphy_cfg *cfg,
+				     unsigned int dpi_htotal,
+				     unsigned int dpi_bpp,
+				     unsigned int dpi_hz,
+				     unsigned int dsi_htotal,
+				     unsigned int dsi_nlanes,
+				     unsigned int *dsi_hfp_ext)
+{
+	u64 dlane_bps, dlane_bps_max, fbdiv, fbdiv_max, adj_dsi_htotal;
+	unsigned long pll_ref_hz = clk_get_rate(dphy->pll_ref_clk);
+
+	memset(cfg, 0, sizeof(*cfg));
+
+	cfg->nlanes = dsi_nlanes;
+
+	if (pll_ref_hz < 9600000 || pll_ref_hz >= 150000000)
+		return -EINVAL;
+	else if (pll_ref_hz < 19200000)
+		cfg->pll_ipdiv = 1;
+	else if (pll_ref_hz < 38400000)
+		cfg->pll_ipdiv = 2;
+	else if (pll_ref_hz < 76800000)
+		cfg->pll_ipdiv = 4;
+	else
+		cfg->pll_ipdiv = 8;
+
+	/*
+	 * Make sure DSI htotal is aligned on a lane boundary when calculating
+	 * the expected data rate. This is done by extending HFP in case of
+	 * misalignment.
+	 */
+	adj_dsi_htotal = dsi_htotal;
+	if (dsi_htotal % dsi_nlanes)
+		adj_dsi_htotal += dsi_nlanes - (dsi_htotal % dsi_nlanes);
+
+	dlane_bps = (u64)dpi_hz * adj_dsi_htotal;
+
+	/* data rate in bytes/sec is not an integer, refuse the mode. */
+	if (do_div(dlane_bps, dsi_nlanes * dpi_htotal))
+		return -EINVAL;
+
+	/* data rate was in bytes/sec, convert to bits/sec. */
+	dlane_bps *= 8;
+
+	if (dlane_bps > 2500000000UL || dlane_bps < 160000000UL)
+		return -EINVAL;
+	else if (dlane_bps >= 1250000000)
+		cfg->pll_opdiv = 1;
+	else if (dlane_bps >= 630000000)
+		cfg->pll_opdiv = 2;
+	else if (dlane_bps >= 320000000)
+		cfg->pll_opdiv = 4;
+	else if (dlane_bps >= 160000000)
+		cfg->pll_opdiv = 8;
+
+	/*
+	 * Allow a deviation of 0.2% on the per-lane data rate to try to
+	 * recover a potential mismatch between DPI and PPI clks.
+	 */
+	dlane_bps_max = dlane_bps + DIV_ROUND_DOWN_ULL(dlane_bps, 500);
+	fbdiv_max = DIV_ROUND_DOWN_ULL(dlane_bps_max * 2 *
+				       cfg->pll_opdiv * cfg->pll_ipdiv,
+				       pll_ref_hz);
+	fbdiv = DIV_ROUND_UP_ULL(dlane_bps * 2 * cfg->pll_opdiv *
+				 cfg->pll_ipdiv,
+				 pll_ref_hz);
+
+	/*
+	 * Iterate over all acceptable fbdiv and try to find an adjusted DSI
+	 * htotal length providing an exact match.
+	 *
+	 * Note that we could do something even trickier by relying on the fact
+	 * that a new line is not necessarily aligned on a lane boundary, so,
+	 * by making adj_dsi_htotal non aligned on a dsi_lanes we can improve a
+	 * bit the precision. With this, the step would be
+	 *
+	 *	pll_ref_hz / (2 * opdiv * ipdiv * nlanes)
+	 *
+	 * instead of
+	 *
+	 *	pll_ref_hz / (2 * opdiv * ipdiv)
+	 *
+	 * The drawback of this approach is that we would need to make sure the
+	 * number or lines is a multiple of the realignment periodicity which is
+	 * a function of the number of lanes and the original misalignment. For
+	 * example, for NLANES = 4 and HTOTAL % NLANES = 3, it takes 4 lines
+	 * to realign on a lane:
+	 * LINE 0: expected number of bytes, starts emitting first byte of
+	 *	   LINE 1 on LANE 3
+	 * LINE 1: expected number of bytes, starts emitting first 2 bytes of
+	 *	   LINE 2 on LANES 2 and 3
+	 * LINE 2: expected number of bytes, starts emitting first 3 bytes of
+	 *	   of LINE 3 on LANES 1, 2 and 3
+	 * LINE 3: one byte less, now things are realigned on LANE 0 for LINE 4
+	 *
+	 * I figured this extra complexity was not worth the benefit, but if
+	 * someone really has unfixable mismatch, that would be something to
+	 * investigate.
+	 */
+	for (; fbdiv <= fbdiv_max; fbdiv++) {
+		u32 rem;
+
+		adj_dsi_htotal = (u64)fbdiv * pll_ref_hz * dsi_nlanes *
+				 dpi_htotal;
+
+		/*
+		 * Do the division in 2 steps to avoid an overflow on the
+		 * divider.
+		 */
+		rem = do_div(adj_dsi_htotal, dpi_hz);
+		if (rem)
+			continue;
+
+		rem = do_div(adj_dsi_htotal,
+			     cfg->pll_opdiv * cfg->pll_ipdiv * 2 * 8);
+		if (rem)
+			continue;
+
+		cfg->pll_fbdiv = fbdiv;
+		*dsi_hfp_ext = adj_dsi_htotal - dsi_htotal;
+		break;
+	}
+
+	/* No match, let's just reject the display mode. */
+	if (!cfg->pll_fbdiv)
+		return -EINVAL;
+
+	dlane_bps = DIV_ROUND_DOWN_ULL((u64)dpi_hz * adj_dsi_htotal * 8,
+				       dsi_nlanes * dpi_htotal);
+	cfg->lane_bps = dlane_bps;
+
+	return 0;
+}
+
+static int cdns_dphy_setup_psm(struct cdns_dphy *dphy)
+{
+	unsigned long psm_clk_hz = clk_get_rate(dphy->psm_clk);
+	unsigned long psm_div;
+
+	if (!psm_clk_hz || psm_clk_hz > 100000000)
+		return -EINVAL;
+
+	psm_div = DIV_ROUND_CLOSEST(psm_clk_hz, 1000000);
+	if (dphy->ops->set_psm_div)
+		dphy->ops->set_psm_div(dphy, psm_div);
+
+	return 0;
+}
+
+static void cdns_dphy_set_clk_lane_cfg(struct cdns_dphy *dphy,
+				       enum cdns_dphy_clk_lane_cfg cfg)
+{
+	if (dphy->ops->set_clk_lane_cfg)
+		dphy->ops->set_clk_lane_cfg(dphy, cfg);
+}
+
+static void cdns_dphy_set_pll_cfg(struct cdns_dphy *dphy,
+				  const struct cdns_dphy_cfg *cfg)
+{
+	if (dphy->ops->set_pll_cfg)
+		dphy->ops->set_pll_cfg(dphy, cfg);
+}
+
+static unsigned long cdns_dphy_get_wakeup_time_ns(struct cdns_dphy *dphy)
+{
+	return dphy->ops->get_wakeup_time_ns(dphy);
+}
+
+static unsigned int dpi_to_dsi_timing(unsigned int dpi_timing,
+				      unsigned int dpi_bpp,
+				      unsigned int dsi_pkt_overhead)
+{
+	unsigned int dsi_timing = DIV_ROUND_UP(dpi_timing * dpi_bpp, 8);
+
+	if (dsi_timing < dsi_pkt_overhead)
+		dsi_timing = 0;
+	else
+		dsi_timing -= dsi_pkt_overhead;
+
+	return dsi_timing;
+}
+
+static int cdns_dsi_mode2cfg(struct cdns_dsi *dsi,
+			     const struct drm_display_mode *mode,
+			     struct cdns_dsi_cfg *dsi_cfg,
+			     struct cdns_dphy_cfg *dphy_cfg,
+			     bool mode_valid_check)
+{
+	unsigned long dsi_htotal = 0, dsi_hss_hsa_hse_hbp = 0;
+	struct cdns_dsi_output *output = &dsi->output;
+	unsigned int dsi_hfp_ext = 0, dpi_hfp, tmp;
+	bool sync_pulse = false;
+	int bpp, nlanes, ret;
+
+	memset(dsi_cfg, 0, sizeof(*dsi_cfg));
+
+	if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE)
+		sync_pulse = true;
+
+	bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format);
+	nlanes = output->dev->lanes;
+
+	if (mode_valid_check)
+		tmp = mode->htotal -
+		      (sync_pulse ? mode->hsync_end : mode->hsync_start);
+	else
+		tmp = mode->crtc_htotal -
+		      (sync_pulse ?
+		       mode->crtc_hsync_end : mode->crtc_hsync_start);
+
+	dsi_cfg->hbp = dpi_to_dsi_timing(tmp, bpp, DSI_HBP_FRAME_OVERHEAD);
+	dsi_htotal += dsi_cfg->hbp + DSI_HBP_FRAME_OVERHEAD;
+	dsi_hss_hsa_hse_hbp += dsi_cfg->hbp + DSI_HBP_FRAME_OVERHEAD;
+
+	if (sync_pulse) {
+		if (mode_valid_check)
+			tmp = mode->hsync_end - mode->hsync_start;
+		else
+			tmp = mode->crtc_hsync_end - mode->crtc_hsync_start;
+
+		dsi_cfg->hsa = dpi_to_dsi_timing(tmp, bpp,
+						 DSI_HSA_FRAME_OVERHEAD);
+		dsi_htotal += dsi_cfg->hsa + DSI_HSA_FRAME_OVERHEAD;
+		dsi_hss_hsa_hse_hbp += dsi_cfg->hsa + DSI_HSA_FRAME_OVERHEAD;
+	}
+
+	dsi_cfg->hact = dpi_to_dsi_timing(mode_valid_check ?
+					  mode->hdisplay : mode->crtc_hdisplay,
+					  bpp, 0);
+	dsi_htotal += dsi_cfg->hact;
+
+	if (mode_valid_check)
+		dpi_hfp = mode->hsync_start - mode->hdisplay;
+	else
+		dpi_hfp = mode->crtc_hsync_start - mode->crtc_hdisplay;
+
+	dsi_cfg->hfp = dpi_to_dsi_timing(dpi_hfp, bpp, DSI_HFP_FRAME_OVERHEAD);
+	dsi_htotal += dsi_cfg->hfp + DSI_HFP_FRAME_OVERHEAD;
+
+	if (mode_valid_check)
+		ret = cdns_dsi_get_dphy_pll_cfg(dsi->dphy, dphy_cfg,
+						mode->htotal, bpp,
+						mode->clock * 1000,
+						dsi_htotal, nlanes,
+						&dsi_hfp_ext);
+	else
+		ret = cdns_dsi_get_dphy_pll_cfg(dsi->dphy, dphy_cfg,
+						mode->crtc_htotal, bpp,
+						mode->crtc_clock * 1000,
+						dsi_htotal, nlanes,
+						&dsi_hfp_ext);
+
+	if (ret)
+		return ret;
+
+	dsi_cfg->hfp += dsi_hfp_ext;
+	dsi_htotal += dsi_hfp_ext;
+	dsi_cfg->htotal = dsi_htotal;
+
+	/*
+	 * Make sure DPI(HFP) > DSI(HSS+HSA+HSE+HBP) to guarantee that the FIFO
+	 * is empty before we start a receiving a new line on the DPI
+	 * interface.
+	 */
+	if ((u64)dphy_cfg->lane_bps * dpi_hfp * nlanes <
+	    (u64)dsi_hss_hsa_hse_hbp *
+	    (mode_valid_check ? mode->clock : mode->crtc_clock) * 1000)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int cdns_dsi_bridge_attach(struct drm_bridge *bridge)
+{
+	struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge);
+	struct cdns_dsi *dsi = input_to_dsi(input);
+	struct cdns_dsi_output *output = &dsi->output;
+
+	if (!drm_core_check_feature(bridge->dev, DRIVER_ATOMIC)) {
+		dev_err(dsi->base.dev,
+			"cdns-dsi driver is only compatible with DRM devices supporting atomic updates");
+		return -ENOTSUPP;
+	}
+
+	return drm_bridge_attach(bridge->encoder, output->bridge, bridge);
+}
+
+static enum drm_mode_status
+cdns_dsi_bridge_mode_valid(struct drm_bridge *bridge,
+			   const struct drm_display_mode *mode)
+{
+	struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge);
+	struct cdns_dsi *dsi = input_to_dsi(input);
+	struct cdns_dsi_output *output = &dsi->output;
+	struct cdns_dphy_cfg dphy_cfg;
+	struct cdns_dsi_cfg dsi_cfg;
+	int bpp, nlanes, ret;
+
+	/*
+	 * VFP_DSI should be less than VFP_DPI and VFP_DSI should be at
+	 * least 1.
+	 */
+	if (mode->vtotal - mode->vsync_end < 2)
+		return MODE_V_ILLEGAL;
+
+	/* VSA_DSI = VSA_DPI and must be at least 2. */
+	if (mode->vsync_end - mode->vsync_start < 2)
+		return MODE_V_ILLEGAL;
+
+	/* HACT must be 32-bits aligned. */
+	bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format);
+	if ((mode->hdisplay * bpp) % 32)
+		return MODE_H_ILLEGAL;
+
+	nlanes = output->dev->lanes;
+
+	ret = cdns_dsi_mode2cfg(dsi, mode, &dsi_cfg, &dphy_cfg, true);
+	if (ret)
+		return MODE_CLOCK_RANGE;
+
+	return MODE_OK;
+}
+
+static void cdns_dsi_bridge_disable(struct drm_bridge *bridge)
+{
+	struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge);
+	struct cdns_dsi *dsi = input_to_dsi(input);
+	u32 val;
+
+	val = readl(dsi->regs + MCTL_MAIN_DATA_CTL);
+	val &= ~(IF_VID_SELECT_MASK | IF_VID_MODE | VID_EN | HOST_EOT_GEN |
+		 DISP_EOT_GEN);
+	writel(val, dsi->regs + MCTL_MAIN_DATA_CTL);
+
+	val = readl(dsi->regs + MCTL_MAIN_EN) & ~IF_EN(input->id);
+	writel(val, dsi->regs + MCTL_MAIN_EN);
+	pm_runtime_put(dsi->base.dev);
+}
+
+static void cdns_dsi_hs_init(struct cdns_dsi *dsi,
+			     const struct cdns_dphy_cfg *dphy_cfg)
+{
+	u32 status;
+
+	/*
+	 * Power all internal DPHY blocks down and maintain their reset line
+	 * asserted before changing the DPHY config.
+	 */
+	writel(DPHY_CMN_PSO | DPHY_PLL_PSO | DPHY_ALL_D_PDN | DPHY_C_PDN |
+	       DPHY_CMN_PDN | DPHY_PLL_PDN,
+	       dsi->regs + MCTL_DPHY_CFG0);
+
+	/*
+	 * Configure the internal PSM clk divider so that the DPHY has a
+	 * 1MHz clk (or something close).
+	 */
+	WARN_ON_ONCE(cdns_dphy_setup_psm(dsi->dphy));
+
+	/*
+	 * Configure attach clk lanes to data lanes: the DPHY has 2 clk lanes
+	 * and 8 data lanes, each clk lane can be attache different set of
+	 * data lanes. The 2 groups are named 'left' and 'right', so here we
+	 * just say that we want the 'left' clk lane to drive the 'left' data
+	 * lanes.
+	 */
+	cdns_dphy_set_clk_lane_cfg(dsi->dphy, DPHY_CLK_CFG_LEFT_DRIVES_LEFT);
+
+	/*
+	 * Configure the DPHY PLL that will be used to generate the TX byte
+	 * clk.
+	 */
+	cdns_dphy_set_pll_cfg(dsi->dphy, dphy_cfg);
+
+	/* Start TX state machine. */
+	writel(DPHY_CMN_SSM_EN | DPHY_CMN_TX_MODE_EN,
+	       dsi->dphy->regs + DPHY_CMN_SSM);
+
+	/* Activate the PLL and wait until it's locked. */
+	writel(PLL_LOCKED, dsi->regs + MCTL_MAIN_STS_CLR);
+	writel(DPHY_CMN_PSO | DPHY_ALL_D_PDN | DPHY_C_PDN | DPHY_CMN_PDN,
+	       dsi->regs + MCTL_DPHY_CFG0);
+	WARN_ON_ONCE(readl_poll_timeout(dsi->regs + MCTL_MAIN_STS, status,
+					status & PLL_LOCKED, 100, 100));
+	/* De-assert data and clock reset lines. */
+	writel(DPHY_CMN_PSO | DPHY_ALL_D_PDN | DPHY_C_PDN | DPHY_CMN_PDN |
+	       DPHY_D_RSTB(dphy_cfg->nlanes) | DPHY_C_RSTB,
+	       dsi->regs + MCTL_DPHY_CFG0);
+}
+
+static void cdns_dsi_init_link(struct cdns_dsi *dsi)
+{
+	struct cdns_dsi_output *output = &dsi->output;
+	unsigned long sysclk_period, ulpout;
+	u32 val;
+	int i;
+
+	if (dsi->link_initialized)
+		return;
+
+	val = 0;
+	for (i = 1; i < output->dev->lanes; i++)
+		val |= DATA_LANE_EN(i);
+
+	if (!(output->dev->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS))
+		val |= CLK_CONTINUOUS;
+
+	writel(val, dsi->regs + MCTL_MAIN_PHY_CTL);
+
+	/* ULPOUT should be set to 1ms and is expressed in sysclk cycles. */
+	sysclk_period = NSEC_PER_SEC / clk_get_rate(dsi->dsi_sys_clk);
+	ulpout = DIV_ROUND_UP(NSEC_PER_MSEC, sysclk_period);
+	writel(CLK_LANE_ULPOUT_TIME(ulpout) | DATA_LANE_ULPOUT_TIME(ulpout),
+	       dsi->regs + MCTL_ULPOUT_TIME);
+
+	writel(LINK_EN, dsi->regs + MCTL_MAIN_DATA_CTL);
+
+	val = CLK_LANE_EN | PLL_START;
+	for (i = 0; i < output->dev->lanes; i++)
+		val |= DATA_LANE_START(i);
+
+	writel(val, dsi->regs + MCTL_MAIN_EN);
+
+	dsi->link_initialized = true;
+}
+
+static void cdns_dsi_bridge_enable(struct drm_bridge *bridge)
+{
+	struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge);
+	struct cdns_dsi *dsi = input_to_dsi(input);
+	struct cdns_dsi_output *output = &dsi->output;
+	struct drm_display_mode *mode;
+	struct cdns_dphy_cfg dphy_cfg;
+	unsigned long tx_byte_period;
+	struct cdns_dsi_cfg dsi_cfg;
+	u32 tmp, reg_wakeup, div;
+	int bpp, nlanes;
+
+	if (WARN_ON(pm_runtime_get_sync(dsi->base.dev) < 0))
+		return;
+
+	mode = &bridge->encoder->crtc->state->adjusted_mode;
+	bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format);
+	nlanes = output->dev->lanes;
+
+	WARN_ON_ONCE(cdns_dsi_mode2cfg(dsi, mode, &dsi_cfg, &dphy_cfg, false));
+
+	cdns_dsi_hs_init(dsi, &dphy_cfg);
+	cdns_dsi_init_link(dsi);
+
+	writel(HBP_LEN(dsi_cfg.hbp) | HSA_LEN(dsi_cfg.hsa),
+	       dsi->regs + VID_HSIZE1);
+	writel(HFP_LEN(dsi_cfg.hfp) | HACT_LEN(dsi_cfg.hact),
+	       dsi->regs + VID_HSIZE2);
+
+	writel(VBP_LEN(mode->crtc_vtotal - mode->crtc_vsync_end - 1) |
+	       VFP_LEN(mode->crtc_vsync_start - mode->crtc_vdisplay) |
+	       VSA_LEN(mode->crtc_vsync_end - mode->crtc_vsync_start + 1),
+	       dsi->regs + VID_VSIZE1);
+	writel(mode->crtc_vdisplay, dsi->regs + VID_VSIZE2);
+
+	tmp = dsi_cfg.htotal -
+	      (dsi_cfg.hsa + DSI_BLANKING_FRAME_OVERHEAD +
+	       DSI_HSA_FRAME_OVERHEAD);
+	writel(BLK_LINE_PULSE_PKT_LEN(tmp), dsi->regs + VID_BLKSIZE2);
+	if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE)
+		writel(MAX_LINE_LIMIT(tmp - DSI_NULL_FRAME_OVERHEAD),
+		       dsi->regs + VID_VCA_SETTING2);
+
+	tmp = dsi_cfg.htotal -
+	      (DSI_HSS_VSS_VSE_FRAME_OVERHEAD + DSI_BLANKING_FRAME_OVERHEAD);
+	writel(BLK_LINE_EVENT_PKT_LEN(tmp), dsi->regs + VID_BLKSIZE1);
+	if (!(output->dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE))
+		writel(MAX_LINE_LIMIT(tmp - DSI_NULL_FRAME_OVERHEAD),
+		       dsi->regs + VID_VCA_SETTING2);
+
+	tmp = DIV_ROUND_UP(dsi_cfg.htotal, nlanes) -
+	      DIV_ROUND_UP(dsi_cfg.hsa, nlanes);
+
+	if (!(output->dev->mode_flags & MIPI_DSI_MODE_EOT_PACKET))
+		tmp -= DIV_ROUND_UP(DSI_EOT_PKT_SIZE, nlanes);
+
+	tx_byte_period = DIV_ROUND_DOWN_ULL((u64)NSEC_PER_SEC * 8,
+					    dphy_cfg.lane_bps);
+	reg_wakeup = cdns_dphy_get_wakeup_time_ns(dsi->dphy) /
+		     tx_byte_period;
+	writel(REG_WAKEUP_TIME(reg_wakeup) | REG_LINE_DURATION(tmp),
+	       dsi->regs + VID_DPHY_TIME);
+
+	/*
+	 * HSTX and LPRX timeouts are both expressed in TX byte clk cycles and
+	 * both should be set to at least the time it takes to transmit a
+	 * frame.
+	 */
+	tmp = NSEC_PER_SEC / drm_mode_vrefresh(mode);
+	tmp /= tx_byte_period;
+
+	for (div = 0; div <= CLK_DIV_MAX; div++) {
+		if (tmp <= HSTX_TIMEOUT_MAX)
+			break;
+
+		tmp >>= 1;
+	}
+
+	if (tmp > HSTX_TIMEOUT_MAX)
+		tmp = HSTX_TIMEOUT_MAX;
+
+	writel(CLK_DIV(div) | HSTX_TIMEOUT(tmp),
+	       dsi->regs + MCTL_DPHY_TIMEOUT1);
+
+	writel(LPRX_TIMEOUT(tmp), dsi->regs + MCTL_DPHY_TIMEOUT2);
+
+	if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO) {
+		switch (output->dev->format) {
+		case MIPI_DSI_FMT_RGB888:
+			tmp = VID_PIXEL_MODE_RGB888 |
+			      VID_DATATYPE(MIPI_DSI_PACKED_PIXEL_STREAM_24);
+			break;
+
+		case MIPI_DSI_FMT_RGB666:
+			tmp = VID_PIXEL_MODE_RGB666 |
+			      VID_DATATYPE(MIPI_DSI_PIXEL_STREAM_3BYTE_18);
+			break;
+
+		case MIPI_DSI_FMT_RGB666_PACKED:
+			tmp = VID_PIXEL_MODE_RGB666_PACKED |
+			      VID_DATATYPE(MIPI_DSI_PACKED_PIXEL_STREAM_18);
+			break;
+
+		case MIPI_DSI_FMT_RGB565:
+			tmp = VID_PIXEL_MODE_RGB565 |
+			      VID_DATATYPE(MIPI_DSI_PACKED_PIXEL_STREAM_16);
+			break;
+
+		default:
+			dev_err(dsi->base.dev, "Unsupported DSI format\n");
+			return;
+		}
+
+		if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE)
+			tmp |= SYNC_PULSE_ACTIVE | SYNC_PULSE_HORIZONTAL;
+
+		tmp |= REG_BLKLINE_MODE(REG_BLK_MODE_BLANKING_PKT) |
+		       REG_BLKEOL_MODE(REG_BLK_MODE_BLANKING_PKT) |
+		       RECOVERY_MODE(RECOVERY_MODE_NEXT_HSYNC) |
+		       VID_IGNORE_MISS_VSYNC;
+
+		writel(tmp, dsi->regs + VID_MAIN_CTL);
+	}
+
+	tmp = readl(dsi->regs + MCTL_MAIN_DATA_CTL);
+	tmp &= ~(IF_VID_SELECT_MASK | HOST_EOT_GEN | IF_VID_MODE);
+
+	if (!(output->dev->mode_flags & MIPI_DSI_MODE_EOT_PACKET))
+		tmp |= HOST_EOT_GEN;
+
+	if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO)
+		tmp |= IF_VID_MODE | IF_VID_SELECT(input->id) | VID_EN;
+
+	writel(tmp, dsi->regs + MCTL_MAIN_DATA_CTL);
+
+	tmp = readl(dsi->regs + MCTL_MAIN_EN) | IF_EN(input->id);
+	writel(tmp, dsi->regs + MCTL_MAIN_EN);
+}
+
+static const struct drm_bridge_funcs cdns_dsi_bridge_funcs = {
+	.attach = cdns_dsi_bridge_attach,
+	.mode_valid = cdns_dsi_bridge_mode_valid,
+	.disable = cdns_dsi_bridge_disable,
+	.enable = cdns_dsi_bridge_enable,
+};
+
+static int cdns_dsi_attach(struct mipi_dsi_host *host,
+			   struct mipi_dsi_device *dev)
+{
+	struct cdns_dsi *dsi = to_cdns_dsi(host);
+	struct cdns_dsi_output *output = &dsi->output;
+	struct cdns_dsi_input *input = &dsi->input;
+	struct drm_bridge *bridge;
+	struct drm_panel *panel;
+	struct device_node *np;
+	int ret;
+
+	/*
+	 * We currently do not support connecting several DSI devices to the
+	 * same host. In order to support that we'd need the DRM bridge
+	 * framework to allow dynamic reconfiguration of the bridge chain.
+	 */
+	if (output->dev)
+		return -EBUSY;
+
+	/* We do not support burst mode yet. */
+	if (dev->mode_flags & MIPI_DSI_MODE_VIDEO_BURST)
+		return -ENOTSUPP;
+
+	/*
+	 * The host <-> device link might be described using an OF-graph
+	 * representation, in this case we extract the device of_node from
+	 * this representation, otherwise we use dsidev->dev.of_node which
+	 * should have been filled by the core.
+	 */
+	np = of_graph_get_remote_node(dsi->base.dev->of_node, DSI_OUTPUT_PORT,
+				      dev->channel);
+	if (!np)
+		np = of_node_get(dev->dev.of_node);
+
+	panel = of_drm_find_panel(np);
+	if (panel) {
+		bridge = drm_panel_bridge_add(panel, DRM_MODE_CONNECTOR_DSI);
+	} else {
+		bridge = of_drm_find_bridge(dev->dev.of_node);
+		if (!bridge)
+			bridge = ERR_PTR(-EINVAL);
+	}
+
+	of_node_put(np);
+
+	if (IS_ERR(bridge)) {
+		ret = PTR_ERR(bridge);
+		dev_err(host->dev, "failed to add DSI device %s (err = %d)",
+			dev->name, ret);
+		return ret;
+	}
+
+	output->dev = dev;
+	output->bridge = bridge;
+	output->panel = panel;
+
+	/*
+	 * The DSI output has been properly configured, we can now safely
+	 * register the input to the bridge framework so that it can take place
+	 * in a display pipeline.
+	 */
+	drm_bridge_add(&input->bridge);
+
+	return 0;
+}
+
+static int cdns_dsi_detach(struct mipi_dsi_host *host,
+			   struct mipi_dsi_device *dev)
+{
+	struct cdns_dsi *dsi = to_cdns_dsi(host);
+	struct cdns_dsi_output *output = &dsi->output;
+	struct cdns_dsi_input *input = &dsi->input;
+
+	drm_bridge_remove(&input->bridge);
+	if (output->panel)
+		drm_panel_bridge_remove(output->bridge);
+
+	return 0;
+}
+
+static irqreturn_t cdns_dsi_interrupt(int irq, void *data)
+{
+	struct cdns_dsi *dsi = data;
+	irqreturn_t ret = IRQ_NONE;
+	u32 flag, ctl;
+
+	flag = readl(dsi->regs + DIRECT_CMD_STS_FLAG);
+	if (flag) {
+		ctl = readl(dsi->regs + DIRECT_CMD_STS_CTL);
+		ctl &= ~flag;
+		writel(ctl, dsi->regs + DIRECT_CMD_STS_CTL);
+		complete(&dsi->direct_cmd_comp);
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static ssize_t cdns_dsi_transfer(struct mipi_dsi_host *host,
+				 const struct mipi_dsi_msg *msg)
+{
+	struct cdns_dsi *dsi = to_cdns_dsi(host);
+	u32 cmd, sts, val, wait = WRITE_COMPLETED, ctl = 0;
+	struct mipi_dsi_packet packet;
+	int ret, i, tx_len, rx_len;
+
+	ret = pm_runtime_get_sync(host->dev);
+	if (ret < 0)
+		return ret;
+
+	cdns_dsi_init_link(dsi);
+
+	ret = mipi_dsi_create_packet(&packet, msg);
+	if (ret)
+		goto out;
+
+	tx_len = msg->tx_buf ? msg->tx_len : 0;
+	rx_len = msg->rx_buf ? msg->rx_len : 0;
+
+	/* For read operations, the maximum TX len is 2. */
+	if (rx_len && tx_len > 2) {
+		ret = -ENOTSUPP;
+		goto out;
+	}
+
+	/* TX len is limited by the CMD FIFO depth. */
+	if (tx_len > dsi->direct_cmd_fifo_depth) {
+		ret = -ENOTSUPP;
+		goto out;
+	}
+
+	/* RX len is limited by the RX FIFO depth. */
+	if (rx_len > dsi->rx_fifo_depth) {
+		ret = -ENOTSUPP;
+		goto out;
+	}
+
+	cmd = CMD_SIZE(tx_len) | CMD_VCHAN_ID(msg->channel) |
+	      CMD_DATATYPE(msg->type);
+
+	if (msg->flags & MIPI_DSI_MSG_USE_LPM)
+		cmd |= CMD_LP_EN;
+
+	if (mipi_dsi_packet_format_is_long(msg->type))
+		cmd |= CMD_LONG;
+
+	if (rx_len) {
+		cmd |= READ_CMD;
+		wait = READ_COMPLETED_WITH_ERR | READ_COMPLETED;
+		ctl = READ_EN | BTA_EN;
+	} else if (msg->flags & MIPI_DSI_MSG_REQ_ACK) {
+		cmd |= BTA_REQ;
+		wait = ACK_WITH_ERR_RCVD | ACK_RCVD;
+		ctl = BTA_EN;
+	}
+
+	writel(readl(dsi->regs + MCTL_MAIN_DATA_CTL) | ctl,
+	       dsi->regs + MCTL_MAIN_DATA_CTL);
+
+	writel(cmd, dsi->regs + DIRECT_CMD_MAIN_SETTINGS);
+
+	for (i = 0; i < tx_len; i += 4) {
+		const u8 *buf = msg->tx_buf;
+		int j;
+
+		val = 0;
+		for (j = 0; j < 4 && j + i < tx_len; j++)
+			val |= (u32)buf[i + j] << (8 * j);
+
+		writel(val, dsi->regs + DIRECT_CMD_WRDATA);
+	}
+
+	/* Clear status flags before sending the command. */
+	writel(wait, dsi->regs + DIRECT_CMD_STS_CLR);
+	writel(wait, dsi->regs + DIRECT_CMD_STS_CTL);
+	reinit_completion(&dsi->direct_cmd_comp);
+	writel(0, dsi->regs + DIRECT_CMD_SEND);
+
+	wait_for_completion_timeout(&dsi->direct_cmd_comp,
+				    msecs_to_jiffies(1000));
+
+	sts = readl(dsi->regs + DIRECT_CMD_STS);
+	writel(wait, dsi->regs + DIRECT_CMD_STS_CLR);
+	writel(0, dsi->regs + DIRECT_CMD_STS_CTL);
+
+	writel(readl(dsi->regs + MCTL_MAIN_DATA_CTL) & ~ctl,
+	       dsi->regs + MCTL_MAIN_DATA_CTL);
+
+	/* We did not receive the events we were waiting for. */
+	if (!(sts & wait)) {
+		ret = -ETIMEDOUT;
+		goto out;
+	}
+
+	/* 'READ' or 'WRITE with ACK' failed. */
+	if (sts & (READ_COMPLETED_WITH_ERR | ACK_WITH_ERR_RCVD)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	for (i = 0; i < rx_len; i += 4) {
+		u8 *buf = msg->rx_buf;
+		int j;
+
+		val = readl(dsi->regs + DIRECT_CMD_RDDATA);
+		for (j = 0; j < 4 && j + i < rx_len; j++)
+			buf[i + j] = val >> (8 * j);
+	}
+
+out:
+	pm_runtime_put(host->dev);
+	return ret;
+}
+
+static const struct mipi_dsi_host_ops cdns_dsi_ops = {
+	.attach = cdns_dsi_attach,
+	.detach = cdns_dsi_detach,
+	.transfer = cdns_dsi_transfer,
+};
+
+static int cdns_dsi_resume(struct device *dev)
+{
+	struct cdns_dsi *dsi = dev_get_drvdata(dev);
+
+	reset_control_deassert(dsi->dsi_p_rst);
+	clk_prepare_enable(dsi->dsi_p_clk);
+	clk_prepare_enable(dsi->dsi_sys_clk);
+	clk_prepare_enable(dsi->dphy->psm_clk);
+	clk_prepare_enable(dsi->dphy->pll_ref_clk);
+
+	return 0;
+}
+
+static int cdns_dsi_suspend(struct device *dev)
+{
+	struct cdns_dsi *dsi = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(dsi->dphy->pll_ref_clk);
+	clk_disable_unprepare(dsi->dphy->psm_clk);
+	clk_disable_unprepare(dsi->dsi_sys_clk);
+	clk_disable_unprepare(dsi->dsi_p_clk);
+	reset_control_assert(dsi->dsi_p_rst);
+	dsi->link_initialized = false;
+	return 0;
+}
+
+static UNIVERSAL_DEV_PM_OPS(cdns_dsi_pm_ops, cdns_dsi_suspend, cdns_dsi_resume,
+			    NULL);
+
+static unsigned long cdns_dphy_ref_get_wakeup_time_ns(struct cdns_dphy *dphy)
+{
+	/* Default wakeup time is 800 ns (in a simulated environment). */
+	return 800;
+}
+
+static void cdns_dphy_ref_set_pll_cfg(struct cdns_dphy *dphy,
+				      const struct cdns_dphy_cfg *cfg)
+{
+	u32 fbdiv_low, fbdiv_high;
+
+	fbdiv_low = (cfg->pll_fbdiv / 4) - 2;
+	fbdiv_high = cfg->pll_fbdiv - fbdiv_low - 2;
+
+	writel(DPHY_CMN_IPDIV_FROM_REG | DPHY_CMN_OPDIV_FROM_REG |
+	       DPHY_CMN_IPDIV(cfg->pll_ipdiv) |
+	       DPHY_CMN_OPDIV(cfg->pll_opdiv),
+	       dphy->regs + DPHY_CMN_OPIPDIV);
+	writel(DPHY_CMN_FBDIV_FROM_REG |
+	       DPHY_CMN_FBDIV_VAL(fbdiv_low, fbdiv_high),
+	       dphy->regs + DPHY_CMN_FBDIV);
+	writel(DPHY_CMN_PWM_HIGH(6) | DPHY_CMN_PWM_LOW(0x101) |
+	       DPHY_CMN_PWM_DIV(0x8),
+	       dphy->regs + DPHY_CMN_PWM);
+}
+
+static void cdns_dphy_ref_set_psm_div(struct cdns_dphy *dphy, u8 div)
+{
+	writel(DPHY_PSM_CFG_FROM_REG | DPHY_PSM_CLK_DIV(div),
+	       dphy->regs + DPHY_PSM_CFG);
+}
+
+/*
+ * This is the reference implementation of DPHY hooks. Specific integration of
+ * this IP may have to re-implement some of them depending on how they decided
+ * to wire things in the SoC.
+ */
+static const struct cdns_dphy_ops ref_dphy_ops = {
+	.get_wakeup_time_ns = cdns_dphy_ref_get_wakeup_time_ns,
+	.set_pll_cfg = cdns_dphy_ref_set_pll_cfg,
+	.set_psm_div = cdns_dphy_ref_set_psm_div,
+};
+
+static const struct of_device_id cdns_dphy_of_match[] = {
+	{ .compatible = "cdns,dphy", .data = &ref_dphy_ops },
+	{ /* sentinel */ },
+};
+
+static struct cdns_dphy *cdns_dphy_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	struct cdns_dphy *dphy;
+	struct of_phandle_args args;
+	struct resource res;
+	int ret;
+
+	ret = of_parse_phandle_with_args(pdev->dev.of_node, "phys",
+					 "#phy-cells", 0, &args);
+	if (ret)
+		return ERR_PTR(-ENOENT);
+
+	match = of_match_node(cdns_dphy_of_match, args.np);
+	if (!match || !match->data)
+		return ERR_PTR(-EINVAL);
+
+	dphy = devm_kzalloc(&pdev->dev, sizeof(*dphy), GFP_KERNEL);
+	if (!dphy)
+		return ERR_PTR(-ENOMEM);
+
+	dphy->ops = match->data;
+
+	ret = of_address_to_resource(args.np, 0, &res);
+	if (ret)
+		return ERR_PTR(ret);
+
+	dphy->regs = devm_ioremap_resource(&pdev->dev, &res);
+	if (IS_ERR(dphy->regs))
+		return ERR_CAST(dphy->regs);
+
+	dphy->psm_clk = of_clk_get_by_name(args.np, "psm");
+	if (IS_ERR(dphy->psm_clk))
+		return ERR_CAST(dphy->psm_clk);
+
+	dphy->pll_ref_clk = of_clk_get_by_name(args.np, "pll_ref");
+	if (IS_ERR(dphy->pll_ref_clk)) {
+		ret = PTR_ERR(dphy->pll_ref_clk);
+		goto err_put_psm_clk;
+	}
+
+	if (dphy->ops->probe) {
+		ret = dphy->ops->probe(dphy);
+		if (ret)
+			goto err_put_pll_ref_clk;
+	}
+
+	return dphy;
+
+err_put_pll_ref_clk:
+	clk_put(dphy->pll_ref_clk);
+
+err_put_psm_clk:
+	clk_put(dphy->psm_clk);
+
+	return ERR_PTR(ret);
+}
+
+static void cdns_dphy_remove(struct cdns_dphy *dphy)
+{
+	if (dphy->ops->remove)
+		dphy->ops->remove(dphy);
+
+	clk_put(dphy->pll_ref_clk);
+	clk_put(dphy->psm_clk);
+}
+
+static int cdns_dsi_drm_probe(struct platform_device *pdev)
+{
+	struct cdns_dsi *dsi;
+	struct cdns_dsi_input *input;
+	struct resource *res;
+	int ret, irq;
+	u32 val;
+
+	dsi = devm_kzalloc(&pdev->dev, sizeof(*dsi), GFP_KERNEL);
+	if (!dsi)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, dsi);
+
+	input = &dsi->input;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dsi->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dsi->regs))
+		return PTR_ERR(dsi->regs);
+
+	dsi->dsi_p_clk = devm_clk_get(&pdev->dev, "dsi_p_clk");
+	if (IS_ERR(dsi->dsi_p_clk))
+		return PTR_ERR(dsi->dsi_p_clk);
+
+	dsi->dsi_p_rst = devm_reset_control_get_optional_exclusive(&pdev->dev,
+								"dsi_p_rst");
+	if (IS_ERR(dsi->dsi_p_rst))
+		return PTR_ERR(dsi->dsi_p_rst);
+
+	dsi->dsi_sys_clk = devm_clk_get(&pdev->dev, "dsi_sys_clk");
+	if (IS_ERR(dsi->dsi_sys_clk))
+		return PTR_ERR(dsi->dsi_sys_clk);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	dsi->dphy = cdns_dphy_probe(pdev);
+	if (IS_ERR(dsi->dphy))
+		return PTR_ERR(dsi->dphy);
+
+	ret = clk_prepare_enable(dsi->dsi_p_clk);
+	if (ret)
+		goto err_remove_dphy;
+
+	val = readl(dsi->regs + ID_REG);
+	if (REV_VENDOR_ID(val) != 0xcad) {
+		dev_err(&pdev->dev, "invalid vendor id\n");
+		ret = -EINVAL;
+		goto err_disable_pclk;
+	}
+
+	val = readl(dsi->regs + IP_CONF);
+	dsi->direct_cmd_fifo_depth = 1 << (DIRCMD_FIFO_DEPTH(val) + 2);
+	dsi->rx_fifo_depth = RX_FIFO_DEPTH(val);
+	init_completion(&dsi->direct_cmd_comp);
+
+	writel(0, dsi->regs + MCTL_MAIN_DATA_CTL);
+	writel(0, dsi->regs + MCTL_MAIN_EN);
+	writel(0, dsi->regs + MCTL_MAIN_PHY_CTL);
+
+	/*
+	 * We only support the DPI input, so force input->id to
+	 * CDNS_DPI_INPUT.
+	 */
+	input->id = CDNS_DPI_INPUT;
+	input->bridge.funcs = &cdns_dsi_bridge_funcs;
+	input->bridge.of_node = pdev->dev.of_node;
+
+	/* Mask all interrupts before registering the IRQ handler. */
+	writel(0, dsi->regs + MCTL_MAIN_STS_CTL);
+	writel(0, dsi->regs + MCTL_DPHY_ERR_CTL1);
+	writel(0, dsi->regs + CMD_MODE_STS_CTL);
+	writel(0, dsi->regs + DIRECT_CMD_STS_CTL);
+	writel(0, dsi->regs + DIRECT_CMD_RD_STS_CTL);
+	writel(0, dsi->regs + VID_MODE_STS_CTL);
+	writel(0, dsi->regs + TVG_STS_CTL);
+	writel(0, dsi->regs + DPI_IRQ_EN);
+	ret = devm_request_irq(&pdev->dev, irq, cdns_dsi_interrupt, 0,
+			       dev_name(&pdev->dev), dsi);
+	if (ret)
+		goto err_disable_pclk;
+
+	pm_runtime_enable(&pdev->dev);
+	dsi->base.dev = &pdev->dev;
+	dsi->base.ops = &cdns_dsi_ops;
+
+	ret = mipi_dsi_host_register(&dsi->base);
+	if (ret)
+		goto err_disable_runtime_pm;
+
+	clk_disable_unprepare(dsi->dsi_p_clk);
+
+	return 0;
+
+err_disable_runtime_pm:
+	pm_runtime_disable(&pdev->dev);
+
+err_disable_pclk:
+	clk_disable_unprepare(dsi->dsi_p_clk);
+
+err_remove_dphy:
+	cdns_dphy_remove(dsi->dphy);
+
+	return ret;
+}
+
+static int cdns_dsi_drm_remove(struct platform_device *pdev)
+{
+	struct cdns_dsi *dsi = platform_get_drvdata(pdev);
+
+	mipi_dsi_host_unregister(&dsi->base);
+	pm_runtime_disable(&pdev->dev);
+	cdns_dphy_remove(dsi->dphy);
+
+	return 0;
+}
+
+static const struct of_device_id cdns_dsi_of_match[] = {
+	{ .compatible = "cdns,dsi" },
+	{ },
+};
+
+static struct platform_driver cdns_dsi_platform_driver = {
+	.probe  = cdns_dsi_drm_probe,
+	.remove = cdns_dsi_drm_remove,
+	.driver = {
+		.name   = "cdns-dsi",
+		.of_match_table = cdns_dsi_of_match,
+		.pm = &cdns_dsi_pm_ops,
+	},
+};
+module_platform_driver(cdns_dsi_platform_driver);
+
+MODULE_AUTHOR("Boris Brezillon <boris.brezillon@bootlin.com>");
+MODULE_DESCRIPTION("Cadence DSI driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:cdns-dsi");
+
diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c
index 498d5948d1a8..9837c8d69e69 100644
--- a/drivers/gpu/drm/bridge/dumb-vga-dac.c
+++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c
@@ -56,7 +56,9 @@ static int dumb_vga_get_modes(struct drm_connector *connector)
 	}
 
 	drm_mode_connector_update_edid_property(connector, edid);
-	return drm_add_edid_modes(connector, edid);
+	ret = drm_add_edid_modes(connector, edid);
+	kfree(edid);
+	return ret;
 
 fallback:
 	/*
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
index 3b7e5c59a5e9..8f9c8a6b46de 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
@@ -152,7 +152,6 @@ static struct platform_driver snd_dw_hdmi_driver = {
 	.remove	= snd_dw_hdmi_remove,
 	.driver	= {
 		.name = DRIVER_NAME,
-		.owner = THIS_MODULE,
 	},
 };
 module_platform_driver(snd_dw_hdmi_driver);
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index ec8d0006ef7c..3c136f2b954f 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -2077,7 +2077,7 @@ static irqreturn_t dw_hdmi_hardirq(int irq, void *dev_id)
 	return ret;
 }
 
-void __dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense)
+void dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense)
 {
 	mutex_lock(&hdmi->mutex);
 
@@ -2103,13 +2103,6 @@ void __dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense)
 	}
 	mutex_unlock(&hdmi->mutex);
 }
-
-void dw_hdmi_setup_rx_sense(struct device *dev, bool hpd, bool rx_sense)
-{
-	struct dw_hdmi *hdmi = dev_get_drvdata(dev);
-
-	__dw_hdmi_setup_rx_sense(hdmi, hpd, rx_sense);
-}
 EXPORT_SYMBOL_GPL(dw_hdmi_setup_rx_sense);
 
 static irqreturn_t dw_hdmi_irq(int irq, void *dev_id)
@@ -2145,9 +2138,9 @@ static irqreturn_t dw_hdmi_irq(int irq, void *dev_id)
 	 */
 	if (intr_stat &
 	    (HDMI_IH_PHY_STAT0_RX_SENSE | HDMI_IH_PHY_STAT0_HPD)) {
-		__dw_hdmi_setup_rx_sense(hdmi,
-					 phy_stat & HDMI_PHY_HPD,
-					 phy_stat & HDMI_PHY_RX_SENSE);
+		dw_hdmi_setup_rx_sense(hdmi,
+				       phy_stat & HDMI_PHY_HPD,
+				       phy_stat & HDMI_PHY_RX_SENSE);
 
 		if ((phy_stat & (HDMI_PHY_RX_SENSE | HDMI_PHY_HPD)) == 0)
 			cec_notifier_set_phys_addr(hdmi->cec_notifier,
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
index 226171a3ece1..fd7999642cf8 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Copyright (c) 2016, Fuzhou Rockchip Electronics Co., Ltd
  * Copyright (C) STMicroelectronics SA 2017
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  * Modified by Philippe Cornu <philippe.cornu@st.com>
  * This generic Synopsys DesignWare MIPI DSI host driver is based on the
  * Rockchip version from rockchip/dw-mipi-dsi.c with phy & bridge APIs.
@@ -775,20 +771,20 @@ static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge,
 
 	clk_prepare_enable(dsi->pclk);
 
-	ret = phy_ops->get_lane_mbps(priv_data, mode, dsi->mode_flags,
+	ret = phy_ops->get_lane_mbps(priv_data, adjusted_mode, dsi->mode_flags,
 				     dsi->lanes, dsi->format, &dsi->lane_mbps);
 	if (ret)
 		DRM_DEBUG_DRIVER("Phy get_lane_mbps() failed\n");
 
 	pm_runtime_get_sync(dsi->dev);
 	dw_mipi_dsi_init(dsi);
-	dw_mipi_dsi_dpi_config(dsi, mode);
+	dw_mipi_dsi_dpi_config(dsi, adjusted_mode);
 	dw_mipi_dsi_packet_handler_config(dsi);
 	dw_mipi_dsi_video_mode_config(dsi);
-	dw_mipi_dsi_video_packet_config(dsi, mode);
+	dw_mipi_dsi_video_packet_config(dsi, adjusted_mode);
 	dw_mipi_dsi_command_mode_config(dsi);
-	dw_mipi_dsi_line_timer_config(dsi, mode);
-	dw_mipi_dsi_vertical_timing_config(dsi, mode);
+	dw_mipi_dsi_line_timer_config(dsi, adjusted_mode);
+	dw_mipi_dsi_vertical_timing_config(dsi, adjusted_mode);
 
 	dw_mipi_dsi_dphy_init(dsi);
 	dw_mipi_dsi_dphy_timing_config(dsi);
@@ -802,7 +798,7 @@ static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge,
 
 	dw_mipi_dsi_dphy_enable(dsi);
 
-	dw_mipi_dsi_wait_for_two_frames(mode);
+	dw_mipi_dsi_wait_for_two_frames(adjusted_mode);
 
 	/* Switch to cmd mode for panel-bridge pre_enable & panel prepare */
 	dw_mipi_dsi_set_mode(dsi, 0);
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 08ab7d6aea65..0fd9cf27542c 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -1102,7 +1102,7 @@ static bool tc_bridge_mode_fixup(struct drm_bridge *bridge,
 	return true;
 }
 
-static int tc_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status tc_connector_mode_valid(struct drm_connector *connector,
 				   struct drm_display_mode *mode)
 {
 	/* DPI interface clock limitation: upto 154 MHz */
diff --git a/drivers/gpu/drm/bridge/thc63lvd1024.c b/drivers/gpu/drm/bridge/thc63lvd1024.c
new file mode 100644
index 000000000000..c8b9edd5a7f4
--- /dev/null
+++ b/drivers/gpu/drm/bridge/thc63lvd1024.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * THC63LVD1024 LVDS to parallel data DRM bridge driver.
+ *
+ * Copyright (C) 2018 Jacopo Mondi <jacopo+renesas@jmondi.org>
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_bridge.h>
+#include <drm/drm_panel.h>
+
+#include <linux/gpio/consumer.h>
+#include <linux/of_graph.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+
+enum thc63_ports {
+	THC63_LVDS_IN0,
+	THC63_LVDS_IN1,
+	THC63_RGB_OUT0,
+	THC63_RGB_OUT1,
+};
+
+struct thc63_dev {
+	struct device *dev;
+
+	struct regulator *vcc;
+
+	struct gpio_desc *pdwn;
+	struct gpio_desc *oe;
+
+	struct drm_bridge bridge;
+	struct drm_bridge *next;
+};
+
+static inline struct thc63_dev *to_thc63(struct drm_bridge *bridge)
+{
+	return container_of(bridge, struct thc63_dev, bridge);
+}
+
+static int thc63_attach(struct drm_bridge *bridge)
+{
+	struct thc63_dev *thc63 = to_thc63(bridge);
+
+	return drm_bridge_attach(bridge->encoder, thc63->next, bridge);
+}
+
+static void thc63_enable(struct drm_bridge *bridge)
+{
+	struct thc63_dev *thc63 = to_thc63(bridge);
+	int ret;
+
+	ret = regulator_enable(thc63->vcc);
+	if (ret) {
+		dev_err(thc63->dev,
+			"Failed to enable regulator \"vcc\": %d\n", ret);
+		return;
+	}
+
+	gpiod_set_value(thc63->pdwn, 0);
+	gpiod_set_value(thc63->oe, 1);
+}
+
+static void thc63_disable(struct drm_bridge *bridge)
+{
+	struct thc63_dev *thc63 = to_thc63(bridge);
+	int ret;
+
+	gpiod_set_value(thc63->oe, 0);
+	gpiod_set_value(thc63->pdwn, 1);
+
+	ret = regulator_disable(thc63->vcc);
+	if (ret)
+		dev_err(thc63->dev,
+			"Failed to disable regulator \"vcc\": %d\n", ret);
+}
+
+static const struct drm_bridge_funcs thc63_bridge_func = {
+	.attach	= thc63_attach,
+	.enable = thc63_enable,
+	.disable = thc63_disable,
+};
+
+static int thc63_parse_dt(struct thc63_dev *thc63)
+{
+	struct device_node *thc63_out;
+	struct device_node *remote;
+
+	thc63_out = of_graph_get_endpoint_by_regs(thc63->dev->of_node,
+						  THC63_RGB_OUT0, -1);
+	if (!thc63_out) {
+		dev_err(thc63->dev, "Missing endpoint in port@%u\n",
+			THC63_RGB_OUT0);
+		return -ENODEV;
+	}
+
+	remote = of_graph_get_remote_port_parent(thc63_out);
+	of_node_put(thc63_out);
+	if (!remote) {
+		dev_err(thc63->dev, "Endpoint in port@%u unconnected\n",
+			THC63_RGB_OUT0);
+		return -ENODEV;
+	}
+
+	if (!of_device_is_available(remote)) {
+		dev_err(thc63->dev, "port@%u remote endpoint is disabled\n",
+			THC63_RGB_OUT0);
+		of_node_put(remote);
+		return -ENODEV;
+	}
+
+	thc63->next = of_drm_find_bridge(remote);
+	of_node_put(remote);
+	if (!thc63->next)
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+
+static int thc63_gpio_init(struct thc63_dev *thc63)
+{
+	thc63->oe = devm_gpiod_get_optional(thc63->dev, "oe", GPIOD_OUT_LOW);
+	if (IS_ERR(thc63->oe)) {
+		dev_err(thc63->dev, "Unable to get \"oe-gpios\": %ld\n",
+			PTR_ERR(thc63->oe));
+		return PTR_ERR(thc63->oe);
+	}
+
+	thc63->pdwn = devm_gpiod_get_optional(thc63->dev, "powerdown",
+					      GPIOD_OUT_HIGH);
+	if (IS_ERR(thc63->pdwn)) {
+		dev_err(thc63->dev, "Unable to get \"powerdown-gpios\": %ld\n",
+			PTR_ERR(thc63->pdwn));
+		return PTR_ERR(thc63->pdwn);
+	}
+
+	return 0;
+}
+
+static int thc63_probe(struct platform_device *pdev)
+{
+	struct thc63_dev *thc63;
+	int ret;
+
+	thc63 = devm_kzalloc(&pdev->dev, sizeof(*thc63), GFP_KERNEL);
+	if (!thc63)
+		return -ENOMEM;
+
+	thc63->dev = &pdev->dev;
+	platform_set_drvdata(pdev, thc63);
+
+	thc63->vcc = devm_regulator_get_optional(thc63->dev, "vcc");
+	if (IS_ERR(thc63->vcc)) {
+		if (PTR_ERR(thc63->vcc) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
+		dev_err(thc63->dev, "Unable to get \"vcc\" supply: %ld\n",
+			PTR_ERR(thc63->vcc));
+		return PTR_ERR(thc63->vcc);
+	}
+
+	ret = thc63_gpio_init(thc63);
+	if (ret)
+		return ret;
+
+	ret = thc63_parse_dt(thc63);
+	if (ret)
+		return ret;
+
+	thc63->bridge.driver_private = thc63;
+	thc63->bridge.of_node = pdev->dev.of_node;
+	thc63->bridge.funcs = &thc63_bridge_func;
+
+	drm_bridge_add(&thc63->bridge);
+
+	return 0;
+}
+
+static int thc63_remove(struct platform_device *pdev)
+{
+	struct thc63_dev *thc63 = platform_get_drvdata(pdev);
+
+	drm_bridge_remove(&thc63->bridge);
+
+	return 0;
+}
+
+static const struct of_device_id thc63_match[] = {
+	{ .compatible = "thine,thc63lvd1024", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, thc63_match);
+
+static struct platform_driver thc63_driver = {
+	.probe	= thc63_probe,
+	.remove	= thc63_remove,
+	.driver	= {
+		.name		= "thc63lvd1024",
+		.of_match_table	= thc63_match,
+	},
+};
+module_platform_driver(thc63_driver);
+
+MODULE_AUTHOR("Jacopo Mondi <jacopo@jmondi.org>");
+MODULE_DESCRIPTION("Thine THC63LVD1024 LVDS decoder DRM bridge driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 7d25c42f22db..895741e9cd7d 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -155,6 +155,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
 						       state->connectors[i].state);
 		state->connectors[i].ptr = NULL;
 		state->connectors[i].state = NULL;
+		state->connectors[i].old_state = NULL;
+		state->connectors[i].new_state = NULL;
 		drm_connector_put(connector);
 	}
 
@@ -169,6 +171,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
 
 		state->crtcs[i].ptr = NULL;
 		state->crtcs[i].state = NULL;
+		state->crtcs[i].old_state = NULL;
+		state->crtcs[i].new_state = NULL;
 	}
 
 	for (i = 0; i < config->num_total_plane; i++) {
@@ -181,6 +185,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
 						   state->planes[i].state);
 		state->planes[i].ptr = NULL;
 		state->planes[i].state = NULL;
+		state->planes[i].old_state = NULL;
+		state->planes[i].new_state = NULL;
 	}
 
 	for (i = 0; i < state->num_private_objs; i++) {
@@ -190,6 +196,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
 						 state->private_objs[i].state);
 		state->private_objs[i].ptr = NULL;
 		state->private_objs[i].state = NULL;
+		state->private_objs[i].old_state = NULL;
+		state->private_objs[i].new_state = NULL;
 	}
 	state->num_private_objs = 0;
 
@@ -783,6 +791,8 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane,
 		state->src_w = val;
 	} else if (property == config->prop_src_h) {
 		state->src_h = val;
+	} else if (property == plane->alpha_property) {
+		state->alpha = val;
 	} else if (property == plane->rotation_property) {
 		if (!is_power_of_2(val & DRM_MODE_ROTATE_MASK))
 			return -EINVAL;
@@ -848,6 +858,8 @@ drm_atomic_plane_get_property(struct drm_plane *plane,
 		*val = state->src_w;
 	} else if (property == config->prop_src_h) {
 		*val = state->src_h;
+	} else if (property == plane->alpha_property) {
+		*val = state->alpha;
 	} else if (property == plane->rotation_property) {
 		*val = state->rotation;
 	} else if (property == plane->zpos_property) {
@@ -1421,7 +1433,9 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state,
 {
 	struct drm_plane *plane = plane_state->plane;
 	struct drm_crtc_state *crtc_state;
-
+	/* Nothing to do for same crtc*/
+	if (plane_state->crtc == crtc)
+		return 0;
 	if (plane_state->crtc) {
 		crtc_state = drm_atomic_get_crtc_state(plane_state->state,
 						       plane_state->crtc);
@@ -1492,6 +1506,14 @@ EXPORT_SYMBOL(drm_atomic_set_fb_for_plane);
  * Otherwise, if &drm_plane_state.fence is not set this function we just set it
  * with the received implicit fence. In both cases this function consumes a
  * reference for @fence.
+ *
+ * This way explicit fencing can be used to overrule implicit fencing, which is
+ * important to make explicit fencing use-cases work: One example is using one
+ * buffer for 2 screens with different refresh rates. Implicit fencing will
+ * clamp rendering to the refresh rate of the slower screen, whereas explicit
+ * fence allows 2 independent render and display loops on a single buffer. If a
+ * driver allows obeys both implicit and explicit fences for plane updates, then
+ * it will break all the benefits of explicit fencing.
  */
 void
 drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state,
@@ -1702,11 +1724,15 @@ int drm_atomic_check_only(struct drm_atomic_state *state)
 		}
 	}
 
-	if (config->funcs->atomic_check)
+	if (config->funcs->atomic_check) {
 		ret = config->funcs->atomic_check(state->dev, state);
 
-	if (ret)
-		return ret;
+		if (ret) {
+			DRM_DEBUG_ATOMIC("atomic driver check for %p failed: %d\n",
+					 state, ret);
+			return ret;
+		}
+	}
 
 	if (!state->allow_modeset) {
 		for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index c35654591c12..130da5195f3b 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -766,7 +766,7 @@ int drm_atomic_helper_check_plane_state(struct drm_plane_state *plane_state,
 	if (crtc_state->enable)
 		drm_mode_get_hv_timing(&crtc_state->mode, &clip.x2, &clip.y2);
 
-	plane_state->visible = drm_rect_clip_scaled(src, dst, &clip, hscale, vscale);
+	plane_state->visible = drm_rect_clip_scaled(src, dst, &clip);
 
 	drm_rect_rotate_inv(src, fb->width << 16, fb->height << 16, rotation);
 
@@ -875,6 +875,11 @@ EXPORT_SYMBOL(drm_atomic_helper_check_planes);
  * functions depend upon an updated adjusted_mode.clock to e.g. properly compute
  * watermarks.
  *
+ * Note that zpos normalization will add all enable planes to the state which
+ * might not desired for some drivers.
+ * For example enable/disable of a cursor plane which have fixed zpos value
+ * would trigger all other enabled planes to be forced to the state change.
+ *
  * RETURNS:
  * Zero for success or -errno
  */
@@ -887,6 +892,12 @@ int drm_atomic_helper_check(struct drm_device *dev,
 	if (ret)
 		return ret;
 
+	if (dev->mode_config.normalize_zpos) {
+		ret = drm_atomic_normalize_zpos(dev, state);
+		if (ret)
+			return ret;
+	}
+
 	ret = drm_atomic_helper_check_planes(dev, state);
 	if (ret)
 		return ret;
@@ -1561,6 +1572,17 @@ void drm_atomic_helper_async_commit(struct drm_device *dev,
 	for_each_new_plane_in_state(state, plane, plane_state, i) {
 		funcs = plane->helper_private;
 		funcs->atomic_async_update(plane, plane_state);
+
+		/*
+		 * ->atomic_async_update() is supposed to update the
+		 * plane->state in-place, make sure at least common
+		 * properties have been properly updated.
+		 */
+		WARN_ON_ONCE(plane->state->fb != plane_state->fb);
+		WARN_ON_ONCE(plane->state->crtc_x != plane_state->crtc_x);
+		WARN_ON_ONCE(plane->state->crtc_y != plane_state->crtc_y);
+		WARN_ON_ONCE(plane->state->src_x != plane_state->src_x);
+		WARN_ON_ONCE(plane->state->src_y != plane_state->src_y);
 	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_async_commit);
@@ -2659,7 +2681,7 @@ int drm_atomic_helper_disable_plane(struct drm_plane *plane,
 		goto fail;
 	}
 
-	if (plane_state->crtc && (plane == plane->crtc->cursor))
+	if (plane_state->crtc && plane_state->crtc->cursor == plane)
 		plane_state->state->legacy_cursor_update = true;
 
 	ret = __drm_atomic_helper_disable_plane(plane, plane_state);
@@ -2881,31 +2903,9 @@ commit:
 	return 0;
 }
 
-/**
- * drm_atomic_helper_disable_all - disable all currently active outputs
- * @dev: DRM device
- * @ctx: lock acquisition context
- *
- * Loops through all connectors, finding those that aren't turned off and then
- * turns them off by setting their DPMS mode to OFF and deactivating the CRTC
- * that they are connected to.
- *
- * This is used for example in suspend/resume to disable all currently active
- * functions when suspending. If you just want to shut down everything at e.g.
- * driver unload, look at drm_atomic_helper_shutdown().
- *
- * Note that if callers haven't already acquired all modeset locks this might
- * return -EDEADLK, which must be handled by calling drm_modeset_backoff().
- *
- * Returns:
- * 0 on success or a negative error code on failure.
- *
- * See also:
- * drm_atomic_helper_suspend(), drm_atomic_helper_resume() and
- * drm_atomic_helper_shutdown().
- */
-int drm_atomic_helper_disable_all(struct drm_device *dev,
-				  struct drm_modeset_acquire_ctx *ctx)
+static int __drm_atomic_helper_disable_all(struct drm_device *dev,
+					   struct drm_modeset_acquire_ctx *ctx,
+					   bool clean_old_fbs)
 {
 	struct drm_atomic_state *state;
 	struct drm_connector_state *conn_state;
@@ -2957,8 +2957,11 @@ int drm_atomic_helper_disable_all(struct drm_device *dev,
 			goto free;
 
 		drm_atomic_set_fb_for_plane(plane_state, NULL);
-		plane_mask |= BIT(drm_plane_index(plane));
-		plane->old_fb = plane->fb;
+
+		if (clean_old_fbs) {
+			plane->old_fb = plane->fb;
+			plane_mask |= BIT(drm_plane_index(plane));
+		}
 	}
 
 	ret = drm_atomic_commit(state);
@@ -2969,6 +2972,34 @@ free:
 	return ret;
 }
 
+/**
+ * drm_atomic_helper_disable_all - disable all currently active outputs
+ * @dev: DRM device
+ * @ctx: lock acquisition context
+ *
+ * Loops through all connectors, finding those that aren't turned off and then
+ * turns them off by setting their DPMS mode to OFF and deactivating the CRTC
+ * that they are connected to.
+ *
+ * This is used for example in suspend/resume to disable all currently active
+ * functions when suspending. If you just want to shut down everything at e.g.
+ * driver unload, look at drm_atomic_helper_shutdown().
+ *
+ * Note that if callers haven't already acquired all modeset locks this might
+ * return -EDEADLK, which must be handled by calling drm_modeset_backoff().
+ *
+ * Returns:
+ * 0 on success or a negative error code on failure.
+ *
+ * See also:
+ * drm_atomic_helper_suspend(), drm_atomic_helper_resume() and
+ * drm_atomic_helper_shutdown().
+ */
+int drm_atomic_helper_disable_all(struct drm_device *dev,
+				  struct drm_modeset_acquire_ctx *ctx)
+{
+	return __drm_atomic_helper_disable_all(dev, ctx, false);
+}
 EXPORT_SYMBOL(drm_atomic_helper_disable_all);
 
 /**
@@ -2991,7 +3022,7 @@ void drm_atomic_helper_shutdown(struct drm_device *dev)
 	while (1) {
 		ret = drm_modeset_lock_all_ctx(dev, &ctx);
 		if (!ret)
-			ret = drm_atomic_helper_disable_all(dev, &ctx);
+			ret = __drm_atomic_helper_disable_all(dev, &ctx, true);
 
 		if (ret != -EDEADLK)
 			break;
@@ -3095,14 +3126,14 @@ int drm_atomic_helper_commit_duplicated_state(struct drm_atomic_state *state,
 	struct drm_connector_state *new_conn_state;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *new_crtc_state;
-	unsigned plane_mask = 0;
-	struct drm_device *dev = state->dev;
-	int ret;
 
 	state->acquire_ctx = ctx;
 
 	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		plane_mask |= BIT(drm_plane_index(plane));
+		WARN_ON(plane->crtc != new_plane_state->crtc);
+		WARN_ON(plane->fb != new_plane_state->fb);
+		WARN_ON(plane->old_fb);
+
 		state->planes[i].old_state = plane->state;
 	}
 
@@ -3112,11 +3143,7 @@ int drm_atomic_helper_commit_duplicated_state(struct drm_atomic_state *state,
 	for_each_new_connector_in_state(state, connector, new_conn_state, i)
 		state->connectors[i].old_state = connector->state;
 
-	ret = drm_atomic_commit(state);
-	if (plane_mask)
-		drm_atomic_clean_old_fb(dev, plane_mask, ret);
-
-	return ret;
+	return drm_atomic_commit(state);
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_duplicated_state);
 
@@ -3484,6 +3511,10 @@ void drm_atomic_helper_plane_reset(struct drm_plane *plane)
 	if (plane->state) {
 		plane->state->plane = plane;
 		plane->state->rotation = DRM_MODE_ROTATE_0;
+
+		/* Reset the alpha value to fully opaque if it matters */
+		if (plane->alpha_property)
+			plane->state->alpha = plane->alpha_property->values[1];
 	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_plane_reset);
diff --git a/drivers/gpu/drm/drm_blend.c b/drivers/gpu/drm/drm_blend.c
index 5a81e1b4c076..a16a74d7e15e 100644
--- a/drivers/gpu/drm/drm_blend.c
+++ b/drivers/gpu/drm/drm_blend.c
@@ -88,6 +88,13 @@
  * On top of this basic transformation additional properties can be exposed by
  * the driver:
  *
+ * alpha:
+ * 	Alpha is setup with drm_plane_create_alpha_property(). It controls the
+ * 	plane-wide opacity, from transparent (0) to opaque (0xffff). It can be
+ * 	combined with pixel alpha.
+ *	The pixel values in the framebuffers are expected to not be
+ *	pre-multiplied by the global alpha associated to the plane.
+ *
  * rotation:
  *	Rotation is set up with drm_plane_create_rotation_property(). It adds a
  *	rotation and reflection step between the source and destination rectangles.
@@ -106,6 +113,38 @@
  */
 
 /**
+ * drm_plane_create_alpha_property - create a new alpha property
+ * @plane: drm plane
+ *
+ * This function creates a generic, mutable, alpha property and enables support
+ * for it in the DRM core. It is attached to @plane.
+ *
+ * The alpha property will be allowed to be within the bounds of 0
+ * (transparent) to 0xffff (opaque).
+ *
+ * Returns:
+ * 0 on success, negative error code on failure.
+ */
+int drm_plane_create_alpha_property(struct drm_plane *plane)
+{
+	struct drm_property *prop;
+
+	prop = drm_property_create_range(plane->dev, 0, "alpha",
+					 0, DRM_BLEND_ALPHA_OPAQUE);
+	if (!prop)
+		return -ENOMEM;
+
+	drm_object_attach_property(&plane->base, prop, DRM_BLEND_ALPHA_OPAQUE);
+	plane->alpha_property = prop;
+
+	if (plane->state)
+		plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_plane_create_alpha_property);
+
+/**
  * drm_plane_create_rotation_property - create a new rotation property
  * @plane: drm plane
  * @rotation: initial value of the rotation property
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index b3cde897cd80..9b9ba5d5ec0c 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -1069,7 +1069,7 @@ int drm_mode_create_tv_properties(struct drm_device *dev,
 		goto nomem;
 
 	for (i = 0; i < num_modes; i++)
-		drm_property_add_enum(dev->mode_config.tv_mode_property, i,
+		drm_property_add_enum(dev->mode_config.tv_mode_property,
 				      i, modes[i]);
 
 	dev->mode_config.tv_brightness_property =
@@ -1156,7 +1156,7 @@ int drm_connector_attach_scaling_mode_property(struct drm_connector *connector,
 {
 	struct drm_device *dev = connector->dev;
 	struct drm_property *scaling_mode_property;
-	int i, j = 0;
+	int i;
 	const unsigned valid_scaling_mode_mask =
 		(1U << ARRAY_SIZE(drm_scaling_mode_enum_list)) - 1;
 
@@ -1177,7 +1177,7 @@ int drm_connector_attach_scaling_mode_property(struct drm_connector *connector,
 		if (!(BIT(i) & scaling_mode_mask))
 			continue;
 
-		ret = drm_property_add_enum(scaling_mode_property, j++,
+		ret = drm_property_add_enum(scaling_mode_property,
 					    drm_scaling_mode_enum_list[i].type,
 					    drm_scaling_mode_enum_list[i].name);
 
@@ -1531,8 +1531,10 @@ static struct drm_encoder *drm_connector_get_encoder(struct drm_connector *conne
 	return connector->encoder;
 }
 
-static bool drm_mode_expose_to_userspace(const struct drm_display_mode *mode,
-					 const struct drm_file *file_priv)
+static bool
+drm_mode_expose_to_userspace(const struct drm_display_mode *mode,
+			     const struct list_head *export_list,
+			     const struct drm_file *file_priv)
 {
 	/*
 	 * If user-space hasn't configured the driver to expose the stereo 3D
@@ -1540,6 +1542,23 @@ static bool drm_mode_expose_to_userspace(const struct drm_display_mode *mode,
 	 */
 	if (!file_priv->stereo_allowed && drm_mode_is_stereo(mode))
 		return false;
+	/*
+	 * If user-space hasn't configured the driver to expose the modes
+	 * with aspect-ratio, don't expose them. However if such a mode
+	 * is unique, let it be exposed, but reset the aspect-ratio flags
+	 * while preparing the list of user-modes.
+	 */
+	if (!file_priv->aspect_ratio_allowed) {
+		struct drm_display_mode *mode_itr;
+
+		list_for_each_entry(mode_itr, export_list, export_head)
+			if (drm_mode_match(mode_itr, mode,
+					   DRM_MODE_MATCH_TIMINGS |
+					   DRM_MODE_MATCH_CLOCK |
+					   DRM_MODE_MATCH_FLAGS |
+					   DRM_MODE_MATCH_3D_FLAGS))
+				return false;
+	}
 
 	return true;
 }
@@ -1559,6 +1578,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	struct drm_mode_modeinfo u_mode;
 	struct drm_mode_modeinfo __user *mode_ptr;
 	uint32_t __user *encoder_ptr;
+	LIST_HEAD(export_list);
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
@@ -1607,21 +1627,31 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 
 	/* delayed so we get modes regardless of pre-fill_modes state */
 	list_for_each_entry(mode, &connector->modes, head)
-		if (drm_mode_expose_to_userspace(mode, file_priv))
+		if (drm_mode_expose_to_userspace(mode, &export_list,
+						 file_priv)) {
+			list_add_tail(&mode->export_head, &export_list);
 			mode_count++;
+		}
 
 	/*
 	 * This ioctl is called twice, once to determine how much space is
 	 * needed, and the 2nd time to fill it.
+	 * The modes that need to be exposed to the user are maintained in the
+	 * 'export_list'. When the ioctl is called first time to determine the,
+	 * space, the export_list gets filled, to find the no.of modes. In the
+	 * 2nd time, the user modes are filled, one by one from the export_list.
 	 */
 	if ((out_resp->count_modes >= mode_count) && mode_count) {
 		copied = 0;
 		mode_ptr = (struct drm_mode_modeinfo __user *)(unsigned long)out_resp->modes_ptr;
-		list_for_each_entry(mode, &connector->modes, head) {
-			if (!drm_mode_expose_to_userspace(mode, file_priv))
-				continue;
-
+		list_for_each_entry(mode, &export_list, export_head) {
 			drm_mode_convert_to_umode(&u_mode, mode);
+			/*
+			 * Reset aspect ratio flags of user-mode, if modes with
+			 * aspect-ratio are not supported.
+			 */
+			if (!file_priv->aspect_ratio_allowed)
+				u_mode.flags &= ~DRM_MODE_FLAG_PIC_AR_MASK;
 			if (copy_to_user(mode_ptr + copied,
 					 &u_mode, sizeof(u_mode))) {
 				ret = -EFAULT;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 03583887cfec..98a36e6c69ad 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -402,6 +402,7 @@ int drm_mode_getcrtc(struct drm_device *dev,
 {
 	struct drm_mode_crtc *crtc_resp = data;
 	struct drm_crtc *crtc;
+	struct drm_plane *plane;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
@@ -410,34 +411,36 @@ int drm_mode_getcrtc(struct drm_device *dev,
 	if (!crtc)
 		return -ENOENT;
 
+	plane = crtc->primary;
+
 	crtc_resp->gamma_size = crtc->gamma_size;
 
-	drm_modeset_lock(&crtc->primary->mutex, NULL);
-	if (crtc->primary->state && crtc->primary->state->fb)
-		crtc_resp->fb_id = crtc->primary->state->fb->base.id;
-	else if (!crtc->primary->state && crtc->primary->fb)
-		crtc_resp->fb_id = crtc->primary->fb->base.id;
+	drm_modeset_lock(&plane->mutex, NULL);
+	if (plane->state && plane->state->fb)
+		crtc_resp->fb_id = plane->state->fb->base.id;
+	else if (!plane->state && plane->fb)
+		crtc_resp->fb_id = plane->fb->base.id;
 	else
 		crtc_resp->fb_id = 0;
 
-	if (crtc->primary->state) {
-		crtc_resp->x = crtc->primary->state->src_x >> 16;
-		crtc_resp->y = crtc->primary->state->src_y >> 16;
+	if (plane->state) {
+		crtc_resp->x = plane->state->src_x >> 16;
+		crtc_resp->y = plane->state->src_y >> 16;
 	}
-	drm_modeset_unlock(&crtc->primary->mutex);
+	drm_modeset_unlock(&plane->mutex);
 
 	drm_modeset_lock(&crtc->mutex, NULL);
 	if (crtc->state) {
 		if (crtc->state->enable) {
 			drm_mode_convert_to_umode(&crtc_resp->mode, &crtc->state->mode);
 			crtc_resp->mode_valid = 1;
-
 		} else {
 			crtc_resp->mode_valid = 0;
 		}
 	} else {
 		crtc_resp->x = crtc->x;
 		crtc_resp->y = crtc->y;
+
 		if (crtc->enabled) {
 			drm_mode_convert_to_umode(&crtc_resp->mode, &crtc->mode);
 			crtc_resp->mode_valid = 1;
@@ -446,6 +449,8 @@ int drm_mode_getcrtc(struct drm_device *dev,
 			crtc_resp->mode_valid = 0;
 		}
 	}
+	if (!file_priv->aspect_ratio_allowed)
+		crtc_resp->mode.flags &= ~DRM_MODE_FLAG_PIC_AR_MASK;
 	drm_modeset_unlock(&crtc->mutex);
 
 	return 0;
@@ -471,7 +476,7 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 
 	ret = crtc->funcs->set_config(set, ctx);
 	if (ret == 0) {
-		crtc->primary->crtc = crtc;
+		crtc->primary->crtc = fb ? crtc : NULL;
 		crtc->primary->fb = fb;
 	}
 
@@ -554,6 +559,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_mode_crtc *crtc_req = data;
 	struct drm_crtc *crtc;
+	struct drm_plane *plane;
 	struct drm_connector **connector_set = NULL, *connector;
 	struct drm_framebuffer *fb = NULL;
 	struct drm_display_mode *mode = NULL;
@@ -580,22 +586,33 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	}
 	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
+	plane = crtc->primary;
+
 	mutex_lock(&crtc->dev->mode_config.mutex);
 	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
 retry:
 	ret = drm_modeset_lock_all_ctx(crtc->dev, &ctx);
 	if (ret)
 		goto out;
+
 	if (crtc_req->mode_valid) {
 		/* If we have a mode we need a framebuffer. */
 		/* If we pass -1, set the mode with the currently bound fb */
 		if (crtc_req->fb_id == -1) {
-			if (!crtc->primary->fb) {
+			struct drm_framebuffer *old_fb;
+
+			if (plane->state)
+				old_fb = plane->state->fb;
+			else
+				old_fb = plane->fb;
+
+			if (!old_fb) {
 				DRM_DEBUG_KMS("CRTC doesn't have current FB\n");
 				ret = -EINVAL;
 				goto out;
 			}
-			fb = crtc->primary->fb;
+
+			fb = old_fb;
 			/* Make refcounting symmetric with the lookup path. */
 			drm_framebuffer_get(fb);
 		} else {
@@ -613,6 +630,13 @@ retry:
 			ret = -ENOMEM;
 			goto out;
 		}
+		if (!file_priv->aspect_ratio_allowed &&
+		    (crtc_req->mode.flags & DRM_MODE_FLAG_PIC_AR_MASK) != DRM_MODE_FLAG_PIC_AR_NONE) {
+			DRM_DEBUG_KMS("Unexpected aspect-ratio flag bits\n");
+			ret = -EINVAL;
+			goto out;
+		}
+
 
 		ret = drm_mode_convert_umode(dev, mode, &crtc_req->mode);
 		if (ret) {
@@ -627,8 +651,8 @@ retry:
 		 * match real hardware capabilities. Skip the check in that
 		 * case.
 		 */
-		if (!crtc->primary->format_default) {
-			ret = drm_plane_check_pixel_format(crtc->primary,
+		if (!plane->format_default) {
+			ret = drm_plane_check_pixel_format(plane,
 							   fb->format->format,
 							   fb->modifier);
 			if (ret) {
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index 3c2b82865ad2..5d307b23a4e6 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -220,3 +220,5 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 
 /* drm_edid.c */
 void drm_mode_fixup_1366x768(struct drm_display_mode *mode);
+void drm_reset_display_info(struct drm_connector *connector);
+u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edid);
diff --git a/drivers/gpu/drm/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/drm_dp_dual_mode_helper.c
index 02a50929af67..e7f4fe2848a5 100644
--- a/drivers/gpu/drm/drm_dp_dual_mode_helper.c
+++ b/drivers/gpu/drm/drm_dp_dual_mode_helper.c
@@ -350,19 +350,44 @@ int drm_dp_dual_mode_set_tmds_output(enum drm_dp_dual_mode_type type,
 {
 	uint8_t tmds_oen = enable ? 0 : DP_DUAL_MODE_TMDS_DISABLE;
 	ssize_t ret;
+	int retry;
 
 	if (type < DRM_DP_DUAL_MODE_TYPE2_DVI)
 		return 0;
 
-	ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN,
-				     &tmds_oen, sizeof(tmds_oen));
-	if (ret) {
-		DRM_DEBUG_KMS("Failed to %s TMDS output buffers\n",
-			      enable ? "enable" : "disable");
-		return ret;
+	/*
+	 * LSPCON adapters in low-power state may ignore the first write, so
+	 * read back and verify the written value a few times.
+	 */
+	for (retry = 0; retry < 3; retry++) {
+		uint8_t tmp;
+
+		ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN,
+					     &tmds_oen, sizeof(tmds_oen));
+		if (ret) {
+			DRM_DEBUG_KMS("Failed to %s TMDS output buffers (%d attempts)\n",
+				      enable ? "enable" : "disable",
+				      retry + 1);
+			return ret;
+		}
+
+		ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_TMDS_OEN,
+					    &tmp, sizeof(tmp));
+		if (ret) {
+			DRM_DEBUG_KMS("I2C read failed during TMDS output buffer %s (%d attempts)\n",
+				      enable ? "enabling" : "disabling",
+				      retry + 1);
+			return ret;
+		}
+
+		if (tmp == tmds_oen)
+			return 0;
 	}
 
-	return 0;
+	DRM_DEBUG_KMS("I2C write value mismatch during TMDS output buffer %s\n",
+		      enable ? "enabling" : "disabling");
+
+	return -EIO;
 }
 EXPORT_SYMBOL(drm_dp_dual_mode_set_tmds_output);
 
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index ffe14ec3e7f2..a7ba602a43a8 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -119,18 +119,32 @@ u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SI
 EXPORT_SYMBOL(drm_dp_get_adjust_request_pre_emphasis);
 
 void drm_dp_link_train_clock_recovery_delay(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
-	if (dpcd[DP_TRAINING_AUX_RD_INTERVAL] == 0)
+	int rd_interval = dpcd[DP_TRAINING_AUX_RD_INTERVAL] &
+			  DP_TRAINING_AUX_RD_MASK;
+
+	if (rd_interval > 4)
+		DRM_DEBUG_KMS("AUX interval %d, out of range (max 4)\n",
+			      rd_interval);
+
+	if (rd_interval == 0 || dpcd[DP_DPCD_REV] >= DP_DPCD_REV_14)
 		udelay(100);
 	else
-		mdelay(dpcd[DP_TRAINING_AUX_RD_INTERVAL] * 4);
+		mdelay(rd_interval * 4);
 }
 EXPORT_SYMBOL(drm_dp_link_train_clock_recovery_delay);
 
 void drm_dp_link_train_channel_eq_delay(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
-	if (dpcd[DP_TRAINING_AUX_RD_INTERVAL] == 0)
+	int rd_interval = dpcd[DP_TRAINING_AUX_RD_INTERVAL] &
+			  DP_TRAINING_AUX_RD_MASK;
+
+	if (rd_interval > 4)
+		DRM_DEBUG_KMS("AUX interval %d, out of range (max 4)\n",
+			      rd_interval);
+
+	if (rd_interval == 0)
 		udelay(400);
 	else
-		mdelay(dpcd[DP_TRAINING_AUX_RD_INTERVAL] * 4);
+		mdelay(rd_interval * 4);
 }
 EXPORT_SYMBOL(drm_dp_link_train_channel_eq_delay);
 
@@ -1145,6 +1159,7 @@ int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE])
 	static const u16 psr_setup_time_us[] = {
 		PSR_SETUP_TIME(330),
 		PSR_SETUP_TIME(275),
+		PSR_SETUP_TIME(220),
 		PSR_SETUP_TIME(165),
 		PSR_SETUP_TIME(110),
 		PSR_SETUP_TIME(55),
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 6fac4129e6a2..658830620ca3 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -2941,12 +2941,14 @@ static void drm_dp_mst_dump_mstb(struct seq_file *m,
 	}
 }
 
+#define DP_PAYLOAD_TABLE_SIZE		64
+
 static bool dump_dp_payload_table(struct drm_dp_mst_topology_mgr *mgr,
 				  char *buf)
 {
 	int i;
 
-	for (i = 0; i < 64; i += 16) {
+	for (i = 0; i < DP_PAYLOAD_TABLE_SIZE; i += 16) {
 		if (drm_dp_dpcd_read(mgr->aux,
 				     DP_PAYLOAD_TABLE_UPDATE_STATUS + i,
 				     &buf[i], 16) != 16)
@@ -3015,7 +3017,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 
 	mutex_lock(&mgr->lock);
 	if (mgr->mst_primary) {
-		u8 buf[64];
+		u8 buf[DP_PAYLOAD_TABLE_SIZE];
 		int ret;
 
 		ret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, buf, DP_RECEIVER_CAP_SIZE);
@@ -3033,8 +3035,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 		seq_printf(m, " revision: hw: %x.%x sw: %x.%x\n",
 			   buf[0x9] >> 4, buf[0x9] & 0xf, buf[0xa], buf[0xb]);
 		if (dump_dp_payload_table(mgr, buf))
-			seq_printf(m, "payload table: %*ph\n", 63, buf);
-
+			seq_printf(m, "payload table: %*ph\n", DP_PAYLOAD_TABLE_SIZE, buf);
 	}
 
 	mutex_unlock(&mgr->lock);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index a1b9338736e3..b553a6f2ff0e 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -32,6 +32,7 @@
 #include <linux/moduleparam.h>
 #include <linux/mount.h>
 #include <linux/slab.h>
+#include <linux/srcu.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drmP.h>
@@ -75,6 +76,8 @@ static bool drm_core_init_complete = false;
 
 static struct dentry *drm_debugfs_root;
 
+DEFINE_STATIC_SRCU(drm_unplug_srcu);
+
 /*
  * DRM Minors
  * A DRM device can provide several char-dev interfaces on the DRM-Major. Each
@@ -96,8 +99,6 @@ static struct drm_minor **drm_minor_get_slot(struct drm_device *dev,
 		return &dev->primary;
 	case DRM_MINOR_RENDER:
 		return &dev->render;
-	case DRM_MINOR_CONTROL:
-		return &dev->control;
 	default:
 		BUG();
 	}
@@ -318,18 +319,51 @@ void drm_put_dev(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_put_dev);
 
-static void drm_device_set_unplugged(struct drm_device *dev)
+/**
+ * drm_dev_enter - Enter device critical section
+ * @dev: DRM device
+ * @idx: Pointer to index that will be passed to the matching drm_dev_exit()
+ *
+ * This function marks and protects the beginning of a section that should not
+ * be entered after the device has been unplugged. The section end is marked
+ * with drm_dev_exit(). Calls to this function can be nested.
+ *
+ * Returns:
+ * True if it is OK to enter the section, false otherwise.
+ */
+bool drm_dev_enter(struct drm_device *dev, int *idx)
+{
+	*idx = srcu_read_lock(&drm_unplug_srcu);
+
+	if (dev->unplugged) {
+		srcu_read_unlock(&drm_unplug_srcu, *idx);
+		return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(drm_dev_enter);
+
+/**
+ * drm_dev_exit - Exit device critical section
+ * @idx: index returned from drm_dev_enter()
+ *
+ * This function marks the end of a section that should not be entered after
+ * the device has been unplugged.
+ */
+void drm_dev_exit(int idx)
 {
-	smp_wmb();
-	atomic_set(&dev->unplugged, 1);
+	srcu_read_unlock(&drm_unplug_srcu, idx);
 }
+EXPORT_SYMBOL(drm_dev_exit);
 
 /**
  * drm_dev_unplug - unplug a DRM device
  * @dev: DRM device
  *
  * This unplugs a hotpluggable DRM device, which makes it inaccessible to
- * userspace operations. Entry-points can use drm_dev_is_unplugged(). This
+ * userspace operations. Entry-points can use drm_dev_enter() and
+ * drm_dev_exit() to protect device resources in a race free manner. This
  * essentially unregisters the device like drm_dev_unregister(), but can be
  * called while there are still open users of @dev.
  */
@@ -338,10 +372,18 @@ void drm_dev_unplug(struct drm_device *dev)
 	drm_dev_unregister(dev);
 
 	mutex_lock(&drm_global_mutex);
-	drm_device_set_unplugged(dev);
 	if (dev->open_count == 0)
 		drm_dev_put(dev);
 	mutex_unlock(&drm_global_mutex);
+
+	/*
+	 * After synchronizing any critical read section is guaranteed to see
+	 * the new value of ->unplugged, and any critical section which might
+	 * still have seen the old value of ->unplugged is guaranteed to have
+	 * finished.
+	 */
+	dev->unplugged = true;
+	synchronize_srcu(&drm_unplug_srcu);
 }
 EXPORT_SYMBOL(drm_dev_unplug);
 
@@ -523,7 +565,6 @@ err_ctxbitmap:
 err_minors:
 	drm_minor_free(dev, DRM_MINOR_PRIMARY);
 	drm_minor_free(dev, DRM_MINOR_RENDER);
-	drm_minor_free(dev, DRM_MINOR_CONTROL);
 	drm_fs_inode_free(dev->anon_inode);
 err_free:
 	mutex_destroy(&dev->master_mutex);
@@ -559,7 +600,6 @@ void drm_dev_fini(struct drm_device *dev)
 
 	drm_minor_free(dev, DRM_MINOR_PRIMARY);
 	drm_minor_free(dev, DRM_MINOR_RENDER);
-	drm_minor_free(dev, DRM_MINOR_CONTROL);
 
 	mutex_destroy(&dev->master_mutex);
 	mutex_destroy(&dev->ctxlist_mutex);
@@ -716,7 +756,7 @@ static void remove_compat_control_link(struct drm_device *dev)
 	if (!minor)
 		return;
 
-	name = kasprintf(GFP_KERNEL, "controlD%d", minor->index);
+	name = kasprintf(GFP_KERNEL, "controlD%d", minor->index + 64);
 	if (!name)
 		return;
 
@@ -752,10 +792,6 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags)
 
 	mutex_lock(&drm_global_mutex);
 
-	ret = drm_minor_register(dev, DRM_MINOR_CONTROL);
-	if (ret)
-		goto err_minors;
-
 	ret = drm_minor_register(dev, DRM_MINOR_RENDER);
 	if (ret)
 		goto err_minors;
@@ -793,7 +829,6 @@ err_minors:
 	remove_compat_control_link(dev);
 	drm_minor_unregister(dev, DRM_MINOR_PRIMARY);
 	drm_minor_unregister(dev, DRM_MINOR_RENDER);
-	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 out_unlock:
 	mutex_unlock(&drm_global_mutex);
 	return ret;
@@ -838,7 +873,6 @@ void drm_dev_unregister(struct drm_device *dev)
 	remove_compat_control_link(dev);
 	drm_minor_unregister(dev, DRM_MINOR_PRIMARY);
 	drm_minor_unregister(dev, DRM_MINOR_RENDER);
-	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 }
 EXPORT_SYMBOL(drm_dev_unregister);
 
diff --git a/drivers/gpu/drm/drm_dumb_buffers.c b/drivers/gpu/drm/drm_dumb_buffers.c
index 39ac15ce4702..9e2ae02f31e0 100644
--- a/drivers/gpu/drm/drm_dumb_buffers.c
+++ b/drivers/gpu/drm/drm_dumb_buffers.c
@@ -65,12 +65,13 @@ int drm_mode_create_dumb_ioctl(struct drm_device *dev,
 		return -EINVAL;
 
 	/* overflow checks for 32bit size calculations */
-	/* NOTE: DIV_ROUND_UP() can overflow */
+	if (args->bpp > U32_MAX - 8)
+		return -EINVAL;
 	cpp = DIV_ROUND_UP(args->bpp, 8);
-	if (!cpp || cpp > 0xffffffffU / args->width)
+	if (cpp > U32_MAX / args->width)
 		return -EINVAL;
 	stride = cpp * args->width;
-	if (args->height > 0xffffffffU / stride)
+	if (args->height > U32_MAX / stride)
 		return -EINVAL;
 
 	/* test for wrap-around */
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 134069f36482..40e1e24f2ff0 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -2930,11 +2930,15 @@ cea_mode_alternate_timings(u8 vic, struct drm_display_mode *mode)
 static u8 drm_match_cea_mode_clock_tolerance(const struct drm_display_mode *to_match,
 					     unsigned int clock_tolerance)
 {
+	unsigned int match_flags = DRM_MODE_MATCH_TIMINGS | DRM_MODE_MATCH_FLAGS;
 	u8 vic;
 
 	if (!to_match->clock)
 		return 0;
 
+	if (to_match->picture_aspect_ratio)
+		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
+
 	for (vic = 1; vic < ARRAY_SIZE(edid_cea_modes); vic++) {
 		struct drm_display_mode cea_mode = edid_cea_modes[vic];
 		unsigned int clock1, clock2;
@@ -2948,7 +2952,7 @@ static u8 drm_match_cea_mode_clock_tolerance(const struct drm_display_mode *to_m
 			continue;
 
 		do {
-			if (drm_mode_equal_no_clocks_no_stereo(to_match, &cea_mode))
+			if (drm_mode_match(to_match, &cea_mode, match_flags))
 				return vic;
 		} while (cea_mode_alternate_timings(vic, &cea_mode));
 	}
@@ -2965,11 +2969,15 @@ static u8 drm_match_cea_mode_clock_tolerance(const struct drm_display_mode *to_m
  */
 u8 drm_match_cea_mode(const struct drm_display_mode *to_match)
 {
+	unsigned int match_flags = DRM_MODE_MATCH_TIMINGS | DRM_MODE_MATCH_FLAGS;
 	u8 vic;
 
 	if (!to_match->clock)
 		return 0;
 
+	if (to_match->picture_aspect_ratio)
+		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
+
 	for (vic = 1; vic < ARRAY_SIZE(edid_cea_modes); vic++) {
 		struct drm_display_mode cea_mode = edid_cea_modes[vic];
 		unsigned int clock1, clock2;
@@ -2983,7 +2991,7 @@ u8 drm_match_cea_mode(const struct drm_display_mode *to_match)
 			continue;
 
 		do {
-			if (drm_mode_equal_no_clocks_no_stereo(to_match, &cea_mode))
+			if (drm_mode_match(to_match, &cea_mode, match_flags))
 				return vic;
 		} while (cea_mode_alternate_timings(vic, &cea_mode));
 	}
@@ -3030,6 +3038,7 @@ hdmi_mode_alternate_clock(const struct drm_display_mode *hdmi_mode)
 static u8 drm_match_hdmi_mode_clock_tolerance(const struct drm_display_mode *to_match,
 					      unsigned int clock_tolerance)
 {
+	unsigned int match_flags = DRM_MODE_MATCH_TIMINGS | DRM_MODE_MATCH_FLAGS;
 	u8 vic;
 
 	if (!to_match->clock)
@@ -3047,7 +3056,7 @@ static u8 drm_match_hdmi_mode_clock_tolerance(const struct drm_display_mode *to_
 		    abs(to_match->clock - clock2) > clock_tolerance)
 			continue;
 
-		if (drm_mode_equal_no_clocks(to_match, hdmi_mode))
+		if (drm_mode_match(to_match, hdmi_mode, match_flags))
 			return vic;
 	}
 
@@ -3064,6 +3073,7 @@ static u8 drm_match_hdmi_mode_clock_tolerance(const struct drm_display_mode *to_
  */
 static u8 drm_match_hdmi_mode(const struct drm_display_mode *to_match)
 {
+	unsigned int match_flags = DRM_MODE_MATCH_TIMINGS | DRM_MODE_MATCH_FLAGS;
 	u8 vic;
 
 	if (!to_match->clock)
@@ -3079,7 +3089,7 @@ static u8 drm_match_hdmi_mode(const struct drm_display_mode *to_match)
 
 		if ((KHZ2PICOS(to_match->clock) == KHZ2PICOS(clock1) ||
 		     KHZ2PICOS(to_match->clock) == KHZ2PICOS(clock2)) &&
-		    drm_mode_equal_no_clocks_no_stereo(to_match, hdmi_mode))
+		    drm_mode_match(to_match, hdmi_mode, match_flags))
 			return vic;
 	}
 	return 0;
@@ -4451,10 +4461,10 @@ drm_reset_display_info(struct drm_connector *connector)
 	info->max_tmds_clock = 0;
 	info->dvi_dual = false;
 	info->has_hdmi_infoframe = false;
+	memset(&info->hdmi, 0, sizeof(info->hdmi));
 
 	info->non_desktop = 0;
 }
-EXPORT_SYMBOL_GPL(drm_reset_display_info);
 
 u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edid)
 {
@@ -4462,17 +4472,11 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi
 
 	u32 quirks = edid_get_quirks(edid);
 
+	drm_reset_display_info(connector);
+
 	info->width_mm = edid->width_cm * 10;
 	info->height_mm = edid->height_cm * 10;
 
-	/* driver figures it out in this case */
-	info->bpc = 0;
-	info->color_formats = 0;
-	info->cea_rev = 0;
-	info->max_tmds_clock = 0;
-	info->dvi_dual = false;
-	info->has_hdmi_infoframe = false;
-
 	info->non_desktop = !!(quirks & EDID_QUIRK_NON_DESKTOP);
 
 	DRM_DEBUG_KMS("non_desktop set to %d\n", info->non_desktop);
@@ -4538,7 +4542,6 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi
 		info->color_formats |= DRM_COLOR_FORMAT_YCRCB422;
 	return quirks;
 }
-EXPORT_SYMBOL_GPL(drm_add_display_info);
 
 static int validate_displayid(u8 *displayid, int length, int idx)
 {
@@ -4830,6 +4833,7 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 					 const struct drm_display_mode *mode,
 					 bool is_hdmi2_sink)
 {
+	enum hdmi_picture_aspect picture_aspect;
 	int err;
 
 	if (!frame || !mode)
@@ -4872,13 +4876,23 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	 * Populate picture aspect ratio from either
 	 * user input (if specified) or from the CEA mode list.
 	 */
-	if (mode->picture_aspect_ratio == HDMI_PICTURE_ASPECT_4_3 ||
-		mode->picture_aspect_ratio == HDMI_PICTURE_ASPECT_16_9)
-		frame->picture_aspect = mode->picture_aspect_ratio;
-	else if (frame->video_code > 0)
-		frame->picture_aspect = drm_get_cea_aspect_ratio(
-						frame->video_code);
+	picture_aspect = mode->picture_aspect_ratio;
+	if (picture_aspect == HDMI_PICTURE_ASPECT_NONE)
+		picture_aspect = drm_get_cea_aspect_ratio(frame->video_code);
+
+	/*
+	 * The infoframe can't convey anything but none, 4:3
+	 * and 16:9, so if the user has asked for anything else
+	 * we can only satisfy it by specifying the right VIC.
+	 */
+	if (picture_aspect > HDMI_PICTURE_ASPECT_16_9) {
+		if (picture_aspect !=
+		    drm_get_cea_aspect_ratio(frame->video_code))
+			return -EINVAL;
+		picture_aspect = HDMI_PICTURE_ASPECT_NONE;
+	}
 
+	frame->picture_aspect = picture_aspect;
 	frame->active_aspect = HDMI_ACTIVE_ASPECT_PICTURE;
 	frame->scan_mode = HDMI_SCAN_MODE_UNDERSCAN;
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 0646b108030b..2ee1eaa66188 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -2183,7 +2183,11 @@ static bool drm_target_cloned(struct drm_fb_helper *fb_helper,
 		for (j = 0; j < i; j++) {
 			if (!enabled[j])
 				continue;
-			if (!drm_mode_equal(modes[j], modes[i]))
+			if (!drm_mode_match(modes[j], modes[i],
+					    DRM_MODE_MATCH_TIMINGS |
+					    DRM_MODE_MATCH_CLOCK |
+					    DRM_MODE_MATCH_FLAGS |
+					    DRM_MODE_MATCH_3D_FLAGS))
 				can_clone = false;
 		}
 	}
@@ -2203,7 +2207,11 @@ static bool drm_target_cloned(struct drm_fb_helper *fb_helper,
 
 		fb_helper_conn = fb_helper->connector_info[i];
 		list_for_each_entry(mode, &fb_helper_conn->connector->modes, head) {
-			if (drm_mode_equal(mode, dmt_mode))
+			if (drm_mode_match(mode, dmt_mode,
+					   DRM_MODE_MATCH_TIMINGS |
+					   DRM_MODE_MATCH_CLOCK |
+					   DRM_MODE_MATCH_FLAGS |
+					   DRM_MODE_MATCH_3D_FLAGS))
 				modes[i] = mode;
 		}
 		if (!modes[i])
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index e394799979a6..6d9b9453707c 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -212,6 +212,7 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 		return -ENOMEM;
 
 	filp->private_data = priv;
+	filp->f_mode |= FMODE_UNSIGNED_OFFSET;
 	priv->filp = filp;
 	priv->pid = get_pid(task_pid(current));
 	priv->minor = minor;
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index ad67203de715..bfedceff87bb 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -468,29 +468,30 @@ int drm_mode_getfb(struct drm_device *dev,
 		goto out;
 	}
 
+	if (!fb->funcs->create_handle) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	r->height = fb->height;
 	r->width = fb->width;
 	r->depth = fb->format->depth;
 	r->bpp = fb->format->cpp[0] * 8;
 	r->pitch = fb->pitches[0];
-	if (fb->funcs->create_handle) {
-		if (drm_is_current_master(file_priv) || capable(CAP_SYS_ADMIN) ||
-		    drm_is_control_client(file_priv)) {
-			ret = fb->funcs->create_handle(fb, file_priv,
-						       &r->handle);
-		} else {
-			/* GET_FB() is an unprivileged ioctl so we must not
-			 * return a buffer-handle to non-master processes! For
-			 * backwards-compatibility reasons, we cannot make
-			 * GET_FB() privileged, so just return an invalid handle
-			 * for non-masters. */
-			r->handle = 0;
-			ret = 0;
-		}
-	} else {
-		ret = -ENODEV;
+
+	/* GET_FB() is an unprivileged ioctl so we must not return a
+	 * buffer-handle to non-master processes! For
+	 * backwards-compatibility reasons, we cannot make GET_FB() privileged,
+	 * so just return an invalid handle for non-masters.
+	 */
+	if (!drm_is_current_master(file_priv) && !capable(CAP_SYS_ADMIN)) {
+		r->handle = 0;
+		ret = 0;
+		goto out;
 	}
 
+	ret = fb->funcs->create_handle(fb, file_priv, &r->handle);
+
 out:
 	drm_framebuffer_put(fb);
 
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 4975ba9a7bc8..4a16d7b26c89 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -436,9 +436,12 @@ err_unref:
  * @obj: object to register
  * @handlep: pionter to return the created handle to the caller
  *
- * Create a handle for this object. This adds a handle reference
- * to the object, which includes a regular reference count. Callers
- * will likely want to dereference the object afterwards.
+ * Create a handle for this object. This adds a handle reference to the object,
+ * which includes a regular reference count. Callers will likely want to
+ * dereference the object afterwards.
+ *
+ * Since this publishes @obj to userspace it must be fully set up by this point,
+ * drivers must call this last in their buffer object creation callbacks.
  */
 int drm_gem_handle_create(struct drm_file *file_priv,
 			  struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
index 4d682a6e8bcb..acfbc0641a06 100644
--- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c
+++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
@@ -22,6 +22,7 @@
 #include <drm/drm_gem.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_modeset_helper.h>
+#include <drm/drm_simple_kms_helper.h>
 
 /**
  * DOC: overview
@@ -266,6 +267,24 @@ int drm_gem_fb_prepare_fb(struct drm_plane *plane,
 EXPORT_SYMBOL_GPL(drm_gem_fb_prepare_fb);
 
 /**
+ * drm_gem_fb_simple_display_pipe_prepare_fb - prepare_fb helper for
+ *     &drm_simple_display_pipe
+ * @pipe: Simple display pipe
+ * @plane_state: Plane state
+ *
+ * This function uses drm_gem_fb_prepare_fb() to check if the plane FB has a
+ * &dma_buf attached, extracts the exclusive fence and attaches it to plane
+ * state for the atomic helper to wait on. Drivers can use this as their
+ * &drm_simple_display_pipe_funcs.prepare_fb callback.
+ */
+int drm_gem_fb_simple_display_pipe_prepare_fb(struct drm_simple_display_pipe *pipe,
+					      struct drm_plane_state *plane_state)
+{
+	return drm_gem_fb_prepare_fb(&pipe->plane, plane_state);
+}
+EXPORT_SYMBOL(drm_gem_fb_simple_display_pipe_prepare_fb);
+
+/**
  * drm_gem_fbdev_fb_create - Create a GEM backed &drm_framebuffer for fbdev
  *                           emulation
  * @dev: DRM device
diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index f8e96e648acf..67b1fca39aa6 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -105,7 +105,7 @@ static int compat_drm_version(struct file *file, unsigned int cmd,
 		.desc = compat_ptr(v32.desc),
 	};
 	err = drm_ioctl_kernel(file, drm_version, &v,
-			DRM_UNLOCKED|DRM_RENDER_ALLOW|DRM_CONTROL_ALLOW);
+			       DRM_UNLOCKED|DRM_RENDER_ALLOW);
 	if (err)
 		return err;
 
@@ -885,7 +885,7 @@ static int compat_drm_mode_addfb2(struct file *file, unsigned int cmd,
 		return -EFAULT;
 
 	err = drm_ioctl_kernel(file, drm_mode_addfb2, &req64,
-				DRM_CONTROL_ALLOW|DRM_UNLOCKED);
+			       DRM_UNLOCKED);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index af782911c505..0d4cfb232576 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -324,6 +324,15 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 			return -EINVAL;
 		file_priv->atomic = req->value;
 		file_priv->universal_planes = req->value;
+		/*
+		 * No atomic user-space blows up on aspect ratio mode bits.
+		 */
+		file_priv->aspect_ratio_allowed = req->value;
+		break;
+	case DRM_CLIENT_CAP_ASPECT_RATIO:
+		if (req->value > 1)
+			return -EINVAL;
+		file_priv->aspect_ratio_allowed = req->value;
 		break;
 	default:
 		return -EINVAL;
@@ -510,13 +519,7 @@ int drm_ioctl_permit(u32 flags, struct drm_file *file_priv)
 
 	/* MASTER is only for master or control clients */
 	if (unlikely((flags & DRM_MASTER) &&
-		     !drm_is_current_master(file_priv) &&
-		     !drm_is_control_client(file_priv)))
-		return -EACCES;
-
-	/* Control clients must be explicitly allowed */
-	if (unlikely(!(flags & DRM_CONTROL_ALLOW) &&
-		     drm_is_control_client(file_priv)))
+		     !drm_is_current_master(file_priv)))
 		return -EACCES;
 
 	/* Render clients must be explicitly allowed */
@@ -539,7 +542,7 @@ EXPORT_SYMBOL(drm_ioctl_permit);
 /* Ioctl table */
 static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version,
-		      DRM_UNLOCKED|DRM_RENDER_ALLOW|DRM_CONTROL_ALLOW),
+		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
@@ -613,41 +616,41 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH|DRM_UNLOCKED),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_UNLOCKED),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANE, drm_mode_getplane, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPLANE, drm_mode_setplane, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR, drm_mode_cursor_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANE, drm_mode_getplane, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPLANE, drm_mode_setplane, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR, drm_mode_cursor_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETGAMMA, drm_mode_gamma_get_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETGAMMA, drm_mode_gamma_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETENCODER, drm_mode_getencoder, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCONNECTOR, drm_mode_getconnector, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_MAP_DUMB, drm_mode_mmap_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROY_DUMB, drm_mode_destroy_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_GETPROPERTIES, drm_mode_obj_get_properties_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_SETPROPERTY, drm_mode_obj_set_property_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR2, drm_mode_cursor2_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATOMIC, drm_mode_atomic_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATEPROPBLOB, drm_mode_createblob_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROYPROPBLOB, drm_mode_destroyblob_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETENCODER, drm_mode_getencoder, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCONNECTOR, drm_mode_getconnector, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_MAP_DUMB, drm_mode_mmap_dumb_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROY_DUMB, drm_mode_destroy_dumb_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_GETPROPERTIES, drm_mode_obj_get_properties_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_SETPROPERTY, drm_mode_obj_set_property_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR2, drm_mode_cursor2_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATOMIC, drm_mode_atomic_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATEPROPBLOB, drm_mode_createblob_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROYPROPBLOB, drm_mode_destroyblob_ioctl, DRM_UNLOCKED),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_CREATE, drm_syncobj_create_ioctl,
 		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
@@ -665,10 +668,10 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE, drm_crtc_queue_sequence_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_LIST_LESSEES, drm_mode_list_lessees_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GET_LEASE, drm_mode_get_lease_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_REVOKE_LEASE, drm_mode_revoke_lease_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_LIST_LESSEES, drm_mode_list_lessees_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GET_LEASE, drm_mode_get_lease_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_REVOKE_LEASE, drm_mode_revoke_lease_ioctl, DRM_MASTER|DRM_UNLOCKED),
 };
 
 #define DRM_CORE_IOCTL_COUNT	ARRAY_SIZE( drm_ioctls )
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index d345563fdff3..50c73c0a20b9 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -340,7 +340,7 @@ static void _drm_lease_revoke(struct drm_master *top)
 				break;
 
 			/* Over */
-			master = list_entry(master->lessee_list.next, struct drm_master, lessee_list);
+			master = list_next_entry(master, lessee_list);
 		}
 	}
 }
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index e82b61e08f8c..c78ca0e84ffd 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -939,17 +939,68 @@ struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_mode_duplicate);
 
+static bool drm_mode_match_timings(const struct drm_display_mode *mode1,
+				   const struct drm_display_mode *mode2)
+{
+	return mode1->hdisplay == mode2->hdisplay &&
+		mode1->hsync_start == mode2->hsync_start &&
+		mode1->hsync_end == mode2->hsync_end &&
+		mode1->htotal == mode2->htotal &&
+		mode1->hskew == mode2->hskew &&
+		mode1->vdisplay == mode2->vdisplay &&
+		mode1->vsync_start == mode2->vsync_start &&
+		mode1->vsync_end == mode2->vsync_end &&
+		mode1->vtotal == mode2->vtotal &&
+		mode1->vscan == mode2->vscan;
+}
+
+static bool drm_mode_match_clock(const struct drm_display_mode *mode1,
+				  const struct drm_display_mode *mode2)
+{
+	/*
+	 * do clock check convert to PICOS
+	 * so fb modes get matched the same
+	 */
+	if (mode1->clock && mode2->clock)
+		return KHZ2PICOS(mode1->clock) == KHZ2PICOS(mode2->clock);
+	else
+		return mode1->clock == mode2->clock;
+}
+
+static bool drm_mode_match_flags(const struct drm_display_mode *mode1,
+				 const struct drm_display_mode *mode2)
+{
+	return (mode1->flags & ~DRM_MODE_FLAG_3D_MASK) ==
+		(mode2->flags & ~DRM_MODE_FLAG_3D_MASK);
+}
+
+static bool drm_mode_match_3d_flags(const struct drm_display_mode *mode1,
+				    const struct drm_display_mode *mode2)
+{
+	return (mode1->flags & DRM_MODE_FLAG_3D_MASK) ==
+		(mode2->flags & DRM_MODE_FLAG_3D_MASK);
+}
+
+static bool drm_mode_match_aspect_ratio(const struct drm_display_mode *mode1,
+					const struct drm_display_mode *mode2)
+{
+	return mode1->picture_aspect_ratio == mode2->picture_aspect_ratio;
+}
+
 /**
- * drm_mode_equal - test modes for equality
+ * drm_mode_match - test modes for (partial) equality
  * @mode1: first mode
  * @mode2: second mode
+ * @match_flags: which parts need to match (DRM_MODE_MATCH_*)
  *
  * Check to see if @mode1 and @mode2 are equivalent.
  *
  * Returns:
- * True if the modes are equal, false otherwise.
+ * True if the modes are (partially) equal, false otherwise.
  */
-bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2)
+bool drm_mode_match(const struct drm_display_mode *mode1,
+		    const struct drm_display_mode *mode2,
+		    unsigned int match_flags)
 {
 	if (!mode1 && !mode2)
 		return true;
@@ -957,15 +1008,49 @@ bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_displ
 	if (!mode1 || !mode2)
 		return false;
 
-	/* do clock check convert to PICOS so fb modes get matched
-	 * the same */
-	if (mode1->clock && mode2->clock) {
-		if (KHZ2PICOS(mode1->clock) != KHZ2PICOS(mode2->clock))
-			return false;
-	} else if (mode1->clock != mode2->clock)
+	if (match_flags & DRM_MODE_MATCH_TIMINGS &&
+	    !drm_mode_match_timings(mode1, mode2))
+		return false;
+
+	if (match_flags & DRM_MODE_MATCH_CLOCK &&
+	    !drm_mode_match_clock(mode1, mode2))
+		return false;
+
+	if (match_flags & DRM_MODE_MATCH_FLAGS &&
+	    !drm_mode_match_flags(mode1, mode2))
+		return false;
+
+	if (match_flags & DRM_MODE_MATCH_3D_FLAGS &&
+	    !drm_mode_match_3d_flags(mode1, mode2))
 		return false;
 
-	return drm_mode_equal_no_clocks(mode1, mode2);
+	if (match_flags & DRM_MODE_MATCH_ASPECT_RATIO &&
+	    !drm_mode_match_aspect_ratio(mode1, mode2))
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL(drm_mode_match);
+
+/**
+ * drm_mode_equal - test modes for equality
+ * @mode1: first mode
+ * @mode2: second mode
+ *
+ * Check to see if @mode1 and @mode2 are equivalent.
+ *
+ * Returns:
+ * True if the modes are equal, false otherwise.
+ */
+bool drm_mode_equal(const struct drm_display_mode *mode1,
+		    const struct drm_display_mode *mode2)
+{
+	return drm_mode_match(mode1, mode2,
+			      DRM_MODE_MATCH_TIMINGS |
+			      DRM_MODE_MATCH_CLOCK |
+			      DRM_MODE_MATCH_FLAGS |
+			      DRM_MODE_MATCH_3D_FLAGS|
+			      DRM_MODE_MATCH_ASPECT_RATIO);
 }
 EXPORT_SYMBOL(drm_mode_equal);
 
@@ -980,13 +1065,13 @@ EXPORT_SYMBOL(drm_mode_equal);
  * Returns:
  * True if the modes are equal, false otherwise.
  */
-bool drm_mode_equal_no_clocks(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2)
+bool drm_mode_equal_no_clocks(const struct drm_display_mode *mode1,
+			      const struct drm_display_mode *mode2)
 {
-	if ((mode1->flags & DRM_MODE_FLAG_3D_MASK) !=
-	    (mode2->flags & DRM_MODE_FLAG_3D_MASK))
-		return false;
-
-	return drm_mode_equal_no_clocks_no_stereo(mode1, mode2);
+	return drm_mode_match(mode1, mode2,
+			      DRM_MODE_MATCH_TIMINGS |
+			      DRM_MODE_MATCH_FLAGS |
+			      DRM_MODE_MATCH_3D_FLAGS);
 }
 EXPORT_SYMBOL(drm_mode_equal_no_clocks);
 
@@ -1004,21 +1089,9 @@ EXPORT_SYMBOL(drm_mode_equal_no_clocks);
 bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1,
 					const struct drm_display_mode *mode2)
 {
-	if (mode1->hdisplay == mode2->hdisplay &&
-	    mode1->hsync_start == mode2->hsync_start &&
-	    mode1->hsync_end == mode2->hsync_end &&
-	    mode1->htotal == mode2->htotal &&
-	    mode1->hskew == mode2->hskew &&
-	    mode1->vdisplay == mode2->vdisplay &&
-	    mode1->vsync_start == mode2->vsync_start &&
-	    mode1->vsync_end == mode2->vsync_end &&
-	    mode1->vtotal == mode2->vtotal &&
-	    mode1->vscan == mode2->vscan &&
-	    (mode1->flags & ~DRM_MODE_FLAG_3D_MASK) ==
-	     (mode2->flags & ~DRM_MODE_FLAG_3D_MASK))
-		return true;
-
-	return false;
+	return drm_mode_match(mode1, mode2,
+			      DRM_MODE_MATCH_TIMINGS |
+			      DRM_MODE_MATCH_FLAGS);
 }
 EXPORT_SYMBOL(drm_mode_equal_no_clocks_no_stereo);
 
@@ -1575,6 +1648,26 @@ void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out,
 	out->vrefresh = in->vrefresh;
 	out->flags = in->flags;
 	out->type = in->type;
+
+	switch (in->picture_aspect_ratio) {
+	case HDMI_PICTURE_ASPECT_4_3:
+		out->flags |= DRM_MODE_FLAG_PIC_AR_4_3;
+		break;
+	case HDMI_PICTURE_ASPECT_16_9:
+		out->flags |= DRM_MODE_FLAG_PIC_AR_16_9;
+		break;
+	case HDMI_PICTURE_ASPECT_64_27:
+		out->flags |= DRM_MODE_FLAG_PIC_AR_64_27;
+		break;
+	case HDMI_PICTURE_ASPECT_256_135:
+		out->flags |= DRM_MODE_FLAG_PIC_AR_256_135;
+		break;
+	case HDMI_PICTURE_ASPECT_RESERVED:
+	default:
+		out->flags |= DRM_MODE_FLAG_PIC_AR_NONE;
+		break;
+	}
+
 	strncpy(out->name, in->name, DRM_DISPLAY_MODE_LEN);
 	out->name[DRM_DISPLAY_MODE_LEN-1] = 0;
 }
@@ -1621,6 +1714,30 @@ int drm_mode_convert_umode(struct drm_device *dev,
 	strncpy(out->name, in->name, DRM_DISPLAY_MODE_LEN);
 	out->name[DRM_DISPLAY_MODE_LEN-1] = 0;
 
+	/* Clearing picture aspect ratio bits from out flags,
+	 * as the aspect-ratio information is not stored in
+	 * flags for kernel-mode, but in picture_aspect_ratio.
+	 */
+	out->flags &= ~DRM_MODE_FLAG_PIC_AR_MASK;
+
+	switch (in->flags & DRM_MODE_FLAG_PIC_AR_MASK) {
+	case DRM_MODE_FLAG_PIC_AR_4_3:
+		out->picture_aspect_ratio |= HDMI_PICTURE_ASPECT_4_3;
+		break;
+	case DRM_MODE_FLAG_PIC_AR_16_9:
+		out->picture_aspect_ratio |= HDMI_PICTURE_ASPECT_16_9;
+		break;
+	case DRM_MODE_FLAG_PIC_AR_64_27:
+		out->picture_aspect_ratio |= HDMI_PICTURE_ASPECT_64_27;
+		break;
+	case DRM_MODE_FLAG_PIC_AR_256_135:
+		out->picture_aspect_ratio |= HDMI_PICTURE_ASPECT_256_135;
+		break;
+	default:
+		out->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
+		break;
+	}
+
 	out->status = drm_mode_validate_driver(dev, out);
 	if (out->status != MODE_OK)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index 902cc1a71e45..fe9c6c731e87 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -60,7 +60,7 @@ static const struct drm_dmi_panel_orientation_data itworks_tw891 = {
 	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
 };
 
-static const struct drm_dmi_panel_orientation_data vios_lth17 = {
+static const struct drm_dmi_panel_orientation_data lcd800x1280_rightside_up = {
 	.width = 800,
 	.height = 1280,
 	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
@@ -102,12 +102,30 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_BOARD_NAME, "TW891"),
 		},
 		.driver_data = (void *)&itworks_tw891,
+	}, {	/*
+		 * Lenovo Ideapad Miix 310 laptop, only some production batches
+		 * have a portrait screen, the resolution checks makes the quirk
+		 * apply only to those batches.
+		 */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80SG"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* Lenovo Ideapad Miix 320 */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80XF"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 320-10ICR"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* VIOS LTH17 */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "VIOS"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "LTH17"),
 		},
-		.driver_data = (void *)&vios_lth17,
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	},
 	{}
 };
@@ -154,10 +172,9 @@ int drm_get_panel_orientation_quirk(int width, int height)
 		if (!bios_date)
 			continue;
 
-		for (i = 0; data->bios_dates[i]; i++) {
-			if (!strcmp(data->bios_dates[i], bios_date))
-				return data->orientation;
-		}
+		i = match_string(data->bios_dates, -1, bios_date);
+		if (i >= 0)
+			return data->orientation;
 	}
 
 	return DRM_MODE_PANEL_ORIENTATION_UNKNOWN;
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 6d2a6e428a3e..035054455301 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -756,6 +756,7 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 				     struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_device *dev = crtc->dev;
+	struct drm_plane *plane = crtc->cursor;
 	struct drm_framebuffer *fb = NULL;
 	struct drm_mode_fb_cmd2 fbreq = {
 		.width = req->width,
@@ -769,8 +770,8 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 	uint32_t src_w = 0, src_h = 0;
 	int ret = 0;
 
-	BUG_ON(!crtc->cursor);
-	WARN_ON(crtc->cursor->crtc != crtc && crtc->cursor->crtc != NULL);
+	BUG_ON(!plane);
+	WARN_ON(plane->crtc != crtc && plane->crtc != NULL);
 
 	/*
 	 * Obtain fb we'll be using (either new or existing) and take an extra
@@ -784,13 +785,18 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 				DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n");
 				return PTR_ERR(fb);
 			}
+
 			fb->hot_x = req->hot_x;
 			fb->hot_y = req->hot_y;
 		} else {
 			fb = NULL;
 		}
 	} else {
-		fb = crtc->cursor->fb;
+		if (plane->state)
+			fb = plane->state->fb;
+		else
+			fb = plane->fb;
+
 		if (fb)
 			drm_framebuffer_get(fb);
 	}
@@ -810,7 +816,7 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 		src_h = fb->height << 16;
 	}
 
-	ret = __setplane_internal(crtc->cursor, crtc, fb,
+	ret = __setplane_internal(plane, crtc, fb,
 				  crtc_x, crtc_y, crtc_w, crtc_h,
 				  0, 0, src_w, src_h, ctx);
 
@@ -931,7 +937,8 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 {
 	struct drm_mode_crtc_page_flip_target *page_flip = data;
 	struct drm_crtc *crtc;
-	struct drm_framebuffer *fb = NULL;
+	struct drm_plane *plane;
+	struct drm_framebuffer *fb = NULL, *old_fb;
 	struct drm_pending_vblank_event *e = NULL;
 	u32 target_vblank = page_flip->sequence;
 	struct drm_modeset_acquire_ctx ctx;
@@ -959,6 +966,8 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	if (!crtc)
 		return -ENOENT;
 
+	plane = crtc->primary;
+
 	if (crtc->funcs->page_flip_target) {
 		u32 current_vblank;
 		int r;
@@ -1003,11 +1012,16 @@ retry:
 	ret = drm_modeset_lock(&crtc->mutex, &ctx);
 	if (ret)
 		goto out;
-	ret = drm_modeset_lock(&crtc->primary->mutex, &ctx);
+	ret = drm_modeset_lock(&plane->mutex, &ctx);
 	if (ret)
 		goto out;
 
-	if (crtc->primary->fb == NULL) {
+	if (plane->state)
+		old_fb = plane->state->fb;
+	else
+		old_fb = plane->fb;
+
+	if (old_fb == NULL) {
 		/* The framebuffer is currently unbound, presumably
 		 * due to a hotplug event, that userspace has not
 		 * yet discovered.
@@ -1022,8 +1036,8 @@ retry:
 		goto out;
 	}
 
-	if (crtc->state) {
-		const struct drm_plane_state *state = crtc->primary->state;
+	if (plane->state) {
+		const struct drm_plane_state *state = plane->state;
 
 		ret = drm_framebuffer_check_src_coords(state->src_x,
 						       state->src_y,
@@ -1031,12 +1045,13 @@ retry:
 						       state->src_h,
 						       fb);
 	} else {
-		ret = drm_crtc_check_viewport(crtc, crtc->x, crtc->y, &crtc->mode, fb);
+		ret = drm_crtc_check_viewport(crtc, crtc->x, crtc->y,
+					      &crtc->mode, fb);
 	}
 	if (ret)
 		goto out;
 
-	if (crtc->primary->fb->format != fb->format) {
+	if (old_fb->format != fb->format) {
 		DRM_DEBUG_KMS("Page flip is not allowed to change frame buffer format.\n");
 		ret = -EINVAL;
 		goto out;
@@ -1048,10 +1063,12 @@ retry:
 			ret = -ENOMEM;
 			goto out;
 		}
+
 		e->event.base.type = DRM_EVENT_FLIP_COMPLETE;
 		e->event.base.length = sizeof(e->event);
 		e->event.vbl.user_data = page_flip->user_data;
 		e->event.vbl.crtc_id = crtc->base.id;
+
 		ret = drm_event_reserve_init(dev, file_priv, &e->base, &e->event.base);
 		if (ret) {
 			kfree(e);
@@ -1060,7 +1077,7 @@ retry:
 		}
 	}
 
-	crtc->primary->old_fb = crtc->primary->fb;
+	plane->old_fb = plane->fb;
 	if (crtc->funcs->page_flip_target)
 		ret = crtc->funcs->page_flip_target(crtc, fb, e,
 						    page_flip->flags,
@@ -1073,19 +1090,18 @@ retry:
 		if (page_flip->flags & DRM_MODE_PAGE_FLIP_EVENT)
 			drm_event_cancel_free(dev, &e->base);
 		/* Keep the old fb, don't unref it. */
-		crtc->primary->old_fb = NULL;
+		plane->old_fb = NULL;
 	} else {
-		crtc->primary->fb = fb;
-		/* Unref only the old framebuffer. */
-		fb = NULL;
+		plane->fb = fb;
+		drm_framebuffer_get(fb);
 	}
 
 out:
 	if (fb)
 		drm_framebuffer_put(fb);
-	if (crtc->primary->old_fb)
-		drm_framebuffer_put(crtc->primary->old_fb);
-	crtc->primary->old_fb = NULL;
+	if (plane->old_fb)
+		drm_framebuffer_put(plane->old_fb);
+	plane->old_fb = NULL;
 
 	if (ret == -EDEADLK) {
 		ret = drm_modeset_backoff(&ctx);
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 7856a9b3f8a8..397b46b33739 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -331,6 +331,9 @@ EXPORT_SYMBOL(drm_gem_map_dma_buf);
 
 /**
  * drm_gem_unmap_dma_buf - unmap_dma_buf implementation for GEM
+ * @attach: attachment to unmap buffer from
+ * @sgt: scatterlist info of the buffer to unmap
+ * @dir: direction of DMA transfer
  *
  * Not implemented. The unmap is done at drm_gem_map_detach().  This can be
  * used as the &dma_buf_ops.unmap_dma_buf callback.
@@ -406,7 +409,10 @@ void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf)
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct drm_device *dev = obj->dev;
 
-	return dev->driver->gem_prime_vmap(obj);
+	if (dev->driver->gem_prime_vmap)
+		return dev->driver->gem_prime_vmap(obj);
+	else
+		return NULL;
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_vmap);
 
@@ -423,12 +429,15 @@ void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct drm_device *dev = obj->dev;
 
-	dev->driver->gem_prime_vunmap(obj, vaddr);
+	if (dev->driver->gem_prime_vunmap)
+		dev->driver->gem_prime_vunmap(obj, vaddr);
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_vunmap);
 
 /**
  * drm_gem_dmabuf_kmap_atomic - map_atomic implementation for GEM
+ * @dma_buf: buffer to be mapped
+ * @page_num: page number within the buffer
  *
  * Not implemented. This can be used as the &dma_buf_ops.map_atomic callback.
  */
@@ -441,6 +450,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_kmap_atomic);
 
 /**
  * drm_gem_dmabuf_kunmap_atomic - unmap_atomic implementation for GEM
+ * @dma_buf: buffer to be unmapped
+ * @page_num: page number within the buffer
+ * @addr: virtual address of the buffer
  *
  * Not implemented. This can be used as the &dma_buf_ops.unmap_atomic callback.
  */
@@ -453,6 +465,8 @@ EXPORT_SYMBOL(drm_gem_dmabuf_kunmap_atomic);
 
 /**
  * drm_gem_dmabuf_kmap - map implementation for GEM
+ * @dma_buf: buffer to be mapped
+ * @page_num: page number within the buffer
  *
  * Not implemented. This can be used as the &dma_buf_ops.map callback.
  */
@@ -464,6 +478,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_kmap);
 
 /**
  * drm_gem_dmabuf_kunmap - unmap implementation for GEM
+ * @dma_buf: buffer to be unmapped
+ * @page_num: page number within the buffer
+ * @addr: virtual address of the buffer
  *
  * Not implemented. This can be used as the &dma_buf_ops.unmap callback.
  */
diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c
index 8f4672daac7f..1f8031e30f53 100644
--- a/drivers/gpu/drm/drm_property.c
+++ b/drivers/gpu/drm/drm_property.c
@@ -169,9 +169,9 @@ struct drm_property *drm_property_create_enum(struct drm_device *dev,
 		return NULL;
 
 	for (i = 0; i < num_values; i++) {
-		ret = drm_property_add_enum(property, i,
-				      props[i].type,
-				      props[i].name);
+		ret = drm_property_add_enum(property,
+					    props[i].type,
+					    props[i].name);
 		if (ret) {
 			drm_property_destroy(dev, property);
 			return NULL;
@@ -209,7 +209,7 @@ struct drm_property *drm_property_create_bitmask(struct drm_device *dev,
 						 uint64_t supported_bits)
 {
 	struct drm_property *property;
-	int i, ret, index = 0;
+	int i, ret;
 	int num_values = hweight64(supported_bits);
 
 	flags |= DRM_MODE_PROP_BITMASK;
@@ -221,14 +221,9 @@ struct drm_property *drm_property_create_bitmask(struct drm_device *dev,
 		if (!(supported_bits & (1ULL << props[i].type)))
 			continue;
 
-		if (WARN_ON(index >= num_values)) {
-			drm_property_destroy(dev, property);
-			return NULL;
-		}
-
-		ret = drm_property_add_enum(property, index++,
-				      props[i].type,
-				      props[i].name);
+		ret = drm_property_add_enum(property,
+					    props[i].type,
+					    props[i].name);
 		if (ret) {
 			drm_property_destroy(dev, property);
 			return NULL;
@@ -376,7 +371,6 @@ EXPORT_SYMBOL(drm_property_create_bool);
 /**
  * drm_property_add_enum - add a possible value to an enumeration property
  * @property: enumeration property to change
- * @index: index of the new enumeration
  * @value: value of the new enumeration
  * @name: symbolic name of the new enumeration
  *
@@ -388,10 +382,11 @@ EXPORT_SYMBOL(drm_property_create_bool);
  * Returns:
  * Zero on success, error code on failure.
  */
-int drm_property_add_enum(struct drm_property *property, int index,
+int drm_property_add_enum(struct drm_property *property,
 			  uint64_t value, const char *name)
 {
 	struct drm_property_enum *prop_enum;
+	int index = 0;
 
 	if (WARN_ON(strlen(name) >= DRM_PROP_NAME_LEN))
 		return -EINVAL;
@@ -411,8 +406,12 @@ int drm_property_add_enum(struct drm_property *property, int index,
 	list_for_each_entry(prop_enum, &property->enum_list, head) {
 		if (WARN_ON(prop_enum->value == value))
 			return -EINVAL;
+		index++;
 	}
 
+	if (WARN_ON(index >= property->num_values))
+		return -EINVAL;
+
 	prop_enum = kzalloc(sizeof(struct drm_property_enum), GFP_KERNEL);
 	if (!prop_enum)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/drm_rect.c b/drivers/gpu/drm/drm_rect.c
index 9817c1445ba9..8c057829b804 100644
--- a/drivers/gpu/drm/drm_rect.c
+++ b/drivers/gpu/drm/drm_rect.c
@@ -50,13 +50,25 @@ bool drm_rect_intersect(struct drm_rect *r1, const struct drm_rect *r2)
 }
 EXPORT_SYMBOL(drm_rect_intersect);
 
+static u32 clip_scaled(u32 src, u32 dst, u32 clip)
+{
+	u64 tmp = mul_u32_u32(src, dst - clip);
+
+	/*
+	 * Round toward 1.0 when clipping so that we don't accidentally
+	 * change upscaling to downscaling or vice versa.
+	 */
+	if (src < (dst << 16))
+		return DIV_ROUND_UP_ULL(tmp, dst);
+	else
+		return DIV_ROUND_DOWN_ULL(tmp, dst);
+}
+
 /**
  * drm_rect_clip_scaled - perform a scaled clip operation
  * @src: source window rectangle
  * @dst: destination window rectangle
  * @clip: clip rectangle
- * @hscale: horizontal scaling factor
- * @vscale: vertical scaling factor
  *
  * Clip rectangle @dst by rectangle @clip. Clip rectangle @src by the
  * same amounts multiplied by @hscale and @vscale.
@@ -66,33 +78,44 @@ EXPORT_SYMBOL(drm_rect_intersect);
  * %false otherwise
  */
 bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst,
-			  const struct drm_rect *clip,
-			  int hscale, int vscale)
+			  const struct drm_rect *clip)
 {
 	int diff;
 
 	diff = clip->x1 - dst->x1;
 	if (diff > 0) {
-		int64_t tmp = src->x1 + (int64_t) diff * hscale;
-		src->x1 = clamp_t(int64_t, tmp, INT_MIN, INT_MAX);
+		u32 new_src_w = clip_scaled(drm_rect_width(src),
+					    drm_rect_width(dst), diff);
+
+		src->x1 = clamp_t(int64_t, src->x2 - new_src_w, INT_MIN, INT_MAX);
+		dst->x1 = clip->x1;
 	}
 	diff = clip->y1 - dst->y1;
 	if (diff > 0) {
-		int64_t tmp = src->y1 + (int64_t) diff * vscale;
-		src->y1 = clamp_t(int64_t, tmp, INT_MIN, INT_MAX);
+		u32 new_src_h = clip_scaled(drm_rect_height(src),
+					    drm_rect_height(dst), diff);
+
+		src->y1 = clamp_t(int64_t, src->y2 - new_src_h, INT_MIN, INT_MAX);
+		dst->y1 = clip->y1;
 	}
 	diff = dst->x2 - clip->x2;
 	if (diff > 0) {
-		int64_t tmp = src->x2 - (int64_t) diff * hscale;
-		src->x2 = clamp_t(int64_t, tmp, INT_MIN, INT_MAX);
+		u32 new_src_w = clip_scaled(drm_rect_width(src),
+					    drm_rect_width(dst), diff);
+
+		src->x2 = clamp_t(int64_t, src->x1 + new_src_w, INT_MIN, INT_MAX);
+		dst->x2 = clip->x2;
 	}
 	diff = dst->y2 - clip->y2;
 	if (diff > 0) {
-		int64_t tmp = src->y2 - (int64_t) diff * vscale;
-		src->y2 = clamp_t(int64_t, tmp, INT_MIN, INT_MAX);
+		u32 new_src_h = clip_scaled(drm_rect_height(src),
+					    drm_rect_height(dst), diff);
+
+		src->y2 = clamp_t(int64_t, src->y1 + new_src_h, INT_MIN, INT_MAX);
+		dst->y2 = clip->y2;
 	}
 
-	return drm_rect_intersect(dst, clip);
+	return drm_rect_visible(dst);
 }
 EXPORT_SYMBOL(drm_rect_clip_scaled);
 
@@ -106,7 +129,10 @@ static int drm_calc_scale(int src, int dst)
 	if (dst == 0)
 		return 0;
 
-	scale = src / dst;
+	if (src > (dst << 16))
+		return DIV_ROUND_UP(src, dst);
+	else
+		scale = src / dst;
 
 	return scale;
 }
@@ -121,6 +147,10 @@ static int drm_calc_scale(int src, int dst)
  * Calculate the horizontal scaling factor as
  * (@src width) / (@dst width).
  *
+ * If the scale is below 1 << 16, round down. If the scale is above
+ * 1 << 16, round up. This will calculate the scale with the most
+ * pessimistic limit calculation.
+ *
  * RETURNS:
  * The horizontal scaling factor, or errno of out of limits.
  */
@@ -152,6 +182,10 @@ EXPORT_SYMBOL(drm_rect_calc_hscale);
  * Calculate the vertical scaling factor as
  * (@src height) / (@dst height).
  *
+ * If the scale is below 1 << 16, round down. If the scale is above
+ * 1 << 16, round up. This will calculate the scale with the most
+ * pessimistic limit calculation.
+ *
  * RETURNS:
  * The vertical scaling factor, or errno of out of limits.
  */
@@ -189,6 +223,10 @@ EXPORT_SYMBOL(drm_rect_calc_vscale);
  * If the calculated scaling factor is above @max_vscale,
  * decrease the height of rectangle @src to compensate.
  *
+ * If the scale is below 1 << 16, round down. If the scale is above
+ * 1 << 16, round up. This will calculate the scale with the most
+ * pessimistic limit calculation.
+ *
  * RETURNS:
  * The horizontal scaling factor.
  */
@@ -239,6 +277,10 @@ EXPORT_SYMBOL(drm_rect_calc_hscale_relaxed);
  * If the calculated scaling factor is above @max_vscale,
  * decrease the height of rectangle @src to compensate.
  *
+ * If the scale is below 1 << 16, round down. If the scale is above
+ * 1 << 16, round up. This will calculate the scale with the most
+ * pessimistic limit calculation.
+ *
  * RETURNS:
  * The vertical scaling factor.
  */
@@ -373,8 +415,8 @@ EXPORT_SYMBOL(drm_rect_rotate);
  * them when doing a rotatation and its inverse.
  * That is, if you do ::
  *
- *     DRM_MODE_PROP_ROTATE(&r, width, height, rotation);
- *     DRM_MODE_ROTATE_inv(&r, width, height, rotation);
+ *     drm_rect_rotate(&r, width, height, rotation);
+ *     drm_rect_rotate_inv(&r, width, height, rotation);
  *
  * you will always get back the original rectangle.
  */
diff --git a/drivers/gpu/drm/drm_scdc_helper.c b/drivers/gpu/drm/drm_scdc_helper.c
index 657ea5ab6c3f..870e25f1f788 100644
--- a/drivers/gpu/drm/drm_scdc_helper.c
+++ b/drivers/gpu/drm/drm_scdc_helper.c
@@ -141,7 +141,7 @@ bool drm_scdc_get_scrambling_status(struct i2c_adapter *adapter)
 
 	ret = drm_scdc_readb(adapter, SCDC_SCRAMBLER_STATUS, &status);
 	if (ret < 0) {
-		DRM_ERROR("Failed to read scrambling status: %d\n", ret);
+		DRM_DEBUG_KMS("Failed to read scrambling status: %d\n", ret);
 		return false;
 	}
 
@@ -168,7 +168,7 @@ bool drm_scdc_set_scrambling(struct i2c_adapter *adapter, bool enable)
 
 	ret = drm_scdc_readb(adapter, SCDC_TMDS_CONFIG, &config);
 	if (ret < 0) {
-		DRM_ERROR("Failed to read TMDS config: %d\n", ret);
+		DRM_DEBUG_KMS("Failed to read TMDS config: %d\n", ret);
 		return false;
 	}
 
@@ -179,7 +179,7 @@ bool drm_scdc_set_scrambling(struct i2c_adapter *adapter, bool enable)
 
 	ret = drm_scdc_writeb(adapter, SCDC_TMDS_CONFIG, config);
 	if (ret < 0) {
-		DRM_ERROR("Failed to enable scrambling: %d\n", ret);
+		DRM_DEBUG_KMS("Failed to enable scrambling: %d\n", ret);
 		return false;
 	}
 
@@ -223,7 +223,7 @@ bool drm_scdc_set_high_tmds_clock_ratio(struct i2c_adapter *adapter, bool set)
 
 	ret = drm_scdc_readb(adapter, SCDC_TMDS_CONFIG, &config);
 	if (ret < 0) {
-		DRM_ERROR("Failed to read TMDS config: %d\n", ret);
+		DRM_DEBUG_KMS("Failed to read TMDS config: %d\n", ret);
 		return false;
 	}
 
@@ -234,7 +234,7 @@ bool drm_scdc_set_high_tmds_clock_ratio(struct i2c_adapter *adapter, bool set)
 
 	ret = drm_scdc_writeb(adapter, SCDC_TMDS_CONFIG, config);
 	if (ret < 0) {
-		DRM_ERROR("Failed to set TMDS clock ratio: %d\n", ret);
+		DRM_DEBUG_KMS("Failed to set TMDS clock ratio: %d\n", ret);
 		return false;
 	}
 
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index 987a353c7f72..7a00455ca568 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -64,13 +64,15 @@ static int drm_simple_kms_crtc_check(struct drm_crtc *crtc,
 static void drm_simple_kms_crtc_enable(struct drm_crtc *crtc,
 				       struct drm_crtc_state *old_state)
 {
+	struct drm_plane *plane;
 	struct drm_simple_display_pipe *pipe;
 
 	pipe = container_of(crtc, struct drm_simple_display_pipe, crtc);
 	if (!pipe->funcs || !pipe->funcs->enable)
 		return;
 
-	pipe->funcs->enable(pipe, crtc->state);
+	plane = &pipe->plane;
+	pipe->funcs->enable(pipe, crtc->state, plane->state);
 }
 
 static void drm_simple_kms_crtc_disable(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index 1c5b5ce1fd7f..b3c1daad1169 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -331,9 +331,7 @@ struct device *drm_sysfs_minor_alloc(struct drm_minor *minor)
 	struct device *kdev;
 	int r;
 
-	if (minor->type == DRM_MINOR_CONTROL)
-		minor_str = "controlD%d";
-	else if (minor->type == DRM_MINOR_RENDER)
+	if (minor->type == DRM_MINOR_RENDER)
 		minor_str = "renderD%d";
 	else
 		minor_str = "card%d";
diff --git a/drivers/gpu/drm/etnaviv/Kconfig b/drivers/gpu/drm/etnaviv/Kconfig
index e5bfeca361bd..041a77e400d4 100644
--- a/drivers/gpu/drm/etnaviv/Kconfig
+++ b/drivers/gpu/drm/etnaviv/Kconfig
@@ -22,11 +22,3 @@ config DRM_ETNAVIV_THERMAL
 	help
 	  Compile in support for thermal throttling.
 	  Say Y unless you want to risk burning your SoC.
-
-config DRM_ETNAVIV_REGISTER_LOGGING
-	bool "enable ETNAVIV register logging"
-	depends on DRM_ETNAVIV
-	help
-	  Compile in support for logging register reads/writes in a format
-	  that can be parsed by envytools demsm tool.  If enabled, register
-	  logging can be switched on via etnaviv.reglog=y module param.
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
index bfc6d4aa3b7c..7fea74861a87 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
@@ -1,18 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2014 Etnaviv Project
- * Author: Christian Gmeiner <christian.gmeiner@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2014-2018 Etnaviv Project
  */
 
 #include "etnaviv_cmdbuf.h"
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_cmd_parser.c b/drivers/gpu/drm/etnaviv/etnaviv_cmd_parser.c
index 68e6d3772ad8..b106e8b288ad 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_cmd_parser.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_cmd_parser.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c b/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c
index 3746827f45eb..a3c44f145c1d 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2017 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2017-2018 Etnaviv Project
  */
 
 #include <drm/drm_mm.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.h b/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.h
index ddc3f7ea169c..acb68c698363 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2017 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __ETNAVIV_CMDBUF_H__
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index ab50090d066c..e5013a999147 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #include <linux/component.h>
@@ -25,57 +14,6 @@
 #include "etnaviv_mmu.h"
 #include "etnaviv_perfmon.h"
 
-#ifdef CONFIG_DRM_ETNAVIV_REGISTER_LOGGING
-static bool reglog;
-MODULE_PARM_DESC(reglog, "Enable register read/write logging");
-module_param(reglog, bool, 0600);
-#else
-#define reglog 0
-#endif
-
-void __iomem *etnaviv_ioremap(struct platform_device *pdev, const char *name,
-		const char *dbgname)
-{
-	struct resource *res;
-	void __iomem *ptr;
-
-	if (name)
-		res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
-	else
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
-	ptr = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(ptr)) {
-		dev_err(&pdev->dev, "failed to ioremap %s: %ld\n", name,
-			PTR_ERR(ptr));
-		return ptr;
-	}
-
-	if (reglog)
-		dev_printk(KERN_DEBUG, &pdev->dev, "IO:region %s 0x%p %08zx\n",
-			   dbgname, ptr, (size_t)resource_size(res));
-
-	return ptr;
-}
-
-void etnaviv_writel(u32 data, void __iomem *addr)
-{
-	if (reglog)
-		printk(KERN_DEBUG "IO:W %p %08x\n", addr, data);
-
-	writel(data, addr);
-}
-
-u32 etnaviv_readl(const void __iomem *addr)
-{
-	u32 val = readl(addr);
-
-	if (reglog)
-		printk(KERN_DEBUG "IO:R %p %08x\n", addr, val);
-
-	return val;
-}
-
 /*
  * DRM operations:
  */
@@ -116,7 +54,7 @@ static int etnaviv_open(struct drm_device *dev, struct drm_file *file)
 			drm_sched_entity_init(&gpu->sched,
 				&ctx->sched_entity[i],
 				&gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL],
-				32, NULL);
+				NULL);
 			}
 	}
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
index ddb17ee565e9..d36c7bbe66db 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #ifndef __ETNAVIV_DRV_H__
@@ -26,6 +15,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/list.h>
+#include <linux/time64.h>
 #include <linux/types.h>
 #include <linux/sizes.h>
 
@@ -101,11 +91,6 @@ void etnaviv_gem_describe_objects(struct etnaviv_drm_private *priv,
 	struct seq_file *m);
 #endif
 
-void __iomem *etnaviv_ioremap(struct platform_device *pdev, const char *name,
-		const char *dbgname);
-void etnaviv_writel(u32 data, void __iomem *addr);
-u32 etnaviv_readl(const void __iomem *addr);
-
 #define DBG(fmt, ...) DRM_DEBUG(fmt"\n", ##__VA_ARGS__)
 #define VERB(fmt, ...) if (0) DRM_DEBUG(fmt"\n", ##__VA_ARGS__)
 
@@ -132,19 +117,27 @@ static inline bool fence_after_eq(u32 a, u32 b)
 	return (s32)(a - b) >= 0;
 }
 
+/*
+ * Etnaviv timeouts are specified wrt CLOCK_MONOTONIC, not jiffies.
+ * We need to calculate the timeout in terms of number of jiffies
+ * between the specified timeout and the current CLOCK_MONOTONIC time.
+ */
 static inline unsigned long etnaviv_timeout_to_jiffies(
 	const struct timespec *timeout)
 {
-	unsigned long timeout_jiffies = timespec_to_jiffies(timeout);
-	unsigned long start_jiffies = jiffies;
-	unsigned long remaining_jiffies;
+	struct timespec64 ts, to;
+
+	to = timespec_to_timespec64(*timeout);
+
+	ktime_get_ts64(&ts);
+
+	/* timeouts before "now" have already expired */
+	if (timespec64_compare(&to, &ts) <= 0)
+		return 0;
 
-	if (time_after(start_jiffies, timeout_jiffies))
-		remaining_jiffies = 0;
-	else
-		remaining_jiffies = timeout_jiffies - start_jiffies;
+	ts = timespec64_sub(to, ts);
 
-	return remaining_jiffies;
+	return timespec64_to_jiffies(&ts);
 }
 
 #endif /* __ETNAVIV_DRV_H__ */
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
index 48aef6cf6a42..9146e30e24a6 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #include <linux/devcoredump.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.h b/drivers/gpu/drm/etnaviv/etnaviv_dump.h
index 97f2f8db9133..2d916c2667ee 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_dump.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.h
@@ -1,20 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * Etnaviv devcoredump file definitions
  */
+
 #ifndef ETNAVIV_DUMP_H
 #define ETNAVIV_DUMP_H
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index fcc969fa0e69..209ef1274b80 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #include <linux/spinlock.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.h b/drivers/gpu/drm/etnaviv/etnaviv_gem.h
index 93e696fcc14f..76079c2291f8 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #ifndef __ETNAVIV_GEM_H__
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
index 5704305d41e6..0566171f8df2 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
@@ -1,18 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2013 Red Hat
- * Author: Rob Clark <robdclark@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2014-2018 Etnaviv Project
  */
 
 #include <linux/dma-buf.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 8a88799bf79b..686f6552db48 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #include <linux/component.h>
@@ -1735,6 +1724,7 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct etnaviv_gpu *gpu;
+	struct resource *res;
 	int err;
 
 	gpu = devm_kzalloc(dev, sizeof(*gpu), GFP_KERNEL);
@@ -1746,7 +1736,8 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev)
 	mutex_init(&gpu->fence_idr_lock);
 
 	/* Map registers: */
-	gpu->mmio = etnaviv_ioremap(pdev, NULL, dev_name(gpu->dev));
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	gpu->mmio = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(gpu->mmio))
 		return PTR_ERR(gpu->mmio);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 3c3005501846..dd430f0f8ff5 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #ifndef __ETNAVIV_GPU_H__
@@ -161,12 +150,12 @@ struct etnaviv_gpu {
 
 static inline void gpu_write(struct etnaviv_gpu *gpu, u32 reg, u32 data)
 {
-	etnaviv_writel(data, gpu->mmio + reg);
+	writel(data, gpu->mmio + reg);
 }
 
 static inline u32 gpu_read(struct etnaviv_gpu *gpu, u32 reg)
 {
-	return etnaviv_readl(gpu->mmio + reg);
+	return readl(gpu->mmio + reg);
 }
 
 static inline bool fence_completed(struct etnaviv_gpu *gpu, u32 fence)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
index ea08bb38caaf..39b463db76c9 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2018 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "etnaviv_gpu.h"
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
index 4b9b11ca6f03..b163bdbcb880 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2014 Christian Gmeiner <christian.gmeiner@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2014-2018 Etnaviv Project
  */
 
 #include <linux/platform_device.h>
@@ -47,11 +36,10 @@ static int __etnaviv_iommu_init(struct etnaviv_iommuv1_domain *etnaviv_domain)
 	u32 *p;
 	int i;
 
-	etnaviv_domain->base.bad_page_cpu = dma_alloc_coherent(
-						etnaviv_domain->base.dev,
-						SZ_4K,
-						&etnaviv_domain->base.bad_page_dma,
-						GFP_KERNEL);
+	etnaviv_domain->base.bad_page_cpu =
+			dma_alloc_wc(etnaviv_domain->base.dev, SZ_4K,
+				     &etnaviv_domain->base.bad_page_dma,
+				     GFP_KERNEL);
 	if (!etnaviv_domain->base.bad_page_cpu)
 		return -ENOMEM;
 
@@ -59,14 +47,14 @@ static int __etnaviv_iommu_init(struct etnaviv_iommuv1_domain *etnaviv_domain)
 	for (i = 0; i < SZ_4K / 4; i++)
 		*p++ = 0xdead55aa;
 
-	etnaviv_domain->pgtable_cpu =
-			dma_alloc_coherent(etnaviv_domain->base.dev, PT_SIZE,
-					   &etnaviv_domain->pgtable_dma,
-					   GFP_KERNEL);
+	etnaviv_domain->pgtable_cpu = dma_alloc_wc(etnaviv_domain->base.dev,
+						   PT_SIZE,
+						   &etnaviv_domain->pgtable_dma,
+						   GFP_KERNEL);
 	if (!etnaviv_domain->pgtable_cpu) {
-		dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-				  etnaviv_domain->base.bad_page_cpu,
-				  etnaviv_domain->base.bad_page_dma);
+		dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+			    etnaviv_domain->base.bad_page_cpu,
+			    etnaviv_domain->base.bad_page_dma);
 		return -ENOMEM;
 	}
 
@@ -81,13 +69,12 @@ static void etnaviv_iommuv1_domain_free(struct etnaviv_iommu_domain *domain)
 	struct etnaviv_iommuv1_domain *etnaviv_domain =
 			to_etnaviv_domain(domain);
 
-	dma_free_coherent(etnaviv_domain->base.dev, PT_SIZE,
-			  etnaviv_domain->pgtable_cpu,
-			  etnaviv_domain->pgtable_dma);
+	dma_free_wc(etnaviv_domain->base.dev, PT_SIZE,
+		    etnaviv_domain->pgtable_cpu, etnaviv_domain->pgtable_dma);
 
-	dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-			  etnaviv_domain->base.bad_page_cpu,
-			  etnaviv_domain->base.bad_page_dma);
+	dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+		    etnaviv_domain->base.bad_page_cpu,
+		    etnaviv_domain->base.bad_page_dma);
 
 	kfree(etnaviv_domain);
 }
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.h b/drivers/gpu/drm/etnaviv/etnaviv_iommu.h
index 01d59bf70d78..b279404ce91a 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (C) 2014 Christian Gmeiner <christian.gmeiner@gmail.com>
-  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2014-2018 Etnaviv Project
  */
 
 #ifndef __ETNAVIV_IOMMU_H__
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index 9752dbd5d28b..71fbc1f96cb6 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2016 Etnaviv Project
-  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2016-2018 Etnaviv Project
  */
 
 #include <linux/platform_device.h>
@@ -47,8 +36,8 @@ struct etnaviv_iommuv2_domain {
 	u32 *mtlb_cpu;
 	dma_addr_t mtlb_dma;
 	/* S(lave) TLB aka second level pagetable */
-	u32 *stlb_cpu[1024];
-	dma_addr_t stlb_dma[1024];
+	u32 *stlb_cpu[MMUv2_MAX_STLB_ENTRIES];
+	dma_addr_t stlb_dma[MMUv2_MAX_STLB_ENTRIES];
 };
 
 static struct etnaviv_iommuv2_domain *
@@ -57,24 +46,54 @@ to_etnaviv_domain(struct etnaviv_iommu_domain *domain)
 	return container_of(domain, struct etnaviv_iommuv2_domain, base);
 }
 
+static int
+etnaviv_iommuv2_ensure_stlb(struct etnaviv_iommuv2_domain *etnaviv_domain,
+			    int stlb)
+{
+	if (etnaviv_domain->stlb_cpu[stlb])
+		return 0;
+
+	etnaviv_domain->stlb_cpu[stlb] =
+			dma_alloc_wc(etnaviv_domain->base.dev, SZ_4K,
+				     &etnaviv_domain->stlb_dma[stlb],
+				     GFP_KERNEL);
+
+	if (!etnaviv_domain->stlb_cpu[stlb])
+		return -ENOMEM;
+
+	memset32(etnaviv_domain->stlb_cpu[stlb], MMUv2_PTE_EXCEPTION,
+		 SZ_4K / sizeof(u32));
+
+	etnaviv_domain->mtlb_cpu[stlb] = etnaviv_domain->stlb_dma[stlb] |
+						      MMUv2_PTE_PRESENT;
+	return 0;
+}
+
 static int etnaviv_iommuv2_map(struct etnaviv_iommu_domain *domain,
 			       unsigned long iova, phys_addr_t paddr,
 			       size_t size, int prot)
 {
 	struct etnaviv_iommuv2_domain *etnaviv_domain =
 			to_etnaviv_domain(domain);
-	int mtlb_entry, stlb_entry;
-	u32 entry = (u32)paddr | MMUv2_PTE_PRESENT;
+	int mtlb_entry, stlb_entry, ret;
+	u32 entry = lower_32_bits(paddr) | MMUv2_PTE_PRESENT;
 
 	if (size != SZ_4K)
 		return -EINVAL;
 
+	if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT))
+		entry |= (upper_32_bits(paddr) & 0xff) << 4;
+
 	if (prot & ETNAVIV_PROT_WRITE)
 		entry |= MMUv2_PTE_WRITEABLE;
 
 	mtlb_entry = (iova & MMUv2_MTLB_MASK) >> MMUv2_MTLB_SHIFT;
 	stlb_entry = (iova & MMUv2_STLB_MASK) >> MMUv2_STLB_SHIFT;
 
+	ret = etnaviv_iommuv2_ensure_stlb(etnaviv_domain, mtlb_entry);
+	if (ret)
+		return ret;
+
 	etnaviv_domain->stlb_cpu[mtlb_entry][stlb_entry] = entry;
 
 	return 0;
@@ -101,14 +120,13 @@ static size_t etnaviv_iommuv2_unmap(struct etnaviv_iommu_domain *domain,
 static int etnaviv_iommuv2_init(struct etnaviv_iommuv2_domain *etnaviv_domain)
 {
 	u32 *p;
-	int ret, i, j;
+	int ret, i;
 
 	/* allocate scratch page */
-	etnaviv_domain->base.bad_page_cpu = dma_alloc_coherent(
-						etnaviv_domain->base.dev,
-						SZ_4K,
-						&etnaviv_domain->base.bad_page_dma,
-						GFP_KERNEL);
+	etnaviv_domain->base.bad_page_cpu =
+			dma_alloc_wc(etnaviv_domain->base.dev, SZ_4K,
+				     &etnaviv_domain->base.bad_page_dma,
+				     GFP_KERNEL);
 	if (!etnaviv_domain->base.bad_page_cpu) {
 		ret = -ENOMEM;
 		goto fail_mem;
@@ -117,67 +135,40 @@ static int etnaviv_iommuv2_init(struct etnaviv_iommuv2_domain *etnaviv_domain)
 	for (i = 0; i < SZ_4K / 4; i++)
 		*p++ = 0xdead55aa;
 
-	etnaviv_domain->pta_cpu = dma_alloc_coherent(etnaviv_domain->base.dev,
-						     SZ_4K,
-						     &etnaviv_domain->pta_dma,
-						     GFP_KERNEL);
+	etnaviv_domain->pta_cpu = dma_alloc_wc(etnaviv_domain->base.dev,
+					       SZ_4K, &etnaviv_domain->pta_dma,
+					       GFP_KERNEL);
 	if (!etnaviv_domain->pta_cpu) {
 		ret = -ENOMEM;
 		goto fail_mem;
 	}
 
-	etnaviv_domain->mtlb_cpu = dma_alloc_coherent(etnaviv_domain->base.dev,
-						  SZ_4K,
-						  &etnaviv_domain->mtlb_dma,
-						  GFP_KERNEL);
+	etnaviv_domain->mtlb_cpu = dma_alloc_wc(etnaviv_domain->base.dev,
+						SZ_4K, &etnaviv_domain->mtlb_dma,
+						GFP_KERNEL);
 	if (!etnaviv_domain->mtlb_cpu) {
 		ret = -ENOMEM;
 		goto fail_mem;
 	}
 
-	/* pre-populate STLB pages (may want to switch to on-demand later) */
-	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++) {
-		etnaviv_domain->stlb_cpu[i] =
-				dma_alloc_coherent(etnaviv_domain->base.dev,
-						   SZ_4K,
-						   &etnaviv_domain->stlb_dma[i],
-						   GFP_KERNEL);
-		if (!etnaviv_domain->stlb_cpu[i]) {
-			ret = -ENOMEM;
-			goto fail_mem;
-		}
-		p = etnaviv_domain->stlb_cpu[i];
-		for (j = 0; j < SZ_4K / 4; j++)
-			*p++ = MMUv2_PTE_EXCEPTION;
-
-		etnaviv_domain->mtlb_cpu[i] = etnaviv_domain->stlb_dma[i] |
-					      MMUv2_PTE_PRESENT;
-	}
+	memset32(etnaviv_domain->mtlb_cpu, MMUv2_PTE_EXCEPTION,
+		 MMUv2_MAX_STLB_ENTRIES);
 
 	return 0;
 
 fail_mem:
 	if (etnaviv_domain->base.bad_page_cpu)
-		dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-				  etnaviv_domain->base.bad_page_cpu,
-				  etnaviv_domain->base.bad_page_dma);
+		dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+			    etnaviv_domain->base.bad_page_cpu,
+			    etnaviv_domain->base.bad_page_dma);
 
 	if (etnaviv_domain->pta_cpu)
-		dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-				  etnaviv_domain->pta_cpu,
-				  etnaviv_domain->pta_dma);
+		dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+			    etnaviv_domain->pta_cpu, etnaviv_domain->pta_dma);
 
 	if (etnaviv_domain->mtlb_cpu)
-		dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-				  etnaviv_domain->mtlb_cpu,
-				  etnaviv_domain->mtlb_dma);
-
-	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++) {
-		if (etnaviv_domain->stlb_cpu[i])
-			dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-					  etnaviv_domain->stlb_cpu[i],
-					  etnaviv_domain->stlb_dma[i]);
-	}
+		dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+			    etnaviv_domain->mtlb_cpu, etnaviv_domain->mtlb_dma);
 
 	return ret;
 }
@@ -188,23 +179,21 @@ static void etnaviv_iommuv2_domain_free(struct etnaviv_iommu_domain *domain)
 			to_etnaviv_domain(domain);
 	int i;
 
-	dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-			  etnaviv_domain->base.bad_page_cpu,
-			  etnaviv_domain->base.bad_page_dma);
+	dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+		    etnaviv_domain->base.bad_page_cpu,
+		    etnaviv_domain->base.bad_page_dma);
 
-	dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-			  etnaviv_domain->pta_cpu,
-			  etnaviv_domain->pta_dma);
+	dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+		    etnaviv_domain->pta_cpu, etnaviv_domain->pta_dma);
 
-	dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-			  etnaviv_domain->mtlb_cpu,
-			  etnaviv_domain->mtlb_dma);
+	dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+		    etnaviv_domain->mtlb_cpu, etnaviv_domain->mtlb_dma);
 
 	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++) {
 		if (etnaviv_domain->stlb_cpu[i])
-			dma_free_coherent(etnaviv_domain->base.dev, SZ_4K,
-					  etnaviv_domain->stlb_cpu[i],
-					  etnaviv_domain->stlb_dma[i]);
+			dma_free_wc(etnaviv_domain->base.dev, SZ_4K,
+				    etnaviv_domain->stlb_cpu[i],
+				    etnaviv_domain->stlb_dma[i]);
 	}
 
 	vfree(etnaviv_domain);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 49e049713a52..8069f9f36a2e 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #include "common.xml.h"
@@ -162,22 +151,10 @@ static int etnaviv_iommu_find_iova(struct etnaviv_iommu *mmu,
 		bool found;
 
 		ret = drm_mm_insert_node_in_range(&mmu->mm, node,
-						  size, 0, 0,
-						  mmu->last_iova, U64_MAX,
-						  mode);
+						  size, 0, 0, 0, U64_MAX, mode);
 		if (ret != -ENOSPC)
 			break;
 
-		/*
-		 * If we did not search from the start of the MMU region,
-		 * try again in case there are free slots.
-		 */
-		if (mmu->last_iova) {
-			mmu->last_iova = 0;
-			mmu->need_flush = true;
-			continue;
-		}
-
 		/* Try to retire some entries */
 		drm_mm_scan_init(&scan, &mmu->mm, size, 0, 0, mode);
 
@@ -274,7 +251,6 @@ int etnaviv_iommu_map_gem(struct etnaviv_iommu *mmu,
 	if (ret < 0)
 		goto unlock;
 
-	mmu->last_iova = node->start + etnaviv_obj->base.size;
 	mapping->iova = node->start;
 	ret = etnaviv_iommu_map(mmu, node->start, sgt, etnaviv_obj->base.size,
 				ETNAVIV_PROT_READ | ETNAVIV_PROT_WRITE);
@@ -381,7 +357,6 @@ int etnaviv_iommu_get_suballoc_va(struct etnaviv_gpu *gpu, dma_addr_t paddr,
 			mutex_unlock(&mmu->lock);
 			return ret;
 		}
-		mmu->last_iova = vram_node->start + size;
 		gpu->mmu->need_flush = true;
 		mutex_unlock(&mmu->lock);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
index ab603f5166b1..a0db17ffb686 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (C) 2015 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2015-2018 Etnaviv Project
  */
 
 #ifndef __ETNAVIV_MMU_H__
@@ -59,7 +48,6 @@ struct etnaviv_iommu {
 	struct mutex lock;
 	struct list_head mappings;
 	struct drm_mm mm;
-	u32 last_iova;
 	bool need_flush;
 };
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
index 26dddfc41aac..9980d81a26e3 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Etnaviv Project
  * Copyright (C) 2017 Zodiac Inflight Innovations
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "etnaviv_gpu.h"
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.h b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.h
index c1653c64ab6b..4a9d508f6e10 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2017 Etnaviv Project
  * Copyright (C) 2017 Zodiac Inflight Innovations
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __ETNAVIV_PERFMON_H__
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 6cf0775dbcd7..a74eb57af15b 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/kthread.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.h b/drivers/gpu/drm/etnaviv/etnaviv_sched.h
index 097635fa78ae..c0a6796e22c9 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2017 Etnaviv Project
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __ETNAVIV_SCHED_H__
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 735ce47688f9..208bc27be3cc 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -1,6 +1,6 @@
 config DRM_EXYNOS
 	tristate "DRM Support for Samsung SoC EXYNOS Series"
-	depends on OF && DRM && (ARCH_S3C64XX || ARCH_EXYNOS || ARCH_MULTIPLATFORM)
+	depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM)
 	select DRM_KMS_HELPER
 	select VIDEOMODE_HELPERS
 	select SND_SOC_HDMI_CODEC if SND_SOC
@@ -95,21 +95,31 @@ config DRM_EXYNOS_G2D
 	help
 	  Choose this option if you want to use Exynos G2D for DRM.
 
+config DRM_EXYNOS_IPP
+	bool
+
 config DRM_EXYNOS_FIMC
 	bool "FIMC"
-	depends on BROKEN && MFD_SYSCON
+	select DRM_EXYNOS_IPP
 	help
 	  Choose this option if you want to use Exynos FIMC for DRM.
 
 config DRM_EXYNOS_ROTATOR
 	bool "Rotator"
-	depends on BROKEN
+	select DRM_EXYNOS_IPP
 	help
 	  Choose this option if you want to use Exynos Rotator for DRM.
 
+config DRM_EXYNOS_SCALER
+	bool "Scaler"
+	select DRM_EXYNOS_IPP
+	help
+	  Choose this option if you want to use Exynos Scaler for DRM.
+
 config DRM_EXYNOS_GSC
 	bool "GScaler"
-	depends on BROKEN && ARCH_EXYNOS5 && VIDEO_SAMSUNG_EXYNOS_GSC=n
+	depends on VIDEO_SAMSUNG_EXYNOS_GSC=n
+	select DRM_EXYNOS_IPP
 	help
 	  Choose this option if you want to use Exynos GSC for DRM.
 
diff --git a/drivers/gpu/drm/exynos/Makefile b/drivers/gpu/drm/exynos/Makefile
index a51c5459bb13..3b323f1e0475 100644
--- a/drivers/gpu/drm/exynos/Makefile
+++ b/drivers/gpu/drm/exynos/Makefile
@@ -18,8 +18,10 @@ exynosdrm-$(CONFIG_DRM_EXYNOS_MIXER)	+= exynos_mixer.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_HDMI)	+= exynos_hdmi.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_VIDI)	+= exynos_drm_vidi.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_G2D)	+= exynos_drm_g2d.o
+exynosdrm-$(CONFIG_DRM_EXYNOS_IPP)	+= exynos_drm_ipp.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_FIMC)	+= exynos_drm_fimc.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_ROTATOR)	+= exynos_drm_rotator.o
+exynosdrm-$(CONFIG_DRM_EXYNOS_SCALER)	+= exynos_drm_scaler.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_GSC)	+= exynos_drm_gsc.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_MIC)     += exynos_drm_mic.o
 
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 1c330f2a7a5d..82c95c34447f 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -31,7 +31,10 @@
 #define DSD_CFG_MUX 0x1004
 #define DSD_CFG_MUX_TE_UNMASK_GLOBAL BIT(13)
 
-#define WINDOWS_NR	3
+#define WINDOWS_NR	5
+#define PRIMARY_WIN	2
+#define CURSON_WIN	4
+
 #define MIN_FB_WIDTH_FOR_16WORD_BURST	128
 
 #define I80_HW_TRG	(1 << 0)
@@ -43,6 +46,9 @@ static const char * const decon_clks_name[] = {
 	"aclk_smmu_decon0x",
 	"aclk_xiu_decon0x",
 	"pclk_smmu_decon0x",
+	"aclk_smmu_decon1x",
+	"aclk_xiu_decon1x",
+	"pclk_smmu_decon1x",
 	"sclk_decon_vclk",
 	"sclk_decon_eclk",
 };
@@ -74,9 +80,8 @@ static const uint32_t decon_formats[] = {
 };
 
 static const enum drm_plane_type decon_win_types[WINDOWS_NR] = {
-	DRM_PLANE_TYPE_PRIMARY,
-	DRM_PLANE_TYPE_OVERLAY,
-	DRM_PLANE_TYPE_CURSOR,
+	[PRIMARY_WIN] = DRM_PLANE_TYPE_PRIMARY,
+	[CURSON_WIN] = DRM_PLANE_TYPE_CURSOR,
 };
 
 static inline void decon_set_bits(struct decon_context *ctx, u32 reg, u32 mask,
@@ -552,12 +557,10 @@ static int decon_bind(struct device *dev, struct device *master, void *data)
 	drm_dev->max_vblank_count = 0xffffffff;
 
 	for (win = ctx->first_win; win < WINDOWS_NR; win++) {
-		int tmp = (win == ctx->first_win) ? 0 : win;
-
 		ctx->configs[win].pixel_formats = decon_formats;
 		ctx->configs[win].num_pixel_formats = ARRAY_SIZE(decon_formats);
-		ctx->configs[win].zpos = win;
-		ctx->configs[win].type = decon_win_types[tmp];
+		ctx->configs[win].zpos = win - ctx->first_win;
+		ctx->configs[win].type = decon_win_types[win];
 
 		ret = exynos_plane_init(drm_dev, &ctx->planes[win], win,
 					&ctx->configs[win]);
@@ -565,7 +568,7 @@ static int decon_bind(struct device *dev, struct device *master, void *data)
 			return ret;
 	}
 
-	exynos_plane = &ctx->planes[ctx->first_win];
+	exynos_plane = &ctx->planes[PRIMARY_WIN];
 	out_type = (ctx->out_type & IFTYPE_HDMI) ? EXYNOS_DISPLAY_TYPE_HDMI
 						  : EXYNOS_DISPLAY_TYPE_LCD;
 	ctx->crtc = exynos_drm_crtc_create(drm_dev, &exynos_plane->base,
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 964831dab102..86330f396784 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -162,7 +162,7 @@ static int exynos_dp_bind(struct device *dev, struct device *master, void *data)
 	dp->drm_dev = drm_dev;
 
 	dp->plat_data.dev_type = EXYNOS_DP;
-	dp->plat_data.power_on = exynos_dp_poweron;
+	dp->plat_data.power_on_start = exynos_dp_poweron;
 	dp->plat_data.power_off = exynos_dp_poweroff;
 	dp->plat_data.attach = exynos_dp_bridge_attach;
 	dp->plat_data.get_modes = exynos_dp_get_modes;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index dc01342e759a..eea90251808f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -228,7 +228,7 @@ struct exynos_drm_crtc *exynos_drm_crtc_get_by_type(struct drm_device *drm_dev,
 		if (to_exynos_crtc(crtc)->type == out_type)
 			return to_exynos_crtc(crtc);
 
-	return ERR_PTR(-EPERM);
+	return ERR_PTR(-ENODEV);
 }
 
 int exynos_drm_set_possible_crtcs(struct drm_encoder *encoder,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index a518e9c6d6cc..a81b4a5e24a7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -27,35 +27,23 @@
 #include "exynos_drm_fb.h"
 #include "exynos_drm_gem.h"
 #include "exynos_drm_plane.h"
+#include "exynos_drm_ipp.h"
 #include "exynos_drm_vidi.h"
 #include "exynos_drm_g2d.h"
 #include "exynos_drm_iommu.h"
 
 #define DRIVER_NAME	"exynos"
 #define DRIVER_DESC	"Samsung SoC DRM"
-#define DRIVER_DATE	"20110530"
-#define DRIVER_MAJOR	1
-#define DRIVER_MINOR	0
-
-int exynos_atomic_check(struct drm_device *dev,
-			struct drm_atomic_state *state)
-{
-	int ret;
-
-	ret = drm_atomic_helper_check_modeset(dev, state);
-	if (ret)
-		return ret;
+#define DRIVER_DATE	"20180330"
 
-	ret = drm_atomic_normalize_zpos(dev, state);
-	if (ret)
-		return ret;
-
-	ret = drm_atomic_helper_check_planes(dev, state);
-	if (ret)
-		return ret;
-
-	return ret;
-}
+/*
+ * Interface history:
+ *
+ * 1.0 - Original version
+ * 1.1 - Upgrade IPP driver to version 2.0
+ */
+#define DRIVER_MAJOR	1
+#define DRIVER_MINOR	1
 
 static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 {
@@ -108,6 +96,16 @@ static const struct drm_ioctl_desc exynos_ioctls[] = {
 			DRM_AUTH | DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(EXYNOS_G2D_EXEC, exynos_g2d_exec_ioctl,
 			DRM_AUTH | DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(EXYNOS_IPP_GET_RESOURCES,
+			exynos_drm_ipp_get_res_ioctl,
+			DRM_AUTH | DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(EXYNOS_IPP_GET_CAPS, exynos_drm_ipp_get_caps_ioctl,
+			DRM_AUTH | DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(EXYNOS_IPP_GET_LIMITS,
+			exynos_drm_ipp_get_limits_ioctl,
+			DRM_AUTH | DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(EXYNOS_IPP_COMMIT, exynos_drm_ipp_commit_ioctl,
+			DRM_AUTH | DRM_RENDER_ALLOW),
 };
 
 static const struct file_operations exynos_drm_driver_fops = {
@@ -204,6 +202,7 @@ struct exynos_drm_driver_info {
 #define DRM_COMPONENT_DRIVER	BIT(0)	/* supports component framework */
 #define DRM_VIRTUAL_DEVICE	BIT(1)	/* create virtual platform device */
 #define DRM_DMA_DEVICE		BIT(2)	/* can be used for dma allocations */
+#define DRM_FIMC_DEVICE		BIT(3)	/* devices shared with V4L2 subsystem */
 
 #define DRV_PTR(drv, cond) (IS_ENABLED(cond) ? &drv : NULL)
 
@@ -243,10 +242,16 @@ static struct exynos_drm_driver_info exynos_drm_drivers[] = {
 		DRV_PTR(g2d_driver, CONFIG_DRM_EXYNOS_G2D),
 	}, {
 		DRV_PTR(fimc_driver, CONFIG_DRM_EXYNOS_FIMC),
+		DRM_COMPONENT_DRIVER | DRM_FIMC_DEVICE,
 	}, {
 		DRV_PTR(rotator_driver, CONFIG_DRM_EXYNOS_ROTATOR),
+		DRM_COMPONENT_DRIVER
+	}, {
+		DRV_PTR(scaler_driver, CONFIG_DRM_EXYNOS_SCALER),
+		DRM_COMPONENT_DRIVER
 	}, {
 		DRV_PTR(gsc_driver, CONFIG_DRM_EXYNOS_GSC),
+		DRM_COMPONENT_DRIVER
 	}, {
 		&exynos_drm_platform_driver,
 		DRM_VIRTUAL_DEVICE
@@ -274,7 +279,11 @@ static struct component_match *exynos_drm_match_add(struct device *dev)
 					    &info->driver->driver,
 					    (void *)platform_bus_type.match))) {
 			put_device(p);
-			component_match_add(dev, &match, compare_dev, d);
+
+			if (!(info->flags & DRM_FIMC_DEVICE) ||
+			    exynos_drm_check_fimc_device(d) == 0)
+				component_match_add(dev, &match,
+						    compare_dev, d);
 			p = d;
 		}
 		put_device(p);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index df2262f70d91..0f6d079a55c9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -273,9 +273,17 @@ static inline int exynos_dpi_bind(struct drm_device *dev,
 }
 #endif
 
+#ifdef CONFIG_DRM_EXYNOS_FIMC
+int exynos_drm_check_fimc_device(struct device *dev);
+#else
+static inline int exynos_drm_check_fimc_device(struct device *dev)
+{
+	return 0;
+}
+#endif
+
 int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state,
 			 bool nonblock);
-int exynos_atomic_check(struct drm_device *dev, struct drm_atomic_state *state);
 
 
 extern struct platform_driver fimd_driver;
@@ -289,6 +297,7 @@ extern struct platform_driver vidi_driver;
 extern struct platform_driver g2d_driver;
 extern struct platform_driver fimc_driver;
 extern struct platform_driver rotator_driver;
+extern struct platform_driver scaler_driver;
 extern struct platform_driver gsc_driver;
 extern struct platform_driver mic_driver;
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 7904ffa9abfb..7c3030b7e586 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -270,7 +270,6 @@ struct exynos_dsi {
 	u32 lanes;
 	u32 mode_flags;
 	u32 format;
-	struct videomode vm;
 
 	int state;
 	struct drm_property *brightness;
@@ -881,30 +880,30 @@ static int exynos_dsi_init_link(struct exynos_dsi *dsi)
 
 static void exynos_dsi_set_display_mode(struct exynos_dsi *dsi)
 {
-	struct videomode *vm = &dsi->vm;
+	struct drm_display_mode *m = &dsi->encoder.crtc->state->adjusted_mode;
 	unsigned int num_bits_resol = dsi->driver_data->num_bits_resol;
 	u32 reg;
 
 	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
 		reg = DSIM_CMD_ALLOW(0xf)
-			| DSIM_STABLE_VFP(vm->vfront_porch)
-			| DSIM_MAIN_VBP(vm->vback_porch);
+			| DSIM_STABLE_VFP(m->vsync_start - m->vdisplay)
+			| DSIM_MAIN_VBP(m->vtotal - m->vsync_end);
 		exynos_dsi_write(dsi, DSIM_MVPORCH_REG, reg);
 
-		reg = DSIM_MAIN_HFP(vm->hfront_porch)
-			| DSIM_MAIN_HBP(vm->hback_porch);
+		reg = DSIM_MAIN_HFP(m->hsync_start - m->hdisplay)
+			| DSIM_MAIN_HBP(m->htotal - m->hsync_end);
 		exynos_dsi_write(dsi, DSIM_MHPORCH_REG, reg);
 
-		reg = DSIM_MAIN_VSA(vm->vsync_len)
-			| DSIM_MAIN_HSA(vm->hsync_len);
+		reg = DSIM_MAIN_VSA(m->vsync_end - m->vsync_start)
+			| DSIM_MAIN_HSA(m->hsync_end - m->hsync_start);
 		exynos_dsi_write(dsi, DSIM_MSYNC_REG, reg);
 	}
-	reg =  DSIM_MAIN_HRESOL(vm->hactive, num_bits_resol) |
-		DSIM_MAIN_VRESOL(vm->vactive, num_bits_resol);
+	reg =  DSIM_MAIN_HRESOL(m->hdisplay, num_bits_resol) |
+		DSIM_MAIN_VRESOL(m->vdisplay, num_bits_resol);
 
 	exynos_dsi_write(dsi, DSIM_MDRESOL_REG, reg);
 
-	dev_dbg(dsi->dev, "LCD size = %dx%d\n", vm->hactive, vm->vactive);
+	dev_dbg(dsi->dev, "LCD size = %dx%d\n", m->hdisplay, m->vdisplay);
 }
 
 static void exynos_dsi_set_display_enable(struct exynos_dsi *dsi, bool enable)
@@ -1265,15 +1264,15 @@ static irqreturn_t exynos_dsi_irq(int irq, void *dev_id)
 
 	if (status & DSIM_INT_SW_RST_RELEASE) {
 		u32 mask = ~(DSIM_INT_RX_DONE | DSIM_INT_SFR_FIFO_EMPTY |
-			DSIM_INT_SFR_HDR_FIFO_EMPTY | DSIM_INT_FRAME_DONE |
-			DSIM_INT_RX_ECC_ERR | DSIM_INT_SW_RST_RELEASE);
+			DSIM_INT_SFR_HDR_FIFO_EMPTY | DSIM_INT_RX_ECC_ERR |
+			DSIM_INT_SW_RST_RELEASE);
 		exynos_dsi_write(dsi, DSIM_INTMSK_REG, mask);
 		complete(&dsi->completed);
 		return IRQ_HANDLED;
 	}
 
 	if (!(status & (DSIM_INT_RX_DONE | DSIM_INT_SFR_FIFO_EMPTY |
-			DSIM_INT_FRAME_DONE | DSIM_INT_PLL_STABLE)))
+			DSIM_INT_PLL_STABLE)))
 		return IRQ_HANDLED;
 
 	if (exynos_dsi_transfer_finish(dsi))
@@ -1485,26 +1484,7 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder)
 	return 0;
 }
 
-static void exynos_dsi_mode_set(struct drm_encoder *encoder,
-				struct drm_display_mode *mode,
-				struct drm_display_mode *adjusted_mode)
-{
-	struct exynos_dsi *dsi = encoder_to_dsi(encoder);
-	struct videomode *vm = &dsi->vm;
-	struct drm_display_mode *m = adjusted_mode;
-
-	vm->hactive = m->hdisplay;
-	vm->vactive = m->vdisplay;
-	vm->vfront_porch = m->vsync_start - m->vdisplay;
-	vm->vback_porch = m->vtotal - m->vsync_end;
-	vm->vsync_len = m->vsync_end - m->vsync_start;
-	vm->hfront_porch = m->hsync_start - m->hdisplay;
-	vm->hback_porch = m->htotal - m->hsync_end;
-	vm->hsync_len = m->hsync_end - m->hsync_start;
-}
-
 static const struct drm_encoder_helper_funcs exynos_dsi_encoder_helper_funcs = {
-	.mode_set = exynos_dsi_mode_set,
 	.enable = exynos_dsi_enable,
 	.disable = exynos_dsi_disable,
 };
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 0faaf829f5bf..7fcc1a7ab1a0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -18,6 +18,7 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <uapi/drm/exynos_drm.h>
 
 #include "exynos_drm_drv.h"
@@ -26,20 +27,6 @@
 #include "exynos_drm_iommu.h"
 #include "exynos_drm_crtc.h"
 
-#define to_exynos_fb(x)	container_of(x, struct exynos_drm_fb, fb)
-
-/*
- * exynos specific framebuffer structure.
- *
- * @fb: drm framebuffer obejct.
- * @exynos_gem: array of exynos specific gem object containing a gem object.
- */
-struct exynos_drm_fb {
-	struct drm_framebuffer	fb;
-	struct exynos_drm_gem	*exynos_gem[MAX_FB_BUFFER];
-	dma_addr_t			dma_addr[MAX_FB_BUFFER];
-};
-
 static int check_fb_gem_memory_type(struct drm_device *drm_dev,
 				    struct exynos_drm_gem *exynos_gem)
 {
@@ -66,40 +53,9 @@ static int check_fb_gem_memory_type(struct drm_device *drm_dev,
 	return 0;
 }
 
-static void exynos_drm_fb_destroy(struct drm_framebuffer *fb)
-{
-	struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
-	unsigned int i;
-
-	drm_framebuffer_cleanup(fb);
-
-	for (i = 0; i < ARRAY_SIZE(exynos_fb->exynos_gem); i++) {
-		struct drm_gem_object *obj;
-
-		if (exynos_fb->exynos_gem[i] == NULL)
-			continue;
-
-		obj = &exynos_fb->exynos_gem[i]->base;
-		drm_gem_object_unreference_unlocked(obj);
-	}
-
-	kfree(exynos_fb);
-	exynos_fb = NULL;
-}
-
-static int exynos_drm_fb_create_handle(struct drm_framebuffer *fb,
-					struct drm_file *file_priv,
-					unsigned int *handle)
-{
-	struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
-
-	return drm_gem_handle_create(file_priv,
-				     &exynos_fb->exynos_gem[0]->base, handle);
-}
-
 static const struct drm_framebuffer_funcs exynos_drm_fb_funcs = {
-	.destroy	= exynos_drm_fb_destroy,
-	.create_handle	= exynos_drm_fb_create_handle,
+	.destroy	= drm_gem_fb_destroy,
+	.create_handle	= drm_gem_fb_create_handle,
 };
 
 struct drm_framebuffer *
@@ -108,12 +64,12 @@ exynos_drm_framebuffer_init(struct drm_device *dev,
 			    struct exynos_drm_gem **exynos_gem,
 			    int count)
 {
-	struct exynos_drm_fb *exynos_fb;
+	struct drm_framebuffer *fb;
 	int i;
 	int ret;
 
-	exynos_fb = kzalloc(sizeof(*exynos_fb), GFP_KERNEL);
-	if (!exynos_fb)
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < count; i++) {
@@ -121,23 +77,21 @@ exynos_drm_framebuffer_init(struct drm_device *dev,
 		if (ret < 0)
 			goto err;
 
-		exynos_fb->exynos_gem[i] = exynos_gem[i];
-		exynos_fb->dma_addr[i] = exynos_gem[i]->dma_addr
-						+ mode_cmd->offsets[i];
+		fb->obj[i] = &exynos_gem[i]->base;
 	}
 
-	drm_helper_mode_fill_fb_struct(dev, &exynos_fb->fb, mode_cmd);
+	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
 
-	ret = drm_framebuffer_init(dev, &exynos_fb->fb, &exynos_drm_fb_funcs);
+	ret = drm_framebuffer_init(dev, fb, &exynos_drm_fb_funcs);
 	if (ret < 0) {
 		DRM_ERROR("failed to initialize framebuffer\n");
 		goto err;
 	}
 
-	return &exynos_fb->fb;
+	return fb;
 
 err:
-	kfree(exynos_fb);
+	kfree(fb);
 	return ERR_PTR(ret);
 }
 
@@ -191,12 +145,13 @@ err:
 
 dma_addr_t exynos_drm_fb_dma_addr(struct drm_framebuffer *fb, int index)
 {
-	struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
+	struct exynos_drm_gem *exynos_gem;
 
 	if (WARN_ON_ONCE(index >= MAX_FB_BUFFER))
 		return 0;
 
-	return exynos_fb->dma_addr[index];
+	exynos_gem = to_exynos_gem(fb->obj[index]);
+	return exynos_gem->dma_addr + fb->offsets[index];
 }
 
 static struct drm_mode_config_helper_funcs exynos_drm_mode_config_helpers = {
@@ -206,7 +161,7 @@ static struct drm_mode_config_helper_funcs exynos_drm_mode_config_helpers = {
 static const struct drm_mode_config_funcs exynos_drm_mode_config_funcs = {
 	.fb_create = exynos_user_fb_create,
 	.output_poll_changed = drm_fb_helper_output_poll_changed,
-	.atomic_check = exynos_atomic_check,
+	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
 };
 
@@ -227,4 +182,6 @@ void exynos_drm_mode_config_init(struct drm_device *dev)
 	dev->mode_config.helper_private = &exynos_drm_mode_config_helpers;
 
 	dev->mode_config.allow_fb_modifiers = true;
+
+	dev->mode_config.normalize_zpos = true;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 5b18b5c5fdf2..5ce84025d1cb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -12,6 +12,7 @@
  *
  */
 #include <linux/kernel.h>
+#include <linux/component.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
@@ -24,8 +25,8 @@
 #include <drm/exynos_drm.h>
 #include "regs-fimc.h"
 #include "exynos_drm_drv.h"
+#include "exynos_drm_iommu.h"
 #include "exynos_drm_ipp.h"
-#include "exynos_drm_fimc.h"
 
 /*
  * FIMC stands for Fully Interactive Mobile Camera and
@@ -33,23 +34,6 @@
  * input DMA reads image data from the memory.
  * output DMA writes image data to memory.
  * FIMC supports image rotation and image effect functions.
- *
- * M2M operation : supports crop/scale/rotation/csc so on.
- * Memory ----> FIMC H/W ----> Memory.
- * Writeback operation : supports cloned screen with FIMD.
- * FIMD ----> FIMC H/W ----> Memory.
- * Output operation : supports direct display using local path.
- * Memory ----> FIMC H/W ----> FIMD.
- */
-
-/*
- * TODO
- * 1. check suspend/resume api if needed.
- * 2. need to check use case platform_device_id.
- * 3. check src/dst size with, height.
- * 4. added check_prepare api for right register.
- * 5. need to add supported list in prop_list.
- * 6. check prescaler/scaler optimization.
  */
 
 #define FIMC_MAX_DEVS	4
@@ -59,29 +43,19 @@
 #define FIMC_BUF_STOP	1
 #define FIMC_BUF_START	2
 #define FIMC_WIDTH_ITU_709	1280
-#define FIMC_REFRESH_MAX	60
-#define FIMC_REFRESH_MIN	12
-#define FIMC_CROP_MAX	8192
-#define FIMC_CROP_MIN	32
-#define FIMC_SCALE_MAX	4224
-#define FIMC_SCALE_MIN	32
+#define FIMC_AUTOSUSPEND_DELAY	2000
+
+static unsigned int fimc_mask = 0xc;
+module_param_named(fimc_devs, fimc_mask, uint, 0644);
+MODULE_PARM_DESC(fimc_devs, "Alias mask for assigning FIMC devices to Exynos DRM");
 
 #define get_fimc_context(dev)	platform_get_drvdata(to_platform_device(dev))
-#define get_ctx_from_ippdrv(ippdrv)	container_of(ippdrv,\
-					struct fimc_context, ippdrv);
-enum fimc_wb {
-	FIMC_WB_NONE,
-	FIMC_WB_A,
-	FIMC_WB_B,
-};
 
 enum {
 	FIMC_CLK_LCLK,
 	FIMC_CLK_GATE,
 	FIMC_CLK_WB_A,
 	FIMC_CLK_WB_B,
-	FIMC_CLK_MUX,
-	FIMC_CLK_PARENT,
 	FIMC_CLKS_MAX
 };
 
@@ -90,12 +64,8 @@ static const char * const fimc_clock_names[] = {
 	[FIMC_CLK_GATE]   = "fimc",
 	[FIMC_CLK_WB_A]   = "pxl_async0",
 	[FIMC_CLK_WB_B]   = "pxl_async1",
-	[FIMC_CLK_MUX]    = "mux",
-	[FIMC_CLK_PARENT] = "parent",
 };
 
-#define FIMC_DEFAULT_LCLK_FREQUENCY 133000000UL
-
 /*
  * A structure of scaler.
  *
@@ -107,7 +77,7 @@ static const char * const fimc_clock_names[] = {
  * @vratio: vertical ratio.
  */
 struct fimc_scaler {
-	bool	range;
+	bool range;
 	bool bypass;
 	bool up_h;
 	bool up_v;
@@ -116,56 +86,32 @@ struct fimc_scaler {
 };
 
 /*
- * A structure of scaler capability.
- *
- * find user manual table 43-1.
- * @in_hori: scaler input horizontal size.
- * @bypass: scaler bypass mode.
- * @dst_h_wo_rot: target horizontal size without output rotation.
- * @dst_h_rot: target horizontal size with output rotation.
- * @rl_w_wo_rot: real width without input rotation.
- * @rl_h_rot: real height without output rotation.
- */
-struct fimc_capability {
-	/* scaler */
-	u32	in_hori;
-	u32	bypass;
-	/* output rotator */
-	u32	dst_h_wo_rot;
-	u32	dst_h_rot;
-	/* input rotator */
-	u32	rl_w_wo_rot;
-	u32	rl_h_rot;
-};
-
-/*
  * A structure of fimc context.
  *
- * @ippdrv: prepare initialization using ippdrv.
  * @regs_res: register resources.
  * @regs: memory mapped io registers.
  * @lock: locking of operations.
  * @clocks: fimc clocks.
- * @clk_frequency: LCLK clock frequency.
- * @sysreg: handle to SYSREG block regmap.
  * @sc: scaler infomations.
  * @pol: porarity of writeback.
  * @id: fimc id.
  * @irq: irq number.
- * @suspended: qos operations.
  */
 struct fimc_context {
-	struct exynos_drm_ippdrv	ippdrv;
+	struct exynos_drm_ipp ipp;
+	struct drm_device *drm_dev;
+	struct device	*dev;
+	struct exynos_drm_ipp_task	*task;
+	struct exynos_drm_ipp_formats	*formats;
+	unsigned int			num_formats;
+
 	struct resource	*regs_res;
 	void __iomem	*regs;
 	spinlock_t	lock;
 	struct clk	*clocks[FIMC_CLKS_MAX];
-	u32		clk_frequency;
-	struct regmap	*sysreg;
 	struct fimc_scaler	sc;
 	int	id;
 	int	irq;
-	bool	suspended;
 };
 
 static u32 fimc_read(struct fimc_context *ctx, u32 reg)
@@ -217,19 +163,10 @@ static void fimc_sw_reset(struct fimc_context *ctx)
 	fimc_write(ctx, 0x0, EXYNOS_CIFCNTSEQ);
 }
 
-static int fimc_set_camblk_fimd0_wb(struct fimc_context *ctx)
-{
-	return regmap_update_bits(ctx->sysreg, SYSREG_CAMERA_BLK,
-				  SYSREG_FIMD0WB_DEST_MASK,
-				  ctx->id << SYSREG_FIMD0WB_DEST_SHIFT);
-}
-
-static void fimc_set_type_ctrl(struct fimc_context *ctx, enum fimc_wb wb)
+static void fimc_set_type_ctrl(struct fimc_context *ctx)
 {
 	u32 cfg;
 
-	DRM_DEBUG_KMS("wb[%d]\n", wb);
-
 	cfg = fimc_read(ctx, EXYNOS_CIGCTRL);
 	cfg &= ~(EXYNOS_CIGCTRL_TESTPATTERN_MASK |
 		EXYNOS_CIGCTRL_SELCAM_ITU_MASK |
@@ -238,23 +175,10 @@ static void fimc_set_type_ctrl(struct fimc_context *ctx, enum fimc_wb wb)
 		EXYNOS_CIGCTRL_SELWB_CAMIF_MASK |
 		EXYNOS_CIGCTRL_SELWRITEBACK_MASK);
 
-	switch (wb) {
-	case FIMC_WB_A:
-		cfg |= (EXYNOS_CIGCTRL_SELWRITEBACK_A |
-			EXYNOS_CIGCTRL_SELWB_CAMIF_WRITEBACK);
-		break;
-	case FIMC_WB_B:
-		cfg |= (EXYNOS_CIGCTRL_SELWRITEBACK_B |
-			EXYNOS_CIGCTRL_SELWB_CAMIF_WRITEBACK);
-		break;
-	case FIMC_WB_NONE:
-	default:
-		cfg |= (EXYNOS_CIGCTRL_SELCAM_ITU_A |
-			EXYNOS_CIGCTRL_SELWRITEBACK_A |
-			EXYNOS_CIGCTRL_SELCAM_MIPI_A |
-			EXYNOS_CIGCTRL_SELCAM_FIMC_ITU);
-		break;
-	}
+	cfg |= (EXYNOS_CIGCTRL_SELCAM_ITU_A |
+		EXYNOS_CIGCTRL_SELWRITEBACK_A |
+		EXYNOS_CIGCTRL_SELCAM_MIPI_A |
+		EXYNOS_CIGCTRL_SELCAM_FIMC_ITU);
 
 	fimc_write(ctx, cfg, EXYNOS_CIGCTRL);
 }
@@ -296,7 +220,6 @@ static void fimc_clear_irq(struct fimc_context *ctx)
 
 static bool fimc_check_ovf(struct fimc_context *ctx)
 {
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 status, flag;
 
 	status = fimc_read(ctx, EXYNOS_CISTATUS);
@@ -310,7 +233,7 @@ static bool fimc_check_ovf(struct fimc_context *ctx)
 			EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
 			EXYNOS_CIWDOFST_CLROVFICR);
 
-		dev_err(ippdrv->dev, "occurred overflow at %d, status 0x%x.\n",
+		dev_err(ctx->dev, "occurred overflow at %d, status 0x%x.\n",
 			ctx->id, status);
 		return true;
 	}
@@ -376,10 +299,8 @@ static void fimc_handle_lastend(struct fimc_context *ctx, bool enable)
 	fimc_write(ctx, cfg, EXYNOS_CIOCTRL);
 }
 
-
-static int fimc_src_set_fmt_order(struct fimc_context *ctx, u32 fmt)
+static void fimc_src_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 {
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg;
 
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
@@ -392,12 +313,12 @@ static int fimc_src_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 	case DRM_FORMAT_RGB565:
 		cfg |= EXYNOS_CISCCTRL_INRGB_FMT_RGB565;
 		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
-		return 0;
+		return;
 	case DRM_FORMAT_RGB888:
 	case DRM_FORMAT_XRGB8888:
 		cfg |= EXYNOS_CISCCTRL_INRGB_FMT_RGB888;
 		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
-		return 0;
+		return;
 	default:
 		/* bypass */
 		break;
@@ -438,20 +359,13 @@ static int fimc_src_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 		cfg |= (EXYNOS_MSCTRL_ORDER2P_LSB_CBCR |
 			EXYNOS_MSCTRL_C_INT_IN_2PLANE);
 		break;
-	default:
-		dev_err(ippdrv->dev, "invalid source yuv order 0x%x.\n", fmt);
-		return -EINVAL;
 	}
 
 	fimc_write(ctx, cfg, EXYNOS_MSCTRL);
-
-	return 0;
 }
 
-static int fimc_src_set_fmt(struct device *dev, u32 fmt)
+static void fimc_src_set_fmt(struct fimc_context *ctx, u32 fmt, bool tiled)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg;
 
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
@@ -485,9 +399,6 @@ static int fimc_src_set_fmt(struct device *dev, u32 fmt)
 	case DRM_FORMAT_NV21:
 		cfg |= EXYNOS_MSCTRL_INFORMAT_YCBCR420;
 		break;
-	default:
-		dev_err(ippdrv->dev, "invalid source format 0x%x.\n", fmt);
-		return -EINVAL;
 	}
 
 	fimc_write(ctx, cfg, EXYNOS_MSCTRL);
@@ -495,22 +406,22 @@ static int fimc_src_set_fmt(struct device *dev, u32 fmt)
 	cfg = fimc_read(ctx, EXYNOS_CIDMAPARAM);
 	cfg &= ~EXYNOS_CIDMAPARAM_R_MODE_MASK;
 
-	cfg |= EXYNOS_CIDMAPARAM_R_MODE_LINEAR;
+	if (tiled)
+		cfg |= EXYNOS_CIDMAPARAM_R_MODE_64X32;
+	else
+		cfg |= EXYNOS_CIDMAPARAM_R_MODE_LINEAR;
 
 	fimc_write(ctx, cfg, EXYNOS_CIDMAPARAM);
 
-	return fimc_src_set_fmt_order(ctx, fmt);
+	fimc_src_set_fmt_order(ctx, fmt);
 }
 
-static int fimc_src_set_transf(struct device *dev,
-		enum drm_exynos_degree degree,
-		enum drm_exynos_flip flip, bool *swap)
+static void fimc_src_set_transf(struct fimc_context *ctx, unsigned int rotation)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	unsigned int degree = rotation & DRM_MODE_ROTATE_MASK;
 	u32 cfg1, cfg2;
 
-	DRM_DEBUG_KMS("degree[%d]flip[0x%x]\n", degree, flip);
+	DRM_DEBUG_KMS("rotation[%x]\n", rotation);
 
 	cfg1 = fimc_read(ctx, EXYNOS_MSCTRL);
 	cfg1 &= ~(EXYNOS_MSCTRL_FLIP_X_MIRROR |
@@ -520,61 +431,56 @@ static int fimc_src_set_transf(struct device *dev,
 	cfg2 &= ~EXYNOS_CITRGFMT_INROT90_CLOCKWISE;
 
 	switch (degree) {
-	case EXYNOS_DRM_DEGREE_0:
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+	case DRM_MODE_ROTATE_0:
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg1 |= EXYNOS_MSCTRL_FLIP_X_MIRROR;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg1 |= EXYNOS_MSCTRL_FLIP_Y_MIRROR;
 		break;
-	case EXYNOS_DRM_DEGREE_90:
+	case DRM_MODE_ROTATE_90:
 		cfg2 |= EXYNOS_CITRGFMT_INROT90_CLOCKWISE;
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg1 |= EXYNOS_MSCTRL_FLIP_X_MIRROR;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg1 |= EXYNOS_MSCTRL_FLIP_Y_MIRROR;
 		break;
-	case EXYNOS_DRM_DEGREE_180:
+	case DRM_MODE_ROTATE_180:
 		cfg1 |= (EXYNOS_MSCTRL_FLIP_X_MIRROR |
 			EXYNOS_MSCTRL_FLIP_Y_MIRROR);
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg1 &= ~EXYNOS_MSCTRL_FLIP_X_MIRROR;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg1 &= ~EXYNOS_MSCTRL_FLIP_Y_MIRROR;
 		break;
-	case EXYNOS_DRM_DEGREE_270:
+	case DRM_MODE_ROTATE_270:
 		cfg1 |= (EXYNOS_MSCTRL_FLIP_X_MIRROR |
 			EXYNOS_MSCTRL_FLIP_Y_MIRROR);
 		cfg2 |= EXYNOS_CITRGFMT_INROT90_CLOCKWISE;
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg1 &= ~EXYNOS_MSCTRL_FLIP_X_MIRROR;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg1 &= ~EXYNOS_MSCTRL_FLIP_Y_MIRROR;
 		break;
-	default:
-		dev_err(ippdrv->dev, "invalid degree value %d.\n", degree);
-		return -EINVAL;
 	}
 
 	fimc_write(ctx, cfg1, EXYNOS_MSCTRL);
 	fimc_write(ctx, cfg2, EXYNOS_CITRGFMT);
-	*swap = (cfg2 & EXYNOS_CITRGFMT_INROT90_CLOCKWISE) ? 1 : 0;
-
-	return 0;
 }
 
-static int fimc_set_window(struct fimc_context *ctx,
-		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz)
+static void fimc_set_window(struct fimc_context *ctx,
+			    struct exynos_drm_ipp_buffer *buf)
 {
 	u32 cfg, h1, h2, v1, v2;
 
 	/* cropped image */
-	h1 = pos->x;
-	h2 = sz->hsize - pos->w - pos->x;
-	v1 = pos->y;
-	v2 = sz->vsize - pos->h - pos->y;
+	h1 = buf->rect.x;
+	h2 = buf->buf.width - buf->rect.w - buf->rect.x;
+	v1 = buf->rect.y;
+	v2 = buf->buf.height - buf->rect.h - buf->rect.y;
 
 	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]hsize[%d]vsize[%d]\n",
-		pos->x, pos->y, pos->w, pos->h, sz->hsize, sz->vsize);
+		buf->rect.x, buf->rect.y, buf->rect.w, buf->rect.h,
+		buf->buf.width, buf->buf.height);
 	DRM_DEBUG_KMS("h1[%d]h2[%d]v1[%d]v2[%d]\n", h1, h2, v1, v2);
 
 	/*
@@ -592,42 +498,30 @@ static int fimc_set_window(struct fimc_context *ctx,
 	cfg = (EXYNOS_CIWDOFST2_WINHOROFST2(h2) |
 		EXYNOS_CIWDOFST2_WINVEROFST2(v2));
 	fimc_write(ctx, cfg, EXYNOS_CIWDOFST2);
-
-	return 0;
 }
 
-static int fimc_src_set_size(struct device *dev, int swap,
-		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz)
+static void fimc_src_set_size(struct fimc_context *ctx,
+			      struct exynos_drm_ipp_buffer *buf)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct drm_exynos_pos img_pos = *pos;
-	struct drm_exynos_sz img_sz = *sz;
 	u32 cfg;
 
-	DRM_DEBUG_KMS("swap[%d]hsize[%d]vsize[%d]\n",
-		swap, sz->hsize, sz->vsize);
+	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", buf->buf.width, buf->buf.height);
 
 	/* original size */
-	cfg = (EXYNOS_ORGISIZE_HORIZONTAL(img_sz.hsize) |
-		EXYNOS_ORGISIZE_VERTICAL(img_sz.vsize));
+	cfg = (EXYNOS_ORGISIZE_HORIZONTAL(buf->buf.width) |
+		EXYNOS_ORGISIZE_VERTICAL(buf->buf.height));
 
 	fimc_write(ctx, cfg, EXYNOS_ORGISIZE);
 
-	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]\n", pos->x, pos->y, pos->w, pos->h);
-
-	if (swap) {
-		img_pos.w = pos->h;
-		img_pos.h = pos->w;
-		img_sz.hsize = sz->vsize;
-		img_sz.vsize = sz->hsize;
-	}
+	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]\n", buf->rect.x, buf->rect.y,
+		buf->rect.w, buf->rect.h);
 
 	/* set input DMA image size */
 	cfg = fimc_read(ctx, EXYNOS_CIREAL_ISIZE);
 	cfg &= ~(EXYNOS_CIREAL_ISIZE_HEIGHT_MASK |
 		EXYNOS_CIREAL_ISIZE_WIDTH_MASK);
-	cfg |= (EXYNOS_CIREAL_ISIZE_WIDTH(img_pos.w) |
-		EXYNOS_CIREAL_ISIZE_HEIGHT(img_pos.h));
+	cfg |= (EXYNOS_CIREAL_ISIZE_WIDTH(buf->rect.w) |
+		EXYNOS_CIREAL_ISIZE_HEIGHT(buf->rect.h));
 	fimc_write(ctx, cfg, EXYNOS_CIREAL_ISIZE);
 
 	/*
@@ -635,91 +529,34 @@ static int fimc_src_set_size(struct device *dev, int swap,
 	 * for now, we support only ITU601 8 bit mode
 	 */
 	cfg = (EXYNOS_CISRCFMT_ITU601_8BIT |
-		EXYNOS_CISRCFMT_SOURCEHSIZE(img_sz.hsize) |
-		EXYNOS_CISRCFMT_SOURCEVSIZE(img_sz.vsize));
+		EXYNOS_CISRCFMT_SOURCEHSIZE(buf->buf.width) |
+		EXYNOS_CISRCFMT_SOURCEVSIZE(buf->buf.height));
 	fimc_write(ctx, cfg, EXYNOS_CISRCFMT);
 
 	/* offset Y(RGB), Cb, Cr */
-	cfg = (EXYNOS_CIIYOFF_HORIZONTAL(img_pos.x) |
-		EXYNOS_CIIYOFF_VERTICAL(img_pos.y));
+	cfg = (EXYNOS_CIIYOFF_HORIZONTAL(buf->rect.x) |
+		EXYNOS_CIIYOFF_VERTICAL(buf->rect.y));
 	fimc_write(ctx, cfg, EXYNOS_CIIYOFF);
-	cfg = (EXYNOS_CIICBOFF_HORIZONTAL(img_pos.x) |
-		EXYNOS_CIICBOFF_VERTICAL(img_pos.y));
+	cfg = (EXYNOS_CIICBOFF_HORIZONTAL(buf->rect.x) |
+		EXYNOS_CIICBOFF_VERTICAL(buf->rect.y));
 	fimc_write(ctx, cfg, EXYNOS_CIICBOFF);
-	cfg = (EXYNOS_CIICROFF_HORIZONTAL(img_pos.x) |
-		EXYNOS_CIICROFF_VERTICAL(img_pos.y));
+	cfg = (EXYNOS_CIICROFF_HORIZONTAL(buf->rect.x) |
+		EXYNOS_CIICROFF_VERTICAL(buf->rect.y));
 	fimc_write(ctx, cfg, EXYNOS_CIICROFF);
 
-	return fimc_set_window(ctx, &img_pos, &img_sz);
+	fimc_set_window(ctx, buf);
 }
 
-static int fimc_src_set_addr(struct device *dev,
-		struct drm_exynos_ipp_buf_info *buf_info, u32 buf_id,
-		enum drm_exynos_ipp_buf_type buf_type)
+static void fimc_src_set_addr(struct fimc_context *ctx,
+			      struct exynos_drm_ipp_buffer *buf)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_property *property;
-	struct drm_exynos_ipp_config *config;
-
-	if (!c_node) {
-		DRM_ERROR("failed to get c_node.\n");
-		return -EINVAL;
-	}
-
-	property = &c_node->property;
-
-	DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]buf_type[%d]\n",
-		property->prop_id, buf_id, buf_type);
-
-	if (buf_id > FIMC_MAX_SRC) {
-		dev_info(ippdrv->dev, "invalid buf_id %d.\n", buf_id);
-		return -ENOMEM;
-	}
-
-	/* address register set */
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		config = &property->config[EXYNOS_DRM_OPS_SRC];
-		fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_Y],
-			EXYNOS_CIIYSA0);
-
-		if (config->fmt == DRM_FORMAT_YVU420) {
-			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
-				EXYNOS_CIICBSA0);
-			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
-				EXYNOS_CIICRSA0);
-		} else {
-			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
-				EXYNOS_CIICBSA0);
-			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
-				EXYNOS_CIICRSA0);
-		}
-		break;
-	case IPP_BUF_DEQUEUE:
-		fimc_write(ctx, 0x0, EXYNOS_CIIYSA0);
-		fimc_write(ctx, 0x0, EXYNOS_CIICBSA0);
-		fimc_write(ctx, 0x0, EXYNOS_CIICRSA0);
-		break;
-	default:
-		/* bypass */
-		break;
-	}
-
-	return 0;
+	fimc_write(ctx, buf->dma_addr[0], EXYNOS_CIIYSA(0));
+	fimc_write(ctx, buf->dma_addr[1], EXYNOS_CIICBSA(0));
+	fimc_write(ctx, buf->dma_addr[2], EXYNOS_CIICRSA(0));
 }
 
-static struct exynos_drm_ipp_ops fimc_src_ops = {
-	.set_fmt = fimc_src_set_fmt,
-	.set_transf = fimc_src_set_transf,
-	.set_size = fimc_src_set_size,
-	.set_addr = fimc_src_set_addr,
-};
-
-static int fimc_dst_set_fmt_order(struct fimc_context *ctx, u32 fmt)
+static void fimc_dst_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 {
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg;
 
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
@@ -732,11 +569,11 @@ static int fimc_dst_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 	case DRM_FORMAT_RGB565:
 		cfg |= EXYNOS_CISCCTRL_OUTRGB_FMT_RGB565;
 		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
-		return 0;
+		return;
 	case DRM_FORMAT_RGB888:
 		cfg |= EXYNOS_CISCCTRL_OUTRGB_FMT_RGB888;
 		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
-		return 0;
+		return;
 	case DRM_FORMAT_XRGB8888:
 		cfg |= (EXYNOS_CISCCTRL_OUTRGB_FMT_RGB888 |
 			EXYNOS_CISCCTRL_EXTRGB_EXTENSION);
@@ -784,20 +621,13 @@ static int fimc_dst_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 		cfg |= EXYNOS_CIOCTRL_ORDER2P_LSB_CBCR;
 		cfg |= EXYNOS_CIOCTRL_YCBCR_2PLANE;
 		break;
-	default:
-		dev_err(ippdrv->dev, "invalid target yuv order 0x%x.\n", fmt);
-		return -EINVAL;
 	}
 
 	fimc_write(ctx, cfg, EXYNOS_CIOCTRL);
-
-	return 0;
 }
 
-static int fimc_dst_set_fmt(struct device *dev, u32 fmt)
+static void fimc_dst_set_fmt(struct fimc_context *ctx, u32 fmt, bool tiled)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg;
 
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
@@ -837,10 +667,6 @@ static int fimc_dst_set_fmt(struct device *dev, u32 fmt)
 		case DRM_FORMAT_NV21:
 			cfg |= EXYNOS_CITRGFMT_OUTFORMAT_YCBCR420;
 			break;
-		default:
-			dev_err(ippdrv->dev, "invalid target format 0x%x.\n",
-				fmt);
-			return -EINVAL;
 		}
 
 		fimc_write(ctx, cfg, EXYNOS_CITRGFMT);
@@ -849,73 +675,67 @@ static int fimc_dst_set_fmt(struct device *dev, u32 fmt)
 	cfg = fimc_read(ctx, EXYNOS_CIDMAPARAM);
 	cfg &= ~EXYNOS_CIDMAPARAM_W_MODE_MASK;
 
-	cfg |= EXYNOS_CIDMAPARAM_W_MODE_LINEAR;
+	if (tiled)
+		cfg |= EXYNOS_CIDMAPARAM_W_MODE_64X32;
+	else
+		cfg |= EXYNOS_CIDMAPARAM_W_MODE_LINEAR;
 
 	fimc_write(ctx, cfg, EXYNOS_CIDMAPARAM);
 
-	return fimc_dst_set_fmt_order(ctx, fmt);
+	fimc_dst_set_fmt_order(ctx, fmt);
 }
 
-static int fimc_dst_set_transf(struct device *dev,
-		enum drm_exynos_degree degree,
-		enum drm_exynos_flip flip, bool *swap)
+static void fimc_dst_set_transf(struct fimc_context *ctx, unsigned int rotation)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	unsigned int degree = rotation & DRM_MODE_ROTATE_MASK;
 	u32 cfg;
 
-	DRM_DEBUG_KMS("degree[%d]flip[0x%x]\n", degree, flip);
+	DRM_DEBUG_KMS("rotation[0x%x]\n", rotation);
 
 	cfg = fimc_read(ctx, EXYNOS_CITRGFMT);
 	cfg &= ~EXYNOS_CITRGFMT_FLIP_MASK;
 	cfg &= ~EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE;
 
 	switch (degree) {
-	case EXYNOS_DRM_DEGREE_0:
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+	case DRM_MODE_ROTATE_0:
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg |= EXYNOS_CITRGFMT_FLIP_X_MIRROR;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg |= EXYNOS_CITRGFMT_FLIP_Y_MIRROR;
 		break;
-	case EXYNOS_DRM_DEGREE_90:
+	case DRM_MODE_ROTATE_90:
 		cfg |= EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE;
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg |= EXYNOS_CITRGFMT_FLIP_X_MIRROR;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg |= EXYNOS_CITRGFMT_FLIP_Y_MIRROR;
 		break;
-	case EXYNOS_DRM_DEGREE_180:
+	case DRM_MODE_ROTATE_180:
 		cfg |= (EXYNOS_CITRGFMT_FLIP_X_MIRROR |
 			EXYNOS_CITRGFMT_FLIP_Y_MIRROR);
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg &= ~EXYNOS_CITRGFMT_FLIP_X_MIRROR;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg &= ~EXYNOS_CITRGFMT_FLIP_Y_MIRROR;
 		break;
-	case EXYNOS_DRM_DEGREE_270:
+	case DRM_MODE_ROTATE_270:
 		cfg |= (EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE |
 			EXYNOS_CITRGFMT_FLIP_X_MIRROR |
 			EXYNOS_CITRGFMT_FLIP_Y_MIRROR);
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg &= ~EXYNOS_CITRGFMT_FLIP_X_MIRROR;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg &= ~EXYNOS_CITRGFMT_FLIP_Y_MIRROR;
 		break;
-	default:
-		dev_err(ippdrv->dev, "invalid degree value %d.\n", degree);
-		return -EINVAL;
 	}
 
 	fimc_write(ctx, cfg, EXYNOS_CITRGFMT);
-	*swap = (cfg & EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE) ? 1 : 0;
-
-	return 0;
 }
 
 static int fimc_set_prescaler(struct fimc_context *ctx, struct fimc_scaler *sc,
-		struct drm_exynos_pos *src, struct drm_exynos_pos *dst)
+			      struct drm_exynos_ipp_task_rect *src,
+			      struct drm_exynos_ipp_task_rect *dst)
 {
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg, cfg_ext, shfactor;
 	u32 pre_dst_width, pre_dst_height;
 	u32 hfactor, vfactor;
@@ -942,13 +762,13 @@ static int fimc_set_prescaler(struct fimc_context *ctx, struct fimc_scaler *sc,
 	/* fimc_ippdrv_check_property assures that dividers are not null */
 	hfactor = fls(src_w / dst_w / 2);
 	if (hfactor > FIMC_SHFACTOR / 2) {
-		dev_err(ippdrv->dev, "failed to get ratio horizontal.\n");
+		dev_err(ctx->dev, "failed to get ratio horizontal.\n");
 		return -EINVAL;
 	}
 
 	vfactor = fls(src_h / dst_h / 2);
 	if (vfactor > FIMC_SHFACTOR / 2) {
-		dev_err(ippdrv->dev, "failed to get ratio vertical.\n");
+		dev_err(ctx->dev, "failed to get ratio vertical.\n");
 		return -EINVAL;
 	}
 
@@ -1019,83 +839,77 @@ static void fimc_set_scaler(struct fimc_context *ctx, struct fimc_scaler *sc)
 	fimc_write(ctx, cfg_ext, EXYNOS_CIEXTEN);
 }
 
-static int fimc_dst_set_size(struct device *dev, int swap,
-		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz)
+static void fimc_dst_set_size(struct fimc_context *ctx,
+			     struct exynos_drm_ipp_buffer *buf)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct drm_exynos_pos img_pos = *pos;
-	struct drm_exynos_sz img_sz = *sz;
-	u32 cfg;
+	u32 cfg, cfg_ext;
 
-	DRM_DEBUG_KMS("swap[%d]hsize[%d]vsize[%d]\n",
-		swap, sz->hsize, sz->vsize);
+	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", buf->buf.width, buf->buf.height);
 
 	/* original size */
-	cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(img_sz.hsize) |
-		EXYNOS_ORGOSIZE_VERTICAL(img_sz.vsize));
+	cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(buf->buf.width) |
+		EXYNOS_ORGOSIZE_VERTICAL(buf->buf.height));
 
 	fimc_write(ctx, cfg, EXYNOS_ORGOSIZE);
 
-	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]\n", pos->x, pos->y, pos->w, pos->h);
+	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]\n", buf->rect.x, buf->rect.y,
+		buf->rect.w, buf->rect.h);
 
 	/* CSC ITU */
 	cfg = fimc_read(ctx, EXYNOS_CIGCTRL);
 	cfg &= ~EXYNOS_CIGCTRL_CSC_MASK;
 
-	if (sz->hsize >= FIMC_WIDTH_ITU_709)
+	if (buf->buf.width >= FIMC_WIDTH_ITU_709)
 		cfg |= EXYNOS_CIGCTRL_CSC_ITU709;
 	else
 		cfg |= EXYNOS_CIGCTRL_CSC_ITU601;
 
 	fimc_write(ctx, cfg, EXYNOS_CIGCTRL);
 
-	if (swap) {
-		img_pos.w = pos->h;
-		img_pos.h = pos->w;
-		img_sz.hsize = sz->vsize;
-		img_sz.vsize = sz->hsize;
-	}
+	cfg_ext = fimc_read(ctx, EXYNOS_CITRGFMT);
 
 	/* target image size */
 	cfg = fimc_read(ctx, EXYNOS_CITRGFMT);
 	cfg &= ~(EXYNOS_CITRGFMT_TARGETH_MASK |
 		EXYNOS_CITRGFMT_TARGETV_MASK);
-	cfg |= (EXYNOS_CITRGFMT_TARGETHSIZE(img_pos.w) |
-		EXYNOS_CITRGFMT_TARGETVSIZE(img_pos.h));
+	if (cfg_ext & EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE)
+		cfg |= (EXYNOS_CITRGFMT_TARGETHSIZE(buf->rect.h) |
+			EXYNOS_CITRGFMT_TARGETVSIZE(buf->rect.w));
+	else
+		cfg |= (EXYNOS_CITRGFMT_TARGETHSIZE(buf->rect.w) |
+			EXYNOS_CITRGFMT_TARGETVSIZE(buf->rect.h));
 	fimc_write(ctx, cfg, EXYNOS_CITRGFMT);
 
 	/* target area */
-	cfg = EXYNOS_CITAREA_TARGET_AREA(img_pos.w * img_pos.h);
+	cfg = EXYNOS_CITAREA_TARGET_AREA(buf->rect.w * buf->rect.h);
 	fimc_write(ctx, cfg, EXYNOS_CITAREA);
 
 	/* offset Y(RGB), Cb, Cr */
-	cfg = (EXYNOS_CIOYOFF_HORIZONTAL(img_pos.x) |
-		EXYNOS_CIOYOFF_VERTICAL(img_pos.y));
+	cfg = (EXYNOS_CIOYOFF_HORIZONTAL(buf->rect.x) |
+		EXYNOS_CIOYOFF_VERTICAL(buf->rect.y));
 	fimc_write(ctx, cfg, EXYNOS_CIOYOFF);
-	cfg = (EXYNOS_CIOCBOFF_HORIZONTAL(img_pos.x) |
-		EXYNOS_CIOCBOFF_VERTICAL(img_pos.y));
+	cfg = (EXYNOS_CIOCBOFF_HORIZONTAL(buf->rect.x) |
+		EXYNOS_CIOCBOFF_VERTICAL(buf->rect.y));
 	fimc_write(ctx, cfg, EXYNOS_CIOCBOFF);
-	cfg = (EXYNOS_CIOCROFF_HORIZONTAL(img_pos.x) |
-		EXYNOS_CIOCROFF_VERTICAL(img_pos.y));
+	cfg = (EXYNOS_CIOCROFF_HORIZONTAL(buf->rect.x) |
+		EXYNOS_CIOCROFF_VERTICAL(buf->rect.y));
 	fimc_write(ctx, cfg, EXYNOS_CIOCROFF);
-
-	return 0;
 }
 
 static void fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
-		enum drm_exynos_ipp_buf_type buf_type)
+		bool enqueue)
 {
 	unsigned long flags;
 	u32 buf_num;
 	u32 cfg;
 
-	DRM_DEBUG_KMS("buf_id[%d]buf_type[%d]\n", buf_id, buf_type);
+	DRM_DEBUG_KMS("buf_id[%d]enqueu[%d]\n", buf_id, enqueue);
 
 	spin_lock_irqsave(&ctx->lock, flags);
 
 	cfg = fimc_read(ctx, EXYNOS_CIFCNTSEQ);
 
-	if (buf_type == IPP_BUF_ENQUEUE)
+	if (enqueue)
 		cfg |= (1 << buf_id);
 	else
 		cfg &= ~(1 << buf_id);
@@ -1104,88 +918,29 @@ static void fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
 
 	buf_num = hweight32(cfg);
 
-	if (buf_type == IPP_BUF_ENQUEUE && buf_num >= FIMC_BUF_START)
+	if (enqueue && buf_num >= FIMC_BUF_START)
 		fimc_mask_irq(ctx, true);
-	else if (buf_type == IPP_BUF_DEQUEUE && buf_num <= FIMC_BUF_STOP)
+	else if (!enqueue && buf_num <= FIMC_BUF_STOP)
 		fimc_mask_irq(ctx, false);
 
 	spin_unlock_irqrestore(&ctx->lock, flags);
 }
 
-static int fimc_dst_set_addr(struct device *dev,
-		struct drm_exynos_ipp_buf_info *buf_info, u32 buf_id,
-		enum drm_exynos_ipp_buf_type buf_type)
+static void fimc_dst_set_addr(struct fimc_context *ctx,
+			     struct exynos_drm_ipp_buffer *buf)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_property *property;
-	struct drm_exynos_ipp_config *config;
-
-	if (!c_node) {
-		DRM_ERROR("failed to get c_node.\n");
-		return -EINVAL;
-	}
-
-	property = &c_node->property;
-
-	DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]buf_type[%d]\n",
-		property->prop_id, buf_id, buf_type);
+	fimc_write(ctx, buf->dma_addr[0], EXYNOS_CIOYSA(0));
+	fimc_write(ctx, buf->dma_addr[1], EXYNOS_CIOCBSA(0));
+	fimc_write(ctx, buf->dma_addr[2], EXYNOS_CIOCRSA(0));
 
-	if (buf_id > FIMC_MAX_DST) {
-		dev_info(ippdrv->dev, "invalid buf_id %d.\n", buf_id);
-		return -ENOMEM;
-	}
-
-	/* address register set */
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		config = &property->config[EXYNOS_DRM_OPS_DST];
-
-		fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_Y],
-			EXYNOS_CIOYSA(buf_id));
-
-		if (config->fmt == DRM_FORMAT_YVU420) {
-			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
-				EXYNOS_CIOCBSA(buf_id));
-			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
-				EXYNOS_CIOCRSA(buf_id));
-		} else {
-			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
-				EXYNOS_CIOCBSA(buf_id));
-			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
-				EXYNOS_CIOCRSA(buf_id));
-		}
-		break;
-	case IPP_BUF_DEQUEUE:
-		fimc_write(ctx, 0x0, EXYNOS_CIOYSA(buf_id));
-		fimc_write(ctx, 0x0, EXYNOS_CIOCBSA(buf_id));
-		fimc_write(ctx, 0x0, EXYNOS_CIOCRSA(buf_id));
-		break;
-	default:
-		/* bypass */
-		break;
-	}
-
-	fimc_dst_set_buf_seq(ctx, buf_id, buf_type);
-
-	return 0;
+	fimc_dst_set_buf_seq(ctx, 0, true);
 }
 
-static struct exynos_drm_ipp_ops fimc_dst_ops = {
-	.set_fmt = fimc_dst_set_fmt,
-	.set_transf = fimc_dst_set_transf,
-	.set_size = fimc_dst_set_size,
-	.set_addr = fimc_dst_set_addr,
-};
+static void fimc_stop(struct fimc_context *ctx);
 
 static irqreturn_t fimc_irq_handler(int irq, void *dev_id)
 {
 	struct fimc_context *ctx = dev_id;
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_event_work *event_work =
-		c_node->event_work;
 	int buf_id;
 
 	DRM_DEBUG_KMS("fimc id[%d]\n", ctx->id);
@@ -1203,170 +958,19 @@ static irqreturn_t fimc_irq_handler(int irq, void *dev_id)
 
 	DRM_DEBUG_KMS("buf_id[%d]\n", buf_id);
 
-	fimc_dst_set_buf_seq(ctx, buf_id, IPP_BUF_DEQUEUE);
-
-	event_work->ippdrv = ippdrv;
-	event_work->buf_id[EXYNOS_DRM_OPS_DST] = buf_id;
-	queue_work(ippdrv->event_workq, &event_work->work);
-
-	return IRQ_HANDLED;
-}
-
-static int fimc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
-{
-	struct drm_exynos_ipp_prop_list *prop_list = &ippdrv->prop_list;
-
-	prop_list->version = 1;
-	prop_list->writeback = 1;
-	prop_list->refresh_min = FIMC_REFRESH_MIN;
-	prop_list->refresh_max = FIMC_REFRESH_MAX;
-	prop_list->flip = (1 << EXYNOS_DRM_FLIP_NONE) |
-				(1 << EXYNOS_DRM_FLIP_VERTICAL) |
-				(1 << EXYNOS_DRM_FLIP_HORIZONTAL);
-	prop_list->degree = (1 << EXYNOS_DRM_DEGREE_0) |
-				(1 << EXYNOS_DRM_DEGREE_90) |
-				(1 << EXYNOS_DRM_DEGREE_180) |
-				(1 << EXYNOS_DRM_DEGREE_270);
-	prop_list->csc = 1;
-	prop_list->crop = 1;
-	prop_list->crop_max.hsize = FIMC_CROP_MAX;
-	prop_list->crop_max.vsize = FIMC_CROP_MAX;
-	prop_list->crop_min.hsize = FIMC_CROP_MIN;
-	prop_list->crop_min.vsize = FIMC_CROP_MIN;
-	prop_list->scale = 1;
-	prop_list->scale_max.hsize = FIMC_SCALE_MAX;
-	prop_list->scale_max.vsize = FIMC_SCALE_MAX;
-	prop_list->scale_min.hsize = FIMC_SCALE_MIN;
-	prop_list->scale_min.vsize = FIMC_SCALE_MIN;
-
-	return 0;
-}
-
-static inline bool fimc_check_drm_flip(enum drm_exynos_flip flip)
-{
-	switch (flip) {
-	case EXYNOS_DRM_FLIP_NONE:
-	case EXYNOS_DRM_FLIP_VERTICAL:
-	case EXYNOS_DRM_FLIP_HORIZONTAL:
-	case EXYNOS_DRM_FLIP_BOTH:
-		return true;
-	default:
-		DRM_DEBUG_KMS("invalid flip\n");
-		return false;
-	}
-}
-
-static int fimc_ippdrv_check_property(struct device *dev,
-		struct drm_exynos_ipp_property *property)
-{
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_prop_list *pp = &ippdrv->prop_list;
-	struct drm_exynos_ipp_config *config;
-	struct drm_exynos_pos *pos;
-	struct drm_exynos_sz *sz;
-	bool swap;
-	int i;
-
-	for_each_ipp_ops(i) {
-		if ((i == EXYNOS_DRM_OPS_SRC) &&
-			(property->cmd == IPP_CMD_WB))
-			continue;
-
-		config = &property->config[i];
-		pos = &config->pos;
-		sz = &config->sz;
-
-		/* check for flip */
-		if (!fimc_check_drm_flip(config->flip)) {
-			DRM_ERROR("invalid flip.\n");
-			goto err_property;
-		}
-
-		/* check for degree */
-		switch (config->degree) {
-		case EXYNOS_DRM_DEGREE_90:
-		case EXYNOS_DRM_DEGREE_270:
-			swap = true;
-			break;
-		case EXYNOS_DRM_DEGREE_0:
-		case EXYNOS_DRM_DEGREE_180:
-			swap = false;
-			break;
-		default:
-			DRM_ERROR("invalid degree.\n");
-			goto err_property;
-		}
-
-		/* check for buffer bound */
-		if ((pos->x + pos->w > sz->hsize) ||
-			(pos->y + pos->h > sz->vsize)) {
-			DRM_ERROR("out of buf bound.\n");
-			goto err_property;
-		}
+	if (ctx->task) {
+		struct exynos_drm_ipp_task *task = ctx->task;
 
-		/* check for crop */
-		if ((i == EXYNOS_DRM_OPS_SRC) && (pp->crop)) {
-			if (swap) {
-				if ((pos->h < pp->crop_min.hsize) ||
-					(sz->vsize > pp->crop_max.hsize) ||
-					(pos->w < pp->crop_min.vsize) ||
-					(sz->hsize > pp->crop_max.vsize)) {
-					DRM_ERROR("out of crop size.\n");
-					goto err_property;
-				}
-			} else {
-				if ((pos->w < pp->crop_min.hsize) ||
-					(sz->hsize > pp->crop_max.hsize) ||
-					(pos->h < pp->crop_min.vsize) ||
-					(sz->vsize > pp->crop_max.vsize)) {
-					DRM_ERROR("out of crop size.\n");
-					goto err_property;
-				}
-			}
-		}
-
-		/* check for scale */
-		if ((i == EXYNOS_DRM_OPS_DST) && (pp->scale)) {
-			if (swap) {
-				if ((pos->h < pp->scale_min.hsize) ||
-					(sz->vsize > pp->scale_max.hsize) ||
-					(pos->w < pp->scale_min.vsize) ||
-					(sz->hsize > pp->scale_max.vsize)) {
-					DRM_ERROR("out of scale size.\n");
-					goto err_property;
-				}
-			} else {
-				if ((pos->w < pp->scale_min.hsize) ||
-					(sz->hsize > pp->scale_max.hsize) ||
-					(pos->h < pp->scale_min.vsize) ||
-					(sz->vsize > pp->scale_max.vsize)) {
-					DRM_ERROR("out of scale size.\n");
-					goto err_property;
-				}
-			}
-		}
+		ctx->task = NULL;
+		pm_runtime_mark_last_busy(ctx->dev);
+		pm_runtime_put_autosuspend(ctx->dev);
+		exynos_drm_ipp_task_done(task, 0);
 	}
 
-	return 0;
+	fimc_dst_set_buf_seq(ctx, buf_id, false);
+	fimc_stop(ctx);
 
-err_property:
-	for_each_ipp_ops(i) {
-		if ((i == EXYNOS_DRM_OPS_SRC) &&
-			(property->cmd == IPP_CMD_WB))
-			continue;
-
-		config = &property->config[i];
-		pos = &config->pos;
-		sz = &config->sz;
-
-		DRM_ERROR("[%s]f[%d]r[%d]pos[%d %d %d %d]sz[%d %d]\n",
-			i ? "dst" : "src", config->flip, config->degree,
-			pos->x, pos->y, pos->w, pos->h,
-			sz->hsize, sz->vsize);
-	}
-
-	return -EINVAL;
+	return IRQ_HANDLED;
 }
 
 static void fimc_clear_addr(struct fimc_context *ctx)
@@ -1386,10 +990,8 @@ static void fimc_clear_addr(struct fimc_context *ctx)
 	}
 }
 
-static int fimc_ippdrv_reset(struct device *dev)
+static void fimc_reset(struct fimc_context *ctx)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-
 	/* reset h/w block */
 	fimc_sw_reset(ctx);
 
@@ -1397,82 +999,26 @@ static int fimc_ippdrv_reset(struct device *dev)
 	memset(&ctx->sc, 0x0, sizeof(ctx->sc));
 
 	fimc_clear_addr(ctx);
-
-	return 0;
 }
 
-static int fimc_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
+static void fimc_start(struct fimc_context *ctx)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_property *property;
-	struct drm_exynos_ipp_config *config;
-	struct drm_exynos_pos	img_pos[EXYNOS_DRM_OPS_MAX];
-	struct drm_exynos_ipp_set_wb set_wb;
-	int ret, i;
 	u32 cfg0, cfg1;
 
-	DRM_DEBUG_KMS("cmd[%d]\n", cmd);
-
-	if (!c_node) {
-		DRM_ERROR("failed to get c_node.\n");
-		return -EINVAL;
-	}
-
-	property = &c_node->property;
-
 	fimc_mask_irq(ctx, true);
 
-	for_each_ipp_ops(i) {
-		config = &property->config[i];
-		img_pos[i] = config->pos;
-	}
-
-	ret = fimc_set_prescaler(ctx, &ctx->sc,
-		&img_pos[EXYNOS_DRM_OPS_SRC],
-		&img_pos[EXYNOS_DRM_OPS_DST]);
-	if (ret) {
-		dev_err(dev, "failed to set prescaler.\n");
-		return ret;
-	}
-
-	/* If set ture, we can save jpeg about screen */
+	/* If set true, we can save jpeg about screen */
 	fimc_handle_jpeg(ctx, false);
 	fimc_set_scaler(ctx, &ctx->sc);
 
-	switch (cmd) {
-	case IPP_CMD_M2M:
-		fimc_set_type_ctrl(ctx, FIMC_WB_NONE);
-		fimc_handle_lastend(ctx, false);
-
-		/* setup dma */
-		cfg0 = fimc_read(ctx, EXYNOS_MSCTRL);
-		cfg0 &= ~EXYNOS_MSCTRL_INPUT_MASK;
-		cfg0 |= EXYNOS_MSCTRL_INPUT_MEMORY;
-		fimc_write(ctx, cfg0, EXYNOS_MSCTRL);
-		break;
-	case IPP_CMD_WB:
-		fimc_set_type_ctrl(ctx, FIMC_WB_A);
-		fimc_handle_lastend(ctx, true);
-
-		/* setup FIMD */
-		ret = fimc_set_camblk_fimd0_wb(ctx);
-		if (ret < 0) {
-			dev_err(dev, "camblk setup failed.\n");
-			return ret;
-		}
+	fimc_set_type_ctrl(ctx);
+	fimc_handle_lastend(ctx, false);
 
-		set_wb.enable = 1;
-		set_wb.refresh = property->refresh_rate;
-		exynos_drm_ippnb_send_event(IPP_SET_WRITEBACK, (void *)&set_wb);
-		break;
-	case IPP_CMD_OUTPUT:
-	default:
-		ret = -EINVAL;
-		dev_err(dev, "invalid operations.\n");
-		return ret;
-	}
+	/* setup dma */
+	cfg0 = fimc_read(ctx, EXYNOS_MSCTRL);
+	cfg0 &= ~EXYNOS_MSCTRL_INPUT_MASK;
+	cfg0 |= EXYNOS_MSCTRL_INPUT_MEMORY;
+	fimc_write(ctx, cfg0, EXYNOS_MSCTRL);
 
 	/* Reset status */
 	fimc_write(ctx, 0x0, EXYNOS_CISTATUS);
@@ -1498,36 +1044,18 @@ static int fimc_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 
 	fimc_clear_bits(ctx, EXYNOS_CIOCTRL, EXYNOS_CIOCTRL_WEAVE_MASK);
 
-	if (cmd == IPP_CMD_M2M)
-		fimc_set_bits(ctx, EXYNOS_MSCTRL, EXYNOS_MSCTRL_ENVID);
-
-	return 0;
+	fimc_set_bits(ctx, EXYNOS_MSCTRL, EXYNOS_MSCTRL_ENVID);
 }
 
-static void fimc_ippdrv_stop(struct device *dev, enum drm_exynos_ipp_cmd cmd)
+static void fimc_stop(struct fimc_context *ctx)
 {
-	struct fimc_context *ctx = get_fimc_context(dev);
-	struct drm_exynos_ipp_set_wb set_wb = {0, 0};
 	u32 cfg;
 
-	DRM_DEBUG_KMS("cmd[%d]\n", cmd);
-
-	switch (cmd) {
-	case IPP_CMD_M2M:
-		/* Source clear */
-		cfg = fimc_read(ctx, EXYNOS_MSCTRL);
-		cfg &= ~EXYNOS_MSCTRL_INPUT_MASK;
-		cfg &= ~EXYNOS_MSCTRL_ENVID;
-		fimc_write(ctx, cfg, EXYNOS_MSCTRL);
-		break;
-	case IPP_CMD_WB:
-		exynos_drm_ippnb_send_event(IPP_SET_WRITEBACK, (void *)&set_wb);
-		break;
-	case IPP_CMD_OUTPUT:
-	default:
-		dev_err(dev, "invalid operations.\n");
-		break;
-	}
+	/* Source clear */
+	cfg = fimc_read(ctx, EXYNOS_MSCTRL);
+	cfg &= ~EXYNOS_MSCTRL_INPUT_MASK;
+	cfg &= ~EXYNOS_MSCTRL_ENVID;
+	fimc_write(ctx, cfg, EXYNOS_MSCTRL);
 
 	fimc_mask_irq(ctx, false);
 
@@ -1545,6 +1073,87 @@ static void fimc_ippdrv_stop(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 	fimc_set_bits(ctx, EXYNOS_CIGCTRL, EXYNOS_CIGCTRL_IRQ_END_DISABLE);
 }
 
+static int fimc_commit(struct exynos_drm_ipp *ipp,
+			  struct exynos_drm_ipp_task *task)
+{
+	struct fimc_context *ctx =
+			container_of(ipp, struct fimc_context, ipp);
+
+	pm_runtime_get_sync(ctx->dev);
+	ctx->task = task;
+
+	fimc_src_set_fmt(ctx, task->src.buf.fourcc, task->src.buf.modifier);
+	fimc_src_set_size(ctx, &task->src);
+	fimc_src_set_transf(ctx, DRM_MODE_ROTATE_0);
+	fimc_src_set_addr(ctx, &task->src);
+	fimc_dst_set_fmt(ctx, task->dst.buf.fourcc, task->dst.buf.modifier);
+	fimc_dst_set_transf(ctx, task->transform.rotation);
+	fimc_dst_set_size(ctx, &task->dst);
+	fimc_dst_set_addr(ctx, &task->dst);
+	fimc_set_prescaler(ctx, &ctx->sc, &task->src.rect, &task->dst.rect);
+	fimc_start(ctx);
+
+	return 0;
+}
+
+static void fimc_abort(struct exynos_drm_ipp *ipp,
+			  struct exynos_drm_ipp_task *task)
+{
+	struct fimc_context *ctx =
+			container_of(ipp, struct fimc_context, ipp);
+
+	fimc_reset(ctx);
+
+	if (ctx->task) {
+		struct exynos_drm_ipp_task *task = ctx->task;
+
+		ctx->task = NULL;
+		pm_runtime_mark_last_busy(ctx->dev);
+		pm_runtime_put_autosuspend(ctx->dev);
+		exynos_drm_ipp_task_done(task, -EIO);
+	}
+}
+
+static struct exynos_drm_ipp_funcs ipp_funcs = {
+	.commit = fimc_commit,
+	.abort = fimc_abort,
+};
+
+static int fimc_bind(struct device *dev, struct device *master, void *data)
+{
+	struct fimc_context *ctx = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_ipp *ipp = &ctx->ipp;
+
+	ctx->drm_dev = drm_dev;
+	drm_iommu_attach_device(drm_dev, dev);
+
+	exynos_drm_ipp_register(drm_dev, ipp, &ipp_funcs,
+			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
+			DRM_EXYNOS_IPP_CAP_SCALE | DRM_EXYNOS_IPP_CAP_CONVERT,
+			ctx->formats, ctx->num_formats, "fimc");
+
+	dev_info(dev, "The exynos fimc has been probed successfully\n");
+
+	return 0;
+}
+
+static void fimc_unbind(struct device *dev, struct device *master,
+			void *data)
+{
+	struct fimc_context *ctx = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_ipp *ipp = &ctx->ipp;
+
+	exynos_drm_ipp_unregister(drm_dev, ipp);
+	drm_iommu_detach_device(drm_dev, dev);
+}
+
+static const struct component_ops fimc_component_ops = {
+	.bind	= fimc_bind,
+	.unbind = fimc_unbind,
+};
+
 static void fimc_put_clocks(struct fimc_context *ctx)
 {
 	int i;
@@ -1559,7 +1168,7 @@ static void fimc_put_clocks(struct fimc_context *ctx)
 
 static int fimc_setup_clocks(struct fimc_context *ctx)
 {
-	struct device *fimc_dev = ctx->ippdrv.dev;
+	struct device *fimc_dev = ctx->dev;
 	struct device *dev;
 	int ret, i;
 
@@ -1574,8 +1183,6 @@ static int fimc_setup_clocks(struct fimc_context *ctx)
 
 		ctx->clocks[i] = clk_get(dev, fimc_clock_names[i]);
 		if (IS_ERR(ctx->clocks[i])) {
-			if (i >= FIMC_CLK_MUX)
-				break;
 			ret = PTR_ERR(ctx->clocks[i]);
 			dev_err(fimc_dev, "failed to get clock: %s\n",
 						fimc_clock_names[i]);
@@ -1583,20 +1190,6 @@ static int fimc_setup_clocks(struct fimc_context *ctx)
 		}
 	}
 
-	/* Optional FIMC LCLK parent clock setting */
-	if (!IS_ERR(ctx->clocks[FIMC_CLK_PARENT])) {
-		ret = clk_set_parent(ctx->clocks[FIMC_CLK_MUX],
-				     ctx->clocks[FIMC_CLK_PARENT]);
-		if (ret < 0) {
-			dev_err(fimc_dev, "failed to set parent.\n");
-			goto e_clk_free;
-		}
-	}
-
-	ret = clk_set_rate(ctx->clocks[FIMC_CLK_LCLK], ctx->clk_frequency);
-	if (ret < 0)
-		goto e_clk_free;
-
 	ret = clk_prepare_enable(ctx->clocks[FIMC_CLK_LCLK]);
 	if (!ret)
 		return ret;
@@ -1605,57 +1198,118 @@ e_clk_free:
 	return ret;
 }
 
-static int fimc_parse_dt(struct fimc_context *ctx)
+int exynos_drm_check_fimc_device(struct device *dev)
 {
-	struct device_node *node = ctx->ippdrv.dev->of_node;
+	int id = of_alias_get_id(dev->of_node, "fimc");
 
-	/* Handle only devices that support the LCD Writeback data path */
-	if (!of_property_read_bool(node, "samsung,lcd-wb"))
-		return -ENODEV;
+	if (id >= 0 && (BIT(id) & fimc_mask))
+		return 0;
+	return -ENODEV;
+}
 
-	if (of_property_read_u32(node, "clock-frequency",
-					&ctx->clk_frequency))
-		ctx->clk_frequency = FIMC_DEFAULT_LCLK_FREQUENCY;
+static const unsigned int fimc_formats[] = {
+	DRM_FORMAT_XRGB8888, DRM_FORMAT_RGB565,
+	DRM_FORMAT_NV12, DRM_FORMAT_NV16, DRM_FORMAT_NV21, DRM_FORMAT_NV61,
+	DRM_FORMAT_UYVY, DRM_FORMAT_VYUY, DRM_FORMAT_YUYV, DRM_FORMAT_YVYU,
+	DRM_FORMAT_YUV420, DRM_FORMAT_YVU420, DRM_FORMAT_YUV422,
+	DRM_FORMAT_YUV444,
+};
 
-	ctx->id = of_alias_get_id(node, "fimc");
+static const unsigned int fimc_tiled_formats[] = {
+	DRM_FORMAT_NV12, DRM_FORMAT_NV21,
+};
 
-	if (ctx->id < 0) {
-		dev_err(ctx->ippdrv.dev, "failed to get node alias id.\n");
-		return -EINVAL;
-	}
+static const struct drm_exynos_ipp_limit fimc_4210_limits_v1[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 16, 8192, 8 }, .v = { 16, 8192, 2 }) },
+	{ IPP_SIZE_LIMIT(AREA, .h = { 16, 4224, 2 }, .v = { 16, 0, 2 }) },
+	{ IPP_SIZE_LIMIT(ROTATED, .h = { 128, 1920 }, .v = { 128, 0 }) },
+	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 64, (1 << 16) * 64 },
+			  .v = { (1 << 16) / 64, (1 << 16) * 64 }) },
+};
 
-	return 0;
-}
+static const struct drm_exynos_ipp_limit fimc_4210_limits_v2[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 16, 8192, 8 }, .v = { 16, 8192, 2 }) },
+	{ IPP_SIZE_LIMIT(AREA, .h = { 16, 1920, 2 }, .v = { 16, 0, 2 }) },
+	{ IPP_SIZE_LIMIT(ROTATED, .h = { 128, 1366 }, .v = { 128, 0 }) },
+	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 64, (1 << 16) * 64 },
+			  .v = { (1 << 16) / 64, (1 << 16) * 64 }) },
+};
+
+static const struct drm_exynos_ipp_limit fimc_4210_limits_tiled_v1[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 128, 1920, 128 }, .v = { 32, 1920, 32 }) },
+	{ IPP_SIZE_LIMIT(AREA, .h = { 128, 1920, 2 }, .v = { 128, 0, 2 }) },
+	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 64, (1 << 16) * 64 },
+			  .v = { (1 << 16) / 64, (1 << 16) * 64 }) },
+};
+
+static const struct drm_exynos_ipp_limit fimc_4210_limits_tiled_v2[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 128, 1920, 128 }, .v = { 32, 1920, 32 }) },
+	{ IPP_SIZE_LIMIT(AREA, .h = { 128, 1366, 2 }, .v = { 128, 0, 2 }) },
+	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 64, (1 << 16) * 64 },
+			  .v = { (1 << 16) / 64, (1 << 16) * 64 }) },
+};
 
 static int fimc_probe(struct platform_device *pdev)
 {
+	const struct drm_exynos_ipp_limit *limits;
+	struct exynos_drm_ipp_formats *formats;
 	struct device *dev = &pdev->dev;
 	struct fimc_context *ctx;
 	struct resource *res;
-	struct exynos_drm_ippdrv *ippdrv;
 	int ret;
+	int i, j, num_limits, num_formats;
 
-	if (!dev->of_node) {
-		dev_err(dev, "device tree node not found.\n");
+	if (exynos_drm_check_fimc_device(dev) != 0)
 		return -ENODEV;
-	}
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
-	ctx->ippdrv.dev = dev;
+	ctx->dev = dev;
+	ctx->id = of_alias_get_id(dev->of_node, "fimc");
 
-	ret = fimc_parse_dt(ctx);
-	if (ret < 0)
-		return ret;
+	/* construct formats/limits array */
+	num_formats = ARRAY_SIZE(fimc_formats) + ARRAY_SIZE(fimc_tiled_formats);
+	formats = devm_kzalloc(dev, sizeof(*formats) * num_formats, GFP_KERNEL);
+	if (!formats)
+		return -ENOMEM;
+
+	/* linear formats */
+	if (ctx->id < 3) {
+		limits = fimc_4210_limits_v1;
+		num_limits = ARRAY_SIZE(fimc_4210_limits_v1);
+	} else {
+		limits = fimc_4210_limits_v2;
+		num_limits = ARRAY_SIZE(fimc_4210_limits_v2);
+	}
+	for (i = 0; i < ARRAY_SIZE(fimc_formats); i++) {
+		formats[i].fourcc = fimc_formats[i];
+		formats[i].type = DRM_EXYNOS_IPP_FORMAT_SOURCE |
+				  DRM_EXYNOS_IPP_FORMAT_DESTINATION;
+		formats[i].limits = limits;
+		formats[i].num_limits = num_limits;
+	}
 
-	ctx->sysreg = syscon_regmap_lookup_by_phandle(dev->of_node,
-						"samsung,sysreg");
-	if (IS_ERR(ctx->sysreg)) {
-		dev_err(dev, "syscon regmap lookup failed.\n");
-		return PTR_ERR(ctx->sysreg);
+	/* tiled formats */
+	if (ctx->id < 3) {
+		limits = fimc_4210_limits_tiled_v1;
+		num_limits = ARRAY_SIZE(fimc_4210_limits_tiled_v1);
+	} else {
+		limits = fimc_4210_limits_tiled_v2;
+		num_limits = ARRAY_SIZE(fimc_4210_limits_tiled_v2);
 	}
+	for (j = i, i = 0; i < ARRAY_SIZE(fimc_tiled_formats); j++, i++) {
+		formats[j].fourcc = fimc_tiled_formats[i];
+		formats[j].modifier = DRM_FORMAT_MOD_SAMSUNG_64_32_TILE;
+		formats[j].type = DRM_EXYNOS_IPP_FORMAT_SOURCE |
+				  DRM_EXYNOS_IPP_FORMAT_DESTINATION;
+		formats[j].limits = limits;
+		formats[j].num_limits = num_limits;
+	}
+
+	ctx->formats = formats;
+	ctx->num_formats = num_formats;
 
 	/* resource memory */
 	ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1670,9 +1324,8 @@ static int fimc_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	ctx->irq = res->start;
-	ret = devm_request_threaded_irq(dev, ctx->irq, NULL, fimc_irq_handler,
-		IRQF_ONESHOT, "drm_fimc", ctx);
+	ret = devm_request_irq(dev, res->start, fimc_irq_handler,
+		0, dev_name(dev), ctx);
 	if (ret < 0) {
 		dev_err(dev, "failed to request irq.\n");
 		return ret;
@@ -1682,39 +1335,24 @@ static int fimc_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
-	ippdrv = &ctx->ippdrv;
-	ippdrv->ops[EXYNOS_DRM_OPS_SRC] = &fimc_src_ops;
-	ippdrv->ops[EXYNOS_DRM_OPS_DST] = &fimc_dst_ops;
-	ippdrv->check_property = fimc_ippdrv_check_property;
-	ippdrv->reset = fimc_ippdrv_reset;
-	ippdrv->start = fimc_ippdrv_start;
-	ippdrv->stop = fimc_ippdrv_stop;
-	ret = fimc_init_prop_list(ippdrv);
-	if (ret < 0) {
-		dev_err(dev, "failed to init property list.\n");
-		goto err_put_clk;
-	}
-
-	DRM_DEBUG_KMS("id[%d]ippdrv[%pK]\n", ctx->id, ippdrv);
-
 	spin_lock_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
 
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, FIMC_AUTOSUSPEND_DELAY);
 	pm_runtime_enable(dev);
 
-	ret = exynos_drm_ippdrv_register(ippdrv);
-	if (ret < 0) {
-		dev_err(dev, "failed to register drm fimc device.\n");
+	ret = component_add(dev, &fimc_component_ops);
+	if (ret)
 		goto err_pm_dis;
-	}
 
 	dev_info(dev, "drm fimc registered successfully.\n");
 
 	return 0;
 
 err_pm_dis:
+	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
-err_put_clk:
 	fimc_put_clocks(ctx);
 
 	return ret;
@@ -1724,42 +1362,24 @@ static int fimc_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct fimc_context *ctx = get_fimc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 
-	exynos_drm_ippdrv_unregister(ippdrv);
+	component_del(dev, &fimc_component_ops);
+	pm_runtime_dont_use_autosuspend(dev);
+	pm_runtime_disable(dev);
 
 	fimc_put_clocks(ctx);
-	pm_runtime_set_suspended(dev);
-	pm_runtime_disable(dev);
 
 	return 0;
 }
 
 #ifdef CONFIG_PM
-static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable)
-{
-	DRM_DEBUG_KMS("enable[%d]\n", enable);
-
-	if (enable) {
-		clk_prepare_enable(ctx->clocks[FIMC_CLK_GATE]);
-		clk_prepare_enable(ctx->clocks[FIMC_CLK_WB_A]);
-		ctx->suspended = false;
-	} else {
-		clk_disable_unprepare(ctx->clocks[FIMC_CLK_GATE]);
-		clk_disable_unprepare(ctx->clocks[FIMC_CLK_WB_A]);
-		ctx->suspended = true;
-	}
-
-	return 0;
-}
-
 static int fimc_runtime_suspend(struct device *dev)
 {
 	struct fimc_context *ctx = get_fimc_context(dev);
 
 	DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
-	return  fimc_clk_ctrl(ctx, false);
+	clk_disable_unprepare(ctx->clocks[FIMC_CLK_GATE]);
+	return 0;
 }
 
 static int fimc_runtime_resume(struct device *dev)
@@ -1767,8 +1387,7 @@ static int fimc_runtime_resume(struct device *dev)
 	struct fimc_context *ctx = get_fimc_context(dev);
 
 	DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
-	return  fimc_clk_ctrl(ctx, true);
+	return clk_prepare_enable(ctx->clocks[FIMC_CLK_GATE]);
 }
 #endif
 
@@ -1795,4 +1414,3 @@ struct platform_driver fimc_driver = {
 		.pm	= &fimc_pm_ops,
 	},
 };
-
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.h b/drivers/gpu/drm/exynos/exynos_drm_fimc.h
deleted file mode 100644
index 127a424c5fdf..000000000000
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *
- * Authors:
- *	Eunchul Kim <chulspro.kim@samsung.com>
- *	Jinyoung Jeon <jy0.jeon@samsung.com>
- *	Sangmin Lee <lsmin.lee@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef _EXYNOS_DRM_FIMC_H_
-#define _EXYNOS_DRM_FIMC_H_
-
-/*
- * TODO
- * FIMD output interface notifier callback.
- */
-
-#endif /* _EXYNOS_DRM_FIMC_H_ */
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index d42ae2bc3e56..01b1570d0c3a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -121,6 +121,12 @@ static struct fimd_driver_data s3c64xx_fimd_driver_data = {
 	.has_limited_fmt = 1,
 };
 
+static struct fimd_driver_data s5pv210_fimd_driver_data = {
+	.timing_base = 0x0,
+	.has_shadowcon = 1,
+	.has_clksel = 1,
+};
+
 static struct fimd_driver_data exynos3_fimd_driver_data = {
 	.timing_base = 0x20000,
 	.lcdblk_offset = 0x210,
@@ -193,6 +199,8 @@ struct fimd_context {
 static const struct of_device_id fimd_driver_dt_match[] = {
 	{ .compatible = "samsung,s3c6400-fimd",
 	  .data = &s3c64xx_fimd_driver_data },
+	{ .compatible = "samsung,s5pv210-fimd",
+	  .data = &s5pv210_fimd_driver_data },
 	{ .compatible = "samsung,exynos3250-fimd",
 	  .data = &exynos3_fimd_driver_data },
 	{ .compatible = "samsung,exynos4210-fimd",
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 11cc01b47bc0..6e1494fa71b4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -431,37 +431,24 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv,
 	return 0;
 }
 
-int exynos_drm_gem_fault(struct vm_fault *vmf)
+vm_fault_t exynos_drm_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct exynos_drm_gem *exynos_gem = to_exynos_gem(obj);
 	unsigned long pfn;
 	pgoff_t page_offset;
-	int ret;
 
 	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	if (page_offset >= (exynos_gem->size >> PAGE_SHIFT)) {
 		DRM_ERROR("invalid page offset\n");
-		ret = -EINVAL;
-		goto out;
+		return VM_FAULT_SIGBUS;
 	}
 
 	pfn = page_to_pfn(exynos_gem->pages[page_offset]);
-	ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
-
-out:
-	switch (ret) {
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return vmf_insert_mixed(vma, vmf->address,
+			__pfn_to_pfn_t(pfn, PFN_DEV));
 }
 
 static int exynos_drm_gem_mmap_obj(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 5a4c7de80f65..9057d7f1d6ed 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -13,6 +13,7 @@
 #define _EXYNOS_DRM_GEM_H_
 
 #include <drm/drm_gem.h>
+#include <linux/mm_types.h>
 
 #define to_exynos_gem(x)	container_of(x, struct exynos_drm_gem, base)
 
@@ -111,7 +112,7 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv,
 			       struct drm_mode_create_dumb *args);
 
 /* page fault handler and mmap fault address(virtual) to physical memory. */
-int exynos_drm_gem_fault(struct vm_fault *vmf);
+vm_fault_t exynos_drm_gem_fault(struct vm_fault *vmf);
 
 /* set vm_flags and we can change the vm attribute to other one at here. */
 int exynos_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 0506b2b17ac1..e99dd1e4ba65 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -12,18 +12,20 @@
  *
  */
 #include <linux/kernel.h>
+#include <linux/component.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
 #include <linux/mfd/syscon.h>
+#include <linux/of_device.h>
 #include <linux/regmap.h>
 
 #include <drm/drmP.h>
 #include <drm/exynos_drm.h>
 #include "regs-gsc.h"
 #include "exynos_drm_drv.h"
+#include "exynos_drm_iommu.h"
 #include "exynos_drm_ipp.h"
-#include "exynos_drm_gsc.h"
 
 /*
  * GSC stands for General SCaler and
@@ -31,26 +33,10 @@
  * input DMA reads image data from the memory.
  * output DMA writes image data to memory.
  * GSC supports image rotation and image effect functions.
- *
- * M2M operation : supports crop/scale/rotation/csc so on.
- * Memory ----> GSC H/W ----> Memory.
- * Writeback operation : supports cloned screen with FIMD.
- * FIMD ----> GSC H/W ----> Memory.
- * Output operation : supports direct display using local path.
- * Memory ----> GSC H/W ----> FIMD, Mixer.
  */
 
-/*
- * TODO
- * 1. check suspend/resume api if needed.
- * 2. need to check use case platform_device_id.
- * 3. check src/dst size with, height.
- * 4. added check_prepare api for right register.
- * 5. need to add supported list in prop_list.
- * 6. check prescaler/scaler optimization.
- */
 
-#define GSC_MAX_DEVS	4
+#define GSC_MAX_CLOCKS	8
 #define GSC_MAX_SRC		4
 #define GSC_MAX_DST		16
 #define GSC_RESET_TIMEOUT	50
@@ -65,8 +51,6 @@
 #define GSC_SC_DOWN_RATIO_4_8		131072
 #define GSC_SC_DOWN_RATIO_3_8		174762
 #define GSC_SC_DOWN_RATIO_2_8		262144
-#define GSC_REFRESH_MIN	12
-#define GSC_REFRESH_MAX	60
 #define GSC_CROP_MAX	8192
 #define GSC_CROP_MIN	32
 #define GSC_SCALE_MAX	4224
@@ -77,10 +61,9 @@
 #define GSC_COEF_H_8T	8
 #define GSC_COEF_V_4T	4
 #define GSC_COEF_DEPTH	3
+#define GSC_AUTOSUSPEND_DELAY		2000
 
 #define get_gsc_context(dev)	platform_get_drvdata(to_platform_device(dev))
-#define get_ctx_from_ippdrv(ippdrv)	container_of(ippdrv,\
-					struct gsc_context, ippdrv);
 #define gsc_read(offset)		readl(ctx->regs + (offset))
 #define gsc_write(cfg, offset)	writel(cfg, ctx->regs + (offset))
 
@@ -104,50 +87,47 @@ struct gsc_scaler {
 };
 
 /*
- * A structure of scaler capability.
- *
- * find user manual 49.2 features.
- * @tile_w: tile mode or rotation width.
- * @tile_h: tile mode or rotation height.
- * @w: other cases width.
- * @h: other cases height.
- */
-struct gsc_capability {
-	/* tile or rotation */
-	u32	tile_w;
-	u32	tile_h;
-	/* other cases */
-	u32	w;
-	u32	h;
-};
-
-/*
  * A structure of gsc context.
  *
- * @ippdrv: prepare initialization using ippdrv.
  * @regs_res: register resources.
  * @regs: memory mapped io registers.
- * @sysreg: handle to SYSREG block regmap.
- * @lock: locking of operations.
  * @gsc_clk: gsc gate clock.
  * @sc: scaler infomations.
  * @id: gsc id.
  * @irq: irq number.
  * @rotation: supports rotation of src.
- * @suspended: qos operations.
  */
 struct gsc_context {
-	struct exynos_drm_ippdrv	ippdrv;
+	struct exynos_drm_ipp ipp;
+	struct drm_device *drm_dev;
+	struct device	*dev;
+	struct exynos_drm_ipp_task	*task;
+	struct exynos_drm_ipp_formats	*formats;
+	unsigned int			num_formats;
+
 	struct resource	*regs_res;
 	void __iomem	*regs;
-	struct regmap	*sysreg;
-	struct mutex	lock;
-	struct clk	*gsc_clk;
+	const char	**clk_names;
+	struct clk	*clocks[GSC_MAX_CLOCKS];
+	int		num_clocks;
 	struct gsc_scaler	sc;
 	int	id;
 	int	irq;
 	bool	rotation;
-	bool	suspended;
+};
+
+/**
+ * struct gsc_driverdata - per device type driver data for init time.
+ *
+ * @limits: picture size limits array
+ * @clk_names: names of clocks needed by this variant
+ * @num_clocks: the number of clocks needed by this variant
+ */
+struct gsc_driverdata {
+	const struct drm_exynos_ipp_limit *limits;
+	int		num_limits;
+	const char	*clk_names[GSC_MAX_CLOCKS];
+	int		num_clocks;
 };
 
 /* 8-tap Filter Coefficient */
@@ -438,25 +418,6 @@ static int gsc_sw_reset(struct gsc_context *ctx)
 	return 0;
 }
 
-static void gsc_set_gscblk_fimd_wb(struct gsc_context *ctx, bool enable)
-{
-	unsigned int gscblk_cfg;
-
-	if (!ctx->sysreg)
-		return;
-
-	regmap_read(ctx->sysreg, SYSREG_GSCBLK_CFG1, &gscblk_cfg);
-
-	if (enable)
-		gscblk_cfg |= GSC_BLK_DISP1WB_DEST(ctx->id) |
-				GSC_BLK_GSCL_WB_IN_SRC_SEL(ctx->id) |
-				GSC_BLK_SW_RESET_WB_DEST(ctx->id);
-	else
-		gscblk_cfg |= GSC_BLK_PXLASYNC_LO_MASK_WB(ctx->id);
-
-	regmap_write(ctx->sysreg, SYSREG_GSCBLK_CFG1, gscblk_cfg);
-}
-
 static void gsc_handle_irq(struct gsc_context *ctx, bool enable,
 		bool overflow, bool done)
 {
@@ -487,10 +448,8 @@ static void gsc_handle_irq(struct gsc_context *ctx, bool enable,
 }
 
 
-static int gsc_src_set_fmt(struct device *dev, u32 fmt)
+static void gsc_src_set_fmt(struct gsc_context *ctx, u32 fmt)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg;
 
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
@@ -506,6 +465,7 @@ static int gsc_src_set_fmt(struct device *dev, u32 fmt)
 		cfg |= GSC_IN_RGB565;
 		break;
 	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
 		cfg |= GSC_IN_XRGB8888;
 		break;
 	case DRM_FORMAT_BGRX8888:
@@ -548,115 +508,84 @@ static int gsc_src_set_fmt(struct device *dev, u32 fmt)
 		cfg |= (GSC_IN_CHROMA_ORDER_CBCR |
 			GSC_IN_YUV420_2P);
 		break;
-	default:
-		dev_err(ippdrv->dev, "invalid target yuv order 0x%x.\n", fmt);
-		return -EINVAL;
 	}
 
 	gsc_write(cfg, GSC_IN_CON);
-
-	return 0;
 }
 
-static int gsc_src_set_transf(struct device *dev,
-		enum drm_exynos_degree degree,
-		enum drm_exynos_flip flip, bool *swap)
+static void gsc_src_set_transf(struct gsc_context *ctx, unsigned int rotation)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	unsigned int degree = rotation & DRM_MODE_ROTATE_MASK;
 	u32 cfg;
 
-	DRM_DEBUG_KMS("degree[%d]flip[0x%x]\n", degree, flip);
-
 	cfg = gsc_read(GSC_IN_CON);
 	cfg &= ~GSC_IN_ROT_MASK;
 
 	switch (degree) {
-	case EXYNOS_DRM_DEGREE_0:
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+	case DRM_MODE_ROTATE_0:
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg |= GSC_IN_ROT_XFLIP;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg |= GSC_IN_ROT_YFLIP;
 		break;
-	case EXYNOS_DRM_DEGREE_90:
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
-			cfg |= GSC_IN_ROT_90_XFLIP;
-		else if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
-			cfg |= GSC_IN_ROT_90_YFLIP;
-		else
-			cfg |= GSC_IN_ROT_90;
+	case DRM_MODE_ROTATE_90:
+		cfg |= GSC_IN_ROT_90;
+		if (rotation & DRM_MODE_REFLECT_Y)
+			cfg |= GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_X)
+			cfg |= GSC_IN_ROT_YFLIP;
 		break;
-	case EXYNOS_DRM_DEGREE_180:
+	case DRM_MODE_ROTATE_180:
 		cfg |= GSC_IN_ROT_180;
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg &= ~GSC_IN_ROT_XFLIP;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg &= ~GSC_IN_ROT_YFLIP;
 		break;
-	case EXYNOS_DRM_DEGREE_270:
+	case DRM_MODE_ROTATE_270:
 		cfg |= GSC_IN_ROT_270;
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg &= ~GSC_IN_ROT_XFLIP;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+		if (rotation & DRM_MODE_REFLECT_X)
 			cfg &= ~GSC_IN_ROT_YFLIP;
 		break;
-	default:
-		dev_err(ippdrv->dev, "invalid degree value %d.\n", degree);
-		return -EINVAL;
 	}
 
 	gsc_write(cfg, GSC_IN_CON);
 
 	ctx->rotation = (cfg & GSC_IN_ROT_90) ? 1 : 0;
-	*swap = ctx->rotation;
-
-	return 0;
 }
 
-static int gsc_src_set_size(struct device *dev, int swap,
-		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz)
+static void gsc_src_set_size(struct gsc_context *ctx,
+			     struct exynos_drm_ipp_buffer *buf)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct drm_exynos_pos img_pos = *pos;
 	struct gsc_scaler *sc = &ctx->sc;
 	u32 cfg;
 
-	DRM_DEBUG_KMS("swap[%d]x[%d]y[%d]w[%d]h[%d]\n",
-		swap, pos->x, pos->y, pos->w, pos->h);
-
-	if (swap) {
-		img_pos.w = pos->h;
-		img_pos.h = pos->w;
-	}
-
 	/* pixel offset */
-	cfg = (GSC_SRCIMG_OFFSET_X(img_pos.x) |
-		GSC_SRCIMG_OFFSET_Y(img_pos.y));
+	cfg = (GSC_SRCIMG_OFFSET_X(buf->rect.x) |
+		GSC_SRCIMG_OFFSET_Y(buf->rect.y));
 	gsc_write(cfg, GSC_SRCIMG_OFFSET);
 
 	/* cropped size */
-	cfg = (GSC_CROPPED_WIDTH(img_pos.w) |
-		GSC_CROPPED_HEIGHT(img_pos.h));
+	cfg = (GSC_CROPPED_WIDTH(buf->rect.w) |
+		GSC_CROPPED_HEIGHT(buf->rect.h));
 	gsc_write(cfg, GSC_CROPPED_SIZE);
 
-	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", sz->hsize, sz->vsize);
-
 	/* original size */
 	cfg = gsc_read(GSC_SRCIMG_SIZE);
 	cfg &= ~(GSC_SRCIMG_HEIGHT_MASK |
 		GSC_SRCIMG_WIDTH_MASK);
 
-	cfg |= (GSC_SRCIMG_WIDTH(sz->hsize) |
-		GSC_SRCIMG_HEIGHT(sz->vsize));
+	cfg |= (GSC_SRCIMG_WIDTH(buf->buf.width) |
+		GSC_SRCIMG_HEIGHT(buf->buf.height));
 
 	gsc_write(cfg, GSC_SRCIMG_SIZE);
 
 	cfg = gsc_read(GSC_IN_CON);
 	cfg &= ~GSC_IN_RGB_TYPE_MASK;
 
-	DRM_DEBUG_KMS("width[%d]range[%d]\n", pos->w, sc->range);
-
-	if (pos->w >= GSC_WIDTH_ITU_709)
+	if (buf->rect.w >= GSC_WIDTH_ITU_709)
 		if (sc->range)
 			cfg |= GSC_IN_RGB_HD_WIDE;
 		else
@@ -668,103 +597,39 @@ static int gsc_src_set_size(struct device *dev, int swap,
 			cfg |= GSC_IN_RGB_SD_NARROW;
 
 	gsc_write(cfg, GSC_IN_CON);
-
-	return 0;
 }
 
-static int gsc_src_set_buf_seq(struct gsc_context *ctx, u32 buf_id,
-		enum drm_exynos_ipp_buf_type buf_type)
+static void gsc_src_set_buf_seq(struct gsc_context *ctx, u32 buf_id,
+			       bool enqueue)
 {
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	bool masked;
+	bool masked = !enqueue;
 	u32 cfg;
 	u32 mask = 0x00000001 << buf_id;
 
-	DRM_DEBUG_KMS("buf_id[%d]buf_type[%d]\n", buf_id, buf_type);
-
 	/* mask register set */
 	cfg = gsc_read(GSC_IN_BASE_ADDR_Y_MASK);
 
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		masked = false;
-		break;
-	case IPP_BUF_DEQUEUE:
-		masked = true;
-		break;
-	default:
-		dev_err(ippdrv->dev, "invalid buf ctrl parameter.\n");
-		return -EINVAL;
-	}
-
 	/* sequence id */
 	cfg &= ~mask;
 	cfg |= masked << buf_id;
 	gsc_write(cfg, GSC_IN_BASE_ADDR_Y_MASK);
 	gsc_write(cfg, GSC_IN_BASE_ADDR_CB_MASK);
 	gsc_write(cfg, GSC_IN_BASE_ADDR_CR_MASK);
-
-	return 0;
 }
 
-static int gsc_src_set_addr(struct device *dev,
-		struct drm_exynos_ipp_buf_info *buf_info, u32 buf_id,
-		enum drm_exynos_ipp_buf_type buf_type)
+static void gsc_src_set_addr(struct gsc_context *ctx, u32 buf_id,
+			    struct exynos_drm_ipp_buffer *buf)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_property *property;
-
-	if (!c_node) {
-		DRM_ERROR("failed to get c_node.\n");
-		return -EFAULT;
-	}
-
-	property = &c_node->property;
-
-	DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]buf_type[%d]\n",
-		property->prop_id, buf_id, buf_type);
-
-	if (buf_id > GSC_MAX_SRC) {
-		dev_info(ippdrv->dev, "invalid buf_id %d.\n", buf_id);
-		return -EINVAL;
-	}
-
 	/* address register set */
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		gsc_write(buf_info->base[EXYNOS_DRM_PLANAR_Y],
-			GSC_IN_BASE_ADDR_Y(buf_id));
-		gsc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
-			GSC_IN_BASE_ADDR_CB(buf_id));
-		gsc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
-			GSC_IN_BASE_ADDR_CR(buf_id));
-		break;
-	case IPP_BUF_DEQUEUE:
-		gsc_write(0x0, GSC_IN_BASE_ADDR_Y(buf_id));
-		gsc_write(0x0, GSC_IN_BASE_ADDR_CB(buf_id));
-		gsc_write(0x0, GSC_IN_BASE_ADDR_CR(buf_id));
-		break;
-	default:
-		/* bypass */
-		break;
-	}
+	gsc_write(buf->dma_addr[0], GSC_IN_BASE_ADDR_Y(buf_id));
+	gsc_write(buf->dma_addr[1], GSC_IN_BASE_ADDR_CB(buf_id));
+	gsc_write(buf->dma_addr[2], GSC_IN_BASE_ADDR_CR(buf_id));
 
-	return gsc_src_set_buf_seq(ctx, buf_id, buf_type);
+	gsc_src_set_buf_seq(ctx, buf_id, true);
 }
 
-static struct exynos_drm_ipp_ops gsc_src_ops = {
-	.set_fmt = gsc_src_set_fmt,
-	.set_transf = gsc_src_set_transf,
-	.set_size = gsc_src_set_size,
-	.set_addr = gsc_src_set_addr,
-};
-
-static int gsc_dst_set_fmt(struct device *dev, u32 fmt)
+static void gsc_dst_set_fmt(struct gsc_context *ctx, u32 fmt)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg;
 
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
@@ -779,8 +644,9 @@ static int gsc_dst_set_fmt(struct device *dev, u32 fmt)
 	case DRM_FORMAT_RGB565:
 		cfg |= GSC_OUT_RGB565;
 		break;
+	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_XRGB8888:
-		cfg |= GSC_OUT_XRGB8888;
+		cfg |= (GSC_OUT_XRGB8888 | GSC_OUT_GLOBAL_ALPHA(0xff));
 		break;
 	case DRM_FORMAT_BGRX8888:
 		cfg |= (GSC_OUT_XRGB8888 | GSC_OUT_RB_SWAP);
@@ -819,69 +685,9 @@ static int gsc_dst_set_fmt(struct device *dev, u32 fmt)
 		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR |
 			GSC_OUT_YUV420_2P);
 		break;
-	default:
-		dev_err(ippdrv->dev, "invalid target yuv order 0x%x.\n", fmt);
-		return -EINVAL;
 	}
 
 	gsc_write(cfg, GSC_OUT_CON);
-
-	return 0;
-}
-
-static int gsc_dst_set_transf(struct device *dev,
-		enum drm_exynos_degree degree,
-		enum drm_exynos_flip flip, bool *swap)
-{
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	u32 cfg;
-
-	DRM_DEBUG_KMS("degree[%d]flip[0x%x]\n", degree, flip);
-
-	cfg = gsc_read(GSC_IN_CON);
-	cfg &= ~GSC_IN_ROT_MASK;
-
-	switch (degree) {
-	case EXYNOS_DRM_DEGREE_0:
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
-			cfg |= GSC_IN_ROT_XFLIP;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
-			cfg |= GSC_IN_ROT_YFLIP;
-		break;
-	case EXYNOS_DRM_DEGREE_90:
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
-			cfg |= GSC_IN_ROT_90_XFLIP;
-		else if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
-			cfg |= GSC_IN_ROT_90_YFLIP;
-		else
-			cfg |= GSC_IN_ROT_90;
-		break;
-	case EXYNOS_DRM_DEGREE_180:
-		cfg |= GSC_IN_ROT_180;
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
-			cfg &= ~GSC_IN_ROT_XFLIP;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
-			cfg &= ~GSC_IN_ROT_YFLIP;
-		break;
-	case EXYNOS_DRM_DEGREE_270:
-		cfg |= GSC_IN_ROT_270;
-		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
-			cfg &= ~GSC_IN_ROT_XFLIP;
-		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
-			cfg &= ~GSC_IN_ROT_YFLIP;
-		break;
-	default:
-		dev_err(ippdrv->dev, "invalid degree value %d.\n", degree);
-		return -EINVAL;
-	}
-
-	gsc_write(cfg, GSC_IN_CON);
-
-	ctx->rotation = (cfg & GSC_IN_ROT_90) ? 1 : 0;
-	*swap = ctx->rotation;
-
-	return 0;
 }
 
 static int gsc_get_ratio_shift(u32 src, u32 dst, u32 *ratio)
@@ -919,9 +725,9 @@ static void gsc_get_prescaler_shfactor(u32 hratio, u32 vratio, u32 *shfactor)
 }
 
 static int gsc_set_prescaler(struct gsc_context *ctx, struct gsc_scaler *sc,
-		struct drm_exynos_pos *src, struct drm_exynos_pos *dst)
+			     struct drm_exynos_ipp_task_rect *src,
+			     struct drm_exynos_ipp_task_rect *dst)
 {
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg;
 	u32 src_w, src_h, dst_w, dst_h;
 	int ret = 0;
@@ -939,13 +745,13 @@ static int gsc_set_prescaler(struct gsc_context *ctx, struct gsc_scaler *sc,
 
 	ret = gsc_get_ratio_shift(src_w, dst_w, &sc->pre_hratio);
 	if (ret) {
-		dev_err(ippdrv->dev, "failed to get ratio horizontal.\n");
+		dev_err(ctx->dev, "failed to get ratio horizontal.\n");
 		return ret;
 	}
 
 	ret = gsc_get_ratio_shift(src_h, dst_h, &sc->pre_vratio);
 	if (ret) {
-		dev_err(ippdrv->dev, "failed to get ratio vertical.\n");
+		dev_err(ctx->dev, "failed to get ratio vertical.\n");
 		return ret;
 	}
 
@@ -1039,47 +845,37 @@ static void gsc_set_scaler(struct gsc_context *ctx, struct gsc_scaler *sc)
 	gsc_write(cfg, GSC_MAIN_V_RATIO);
 }
 
-static int gsc_dst_set_size(struct device *dev, int swap,
-		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz)
+static void gsc_dst_set_size(struct gsc_context *ctx,
+			     struct exynos_drm_ipp_buffer *buf)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct drm_exynos_pos img_pos = *pos;
 	struct gsc_scaler *sc = &ctx->sc;
 	u32 cfg;
 
-	DRM_DEBUG_KMS("swap[%d]x[%d]y[%d]w[%d]h[%d]\n",
-		swap, pos->x, pos->y, pos->w, pos->h);
-
-	if (swap) {
-		img_pos.w = pos->h;
-		img_pos.h = pos->w;
-	}
-
 	/* pixel offset */
-	cfg = (GSC_DSTIMG_OFFSET_X(pos->x) |
-		GSC_DSTIMG_OFFSET_Y(pos->y));
+	cfg = (GSC_DSTIMG_OFFSET_X(buf->rect.x) |
+		GSC_DSTIMG_OFFSET_Y(buf->rect.y));
 	gsc_write(cfg, GSC_DSTIMG_OFFSET);
 
 	/* scaled size */
-	cfg = (GSC_SCALED_WIDTH(img_pos.w) | GSC_SCALED_HEIGHT(img_pos.h));
+	if (ctx->rotation)
+		cfg = (GSC_SCALED_WIDTH(buf->rect.h) |
+		       GSC_SCALED_HEIGHT(buf->rect.w));
+	else
+		cfg = (GSC_SCALED_WIDTH(buf->rect.w) |
+		       GSC_SCALED_HEIGHT(buf->rect.h));
 	gsc_write(cfg, GSC_SCALED_SIZE);
 
-	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", sz->hsize, sz->vsize);
-
 	/* original size */
 	cfg = gsc_read(GSC_DSTIMG_SIZE);
-	cfg &= ~(GSC_DSTIMG_HEIGHT_MASK |
-		GSC_DSTIMG_WIDTH_MASK);
-	cfg |= (GSC_DSTIMG_WIDTH(sz->hsize) |
-		GSC_DSTIMG_HEIGHT(sz->vsize));
+	cfg &= ~(GSC_DSTIMG_HEIGHT_MASK | GSC_DSTIMG_WIDTH_MASK);
+	cfg |= GSC_DSTIMG_WIDTH(buf->buf.width) |
+	       GSC_DSTIMG_HEIGHT(buf->buf.height);
 	gsc_write(cfg, GSC_DSTIMG_SIZE);
 
 	cfg = gsc_read(GSC_OUT_CON);
 	cfg &= ~GSC_OUT_RGB_TYPE_MASK;
 
-	DRM_DEBUG_KMS("width[%d]range[%d]\n", pos->w, sc->range);
-
-	if (pos->w >= GSC_WIDTH_ITU_709)
+	if (buf->rect.w >= GSC_WIDTH_ITU_709)
 		if (sc->range)
 			cfg |= GSC_OUT_RGB_HD_WIDE;
 		else
@@ -1091,8 +887,6 @@ static int gsc_dst_set_size(struct device *dev, int swap,
 			cfg |= GSC_OUT_RGB_SD_NARROW;
 
 	gsc_write(cfg, GSC_OUT_CON);
-
-	return 0;
 }
 
 static int gsc_dst_get_buf_seq(struct gsc_context *ctx)
@@ -1111,35 +905,16 @@ static int gsc_dst_get_buf_seq(struct gsc_context *ctx)
 	return buf_num;
 }
 
-static int gsc_dst_set_buf_seq(struct gsc_context *ctx, u32 buf_id,
-		enum drm_exynos_ipp_buf_type buf_type)
+static void gsc_dst_set_buf_seq(struct gsc_context *ctx, u32 buf_id,
+				bool enqueue)
 {
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	bool masked;
+	bool masked = !enqueue;
 	u32 cfg;
 	u32 mask = 0x00000001 << buf_id;
-	int ret = 0;
-
-	DRM_DEBUG_KMS("buf_id[%d]buf_type[%d]\n", buf_id, buf_type);
-
-	mutex_lock(&ctx->lock);
 
 	/* mask register set */
 	cfg = gsc_read(GSC_OUT_BASE_ADDR_Y_MASK);
 
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		masked = false;
-		break;
-	case IPP_BUF_DEQUEUE:
-		masked = true;
-		break;
-	default:
-		dev_err(ippdrv->dev, "invalid buf ctrl parameter.\n");
-		ret =  -EINVAL;
-		goto err_unlock;
-	}
-
 	/* sequence id */
 	cfg &= ~mask;
 	cfg |= masked << buf_id;
@@ -1148,94 +923,29 @@ static int gsc_dst_set_buf_seq(struct gsc_context *ctx, u32 buf_id,
 	gsc_write(cfg, GSC_OUT_BASE_ADDR_CR_MASK);
 
 	/* interrupt enable */
-	if (buf_type == IPP_BUF_ENQUEUE &&
-	    gsc_dst_get_buf_seq(ctx) >= GSC_BUF_START)
+	if (enqueue && gsc_dst_get_buf_seq(ctx) >= GSC_BUF_START)
 		gsc_handle_irq(ctx, true, false, true);
 
 	/* interrupt disable */
-	if (buf_type == IPP_BUF_DEQUEUE &&
-	    gsc_dst_get_buf_seq(ctx) <= GSC_BUF_STOP)
+	if (!enqueue && gsc_dst_get_buf_seq(ctx) <= GSC_BUF_STOP)
 		gsc_handle_irq(ctx, false, false, true);
-
-err_unlock:
-	mutex_unlock(&ctx->lock);
-	return ret;
 }
 
-static int gsc_dst_set_addr(struct device *dev,
-		struct drm_exynos_ipp_buf_info *buf_info, u32 buf_id,
-		enum drm_exynos_ipp_buf_type buf_type)
+static void gsc_dst_set_addr(struct gsc_context *ctx,
+			     u32 buf_id, struct exynos_drm_ipp_buffer *buf)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_property *property;
-
-	if (!c_node) {
-		DRM_ERROR("failed to get c_node.\n");
-		return -EFAULT;
-	}
-
-	property = &c_node->property;
-
-	DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]buf_type[%d]\n",
-		property->prop_id, buf_id, buf_type);
-
-	if (buf_id > GSC_MAX_DST) {
-		dev_info(ippdrv->dev, "invalid buf_id %d.\n", buf_id);
-		return -EINVAL;
-	}
-
 	/* address register set */
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		gsc_write(buf_info->base[EXYNOS_DRM_PLANAR_Y],
-			GSC_OUT_BASE_ADDR_Y(buf_id));
-		gsc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
-			GSC_OUT_BASE_ADDR_CB(buf_id));
-		gsc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
-			GSC_OUT_BASE_ADDR_CR(buf_id));
-		break;
-	case IPP_BUF_DEQUEUE:
-		gsc_write(0x0, GSC_OUT_BASE_ADDR_Y(buf_id));
-		gsc_write(0x0, GSC_OUT_BASE_ADDR_CB(buf_id));
-		gsc_write(0x0, GSC_OUT_BASE_ADDR_CR(buf_id));
-		break;
-	default:
-		/* bypass */
-		break;
-	}
+	gsc_write(buf->dma_addr[0], GSC_OUT_BASE_ADDR_Y(buf_id));
+	gsc_write(buf->dma_addr[1], GSC_OUT_BASE_ADDR_CB(buf_id));
+	gsc_write(buf->dma_addr[2], GSC_OUT_BASE_ADDR_CR(buf_id));
 
-	return gsc_dst_set_buf_seq(ctx, buf_id, buf_type);
-}
-
-static struct exynos_drm_ipp_ops gsc_dst_ops = {
-	.set_fmt = gsc_dst_set_fmt,
-	.set_transf = gsc_dst_set_transf,
-	.set_size = gsc_dst_set_size,
-	.set_addr = gsc_dst_set_addr,
-};
-
-static int gsc_clk_ctrl(struct gsc_context *ctx, bool enable)
-{
-	DRM_DEBUG_KMS("enable[%d]\n", enable);
-
-	if (enable) {
-		clk_prepare_enable(ctx->gsc_clk);
-		ctx->suspended = false;
-	} else {
-		clk_disable_unprepare(ctx->gsc_clk);
-		ctx->suspended = true;
-	}
-
-	return 0;
+	gsc_dst_set_buf_seq(ctx, buf_id, true);
 }
 
 static int gsc_get_src_buf_index(struct gsc_context *ctx)
 {
 	u32 cfg, curr_index, i;
 	u32 buf_id = GSC_MAX_SRC;
-	int ret;
 
 	DRM_DEBUG_KMS("gsc id[%d]\n", ctx->id);
 
@@ -1249,19 +959,15 @@ static int gsc_get_src_buf_index(struct gsc_context *ctx)
 		}
 	}
 
+	DRM_DEBUG_KMS("cfg[0x%x]curr_index[%d]buf_id[%d]\n", cfg,
+		curr_index, buf_id);
+
 	if (buf_id == GSC_MAX_SRC) {
 		DRM_ERROR("failed to get in buffer index.\n");
 		return -EINVAL;
 	}
 
-	ret = gsc_src_set_buf_seq(ctx, buf_id, IPP_BUF_DEQUEUE);
-	if (ret < 0) {
-		DRM_ERROR("failed to dequeue.\n");
-		return ret;
-	}
-
-	DRM_DEBUG_KMS("cfg[0x%x]curr_index[%d]buf_id[%d]\n", cfg,
-		curr_index, buf_id);
+	gsc_src_set_buf_seq(ctx, buf_id, false);
 
 	return buf_id;
 }
@@ -1270,7 +976,6 @@ static int gsc_get_dst_buf_index(struct gsc_context *ctx)
 {
 	u32 cfg, curr_index, i;
 	u32 buf_id = GSC_MAX_DST;
-	int ret;
 
 	DRM_DEBUG_KMS("gsc id[%d]\n", ctx->id);
 
@@ -1289,11 +994,7 @@ static int gsc_get_dst_buf_index(struct gsc_context *ctx)
 		return -EINVAL;
 	}
 
-	ret = gsc_dst_set_buf_seq(ctx, buf_id, IPP_BUF_DEQUEUE);
-	if (ret < 0) {
-		DRM_ERROR("failed to dequeue.\n");
-		return ret;
-	}
+	gsc_dst_set_buf_seq(ctx, buf_id, false);
 
 	DRM_DEBUG_KMS("cfg[0x%x]curr_index[%d]buf_id[%d]\n", cfg,
 		curr_index, buf_id);
@@ -1304,215 +1005,55 @@ static int gsc_get_dst_buf_index(struct gsc_context *ctx)
 static irqreturn_t gsc_irq_handler(int irq, void *dev_id)
 {
 	struct gsc_context *ctx = dev_id;
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_event_work *event_work =
-		c_node->event_work;
 	u32 status;
-	int buf_id[EXYNOS_DRM_OPS_MAX];
+	int err = 0;
 
 	DRM_DEBUG_KMS("gsc id[%d]\n", ctx->id);
 
 	status = gsc_read(GSC_IRQ);
 	if (status & GSC_IRQ_STATUS_OR_IRQ) {
-		dev_err(ippdrv->dev, "occurred overflow at %d, status 0x%x.\n",
+		dev_err(ctx->dev, "occurred overflow at %d, status 0x%x.\n",
 			ctx->id, status);
-		return IRQ_NONE;
+		err = -EINVAL;
 	}
 
 	if (status & GSC_IRQ_STATUS_OR_FRM_DONE) {
-		dev_dbg(ippdrv->dev, "occurred frame done at %d, status 0x%x.\n",
-			ctx->id, status);
-
-		buf_id[EXYNOS_DRM_OPS_SRC] = gsc_get_src_buf_index(ctx);
-		if (buf_id[EXYNOS_DRM_OPS_SRC] < 0)
-			return IRQ_HANDLED;
-
-		buf_id[EXYNOS_DRM_OPS_DST] = gsc_get_dst_buf_index(ctx);
-		if (buf_id[EXYNOS_DRM_OPS_DST] < 0)
-			return IRQ_HANDLED;
-
-		DRM_DEBUG_KMS("buf_id_src[%d]buf_id_dst[%d]\n",
-			buf_id[EXYNOS_DRM_OPS_SRC], buf_id[EXYNOS_DRM_OPS_DST]);
-
-		event_work->ippdrv = ippdrv;
-		event_work->buf_id[EXYNOS_DRM_OPS_SRC] =
-			buf_id[EXYNOS_DRM_OPS_SRC];
-		event_work->buf_id[EXYNOS_DRM_OPS_DST] =
-			buf_id[EXYNOS_DRM_OPS_DST];
-		queue_work(ippdrv->event_workq, &event_work->work);
-	}
-
-	return IRQ_HANDLED;
-}
-
-static int gsc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
-{
-	struct drm_exynos_ipp_prop_list *prop_list = &ippdrv->prop_list;
-
-	prop_list->version = 1;
-	prop_list->writeback = 1;
-	prop_list->refresh_min = GSC_REFRESH_MIN;
-	prop_list->refresh_max = GSC_REFRESH_MAX;
-	prop_list->flip = (1 << EXYNOS_DRM_FLIP_VERTICAL) |
-				(1 << EXYNOS_DRM_FLIP_HORIZONTAL);
-	prop_list->degree = (1 << EXYNOS_DRM_DEGREE_0) |
-				(1 << EXYNOS_DRM_DEGREE_90) |
-				(1 << EXYNOS_DRM_DEGREE_180) |
-				(1 << EXYNOS_DRM_DEGREE_270);
-	prop_list->csc = 1;
-	prop_list->crop = 1;
-	prop_list->crop_max.hsize = GSC_CROP_MAX;
-	prop_list->crop_max.vsize = GSC_CROP_MAX;
-	prop_list->crop_min.hsize = GSC_CROP_MIN;
-	prop_list->crop_min.vsize = GSC_CROP_MIN;
-	prop_list->scale = 1;
-	prop_list->scale_max.hsize = GSC_SCALE_MAX;
-	prop_list->scale_max.vsize = GSC_SCALE_MAX;
-	prop_list->scale_min.hsize = GSC_SCALE_MIN;
-	prop_list->scale_min.vsize = GSC_SCALE_MIN;
-
-	return 0;
-}
-
-static inline bool gsc_check_drm_flip(enum drm_exynos_flip flip)
-{
-	switch (flip) {
-	case EXYNOS_DRM_FLIP_NONE:
-	case EXYNOS_DRM_FLIP_VERTICAL:
-	case EXYNOS_DRM_FLIP_HORIZONTAL:
-	case EXYNOS_DRM_FLIP_BOTH:
-		return true;
-	default:
-		DRM_DEBUG_KMS("invalid flip\n");
-		return false;
-	}
-}
-
-static int gsc_ippdrv_check_property(struct device *dev,
-		struct drm_exynos_ipp_property *property)
-{
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_prop_list *pp = &ippdrv->prop_list;
-	struct drm_exynos_ipp_config *config;
-	struct drm_exynos_pos *pos;
-	struct drm_exynos_sz *sz;
-	bool swap;
-	int i;
-
-	for_each_ipp_ops(i) {
-		if ((i == EXYNOS_DRM_OPS_SRC) &&
-			(property->cmd == IPP_CMD_WB))
-			continue;
+		int src_buf_id, dst_buf_id;
 
-		config = &property->config[i];
-		pos = &config->pos;
-		sz = &config->sz;
-
-		/* check for flip */
-		if (!gsc_check_drm_flip(config->flip)) {
-			DRM_ERROR("invalid flip.\n");
-			goto err_property;
-		}
-
-		/* check for degree */
-		switch (config->degree) {
-		case EXYNOS_DRM_DEGREE_90:
-		case EXYNOS_DRM_DEGREE_270:
-			swap = true;
-			break;
-		case EXYNOS_DRM_DEGREE_0:
-		case EXYNOS_DRM_DEGREE_180:
-			swap = false;
-			break;
-		default:
-			DRM_ERROR("invalid degree.\n");
-			goto err_property;
-		}
+		dev_dbg(ctx->dev, "occurred frame done at %d, status 0x%x.\n",
+			ctx->id, status);
 
-		/* check for buffer bound */
-		if ((pos->x + pos->w > sz->hsize) ||
-			(pos->y + pos->h > sz->vsize)) {
-			DRM_ERROR("out of buf bound.\n");
-			goto err_property;
-		}
+		src_buf_id = gsc_get_src_buf_index(ctx);
+		dst_buf_id = gsc_get_dst_buf_index(ctx);
 
-		/* check for crop */
-		if ((i == EXYNOS_DRM_OPS_SRC) && (pp->crop)) {
-			if (swap) {
-				if ((pos->h < pp->crop_min.hsize) ||
-					(sz->vsize > pp->crop_max.hsize) ||
-					(pos->w < pp->crop_min.vsize) ||
-					(sz->hsize > pp->crop_max.vsize)) {
-					DRM_ERROR("out of crop size.\n");
-					goto err_property;
-				}
-			} else {
-				if ((pos->w < pp->crop_min.hsize) ||
-					(sz->hsize > pp->crop_max.hsize) ||
-					(pos->h < pp->crop_min.vsize) ||
-					(sz->vsize > pp->crop_max.vsize)) {
-					DRM_ERROR("out of crop size.\n");
-					goto err_property;
-				}
-			}
-		}
+		DRM_DEBUG_KMS("buf_id_src[%d]buf_id_dst[%d]\n",	src_buf_id,
+			      dst_buf_id);
 
-		/* check for scale */
-		if ((i == EXYNOS_DRM_OPS_DST) && (pp->scale)) {
-			if (swap) {
-				if ((pos->h < pp->scale_min.hsize) ||
-					(sz->vsize > pp->scale_max.hsize) ||
-					(pos->w < pp->scale_min.vsize) ||
-					(sz->hsize > pp->scale_max.vsize)) {
-					DRM_ERROR("out of scale size.\n");
-					goto err_property;
-				}
-			} else {
-				if ((pos->w < pp->scale_min.hsize) ||
-					(sz->hsize > pp->scale_max.hsize) ||
-					(pos->h < pp->scale_min.vsize) ||
-					(sz->vsize > pp->scale_max.vsize)) {
-					DRM_ERROR("out of scale size.\n");
-					goto err_property;
-				}
-			}
-		}
+		if (src_buf_id < 0 || dst_buf_id < 0)
+			err = -EINVAL;
 	}
 
-	return 0;
-
-err_property:
-	for_each_ipp_ops(i) {
-		if ((i == EXYNOS_DRM_OPS_SRC) &&
-			(property->cmd == IPP_CMD_WB))
-			continue;
+	if (ctx->task) {
+		struct exynos_drm_ipp_task *task = ctx->task;
 
-		config = &property->config[i];
-		pos = &config->pos;
-		sz = &config->sz;
-
-		DRM_ERROR("[%s]f[%d]r[%d]pos[%d %d %d %d]sz[%d %d]\n",
-			i ? "dst" : "src", config->flip, config->degree,
-			pos->x, pos->y, pos->w, pos->h,
-			sz->hsize, sz->vsize);
+		ctx->task = NULL;
+		pm_runtime_mark_last_busy(ctx->dev);
+		pm_runtime_put_autosuspend(ctx->dev);
+		exynos_drm_ipp_task_done(task, err);
 	}
 
-	return -EINVAL;
+	return IRQ_HANDLED;
 }
 
-
-static int gsc_ippdrv_reset(struct device *dev)
+static int gsc_reset(struct gsc_context *ctx)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
 	struct gsc_scaler *sc = &ctx->sc;
 	int ret;
 
 	/* reset h/w block */
 	ret = gsc_sw_reset(ctx);
 	if (ret < 0) {
-		dev_err(dev, "failed to reset hardware.\n");
+		dev_err(ctx->dev, "failed to reset hardware.\n");
 		return ret;
 	}
 
@@ -1523,166 +1064,172 @@ static int gsc_ippdrv_reset(struct device *dev)
 	return 0;
 }
 
-static int gsc_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
+static void gsc_start(struct gsc_context *ctx)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_property *property;
-	struct drm_exynos_ipp_config *config;
-	struct drm_exynos_pos	img_pos[EXYNOS_DRM_OPS_MAX];
-	struct drm_exynos_ipp_set_wb set_wb;
 	u32 cfg;
-	int ret, i;
-
-	DRM_DEBUG_KMS("cmd[%d]\n", cmd);
-
-	if (!c_node) {
-		DRM_ERROR("failed to get c_node.\n");
-		return -EINVAL;
-	}
-
-	property = &c_node->property;
 
 	gsc_handle_irq(ctx, true, false, true);
 
-	for_each_ipp_ops(i) {
-		config = &property->config[i];
-		img_pos[i] = config->pos;
-	}
+	/* enable one shot */
+	cfg = gsc_read(GSC_ENABLE);
+	cfg &= ~(GSC_ENABLE_ON_CLEAR_MASK |
+		GSC_ENABLE_CLK_GATE_MODE_MASK);
+	cfg |= GSC_ENABLE_ON_CLEAR_ONESHOT;
+	gsc_write(cfg, GSC_ENABLE);
 
-	switch (cmd) {
-	case IPP_CMD_M2M:
-		/* enable one shot */
-		cfg = gsc_read(GSC_ENABLE);
-		cfg &= ~(GSC_ENABLE_ON_CLEAR_MASK |
-			GSC_ENABLE_CLK_GATE_MODE_MASK);
-		cfg |= GSC_ENABLE_ON_CLEAR_ONESHOT;
-		gsc_write(cfg, GSC_ENABLE);
-
-		/* src dma memory */
-		cfg = gsc_read(GSC_IN_CON);
-		cfg &= ~(GSC_IN_PATH_MASK | GSC_IN_LOCAL_SEL_MASK);
-		cfg |= GSC_IN_PATH_MEMORY;
-		gsc_write(cfg, GSC_IN_CON);
-
-		/* dst dma memory */
-		cfg = gsc_read(GSC_OUT_CON);
-		cfg |= GSC_OUT_PATH_MEMORY;
-		gsc_write(cfg, GSC_OUT_CON);
-		break;
-	case IPP_CMD_WB:
-		set_wb.enable = 1;
-		set_wb.refresh = property->refresh_rate;
-		gsc_set_gscblk_fimd_wb(ctx, set_wb.enable);
-		exynos_drm_ippnb_send_event(IPP_SET_WRITEBACK, (void *)&set_wb);
-
-		/* src local path */
-		cfg = gsc_read(GSC_IN_CON);
-		cfg &= ~(GSC_IN_PATH_MASK | GSC_IN_LOCAL_SEL_MASK);
-		cfg |= (GSC_IN_PATH_LOCAL | GSC_IN_LOCAL_FIMD_WB);
-		gsc_write(cfg, GSC_IN_CON);
-
-		/* dst dma memory */
-		cfg = gsc_read(GSC_OUT_CON);
-		cfg |= GSC_OUT_PATH_MEMORY;
-		gsc_write(cfg, GSC_OUT_CON);
-		break;
-	case IPP_CMD_OUTPUT:
-		/* src dma memory */
-		cfg = gsc_read(GSC_IN_CON);
-		cfg &= ~(GSC_IN_PATH_MASK | GSC_IN_LOCAL_SEL_MASK);
-		cfg |= GSC_IN_PATH_MEMORY;
-		gsc_write(cfg, GSC_IN_CON);
-
-		/* dst local path */
-		cfg = gsc_read(GSC_OUT_CON);
-		cfg |= GSC_OUT_PATH_MEMORY;
-		gsc_write(cfg, GSC_OUT_CON);
-		break;
-	default:
-		ret = -EINVAL;
-		dev_err(dev, "invalid operations.\n");
-		return ret;
-	}
+	/* src dma memory */
+	cfg = gsc_read(GSC_IN_CON);
+	cfg &= ~(GSC_IN_PATH_MASK | GSC_IN_LOCAL_SEL_MASK);
+	cfg |= GSC_IN_PATH_MEMORY;
+	gsc_write(cfg, GSC_IN_CON);
 
-	ret = gsc_set_prescaler(ctx, &ctx->sc,
-		&img_pos[EXYNOS_DRM_OPS_SRC],
-		&img_pos[EXYNOS_DRM_OPS_DST]);
-	if (ret) {
-		dev_err(dev, "failed to set prescaler.\n");
-		return ret;
-	}
+	/* dst dma memory */
+	cfg = gsc_read(GSC_OUT_CON);
+	cfg |= GSC_OUT_PATH_MEMORY;
+	gsc_write(cfg, GSC_OUT_CON);
 
 	gsc_set_scaler(ctx, &ctx->sc);
 
 	cfg = gsc_read(GSC_ENABLE);
 	cfg |= GSC_ENABLE_ON;
 	gsc_write(cfg, GSC_ENABLE);
+}
+
+static int gsc_commit(struct exynos_drm_ipp *ipp,
+			  struct exynos_drm_ipp_task *task)
+{
+	struct gsc_context *ctx = container_of(ipp, struct gsc_context, ipp);
+	int ret;
+
+	pm_runtime_get_sync(ctx->dev);
+	ctx->task = task;
+
+	ret = gsc_reset(ctx);
+	if (ret) {
+		pm_runtime_put_autosuspend(ctx->dev);
+		ctx->task = NULL;
+		return ret;
+	}
+
+	gsc_src_set_fmt(ctx, task->src.buf.fourcc);
+	gsc_src_set_transf(ctx, task->transform.rotation);
+	gsc_src_set_size(ctx, &task->src);
+	gsc_src_set_addr(ctx, 0, &task->src);
+	gsc_dst_set_fmt(ctx, task->dst.buf.fourcc);
+	gsc_dst_set_size(ctx, &task->dst);
+	gsc_dst_set_addr(ctx, 0, &task->dst);
+	gsc_set_prescaler(ctx, &ctx->sc, &task->src.rect, &task->dst.rect);
+	gsc_start(ctx);
 
 	return 0;
 }
 
-static void gsc_ippdrv_stop(struct device *dev, enum drm_exynos_ipp_cmd cmd)
+static void gsc_abort(struct exynos_drm_ipp *ipp,
+			  struct exynos_drm_ipp_task *task)
 {
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct drm_exynos_ipp_set_wb set_wb = {0, 0};
-	u32 cfg;
+	struct gsc_context *ctx =
+			container_of(ipp, struct gsc_context, ipp);
 
-	DRM_DEBUG_KMS("cmd[%d]\n", cmd);
+	gsc_reset(ctx);
+	if (ctx->task) {
+		struct exynos_drm_ipp_task *task = ctx->task;
 
-	switch (cmd) {
-	case IPP_CMD_M2M:
-		/* bypass */
-		break;
-	case IPP_CMD_WB:
-		gsc_set_gscblk_fimd_wb(ctx, set_wb.enable);
-		exynos_drm_ippnb_send_event(IPP_SET_WRITEBACK, (void *)&set_wb);
-		break;
-	case IPP_CMD_OUTPUT:
-	default:
-		dev_err(dev, "invalid operations.\n");
-		break;
+		ctx->task = NULL;
+		pm_runtime_mark_last_busy(ctx->dev);
+		pm_runtime_put_autosuspend(ctx->dev);
+		exynos_drm_ipp_task_done(task, -EIO);
 	}
+}
 
-	gsc_handle_irq(ctx, false, false, true);
+static struct exynos_drm_ipp_funcs ipp_funcs = {
+	.commit = gsc_commit,
+	.abort = gsc_abort,
+};
 
-	/* reset sequence */
-	gsc_write(0xff, GSC_OUT_BASE_ADDR_Y_MASK);
-	gsc_write(0xff, GSC_OUT_BASE_ADDR_CB_MASK);
-	gsc_write(0xff, GSC_OUT_BASE_ADDR_CR_MASK);
+static int gsc_bind(struct device *dev, struct device *master, void *data)
+{
+	struct gsc_context *ctx = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_ipp *ipp = &ctx->ipp;
 
-	cfg = gsc_read(GSC_ENABLE);
-	cfg &= ~GSC_ENABLE_ON;
-	gsc_write(cfg, GSC_ENABLE);
+	ctx->drm_dev = drm_dev;
+	drm_iommu_attach_device(drm_dev, dev);
+
+	exynos_drm_ipp_register(drm_dev, ipp, &ipp_funcs,
+			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
+			DRM_EXYNOS_IPP_CAP_SCALE | DRM_EXYNOS_IPP_CAP_CONVERT,
+			ctx->formats, ctx->num_formats, "gsc");
+
+	dev_info(dev, "The exynos gscaler has been probed successfully\n");
+
+	return 0;
+}
+
+static void gsc_unbind(struct device *dev, struct device *master,
+			void *data)
+{
+	struct gsc_context *ctx = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_ipp *ipp = &ctx->ipp;
+
+	exynos_drm_ipp_unregister(drm_dev, ipp);
+	drm_iommu_detach_device(drm_dev, dev);
 }
 
+static const struct component_ops gsc_component_ops = {
+	.bind	= gsc_bind,
+	.unbind = gsc_unbind,
+};
+
+static const unsigned int gsc_formats[] = {
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB8888, DRM_FORMAT_RGB565, DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_NV12, DRM_FORMAT_NV16, DRM_FORMAT_NV21, DRM_FORMAT_NV61,
+	DRM_FORMAT_UYVY, DRM_FORMAT_VYUY, DRM_FORMAT_YUYV, DRM_FORMAT_YVYU,
+	DRM_FORMAT_YUV420, DRM_FORMAT_YVU420, DRM_FORMAT_YUV422,
+};
+
 static int gsc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct gsc_driverdata *driver_data;
+	struct exynos_drm_ipp_formats *formats;
 	struct gsc_context *ctx;
 	struct resource *res;
-	struct exynos_drm_ippdrv *ippdrv;
-	int ret;
+	int ret, i;
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
-	if (dev->of_node) {
-		ctx->sysreg = syscon_regmap_lookup_by_phandle(dev->of_node,
-							"samsung,sysreg");
-		if (IS_ERR(ctx->sysreg)) {
-			dev_warn(dev, "failed to get system register.\n");
-			ctx->sysreg = NULL;
-		}
+	formats = devm_kzalloc(dev, sizeof(*formats) *
+			       (ARRAY_SIZE(gsc_formats)), GFP_KERNEL);
+	if (!formats)
+		return -ENOMEM;
+
+	driver_data = (struct gsc_driverdata *)of_device_get_match_data(dev);
+	ctx->dev = dev;
+	ctx->num_clocks = driver_data->num_clocks;
+	ctx->clk_names = driver_data->clk_names;
+
+	for (i = 0; i < ARRAY_SIZE(gsc_formats); i++) {
+		formats[i].fourcc = gsc_formats[i];
+		formats[i].type = DRM_EXYNOS_IPP_FORMAT_SOURCE |
+				  DRM_EXYNOS_IPP_FORMAT_DESTINATION;
+		formats[i].limits = driver_data->limits;
+		formats[i].num_limits = driver_data->num_limits;
 	}
+	ctx->formats = formats;
+	ctx->num_formats = ARRAY_SIZE(gsc_formats);
 
 	/* clock control */
-	ctx->gsc_clk = devm_clk_get(dev, "gscl");
-	if (IS_ERR(ctx->gsc_clk)) {
-		dev_err(dev, "failed to get gsc clock.\n");
-		return PTR_ERR(ctx->gsc_clk);
+	for (i = 0; i < ctx->num_clocks; i++) {
+		ctx->clocks[i] = devm_clk_get(dev, ctx->clk_names[i]);
+		if (IS_ERR(ctx->clocks[i])) {
+			dev_err(dev, "failed to get clock: %s\n",
+				ctx->clk_names[i]);
+			return PTR_ERR(ctx->clocks[i]);
+		}
 	}
 
 	/* resource memory */
@@ -1699,8 +1246,8 @@ static int gsc_probe(struct platform_device *pdev)
 	}
 
 	ctx->irq = res->start;
-	ret = devm_request_threaded_irq(dev, ctx->irq, NULL, gsc_irq_handler,
-		IRQF_ONESHOT, "drm_gsc", ctx);
+	ret = devm_request_irq(dev, ctx->irq, gsc_irq_handler, 0,
+			       dev_name(dev), ctx);
 	if (ret < 0) {
 		dev_err(dev, "failed to request irq.\n");
 		return ret;
@@ -1709,38 +1256,22 @@ static int gsc_probe(struct platform_device *pdev)
 	/* context initailization */
 	ctx->id = pdev->id;
 
-	ippdrv = &ctx->ippdrv;
-	ippdrv->dev = dev;
-	ippdrv->ops[EXYNOS_DRM_OPS_SRC] = &gsc_src_ops;
-	ippdrv->ops[EXYNOS_DRM_OPS_DST] = &gsc_dst_ops;
-	ippdrv->check_property = gsc_ippdrv_check_property;
-	ippdrv->reset = gsc_ippdrv_reset;
-	ippdrv->start = gsc_ippdrv_start;
-	ippdrv->stop = gsc_ippdrv_stop;
-	ret = gsc_init_prop_list(ippdrv);
-	if (ret < 0) {
-		dev_err(dev, "failed to init property list.\n");
-		return ret;
-	}
-
-	DRM_DEBUG_KMS("id[%d]ippdrv[%pK]\n", ctx->id, ippdrv);
-
-	mutex_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
 
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, GSC_AUTOSUSPEND_DELAY);
 	pm_runtime_enable(dev);
 
-	ret = exynos_drm_ippdrv_register(ippdrv);
-	if (ret < 0) {
-		dev_err(dev, "failed to register drm gsc device.\n");
-		goto err_ippdrv_register;
-	}
+	ret = component_add(dev, &gsc_component_ops);
+	if (ret)
+		goto err_pm_dis;
 
 	dev_info(dev, "drm gsc registered successfully.\n");
 
 	return 0;
 
-err_ippdrv_register:
+err_pm_dis:
+	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
 	return ret;
 }
@@ -1748,13 +1279,8 @@ err_ippdrv_register:
 static int gsc_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct gsc_context *ctx = get_gsc_context(dev);
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 
-	exynos_drm_ippdrv_unregister(ippdrv);
-	mutex_destroy(&ctx->lock);
-
-	pm_runtime_set_suspended(dev);
+	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
 
 	return 0;
@@ -1763,19 +1289,32 @@ static int gsc_remove(struct platform_device *pdev)
 static int __maybe_unused gsc_runtime_suspend(struct device *dev)
 {
 	struct gsc_context *ctx = get_gsc_context(dev);
+	int i;
 
 	DRM_DEBUG_KMS("id[%d]\n", ctx->id);
 
-	return  gsc_clk_ctrl(ctx, false);
+	for (i = ctx->num_clocks - 1; i >= 0; i--)
+		clk_disable_unprepare(ctx->clocks[i]);
+
+	return 0;
 }
 
 static int __maybe_unused gsc_runtime_resume(struct device *dev)
 {
 	struct gsc_context *ctx = get_gsc_context(dev);
+	int i, ret;
 
 	DRM_DEBUG_KMS("id[%d]\n", ctx->id);
 
-	return  gsc_clk_ctrl(ctx, true);
+	for (i = 0; i < ctx->num_clocks; i++) {
+		ret = clk_prepare_enable(ctx->clocks[i]);
+		if (ret) {
+			while (--i > 0)
+				clk_disable_unprepare(ctx->clocks[i]);
+			return ret;
+		}
+	}
+	return 0;
 }
 
 static const struct dev_pm_ops gsc_pm_ops = {
@@ -1784,9 +1323,66 @@ static const struct dev_pm_ops gsc_pm_ops = {
 	SET_RUNTIME_PM_OPS(gsc_runtime_suspend, gsc_runtime_resume, NULL)
 };
 
+static const struct drm_exynos_ipp_limit gsc_5250_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, 4800, 8 }, .v = { 16, 3344, 8 }) },
+	{ IPP_SIZE_LIMIT(AREA, .h = { 16, 4800, 2 }, .v = { 8, 3344, 2 }) },
+	{ IPP_SIZE_LIMIT(ROTATED, .h = { 32, 2048 }, .v = { 16, 2048 }) },
+	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 16, (1 << 16) * 8 },
+			  .v = { (1 << 16) / 16, (1 << 16) * 8 }) },
+};
+
+static const struct drm_exynos_ipp_limit gsc_5420_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, 4800, 8 }, .v = { 16, 3344, 8 }) },
+	{ IPP_SIZE_LIMIT(AREA, .h = { 16, 4800, 2 }, .v = { 8, 3344, 2 }) },
+	{ IPP_SIZE_LIMIT(ROTATED, .h = { 16, 2016 }, .v = { 8, 2016 }) },
+	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 16, (1 << 16) * 8 },
+			  .v = { (1 << 16) / 16, (1 << 16) * 8 }) },
+};
+
+static const struct drm_exynos_ipp_limit gsc_5433_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, 8191, 2 }, .v = { 16, 8191, 2 }) },
+	{ IPP_SIZE_LIMIT(AREA, .h = { 16, 4800, 1 }, .v = { 8, 3344, 1 }) },
+	{ IPP_SIZE_LIMIT(ROTATED, .h = { 32, 2047 }, .v = { 8, 8191 }) },
+	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 16, (1 << 16) * 8 },
+			  .v = { (1 << 16) / 16, (1 << 16) * 8 }) },
+};
+
+static struct gsc_driverdata gsc_exynos5250_drvdata = {
+	.clk_names = {"gscl"},
+	.num_clocks = 1,
+	.limits = gsc_5250_limits,
+	.num_limits = ARRAY_SIZE(gsc_5250_limits),
+};
+
+static struct gsc_driverdata gsc_exynos5420_drvdata = {
+	.clk_names = {"gscl"},
+	.num_clocks = 1,
+	.limits = gsc_5420_limits,
+	.num_limits = ARRAY_SIZE(gsc_5420_limits),
+};
+
+static struct gsc_driverdata gsc_exynos5433_drvdata = {
+	.clk_names = {"pclk", "aclk", "aclk_xiu", "aclk_gsclbend"},
+	.num_clocks = 4,
+	.limits = gsc_5433_limits,
+	.num_limits = ARRAY_SIZE(gsc_5433_limits),
+};
+
 static const struct of_device_id exynos_drm_gsc_of_match[] = {
-	{ .compatible = "samsung,exynos5-gsc" },
-	{ },
+	{
+		.compatible = "samsung,exynos5-gsc",
+		.data = &gsc_exynos5250_drvdata,
+	}, {
+		.compatible = "samsung,exynos5250-gsc",
+		.data = &gsc_exynos5250_drvdata,
+	}, {
+		.compatible = "samsung,exynos5420-gsc",
+		.data = &gsc_exynos5420_drvdata,
+	}, {
+		.compatible = "samsung,exynos5433-gsc",
+		.data = &gsc_exynos5433_drvdata,
+	}, {
+	},
 };
 MODULE_DEVICE_TABLE(of, exynos_drm_gsc_of_match);
 
@@ -1800,4 +1396,3 @@ struct platform_driver gsc_driver = {
 		.of_match_table = of_match_ptr(exynos_drm_gsc_of_match),
 	},
 };
-
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.h b/drivers/gpu/drm/exynos/exynos_drm_gsc.h
deleted file mode 100644
index 29ec1c5efcf2..000000000000
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *
- * Authors:
- *	Eunchul Kim <chulspro.kim@samsung.com>
- *	Jinyoung Jeon <jy0.jeon@samsung.com>
- *	Sangmin Lee <lsmin.lee@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef _EXYNOS_DRM_GSC_H_
-#define _EXYNOS_DRM_GSC_H_
-
-/*
- * TODO
- * FIMD output interface notifier callback.
- * Mixer output interface notifier callback.
- */
-
-#endif /* _EXYNOS_DRM_GSC_H_ */
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
new file mode 100644
index 000000000000..26374e58c557
--- /dev/null
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -0,0 +1,916 @@
+/*
+ * Copyright (C) 2017 Samsung Electronics Co.Ltd
+ * Authors:
+ *	Marek Szyprowski <m.szyprowski@samsung.com>
+ *
+ * Exynos DRM Image Post Processing (IPP) related functions
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ */
+
+
+#include <drm/drmP.h>
+#include <drm/drm_mode.h>
+#include <uapi/drm/exynos_drm.h>
+
+#include "exynos_drm_drv.h"
+#include "exynos_drm_gem.h"
+#include "exynos_drm_ipp.h"
+
+static int num_ipp;
+static LIST_HEAD(ipp_list);
+
+/**
+ * exynos_drm_ipp_register - Register a new picture processor hardware module
+ * @dev: DRM device
+ * @ipp: ipp module to init
+ * @funcs: callbacks for the new ipp object
+ * @caps: bitmask of ipp capabilities (%DRM_EXYNOS_IPP_CAP_*)
+ * @formats: array of supported formats
+ * @num_formats: size of the supported formats array
+ * @name: name (for debugging purposes)
+ *
+ * Initializes a ipp module.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
+int exynos_drm_ipp_register(struct drm_device *dev, struct exynos_drm_ipp *ipp,
+		const struct exynos_drm_ipp_funcs *funcs, unsigned int caps,
+		const struct exynos_drm_ipp_formats *formats,
+		unsigned int num_formats, const char *name)
+{
+	WARN_ON(!ipp);
+	WARN_ON(!funcs);
+	WARN_ON(!formats);
+	WARN_ON(!num_formats);
+
+	spin_lock_init(&ipp->lock);
+	INIT_LIST_HEAD(&ipp->todo_list);
+	init_waitqueue_head(&ipp->done_wq);
+	ipp->dev = dev;
+	ipp->funcs = funcs;
+	ipp->capabilities = caps;
+	ipp->name = name;
+	ipp->formats = formats;
+	ipp->num_formats = num_formats;
+
+	/* ipp_list modification is serialized by component framework */
+	list_add_tail(&ipp->head, &ipp_list);
+	ipp->id = num_ipp++;
+
+	DRM_DEBUG_DRIVER("Registered ipp %d\n", ipp->id);
+
+	return 0;
+}
+
+/**
+ * exynos_drm_ipp_unregister - Unregister the picture processor module
+ * @dev: DRM device
+ * @ipp: ipp module
+ */
+void exynos_drm_ipp_unregister(struct drm_device *dev,
+			       struct exynos_drm_ipp *ipp)
+{
+	WARN_ON(ipp->task);
+	WARN_ON(!list_empty(&ipp->todo_list));
+	list_del(&ipp->head);
+}
+
+/**
+ * exynos_drm_ipp_ioctl_get_res_ioctl - enumerate all ipp modules
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * Construct a list of ipp ids.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
+int exynos_drm_ipp_get_res_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct drm_exynos_ioctl_ipp_get_res *resp = data;
+	struct exynos_drm_ipp *ipp;
+	uint32_t __user *ipp_ptr = (uint32_t __user *)
+						(unsigned long)resp->ipp_id_ptr;
+	unsigned int count = num_ipp, copied = 0;
+
+	/*
+	 * This ioctl is called twice, once to determine how much space is
+	 * needed, and the 2nd time to fill it.
+	 */
+	if (count && resp->count_ipps >= count) {
+		list_for_each_entry(ipp, &ipp_list, head) {
+			if (put_user(ipp->id, ipp_ptr + copied))
+				return -EFAULT;
+			copied++;
+		}
+	}
+	resp->count_ipps = count;
+
+	return 0;
+}
+
+static inline struct exynos_drm_ipp *__ipp_get(uint32_t id)
+{
+	struct exynos_drm_ipp *ipp;
+
+	list_for_each_entry(ipp, &ipp_list, head)
+		if (ipp->id == id)
+			return ipp;
+	return NULL;
+}
+
+/**
+ * exynos_drm_ipp_ioctl_get_caps - get ipp module capabilities and formats
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * Construct a structure describing ipp module capabilities.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
+int exynos_drm_ipp_get_caps_ioctl(struct drm_device *dev, void *data,
+				  struct drm_file *file_priv)
+{
+	struct drm_exynos_ioctl_ipp_get_caps *resp = data;
+	void __user *ptr = (void __user *)(unsigned long)resp->formats_ptr;
+	struct exynos_drm_ipp *ipp;
+	int i;
+
+	ipp = __ipp_get(resp->ipp_id);
+	if (!ipp)
+		return -ENOENT;
+
+	resp->ipp_id = ipp->id;
+	resp->capabilities = ipp->capabilities;
+
+	/*
+	 * This ioctl is called twice, once to determine how much space is
+	 * needed, and the 2nd time to fill it.
+	 */
+	if (resp->formats_count >= ipp->num_formats) {
+		for (i = 0; i < ipp->num_formats; i++) {
+			struct drm_exynos_ipp_format tmp = {
+				.fourcc = ipp->formats[i].fourcc,
+				.type = ipp->formats[i].type,
+				.modifier = ipp->formats[i].modifier,
+			};
+
+			if (copy_to_user(ptr, &tmp, sizeof(tmp)))
+				return -EFAULT;
+			ptr += sizeof(tmp);
+		}
+	}
+	resp->formats_count = ipp->num_formats;
+
+	return 0;
+}
+
+static inline const struct exynos_drm_ipp_formats *__ipp_format_get(
+				struct exynos_drm_ipp *ipp, uint32_t fourcc,
+				uint64_t mod, unsigned int type)
+{
+	int i;
+
+	for (i = 0; i < ipp->num_formats; i++) {
+		if ((ipp->formats[i].type & type) &&
+		    ipp->formats[i].fourcc == fourcc &&
+		    ipp->formats[i].modifier == mod)
+			return &ipp->formats[i];
+	}
+	return NULL;
+}
+
+/**
+ * exynos_drm_ipp_get_limits_ioctl - get ipp module limits
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * Construct a structure describing ipp module limitations for provided
+ * picture format.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
+int exynos_drm_ipp_get_limits_ioctl(struct drm_device *dev, void *data,
+				    struct drm_file *file_priv)
+{
+	struct drm_exynos_ioctl_ipp_get_limits *resp = data;
+	void __user *ptr = (void __user *)(unsigned long)resp->limits_ptr;
+	const struct exynos_drm_ipp_formats *format;
+	struct exynos_drm_ipp *ipp;
+
+	if (resp->type != DRM_EXYNOS_IPP_FORMAT_SOURCE &&
+	    resp->type != DRM_EXYNOS_IPP_FORMAT_DESTINATION)
+		return -EINVAL;
+
+	ipp = __ipp_get(resp->ipp_id);
+	if (!ipp)
+		return -ENOENT;
+
+	format = __ipp_format_get(ipp, resp->fourcc, resp->modifier,
+				  resp->type);
+	if (!format)
+		return -EINVAL;
+
+	/*
+	 * This ioctl is called twice, once to determine how much space is
+	 * needed, and the 2nd time to fill it.
+	 */
+	if (format->num_limits && resp->limits_count >= format->num_limits)
+		if (copy_to_user((void __user *)ptr, format->limits,
+				 sizeof(*format->limits) * format->num_limits))
+			return -EFAULT;
+	resp->limits_count = format->num_limits;
+
+	return 0;
+}
+
+struct drm_pending_exynos_ipp_event {
+	struct drm_pending_event base;
+	struct drm_exynos_ipp_event event;
+};
+
+static inline struct exynos_drm_ipp_task *
+			exynos_drm_ipp_task_alloc(struct exynos_drm_ipp *ipp)
+{
+	struct exynos_drm_ipp_task *task;
+
+	task = kzalloc(sizeof(*task), GFP_KERNEL);
+	if (!task)
+		return NULL;
+
+	task->dev = ipp->dev;
+	task->ipp = ipp;
+
+	/* some defaults */
+	task->src.rect.w = task->dst.rect.w = UINT_MAX;
+	task->src.rect.h = task->dst.rect.h = UINT_MAX;
+	task->transform.rotation = DRM_MODE_ROTATE_0;
+
+	DRM_DEBUG_DRIVER("Allocated task %pK\n", task);
+
+	return task;
+}
+
+static const struct exynos_drm_param_map {
+	unsigned int id;
+	unsigned int size;
+	unsigned int offset;
+} exynos_drm_ipp_params_maps[] = {
+	{
+		DRM_EXYNOS_IPP_TASK_BUFFER | DRM_EXYNOS_IPP_TASK_TYPE_SOURCE,
+		sizeof(struct drm_exynos_ipp_task_buffer),
+		offsetof(struct exynos_drm_ipp_task, src.buf),
+	}, {
+		DRM_EXYNOS_IPP_TASK_BUFFER |
+			DRM_EXYNOS_IPP_TASK_TYPE_DESTINATION,
+		sizeof(struct drm_exynos_ipp_task_buffer),
+		offsetof(struct exynos_drm_ipp_task, dst.buf),
+	}, {
+		DRM_EXYNOS_IPP_TASK_RECTANGLE | DRM_EXYNOS_IPP_TASK_TYPE_SOURCE,
+		sizeof(struct drm_exynos_ipp_task_rect),
+		offsetof(struct exynos_drm_ipp_task, src.rect),
+	}, {
+		DRM_EXYNOS_IPP_TASK_RECTANGLE |
+			DRM_EXYNOS_IPP_TASK_TYPE_DESTINATION,
+		sizeof(struct drm_exynos_ipp_task_rect),
+		offsetof(struct exynos_drm_ipp_task, dst.rect),
+	}, {
+		DRM_EXYNOS_IPP_TASK_TRANSFORM,
+		sizeof(struct drm_exynos_ipp_task_transform),
+		offsetof(struct exynos_drm_ipp_task, transform),
+	}, {
+		DRM_EXYNOS_IPP_TASK_ALPHA,
+		sizeof(struct drm_exynos_ipp_task_alpha),
+		offsetof(struct exynos_drm_ipp_task, alpha),
+	},
+};
+
+static int exynos_drm_ipp_task_set(struct exynos_drm_ipp_task *task,
+				   struct drm_exynos_ioctl_ipp_commit *arg)
+{
+	const struct exynos_drm_param_map *map = exynos_drm_ipp_params_maps;
+	void __user *params = (void __user *)(unsigned long)arg->params_ptr;
+	unsigned int size = arg->params_size;
+	uint32_t id;
+	int i;
+
+	while (size) {
+		if (get_user(id, (uint32_t __user *)params))
+			return -EFAULT;
+
+		for (i = 0; i < ARRAY_SIZE(exynos_drm_ipp_params_maps); i++)
+			if (map[i].id == id)
+				break;
+		if (i == ARRAY_SIZE(exynos_drm_ipp_params_maps) ||
+		    map[i].size > size)
+			return -EINVAL;
+
+		if (copy_from_user((void *)task + map[i].offset, params,
+				   map[i].size))
+			return -EFAULT;
+
+		params += map[i].size;
+		size -= map[i].size;
+	}
+
+	DRM_DEBUG_DRIVER("Got task %pK configuration from userspace\n", task);
+	return 0;
+}
+
+static int exynos_drm_ipp_task_setup_buffer(struct exynos_drm_ipp_buffer *buf,
+					    struct drm_file *filp)
+{
+	int ret = 0;
+	int i;
+
+	/* basic checks */
+	if (buf->buf.width == 0 || buf->buf.height == 0)
+		return -EINVAL;
+	buf->format = drm_format_info(buf->buf.fourcc);
+	for (i = 0; i < buf->format->num_planes; i++) {
+		unsigned int width = (i == 0) ? buf->buf.width :
+			     DIV_ROUND_UP(buf->buf.width, buf->format->hsub);
+
+		if (buf->buf.pitch[i] == 0)
+			buf->buf.pitch[i] = width * buf->format->cpp[i];
+		if (buf->buf.pitch[i] < width * buf->format->cpp[i])
+			return -EINVAL;
+		if (!buf->buf.gem_id[i])
+			return -ENOENT;
+	}
+
+	/* pitch for additional planes must match */
+	if (buf->format->num_planes > 2 &&
+	    buf->buf.pitch[1] != buf->buf.pitch[2])
+		return -EINVAL;
+
+	/* get GEM buffers and check their size */
+	for (i = 0; i < buf->format->num_planes; i++) {
+		unsigned int height = (i == 0) ? buf->buf.height :
+			     DIV_ROUND_UP(buf->buf.height, buf->format->vsub);
+		unsigned long size = height * buf->buf.pitch[i];
+		struct drm_gem_object *obj = drm_gem_object_lookup(filp,
+							    buf->buf.gem_id[i]);
+		if (!obj) {
+			ret = -ENOENT;
+			goto gem_free;
+		}
+		buf->exynos_gem[i] = to_exynos_gem(obj);
+
+		if (size + buf->buf.offset[i] > buf->exynos_gem[i]->size) {
+			i++;
+			ret = -EINVAL;
+			goto gem_free;
+		}
+		buf->dma_addr[i] = buf->exynos_gem[i]->dma_addr +
+				   buf->buf.offset[i];
+	}
+
+	return 0;
+gem_free:
+	while (i--) {
+		drm_gem_object_put_unlocked(&buf->exynos_gem[i]->base);
+		buf->exynos_gem[i] = NULL;
+	}
+	return ret;
+}
+
+static void exynos_drm_ipp_task_release_buf(struct exynos_drm_ipp_buffer *buf)
+{
+	int i;
+
+	if (!buf->exynos_gem[0])
+		return;
+	for (i = 0; i < buf->format->num_planes; i++)
+		drm_gem_object_put_unlocked(&buf->exynos_gem[i]->base);
+}
+
+static void exynos_drm_ipp_task_free(struct exynos_drm_ipp *ipp,
+				 struct exynos_drm_ipp_task *task)
+{
+	DRM_DEBUG_DRIVER("Freeing task %pK\n", task);
+
+	exynos_drm_ipp_task_release_buf(&task->src);
+	exynos_drm_ipp_task_release_buf(&task->dst);
+	if (task->event)
+		drm_event_cancel_free(ipp->dev, &task->event->base);
+	kfree(task);
+}
+
+struct drm_ipp_limit {
+	struct drm_exynos_ipp_limit_val h;
+	struct drm_exynos_ipp_limit_val v;
+};
+
+enum drm_ipp_size_id {
+	IPP_LIMIT_BUFFER, IPP_LIMIT_AREA, IPP_LIMIT_ROTATED, IPP_LIMIT_MAX
+};
+
+static const enum drm_ipp_size_id limit_id_fallback[IPP_LIMIT_MAX][4] = {
+	[IPP_LIMIT_BUFFER]  = { DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
+	[IPP_LIMIT_AREA]    = { DRM_EXYNOS_IPP_LIMIT_SIZE_AREA,
+				DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
+	[IPP_LIMIT_ROTATED] = { DRM_EXYNOS_IPP_LIMIT_SIZE_ROTATED,
+				DRM_EXYNOS_IPP_LIMIT_SIZE_AREA,
+				DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
+};
+
+static inline void __limit_set_val(unsigned int *ptr, unsigned int val)
+{
+	if (!*ptr)
+		*ptr = val;
+}
+
+static void __get_size_limit(const struct drm_exynos_ipp_limit *limits,
+			     unsigned int num_limits, enum drm_ipp_size_id id,
+			     struct drm_ipp_limit *res)
+{
+	const struct drm_exynos_ipp_limit *l = limits;
+	int i = 0;
+
+	memset(res, 0, sizeof(*res));
+	for (i = 0; limit_id_fallback[id][i]; i++)
+		for (l = limits; l - limits < num_limits; l++) {
+			if (((l->type & DRM_EXYNOS_IPP_LIMIT_TYPE_MASK) !=
+			      DRM_EXYNOS_IPP_LIMIT_TYPE_SIZE) ||
+			    ((l->type & DRM_EXYNOS_IPP_LIMIT_SIZE_MASK) !=
+						     limit_id_fallback[id][i]))
+				continue;
+			__limit_set_val(&res->h.min, l->h.min);
+			__limit_set_val(&res->h.max, l->h.max);
+			__limit_set_val(&res->h.align, l->h.align);
+			__limit_set_val(&res->v.min, l->v.min);
+			__limit_set_val(&res->v.max, l->v.max);
+			__limit_set_val(&res->v.align, l->v.align);
+		}
+}
+
+static inline bool __align_check(unsigned int val, unsigned int align)
+{
+	if (align && (val & (align - 1))) {
+		DRM_DEBUG_DRIVER("Value %d exceeds HW limits (align %d)\n",
+				 val, align);
+		return false;
+	}
+	return true;
+}
+
+static inline bool __size_limit_check(unsigned int val,
+				 struct drm_exynos_ipp_limit_val *l)
+{
+	if ((l->min && val < l->min) || (l->max && val > l->max)) {
+		DRM_DEBUG_DRIVER("Value %d exceeds HW limits (min %d, max %d)\n",
+				 val, l->min, l->max);
+		return false;
+	}
+	return __align_check(val, l->align);
+}
+
+static int exynos_drm_ipp_check_size_limits(struct exynos_drm_ipp_buffer *buf,
+	const struct drm_exynos_ipp_limit *limits, unsigned int num_limits,
+	bool rotate, bool swap)
+{
+	enum drm_ipp_size_id id = rotate ? IPP_LIMIT_ROTATED : IPP_LIMIT_AREA;
+	struct drm_ipp_limit l;
+	struct drm_exynos_ipp_limit_val *lh = &l.h, *lv = &l.v;
+
+	if (!limits)
+		return 0;
+
+	__get_size_limit(limits, num_limits, IPP_LIMIT_BUFFER, &l);
+	if (!__size_limit_check(buf->buf.width, &l.h) ||
+	    !__size_limit_check(buf->buf.height, &l.v))
+		return -EINVAL;
+
+	if (swap) {
+		lv = &l.h;
+		lh = &l.v;
+	}
+	__get_size_limit(limits, num_limits, id, &l);
+	if (!__size_limit_check(buf->rect.w, lh) ||
+	    !__align_check(buf->rect.x, lh->align) ||
+	    !__size_limit_check(buf->rect.h, lv) ||
+	    !__align_check(buf->rect.y, lv->align))
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline bool __scale_limit_check(unsigned int src, unsigned int dst,
+				       unsigned int min, unsigned int max)
+{
+	if ((max && (dst << 16) > src * max) ||
+	    (min && (dst << 16) < src * min)) {
+		DRM_DEBUG_DRIVER("Scale from %d to %d exceeds HW limits (ratio min %d.%05d, max %d.%05d)\n",
+			 src, dst,
+			 min >> 16, 100000 * (min & 0xffff) / (1 << 16),
+			 max >> 16, 100000 * (max & 0xffff) / (1 << 16));
+		return false;
+	}
+	return true;
+}
+
+static int exynos_drm_ipp_check_scale_limits(
+				struct drm_exynos_ipp_task_rect *src,
+				struct drm_exynos_ipp_task_rect *dst,
+				const struct drm_exynos_ipp_limit *limits,
+				unsigned int num_limits, bool swap)
+{
+	const struct drm_exynos_ipp_limit_val *lh, *lv;
+	int dw, dh;
+
+	for (; num_limits; limits++, num_limits--)
+		if ((limits->type & DRM_EXYNOS_IPP_LIMIT_TYPE_MASK) ==
+		    DRM_EXYNOS_IPP_LIMIT_TYPE_SCALE)
+			break;
+	if (!num_limits)
+		return 0;
+
+	lh = (!swap) ? &limits->h : &limits->v;
+	lv = (!swap) ? &limits->v : &limits->h;
+	dw = (!swap) ? dst->w : dst->h;
+	dh = (!swap) ? dst->h : dst->w;
+
+	if (!__scale_limit_check(src->w, dw, lh->min, lh->max) ||
+	    !__scale_limit_check(src->h, dh, lv->min, lv->max))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
+{
+	struct exynos_drm_ipp *ipp = task->ipp;
+	const struct exynos_drm_ipp_formats *src_fmt, *dst_fmt;
+	struct exynos_drm_ipp_buffer *src = &task->src, *dst = &task->dst;
+	unsigned int rotation = task->transform.rotation;
+	int ret = 0;
+	bool swap = drm_rotation_90_or_270(rotation);
+	bool rotate = (rotation != DRM_MODE_ROTATE_0);
+	bool scale = false;
+
+	DRM_DEBUG_DRIVER("Checking task %pK\n", task);
+
+	if (src->rect.w == UINT_MAX)
+		src->rect.w = src->buf.width;
+	if (src->rect.h == UINT_MAX)
+		src->rect.h = src->buf.height;
+	if (dst->rect.w == UINT_MAX)
+		dst->rect.w = dst->buf.width;
+	if (dst->rect.h == UINT_MAX)
+		dst->rect.h = dst->buf.height;
+
+	if (src->rect.x + src->rect.w > (src->buf.width) ||
+	    src->rect.y + src->rect.h > (src->buf.height) ||
+	    dst->rect.x + dst->rect.w > (dst->buf.width) ||
+	    dst->rect.y + dst->rect.h > (dst->buf.height)) {
+		DRM_DEBUG_DRIVER("Task %pK: defined area is outside provided buffers\n",
+				 task);
+		return -EINVAL;
+	}
+
+	if ((!swap && (src->rect.w != dst->rect.w ||
+		       src->rect.h != dst->rect.h)) ||
+	    (swap && (src->rect.w != dst->rect.h ||
+		      src->rect.h != dst->rect.w)))
+		scale = true;
+
+	if ((!(ipp->capabilities & DRM_EXYNOS_IPP_CAP_CROP) &&
+	     (src->rect.x || src->rect.y || dst->rect.x || dst->rect.y)) ||
+	    (!(ipp->capabilities & DRM_EXYNOS_IPP_CAP_ROTATE) && rotate) ||
+	    (!(ipp->capabilities & DRM_EXYNOS_IPP_CAP_SCALE) && scale) ||
+	    (!(ipp->capabilities & DRM_EXYNOS_IPP_CAP_CONVERT) &&
+	     src->buf.fourcc != dst->buf.fourcc)) {
+		DRM_DEBUG_DRIVER("Task %pK: hw capabilities exceeded\n", task);
+		return -EINVAL;
+	}
+
+	src_fmt = __ipp_format_get(ipp, src->buf.fourcc, src->buf.modifier,
+				   DRM_EXYNOS_IPP_FORMAT_SOURCE);
+	if (!src_fmt) {
+		DRM_DEBUG_DRIVER("Task %pK: src format not supported\n", task);
+		return -EINVAL;
+	}
+	ret = exynos_drm_ipp_check_size_limits(src, src_fmt->limits,
+					       src_fmt->num_limits,
+					       rotate, false);
+	if (ret)
+		return ret;
+	ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
+						src_fmt->limits,
+						src_fmt->num_limits, swap);
+	if (ret)
+		return ret;
+
+	dst_fmt = __ipp_format_get(ipp, dst->buf.fourcc, dst->buf.modifier,
+				   DRM_EXYNOS_IPP_FORMAT_DESTINATION);
+	if (!dst_fmt) {
+		DRM_DEBUG_DRIVER("Task %pK: dst format not supported\n", task);
+		return -EINVAL;
+	}
+	ret = exynos_drm_ipp_check_size_limits(dst, dst_fmt->limits,
+					       dst_fmt->num_limits,
+					       false, swap);
+	if (ret)
+		return ret;
+	ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
+						dst_fmt->limits,
+						dst_fmt->num_limits, swap);
+	if (ret)
+		return ret;
+
+	DRM_DEBUG_DRIVER("Task %pK: all checks done.\n", task);
+
+	return ret;
+}
+
+static int exynos_drm_ipp_task_setup_buffers(struct exynos_drm_ipp_task *task,
+				     struct drm_file *filp)
+{
+	struct exynos_drm_ipp_buffer *src = &task->src, *dst = &task->dst;
+	int ret = 0;
+
+	DRM_DEBUG_DRIVER("Setting buffer for task %pK\n", task);
+
+	ret = exynos_drm_ipp_task_setup_buffer(src, filp);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Task %pK: src buffer setup failed\n", task);
+		return ret;
+	}
+	ret = exynos_drm_ipp_task_setup_buffer(dst, filp);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Task %pK: dst buffer setup failed\n", task);
+		return ret;
+	}
+
+	DRM_DEBUG_DRIVER("Task %pK: buffers prepared.\n", task);
+
+	return ret;
+}
+
+
+static int exynos_drm_ipp_event_create(struct exynos_drm_ipp_task *task,
+				 struct drm_file *file_priv, uint64_t user_data)
+{
+	struct drm_pending_exynos_ipp_event *e = NULL;
+	int ret;
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (!e)
+		return -ENOMEM;
+
+	e->event.base.type = DRM_EXYNOS_IPP_EVENT;
+	e->event.base.length = sizeof(e->event);
+	e->event.user_data = user_data;
+
+	ret = drm_event_reserve_init(task->dev, file_priv, &e->base,
+				     &e->event.base);
+	if (ret)
+		goto free;
+
+	task->event = e;
+	return 0;
+free:
+	kfree(e);
+	return ret;
+}
+
+static void exynos_drm_ipp_event_send(struct exynos_drm_ipp_task *task)
+{
+	struct timespec64 now;
+
+	ktime_get_ts64(&now);
+	task->event->event.tv_sec = now.tv_sec;
+	task->event->event.tv_usec = now.tv_nsec / NSEC_PER_USEC;
+	task->event->event.sequence = atomic_inc_return(&task->ipp->sequence);
+
+	drm_send_event(task->dev, &task->event->base);
+}
+
+static int exynos_drm_ipp_task_cleanup(struct exynos_drm_ipp_task *task)
+{
+	int ret = task->ret;
+
+	if (ret == 0 && task->event) {
+		exynos_drm_ipp_event_send(task);
+		/* ensure event won't be canceled on task free */
+		task->event = NULL;
+	}
+
+	exynos_drm_ipp_task_free(task->ipp, task);
+	return ret;
+}
+
+static void exynos_drm_ipp_cleanup_work(struct work_struct *work)
+{
+	struct exynos_drm_ipp_task *task = container_of(work,
+				      struct exynos_drm_ipp_task, cleanup_work);
+
+	exynos_drm_ipp_task_cleanup(task);
+}
+
+static void exynos_drm_ipp_next_task(struct exynos_drm_ipp *ipp);
+
+/**
+ * exynos_drm_ipp_task_done - finish given task and set return code
+ * @task: ipp task to finish
+ * @ret: error code or 0 if operation has been performed successfully
+ */
+void exynos_drm_ipp_task_done(struct exynos_drm_ipp_task *task, int ret)
+{
+	struct exynos_drm_ipp *ipp = task->ipp;
+	unsigned long flags;
+
+	DRM_DEBUG_DRIVER("ipp: %d, task %pK done: %d\n", ipp->id, task, ret);
+
+	spin_lock_irqsave(&ipp->lock, flags);
+	if (ipp->task == task)
+		ipp->task = NULL;
+	task->flags |= DRM_EXYNOS_IPP_TASK_DONE;
+	task->ret = ret;
+	spin_unlock_irqrestore(&ipp->lock, flags);
+
+	exynos_drm_ipp_next_task(ipp);
+	wake_up(&ipp->done_wq);
+
+	if (task->flags & DRM_EXYNOS_IPP_TASK_ASYNC) {
+		INIT_WORK(&task->cleanup_work, exynos_drm_ipp_cleanup_work);
+		schedule_work(&task->cleanup_work);
+	}
+}
+
+static void exynos_drm_ipp_next_task(struct exynos_drm_ipp *ipp)
+{
+	struct exynos_drm_ipp_task *task;
+	unsigned long flags;
+	int ret;
+
+	DRM_DEBUG_DRIVER("ipp: %d, try to run new task\n", ipp->id);
+
+	spin_lock_irqsave(&ipp->lock, flags);
+
+	if (ipp->task || list_empty(&ipp->todo_list)) {
+		spin_unlock_irqrestore(&ipp->lock, flags);
+		return;
+	}
+
+	task = list_first_entry(&ipp->todo_list, struct exynos_drm_ipp_task,
+				head);
+	list_del_init(&task->head);
+	ipp->task = task;
+
+	spin_unlock_irqrestore(&ipp->lock, flags);
+
+	DRM_DEBUG_DRIVER("ipp: %d, selected task %pK to run\n", ipp->id, task);
+
+	ret = ipp->funcs->commit(ipp, task);
+	if (ret)
+		exynos_drm_ipp_task_done(task, ret);
+}
+
+static void exynos_drm_ipp_schedule_task(struct exynos_drm_ipp *ipp,
+					 struct exynos_drm_ipp_task *task)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ipp->lock, flags);
+	list_add(&task->head, &ipp->todo_list);
+	spin_unlock_irqrestore(&ipp->lock, flags);
+
+	exynos_drm_ipp_next_task(ipp);
+}
+
+static void exynos_drm_ipp_task_abort(struct exynos_drm_ipp *ipp,
+				      struct exynos_drm_ipp_task *task)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ipp->lock, flags);
+	if (task->flags & DRM_EXYNOS_IPP_TASK_DONE) {
+		/* already completed task */
+		exynos_drm_ipp_task_cleanup(task);
+	} else if (ipp->task != task) {
+		/* task has not been scheduled for execution yet */
+		list_del_init(&task->head);
+		exynos_drm_ipp_task_cleanup(task);
+	} else {
+		/*
+		 * currently processed task, call abort() and perform
+		 * cleanup with async worker
+		 */
+		task->flags |= DRM_EXYNOS_IPP_TASK_ASYNC;
+		spin_unlock_irqrestore(&ipp->lock, flags);
+		if (ipp->funcs->abort)
+			ipp->funcs->abort(ipp, task);
+		return;
+	}
+	spin_unlock_irqrestore(&ipp->lock, flags);
+}
+
+/**
+ * exynos_drm_ipp_commit_ioctl - perform image processing operation
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * Construct a ipp task from the set of properties provided from the user
+ * and try to schedule it to framebuffer processor hardware.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
+int exynos_drm_ipp_commit_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_priv)
+{
+	struct drm_exynos_ioctl_ipp_commit *arg = data;
+	struct exynos_drm_ipp *ipp;
+	struct exynos_drm_ipp_task *task;
+	int ret = 0;
+
+	if ((arg->flags & ~DRM_EXYNOS_IPP_FLAGS) || arg->reserved)
+		return -EINVAL;
+
+	/* can't test and expect an event at the same time */
+	if ((arg->flags & DRM_EXYNOS_IPP_FLAG_TEST_ONLY) &&
+			(arg->flags & DRM_EXYNOS_IPP_FLAG_EVENT))
+		return -EINVAL;
+
+	ipp = __ipp_get(arg->ipp_id);
+	if (!ipp)
+		return -ENOENT;
+
+	task = exynos_drm_ipp_task_alloc(ipp);
+	if (!task)
+		return -ENOMEM;
+
+	ret = exynos_drm_ipp_task_set(task, arg);
+	if (ret)
+		goto free;
+
+	ret = exynos_drm_ipp_task_check(task);
+	if (ret)
+		goto free;
+
+	ret = exynos_drm_ipp_task_setup_buffers(task, file_priv);
+	if (ret || arg->flags & DRM_EXYNOS_IPP_FLAG_TEST_ONLY)
+		goto free;
+
+	if (arg->flags & DRM_EXYNOS_IPP_FLAG_EVENT) {
+		ret = exynos_drm_ipp_event_create(task, file_priv,
+						 arg->user_data);
+		if (ret)
+			goto free;
+	}
+
+	/*
+	 * Queue task for processing on the hardware. task object will be
+	 * then freed after exynos_drm_ipp_task_done()
+	 */
+	if (arg->flags & DRM_EXYNOS_IPP_FLAG_NONBLOCK) {
+		DRM_DEBUG_DRIVER("ipp: %d, nonblocking processing task %pK\n",
+				 ipp->id, task);
+
+		task->flags |= DRM_EXYNOS_IPP_TASK_ASYNC;
+		exynos_drm_ipp_schedule_task(task->ipp, task);
+		ret = 0;
+	} else {
+		DRM_DEBUG_DRIVER("ipp: %d, processing task %pK\n", ipp->id,
+				 task);
+		exynos_drm_ipp_schedule_task(ipp, task);
+		ret = wait_event_interruptible(ipp->done_wq,
+					task->flags & DRM_EXYNOS_IPP_TASK_DONE);
+		if (ret)
+			exynos_drm_ipp_task_abort(ipp, task);
+		else
+			ret = exynos_drm_ipp_task_cleanup(task);
+	}
+	return ret;
+free:
+	exynos_drm_ipp_task_free(ipp, task);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.h b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
new file mode 100644
index 000000000000..0b27d4a9bf94
--- /dev/null
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
@@ -0,0 +1,175 @@
+/*
+ * Copyright (c) 2017 Samsung Electronics Co., Ltd.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef _EXYNOS_DRM_IPP_H_
+#define _EXYNOS_DRM_IPP_H_
+
+#include <drm/drmP.h>
+
+struct exynos_drm_ipp;
+struct exynos_drm_ipp_task;
+
+/**
+ * struct exynos_drm_ipp_funcs - exynos_drm_ipp control functions
+ */
+struct exynos_drm_ipp_funcs {
+	/**
+	 * @commit:
+	 *
+	 * This is the main entry point to start framebuffer processing
+	 * in the hardware. The exynos_drm_ipp_task has been already validated.
+	 * This function must not wait until the device finishes processing.
+	 * When the driver finishes processing, it has to call
+	 * exynos_exynos_drm_ipp_task_done() function.
+	 *
+	 * RETURNS:
+	 *
+	 * 0 on success or negative error codes in case of failure.
+	 */
+	int (*commit)(struct exynos_drm_ipp *ipp,
+		      struct exynos_drm_ipp_task *task);
+
+	/**
+	 * @abort:
+	 *
+	 * Informs the driver that it has to abort the currently running
+	 * task as soon as possible (i.e. as soon as it can stop the device
+	 * safely), even if the task would not have been finished by then.
+	 * After the driver performs the necessary steps, it has to call
+	 * exynos_drm_ipp_task_done() (as if the task ended normally).
+	 * This function does not have to (and will usually not) wait
+	 * until the device enters a state when it can be stopped.
+	 */
+	void (*abort)(struct exynos_drm_ipp *ipp,
+		      struct exynos_drm_ipp_task *task);
+};
+
+/**
+ * struct exynos_drm_ipp - central picture processor module structure
+ */
+struct exynos_drm_ipp {
+	struct drm_device *dev;
+	struct list_head head;
+	unsigned int id;
+
+	const char *name;
+	const struct exynos_drm_ipp_funcs *funcs;
+	unsigned int capabilities;
+	const struct exynos_drm_ipp_formats *formats;
+	unsigned int num_formats;
+	atomic_t sequence;
+
+	spinlock_t lock;
+	struct exynos_drm_ipp_task *task;
+	struct list_head todo_list;
+	wait_queue_head_t done_wq;
+};
+
+struct exynos_drm_ipp_buffer {
+	struct drm_exynos_ipp_task_buffer buf;
+	struct drm_exynos_ipp_task_rect rect;
+
+	struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER];
+	const struct drm_format_info *format;
+	dma_addr_t dma_addr[MAX_FB_BUFFER];
+};
+
+/**
+ * struct exynos_drm_ipp_task - a structure describing transformation that
+ * has to be performed by the picture processor hardware module
+ */
+struct exynos_drm_ipp_task {
+	struct drm_device *dev;
+	struct exynos_drm_ipp *ipp;
+	struct list_head head;
+
+	struct exynos_drm_ipp_buffer src;
+	struct exynos_drm_ipp_buffer dst;
+
+	struct drm_exynos_ipp_task_transform transform;
+	struct drm_exynos_ipp_task_alpha alpha;
+
+	struct work_struct cleanup_work;
+	unsigned int flags;
+	int ret;
+
+	struct drm_pending_exynos_ipp_event *event;
+};
+
+#define DRM_EXYNOS_IPP_TASK_DONE	(1 << 0)
+#define DRM_EXYNOS_IPP_TASK_ASYNC	(1 << 1)
+
+struct exynos_drm_ipp_formats {
+	uint32_t fourcc;
+	uint32_t type;
+	uint64_t modifier;
+	const struct drm_exynos_ipp_limit *limits;
+	unsigned int num_limits;
+};
+
+/* helper macros to set exynos_drm_ipp_formats structure and limits*/
+#define IPP_SRCDST_MFORMAT(f, m, l) \
+	.fourcc = DRM_FORMAT_##f, .modifier = m, .limits = l, \
+	.num_limits = ARRAY_SIZE(l), \
+	.type = (DRM_EXYNOS_IPP_FORMAT_SOURCE | \
+		 DRM_EXYNOS_IPP_FORMAT_DESTINATION)
+
+#define IPP_SRCDST_FORMAT(f, l) IPP_SRCDST_MFORMAT(f, 0, l)
+
+#define IPP_SIZE_LIMIT(l, val...)	\
+	.type = (DRM_EXYNOS_IPP_LIMIT_TYPE_SIZE | \
+		 DRM_EXYNOS_IPP_LIMIT_SIZE_##l), val
+
+#define IPP_SCALE_LIMIT(val...)		\
+	.type = (DRM_EXYNOS_IPP_LIMIT_TYPE_SCALE), val
+
+int exynos_drm_ipp_register(struct drm_device *dev, struct exynos_drm_ipp *ipp,
+		const struct exynos_drm_ipp_funcs *funcs, unsigned int caps,
+		const struct exynos_drm_ipp_formats *formats,
+		unsigned int num_formats, const char *name);
+void exynos_drm_ipp_unregister(struct drm_device *dev,
+			       struct exynos_drm_ipp *ipp);
+
+void exynos_drm_ipp_task_done(struct exynos_drm_ipp_task *task, int ret);
+
+#ifdef CONFIG_DRM_EXYNOS_IPP
+int exynos_drm_ipp_get_res_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
+int exynos_drm_ipp_get_caps_ioctl(struct drm_device *dev, void *data,
+				  struct drm_file *file_priv);
+int exynos_drm_ipp_get_limits_ioctl(struct drm_device *dev, void *data,
+				    struct drm_file *file_priv);
+int exynos_drm_ipp_commit_ioctl(struct drm_device *dev,
+				void *data, struct drm_file *file_priv);
+#else
+static inline int exynos_drm_ipp_get_res_ioctl(struct drm_device *dev,
+	 void *data, struct drm_file *file_priv)
+{
+	struct drm_exynos_ioctl_ipp_get_res *resp = data;
+
+	resp->count_ipps = 0;
+	return 0;
+}
+static inline int exynos_drm_ipp_get_caps_ioctl(struct drm_device *dev,
+	 void *data, struct drm_file *file_priv)
+{
+	return -ENODEV;
+}
+static inline int exynos_drm_ipp_get_limits_ioctl(struct drm_device *dev,
+	 void *data, struct drm_file *file_priv)
+{
+	return -ENODEV;
+}
+static inline int exynos_drm_ipp_commit_ioctl(struct drm_device *dev,
+	 void *data, struct drm_file *file_priv)
+{
+	return -ENODEV;
+}
+#endif
+#endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index d2a90dae5c71..38a2a7f1204b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -289,13 +289,12 @@ static const struct drm_plane_helper_funcs plane_helper_funcs = {
 };
 
 static void exynos_plane_attach_zpos_property(struct drm_plane *plane,
-					      bool immutable)
+					      int zpos, bool immutable)
 {
-	/* FIXME */
 	if (immutable)
-		drm_plane_create_zpos_immutable_property(plane, 0);
+		drm_plane_create_zpos_immutable_property(plane, zpos);
 	else
-		drm_plane_create_zpos_property(plane, 0, 0, MAX_PLANE - 1);
+		drm_plane_create_zpos_property(plane, zpos, 0, MAX_PLANE - 1);
 }
 
 int exynos_plane_init(struct drm_device *dev,
@@ -320,7 +319,7 @@ int exynos_plane_init(struct drm_device *dev,
 	exynos_plane->index = index;
 	exynos_plane->config = config;
 
-	exynos_plane_attach_zpos_property(&exynos_plane->base,
+	exynos_plane_attach_zpos_property(&exynos_plane->base, config->zpos,
 			   !(config->capabilities & EXYNOS_DRM_PLANE_CAP_ZPOS));
 
 	return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 79282a820ecc..1a76dd3d52e1 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/component.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -22,29 +23,18 @@
 #include <drm/exynos_drm.h>
 #include "regs-rotator.h"
 #include "exynos_drm_drv.h"
+#include "exynos_drm_iommu.h"
 #include "exynos_drm_ipp.h"
 
 /*
  * Rotator supports image crop/rotator and input/output DMA operations.
  * input DMA reads image data from the memory.
  * output DMA writes image data to memory.
- *
- * M2M operation : supports crop/scale/rotation/csc so on.
- * Memory ----> Rotator H/W ----> Memory.
  */
 
-/*
- * TODO
- * 1. check suspend/resume api if needed.
- * 2. need to check use case platform_device_id.
- * 3. check src/dst size with, height.
- * 4. need to add supported list in prop_list.
- */
+#define ROTATOR_AUTOSUSPEND_DELAY	2000
 
-#define get_rot_context(dev)	platform_get_drvdata(to_platform_device(dev))
-#define get_ctx_from_ippdrv(ippdrv)	container_of(ippdrv,\
-					struct rot_context, ippdrv);
-#define rot_read(offset)		readl(rot->regs + (offset))
+#define rot_read(offset)	readl(rot->regs + (offset))
 #define rot_write(cfg, offset)	writel(cfg, rot->regs + (offset))
 
 enum rot_irq_status {
@@ -52,54 +42,28 @@ enum rot_irq_status {
 	ROT_IRQ_STATUS_ILLEGAL	= 9,
 };
 
-/*
- * A structure of limitation.
- *
- * @min_w: minimum width.
- * @min_h: minimum height.
- * @max_w: maximum width.
- * @max_h: maximum height.
- * @align: align size.
- */
-struct rot_limit {
-	u32	min_w;
-	u32	min_h;
-	u32	max_w;
-	u32	max_h;
-	u32	align;
-};
-
-/*
- * A structure of limitation table.
- *
- * @ycbcr420_2p: case of YUV.
- * @rgb888: case of RGB.
- */
-struct rot_limit_table {
-	struct rot_limit	ycbcr420_2p;
-	struct rot_limit	rgb888;
+struct rot_variant {
+	const struct exynos_drm_ipp_formats *formats;
+	unsigned int	num_formats;
 };
 
 /*
  * A structure of rotator context.
  * @ippdrv: prepare initialization using ippdrv.
- * @regs_res: register resources.
  * @regs: memory mapped io registers.
  * @clock: rotator gate clock.
  * @limit_tbl: limitation of rotator.
  * @irq: irq number.
- * @cur_buf_id: current operation buffer id.
- * @suspended: suspended state.
  */
 struct rot_context {
-	struct exynos_drm_ippdrv	ippdrv;
-	struct resource	*regs_res;
+	struct exynos_drm_ipp ipp;
+	struct drm_device *drm_dev;
+	struct device	*dev;
 	void __iomem	*regs;
 	struct clk	*clock;
-	struct rot_limit_table	*limit_tbl;
-	int	irq;
-	int	cur_buf_id[EXYNOS_DRM_OPS_MAX];
-	bool	suspended;
+	const struct exynos_drm_ipp_formats *formats;
+	unsigned int	num_formats;
+	struct exynos_drm_ipp_task	*task;
 };
 
 static void rotator_reg_set_irq(struct rot_context *rot, bool enable)
@@ -114,15 +78,6 @@ static void rotator_reg_set_irq(struct rot_context *rot, bool enable)
 	rot_write(val, ROT_CONFIG);
 }
 
-static u32 rotator_reg_get_fmt(struct rot_context *rot)
-{
-	u32 val = rot_read(ROT_CONTROL);
-
-	val &= ROT_CONTROL_FMT_MASK;
-
-	return val;
-}
-
 static enum rot_irq_status rotator_reg_get_irq_status(struct rot_context *rot)
 {
 	u32 val = rot_read(ROT_STATUS);
@@ -138,9 +93,6 @@ static enum rot_irq_status rotator_reg_get_irq_status(struct rot_context *rot)
 static irqreturn_t rotator_irq_handler(int irq, void *arg)
 {
 	struct rot_context *rot = arg;
-	struct exynos_drm_ippdrv *ippdrv = &rot->ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->c_node;
-	struct drm_exynos_ipp_event_work *event_work = c_node->event_work;
 	enum rot_irq_status irq_status;
 	u32 val;
 
@@ -152,56 +104,21 @@ static irqreturn_t rotator_irq_handler(int irq, void *arg)
 	val |= ROT_STATUS_IRQ_PENDING((u32)irq_status);
 	rot_write(val, ROT_STATUS);
 
-	if (irq_status == ROT_IRQ_STATUS_COMPLETE) {
-		event_work->ippdrv = ippdrv;
-		event_work->buf_id[EXYNOS_DRM_OPS_DST] =
-			rot->cur_buf_id[EXYNOS_DRM_OPS_DST];
-		queue_work(ippdrv->event_workq, &event_work->work);
-	} else {
-		DRM_ERROR("the SFR is set illegally\n");
+	if (rot->task) {
+		struct exynos_drm_ipp_task *task = rot->task;
+
+		rot->task = NULL;
+		pm_runtime_mark_last_busy(rot->dev);
+		pm_runtime_put_autosuspend(rot->dev);
+		exynos_drm_ipp_task_done(task,
+			irq_status == ROT_IRQ_STATUS_COMPLETE ? 0 : -EINVAL);
 	}
 
 	return IRQ_HANDLED;
 }
 
-static void rotator_align_size(struct rot_context *rot, u32 fmt, u32 *hsize,
-		u32 *vsize)
+static void rotator_src_set_fmt(struct rot_context *rot, u32 fmt)
 {
-	struct rot_limit_table *limit_tbl = rot->limit_tbl;
-	struct rot_limit *limit;
-	u32 mask, val;
-
-	/* Get size limit */
-	if (fmt == ROT_CONTROL_FMT_RGB888)
-		limit = &limit_tbl->rgb888;
-	else
-		limit = &limit_tbl->ycbcr420_2p;
-
-	/* Get mask for rounding to nearest aligned val */
-	mask = ~((1 << limit->align) - 1);
-
-	/* Set aligned width */
-	val = ROT_ALIGN(*hsize, limit->align, mask);
-	if (val < limit->min_w)
-		*hsize = ROT_MIN(limit->min_w, mask);
-	else if (val > limit->max_w)
-		*hsize = ROT_MAX(limit->max_w, mask);
-	else
-		*hsize = val;
-
-	/* Set aligned height */
-	val = ROT_ALIGN(*vsize, limit->align, mask);
-	if (val < limit->min_h)
-		*vsize = ROT_MIN(limit->min_h, mask);
-	else if (val > limit->max_h)
-		*vsize = ROT_MAX(limit->max_h, mask);
-	else
-		*vsize = val;
-}
-
-static int rotator_src_set_fmt(struct device *dev, u32 fmt)
-{
-	struct rot_context *rot = dev_get_drvdata(dev);
 	u32 val;
 
 	val = rot_read(ROT_CONTROL);
@@ -214,515 +131,176 @@ static int rotator_src_set_fmt(struct device *dev, u32 fmt)
 	case DRM_FORMAT_XRGB8888:
 		val |= ROT_CONTROL_FMT_RGB888;
 		break;
-	default:
-		DRM_ERROR("invalid image format\n");
-		return -EINVAL;
 	}
 
 	rot_write(val, ROT_CONTROL);
-
-	return 0;
 }
 
-static inline bool rotator_check_reg_fmt(u32 fmt)
+static void rotator_src_set_buf(struct rot_context *rot,
+				struct exynos_drm_ipp_buffer *buf)
 {
-	if ((fmt == ROT_CONTROL_FMT_YCBCR420_2P) ||
-	    (fmt == ROT_CONTROL_FMT_RGB888))
-		return true;
-
-	return false;
-}
-
-static int rotator_src_set_size(struct device *dev, int swap,
-		struct drm_exynos_pos *pos,
-		struct drm_exynos_sz *sz)
-{
-	struct rot_context *rot = dev_get_drvdata(dev);
-	u32 fmt, hsize, vsize;
 	u32 val;
 
-	/* Get format */
-	fmt = rotator_reg_get_fmt(rot);
-	if (!rotator_check_reg_fmt(fmt)) {
-		DRM_ERROR("invalid format.\n");
-		return -EINVAL;
-	}
-
-	/* Align buffer size */
-	hsize = sz->hsize;
-	vsize = sz->vsize;
-	rotator_align_size(rot, fmt, &hsize, &vsize);
-
 	/* Set buffer size configuration */
-	val = ROT_SET_BUF_SIZE_H(vsize) | ROT_SET_BUF_SIZE_W(hsize);
+	val = ROT_SET_BUF_SIZE_H(buf->buf.height) |
+	      ROT_SET_BUF_SIZE_W(buf->buf.pitch[0] / buf->format->cpp[0]);
 	rot_write(val, ROT_SRC_BUF_SIZE);
 
 	/* Set crop image position configuration */
-	val = ROT_CROP_POS_Y(pos->y) | ROT_CROP_POS_X(pos->x);
+	val = ROT_CROP_POS_Y(buf->rect.y) | ROT_CROP_POS_X(buf->rect.x);
 	rot_write(val, ROT_SRC_CROP_POS);
-	val = ROT_SRC_CROP_SIZE_H(pos->h) | ROT_SRC_CROP_SIZE_W(pos->w);
+	val = ROT_SRC_CROP_SIZE_H(buf->rect.h) |
+	      ROT_SRC_CROP_SIZE_W(buf->rect.w);
 	rot_write(val, ROT_SRC_CROP_SIZE);
 
-	return 0;
+	/* Set buffer DMA address */
+	rot_write(buf->dma_addr[0], ROT_SRC_BUF_ADDR(0));
+	rot_write(buf->dma_addr[1], ROT_SRC_BUF_ADDR(1));
 }
 
-static int rotator_src_set_addr(struct device *dev,
-		struct drm_exynos_ipp_buf_info *buf_info,
-		u32 buf_id, enum drm_exynos_ipp_buf_type buf_type)
+static void rotator_dst_set_transf(struct rot_context *rot,
+				   unsigned int rotation)
 {
-	struct rot_context *rot = dev_get_drvdata(dev);
-	dma_addr_t addr[EXYNOS_DRM_PLANAR_MAX];
-	u32 val, fmt, hsize, vsize;
-	int i;
-
-	/* Set current buf_id */
-	rot->cur_buf_id[EXYNOS_DRM_OPS_SRC] = buf_id;
-
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		/* Set address configuration */
-		for_each_ipp_planar(i)
-			addr[i] = buf_info->base[i];
-
-		/* Get format */
-		fmt = rotator_reg_get_fmt(rot);
-		if (!rotator_check_reg_fmt(fmt)) {
-			DRM_ERROR("invalid format.\n");
-			return -EINVAL;
-		}
-
-		/* Re-set cb planar for NV12 format */
-		if ((fmt == ROT_CONTROL_FMT_YCBCR420_2P) &&
-		    !addr[EXYNOS_DRM_PLANAR_CB]) {
-
-			val = rot_read(ROT_SRC_BUF_SIZE);
-			hsize = ROT_GET_BUF_SIZE_W(val);
-			vsize = ROT_GET_BUF_SIZE_H(val);
-
-			/* Set cb planar */
-			addr[EXYNOS_DRM_PLANAR_CB] =
-				addr[EXYNOS_DRM_PLANAR_Y] + hsize * vsize;
-		}
-
-		for_each_ipp_planar(i)
-			rot_write(addr[i], ROT_SRC_BUF_ADDR(i));
-		break;
-	case IPP_BUF_DEQUEUE:
-		for_each_ipp_planar(i)
-			rot_write(0x0, ROT_SRC_BUF_ADDR(i));
-		break;
-	default:
-		/* Nothing to do */
-		break;
-	}
-
-	return 0;
-}
-
-static int rotator_dst_set_transf(struct device *dev,
-		enum drm_exynos_degree degree,
-		enum drm_exynos_flip flip, bool *swap)
-{
-	struct rot_context *rot = dev_get_drvdata(dev);
 	u32 val;
 
 	/* Set transform configuration */
 	val = rot_read(ROT_CONTROL);
 	val &= ~ROT_CONTROL_FLIP_MASK;
 
-	switch (flip) {
-	case EXYNOS_DRM_FLIP_VERTICAL:
-		val |= ROT_CONTROL_FLIP_VERTICAL;
-		break;
-	case EXYNOS_DRM_FLIP_HORIZONTAL:
+	if (rotation & DRM_MODE_REFLECT_X)
 		val |= ROT_CONTROL_FLIP_HORIZONTAL;
-		break;
-	default:
-		/* Flip None */
-		break;
-	}
+	if (rotation & DRM_MODE_REFLECT_Y)
+		val |= ROT_CONTROL_FLIP_VERTICAL;
 
 	val &= ~ROT_CONTROL_ROT_MASK;
 
-	switch (degree) {
-	case EXYNOS_DRM_DEGREE_90:
+	if (rotation & DRM_MODE_ROTATE_90)
 		val |= ROT_CONTROL_ROT_90;
-		break;
-	case EXYNOS_DRM_DEGREE_180:
+	else if (rotation & DRM_MODE_ROTATE_180)
 		val |= ROT_CONTROL_ROT_180;
-		break;
-	case EXYNOS_DRM_DEGREE_270:
+	else if (rotation & DRM_MODE_ROTATE_270)
 		val |= ROT_CONTROL_ROT_270;
-		break;
-	default:
-		/* Rotation 0 Degree */
-		break;
-	}
 
 	rot_write(val, ROT_CONTROL);
-
-	/* Check degree for setting buffer size swap */
-	if ((degree == EXYNOS_DRM_DEGREE_90) ||
-	    (degree == EXYNOS_DRM_DEGREE_270))
-		*swap = true;
-	else
-		*swap = false;
-
-	return 0;
 }
 
-static int rotator_dst_set_size(struct device *dev, int swap,
-		struct drm_exynos_pos *pos,
-		struct drm_exynos_sz *sz)
+static void rotator_dst_set_buf(struct rot_context *rot,
+				struct exynos_drm_ipp_buffer *buf)
 {
-	struct rot_context *rot = dev_get_drvdata(dev);
-	u32 val, fmt, hsize, vsize;
-
-	/* Get format */
-	fmt = rotator_reg_get_fmt(rot);
-	if (!rotator_check_reg_fmt(fmt)) {
-		DRM_ERROR("invalid format.\n");
-		return -EINVAL;
-	}
-
-	/* Align buffer size */
-	hsize = sz->hsize;
-	vsize = sz->vsize;
-	rotator_align_size(rot, fmt, &hsize, &vsize);
+	u32 val;
 
 	/* Set buffer size configuration */
-	val = ROT_SET_BUF_SIZE_H(vsize) | ROT_SET_BUF_SIZE_W(hsize);
+	val = ROT_SET_BUF_SIZE_H(buf->buf.height) |
+	      ROT_SET_BUF_SIZE_W(buf->buf.pitch[0] / buf->format->cpp[0]);
 	rot_write(val, ROT_DST_BUF_SIZE);
 
 	/* Set crop image position configuration */
-	val = ROT_CROP_POS_Y(pos->y) | ROT_CROP_POS_X(pos->x);
+	val = ROT_CROP_POS_Y(buf->rect.y) | ROT_CROP_POS_X(buf->rect.x);
 	rot_write(val, ROT_DST_CROP_POS);
 
-	return 0;
+	/* Set buffer DMA address */
+	rot_write(buf->dma_addr[0], ROT_DST_BUF_ADDR(0));
+	rot_write(buf->dma_addr[1], ROT_DST_BUF_ADDR(1));
 }
 
-static int rotator_dst_set_addr(struct device *dev,
-		struct drm_exynos_ipp_buf_info *buf_info,
-		u32 buf_id, enum drm_exynos_ipp_buf_type buf_type)
+static void rotator_start(struct rot_context *rot)
 {
-	struct rot_context *rot = dev_get_drvdata(dev);
-	dma_addr_t addr[EXYNOS_DRM_PLANAR_MAX];
-	u32 val, fmt, hsize, vsize;
-	int i;
-
-	/* Set current buf_id */
-	rot->cur_buf_id[EXYNOS_DRM_OPS_DST] = buf_id;
-
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		/* Set address configuration */
-		for_each_ipp_planar(i)
-			addr[i] = buf_info->base[i];
-
-		/* Get format */
-		fmt = rotator_reg_get_fmt(rot);
-		if (!rotator_check_reg_fmt(fmt)) {
-			DRM_ERROR("invalid format.\n");
-			return -EINVAL;
-		}
-
-		/* Re-set cb planar for NV12 format */
-		if ((fmt == ROT_CONTROL_FMT_YCBCR420_2P) &&
-		    !addr[EXYNOS_DRM_PLANAR_CB]) {
-			/* Get buf size */
-			val = rot_read(ROT_DST_BUF_SIZE);
-
-			hsize = ROT_GET_BUF_SIZE_W(val);
-			vsize = ROT_GET_BUF_SIZE_H(val);
-
-			/* Set cb planar */
-			addr[EXYNOS_DRM_PLANAR_CB] =
-				addr[EXYNOS_DRM_PLANAR_Y] + hsize * vsize;
-		}
-
-		for_each_ipp_planar(i)
-			rot_write(addr[i], ROT_DST_BUF_ADDR(i));
-		break;
-	case IPP_BUF_DEQUEUE:
-		for_each_ipp_planar(i)
-			rot_write(0x0, ROT_DST_BUF_ADDR(i));
-		break;
-	default:
-		/* Nothing to do */
-		break;
-	}
+	u32 val;
 
-	return 0;
+	/* Set interrupt enable */
+	rotator_reg_set_irq(rot, true);
+
+	val = rot_read(ROT_CONTROL);
+	val |= ROT_CONTROL_START;
+	rot_write(val, ROT_CONTROL);
 }
 
-static struct exynos_drm_ipp_ops rot_src_ops = {
-	.set_fmt	=	rotator_src_set_fmt,
-	.set_size	=	rotator_src_set_size,
-	.set_addr	=	rotator_src_set_addr,
-};
+static int rotator_commit(struct exynos_drm_ipp *ipp,
+			  struct exynos_drm_ipp_task *task)
+{
+	struct rot_context *rot =
+			container_of(ipp, struct rot_context, ipp);
 
-static struct exynos_drm_ipp_ops rot_dst_ops = {
-	.set_transf	=	rotator_dst_set_transf,
-	.set_size	=	rotator_dst_set_size,
-	.set_addr	=	rotator_dst_set_addr,
-};
+	pm_runtime_get_sync(rot->dev);
+	rot->task = task;
 
-static int rotator_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
-{
-	struct drm_exynos_ipp_prop_list *prop_list = &ippdrv->prop_list;
-
-	prop_list->version = 1;
-	prop_list->flip = (1 << EXYNOS_DRM_FLIP_VERTICAL) |
-				(1 << EXYNOS_DRM_FLIP_HORIZONTAL);
-	prop_list->degree = (1 << EXYNOS_DRM_DEGREE_0) |
-				(1 << EXYNOS_DRM_DEGREE_90) |
-				(1 << EXYNOS_DRM_DEGREE_180) |
-				(1 << EXYNOS_DRM_DEGREE_270);
-	prop_list->csc = 0;
-	prop_list->crop = 0;
-	prop_list->scale = 0;
+	rotator_src_set_fmt(rot, task->src.buf.fourcc);
+	rotator_src_set_buf(rot, &task->src);
+	rotator_dst_set_transf(rot, task->transform.rotation);
+	rotator_dst_set_buf(rot, &task->dst);
+	rotator_start(rot);
 
 	return 0;
 }
 
-static inline bool rotator_check_drm_fmt(u32 fmt)
-{
-	switch (fmt) {
-	case DRM_FORMAT_XRGB8888:
-	case DRM_FORMAT_NV12:
-		return true;
-	default:
-		DRM_DEBUG_KMS("not support format\n");
-		return false;
-	}
-}
-
-static inline bool rotator_check_drm_flip(enum drm_exynos_flip flip)
-{
-	switch (flip) {
-	case EXYNOS_DRM_FLIP_NONE:
-	case EXYNOS_DRM_FLIP_VERTICAL:
-	case EXYNOS_DRM_FLIP_HORIZONTAL:
-	case EXYNOS_DRM_FLIP_BOTH:
-		return true;
-	default:
-		DRM_DEBUG_KMS("invalid flip\n");
-		return false;
-	}
-}
+static const struct exynos_drm_ipp_funcs ipp_funcs = {
+	.commit = rotator_commit,
+};
 
-static int rotator_ippdrv_check_property(struct device *dev,
-		struct drm_exynos_ipp_property *property)
+static int rotator_bind(struct device *dev, struct device *master, void *data)
 {
-	struct drm_exynos_ipp_config *src_config =
-					&property->config[EXYNOS_DRM_OPS_SRC];
-	struct drm_exynos_ipp_config *dst_config =
-					&property->config[EXYNOS_DRM_OPS_DST];
-	struct drm_exynos_pos *src_pos = &src_config->pos;
-	struct drm_exynos_pos *dst_pos = &dst_config->pos;
-	struct drm_exynos_sz *src_sz = &src_config->sz;
-	struct drm_exynos_sz *dst_sz = &dst_config->sz;
-	bool swap = false;
-
-	/* Check format configuration */
-	if (src_config->fmt != dst_config->fmt) {
-		DRM_DEBUG_KMS("not support csc feature\n");
-		return -EINVAL;
-	}
-
-	if (!rotator_check_drm_fmt(dst_config->fmt)) {
-		DRM_DEBUG_KMS("invalid format\n");
-		return -EINVAL;
-	}
-
-	/* Check transform configuration */
-	if (src_config->degree != EXYNOS_DRM_DEGREE_0) {
-		DRM_DEBUG_KMS("not support source-side rotation\n");
-		return -EINVAL;
-	}
-
-	switch (dst_config->degree) {
-	case EXYNOS_DRM_DEGREE_90:
-	case EXYNOS_DRM_DEGREE_270:
-		swap = true;
-	case EXYNOS_DRM_DEGREE_0:
-	case EXYNOS_DRM_DEGREE_180:
-		/* No problem */
-		break;
-	default:
-		DRM_DEBUG_KMS("invalid degree\n");
-		return -EINVAL;
-	}
-
-	if (src_config->flip != EXYNOS_DRM_FLIP_NONE) {
-		DRM_DEBUG_KMS("not support source-side flip\n");
-		return -EINVAL;
-	}
+	struct rot_context *rot = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_ipp *ipp = &rot->ipp;
 
-	if (!rotator_check_drm_flip(dst_config->flip)) {
-		DRM_DEBUG_KMS("invalid flip\n");
-		return -EINVAL;
-	}
+	rot->drm_dev = drm_dev;
+	drm_iommu_attach_device(drm_dev, dev);
 
-	/* Check size configuration */
-	if ((src_pos->x + src_pos->w > src_sz->hsize) ||
-		(src_pos->y + src_pos->h > src_sz->vsize)) {
-		DRM_DEBUG_KMS("out of source buffer bound\n");
-		return -EINVAL;
-	}
+	exynos_drm_ipp_register(drm_dev, ipp, &ipp_funcs,
+			   DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE,
+			   rot->formats, rot->num_formats, "rotator");
 
-	if (swap) {
-		if ((dst_pos->x + dst_pos->h > dst_sz->vsize) ||
-			(dst_pos->y + dst_pos->w > dst_sz->hsize)) {
-			DRM_DEBUG_KMS("out of destination buffer bound\n");
-			return -EINVAL;
-		}
-
-		if ((src_pos->w != dst_pos->h) || (src_pos->h != dst_pos->w)) {
-			DRM_DEBUG_KMS("not support scale feature\n");
-			return -EINVAL;
-		}
-	} else {
-		if ((dst_pos->x + dst_pos->w > dst_sz->hsize) ||
-			(dst_pos->y + dst_pos->h > dst_sz->vsize)) {
-			DRM_DEBUG_KMS("out of destination buffer bound\n");
-			return -EINVAL;
-		}
-
-		if ((src_pos->w != dst_pos->w) || (src_pos->h != dst_pos->h)) {
-			DRM_DEBUG_KMS("not support scale feature\n");
-			return -EINVAL;
-		}
-	}
+	dev_info(dev, "The exynos rotator has been probed successfully\n");
 
 	return 0;
 }
 
-static int rotator_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
+static void rotator_unbind(struct device *dev, struct device *master,
+			void *data)
 {
 	struct rot_context *rot = dev_get_drvdata(dev);
-	u32 val;
-
-	if (rot->suspended) {
-		DRM_ERROR("suspended state\n");
-		return -EPERM;
-	}
-
-	if (cmd != IPP_CMD_M2M) {
-		DRM_ERROR("not support cmd: %d\n", cmd);
-		return -EINVAL;
-	}
-
-	/* Set interrupt enable */
-	rotator_reg_set_irq(rot, true);
-
-	val = rot_read(ROT_CONTROL);
-	val |= ROT_CONTROL_START;
-
-	rot_write(val, ROT_CONTROL);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_ipp *ipp = &rot->ipp;
 
-	return 0;
+	exynos_drm_ipp_unregister(drm_dev, ipp);
+	drm_iommu_detach_device(rot->drm_dev, rot->dev);
 }
 
-static struct rot_limit_table rot_limit_tbl_4210 = {
-	.ycbcr420_2p = {
-		.min_w = 32,
-		.min_h = 32,
-		.max_w = SZ_64K,
-		.max_h = SZ_64K,
-		.align = 3,
-	},
-	.rgb888 = {
-		.min_w = 8,
-		.min_h = 8,
-		.max_w = SZ_16K,
-		.max_h = SZ_16K,
-		.align = 2,
-	},
-};
-
-static struct rot_limit_table rot_limit_tbl_4x12 = {
-	.ycbcr420_2p = {
-		.min_w = 32,
-		.min_h = 32,
-		.max_w = SZ_32K,
-		.max_h = SZ_32K,
-		.align = 3,
-	},
-	.rgb888 = {
-		.min_w = 8,
-		.min_h = 8,
-		.max_w = SZ_8K,
-		.max_h = SZ_8K,
-		.align = 2,
-	},
+static const struct component_ops rotator_component_ops = {
+	.bind	= rotator_bind,
+	.unbind = rotator_unbind,
 };
 
-static struct rot_limit_table rot_limit_tbl_5250 = {
-	.ycbcr420_2p = {
-		.min_w = 32,
-		.min_h = 32,
-		.max_w = SZ_32K,
-		.max_h = SZ_32K,
-		.align = 3,
-	},
-	.rgb888 = {
-		.min_w = 8,
-		.min_h = 8,
-		.max_w = SZ_8K,
-		.max_h = SZ_8K,
-		.align = 1,
-	},
-};
-
-static const struct of_device_id exynos_rotator_match[] = {
-	{
-		.compatible = "samsung,exynos4210-rotator",
-		.data = &rot_limit_tbl_4210,
-	},
-	{
-		.compatible = "samsung,exynos4212-rotator",
-		.data = &rot_limit_tbl_4x12,
-	},
-	{
-		.compatible = "samsung,exynos5250-rotator",
-		.data = &rot_limit_tbl_5250,
-	},
-	{},
-};
-MODULE_DEVICE_TABLE(of, exynos_rotator_match);
-
 static int rotator_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct resource	*regs_res;
 	struct rot_context *rot;
-	struct exynos_drm_ippdrv *ippdrv;
+	const struct rot_variant *variant;
+	int irq;
 	int ret;
 
-	if (!dev->of_node) {
-		dev_err(dev, "cannot find of_node.\n");
-		return -ENODEV;
-	}
-
 	rot = devm_kzalloc(dev, sizeof(*rot), GFP_KERNEL);
 	if (!rot)
 		return -ENOMEM;
 
-	rot->limit_tbl = (struct rot_limit_table *)
-				of_device_get_match_data(dev);
-	rot->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rot->regs = devm_ioremap_resource(dev, rot->regs_res);
+	variant = of_device_get_match_data(dev);
+	rot->formats = variant->formats;
+	rot->num_formats = variant->num_formats;
+	rot->dev = dev;
+	regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rot->regs = devm_ioremap_resource(dev, regs_res);
 	if (IS_ERR(rot->regs))
 		return PTR_ERR(rot->regs);
 
-	rot->irq = platform_get_irq(pdev, 0);
-	if (rot->irq < 0) {
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
 		dev_err(dev, "failed to get irq\n");
-		return rot->irq;
+		return irq;
 	}
 
-	ret = devm_request_threaded_irq(dev, rot->irq, NULL,
-			rotator_irq_handler, IRQF_ONESHOT, "drm_rotator", rot);
+	ret = devm_request_irq(dev, irq, rotator_irq_handler, 0, dev_name(dev),
+			       rot);
 	if (ret < 0) {
 		dev_err(dev, "failed to request irq\n");
 		return ret;
@@ -734,35 +312,19 @@ static int rotator_probe(struct platform_device *pdev)
 		return PTR_ERR(rot->clock);
 	}
 
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, ROTATOR_AUTOSUSPEND_DELAY);
 	pm_runtime_enable(dev);
-
-	ippdrv = &rot->ippdrv;
-	ippdrv->dev = dev;
-	ippdrv->ops[EXYNOS_DRM_OPS_SRC] = &rot_src_ops;
-	ippdrv->ops[EXYNOS_DRM_OPS_DST] = &rot_dst_ops;
-	ippdrv->check_property = rotator_ippdrv_check_property;
-	ippdrv->start = rotator_ippdrv_start;
-	ret = rotator_init_prop_list(ippdrv);
-	if (ret < 0) {
-		dev_err(dev, "failed to init property list.\n");
-		goto err_ippdrv_register;
-	}
-
-	DRM_DEBUG_KMS("ippdrv[%pK]\n", ippdrv);
-
 	platform_set_drvdata(pdev, rot);
 
-	ret = exynos_drm_ippdrv_register(ippdrv);
-	if (ret < 0) {
-		dev_err(dev, "failed to register drm rotator device\n");
-		goto err_ippdrv_register;
-	}
-
-	dev_info(dev, "The exynos rotator is probed successfully\n");
+	ret = component_add(dev, &rotator_component_ops);
+	if (ret)
+		goto err_component;
 
 	return 0;
 
-err_ippdrv_register:
+err_component:
+	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
 	return ret;
 }
@@ -770,45 +332,101 @@ err_ippdrv_register:
 static int rotator_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct rot_context *rot = dev_get_drvdata(dev);
-	struct exynos_drm_ippdrv *ippdrv = &rot->ippdrv;
-
-	exynos_drm_ippdrv_unregister(ippdrv);
 
+	component_del(dev, &rotator_component_ops);
+	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
 
 	return 0;
 }
 
 #ifdef CONFIG_PM
-static int rotator_clk_crtl(struct rot_context *rot, bool enable)
-{
-	if (enable) {
-		clk_prepare_enable(rot->clock);
-		rot->suspended = false;
-	} else {
-		clk_disable_unprepare(rot->clock);
-		rot->suspended = true;
-	}
-
-	return 0;
-}
-
 static int rotator_runtime_suspend(struct device *dev)
 {
 	struct rot_context *rot = dev_get_drvdata(dev);
 
-	return  rotator_clk_crtl(rot, false);
+	clk_disable_unprepare(rot->clock);
+	return 0;
 }
 
 static int rotator_runtime_resume(struct device *dev)
 {
 	struct rot_context *rot = dev_get_drvdata(dev);
 
-	return  rotator_clk_crtl(rot, true);
+	return clk_prepare_enable(rot->clock);
 }
 #endif
 
+static const struct drm_exynos_ipp_limit rotator_4210_rbg888_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 8, SZ_16K }, .v = { 8, SZ_16K }) },
+	{ IPP_SIZE_LIMIT(AREA, .h.align = 4, .v.align = 4) },
+};
+
+static const struct drm_exynos_ipp_limit rotator_4412_rbg888_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 8, SZ_8K }, .v = { 8, SZ_8K }) },
+	{ IPP_SIZE_LIMIT(AREA, .h.align = 4, .v.align = 4) },
+};
+
+static const struct drm_exynos_ipp_limit rotator_5250_rbg888_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 8, SZ_8K }, .v = { 8, SZ_8K }) },
+	{ IPP_SIZE_LIMIT(AREA, .h.align = 2, .v.align = 2) },
+};
+
+static const struct drm_exynos_ipp_limit rotator_4210_yuv_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, SZ_64K }, .v = { 32, SZ_64K }) },
+	{ IPP_SIZE_LIMIT(AREA, .h.align = 8, .v.align = 8) },
+};
+
+static const struct drm_exynos_ipp_limit rotator_4412_yuv_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, SZ_32K }, .v = { 32, SZ_32K }) },
+	{ IPP_SIZE_LIMIT(AREA, .h.align = 8, .v.align = 8) },
+};
+
+static const struct exynos_drm_ipp_formats rotator_4210_formats[] = {
+	{ IPP_SRCDST_FORMAT(XRGB8888, rotator_4210_rbg888_limits) },
+	{ IPP_SRCDST_FORMAT(NV12, rotator_4210_yuv_limits) },
+};
+
+static const struct exynos_drm_ipp_formats rotator_4412_formats[] = {
+	{ IPP_SRCDST_FORMAT(XRGB8888, rotator_4412_rbg888_limits) },
+	{ IPP_SRCDST_FORMAT(NV12, rotator_4412_yuv_limits) },
+};
+
+static const struct exynos_drm_ipp_formats rotator_5250_formats[] = {
+	{ IPP_SRCDST_FORMAT(XRGB8888, rotator_5250_rbg888_limits) },
+	{ IPP_SRCDST_FORMAT(NV12, rotator_4412_yuv_limits) },
+};
+
+static const struct rot_variant rotator_4210_data = {
+	.formats = rotator_4210_formats,
+	.num_formats = ARRAY_SIZE(rotator_4210_formats),
+};
+
+static const struct rot_variant rotator_4412_data = {
+	.formats = rotator_4412_formats,
+	.num_formats = ARRAY_SIZE(rotator_4412_formats),
+};
+
+static const struct rot_variant rotator_5250_data = {
+	.formats = rotator_5250_formats,
+	.num_formats = ARRAY_SIZE(rotator_5250_formats),
+};
+
+static const struct of_device_id exynos_rotator_match[] = {
+	{
+		.compatible = "samsung,exynos4210-rotator",
+		.data = &rotator_4210_data,
+	}, {
+		.compatible = "samsung,exynos4212-rotator",
+		.data = &rotator_4412_data,
+	}, {
+		.compatible = "samsung,exynos5250-rotator",
+		.data = &rotator_5250_data,
+	}, {
+	},
+};
+MODULE_DEVICE_TABLE(of, exynos_rotator_match);
+
 static const struct dev_pm_ops rotator_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
 				pm_runtime_force_resume)
@@ -820,7 +438,7 @@ struct platform_driver rotator_driver = {
 	.probe		= rotator_probe,
 	.remove		= rotator_remove,
 	.driver		= {
-		.name	= "exynos-rot",
+		.name	= "exynos-rotator",
 		.owner	= THIS_MODULE,
 		.pm	= &rotator_pm_ops,
 		.of_match_table = exynos_rotator_match,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
new file mode 100644
index 000000000000..91d4382343d0
--- /dev/null
+++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
@@ -0,0 +1,694 @@
+/*
+ * Copyright (C) 2017 Samsung Electronics Co.Ltd
+ * Author:
+ *	Andrzej Pietrasiewicz <andrzej.p@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundationr
+ */
+
+#include <linux/kernel.h>
+#include <linux/component.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/of_device.h>
+#include <linux/pm_runtime.h>
+
+#include <drm/drmP.h>
+#include <drm/exynos_drm.h>
+#include "regs-scaler.h"
+#include "exynos_drm_fb.h"
+#include "exynos_drm_drv.h"
+#include "exynos_drm_iommu.h"
+#include "exynos_drm_ipp.h"
+
+#define scaler_read(offset)		readl(scaler->regs + (offset))
+#define scaler_write(cfg, offset)	writel(cfg, scaler->regs + (offset))
+#define SCALER_MAX_CLK			4
+#define SCALER_AUTOSUSPEND_DELAY	2000
+
+struct scaler_data {
+	const char	*clk_name[SCALER_MAX_CLK];
+	unsigned int	num_clk;
+	const struct exynos_drm_ipp_formats *formats;
+	unsigned int	num_formats;
+};
+
+struct scaler_context {
+	struct exynos_drm_ipp		ipp;
+	struct drm_device		*drm_dev;
+	struct device			*dev;
+	void __iomem			*regs;
+	struct clk			*clock[SCALER_MAX_CLK];
+	struct exynos_drm_ipp_task	*task;
+	const struct scaler_data	*scaler_data;
+};
+
+static u32 scaler_get_format(u32 drm_fmt)
+{
+	switch (drm_fmt) {
+	case DRM_FORMAT_NV21:
+		return SCALER_YUV420_2P_UV;
+	case DRM_FORMAT_NV12:
+		return SCALER_YUV420_2P_VU;
+	case DRM_FORMAT_YUV420:
+		return SCALER_YUV420_3P;
+	case DRM_FORMAT_YUYV:
+		return SCALER_YUV422_1P_YUYV;
+	case DRM_FORMAT_UYVY:
+		return SCALER_YUV422_1P_UYVY;
+	case DRM_FORMAT_YVYU:
+		return SCALER_YUV422_1P_YVYU;
+	case DRM_FORMAT_NV61:
+		return SCALER_YUV422_2P_UV;
+	case DRM_FORMAT_NV16:
+		return SCALER_YUV422_2P_VU;
+	case DRM_FORMAT_YUV422:
+		return SCALER_YUV422_3P;
+	case DRM_FORMAT_NV42:
+		return SCALER_YUV444_2P_UV;
+	case DRM_FORMAT_NV24:
+		return SCALER_YUV444_2P_VU;
+	case DRM_FORMAT_YUV444:
+		return SCALER_YUV444_3P;
+	case DRM_FORMAT_RGB565:
+		return SCALER_RGB_565;
+	case DRM_FORMAT_XRGB1555:
+		return SCALER_ARGB1555;
+	case DRM_FORMAT_ARGB1555:
+		return SCALER_ARGB1555;
+	case DRM_FORMAT_XRGB4444:
+		return SCALER_ARGB4444;
+	case DRM_FORMAT_ARGB4444:
+		return SCALER_ARGB4444;
+	case DRM_FORMAT_XRGB8888:
+		return SCALER_ARGB8888;
+	case DRM_FORMAT_ARGB8888:
+		return SCALER_ARGB8888;
+	case DRM_FORMAT_RGBX8888:
+		return SCALER_RGBA8888;
+	case DRM_FORMAT_RGBA8888:
+		return SCALER_RGBA8888;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static inline void scaler_enable_int(struct scaler_context *scaler)
+{
+	u32 val;
+
+	val = SCALER_INT_EN_TIMEOUT |
+		SCALER_INT_EN_ILLEGAL_BLEND |
+		SCALER_INT_EN_ILLEGAL_RATIO |
+		SCALER_INT_EN_ILLEGAL_DST_HEIGHT |
+		SCALER_INT_EN_ILLEGAL_DST_WIDTH |
+		SCALER_INT_EN_ILLEGAL_DST_V_POS |
+		SCALER_INT_EN_ILLEGAL_DST_H_POS |
+		SCALER_INT_EN_ILLEGAL_DST_C_SPAN |
+		SCALER_INT_EN_ILLEGAL_DST_Y_SPAN |
+		SCALER_INT_EN_ILLEGAL_DST_CR_BASE |
+		SCALER_INT_EN_ILLEGAL_DST_CB_BASE |
+		SCALER_INT_EN_ILLEGAL_DST_Y_BASE |
+		SCALER_INT_EN_ILLEGAL_DST_COLOR |
+		SCALER_INT_EN_ILLEGAL_SRC_HEIGHT |
+		SCALER_INT_EN_ILLEGAL_SRC_WIDTH |
+		SCALER_INT_EN_ILLEGAL_SRC_CV_POS |
+		SCALER_INT_EN_ILLEGAL_SRC_CH_POS |
+		SCALER_INT_EN_ILLEGAL_SRC_YV_POS |
+		SCALER_INT_EN_ILLEGAL_SRC_YH_POS |
+		SCALER_INT_EN_ILLEGAL_DST_SPAN |
+		SCALER_INT_EN_ILLEGAL_SRC_Y_SPAN |
+		SCALER_INT_EN_ILLEGAL_SRC_CR_BASE |
+		SCALER_INT_EN_ILLEGAL_SRC_CB_BASE |
+		SCALER_INT_EN_ILLEGAL_SRC_Y_BASE |
+		SCALER_INT_EN_ILLEGAL_SRC_COLOR |
+		SCALER_INT_EN_FRAME_END;
+	scaler_write(val, SCALER_INT_EN);
+}
+
+static inline void scaler_set_src_fmt(struct scaler_context *scaler,
+	u32 src_fmt)
+{
+	u32 val;
+
+	val = SCALER_SRC_CFG_SET_COLOR_FORMAT(src_fmt);
+	scaler_write(val, SCALER_SRC_CFG);
+}
+
+static inline void scaler_set_src_base(struct scaler_context *scaler,
+	struct exynos_drm_ipp_buffer *src_buf)
+{
+	static unsigned int bases[] = {
+		SCALER_SRC_Y_BASE,
+		SCALER_SRC_CB_BASE,
+		SCALER_SRC_CR_BASE,
+	};
+	int i;
+
+	for (i = 0; i < src_buf->format->num_planes; ++i)
+		scaler_write(src_buf->dma_addr[i], bases[i]);
+}
+
+static inline void scaler_set_src_span(struct scaler_context *scaler,
+	struct exynos_drm_ipp_buffer *src_buf)
+{
+	u32 val;
+
+	val = SCALER_SRC_SPAN_SET_Y_SPAN(src_buf->buf.pitch[0] /
+		src_buf->format->cpp[0]);
+
+	if (src_buf->format->num_planes > 1)
+		val |= SCALER_SRC_SPAN_SET_C_SPAN(src_buf->buf.pitch[1]);
+
+	scaler_write(val, SCALER_SRC_SPAN);
+}
+
+static inline void scaler_set_src_luma_pos(struct scaler_context *scaler,
+	struct drm_exynos_ipp_task_rect *src_pos)
+{
+	u32 val;
+
+	val = SCALER_SRC_Y_POS_SET_YH_POS(src_pos->x << 2);
+	val |=  SCALER_SRC_Y_POS_SET_YV_POS(src_pos->y << 2);
+	scaler_write(val, SCALER_SRC_Y_POS);
+	scaler_write(val, SCALER_SRC_C_POS); /* ATTENTION! */
+}
+
+static inline void scaler_set_src_wh(struct scaler_context *scaler,
+	struct drm_exynos_ipp_task_rect *src_pos)
+{
+	u32 val;
+
+	val = SCALER_SRC_WH_SET_WIDTH(src_pos->w);
+	val |= SCALER_SRC_WH_SET_HEIGHT(src_pos->h);
+	scaler_write(val, SCALER_SRC_WH);
+}
+
+static inline void scaler_set_dst_fmt(struct scaler_context *scaler,
+	u32 dst_fmt)
+{
+	u32 val;
+
+	val = SCALER_DST_CFG_SET_COLOR_FORMAT(dst_fmt);
+	scaler_write(val, SCALER_DST_CFG);
+}
+
+static inline void scaler_set_dst_base(struct scaler_context *scaler,
+	struct exynos_drm_ipp_buffer *dst_buf)
+{
+	static unsigned int bases[] = {
+		SCALER_DST_Y_BASE,
+		SCALER_DST_CB_BASE,
+		SCALER_DST_CR_BASE,
+	};
+	int i;
+
+	for (i = 0; i < dst_buf->format->num_planes; ++i)
+		scaler_write(dst_buf->dma_addr[i], bases[i]);
+}
+
+static inline void scaler_set_dst_span(struct scaler_context *scaler,
+	struct exynos_drm_ipp_buffer *dst_buf)
+{
+	u32 val;
+
+	val = SCALER_DST_SPAN_SET_Y_SPAN(dst_buf->buf.pitch[0] /
+		dst_buf->format->cpp[0]);
+
+	if (dst_buf->format->num_planes > 1)
+		val |= SCALER_DST_SPAN_SET_C_SPAN(dst_buf->buf.pitch[1]);
+
+	scaler_write(val, SCALER_DST_SPAN);
+}
+
+static inline void scaler_set_dst_luma_pos(struct scaler_context *scaler,
+	struct drm_exynos_ipp_task_rect *dst_pos)
+{
+	u32 val;
+
+	val = SCALER_DST_WH_SET_WIDTH(dst_pos->w);
+	val |= SCALER_DST_WH_SET_HEIGHT(dst_pos->h);
+	scaler_write(val, SCALER_DST_WH);
+}
+
+static inline void scaler_set_dst_wh(struct scaler_context *scaler,
+	struct drm_exynos_ipp_task_rect *dst_pos)
+{
+	u32 val;
+
+	val = SCALER_DST_POS_SET_H_POS(dst_pos->x);
+	val |= SCALER_DST_POS_SET_V_POS(dst_pos->y);
+	scaler_write(val, SCALER_DST_POS);
+}
+
+static inline void scaler_set_hv_ratio(struct scaler_context *scaler,
+	unsigned int rotation,
+	struct drm_exynos_ipp_task_rect *src_pos,
+	struct drm_exynos_ipp_task_rect *dst_pos)
+{
+	u32 val, h_ratio, v_ratio;
+
+	if (drm_rotation_90_or_270(rotation)) {
+		h_ratio = (src_pos->h << 16) / dst_pos->w;
+		v_ratio = (src_pos->w << 16) / dst_pos->h;
+	} else {
+		h_ratio = (src_pos->w << 16) / dst_pos->w;
+		v_ratio = (src_pos->h << 16) / dst_pos->h;
+	}
+
+	val = SCALER_H_RATIO_SET(h_ratio);
+	scaler_write(val, SCALER_H_RATIO);
+
+	val = SCALER_V_RATIO_SET(v_ratio);
+	scaler_write(val, SCALER_V_RATIO);
+}
+
+static inline void scaler_set_rotation(struct scaler_context *scaler,
+	unsigned int rotation)
+{
+	u32 val = 0;
+
+	if (rotation & DRM_MODE_ROTATE_90)
+		val |= SCALER_ROT_CFG_SET_ROTMODE(SCALER_ROT_MODE_90);
+	else if (rotation & DRM_MODE_ROTATE_180)
+		val |= SCALER_ROT_CFG_SET_ROTMODE(SCALER_ROT_MODE_180);
+	else if (rotation & DRM_MODE_ROTATE_270)
+		val |= SCALER_ROT_CFG_SET_ROTMODE(SCALER_ROT_MODE_270);
+	if (rotation & DRM_MODE_REFLECT_X)
+		val |= SCALER_ROT_CFG_FLIP_X_EN;
+	if (rotation & DRM_MODE_REFLECT_Y)
+		val |= SCALER_ROT_CFG_FLIP_Y_EN;
+	scaler_write(val, SCALER_ROT_CFG);
+}
+
+static inline void scaler_set_csc(struct scaler_context *scaler,
+	const struct drm_format_info *fmt)
+{
+	static const u32 csc_mtx[2][3][3] = {
+		{ /* YCbCr to RGB */
+			{0x254, 0x000, 0x331},
+			{0x254, 0xf38, 0xe60},
+			{0x254, 0x409, 0x000},
+		},
+		{ /* RGB to YCbCr */
+			{0x084, 0x102, 0x032},
+			{0xfb4, 0xf6b, 0x0e1},
+			{0x0e1, 0xf44, 0xfdc},
+		},
+	};
+	int i, j, dir;
+
+	switch (fmt->format) {
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_XRGB1555:
+	case DRM_FORMAT_ARGB1555:
+	case DRM_FORMAT_XRGB4444:
+	case DRM_FORMAT_ARGB4444:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_RGBX8888:
+	case DRM_FORMAT_RGBA8888:
+		dir = 1;
+		break;
+	default:
+		dir = 0;
+	}
+
+	for (i = 0; i < 3; i++)
+		for (j = 0; j < 3; j++)
+			scaler_write(csc_mtx[dir][i][j], SCALER_CSC_COEF(j, i));
+}
+
+static inline void scaler_set_timer(struct scaler_context *scaler,
+	unsigned int timer, unsigned int divider)
+{
+	u32 val;
+
+	val = SCALER_TIMEOUT_CTRL_TIMER_ENABLE;
+	val |= SCALER_TIMEOUT_CTRL_SET_TIMER_VALUE(timer);
+	val |= SCALER_TIMEOUT_CTRL_SET_TIMER_DIV(divider);
+	scaler_write(val, SCALER_TIMEOUT_CTRL);
+}
+
+static inline void scaler_start_hw(struct scaler_context *scaler)
+{
+	scaler_write(SCALER_CFG_START_CMD, SCALER_CFG);
+}
+
+static int scaler_commit(struct exynos_drm_ipp *ipp,
+			  struct exynos_drm_ipp_task *task)
+{
+	struct scaler_context *scaler =
+			container_of(ipp, struct scaler_context, ipp);
+
+	u32 src_fmt = scaler_get_format(task->src.buf.fourcc);
+	struct drm_exynos_ipp_task_rect *src_pos = &task->src.rect;
+
+	u32 dst_fmt = scaler_get_format(task->dst.buf.fourcc);
+	struct drm_exynos_ipp_task_rect *dst_pos = &task->dst.rect;
+
+	scaler->task = task;
+
+	pm_runtime_get_sync(scaler->dev);
+
+	scaler_set_src_fmt(scaler, src_fmt);
+	scaler_set_src_base(scaler, &task->src);
+	scaler_set_src_span(scaler, &task->src);
+	scaler_set_src_luma_pos(scaler, src_pos);
+	scaler_set_src_wh(scaler, src_pos);
+
+	scaler_set_dst_fmt(scaler, dst_fmt);
+	scaler_set_dst_base(scaler, &task->dst);
+	scaler_set_dst_span(scaler, &task->dst);
+	scaler_set_dst_luma_pos(scaler, dst_pos);
+	scaler_set_dst_wh(scaler, dst_pos);
+
+	scaler_set_hv_ratio(scaler, task->transform.rotation, src_pos, dst_pos);
+	scaler_set_rotation(scaler, task->transform.rotation);
+
+	scaler_set_csc(scaler, task->src.format);
+
+	scaler_set_timer(scaler, 0xffff, 0xf);
+
+	scaler_enable_int(scaler);
+	scaler_start_hw(scaler);
+
+	return 0;
+}
+
+static struct exynos_drm_ipp_funcs ipp_funcs = {
+	.commit = scaler_commit,
+};
+
+static inline void scaler_disable_int(struct scaler_context *scaler)
+{
+	scaler_write(0, SCALER_INT_EN);
+}
+
+static inline u32 scaler_get_int_status(struct scaler_context *scaler)
+{
+	return scaler_read(SCALER_INT_STATUS);
+}
+
+static inline int scaler_task_done(u32 val)
+{
+	return val & SCALER_INT_STATUS_FRAME_END ? 0 : -EINVAL;
+}
+
+static irqreturn_t scaler_irq_handler(int irq, void *arg)
+{
+	struct scaler_context *scaler = arg;
+
+	u32 val = scaler_get_int_status(scaler);
+
+	scaler_disable_int(scaler);
+
+	if (scaler->task) {
+		struct exynos_drm_ipp_task *task = scaler->task;
+
+		scaler->task = NULL;
+		pm_runtime_mark_last_busy(scaler->dev);
+		pm_runtime_put_autosuspend(scaler->dev);
+		exynos_drm_ipp_task_done(task, scaler_task_done(val));
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int scaler_bind(struct device *dev, struct device *master, void *data)
+{
+	struct scaler_context *scaler = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_ipp *ipp = &scaler->ipp;
+
+	scaler->drm_dev = drm_dev;
+	drm_iommu_attach_device(drm_dev, dev);
+
+	exynos_drm_ipp_register(drm_dev, ipp, &ipp_funcs,
+			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
+			DRM_EXYNOS_IPP_CAP_SCALE | DRM_EXYNOS_IPP_CAP_CONVERT,
+			scaler->scaler_data->formats,
+			scaler->scaler_data->num_formats, "scaler");
+
+	dev_info(dev, "The exynos scaler has been probed successfully\n");
+
+	return 0;
+}
+
+static void scaler_unbind(struct device *dev, struct device *master,
+			void *data)
+{
+	struct scaler_context *scaler = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_ipp *ipp = &scaler->ipp;
+
+	exynos_drm_ipp_unregister(drm_dev, ipp);
+	drm_iommu_detach_device(scaler->drm_dev, scaler->dev);
+}
+
+static const struct component_ops scaler_component_ops = {
+	.bind	= scaler_bind,
+	.unbind = scaler_unbind,
+};
+
+static int scaler_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource	*regs_res;
+	struct scaler_context *scaler;
+	int irq;
+	int ret, i;
+
+	scaler = devm_kzalloc(dev, sizeof(*scaler), GFP_KERNEL);
+	if (!scaler)
+		return -ENOMEM;
+
+	scaler->scaler_data =
+		(struct scaler_data *)of_device_get_match_data(dev);
+
+	scaler->dev = dev;
+	regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	scaler->regs = devm_ioremap_resource(dev, regs_res);
+	if (IS_ERR(scaler->regs))
+		return PTR_ERR(scaler->regs);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "failed to get irq\n");
+		return irq;
+	}
+
+	ret = devm_request_threaded_irq(dev, irq, NULL,	scaler_irq_handler,
+					IRQF_ONESHOT, "drm_scaler", scaler);
+	if (ret < 0) {
+		dev_err(dev, "failed to request irq\n");
+		return ret;
+	}
+
+	for (i = 0; i < scaler->scaler_data->num_clk; ++i) {
+		scaler->clock[i] = devm_clk_get(dev,
+					      scaler->scaler_data->clk_name[i]);
+		if (IS_ERR(scaler->clock[i])) {
+			dev_err(dev, "failed to get clock\n");
+			return PTR_ERR(scaler->clock[i]);
+		}
+	}
+
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, SCALER_AUTOSUSPEND_DELAY);
+	pm_runtime_enable(dev);
+	platform_set_drvdata(pdev, scaler);
+
+	ret = component_add(dev, &scaler_component_ops);
+	if (ret)
+		goto err_ippdrv_register;
+
+	return 0;
+
+err_ippdrv_register:
+	pm_runtime_dont_use_autosuspend(dev);
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static int scaler_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	component_del(dev, &scaler_component_ops);
+	pm_runtime_dont_use_autosuspend(dev);
+	pm_runtime_disable(dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+
+static int clk_disable_unprepare_wrapper(struct clk *clk)
+{
+	clk_disable_unprepare(clk);
+
+	return 0;
+}
+
+static int scaler_clk_ctrl(struct scaler_context *scaler, bool enable)
+{
+	int (*clk_fun)(struct clk *clk), i;
+
+	clk_fun = enable ? clk_prepare_enable : clk_disable_unprepare_wrapper;
+
+	for (i = 0; i < scaler->scaler_data->num_clk; ++i)
+		clk_fun(scaler->clock[i]);
+
+	return 0;
+}
+
+static int scaler_runtime_suspend(struct device *dev)
+{
+	struct scaler_context *scaler = dev_get_drvdata(dev);
+
+	return  scaler_clk_ctrl(scaler, false);
+}
+
+static int scaler_runtime_resume(struct device *dev)
+{
+	struct scaler_context *scaler = dev_get_drvdata(dev);
+
+	return  scaler_clk_ctrl(scaler, true);
+}
+#endif
+
+static const struct dev_pm_ops scaler_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(scaler_runtime_suspend, scaler_runtime_resume, NULL)
+};
+
+static const struct drm_exynos_ipp_limit scaler_5420_two_pixel_hv_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 16, SZ_8K }, .v = { 16, SZ_8K }) },
+	{ IPP_SIZE_LIMIT(AREA, .h.align = 2, .v.align = 2) },
+	{ IPP_SCALE_LIMIT(.h = { 65536 * 1 / 4, 65536 * 16 },
+			  .v = { 65536 * 1 / 4, 65536 * 16 }) },
+};
+
+static const struct drm_exynos_ipp_limit scaler_5420_two_pixel_h_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 16, SZ_8K }, .v = { 16, SZ_8K }) },
+	{ IPP_SIZE_LIMIT(AREA, .h.align = 2, .v.align = 1) },
+	{ IPP_SCALE_LIMIT(.h = { 65536 * 1 / 4, 65536 * 16 },
+			  .v = { 65536 * 1 / 4, 65536 * 16 }) },
+};
+
+static const struct drm_exynos_ipp_limit scaler_5420_one_pixel_limits[] = {
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 16, SZ_8K }, .v = { 16, SZ_8K }) },
+	{ IPP_SCALE_LIMIT(.h = { 65536 * 1 / 4, 65536 * 16 },
+			  .v = { 65536 * 1 / 4, 65536 * 16 }) },
+};
+
+static const struct exynos_drm_ipp_formats exynos5420_formats[] = {
+	/* SCALER_YUV420_2P_UV */
+	{ IPP_SRCDST_FORMAT(NV21, scaler_5420_two_pixel_hv_limits) },
+
+	/* SCALER_YUV420_2P_VU */
+	{ IPP_SRCDST_FORMAT(NV12, scaler_5420_two_pixel_hv_limits) },
+
+	/* SCALER_YUV420_3P */
+	{ IPP_SRCDST_FORMAT(YUV420, scaler_5420_two_pixel_hv_limits) },
+
+	/* SCALER_YUV422_1P_YUYV */
+	{ IPP_SRCDST_FORMAT(YUYV, scaler_5420_two_pixel_h_limits) },
+
+	/* SCALER_YUV422_1P_UYVY */
+	{ IPP_SRCDST_FORMAT(UYVY, scaler_5420_two_pixel_h_limits) },
+
+	/* SCALER_YUV422_1P_YVYU */
+	{ IPP_SRCDST_FORMAT(YVYU, scaler_5420_two_pixel_h_limits) },
+
+	/* SCALER_YUV422_2P_UV */
+	{ IPP_SRCDST_FORMAT(NV61, scaler_5420_two_pixel_h_limits) },
+
+	/* SCALER_YUV422_2P_VU */
+	{ IPP_SRCDST_FORMAT(NV16, scaler_5420_two_pixel_h_limits) },
+
+	/* SCALER_YUV422_3P */
+	{ IPP_SRCDST_FORMAT(YUV422, scaler_5420_two_pixel_h_limits) },
+
+	/* SCALER_YUV444_2P_UV */
+	{ IPP_SRCDST_FORMAT(NV42, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_YUV444_2P_VU */
+	{ IPP_SRCDST_FORMAT(NV24, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_YUV444_3P */
+	{ IPP_SRCDST_FORMAT(YUV444, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_RGB_565 */
+	{ IPP_SRCDST_FORMAT(RGB565, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_ARGB1555 */
+	{ IPP_SRCDST_FORMAT(XRGB1555, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_ARGB1555 */
+	{ IPP_SRCDST_FORMAT(ARGB1555, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_ARGB4444 */
+	{ IPP_SRCDST_FORMAT(XRGB4444, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_ARGB4444 */
+	{ IPP_SRCDST_FORMAT(ARGB4444, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_ARGB8888 */
+	{ IPP_SRCDST_FORMAT(XRGB8888, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_ARGB8888 */
+	{ IPP_SRCDST_FORMAT(ARGB8888, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_RGBA8888 */
+	{ IPP_SRCDST_FORMAT(RGBX8888, scaler_5420_one_pixel_limits) },
+
+	/* SCALER_RGBA8888 */
+	{ IPP_SRCDST_FORMAT(RGBA8888, scaler_5420_one_pixel_limits) },
+};
+
+static const struct scaler_data exynos5420_data = {
+	.clk_name	= {"mscl"},
+	.num_clk	= 1,
+	.formats	= exynos5420_formats,
+	.num_formats	= ARRAY_SIZE(exynos5420_formats),
+};
+
+static const struct scaler_data exynos5433_data = {
+	.clk_name	= {"pclk", "aclk", "aclk_xiu"},
+	.num_clk	= 3,
+	.formats	= exynos5420_formats, /* intentional */
+	.num_formats	= ARRAY_SIZE(exynos5420_formats),
+};
+
+static const struct of_device_id exynos_scaler_match[] = {
+	{
+		.compatible = "samsung,exynos5420-scaler",
+		.data = &exynos5420_data,
+	}, {
+		.compatible = "samsung,exynos5433-scaler",
+		.data = &exynos5433_data,
+	}, {
+	},
+};
+MODULE_DEVICE_TABLE(of, exynos_scaler_match);
+
+struct platform_driver scaler_driver = {
+	.probe		= scaler_probe,
+	.remove		= scaler_remove,
+	.driver		= {
+		.name	= "exynos-scaler",
+		.owner	= THIS_MODULE,
+		.pm	= &scaler_pm_ops,
+		.of_match_table = exynos_scaler_match,
+	},
+};
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index abd84cbcf1c2..09c4bc0b1859 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -954,8 +954,6 @@ static int hdmi_create_connector(struct drm_encoder *encoder)
 	drm_mode_connector_attach_encoder(connector, encoder);
 
 	if (hdata->bridge) {
-		encoder->bridge = hdata->bridge;
-		hdata->bridge->encoder = encoder;
 		ret = drm_bridge_attach(encoder, hdata->bridge, NULL);
 		if (ret)
 			DRM_ERROR("Failed to attach bridge\n");
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 257299ec95c4..272c79f5f5bf 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -473,7 +473,7 @@ static void vp_video_buffer(struct mixer_context *ctx,
 			chroma_addr[1] = chroma_addr[0] + 0x40;
 		} else {
 			luma_addr[1] = luma_addr[0] + fb->pitches[0];
-			chroma_addr[1] = chroma_addr[0] + fb->pitches[0];
+			chroma_addr[1] = chroma_addr[0] + fb->pitches[1];
 		}
 	} else {
 		luma_addr[1] = 0;
@@ -482,6 +482,7 @@ static void vp_video_buffer(struct mixer_context *ctx,
 
 	spin_lock_irqsave(&ctx->reg_slock, flags);
 
+	vp_reg_write(ctx, VP_SHADOW_UPDATE, 1);
 	/* interlace or progressive scan mode */
 	val = (test_bit(MXR_BIT_INTERLACE, &ctx->flags) ? ~0 : 0);
 	vp_reg_writemask(ctx, VP_MODE, val, VP_MODE_LINE_SKIP);
@@ -495,21 +496,23 @@ static void vp_video_buffer(struct mixer_context *ctx,
 	vp_reg_write(ctx, VP_IMG_SIZE_Y, VP_IMG_HSIZE(fb->pitches[0]) |
 		VP_IMG_VSIZE(fb->height));
 	/* chroma plane for NV12/NV21 is half the height of the luma plane */
-	vp_reg_write(ctx, VP_IMG_SIZE_C, VP_IMG_HSIZE(fb->pitches[0]) |
+	vp_reg_write(ctx, VP_IMG_SIZE_C, VP_IMG_HSIZE(fb->pitches[1]) |
 		VP_IMG_VSIZE(fb->height / 2));
 
 	vp_reg_write(ctx, VP_SRC_WIDTH, state->src.w);
-	vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h);
 	vp_reg_write(ctx, VP_SRC_H_POSITION,
 			VP_SRC_H_POSITION_VAL(state->src.x));
-	vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y);
-
 	vp_reg_write(ctx, VP_DST_WIDTH, state->crtc.w);
 	vp_reg_write(ctx, VP_DST_H_POSITION, state->crtc.x);
+
 	if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) {
+		vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h / 2);
+		vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y / 2);
 		vp_reg_write(ctx, VP_DST_HEIGHT, state->crtc.h / 2);
 		vp_reg_write(ctx, VP_DST_V_POSITION, state->crtc.y / 2);
 	} else {
+		vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h);
+		vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y);
 		vp_reg_write(ctx, VP_DST_HEIGHT, state->crtc.h);
 		vp_reg_write(ctx, VP_DST_V_POSITION, state->crtc.y);
 	}
@@ -699,6 +702,15 @@ static irqreturn_t mixer_irq_handler(int irq, void *arg)
 
 		/* interlace scan need to check shadow register */
 		if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) {
+			if (test_bit(MXR_BIT_VP_ENABLED, &ctx->flags) &&
+			    vp_reg_read(ctx, VP_SHADOW_UPDATE))
+				goto out;
+
+			base = mixer_reg_read(ctx, MXR_CFG);
+			shadow = mixer_reg_read(ctx, MXR_CFG_S);
+			if (base != shadow)
+				goto out;
+
 			base = mixer_reg_read(ctx, MXR_GRAPHIC_BASE(0));
 			shadow = mixer_reg_read(ctx, MXR_GRAPHIC_BASE_S(0));
 			if (base != shadow)
diff --git a/drivers/gpu/drm/exynos/regs-mixer.h b/drivers/gpu/drm/exynos/regs-mixer.h
index c311f571bdf9..189cfa2470a8 100644
--- a/drivers/gpu/drm/exynos/regs-mixer.h
+++ b/drivers/gpu/drm/exynos/regs-mixer.h
@@ -47,6 +47,7 @@
 #define MXR_MO				0x0304
 #define MXR_RESOLUTION			0x0310
 
+#define MXR_CFG_S			0x2004
 #define MXR_GRAPHIC0_BASE_S		0x2024
 #define MXR_GRAPHIC1_BASE_S		0x2044
 
diff --git a/drivers/gpu/drm/exynos/regs-scaler.h b/drivers/gpu/drm/exynos/regs-scaler.h
new file mode 100644
index 000000000000..fc7ccad75e74
--- /dev/null
+++ b/drivers/gpu/drm/exynos/regs-scaler.h
@@ -0,0 +1,426 @@
+/* drivers/gpu/drm/exynos/regs-scaler.h
+ *
+ * Copyright (c) 2017 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com/
+ * Author: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
+ *
+ * Register definition file for Samsung scaler driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EXYNOS_REGS_SCALER_H
+#define EXYNOS_REGS_SCALER_H
+
+/* Register part */
+
+/* Global setting */
+#define SCALER_STATUS			0x0	/* no shadow */
+#define SCALER_CFG			0x4
+
+/* Interrupt */
+#define SCALER_INT_EN			0x8	/* no shadow */
+#define SCALER_INT_STATUS		0xc	/* no shadow */
+
+/* SRC */
+#define SCALER_SRC_CFG			0x10
+#define SCALER_SRC_Y_BASE		0x14
+#define SCALER_SRC_CB_BASE		0x18
+#define SCALER_SRC_CR_BASE		0x294
+#define SCALER_SRC_SPAN			0x1c
+#define SCALER_SRC_Y_POS		0x20
+#define SCALER_SRC_WH			0x24
+#define SCALER_SRC_C_POS		0x28
+
+/* DST */
+#define SCALER_DST_CFG			0x30
+#define SCALER_DST_Y_BASE		0x34
+#define SCALER_DST_CB_BASE		0x38
+#define SCALER_DST_CR_BASE		0x298
+#define SCALER_DST_SPAN			0x3c
+#define SCALER_DST_WH			0x40
+#define SCALER_DST_POS			0x44
+
+/* Ratio */
+#define SCALER_H_RATIO			0x50
+#define SCALER_V_RATIO			0x54
+
+/* Rotation */
+#define SCALER_ROT_CFG			0x58
+
+/* Coefficient */
+/*
+ * YHCOEF_{x}{A|B|C|D}			CHCOEF_{x}{A|B|C|D}
+ *
+ *	A	B	C	D	A	B	C	D
+ * 0	60	64	68	6c	140	144	148	14c
+ * 1	70	74	78	7c	150	154	158	15c
+ * 2	80	84	88	8c	160	164	168	16c
+ * 3	90	94	98	9c	170	174	178	17c
+ * 4	a0	a4	a8	ac	180	184	188	18c
+ * 5	b0	b4	b8	bc	190	194	198	19c
+ * 6	c0	c4	c8	cc	1a0	1a4	1a8	1ac
+ * 7	d0	d4	d8	dc	1b0	1b4	1b8	1bc
+ * 8	e0	e4	e8	ec	1c0	1c4	1c8	1cc
+ *
+ *
+ * YVCOEF_{x}{A|B}			CVCOEF_{x}{A|B}
+ *
+ *	A	B			A	B
+ * 0	f0	f4			1d0	1d4
+ * 1	f8	fc			1d8	1dc
+ * 2	100	104			1e0	1e4
+ * 3	108	10c			1e8	1ec
+ * 4	110	114			1f0	1f4
+ * 5	118	11c			1f8	1fc
+ * 6	120	124			200	204
+ * 7	128	12c			208	20c
+ * 8	130	134			210	214
+ */
+#define _SCALER_HCOEF_DELTA(r, c)	((r) * 0x10 + (c) * 0x4)
+#define _SCALER_VCOEF_DELTA(r, c)	((r) * 0x8 + (c) * 0x4)
+
+#define SCALER_YHCOEF(r, c)		(0x60 + _SCALER_HCOEF_DELTA((r), (c)))
+#define SCALER_YVCOEF(r, c)		(0xf0 + _SCALER_VCOEF_DELTA((r), (c)))
+#define SCALER_CHCOEF(r, c)		(0x140 + _SCALER_HCOEF_DELTA((r), (c)))
+#define SCALER_CVCOEF(r, c)		(0x1d0 + _SCALER_VCOEF_DELTA((r), (c)))
+
+
+/* Color Space Conversion */
+#define SCALER_CSC_COEF(x, y)		(0x220 + (y) * 0xc + (x) * 0x4)
+
+/* Dithering */
+#define SCALER_DITH_CFG			0x250
+
+/* Version Number */
+#define SCALER_VER			0x260	/* no shadow */
+
+/* Cycle count and Timeout */
+#define SCALER_CYCLE_COUNT		0x278	/* no shadow */
+#define SCALER_TIMEOUT_CTRL		0x2c0	/* no shadow */
+#define SCALER_TIMEOUT_CNT		0x2c4	/* no shadow */
+
+/* Blending */
+#define SCALER_SRC_BLEND_COLOR		0x280
+#define SCALER_SRC_BLEND_ALPHA		0x284
+#define SCALER_DST_BLEND_COLOR		0x288
+#define SCALER_DST_BLEND_ALPHA		0x28c
+
+/* Color Fill */
+#define SCALER_FILL_COLOR		0x290
+
+/* Multiple Command Queue */
+#define SCALER_ADDR_Q_CONFIG		0x2a0	/* no shadow */
+#define SCALER_SRC_ADDR_Q_STATUS	0x2a4	/* no shadow */
+#define SCALER_SRC_ADDR_Q		0x2a8	/* no shadow */
+
+/* CRC */
+#define SCALER_CRC_COLOR00_10		0x2b0	/* no shadow */
+#define SCALER_CRC_COLOR20_30		0x2b4	/* no shadow */
+#define SCALER_CRC_COLOR01_11		0x2b8	/* no shadow */
+#define SCALER_CRC_COLOR21_31		0x2bc	/* no shadow */
+
+/* Shadow Registers */
+#define SCALER_SHADOW_OFFSET		0x1000
+
+
+/* Bit definition part */
+#define SCALER_MASK(hi_b, lo_b)		((1 << ((hi_b) - (lo_b) + 1)) - 1)
+#define SCALER_GET(reg, hi_b, lo_b)	\
+	(((reg) >> (lo_b)) & SCALER_MASK(hi_b, lo_b))
+#define SCALER_SET(val, hi_b, lo_b) \
+	(((val) & SCALER_MASK(hi_b, lo_b)) << lo_b)
+
+/* SCALER_STATUS */
+#define SCALER_STATUS_SCALER_RUNNING		(1 << 1)
+#define SCALER_STATUS_SCALER_READY_CLK_DOWN	(1 << 0)
+
+/* SCALER_CFG */
+#define SCALER_CFG_FILL_EN			(1 << 24)
+#define SCALER_CFG_BLEND_COLOR_DIVIDE_ALPHA_EN	(1 << 17)
+#define SCALER_CFG_BLEND_EN			(1 << 16)
+#define SCALER_CFG_CSC_Y_OFFSET_SRC_EN		(1 << 10)
+#define SCALER_CFG_CSC_Y_OFFSET_DST_EN		(1 << 9)
+#define SCALER_CFG_16_BURST_MODE		(1 << 8)
+#define SCALER_CFG_SOFT_RESET			(1 << 1)
+#define SCALER_CFG_START_CMD			(1 << 0)
+
+/* SCALER_INT_EN */
+#define SCALER_INT_EN_TIMEOUT			(1 << 31)
+#define SCALER_INT_EN_ILLEGAL_BLEND		(1 << 24)
+#define SCALER_INT_EN_ILLEGAL_RATIO		(1 << 23)
+#define SCALER_INT_EN_ILLEGAL_DST_HEIGHT	(1 << 22)
+#define SCALER_INT_EN_ILLEGAL_DST_WIDTH		(1 << 21)
+#define SCALER_INT_EN_ILLEGAL_DST_V_POS		(1 << 20)
+#define SCALER_INT_EN_ILLEGAL_DST_H_POS		(1 << 19)
+#define SCALER_INT_EN_ILLEGAL_DST_C_SPAN	(1 << 18)
+#define SCALER_INT_EN_ILLEGAL_DST_Y_SPAN	(1 << 17)
+#define SCALER_INT_EN_ILLEGAL_DST_CR_BASE	(1 << 16)
+#define SCALER_INT_EN_ILLEGAL_DST_CB_BASE	(1 << 15)
+#define SCALER_INT_EN_ILLEGAL_DST_Y_BASE	(1 << 14)
+#define SCALER_INT_EN_ILLEGAL_DST_COLOR		(1 << 13)
+#define SCALER_INT_EN_ILLEGAL_SRC_HEIGHT	(1 << 12)
+#define SCALER_INT_EN_ILLEGAL_SRC_WIDTH		(1 << 11)
+#define SCALER_INT_EN_ILLEGAL_SRC_CV_POS	(1 << 10)
+#define SCALER_INT_EN_ILLEGAL_SRC_CH_POS	(1 << 9)
+#define SCALER_INT_EN_ILLEGAL_SRC_YV_POS	(1 << 8)
+#define SCALER_INT_EN_ILLEGAL_SRC_YH_POS	(1 << 7)
+#define SCALER_INT_EN_ILLEGAL_DST_SPAN		(1 << 6)
+#define SCALER_INT_EN_ILLEGAL_SRC_Y_SPAN	(1 << 5)
+#define SCALER_INT_EN_ILLEGAL_SRC_CR_BASE	(1 << 4)
+#define SCALER_INT_EN_ILLEGAL_SRC_CB_BASE	(1 << 3)
+#define SCALER_INT_EN_ILLEGAL_SRC_Y_BASE	(1 << 2)
+#define SCALER_INT_EN_ILLEGAL_SRC_COLOR		(1 << 1)
+#define SCALER_INT_EN_FRAME_END			(1 << 0)
+
+/* SCALER_INT_STATUS */
+#define SCALER_INT_STATUS_TIMEOUT		(1 << 31)
+#define SCALER_INT_STATUS_ILLEGAL_BLEND		(1 << 24)
+#define SCALER_INT_STATUS_ILLEGAL_RATIO		(1 << 23)
+#define SCALER_INT_STATUS_ILLEGAL_DST_HEIGHT	(1 << 22)
+#define SCALER_INT_STATUS_ILLEGAL_DST_WIDTH	(1 << 21)
+#define SCALER_INT_STATUS_ILLEGAL_DST_V_POS	(1 << 20)
+#define SCALER_INT_STATUS_ILLEGAL_DST_H_POS	(1 << 19)
+#define SCALER_INT_STATUS_ILLEGAL_DST_C_SPAN	(1 << 18)
+#define SCALER_INT_STATUS_ILLEGAL_DST_Y_SPAN	(1 << 17)
+#define SCALER_INT_STATUS_ILLEGAL_DST_CR_BASE	(1 << 16)
+#define SCALER_INT_STATUS_ILLEGAL_DST_CB_BASE	(1 << 15)
+#define SCALER_INT_STATUS_ILLEGAL_DST_Y_BASE	(1 << 14)
+#define SCALER_INT_STATUS_ILLEGAL_DST_COLOR	(1 << 13)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_HEIGHT	(1 << 12)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_WIDTH	(1 << 11)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_CV_POS	(1 << 10)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_CH_POS	(1 << 9)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_YV_POS	(1 << 8)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_YH_POS	(1 << 7)
+#define SCALER_INT_STATUS_ILLEGAL_DST_SPAN	(1 << 6)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_Y_SPAN	(1 << 5)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_CR_BASE	(1 << 4)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_CB_BASE	(1 << 3)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_Y_BASE	(1 << 2)
+#define SCALER_INT_STATUS_ILLEGAL_SRC_COLOR	(1 << 1)
+#define SCALER_INT_STATUS_FRAME_END		(1 << 0)
+
+/* SCALER_SRC_CFG */
+#define SCALER_SRC_CFG_TILE_EN			(1 << 10)
+#define SCALER_SRC_CFG_GET_BYTE_SWAP(r)		SCALER_GET(r, 6, 5)
+#define SCALER_SRC_CFG_SET_BYTE_SWAP(v)		SCALER_SET(v, 6, 5)
+#define SCALER_SRC_CFG_GET_COLOR_FORMAT(r)	SCALER_GET(r, 4, 0)
+#define SCALER_SRC_CFG_SET_COLOR_FORMAT(v)	SCALER_SET(v, 4, 0)
+#define SCALER_YUV420_2P_UV			0
+#define SCALER_YUV422_2P_UV			2
+#define SCALER_YUV444_2P_UV			3
+#define SCALER_RGB_565				4
+#define SCALER_ARGB1555				5
+#define SCALER_ARGB8888				6
+#define SCALER_ARGB8888_PRE			7
+#define SCALER_YUV422_1P_YVYU			9
+#define SCALER_YUV422_1P_YUYV			10
+#define SCALER_YUV422_1P_UYVY			11
+#define SCALER_ARGB4444				12
+#define SCALER_L8A8				13
+#define SCALER_RGBA8888				14
+#define SCALER_L8				15
+#define SCALER_YUV420_2P_VU			16
+#define SCALER_YUV422_2P_VU			18
+#define SCALER_YUV444_2P_VU			19
+#define SCALER_YUV420_3P			20
+#define SCALER_YUV422_3P			22
+#define SCALER_YUV444_3P			23
+
+/* SCALER_SRC_SPAN */
+#define SCALER_SRC_SPAN_GET_C_SPAN(r)		SCALER_GET(r, 29, 16)
+#define SCALER_SRC_SPAN_SET_C_SPAN(v)		SCALER_SET(v, 29, 16)
+#define SCALER_SRC_SPAN_GET_Y_SPAN(r)		SCALER_GET(r, 13, 0)
+#define SCALER_SRC_SPAN_SET_Y_SPAN(v)		SCALER_SET(v, 13, 0)
+
+/* SCALER_SRC_Y_POS */
+#define SCALER_SRC_Y_POS_GET_YH_POS(r)		SCALER_GET(r, 31, 16)
+#define SCALER_SRC_Y_POS_SET_YH_POS(v)		SCALER_SET(v, 31, 16)
+#define SCALER_SRC_Y_POS_GET_YV_POS(r)		SCALER_GET(r, 15, 0)
+#define SCALER_SRC_Y_POS_SET_YV_POS(v)		SCALER_SET(v, 15, 0)
+
+/* SCALER_SRC_WH */
+#define SCALER_SRC_WH_GET_WIDTH(r)		SCALER_GET(r, 29, 16)
+#define SCALER_SRC_WH_SET_WIDTH(v)		SCALER_SET(v, 29, 16)
+#define SCALER_SRC_WH_GET_HEIGHT(r)		SCALER_GET(r, 13, 0)
+#define SCALER_SRC_WH_SET_HEIGHT(v)		SCALER_SET(v, 13, 0)
+
+/* SCALER_SRC_C_POS */
+#define SCALER_SRC_C_POS_GET_CH_POS(r)		SCALER_GET(r, 31, 16)
+#define SCALER_SRC_C_POS_SET_CH_POS(v)		SCALER_SET(v, 31, 16)
+#define SCALER_SRC_C_POS_GET_CV_POS(r)		SCALER_GET(r, 15, 0)
+#define SCALER_SRC_C_POS_SET_CV_POS(v)		SCALER_SET(v, 15, 0)
+
+/* SCALER_DST_CFG */
+#define SCALER_DST_CFG_GET_BYTE_SWAP(r)		SCALER_GET(r, 6, 5)
+#define SCALER_DST_CFG_SET_BYTE_SWAP(v)		SCALER_SET(v, 6, 5)
+#define SCALER_DST_CFG_GET_COLOR_FORMAT(r)	SCALER_GET(r, 4, 0)
+#define SCALER_DST_CFG_SET_COLOR_FORMAT(v)	SCALER_SET(v, 4, 0)
+
+/* SCALER_DST_SPAN */
+#define SCALER_DST_SPAN_GET_C_SPAN(r)		SCALER_GET(r, 29, 16)
+#define SCALER_DST_SPAN_SET_C_SPAN(v)		SCALER_SET(v, 29, 16)
+#define SCALER_DST_SPAN_GET_Y_SPAN(r)		SCALER_GET(r, 13, 0)
+#define SCALER_DST_SPAN_SET_Y_SPAN(v)		SCALER_SET(v, 13, 0)
+
+/* SCALER_DST_WH */
+#define SCALER_DST_WH_GET_WIDTH(r)		SCALER_GET(r, 29, 16)
+#define SCALER_DST_WH_SET_WIDTH(v)		SCALER_SET(v, 29, 16)
+#define SCALER_DST_WH_GET_HEIGHT(r)		SCALER_GET(r, 13, 0)
+#define SCALER_DST_WH_SET_HEIGHT(v)		SCALER_SET(v, 13, 0)
+
+/* SCALER_DST_POS */
+#define SCALER_DST_POS_GET_H_POS(r)		SCALER_GET(r, 29, 16)
+#define SCALER_DST_POS_SET_H_POS(v)		SCALER_SET(v, 29, 16)
+#define SCALER_DST_POS_GET_V_POS(r)		SCALER_GET(r, 13, 0)
+#define SCALER_DST_POS_SET_V_POS(v)		SCALER_SET(v, 13, 0)
+
+/* SCALER_H_RATIO */
+#define SCALER_H_RATIO_GET(r)			SCALER_GET(r, 18, 0)
+#define SCALER_H_RATIO_SET(v)			SCALER_SET(v, 18, 0)
+
+/* SCALER_V_RATIO */
+#define SCALER_V_RATIO_GET(r)			SCALER_GET(r, 18, 0)
+#define SCALER_V_RATIO_SET(v)			SCALER_SET(v, 18, 0)
+
+/* SCALER_ROT_CFG */
+#define SCALER_ROT_CFG_FLIP_X_EN		(1 << 3)
+#define SCALER_ROT_CFG_FLIP_Y_EN		(1 << 2)
+#define SCALER_ROT_CFG_GET_ROTMODE(r)		SCALER_GET(r, 1, 0)
+#define SCALER_ROT_CFG_SET_ROTMODE(v)		SCALER_SET(v, 1, 0)
+#define SCALER_ROT_MODE_90			1
+#define SCALER_ROT_MODE_180			2
+#define SCALER_ROT_MODE_270			3
+
+/* SCALER_HCOEF, SCALER_VCOEF */
+#define SCALER_COEF_SHIFT(i)			(16 * (1 - (i) % 2))
+#define SCALER_COEF_GET(r, i)			\
+				(((r) >> SCALER_COEF_SHIFT(i)) & 0x1ff)
+#define SCALER_COEF_SET(v, i)			\
+				(((v) & 0x1ff) << SCALER_COEF_SHIFT(i))
+
+/* SCALER_CSC_COEFxy */
+#define SCALER_CSC_COEF_GET(r)			SCALER_GET(r, 11, 0)
+#define SCALER_CSC_COEF_SET(v)			SCALER_SET(v, 11, 0)
+
+/* SCALER_DITH_CFG */
+#define SCALER_DITH_CFG_GET_R_TYPE(r)		SCALER_GET(r, 8, 6)
+#define SCALER_DITH_CFG_SET_R_TYPE(v)		SCALER_SET(v, 8, 6)
+#define SCALER_DITH_CFG_GET_G_TYPE(r)		SCALER_GET(r, 5, 3)
+#define SCALER_DITH_CFG_SET_G_TYPE(v)		SCALER_SET(v, 5, 3)
+#define SCALER_DITH_CFG_GET_B_TYPE(r)		SCALER_GET(r, 2, 0)
+#define SCALER_DITH_CFG_SET_B_TYPE(v)		SCALER_SET(v, 2, 0)
+
+/* SCALER_TIMEOUT_CTRL */
+#define SCALER_TIMEOUT_CTRL_GET_TIMER_VALUE(r)	SCALER_GET(r, 31, 16)
+#define SCALER_TIMEOUT_CTRL_SET_TIMER_VALUE(v)	SCALER_SET(v, 31, 16)
+#define SCALER_TIMEOUT_CTRL_GET_TIMER_DIV(r)	SCALER_GET(r, 7, 4)
+#define SCALER_TIMEOUT_CTRL_SET_TIMER_DIV(v)	SCALER_SET(v, 7, 4)
+#define SCALER_TIMEOUT_CTRL_TIMER_ENABLE	(1 << 0)
+
+/* SCALER_TIMEOUT_CNT */
+#define SCALER_TIMEOUT_CTRL_GET_TIMER_COUNT(r)	SCALER_GET(r, 31, 16)
+
+/* SCALER_SRC_BLEND_COLOR */
+#define SCALER_SRC_BLEND_COLOR_SEL_INV		(1 << 31)
+#define SCALER_SRC_BLEND_COLOR_GET_SEL(r)	SCALER_GET(r, 30, 29)
+#define SCALER_SRC_BLEND_COLOR_SET_SEL(v)	SCALER_SET(v, 30, 29)
+#define SCALER_SRC_BLEND_COLOR_OP_SEL_INV	(1 << 28)
+#define SCALER_SRC_BLEND_COLOR_GET_OP_SEL(r)	SCALER_GET(r, 27, 24)
+#define SCALER_SRC_BLEND_COLOR_SET_OP_SEL(v)	SCALER_SET(v, 27, 24)
+#define SCALER_SRC_BLEND_COLOR_GET_COLOR0(r)	SCALER_GET(r, 23, 16)
+#define SCALER_SRC_BLEND_COLOR_SET_COLOR0(v)	SCALER_SET(v, 23, 16)
+#define SCALER_SRC_BLEND_COLOR_GET_COLOR1(r)	SCALER_GET(r, 15, 8)
+#define SCALER_SRC_BLEND_COLOR_SET_COLOR1(v)	SCALER_SET(v, 15, 8)
+#define SCALER_SRC_BLEND_COLOR_GET_COLOR2(r)	SCALER_GET(r, 7, 0)
+#define SCALER_SRC_BLEND_COLOR_SET_COLOR2(v)	SCALER_SET(v, 7, 0)
+
+/* SCALER_SRC_BLEND_ALPHA */
+#define SCALER_SRC_BLEND_ALPHA_SEL_INV		(1 << 31)
+#define SCALER_SRC_BLEND_ALPHA_GET_SEL(r)	SCALER_GET(r, 30, 29)
+#define SCALER_SRC_BLEND_ALPHA_SET_SEL(v)	SCALER_SET(v, 30, 29)
+#define SCALER_SRC_BLEND_ALPHA_OP_SEL_INV	(1 << 28)
+#define SCALER_SRC_BLEND_ALPHA_GET_OP_SEL(r)	SCALER_GET(r, 27, 24)
+#define SCALER_SRC_BLEND_ALPHA_SET_OP_SEL(v)	SCALER_SET(v, 27, 24)
+#define SCALER_SRC_BLEND_ALPHA_GET_ALPHA(r)	SCALER_GET(r, 7, 0)
+#define SCALER_SRC_BLEND_ALPHA_SET_ALPHA(v)	SCALER_SET(v, 7, 0)
+
+/* SCALER_DST_BLEND_COLOR */
+#define SCALER_DST_BLEND_COLOR_SEL_INV		(1 << 31)
+#define SCALER_DST_BLEND_COLOR_GET_SEL(r)	SCALER_GET(r, 30, 29)
+#define SCALER_DST_BLEND_COLOR_SET_SEL(v)	SCALER_SET(v, 30, 29)
+#define SCALER_DST_BLEND_COLOR_OP_SEL_INV	(1 << 28)
+#define SCALER_DST_BLEND_COLOR_GET_OP_SEL(r)	SCALER_GET(r, 27, 24)
+#define SCALER_DST_BLEND_COLOR_SET_OP_SEL(v)	SCALER_SET(v, 27, 24)
+#define SCALER_DST_BLEND_COLOR_GET_COLOR0(r)	SCALER_GET(r, 23, 16)
+#define SCALER_DST_BLEND_COLOR_SET_COLOR0(v)	SCALER_SET(v, 23, 16)
+#define SCALER_DST_BLEND_COLOR_GET_COLOR1(r)	SCALER_GET(r, 15, 8)
+#define SCALER_DST_BLEND_COLOR_SET_COLOR1(v)	SCALER_SET(v, 15, 8)
+#define SCALER_DST_BLEND_COLOR_GET_COLOR2(r)	SCALER_GET(r, 7, 0)
+#define SCALER_DST_BLEND_COLOR_SET_COLOR2(v)	SCALER_SET(v, 7, 0)
+
+/* SCALER_DST_BLEND_ALPHA */
+#define SCALER_DST_BLEND_ALPHA_SEL_INV		(1 << 31)
+#define SCALER_DST_BLEND_ALPHA_GET_SEL(r)	SCALER_GET(r, 30, 29)
+#define SCALER_DST_BLEND_ALPHA_SET_SEL(v)	SCALER_SET(v, 30, 29)
+#define SCALER_DST_BLEND_ALPHA_OP_SEL_INV	(1 << 28)
+#define SCALER_DST_BLEND_ALPHA_GET_OP_SEL(r)	SCALER_GET(r, 27, 24)
+#define SCALER_DST_BLEND_ALPHA_SET_OP_SEL(v)	SCALER_SET(v, 27, 24)
+#define SCALER_DST_BLEND_ALPHA_GET_ALPHA(r)	SCALER_GET(r, 7, 0)
+#define SCALER_DST_BLEND_ALPHA_SET_ALPHA(v)	SCALER_SET(v, 7, 0)
+
+/* SCALER_FILL_COLOR */
+#define SCALER_FILL_COLOR_GET_ALPHA(r)		SCALER_GET(r, 31, 24)
+#define SCALER_FILL_COLOR_SET_ALPHA(v)		SCALER_SET(v, 31, 24)
+#define SCALER_FILL_COLOR_GET_FILL_COLOR0(r)	SCALER_GET(r, 23, 16)
+#define SCALER_FILL_COLOR_SET_FILL_COLOR0(v)	SCALER_SET(v, 23, 16)
+#define SCALER_FILL_COLOR_GET_FILL_COLOR1(r)	SCALER_GET(r, 15, 8)
+#define SCALER_FILL_COLOR_SET_FILL_COLOR1(v)	SCALER_SET(v, 15, 8)
+#define SCALER_FILL_COLOR_GET_FILL_COLOR2(r)	SCALER_GET(r, 7, 0)
+#define SCALER_FILL_COLOR_SET_FILL_COLOR2(v)	SCALER_SET(v, 7, 0)
+
+/* SCALER_ADDR_Q_CONFIG */
+#define SCALER_ADDR_Q_CONFIG_RST		(1 << 0)
+
+/* SCALER_SRC_ADDR_Q_STATUS */
+#define SCALER_SRC_ADDR_Q_STATUS_Y_FULL		(1 << 23)
+#define SCALER_SRC_ADDR_Q_STATUS_Y_EMPTY	(1 << 22)
+#define SCALER_SRC_ADDR_Q_STATUS_GET_Y_WR_IDX(r)	SCALER_GET(r, 21, 16)
+#define SCALER_SRC_ADDR_Q_STATUS_CB_FULL	(1 << 15)
+#define SCALER_SRC_ADDR_Q_STATUS_CB_EMPTY	(1 << 14)
+#define SCALER_SRC_ADDR_Q_STATUS_GET_CB_WR_IDX(r)	SCALER_GET(r, 13, 8)
+#define SCALER_SRC_ADDR_Q_STATUS_CR_FULL	(1 << 7)
+#define SCALER_SRC_ADDR_Q_STATUS_CR_EMPTY	(1 << 6)
+#define SCALER_SRC_ADDR_Q_STATUS_GET_CR_WR_IDX(r)	SCALER_GET(r, 5, 0)
+
+/* SCALER_DST_ADDR_Q_STATUS */
+#define SCALER_DST_ADDR_Q_STATUS_Y_FULL		(1 << 23)
+#define SCALER_DST_ADDR_Q_STATUS_Y_EMPTY	(1 << 22)
+#define SCALER_DST_ADDR_Q_STATUS_GET_Y_WR_IDX(r)	SCALER_GET(r, 21, 16)
+#define SCALER_DST_ADDR_Q_STATUS_CB_FULL	(1 << 15)
+#define SCALER_DST_ADDR_Q_STATUS_CB_EMPTY	(1 << 14)
+#define SCALER_DST_ADDR_Q_STATUS_GET_CB_WR_IDX(r)	SCALER_GET(r, 13, 8)
+#define SCALER_DST_ADDR_Q_STATUS_CR_FULL	(1 << 7)
+#define SCALER_DST_ADDR_Q_STATUS_CR_EMPTY	(1 << 6)
+#define SCALER_DST_ADDR_Q_STATUS_GET_CR_WR_IDX(r)	SCALER_GET(r, 5, 0)
+
+/* SCALER_CRC_COLOR00_10 */
+#define SCALER_CRC_COLOR00_10_GET_00(r)		SCALER_GET(r, 31, 16)
+#define SCALER_CRC_COLOR00_10_GET_10(r)		SCALER_GET(r, 15, 0)
+
+/* SCALER_CRC_COLOR20_30 */
+#define SCALER_CRC_COLOR20_30_GET_20(r)		SCALER_GET(r, 31, 16)
+#define SCALER_CRC_COLOR20_30_GET_30(r)		SCALER_GET(r, 15, 0)
+
+/* SCALER_CRC_COLOR01_11 */
+#define SCALER_CRC_COLOR01_11_GET_01(r)		SCALER_GET(r, 31, 16)
+#define SCALER_CRC_COLOR01_11_GET_11(r)		SCALER_GET(r, 15, 0)
+
+/* SCALER_CRC_COLOR21_31 */
+#define SCALER_CRC_COLOR21_31_GET_21(r)		SCALER_GET(r, 31, 16)
+#define SCALER_CRC_COLOR21_31_GET_31(r)		SCALER_GET(r, 15, 0)
+
+#endif /* EXYNOS_REGS_SCALER_H */
diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c
index 3a3bf752e03a..34b85767e4da 100644
--- a/drivers/gpu/drm/gma500/cdv_device.c
+++ b/drivers/gpu/drm/gma500/cdv_device.c
@@ -485,7 +485,7 @@ void cdv_intel_attach_force_audio_property(struct drm_connector *connector)
 			return;
 
 		for (i = 0; i < ARRAY_SIZE(force_audio_names); i++)
-			drm_property_add_enum(prop, i, i-1, force_audio_names[i]);
+			drm_property_add_enum(prop, i-1, force_audio_names[i]);
 
 		dev_priv->force_audio_property = prop;
 	}
@@ -514,7 +514,7 @@ void cdv_intel_attach_broadcast_rgb_property(struct drm_connector *connector)
 			return;
 
 		for (i = 0; i < ARRAY_SIZE(broadcast_rgb_names); i++)
-			drm_property_add_enum(prop, i, i, broadcast_rgb_names[i]);
+			drm_property_add_enum(prop, i, broadcast_rgb_names[i]);
 
 		dev_priv->broadcast_rgb_property = prop;
 	}
diff --git a/drivers/gpu/drm/gma500/cdv_intel_crt.c b/drivers/gpu/drm/gma500/cdv_intel_crt.c
index b837e7a92196..cb5a14b7ec7f 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_crt.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_crt.c
@@ -64,7 +64,7 @@ static void cdv_intel_crt_dpms(struct drm_encoder *encoder, int mode)
 	REG_WRITE(reg, temp);
 }
 
-static int cdv_intel_crt_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status cdv_intel_crt_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index a4bb89b7878f..5ea785f07ba8 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -505,7 +505,7 @@ static void cdv_intel_edp_backlight_off (struct gma_encoder *intel_encoder)
 	msleep(intel_dp->backlight_off_delay);
 }
 
-static int
+static enum drm_mode_status
 cdv_intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
 {
diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
index 563f193fcfac..f0878998526a 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
@@ -223,7 +223,7 @@ static int cdv_hdmi_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static int cdv_hdmi_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status cdv_hdmi_mode_valid(struct drm_connector *connector,
 				 struct drm_display_mode *mode)
 {
 	if (mode->clock > 165000)
diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
index e64960db3224..de9531caaca0 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
@@ -244,7 +244,7 @@ static void cdv_intel_lvds_restore(struct drm_connector *connector)
 {
 }
 
-static int cdv_intel_lvds_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status cdv_intel_lvds_mode_valid(struct drm_connector *connector,
 			      struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_output.c b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
index acb3848ef1c9..fe020926ea4f 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_output.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
@@ -346,7 +346,7 @@ static int mdfld_dsi_connector_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static int mdfld_dsi_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status mdfld_dsi_connector_mode_valid(struct drm_connector *connector,
 						struct drm_display_mode *mode)
 {
 	struct mdfld_dsi_connector *dsi_connector =
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index 8b2eb32ee988..78566a80ad25 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -509,7 +509,7 @@ static void oaktrail_hdmi_dpms(struct drm_encoder *encoder, int mode)
 	HDMI_WRITE(HDMI_VIDEO_REG, temp);
 }
 
-static int oaktrail_hdmi_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status oaktrail_hdmi_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
 	if (mode->clock > 165000)
diff --git a/drivers/gpu/drm/gma500/psb_intel_drv.h b/drivers/gpu/drm/gma500/psb_intel_drv.h
index e8e4ea14b12b..e05e5399af2d 100644
--- a/drivers/gpu/drm/gma500/psb_intel_drv.h
+++ b/drivers/gpu/drm/gma500/psb_intel_drv.h
@@ -255,7 +255,7 @@ extern int intelfb_remove(struct drm_device *dev,
 extern bool psb_intel_lvds_mode_fixup(struct drm_encoder *encoder,
 				      const struct drm_display_mode *mode,
 				      struct drm_display_mode *adjusted_mode);
-extern int psb_intel_lvds_mode_valid(struct drm_connector *connector,
+extern enum drm_mode_status psb_intel_lvds_mode_valid(struct drm_connector *connector,
 				     struct drm_display_mode *mode);
 extern int psb_intel_lvds_set_property(struct drm_connector *connector,
 					struct drm_property *property,
diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c
index be3eefec5152..8baf6325c6e4 100644
--- a/drivers/gpu/drm/gma500/psb_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c
@@ -343,7 +343,7 @@ static void psb_intel_lvds_restore(struct drm_connector *connector)
 	}
 }
 
-int psb_intel_lvds_mode_valid(struct drm_connector *connector,
+enum drm_mode_status psb_intel_lvds_mode_valid(struct drm_connector *connector,
 				 struct drm_display_mode *mode)
 {
 	struct drm_psb_private *dev_priv = connector->dev->dev_private;
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index 84507912be84..f2ee6aa10afa 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -1157,7 +1157,7 @@ static void psb_intel_sdvo_dpms(struct drm_encoder *encoder, int mode)
 	return;
 }
 
-static int psb_intel_sdvo_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status psb_intel_sdvo_mode_valid(struct drm_connector *connector,
 				 struct drm_display_mode *mode)
 {
 	struct psb_intel_sdvo *psb_intel_sdvo = intel_attached_sdvo(connector);
@@ -2281,7 +2281,7 @@ static bool psb_intel_sdvo_tv_create_property(struct psb_intel_sdvo *psb_intel_s
 
 	for (i = 0; i < psb_intel_sdvo_connector->format_supported_num; i++)
 		drm_property_add_enum(
-				psb_intel_sdvo_connector->tv_format, i,
+				psb_intel_sdvo_connector->tv_format,
 				i, tv_format_names[psb_intel_sdvo_connector->tv_format_supported[i]]);
 
 	psb_intel_sdvo->tv_format_index = psb_intel_sdvo_connector->tv_format_supported[0];
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
index f4eba87c96f3..d2f4749ebf8d 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
@@ -27,7 +27,7 @@ static int hibmc_connector_get_modes(struct drm_connector *connector)
 	return drm_add_modes_noedid(connector, 800, 600);
 }
 
-static int hibmc_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status hibmc_connector_mode_valid(struct drm_connector *connector,
 				      struct drm_display_mode *mode)
 {
 	return MODE_OK;
diff --git a/drivers/gpu/drm/i2c/Kconfig b/drivers/gpu/drm/i2c/Kconfig
index a6c92beb410a..65d3acb61c03 100644
--- a/drivers/gpu/drm/i2c/Kconfig
+++ b/drivers/gpu/drm/i2c/Kconfig
@@ -22,8 +22,14 @@ config DRM_I2C_SIL164
 config DRM_I2C_NXP_TDA998X
 	tristate "NXP Semiconductors TDA998X HDMI encoder"
 	default m if DRM_TILCDC
+	select CEC_CORE if CEC_NOTIFIER
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	help
 	  Support for NXP Semiconductors TDA998X HDMI encoders.
 
+config DRM_I2C_NXP_TDA9950
+	tristate "NXP Semiconductors TDA9950/TDA998X HDMI CEC"
+	select CEC_NOTIFIER
+	select CEC_CORE
+
 endmenu
diff --git a/drivers/gpu/drm/i2c/Makefile b/drivers/gpu/drm/i2c/Makefile
index b20100c18ffb..a962f6f08568 100644
--- a/drivers/gpu/drm/i2c/Makefile
+++ b/drivers/gpu/drm/i2c/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_DRM_I2C_SIL164) += sil164.o
 
 tda998x-y := tda998x_drv.o
 obj-$(CONFIG_DRM_I2C_NXP_TDA998X) += tda998x.o
+obj-$(CONFIG_DRM_I2C_NXP_TDA9950) += tda9950.o
diff --git a/drivers/gpu/drm/i2c/tda9950.c b/drivers/gpu/drm/i2c/tda9950.c
new file mode 100644
index 000000000000..3f7396caad48
--- /dev/null
+++ b/drivers/gpu/drm/i2c/tda9950.c
@@ -0,0 +1,509 @@
+/*
+ *  TDA9950 Consumer Electronics Control driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * The NXP TDA9950 implements the HDMI Consumer Electronics Control
+ * interface.  The host interface is similar to a mailbox: the data
+ * registers starting at REG_CDR0 are written to send a command to the
+ * internal CPU, and replies are read from these registers.
+ *
+ * As the data registers represent a mailbox, they must be accessed
+ * as a single I2C transaction.  See the TDA9950 data sheet for details.
+ */
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/platform_data/tda9950.h>
+#include <linux/slab.h>
+#include <drm/drm_edid.h>
+#include <media/cec.h>
+#include <media/cec-notifier.h>
+
+enum {
+	REG_CSR = 0x00,
+	CSR_BUSY = BIT(7),
+	CSR_INT  = BIT(6),
+	CSR_ERR  = BIT(5),
+
+	REG_CER = 0x01,
+
+	REG_CVR = 0x02,
+
+	REG_CCR = 0x03,
+	CCR_RESET = BIT(7),
+	CCR_ON    = BIT(6),
+
+	REG_ACKH = 0x04,
+	REG_ACKL = 0x05,
+
+	REG_CCONR = 0x06,
+	CCONR_ENABLE_ERROR = BIT(4),
+	CCONR_RETRY_MASK = 7,
+
+	REG_CDR0 = 0x07,
+
+	CDR1_REQ = 0x00,
+	CDR1_CNF = 0x01,
+	CDR1_IND = 0x81,
+	CDR1_ERR = 0x82,
+	CDR1_IER = 0x83,
+
+	CDR2_CNF_SUCCESS    = 0x00,
+	CDR2_CNF_OFF_STATE  = 0x80,
+	CDR2_CNF_BAD_REQ    = 0x81,
+	CDR2_CNF_CEC_ACCESS = 0x82,
+	CDR2_CNF_ARB_ERROR  = 0x83,
+	CDR2_CNF_BAD_TIMING = 0x84,
+	CDR2_CNF_NACK_ADDR  = 0x85,
+	CDR2_CNF_NACK_DATA  = 0x86,
+};
+
+struct tda9950_priv {
+	struct i2c_client *client;
+	struct device *hdmi;
+	struct cec_adapter *adap;
+	struct tda9950_glue *glue;
+	u16 addresses;
+	struct cec_msg rx_msg;
+	struct cec_notifier *notify;
+	bool open;
+};
+
+static int tda9950_write_range(struct i2c_client *client, u8 addr, u8 *p, int cnt)
+{
+	struct i2c_msg msg;
+	u8 buf[cnt + 1];
+	int ret;
+
+	buf[0] = addr;
+	memcpy(buf + 1, p, cnt);
+
+	msg.addr = client->addr;
+	msg.flags = 0;
+	msg.len = cnt + 1;
+	msg.buf = buf;
+
+	dev_dbg(&client->dev, "wr 0x%02x: %*ph\n", addr, cnt, p);
+
+	ret = i2c_transfer(client->adapter, &msg, 1);
+	if (ret < 0)
+		dev_err(&client->dev, "Error %d writing to cec:0x%x\n", ret, addr);
+	return ret < 0 ? ret : 0;
+}
+
+static void tda9950_write(struct i2c_client *client, u8 addr, u8 val)
+{
+	tda9950_write_range(client, addr, &val, 1);
+}
+
+static int tda9950_read_range(struct i2c_client *client, u8 addr, u8 *p, int cnt)
+{
+	struct i2c_msg msg[2];
+	int ret;
+
+	msg[0].addr = client->addr;
+	msg[0].flags = 0;
+	msg[0].len = 1;
+	msg[0].buf = &addr;
+	msg[1].addr = client->addr;
+	msg[1].flags = I2C_M_RD;
+	msg[1].len = cnt;
+	msg[1].buf = p;
+
+	ret = i2c_transfer(client->adapter, msg, 2);
+	if (ret < 0)
+		dev_err(&client->dev, "Error %d reading from cec:0x%x\n", ret, addr);
+
+	dev_dbg(&client->dev, "rd 0x%02x: %*ph\n", addr, cnt, p);
+
+	return ret;
+}
+
+static u8 tda9950_read(struct i2c_client *client, u8 addr)
+{
+	int ret;
+	u8 val;
+
+	ret = tda9950_read_range(client, addr, &val, 1);
+	if (ret < 0)
+		val = 0;
+
+	return val;
+}
+
+static irqreturn_t tda9950_irq(int irq, void *data)
+{
+	struct tda9950_priv *priv = data;
+	unsigned int tx_status;
+	u8 csr, cconr, buf[19];
+	u8 arb_lost_cnt, nack_cnt, err_cnt;
+
+	if (!priv->open)
+		return IRQ_NONE;
+
+	csr = tda9950_read(priv->client, REG_CSR);
+	if (!(csr & CSR_INT))
+		return IRQ_NONE;
+
+	cconr = tda9950_read(priv->client, REG_CCONR) & CCONR_RETRY_MASK;
+
+	tda9950_read_range(priv->client, REG_CDR0, buf, sizeof(buf));
+
+	/*
+	 * This should never happen: the data sheet says that there will
+	 * always be a valid message if the interrupt line is asserted.
+	 */
+	if (buf[0] == 0) {
+		dev_warn(&priv->client->dev, "interrupt pending, but no message?\n");
+		return IRQ_NONE;
+	}
+
+	switch (buf[1]) {
+	case CDR1_CNF: /* transmit result */
+		arb_lost_cnt = nack_cnt = err_cnt = 0;
+		switch (buf[2]) {
+		case CDR2_CNF_SUCCESS:
+			tx_status = CEC_TX_STATUS_OK;
+			break;
+
+		case CDR2_CNF_ARB_ERROR:
+			tx_status = CEC_TX_STATUS_ARB_LOST;
+			arb_lost_cnt = cconr;
+			break;
+
+		case CDR2_CNF_NACK_ADDR:
+			tx_status = CEC_TX_STATUS_NACK;
+			nack_cnt = cconr;
+			break;
+
+		default: /* some other error, refer to TDA9950 docs */
+			dev_err(&priv->client->dev, "CNF reply error 0x%02x\n",
+				buf[2]);
+			tx_status = CEC_TX_STATUS_ERROR;
+			err_cnt = cconr;
+			break;
+		}
+		/* TDA9950 executes all retries for us */
+		tx_status |= CEC_TX_STATUS_MAX_RETRIES;
+		cec_transmit_done(priv->adap, tx_status, arb_lost_cnt,
+				  nack_cnt, 0, err_cnt);
+		break;
+
+	case CDR1_IND:
+		priv->rx_msg.len = buf[0] - 2;
+		if (priv->rx_msg.len > CEC_MAX_MSG_SIZE)
+			priv->rx_msg.len = CEC_MAX_MSG_SIZE;
+
+		memcpy(priv->rx_msg.msg, buf + 2, priv->rx_msg.len);
+		cec_received_msg(priv->adap, &priv->rx_msg);
+		break;
+
+	default: /* unknown */
+		dev_err(&priv->client->dev, "unknown service id 0x%02x\n",
+			buf[1]);
+		break;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int tda9950_cec_transmit(struct cec_adapter *adap, u8 attempts,
+				u32 signal_free_time, struct cec_msg *msg)
+{
+	struct tda9950_priv *priv = adap->priv;
+	u8 buf[CEC_MAX_MSG_SIZE + 2];
+
+	buf[0] = 2 + msg->len;
+	buf[1] = CDR1_REQ;
+	memcpy(buf + 2, msg->msg, msg->len);
+
+	if (attempts > 5)
+		attempts = 5;
+
+	tda9950_write(priv->client, REG_CCONR, attempts);
+
+	return tda9950_write_range(priv->client, REG_CDR0, buf, 2 + msg->len);
+}
+
+static int tda9950_cec_adap_log_addr(struct cec_adapter *adap, u8 addr)
+{
+	struct tda9950_priv *priv = adap->priv;
+	u16 addresses;
+	u8 buf[2];
+
+	if (addr == CEC_LOG_ADDR_INVALID)
+		addresses = priv->addresses = 0;
+	else
+		addresses = priv->addresses |= BIT(addr);
+
+	/* TDA9950 doesn't want address 15 set */
+	addresses &= 0x7fff;
+	buf[0] = addresses >> 8;
+	buf[1] = addresses;
+
+	return tda9950_write_range(priv->client, REG_ACKH, buf, 2);
+}
+
+/*
+ * When operating as part of the TDA998x, we need additional handling
+ * to initialise and shut down the TDA9950 part of the device.  These
+ * two hooks are provided to allow the TDA998x code to perform those
+ * activities.
+ */
+static int tda9950_glue_open(struct tda9950_priv *priv)
+{
+	int ret = 0;
+
+	if (priv->glue && priv->glue->open)
+		ret = priv->glue->open(priv->glue->data);
+
+	priv->open = true;
+
+	return ret;
+}
+
+static void tda9950_glue_release(struct tda9950_priv *priv)
+{
+	priv->open = false;
+
+	if (priv->glue && priv->glue->release)
+		priv->glue->release(priv->glue->data);
+}
+
+static int tda9950_open(struct tda9950_priv *priv)
+{
+	struct i2c_client *client = priv->client;
+	int ret;
+
+	ret = tda9950_glue_open(priv);
+	if (ret)
+		return ret;
+
+	/* Reset the TDA9950, and wait 250ms for it to recover */
+	tda9950_write(client, REG_CCR, CCR_RESET);
+	msleep(250);
+
+	tda9950_cec_adap_log_addr(priv->adap, CEC_LOG_ADDR_INVALID);
+
+	/* Start the command processor */
+	tda9950_write(client, REG_CCR, CCR_ON);
+
+	return 0;
+}
+
+static void tda9950_release(struct tda9950_priv *priv)
+{
+	struct i2c_client *client = priv->client;
+	int timeout = 50;
+	u8 csr;
+
+	/* Stop the command processor */
+	tda9950_write(client, REG_CCR, 0);
+
+	/* Wait up to .5s for it to signal non-busy */
+	do {
+		csr = tda9950_read(client, REG_CSR);
+		if (!(csr & CSR_BUSY) || --timeout)
+			break;
+		msleep(10);
+	} while (1);
+
+	/* Warn the user that their IRQ may die if it's shared. */
+	if (csr & CSR_BUSY)
+		dev_warn(&client->dev, "command processor failed to stop, irq%d may die (csr=0x%02x)\n",
+			 client->irq, csr);
+
+	tda9950_glue_release(priv);
+}
+
+static int tda9950_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct tda9950_priv *priv = adap->priv;
+
+	if (!enable) {
+		tda9950_release(priv);
+		return 0;
+	} else {
+		return tda9950_open(priv);
+	}
+}
+
+static const struct cec_adap_ops tda9950_cec_ops = {
+	.adap_enable = tda9950_cec_adap_enable,
+	.adap_log_addr = tda9950_cec_adap_log_addr,
+	.adap_transmit = tda9950_cec_transmit,
+};
+
+/*
+ * When operating as part of the TDA998x, we need to claim additional
+ * resources.  These two hooks permit the management of those resources.
+ */
+static void tda9950_devm_glue_exit(void *data)
+{
+	struct tda9950_glue *glue = data;
+
+	if (glue && glue->exit)
+		glue->exit(glue->data);
+}
+
+static int tda9950_devm_glue_init(struct device *dev, struct tda9950_glue *glue)
+{
+	int ret;
+
+	if (glue && glue->init) {
+		ret = glue->init(glue->data);
+		if (ret)
+			return ret;
+	}
+
+	ret = devm_add_action(dev, tda9950_devm_glue_exit, glue);
+	if (ret)
+		tda9950_devm_glue_exit(glue);
+
+	return ret;
+}
+
+static void tda9950_cec_del(void *data)
+{
+	struct tda9950_priv *priv = data;
+
+	cec_delete_adapter(priv->adap);
+}
+
+static int tda9950_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct tda9950_glue *glue = client->dev.platform_data;
+	struct device *dev = &client->dev;
+	struct tda9950_priv *priv;
+	unsigned long irqflags;
+	int ret;
+	u8 cvr;
+
+	/*
+	 * We must have I2C functionality: our multi-byte accesses
+	 * must be performed as a single contiguous transaction.
+	 */
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		dev_err(&client->dev,
+			"adapter does not support I2C functionality\n");
+		return -ENXIO;
+	}
+
+	/* We must have an interrupt to be functional. */
+	if (client->irq <= 0) {
+		dev_err(&client->dev, "driver requires an interrupt\n");
+		return -ENXIO;
+	}
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->client = client;
+	priv->glue = glue;
+
+	i2c_set_clientdata(client, priv);
+
+	/*
+	 * If we're part of a TDA998x, we want the class devices to be
+	 * associated with the HDMI Tx so we have a tight relationship
+	 * between the HDMI interface and the CEC interface.
+	 */
+	priv->hdmi = dev;
+	if (glue && glue->parent)
+		priv->hdmi = glue->parent;
+
+	priv->adap = cec_allocate_adapter(&tda9950_cec_ops, priv, "tda9950",
+					  CEC_CAP_DEFAULTS,
+					  CEC_MAX_LOG_ADDRS);
+	if (IS_ERR(priv->adap))
+		return PTR_ERR(priv->adap);
+
+	ret = devm_add_action(dev, tda9950_cec_del, priv);
+	if (ret) {
+		cec_delete_adapter(priv->adap);
+		return ret;
+	}
+
+	ret = tda9950_devm_glue_init(dev, glue);
+	if (ret)
+		return ret;
+
+	ret = tda9950_glue_open(priv);
+	if (ret)
+		return ret;
+
+	cvr = tda9950_read(client, REG_CVR);
+
+	dev_info(&client->dev,
+		 "TDA9950 CEC interface, hardware version %u.%u\n",
+		 cvr >> 4, cvr & 15);
+
+	tda9950_glue_release(priv);
+
+	irqflags = IRQF_TRIGGER_FALLING;
+	if (glue)
+		irqflags = glue->irq_flags;
+
+	ret = devm_request_threaded_irq(dev, client->irq, NULL, tda9950_irq,
+					irqflags | IRQF_SHARED | IRQF_ONESHOT,
+					dev_name(&client->dev), priv);
+	if (ret < 0)
+		return ret;
+
+	priv->notify = cec_notifier_get(priv->hdmi);
+	if (!priv->notify)
+		return -ENOMEM;
+
+	ret = cec_register_adapter(priv->adap, priv->hdmi);
+	if (ret < 0) {
+		cec_notifier_put(priv->notify);
+		return ret;
+	}
+
+	/*
+	 * CEC documentation says we must not call cec_delete_adapter
+	 * after a successful call to cec_register_adapter().
+	 */
+	devm_remove_action(dev, tda9950_cec_del, priv);
+
+	cec_register_cec_notifier(priv->adap, priv->notify);
+
+	return 0;
+}
+
+static int tda9950_remove(struct i2c_client *client)
+{
+	struct tda9950_priv *priv = i2c_get_clientdata(client);
+
+	cec_unregister_adapter(priv->adap);
+	cec_notifier_put(priv->notify);
+
+	return 0;
+}
+
+static struct i2c_device_id tda9950_ids[] = {
+	{ "tda9950", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, tda9950_ids);
+
+static struct i2c_driver tda9950_driver = {
+	.probe = tda9950_probe,
+	.remove = tda9950_remove,
+	.driver = {
+		.name = "tda9950",
+	},
+	.id_table = tda9950_ids,
+};
+
+module_i2c_driver(tda9950_driver);
+
+MODULE_AUTHOR("Russell King <rmk+kernel@armlinux.org.uk>");
+MODULE_DESCRIPTION("TDA9950/TDA998x Consumer Electronics Control Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 9e67a7b4e3a4..6ebd8842dbcc 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -16,8 +16,10 @@
  */
 
 #include <linux/component.h>
+#include <linux/gpio/consumer.h>
 #include <linux/hdmi.h>
 #include <linux/module.h>
+#include <linux/platform_data/tda9950.h>
 #include <linux/irq.h>
 #include <sound/asoundef.h>
 #include <sound/hdmi-codec.h>
@@ -29,6 +31,8 @@
 #include <drm/drm_of.h>
 #include <drm/i2c/tda998x.h>
 
+#include <media/cec-notifier.h>
+
 #define DBG(fmt, ...) DRM_DEBUG(fmt"\n", ##__VA_ARGS__)
 
 struct tda998x_audio_port {
@@ -55,6 +59,7 @@ struct tda998x_priv {
 	struct platform_device *audio_pdev;
 	struct mutex audio_mutex;
 
+	struct mutex edid_mutex;
 	wait_queue_head_t wq_edid;
 	volatile int wq_edid_wait;
 
@@ -67,6 +72,9 @@ struct tda998x_priv {
 	struct drm_connector connector;
 
 	struct tda998x_audio_port audio_port[2];
+	struct tda9950_glue cec_glue;
+	struct gpio_desc *calib;
+	struct cec_notifier *cec_notify;
 };
 
 #define conn_to_tda998x_priv(x) \
@@ -345,6 +353,12 @@ struct tda998x_priv {
 #define REG_CEC_INTSTATUS	  0xee		      /* read */
 # define CEC_INTSTATUS_CEC	  (1 << 0)
 # define CEC_INTSTATUS_HDMI	  (1 << 1)
+#define REG_CEC_CAL_XOSC_CTRL1    0xf2
+# define CEC_CAL_XOSC_CTRL1_ENA_CAL	BIT(0)
+#define REG_CEC_DES_FREQ2         0xf5
+# define CEC_DES_FREQ2_DIS_AUTOCAL BIT(7)
+#define REG_CEC_CLK               0xf6
+# define CEC_CLK_FRO              0x11
 #define REG_CEC_FRO_IM_CLK_CTRL   0xfb                /* read/write */
 # define CEC_FRO_IM_CLK_CTRL_GHOST_DIS (1 << 7)
 # define CEC_FRO_IM_CLK_CTRL_ENA_OTP   (1 << 6)
@@ -359,6 +373,7 @@ struct tda998x_priv {
 # define CEC_RXSHPDLEV_HPD        (1 << 1)
 
 #define REG_CEC_ENAMODS           0xff                /* read/write */
+# define CEC_ENAMODS_EN_CEC_CLK   (1 << 7)
 # define CEC_ENAMODS_DIS_FRO      (1 << 6)
 # define CEC_ENAMODS_DIS_CCLK     (1 << 5)
 # define CEC_ENAMODS_EN_RXSENS    (1 << 2)
@@ -417,6 +432,114 @@ cec_read(struct tda998x_priv *priv, u8 addr)
 	return val;
 }
 
+static void cec_enamods(struct tda998x_priv *priv, u8 mods, bool enable)
+{
+	int val = cec_read(priv, REG_CEC_ENAMODS);
+
+	if (val < 0)
+		return;
+
+	if (enable)
+		val |= mods;
+	else
+		val &= ~mods;
+
+	cec_write(priv, REG_CEC_ENAMODS, val);
+}
+
+static void tda998x_cec_set_calibration(struct tda998x_priv *priv, bool enable)
+{
+	if (enable) {
+		u8 val;
+
+		cec_write(priv, 0xf3, 0xc0);
+		cec_write(priv, 0xf4, 0xd4);
+
+		/* Enable automatic calibration mode */
+		val = cec_read(priv, REG_CEC_DES_FREQ2);
+		val &= ~CEC_DES_FREQ2_DIS_AUTOCAL;
+		cec_write(priv, REG_CEC_DES_FREQ2, val);
+
+		/* Enable free running oscillator */
+		cec_write(priv, REG_CEC_CLK, CEC_CLK_FRO);
+		cec_enamods(priv, CEC_ENAMODS_DIS_FRO, false);
+
+		cec_write(priv, REG_CEC_CAL_XOSC_CTRL1,
+			  CEC_CAL_XOSC_CTRL1_ENA_CAL);
+	} else {
+		cec_write(priv, REG_CEC_CAL_XOSC_CTRL1, 0);
+	}
+}
+
+/*
+ * Calibration for the internal oscillator: we need to set calibration mode,
+ * and then pulse the IRQ line low for a 10ms ± 1% period.
+ */
+static void tda998x_cec_calibration(struct tda998x_priv *priv)
+{
+	struct gpio_desc *calib = priv->calib;
+
+	mutex_lock(&priv->edid_mutex);
+	if (priv->hdmi->irq > 0)
+		disable_irq(priv->hdmi->irq);
+	gpiod_direction_output(calib, 1);
+	tda998x_cec_set_calibration(priv, true);
+
+	local_irq_disable();
+	gpiod_set_value(calib, 0);
+	mdelay(10);
+	gpiod_set_value(calib, 1);
+	local_irq_enable();
+
+	tda998x_cec_set_calibration(priv, false);
+	gpiod_direction_input(calib);
+	if (priv->hdmi->irq > 0)
+		enable_irq(priv->hdmi->irq);
+	mutex_unlock(&priv->edid_mutex);
+}
+
+static int tda998x_cec_hook_init(void *data)
+{
+	struct tda998x_priv *priv = data;
+	struct gpio_desc *calib;
+
+	calib = gpiod_get(&priv->hdmi->dev, "nxp,calib", GPIOD_ASIS);
+	if (IS_ERR(calib)) {
+		dev_warn(&priv->hdmi->dev, "failed to get calibration gpio: %ld\n",
+			 PTR_ERR(calib));
+		return PTR_ERR(calib);
+	}
+
+	priv->calib = calib;
+
+	return 0;
+}
+
+static void tda998x_cec_hook_exit(void *data)
+{
+	struct tda998x_priv *priv = data;
+
+	gpiod_put(priv->calib);
+	priv->calib = NULL;
+}
+
+static int tda998x_cec_hook_open(void *data)
+{
+	struct tda998x_priv *priv = data;
+
+	cec_enamods(priv, CEC_ENAMODS_EN_CEC_CLK | CEC_ENAMODS_EN_CEC, true);
+	tda998x_cec_calibration(priv);
+
+	return 0;
+}
+
+static void tda998x_cec_hook_release(void *data)
+{
+	struct tda998x_priv *priv = data;
+
+	cec_enamods(priv, CEC_ENAMODS_EN_CEC_CLK | CEC_ENAMODS_EN_CEC, false);
+}
+
 static int
 set_page(struct tda998x_priv *priv, u16 reg)
 {
@@ -657,10 +780,13 @@ static irqreturn_t tda998x_irq_thread(int irq, void *data)
 			sta, cec, lvl, flag0, flag1, flag2);
 
 		if (cec & CEC_RXSHPDINT_HPD) {
-			if (lvl & CEC_RXSHPDLEV_HPD)
+			if (lvl & CEC_RXSHPDLEV_HPD) {
 				tda998x_edid_delay_start(priv);
-			else
+			} else {
 				schedule_work(&priv->detect_work);
+				cec_notifier_set_phys_addr(priv->cec_notify,
+						   CEC_PHYS_ADDR_INVALID);
+			}
 
 			handled = true;
 		}
@@ -981,6 +1107,8 @@ static int tda998x_connector_fill_modes(struct drm_connector *connector,
 	if (connector->edid_blob_ptr) {
 		struct edid *edid = (void *)connector->edid_blob_ptr->data;
 
+		cec_notifier_set_phys_addr_from_edid(priv->cec_notify, edid);
+
 		priv->sink_has_audio = drm_detect_monitor_audio(edid);
 	} else {
 		priv->sink_has_audio = false;
@@ -1024,6 +1152,8 @@ static int read_edid_block(void *data, u8 *buf, unsigned int blk, size_t length)
 	offset = (blk & 1) ? 128 : 0;
 	segptr = blk / 2;
 
+	mutex_lock(&priv->edid_mutex);
+
 	reg_write(priv, REG_DDC_ADDR, 0xa0);
 	reg_write(priv, REG_DDC_OFFS, offset);
 	reg_write(priv, REG_DDC_SEGM_ADDR, 0x60);
@@ -1043,14 +1173,15 @@ static int read_edid_block(void *data, u8 *buf, unsigned int blk, size_t length)
 					msecs_to_jiffies(100));
 		if (i < 0) {
 			dev_err(&priv->hdmi->dev, "read edid wait err %d\n", i);
-			return i;
+			ret = i;
+			goto failed;
 		}
 	} else {
 		for (i = 100; i > 0; i--) {
 			msleep(1);
 			ret = reg_read(priv, REG_INT_FLAGS_2);
 			if (ret < 0)
-				return ret;
+				goto failed;
 			if (ret & INT_FLAGS_2_EDID_BLK_RD)
 				break;
 		}
@@ -1058,17 +1189,22 @@ static int read_edid_block(void *data, u8 *buf, unsigned int blk, size_t length)
 
 	if (i == 0) {
 		dev_err(&priv->hdmi->dev, "read edid timeout\n");
-		return -ETIMEDOUT;
+		ret = -ETIMEDOUT;
+		goto failed;
 	}
 
 	ret = reg_read_range(priv, REG_EDID_DATA_0, buf, length);
 	if (ret != length) {
 		dev_err(&priv->hdmi->dev, "failed to read edid block %d: %d\n",
 			blk, ret);
-		return ret;
+		goto failed;
 	}
 
-	return 0;
+	ret = 0;
+
+ failed:
+	mutex_unlock(&priv->edid_mutex);
+	return ret;
 }
 
 static int tda998x_connector_get_modes(struct drm_connector *connector)
@@ -1106,7 +1242,7 @@ static int tda998x_connector_get_modes(struct drm_connector *connector)
 	return n;
 }
 
-static int tda998x_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status tda998x_connector_mode_valid(struct drm_connector *connector,
 					struct drm_display_mode *mode)
 {
 	/* TDA19988 dotclock can go up to 165MHz */
@@ -1423,6 +1559,9 @@ static void tda998x_destroy(struct tda998x_priv *priv)
 	cancel_work_sync(&priv->detect_work);
 
 	i2c_unregister_device(priv->cec);
+
+	if (priv->cec_notify)
+		cec_notifier_put(priv->cec_notify);
 }
 
 /* I2C driver functions */
@@ -1472,10 +1611,16 @@ static int tda998x_get_audio_ports(struct tda998x_priv *priv,
 static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 {
 	struct device_node *np = client->dev.of_node;
+	struct i2c_board_info cec_info;
 	u32 video;
 	int rev_lo, rev_hi, ret;
 
-	mutex_init(&priv->audio_mutex); /* Protect access from audio thread */
+	mutex_init(&priv->mutex);	/* protect the page access */
+	mutex_init(&priv->audio_mutex); /* protect access from audio thread */
+	mutex_init(&priv->edid_mutex);
+	init_waitqueue_head(&priv->edid_delay_waitq);
+	timer_setup(&priv->edid_delay_timer, tda998x_edid_delay_done, 0);
+	INIT_WORK(&priv->detect_work, tda998x_detect_work);
 
 	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(2) | VIP_CNTRL_0_SWAP_B(3);
 	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1);
@@ -1485,14 +1630,6 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	priv->cec_addr = 0x34 + (client->addr & 0x03);
 	priv->current_page = 0xff;
 	priv->hdmi = client;
-	priv->cec = i2c_new_dummy(client->adapter, priv->cec_addr);
-	if (!priv->cec)
-		return -ENODEV;
-
-	mutex_init(&priv->mutex);	/* protect the page access */
-	init_waitqueue_head(&priv->edid_delay_waitq);
-	timer_setup(&priv->edid_delay_timer, tda998x_edid_delay_done, 0);
-	INIT_WORK(&priv->detect_work, tda998x_detect_work);
 
 	/* wake up the device: */
 	cec_write(priv, REG_CEC_ENAMODS,
@@ -1502,10 +1639,15 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 
 	/* read version: */
 	rev_lo = reg_read(priv, REG_VERSION_LSB);
+	if (rev_lo < 0) {
+		dev_err(&client->dev, "failed to read version: %d\n", rev_lo);
+		return rev_lo;
+	}
+
 	rev_hi = reg_read(priv, REG_VERSION_MSB);
-	if (rev_lo < 0 || rev_hi < 0) {
-		ret = rev_lo < 0 ? rev_lo : rev_hi;
-		goto fail;
+	if (rev_hi < 0) {
+		dev_err(&client->dev, "failed to read version: %d\n", rev_hi);
+		return rev_hi;
 	}
 
 	priv->rev = rev_lo | rev_hi << 8;
@@ -1529,7 +1671,7 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	default:
 		dev_err(&client->dev, "found unsupported device: %04x\n",
 			priv->rev);
-		goto fail;
+		return -ENXIO;
 	}
 
 	/* after reset, enable DDC: */
@@ -1545,6 +1687,15 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	cec_write(priv, REG_CEC_FRO_IM_CLK_CTRL,
 			CEC_FRO_IM_CLK_CTRL_GHOST_DIS | CEC_FRO_IM_CLK_CTRL_IMCLK_SEL);
 
+	/* ensure interrupts are disabled */
+	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
+
+	/* clear pending interrupts */
+	cec_read(priv, REG_CEC_RXSHPDINT);
+	reg_read(priv, REG_INT_FLAGS_0);
+	reg_read(priv, REG_INT_FLAGS_1);
+	reg_read(priv, REG_INT_FLAGS_2);
+
 	/* initialize the optional IRQ */
 	if (client->irq) {
 		unsigned long irq_flags;
@@ -1552,13 +1703,11 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 		/* init read EDID waitqueue and HDP work */
 		init_waitqueue_head(&priv->wq_edid);
 
-		/* clear pending interrupts */
-		reg_read(priv, REG_INT_FLAGS_0);
-		reg_read(priv, REG_INT_FLAGS_1);
-		reg_read(priv, REG_INT_FLAGS_2);
-
 		irq_flags =
 			irqd_get_trigger_type(irq_get_irq_data(client->irq));
+
+		priv->cec_glue.irq_flags = irq_flags;
+
 		irq_flags |= IRQF_SHARED | IRQF_ONESHOT;
 		ret = request_threaded_irq(client->irq, NULL,
 					   tda998x_irq_thread, irq_flags,
@@ -1567,13 +1716,46 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 			dev_err(&client->dev,
 				"failed to request IRQ#%u: %d\n",
 				client->irq, ret);
-			goto fail;
+			goto err_irq;
 		}
 
 		/* enable HPD irq */
 		cec_write(priv, REG_CEC_RXSHPDINTENA, CEC_RXSHPDLEV_HPD);
 	}
 
+	priv->cec_notify = cec_notifier_get(&client->dev);
+	if (!priv->cec_notify) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	priv->cec_glue.parent = &client->dev;
+	priv->cec_glue.data = priv;
+	priv->cec_glue.init = tda998x_cec_hook_init;
+	priv->cec_glue.exit = tda998x_cec_hook_exit;
+	priv->cec_glue.open = tda998x_cec_hook_open;
+	priv->cec_glue.release = tda998x_cec_hook_release;
+
+	/*
+	 * Some TDA998x are actually two I2C devices merged onto one piece
+	 * of silicon: TDA9989 and TDA19989 combine the HDMI transmitter
+	 * with a slightly modified TDA9950 CEC device.  The CEC device
+	 * is at the TDA9950 address, with the address pins strapped across
+	 * to the TDA998x address pins.  Hence, it always has the same
+	 * offset.
+	 */
+	memset(&cec_info, 0, sizeof(cec_info));
+	strlcpy(cec_info.type, "tda9950", sizeof(cec_info.type));
+	cec_info.addr = priv->cec_addr;
+	cec_info.platform_data = &priv->cec_glue;
+	cec_info.irq = client->irq;
+
+	priv->cec = i2c_new_device(client->adapter, &cec_info);
+	if (!priv->cec) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
 	/* enable EDID read irq: */
 	reg_set(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
 
@@ -1596,12 +1778,18 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 		tda998x_audio_codec_init(priv, &client->dev);
 
 	return 0;
+
 fail:
 	/* if encoder_init fails, the encoder slave is never registered,
 	 * so cleanup here:
 	 */
 	i2c_unregister_device(priv->cec);
-	return -ENXIO;
+	if (priv->cec_notify)
+		cec_notifier_put(priv->cec_notify);
+	if (client->irq)
+		free_irq(client->irq, priv);
+err_irq:
+	return ret;
 }
 
 static void tda998x_encoder_prepare(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 108d21f34777..9de8b1c51a5c 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -25,7 +25,8 @@ config DRM_I915_DEBUG
         select X86_MSR # used by igt/pm_rpm
         select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
         select DRM_DEBUG_MM if DRM=y
-	select DRM_DEBUG_MM_SELFTEST
+        select STACKDEPOT if DRM=y # for DRM_DEBUG_MM
+	select DRM_DEBUG_SELFTEST
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
 	select DRM_I915_SW_FENCE_DEBUG_OBJECTS
 	select DRM_I915_SELFTEST
@@ -89,6 +90,18 @@ config DRM_I915_SW_FENCE_CHECK_DAG
 
           If in doubt, say "N".
 
+config DRM_I915_DEBUG_GUC
+        bool "Enable additional driver debugging for GuC"
+        depends on DRM_I915
+        default n
+        help
+          Choose this option to turn on extra driver debugging that may affect
+          performance but will help resolve GuC related issues.
+
+          Recommended for driver developers only.
+
+          If in doubt, say "N".
+
 config DRM_I915_SELFTEST
 	bool "Enable selftests upon driver load"
 	depends on DRM_I915
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 4eee91a3a236..4c6adae23e18 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -12,12 +12,16 @@
 # Note the danger in using -Wall -Wextra is that when CI updates gcc we
 # will most likely get a sudden build breakage... Hopefully we will fix
 # new warnings before CI updates!
-subdir-ccflags-y := -Wall -Wextra
+subdir-ccflags-y := -Wall -Wextra -Wvla
 subdir-ccflags-y += $(call cc-disable-warning, unused-parameter)
 subdir-ccflags-y += $(call cc-disable-warning, type-limits)
 subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers)
 subdir-ccflags-y += $(call cc-disable-warning, implicit-fallthrough)
 subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable)
+# clang warnings
+subdir-ccflags-y += $(call cc-disable-warning, sign-compare)
+subdir-ccflags-y += $(call cc-disable-warning, sometimes-uninitialized)
+subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides)
 subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror
 
 # Fine grained warnings disable
@@ -43,7 +47,8 @@ i915-y := i915_drv.o \
 	  intel_csr.o \
 	  intel_device_info.o \
 	  intel_pm.o \
-	  intel_runtime_pm.o
+	  intel_runtime_pm.o \
+	  intel_workarounds.o
 
 i915-$(CONFIG_COMPAT)   += i915_ioc32.o
 i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o intel_pipe_crc.o
@@ -66,11 +71,11 @@ i915-y += i915_cmd_parser.o \
 	  i915_gem_shrinker.o \
 	  i915_gem_stolen.o \
 	  i915_gem_tiling.o \
-	  i915_gem_timeline.o \
 	  i915_gem_userptr.o \
 	  i915_gemfs.o \
 	  i915_query.o \
 	  i915_request.o \
+	  i915_timeline.o \
 	  i915_trace_points.o \
 	  i915_vma.o \
 	  intel_breadcrumbs.o \
@@ -79,7 +84,8 @@ i915-y += i915_cmd_parser.o \
 	  intel_lrc.o \
 	  intel_mocs.o \
 	  intel_ringbuffer.o \
-	  intel_uncore.o
+	  intel_uncore.o \
+	  intel_wopcm.o
 
 # general-purpose microcontroller (GuC) support
 i915-y += intel_uc.o \
@@ -152,7 +158,8 @@ i915-y += dvo_ch7017.o \
 i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o
 i915-$(CONFIG_DRM_I915_SELFTEST) += \
 	selftests/i915_random.o \
-	selftests/i915_selftest.o
+	selftests/i915_selftest.o \
+	selftests/igt_flush_test.o
 
 # virtual gpu code
 i915-y += i915_vgpu.o
@@ -171,7 +178,8 @@ i915-y += i915_perf.o \
 	  i915_oa_glk.o \
 	  i915_oa_cflgt2.o \
 	  i915_oa_cflgt3.o \
-	  i915_oa_cnl.o
+	  i915_oa_cnl.o \
+	  i915_oa_icl.o
 
 ifeq ($(CONFIG_DRM_I915_GVT),y)
 i915-y += intel_gvt.o
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index db6b94dda5df..718ca08f9575 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -813,15 +813,31 @@ static inline bool is_force_nonpriv_mmio(unsigned int offset)
 }
 
 static int force_nonpriv_reg_handler(struct parser_exec_state *s,
-				     unsigned int offset, unsigned int index)
+		unsigned int offset, unsigned int index, char *cmd)
 {
 	struct intel_gvt *gvt = s->vgpu->gvt;
-	unsigned int data = cmd_val(s, index + 1);
+	unsigned int data;
+	u32 ring_base;
+	u32 nopid;
+	struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
+
+	if (!strcmp(cmd, "lri"))
+		data = cmd_val(s, index + 1);
+	else {
+		gvt_err("Unexpected forcenonpriv 0x%x write from cmd %s\n",
+			offset, cmd);
+		return -EINVAL;
+	}
+
+	ring_base = dev_priv->engine[s->ring_id]->mmio_base;
+	nopid = i915_mmio_reg_offset(RING_NOPID(ring_base));
 
-	if (!intel_gvt_in_force_nonpriv_whitelist(gvt, data)) {
+	if (!intel_gvt_in_force_nonpriv_whitelist(gvt, data) &&
+			data != nopid) {
 		gvt_err("Unexpected forcenonpriv 0x%x LRI write, value=0x%x\n",
 			offset, data);
-		return -EPERM;
+		patch_value(s, cmd_ptr(s, index), nopid);
+		return 0;
 	}
 	return 0;
 }
@@ -869,7 +885,7 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 		return -EINVAL;
 
 	if (is_force_nonpriv_mmio(offset) &&
-		force_nonpriv_reg_handler(s, offset, index))
+		force_nonpriv_reg_handler(s, offset, index, cmd))
 		return -EPERM;
 
 	if (offset == i915_mmio_reg_offset(DERRMR) ||
@@ -1080,6 +1096,7 @@ static int cmd_handler_mi_user_interrupt(struct parser_exec_state *s)
 {
 	set_bit(cmd_interrupt_events[s->ring_id].mi_user_interrupt,
 			s->workload->pending_events);
+	patch_value(s, cmd_ptr(s, 0), MI_NOOP);
 	return 0;
 }
 
@@ -1603,7 +1620,8 @@ static int batch_buffer_needs_scan(struct parser_exec_state *s)
 	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
 		|| IS_KABYLAKE(gvt->dev_priv)) {
 		/* BDW decides privilege based on address space */
-		if (cmd_val(s, 0) & (1 << 8))
+		if (cmd_val(s, 0) & (1 << 8) &&
+			!(s->vgpu->scan_nonprivbb & (1 << s->ring_id)))
 			return 0;
 	}
 	return 1;
@@ -1617,6 +1635,8 @@ static int find_bb_size(struct parser_exec_state *s, unsigned long *bb_size)
 	bool bb_end = false;
 	struct intel_vgpu *vgpu = s->vgpu;
 	u32 cmd;
+	struct intel_vgpu_mm *mm = (s->buf_addr_type == GTT_BUFFER) ?
+		s->vgpu->gtt.ggtt_mm : s->workload->shadow_mm;
 
 	*bb_size = 0;
 
@@ -1628,18 +1648,22 @@ static int find_bb_size(struct parser_exec_state *s, unsigned long *bb_size)
 	cmd = cmd_val(s, 0);
 	info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
 	if (info == NULL) {
-		gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
-				cmd, get_opcode(cmd, s->ring_id));
+		gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x, addr_type=%s, ring %d, workload=%p\n",
+				cmd, get_opcode(cmd, s->ring_id),
+				(s->buf_addr_type == PPGTT_BUFFER) ?
+				"ppgtt" : "ggtt", s->ring_id, s->workload);
 		return -EBADRQC;
 	}
 	do {
-		if (copy_gma_to_hva(s->vgpu, s->vgpu->gtt.ggtt_mm,
+		if (copy_gma_to_hva(s->vgpu, mm,
 				gma, gma + 4, &cmd) < 0)
 			return -EFAULT;
 		info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
 		if (info == NULL) {
-			gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
-				cmd, get_opcode(cmd, s->ring_id));
+			gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x, addr_type=%s, ring %d, workload=%p\n",
+				cmd, get_opcode(cmd, s->ring_id),
+				(s->buf_addr_type == PPGTT_BUFFER) ?
+				"ppgtt" : "ggtt", s->ring_id, s->workload);
 			return -EBADRQC;
 		}
 
@@ -1665,6 +1689,9 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	unsigned long gma = 0;
 	unsigned long bb_size;
 	int ret = 0;
+	struct intel_vgpu_mm *mm = (s->buf_addr_type == GTT_BUFFER) ?
+		s->vgpu->gtt.ggtt_mm : s->workload->shadow_mm;
+	unsigned long gma_start_offset = 0;
 
 	/* get the start gm address of the batch buffer */
 	gma = get_gma_bb_from_cmd(s, 1);
@@ -1679,8 +1706,24 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	if (!bb)
 		return -ENOMEM;
 
+	bb->ppgtt = (s->buf_addr_type == GTT_BUFFER) ? false : true;
+
+	/* the gma_start_offset stores the batch buffer's start gma's
+	 * offset relative to page boundary. so for non-privileged batch
+	 * buffer, the shadowed gem object holds exactly the same page
+	 * layout as original gem object. This is for the convience of
+	 * replacing the whole non-privilged batch buffer page to this
+	 * shadowed one in PPGTT at the same gma address. (this replacing
+	 * action is not implemented yet now, but may be necessary in
+	 * future).
+	 * for prileged batch buffer, we just change start gma address to
+	 * that of shadowed page.
+	 */
+	if (bb->ppgtt)
+		gma_start_offset = gma & ~I915_GTT_PAGE_MASK;
+
 	bb->obj = i915_gem_object_create(s->vgpu->gvt->dev_priv,
-					 roundup(bb_size, PAGE_SIZE));
+			 roundup(bb_size + gma_start_offset, PAGE_SIZE));
 	if (IS_ERR(bb->obj)) {
 		ret = PTR_ERR(bb->obj);
 		goto err_free_bb;
@@ -1701,9 +1744,9 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 		bb->clflush &= ~CLFLUSH_BEFORE;
 	}
 
-	ret = copy_gma_to_hva(s->vgpu, s->vgpu->gtt.ggtt_mm,
+	ret = copy_gma_to_hva(s->vgpu, mm,
 			      gma, gma + bb_size,
-			      bb->va);
+			      bb->va + gma_start_offset);
 	if (ret < 0) {
 		gvt_vgpu_err("fail to copy guest ring buffer\n");
 		ret = -EFAULT;
@@ -1729,7 +1772,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	 * buffer's gma in pair. After all, we don't want to pin the shadow
 	 * buffer here (too early).
 	 */
-	s->ip_va = bb->va;
+	s->ip_va = bb->va + gma_start_offset;
 	s->ip_gma = gma;
 	return 0;
 err_unmap:
@@ -2468,15 +2511,18 @@ static int cmd_parser_exec(struct parser_exec_state *s)
 
 	info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
 	if (info == NULL) {
-		gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
-				cmd, get_opcode(cmd, s->ring_id));
+		gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x, addr_type=%s, ring %d, workload=%p\n",
+				cmd, get_opcode(cmd, s->ring_id),
+				(s->buf_addr_type == PPGTT_BUFFER) ?
+				"ppgtt" : "ggtt", s->ring_id, s->workload);
 		return -EBADRQC;
 	}
 
 	s->info = info;
 
 	trace_gvt_command(vgpu->id, s->ring_id, s->ip_gma, s->ip_va,
-			  cmd_length(s), s->buf_type);
+			  cmd_length(s), s->buf_type, s->buf_addr_type,
+			  s->workload, info->name);
 
 	if (info->handler) {
 		ret = info->handler(s);
diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index 32a66dfdf112..2ec89bcb59f1 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -122,18 +122,69 @@ static int vgpu_mmio_diff_show(struct seq_file *s, void *unused)
 	seq_printf(s, "Total: %d, Diff: %d\n", param.total, param.diff);
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(vgpu_mmio_diff);
 
-static int vgpu_mmio_diff_open(struct inode *inode, struct file *file)
+static int
+vgpu_scan_nonprivbb_get(void *data, u64 *val)
 {
-	return single_open(file, vgpu_mmio_diff_show, inode->i_private);
+	struct intel_vgpu *vgpu = (struct intel_vgpu *)data;
+	*val = vgpu->scan_nonprivbb;
+	return 0;
 }
 
-static const struct file_operations vgpu_mmio_diff_fops = {
-	.open		= vgpu_mmio_diff_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+/*
+ * set/unset bit engine_id of vgpu->scan_nonprivbb to turn on/off scanning
+ * of non-privileged batch buffer. e.g.
+ * if vgpu->scan_nonprivbb=3, then it will scan non-privileged batch buffer
+ * on engine 0 and 1.
+ */
+static int
+vgpu_scan_nonprivbb_set(void *data, u64 val)
+{
+	struct intel_vgpu *vgpu = (struct intel_vgpu *)data;
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+	enum intel_engine_id id;
+	char buf[128], *s;
+	int len;
+
+	val &= (1 << I915_NUM_ENGINES) - 1;
+
+	if (vgpu->scan_nonprivbb == val)
+		return 0;
+
+	if (!val)
+		goto done;
+
+	len = sprintf(buf,
+		"gvt: vgpu %d turns on non-privileged batch buffers scanning on Engines:",
+		vgpu->id);
+
+	s = buf + len;
+
+	for (id = 0; id < I915_NUM_ENGINES; id++) {
+		struct intel_engine_cs *engine;
+
+		engine = dev_priv->engine[id];
+		if (engine && (val & (1 << id))) {
+			len = snprintf(s, 4, "%d, ", engine->id);
+			s += len;
+		} else
+			val &=  ~(1 << id);
+	}
+
+	if (val)
+		sprintf(s, "low performance expected.");
+
+	pr_warn("%s\n", buf);
+
+done:
+	vgpu->scan_nonprivbb = val;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vgpu_scan_nonprivbb_fops,
+			vgpu_scan_nonprivbb_get, vgpu_scan_nonprivbb_set,
+			"0x%llx\n");
 
 /**
  * intel_gvt_debugfs_add_vgpu - register debugfs entries for a vGPU
@@ -162,6 +213,11 @@ int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu)
 	if (!ent)
 		return -ENOMEM;
 
+	ent = debugfs_create_file("scan_nonprivbb", 0644, vgpu->debugfs,
+				 vgpu, &vgpu_scan_nonprivbb_fops);
+	if (!ent)
+		return -ENOMEM;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index dd96ffc878ac..6d8180e8d1e2 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -169,6 +169,8 @@ static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = {
 static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+	int pipe;
+
 	vgpu_vreg_t(vgpu, SDEISR) &= ~(SDE_PORTB_HOTPLUG_CPT |
 			SDE_PORTC_HOTPLUG_CPT |
 			SDE_PORTD_HOTPLUG_CPT);
@@ -267,6 +269,14 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	if (IS_BROADWELL(dev_priv))
 		vgpu_vreg_t(vgpu, PCH_ADPA) &= ~ADPA_CRT_HOTPLUG_MONITOR_MASK;
 
+	/* Disable Primary/Sprite/Cursor plane */
+	for_each_pipe(dev_priv, pipe) {
+		vgpu_vreg_t(vgpu, DSPCNTR(pipe)) &= ~DISPLAY_PLANE_ENABLE;
+		vgpu_vreg_t(vgpu, SPRCTL(pipe)) &= ~SPRITE_ENABLE;
+		vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~CURSOR_MODE;
+		vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= CURSOR_MODE_DISABLE;
+	}
+
 	vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index b555eb26f9ce..6f4f8e941fc2 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -323,6 +323,7 @@ static void update_fb_info(struct vfio_device_gfx_plane_info *gvt_dmabuf,
 		      struct intel_vgpu_fb_info *fb_info)
 {
 	gvt_dmabuf->drm_format = fb_info->drm_format;
+	gvt_dmabuf->drm_format_mod = fb_info->drm_format_mod;
 	gvt_dmabuf->width = fb_info->width;
 	gvt_dmabuf->height = fb_info->height;
 	gvt_dmabuf->stride = fb_info->stride;
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c
index 6b50fe78dc1b..1c120683e958 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.c
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c
@@ -245,16 +245,13 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 	plane->hw_format = fmt;
 
 	plane->base = vgpu_vreg_t(vgpu, DSPSURF(pipe)) & I915_GTT_PAGE_MASK;
-	if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
-		gvt_vgpu_err("invalid gma address: %lx\n",
-			     (unsigned long)plane->base);
+	if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
 		return  -EINVAL;
-	}
 
 	plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
 	if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
-		gvt_vgpu_err("invalid gma address: %lx\n",
-				(unsigned long)plane->base);
+		gvt_vgpu_err("Translate primary plane gma 0x%x to gpa fail\n",
+				plane->base);
 		return  -EINVAL;
 	}
 
@@ -371,16 +368,13 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu,
 			alpha_plane, alpha_force);
 
 	plane->base = vgpu_vreg_t(vgpu, CURBASE(pipe)) & I915_GTT_PAGE_MASK;
-	if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
-		gvt_vgpu_err("invalid gma address: %lx\n",
-			     (unsigned long)plane->base);
+	if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
 		return  -EINVAL;
-	}
 
 	plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
 	if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
-		gvt_vgpu_err("invalid gma address: %lx\n",
-				(unsigned long)plane->base);
+		gvt_vgpu_err("Translate cursor plane gma 0x%x to gpa fail\n",
+				plane->base);
 		return  -EINVAL;
 	}
 
@@ -476,16 +470,13 @@ int intel_vgpu_decode_sprite_plane(struct intel_vgpu *vgpu,
 	plane->drm_format = drm_format;
 
 	plane->base = vgpu_vreg_t(vgpu, SPRSURF(pipe)) & I915_GTT_PAGE_MASK;
-	if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
-		gvt_vgpu_err("invalid gma address: %lx\n",
-			     (unsigned long)plane->base);
+	if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
 		return  -EINVAL;
-	}
 
 	plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
 	if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
-		gvt_vgpu_err("invalid gma address: %lx\n",
-				(unsigned long)plane->base);
+		gvt_vgpu_err("Translate sprite plane gma 0x%x to gpa fail\n",
+				plane->base);
 		return  -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index d29281231507..78e55aafc8bc 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -530,6 +530,16 @@ static void ggtt_set_guest_entry(struct intel_vgpu_mm *mm,
 			   false, 0, mm->vgpu);
 }
 
+static void ggtt_get_host_entry(struct intel_vgpu_mm *mm,
+		struct intel_gvt_gtt_entry *entry, unsigned long index)
+{
+	struct intel_gvt_gtt_pte_ops *pte_ops = mm->vgpu->gvt->gtt.pte_ops;
+
+	GEM_BUG_ON(mm->type != INTEL_GVT_MM_GGTT);
+
+	pte_ops->get_entry(NULL, entry, index, false, 0, mm->vgpu);
+}
+
 static void ggtt_set_host_entry(struct intel_vgpu_mm *mm,
 		struct intel_gvt_gtt_entry *entry, unsigned long index)
 {
@@ -1818,6 +1828,18 @@ int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, unsigned int off,
 	return ret;
 }
 
+static void ggtt_invalidate_pte(struct intel_vgpu *vgpu,
+		struct intel_gvt_gtt_entry *entry)
+{
+	struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
+	unsigned long pfn;
+
+	pfn = pte_ops->get_pfn(entry);
+	if (pfn != vgpu->gvt->gtt.scratch_mfn)
+		intel_gvt_hypervisor_dma_unmap_guest_page(vgpu,
+						pfn << PAGE_SHIFT);
+}
+
 static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	void *p_data, unsigned int bytes)
 {
@@ -1844,10 +1866,10 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 
 	memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data,
 			bytes);
-	m = e;
 
 	if (ops->test_present(&e)) {
 		gfn = ops->get_pfn(&e);
+		m = e;
 
 		/* one PTE update may be issued in multiple writes and the
 		 * first write may not construct a valid gfn
@@ -1868,8 +1890,12 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 			ops->set_pfn(&m, gvt->gtt.scratch_mfn);
 		} else
 			ops->set_pfn(&m, dma_addr >> PAGE_SHIFT);
-	} else
+	} else {
+		ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index);
+		ggtt_invalidate_pte(vgpu, &m);
 		ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+		ops->clear_present(&m);
+	}
 
 out:
 	ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index);
@@ -2030,7 +2056,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
 		return PTR_ERR(gtt->ggtt_mm);
 	}
 
-	intel_vgpu_reset_ggtt(vgpu);
+	intel_vgpu_reset_ggtt(vgpu, false);
 
 	return create_scratch_page_tree(vgpu);
 }
@@ -2315,17 +2341,19 @@ void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu)
 /**
  * intel_vgpu_reset_ggtt - reset the GGTT entry
  * @vgpu: a vGPU
+ * @invalidate_old: invalidate old entries
  *
  * This function is called at the vGPU create stage
  * to reset all the GGTT entries.
  *
  */
-void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu)
+void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
 	struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry entry = {.type = GTT_TYPE_GGTT_PTE};
+	struct intel_gvt_gtt_entry old_entry;
 	u32 index;
 	u32 num_entries;
 
@@ -2334,13 +2362,23 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu)
 
 	index = vgpu_aperture_gmadr_base(vgpu) >> PAGE_SHIFT;
 	num_entries = vgpu_aperture_sz(vgpu) >> PAGE_SHIFT;
-	while (num_entries--)
+	while (num_entries--) {
+		if (invalidate_old) {
+			ggtt_get_host_entry(vgpu->gtt.ggtt_mm, &old_entry, index);
+			ggtt_invalidate_pte(vgpu, &old_entry);
+		}
 		ggtt_set_host_entry(vgpu->gtt.ggtt_mm, &entry, index++);
+	}
 
 	index = vgpu_hidden_gmadr_base(vgpu) >> PAGE_SHIFT;
 	num_entries = vgpu_hidden_sz(vgpu) >> PAGE_SHIFT;
-	while (num_entries--)
+	while (num_entries--) {
+		if (invalidate_old) {
+			ggtt_get_host_entry(vgpu->gtt.ggtt_mm, &old_entry, index);
+			ggtt_invalidate_pte(vgpu, &old_entry);
+		}
 		ggtt_set_host_entry(vgpu->gtt.ggtt_mm, &entry, index++);
+	}
 
 	ggtt_invalidate(dev_priv);
 }
@@ -2360,5 +2398,5 @@ void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu)
 	 * removing the shadow pages.
 	 */
 	intel_vgpu_destroy_all_ppgtt_mm(vgpu);
-	intel_vgpu_reset_ggtt(vgpu);
+	intel_vgpu_reset_ggtt(vgpu, true);
 }
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index a8b369cd352b..3792f2b7f4ff 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -193,7 +193,7 @@ struct intel_vgpu_gtt {
 
 extern int intel_vgpu_init_gtt(struct intel_vgpu *vgpu);
 extern void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu);
-void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu);
+void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old);
 void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu);
 
 extern int intel_gvt_init_gtt(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index efacd8abbedc..05d15a095310 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -99,7 +99,6 @@ struct intel_vgpu_fence {
 struct intel_vgpu_mmio {
 	void *vreg;
 	void *sreg;
-	bool disable_warn_untrack;
 };
 
 #define INTEL_GVT_MAX_BAR_NUM 4
@@ -226,6 +225,7 @@ struct intel_vgpu {
 
 	struct completion vblank_done;
 
+	u32 scan_nonprivbb;
 };
 
 /* validating GM healthy status*/
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 8c5d5d005854..4b6532fb789a 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -191,6 +191,8 @@ static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
 	unsigned int max_fence = vgpu_fence_sz(vgpu);
 
 	if (fence_num >= max_fence) {
+		gvt_vgpu_err("access oob fence reg %d/%d\n",
+			     fence_num, max_fence);
 
 		/* When guest access oob fence regs without access
 		 * pv_info first, we treat guest not supporting GVT,
@@ -200,11 +202,6 @@ static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
 			enter_failsafe_mode(vgpu,
 					GVT_FAILSAFE_UNSUPPORTED_GUEST);
 
-		if (!vgpu->mmio.disable_warn_untrack) {
-			gvt_vgpu_err("found oob fence register access\n");
-			gvt_vgpu_err("total fence %d, access fence %d\n",
-				     max_fence, fence_num);
-		}
 		memset(p_data, 0, bytes);
 		return -EINVAL;
 	}
@@ -477,22 +474,28 @@ static int force_nonpriv_write(struct intel_vgpu *vgpu,
 	unsigned int offset, void *p_data, unsigned int bytes)
 {
 	u32 reg_nonpriv = *(u32 *)p_data;
+	int ring_id = intel_gvt_render_mmio_to_ring_id(vgpu->gvt, offset);
+	u32 ring_base;
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int ret = -EINVAL;
 
-	if ((bytes != 4) || ((offset & (bytes - 1)) != 0)) {
-		gvt_err("vgpu(%d) Invalid FORCE_NONPRIV offset %x(%dB)\n",
-			vgpu->id, offset, bytes);
+	if ((bytes != 4) || ((offset & (bytes - 1)) != 0) || ring_id < 0) {
+		gvt_err("vgpu(%d) ring %d Invalid FORCE_NONPRIV offset %x(%dB)\n",
+			vgpu->id, ring_id, offset, bytes);
 		return ret;
 	}
 
-	if (in_whitelist(reg_nonpriv)) {
+	ring_base = dev_priv->engine[ring_id]->mmio_base;
+
+	if (in_whitelist(reg_nonpriv) ||
+		reg_nonpriv == i915_mmio_reg_offset(RING_NOPID(ring_base))) {
 		ret = intel_vgpu_default_mmio_write(vgpu, offset, p_data,
 			bytes);
-	} else {
-		gvt_err("vgpu(%d) Invalid FORCE_NONPRIV write %x\n",
-			vgpu->id, reg_nonpriv);
-	}
-	return ret;
+	} else
+		gvt_err("vgpu(%d) Invalid FORCE_NONPRIV write %x at offset %x\n",
+			vgpu->id, reg_nonpriv, offset);
+
+	return 0;
 }
 
 static int ddi_buf_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
@@ -1150,6 +1153,7 @@ static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification)
 	switch (notification) {
 	case VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE:
 		root_entry_type = GTT_TYPE_PPGTT_ROOT_L3_ENTRY;
+		/* fall through */
 	case VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE:
 		mm = intel_vgpu_get_ppgtt_mm(vgpu, root_entry_type, pdps);
 		return PTR_ERR_OR_ZERO(mm);
@@ -3091,9 +3095,7 @@ int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset,
 	 */
 	mmio_info = find_mmio_info(gvt, offset);
 	if (!mmio_info) {
-		if (!vgpu->mmio.disable_warn_untrack)
-			gvt_vgpu_err("untracked MMIO %08x len %d\n",
-				     offset, bytes);
+		gvt_dbg_mmio("untracked MMIO %08x len %d\n", offset, bytes);
 		goto default_rw;
 	}
 
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index c16a492449d7..1466d8769ec9 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1301,7 +1301,7 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 
 	}
 
-	return 0;
+	return -ENOTTY;
 }
 
 static ssize_t
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 11b71b33f1c0..e4960aff68bd 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -244,8 +244,6 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu, bool dmlr)
 
 		/* set the bit 0:2(Core C-State ) to C0 */
 		vgpu_vreg_t(vgpu, GEN6_GT_CORE_STATUS) = 0;
-
-		vgpu->mmio.disable_warn_untrack = false;
 	} else {
 #define GVT_GEN8_MMIO_RESET_OFFSET		(0x44200)
 		/* only reset the engine related, so starting with 0x44200
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index a5bac83d53a9..0f949554d118 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -448,7 +448,7 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 
 bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id)
 {
-	u32 *reg_state = ctx->engine[ring_id].lrc_reg_state;
+	u32 *reg_state = ctx->__engine[ring_id].lrc_reg_state;
 	u32 inhibit_mask =
 		_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
 
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index 75b7bc7b344c..d053cbe1dc94 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -53,7 +53,6 @@ struct vgpu_sched_data {
 	bool active;
 
 	ktime_t sched_in_time;
-	ktime_t sched_out_time;
 	ktime_t sched_time;
 	ktime_t left_ts;
 	ktime_t allocated_ts;
@@ -66,17 +65,22 @@ struct gvt_sched_data {
 	struct hrtimer timer;
 	unsigned long period;
 	struct list_head lru_runq_head;
+	ktime_t expire_time;
 };
 
-static void vgpu_update_timeslice(struct intel_vgpu *pre_vgpu)
+static void vgpu_update_timeslice(struct intel_vgpu *vgpu, ktime_t cur_time)
 {
 	ktime_t delta_ts;
-	struct vgpu_sched_data *vgpu_data = pre_vgpu->sched_data;
+	struct vgpu_sched_data *vgpu_data;
 
-	delta_ts = vgpu_data->sched_out_time - vgpu_data->sched_in_time;
+	if (!vgpu || vgpu == vgpu->gvt->idle_vgpu)
+		return;
 
-	vgpu_data->sched_time += delta_ts;
-	vgpu_data->left_ts -= delta_ts;
+	vgpu_data = vgpu->sched_data;
+	delta_ts = ktime_sub(cur_time, vgpu_data->sched_in_time);
+	vgpu_data->sched_time = ktime_add(vgpu_data->sched_time, delta_ts);
+	vgpu_data->left_ts = ktime_sub(vgpu_data->left_ts, delta_ts);
+	vgpu_data->sched_in_time = cur_time;
 }
 
 #define GVT_TS_BALANCE_PERIOD_MS 100
@@ -150,11 +154,7 @@ static void try_to_schedule_next_vgpu(struct intel_gvt *gvt)
 	}
 
 	cur_time = ktime_get();
-	if (scheduler->current_vgpu) {
-		vgpu_data = scheduler->current_vgpu->sched_data;
-		vgpu_data->sched_out_time = cur_time;
-		vgpu_update_timeslice(scheduler->current_vgpu);
-	}
+	vgpu_update_timeslice(scheduler->current_vgpu, cur_time);
 	vgpu_data = scheduler->next_vgpu->sched_data;
 	vgpu_data->sched_in_time = cur_time;
 
@@ -226,17 +226,22 @@ out:
 void intel_gvt_schedule(struct intel_gvt *gvt)
 {
 	struct gvt_sched_data *sched_data = gvt->scheduler.sched_data;
-	static uint64_t timer_check;
+	ktime_t cur_time;
 
 	mutex_lock(&gvt->lock);
+	cur_time = ktime_get();
 
 	if (test_and_clear_bit(INTEL_GVT_REQUEST_SCHED,
 				(void *)&gvt->service_request)) {
-		if (!(timer_check++ % GVT_TS_BALANCE_PERIOD_MS))
+		if (cur_time >= sched_data->expire_time) {
 			gvt_balance_timeslice(sched_data);
+			sched_data->expire_time = ktime_add_ms(
+				cur_time, GVT_TS_BALANCE_PERIOD_MS);
+		}
 	}
 	clear_bit(INTEL_GVT_REQUEST_EVENT_SCHED, (void *)&gvt->service_request);
 
+	vgpu_update_timeslice(gvt->scheduler.current_vgpu, cur_time);
 	tbs_sched_func(sched_data);
 
 	mutex_unlock(&gvt->lock);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 638abe84857c..c2d183b91500 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -58,7 +58,7 @@ static void update_shadow_pdps(struct intel_vgpu_workload *workload)
 	int ring_id = workload->ring_id;
 	struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->engine[ring_id].state->obj;
+		shadow_ctx->__engine[ring_id].state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 
@@ -97,7 +97,7 @@ static void sr_oa_regs(struct intel_vgpu_workload *workload,
 		i915_mmio_reg_offset(EU_PERF_CNTL6),
 	};
 
-	if (!workload || !reg_state || workload->ring_id != RCS)
+	if (workload->ring_id != RCS)
 		return;
 
 	if (save) {
@@ -130,7 +130,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	int ring_id = workload->ring_id;
 	struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->engine[ring_id].state->obj;
+		shadow_ctx->__engine[ring_id].state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *dst;
@@ -283,7 +283,7 @@ static int shadow_context_status_change(struct notifier_block *nb,
 static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
 		struct intel_engine_cs *engine)
 {
-	struct intel_context *ce = &ctx->engine[engine->id];
+	struct intel_context *ce = to_intel_context(ctx, engine);
 	u64 desc = 0;
 
 	desc = ce->lrc_desc;
@@ -389,7 +389,7 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 	 * shadow_ctx pages invalid. So gvt need to pin itself. After update
 	 * the guest context, gvt can unpin the shadow_ctx safely.
 	 */
-	ring = engine->context_pin(engine, shadow_ctx);
+	ring = intel_context_pin(shadow_ctx, engine);
 	if (IS_ERR(ring)) {
 		ret = PTR_ERR(ring);
 		gvt_vgpu_err("fail to pin shadow context\n");
@@ -403,7 +403,7 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 	return 0;
 
 err_unpin:
-	engine->context_unpin(engine, shadow_ctx);
+	intel_context_unpin(shadow_ctx, engine);
 err_shadow:
 	release_shadow_wa_ctx(&workload->wa_ctx);
 err_scan:
@@ -437,7 +437,7 @@ static int intel_gvt_generate_request(struct intel_vgpu_workload *workload)
 	return 0;
 
 err_unpin:
-	engine->context_unpin(engine, shadow_ctx);
+	intel_context_unpin(shadow_ctx, engine);
 	release_shadow_wa_ctx(&workload->wa_ctx);
 	return ret;
 }
@@ -452,12 +452,6 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 	int ret;
 
 	list_for_each_entry(bb, &workload->shadow_bb, list) {
-		bb->vma = i915_gem_object_ggtt_pin(bb->obj, NULL, 0, 0, 0);
-		if (IS_ERR(bb->vma)) {
-			ret = PTR_ERR(bb->vma);
-			goto err;
-		}
-
 		/* For privilge batch buffer and not wa_ctx, the bb_start_cmd_va
 		 * is only updated into ring_scan_buffer, not real ring address
 		 * allocated in later copy_workload_to_ring_buffer. pls be noted
@@ -469,25 +463,53 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 			bb->bb_start_cmd_va = workload->shadow_ring_buffer_va
 				+ bb->bb_offset;
 
-		/* relocate shadow batch buffer */
-		bb->bb_start_cmd_va[1] = i915_ggtt_offset(bb->vma);
-		if (gmadr_bytes == 8)
-			bb->bb_start_cmd_va[2] = 0;
+		if (bb->ppgtt) {
+			/* for non-priv bb, scan&shadow is only for
+			 * debugging purpose, so the content of shadow bb
+			 * is the same as original bb. Therefore,
+			 * here, rather than switch to shadow bb's gma
+			 * address, we directly use original batch buffer's
+			 * gma address, and send original bb to hardware
+			 * directly
+			 */
+			if (bb->clflush & CLFLUSH_AFTER) {
+				drm_clflush_virt_range(bb->va,
+						bb->obj->base.size);
+				bb->clflush &= ~CLFLUSH_AFTER;
+			}
+			i915_gem_obj_finish_shmem_access(bb->obj);
+			bb->accessing = false;
+
+		} else {
+			bb->vma = i915_gem_object_ggtt_pin(bb->obj,
+					NULL, 0, 0, 0);
+			if (IS_ERR(bb->vma)) {
+				ret = PTR_ERR(bb->vma);
+				goto err;
+			}
 
-		/* No one is going to touch shadow bb from now on. */
-		if (bb->clflush & CLFLUSH_AFTER) {
-			drm_clflush_virt_range(bb->va, bb->obj->base.size);
-			bb->clflush &= ~CLFLUSH_AFTER;
-		}
+			/* relocate shadow batch buffer */
+			bb->bb_start_cmd_va[1] = i915_ggtt_offset(bb->vma);
+			if (gmadr_bytes == 8)
+				bb->bb_start_cmd_va[2] = 0;
 
-		ret = i915_gem_object_set_to_gtt_domain(bb->obj, false);
-		if (ret)
-			goto err;
+			/* No one is going to touch shadow bb from now on. */
+			if (bb->clflush & CLFLUSH_AFTER) {
+				drm_clflush_virt_range(bb->va,
+						bb->obj->base.size);
+				bb->clflush &= ~CLFLUSH_AFTER;
+			}
 
-		i915_gem_obj_finish_shmem_access(bb->obj);
-		bb->accessing = false;
+			ret = i915_gem_object_set_to_gtt_domain(bb->obj,
+					false);
+			if (ret)
+				goto err;
 
-		i915_vma_move_to_active(bb->vma, workload->req, 0);
+			i915_gem_obj_finish_shmem_access(bb->obj);
+			bb->accessing = false;
+
+			i915_vma_move_to_active(bb->vma, workload->req, 0);
+		}
 	}
 	return 0;
 err:
@@ -504,7 +526,7 @@ static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	struct intel_vgpu_submission *s = &workload->vgpu->submission;
 	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->engine[ring_id].state->obj;
+		shadow_ctx->__engine[ring_id].state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 
@@ -666,7 +688,7 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 
 	ret = prepare_workload(workload);
 	if (ret) {
-		engine->context_unpin(engine, shadow_ctx);
+		intel_context_unpin(shadow_ctx, engine);
 		goto out;
 	}
 
@@ -749,7 +771,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
 	int ring_id = workload->ring_id;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->engine[ring_id].state->obj;
+		shadow_ctx->__engine[ring_id].state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *src;
@@ -876,7 +898,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 		}
 		mutex_lock(&dev_priv->drm.struct_mutex);
 		/* unpin shadow ctx as the shadow_ctx update is done */
-		engine->context_unpin(engine, s->shadow_ctx);
+		intel_context_unpin(s->shadow_ctx, engine);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
 	}
 
@@ -1134,9 +1156,6 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	if (IS_ERR(s->shadow_ctx))
 		return PTR_ERR(s->shadow_ctx);
 
-	if (HAS_LOGICAL_RING_PREEMPTION(vgpu->gvt->dev_priv))
-		s->shadow_ctx->priority = INT_MAX;
-
 	bitmap_zero(s->shadow_ctx_desc_updated, I915_NUM_ENGINES);
 
 	s->workloads = kmem_cache_create_usercopy("gvt-g_vgpu_workload",
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 486ed57a4ad1..6c644782193e 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -125,6 +125,7 @@ struct intel_vgpu_shadow_bb {
 	unsigned int clflush;
 	bool accessing;
 	unsigned long bb_offset;
+	bool ppgtt;
 };
 
 #define workload_q_head(vgpu, ring_id) \
diff --git a/drivers/gpu/drm/i915/gvt/trace.h b/drivers/gpu/drm/i915/gvt/trace.h
index 82093f1e8612..1fd64202d74e 100644
--- a/drivers/gpu/drm/i915/gvt/trace.h
+++ b/drivers/gpu/drm/i915/gvt/trace.h
@@ -224,19 +224,25 @@ TRACE_EVENT(oos_sync,
 	TP_printk("%s", __entry->buf)
 );
 
+#define GVT_CMD_STR_LEN 40
 TRACE_EVENT(gvt_command,
-	TP_PROTO(u8 vgpu_id, u8 ring_id, u32 ip_gma, u32 *cmd_va, u32 cmd_len,
-		 u32 buf_type),
+	TP_PROTO(u8 vgpu_id, u8 ring_id, u32 ip_gma, u32 *cmd_va,
+		u32 cmd_len,  u32 buf_type, u32 buf_addr_type,
+		void *workload, char *cmd_name),
 
-	TP_ARGS(vgpu_id, ring_id, ip_gma, cmd_va, cmd_len, buf_type),
+	TP_ARGS(vgpu_id, ring_id, ip_gma, cmd_va, cmd_len, buf_type,
+		buf_addr_type, workload, cmd_name),
 
 	TP_STRUCT__entry(
 		__field(u8, vgpu_id)
 		__field(u8, ring_id)
 		__field(u32, ip_gma)
 		__field(u32, buf_type)
+		__field(u32, buf_addr_type)
 		__field(u32, cmd_len)
+		__field(void*, workload)
 		__dynamic_array(u32, raw_cmd, cmd_len)
+		__array(char, cmd_name, GVT_CMD_STR_LEN)
 	),
 
 	TP_fast_assign(
@@ -244,17 +250,25 @@ TRACE_EVENT(gvt_command,
 		__entry->ring_id = ring_id;
 		__entry->ip_gma = ip_gma;
 		__entry->buf_type = buf_type;
+		__entry->buf_addr_type = buf_addr_type;
 		__entry->cmd_len = cmd_len;
+		__entry->workload = workload;
+		snprintf(__entry->cmd_name, GVT_CMD_STR_LEN, "%s", cmd_name);
 		memcpy(__get_dynamic_array(raw_cmd), cmd_va, cmd_len * sizeof(*cmd_va));
 	),
 
 
-	TP_printk("vgpu%d ring %d: buf_type %u, ip_gma %08x, raw cmd %s",
+	TP_printk("vgpu%d ring %d: address_type %u, buf_type %u, ip_gma %08x,cmd (name=%s,len=%u,raw cmd=%s), workload=%p\n",
 		__entry->vgpu_id,
 		__entry->ring_id,
+		__entry->buf_addr_type,
 		__entry->buf_type,
 		__entry->ip_gma,
-		__print_array(__get_dynamic_array(raw_cmd), __entry->cmd_len, 4))
+		__entry->cmd_name,
+		__entry->cmd_len,
+		__print_array(__get_dynamic_array(raw_cmd),
+			__entry->cmd_len, 4),
+		__entry->workload)
 );
 
 #define GVT_TEMP_STR_LEN 10
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 89f7ff2c652e..13e7b9e4a6e6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -377,16 +377,19 @@ static void print_batch_pool_stats(struct seq_file *m,
 	print_file_stats(m, "[k]batch pool", stats);
 }
 
-static int per_file_ctx_stats(int id, void *ptr, void *data)
+static int per_file_ctx_stats(int idx, void *ptr, void *data)
 {
 	struct i915_gem_context *ctx = ptr;
-	int n;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, ctx->i915, id) {
+		struct intel_context *ce = to_intel_context(ctx, engine);
 
-	for (n = 0; n < ARRAY_SIZE(ctx->engine); n++) {
-		if (ctx->engine[n].state)
-			per_file_stats(0, ctx->engine[n].state->obj, data);
-		if (ctx->engine[n].ring)
-			per_file_stats(0, ctx->engine[n].ring->vma->obj, data);
+		if (ce->state)
+			per_file_stats(0, ce->state->obj, data);
+		if (ce->ring)
+			per_file_stats(0, ce->ring->vma->obj, data);
 	}
 
 	return 0;
@@ -1215,20 +1218,20 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 0 :
 			    rp_state_cap >> 16) & 0xff;
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
-			     IS_CANNONLAKE(dev_priv) ? GEN9_FREQ_SCALER : 1);
+			     INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Lowest (RPN) frequency: %dMHz\n",
 			   intel_gpu_freq(dev_priv, max_freq));
 
 		max_freq = (rp_state_cap & 0xff00) >> 8;
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
-			     IS_CANNONLAKE(dev_priv) ? GEN9_FREQ_SCALER : 1);
+			     INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Nominal (RP1) frequency: %dMHz\n",
 			   intel_gpu_freq(dev_priv, max_freq));
 
 		max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 16 :
 			    rp_state_cap >> 0) & 0xff;
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
-			     IS_CANNONLAKE(dev_priv) ? GEN9_FREQ_SCALER : 1);
+			     INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
 			   intel_gpu_freq(dev_priv, max_freq));
 		seq_printf(m, "Max overclocked frequency: %dMHz\n",
@@ -1340,10 +1343,9 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 		struct rb_node *rb;
 
 		seq_printf(m, "%s:\n", engine->name);
-		seq_printf(m, "\tseqno = %x [current %x, last %x], inflight %d\n",
+		seq_printf(m, "\tseqno = %x [current %x, last %x]\n",
 			   engine->hangcheck.seqno, seqno[id],
-			   intel_engine_last_submit(engine),
-			   engine->timeline->inflight_seqnos);
+			   intel_engine_last_submit(engine));
 		seq_printf(m, "\twaiters? %s, fake irq active? %s, stalled? %s\n",
 			   yesno(intel_engine_has_waiter(engine)),
 			   yesno(test_bit(engine->id,
@@ -1796,9 +1798,9 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	int ret = 0;
-	int gpu_freq, ia_freq;
 	unsigned int max_gpu_freq, min_gpu_freq;
+	int gpu_freq, ia_freq;
+	int ret;
 
 	if (!HAS_LLC(dev_priv))
 		return -ENODEV;
@@ -1809,13 +1811,12 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 	if (ret)
 		goto out;
 
-	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+	min_gpu_freq = rps->min_freq;
+	max_gpu_freq = rps->max_freq;
+	if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
 		/* Convert GT frequency to 50 HZ units */
-		min_gpu_freq = rps->min_freq_softlimit / GEN9_FREQ_SCALER;
-		max_gpu_freq = rps->max_freq_softlimit / GEN9_FREQ_SCALER;
-	} else {
-		min_gpu_freq = rps->min_freq_softlimit;
-		max_gpu_freq = rps->max_freq_softlimit;
+		min_gpu_freq /= GEN9_FREQ_SCALER;
+		max_gpu_freq /= GEN9_FREQ_SCALER;
 	}
 
 	seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
@@ -1828,7 +1829,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 		seq_printf(m, "%d\t\t%d\t\t\t\t%d\n",
 			   intel_gpu_freq(dev_priv, (gpu_freq *
 						     (IS_GEN9_BC(dev_priv) ||
-						      IS_CANNONLAKE(dev_priv) ?
+						      INTEL_GEN(dev_priv) >= 10 ?
 						      GEN9_FREQ_SCALER : 1))),
 			   ((ia_freq >> 0) & 0xff) * 100,
 			   ((ia_freq >> 8) & 0xff) * 100);
@@ -1923,8 +1924,8 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 
 static void describe_ctx_ring(struct seq_file *m, struct intel_ring *ring)
 {
-	seq_printf(m, " (ringbuffer, space: %d, head: %u, tail: %u)",
-		   ring->space, ring->head, ring->tail);
+	seq_printf(m, " (ringbuffer, space: %d, head: %u, tail: %u, emit: %u)",
+		   ring->space, ring->head, ring->tail, ring->emit);
 }
 
 static int i915_context_status(struct seq_file *m, void *unused)
@@ -1961,7 +1962,8 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		seq_putc(m, '\n');
 
 		for_each_engine(engine, dev_priv, id) {
-			struct intel_context *ce = &ctx->engine[engine->id];
+			struct intel_context *ce =
+				to_intel_context(ctx, engine);
 
 			seq_printf(m, "%s: ", engine->name);
 			if (ce->state)
@@ -2326,30 +2328,45 @@ static int i915_guc_load_status_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-static void i915_guc_log_info(struct seq_file *m,
-			      struct drm_i915_private *dev_priv)
+static const char *
+stringify_guc_log_type(enum guc_log_buffer_type type)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	switch (type) {
+	case GUC_ISR_LOG_BUFFER:
+		return "ISR";
+	case GUC_DPC_LOG_BUFFER:
+		return "DPC";
+	case GUC_CRASH_DUMP_LOG_BUFFER:
+		return "CRASH";
+	default:
+		MISSING_CASE(type);
+	}
 
-	seq_puts(m, "\nGuC logging stats:\n");
+	return "";
+}
 
-	seq_printf(m, "\tISR:   flush count %10u, overflow count %10u\n",
-		   guc->log.flush_count[GUC_ISR_LOG_BUFFER],
-		   guc->log.total_overflow_count[GUC_ISR_LOG_BUFFER]);
+static void i915_guc_log_info(struct seq_file *m,
+			      struct drm_i915_private *dev_priv)
+{
+	struct intel_guc_log *log = &dev_priv->guc.log;
+	enum guc_log_buffer_type type;
 
-	seq_printf(m, "\tDPC:   flush count %10u, overflow count %10u\n",
-		   guc->log.flush_count[GUC_DPC_LOG_BUFFER],
-		   guc->log.total_overflow_count[GUC_DPC_LOG_BUFFER]);
+	if (!intel_guc_log_relay_enabled(log)) {
+		seq_puts(m, "GuC log relay disabled\n");
+		return;
+	}
 
-	seq_printf(m, "\tCRASH: flush count %10u, overflow count %10u\n",
-		   guc->log.flush_count[GUC_CRASH_DUMP_LOG_BUFFER],
-		   guc->log.total_overflow_count[GUC_CRASH_DUMP_LOG_BUFFER]);
+	seq_puts(m, "GuC logging stats:\n");
 
-	seq_printf(m, "\tTotal flush interrupt count: %u\n",
-		   guc->log.flush_interrupt_count);
+	seq_printf(m, "\tRelay full count: %u\n",
+		   log->relay.full_count);
 
-	seq_printf(m, "\tCapture miss count: %u\n",
-		   guc->log.capture_miss_count);
+	for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
+		seq_printf(m, "\t%s:\tflush count %10u, overflow count %10u\n",
+			   stringify_guc_log_type(type),
+			   log->stats[type].flush,
+			   log->stats[type].sampled_overflow);
+	}
 }
 
 static void i915_guc_client_info(struct seq_file *m,
@@ -2379,14 +2396,19 @@ static int i915_guc_info(struct seq_file *m, void *data)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	const struct intel_guc *guc = &dev_priv->guc;
 
-	if (!USES_GUC_SUBMISSION(dev_priv))
+	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
+	i915_guc_log_info(m, dev_priv);
+
+	if (!USES_GUC_SUBMISSION(dev_priv))
+		return 0;
+
 	GEM_BUG_ON(!guc->execbuf_client);
 
-	seq_printf(m, "Doorbell map:\n");
+	seq_printf(m, "\nDoorbell map:\n");
 	seq_printf(m, "\t%*pb\n", GUC_NUM_DOORBELLS, guc->doorbell_bitmap);
-	seq_printf(m, "Doorbell next cacheline: 0x%x\n\n", guc->db_cacheline);
+	seq_printf(m, "Doorbell next cacheline: 0x%x\n", guc->db_cacheline);
 
 	seq_printf(m, "\nGuC execbuf client @ %p:\n", guc->execbuf_client);
 	i915_guc_client_info(m, dev_priv, guc->execbuf_client);
@@ -2396,8 +2418,6 @@ static int i915_guc_info(struct seq_file *m, void *data)
 		i915_guc_client_info(m, dev_priv, guc->preempt_client);
 	}
 
-	i915_guc_log_info(m, dev_priv);
-
 	/* Add more as required ... */
 
 	return 0;
@@ -2496,35 +2516,73 @@ static int i915_guc_log_dump(struct seq_file *m, void *data)
 	return 0;
 }
 
-static int i915_guc_log_control_get(void *data, u64 *val)
+static int i915_guc_log_level_get(void *data, u64 *val)
 {
 	struct drm_i915_private *dev_priv = data;
 
-	if (!HAS_GUC(dev_priv))
+	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
-	if (!dev_priv->guc.log.vma)
-		return -EINVAL;
-
-	*val = i915_modparams.guc_log_level;
+	*val = intel_guc_log_level_get(&dev_priv->guc.log);
 
 	return 0;
 }
 
-static int i915_guc_log_control_set(void *data, u64 val)
+static int i915_guc_log_level_set(void *data, u64 val)
 {
 	struct drm_i915_private *dev_priv = data;
 
-	if (!HAS_GUC(dev_priv))
+	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
-	return intel_guc_log_control(&dev_priv->guc, val);
+	return intel_guc_log_level_set(&dev_priv->guc.log, val);
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(i915_guc_log_control_fops,
-			i915_guc_log_control_get, i915_guc_log_control_set,
+DEFINE_SIMPLE_ATTRIBUTE(i915_guc_log_level_fops,
+			i915_guc_log_level_get, i915_guc_log_level_set,
 			"%lld\n");
 
+static int i915_guc_log_relay_open(struct inode *inode, struct file *file)
+{
+	struct drm_i915_private *dev_priv = inode->i_private;
+
+	if (!USES_GUC(dev_priv))
+		return -ENODEV;
+
+	file->private_data = &dev_priv->guc.log;
+
+	return intel_guc_log_relay_open(&dev_priv->guc.log);
+}
+
+static ssize_t
+i915_guc_log_relay_write(struct file *filp,
+			 const char __user *ubuf,
+			 size_t cnt,
+			 loff_t *ppos)
+{
+	struct intel_guc_log *log = filp->private_data;
+
+	intel_guc_log_relay_flush(log);
+
+	return cnt;
+}
+
+static int i915_guc_log_relay_release(struct inode *inode, struct file *file)
+{
+	struct drm_i915_private *dev_priv = inode->i_private;
+
+	intel_guc_log_relay_close(&dev_priv->guc.log);
+
+	return 0;
+}
+
+static const struct file_operations i915_guc_log_relay_fops = {
+	.owner = THIS_MODULE,
+	.open = i915_guc_log_relay_open,
+	.write = i915_guc_log_relay_write,
+	.release = i915_guc_log_relay_release,
+};
+
 static const char *psr2_live_status(u32 val)
 {
 	static const char * const live_status[] = {
@@ -2548,6 +2606,26 @@ static const char *psr2_live_status(u32 val)
 	return "unknown";
 }
 
+static const char *psr_sink_status(u8 val)
+{
+	static const char * const sink_status[] = {
+		"inactive",
+		"transition to active, capture and display",
+		"active, display from RFB",
+		"active, capture and display on sink device timings",
+		"transition to inactive, capture and display, timing re-sync",
+		"reserved",
+		"reserved",
+		"sink internal error"
+	};
+
+	val &= DP_PSR_SINK_STATE_MASK;
+	if (val < ARRAY_SIZE(sink_status))
+		return sink_status[val];
+
+	return "unknown";
+}
+
 static int i915_edp_psr_status(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -2569,14 +2647,13 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 
 	mutex_lock(&dev_priv->psr.lock);
 	seq_printf(m, "Enabled: %s\n", yesno((bool)dev_priv->psr.enabled));
-	seq_printf(m, "Active: %s\n", yesno(dev_priv->psr.active));
 	seq_printf(m, "Busy frontbuffer bits: 0x%03x\n",
 		   dev_priv->psr.busy_frontbuffer_bits);
 	seq_printf(m, "Re-enable work scheduled: %s\n",
 		   yesno(work_busy(&dev_priv->psr.work.work)));
 
 	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.psr2_support)
+		if (dev_priv->psr.psr2_enabled)
 			enabled = I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE;
 		else
 			enabled = I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE;
@@ -2624,18 +2701,67 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 
 		seq_printf(m, "Performance_Counter: %u\n", psrperf);
 	}
-	if (dev_priv->psr.psr2_support) {
+	if (dev_priv->psr.psr2_enabled) {
 		u32 psr2 = I915_READ(EDP_PSR2_STATUS);
 
 		seq_printf(m, "EDP_PSR2_STATUS: %x [%s]\n",
 			   psr2, psr2_live_status(psr2));
 	}
+
+	if (dev_priv->psr.enabled) {
+		struct drm_dp_aux *aux = &dev_priv->psr.enabled->aux;
+		u8 val;
+
+		if (drm_dp_dpcd_readb(aux, DP_PSR_STATUS, &val) == 1)
+			seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val,
+				   psr_sink_status(val));
+	}
 	mutex_unlock(&dev_priv->psr.lock);
 
+	if (READ_ONCE(dev_priv->psr.debug)) {
+		seq_printf(m, "Last attempted entry at: %lld\n",
+			   dev_priv->psr.last_entry_attempt);
+		seq_printf(m, "Last exit at: %lld\n",
+			   dev_priv->psr.last_exit);
+	}
+
 	intel_runtime_pm_put(dev_priv);
 	return 0;
 }
 
+static int
+i915_edp_psr_debug_set(void *data, u64 val)
+{
+	struct drm_i915_private *dev_priv = data;
+
+	if (!CAN_PSR(dev_priv))
+		return -ENODEV;
+
+	DRM_DEBUG_KMS("PSR debug %s\n", enableddisabled(val));
+
+	intel_runtime_pm_get(dev_priv);
+	intel_psr_irq_control(dev_priv, !!val);
+	intel_runtime_pm_put(dev_priv);
+
+	return 0;
+}
+
+static int
+i915_edp_psr_debug_get(void *data, u64 *val)
+{
+	struct drm_i915_private *dev_priv = data;
+
+	if (!CAN_PSR(dev_priv))
+		return -ENODEV;
+
+	*val = READ_ONCE(dev_priv->psr.debug);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(i915_edp_psr_debug_fops,
+			i915_edp_psr_debug_get, i915_edp_psr_debug_set,
+			"%llu\n");
+
 static int i915_sink_crc(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -3231,7 +3357,8 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
 		struct intel_shared_dpll *pll = &dev_priv->shared_dplls[i];
 
-		seq_printf(m, "DPLL%i: %s, id: %i\n", i, pll->name, pll->id);
+		seq_printf(m, "DPLL%i: %s, id: %i\n", i, pll->info->name,
+			   pll->info->id);
 		seq_printf(m, " crtc_mask: 0x%08x, active: 0x%x, on: %s\n",
 			   pll->state.crtc_mask, pll->active_mask, yesno(pll->on));
 		seq_printf(m, " tracked hardware state:\n");
@@ -3241,6 +3368,28 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 		seq_printf(m, " fp0:     0x%08x\n", pll->state.hw_state.fp0);
 		seq_printf(m, " fp1:     0x%08x\n", pll->state.hw_state.fp1);
 		seq_printf(m, " wrpll:   0x%08x\n", pll->state.hw_state.wrpll);
+		seq_printf(m, " cfgcr0:  0x%08x\n", pll->state.hw_state.cfgcr0);
+		seq_printf(m, " cfgcr1:  0x%08x\n", pll->state.hw_state.cfgcr1);
+		seq_printf(m, " mg_refclkin_ctl:        0x%08x\n",
+			   pll->state.hw_state.mg_refclkin_ctl);
+		seq_printf(m, " mg_clktop2_coreclkctl1: 0x%08x\n",
+			   pll->state.hw_state.mg_clktop2_coreclkctl1);
+		seq_printf(m, " mg_clktop2_hsclkctl:    0x%08x\n",
+			   pll->state.hw_state.mg_clktop2_hsclkctl);
+		seq_printf(m, " mg_pll_div0:  0x%08x\n",
+			   pll->state.hw_state.mg_pll_div0);
+		seq_printf(m, " mg_pll_div1:  0x%08x\n",
+			   pll->state.hw_state.mg_pll_div1);
+		seq_printf(m, " mg_pll_lf:    0x%08x\n",
+			   pll->state.hw_state.mg_pll_lf);
+		seq_printf(m, " mg_pll_frac_lock: 0x%08x\n",
+			   pll->state.hw_state.mg_pll_frac_lock);
+		seq_printf(m, " mg_pll_ssc:   0x%08x\n",
+			   pll->state.hw_state.mg_pll_ssc);
+		seq_printf(m, " mg_pll_bias:  0x%08x\n",
+			   pll->state.hw_state.mg_pll_bias);
+		seq_printf(m, " mg_pll_tdc_coldst_bias: 0x%08x\n",
+			   pll->state.hw_state.mg_pll_tdc_coldst_bias);
 	}
 	drm_modeset_unlock_all(dev);
 
@@ -3249,24 +3398,13 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 
 static int i915_wa_registers(struct seq_file *m, void *unused)
 {
-	int i;
-	int ret;
-	struct intel_engine_cs *engine;
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
 	struct i915_workarounds *workarounds = &dev_priv->workarounds;
-	enum intel_engine_id id;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
+	int i;
 
 	intel_runtime_pm_get(dev_priv);
 
 	seq_printf(m, "Workarounds applied: %d\n", workarounds->count);
-	for_each_engine(engine, dev_priv, id)
-		seq_printf(m, "HW whitelist count for %s: %d\n",
-			   engine->name, workarounds->hw_whitelist_count[id]);
 	for (i = 0; i < workarounds->count; ++i) {
 		i915_reg_t addr;
 		u32 mask, value, read;
@@ -3282,7 +3420,6 @@ static int i915_wa_registers(struct seq_file *m, void *unused)
 	}
 
 	intel_runtime_pm_put(dev_priv);
-	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 }
@@ -3567,7 +3704,8 @@ static ssize_t i915_displayport_test_active_write(struct file *file,
 
 static int i915_displayport_test_active_show(struct seq_file *m, void *data)
 {
-	struct drm_device *dev = m->private;
+	struct drm_i915_private *dev_priv = m->private;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_dp *intel_dp;
@@ -3601,10 +3739,8 @@ static int i915_displayport_test_active_show(struct seq_file *m, void *data)
 static int i915_displayport_test_active_open(struct inode *inode,
 					     struct file *file)
 {
-	struct drm_i915_private *dev_priv = inode->i_private;
-
 	return single_open(file, i915_displayport_test_active_show,
-			   &dev_priv->drm);
+			   inode->i_private);
 }
 
 static const struct file_operations i915_displayport_test_active_fops = {
@@ -3618,7 +3754,8 @@ static const struct file_operations i915_displayport_test_active_fops = {
 
 static int i915_displayport_test_data_show(struct seq_file *m, void *data)
 {
-	struct drm_device *dev = m->private;
+	struct drm_i915_private *dev_priv = m->private;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_dp *intel_dp;
@@ -3657,26 +3794,12 @@ static int i915_displayport_test_data_show(struct seq_file *m, void *data)
 
 	return 0;
 }
-static int i915_displayport_test_data_open(struct inode *inode,
-					   struct file *file)
-{
-	struct drm_i915_private *dev_priv = inode->i_private;
-
-	return single_open(file, i915_displayport_test_data_show,
-			   &dev_priv->drm);
-}
-
-static const struct file_operations i915_displayport_test_data_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_displayport_test_data_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release
-};
+DEFINE_SHOW_ATTRIBUTE(i915_displayport_test_data);
 
 static int i915_displayport_test_type_show(struct seq_file *m, void *data)
 {
-	struct drm_device *dev = m->private;
+	struct drm_i915_private *dev_priv = m->private;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 	struct intel_dp *intel_dp;
@@ -3703,23 +3826,7 @@ static int i915_displayport_test_type_show(struct seq_file *m, void *data)
 
 	return 0;
 }
-
-static int i915_displayport_test_type_open(struct inode *inode,
-				       struct file *file)
-{
-	struct drm_i915_private *dev_priv = inode->i_private;
-
-	return single_open(file, i915_displayport_test_type_show,
-			   &dev_priv->drm);
-}
-
-static const struct file_operations i915_displayport_test_type_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_displayport_test_type_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release
-};
+DEFINE_SHOW_ATTRIBUTE(i915_displayport_test_type);
 
 static void wm_latency_show(struct seq_file *m, const uint16_t wm[8])
 {
@@ -3987,8 +4094,8 @@ i915_wedged_set(void *data, u64 val)
 		engine->hangcheck.stalled = true;
 	}
 
-	i915_handle_error(i915, val, "Manually set wedged engine mask = %llx",
-			  val);
+	i915_handle_error(i915, val, I915_ERROR_CAPTURE,
+			  "Manually set wedged engine mask = %llx", val);
 
 	wait_on_bit(&i915->gpu_error.flags,
 		    I915_RESET_HANDOFF,
@@ -4152,119 +4259,6 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_drop_caches_fops,
 			"0x%08llx\n");
 
 static int
-i915_max_freq_get(void *data, u64 *val)
-{
-	struct drm_i915_private *dev_priv = data;
-
-	if (INTEL_GEN(dev_priv) < 6)
-		return -ENODEV;
-
-	*val = intel_gpu_freq(dev_priv, dev_priv->gt_pm.rps.max_freq_softlimit);
-	return 0;
-}
-
-static int
-i915_max_freq_set(void *data, u64 val)
-{
-	struct drm_i915_private *dev_priv = data;
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u32 hw_max, hw_min;
-	int ret;
-
-	if (INTEL_GEN(dev_priv) < 6)
-		return -ENODEV;
-
-	DRM_DEBUG_DRIVER("Manually setting max freq to %llu\n", val);
-
-	ret = mutex_lock_interruptible(&dev_priv->pcu_lock);
-	if (ret)
-		return ret;
-
-	/*
-	 * Turbo will still be enabled, but won't go above the set value.
-	 */
-	val = intel_freq_opcode(dev_priv, val);
-
-	hw_max = rps->max_freq;
-	hw_min = rps->min_freq;
-
-	if (val < hw_min || val > hw_max || val < rps->min_freq_softlimit) {
-		mutex_unlock(&dev_priv->pcu_lock);
-		return -EINVAL;
-	}
-
-	rps->max_freq_softlimit = val;
-
-	if (intel_set_rps(dev_priv, val))
-		DRM_DEBUG_DRIVER("failed to update RPS to new softlimit\n");
-
-	mutex_unlock(&dev_priv->pcu_lock);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(i915_max_freq_fops,
-			i915_max_freq_get, i915_max_freq_set,
-			"%llu\n");
-
-static int
-i915_min_freq_get(void *data, u64 *val)
-{
-	struct drm_i915_private *dev_priv = data;
-
-	if (INTEL_GEN(dev_priv) < 6)
-		return -ENODEV;
-
-	*val = intel_gpu_freq(dev_priv, dev_priv->gt_pm.rps.min_freq_softlimit);
-	return 0;
-}
-
-static int
-i915_min_freq_set(void *data, u64 val)
-{
-	struct drm_i915_private *dev_priv = data;
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u32 hw_max, hw_min;
-	int ret;
-
-	if (INTEL_GEN(dev_priv) < 6)
-		return -ENODEV;
-
-	DRM_DEBUG_DRIVER("Manually setting min freq to %llu\n", val);
-
-	ret = mutex_lock_interruptible(&dev_priv->pcu_lock);
-	if (ret)
-		return ret;
-
-	/*
-	 * Turbo will still be enabled, but won't go below the set value.
-	 */
-	val = intel_freq_opcode(dev_priv, val);
-
-	hw_max = rps->max_freq;
-	hw_min = rps->min_freq;
-
-	if (val < hw_min ||
-	    val > hw_max || val > rps->max_freq_softlimit) {
-		mutex_unlock(&dev_priv->pcu_lock);
-		return -EINVAL;
-	}
-
-	rps->min_freq_softlimit = val;
-
-	if (intel_set_rps(dev_priv, val))
-		DRM_DEBUG_DRIVER("failed to update RPS to new softlimit\n");
-
-	mutex_unlock(&dev_priv->pcu_lock);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(i915_min_freq_fops,
-			i915_min_freq_get, i915_min_freq_set,
-			"%llu\n");
-
-static int
 i915_cache_sharing_get(void *data, u64 *val)
 {
 	struct drm_i915_private *dev_priv = data;
@@ -4316,9 +4310,10 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_cache_sharing_fops,
 static void cherryview_sseu_device_status(struct drm_i915_private *dev_priv,
 					  struct sseu_dev_info *sseu)
 {
-	int ss_max = 2;
+#define SS_MAX 2
+	const int ss_max = SS_MAX;
+	u32 sig1[SS_MAX], sig2[SS_MAX];
 	int ss;
-	u32 sig1[ss_max], sig2[ss_max];
 
 	sig1[0] = I915_READ(CHV_POWER_SS0_SIG1);
 	sig1[1] = I915_READ(CHV_POWER_SS1_SIG1);
@@ -4342,15 +4337,16 @@ static void cherryview_sseu_device_status(struct drm_i915_private *dev_priv,
 		sseu->eu_per_subslice = max_t(unsigned int,
 					      sseu->eu_per_subslice, eu_cnt);
 	}
+#undef SS_MAX
 }
 
 static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
 				     struct sseu_dev_info *sseu)
 {
+#define SS_MAX 6
 	const struct intel_device_info *info = INTEL_INFO(dev_priv);
+	u32 s_reg[SS_MAX], eu_reg[2 * SS_MAX], eu_mask[2];
 	int s, ss;
-	u32 s_reg[info->sseu.max_slices];
-	u32 eu_reg[2 * info->sseu.max_subslices], eu_mask[2];
 
 	for (s = 0; s < info->sseu.max_slices; s++) {
 		/*
@@ -4397,15 +4393,16 @@ static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
 						      eu_cnt);
 		}
 	}
+#undef SS_MAX
 }
 
 static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 				    struct sseu_dev_info *sseu)
 {
+#define SS_MAX 3
 	const struct intel_device_info *info = INTEL_INFO(dev_priv);
+	u32 s_reg[SS_MAX], eu_reg[2 * SS_MAX], eu_mask[2];
 	int s, ss;
-	u32 s_reg[info->sseu.max_slices];
-	u32 eu_reg[2 * info->sseu.max_subslices], eu_mask[2];
 
 	for (s = 0; s < info->sseu.max_slices; s++) {
 		s_reg[s] = I915_READ(GEN9_SLICE_PGCTL_ACK(s));
@@ -4452,6 +4449,7 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 						      eu_cnt);
 		}
 	}
+#undef SS_MAX
 }
 
 static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
@@ -4703,6 +4701,67 @@ static int i915_drrs_ctl_set(void *data, u64 val)
 
 DEFINE_SIMPLE_ATTRIBUTE(i915_drrs_ctl_fops, NULL, i915_drrs_ctl_set, "%llu\n");
 
+static ssize_t
+i915_fifo_underrun_reset_write(struct file *filp,
+			       const char __user *ubuf,
+			       size_t cnt, loff_t *ppos)
+{
+	struct drm_i915_private *dev_priv = filp->private_data;
+	struct intel_crtc *intel_crtc;
+	struct drm_device *dev = &dev_priv->drm;
+	int ret;
+	bool reset;
+
+	ret = kstrtobool_from_user(ubuf, cnt, &reset);
+	if (ret)
+		return ret;
+
+	if (!reset)
+		return cnt;
+
+	for_each_intel_crtc(dev, intel_crtc) {
+		struct drm_crtc_commit *commit;
+		struct intel_crtc_state *crtc_state;
+
+		ret = drm_modeset_lock_single_interruptible(&intel_crtc->base.mutex);
+		if (ret)
+			return ret;
+
+		crtc_state = to_intel_crtc_state(intel_crtc->base.state);
+		commit = crtc_state->base.commit;
+		if (commit) {
+			ret = wait_for_completion_interruptible(&commit->hw_done);
+			if (!ret)
+				ret = wait_for_completion_interruptible(&commit->flip_done);
+		}
+
+		if (!ret && crtc_state->base.active) {
+			DRM_DEBUG_KMS("Re-arming FIFO underruns on pipe %c\n",
+				      pipe_name(intel_crtc->pipe));
+
+			intel_crtc_arm_fifo_underrun(intel_crtc, crtc_state);
+		}
+
+		drm_modeset_unlock(&intel_crtc->base.mutex);
+
+		if (ret)
+			return ret;
+	}
+
+	ret = intel_fbc_reset_underrun(dev_priv);
+	if (ret)
+		return ret;
+
+	return cnt;
+}
+
+static const struct file_operations i915_fifo_underrun_reset_ops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = i915_fifo_underrun_reset_write,
+	.llseek = default_llseek,
+};
+
 static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_capabilities", i915_capabilities, 0},
 	{"i915_gem_objects", i915_gem_object_info, 0},
@@ -4760,8 +4819,6 @@ static const struct i915_debugfs_files {
 	const struct file_operations *fops;
 } i915_debugfs_files[] = {
 	{"i915_wedged", &i915_wedged_fops},
-	{"i915_max_freq", &i915_max_freq_fops},
-	{"i915_min_freq", &i915_min_freq_fops},
 	{"i915_cache_sharing", &i915_cache_sharing_fops},
 	{"i915_ring_missed_irq", &i915_ring_missed_irq_fops},
 	{"i915_ring_test_irq", &i915_ring_test_irq_fops},
@@ -4770,6 +4827,7 @@ static const struct i915_debugfs_files {
 	{"i915_error_state", &i915_error_state_fops},
 	{"i915_gpu_info", &i915_gpu_info_fops},
 #endif
+	{"i915_fifo_underrun_reset", &i915_fifo_underrun_reset_ops},
 	{"i915_next_seqno", &i915_next_seqno_fops},
 	{"i915_display_crc_ctl", &i915_display_crc_ctl_fops},
 	{"i915_pri_wm_latency", &i915_pri_wm_latency_fops},
@@ -4779,10 +4837,12 @@ static const struct i915_debugfs_files {
 	{"i915_dp_test_data", &i915_displayport_test_data_fops},
 	{"i915_dp_test_type", &i915_displayport_test_type_fops},
 	{"i915_dp_test_active", &i915_displayport_test_active_fops},
-	{"i915_guc_log_control", &i915_guc_log_control_fops},
+	{"i915_guc_log_level", &i915_guc_log_level_fops},
+	{"i915_guc_log_relay", &i915_guc_log_relay_fops},
 	{"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops},
 	{"i915_ipc_status", &i915_ipc_status_fops},
-	{"i915_drrs_ctl", &i915_drrs_ctl_fops}
+	{"i915_drrs_ctl", &i915_drrs_ctl_fops},
+	{"i915_edp_psr_debug", &i915_edp_psr_debug_fops}
 };
 
 int i915_debugfs_register(struct drm_i915_private *dev_priv)
@@ -4876,19 +4936,7 @@ static int i915_dpcd_show(struct seq_file *m, void *data)
 
 	return 0;
 }
-
-static int i915_dpcd_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, i915_dpcd_show, inode->i_private);
-}
-
-static const struct file_operations i915_dpcd_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_dpcd_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(i915_dpcd);
 
 static int i915_panel_show(struct seq_file *m, void *data)
 {
@@ -4910,19 +4958,7 @@ static int i915_panel_show(struct seq_file *m, void *data)
 
 	return 0;
 }
-
-static int i915_panel_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, i915_panel_show, inode->i_private);
-}
-
-static const struct file_operations i915_panel_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_panel_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(i915_panel);
 
 /**
  * i915_debugfs_connector_add - add i915 specific connector debugfs files
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 84ca369f15a5..9c449b8d8eab 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -101,7 +101,13 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 		   __builtin_return_address(0), &vaf);
 
 	if (is_error && !shown_bug_once) {
-		dev_notice(kdev, "%s", FDO_BUG_MSG);
+		/*
+		 * Ask the user to file a bug report for the error, except
+		 * if they may have caused the bug by fiddling with unsafe
+		 * module parameters.
+		 */
+		if (!test_taint(TAINT_USER))
+			dev_notice(kdev, "%s", FDO_BUG_MSG);
 		shown_bug_once = true;
 	}
 
@@ -377,9 +383,9 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = INTEL_INFO(dev_priv)->sseu.min_eu_in_pool;
 		break;
 	case I915_PARAM_HUC_STATUS:
-		intel_runtime_pm_get(dev_priv);
-		value = I915_READ(HUC_STATUS2) & HUC_FW_VERIFIED;
-		intel_runtime_pm_put(dev_priv);
+		value = intel_huc_check_status(&dev_priv->huc);
+		if (value < 0)
+			return value;
 		break;
 	case I915_PARAM_MMAP_GTT_VERSION:
 		/* Though we've started our numbering from 1, and so class all
@@ -695,11 +701,9 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	if (ret)
 		goto cleanup_irq;
 
-	intel_uc_init_fw(dev_priv);
-
 	ret = i915_gem_init(dev_priv);
 	if (ret)
-		goto cleanup_uc;
+		goto cleanup_irq;
 
 	intel_setup_overlay(dev_priv);
 
@@ -719,8 +723,6 @@ cleanup_gem:
 	if (i915_gem_suspend(dev_priv))
 		DRM_ERROR("failed to idle hardware; continuing to unload!\n");
 	i915_gem_fini(dev_priv);
-cleanup_uc:
-	intel_uc_fini_fw(dev_priv);
 cleanup_irq:
 	drm_irq_uninstall(dev);
 	intel_teardown_gmbus(dev_priv);
@@ -922,16 +924,21 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
 	mutex_init(&dev_priv->wm.wm_mutex);
 	mutex_init(&dev_priv->pps_mutex);
 
-	intel_uc_init_early(dev_priv);
 	i915_memcpy_init_early(dev_priv);
 
 	ret = i915_workqueues_init(dev_priv);
 	if (ret < 0)
 		goto err_engines;
 
+	ret = i915_gem_init_early(dev_priv);
+	if (ret < 0)
+		goto err_workqueues;
+
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(dev_priv);
 
+	intel_wopcm_init_early(&dev_priv->wopcm);
+	intel_uc_init_early(dev_priv);
 	intel_pm_setup(dev_priv);
 	intel_init_dpio(dev_priv);
 	intel_power_domains_init(dev_priv);
@@ -940,18 +947,13 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
 	intel_init_display_hooks(dev_priv);
 	intel_init_clock_gating_hooks(dev_priv);
 	intel_init_audio_hooks(dev_priv);
-	ret = i915_gem_load_init(dev_priv);
-	if (ret < 0)
-		goto err_irq;
-
 	intel_display_crc_init(dev_priv);
 
 	intel_detect_preproduction_hw(dev_priv);
 
 	return 0;
 
-err_irq:
-	intel_irq_fini(dev_priv);
+err_workqueues:
 	i915_workqueues_cleanup(dev_priv);
 err_engines:
 	i915_engines_cleanup(dev_priv);
@@ -964,8 +966,9 @@ err_engines:
  */
 static void i915_driver_cleanup_early(struct drm_i915_private *dev_priv)
 {
-	i915_gem_load_cleanup(dev_priv);
 	intel_irq_fini(dev_priv);
+	intel_uc_cleanup_early(dev_priv);
+	i915_gem_cleanup_early(dev_priv);
 	i915_workqueues_cleanup(dev_priv);
 	i915_engines_cleanup(dev_priv);
 }
@@ -1035,6 +1038,10 @@ static int i915_driver_init_mmio(struct drm_i915_private *dev_priv)
 
 	intel_uncore_init(dev_priv);
 
+	intel_device_info_init_mmio(dev_priv);
+
+	intel_uncore_prune(dev_priv);
+
 	intel_uc_init_mmio(dev_priv);
 
 	ret = intel_engines_init_mmio(dev_priv);
@@ -1077,8 +1084,6 @@ static void intel_sanitize_options(struct drm_i915_private *dev_priv)
 					    i915_modparams.enable_ppgtt);
 	DRM_DEBUG_DRIVER("ppgtt mode: %i\n", i915_modparams.enable_ppgtt);
 
-	intel_uc_sanitize_options(dev_priv);
-
 	intel_gvt_sanitize_options(dev_priv);
 }
 
@@ -1105,30 +1110,32 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	ret = i915_ggtt_probe_hw(dev_priv);
 	if (ret)
-		return ret;
+		goto err_perf;
 
-	/* WARNING: Apparently we must kick fbdev drivers before vgacon,
-	 * otherwise the vga fbdev driver falls over. */
+	/*
+	 * WARNING: Apparently we must kick fbdev drivers before vgacon,
+	 * otherwise the vga fbdev driver falls over.
+	 */
 	ret = i915_kick_out_firmware_fb(dev_priv);
 	if (ret) {
 		DRM_ERROR("failed to remove conflicting framebuffer drivers\n");
-		goto out_ggtt;
+		goto err_ggtt;
 	}
 
 	ret = i915_kick_out_vgacon(dev_priv);
 	if (ret) {
 		DRM_ERROR("failed to remove conflicting VGA console\n");
-		goto out_ggtt;
+		goto err_ggtt;
 	}
 
 	ret = i915_ggtt_init_hw(dev_priv);
 	if (ret)
-		return ret;
+		goto err_ggtt;
 
 	ret = i915_ggtt_enable_hw(dev_priv);
 	if (ret) {
 		DRM_ERROR("failed to enable GGTT\n");
-		goto out_ggtt;
+		goto err_ggtt;
 	}
 
 	pci_set_master(pdev);
@@ -1139,7 +1146,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 		if (ret) {
 			DRM_ERROR("failed to set DMA mask\n");
 
-			goto out_ggtt;
+			goto err_ggtt;
 		}
 	}
 
@@ -1157,7 +1164,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 		if (ret) {
 			DRM_ERROR("failed to set DMA mask\n");
 
-			goto out_ggtt;
+			goto err_ggtt;
 		}
 	}
 
@@ -1190,13 +1197,14 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	ret = intel_gvt_init(dev_priv);
 	if (ret)
-		goto out_ggtt;
+		goto err_ggtt;
 
 	return 0;
 
-out_ggtt:
+err_ggtt:
 	i915_ggtt_cleanup_hw(dev_priv);
-
+err_perf:
+	i915_perf_fini(dev_priv);
 	return ret;
 }
 
@@ -1241,7 +1249,6 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 	/* Reveal our presence to userspace */
 	if (drm_dev_register(dev, 0) == 0) {
 		i915_debugfs_register(dev_priv);
-		i915_guc_log_register(dev_priv);
 		i915_setup_sysfs(dev_priv);
 
 		/* Depends on sysfs having been initialized */
@@ -1301,7 +1308,6 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv)
 	i915_pmu_unregister(dev_priv);
 
 	i915_teardown_sysfs(dev_priv);
-	i915_guc_log_unregister(dev_priv);
 	drm_dev_unregister(&dev_priv->drm);
 
 	i915_gem_shrinker_unregister(dev_priv);
@@ -1460,7 +1466,6 @@ void i915_driver_unload(struct drm_device *dev)
 	i915_reset_error_state(dev_priv);
 
 	i915_gem_fini(dev_priv);
-	intel_uc_fini_fw(dev_priv);
 	intel_fbc_cleanup_cfb(dev_priv);
 
 	intel_power_domains_fini(dev_priv);
@@ -1873,7 +1878,8 @@ static int i915_resume_switcheroo(struct drm_device *dev)
 /**
  * i915_reset - reset chip after a hang
  * @i915: #drm_i915_private to reset
- * @flags: Instructions
+ * @stalled_mask: mask of the stalled engines with the guilty requests
+ * @reason: user error message for why we are resetting
  *
  * Reset the chip.  Useful if a hang is detected. Marks the device as wedged
  * on failure.
@@ -1888,12 +1894,16 @@ static int i915_resume_switcheroo(struct drm_device *dev)
  *   - re-init interrupt state
  *   - re-init display
  */
-void i915_reset(struct drm_i915_private *i915, unsigned int flags)
+void i915_reset(struct drm_i915_private *i915,
+		unsigned int stalled_mask,
+		const char *reason)
 {
 	struct i915_gpu_error *error = &i915->gpu_error;
 	int ret;
 	int i;
 
+	GEM_TRACE("flags=%lx\n", error->flags);
+
 	might_sleep();
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags));
@@ -1905,8 +1915,8 @@ void i915_reset(struct drm_i915_private *i915, unsigned int flags)
 	if (!i915_gem_unset_wedged(i915))
 		goto wakeup;
 
-	if (!(flags & I915_RESET_QUIET))
-		dev_notice(i915->drm.dev, "Resetting chip after gpu hang\n");
+	if (reason)
+		dev_notice(i915->drm.dev, "Resetting chip for %s\n", reason);
 	error->reset_count++;
 
 	disable_irq(i915->drm.irq);
@@ -1949,7 +1959,7 @@ void i915_reset(struct drm_i915_private *i915, unsigned int flags)
 		goto error;
 	}
 
-	i915_gem_reset(i915);
+	i915_gem_reset(i915, stalled_mask);
 	intel_overlay_reset(i915);
 
 	/*
@@ -1995,7 +2005,6 @@ taint:
 error:
 	i915_gem_set_wedged(i915);
 	i915_retire_requests(i915);
-	intel_gpu_reset(i915, ALL_ENGINES);
 	goto finish;
 }
 
@@ -2008,7 +2017,7 @@ static inline int intel_gt_reset_engine(struct drm_i915_private *dev_priv,
 /**
  * i915_reset_engine - reset GPU engine to recover from a hang
  * @engine: engine to reset
- * @flags: options
+ * @msg: reason for GPU reset; or NULL for no dev_notice()
  *
  * Reset a specific GPU engine. Useful if a hang is detected.
  * Returns zero on successful reset or otherwise an error code.
@@ -2018,12 +2027,13 @@ static inline int intel_gt_reset_engine(struct drm_i915_private *dev_priv,
  *  - reset engine (which will force the engine to idle)
  *  - re-init/configure engine
  */
-int i915_reset_engine(struct intel_engine_cs *engine, unsigned int flags)
+int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
 {
 	struct i915_gpu_error *error = &engine->i915->gpu_error;
 	struct i915_request *active_request;
 	int ret;
 
+	GEM_TRACE("%s flags=%lx\n", engine->name, error->flags);
 	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags));
 
 	active_request = i915_gem_reset_prepare_engine(engine);
@@ -2033,10 +2043,9 @@ int i915_reset_engine(struct intel_engine_cs *engine, unsigned int flags)
 		goto out;
 	}
 
-	if (!(flags & I915_RESET_QUIET)) {
+	if (msg)
 		dev_notice(engine->i915->drm.dev,
-			   "Resetting %s after gpu hang\n", engine->name);
-	}
+			   "Resetting %s for %s\n", engine->name, msg);
 	error->reset_engine_count[engine->id]++;
 
 	if (!engine->i915->guc.execbuf_client)
@@ -2056,7 +2065,7 @@ int i915_reset_engine(struct intel_engine_cs *engine, unsigned int flags)
 	 * active request and can drop it, adjust head to skip the offending
 	 * request to resume executing remaining requests in the queue.
 	 */
-	i915_gem_reset_engine(engine, active_request);
+	i915_gem_reset_engine(engine, active_request, true);
 
 	/*
 	 * The engine and its registers (and workarounds in case of render)
@@ -2465,10 +2474,13 @@ static void vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv,
 	/*
 	 * RC6 transitioning can be delayed up to 2 msec (see
 	 * valleyview_enable_rps), use 3 msec for safety.
+	 *
+	 * This can fail to turn off the rc6 if the GPU is stuck after a failed
+	 * reset and we are trying to force the machine to sleep.
 	 */
 	if (vlv_wait_for_pw_status(dev_priv, mask, val))
-		DRM_ERROR("timeout waiting for GT wells to go %s\n",
-			  onoff(wait_for_on));
+		DRM_DEBUG_DRIVER("timeout waiting for GT wells to go %s\n",
+				 onoff(wait_for_on));
 }
 
 static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv)
@@ -2819,10 +2831,10 @@ static const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GET_PIPE_FROM_CRTC_ID, intel_get_pipe_from_crtc_id_ioctl, 0),
 	DRM_IOCTL_DEF_DRV(I915_GEM_MADVISE, i915_gem_madvise_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image_ioctl, DRM_MASTER),
+	DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs_ioctl, DRM_MASTER),
+	DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey_ioctl, DRM_MASTER),
+	DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, drm_noop, DRM_MASTER),
 	DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_RENDER_ALLOW),
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ce18b6cf6e68..34c125e2d90c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -64,6 +64,7 @@
 #include "intel_opregion.h"
 #include "intel_ringbuffer.h"
 #include "intel_uncore.h"
+#include "intel_wopcm.h"
 #include "intel_uc.h"
 
 #include "i915_gem.h"
@@ -71,9 +72,10 @@
 #include "i915_gem_fence_reg.h"
 #include "i915_gem_object.h"
 #include "i915_gem_gtt.h"
-#include "i915_gem_timeline.h"
-
+#include "i915_gpu_error.h"
 #include "i915_request.h"
+#include "i915_scheduler.h"
+#include "i915_timeline.h"
 #include "i915_vma.h"
 
 #include "intel_gvt.h"
@@ -83,8 +85,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180308"
-#define DRIVER_TIMESTAMP	1520513379
+#define DRIVER_DATE		"20180514"
+#define DRIVER_TIMESTAMP	1526300884
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
@@ -261,6 +263,7 @@ enum hpd_pin {
 	HPD_PORT_C,
 	HPD_PORT_D,
 	HPD_PORT_E,
+	HPD_PORT_F,
 	HPD_NUM_PINS
 };
 
@@ -453,172 +456,6 @@ struct intel_csr {
 	uint32_t allowed_dc_mask;
 };
 
-struct intel_display_error_state;
-
-struct i915_gpu_state {
-	struct kref ref;
-	ktime_t time;
-	ktime_t boottime;
-	ktime_t uptime;
-
-	struct drm_i915_private *i915;
-
-	char error_msg[128];
-	bool simulated;
-	bool awake;
-	bool wakelock;
-	bool suspended;
-	int iommu;
-	u32 reset_count;
-	u32 suspend_count;
-	struct intel_device_info device_info;
-	struct intel_driver_caps driver_caps;
-	struct i915_params params;
-
-	struct i915_error_uc {
-		struct intel_uc_fw guc_fw;
-		struct intel_uc_fw huc_fw;
-		struct drm_i915_error_object *guc_log;
-	} uc;
-
-	/* Generic register state */
-	u32 eir;
-	u32 pgtbl_er;
-	u32 ier;
-	u32 gtier[4], ngtier;
-	u32 ccid;
-	u32 derrmr;
-	u32 forcewake;
-	u32 error; /* gen6+ */
-	u32 err_int; /* gen7 */
-	u32 fault_data0; /* gen8, gen9 */
-	u32 fault_data1; /* gen8, gen9 */
-	u32 done_reg;
-	u32 gac_eco;
-	u32 gam_ecochk;
-	u32 gab_ctl;
-	u32 gfx_mode;
-
-	u32 nfence;
-	u64 fence[I915_MAX_NUM_FENCES];
-	struct intel_overlay_error_state *overlay;
-	struct intel_display_error_state *display;
-
-	struct drm_i915_error_engine {
-		int engine_id;
-		/* Software tracked state */
-		bool idle;
-		bool waiting;
-		int num_waiters;
-		unsigned long hangcheck_timestamp;
-		bool hangcheck_stalled;
-		enum intel_engine_hangcheck_action hangcheck_action;
-		struct i915_address_space *vm;
-		int num_requests;
-		u32 reset_count;
-
-		/* position of active request inside the ring */
-		u32 rq_head, rq_post, rq_tail;
-
-		/* our own tracking of ring head and tail */
-		u32 cpu_ring_head;
-		u32 cpu_ring_tail;
-
-		u32 last_seqno;
-
-		/* Register state */
-		u32 start;
-		u32 tail;
-		u32 head;
-		u32 ctl;
-		u32 mode;
-		u32 hws;
-		u32 ipeir;
-		u32 ipehr;
-		u32 bbstate;
-		u32 instpm;
-		u32 instps;
-		u32 seqno;
-		u64 bbaddr;
-		u64 acthd;
-		u32 fault_reg;
-		u64 faddr;
-		u32 rc_psmi; /* sleep state */
-		u32 semaphore_mboxes[I915_NUM_ENGINES - 1];
-		struct intel_instdone instdone;
-
-		struct drm_i915_error_context {
-			char comm[TASK_COMM_LEN];
-			pid_t pid;
-			u32 handle;
-			u32 hw_id;
-			int priority;
-			int ban_score;
-			int active;
-			int guilty;
-			bool bannable;
-		} context;
-
-		struct drm_i915_error_object {
-			u64 gtt_offset;
-			u64 gtt_size;
-			int page_count;
-			int unused;
-			u32 *pages[0];
-		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
-
-		struct drm_i915_error_object **user_bo;
-		long user_bo_count;
-
-		struct drm_i915_error_object *wa_ctx;
-		struct drm_i915_error_object *default_state;
-
-		struct drm_i915_error_request {
-			long jiffies;
-			pid_t pid;
-			u32 context;
-			int priority;
-			int ban_score;
-			u32 seqno;
-			u32 head;
-			u32 tail;
-		} *requests, execlist[EXECLIST_MAX_PORTS];
-		unsigned int num_ports;
-
-		struct drm_i915_error_waiter {
-			char comm[TASK_COMM_LEN];
-			pid_t pid;
-			u32 seqno;
-		} *waiters;
-
-		struct {
-			u32 gfx_mode;
-			union {
-				u64 pdp[4];
-				u32 pp_dir_base;
-			};
-		} vm_info;
-	} engine[I915_NUM_ENGINES];
-
-	struct drm_i915_error_buffer {
-		u32 size;
-		u32 name;
-		u32 rseqno[I915_NUM_ENGINES], wseqno;
-		u64 gtt_offset;
-		u32 read_domains;
-		u32 write_domain;
-		s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
-		u32 tiling:2;
-		u32 dirty:1;
-		u32 purgeable:1;
-		u32 userptr:1;
-		s32 engine:4;
-		u32 cache_level:3;
-	} *active_bo[I915_NUM_ENGINES], *pinned_bo;
-	u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count;
-	struct i915_address_space *active_vm[I915_NUM_ENGINES];
-};
-
 enum i915_cache_level {
 	I915_CACHE_NONE = 0,
 	I915_CACHE_LLC, /* also used for snoopable memory on non-LLC */
@@ -766,12 +603,16 @@ struct i915_psr {
 	bool active;
 	struct delayed_work work;
 	unsigned busy_frontbuffer_bits;
-	bool psr2_support;
-	bool aux_frame_sync;
+	bool sink_psr2_support;
 	bool link_standby;
-	bool y_cord_support;
 	bool colorimetry_support;
 	bool alpm;
+	bool has_hw_tracking;
+	bool psr2_enabled;
+	u8 sink_sync_latency;
+	bool debug;
+	ktime_t last_entry_attempt;
+	ktime_t last_exit;
 
 	void (*enable_source)(struct intel_dp *,
 			      const struct intel_crtc_state *);
@@ -1146,16 +987,6 @@ struct i915_gem_mm {
 	u32 object_count;
 };
 
-struct drm_i915_error_state_buf {
-	struct drm_i915_private *i915;
-	unsigned bytes;
-	unsigned size;
-	int err;
-	u8 *buf;
-	loff_t start;
-	loff_t pos;
-};
-
 #define I915_IDLE_ENGINES_TIMEOUT (200) /* in ms */
 
 #define I915_RESET_TIMEOUT (10 * HZ) /* 10s */
@@ -1164,102 +995,6 @@ struct drm_i915_error_state_buf {
 #define I915_ENGINE_DEAD_TIMEOUT  (4 * HZ)  /* Seqno, head and subunits dead */
 #define I915_SEQNO_DEAD_TIMEOUT   (12 * HZ) /* Seqno dead with active head */
 
-struct i915_gpu_error {
-	/* For hangcheck timer */
-#define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
-#define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD)
-
-	struct delayed_work hangcheck_work;
-
-	/* For reset and error_state handling. */
-	spinlock_t lock;
-	/* Protected by the above dev->gpu_error.lock. */
-	struct i915_gpu_state *first_error;
-
-	atomic_t pending_fb_pin;
-
-	unsigned long missed_irq_rings;
-
-	/**
-	 * State variable controlling the reset flow and count
-	 *
-	 * This is a counter which gets incremented when reset is triggered,
-	 *
-	 * Before the reset commences, the I915_RESET_BACKOFF bit is set
-	 * meaning that any waiters holding onto the struct_mutex should
-	 * relinquish the lock immediately in order for the reset to start.
-	 *
-	 * If reset is not completed succesfully, the I915_WEDGE bit is
-	 * set meaning that hardware is terminally sour and there is no
-	 * recovery. All waiters on the reset_queue will be woken when
-	 * that happens.
-	 *
-	 * This counter is used by the wait_seqno code to notice that reset
-	 * event happened and it needs to restart the entire ioctl (since most
-	 * likely the seqno it waited for won't ever signal anytime soon).
-	 *
-	 * This is important for lock-free wait paths, where no contended lock
-	 * naturally enforces the correct ordering between the bail-out of the
-	 * waiter and the gpu reset work code.
-	 */
-	unsigned long reset_count;
-
-	/**
-	 * flags: Control various stages of the GPU reset
-	 *
-	 * #I915_RESET_BACKOFF - When we start a reset, we want to stop any
-	 * other users acquiring the struct_mutex. To do this we set the
-	 * #I915_RESET_BACKOFF bit in the error flags when we detect a reset
-	 * and then check for that bit before acquiring the struct_mutex (in
-	 * i915_mutex_lock_interruptible()?). I915_RESET_BACKOFF serves a
-	 * secondary role in preventing two concurrent global reset attempts.
-	 *
-	 * #I915_RESET_HANDOFF - To perform the actual GPU reset, we need the
-	 * struct_mutex. We try to acquire the struct_mutex in the reset worker,
-	 * but it may be held by some long running waiter (that we cannot
-	 * interrupt without causing trouble). Once we are ready to do the GPU
-	 * reset, we set the I915_RESET_HANDOFF bit and wakeup any waiters. If
-	 * they already hold the struct_mutex and want to participate they can
-	 * inspect the bit and do the reset directly, otherwise the worker
-	 * waits for the struct_mutex.
-	 *
-	 * #I915_RESET_ENGINE[num_engines] - Since the driver doesn't need to
-	 * acquire the struct_mutex to reset an engine, we need an explicit
-	 * flag to prevent two concurrent reset attempts in the same engine.
-	 * As the number of engines continues to grow, allocate the flags from
-	 * the most significant bits.
-	 *
-	 * #I915_WEDGED - If reset fails and we can no longer use the GPU,
-	 * we set the #I915_WEDGED bit. Prior to command submission, e.g.
-	 * i915_request_alloc(), this bit is checked and the sequence
-	 * aborted (with -EIO reported to userspace) if set.
-	 */
-	unsigned long flags;
-#define I915_RESET_BACKOFF	0
-#define I915_RESET_HANDOFF	1
-#define I915_RESET_MODESET	2
-#define I915_WEDGED		(BITS_PER_LONG - 1)
-#define I915_RESET_ENGINE	(I915_WEDGED - I915_NUM_ENGINES)
-
-	/** Number of times an engine has been reset */
-	u32 reset_engine_count[I915_NUM_ENGINES];
-
-	/**
-	 * Waitqueue to signal when a hang is detected. Used to for waiters
-	 * to release the struct_mutex for the reset to procede.
-	 */
-	wait_queue_head_t wait_queue;
-
-	/**
-	 * Waitqueue to signal when the reset has completed. Used by clients
-	 * that wait for dev_priv->mm.wedged to settle.
-	 */
-	wait_queue_head_t reset_queue;
-
-	/* For missed irq/seqno simulation. */
-	unsigned long test_irq_rings;
-};
-
 enum modeset_restore {
 	MODESET_ON_LID_OPEN,
 	MODESET_DONE,
@@ -1338,6 +1073,7 @@ struct intel_vbt_data {
 	} edp;
 
 	struct {
+		bool enable;
 		bool full_link;
 		bool require_aux_wakeup;
 		int idle_frames;
@@ -1451,11 +1187,13 @@ static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1,
 }
 
 struct skl_ddb_allocation {
-	struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* packed/uv */
-	struct skl_ddb_entry y_plane[I915_MAX_PIPES][I915_MAX_PLANES];
+	/* packed/y */
+	struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES];
+	struct skl_ddb_entry uv_plane[I915_MAX_PIPES][I915_MAX_PLANES];
+	u8 enabled_slices; /* GEN11 has configurable 2 slices */
 };
 
-struct skl_wm_values {
+struct skl_ddb_values {
 	unsigned dirty_pipes;
 	struct skl_ddb_allocation ddb;
 };
@@ -1470,6 +1208,7 @@ struct skl_wm_level {
 struct skl_wm_params {
 	bool x_tiled, y_tiled;
 	bool rc_surface;
+	bool is_planar;
 	uint32_t width;
 	uint8_t cpp;
 	uint32_t plane_pixel_rate;
@@ -1564,7 +1303,6 @@ struct i915_wa_reg {
 struct i915_workarounds {
 	struct i915_wa_reg reg[I915_MAX_WA_REGS];
 	u32 count;
-	u32 hw_whitelist_count[I915_NUM_ENGINES];
 };
 
 struct i915_virtual_gpu {
@@ -1860,6 +1598,8 @@ struct drm_i915_private {
 
 	struct intel_gvt *gvt;
 
+	struct intel_wopcm wopcm;
+
 	struct intel_huc huc;
 	struct intel_guc guc;
 
@@ -2152,7 +1892,7 @@ struct drm_i915_private {
 		/* current hardware state */
 		union {
 			struct ilk_wm_values hw;
-			struct skl_wm_values skl_hw;
+			struct skl_ddb_values skl_hw;
 			struct vlv_wm_values vlv;
 			struct g4x_wm_values g4x;
 		};
@@ -2321,8 +2061,11 @@ struct drm_i915_private {
 		void (*cleanup_engine)(struct intel_engine_cs *engine);
 
 		struct list_head timelines;
-		struct i915_gem_timeline global_timeline;
+
+		struct list_head active_rings;
+		struct list_head closed_vma;
 		u32 active_requests;
+		u32 request_serial;
 
 		/**
 		 * Is the GPU currently considered idle, or busy executing
@@ -2392,6 +2135,11 @@ static inline struct drm_i915_private *kdev_to_i915(struct device *kdev)
 	return to_i915(dev_get_drvdata(kdev));
 }
 
+static inline struct drm_i915_private *wopcm_to_i915(struct intel_wopcm *wopcm)
+{
+	return container_of(wopcm, struct drm_i915_private, wopcm);
+}
+
 static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc)
 {
 	return container_of(guc, struct drm_i915_private, guc);
@@ -2411,8 +2159,10 @@ static inline struct drm_i915_private *huc_to_i915(struct intel_huc *huc)
 
 /* Iterator over subset of engines selected by mask */
 #define for_each_engine_masked(engine__, dev_priv__, mask__, tmp__) \
-	for (tmp__ = mask__ & INTEL_INFO(dev_priv__)->ring_mask;	\
-	     tmp__ ? (engine__ = (dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : 0; )
+	for ((tmp__) = (mask__) & INTEL_INFO(dev_priv__)->ring_mask; \
+	     (tmp__) ? \
+	     ((engine__) = (dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : \
+	     0;)
 
 enum hdmi_force_audio {
 	HDMI_AUDIO_OFF_DVI = -2,	/* no aux data for HDMI-DVI converter */
@@ -2720,6 +2470,15 @@ intel_info(const struct drm_i915_private *dev_priv)
 #define IS_CNL_REVID(p, since, until) \
 	(IS_CANNONLAKE(p) && IS_REVID(p, since, until))
 
+#define ICL_REVID_A0		0x0
+#define ICL_REVID_A2		0x1
+#define ICL_REVID_B0		0x3
+#define ICL_REVID_B2		0x4
+#define ICL_REVID_C0		0x5
+
+#define IS_ICL_REVID(p, since, until) \
+	(IS_ICELAKE(p) && IS_REVID(p, since, until))
+
 /*
  * The genX designation typically refers to the render engine, so render
  * capability related checks should use IS_GEN, while display and other checks
@@ -2963,10 +2722,11 @@ extern void i915_driver_unload(struct drm_device *dev);
 extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask);
 extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv);
 
-#define I915_RESET_QUIET BIT(0)
-extern void i915_reset(struct drm_i915_private *i915, unsigned int flags);
+extern void i915_reset(struct drm_i915_private *i915,
+		       unsigned int stalled_mask,
+		       const char *reason);
 extern int i915_reset_engine(struct intel_engine_cs *engine,
-			     unsigned int flags);
+			     const char *reason);
 
 extern bool intel_has_reset_engine(struct drm_i915_private *dev_priv);
 extern int intel_reset_guc(struct drm_i915_private *dev_priv);
@@ -3014,10 +2774,12 @@ static inline void i915_queue_hangcheck(struct drm_i915_private *dev_priv)
 			   &dev_priv->gpu_error.hangcheck_work, delay);
 }
 
-__printf(3, 4)
+__printf(4, 5)
 void i915_handle_error(struct drm_i915_private *dev_priv,
 		       u32 engine_mask,
+		       unsigned long flags,
 		       const char *fmt, ...);
+#define I915_ERROR_CAPTURE BIT(0)
 
 extern void intel_irq_init(struct drm_i915_private *dev_priv);
 extern void intel_irq_fini(struct drm_i915_private *dev_priv);
@@ -3132,8 +2894,8 @@ int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 void i915_gem_sanitize(struct drm_i915_private *i915);
-int i915_gem_load_init(struct drm_i915_private *dev_priv);
-void i915_gem_load_cleanup(struct drm_i915_private *dev_priv);
+int i915_gem_init_early(struct drm_i915_private *dev_priv);
+void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
 void i915_gem_load_init_fences(struct drm_i915_private *dev_priv);
 int i915_gem_freeze(struct drm_i915_private *dev_priv);
 int i915_gem_freeze_late(struct drm_i915_private *dev_priv);
@@ -3388,13 +3150,15 @@ static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
 struct i915_request *
 i915_gem_reset_prepare_engine(struct intel_engine_cs *engine);
 int i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
-void i915_gem_reset(struct drm_i915_private *dev_priv);
+void i915_gem_reset(struct drm_i915_private *dev_priv,
+		    unsigned int stalled_mask);
 void i915_gem_reset_finish_engine(struct intel_engine_cs *engine);
 void i915_gem_reset_finish(struct drm_i915_private *dev_priv);
 void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
 bool i915_gem_unset_wedged(struct drm_i915_private *dev_priv);
 void i915_gem_reset_engine(struct intel_engine_cs *engine,
-			   struct i915_request *request);
+			   struct i915_request *request,
+			   bool stalled);
 
 void i915_gem_init_mmio(struct drm_i915_private *i915);
 int __must_check i915_gem_init(struct drm_i915_private *dev_priv);
@@ -3412,7 +3176,7 @@ int i915_gem_object_wait(struct drm_i915_gem_object *obj,
 			 struct intel_rps_client *rps);
 int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 				  unsigned int flags,
-				  int priority);
+				  const struct i915_sched_attr *attr);
 #define I915_PRIORITY_DISPLAY I915_PRIORITY_MAX
 
 int __must_check
@@ -3481,16 +3245,6 @@ i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
 	return ctx;
 }
 
-static inline struct intel_timeline *
-i915_gem_context_lookup_timeline(struct i915_gem_context *ctx,
-				 struct intel_engine_cs *engine)
-{
-	struct i915_address_space *vm;
-
-	vm = ctx->ppgtt ? &ctx->ppgtt->base : &ctx->i915->ggtt.base;
-	return &vm->timeline.engine[engine->id];
-}
-
 int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file);
 int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
@@ -3589,64 +3343,6 @@ static inline int i915_debugfs_connector_add(struct drm_connector *connector)
 static inline void intel_display_crc_init(struct drm_i915_private *dev_priv) {}
 #endif
 
-/* i915_gpu_error.c */
-#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
-
-__printf(2, 3)
-void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
-int i915_error_state_to_str(struct drm_i915_error_state_buf *estr,
-			    const struct i915_gpu_state *gpu);
-int i915_error_state_buf_init(struct drm_i915_error_state_buf *eb,
-			      struct drm_i915_private *i915,
-			      size_t count, loff_t pos);
-static inline void i915_error_state_buf_release(
-	struct drm_i915_error_state_buf *eb)
-{
-	kfree(eb->buf);
-}
-
-struct i915_gpu_state *i915_capture_gpu_state(struct drm_i915_private *i915);
-void i915_capture_error_state(struct drm_i915_private *dev_priv,
-			      u32 engine_mask,
-			      const char *error_msg);
-
-static inline struct i915_gpu_state *
-i915_gpu_state_get(struct i915_gpu_state *gpu)
-{
-	kref_get(&gpu->ref);
-	return gpu;
-}
-
-void __i915_gpu_state_free(struct kref *kref);
-static inline void i915_gpu_state_put(struct i915_gpu_state *gpu)
-{
-	if (gpu)
-		kref_put(&gpu->ref, __i915_gpu_state_free);
-}
-
-struct i915_gpu_state *i915_first_error_state(struct drm_i915_private *i915);
-void i915_reset_error_state(struct drm_i915_private *i915);
-
-#else
-
-static inline void i915_capture_error_state(struct drm_i915_private *dev_priv,
-					    u32 engine_mask,
-					    const char *error_msg)
-{
-}
-
-static inline struct i915_gpu_state *
-i915_first_error_state(struct drm_i915_private *i915)
-{
-	return NULL;
-}
-
-static inline void i915_reset_error_state(struct drm_i915_private *i915)
-{
-}
-
-#endif
-
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 
 /* i915_cmd_parser.c */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 7b5a9d7c9593..0a2070112b66 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -35,6 +35,7 @@
 #include "intel_drv.h"
 #include "intel_frontbuffer.h"
 #include "intel_mocs.h"
+#include "intel_workarounds.h"
 #include "i915_gemfs.h"
 #include <linux/dma-fence-array.h>
 #include <linux/kthread.h>
@@ -136,6 +137,102 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
 	return 0;
 }
 
+static u32 __i915_gem_park(struct drm_i915_private *i915)
+{
+	lockdep_assert_held(&i915->drm.struct_mutex);
+	GEM_BUG_ON(i915->gt.active_requests);
+	GEM_BUG_ON(!list_empty(&i915->gt.active_rings));
+
+	if (!i915->gt.awake)
+		return I915_EPOCH_INVALID;
+
+	GEM_BUG_ON(i915->gt.epoch == I915_EPOCH_INVALID);
+
+	/*
+	 * Be paranoid and flush a concurrent interrupt to make sure
+	 * we don't reactivate any irq tasklets after parking.
+	 *
+	 * FIXME: Note that even though we have waited for execlists to be idle,
+	 * there may still be an in-flight interrupt even though the CSB
+	 * is now empty. synchronize_irq() makes sure that a residual interrupt
+	 * is completed before we continue, but it doesn't prevent the HW from
+	 * raising a spurious interrupt later. To complete the shield we should
+	 * coordinate disabling the CS irq with flushing the interrupts.
+	 */
+	synchronize_irq(i915->drm.irq);
+
+	intel_engines_park(i915);
+	i915_timelines_park(i915);
+
+	i915_pmu_gt_parked(i915);
+	i915_vma_parked(i915);
+
+	i915->gt.awake = false;
+
+	if (INTEL_GEN(i915) >= 6)
+		gen6_rps_idle(i915);
+
+	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ);
+
+	intel_runtime_pm_put(i915);
+
+	return i915->gt.epoch;
+}
+
+void i915_gem_park(struct drm_i915_private *i915)
+{
+	lockdep_assert_held(&i915->drm.struct_mutex);
+	GEM_BUG_ON(i915->gt.active_requests);
+
+	if (!i915->gt.awake)
+		return;
+
+	/* Defer the actual call to __i915_gem_park() to prevent ping-pongs */
+	mod_delayed_work(i915->wq, &i915->gt.idle_work, msecs_to_jiffies(100));
+}
+
+void i915_gem_unpark(struct drm_i915_private *i915)
+{
+	lockdep_assert_held(&i915->drm.struct_mutex);
+	GEM_BUG_ON(!i915->gt.active_requests);
+
+	if (i915->gt.awake)
+		return;
+
+	intel_runtime_pm_get_noresume(i915);
+
+	/*
+	 * It seems that the DMC likes to transition between the DC states a lot
+	 * when there are no connected displays (no active power domains) during
+	 * command submission.
+	 *
+	 * This activity has negative impact on the performance of the chip with
+	 * huge latencies observed in the interrupt handler and elsewhere.
+	 *
+	 * Work around it by grabbing a GT IRQ power domain whilst there is any
+	 * GT activity, preventing any DC state transitions.
+	 */
+	intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
+
+	i915->gt.awake = true;
+	if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */
+		i915->gt.epoch = 1;
+
+	intel_enable_gt_powersave(i915);
+	i915_update_gfx_val(i915);
+	if (INTEL_GEN(i915) >= 6)
+		gen6_rps_busy(i915);
+	i915_pmu_gt_unparked(i915);
+
+	intel_engines_unpark(i915);
+
+	i915_queue_hangcheck(i915);
+
+	queue_delayed_work(i915->wq,
+			   &i915->gt.retire_work,
+			   round_jiffies_up_relative(HZ));
+}
+
 int
 i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *file)
@@ -469,7 +566,8 @@ i915_gem_object_wait_reservation(struct reservation_object *resv,
 	return timeout;
 }
 
-static void __fence_set_priority(struct dma_fence *fence, int prio)
+static void __fence_set_priority(struct dma_fence *fence,
+				 const struct i915_sched_attr *attr)
 {
 	struct i915_request *rq;
 	struct intel_engine_cs *engine;
@@ -480,13 +578,16 @@ static void __fence_set_priority(struct dma_fence *fence, int prio)
 	rq = to_request(fence);
 	engine = rq->engine;
 
-	rcu_read_lock();
+	local_bh_disable();
+	rcu_read_lock(); /* RCU serialisation for set-wedged protection */
 	if (engine->schedule)
-		engine->schedule(rq, prio);
+		engine->schedule(rq, attr);
 	rcu_read_unlock();
+	local_bh_enable(); /* kick the tasklets if queues were reprioritised */
 }
 
-static void fence_set_priority(struct dma_fence *fence, int prio)
+static void fence_set_priority(struct dma_fence *fence,
+			       const struct i915_sched_attr *attr)
 {
 	/* Recurse once into a fence-array */
 	if (dma_fence_is_array(fence)) {
@@ -494,16 +595,16 @@ static void fence_set_priority(struct dma_fence *fence, int prio)
 		int i;
 
 		for (i = 0; i < array->num_fences; i++)
-			__fence_set_priority(array->fences[i], prio);
+			__fence_set_priority(array->fences[i], attr);
 	} else {
-		__fence_set_priority(fence, prio);
+		__fence_set_priority(fence, attr);
 	}
 }
 
 int
 i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 			      unsigned int flags,
-			      int prio)
+			      const struct i915_sched_attr *attr)
 {
 	struct dma_fence *excl;
 
@@ -518,7 +619,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 			return ret;
 
 		for (i = 0; i < count; i++) {
-			fence_set_priority(shared[i], prio);
+			fence_set_priority(shared[i], attr);
 			dma_fence_put(shared[i]);
 		}
 
@@ -528,7 +629,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 	}
 
 	if (excl) {
-		fence_set_priority(excl, prio);
+		fence_set_priority(excl, attr);
 		dma_fence_put(excl);
 	}
 	return 0;
@@ -2879,8 +2980,8 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
 	 * extra delay for a recent interrupt is pointless. Hence, we do
 	 * not need an engine->irq_seqno_barrier() before the seqno reads.
 	 */
-	spin_lock_irqsave(&engine->timeline->lock, flags);
-	list_for_each_entry(request, &engine->timeline->requests, link) {
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	list_for_each_entry(request, &engine->timeline.requests, link) {
 		if (__i915_request_completed(request, request->global_seqno))
 			continue;
 
@@ -2891,25 +2992,11 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
 		active = request;
 		break;
 	}
-	spin_unlock_irqrestore(&engine->timeline->lock, flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 	return active;
 }
 
-static bool engine_stalled(struct intel_engine_cs *engine)
-{
-	if (!engine->hangcheck.stalled)
-		return false;
-
-	/* Check for possible seqno movement after hang declaration */
-	if (engine->hangcheck.seqno != intel_engine_get_seqno(engine)) {
-		DRM_DEBUG_DRIVER("%s pardoned\n", engine->name);
-		return false;
-	}
-
-	return true;
-}
-
 /*
  * Ensure irq handler finishes, and not run again.
  * Also return the active request so that we only search for it once.
@@ -2998,6 +3085,7 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
 	}
 
 	i915_gem_revoke_fences(dev_priv);
+	intel_uc_sanitize(dev_priv);
 
 	return err;
 }
@@ -3025,15 +3113,15 @@ static void engine_skip_context(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
 	struct i915_gem_context *hung_ctx = request->ctx;
-	struct intel_timeline *timeline;
+	struct i915_timeline *timeline = request->timeline;
 	unsigned long flags;
 
-	timeline = i915_gem_context_lookup_timeline(hung_ctx, engine);
+	GEM_BUG_ON(timeline == &engine->timeline);
 
-	spin_lock_irqsave(&engine->timeline->lock, flags);
-	spin_lock(&timeline->lock);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	spin_lock_nested(&timeline->lock, SINGLE_DEPTH_NESTING);
 
-	list_for_each_entry_continue(request, &engine->timeline->requests, link)
+	list_for_each_entry_continue(request, &engine->timeline.requests, link)
 		if (request->ctx == hung_ctx)
 			skip_request(request);
 
@@ -3041,13 +3129,14 @@ static void engine_skip_context(struct i915_request *request)
 		skip_request(request);
 
 	spin_unlock(&timeline->lock);
-	spin_unlock_irqrestore(&engine->timeline->lock, flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
 /* Returns the request if it was guilty of the hang */
 static struct i915_request *
 i915_gem_reset_request(struct intel_engine_cs *engine,
-		       struct i915_request *request)
+		       struct i915_request *request,
+		       bool stalled)
 {
 	/* The guilty request will get skipped on a hung engine.
 	 *
@@ -3070,7 +3159,15 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 	 * subsequent hangs.
 	 */
 
-	if (engine_stalled(engine)) {
+	if (i915_request_completed(request)) {
+		GEM_TRACE("%s pardoned global=%d (fence %llx:%d), current %d\n",
+			  engine->name, request->global_seqno,
+			  request->fence.context, request->fence.seqno,
+			  intel_engine_get_seqno(engine));
+		stalled = false;
+	}
+
+	if (stalled) {
 		i915_gem_context_mark_guilty(request->ctx);
 		skip_request(request);
 
@@ -3089,11 +3186,11 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 			dma_fence_set_error(&request->fence, -EAGAIN);
 
 			/* Rewind the engine to replay the incomplete rq */
-			spin_lock_irq(&engine->timeline->lock);
+			spin_lock_irq(&engine->timeline.lock);
 			request = list_prev_entry(request, link);
-			if (&request->link == &engine->timeline->requests)
+			if (&request->link == &engine->timeline.requests)
 				request = NULL;
-			spin_unlock_irq(&engine->timeline->lock);
+			spin_unlock_irq(&engine->timeline.lock);
 		}
 	}
 
@@ -3101,7 +3198,8 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 }
 
 void i915_gem_reset_engine(struct intel_engine_cs *engine,
-			   struct i915_request *request)
+			   struct i915_request *request,
+			   bool stalled)
 {
 	/*
 	 * Make sure this write is visible before we re-enable the interrupt
@@ -3111,7 +3209,7 @@ void i915_gem_reset_engine(struct intel_engine_cs *engine,
 	smp_store_mb(engine->irq_posted, 0);
 
 	if (request)
-		request = i915_gem_reset_request(engine, request);
+		request = i915_gem_reset_request(engine, request, stalled);
 
 	if (request) {
 		DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n",
@@ -3122,7 +3220,8 @@ void i915_gem_reset_engine(struct intel_engine_cs *engine,
 	engine->reset_hw(engine, request);
 }
 
-void i915_gem_reset(struct drm_i915_private *dev_priv)
+void i915_gem_reset(struct drm_i915_private *dev_priv,
+		    unsigned int stalled_mask)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -3134,10 +3233,12 @@ void i915_gem_reset(struct drm_i915_private *dev_priv)
 	for_each_engine(engine, dev_priv, id) {
 		struct i915_gem_context *ctx;
 
-		i915_gem_reset_engine(engine, engine->hangcheck.active_request);
+		i915_gem_reset_engine(engine,
+				      engine->hangcheck.active_request,
+				      stalled_mask & ENGINE_MASK(id));
 		ctx = fetch_and_zero(&engine->last_retired_context);
 		if (ctx)
-			engine->context_unpin(engine, ctx);
+			intel_context_unpin(ctx, engine);
 
 		/*
 		 * Ostensibily, we always want a context loaded for powersaving,
@@ -3160,13 +3261,6 @@ void i915_gem_reset(struct drm_i915_private *dev_priv)
 	}
 
 	i915_gem_restore_fences(dev_priv);
-
-	if (dev_priv->gt.awake) {
-		intel_sanitize_gt_powersave(dev_priv);
-		intel_enable_gt_powersave(dev_priv);
-		if (INTEL_GEN(dev_priv) >= 6)
-			gen6_rps_busy(dev_priv);
-	}
 }
 
 void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
@@ -3192,6 +3286,9 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
 
 static void nop_submit_request(struct i915_request *request)
 {
+	GEM_TRACE("%s fence %llx:%d -> -EIO\n",
+		  request->engine->name,
+		  request->fence.context, request->fence.seqno);
 	dma_fence_set_error(&request->fence, -EIO);
 
 	i915_request_submit(request);
@@ -3201,12 +3298,15 @@ static void nop_complete_submit_request(struct i915_request *request)
 {
 	unsigned long flags;
 
+	GEM_TRACE("%s fence %llx:%d -> -EIO\n",
+		  request->engine->name,
+		  request->fence.context, request->fence.seqno);
 	dma_fence_set_error(&request->fence, -EIO);
 
-	spin_lock_irqsave(&request->engine->timeline->lock, flags);
+	spin_lock_irqsave(&request->engine->timeline.lock, flags);
 	__i915_request_submit(request);
 	intel_engine_init_global_seqno(request->engine, request->global_seqno);
-	spin_unlock_irqrestore(&request->engine->timeline->lock, flags);
+	spin_unlock_irqrestore(&request->engine->timeline.lock, flags);
 }
 
 void i915_gem_set_wedged(struct drm_i915_private *i915)
@@ -3214,7 +3314,9 @@ void i915_gem_set_wedged(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	if (drm_debug & DRM_UT_DRIVER) {
+	GEM_TRACE("start\n");
+
+	if (GEM_SHOW_DEBUG()) {
 		struct drm_printer p = drm_debug_printer(__func__);
 
 		for_each_engine(engine, i915, id)
@@ -3237,6 +3339,9 @@ void i915_gem_set_wedged(struct drm_i915_private *i915)
 	}
 	i915->caps.scheduler = 0;
 
+	/* Even if the GPU reset fails, it should still stop the engines */
+	intel_gpu_reset(i915, ALL_ENGINES);
+
 	/*
 	 * Make sure no one is running the old callback before we proceed with
 	 * cancelling requests and resetting the completion tracking. Otherwise
@@ -3270,27 +3375,31 @@ void i915_gem_set_wedged(struct drm_i915_private *i915)
 		 * (lockless) lookup doesn't try and wait upon the request as we
 		 * reset it.
 		 */
-		spin_lock_irqsave(&engine->timeline->lock, flags);
+		spin_lock_irqsave(&engine->timeline.lock, flags);
 		intel_engine_init_global_seqno(engine,
 					       intel_engine_last_submit(engine));
-		spin_unlock_irqrestore(&engine->timeline->lock, flags);
+		spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 		i915_gem_reset_finish_engine(engine);
 	}
 
+	GEM_TRACE("end\n");
+
 	wake_up_all(&i915->gpu_error.reset_queue);
 }
 
 bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 {
-	struct i915_gem_timeline *tl;
-	int i;
+	struct i915_timeline *tl;
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	if (!test_bit(I915_WEDGED, &i915->gpu_error.flags))
 		return true;
 
-	/* Before unwedging, make sure that all pending operations
+	GEM_TRACE("start\n");
+
+	/*
+	 * Before unwedging, make sure that all pending operations
 	 * are flushed and errored out - we may have requests waiting upon
 	 * third party fences. We marked all inflight requests as EIO, and
 	 * every execbuf since returned EIO, for consistency we want all
@@ -3300,31 +3409,33 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 	 * No more can be submitted until we reset the wedged bit.
 	 */
 	list_for_each_entry(tl, &i915->gt.timelines, link) {
-		for (i = 0; i < ARRAY_SIZE(tl->engine); i++) {
-			struct i915_request *rq;
+		struct i915_request *rq;
 
-			rq = i915_gem_active_peek(&tl->engine[i].last_request,
-						  &i915->drm.struct_mutex);
-			if (!rq)
-				continue;
+		rq = i915_gem_active_peek(&tl->last_request,
+					  &i915->drm.struct_mutex);
+		if (!rq)
+			continue;
 
-			/* We can't use our normal waiter as we want to
-			 * avoid recursively trying to handle the current
-			 * reset. The basic dma_fence_default_wait() installs
-			 * a callback for dma_fence_signal(), which is
-			 * triggered by our nop handler (indirectly, the
-			 * callback enables the signaler thread which is
-			 * woken by the nop_submit_request() advancing the seqno
-			 * and when the seqno passes the fence, the signaler
-			 * then signals the fence waking us up).
-			 */
-			if (dma_fence_default_wait(&rq->fence, true,
-						   MAX_SCHEDULE_TIMEOUT) < 0)
-				return false;
-		}
+		/*
+		 * We can't use our normal waiter as we want to
+		 * avoid recursively trying to handle the current
+		 * reset. The basic dma_fence_default_wait() installs
+		 * a callback for dma_fence_signal(), which is
+		 * triggered by our nop handler (indirectly, the
+		 * callback enables the signaler thread which is
+		 * woken by the nop_submit_request() advancing the seqno
+		 * and when the seqno passes the fence, the signaler
+		 * then signals the fence waking us up).
+		 */
+		if (dma_fence_default_wait(&rq->fence, true,
+					   MAX_SCHEDULE_TIMEOUT) < 0)
+			return false;
 	}
+	i915_retire_requests(i915);
+	GEM_BUG_ON(i915->gt.active_requests);
 
-	/* Undo nop_submit_request. We prevent all new i915 requests from
+	/*
+	 * Undo nop_submit_request. We prevent all new i915 requests from
 	 * being queued (by disallowing execbuf whilst wedged) so having
 	 * waited for all active requests above, we know the system is idle
 	 * and do not have to worry about a thread being inside
@@ -3335,6 +3446,8 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 	intel_engines_reset_default_submission(i915);
 	i915_gem_contexts_lost(i915);
 
+	GEM_TRACE("end\n");
+
 	smp_mb__before_atomic(); /* complete takeover before enabling execbuf */
 	clear_bit(I915_WEDGED, &i915->gpu_error.flags);
 
@@ -3473,36 +3586,9 @@ i915_gem_idle_work_handler(struct work_struct *work)
 	if (new_requests_since_last_retire(dev_priv))
 		goto out_unlock;
 
-	/*
-	 * Be paranoid and flush a concurrent interrupt to make sure
-	 * we don't reactivate any irq tasklets after parking.
-	 *
-	 * FIXME: Note that even though we have waited for execlists to be idle,
-	 * there may still be an in-flight interrupt even though the CSB
-	 * is now empty. synchronize_irq() makes sure that a residual interrupt
-	 * is completed before we continue, but it doesn't prevent the HW from
-	 * raising a spurious interrupt later. To complete the shield we should
-	 * coordinate disabling the CS irq with flushing the interrupts.
-	 */
-	synchronize_irq(dev_priv->drm.irq);
-
-	intel_engines_park(dev_priv);
-	i915_gem_timelines_park(dev_priv);
+	epoch = __i915_gem_park(dev_priv);
 
-	i915_pmu_gt_parked(dev_priv);
-
-	GEM_BUG_ON(!dev_priv->gt.awake);
-	dev_priv->gt.awake = false;
-	epoch = dev_priv->gt.epoch;
-	GEM_BUG_ON(epoch == I915_EPOCH_INVALID);
 	rearm_hangcheck = false;
-
-	if (INTEL_GEN(dev_priv) >= 6)
-		gen6_rps_idle(dev_priv);
-
-	intel_display_power_put(dev_priv, POWER_DOMAIN_GT_IRQ);
-
-	intel_runtime_pm_put(dev_priv);
 out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
@@ -3648,17 +3734,9 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	return ret;
 }
 
-static int wait_for_timeline(struct i915_gem_timeline *tl, unsigned int flags)
+static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags)
 {
-	int ret, i;
-
-	for (i = 0; i < ARRAY_SIZE(tl->engine); i++) {
-		ret = i915_gem_active_wait(&tl->engine[i].last_request, flags);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
+	return i915_gem_active_wait(&tl->last_request, flags);
 }
 
 static int wait_for_engines(struct drm_i915_private *i915)
@@ -3666,16 +3744,7 @@ static int wait_for_engines(struct drm_i915_private *i915)
 	if (wait_for(intel_engines_are_idle(i915), I915_IDLE_ENGINES_TIMEOUT)) {
 		dev_err(i915->drm.dev,
 			"Failed to idle engines, declaring wedged!\n");
-		if (drm_debug & DRM_UT_DRIVER) {
-			struct drm_printer p = drm_debug_printer(__func__);
-			struct intel_engine_cs *engine;
-			enum intel_engine_id id;
-
-			for_each_engine(engine, i915, id)
-				intel_engine_dump(engine, &p,
-						  "%s\n", engine->name);
-		}
-
+		GEM_TRACE_DUMP();
 		i915_gem_set_wedged(i915);
 		return -EIO;
 	}
@@ -3685,30 +3754,37 @@ static int wait_for_engines(struct drm_i915_private *i915)
 
 int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 {
-	int ret;
-
 	/* If the device is asleep, we have no requests outstanding */
 	if (!READ_ONCE(i915->gt.awake))
 		return 0;
 
 	if (flags & I915_WAIT_LOCKED) {
-		struct i915_gem_timeline *tl;
+		struct i915_timeline *tl;
+		int err;
 
 		lockdep_assert_held(&i915->drm.struct_mutex);
 
 		list_for_each_entry(tl, &i915->gt.timelines, link) {
-			ret = wait_for_timeline(tl, flags);
-			if (ret)
-				return ret;
+			err = wait_for_timeline(tl, flags);
+			if (err)
+				return err;
 		}
 		i915_retire_requests(i915);
 
-		ret = wait_for_engines(i915);
+		return wait_for_engines(i915);
 	} else {
-		ret = wait_for_timeline(&i915->gt.global_timeline, flags);
-	}
+		struct intel_engine_cs *engine;
+		enum intel_engine_id id;
+		int err;
 
-	return ret;
+		for_each_engine(engine, i915, id) {
+			err = wait_for_timeline(&engine->timeline, flags);
+			if (err)
+				return err;
+		}
+
+		return 0;
+	}
 }
 
 static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj)
@@ -4088,9 +4164,10 @@ out:
 }
 
 /*
- * Prepare buffer for display plane (scanout, cursors, etc).
- * Can be called from an uninterruptible phase (modesetting) and allows
- * any flushes to be pipelined (for pageflips).
+ * Prepare buffer for display plane (scanout, cursors, etc). Can be called from
+ * an uninterruptible phase (modesetting) and allows any flushes to be pipelined
+ * (for pageflips). We only flush the caches while preparing the buffer for
+ * display, the callers are responsible for frontbuffer flush.
  */
 struct i915_vma *
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
@@ -4146,9 +4223,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 
 	vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
 
-	/* Treat this as an end-of-frame, like intel_user_framebuffer_dirty() */
 	__i915_gem_object_flush_for_display(obj);
-	intel_fb_obj_flush(obj, ORIGIN_DIRTYFB);
 
 	/* It should now be out of any other write domains, and we can update
 	 * the domain values for our changes.
@@ -4723,7 +4798,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 					 &obj->vma_list, obj_link) {
 			GEM_BUG_ON(i915_vma_is_active(vma));
 			vma->flags &= ~I915_VMA_PIN_MASK;
-			i915_vma_close(vma);
+			i915_vma_destroy(vma);
 		}
 		GEM_BUG_ON(!list_empty(&obj->vma_list));
 		GEM_BUG_ON(!RB_EMPTY_ROOT(&obj->vma_tree));
@@ -4878,7 +4953,7 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 	enum intel_engine_id id;
 
 	for_each_engine(engine, i915, id) {
-		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline->last_request));
+		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
 		GEM_BUG_ON(engine->last_retired_context != kernel_context);
 	}
 }
@@ -4973,6 +5048,7 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	 * machines is a good idea, we don't - just in case it leaves the
 	 * machine in an unusable condition.
 	 */
+	intel_uc_sanitize(dev_priv);
 	i915_gem_sanitize(dev_priv);
 
 	intel_runtime_pm_put(dev_priv);
@@ -5118,6 +5194,8 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv)
 		}
 	}
 
+	intel_gt_workarounds_apply(dev_priv);
+
 	i915_gem_init_swizzling(dev_priv);
 
 	/*
@@ -5140,6 +5218,12 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv)
 		goto out;
 	}
 
+	ret = intel_wopcm_init_hw(&dev_priv->wopcm);
+	if (ret) {
+		DRM_ERROR("Enabling WOPCM failed (%d)\n", ret);
+		goto out;
+	}
+
 	/* We can't enable contexts until all firmware is loaded */
 	ret = intel_uc_init_hw(dev_priv);
 	if (ret) {
@@ -5207,7 +5291,7 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	for_each_engine(engine, i915, id) {
 		struct i915_vma *state;
 
-		state = ctx->engine[id].state;
+		state = to_intel_context(ctx, engine)->state;
 		if (!state)
 			continue;
 
@@ -5297,6 +5381,10 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
+	ret = intel_wopcm_init(&dev_priv->wopcm);
+	if (ret)
+		return ret;
+
 	ret = intel_uc_init_misc(dev_priv);
 	if (ret)
 		return ret;
@@ -5478,8 +5566,7 @@ static void i915_gem_init__mm(struct drm_i915_private *i915)
 	INIT_WORK(&i915->mm.free_work, __i915_gem_free_work);
 }
 
-int
-i915_gem_load_init(struct drm_i915_private *dev_priv)
+int i915_gem_init_early(struct drm_i915_private *dev_priv)
 {
 	int err = -ENOMEM;
 
@@ -5512,12 +5599,9 @@ i915_gem_load_init(struct drm_i915_private *dev_priv)
 	if (!dev_priv->priorities)
 		goto err_dependencies;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	INIT_LIST_HEAD(&dev_priv->gt.timelines);
-	err = i915_gem_timeline_init__global(dev_priv);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-	if (err)
-		goto err_priorities;
+	INIT_LIST_HEAD(&dev_priv->gt.active_rings);
+	INIT_LIST_HEAD(&dev_priv->gt.closed_vma);
 
 	i915_gem_init__mm(dev_priv);
 
@@ -5538,8 +5622,6 @@ i915_gem_load_init(struct drm_i915_private *dev_priv)
 
 	return 0;
 
-err_priorities:
-	kmem_cache_destroy(dev_priv->priorities);
 err_dependencies:
 	kmem_cache_destroy(dev_priv->dependencies);
 err_requests:
@@ -5554,17 +5636,13 @@ err_out:
 	return err;
 }
 
-void i915_gem_load_cleanup(struct drm_i915_private *dev_priv)
+void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
 {
 	i915_gem_drain_freed_objects(dev_priv);
 	GEM_BUG_ON(!llist_empty(&dev_priv->mm.free_list));
 	GEM_BUG_ON(atomic_read(&dev_priv->mm.free_count));
 	WARN_ON(dev_priv->mm.object_count);
-
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	i915_gem_timeline_fini(&dev_priv->gt.global_timeline);
 	WARN_ON(!list_empty(&dev_priv->gt.timelines));
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	kmem_cache_destroy(dev_priv->priorities);
 	kmem_cache_destroy(dev_priv->dependencies);
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index f54c4ff74ded..525920404ede 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -27,7 +27,12 @@
 
 #include <linux/bug.h>
 
+struct drm_i915_private;
+
 #ifdef CONFIG_DRM_I915_DEBUG_GEM
+
+#define GEM_SHOW_DEBUG() (drm_debug & DRM_UT_DRIVER)
+
 #define GEM_BUG_ON(condition) do { if (unlikely((condition))) {	\
 		pr_err("%s:%d GEM_BUG_ON(%s)\n", \
 		       __func__, __LINE__, __stringify(condition)); \
@@ -43,6 +48,9 @@
 #define GEM_DEBUG_BUG_ON(expr) GEM_BUG_ON(expr)
 
 #else
+
+#define GEM_SHOW_DEBUG() (0)
+
 #define GEM_BUG_ON(expr) BUILD_BUG_ON_INVALID(expr)
 #define GEM_WARN_ON(expr) (BUILD_BUG_ON_INVALID(expr), 0)
 
@@ -53,10 +61,15 @@
 
 #if IS_ENABLED(CONFIG_DRM_I915_TRACE_GEM)
 #define GEM_TRACE(...) trace_printk(__VA_ARGS__)
+#define GEM_TRACE_DUMP() ftrace_dump(DUMP_ALL)
 #else
 #define GEM_TRACE(...) do { } while (0)
+#define GEM_TRACE_DUMP() do { } while (0)
 #endif
 
 #define I915_NUM_ENGINES 8
 
+void i915_gem_park(struct drm_i915_private *i915);
+void i915_gem_unpark(struct drm_i915_private *i915);
+
 #endif /* __I915_GEM_H__ */
diff --git a/drivers/gpu/drm/i915/i915_gem_batch_pool.c b/drivers/gpu/drm/i915/i915_gem_batch_pool.c
index d3cbe8432f48..f3890b664e3f 100644
--- a/drivers/gpu/drm/i915/i915_gem_batch_pool.c
+++ b/drivers/gpu/drm/i915/i915_gem_batch_pool.c
@@ -1,29 +1,11 @@
 /*
- * Copyright © 2014 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
+ * SPDX-License-Identifier: MIT
  *
+ * Copyright © 2014-2018 Intel Corporation
  */
 
-#include "i915_drv.h"
 #include "i915_gem_batch_pool.h"
+#include "i915_drv.h"
 
 /**
  * DOC: batch pool
@@ -41,11 +23,11 @@
 
 /**
  * i915_gem_batch_pool_init() - initialize a batch buffer pool
- * @engine: the associated request submission engine
  * @pool: the batch buffer pool
+ * @engine: the associated request submission engine
  */
-void i915_gem_batch_pool_init(struct intel_engine_cs *engine,
-			      struct i915_gem_batch_pool *pool)
+void i915_gem_batch_pool_init(struct i915_gem_batch_pool *pool,
+			      struct intel_engine_cs *engine)
 {
 	int n;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_batch_pool.h b/drivers/gpu/drm/i915/i915_gem_batch_pool.h
index 10d5ac4c00d3..56947daaaf65 100644
--- a/drivers/gpu/drm/i915/i915_gem_batch_pool.h
+++ b/drivers/gpu/drm/i915/i915_gem_batch_pool.h
@@ -1,31 +1,13 @@
 /*
- * Copyright © 2014 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
+ * SPDX-License-Identifier: MIT
  *
+ * Copyright © 2014-2018 Intel Corporation
  */
 
 #ifndef I915_GEM_BATCH_POOL_H
 #define I915_GEM_BATCH_POOL_H
 
-#include "i915_drv.h"
+#include <linux/types.h>
 
 struct intel_engine_cs;
 
@@ -34,9 +16,8 @@ struct i915_gem_batch_pool {
 	struct list_head cache_list[4];
 };
 
-/* i915_gem_batch_pool.c */
-void i915_gem_batch_pool_init(struct intel_engine_cs *engine,
-			      struct i915_gem_batch_pool *pool);
+void i915_gem_batch_pool_init(struct i915_gem_batch_pool *pool,
+			      struct intel_engine_cs *engine);
 void i915_gem_batch_pool_fini(struct i915_gem_batch_pool *pool);
 struct drm_i915_gem_object*
 i915_gem_batch_pool_get(struct i915_gem_batch_pool *pool, size_t size);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index f2cbea7cf940..33f8a4b3c981 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -90,6 +90,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include "intel_workarounds.h"
 
 #define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1
 
@@ -116,15 +117,15 @@ static void lut_close(struct i915_gem_context *ctx)
 
 static void i915_gem_context_free(struct i915_gem_context *ctx)
 {
-	int i;
+	unsigned int n;
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
 
 	i915_ppgtt_put(ctx->ppgtt);
 
-	for (i = 0; i < I915_NUM_ENGINES; i++) {
-		struct intel_context *ce = &ctx->engine[i];
+	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
+		struct intel_context *ce = &ctx->__engine[n];
 
 		if (!ce->state)
 			continue;
@@ -280,7 +281,7 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	kref_init(&ctx->ref);
 	list_add_tail(&ctx->link, &dev_priv->contexts.list);
 	ctx->i915 = dev_priv;
-	ctx->priority = I915_PRIORITY_NORMAL;
+	ctx->sched.priority = I915_PRIORITY_NORMAL;
 
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
 	INIT_LIST_HEAD(&ctx->handles_list);
@@ -318,12 +319,13 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	ctx->desc_template =
 		default_desc_template(dev_priv, dev_priv->mm.aliasing_ppgtt);
 
-	/* GuC requires the ring to be placed above GUC_WOPCM_TOP. If GuC is not
+	/*
+	 * GuC requires the ring to be placed in Non-WOPCM memory. If GuC is not
 	 * present or not in use we still need a small bias as ring wraparound
 	 * at offset 0 sometimes hangs. No idea why.
 	 */
 	if (USES_GUC(dev_priv))
-		ctx->ggtt_offset_bias = GUC_WOPCM_TOP;
+		ctx->ggtt_offset_bias = dev_priv->guc.ggtt_pin_bias;
 	else
 		ctx->ggtt_offset_bias = I915_GTT_PAGE_SIZE;
 
@@ -429,7 +431,7 @@ i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio)
 		return ctx;
 
 	i915_gem_context_clear_bannable(ctx);
-	ctx->priority = prio;
+	ctx->sched.priority = prio;
 	ctx->ring_size = PAGE_SIZE;
 
 	GEM_BUG_ON(!i915_gem_context_is_kernel(ctx));
@@ -458,11 +460,16 @@ static bool needs_preempt_context(struct drm_i915_private *i915)
 int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
 {
 	struct i915_gem_context *ctx;
+	int ret;
 
 	/* Reassure ourselves we are only called once */
 	GEM_BUG_ON(dev_priv->kernel_context);
 	GEM_BUG_ON(dev_priv->preempt_context);
 
+	ret = intel_ctx_workarounds_init(dev_priv);
+	if (ret)
+		return ret;
+
 	INIT_LIST_HEAD(&dev_priv->contexts.list);
 	INIT_WORK(&dev_priv->contexts.free_work, contexts_free_worker);
 	init_llist_head(&dev_priv->contexts.free_list);
@@ -514,7 +521,7 @@ void i915_gem_contexts_lost(struct drm_i915_private *dev_priv)
 		if (!engine->last_retired_context)
 			continue;
 
-		engine->context_unpin(engine, engine->last_retired_context);
+		intel_context_unpin(engine->last_retired_context, engine);
 		engine->last_retired_context = NULL;
 	}
 }
@@ -570,19 +577,29 @@ void i915_gem_context_close(struct drm_file *file)
 	idr_destroy(&file_priv->context_idr);
 }
 
-static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine)
+static struct i915_request *
+last_request_on_engine(struct i915_timeline *timeline,
+		       struct intel_engine_cs *engine)
 {
-	struct i915_gem_timeline *timeline;
+	struct i915_request *rq;
 
-	list_for_each_entry(timeline, &engine->i915->gt.timelines, link) {
-		struct intel_timeline *tl;
+	if (timeline == &engine->timeline)
+		return NULL;
 
-		if (timeline == &engine->i915->gt.global_timeline)
-			continue;
+	rq = i915_gem_active_raw(&timeline->last_request,
+				 &engine->i915->drm.struct_mutex);
+	if (rq && rq->engine == engine)
+		return rq;
+
+	return NULL;
+}
 
-		tl = &timeline->engine[engine->id];
-		if (i915_gem_active_peek(&tl->last_request,
-					 &engine->i915->drm.struct_mutex))
+static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine)
+{
+	struct i915_timeline *timeline;
+
+	list_for_each_entry(timeline, &engine->i915->gt.timelines, link) {
+		if (last_request_on_engine(timeline, engine))
 			return false;
 	}
 
@@ -592,7 +609,7 @@ static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine)
 int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
-	struct i915_gem_timeline *timeline;
+	struct i915_timeline *timeline;
 	enum intel_engine_id id;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
@@ -612,11 +629,8 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
 		/* Queue this switch after all other activity */
 		list_for_each_entry(timeline, &dev_priv->gt.timelines, link) {
 			struct i915_request *prev;
-			struct intel_timeline *tl;
 
-			tl = &timeline->engine[engine->id];
-			prev = i915_gem_active_raw(&tl->last_request,
-						   &dev_priv->drm.struct_mutex);
+			prev = last_request_on_engine(timeline, engine);
 			if (prev)
 				i915_sw_fence_await_sw_fence_gfp(&rq->submit,
 								 &prev->submit,
@@ -746,7 +760,7 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		args->value = i915_gem_context_is_bannable(ctx);
 		break;
 	case I915_CONTEXT_PARAM_PRIORITY:
-		args->value = ctx->priority;
+		args->value = ctx->sched.priority;
 		break;
 	default:
 		ret = -EINVAL;
@@ -819,7 +833,7 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 				 !capable(CAP_SYS_NICE))
 				ret = -EPERM;
 			else
-				ctx->priority = priority;
+				ctx->sched.priority = priority;
 		}
 		break;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 7854262ddfd9..ace3b129c189 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -137,18 +137,7 @@ struct i915_gem_context {
 	 */
 	u32 user_handle;
 
-	/**
-	 * @priority: execution and service priority
-	 *
-	 * All clients are equal, but some are more equal than others!
-	 *
-	 * Requests from a context with a greater (more positive) value of
-	 * @priority will be executed before those with a lower @priority
-	 * value, forming a simple QoS.
-	 *
-	 * The &drm_i915_private.kernel_context is assigned the lowest priority.
-	 */
-	int priority;
+	struct i915_sched_attr sched;
 
 	/** ggtt_offset_bias: placement restriction for context objects */
 	u32 ggtt_offset_bias;
@@ -160,7 +149,7 @@ struct i915_gem_context {
 		u32 *lrc_reg_state;
 		u64 lrc_desc;
 		int pin_count;
-	} engine[I915_NUM_ENGINES];
+	} __engine[I915_NUM_ENGINES];
 
 	/** ring_size: size for allocating the per-engine ring buffer */
 	u32 ring_size;
@@ -267,6 +256,34 @@ static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
 	return !ctx->file_priv;
 }
 
+static inline struct intel_context *
+to_intel_context(struct i915_gem_context *ctx,
+		 const struct intel_engine_cs *engine)
+{
+	return &ctx->__engine[engine->id];
+}
+
+static inline struct intel_ring *
+intel_context_pin(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
+{
+	return engine->context_pin(engine, ctx);
+}
+
+static inline void __intel_context_pin(struct i915_gem_context *ctx,
+				       const struct intel_engine_cs *engine)
+{
+	struct intel_context *ce = to_intel_context(ctx, engine);
+
+	GEM_BUG_ON(!ce->pin_count);
+	ce->pin_count++;
+}
+
+static inline void intel_context_unpin(struct i915_gem_context *ctx,
+				       struct intel_engine_cs *engine)
+{
+	engine->context_unpin(engine, ctx);
+}
+
 /* i915_gem_context.c */
 int __must_check i915_gem_contexts_init(struct drm_i915_private *dev_priv);
 void i915_gem_contexts_lost(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 8c170db8495d..f627a8c47c58 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -81,6 +81,35 @@ enum {
  * but this remains just a hint as the kernel may choose a new location for
  * any object in the future.
  *
+ * At the level of talking to the hardware, submitting a batchbuffer for the
+ * GPU to execute is to add content to a buffer from which the HW
+ * command streamer is reading.
+ *
+ * 1. Add a command to load the HW context. For Logical Ring Contexts, i.e.
+ *    Execlists, this command is not placed on the same buffer as the
+ *    remaining items.
+ *
+ * 2. Add a command to invalidate caches to the buffer.
+ *
+ * 3. Add a batchbuffer start command to the buffer; the start command is
+ *    essentially a token together with the GPU address of the batchbuffer
+ *    to be executed.
+ *
+ * 4. Add a pipeline flush to the buffer.
+ *
+ * 5. Add a memory write command to the buffer to record when the GPU
+ *    is done executing the batchbuffer. The memory write writes the
+ *    global sequence number of the request, ``i915_request::global_seqno``;
+ *    the i915 driver uses the current value in the register to determine
+ *    if the GPU has completed the batchbuffer.
+ *
+ * 6. Add a user interrupt command to the buffer. This command instructs
+ *    the GPU to issue an interrupt when the command, pipeline flush and
+ *    memory write are completed.
+ *
+ * 7. Inform the hardware of the additional commands added to the buffer
+ *    (by updating the tail pointer).
+ *
  * Processing an execbuf ioctl is conceptually split up into a few phases.
  *
  * 1. Validation - Ensure all the pointers, handles and flags are valid.
@@ -728,12 +757,13 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 
 		err = radix_tree_insert(handles_vma, handle, vma);
 		if (unlikely(err)) {
-			kfree(lut);
+			kmem_cache_free(eb->i915->luts, lut);
 			goto err_obj;
 		}
 
 		/* transfer ref to ctx */
-		vma->open_count++;
+		if (!vma->open_count++)
+			i915_vma_reopen(vma);
 		list_add(&lut->obj_link, &obj->lut_list);
 		list_add(&lut->ctx_link, &eb->ctx->handles_list);
 		lut->ctx = eb->ctx;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 21d72f695adb..996ab2ad6c45 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -110,7 +110,8 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma);
 
 static void gen6_ggtt_invalidate(struct drm_i915_private *dev_priv)
 {
-	/* Note that as an uncached mmio write, this should flush the
+	/*
+	 * Note that as an uncached mmio write, this will flush the
 	 * WCB of the writes into the GGTT before it triggers the invalidate.
 	 */
 	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
@@ -1161,6 +1162,27 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
 			vaddr[idx.pde] |= GEN8_PDE_IPS_64K;
 			kunmap_atomic(vaddr);
 			page_size = I915_GTT_PAGE_SIZE_64K;
+
+			/*
+			 * We write all 4K page entries, even when using 64K
+			 * pages. In order to verify that the HW isn't cheating
+			 * by using the 4K PTE instead of the 64K PTE, we want
+			 * to remove all the surplus entries. If the HW skipped
+			 * the 64K PTE, it will read/write into the scratch page
+			 * instead - which we detect as missing results during
+			 * selftests.
+			 */
+			if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) {
+				u16 i;
+
+				encode = pte_encode | vma->vm->scratch_page.daddr;
+				vaddr = kmap_atomic_px(pd->page_table[idx.pde]);
+
+				for (i = 1; i < index; i += 16)
+					memset64(vaddr + i, encode, 15);
+
+				kunmap_atomic(vaddr);
+			}
 		}
 
 		vma->page_sizes.gtt |= page_size;
@@ -2111,8 +2133,6 @@ static void i915_address_space_init(struct i915_address_space *vm,
 				    struct drm_i915_private *dev_priv,
 				    const char *name)
 {
-	i915_gem_timeline_init(dev_priv, &vm->timeline, name);
-
 	drm_mm_init(&vm->mm, 0, vm->total);
 	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
 
@@ -2129,7 +2149,6 @@ static void i915_address_space_fini(struct i915_address_space *vm)
 	if (pagevec_count(&vm->free_pages))
 		vm_free_pages_release(vm, true);
 
-	i915_gem_timeline_fini(&vm->timeline);
 	drm_mm_takedown(&vm->mm);
 	list_del(&vm->global_link);
 }
@@ -2140,15 +2159,15 @@ static void gtt_write_workarounds(struct drm_i915_private *dev_priv)
 	 * called on driver load and after a GPU reset, so you can place
 	 * workarounds here even if they get overwritten by GPU reset.
 	 */
-	/* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt,kbl,glk,cfl,cnl */
+	/* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt,kbl,glk,cfl,cnl,icl */
 	if (IS_BROADWELL(dev_priv))
 		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW);
 	else if (IS_CHERRYVIEW(dev_priv))
 		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV);
-	else if (IS_GEN9_BC(dev_priv) || IS_GEN10(dev_priv))
-		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
 	else if (IS_GEN9_LP(dev_priv))
 		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
+	else if (INTEL_GEN(dev_priv) >= 9)
+		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
 
 	/*
 	 * To support 64K PTEs we need to first enable the use of the
@@ -2222,6 +2241,12 @@ i915_ppgtt_create(struct drm_i915_private *dev_priv,
 
 void i915_ppgtt_close(struct i915_address_space *vm)
 {
+	GEM_BUG_ON(vm->closed);
+	vm->closed = true;
+}
+
+static void ppgtt_destroy_vma(struct i915_address_space *vm)
+{
 	struct list_head *phases[] = {
 		&vm->active_list,
 		&vm->inactive_list,
@@ -2229,15 +2254,12 @@ void i915_ppgtt_close(struct i915_address_space *vm)
 		NULL,
 	}, **phase;
 
-	GEM_BUG_ON(vm->closed);
 	vm->closed = true;
-
 	for (phase = phases; *phase; phase++) {
 		struct i915_vma *vma, *vn;
 
 		list_for_each_entry_safe(vma, vn, *phase, vm_link)
-			if (!i915_vma_is_closed(vma))
-				i915_vma_close(vma);
+			i915_vma_destroy(vma);
 	}
 }
 
@@ -2248,7 +2270,8 @@ void i915_ppgtt_release(struct kref *kref)
 
 	trace_i915_ppgtt_release(&ppgtt->base);
 
-	/* vmas should already be unbound and destroyed */
+	ppgtt_destroy_vma(&ppgtt->base);
+
 	GEM_BUG_ON(!list_empty(&ppgtt->base.active_list));
 	GEM_BUG_ON(!list_empty(&ppgtt->base.inactive_list));
 	GEM_BUG_ON(!list_empty(&ppgtt->base.unbound_list));
@@ -2417,11 +2440,9 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	for_each_sgt_dma(addr, sgt_iter, vma->pages)
 		gen8_set_pte(gtt_entries++, pte_encode | addr);
 
-	wmb();
-
-	/* This next bit makes the above posting read even more important. We
-	 * want to flush the TLBs only after we're certain all the PTE updates
-	 * have finished.
+	/*
+	 * We want to flush the TLBs only after we're certain all the PTE
+	 * updates have finished.
 	 */
 	ggtt->invalidate(vm->i915);
 }
@@ -2459,11 +2480,10 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	dma_addr_t addr;
 	for_each_sgt_dma(addr, iter, vma->pages)
 		iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]);
-	wmb();
 
-	/* This next bit makes the above posting read even more important. We
-	 * want to flush the TLBs only after we're certain all the PTE updates
-	 * have finished.
+	/*
+	 * We want to flush the TLBs only after we're certain all the PTE
+	 * updates have finished.
 	 */
 	ggtt->invalidate(vm->i915);
 }
@@ -3325,14 +3345,10 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
 
 	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-
-	if (INTEL_GEN(dev_priv) >= 9) {
-		size = gen8_get_total_gtt_size(snb_gmch_ctl);
-	} else if (IS_CHERRYVIEW(dev_priv)) {
+	if (IS_CHERRYVIEW(dev_priv))
 		size = chv_get_total_gtt_size(snb_gmch_ctl);
-	} else {
+	else
 		size = gen8_get_total_gtt_size(snb_gmch_ctl);
-	}
 
 	ggtt->base.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
 	ggtt->base.cleanup = gen6_gmch_remove;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 6efc017e8bb3..aec4f73574f4 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -38,10 +38,9 @@
 #include <linux/mm.h>
 #include <linux/pagevec.h>
 
-#include "i915_gem_timeline.h"
-
 #include "i915_request.h"
 #include "i915_selftest.h"
+#include "i915_timeline.h"
 
 #define I915_GTT_PAGE_SIZE_4K BIT(12)
 #define I915_GTT_PAGE_SIZE_64K BIT(16)
@@ -257,7 +256,6 @@ struct i915_pml4 {
 
 struct i915_address_space {
 	struct drm_mm mm;
-	struct i915_gem_timeline timeline;
 	struct drm_i915_private *i915;
 	struct device *dma;
 	/* Every address space belongs to a struct file - except for the global
@@ -344,6 +342,7 @@ struct i915_address_space {
 	void (*clear_pages)(struct i915_vma *vma);
 
 	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
+	I915_SELFTEST_DECLARE(bool scrub_64K);
 };
 
 #define i915_is_ggtt(V) (!(V)->file)
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 62aa67960bf4..ad949cc30928 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -51,6 +51,10 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return -ENODEV;
 
+	/* WaSkipStolenMemoryFirstPage:bdw+ */
+	if (INTEL_GEN(dev_priv) >= 8 && start < 4096)
+		start = 4096;
+
 	mutex_lock(&dev_priv->mm.stolen_lock);
 	ret = drm_mm_insert_node_in_range(&dev_priv->mm.stolen, node,
 					  size, alignment, 0,
@@ -121,8 +125,8 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 
 		if (stolen[0].start != stolen[1].start ||
 		    stolen[0].end != stolen[1].end) {
-			DRM_DEBUG_KMS("GTT within stolen memory at %pR\n", &ggtt_res);
-			DRM_DEBUG_KMS("Stolen memory adjusted to %pR\n", dsm);
+			DRM_DEBUG_DRIVER("GTT within stolen memory at %pR\n", &ggtt_res);
+			DRM_DEBUG_DRIVER("Stolen memory adjusted to %pR\n", dsm);
 		}
 	}
 
@@ -174,18 +178,19 @@ void i915_gem_cleanup_stolen(struct drm_device *dev)
 }
 
 static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
-				    resource_size_t *base, resource_size_t *size)
+				    resource_size_t *base,
+				    resource_size_t *size)
 {
-	uint32_t reg_val = I915_READ(IS_GM45(dev_priv) ?
-				     CTG_STOLEN_RESERVED :
-				     ELK_STOLEN_RESERVED);
+	u32 reg_val = I915_READ(IS_GM45(dev_priv) ?
+				CTG_STOLEN_RESERVED :
+				ELK_STOLEN_RESERVED);
 	resource_size_t stolen_top = dev_priv->dsm.end + 1;
 
-	if ((reg_val & G4X_STOLEN_RESERVED_ENABLE) == 0) {
-		*base = 0;
-		*size = 0;
+	DRM_DEBUG_DRIVER("%s_STOLEN_RESERVED = %08x\n",
+			 IS_GM45(dev_priv) ? "CTG" : "ELK", reg_val);
+
+	if ((reg_val & G4X_STOLEN_RESERVED_ENABLE) == 0)
 		return;
-	}
 
 	/*
 	 * Whether ILK really reuses the ELK register for this is unclear.
@@ -193,30 +198,25 @@ static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	 */
 	WARN(IS_GEN5(dev_priv), "ILK stolen reserved found? 0x%08x\n", reg_val);
 
-	*base = (reg_val & G4X_STOLEN_RESERVED_ADDR2_MASK) << 16;
+	if (!(reg_val & G4X_STOLEN_RESERVED_ADDR2_MASK))
+		return;
 
+	*base = (reg_val & G4X_STOLEN_RESERVED_ADDR2_MASK) << 16;
 	WARN_ON((reg_val & G4X_STOLEN_RESERVED_ADDR1_MASK) < *base);
 
-	/* On these platforms, the register doesn't have a size field, so the
-	 * size is the distance between the base and the top of the stolen
-	 * memory. We also have the genuine case where base is zero and there's
-	 * nothing reserved. */
-	if (*base == 0)
-		*size = 0;
-	else
-		*size = stolen_top - *base;
+	*size = stolen_top - *base;
 }
 
 static void gen6_get_stolen_reserved(struct drm_i915_private *dev_priv,
-				     resource_size_t *base, resource_size_t *size)
+				     resource_size_t *base,
+				     resource_size_t *size)
 {
-	uint32_t reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+
+	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
-	if ((reg_val & GEN6_STOLEN_RESERVED_ENABLE) == 0) {
-		*base = 0;
-		*size = 0;
+	if (!(reg_val & GEN6_STOLEN_RESERVED_ENABLE))
 		return;
-	}
 
 	*base = reg_val & GEN6_STOLEN_RESERVED_ADDR_MASK;
 
@@ -239,17 +239,44 @@ static void gen6_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void gen7_get_stolen_reserved(struct drm_i915_private *dev_priv,
-				     resource_size_t *base, resource_size_t *size)
+static void vlv_get_stolen_reserved(struct drm_i915_private *dev_priv,
+				    resource_size_t *base,
+				    resource_size_t *size)
 {
-	uint32_t reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	resource_size_t stolen_top = dev_priv->dsm.end + 1;
+
+	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
-	if ((reg_val & GEN6_STOLEN_RESERVED_ENABLE) == 0) {
-		*base = 0;
-		*size = 0;
+	if (!(reg_val & GEN6_STOLEN_RESERVED_ENABLE))
 		return;
+
+	switch (reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK) {
+	default:
+		MISSING_CASE(reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK);
+	case GEN7_STOLEN_RESERVED_1M:
+		*size = 1024 * 1024;
+		break;
 	}
 
+	/*
+	 * On vlv, the ADDR_MASK portion is left as 0 and HW deduces the
+	 * reserved location as (top - size).
+	 */
+	*base = stolen_top - *size;
+}
+
+static void gen7_get_stolen_reserved(struct drm_i915_private *dev_priv,
+				     resource_size_t *base,
+				     resource_size_t *size)
+{
+	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+
+	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
+
+	if (!(reg_val & GEN6_STOLEN_RESERVED_ENABLE))
+		return;
+
 	*base = reg_val & GEN7_STOLEN_RESERVED_ADDR_MASK;
 
 	switch (reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK) {
@@ -266,15 +293,15 @@ static void gen7_get_stolen_reserved(struct drm_i915_private *dev_priv,
 }
 
 static void chv_get_stolen_reserved(struct drm_i915_private *dev_priv,
-				    resource_size_t *base, resource_size_t *size)
+				    resource_size_t *base,
+				    resource_size_t *size)
 {
-	uint32_t reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
 
-	if ((reg_val & GEN6_STOLEN_RESERVED_ENABLE) == 0) {
-		*base = 0;
-		*size = 0;
+	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
+
+	if (!(reg_val & GEN6_STOLEN_RESERVED_ENABLE))
 		return;
-	}
 
 	*base = reg_val & GEN6_STOLEN_RESERVED_ADDR_MASK;
 
@@ -298,36 +325,28 @@ static void chv_get_stolen_reserved(struct drm_i915_private *dev_priv,
 }
 
 static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
-				    resource_size_t *base, resource_size_t *size)
+				    resource_size_t *base,
+				    resource_size_t *size)
 {
-	uint32_t reg_val = I915_READ(GEN6_STOLEN_RESERVED);
-	resource_size_t stolen_top;
+	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	resource_size_t stolen_top = dev_priv->dsm.end + 1;
 
-	if ((reg_val & GEN6_STOLEN_RESERVED_ENABLE) == 0) {
-		*base = 0;
-		*size = 0;
+	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
+
+	if (!(reg_val & GEN6_STOLEN_RESERVED_ENABLE))
 		return;
-	}
 
-	stolen_top = dev_priv->dsm.end + 1;
+	if (!(reg_val & GEN6_STOLEN_RESERVED_ADDR_MASK))
+		return;
 
 	*base = reg_val & GEN6_STOLEN_RESERVED_ADDR_MASK;
-
-	/* On these platforms, the register doesn't have a size field, so the
-	 * size is the distance between the base and the top of the stolen
-	 * memory. We also have the genuine case where base is zero and there's
-	 * nothing reserved. */
-	if (*base == 0)
-		*size = 0;
-	else
-		*size = stolen_top - *base;
+	*size = stolen_top - *base;
 }
 
 int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 {
 	resource_size_t reserved_base, stolen_top;
 	resource_size_t reserved_total, reserved_size;
-	resource_size_t stolen_usable_start;
 
 	mutex_init(&dev_priv->mm.stolen_lock);
 
@@ -353,7 +372,7 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 	GEM_BUG_ON(dev_priv->dsm.end <= dev_priv->dsm.start);
 
 	stolen_top = dev_priv->dsm.end + 1;
-	reserved_base = 0;
+	reserved_base = stolen_top;
 	reserved_size = 0;
 
 	switch (INTEL_GEN(dev_priv)) {
@@ -373,8 +392,12 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 					 &reserved_base, &reserved_size);
 		break;
 	case 7:
-		gen7_get_stolen_reserved(dev_priv,
-					 &reserved_base, &reserved_size);
+		if (IS_VALLEYVIEW(dev_priv))
+			vlv_get_stolen_reserved(dev_priv,
+						&reserved_base, &reserved_size);
+		else
+			gen7_get_stolen_reserved(dev_priv,
+						 &reserved_base, &reserved_size);
 		break;
 	default:
 		if (IS_LP(dev_priv))
@@ -386,11 +409,16 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	/* It is possible for the reserved base to be zero, but the register
-	 * field for size doesn't have a zero option. */
-	if (reserved_base == 0) {
-		reserved_size = 0;
+	/*
+	 * Our expectation is that the reserved space is at the top of the
+	 * stolen region and *never* at the bottom. If we see !reserved_base,
+	 * it likely means we failed to read the registers correctly.
+	 */
+	if (!reserved_base) {
+		DRM_ERROR("inconsistent reservation %pa + %pa; ignoring\n",
+			  &reserved_base, &reserved_size);
 		reserved_base = stolen_top;
+		reserved_size = 0;
 	}
 
 	dev_priv->dsm_reserved =
@@ -406,21 +434,15 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 	 * memory, so just consider the start. */
 	reserved_total = stolen_top - reserved_base;
 
-	DRM_DEBUG_KMS("Memory reserved for graphics device: %lluK, usable: %lluK\n",
-		      (u64)resource_size(&dev_priv->dsm) >> 10,
-		      ((u64)resource_size(&dev_priv->dsm) - reserved_total) >> 10);
-
-	stolen_usable_start = 0;
-	/* WaSkipStolenMemoryFirstPage:bdw+ */
-	if (INTEL_GEN(dev_priv) >= 8)
-		stolen_usable_start = 4096;
+	DRM_DEBUG_DRIVER("Memory reserved for graphics device: %lluK, usable: %lluK\n",
+			 (u64)resource_size(&dev_priv->dsm) >> 10,
+			 ((u64)resource_size(&dev_priv->dsm) - reserved_total) >> 10);
 
 	dev_priv->stolen_usable_size =
-		resource_size(&dev_priv->dsm) - reserved_total - stolen_usable_start;
+		resource_size(&dev_priv->dsm) - reserved_total;
 
 	/* Basic memrange allocator for stolen space. */
-	drm_mm_init(&dev_priv->mm.stolen, stolen_usable_start,
-		    dev_priv->stolen_usable_size);
+	drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->stolen_usable_size);
 
 	return 0;
 }
@@ -580,8 +602,8 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	DRM_DEBUG_KMS("creating preallocated stolen object: stolen_offset=%pa, gtt_offset=%pa, size=%pa\n",
-			&stolen_offset, &gtt_offset, &size);
+	DRM_DEBUG_DRIVER("creating preallocated stolen object: stolen_offset=%pa, gtt_offset=%pa, size=%pa\n",
+			 &stolen_offset, &gtt_offset, &size);
 
 	/* KISS and expect everything to be page-aligned */
 	if (WARN_ON(size == 0) ||
@@ -599,14 +621,14 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	ret = drm_mm_reserve_node(&dev_priv->mm.stolen, stolen);
 	mutex_unlock(&dev_priv->mm.stolen_lock);
 	if (ret) {
-		DRM_DEBUG_KMS("failed to allocate stolen space\n");
+		DRM_DEBUG_DRIVER("failed to allocate stolen space\n");
 		kfree(stolen);
 		return NULL;
 	}
 
 	obj = _i915_gem_object_create_stolen(dev_priv, stolen);
 	if (obj == NULL) {
-		DRM_DEBUG_KMS("failed to allocate stolen object\n");
+		DRM_DEBUG_DRIVER("failed to allocate stolen object\n");
 		i915_gem_stolen_remove_node(dev_priv, stolen);
 		kfree(stolen);
 		return NULL;
@@ -635,7 +657,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 				   size, gtt_offset, obj->cache_level,
 				   0);
 	if (ret) {
-		DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
+		DRM_DEBUG_DRIVER("failed to allocate stolen GTT space\n");
 		goto err_pages;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.c b/drivers/gpu/drm/i915/i915_gem_timeline.c
deleted file mode 100644
index e9fd87604067..000000000000
--- a/drivers/gpu/drm/i915/i915_gem_timeline.c
+++ /dev/null
@@ -1,154 +0,0 @@
-/*
- * Copyright © 2016 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- */
-
-#include "i915_drv.h"
-#include "i915_syncmap.h"
-
-static void __intel_timeline_init(struct intel_timeline *tl,
-				  struct i915_gem_timeline *parent,
-				  u64 context,
-				  struct lock_class_key *lockclass,
-				  const char *lockname)
-{
-	tl->fence_context = context;
-	tl->common = parent;
-	spin_lock_init(&tl->lock);
-	lockdep_set_class_and_name(&tl->lock, lockclass, lockname);
-	init_request_active(&tl->last_request, NULL);
-	INIT_LIST_HEAD(&tl->requests);
-	i915_syncmap_init(&tl->sync);
-}
-
-static void __intel_timeline_fini(struct intel_timeline *tl)
-{
-	GEM_BUG_ON(!list_empty(&tl->requests));
-
-	i915_syncmap_free(&tl->sync);
-}
-
-static int __i915_gem_timeline_init(struct drm_i915_private *i915,
-				    struct i915_gem_timeline *timeline,
-				    const char *name,
-				    struct lock_class_key *lockclass,
-				    const char *lockname)
-{
-	unsigned int i;
-	u64 fences;
-
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
-	/*
-	 * Ideally we want a set of engines on a single leaf as we expect
-	 * to mostly be tracking synchronisation between engines. It is not
-	 * a huge issue if this is not the case, but we may want to mitigate
-	 * any page crossing penalties if they become an issue.
-	 */
-	BUILD_BUG_ON(KSYNCMAP < I915_NUM_ENGINES);
-
-	timeline->i915 = i915;
-	timeline->name = kstrdup(name ?: "[kernel]", GFP_KERNEL);
-	if (!timeline->name)
-		return -ENOMEM;
-
-	list_add(&timeline->link, &i915->gt.timelines);
-
-	/* Called during early_init before we know how many engines there are */
-	fences = dma_fence_context_alloc(ARRAY_SIZE(timeline->engine));
-	for (i = 0; i < ARRAY_SIZE(timeline->engine); i++)
-		__intel_timeline_init(&timeline->engine[i],
-				      timeline, fences++,
-				      lockclass, lockname);
-
-	return 0;
-}
-
-int i915_gem_timeline_init(struct drm_i915_private *i915,
-			   struct i915_gem_timeline *timeline,
-			   const char *name)
-{
-	static struct lock_class_key class;
-
-	return __i915_gem_timeline_init(i915, timeline, name,
-					&class, "&timeline->lock");
-}
-
-int i915_gem_timeline_init__global(struct drm_i915_private *i915)
-{
-	static struct lock_class_key class;
-
-	return __i915_gem_timeline_init(i915,
-					&i915->gt.global_timeline,
-					"[execution]",
-					&class, "&global_timeline->lock");
-}
-
-/**
- * i915_gem_timelines_park - called when the driver idles
- * @i915: the drm_i915_private device
- *
- * When the driver is completely idle, we know that all of our sync points
- * have been signaled and our tracking is then entirely redundant. Any request
- * to wait upon an older sync point will be completed instantly as we know
- * the fence is signaled and therefore we will not even look them up in the
- * sync point map.
- */
-void i915_gem_timelines_park(struct drm_i915_private *i915)
-{
-	struct i915_gem_timeline *timeline;
-	int i;
-
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
-	list_for_each_entry(timeline, &i915->gt.timelines, link) {
-		for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) {
-			struct intel_timeline *tl = &timeline->engine[i];
-
-			/*
-			 * All known fences are completed so we can scrap
-			 * the current sync point tracking and start afresh,
-			 * any attempt to wait upon a previous sync point
-			 * will be skipped as the fence was signaled.
-			 */
-			i915_syncmap_free(&tl->sync);
-		}
-	}
-}
-
-void i915_gem_timeline_fini(struct i915_gem_timeline *timeline)
-{
-	int i;
-
-	lockdep_assert_held(&timeline->i915->drm.struct_mutex);
-
-	for (i = 0; i < ARRAY_SIZE(timeline->engine); i++)
-		__intel_timeline_fini(&timeline->engine[i]);
-
-	list_del(&timeline->link);
-	kfree(timeline->name);
-}
-
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/mock_timeline.c"
-#include "selftests/i915_gem_timeline.c"
-#endif
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index d596a8302ca3..854bd51b9478 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -778,6 +778,9 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 			    I915_USERPTR_UNSYNCHRONIZED))
 		return -EINVAL;
 
+	if (!args->user_size)
+		return -EINVAL;
+
 	if (offset_in_page(args->user_ptr | args->user_size))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index f89ac7a8f95f..df234dc23274 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -32,6 +32,7 @@
 #include <linux/zlib.h>
 #include <drm/drm_print.h>
 
+#include "i915_gpu_error.h"
 #include "i915_drv.h"
 
 static inline const struct intel_engine_cs *
@@ -403,16 +404,17 @@ static const char *bannable(const struct drm_i915_error_context *ctx)
 
 static void error_print_request(struct drm_i915_error_state_buf *m,
 				const char *prefix,
-				const struct drm_i915_error_request *erq)
+				const struct drm_i915_error_request *erq,
+				const unsigned long epoch)
 {
 	if (!erq->seqno)
 		return;
 
-	err_printf(m, "%s pid %d, ban score %d, seqno %8x:%08x, prio %d, emitted %dms ago, head %08x, tail %08x\n",
+	err_printf(m, "%s pid %d, ban score %d, seqno %8x:%08x, prio %d, emitted %dms, start %08x, head %08x, tail %08x\n",
 		   prefix, erq->pid, erq->ban_score,
-		   erq->context, erq->seqno, erq->priority,
-		   jiffies_to_msecs(jiffies - erq->jiffies),
-		   erq->head, erq->tail);
+		   erq->context, erq->seqno, erq->sched_attr.priority,
+		   jiffies_to_msecs(erq->jiffies - epoch),
+		   erq->start, erq->head, erq->tail);
 }
 
 static void error_print_context(struct drm_i915_error_state_buf *m,
@@ -421,12 +423,13 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
 {
 	err_printf(m, "%s%s[%d] user_handle %d hw_id %d, prio %d, ban score %d%s guilty %d active %d\n",
 		   header, ctx->comm, ctx->pid, ctx->handle, ctx->hw_id,
-		   ctx->priority, ctx->ban_score, bannable(ctx),
+		   ctx->sched_attr.priority, ctx->ban_score, bannable(ctx),
 		   ctx->guilty, ctx->active);
 }
 
 static void error_print_engine(struct drm_i915_error_state_buf *m,
-			       const struct drm_i915_error_engine *ee)
+			       const struct drm_i915_error_engine *ee,
+			       const unsigned long epoch)
 {
 	int n;
 
@@ -496,14 +499,15 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 	err_printf(m, "  hangcheck stall: %s\n", yesno(ee->hangcheck_stalled));
 	err_printf(m, "  hangcheck action: %s\n",
 		   hangcheck_action_to_str(ee->hangcheck_action));
-	err_printf(m, "  hangcheck action timestamp: %lu, %u ms ago\n",
+	err_printf(m, "  hangcheck action timestamp: %dms (%lu%s)\n",
+		   jiffies_to_msecs(ee->hangcheck_timestamp - epoch),
 		   ee->hangcheck_timestamp,
-		   jiffies_to_msecs(jiffies - ee->hangcheck_timestamp));
+		   ee->hangcheck_timestamp == epoch ? "; epoch" : "");
 	err_printf(m, "  engine reset count: %u\n", ee->reset_count);
 
 	for (n = 0; n < ee->num_ports; n++) {
 		err_printf(m, "  ELSP[%d]:", n);
-		error_print_request(m, " ", &ee->execlist[n]);
+		error_print_request(m, " ", &ee->execlist[n], epoch);
 	}
 
 	error_print_context(m, "  Active context: ", &ee->context);
@@ -649,6 +653,11 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	ts = ktime_to_timespec64(error->uptime);
 	err_printf(m, "Uptime: %lld s %ld us\n",
 		   (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC);
+	err_printf(m, "Epoch: %lu jiffies (%u HZ)\n", error->epoch, HZ);
+	err_printf(m, "Capture: %lu jiffies; %d ms ago, %d ms after epoch\n",
+		   error->capture,
+		   jiffies_to_msecs(jiffies - error->capture),
+		   jiffies_to_msecs(error->capture - error->epoch));
 
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		if (error->engine[i].hangcheck_stalled &&
@@ -709,7 +718,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		if (error->engine[i].engine_id != -1)
-			error_print_engine(m, &error->engine[i]);
+			error_print_engine(m, &error->engine[i], error->epoch);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(error->active_vm); i++) {
@@ -768,7 +777,9 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 				   dev_priv->engine[i]->name,
 				   ee->num_requests);
 			for (j = 0; j < ee->num_requests; j++)
-				error_print_request(m, " ", &ee->requests[j]);
+				error_print_request(m, " ",
+						    &ee->requests[j],
+						    error->epoch);
 		}
 
 		if (IS_ERR(ee->waiters)) {
@@ -1277,10 +1288,11 @@ static void record_request(struct i915_request *request,
 			   struct drm_i915_error_request *erq)
 {
 	erq->context = request->ctx->hw_id;
-	erq->priority = request->priotree.priority;
+	erq->sched_attr = request->sched.attr;
 	erq->ban_score = atomic_read(&request->ctx->ban_score);
 	erq->seqno = request->global_seqno;
 	erq->jiffies = request->emitted_jiffies;
+	erq->start = i915_ggtt_offset(request->ring->vma);
 	erq->head = request->head;
 	erq->tail = request->tail;
 
@@ -1298,7 +1310,7 @@ static void engine_record_requests(struct intel_engine_cs *engine,
 
 	count = 0;
 	request = first;
-	list_for_each_entry_from(request, &engine->timeline->requests, link)
+	list_for_each_entry_from(request, &engine->timeline.requests, link)
 		count++;
 	if (!count)
 		return;
@@ -1311,7 +1323,7 @@ static void engine_record_requests(struct intel_engine_cs *engine,
 
 	count = 0;
 	request = first;
-	list_for_each_entry_from(request, &engine->timeline->requests, link) {
+	list_for_each_entry_from(request, &engine->timeline.requests, link) {
 		if (count >= ee->num_requests) {
 			/*
 			 * If the ring request list was changed in
@@ -1371,7 +1383,7 @@ static void record_context(struct drm_i915_error_context *e,
 
 	e->handle = ctx->user_handle;
 	e->hw_id = ctx->hw_id;
-	e->priority = ctx->priority;
+	e->sched_attr = ctx->sched;
 	e->ban_score = atomic_read(&ctx->ban_score);
 	e->bannable = i915_gem_context_is_bannable(ctx);
 	e->guilty = atomic_read(&ctx->guilty_count);
@@ -1471,7 +1483,8 @@ static void gem_record_rings(struct i915_gpu_state *error)
 
 			ee->ctx =
 				i915_error_object_create(i915,
-							 request->ctx->engine[i].state);
+							 to_intel_context(request->ctx,
+									  engine)->state);
 
 			error->simulated |=
 				i915_gem_context_no_error_capture(request->ctx);
@@ -1734,6 +1747,22 @@ static void capture_params(struct i915_gpu_state *error)
 #undef DUP
 }
 
+static unsigned long capture_find_epoch(const struct i915_gpu_state *error)
+{
+	unsigned long epoch = error->capture;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
+		const struct drm_i915_error_engine *ee = &error->engine[i];
+
+		if (ee->hangcheck_stalled &&
+		    time_before(ee->hangcheck_timestamp, epoch))
+			epoch = ee->hangcheck_timestamp;
+	}
+
+	return epoch;
+}
+
 static int capture(void *data)
 {
 	struct i915_gpu_state *error = data;
@@ -1742,6 +1771,7 @@ static int capture(void *data)
 	error->boottime = ktime_get_boottime();
 	error->uptime = ktime_sub(ktime_get(),
 				  error->i915->gt.last_init_time);
+	error->capture = jiffies;
 
 	capture_params(error);
 	capture_gen_state(error);
@@ -1755,6 +1785,8 @@ static int capture(void *data)
 	error->overlay = intel_overlay_capture_error_state(error->i915);
 	error->display = intel_display_capture_error_state(error->i915);
 
+	error->epoch = capture_find_epoch(error);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
new file mode 100644
index 000000000000..dac0f8c4c1cf
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -0,0 +1,366 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright � 2008-2018 Intel Corporation
+ */
+
+#ifndef _I915_GPU_ERROR_H_
+#define _I915_GPU_ERROR_H_
+
+#include <linux/kref.h>
+#include <linux/ktime.h>
+#include <linux/sched.h>
+
+#include <drm/drm_mm.h>
+
+#include "intel_device_info.h"
+#include "intel_ringbuffer.h"
+#include "intel_uc_fw.h"
+
+#include "i915_gem.h"
+#include "i915_gem_gtt.h"
+#include "i915_params.h"
+#include "i915_scheduler.h"
+
+struct drm_i915_private;
+struct intel_overlay_error_state;
+struct intel_display_error_state;
+
+struct i915_gpu_state {
+	struct kref ref;
+	ktime_t time;
+	ktime_t boottime;
+	ktime_t uptime;
+	unsigned long capture;
+	unsigned long epoch;
+
+	struct drm_i915_private *i915;
+
+	char error_msg[128];
+	bool simulated;
+	bool awake;
+	bool wakelock;
+	bool suspended;
+	int iommu;
+	u32 reset_count;
+	u32 suspend_count;
+	struct intel_device_info device_info;
+	struct intel_driver_caps driver_caps;
+	struct i915_params params;
+
+	struct i915_error_uc {
+		struct intel_uc_fw guc_fw;
+		struct intel_uc_fw huc_fw;
+		struct drm_i915_error_object *guc_log;
+	} uc;
+
+	/* Generic register state */
+	u32 eir;
+	u32 pgtbl_er;
+	u32 ier;
+	u32 gtier[4], ngtier;
+	u32 ccid;
+	u32 derrmr;
+	u32 forcewake;
+	u32 error; /* gen6+ */
+	u32 err_int; /* gen7 */
+	u32 fault_data0; /* gen8, gen9 */
+	u32 fault_data1; /* gen8, gen9 */
+	u32 done_reg;
+	u32 gac_eco;
+	u32 gam_ecochk;
+	u32 gab_ctl;
+	u32 gfx_mode;
+
+	u32 nfence;
+	u64 fence[I915_MAX_NUM_FENCES];
+	struct intel_overlay_error_state *overlay;
+	struct intel_display_error_state *display;
+
+	struct drm_i915_error_engine {
+		int engine_id;
+		/* Software tracked state */
+		bool idle;
+		bool waiting;
+		int num_waiters;
+		unsigned long hangcheck_timestamp;
+		bool hangcheck_stalled;
+		enum intel_engine_hangcheck_action hangcheck_action;
+		struct i915_address_space *vm;
+		int num_requests;
+		u32 reset_count;
+
+		/* position of active request inside the ring */
+		u32 rq_head, rq_post, rq_tail;
+
+		/* our own tracking of ring head and tail */
+		u32 cpu_ring_head;
+		u32 cpu_ring_tail;
+
+		u32 last_seqno;
+
+		/* Register state */
+		u32 start;
+		u32 tail;
+		u32 head;
+		u32 ctl;
+		u32 mode;
+		u32 hws;
+		u32 ipeir;
+		u32 ipehr;
+		u32 bbstate;
+		u32 instpm;
+		u32 instps;
+		u32 seqno;
+		u64 bbaddr;
+		u64 acthd;
+		u32 fault_reg;
+		u64 faddr;
+		u32 rc_psmi; /* sleep state */
+		u32 semaphore_mboxes[I915_NUM_ENGINES - 1];
+		struct intel_instdone instdone;
+
+		struct drm_i915_error_context {
+			char comm[TASK_COMM_LEN];
+			pid_t pid;
+			u32 handle;
+			u32 hw_id;
+			int ban_score;
+			int active;
+			int guilty;
+			bool bannable;
+			struct i915_sched_attr sched_attr;
+		} context;
+
+		struct drm_i915_error_object {
+			u64 gtt_offset;
+			u64 gtt_size;
+			int page_count;
+			int unused;
+			u32 *pages[0];
+		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
+
+		struct drm_i915_error_object **user_bo;
+		long user_bo_count;
+
+		struct drm_i915_error_object *wa_ctx;
+		struct drm_i915_error_object *default_state;
+
+		struct drm_i915_error_request {
+			long jiffies;
+			pid_t pid;
+			u32 context;
+			int ban_score;
+			u32 seqno;
+			u32 start;
+			u32 head;
+			u32 tail;
+			struct i915_sched_attr sched_attr;
+		} *requests, execlist[EXECLIST_MAX_PORTS];
+		unsigned int num_ports;
+
+		struct drm_i915_error_waiter {
+			char comm[TASK_COMM_LEN];
+			pid_t pid;
+			u32 seqno;
+		} *waiters;
+
+		struct {
+			u32 gfx_mode;
+			union {
+				u64 pdp[4];
+				u32 pp_dir_base;
+			};
+		} vm_info;
+	} engine[I915_NUM_ENGINES];
+
+	struct drm_i915_error_buffer {
+		u32 size;
+		u32 name;
+		u32 rseqno[I915_NUM_ENGINES], wseqno;
+		u64 gtt_offset;
+		u32 read_domains;
+		u32 write_domain;
+		s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
+		u32 tiling:2;
+		u32 dirty:1;
+		u32 purgeable:1;
+		u32 userptr:1;
+		s32 engine:4;
+		u32 cache_level:3;
+	} *active_bo[I915_NUM_ENGINES], *pinned_bo;
+	u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count;
+	struct i915_address_space *active_vm[I915_NUM_ENGINES];
+};
+
+struct i915_gpu_error {
+	/* For hangcheck timer */
+#define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
+#define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD)
+
+	struct delayed_work hangcheck_work;
+
+	/* For reset and error_state handling. */
+	spinlock_t lock;
+	/* Protected by the above dev->gpu_error.lock. */
+	struct i915_gpu_state *first_error;
+
+	atomic_t pending_fb_pin;
+
+	unsigned long missed_irq_rings;
+
+	/**
+	 * State variable controlling the reset flow and count
+	 *
+	 * This is a counter which gets incremented when reset is triggered,
+	 *
+	 * Before the reset commences, the I915_RESET_BACKOFF bit is set
+	 * meaning that any waiters holding onto the struct_mutex should
+	 * relinquish the lock immediately in order for the reset to start.
+	 *
+	 * If reset is not completed successfully, the I915_WEDGE bit is
+	 * set meaning that hardware is terminally sour and there is no
+	 * recovery. All waiters on the reset_queue will be woken when
+	 * that happens.
+	 *
+	 * This counter is used by the wait_seqno code to notice that reset
+	 * event happened and it needs to restart the entire ioctl (since most
+	 * likely the seqno it waited for won't ever signal anytime soon).
+	 *
+	 * This is important for lock-free wait paths, where no contended lock
+	 * naturally enforces the correct ordering between the bail-out of the
+	 * waiter and the gpu reset work code.
+	 */
+	unsigned long reset_count;
+
+	/**
+	 * flags: Control various stages of the GPU reset
+	 *
+	 * #I915_RESET_BACKOFF - When we start a reset, we want to stop any
+	 * other users acquiring the struct_mutex. To do this we set the
+	 * #I915_RESET_BACKOFF bit in the error flags when we detect a reset
+	 * and then check for that bit before acquiring the struct_mutex (in
+	 * i915_mutex_lock_interruptible()?). I915_RESET_BACKOFF serves a
+	 * secondary role in preventing two concurrent global reset attempts.
+	 *
+	 * #I915_RESET_HANDOFF - To perform the actual GPU reset, we need the
+	 * struct_mutex. We try to acquire the struct_mutex in the reset worker,
+	 * but it may be held by some long running waiter (that we cannot
+	 * interrupt without causing trouble). Once we are ready to do the GPU
+	 * reset, we set the I915_RESET_HANDOFF bit and wakeup any waiters. If
+	 * they already hold the struct_mutex and want to participate they can
+	 * inspect the bit and do the reset directly, otherwise the worker
+	 * waits for the struct_mutex.
+	 *
+	 * #I915_RESET_ENGINE[num_engines] - Since the driver doesn't need to
+	 * acquire the struct_mutex to reset an engine, we need an explicit
+	 * flag to prevent two concurrent reset attempts in the same engine.
+	 * As the number of engines continues to grow, allocate the flags from
+	 * the most significant bits.
+	 *
+	 * #I915_WEDGED - If reset fails and we can no longer use the GPU,
+	 * we set the #I915_WEDGED bit. Prior to command submission, e.g.
+	 * i915_request_alloc(), this bit is checked and the sequence
+	 * aborted (with -EIO reported to userspace) if set.
+	 */
+	unsigned long flags;
+#define I915_RESET_BACKOFF	0
+#define I915_RESET_HANDOFF	1
+#define I915_RESET_MODESET	2
+#define I915_WEDGED		(BITS_PER_LONG - 1)
+#define I915_RESET_ENGINE	(I915_WEDGED - I915_NUM_ENGINES)
+
+	/** Number of times an engine has been reset */
+	u32 reset_engine_count[I915_NUM_ENGINES];
+
+	/** Set of stalled engines with guilty requests, in the current reset */
+	u32 stalled_mask;
+
+	/** Reason for the current *global* reset */
+	const char *reason;
+
+	/**
+	 * Waitqueue to signal when a hang is detected. Used to for waiters
+	 * to release the struct_mutex for the reset to procede.
+	 */
+	wait_queue_head_t wait_queue;
+
+	/**
+	 * Waitqueue to signal when the reset has completed. Used by clients
+	 * that wait for dev_priv->mm.wedged to settle.
+	 */
+	wait_queue_head_t reset_queue;
+
+	/* For missed irq/seqno simulation. */
+	unsigned long test_irq_rings;
+};
+
+struct drm_i915_error_state_buf {
+	struct drm_i915_private *i915;
+	unsigned int bytes;
+	unsigned int size;
+	int err;
+	u8 *buf;
+	loff_t start;
+	loff_t pos;
+};
+
+#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
+
+__printf(2, 3)
+void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
+int i915_error_state_to_str(struct drm_i915_error_state_buf *estr,
+			    const struct i915_gpu_state *gpu);
+int i915_error_state_buf_init(struct drm_i915_error_state_buf *eb,
+			      struct drm_i915_private *i915,
+			      size_t count, loff_t pos);
+
+static inline void
+i915_error_state_buf_release(struct drm_i915_error_state_buf *eb)
+{
+	kfree(eb->buf);
+}
+
+struct i915_gpu_state *i915_capture_gpu_state(struct drm_i915_private *i915);
+void i915_capture_error_state(struct drm_i915_private *dev_priv,
+			      u32 engine_mask,
+			      const char *error_msg);
+
+static inline struct i915_gpu_state *
+i915_gpu_state_get(struct i915_gpu_state *gpu)
+{
+	kref_get(&gpu->ref);
+	return gpu;
+}
+
+void __i915_gpu_state_free(struct kref *kref);
+static inline void i915_gpu_state_put(struct i915_gpu_state *gpu)
+{
+	if (gpu)
+		kref_put(&gpu->ref, __i915_gpu_state_free);
+}
+
+struct i915_gpu_state *i915_first_error_state(struct drm_i915_private *i915);
+void i915_reset_error_state(struct drm_i915_private *i915);
+
+#else
+
+static inline void i915_capture_error_state(struct drm_i915_private *dev_priv,
+					    u32 engine_mask,
+					    const char *error_msg)
+{
+}
+
+static inline struct i915_gpu_state *
+i915_first_error_state(struct drm_i915_private *i915)
+{
+	return NULL;
+}
+
+static inline void i915_reset_error_state(struct drm_i915_private *i915)
+{
+}
+
+#endif /* IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) */
+
+#endif /* _I915_GPU_ERROR_H_ */
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 633c18785c1e..f9bc3aaa90d0 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -243,6 +243,41 @@ void i915_hotplug_interrupt_update(struct drm_i915_private *dev_priv,
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
 
+static u32
+gen11_gt_engine_identity(struct drm_i915_private * const i915,
+			 const unsigned int bank, const unsigned int bit);
+
+bool gen11_reset_one_iir(struct drm_i915_private * const i915,
+			 const unsigned int bank,
+			 const unsigned int bit)
+{
+	void __iomem * const regs = i915->regs;
+	u32 dw;
+
+	lockdep_assert_held(&i915->irq_lock);
+
+	dw = raw_reg_read(regs, GEN11_GT_INTR_DW(bank));
+	if (dw & BIT(bit)) {
+		/*
+		 * According to the BSpec, DW_IIR bits cannot be cleared without
+		 * first servicing the Selector & Shared IIR registers.
+		 */
+		gen11_gt_engine_identity(i915, bank, bit);
+
+		/*
+		 * We locked GT INT DW by reading it. If we want to (try
+		 * to) recover from this succesfully, we need to clear
+		 * our bit, otherwise we are locking the register for
+		 * everybody.
+		 */
+		raw_reg_write(regs, GEN11_GT_INTR_DW(bank), BIT(bit));
+
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * ilk_update_display_irq - update DEIMR
  * @dev_priv: driver private
@@ -308,17 +343,29 @@ void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
 
 static i915_reg_t gen6_pm_iir(struct drm_i915_private *dev_priv)
 {
+	WARN_ON_ONCE(INTEL_GEN(dev_priv) >= 11);
+
 	return INTEL_GEN(dev_priv) >= 8 ? GEN8_GT_IIR(2) : GEN6_PMIIR;
 }
 
 static i915_reg_t gen6_pm_imr(struct drm_i915_private *dev_priv)
 {
-	return INTEL_GEN(dev_priv) >= 8 ? GEN8_GT_IMR(2) : GEN6_PMIMR;
+	if (INTEL_GEN(dev_priv) >= 11)
+		return GEN11_GPM_WGBOXPERF_INTR_MASK;
+	else if (INTEL_GEN(dev_priv) >= 8)
+		return GEN8_GT_IMR(2);
+	else
+		return GEN6_PMIMR;
 }
 
 static i915_reg_t gen6_pm_ier(struct drm_i915_private *dev_priv)
 {
-	return INTEL_GEN(dev_priv) >= 8 ? GEN8_GT_IER(2) : GEN6_PMIER;
+	if (INTEL_GEN(dev_priv) >= 11)
+		return GEN11_GPM_WGBOXPERF_INTR_ENABLE;
+	else if (INTEL_GEN(dev_priv) >= 8)
+		return GEN8_GT_IER(2);
+	else
+		return GEN6_PMIER;
 }
 
 /**
@@ -400,6 +447,18 @@ static void gen6_disable_pm_irq(struct drm_i915_private *dev_priv, u32 disable_m
 	/* though a barrier is missing here, but don't really need a one */
 }
 
+void gen11_reset_rps_interrupts(struct drm_i915_private *dev_priv)
+{
+	spin_lock_irq(&dev_priv->irq_lock);
+
+	while (gen11_reset_one_iir(dev_priv, 0, GEN11_GTPM))
+		;
+
+	dev_priv->gt_pm.rps.pm_iir = 0;
+
+	spin_unlock_irq(&dev_priv->irq_lock);
+}
+
 void gen6_reset_rps_interrupts(struct drm_i915_private *dev_priv)
 {
 	spin_lock_irq(&dev_priv->irq_lock);
@@ -415,12 +474,14 @@ void gen6_enable_rps_interrupts(struct drm_i915_private *dev_priv)
 	if (READ_ONCE(rps->interrupts_enabled))
 		return;
 
-	if (WARN_ON_ONCE(IS_GEN11(dev_priv)))
-		return;
-
 	spin_lock_irq(&dev_priv->irq_lock);
 	WARN_ON_ONCE(rps->pm_iir);
-	WARN_ON_ONCE(I915_READ(gen6_pm_iir(dev_priv)) & dev_priv->pm_rps_events);
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		WARN_ON_ONCE(gen11_reset_one_iir(dev_priv, 0, GEN11_GTPM));
+	else
+		WARN_ON_ONCE(I915_READ(gen6_pm_iir(dev_priv)) & dev_priv->pm_rps_events);
+
 	rps->interrupts_enabled = true;
 	gen6_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
 
@@ -434,9 +495,6 @@ void gen6_disable_rps_interrupts(struct drm_i915_private *dev_priv)
 	if (!READ_ONCE(rps->interrupts_enabled))
 		return;
 
-	if (WARN_ON_ONCE(IS_GEN11(dev_priv)))
-		return;
-
 	spin_lock_irq(&dev_priv->irq_lock);
 	rps->interrupts_enabled = false;
 
@@ -453,7 +511,10 @@ void gen6_disable_rps_interrupts(struct drm_i915_private *dev_priv)
 	 * state of the worker can be discarded.
 	 */
 	cancel_work_sync(&rps->work);
-	gen6_reset_rps_interrupts(dev_priv);
+	if (INTEL_GEN(dev_priv) >= 11)
+		gen11_reset_rps_interrupts(dev_priv);
+	else
+		gen6_reset_rps_interrupts(dev_priv);
 }
 
 void gen9_reset_guc_interrupts(struct drm_i915_private *dev_priv)
@@ -1399,19 +1460,18 @@ static void snb_gt_irq_handler(struct drm_i915_private *dev_priv,
 }
 
 static void
-gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift)
+gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	bool tasklet = false;
 
-	if (iir & (GT_CONTEXT_SWITCH_INTERRUPT << test_shift)) {
-		if (READ_ONCE(engine->execlists.active)) {
-			__set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-			tasklet = true;
-		}
+	if (iir & GT_CONTEXT_SWITCH_INTERRUPT) {
+		if (READ_ONCE(engine->execlists.active))
+			tasklet = !test_and_set_bit(ENGINE_IRQ_EXECLIST,
+						    &engine->irq_posted);
 	}
 
-	if (iir & (GT_RENDER_USER_INTERRUPT << test_shift)) {
+	if (iir & GT_RENDER_USER_INTERRUPT) {
 		notify_ring(engine);
 		tasklet |= USES_GUC_SUBMISSION(engine->i915);
 	}
@@ -1466,21 +1526,21 @@ static void gen8_gt_irq_handler(struct drm_i915_private *i915,
 {
 	if (master_ctl & (GEN8_GT_RCS_IRQ | GEN8_GT_BCS_IRQ)) {
 		gen8_cs_irq_handler(i915->engine[RCS],
-				    gt_iir[0], GEN8_RCS_IRQ_SHIFT);
+				    gt_iir[0] >> GEN8_RCS_IRQ_SHIFT);
 		gen8_cs_irq_handler(i915->engine[BCS],
-				    gt_iir[0], GEN8_BCS_IRQ_SHIFT);
+				    gt_iir[0] >> GEN8_BCS_IRQ_SHIFT);
 	}
 
 	if (master_ctl & (GEN8_GT_VCS1_IRQ | GEN8_GT_VCS2_IRQ)) {
 		gen8_cs_irq_handler(i915->engine[VCS],
-				    gt_iir[1], GEN8_VCS1_IRQ_SHIFT);
+				    gt_iir[1] >> GEN8_VCS1_IRQ_SHIFT);
 		gen8_cs_irq_handler(i915->engine[VCS2],
-				    gt_iir[1], GEN8_VCS2_IRQ_SHIFT);
+				    gt_iir[1] >> GEN8_VCS2_IRQ_SHIFT);
 	}
 
 	if (master_ctl & GEN8_GT_VECS_IRQ) {
 		gen8_cs_irq_handler(i915->engine[VECS],
-				    gt_iir[3], GEN8_VECS_IRQ_SHIFT);
+				    gt_iir[3] >> GEN8_VECS_IRQ_SHIFT);
 	}
 
 	if (master_ctl & (GEN8_GT_PM_IRQ | GEN8_GT_GUC_IRQ)) {
@@ -1627,7 +1687,7 @@ static void display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
 	int head, tail;
 
 	spin_lock(&pipe_crc->lock);
-	if (pipe_crc->source) {
+	if (pipe_crc->source && !crtc->base.crc.opened) {
 		if (!pipe_crc->entries) {
 			spin_unlock(&pipe_crc->lock);
 			DRM_DEBUG_KMS("spurious interrupt\n");
@@ -1667,7 +1727,7 @@ static void display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
 		 * On GEN8+ sometimes the second CRC is bonkers as well, so
 		 * don't trust that one either.
 		 */
-		if (pipe_crc->skipped == 0 ||
+		if (pipe_crc->skipped <= 0 ||
 		    (INTEL_GEN(dev_priv) >= 8 && pipe_crc->skipped == 1)) {
 			pipe_crc->skipped++;
 			spin_unlock(&pipe_crc->lock);
@@ -1766,37 +1826,8 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 
 static void gen9_guc_irq_handler(struct drm_i915_private *dev_priv, u32 gt_iir)
 {
-	if (gt_iir & GEN9_GUC_TO_HOST_INT_EVENT) {
-		/* Sample the log buffer flush related bits & clear them out now
-		 * itself from the message identity register to minimize the
-		 * probability of losing a flush interrupt, when there are back
-		 * to back flush interrupts.
-		 * There can be a new flush interrupt, for different log buffer
-		 * type (like for ISR), whilst Host is handling one (for DPC).
-		 * Since same bit is used in message register for ISR & DPC, it
-		 * could happen that GuC sets the bit for 2nd interrupt but Host
-		 * clears out the bit on handling the 1st interrupt.
-		 */
-		u32 msg, flush;
-
-		msg = I915_READ(SOFT_SCRATCH(15));
-		flush = msg & (INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED |
-			       INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER);
-		if (flush) {
-			/* Clear the message bits that are handled */
-			I915_WRITE(SOFT_SCRATCH(15), msg & ~flush);
-
-			/* Handle flush interrupt in bottom half */
-			queue_work(dev_priv->guc.log.runtime.flush_wq,
-				   &dev_priv->guc.log.runtime.flush_work);
-
-			dev_priv->guc.log.flush_interrupt_count++;
-		} else {
-			/* Not clearing of unhandled event bits won't result in
-			 * re-triggering of the interrupt.
-			 */
-		}
-	}
+	if (gt_iir & GEN9_GUC_TO_HOST_INT_EVENT)
+		intel_guc_to_host_event_handler(&dev_priv->guc);
 }
 
 static void i9xx_pipestat_irq_reset(struct drm_i915_private *dev_priv)
@@ -2433,6 +2464,13 @@ static void ivb_display_irq_handler(struct drm_i915_private *dev_priv,
 	if (de_iir & DE_ERR_INT_IVB)
 		ivb_err_int_handler(dev_priv);
 
+	if (de_iir & DE_EDP_PSR_INT_HSW) {
+		u32 psr_iir = I915_READ(EDP_PSR_IIR);
+
+		intel_psr_irq_handler(dev_priv, psr_iir);
+		I915_WRITE(EDP_PSR_IIR, psr_iir);
+	}
+
 	if (de_iir & DE_AUX_CHANNEL_A_IVB)
 		dp_aux_irq_handler(dev_priv);
 
@@ -2562,11 +2600,25 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 	if (master_ctl & GEN8_DE_MISC_IRQ) {
 		iir = I915_READ(GEN8_DE_MISC_IIR);
 		if (iir) {
+			bool found = false;
+
 			I915_WRITE(GEN8_DE_MISC_IIR, iir);
 			ret = IRQ_HANDLED;
-			if (iir & GEN8_DE_MISC_GSE)
+
+			if (iir & GEN8_DE_MISC_GSE) {
 				intel_opregion_asle_intr(dev_priv);
-			else
+				found = true;
+			}
+
+			if (iir & GEN8_DE_EDP_PSR) {
+				u32 psr_iir = I915_READ(EDP_PSR_IIR);
+
+				intel_psr_irq_handler(dev_priv, psr_iir);
+				I915_WRITE(EDP_PSR_IIR, psr_iir);
+				found = true;
+			}
+
+			if (!found)
 				DRM_ERROR("Unexpected DE Misc interrupt\n");
 		}
 		else
@@ -2762,58 +2814,16 @@ static void __fini_wedge(struct wedge_me *w)
 	     (W)->i915;							\
 	     __fini_wedge((W)))
 
-static __always_inline void
-gen11_cs_irq_handler(struct intel_engine_cs * const engine, const u32 iir)
-{
-	gen8_cs_irq_handler(engine, iir, 0);
-}
-
-static void
-gen11_gt_engine_irq_handler(struct drm_i915_private * const i915,
-			    const unsigned int bank,
-			    const unsigned int engine_n,
-			    const u16 iir)
-{
-	struct intel_engine_cs ** const engine = i915->engine;
-
-	switch (bank) {
-	case 0:
-		switch (engine_n) {
-
-		case GEN11_RCS0:
-			return gen11_cs_irq_handler(engine[RCS], iir);
-
-		case GEN11_BCS:
-			return gen11_cs_irq_handler(engine[BCS], iir);
-		}
-	case 1:
-		switch (engine_n) {
-
-		case GEN11_VCS(0):
-			return gen11_cs_irq_handler(engine[_VCS(0)], iir);
-		case GEN11_VCS(1):
-			return gen11_cs_irq_handler(engine[_VCS(1)], iir);
-		case GEN11_VCS(2):
-			return gen11_cs_irq_handler(engine[_VCS(2)], iir);
-		case GEN11_VCS(3):
-			return gen11_cs_irq_handler(engine[_VCS(3)], iir);
-
-		case GEN11_VECS(0):
-			return gen11_cs_irq_handler(engine[_VECS(0)], iir);
-		case GEN11_VECS(1):
-			return gen11_cs_irq_handler(engine[_VECS(1)], iir);
-		}
-	}
-}
-
 static u32
-gen11_gt_engine_intr(struct drm_i915_private * const i915,
-		     const unsigned int bank, const unsigned int bit)
+gen11_gt_engine_identity(struct drm_i915_private * const i915,
+			 const unsigned int bank, const unsigned int bit)
 {
 	void __iomem * const regs = i915->regs;
 	u32 timeout_ts;
 	u32 ident;
 
+	lockdep_assert_held(&i915->irq_lock);
+
 	raw_reg_write(regs, GEN11_IIR_REG_SELECTOR(bank), BIT(bit));
 
 	/*
@@ -2835,42 +2845,101 @@ gen11_gt_engine_intr(struct drm_i915_private * const i915,
 	raw_reg_write(regs, GEN11_INTR_IDENTITY_REG(bank),
 		      GEN11_INTR_DATA_VALID);
 
-	return ident & GEN11_INTR_ENGINE_MASK;
+	return ident;
 }
 
 static void
-gen11_gt_irq_handler(struct drm_i915_private * const i915,
-		     const u32 master_ctl)
+gen11_other_irq_handler(struct drm_i915_private * const i915,
+			const u8 instance, const u16 iir)
+{
+	if (instance == OTHER_GTPM_INSTANCE)
+		return gen6_rps_irq_handler(i915, iir);
+
+	WARN_ONCE(1, "unhandled other interrupt instance=0x%x, iir=0x%x\n",
+		  instance, iir);
+}
+
+static void
+gen11_engine_irq_handler(struct drm_i915_private * const i915,
+			 const u8 class, const u8 instance, const u16 iir)
+{
+	struct intel_engine_cs *engine;
+
+	if (instance <= MAX_ENGINE_INSTANCE)
+		engine = i915->engine_class[class][instance];
+	else
+		engine = NULL;
+
+	if (likely(engine))
+		return gen8_cs_irq_handler(engine, iir);
+
+	WARN_ONCE(1, "unhandled engine interrupt class=0x%x, instance=0x%x\n",
+		  class, instance);
+}
+
+static void
+gen11_gt_identity_handler(struct drm_i915_private * const i915,
+			  const u32 identity)
+{
+	const u8 class = GEN11_INTR_ENGINE_CLASS(identity);
+	const u8 instance = GEN11_INTR_ENGINE_INSTANCE(identity);
+	const u16 intr = GEN11_INTR_ENGINE_INTR(identity);
+
+	if (unlikely(!intr))
+		return;
+
+	if (class <= COPY_ENGINE_CLASS)
+		return gen11_engine_irq_handler(i915, class, instance, intr);
+
+	if (class == OTHER_CLASS)
+		return gen11_other_irq_handler(i915, instance, intr);
+
+	WARN_ONCE(1, "unknown interrupt class=0x%x, instance=0x%x, intr=0x%x\n",
+		  class, instance, intr);
+}
+
+static void
+gen11_gt_bank_handler(struct drm_i915_private * const i915,
+		      const unsigned int bank)
 {
 	void __iomem * const regs = i915->regs;
-	unsigned int bank;
+	unsigned long intr_dw;
+	unsigned int bit;
 
-	for (bank = 0; bank < 2; bank++) {
-		unsigned long intr_dw;
-		unsigned int bit;
+	lockdep_assert_held(&i915->irq_lock);
 
-		if (!(master_ctl & GEN11_GT_DW_IRQ(bank)))
-			continue;
+	intr_dw = raw_reg_read(regs, GEN11_GT_INTR_DW(bank));
 
-		intr_dw = raw_reg_read(regs, GEN11_GT_INTR_DW(bank));
+	if (unlikely(!intr_dw)) {
+		DRM_ERROR("GT_INTR_DW%u blank!\n", bank);
+		return;
+	}
 
-		if (unlikely(!intr_dw)) {
-			DRM_ERROR("GT_INTR_DW%u blank!\n", bank);
-			continue;
-		}
+	for_each_set_bit(bit, &intr_dw, 32) {
+		const u32 ident = gen11_gt_engine_identity(i915,
+							   bank, bit);
 
-		for_each_set_bit(bit, &intr_dw, 32) {
-			const u16 iir = gen11_gt_engine_intr(i915, bank, bit);
+		gen11_gt_identity_handler(i915, ident);
+	}
 
-			if (unlikely(!iir))
-				continue;
+	/* Clear must be after shared has been served for engine */
+	raw_reg_write(regs, GEN11_GT_INTR_DW(bank), intr_dw);
+}
 
-			gen11_gt_engine_irq_handler(i915, bank, bit, iir);
-		}
+static void
+gen11_gt_irq_handler(struct drm_i915_private * const i915,
+		     const u32 master_ctl)
+{
+	unsigned int bank;
 
-		/* Clear must be after shared has been served for engine */
-		raw_reg_write(regs, GEN11_GT_INTR_DW(bank), intr_dw);
+	spin_lock(&i915->irq_lock);
+
+	for (bank = 0; bank < 2; bank++) {
+		if (master_ctl & GEN11_GT_DW_IRQ(bank))
+			gen11_gt_bank_handler(i915, bank);
 	}
+
+	spin_unlock(&i915->irq_lock);
 }
 
 static irqreturn_t gen11_irq_handler(int irq, void *arg)
@@ -2912,15 +2981,11 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-/**
- * i915_reset_device - do process context error handling work
- * @dev_priv: i915 device private
- *
- * Fire an error uevent so userspace can see that a hang or error
- * was detected.
- */
-static void i915_reset_device(struct drm_i915_private *dev_priv)
+static void i915_reset_device(struct drm_i915_private *dev_priv,
+			      u32 engine_mask,
+			      const char *reason)
 {
+	struct i915_gpu_error *error = &dev_priv->gpu_error;
 	struct kobject *kobj = &dev_priv->drm.primary->kdev->kobj;
 	char *error_event[] = { I915_ERROR_UEVENT "=1", NULL };
 	char *reset_event[] = { I915_RESET_UEVENT "=1", NULL };
@@ -2936,29 +3001,35 @@ static void i915_reset_device(struct drm_i915_private *dev_priv)
 	i915_wedge_on_timeout(&w, dev_priv, 5*HZ) {
 		intel_prepare_reset(dev_priv);
 
+		error->reason = reason;
+		error->stalled_mask = engine_mask;
+
 		/* Signal that locked waiters should reset the GPU */
-		set_bit(I915_RESET_HANDOFF, &dev_priv->gpu_error.flags);
-		wake_up_all(&dev_priv->gpu_error.wait_queue);
+		smp_mb__before_atomic();
+		set_bit(I915_RESET_HANDOFF, &error->flags);
+		wake_up_all(&error->wait_queue);
 
 		/* Wait for anyone holding the lock to wakeup, without
 		 * blocking indefinitely on struct_mutex.
 		 */
 		do {
 			if (mutex_trylock(&dev_priv->drm.struct_mutex)) {
-				i915_reset(dev_priv, 0);
+				i915_reset(dev_priv, engine_mask, reason);
 				mutex_unlock(&dev_priv->drm.struct_mutex);
 			}
-		} while (wait_on_bit_timeout(&dev_priv->gpu_error.flags,
+		} while (wait_on_bit_timeout(&error->flags,
 					     I915_RESET_HANDOFF,
 					     TASK_UNINTERRUPTIBLE,
 					     1));
 
+		error->stalled_mask = 0;
+		error->reason = NULL;
+
 		intel_finish_reset(dev_priv);
 	}
 
-	if (!test_bit(I915_WEDGED, &dev_priv->gpu_error.flags))
-		kobject_uevent_env(kobj,
-				   KOBJ_CHANGE, reset_done_event);
+	if (!test_bit(I915_WEDGED, &error->flags))
+		kobject_uevent_env(kobj, KOBJ_CHANGE, reset_done_event);
 }
 
 static void i915_clear_error_registers(struct drm_i915_private *dev_priv)
@@ -2990,6 +3061,7 @@ static void i915_clear_error_registers(struct drm_i915_private *dev_priv)
  * i915_handle_error - handle a gpu error
  * @dev_priv: i915 device private
  * @engine_mask: mask representing engines that are hung
+ * @flags: control flags
  * @fmt: Error message format string
  *
  * Do some basic checking of register state at error time and
@@ -3000,16 +3072,23 @@ static void i915_clear_error_registers(struct drm_i915_private *dev_priv)
  */
 void i915_handle_error(struct drm_i915_private *dev_priv,
 		       u32 engine_mask,
+		       unsigned long flags,
 		       const char *fmt, ...)
 {
 	struct intel_engine_cs *engine;
 	unsigned int tmp;
-	va_list args;
 	char error_msg[80];
+	char *msg = NULL;
 
-	va_start(args, fmt);
-	vscnprintf(error_msg, sizeof(error_msg), fmt, args);
-	va_end(args);
+	if (fmt) {
+		va_list args;
+
+		va_start(args, fmt);
+		vscnprintf(error_msg, sizeof(error_msg), fmt, args);
+		va_end(args);
+
+		msg = error_msg;
+	}
 
 	/*
 	 * In most cases it's guaranteed that we get here with an RPM
@@ -3020,8 +3099,12 @@ void i915_handle_error(struct drm_i915_private *dev_priv,
 	 */
 	intel_runtime_pm_get(dev_priv);
 
-	i915_capture_error_state(dev_priv, engine_mask, error_msg);
-	i915_clear_error_registers(dev_priv);
+	engine_mask &= INTEL_INFO(dev_priv)->ring_mask;
+
+	if (flags & I915_ERROR_CAPTURE) {
+		i915_capture_error_state(dev_priv, engine_mask, msg);
+		i915_clear_error_registers(dev_priv);
+	}
 
 	/*
 	 * Try engine reset when available. We fall back to full reset if
@@ -3034,7 +3117,7 @@ void i915_handle_error(struct drm_i915_private *dev_priv,
 					     &dev_priv->gpu_error.flags))
 				continue;
 
-			if (i915_reset_engine(engine, 0) == 0)
+			if (i915_reset_engine(engine, msg) == 0)
 				engine_mask &= ~intel_engine_flag(engine);
 
 			clear_bit(I915_RESET_ENGINE + engine->id,
@@ -3064,7 +3147,7 @@ void i915_handle_error(struct drm_i915_private *dev_priv,
 				    TASK_UNINTERRUPTIBLE);
 	}
 
-	i915_reset_device(dev_priv);
+	i915_reset_device(dev_priv, engine_mask, msg);
 
 	for_each_engine(engine, dev_priv, tmp) {
 		clear_bit(I915_RESET_ENGINE + engine->id,
@@ -3286,6 +3369,11 @@ static void ironlake_irq_reset(struct drm_device *dev)
 	if (IS_GEN7(dev_priv))
 		I915_WRITE(GEN7_ERR_INT, 0xffffffff);
 
+	if (IS_HASWELL(dev_priv)) {
+		I915_WRITE(EDP_PSR_IMR, 0xffffffff);
+		I915_WRITE(EDP_PSR_IIR, 0xffffffff);
+	}
+
 	gen5_gt_irq_reset(dev_priv);
 
 	ibx_irq_reset(dev_priv);
@@ -3324,6 +3412,9 @@ static void gen8_irq_reset(struct drm_device *dev)
 
 	gen8_gt_irq_reset(dev_priv);
 
+	I915_WRITE(EDP_PSR_IMR, 0xffffffff);
+	I915_WRITE(EDP_PSR_IIR, 0xffffffff);
+
 	for_each_pipe(dev_priv, pipe)
 		if (intel_display_power_is_enabled(dev_priv,
 						   POWER_DOMAIN_PIPE(pipe)))
@@ -3349,6 +3440,9 @@ static void gen11_gt_irq_reset(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN11_VCS0_VCS1_INTR_MASK,	~0);
 	I915_WRITE(GEN11_VCS2_VCS3_INTR_MASK,	~0);
 	I915_WRITE(GEN11_VECS0_VECS1_INTR_MASK,	~0);
+
+	I915_WRITE(GEN11_GPM_WGBOXPERF_INTR_ENABLE, 0);
+	I915_WRITE(GEN11_GPM_WGBOXPERF_INTR_MASK,  ~0);
 }
 
 static void gen11_irq_reset(struct drm_device *dev)
@@ -3697,6 +3791,12 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
 			      DE_DP_A_HOTPLUG);
 	}
 
+	if (IS_HASWELL(dev_priv)) {
+		gen3_assert_iir_is_zero(dev_priv, EDP_PSR_IIR);
+		intel_psr_irq_control(dev_priv, dev_priv->psr.debug);
+		display_mask |= DE_EDP_PSR_INT_HSW;
+	}
+
 	dev_priv->irq_mask = ~display_mask;
 
 	ibx_irq_pre_postinstall(dev);
@@ -3807,7 +3907,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	uint32_t de_pipe_enables;
 	u32 de_port_masked = GEN8_AUX_CHANNEL_A;
 	u32 de_port_enables;
-	u32 de_misc_masked = GEN8_DE_MISC_GSE;
+	u32 de_misc_masked = GEN8_DE_MISC_GSE | GEN8_DE_EDP_PSR;
 	enum pipe pipe;
 
 	if (INTEL_GEN(dev_priv) >= 9) {
@@ -3832,6 +3932,9 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	else if (IS_BROADWELL(dev_priv))
 		de_port_enables |= GEN8_PORT_DP_A_HOTPLUG;
 
+	gen3_assert_iir_is_zero(dev_priv, EDP_PSR_IIR);
+	intel_psr_irq_control(dev_priv, dev_priv->psr.debug);
+
 	for_each_pipe(dev_priv, pipe) {
 		dev_priv->de_irq_mask[pipe] = ~de_pipe_masked;
 
@@ -3887,7 +3990,14 @@ static void gen11_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN11_VCS2_VCS3_INTR_MASK,	~(irqs | irqs << 16));
 	I915_WRITE(GEN11_VECS0_VECS1_INTR_MASK,	~(irqs | irqs << 16));
 
-	dev_priv->pm_imr = 0xffffffff; /* TODO */
+	/*
+	 * RPS interrupts will get enabled/disabled on demand when RPS itself
+	 * is enabled/disabled.
+	 */
+	dev_priv->pm_ier = 0x0;
+	dev_priv->pm_imr = ~dev_priv->pm_ier;
+	I915_WRITE(GEN11_GPM_WGBOXPERF_INTR_ENABLE, 0);
+	I915_WRITE(GEN11_GPM_WGBOXPERF_INTR_MASK,  ~0);
 }
 
 static int gen11_irq_postinstall(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_oa_icl.c b/drivers/gpu/drm/i915/i915_oa_icl.c
new file mode 100644
index 000000000000..a5667926e3de
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_oa_icl.c
@@ -0,0 +1,118 @@
+/*
+ * Autogenerated file by GPU Top : https://github.com/rib/gputop
+ * DO NOT EDIT manually!
+ *
+ *
+ * Copyright (c) 2015 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/sysfs.h>
+
+#include "i915_drv.h"
+#include "i915_oa_icl.h"
+
+static const struct i915_oa_reg b_counter_config_test_oa[] = {
+	{ _MMIO(0x2740), 0x00000000 },
+	{ _MMIO(0x2710), 0x00000000 },
+	{ _MMIO(0x2714), 0xf0800000 },
+	{ _MMIO(0x2720), 0x00000000 },
+	{ _MMIO(0x2724), 0xf0800000 },
+	{ _MMIO(0x2770), 0x00000004 },
+	{ _MMIO(0x2774), 0x0000ffff },
+	{ _MMIO(0x2778), 0x00000003 },
+	{ _MMIO(0x277c), 0x0000ffff },
+	{ _MMIO(0x2780), 0x00000007 },
+	{ _MMIO(0x2784), 0x0000ffff },
+	{ _MMIO(0x2788), 0x00100002 },
+	{ _MMIO(0x278c), 0x0000fff7 },
+	{ _MMIO(0x2790), 0x00100002 },
+	{ _MMIO(0x2794), 0x0000ffcf },
+	{ _MMIO(0x2798), 0x00100082 },
+	{ _MMIO(0x279c), 0x0000ffef },
+	{ _MMIO(0x27a0), 0x001000c2 },
+	{ _MMIO(0x27a4), 0x0000ffe7 },
+	{ _MMIO(0x27a8), 0x00100001 },
+	{ _MMIO(0x27ac), 0x0000ffe7 },
+};
+
+static const struct i915_oa_reg flex_eu_config_test_oa[] = {
+};
+
+static const struct i915_oa_reg mux_config_test_oa[] = {
+	{ _MMIO(0xd04), 0x00000200 },
+	{ _MMIO(0x9840), 0x00000000 },
+	{ _MMIO(0x9884), 0x00000000 },
+	{ _MMIO(0x9888), 0x10060000 },
+	{ _MMIO(0x9888), 0x22060000 },
+	{ _MMIO(0x9888), 0x16060000 },
+	{ _MMIO(0x9888), 0x24060000 },
+	{ _MMIO(0x9888), 0x18060000 },
+	{ _MMIO(0x9888), 0x1a060000 },
+	{ _MMIO(0x9888), 0x12060000 },
+	{ _MMIO(0x9888), 0x14060000 },
+	{ _MMIO(0x9888), 0x10060000 },
+	{ _MMIO(0x9888), 0x22060000 },
+	{ _MMIO(0x9884), 0x00000003 },
+	{ _MMIO(0x9888), 0x16130000 },
+	{ _MMIO(0x9888), 0x24000001 },
+	{ _MMIO(0x9888), 0x0e130056 },
+	{ _MMIO(0x9888), 0x10130000 },
+	{ _MMIO(0x9888), 0x1a130000 },
+	{ _MMIO(0x9888), 0x541f0001 },
+	{ _MMIO(0x9888), 0x181f0000 },
+	{ _MMIO(0x9888), 0x4c1f0000 },
+	{ _MMIO(0x9888), 0x301f0000 },
+};
+
+static ssize_t
+show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "1\n");
+}
+
+void
+i915_perf_load_test_config_icl(struct drm_i915_private *dev_priv)
+{
+	strlcpy(dev_priv->perf.oa.test_config.uuid,
+		"a291665e-244b-4b76-9b9a-01de9d3c8068",
+		sizeof(dev_priv->perf.oa.test_config.uuid));
+	dev_priv->perf.oa.test_config.id = 1;
+
+	dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa;
+	dev_priv->perf.oa.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
+
+	dev_priv->perf.oa.test_config.b_counter_regs = b_counter_config_test_oa;
+	dev_priv->perf.oa.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
+
+	dev_priv->perf.oa.test_config.flex_regs = flex_eu_config_test_oa;
+	dev_priv->perf.oa.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
+
+	dev_priv->perf.oa.test_config.sysfs_metric.name = "a291665e-244b-4b76-9b9a-01de9d3c8068";
+	dev_priv->perf.oa.test_config.sysfs_metric.attrs = dev_priv->perf.oa.test_config.attrs;
+
+	dev_priv->perf.oa.test_config.attrs[0] = &dev_priv->perf.oa.test_config.sysfs_metric_id.attr;
+
+	dev_priv->perf.oa.test_config.sysfs_metric_id.attr.name = "id";
+	dev_priv->perf.oa.test_config.sysfs_metric_id.attr.mode = 0444;
+	dev_priv->perf.oa.test_config.sysfs_metric_id.show = show_test_oa_id;
+}
diff --git a/drivers/gpu/drm/i915/i915_oa_icl.h b/drivers/gpu/drm/i915/i915_oa_icl.h
new file mode 100644
index 000000000000..ae1c24aafe4f
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_oa_icl.h
@@ -0,0 +1,34 @@
+/*
+ * Autogenerated file by GPU Top : https://github.com/rib/gputop
+ * DO NOT EDIT manually!
+ *
+ *
+ * Copyright (c) 2015 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __I915_OA_ICL_H__
+#define __I915_OA_ICL_H__
+
+extern void i915_perf_load_test_config_icl(struct drm_i915_private *dev_priv);
+
+#endif
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 08108ce5be21..66ea3552c63e 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -164,6 +164,9 @@ i915_param_named_unsafe(guc_firmware_path, charp, 0400,
 i915_param_named_unsafe(huc_firmware_path, charp, 0400,
 	"HuC firmware path to use instead of the default one");
 
+i915_param_named_unsafe(dmc_firmware_path, charp, 0400,
+	"DMC firmware path to use instead of the default one");
+
 i915_param_named_unsafe(enable_dp_mst, bool, 0600,
 	"Enable multi-stream transport (MST) for new DisplayPort sinks. (default: true)");
 
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 430f5f9d0ff4..6684025b7af8 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -48,9 +48,10 @@ struct drm_printer;
 	param(int, enable_ips, 1) \
 	param(int, invert_brightness, 0) \
 	param(int, enable_guc, 0) \
-	param(int, guc_log_level, 0) \
+	param(int, guc_log_level, -1) \
 	param(char *, guc_firmware_path, NULL) \
 	param(char *, huc_firmware_path, NULL) \
+	param(char *, dmc_firmware_path, NULL) \
 	param(int, mmio_debug, 0) \
 	param(int, edp_vswing, 0) \
 	param(int, reset, 2) \
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 062e91b39085..4364922e935d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -602,6 +602,7 @@ static const struct intel_device_info intel_icelake_11_info = {
 	PLATFORM(INTEL_ICELAKE),
 	.is_alpha_support = 1,
 	.has_resource_streamer = 0,
+	.ring_mask = RENDER_RING | BLT_RING | VEBOX_RING | BSD_RING | BSD3_RING,
 };
 
 #undef GEN
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index abaca6edeb71..019bd2d073ad 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -209,6 +209,7 @@
 #include "i915_oa_cflgt2.h"
 #include "i915_oa_cflgt3.h"
 #include "i915_oa_cnl.h"
+#include "i915_oa_icl.h"
 
 /* HW requires this to be a power of two, between 128k and 16M, though driver
  * is currently generally designed assuming the largest 16M size is used such
@@ -1042,7 +1043,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 
 		I915_WRITE(GEN7_OASTATUS2,
 			   ((head & GEN7_OASTATUS2_HEAD_MASK) |
-			    OA_MEM_SELECT_GGTT));
+			    GEN7_OASTATUS2_MEM_SELECT_GGTT));
 		dev_priv->perf.oa.oa_buffer.head = head;
 
 		spin_unlock_irqrestore(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags);
@@ -1233,7 +1234,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		 *
 		 * NB: implied RCS engine...
 		 */
-		ring = engine->context_pin(engine, stream->ctx);
+		ring = intel_context_pin(stream->ctx, engine);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
 		if (IS_ERR(ring))
 			return PTR_ERR(ring);
@@ -1245,7 +1246,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		 * with gen8+ and execlists
 		 */
 		dev_priv->perf.oa.specific_ctx_id =
-			i915_ggtt_offset(stream->ctx->engine[engine->id].state);
+			i915_ggtt_offset(to_intel_context(stream->ctx, engine)->state);
 	}
 
 	return 0;
@@ -1270,7 +1271,7 @@ static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 		mutex_lock(&dev_priv->drm.struct_mutex);
 
 		dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
-		engine->context_unpin(engine, stream->ctx);
+		intel_context_unpin(stream->ctx, engine);
 
 		mutex_unlock(&dev_priv->drm.struct_mutex);
 	}
@@ -1332,7 +1333,8 @@ static void gen7_init_oa_buffer(struct drm_i915_private *dev_priv)
 	/* Pre-DevBDW: OABUFFER must be set with counters off,
 	 * before OASTATUS1, but after OASTATUS2
 	 */
-	I915_WRITE(GEN7_OASTATUS2, gtt_offset | OA_MEM_SELECT_GGTT); /* head */
+	I915_WRITE(GEN7_OASTATUS2,
+		   gtt_offset | GEN7_OASTATUS2_MEM_SELECT_GGTT); /* head */
 	dev_priv->perf.oa.oa_buffer.head = gtt_offset;
 
 	I915_WRITE(GEN7_OABUFFER, gtt_offset);
@@ -1392,7 +1394,7 @@ static void gen8_init_oa_buffer(struct drm_i915_private *dev_priv)
 	 *  bit."
 	 */
 	I915_WRITE(GEN8_OABUFFER, gtt_offset |
-		   OABUFFER_SIZE_16M | OA_MEM_SELECT_GGTT);
+		   OABUFFER_SIZE_16M | GEN8_OABUFFER_MEM_SELECT_GGTT);
 	I915_WRITE(GEN8_OATAILPTR, gtt_offset & GEN8_OATAILPTR_MASK);
 
 	/* Mark that we need updated tail pointers to read from... */
@@ -1693,7 +1695,7 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr
 						 const struct i915_oa_config *oa_config)
 {
 	struct intel_engine_cs *engine = dev_priv->engine[RCS];
-	struct i915_gem_timeline *timeline;
+	struct i915_timeline *timeline;
 	struct i915_request *rq;
 	int ret;
 
@@ -1714,15 +1716,11 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr
 	/* Queue this switch after all other activity */
 	list_for_each_entry(timeline, &dev_priv->gt.timelines, link) {
 		struct i915_request *prev;
-		struct intel_timeline *tl;
 
-		tl = &timeline->engine[engine->id];
-		prev = i915_gem_active_raw(&tl->last_request,
+		prev = i915_gem_active_raw(&timeline->last_request,
 					   &dev_priv->drm.struct_mutex);
 		if (prev)
-			i915_sw_fence_await_sw_fence_gfp(&rq->submit,
-							 &prev->submit,
-							 GFP_KERNEL);
+			i915_request_await_dma_fence(rq, &prev->fence);
 	}
 
 	i915_request_add(rq);
@@ -1757,6 +1755,7 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr
 static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv,
 				       const struct i915_oa_config *oa_config)
 {
+	struct intel_engine_cs *engine = dev_priv->engine[RCS];
 	struct i915_gem_context *ctx;
 	int ret;
 	unsigned int wait_flags = I915_WAIT_LOCKED;
@@ -1787,7 +1786,7 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv,
 
 	/* Update all contexts now that we've stalled the submission. */
 	list_for_each_entry(ctx, &dev_priv->contexts.list, link) {
-		struct intel_context *ce = &ctx->engine[RCS];
+		struct intel_context *ce = to_intel_context(ctx, engine);
 		u32 *regs;
 
 		/* OA settings will be set upon first use */
@@ -1840,7 +1839,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv,
 	 * be read back from automatically triggered reports, as part of the
 	 * RPT_ID field.
 	 */
-	if (IS_GEN9(dev_priv) || IS_GEN10(dev_priv)) {
+	if (IS_GEN(dev_priv, 9, 11)) {
 		I915_WRITE(GEN8_OA_DEBUG,
 			   _MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
 					      GEN9_OA_DEBUG_INCLUDE_CLK_RATIO));
@@ -1870,7 +1869,6 @@ static void gen8_disable_metric_set(struct drm_i915_private *dev_priv)
 
 	I915_WRITE(GDT_CHICKEN_BITS, (I915_READ(GDT_CHICKEN_BITS) &
 				      ~GT_NOA_ENABLE));
-
 }
 
 static void gen10_disable_metric_set(struct drm_i915_private *dev_priv)
@@ -1885,6 +1883,13 @@ static void gen10_disable_metric_set(struct drm_i915_private *dev_priv)
 
 static void gen7_oa_enable(struct drm_i915_private *dev_priv)
 {
+	struct i915_gem_context *ctx =
+			dev_priv->perf.oa.exclusive_stream->ctx;
+	u32 ctx_id = dev_priv->perf.oa.specific_ctx_id;
+	bool periodic = dev_priv->perf.oa.periodic;
+	u32 period_exponent = dev_priv->perf.oa.period_exponent;
+	u32 report_format = dev_priv->perf.oa.oa_buffer.format;
+
 	/*
 	 * Reset buf pointers so we don't forward reports from before now.
 	 *
@@ -1896,25 +1901,14 @@ static void gen7_oa_enable(struct drm_i915_private *dev_priv)
 	 */
 	gen7_init_oa_buffer(dev_priv);
 
-	if (dev_priv->perf.oa.exclusive_stream->enabled) {
-		struct i915_gem_context *ctx =
-			dev_priv->perf.oa.exclusive_stream->ctx;
-		u32 ctx_id = dev_priv->perf.oa.specific_ctx_id;
-
-		bool periodic = dev_priv->perf.oa.periodic;
-		u32 period_exponent = dev_priv->perf.oa.period_exponent;
-		u32 report_format = dev_priv->perf.oa.oa_buffer.format;
-
-		I915_WRITE(GEN7_OACONTROL,
-			   (ctx_id & GEN7_OACONTROL_CTX_MASK) |
-			   (period_exponent <<
-			    GEN7_OACONTROL_TIMER_PERIOD_SHIFT) |
-			   (periodic ? GEN7_OACONTROL_TIMER_ENABLE : 0) |
-			   (report_format << GEN7_OACONTROL_FORMAT_SHIFT) |
-			   (ctx ? GEN7_OACONTROL_PER_CTX_ENABLE : 0) |
-			   GEN7_OACONTROL_ENABLE);
-	} else
-		I915_WRITE(GEN7_OACONTROL, 0);
+	I915_WRITE(GEN7_OACONTROL,
+		   (ctx_id & GEN7_OACONTROL_CTX_MASK) |
+		   (period_exponent <<
+		    GEN7_OACONTROL_TIMER_PERIOD_SHIFT) |
+		   (periodic ? GEN7_OACONTROL_TIMER_ENABLE : 0) |
+		   (report_format << GEN7_OACONTROL_FORMAT_SHIFT) |
+		   (ctx ? GEN7_OACONTROL_PER_CTX_ENABLE : 0) |
+		   GEN7_OACONTROL_ENABLE);
 }
 
 static void gen8_oa_enable(struct drm_i915_private *dev_priv)
@@ -1966,11 +1960,19 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream)
 static void gen7_oa_disable(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(GEN7_OACONTROL, 0);
+	if (intel_wait_for_register(dev_priv,
+				    GEN7_OACONTROL, GEN7_OACONTROL_ENABLE, 0,
+				    50))
+		DRM_ERROR("wait for OA to be disabled timed out\n");
 }
 
 static void gen8_oa_disable(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(GEN8_OACONTROL, 0);
+	if (intel_wait_for_register(dev_priv,
+				    GEN8_OACONTROL, GEN8_OA_COUNTER_ENABLE, 0,
+				    50))
+		DRM_ERROR("wait for OA to be disabled timed out\n");
 }
 
 /**
@@ -2099,13 +2101,17 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 
 	if (stream->ctx) {
 		ret = oa_get_render_ctx_id(stream);
-		if (ret)
+		if (ret) {
+			DRM_DEBUG("Invalid context id to filter with\n");
 			return ret;
+		}
 	}
 
 	ret = get_oa_config(dev_priv, props->metrics_set, &stream->oa_config);
-	if (ret)
+	if (ret) {
+		DRM_DEBUG("Invalid OA config id=%i\n", props->metrics_set);
 		goto err_config;
+	}
 
 	/* PRM - observability performance counters:
 	 *
@@ -2132,8 +2138,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 
 	ret = dev_priv->perf.oa.ops.enable_metric_set(dev_priv,
 						      stream->oa_config);
-	if (ret)
+	if (ret) {
+		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
+	}
 
 	stream->ops = &i915_oa_stream_ops;
 
@@ -2745,7 +2753,8 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
 			props->ctx_handle = value;
 			break;
 		case DRM_I915_PERF_PROP_SAMPLE_OA:
-			props->sample_flags |= SAMPLE_OA_REPORT;
+			if (value)
+				props->sample_flags |= SAMPLE_OA_REPORT;
 			break;
 		case DRM_I915_PERF_PROP_OA_METRICS_SET:
 			if (value == 0) {
@@ -2935,6 +2944,8 @@ void i915_perf_register(struct drm_i915_private *dev_priv)
 			i915_perf_load_test_config_cflgt3(dev_priv);
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		i915_perf_load_test_config_cnl(dev_priv);
+	} else if (IS_ICELAKE(dev_priv)) {
+		i915_perf_load_test_config_icl(dev_priv);
 	}
 
 	if (dev_priv->perf.oa.test_config.id == 0)
@@ -3292,6 +3303,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 
 	mutex_unlock(&dev_priv->perf.metrics_lock);
 
+	DRM_DEBUG("Added config %s id=%i\n", oa_config->uuid, oa_config->id);
+
 	return oa_config->id;
 
 sysfs_err:
@@ -3348,6 +3361,9 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 			   &oa_config->sysfs_metric);
 
 	idr_remove(&dev_priv->perf.metrics_idr, *arg);
+
+	DRM_DEBUG("Removed config %s id=%i\n", oa_config->uuid, oa_config->id);
+
 	put_oa_config(dev_priv, oa_config);
 
 config_err:
@@ -3467,7 +3483,7 @@ void i915_perf_init(struct drm_i915_private *dev_priv)
 
 				dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16);
 			}
-		} else if (IS_GEN10(dev_priv)) {
+		} else if (IS_GEN(dev_priv, 10, 11)) {
 			dev_priv->perf.oa.ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
 			dev_priv->perf.oa.ops.is_valid_mux_reg =
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index d8feb9053e0c..dc87797db500 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -1,33 +1,12 @@
 /*
- * Copyright © 2017 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
+ * SPDX-License-Identifier: MIT
  *
+ * Copyright © 2017-2018 Intel Corporation
  */
 
-#include <linux/perf_event.h>
-#include <linux/pm_runtime.h>
-
-#include "i915_drv.h"
 #include "i915_pmu.h"
 #include "intel_ringbuffer.h"
+#include "i915_drv.h"
 
 /* Frequency for the sampling timer for events which need it. */
 #define FREQUENCY 200
@@ -473,20 +452,37 @@ static u64 get_rc6(struct drm_i915_private *i915)
 		spin_lock_irqsave(&i915->pmu.lock, flags);
 		spin_lock(&kdev->power.lock);
 
-		if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
-			i915->pmu.suspended_jiffies_last =
-						kdev->power.suspended_jiffies;
+		/*
+		 * After the above branch intel_runtime_pm_get_if_in_use failed
+		 * to get the runtime PM reference we cannot assume we are in
+		 * runtime suspend since we can either: a) race with coming out
+		 * of it before we took the power.lock, or b) there are other
+		 * states than suspended which can bring us here.
+		 *
+		 * We need to double-check that we are indeed currently runtime
+		 * suspended and if not we cannot do better than report the last
+		 * known RC6 value.
+		 */
+		if (kdev->power.runtime_status == RPM_SUSPENDED) {
+			if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
+				i915->pmu.suspended_jiffies_last =
+						  kdev->power.suspended_jiffies;
 
-		val = kdev->power.suspended_jiffies -
-		      i915->pmu.suspended_jiffies_last;
-		val += jiffies - kdev->power.accounting_timestamp;
+			val = kdev->power.suspended_jiffies -
+			      i915->pmu.suspended_jiffies_last;
+			val += jiffies - kdev->power.accounting_timestamp;
 
-		spin_unlock(&kdev->power.lock);
+			val = jiffies_to_nsecs(val);
+			val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
 
-		val = jiffies_to_nsecs(val);
-		val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
-		i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
+			i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
+		} else if (i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
+			val = i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
+		} else {
+			val = i915->pmu.sample[__I915_SAMPLE_RC6].cur;
+		}
 
+		spin_unlock(&kdev->power.lock);
 		spin_unlock_irqrestore(&i915->pmu.lock, flags);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index aa1b1a987ea1..2ba735299f7c 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -1,29 +1,19 @@
 /*
- * Copyright © 2017 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
+ * SPDX-License-Identifier: MIT
  *
+ * Copyright © 2017-2018 Intel Corporation
  */
+
 #ifndef __I915_PMU_H__
 #define __I915_PMU_H__
 
+#include <linux/hrtimer.h>
+#include <linux/perf_event.h>
+#include <linux/spinlock_types.h>
+#include <drm/i915_drm.h>
+
+struct drm_i915_private;
+
 enum {
 	__I915_SAMPLE_FREQ_ACT = 0,
 	__I915_SAMPLE_FREQ_REQ,
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index 3ace929dd90f..3f502eef2431 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -4,6 +4,8 @@
  * Copyright © 2018 Intel Corporation
  */
 
+#include <linux/nospec.h>
+
 #include "i915_drv.h"
 #include "i915_query.h"
 #include <uapi/drm/i915_drm.h>
@@ -100,7 +102,7 @@ int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	for (i = 0; i < args->num_items; i++, user_item_ptr++) {
 		struct drm_i915_query_item item;
-		u64 func_idx;
+		unsigned long func_idx;
 		int ret;
 
 		if (copy_from_user(&item, user_item_ptr, sizeof(item)))
@@ -109,12 +111,17 @@ int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		if (item.query_id == 0)
 			return -EINVAL;
 
+		if (overflows_type(item.query_id - 1, unsigned long))
+			return -EINVAL;
+
 		func_idx = item.query_id - 1;
 
-		if (func_idx < ARRAY_SIZE(i915_query_funcs))
+		ret = -EINVAL;
+		if (func_idx < ARRAY_SIZE(i915_query_funcs)) {
+			func_idx = array_index_nospec(func_idx,
+						      ARRAY_SIZE(i915_query_funcs));
 			ret = i915_query_funcs[func_idx](dev_priv, &item);
-		else
-			ret = -EINVAL;
+		}
 
 		/* Only write the length back to userspace if they differ. */
 		if (ret != item.length && put_user(ret, &user_item_ptr->length))
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e6a8c0ee7df1..f11bb213ec07 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -153,9 +153,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define _MMIO_PORT3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
 #define _PLL(pll, a, b) ((a) + (pll)*((b)-(a)))
 #define _MMIO_PLL(pll, a, b) _MMIO(_PLL(pll, a, b))
-#define _MMIO_PORT6(port, a, b, c, d, e, f) _MMIO(_PICK(port, a, b, c, d, e, f))
-#define _MMIO_PORT6_LN(port, ln, a0, a1, b, c, d, e, f)			\
-	_MMIO(_PICK(port, a0, b, c, d, e, f) + (ln * (a1 - a0)))
 #define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__)
 #define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c))
 
@@ -191,6 +188,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OTHER_CLASS		4
 #define MAX_ENGINE_CLASS	4
 
+#define OTHER_GTPM_INSTANCE	1
 #define MAX_ENGINE_INSTANCE    3
 
 /* PCI config space */
@@ -304,6 +302,17 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN6_GRDOM_VECS		(1 << 4)
 #define  GEN9_GRDOM_GUC			(1 << 5)
 #define  GEN8_GRDOM_MEDIA2		(1 << 7)
+/* GEN11 changed all bit defs except for FULL & RENDER */
+#define  GEN11_GRDOM_FULL		GEN6_GRDOM_FULL
+#define  GEN11_GRDOM_RENDER		GEN6_GRDOM_RENDER
+#define  GEN11_GRDOM_BLT		(1 << 2)
+#define  GEN11_GRDOM_GUC		(1 << 3)
+#define  GEN11_GRDOM_MEDIA		(1 << 5)
+#define  GEN11_GRDOM_MEDIA2		(1 << 6)
+#define  GEN11_GRDOM_MEDIA3		(1 << 7)
+#define  GEN11_GRDOM_MEDIA4		(1 << 8)
+#define  GEN11_GRDOM_VECS		(1 << 13)
+#define  GEN11_GRDOM_VECS2		(1 << 14)
 
 #define RING_PP_DIR_BASE(engine)	_MMIO((engine)->mmio_base+0x228)
 #define RING_PP_DIR_BASE_READ(engine)	_MMIO((engine)->mmio_base+0x518)
@@ -430,145 +439,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define VGA_CR_INDEX_CGA 0x3d4
 #define VGA_CR_DATA_CGA 0x3d5
 
-/*
- * Instruction field definitions used by the command parser
- */
-#define INSTR_CLIENT_SHIFT      29
-#define   INSTR_MI_CLIENT       0x0
-#define   INSTR_BC_CLIENT       0x2
-#define   INSTR_RC_CLIENT       0x3
-#define INSTR_SUBCLIENT_SHIFT   27
-#define INSTR_SUBCLIENT_MASK    0x18000000
-#define   INSTR_MEDIA_SUBCLIENT 0x2
-#define INSTR_26_TO_24_MASK	0x7000000
-#define   INSTR_26_TO_24_SHIFT	24
-
-/*
- * Memory interface instructions used by the kernel
- */
-#define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags))
-/* Many MI commands use bit 22 of the header dword for GGTT vs PPGTT */
-#define  MI_GLOBAL_GTT    (1<<22)
-
-#define MI_NOOP			MI_INSTR(0, 0)
-#define MI_USER_INTERRUPT	MI_INSTR(0x02, 0)
-#define MI_WAIT_FOR_EVENT       MI_INSTR(0x03, 0)
-#define   MI_WAIT_FOR_OVERLAY_FLIP	(1<<16)
-#define   MI_WAIT_FOR_PLANE_B_FLIP      (1<<6)
-#define   MI_WAIT_FOR_PLANE_A_FLIP      (1<<2)
-#define   MI_WAIT_FOR_PLANE_A_SCANLINES (1<<1)
-#define MI_FLUSH		MI_INSTR(0x04, 0)
-#define   MI_READ_FLUSH		(1 << 0)
-#define   MI_EXE_FLUSH		(1 << 1)
-#define   MI_NO_WRITE_FLUSH	(1 << 2)
-#define   MI_SCENE_COUNT	(1 << 3) /* just increment scene count */
-#define   MI_END_SCENE		(1 << 4) /* flush binner and incr scene count */
-#define   MI_INVALIDATE_ISP	(1 << 5) /* invalidate indirect state pointers */
-#define MI_REPORT_HEAD		MI_INSTR(0x07, 0)
-#define MI_ARB_ON_OFF		MI_INSTR(0x08, 0)
-#define   MI_ARB_ENABLE			(1<<0)
-#define   MI_ARB_DISABLE		(0<<0)
-#define MI_BATCH_BUFFER_END	MI_INSTR(0x0a, 0)
-#define MI_SUSPEND_FLUSH	MI_INSTR(0x0b, 0)
-#define   MI_SUSPEND_FLUSH_EN	(1<<0)
-#define MI_SET_APPID		MI_INSTR(0x0e, 0)
-#define MI_OVERLAY_FLIP		MI_INSTR(0x11, 0)
-#define   MI_OVERLAY_CONTINUE	(0x0<<21)
-#define   MI_OVERLAY_ON		(0x1<<21)
-#define   MI_OVERLAY_OFF	(0x2<<21)
-#define MI_LOAD_SCAN_LINES_INCL MI_INSTR(0x12, 0)
-#define MI_DISPLAY_FLIP		MI_INSTR(0x14, 2)
-#define MI_DISPLAY_FLIP_I915	MI_INSTR(0x14, 1)
-#define   MI_DISPLAY_FLIP_PLANE(n) ((n) << 20)
-/* IVB has funny definitions for which plane to flip. */
-#define   MI_DISPLAY_FLIP_IVB_PLANE_A  (0 << 19)
-#define   MI_DISPLAY_FLIP_IVB_PLANE_B  (1 << 19)
-#define   MI_DISPLAY_FLIP_IVB_SPRITE_A (2 << 19)
-#define   MI_DISPLAY_FLIP_IVB_SPRITE_B (3 << 19)
-#define   MI_DISPLAY_FLIP_IVB_PLANE_C  (4 << 19)
-#define   MI_DISPLAY_FLIP_IVB_SPRITE_C (5 << 19)
-/* SKL ones */
-#define   MI_DISPLAY_FLIP_SKL_PLANE_1_A	(0 << 8)
-#define   MI_DISPLAY_FLIP_SKL_PLANE_1_B	(1 << 8)
-#define   MI_DISPLAY_FLIP_SKL_PLANE_1_C	(2 << 8)
-#define   MI_DISPLAY_FLIP_SKL_PLANE_2_A	(4 << 8)
-#define   MI_DISPLAY_FLIP_SKL_PLANE_2_B	(5 << 8)
-#define   MI_DISPLAY_FLIP_SKL_PLANE_2_C	(6 << 8)
-#define   MI_DISPLAY_FLIP_SKL_PLANE_3_A	(7 << 8)
-#define   MI_DISPLAY_FLIP_SKL_PLANE_3_B	(8 << 8)
-#define   MI_DISPLAY_FLIP_SKL_PLANE_3_C	(9 << 8)
-#define MI_SEMAPHORE_MBOX	MI_INSTR(0x16, 1) /* gen6, gen7 */
-#define   MI_SEMAPHORE_GLOBAL_GTT    (1<<22)
-#define   MI_SEMAPHORE_UPDATE	    (1<<21)
-#define   MI_SEMAPHORE_COMPARE	    (1<<20)
-#define   MI_SEMAPHORE_REGISTER	    (1<<18)
-#define   MI_SEMAPHORE_SYNC_VR	    (0<<16) /* RCS  wait for VCS  (RVSYNC) */
-#define   MI_SEMAPHORE_SYNC_VER	    (1<<16) /* RCS  wait for VECS (RVESYNC) */
-#define   MI_SEMAPHORE_SYNC_BR	    (2<<16) /* RCS  wait for BCS  (RBSYNC) */
-#define   MI_SEMAPHORE_SYNC_BV	    (0<<16) /* VCS  wait for BCS  (VBSYNC) */
-#define   MI_SEMAPHORE_SYNC_VEV	    (1<<16) /* VCS  wait for VECS (VVESYNC) */
-#define   MI_SEMAPHORE_SYNC_RV	    (2<<16) /* VCS  wait for RCS  (VRSYNC) */
-#define   MI_SEMAPHORE_SYNC_RB	    (0<<16) /* BCS  wait for RCS  (BRSYNC) */
-#define   MI_SEMAPHORE_SYNC_VEB	    (1<<16) /* BCS  wait for VECS (BVESYNC) */
-#define   MI_SEMAPHORE_SYNC_VB	    (2<<16) /* BCS  wait for VCS  (BVSYNC) */
-#define   MI_SEMAPHORE_SYNC_BVE	    (0<<16) /* VECS wait for BCS  (VEBSYNC) */
-#define   MI_SEMAPHORE_SYNC_VVE	    (1<<16) /* VECS wait for VCS  (VEVSYNC) */
-#define   MI_SEMAPHORE_SYNC_RVE	    (2<<16) /* VECS wait for RCS  (VERSYNC) */
-#define   MI_SEMAPHORE_SYNC_INVALID (3<<16)
-#define   MI_SEMAPHORE_SYNC_MASK    (3<<16)
-#define MI_SET_CONTEXT		MI_INSTR(0x18, 0)
-#define   MI_MM_SPACE_GTT		(1<<8)
-#define   MI_MM_SPACE_PHYSICAL		(0<<8)
-#define   MI_SAVE_EXT_STATE_EN		(1<<3)
-#define   MI_RESTORE_EXT_STATE_EN	(1<<2)
-#define   MI_FORCE_RESTORE		(1<<1)
-#define   MI_RESTORE_INHIBIT		(1<<0)
-#define   HSW_MI_RS_SAVE_STATE_EN       (1<<3)
-#define   HSW_MI_RS_RESTORE_STATE_EN    (1<<2)
-#define MI_SEMAPHORE_SIGNAL	MI_INSTR(0x1b, 0) /* GEN8+ */
-#define   MI_SEMAPHORE_TARGET(engine)	((engine)<<15)
-#define MI_SEMAPHORE_WAIT	MI_INSTR(0x1c, 2) /* GEN8+ */
-#define   MI_SEMAPHORE_POLL		(1<<15)
-#define   MI_SEMAPHORE_SAD_GTE_SDD	(1<<12)
-#define MI_STORE_DWORD_IMM	MI_INSTR(0x20, 1)
-#define MI_STORE_DWORD_IMM_GEN4	MI_INSTR(0x20, 2)
-#define   MI_MEM_VIRTUAL	(1 << 22) /* 945,g33,965 */
-#define   MI_USE_GGTT		(1 << 22) /* g4x+ */
-#define MI_STORE_DWORD_INDEX	MI_INSTR(0x21, 1)
-#define   MI_STORE_DWORD_INDEX_SHIFT 2
-/* Official intel docs are somewhat sloppy concerning MI_LOAD_REGISTER_IMM:
- * - Always issue a MI_NOOP _before_ the MI_LOAD_REGISTER_IMM - otherwise hw
- *   simply ignores the register load under certain conditions.
- * - One can actually load arbitrary many arbitrary registers: Simply issue x
- *   address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
- */
-#define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
-#define   MI_LRI_FORCE_POSTED		(1<<12)
-#define MI_STORE_REGISTER_MEM        MI_INSTR(0x24, 1)
-#define MI_STORE_REGISTER_MEM_GEN8   MI_INSTR(0x24, 2)
-#define   MI_SRM_LRM_GLOBAL_GTT		(1<<22)
-#define MI_FLUSH_DW		MI_INSTR(0x26, 1) /* for GEN6 */
-#define   MI_FLUSH_DW_STORE_INDEX	(1<<21)
-#define   MI_INVALIDATE_TLB		(1<<18)
-#define   MI_FLUSH_DW_OP_STOREDW	(1<<14)
-#define   MI_FLUSH_DW_OP_MASK		(3<<14)
-#define   MI_FLUSH_DW_NOTIFY		(1<<8)
-#define   MI_INVALIDATE_BSD		(1<<7)
-#define   MI_FLUSH_DW_USE_GTT		(1<<2)
-#define   MI_FLUSH_DW_USE_PPGTT		(0<<2)
-#define MI_LOAD_REGISTER_MEM	   MI_INSTR(0x29, 1)
-#define MI_LOAD_REGISTER_MEM_GEN8  MI_INSTR(0x29, 2)
-#define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
-#define   MI_BATCH_NON_SECURE		(1)
-/* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
-#define   MI_BATCH_NON_SECURE_I965	(1<<8)
-#define   MI_BATCH_PPGTT_HSW		(1<<8)
-#define   MI_BATCH_NON_SECURE_HSW	(1<<13)
-#define MI_BATCH_BUFFER_START	MI_INSTR(0x31, 0)
-#define   MI_BATCH_GTT		    (2<<6) /* aliased with (1<<7) on gen4 */
-#define MI_BATCH_BUFFER_START_GEN8	MI_INSTR(0x31, 1)
-#define   MI_BATCH_RESOURCE_STREAMER (1<<10)
-
 #define MI_PREDICATE_SRC0	_MMIO(0x2400)
 #define MI_PREDICATE_SRC0_UDW	_MMIO(0x2400 + 4)
 #define MI_PREDICATE_SRC1	_MMIO(0x2408)
@@ -579,130 +449,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  LOWER_SLICE_DISABLED	(0<<0)
 
 /*
- * 3D instructions used by the kernel
- */
-#define GFX_INSTR(opcode, flags) ((0x3 << 29) | ((opcode) << 24) | (flags))
-
-#define GEN9_MEDIA_POOL_STATE     ((0x3 << 29) | (0x2 << 27) | (0x5 << 16) | 4)
-#define   GEN9_MEDIA_POOL_ENABLE  (1 << 31)
-#define GFX_OP_RASTER_RULES    ((0x3<<29)|(0x7<<24))
-#define GFX_OP_SCISSOR         ((0x3<<29)|(0x1c<<24)|(0x10<<19))
-#define   SC_UPDATE_SCISSOR       (0x1<<1)
-#define   SC_ENABLE_MASK          (0x1<<0)
-#define   SC_ENABLE               (0x1<<0)
-#define GFX_OP_LOAD_INDIRECT   ((0x3<<29)|(0x1d<<24)|(0x7<<16))
-#define GFX_OP_SCISSOR_INFO    ((0x3<<29)|(0x1d<<24)|(0x81<<16)|(0x1))
-#define   SCI_YMIN_MASK      (0xffff<<16)
-#define   SCI_XMIN_MASK      (0xffff<<0)
-#define   SCI_YMAX_MASK      (0xffff<<16)
-#define   SCI_XMAX_MASK      (0xffff<<0)
-#define GFX_OP_SCISSOR_ENABLE	 ((0x3<<29)|(0x1c<<24)|(0x10<<19))
-#define GFX_OP_SCISSOR_RECT	 ((0x3<<29)|(0x1d<<24)|(0x81<<16)|1)
-#define GFX_OP_COLOR_FACTOR      ((0x3<<29)|(0x1d<<24)|(0x1<<16)|0x0)
-#define GFX_OP_STIPPLE           ((0x3<<29)|(0x1d<<24)|(0x83<<16))
-#define GFX_OP_MAP_INFO          ((0x3<<29)|(0x1d<<24)|0x4)
-#define GFX_OP_DESTBUFFER_VARS   ((0x3<<29)|(0x1d<<24)|(0x85<<16)|0x0)
-#define GFX_OP_DESTBUFFER_INFO	 ((0x3<<29)|(0x1d<<24)|(0x8e<<16)|1)
-#define GFX_OP_DRAWRECT_INFO     ((0x3<<29)|(0x1d<<24)|(0x80<<16)|(0x3))
-#define GFX_OP_DRAWRECT_INFO_I965  ((0x7900<<16)|0x2)
-
-#define COLOR_BLT_CMD			(2<<29 | 0x40<<22 | (5-2))
-#define SRC_COPY_BLT_CMD		((2<<29)|(0x43<<22)|4)
-#define XY_SRC_COPY_BLT_CMD		((2<<29)|(0x53<<22)|6)
-#define XY_MONO_SRC_COPY_IMM_BLT	((2<<29)|(0x71<<22)|5)
-#define   BLT_WRITE_A			(2<<20)
-#define   BLT_WRITE_RGB			(1<<20)
-#define   BLT_WRITE_RGBA		(BLT_WRITE_RGB | BLT_WRITE_A)
-#define   BLT_DEPTH_8			(0<<24)
-#define   BLT_DEPTH_16_565		(1<<24)
-#define   BLT_DEPTH_16_1555		(2<<24)
-#define   BLT_DEPTH_32			(3<<24)
-#define   BLT_ROP_SRC_COPY		(0xcc<<16)
-#define   BLT_ROP_COLOR_COPY		(0xf0<<16)
-#define XY_SRC_COPY_BLT_SRC_TILED	(1<<15) /* 965+ only */
-#define XY_SRC_COPY_BLT_DST_TILED	(1<<11) /* 965+ only */
-#define CMD_OP_DISPLAYBUFFER_INFO ((0x0<<29)|(0x14<<23)|2)
-#define   ASYNC_FLIP                (1<<22)
-#define   DISPLAY_PLANE_A           (0<<20)
-#define   DISPLAY_PLANE_B           (1<<20)
-#define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2))
-#define   PIPE_CONTROL_FLUSH_L3				(1<<27)
-#define   PIPE_CONTROL_GLOBAL_GTT_IVB			(1<<24) /* gen7+ */
-#define   PIPE_CONTROL_MMIO_WRITE			(1<<23)
-#define   PIPE_CONTROL_STORE_DATA_INDEX			(1<<21)
-#define   PIPE_CONTROL_CS_STALL				(1<<20)
-#define   PIPE_CONTROL_TLB_INVALIDATE			(1<<18)
-#define   PIPE_CONTROL_MEDIA_STATE_CLEAR		(1<<16)
-#define   PIPE_CONTROL_QW_WRITE				(1<<14)
-#define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
-#define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
-#define   PIPE_CONTROL_WRITE_FLUSH			(1<<12)
-#define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12) /* gen6+ */
-#define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11) /* MBZ on Ironlake */
-#define   PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE		(1<<10) /* GM45+ only */
-#define   PIPE_CONTROL_INDIRECT_STATE_DISABLE		(1<<9)
-#define   PIPE_CONTROL_NOTIFY				(1<<8)
-#define   PIPE_CONTROL_FLUSH_ENABLE			(1<<7) /* gen7+ */
-#define   PIPE_CONTROL_DC_FLUSH_ENABLE			(1<<5)
-#define   PIPE_CONTROL_VF_CACHE_INVALIDATE		(1<<4)
-#define   PIPE_CONTROL_CONST_CACHE_INVALIDATE		(1<<3)
-#define   PIPE_CONTROL_STATE_CACHE_INVALIDATE		(1<<2)
-#define   PIPE_CONTROL_STALL_AT_SCOREBOARD		(1<<1)
-#define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
-#define   PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
-
-/*
- * Commands used only by the command parser
- */
-#define MI_SET_PREDICATE        MI_INSTR(0x01, 0)
-#define MI_ARB_CHECK            MI_INSTR(0x05, 0)
-#define MI_RS_CONTROL           MI_INSTR(0x06, 0)
-#define MI_URB_ATOMIC_ALLOC     MI_INSTR(0x09, 0)
-#define MI_PREDICATE            MI_INSTR(0x0C, 0)
-#define MI_RS_CONTEXT           MI_INSTR(0x0F, 0)
-#define MI_TOPOLOGY_FILTER      MI_INSTR(0x0D, 0)
-#define MI_LOAD_SCAN_LINES_EXCL MI_INSTR(0x13, 0)
-#define MI_URB_CLEAR            MI_INSTR(0x19, 0)
-#define MI_UPDATE_GTT           MI_INSTR(0x23, 0)
-#define MI_CLFLUSH              MI_INSTR(0x27, 0)
-#define MI_REPORT_PERF_COUNT    MI_INSTR(0x28, 0)
-#define   MI_REPORT_PERF_COUNT_GGTT (1<<0)
-#define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 0)
-#define MI_RS_STORE_DATA_IMM    MI_INSTR(0x2B, 0)
-#define MI_LOAD_URB_MEM         MI_INSTR(0x2C, 0)
-#define MI_STORE_URB_MEM        MI_INSTR(0x2D, 0)
-#define MI_CONDITIONAL_BATCH_BUFFER_END MI_INSTR(0x36, 0)
-
-#define PIPELINE_SELECT                ((0x3<<29)|(0x1<<27)|(0x1<<24)|(0x4<<16))
-#define GFX_OP_3DSTATE_VF_STATISTICS   ((0x3<<29)|(0x1<<27)|(0x0<<24)|(0xB<<16))
-#define MEDIA_VFE_STATE                ((0x3<<29)|(0x2<<27)|(0x0<<24)|(0x0<<16))
-#define  MEDIA_VFE_STATE_MMIO_ACCESS_MASK (0x18)
-#define GPGPU_OBJECT                   ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x4<<16))
-#define GPGPU_WALKER                   ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x5<<16))
-#define GFX_OP_3DSTATE_DX9_CONSTANTF_VS \
-	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x39<<16))
-#define GFX_OP_3DSTATE_DX9_CONSTANTF_PS \
-	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x3A<<16))
-#define GFX_OP_3DSTATE_SO_DECL_LIST \
-	((0x3<<29)|(0x3<<27)|(0x1<<24)|(0x17<<16))
-
-#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_VS \
-	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x43<<16))
-#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_GS \
-	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x44<<16))
-#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_HS \
-	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x45<<16))
-#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_DS \
-	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x46<<16))
-#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS \
-	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x47<<16))
-
-#define MFX_WAIT  ((0x3<<29)|(0x1<<27)|(0x0<<16))
-
-#define COLOR_BLT     ((0x2<<29)|(0x40<<22))
-#define SRC_COPY_BLT  ((0x2<<29)|(0x43<<22))
-
-/*
  * Registers used only by the command parser
  */
 #define BCS_SWCTRL _MMIO(0x22200)
@@ -802,6 +548,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define GEN8_OABUFFER_UDW _MMIO(0x23b4)
 #define GEN8_OABUFFER _MMIO(0x2b14)
+#define  GEN8_OABUFFER_MEM_SELECT_GGTT      (1 << 0)  /* 0: PPGTT, 1: GGTT */
 
 #define GEN7_OASTATUS1 _MMIO(0x2364)
 #define  GEN7_OASTATUS1_TAIL_MASK	    0xffffffc0
@@ -810,7 +557,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN7_OASTATUS1_REPORT_LOST	    (1<<0)
 
 #define GEN7_OASTATUS2 _MMIO(0x2368)
-#define GEN7_OASTATUS2_HEAD_MASK    0xffffffc0
+#define  GEN7_OASTATUS2_HEAD_MASK           0xffffffc0
+#define  GEN7_OASTATUS2_MEM_SELECT_GGTT     (1 << 0) /* 0: PPGTT, 1: GGTT */
 
 #define GEN8_OASTATUS _MMIO(0x2b08)
 #define  GEN8_OASTATUS_OVERRUN_STATUS	    (1<<3)
@@ -832,8 +580,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OABUFFER_SIZE_8M    (6<<3)
 #define OABUFFER_SIZE_16M   (7<<3)
 
-#define OA_MEM_SELECT_GGTT  (1<<0)
-
 /*
  * Flexible, Aggregate EU Counter Registers.
  * Note: these aren't contiguous
@@ -1127,6 +873,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK	(1 << GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT)
 #define  GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ	0
 #define  GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ	1
+#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT	3
+#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK	(0x7 << GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT)
+#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ	0
+#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ	1
+#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_38_4_MHZ	2
+#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_25_MHZ	3
 #define  GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT	1
 #define  GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK	(0x3 << GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT)
 
@@ -1948,79 +1700,100 @@ enum i915_power_well_id {
 #define _CNL_PORT_PCS_DW1_LN0_C		0x162C04
 #define _CNL_PORT_PCS_DW1_LN0_D		0x162E04
 #define _CNL_PORT_PCS_DW1_LN0_F		0x162804
-#define CNL_PORT_PCS_DW1_GRP(port)	_MMIO_PORT6(port, \
+#define CNL_PORT_PCS_DW1_GRP(port)	_MMIO(_PICK(port, \
 						    _CNL_PORT_PCS_DW1_GRP_AE, \
 						    _CNL_PORT_PCS_DW1_GRP_B, \
 						    _CNL_PORT_PCS_DW1_GRP_C, \
 						    _CNL_PORT_PCS_DW1_GRP_D, \
 						    _CNL_PORT_PCS_DW1_GRP_AE, \
-						    _CNL_PORT_PCS_DW1_GRP_F)
-#define CNL_PORT_PCS_DW1_LN0(port)	_MMIO_PORT6(port, \
+						    _CNL_PORT_PCS_DW1_GRP_F))
+
+#define CNL_PORT_PCS_DW1_LN0(port)	_MMIO(_PICK(port, \
 						    _CNL_PORT_PCS_DW1_LN0_AE, \
 						    _CNL_PORT_PCS_DW1_LN0_B, \
 						    _CNL_PORT_PCS_DW1_LN0_C, \
 						    _CNL_PORT_PCS_DW1_LN0_D, \
 						    _CNL_PORT_PCS_DW1_LN0_AE, \
-						    _CNL_PORT_PCS_DW1_LN0_F)
+						    _CNL_PORT_PCS_DW1_LN0_F))
+#define _ICL_PORT_PCS_DW1_GRP_A		0x162604
+#define _ICL_PORT_PCS_DW1_GRP_B		0x6C604
+#define _ICL_PORT_PCS_DW1_LN0_A		0x162804
+#define _ICL_PORT_PCS_DW1_LN0_B		0x6C804
+#define ICL_PORT_PCS_DW1_GRP(port)	_MMIO_PORT(port,\
+						   _ICL_PORT_PCS_DW1_GRP_A, \
+						   _ICL_PORT_PCS_DW1_GRP_B)
+#define ICL_PORT_PCS_DW1_LN0(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_PCS_DW1_LN0_A, \
+						   _ICL_PORT_PCS_DW1_LN0_B)
 #define   COMMON_KEEPER_EN		(1 << 26)
 
-#define _CNL_PORT_TX_DW2_GRP_AE		0x162348
-#define _CNL_PORT_TX_DW2_GRP_B		0x1623C8
-#define _CNL_PORT_TX_DW2_GRP_C		0x162B48
-#define _CNL_PORT_TX_DW2_GRP_D		0x162BC8
-#define _CNL_PORT_TX_DW2_GRP_F		0x162A48
-#define _CNL_PORT_TX_DW2_LN0_AE		0x162448
-#define _CNL_PORT_TX_DW2_LN0_B		0x162648
-#define _CNL_PORT_TX_DW2_LN0_C		0x162C48
-#define _CNL_PORT_TX_DW2_LN0_D		0x162E48
-#define _CNL_PORT_TX_DW2_LN0_F		0x162848
-#define CNL_PORT_TX_DW2_GRP(port)	_MMIO_PORT6(port, \
-						    _CNL_PORT_TX_DW2_GRP_AE, \
-						    _CNL_PORT_TX_DW2_GRP_B, \
-						    _CNL_PORT_TX_DW2_GRP_C, \
-						    _CNL_PORT_TX_DW2_GRP_D, \
-						    _CNL_PORT_TX_DW2_GRP_AE, \
-						    _CNL_PORT_TX_DW2_GRP_F)
-#define CNL_PORT_TX_DW2_LN0(port)	_MMIO_PORT6(port, \
-						    _CNL_PORT_TX_DW2_LN0_AE, \
-						    _CNL_PORT_TX_DW2_LN0_B, \
-						    _CNL_PORT_TX_DW2_LN0_C, \
-						    _CNL_PORT_TX_DW2_LN0_D, \
-						    _CNL_PORT_TX_DW2_LN0_AE, \
-						    _CNL_PORT_TX_DW2_LN0_F)
-#define   SWING_SEL_UPPER(x)		((x >> 3) << 15)
+/* CNL Port TX registers */
+#define _CNL_PORT_TX_AE_GRP_OFFSET		0x162340
+#define _CNL_PORT_TX_B_GRP_OFFSET		0x1623C0
+#define _CNL_PORT_TX_C_GRP_OFFSET		0x162B40
+#define _CNL_PORT_TX_D_GRP_OFFSET		0x162BC0
+#define _CNL_PORT_TX_F_GRP_OFFSET		0x162A40
+#define _CNL_PORT_TX_AE_LN0_OFFSET		0x162440
+#define _CNL_PORT_TX_B_LN0_OFFSET		0x162640
+#define _CNL_PORT_TX_C_LN0_OFFSET		0x162C40
+#define _CNL_PORT_TX_D_LN0_OFFSET		0x162E40
+#define _CNL_PORT_TX_F_LN0_OFFSET		0x162840
+#define _CNL_PORT_TX_DW_GRP(port, dw)	(_PICK((port), \
+					       _CNL_PORT_TX_AE_GRP_OFFSET, \
+					       _CNL_PORT_TX_B_GRP_OFFSET, \
+					       _CNL_PORT_TX_B_GRP_OFFSET, \
+					       _CNL_PORT_TX_D_GRP_OFFSET, \
+					       _CNL_PORT_TX_AE_GRP_OFFSET, \
+					       _CNL_PORT_TX_F_GRP_OFFSET) + \
+					       4*(dw))
+#define _CNL_PORT_TX_DW_LN0(port, dw)	(_PICK((port), \
+					       _CNL_PORT_TX_AE_LN0_OFFSET, \
+					       _CNL_PORT_TX_B_LN0_OFFSET, \
+					       _CNL_PORT_TX_B_LN0_OFFSET, \
+					       _CNL_PORT_TX_D_LN0_OFFSET, \
+					       _CNL_PORT_TX_AE_LN0_OFFSET, \
+					       _CNL_PORT_TX_F_LN0_OFFSET) + \
+					       4*(dw))
+
+#define CNL_PORT_TX_DW2_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP((port), 2))
+#define CNL_PORT_TX_DW2_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0((port), 2))
+#define _ICL_PORT_TX_DW2_GRP_A		0x162688
+#define _ICL_PORT_TX_DW2_GRP_B		0x6C688
+#define _ICL_PORT_TX_DW2_LN0_A		0x162888
+#define _ICL_PORT_TX_DW2_LN0_B		0x6C888
+#define ICL_PORT_TX_DW2_GRP(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW2_GRP_A, \
+						   _ICL_PORT_TX_DW2_GRP_B)
+#define ICL_PORT_TX_DW2_LN0(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW2_LN0_A, \
+						   _ICL_PORT_TX_DW2_LN0_B)
+#define   SWING_SEL_UPPER(x)		(((x) >> 3) << 15)
 #define   SWING_SEL_UPPER_MASK		(1 << 15)
-#define   SWING_SEL_LOWER(x)		((x & 0x7) << 11)
+#define   SWING_SEL_LOWER(x)		(((x) & 0x7) << 11)
 #define   SWING_SEL_LOWER_MASK		(0x7 << 11)
 #define   RCOMP_SCALAR(x)		((x) << 0)
 #define   RCOMP_SCALAR_MASK		(0xFF << 0)
 
-#define _CNL_PORT_TX_DW4_GRP_AE		0x162350
-#define _CNL_PORT_TX_DW4_GRP_B		0x1623D0
-#define _CNL_PORT_TX_DW4_GRP_C		0x162B50
-#define _CNL_PORT_TX_DW4_GRP_D		0x162BD0
-#define _CNL_PORT_TX_DW4_GRP_F		0x162A50
 #define _CNL_PORT_TX_DW4_LN0_AE		0x162450
 #define _CNL_PORT_TX_DW4_LN1_AE		0x1624D0
-#define _CNL_PORT_TX_DW4_LN0_B		0x162650
-#define _CNL_PORT_TX_DW4_LN0_C		0x162C50
-#define _CNL_PORT_TX_DW4_LN0_D		0x162E50
-#define _CNL_PORT_TX_DW4_LN0_F		0x162850
-#define CNL_PORT_TX_DW4_GRP(port)       _MMIO_PORT6(port, \
-						    _CNL_PORT_TX_DW4_GRP_AE, \
-						    _CNL_PORT_TX_DW4_GRP_B, \
-						    _CNL_PORT_TX_DW4_GRP_C, \
-						    _CNL_PORT_TX_DW4_GRP_D, \
-						    _CNL_PORT_TX_DW4_GRP_AE, \
-						    _CNL_PORT_TX_DW4_GRP_F)
-#define CNL_PORT_TX_DW4_LN(port, ln)       _MMIO_PORT6_LN(port, ln,	\
-						    _CNL_PORT_TX_DW4_LN0_AE, \
-						    _CNL_PORT_TX_DW4_LN1_AE, \
-						    _CNL_PORT_TX_DW4_LN0_B, \
-						    _CNL_PORT_TX_DW4_LN0_C, \
-						    _CNL_PORT_TX_DW4_LN0_D, \
-						    _CNL_PORT_TX_DW4_LN0_AE, \
-						    _CNL_PORT_TX_DW4_LN0_F)
+#define CNL_PORT_TX_DW4_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP((port), 4))
+#define CNL_PORT_TX_DW4_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0((port), 4))
+#define CNL_PORT_TX_DW4_LN(port, ln)   _MMIO(_CNL_PORT_TX_DW_LN0((port), 4) + \
+					     (ln * (_CNL_PORT_TX_DW4_LN1_AE - \
+						    _CNL_PORT_TX_DW4_LN0_AE)))
+#define _ICL_PORT_TX_DW4_GRP_A		0x162690
+#define _ICL_PORT_TX_DW4_GRP_B		0x6C690
+#define _ICL_PORT_TX_DW4_LN0_A		0x162890
+#define _ICL_PORT_TX_DW4_LN1_A		0x162990
+#define _ICL_PORT_TX_DW4_LN0_B		0x6C890
+#define ICL_PORT_TX_DW4_GRP(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW4_GRP_A, \
+						   _ICL_PORT_TX_DW4_GRP_B)
+#define ICL_PORT_TX_DW4_LN(port, ln)	_MMIO(_PORT(port, \
+						   _ICL_PORT_TX_DW4_LN0_A, \
+						   _ICL_PORT_TX_DW4_LN0_B) + \
+					      (ln * (_ICL_PORT_TX_DW4_LN1_A - \
+						     _ICL_PORT_TX_DW4_LN0_A)))
 #define   LOADGEN_SELECT		(1 << 31)
 #define   POST_CURSOR_1(x)		((x) << 12)
 #define   POST_CURSOR_1_MASK		(0x3F << 12)
@@ -2029,64 +1802,147 @@ enum i915_power_well_id {
 #define   CURSOR_COEFF(x)		((x) << 0)
 #define   CURSOR_COEFF_MASK		(0x3F << 0)
 
-#define _CNL_PORT_TX_DW5_GRP_AE		0x162354
-#define _CNL_PORT_TX_DW5_GRP_B		0x1623D4
-#define _CNL_PORT_TX_DW5_GRP_C		0x162B54
-#define _CNL_PORT_TX_DW5_GRP_D		0x162BD4
-#define _CNL_PORT_TX_DW5_GRP_F		0x162A54
-#define _CNL_PORT_TX_DW5_LN0_AE		0x162454
-#define _CNL_PORT_TX_DW5_LN0_B		0x162654
-#define _CNL_PORT_TX_DW5_LN0_C		0x162C54
-#define _CNL_PORT_TX_DW5_LN0_D		0x162E54
-#define _CNL_PORT_TX_DW5_LN0_F		0x162854
-#define CNL_PORT_TX_DW5_GRP(port)	_MMIO_PORT6(port, \
-						    _CNL_PORT_TX_DW5_GRP_AE, \
-						    _CNL_PORT_TX_DW5_GRP_B, \
-						    _CNL_PORT_TX_DW5_GRP_C, \
-						    _CNL_PORT_TX_DW5_GRP_D, \
-						    _CNL_PORT_TX_DW5_GRP_AE, \
-						    _CNL_PORT_TX_DW5_GRP_F)
-#define CNL_PORT_TX_DW5_LN0(port)	_MMIO_PORT6(port, \
-						    _CNL_PORT_TX_DW5_LN0_AE, \
-						    _CNL_PORT_TX_DW5_LN0_B, \
-						    _CNL_PORT_TX_DW5_LN0_C, \
-						    _CNL_PORT_TX_DW5_LN0_D, \
-						    _CNL_PORT_TX_DW5_LN0_AE, \
-						    _CNL_PORT_TX_DW5_LN0_F)
+#define CNL_PORT_TX_DW5_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP((port), 5))
+#define CNL_PORT_TX_DW5_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0((port), 5))
+#define _ICL_PORT_TX_DW5_GRP_A		0x162694
+#define _ICL_PORT_TX_DW5_GRP_B		0x6C694
+#define _ICL_PORT_TX_DW5_LN0_A		0x162894
+#define _ICL_PORT_TX_DW5_LN0_B		0x6C894
+#define ICL_PORT_TX_DW5_GRP(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW5_GRP_A, \
+						   _ICL_PORT_TX_DW5_GRP_B)
+#define ICL_PORT_TX_DW5_LN0(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW5_LN0_A, \
+						   _ICL_PORT_TX_DW5_LN0_B)
 #define   TX_TRAINING_EN		(1 << 31)
+#define   TAP2_DISABLE			(1 << 30)
 #define   TAP3_DISABLE			(1 << 29)
 #define   SCALING_MODE_SEL(x)		((x) << 18)
 #define   SCALING_MODE_SEL_MASK		(0x7 << 18)
 #define   RTERM_SELECT(x)		((x) << 3)
 #define   RTERM_SELECT_MASK		(0x7 << 3)
 
-#define _CNL_PORT_TX_DW7_GRP_AE		0x16235C
-#define _CNL_PORT_TX_DW7_GRP_B		0x1623DC
-#define _CNL_PORT_TX_DW7_GRP_C		0x162B5C
-#define _CNL_PORT_TX_DW7_GRP_D		0x162BDC
-#define _CNL_PORT_TX_DW7_GRP_F		0x162A5C
-#define _CNL_PORT_TX_DW7_LN0_AE		0x16245C
-#define _CNL_PORT_TX_DW7_LN0_B		0x16265C
-#define _CNL_PORT_TX_DW7_LN0_C		0x162C5C
-#define _CNL_PORT_TX_DW7_LN0_D		0x162E5C
-#define _CNL_PORT_TX_DW7_LN0_F		0x16285C
-#define CNL_PORT_TX_DW7_GRP(port)	_MMIO_PORT6(port, \
-						    _CNL_PORT_TX_DW7_GRP_AE, \
-						    _CNL_PORT_TX_DW7_GRP_B, \
-						    _CNL_PORT_TX_DW7_GRP_C, \
-						    _CNL_PORT_TX_DW7_GRP_D, \
-						    _CNL_PORT_TX_DW7_GRP_AE, \
-						    _CNL_PORT_TX_DW7_GRP_F)
-#define CNL_PORT_TX_DW7_LN0(port)	_MMIO_PORT6(port, \
-						    _CNL_PORT_TX_DW7_LN0_AE, \
-						    _CNL_PORT_TX_DW7_LN0_B, \
-						    _CNL_PORT_TX_DW7_LN0_C, \
-						    _CNL_PORT_TX_DW7_LN0_D, \
-						    _CNL_PORT_TX_DW7_LN0_AE, \
-						    _CNL_PORT_TX_DW7_LN0_F)
+#define CNL_PORT_TX_DW7_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP((port), 7))
+#define CNL_PORT_TX_DW7_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0((port), 7))
 #define   N_SCALAR(x)			((x) << 24)
 #define   N_SCALAR_MASK			(0x7F << 24)
 
+#define _ICL_MG_PHY_PORT_LN(port, ln, ln0p1, ln0p2, ln1p1) \
+	_MMIO(_PORT((port) - PORT_C, ln0p1, ln0p2) + (ln) * ((ln1p1) - (ln0p1)))
+
+#define _ICL_MG_TX_LINK_PARAMS_TX1LN0_PORT1		0x16812C
+#define _ICL_MG_TX_LINK_PARAMS_TX1LN1_PORT1		0x16852C
+#define _ICL_MG_TX_LINK_PARAMS_TX1LN0_PORT2		0x16912C
+#define _ICL_MG_TX_LINK_PARAMS_TX1LN1_PORT2		0x16952C
+#define _ICL_MG_TX_LINK_PARAMS_TX1LN0_PORT3		0x16A12C
+#define _ICL_MG_TX_LINK_PARAMS_TX1LN1_PORT3		0x16A52C
+#define _ICL_MG_TX_LINK_PARAMS_TX1LN0_PORT4		0x16B12C
+#define _ICL_MG_TX_LINK_PARAMS_TX1LN1_PORT4		0x16B52C
+#define ICL_PORT_MG_TX1_LINK_PARAMS(port, ln) \
+	_ICL_MG_PHY_PORT_LN(port, ln, _ICL_MG_TX_LINK_PARAMS_TX1LN0_PORT1, \
+				      _ICL_MG_TX_LINK_PARAMS_TX1LN0_PORT2, \
+				      _ICL_MG_TX_LINK_PARAMS_TX1LN1_PORT1)
+
+#define _ICL_MG_TX_LINK_PARAMS_TX2LN0_PORT1		0x1680AC
+#define _ICL_MG_TX_LINK_PARAMS_TX2LN1_PORT1		0x1684AC
+#define _ICL_MG_TX_LINK_PARAMS_TX2LN0_PORT2		0x1690AC
+#define _ICL_MG_TX_LINK_PARAMS_TX2LN1_PORT2		0x1694AC
+#define _ICL_MG_TX_LINK_PARAMS_TX2LN0_PORT3		0x16A0AC
+#define _ICL_MG_TX_LINK_PARAMS_TX2LN1_PORT3		0x16A4AC
+#define _ICL_MG_TX_LINK_PARAMS_TX2LN0_PORT4		0x16B0AC
+#define _ICL_MG_TX_LINK_PARAMS_TX2LN1_PORT4		0x16B4AC
+#define ICL_PORT_MG_TX2_LINK_PARAMS(port, ln) \
+	_ICL_MG_PHY_PORT_LN(port, ln, _ICL_MG_TX_LINK_PARAMS_TX2LN0_PORT1, \
+				      _ICL_MG_TX_LINK_PARAMS_TX2LN0_PORT2, \
+				      _ICL_MG_TX_LINK_PARAMS_TX2LN1_PORT1)
+#define CRI_USE_FS32			(1 << 5)
+
+#define _ICL_MG_TX_PISO_READLOAD_TX1LN0_PORT1		0x16814C
+#define _ICL_MG_TX_PISO_READLOAD_TX1LN1_PORT1		0x16854C
+#define _ICL_MG_TX_PISO_READLOAD_TX1LN0_PORT2		0x16914C
+#define _ICL_MG_TX_PISO_READLOAD_TX1LN1_PORT2		0x16954C
+#define _ICL_MG_TX_PISO_READLOAD_TX1LN0_PORT3		0x16A14C
+#define _ICL_MG_TX_PISO_READLOAD_TX1LN1_PORT3		0x16A54C
+#define _ICL_MG_TX_PISO_READLOAD_TX1LN0_PORT4		0x16B14C
+#define _ICL_MG_TX_PISO_READLOAD_TX1LN1_PORT4		0x16B54C
+#define ICL_PORT_MG_TX1_PISO_READLOAD(port, ln) \
+	_ICL_MG_PHY_PORT_LN(port, ln, _ICL_MG_TX_PISO_READLOAD_TX1LN0_PORT1, \
+				      _ICL_MG_TX_PISO_READLOAD_TX1LN0_PORT2, \
+				      _ICL_MG_TX_PISO_READLOAD_TX1LN1_PORT1)
+
+#define _ICL_MG_TX_PISO_READLOAD_TX2LN0_PORT1		0x1680CC
+#define _ICL_MG_TX_PISO_READLOAD_TX2LN1_PORT1		0x1684CC
+#define _ICL_MG_TX_PISO_READLOAD_TX2LN0_PORT2		0x1690CC
+#define _ICL_MG_TX_PISO_READLOAD_TX2LN1_PORT2		0x1694CC
+#define _ICL_MG_TX_PISO_READLOAD_TX2LN0_PORT3		0x16A0CC
+#define _ICL_MG_TX_PISO_READLOAD_TX2LN1_PORT3		0x16A4CC
+#define _ICL_MG_TX_PISO_READLOAD_TX2LN0_PORT4		0x16B0CC
+#define _ICL_MG_TX_PISO_READLOAD_TX2LN1_PORT4		0x16B4CC
+#define ICL_PORT_MG_TX2_PISO_READLOAD(port, ln) \
+	_ICL_MG_PHY_PORT_LN(port, ln, _ICL_MG_TX_PISO_READLOAD_TX2LN0_PORT1, \
+				      _ICL_MG_TX_PISO_READLOAD_TX2LN0_PORT2, \
+				      _ICL_MG_TX_PISO_READLOAD_TX2LN1_PORT1)
+#define CRI_CALCINIT					(1 << 1)
+
+#define _ICL_MG_TX_SWINGCTRL_TX1LN0_PORT1		0x168148
+#define _ICL_MG_TX_SWINGCTRL_TX1LN1_PORT1		0x168548
+#define _ICL_MG_TX_SWINGCTRL_TX1LN0_PORT2		0x169148
+#define _ICL_MG_TX_SWINGCTRL_TX1LN1_PORT2		0x169548
+#define _ICL_MG_TX_SWINGCTRL_TX1LN0_PORT3		0x16A148
+#define _ICL_MG_TX_SWINGCTRL_TX1LN1_PORT3		0x16A548
+#define _ICL_MG_TX_SWINGCTRL_TX1LN0_PORT4		0x16B148
+#define _ICL_MG_TX_SWINGCTRL_TX1LN1_PORT4		0x16B548
+#define ICL_PORT_MG_TX1_SWINGCTRL(port, ln) \
+	_ICL_MG_PHY_PORT_LN(port, ln, _ICL_MG_TX_SWINGCTRL_TX1LN0_PORT1, \
+				      _ICL_MG_TX_SWINGCTRL_TX1LN0_PORT2, \
+				      _ICL_MG_TX_SWINGCTRL_TX1LN1_PORT1)
+
+#define _ICL_MG_TX_SWINGCTRL_TX2LN0_PORT1		0x1680C8
+#define _ICL_MG_TX_SWINGCTRL_TX2LN1_PORT1		0x1684C8
+#define _ICL_MG_TX_SWINGCTRL_TX2LN0_PORT2		0x1690C8
+#define _ICL_MG_TX_SWINGCTRL_TX2LN1_PORT2		0x1694C8
+#define _ICL_MG_TX_SWINGCTRL_TX2LN0_PORT3		0x16A0C8
+#define _ICL_MG_TX_SWINGCTRL_TX2LN1_PORT3		0x16A4C8
+#define _ICL_MG_TX_SWINGCTRL_TX2LN0_PORT4		0x16B0C8
+#define _ICL_MG_TX_SWINGCTRL_TX2LN1_PORT4		0x16B4C8
+#define ICL_PORT_MG_TX2_SWINGCTRL(port, ln) \
+	_ICL_MG_PHY_PORT_LN(port, ln, _ICL_MG_TX_SWINGCTRL_TX2LN0_PORT1, \
+				      _ICL_MG_TX_SWINGCTRL_TX2LN0_PORT2, \
+				      _ICL_MG_TX_SWINGCTRL_TX2LN1_PORT1)
+#define CRI_TXDEEMPH_OVERRIDE_17_12(x)			((x) << 0)
+#define CRI_TXDEEMPH_OVERRIDE_17_12_MASK		(0x3F << 0)
+
+#define _ICL_MG_TX_DRVCTRL_TX1LN0_PORT1			0x168144
+#define _ICL_MG_TX_DRVCTRL_TX1LN1_PORT1			0x168544
+#define _ICL_MG_TX_DRVCTRL_TX1LN0_PORT2			0x169144
+#define _ICL_MG_TX_DRVCTRL_TX1LN1_PORT2			0x169544
+#define _ICL_MG_TX_DRVCTRL_TX1LN0_PORT3			0x16A144
+#define _ICL_MG_TX_DRVCTRL_TX1LN1_PORT3			0x16A544
+#define _ICL_MG_TX_DRVCTRL_TX1LN0_PORT4			0x16B144
+#define _ICL_MG_TX_DRVCTRL_TX1LN1_PORT4			0x16B544
+#define ICL_PORT_MG_TX1_DRVCTRL(port, ln) \
+	_ICL_MG_PHY_PORT_LN(port, ln, _ICL_MG_TX_DRVCTRL_TX1LN0_PORT1, \
+				      _ICL_MG_TX_DRVCTRL_TX1LN0_PORT2, \
+				      _ICL_MG_TX_DRVCTRL_TX1LN1_PORT1)
+
+#define _ICL_MG_TX_DRVCTRL_TX2LN0_PORT1			0x1680C4
+#define _ICL_MG_TX_DRVCTRL_TX2LN1_PORT1			0x1684C4
+#define _ICL_MG_TX_DRVCTRL_TX2LN0_PORT2			0x1690C4
+#define _ICL_MG_TX_DRVCTRL_TX2LN1_PORT2			0x1694C4
+#define _ICL_MG_TX_DRVCTRL_TX2LN0_PORT3			0x16A0C4
+#define _ICL_MG_TX_DRVCTRL_TX2LN1_PORT3			0x16A4C4
+#define _ICL_MG_TX_DRVCTRL_TX2LN0_PORT4			0x16B0C4
+#define _ICL_MG_TX_DRVCTRL_TX2LN1_PORT4			0x16B4C4
+#define ICL_PORT_MG_TX2_DRVCTRL(port, ln) \
+	_ICL_MG_PHY_PORT_LN(port, ln, _ICL_MG_TX_DRVCTRL_TX2LN0_PORT1, \
+				      _ICL_MG_TX_DRVCTRL_TX2LN0_PORT2, \
+				      _ICL_MG_TX_DRVCTRL_TX2LN1_PORT1)
+#define CRI_TXDEEMPH_OVERRIDE_11_6(x)			((x) << 24)
+#define CRI_TXDEEMPH_OVERRIDE_11_6_MASK			(0x3F << 24)
+#define CRI_TXDEEMPH_OVERRIDE_EN			(1 << 22)
+#define CRI_TXDEEMPH_OVERRIDE_5_0(x)			((x) << 16)
+#define CRI_TXDEEMPH_OVERRIDE_5_0_MASK			(0x3F << 16)
+
 /* The spec defines this only for BXT PHY0, but lets assume that this
  * would exist for PHY1 too if it had a second channel.
  */
@@ -2473,6 +2329,10 @@ enum i915_power_well_id {
 #define   GEN8_MCR_SLICE_MASK		GEN8_MCR_SLICE(3)
 #define   GEN8_MCR_SUBSLICE(subslice)	(((subslice) & 3) << 24)
 #define   GEN8_MCR_SUBSLICE_MASK	GEN8_MCR_SUBSLICE(3)
+#define   GEN11_MCR_SLICE(slice)	(((slice) & 0xf) << 27)
+#define   GEN11_MCR_SLICE_MASK		GEN11_MCR_SLICE(0xf)
+#define   GEN11_MCR_SUBSLICE(subslice)	(((subslice) & 0x7) << 24)
+#define   GEN11_MCR_SUBSLICE_MASK	GEN11_MCR_SUBSLICE(0x7)
 #define RING_IPEIR(base)	_MMIO((base)+0x64)
 #define RING_IPEHR(base)	_MMIO((base)+0x68)
 /*
@@ -2867,6 +2727,19 @@ enum i915_power_well_id {
 #define GEN10_EU_DISABLE3		_MMIO(0x9140)
 #define   GEN10_EU_DIS_SS_MASK		0xff
 
+#define GEN11_GT_VEBOX_VDBOX_DISABLE	_MMIO(0x9140)
+#define   GEN11_GT_VDBOX_DISABLE_MASK	0xff
+#define   GEN11_GT_VEBOX_DISABLE_SHIFT	16
+#define   GEN11_GT_VEBOX_DISABLE_MASK	(0xff << GEN11_GT_VEBOX_DISABLE_SHIFT)
+
+#define GEN11_EU_DISABLE _MMIO(0x9134)
+#define GEN11_EU_DIS_MASK 0xFF
+
+#define GEN11_GT_SLICE_ENABLE _MMIO(0x9138)
+#define GEN11_GT_S_ENA_MASK 0xFF
+
+#define GEN11_GT_SUBSLICE_DISABLE _MMIO(0x913C)
+
 #define GEN6_BSD_SLEEP_PSMI_CONTROL	_MMIO(0x12050)
 #define   GEN6_BSD_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN6_BSD_SLEEP_FLUSH_DISABLE	(1 << 2)
@@ -3951,6 +3824,9 @@ enum {
 #define _CLKGATE_DIS_PSL_A		0x46520
 #define _CLKGATE_DIS_PSL_B		0x46524
 #define _CLKGATE_DIS_PSL_C		0x46528
+#define   DUPS1_GATING_DIS		(1 << 15)
+#define   DUPS2_GATING_DIS		(1 << 19)
+#define   DUPS3_GATING_DIS		(1 << 23)
 #define   DPF_GATING_DIS		(1 << 10)
 #define   DPF_RAM_GATING_DIS		(1 << 9)
 #define   DPFR_GATING_DIS		(1 << 8)
@@ -3964,6 +3840,7 @@ enum {
 #define SLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x94d4)
 #define  SARBUNIT_CLKGATE_DIS		(1 << 5)
 #define  RCCUNIT_CLKGATE_DIS		(1 << 7)
+#define  MSCUNIT_CLKGATE_DIS		(1 << 10)
 
 #define SUBSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9524)
 #define  GWUNIT_CLKGATE_DIS		(1 << 16)
@@ -3971,6 +3848,9 @@ enum {
 #define UNSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9434)
 #define  VFUNIT_CLKGATE_DIS		(1 << 20)
 
+#define INF_UNIT_LEVEL_CLKGATE		_MMIO(0x9560)
+#define   CGPSF_CLKGATE_DIS		(1 << 3)
+
 /*
  * Display engine regs
  */
@@ -4150,7 +4030,20 @@ enum {
 #define   EDP_PSR_TP1_TIME_0us			(3<<4)
 #define   EDP_PSR_IDLE_FRAME_SHIFT		0
 
+/* Bspec claims those aren't shifted but stay at 0x64800 */
+#define EDP_PSR_IMR				_MMIO(0x64834)
+#define EDP_PSR_IIR				_MMIO(0x64838)
+#define   EDP_PSR_ERROR(trans)			(1 << (((trans) * 8 + 10) & 31))
+#define   EDP_PSR_POST_EXIT(trans)		(1 << (((trans) * 8 + 9) & 31))
+#define   EDP_PSR_PRE_ENTRY(trans)		(1 << (((trans) * 8 + 8) & 31))
+
 #define EDP_PSR_AUX_CTL				_MMIO(dev_priv->psr_mmio_base + 0x10)
+#define   EDP_PSR_AUX_CTL_TIME_OUT_MASK		(3 << 26)
+#define   EDP_PSR_AUX_CTL_MESSAGE_SIZE_MASK	(0x1f << 20)
+#define   EDP_PSR_AUX_CTL_PRECHARGE_2US_MASK	(0xf << 16)
+#define   EDP_PSR_AUX_CTL_ERROR_INTERRUPT	(1 << 11)
+#define   EDP_PSR_AUX_CTL_BIT_CLOCK_2X_MASK	(0x7ff)
+
 #define EDP_PSR_AUX_DATA(i)			_MMIO(dev_priv->psr_mmio_base + 0x14 + (i) * 4) /* 5 registers */
 
 #define EDP_PSR_STATUS				_MMIO(dev_priv->psr_mmio_base + 0x40)
@@ -4180,17 +4073,19 @@ enum {
 #define EDP_PSR_PERF_CNT		_MMIO(dev_priv->psr_mmio_base + 0x44)
 #define   EDP_PSR_PERF_CNT_MASK		0xffffff
 
-#define EDP_PSR_DEBUG				_MMIO(dev_priv->psr_mmio_base + 0x60)
+#define EDP_PSR_DEBUG				_MMIO(dev_priv->psr_mmio_base + 0x60) /* PSR_MASK on SKL+ */
 #define   EDP_PSR_DEBUG_MASK_MAX_SLEEP         (1<<28)
 #define   EDP_PSR_DEBUG_MASK_LPSP              (1<<27)
 #define   EDP_PSR_DEBUG_MASK_MEMUP             (1<<26)
 #define   EDP_PSR_DEBUG_MASK_HPD               (1<<25)
 #define   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE    (1<<16)
-#define   EDP_PSR_DEBUG_EXIT_ON_PIXEL_UNDERRUN (1<<15)
+#define   EDP_PSR_DEBUG_EXIT_ON_PIXEL_UNDERRUN (1<<15) /* SKL+ */
 
 #define EDP_PSR2_CTL			_MMIO(0x6f900)
 #define   EDP_PSR2_ENABLE		(1<<31)
 #define   EDP_SU_TRACK_ENABLE		(1<<30)
+#define   EDP_Y_COORDINATE_VALID	(1<<26) /* GLK and CNL+ */
+#define   EDP_Y_COORDINATE_ENABLE	(1<<25) /* GLK and CNL+ */
 #define   EDP_MAX_SU_DISABLE_TIME(t)	((t)<<20)
 #define   EDP_MAX_SU_DISABLE_TIME_MASK	(0x1f<<20)
 #define   EDP_PSR2_TP2_TIME_500		(0<<8)
@@ -4200,8 +4095,32 @@ enum {
 #define   EDP_PSR2_TP2_TIME_MASK	(3<<8)
 #define   EDP_PSR2_FRAME_BEFORE_SU_SHIFT 4
 #define   EDP_PSR2_FRAME_BEFORE_SU_MASK	(0xf<<4)
-#define   EDP_PSR2_IDLE_MASK		0xf
 #define   EDP_PSR2_FRAME_BEFORE_SU(a)	((a)<<4)
+#define   EDP_PSR2_IDLE_FRAME_MASK	0xf
+#define   EDP_PSR2_IDLE_FRAME_SHIFT	0
+
+#define _PSR_EVENT_TRANS_A			0x60848
+#define _PSR_EVENT_TRANS_B			0x61848
+#define _PSR_EVENT_TRANS_C			0x62848
+#define _PSR_EVENT_TRANS_D			0x63848
+#define _PSR_EVENT_TRANS_EDP			0x6F848
+#define PSR_EVENT(trans)			_MMIO_TRANS2(trans, _PSR_EVENT_TRANS_A)
+#define  PSR_EVENT_PSR2_WD_TIMER_EXPIRE		(1 << 17)
+#define  PSR_EVENT_PSR2_DISABLED		(1 << 16)
+#define  PSR_EVENT_SU_DIRTY_FIFO_UNDERRUN	(1 << 15)
+#define  PSR_EVENT_SU_CRC_FIFO_UNDERRUN		(1 << 14)
+#define  PSR_EVENT_GRAPHICS_RESET		(1 << 12)
+#define  PSR_EVENT_PCH_INTERRUPT		(1 << 11)
+#define  PSR_EVENT_MEMORY_UP			(1 << 10)
+#define  PSR_EVENT_FRONT_BUFFER_MODIFY		(1 << 9)
+#define  PSR_EVENT_WD_TIMER_EXPIRE		(1 << 8)
+#define  PSR_EVENT_PIPE_REGISTERS_UPDATE	(1 << 6)
+#define  PSR_EVENT_REGISTER_UPDATE		(1 << 5)
+#define  PSR_EVENT_HDCP_ENABLE			(1 << 4)
+#define  PSR_EVENT_KVMR_SESSION_ENABLE		(1 << 3)
+#define  PSR_EVENT_VBI_ENABLE			(1 << 2)
+#define  PSR_EVENT_LPSP_MODE_EXIT		(1 << 1)
+#define  PSR_EVENT_PSR_DISABLE			(1 << 0)
 
 #define EDP_PSR2_STATUS			_MMIO(0x6f940)
 #define EDP_PSR2_STATUS_STATE_MASK     (0xf<<28)
@@ -5265,8 +5184,6 @@ enum {
 #define   DP_LINK_TRAIN_OFF		(3 << 28)
 #define   DP_LINK_TRAIN_MASK		(3 << 28)
 #define   DP_LINK_TRAIN_SHIFT		28
-#define   DP_LINK_TRAIN_PAT_3_CHV	(1 << 14)
-#define   DP_LINK_TRAIN_MASK_CHV	((3 << 28)|(1<<14))
 
 /* CPT Link training mode */
 #define   DP_LINK_TRAIN_PAT_1_CPT	(0 << 8)
@@ -6009,6 +5926,7 @@ enum {
 #define CURSIZE			_MMIO(0x700a0) /* 845/865 */
 #define _CUR_FBC_CTL_A		0x700a0 /* ivb+ */
 #define   CUR_FBC_CTL_EN	(1 << 31)
+#define _CURASURFLIVE		0x700ac /* g4x+ */
 #define _CURBCNTR		0x700c0
 #define _CURBBASE		0x700c4
 #define _CURBPOS		0x700c8
@@ -6025,6 +5943,7 @@ enum {
 #define CURBASE(pipe) _CURSOR2(pipe, _CURABASE)
 #define CURPOS(pipe) _CURSOR2(pipe, _CURAPOS)
 #define CUR_FBC_CTL(pipe) _CURSOR2(pipe, _CUR_FBC_CTL_A)
+#define CURSURFLIVE(pipe) _CURSOR2(pipe, _CURASURFLIVE)
 
 #define CURSOR_A_OFFSET 0x70080
 #define CURSOR_B_OFFSET 0x700c0
@@ -6492,9 +6411,9 @@ enum {
 #define _PLANE_COLOR_CTL_1_A			0x701CC /* GLK+ */
 #define _PLANE_COLOR_CTL_2_A			0x702CC /* GLK+ */
 #define _PLANE_COLOR_CTL_3_A			0x703CC /* GLK+ */
-#define   PLANE_COLOR_PIPE_GAMMA_ENABLE		(1 << 30)
+#define   PLANE_COLOR_PIPE_GAMMA_ENABLE		(1 << 30) /* Pre-ICL */
 #define   PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE	(1 << 28)
-#define   PLANE_COLOR_PIPE_CSC_ENABLE		(1 << 23)
+#define   PLANE_COLOR_PIPE_CSC_ENABLE		(1 << 23) /* Pre-ICL */
 #define   PLANE_COLOR_CSC_MODE_BYPASS			(0 << 17)
 #define   PLANE_COLOR_CSC_MODE_YUV601_TO_RGB709		(1 << 17)
 #define   PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709		(2 << 17)
@@ -6589,6 +6508,9 @@ enum {
 
 #define _PLANE_BUF_CFG_1_B			0x7127c
 #define _PLANE_BUF_CFG_2_B			0x7137c
+#define  SKL_DDB_ENTRY_MASK			0x3FF
+#define  ICL_DDB_ENTRY_MASK			0x7FF
+#define  DDB_ENTRY_END_SHIFT			16
 #define _PLANE_BUF_CFG_1(pipe)	\
 	_PIPE(pipe, _PLANE_BUF_CFG_1_A, _PLANE_BUF_CFG_1_B)
 #define _PLANE_BUF_CFG_2(pipe)	\
@@ -6779,6 +6701,8 @@ enum {
 #define PS_SCALER_MODE_MASK (3 << 28)
 #define PS_SCALER_MODE_DYN  (0 << 28)
 #define PS_SCALER_MODE_HQ  (1 << 28)
+#define SKL_PS_SCALER_MODE_NV12 (2 << 28)
+#define PS_SCALER_MODE_PLANAR (1 << 29)
 #define PS_PLANE_SEL_MASK  (7 << 25)
 #define PS_PLANE_SEL(plane) (((plane) + 1) << 25)
 #define PS_FILTER_MASK         (3 << 23)
@@ -6950,6 +6874,7 @@ enum {
 #define DE_PCH_EVENT_IVB		(1<<28)
 #define DE_DP_A_HOTPLUG_IVB		(1<<27)
 #define DE_AUX_CHANNEL_A_IVB		(1<<26)
+#define DE_EDP_PSR_INT_HSW		(1<<19)
 #define DE_SPRITEC_FLIP_DONE_IVB	(1<<14)
 #define DE_PLANEC_FLIP_DONE_IVB		(1<<13)
 #define DE_PIPEC_VBLANK_IVB		(1<<10)
@@ -7074,6 +6999,7 @@ enum {
 #define GEN8_DE_MISC_IIR _MMIO(0x44468)
 #define GEN8_DE_MISC_IER _MMIO(0x4446c)
 #define  GEN8_DE_MISC_GSE		(1 << 27)
+#define  GEN8_DE_EDP_PSR		(1 << 19)
 
 #define GEN8_PCU_ISR _MMIO(0x444e0)
 #define GEN8_PCU_IMR _MMIO(0x444e4)
@@ -7117,7 +7043,9 @@ enum {
 #define GEN11_INTR_IDENTITY_REG0	_MMIO(0x190060)
 #define GEN11_INTR_IDENTITY_REG1	_MMIO(0x190064)
 #define  GEN11_INTR_DATA_VALID		(1 << 31)
-#define  GEN11_INTR_ENGINE_MASK		(0xffff)
+#define  GEN11_INTR_ENGINE_CLASS(x)	(((x) & GENMASK(18, 16)) >> 16)
+#define  GEN11_INTR_ENGINE_INSTANCE(x)	(((x) & GENMASK(25, 20)) >> 20)
+#define  GEN11_INTR_ENGINE_INTR(x)	((x) & 0xffff)
 
 #define GEN11_INTR_IDENTITY_REG(x)	_MMIO(0x190060 + (x * 4))
 
@@ -7197,6 +7125,7 @@ enum {
 #define CHICKEN_TRANS_A         0x420c0
 #define CHICKEN_TRANS_B         0x420c4
 #define CHICKEN_TRANS(trans) _MMIO_TRANS(trans, CHICKEN_TRANS_A, CHICKEN_TRANS_B)
+#define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1<<25) /* GLK and CNL+ */
 #define  DDI_TRAINING_OVERRIDE_ENABLE	(1<<19)
 #define  DDI_TRAINING_OVERRIDE_VALUE	(1<<18)
 #define  DDIE_TRAINING_OVERRIDE_ENABLE	(1<<17) /* CHICKEN_TRANS_A only */
@@ -7301,18 +7230,22 @@ enum {
 #define GEN7_L3CNTLREG3				_MMIO(0xB024)
 
 #define GEN7_L3_CHICKEN_MODE_REGISTER		_MMIO(0xB030)
-#define  GEN7_WA_L3_CHICKEN_MODE				0x20000000
+#define   GEN7_WA_L3_CHICKEN_MODE		0x20000000
+#define GEN10_L3_CHICKEN_MODE_REGISTER		_MMIO(0xB114)
+#define   GEN11_I2M_WRITE_DISABLE		(1 << 28)
 
 #define GEN7_L3SQCREG4				_MMIO(0xb034)
 #define  L3SQ_URB_READ_CAM_MATCH_DISABLE	(1<<27)
 
 #define GEN8_L3SQCREG4				_MMIO(0xb118)
-#define  GEN8_LQSC_RO_PERF_DIS			(1<<27)
-#define  GEN8_LQSC_FLUSH_COHERENT_LINES		(1<<21)
+#define  GEN11_LQSC_CLEAN_EVICT_DISABLE		(1 << 6)
+#define  GEN8_LQSC_RO_PERF_DIS			(1 << 27)
+#define  GEN8_LQSC_FLUSH_COHERENT_LINES		(1 << 21)
 
 /* GEN8 chicken */
 #define HDC_CHICKEN0				_MMIO(0x7300)
 #define CNL_HDC_CHICKEN0			_MMIO(0xE5F0)
+#define ICL_HDC_MODE				_MMIO(0xE5F4)
 #define  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE	(1<<15)
 #define  HDC_FENCE_DEST_SLM_DISABLE		(1<<14)
 #define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1<<11)
@@ -7326,6 +7259,9 @@ enum {
 #define SLICE_ECO_CHICKEN0			_MMIO(0x7308)
 #define   PIXEL_MASK_CAMMING_DISABLE		(1 << 14)
 
+#define GEN9_WM_CHICKEN3			_MMIO(0x5588)
+#define   GEN9_FACTOR_IN_CLR_VAL_HIZ		(1 << 9)
+
 /* WaCatErrorRejectionIssue */
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		_MMIO(0x9030)
 #define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
@@ -8324,8 +8260,30 @@ enum {
 #define   GEN8_DOP_CLOCK_GATE_GUC_ENABLE	(1<<4)
 #define   GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE     (1<<6)
 
-#define GEN8_GARBCNTL                   _MMIO(0xB004)
-#define   GEN9_GAPS_TSV_CREDIT_DISABLE  (1<<7)
+#define GEN8_GARBCNTL				_MMIO(0xB004)
+#define   GEN9_GAPS_TSV_CREDIT_DISABLE		(1 << 7)
+#define   GEN11_ARBITRATION_PRIO_ORDER_MASK	(0x3f << 22)
+#define   GEN11_HASH_CTRL_EXCL_MASK		(0x7f << 0)
+#define   GEN11_HASH_CTRL_EXCL_BIT0		(1 << 0)
+
+#define GEN11_GLBLINVL				_MMIO(0xB404)
+#define   GEN11_BANK_HASH_ADDR_EXCL_MASK	(0x7f << 5)
+#define   GEN11_BANK_HASH_ADDR_EXCL_BIT0	(1 << 5)
+
+#define GEN10_DFR_RATIO_EN_AND_CHICKEN	_MMIO(0x9550)
+#define   DFR_DISABLE			(1 << 9)
+
+#define GEN11_GACB_PERF_CTRL			_MMIO(0x4B80)
+#define   GEN11_HASH_CTRL_MASK			(0x3 << 12 | 0xf << 0)
+#define   GEN11_HASH_CTRL_BIT0			(1 << 0)
+#define   GEN11_HASH_CTRL_BIT4			(1 << 12)
+
+#define GEN11_LSN_UNSLCVC				_MMIO(0xB43C)
+#define   GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC	(1 << 9)
+#define   GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC	(1 << 7)
+
+#define GAMW_ECO_DEV_RW_IA_REG			_MMIO(0x4080)
+#define   GAMW_ECO_DEV_CTX_RELOAD_DISABLE	(1 << 7)
 
 /* IVYBRIDGE DPF */
 #define GEN7_L3CDERRST1(slice)		_MMIO(0xB008 + (slice) * 0x200) /* L3CD Error Status 1 */
@@ -8834,6 +8792,12 @@ enum skl_power_gate {
 #define  PORT_CLK_SEL_NONE		(7<<29)
 #define  PORT_CLK_SEL_MASK		(7<<29)
 
+/* On ICL+ this is the same as PORT_CLK_SEL, but all bits change. */
+#define DDI_CLK_SEL(port)		PORT_CLK_SEL(port)
+#define  DDI_CLK_SEL_NONE		(0x0 << 28)
+#define  DDI_CLK_SEL_MG			(0x8 << 28)
+#define  DDI_CLK_SEL_MASK		(0xF << 28)
+
 /* Transcoder clock selection */
 #define _TRANS_CLK_SEL_A		0x46140
 #define _TRANS_CLK_SEL_B		0x46144
@@ -8964,6 +8928,7 @@ enum skl_power_gate {
  * CNL Clocks
  */
 #define DPCLKA_CFGCR0				_MMIO(0x6C200)
+#define DPCLKA_CFGCR0_ICL			_MMIO(0x164280)
 #define  DPCLKA_CFGCR0_DDI_CLK_OFF(port)	(1 << ((port) ==  PORT_F ? 23 : \
 						      (port)+10))
 #define  DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port)	((port) == PORT_F ? 21 : \
@@ -8980,10 +8945,141 @@ enum skl_power_gate {
 #define  PLL_POWER_STATE	(1 << 26)
 #define CNL_DPLL_ENABLE(pll)	_MMIO_PLL(pll, DPLL0_ENABLE, DPLL1_ENABLE)
 
+#define _MG_PLL1_ENABLE		0x46030
+#define _MG_PLL2_ENABLE		0x46034
+#define _MG_PLL3_ENABLE		0x46038
+#define _MG_PLL4_ENABLE		0x4603C
+/* Bits are the same as DPLL0_ENABLE */
+#define MG_PLL_ENABLE(port)	_MMIO_PORT((port) - PORT_C, _MG_PLL1_ENABLE, \
+					   _MG_PLL2_ENABLE)
+
+#define _MG_REFCLKIN_CTL_PORT1				0x16892C
+#define _MG_REFCLKIN_CTL_PORT2				0x16992C
+#define _MG_REFCLKIN_CTL_PORT3				0x16A92C
+#define _MG_REFCLKIN_CTL_PORT4				0x16B92C
+#define   MG_REFCLKIN_CTL_OD_2_MUX(x)			((x) << 8)
+#define MG_REFCLKIN_CTL(port) _MMIO_PORT((port) - PORT_C, \
+					 _MG_REFCLKIN_CTL_PORT1, \
+					 _MG_REFCLKIN_CTL_PORT2)
+
+#define _MG_CLKTOP2_CORECLKCTL1_PORT1			0x1688D8
+#define _MG_CLKTOP2_CORECLKCTL1_PORT2			0x1698D8
+#define _MG_CLKTOP2_CORECLKCTL1_PORT3			0x16A8D8
+#define _MG_CLKTOP2_CORECLKCTL1_PORT4			0x16B8D8
+#define   MG_CLKTOP2_CORECLKCTL1_B_DIVRATIO(x)		((x) << 16)
+#define   MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO(x)		((x) << 8)
+#define MG_CLKTOP2_CORECLKCTL1(port) _MMIO_PORT((port) - PORT_C, \
+						_MG_CLKTOP2_CORECLKCTL1_PORT1, \
+						_MG_CLKTOP2_CORECLKCTL1_PORT2)
+
+#define _MG_CLKTOP2_HSCLKCTL_PORT1			0x1688D4
+#define _MG_CLKTOP2_HSCLKCTL_PORT2			0x1698D4
+#define _MG_CLKTOP2_HSCLKCTL_PORT3			0x16A8D4
+#define _MG_CLKTOP2_HSCLKCTL_PORT4			0x16B8D4
+#define   MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL(x)		((x) << 16)
+#define   MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL(x)	((x) << 14)
+#define   MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO(x)		((x) << 12)
+#define   MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO(x)		((x) << 8)
+#define MG_CLKTOP2_HSCLKCTL(port) _MMIO_PORT((port) - PORT_C, \
+					     _MG_CLKTOP2_HSCLKCTL_PORT1, \
+					     _MG_CLKTOP2_HSCLKCTL_PORT2)
+
+#define _MG_PLL_DIV0_PORT1				0x168A00
+#define _MG_PLL_DIV0_PORT2				0x169A00
+#define _MG_PLL_DIV0_PORT3				0x16AA00
+#define _MG_PLL_DIV0_PORT4				0x16BA00
+#define   MG_PLL_DIV0_FRACNEN_H				(1 << 30)
+#define   MG_PLL_DIV0_FBDIV_FRAC(x)			((x) << 8)
+#define   MG_PLL_DIV0_FBDIV_INT(x)			((x) << 0)
+#define MG_PLL_DIV0(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_DIV0_PORT1, \
+				     _MG_PLL_DIV0_PORT2)
+
+#define _MG_PLL_DIV1_PORT1				0x168A04
+#define _MG_PLL_DIV1_PORT2				0x169A04
+#define _MG_PLL_DIV1_PORT3				0x16AA04
+#define _MG_PLL_DIV1_PORT4				0x16BA04
+#define   MG_PLL_DIV1_IREF_NDIVRATIO(x)			((x) << 16)
+#define   MG_PLL_DIV1_DITHER_DIV_1			(0 << 12)
+#define   MG_PLL_DIV1_DITHER_DIV_2			(1 << 12)
+#define   MG_PLL_DIV1_DITHER_DIV_4			(2 << 12)
+#define   MG_PLL_DIV1_DITHER_DIV_8			(3 << 12)
+#define   MG_PLL_DIV1_NDIVRATIO(x)			((x) << 4)
+#define   MG_PLL_DIV1_FBPREDIV(x)			((x) << 0)
+#define MG_PLL_DIV1(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_DIV1_PORT1, \
+				     _MG_PLL_DIV1_PORT2)
+
+#define _MG_PLL_LF_PORT1				0x168A08
+#define _MG_PLL_LF_PORT2				0x169A08
+#define _MG_PLL_LF_PORT3				0x16AA08
+#define _MG_PLL_LF_PORT4				0x16BA08
+#define   MG_PLL_LF_TDCTARGETCNT(x)			((x) << 24)
+#define   MG_PLL_LF_AFCCNTSEL_256			(0 << 20)
+#define   MG_PLL_LF_AFCCNTSEL_512			(1 << 20)
+#define   MG_PLL_LF_GAINCTRL(x)				((x) << 16)
+#define   MG_PLL_LF_INT_COEFF(x)			((x) << 8)
+#define   MG_PLL_LF_PROP_COEFF(x)			((x) << 0)
+#define MG_PLL_LF(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_LF_PORT1, \
+				   _MG_PLL_LF_PORT2)
+
+#define _MG_PLL_FRAC_LOCK_PORT1				0x168A0C
+#define _MG_PLL_FRAC_LOCK_PORT2				0x169A0C
+#define _MG_PLL_FRAC_LOCK_PORT3				0x16AA0C
+#define _MG_PLL_FRAC_LOCK_PORT4				0x16BA0C
+#define   MG_PLL_FRAC_LOCK_TRUELOCK_CRIT_32		(1 << 18)
+#define   MG_PLL_FRAC_LOCK_EARLYLOCK_CRIT_32		(1 << 16)
+#define   MG_PLL_FRAC_LOCK_LOCKTHRESH(x)		((x) << 11)
+#define   MG_PLL_FRAC_LOCK_DCODITHEREN			(1 << 10)
+#define   MG_PLL_FRAC_LOCK_FEEDFWRDCAL_EN		(1 << 8)
+#define   MG_PLL_FRAC_LOCK_FEEDFWRDGAIN(x)		((x) << 0)
+#define MG_PLL_FRAC_LOCK(port) _MMIO_PORT((port) - PORT_C, \
+					  _MG_PLL_FRAC_LOCK_PORT1, \
+					  _MG_PLL_FRAC_LOCK_PORT2)
+
+#define _MG_PLL_SSC_PORT1				0x168A10
+#define _MG_PLL_SSC_PORT2				0x169A10
+#define _MG_PLL_SSC_PORT3				0x16AA10
+#define _MG_PLL_SSC_PORT4				0x16BA10
+#define   MG_PLL_SSC_EN					(1 << 28)
+#define   MG_PLL_SSC_TYPE(x)				((x) << 26)
+#define   MG_PLL_SSC_STEPLENGTH(x)			((x) << 16)
+#define   MG_PLL_SSC_STEPNUM(x)				((x) << 10)
+#define   MG_PLL_SSC_FLLEN				(1 << 9)
+#define   MG_PLL_SSC_STEPSIZE(x)			((x) << 0)
+#define MG_PLL_SSC(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_SSC_PORT1, \
+				    _MG_PLL_SSC_PORT2)
+
+#define _MG_PLL_BIAS_PORT1				0x168A14
+#define _MG_PLL_BIAS_PORT2				0x169A14
+#define _MG_PLL_BIAS_PORT3				0x16AA14
+#define _MG_PLL_BIAS_PORT4				0x16BA14
+#define   MG_PLL_BIAS_BIAS_GB_SEL(x)			((x) << 30)
+#define   MG_PLL_BIAS_INIT_DCOAMP(x)			((x) << 24)
+#define   MG_PLL_BIAS_BIAS_BONUS(x)			((x) << 16)
+#define   MG_PLL_BIAS_BIASCAL_EN			(1 << 15)
+#define   MG_PLL_BIAS_CTRIM(x)				((x) << 8)
+#define   MG_PLL_BIAS_VREF_RDAC(x)			((x) << 5)
+#define   MG_PLL_BIAS_IREFTRIM(x)			((x) << 0)
+#define MG_PLL_BIAS(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_BIAS_PORT1, \
+				     _MG_PLL_BIAS_PORT2)
+
+#define _MG_PLL_TDC_COLDST_BIAS_PORT1			0x168A18
+#define _MG_PLL_TDC_COLDST_BIAS_PORT2			0x169A18
+#define _MG_PLL_TDC_COLDST_BIAS_PORT3			0x16AA18
+#define _MG_PLL_TDC_COLDST_BIAS_PORT4			0x16BA18
+#define   MG_PLL_TDC_COLDST_IREFINT_EN			(1 << 27)
+#define   MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(x)	((x) << 17)
+#define   MG_PLL_TDC_COLDST_COLDSTART			(1 << 16)
+#define   MG_PLL_TDC_TDCOVCCORR_EN			(1 << 2)
+#define   MG_PLL_TDC_TDCSEL(x)				((x) << 0)
+#define MG_PLL_TDC_COLDST_BIAS(port) _MMIO_PORT((port) - PORT_C, \
+						_MG_PLL_TDC_COLDST_BIAS_PORT1, \
+						_MG_PLL_TDC_COLDST_BIAS_PORT2)
+
 #define _CNL_DPLL0_CFGCR0		0x6C000
 #define _CNL_DPLL1_CFGCR0		0x6C080
 #define  DPLL_CFGCR0_HDMI_MODE		(1 << 30)
 #define  DPLL_CFGCR0_SSC_ENABLE		(1 << 29)
+#define  DPLL_CFGCR0_SSC_ENABLE_ICL	(1 << 25)
 #define  DPLL_CFGCR0_LINK_RATE_MASK	(0xf << 25)
 #define  DPLL_CFGCR0_LINK_RATE_2700	(0 << 25)
 #define  DPLL_CFGCR0_LINK_RATE_1350	(1 << 25)
@@ -9017,8 +9113,19 @@ enum skl_power_gate {
 #define  DPLL_CFGCR1_PDIV_5		(4 << 2)
 #define  DPLL_CFGCR1_PDIV_7		(8 << 2)
 #define  DPLL_CFGCR1_CENTRAL_FREQ	(3 << 0)
+#define  DPLL_CFGCR1_CENTRAL_FREQ_8400	(3 << 0)
 #define CNL_DPLL_CFGCR1(pll)		_MMIO_PLL(pll, _CNL_DPLL0_CFGCR1, _CNL_DPLL1_CFGCR1)
 
+#define _ICL_DPLL0_CFGCR0		0x164000
+#define _ICL_DPLL1_CFGCR0		0x164080
+#define ICL_DPLL_CFGCR0(pll)		_MMIO_PLL(pll, _ICL_DPLL0_CFGCR0, \
+						  _ICL_DPLL1_CFGCR0)
+
+#define _ICL_DPLL0_CFGCR1		0x164004
+#define _ICL_DPLL1_CFGCR1		0x164084
+#define ICL_DPLL_CFGCR1(pll)		_MMIO_PLL(pll, _ICL_DPLL0_CFGCR1, \
+						  _ICL_DPLL1_CFGCR1)
+
 /* BXT display engine PLL */
 #define BXT_DE_PLL_CTL			_MMIO(0x6d000)
 #define   BXT_DE_PLL_RATIO(x)		(x)	/* {60,65,100} * 19.2MHz */
@@ -9790,6 +9897,13 @@ enum skl_power_gate {
 #define GEN9_MFX1_MOCS(i)	_MMIO(0xca00 + (i) * 4)	/* Media 1 MOCS registers */
 #define GEN9_VEBOX_MOCS(i)	_MMIO(0xcb00 + (i) * 4)	/* Video MOCS registers */
 #define GEN9_BLT_MOCS(i)	_MMIO(0xcc00 + (i) * 4)	/* Blitter MOCS registers */
+/* Media decoder 2 MOCS registers */
+#define GEN11_MFX2_MOCS(i)	_MMIO(0x10000 + (i) * 4)
+
+#define GEN10_SCRATCH_LNCF2		_MMIO(0xb0a0)
+#define   PMFLUSHDONE_LNICRSDROP	(1 << 20)
+#define   PMFLUSH_GAPL3UNBLOCK		(1 << 21)
+#define   PMFLUSHDONE_LNEBLK		(1 << 22)
 
 /* gamt regs */
 #define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 282f57630cc1..8928894dd9c7 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -49,7 +49,7 @@ static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 		return "signaled";
 
-	return to_request(fence)->timeline->common->name;
+	return to_request(fence)->timeline->name;
 }
 
 static bool i915_fence_signaled(struct dma_fence *fence)
@@ -59,11 +59,7 @@ static bool i915_fence_signaled(struct dma_fence *fence)
 
 static bool i915_fence_enable_signaling(struct dma_fence *fence)
 {
-	if (i915_fence_signaled(fence))
-		return false;
-
-	intel_engine_enable_signaling(to_request(fence), true);
-	return !i915_fence_signaled(fence);
+	return intel_engine_enable_signaling(to_request(fence), true);
 }
 
 static signed long i915_fence_wait(struct dma_fence *fence,
@@ -129,22 +125,22 @@ i915_dependency_free(struct drm_i915_private *i915,
 }
 
 static void
-__i915_priotree_add_dependency(struct i915_priotree *pt,
-			       struct i915_priotree *signal,
-			       struct i915_dependency *dep,
-			       unsigned long flags)
+__i915_sched_node_add_dependency(struct i915_sched_node *node,
+				 struct i915_sched_node *signal,
+				 struct i915_dependency *dep,
+				 unsigned long flags)
 {
 	INIT_LIST_HEAD(&dep->dfs_link);
 	list_add(&dep->wait_link, &signal->waiters_list);
-	list_add(&dep->signal_link, &pt->signalers_list);
+	list_add(&dep->signal_link, &node->signalers_list);
 	dep->signaler = signal;
 	dep->flags = flags;
 }
 
 static int
-i915_priotree_add_dependency(struct drm_i915_private *i915,
-			     struct i915_priotree *pt,
-			     struct i915_priotree *signal)
+i915_sched_node_add_dependency(struct drm_i915_private *i915,
+			       struct i915_sched_node *node,
+			       struct i915_sched_node *signal)
 {
 	struct i915_dependency *dep;
 
@@ -152,16 +148,18 @@ i915_priotree_add_dependency(struct drm_i915_private *i915,
 	if (!dep)
 		return -ENOMEM;
 
-	__i915_priotree_add_dependency(pt, signal, dep, I915_DEPENDENCY_ALLOC);
+	__i915_sched_node_add_dependency(node, signal, dep,
+					 I915_DEPENDENCY_ALLOC);
 	return 0;
 }
 
 static void
-i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt)
+i915_sched_node_fini(struct drm_i915_private *i915,
+		     struct i915_sched_node *node)
 {
-	struct i915_dependency *dep, *next;
+	struct i915_dependency *dep, *tmp;
 
-	GEM_BUG_ON(!list_empty(&pt->link));
+	GEM_BUG_ON(!list_empty(&node->link));
 
 	/*
 	 * Everyone we depended upon (the fences we wait to be signaled)
@@ -169,8 +167,8 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt)
 	 * However, retirement is run independently on each timeline and
 	 * so we may be called out-of-order.
 	 */
-	list_for_each_entry_safe(dep, next, &pt->signalers_list, signal_link) {
-		GEM_BUG_ON(!i915_priotree_signaled(dep->signaler));
+	list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) {
+		GEM_BUG_ON(!i915_sched_node_signaled(dep->signaler));
 		GEM_BUG_ON(!list_empty(&dep->dfs_link));
 
 		list_del(&dep->wait_link);
@@ -179,8 +177,8 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt)
 	}
 
 	/* Remove ourselves from everyone who depends upon us */
-	list_for_each_entry_safe(dep, next, &pt->waiters_list, wait_link) {
-		GEM_BUG_ON(dep->signaler != pt);
+	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
+		GEM_BUG_ON(dep->signaler != node);
 		GEM_BUG_ON(!list_empty(&dep->dfs_link));
 
 		list_del(&dep->signal_link);
@@ -190,17 +188,18 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt)
 }
 
 static void
-i915_priotree_init(struct i915_priotree *pt)
+i915_sched_node_init(struct i915_sched_node *node)
 {
-	INIT_LIST_HEAD(&pt->signalers_list);
-	INIT_LIST_HEAD(&pt->waiters_list);
-	INIT_LIST_HEAD(&pt->link);
-	pt->priority = I915_PRIORITY_INVALID;
+	INIT_LIST_HEAD(&node->signalers_list);
+	INIT_LIST_HEAD(&node->waiters_list);
+	INIT_LIST_HEAD(&node->link);
+	node->attr.priority = I915_PRIORITY_INVALID;
 }
 
 static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno)
 {
 	struct intel_engine_cs *engine;
+	struct i915_timeline *timeline;
 	enum intel_engine_id id;
 	int ret;
 
@@ -211,30 +210,37 @@ static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno)
 	if (ret)
 		return ret;
 
+	GEM_BUG_ON(i915->gt.active_requests);
+
 	/* If the seqno wraps around, we need to clear the breadcrumb rbtree */
 	for_each_engine(engine, i915, id) {
-		struct i915_gem_timeline *timeline;
-		struct intel_timeline *tl = engine->timeline;
+		GEM_TRACE("%s seqno %d (current %d) -> %d\n",
+			  engine->name,
+			  engine->timeline.seqno,
+			  intel_engine_get_seqno(engine),
+			  seqno);
 
-		if (!i915_seqno_passed(seqno, tl->seqno)) {
+		if (!i915_seqno_passed(seqno, engine->timeline.seqno)) {
 			/* Flush any waiters before we reuse the seqno */
 			intel_engine_disarm_breadcrumbs(engine);
+			intel_engine_init_hangcheck(engine);
 			GEM_BUG_ON(!list_empty(&engine->breadcrumbs.signals));
 		}
 
 		/* Check we are idle before we fiddle with hw state! */
 		GEM_BUG_ON(!intel_engine_is_idle(engine));
-		GEM_BUG_ON(i915_gem_active_isset(&engine->timeline->last_request));
+		GEM_BUG_ON(i915_gem_active_isset(&engine->timeline.last_request));
 
 		/* Finally reset hw state */
 		intel_engine_init_global_seqno(engine, seqno);
-		tl->seqno = seqno;
-
-		list_for_each_entry(timeline, &i915->gt.timelines, link)
-			memset(timeline->engine[id].global_sync, 0,
-			       sizeof(timeline->engine[id].global_sync));
+		engine->timeline.seqno = seqno;
 	}
 
+	list_for_each_entry(timeline, &i915->gt.timelines, link)
+		memset(timeline->global_sync, 0, sizeof(timeline->global_sync));
+
+	i915->gt.request_serial = seqno;
+
 	return 0;
 }
 
@@ -251,83 +257,37 @@ int i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno)
 	return reset_all_global_seqno(i915, seqno - 1);
 }
 
-static void mark_busy(struct drm_i915_private *i915)
+static int reserve_gt(struct drm_i915_private *i915)
 {
-	if (i915->gt.awake)
-		return;
-
-	GEM_BUG_ON(!i915->gt.active_requests);
-
-	intel_runtime_pm_get_noresume(i915);
+	int ret;
 
 	/*
-	 * It seems that the DMC likes to transition between the DC states a lot
-	 * when there are no connected displays (no active power domains) during
-	 * command submission.
-	 *
-	 * This activity has negative impact on the performance of the chip with
-	 * huge latencies observed in the interrupt handler and elsewhere.
+	 * Reservation is fine until we may need to wrap around
 	 *
-	 * Work around it by grabbing a GT IRQ power domain whilst there is any
-	 * GT activity, preventing any DC state transitions.
+	 * By incrementing the serial for every request, we know that no
+	 * individual engine may exceed that serial (as each is reset to 0
+	 * on any wrap). This protects even the most pessimistic of migrations
+	 * of every request from all engines onto just one.
 	 */
-	intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
-
-	i915->gt.awake = true;
-	if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */
-		i915->gt.epoch = 1;
-
-	intel_enable_gt_powersave(i915);
-	i915_update_gfx_val(i915);
-	if (INTEL_GEN(i915) >= 6)
-		gen6_rps_busy(i915);
-	i915_pmu_gt_unparked(i915);
-
-	intel_engines_unpark(i915);
-
-	i915_queue_hangcheck(i915);
-
-	queue_delayed_work(i915->wq,
-			   &i915->gt.retire_work,
-			   round_jiffies_up_relative(HZ));
-}
-
-static int reserve_engine(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *i915 = engine->i915;
-	u32 active = ++engine->timeline->inflight_seqnos;
-	u32 seqno = engine->timeline->seqno;
-	int ret;
-
-	/* Reservation is fine until we need to wrap around */
-	if (unlikely(add_overflows(seqno, active))) {
+	while (unlikely(++i915->gt.request_serial == 0)) {
 		ret = reset_all_global_seqno(i915, 0);
 		if (ret) {
-			engine->timeline->inflight_seqnos--;
+			i915->gt.request_serial--;
 			return ret;
 		}
 	}
 
 	if (!i915->gt.active_requests++)
-		mark_busy(i915);
+		i915_gem_unpark(i915);
 
 	return 0;
 }
 
-static void unreserve_engine(struct intel_engine_cs *engine)
+static void unreserve_gt(struct drm_i915_private *i915)
 {
-	struct drm_i915_private *i915 = engine->i915;
-
-	if (!--i915->gt.active_requests) {
-		/* Cancel the mark_busy() from our reserve_engine() */
-		GEM_BUG_ON(!i915->gt.awake);
-		mod_delayed_work(i915->wq,
-				 &i915->gt.idle_work,
-				 msecs_to_jiffies(100));
-	}
-
-	GEM_BUG_ON(!engine->timeline->inflight_seqnos);
-	engine->timeline->inflight_seqnos--;
+	GEM_BUG_ON(!i915->gt.active_requests);
+	if (!--i915->gt.active_requests)
+		i915_gem_park(i915);
 }
 
 void i915_gem_retire_noop(struct i915_gem_active *active,
@@ -338,6 +298,7 @@ void i915_gem_retire_noop(struct i915_gem_active *active,
 
 static void advance_ring(struct i915_request *request)
 {
+	struct intel_ring *ring = request->ring;
 	unsigned int tail;
 
 	/*
@@ -349,7 +310,8 @@ static void advance_ring(struct i915_request *request)
 	 * Note this requires that we are always called in request
 	 * completion order.
 	 */
-	if (list_is_last(&request->ring_link, &request->ring->request_list)) {
+	GEM_BUG_ON(!list_is_first(&request->ring_link, &ring->request_list));
+	if (list_is_last(&request->ring_link, &ring->request_list)) {
 		/*
 		 * We may race here with execlists resubmitting this request
 		 * as we retire it. The resubmission will move the ring->tail
@@ -358,13 +320,14 @@ static void advance_ring(struct i915_request *request)
 		 * is just about to be. Either works, if we miss the last two
 		 * noops - they are safe to be replayed on a reset.
 		 */
-		tail = READ_ONCE(request->ring->tail);
+		tail = READ_ONCE(request->tail);
+		list_del(&ring->active_link);
 	} else {
 		tail = request->postfix;
 	}
-	list_del(&request->ring_link);
+	list_del_init(&request->ring_link);
 
-	request->ring->head = tail;
+	ring->head = tail;
 }
 
 static void free_capture_list(struct i915_request *request)
@@ -380,25 +343,84 @@ static void free_capture_list(struct i915_request *request)
 	}
 }
 
+static void __retire_engine_request(struct intel_engine_cs *engine,
+				    struct i915_request *rq)
+{
+	GEM_TRACE("%s(%s) fence %llx:%d, global=%d, current %d\n",
+		  __func__, engine->name,
+		  rq->fence.context, rq->fence.seqno,
+		  rq->global_seqno,
+		  intel_engine_get_seqno(engine));
+
+	GEM_BUG_ON(!i915_request_completed(rq));
+
+	local_irq_disable();
+
+	spin_lock(&engine->timeline.lock);
+	GEM_BUG_ON(!list_is_first(&rq->link, &engine->timeline.requests));
+	list_del_init(&rq->link);
+	spin_unlock(&engine->timeline.lock);
+
+	spin_lock(&rq->lock);
+	if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags))
+		dma_fence_signal_locked(&rq->fence);
+	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags))
+		intel_engine_cancel_signaling(rq);
+	if (rq->waitboost) {
+		GEM_BUG_ON(!atomic_read(&rq->i915->gt_pm.rps.num_waiters));
+		atomic_dec(&rq->i915->gt_pm.rps.num_waiters);
+	}
+	spin_unlock(&rq->lock);
+
+	local_irq_enable();
+
+	/*
+	 * The backing object for the context is done after switching to the
+	 * *next* context. Therefore we cannot retire the previous context until
+	 * the next context has already started running. However, since we
+	 * cannot take the required locks at i915_request_submit() we
+	 * defer the unpinning of the active context to now, retirement of
+	 * the subsequent request.
+	 */
+	if (engine->last_retired_context)
+		intel_context_unpin(engine->last_retired_context, engine);
+	engine->last_retired_context = rq->ctx;
+}
+
+static void __retire_engine_upto(struct intel_engine_cs *engine,
+				 struct i915_request *rq)
+{
+	struct i915_request *tmp;
+
+	if (list_empty(&rq->link))
+		return;
+
+	do {
+		tmp = list_first_entry(&engine->timeline.requests,
+				       typeof(*tmp), link);
+
+		GEM_BUG_ON(tmp->engine != engine);
+		__retire_engine_request(engine, tmp);
+	} while (tmp != rq);
+}
+
 static void i915_request_retire(struct i915_request *request)
 {
-	struct intel_engine_cs *engine = request->engine;
 	struct i915_gem_active *active, *next;
 
+	GEM_TRACE("%s fence %llx:%d, global=%d, current %d\n",
+		  request->engine->name,
+		  request->fence.context, request->fence.seqno,
+		  request->global_seqno,
+		  intel_engine_get_seqno(request->engine));
+
 	lockdep_assert_held(&request->i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915_sw_fence_signaled(&request->submit));
 	GEM_BUG_ON(!i915_request_completed(request));
-	GEM_BUG_ON(!request->i915->gt.active_requests);
 
 	trace_i915_request_retire(request);
 
-	spin_lock_irq(&engine->timeline->lock);
-	list_del_init(&request->link);
-	spin_unlock_irq(&engine->timeline->lock);
-
-	unreserve_engine(request->engine);
 	advance_ring(request);
-
 	free_capture_list(request);
 
 	/*
@@ -434,73 +456,74 @@ static void i915_request_retire(struct i915_request *request)
 
 	/* Retirement decays the ban score as it is a sign of ctx progress */
 	atomic_dec_if_positive(&request->ctx->ban_score);
+	intel_context_unpin(request->ctx, request->engine);
 
-	/*
-	 * The backing object for the context is done after switching to the
-	 * *next* context. Therefore we cannot retire the previous context until
-	 * the next context has already started running. However, since we
-	 * cannot take the required locks at i915_request_submit() we
-	 * defer the unpinning of the active context to now, retirement of
-	 * the subsequent request.
-	 */
-	if (engine->last_retired_context)
-		engine->context_unpin(engine, engine->last_retired_context);
-	engine->last_retired_context = request->ctx;
+	__retire_engine_upto(request->engine, request);
 
-	spin_lock_irq(&request->lock);
-	if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags))
-		dma_fence_signal_locked(&request->fence);
-	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags))
-		intel_engine_cancel_signaling(request);
-	if (request->waitboost) {
-		GEM_BUG_ON(!atomic_read(&request->i915->gt_pm.rps.num_waiters));
-		atomic_dec(&request->i915->gt_pm.rps.num_waiters);
-	}
-	spin_unlock_irq(&request->lock);
+	unreserve_gt(request->i915);
 
-	i915_priotree_fini(request->i915, &request->priotree);
+	i915_sched_node_fini(request->i915, &request->sched);
 	i915_request_put(request);
 }
 
 void i915_request_retire_upto(struct i915_request *rq)
 {
-	struct intel_engine_cs *engine = rq->engine;
+	struct intel_ring *ring = rq->ring;
 	struct i915_request *tmp;
 
+	GEM_TRACE("%s fence %llx:%d, global=%d, current %d\n",
+		  rq->engine->name,
+		  rq->fence.context, rq->fence.seqno,
+		  rq->global_seqno,
+		  intel_engine_get_seqno(rq->engine));
+
 	lockdep_assert_held(&rq->i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915_request_completed(rq));
 
-	if (list_empty(&rq->link))
+	if (list_empty(&rq->ring_link))
 		return;
 
 	do {
-		tmp = list_first_entry(&engine->timeline->requests,
-				       typeof(*tmp), link);
+		tmp = list_first_entry(&ring->request_list,
+				       typeof(*tmp), ring_link);
 
 		i915_request_retire(tmp);
 	} while (tmp != rq);
 }
 
-static u32 timeline_get_seqno(struct intel_timeline *tl)
+static u32 timeline_get_seqno(struct i915_timeline *tl)
 {
 	return ++tl->seqno;
 }
 
+static void move_to_timeline(struct i915_request *request,
+			     struct i915_timeline *timeline)
+{
+	GEM_BUG_ON(request->timeline == &request->engine->timeline);
+	lockdep_assert_held(&request->engine->timeline.lock);
+
+	spin_lock_nested(&request->timeline->lock, SINGLE_DEPTH_NESTING);
+	list_move_tail(&request->link, &timeline->requests);
+	spin_unlock(&request->timeline->lock);
+}
+
 void __i915_request_submit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
-	struct intel_timeline *timeline;
 	u32 seqno;
 
+	GEM_TRACE("%s fence %llx:%d -> global=%d, current %d\n",
+		  engine->name,
+		  request->fence.context, request->fence.seqno,
+		  engine->timeline.seqno + 1,
+		  intel_engine_get_seqno(engine));
+
 	GEM_BUG_ON(!irqs_disabled());
-	lockdep_assert_held(&engine->timeline->lock);
+	lockdep_assert_held(&engine->timeline.lock);
 
-	/* Transfer from per-context onto the global per-engine timeline */
-	timeline = engine->timeline;
-	GEM_BUG_ON(timeline == request->timeline);
 	GEM_BUG_ON(request->global_seqno);
 
-	seqno = timeline_get_seqno(timeline);
+	seqno = timeline_get_seqno(&engine->timeline);
 	GEM_BUG_ON(!seqno);
 	GEM_BUG_ON(i915_seqno_passed(intel_engine_get_seqno(engine), seqno));
 
@@ -514,9 +537,8 @@ void __i915_request_submit(struct i915_request *request)
 	engine->emit_breadcrumb(request,
 				request->ring->vaddr + request->postfix);
 
-	spin_lock(&request->timeline->lock);
-	list_move_tail(&request->link, &timeline->requests);
-	spin_unlock(&request->timeline->lock);
+	/* Transfer from per-context onto the global per-engine timeline */
+	move_to_timeline(request, &engine->timeline);
 
 	trace_i915_request_execute(request);
 
@@ -529,30 +551,35 @@ void i915_request_submit(struct i915_request *request)
 	unsigned long flags;
 
 	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->timeline->lock, flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	__i915_request_submit(request);
 
-	spin_unlock_irqrestore(&engine->timeline->lock, flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
 void __i915_request_unsubmit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
-	struct intel_timeline *timeline;
+
+	GEM_TRACE("%s fence %llx:%d <- global=%d, current %d\n",
+		  engine->name,
+		  request->fence.context, request->fence.seqno,
+		  request->global_seqno,
+		  intel_engine_get_seqno(engine));
 
 	GEM_BUG_ON(!irqs_disabled());
-	lockdep_assert_held(&engine->timeline->lock);
+	lockdep_assert_held(&engine->timeline.lock);
 
 	/*
 	 * Only unwind in reverse order, required so that the per-context list
 	 * is kept in seqno/ring order.
 	 */
 	GEM_BUG_ON(!request->global_seqno);
-	GEM_BUG_ON(request->global_seqno != engine->timeline->seqno);
+	GEM_BUG_ON(request->global_seqno != engine->timeline.seqno);
 	GEM_BUG_ON(i915_seqno_passed(intel_engine_get_seqno(engine),
 				     request->global_seqno));
-	engine->timeline->seqno--;
+	engine->timeline.seqno--;
 
 	/* We may be recursing from the signal callback of another i915 fence */
 	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
@@ -562,12 +589,7 @@ void __i915_request_unsubmit(struct i915_request *request)
 	spin_unlock(&request->lock);
 
 	/* Transfer back from the global per-engine timeline to per-context */
-	timeline = request->timeline;
-	GEM_BUG_ON(timeline == engine->timeline);
-
-	spin_lock(&timeline->lock);
-	list_move(&request->link, &timeline->requests);
-	spin_unlock(&timeline->lock);
+	move_to_timeline(request, request->timeline);
 
 	/*
 	 * We don't need to wake_up any waiters on request->execute, they
@@ -584,11 +606,11 @@ void i915_request_unsubmit(struct i915_request *request)
 	unsigned long flags;
 
 	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->timeline->lock, flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	__i915_request_unsubmit(request);
 
-	spin_unlock_irqrestore(&engine->timeline->lock, flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
 static int __i915_sw_fence_call
@@ -659,12 +681,12 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	 * GGTT space, so do this first before we reserve a seqno for
 	 * ourselves.
 	 */
-	ring = engine->context_pin(engine, ctx);
+	ring = intel_context_pin(ctx, engine);
 	if (IS_ERR(ring))
 		return ERR_CAST(ring);
 	GEM_BUG_ON(!ring);
 
-	ret = reserve_engine(engine);
+	ret = reserve_gt(i915);
 	if (ret)
 		goto err_unpin;
 
@@ -672,10 +694,10 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	if (ret)
 		goto err_unreserve;
 
-	/* Move the oldest request to the slab-cache (if not in use!) */
-	rq = list_first_entry_or_null(&engine->timeline->requests,
-				      typeof(*rq), link);
-	if (rq && i915_request_completed(rq))
+	/* Move our oldest request to the slab-cache (if not in use!) */
+	rq = list_first_entry(&ring->request_list, typeof(*rq), ring_link);
+	if (!list_is_last(&rq->ring_link, &ring->request_list) &&
+	    i915_request_completed(rq))
 		i915_request_retire(rq);
 
 	/*
@@ -735,8 +757,13 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		}
 	}
 
-	rq->timeline = i915_gem_context_lookup_timeline(ctx, engine);
-	GEM_BUG_ON(rq->timeline == engine->timeline);
+	INIT_LIST_HEAD(&rq->active_list);
+	rq->i915 = i915;
+	rq->engine = engine;
+	rq->ctx = ctx;
+	rq->ring = ring;
+	rq->timeline = ring->timeline;
+	GEM_BUG_ON(rq->timeline == &engine->timeline);
 
 	spin_lock_init(&rq->lock);
 	dma_fence_init(&rq->fence,
@@ -749,13 +776,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	i915_sw_fence_init(&i915_request_get(rq)->submit, submit_notify);
 	init_waitqueue_head(&rq->execute);
 
-	i915_priotree_init(&rq->priotree);
-
-	INIT_LIST_HEAD(&rq->active_list);
-	rq->i915 = i915;
-	rq->engine = engine;
-	rq->ctx = ctx;
-	rq->ring = ring;
+	i915_sched_node_init(&rq->sched);
 
 	/* No zalloc, must clear what we need by hand */
 	rq->global_seqno = 0;
@@ -792,6 +813,9 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	if (ret)
 		goto err_unwind;
 
+	/* Keep a second pin for the dual retirement along engine and ring */
+	__intel_context_pin(rq->ctx, engine);
+
 	/* Check that we didn't interrupt ourselves with a new request */
 	GEM_BUG_ON(rq->timeline->seqno != rq->fence.seqno);
 	return rq;
@@ -801,14 +825,14 @@ err_unwind:
 
 	/* Make sure we didn't add ourselves to external state before freeing */
 	GEM_BUG_ON(!list_empty(&rq->active_list));
-	GEM_BUG_ON(!list_empty(&rq->priotree.signalers_list));
-	GEM_BUG_ON(!list_empty(&rq->priotree.waiters_list));
+	GEM_BUG_ON(!list_empty(&rq->sched.signalers_list));
+	GEM_BUG_ON(!list_empty(&rq->sched.waiters_list));
 
 	kmem_cache_free(i915->requests, rq);
 err_unreserve:
-	unreserve_engine(engine);
+	unreserve_gt(i915);
 err_unpin:
-	engine->context_unpin(engine, ctx);
+	intel_context_unpin(ctx, engine);
 	return ERR_PTR(ret);
 }
 
@@ -824,9 +848,9 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 		return 0;
 
 	if (to->engine->schedule) {
-		ret = i915_priotree_add_dependency(to->i915,
-						   &to->priotree,
-						   &from->priotree);
+		ret = i915_sched_node_add_dependency(to->i915,
+						     &to->sched,
+						     &from->sched);
 		if (ret < 0)
 			return ret;
 	}
@@ -904,7 +928,7 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 		/* Squash repeated waits to the same timelines */
 		if (fence->context != rq->i915->mm.unordered_timeline &&
-		    intel_timeline_sync_is_later(rq->timeline, fence))
+		    i915_timeline_sync_is_later(rq->timeline, fence))
 			continue;
 
 		if (dma_fence_is_i915(fence))
@@ -918,7 +942,7 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 		/* Record the latest fence used against each timeline */
 		if (fence->context != rq->i915->mm.unordered_timeline)
-			intel_timeline_sync_set(rq->timeline, fence);
+			i915_timeline_sync_set(rq->timeline, fence);
 	} while (--nchild);
 
 	return 0;
@@ -995,11 +1019,14 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 {
 	struct intel_engine_cs *engine = request->engine;
 	struct intel_ring *ring = request->ring;
-	struct intel_timeline *timeline = request->timeline;
+	struct i915_timeline *timeline = request->timeline;
 	struct i915_request *prev;
 	u32 *cs;
 	int err;
 
+	GEM_TRACE("%s fence %llx:%d\n",
+		  engine->name, request->fence.context, request->fence.seqno);
+
 	lockdep_assert_held(&request->i915->drm.struct_mutex);
 	trace_i915_request_add(request);
 
@@ -1054,10 +1081,10 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 		i915_sw_fence_await_sw_fence(&request->submit, &prev->submit,
 					     &request->submitq);
 		if (engine->schedule)
-			__i915_priotree_add_dependency(&request->priotree,
-						       &prev->priotree,
-						       &request->dep,
-						       0);
+			__i915_sched_node_add_dependency(&request->sched,
+							 &prev->sched,
+							 &request->dep,
+							 0);
 	}
 
 	spin_lock_irq(&timeline->lock);
@@ -1068,6 +1095,8 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	i915_gem_active_set(&timeline->last_request, request);
 
 	list_add_tail(&request->ring_link, &ring->request_list);
+	if (list_is_first(&request->ring_link, &ring->request_list))
+		list_add(&ring->active_link, &request->i915->gt.active_rings);
 	request->emitted_jiffies = jiffies;
 
 	/*
@@ -1081,12 +1110,11 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	 * decide whether to preempt the entire chain so that it is ready to
 	 * run at the earliest possible convenience.
 	 */
-	rcu_read_lock();
+	local_bh_disable();
+	rcu_read_lock(); /* RCU serialisation for set-wedged protection */
 	if (engine->schedule)
-		engine->schedule(request, request->ctx->priority);
+		engine->schedule(request, &request->ctx->sched);
 	rcu_read_unlock();
-
-	local_bh_disable();
 	i915_sw_fence_commit(&request->submit);
 	local_bh_enable(); /* Kick the execlists tasklet if just scheduled */
 
@@ -1206,11 +1234,13 @@ static bool __i915_spin_request(const struct i915_request *rq,
 
 static bool __i915_wait_request_check_and_reset(struct i915_request *request)
 {
-	if (likely(!i915_reset_handoff(&request->i915->gpu_error)))
+	struct i915_gpu_error *error = &request->i915->gpu_error;
+
+	if (likely(!i915_reset_handoff(error)))
 		return false;
 
 	__set_current_state(TASK_RUNNING);
-	i915_reset(request->i915, 0);
+	i915_reset(request->i915, error->stalled_mask, error->reason);
 	return true;
 }
 
@@ -1373,38 +1403,30 @@ complete:
 	return timeout;
 }
 
-static void engine_retire_requests(struct intel_engine_cs *engine)
+static void ring_retire_requests(struct intel_ring *ring)
 {
 	struct i915_request *request, *next;
-	u32 seqno = intel_engine_get_seqno(engine);
-	LIST_HEAD(retire);
 
-	spin_lock_irq(&engine->timeline->lock);
 	list_for_each_entry_safe(request, next,
-				 &engine->timeline->requests, link) {
-		if (!i915_seqno_passed(seqno, request->global_seqno))
+				 &ring->request_list, ring_link) {
+		if (!i915_request_completed(request))
 			break;
 
-		list_move_tail(&request->link, &retire);
-	}
-	spin_unlock_irq(&engine->timeline->lock);
-
-	list_for_each_entry_safe(request, next, &retire, link)
 		i915_request_retire(request);
+	}
 }
 
 void i915_retire_requests(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	struct intel_ring *ring, *tmp;
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
 
 	if (!i915->gt.active_requests)
 		return;
 
-	for_each_engine(engine, i915, id)
-		engine_retire_requests(engine);
+	list_for_each_entry_safe(ring, tmp, &i915->gt.active_rings, active_link)
+		ring_retire_requests(ring);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 7d6eb82eeb91..eddbd4245cb3 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -28,13 +28,16 @@
 #include <linux/dma-fence.h>
 
 #include "i915_gem.h"
+#include "i915_scheduler.h"
 #include "i915_sw_fence.h"
+#include "i915_scheduler.h"
 
 #include <uapi/drm/i915_drm.h>
 
 struct drm_file;
 struct drm_i915_gem_object;
 struct i915_request;
+struct i915_timeline;
 
 struct intel_wait {
 	struct rb_node node;
@@ -48,44 +51,6 @@ struct intel_signal_node {
 	struct list_head link;
 };
 
-struct i915_dependency {
-	struct i915_priotree *signaler;
-	struct list_head signal_link;
-	struct list_head wait_link;
-	struct list_head dfs_link;
-	unsigned long flags;
-#define I915_DEPENDENCY_ALLOC BIT(0)
-};
-
-/*
- * "People assume that time is a strict progression of cause to effect, but
- * actually, from a nonlinear, non-subjective viewpoint, it's more like a big
- * ball of wibbly-wobbly, timey-wimey ... stuff." -The Doctor, 2015
- *
- * Requests exist in a complex web of interdependencies. Each request
- * has to wait for some other request to complete before it is ready to be run
- * (e.g. we have to wait until the pixels have been rendering into a texture
- * before we can copy from it). We track the readiness of a request in terms
- * of fences, but we also need to keep the dependency tree for the lifetime
- * of the request (beyond the life of an individual fence). We use the tree
- * at various points to reorder the requests whilst keeping the requests
- * in order with respect to their various dependencies.
- */
-struct i915_priotree {
-	struct list_head signalers_list; /* those before us, we depend upon */
-	struct list_head waiters_list; /* those after us, they depend upon us */
-	struct list_head link;
-	int priority;
-};
-
-enum {
-	I915_PRIORITY_MIN = I915_CONTEXT_MIN_USER_PRIORITY - 1,
-	I915_PRIORITY_NORMAL = I915_CONTEXT_DEFAULT_PRIORITY,
-	I915_PRIORITY_MAX = I915_CONTEXT_MAX_USER_PRIORITY + 1,
-
-	I915_PRIORITY_INVALID = INT_MIN
-};
-
 struct i915_capture_list {
 	struct i915_capture_list *next;
 	struct i915_vma *vma;
@@ -131,7 +96,7 @@ struct i915_request {
 	struct i915_gem_context *ctx;
 	struct intel_engine_cs *engine;
 	struct intel_ring *ring;
-	struct intel_timeline *timeline;
+	struct i915_timeline *timeline;
 	struct intel_signal_node signaling;
 
 	/*
@@ -154,7 +119,7 @@ struct i915_request {
 	 * to retirement), i.e. bidirectional dependency information for the
 	 * request not tied to individual fences.
 	 */
-	struct i915_priotree priotree;
+	struct i915_sched_node sched;
 	struct i915_dependency dep;
 
 	/**
@@ -343,10 +308,10 @@ static inline bool i915_request_started(const struct i915_request *rq)
 				 seqno - 1);
 }
 
-static inline bool i915_priotree_signaled(const struct i915_priotree *pt)
+static inline bool i915_sched_node_signaled(const struct i915_sched_node *node)
 {
 	const struct i915_request *rq =
-		container_of(pt, const struct i915_request, priotree);
+		container_of(node, const struct i915_request, sched);
 
 	return i915_request_completed(rq);
 }
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
new file mode 100644
index 000000000000..70a42220358d
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -0,0 +1,72 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#ifndef _I915_SCHEDULER_H_
+#define _I915_SCHEDULER_H_
+
+#include <linux/bitops.h>
+
+#include <uapi/drm/i915_drm.h>
+
+enum {
+	I915_PRIORITY_MIN = I915_CONTEXT_MIN_USER_PRIORITY - 1,
+	I915_PRIORITY_NORMAL = I915_CONTEXT_DEFAULT_PRIORITY,
+	I915_PRIORITY_MAX = I915_CONTEXT_MAX_USER_PRIORITY + 1,
+
+	I915_PRIORITY_INVALID = INT_MIN
+};
+
+struct i915_sched_attr {
+	/**
+	 * @priority: execution and service priority
+	 *
+	 * All clients are equal, but some are more equal than others!
+	 *
+	 * Requests from a context with a greater (more positive) value of
+	 * @priority will be executed before those with a lower @priority
+	 * value, forming a simple QoS.
+	 *
+	 * The &drm_i915_private.kernel_context is assigned the lowest priority.
+	 */
+	int priority;
+};
+
+/*
+ * "People assume that time is a strict progression of cause to effect, but
+ * actually, from a nonlinear, non-subjective viewpoint, it's more like a big
+ * ball of wibbly-wobbly, timey-wimey ... stuff." -The Doctor, 2015
+ *
+ * Requests exist in a complex web of interdependencies. Each request
+ * has to wait for some other request to complete before it is ready to be run
+ * (e.g. we have to wait until the pixels have been rendering into a texture
+ * before we can copy from it). We track the readiness of a request in terms
+ * of fences, but we also need to keep the dependency tree for the lifetime
+ * of the request (beyond the life of an individual fence). We use the tree
+ * at various points to reorder the requests whilst keeping the requests
+ * in order with respect to their various dependencies.
+ *
+ * There is no active component to the "scheduler". As we know the dependency
+ * DAG of each request, we are able to insert it into a sorted queue when it
+ * is ready, and are able to reorder its portion of the graph to accommodate
+ * dynamic priority changes.
+ */
+struct i915_sched_node {
+	struct list_head signalers_list; /* those before us, we depend upon */
+	struct list_head waiters_list; /* those after us, they depend upon us */
+	struct list_head link;
+	struct i915_sched_attr attr;
+};
+
+struct i915_dependency {
+	struct i915_sched_node *signaler;
+	struct list_head signal_link;
+	struct list_head wait_link;
+	struct list_head dfs_link;
+	unsigned long flags;
+#define I915_DEPENDENCY_ALLOC BIT(0)
+};
+
+#endif /* _I915_SCHEDULER_H_ */
diff --git a/drivers/gpu/drm/i915/i915_timeline.c b/drivers/gpu/drm/i915/i915_timeline.c
new file mode 100644
index 000000000000..4667cc08c416
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_timeline.c
@@ -0,0 +1,105 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2016-2018 Intel Corporation
+ */
+
+#include "i915_drv.h"
+
+#include "i915_timeline.h"
+#include "i915_syncmap.h"
+
+void i915_timeline_init(struct drm_i915_private *i915,
+			struct i915_timeline *timeline,
+			const char *name)
+{
+	lockdep_assert_held(&i915->drm.struct_mutex);
+
+	/*
+	 * Ideally we want a set of engines on a single leaf as we expect
+	 * to mostly be tracking synchronisation between engines. It is not
+	 * a huge issue if this is not the case, but we may want to mitigate
+	 * any page crossing penalties if they become an issue.
+	 */
+	BUILD_BUG_ON(KSYNCMAP < I915_NUM_ENGINES);
+
+	timeline->name = name;
+
+	list_add(&timeline->link, &i915->gt.timelines);
+
+	/* Called during early_init before we know how many engines there are */
+
+	timeline->fence_context = dma_fence_context_alloc(1);
+
+	spin_lock_init(&timeline->lock);
+
+	init_request_active(&timeline->last_request, NULL);
+	INIT_LIST_HEAD(&timeline->requests);
+
+	i915_syncmap_init(&timeline->sync);
+}
+
+/**
+ * i915_timelines_park - called when the driver idles
+ * @i915: the drm_i915_private device
+ *
+ * When the driver is completely idle, we know that all of our sync points
+ * have been signaled and our tracking is then entirely redundant. Any request
+ * to wait upon an older sync point will be completed instantly as we know
+ * the fence is signaled and therefore we will not even look them up in the
+ * sync point map.
+ */
+void i915_timelines_park(struct drm_i915_private *i915)
+{
+	struct i915_timeline *timeline;
+
+	lockdep_assert_held(&i915->drm.struct_mutex);
+
+	list_for_each_entry(timeline, &i915->gt.timelines, link) {
+		/*
+		 * All known fences are completed so we can scrap
+		 * the current sync point tracking and start afresh,
+		 * any attempt to wait upon a previous sync point
+		 * will be skipped as the fence was signaled.
+		 */
+		i915_syncmap_free(&timeline->sync);
+	}
+}
+
+void i915_timeline_fini(struct i915_timeline *timeline)
+{
+	GEM_BUG_ON(!list_empty(&timeline->requests));
+
+	i915_syncmap_free(&timeline->sync);
+
+	list_del(&timeline->link);
+}
+
+struct i915_timeline *
+i915_timeline_create(struct drm_i915_private *i915, const char *name)
+{
+	struct i915_timeline *timeline;
+
+	timeline = kzalloc(sizeof(*timeline), GFP_KERNEL);
+	if (!timeline)
+		return ERR_PTR(-ENOMEM);
+
+	i915_timeline_init(i915, timeline, name);
+	kref_init(&timeline->kref);
+
+	return timeline;
+}
+
+void __i915_timeline_free(struct kref *kref)
+{
+	struct i915_timeline *timeline =
+		container_of(kref, typeof(*timeline), kref);
+
+	i915_timeline_fini(timeline);
+	kfree(timeline);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/mock_timeline.c"
+#include "selftests/i915_timeline.c"
+#endif
diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h
index 33e01bf6aa36..dc2a4632faa7 100644
--- a/drivers/gpu/drm/i915/i915_gem_timeline.h
+++ b/drivers/gpu/drm/i915/i915_timeline.h
@@ -22,27 +22,20 @@
  *
  */
 
-#ifndef I915_GEM_TIMELINE_H
-#define I915_GEM_TIMELINE_H
+#ifndef I915_TIMELINE_H
+#define I915_TIMELINE_H
 
 #include <linux/list.h>
+#include <linux/kref.h>
 
 #include "i915_request.h"
 #include "i915_syncmap.h"
 #include "i915_utils.h"
 
-struct i915_gem_timeline;
-
-struct intel_timeline {
+struct i915_timeline {
 	u64 fence_context;
 	u32 seqno;
 
-	/**
-	 * Count of outstanding requests, from the time they are constructed
-	 * to the moment they are retired. Loosely coupled to hardware.
-	 */
-	u32 inflight_seqnos;
-
 	spinlock_t lock;
 
 	/**
@@ -77,47 +70,57 @@ struct intel_timeline {
 	 */
 	u32 global_sync[I915_NUM_ENGINES];
 
-	struct i915_gem_timeline *common;
-};
-
-struct i915_gem_timeline {
 	struct list_head link;
-
-	struct drm_i915_private *i915;
 	const char *name;
 
-	struct intel_timeline engine[I915_NUM_ENGINES];
+	struct kref kref;
 };
 
-int i915_gem_timeline_init(struct drm_i915_private *i915,
-			   struct i915_gem_timeline *tl,
-			   const char *name);
-int i915_gem_timeline_init__global(struct drm_i915_private *i915);
-void i915_gem_timelines_park(struct drm_i915_private *i915);
-void i915_gem_timeline_fini(struct i915_gem_timeline *tl);
+void i915_timeline_init(struct drm_i915_private *i915,
+			struct i915_timeline *tl,
+			const char *name);
+void i915_timeline_fini(struct i915_timeline *tl);
+
+struct i915_timeline *
+i915_timeline_create(struct drm_i915_private *i915, const char *name);
 
-static inline int __intel_timeline_sync_set(struct intel_timeline *tl,
-					    u64 context, u32 seqno)
+static inline struct i915_timeline *
+i915_timeline_get(struct i915_timeline *timeline)
+{
+	kref_get(&timeline->kref);
+	return timeline;
+}
+
+void __i915_timeline_free(struct kref *kref);
+static inline void i915_timeline_put(struct i915_timeline *timeline)
+{
+	kref_put(&timeline->kref, __i915_timeline_free);
+}
+
+static inline int __i915_timeline_sync_set(struct i915_timeline *tl,
+					   u64 context, u32 seqno)
 {
 	return i915_syncmap_set(&tl->sync, context, seqno);
 }
 
-static inline int intel_timeline_sync_set(struct intel_timeline *tl,
-					  const struct dma_fence *fence)
+static inline int i915_timeline_sync_set(struct i915_timeline *tl,
+					 const struct dma_fence *fence)
 {
-	return __intel_timeline_sync_set(tl, fence->context, fence->seqno);
+	return __i915_timeline_sync_set(tl, fence->context, fence->seqno);
 }
 
-static inline bool __intel_timeline_sync_is_later(struct intel_timeline *tl,
-						  u64 context, u32 seqno)
+static inline bool __i915_timeline_sync_is_later(struct i915_timeline *tl,
+						 u64 context, u32 seqno)
 {
 	return i915_syncmap_is_later(&tl->sync, context, seqno);
 }
 
-static inline bool intel_timeline_sync_is_later(struct intel_timeline *tl,
-						const struct dma_fence *fence)
+static inline bool i915_timeline_sync_is_later(struct i915_timeline *tl,
+					       const struct dma_fence *fence)
 {
-	return __intel_timeline_sync_is_later(tl, fence->context, fence->seqno);
+	return __i915_timeline_sync_is_later(tl, fence->context, fence->seqno);
 }
 
+void i915_timelines_park(struct drm_i915_private *i915);
+
 #endif
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 408827bf5d96..8cc3a256f29d 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -679,45 +679,68 @@ DEFINE_EVENT(i915_request, i915_request_execute,
 	     TP_ARGS(rq)
 );
 
-DECLARE_EVENT_CLASS(i915_request_hw,
-		    TP_PROTO(struct i915_request *rq, unsigned int port),
-		    TP_ARGS(rq, port),
-
-		    TP_STRUCT__entry(
-				     __field(u32, dev)
-				     __field(u32, hw_id)
-				     __field(u32, ring)
-				     __field(u32, ctx)
-				     __field(u32, seqno)
-				     __field(u32, global_seqno)
-				     __field(u32, port)
-				    ),
-
-		    TP_fast_assign(
-				   __entry->dev = rq->i915->drm.primary->index;
-				   __entry->hw_id = rq->ctx->hw_id;
-				   __entry->ring = rq->engine->id;
-				   __entry->ctx = rq->fence.context;
-				   __entry->seqno = rq->fence.seqno;
-				   __entry->global_seqno = rq->global_seqno;
-				   __entry->port = port;
-				  ),
-
-		    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, port=%u",
-			      __entry->dev, __entry->hw_id, __entry->ring,
-			      __entry->ctx, __entry->seqno,
-			      __entry->global_seqno, __entry->port)
-);
+TRACE_EVENT(i915_request_in,
+	    TP_PROTO(struct i915_request *rq, unsigned int port),
+	    TP_ARGS(rq, port),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u32, hw_id)
+			     __field(u32, ring)
+			     __field(u32, ctx)
+			     __field(u32, seqno)
+			     __field(u32, global_seqno)
+			     __field(u32, port)
+			     __field(u32, prio)
+			    ),
+
+	    TP_fast_assign(
+			   __entry->dev = rq->i915->drm.primary->index;
+			   __entry->hw_id = rq->ctx->hw_id;
+			   __entry->ring = rq->engine->id;
+			   __entry->ctx = rq->fence.context;
+			   __entry->seqno = rq->fence.seqno;
+			   __entry->global_seqno = rq->global_seqno;
+			   __entry->prio = rq->sched.attr.priority;
+			   __entry->port = port;
+			   ),
 
-DEFINE_EVENT(i915_request_hw, i915_request_in,
-	     TP_PROTO(struct i915_request *rq, unsigned int port),
-	     TP_ARGS(rq, port)
+	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u",
+		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
+		      __entry->seqno, __entry->prio, __entry->global_seqno,
+		      __entry->port)
 );
 
-DEFINE_EVENT(i915_request, i915_request_out,
-	     TP_PROTO(struct i915_request *rq),
-	     TP_ARGS(rq)
+TRACE_EVENT(i915_request_out,
+	    TP_PROTO(struct i915_request *rq),
+	    TP_ARGS(rq),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u32, hw_id)
+			     __field(u32, ring)
+			     __field(u32, ctx)
+			     __field(u32, seqno)
+			     __field(u32, global_seqno)
+			     __field(u32, completed)
+			    ),
+
+	    TP_fast_assign(
+			   __entry->dev = rq->i915->drm.primary->index;
+			   __entry->hw_id = rq->ctx->hw_id;
+			   __entry->ring = rq->engine->id;
+			   __entry->ctx = rq->fence.context;
+			   __entry->seqno = rq->fence.seqno;
+			   __entry->global_seqno = rq->global_seqno;
+			   __entry->completed = i915_request_completed(rq);
+			   ),
+
+		    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, completed?=%u",
+			      __entry->dev, __entry->hw_id, __entry->ring,
+			      __entry->ctx, __entry->seqno,
+			      __entry->global_seqno, __entry->completed)
 );
+
 #else
 #if !defined(TRACE_HEADER_MULTI_READ)
 static inline void
@@ -811,42 +834,6 @@ DEFINE_EVENT(i915_request, i915_request_wait_end,
 	    TP_ARGS(rq)
 );
 
-TRACE_EVENT(i915_flip_request,
-	    TP_PROTO(int plane, struct drm_i915_gem_object *obj),
-
-	    TP_ARGS(plane, obj),
-
-	    TP_STRUCT__entry(
-		    __field(int, plane)
-		    __field(struct drm_i915_gem_object *, obj)
-		    ),
-
-	    TP_fast_assign(
-		    __entry->plane = plane;
-		    __entry->obj = obj;
-		    ),
-
-	    TP_printk("plane=%d, obj=%p", __entry->plane, __entry->obj)
-);
-
-TRACE_EVENT(i915_flip_complete,
-	    TP_PROTO(int plane, struct drm_i915_gem_object *obj),
-
-	    TP_ARGS(plane, obj),
-
-	    TP_STRUCT__entry(
-		    __field(int, plane)
-		    __field(struct drm_i915_gem_object *, obj)
-		    ),
-
-	    TP_fast_assign(
-		    __entry->plane = plane;
-		    __entry->obj = obj;
-		    ),
-
-	    TP_printk("plane=%d, obj=%p", __entry->plane, __entry->obj)
-);
-
 TRACE_EVENT_CONDITION(i915_reg_rw,
 	TP_PROTO(bool write, i915_reg_t reg, u64 val, int len, bool trace),
 
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 51dbfe5bb418..00165ad55fb3 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -40,8 +40,8 @@
 #undef WARN_ON_ONCE
 #define WARN_ON_ONCE(x) WARN_ONCE((x), "%s", "WARN_ON_ONCE(" __stringify(x) ")")
 
-#define MISSING_CASE(x) WARN(1, "Missing switch case (%lu) in %s\n", \
-			     (long)(x), __func__)
+#define MISSING_CASE(x) WARN(1, "Missing case (%s == %ld)\n", \
+			     __stringify(x), (long)(x))
 
 #if GCC_VERSION >= 70000
 #define add_overflows(A, B) \
@@ -120,6 +120,12 @@ static inline u64 ptr_to_u64(const void *ptr)
 
 #include <linux/list.h>
 
+static inline int list_is_first(const struct list_head *list,
+				const struct list_head *head)
+{
+	return head->next == list;
+}
+
 static inline void __list_del_many(struct list_head *head,
 				   struct list_head *first)
 {
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 4bda3bd29bf5..9324d476e0a7 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -46,8 +46,6 @@ i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq)
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
-	if (unlikely(i915_vma_is_closed(vma) && !i915_vma_is_pinned(vma)))
-		WARN_ON(i915_vma_unbind(vma));
 
 	GEM_BUG_ON(!i915_gem_object_is_active(obj));
 	if (--obj->active_count)
@@ -232,7 +230,6 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 	if (!vma)
 		vma = vma_create(obj, vm, view);
 
-	GEM_BUG_ON(!IS_ERR(vma) && i915_vma_is_closed(vma));
 	GEM_BUG_ON(!IS_ERR(vma) && i915_vma_compare(vma, vm, view));
 	GEM_BUG_ON(!IS_ERR(vma) && vma_lookup(obj, vm, view) != vma);
 	return vma;
@@ -684,13 +681,43 @@ err_unpin:
 	return ret;
 }
 
-static void i915_vma_destroy(struct i915_vma *vma)
+void i915_vma_close(struct i915_vma *vma)
+{
+	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
+
+	GEM_BUG_ON(i915_vma_is_closed(vma));
+	vma->flags |= I915_VMA_CLOSED;
+
+	/*
+	 * We defer actually closing, unbinding and destroying the VMA until
+	 * the next idle point, or if the object is freed in the meantime. By
+	 * postponing the unbind, we allow for it to be resurrected by the
+	 * client, avoiding the work required to rebind the VMA. This is
+	 * advantageous for DRI, where the client/server pass objects
+	 * between themselves, temporarily opening a local VMA to the
+	 * object, and then closing it again. The same object is then reused
+	 * on the next frame (or two, depending on the depth of the swap queue)
+	 * causing us to rebind the VMA once more. This ends up being a lot
+	 * of wasted work for the steady state.
+	 */
+	list_add_tail(&vma->closed_link, &vma->vm->i915->gt.closed_vma);
+}
+
+void i915_vma_reopen(struct i915_vma *vma)
+{
+	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
+
+	if (vma->flags & I915_VMA_CLOSED) {
+		vma->flags &= ~I915_VMA_CLOSED;
+		list_del(&vma->closed_link);
+	}
+}
+
+static void __i915_vma_destroy(struct i915_vma *vma)
 {
 	int i;
 
 	GEM_BUG_ON(vma->node.allocated);
-	GEM_BUG_ON(i915_vma_is_active(vma));
-	GEM_BUG_ON(!i915_vma_is_closed(vma));
 	GEM_BUG_ON(vma->fence);
 
 	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
@@ -699,6 +726,7 @@ static void i915_vma_destroy(struct i915_vma *vma)
 
 	list_del(&vma->obj_link);
 	list_del(&vma->vm_link);
+	rb_erase(&vma->obj_node, &vma->obj->vma_tree);
 
 	if (!i915_vma_is_ggtt(vma))
 		i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm));
@@ -706,15 +734,30 @@ static void i915_vma_destroy(struct i915_vma *vma)
 	kmem_cache_free(to_i915(vma->obj->base.dev)->vmas, vma);
 }
 
-void i915_vma_close(struct i915_vma *vma)
+void i915_vma_destroy(struct i915_vma *vma)
 {
-	GEM_BUG_ON(i915_vma_is_closed(vma));
-	vma->flags |= I915_VMA_CLOSED;
+	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
 
-	rb_erase(&vma->obj_node, &vma->obj->vma_tree);
+	GEM_BUG_ON(i915_vma_is_active(vma));
+	GEM_BUG_ON(i915_vma_is_pinned(vma));
+
+	if (i915_vma_is_closed(vma))
+		list_del(&vma->closed_link);
+
+	WARN_ON(i915_vma_unbind(vma));
+	__i915_vma_destroy(vma);
+}
+
+void i915_vma_parked(struct drm_i915_private *i915)
+{
+	struct i915_vma *vma, *next;
 
-	if (!i915_vma_is_active(vma) && !i915_vma_is_pinned(vma))
-		WARN_ON(i915_vma_unbind(vma));
+	list_for_each_entry_safe(vma, next, &i915->gt.closed_vma, closed_link) {
+		GEM_BUG_ON(!i915_vma_is_closed(vma));
+		i915_vma_destroy(vma);
+	}
+
+	GEM_BUG_ON(!list_empty(&i915->gt.closed_vma));
 }
 
 static void __i915_vma_iounmap(struct i915_vma *vma)
@@ -804,7 +847,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 		return -EBUSY;
 
 	if (!drm_mm_node_allocated(&vma->node))
-		goto destroy;
+		return 0;
 
 	GEM_BUG_ON(obj->bind_count == 0);
 	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
@@ -841,10 +884,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 
 	i915_vma_remove(vma);
 
-destroy:
-	if (unlikely(i915_vma_is_closed(vma)))
-		i915_vma_destroy(vma);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 8c5022095418..fc4294cfaa91 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -119,6 +119,8 @@ struct i915_vma {
 	/** This vma's place in the eviction list */
 	struct list_head evict_link;
 
+	struct list_head closed_link;
+
 	/**
 	 * Used for performing relocations during execbuffer insertion.
 	 */
@@ -285,6 +287,8 @@ void i915_vma_revoke_mmap(struct i915_vma *vma);
 int __must_check i915_vma_unbind(struct i915_vma *vma);
 void i915_vma_unlink_ctx(struct i915_vma *vma);
 void i915_vma_close(struct i915_vma *vma);
+void i915_vma_reopen(struct i915_vma *vma);
+void i915_vma_destroy(struct i915_vma *vma);
 
 int __i915_vma_do_pin(struct i915_vma *vma,
 		      u64 size, u64 alignment, u64 flags);
@@ -408,6 +412,8 @@ i915_vma_unpin_fence(struct i915_vma *vma)
 		__i915_vma_unpin_fence(vma);
 }
 
+void i915_vma_parked(struct drm_i915_private *i915);
+
 #define for_each_until(cond) if (cond) break; else
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index e9fb692076d7..40285d1b91b7 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -227,6 +227,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 	struct drm_atomic_state *drm_state = crtc_state->base.state;
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(drm_state);
 	int num_scalers_need;
 	int i, j;
 
@@ -304,8 +305,8 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 				continue;
 			}
 
-			plane_state = intel_atomic_get_existing_plane_state(drm_state,
-									    intel_plane);
+			plane_state = intel_atomic_get_new_plane_state(intel_state,
+								       intel_plane);
 			scaler_id = &plane_state->scaler_id;
 		}
 
@@ -328,8 +329,18 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 		}
 
 		/* set scaler mode */
-		if (IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) {
-			scaler_state->scalers[*scaler_id].mode = 0;
+		if ((INTEL_GEN(dev_priv) >= 9) &&
+		    plane_state && plane_state->base.fb &&
+		    plane_state->base.fb->format->format ==
+		    DRM_FORMAT_NV12) {
+			if (INTEL_GEN(dev_priv) == 9 &&
+			    !IS_GEMINILAKE(dev_priv) &&
+			    !IS_SKYLAKE(dev_priv))
+				scaler_state->scalers[*scaler_id].mode =
+					SKL_PS_SCALER_MODE_NV12;
+			else
+				scaler_state->scalers[*scaler_id].mode =
+					PS_SCALER_MODE_PLANAR;
 		} else if (num_scalers_need == 1 && intel_crtc->pipe != PIPE_C) {
 			/*
 			 * when only 1 scaler is in use on either pipe A or B,
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index 7481ce85746b..6d068786eb41 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -183,11 +183,16 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 	}
 
 	/* FIXME pre-g4x don't work like this */
-	if (intel_state->base.visible)
+	if (state->visible)
 		crtc_state->active_planes |= BIT(intel_plane->id);
 	else
 		crtc_state->active_planes &= ~BIT(intel_plane->id);
 
+	if (state->visible && state->fb->format->format == DRM_FORMAT_NV12)
+		crtc_state->nv12_planes |= BIT(intel_plane->id);
+	else
+		crtc_state->nv12_planes &= ~BIT(intel_plane->id);
+
 	return intel_plane_atomic_calc_changes(old_crtc_state,
 					       &crtc_state->base,
 					       old_plane_state,
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 709d6ca68074..3ea566f99450 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -729,7 +729,7 @@ static void i915_audio_component_codec_wake_override(struct device *kdev,
 	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
 	u32 tmp;
 
-	if (!IS_GEN9_BC(dev_priv))
+	if (!IS_GEN9(dev_priv))
 		return;
 
 	i915_audio_component_get_power(kdev);
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index c5c7530ba157..54270bdde100 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -530,6 +530,7 @@ parse_driver_features(struct drm_i915_private *dev_priv,
 	 */
 	if (!driver->drrs_enabled)
 		dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED;
+	dev_priv->vbt.psr.enable = driver->psr_enabled;
 }
 
 static void
@@ -1215,10 +1216,8 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 {
 	struct child_device_config *it, *child = NULL;
 	struct ddi_vbt_port_info *info = &dev_priv->vbt.ddi_port_info[port];
-	uint8_t hdmi_level_shift;
 	int i, j;
 	bool is_dvi, is_hdmi, is_dp, is_edp, is_crt;
-	uint8_t aux_channel, ddc_pin;
 	/* Each DDI port can have more than one value on the "DVO Port" field,
 	 * so look for all the possible values for each port.
 	 */
@@ -1255,9 +1254,6 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 	if (!child)
 		return;
 
-	aux_channel = child->aux_channel;
-	ddc_pin = child->ddc_pin;
-
 	is_dvi = child->device_type & DEVICE_TYPE_TMDS_DVI_SIGNALING;
 	is_dp = child->device_type & DEVICE_TYPE_DISPLAYPORT_OUTPUT;
 	is_crt = child->device_type & DEVICE_TYPE_ANALOG_OUTPUT;
@@ -1271,13 +1267,6 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 		is_hdmi = false;
 	}
 
-	if (port == PORT_A && is_dvi) {
-		DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n",
-			      is_hdmi ? "/HDMI" : "");
-		is_dvi = false;
-		is_hdmi = false;
-	}
-
 	info->supports_dvi = is_dvi;
 	info->supports_hdmi = is_hdmi;
 	info->supports_dp = is_dp;
@@ -1303,20 +1292,28 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 		DRM_DEBUG_KMS("Port %c is internal DP\n", port_name(port));
 
 	if (is_dvi) {
-		info->alternate_ddc_pin = map_ddc_pin(dev_priv, ddc_pin);
+		u8 ddc_pin;
 
-		sanitize_ddc_pin(dev_priv, port);
+		ddc_pin = map_ddc_pin(dev_priv, child->ddc_pin);
+		if (intel_gmbus_is_valid_pin(dev_priv, ddc_pin)) {
+			info->alternate_ddc_pin = ddc_pin;
+			sanitize_ddc_pin(dev_priv, port);
+		} else {
+			DRM_DEBUG_KMS("Port %c has invalid DDC pin %d, "
+				      "sticking to defaults\n",
+				      port_name(port), ddc_pin);
+		}
 	}
 
 	if (is_dp) {
-		info->alternate_aux_channel = aux_channel;
+		info->alternate_aux_channel = child->aux_channel;
 
 		sanitize_aux_ch(dev_priv, port);
 	}
 
 	if (bdb_version >= 158) {
 		/* The VBT HDMI level shift values match the table we have. */
-		hdmi_level_shift = child->hdmi_level_shifter_value;
+		u8 hdmi_level_shift = child->hdmi_level_shifter_value;
 		DRM_DEBUG_KMS("VBT HDMI level shift for port %c: %d\n",
 			      port_name(port),
 			      hdmi_level_shift);
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 1f79e7a47433..18e643df523e 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -82,7 +82,7 @@ static unsigned long wait_timeout(void)
 
 static noinline void missed_breadcrumb(struct intel_engine_cs *engine)
 {
-	if (drm_debug & DRM_UT_DRIVER) {
+	if (GEM_SHOW_DEBUG()) {
 		struct drm_printer p = drm_debug_printer(__func__);
 
 		intel_engine_dump(engine, &p,
@@ -130,11 +130,12 @@ static void intel_breadcrumbs_hangcheck(struct timer_list *t)
 
 static void intel_breadcrumbs_fake_irq(struct timer_list *t)
 {
-	struct intel_engine_cs *engine = from_timer(engine, t,
-						    breadcrumbs.fake_irq);
+	struct intel_engine_cs *engine =
+		from_timer(engine, t, breadcrumbs.fake_irq);
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
 
-	/* The timer persists in case we cannot enable interrupts,
+	/*
+	 * The timer persists in case we cannot enable interrupts,
 	 * or if we have previously seen seqno/interrupt incoherency
 	 * ("missed interrupt" syndrome, better known as a "missed breadcrumb").
 	 * Here the worker will wake up every jiffie in order to kick the
@@ -148,6 +149,12 @@ static void intel_breadcrumbs_fake_irq(struct timer_list *t)
 	if (!b->irq_armed)
 		return;
 
+	/* If the user has disabled the fake-irq, restore the hangchecking */
+	if (!test_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings)) {
+		mod_timer(&b->hangcheck, wait_timeout());
+		return;
+	}
+
 	mod_timer(&b->fake_irq, jiffies + 1);
 }
 
@@ -730,10 +737,11 @@ static void insert_signal(struct intel_breadcrumbs *b,
 	list_add(&request->signaling.link, &iter->signaling.link);
 }
 
-void intel_engine_enable_signaling(struct i915_request *request, bool wakeup)
+bool intel_engine_enable_signaling(struct i915_request *request, bool wakeup)
 {
 	struct intel_engine_cs *engine = request->engine;
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct intel_wait *wait = &request->signaling.wait;
 	u32 seqno;
 
 	/*
@@ -750,12 +758,12 @@ void intel_engine_enable_signaling(struct i915_request *request, bool wakeup)
 
 	seqno = i915_request_global_seqno(request);
 	if (!seqno) /* will be enabled later upon execution */
-		return;
+		return true;
 
-	GEM_BUG_ON(request->signaling.wait.seqno);
-	request->signaling.wait.tsk = b->signaler;
-	request->signaling.wait.request = request;
-	request->signaling.wait.seqno = seqno;
+	GEM_BUG_ON(wait->seqno);
+	wait->tsk = b->signaler;
+	wait->request = request;
+	wait->seqno = seqno;
 
 	/*
 	 * Add ourselves into the list of waiters, but registering our
@@ -768,11 +776,15 @@ void intel_engine_enable_signaling(struct i915_request *request, bool wakeup)
 	 */
 	spin_lock(&b->rb_lock);
 	insert_signal(b, request, seqno);
-	wakeup &= __intel_engine_add_wait(engine, &request->signaling.wait);
+	wakeup &= __intel_engine_add_wait(engine, wait);
 	spin_unlock(&b->rb_lock);
 
-	if (wakeup)
+	if (wakeup) {
 		wake_up_process(b->signaler);
+		return !intel_wait_complete(wait);
+	}
+
+	return true;
 }
 
 void intel_engine_cancel_signaling(struct i915_request *request)
@@ -826,8 +838,8 @@ static void cancel_fake_irq(struct intel_engine_cs *engine)
 {
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
 
+	del_timer_sync(&b->fake_irq); /* may queue b->hangcheck */
 	del_timer_sync(&b->hangcheck);
-	del_timer_sync(&b->fake_irq);
 	clear_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings);
 }
 
@@ -835,15 +847,22 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
 {
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
 
-	cancel_fake_irq(engine);
 	spin_lock_irq(&b->irq_lock);
 
+	/*
+	 * Leave the fake_irq timer enabled (if it is running), but clear the
+	 * bit so that it turns itself off on its next wake up and goes back
+	 * to the long hangcheck interval if still required.
+	 */
+	clear_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings);
+
 	if (b->irq_enabled)
 		irq_enable(engine);
 	else
 		irq_disable(engine);
 
-	/* We set the IRQ_BREADCRUMB bit when we enable the irq presuming the
+	/*
+	 * We set the IRQ_BREADCRUMB bit when we enable the irq presuming the
 	 * GPU is active and may have already executed the MI_USER_INTERRUPT
 	 * before the CPU is ready to receive. However, the engine is currently
 	 * idle (we haven't started it yet), there is no possibility for a
@@ -852,9 +871,6 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
 	 */
 	clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
 
-	if (b->irq_armed)
-		enable_fake_irq(b);
-
 	spin_unlock_irq(&b->irq_lock);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index fc8b2c6e3508..704ddb4d3ca7 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -2140,10 +2140,22 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 		}
 	}
 
-	/* According to BSpec, "The CD clock frequency must be at least twice
+	/*
+	 * According to BSpec, "The CD clock frequency must be at least twice
 	 * the frequency of the Azalia BCLK." and BCLK is 96 MHz by default.
+	 *
+	 * FIXME: Check the actual, not default, BCLK being used.
+	 *
+	 * FIXME: This does not depend on ->has_audio because the higher CDCLK
+	 * is required for audio probe, also when there are no audio capable
+	 * displays connected at probe time. This leads to unnecessarily high
+	 * CDCLK when audio is not required.
+	 *
+	 * FIXME: This limit is only applied when there are displays connected
+	 * at probe time. If we probe without displays, we'll still end up using
+	 * the platform minimum CDCLK, failing audio probe.
 	 */
-	if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9)
+	if (INTEL_GEN(dev_priv) >= 9)
 		min_cdclk = max(2 * 96000, min_cdclk);
 
 	/*
@@ -2290,9 +2302,44 @@ static int bdw_modeset_calc_cdclk(struct drm_atomic_state *state)
 	return 0;
 }
 
+static int skl_dpll0_vco(struct intel_atomic_state *intel_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(intel_state->base.dev);
+	struct intel_crtc *crtc;
+	struct intel_crtc_state *crtc_state;
+	int vco, i;
+
+	vco = intel_state->cdclk.logical.vco;
+	if (!vco)
+		vco = dev_priv->skl_preferred_vco_freq;
+
+	for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
+		if (!crtc_state->base.enable)
+			continue;
+
+		if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
+			continue;
+
+		/*
+		 * DPLL0 VCO may need to be adjusted to get the correct
+		 * clock for eDP. This will affect cdclk as well.
+		 */
+		switch (crtc_state->port_clock / 2) {
+		case 108000:
+		case 216000:
+			vco = 8640000;
+			break;
+		default:
+			vco = 8100000;
+			break;
+		}
+	}
+
+	return vco;
+}
+
 static int skl_modeset_calc_cdclk(struct drm_atomic_state *state)
 {
-	struct drm_i915_private *dev_priv = to_i915(state->dev);
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
 	int min_cdclk, cdclk, vco;
 
@@ -2300,9 +2347,7 @@ static int skl_modeset_calc_cdclk(struct drm_atomic_state *state)
 	if (min_cdclk < 0)
 		return min_cdclk;
 
-	vco = intel_state->cdclk.logical.vco;
-	if (!vco)
-		vco = dev_priv->skl_preferred_vco_freq;
+	vco = skl_dpll0_vco(intel_state);
 
 	/*
 	 * FIXME should also account for plane ratio
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index c0a8805b277f..de0e22322c76 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -748,6 +748,11 @@ intel_crt_detect(struct drm_connector *connector,
 		      connector->base.id, connector->name,
 		      force);
 
+	if (i915_modparams.load_detect_test) {
+		intel_display_power_get(dev_priv, intel_encoder->power_domain);
+		goto load_detect;
+	}
+
 	/* Skip machines without VGA that falsely report hotplug events */
 	if (dmi_check_system(intel_spurious_crt_detect))
 		return connector_status_disconnected;
@@ -776,11 +781,12 @@ intel_crt_detect(struct drm_connector *connector,
 	 * broken monitor (without edid) to work behind a broken kvm (that fails
 	 * to have the right resistors for HP detection) needs to fix this up.
 	 * For now just bail out. */
-	if (I915_HAS_HOTPLUG(dev_priv) && !i915_modparams.load_detect_test) {
+	if (I915_HAS_HOTPLUG(dev_priv)) {
 		status = connector_status_disconnected;
 		goto out;
 	}
 
+load_detect:
 	if (!force) {
 		status = connector->status;
 		goto out;
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 41e6c75a7f3c..cf9b600cca79 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -35,6 +35,7 @@
  */
 
 #define I915_CSR_GLK "i915/glk_dmc_ver1_04.bin"
+MODULE_FIRMWARE(I915_CSR_GLK);
 #define GLK_CSR_VERSION_REQUIRED	CSR_VERSION(1, 4)
 
 #define I915_CSR_CNL "i915/cnl_dmc_ver1_07.bin"
@@ -297,7 +298,10 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
 
 	csr->version = css_header->version;
 
-	if (IS_CANNONLAKE(dev_priv)) {
+	if (csr->fw_path == i915_modparams.dmc_firmware_path) {
+		/* Bypass version check for firmware override. */
+		required_version = csr->version;
+	} else if (IS_CANNONLAKE(dev_priv)) {
 		required_version = CNL_CSR_VERSION_REQUIRED;
 	} else if (IS_GEMINILAKE(dev_priv)) {
 		required_version = GLK_CSR_VERSION_REQUIRED;
@@ -452,7 +456,9 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv)
 	if (!HAS_CSR(dev_priv))
 		return;
 
-	if (IS_CANNONLAKE(dev_priv))
+	if (i915_modparams.dmc_firmware_path)
+		csr->fw_path = i915_modparams.dmc_firmware_path;
+	else if (IS_CANNONLAKE(dev_priv))
 		csr->fw_path = I915_CSR_CNL;
 	else if (IS_GEMINILAKE(dev_priv))
 		csr->fw_path = I915_CSR_GLK;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 8c2d778560f0..b98ac0541f19 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -493,6 +493,125 @@ static const struct cnl_ddi_buf_trans cnl_ddi_translations_edp_1_05V[] = {
 	{ 0x2, 0x7F, 0x3F, 0x00, 0x00 },	/* 400   400      0.0   */
 };
 
+struct icl_combo_phy_ddi_buf_trans {
+	u32 dw2_swing_select;
+	u32 dw2_swing_scalar;
+	u32 dw4_scaling;
+};
+
+/* Voltage Swing Programming for VccIO 0.85V for DP */
+static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_85V[] = {
+				/* Voltage mV  db    */
+	{ 0x2, 0x98, 0x0018 },	/* 400         0.0   */
+	{ 0x2, 0x98, 0x3015 },	/* 400         3.5   */
+	{ 0x2, 0x98, 0x6012 },	/* 400         6.0   */
+	{ 0x2, 0x98, 0x900F },	/* 400         9.5   */
+	{ 0xB, 0x70, 0x0018 },	/* 600         0.0   */
+	{ 0xB, 0x70, 0x3015 },	/* 600         3.5   */
+	{ 0xB, 0x70, 0x6012 },	/* 600         6.0   */
+	{ 0x5, 0x00, 0x0018 },	/* 800         0.0   */
+	{ 0x5, 0x00, 0x3015 },	/* 800         3.5   */
+	{ 0x6, 0x98, 0x0018 },	/* 1200        0.0   */
+};
+
+/* FIXME - After table is updated in Bspec */
+/* Voltage Swing Programming for VccIO 0.85V for eDP */
+static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_85V[] = {
+				/* Voltage mV  db    */
+	{ 0x0, 0x00, 0x00 },	/* 200         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 200         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 200         4.0   */
+	{ 0x0, 0x00, 0x00 },	/* 200         6.0   */
+	{ 0x0, 0x00, 0x00 },	/* 250         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 250         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 250         4.0   */
+	{ 0x0, 0x00, 0x00 },	/* 300         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 300         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 350         0.0   */
+};
+
+/* Voltage Swing Programming for VccIO 0.95V for DP */
+static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_95V[] = {
+				/* Voltage mV  db    */
+	{ 0x2, 0x98, 0x0018 },	/* 400         0.0   */
+	{ 0x2, 0x98, 0x3015 },	/* 400         3.5   */
+	{ 0x2, 0x98, 0x6012 },	/* 400         6.0   */
+	{ 0x2, 0x98, 0x900F },	/* 400         9.5   */
+	{ 0x4, 0x98, 0x0018 },	/* 600         0.0   */
+	{ 0x4, 0x98, 0x3015 },	/* 600         3.5   */
+	{ 0x4, 0x98, 0x6012 },	/* 600         6.0   */
+	{ 0x5, 0x76, 0x0018 },	/* 800         0.0   */
+	{ 0x5, 0x76, 0x3015 },	/* 800         3.5   */
+	{ 0x6, 0x98, 0x0018 },	/* 1200        0.0   */
+};
+
+/* FIXME - After table is updated in Bspec */
+/* Voltage Swing Programming for VccIO 0.95V for eDP */
+static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_95V[] = {
+				/* Voltage mV  db    */
+	{ 0x0, 0x00, 0x00 },	/* 200         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 200         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 200         4.0   */
+	{ 0x0, 0x00, 0x00 },	/* 200         6.0   */
+	{ 0x0, 0x00, 0x00 },	/* 250         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 250         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 250         4.0   */
+	{ 0x0, 0x00, 0x00 },	/* 300         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 300         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 350         0.0   */
+};
+
+/* Voltage Swing Programming for VccIO 1.05V for DP */
+static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_1_05V[] = {
+				/* Voltage mV  db    */
+	{ 0x2, 0x98, 0x0018 },	/* 400         0.0   */
+	{ 0x2, 0x98, 0x3015 },	/* 400         3.5   */
+	{ 0x2, 0x98, 0x6012 },	/* 400         6.0   */
+	{ 0x2, 0x98, 0x900F },	/* 400         9.5   */
+	{ 0x4, 0x98, 0x0018 },	/* 600         0.0   */
+	{ 0x4, 0x98, 0x3015 },	/* 600         3.5   */
+	{ 0x4, 0x98, 0x6012 },	/* 600         6.0   */
+	{ 0x5, 0x71, 0x0018 },	/* 800         0.0   */
+	{ 0x5, 0x71, 0x3015 },	/* 800         3.5   */
+	{ 0x6, 0x98, 0x0018 },	/* 1200        0.0   */
+};
+
+/* FIXME - After table is updated in Bspec */
+/* Voltage Swing Programming for VccIO 1.05V for eDP */
+static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_1_05V[] = {
+				/* Voltage mV  db    */
+	{ 0x0, 0x00, 0x00 },	/* 200         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 200         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 200         4.0   */
+	{ 0x0, 0x00, 0x00 },	/* 200         6.0   */
+	{ 0x0, 0x00, 0x00 },	/* 250         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 250         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 250         4.0   */
+	{ 0x0, 0x00, 0x00 },	/* 300         0.0   */
+	{ 0x0, 0x00, 0x00 },	/* 300         1.5   */
+	{ 0x0, 0x00, 0x00 },	/* 350         0.0   */
+};
+
+struct icl_mg_phy_ddi_buf_trans {
+	u32 cri_txdeemph_override_5_0;
+	u32 cri_txdeemph_override_11_6;
+	u32 cri_txdeemph_override_17_12;
+};
+
+static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations[] = {
+				/* Voltage swing  pre-emphasis */
+	{ 0x0, 0x1B, 0x00 },	/* 0              0   */
+	{ 0x0, 0x23, 0x08 },	/* 0              1   */
+	{ 0x0, 0x2D, 0x12 },	/* 0              2   */
+	{ 0x0, 0x00, 0x00 },	/* 0              3   */
+	{ 0x0, 0x23, 0x00 },	/* 1              0   */
+	{ 0x0, 0x2B, 0x09 },	/* 1              1   */
+	{ 0x0, 0x2E, 0x11 },	/* 1              2   */
+	{ 0x0, 0x2F, 0x00 },	/* 2              0   */
+	{ 0x0, 0x33, 0x0C },	/* 2              1   */
+	{ 0x0, 0x00, 0x00 },	/* 3              0   */
+};
+
 static const struct ddi_buf_trans *
 bdw_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries)
 {
@@ -751,6 +870,45 @@ cnl_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries)
 	}
 }
 
+static const struct icl_combo_phy_ddi_buf_trans *
+icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, enum port port,
+			int type, int *n_entries)
+{
+	u32 voltage = I915_READ(ICL_PORT_COMP_DW3(port)) & VOLTAGE_INFO_MASK;
+
+	if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) {
+		switch (voltage) {
+		case VOLTAGE_INFO_0_85V:
+			*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_85V);
+			return icl_combo_phy_ddi_translations_edp_0_85V;
+		case VOLTAGE_INFO_0_95V:
+			*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_95V);
+			return icl_combo_phy_ddi_translations_edp_0_95V;
+		case VOLTAGE_INFO_1_05V:
+			*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_1_05V);
+			return icl_combo_phy_ddi_translations_edp_1_05V;
+		default:
+			MISSING_CASE(voltage);
+			return NULL;
+		}
+	} else {
+		switch (voltage) {
+		case VOLTAGE_INFO_0_85V:
+			*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_85V);
+			return icl_combo_phy_ddi_translations_dp_hdmi_0_85V;
+		case VOLTAGE_INFO_0_95V:
+			*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_95V);
+			return icl_combo_phy_ddi_translations_dp_hdmi_0_95V;
+		case VOLTAGE_INFO_1_05V:
+			*n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_1_05V);
+			return icl_combo_phy_ddi_translations_dp_hdmi_1_05V;
+		default:
+			MISSING_CASE(voltage);
+			return NULL;
+		}
+	}
+}
+
 static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port)
 {
 	int n_entries, level, default_entry;
@@ -875,7 +1033,7 @@ static void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
 
 static uint32_t hsw_pll_to_ddi_pll_sel(const struct intel_shared_dpll *pll)
 {
-	switch (pll->id) {
+	switch (pll->info->id) {
 	case DPLL_ID_WRPLL1:
 		return PORT_CLK_SEL_WRPLL1;
 	case DPLL_ID_WRPLL2:
@@ -889,11 +1047,30 @@ static uint32_t hsw_pll_to_ddi_pll_sel(const struct intel_shared_dpll *pll)
 	case DPLL_ID_LCPLL_2700:
 		return PORT_CLK_SEL_LCPLL_2700;
 	default:
-		MISSING_CASE(pll->id);
+		MISSING_CASE(pll->info->id);
 		return PORT_CLK_SEL_NONE;
 	}
 }
 
+static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder,
+				       const struct intel_shared_dpll *pll)
+{
+	const enum intel_dpll_id id = pll->info->id;
+
+	switch (id) {
+	default:
+		MISSING_CASE(id);
+	case DPLL_ID_ICL_DPLL0:
+	case DPLL_ID_ICL_DPLL1:
+		return DDI_CLK_SEL_NONE;
+	case DPLL_ID_ICL_MGPLL1:
+	case DPLL_ID_ICL_MGPLL2:
+	case DPLL_ID_ICL_MGPLL3:
+	case DPLL_ID_ICL_MGPLL4:
+		return DDI_CLK_SEL_MG;
+	}
+}
+
 /* Starting with Haswell, different DDI ports can work in FDI mode for
  * connection to the PCH-located connectors. For this, it is necessary to train
  * both the DDI port and PCH receiver for the desired DDI buffer settings.
@@ -1906,7 +2083,13 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 	enum port port = encoder->port;
 	int n_entries;
 
-	if (IS_CANNONLAKE(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		if (port == PORT_A || port == PORT_B)
+			icl_get_combo_buf_trans(dev_priv, port, encoder->type,
+						&n_entries);
+		else
+			n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations);
+	} else if (IS_CANNONLAKE(dev_priv)) {
 		if (encoder->type == INTEL_OUTPUT_EDP)
 			cnl_get_buf_trans_edp(dev_priv, &n_entries);
 		else
@@ -2063,6 +2246,146 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder,
 	I915_WRITE(CNL_PORT_TX_DW5_GRP(port), val);
 }
 
+static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv,
+					 u32 level, enum port port, int type)
+{
+	const struct icl_combo_phy_ddi_buf_trans *ddi_translations = NULL;
+	u32 n_entries, val;
+	int ln;
+
+	ddi_translations = icl_get_combo_buf_trans(dev_priv, port, type,
+						   &n_entries);
+	if (!ddi_translations)
+		return;
+
+	if (level >= n_entries) {
+		DRM_DEBUG_KMS("DDI translation not found for level %d. Using %d instead.", level, n_entries - 1);
+		level = n_entries - 1;
+	}
+
+	/* Set PORT_TX_DW5 Rterm Sel to 110b. */
+	val = I915_READ(ICL_PORT_TX_DW5_LN0(port));
+	val &= ~RTERM_SELECT_MASK;
+	val |= RTERM_SELECT(0x6);
+	I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val);
+
+	/* Program PORT_TX_DW5 */
+	val = I915_READ(ICL_PORT_TX_DW5_LN0(port));
+	/* Set DisableTap2 and DisableTap3 if MIPI DSI
+	 * Clear DisableTap2 and DisableTap3 for all other Ports
+	 */
+	if (type == INTEL_OUTPUT_DSI) {
+		val |= TAP2_DISABLE;
+		val |= TAP3_DISABLE;
+	} else {
+		val &= ~TAP2_DISABLE;
+		val &= ~TAP3_DISABLE;
+	}
+	I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val);
+
+	/* Program PORT_TX_DW2 */
+	val = I915_READ(ICL_PORT_TX_DW2_LN0(port));
+	val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK |
+		 RCOMP_SCALAR_MASK);
+	val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_select);
+	val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_select);
+	/* Program Rcomp scalar for every table entry */
+	val |= RCOMP_SCALAR(ddi_translations[level].dw2_swing_scalar);
+	I915_WRITE(ICL_PORT_TX_DW2_GRP(port), val);
+
+	/* Program PORT_TX_DW4 */
+	/* We cannot write to GRP. It would overwrite individual loadgen. */
+	for (ln = 0; ln <= 3; ln++) {
+		val = I915_READ(ICL_PORT_TX_DW4_LN(port, ln));
+		val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK |
+			 CURSOR_COEFF_MASK);
+		val |= ddi_translations[level].dw4_scaling;
+		I915_WRITE(ICL_PORT_TX_DW4_LN(port, ln), val);
+	}
+}
+
+static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
+					      u32 level,
+					      enum intel_output_type type)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum port port = encoder->port;
+	int width = 0;
+	int rate = 0;
+	u32 val;
+	int ln = 0;
+
+	if (type == INTEL_OUTPUT_HDMI) {
+		width = 4;
+		/* Rate is always < than 6GHz for HDMI */
+	} else {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+
+		width = intel_dp->lane_count;
+		rate = intel_dp->link_rate;
+	}
+
+	/*
+	 * 1. If port type is eDP or DP,
+	 * set PORT_PCS_DW1 cmnkeeper_enable to 1b,
+	 * else clear to 0b.
+	 */
+	val = I915_READ(ICL_PORT_PCS_DW1_LN0(port));
+	if (type == INTEL_OUTPUT_HDMI)
+		val &= ~COMMON_KEEPER_EN;
+	else
+		val |= COMMON_KEEPER_EN;
+	I915_WRITE(ICL_PORT_PCS_DW1_GRP(port), val);
+
+	/* 2. Program loadgen select */
+	/*
+	 * Program PORT_TX_DW4_LN depending on Bit rate and used lanes
+	 * <= 6 GHz and 4 lanes (LN0=0, LN1=1, LN2=1, LN3=1)
+	 * <= 6 GHz and 1,2 lanes (LN0=0, LN1=1, LN2=1, LN3=0)
+	 * > 6 GHz (LN0=0, LN1=0, LN2=0, LN3=0)
+	 */
+	for (ln = 0; ln <= 3; ln++) {
+		val = I915_READ(ICL_PORT_TX_DW4_LN(port, ln));
+		val &= ~LOADGEN_SELECT;
+
+		if ((rate <= 600000 && width == 4 && ln >= 1) ||
+		    (rate <= 600000 && width < 4 && (ln == 1 || ln == 2))) {
+			val |= LOADGEN_SELECT;
+		}
+		I915_WRITE(ICL_PORT_TX_DW4_LN(port, ln), val);
+	}
+
+	/* 3. Set PORT_CL_DW5 SUS Clock Config to 11b */
+	val = I915_READ(ICL_PORT_CL_DW5(port));
+	val |= SUS_CLOCK_CONFIG;
+	I915_WRITE(ICL_PORT_CL_DW5(port), val);
+
+	/* 4. Clear training enable to change swing values */
+	val = I915_READ(ICL_PORT_TX_DW5_LN0(port));
+	val &= ~TX_TRAINING_EN;
+	I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val);
+
+	/* 5. Program swing and de-emphasis */
+	icl_ddi_combo_vswing_program(dev_priv, level, port, type);
+
+	/* 6. Set training enable to trigger update */
+	val = I915_READ(ICL_PORT_TX_DW5_LN0(port));
+	val |= TX_TRAINING_EN;
+	I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val);
+}
+
+static void icl_ddi_vswing_sequence(struct intel_encoder *encoder, u32 level,
+				    enum intel_output_type type)
+{
+	enum port port = encoder->port;
+
+	if (port == PORT_A || port == PORT_B)
+		icl_combo_phy_ddi_vswing_sequence(encoder, level, type);
+	else
+		/* Not Implemented Yet */
+		WARN_ON(1);
+}
+
 static uint32_t translate_signal_level(int signal_levels)
 {
 	int i;
@@ -2094,7 +2417,9 @@ u32 bxt_signal_levels(struct intel_dp *intel_dp)
 	struct intel_encoder *encoder = &dport->base;
 	int level = intel_ddi_dp_level(intel_dp);
 
-	if (IS_CANNONLAKE(dev_priv))
+	if (IS_ICELAKE(dev_priv))
+		icl_ddi_vswing_sequence(encoder, level, encoder->type);
+	else if (IS_CANNONLAKE(dev_priv))
 		cnl_ddi_vswing_sequence(encoder, level, encoder->type);
 	else
 		bxt_ddi_vswing_sequence(encoder, level, encoder->type);
@@ -2115,6 +2440,69 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp)
 	return DDI_BUF_TRANS_SELECT(level);
 }
 
+void icl_map_plls_to_ports(struct drm_crtc *crtc,
+			   struct intel_crtc_state *crtc_state,
+			   struct drm_atomic_state *old_state)
+{
+	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+	struct drm_connector_state *conn_state;
+	struct drm_connector *conn;
+	int i;
+
+	for_each_new_connector_in_state(old_state, conn, conn_state, i) {
+		struct intel_encoder *encoder =
+			to_intel_encoder(conn_state->best_encoder);
+		enum port port = encoder->port;
+		uint32_t val;
+
+		if (conn_state->crtc != crtc)
+			continue;
+
+		mutex_lock(&dev_priv->dpll_lock);
+
+		val = I915_READ(DPCLKA_CFGCR0_ICL);
+		WARN_ON((val & DPCLKA_CFGCR0_DDI_CLK_OFF(port)) == 0);
+
+		if (port == PORT_A || port == PORT_B) {
+			val &= ~DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port);
+			val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port);
+			I915_WRITE(DPCLKA_CFGCR0_ICL, val);
+			POSTING_READ(DPCLKA_CFGCR0_ICL);
+		}
+
+		val &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port);
+		I915_WRITE(DPCLKA_CFGCR0_ICL, val);
+
+		mutex_unlock(&dev_priv->dpll_lock);
+	}
+}
+
+void icl_unmap_plls_to_ports(struct drm_crtc *crtc,
+			     struct intel_crtc_state *crtc_state,
+			     struct drm_atomic_state *old_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+	struct drm_connector_state *old_conn_state;
+	struct drm_connector *conn;
+	int i;
+
+	for_each_old_connector_in_state(old_state, conn, old_conn_state, i) {
+		struct intel_encoder *encoder =
+			to_intel_encoder(old_conn_state->best_encoder);
+		enum port port = encoder->port;
+
+		if (old_conn_state->crtc != crtc)
+			continue;
+
+		mutex_lock(&dev_priv->dpll_lock);
+		I915_WRITE(DPCLKA_CFGCR0_ICL,
+			   I915_READ(DPCLKA_CFGCR0_ICL) |
+			   DPCLKA_CFGCR0_DDI_CLK_OFF(port));
+		mutex_unlock(&dev_priv->dpll_lock);
+	}
+}
+
 static void intel_ddi_clk_select(struct intel_encoder *encoder,
 				 const struct intel_shared_dpll *pll)
 {
@@ -2127,11 +2515,15 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder,
 
 	mutex_lock(&dev_priv->dpll_lock);
 
-	if (IS_CANNONLAKE(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		if (port >= PORT_C)
+			I915_WRITE(DDI_CLK_SEL(port),
+				   icl_pll_to_ddi_pll_sel(encoder, pll));
+	} else if (IS_CANNONLAKE(dev_priv)) {
 		/* Configure DPCLKA_CFGCR0 to map the DPLL to the DDI. */
 		val = I915_READ(DPCLKA_CFGCR0);
 		val &= ~DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port);
-		val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->id, port);
+		val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port);
 		I915_WRITE(DPCLKA_CFGCR0, val);
 
 		/*
@@ -2148,7 +2540,7 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder,
 
 		val &= ~(DPLL_CTRL2_DDI_CLK_OFF(port) |
 			 DPLL_CTRL2_DDI_CLK_SEL_MASK(port));
-		val |= (DPLL_CTRL2_DDI_CLK_SEL(pll->id, port) |
+		val |= (DPLL_CTRL2_DDI_CLK_SEL(pll->info->id, port) |
 			DPLL_CTRL2_DDI_SEL_OVERRIDE(port));
 
 		I915_WRITE(DPLL_CTRL2, val);
@@ -2165,14 +2557,18 @@ static void intel_ddi_clk_disable(struct intel_encoder *encoder)
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 
-	if (IS_CANNONLAKE(dev_priv))
+	if (IS_ICELAKE(dev_priv)) {
+		if (port >= PORT_C)
+			I915_WRITE(DDI_CLK_SEL(port), DDI_CLK_SEL_NONE);
+	} else if (IS_CANNONLAKE(dev_priv)) {
 		I915_WRITE(DPCLKA_CFGCR0, I915_READ(DPCLKA_CFGCR0) |
 			   DPCLKA_CFGCR0_DDI_CLK_OFF(port));
-	else if (IS_GEN9_BC(dev_priv))
+	} else if (IS_GEN9_BC(dev_priv)) {
 		I915_WRITE(DPLL_CTRL2, I915_READ(DPLL_CTRL2) |
 			   DPLL_CTRL2_DDI_CLK_OFF(port));
-	else if (INTEL_GEN(dev_priv) < 9)
+	} else if (INTEL_GEN(dev_priv) < 9) {
 		I915_WRITE(PORT_CLK_SEL(port), PORT_CLK_SEL_NONE);
+	}
 }
 
 static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
@@ -2197,7 +2593,9 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 
 	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
-	if (IS_CANNONLAKE(dev_priv))
+	if (IS_ICELAKE(dev_priv))
+		icl_ddi_vswing_sequence(encoder, level, encoder->type);
+	else if (IS_CANNONLAKE(dev_priv))
 		cnl_ddi_vswing_sequence(encoder, level, encoder->type);
 	else if (IS_GEN9_LP(dev_priv))
 		bxt_ddi_vswing_sequence(encoder, level, encoder->type);
@@ -2205,7 +2603,8 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 		intel_prepare_dp_ddi_buffers(encoder, crtc_state);
 
 	intel_ddi_init_dp_buf_reg(encoder);
-	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+	if (!is_mst)
+		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 	intel_dp_start_link_train(intel_dp);
 	if (port != PORT_A || INTEL_GEN(dev_priv) >= 9)
 		intel_dp_stop_link_train(intel_dp);
@@ -2227,7 +2626,9 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 
 	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
-	if (IS_CANNONLAKE(dev_priv))
+	if (IS_ICELAKE(dev_priv))
+		icl_ddi_vswing_sequence(encoder, level, INTEL_OUTPUT_HDMI);
+	else if (IS_CANNONLAKE(dev_priv))
 		cnl_ddi_vswing_sequence(encoder, level, INTEL_OUTPUT_HDMI);
 	else if (IS_GEN9_LP(dev_priv))
 		bxt_ddi_vswing_sequence(encoder, level, INTEL_OUTPUT_HDMI);
@@ -2303,12 +2704,15 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
 	struct intel_dp *intel_dp = &dig_port->dp;
+	bool is_mst = intel_crtc_has_type(old_crtc_state,
+					  INTEL_OUTPUT_DP_MST);
 
 	/*
 	 * Power down sink before disabling the port, otherwise we end
 	 * up getting interrupts from the sink on detecting link loss.
 	 */
-	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+	if (!is_mst)
+		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 
 	intel_disable_ddi_buf(encoder);
 
@@ -2424,12 +2828,14 @@ static void intel_enable_ddi_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct drm_connector *connector = conn_state->connector;
 	enum port port = encoder->port;
 
-	intel_hdmi_handle_sink_scrambling(encoder,
-					  conn_state->connector,
-					  crtc_state->hdmi_high_tmds_clock_ratio,
-					  crtc_state->hdmi_scrambling);
+	if (!intel_hdmi_handle_sink_scrambling(encoder, connector,
+					       crtc_state->hdmi_high_tmds_clock_ratio,
+					       crtc_state->hdmi_scrambling))
+		DRM_ERROR("[CONNECTOR:%d:%s] Failed to configure sink scrambling/TMDS bit clock ratio\n",
+			  connector->base.id, connector->name);
 
 	/* Display WA #1143: skl,kbl,cfl */
 	if (IS_GEN9_BC(dev_priv)) {
@@ -2520,13 +2926,16 @@ static void intel_disable_ddi_hdmi(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *old_crtc_state,
 				   const struct drm_connector_state *old_conn_state)
 {
+	struct drm_connector *connector = old_conn_state->connector;
+
 	if (old_crtc_state->has_audio)
 		intel_audio_codec_disable(encoder,
 					  old_crtc_state, old_conn_state);
 
-	intel_hdmi_handle_sink_scrambling(encoder,
-					  old_conn_state->connector,
-					  false, false);
+	if (!intel_hdmi_handle_sink_scrambling(encoder, connector,
+					       false, false))
+		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Failed to reset sink scrambling/TMDS bit clock ratio\n",
+			      connector->base.id, connector->name);
 }
 
 static void intel_disable_ddi(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 3dd350f7b8e6..0fd13df424cf 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -83,11 +83,11 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 {
 	int s;
 
-	drm_printf(p, "slice mask: %04x\n", sseu->slice_mask);
-	drm_printf(p, "slice total: %u\n", hweight8(sseu->slice_mask));
+	drm_printf(p, "slice total: %u, mask=%04x\n",
+		   hweight8(sseu->slice_mask), sseu->slice_mask);
 	drm_printf(p, "subslice total: %u\n", sseu_subslice_total(sseu));
-	for (s = 0; s < ARRAY_SIZE(sseu->subslice_mask); s++) {
-		drm_printf(p, "slice%d %u subslices mask=%04x\n",
+	for (s = 0; s < sseu->max_slices; s++) {
+		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
 			   s, hweight8(sseu->subslice_mask[s]),
 			   sseu->subslice_mask[s]);
 	}
@@ -158,6 +158,45 @@ static u16 compute_eu_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
+static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
+{
+	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
+	u8 s_en;
+	u32 ss_en, ss_en_mask;
+	u8 eu_en;
+	int s;
+
+	sseu->max_slices = 1;
+	sseu->max_subslices = 8;
+	sseu->max_eus_per_subslice = 8;
+
+	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
+	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
+	ss_en_mask = BIT(sseu->max_subslices) - 1;
+	eu_en = ~(I915_READ(GEN11_EU_DISABLE) & GEN11_EU_DIS_MASK);
+
+	for (s = 0; s < sseu->max_slices; s++) {
+		if (s_en & BIT(s)) {
+			int ss_idx = sseu->max_subslices * s;
+			int ss;
+
+			sseu->slice_mask |= BIT(s);
+			sseu->subslice_mask[s] = (ss_en >> ss_idx) & ss_en_mask;
+			for (ss = 0; ss < sseu->max_subslices; ss++) {
+				if (sseu->subslice_mask[s] & BIT(ss))
+					sseu_set_eus(sseu, s, ss, eu_en);
+			}
+		}
+	}
+	sseu->eu_per_subslice = hweight8(eu_en);
+	sseu->eu_total = compute_eu_total(sseu);
+
+	/* ICL has no power gating restrictions. */
+	sseu->has_slice_pg = 1;
+	sseu->has_subslice_pg = 1;
+	sseu->has_eu_pg = 1;
+}
+
 static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
@@ -557,6 +596,52 @@ static u32 read_reference_ts_freq(struct drm_i915_private *dev_priv)
 	return base_freq + frac_freq;
 }
 
+static u32 gen10_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
+					u32 rpm_config_reg)
+{
+	u32 f19_2_mhz = 19200;
+	u32 f24_mhz = 24000;
+	u32 crystal_clock = (rpm_config_reg &
+			     GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
+			    GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
+
+	switch (crystal_clock) {
+	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
+		return f19_2_mhz;
+	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
+		return f24_mhz;
+	default:
+		MISSING_CASE(crystal_clock);
+		return 0;
+	}
+}
+
+static u32 gen11_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
+					u32 rpm_config_reg)
+{
+	u32 f19_2_mhz = 19200;
+	u32 f24_mhz = 24000;
+	u32 f25_mhz = 25000;
+	u32 f38_4_mhz = 38400;
+	u32 crystal_clock = (rpm_config_reg &
+			     GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
+			    GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
+
+	switch (crystal_clock) {
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
+		return f24_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
+		return f19_2_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_38_4_MHZ:
+		return f38_4_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_25_MHZ:
+		return f25_mhz;
+	default:
+		MISSING_CASE(crystal_clock);
+		return 0;
+	}
+}
+
 static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv)
 {
 	u32 f12_5_mhz = 12500;
@@ -597,10 +682,9 @@ static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv)
 		}
 
 		return freq;
-	} else if (INTEL_GEN(dev_priv) <= 10) {
+	} else if (INTEL_GEN(dev_priv) <= 11) {
 		u32 ctc_reg = I915_READ(CTC_MODE);
 		u32 freq = 0;
-		u32 rpm_config_reg = 0;
 
 		/* First figure out the reference frequency. There are 2 ways
 		 * we can compute the frequency, either through the
@@ -610,20 +694,14 @@ static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv)
 		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
 			freq = read_reference_ts_freq(dev_priv);
 		} else {
-			u32 crystal_clock;
-
-			rpm_config_reg = I915_READ(RPM_CONFIG0);
-			crystal_clock = (rpm_config_reg &
-					 GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
-				GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
-			switch (crystal_clock) {
-			case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
-				freq = f19_2_mhz;
-				break;
-			case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
-				freq = f24_mhz;
-				break;
-			}
+			u32 rpm_config_reg = I915_READ(RPM_CONFIG0);
+
+			if (INTEL_GEN(dev_priv) <= 10)
+				freq = gen10_get_crystal_clock_freq(dev_priv,
+								rpm_config_reg);
+			else
+				freq = gen11_get_crystal_clock_freq(dev_priv,
+								rpm_config_reg);
 
 			/* Now figure out how the command stream's timestamp
 			 * register increments from this frequency (it might
@@ -768,8 +846,10 @@ void intel_device_info_runtime_init(struct intel_device_info *info)
 		broadwell_sseu_info_init(dev_priv);
 	else if (INTEL_GEN(dev_priv) == 9)
 		gen9_sseu_info_init(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 10)
+	else if (INTEL_GEN(dev_priv) == 10)
 		gen10_sseu_info_init(dev_priv);
+	else if (INTEL_GEN(dev_priv) >= 11)
+		gen11_sseu_info_init(dev_priv);
 
 	/* Initialize command stream timestamp frequency */
 	info->cs_timestamp_frequency_khz = read_timestamp_frequency(dev_priv);
@@ -780,3 +860,50 @@ void intel_driver_caps_print(const struct intel_driver_caps *caps,
 {
 	drm_printf(p, "scheduler: %x\n", caps->scheduler);
 }
+
+/*
+ * Determine which engines are fused off in our particular hardware. Since the
+ * fuse register is in the blitter powerwell, we need forcewake to be ready at
+ * this point (but later we need to prune the forcewake domains for engines that
+ * are indeed fused off).
+ */
+void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
+{
+	struct intel_device_info *info = mkwrite_device_info(dev_priv);
+	u8 vdbox_disable, vebox_disable;
+	u32 media_fuse;
+	int i;
+
+	if (INTEL_GEN(dev_priv) < 11)
+		return;
+
+	media_fuse = I915_READ(GEN11_GT_VEBOX_VDBOX_DISABLE);
+
+	vdbox_disable = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK;
+	vebox_disable = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >>
+			GEN11_GT_VEBOX_DISABLE_SHIFT;
+
+	DRM_DEBUG_DRIVER("vdbox disable: %04x\n", vdbox_disable);
+	for (i = 0; i < I915_MAX_VCS; i++) {
+		if (!HAS_ENGINE(dev_priv, _VCS(i)))
+			continue;
+
+		if (!(BIT(i) & vdbox_disable))
+			continue;
+
+		info->ring_mask &= ~ENGINE_MASK(_VCS(i));
+		DRM_DEBUG_DRIVER("vcs%u fused off\n", i);
+	}
+
+	DRM_DEBUG_DRIVER("vebox disable: %04x\n", vebox_disable);
+	for (i = 0; i < I915_MAX_VECS; i++) {
+		if (!HAS_ENGINE(dev_priv, _VECS(i)))
+			continue;
+
+		if (!(BIT(i) & vebox_disable))
+			continue;
+
+		info->ring_mask &= ~ENGINE_MASK(_VECS(i));
+		DRM_DEBUG_DRIVER("vecs%u fused off\n", i);
+	}
+}
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 0835752c8b22..933e31669557 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -114,7 +114,7 @@ enum intel_platform {
 	func(has_ipc);
 
 #define GEN_MAX_SLICES		(6) /* CNL upper bound */
-#define GEN_MAX_SUBSLICES	(7)
+#define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
 
 struct sseu_dev_info {
 	u8 slice_mask;
@@ -247,6 +247,8 @@ void intel_device_info_dump_runtime(const struct intel_device_info *info,
 void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
 				     struct drm_printer *p);
 
+void intel_device_info_init_mmio(struct drm_i915_private *dev_priv);
+
 void intel_driver_caps_print(const struct intel_driver_caps *caps,
 			     struct drm_printer *p);
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3b48fd2561fe..ad588d564198 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -88,6 +88,22 @@ static const uint32_t skl_primary_formats[] = {
 	DRM_FORMAT_VYUY,
 };
 
+static const uint32_t skl_pri_planar_formats[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_NV12,
+};
+
 static const uint64_t skl_format_modifiers_noccs[] = {
 	I915_FORMAT_MOD_Yf_TILED,
 	I915_FORMAT_MOD_Y_TILED,
@@ -488,6 +504,33 @@ static const struct intel_limit intel_limits_bxt = {
 	.p2 = { .p2_slow = 1, .p2_fast = 20 },
 };
 
+static void
+skl_wa_528(struct drm_i915_private *dev_priv, int pipe, bool enable)
+{
+	if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))
+		return;
+
+	if (enable)
+		I915_WRITE(CHICKEN_PIPESL_1(pipe), HSW_FBCQ_DIS);
+	else
+		I915_WRITE(CHICKEN_PIPESL_1(pipe), 0);
+}
+
+static void
+skl_wa_clkgate(struct drm_i915_private *dev_priv, int pipe, bool enable)
+{
+	if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))
+		return;
+
+	if (enable)
+		I915_WRITE(CLKGATE_DIS_PSL(pipe),
+			   DUPS1_GATING_DIS | DUPS2_GATING_DIS);
+	else
+		I915_WRITE(CLKGATE_DIS_PSL(pipe),
+			   I915_READ(CLKGATE_DIS_PSL(pipe)) &
+			   ~(DUPS1_GATING_DIS | DUPS2_GATING_DIS));
+}
+
 static bool
 needs_modeset(const struct drm_crtc_state *state)
 {
@@ -2657,11 +2700,13 @@ static int i9xx_format_to_fourcc(int format)
 	}
 }
 
-static int skl_format_to_fourcc(int format, bool rgb_order, bool alpha)
+int skl_format_to_fourcc(int format, bool rgb_order, bool alpha)
 {
 	switch (format) {
 	case PLANE_CTL_FORMAT_RGB_565:
 		return DRM_FORMAT_RGB565;
+	case PLANE_CTL_FORMAT_NV12:
+		return DRM_FORMAT_NV12;
 	default:
 	case PLANE_CTL_FORMAT_XRGB_8888:
 		if (rgb_order) {
@@ -2824,7 +2869,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 			continue;
 
 		if (intel_plane_ggtt_offset(state) == plane_config->base) {
-			fb = c->primary->fb;
+			fb = state->base.fb;
 			drm_framebuffer_get(fb);
 			goto valid_fb;
 		}
@@ -2858,6 +2903,9 @@ valid_fb:
 		return;
 	}
 
+	obj = intel_fb_obj(fb);
+	intel_fb_obj_flush(obj, ORIGIN_DIRTYFB);
+
 	plane_state->src_x = 0;
 	plane_state->src_y = 0;
 	plane_state->src_w = fb->width << 16;
@@ -2871,7 +2919,6 @@ valid_fb:
 	intel_state->base.src = drm_plane_state_src(plane_state);
 	intel_state->base.dst = drm_plane_state_dest(plane_state);
 
-	obj = intel_fb_obj(fb);
 	if (i915_gem_object_is_tiled(obj))
 		dev_priv->preserve_bios_swizzle = true;
 
@@ -3071,6 +3118,29 @@ static int skl_check_main_surface(const struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
+static int
+skl_check_nv12_surface(const struct intel_crtc_state *crtc_state,
+		       struct intel_plane_state *plane_state)
+{
+	/* Display WA #1106 */
+	if (plane_state->base.rotation !=
+	    (DRM_MODE_REFLECT_X | DRM_MODE_ROTATE_90) &&
+	    plane_state->base.rotation != DRM_MODE_ROTATE_270)
+		return 0;
+
+	/*
+	 * src coordinates are rotated here.
+	 * We check height but report it as width
+	 */
+	if (((drm_rect_height(&plane_state->base.src) >> 16) % 4) != 0) {
+		DRM_DEBUG_KMS("src width must be multiple "
+			      "of 4 for rotated NV12\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state)
 {
 	const struct drm_framebuffer *fb = plane_state->base.fb;
@@ -3154,6 +3224,9 @@ int skl_check_plane_surface(const struct intel_crtc_state *crtc_state,
 	 * the main surface setup depends on it.
 	 */
 	if (fb->format->format == DRM_FORMAT_NV12) {
+		ret = skl_check_nv12_surface(crtc_state, plane_state);
+		if (ret)
+			return ret;
 		ret = skl_check_nv12_aux_surface(plane_state);
 		if (ret)
 			return ret;
@@ -3464,6 +3537,8 @@ static u32 skl_plane_ctl_format(uint32_t pixel_format)
 		return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_UYVY;
 	case DRM_FORMAT_VYUY:
 		return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_VYUY;
+	case DRM_FORMAT_NV12:
+		return PLANE_CTL_FORMAT_NV12;
 	default:
 		MISSING_CASE(pixel_format);
 	}
@@ -3602,15 +3677,24 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
+	struct drm_i915_private *dev_priv =
+		to_i915(plane_state->base.plane->dev);
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	u32 plane_color_ctl = 0;
 
-	plane_color_ctl |= PLANE_COLOR_PIPE_GAMMA_ENABLE;
-	plane_color_ctl |= PLANE_COLOR_PIPE_CSC_ENABLE;
+	if (INTEL_GEN(dev_priv) < 11) {
+		plane_color_ctl |= PLANE_COLOR_PIPE_GAMMA_ENABLE;
+		plane_color_ctl |= PLANE_COLOR_PIPE_CSC_ENABLE;
+	}
 	plane_color_ctl |= PLANE_COLOR_PLANE_GAMMA_DISABLE;
 	plane_color_ctl |= glk_plane_color_ctl_alpha(fb->format->format);
 
 	if (intel_format_is_yuv(fb->format->format)) {
+		if (fb->format->format == DRM_FORMAT_NV12) {
+			plane_color_ctl |=
+				PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
+			goto out;
+		}
 		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
 		else
@@ -3619,7 +3703,7 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 		if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 			plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE;
 	}
-
+out:
 	return plane_color_ctl;
 }
 
@@ -3675,7 +3759,6 @@ void intel_prepare_reset(struct drm_i915_private *dev_priv)
 	struct drm_atomic_state *state;
 	int ret;
 
-
 	/* reset doesn't touch the display */
 	if (!i915_modparams.force_reset_modeset_test &&
 	    !gpu_reset_clobbers_display(dev_priv))
@@ -3729,19 +3812,17 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
 	struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx;
-	struct drm_atomic_state *state = dev_priv->modeset_restore_state;
+	struct drm_atomic_state *state;
 	int ret;
 
 	/* reset doesn't touch the display */
-	if (!i915_modparams.force_reset_modeset_test &&
-	    !gpu_reset_clobbers_display(dev_priv))
+	if (!test_bit(I915_RESET_MODESET, &dev_priv->gpu_error.flags))
 		return;
 
+	state = fetch_and_zero(&dev_priv->modeset_restore_state);
 	if (!state)
 		goto unlock;
 
-	dev_priv->modeset_restore_state = NULL;
-
 	/* reset doesn't touch the display */
 	if (!gpu_reset_clobbers_display(dev_priv)) {
 		/* for testing only restore the display */
@@ -4703,7 +4784,9 @@ static void cpt_verify_modeset(struct drm_device *dev, int pipe)
 static int
 skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		  unsigned int scaler_user, int *scaler_id,
-		  int src_w, int src_h, int dst_w, int dst_h)
+		  int src_w, int src_h, int dst_w, int dst_h,
+		  bool plane_scaler_check,
+		  uint32_t pixel_format)
 {
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
@@ -4721,6 +4804,10 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 	 */
 	need_scaling = src_w != dst_w || src_h != dst_h;
 
+	if (plane_scaler_check)
+		if (pixel_format == DRM_FORMAT_NV12)
+			need_scaling = true;
+
 	if (crtc_state->ycbcr420 && scaler_user == SKL_CRTC_INDEX)
 		need_scaling = true;
 
@@ -4760,12 +4847,21 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		return 0;
 	}
 
+	if (plane_scaler_check && pixel_format == DRM_FORMAT_NV12 &&
+	    (src_h < SKL_MIN_YUV_420_SRC_H || src_w < SKL_MIN_YUV_420_SRC_W)) {
+		DRM_DEBUG_KMS("NV12: src dimensions not met\n");
+		return -EINVAL;
+	}
+
 	/* range checks */
 	if (src_w < SKL_MIN_SRC_W || src_h < SKL_MIN_SRC_H ||
-		dst_w < SKL_MIN_DST_W || dst_h < SKL_MIN_DST_H ||
-
-		src_w > SKL_MAX_SRC_W || src_h > SKL_MAX_SRC_H ||
-		dst_w > SKL_MAX_DST_W || dst_h > SKL_MAX_DST_H) {
+	    dst_w < SKL_MIN_DST_W || dst_h < SKL_MIN_DST_H ||
+	    (IS_GEN11(dev_priv) &&
+	     (src_w > ICL_MAX_SRC_W || src_h > ICL_MAX_SRC_H ||
+	      dst_w > ICL_MAX_DST_W || dst_h > ICL_MAX_DST_H)) ||
+	    (!IS_GEN11(dev_priv) &&
+	     (src_w > SKL_MAX_SRC_W || src_h > SKL_MAX_SRC_H ||
+	      dst_w > SKL_MAX_DST_W || dst_h > SKL_MAX_DST_H)))	{
 		DRM_DEBUG_KMS("scaler_user index %u.%u: src %ux%u dst %ux%u "
 			"size is out of scaler range\n",
 			intel_crtc->pipe, scaler_user, src_w, src_h, dst_w, dst_h);
@@ -4796,9 +4892,10 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state)
 	const struct drm_display_mode *adjusted_mode = &state->base.adjusted_mode;
 
 	return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX,
-		&state->scaler_state.scaler_id,
-		state->pipe_src_w, state->pipe_src_h,
-		adjusted_mode->crtc_hdisplay, adjusted_mode->crtc_vdisplay);
+				 &state->scaler_state.scaler_id,
+				 state->pipe_src_w, state->pipe_src_h,
+				 adjusted_mode->crtc_hdisplay,
+				 adjusted_mode->crtc_vdisplay, false, 0);
 }
 
 /**
@@ -4827,7 +4924,8 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 				drm_rect_width(&plane_state->base.src) >> 16,
 				drm_rect_height(&plane_state->base.src) >> 16,
 				drm_rect_width(&plane_state->base.dst),
-				drm_rect_height(&plane_state->base.dst));
+				drm_rect_height(&plane_state->base.dst),
+				fb ? true : false, fb ? fb->format->format : 0);
 
 	if (ret || plane_state->scaler_id < 0)
 		return ret;
@@ -4853,6 +4951,7 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_VYUY:
+	case DRM_FORMAT_NV12:
 		break;
 	default:
 		DRM_DEBUG_KMS("[PLANE:%d:%s] FB:%d unsupported scaling format 0x%x\n",
@@ -5096,16 +5195,34 @@ static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_s
 	return !old_crtc_state->ips_enabled;
 }
 
+static bool needs_nv12_wa(struct drm_i915_private *dev_priv,
+			  const struct intel_crtc_state *crtc_state)
+{
+	if (!crtc_state->nv12_planes)
+		return false;
+
+	if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))
+		return false;
+
+	if ((INTEL_GEN(dev_priv) == 9 && !IS_GEMINILAKE(dev_priv)) ||
+	    IS_CANNONLAKE(dev_priv))
+		return true;
+
+	return false;
+}
+
 static void intel_post_plane_update(struct intel_crtc_state *old_crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_atomic_state *old_state = old_crtc_state->base.state;
 	struct intel_crtc_state *pipe_config =
 		intel_atomic_get_new_crtc_state(to_intel_atomic_state(old_state),
 						crtc);
 	struct drm_plane *primary = crtc->base.primary;
-	struct drm_plane_state *old_pri_state =
-		drm_atomic_get_existing_plane_state(old_state, primary);
+	struct drm_plane_state *old_primary_state =
+		drm_atomic_get_old_plane_state(old_state, primary);
 
 	intel_frontbuffer_flip(to_i915(crtc->base.dev), pipe_config->fb_bits);
 
@@ -5115,20 +5232,24 @@ static void intel_post_plane_update(struct intel_crtc_state *old_crtc_state)
 	if (hsw_post_update_enable_ips(old_crtc_state, pipe_config))
 		hsw_enable_ips(pipe_config);
 
-	if (old_pri_state) {
-		struct intel_plane_state *primary_state =
-			intel_atomic_get_new_plane_state(to_intel_atomic_state(old_state),
-							 to_intel_plane(primary));
-		struct intel_plane_state *old_primary_state =
-			to_intel_plane_state(old_pri_state);
+	if (old_primary_state) {
+		struct drm_plane_state *new_primary_state =
+			drm_atomic_get_new_plane_state(old_state, primary);
 
 		intel_fbc_post_update(crtc);
 
-		if (primary_state->base.visible &&
+		if (new_primary_state->visible &&
 		    (needs_modeset(&pipe_config->base) ||
-		     !old_primary_state->base.visible))
+		     !old_primary_state->visible))
 			intel_post_enable_primary(&crtc->base, pipe_config);
 	}
+
+	/* Display WA 827 */
+	if (needs_nv12_wa(dev_priv, old_crtc_state) &&
+	    !needs_nv12_wa(dev_priv, pipe_config)) {
+		skl_wa_clkgate(dev_priv, crtc->pipe, false);
+		skl_wa_528(dev_priv, crtc->pipe, false);
+	}
 }
 
 static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
@@ -5139,8 +5260,8 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_atomic_state *old_state = old_crtc_state->base.state;
 	struct drm_plane *primary = crtc->base.primary;
-	struct drm_plane_state *old_pri_state =
-		drm_atomic_get_existing_plane_state(old_state, primary);
+	struct drm_plane_state *old_primary_state =
+		drm_atomic_get_old_plane_state(old_state, primary);
 	bool modeset = needs_modeset(&pipe_config->base);
 	struct intel_atomic_state *old_intel_state =
 		to_intel_atomic_state(old_state);
@@ -5148,23 +5269,28 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
 	if (hsw_pre_update_disable_ips(old_crtc_state, pipe_config))
 		hsw_disable_ips(old_crtc_state);
 
-	if (old_pri_state) {
-		struct intel_plane_state *primary_state =
+	if (old_primary_state) {
+		struct intel_plane_state *new_primary_state =
 			intel_atomic_get_new_plane_state(old_intel_state,
 							 to_intel_plane(primary));
-		struct intel_plane_state *old_primary_state =
-			to_intel_plane_state(old_pri_state);
 
-		intel_fbc_pre_update(crtc, pipe_config, primary_state);
+		intel_fbc_pre_update(crtc, pipe_config, new_primary_state);
 		/*
 		 * Gen2 reports pipe underruns whenever all planes are disabled.
 		 * So disable underrun reporting before all the planes get disabled.
 		 */
-		if (IS_GEN2(dev_priv) && old_primary_state->base.visible &&
-		    (modeset || !primary_state->base.visible))
+		if (IS_GEN2(dev_priv) && old_primary_state->visible &&
+		    (modeset || !new_primary_state->base.visible))
 			intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
 	}
 
+	/* Display WA 827 */
+	if (!needs_nv12_wa(dev_priv, old_crtc_state) &&
+	    needs_nv12_wa(dev_priv, pipe_config)) {
+		skl_wa_clkgate(dev_priv, crtc->pipe, true);
+		skl_wa_528(dev_priv, crtc->pipe, true);
+	}
+
 	/*
 	 * Vblank time updates from the shadow to live plane control register
 	 * are blocked if the memory self-refresh mode is active at that
@@ -5499,6 +5625,9 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	if (intel_crtc->config->shared_dpll)
 		intel_enable_shared_dpll(intel_crtc);
 
+	if (INTEL_GEN(dev_priv) >= 11)
+		icl_map_plls_to_ports(crtc, pipe_config, old_state);
+
 	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		intel_dp_set_m_n(intel_crtc, M1_N1);
 
@@ -5696,6 +5825,9 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 		intel_ddi_disable_pipe_clock(intel_crtc->config);
 
 	intel_encoders_post_disable(crtc, old_crtc_state, old_state);
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		icl_unmap_plls_to_ports(crtc, old_crtc_state, old_state);
 }
 
 static void i9xx_pfit_enable(struct intel_crtc *crtc)
@@ -8766,8 +8898,8 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 			intel_get_shared_dpll_by_id(dev_priv, pll_id);
 		pll = pipe_config->shared_dpll;
 
-		WARN_ON(!pll->funcs.get_hw_state(dev_priv, pll,
-						 &pipe_config->dpll_hw_state));
+		WARN_ON(!pll->info->funcs->get_hw_state(dev_priv, pll,
+						&pipe_config->dpll_hw_state));
 
 		tmp = pipe_config->dpll_hw_state.dpll;
 		pipe_config->pixel_multiplier =
@@ -9243,8 +9375,8 @@ static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 
 	pll = pipe_config->shared_dpll;
 	if (pll) {
-		WARN_ON(!pll->funcs.get_hw_state(dev_priv, pll,
-						 &pipe_config->dpll_hw_state));
+		WARN_ON(!pll->info->funcs->get_hw_state(dev_priv, pll,
+						&pipe_config->dpll_hw_state));
 	}
 
 	/*
@@ -9974,6 +10106,8 @@ found:
 	ret = PTR_ERR_OR_ZERO(drm_atomic_get_connector_state(restore_state, connector));
 	if (!ret)
 		ret = PTR_ERR_OR_ZERO(drm_atomic_get_crtc_state(restore_state, crtc));
+	if (!ret)
+		ret = drm_atomic_add_affected_planes(restore_state, crtc);
 	if (ret) {
 		DRM_DEBUG_KMS("Failed to create a copy of old state to restore: %i\n", ret);
 		goto fail;
@@ -10773,7 +10907,7 @@ static bool check_digital_port_conflicts(struct drm_atomic_state *state)
 		struct drm_connector_state *connector_state;
 		struct intel_encoder *encoder;
 
-		connector_state = drm_atomic_get_existing_connector_state(state, connector);
+		connector_state = drm_atomic_get_new_connector_state(state, connector);
 		if (!connector_state)
 			connector_state = connector->state;
 
@@ -11085,39 +11219,42 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 		(current_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED) &&
 		!(pipe_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED);
 
-#define PIPE_CONF_CHECK_X(name)	\
+#define PIPE_CONF_CHECK_X(name) do { \
 	if (current_config->name != pipe_config->name) { \
 		pipe_config_err(adjust, __stringify(name), \
 			  "(expected 0x%08x, found 0x%08x)\n", \
 			  current_config->name, \
 			  pipe_config->name); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
-#define PIPE_CONF_CHECK_I(name)	\
+#define PIPE_CONF_CHECK_I(name) do { \
 	if (current_config->name != pipe_config->name) { \
 		pipe_config_err(adjust, __stringify(name), \
 			  "(expected %i, found %i)\n", \
 			  current_config->name, \
 			  pipe_config->name); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
-#define PIPE_CONF_CHECK_BOOL(name)	\
+#define PIPE_CONF_CHECK_BOOL(name) do { \
 	if (current_config->name != pipe_config->name) { \
 		pipe_config_err(adjust, __stringify(name), \
 			  "(expected %s, found %s)\n", \
 			  yesno(current_config->name), \
 			  yesno(pipe_config->name)); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
 /*
  * Checks state where we only read out the enabling, but not the entire
  * state itself (like full infoframes or ELD for audio). These states
  * require a full modeset on bootup to fix up.
  */
-#define PIPE_CONF_CHECK_BOOL_INCOMPLETE(name) \
+#define PIPE_CONF_CHECK_BOOL_INCOMPLETE(name) do { \
 	if (!fixup_inherited || (!current_config->name && !pipe_config->name)) { \
 		PIPE_CONF_CHECK_BOOL(name); \
 	} else { \
@@ -11126,18 +11263,20 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 			  yesno(current_config->name), \
 			  yesno(pipe_config->name)); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
-#define PIPE_CONF_CHECK_P(name)	\
+#define PIPE_CONF_CHECK_P(name) do { \
 	if (current_config->name != pipe_config->name) { \
 		pipe_config_err(adjust, __stringify(name), \
 			  "(expected %p, found %p)\n", \
 			  current_config->name, \
 			  pipe_config->name); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
-#define PIPE_CONF_CHECK_M_N(name) \
+#define PIPE_CONF_CHECK_M_N(name) do { \
 	if (!intel_compare_link_m_n(&current_config->name, \
 				    &pipe_config->name,\
 				    adjust)) { \
@@ -11155,14 +11294,15 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 			  pipe_config->name.link_m, \
 			  pipe_config->name.link_n); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
 /* This is required for BDW+ where there is only one set of registers for
  * switching between high and low RR.
  * This macro can be used whenever a comparison has to be made between one
  * hw state and multiple sw state variables.
  */
-#define PIPE_CONF_CHECK_M_N_ALT(name, alt_name) \
+#define PIPE_CONF_CHECK_M_N_ALT(name, alt_name) do { \
 	if (!intel_compare_link_m_n(&current_config->name, \
 				    &pipe_config->name, adjust) && \
 	    !intel_compare_link_m_n(&current_config->alt_name, \
@@ -11187,9 +11327,10 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 			  pipe_config->name.link_m, \
 			  pipe_config->name.link_n); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
-#define PIPE_CONF_CHECK_FLAGS(name, mask)	\
+#define PIPE_CONF_CHECK_FLAGS(name, mask) do { \
 	if ((current_config->name ^ pipe_config->name) & (mask)) { \
 		pipe_config_err(adjust, __stringify(name), \
 			  "(%x) (expected %i, found %i)\n", \
@@ -11197,16 +11338,18 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 			  current_config->name & (mask), \
 			  pipe_config->name & (mask)); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
-#define PIPE_CONF_CHECK_CLOCK_FUZZY(name) \
+#define PIPE_CONF_CHECK_CLOCK_FUZZY(name) do { \
 	if (!intel_fuzzy_clock_check(current_config->name, pipe_config->name)) { \
 		pipe_config_err(adjust, __stringify(name), \
 			  "(expected %i, found %i)\n", \
 			  current_config->name, \
 			  pipe_config->name); \
 		ret = false; \
-	}
+	} \
+} while (0)
 
 #define PIPE_CONF_QUIRK(quirk)	\
 	((current_config->quirks | pipe_config->quirks) & (quirk))
@@ -11315,6 +11458,16 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 	PIPE_CONF_CHECK_X(dpll_hw_state.pll9);
 	PIPE_CONF_CHECK_X(dpll_hw_state.pll10);
 	PIPE_CONF_CHECK_X(dpll_hw_state.pcsdw12);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_refclkin_ctl);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_clktop2_coreclkctl1);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_clktop2_hsclkctl);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_div0);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_div1);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_lf);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_frac_lock);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_ssc);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_bias);
+	PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_tdc_coldst_bias);
 
 	PIPE_CONF_CHECK_X(dsi_pll.ctrl);
 	PIPE_CONF_CHECK_X(dsi_pll.div);
@@ -11378,6 +11531,11 @@ static void verify_wm_state(struct drm_crtc *crtc,
 	skl_ddb_get_hw_state(dev_priv, &hw_ddb);
 	sw_ddb = &dev_priv->wm.skl_hw.ddb;
 
+	if (INTEL_GEN(dev_priv) >= 11)
+		if (hw_ddb.enabled_slices != sw_ddb->enabled_slices)
+			DRM_ERROR("mismatch in DBUF Slices (expected %u, got %u)\n",
+				  sw_ddb->enabled_slices,
+				  hw_ddb.enabled_slices);
 	/* planes */
 	for_each_universal_plane(dev_priv, pipe, plane) {
 		hw_plane_wm = &hw_wm.planes[plane];
@@ -11643,11 +11801,11 @@ verify_single_dpll_state(struct drm_i915_private *dev_priv,
 
 	memset(&dpll_hw_state, 0, sizeof(dpll_hw_state));
 
-	DRM_DEBUG_KMS("%s\n", pll->name);
+	DRM_DEBUG_KMS("%s\n", pll->info->name);
 
-	active = pll->funcs.get_hw_state(dev_priv, pll, &dpll_hw_state);
+	active = pll->info->funcs->get_hw_state(dev_priv, pll, &dpll_hw_state);
 
-	if (!(pll->flags & INTEL_DPLL_ALWAYS_ON)) {
+	if (!(pll->info->flags & INTEL_DPLL_ALWAYS_ON)) {
 		I915_STATE_WARN(!pll->on && pll->active_mask,
 		     "pll in active use but not on in sw tracking\n");
 		I915_STATE_WARN(pll->on && !pll->active_mask,
@@ -12136,20 +12294,23 @@ static void intel_update_crtc(struct drm_crtc *crtc,
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_crtc_state *pipe_config = to_intel_crtc_state(new_crtc_state);
 	bool modeset = needs_modeset(new_crtc_state);
+	struct intel_plane_state *new_plane_state =
+		intel_atomic_get_new_plane_state(to_intel_atomic_state(state),
+						 to_intel_plane(crtc->primary));
 
 	if (modeset) {
 		update_scanline_offset(intel_crtc);
 		dev_priv->display.crtc_enable(pipe_config, state);
+
+		/* vblanks work again, re-enable pipe CRC. */
+		intel_crtc_enable_pipe_crc(intel_crtc);
 	} else {
 		intel_pre_plane_update(to_intel_crtc_state(old_crtc_state),
 				       pipe_config);
 	}
 
-	if (drm_atomic_get_existing_plane_state(state, crtc->primary)) {
-		intel_fbc_enable(
-		    intel_crtc, pipe_config,
-		    to_intel_plane_state(crtc->primary->state));
-	}
+	if (new_plane_state)
+		intel_fbc_enable(intel_crtc, pipe_config, new_plane_state);
 
 	drm_atomic_helper_commit_planes_on_crtc(old_crtc_state);
 }
@@ -12181,6 +12342,8 @@ static void skl_update_crtcs(struct drm_atomic_state *state)
 	bool progress;
 	enum pipe pipe;
 	int i;
+	u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices;
+	u8 required_slices = intel_state->wm_results.ddb.enabled_slices;
 
 	const struct skl_ddb_entry *entries[I915_MAX_PIPES] = {};
 
@@ -12189,6 +12352,10 @@ static void skl_update_crtcs(struct drm_atomic_state *state)
 		if (new_crtc_state->active)
 			entries[i] = &to_intel_crtc_state(old_crtc_state)->wm.skl.ddb;
 
+	/* If 2nd DBuf slice required, enable it here */
+	if (INTEL_GEN(dev_priv) >= 11 && required_slices > hw_enabled_slices)
+		icl_dbuf_slices_update(dev_priv, required_slices);
+
 	/*
 	 * Whenever the number of active pipes changes, we need to make sure we
 	 * update the pipes in the right order so that their ddb allocations
@@ -12239,6 +12406,10 @@ static void skl_update_crtcs(struct drm_atomic_state *state)
 			progress = true;
 		}
 	} while (progress);
+
+	/* If 2nd DBuf slice is no more required disable it */
+	if (INTEL_GEN(dev_priv) >= 11 && required_slices < hw_enabled_slices)
+		icl_dbuf_slices_update(dev_priv, required_slices);
 }
 
 static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv)
@@ -12320,6 +12491,13 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 
 		if (old_crtc_state->active) {
 			intel_crtc_disable_planes(crtc, old_crtc_state->plane_mask);
+
+			/*
+			 * We need to disable pipe CRC before disabling the pipe,
+			 * or we race against vblank off.
+			 */
+			intel_crtc_disable_pipe_crc(intel_crtc);
+
 			dev_priv->display.crtc_disable(to_intel_crtc_state(old_crtc_state), state);
 			intel_crtc->active = false;
 			intel_fbc_disable(intel_crtc);
@@ -12695,6 +12873,15 @@ static void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state)
 		intel_unpin_fb_vma(vma, old_plane_state->flags);
 }
 
+static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj)
+{
+	struct i915_sched_attr attr = {
+		.priority = I915_PRIORITY_DISPLAY,
+	};
+
+	i915_gem_object_wait_priority(obj, 0, &attr);
+}
+
 /**
  * intel_prepare_plane_fb - Prepare fb for usage on plane
  * @plane: drm plane to prepare for
@@ -12723,8 +12910,8 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 
 	if (old_obj) {
 		struct drm_crtc_state *crtc_state =
-			drm_atomic_get_existing_crtc_state(new_state->state,
-							   plane->state->crtc);
+			drm_atomic_get_new_crtc_state(new_state->state,
+						      plane->state->crtc);
 
 		/* Big Hammer, we also need to ensure that any pending
 		 * MI_WAIT_FOR_EVENT inside a user batch buffer on the
@@ -12771,13 +12958,15 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 
 	ret = intel_plane_pin_fb(to_intel_plane_state(new_state));
 
-	i915_gem_object_wait_priority(obj, 0, I915_PRIORITY_DISPLAY);
+	fb_obj_bump_render_priority(obj);
 
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 	i915_gem_object_unpin_pages(obj);
 	if (ret)
 		return ret;
 
+	intel_fb_obj_flush(obj, ORIGIN_DIRTYFB);
+
 	if (!new_state->fence) { /* implicit fencing */
 		struct dma_fence *fence;
 
@@ -12822,11 +13011,13 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 }
 
 int
-skl_max_scale(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state)
+skl_max_scale(struct intel_crtc *intel_crtc,
+	      struct intel_crtc_state *crtc_state,
+	      uint32_t pixel_format)
 {
 	struct drm_i915_private *dev_priv;
-	int max_scale;
-	int crtc_clock, max_dotclk;
+	int max_scale, mult;
+	int crtc_clock, max_dotclk, tmpclk1, tmpclk2;
 
 	if (!intel_crtc || !crtc_state->base.enable)
 		return DRM_PLANE_HELPER_NO_SCALING;
@@ -12848,8 +13039,10 @@ skl_max_scale(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state
 	 *            or
 	 *    cdclk/crtc_clock
 	 */
-	max_scale = min((1 << 16) * 3 - 1,
-			(1 << 8) * ((max_dotclk << 8) / crtc_clock));
+	mult = pixel_format == DRM_FORMAT_NV12 ? 2 : 3;
+	tmpclk1 = (1 << 16) * mult - 1;
+	tmpclk2 = (1 << 8) * ((max_dotclk << 8) / crtc_clock);
+	max_scale = min(tmpclk1, tmpclk2);
 
 	return max_scale;
 }
@@ -12865,12 +13058,16 @@ intel_check_primary_plane(struct intel_plane *plane,
 	int max_scale = DRM_PLANE_HELPER_NO_SCALING;
 	bool can_position = false;
 	int ret;
+	uint32_t pixel_format = 0;
 
 	if (INTEL_GEN(dev_priv) >= 9) {
 		/* use scaler when colorkey is not required */
 		if (!state->ckey.flags) {
 			min_scale = 1;
-			max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state);
+			if (state->base.fb)
+				pixel_format = state->base.fb->format->format;
+			max_scale = skl_max_scale(to_intel_crtc(crtc),
+						  crtc_state, pixel_format);
 		}
 		can_position = true;
 	}
@@ -12943,10 +13140,25 @@ out:
 							   intel_cstate);
 }
 
+void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
+				  struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+	if (!IS_GEN2(dev_priv))
+		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
+
+	if (crtc_state->has_pch_encoder) {
+		enum pipe pch_transcoder =
+			intel_crtc_pch_transcoder(crtc);
+
+		intel_set_pch_fifo_underrun_reporting(dev_priv, pch_transcoder, true);
+	}
+}
+
 static void intel_finish_crtc_commit(struct drm_crtc *crtc,
 				     struct drm_crtc_state *old_crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_atomic_state *old_intel_state =
 		to_intel_atomic_state(old_crtc_state->state);
@@ -12957,17 +13169,8 @@ static void intel_finish_crtc_commit(struct drm_crtc *crtc,
 
 	if (new_crtc_state->update_pipe &&
 	    !needs_modeset(&new_crtc_state->base) &&
-	    old_crtc_state->mode.private_flags & I915_MODE_FLAG_INHERITED) {
-		if (!IS_GEN2(dev_priv))
-			intel_set_cpu_fifo_underrun_reporting(dev_priv, intel_crtc->pipe, true);
-
-		if (new_crtc_state->has_pch_encoder) {
-			enum pipe pch_transcoder =
-				intel_crtc_pch_transcoder(intel_crtc);
-
-			intel_set_pch_fifo_underrun_reporting(dev_priv, pch_transcoder, true);
-		}
-	}
+	    old_crtc_state->mode.private_flags & I915_MODE_FLAG_INHERITED)
+		intel_crtc_arm_fifo_underrun(intel_crtc, new_crtc_state);
 }
 
 /**
@@ -13031,6 +13234,7 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier)
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_VYUY:
+	case DRM_FORMAT_NV12:
 		if (modifier == I915_FORMAT_MOD_Yf_TILED)
 			return true;
 		/* fall through */
@@ -13165,8 +13369,9 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 	if (ret)
 		goto out_unlock;
 
-	old_fb = old_plane_state->fb;
+	intel_fb_obj_flush(intel_fb_obj(fb), ORIGIN_FLIP);
 
+	old_fb = old_plane_state->fb;
 	i915_gem_track_fb(intel_fb_obj(old_fb), intel_fb_obj(fb),
 			  intel_plane->frontbuffer_bit);
 
@@ -13237,6 +13442,30 @@ static bool skl_plane_has_fbc(struct drm_i915_private *dev_priv,
 	return pipe == PIPE_A && plane_id == PLANE_PRIMARY;
 }
 
+bool skl_plane_has_planar(struct drm_i915_private *dev_priv,
+			  enum pipe pipe, enum plane_id plane_id)
+{
+	if (plane_id == PLANE_PRIMARY) {
+		if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))
+			return false;
+		else if ((INTEL_GEN(dev_priv) == 9 && pipe == PIPE_C) &&
+			 !IS_GEMINILAKE(dev_priv))
+			return false;
+	} else if (plane_id >= PLANE_SPRITE0) {
+		if (plane_id == PLANE_CURSOR)
+			return false;
+		if (IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) == 10) {
+			if (plane_id != PLANE_SPRITE0)
+				return false;
+		} else {
+			if (plane_id != PLANE_SPRITE0 || pipe == PIPE_C ||
+			    IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))
+				return false;
+		}
+	}
+	return true;
+}
+
 static struct intel_plane *
 intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
@@ -13297,8 +13526,13 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	primary->check_plane = intel_check_primary_plane;
 
 	if (INTEL_GEN(dev_priv) >= 9) {
-		intel_primary_formats = skl_primary_formats;
-		num_formats = ARRAY_SIZE(skl_primary_formats);
+		if (skl_plane_has_planar(dev_priv, pipe, PLANE_PRIMARY)) {
+			intel_primary_formats = skl_pri_planar_formats;
+			num_formats = ARRAY_SIZE(skl_pri_planar_formats);
+		} else {
+			intel_primary_formats = skl_primary_formats;
+			num_formats = ARRAY_SIZE(skl_primary_formats);
+		}
 
 		if (skl_plane_has_ccs(dev_priv, pipe, PLANE_PRIMARY))
 			modifiers = skl_format_modifiers_ccs;
@@ -13553,10 +13787,17 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 	/* initialize shared scalers */
 	intel_crtc_init_scalers(intel_crtc, crtc_state);
 
-	BUG_ON(pipe >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
-	       dev_priv->plane_to_crtc_mapping[primary->i9xx_plane] != NULL);
-	dev_priv->plane_to_crtc_mapping[primary->i9xx_plane] = intel_crtc;
-	dev_priv->pipe_to_crtc_mapping[intel_crtc->pipe] = intel_crtc;
+	BUG_ON(pipe >= ARRAY_SIZE(dev_priv->pipe_to_crtc_mapping) ||
+	       dev_priv->pipe_to_crtc_mapping[pipe] != NULL);
+	dev_priv->pipe_to_crtc_mapping[pipe] = intel_crtc;
+
+	if (INTEL_GEN(dev_priv) < 9) {
+		enum i9xx_plane_id i9xx_plane = primary->i9xx_plane;
+
+		BUG_ON(i9xx_plane >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
+		       dev_priv->plane_to_crtc_mapping[i9xx_plane] != NULL);
+		dev_priv->plane_to_crtc_mapping[i9xx_plane] = intel_crtc;
+	}
 
 	drm_crtc_helper_add(&intel_crtc->base, &intel_helper_funcs);
 
@@ -14112,6 +14353,20 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 			goto err;
 		}
 		break;
+	case DRM_FORMAT_NV12:
+		if (mode_cmd->modifier[0] == I915_FORMAT_MOD_Y_TILED_CCS ||
+		    mode_cmd->modifier[0] == I915_FORMAT_MOD_Yf_TILED_CCS) {
+			DRM_DEBUG_KMS("RC not to be enabled with NV12\n");
+			goto err;
+		}
+		if (INTEL_GEN(dev_priv) < 9 || IS_SKYLAKE(dev_priv) ||
+		    IS_BROXTON(dev_priv)) {
+			DRM_DEBUG_KMS("unsupported pixel format: %s\n",
+				      drm_get_format_name(mode_cmd->pixel_format,
+							  &format_name));
+			goto err;
+		}
+		break;
 	default:
 		DRM_DEBUG_KMS("unsupported pixel format: %s\n",
 			      drm_get_format_name(mode_cmd->pixel_format, &format_name));
@@ -14124,6 +14379,14 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 
 	drm_helper_mode_fill_fb_struct(&dev_priv->drm, fb, mode_cmd);
 
+	if (fb->format->format == DRM_FORMAT_NV12 &&
+	    (fb->width < SKL_MIN_YUV_420_SRC_W ||
+	     fb->height < SKL_MIN_YUV_420_SRC_H ||
+	     (fb->width % 4) != 0 || (fb->height % 4) != 0)) {
+		DRM_DEBUG_KMS("src dimensions not correct for NV12\n");
+		return -EINVAL;
+	}
+
 	for (i = 0; i < fb->format->num_planes; i++) {
 		u32 stride_alignment;
 
@@ -15101,8 +15364,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
 		struct intel_shared_dpll *pll = &dev_priv->shared_dplls[i];
 
-		pll->on = pll->funcs.get_hw_state(dev_priv, pll,
-						  &pll->state.hw_state);
+		pll->on = pll->info->funcs->get_hw_state(dev_priv, pll,
+							&pll->state.hw_state);
 		pll->state.crtc_mask = 0;
 		for_each_intel_crtc(dev, crtc) {
 			struct intel_crtc_state *crtc_state =
@@ -15115,7 +15378,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		pll->active_mask = pll->state.crtc_mask;
 
 		DRM_DEBUG_KMS("%s hw state readout: crtc_mask 0x%08x, on %i\n",
-			      pll->name, pll->state.crtc_mask, pll->on);
+			      pll->info->name, pll->state.crtc_mask, pll->on);
 	}
 
 	for_each_intel_encoder(dev, encoder) {
@@ -15178,6 +15441,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		memset(&crtc->base.mode, 0, sizeof(crtc->base.mode));
 		if (crtc_state->base.active) {
 			intel_mode_from_pipe_config(&crtc->base.mode, crtc_state);
+			crtc->base.mode.hdisplay = crtc_state->pipe_src_w;
+			crtc->base.mode.vdisplay = crtc_state->pipe_src_h;
 			intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode, crtc_state);
 			WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode));
 
@@ -15289,9 +15554,10 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 		if (!pll->on || pll->active_mask)
 			continue;
 
-		DRM_DEBUG_KMS("%s enabled but not in use, disabling\n", pll->name);
+		DRM_DEBUG_KMS("%s enabled but not in use, disabling\n",
+			      pll->info->name);
 
-		pll->funcs.disable(dev_priv, pll);
+		pll->info->funcs->disable(dev_priv, pll);
 		pll->on = false;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index 4e7418b345bc..2ef31617614a 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -218,6 +218,10 @@ struct intel_link_m_n {
 	for ((__p) = 0; (__p) < INTEL_INFO(__dev_priv)->num_pipes; (__p)++) \
 		for_each_if((__mask) & BIT(__p))
 
+#define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \
+	for ((__t) = 0; (__t) < I915_MAX_TRANSCODERS; (__t)++)	\
+		for_each_if ((__mask) & (1 << (__t)))
+
 #define for_each_universal_plane(__dev_priv, __pipe, __p)		\
 	for ((__p) = 0;							\
 	     (__p) < INTEL_INFO(__dev_priv)->num_sprites[(__pipe)] + 1;	\
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 9a4a51e79fa1..dde92e4af5d3 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -43,7 +43,6 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
-#define DP_LINK_CHECK_TIMEOUT	(10 * 1000)
 #define DP_DPRX_ESI_LEN 14
 
 /* Compliance test status bits  */
@@ -92,8 +91,6 @@ static const struct dp_link_dpll chv_dpll[] = {
 		{ .p1 = 4, .p2 = 2, .n = 1, .m1 = 2, .m2 = 0x819999a } },
 	{ 270000,	/* m2_int = 27, m2_fraction = 0 */
 		{ .p1 = 4, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } },
-	{ 540000,	/* m2_int = 27, m2_fraction = 0 */
-		{ .p1 = 2, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } }
 };
 
 /**
@@ -1650,9 +1647,17 @@ void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock,
 	}
 }
 
+struct link_config_limits {
+	int min_clock, max_clock;
+	int min_lane_count, max_lane_count;
+	int min_bpp, max_bpp;
+};
+
 static int intel_dp_compute_bpp(struct intel_dp *intel_dp,
 				struct intel_crtc_state *pipe_config)
 {
+	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
+	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	int bpp, bpc;
 
 	bpp = pipe_config->pipe_bpp;
@@ -1661,13 +1666,16 @@ static int intel_dp_compute_bpp(struct intel_dp *intel_dp,
 	if (bpc > 0)
 		bpp = min(bpp, 3*bpc);
 
-	/* For DP Compliance we override the computed bpp for the pipe */
-	if (intel_dp->compliance.test_data.bpc != 0) {
-		pipe_config->pipe_bpp =	3*intel_dp->compliance.test_data.bpc;
-		pipe_config->dither_force_disable = pipe_config->pipe_bpp == 6*3;
-		DRM_DEBUG_KMS("Setting pipe_bpp to %d\n",
-			      pipe_config->pipe_bpp);
+	if (intel_dp_is_edp(intel_dp)) {
+		/* Get bpp from vbt only for panels that dont have bpp in edid */
+		if (intel_connector->base.display_info.bpc == 0 &&
+		    dev_priv->vbt.edp.bpp && dev_priv->vbt.edp.bpp < bpp) {
+			DRM_DEBUG_KMS("clamping bpp for eDP panel to BIOS-provided %i\n",
+				      dev_priv->vbt.edp.bpp);
+			bpp = dev_priv->vbt.edp.bpp;
+		}
 	}
+
 	return bpp;
 }
 
@@ -1688,6 +1696,142 @@ static bool intel_edp_compare_alt_mode(struct drm_display_mode *m1,
 	return bres;
 }
 
+/* Adjust link config limits based on compliance test requests. */
+static void
+intel_dp_adjust_compliance_config(struct intel_dp *intel_dp,
+				  struct intel_crtc_state *pipe_config,
+				  struct link_config_limits *limits)
+{
+	/* For DP Compliance we override the computed bpp for the pipe */
+	if (intel_dp->compliance.test_data.bpc != 0) {
+		int bpp = 3 * intel_dp->compliance.test_data.bpc;
+
+		limits->min_bpp = limits->max_bpp = bpp;
+		pipe_config->dither_force_disable = bpp == 6 * 3;
+
+		DRM_DEBUG_KMS("Setting pipe_bpp to %d\n", bpp);
+	}
+
+	/* Use values requested by Compliance Test Request */
+	if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) {
+		int index;
+
+		/* Validate the compliance test data since max values
+		 * might have changed due to link train fallback.
+		 */
+		if (intel_dp_link_params_valid(intel_dp, intel_dp->compliance.test_link_rate,
+					       intel_dp->compliance.test_lane_count)) {
+			index = intel_dp_rate_index(intel_dp->common_rates,
+						    intel_dp->num_common_rates,
+						    intel_dp->compliance.test_link_rate);
+			if (index >= 0)
+				limits->min_clock = limits->max_clock = index;
+			limits->min_lane_count = limits->max_lane_count =
+				intel_dp->compliance.test_lane_count;
+		}
+	}
+}
+
+/* Optimize link config in order: max bpp, min clock, min lanes */
+static bool
+intel_dp_compute_link_config_wide(struct intel_dp *intel_dp,
+				  struct intel_crtc_state *pipe_config,
+				  const struct link_config_limits *limits)
+{
+	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	int bpp, clock, lane_count;
+	int mode_rate, link_clock, link_avail;
+
+	for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) {
+		mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
+						   bpp);
+
+		for (clock = limits->min_clock; clock <= limits->max_clock; clock++) {
+			for (lane_count = limits->min_lane_count;
+			     lane_count <= limits->max_lane_count;
+			     lane_count <<= 1) {
+				link_clock = intel_dp->common_rates[clock];
+				link_avail = intel_dp_max_data_rate(link_clock,
+								    lane_count);
+
+				if (mode_rate <= link_avail) {
+					pipe_config->lane_count = lane_count;
+					pipe_config->pipe_bpp = bpp;
+					pipe_config->port_clock = link_clock;
+
+					return true;
+				}
+			}
+		}
+	}
+
+	return false;
+}
+
+static bool
+intel_dp_compute_link_config(struct intel_encoder *encoder,
+			     struct intel_crtc_state *pipe_config)
+{
+	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct link_config_limits limits;
+	int common_len;
+
+	common_len = intel_dp_common_len_rate_limit(intel_dp,
+						    intel_dp->max_link_rate);
+
+	/* No common link rates between source and sink */
+	WARN_ON(common_len <= 0);
+
+	limits.min_clock = 0;
+	limits.max_clock = common_len - 1;
+
+	limits.min_lane_count = 1;
+	limits.max_lane_count = intel_dp_max_lane_count(intel_dp);
+
+	limits.min_bpp = 6 * 3;
+	limits.max_bpp = intel_dp_compute_bpp(intel_dp, pipe_config);
+
+	if (intel_dp_is_edp(intel_dp)) {
+		/*
+		 * Use the maximum clock and number of lanes the eDP panel
+		 * advertizes being capable of. The panels are generally
+		 * designed to support only a single clock and lane
+		 * configuration, and typically these values correspond to the
+		 * native resolution of the panel.
+		 */
+		limits.min_lane_count = limits.max_lane_count;
+		limits.min_clock = limits.max_clock;
+	}
+
+	intel_dp_adjust_compliance_config(intel_dp, pipe_config, &limits);
+
+	DRM_DEBUG_KMS("DP link computation with max lane count %i "
+		      "max rate %d max bpp %d pixel clock %iKHz\n",
+		      limits.max_lane_count,
+		      intel_dp->common_rates[limits.max_clock],
+		      limits.max_bpp, adjusted_mode->crtc_clock);
+
+	/*
+	 * Optimize for slow and wide. This is the place to add alternative
+	 * optimization policy.
+	 */
+	if (!intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits))
+		return false;
+
+	DRM_DEBUG_KMS("DP lane count %d clock %d bpp %d\n",
+		      pipe_config->lane_count, pipe_config->port_clock,
+		      pipe_config->pipe_bpp);
+
+	DRM_DEBUG_KMS("DP link rate required %i available %i\n",
+		      intel_dp_link_required(adjusted_mode->crtc_clock,
+					     pipe_config->pipe_bpp),
+		      intel_dp_max_data_rate(pipe_config->port_clock,
+					     pipe_config->lane_count));
+
+	return true;
+}
+
 bool
 intel_dp_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_state *pipe_config,
@@ -1701,27 +1845,9 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
-	int lane_count, clock;
-	int min_lane_count = 1;
-	int max_lane_count = intel_dp_max_lane_count(intel_dp);
-	/* Conveniently, the link BW constants become indices with a shift...*/
-	int min_clock = 0;
-	int max_clock;
-	int bpp, mode_rate;
-	int link_avail, link_clock;
-	int common_len;
-	uint8_t link_bw, rate_select;
 	bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,
 					   DP_DPCD_QUIRK_LIMITED_M_N);
 
-	common_len = intel_dp_common_len_rate_limit(intel_dp,
-						    intel_dp->max_link_rate);
-
-	/* No common link rates between source and sink */
-	WARN_ON(common_len <= 0);
-
-	max_clock = common_len - 1;
-
 	if (HAS_PCH_SPLIT(dev_priv) && !HAS_DDI(dev_priv) && port != PORT_A)
 		pipe_config->has_pch_encoder = true;
 
@@ -1747,6 +1873,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 
 		if (INTEL_GEN(dev_priv) >= 9) {
 			int ret;
+
 			ret = skl_update_scaler_crtc(pipe_config);
 			if (ret)
 				return ret;
@@ -1767,75 +1894,9 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return false;
 
-	/* Use values requested by Compliance Test Request */
-	if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) {
-		int index;
-
-		/* Validate the compliance test data since max values
-		 * might have changed due to link train fallback.
-		 */
-		if (intel_dp_link_params_valid(intel_dp, intel_dp->compliance.test_link_rate,
-					       intel_dp->compliance.test_lane_count)) {
-			index = intel_dp_rate_index(intel_dp->common_rates,
-						    intel_dp->num_common_rates,
-						    intel_dp->compliance.test_link_rate);
-			if (index >= 0)
-				min_clock = max_clock = index;
-			min_lane_count = max_lane_count = intel_dp->compliance.test_lane_count;
-		}
-	}
-	DRM_DEBUG_KMS("DP link computation with max lane count %i "
-		      "max bw %d pixel clock %iKHz\n",
-		      max_lane_count, intel_dp->common_rates[max_clock],
-		      adjusted_mode->crtc_clock);
-
-	/* Walk through all bpp values. Luckily they're all nicely spaced with 2
-	 * bpc in between. */
-	bpp = intel_dp_compute_bpp(intel_dp, pipe_config);
-	if (intel_dp_is_edp(intel_dp)) {
-
-		/* Get bpp from vbt only for panels that dont have bpp in edid */
-		if (intel_connector->base.display_info.bpc == 0 &&
-			(dev_priv->vbt.edp.bpp && dev_priv->vbt.edp.bpp < bpp)) {
-			DRM_DEBUG_KMS("clamping bpp for eDP panel to BIOS-provided %i\n",
-				      dev_priv->vbt.edp.bpp);
-			bpp = dev_priv->vbt.edp.bpp;
-		}
-
-		/*
-		 * Use the maximum clock and number of lanes the eDP panel
-		 * advertizes being capable of. The panels are generally
-		 * designed to support only a single clock and lane
-		 * configuration, and typically these values correspond to the
-		 * native resolution of the panel.
-		 */
-		min_lane_count = max_lane_count;
-		min_clock = max_clock;
-	}
-
-	for (; bpp >= 6*3; bpp -= 2*3) {
-		mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
-						   bpp);
-
-		for (clock = min_clock; clock <= max_clock; clock++) {
-			for (lane_count = min_lane_count;
-				lane_count <= max_lane_count;
-				lane_count <<= 1) {
-
-				link_clock = intel_dp->common_rates[clock];
-				link_avail = intel_dp_max_data_rate(link_clock,
-								    lane_count);
-
-				if (mode_rate <= link_avail) {
-					goto found;
-				}
-			}
-		}
-	}
-
-	return false;
+	if (!intel_dp_compute_link_config(encoder, pipe_config))
+		return false;
 
-found:
 	if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) {
 		/*
 		 * See:
@@ -1843,7 +1904,7 @@ found:
 		 * VESA DisplayPort Ver.1.2a - 5.1.1.1 Video Colorimetry
 		 */
 		pipe_config->limited_color_range =
-			bpp != 18 &&
+			pipe_config->pipe_bpp != 18 &&
 			drm_default_rgb_quant_range(adjusted_mode) ==
 			HDMI_QUANTIZATION_RANGE_LIMITED;
 	} else {
@@ -1851,21 +1912,7 @@ found:
 			intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED;
 	}
 
-	pipe_config->lane_count = lane_count;
-
-	pipe_config->pipe_bpp = bpp;
-	pipe_config->port_clock = intel_dp->common_rates[clock];
-
-	intel_dp_compute_rate(intel_dp, pipe_config->port_clock,
-			      &link_bw, &rate_select);
-
-	DRM_DEBUG_KMS("DP link bw %02x rate select %02x lane count %d clock %d bpp %d\n",
-		      link_bw, rate_select, pipe_config->lane_count,
-		      pipe_config->port_clock, bpp);
-	DRM_DEBUG_KMS("DP link bw required %i available %i\n",
-		      mode_rate, link_avail);
-
-	intel_link_compute_m_n(bpp, lane_count,
+	intel_link_compute_m_n(pipe_config->pipe_bpp, pipe_config->lane_count,
 			       adjusted_mode->crtc_clock,
 			       pipe_config->port_clock,
 			       &pipe_config->dp_m_n,
@@ -1874,31 +1921,12 @@ found:
 	if (intel_connector->panel.downclock_mode != NULL &&
 		dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) {
 			pipe_config->has_drrs = true;
-			intel_link_compute_m_n(bpp, lane_count,
-				intel_connector->panel.downclock_mode->clock,
-				pipe_config->port_clock,
-				&pipe_config->dp_m2_n2,
-				reduce_m_n);
-	}
-
-	/*
-	 * DPLL0 VCO may need to be adjusted to get the correct
-	 * clock for eDP. This will affect cdclk as well.
-	 */
-	if (intel_dp_is_edp(intel_dp) && IS_GEN9_BC(dev_priv)) {
-		int vco;
-
-		switch (pipe_config->port_clock / 2) {
-		case 108000:
-		case 216000:
-			vco = 8640000;
-			break;
-		default:
-			vco = 8100000;
-			break;
-		}
-
-		to_intel_atomic_state(pipe_config->base.state)->cdclk.logical.vco = vco;
+			intel_link_compute_m_n(pipe_config->pipe_bpp,
+					       pipe_config->lane_count,
+					       intel_connector->panel.downclock_mode->clock,
+					       pipe_config->port_clock,
+					       &pipe_config->dp_m2_n2,
+					       reduce_m_n);
 	}
 
 	if (!HAS_DDI(dev_priv))
@@ -2901,10 +2929,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 		}
 
 	} else {
-		if (IS_CHERRYVIEW(dev_priv))
-			*DP &= ~DP_LINK_TRAIN_MASK_CHV;
-		else
-			*DP &= ~DP_LINK_TRAIN_MASK;
+		*DP &= ~DP_LINK_TRAIN_MASK;
 
 		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
 		case DP_TRAINING_PATTERN_DISABLE:
@@ -2917,12 +2942,8 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 			*DP |= DP_LINK_TRAIN_PAT_2;
 			break;
 		case DP_TRAINING_PATTERN_3:
-			if (IS_CHERRYVIEW(dev_priv)) {
-				*DP |= DP_LINK_TRAIN_PAT_3_CHV;
-			} else {
-				DRM_DEBUG_KMS("TPS3 not supported, using TPS2 instead\n");
-				*DP |= DP_LINK_TRAIN_PAT_2;
-			}
+			DRM_DEBUG_KMS("TPS3 not supported, using TPS2 instead\n");
+			*DP |= DP_LINK_TRAIN_PAT_2;
 			break;
 		}
 	}
@@ -3661,10 +3682,7 @@ intel_dp_link_down(struct intel_encoder *encoder,
 		DP &= ~DP_LINK_TRAIN_MASK_CPT;
 		DP |= DP_LINK_TRAIN_PAT_IDLE_CPT;
 	} else {
-		if (IS_CHERRYVIEW(dev_priv))
-			DP &= ~DP_LINK_TRAIN_MASK_CHV;
-		else
-			DP &= ~DP_LINK_TRAIN_MASK;
+		DP &= ~DP_LINK_TRAIN_MASK;
 		DP |= DP_LINK_TRAIN_PAT_IDLE;
 	}
 	I915_WRITE(intel_dp->output_reg, DP);
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index f59b59bb0a21..3fcaa98b9055 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -139,6 +139,11 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 	intel_dp_compute_rate(intel_dp, intel_dp->link_rate,
 			      &link_bw, &rate_select);
 
+	if (link_bw)
+		DRM_DEBUG_KMS("Using LINK_BW_SET value %02x\n", link_bw);
+	else
+		DRM_DEBUG_KMS("Using LINK_RATE_SET value %02x\n", rate_select);
+
 	/* Write the link configuration data */
 	link_config[0] = link_bw;
 	link_config[1] = intel_dp->lane_count;
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index c3de0918ee13..9e6956c08688 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -180,9 +180,11 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder,
 	intel_dp->active_mst_links--;
 
 	intel_mst->connector = NULL;
-	if (intel_dp->active_mst_links == 0)
+	if (intel_dp->active_mst_links == 0) {
+		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 		intel_dig_port->base.post_disable(&intel_dig_port->base,
 						  old_crtc_state, NULL);
+	}
 
 	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
 }
@@ -223,7 +225,11 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 
 	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
 
+	if (intel_dp->active_mst_links == 0)
+		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+
 	drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port, true);
+
 	if (intel_dp->active_mst_links == 0)
 		intel_dig_port->base.pre_enable(&intel_dig_port->base,
 						pipe_config, NULL);
diff --git a/drivers/gpu/drm/i915/intel_dpio_phy.c b/drivers/gpu/drm/i915/intel_dpio_phy.c
index c8e9e44e5981..00b3ab656b06 100644
--- a/drivers/gpu/drm/i915/intel_dpio_phy.c
+++ b/drivers/gpu/drm/i915/intel_dpio_phy.c
@@ -380,13 +380,14 @@ static void _bxt_ddi_phy_init(struct drm_i915_private *dev_priv,
 	 * all 1s.  Eventually they become accessible as they power up, then
 	 * the reserved bit will give the default 0.  Poll on the reserved bit
 	 * becoming 0 to find when the PHY is accessible.
-	 * HW team confirmed that the time to reach phypowergood status is
-	 * anywhere between 50 us and 100us.
+	 * The flag should get set in 100us according to the HW team, but
+	 * use 1ms due to occasional timeouts observed with that.
 	 */
-	if (wait_for_us(((I915_READ(BXT_PORT_CL1CM_DW0(phy)) &
-		(PHY_RESERVED | PHY_POWER_GOOD)) == PHY_POWER_GOOD), 100)) {
+	if (intel_wait_for_register_fw(dev_priv, BXT_PORT_CL1CM_DW0(phy),
+				       PHY_RESERVED | PHY_POWER_GOOD,
+				       PHY_POWER_GOOD,
+				       1))
 		DRM_ERROR("timeout during PHY%d power on\n", phy);
-	}
 
 	/* Program PLL Rcomp code offset */
 	val = I915_READ(BXT_PORT_CL1CM_DW9(phy));
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 51c5ae4e9116..383fbc15113d 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -118,10 +118,10 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv,
 	if (WARN(!pll, "asserting DPLL %s with no DPLL\n", onoff(state)))
 		return;
 
-	cur_state = pll->funcs.get_hw_state(dev_priv, pll, &hw_state);
+	cur_state = pll->info->funcs->get_hw_state(dev_priv, pll, &hw_state);
 	I915_STATE_WARN(cur_state != state,
 	     "%s assertion failure (expected %s, current %s)\n",
-			pll->name, onoff(state), onoff(cur_state));
+			pll->info->name, onoff(state), onoff(cur_state));
 }
 
 /**
@@ -143,11 +143,11 @@ void intel_prepare_shared_dpll(struct intel_crtc *crtc)
 	mutex_lock(&dev_priv->dpll_lock);
 	WARN_ON(!pll->state.crtc_mask);
 	if (!pll->active_mask) {
-		DRM_DEBUG_DRIVER("setting up %s\n", pll->name);
+		DRM_DEBUG_DRIVER("setting up %s\n", pll->info->name);
 		WARN_ON(pll->on);
 		assert_shared_dpll_disabled(dev_priv, pll);
 
-		pll->funcs.prepare(dev_priv, pll);
+		pll->info->funcs->prepare(dev_priv, pll);
 	}
 	mutex_unlock(&dev_priv->dpll_lock);
 }
@@ -179,7 +179,7 @@ void intel_enable_shared_dpll(struct intel_crtc *crtc)
 	pll->active_mask |= crtc_mask;
 
 	DRM_DEBUG_KMS("enable %s (active %x, on? %d) for crtc %d\n",
-		      pll->name, pll->active_mask, pll->on,
+		      pll->info->name, pll->active_mask, pll->on,
 		      crtc->base.base.id);
 
 	if (old_mask) {
@@ -189,8 +189,8 @@ void intel_enable_shared_dpll(struct intel_crtc *crtc)
 	}
 	WARN_ON(pll->on);
 
-	DRM_DEBUG_KMS("enabling %s\n", pll->name);
-	pll->funcs.enable(dev_priv, pll);
+	DRM_DEBUG_KMS("enabling %s\n", pll->info->name);
+	pll->info->funcs->enable(dev_priv, pll);
 	pll->on = true;
 
 out:
@@ -221,7 +221,7 @@ void intel_disable_shared_dpll(struct intel_crtc *crtc)
 		goto out;
 
 	DRM_DEBUG_KMS("disable %s (active %x, on? %d) for crtc %d\n",
-		      pll->name, pll->active_mask, pll->on,
+		      pll->info->name, pll->active_mask, pll->on,
 		      crtc->base.base.id);
 
 	assert_shared_dpll_enabled(dev_priv, pll);
@@ -231,8 +231,8 @@ void intel_disable_shared_dpll(struct intel_crtc *crtc)
 	if (pll->active_mask)
 		goto out;
 
-	DRM_DEBUG_KMS("disabling %s\n", pll->name);
-	pll->funcs.disable(dev_priv, pll);
+	DRM_DEBUG_KMS("disabling %s\n", pll->info->name);
+	pll->info->funcs->disable(dev_priv, pll);
 	pll->on = false;
 
 out:
@@ -263,7 +263,8 @@ intel_find_shared_dpll(struct intel_crtc *crtc,
 			   &shared_dpll[i].hw_state,
 			   sizeof(crtc_state->dpll_hw_state)) == 0) {
 			DRM_DEBUG_KMS("[CRTC:%d:%s] sharing existing %s (crtc mask 0x%08x, active %x)\n",
-				      crtc->base.base.id, crtc->base.name, pll->name,
+				      crtc->base.base.id, crtc->base.name,
+				      pll->info->name,
 				      shared_dpll[i].crtc_mask,
 				      pll->active_mask);
 			return pll;
@@ -275,7 +276,8 @@ intel_find_shared_dpll(struct intel_crtc *crtc,
 		pll = &dev_priv->shared_dplls[i];
 		if (shared_dpll[i].crtc_mask == 0) {
 			DRM_DEBUG_KMS("[CRTC:%d:%s] allocated %s\n",
-				      crtc->base.base.id, crtc->base.name, pll->name);
+				      crtc->base.base.id, crtc->base.name,
+				      pll->info->name);
 			return pll;
 		}
 	}
@@ -289,19 +291,19 @@ intel_reference_shared_dpll(struct intel_shared_dpll *pll,
 {
 	struct intel_shared_dpll_state *shared_dpll;
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	enum intel_dpll_id i = pll->id;
+	const enum intel_dpll_id id = pll->info->id;
 
 	shared_dpll = intel_atomic_get_shared_dpll_state(crtc_state->base.state);
 
-	if (shared_dpll[i].crtc_mask == 0)
-		shared_dpll[i].hw_state =
+	if (shared_dpll[id].crtc_mask == 0)
+		shared_dpll[id].hw_state =
 			crtc_state->dpll_hw_state;
 
 	crtc_state->shared_dpll = pll;
-	DRM_DEBUG_DRIVER("using %s for pipe %c\n", pll->name,
+	DRM_DEBUG_DRIVER("using %s for pipe %c\n", pll->info->name,
 			 pipe_name(crtc->pipe));
 
-	shared_dpll[pll->id].crtc_mask |= 1 << crtc->pipe;
+	shared_dpll[id].crtc_mask |= 1 << crtc->pipe;
 }
 
 /**
@@ -341,15 +343,16 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 				      struct intel_shared_dpll *pll,
 				      struct intel_dpll_hw_state *hw_state)
 {
+	const enum intel_dpll_id id = pll->info->id;
 	uint32_t val;
 
 	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
-	val = I915_READ(PCH_DPLL(pll->id));
+	val = I915_READ(PCH_DPLL(id));
 	hw_state->dpll = val;
-	hw_state->fp0 = I915_READ(PCH_FP0(pll->id));
-	hw_state->fp1 = I915_READ(PCH_FP1(pll->id));
+	hw_state->fp0 = I915_READ(PCH_FP0(id));
+	hw_state->fp1 = I915_READ(PCH_FP1(id));
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
 
@@ -359,8 +362,10 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 static void ibx_pch_dpll_prepare(struct drm_i915_private *dev_priv,
 				 struct intel_shared_dpll *pll)
 {
-	I915_WRITE(PCH_FP0(pll->id), pll->state.hw_state.fp0);
-	I915_WRITE(PCH_FP1(pll->id), pll->state.hw_state.fp1);
+	const enum intel_dpll_id id = pll->info->id;
+
+	I915_WRITE(PCH_FP0(id), pll->state.hw_state.fp0);
+	I915_WRITE(PCH_FP1(id), pll->state.hw_state.fp1);
 }
 
 static void ibx_assert_pch_refclk_enabled(struct drm_i915_private *dev_priv)
@@ -379,13 +384,15 @@ static void ibx_assert_pch_refclk_enabled(struct drm_i915_private *dev_priv)
 static void ibx_pch_dpll_enable(struct drm_i915_private *dev_priv,
 				struct intel_shared_dpll *pll)
 {
+	const enum intel_dpll_id id = pll->info->id;
+
 	/* PCH refclock must be enabled first */
 	ibx_assert_pch_refclk_enabled(dev_priv);
 
-	I915_WRITE(PCH_DPLL(pll->id), pll->state.hw_state.dpll);
+	I915_WRITE(PCH_DPLL(id), pll->state.hw_state.dpll);
 
 	/* Wait for the clocks to stabilize. */
-	POSTING_READ(PCH_DPLL(pll->id));
+	POSTING_READ(PCH_DPLL(id));
 	udelay(150);
 
 	/* The pixel multiplier can only be updated once the
@@ -393,14 +400,15 @@ static void ibx_pch_dpll_enable(struct drm_i915_private *dev_priv,
 	 *
 	 * So write it again.
 	 */
-	I915_WRITE(PCH_DPLL(pll->id), pll->state.hw_state.dpll);
-	POSTING_READ(PCH_DPLL(pll->id));
+	I915_WRITE(PCH_DPLL(id), pll->state.hw_state.dpll);
+	POSTING_READ(PCH_DPLL(id));
 	udelay(200);
 }
 
 static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv,
 				 struct intel_shared_dpll *pll)
 {
+	const enum intel_dpll_id id = pll->info->id;
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_crtc *crtc;
 
@@ -410,8 +418,8 @@ static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv,
 			assert_pch_transcoder_disabled(dev_priv, crtc->pipe);
 	}
 
-	I915_WRITE(PCH_DPLL(pll->id), 0);
-	POSTING_READ(PCH_DPLL(pll->id));
+	I915_WRITE(PCH_DPLL(id), 0);
+	POSTING_READ(PCH_DPLL(id));
 	udelay(200);
 }
 
@@ -429,7 +437,8 @@ ibx_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 		pll = &dev_priv->shared_dplls[i];
 
 		DRM_DEBUG_KMS("[CRTC:%d:%s] using pre-allocated %s\n",
-			      crtc->base.base.id, crtc->base.name, pll->name);
+			      crtc->base.base.id, crtc->base.name,
+			      pll->info->name);
 	} else {
 		pll = intel_find_shared_dpll(crtc, crtc_state,
 					     DPLL_ID_PCH_PLL_A,
@@ -466,8 +475,10 @@ static const struct intel_shared_dpll_funcs ibx_pch_dpll_funcs = {
 static void hsw_ddi_wrpll_enable(struct drm_i915_private *dev_priv,
 			       struct intel_shared_dpll *pll)
 {
-	I915_WRITE(WRPLL_CTL(pll->id), pll->state.hw_state.wrpll);
-	POSTING_READ(WRPLL_CTL(pll->id));
+	const enum intel_dpll_id id = pll->info->id;
+
+	I915_WRITE(WRPLL_CTL(id), pll->state.hw_state.wrpll);
+	POSTING_READ(WRPLL_CTL(id));
 	udelay(20);
 }
 
@@ -482,11 +493,12 @@ static void hsw_ddi_spll_enable(struct drm_i915_private *dev_priv,
 static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv,
 				  struct intel_shared_dpll *pll)
 {
+	const enum intel_dpll_id id = pll->info->id;
 	uint32_t val;
 
-	val = I915_READ(WRPLL_CTL(pll->id));
-	I915_WRITE(WRPLL_CTL(pll->id), val & ~WRPLL_PLL_ENABLE);
-	POSTING_READ(WRPLL_CTL(pll->id));
+	val = I915_READ(WRPLL_CTL(id));
+	I915_WRITE(WRPLL_CTL(id), val & ~WRPLL_PLL_ENABLE);
+	POSTING_READ(WRPLL_CTL(id));
 }
 
 static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv,
@@ -503,12 +515,13 @@ static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
 				       struct intel_shared_dpll *pll,
 				       struct intel_dpll_hw_state *hw_state)
 {
+	const enum intel_dpll_id id = pll->info->id;
 	uint32_t val;
 
 	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
-	val = I915_READ(WRPLL_CTL(pll->id));
+	val = I915_READ(WRPLL_CTL(id));
 	hw_state->wrpll = val;
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
@@ -914,13 +927,15 @@ static const struct skl_dpll_regs skl_dpll_regs[4] = {
 static void skl_ddi_pll_write_ctrl1(struct drm_i915_private *dev_priv,
 				    struct intel_shared_dpll *pll)
 {
+	const enum intel_dpll_id id = pll->info->id;
 	uint32_t val;
 
 	val = I915_READ(DPLL_CTRL1);
 
-	val &= ~(DPLL_CTRL1_HDMI_MODE(pll->id) | DPLL_CTRL1_SSC(pll->id) |
-		 DPLL_CTRL1_LINK_RATE_MASK(pll->id));
-	val |= pll->state.hw_state.ctrl1 << (pll->id * 6);
+	val &= ~(DPLL_CTRL1_HDMI_MODE(id) |
+		 DPLL_CTRL1_SSC(id) |
+		 DPLL_CTRL1_LINK_RATE_MASK(id));
+	val |= pll->state.hw_state.ctrl1 << (id * 6);
 
 	I915_WRITE(DPLL_CTRL1, val);
 	POSTING_READ(DPLL_CTRL1);
@@ -930,24 +945,25 @@ static void skl_ddi_pll_enable(struct drm_i915_private *dev_priv,
 			       struct intel_shared_dpll *pll)
 {
 	const struct skl_dpll_regs *regs = skl_dpll_regs;
+	const enum intel_dpll_id id = pll->info->id;
 
 	skl_ddi_pll_write_ctrl1(dev_priv, pll);
 
-	I915_WRITE(regs[pll->id].cfgcr1, pll->state.hw_state.cfgcr1);
-	I915_WRITE(regs[pll->id].cfgcr2, pll->state.hw_state.cfgcr2);
-	POSTING_READ(regs[pll->id].cfgcr1);
-	POSTING_READ(regs[pll->id].cfgcr2);
+	I915_WRITE(regs[id].cfgcr1, pll->state.hw_state.cfgcr1);
+	I915_WRITE(regs[id].cfgcr2, pll->state.hw_state.cfgcr2);
+	POSTING_READ(regs[id].cfgcr1);
+	POSTING_READ(regs[id].cfgcr2);
 
 	/* the enable bit is always bit 31 */
-	I915_WRITE(regs[pll->id].ctl,
-		   I915_READ(regs[pll->id].ctl) | LCPLL_PLL_ENABLE);
+	I915_WRITE(regs[id].ctl,
+		   I915_READ(regs[id].ctl) | LCPLL_PLL_ENABLE);
 
 	if (intel_wait_for_register(dev_priv,
 				    DPLL_STATUS,
-				    DPLL_LOCK(pll->id),
-				    DPLL_LOCK(pll->id),
+				    DPLL_LOCK(id),
+				    DPLL_LOCK(id),
 				    5))
-		DRM_ERROR("DPLL %d not locked\n", pll->id);
+		DRM_ERROR("DPLL %d not locked\n", id);
 }
 
 static void skl_ddi_dpll0_enable(struct drm_i915_private *dev_priv,
@@ -960,11 +976,12 @@ static void skl_ddi_pll_disable(struct drm_i915_private *dev_priv,
 				struct intel_shared_dpll *pll)
 {
 	const struct skl_dpll_regs *regs = skl_dpll_regs;
+	const enum intel_dpll_id id = pll->info->id;
 
 	/* the enable bit is always bit 31 */
-	I915_WRITE(regs[pll->id].ctl,
-		   I915_READ(regs[pll->id].ctl) & ~LCPLL_PLL_ENABLE);
-	POSTING_READ(regs[pll->id].ctl);
+	I915_WRITE(regs[id].ctl,
+		   I915_READ(regs[id].ctl) & ~LCPLL_PLL_ENABLE);
+	POSTING_READ(regs[id].ctl);
 }
 
 static void skl_ddi_dpll0_disable(struct drm_i915_private *dev_priv,
@@ -978,6 +995,7 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	uint32_t val;
 	const struct skl_dpll_regs *regs = skl_dpll_regs;
+	const enum intel_dpll_id id = pll->info->id;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
@@ -985,17 +1003,17 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 
 	ret = false;
 
-	val = I915_READ(regs[pll->id].ctl);
+	val = I915_READ(regs[id].ctl);
 	if (!(val & LCPLL_PLL_ENABLE))
 		goto out;
 
 	val = I915_READ(DPLL_CTRL1);
-	hw_state->ctrl1 = (val >> (pll->id * 6)) & 0x3f;
+	hw_state->ctrl1 = (val >> (id * 6)) & 0x3f;
 
 	/* avoid reading back stale values if HDMI mode is not enabled */
-	if (val & DPLL_CTRL1_HDMI_MODE(pll->id)) {
-		hw_state->cfgcr1 = I915_READ(regs[pll->id].cfgcr1);
-		hw_state->cfgcr2 = I915_READ(regs[pll->id].cfgcr2);
+	if (val & DPLL_CTRL1_HDMI_MODE(id)) {
+		hw_state->cfgcr1 = I915_READ(regs[id].cfgcr1);
+		hw_state->cfgcr2 = I915_READ(regs[id].cfgcr2);
 	}
 	ret = true;
 
@@ -1011,6 +1029,7 @@ static bool skl_ddi_dpll0_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	uint32_t val;
 	const struct skl_dpll_regs *regs = skl_dpll_regs;
+	const enum intel_dpll_id id = pll->info->id;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
@@ -1019,12 +1038,12 @@ static bool skl_ddi_dpll0_get_hw_state(struct drm_i915_private *dev_priv,
 	ret = false;
 
 	/* DPLL0 is always enabled since it drives CDCLK */
-	val = I915_READ(regs[pll->id].ctl);
+	val = I915_READ(regs[id].ctl);
 	if (WARN_ON(!(val & LCPLL_PLL_ENABLE)))
 		goto out;
 
 	val = I915_READ(DPLL_CTRL1);
-	hw_state->ctrl1 = (val >> (pll->id * 6)) & 0x3f;
+	hw_state->ctrl1 = (val >> (id * 6)) & 0x3f;
 
 	ret = true;
 
@@ -1424,7 +1443,7 @@ static void bxt_ddi_pll_enable(struct drm_i915_private *dev_priv,
 				struct intel_shared_dpll *pll)
 {
 	uint32_t temp;
-	enum port port = (enum port)pll->id;	/* 1:1 port->PLL mapping */
+	enum port port = (enum port)pll->info->id; /* 1:1 port->PLL mapping */
 	enum dpio_phy phy;
 	enum dpio_channel ch;
 
@@ -1543,7 +1562,7 @@ static void bxt_ddi_pll_enable(struct drm_i915_private *dev_priv,
 static void bxt_ddi_pll_disable(struct drm_i915_private *dev_priv,
 					struct intel_shared_dpll *pll)
 {
-	enum port port = (enum port)pll->id;	/* 1:1 port->PLL mapping */
+	enum port port = (enum port)pll->info->id; /* 1:1 port->PLL mapping */
 	uint32_t temp;
 
 	temp = I915_READ(BXT_PORT_PLL_ENABLE(port));
@@ -1566,7 +1585,7 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 					struct intel_shared_dpll *pll,
 					struct intel_dpll_hw_state *hw_state)
 {
-	enum port port = (enum port)pll->id;	/* 1:1 port->PLL mapping */
+	enum port port = (enum port)pll->info->id; /* 1:1 port->PLL mapping */
 	uint32_t val;
 	bool ret;
 	enum dpio_phy phy;
@@ -1824,7 +1843,7 @@ bxt_get_dpll(struct intel_crtc *crtc,
 	pll = intel_get_shared_dpll_by_id(dev_priv, i);
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s] using pre-allocated %s\n",
-		      crtc->base.base.id, crtc->base.name, pll->name);
+		      crtc->base.base.id, crtc->base.name, pll->info->name);
 
 	intel_reference_shared_dpll(pll, crtc_state);
 
@@ -1877,13 +1896,6 @@ static void intel_ddi_pll_init(struct drm_device *dev)
 	}
 }
 
-struct dpll_info {
-	const char *name;
-	const int id;
-	const struct intel_shared_dpll_funcs *funcs;
-	uint32_t flags;
-};
-
 struct intel_dpll_mgr {
 	const struct dpll_info *dpll_info;
 
@@ -1896,9 +1908,9 @@ struct intel_dpll_mgr {
 };
 
 static const struct dpll_info pch_plls[] = {
-	{ "PCH DPLL A", DPLL_ID_PCH_PLL_A, &ibx_pch_dpll_funcs, 0 },
-	{ "PCH DPLL B", DPLL_ID_PCH_PLL_B, &ibx_pch_dpll_funcs, 0 },
-	{ NULL, -1, NULL, 0 },
+	{ "PCH DPLL A", &ibx_pch_dpll_funcs, DPLL_ID_PCH_PLL_A, 0 },
+	{ "PCH DPLL B", &ibx_pch_dpll_funcs, DPLL_ID_PCH_PLL_B, 0 },
+	{ },
 };
 
 static const struct intel_dpll_mgr pch_pll_mgr = {
@@ -1908,13 +1920,13 @@ static const struct intel_dpll_mgr pch_pll_mgr = {
 };
 
 static const struct dpll_info hsw_plls[] = {
-	{ "WRPLL 1",    DPLL_ID_WRPLL1,     &hsw_ddi_wrpll_funcs, 0 },
-	{ "WRPLL 2",    DPLL_ID_WRPLL2,     &hsw_ddi_wrpll_funcs, 0 },
-	{ "SPLL",       DPLL_ID_SPLL,       &hsw_ddi_spll_funcs,  0 },
-	{ "LCPLL 810",  DPLL_ID_LCPLL_810,  &hsw_ddi_lcpll_funcs, INTEL_DPLL_ALWAYS_ON },
-	{ "LCPLL 1350", DPLL_ID_LCPLL_1350, &hsw_ddi_lcpll_funcs, INTEL_DPLL_ALWAYS_ON },
-	{ "LCPLL 2700", DPLL_ID_LCPLL_2700, &hsw_ddi_lcpll_funcs, INTEL_DPLL_ALWAYS_ON },
-	{ NULL, -1, NULL, },
+	{ "WRPLL 1",    &hsw_ddi_wrpll_funcs, DPLL_ID_WRPLL1,     0 },
+	{ "WRPLL 2",    &hsw_ddi_wrpll_funcs, DPLL_ID_WRPLL2,     0 },
+	{ "SPLL",       &hsw_ddi_spll_funcs,  DPLL_ID_SPLL,       0 },
+	{ "LCPLL 810",  &hsw_ddi_lcpll_funcs, DPLL_ID_LCPLL_810,  INTEL_DPLL_ALWAYS_ON },
+	{ "LCPLL 1350", &hsw_ddi_lcpll_funcs, DPLL_ID_LCPLL_1350, INTEL_DPLL_ALWAYS_ON },
+	{ "LCPLL 2700", &hsw_ddi_lcpll_funcs, DPLL_ID_LCPLL_2700, INTEL_DPLL_ALWAYS_ON },
+	{ },
 };
 
 static const struct intel_dpll_mgr hsw_pll_mgr = {
@@ -1924,11 +1936,11 @@ static const struct intel_dpll_mgr hsw_pll_mgr = {
 };
 
 static const struct dpll_info skl_plls[] = {
-	{ "DPLL 0", DPLL_ID_SKL_DPLL0, &skl_ddi_dpll0_funcs, INTEL_DPLL_ALWAYS_ON },
-	{ "DPLL 1", DPLL_ID_SKL_DPLL1, &skl_ddi_pll_funcs,   0 },
-	{ "DPLL 2", DPLL_ID_SKL_DPLL2, &skl_ddi_pll_funcs,   0 },
-	{ "DPLL 3", DPLL_ID_SKL_DPLL3, &skl_ddi_pll_funcs,   0 },
-	{ NULL, -1, NULL, },
+	{ "DPLL 0", &skl_ddi_dpll0_funcs, DPLL_ID_SKL_DPLL0, INTEL_DPLL_ALWAYS_ON },
+	{ "DPLL 1", &skl_ddi_pll_funcs,   DPLL_ID_SKL_DPLL1, 0 },
+	{ "DPLL 2", &skl_ddi_pll_funcs,   DPLL_ID_SKL_DPLL2, 0 },
+	{ "DPLL 3", &skl_ddi_pll_funcs,   DPLL_ID_SKL_DPLL3, 0 },
+	{ },
 };
 
 static const struct intel_dpll_mgr skl_pll_mgr = {
@@ -1938,10 +1950,10 @@ static const struct intel_dpll_mgr skl_pll_mgr = {
 };
 
 static const struct dpll_info bxt_plls[] = {
-	{ "PORT PLL A", DPLL_ID_SKL_DPLL0, &bxt_ddi_pll_funcs, 0 },
-	{ "PORT PLL B", DPLL_ID_SKL_DPLL1, &bxt_ddi_pll_funcs, 0 },
-	{ "PORT PLL C", DPLL_ID_SKL_DPLL2, &bxt_ddi_pll_funcs, 0 },
-	{ NULL, -1, NULL, },
+	{ "PORT PLL A", &bxt_ddi_pll_funcs, DPLL_ID_SKL_DPLL0, 0 },
+	{ "PORT PLL B", &bxt_ddi_pll_funcs, DPLL_ID_SKL_DPLL1, 0 },
+	{ "PORT PLL C", &bxt_ddi_pll_funcs, DPLL_ID_SKL_DPLL2, 0 },
+	{ },
 };
 
 static const struct intel_dpll_mgr bxt_pll_mgr = {
@@ -1953,38 +1965,39 @@ static const struct intel_dpll_mgr bxt_pll_mgr = {
 static void cnl_ddi_pll_enable(struct drm_i915_private *dev_priv,
 			       struct intel_shared_dpll *pll)
 {
+	const enum intel_dpll_id id = pll->info->id;
 	uint32_t val;
 
 	/* 1. Enable DPLL power in DPLL_ENABLE. */
-	val = I915_READ(CNL_DPLL_ENABLE(pll->id));
+	val = I915_READ(CNL_DPLL_ENABLE(id));
 	val |= PLL_POWER_ENABLE;
-	I915_WRITE(CNL_DPLL_ENABLE(pll->id), val);
+	I915_WRITE(CNL_DPLL_ENABLE(id), val);
 
 	/* 2. Wait for DPLL power state enabled in DPLL_ENABLE. */
 	if (intel_wait_for_register(dev_priv,
-				    CNL_DPLL_ENABLE(pll->id),
+				    CNL_DPLL_ENABLE(id),
 				    PLL_POWER_STATE,
 				    PLL_POWER_STATE,
 				    5))
-		DRM_ERROR("PLL %d Power not enabled\n", pll->id);
+		DRM_ERROR("PLL %d Power not enabled\n", id);
 
 	/*
 	 * 3. Configure DPLL_CFGCR0 to set SSC enable/disable,
 	 * select DP mode, and set DP link rate.
 	 */
 	val = pll->state.hw_state.cfgcr0;
-	I915_WRITE(CNL_DPLL_CFGCR0(pll->id), val);
+	I915_WRITE(CNL_DPLL_CFGCR0(id), val);
 
 	/* 4. Reab back to ensure writes completed */
-	POSTING_READ(CNL_DPLL_CFGCR0(pll->id));
+	POSTING_READ(CNL_DPLL_CFGCR0(id));
 
 	/* 3. Configure DPLL_CFGCR0 */
 	/* Avoid touch CFGCR1 if HDMI mode is not enabled */
 	if (pll->state.hw_state.cfgcr0 & DPLL_CFGCR0_HDMI_MODE) {
 		val = pll->state.hw_state.cfgcr1;
-		I915_WRITE(CNL_DPLL_CFGCR1(pll->id), val);
+		I915_WRITE(CNL_DPLL_CFGCR1(id), val);
 		/* 4. Reab back to ensure writes completed */
-		POSTING_READ(CNL_DPLL_CFGCR1(pll->id));
+		POSTING_READ(CNL_DPLL_CFGCR1(id));
 	}
 
 	/*
@@ -1997,17 +2010,17 @@ static void cnl_ddi_pll_enable(struct drm_i915_private *dev_priv,
 	 */
 
 	/* 6. Enable DPLL in DPLL_ENABLE. */
-	val = I915_READ(CNL_DPLL_ENABLE(pll->id));
+	val = I915_READ(CNL_DPLL_ENABLE(id));
 	val |= PLL_ENABLE;
-	I915_WRITE(CNL_DPLL_ENABLE(pll->id), val);
+	I915_WRITE(CNL_DPLL_ENABLE(id), val);
 
 	/* 7. Wait for PLL lock status in DPLL_ENABLE. */
 	if (intel_wait_for_register(dev_priv,
-				    CNL_DPLL_ENABLE(pll->id),
+				    CNL_DPLL_ENABLE(id),
 				    PLL_LOCK,
 				    PLL_LOCK,
 				    5))
-		DRM_ERROR("PLL %d not locked\n", pll->id);
+		DRM_ERROR("PLL %d not locked\n", id);
 
 	/*
 	 * 8. If the frequency will result in a change to the voltage
@@ -2027,6 +2040,7 @@ static void cnl_ddi_pll_enable(struct drm_i915_private *dev_priv,
 static void cnl_ddi_pll_disable(struct drm_i915_private *dev_priv,
 				struct intel_shared_dpll *pll)
 {
+	const enum intel_dpll_id id = pll->info->id;
 	uint32_t val;
 
 	/*
@@ -2044,17 +2058,17 @@ static void cnl_ddi_pll_disable(struct drm_i915_private *dev_priv,
 	 */
 
 	/* 3. Disable DPLL through DPLL_ENABLE. */
-	val = I915_READ(CNL_DPLL_ENABLE(pll->id));
+	val = I915_READ(CNL_DPLL_ENABLE(id));
 	val &= ~PLL_ENABLE;
-	I915_WRITE(CNL_DPLL_ENABLE(pll->id), val);
+	I915_WRITE(CNL_DPLL_ENABLE(id), val);
 
 	/* 4. Wait for PLL not locked status in DPLL_ENABLE. */
 	if (intel_wait_for_register(dev_priv,
-				    CNL_DPLL_ENABLE(pll->id),
+				    CNL_DPLL_ENABLE(id),
 				    PLL_LOCK,
 				    0,
 				    5))
-		DRM_ERROR("PLL %d locked\n", pll->id);
+		DRM_ERROR("PLL %d locked\n", id);
 
 	/*
 	 * 5. If the frequency will result in a change to the voltage
@@ -2066,23 +2080,24 @@ static void cnl_ddi_pll_disable(struct drm_i915_private *dev_priv,
 	 */
 
 	/* 6. Disable DPLL power in DPLL_ENABLE. */
-	val = I915_READ(CNL_DPLL_ENABLE(pll->id));
+	val = I915_READ(CNL_DPLL_ENABLE(id));
 	val &= ~PLL_POWER_ENABLE;
-	I915_WRITE(CNL_DPLL_ENABLE(pll->id), val);
+	I915_WRITE(CNL_DPLL_ENABLE(id), val);
 
 	/* 7. Wait for DPLL power state disabled in DPLL_ENABLE. */
 	if (intel_wait_for_register(dev_priv,
-				    CNL_DPLL_ENABLE(pll->id),
+				    CNL_DPLL_ENABLE(id),
 				    PLL_POWER_STATE,
 				    0,
 				    5))
-		DRM_ERROR("PLL %d Power not disabled\n", pll->id);
+		DRM_ERROR("PLL %d Power not disabled\n", id);
 }
 
 static bool cnl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 				     struct intel_shared_dpll *pll,
 				     struct intel_dpll_hw_state *hw_state)
 {
+	const enum intel_dpll_id id = pll->info->id;
 	uint32_t val;
 	bool ret;
 
@@ -2091,16 +2106,16 @@ static bool cnl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 
 	ret = false;
 
-	val = I915_READ(CNL_DPLL_ENABLE(pll->id));
+	val = I915_READ(CNL_DPLL_ENABLE(id));
 	if (!(val & PLL_ENABLE))
 		goto out;
 
-	val = I915_READ(CNL_DPLL_CFGCR0(pll->id));
+	val = I915_READ(CNL_DPLL_CFGCR0(id));
 	hw_state->cfgcr0 = val;
 
 	/* avoid reading back stale values if HDMI mode is not enabled */
 	if (val & DPLL_CFGCR0_HDMI_MODE) {
-		hw_state->cfgcr1 = I915_READ(CNL_DPLL_CFGCR1(pll->id));
+		hw_state->cfgcr1 = I915_READ(CNL_DPLL_CFGCR1(id));
 	}
 	ret = true;
 
@@ -2203,6 +2218,7 @@ cnl_ddi_calculate_wrpll(int clock,
 			struct skl_wrpll_params *wrpll_params)
 {
 	u32 afe_clock = clock * 5;
+	uint32_t ref_clock;
 	u32 dco_min = 7998000;
 	u32 dco_max = 10000000;
 	u32 dco_mid = (dco_min + dco_max) / 2;
@@ -2235,8 +2251,17 @@ cnl_ddi_calculate_wrpll(int clock,
 
 	cnl_wrpll_get_multipliers(best_div, &pdiv, &qdiv, &kdiv);
 
-	cnl_wrpll_params_populate(wrpll_params, best_dco,
-				  dev_priv->cdclk.hw.ref, pdiv, qdiv, kdiv);
+	ref_clock = dev_priv->cdclk.hw.ref;
+
+	/*
+	 * For ICL, the spec states: if reference frequency is 38.4, use 19.2
+	 * because the DPLL automatically divides that by 2.
+	 */
+	if (IS_ICELAKE(dev_priv) && ref_clock == 38400)
+		ref_clock = 19200;
+
+	cnl_wrpll_params_populate(wrpll_params, best_dco, ref_clock, pdiv, qdiv,
+				  kdiv);
 
 	return true;
 }
@@ -2372,10 +2397,10 @@ static const struct intel_shared_dpll_funcs cnl_ddi_pll_funcs = {
 };
 
 static const struct dpll_info cnl_plls[] = {
-	{ "DPLL 0", DPLL_ID_SKL_DPLL0, &cnl_ddi_pll_funcs, 0 },
-	{ "DPLL 1", DPLL_ID_SKL_DPLL1, &cnl_ddi_pll_funcs, 0 },
-	{ "DPLL 2", DPLL_ID_SKL_DPLL2, &cnl_ddi_pll_funcs, 0 },
-	{ NULL, -1, NULL, },
+	{ "DPLL 0", &cnl_ddi_pll_funcs, DPLL_ID_SKL_DPLL0, 0 },
+	{ "DPLL 1", &cnl_ddi_pll_funcs, DPLL_ID_SKL_DPLL1, 0 },
+	{ "DPLL 2", &cnl_ddi_pll_funcs, DPLL_ID_SKL_DPLL2, 0 },
+	{ },
 };
 
 static const struct intel_dpll_mgr cnl_pll_mgr = {
@@ -2384,6 +2409,644 @@ static const struct intel_dpll_mgr cnl_pll_mgr = {
 	.dump_hw_state = cnl_dump_hw_state,
 };
 
+/*
+ * These values alrea already adjusted: they're the bits we write to the
+ * registers, not the logical values.
+ */
+static const struct skl_wrpll_params icl_dp_combo_pll_24MHz_values[] = {
+	{ .dco_integer = 0x151, .dco_fraction = 0x4000,		/* [0]: 5.4 */
+	  .pdiv = 0x2 /* 3 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x151, .dco_fraction = 0x4000,		/* [1]: 2.7 */
+	  .pdiv = 0x2 /* 3 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x151, .dco_fraction = 0x4000,		/* [2]: 1.62 */
+	  .pdiv = 0x4 /* 5 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x151, .dco_fraction = 0x4000,		/* [3]: 3.24 */
+	  .pdiv = 0x4 /* 5 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x168, .dco_fraction = 0x0000,		/* [4]: 2.16 */
+	  .pdiv = 0x1 /* 2 */, .kdiv = 2, .qdiv_mode = 1, .qdiv_ratio = 2},
+	{ .dco_integer = 0x168, .dco_fraction = 0x0000,		/* [5]: 4.32 */
+	  .pdiv = 0x1 /* 2 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x195, .dco_fraction = 0x0000,		/* [6]: 6.48 */
+	  .pdiv = 0x2 /* 3 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x151, .dco_fraction = 0x4000,		/* [7]: 8.1 */
+	  .pdiv = 0x1 /* 2 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0},
+};
+
+/* Also used for 38.4 MHz values. */
+static const struct skl_wrpll_params icl_dp_combo_pll_19_2MHz_values[] = {
+	{ .dco_integer = 0x1A5, .dco_fraction = 0x7000,		/* [0]: 5.4 */
+	  .pdiv = 0x2 /* 3 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x1A5, .dco_fraction = 0x7000,		/* [1]: 2.7 */
+	  .pdiv = 0x2 /* 3 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x1A5, .dco_fraction = 0x7000,		/* [2]: 1.62 */
+	  .pdiv = 0x4 /* 5 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x1A5, .dco_fraction = 0x7000,		/* [3]: 3.24 */
+	  .pdiv = 0x4 /* 5 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x1C2, .dco_fraction = 0x0000,		/* [4]: 2.16 */
+	  .pdiv = 0x1 /* 2 */, .kdiv = 2, .qdiv_mode = 1, .qdiv_ratio = 2},
+	{ .dco_integer = 0x1C2, .dco_fraction = 0x0000,		/* [5]: 4.32 */
+	  .pdiv = 0x1 /* 2 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x1FA, .dco_fraction = 0x2000,		/* [6]: 6.48 */
+	  .pdiv = 0x2 /* 3 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0},
+	{ .dco_integer = 0x1A5, .dco_fraction = 0x7000,		/* [7]: 8.1 */
+	  .pdiv = 0x1 /* 2 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0},
+};
+
+static bool icl_calc_dp_combo_pll(struct drm_i915_private *dev_priv, int clock,
+				  struct skl_wrpll_params *pll_params)
+{
+	const struct skl_wrpll_params *params;
+
+	params = dev_priv->cdclk.hw.ref == 24000 ?
+			icl_dp_combo_pll_24MHz_values :
+			icl_dp_combo_pll_19_2MHz_values;
+
+	switch (clock) {
+	case 540000:
+		*pll_params = params[0];
+		break;
+	case 270000:
+		*pll_params = params[1];
+		break;
+	case 162000:
+		*pll_params = params[2];
+		break;
+	case 324000:
+		*pll_params = params[3];
+		break;
+	case 216000:
+		*pll_params = params[4];
+		break;
+	case 432000:
+		*pll_params = params[5];
+		break;
+	case 648000:
+		*pll_params = params[6];
+		break;
+	case 810000:
+		*pll_params = params[7];
+		break;
+	default:
+		MISSING_CASE(clock);
+		return false;
+	}
+
+	return true;
+}
+
+static bool icl_calc_dpll_state(struct intel_crtc_state *crtc_state,
+				struct intel_encoder *encoder, int clock,
+				struct intel_dpll_hw_state *pll_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	uint32_t cfgcr0, cfgcr1;
+	struct skl_wrpll_params pll_params = { 0 };
+	bool ret;
+
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
+		ret = cnl_ddi_calculate_wrpll(clock, dev_priv, &pll_params);
+	else
+		ret = icl_calc_dp_combo_pll(dev_priv, clock, &pll_params);
+
+	if (!ret)
+		return false;
+
+	cfgcr0 = DPLL_CFGCR0_DCO_FRACTION(pll_params.dco_fraction) |
+		 pll_params.dco_integer;
+
+	cfgcr1 = DPLL_CFGCR1_QDIV_RATIO(pll_params.qdiv_ratio) |
+		 DPLL_CFGCR1_QDIV_MODE(pll_params.qdiv_mode) |
+		 DPLL_CFGCR1_KDIV(pll_params.kdiv) |
+		 DPLL_CFGCR1_PDIV(pll_params.pdiv) |
+		 DPLL_CFGCR1_CENTRAL_FREQ_8400;
+
+	pll_state->cfgcr0 = cfgcr0;
+	pll_state->cfgcr1 = cfgcr1;
+	return true;
+}
+
+static enum port icl_mg_pll_id_to_port(enum intel_dpll_id id)
+{
+	return id - DPLL_ID_ICL_MGPLL1 + PORT_C;
+}
+
+static enum intel_dpll_id icl_port_to_mg_pll_id(enum port port)
+{
+	return port - PORT_C + DPLL_ID_ICL_MGPLL1;
+}
+
+static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
+				     uint32_t *target_dco_khz,
+				     struct intel_dpll_hw_state *state)
+{
+	uint32_t dco_min_freq, dco_max_freq;
+	int div1_vals[] = {7, 5, 3, 2};
+	unsigned int i;
+	int div2;
+
+	dco_min_freq = is_dp ? 8100000 : use_ssc ? 8000000 : 7992000;
+	dco_max_freq = is_dp ? 8100000 : 10000000;
+
+	for (i = 0; i < ARRAY_SIZE(div1_vals); i++) {
+		int div1 = div1_vals[i];
+
+		for (div2 = 10; div2 > 0; div2--) {
+			int dco = div1 * div2 * clock_khz * 5;
+			int a_divratio, tlinedrv, inputsel, hsdiv;
+
+			if (dco < dco_min_freq || dco > dco_max_freq)
+				continue;
+
+			if (div2 >= 2) {
+				a_divratio = is_dp ? 10 : 5;
+				tlinedrv = 2;
+			} else {
+				a_divratio = 5;
+				tlinedrv = 0;
+			}
+			inputsel = is_dp ? 0 : 1;
+
+			switch (div1) {
+			default:
+				MISSING_CASE(div1);
+			case 2:
+				hsdiv = 0;
+				break;
+			case 3:
+				hsdiv = 1;
+				break;
+			case 5:
+				hsdiv = 2;
+				break;
+			case 7:
+				hsdiv = 3;
+				break;
+			}
+
+			*target_dco_khz = dco;
+
+			state->mg_refclkin_ctl = MG_REFCLKIN_CTL_OD_2_MUX(1);
+
+			state->mg_clktop2_coreclkctl1 =
+				MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO(a_divratio);
+
+			state->mg_clktop2_hsclkctl =
+				MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL(tlinedrv) |
+				MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL(inputsel) |
+				MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO(hsdiv) |
+				MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO(div2);
+
+			return true;
+		}
+	}
+
+	return false;
+}
+
+/*
+ * The specification for this function uses real numbers, so the math had to be
+ * adapted to integer-only calculation, that's why it looks so different.
+ */
+static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
+				  struct intel_encoder *encoder, int clock,
+				  struct intel_dpll_hw_state *pll_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	int refclk_khz = dev_priv->cdclk.hw.ref;
+	uint32_t dco_khz, m1div, m2div_int, m2div_rem, m2div_frac;
+	uint32_t iref_ndiv, iref_trim, iref_pulse_w;
+	uint32_t prop_coeff, int_coeff;
+	uint32_t tdc_targetcnt, feedfwgain;
+	uint64_t ssc_stepsize, ssc_steplen, ssc_steplog;
+	uint64_t tmp;
+	bool use_ssc = false;
+	bool is_dp = !intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI);
+
+	if (!icl_mg_pll_find_divisors(clock, is_dp, use_ssc, &dco_khz,
+				      pll_state)) {
+		DRM_DEBUG_KMS("Failed to find divisors for clock %d\n", clock);
+		return false;
+	}
+
+	m1div = 2;
+	m2div_int = dco_khz / (refclk_khz * m1div);
+	if (m2div_int > 255) {
+		m1div = 4;
+		m2div_int = dco_khz / (refclk_khz * m1div);
+		if (m2div_int > 255) {
+			DRM_DEBUG_KMS("Failed to find mdiv for clock %d\n",
+				      clock);
+			return false;
+		}
+	}
+	m2div_rem = dco_khz % (refclk_khz * m1div);
+
+	tmp = (uint64_t)m2div_rem * (1 << 22);
+	do_div(tmp, refclk_khz * m1div);
+	m2div_frac = tmp;
+
+	switch (refclk_khz) {
+	case 19200:
+		iref_ndiv = 1;
+		iref_trim = 28;
+		iref_pulse_w = 1;
+		break;
+	case 24000:
+		iref_ndiv = 1;
+		iref_trim = 25;
+		iref_pulse_w = 2;
+		break;
+	case 38400:
+		iref_ndiv = 2;
+		iref_trim = 28;
+		iref_pulse_w = 1;
+		break;
+	default:
+		MISSING_CASE(refclk_khz);
+		return false;
+	}
+
+	/*
+	 * tdc_res = 0.000003
+	 * tdc_targetcnt = int(2 / (tdc_res * 8 * 50 * 1.1) / refclk_mhz + 0.5)
+	 *
+	 * The multiplication by 1000 is due to refclk MHz to KHz conversion. It
+	 * was supposed to be a division, but we rearranged the operations of
+	 * the formula to avoid early divisions so we don't multiply the
+	 * rounding errors.
+	 *
+	 * 0.000003 * 8 * 50 * 1.1 = 0.00132, also known as 132 / 100000, which
+	 * we also rearrange to work with integers.
+	 *
+	 * The 0.5 transformed to 5 results in a multiplication by 10 and the
+	 * last division by 10.
+	 */
+	tdc_targetcnt = (2 * 1000 * 100000 * 10 / (132 * refclk_khz) + 5) / 10;
+
+	/*
+	 * Here we divide dco_khz by 10 in order to allow the dividend to fit in
+	 * 32 bits. That's not a problem since we round the division down
+	 * anyway.
+	 */
+	feedfwgain = (use_ssc || m2div_rem > 0) ?
+		m1div * 1000000 * 100 / (dco_khz * 3 / 10) : 0;
+
+	if (dco_khz >= 9000000) {
+		prop_coeff = 5;
+		int_coeff = 10;
+	} else {
+		prop_coeff = 4;
+		int_coeff = 8;
+	}
+
+	if (use_ssc) {
+		tmp = (uint64_t)dco_khz * 47 * 32;
+		do_div(tmp, refclk_khz * m1div * 10000);
+		ssc_stepsize = tmp;
+
+		tmp = (uint64_t)dco_khz * 1000;
+		ssc_steplen = DIV_ROUND_UP_ULL(tmp, 32 * 2 * 32);
+	} else {
+		ssc_stepsize = 0;
+		ssc_steplen = 0;
+	}
+	ssc_steplog = 4;
+
+	pll_state->mg_pll_div0 = (m2div_rem > 0 ? MG_PLL_DIV0_FRACNEN_H : 0) |
+				  MG_PLL_DIV0_FBDIV_FRAC(m2div_frac) |
+				  MG_PLL_DIV0_FBDIV_INT(m2div_int);
+
+	pll_state->mg_pll_div1 = MG_PLL_DIV1_IREF_NDIVRATIO(iref_ndiv) |
+				 MG_PLL_DIV1_DITHER_DIV_2 |
+				 MG_PLL_DIV1_NDIVRATIO(1) |
+				 MG_PLL_DIV1_FBPREDIV(m1div);
+
+	pll_state->mg_pll_lf = MG_PLL_LF_TDCTARGETCNT(tdc_targetcnt) |
+			       MG_PLL_LF_AFCCNTSEL_512 |
+			       MG_PLL_LF_GAINCTRL(1) |
+			       MG_PLL_LF_INT_COEFF(int_coeff) |
+			       MG_PLL_LF_PROP_COEFF(prop_coeff);
+
+	pll_state->mg_pll_frac_lock = MG_PLL_FRAC_LOCK_TRUELOCK_CRIT_32 |
+				      MG_PLL_FRAC_LOCK_EARLYLOCK_CRIT_32 |
+				      MG_PLL_FRAC_LOCK_LOCKTHRESH(10) |
+				      MG_PLL_FRAC_LOCK_DCODITHEREN |
+				      MG_PLL_FRAC_LOCK_FEEDFWRDGAIN(feedfwgain);
+	if (use_ssc || m2div_rem > 0)
+		pll_state->mg_pll_frac_lock |= MG_PLL_FRAC_LOCK_FEEDFWRDCAL_EN;
+
+	pll_state->mg_pll_ssc = (use_ssc ? MG_PLL_SSC_EN : 0) |
+				MG_PLL_SSC_TYPE(2) |
+				MG_PLL_SSC_STEPLENGTH(ssc_steplen) |
+				MG_PLL_SSC_STEPNUM(ssc_steplog) |
+				MG_PLL_SSC_FLLEN |
+				MG_PLL_SSC_STEPSIZE(ssc_stepsize);
+
+	pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART;
+
+	if (refclk_khz != 38400) {
+		pll_state->mg_pll_tdc_coldst_bias |=
+			MG_PLL_TDC_COLDST_IREFINT_EN |
+			MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
+			MG_PLL_TDC_COLDST_COLDSTART |
+			MG_PLL_TDC_TDCOVCCORR_EN |
+			MG_PLL_TDC_TDCSEL(3);
+
+		pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) |
+					 MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
+					 MG_PLL_BIAS_BIAS_BONUS(10) |
+					 MG_PLL_BIAS_BIASCAL_EN |
+					 MG_PLL_BIAS_CTRIM(12) |
+					 MG_PLL_BIAS_VREF_RDAC(4) |
+					 MG_PLL_BIAS_IREFTRIM(iref_trim);
+	}
+
+	return true;
+}
+
+static struct intel_shared_dpll *
+icl_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
+	     struct intel_encoder *encoder)
+{
+	struct intel_shared_dpll *pll;
+	struct intel_dpll_hw_state pll_state = {};
+	enum port port = encoder->port;
+	enum intel_dpll_id min, max;
+	int clock = crtc_state->port_clock;
+	bool ret;
+
+	switch (port) {
+	case PORT_A:
+	case PORT_B:
+		min = DPLL_ID_ICL_DPLL0;
+		max = DPLL_ID_ICL_DPLL1;
+		ret = icl_calc_dpll_state(crtc_state, encoder, clock,
+					  &pll_state);
+		break;
+	case PORT_C:
+	case PORT_D:
+	case PORT_E:
+	case PORT_F:
+		min = icl_port_to_mg_pll_id(port);
+		max = min;
+		ret = icl_calc_mg_pll_state(crtc_state, encoder, clock,
+					    &pll_state);
+		break;
+	default:
+		MISSING_CASE(port);
+		return NULL;
+	}
+
+	if (!ret) {
+		DRM_DEBUG_KMS("Could not calculate PLL state.\n");
+		return NULL;
+	}
+
+	crtc_state->dpll_hw_state = pll_state;
+
+	pll = intel_find_shared_dpll(crtc, crtc_state, min, max);
+	if (!pll) {
+		DRM_DEBUG_KMS("No PLL selected\n");
+		return NULL;
+	}
+
+	intel_reference_shared_dpll(pll, crtc_state);
+
+	return pll;
+}
+
+static i915_reg_t icl_pll_id_to_enable_reg(enum intel_dpll_id id)
+{
+	switch (id) {
+	default:
+		MISSING_CASE(id);
+	case DPLL_ID_ICL_DPLL0:
+	case DPLL_ID_ICL_DPLL1:
+		return CNL_DPLL_ENABLE(id);
+	case DPLL_ID_ICL_MGPLL1:
+	case DPLL_ID_ICL_MGPLL2:
+	case DPLL_ID_ICL_MGPLL3:
+	case DPLL_ID_ICL_MGPLL4:
+		return MG_PLL_ENABLE(icl_mg_pll_id_to_port(id));
+	}
+}
+
+static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
+				 struct intel_shared_dpll *pll,
+				 struct intel_dpll_hw_state *hw_state)
+{
+	const enum intel_dpll_id id = pll->info->id;
+	uint32_t val;
+	enum port port;
+	bool ret = false;
+
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+		return false;
+
+	val = I915_READ(icl_pll_id_to_enable_reg(id));
+	if (!(val & PLL_ENABLE))
+		goto out;
+
+	switch (id) {
+	case DPLL_ID_ICL_DPLL0:
+	case DPLL_ID_ICL_DPLL1:
+		hw_state->cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(id));
+		hw_state->cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(id));
+		break;
+	case DPLL_ID_ICL_MGPLL1:
+	case DPLL_ID_ICL_MGPLL2:
+	case DPLL_ID_ICL_MGPLL3:
+	case DPLL_ID_ICL_MGPLL4:
+		port = icl_mg_pll_id_to_port(id);
+		hw_state->mg_refclkin_ctl = I915_READ(MG_REFCLKIN_CTL(port));
+		hw_state->mg_clktop2_coreclkctl1 =
+			I915_READ(MG_CLKTOP2_CORECLKCTL1(port));
+		hw_state->mg_clktop2_hsclkctl =
+			I915_READ(MG_CLKTOP2_HSCLKCTL(port));
+		hw_state->mg_pll_div0 = I915_READ(MG_PLL_DIV0(port));
+		hw_state->mg_pll_div1 = I915_READ(MG_PLL_DIV1(port));
+		hw_state->mg_pll_lf = I915_READ(MG_PLL_LF(port));
+		hw_state->mg_pll_frac_lock = I915_READ(MG_PLL_FRAC_LOCK(port));
+		hw_state->mg_pll_ssc = I915_READ(MG_PLL_SSC(port));
+		hw_state->mg_pll_bias = I915_READ(MG_PLL_BIAS(port));
+		hw_state->mg_pll_tdc_coldst_bias =
+			I915_READ(MG_PLL_TDC_COLDST_BIAS(port));
+		break;
+	default:
+		MISSING_CASE(id);
+	}
+
+	ret = true;
+out:
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	return ret;
+}
+
+static void icl_dpll_write(struct drm_i915_private *dev_priv,
+			   struct intel_shared_dpll *pll)
+{
+	struct intel_dpll_hw_state *hw_state = &pll->state.hw_state;
+	const enum intel_dpll_id id = pll->info->id;
+
+	I915_WRITE(ICL_DPLL_CFGCR0(id), hw_state->cfgcr0);
+	I915_WRITE(ICL_DPLL_CFGCR1(id), hw_state->cfgcr1);
+	POSTING_READ(ICL_DPLL_CFGCR1(id));
+}
+
+static void icl_mg_pll_write(struct drm_i915_private *dev_priv,
+			     struct intel_shared_dpll *pll)
+{
+	struct intel_dpll_hw_state *hw_state = &pll->state.hw_state;
+	enum port port = icl_mg_pll_id_to_port(pll->info->id);
+
+	I915_WRITE(MG_REFCLKIN_CTL(port), hw_state->mg_refclkin_ctl);
+	I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port),
+		   hw_state->mg_clktop2_coreclkctl1);
+	I915_WRITE(MG_CLKTOP2_HSCLKCTL(port), hw_state->mg_clktop2_hsclkctl);
+	I915_WRITE(MG_PLL_DIV0(port), hw_state->mg_pll_div0);
+	I915_WRITE(MG_PLL_DIV1(port), hw_state->mg_pll_div1);
+	I915_WRITE(MG_PLL_LF(port), hw_state->mg_pll_lf);
+	I915_WRITE(MG_PLL_FRAC_LOCK(port), hw_state->mg_pll_frac_lock);
+	I915_WRITE(MG_PLL_SSC(port), hw_state->mg_pll_ssc);
+	I915_WRITE(MG_PLL_BIAS(port), hw_state->mg_pll_bias);
+	I915_WRITE(MG_PLL_TDC_COLDST_BIAS(port),
+		   hw_state->mg_pll_tdc_coldst_bias);
+	POSTING_READ(MG_PLL_TDC_COLDST_BIAS(port));
+}
+
+static void icl_pll_enable(struct drm_i915_private *dev_priv,
+			   struct intel_shared_dpll *pll)
+{
+	const enum intel_dpll_id id = pll->info->id;
+	i915_reg_t enable_reg = icl_pll_id_to_enable_reg(id);
+	uint32_t val;
+
+	val = I915_READ(enable_reg);
+	val |= PLL_POWER_ENABLE;
+	I915_WRITE(enable_reg, val);
+
+	/*
+	 * The spec says we need to "wait" but it also says it should be
+	 * immediate.
+	 */
+	if (intel_wait_for_register(dev_priv, enable_reg, PLL_POWER_STATE,
+				    PLL_POWER_STATE, 1))
+		DRM_ERROR("PLL %d Power not enabled\n", id);
+
+	switch (id) {
+	case DPLL_ID_ICL_DPLL0:
+	case DPLL_ID_ICL_DPLL1:
+		icl_dpll_write(dev_priv, pll);
+		break;
+	case DPLL_ID_ICL_MGPLL1:
+	case DPLL_ID_ICL_MGPLL2:
+	case DPLL_ID_ICL_MGPLL3:
+	case DPLL_ID_ICL_MGPLL4:
+		icl_mg_pll_write(dev_priv, pll);
+		break;
+	default:
+		MISSING_CASE(id);
+	}
+
+	/*
+	 * DVFS pre sequence would be here, but in our driver the cdclk code
+	 * paths should already be setting the appropriate voltage, hence we do
+	 * nothign here.
+	 */
+
+	val = I915_READ(enable_reg);
+	val |= PLL_ENABLE;
+	I915_WRITE(enable_reg, val);
+
+	if (intel_wait_for_register(dev_priv, enable_reg, PLL_LOCK, PLL_LOCK,
+				    1)) /* 600us actually. */
+		DRM_ERROR("PLL %d not locked\n", id);
+
+	/* DVFS post sequence would be here. See the comment above. */
+}
+
+static void icl_pll_disable(struct drm_i915_private *dev_priv,
+			    struct intel_shared_dpll *pll)
+{
+	const enum intel_dpll_id id = pll->info->id;
+	i915_reg_t enable_reg = icl_pll_id_to_enable_reg(id);
+	uint32_t val;
+
+	/* The first steps are done by intel_ddi_post_disable(). */
+
+	/*
+	 * DVFS pre sequence would be here, but in our driver the cdclk code
+	 * paths should already be setting the appropriate voltage, hence we do
+	 * nothign here.
+	 */
+
+	val = I915_READ(enable_reg);
+	val &= ~PLL_ENABLE;
+	I915_WRITE(enable_reg, val);
+
+	/* Timeout is actually 1us. */
+	if (intel_wait_for_register(dev_priv, enable_reg, PLL_LOCK, 0, 1))
+		DRM_ERROR("PLL %d locked\n", id);
+
+	/* DVFS post sequence would be here. See the comment above. */
+
+	val = I915_READ(enable_reg);
+	val &= ~PLL_POWER_ENABLE;
+	I915_WRITE(enable_reg, val);
+
+	/*
+	 * The spec says we need to "wait" but it also says it should be
+	 * immediate.
+	 */
+	if (intel_wait_for_register(dev_priv, enable_reg, PLL_POWER_STATE, 0,
+				    1))
+		DRM_ERROR("PLL %d Power not disabled\n", id);
+}
+
+static void icl_dump_hw_state(struct drm_i915_private *dev_priv,
+			      struct intel_dpll_hw_state *hw_state)
+{
+	DRM_DEBUG_KMS("dpll_hw_state: cfgcr0: 0x%x, cfgcr1: 0x%x, "
+		      "mg_refclkin_ctl: 0x%x, hg_clktop2_coreclkctl1: 0x%x, "
+		      "mg_clktop2_hsclkctl: 0x%x, mg_pll_div0: 0x%x, "
+		      "mg_pll_div2: 0x%x, mg_pll_lf: 0x%x, "
+		      "mg_pll_frac_lock: 0x%x, mg_pll_ssc: 0x%x, "
+		      "mg_pll_bias: 0x%x, mg_pll_tdc_coldst_bias: 0x%x\n",
+		      hw_state->cfgcr0, hw_state->cfgcr1,
+		      hw_state->mg_refclkin_ctl,
+		      hw_state->mg_clktop2_coreclkctl1,
+		      hw_state->mg_clktop2_hsclkctl,
+		      hw_state->mg_pll_div0,
+		      hw_state->mg_pll_div1,
+		      hw_state->mg_pll_lf,
+		      hw_state->mg_pll_frac_lock,
+		      hw_state->mg_pll_ssc,
+		      hw_state->mg_pll_bias,
+		      hw_state->mg_pll_tdc_coldst_bias);
+}
+
+static const struct intel_shared_dpll_funcs icl_pll_funcs = {
+	.enable = icl_pll_enable,
+	.disable = icl_pll_disable,
+	.get_hw_state = icl_pll_get_hw_state,
+};
+
+static const struct dpll_info icl_plls[] = {
+	{ "DPLL 0",   &icl_pll_funcs, DPLL_ID_ICL_DPLL0,  0 },
+	{ "DPLL 1",   &icl_pll_funcs, DPLL_ID_ICL_DPLL1,  0 },
+	{ "MG PLL 1", &icl_pll_funcs, DPLL_ID_ICL_MGPLL1, 0 },
+	{ "MG PLL 2", &icl_pll_funcs, DPLL_ID_ICL_MGPLL2, 0 },
+	{ "MG PLL 3", &icl_pll_funcs, DPLL_ID_ICL_MGPLL3, 0 },
+	{ "MG PLL 4", &icl_pll_funcs, DPLL_ID_ICL_MGPLL4, 0 },
+	{ },
+};
+
+static const struct intel_dpll_mgr icl_pll_mgr = {
+	.dpll_info = icl_plls,
+	.get_dpll = icl_get_dpll,
+	.dump_hw_state = icl_dump_hw_state,
+};
+
 /**
  * intel_shared_dpll_init - Initialize shared DPLLs
  * @dev: drm device
@@ -2397,7 +3060,9 @@ void intel_shared_dpll_init(struct drm_device *dev)
 	const struct dpll_info *dpll_info;
 	int i;
 
-	if (IS_CANNONLAKE(dev_priv))
+	if (IS_ICELAKE(dev_priv))
+		dpll_mgr = &icl_pll_mgr;
+	else if (IS_CANNONLAKE(dev_priv))
 		dpll_mgr = &cnl_pll_mgr;
 	else if (IS_GEN9_BC(dev_priv))
 		dpll_mgr = &skl_pll_mgr;
@@ -2415,13 +3080,9 @@ void intel_shared_dpll_init(struct drm_device *dev)
 
 	dpll_info = dpll_mgr->dpll_info;
 
-	for (i = 0; dpll_info[i].id >= 0; i++) {
+	for (i = 0; dpll_info[i].name; i++) {
 		WARN_ON(i != dpll_info[i].id);
-
-		dev_priv->shared_dplls[i].id = dpll_info[i].id;
-		dev_priv->shared_dplls[i].name = dpll_info[i].name;
-		dev_priv->shared_dplls[i].funcs = *dpll_info[i].funcs;
-		dev_priv->shared_dplls[i].flags = dpll_info[i].flags;
+		dev_priv->shared_dplls[i].info = &dpll_info[i];
 	}
 
 	dev_priv->dpll_mgr = dpll_mgr;
@@ -2481,7 +3142,7 @@ void intel_release_shared_dpll(struct intel_shared_dpll *dpll,
 	struct intel_shared_dpll_state *shared_dpll_state;
 
 	shared_dpll_state = intel_atomic_get_shared_dpll_state(state);
-	shared_dpll_state[dpll->id].crtc_mask &= ~(1 << crtc->pipe);
+	shared_dpll_state[dpll->info->id].crtc_mask &= ~(1 << crtc->pipe);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.h b/drivers/gpu/drm/i915/intel_dpll_mgr.h
index f24ccf443d25..7a0cd564a9ee 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.h
@@ -103,6 +103,32 @@ enum intel_dpll_id {
 	 * @DPLL_ID_SKL_DPLL3: SKL and later DPLL3
 	 */
 	DPLL_ID_SKL_DPLL3 = 3,
+
+
+	/**
+	 * @DPLL_ID_ICL_DPLL0: ICL combo PHY DPLL0
+	 */
+	DPLL_ID_ICL_DPLL0 = 0,
+	/**
+	 * @DPLL_ID_ICL_DPLL1: ICL combo PHY DPLL1
+	 */
+	DPLL_ID_ICL_DPLL1 = 1,
+	/**
+	 * @DPLL_ID_ICL_MGPLL1: ICL MG PLL 1 port 1 (C)
+	 */
+	DPLL_ID_ICL_MGPLL1 = 2,
+	/**
+	 * @DPLL_ID_ICL_MGPLL2: ICL MG PLL 1 port 2 (D)
+	 */
+	DPLL_ID_ICL_MGPLL2 = 3,
+	/**
+	 * @DPLL_ID_ICL_MGPLL3: ICL MG PLL 1 port 3 (E)
+	 */
+	DPLL_ID_ICL_MGPLL3 = 4,
+	/**
+	 * @DPLL_ID_ICL_MGPLL4: ICL MG PLL 1 port 4 (F)
+	 */
+	DPLL_ID_ICL_MGPLL4 = 5,
 };
 #define I915_NUM_PLLS 6
 
@@ -135,6 +161,21 @@ struct intel_dpll_hw_state {
 	/* bxt */
 	uint32_t ebb0, ebb4, pll0, pll1, pll2, pll3, pll6, pll8, pll9, pll10,
 		 pcsdw12;
+
+	/*
+	 * ICL uses the following, already defined:
+	 * uint32_t cfgcr0, cfgcr1;
+	 */
+	uint32_t mg_refclkin_ctl;
+	uint32_t mg_clktop2_coreclkctl1;
+	uint32_t mg_clktop2_hsclkctl;
+	uint32_t mg_pll_div0;
+	uint32_t mg_pll_div1;
+	uint32_t mg_pll_lf;
+	uint32_t mg_pll_frac_lock;
+	uint32_t mg_pll_ssc;
+	uint32_t mg_pll_bias;
+	uint32_t mg_pll_tdc_coldst_bias;
 };
 
 /**
@@ -206,6 +247,37 @@ struct intel_shared_dpll_funcs {
 };
 
 /**
+ * struct dpll_info - display PLL platform specific info
+ */
+struct dpll_info {
+	/**
+	 * @name: DPLL name; used for logging
+	 */
+	const char *name;
+
+	/**
+	 * @funcs: platform specific hooks
+	 */
+	const struct intel_shared_dpll_funcs *funcs;
+
+	/**
+	 * @id: unique indentifier for this DPLL; should match the index in the
+	 * dev_priv->shared_dplls array
+	 */
+	enum intel_dpll_id id;
+
+#define INTEL_DPLL_ALWAYS_ON	(1 << 0)
+	/**
+	 * @flags:
+	 *
+	 * INTEL_DPLL_ALWAYS_ON
+	 *     Inform the state checker that the DPLL is kept enabled even if
+	 *     not in use by any CRTC.
+	 */
+	uint32_t flags;
+};
+
+/**
  * struct intel_shared_dpll - display PLL with tracked state and users
  */
 struct intel_shared_dpll {
@@ -228,30 +300,9 @@ struct intel_shared_dpll {
 	bool on;
 
 	/**
-	 * @name: DPLL name; used for logging
+	 * @info: platform specific info
 	 */
-	const char *name;
-
-	/**
-	 * @id: unique indentifier for this DPLL; should match the index in the
-	 * dev_priv->shared_dplls array
-	 */
-	enum intel_dpll_id id;
-
-	/**
-	 * @funcs: platform specific hooks
-	 */
-	struct intel_shared_dpll_funcs funcs;
-
-#define INTEL_DPLL_ALWAYS_ON	(1 << 0)
-	/**
-	 * @flags:
-	 *
-	 * INTEL_DPLL_ALWAYS_ON
-	 *     Inform the state checker that the DPLL is kept enabled even if
-	 *     not in use by any CRTC.
-	 */
-	uint32_t flags;
+	const struct dpll_info *info;
 };
 
 #define SKL_DPLL0 0
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index d4368589b355..d7dbca1aabff 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -49,13 +49,15 @@
  * check the condition before the timeout.
  */
 #define __wait_for(OP, COND, US, Wmin, Wmax) ({ \
-	unsigned long timeout__ = jiffies + usecs_to_jiffies(US) + 1;	\
+	const ktime_t end__ = ktime_add_ns(ktime_get_raw(), 1000ll * (US)); \
 	long wait__ = (Wmin); /* recommended min for usleep is 10 us */	\
 	int ret__;							\
 	might_sleep();							\
 	for (;;) {							\
-		bool expired__ = time_after(jiffies, timeout__);	\
+		const bool expired__ = ktime_after(ktime_get_raw(), end__); \
 		OP;							\
+		/* Guarantee COND check prior to timeout */		\
+		barrier();						\
 		if (COND) {						\
 			ret__ = 0;					\
 			break;						\
@@ -96,6 +98,8 @@
 		u64 now = local_clock(); \
 		if (!(ATOMIC)) \
 			preempt_enable(); \
+		/* Guarantee COND check prior to timeout */ \
+		barrier(); \
 		if (COND) { \
 			ret = 0; \
 			break; \
@@ -140,6 +144,10 @@
 #define KHz(x) (1000 * (x))
 #define MHz(x) KHz(1000 * (x))
 
+#define KBps(x) (1000 * (x))
+#define MBps(x) KBps(1000 * (x))
+#define GBps(x) ((u64)1000 * MBps((x)))
+
 /*
  * Display related stuff
  */
@@ -482,7 +490,7 @@ struct intel_atomic_state {
 	bool skip_intermediate_wm;
 
 	/* Gen9+ only */
-	struct skl_wm_values wm_results;
+	struct skl_ddb_values wm_results;
 
 	struct i915_sw_fence commit_ready;
 
@@ -548,6 +556,12 @@ struct intel_initial_plane_config {
 #define SKL_MAX_DST_W 4096
 #define SKL_MIN_DST_H 8
 #define SKL_MAX_DST_H 4096
+#define ICL_MAX_SRC_W 5120
+#define ICL_MAX_SRC_H 4096
+#define ICL_MAX_DST_W 5120
+#define ICL_MAX_DST_H 4096
+#define SKL_MIN_YUV_420_SRC_W 16
+#define SKL_MIN_YUV_420_SRC_H 16
 
 struct intel_scaler {
 	int in_use;
@@ -598,7 +612,9 @@ struct intel_pipe_wm {
 
 struct skl_plane_wm {
 	struct skl_wm_level wm[8];
+	struct skl_wm_level uv_wm[8];
 	struct skl_wm_level trans_wm;
+	bool is_planar;
 };
 
 struct skl_pipe_wm {
@@ -874,6 +890,7 @@ struct intel_crtc_state {
 
 	/* bitmask of visible planes (enum plane_id) */
 	u8 active_planes;
+	u8 nv12_planes;
 
 	/* HDMI scrambling status */
 	bool hdmi_scrambling;
@@ -1321,10 +1338,14 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv);
 void intel_check_pch_fifo_underruns(struct drm_i915_private *dev_priv);
 
 /* i915_irq.c */
+bool gen11_reset_one_iir(struct drm_i915_private * const i915,
+			 const unsigned int bank,
+			 const unsigned int bit);
 void gen5_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen6_mask_pm_irq(struct drm_i915_private *dev_priv, u32 mask);
 void gen6_unmask_pm_irq(struct drm_i915_private *dev_priv, u32 mask);
+void gen11_reset_rps_interrupts(struct drm_i915_private *dev_priv);
 void gen6_reset_rps_interrupts(struct drm_i915_private *dev_priv);
 void gen6_enable_rps_interrupts(struct drm_i915_private *dev_priv);
 void gen6_disable_rps_interrupts(struct drm_i915_private *dev_priv);
@@ -1389,6 +1410,12 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp);
 u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder);
 int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
 				     bool enable);
+void icl_map_plls_to_ports(struct drm_crtc *crtc,
+			   struct intel_crtc_state *crtc_state,
+			   struct drm_atomic_state *old_state);
+void icl_unmap_plls_to_ports(struct drm_crtc *crtc,
+			     struct intel_crtc_state *crtc_state,
+			     struct drm_atomic_state *old_state);
 
 unsigned int intel_fb_align_height(const struct drm_framebuffer *fb,
 				   int plane, unsigned int height);
@@ -1571,8 +1598,6 @@ void bxt_enable_dc9(struct drm_i915_private *dev_priv);
 void bxt_disable_dc9(struct drm_i915_private *dev_priv);
 void gen9_enable_dc5(struct drm_i915_private *dev_priv);
 unsigned int skl_cdclk_get_vco(unsigned int freq);
-void skl_enable_dc6(struct drm_i915_private *dev_priv);
-void skl_disable_dc6(struct drm_i915_private *dev_priv);
 void intel_dp_get_m_n(struct intel_crtc *crtc,
 		      struct intel_crtc_state *pipe_config);
 void intel_dp_set_m_n(struct intel_crtc *crtc, enum link_m_n_set m_n);
@@ -1588,9 +1613,12 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state);
 enum intel_display_power_domain intel_port_to_power_domain(enum port port);
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_state *pipe_config);
+void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
+				  struct intel_crtc_state *crtc_state);
 
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
-int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state);
+int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
+		  uint32_t pixel_format);
 
 static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *state)
 {
@@ -1607,6 +1635,7 @@ u32 skl_plane_stride(const struct drm_framebuffer *fb, int plane,
 int skl_check_plane_surface(const struct intel_crtc_state *crtc_state,
 			    struct intel_plane_state *plane_state);
 int i9xx_check_plane_surface(struct intel_plane_state *plane_state);
+int skl_format_to_fourcc(int format, bool rgb_order, bool alpha);
 
 /* intel_csr.c */
 void intel_csr_ucode_init(struct drm_i915_private *);
@@ -1773,6 +1802,7 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv,
 		     unsigned int frontbuffer_bits, enum fb_op_origin origin);
 void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv);
 void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *dev_priv);
+int intel_fbc_reset_underrun(struct drm_i915_private *dev_priv);
 
 /* intel_hdmi.c */
 void intel_hdmi_init(struct drm_i915_private *dev_priv, i915_reg_t hdmi_reg,
@@ -1783,7 +1813,7 @@ struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder);
 bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 			       struct intel_crtc_state *pipe_config,
 			       struct drm_connector_state *conn_state);
-void intel_hdmi_handle_sink_scrambling(struct intel_encoder *intel_encoder,
+bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder,
 				       struct drm_connector *connector,
 				       bool high_tmds_clock_ratio,
 				       bool scrambling);
@@ -1877,7 +1907,8 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 void intel_psr_disable(struct intel_dp *intel_dp,
 		      const struct intel_crtc_state *old_crtc_state);
 void intel_psr_invalidate(struct drm_i915_private *dev_priv,
-			  unsigned frontbuffer_bits);
+			  unsigned frontbuffer_bits,
+			  enum fb_op_origin origin);
 void intel_psr_flush(struct drm_i915_private *dev_priv,
 		     unsigned frontbuffer_bits,
 		     enum fb_op_origin origin);
@@ -1886,6 +1917,8 @@ void intel_psr_single_frame_update(struct drm_i915_private *dev_priv,
 				   unsigned frontbuffer_bits);
 void intel_psr_compute_config(struct intel_dp *intel_dp,
 			      struct intel_crtc_state *crtc_state);
+void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug);
+void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir);
 
 /* intel_runtime_pm.c */
 int intel_power_domains_init(struct drm_i915_private *);
@@ -1909,6 +1942,8 @@ bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
 					enum intel_display_power_domain domain);
 void intel_display_power_put(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
+void icl_dbuf_slices_update(struct drm_i915_private *dev_priv,
+			    u8 req_slices);
 
 static inline void
 assert_rpm_device_not_suspended(struct drm_i915_private *dev_priv)
@@ -2046,6 +2081,9 @@ void skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc);
 bool skl_plane_get_hw_state(struct intel_plane *plane);
 bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
 		       enum pipe pipe, enum plane_id plane_id);
+bool intel_format_is_yuv(uint32_t format);
+bool skl_plane_has_planar(struct drm_i915_private *dev_priv,
+			  enum pipe pipe, enum plane_id plane_id);
 
 /* intel_tv.c */
 void intel_tv_init(struct drm_i915_private *dev_priv);
@@ -2082,31 +2120,6 @@ intel_atomic_get_crtc_state(struct drm_atomic_state *state,
 	return to_intel_crtc_state(crtc_state);
 }
 
-static inline struct intel_crtc_state *
-intel_atomic_get_existing_crtc_state(struct drm_atomic_state *state,
-				     struct intel_crtc *crtc)
-{
-	struct drm_crtc_state *crtc_state;
-
-	crtc_state = drm_atomic_get_existing_crtc_state(state, &crtc->base);
-
-	if (crtc_state)
-		return to_intel_crtc_state(crtc_state);
-	else
-		return NULL;
-}
-
-static inline struct intel_plane_state *
-intel_atomic_get_existing_plane_state(struct drm_atomic_state *state,
-				      struct intel_plane *plane)
-{
-	struct drm_plane_state *plane_state;
-
-	plane_state = drm_atomic_get_existing_plane_state(state, &plane->base);
-
-	return to_intel_plane_state(plane_state);
-}
-
 int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 			       struct intel_crtc *intel_crtc,
 			       struct intel_crtc_state *crtc_state);
@@ -2138,8 +2151,17 @@ int intel_pipe_crc_create(struct drm_minor *minor);
 #ifdef CONFIG_DEBUG_FS
 int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
 			      size_t *values_cnt);
+void intel_crtc_disable_pipe_crc(struct intel_crtc *crtc);
+void intel_crtc_enable_pipe_crc(struct intel_crtc *crtc);
 #else
 #define intel_crtc_set_crc_source NULL
+static inline void intel_crtc_disable_pipe_crc(struct intel_crtc *crtc)
+{
+}
+
+static inline void intel_crtc_enable_pipe_crc(struct intel_crtc *crtc)
+{
+}
 #endif
 extern const struct file_operations i915_display_crc_ctl_fops;
 #endif /* __INTEL_DRV_H__ */
diff --git a/drivers/gpu/drm/i915/intel_dsi_vbt.c b/drivers/gpu/drm/i915/intel_dsi_vbt.c
index 91c07b0c8db9..4d6ffa7b3e7b 100644
--- a/drivers/gpu/drm/i915/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_vbt.c
@@ -647,6 +647,11 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id)
 	/* prepare count */
 	prepare_cnt = DIV_ROUND_UP(ths_prepare_ns * ui_den, ui_num * mul);
 
+	if (prepare_cnt > PREPARE_CNT_MAX) {
+		DRM_DEBUG_KMS("prepare count too high %u\n", prepare_cnt);
+		prepare_cnt = PREPARE_CNT_MAX;
+	}
+
 	/* exit zero count */
 	exit_zero_cnt = DIV_ROUND_UP(
 				(ths_prepare_hszero - ths_prepare_ns) * ui_den,
@@ -662,32 +667,29 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id)
 	if (exit_zero_cnt < (55 * ui_den / ui_num) && (55 * ui_den) % ui_num)
 		exit_zero_cnt += 1;
 
+	if (exit_zero_cnt > EXIT_ZERO_CNT_MAX) {
+		DRM_DEBUG_KMS("exit zero count too high %u\n", exit_zero_cnt);
+		exit_zero_cnt = EXIT_ZERO_CNT_MAX;
+	}
+
 	/* clk zero count */
 	clk_zero_cnt = DIV_ROUND_UP(
 				(tclk_prepare_clkzero -	ths_prepare_ns)
 				* ui_den, ui_num * mul);
 
+	if (clk_zero_cnt > CLK_ZERO_CNT_MAX) {
+		DRM_DEBUG_KMS("clock zero count too high %u\n", clk_zero_cnt);
+		clk_zero_cnt = CLK_ZERO_CNT_MAX;
+	}
+
 	/* trail count */
 	tclk_trail_ns = max(mipi_config->tclk_trail, mipi_config->ths_trail);
 	trail_cnt = DIV_ROUND_UP(tclk_trail_ns * ui_den, ui_num * mul);
 
-	if (prepare_cnt > PREPARE_CNT_MAX ||
-		exit_zero_cnt > EXIT_ZERO_CNT_MAX ||
-		clk_zero_cnt > CLK_ZERO_CNT_MAX ||
-		trail_cnt > TRAIL_CNT_MAX)
-		DRM_DEBUG_DRIVER("Values crossing maximum limits, restricting to max values\n");
-
-	if (prepare_cnt > PREPARE_CNT_MAX)
-		prepare_cnt = PREPARE_CNT_MAX;
-
-	if (exit_zero_cnt > EXIT_ZERO_CNT_MAX)
-		exit_zero_cnt = EXIT_ZERO_CNT_MAX;
-
-	if (clk_zero_cnt > CLK_ZERO_CNT_MAX)
-		clk_zero_cnt = CLK_ZERO_CNT_MAX;
-
-	if (trail_cnt > TRAIL_CNT_MAX)
+	if (trail_cnt > TRAIL_CNT_MAX) {
+		DRM_DEBUG_KMS("trail count too high %u\n", trail_cnt);
 		trail_cnt = TRAIL_CNT_MAX;
+	}
 
 	/* B080 */
 	intel_dsi->dphy_reg = exit_zero_cnt << 24 | trail_cnt << 16 |
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 4ba139c27fba..6bfd7e3ed152 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -81,13 +81,17 @@ static const struct engine_class_info intel_engine_classes[] = {
 	},
 };
 
+#define MAX_MMIO_BASES 3
 struct engine_info {
 	unsigned int hw_id;
 	unsigned int uabi_id;
 	u8 class;
 	u8 instance;
-	u32 mmio_base;
-	unsigned irq_shift;
+	/* mmio bases table *must* be sorted in reverse gen order */
+	struct engine_mmio_base {
+		u32 gen : 8;
+		u32 base : 24;
+	} mmio_bases[MAX_MMIO_BASES];
 };
 
 static const struct engine_info intel_engines[] = {
@@ -96,64 +100,76 @@ static const struct engine_info intel_engines[] = {
 		.uabi_id = I915_EXEC_RENDER,
 		.class = RENDER_CLASS,
 		.instance = 0,
-		.mmio_base = RENDER_RING_BASE,
-		.irq_shift = GEN8_RCS_IRQ_SHIFT,
+		.mmio_bases = {
+			{ .gen = 1, .base = RENDER_RING_BASE }
+		},
 	},
 	[BCS] = {
 		.hw_id = BCS_HW,
 		.uabi_id = I915_EXEC_BLT,
 		.class = COPY_ENGINE_CLASS,
 		.instance = 0,
-		.mmio_base = BLT_RING_BASE,
-		.irq_shift = GEN8_BCS_IRQ_SHIFT,
+		.mmio_bases = {
+			{ .gen = 6, .base = BLT_RING_BASE }
+		},
 	},
 	[VCS] = {
 		.hw_id = VCS_HW,
 		.uabi_id = I915_EXEC_BSD,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 0,
-		.mmio_base = GEN6_BSD_RING_BASE,
-		.irq_shift = GEN8_VCS1_IRQ_SHIFT,
+		.mmio_bases = {
+			{ .gen = 11, .base = GEN11_BSD_RING_BASE },
+			{ .gen = 6, .base = GEN6_BSD_RING_BASE },
+			{ .gen = 4, .base = BSD_RING_BASE }
+		},
 	},
 	[VCS2] = {
 		.hw_id = VCS2_HW,
 		.uabi_id = I915_EXEC_BSD,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 1,
-		.mmio_base = GEN8_BSD2_RING_BASE,
-		.irq_shift = GEN8_VCS2_IRQ_SHIFT,
+		.mmio_bases = {
+			{ .gen = 11, .base = GEN11_BSD2_RING_BASE },
+			{ .gen = 8, .base = GEN8_BSD2_RING_BASE }
+		},
 	},
 	[VCS3] = {
 		.hw_id = VCS3_HW,
 		.uabi_id = I915_EXEC_BSD,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 2,
-		.mmio_base = GEN11_BSD3_RING_BASE,
-		.irq_shift = 0, /* not used */
+		.mmio_bases = {
+			{ .gen = 11, .base = GEN11_BSD3_RING_BASE }
+		},
 	},
 	[VCS4] = {
 		.hw_id = VCS4_HW,
 		.uabi_id = I915_EXEC_BSD,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 3,
-		.mmio_base = GEN11_BSD4_RING_BASE,
-		.irq_shift = 0, /* not used */
+		.mmio_bases = {
+			{ .gen = 11, .base = GEN11_BSD4_RING_BASE }
+		},
 	},
 	[VECS] = {
 		.hw_id = VECS_HW,
 		.uabi_id = I915_EXEC_VEBOX,
 		.class = VIDEO_ENHANCEMENT_CLASS,
 		.instance = 0,
-		.mmio_base = VEBOX_RING_BASE,
-		.irq_shift = GEN8_VECS_IRQ_SHIFT,
+		.mmio_bases = {
+			{ .gen = 11, .base = GEN11_VEBOX_RING_BASE },
+			{ .gen = 7, .base = VEBOX_RING_BASE }
+		},
 	},
 	[VECS2] = {
 		.hw_id = VECS2_HW,
 		.uabi_id = I915_EXEC_VEBOX,
 		.class = VIDEO_ENHANCEMENT_CLASS,
 		.instance = 1,
-		.mmio_base = GEN11_VEBOX2_RING_BASE,
-		.irq_shift = 0, /* not used */
+		.mmio_bases = {
+			{ .gen = 11, .base = GEN11_VEBOX2_RING_BASE }
+		},
 	},
 };
 
@@ -223,16 +239,36 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 	}
 }
 
+static u32 __engine_mmio_base(struct drm_i915_private *i915,
+			      const struct engine_mmio_base *bases)
+{
+	int i;
+
+	for (i = 0; i < MAX_MMIO_BASES; i++)
+		if (INTEL_GEN(i915) >= bases[i].gen)
+			break;
+
+	GEM_BUG_ON(i == MAX_MMIO_BASES);
+	GEM_BUG_ON(!bases[i].base);
+
+	return bases[i].base;
+}
+
+static void __sprint_engine_name(char *name, const struct engine_info *info)
+{
+	WARN_ON(snprintf(name, INTEL_ENGINE_CS_MAX_NAME, "%s%u",
+			 intel_engine_classes[info->class].name,
+			 info->instance) >= INTEL_ENGINE_CS_MAX_NAME);
+}
+
 static int
 intel_engine_setup(struct drm_i915_private *dev_priv,
 		   enum intel_engine_id id)
 {
 	const struct engine_info *info = &intel_engines[id];
-	const struct engine_class_info *class_info;
 	struct intel_engine_cs *engine;
 
 	GEM_BUG_ON(info->class >= ARRAY_SIZE(intel_engine_classes));
-	class_info = &intel_engine_classes[info->class];
 
 	BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH));
 	BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH));
@@ -253,35 +289,14 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 
 	engine->id = id;
 	engine->i915 = dev_priv;
-	WARN_ON(snprintf(engine->name, sizeof(engine->name), "%s%u",
-			 class_info->name, info->instance) >=
-		sizeof(engine->name));
+	__sprint_engine_name(engine->name, info);
 	engine->hw_id = engine->guc_id = info->hw_id;
-	if (INTEL_GEN(dev_priv) >= 11) {
-		switch (engine->id) {
-		case VCS:
-			engine->mmio_base = GEN11_BSD_RING_BASE;
-			break;
-		case VCS2:
-			engine->mmio_base = GEN11_BSD2_RING_BASE;
-			break;
-		case VECS:
-			engine->mmio_base = GEN11_VEBOX_RING_BASE;
-			break;
-		default:
-			/* take the original value for all other engines  */
-			engine->mmio_base = info->mmio_base;
-			break;
-		}
-	} else {
-		engine->mmio_base = info->mmio_base;
-	}
-	engine->irq_shift = info->irq_shift;
+	engine->mmio_base = __engine_mmio_base(dev_priv, info->mmio_bases);
 	engine->class = info->class;
 	engine->instance = info->instance;
 
 	engine->uabi_id = info->uabi_id;
-	engine->uabi_class = class_info->uabi_class;
+	engine->uabi_class = intel_engine_classes[info->class].uabi_class;
 
 	engine->context_size = __intel_engine_context_size(dev_priv,
 							   engine->class);
@@ -291,7 +306,7 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
-	spin_lock_init(&engine->stats.lock);
+	seqlock_init(&engine->stats.lock);
 
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
@@ -436,21 +451,13 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno)
 	GEM_BUG_ON(intel_engine_get_seqno(engine) != seqno);
 }
 
-static void intel_engine_init_timeline(struct intel_engine_cs *engine)
+static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
 {
-	engine->timeline = &engine->i915->gt.global_timeline.engine[engine->id];
+	i915_gem_batch_pool_init(&engine->batch_pool, engine);
 }
 
 static bool csb_force_mmio(struct drm_i915_private *i915)
 {
-	/*
-	 * IOMMU adds unpredictable latency causing the CSB write (from the
-	 * GPU into the HWSP) to only be visible some time after the interrupt
-	 * (missed breadcrumb syndrome).
-	 */
-	if (intel_vtd_active())
-		return true;
-
 	/* Older GVT emulation depends upon intercepting CSB mmio */
 	if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915))
 		return true;
@@ -484,12 +491,11 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
  */
 void intel_engine_setup_common(struct intel_engine_cs *engine)
 {
-	intel_engine_init_execlist(engine);
+	i915_timeline_init(engine->i915, &engine->timeline, engine->name);
 
-	intel_engine_init_timeline(engine);
+	intel_engine_init_execlist(engine);
 	intel_engine_init_hangcheck(engine);
-	i915_gem_batch_pool_init(engine, &engine->batch_pool);
-
+	intel_engine_init_batch_pool(engine);
 	intel_engine_init_cmd_parser(engine);
 }
 
@@ -520,8 +526,6 @@ int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
 		goto err_unref;
 
 	engine->scratch = vma;
-	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
-			 engine->name, i915_ggtt_offset(vma));
 	return 0;
 
 err_unref:
@@ -615,9 +619,6 @@ static int init_status_page(struct intel_engine_cs *engine)
 	engine->status_page.vma = vma;
 	engine->status_page.ggtt_offset = i915_ggtt_offset(vma);
 	engine->status_page.page_addr = memset(vaddr, 0, PAGE_SIZE);
-
-	DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
-			 engine->name, i915_ggtt_offset(vma));
 	return 0;
 
 err_unpin:
@@ -669,7 +670,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	 * be available. To avoid this we always pin the default
 	 * context.
 	 */
-	ring = engine->context_pin(engine, engine->i915->kernel_context);
+	ring = intel_context_pin(engine->i915->kernel_context, engine);
 	if (IS_ERR(ring))
 		return PTR_ERR(ring);
 
@@ -678,8 +679,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	 * we can interrupt the engine at any time.
 	 */
 	if (engine->i915->preempt_context) {
-		ring = engine->context_pin(engine,
-					   engine->i915->preempt_context);
+		ring = intel_context_pin(engine->i915->preempt_context, engine);
 		if (IS_ERR(ring)) {
 			ret = PTR_ERR(ring);
 			goto err_unpin_kernel;
@@ -703,9 +703,9 @@ err_breadcrumbs:
 	intel_engine_fini_breadcrumbs(engine);
 err_unpin_preempt:
 	if (engine->i915->preempt_context)
-		engine->context_unpin(engine, engine->i915->preempt_context);
+		intel_context_unpin(engine->i915->preempt_context, engine);
 err_unpin_kernel:
-	engine->context_unpin(engine, engine->i915->kernel_context);
+	intel_context_unpin(engine->i915->kernel_context, engine);
 	return ret;
 }
 
@@ -733,8 +733,10 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 		i915_gem_object_put(engine->default_state);
 
 	if (engine->i915->preempt_context)
-		engine->context_unpin(engine, engine->i915->preempt_context);
-	engine->context_unpin(engine, engine->i915->kernel_context);
+		intel_context_unpin(engine->i915->preempt_context, engine);
+	intel_context_unpin(engine->i915->kernel_context, engine);
+
+	i915_timeline_fini(&engine->timeline);
 }
 
 u64 intel_engine_get_active_head(const struct intel_engine_cs *engine)
@@ -782,10 +784,24 @@ static inline uint32_t
 read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 		  int subslice, i915_reg_t reg)
 {
+	uint32_t mcr_slice_subslice_mask;
+	uint32_t mcr_slice_subslice_select;
 	uint32_t mcr;
 	uint32_t ret;
 	enum forcewake_domains fw_domains;
 
+	if (INTEL_GEN(dev_priv) >= 11) {
+		mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK |
+					  GEN11_MCR_SUBSLICE_MASK;
+		mcr_slice_subslice_select = GEN11_MCR_SLICE(slice) |
+					    GEN11_MCR_SUBSLICE(subslice);
+	} else {
+		mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK |
+					  GEN8_MCR_SUBSLICE_MASK;
+		mcr_slice_subslice_select = GEN8_MCR_SLICE(slice) |
+					    GEN8_MCR_SUBSLICE(subslice);
+	}
+
 	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg,
 						    FW_REG_READ);
 	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
@@ -800,14 +816,14 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 	 * The HW expects the slice and sublice selectors to be reset to 0
 	 * after reading out the registers.
 	 */
-	WARN_ON_ONCE(mcr & (GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK));
-	mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK);
-	mcr |= GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
+	WARN_ON_ONCE(mcr & mcr_slice_subslice_mask);
+	mcr &= ~mcr_slice_subslice_mask;
+	mcr |= mcr_slice_subslice_select;
 	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
 
 	ret = I915_READ_FW(reg);
 
-	mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK);
+	mcr &= ~mcr_slice_subslice_mask;
 	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
 
 	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
@@ -871,640 +887,6 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 	}
 }
 
-static int wa_add(struct drm_i915_private *dev_priv,
-		  i915_reg_t addr,
-		  const u32 mask, const u32 val)
-{
-	const u32 idx = dev_priv->workarounds.count;
-
-	if (WARN_ON(idx >= I915_MAX_WA_REGS))
-		return -ENOSPC;
-
-	dev_priv->workarounds.reg[idx].addr = addr;
-	dev_priv->workarounds.reg[idx].value = val;
-	dev_priv->workarounds.reg[idx].mask = mask;
-
-	dev_priv->workarounds.count++;
-
-	return 0;
-}
-
-#define WA_REG(addr, mask, val) do { \
-		const int r = wa_add(dev_priv, (addr), (mask), (val)); \
-		if (r) \
-			return r; \
-	} while (0)
-
-#define WA_SET_BIT_MASKED(addr, mask) \
-	WA_REG(addr, (mask), _MASKED_BIT_ENABLE(mask))
-
-#define WA_CLR_BIT_MASKED(addr, mask) \
-	WA_REG(addr, (mask), _MASKED_BIT_DISABLE(mask))
-
-#define WA_SET_FIELD_MASKED(addr, mask, value) \
-	WA_REG(addr, mask, _MASKED_FIELD(mask, value))
-
-static int wa_ring_whitelist_reg(struct intel_engine_cs *engine,
-				 i915_reg_t reg)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	struct i915_workarounds *wa = &dev_priv->workarounds;
-	const uint32_t index = wa->hw_whitelist_count[engine->id];
-
-	if (WARN_ON(index >= RING_MAX_NONPRIV_SLOTS))
-		return -EINVAL;
-
-	I915_WRITE(RING_FORCE_TO_NONPRIV(engine->mmio_base, index),
-		   i915_mmio_reg_offset(reg));
-	wa->hw_whitelist_count[engine->id]++;
-
-	return 0;
-}
-
-static int gen8_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-
-	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
-
-	/* WaDisableAsyncFlipPerfMode:bdw,chv */
-	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
-
-	/* WaDisablePartialInstShootdown:bdw,chv */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
-			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
-
-	/* Use Force Non-Coherent whenever executing a 3D context. This is a
-	 * workaround for for a possible hang in the unlikely event a TLB
-	 * invalidation occurs during a PSD flush.
-	 */
-	/* WaForceEnableNonCoherent:bdw,chv */
-	/* WaHdcDisableFetchWhenMasked:bdw,chv */
-	WA_SET_BIT_MASKED(HDC_CHICKEN0,
-			  HDC_DONOT_FETCH_MEM_WHEN_MASKED |
-			  HDC_FORCE_NON_COHERENT);
-
-	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
-	 * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
-	 *  polygons in the same 8x4 pixel/sample area to be processed without
-	 *  stalling waiting for the earlier ones to write to Hierarchical Z
-	 *  buffer."
-	 *
-	 * This optimization is off by default for BDW and CHV; turn it on.
-	 */
-	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
-
-	/* Wa4x4STCOptimizationDisable:bdw,chv */
-	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
-
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	WA_SET_FIELD_MASKED(GEN7_GT_MODE,
-			    GEN6_WIZ_HASHING_MASK,
-			    GEN6_WIZ_HASHING_16x4);
-
-	return 0;
-}
-
-static int bdw_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	ret = gen8_init_workarounds(engine);
-	if (ret)
-		return ret;
-
-	/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
-
-	/* WaDisableDopClockGating:bdw
-	 *
-	 * Also see the related UCGTCL1 write in broadwell_init_clock_gating()
-	 * to disable EUTC clock gating.
-	 */
-	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
-			  DOP_CLOCK_GATING_DISABLE);
-
-	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
-			  GEN8_SAMPLER_POWER_BYPASS_DIS);
-
-	WA_SET_BIT_MASKED(HDC_CHICKEN0,
-			  /* WaForceContextSaveRestoreNonCoherent:bdw */
-			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
-			  /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
-			  (IS_BDW_GT3(dev_priv) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
-
-	return 0;
-}
-
-static int chv_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	ret = gen8_init_workarounds(engine);
-	if (ret)
-		return ret;
-
-	/* WaDisableThreadStallDopClockGating:chv */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
-
-	/* Improve HiZ throughput on CHV. */
-	WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
-
-	return 0;
-}
-
-static int gen9_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	/* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */
-	I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE));
-
-	/* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */
-	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
-		   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
-
-	/* WaDisableKillLogic:bxt,skl,kbl */
-	if (!IS_COFFEELAKE(dev_priv))
-		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
-			   ECOCHK_DIS_TLB);
-
-	if (HAS_LLC(dev_priv)) {
-		/* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
-		 *
-		 * Must match Display Engine. See
-		 * WaCompressedResourceDisplayNewHashMode.
-		 */
-		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
-				  GEN9_PBE_COMPRESSED_HASH_SELECTION);
-		WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
-				  GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR);
-
-		I915_WRITE(MMCD_MISC_CTRL,
-			   I915_READ(MMCD_MISC_CTRL) |
-			   MMCD_PCLA |
-			   MMCD_HOTSPOT_EN);
-	}
-
-	/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */
-	/* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
-			  FLOW_CONTROL_ENABLE |
-			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
-
-	/* Syncing dependencies between camera and graphics:skl,bxt,kbl */
-	if (!IS_COFFEELAKE(dev_priv))
-		WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
-				  GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
-
-	/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */
-	/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */
-	WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
-			  GEN9_ENABLE_YV12_BUGFIX |
-			  GEN9_ENABLE_GPGPU_PREEMPTION);
-
-	/* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk,cfl */
-	/* WaDisablePartialResolveInVc:skl,bxt,kbl,cfl */
-	WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE |
-					 GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE));
-
-	/* WaCcsTlbPrefetchDisable:skl,bxt,kbl,glk,cfl */
-	WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
-			  GEN9_CCS_TLB_PREFETCH_ENABLE);
-
-	/* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl,cfl */
-	WA_SET_BIT_MASKED(HDC_CHICKEN0,
-			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
-			  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE);
-
-	/* WaForceEnableNonCoherent and WaDisableHDCInvalidation are
-	 * both tied to WaForceContextSaveRestoreNonCoherent
-	 * in some hsds for skl. We keep the tie for all gen9. The
-	 * documentation is a bit hazy and so we want to get common behaviour,
-	 * even though there is no clear evidence we would need both on kbl/bxt.
-	 * This area has been source of system hangs so we play it safe
-	 * and mimic the skl regardless of what bspec says.
-	 *
-	 * Use Force Non-Coherent whenever executing a 3D context. This
-	 * is a workaround for a possible hang in the unlikely event
-	 * a TLB invalidation occurs during a PSD flush.
-	 */
-
-	/* WaForceEnableNonCoherent:skl,bxt,kbl,cfl */
-	WA_SET_BIT_MASKED(HDC_CHICKEN0,
-			  HDC_FORCE_NON_COHERENT);
-
-	/* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */
-	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
-		   BDW_DISABLE_HDC_INVALIDATION);
-
-	/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl,cfl */
-	if (IS_SKYLAKE(dev_priv) ||
-	    IS_KABYLAKE(dev_priv) ||
-	    IS_COFFEELAKE(dev_priv))
-		WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
-				  GEN8_SAMPLER_POWER_BYPASS_DIS);
-
-	/* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */
-	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
-
-	/* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */
-	if (IS_GEN9_LP(dev_priv)) {
-		u32 val = I915_READ(GEN8_L3SQCREG1);
-
-		val &= ~L3_PRIO_CREDITS_MASK;
-		val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2);
-		I915_WRITE(GEN8_L3SQCREG1, val);
-	}
-
-	/* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */
-	I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) |
-				    GEN8_LQSC_FLUSH_COHERENT_LINES));
-
-	/*
-	 * Supporting preemption with fine-granularity requires changes in the
-	 * batch buffer programming. Since we can't break old userspace, we
-	 * need to set our default preemption level to safe value. Userspace is
-	 * still able to use more fine-grained preemption levels, since in
-	 * WaEnablePreemptionGranularityControlByUMD we're whitelisting the
-	 * per-ctx register. As such, WaDisable{3D,GPGPU}MidCmdPreemption are
-	 * not real HW workarounds, but merely a way to start using preemption
-	 * while maintaining old contract with userspace.
-	 */
-
-	/* WaDisable3DMidCmdPreemption:skl,bxt,glk,cfl,[cnl] */
-	WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
-
-	/* WaDisableGPGPUMidCmdPreemption:skl,bxt,blk,cfl,[cnl] */
-	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK,
-			    GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
-
-	/* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */
-	ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG);
-	if (ret)
-		return ret;
-
-	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */
-	I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
-		   _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
-	ret = wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1);
-	if (ret)
-		return ret;
-
-	/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
-	ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-static int skl_tune_iz_hashing(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	u8 vals[3] = { 0, 0, 0 };
-	unsigned int i;
-
-	for (i = 0; i < 3; i++) {
-		u8 ss;
-
-		/*
-		 * Only consider slices where one, and only one, subslice has 7
-		 * EUs
-		 */
-		if (!is_power_of_2(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i]))
-			continue;
-
-		/*
-		 * subslice_7eu[i] != 0 (because of the check above) and
-		 * ss_max == 4 (maximum number of subslices possible per slice)
-		 *
-		 * ->    0 <= ss <= 3;
-		 */
-		ss = ffs(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i]) - 1;
-		vals[i] = 3 - ss;
-	}
-
-	if (vals[0] == 0 && vals[1] == 0 && vals[2] == 0)
-		return 0;
-
-	/* Tune IZ hashing. See intel_device_info_runtime_init() */
-	WA_SET_FIELD_MASKED(GEN7_GT_MODE,
-			    GEN9_IZ_HASHING_MASK(2) |
-			    GEN9_IZ_HASHING_MASK(1) |
-			    GEN9_IZ_HASHING_MASK(0),
-			    GEN9_IZ_HASHING(2, vals[2]) |
-			    GEN9_IZ_HASHING(1, vals[1]) |
-			    GEN9_IZ_HASHING(0, vals[0]));
-
-	return 0;
-}
-
-static int skl_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	ret = gen9_init_workarounds(engine);
-	if (ret)
-		return ret;
-
-	/* WaEnableGapsTsvCreditFix:skl */
-	I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
-				   GEN9_GAPS_TSV_CREDIT_DISABLE));
-
-	/* WaDisableGafsUnitClkGating:skl */
-	I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) |
-				  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE));
-
-	/* WaInPlaceDecompressionHang:skl */
-	if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER))
-		I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
-			   (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
-			    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
-	/* WaDisableLSQCROPERFforOCL:skl */
-	ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
-	if (ret)
-		return ret;
-
-	return skl_tune_iz_hashing(engine);
-}
-
-static int bxt_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	ret = gen9_init_workarounds(engine);
-	if (ret)
-		return ret;
-
-	/* WaDisableThreadStallDopClockGating:bxt */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
-			  STALL_DOP_GATING_DISABLE);
-
-	/* WaDisablePooledEuLoadBalancingFix:bxt */
-	I915_WRITE(FF_SLICE_CS_CHICKEN2,
-		   _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE));
-
-	/* WaToEnableHwFixForPushConstHWBug:bxt */
-	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
-			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
-	/* WaInPlaceDecompressionHang:bxt */
-	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
-		   (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
-		    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
-	return 0;
-}
-
-static int cnl_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	/* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */
-	if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0))
-		I915_WRITE(GAMT_CHKN_BIT_REG,
-			   (I915_READ(GAMT_CHKN_BIT_REG) |
-			    GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT));
-
-	/* WaForceContextSaveRestoreNonCoherent:cnl */
-	WA_SET_BIT_MASKED(CNL_HDC_CHICKEN0,
-			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT);
-
-	/* WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod) */
-	if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0))
-		WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, THROTTLE_12_5);
-
-	/* WaDisableReplayBufferBankArbitrationOptimization:cnl */
-	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
-			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
-	/* WaDisableEnhancedSBEVertexCaching:cnl (pre-prod) */
-	if (IS_CNL_REVID(dev_priv, 0, CNL_REVID_B0))
-		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
-				  GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE);
-
-	/* WaInPlaceDecompressionHang:cnl */
-	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
-		   (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
-		    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
-	/* WaPushConstantDereferenceHoldDisable:cnl */
-	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE);
-
-	/* FtrEnableFastAnisoL1BankingFix: cnl */
-	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, CNL_FAST_ANISO_L1_BANKING_FIX);
-
-	/* WaDisable3DMidCmdPreemption:cnl */
-	WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
-
-	/* WaDisableGPGPUMidCmdPreemption:cnl */
-	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK,
-			    GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
-
-	/* WaEnablePreemptionGranularityControlByUMD:cnl */
-	I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
-		   _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
-	ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1);
-	if (ret)
-		return ret;
-
-	/* WaDisableEarlyEOT:cnl */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, DISABLE_EARLY_EOT);
-
-	return 0;
-}
-
-static int kbl_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	ret = gen9_init_workarounds(engine);
-	if (ret)
-		return ret;
-
-	/* WaEnableGapsTsvCreditFix:kbl */
-	I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
-				   GEN9_GAPS_TSV_CREDIT_DISABLE));
-
-	/* WaDisableDynamicCreditSharing:kbl */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
-		I915_WRITE(GAMT_CHKN_BIT_REG,
-			   (I915_READ(GAMT_CHKN_BIT_REG) |
-			    GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING));
-
-	/* WaDisableFenceDestinationToSLM:kbl (pre-prod) */
-	if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0))
-		WA_SET_BIT_MASKED(HDC_CHICKEN0,
-				  HDC_FENCE_DEST_SLM_DISABLE);
-
-	/* WaToEnableHwFixForPushConstHWBug:kbl */
-	if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER))
-		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
-				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
-	/* WaDisableGafsUnitClkGating:kbl */
-	I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) |
-				  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE));
-
-	/* WaDisableSbeCacheDispatchPortSharing:kbl */
-	WA_SET_BIT_MASKED(
-		GEN7_HALF_SLICE_CHICKEN1,
-		GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
-
-	/* WaInPlaceDecompressionHang:kbl */
-	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
-		   (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
-		    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
-	/* WaDisableLSQCROPERFforOCL:kbl */
-	ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-static int glk_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	ret = gen9_init_workarounds(engine);
-	if (ret)
-		return ret;
-
-	/* WA #0862: Userspace has to set "Barrier Mode" to avoid hangs. */
-	ret = wa_ring_whitelist_reg(engine, GEN9_SLICE_COMMON_ECO_CHICKEN1);
-	if (ret)
-		return ret;
-
-	/* WaToEnableHwFixForPushConstHWBug:glk */
-	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
-			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
-	return 0;
-}
-
-static int cfl_init_workarounds(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int ret;
-
-	ret = gen9_init_workarounds(engine);
-	if (ret)
-		return ret;
-
-	/* WaEnableGapsTsvCreditFix:cfl */
-	I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
-				   GEN9_GAPS_TSV_CREDIT_DISABLE));
-
-	/* WaToEnableHwFixForPushConstHWBug:cfl */
-	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
-			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
-	/* WaDisableGafsUnitClkGating:cfl */
-	I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) |
-				  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE));
-
-	/* WaDisableSbeCacheDispatchPortSharing:cfl */
-	WA_SET_BIT_MASKED(
-		GEN7_HALF_SLICE_CHICKEN1,
-		GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
-
-	/* WaInPlaceDecompressionHang:cfl */
-	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
-		   (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
-		    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
-	return 0;
-}
-
-int init_workarounds_ring(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int err;
-
-	if (GEM_WARN_ON(engine->id != RCS))
-		return -EINVAL;
-
-	dev_priv->workarounds.count = 0;
-	dev_priv->workarounds.hw_whitelist_count[engine->id] = 0;
-
-	if (IS_BROADWELL(dev_priv))
-		err = bdw_init_workarounds(engine);
-	else if (IS_CHERRYVIEW(dev_priv))
-		err = chv_init_workarounds(engine);
-	else if (IS_SKYLAKE(dev_priv))
-		err =  skl_init_workarounds(engine);
-	else if (IS_BROXTON(dev_priv))
-		err = bxt_init_workarounds(engine);
-	else if (IS_KABYLAKE(dev_priv))
-		err = kbl_init_workarounds(engine);
-	else if (IS_GEMINILAKE(dev_priv))
-		err =  glk_init_workarounds(engine);
-	else if (IS_COFFEELAKE(dev_priv))
-		err = cfl_init_workarounds(engine);
-	else if (IS_CANNONLAKE(dev_priv))
-		err = cnl_init_workarounds(engine);
-	else
-		err = 0;
-	if (err)
-		return err;
-
-	DRM_DEBUG_DRIVER("%s: Number of context specific w/a: %d\n",
-			 engine->name, dev_priv->workarounds.count);
-	return 0;
-}
-
-int intel_ring_workarounds_emit(struct i915_request *rq)
-{
-	struct i915_workarounds *w = &rq->i915->workarounds;
-	u32 *cs;
-	int ret, i;
-
-	if (w->count == 0)
-		return 0;
-
-	ret = rq->engine->emit_flush(rq, EMIT_BARRIER);
-	if (ret)
-		return ret;
-
-	cs = intel_ring_begin(rq, w->count * 2 + 2);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(w->count);
-	for (i = 0; i < w->count; i++) {
-		*cs++ = i915_mmio_reg_offset(w->reg[i].addr);
-		*cs++ = w->reg[i].value;
-	}
-	*cs++ = MI_NOOP;
-
-	intel_ring_advance(rq, cs);
-
-	ret = rq->engine->emit_flush(rq, EMIT_BARRIER);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
 static bool ring_is_idle(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
@@ -1607,7 +989,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 	 * the last request that remains in the timeline. When idle, it is
 	 * the last executed context as tracked by retirement.
 	 */
-	rq = __i915_gem_active_peek(&engine->timeline->last_request);
+	rq = __i915_gem_active_peek(&engine->timeline.last_request);
 	if (rq)
 		return rq->ctx == kernel_context;
 	else
@@ -1655,6 +1037,9 @@ void intel_engines_park(struct drm_i915_private *i915)
 			intel_engine_dump(engine, &p, NULL);
 		}
 
+		/* Must be reset upon idling, or we may miss the busy wakeup. */
+		GEM_BUG_ON(engine->execlists.queue_priority != INT_MIN);
+
 		if (engine->park)
 			engine->park(engine);
 
@@ -1677,6 +1062,8 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 	for_each_engine(engine, i915, id) {
 		if (engine->unpark)
 			engine->unpark(engine);
+
+		intel_engine_init_hangcheck(engine);
 	}
 }
 
@@ -1709,17 +1096,37 @@ unsigned int intel_engines_has_context_isolation(struct drm_i915_private *i915)
 	return which;
 }
 
+static int print_sched_attr(struct drm_i915_private *i915,
+			    const struct i915_sched_attr *attr,
+			    char *buf, int x, int len)
+{
+	if (attr->priority == I915_PRIORITY_INVALID)
+		return x;
+
+	x += snprintf(buf + x, len - x,
+		      " prio=%d", attr->priority);
+
+	return x;
+}
+
 static void print_request(struct drm_printer *m,
 			  struct i915_request *rq,
 			  const char *prefix)
 {
-	drm_printf(m, "%s%x%s [%llx:%x] prio=%d @ %dms: %s\n", prefix,
+	const char *name = rq->fence.ops->get_timeline_name(&rq->fence);
+	char buf[80];
+	int x = 0;
+
+	x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf));
+
+	drm_printf(m, "%s%x%s [%llx:%x]%s @ %dms: %s\n",
+		   prefix,
 		   rq->global_seqno,
 		   i915_request_completed(rq) ? "!" : "",
 		   rq->fence.context, rq->fence.seqno,
-		   rq->priotree.priority,
+		   buf,
 		   jiffies_to_msecs(jiffies - rq->emitted_jiffies),
-		   rq->timeline->common->name);
+		   name);
 }
 
 static void hexdump(struct drm_printer *m, const void *buf, size_t len)
@@ -1825,12 +1232,15 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
 		read = GEN8_CSB_READ_PTR(ptr);
 		write = GEN8_CSB_WRITE_PTR(ptr);
-		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n",
+		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s, tasklet queued? %s (%s)\n",
 			   read, execlists->csb_head,
 			   write,
 			   intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
 			   yesno(test_bit(ENGINE_IRQ_EXECLIST,
-					  &engine->irq_posted)));
+					  &engine->irq_posted)),
+			   yesno(test_bit(TASKLET_STATE_SCHED,
+					  &engine->execlists.tasklet.state)),
+			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)));
 		if (read >= GEN8_CSB_ENTRIES)
 			read = 0;
 		if (write >= GEN8_CSB_ENTRIES)
@@ -1857,8 +1267,9 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 				char hdr[80];
 
 				snprintf(hdr, sizeof(hdr),
-					 "\t\tELSP[%d] count=%d, rq: ",
-					 idx, count);
+					 "\t\tELSP[%d] count=%d, ring->start=%08x, rq: ",
+					 idx, count,
+					 i915_ggtt_offset(rq->ring->vma));
 				print_request(m, rq, hdr);
 			} else {
 				drm_printf(m, "\t\tELSP[%d] idle\n", idx);
@@ -1880,11 +1291,13 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
 {
+	const int MAX_REQUESTS_TO_SHOW = 8;
 	struct intel_breadcrumbs * const b = &engine->breadcrumbs;
 	const struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_gpu_error * const error = &engine->i915->gpu_error;
-	struct i915_request *rq;
+	struct i915_request *rq, *last;
 	struct rb_node *rb;
+	int count;
 
 	if (header) {
 		va_list ap;
@@ -1897,12 +1310,11 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	if (i915_terminally_wedged(&engine->i915->gpu_error))
 		drm_printf(m, "*** WEDGED ***\n");
 
-	drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d\n",
+	drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms]\n",
 		   intel_engine_get_seqno(engine),
 		   intel_engine_last_submit(engine),
 		   engine->hangcheck.seqno,
-		   jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp),
-		   engine->timeline->inflight_seqnos);
+		   jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
 	drm_printf(m, "\tReset count: %d (global %d)\n",
 		   i915_reset_engine_count(error, engine),
 		   i915_reset_count(error));
@@ -1911,14 +1323,14 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 
 	drm_printf(m, "\tRequests:\n");
 
-	rq = list_first_entry(&engine->timeline->requests,
+	rq = list_first_entry(&engine->timeline.requests,
 			      struct i915_request, link);
-	if (&rq->link != &engine->timeline->requests)
+	if (&rq->link != &engine->timeline.requests)
 		print_request(m, rq, "\t\tfirst  ");
 
-	rq = list_last_entry(&engine->timeline->requests,
+	rq = list_last_entry(&engine->timeline.requests,
 			     struct i915_request, link);
-	if (&rq->link != &engine->timeline->requests)
+	if (&rq->link != &engine->timeline.requests)
 		print_request(m, rq, "\t\tlast   ");
 
 	rq = i915_gem_find_active_request(engine);
@@ -1929,12 +1341,16 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   rq->head, rq->postfix, rq->tail,
 			   rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
 			   rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
-		drm_printf(m, "\t\tring->start: 0x%08x\n",
+		drm_printf(m, "\t\tring->start:  0x%08x\n",
 			   i915_ggtt_offset(rq->ring->vma));
-		drm_printf(m, "\t\tring->head:  0x%08x\n",
+		drm_printf(m, "\t\tring->head:   0x%08x\n",
 			   rq->ring->head);
-		drm_printf(m, "\t\tring->tail:  0x%08x\n",
+		drm_printf(m, "\t\tring->tail:   0x%08x\n",
 			   rq->ring->tail);
+		drm_printf(m, "\t\tring->emit:   0x%08x\n",
+			   rq->ring->emit);
+		drm_printf(m, "\t\tring->space:  0x%08x\n",
+			   rq->ring->space);
 	}
 
 	rcu_read_unlock();
@@ -1946,18 +1362,49 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		drm_printf(m, "\tDevice is asleep; skipping register dump\n");
 	}
 
-	spin_lock_irq(&engine->timeline->lock);
-	list_for_each_entry(rq, &engine->timeline->requests, link)
-		print_request(m, rq, "\t\tE ");
+	spin_lock_irq(&engine->timeline.lock);
+
+	last = NULL;
+	count = 0;
+	list_for_each_entry(rq, &engine->timeline.requests, link) {
+		if (count++ < MAX_REQUESTS_TO_SHOW - 1)
+			print_request(m, rq, "\t\tE ");
+		else
+			last = rq;
+	}
+	if (last) {
+		if (count > MAX_REQUESTS_TO_SHOW) {
+			drm_printf(m,
+				   "\t\t...skipping %d executing requests...\n",
+				   count - MAX_REQUESTS_TO_SHOW);
+		}
+		print_request(m, last, "\t\tE ");
+	}
+
+	last = NULL;
+	count = 0;
 	drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
 	for (rb = execlists->first; rb; rb = rb_next(rb)) {
 		struct i915_priolist *p =
 			rb_entry(rb, typeof(*p), node);
 
-		list_for_each_entry(rq, &p->requests, priotree.link)
-			print_request(m, rq, "\t\tQ ");
+		list_for_each_entry(rq, &p->requests, sched.link) {
+			if (count++ < MAX_REQUESTS_TO_SHOW - 1)
+				print_request(m, rq, "\t\tQ ");
+			else
+				last = rq;
+		}
+	}
+	if (last) {
+		if (count > MAX_REQUESTS_TO_SHOW) {
+			drm_printf(m,
+				   "\t\t...skipping %d queued requests...\n",
+				   count - MAX_REQUESTS_TO_SHOW);
+		}
+		print_request(m, last, "\t\tQ ");
 	}
-	spin_unlock_irq(&engine->timeline->lock);
+
+	spin_unlock_irq(&engine->timeline.lock);
 
 	spin_lock_irq(&b->rb_lock);
 	for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
@@ -2022,7 +1469,7 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 		return -ENODEV;
 
 	tasklet_disable(&execlists->tasklet);
-	spin_lock_irqsave(&engine->stats.lock, flags);
+	write_seqlock_irqsave(&engine->stats.lock, flags);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -2046,7 +1493,7 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	spin_unlock_irqrestore(&engine->stats.lock, flags);
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 	tasklet_enable(&execlists->tasklet);
 
 	return err;
@@ -2075,12 +1522,13 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
  */
 ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
 {
+	unsigned int seq;
 	ktime_t total;
-	unsigned long flags;
 
-	spin_lock_irqsave(&engine->stats.lock, flags);
-	total = __intel_engine_get_busy_time(engine);
-	spin_unlock_irqrestore(&engine->stats.lock, flags);
+	do {
+		seq = read_seqbegin(&engine->stats.lock);
+		total = __intel_engine_get_busy_time(engine);
+	} while (read_seqretry(&engine->stats.lock, seq));
 
 	return total;
 }
@@ -2098,15 +1546,16 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return;
 
-	spin_lock_irqsave(&engine->stats.lock, flags);
+	write_seqlock_irqsave(&engine->stats.lock, flags);
 	WARN_ON_ONCE(engine->stats.enabled == 0);
 	if (--engine->stats.enabled == 0) {
 		engine->stats.total = __intel_engine_get_busy_time(engine);
 		engine->stats.active = 0;
 	}
-	spin_unlock_irqrestore(&engine->stats.lock, flags);
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_engine.c"
+#include "selftests/intel_engine_cs.c"
 #endif
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 707d49c12638..b431b6733cc1 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -1272,6 +1272,34 @@ out:
 	mutex_unlock(&fbc->lock);
 }
 
+/*
+ * intel_fbc_reset_underrun - reset FBC fifo underrun status.
+ * @dev_priv: i915 device instance
+ *
+ * See intel_fbc_handle_fifo_underrun_irq(). For automated testing we
+ * want to re-enable FBC after an underrun to increase test coverage.
+ */
+int intel_fbc_reset_underrun(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	cancel_work_sync(&dev_priv->fbc.underrun_work);
+
+	ret = mutex_lock_interruptible(&dev_priv->fbc.lock);
+	if (ret)
+		return ret;
+
+	if (dev_priv->fbc.underrun_detected) {
+		DRM_DEBUG_KMS("Re-allowing FBC after fifo underrun\n");
+		dev_priv->fbc.no_fbc_reason = "FIFO underrun cleared";
+	}
+
+	dev_priv->fbc.underrun_detected = false;
+	mutex_unlock(&dev_priv->fbc.lock);
+
+	return 0;
+}
+
 /**
  * intel_fbc_handle_fifo_underrun_irq - disable FBC when we get a FIFO underrun
  * @dev_priv: i915 device instance
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 6f12adc06365..e9e02b58b7be 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -221,6 +221,9 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		goto out_unlock;
 	}
 
+	fb = &ifbdev->fb->base;
+	intel_fb_obj_flush(intel_fb_obj(fb), ORIGIN_DIRTYFB);
+
 	info = drm_fb_helper_alloc_fbi(helper);
 	if (IS_ERR(info)) {
 		DRM_ERROR("Failed to allocate fb_info\n");
@@ -230,8 +233,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	info->par = helper;
 
-	fb = &ifbdev->fb->base;
-
 	ifbdev->helper.fb = fb;
 
 	strcpy(info->fix.id, "inteldrmfb");
@@ -640,7 +641,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 		if (!crtc->state->active)
 			continue;
 
-		WARN(!crtc->primary->fb,
+		WARN(!crtc->primary->state->fb,
 		     "re-used BIOS config but lost an fb on crtc %d\n",
 		     crtc->base.id);
 	}
@@ -806,7 +807,7 @@ void intel_fbdev_output_poll_changed(struct drm_device *dev)
 		return;
 
 	intel_fbdev_sync(ifbdev);
-	if (ifbdev->vma)
+	if (ifbdev->vma || ifbdev->helper.deferred_setup)
 		drm_fb_helper_hotplug_event(&ifbdev->helper);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c
index 3a8d3d06c26a..7fff0a0eceb4 100644
--- a/drivers/gpu/drm/i915/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/intel_frontbuffer.c
@@ -80,7 +80,7 @@ void __intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
 	}
 
 	might_sleep();
-	intel_psr_invalidate(dev_priv, frontbuffer_bits);
+	intel_psr_invalidate(dev_priv, frontbuffer_bits, origin);
 	intel_edp_drrs_invalidate(dev_priv, frontbuffer_bits);
 	intel_fbc_invalidate(dev_priv, frontbuffer_bits, origin);
 }
diff --git a/drivers/gpu/drm/i915/intel_gpu_commands.h b/drivers/gpu/drm/i915/intel_gpu_commands.h
new file mode 100644
index 000000000000..105e2a9e874a
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_gpu_commands.h
@@ -0,0 +1,274 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright � 2003-2018 Intel Corporation
+ */
+
+#ifndef _INTEL_GPU_COMMANDS_H_
+#define _INTEL_GPU_COMMANDS_H_
+
+/*
+ * Instruction field definitions used by the command parser
+ */
+#define INSTR_CLIENT_SHIFT      29
+#define   INSTR_MI_CLIENT       0x0
+#define   INSTR_BC_CLIENT       0x2
+#define   INSTR_RC_CLIENT       0x3
+#define INSTR_SUBCLIENT_SHIFT   27
+#define INSTR_SUBCLIENT_MASK    0x18000000
+#define   INSTR_MEDIA_SUBCLIENT 0x2
+#define INSTR_26_TO_24_MASK	0x7000000
+#define   INSTR_26_TO_24_SHIFT	24
+
+/*
+ * Memory interface instructions used by the kernel
+ */
+#define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags))
+/* Many MI commands use bit 22 of the header dword for GGTT vs PPGTT */
+#define  MI_GLOBAL_GTT    (1<<22)
+
+#define MI_NOOP			MI_INSTR(0, 0)
+#define MI_USER_INTERRUPT	MI_INSTR(0x02, 0)
+#define MI_WAIT_FOR_EVENT       MI_INSTR(0x03, 0)
+#define   MI_WAIT_FOR_OVERLAY_FLIP	(1<<16)
+#define   MI_WAIT_FOR_PLANE_B_FLIP      (1<<6)
+#define   MI_WAIT_FOR_PLANE_A_FLIP      (1<<2)
+#define   MI_WAIT_FOR_PLANE_A_SCANLINES (1<<1)
+#define MI_FLUSH		MI_INSTR(0x04, 0)
+#define   MI_READ_FLUSH		(1 << 0)
+#define   MI_EXE_FLUSH		(1 << 1)
+#define   MI_NO_WRITE_FLUSH	(1 << 2)
+#define   MI_SCENE_COUNT	(1 << 3) /* just increment scene count */
+#define   MI_END_SCENE		(1 << 4) /* flush binner and incr scene count */
+#define   MI_INVALIDATE_ISP	(1 << 5) /* invalidate indirect state pointers */
+#define MI_REPORT_HEAD		MI_INSTR(0x07, 0)
+#define MI_ARB_ON_OFF		MI_INSTR(0x08, 0)
+#define   MI_ARB_ENABLE			(1<<0)
+#define   MI_ARB_DISABLE		(0<<0)
+#define MI_BATCH_BUFFER_END	MI_INSTR(0x0a, 0)
+#define MI_SUSPEND_FLUSH	MI_INSTR(0x0b, 0)
+#define   MI_SUSPEND_FLUSH_EN	(1<<0)
+#define MI_SET_APPID		MI_INSTR(0x0e, 0)
+#define MI_OVERLAY_FLIP		MI_INSTR(0x11, 0)
+#define   MI_OVERLAY_CONTINUE	(0x0<<21)
+#define   MI_OVERLAY_ON		(0x1<<21)
+#define   MI_OVERLAY_OFF	(0x2<<21)
+#define MI_LOAD_SCAN_LINES_INCL MI_INSTR(0x12, 0)
+#define MI_DISPLAY_FLIP		MI_INSTR(0x14, 2)
+#define MI_DISPLAY_FLIP_I915	MI_INSTR(0x14, 1)
+#define   MI_DISPLAY_FLIP_PLANE(n) ((n) << 20)
+/* IVB has funny definitions for which plane to flip. */
+#define   MI_DISPLAY_FLIP_IVB_PLANE_A  (0 << 19)
+#define   MI_DISPLAY_FLIP_IVB_PLANE_B  (1 << 19)
+#define   MI_DISPLAY_FLIP_IVB_SPRITE_A (2 << 19)
+#define   MI_DISPLAY_FLIP_IVB_SPRITE_B (3 << 19)
+#define   MI_DISPLAY_FLIP_IVB_PLANE_C  (4 << 19)
+#define   MI_DISPLAY_FLIP_IVB_SPRITE_C (5 << 19)
+/* SKL ones */
+#define   MI_DISPLAY_FLIP_SKL_PLANE_1_A	(0 << 8)
+#define   MI_DISPLAY_FLIP_SKL_PLANE_1_B	(1 << 8)
+#define   MI_DISPLAY_FLIP_SKL_PLANE_1_C	(2 << 8)
+#define   MI_DISPLAY_FLIP_SKL_PLANE_2_A	(4 << 8)
+#define   MI_DISPLAY_FLIP_SKL_PLANE_2_B	(5 << 8)
+#define   MI_DISPLAY_FLIP_SKL_PLANE_2_C	(6 << 8)
+#define   MI_DISPLAY_FLIP_SKL_PLANE_3_A	(7 << 8)
+#define   MI_DISPLAY_FLIP_SKL_PLANE_3_B	(8 << 8)
+#define   MI_DISPLAY_FLIP_SKL_PLANE_3_C	(9 << 8)
+#define MI_SEMAPHORE_MBOX	MI_INSTR(0x16, 1) /* gen6, gen7 */
+#define   MI_SEMAPHORE_GLOBAL_GTT    (1<<22)
+#define   MI_SEMAPHORE_UPDATE	    (1<<21)
+#define   MI_SEMAPHORE_COMPARE	    (1<<20)
+#define   MI_SEMAPHORE_REGISTER	    (1<<18)
+#define   MI_SEMAPHORE_SYNC_VR	    (0<<16) /* RCS  wait for VCS  (RVSYNC) */
+#define   MI_SEMAPHORE_SYNC_VER	    (1<<16) /* RCS  wait for VECS (RVESYNC) */
+#define   MI_SEMAPHORE_SYNC_BR	    (2<<16) /* RCS  wait for BCS  (RBSYNC) */
+#define   MI_SEMAPHORE_SYNC_BV	    (0<<16) /* VCS  wait for BCS  (VBSYNC) */
+#define   MI_SEMAPHORE_SYNC_VEV	    (1<<16) /* VCS  wait for VECS (VVESYNC) */
+#define   MI_SEMAPHORE_SYNC_RV	    (2<<16) /* VCS  wait for RCS  (VRSYNC) */
+#define   MI_SEMAPHORE_SYNC_RB	    (0<<16) /* BCS  wait for RCS  (BRSYNC) */
+#define   MI_SEMAPHORE_SYNC_VEB	    (1<<16) /* BCS  wait for VECS (BVESYNC) */
+#define   MI_SEMAPHORE_SYNC_VB	    (2<<16) /* BCS  wait for VCS  (BVSYNC) */
+#define   MI_SEMAPHORE_SYNC_BVE	    (0<<16) /* VECS wait for BCS  (VEBSYNC) */
+#define   MI_SEMAPHORE_SYNC_VVE	    (1<<16) /* VECS wait for VCS  (VEVSYNC) */
+#define   MI_SEMAPHORE_SYNC_RVE	    (2<<16) /* VECS wait for RCS  (VERSYNC) */
+#define   MI_SEMAPHORE_SYNC_INVALID (3<<16)
+#define   MI_SEMAPHORE_SYNC_MASK    (3<<16)
+#define MI_SET_CONTEXT		MI_INSTR(0x18, 0)
+#define   MI_MM_SPACE_GTT		(1<<8)
+#define   MI_MM_SPACE_PHYSICAL		(0<<8)
+#define   MI_SAVE_EXT_STATE_EN		(1<<3)
+#define   MI_RESTORE_EXT_STATE_EN	(1<<2)
+#define   MI_FORCE_RESTORE		(1<<1)
+#define   MI_RESTORE_INHIBIT		(1<<0)
+#define   HSW_MI_RS_SAVE_STATE_EN       (1<<3)
+#define   HSW_MI_RS_RESTORE_STATE_EN    (1<<2)
+#define MI_SEMAPHORE_SIGNAL	MI_INSTR(0x1b, 0) /* GEN8+ */
+#define   MI_SEMAPHORE_TARGET(engine)	((engine)<<15)
+#define MI_SEMAPHORE_WAIT	MI_INSTR(0x1c, 2) /* GEN8+ */
+#define   MI_SEMAPHORE_POLL		(1<<15)
+#define   MI_SEMAPHORE_SAD_GTE_SDD	(1<<12)
+#define MI_STORE_DWORD_IMM	MI_INSTR(0x20, 1)
+#define MI_STORE_DWORD_IMM_GEN4	MI_INSTR(0x20, 2)
+#define   MI_MEM_VIRTUAL	(1 << 22) /* 945,g33,965 */
+#define   MI_USE_GGTT		(1 << 22) /* g4x+ */
+#define MI_STORE_DWORD_INDEX	MI_INSTR(0x21, 1)
+#define   MI_STORE_DWORD_INDEX_SHIFT 2
+/*
+ * Official intel docs are somewhat sloppy concerning MI_LOAD_REGISTER_IMM:
+ * - Always issue a MI_NOOP _before_ the MI_LOAD_REGISTER_IMM - otherwise hw
+ *   simply ignores the register load under certain conditions.
+ * - One can actually load arbitrary many arbitrary registers: Simply issue x
+ *   address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
+ */
+#define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
+#define   MI_LRI_FORCE_POSTED		(1<<12)
+#define MI_STORE_REGISTER_MEM        MI_INSTR(0x24, 1)
+#define MI_STORE_REGISTER_MEM_GEN8   MI_INSTR(0x24, 2)
+#define   MI_SRM_LRM_GLOBAL_GTT		(1<<22)
+#define MI_FLUSH_DW		MI_INSTR(0x26, 1) /* for GEN6 */
+#define   MI_FLUSH_DW_STORE_INDEX	(1<<21)
+#define   MI_INVALIDATE_TLB		(1<<18)
+#define   MI_FLUSH_DW_OP_STOREDW	(1<<14)
+#define   MI_FLUSH_DW_OP_MASK		(3<<14)
+#define   MI_FLUSH_DW_NOTIFY		(1<<8)
+#define   MI_INVALIDATE_BSD		(1<<7)
+#define   MI_FLUSH_DW_USE_GTT		(1<<2)
+#define   MI_FLUSH_DW_USE_PPGTT		(0<<2)
+#define MI_LOAD_REGISTER_MEM	   MI_INSTR(0x29, 1)
+#define MI_LOAD_REGISTER_MEM_GEN8  MI_INSTR(0x29, 2)
+#define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
+#define   MI_BATCH_NON_SECURE		(1)
+/* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
+#define   MI_BATCH_NON_SECURE_I965	(1<<8)
+#define   MI_BATCH_PPGTT_HSW		(1<<8)
+#define   MI_BATCH_NON_SECURE_HSW	(1<<13)
+#define MI_BATCH_BUFFER_START	MI_INSTR(0x31, 0)
+#define   MI_BATCH_GTT		    (2<<6) /* aliased with (1<<7) on gen4 */
+#define MI_BATCH_BUFFER_START_GEN8	MI_INSTR(0x31, 1)
+#define   MI_BATCH_RESOURCE_STREAMER (1<<10)
+
+/*
+ * 3D instructions used by the kernel
+ */
+#define GFX_INSTR(opcode, flags) ((0x3 << 29) | ((opcode) << 24) | (flags))
+
+#define GEN9_MEDIA_POOL_STATE     ((0x3 << 29) | (0x2 << 27) | (0x5 << 16) | 4)
+#define   GEN9_MEDIA_POOL_ENABLE  (1 << 31)
+#define GFX_OP_RASTER_RULES    ((0x3<<29)|(0x7<<24))
+#define GFX_OP_SCISSOR         ((0x3<<29)|(0x1c<<24)|(0x10<<19))
+#define   SC_UPDATE_SCISSOR       (0x1<<1)
+#define   SC_ENABLE_MASK          (0x1<<0)
+#define   SC_ENABLE               (0x1<<0)
+#define GFX_OP_LOAD_INDIRECT   ((0x3<<29)|(0x1d<<24)|(0x7<<16))
+#define GFX_OP_SCISSOR_INFO    ((0x3<<29)|(0x1d<<24)|(0x81<<16)|(0x1))
+#define   SCI_YMIN_MASK      (0xffff<<16)
+#define   SCI_XMIN_MASK      (0xffff<<0)
+#define   SCI_YMAX_MASK      (0xffff<<16)
+#define   SCI_XMAX_MASK      (0xffff<<0)
+#define GFX_OP_SCISSOR_ENABLE	 ((0x3<<29)|(0x1c<<24)|(0x10<<19))
+#define GFX_OP_SCISSOR_RECT	 ((0x3<<29)|(0x1d<<24)|(0x81<<16)|1)
+#define GFX_OP_COLOR_FACTOR      ((0x3<<29)|(0x1d<<24)|(0x1<<16)|0x0)
+#define GFX_OP_STIPPLE           ((0x3<<29)|(0x1d<<24)|(0x83<<16))
+#define GFX_OP_MAP_INFO          ((0x3<<29)|(0x1d<<24)|0x4)
+#define GFX_OP_DESTBUFFER_VARS   ((0x3<<29)|(0x1d<<24)|(0x85<<16)|0x0)
+#define GFX_OP_DESTBUFFER_INFO	 ((0x3<<29)|(0x1d<<24)|(0x8e<<16)|1)
+#define GFX_OP_DRAWRECT_INFO     ((0x3<<29)|(0x1d<<24)|(0x80<<16)|(0x3))
+#define GFX_OP_DRAWRECT_INFO_I965  ((0x7900<<16)|0x2)
+
+#define COLOR_BLT_CMD			(2<<29 | 0x40<<22 | (5-2))
+#define SRC_COPY_BLT_CMD		((2<<29)|(0x43<<22)|4)
+#define XY_SRC_COPY_BLT_CMD		((2<<29)|(0x53<<22)|6)
+#define XY_MONO_SRC_COPY_IMM_BLT	((2<<29)|(0x71<<22)|5)
+#define   BLT_WRITE_A			(2<<20)
+#define   BLT_WRITE_RGB			(1<<20)
+#define   BLT_WRITE_RGBA		(BLT_WRITE_RGB | BLT_WRITE_A)
+#define   BLT_DEPTH_8			(0<<24)
+#define   BLT_DEPTH_16_565		(1<<24)
+#define   BLT_DEPTH_16_1555		(2<<24)
+#define   BLT_DEPTH_32			(3<<24)
+#define   BLT_ROP_SRC_COPY		(0xcc<<16)
+#define   BLT_ROP_COLOR_COPY		(0xf0<<16)
+#define XY_SRC_COPY_BLT_SRC_TILED	(1<<15) /* 965+ only */
+#define XY_SRC_COPY_BLT_DST_TILED	(1<<11) /* 965+ only */
+#define CMD_OP_DISPLAYBUFFER_INFO ((0x0<<29)|(0x14<<23)|2)
+#define   ASYNC_FLIP                (1<<22)
+#define   DISPLAY_PLANE_A           (0<<20)
+#define   DISPLAY_PLANE_B           (1<<20)
+#define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2))
+#define   PIPE_CONTROL_FLUSH_L3				(1<<27)
+#define   PIPE_CONTROL_GLOBAL_GTT_IVB			(1<<24) /* gen7+ */
+#define   PIPE_CONTROL_MMIO_WRITE			(1<<23)
+#define   PIPE_CONTROL_STORE_DATA_INDEX			(1<<21)
+#define   PIPE_CONTROL_CS_STALL				(1<<20)
+#define   PIPE_CONTROL_TLB_INVALIDATE			(1<<18)
+#define   PIPE_CONTROL_MEDIA_STATE_CLEAR		(1<<16)
+#define   PIPE_CONTROL_QW_WRITE				(1<<14)
+#define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
+#define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
+#define   PIPE_CONTROL_WRITE_FLUSH			(1<<12)
+#define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12) /* gen6+ */
+#define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11) /* MBZ on ILK */
+#define   PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE		(1<<10) /* GM45+ only */
+#define   PIPE_CONTROL_INDIRECT_STATE_DISABLE		(1<<9)
+#define   PIPE_CONTROL_NOTIFY				(1<<8)
+#define   PIPE_CONTROL_FLUSH_ENABLE			(1<<7) /* gen7+ */
+#define   PIPE_CONTROL_DC_FLUSH_ENABLE			(1<<5)
+#define   PIPE_CONTROL_VF_CACHE_INVALIDATE		(1<<4)
+#define   PIPE_CONTROL_CONST_CACHE_INVALIDATE		(1<<3)
+#define   PIPE_CONTROL_STATE_CACHE_INVALIDATE		(1<<2)
+#define   PIPE_CONTROL_STALL_AT_SCOREBOARD		(1<<1)
+#define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
+#define   PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
+
+/*
+ * Commands used only by the command parser
+ */
+#define MI_SET_PREDICATE        MI_INSTR(0x01, 0)
+#define MI_ARB_CHECK            MI_INSTR(0x05, 0)
+#define MI_RS_CONTROL           MI_INSTR(0x06, 0)
+#define MI_URB_ATOMIC_ALLOC     MI_INSTR(0x09, 0)
+#define MI_PREDICATE            MI_INSTR(0x0C, 0)
+#define MI_RS_CONTEXT           MI_INSTR(0x0F, 0)
+#define MI_TOPOLOGY_FILTER      MI_INSTR(0x0D, 0)
+#define MI_LOAD_SCAN_LINES_EXCL MI_INSTR(0x13, 0)
+#define MI_URB_CLEAR            MI_INSTR(0x19, 0)
+#define MI_UPDATE_GTT           MI_INSTR(0x23, 0)
+#define MI_CLFLUSH              MI_INSTR(0x27, 0)
+#define MI_REPORT_PERF_COUNT    MI_INSTR(0x28, 0)
+#define   MI_REPORT_PERF_COUNT_GGTT (1<<0)
+#define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 0)
+#define MI_RS_STORE_DATA_IMM    MI_INSTR(0x2B, 0)
+#define MI_LOAD_URB_MEM         MI_INSTR(0x2C, 0)
+#define MI_STORE_URB_MEM        MI_INSTR(0x2D, 0)
+#define MI_CONDITIONAL_BATCH_BUFFER_END MI_INSTR(0x36, 0)
+
+#define PIPELINE_SELECT                ((0x3<<29)|(0x1<<27)|(0x1<<24)|(0x4<<16))
+#define GFX_OP_3DSTATE_VF_STATISTICS   ((0x3<<29)|(0x1<<27)|(0x0<<24)|(0xB<<16))
+#define MEDIA_VFE_STATE                ((0x3<<29)|(0x2<<27)|(0x0<<24)|(0x0<<16))
+#define  MEDIA_VFE_STATE_MMIO_ACCESS_MASK (0x18)
+#define GPGPU_OBJECT                   ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x4<<16))
+#define GPGPU_WALKER                   ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x5<<16))
+#define GFX_OP_3DSTATE_DX9_CONSTANTF_VS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x39<<16))
+#define GFX_OP_3DSTATE_DX9_CONSTANTF_PS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x3A<<16))
+#define GFX_OP_3DSTATE_SO_DECL_LIST \
+	((0x3<<29)|(0x3<<27)|(0x1<<24)|(0x17<<16))
+
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_VS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x43<<16))
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_GS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x44<<16))
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_HS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x45<<16))
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_DS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x46<<16))
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x47<<16))
+
+#define MFX_WAIT  ((0x3<<29)|(0x1<<27)|(0x0<<16))
+
+#define COLOR_BLT     ((0x2<<29)|(0x40<<22))
+#define SRC_COPY_BLT  ((0x2<<29)|(0x43<<22))
+
+#endif /* _INTEL_GPU_COMMANDS_H_ */
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index ff08ea0ebf49..116f4ccf1bbd 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -64,10 +64,12 @@ void intel_guc_init_early(struct intel_guc *guc)
 {
 	intel_guc_fw_init_early(guc);
 	intel_guc_ct_init_early(&guc->ct);
-	intel_guc_log_init_early(guc);
+	intel_guc_log_init_early(&guc->log);
 
 	mutex_init(&guc->send_mutex);
+	spin_lock_init(&guc->irq_lock);
 	guc->send = intel_guc_send_nop;
+	guc->handler = intel_guc_to_host_event_handler_nop;
 	guc->notify = gen8_guc_raise_irq;
 }
 
@@ -86,9 +88,10 @@ int intel_guc_init_wq(struct intel_guc *guc)
 	 * or scheduled later on resume. This way the handling of work
 	 * item can be kept same between system suspend & rpm suspend.
 	 */
-	guc->log.runtime.flush_wq = alloc_ordered_workqueue("i915-guc_log",
-						WQ_HIGHPRI | WQ_FREEZABLE);
-	if (!guc->log.runtime.flush_wq) {
+	guc->log.relay.flush_wq =
+		alloc_ordered_workqueue("i915-guc_log",
+					WQ_HIGHPRI | WQ_FREEZABLE);
+	if (!guc->log.relay.flush_wq) {
 		DRM_ERROR("Couldn't allocate workqueue for GuC log\n");
 		return -ENOMEM;
 	}
@@ -111,7 +114,7 @@ int intel_guc_init_wq(struct intel_guc *guc)
 		guc->preempt_wq = alloc_ordered_workqueue("i915-guc_preempt",
 							  WQ_HIGHPRI);
 		if (!guc->preempt_wq) {
-			destroy_workqueue(guc->log.runtime.flush_wq);
+			destroy_workqueue(guc->log.relay.flush_wq);
 			DRM_ERROR("Couldn't allocate workqueue for GuC "
 				  "preemption\n");
 			return -ENOMEM;
@@ -129,7 +132,7 @@ void intel_guc_fini_wq(struct intel_guc *guc)
 	    USES_GUC_SUBMISSION(dev_priv))
 		destroy_workqueue(guc->preempt_wq);
 
-	destroy_workqueue(guc->log.runtime.flush_wq);
+	destroy_workqueue(guc->log.relay.flush_wq);
 }
 
 static int guc_shared_data_create(struct intel_guc *guc)
@@ -169,7 +172,7 @@ int intel_guc_init(struct intel_guc *guc)
 		return ret;
 	GEM_BUG_ON(!guc->shared_data);
 
-	ret = intel_guc_log_create(guc);
+	ret = intel_guc_log_create(&guc->log);
 	if (ret)
 		goto err_shared;
 
@@ -184,7 +187,7 @@ int intel_guc_init(struct intel_guc *guc)
 	return 0;
 
 err_log:
-	intel_guc_log_destroy(guc);
+	intel_guc_log_destroy(&guc->log);
 err_shared:
 	guc_shared_data_destroy(guc);
 	return ret;
@@ -196,41 +199,27 @@ void intel_guc_fini(struct intel_guc *guc)
 
 	i915_ggtt_disable_guc(dev_priv);
 	intel_guc_ads_destroy(guc);
-	intel_guc_log_destroy(guc);
+	intel_guc_log_destroy(&guc->log);
 	guc_shared_data_destroy(guc);
 }
 
-static u32 get_gt_type(struct drm_i915_private *dev_priv)
+static u32 get_log_control_flags(void)
 {
-	/* XXX: GT type based on PCI device ID? field seems unused by fw */
-	return 0;
-}
-
-static u32 get_core_family(struct drm_i915_private *dev_priv)
-{
-	u32 gen = INTEL_GEN(dev_priv);
+	u32 level = i915_modparams.guc_log_level;
+	u32 flags = 0;
 
-	switch (gen) {
-	case 9:
-		return GUC_CORE_FAMILY_GEN9;
-
-	default:
-		MISSING_CASE(gen);
-		return GUC_CORE_FAMILY_UNKNOWN;
-	}
-}
+	GEM_BUG_ON(level < 0);
 
-static u32 get_log_verbosity_flags(void)
-{
-	if (i915_modparams.guc_log_level > 0) {
-		u32 verbosity = i915_modparams.guc_log_level - 1;
+	if (!GUC_LOG_LEVEL_IS_ENABLED(level))
+		flags |= GUC_LOG_DEFAULT_DISABLED;
 
-		GEM_BUG_ON(verbosity > GUC_LOG_VERBOSITY_MAX);
-		return verbosity << GUC_LOG_VERBOSITY_SHIFT;
-	}
+	if (!GUC_LOG_LEVEL_IS_VERBOSE(level))
+		flags |= GUC_LOG_DISABLED;
+	else
+		flags |= GUC_LOG_LEVEL_TO_VERBOSITY(level) <<
+			 GUC_LOG_VERBOSITY_SHIFT;
 
-	GEM_BUG_ON(i915_modparams.enable_guc < 0);
-	return GUC_LOG_DISABLED;
+	return flags;
 }
 
 /*
@@ -246,10 +235,6 @@ void intel_guc_init_params(struct intel_guc *guc)
 
 	memset(params, 0, sizeof(params));
 
-	params[GUC_CTL_DEVICE_INFO] |=
-		(get_gt_type(dev_priv) << GUC_CTL_GT_TYPE_SHIFT) |
-		(get_core_family(dev_priv) << GUC_CTL_CORE_FAMILY_SHIFT);
-
 	/*
 	 * GuC ARAT increment is 10 ns. GuC default scheduler quantum is one
 	 * second. This ARAR is calculated by:
@@ -265,12 +250,13 @@ void intel_guc_init_params(struct intel_guc *guc)
 
 	params[GUC_CTL_LOG_PARAMS] = guc->log.flags;
 
-	params[GUC_CTL_DEBUG] = get_log_verbosity_flags();
+	params[GUC_CTL_DEBUG] = get_log_control_flags();
 
 	/* If GuC submission is enabled, set up additional parameters here */
 	if (USES_GUC_SUBMISSION(dev_priv)) {
-		u32 ads = guc_ggtt_offset(guc->ads_vma) >> PAGE_SHIFT;
-		u32 pgs = guc_ggtt_offset(dev_priv->guc.stage_desc_pool);
+		u32 ads = intel_guc_ggtt_offset(guc,
+						guc->ads_vma) >> PAGE_SHIFT;
+		u32 pgs = intel_guc_ggtt_offset(guc, guc->stage_desc_pool);
 		u32 ctx_in_16 = GUC_MAX_STAGE_DESCRIPTORS / 16;
 
 		params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT;
@@ -301,16 +287,23 @@ void intel_guc_init_params(struct intel_guc *guc)
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_BLITTER);
 }
 
-int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len)
+int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len,
+		       u32 *response_buf, u32 response_buf_size)
 {
 	WARN(1, "Unexpected send: action=%#x\n", *action);
 	return -ENODEV;
 }
 
+void intel_guc_to_host_event_handler_nop(struct intel_guc *guc)
+{
+	WARN(1, "Unexpected event: no suitable handler\n");
+}
+
 /*
  * This function implements the MMIO based host to GuC interface.
  */
-int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len)
+int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
+			u32 *response_buf, u32 response_buf_size)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	u32 status;
@@ -320,6 +313,9 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len)
 	GEM_BUG_ON(!len);
 	GEM_BUG_ON(len > guc->send_regs.count);
 
+	/* We expect only action code */
+	GEM_BUG_ON(*action & ~INTEL_GUC_MSG_CODE_MASK);
+
 	/* If CT is available, we expect to use MMIO only during init/fini */
 	GEM_BUG_ON(HAS_GUC_CT(dev_priv) &&
 		*action != INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER &&
@@ -341,29 +337,74 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len)
 	 */
 	ret = __intel_wait_for_register_fw(dev_priv,
 					   guc_send_reg(guc, 0),
-					   INTEL_GUC_RECV_MASK,
-					   INTEL_GUC_RECV_MASK,
+					   INTEL_GUC_MSG_TYPE_MASK,
+					   INTEL_GUC_MSG_TYPE_RESPONSE <<
+					   INTEL_GUC_MSG_TYPE_SHIFT,
 					   10, 10, &status);
-	if (status != INTEL_GUC_STATUS_SUCCESS) {
-		/*
-		 * Either the GuC explicitly returned an error (which
-		 * we convert to -EIO here) or no response at all was
-		 * received within the timeout limit (-ETIMEDOUT)
-		 */
-		if (ret != -ETIMEDOUT)
-			ret = -EIO;
-
-		DRM_WARN("INTEL_GUC_SEND: Action 0x%X failed;"
-			 " ret=%d status=0x%08X response=0x%08X\n",
-			 action[0], ret, status, I915_READ(SOFT_SCRATCH(15)));
+	/* If GuC explicitly returned an error, convert it to -EIO */
+	if (!ret && !INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(status))
+		ret = -EIO;
+
+	if (ret) {
+		DRM_DEBUG_DRIVER("INTEL_GUC_SEND: Action 0x%X failed;"
+				 " ret=%d status=0x%08X response=0x%08X\n",
+				 action[0], ret, status,
+				 I915_READ(SOFT_SCRATCH(15)));
+		goto out;
 	}
 
+	if (response_buf) {
+		int count = min(response_buf_size, guc->send_regs.count - 1);
+
+		for (i = 0; i < count; i++)
+			response_buf[i] = I915_READ(guc_send_reg(guc, i + 1));
+	}
+
+	/* Use data from the GuC response as our return value */
+	ret = INTEL_GUC_MSG_TO_DATA(status);
+
+out:
 	intel_uncore_forcewake_put(dev_priv, guc->send_regs.fw_domains);
 	mutex_unlock(&guc->send_mutex);
 
 	return ret;
 }
 
+void intel_guc_to_host_event_handler_mmio(struct intel_guc *guc)
+{
+	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	u32 msg, val;
+
+	/*
+	 * Sample the log buffer flush related bits & clear them out now
+	 * itself from the message identity register to minimize the
+	 * probability of losing a flush interrupt, when there are back
+	 * to back flush interrupts.
+	 * There can be a new flush interrupt, for different log buffer
+	 * type (like for ISR), whilst Host is handling one (for DPC).
+	 * Since same bit is used in message register for ISR & DPC, it
+	 * could happen that GuC sets the bit for 2nd interrupt but Host
+	 * clears out the bit on handling the 1st interrupt.
+	 */
+	spin_lock(&guc->irq_lock);
+	val = I915_READ(SOFT_SCRATCH(15));
+	msg = val & guc->msg_enabled_mask;
+	I915_WRITE(SOFT_SCRATCH(15), val & ~msg);
+	spin_unlock(&guc->irq_lock);
+
+	intel_guc_to_host_process_recv_msg(guc, msg);
+}
+
+void intel_guc_to_host_process_recv_msg(struct intel_guc *guc, u32 msg)
+{
+	/* Make sure to handle only enabled messages */
+	msg &= guc->msg_enabled_mask;
+
+	if (msg & (INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER |
+		   INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED))
+		intel_guc_log_handle_flush_event(&guc->log);
+}
+
 int intel_guc_sample_forcewake(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -410,7 +451,7 @@ int intel_guc_suspend(struct intel_guc *guc)
 	u32 data[] = {
 		INTEL_GUC_ACTION_ENTER_S_STATE,
 		GUC_POWER_D1, /* any value greater than GUC_POWER_D0 */
-		guc_ggtt_offset(guc->shared_data)
+		intel_guc_ggtt_offset(guc, guc->shared_data)
 	};
 
 	return intel_guc_send(guc, data, ARRAY_SIZE(data));
@@ -434,7 +475,7 @@ int intel_guc_reset_engine(struct intel_guc *guc,
 	data[3] = 0;
 	data[4] = 0;
 	data[5] = guc->execbuf_client->stage_id;
-	data[6] = guc_ggtt_offset(guc->shared_data);
+	data[6] = intel_guc_ggtt_offset(guc, guc->shared_data);
 
 	return intel_guc_send(guc, data, ARRAY_SIZE(data));
 }
@@ -448,13 +489,66 @@ int intel_guc_resume(struct intel_guc *guc)
 	u32 data[] = {
 		INTEL_GUC_ACTION_EXIT_S_STATE,
 		GUC_POWER_D0,
-		guc_ggtt_offset(guc->shared_data)
+		intel_guc_ggtt_offset(guc, guc->shared_data)
 	};
 
 	return intel_guc_send(guc, data, ARRAY_SIZE(data));
 }
 
 /**
+ * DOC: GuC Address Space
+ *
+ * The layout of GuC address space is shown below:
+ *
+ * ::
+ *
+ *     +==============> +====================+ <== GUC_GGTT_TOP
+ *     ^                |                    |
+ *     |                |                    |
+ *     |                |        DRAM        |
+ *     |                |       Memory       |
+ *     |                |                    |
+ *    GuC               |                    |
+ *  Address  +========> +====================+ <== WOPCM Top
+ *   Space   ^          |   HW contexts RSVD |
+ *     |     |          |        WOPCM       |
+ *     |     |     +==> +--------------------+ <== GuC WOPCM Top
+ *     |    GuC    ^    |                    |
+ *     |    GGTT   |    |                    |
+ *     |    Pin   GuC   |        GuC         |
+ *     |    Bias WOPCM  |       WOPCM        |
+ *     |     |    Size  |                    |
+ *     |     |     |    |                    |
+ *     v     v     v    |                    |
+ *     +=====+=====+==> +====================+ <== GuC WOPCM Base
+ *                      |   Non-GuC WOPCM    |
+ *                      |   (HuC/Reserved)   |
+ *                      +====================+ <== WOPCM Base
+ *
+ * The lower part of GuC Address Space [0, ggtt_pin_bias) is mapped to WOPCM
+ * while upper part of GuC Address Space [ggtt_pin_bias, GUC_GGTT_TOP) is mapped
+ * to DRAM. The value of the GuC ggtt_pin_bias is determined by WOPCM size and
+ * actual GuC WOPCM size.
+ */
+
+/**
+ * intel_guc_init_ggtt_pin_bias() - Initialize the GuC ggtt_pin_bias value.
+ * @guc: intel_guc structure.
+ *
+ * This function will calculate and initialize the ggtt_pin_bias value based on
+ * overall WOPCM size and GuC WOPCM size.
+ */
+void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc)
+{
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+
+	GEM_BUG_ON(!i915->wopcm.size);
+	GEM_BUG_ON(i915->wopcm.size < i915->wopcm.guc.base);
+
+	guc->ggtt_pin_bias = i915->wopcm.size - i915->wopcm.guc.base;
+}
+
+/**
  * intel_guc_allocate_vma() - Allocate a GGTT VMA for GuC usage
  * @guc:	the guc
  * @size:	size of area to allocate (both virtual space and memory)
@@ -462,7 +556,7 @@ int intel_guc_resume(struct intel_guc *guc)
  * This is a wrapper to create an object for use with the GuC. In order to
  * use it inside the GuC, an object needs to be pinned lifetime, so we allocate
  * both some backing storage and a range inside the Global GTT. We must pin
- * it in the GGTT somewhere other than than [0, GUC_WOPCM_TOP) because that
+ * it in the GGTT somewhere other than than [0, GUC ggtt_pin_bias) because that
  * range is reserved inside GuC.
  *
  * Return:	A i915_vma if successful, otherwise an ERR_PTR.
@@ -483,7 +577,7 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size)
 		goto err;
 
 	ret = i915_vma_pin(vma, 0, PAGE_SIZE,
-			   PIN_GLOBAL | PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+			   PIN_GLOBAL | PIN_OFFSET_BIAS | guc->ggtt_pin_bias);
 	if (ret) {
 		vma = ERR_PTR(ret);
 		goto err;
@@ -495,14 +589,3 @@ err:
 	i915_gem_object_put(obj);
 	return vma;
 }
-
-u32 intel_guc_wopcm_size(struct drm_i915_private *dev_priv)
-{
-	u32 wopcm_size = GUC_WOPCM_TOP;
-
-	/* On BXT, the top of WOPCM is reserved for RC6 context */
-	if (IS_GEN9_LP(dev_priv))
-		wopcm_size -= BXT_GUC_WOPCM_RC6_RESERVED;
-
-	return wopcm_size;
-}
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index b9424ac644ac..f1265e122d30 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -49,11 +49,16 @@ struct intel_guc {
 	struct intel_guc_log log;
 	struct intel_guc_ct ct;
 
+	/* Offset where Non-WOPCM memory starts. */
+	u32 ggtt_pin_bias;
+
 	/* Log snapshot if GuC errors during load */
 	struct drm_i915_gem_object *load_err_log;
 
 	/* intel_guc_recv interrupt related state */
+	spinlock_t irq_lock;
 	bool interrupts_enabled;
+	unsigned int msg_enabled_mask;
 
 	struct i915_vma *ads_vma;
 	struct i915_vma *stage_desc_pool;
@@ -83,7 +88,11 @@ struct intel_guc {
 	struct mutex send_mutex;
 
 	/* GuC's FW specific send function */
-	int (*send)(struct intel_guc *guc, const u32 *data, u32 len);
+	int (*send)(struct intel_guc *guc, const u32 *data, u32 len,
+		    u32 *response_buf, u32 response_buf_size);
+
+	/* GuC's FW specific event handler function */
+	void (*handler)(struct intel_guc *guc);
 
 	/* GuC's FW specific notify function */
 	void (*notify)(struct intel_guc *guc);
@@ -92,7 +101,14 @@ struct intel_guc {
 static
 inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len)
 {
-	return guc->send(guc, action, len);
+	return guc->send(guc, action, len, NULL, 0);
+}
+
+static inline int
+intel_guc_send_and_receive(struct intel_guc *guc, const u32 *action, u32 len,
+			   u32 *response_buf, u32 response_buf_size)
+{
+	return guc->send(guc, action, len, response_buf, response_buf_size);
 }
 
 static inline void intel_guc_notify(struct intel_guc *guc)
@@ -100,17 +116,33 @@ static inline void intel_guc_notify(struct intel_guc *guc)
 	guc->notify(guc);
 }
 
-/*
- * GuC does not allow any gfx GGTT address that falls into range [0, WOPCM_TOP),
- * which is reserved for Boot ROM, SRAM and WOPCM. Currently this top address is
- * 512K. In order to exclude 0-512K address space from GGTT, all gfx objects
- * used by GuC is pinned with PIN_OFFSET_BIAS along with size of WOPCM.
+static inline void intel_guc_to_host_event_handler(struct intel_guc *guc)
+{
+	guc->handler(guc);
+}
+
+/* GuC addresses above GUC_GGTT_TOP also don't map through the GTT */
+#define GUC_GGTT_TOP	0xFEE00000
+
+/**
+ * intel_guc_ggtt_offset() - Get and validate the GGTT offset of @vma
+ * @guc: intel_guc structure.
+ * @vma: i915 graphics virtual memory area.
+ *
+ * GuC does not allow any gfx GGTT address that falls into range
+ * [0, GuC ggtt_pin_bias), which is reserved for Boot ROM, SRAM and WOPCM.
+ * Currently, in order to exclude [0, GuC ggtt_pin_bias) address space from
+ * GGTT, all gfx objects used by GuC are allocated with intel_guc_allocate_vma()
+ * and pinned with PIN_OFFSET_BIAS along with the value of GuC ggtt_pin_bias.
+ *
+ * Return: GGTT offset of the @vma.
  */
-static inline u32 guc_ggtt_offset(struct i915_vma *vma)
+static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc,
+					struct i915_vma *vma)
 {
 	u32 offset = i915_ggtt_offset(vma);
 
-	GEM_BUG_ON(offset < GUC_WOPCM_TOP);
+	GEM_BUG_ON(offset < guc->ggtt_pin_bias);
 	GEM_BUG_ON(range_overflows_t(u64, offset, vma->size, GUC_GGTT_TOP));
 
 	return offset;
@@ -119,17 +151,43 @@ static inline u32 guc_ggtt_offset(struct i915_vma *vma)
 void intel_guc_init_early(struct intel_guc *guc);
 void intel_guc_init_send_regs(struct intel_guc *guc);
 void intel_guc_init_params(struct intel_guc *guc);
+void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc);
 int intel_guc_init_wq(struct intel_guc *guc);
 void intel_guc_fini_wq(struct intel_guc *guc);
 int intel_guc_init(struct intel_guc *guc);
 void intel_guc_fini(struct intel_guc *guc);
-int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len);
-int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len);
+int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len,
+		       u32 *response_buf, u32 response_buf_size);
+int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
+			u32 *response_buf, u32 response_buf_size);
+void intel_guc_to_host_event_handler(struct intel_guc *guc);
+void intel_guc_to_host_event_handler_nop(struct intel_guc *guc);
+void intel_guc_to_host_event_handler_mmio(struct intel_guc *guc);
+void intel_guc_to_host_process_recv_msg(struct intel_guc *guc, u32 msg);
 int intel_guc_sample_forcewake(struct intel_guc *guc);
 int intel_guc_auth_huc(struct intel_guc *guc, u32 rsa_offset);
 int intel_guc_suspend(struct intel_guc *guc);
 int intel_guc_resume(struct intel_guc *guc);
 struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size);
-u32 intel_guc_wopcm_size(struct drm_i915_private *dev_priv);
+
+static inline int intel_guc_sanitize(struct intel_guc *guc)
+{
+	intel_uc_fw_sanitize(&guc->fw);
+	return 0;
+}
+
+static inline void intel_guc_enable_msg(struct intel_guc *guc, u32 mask)
+{
+	spin_lock_irq(&guc->irq_lock);
+	guc->msg_enabled_mask |= mask;
+	spin_unlock_irq(&guc->irq_lock);
+}
+
+static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask)
+{
+	spin_lock_irq(&guc->irq_lock);
+	guc->msg_enabled_mask &= ~mask;
+	spin_unlock_irq(&guc->irq_lock);
+}
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_guc_ads.c b/drivers/gpu/drm/i915/intel_guc_ads.c
index ac627534667d..dcaa3fb71765 100644
--- a/drivers/gpu/drm/i915/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/intel_guc_ads.c
@@ -75,7 +75,7 @@ static void guc_policies_init(struct guc_policies *policies)
 int intel_guc_ads_create(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct i915_vma *vma;
+	struct i915_vma *vma, *kernel_ctx_vma;
 	struct page *page;
 	/* The ads obj includes the struct itself and buffers passed to GuC */
 	struct {
@@ -121,9 +121,10 @@ int intel_guc_ads_create(struct intel_guc *guc)
 	 * to find it. Note that we have to skip our header (1 page),
 	 * because our GuC shared data is there.
 	 */
+	kernel_ctx_vma = to_intel_context(dev_priv->kernel_context,
+					  dev_priv->engine[RCS])->state;
 	blob->ads.golden_context_lrca =
-		guc_ggtt_offset(dev_priv->kernel_context->engine[RCS].state) +
-		skipped_offset;
+		intel_guc_ggtt_offset(guc, kernel_ctx_vma) + skipped_offset;
 
 	/*
 	 * The GuC expects us to exclude the portion of the context image that
@@ -135,7 +136,7 @@ int intel_guc_ads_create(struct intel_guc *guc)
 		blob->ads.eng_state_size[engine->guc_id] =
 			engine->context_size - skipped_size;
 
-	base = guc_ggtt_offset(vma);
+	base = intel_guc_ggtt_offset(guc, vma);
 	blob->ads.scheduler_policies = base + ptr_offset(blob, policies);
 	blob->ads.reg_state_buffer = base + ptr_offset(blob, reg_state_buffer);
 	blob->ads.reg_state_addr = base + ptr_offset(blob, reg_state);
diff --git a/drivers/gpu/drm/i915/intel_guc_ct.c b/drivers/gpu/drm/i915/intel_guc_ct.c
index 24ad55752396..371b6005954a 100644
--- a/drivers/gpu/drm/i915/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/intel_guc_ct.c
@@ -24,14 +24,49 @@
 #include "i915_drv.h"
 #include "intel_guc_ct.h"
 
+#ifdef CONFIG_DRM_I915_DEBUG_GUC
+#define CT_DEBUG_DRIVER(...)	DRM_DEBUG_DRIVER(__VA_ARGS__)
+#else
+#define CT_DEBUG_DRIVER(...)	do { } while (0)
+#endif
+
+struct ct_request {
+	struct list_head link;
+	u32 fence;
+	u32 status;
+	u32 response_len;
+	u32 *response_buf;
+};
+
+struct ct_incoming_request {
+	struct list_head link;
+	u32 msg[];
+};
+
 enum { CTB_SEND = 0, CTB_RECV = 1 };
 
 enum { CTB_OWNER_HOST = 0 };
 
+static void ct_incoming_request_worker_func(struct work_struct *w);
+
+/**
+ * intel_guc_ct_init_early - Initialize CT state without requiring device access
+ * @ct: pointer to CT struct
+ */
 void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 {
 	/* we're using static channel owners */
 	ct->host_channel.owner = CTB_OWNER_HOST;
+
+	spin_lock_init(&ct->lock);
+	INIT_LIST_HEAD(&ct->pending_requests);
+	INIT_LIST_HEAD(&ct->incoming_requests);
+	INIT_WORK(&ct->worker, ct_incoming_request_worker_func);
+}
+
+static inline struct intel_guc *ct_to_guc(struct intel_guc_ct *ct)
+{
+	return container_of(ct, struct intel_guc, ct);
 }
 
 static inline const char *guc_ct_buffer_type_to_str(u32 type)
@@ -49,8 +84,8 @@ static inline const char *guc_ct_buffer_type_to_str(u32 type)
 static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc,
 				    u32 cmds_addr, u32 size, u32 owner)
 {
-	DRM_DEBUG_DRIVER("CT: desc %p init addr=%#x size=%u owner=%u\n",
-			 desc, cmds_addr, size, owner);
+	CT_DEBUG_DRIVER("CT: desc %p init addr=%#x size=%u owner=%u\n",
+			desc, cmds_addr, size, owner);
 	memset(desc, 0, sizeof(*desc));
 	desc->addr = cmds_addr;
 	desc->size = size;
@@ -59,8 +94,8 @@ static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc,
 
 static void guc_ct_buffer_desc_reset(struct guc_ct_buffer_desc *desc)
 {
-	DRM_DEBUG_DRIVER("CT: desc %p reset head=%u tail=%u\n",
-			 desc, desc->head, desc->tail);
+	CT_DEBUG_DRIVER("CT: desc %p reset head=%u tail=%u\n",
+			desc, desc->head, desc->tail);
 	desc->head = 0;
 	desc->tail = 0;
 	desc->is_in_error = 0;
@@ -79,7 +114,7 @@ static int guc_action_register_ct_buffer(struct intel_guc *guc,
 	int err;
 
 	/* Can't use generic send(), CT registration must go over MMIO */
-	err = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action));
+	err = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
 	if (err)
 		DRM_ERROR("CT: register %s buffer failed; err=%d\n",
 			  guc_ct_buffer_type_to_str(type), err);
@@ -98,7 +133,7 @@ static int guc_action_deregister_ct_buffer(struct intel_guc *guc,
 	int err;
 
 	/* Can't use generic send(), CT deregistration must go over MMIO */
-	err = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action));
+	err = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
 	if (err)
 		DRM_ERROR("CT: deregister %s buffer failed; owner=%d err=%d\n",
 			  guc_ct_buffer_type_to_str(type), owner, err);
@@ -156,7 +191,8 @@ static int ctch_init(struct intel_guc *guc,
 		err = PTR_ERR(blob);
 		goto err_vma;
 	}
-	DRM_DEBUG_DRIVER("CT: vma base=%#x\n", guc_ggtt_offset(ctch->vma));
+	CT_DEBUG_DRIVER("CT: vma base=%#x\n",
+			intel_guc_ggtt_offset(guc, ctch->vma));
 
 	/* store pointers to desc and cmds */
 	for (i = 0; i < ARRAY_SIZE(ctch->ctbs); i++) {
@@ -170,8 +206,8 @@ static int ctch_init(struct intel_guc *guc,
 err_vma:
 	i915_vma_unpin_and_release(&ctch->vma);
 err_out:
-	DRM_DEBUG_DRIVER("CT: channel %d initialization failed; err=%d\n",
-			 ctch->owner, err);
+	CT_DEBUG_DRIVER("CT: channel %d initialization failed; err=%d\n",
+			ctch->owner, err);
 	return err;
 }
 
@@ -191,8 +227,8 @@ static int ctch_open(struct intel_guc *guc,
 	int err;
 	int i;
 
-	DRM_DEBUG_DRIVER("CT: channel %d reopen=%s\n",
-			 ctch->owner, yesno(ctch_is_open(ctch)));
+	CT_DEBUG_DRIVER("CT: channel %d reopen=%s\n",
+			ctch->owner, yesno(ctch_is_open(ctch)));
 
 	if (!ctch->vma) {
 		err = ctch_init(guc, ctch);
@@ -202,7 +238,7 @@ static int ctch_open(struct intel_guc *guc,
 	}
 
 	/* vma should be already allocated and map'ed */
-	base = guc_ggtt_offset(ctch->vma);
+	base = intel_guc_ggtt_offset(guc, ctch->vma);
 
 	/* (re)initialize descriptors
 	 * cmds buffers are in the second half of the blob page
@@ -263,10 +299,29 @@ static u32 ctch_get_next_fence(struct intel_guc_ct_channel *ctch)
 	return ++ctch->next_fence;
 }
 
+/**
+ * DOC: CTB Host to GuC request
+ *
+ * Format of the CTB Host to GuC request message is as follows::
+ *
+ *      +------------+---------+---------+---------+---------+
+ *      |   msg[0]   |   [1]   |   [2]   |   ...   |  [n-1]  |
+ *      +------------+---------+---------+---------+---------+
+ *      |   MESSAGE  |       MESSAGE PAYLOAD                 |
+ *      +   HEADER   +---------+---------+---------+---------+
+ *      |            |    0    |    1    |   ...   |    n    |
+ *      +============+=========+=========+=========+=========+
+ *      |  len >= 1  |  FENCE  |     request specific data   |
+ *      +------+-----+---------+---------+---------+---------+
+ *
+ *                   ^-----------------len-------------------^
+ */
+
 static int ctb_write(struct intel_guc_ct_buffer *ctb,
 		     const u32 *action,
 		     u32 len /* in dwords */,
-		     u32 fence)
+		     u32 fence,
+		     bool want_response)
 {
 	struct guc_ct_buffer_desc *desc = ctb->desc;
 	u32 head = desc->head / 4;	/* in dwords */
@@ -295,15 +350,21 @@ static int ctb_write(struct intel_guc_ct_buffer *ctb,
 	if (unlikely(used + len + 1 >= size))
 		return -ENOSPC;
 
-	/* Write the message. The format is the following:
+	/*
+	 * Write the message. The format is the following:
 	 * DW0: header (including action code)
 	 * DW1: fence
 	 * DW2+: action data
 	 */
 	header = (len << GUC_CT_MSG_LEN_SHIFT) |
 		 (GUC_CT_MSG_WRITE_FENCE_TO_DESC) |
+		 (want_response ? GUC_CT_MSG_SEND_STATUS : 0) |
 		 (action[0] << GUC_CT_MSG_ACTION_SHIFT);
 
+	CT_DEBUG_DRIVER("CT: writing %*ph %*ph %*ph\n",
+			4, &header, 4, &fence,
+			4 * (len - 1), &action[1]);
+
 	cmds[tail] = header;
 	tail = (tail + 1) % size;
 
@@ -322,16 +383,25 @@ static int ctb_write(struct intel_guc_ct_buffer *ctb,
 	return 0;
 }
 
-/* Wait for the response from the GuC.
+/**
+ * wait_for_ctb_desc_update - Wait for the CT buffer descriptor update.
+ * @desc:	buffer descriptor
  * @fence:	response fence
  * @status:	placeholder for status
- * return:	0 response received (status is valid)
- *		-ETIMEDOUT no response within hardcoded timeout
- *		-EPROTO no response, ct buffer was in error
+ *
+ * Guc will update CT buffer descriptor with new fence and status
+ * after processing the command identified by the fence. Wait for
+ * specified fence and then read from the descriptor status of the
+ * command.
+ *
+ * Return:
+ * *	0 response received (status is valid)
+ * *	-ETIMEDOUT no response within hardcoded timeout
+ * *	-EPROTO no response, CT buffer is in error
  */
-static int wait_for_response(struct guc_ct_buffer_desc *desc,
-			     u32 fence,
-			     u32 *status)
+static int wait_for_ctb_desc_update(struct guc_ct_buffer_desc *desc,
+				    u32 fence,
+				    u32 *status)
 {
 	int err;
 
@@ -363,71 +433,440 @@ static int wait_for_response(struct guc_ct_buffer_desc *desc,
 	return err;
 }
 
-static int ctch_send(struct intel_guc *guc,
+/**
+ * wait_for_ct_request_update - Wait for CT request state update.
+ * @req:	pointer to pending request
+ * @status:	placeholder for status
+ *
+ * For each sent request, Guc shall send bac CT response message.
+ * Our message handler will update status of tracked request once
+ * response message with given fence is received. Wait here and
+ * check for valid response status value.
+ *
+ * Return:
+ * *	0 response received (status is valid)
+ * *	-ETIMEDOUT no response within hardcoded timeout
+ */
+static int wait_for_ct_request_update(struct ct_request *req, u32 *status)
+{
+	int err;
+
+	/*
+	 * Fast commands should complete in less than 10us, so sample quickly
+	 * up to that length of time, then switch to a slower sleep-wait loop.
+	 * No GuC command should ever take longer than 10ms.
+	 */
+#define done INTEL_GUC_MSG_IS_RESPONSE(READ_ONCE(req->status))
+	err = wait_for_us(done, 10);
+	if (err)
+		err = wait_for(done, 10);
+#undef done
+
+	if (unlikely(err))
+		DRM_ERROR("CT: fence %u err %d\n", req->fence, err);
+
+	*status = req->status;
+	return err;
+}
+
+static int ctch_send(struct intel_guc_ct *ct,
 		     struct intel_guc_ct_channel *ctch,
 		     const u32 *action,
 		     u32 len,
+		     u32 *response_buf,
+		     u32 response_buf_size,
 		     u32 *status)
 {
 	struct intel_guc_ct_buffer *ctb = &ctch->ctbs[CTB_SEND];
 	struct guc_ct_buffer_desc *desc = ctb->desc;
+	struct ct_request request;
+	unsigned long flags;
 	u32 fence;
 	int err;
 
 	GEM_BUG_ON(!ctch_is_open(ctch));
 	GEM_BUG_ON(!len);
 	GEM_BUG_ON(len & ~GUC_CT_MSG_LEN_MASK);
+	GEM_BUG_ON(!response_buf && response_buf_size);
 
 	fence = ctch_get_next_fence(ctch);
-	err = ctb_write(ctb, action, len, fence);
+	request.fence = fence;
+	request.status = 0;
+	request.response_len = response_buf_size;
+	request.response_buf = response_buf;
+
+	spin_lock_irqsave(&ct->lock, flags);
+	list_add_tail(&request.link, &ct->pending_requests);
+	spin_unlock_irqrestore(&ct->lock, flags);
+
+	err = ctb_write(ctb, action, len, fence, !!response_buf);
 	if (unlikely(err))
-		return err;
+		goto unlink;
 
-	intel_guc_notify(guc);
+	intel_guc_notify(ct_to_guc(ct));
 
-	err = wait_for_response(desc, fence, status);
+	if (response_buf)
+		err = wait_for_ct_request_update(&request, status);
+	else
+		err = wait_for_ctb_desc_update(desc, fence, status);
 	if (unlikely(err))
-		return err;
-	if (*status != INTEL_GUC_STATUS_SUCCESS)
-		return -EIO;
-	return 0;
+		goto unlink;
+
+	if (!INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(*status)) {
+		err = -EIO;
+		goto unlink;
+	}
+
+	if (response_buf) {
+		/* There shall be no data in the status */
+		WARN_ON(INTEL_GUC_MSG_TO_DATA(request.status));
+		/* Return actual response len */
+		err = request.response_len;
+	} else {
+		/* There shall be no response payload */
+		WARN_ON(request.response_len);
+		/* Return data decoded from the status dword */
+		err = INTEL_GUC_MSG_TO_DATA(*status);
+	}
+
+unlink:
+	spin_lock_irqsave(&ct->lock, flags);
+	list_del(&request.link);
+	spin_unlock_irqrestore(&ct->lock, flags);
+
+	return err;
 }
 
 /*
  * Command Transport (CT) buffer based GuC send function.
  */
-static int intel_guc_send_ct(struct intel_guc *guc, const u32 *action, u32 len)
+static int intel_guc_send_ct(struct intel_guc *guc, const u32 *action, u32 len,
+			     u32 *response_buf, u32 response_buf_size)
 {
-	struct intel_guc_ct_channel *ctch = &guc->ct.host_channel;
+	struct intel_guc_ct *ct = &guc->ct;
+	struct intel_guc_ct_channel *ctch = &ct->host_channel;
 	u32 status = ~0; /* undefined */
-	int err;
+	int ret;
 
 	mutex_lock(&guc->send_mutex);
 
-	err = ctch_send(guc, ctch, action, len, &status);
-	if (unlikely(err)) {
+	ret = ctch_send(ct, ctch, action, len, response_buf, response_buf_size,
+			&status);
+	if (unlikely(ret < 0)) {
 		DRM_ERROR("CT: send action %#X failed; err=%d status=%#X\n",
-			  action[0], err, status);
+			  action[0], ret, status);
+	} else if (unlikely(ret)) {
+		CT_DEBUG_DRIVER("CT: send action %#x returned %d (%#x)\n",
+				action[0], ret, ret);
 	}
 
 	mutex_unlock(&guc->send_mutex);
-	return err;
+	return ret;
+}
+
+static inline unsigned int ct_header_get_len(u32 header)
+{
+	return (header >> GUC_CT_MSG_LEN_SHIFT) & GUC_CT_MSG_LEN_MASK;
+}
+
+static inline unsigned int ct_header_get_action(u32 header)
+{
+	return (header >> GUC_CT_MSG_ACTION_SHIFT) & GUC_CT_MSG_ACTION_MASK;
+}
+
+static inline bool ct_header_is_response(u32 header)
+{
+	return ct_header_get_action(header) == INTEL_GUC_ACTION_DEFAULT;
+}
+
+static int ctb_read(struct intel_guc_ct_buffer *ctb, u32 *data)
+{
+	struct guc_ct_buffer_desc *desc = ctb->desc;
+	u32 head = desc->head / 4;	/* in dwords */
+	u32 tail = desc->tail / 4;	/* in dwords */
+	u32 size = desc->size / 4;	/* in dwords */
+	u32 *cmds = ctb->cmds;
+	s32 available;			/* in dwords */
+	unsigned int len;
+	unsigned int i;
+
+	GEM_BUG_ON(desc->size % 4);
+	GEM_BUG_ON(desc->head % 4);
+	GEM_BUG_ON(desc->tail % 4);
+	GEM_BUG_ON(tail >= size);
+	GEM_BUG_ON(head >= size);
+
+	/* tail == head condition indicates empty */
+	available = tail - head;
+	if (unlikely(available == 0))
+		return -ENODATA;
+
+	/* beware of buffer wrap case */
+	if (unlikely(available < 0))
+		available += size;
+	CT_DEBUG_DRIVER("CT: available %d (%u:%u)\n", available, head, tail);
+	GEM_BUG_ON(available < 0);
+
+	data[0] = cmds[head];
+	head = (head + 1) % size;
+
+	/* message len with header */
+	len = ct_header_get_len(data[0]) + 1;
+	if (unlikely(len > (u32)available)) {
+		DRM_ERROR("CT: incomplete message %*ph %*ph %*ph\n",
+			  4, data,
+			  4 * (head + available - 1 > size ?
+			       size - head : available - 1), &cmds[head],
+			  4 * (head + available - 1 > size ?
+			       available - 1 - size + head : 0), &cmds[0]);
+		return -EPROTO;
+	}
+
+	for (i = 1; i < len; i++) {
+		data[i] = cmds[head];
+		head = (head + 1) % size;
+	}
+	CT_DEBUG_DRIVER("CT: received %*ph\n", 4 * len, data);
+
+	desc->head = head * 4;
+	return 0;
 }
 
 /**
- * Enable buffer based command transport
+ * DOC: CTB GuC to Host response
+ *
+ * Format of the CTB GuC to Host response message is as follows::
+ *
+ *      +------------+---------+---------+---------+---------+---------+
+ *      |   msg[0]   |   [1]   |   [2]   |   [3]   |   ...   |  [n-1]  |
+ *      +------------+---------+---------+---------+---------+---------+
+ *      |   MESSAGE  |       MESSAGE PAYLOAD                           |
+ *      +   HEADER   +---------+---------+---------+---------+---------+
+ *      |            |    0    |    1    |    2    |   ...   |    n    |
+ *      +============+=========+=========+=========+=========+=========+
+ *      |  len >= 2  |  FENCE  |  STATUS |   response specific data    |
+ *      +------+-----+---------+---------+---------+---------+---------+
+ *
+ *                   ^-----------------------len-----------------------^
+ */
+
+static int ct_handle_response(struct intel_guc_ct *ct, const u32 *msg)
+{
+	u32 header = msg[0];
+	u32 len = ct_header_get_len(header);
+	u32 msglen = len + 1; /* total message length including header */
+	u32 fence;
+	u32 status;
+	u32 datalen;
+	struct ct_request *req;
+	bool found = false;
+
+	GEM_BUG_ON(!ct_header_is_response(header));
+	GEM_BUG_ON(!in_irq());
+
+	/* Response payload shall at least include fence and status */
+	if (unlikely(len < 2)) {
+		DRM_ERROR("CT: corrupted response %*ph\n", 4 * msglen, msg);
+		return -EPROTO;
+	}
+
+	fence = msg[1];
+	status = msg[2];
+	datalen = len - 2;
+
+	/* Format of the status follows RESPONSE message */
+	if (unlikely(!INTEL_GUC_MSG_IS_RESPONSE(status))) {
+		DRM_ERROR("CT: corrupted response %*ph\n", 4 * msglen, msg);
+		return -EPROTO;
+	}
+
+	CT_DEBUG_DRIVER("CT: response fence %u status %#x\n", fence, status);
+
+	spin_lock(&ct->lock);
+	list_for_each_entry(req, &ct->pending_requests, link) {
+		if (unlikely(fence != req->fence)) {
+			CT_DEBUG_DRIVER("CT: request %u awaits response\n",
+					req->fence);
+			continue;
+		}
+		if (unlikely(datalen > req->response_len)) {
+			DRM_ERROR("CT: response %u too long %*ph\n",
+				  req->fence, 4 * msglen, msg);
+			datalen = 0;
+		}
+		if (datalen)
+			memcpy(req->response_buf, msg + 3, 4 * datalen);
+		req->response_len = datalen;
+		WRITE_ONCE(req->status, status);
+		found = true;
+		break;
+	}
+	spin_unlock(&ct->lock);
+
+	if (!found)
+		DRM_ERROR("CT: unsolicited response %*ph\n", 4 * msglen, msg);
+	return 0;
+}
+
+static void ct_process_request(struct intel_guc_ct *ct,
+			       u32 action, u32 len, const u32 *payload)
+{
+	struct intel_guc *guc = ct_to_guc(ct);
+
+	CT_DEBUG_DRIVER("CT: request %x %*ph\n", action, 4 * len, payload);
+
+	switch (action) {
+	case INTEL_GUC_ACTION_DEFAULT:
+		if (unlikely(len < 1))
+			goto fail_unexpected;
+		intel_guc_to_host_process_recv_msg(guc, *payload);
+		break;
+
+	default:
+fail_unexpected:
+		DRM_ERROR("CT: unexpected request %x %*ph\n",
+			  action, 4 * len, payload);
+		break;
+	}
+}
+
+static bool ct_process_incoming_requests(struct intel_guc_ct *ct)
+{
+	unsigned long flags;
+	struct ct_incoming_request *request;
+	u32 header;
+	u32 *payload;
+	bool done;
+
+	spin_lock_irqsave(&ct->lock, flags);
+	request = list_first_entry_or_null(&ct->incoming_requests,
+					   struct ct_incoming_request, link);
+	if (request)
+		list_del(&request->link);
+	done = !!list_empty(&ct->incoming_requests);
+	spin_unlock_irqrestore(&ct->lock, flags);
+
+	if (!request)
+		return true;
+
+	header = request->msg[0];
+	payload = &request->msg[1];
+	ct_process_request(ct,
+			   ct_header_get_action(header),
+			   ct_header_get_len(header),
+			   payload);
+
+	kfree(request);
+	return done;
+}
+
+static void ct_incoming_request_worker_func(struct work_struct *w)
+{
+	struct intel_guc_ct *ct = container_of(w, struct intel_guc_ct, worker);
+	bool done;
+
+	done = ct_process_incoming_requests(ct);
+	if (!done)
+		queue_work(system_unbound_wq, &ct->worker);
+}
+
+/**
+ * DOC: CTB GuC to Host request
+ *
+ * Format of the CTB GuC to Host request message is as follows::
+ *
+ *      +------------+---------+---------+---------+---------+---------+
+ *      |   msg[0]   |   [1]   |   [2]   |   [3]   |   ...   |  [n-1]  |
+ *      +------------+---------+---------+---------+---------+---------+
+ *      |   MESSAGE  |       MESSAGE PAYLOAD                           |
+ *      +   HEADER   +---------+---------+---------+---------+---------+
+ *      |            |    0    |    1    |    2    |   ...   |    n    |
+ *      +============+=========+=========+=========+=========+=========+
+ *      |     len    |            request specific data                |
+ *      +------+-----+---------+---------+---------+---------+---------+
+ *
+ *                   ^-----------------------len-----------------------^
+ */
+
+static int ct_handle_request(struct intel_guc_ct *ct, const u32 *msg)
+{
+	u32 header = msg[0];
+	u32 len = ct_header_get_len(header);
+	u32 msglen = len + 1; /* total message length including header */
+	struct ct_incoming_request *request;
+	unsigned long flags;
+
+	GEM_BUG_ON(ct_header_is_response(header));
+
+	request = kmalloc(sizeof(*request) + 4 * msglen, GFP_ATOMIC);
+	if (unlikely(!request)) {
+		DRM_ERROR("CT: dropping request %*ph\n", 4 * msglen, msg);
+		return 0; /* XXX: -ENOMEM ? */
+	}
+	memcpy(request->msg, msg, 4 * msglen);
+
+	spin_lock_irqsave(&ct->lock, flags);
+	list_add_tail(&request->link, &ct->incoming_requests);
+	spin_unlock_irqrestore(&ct->lock, flags);
+
+	queue_work(system_unbound_wq, &ct->worker);
+	return 0;
+}
+
+static void ct_process_host_channel(struct intel_guc_ct *ct)
+{
+	struct intel_guc_ct_channel *ctch = &ct->host_channel;
+	struct intel_guc_ct_buffer *ctb = &ctch->ctbs[CTB_RECV];
+	u32 msg[GUC_CT_MSG_LEN_MASK + 1]; /* one extra dw for the header */
+	int err = 0;
+
+	if (!ctch_is_open(ctch))
+		return;
+
+	do {
+		err = ctb_read(ctb, msg);
+		if (err)
+			break;
+
+		if (ct_header_is_response(msg[0]))
+			err = ct_handle_response(ct, msg);
+		else
+			err = ct_handle_request(ct, msg);
+	} while (!err);
+
+	if (GEM_WARN_ON(err == -EPROTO)) {
+		DRM_ERROR("CT: corrupted message detected!\n");
+		ctb->desc->is_in_error = 1;
+	}
+}
+
+/*
+ * When we're communicating with the GuC over CT, GuC uses events
+ * to notify us about new messages being posted on the RECV buffer.
+ */
+static void intel_guc_to_host_event_handler_ct(struct intel_guc *guc)
+{
+	struct intel_guc_ct *ct = &guc->ct;
+
+	ct_process_host_channel(ct);
+}
+
+/**
+ * intel_guc_ct_enable - Enable buffer based command transport.
+ * @ct: pointer to CT struct
+ *
  * Shall only be called for platforms with HAS_GUC_CT.
- * @guc:	the guc
- * return:	0 on success
- *		non-zero on failure
+ *
+ * Return: 0 on success, a negative errno code on failure.
  */
-int intel_guc_enable_ct(struct intel_guc *guc)
+int intel_guc_ct_enable(struct intel_guc_ct *ct)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct intel_guc_ct_channel *ctch = &guc->ct.host_channel;
+	struct intel_guc *guc = ct_to_guc(ct);
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+	struct intel_guc_ct_channel *ctch = &ct->host_channel;
 	int err;
 
-	GEM_BUG_ON(!HAS_GUC_CT(dev_priv));
+	GEM_BUG_ON(!HAS_GUC_CT(i915));
 
 	err = ctch_open(guc, ctch);
 	if (unlikely(err))
@@ -435,21 +874,24 @@ int intel_guc_enable_ct(struct intel_guc *guc)
 
 	/* Switch into cmd transport buffer based send() */
 	guc->send = intel_guc_send_ct;
+	guc->handler = intel_guc_to_host_event_handler_ct;
 	DRM_INFO("CT: %s\n", enableddisabled(true));
 	return 0;
 }
 
 /**
- * Disable buffer based command transport.
+ * intel_guc_ct_disable - Disable buffer based command transport.
+ * @ct: pointer to CT struct
+ *
  * Shall only be called for platforms with HAS_GUC_CT.
- * @guc: the guc
  */
-void intel_guc_disable_ct(struct intel_guc *guc)
+void intel_guc_ct_disable(struct intel_guc_ct *ct)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct intel_guc_ct_channel *ctch = &guc->ct.host_channel;
+	struct intel_guc *guc = ct_to_guc(ct);
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+	struct intel_guc_ct_channel *ctch = &ct->host_channel;
 
-	GEM_BUG_ON(!HAS_GUC_CT(dev_priv));
+	GEM_BUG_ON(!HAS_GUC_CT(i915));
 
 	if (!ctch_is_open(ctch))
 		return;
@@ -458,5 +900,6 @@ void intel_guc_disable_ct(struct intel_guc *guc)
 
 	/* Disable send */
 	guc->send = intel_guc_send_nop;
+	guc->handler = intel_guc_to_host_event_handler_nop;
 	DRM_INFO("CT: %s\n", enableddisabled(false));
 }
diff --git a/drivers/gpu/drm/i915/intel_guc_ct.h b/drivers/gpu/drm/i915/intel_guc_ct.h
index 6d97f36fcc62..d774895ab143 100644
--- a/drivers/gpu/drm/i915/intel_guc_ct.h
+++ b/drivers/gpu/drm/i915/intel_guc_ct.h
@@ -75,12 +75,22 @@ struct intel_guc_ct_channel {
 struct intel_guc_ct {
 	struct intel_guc_ct_channel host_channel;
 	/* other channels are tbd */
+
+	/** @lock: protects pending requests list */
+	spinlock_t lock;
+
+	/** @pending_requests: list of requests waiting for response */
+	struct list_head pending_requests;
+
+	/** @incoming_requests: list of incoming requests */
+	struct list_head incoming_requests;
+
+	/** @worker: worker for handling incoming requests */
+	struct work_struct worker;
 };
 
 void intel_guc_ct_init_early(struct intel_guc_ct *ct);
-
-/* XXX: move to intel_uc.h ? don't fit there either */
-int intel_guc_enable_ct(struct intel_guc *guc);
-void intel_guc_disable_ct(struct intel_guc *guc);
+int intel_guc_ct_enable(struct intel_guc_ct *ct);
+void intel_guc_ct_disable(struct intel_guc_ct *ct);
 
 #endif /* _INTEL_GUC_CT_H_ */
diff --git a/drivers/gpu/drm/i915/intel_guc_fw.c b/drivers/gpu/drm/i915/intel_guc_fw.c
index d07f2b985f1c..a9e6fcce467c 100644
--- a/drivers/gpu/drm/i915/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/intel_guc_fw.c
@@ -165,7 +165,7 @@ static int guc_xfer_ucode(struct intel_guc *guc, struct i915_vma *vma)
 	I915_WRITE(DMA_COPY_SIZE, guc_fw->header_size + guc_fw->ucode_size);
 
 	/* Set the source address for the new blob */
-	offset = guc_ggtt_offset(vma) + guc_fw->header_offset;
+	offset = intel_guc_ggtt_offset(guc, vma) + guc_fw->header_offset;
 	I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset));
 	I915_WRITE(DMA_ADDR_0_HIGH, upper_32_bits(offset) & 0xFFFF);
 
@@ -275,9 +275,8 @@ static int guc_fw_xfer(struct intel_uc_fw *guc_fw, struct i915_vma *vma)
  * Called from intel_uc_init_hw() during driver load, resume from sleep and
  * after a GPU reset.
  *
- * The firmware image should have already been fetched into memory by the
- * earlier call to intel_uc_init_fw(), so here we need to only check that
- * fetch succeeded, and then transfer the image to the h/w.
+ * The firmware image should have already been fetched into memory, so only
+ * check that fetch succeeded, and then transfer the image to the h/w.
  *
  * Return:	non-zero code on error
  */
diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h
index 6a10aa6f04d3..0867ba76d445 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -23,9 +23,6 @@
 #ifndef _INTEL_GUC_FWIF_H
 #define _INTEL_GUC_FWIF_H
 
-#define GUC_CORE_FAMILY_GEN9		12
-#define GUC_CORE_FAMILY_UNKNOWN		0x7fffffff
-
 #define GUC_CLIENT_PRIORITY_KMD_HIGH	0
 #define GUC_CLIENT_PRIORITY_HIGH	1
 #define GUC_CLIENT_PRIORITY_KMD_NORMAL	2
@@ -82,8 +79,6 @@
 #define GUC_CTL_ARAT_LOW		2
 
 #define GUC_CTL_DEVICE_INFO		3
-#define   GUC_CTL_GT_TYPE_SHIFT		0
-#define   GUC_CTL_CORE_FAMILY_SHIFT	7
 
 #define GUC_CTL_LOG_PARAMS		4
 #define   GUC_LOG_VALID			(1 << 0)
@@ -127,7 +122,7 @@
 #define   GUC_PROFILE_ENABLED		(1 << 7)
 #define   GUC_WQ_TRACK_ENABLED		(1 << 8)
 #define   GUC_ADS_ENABLED		(1 << 9)
-#define   GUC_DEBUG_RESERVED		(1 << 10)
+#define   GUC_LOG_DEFAULT_DISABLED	(1 << 10)
 #define   GUC_ADS_ADDR_SHIFT		11
 #define   GUC_ADS_ADDR_MASK		0xfffff800
 
@@ -327,6 +322,58 @@ struct guc_stage_desc {
 	u64 desc_private;
 } __packed;
 
+/**
+ * DOC: CTB based communication
+ *
+ * The CTB (command transport buffer) communication between Host and GuC
+ * is based on u32 data stream written to the shared buffer. One buffer can
+ * be used to transmit data only in one direction (one-directional channel).
+ *
+ * Current status of the each buffer is stored in the buffer descriptor.
+ * Buffer descriptor holds tail and head fields that represents active data
+ * stream. The tail field is updated by the data producer (sender), and head
+ * field is updated by the data consumer (receiver)::
+ *
+ *      +------------+
+ *      | DESCRIPTOR |          +=================+============+========+
+ *      +============+          |                 | MESSAGE(s) |        |
+ *      | address    |--------->+=================+============+========+
+ *      +------------+
+ *      | head       |          ^-----head--------^
+ *      +------------+
+ *      | tail       |          ^---------tail-----------------^
+ *      +------------+
+ *      | size       |          ^---------------size--------------------^
+ *      +------------+
+ *
+ * Each message in data stream starts with the single u32 treated as a header,
+ * followed by optional set of u32 data that makes message specific payload::
+ *
+ *      +------------+---------+---------+---------+
+ *      |         MESSAGE                          |
+ *      +------------+---------+---------+---------+
+ *      |   msg[0]   |   [1]   |   ...   |  [n-1]  |
+ *      +------------+---------+---------+---------+
+ *      |   MESSAGE  |       MESSAGE PAYLOAD       |
+ *      +   HEADER   +---------+---------+---------+
+ *      |            |    0    |   ...   |    n    |
+ *      +======+=====+=========+=========+=========+
+ *      | 31:16| code|         |         |         |
+ *      +------+-----+         |         |         |
+ *      |  15:5|flags|         |         |         |
+ *      +------+-----+         |         |         |
+ *      |   4:0|  len|         |         |         |
+ *      +------+-----+---------+---------+---------+
+ *
+ *                   ^-------------len-------------^
+ *
+ * The message header consists of:
+ *
+ * - **len**, indicates length of the message payload (in u32)
+ * - **code**, indicates message code
+ * - **flags**, holds various bits to control message handling
+ */
+
 /*
  * Describes single command transport buffer.
  * Used by both guc-master and clients.
@@ -534,16 +581,6 @@ struct guc_log_buffer_state {
 	u32 version;
 } __packed;
 
-union guc_log_control {
-	struct {
-		u32 logging_enabled:1;
-		u32 reserved1:3;
-		u32 verbosity:4;
-		u32 reserved2:24;
-	};
-	u32 value;
-} __packed;
-
 struct guc_ctx_report {
 	u32 report_return_status;
 	u32 reserved1[64];
@@ -570,7 +607,68 @@ struct guc_shared_ctx_data {
 	struct guc_ctx_report preempt_ctx_report[GUC_MAX_ENGINES_NUM];
 } __packed;
 
-/* This Action will be programmed in C180 - SOFT_SCRATCH_O_REG */
+/**
+ * DOC: MMIO based communication
+ *
+ * The MMIO based communication between Host and GuC uses software scratch
+ * registers, where first register holds data treated as message header,
+ * and other registers are used to hold message payload.
+ *
+ * For Gen9+, GuC uses software scratch registers 0xC180-0xC1B8
+ *
+ *      +-----------+---------+---------+---------+
+ *      |  MMIO[0]  | MMIO[1] |   ...   | MMIO[n] |
+ *      +-----------+---------+---------+---------+
+ *      | header    |      optional payload       |
+ *      +======+====+=========+=========+=========+
+ *      | 31:28|type|         |         |         |
+ *      +------+----+         |         |         |
+ *      | 27:16|data|         |         |         |
+ *      +------+----+         |         |         |
+ *      |  15:0|code|         |         |         |
+ *      +------+----+---------+---------+---------+
+ *
+ * The message header consists of:
+ *
+ * - **type**, indicates message type
+ * - **code**, indicates message code, is specific for **type**
+ * - **data**, indicates message data, optional, depends on **code**
+ *
+ * The following message **types** are supported:
+ *
+ * - **REQUEST**, indicates Host-to-GuC request, requested GuC action code
+ *   must be priovided in **code** field. Optional action specific parameters
+ *   can be provided in remaining payload registers or **data** field.
+ *
+ * - **RESPONSE**, indicates GuC-to-Host response from earlier GuC request,
+ *   action response status will be provided in **code** field. Optional
+ *   response data can be returned in remaining payload registers or **data**
+ *   field.
+ */
+
+#define INTEL_GUC_MSG_TYPE_SHIFT	28
+#define INTEL_GUC_MSG_TYPE_MASK		(0xF << INTEL_GUC_MSG_TYPE_SHIFT)
+#define INTEL_GUC_MSG_DATA_SHIFT	16
+#define INTEL_GUC_MSG_DATA_MASK		(0xFFF << INTEL_GUC_MSG_DATA_SHIFT)
+#define INTEL_GUC_MSG_CODE_SHIFT	0
+#define INTEL_GUC_MSG_CODE_MASK		(0xFFFF << INTEL_GUC_MSG_CODE_SHIFT)
+
+#define __INTEL_GUC_MSG_GET(T, m) \
+	(((m) & INTEL_GUC_MSG_ ## T ## _MASK) >> INTEL_GUC_MSG_ ## T ## _SHIFT)
+#define INTEL_GUC_MSG_TO_TYPE(m)	__INTEL_GUC_MSG_GET(TYPE, m)
+#define INTEL_GUC_MSG_TO_DATA(m)	__INTEL_GUC_MSG_GET(DATA, m)
+#define INTEL_GUC_MSG_TO_CODE(m)	__INTEL_GUC_MSG_GET(CODE, m)
+
+enum intel_guc_msg_type {
+	INTEL_GUC_MSG_TYPE_REQUEST = 0x0,
+	INTEL_GUC_MSG_TYPE_RESPONSE = 0xF,
+};
+
+#define __INTEL_GUC_MSG_TYPE_IS(T, m) \
+	(INTEL_GUC_MSG_TO_TYPE(m) == INTEL_GUC_MSG_TYPE_ ## T)
+#define INTEL_GUC_MSG_IS_REQUEST(m)	__INTEL_GUC_MSG_TYPE_IS(REQUEST, m)
+#define INTEL_GUC_MSG_IS_RESPONSE(m)	__INTEL_GUC_MSG_TYPE_IS(RESPONSE, m)
+
 enum intel_guc_action {
 	INTEL_GUC_ACTION_DEFAULT = 0x0,
 	INTEL_GUC_ACTION_REQUEST_PREEMPTION = 0x2,
@@ -602,24 +700,22 @@ enum intel_guc_report_status {
 	INTEL_GUC_REPORT_STATUS_COMPLETE = 0x4,
 };
 
-/*
- * The GuC sends its response to a command by overwriting the
- * command in SS0. The response is distinguishable from a command
- * by the fact that all the MASK bits are set. The remaining bits
- * give more detail.
- */
-#define	INTEL_GUC_RECV_MASK	((u32)0xF0000000)
-#define	INTEL_GUC_RECV_IS_RESPONSE(x)	((u32)(x) >= INTEL_GUC_RECV_MASK)
-#define	INTEL_GUC_RECV_STATUS(x)	(INTEL_GUC_RECV_MASK | (x))
-
-/* GUC will return status back to SOFT_SCRATCH_O_REG */
-enum intel_guc_status {
-	INTEL_GUC_STATUS_SUCCESS = INTEL_GUC_RECV_STATUS(0x0),
-	INTEL_GUC_STATUS_ALLOCATE_DOORBELL_FAIL = INTEL_GUC_RECV_STATUS(0x10),
-	INTEL_GUC_STATUS_DEALLOCATE_DOORBELL_FAIL = INTEL_GUC_RECV_STATUS(0x20),
-	INTEL_GUC_STATUS_GENERIC_FAIL = INTEL_GUC_RECV_STATUS(0x0000F000)
+#define GUC_LOG_CONTROL_LOGGING_ENABLED	(1 << 0)
+#define GUC_LOG_CONTROL_VERBOSITY_SHIFT	4
+#define GUC_LOG_CONTROL_VERBOSITY_MASK	(0xF << GUC_LOG_CONTROL_VERBOSITY_SHIFT)
+#define GUC_LOG_CONTROL_DEFAULT_LOGGING	(1 << 8)
+
+enum intel_guc_response_status {
+	INTEL_GUC_RESPONSE_STATUS_SUCCESS = 0x0,
+	INTEL_GUC_RESPONSE_STATUS_GENERIC_FAIL = 0xF000,
 };
 
+#define INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(m) \
+	 (typecheck(u32, (m)) && \
+	  ((m) & (INTEL_GUC_MSG_TYPE_MASK | INTEL_GUC_MSG_CODE_MASK)) == \
+	  ((INTEL_GUC_MSG_TYPE_RESPONSE << INTEL_GUC_MSG_TYPE_SHIFT) | \
+	   (INTEL_GUC_RESPONSE_STATUS_SUCCESS << INTEL_GUC_MSG_CODE_SHIFT)))
+
 /* This action will be programmed in C1BC - SOFT_SCRATCH_15_REG */
 enum intel_guc_recv_message {
 	INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED = BIT(1),
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index c0c2e7d1c7d7..401e1704d61e 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -23,12 +23,11 @@
  */
 
 #include <linux/debugfs.h>
-#include <linux/relay.h>
 
 #include "intel_guc_log.h"
 #include "i915_drv.h"
 
-static void guc_log_capture_logs(struct intel_guc *guc);
+static void guc_log_capture_logs(struct intel_guc_log *log);
 
 /**
  * DOC: GuC firmware log
@@ -39,7 +38,7 @@ static void guc_log_capture_logs(struct intel_guc *guc);
  * registers value.
  */
 
-static int guc_log_flush_complete(struct intel_guc *guc)
+static int guc_action_flush_log_complete(struct intel_guc *guc)
 {
 	u32 action[] = {
 		INTEL_GUC_ACTION_LOG_BUFFER_FILE_FLUSH_COMPLETE
@@ -48,7 +47,7 @@ static int guc_log_flush_complete(struct intel_guc *guc)
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
-static int guc_log_flush(struct intel_guc *guc)
+static int guc_action_flush_log(struct intel_guc *guc)
 {
 	u32 action[] = {
 		INTEL_GUC_ACTION_FORCE_LOG_BUFFER_FLUSH,
@@ -58,22 +57,40 @@ static int guc_log_flush(struct intel_guc *guc)
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
-static int guc_log_control(struct intel_guc *guc, bool enable, u32 verbosity)
+static int guc_action_control_log(struct intel_guc *guc, bool enable,
+				  bool default_logging, u32 verbosity)
 {
-	union guc_log_control control_val = {
-		{
-			.logging_enabled = enable,
-			.verbosity = verbosity,
-		},
-	};
 	u32 action[] = {
 		INTEL_GUC_ACTION_UK_LOG_ENABLE_LOGGING,
-		control_val.value
+		(enable ? GUC_LOG_CONTROL_LOGGING_ENABLED : 0) |
+		(verbosity << GUC_LOG_CONTROL_VERBOSITY_SHIFT) |
+		(default_logging ? GUC_LOG_CONTROL_DEFAULT_LOGGING : 0)
 	};
 
+	GEM_BUG_ON(verbosity > GUC_LOG_VERBOSITY_MAX);
+
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
+static inline struct intel_guc *log_to_guc(struct intel_guc_log *log)
+{
+	return container_of(log, struct intel_guc, log);
+}
+
+static void guc_log_enable_flush_events(struct intel_guc_log *log)
+{
+	intel_guc_enable_msg(log_to_guc(log),
+			     INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER |
+			     INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED);
+}
+
+static void guc_log_disable_flush_events(struct intel_guc_log *log)
+{
+	intel_guc_disable_msg(log_to_guc(log),
+			      INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER |
+			      INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED);
+}
+
 /*
  * Sub buffer switch callback. Called whenever relay has to switch to a new
  * sub buffer, relay stays on the same sub buffer if 0 is returned.
@@ -121,14 +138,7 @@ static struct dentry *create_buf_file_callback(const char *filename,
 	if (!parent)
 		return NULL;
 
-	/*
-	 * Not using the channel filename passed as an argument, since for each
-	 * channel relay appends the corresponding CPU number to the filename
-	 * passed in relay_open(). This should be fine as relay just needs a
-	 * dentry of the file associated with the channel buffer and that file's
-	 * name need not be same as the filename passed as an argument.
-	 */
-	buf_file = debugfs_create_file("guc_log", mode,
+	buf_file = debugfs_create_file(filename, mode,
 				       parent, buf, &relay_file_operations);
 	return buf_file;
 }
@@ -149,59 +159,7 @@ static struct rchan_callbacks relay_callbacks = {
 	.remove_buf_file = remove_buf_file_callback,
 };
 
-static int guc_log_relay_file_create(struct intel_guc *guc)
-{
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct dentry *log_dir;
-	int ret;
-
-	if (!i915_modparams.guc_log_level)
-		return 0;
-
-	mutex_lock(&guc->log.runtime.relay_lock);
-
-	/* For now create the log file in /sys/kernel/debug/dri/0 dir */
-	log_dir = dev_priv->drm.primary->debugfs_root;
-
-	/*
-	 * If /sys/kernel/debug/dri/0 location do not exist, then debugfs is
-	 * not mounted and so can't create the relay file.
-	 * The relay API seems to fit well with debugfs only, for availing relay
-	 * there are 3 requirements which can be met for debugfs file only in a
-	 * straightforward/clean manner :-
-	 * i)   Need the associated dentry pointer of the file, while opening the
-	 *      relay channel.
-	 * ii)  Should be able to use 'relay_file_operations' fops for the file.
-	 * iii) Set the 'i_private' field of file's inode to the pointer of
-	 *	relay channel buffer.
-	 */
-	if (!log_dir) {
-		DRM_ERROR("Debugfs dir not available yet for GuC log file\n");
-		ret = -ENODEV;
-		goto out_unlock;
-	}
-
-	ret = relay_late_setup_files(guc->log.runtime.relay_chan, "guc_log", log_dir);
-	if (ret < 0 && ret != -EEXIST) {
-		DRM_ERROR("Couldn't associate relay chan with file %d\n", ret);
-		goto out_unlock;
-	}
-
-	ret = 0;
-
-out_unlock:
-	mutex_unlock(&guc->log.runtime.relay_lock);
-	return ret;
-}
-
-static bool guc_log_has_relay(struct intel_guc *guc)
-{
-	lockdep_assert_held(&guc->log.runtime.relay_lock);
-
-	return guc->log.runtime.relay_chan != NULL;
-}
-
-static void guc_move_to_next_buf(struct intel_guc *guc)
+static void guc_move_to_next_buf(struct intel_guc_log *log)
 {
 	/*
 	 * Make sure the updates made in the sub buffer are visible when
@@ -209,21 +167,15 @@ static void guc_move_to_next_buf(struct intel_guc *guc)
 	 */
 	smp_wmb();
 
-	if (!guc_log_has_relay(guc))
-		return;
-
 	/* All data has been written, so now move the offset of sub buffer. */
-	relay_reserve(guc->log.runtime.relay_chan, guc->log.vma->obj->base.size);
+	relay_reserve(log->relay.channel, log->vma->obj->base.size);
 
 	/* Switch to the next sub buffer */
-	relay_flush(guc->log.runtime.relay_chan);
+	relay_flush(log->relay.channel);
 }
 
-static void *guc_get_write_buffer(struct intel_guc *guc)
+static void *guc_get_write_buffer(struct intel_guc_log *log)
 {
-	if (!guc_log_has_relay(guc))
-		return NULL;
-
 	/*
 	 * Just get the base address of a new sub buffer and copy data into it
 	 * ourselves. NULL will be returned in no-overwrite mode, if all sub
@@ -233,25 +185,25 @@ static void *guc_get_write_buffer(struct intel_guc *guc)
 	 * done without using relay_reserve() along with relay_write(). So its
 	 * better to use relay_reserve() alone.
 	 */
-	return relay_reserve(guc->log.runtime.relay_chan, 0);
+	return relay_reserve(log->relay.channel, 0);
 }
 
-static bool guc_check_log_buf_overflow(struct intel_guc *guc,
+static bool guc_check_log_buf_overflow(struct intel_guc_log *log,
 				       enum guc_log_buffer_type type,
 				       unsigned int full_cnt)
 {
-	unsigned int prev_full_cnt = guc->log.prev_overflow_count[type];
+	unsigned int prev_full_cnt = log->stats[type].sampled_overflow;
 	bool overflow = false;
 
 	if (full_cnt != prev_full_cnt) {
 		overflow = true;
 
-		guc->log.prev_overflow_count[type] = full_cnt;
-		guc->log.total_overflow_count[type] += full_cnt - prev_full_cnt;
+		log->stats[type].overflow = full_cnt;
+		log->stats[type].sampled_overflow += full_cnt - prev_full_cnt;
 
 		if (full_cnt < prev_full_cnt) {
 			/* buffer_full_cnt is a 4 bit counter */
-			guc->log.total_overflow_count[type] += 16;
+			log->stats[type].sampled_overflow += 16;
 		}
 		DRM_ERROR_RATELIMITED("GuC log buffer overflow\n");
 	}
@@ -275,7 +227,7 @@ static unsigned int guc_get_log_buffer_size(enum guc_log_buffer_type type)
 	return 0;
 }
 
-static void guc_read_update_log_buffer(struct intel_guc *guc)
+static void guc_read_update_log_buffer(struct intel_guc_log *log)
 {
 	unsigned int buffer_size, read_offset, write_offset, bytes_to_copy, full_cnt;
 	struct guc_log_buffer_state *log_buf_state, *log_buf_snapshot_state;
@@ -284,16 +236,16 @@ static void guc_read_update_log_buffer(struct intel_guc *guc)
 	void *src_data, *dst_data;
 	bool new_overflow;
 
-	if (WARN_ON(!guc->log.runtime.buf_addr))
-		return;
+	mutex_lock(&log->relay.lock);
 
-	/* Get the pointer to shared GuC log buffer */
-	log_buf_state = src_data = guc->log.runtime.buf_addr;
+	if (WARN_ON(!intel_guc_log_relay_enabled(log)))
+		goto out_unlock;
 
-	mutex_lock(&guc->log.runtime.relay_lock);
+	/* Get the pointer to shared GuC log buffer */
+	log_buf_state = src_data = log->relay.buf_addr;
 
 	/* Get the pointer to local buffer to store the logs */
-	log_buf_snapshot_state = dst_data = guc_get_write_buffer(guc);
+	log_buf_snapshot_state = dst_data = guc_get_write_buffer(log);
 
 	if (unlikely(!log_buf_snapshot_state)) {
 		/*
@@ -301,10 +253,9 @@ static void guc_read_update_log_buffer(struct intel_guc *guc)
 		 * getting consumed by User at a slow rate.
 		 */
 		DRM_ERROR_RATELIMITED("no sub-buffer to capture logs\n");
-		guc->log.capture_miss_count++;
-		mutex_unlock(&guc->log.runtime.relay_lock);
+		log->relay.full_count++;
 
-		return;
+		goto out_unlock;
 	}
 
 	/* Actual logs are present from the 2nd page */
@@ -325,8 +276,8 @@ static void guc_read_update_log_buffer(struct intel_guc *guc)
 		full_cnt = log_buf_state_local.buffer_full_cnt;
 
 		/* Bookkeeping stuff */
-		guc->log.flush_count[type] += log_buf_state_local.flush_to_file;
-		new_overflow = guc_check_log_buf_overflow(guc, type, full_cnt);
+		log->stats[type].flush += log_buf_state_local.flush_to_file;
+		new_overflow = guc_check_log_buf_overflow(log, type, full_cnt);
 
 		/* Update the state of shared log buffer */
 		log_buf_state->read_ptr = write_offset;
@@ -373,38 +324,35 @@ static void guc_read_update_log_buffer(struct intel_guc *guc)
 		dst_data += buffer_size;
 	}
 
-	guc_move_to_next_buf(guc);
+	guc_move_to_next_buf(log);
 
-	mutex_unlock(&guc->log.runtime.relay_lock);
+out_unlock:
+	mutex_unlock(&log->relay.lock);
 }
 
 static void capture_logs_work(struct work_struct *work)
 {
-	struct intel_guc *guc =
-		container_of(work, struct intel_guc, log.runtime.flush_work);
-
-	guc_log_capture_logs(guc);
-}
+	struct intel_guc_log *log =
+		container_of(work, struct intel_guc_log, relay.flush_work);
 
-static bool guc_log_has_runtime(struct intel_guc *guc)
-{
-	return guc->log.runtime.buf_addr != NULL;
+	guc_log_capture_logs(log);
 }
 
-static int guc_log_runtime_create(struct intel_guc *guc)
+static int guc_log_map(struct intel_guc_log *log)
 {
+	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	void *vaddr;
 	int ret;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+	lockdep_assert_held(&log->relay.lock);
 
-	if (!guc->log.vma)
+	if (!log->vma)
 		return -ENODEV;
 
-	GEM_BUG_ON(guc_log_has_runtime(guc));
-
-	ret = i915_gem_object_set_to_wc_domain(guc->log.vma->obj, true);
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	ret = i915_gem_object_set_to_wc_domain(log->vma->obj, true);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
 	if (ret)
 		return ret;
 
@@ -413,49 +361,40 @@ static int guc_log_runtime_create(struct intel_guc *guc)
 	 * buffer pages, so that we can directly get the data
 	 * (up-to-date) from memory.
 	 */
-	vaddr = i915_gem_object_pin_map(guc->log.vma->obj, I915_MAP_WC);
+	vaddr = i915_gem_object_pin_map(log->vma->obj, I915_MAP_WC);
 	if (IS_ERR(vaddr)) {
 		DRM_ERROR("Couldn't map log buffer pages %d\n", ret);
 		return PTR_ERR(vaddr);
 	}
 
-	guc->log.runtime.buf_addr = vaddr;
+	log->relay.buf_addr = vaddr;
 
 	return 0;
 }
 
-static void guc_log_runtime_destroy(struct intel_guc *guc)
+static void guc_log_unmap(struct intel_guc_log *log)
 {
-	/*
-	 * It's possible that the runtime stuff was never allocated because
-	 * GuC log was disabled at the boot time.
-	 */
-	if (!guc_log_has_runtime(guc))
-		return;
+	lockdep_assert_held(&log->relay.lock);
 
-	i915_gem_object_unpin_map(guc->log.vma->obj);
-	guc->log.runtime.buf_addr = NULL;
+	i915_gem_object_unpin_map(log->vma->obj);
+	log->relay.buf_addr = NULL;
 }
 
-void intel_guc_log_init_early(struct intel_guc *guc)
+void intel_guc_log_init_early(struct intel_guc_log *log)
 {
-	mutex_init(&guc->log.runtime.relay_lock);
-	INIT_WORK(&guc->log.runtime.flush_work, capture_logs_work);
+	mutex_init(&log->relay.lock);
+	INIT_WORK(&log->relay.flush_work, capture_logs_work);
 }
 
-int intel_guc_log_relay_create(struct intel_guc *guc)
+static int guc_log_relay_create(struct intel_guc_log *log)
 {
+	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	struct rchan *guc_log_relay_chan;
 	size_t n_subbufs, subbuf_size;
 	int ret;
 
-	if (!i915_modparams.guc_log_level)
-		return 0;
-
-	mutex_lock(&guc->log.runtime.relay_lock);
-
-	GEM_BUG_ON(guc_log_has_relay(guc));
+	lockdep_assert_held(&log->relay.lock);
 
 	 /* Keep the size of sub buffers same as shared log buffer */
 	subbuf_size = GUC_LOG_SIZE;
@@ -468,157 +407,56 @@ int intel_guc_log_relay_create(struct intel_guc *guc)
 	 */
 	n_subbufs = 8;
 
-	/*
-	 * Create a relay channel, so that we have buffers for storing
-	 * the GuC firmware logs, the channel will be linked with a file
-	 * later on when debugfs is registered.
-	 */
-	guc_log_relay_chan = relay_open(NULL, NULL, subbuf_size,
-					n_subbufs, &relay_callbacks, dev_priv);
+	guc_log_relay_chan = relay_open("guc_log",
+					dev_priv->drm.primary->debugfs_root,
+					subbuf_size, n_subbufs,
+					&relay_callbacks, dev_priv);
 	if (!guc_log_relay_chan) {
 		DRM_ERROR("Couldn't create relay chan for GuC logging\n");
 
 		ret = -ENOMEM;
-		goto err;
+		return ret;
 	}
 
 	GEM_BUG_ON(guc_log_relay_chan->subbuf_size < subbuf_size);
-	guc->log.runtime.relay_chan = guc_log_relay_chan;
-
-	mutex_unlock(&guc->log.runtime.relay_lock);
+	log->relay.channel = guc_log_relay_chan;
 
 	return 0;
-
-err:
-	mutex_unlock(&guc->log.runtime.relay_lock);
-	/* logging will be off */
-	i915_modparams.guc_log_level = 0;
-	return ret;
-}
-
-void intel_guc_log_relay_destroy(struct intel_guc *guc)
-{
-	mutex_lock(&guc->log.runtime.relay_lock);
-
-	/*
-	 * It's possible that the relay was never allocated because
-	 * GuC log was disabled at the boot time.
-	 */
-	if (!guc_log_has_relay(guc))
-		goto out_unlock;
-
-	relay_close(guc->log.runtime.relay_chan);
-	guc->log.runtime.relay_chan = NULL;
-
-out_unlock:
-	mutex_unlock(&guc->log.runtime.relay_lock);
 }
 
-static int guc_log_late_setup(struct intel_guc *guc)
+static void guc_log_relay_destroy(struct intel_guc_log *log)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	int ret;
-
-	if (!guc_log_has_runtime(guc)) {
-		/*
-		 * If log was disabled at boot time, then setup needed to handle
-		 * log buffer flush interrupts would not have been done yet, so
-		 * do that now.
-		 */
-		ret = intel_guc_log_relay_create(guc);
-		if (ret)
-			goto err;
-
-		mutex_lock(&dev_priv->drm.struct_mutex);
-		intel_runtime_pm_get(dev_priv);
-		ret = guc_log_runtime_create(guc);
-		intel_runtime_pm_put(dev_priv);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
-
-		if (ret)
-			goto err_relay;
-	}
-
-	ret = guc_log_relay_file_create(guc);
-	if (ret)
-		goto err_runtime;
-
-	return 0;
+	lockdep_assert_held(&log->relay.lock);
 
-err_runtime:
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	guc_log_runtime_destroy(guc);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-err_relay:
-	intel_guc_log_relay_destroy(guc);
-err:
-	/* logging will remain off */
-	i915_modparams.guc_log_level = 0;
-	return ret;
+	relay_close(log->relay.channel);
+	log->relay.channel = NULL;
 }
 
-static void guc_log_capture_logs(struct intel_guc *guc)
+static void guc_log_capture_logs(struct intel_guc_log *log)
 {
+	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
-	guc_read_update_log_buffer(guc);
+	guc_read_update_log_buffer(log);
 
 	/*
 	 * Generally device is expected to be active only at this
 	 * time, so get/put should be really quick.
 	 */
 	intel_runtime_pm_get(dev_priv);
-	guc_log_flush_complete(guc);
-	intel_runtime_pm_put(dev_priv);
-}
-
-static void guc_flush_logs(struct intel_guc *guc)
-{
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-
-	if (!USES_GUC_SUBMISSION(dev_priv) || !i915_modparams.guc_log_level)
-		return;
-
-	/* First disable the interrupts, will be renabled afterwards */
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	intel_runtime_pm_get(dev_priv);
-	gen9_disable_guc_interrupts(dev_priv);
-	intel_runtime_pm_put(dev_priv);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-
-	/*
-	 * Before initiating the forceful flush, wait for any pending/ongoing
-	 * flush to complete otherwise forceful flush may not actually happen.
-	 */
-	flush_work(&guc->log.runtime.flush_work);
-
-	/* Ask GuC to update the log buffer state */
-	intel_runtime_pm_get(dev_priv);
-	guc_log_flush(guc);
+	guc_action_flush_log_complete(guc);
 	intel_runtime_pm_put(dev_priv);
-
-	/* GuC would have updated log buffer by now, so capture it */
-	guc_log_capture_logs(guc);
 }
 
-int intel_guc_log_create(struct intel_guc *guc)
+int intel_guc_log_create(struct intel_guc_log *log)
 {
+	struct intel_guc *guc = log_to_guc(log);
 	struct i915_vma *vma;
 	unsigned long offset;
 	u32 flags;
 	int ret;
 
-	GEM_BUG_ON(guc->log.vma);
-
-	/*
-	 * We require SSE 4.1 for fast reads from the GuC log buffer and
-	 * it should be present on the chipsets supporting GuC based
-	 * submisssions.
-	 */
-	if (WARN_ON(!i915_has_memcpy_from_wc())) {
-		ret = -EINVAL;
-		goto err;
-	}
+	GEM_BUG_ON(log->vma);
 
 	vma = intel_guc_allocate_vma(guc, GUC_LOG_SIZE);
 	if (IS_ERR(vma)) {
@@ -626,13 +464,7 @@ int intel_guc_log_create(struct intel_guc *guc)
 		goto err;
 	}
 
-	guc->log.vma = vma;
-
-	if (i915_modparams.guc_log_level) {
-		ret = guc_log_runtime_create(guc);
-		if (ret < 0)
-			goto err_vma;
-	}
+	log->vma = vma;
 
 	/* each allocated unit is a page */
 	flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL |
@@ -640,117 +472,159 @@ int intel_guc_log_create(struct intel_guc *guc)
 		(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
 		(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT);
 
-	offset = guc_ggtt_offset(vma) >> PAGE_SHIFT; /* in pages */
-	guc->log.flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
+	offset = intel_guc_ggtt_offset(guc, vma) >> PAGE_SHIFT;
+	log->flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
 
 	return 0;
 
-err_vma:
-	i915_vma_unpin_and_release(&guc->log.vma);
 err:
 	/* logging will be off */
 	i915_modparams.guc_log_level = 0;
 	return ret;
 }
 
-void intel_guc_log_destroy(struct intel_guc *guc)
+void intel_guc_log_destroy(struct intel_guc_log *log)
+{
+	i915_vma_unpin_and_release(&log->vma);
+}
+
+int intel_guc_log_level_get(struct intel_guc_log *log)
 {
-	guc_log_runtime_destroy(guc);
-	i915_vma_unpin_and_release(&guc->log.vma);
+	GEM_BUG_ON(!log->vma);
+	GEM_BUG_ON(i915_modparams.guc_log_level < 0);
+
+	return i915_modparams.guc_log_level;
 }
 
-int intel_guc_log_control(struct intel_guc *guc, u64 control_val)
+int intel_guc_log_level_set(struct intel_guc_log *log, u64 val)
 {
+	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	bool enable_logging = control_val > 0;
-	u32 verbosity;
 	int ret;
 
-	if (!guc->log.vma)
-		return -ENODEV;
+	BUILD_BUG_ON(GUC_LOG_VERBOSITY_MIN != 0);
+	GEM_BUG_ON(!log->vma);
+	GEM_BUG_ON(i915_modparams.guc_log_level < 0);
 
-	BUILD_BUG_ON(GUC_LOG_VERBOSITY_MIN);
-	if (control_val > 1 + GUC_LOG_VERBOSITY_MAX)
+	/*
+	 * GuC is recognizing log levels starting from 0 to max, we're using 0
+	 * as indication that logging should be disabled.
+	 */
+	if (val < GUC_LOG_LEVEL_DISABLED || val > GUC_LOG_LEVEL_MAX)
 		return -EINVAL;
 
-	/* This combination doesn't make sense & won't have any effect */
-	if (!enable_logging && !i915_modparams.guc_log_level)
-		return 0;
+	mutex_lock(&dev_priv->drm.struct_mutex);
 
-	verbosity = enable_logging ? control_val - 1 : 0;
+	if (i915_modparams.guc_log_level == val) {
+		ret = 0;
+		goto out_unlock;
+	}
 
-	ret = mutex_lock_interruptible(&dev_priv->drm.struct_mutex);
-	if (ret)
-		return ret;
 	intel_runtime_pm_get(dev_priv);
-	ret = guc_log_control(guc, enable_logging, verbosity);
+	ret = guc_action_control_log(guc, GUC_LOG_LEVEL_IS_VERBOSE(val),
+				     GUC_LOG_LEVEL_IS_ENABLED(val),
+				     GUC_LOG_LEVEL_TO_VERBOSITY(val));
 	intel_runtime_pm_put(dev_priv);
+	if (ret) {
+		DRM_DEBUG_DRIVER("guc_log_control action failed %d\n", ret);
+		goto out_unlock;
+	}
+
+	i915_modparams.guc_log_level = val;
+
+out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	if (ret < 0) {
-		DRM_DEBUG_DRIVER("guc_logging_control action failed %d\n", ret);
-		return ret;
-	}
+	return ret;
+}
 
-	if (enable_logging) {
-		i915_modparams.guc_log_level = 1 + verbosity;
+bool intel_guc_log_relay_enabled(const struct intel_guc_log *log)
+{
+	return log->relay.buf_addr;
+}
 
-		/*
-		 * If log was disabled at boot time, then the relay channel file
-		 * wouldn't have been created by now and interrupts also would
-		 * not have been enabled. Try again now, just in case.
-		 */
-		ret = guc_log_late_setup(guc);
-		if (ret < 0) {
-			DRM_DEBUG_DRIVER("GuC log late setup failed %d\n", ret);
-			return ret;
-		}
+int intel_guc_log_relay_open(struct intel_guc_log *log)
+{
+	int ret;
 
-		/* GuC logging is currently the only user of Guc2Host interrupts */
-		mutex_lock(&dev_priv->drm.struct_mutex);
-		intel_runtime_pm_get(dev_priv);
-		gen9_enable_guc_interrupts(dev_priv);
-		intel_runtime_pm_put(dev_priv);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
-	} else {
-		/*
-		 * Once logging is disabled, GuC won't generate logs & send an
-		 * interrupt. But there could be some data in the log buffer
-		 * which is yet to be captured. So request GuC to update the log
-		 * buffer state and then collect the left over logs.
-		 */
-		guc_flush_logs(guc);
+	mutex_lock(&log->relay.lock);
 
-		/* As logging is disabled, update log level to reflect that */
-		i915_modparams.guc_log_level = 0;
+	if (intel_guc_log_relay_enabled(log)) {
+		ret = -EEXIST;
+		goto out_unlock;
 	}
 
-	return ret;
-}
+	/*
+	 * We require SSE 4.1 for fast reads from the GuC log buffer and
+	 * it should be present on the chipsets supporting GuC based
+	 * submisssions.
+	 */
+	if (!i915_has_memcpy_from_wc()) {
+		ret = -ENXIO;
+		goto out_unlock;
+	}
 
-void i915_guc_log_register(struct drm_i915_private *dev_priv)
-{
-	if (!USES_GUC_SUBMISSION(dev_priv) || !i915_modparams.guc_log_level)
-		return;
+	ret = guc_log_relay_create(log);
+	if (ret)
+		goto out_unlock;
+
+	ret = guc_log_map(log);
+	if (ret)
+		goto out_relay;
 
-	guc_log_late_setup(&dev_priv->guc);
+	mutex_unlock(&log->relay.lock);
+
+	guc_log_enable_flush_events(log);
+
+	/*
+	 * When GuC is logging without us relaying to userspace, we're ignoring
+	 * the flush notification. This means that we need to unconditionally
+	 * flush on relay enabling, since GuC only notifies us once.
+	 */
+	queue_work(log->relay.flush_wq, &log->relay.flush_work);
+
+	return 0;
+
+out_relay:
+	guc_log_relay_destroy(log);
+out_unlock:
+	mutex_unlock(&log->relay.lock);
+
+	return ret;
 }
 
-void i915_guc_log_unregister(struct drm_i915_private *dev_priv)
+void intel_guc_log_relay_flush(struct intel_guc_log *log)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = log_to_guc(log);
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+
+	/*
+	 * Before initiating the forceful flush, wait for any pending/ongoing
+	 * flush to complete otherwise forceful flush may not actually happen.
+	 */
+	flush_work(&log->relay.flush_work);
 
-	if (!USES_GUC_SUBMISSION(dev_priv))
-		return;
+	intel_runtime_pm_get(i915);
+	guc_action_flush_log(guc);
+	intel_runtime_pm_put(i915);
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	/* GuC logging is currently the only user of Guc2Host interrupts */
-	intel_runtime_pm_get(dev_priv);
-	gen9_disable_guc_interrupts(dev_priv);
-	intel_runtime_pm_put(dev_priv);
+	/* GuC would have updated log buffer by now, so capture it */
+	guc_log_capture_logs(log);
+}
 
-	guc_log_runtime_destroy(guc);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+void intel_guc_log_relay_close(struct intel_guc_log *log)
+{
+	guc_log_disable_flush_events(log);
+	flush_work(&log->relay.flush_work);
+
+	mutex_lock(&log->relay.lock);
+	GEM_BUG_ON(!intel_guc_log_relay_enabled(log));
+	guc_log_unmap(log);
+	guc_log_relay_destroy(log);
+	mutex_unlock(&log->relay.lock);
+}
 
-	intel_guc_log_relay_destroy(guc);
+void intel_guc_log_handle_flush_event(struct intel_guc_log *log)
+{
+	queue_work(log->relay.flush_wq, &log->relay.flush_work);
 }
diff --git a/drivers/gpu/drm/i915/intel_guc_log.h b/drivers/gpu/drm/i915/intel_guc_log.h
index dab0e949567a..fa80535a6f9d 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/intel_guc_log.h
@@ -25,11 +25,12 @@
 #ifndef _INTEL_GUC_LOG_H_
 #define _INTEL_GUC_LOG_H_
 
+#include <linux/mutex.h>
+#include <linux/relay.h>
 #include <linux/workqueue.h>
 
 #include "intel_guc_fwif.h"
 
-struct drm_i915_private;
 struct intel_guc;
 
 /*
@@ -39,33 +40,53 @@ struct intel_guc;
 #define GUC_LOG_SIZE	((1 + GUC_LOG_DPC_PAGES + 1 + GUC_LOG_ISR_PAGES + \
 			  1 + GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT)
 
+/*
+ * While we're using plain log level in i915, GuC controls are much more...
+ * "elaborate"? We have a couple of bits for verbosity, separate bit for actual
+ * log enabling, and separate bit for default logging - which "conveniently"
+ * ignores the enable bit.
+ */
+#define GUC_LOG_LEVEL_DISABLED		0
+#define GUC_LOG_LEVEL_NON_VERBOSE	1
+#define GUC_LOG_LEVEL_IS_ENABLED(x)	((x) > GUC_LOG_LEVEL_DISABLED)
+#define GUC_LOG_LEVEL_IS_VERBOSE(x)	((x) > GUC_LOG_LEVEL_NON_VERBOSE)
+#define GUC_LOG_LEVEL_TO_VERBOSITY(x) ({		\
+	typeof(x) _x = (x);				\
+	GUC_LOG_LEVEL_IS_VERBOSE(_x) ? _x - 2 : 0;	\
+})
+#define GUC_VERBOSITY_TO_LOG_LEVEL(x)	((x) + 2)
+#define GUC_LOG_LEVEL_MAX GUC_VERBOSITY_TO_LOG_LEVEL(GUC_LOG_VERBOSITY_MAX)
+
 struct intel_guc_log {
 	u32 flags;
 	struct i915_vma *vma;
-	/* The runtime stuff gets created only when GuC logging gets enabled */
 	struct {
 		void *buf_addr;
 		struct workqueue_struct *flush_wq;
 		struct work_struct flush_work;
-		struct rchan *relay_chan;
-		/* To serialize the access to relay_chan */
-		struct mutex relay_lock;
-	} runtime;
+		struct rchan *channel;
+		struct mutex lock;
+		u32 full_count;
+	} relay;
 	/* logging related stats */
-	u32 capture_miss_count;
-	u32 flush_interrupt_count;
-	u32 prev_overflow_count[GUC_MAX_LOG_BUFFER];
-	u32 total_overflow_count[GUC_MAX_LOG_BUFFER];
-	u32 flush_count[GUC_MAX_LOG_BUFFER];
+	struct {
+		u32 sampled_overflow;
+		u32 overflow;
+		u32 flush;
+	} stats[GUC_MAX_LOG_BUFFER];
 };
 
-int intel_guc_log_create(struct intel_guc *guc);
-void intel_guc_log_destroy(struct intel_guc *guc);
-void intel_guc_log_init_early(struct intel_guc *guc);
-int intel_guc_log_relay_create(struct intel_guc *guc);
-void intel_guc_log_relay_destroy(struct intel_guc *guc);
-int intel_guc_log_control(struct intel_guc *guc, u64 control_val);
-void i915_guc_log_register(struct drm_i915_private *dev_priv);
-void i915_guc_log_unregister(struct drm_i915_private *dev_priv);
+void intel_guc_log_init_early(struct intel_guc_log *log);
+int intel_guc_log_create(struct intel_guc_log *log);
+void intel_guc_log_destroy(struct intel_guc_log *log);
+
+int intel_guc_log_level_get(struct intel_guc_log *log);
+int intel_guc_log_level_set(struct intel_guc_log *log, u64 control_val);
+bool intel_guc_log_relay_enabled(const struct intel_guc_log *log);
+int intel_guc_log_relay_open(struct intel_guc_log *log);
+void intel_guc_log_relay_flush(struct intel_guc_log *log);
+void intel_guc_log_relay_close(struct intel_guc_log *log);
+
+void intel_guc_log_handle_flush_event(struct intel_guc_log *log);
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_guc_reg.h b/drivers/gpu/drm/i915/intel_guc_reg.h
index 19a9247c5664..d86084742a4a 100644
--- a/drivers/gpu/drm/i915/intel_guc_reg.h
+++ b/drivers/gpu/drm/i915/intel_guc_reg.h
@@ -66,22 +66,20 @@
 #define   UOS_MOVE			  (1<<4)
 #define   START_DMA			  (1<<0)
 #define DMA_GUC_WOPCM_OFFSET		_MMIO(0xc340)
+#define   GUC_WOPCM_OFFSET_VALID	  (1<<0)
 #define   HUC_LOADING_AGENT_VCR		  (0<<1)
 #define   HUC_LOADING_AGENT_GUC		  (1<<1)
-#define   GUC_WOPCM_OFFSET_VALUE	  0x80000	/* 512KB */
+#define   GUC_WOPCM_OFFSET_SHIFT	14
+#define   GUC_WOPCM_OFFSET_MASK		  (0x3ffff << GUC_WOPCM_OFFSET_SHIFT)
 #define GUC_MAX_IDLE_COUNT		_MMIO(0xC3E4)
 
 #define HUC_STATUS2             _MMIO(0xD3B0)
 #define   HUC_FW_VERIFIED       (1<<7)
 
-/* Defines WOPCM space available to GuC firmware */
 #define GUC_WOPCM_SIZE			_MMIO(0xc050)
-/* GuC addresses below GUC_WOPCM_TOP don't map through the GTT */
-#define   GUC_WOPCM_TOP			  (0x80 << 12)	/* 512KB */
-#define   BXT_GUC_WOPCM_RC6_RESERVED	  (0x10 << 12)	/* 64KB  */
-
-/* GuC addresses above GUC_GGTT_TOP also don't map through the GTT */
-#define GUC_GGTT_TOP			0xFEE00000
+#define   GUC_WOPCM_SIZE_LOCKED		  (1<<0)
+#define   GUC_WOPCM_SIZE_SHIFT		12
+#define   GUC_WOPCM_SIZE_MASK		  (0xfffff << GUC_WOPCM_SIZE_SHIFT)
 
 #define GEN8_GT_PM_CONFIG		_MMIO(0x138140)
 #define GEN9LP_GT_PM_CONFIG		_MMIO(0x138140)
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 8a8ad2fe158d..2feb65096966 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -124,9 +124,17 @@ static int reserve_doorbell(struct intel_guc_client *client)
 	return 0;
 }
 
+static bool has_doorbell(struct intel_guc_client *client)
+{
+	if (client->doorbell_id == GUC_DOORBELL_INVALID)
+		return false;
+
+	return test_bit(client->doorbell_id, client->guc->doorbell_bitmap);
+}
+
 static void unreserve_doorbell(struct intel_guc_client *client)
 {
-	GEM_BUG_ON(client->doorbell_id == GUC_DOORBELL_INVALID);
+	GEM_BUG_ON(!has_doorbell(client));
 
 	__clear_bit(client->doorbell_id, client->guc->doorbell_bitmap);
 	client->doorbell_id = GUC_DOORBELL_INVALID;
@@ -184,14 +192,6 @@ static struct guc_doorbell_info *__get_doorbell(struct intel_guc_client *client)
 	return client->vaddr + client->doorbell_offset;
 }
 
-static bool has_doorbell(struct intel_guc_client *client)
-{
-	if (client->doorbell_id == GUC_DOORBELL_INVALID)
-		return false;
-
-	return test_bit(client->doorbell_id, client->guc->doorbell_bitmap);
-}
-
 static void __create_doorbell(struct intel_guc_client *client)
 {
 	struct guc_doorbell_info *doorbell;
@@ -207,7 +207,6 @@ static void __destroy_doorbell(struct intel_guc_client *client)
 	struct guc_doorbell_info *doorbell;
 	u16 db_id = client->doorbell_id;
 
-
 	doorbell = __get_doorbell(client);
 	doorbell->db_status = GUC_DOORBELL_DISABLED;
 	doorbell->cookie = 0;
@@ -224,6 +223,9 @@ static int create_doorbell(struct intel_guc_client *client)
 {
 	int ret;
 
+	if (WARN_ON(!has_doorbell(client)))
+		return -ENODEV; /* internal setup error, should never happen */
+
 	__update_doorbell_desc(client, client->doorbell_id);
 	__create_doorbell(client);
 
@@ -231,8 +233,8 @@ static int create_doorbell(struct intel_guc_client *client)
 	if (ret) {
 		__destroy_doorbell(client);
 		__update_doorbell_desc(client, GUC_DOORBELL_INVALID);
-		DRM_ERROR("Couldn't create client %u doorbell: %d\n",
-			  client->stage_id, ret);
+		DRM_DEBUG_DRIVER("Couldn't create client %u doorbell: %d\n",
+				 client->stage_id, ret);
 		return ret;
 	}
 
@@ -362,7 +364,7 @@ static void guc_stage_desc_init(struct intel_guc *guc,
 	desc->db_id = client->doorbell_id;
 
 	for_each_engine_masked(engine, dev_priv, client->engines, tmp) {
-		struct intel_context *ce = &ctx->engine[engine->id];
+		struct intel_context *ce = to_intel_context(ctx, engine);
 		u32 guc_engine_id = engine->guc_id;
 		struct guc_execlist_context *lrc = &desc->lrc[guc_engine_id];
 
@@ -386,8 +388,8 @@ static void guc_stage_desc_init(struct intel_guc *guc,
 		lrc->context_desc = lower_32_bits(ce->lrc_desc);
 
 		/* The state page is after PPHWSP */
-		lrc->ring_lrca =
-			guc_ggtt_offset(ce->state) + LRC_STATE_PN * PAGE_SIZE;
+		lrc->ring_lrca = intel_guc_ggtt_offset(guc, ce->state) +
+				 LRC_STATE_PN * PAGE_SIZE;
 
 		/* XXX: In direct submission, the GuC wants the HW context id
 		 * here. In proxy submission, it wants the stage id
@@ -395,7 +397,7 @@ static void guc_stage_desc_init(struct intel_guc *guc,
 		lrc->context_id = (client->stage_id << GUC_ELC_CTXID_OFFSET) |
 				(guc_engine_id << GUC_ELC_ENGINE_OFFSET);
 
-		lrc->ring_begin = guc_ggtt_offset(ce->ring->vma);
+		lrc->ring_begin = intel_guc_ggtt_offset(guc, ce->ring->vma);
 		lrc->ring_end = lrc->ring_begin + ce->ring->size - 1;
 		lrc->ring_next_free_location = lrc->ring_begin;
 		lrc->ring_current_tail_pointer_value = 0;
@@ -411,7 +413,7 @@ static void guc_stage_desc_init(struct intel_guc *guc,
 	 * The doorbell, process descriptor, and workqueue are all parts
 	 * of the client object, which the GuC will reference via the GGTT
 	 */
-	gfx_addr = guc_ggtt_offset(client->vma);
+	gfx_addr = intel_guc_ggtt_offset(guc, client->vma);
 	desc->db_trigger_phy = sg_dma_address(client->vma->pages->sgl) +
 				client->doorbell_offset;
 	desc->db_trigger_cpu = ptr_to_u64(__get_doorbell(client));
@@ -584,7 +586,7 @@ static void inject_preempt_context(struct work_struct *work)
 	data[3] = engine->guc_id;
 	data[4] = guc->execbuf_client->priority;
 	data[5] = guc->execbuf_client->stage_id;
-	data[6] = guc_ggtt_offset(guc->shared_data);
+	data[6] = intel_guc_ggtt_offset(guc, guc->shared_data);
 
 	if (WARN_ON(intel_guc_send(guc, data, ARRAY_SIZE(data)))) {
 		execlists_clear_active(&engine->execlists,
@@ -657,7 +659,17 @@ static void port_assign(struct execlist_port *port, struct i915_request *rq)
 	port_set(port, i915_request_get(rq));
 }
 
-static void guc_dequeue(struct intel_engine_cs *engine)
+static inline int rq_prio(const struct i915_request *rq)
+{
+	return rq->sched.attr.priority;
+}
+
+static inline int port_prio(const struct execlist_port *port)
+{
+	return rq_prio(port_request(port));
+}
+
+static bool __guc_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
@@ -667,28 +679,29 @@ static void guc_dequeue(struct intel_engine_cs *engine)
 	bool submit = false;
 	struct rb_node *rb;
 
-	spin_lock_irq(&engine->timeline->lock);
+	lockdep_assert_held(&engine->timeline.lock);
+
 	rb = execlists->first;
 	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
 
 	if (port_isset(port)) {
-		if (engine->i915->preempt_context) {
+		if (intel_engine_has_preemption(engine)) {
 			struct guc_preempt_work *preempt_work =
 				&engine->i915->guc.preempt_work[engine->id];
+			int prio = execlists->queue_priority;
 
-			if (execlists->queue_priority >
-			    max(port_request(port)->priotree.priority, 0)) {
+			if (__execlists_need_preempt(prio, port_prio(port))) {
 				execlists_set_active(execlists,
 						     EXECLISTS_ACTIVE_PREEMPT);
 				queue_work(engine->i915->guc.preempt_wq,
 					   &preempt_work->work);
-				goto unlock;
+				return false;
 			}
 		}
 
 		port++;
 		if (port_isset(port))
-			goto unlock;
+			return false;
 	}
 	GEM_BUG_ON(port_isset(port));
 
@@ -696,11 +709,11 @@ static void guc_dequeue(struct intel_engine_cs *engine)
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
-		list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) {
+		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
 			if (last && rq->ctx != last->ctx) {
 				if (port == last_port) {
 					__list_del_many(&p->requests,
-							&rq->priotree.link);
+							&rq->sched.link);
 					goto done;
 				}
 
@@ -709,7 +722,7 @@ static void guc_dequeue(struct intel_engine_cs *engine)
 				port++;
 			}
 
-			INIT_LIST_HEAD(&rq->priotree.link);
+			INIT_LIST_HEAD(&rq->sched.link);
 
 			__i915_request_submit(rq);
 			trace_i915_request_in(rq, port_index(port, execlists));
@@ -726,19 +739,34 @@ static void guc_dequeue(struct intel_engine_cs *engine)
 done:
 	execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN;
 	execlists->first = rb;
-	if (submit) {
+	if (submit)
 		port_assign(port, last);
-		execlists_set_active(execlists, EXECLISTS_ACTIVE_USER);
-		guc_submit(engine);
-	}
+	if (last)
+		execlists_user_begin(execlists, execlists->port);
 
 	/* We must always keep the beast fed if we have work piled up */
 	GEM_BUG_ON(port_isset(execlists->port) &&
 		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
 	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
 
-unlock:
-	spin_unlock_irq(&engine->timeline->lock);
+	return submit;
+}
+
+static void guc_dequeue(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+	bool submit;
+
+	local_irq_save(flags);
+
+	spin_lock(&engine->timeline.lock);
+	submit = __guc_dequeue(engine);
+	spin_unlock(&engine->timeline.lock);
+
+	if (submit)
+		guc_submit(engine);
+
+	local_irq_restore(flags);
 }
 
 static void guc_submission_tasklet(unsigned long data)
@@ -748,17 +776,20 @@ static void guc_submission_tasklet(unsigned long data)
 	struct execlist_port *port = execlists->port;
 	struct i915_request *rq;
 
-	rq = port_request(&port[0]);
+	rq = port_request(port);
 	while (rq && i915_request_completed(rq)) {
 		trace_i915_request_out(rq);
 		i915_request_put(rq);
 
-		execlists_port_complete(execlists, port);
-
-		rq = port_request(&port[0]);
+		port = execlists_port_complete(execlists, port);
+		if (port_isset(port)) {
+			execlists_user_begin(execlists, port);
+			rq = port_request(port);
+		} else {
+			execlists_user_end(execlists);
+			rq = NULL;
+		}
 	}
-	if (!rq)
-		execlists_clear_active(execlists, EXECLISTS_ACTIVE_USER);
 
 	if (execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT) &&
 	    intel_read_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX) ==
@@ -977,7 +1008,8 @@ static void guc_fill_preempt_context(struct intel_guc *guc)
 	enum intel_engine_id id;
 
 	for_each_engine(engine, dev_priv, id) {
-		struct intel_context *ce = &client->owner->engine[id];
+		struct intel_context *ce =
+			to_intel_context(client->owner, engine);
 		u32 addr = intel_hws_preempt_done_address(engine);
 		u32 *cs;
 
diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index c8ea510629fa..d47e346bd49e 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -246,9 +246,8 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd)
 	 */
 	tmp = I915_READ_CTL(engine);
 	if (tmp & RING_WAIT) {
-		i915_handle_error(dev_priv, BIT(engine->id),
-				  "Kicking stuck wait on %s",
-				  engine->name);
+		i915_handle_error(dev_priv, BIT(engine->id), 0,
+				  "stuck wait on %s", engine->name);
 		I915_WRITE_CTL(engine, tmp);
 		return ENGINE_WAIT_KICK;
 	}
@@ -258,8 +257,8 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd)
 		default:
 			return ENGINE_DEAD;
 		case 1:
-			i915_handle_error(dev_priv, ALL_ENGINES,
-					  "Kicking stuck semaphore on %s",
+			i915_handle_error(dev_priv, ALL_ENGINES, 0,
+					  "stuck semaphore on %s",
 					  engine->name);
 			I915_WRITE_CTL(engine, tmp);
 			return ENGINE_WAIT_KICK;
@@ -357,7 +356,7 @@ static void hangcheck_accumulate_sample(struct intel_engine_cs *engine,
 		break;
 
 	case ENGINE_DEAD:
-		if (drm_debug & DRM_UT_DRIVER) {
+		if (GEM_SHOW_DEBUG()) {
 			struct drm_printer p = drm_debug_printer("hangcheck");
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 		}
@@ -386,13 +385,13 @@ static void hangcheck_declare_hang(struct drm_i915_private *i915,
 	if (stuck != hung)
 		hung &= ~stuck;
 	len = scnprintf(msg, sizeof(msg),
-			"%s on ", stuck == hung ? "No progress" : "Hang");
+			"%s on ", stuck == hung ? "no progress" : "hang");
 	for_each_engine_masked(engine, i915, hung, tmp)
 		len += scnprintf(msg + len, sizeof(msg) - len,
 				 "%s, ", engine->name);
 	msg[len-2] = '\0';
 
-	return i915_handle_error(i915, hung, "%s", msg);
+	return i915_handle_error(i915, hung, I915_ERROR_CAPTURE, "%s", msg);
 }
 
 /*
@@ -453,6 +452,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
 {
 	memset(&engine->hangcheck, 0, sizeof(engine->hangcheck));
+	engine->hangcheck.action_timestamp = jiffies;
 }
 
 void intel_hangcheck_init(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/intel_hdcp.c b/drivers/gpu/drm/i915/intel_hdcp.c
index 14ca5d3057a7..2db5da550a1c 100644
--- a/drivers/gpu/drm/i915/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/intel_hdcp.c
@@ -37,6 +37,43 @@ static int intel_hdcp_poll_ksv_fifo(struct intel_digital_port *intel_dig_port,
 	return 0;
 }
 
+static bool hdcp_key_loadable(struct drm_i915_private *dev_priv)
+{
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *power_well;
+	enum i915_power_well_id id;
+	bool enabled = false;
+
+	/*
+	 * On HSW and BDW, Display HW loads the Key as soon as Display resumes.
+	 * On all BXT+, SW can load the keys only when the PW#1 is turned on.
+	 */
+	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+		id = HSW_DISP_PW_GLOBAL;
+	else
+		id = SKL_DISP_PW_1;
+
+	mutex_lock(&power_domains->lock);
+
+	/* PG1 (power well #1) needs to be enabled */
+	for_each_power_well(dev_priv, power_well) {
+		if (power_well->id == id) {
+			enabled = power_well->ops->is_enabled(dev_priv,
+							      power_well);
+			break;
+		}
+	}
+	mutex_unlock(&power_domains->lock);
+
+	/*
+	 * Another req for hdcp key loadability is enabled state of pll for
+	 * cdclk. Without active crtc we wont land here. So we are assuming that
+	 * cdclk is already on.
+	 */
+
+	return enabled;
+}
+
 static void intel_hdcp_clear_keys(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(HDCP_KEY_CONF, HDCP_CLEAR_KEYS_TRIGGER);
@@ -142,53 +179,17 @@ bool intel_hdcp_is_ksv_valid(u8 *ksv)
 	return true;
 }
 
-/* Implements Part 2 of the HDCP authorization procedure */
 static
-int intel_hdcp_auth_downstream(struct intel_digital_port *intel_dig_port,
-			       const struct intel_hdcp_shim *shim)
+int intel_hdcp_validate_v_prime(struct intel_digital_port *intel_dig_port,
+				const struct intel_hdcp_shim *shim,
+				u8 *ksv_fifo, u8 num_downstream, u8 *bstatus)
 {
 	struct drm_i915_private *dev_priv;
 	u32 vprime, sha_text, sha_leftovers, rep_ctl;
-	u8 bstatus[2], num_downstream, *ksv_fifo;
 	int ret, i, j, sha_idx;
 
 	dev_priv = intel_dig_port->base.base.dev->dev_private;
 
-	ret = intel_hdcp_poll_ksv_fifo(intel_dig_port, shim);
-	if (ret) {
-		DRM_ERROR("KSV list failed to become ready (%d)\n", ret);
-		return ret;
-	}
-
-	ret = shim->read_bstatus(intel_dig_port, bstatus);
-	if (ret)
-		return ret;
-
-	if (DRM_HDCP_MAX_DEVICE_EXCEEDED(bstatus[0]) ||
-	    DRM_HDCP_MAX_CASCADE_EXCEEDED(bstatus[1])) {
-		DRM_ERROR("Max Topology Limit Exceeded\n");
-		return -EPERM;
-	}
-
-	/*
-	 * When repeater reports 0 device count, HDCP1.4 spec allows disabling
-	 * the HDCP encryption. That implies that repeater can't have its own
-	 * display. As there is no consumption of encrypted content in the
-	 * repeater with 0 downstream devices, we are failing the
-	 * authentication.
-	 */
-	num_downstream = DRM_HDCP_NUM_DOWNSTREAM(bstatus[0]);
-	if (num_downstream == 0)
-		return -EINVAL;
-
-	ksv_fifo = kzalloc(num_downstream * DRM_HDCP_KSV_LEN, GFP_KERNEL);
-	if (!ksv_fifo)
-		return -ENOMEM;
-
-	ret = shim->read_ksv_fifo(intel_dig_port, num_downstream, ksv_fifo);
-	if (ret)
-		return ret;
-
 	/* Process V' values from the receiver */
 	for (i = 0; i < DRM_HDCP_V_PRIME_NUM_PARTS; i++) {
 		ret = shim->read_v_prime_part(intel_dig_port, i, &vprime);
@@ -353,7 +354,8 @@ int intel_hdcp_auth_downstream(struct intel_digital_port *intel_dig_port,
 			return ret;
 		sha_idx += sizeof(sha_text);
 	} else {
-		DRM_ERROR("Invalid number of leftovers %d\n", sha_leftovers);
+		DRM_DEBUG_KMS("Invalid number of leftovers %d\n",
+			      sha_leftovers);
 		return -EINVAL;
 	}
 
@@ -381,17 +383,83 @@ int intel_hdcp_auth_downstream(struct intel_digital_port *intel_dig_port,
 	if (intel_wait_for_register(dev_priv, HDCP_REP_CTL,
 				    HDCP_SHA1_COMPLETE,
 				    HDCP_SHA1_COMPLETE, 1)) {
-		DRM_ERROR("Timed out waiting for SHA1 complete\n");
+		DRM_DEBUG_KMS("Timed out waiting for SHA1 complete\n");
 		return -ETIMEDOUT;
 	}
 	if (!(I915_READ(HDCP_REP_CTL) & HDCP_SHA1_V_MATCH)) {
-		DRM_ERROR("SHA-1 mismatch, HDCP failed\n");
+		DRM_DEBUG_KMS("SHA-1 mismatch, HDCP failed\n");
 		return -ENXIO;
 	}
 
+	return 0;
+}
+
+/* Implements Part 2 of the HDCP authorization procedure */
+static
+int intel_hdcp_auth_downstream(struct intel_digital_port *intel_dig_port,
+			       const struct intel_hdcp_shim *shim)
+{
+	u8 bstatus[2], num_downstream, *ksv_fifo;
+	int ret, i, tries = 3;
+
+	ret = intel_hdcp_poll_ksv_fifo(intel_dig_port, shim);
+	if (ret) {
+		DRM_ERROR("KSV list failed to become ready (%d)\n", ret);
+		return ret;
+	}
+
+	ret = shim->read_bstatus(intel_dig_port, bstatus);
+	if (ret)
+		return ret;
+
+	if (DRM_HDCP_MAX_DEVICE_EXCEEDED(bstatus[0]) ||
+	    DRM_HDCP_MAX_CASCADE_EXCEEDED(bstatus[1])) {
+		DRM_ERROR("Max Topology Limit Exceeded\n");
+		return -EPERM;
+	}
+
+	/*
+	 * When repeater reports 0 device count, HDCP1.4 spec allows disabling
+	 * the HDCP encryption. That implies that repeater can't have its own
+	 * display. As there is no consumption of encrypted content in the
+	 * repeater with 0 downstream devices, we are failing the
+	 * authentication.
+	 */
+	num_downstream = DRM_HDCP_NUM_DOWNSTREAM(bstatus[0]);
+	if (num_downstream == 0)
+		return -EINVAL;
+
+	ksv_fifo = kzalloc(num_downstream * DRM_HDCP_KSV_LEN, GFP_KERNEL);
+	if (!ksv_fifo)
+		return -ENOMEM;
+
+	ret = shim->read_ksv_fifo(intel_dig_port, num_downstream, ksv_fifo);
+	if (ret)
+		goto err;
+
+	/*
+	 * When V prime mismatches, DP Spec mandates re-read of
+	 * V prime atleast twice.
+	 */
+	for (i = 0; i < tries; i++) {
+		ret = intel_hdcp_validate_v_prime(intel_dig_port, shim,
+						  ksv_fifo, num_downstream,
+						  bstatus);
+		if (!ret)
+			break;
+	}
+
+	if (i == tries) {
+		DRM_ERROR("V Prime validation failed.(%d)\n", ret);
+		goto err;
+	}
+
 	DRM_DEBUG_KMS("HDCP is enabled (%d downstream devices)\n",
 		      num_downstream);
-	return 0;
+	ret = 0;
+err:
+	kfree(ksv_fifo);
+	return ret;
 }
 
 /* Implements Part 1 of the HDCP authorization procedure */
@@ -506,15 +574,26 @@ static int intel_hdcp_auth(struct intel_digital_port *intel_dig_port,
 	 */
 	wait_remaining_ms_from_jiffies(r0_prime_gen_start, 300);
 
-	ri.reg = 0;
-	ret = shim->read_ri_prime(intel_dig_port, ri.shim);
-	if (ret)
-		return ret;
-	I915_WRITE(PORT_HDCP_RPRIME(port), ri.reg);
+	tries = 3;
 
-	/* Wait for Ri prime match */
-	if (wait_for(I915_READ(PORT_HDCP_STATUS(port)) &
-		     (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) {
+	/*
+	 * DP HDCP Spec mandates the two more reattempt to read R0, incase
+	 * of R0 mismatch.
+	 */
+	for (i = 0; i < tries; i++) {
+		ri.reg = 0;
+		ret = shim->read_ri_prime(intel_dig_port, ri.shim);
+		if (ret)
+			return ret;
+		I915_WRITE(PORT_HDCP_RPRIME(port), ri.reg);
+
+		/* Wait for Ri prime match */
+		if (!wait_for(I915_READ(PORT_HDCP_STATUS(port)) &
+		    (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1))
+			break;
+	}
+
+	if (i == tries) {
 		DRM_ERROR("Timed out waiting for Ri prime match (%x)\n",
 			  I915_READ(PORT_HDCP_STATUS(port)));
 		return -ETIMEDOUT;
@@ -580,8 +659,8 @@ static int _intel_hdcp_enable(struct intel_connector *connector)
 	DRM_DEBUG_KMS("[%s:%d] HDCP is being enabled...\n",
 		      connector->base.name, connector->base.base.id);
 
-	if (!(I915_READ(SKL_FUSE_STATUS) & SKL_FUSE_PG_DIST_STATUS(1))) {
-		DRM_ERROR("PG1 is disabled, cannot load keys\n");
+	if (!hdcp_key_loadable(dev_priv)) {
+		DRM_ERROR("HDCP key Load is not possible\n");
 		return -ENXIO;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 1baef4ac7ecb..ee929f31f7db 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -2082,41 +2082,33 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
  * it enables scrambling. This should be called before enabling the HDMI
  * 2.0 port, as the sink can choose to disable the scrambling if it doesn't
  * detect a scrambled clock within 100 ms.
+ *
+ * Returns:
+ * True on success, false on failure.
  */
-void intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder,
+bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder,
 				       struct drm_connector *connector,
 				       bool high_tmds_clock_ratio,
 				       bool scrambling)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
 	struct drm_scrambling *sink_scrambling =
-				&connector->display_info.hdmi.scdc.scrambling;
-	struct i2c_adapter *adptr = intel_gmbus_get_adapter(dev_priv,
-							   intel_hdmi->ddc_bus);
-	bool ret;
+		&connector->display_info.hdmi.scdc.scrambling;
+	struct i2c_adapter *adapter =
+		intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus);
 
 	if (!sink_scrambling->supported)
-		return;
-
-	DRM_DEBUG_KMS("Setting sink scrambling for enc:%s connector:%s\n",
-		      encoder->base.name, connector->name);
+		return true;
 
-	/* Set TMDS bit clock ratio to 1/40 or 1/10 */
-	ret = drm_scdc_set_high_tmds_clock_ratio(adptr, high_tmds_clock_ratio);
-	if (!ret) {
-		DRM_ERROR("Set TMDS ratio failed\n");
-		return;
-	}
-
-	/* Enable/disable sink scrambling */
-	ret = drm_scdc_set_scrambling(adptr, scrambling);
-	if (!ret) {
-		DRM_ERROR("Set sink scrambling failed\n");
-		return;
-	}
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] scrambling=%s, TMDS bit clock ratio=1/%d\n",
+		      connector->base.id, connector->name,
+		      yesno(scrambling), high_tmds_clock_ratio ? 40 : 10);
 
-	DRM_DEBUG_KMS("sink scrambling handled\n");
+	/* Set TMDS bit clock ratio to 1/40 or 1/10, and enable/disable scrambling */
+	return drm_scdc_set_high_tmds_clock_ratio(adapter,
+						  high_tmds_clock_ratio) &&
+		drm_scdc_set_scrambling(adapter, scrambling);
 }
 
 static u8 chv_port_to_ddc_pin(struct drm_i915_private *dev_priv, enum port port)
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index 0e3d3e89d66a..43aa92beff2a 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -100,6 +100,8 @@ enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
 		if (IS_CNL_WITH_PORT_F(dev_priv))
 			return PORT_F;
 		return PORT_E;
+	case HPD_PORT_F:
+		return PORT_F;
 	default:
 		return PORT_NONE; /* no port for this pin */
 	}
@@ -132,6 +134,7 @@ enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv,
 	case PORT_F:
 		if (IS_CNL_WITH_PORT_F(dev_priv))
 			return HPD_PORT_E;
+		return HPD_PORT_F;
 	default:
 		MISSING_CASE(port);
 		return HPD_NONE;
diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
index 65e2afb9b955..291285277403 100644
--- a/drivers/gpu/drm/i915/intel_huc.c
+++ b/drivers/gpu/drm/i915/intel_huc.c
@@ -55,7 +55,7 @@ int intel_huc_auth(struct intel_huc *huc)
 		return -ENOEXEC;
 
 	vma = i915_gem_object_ggtt_pin(huc->fw.obj, NULL, 0, 0,
-				PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+				       PIN_OFFSET_BIAS | guc->ggtt_pin_bias);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		DRM_ERROR("HuC: Failed to pin huc fw object %d\n", ret);
@@ -63,7 +63,8 @@ int intel_huc_auth(struct intel_huc *huc)
 	}
 
 	ret = intel_guc_auth_huc(guc,
-				 guc_ggtt_offset(vma) + huc->fw.rsa_offset);
+				 intel_guc_ggtt_offset(guc, vma) +
+				 huc->fw.rsa_offset);
 	if (ret) {
 		DRM_ERROR("HuC: GuC did not ack Auth request %d\n", ret);
 		goto fail_unpin;
@@ -91,3 +92,28 @@ fail:
 	DRM_ERROR("HuC: Authentication failed %d\n", ret);
 	return ret;
 }
+
+/**
+ * intel_huc_check_status() - check HuC status
+ * @huc: intel_huc structure
+ *
+ * This function reads status register to verify if HuC
+ * firmware was successfully loaded.
+ *
+ * Returns positive value if HuC firmware is loaded and verified
+ * and -ENODEV if HuC is not present.
+ */
+int intel_huc_check_status(struct intel_huc *huc)
+{
+	struct drm_i915_private *dev_priv = huc_to_i915(huc);
+	u32 status;
+
+	if (!HAS_HUC(dev_priv))
+		return -ENODEV;
+
+	intel_runtime_pm_get(dev_priv);
+	status = I915_READ(HUC_STATUS2) & HUC_FW_VERIFIED;
+	intel_runtime_pm_put(dev_priv);
+
+	return status;
+}
diff --git a/drivers/gpu/drm/i915/intel_huc.h b/drivers/gpu/drm/i915/intel_huc.h
index 5d6e804f9771..aa854907abac 100644
--- a/drivers/gpu/drm/i915/intel_huc.h
+++ b/drivers/gpu/drm/i915/intel_huc.h
@@ -37,5 +37,12 @@ struct intel_huc {
 
 void intel_huc_init_early(struct intel_huc *huc);
 int intel_huc_auth(struct intel_huc *huc);
+int intel_huc_check_status(struct intel_huc *huc);
+
+static inline int intel_huc_sanitize(struct intel_huc *huc)
+{
+	intel_uc_fw_sanitize(&huc->fw);
+	return 0;
+}
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_huc_fw.c b/drivers/gpu/drm/i915/intel_huc_fw.c
index c66afa9b989a..f93d2384d482 100644
--- a/drivers/gpu/drm/i915/intel_huc_fw.c
+++ b/drivers/gpu/drm/i915/intel_huc_fw.c
@@ -118,7 +118,8 @@ static int huc_fw_xfer(struct intel_uc_fw *huc_fw, struct i915_vma *vma)
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
 	/* Set the source address for the uCode */
-	offset = guc_ggtt_offset(vma) + huc_fw->header_offset;
+	offset = intel_guc_ggtt_offset(&dev_priv->guc, vma) +
+		 huc_fw->header_offset;
 	I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset));
 	I915_WRITE(DMA_ADDR_0_HIGH, upper_32_bits(offset) & 0xFFFF);
 
@@ -154,9 +155,8 @@ static int huc_fw_xfer(struct intel_uc_fw *huc_fw, struct i915_vma *vma)
  * Called from intel_uc_init_hw() during driver load, resume from sleep and
  * after a GPU reset. Note that HuC must be loaded before GuC.
  *
- * The firmware image should have already been fetched into memory by the
- * earlier call to intel_uc_init_fw(), so here we need to only check that
- * fetch succeeded, and then transfer the image to the h/w.
+ * The firmware image should have already been fetched into memory, so only
+ * check that fetch succeeded, and then transfer the image to the h/w.
  *
  * Return:	non-zero code on error
  */
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 697af5add78b..15434cad5430 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -139,6 +139,7 @@
 #include "i915_gem_render_state.h"
 #include "intel_lrc_reg.h"
 #include "intel_mocs.h"
+#include "intel_workarounds.h"
 
 #define RING_EXECLIST_QFULL		(1 << 0x2)
 #define RING_EXECLIST1_VALID		(1 << 0x3)
@@ -176,14 +177,16 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 
 static inline int rq_prio(const struct i915_request *rq)
 {
-	return rq->priotree.priority;
+	return rq->sched.attr.priority;
 }
 
 static inline bool need_preempt(const struct intel_engine_cs *engine,
 				const struct i915_request *last,
 				int prio)
 {
-	return engine->i915->preempt_context && prio > max(rq_prio(last), 0);
+	return (intel_engine_has_preemption(engine) &&
+		__execlists_need_preempt(prio, rq_prio(last)) &&
+		!i915_request_completed(last));
 }
 
 /**
@@ -221,7 +224,7 @@ static void
 intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
 				   struct intel_engine_cs *engine)
 {
-	struct intel_context *ce = &ctx->engine[engine->id];
+	struct intel_context *ce = to_intel_context(ctx, engine);
 	u64 desc;
 
 	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (BIT(GEN8_CTX_ID_WIDTH)));
@@ -255,9 +258,7 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
 }
 
 static struct i915_priolist *
-lookup_priolist(struct intel_engine_cs *engine,
-		struct i915_priotree *pt,
-		int prio)
+lookup_priolist(struct intel_engine_cs *engine, int prio)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_priolist *p;
@@ -328,10 +329,10 @@ static void __unwind_incomplete_requests(struct intel_engine_cs *engine)
 	struct i915_priolist *uninitialized_var(p);
 	int last_prio = I915_PRIORITY_INVALID;
 
-	lockdep_assert_held(&engine->timeline->lock);
+	lockdep_assert_held(&engine->timeline.lock);
 
 	list_for_each_entry_safe_reverse(rq, rn,
-					 &engine->timeline->requests,
+					 &engine->timeline.requests,
 					 link) {
 		if (i915_request_completed(rq))
 			return;
@@ -342,10 +343,11 @@ static void __unwind_incomplete_requests(struct intel_engine_cs *engine)
 		GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
 		if (rq_prio(rq) != last_prio) {
 			last_prio = rq_prio(rq);
-			p = lookup_priolist(engine, &rq->priotree, last_prio);
+			p = lookup_priolist(engine, last_prio);
 		}
 
-		list_add(&rq->priotree.link, &p->requests);
+		GEM_BUG_ON(p->priority != rq_prio(rq));
+		list_add(&rq->sched.link, &p->requests);
 	}
 }
 
@@ -354,10 +356,13 @@ execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists)
 {
 	struct intel_engine_cs *engine =
 		container_of(execlists, typeof(*engine), execlists);
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
-	spin_lock_irq(&engine->timeline->lock);
 	__unwind_incomplete_requests(engine);
-	spin_unlock_irq(&engine->timeline->lock);
+
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
 static inline void
@@ -374,6 +379,19 @@ execlists_context_status_change(struct i915_request *rq, unsigned long status)
 				   status, rq);
 }
 
+inline void
+execlists_user_begin(struct intel_engine_execlists *execlists,
+		     const struct execlist_port *port)
+{
+	execlists_set_active_once(execlists, EXECLISTS_ACTIVE_USER);
+}
+
+inline void
+execlists_user_end(struct intel_engine_execlists *execlists)
+{
+	execlists_clear_active(execlists, EXECLISTS_ACTIVE_USER);
+}
+
 static inline void
 execlists_context_schedule_in(struct i915_request *rq)
 {
@@ -382,10 +400,11 @@ execlists_context_schedule_in(struct i915_request *rq)
 }
 
 static inline void
-execlists_context_schedule_out(struct i915_request *rq)
+execlists_context_schedule_out(struct i915_request *rq, unsigned long status)
 {
 	intel_engine_context_out(rq->engine);
-	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
+	execlists_context_status_change(rq, status);
+	trace_i915_request_out(rq);
 }
 
 static void
@@ -399,7 +418,7 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
-	struct intel_context *ce = &rq->ctx->engine[rq->engine->id];
+	struct intel_context *ce = to_intel_context(rq->ctx, rq->engine);
 	struct i915_hw_ppgtt *ppgtt =
 		rq->ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
 	u32 *reg_state = ce->lrc_reg_state;
@@ -454,10 +473,12 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 			desc = execlists_update_context(rq);
 			GEM_DEBUG_EXEC(port[n].context_id = upper_32_bits(desc));
 
-			GEM_TRACE("%s in[%d]:  ctx=%d.%d, seqno=%x, prio=%d\n",
+			GEM_TRACE("%s in[%d]:  ctx=%d.%d, global=%d (fence %llx:%d) (current %d), prio=%d\n",
 				  engine->name, n,
 				  port[n].context_id, count,
 				  rq->global_seqno,
+				  rq->fence.context, rq->fence.seqno,
+				  intel_engine_get_seqno(engine),
 				  rq_prio(rq));
 		} else {
 			GEM_BUG_ON(!n);
@@ -506,7 +527,7 @@ static void inject_preempt_context(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists *execlists = &engine->execlists;
 	struct intel_context *ce =
-		&engine->i915->preempt_context->engine[engine->id];
+		to_intel_context(engine->i915->preempt_context, engine);
 	unsigned int n;
 
 	GEM_BUG_ON(execlists->preempt_complete_status !=
@@ -535,7 +556,7 @@ static void inject_preempt_context(struct intel_engine_cs *engine)
 	execlists_set_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT);
 }
 
-static void execlists_dequeue(struct intel_engine_cs *engine)
+static bool __execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
@@ -545,6 +566,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	struct rb_node *rb;
 	bool submit = false;
 
+	lockdep_assert_held(&engine->timeline.lock);
+
 	/* Hardware submission is through 2 ports. Conceptually each port
 	 * has a (RING_START, RING_HEAD, RING_TAIL) tuple. RING_START is
 	 * static for a context, and unique to each, so we only execute
@@ -566,7 +589,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
-	spin_lock_irq(&engine->timeline->lock);
 	rb = execlists->first;
 	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
 
@@ -577,9 +599,11 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		 * know the next preemption status we see corresponds
 		 * to this ELSP update.
 		 */
+		GEM_BUG_ON(!execlists_is_active(execlists,
+						EXECLISTS_ACTIVE_USER));
 		GEM_BUG_ON(!port_count(&port[0]));
 		if (port_count(&port[0]) > 1)
-			goto unlock;
+			return false;
 
 		/*
 		 * If we write to ELSP a second time before the HW has had
@@ -589,11 +613,11 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		 * the HW to indicate that it has had a chance to respond.
 		 */
 		if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_HWACK))
-			goto unlock;
+			return false;
 
 		if (need_preempt(engine, last, execlists->queue_priority)) {
 			inject_preempt_context(engine);
-			goto unlock;
+			return false;
 		}
 
 		/*
@@ -618,7 +642,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		 * priorities of the ports haven't been switch.
 		 */
 		if (port_count(&port[1]))
-			goto unlock;
+			return false;
 
 		/*
 		 * WaIdleLiteRestore:bdw,skl
@@ -635,7 +659,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
-		list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) {
+		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
 			/*
 			 * Can we combine this request with the current port?
 			 * It has to be the same context/ringbuffer and not
@@ -655,7 +679,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 */
 				if (port == last_port) {
 					__list_del_many(&p->requests,
-							&rq->priotree.link);
+							&rq->sched.link);
 					goto done;
 				}
 
@@ -669,7 +693,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				if (ctx_single_port_submission(last->ctx) ||
 				    ctx_single_port_submission(rq->ctx)) {
 					__list_del_many(&p->requests,
-							&rq->priotree.link);
+							&rq->sched.link);
 					goto done;
 				}
 
@@ -682,7 +706,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				GEM_BUG_ON(port_isset(port));
 			}
 
-			INIT_LIST_HEAD(&rq->priotree.link);
+			INIT_LIST_HEAD(&rq->sched.link);
 			__i915_request_submit(rq);
 			trace_i915_request_in(rq, port_index(port, execlists));
 			last = rq;
@@ -695,8 +719,27 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
 	}
+
 done:
-	execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN;
+	/*
+	 * Here be a bit of magic! Or sleight-of-hand, whichever you prefer.
+	 *
+	 * We choose queue_priority such that if we add a request of greater
+	 * priority than this, we kick the submission tasklet to decide on
+	 * the right order of submitting the requests to hardware. We must
+	 * also be prepared to reorder requests as they are in-flight on the
+	 * HW. We derive the queue_priority then as the first "hole" in
+	 * the HW submission ports and if there are no available slots,
+	 * the priority of the lowest executing request, i.e. last.
+	 *
+	 * When we do receive a higher priority request ready to run from the
+	 * user, see queue_request(), the queue_priority is bumped to that
+	 * request triggering preemption on the next dequeue (or subsequent
+	 * interrupt for secondary ports).
+	 */
+	execlists->queue_priority =
+		port != execlists->port ? rq_prio(last) : INT_MIN;
+
 	execlists->first = rb;
 	if (submit)
 		port_assign(port, last);
@@ -704,13 +747,25 @@ done:
 	/* We must always keep the beast fed if we have work piled up */
 	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
 
-unlock:
-	spin_unlock_irq(&engine->timeline->lock);
+	/* Re-evaluate the executing context setup after each preemptive kick */
+	if (last)
+		execlists_user_begin(execlists, execlists->port);
+
+	return submit;
+}
 
-	if (submit) {
-		execlists_set_active(execlists, EXECLISTS_ACTIVE_USER);
+static void execlists_dequeue(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	unsigned long flags;
+	bool submit;
+
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	submit = __execlists_dequeue(engine);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
+
+	if (submit)
 		execlists_submit_ports(engine);
-	}
 
 	GEM_BUG_ON(port_isset(execlists->port) &&
 		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
@@ -725,19 +780,101 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
 	while (num_ports-- && port_isset(port)) {
 		struct i915_request *rq = port_request(port);
 
-		GEM_BUG_ON(!execlists->active);
-		intel_engine_context_out(rq->engine);
+		GEM_TRACE("%s:port%u global=%d (fence %llx:%d), (current %d)\n",
+			  rq->engine->name,
+			  (unsigned int)(port - execlists->port),
+			  rq->global_seqno,
+			  rq->fence.context, rq->fence.seqno,
+			  intel_engine_get_seqno(rq->engine));
 
-		execlists_context_status_change(rq,
-						i915_request_completed(rq) ?
-						INTEL_CONTEXT_SCHEDULE_OUT :
-						INTEL_CONTEXT_SCHEDULE_PREEMPTED);
+		GEM_BUG_ON(!execlists->active);
+		execlists_context_schedule_out(rq,
+					       i915_request_completed(rq) ?
+					       INTEL_CONTEXT_SCHEDULE_OUT :
+					       INTEL_CONTEXT_SCHEDULE_PREEMPTED);
 
 		i915_request_put(rq);
 
 		memset(port, 0, sizeof(*port));
 		port++;
 	}
+
+	execlists_user_end(execlists);
+}
+
+static void clear_gtiir(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	int i;
+
+	/*
+	 * Clear any pending interrupt state.
+	 *
+	 * We do it twice out of paranoia that some of the IIR are
+	 * double buffered, and so if we only reset it once there may
+	 * still be an interrupt pending.
+	 */
+	if (INTEL_GEN(dev_priv) >= 11) {
+		static const struct {
+			u8 bank;
+			u8 bit;
+		} gen11_gtiir[] = {
+			[RCS] = {0, GEN11_RCS0},
+			[BCS] = {0, GEN11_BCS},
+			[_VCS(0)] = {1, GEN11_VCS(0)},
+			[_VCS(1)] = {1, GEN11_VCS(1)},
+			[_VCS(2)] = {1, GEN11_VCS(2)},
+			[_VCS(3)] = {1, GEN11_VCS(3)},
+			[_VECS(0)] = {1, GEN11_VECS(0)},
+			[_VECS(1)] = {1, GEN11_VECS(1)},
+		};
+		unsigned long irqflags;
+
+		GEM_BUG_ON(engine->id >= ARRAY_SIZE(gen11_gtiir));
+
+		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+		for (i = 0; i < 2; i++) {
+			gen11_reset_one_iir(dev_priv,
+					    gen11_gtiir[engine->id].bank,
+					    gen11_gtiir[engine->id].bit);
+		}
+		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+	} else {
+		static const u8 gtiir[] = {
+			[RCS]  = 0,
+			[BCS]  = 0,
+			[VCS]  = 1,
+			[VCS2] = 1,
+			[VECS] = 3,
+		};
+
+		GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir));
+
+		for (i = 0; i < 2; i++) {
+			I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
+				   engine->irq_keep_mask);
+			POSTING_READ(GEN8_GT_IIR(gtiir[engine->id]));
+		}
+		GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) &
+			   engine->irq_keep_mask);
+	}
+}
+
+static void reset_irq(struct intel_engine_cs *engine)
+{
+	/* Mark all CS interrupts as complete */
+	smp_store_mb(engine->execlists.active, 0);
+	synchronize_hardirq(engine->i915->drm.irq);
+
+	clear_gtiir(engine);
+
+	/*
+	 * The port is checked prior to scheduling a tasklet, but
+	 * just in case we have suspended the tasklet to do the
+	 * wedging make sure that when it wakes, it decides there
+	 * is no work to do by clearing the irq_posted bit.
+	 */
+	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 }
 
 static void execlists_cancel_requests(struct intel_engine_cs *engine)
@@ -747,7 +884,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	struct rb_node *rb;
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	GEM_TRACE("%s current %d\n",
+		  engine->name, intel_engine_get_seqno(engine));
 
 	/*
 	 * Before we call engine->cancel_requests(), we should have exclusive
@@ -767,11 +905,12 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 
 	/* Cancel the requests on the HW and clear the ELSP tracker. */
 	execlists_cancel_port_requests(execlists);
+	reset_irq(engine);
 
-	spin_lock(&engine->timeline->lock);
+	spin_lock(&engine->timeline.lock);
 
 	/* Mark all executing requests as skipped. */
-	list_for_each_entry(rq, &engine->timeline->requests, link) {
+	list_for_each_entry(rq, &engine->timeline.requests, link) {
 		GEM_BUG_ON(!rq->global_seqno);
 		if (!i915_request_completed(rq))
 			dma_fence_set_error(&rq->fence, -EIO);
@@ -782,8 +921,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	while (rb) {
 		struct i915_priolist *p = to_priolist(rb);
 
-		list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) {
-			INIT_LIST_HEAD(&rq->priotree.link);
+		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
+			INIT_LIST_HEAD(&rq->sched.link);
 
 			dma_fence_set_error(&rq->fence, -EIO);
 			__i915_request_submit(rq);
@@ -803,18 +942,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	execlists->first = NULL;
 	GEM_BUG_ON(port_isset(execlists->port));
 
-	spin_unlock(&engine->timeline->lock);
-
-	/*
-	 * The port is checked prior to scheduling a tasklet, but
-	 * just in case we have suspended the tasklet to do the
-	 * wedging make sure that when it wakes, it decides there
-	 * is no work to do by clearing the irq_posted bit.
-	 */
-	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-
-	/* Mark all CS interrupts as complete */
-	execlists->active = 0;
+	spin_unlock(&engine->timeline.lock);
 
 	local_irq_restore(flags);
 }
@@ -827,7 +955,7 @@ static void execlists_submission_tasklet(unsigned long data)
 {
 	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
 	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct execlist_port * const port = execlists->port;
+	struct execlist_port *port = execlists->port;
 	struct drm_i915_private *dev_priv = engine->i915;
 	bool fw = false;
 
@@ -880,6 +1008,7 @@ static void execlists_submission_tasklet(unsigned long data)
 
 			head = execlists->csb_head;
 			tail = READ_ONCE(buf[write_idx]);
+			rmb(); /* Hopefully paired with a wmb() in HW */
 		}
 		GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
 			  engine->name,
@@ -954,10 +1083,13 @@ static void execlists_submission_tasklet(unsigned long data)
 							EXECLISTS_ACTIVE_USER));
 
 			rq = port_unpack(port, &count);
-			GEM_TRACE("%s out[0]: ctx=%d.%d, seqno=%x, prio=%d\n",
+			GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%d) (current %d), prio=%d\n",
 				  engine->name,
 				  port->context_id, count,
 				  rq ? rq->global_seqno : 0,
+				  rq ? rq->fence.context : 0,
+				  rq ? rq->fence.seqno : 0,
+				  intel_engine_get_seqno(engine),
 				  rq ? rq_prio(rq) : 0);
 
 			/* Check the context/desc id for this event matches */
@@ -965,28 +1097,43 @@ static void execlists_submission_tasklet(unsigned long data)
 
 			GEM_BUG_ON(count == 0);
 			if (--count == 0) {
+				/*
+				 * On the final event corresponding to the
+				 * submission of this context, we expect either
+				 * an element-switch event or a completion
+				 * event (and on completion, the active-idle
+				 * marker). No more preemptions, lite-restore
+				 * or otherwise.
+				 */
 				GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
 				GEM_BUG_ON(port_isset(&port[1]) &&
 					   !(status & GEN8_CTX_STATUS_ELEMENT_SWITCH));
+				GEM_BUG_ON(!port_isset(&port[1]) &&
+					   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
+
+				/*
+				 * We rely on the hardware being strongly
+				 * ordered, that the breadcrumb write is
+				 * coherent (visible from the CPU) before the
+				 * user interrupt and CSB is processed.
+				 */
 				GEM_BUG_ON(!i915_request_completed(rq));
-				execlists_context_schedule_out(rq);
-				trace_i915_request_out(rq);
+
+				execlists_context_schedule_out(rq,
+							       INTEL_CONTEXT_SCHEDULE_OUT);
 				i915_request_put(rq);
 
 				GEM_TRACE("%s completed ctx=%d\n",
 					  engine->name, port->context_id);
 
-				execlists_port_complete(execlists, port);
+				port = execlists_port_complete(execlists, port);
+				if (port_isset(port))
+					execlists_user_begin(execlists, port);
+				else
+					execlists_user_end(execlists);
 			} else {
 				port_set(port, port_pack(rq, count));
 			}
-
-			/* After the final element, the hw should be idle */
-			GEM_BUG_ON(port_count(port) == 0 &&
-				   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
-			if (port_count(port) == 0)
-				execlists_clear_active(execlists,
-						       EXECLISTS_ACTIVE_USER);
 		}
 
 		if (head != execlists->csb_head) {
@@ -1001,21 +1148,31 @@ static void execlists_submission_tasklet(unsigned long data)
 
 	if (fw)
 		intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
+
+	/* If the engine is now idle, so should be the flag; and vice versa. */
+	GEM_BUG_ON(execlists_is_active(&engine->execlists,
+				       EXECLISTS_ACTIVE_USER) ==
+		   !port_isset(engine->execlists.port));
 }
 
 static void queue_request(struct intel_engine_cs *engine,
-			  struct i915_priotree *pt,
+			  struct i915_sched_node *node,
 			  int prio)
 {
-	list_add_tail(&pt->link, &lookup_priolist(engine, pt, prio)->requests);
+	list_add_tail(&node->link,
+		      &lookup_priolist(engine, prio)->requests);
+}
+
+static void __submit_queue(struct intel_engine_cs *engine, int prio)
+{
+	engine->execlists.queue_priority = prio;
+	tasklet_hi_schedule(&engine->execlists.tasklet);
 }
 
 static void submit_queue(struct intel_engine_cs *engine, int prio)
 {
-	if (prio > engine->execlists.queue_priority) {
-		engine->execlists.queue_priority = prio;
-		tasklet_hi_schedule(&engine->execlists.tasklet);
-	}
+	if (prio > engine->execlists.queue_priority)
+		__submit_queue(engine, prio);
 }
 
 static void execlists_submit_request(struct i915_request *request)
@@ -1024,42 +1181,45 @@ static void execlists_submit_request(struct i915_request *request)
 	unsigned long flags;
 
 	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->timeline->lock, flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
-	queue_request(engine, &request->priotree, rq_prio(request));
+	queue_request(engine, &request->sched, rq_prio(request));
 	submit_queue(engine, rq_prio(request));
 
 	GEM_BUG_ON(!engine->execlists.first);
-	GEM_BUG_ON(list_empty(&request->priotree.link));
+	GEM_BUG_ON(list_empty(&request->sched.link));
 
-	spin_unlock_irqrestore(&engine->timeline->lock, flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
-static struct i915_request *pt_to_request(struct i915_priotree *pt)
+static struct i915_request *sched_to_request(struct i915_sched_node *node)
 {
-	return container_of(pt, struct i915_request, priotree);
+	return container_of(node, struct i915_request, sched);
 }
 
 static struct intel_engine_cs *
-pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked)
+sched_lock_engine(struct i915_sched_node *node, struct intel_engine_cs *locked)
 {
-	struct intel_engine_cs *engine = pt_to_request(pt)->engine;
+	struct intel_engine_cs *engine = sched_to_request(node)->engine;
 
 	GEM_BUG_ON(!locked);
 
 	if (engine != locked) {
-		spin_unlock(&locked->timeline->lock);
-		spin_lock(&engine->timeline->lock);
+		spin_unlock(&locked->timeline.lock);
+		spin_lock(&engine->timeline.lock);
 	}
 
 	return engine;
 }
 
-static void execlists_schedule(struct i915_request *request, int prio)
+static void execlists_schedule(struct i915_request *request,
+			       const struct i915_sched_attr *attr)
 {
-	struct intel_engine_cs *engine;
+	struct i915_priolist *uninitialized_var(pl);
+	struct intel_engine_cs *engine, *last;
 	struct i915_dependency *dep, *p;
 	struct i915_dependency stack;
+	const int prio = attr->priority;
 	LIST_HEAD(dfs);
 
 	GEM_BUG_ON(prio == I915_PRIORITY_INVALID);
@@ -1067,23 +1227,23 @@ static void execlists_schedule(struct i915_request *request, int prio)
 	if (i915_request_completed(request))
 		return;
 
-	if (prio <= READ_ONCE(request->priotree.priority))
+	if (prio <= READ_ONCE(request->sched.attr.priority))
 		return;
 
 	/* Need BKL in order to use the temporary link inside i915_dependency */
 	lockdep_assert_held(&request->i915->drm.struct_mutex);
 
-	stack.signaler = &request->priotree;
+	stack.signaler = &request->sched;
 	list_add(&stack.dfs_link, &dfs);
 
 	/*
 	 * Recursively bump all dependent priorities to match the new request.
 	 *
 	 * A naive approach would be to use recursion:
-	 * static void update_priorities(struct i915_priotree *pt, prio) {
-	 *	list_for_each_entry(dep, &pt->signalers_list, signal_link)
+	 * static void update_priorities(struct i915_sched_node *node, prio) {
+	 *	list_for_each_entry(dep, &node->signalers_list, signal_link)
 	 *		update_priorities(dep->signal, prio)
-	 *	queue_request(pt);
+	 *	queue_request(node);
 	 * }
 	 * but that may have unlimited recursion depth and so runs a very
 	 * real risk of overunning the kernel stack. Instead, we build
@@ -1095,7 +1255,7 @@ static void execlists_schedule(struct i915_request *request, int prio)
 	 * last element in the list is the request we must execute first.
 	 */
 	list_for_each_entry(dep, &dfs, dfs_link) {
-		struct i915_priotree *pt = dep->signaler;
+		struct i915_sched_node *node = dep->signaler;
 
 		/*
 		 * Within an engine, there can be no cycle, but we may
@@ -1103,14 +1263,14 @@ static void execlists_schedule(struct i915_request *request, int prio)
 		 * (redundant dependencies are not eliminated) and across
 		 * engines.
 		 */
-		list_for_each_entry(p, &pt->signalers_list, signal_link) {
+		list_for_each_entry(p, &node->signalers_list, signal_link) {
 			GEM_BUG_ON(p == dep); /* no cycles! */
 
-			if (i915_priotree_signaled(p->signaler))
+			if (i915_sched_node_signaled(p->signaler))
 				continue;
 
-			GEM_BUG_ON(p->signaler->priority < pt->priority);
-			if (prio > READ_ONCE(p->signaler->priority))
+			GEM_BUG_ON(p->signaler->attr.priority < node->attr.priority);
+			if (prio > READ_ONCE(p->signaler->attr.priority))
 				list_move_tail(&p->dfs_link, &dfs);
 		}
 	}
@@ -1121,37 +1281,45 @@ static void execlists_schedule(struct i915_request *request, int prio)
 	 * execlists_submit_request()), we can set our own priority and skip
 	 * acquiring the engine locks.
 	 */
-	if (request->priotree.priority == I915_PRIORITY_INVALID) {
-		GEM_BUG_ON(!list_empty(&request->priotree.link));
-		request->priotree.priority = prio;
+	if (request->sched.attr.priority == I915_PRIORITY_INVALID) {
+		GEM_BUG_ON(!list_empty(&request->sched.link));
+		request->sched.attr = *attr;
 		if (stack.dfs_link.next == stack.dfs_link.prev)
 			return;
 		__list_del_entry(&stack.dfs_link);
 	}
 
+	last = NULL;
 	engine = request->engine;
-	spin_lock_irq(&engine->timeline->lock);
+	spin_lock_irq(&engine->timeline.lock);
 
 	/* Fifo and depth-first replacement ensure our deps execute before us */
 	list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
-		struct i915_priotree *pt = dep->signaler;
+		struct i915_sched_node *node = dep->signaler;
 
 		INIT_LIST_HEAD(&dep->dfs_link);
 
-		engine = pt_lock_engine(pt, engine);
+		engine = sched_lock_engine(node, engine);
 
-		if (prio <= pt->priority)
+		if (prio <= node->attr.priority)
 			continue;
 
-		pt->priority = prio;
-		if (!list_empty(&pt->link)) {
-			__list_del_entry(&pt->link);
-			queue_request(engine, pt, prio);
+		node->attr.priority = prio;
+		if (!list_empty(&node->link)) {
+			if (last != engine) {
+				pl = lookup_priolist(engine, prio);
+				last = engine;
+			}
+			GEM_BUG_ON(pl->priority != prio);
+			list_move_tail(&node->link, &pl->requests);
 		}
-		submit_queue(engine, prio);
+
+		if (prio > engine->execlists.queue_priority &&
+		    i915_sw_fence_done(&sched_to_request(node)->submit))
+			__submit_queue(engine, prio);
 	}
 
-	spin_unlock_irq(&engine->timeline->lock);
+	spin_unlock_irq(&engine->timeline.lock);
 }
 
 static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
@@ -1181,7 +1349,7 @@ static struct intel_ring *
 execlists_context_pin(struct intel_engine_cs *engine,
 		      struct i915_gem_context *ctx)
 {
-	struct intel_context *ce = &ctx->engine[engine->id];
+	struct intel_context *ce = to_intel_context(ctx, engine);
 	void *vaddr;
 	int ret;
 
@@ -1215,6 +1383,7 @@ execlists_context_pin(struct intel_engine_cs *engine,
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
 		i915_ggtt_offset(ce->ring->vma);
+	ce->lrc_reg_state[CTX_RING_HEAD+1] = ce->ring->head;
 
 	ce->state->obj->pin_global++;
 	i915_gem_context_get(ctx);
@@ -1233,7 +1402,7 @@ err:
 static void execlists_context_unpin(struct intel_engine_cs *engine,
 				    struct i915_gem_context *ctx)
 {
-	struct intel_context *ce = &ctx->engine[engine->id];
+	struct intel_context *ce = to_intel_context(ctx, engine);
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
 	GEM_BUG_ON(ce->pin_count == 0);
@@ -1252,8 +1421,8 @@ static void execlists_context_unpin(struct intel_engine_cs *engine,
 
 static int execlists_request_alloc(struct i915_request *request)
 {
-	struct intel_engine_cs *engine = request->engine;
-	struct intel_context *ce = &request->ctx->engine[engine->id];
+	struct intel_context *ce =
+		to_intel_context(request->ctx, request->engine);
 	int ret;
 
 	GEM_BUG_ON(!ce->pin_count);
@@ -1513,6 +1682,8 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 		return -EINVAL;
 
 	switch (INTEL_GEN(engine->i915)) {
+	case 11:
+		return 0;
 	case 10:
 		wa_bb_fn[0] = gen10_init_indirectctx_bb;
 		wa_bb_fn[1] = NULL;
@@ -1565,14 +1736,6 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 	return ret;
 }
 
-static u8 gtiir[] = {
-	[RCS] = 0,
-	[BCS] = 0,
-	[VCS] = 1,
-	[VCS2] = 1,
-	[VECS] = 3,
-};
-
 static void enable_execlists(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
@@ -1632,6 +1795,8 @@ static int gen8_init_render_ring(struct intel_engine_cs *engine)
 	if (ret)
 		return ret;
 
+	intel_whitelist_workarounds_apply(engine);
+
 	/* We need to disable the AsyncFlip performance optimisations in order
 	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
 	 * programmed to '1' on all products.
@@ -1642,7 +1807,7 @@ static int gen8_init_render_ring(struct intel_engine_cs *engine)
 
 	I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	return init_workarounds_ring(engine);
+	return 0;
 }
 
 static int gen9_init_render_ring(struct intel_engine_cs *engine)
@@ -1653,49 +1818,25 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine)
 	if (ret)
 		return ret;
 
-	return init_workarounds_ring(engine);
-}
-
-static void reset_irq(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int i;
-
-	GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir));
-
-	/*
-	 * Clear any pending interrupt state.
-	 *
-	 * We do it twice out of paranoia that some of the IIR are double
-	 * buffered, and if we only reset it once there may still be
-	 * an interrupt pending.
-	 */
-	for (i = 0; i < 2; i++) {
-		I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
-			   GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift);
-		POSTING_READ(GEN8_GT_IIR(gtiir[engine->id]));
-	}
-	GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) &
-		   (GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift));
+	intel_whitelist_workarounds_apply(engine);
 
-	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
+	return 0;
 }
 
 static void reset_common_ring(struct intel_engine_cs *engine,
 			      struct i915_request *request)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct intel_context *ce;
 	unsigned long flags;
+	u32 *regs;
 
-	GEM_TRACE("%s seqno=%x\n",
-		  engine->name, request ? request->global_seqno : 0);
+	GEM_TRACE("%s request global=%x, current=%d\n",
+		  engine->name, request ? request->global_seqno : 0,
+		  intel_engine_get_seqno(engine));
 
 	/* See execlists_cancel_requests() for the irq/spinlock split. */
 	local_irq_save(flags);
 
-	reset_irq(engine);
-
 	/*
 	 * Catch up with any missed context-switch interrupts.
 	 *
@@ -1706,14 +1847,12 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 	 * requests were completed.
 	 */
 	execlists_cancel_port_requests(execlists);
+	reset_irq(engine);
 
 	/* Push back any incomplete requests for replay after the reset. */
-	spin_lock(&engine->timeline->lock);
+	spin_lock(&engine->timeline.lock);
 	__unwind_incomplete_requests(engine);
-	spin_unlock(&engine->timeline->lock);
-
-	/* Mark all CS interrupts as complete */
-	execlists->active = 0;
+	spin_unlock(&engine->timeline.lock);
 
 	local_irq_restore(flags);
 
@@ -1739,14 +1878,24 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 	 * future request will be after userspace has had the opportunity
 	 * to recreate its own state.
 	 */
-	ce = &request->ctx->engine[engine->id];
-	execlists_init_reg_state(ce->lrc_reg_state,
-				 request->ctx, engine, ce->ring);
+	regs = to_intel_context(request->ctx, engine)->lrc_reg_state;
+	if (engine->default_state) {
+		void *defaults;
+
+		defaults = i915_gem_object_pin_map(engine->default_state,
+						   I915_MAP_WB);
+		if (!IS_ERR(defaults)) {
+			memcpy(regs, /* skip restoring the vanilla PPHWSP */
+			       defaults + LRC_STATE_PN * PAGE_SIZE,
+			       engine->context_size - PAGE_SIZE);
+			i915_gem_object_unpin_map(engine->default_state);
+		}
+	}
+	execlists_init_reg_state(regs, request->ctx, engine, request->ring);
 
 	/* Move the RING_HEAD onto the breadcrumb, past the hanging batch */
-	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
-		i915_ggtt_offset(ce->ring->vma);
-	ce->lrc_reg_state[CTX_RING_HEAD+1] = request->postfix;
+	regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma);
+	regs[CTX_RING_HEAD + 1] = request->postfix;
 
 	request->ring->head = request->postfix;
 	intel_ring_update_space(request->ring);
@@ -1807,7 +1956,7 @@ static int gen8_emit_bb_start(struct i915_request *rq,
 		rq->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine);
 	}
 
-	cs = intel_ring_begin(rq, 4);
+	cs = intel_ring_begin(rq, 6);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
@@ -1836,6 +1985,9 @@ static int gen8_emit_bb_start(struct i915_request *rq,
 		(flags & I915_DISPATCH_RS ? MI_BATCH_RESOURCE_STREAMER : 0);
 	*cs++ = lower_32_bits(offset);
 	*cs++ = upper_32_bits(offset);
+
+	*cs++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+	*cs++ = MI_NOOP;
 	intel_ring_advance(rq, cs);
 
 	return 0;
@@ -1978,7 +2130,7 @@ static void gen8_emit_breadcrumb(struct i915_request *request, u32 *cs)
 	cs = gen8_emit_ggtt_write(cs, request->global_seqno,
 				  intel_hws_seqno_address(request->engine));
 	*cs++ = MI_USER_INTERRUPT;
-	*cs++ = MI_NOOP;
+	*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
 	request->tail = intel_ring_offset(request, cs);
 	assert_ring_tail_valid(request->ring, request->tail);
 
@@ -1994,7 +2146,7 @@ static void gen8_emit_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 	cs = gen8_emit_ggtt_write_rcs(cs, request->global_seqno,
 				      intel_hws_seqno_address(request->engine));
 	*cs++ = MI_USER_INTERRUPT;
-	*cs++ = MI_NOOP;
+	*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
 	request->tail = intel_ring_offset(request, cs);
 	assert_ring_tail_valid(request->ring, request->tail);
 
@@ -2006,7 +2158,7 @@ static int gen8_init_rcs_context(struct i915_request *rq)
 {
 	int ret;
 
-	ret = intel_ring_workarounds_emit(rq);
+	ret = intel_ctx_workarounds_emit(rq);
 	if (ret)
 		return ret;
 
@@ -2066,11 +2218,13 @@ static void execlists_set_default_submission(struct intel_engine_cs *engine)
 	engine->unpark = NULL;
 
 	engine->flags |= I915_ENGINE_SUPPORTS_STATS;
+	if (engine->i915->preempt_context)
+		engine->flags |= I915_ENGINE_HAS_PREEMPTION;
 
 	engine->i915->caps.scheduler =
 		I915_SCHEDULER_CAP_ENABLED |
 		I915_SCHEDULER_CAP_PRIORITY;
-	if (engine->i915->preempt_context)
+	if (intel_engine_has_preemption(engine))
 		engine->i915->caps.scheduler |= I915_SCHEDULER_CAP_PREEMPTION;
 }
 
@@ -2109,7 +2263,20 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 static inline void
 logical_ring_default_irqs(struct intel_engine_cs *engine)
 {
-	unsigned shift = engine->irq_shift;
+	unsigned int shift = 0;
+
+	if (INTEL_GEN(engine->i915) < 11) {
+		const u8 irq_shifts[] = {
+			[RCS]  = GEN8_RCS_IRQ_SHIFT,
+			[BCS]  = GEN8_BCS_IRQ_SHIFT,
+			[VCS]  = GEN8_VCS1_IRQ_SHIFT,
+			[VCS2] = GEN8_VCS2_IRQ_SHIFT,
+			[VECS] = GEN8_VECS_IRQ_SHIFT,
+		};
+
+		shift = irq_shifts[engine->id];
+	}
+
 	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift;
 	engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift;
 }
@@ -2165,9 +2332,13 @@ static int logical_ring_init(struct intel_engine_cs *engine)
 	}
 
 	engine->execlists.preempt_complete_status = ~0u;
-	if (engine->i915->preempt_context)
+	if (engine->i915->preempt_context) {
+		struct intel_context *ce =
+			to_intel_context(engine->i915->preempt_context, engine);
+
 		engine->execlists.preempt_complete_status =
-			upper_32_bits(engine->i915->preempt_context->engine[engine->id].lrc_desc);
+			upper_32_bits(ce->lrc_desc);
+	}
 
 	return 0;
 
@@ -2421,8 +2592,10 @@ populate_lr_context(struct i915_gem_context *ctx,
 
 		defaults = i915_gem_object_pin_map(engine->default_state,
 						   I915_MAP_WB);
-		if (IS_ERR(defaults))
-			return PTR_ERR(defaults);
+		if (IS_ERR(defaults)) {
+			ret = PTR_ERR(defaults);
+			goto err_unpin_ctx;
+		}
 
 		memcpy(vaddr + start, defaults + start, engine->context_size);
 		i915_gem_object_unpin_map(engine->default_state);
@@ -2440,19 +2613,20 @@ populate_lr_context(struct i915_gem_context *ctx,
 			_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
 					   CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT);
 
+err_unpin_ctx:
 	i915_gem_object_unpin_map(ctx_obj);
-
-	return 0;
+	return ret;
 }
 
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 					    struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_object *ctx_obj;
-	struct intel_context *ce = &ctx->engine[engine->id];
+	struct intel_context *ce = to_intel_context(ctx, engine);
 	struct i915_vma *vma;
 	uint32_t context_size;
 	struct intel_ring *ring;
+	struct i915_timeline *timeline;
 	int ret;
 
 	if (ce->state)
@@ -2468,8 +2642,8 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 
 	ctx_obj = i915_gem_object_create(ctx->i915, context_size);
 	if (IS_ERR(ctx_obj)) {
-		DRM_DEBUG_DRIVER("Alloc LRC backing obj failed.\n");
-		return PTR_ERR(ctx_obj);
+		ret = PTR_ERR(ctx_obj);
+		goto error_deref_obj;
 	}
 
 	vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL);
@@ -2478,7 +2652,14 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 		goto error_deref_obj;
 	}
 
-	ring = intel_engine_create_ring(engine, ctx->ring_size);
+	timeline = i915_timeline_create(ctx->i915, ctx->name);
+	if (IS_ERR(timeline)) {
+		ret = PTR_ERR(timeline);
+		goto error_deref_obj;
+	}
+
+	ring = intel_engine_create_ring(engine, timeline, ctx->ring_size);
+	i915_timeline_put(timeline);
 	if (IS_ERR(ring)) {
 		ret = PTR_ERR(ring);
 		goto error_deref_obj;
@@ -2520,7 +2701,8 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv)
 	 */
 	list_for_each_entry(ctx, &dev_priv->contexts.list, link) {
 		for_each_engine(engine, dev_priv, id) {
-			struct intel_context *ce = &ctx->engine[engine->id];
+			struct intel_context *ce =
+				to_intel_context(ctx, engine);
 			u32 *reg;
 
 			if (!ce->state)
@@ -2542,3 +2724,7 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv)
 		}
 	}
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/intel_lrc.c"
+#endif
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 59d7b86012e9..4ec7d8dd13c8 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -108,7 +108,7 @@ static inline uint64_t
 intel_lr_context_descriptor(struct i915_gem_context *ctx,
 			    struct intel_engine_cs *engine)
 {
-	return ctx->engine[engine->id].lrc_desc;
+	return to_intel_context(ctx, engine)->lrc_desc;
 }
 
 #endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index d35d2d50f595..e125d16a1aa7 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -326,7 +326,8 @@ static void intel_enable_lvds(struct intel_encoder *encoder,
 
 	I915_WRITE(PP_CONTROL(0), I915_READ(PP_CONTROL(0)) | PANEL_POWER_ON);
 	POSTING_READ(lvds_encoder->reg);
-	if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 1000))
+
+	if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 5000))
 		DRM_ERROR("timed out waiting for panel to power on\n");
 
 	intel_panel_enable_backlight(pipe_config, conn_state);
@@ -573,6 +574,36 @@ exit:
 	return NOTIFY_OK;
 }
 
+static int
+intel_lvds_connector_register(struct drm_connector *connector)
+{
+	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
+	int ret;
+
+	ret = intel_connector_register(connector);
+	if (ret)
+		return ret;
+
+	lvds->lid_notifier.notifier_call = intel_lid_notify;
+	if (acpi_lid_notifier_register(&lvds->lid_notifier)) {
+		DRM_DEBUG_KMS("lid notifier registration failed\n");
+		lvds->lid_notifier.notifier_call = NULL;
+	}
+
+	return 0;
+}
+
+static void
+intel_lvds_connector_unregister(struct drm_connector *connector)
+{
+	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
+
+	if (lvds->lid_notifier.notifier_call)
+		acpi_lid_notifier_unregister(&lvds->lid_notifier);
+
+	intel_connector_unregister(connector);
+}
+
 /**
  * intel_lvds_destroy - unregister and free LVDS structures
  * @connector: connector to free
@@ -585,9 +616,6 @@ static void intel_lvds_destroy(struct drm_connector *connector)
 	struct intel_lvds_connector *lvds_connector =
 		to_lvds_connector(connector);
 
-	if (lvds_connector->lid_notifier.notifier_call)
-		acpi_lid_notifier_unregister(&lvds_connector->lid_notifier);
-
 	if (!IS_ERR_OR_NULL(lvds_connector->base.edid))
 		kfree(lvds_connector->base.edid);
 
@@ -608,8 +636,8 @@ static const struct drm_connector_funcs intel_lvds_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_get_property = intel_digital_connector_atomic_get_property,
 	.atomic_set_property = intel_digital_connector_atomic_set_property,
-	.late_register = intel_connector_register,
-	.early_unregister = intel_connector_unregister,
+	.late_register = intel_lvds_connector_register,
+	.early_unregister = intel_lvds_connector_unregister,
 	.destroy = intel_lvds_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
@@ -826,6 +854,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "D525MW"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Radiant P845",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Radiant Systems Inc"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P845"),
+		},
+	},
 
 	{ }	/* terminating entry */
 };
@@ -1149,12 +1185,6 @@ out:
 
 	lvds_encoder->a3_power = lvds & LVDS_A3_POWER_MASK;
 
-	lvds_connector->lid_notifier.notifier_call = intel_lid_notify;
-	if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) {
-		DRM_DEBUG_KMS("lid notifier registration failed\n");
-		lvds_connector->lid_notifier.notifier_call = NULL;
-	}
-
 	return;
 
 failed:
diff --git a/drivers/gpu/drm/i915/intel_mocs.c b/drivers/gpu/drm/i915/intel_mocs.c
index c0b34b7943b9..9f0bd6a4cb79 100644
--- a/drivers/gpu/drm/i915/intel_mocs.c
+++ b/drivers/gpu/drm/i915/intel_mocs.c
@@ -178,7 +178,8 @@ static bool get_mocs_settings(struct drm_i915_private *dev_priv,
 {
 	bool result = false;
 
-	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv) ||
+	    IS_ICELAKE(dev_priv)) {
 		table->size  = ARRAY_SIZE(skylake_mocs_table);
 		table->table = skylake_mocs_table;
 		result = true;
@@ -217,6 +218,8 @@ static i915_reg_t mocs_register(enum intel_engine_id engine_id, int index)
 		return GEN9_VEBOX_MOCS(index);
 	case VCS2:
 		return GEN9_MFX1_MOCS(index);
+	case VCS3:
+		return GEN11_MFX2_MOCS(index);
 	default:
 		MISSING_CASE(engine_id);
 		return INVALID_MMIO_REG;
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 36671a937fa4..c2f10d899329 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -807,6 +807,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 		ret = PTR_ERR(vma);
 		goto out_pin_section;
 	}
+	intel_fb_obj_flush(new_bo, ORIGIN_DIRTYFB);
 
 	ret = i915_vma_put_fence(vma);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c
index 1f5cd572a7ff..39a4e4edda07 100644
--- a/drivers/gpu/drm/i915/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/intel_pipe_crc.c
@@ -569,7 +569,8 @@ unlock:
 static int ivb_pipe_crc_ctl_reg(struct drm_i915_private *dev_priv,
 				enum pipe pipe,
 				enum intel_pipe_crc_source *source,
-				uint32_t *val)
+				uint32_t *val,
+				bool set_wa)
 {
 	if (*source == INTEL_PIPE_CRC_SOURCE_AUTO)
 		*source = INTEL_PIPE_CRC_SOURCE_PF;
@@ -582,7 +583,7 @@ static int ivb_pipe_crc_ctl_reg(struct drm_i915_private *dev_priv,
 		*val = PIPE_CRC_ENABLE | PIPE_CRC_SOURCE_SPRITE_IVB;
 		break;
 	case INTEL_PIPE_CRC_SOURCE_PF:
-		if ((IS_HASWELL(dev_priv) ||
+		if (set_wa && (IS_HASWELL(dev_priv) ||
 		     IS_BROADWELL(dev_priv)) && pipe == PIPE_A)
 			hsw_pipe_A_crc_wa(dev_priv, true);
 
@@ -600,7 +601,8 @@ static int ivb_pipe_crc_ctl_reg(struct drm_i915_private *dev_priv,
 
 static int get_new_crc_ctl_reg(struct drm_i915_private *dev_priv,
 			       enum pipe pipe,
-			       enum intel_pipe_crc_source *source, u32 *val)
+			       enum intel_pipe_crc_source *source, u32 *val,
+			       bool set_wa)
 {
 	if (IS_GEN2(dev_priv))
 		return i8xx_pipe_crc_ctl_reg(source, val);
@@ -611,7 +613,7 @@ static int get_new_crc_ctl_reg(struct drm_i915_private *dev_priv,
 	else if (IS_GEN5(dev_priv) || IS_GEN6(dev_priv))
 		return ilk_pipe_crc_ctl_reg(source, val);
 	else
-		return ivb_pipe_crc_ctl_reg(dev_priv, pipe, source, val);
+		return ivb_pipe_crc_ctl_reg(dev_priv, pipe, source, val, set_wa);
 }
 
 static int pipe_crc_set_source(struct drm_i915_private *dev_priv,
@@ -636,7 +638,7 @@ static int pipe_crc_set_source(struct drm_i915_private *dev_priv,
 		return -EIO;
 	}
 
-	ret = get_new_crc_ctl_reg(dev_priv, pipe, &source, &val);
+	ret = get_new_crc_ctl_reg(dev_priv, pipe, &source, &val, true);
 	if (ret != 0)
 		goto out;
 
@@ -764,13 +766,12 @@ display_crc_ctl_parse_object(const char *buf, enum intel_pipe_crc_object *o)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(pipe_crc_objects); i++)
-		if (!strcmp(buf, pipe_crc_objects[i])) {
-			*o = i;
-			return 0;
-		}
+	i = match_string(pipe_crc_objects, ARRAY_SIZE(pipe_crc_objects), buf);
+	if (i < 0)
+		return i;
 
-	return -EINVAL;
+	*o = i;
+	return 0;
 }
 
 static int display_crc_ctl_parse_pipe(struct drm_i915_private *dev_priv,
@@ -796,13 +797,12 @@ display_crc_ctl_parse_source(const char *buf, enum intel_pipe_crc_source *s)
 		return 0;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(pipe_crc_sources); i++)
-		if (!strcmp(buf, pipe_crc_sources[i])) {
-			*s = i;
-			return 0;
-		}
+	i = match_string(pipe_crc_sources, ARRAY_SIZE(pipe_crc_sources), buf);
+	if (i < 0)
+		return i;
 
-	return -EINVAL;
+	*s = i;
+	return 0;
 }
 
 static int display_crc_ctl_parse(struct drm_i915_private *dev_priv,
@@ -916,7 +916,7 @@ int intel_pipe_crc_create(struct drm_minor *minor)
 int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
 			      size_t *values_cnt)
 {
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[crtc->index];
 	enum intel_display_power_domain power_domain;
 	enum intel_pipe_crc_source source;
@@ -934,10 +934,11 @@ int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
 		return -EIO;
 	}
 
-	ret = get_new_crc_ctl_reg(dev_priv, crtc->index, &source, &val);
+	ret = get_new_crc_ctl_reg(dev_priv, crtc->index, &source, &val, true);
 	if (ret != 0)
 		goto out;
 
+	pipe_crc->source = source;
 	I915_WRITE(PIPE_CRC_CTL(crtc->index), val);
 	POSTING_READ(PIPE_CRC_CTL(crtc->index));
 
@@ -959,3 +960,39 @@ out:
 
 	return ret;
 }
+
+void intel_crtc_enable_pipe_crc(struct intel_crtc *intel_crtc)
+{
+	struct drm_crtc *crtc = &intel_crtc->base;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[crtc->index];
+	u32 val = 0;
+
+	if (!crtc->crc.opened)
+		return;
+
+	if (get_new_crc_ctl_reg(dev_priv, crtc->index, &pipe_crc->source, &val, false) < 0)
+		return;
+
+	/* Don't need pipe_crc->lock here, IRQs are not generated. */
+	pipe_crc->skipped = 0;
+
+	I915_WRITE(PIPE_CRC_CTL(crtc->index), val);
+	POSTING_READ(PIPE_CRC_CTL(crtc->index));
+}
+
+void intel_crtc_disable_pipe_crc(struct intel_crtc *intel_crtc)
+{
+	struct drm_crtc *crtc = &intel_crtc->base;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[crtc->index];
+
+	/* Swallow crc's until we stop generating them. */
+	spin_lock_irq(&pipe_crc->lock);
+	pipe_crc->skipped = INT_MIN;
+	spin_unlock_irq(&pipe_crc->lock);
+
+	I915_WRITE(PIPE_CRC_CTL(crtc->index), 0);
+	POSTING_READ(PIPE_CRC_CTL(crtc->index));
+	synchronize_irq(dev_priv->drm.irq);
+}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b8da4dcdd584..b85229e153c4 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3567,6 +3567,23 @@ bool ilk_disable_lp_wm(struct drm_device *dev)
 	return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL);
 }
 
+static u8 intel_enabled_dbuf_slices_num(struct drm_i915_private *dev_priv)
+{
+	u8 enabled_slices;
+
+	/* Slice 1 will always be enabled */
+	enabled_slices = 1;
+
+	/* Gen prior to GEN11 have only one DBuf slice */
+	if (INTEL_GEN(dev_priv) < 11)
+		return enabled_slices;
+
+	if (I915_READ(DBUF_CTL_S2) & DBUF_POWER_STATE)
+		enabled_slices++;
+
+	return enabled_slices;
+}
+
 /*
  * FIXME: We still don't have the proper code detect if we need to apply the WA,
  * so assume we'll always need it in order to avoid underruns.
@@ -3754,9 +3771,42 @@ bool intel_can_enable_sagv(struct drm_atomic_state *state)
 	return true;
 }
 
+static unsigned int intel_get_ddb_size(struct drm_i915_private *dev_priv,
+				       const struct intel_crtc_state *cstate,
+				       const unsigned int total_data_rate,
+				       const int num_active,
+				       struct skl_ddb_allocation *ddb)
+{
+	const struct drm_display_mode *adjusted_mode;
+	u64 total_data_bw;
+	u16 ddb_size = INTEL_INFO(dev_priv)->ddb_size;
+
+	WARN_ON(ddb_size == 0);
+
+	if (INTEL_GEN(dev_priv) < 11)
+		return ddb_size - 4; /* 4 blocks for bypass path allocation */
+
+	adjusted_mode = &cstate->base.adjusted_mode;
+	total_data_bw = (u64)total_data_rate * drm_mode_vrefresh(adjusted_mode);
+
+	/*
+	 * 12GB/s is maximum BW supported by single DBuf slice.
+	 */
+	if (total_data_bw >= GBps(12) || num_active > 1) {
+		ddb->enabled_slices = 2;
+	} else {
+		ddb->enabled_slices = 1;
+		ddb_size /= 2;
+	}
+
+	return ddb_size;
+}
+
 static void
 skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
 				   const struct intel_crtc_state *cstate,
+				   const unsigned int total_data_rate,
+				   struct skl_ddb_allocation *ddb,
 				   struct skl_ddb_entry *alloc, /* out */
 				   int *num_active /* out */)
 {
@@ -3779,11 +3829,8 @@ skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
 	else
 		*num_active = hweight32(dev_priv->active_crtcs);
 
-	ddb_size = INTEL_INFO(dev_priv)->ddb_size;
-	WARN_ON(ddb_size == 0);
-
-	if (INTEL_GEN(dev_priv) < 11)
-		ddb_size -= 4; /* 4 blocks for bypass path allocation */
+	ddb_size = intel_get_ddb_size(dev_priv, cstate, total_data_rate,
+				      *num_active, ddb);
 
 	/*
 	 * If the state doesn't change the active CRTC's, then there's
@@ -3817,14 +3864,64 @@ static unsigned int skl_cursor_allocation(int num_active)
 	return 8;
 }
 
-static void skl_ddb_entry_init_from_hw(struct skl_ddb_entry *entry, u32 reg)
+static void skl_ddb_entry_init_from_hw(struct drm_i915_private *dev_priv,
+				       struct skl_ddb_entry *entry, u32 reg)
 {
-	entry->start = reg & 0x3ff;
-	entry->end = (reg >> 16) & 0x3ff;
+	u16 mask;
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		mask = ICL_DDB_ENTRY_MASK;
+	else
+		mask = SKL_DDB_ENTRY_MASK;
+	entry->start = reg & mask;
+	entry->end = (reg >> DDB_ENTRY_END_SHIFT) & mask;
+
 	if (entry->end)
 		entry->end += 1;
 }
 
+static void
+skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv,
+			   const enum pipe pipe,
+			   const enum plane_id plane_id,
+			   struct skl_ddb_allocation *ddb /* out */)
+{
+	u32 val, val2 = 0;
+	int fourcc, pixel_format;
+
+	/* Cursor doesn't support NV12/planar, so no extra calculation needed */
+	if (plane_id == PLANE_CURSOR) {
+		val = I915_READ(CUR_BUF_CFG(pipe));
+		skl_ddb_entry_init_from_hw(dev_priv,
+					   &ddb->plane[pipe][plane_id], val);
+		return;
+	}
+
+	val = I915_READ(PLANE_CTL(pipe, plane_id));
+
+	/* No DDB allocated for disabled planes */
+	if (!(val & PLANE_CTL_ENABLE))
+		return;
+
+	pixel_format = val & PLANE_CTL_FORMAT_MASK;
+	fourcc = skl_format_to_fourcc(pixel_format,
+				      val & PLANE_CTL_ORDER_RGBX,
+				      val & PLANE_CTL_ALPHA_MASK);
+
+	val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
+	val2 = I915_READ(PLANE_NV12_BUF_CFG(pipe, plane_id));
+
+	if (fourcc == DRM_FORMAT_NV12) {
+		skl_ddb_entry_init_from_hw(dev_priv,
+					   &ddb->plane[pipe][plane_id], val2);
+		skl_ddb_entry_init_from_hw(dev_priv,
+					   &ddb->uv_plane[pipe][plane_id], val);
+	} else {
+		skl_ddb_entry_init_from_hw(dev_priv,
+					   &ddb->plane[pipe][plane_id], val);
+	}
+}
+
 void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 			  struct skl_ddb_allocation *ddb /* out */)
 {
@@ -3832,6 +3929,8 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 
 	memset(ddb, 0, sizeof(*ddb));
 
+	ddb->enabled_slices = intel_enabled_dbuf_slices_num(dev_priv);
+
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
 		enum intel_display_power_domain power_domain;
 		enum plane_id plane_id;
@@ -3841,16 +3940,9 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 		if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 			continue;
 
-		for_each_plane_id_on_crtc(crtc, plane_id) {
-			u32 val;
-
-			if (plane_id != PLANE_CURSOR)
-				val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
-			else
-				val = I915_READ(CUR_BUF_CFG(pipe));
-
-			skl_ddb_entry_init_from_hw(&ddb->plane[pipe][plane_id], val);
-		}
+		for_each_plane_id_on_crtc(crtc, plane_id)
+			skl_ddb_get_hw_plane_state(dev_priv, pipe,
+						   plane_id, ddb);
 
 		intel_display_power_put(dev_priv, power_domain);
 	}
@@ -4009,9 +4101,9 @@ int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 static unsigned int
 skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 			     const struct drm_plane_state *pstate,
-			     int y)
+			     const int plane)
 {
-	struct intel_plane *plane = to_intel_plane(pstate->plane);
+	struct intel_plane *intel_plane = to_intel_plane(pstate->plane);
 	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
 	uint32_t data_rate;
 	uint32_t width = 0, height = 0;
@@ -4025,9 +4117,9 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 	fb = pstate->fb;
 	format = fb->format->format;
 
-	if (plane->id == PLANE_CURSOR)
+	if (intel_plane->id == PLANE_CURSOR)
 		return 0;
-	if (y && format != DRM_FORMAT_NV12)
+	if (plane == 1 && format != DRM_FORMAT_NV12)
 		return 0;
 
 	/*
@@ -4038,19 +4130,14 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 	width = drm_rect_width(&intel_pstate->base.src) >> 16;
 	height = drm_rect_height(&intel_pstate->base.src) >> 16;
 
-	/* for planar format */
-	if (format == DRM_FORMAT_NV12) {
-		if (y)  /* y-plane data rate */
-			data_rate = width * height *
-				fb->format->cpp[0];
-		else    /* uv-plane data rate */
-			data_rate = (width / 2) * (height / 2) *
-				fb->format->cpp[1];
-	} else {
-		/* for packed formats */
-		data_rate = width * height * fb->format->cpp[0];
+	/* UV plane does 1/2 pixel sub-sampling */
+	if (plane == 1 && format == DRM_FORMAT_NV12) {
+		width /= 2;
+		height /= 2;
 	}
 
+	data_rate = width * height * fb->format->cpp[plane];
+
 	down_scale_amount = skl_plane_downscale_amount(cstate, intel_pstate);
 
 	return mul_round_up_u32_fixed16(data_rate, down_scale_amount);
@@ -4063,8 +4150,8 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
  */
 static unsigned int
 skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate,
-				 unsigned *plane_data_rate,
-				 unsigned *plane_y_data_rate)
+				 unsigned int *plane_data_rate,
+				 unsigned int *uv_plane_data_rate)
 {
 	struct drm_crtc_state *cstate = &intel_cstate->base;
 	struct drm_atomic_state *state = cstate->state;
@@ -4080,17 +4167,17 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate,
 		enum plane_id plane_id = to_intel_plane(plane)->id;
 		unsigned int rate;
 
-		/* packed/uv */
+		/* packed/y */
 		rate = skl_plane_relative_data_rate(intel_cstate,
 						    pstate, 0);
 		plane_data_rate[plane_id] = rate;
 
 		total_data_rate += rate;
 
-		/* y-plane */
+		/* uv-plane */
 		rate = skl_plane_relative_data_rate(intel_cstate,
 						    pstate, 1);
-		plane_y_data_rate[plane_id] = rate;
+		uv_plane_data_rate[plane_id] = rate;
 
 		total_data_rate += rate;
 	}
@@ -4099,8 +4186,7 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate,
 }
 
 static uint16_t
-skl_ddb_min_alloc(const struct drm_plane_state *pstate,
-		  const int y)
+skl_ddb_min_alloc(const struct drm_plane_state *pstate, const int plane)
 {
 	struct drm_framebuffer *fb = pstate->fb;
 	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
@@ -4111,8 +4197,8 @@ skl_ddb_min_alloc(const struct drm_plane_state *pstate,
 	if (WARN_ON(!fb))
 		return 0;
 
-	/* For packed formats, no y-plane, return 0 */
-	if (y && fb->format->format != DRM_FORMAT_NV12)
+	/* For packed formats, and uv-plane, return 0 */
+	if (plane == 1 && fb->format->format != DRM_FORMAT_NV12)
 		return 0;
 
 	/* For Non Y-tile return 8-blocks */
@@ -4131,15 +4217,12 @@ skl_ddb_min_alloc(const struct drm_plane_state *pstate,
 	src_h = drm_rect_height(&intel_pstate->base.src) >> 16;
 
 	/* Halve UV plane width and height for NV12 */
-	if (fb->format->format == DRM_FORMAT_NV12 && !y) {
+	if (plane == 1) {
 		src_w /= 2;
 		src_h /= 2;
 	}
 
-	if (fb->format->format == DRM_FORMAT_NV12 && !y)
-		plane_bpp = fb->format->cpp[1];
-	else
-		plane_bpp = fb->format->cpp[0];
+	plane_bpp = fb->format->cpp[plane];
 
 	if (drm_rotation_90_or_270(pstate->rotation)) {
 		switch (plane_bpp) {
@@ -4167,7 +4250,7 @@ skl_ddb_min_alloc(const struct drm_plane_state *pstate,
 
 static void
 skl_ddb_calc_min(const struct intel_crtc_state *cstate, int num_active,
-		 uint16_t *minimum, uint16_t *y_minimum)
+		 uint16_t *minimum, uint16_t *uv_minimum)
 {
 	const struct drm_plane_state *pstate;
 	struct drm_plane *plane;
@@ -4182,7 +4265,7 @@ skl_ddb_calc_min(const struct intel_crtc_state *cstate, int num_active,
 			continue;
 
 		minimum[plane_id] = skl_ddb_min_alloc(pstate, 0);
-		y_minimum[plane_id] = skl_ddb_min_alloc(pstate, 1);
+		uv_minimum[plane_id] = skl_ddb_min_alloc(pstate, 1);
 	}
 
 	minimum[PLANE_CURSOR] = skl_cursor_allocation(num_active);
@@ -4200,17 +4283,17 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	struct skl_ddb_entry *alloc = &cstate->wm.skl.ddb;
 	uint16_t alloc_size, start;
 	uint16_t minimum[I915_MAX_PLANES] = {};
-	uint16_t y_minimum[I915_MAX_PLANES] = {};
+	uint16_t uv_minimum[I915_MAX_PLANES] = {};
 	unsigned int total_data_rate;
 	enum plane_id plane_id;
 	int num_active;
-	unsigned plane_data_rate[I915_MAX_PLANES] = {};
-	unsigned plane_y_data_rate[I915_MAX_PLANES] = {};
+	unsigned int plane_data_rate[I915_MAX_PLANES] = {};
+	unsigned int uv_plane_data_rate[I915_MAX_PLANES] = {};
 	uint16_t total_min_blocks = 0;
 
 	/* Clear the partitioning for disabled planes. */
 	memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
-	memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe]));
+	memset(ddb->uv_plane[pipe], 0, sizeof(ddb->uv_plane[pipe]));
 
 	if (WARN_ON(!state))
 		return 0;
@@ -4220,12 +4303,16 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		return 0;
 	}
 
-	skl_ddb_get_pipe_allocation_limits(dev, cstate, alloc, &num_active);
+	total_data_rate = skl_get_total_relative_data_rate(cstate,
+							   plane_data_rate,
+							   uv_plane_data_rate);
+	skl_ddb_get_pipe_allocation_limits(dev, cstate, total_data_rate, ddb,
+					   alloc, &num_active);
 	alloc_size = skl_ddb_entry_size(alloc);
 	if (alloc_size == 0)
 		return 0;
 
-	skl_ddb_calc_min(cstate, num_active, minimum, y_minimum);
+	skl_ddb_calc_min(cstate, num_active, minimum, uv_minimum);
 
 	/*
 	 * 1. Allocate the mininum required blocks for each active plane
@@ -4235,7 +4322,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 
 	for_each_plane_id_on_crtc(intel_crtc, plane_id) {
 		total_min_blocks += minimum[plane_id];
-		total_min_blocks += y_minimum[plane_id];
+		total_min_blocks += uv_minimum[plane_id];
 	}
 
 	if (total_min_blocks > alloc_size) {
@@ -4255,16 +4342,13 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	 *
 	 * FIXME: we may not allocate every single block here.
 	 */
-	total_data_rate = skl_get_total_relative_data_rate(cstate,
-							   plane_data_rate,
-							   plane_y_data_rate);
 	if (total_data_rate == 0)
 		return 0;
 
 	start = alloc->start;
 	for_each_plane_id_on_crtc(intel_crtc, plane_id) {
-		unsigned int data_rate, y_data_rate;
-		uint16_t plane_blocks, y_plane_blocks = 0;
+		unsigned int data_rate, uv_data_rate;
+		uint16_t plane_blocks, uv_plane_blocks;
 
 		if (plane_id == PLANE_CURSOR)
 			continue;
@@ -4288,21 +4372,20 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 
 		start += plane_blocks;
 
-		/*
-		 * allocation for y_plane part of planar format:
-		 */
-		y_data_rate = plane_y_data_rate[plane_id];
+		/* Allocate DDB for UV plane for planar format/NV12 */
+		uv_data_rate = uv_plane_data_rate[plane_id];
 
-		y_plane_blocks = y_minimum[plane_id];
-		y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate,
-					total_data_rate);
+		uv_plane_blocks = uv_minimum[plane_id];
+		uv_plane_blocks += div_u64((uint64_t)alloc_size * uv_data_rate,
+					   total_data_rate);
 
-		if (y_data_rate) {
-			ddb->y_plane[pipe][plane_id].start = start;
-			ddb->y_plane[pipe][plane_id].end = start + y_plane_blocks;
+		if (uv_data_rate) {
+			ddb->uv_plane[pipe][plane_id].start = start;
+			ddb->uv_plane[pipe][plane_id].end =
+				start + uv_plane_blocks;
 		}
 
-		start += y_plane_blocks;
+		start += uv_plane_blocks;
 	}
 
 	return 0;
@@ -4398,7 +4481,7 @@ static int
 skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
 			    struct intel_crtc_state *cstate,
 			    const struct intel_plane_state *intel_pstate,
-			    struct skl_wm_params *wp)
+			    struct skl_wm_params *wp, int plane_id)
 {
 	struct intel_plane *plane = to_intel_plane(intel_pstate->base.plane);
 	const struct drm_plane_state *pstate = &intel_pstate->base;
@@ -4411,6 +4494,12 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
 	if (!intel_wm_plane_visible(cstate, intel_pstate))
 		return 0;
 
+	/* only NV12 format has two planes */
+	if (plane_id == 1 && fb->format->format != DRM_FORMAT_NV12) {
+		DRM_DEBUG_KMS("Non NV12 format have single plane\n");
+		return -EINVAL;
+	}
+
 	wp->y_tiled = fb->modifier == I915_FORMAT_MOD_Y_TILED ||
 		      fb->modifier == I915_FORMAT_MOD_Yf_TILED ||
 		      fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
@@ -4418,6 +4507,7 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
 	wp->x_tiled = fb->modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 			 fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
+	wp->is_planar = fb->format->format == DRM_FORMAT_NV12;
 
 	if (plane->id == PLANE_CURSOR) {
 		wp->width = intel_pstate->base.crtc_w;
@@ -4430,8 +4520,10 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
 		wp->width = drm_rect_width(&intel_pstate->base.src) >> 16;
 	}
 
-	wp->cpp = (fb->format->format == DRM_FORMAT_NV12) ? fb->format->cpp[1] :
-							    fb->format->cpp[0];
+	if (plane_id == 1 && wp->is_planar)
+		wp->width /= 2;
+
+	wp->cpp = fb->format->cpp[plane_id];
 	wp->plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate,
 							     intel_pstate);
 
@@ -4499,9 +4591,8 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 				uint16_t ddb_allocation,
 				int level,
 				const struct skl_wm_params *wp,
-				uint16_t *out_blocks, /* out */
-				uint8_t *out_lines, /* out */
-				bool *enabled /* out */)
+				const struct skl_wm_level *result_prev,
+				struct skl_wm_level *result /* out */)
 {
 	const struct drm_plane_state *pstate = &intel_pstate->base;
 	uint32_t latency = dev_priv->wm.skl_latency[level];
@@ -4515,7 +4606,7 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 
 	if (latency == 0 ||
 	    !intel_wm_plane_visible(cstate, intel_pstate)) {
-		*enabled = false;
+		result->plane_en = false;
 		return 0;
 	}
 
@@ -4568,6 +4659,15 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 		} else {
 			res_blocks++;
 		}
+
+		/*
+		 * Make sure result blocks for higher latency levels are atleast
+		 * as high as level below the current level.
+		 * Assumption in DDB algorithm optimization for special cases.
+		 * Also covers Display WA #1125 for RC.
+		 */
+		if (result_prev->plane_res_b > res_blocks)
+			res_blocks = result_prev->plane_res_b;
 	}
 
 	if (INTEL_GEN(dev_priv) >= 11) {
@@ -4596,7 +4696,7 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	if ((level > 0 && res_lines > 31) ||
 	    res_blocks >= ddb_allocation ||
 	    min_disp_buf_needed >= ddb_allocation) {
-		*enabled = false;
+		result->plane_en = false;
 
 		/*
 		 * If there are no valid level 0 watermarks, then we can't
@@ -4615,10 +4715,21 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 		}
 	}
 
+	/*
+	 * Display WA #826 (SKL:ALL, BXT:ALL) & #1059 (CNL:A)
+	 * disable wm level 1-7 on NV12 planes
+	 */
+	if (wp->is_planar && level >= 1 &&
+	    (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv) ||
+	     IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_A0))) {
+		result->plane_en = false;
+		return 0;
+	}
+
 	/* The number of lines are ignored for the level 0 watermark. */
-	*out_lines = level ? res_lines : 0;
-	*out_blocks = res_blocks;
-	*enabled = true;
+	result->plane_res_b = res_blocks;
+	result->plane_res_l = res_lines;
+	result->plane_en = true;
 
 	return 0;
 }
@@ -4629,7 +4740,8 @@ skl_compute_wm_levels(const struct drm_i915_private *dev_priv,
 		      struct intel_crtc_state *cstate,
 		      const struct intel_plane_state *intel_pstate,
 		      const struct skl_wm_params *wm_params,
-		      struct skl_plane_wm *wm)
+		      struct skl_plane_wm *wm,
+		      int plane_id)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
 	struct drm_plane *plane = intel_pstate->base.plane;
@@ -4637,15 +4749,26 @@ skl_compute_wm_levels(const struct drm_i915_private *dev_priv,
 	uint16_t ddb_blocks;
 	enum pipe pipe = intel_crtc->pipe;
 	int level, max_level = ilk_wm_max_level(dev_priv);
+	enum plane_id intel_plane_id = intel_plane->id;
 	int ret;
 
 	if (WARN_ON(!intel_pstate->base.fb))
 		return -EINVAL;
 
-	ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][intel_plane->id]);
+	ddb_blocks = plane_id ?
+		     skl_ddb_entry_size(&ddb->uv_plane[pipe][intel_plane_id]) :
+		     skl_ddb_entry_size(&ddb->plane[pipe][intel_plane_id]);
 
 	for (level = 0; level <= max_level; level++) {
-		struct skl_wm_level *result = &wm->wm[level];
+		struct skl_wm_level *result = plane_id ? &wm->uv_wm[level] :
+							  &wm->wm[level];
+		struct skl_wm_level *result_prev;
+
+		if (level)
+			result_prev = plane_id ? &wm->uv_wm[level - 1] :
+						  &wm->wm[level - 1];
+		else
+			result_prev = plane_id ? &wm->uv_wm[0] : &wm->wm[0];
 
 		ret = skl_compute_plane_wm(dev_priv,
 					   cstate,
@@ -4653,13 +4776,15 @@ skl_compute_wm_levels(const struct drm_i915_private *dev_priv,
 					   ddb_blocks,
 					   level,
 					   wm_params,
-					   &result->plane_res_b,
-					   &result->plane_res_l,
-					   &result->plane_en);
+					   result_prev,
+					   result);
 		if (ret)
 			return ret;
 	}
 
+	if (intel_pstate->base.fb->format->format == DRM_FORMAT_NV12)
+		wm->is_planar = true;
+
 	return 0;
 }
 
@@ -4769,20 +4894,39 @@ static int skl_build_pipe_wm(struct intel_crtc_state *cstate,
 
 		wm = &pipe_wm->planes[plane_id];
 		ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][plane_id]);
-		memset(&wm_params, 0, sizeof(struct skl_wm_params));
 
 		ret = skl_compute_plane_wm_params(dev_priv, cstate,
-						  intel_pstate, &wm_params);
+						  intel_pstate, &wm_params, 0);
 		if (ret)
 			return ret;
 
 		ret = skl_compute_wm_levels(dev_priv, ddb, cstate,
-					    intel_pstate, &wm_params, wm);
+					    intel_pstate, &wm_params, wm, 0);
 		if (ret)
 			return ret;
+
 		skl_compute_transition_wm(cstate, &wm_params, &wm->wm[0],
 					  ddb_blocks, &wm->trans_wm);
+
+		/* uv plane watermarks must also be validated for NV12/Planar */
+		if (wm_params.is_planar) {
+			memset(&wm_params, 0, sizeof(struct skl_wm_params));
+			wm->is_planar = true;
+
+			ret = skl_compute_plane_wm_params(dev_priv, cstate,
+							  intel_pstate,
+							  &wm_params, 1);
+			if (ret)
+				return ret;
+
+			ret = skl_compute_wm_levels(dev_priv, ddb, cstate,
+						    intel_pstate, &wm_params,
+						    wm, 1);
+			if (ret)
+				return ret;
+		}
 	}
+
 	pipe_wm->linetime = skl_compute_linetime_wm(cstate);
 
 	return 0;
@@ -4833,10 +4977,21 @@ static void skl_write_plane_wm(struct intel_crtc *intel_crtc,
 
 	skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
 			    &ddb->plane[pipe][plane_id]);
-	if (INTEL_GEN(dev_priv) < 11)
+	if (INTEL_GEN(dev_priv) >= 11)
+		return skl_ddb_entry_write(dev_priv,
+					   PLANE_BUF_CFG(pipe, plane_id),
+					   &ddb->plane[pipe][plane_id]);
+	if (wm->is_planar) {
+		skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
+				    &ddb->uv_plane[pipe][plane_id]);
 		skl_ddb_entry_write(dev_priv,
 				    PLANE_NV12_BUF_CFG(pipe, plane_id),
-				    &ddb->y_plane[pipe][plane_id]);
+				    &ddb->plane[pipe][plane_id]);
+	} else {
+		skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
+				    &ddb->plane[pipe][plane_id]);
+		I915_WRITE(PLANE_NV12_BUF_CFG(pipe, plane_id), 0x0);
+	}
 }
 
 static void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
@@ -4944,15 +5099,13 @@ skl_ddb_add_affected_planes(struct intel_crtc_state *cstate)
 	struct drm_plane *plane;
 	enum pipe pipe = intel_crtc->pipe;
 
-	WARN_ON(!drm_atomic_get_existing_crtc_state(state, crtc));
-
 	drm_for_each_plane_mask(plane, dev, cstate->base.plane_mask) {
 		enum plane_id plane_id = to_intel_plane(plane)->id;
 
 		if (skl_ddb_entry_equal(&cur_ddb->plane[pipe][plane_id],
 					&new_ddb->plane[pipe][plane_id]) &&
-		    skl_ddb_entry_equal(&cur_ddb->y_plane[pipe][plane_id],
-					&new_ddb->y_plane[pipe][plane_id]))
+		    skl_ddb_entry_equal(&cur_ddb->uv_plane[pipe][plane_id],
+					&new_ddb->uv_plane[pipe][plane_id]))
 			continue;
 
 		plane_state = drm_atomic_get_plane_state(state, plane);
@@ -4966,69 +5119,16 @@ skl_ddb_add_affected_planes(struct intel_crtc_state *cstate)
 static int
 skl_compute_ddb(struct drm_atomic_state *state)
 {
-	struct drm_device *dev = state->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	const struct drm_i915_private *dev_priv = to_i915(state->dev);
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct intel_crtc *intel_crtc;
 	struct skl_ddb_allocation *ddb = &intel_state->wm_results.ddb;
-	uint32_t realloc_pipes = pipes_modified(state);
-	int ret;
-
-	/*
-	 * If this is our first atomic update following hardware readout,
-	 * we can't trust the DDB that the BIOS programmed for us.  Let's
-	 * pretend that all pipes switched active status so that we'll
-	 * ensure a full DDB recompute.
-	 */
-	if (dev_priv->wm.distrust_bios_wm) {
-		ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
-				       state->acquire_ctx);
-		if (ret)
-			return ret;
-
-		intel_state->active_pipe_changes = ~0;
-
-		/*
-		 * We usually only initialize intel_state->active_crtcs if we
-		 * we're doing a modeset; make sure this field is always
-		 * initialized during the sanitization process that happens
-		 * on the first commit too.
-		 */
-		if (!intel_state->modeset)
-			intel_state->active_crtcs = dev_priv->active_crtcs;
-	}
-
-	/*
-	 * If the modeset changes which CRTC's are active, we need to
-	 * recompute the DDB allocation for *all* active pipes, even
-	 * those that weren't otherwise being modified in any way by this
-	 * atomic commit.  Due to the shrinking of the per-pipe allocations
-	 * when new active CRTC's are added, it's possible for a pipe that
-	 * we were already using and aren't changing at all here to suddenly
-	 * become invalid if its DDB needs exceeds its new allocation.
-	 *
-	 * Note that if we wind up doing a full DDB recompute, we can't let
-	 * any other display updates race with this transaction, so we need
-	 * to grab the lock on *all* CRTC's.
-	 */
-	if (intel_state->active_pipe_changes) {
-		realloc_pipes = ~0;
-		intel_state->wm_results.dirty_pipes = ~0;
-	}
+	struct intel_crtc *crtc;
+	struct intel_crtc_state *cstate;
+	int ret, i;
 
-	/*
-	 * We're not recomputing for the pipes not included in the commit, so
-	 * make sure we start with the current state.
-	 */
 	memcpy(ddb, &dev_priv->wm.skl_hw.ddb, sizeof(*ddb));
 
-	for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
-		struct intel_crtc_state *cstate;
-
-		cstate = intel_atomic_get_crtc_state(state, intel_crtc);
-		if (IS_ERR(cstate))
-			return PTR_ERR(cstate);
-
+	for_each_new_intel_crtc_in_state(intel_state, crtc, cstate, i) {
 		ret = skl_allocate_pipe_ddb(cstate, ddb);
 		if (ret)
 			return ret;
@@ -5042,14 +5142,15 @@ skl_compute_ddb(struct drm_atomic_state *state)
 }
 
 static void
-skl_copy_wm_for_pipe(struct skl_wm_values *dst,
-		     struct skl_wm_values *src,
-		     enum pipe pipe)
+skl_copy_ddb_for_pipe(struct skl_ddb_values *dst,
+		      struct skl_ddb_values *src,
+		      enum pipe pipe)
 {
-	memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe],
-	       sizeof(dst->ddb.y_plane[pipe]));
+	memcpy(dst->ddb.uv_plane[pipe], src->ddb.uv_plane[pipe],
+	       sizeof(dst->ddb.uv_plane[pipe]));
 	memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe],
 	       sizeof(dst->ddb.plane[pipe]));
+	dst->ddb.enabled_slices = src->ddb.enabled_slices;
 }
 
 static void
@@ -5090,23 +5191,23 @@ skl_print_wm_changes(const struct drm_atomic_state *state)
 }
 
 static int
-skl_compute_wm(struct drm_atomic_state *state)
+skl_ddb_add_affected_pipes(struct drm_atomic_state *state, bool *changed)
 {
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *cstate;
-	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct skl_wm_values *results = &intel_state->wm_results;
 	struct drm_device *dev = state->dev;
-	struct skl_pipe_wm *pipe_wm;
-	bool changed = false;
+	const struct drm_i915_private *dev_priv = to_i915(dev);
+	const struct drm_crtc *crtc;
+	const struct drm_crtc_state *cstate;
+	struct intel_crtc *intel_crtc;
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	uint32_t realloc_pipes = pipes_modified(state);
 	int ret, i;
 
 	/*
 	 * When we distrust bios wm we always need to recompute to set the
 	 * expected DDB allocations for each CRTC.
 	 */
-	if (to_i915(dev)->wm.distrust_bios_wm)
-		changed = true;
+	if (dev_priv->wm.distrust_bios_wm)
+		(*changed) = true;
 
 	/*
 	 * If this transaction isn't actually touching any CRTC's, don't
@@ -5117,14 +5218,86 @@ skl_compute_wm(struct drm_atomic_state *state)
 	 * hold _all_ CRTC state mutexes.
 	 */
 	for_each_new_crtc_in_state(state, crtc, cstate, i)
-		changed = true;
+		(*changed) = true;
 
-	if (!changed)
+	if (!*changed)
 		return 0;
 
+	/*
+	 * If this is our first atomic update following hardware readout,
+	 * we can't trust the DDB that the BIOS programmed for us.  Let's
+	 * pretend that all pipes switched active status so that we'll
+	 * ensure a full DDB recompute.
+	 */
+	if (dev_priv->wm.distrust_bios_wm) {
+		ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
+				       state->acquire_ctx);
+		if (ret)
+			return ret;
+
+		intel_state->active_pipe_changes = ~0;
+
+		/*
+		 * We usually only initialize intel_state->active_crtcs if we
+		 * we're doing a modeset; make sure this field is always
+		 * initialized during the sanitization process that happens
+		 * on the first commit too.
+		 */
+		if (!intel_state->modeset)
+			intel_state->active_crtcs = dev_priv->active_crtcs;
+	}
+
+	/*
+	 * If the modeset changes which CRTC's are active, we need to
+	 * recompute the DDB allocation for *all* active pipes, even
+	 * those that weren't otherwise being modified in any way by this
+	 * atomic commit.  Due to the shrinking of the per-pipe allocations
+	 * when new active CRTC's are added, it's possible for a pipe that
+	 * we were already using and aren't changing at all here to suddenly
+	 * become invalid if its DDB needs exceeds its new allocation.
+	 *
+	 * Note that if we wind up doing a full DDB recompute, we can't let
+	 * any other display updates race with this transaction, so we need
+	 * to grab the lock on *all* CRTC's.
+	 */
+	if (intel_state->active_pipe_changes) {
+		realloc_pipes = ~0;
+		intel_state->wm_results.dirty_pipes = ~0;
+	}
+
+	/*
+	 * We're not recomputing for the pipes not included in the commit, so
+	 * make sure we start with the current state.
+	 */
+	for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
+		struct intel_crtc_state *cstate;
+
+		cstate = intel_atomic_get_crtc_state(state, intel_crtc);
+		if (IS_ERR(cstate))
+			return PTR_ERR(cstate);
+	}
+
+	return 0;
+}
+
+static int
+skl_compute_wm(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *cstate;
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct skl_ddb_values *results = &intel_state->wm_results;
+	struct skl_pipe_wm *pipe_wm;
+	bool changed = false;
+	int ret, i;
+
 	/* Clear all dirty flags */
 	results->dirty_pipes = 0;
 
+	ret = skl_ddb_add_affected_pipes(state, &changed);
+	if (ret || !changed)
+		return ret;
+
 	ret = skl_compute_ddb(state);
 	if (ret)
 		return ret;
@@ -5197,8 +5370,8 @@ static void skl_initial_wm(struct intel_atomic_state *state,
 	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct skl_wm_values *results = &state->wm_results;
-	struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw;
+	struct skl_ddb_values *results = &state->wm_results;
+	struct skl_ddb_values *hw_vals = &dev_priv->wm.skl_hw;
 	enum pipe pipe = intel_crtc->pipe;
 
 	if ((results->dirty_pipes & drm_crtc_mask(&intel_crtc->base)) == 0)
@@ -5209,7 +5382,7 @@ static void skl_initial_wm(struct intel_atomic_state *state,
 	if (cstate->base.active_changed)
 		skl_atomic_update_crtc_wm(state, cstate);
 
-	skl_copy_wm_for_pipe(hw_vals, results, pipe);
+	skl_copy_ddb_for_pipe(hw_vals, results, pipe);
 
 	mutex_unlock(&dev_priv->wm.wm_mutex);
 }
@@ -5341,7 +5514,7 @@ void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc,
 void skl_wm_get_hw_state(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct skl_wm_values *hw = &dev_priv->wm.skl_hw;
+	struct skl_ddb_values *hw = &dev_priv->wm.skl_hw;
 	struct skl_ddb_allocation *ddb = &dev_priv->wm.skl_hw.ddb;
 	struct drm_crtc *crtc;
 	struct intel_crtc *intel_crtc;
@@ -5362,8 +5535,12 @@ void skl_wm_get_hw_state(struct drm_device *dev)
 		/* Fully recompute DDB on first atomic commit */
 		dev_priv->wm.distrust_bios_wm = true;
 	} else {
-		/* Easy/common case; just sanitize DDB now if everything off */
-		memset(ddb, 0, sizeof(*ddb));
+		/*
+		 * Easy/common case; just sanitize DDB now if everything off
+		 * Keep dbuf slice info intact
+		 */
+		memset(ddb->plane, 0, sizeof(ddb->plane));
+		memset(ddb->uv_plane, 0, sizeof(ddb->uv_plane));
 	}
 }
 
@@ -6572,7 +6749,7 @@ static void gen6_init_rps_frequencies(struct drm_i915_private *dev_priv)
 
 	rps->efficient_freq = rps->rp1_freq;
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv) ||
-	    IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+	    IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
 		u32 ddcc_status = 0;
 
 		if (sandybridge_pcode_read(dev_priv,
@@ -6585,7 +6762,7 @@ static void gen6_init_rps_frequencies(struct drm_i915_private *dev_priv)
 					rps->max_freq);
 	}
 
-	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
 		/* Store the frequency values in 16.66 MHZ units, which is
 		 * the natural hardware unit for SKL
 		 */
@@ -6890,15 +7067,18 @@ static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	int min_freq = 15;
+	const int min_freq = 15;
+	const int scaling_factor = 180;
 	unsigned int gpu_freq;
 	unsigned int max_ia_freq, min_ring_freq;
 	unsigned int max_gpu_freq, min_gpu_freq;
-	int scaling_factor = 180;
 	struct cpufreq_policy *policy;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
 
+	if (rps->max_freq <= rps->min_freq)
+		return;
+
 	policy = cpufreq_cpu_get(0);
 	if (policy) {
 		max_ia_freq = policy->cpuinfo.max_freq;
@@ -6918,13 +7098,12 @@ static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 	/* convert DDR frequency from units of 266.6MHz to bandwidth */
 	min_ring_freq = mult_frac(min_ring_freq, 8, 3);
 
-	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+	min_gpu_freq = rps->min_freq;
+	max_gpu_freq = rps->max_freq;
+	if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
 		/* Convert GT frequency to 50 HZ units */
-		min_gpu_freq = rps->min_freq / GEN9_FREQ_SCALER;
-		max_gpu_freq = rps->max_freq / GEN9_FREQ_SCALER;
-	} else {
-		min_gpu_freq = rps->min_freq;
-		max_gpu_freq = rps->max_freq;
+		min_gpu_freq /= GEN9_FREQ_SCALER;
+		max_gpu_freq /= GEN9_FREQ_SCALER;
 	}
 
 	/*
@@ -6933,10 +7112,10 @@ static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 	 * the PCU should use as a reference to determine the ring frequency.
 	 */
 	for (gpu_freq = max_gpu_freq; gpu_freq >= min_gpu_freq; gpu_freq--) {
-		int diff = max_gpu_freq - gpu_freq;
+		const int diff = max_gpu_freq - gpu_freq;
 		unsigned int ia_freq = 0, ring_freq = 0;
 
-		if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+		if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
 			/*
 			 * ring_freq = 2 * GT. ring_freq is in 100MHz units
 			 * No floor required for ring frequency on SKL.
@@ -8026,10 +8205,10 @@ void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv)
 	dev_priv->gt_pm.rc6.enabled = true; /* force RC6 disabling */
 	intel_disable_gt_powersave(dev_priv);
 
-	if (INTEL_GEN(dev_priv) < 11)
-		gen6_reset_rps_interrupts(dev_priv);
+	if (INTEL_GEN(dev_priv) >= 11)
+		gen11_reset_rps_interrupts(dev_priv);
 	else
-		WARN_ON_ONCE(1);
+		gen6_reset_rps_interrupts(dev_priv);
 }
 
 static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
@@ -8142,8 +8321,6 @@ static void intel_enable_rps(struct drm_i915_private *dev_priv)
 		cherryview_enable_rps(dev_priv);
 	} else if (IS_VALLEYVIEW(dev_priv)) {
 		valleyview_enable_rps(dev_priv);
-	} else if (WARN_ON_ONCE(INTEL_GEN(dev_priv) >= 11)) {
-		/* TODO */
 	} else if (INTEL_GEN(dev_priv) >= 9) {
 		gen9_enable_rps(dev_priv);
 	} else if (IS_BROADWELL(dev_priv)) {
@@ -8487,6 +8664,13 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv,
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 }
 
+static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
+{
+	/* This is not an Wa. Enable to reduce Sampler power */
+	I915_WRITE(GEN10_DFR_RATIO_EN_AND_CHICKEN,
+		   I915_READ(GEN10_DFR_RATIO_EN_AND_CHICKEN) & ~DFR_DISABLE);
+}
+
 static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	if (!HAS_PCH_CNP(dev_priv))
@@ -9013,7 +9197,9 @@ static void nop_init_clock_gating(struct drm_i915_private *dev_priv)
  */
 void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
 {
-	if (IS_CANNONLAKE(dev_priv))
+	if (IS_ICELAKE(dev_priv))
+		dev_priv->display.init_clock_gating = icl_init_clock_gating;
+	else if (IS_CANNONLAKE(dev_priv))
 		dev_priv->display.init_clock_gating = cnl_init_clock_gating;
 	else if (IS_COFFEELAKE(dev_priv))
 		dev_priv->display.init_clock_gating = cfl_init_clock_gating;
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 23175c5c4a50..db27f2faa1de 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -93,7 +93,115 @@ static void psr_aux_io_power_put(struct intel_dp *intel_dp)
 	intel_display_power_put(dev_priv, psr_aux_domain(intel_dp));
 }
 
-static bool intel_dp_get_y_cord_status(struct intel_dp *intel_dp)
+void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug)
+{
+	u32 debug_mask, mask;
+
+	/* No PSR interrupts on VLV/CHV */
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		return;
+
+	mask = EDP_PSR_ERROR(TRANSCODER_EDP);
+	debug_mask = EDP_PSR_POST_EXIT(TRANSCODER_EDP) |
+		     EDP_PSR_PRE_ENTRY(TRANSCODER_EDP);
+
+	if (INTEL_GEN(dev_priv) >= 8) {
+		mask |= EDP_PSR_ERROR(TRANSCODER_A) |
+			EDP_PSR_ERROR(TRANSCODER_B) |
+			EDP_PSR_ERROR(TRANSCODER_C);
+
+		debug_mask |= EDP_PSR_POST_EXIT(TRANSCODER_A) |
+			      EDP_PSR_PRE_ENTRY(TRANSCODER_A) |
+			      EDP_PSR_POST_EXIT(TRANSCODER_B) |
+			      EDP_PSR_PRE_ENTRY(TRANSCODER_B) |
+			      EDP_PSR_POST_EXIT(TRANSCODER_C) |
+			      EDP_PSR_PRE_ENTRY(TRANSCODER_C);
+	}
+
+	if (debug)
+		mask |= debug_mask;
+
+	WRITE_ONCE(dev_priv->psr.debug, debug);
+	I915_WRITE(EDP_PSR_IMR, ~mask);
+}
+
+static void psr_event_print(u32 val, bool psr2_enabled)
+{
+	DRM_DEBUG_KMS("PSR exit events: 0x%x\n", val);
+	if (val & PSR_EVENT_PSR2_WD_TIMER_EXPIRE)
+		DRM_DEBUG_KMS("\tPSR2 watchdog timer expired\n");
+	if ((val & PSR_EVENT_PSR2_DISABLED) && psr2_enabled)
+		DRM_DEBUG_KMS("\tPSR2 disabled\n");
+	if (val & PSR_EVENT_SU_DIRTY_FIFO_UNDERRUN)
+		DRM_DEBUG_KMS("\tSU dirty FIFO underrun\n");
+	if (val & PSR_EVENT_SU_CRC_FIFO_UNDERRUN)
+		DRM_DEBUG_KMS("\tSU CRC FIFO underrun\n");
+	if (val & PSR_EVENT_GRAPHICS_RESET)
+		DRM_DEBUG_KMS("\tGraphics reset\n");
+	if (val & PSR_EVENT_PCH_INTERRUPT)
+		DRM_DEBUG_KMS("\tPCH interrupt\n");
+	if (val & PSR_EVENT_MEMORY_UP)
+		DRM_DEBUG_KMS("\tMemory up\n");
+	if (val & PSR_EVENT_FRONT_BUFFER_MODIFY)
+		DRM_DEBUG_KMS("\tFront buffer modification\n");
+	if (val & PSR_EVENT_WD_TIMER_EXPIRE)
+		DRM_DEBUG_KMS("\tPSR watchdog timer expired\n");
+	if (val & PSR_EVENT_PIPE_REGISTERS_UPDATE)
+		DRM_DEBUG_KMS("\tPIPE registers updated\n");
+	if (val & PSR_EVENT_REGISTER_UPDATE)
+		DRM_DEBUG_KMS("\tRegister updated\n");
+	if (val & PSR_EVENT_HDCP_ENABLE)
+		DRM_DEBUG_KMS("\tHDCP enabled\n");
+	if (val & PSR_EVENT_KVMR_SESSION_ENABLE)
+		DRM_DEBUG_KMS("\tKVMR session enabled\n");
+	if (val & PSR_EVENT_VBI_ENABLE)
+		DRM_DEBUG_KMS("\tVBI enabled\n");
+	if (val & PSR_EVENT_LPSP_MODE_EXIT)
+		DRM_DEBUG_KMS("\tLPSP mode exited\n");
+	if ((val & PSR_EVENT_PSR_DISABLE) && !psr2_enabled)
+		DRM_DEBUG_KMS("\tPSR disabled\n");
+}
+
+void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
+{
+	u32 transcoders = BIT(TRANSCODER_EDP);
+	enum transcoder cpu_transcoder;
+	ktime_t time_ns =  ktime_get();
+
+	if (INTEL_GEN(dev_priv) >= 8)
+		transcoders |= BIT(TRANSCODER_A) |
+			       BIT(TRANSCODER_B) |
+			       BIT(TRANSCODER_C);
+
+	for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, transcoders) {
+		/* FIXME: Exit PSR and link train manually when this happens. */
+		if (psr_iir & EDP_PSR_ERROR(cpu_transcoder))
+			DRM_DEBUG_KMS("[transcoder %s] PSR aux error\n",
+				      transcoder_name(cpu_transcoder));
+
+		if (psr_iir & EDP_PSR_PRE_ENTRY(cpu_transcoder)) {
+			dev_priv->psr.last_entry_attempt = time_ns;
+			DRM_DEBUG_KMS("[transcoder %s] PSR entry attempt in 2 vblanks\n",
+				      transcoder_name(cpu_transcoder));
+		}
+
+		if (psr_iir & EDP_PSR_POST_EXIT(cpu_transcoder)) {
+			dev_priv->psr.last_exit = time_ns;
+			DRM_DEBUG_KMS("[transcoder %s] PSR exit completed\n",
+				      transcoder_name(cpu_transcoder));
+
+			if (INTEL_GEN(dev_priv) >= 9) {
+				u32 val = I915_READ(PSR_EVENT(cpu_transcoder));
+				bool psr2_enabled = dev_priv->psr.psr2_enabled;
+
+				I915_WRITE(PSR_EVENT(cpu_transcoder), val);
+				psr_event_print(val, psr2_enabled);
+			}
+		}
+	}
+}
+
+static bool intel_dp_get_y_coord_required(struct intel_dp *intel_dp)
 {
 	uint8_t psr_caps = 0;
 
@@ -122,6 +230,18 @@ static bool intel_dp_get_alpm_status(struct intel_dp *intel_dp)
 	return alpm_caps & DP_ALPM_CAP;
 }
 
+static u8 intel_dp_get_sink_sync_latency(struct intel_dp *intel_dp)
+{
+	u8 val = 0;
+
+	if (drm_dp_dpcd_readb(&intel_dp->aux,
+			      DP_SYNCHRONIZATION_LATENCY_IN_SINK, &val) == 1)
+		val &= DP_MAX_RESYNC_FRAME_COUNT_MASK;
+	else
+		DRM_ERROR("Unable to get sink synchronization latency\n");
+	return val;
+}
+
 void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv =
@@ -130,33 +250,36 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	drm_dp_dpcd_read(&intel_dp->aux, DP_PSR_SUPPORT, intel_dp->psr_dpcd,
 			 sizeof(intel_dp->psr_dpcd));
 
-	if (intel_dp->psr_dpcd[0] & DP_PSR_IS_SUPPORTED) {
+	if (intel_dp->psr_dpcd[0]) {
 		dev_priv->psr.sink_support = true;
 		DRM_DEBUG_KMS("Detected EDP PSR Panel.\n");
 	}
 
 	if (INTEL_GEN(dev_priv) >= 9 &&
-	    (intel_dp->psr_dpcd[0] & DP_PSR2_IS_SUPPORTED)) {
-		uint8_t frame_sync_cap;
+	    (intel_dp->psr_dpcd[0] == DP_PSR2_WITH_Y_COORD_IS_SUPPORTED)) {
+		/*
+		 * All panels that supports PSR version 03h (PSR2 +
+		 * Y-coordinate) can handle Y-coordinates in VSC but we are
+		 * only sure that it is going to be used when required by the
+		 * panel. This way panel is capable to do selective update
+		 * without a aux frame sync.
+		 *
+		 * To support PSR version 02h and PSR version 03h without
+		 * Y-coordinate requirement panels we would need to enable
+		 * GTC first.
+		 */
+		dev_priv->psr.sink_psr2_support =
+				intel_dp_get_y_coord_required(intel_dp);
+		DRM_DEBUG_KMS("PSR2 %s on sink", dev_priv->psr.sink_psr2_support
+			      ? "supported" : "not supported");
 
-		dev_priv->psr.sink_support = true;
-		if (drm_dp_dpcd_readb(&intel_dp->aux,
-				      DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP,
-				      &frame_sync_cap) != 1)
-			frame_sync_cap = 0;
-		dev_priv->psr.aux_frame_sync = frame_sync_cap & DP_AUX_FRAME_SYNC_CAP;
-		/* PSR2 needs frame sync as well */
-		dev_priv->psr.psr2_support = dev_priv->psr.aux_frame_sync;
-		DRM_DEBUG_KMS("PSR2 %s on sink",
-			      dev_priv->psr.psr2_support ? "supported" : "not supported");
-
-		if (dev_priv->psr.psr2_support) {
-			dev_priv->psr.y_cord_support =
-				intel_dp_get_y_cord_status(intel_dp);
+		if (dev_priv->psr.sink_psr2_support) {
 			dev_priv->psr.colorimetry_support =
 				intel_dp_get_colorimetry_status(intel_dp);
 			dev_priv->psr.alpm =
 				intel_dp_get_alpm_status(intel_dp);
+			dev_priv->psr.sink_sync_latency =
+				intel_dp_get_sink_sync_latency(intel_dp);
 		}
 	}
 }
@@ -193,21 +316,17 @@ static void hsw_psr_setup_vsc(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
 	struct edp_vsc_psr psr_vsc;
 
-	if (dev_priv->psr.psr2_support) {
+	if (dev_priv->psr.psr2_enabled) {
 		/* Prepare VSC Header for SU as per EDP 1.4 spec, Table 6.11 */
 		memset(&psr_vsc, 0, sizeof(psr_vsc));
 		psr_vsc.sdp_header.HB0 = 0;
 		psr_vsc.sdp_header.HB1 = 0x7;
-		if (dev_priv->psr.colorimetry_support &&
-		    dev_priv->psr.y_cord_support) {
+		if (dev_priv->psr.colorimetry_support) {
 			psr_vsc.sdp_header.HB2 = 0x5;
 			psr_vsc.sdp_header.HB3 = 0x13;
-		} else if (dev_priv->psr.y_cord_support) {
+		} else {
 			psr_vsc.sdp_header.HB2 = 0x4;
 			psr_vsc.sdp_header.HB3 = 0xe;
-		} else {
-			psr_vsc.sdp_header.HB2 = 0x3;
-			psr_vsc.sdp_header.HB3 = 0xc;
 		}
 	} else {
 		/* Prepare VSC packet as per EDP 1.3 spec, Table 3.10 */
@@ -228,31 +347,12 @@ static void vlv_psr_enable_sink(struct intel_dp *intel_dp)
 			   DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
 }
 
-static i915_reg_t psr_aux_ctl_reg(struct drm_i915_private *dev_priv,
-				       enum port port)
-{
-	if (INTEL_GEN(dev_priv) >= 9)
-		return DP_AUX_CH_CTL(port);
-	else
-		return EDP_PSR_AUX_CTL;
-}
-
-static i915_reg_t psr_aux_data_reg(struct drm_i915_private *dev_priv,
-					enum port port, int index)
-{
-	if (INTEL_GEN(dev_priv) >= 9)
-		return DP_AUX_CH_DATA(port, index);
-	else
-		return EDP_PSR_AUX_DATA(index);
-}
-
-static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
+static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	uint32_t aux_clock_divider;
-	i915_reg_t aux_ctl_reg;
+	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
+	u32 aux_clock_divider, aux_ctl;
+	int i;
 	static const uint8_t aux_msg[] = {
 		[0] = DP_AUX_NATIVE_WRITE << 4,
 		[1] = DP_SET_POWER >> 8,
@@ -260,41 +360,47 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 		[3] = 1 - 1,
 		[4] = DP_SET_POWER_D0,
 	};
-	enum port port = dig_port->base.port;
-	u32 aux_ctl;
-	int i;
+	u32 psr_aux_mask = EDP_PSR_AUX_CTL_TIME_OUT_MASK |
+			   EDP_PSR_AUX_CTL_MESSAGE_SIZE_MASK |
+			   EDP_PSR_AUX_CTL_PRECHARGE_2US_MASK |
+			   EDP_PSR_AUX_CTL_BIT_CLOCK_2X_MASK;
 
 	BUILD_BUG_ON(sizeof(aux_msg) > 20);
+	for (i = 0; i < sizeof(aux_msg); i += 4)
+		I915_WRITE(EDP_PSR_AUX_DATA(i >> 2),
+			   intel_dp_pack_aux(&aux_msg[i], sizeof(aux_msg) - i));
 
 	aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, 0);
 
-	/* Enable AUX frame sync at sink */
-	if (dev_priv->psr.aux_frame_sync)
-		drm_dp_dpcd_writeb(&intel_dp->aux,
-				DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF,
-				DP_AUX_FRAME_SYNC_ENABLE);
+	/* Start with bits set for DDI_AUX_CTL register */
+	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, 0, sizeof(aux_msg),
+					     aux_clock_divider);
+
+	/* Select only valid bits for SRD_AUX_CTL */
+	aux_ctl &= psr_aux_mask;
+	I915_WRITE(EDP_PSR_AUX_CTL, aux_ctl);
+}
+
+static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	u8 dpcd_val = DP_PSR_ENABLE;
+
 	/* Enable ALPM at sink for psr2 */
-	if (dev_priv->psr.psr2_support && dev_priv->psr.alpm)
+	if (dev_priv->psr.psr2_enabled && dev_priv->psr.alpm)
 		drm_dp_dpcd_writeb(&intel_dp->aux,
 				DP_RECEIVER_ALPM_CONFIG,
 				DP_ALPM_ENABLE);
-	if (dev_priv->psr.link_standby)
-		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
-				   DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
-	else
-		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
-				   DP_PSR_ENABLE);
-
-	aux_ctl_reg = psr_aux_ctl_reg(dev_priv, port);
 
-	/* Setup AUX registers */
-	for (i = 0; i < sizeof(aux_msg); i += 4)
-		I915_WRITE(psr_aux_data_reg(dev_priv, port, i >> 2),
-			   intel_dp_pack_aux(&aux_msg[i], sizeof(aux_msg) - i));
+	if (dev_priv->psr.psr2_enabled)
+		dpcd_val |= DP_PSR_ENABLE_PSR2;
+	if (dev_priv->psr.link_standby)
+		dpcd_val |= DP_PSR_MAIN_LINK_ACTIVE;
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, dpcd_val);
 
-	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, 0, sizeof(aux_msg),
-					     aux_clock_divider);
-	I915_WRITE(aux_ctl_reg, aux_ctl);
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, DP_SET_POWER_D0);
 }
 
 static void vlv_psr_enable_source(struct intel_dp *intel_dp,
@@ -396,25 +502,16 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 	 * with the 5 or 6 idle patterns.
 	 */
 	uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
-	uint32_t val;
-	uint8_t sink_latency;
-
-	val = idle_frames << EDP_PSR_IDLE_FRAME_SHIFT;
+	u32 val = idle_frames << EDP_PSR2_IDLE_FRAME_SHIFT;
 
 	/* FIXME: selective update is probably totally broken because it doesn't
 	 * mesh at all with our frontbuffer tracking. And the hw alone isn't
 	 * good enough. */
-	val |= EDP_PSR2_ENABLE |
-		EDP_SU_TRACK_ENABLE;
+	val |= EDP_PSR2_ENABLE | EDP_SU_TRACK_ENABLE;
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		val |= EDP_Y_COORDINATE_ENABLE;
 
-	if (drm_dp_dpcd_readb(&intel_dp->aux,
-				DP_SYNCHRONIZATION_LATENCY_IN_SINK,
-				&sink_latency) == 1) {
-		sink_latency &= DP_MAX_RESYNC_FRAME_COUNT_MASK;
-	} else {
-		sink_latency = 0;
-	}
-	val |= EDP_PSR2_FRAME_BEFORE_SU(sink_latency + 1);
+	val |= EDP_PSR2_FRAME_BEFORE_SU(dev_priv->psr.sink_sync_latency + 1);
 
 	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
 		val |= EDP_PSR2_TP2_TIME_2500;
@@ -440,7 +537,7 @@ static void hsw_psr_activate(struct intel_dp *intel_dp)
 	 */
 
 	/* psr1 and psr2 are mutually exclusive.*/
-	if (dev_priv->psr.psr2_support)
+	if (dev_priv->psr.psr2_enabled)
 		hsw_activate_psr2(intel_dp);
 	else
 		hsw_activate_psr1(intel_dp);
@@ -460,7 +557,7 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 	 * dynamically during PSR enable, and extracted from sink
 	 * caps during eDP detection.
 	 */
-	if (!dev_priv->psr.psr2_support)
+	if (!dev_priv->psr.sink_psr2_support)
 		return false;
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
@@ -478,15 +575,6 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 		return false;
 	}
 
-	/*
-	 * FIXME:enable psr2 only for y-cordinate psr2 panels
-	 * After gtc implementation , remove this restriction.
-	 */
-	if (!dev_priv->psr.y_cord_support) {
-		DRM_DEBUG_KMS("PSR2 not enabled, panel does not support Y coordinate\n");
-		return false;
-	}
-
 	return true;
 }
 
@@ -568,7 +656,7 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
-	if (dev_priv->psr.psr2_support)
+	if (dev_priv->psr.psr2_enabled)
 		WARN_ON(I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE);
 	else
 		WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
@@ -586,14 +674,24 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp,
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	u32 chicken;
 
 	psr_aux_io_power_get(intel_dp);
 
-	if (dev_priv->psr.psr2_support) {
-		chicken = PSR2_VSC_ENABLE_PROG_HEADER;
-		if (dev_priv->psr.y_cord_support)
-			chicken |= PSR2_ADD_VERTICAL_LINE_COUNT;
+	/* Only HSW and BDW have PSR AUX registers that need to be setup. SKL+
+	 * use hardcoded values PSR AUX transactions
+	 */
+	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+		hsw_psr_setup_aux(intel_dp);
+
+	if (dev_priv->psr.psr2_enabled) {
+		u32 chicken = I915_READ(CHICKEN_TRANS(cpu_transcoder));
+
+		if (INTEL_GEN(dev_priv) == 9 && !IS_GEMINILAKE(dev_priv))
+			chicken |= (PSR2_VSC_ENABLE_PROG_HEADER
+				   | PSR2_ADD_VERTICAL_LINE_COUNT);
+
+		else
+			chicken &= ~VSC_DATA_SEL_SOFTWARE_CONTROL;
 		I915_WRITE(CHICKEN_TRANS(cpu_transcoder), chicken);
 
 		I915_WRITE(EDP_PSR_DEBUG,
@@ -613,7 +711,8 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp,
 		I915_WRITE(EDP_PSR_DEBUG,
 			   EDP_PSR_DEBUG_MASK_MEMUP |
 			   EDP_PSR_DEBUG_MASK_HPD |
-			   EDP_PSR_DEBUG_MASK_LPSP);
+			   EDP_PSR_DEBUG_MASK_LPSP |
+			   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE);
 	}
 }
 
@@ -644,7 +743,7 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 		goto unlock;
 	}
 
-	dev_priv->psr.psr2_support = crtc_state->has_psr2;
+	dev_priv->psr.psr2_enabled = crtc_state->has_psr2;
 	dev_priv->psr.busy_frontbuffer_bits = 0;
 
 	dev_priv->psr.setup_vsc(intel_dp, crtc_state);
@@ -714,12 +813,7 @@ static void hsw_psr_disable(struct intel_dp *intel_dp,
 		i915_reg_t psr_status;
 		u32 psr_status_mask;
 
-		if (dev_priv->psr.aux_frame_sync)
-			drm_dp_dpcd_writeb(&intel_dp->aux,
-					DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF,
-					0);
-
-		if (dev_priv->psr.psr2_support) {
+		if (dev_priv->psr.psr2_enabled) {
 			psr_status = EDP_PSR2_STATUS;
 			psr_status_mask = EDP_PSR2_STATUS_STATE_MASK;
 
@@ -743,7 +837,7 @@ static void hsw_psr_disable(struct intel_dp *intel_dp,
 
 		dev_priv->psr.active = false;
 	} else {
-		if (dev_priv->psr.psr2_support)
+		if (dev_priv->psr.psr2_enabled)
 			WARN_ON(I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE);
 		else
 			WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
@@ -789,53 +883,59 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 	cancel_delayed_work_sync(&dev_priv->psr.work);
 }
 
-static void intel_psr_work(struct work_struct *work)
+static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), psr.work.work);
-	struct intel_dp *intel_dp = dev_priv->psr.enabled;
-	struct drm_crtc *crtc = dp_to_dig_port(intel_dp)->base.base.crtc;
-	enum pipe pipe = to_intel_crtc(crtc)->pipe;
+	struct intel_dp *intel_dp;
+	i915_reg_t reg;
+	u32 mask;
+	int err;
+
+	intel_dp = dev_priv->psr.enabled;
+	if (!intel_dp)
+		return false;
 
-	/* We have to make sure PSR is ready for re-enable
-	 * otherwise it keeps disabled until next full enable/disable cycle.
-	 * PSR might take some time to get fully disabled
-	 * and be ready for re-enable.
-	 */
 	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.psr2_support) {
-			if (intel_wait_for_register(dev_priv,
-						    EDP_PSR2_STATUS,
-						    EDP_PSR2_STATUS_STATE_MASK,
-						    0,
-						    50)) {
-				DRM_ERROR("Timed out waiting for PSR2 Idle for re-enable\n");
-				return;
-			}
+		if (dev_priv->psr.psr2_enabled) {
+			reg = EDP_PSR2_STATUS;
+			mask = EDP_PSR2_STATUS_STATE_MASK;
 		} else {
-			if (intel_wait_for_register(dev_priv,
-						    EDP_PSR_STATUS,
-						    EDP_PSR_STATUS_STATE_MASK,
-						    0,
-						    50)) {
-				DRM_ERROR("Timed out waiting for PSR Idle for re-enable\n");
-				return;
-			}
+			reg = EDP_PSR_STATUS;
+			mask = EDP_PSR_STATUS_STATE_MASK;
 		}
 	} else {
-		if (intel_wait_for_register(dev_priv,
-					    VLV_PSRSTAT(pipe),
-					    VLV_EDP_PSR_IN_TRANS,
-					    0,
-					    1)) {
-			DRM_ERROR("Timed out waiting for PSR Idle for re-enable\n");
-			return;
-		}
+		struct drm_crtc *crtc =
+			dp_to_dig_port(intel_dp)->base.base.crtc;
+		enum pipe pipe = to_intel_crtc(crtc)->pipe;
+
+		reg = VLV_PSRSTAT(pipe);
+		mask = VLV_EDP_PSR_IN_TRANS;
 	}
+
+	mutex_unlock(&dev_priv->psr.lock);
+
+	err = intel_wait_for_register(dev_priv, reg, mask, 0, 50);
+	if (err)
+		DRM_ERROR("Timed out waiting for PSR Idle for re-enable\n");
+
+	/* After the unlocked wait, verify that PSR is still wanted! */
 	mutex_lock(&dev_priv->psr.lock);
-	intel_dp = dev_priv->psr.enabled;
+	return err == 0 && dev_priv->psr.enabled;
+}
 
-	if (!intel_dp)
+static void intel_psr_work(struct work_struct *work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(work, typeof(*dev_priv), psr.work.work);
+
+	mutex_lock(&dev_priv->psr.lock);
+
+	/*
+	 * We have to make sure PSR is ready for re-enable
+	 * otherwise it keeps disabled until next full enable/disable cycle.
+	 * PSR might take some time to get fully disabled
+	 * and be ready for re-enable.
+	 */
+	if (!psr_wait_for_idle(dev_priv))
 		goto unlock;
 
 	/*
@@ -846,7 +946,7 @@ static void intel_psr_work(struct work_struct *work)
 	if (dev_priv->psr.busy_frontbuffer_bits)
 		goto unlock;
 
-	intel_psr_activate(intel_dp);
+	intel_psr_activate(dev_priv->psr.enabled);
 unlock:
 	mutex_unlock(&dev_priv->psr.lock);
 }
@@ -862,11 +962,7 @@ static void intel_psr_exit(struct drm_i915_private *dev_priv)
 		return;
 
 	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.aux_frame_sync)
-			drm_dp_dpcd_writeb(&intel_dp->aux,
-					DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF,
-					0);
-		if (dev_priv->psr.psr2_support) {
+		if (dev_priv->psr.psr2_enabled) {
 			val = I915_READ(EDP_PSR2_CTL);
 			WARN_ON(!(val & EDP_PSR2_ENABLE));
 			I915_WRITE(EDP_PSR2_CTL, val & ~EDP_PSR2_ENABLE);
@@ -957,6 +1053,7 @@ void intel_psr_single_frame_update(struct drm_i915_private *dev_priv,
  * intel_psr_invalidate - Invalidade PSR
  * @dev_priv: i915 device
  * @frontbuffer_bits: frontbuffer plane tracking bits
+ * @origin: which operation caused the invalidate
  *
  * Since the hardware frontbuffer tracking has gaps we need to integrate
  * with the software frontbuffer tracking. This function gets called every
@@ -966,7 +1063,7 @@ void intel_psr_single_frame_update(struct drm_i915_private *dev_priv,
  * Dirty frontbuffers relevant to PSR are tracked in busy_frontbuffer_bits."
  */
 void intel_psr_invalidate(struct drm_i915_private *dev_priv,
-			  unsigned frontbuffer_bits)
+			  unsigned frontbuffer_bits, enum fb_op_origin origin)
 {
 	struct drm_crtc *crtc;
 	enum pipe pipe;
@@ -974,6 +1071,9 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv,
 	if (!CAN_PSR(dev_priv))
 		return;
 
+	if (dev_priv->psr.has_hw_tracking && origin == ORIGIN_FLIP)
+		return;
+
 	mutex_lock(&dev_priv->psr.lock);
 	if (!dev_priv->psr.enabled) {
 		mutex_unlock(&dev_priv->psr.lock);
@@ -1014,6 +1114,9 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 	if (!CAN_PSR(dev_priv))
 		return;
 
+	if (dev_priv->psr.has_hw_tracking && origin == ORIGIN_FLIP)
+		return;
+
 	mutex_lock(&dev_priv->psr.lock);
 	if (!dev_priv->psr.enabled) {
 		mutex_unlock(&dev_priv->psr.lock);
@@ -1027,8 +1130,23 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 	dev_priv->psr.busy_frontbuffer_bits &= ~frontbuffer_bits;
 
 	/* By definition flush = invalidate + flush */
-	if (frontbuffer_bits)
-		intel_psr_exit(dev_priv);
+	if (frontbuffer_bits) {
+		if (dev_priv->psr.psr2_enabled ||
+		    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+			intel_psr_exit(dev_priv);
+		} else {
+			/*
+			 * Display WA #0884: all
+			 * This documented WA for bxt can be safely applied
+			 * broadly so we can force HW tracking to exit PSR
+			 * instead of disabling and re-enabling.
+			 * Workaround tells us to write 0 to CUR_SURFLIVE_A,
+			 * but it makes more sense write to the current active
+			 * pipe.
+			 */
+			I915_WRITE(CURSURFLIVE(pipe), 0);
+		}
+	}
 
 	if (!dev_priv->psr.active && !dev_priv->psr.busy_frontbuffer_bits)
 		if (!work_busy(&dev_priv->psr.work.work))
@@ -1055,9 +1173,12 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	if (!dev_priv->psr.sink_support)
 		return;
 
-	/* Per platform default: all disabled. */
-	if (i915_modparams.enable_psr == -1)
+	if (i915_modparams.enable_psr == -1) {
+		i915_modparams.enable_psr = dev_priv->vbt.psr.enable;
+
+		/* Per platform default: all disabled. */
 		i915_modparams.enable_psr = 0;
+	}
 
 	/* Set link_standby x link_off defaults */
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
@@ -1090,6 +1211,7 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 		dev_priv->psr.activate = vlv_psr_activate;
 		dev_priv->psr.setup_vsc = vlv_psr_setup_vsc;
 	} else {
+		dev_priv->psr.has_hw_tracking = true;
 		dev_priv->psr.enable_source = hsw_psr_enable_source;
 		dev_priv->psr.disable_source = hsw_psr_disable;
 		dev_priv->psr.enable_sink = hsw_psr_enable_sink;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 1d599524a759..8f19349a6055 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -36,6 +36,7 @@
 #include "i915_gem_render_state.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
+#include "intel_workarounds.h"
 
 /* Rough estimate of the typical request size, performing a flush,
  * set-context and then emitting the batch.
@@ -557,7 +558,8 @@ static void reset_ring_common(struct intel_engine_cs *engine,
 	 */
 	if (request) {
 		struct drm_i915_private *dev_priv = request->i915;
-		struct intel_context *ce = &request->ctx->engine[engine->id];
+		struct intel_context *ce = to_intel_context(request->ctx,
+							    engine);
 		struct i915_hw_ppgtt *ppgtt;
 
 		if (ce->state) {
@@ -599,7 +601,7 @@ static int intel_rcs_ctx_init(struct i915_request *rq)
 {
 	int ret;
 
-	ret = intel_ring_workarounds_emit(rq);
+	ret = intel_ctx_workarounds_emit(rq);
 	if (ret != 0)
 		return ret;
 
@@ -617,6 +619,8 @@ static int init_render_ring(struct intel_engine_cs *engine)
 	if (ret)
 		return ret;
 
+	intel_whitelist_workarounds_apply(engine);
+
 	/* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */
 	if (IS_GEN(dev_priv, 4, 6))
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH));
@@ -658,7 +662,7 @@ static int init_render_ring(struct intel_engine_cs *engine)
 	if (INTEL_GEN(dev_priv) >= 6)
 		I915_WRITE_IMR(engine, ~engine->irq_keep_mask);
 
-	return init_workarounds_ring(engine);
+	return 0;
 }
 
 static u32 *gen6_signal(struct i915_request *rq, u32 *cs)
@@ -693,17 +697,17 @@ static void cancel_requests(struct intel_engine_cs *engine)
 	struct i915_request *request;
 	unsigned long flags;
 
-	spin_lock_irqsave(&engine->timeline->lock, flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	/* Mark all submitted requests as skipped. */
-	list_for_each_entry(request, &engine->timeline->requests, link) {
+	list_for_each_entry(request, &engine->timeline.requests, link) {
 		GEM_BUG_ON(!request->global_seqno);
 		if (!i915_request_completed(request))
 			dma_fence_set_error(&request->fence, -EIO);
 	}
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
-	spin_unlock_irqrestore(&engine->timeline->lock, flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
 static void i9xx_submit_request(struct i915_request *request)
@@ -1062,7 +1066,6 @@ err:
 
 void intel_ring_reset(struct intel_ring *ring, u32 tail)
 {
-	GEM_BUG_ON(!list_empty(&ring->request_list));
 	ring->tail = tail;
 	ring->head = tail;
 	ring->emit = tail;
@@ -1114,19 +1117,24 @@ err:
 }
 
 struct intel_ring *
-intel_engine_create_ring(struct intel_engine_cs *engine, int size)
+intel_engine_create_ring(struct intel_engine_cs *engine,
+			 struct i915_timeline *timeline,
+			 int size)
 {
 	struct intel_ring *ring;
 	struct i915_vma *vma;
 
 	GEM_BUG_ON(!is_power_of_2(size));
 	GEM_BUG_ON(RING_CTL_SIZE(size) & ~RING_NR_PAGES);
+	GEM_BUG_ON(timeline == &engine->timeline);
+	lockdep_assert_held(&engine->i915->drm.struct_mutex);
 
 	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
 	if (!ring)
 		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&ring->request_list);
+	ring->timeline = i915_timeline_get(timeline);
 
 	ring->size = size;
 	/* Workaround an erratum on the i830 which causes a hang if
@@ -1157,12 +1165,13 @@ intel_ring_free(struct intel_ring *ring)
 	i915_vma_close(ring->vma);
 	__i915_gem_object_release_unless_active(obj);
 
+	i915_timeline_put(ring->timeline);
 	kfree(ring);
 }
 
-static int context_pin(struct i915_gem_context *ctx)
+static int context_pin(struct intel_context *ce)
 {
-	struct i915_vma *vma = ctx->engine[RCS].state;
+	struct i915_vma *vma = ce->state;
 	int ret;
 
 	/*
@@ -1253,7 +1262,7 @@ static struct intel_ring *
 intel_ring_context_pin(struct intel_engine_cs *engine,
 		       struct i915_gem_context *ctx)
 {
-	struct intel_context *ce = &ctx->engine[engine->id];
+	struct intel_context *ce = to_intel_context(ctx, engine);
 	int ret;
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
@@ -1275,7 +1284,7 @@ intel_ring_context_pin(struct intel_engine_cs *engine,
 	}
 
 	if (ce->state) {
-		ret = context_pin(ctx);
+		ret = context_pin(ce);
 		if (ret)
 			goto err;
 
@@ -1296,7 +1305,7 @@ err:
 static void intel_ring_context_unpin(struct intel_engine_cs *engine,
 				     struct i915_gem_context *ctx)
 {
-	struct intel_context *ce = &ctx->engine[engine->id];
+	struct intel_context *ce = to_intel_context(ctx, engine);
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
 	GEM_BUG_ON(ce->pin_count == 0);
@@ -1315,6 +1324,7 @@ static void intel_ring_context_unpin(struct intel_engine_cs *engine,
 static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 {
 	struct intel_ring *ring;
+	struct i915_timeline *timeline;
 	int err;
 
 	intel_engine_setup_common(engine);
@@ -1323,7 +1333,14 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 	if (err)
 		goto err;
 
-	ring = intel_engine_create_ring(engine, 32 * PAGE_SIZE);
+	timeline = i915_timeline_create(engine->i915, engine->name);
+	if (IS_ERR(timeline)) {
+		err = PTR_ERR(timeline);
+		goto err;
+	}
+
+	ring = intel_engine_create_ring(engine, timeline, 32 * PAGE_SIZE);
+	i915_timeline_put(timeline);
 	if (IS_ERR(ring)) {
 		err = PTR_ERR(ring);
 		goto err;
@@ -1424,7 +1441,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 
 	*cs++ = MI_NOOP;
 	*cs++ = MI_SET_CONTEXT;
-	*cs++ = i915_ggtt_offset(rq->ctx->engine[RCS].state) | flags;
+	*cs++ = i915_ggtt_offset(to_intel_context(rq->ctx, engine)->state) | flags;
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -1515,7 +1532,7 @@ static int switch_context(struct i915_request *rq)
 		hw_flags = MI_FORCE_RESTORE;
 	}
 
-	if (to_ctx->engine[engine->id].state &&
+	if (to_intel_context(to_ctx, engine)->state &&
 	    (to_ctx != from_ctx || hw_flags & MI_FORCE_RESTORE)) {
 		GEM_BUG_ON(engine->id != RCS);
 
@@ -1563,7 +1580,7 @@ static int ring_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!request->ctx->engine[request->engine->id].pin_count);
+	GEM_BUG_ON(!to_intel_context(request->ctx, request->engine)->pin_count);
 
 	/* Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
@@ -1593,6 +1610,7 @@ static noinline int wait_for_space(struct intel_ring *ring, unsigned int bytes)
 	if (intel_ring_update_space(ring) >= bytes)
 		return 0;
 
+	GEM_BUG_ON(list_empty(&ring->request_list));
 	list_for_each_entry(target, &ring->request_list, ring_link) {
 		/* Would completion of this request free enough space? */
 		if (bytes <= __intel_ring_space(target->postfix,
@@ -1692,17 +1710,18 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
 		need_wrap &= ~1;
 		GEM_BUG_ON(need_wrap > ring->space);
 		GEM_BUG_ON(ring->emit + need_wrap > ring->size);
+		GEM_BUG_ON(!IS_ALIGNED(need_wrap, sizeof(u64)));
 
 		/* Fill the tail with MI_NOOP */
-		memset(ring->vaddr + ring->emit, 0, need_wrap);
-		ring->emit = 0;
+		memset64(ring->vaddr + ring->emit, 0, need_wrap / sizeof(u64));
 		ring->space -= need_wrap;
+		ring->emit = 0;
 	}
 
 	GEM_BUG_ON(ring->emit > ring->size - bytes);
 	GEM_BUG_ON(ring->space < bytes);
 	cs = ring->vaddr + ring->emit;
-	GEM_DEBUG_EXEC(memset(cs, POISON_INUSE, bytes));
+	GEM_DEBUG_EXEC(memset32(cs, POISON_INUSE, bytes / sizeof(*cs)));
 	ring->emit += bytes;
 	ring->space -= bytes;
 
@@ -1712,22 +1731,24 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
 /* Align the ring tail to a cacheline boundary */
 int intel_ring_cacheline_align(struct i915_request *rq)
 {
-	int num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32);
-	u32 *cs;
+	int num_dwords;
+	void *cs;
 
+	num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32);
 	if (num_dwords == 0)
 		return 0;
 
-	num_dwords = CACHELINE_BYTES / sizeof(u32) - num_dwords;
+	num_dwords = CACHELINE_DWORDS - num_dwords;
+	GEM_BUG_ON(num_dwords & 1);
+
 	cs = intel_ring_begin(rq, num_dwords);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
-	while (num_dwords--)
-		*cs++ = MI_NOOP;
-
+	memset64(cs, (u64)MI_NOOP << 32 | MI_NOOP, num_dwords / 2);
 	intel_ring_advance(rq, cs);
 
+	GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1));
 	return 0;
 }
 
@@ -1943,8 +1964,6 @@ static void intel_ring_init_semaphores(struct drm_i915_private *dev_priv,
 static void intel_ring_init_irq(struct drm_i915_private *dev_priv,
 				struct intel_engine_cs *engine)
 {
-	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << engine->irq_shift;
-
 	if (INTEL_GEN(dev_priv) >= 6) {
 		engine->irq_enable = gen6_irq_enable;
 		engine->irq_disable = gen6_irq_disable;
@@ -2029,6 +2048,8 @@ int intel_init_render_ring_buffer(struct intel_engine_cs *engine)
 	if (HAS_L3_DPF(dev_priv))
 		engine->irq_keep_mask = GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
 
+	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
+
 	if (INTEL_GEN(dev_priv) >= 6) {
 		engine->init_context = intel_rcs_ctx_init;
 		engine->emit_flush = gen7_render_ring_flush;
@@ -2079,7 +2100,6 @@ int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine)
 		engine->emit_flush = gen6_bsd_ring_flush;
 		engine->irq_enable_mask = GT_BSD_USER_INTERRUPT;
 	} else {
-		engine->mmio_base = BSD_RING_BASE;
 		engine->emit_flush = bsd_ring_flush;
 		if (IS_GEN5(dev_priv))
 			engine->irq_enable_mask = ILK_BSD_USER_INTERRUPT;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 0320c2c4cfba..010750e8ee44 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -3,15 +3,19 @@
 #define _INTEL_RINGBUFFER_H_
 
 #include <linux/hashtable.h>
+#include <linux/seqlock.h>
 
 #include "i915_gem_batch_pool.h"
-#include "i915_gem_timeline.h"
 
+#include "i915_reg.h"
 #include "i915_pmu.h"
 #include "i915_request.h"
 #include "i915_selftest.h"
+#include "i915_timeline.h"
+#include "intel_gpu_commands.h"
 
 struct drm_printer;
+struct i915_sched_attr;
 
 #define I915_CMD_HASH_ORDER 9
 
@@ -84,7 +88,7 @@ hangcheck_action_to_str(const enum intel_engine_hangcheck_action a)
 }
 
 #define I915_MAX_SLICES	3
-#define I915_MAX_SUBSLICES 3
+#define I915_MAX_SUBSLICES 8
 
 #define instdone_slice_mask(dev_priv__) \
 	(INTEL_GEN(dev_priv__) == 7 ? \
@@ -125,7 +129,9 @@ struct intel_ring {
 	struct i915_vma *vma;
 	void *vaddr;
 
+	struct i915_timeline *timeline;
 	struct list_head request_list;
+	struct list_head active_link;
 
 	u32 head;
 	u32 tail;
@@ -330,10 +336,10 @@ struct intel_engine_cs {
 	u8 instance;
 	u32 context_size;
 	u32 mmio_base;
-	unsigned int irq_shift;
 
 	struct intel_ring *buffer;
-	struct intel_timeline *timeline;
+
+	struct i915_timeline timeline;
 
 	struct drm_i915_gem_object *default_state;
 
@@ -459,7 +465,8 @@ struct intel_engine_cs {
 	 *
 	 * Called under the struct_mutex.
 	 */
-	void		(*schedule)(struct i915_request *request, int priority);
+	void		(*schedule)(struct i915_request *request,
+				    const struct i915_sched_attr *attr);
 
 	/*
 	 * Cancel all requests on the hardware, or queued for execution.
@@ -561,6 +568,7 @@ struct intel_engine_cs {
 
 #define I915_ENGINE_NEEDS_CMD_PARSER BIT(0)
 #define I915_ENGINE_SUPPORTS_STATS   BIT(1)
+#define I915_ENGINE_HAS_PREEMPTION   BIT(2)
 	unsigned int flags;
 
 	/*
@@ -591,7 +599,7 @@ struct intel_engine_cs {
 		/**
 		 * @lock: Lock protecting the below fields.
 		 */
-		spinlock_t lock;
+		seqlock_t lock;
 		/**
 		 * @enabled: Reference count indicating number of listeners.
 		 */
@@ -620,16 +628,29 @@ struct intel_engine_cs {
 	} stats;
 };
 
-static inline bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine)
+static inline bool
+intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine)
 {
 	return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER;
 }
 
-static inline bool intel_engine_supports_stats(struct intel_engine_cs *engine)
+static inline bool
+intel_engine_supports_stats(const struct intel_engine_cs *engine)
 {
 	return engine->flags & I915_ENGINE_SUPPORTS_STATS;
 }
 
+static inline bool
+intel_engine_has_preemption(const struct intel_engine_cs *engine)
+{
+	return engine->flags & I915_ENGINE_HAS_PREEMPTION;
+}
+
+static inline bool __execlists_need_preempt(int prio, int last)
+{
+	return prio > max(0, last);
+}
+
 static inline void
 execlists_set_active(struct intel_engine_execlists *execlists,
 		     unsigned int bit)
@@ -637,6 +658,13 @@ execlists_set_active(struct intel_engine_execlists *execlists,
 	__set_bit(bit, (unsigned long *)&execlists->active);
 }
 
+static inline bool
+execlists_set_active_once(struct intel_engine_execlists *execlists,
+			  unsigned int bit)
+{
+	return !__test_and_set_bit(bit, (unsigned long *)&execlists->active);
+}
+
 static inline void
 execlists_clear_active(struct intel_engine_execlists *execlists,
 		       unsigned int bit)
@@ -651,6 +679,10 @@ execlists_is_active(const struct intel_engine_execlists *execlists,
 	return test_bit(bit, (unsigned long *)&execlists->active);
 }
 
+void execlists_user_begin(struct intel_engine_execlists *execlists,
+			  const struct execlist_port *port);
+void execlists_user_end(struct intel_engine_execlists *execlists);
+
 void
 execlists_cancel_port_requests(struct intel_engine_execlists * const execlists);
 
@@ -663,7 +695,7 @@ execlists_num_ports(const struct intel_engine_execlists * const execlists)
 	return execlists->port_mask + 1;
 }
 
-static inline void
+static inline struct execlist_port *
 execlists_port_complete(struct intel_engine_execlists * const execlists,
 			struct execlist_port * const port)
 {
@@ -674,6 +706,8 @@ execlists_port_complete(struct intel_engine_execlists * const execlists,
 
 	memmove(port, port + 1, m * sizeof(struct execlist_port));
 	memset(port + m, 0, sizeof(struct execlist_port));
+
+	return port;
 }
 
 static inline unsigned int
@@ -736,7 +770,9 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
 #define CNL_HWS_CSB_WRITE_INDEX		0x2f
 
 struct intel_ring *
-intel_engine_create_ring(struct intel_engine_cs *engine, int size);
+intel_engine_create_ring(struct intel_engine_cs *engine,
+			 struct i915_timeline *timeline,
+			 int size);
 int intel_ring_pin(struct intel_ring *ring,
 		   struct drm_i915_private *i915,
 		   unsigned int offset_bias);
@@ -854,12 +890,9 @@ static inline u32 intel_engine_last_submit(struct intel_engine_cs *engine)
 	 * wtih serialising this hint with anything, so document it as
 	 * a hint and nothing more.
 	 */
-	return READ_ONCE(engine->timeline->seqno);
+	return READ_ONCE(engine->timeline.seqno);
 }
 
-int init_workarounds_ring(struct intel_engine_cs *engine);
-int intel_ring_workarounds_emit(struct i915_request *rq);
-
 void intel_engine_get_instdone(struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone);
 
@@ -939,7 +972,7 @@ bool intel_engine_add_wait(struct intel_engine_cs *engine,
 			   struct intel_wait *wait);
 void intel_engine_remove_wait(struct intel_engine_cs *engine,
 			      struct intel_wait *wait);
-void intel_engine_enable_signaling(struct i915_request *request, bool wakeup);
+bool intel_engine_enable_signaling(struct i915_request *request, bool wakeup);
 void intel_engine_cancel_signaling(struct i915_request *request);
 
 static inline bool intel_engine_has_waiter(const struct intel_engine_cs *engine)
@@ -1037,7 +1070,7 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine)
 	if (READ_ONCE(engine->stats.enabled) == 0)
 		return;
 
-	spin_lock_irqsave(&engine->stats.lock, flags);
+	write_seqlock_irqsave(&engine->stats.lock, flags);
 
 	if (engine->stats.enabled > 0) {
 		if (engine->stats.active++ == 0)
@@ -1045,7 +1078,7 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine)
 		GEM_BUG_ON(engine->stats.active == 0);
 	}
 
-	spin_unlock_irqrestore(&engine->stats.lock, flags);
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
 static inline void intel_engine_context_out(struct intel_engine_cs *engine)
@@ -1055,7 +1088,7 @@ static inline void intel_engine_context_out(struct intel_engine_cs *engine)
 	if (READ_ONCE(engine->stats.enabled) == 0)
 		return;
 
-	spin_lock_irqsave(&engine->stats.lock, flags);
+	write_seqlock_irqsave(&engine->stats.lock, flags);
 
 	if (engine->stats.enabled > 0) {
 		ktime_t last;
@@ -1082,7 +1115,7 @@ static inline void intel_engine_context_out(struct intel_engine_cs *engine)
 		}
 	}
 
-	spin_unlock_irqrestore(&engine->stats.lock, flags);
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
 int intel_enable_engine_stats(struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 53ea564f971e..53a6eaa9671a 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -542,6 +542,29 @@ void gen9_sanitize_dc_state(struct drm_i915_private *dev_priv)
 	dev_priv->csr.dc_state = val;
 }
 
+/**
+ * gen9_set_dc_state - set target display C power state
+ * @dev_priv: i915 device instance
+ * @state: target DC power state
+ * - DC_STATE_DISABLE
+ * - DC_STATE_EN_UPTO_DC5
+ * - DC_STATE_EN_UPTO_DC6
+ * - DC_STATE_EN_DC9
+ *
+ * Signal to DMC firmware/HW the target DC power state passed in @state.
+ * DMC/HW can turn off individual display clocks and power rails when entering
+ * a deeper DC power state (higher in number) and turns these back when exiting
+ * that state to a shallower power state (lower in number). The HW will decide
+ * when to actually enter a given state on an on-demand basis, for instance
+ * depending on the active state of display pipes. The state of display
+ * registers backed by affected power rails are saved/restored as needed.
+ *
+ * Based on the above enabling a deeper DC power state is asynchronous wrt.
+ * enabling it. Disabling a deeper power state is synchronous: for instance
+ * setting %DC_STATE_DISABLE won't complete until all HW resources are turned
+ * back on and register state is restored. This is guaranteed by the MMIO write
+ * to DC_STATE_EN blocking until the state is restored.
+ */
 static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state)
 {
 	uint32_t val;
@@ -635,26 +658,18 @@ static void assert_can_enable_dc6(struct drm_i915_private *dev_priv)
 	assert_csr_loaded(dev_priv);
 }
 
-void skl_enable_dc6(struct drm_i915_private *dev_priv)
+static void skl_enable_dc6(struct drm_i915_private *dev_priv)
 {
 	assert_can_enable_dc6(dev_priv);
 
 	DRM_DEBUG_KMS("Enabling DC6\n");
 
-	gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
-
-}
-
-void skl_disable_dc6(struct drm_i915_private *dev_priv)
-{
-	DRM_DEBUG_KMS("Disabling DC6\n");
-
 	/* Wa Display #1183: skl,kbl,cfl */
 	if (IS_GEN9_BC(dev_priv))
 		I915_WRITE(GEN8_CHICKEN_DCPR_1, I915_READ(GEN8_CHICKEN_DCPR_1) |
 			   SKL_SELECT_ALTERNATE_DC_EXIT);
 
-	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
+	gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
 }
 
 static void hsw_power_well_sync_hw(struct drm_i915_private *dev_priv,
@@ -2627,32 +2642,69 @@ static void intel_power_domains_sync_hw(struct drm_i915_private *dev_priv)
 	mutex_unlock(&power_domains->lock);
 }
 
-static void gen9_dbuf_enable(struct drm_i915_private *dev_priv)
+static inline
+bool intel_dbuf_slice_set(struct drm_i915_private *dev_priv,
+			  i915_reg_t reg, bool enable)
 {
-	I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) | DBUF_POWER_REQUEST);
-	POSTING_READ(DBUF_CTL);
+	u32 val, status;
 
+	val = I915_READ(reg);
+	val = enable ? (val | DBUF_POWER_REQUEST) : (val & ~DBUF_POWER_REQUEST);
+	I915_WRITE(reg, val);
+	POSTING_READ(reg);
 	udelay(10);
 
-	if (!(I915_READ(DBUF_CTL) & DBUF_POWER_STATE))
-		DRM_ERROR("DBuf power enable timeout\n");
+	status = I915_READ(reg) & DBUF_POWER_STATE;
+	if ((enable && !status) || (!enable && status)) {
+		DRM_ERROR("DBus power %s timeout!\n",
+			  enable ? "enable" : "disable");
+		return false;
+	}
+	return true;
+}
+
+static void gen9_dbuf_enable(struct drm_i915_private *dev_priv)
+{
+	intel_dbuf_slice_set(dev_priv, DBUF_CTL, true);
 }
 
 static void gen9_dbuf_disable(struct drm_i915_private *dev_priv)
 {
-	I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) & ~DBUF_POWER_REQUEST);
-	POSTING_READ(DBUF_CTL);
+	intel_dbuf_slice_set(dev_priv, DBUF_CTL, false);
+}
 
-	udelay(10);
+static u8 intel_dbuf_max_slices(struct drm_i915_private *dev_priv)
+{
+	if (INTEL_GEN(dev_priv) < 11)
+		return 1;
+	return 2;
+}
 
-	if (I915_READ(DBUF_CTL) & DBUF_POWER_STATE)
-		DRM_ERROR("DBuf power disable timeout!\n");
+void icl_dbuf_slices_update(struct drm_i915_private *dev_priv,
+			    u8 req_slices)
+{
+	u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices;
+	u32 val;
+	bool ret;
+
+	if (req_slices > intel_dbuf_max_slices(dev_priv)) {
+		DRM_ERROR("Invalid number of dbuf slices requested\n");
+		return;
+	}
+
+	if (req_slices == hw_enabled_slices || req_slices == 0)
+		return;
+
+	val = I915_READ(DBUF_CTL_S2);
+	if (req_slices > hw_enabled_slices)
+		ret = intel_dbuf_slice_set(dev_priv, DBUF_CTL_S2, true);
+	else
+		ret = intel_dbuf_slice_set(dev_priv, DBUF_CTL_S2, false);
+
+	if (ret)
+		dev_priv->wm.skl_hw.ddb.enabled_slices = req_slices;
 }
 
-/*
- * TODO: we shouldn't always enable DBUF_CTL_S2, we should only enable it when
- * needed and keep it disabled as much as possible.
- */
 static void icl_dbuf_enable(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(DBUF_CTL_S1, I915_READ(DBUF_CTL_S1) | DBUF_POWER_REQUEST);
@@ -2664,6 +2716,8 @@ static void icl_dbuf_enable(struct drm_i915_private *dev_priv)
 	if (!(I915_READ(DBUF_CTL_S1) & DBUF_POWER_STATE) ||
 	    !(I915_READ(DBUF_CTL_S2) & DBUF_POWER_STATE))
 		DRM_ERROR("DBuf power enable timeout\n");
+	else
+		dev_priv->wm.skl_hw.ddb.enabled_slices = 2;
 }
 
 static void icl_dbuf_disable(struct drm_i915_private *dev_priv)
@@ -2677,6 +2731,8 @@ static void icl_dbuf_disable(struct drm_i915_private *dev_priv)
 	if ((I915_READ(DBUF_CTL_S1) & DBUF_POWER_STATE) ||
 	    (I915_READ(DBUF_CTL_S2) & DBUF_POWER_STATE))
 		DRM_ERROR("DBuf power disable timeout!\n");
+	else
+		dev_priv->wm.skl_hw.ddb.enabled_slices = 0;
 }
 
 static void icl_mbus_init(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 96e213ec202d..25005023c243 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -2779,9 +2779,8 @@ static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo,
 		return false;
 
 	for (i = 0; i < intel_sdvo_connector->format_supported_num; i++)
-		drm_property_add_enum(
-				intel_sdvo_connector->tv_format, i,
-				i, tv_format_names[intel_sdvo_connector->tv_format_supported[i]]);
+		drm_property_add_enum(intel_sdvo_connector->tv_format, i,
+				      tv_format_names[intel_sdvo_connector->tv_format_supported[i]]);
 
 	intel_sdvo_connector->base.base.state->tv.mode = intel_sdvo_connector->tv_format_supported[0];
 	drm_object_attach_property(&intel_sdvo_connector->base.base.base,
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index dbdcf85032df..ee23613f9fd4 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -48,6 +48,7 @@ bool intel_format_is_yuv(u32 format)
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_VYUY:
 	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_NV12:
 		return true;
 	default:
 		return false;
@@ -130,7 +131,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 		if (scanline < min || scanline > max)
 			break;
 
-		if (timeout <= 0) {
+		if (!timeout) {
 			DRM_ERROR("Potential atomic update failure on pipe %c\n",
 				  pipe_name(crtc->pipe));
 			break;
@@ -935,20 +936,11 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_framebuffer *fb = state->base.fb;
-	int crtc_x, crtc_y;
-	unsigned int crtc_w, crtc_h;
-	uint32_t src_x, src_y, src_w, src_h;
-	struct drm_rect *src = &state->base.src;
-	struct drm_rect *dst = &state->base.dst;
-	struct drm_rect clip = {};
 	int max_stride = INTEL_GEN(dev_priv) >= 9 ? 32768 : 16384;
-	int hscale, vscale;
 	int max_scale, min_scale;
 	bool can_scale;
 	int ret;
-
-	*src = drm_plane_state_src(&state->base);
-	*dst = drm_plane_state_dest(&state->base);
+	uint32_t pixel_format = 0;
 
 	if (!fb) {
 		state->base.visible = false;
@@ -969,11 +961,14 @@ intel_check_sprite_plane(struct intel_plane *plane,
 
 	/* setup can_scale, min_scale, max_scale */
 	if (INTEL_GEN(dev_priv) >= 9) {
+		if (state->base.fb)
+			pixel_format = state->base.fb->format->format;
 		/* use scaler when colorkey is not required */
 		if (!state->ckey.flags) {
 			can_scale = 1;
 			min_scale = 1;
-			max_scale = skl_max_scale(crtc, crtc_state);
+			max_scale =
+				skl_max_scale(crtc, crtc_state, pixel_format);
 		} else {
 			can_scale = 0;
 			min_scale = DRM_PLANE_HELPER_NO_SCALING;
@@ -985,64 +980,19 @@ intel_check_sprite_plane(struct intel_plane *plane,
 		min_scale = plane->can_scale ? 1 : (1 << 16);
 	}
 
-	/*
-	 * FIXME the following code does a bunch of fuzzy adjustments to the
-	 * coordinates and sizes. We probably need some way to decide whether
-	 * more strict checking should be done instead.
-	 */
-	drm_rect_rotate(src, fb->width << 16, fb->height << 16,
-			state->base.rotation);
-
-	hscale = drm_rect_calc_hscale_relaxed(src, dst, min_scale, max_scale);
-	BUG_ON(hscale < 0);
-
-	vscale = drm_rect_calc_vscale_relaxed(src, dst, min_scale, max_scale);
-	BUG_ON(vscale < 0);
-
-	if (crtc_state->base.enable)
-		drm_mode_get_hv_timing(&crtc_state->base.mode,
-				       &clip.x2, &clip.y2);
-
-	state->base.visible = drm_rect_clip_scaled(src, dst, &clip, hscale, vscale);
-
-	crtc_x = dst->x1;
-	crtc_y = dst->y1;
-	crtc_w = drm_rect_width(dst);
-	crtc_h = drm_rect_height(dst);
+	ret = drm_atomic_helper_check_plane_state(&state->base,
+						  &crtc_state->base,
+						  min_scale, max_scale,
+						  true, true);
+	if (ret)
+		return ret;
 
 	if (state->base.visible) {
-		/* check again in case clipping clamped the results */
-		hscale = drm_rect_calc_hscale(src, dst, min_scale, max_scale);
-		if (hscale < 0) {
-			DRM_DEBUG_KMS("Horizontal scaling factor out of limits\n");
-			drm_rect_debug_print("src: ", src, true);
-			drm_rect_debug_print("dst: ", dst, false);
-
-			return hscale;
-		}
-
-		vscale = drm_rect_calc_vscale(src, dst, min_scale, max_scale);
-		if (vscale < 0) {
-			DRM_DEBUG_KMS("Vertical scaling factor out of limits\n");
-			drm_rect_debug_print("src: ", src, true);
-			drm_rect_debug_print("dst: ", dst, false);
-
-			return vscale;
-		}
-
-		/* Make the source viewport size an exact multiple of the scaling factors. */
-		drm_rect_adjust_size(src,
-				     drm_rect_width(dst) * hscale - drm_rect_width(src),
-				     drm_rect_height(dst) * vscale - drm_rect_height(src));
-
-		drm_rect_rotate_inv(src, fb->width << 16, fb->height << 16,
-				    state->base.rotation);
-
-		/* sanity check to make sure the src viewport wasn't enlarged */
-		WARN_ON(src->x1 < (int) state->base.src_x ||
-			src->y1 < (int) state->base.src_y ||
-			src->x2 > (int) state->base.src_x + state->base.src_w ||
-			src->y2 > (int) state->base.src_y + state->base.src_h);
+		struct drm_rect *src = &state->base.src;
+		struct drm_rect *dst = &state->base.dst;
+		unsigned int crtc_w = drm_rect_width(dst);
+		unsigned int crtc_h = drm_rect_height(dst);
+		uint32_t src_x, src_y, src_w, src_h;
 
 		/*
 		 * Hardware doesn't handle subpixel coordinates.
@@ -1055,58 +1005,40 @@ intel_check_sprite_plane(struct intel_plane *plane,
 		src_y = src->y1 >> 16;
 		src_h = drm_rect_height(src) >> 16;
 
-		if (intel_format_is_yuv(fb->format->format)) {
-			src_x &= ~1;
-			src_w &= ~1;
-
-			/*
-			 * Must keep src and dst the
-			 * same if we can't scale.
-			 */
-			if (!can_scale)
-				crtc_w &= ~1;
+		src->x1 = src_x << 16;
+		src->x2 = (src_x + src_w) << 16;
+		src->y1 = src_y << 16;
+		src->y2 = (src_y + src_h) << 16;
 
-			if (crtc_w == 0)
-				state->base.visible = false;
+		if (intel_format_is_yuv(fb->format->format) &&
+    		    fb->format->format != DRM_FORMAT_NV12 &&
+		    (src_x % 2 || src_w % 2)) {
+			DRM_DEBUG_KMS("src x/w (%u, %u) must be a multiple of 2 for YUV planes\n",
+				      src_x, src_w);
+			return -EINVAL;
 		}
-	}
-
-	/* Check size restrictions when scaling */
-	if (state->base.visible && (src_w != crtc_w || src_h != crtc_h)) {
-		unsigned int width_bytes;
-		int cpp = fb->format->cpp[0];
 
-		WARN_ON(!can_scale);
+		/* Check size restrictions when scaling */
+		if (src_w != crtc_w || src_h != crtc_h) {
+			unsigned int width_bytes;
+			int cpp = fb->format->cpp[0];
 
-		/* FIXME interlacing min height is 6 */
+			WARN_ON(!can_scale);
 
-		if (crtc_w < 3 || crtc_h < 3)
-			state->base.visible = false;
+			width_bytes = ((src_x * cpp) & 63) + src_w * cpp;
 
-		if (src_w < 3 || src_h < 3)
-			state->base.visible = false;
-
-		width_bytes = ((src_x * cpp) & 63) + src_w * cpp;
-
-		if (INTEL_GEN(dev_priv) < 9 && (src_w > 2048 || src_h > 2048 ||
-		    width_bytes > 4096 || fb->pitches[0] > 4096)) {
-			DRM_DEBUG_KMS("Source dimensions exceed hardware limits\n");
-			return -EINVAL;
+			/* FIXME interlacing min height is 6 */
+			if (INTEL_GEN(dev_priv) < 9 && (
+			     src_w < 3 || src_h < 3 ||
+			     src_w > 2048 || src_h > 2048 ||
+			     crtc_w < 3 || crtc_h < 3 ||
+			     width_bytes > 4096 || fb->pitches[0] > 4096)) {
+				DRM_DEBUG_KMS("Source dimensions exceed hardware limits\n");
+				return -EINVAL;
+			}
 		}
 	}
 
-	if (state->base.visible) {
-		src->x1 = src_x << 16;
-		src->x2 = (src_x + src_w) << 16;
-		src->y1 = src_y << 16;
-		src->y2 = (src_y + src_h) << 16;
-	}
-
-	dst->x1 = crtc_x;
-	dst->x2 = crtc_x + crtc_w;
-	dst->y1 = crtc_y;
-	dst->y2 = crtc_y + crtc_h;
-
 	if (INTEL_GEN(dev_priv) >= 9) {
 		ret = skl_check_plane_surface(crtc_state, state);
 		if (ret)
@@ -1248,6 +1180,19 @@ static uint32_t skl_plane_formats[] = {
 	DRM_FORMAT_VYUY,
 };
 
+static uint32_t skl_planar_formats[] = {
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_NV12,
+};
+
 static const uint64_t skl_plane_format_modifiers_noccs[] = {
 	I915_FORMAT_MOD_Yf_TILED,
 	I915_FORMAT_MOD_Y_TILED,
@@ -1342,6 +1287,7 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier)
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_VYUY:
+	case DRM_FORMAT_NV12:
 		if (modifier == I915_FORMAT_MOD_Yf_TILED)
 			return true;
 		/* fall through */
@@ -1441,8 +1387,14 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		intel_plane->disable_plane = skl_disable_plane;
 		intel_plane->get_hw_state = skl_plane_get_hw_state;
 
-		plane_formats = skl_plane_formats;
-		num_plane_formats = ARRAY_SIZE(skl_plane_formats);
+		if (skl_plane_has_planar(dev_priv, pipe,
+					 PLANE_SPRITE0 + plane)) {
+			plane_formats = skl_planar_formats;
+			num_plane_formats = ARRAY_SIZE(skl_planar_formats);
+		} else {
+			plane_formats = skl_plane_formats;
+			num_plane_formats = ARRAY_SIZE(skl_plane_formats);
+		}
 
 		if (skl_plane_has_ccs(dev_priv, pipe, PLANE_SPRITE0 + plane))
 			modifiers = skl_plane_format_modifiers_ccs;
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index e5bf0d37bf43..1cffaf7b5dbe 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -69,13 +69,15 @@ static int __get_platform_enable_guc(struct drm_i915_private *dev_priv)
 
 static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
 {
-	int guc_log_level = 0; /* disabled */
+	int guc_log_level;
 
-	/* Enable if we're running on platform with GuC and debug config */
-	if (HAS_GUC(dev_priv) && intel_uc_is_using_guc() &&
-	    (IS_ENABLED(CONFIG_DRM_I915_DEBUG) ||
-	     IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)))
-		guc_log_level = 1 + GUC_LOG_VERBOSITY_MAX;
+	if (!HAS_GUC(dev_priv) || !intel_uc_is_using_guc())
+		guc_log_level = GUC_LOG_LEVEL_DISABLED;
+	else if (IS_ENABLED(CONFIG_DRM_I915_DEBUG) ||
+		 IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		guc_log_level = GUC_LOG_LEVEL_MAX;
+	else
+		guc_log_level = GUC_LOG_LEVEL_NON_VERBOSE;
 
 	/* Any platform specific fine-tuning can be done here */
 
@@ -83,7 +85,7 @@ static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
 }
 
 /**
- * intel_uc_sanitize_options - sanitize uC related modparam options
+ * sanitize_options_early - sanitize uC related modparam options
  * @dev_priv: device private
  *
  * In case of "enable_guc" option this function will attempt to modify
@@ -99,7 +101,7 @@ static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
  * unless GuC is enabled on given platform and the driver is compiled with
  * debug config when this modparam will default to "enable(1..4)".
  */
-void intel_uc_sanitize_options(struct drm_i915_private *dev_priv)
+static void sanitize_options_early(struct drm_i915_private *dev_priv)
 {
 	struct intel_uc_fw *guc_fw = &dev_priv->guc.fw;
 	struct intel_uc_fw *huc_fw = &dev_priv->huc.fw;
@@ -142,51 +144,53 @@ void intel_uc_sanitize_options(struct drm_i915_private *dev_priv)
 		i915_modparams.guc_log_level = 0;
 	}
 
-	if (i915_modparams.guc_log_level > 1 + GUC_LOG_VERBOSITY_MAX) {
+	if (i915_modparams.guc_log_level > GUC_LOG_LEVEL_MAX) {
 		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
 			 "guc_log_level", i915_modparams.guc_log_level,
 			 "verbosity too high");
-		i915_modparams.guc_log_level = 1 + GUC_LOG_VERBOSITY_MAX;
+		i915_modparams.guc_log_level = GUC_LOG_LEVEL_MAX;
 	}
 
-	DRM_DEBUG_DRIVER("guc_log_level=%d (enabled:%s verbosity:%d)\n",
+	DRM_DEBUG_DRIVER("guc_log_level=%d (enabled:%s, verbose:%s, verbosity:%d)\n",
 			 i915_modparams.guc_log_level,
 			 yesno(i915_modparams.guc_log_level),
-			 i915_modparams.guc_log_level - 1);
+			 yesno(GUC_LOG_LEVEL_IS_VERBOSE(i915_modparams.guc_log_level)),
+			 GUC_LOG_LEVEL_TO_VERBOSITY(i915_modparams.guc_log_level));
 
 	/* Make sure that sanitization was done */
 	GEM_BUG_ON(i915_modparams.enable_guc < 0);
 	GEM_BUG_ON(i915_modparams.guc_log_level < 0);
 }
 
-void intel_uc_init_early(struct drm_i915_private *dev_priv)
+void intel_uc_init_early(struct drm_i915_private *i915)
 {
-	intel_guc_init_early(&dev_priv->guc);
-	intel_huc_init_early(&dev_priv->huc);
-}
+	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 
-void intel_uc_init_fw(struct drm_i915_private *dev_priv)
-{
-	if (!USES_GUC(dev_priv))
-		return;
+	intel_guc_init_early(guc);
+	intel_huc_init_early(huc);
 
-	if (USES_HUC(dev_priv))
-		intel_uc_fw_fetch(dev_priv, &dev_priv->huc.fw);
+	sanitize_options_early(i915);
 
-	intel_uc_fw_fetch(dev_priv, &dev_priv->guc.fw);
+	if (USES_GUC(i915))
+		intel_uc_fw_fetch(i915, &guc->fw);
+
+	if (USES_HUC(i915))
+		intel_uc_fw_fetch(i915, &huc->fw);
 }
 
-void intel_uc_fini_fw(struct drm_i915_private *dev_priv)
+void intel_uc_cleanup_early(struct drm_i915_private *i915)
 {
-	if (!USES_GUC(dev_priv))
-		return;
+	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 
-	intel_uc_fw_fini(&dev_priv->guc.fw);
+	if (USES_HUC(i915))
+		intel_uc_fw_fini(&huc->fw);
 
-	if (USES_HUC(dev_priv))
-		intel_uc_fw_fini(&dev_priv->huc.fw);
+	if (USES_GUC(i915))
+		intel_uc_fw_fini(&guc->fw);
 
-	guc_free_load_err_log(&dev_priv->guc);
+	guc_free_load_err_log(guc);
 }
 
 /**
@@ -223,10 +227,13 @@ static int guc_enable_communication(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
+	gen9_enable_guc_interrupts(dev_priv);
+
 	if (HAS_GUC_CT(dev_priv))
-		return intel_guc_enable_ct(guc);
+		return intel_guc_ct_enable(&guc->ct);
 
 	guc->send = intel_guc_send_mmio;
+	guc->handler = intel_guc_to_host_event_handler_mmio;
 	return 0;
 }
 
@@ -235,9 +242,12 @@ static void guc_disable_communication(struct intel_guc *guc)
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
 	if (HAS_GUC_CT(dev_priv))
-		intel_guc_disable_ct(guc);
+		intel_guc_ct_disable(&guc->ct);
+
+	gen9_disable_guc_interrupts(dev_priv);
 
 	guc->send = intel_guc_send_nop;
+	guc->handler = intel_guc_to_host_event_handler_nop;
 }
 
 int intel_uc_init_misc(struct drm_i915_private *dev_priv)
@@ -248,24 +258,13 @@ int intel_uc_init_misc(struct drm_i915_private *dev_priv)
 	if (!USES_GUC(dev_priv))
 		return 0;
 
-	ret = intel_guc_init_wq(guc);
-	if (ret) {
-		DRM_ERROR("Couldn't allocate workqueues for GuC\n");
-		goto err;
-	}
+	intel_guc_init_ggtt_pin_bias(guc);
 
-	ret = intel_guc_log_relay_create(guc);
-	if (ret) {
-		DRM_ERROR("Couldn't allocate relay for GuC log\n");
-		goto err_relay;
-	}
+	ret = intel_guc_init_wq(guc);
+	if (ret)
+		return ret;
 
 	return 0;
-
-err_relay:
-	intel_guc_fini_wq(guc);
-err:
-	return ret;
 }
 
 void intel_uc_fini_misc(struct drm_i915_private *dev_priv)
@@ -276,8 +275,6 @@ void intel_uc_fini_misc(struct drm_i915_private *dev_priv)
 		return;
 
 	intel_guc_fini_wq(guc);
-
-	intel_guc_log_relay_destroy(guc);
 }
 
 int intel_uc_init(struct drm_i915_private *dev_priv)
@@ -325,6 +322,24 @@ void intel_uc_fini(struct drm_i915_private *dev_priv)
 	intel_guc_fini(guc);
 }
 
+void intel_uc_sanitize(struct drm_i915_private *i915)
+{
+	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
+
+	if (!USES_GUC(i915))
+		return;
+
+	GEM_BUG_ON(!HAS_GUC(i915));
+
+	guc_disable_communication(guc);
+
+	intel_huc_sanitize(huc);
+	intel_guc_sanitize(guc);
+
+	__intel_uc_reset_hw(i915);
+}
+
 int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
@@ -336,14 +351,8 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 
 	GEM_BUG_ON(!HAS_GUC(dev_priv));
 
-	guc_disable_communication(guc);
 	gen9_reset_guc_interrupts(dev_priv);
 
-	/* init WOPCM */
-	I915_WRITE(GUC_WOPCM_SIZE, intel_guc_wopcm_size(dev_priv));
-	I915_WRITE(DMA_GUC_WOPCM_OFFSET,
-		   GUC_WOPCM_OFFSET_VALUE | HUC_LOADING_AGENT_GUC);
-
 	/* WaEnableuKernelHeaderValidFix:skl */
 	/* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */
 	if (IS_GEN9(dev_priv))
@@ -390,12 +399,9 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	}
 
 	if (USES_GUC_SUBMISSION(dev_priv)) {
-		if (i915_modparams.guc_log_level)
-			gen9_enable_guc_interrupts(dev_priv);
-
 		ret = intel_guc_submission_enable(guc);
 		if (ret)
-			goto err_interrupts;
+			goto err_communication;
 	}
 
 	dev_info(dev_priv->drm.dev, "GuC firmware version %u.%u\n",
@@ -410,8 +416,6 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	/*
 	 * We've failed to load the firmware :(
 	 */
-err_interrupts:
-	gen9_disable_guc_interrupts(dev_priv);
 err_communication:
 	guc_disable_communication(guc);
 err_log_capture:
@@ -441,9 +445,6 @@ void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
 		intel_guc_submission_disable(guc);
 
 	guc_disable_communication(guc);
-
-	if (USES_GUC_SUBMISSION(dev_priv))
-		gen9_disable_guc_interrupts(dev_priv);
 }
 
 int intel_uc_suspend(struct drm_i915_private *i915)
@@ -479,8 +480,7 @@ int intel_uc_resume(struct drm_i915_private *i915)
 	if (guc->fw.load_status != INTEL_UC_FIRMWARE_SUCCESS)
 		return 0;
 
-	if (i915_modparams.guc_log_level)
-		gen9_enable_guc_interrupts(i915);
+	gen9_enable_guc_interrupts(i915);
 
 	err = intel_guc_resume(guc);
 	if (err) {
diff --git a/drivers/gpu/drm/i915/intel_uc.h b/drivers/gpu/drm/i915/intel_uc.h
index f76d51d1ce70..25d73ada74ae 100644
--- a/drivers/gpu/drm/i915/intel_uc.h
+++ b/drivers/gpu/drm/i915/intel_uc.h
@@ -28,13 +28,12 @@
 #include "intel_huc.h"
 #include "i915_params.h"
 
-void intel_uc_sanitize_options(struct drm_i915_private *dev_priv);
 void intel_uc_init_early(struct drm_i915_private *dev_priv);
+void intel_uc_cleanup_early(struct drm_i915_private *dev_priv);
 void intel_uc_init_mmio(struct drm_i915_private *dev_priv);
-void intel_uc_init_fw(struct drm_i915_private *dev_priv);
-void intel_uc_fini_fw(struct drm_i915_private *dev_priv);
 int intel_uc_init_misc(struct drm_i915_private *dev_priv);
 void intel_uc_fini_misc(struct drm_i915_private *dev_priv);
+void intel_uc_sanitize(struct drm_i915_private *dev_priv);
 int intel_uc_init_hw(struct drm_i915_private *dev_priv);
 void intel_uc_fini_hw(struct drm_i915_private *dev_priv);
 int intel_uc_init(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_uc_fw.c b/drivers/gpu/drm/i915/intel_uc_fw.c
index 3ec0ce505b76..6e8e0b546743 100644
--- a/drivers/gpu/drm/i915/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/intel_uc_fw.c
@@ -95,15 +95,6 @@ void intel_uc_fw_fetch(struct drm_i915_private *dev_priv,
 	uc_fw->ucode_offset = uc_fw->header_offset + uc_fw->header_size;
 	uc_fw->ucode_size = (css->size_dw - css->header_size_dw) * sizeof(u32);
 
-	/* Header and uCode will be loaded to WOPCM */
-	size = uc_fw->header_size + uc_fw->ucode_size;
-	if (size > intel_guc_wopcm_size(dev_priv)) {
-		DRM_WARN("%s: Firmware is too large to fit in WOPCM\n",
-			 intel_uc_fw_type_repr(uc_fw->type));
-		err = -E2BIG;
-		goto fail;
-	}
-
 	/* now RSA */
 	if (css->key_size_dw != UOS_RSA_SCRATCH_COUNT) {
 		DRM_WARN("%s: Mismatched firmware RSA key size (%u)\n",
@@ -209,6 +200,7 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw,
 				   struct i915_vma *vma))
 {
 	struct i915_vma *vma;
+	u32 ggtt_pin_bias;
 	int err;
 
 	DRM_DEBUG_DRIVER("%s fw load %s\n",
@@ -230,8 +222,9 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw,
 		goto fail;
 	}
 
+	ggtt_pin_bias = to_i915(uc_fw->obj->base.dev)->guc.ggtt_pin_bias;
 	vma = i915_gem_object_ggtt_pin(uc_fw->obj, NULL, 0, 0,
-				       PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+				       PIN_OFFSET_BIAS | ggtt_pin_bias);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		DRM_DEBUG_DRIVER("%s fw ggtt-pin err=%d\n",
diff --git a/drivers/gpu/drm/i915/intel_uc_fw.h b/drivers/gpu/drm/i915/intel_uc_fw.h
index d5fd4609c785..87910aa83267 100644
--- a/drivers/gpu/drm/i915/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/intel_uc_fw.h
@@ -30,7 +30,7 @@ struct drm_i915_private;
 struct i915_vma;
 
 /* Home of GuC, HuC and DMC firmwares */
-#define INTEL_UC_FIRMWARE_URL "https://01.org/linuxgraphics/downloads/firmware"
+#define INTEL_UC_FIRMWARE_URL "https://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git/tree/i915"
 
 enum intel_uc_fw_status {
 	INTEL_UC_FIRMWARE_FAIL = -1,
@@ -115,6 +115,28 @@ static inline bool intel_uc_fw_is_selected(struct intel_uc_fw *uc_fw)
 	return uc_fw->path != NULL;
 }
 
+static inline void intel_uc_fw_sanitize(struct intel_uc_fw *uc_fw)
+{
+	if (uc_fw->load_status == INTEL_UC_FIRMWARE_SUCCESS)
+		uc_fw->load_status = INTEL_UC_FIRMWARE_PENDING;
+}
+
+/**
+ * intel_uc_fw_get_upload_size() - Get size of firmware needed to be uploaded.
+ * @uc_fw: uC firmware.
+ *
+ * Get the size of the firmware and header that will be uploaded to WOPCM.
+ *
+ * Return: Upload firmware size, or zero on firmware fetch failure.
+ */
+static inline u32 intel_uc_fw_get_upload_size(struct intel_uc_fw *uc_fw)
+{
+	if (uc_fw->fetch_status != INTEL_UC_FIRMWARE_SUCCESS)
+		return 0;
+
+	return uc_fw->header_size + uc_fw->ucode_size;
+}
+
 void intel_uc_fw_fetch(struct drm_i915_private *dev_priv,
 		       struct intel_uc_fw *uc_fw);
 int intel_uc_fw_upload(struct intel_uc_fw *uc_fw,
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 4df7c2ef8576..448293eb638d 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -62,6 +62,11 @@ static inline void
 fw_domain_reset(struct drm_i915_private *i915,
 		const struct intel_uncore_forcewake_domain *d)
 {
+	/*
+	 * We don't really know if the powerwell for the forcewake domain we are
+	 * trying to reset here does exist at this point (engines could be fused
+	 * off in ICL+), so no waiting for acks
+	 */
 	__raw_i915_write32(i915, d->reg_set, i915->uncore.fw_reset);
 }
 
@@ -134,7 +139,9 @@ fw_domain_wait_ack_with_fallback(const struct drm_i915_private *i915,
 	 * in the hope that the original ack will be delivered along with
 	 * the fallback ack.
 	 *
-	 * This workaround is described in HSDES #1604254524
+	 * This workaround is described in HSDES #1604254524 and it's known as:
+	 * WaRsForcewakeAddDelayForAck:skl,bxt,kbl,glk,cfl,cnl,icl
+	 * although the name is a bit misleading.
 	 */
 
 	pass = 1;
@@ -1353,6 +1360,23 @@ static void fw_domain_init(struct drm_i915_private *dev_priv,
 	fw_domain_reset(dev_priv, d);
 }
 
+static void fw_domain_fini(struct drm_i915_private *dev_priv,
+			   enum forcewake_domain_id domain_id)
+{
+	struct intel_uncore_forcewake_domain *d;
+
+	if (WARN_ON(domain_id >= FW_DOMAIN_ID_COUNT))
+		return;
+
+	d = &dev_priv->uncore.fw_domain[domain_id];
+
+	WARN_ON(d->wake_count);
+	WARN_ON(hrtimer_cancel(&d->timer));
+	memset(d, 0, sizeof(*d));
+
+	dev_priv->uncore.fw_domains &= ~BIT(domain_id);
+}
+
 static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv)
 {
 	if (INTEL_GEN(dev_priv) <= 5 || intel_vgpu_active(dev_priv))
@@ -1372,7 +1396,8 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv)
 	if (INTEL_GEN(dev_priv) >= 11) {
 		int i;
 
-		dev_priv->uncore.funcs.force_wake_get = fw_domains_get;
+		dev_priv->uncore.funcs.force_wake_get =
+			fw_domains_get_with_fallback;
 		dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 			       FORCEWAKE_RENDER_GEN9,
@@ -1565,6 +1590,40 @@ void intel_uncore_init(struct drm_i915_private *dev_priv)
 		&dev_priv->uncore.pmic_bus_access_nb);
 }
 
+/*
+ * We might have detected that some engines are fused off after we initialized
+ * the forcewake domains. Prune them, to make sure they only reference existing
+ * engines.
+ */
+void intel_uncore_prune(struct drm_i915_private *dev_priv)
+{
+	if (INTEL_GEN(dev_priv) >= 11) {
+		enum forcewake_domains fw_domains = dev_priv->uncore.fw_domains;
+		enum forcewake_domain_id domain_id;
+		int i;
+
+		for (i = 0; i < I915_MAX_VCS; i++) {
+			domain_id = FW_DOMAIN_ID_MEDIA_VDBOX0 + i;
+
+			if (HAS_ENGINE(dev_priv, _VCS(i)))
+				continue;
+
+			if (fw_domains & BIT(domain_id))
+				fw_domain_fini(dev_priv, domain_id);
+		}
+
+		for (i = 0; i < I915_MAX_VECS; i++) {
+			domain_id = FW_DOMAIN_ID_MEDIA_VEBOX0 + i;
+
+			if (HAS_ENGINE(dev_priv, _VECS(i)))
+				continue;
+
+			if (fw_domains & BIT(domain_id))
+				fw_domain_fini(dev_priv, domain_id);
+		}
+	}
+}
+
 void intel_uncore_fini(struct drm_i915_private *dev_priv)
 {
 	/* Paranoia: make sure we have disabled everything before we exit. */
@@ -1646,11 +1705,10 @@ static void gen3_stop_engine(struct intel_engine_cs *engine)
 	const i915_reg_t mode = RING_MI_MODE(base);
 
 	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
-	if (intel_wait_for_register_fw(dev_priv,
-				       mode,
-				       MODE_IDLE,
-				       MODE_IDLE,
-				       500))
+	if (__intel_wait_for_register_fw(dev_priv,
+					 mode, MODE_IDLE, MODE_IDLE,
+					 500, 0,
+					 NULL))
 		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
 				 engine->name);
 
@@ -1804,9 +1862,10 @@ static int gen6_hw_domain_reset(struct drm_i915_private *dev_priv,
 	__raw_i915_write32(dev_priv, GEN6_GDRST, hw_domain_mask);
 
 	/* Wait for the device to ack the reset requests */
-	err = intel_wait_for_register_fw(dev_priv,
-					  GEN6_GDRST, hw_domain_mask, 0,
-					  500);
+	err = __intel_wait_for_register_fw(dev_priv,
+					   GEN6_GDRST, hw_domain_mask, 0,
+					   500, 0,
+					   NULL);
 	if (err)
 		DRM_DEBUG_DRIVER("Wait for 0x%08x engines reset failed\n",
 				 hw_domain_mask);
@@ -1854,6 +1913,50 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv,
 }
 
 /**
+ * gen11_reset_engines - reset individual engines
+ * @dev_priv: i915 device
+ * @engine_mask: mask of intel_ring_flag() engines or ALL_ENGINES for full reset
+ *
+ * This function will reset the individual engines that are set in engine_mask.
+ * If you provide ALL_ENGINES as mask, full global domain reset will be issued.
+ *
+ * Note: It is responsibility of the caller to handle the difference between
+ * asking full domain reset versus reset for all available individual engines.
+ *
+ * Returns 0 on success, nonzero on error.
+ */
+static int gen11_reset_engines(struct drm_i915_private *dev_priv,
+			       unsigned engine_mask)
+{
+	struct intel_engine_cs *engine;
+	const u32 hw_engine_mask[I915_NUM_ENGINES] = {
+		[RCS] = GEN11_GRDOM_RENDER,
+		[BCS] = GEN11_GRDOM_BLT,
+		[VCS] = GEN11_GRDOM_MEDIA,
+		[VCS2] = GEN11_GRDOM_MEDIA2,
+		[VCS3] = GEN11_GRDOM_MEDIA3,
+		[VCS4] = GEN11_GRDOM_MEDIA4,
+		[VECS] = GEN11_GRDOM_VECS,
+		[VECS2] = GEN11_GRDOM_VECS2,
+	};
+	u32 hw_mask;
+
+	BUILD_BUG_ON(VECS2 + 1 != I915_NUM_ENGINES);
+
+	if (engine_mask == ALL_ENGINES) {
+		hw_mask = GEN11_GRDOM_FULL;
+	} else {
+		unsigned int tmp;
+
+		hw_mask = 0;
+		for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
+			hw_mask |= hw_engine_mask[engine->id];
+	}
+
+	return gen6_hw_domain_reset(dev_priv, hw_mask);
+}
+
+/**
  * __intel_wait_for_register_fw - wait until register matches expected state
  * @dev_priv: the i915 device
  * @reg: the register to read
@@ -1940,7 +2043,7 @@ int __intel_wait_for_register(struct drm_i915_private *dev_priv,
 	u32 reg_value;
 	int ret;
 
-	might_sleep();
+	might_sleep_if(slow_timeout_ms);
 
 	spin_lock_irq(&dev_priv->uncore.lock);
 	intel_uncore_forcewake_get__locked(dev_priv, fw);
@@ -1952,7 +2055,7 @@ int __intel_wait_for_register(struct drm_i915_private *dev_priv,
 	intel_uncore_forcewake_put__locked(dev_priv, fw);
 	spin_unlock_irq(&dev_priv->uncore.lock);
 
-	if (ret)
+	if (ret && slow_timeout_ms)
 		ret = __wait_for(reg_value = I915_READ_NOTRACE(reg),
 				 (reg_value & mask) == value,
 				 slow_timeout_ms * 1000, 10, 1000);
@@ -1971,11 +2074,12 @@ static int gen8_reset_engine_start(struct intel_engine_cs *engine)
 	I915_WRITE_FW(RING_RESET_CTL(engine->mmio_base),
 		      _MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET));
 
-	ret = intel_wait_for_register_fw(dev_priv,
-					 RING_RESET_CTL(engine->mmio_base),
-					 RESET_CTL_READY_TO_RESET,
-					 RESET_CTL_READY_TO_RESET,
-					 700);
+	ret = __intel_wait_for_register_fw(dev_priv,
+					   RING_RESET_CTL(engine->mmio_base),
+					   RESET_CTL_READY_TO_RESET,
+					   RESET_CTL_READY_TO_RESET,
+					   700, 0,
+					   NULL);
 	if (ret)
 		DRM_ERROR("%s: reset request timeout\n", engine->name);
 
@@ -2000,7 +2104,10 @@ static int gen8_reset_engines(struct drm_i915_private *dev_priv,
 		if (gen8_reset_engine_start(engine))
 			goto not_ready;
 
-	return gen6_reset_engines(dev_priv, engine_mask);
+	if (INTEL_GEN(dev_priv) >= 11)
+		return gen11_reset_engines(dev_priv, engine_mask);
+	else
+		return gen6_reset_engines(dev_priv, engine_mask);
 
 not_ready:
 	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
@@ -2038,15 +2145,31 @@ int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 	int retry;
 	int ret;
 
-	might_sleep();
+	/*
+	 * We want to perform per-engine reset from atomic context (e.g.
+	 * softirq), which imposes the constraint that we cannot sleep.
+	 * However, experience suggests that spending a bit of time waiting
+	 * for a reset helps in various cases, so for a full-device reset
+	 * we apply the opposite rule and wait if we want to. As we should
+	 * always follow up a failed per-engine reset with a full device reset,
+	 * being a little faster, stricter and more error prone for the
+	 * atomic case seems an acceptable compromise.
+	 *
+	 * Unfortunately this leads to a bimodal routine, when the goal was
+	 * to have a single reset function that worked for resetting any
+	 * number of engines simultaneously.
+	 */
+	might_sleep_if(engine_mask == ALL_ENGINES);
 
-	/* If the power well sleeps during the reset, the reset
+	/*
+	 * If the power well sleeps during the reset, the reset
 	 * request may be dropped and never completes (causing -EIO).
 	 */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 	for (retry = 0; retry < 3; retry++) {
 
-		/* We stop engines, otherwise we might get failed reset and a
+		/*
+		 * We stop engines, otherwise we might get failed reset and a
 		 * dead gpu (on elk). Also as modern gpu as kbl can suffer
 		 * from system hang if batchbuffer is progressing when
 		 * the reset is issued, regardless of READY_TO_RESET ack.
@@ -2060,9 +2183,11 @@ int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 		i915_stop_engines(dev_priv, engine_mask);
 
 		ret = -ENODEV;
-		if (reset)
+		if (reset) {
+			GEM_TRACE("engine_mask=%x\n", engine_mask);
 			ret = reset(dev_priv, engine_mask);
-		if (ret != -ETIMEDOUT)
+		}
+		if (ret != -ETIMEDOUT || engine_mask != ALL_ENGINES)
 			break;
 
 		cond_resched();
@@ -2085,12 +2210,14 @@ bool intel_has_reset_engine(struct drm_i915_private *dev_priv)
 
 int intel_reset_guc(struct drm_i915_private *dev_priv)
 {
+	u32 guc_domain = INTEL_GEN(dev_priv) >= 11 ? GEN11_GRDOM_GUC :
+						     GEN9_GRDOM_GUC;
 	int ret;
 
 	GEM_BUG_ON(!HAS_GUC(dev_priv));
 
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-	ret = gen6_hw_domain_reset(dev_priv, GEN9_GRDOM_GUC);
+	ret = gen6_hw_domain_reset(dev_priv, guc_domain);
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index dfdf444e4bcc..47478d609630 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -140,6 +140,7 @@ struct intel_uncore {
 
 void intel_uncore_sanitize(struct drm_i915_private *dev_priv);
 void intel_uncore_init(struct drm_i915_private *dev_priv);
+void intel_uncore_prune(struct drm_i915_private *dev_priv);
 bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv);
 bool intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv);
 void intel_uncore_fini(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_wopcm.c b/drivers/gpu/drm/i915/intel_wopcm.c
new file mode 100644
index 000000000000..74bf76f3fddc
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_wopcm.c
@@ -0,0 +1,275 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2017-2018 Intel Corporation
+ */
+
+#include "intel_wopcm.h"
+#include "i915_drv.h"
+
+/**
+ * DOC: WOPCM Layout
+ *
+ * The layout of the WOPCM will be fixed after writing to GuC WOPCM size and
+ * offset registers whose values are calculated and determined by HuC/GuC
+ * firmware size and set of hardware requirements/restrictions as shown below:
+ *
+ * ::
+ *
+ *    +=========> +====================+ <== WOPCM Top
+ *    ^           |  HW contexts RSVD  |
+ *    |     +===> +====================+ <== GuC WOPCM Top
+ *    |     ^     |                    |
+ *    |     |     |                    |
+ *    |     |     |                    |
+ *    |    GuC    |                    |
+ *    |   WOPCM   |                    |
+ *    |    Size   +--------------------+
+ *  WOPCM   |     |    GuC FW RSVD     |
+ *    |     |     +--------------------+
+ *    |     |     |   GuC Stack RSVD   |
+ *    |     |     +------------------- +
+ *    |     v     |   GuC WOPCM RSVD   |
+ *    |     +===> +====================+ <== GuC WOPCM base
+ *    |           |     WOPCM RSVD     |
+ *    |           +------------------- + <== HuC Firmware Top
+ *    v           |      HuC FW        |
+ *    +=========> +====================+ <== WOPCM Base
+ *
+ * GuC accessible WOPCM starts at GuC WOPCM base and ends at GuC WOPCM top.
+ * The top part of the WOPCM is reserved for hardware contexts (e.g. RC6
+ * context).
+ */
+
+/* Default WOPCM size 1MB. */
+#define GEN9_WOPCM_SIZE			(1024 * 1024)
+/* 16KB WOPCM (RSVD WOPCM) is reserved from HuC firmware top. */
+#define WOPCM_RESERVED_SIZE		(16 * 1024)
+
+/* 16KB reserved at the beginning of GuC WOPCM. */
+#define GUC_WOPCM_RESERVED		(16 * 1024)
+/* 8KB from GUC_WOPCM_RESERVED is reserved for GuC stack. */
+#define GUC_WOPCM_STACK_RESERVED	(8 * 1024)
+
+/* GuC WOPCM Offset value needs to be aligned to 16KB. */
+#define GUC_WOPCM_OFFSET_ALIGNMENT	(1UL << GUC_WOPCM_OFFSET_SHIFT)
+
+/* 24KB at the end of WOPCM is reserved for RC6 CTX on BXT. */
+#define BXT_WOPCM_RC6_CTX_RESERVED	(24 * 1024)
+/* 36KB WOPCM reserved at the end of WOPCM on CNL. */
+#define CNL_WOPCM_HW_CTX_RESERVED	(36 * 1024)
+
+/* 128KB from GUC_WOPCM_RESERVED is reserved for FW on Gen9. */
+#define GEN9_GUC_FW_RESERVED	(128 * 1024)
+#define GEN9_GUC_WOPCM_OFFSET	(GUC_WOPCM_RESERVED + GEN9_GUC_FW_RESERVED)
+
+/**
+ * intel_wopcm_init_early() - Early initialization of the WOPCM.
+ * @wopcm: pointer to intel_wopcm.
+ *
+ * Setup the size of WOPCM which will be used by later on WOPCM partitioning.
+ */
+void intel_wopcm_init_early(struct intel_wopcm *wopcm)
+{
+	wopcm->size = GEN9_WOPCM_SIZE;
+
+	DRM_DEBUG_DRIVER("WOPCM size: %uKiB\n", wopcm->size / 1024);
+}
+
+static inline u32 context_reserved_size(struct drm_i915_private *i915)
+{
+	if (IS_GEN9_LP(i915))
+		return BXT_WOPCM_RC6_CTX_RESERVED;
+	else if (INTEL_GEN(i915) >= 10)
+		return CNL_WOPCM_HW_CTX_RESERVED;
+	else
+		return 0;
+}
+
+static inline int gen9_check_dword_gap(u32 guc_wopcm_base, u32 guc_wopcm_size)
+{
+	u32 offset;
+
+	/*
+	 * GuC WOPCM size shall be at least a dword larger than the offset from
+	 * WOPCM base (GuC WOPCM offset from WOPCM base + GEN9_GUC_WOPCM_OFFSET)
+	 * due to hardware limitation on Gen9.
+	 */
+	offset = guc_wopcm_base + GEN9_GUC_WOPCM_OFFSET;
+	if (offset > guc_wopcm_size ||
+	    (guc_wopcm_size - offset) < sizeof(u32)) {
+		DRM_ERROR("GuC WOPCM size %uKiB is too small. %uKiB needed.\n",
+			  guc_wopcm_size / 1024,
+			  (u32)(offset + sizeof(u32)) / 1024);
+		return -E2BIG;
+	}
+
+	return 0;
+}
+
+static inline int gen9_check_huc_fw_fits(u32 guc_wopcm_size, u32 huc_fw_size)
+{
+	/*
+	 * On Gen9 & CNL A0, hardware requires the total available GuC WOPCM
+	 * size to be larger than or equal to HuC firmware size. Otherwise,
+	 * firmware uploading would fail.
+	 */
+	if (huc_fw_size > guc_wopcm_size - GUC_WOPCM_RESERVED) {
+		DRM_ERROR("HuC FW (%uKiB) won't fit in GuC WOPCM (%uKiB).\n",
+			  huc_fw_size / 1024,
+			  (guc_wopcm_size - GUC_WOPCM_RESERVED) / 1024);
+		return -E2BIG;
+	}
+
+	return 0;
+}
+
+static inline int check_hw_restriction(struct drm_i915_private *i915,
+				       u32 guc_wopcm_base, u32 guc_wopcm_size,
+				       u32 huc_fw_size)
+{
+	int err = 0;
+
+	if (IS_GEN9(i915))
+		err = gen9_check_dword_gap(guc_wopcm_base, guc_wopcm_size);
+
+	if (!err &&
+	    (IS_GEN9(i915) || IS_CNL_REVID(i915, CNL_REVID_A0, CNL_REVID_A0)))
+		err = gen9_check_huc_fw_fits(guc_wopcm_size, huc_fw_size);
+
+	return err;
+}
+
+/**
+ * intel_wopcm_init() - Initialize the WOPCM structure.
+ * @wopcm: pointer to intel_wopcm.
+ *
+ * This function will partition WOPCM space based on GuC and HuC firmware sizes
+ * and will allocate max remaining for use by GuC. This function will also
+ * enforce platform dependent hardware restrictions on GuC WOPCM offset and
+ * size. It will fail the WOPCM init if any of these checks were failed, so that
+ * the following GuC firmware uploading would be aborted.
+ *
+ * Return: 0 on success, non-zero error code on failure.
+ */
+int intel_wopcm_init(struct intel_wopcm *wopcm)
+{
+	struct drm_i915_private *i915 = wopcm_to_i915(wopcm);
+	u32 guc_fw_size = intel_uc_fw_get_upload_size(&i915->guc.fw);
+	u32 huc_fw_size = intel_uc_fw_get_upload_size(&i915->huc.fw);
+	u32 ctx_rsvd = context_reserved_size(i915);
+	u32 guc_wopcm_base;
+	u32 guc_wopcm_size;
+	u32 guc_wopcm_rsvd;
+	int err;
+
+	GEM_BUG_ON(!wopcm->size);
+
+	if (guc_fw_size >= wopcm->size) {
+		DRM_ERROR("GuC FW (%uKiB) is too big to fit in WOPCM.",
+			  guc_fw_size / 1024);
+		return -E2BIG;
+	}
+
+	if (huc_fw_size >= wopcm->size) {
+		DRM_ERROR("HuC FW (%uKiB) is too big to fit in WOPCM.",
+			  huc_fw_size / 1024);
+		return -E2BIG;
+	}
+
+	guc_wopcm_base = ALIGN(huc_fw_size + WOPCM_RESERVED_SIZE,
+			       GUC_WOPCM_OFFSET_ALIGNMENT);
+	if ((guc_wopcm_base + ctx_rsvd) >= wopcm->size) {
+		DRM_ERROR("GuC WOPCM base (%uKiB) is too big.\n",
+			  guc_wopcm_base / 1024);
+		return -E2BIG;
+	}
+
+	guc_wopcm_size = wopcm->size - guc_wopcm_base - ctx_rsvd;
+	guc_wopcm_size &= GUC_WOPCM_SIZE_MASK;
+
+	DRM_DEBUG_DRIVER("Calculated GuC WOPCM Region: [%uKiB, %uKiB)\n",
+			 guc_wopcm_base / 1024, guc_wopcm_size / 1024);
+
+	guc_wopcm_rsvd = GUC_WOPCM_RESERVED + GUC_WOPCM_STACK_RESERVED;
+	if ((guc_fw_size + guc_wopcm_rsvd) > guc_wopcm_size) {
+		DRM_ERROR("Need %uKiB WOPCM for GuC, %uKiB available.\n",
+			  (guc_fw_size + guc_wopcm_rsvd) / 1024,
+			  guc_wopcm_size / 1024);
+		return -E2BIG;
+	}
+
+	err = check_hw_restriction(i915, guc_wopcm_base, guc_wopcm_size,
+				   huc_fw_size);
+	if (err)
+		return err;
+
+	wopcm->guc.base = guc_wopcm_base;
+	wopcm->guc.size = guc_wopcm_size;
+
+	return 0;
+}
+
+static inline int write_and_verify(struct drm_i915_private *dev_priv,
+				   i915_reg_t reg, u32 val, u32 mask,
+				   u32 locked_bit)
+{
+	u32 reg_val;
+
+	GEM_BUG_ON(val & ~mask);
+
+	I915_WRITE(reg, val);
+
+	reg_val = I915_READ(reg);
+
+	return (reg_val & mask) != (val | locked_bit) ? -EIO : 0;
+}
+
+/**
+ * intel_wopcm_init_hw() - Setup GuC WOPCM registers.
+ * @wopcm: pointer to intel_wopcm.
+ *
+ * Setup the GuC WOPCM size and offset registers with the calculated values. It
+ * will verify the register values to make sure the registers are locked with
+ * correct values.
+ *
+ * Return: 0 on success. -EIO if registers were locked with incorrect values.
+ */
+int intel_wopcm_init_hw(struct intel_wopcm *wopcm)
+{
+	struct drm_i915_private *dev_priv = wopcm_to_i915(wopcm);
+	u32 huc_agent;
+	u32 mask;
+	int err;
+
+	if (!USES_GUC(dev_priv))
+		return 0;
+
+	GEM_BUG_ON(!HAS_GUC(dev_priv));
+	GEM_BUG_ON(!wopcm->guc.size);
+	GEM_BUG_ON(!wopcm->guc.base);
+
+	err = write_and_verify(dev_priv, GUC_WOPCM_SIZE, wopcm->guc.size,
+			       GUC_WOPCM_SIZE_MASK | GUC_WOPCM_SIZE_LOCKED,
+			       GUC_WOPCM_SIZE_LOCKED);
+	if (err)
+		goto err_out;
+
+	huc_agent = USES_HUC(dev_priv) ? HUC_LOADING_AGENT_GUC : 0;
+	mask = GUC_WOPCM_OFFSET_MASK | GUC_WOPCM_OFFSET_VALID | huc_agent;
+	err = write_and_verify(dev_priv, DMA_GUC_WOPCM_OFFSET,
+			       wopcm->guc.base | huc_agent, mask,
+			       GUC_WOPCM_OFFSET_VALID);
+	if (err)
+		goto err_out;
+
+	return 0;
+
+err_out:
+	DRM_ERROR("Failed to init WOPCM registers:\n");
+	DRM_ERROR("DMA_GUC_WOPCM_OFFSET=%#x\n",
+		  I915_READ(DMA_GUC_WOPCM_OFFSET));
+	DRM_ERROR("GUC_WOPCM_SIZE=%#x\n", I915_READ(GUC_WOPCM_SIZE));
+
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/intel_wopcm.h b/drivers/gpu/drm/i915/intel_wopcm.h
new file mode 100644
index 000000000000..6298910a384c
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_wopcm.h
@@ -0,0 +1,31 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2017-2018 Intel Corporation
+ */
+
+#ifndef _INTEL_WOPCM_H_
+#define _INTEL_WOPCM_H_
+
+#include <linux/types.h>
+
+/**
+ * struct intel_wopcm - Overall WOPCM info and WOPCM regions.
+ * @size: Size of overall WOPCM.
+ * @guc: GuC WOPCM Region info.
+ * @guc.base: GuC WOPCM base which is offset from WOPCM base.
+ * @guc.size: Size of the GuC WOPCM region.
+ */
+struct intel_wopcm {
+	u32 size;
+	struct {
+		u32 base;
+		u32 size;
+	} guc;
+};
+
+void intel_wopcm_init_early(struct intel_wopcm *wopcm);
+int intel_wopcm_init(struct intel_wopcm *wopcm);
+int intel_wopcm_init_hw(struct intel_wopcm *wopcm);
+
+#endif
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
new file mode 100644
index 000000000000..2df3538ceba5
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -0,0 +1,949 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2014-2018 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_workarounds.h"
+
+/**
+ * DOC: Hardware workarounds
+ *
+ * This file is intended as a central place to implement most [1]_ of the
+ * required workarounds for hardware to work as originally intended. They fall
+ * in five basic categories depending on how/when they are applied:
+ *
+ * - Workarounds that touch registers that are saved/restored to/from the HW
+ *   context image. The list is emitted (via Load Register Immediate commands)
+ *   everytime a new context is created.
+ * - GT workarounds. The list of these WAs is applied whenever these registers
+ *   revert to default values (on GPU reset, suspend/resume [2]_, etc..).
+ * - Display workarounds. The list is applied during display clock-gating
+ *   initialization.
+ * - Workarounds that whitelist a privileged register, so that UMDs can manage
+ *   them directly. This is just a special case of a MMMIO workaround (as we
+ *   write the list of these to/be-whitelisted registers to some special HW
+ *   registers).
+ * - Workaround batchbuffers, that get executed automatically by the hardware
+ *   on every HW context restore.
+ *
+ * .. [1] Please notice that there are other WAs that, due to their nature,
+ *    cannot be applied from a central place. Those are peppered around the rest
+ *    of the code, as needed.
+ *
+ * .. [2] Technically, some registers are powercontext saved & restored, so they
+ *    survive a suspend/resume. In practice, writing them again is not too
+ *    costly and simplifies things. We can revisit this in the future.
+ *
+ * Layout
+ * ''''''
+ *
+ * Keep things in this file ordered by WA type, as per the above (context, GT,
+ * display, register whitelist, batchbuffer). Then, inside each type, keep the
+ * following order:
+ *
+ * - Infrastructure functions and macros
+ * - WAs per platform in standard gen/chrono order
+ * - Public functions to init or apply the given workaround type.
+ */
+
+static int wa_add(struct drm_i915_private *dev_priv,
+		  i915_reg_t addr,
+		  const u32 mask, const u32 val)
+{
+	const unsigned int idx = dev_priv->workarounds.count;
+
+	if (WARN_ON(idx >= I915_MAX_WA_REGS))
+		return -ENOSPC;
+
+	dev_priv->workarounds.reg[idx].addr = addr;
+	dev_priv->workarounds.reg[idx].value = val;
+	dev_priv->workarounds.reg[idx].mask = mask;
+
+	dev_priv->workarounds.count++;
+
+	return 0;
+}
+
+#define WA_REG(addr, mask, val) do { \
+		const int r = wa_add(dev_priv, (addr), (mask), (val)); \
+		if (r) \
+			return r; \
+	} while (0)
+
+#define WA_SET_BIT_MASKED(addr, mask) \
+	WA_REG(addr, (mask), _MASKED_BIT_ENABLE(mask))
+
+#define WA_CLR_BIT_MASKED(addr, mask) \
+	WA_REG(addr, (mask), _MASKED_BIT_DISABLE(mask))
+
+#define WA_SET_FIELD_MASKED(addr, mask, value) \
+	WA_REG(addr, (mask), _MASKED_FIELD(mask, value))
+
+static int gen8_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
+
+	/* WaDisableAsyncFlipPerfMode:bdw,chv */
+	WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
+	/* WaDisablePartialInstShootdown:bdw,chv */
+	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
+			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
+
+	/* Use Force Non-Coherent whenever executing a 3D context. This is a
+	 * workaround for for a possible hang in the unlikely event a TLB
+	 * invalidation occurs during a PSD flush.
+	 */
+	/* WaForceEnableNonCoherent:bdw,chv */
+	/* WaHdcDisableFetchWhenMasked:bdw,chv */
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  HDC_DONOT_FETCH_MEM_WHEN_MASKED |
+			  HDC_FORCE_NON_COHERENT);
+
+	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
+	 * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
+	 *  polygons in the same 8x4 pixel/sample area to be processed without
+	 *  stalling waiting for the earlier ones to write to Hierarchical Z
+	 *  buffer."
+	 *
+	 * This optimization is off by default for BDW and CHV; turn it on.
+	 */
+	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
+
+	/* Wa4x4STCOptimizationDisable:bdw,chv */
+	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	WA_SET_FIELD_MASKED(GEN7_GT_MODE,
+			    GEN6_WIZ_HASHING_MASK,
+			    GEN6_WIZ_HASHING_16x4);
+
+	return 0;
+}
+
+static int bdw_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = gen8_ctx_workarounds_init(dev_priv);
+	if (ret)
+		return ret;
+
+	/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
+	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
+
+	/* WaDisableDopClockGating:bdw
+	 *
+	 * Also see the related UCGTCL1 write in broadwell_init_clock_gating()
+	 * to disable EUTC clock gating.
+	 */
+	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
+			  DOP_CLOCK_GATING_DISABLE);
+
+	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
+			  GEN8_SAMPLER_POWER_BYPASS_DIS);
+
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  /* WaForceContextSaveRestoreNonCoherent:bdw */
+			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
+			  /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
+			  (IS_BDW_GT3(dev_priv) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
+
+	return 0;
+}
+
+static int chv_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = gen8_ctx_workarounds_init(dev_priv);
+	if (ret)
+		return ret;
+
+	/* WaDisableThreadStallDopClockGating:chv */
+	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
+
+	/* Improve HiZ throughput on CHV. */
+	WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
+
+	return 0;
+}
+
+static int gen9_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	if (HAS_LLC(dev_priv)) {
+		/* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
+		 *
+		 * Must match Display Engine. See
+		 * WaCompressedResourceDisplayNewHashMode.
+		 */
+		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+				  GEN9_PBE_COMPRESSED_HASH_SELECTION);
+		WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
+				  GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR);
+	}
+
+	/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */
+	/* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */
+	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
+			  FLOW_CONTROL_ENABLE |
+			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
+
+	/* Syncing dependencies between camera and graphics:skl,bxt,kbl */
+	if (!IS_COFFEELAKE(dev_priv))
+		WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
+				  GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
+
+	/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */
+	/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */
+	WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
+			  GEN9_ENABLE_YV12_BUGFIX |
+			  GEN9_ENABLE_GPGPU_PREEMPTION);
+
+	/* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk,cfl */
+	/* WaDisablePartialResolveInVc:skl,bxt,kbl,cfl */
+	WA_SET_BIT_MASKED(CACHE_MODE_1,
+			  GEN8_4x4_STC_OPTIMIZATION_DISABLE |
+			  GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE);
+
+	/* WaCcsTlbPrefetchDisable:skl,bxt,kbl,glk,cfl */
+	WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
+			  GEN9_CCS_TLB_PREFETCH_ENABLE);
+
+	/* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl,cfl */
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
+			  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE);
+
+	/* WaForceEnableNonCoherent and WaDisableHDCInvalidation are
+	 * both tied to WaForceContextSaveRestoreNonCoherent
+	 * in some hsds for skl. We keep the tie for all gen9. The
+	 * documentation is a bit hazy and so we want to get common behaviour,
+	 * even though there is no clear evidence we would need both on kbl/bxt.
+	 * This area has been source of system hangs so we play it safe
+	 * and mimic the skl regardless of what bspec says.
+	 *
+	 * Use Force Non-Coherent whenever executing a 3D context. This
+	 * is a workaround for a possible hang in the unlikely event
+	 * a TLB invalidation occurs during a PSD flush.
+	 */
+
+	/* WaForceEnableNonCoherent:skl,bxt,kbl,cfl */
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  HDC_FORCE_NON_COHERENT);
+
+	/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl,cfl */
+	if (IS_SKYLAKE(dev_priv) ||
+	    IS_KABYLAKE(dev_priv) ||
+	    IS_COFFEELAKE(dev_priv))
+		WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
+				  GEN8_SAMPLER_POWER_BYPASS_DIS);
+
+	/* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */
+	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
+
+	/*
+	 * Supporting preemption with fine-granularity requires changes in the
+	 * batch buffer programming. Since we can't break old userspace, we
+	 * need to set our default preemption level to safe value. Userspace is
+	 * still able to use more fine-grained preemption levels, since in
+	 * WaEnablePreemptionGranularityControlByUMD we're whitelisting the
+	 * per-ctx register. As such, WaDisable{3D,GPGPU}MidCmdPreemption are
+	 * not real HW workarounds, but merely a way to start using preemption
+	 * while maintaining old contract with userspace.
+	 */
+
+	/* WaDisable3DMidCmdPreemption:skl,bxt,glk,cfl,[cnl] */
+	WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
+
+	/* WaDisableGPGPUMidCmdPreemption:skl,bxt,blk,cfl,[cnl] */
+	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
+			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
+			    GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
+
+	/* WaClearHIZ_WM_CHICKEN3:bxt,glk */
+	if (IS_GEN9_LP(dev_priv))
+		WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ);
+
+	return 0;
+}
+
+static int skl_tune_iz_hashing(struct drm_i915_private *dev_priv)
+{
+	u8 vals[3] = { 0, 0, 0 };
+	unsigned int i;
+
+	for (i = 0; i < 3; i++) {
+		u8 ss;
+
+		/*
+		 * Only consider slices where one, and only one, subslice has 7
+		 * EUs
+		 */
+		if (!is_power_of_2(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i]))
+			continue;
+
+		/*
+		 * subslice_7eu[i] != 0 (because of the check above) and
+		 * ss_max == 4 (maximum number of subslices possible per slice)
+		 *
+		 * ->    0 <= ss <= 3;
+		 */
+		ss = ffs(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i]) - 1;
+		vals[i] = 3 - ss;
+	}
+
+	if (vals[0] == 0 && vals[1] == 0 && vals[2] == 0)
+		return 0;
+
+	/* Tune IZ hashing. See intel_device_info_runtime_init() */
+	WA_SET_FIELD_MASKED(GEN7_GT_MODE,
+			    GEN9_IZ_HASHING_MASK(2) |
+			    GEN9_IZ_HASHING_MASK(1) |
+			    GEN9_IZ_HASHING_MASK(0),
+			    GEN9_IZ_HASHING(2, vals[2]) |
+			    GEN9_IZ_HASHING(1, vals[1]) |
+			    GEN9_IZ_HASHING(0, vals[0]));
+
+	return 0;
+}
+
+static int skl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = gen9_ctx_workarounds_init(dev_priv);
+	if (ret)
+		return ret;
+
+	return skl_tune_iz_hashing(dev_priv);
+}
+
+static int bxt_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = gen9_ctx_workarounds_init(dev_priv);
+	if (ret)
+		return ret;
+
+	/* WaDisableThreadStallDopClockGating:bxt */
+	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
+			  STALL_DOP_GATING_DISABLE);
+
+	/* WaToEnableHwFixForPushConstHWBug:bxt */
+	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	return 0;
+}
+
+static int kbl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = gen9_ctx_workarounds_init(dev_priv);
+	if (ret)
+		return ret;
+
+	/* WaDisableFenceDestinationToSLM:kbl (pre-prod) */
+	if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0))
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE);
+
+	/* WaToEnableHwFixForPushConstHWBug:kbl */
+	if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER))
+		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	/* WaDisableSbeCacheDispatchPortSharing:kbl */
+	WA_SET_BIT_MASKED(GEN7_HALF_SLICE_CHICKEN1,
+			  GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
+
+	return 0;
+}
+
+static int glk_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = gen9_ctx_workarounds_init(dev_priv);
+	if (ret)
+		return ret;
+
+	/* WaToEnableHwFixForPushConstHWBug:glk */
+	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	return 0;
+}
+
+static int cfl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = gen9_ctx_workarounds_init(dev_priv);
+	if (ret)
+		return ret;
+
+	/* WaToEnableHwFixForPushConstHWBug:cfl */
+	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	/* WaDisableSbeCacheDispatchPortSharing:cfl */
+	WA_SET_BIT_MASKED(GEN7_HALF_SLICE_CHICKEN1,
+			  GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
+
+	return 0;
+}
+
+static int cnl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	/* WaForceContextSaveRestoreNonCoherent:cnl */
+	WA_SET_BIT_MASKED(CNL_HDC_CHICKEN0,
+			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT);
+
+	/* WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod) */
+	if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0))
+		WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, THROTTLE_12_5);
+
+	/* WaDisableReplayBufferBankArbitrationOptimization:cnl */
+	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	/* WaDisableEnhancedSBEVertexCaching:cnl (pre-prod) */
+	if (IS_CNL_REVID(dev_priv, 0, CNL_REVID_B0))
+		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+				  GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE);
+
+	/* WaPushConstantDereferenceHoldDisable:cnl */
+	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE);
+
+	/* FtrEnableFastAnisoL1BankingFix:cnl */
+	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, CNL_FAST_ANISO_L1_BANKING_FIX);
+
+	/* WaDisable3DMidCmdPreemption:cnl */
+	WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
+
+	/* WaDisableGPGPUMidCmdPreemption:cnl */
+	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
+			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
+			    GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
+
+	/* WaDisableEarlyEOT:cnl */
+	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, DISABLE_EARLY_EOT);
+
+	return 0;
+}
+
+static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	/* Wa_1604370585:icl (pre-prod)
+	 * Formerly known as WaPushConstantDereferenceHoldDisable
+	 */
+	if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0))
+		WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
+				  PUSH_CONSTANT_DEREF_DISABLE);
+
+	/* WaForceEnableNonCoherent:icl
+	 * This is not the same workaround as in early Gen9 platforms, where
+	 * lacking this could cause system hangs, but coherency performance
+	 * overhead is high and only a few compute workloads really need it
+	 * (the register is whitelisted in hardware now, so UMDs can opt in
+	 * for coherency if they have a good reason).
+	 */
+	WA_SET_BIT_MASKED(ICL_HDC_MODE, HDC_FORCE_NON_COHERENT);
+
+	return 0;
+}
+
+int intel_ctx_workarounds_init(struct drm_i915_private *dev_priv)
+{
+	int err = 0;
+
+	dev_priv->workarounds.count = 0;
+
+	if (INTEL_GEN(dev_priv) < 8)
+		err = 0;
+	else if (IS_BROADWELL(dev_priv))
+		err = bdw_ctx_workarounds_init(dev_priv);
+	else if (IS_CHERRYVIEW(dev_priv))
+		err = chv_ctx_workarounds_init(dev_priv);
+	else if (IS_SKYLAKE(dev_priv))
+		err = skl_ctx_workarounds_init(dev_priv);
+	else if (IS_BROXTON(dev_priv))
+		err = bxt_ctx_workarounds_init(dev_priv);
+	else if (IS_KABYLAKE(dev_priv))
+		err = kbl_ctx_workarounds_init(dev_priv);
+	else if (IS_GEMINILAKE(dev_priv))
+		err = glk_ctx_workarounds_init(dev_priv);
+	else if (IS_COFFEELAKE(dev_priv))
+		err = cfl_ctx_workarounds_init(dev_priv);
+	else if (IS_CANNONLAKE(dev_priv))
+		err = cnl_ctx_workarounds_init(dev_priv);
+	else if (IS_ICELAKE(dev_priv))
+		err = icl_ctx_workarounds_init(dev_priv);
+	else
+		MISSING_CASE(INTEL_GEN(dev_priv));
+	if (err)
+		return err;
+
+	DRM_DEBUG_DRIVER("Number of context specific w/a: %d\n",
+			 dev_priv->workarounds.count);
+	return 0;
+}
+
+int intel_ctx_workarounds_emit(struct i915_request *rq)
+{
+	struct i915_workarounds *w = &rq->i915->workarounds;
+	u32 *cs;
+	int ret, i;
+
+	if (w->count == 0)
+		return 0;
+
+	ret = rq->engine->emit_flush(rq, EMIT_BARRIER);
+	if (ret)
+		return ret;
+
+	cs = intel_ring_begin(rq, (w->count * 2 + 2));
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	*cs++ = MI_LOAD_REGISTER_IMM(w->count);
+	for (i = 0; i < w->count; i++) {
+		*cs++ = i915_mmio_reg_offset(w->reg[i].addr);
+		*cs++ = w->reg[i].value;
+	}
+	*cs++ = MI_NOOP;
+
+	intel_ring_advance(rq, cs);
+
+	ret = rq->engine->emit_flush(rq, EMIT_BARRIER);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void bdw_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+}
+
+static void chv_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+}
+
+static void gen9_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	/* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */
+	I915_WRITE(GEN9_CSFE_CHICKEN1_RCS,
+		   _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE));
+
+	/* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */
+	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
+		   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
+
+	/* WaDisableKillLogic:bxt,skl,kbl */
+	if (!IS_COFFEELAKE(dev_priv))
+		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+			   ECOCHK_DIS_TLB);
+
+	if (HAS_LLC(dev_priv)) {
+		/* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
+		 *
+		 * Must match Display Engine. See
+		 * WaCompressedResourceDisplayNewHashMode.
+		 */
+		I915_WRITE(MMCD_MISC_CTRL,
+			   I915_READ(MMCD_MISC_CTRL) |
+			   MMCD_PCLA |
+			   MMCD_HOTSPOT_EN);
+	}
+
+	/* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */
+	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+		   BDW_DISABLE_HDC_INVALIDATION);
+
+	/* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */
+	if (IS_GEN9_LP(dev_priv)) {
+		u32 val = I915_READ(GEN8_L3SQCREG1);
+
+		val &= ~L3_PRIO_CREDITS_MASK;
+		val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2);
+		I915_WRITE(GEN8_L3SQCREG1, val);
+	}
+
+	/* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */
+	I915_WRITE(GEN8_L3SQCREG4,
+		   I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES);
+
+	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */
+	I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
+		   _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
+}
+
+static void skl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	gen9_gt_workarounds_apply(dev_priv);
+
+	/* WaEnableGapsTsvCreditFix:skl */
+	I915_WRITE(GEN8_GARBCNTL,
+		   I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE);
+
+	/* WaDisableGafsUnitClkGating:skl */
+	I915_WRITE(GEN7_UCGCTL4,
+		   I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaInPlaceDecompressionHang:skl */
+	if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER))
+		I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
+			   I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
+			   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+}
+
+static void bxt_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	gen9_gt_workarounds_apply(dev_priv);
+
+	/* WaDisablePooledEuLoadBalancingFix:bxt */
+	I915_WRITE(FF_SLICE_CS_CHICKEN2,
+		   _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE));
+
+	/* WaInPlaceDecompressionHang:bxt */
+	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
+		   I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
+		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+}
+
+static void kbl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	gen9_gt_workarounds_apply(dev_priv);
+
+	/* WaEnableGapsTsvCreditFix:kbl */
+	I915_WRITE(GEN8_GARBCNTL,
+		   I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE);
+
+	/* WaDisableDynamicCreditSharing:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		I915_WRITE(GAMT_CHKN_BIT_REG,
+			   I915_READ(GAMT_CHKN_BIT_REG) |
+			   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
+
+	/* WaDisableGafsUnitClkGating:kbl */
+	I915_WRITE(GEN7_UCGCTL4,
+		   I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaInPlaceDecompressionHang:kbl */
+	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
+		   I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
+		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+}
+
+static void glk_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	gen9_gt_workarounds_apply(dev_priv);
+}
+
+static void cfl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	gen9_gt_workarounds_apply(dev_priv);
+
+	/* WaEnableGapsTsvCreditFix:cfl */
+	I915_WRITE(GEN8_GARBCNTL,
+		   I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE);
+
+	/* WaDisableGafsUnitClkGating:cfl */
+	I915_WRITE(GEN7_UCGCTL4,
+		   I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaInPlaceDecompressionHang:cfl */
+	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
+		   I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
+		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+}
+
+static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	/* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */
+	if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0))
+		I915_WRITE(GAMT_CHKN_BIT_REG,
+			   I915_READ(GAMT_CHKN_BIT_REG) |
+			   GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT);
+
+	/* WaInPlaceDecompressionHang:cnl */
+	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
+		   I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
+		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+
+	/* WaEnablePreemptionGranularityControlByUMD:cnl */
+	I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
+		   _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
+}
+
+static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	/* This is not an Wa. Enable for better image quality */
+	I915_WRITE(_3D_CHICKEN3,
+		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE));
+
+	/* WaInPlaceDecompressionHang:icl */
+	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
+					    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+
+	/* WaPipelineFlushCoherentLines:icl */
+	I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
+				   GEN8_LQSC_FLUSH_COHERENT_LINES);
+
+	/* Wa_1405543622:icl
+	 * Formerly known as WaGAPZPriorityScheme
+	 */
+	I915_WRITE(GEN8_GARBCNTL, I915_READ(GEN8_GARBCNTL) |
+				  GEN11_ARBITRATION_PRIO_ORDER_MASK);
+
+	/* Wa_1604223664:icl
+	 * Formerly known as WaL3BankAddressHashing
+	 */
+	I915_WRITE(GEN8_GARBCNTL,
+		   (I915_READ(GEN8_GARBCNTL) & ~GEN11_HASH_CTRL_EXCL_MASK) |
+		   GEN11_HASH_CTRL_EXCL_BIT0);
+	I915_WRITE(GEN11_GLBLINVL,
+		   (I915_READ(GEN11_GLBLINVL) & ~GEN11_BANK_HASH_ADDR_EXCL_MASK) |
+		   GEN11_BANK_HASH_ADDR_EXCL_BIT0);
+
+	/* WaModifyGamTlbPartitioning:icl */
+	I915_WRITE(GEN11_GACB_PERF_CTRL,
+		   (I915_READ(GEN11_GACB_PERF_CTRL) & ~GEN11_HASH_CTRL_MASK) |
+		   GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4);
+
+	/* Wa_1405733216:icl
+	 * Formerly known as WaDisableCleanEvicts
+	 */
+	I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
+				   GEN11_LQSC_CLEAN_EVICT_DISABLE);
+
+	/* Wa_1405766107:icl
+	 * Formerly known as WaCL2SFHalfMaxAlloc
+	 */
+	I915_WRITE(GEN11_LSN_UNSLCVC, I915_READ(GEN11_LSN_UNSLCVC) |
+				      GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC |
+				      GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC);
+
+	/* Wa_220166154:icl
+	 * Formerly known as WaDisCtxReload
+	 */
+	I915_WRITE(GAMW_ECO_DEV_RW_IA_REG, I915_READ(GAMW_ECO_DEV_RW_IA_REG) |
+					   GAMW_ECO_DEV_CTX_RELOAD_DISABLE);
+
+	/* Wa_1405779004:icl (pre-prod) */
+	if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0))
+		I915_WRITE(SLICE_UNIT_LEVEL_CLKGATE,
+			   I915_READ(SLICE_UNIT_LEVEL_CLKGATE) |
+			   MSCUNIT_CLKGATE_DIS);
+
+	/* Wa_1406680159:icl */
+	I915_WRITE(SUBSLICE_UNIT_LEVEL_CLKGATE,
+		   I915_READ(SUBSLICE_UNIT_LEVEL_CLKGATE) |
+		   GWUNIT_CLKGATE_DIS);
+
+	/* Wa_1604302699:icl */
+	I915_WRITE(GEN10_L3_CHICKEN_MODE_REGISTER,
+		   I915_READ(GEN10_L3_CHICKEN_MODE_REGISTER) |
+		   GEN11_I2M_WRITE_DISABLE);
+
+	/* Wa_1406838659:icl (pre-prod) */
+	if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0))
+		I915_WRITE(INF_UNIT_LEVEL_CLKGATE,
+			   I915_READ(INF_UNIT_LEVEL_CLKGATE) |
+			   CGPSF_CLKGATE_DIS);
+
+	/* WaForwardProgressSoftReset:icl */
+	I915_WRITE(GEN10_SCRATCH_LNCF2,
+		   I915_READ(GEN10_SCRATCH_LNCF2) |
+		   PMFLUSHDONE_LNICRSDROP |
+		   PMFLUSH_GAPL3UNBLOCK |
+		   PMFLUSHDONE_LNEBLK);
+}
+
+void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv)
+{
+	if (INTEL_GEN(dev_priv) < 8)
+		return;
+	else if (IS_BROADWELL(dev_priv))
+		bdw_gt_workarounds_apply(dev_priv);
+	else if (IS_CHERRYVIEW(dev_priv))
+		chv_gt_workarounds_apply(dev_priv);
+	else if (IS_SKYLAKE(dev_priv))
+		skl_gt_workarounds_apply(dev_priv);
+	else if (IS_BROXTON(dev_priv))
+		bxt_gt_workarounds_apply(dev_priv);
+	else if (IS_KABYLAKE(dev_priv))
+		kbl_gt_workarounds_apply(dev_priv);
+	else if (IS_GEMINILAKE(dev_priv))
+		glk_gt_workarounds_apply(dev_priv);
+	else if (IS_COFFEELAKE(dev_priv))
+		cfl_gt_workarounds_apply(dev_priv);
+	else if (IS_CANNONLAKE(dev_priv))
+		cnl_gt_workarounds_apply(dev_priv);
+	else if (IS_ICELAKE(dev_priv))
+		icl_gt_workarounds_apply(dev_priv);
+	else
+		MISSING_CASE(INTEL_GEN(dev_priv));
+}
+
+struct whitelist {
+	i915_reg_t reg[RING_MAX_NONPRIV_SLOTS];
+	unsigned int count;
+	u32 nopid;
+};
+
+static void whitelist_reg(struct whitelist *w, i915_reg_t reg)
+{
+	if (GEM_WARN_ON(w->count >= RING_MAX_NONPRIV_SLOTS))
+		return;
+
+	w->reg[w->count++] = reg;
+}
+
+static void bdw_whitelist_build(struct whitelist *w)
+{
+}
+
+static void chv_whitelist_build(struct whitelist *w)
+{
+}
+
+static void gen9_whitelist_build(struct whitelist *w)
+{
+	/* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */
+	whitelist_reg(w, GEN9_CTX_PREEMPT_REG);
+
+	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */
+	whitelist_reg(w, GEN8_CS_CHICKEN1);
+
+	/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
+	whitelist_reg(w, GEN8_HDC_CHICKEN1);
+}
+
+static void skl_whitelist_build(struct whitelist *w)
+{
+	gen9_whitelist_build(w);
+
+	/* WaDisableLSQCROPERFforOCL:skl */
+	whitelist_reg(w, GEN8_L3SQCREG4);
+}
+
+static void bxt_whitelist_build(struct whitelist *w)
+{
+	gen9_whitelist_build(w);
+}
+
+static void kbl_whitelist_build(struct whitelist *w)
+{
+	gen9_whitelist_build(w);
+
+	/* WaDisableLSQCROPERFforOCL:kbl */
+	whitelist_reg(w, GEN8_L3SQCREG4);
+}
+
+static void glk_whitelist_build(struct whitelist *w)
+{
+	gen9_whitelist_build(w);
+
+	/* WA #0862: Userspace has to set "Barrier Mode" to avoid hangs. */
+	whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1);
+}
+
+static void cfl_whitelist_build(struct whitelist *w)
+{
+	gen9_whitelist_build(w);
+}
+
+static void cnl_whitelist_build(struct whitelist *w)
+{
+	/* WaEnablePreemptionGranularityControlByUMD:cnl */
+	whitelist_reg(w, GEN8_CS_CHICKEN1);
+}
+
+static void icl_whitelist_build(struct whitelist *w)
+{
+}
+
+static struct whitelist *whitelist_build(struct intel_engine_cs *engine,
+					 struct whitelist *w)
+{
+	struct drm_i915_private *i915 = engine->i915;
+
+	GEM_BUG_ON(engine->id != RCS);
+
+	w->count = 0;
+	w->nopid = i915_mmio_reg_offset(RING_NOPID(engine->mmio_base));
+
+	if (INTEL_GEN(i915) < 8)
+		return NULL;
+	else if (IS_BROADWELL(i915))
+		bdw_whitelist_build(w);
+	else if (IS_CHERRYVIEW(i915))
+		chv_whitelist_build(w);
+	else if (IS_SKYLAKE(i915))
+		skl_whitelist_build(w);
+	else if (IS_BROXTON(i915))
+		bxt_whitelist_build(w);
+	else if (IS_KABYLAKE(i915))
+		kbl_whitelist_build(w);
+	else if (IS_GEMINILAKE(i915))
+		glk_whitelist_build(w);
+	else if (IS_COFFEELAKE(i915))
+		cfl_whitelist_build(w);
+	else if (IS_CANNONLAKE(i915))
+		cnl_whitelist_build(w);
+	else if (IS_ICELAKE(i915))
+		icl_whitelist_build(w);
+	else
+		MISSING_CASE(INTEL_GEN(i915));
+
+	return w;
+}
+
+static void whitelist_apply(struct intel_engine_cs *engine,
+			    const struct whitelist *w)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	const u32 base = engine->mmio_base;
+	unsigned int i;
+
+	if (!w)
+		return;
+
+	intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
+
+	for (i = 0; i < w->count; i++)
+		I915_WRITE_FW(RING_FORCE_TO_NONPRIV(base, i),
+			      i915_mmio_reg_offset(w->reg[i]));
+
+	/* And clear the rest just in case of garbage */
+	for (; i < RING_MAX_NONPRIV_SLOTS; i++)
+		I915_WRITE_FW(RING_FORCE_TO_NONPRIV(base, i), w->nopid);
+
+	intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL);
+}
+
+void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine)
+{
+	struct whitelist w;
+
+	whitelist_apply(engine, whitelist_build(engine, &w));
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/intel_workarounds.c"
+#endif
diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h
new file mode 100644
index 000000000000..b11d0623e626
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_workarounds.h
@@ -0,0 +1,17 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2014-2018 Intel Corporation
+ */
+
+#ifndef _I915_WORKAROUNDS_H_
+#define _I915_WORKAROUNDS_H_
+
+int intel_ctx_workarounds_init(struct drm_i915_private *dev_priv);
+int intel_ctx_workarounds_emit(struct i915_request *rq);
+
+void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv);
+
+void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine);
+
+#endif
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 05bbef363fff..91c72911be3c 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -1091,7 +1091,7 @@ static int __igt_write_huge(struct i915_gem_context *ctx,
 out_vma_unpin:
 	i915_vma_unpin(vma);
 out_vma_close:
-	i915_vma_close(vma);
+	i915_vma_destroy(vma);
 
 	return err;
 }
@@ -1757,6 +1757,9 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 		goto out_unlock;
 	}
 
+	if (ctx->ppgtt)
+		ctx->ppgtt->base.scrub_64K = true;
+
 	err = i915_subtests(tests, ctx);
 
 out_unlock:
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 7ecaed50d0b9..ddb03f009232 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -23,6 +23,7 @@
  */
 
 #include "../i915_selftest.h"
+#include "igt_flush_test.h"
 
 #include "mock_drm.h"
 #include "huge_gem_object.h"
@@ -411,6 +412,8 @@ static int igt_ctx_exec(void *arg)
 	}
 
 out_unlock:
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	mock_file_free(i915, file);
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 9c76f0305b6a..a00e2bd08bce 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -11,6 +11,7 @@
  */
 selftest(sanitycheck, i915_live_sanitycheck) /* keep first (igt selfcheck) */
 selftest(uncore, intel_uncore_live_selftests)
+selftest(workarounds, intel_workarounds_live_selftests)
 selftest(requests, i915_request_live_selftests)
 selftest(objects, i915_gem_object_live_selftests)
 selftest(dmabuf, i915_gem_dmabuf_live_selftests)
@@ -20,4 +21,5 @@ selftest(evict, i915_gem_evict_live_selftests)
 selftest(hugepages, i915_gem_huge_page_live_selftests)
 selftest(contexts, i915_gem_context_live_selftests)
 selftest(hangcheck, intel_hangcheck_live_selftests)
+selftest(execlists, intel_execlists_live_selftests)
 selftest(guc, intel_guc_live_selftest)
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index 9a48aa441743..d16d74178e9d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -14,6 +14,7 @@ selftest(fence, i915_sw_fence_mock_selftests)
 selftest(scatterlist, scatterlist_mock_selftests)
 selftest(syncmap, i915_syncmap_mock_selftests)
 selftest(uncore, intel_uncore_mock_selftests)
+selftest(engine, intel_engine_cs_mock_selftests)
 selftest(breadcrumbs, intel_breadcrumbs_mock_selftests)
 selftest(timelines, i915_gem_timeline_mock_selftests)
 selftest(requests, i915_request_mock_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c b/drivers/gpu/drm/i915/selftests/i915_timeline.c
index 3000e6a7d82d..19f1c6a5c8fb 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/i915_timeline.c
@@ -1,25 +1,7 @@
 /*
- * Copyright © 2017 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
+ * SPDX-License-Identifier: MIT
  *
+ * Copyright © 2017-2018 Intel Corporation
  */
 
 #include "../i915_selftest.h"
@@ -35,21 +17,21 @@ struct __igt_sync {
 	bool set;
 };
 
-static int __igt_sync(struct intel_timeline *tl,
+static int __igt_sync(struct i915_timeline *tl,
 		      u64 ctx,
 		      const struct __igt_sync *p,
 		      const char *name)
 {
 	int ret;
 
-	if (__intel_timeline_sync_is_later(tl, ctx, p->seqno) != p->expected) {
+	if (__i915_timeline_sync_is_later(tl, ctx, p->seqno) != p->expected) {
 		pr_err("%s: %s(ctx=%llu, seqno=%u) expected passed %s but failed\n",
 		       name, p->name, ctx, p->seqno, yesno(p->expected));
 		return -EINVAL;
 	}
 
 	if (p->set) {
-		ret = __intel_timeline_sync_set(tl, ctx, p->seqno);
+		ret = __i915_timeline_sync_set(tl, ctx, p->seqno);
 		if (ret)
 			return ret;
 	}
@@ -77,37 +59,31 @@ static int igt_sync(void *arg)
 		{ "unwrap", UINT_MAX, true, false },
 		{},
 	}, *p;
-	struct intel_timeline *tl;
+	struct i915_timeline tl;
 	int order, offset;
 	int ret = -ENODEV;
 
-	tl = mock_timeline(0);
-	if (!tl)
-		return -ENOMEM;
-
+	mock_timeline_init(&tl, 0);
 	for (p = pass; p->name; p++) {
 		for (order = 1; order < 64; order++) {
 			for (offset = -1; offset <= (order > 1); offset++) {
 				u64 ctx = BIT_ULL(order) + offset;
 
-				ret = __igt_sync(tl, ctx, p, "1");
+				ret = __igt_sync(&tl, ctx, p, "1");
 				if (ret)
 					goto out;
 			}
 		}
 	}
-	mock_timeline_destroy(tl);
-
-	tl = mock_timeline(0);
-	if (!tl)
-		return -ENOMEM;
+	mock_timeline_fini(&tl);
 
+	mock_timeline_init(&tl, 0);
 	for (order = 1; order < 64; order++) {
 		for (offset = -1; offset <= (order > 1); offset++) {
 			u64 ctx = BIT_ULL(order) + offset;
 
 			for (p = pass; p->name; p++) {
-				ret = __igt_sync(tl, ctx, p, "2");
+				ret = __igt_sync(&tl, ctx, p, "2");
 				if (ret)
 					goto out;
 			}
@@ -115,7 +91,7 @@ static int igt_sync(void *arg)
 	}
 
 out:
-	mock_timeline_destroy(tl);
+	mock_timeline_fini(&tl);
 	return ret;
 }
 
@@ -127,15 +103,13 @@ static unsigned int random_engine(struct rnd_state *rnd)
 static int bench_sync(void *arg)
 {
 	struct rnd_state prng;
-	struct intel_timeline *tl;
+	struct i915_timeline tl;
 	unsigned long end_time, count;
 	u64 prng32_1M;
 	ktime_t kt;
 	int order, last_order;
 
-	tl = mock_timeline(0);
-	if (!tl)
-		return -ENOMEM;
+	mock_timeline_init(&tl, 0);
 
 	/* Lookups from cache are very fast and so the random number generation
 	 * and the loop itself becomes a significant factor in the per-iteration
@@ -167,7 +141,7 @@ static int bench_sync(void *arg)
 	do {
 		u64 id = i915_prandom_u64_state(&prng);
 
-		__intel_timeline_sync_set(tl, id, 0);
+		__i915_timeline_sync_set(&tl, id, 0);
 		count++;
 	} while (!time_after(jiffies, end_time));
 	kt = ktime_sub(ktime_get(), kt);
@@ -182,8 +156,8 @@ static int bench_sync(void *arg)
 	while (end_time--) {
 		u64 id = i915_prandom_u64_state(&prng);
 
-		if (!__intel_timeline_sync_is_later(tl, id, 0)) {
-			mock_timeline_destroy(tl);
+		if (!__i915_timeline_sync_is_later(&tl, id, 0)) {
+			mock_timeline_fini(&tl);
 			pr_err("Lookup of %llu failed\n", id);
 			return -EINVAL;
 		}
@@ -193,19 +167,17 @@ static int bench_sync(void *arg)
 	pr_info("%s: %lu random lookups, %lluns/lookup\n",
 		__func__, count, (long long)div64_ul(ktime_to_ns(kt), count));
 
-	mock_timeline_destroy(tl);
+	mock_timeline_fini(&tl);
 	cond_resched();
 
-	tl = mock_timeline(0);
-	if (!tl)
-		return -ENOMEM;
+	mock_timeline_init(&tl, 0);
 
 	/* Benchmark setting the first N (in order) contexts */
 	count = 0;
 	kt = ktime_get();
 	end_time = jiffies + HZ/10;
 	do {
-		__intel_timeline_sync_set(tl, count++, 0);
+		__i915_timeline_sync_set(&tl, count++, 0);
 	} while (!time_after(jiffies, end_time));
 	kt = ktime_sub(ktime_get(), kt);
 	pr_info("%s: %lu in-order insertions, %lluns/insert\n",
@@ -215,9 +187,9 @@ static int bench_sync(void *arg)
 	end_time = count;
 	kt = ktime_get();
 	while (end_time--) {
-		if (!__intel_timeline_sync_is_later(tl, end_time, 0)) {
+		if (!__i915_timeline_sync_is_later(&tl, end_time, 0)) {
 			pr_err("Lookup of %lu failed\n", end_time);
-			mock_timeline_destroy(tl);
+			mock_timeline_fini(&tl);
 			return -EINVAL;
 		}
 	}
@@ -225,12 +197,10 @@ static int bench_sync(void *arg)
 	pr_info("%s: %lu in-order lookups, %lluns/lookup\n",
 		__func__, count, (long long)div64_ul(ktime_to_ns(kt), count));
 
-	mock_timeline_destroy(tl);
+	mock_timeline_fini(&tl);
 	cond_resched();
 
-	tl = mock_timeline(0);
-	if (!tl)
-		return -ENOMEM;
+	mock_timeline_init(&tl, 0);
 
 	/* Benchmark searching for a random context id and maybe changing it */
 	prandom_seed_state(&prng, i915_selftest.random_seed);
@@ -241,8 +211,8 @@ static int bench_sync(void *arg)
 		u32 id = random_engine(&prng);
 		u32 seqno = prandom_u32_state(&prng);
 
-		if (!__intel_timeline_sync_is_later(tl, id, seqno))
-			__intel_timeline_sync_set(tl, id, seqno);
+		if (!__i915_timeline_sync_is_later(&tl, id, seqno))
+			__i915_timeline_sync_set(&tl, id, seqno);
 
 		count++;
 	} while (!time_after(jiffies, end_time));
@@ -250,7 +220,7 @@ static int bench_sync(void *arg)
 	kt = ktime_sub_ns(kt, (count * prng32_1M * 2) >> 20);
 	pr_info("%s: %lu repeated insert/lookups, %lluns/op\n",
 		__func__, count, (long long)div64_ul(ktime_to_ns(kt), count));
-	mock_timeline_destroy(tl);
+	mock_timeline_fini(&tl);
 	cond_resched();
 
 	/* Benchmark searching for a known context id and changing the seqno */
@@ -258,9 +228,7 @@ static int bench_sync(void *arg)
 	     ({ int tmp = last_order; last_order = order; order += tmp; })) {
 		unsigned int mask = BIT(order) - 1;
 
-		tl = mock_timeline(0);
-		if (!tl)
-			return -ENOMEM;
+		mock_timeline_init(&tl, 0);
 
 		count = 0;
 		kt = ktime_get();
@@ -272,8 +240,8 @@ static int bench_sync(void *arg)
 			 */
 			u64 id = (u64)(count & mask) << order;
 
-			__intel_timeline_sync_is_later(tl, id, 0);
-			__intel_timeline_sync_set(tl, id, 0);
+			__i915_timeline_sync_is_later(&tl, id, 0);
+			__i915_timeline_sync_set(&tl, id, 0);
 
 			count++;
 		} while (!time_after(jiffies, end_time));
@@ -281,7 +249,7 @@ static int bench_sync(void *arg)
 		pr_info("%s: %lu cyclic/%d insert/lookups, %lluns/op\n",
 			__func__, count, order,
 			(long long)div64_ul(ktime_to_ns(kt), count));
-		mock_timeline_destroy(tl);
+		mock_timeline_fini(&tl);
 		cond_resched();
 	}
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index eb89e301b602..e90f97236e50 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -81,7 +81,7 @@ checked_vma_instance(struct drm_i915_gem_object *obj,
 	}
 
 	if (i915_vma_compare(vma, vm, view)) {
-		pr_err("i915_vma_compare failed with create parmaters!\n");
+		pr_err("i915_vma_compare failed with create parameters!\n");
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
new file mode 100644
index 000000000000..0d06f559243f
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -0,0 +1,70 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include "../i915_drv.h"
+
+#include "../i915_selftest.h"
+#include "igt_flush_test.h"
+
+struct wedge_me {
+	struct delayed_work work;
+	struct drm_i915_private *i915;
+	const void *symbol;
+};
+
+static void wedge_me(struct work_struct *work)
+{
+	struct wedge_me *w = container_of(work, typeof(*w), work.work);
+
+	pr_err("%pS timed out, cancelling all further testing.\n", w->symbol);
+
+	GEM_TRACE("%pS timed out.\n", w->symbol);
+	GEM_TRACE_DUMP();
+
+	i915_gem_set_wedged(w->i915);
+}
+
+static void __init_wedge(struct wedge_me *w,
+			 struct drm_i915_private *i915,
+			 long timeout,
+			 const void *symbol)
+{
+	w->i915 = i915;
+	w->symbol = symbol;
+
+	INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me);
+	schedule_delayed_work(&w->work, timeout);
+}
+
+static void __fini_wedge(struct wedge_me *w)
+{
+	cancel_delayed_work_sync(&w->work);
+	destroy_delayed_work_on_stack(&w->work);
+	w->i915 = NULL;
+}
+
+#define wedge_on_timeout(W, DEV, TIMEOUT)				\
+	for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \
+	     (W)->i915;							\
+	     __fini_wedge((W)))
+
+int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
+{
+	struct wedge_me w;
+
+	cond_resched();
+
+	if (flags & I915_WAIT_LOCKED &&
+	    i915_gem_switch_to_kernel_context(i915)) {
+		pr_err("Failed to switch back to kernel context; declaring wedged\n");
+		i915_gem_set_wedged(i915);
+	}
+
+	wedge_on_timeout(&w, i915, HZ)
+		i915_gem_wait_for_idle(i915, flags);
+
+	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
+}
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.h b/drivers/gpu/drm/i915/selftests/igt_flush_test.h
new file mode 100644
index 000000000000..63e009927c43
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.h
@@ -0,0 +1,14 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#ifndef IGT_FLUSH_TEST_H
+#define IGT_FLUSH_TEST_H
+
+struct drm_i915_private;
+
+int igt_flush_test(struct drm_i915_private *i915, unsigned int flags);
+
+#endif /* IGT_FLUSH_TEST_H */
diff --git a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
index 46580026c7fc..d6926e7820e5 100644
--- a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
@@ -412,10 +412,11 @@ static int igt_wakeup(void *arg)
 		 * that they are ready for the next test. We wait until all
 		 * threads are complete and waiting for us (i.e. not a seqno).
 		 */
-		err = wait_var_event_timeout(&done, !atomic_read(&done), 10 * HZ);
-		if (err) {
+		if (!wait_var_event_timeout(&done,
+					    !atomic_read(&done), 10 * HZ)) {
 			pr_err("Timed out waiting for %d remaining waiters\n",
 			       atomic_read(&done));
+			err = -ETIMEDOUT;
 			break;
 		}
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_engine_cs.c b/drivers/gpu/drm/i915/selftests/intel_engine_cs.c
new file mode 100644
index 000000000000..cfaa6b296835
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/intel_engine_cs.c
@@ -0,0 +1,58 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include "../i915_selftest.h"
+
+static int intel_mmio_bases_check(void *arg)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(intel_engines); i++) {
+		const struct engine_info *info = &intel_engines[i];
+		char name[INTEL_ENGINE_CS_MAX_NAME];
+		u8 prev = U8_MAX;
+
+		__sprint_engine_name(name, info);
+
+		for (j = 0; j < MAX_MMIO_BASES; j++) {
+			u8 gen = info->mmio_bases[j].gen;
+			u32 base = info->mmio_bases[j].base;
+
+			if (gen >= prev) {
+				pr_err("%s: %s: mmio base for gen %x "
+					"is before the one for gen %x\n",
+				       __func__, name, prev, gen);
+				return -EINVAL;
+			}
+
+			if (gen == 0)
+				break;
+
+			if (!base) {
+				pr_err("%s: %s: invalid mmio base (%x) "
+					"for gen %x at entry %u\n",
+				       __func__, name, base, gen, j);
+				return -EINVAL;
+			}
+
+			prev = gen;
+		}
+
+		pr_info("%s: min gen supported for %s = %d\n",
+			__func__, name, prev);
+	}
+
+	return 0;
+}
+
+int intel_engine_cs_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(intel_mmio_bases_check),
+	};
+
+	return i915_subtests(tests, NULL);
+}
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index df7898c8edcb..438e0b045a2c 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -25,10 +25,14 @@
 #include <linux/kthread.h>
 
 #include "../i915_selftest.h"
+#include "i915_random.h"
+#include "igt_flush_test.h"
 
 #include "mock_context.h"
 #include "mock_drm.h"
 
+#define IGT_IDLE_TIMEOUT 50 /* ms; time to wait after flushing between tests */
+
 struct hang {
 	struct drm_i915_private *i915;
 	struct drm_i915_gem_object *hws;
@@ -250,58 +254,6 @@ static u32 hws_seqno(const struct hang *h, const struct i915_request *rq)
 	return READ_ONCE(h->seqno[rq->fence.context % (PAGE_SIZE/sizeof(u32))]);
 }
 
-struct wedge_me {
-	struct delayed_work work;
-	struct drm_i915_private *i915;
-	const void *symbol;
-};
-
-static void wedge_me(struct work_struct *work)
-{
-	struct wedge_me *w = container_of(work, typeof(*w), work.work);
-
-	pr_err("%pS timed out, cancelling all further testing.\n",
-	       w->symbol);
-	i915_gem_set_wedged(w->i915);
-}
-
-static void __init_wedge(struct wedge_me *w,
-			 struct drm_i915_private *i915,
-			 long timeout,
-			 const void *symbol)
-{
-	w->i915 = i915;
-	w->symbol = symbol;
-
-	INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me);
-	schedule_delayed_work(&w->work, timeout);
-}
-
-static void __fini_wedge(struct wedge_me *w)
-{
-	cancel_delayed_work_sync(&w->work);
-	destroy_delayed_work_on_stack(&w->work);
-	w->i915 = NULL;
-}
-
-#define wedge_on_timeout(W, DEV, TIMEOUT)				\
-	for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \
-	     (W)->i915;							\
-	     __fini_wedge((W)))
-
-static noinline int
-flush_test(struct drm_i915_private *i915, unsigned int flags)
-{
-	struct wedge_me w;
-
-	cond_resched();
-
-	wedge_on_timeout(&w, i915, HZ)
-		i915_gem_wait_for_idle(i915, flags);
-
-	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
-}
-
 static void hang_fini(struct hang *h)
 {
 	*h->batch = MI_BATCH_BUFFER_END;
@@ -315,10 +267,10 @@ static void hang_fini(struct hang *h)
 
 	kernel_context_close(h->ctx);
 
-	flush_test(h->i915, I915_WAIT_LOCKED);
+	igt_flush_test(h->i915, I915_WAIT_LOCKED);
 }
 
-static bool wait_for_hang(struct hang *h, struct i915_request *rq)
+static bool wait_until_running(struct hang *h, struct i915_request *rq)
 {
 	return !(wait_for_us(i915_seqno_passed(hws_seqno(h, rq),
 					       rq->fence.seqno),
@@ -433,7 +385,7 @@ static int igt_global_reset(void *arg)
 	mutex_lock(&i915->drm.struct_mutex);
 	reset_count = i915_reset_count(&i915->gpu_error);
 
-	i915_reset(i915, I915_RESET_QUIET);
+	i915_reset(i915, ALL_ENGINES, NULL);
 
 	if (i915_reset_count(&i915->gpu_error) == reset_count) {
 		pr_err("No GPU reset recorded!\n");
@@ -450,6 +402,11 @@ static int igt_global_reset(void *arg)
 	return err;
 }
 
+static bool wait_for_idle(struct intel_engine_cs *engine)
+{
+	return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0;
+}
+
 static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 {
 	struct intel_engine_cs *engine;
@@ -477,12 +434,21 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 		if (active && !intel_engine_can_store_dword(engine))
 			continue;
 
+		if (!wait_for_idle(engine)) {
+			pr_err("%s failed to idle before reset\n",
+			       engine->name);
+			err = -EIO;
+			break;
+		}
+
 		reset_count = i915_reset_count(&i915->gpu_error);
 		reset_engine_count = i915_reset_engine_count(&i915->gpu_error,
 							     engine);
 
 		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
 		do {
+			u32 seqno = intel_engine_get_seqno(engine);
+
 			if (active) {
 				struct i915_request *rq;
 
@@ -498,7 +464,7 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 				__i915_request_add(rq, true);
 				mutex_unlock(&i915->drm.struct_mutex);
 
-				if (!wait_for_hang(&h, rq)) {
+				if (!wait_until_running(&h, rq)) {
 					struct drm_printer p = drm_info_printer(i915->drm.dev);
 
 					pr_err("%s: Failed to start request %x, at %x\n",
@@ -511,14 +477,12 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 					break;
 				}
 
+				GEM_BUG_ON(!rq->global_seqno);
+				seqno = rq->global_seqno - 1;
 				i915_request_put(rq);
 			}
 
-			engine->hangcheck.stalled = true;
-			engine->hangcheck.seqno =
-				intel_engine_get_seqno(engine);
-
-			err = i915_reset_engine(engine, I915_RESET_QUIET);
+			err = i915_reset_engine(engine, NULL);
 			if (err) {
 				pr_err("i915_reset_engine failed\n");
 				break;
@@ -539,14 +503,25 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 				break;
 			}
 
-			engine->hangcheck.stalled = false;
+			if (!wait_for_idle(engine)) {
+				struct drm_printer p =
+					drm_info_printer(i915->drm.dev);
+
+				pr_err("%s failed to idle after reset\n",
+				       engine->name);
+				intel_engine_dump(engine, &p,
+						  "%s\n", engine->name);
+
+				err = -EIO;
+				break;
+			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
 
 		if (err)
 			break;
 
-		err = flush_test(i915, 0);
+		err = igt_flush_test(i915, 0);
 		if (err)
 			break;
 	}
@@ -573,11 +548,25 @@ static int igt_reset_active_engine(void *arg)
 	return __igt_reset_engine(arg, true);
 }
 
+struct active_engine {
+	struct task_struct *task;
+	struct intel_engine_cs *engine;
+	unsigned long resets;
+	unsigned int flags;
+};
+
+#define TEST_ACTIVE	BIT(0)
+#define TEST_OTHERS	BIT(1)
+#define TEST_SELF	BIT(2)
+#define TEST_PRIORITY	BIT(3)
+
 static int active_engine(void *data)
 {
-	struct intel_engine_cs *engine = data;
-	struct i915_request *rq[2] = {};
-	struct i915_gem_context *ctx[2];
+	I915_RND_STATE(prng);
+	struct active_engine *arg = data;
+	struct intel_engine_cs *engine = arg->engine;
+	struct i915_request *rq[8] = {};
+	struct i915_gem_context *ctx[ARRAY_SIZE(rq)];
 	struct drm_file *file;
 	unsigned long count = 0;
 	int err = 0;
@@ -586,25 +575,20 @@ static int active_engine(void *data)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&engine->i915->drm.struct_mutex);
-	ctx[0] = live_context(engine->i915, file);
-	mutex_unlock(&engine->i915->drm.struct_mutex);
-	if (IS_ERR(ctx[0])) {
-		err = PTR_ERR(ctx[0]);
-		goto err_file;
-	}
-
-	mutex_lock(&engine->i915->drm.struct_mutex);
-	ctx[1] = live_context(engine->i915, file);
-	mutex_unlock(&engine->i915->drm.struct_mutex);
-	if (IS_ERR(ctx[1])) {
-		err = PTR_ERR(ctx[1]);
-		i915_gem_context_put(ctx[0]);
-		goto err_file;
+	for (count = 0; count < ARRAY_SIZE(ctx); count++) {
+		mutex_lock(&engine->i915->drm.struct_mutex);
+		ctx[count] = live_context(engine->i915, file);
+		mutex_unlock(&engine->i915->drm.struct_mutex);
+		if (IS_ERR(ctx[count])) {
+			err = PTR_ERR(ctx[count]);
+			while (--count)
+				i915_gem_context_put(ctx[count]);
+			goto err_file;
+		}
 	}
 
 	while (!kthread_should_stop()) {
-		unsigned int idx = count++ & 1;
+		unsigned int idx = count++ & (ARRAY_SIZE(rq) - 1);
 		struct i915_request *old = rq[idx];
 		struct i915_request *new;
 
@@ -616,14 +600,28 @@ static int active_engine(void *data)
 			break;
 		}
 
+		if (arg->flags & TEST_PRIORITY)
+			ctx[idx]->sched.priority =
+				i915_prandom_u32_max_state(512, &prng);
+
 		rq[idx] = i915_request_get(new);
 		i915_request_add(new);
 		mutex_unlock(&engine->i915->drm.struct_mutex);
 
 		if (old) {
-			i915_request_wait(old, 0, MAX_SCHEDULE_TIMEOUT);
+			if (i915_request_wait(old, 0, HZ) < 0) {
+				GEM_TRACE("%s timed out.\n", engine->name);
+				GEM_TRACE_DUMP();
+
+				i915_gem_set_wedged(engine->i915);
+				i915_request_put(old);
+				err = -EIO;
+				break;
+			}
 			i915_request_put(old);
 		}
+
+		cond_resched();
 	}
 
 	for (count = 0; count < ARRAY_SIZE(rq); count++)
@@ -634,8 +632,9 @@ err_file:
 	return err;
 }
 
-static int __igt_reset_engine_others(struct drm_i915_private *i915,
-				     bool active)
+static int __igt_reset_engines(struct drm_i915_private *i915,
+			       const char *test_name,
+			       unsigned int flags)
 {
 	struct intel_engine_cs *engine, *other;
 	enum intel_engine_id id, tmp;
@@ -649,50 +648,68 @@ static int __igt_reset_engine_others(struct drm_i915_private *i915,
 	if (!intel_has_reset_engine(i915))
 		return 0;
 
-	if (active) {
+	if (flags & TEST_ACTIVE) {
 		mutex_lock(&i915->drm.struct_mutex);
 		err = hang_init(&h, i915);
 		mutex_unlock(&i915->drm.struct_mutex);
 		if (err)
 			return err;
+
+		if (flags & TEST_PRIORITY)
+			h.ctx->sched.priority = 1024;
 	}
 
 	for_each_engine(engine, i915, id) {
-		struct task_struct *threads[I915_NUM_ENGINES] = {};
-		unsigned long resets[I915_NUM_ENGINES];
+		struct active_engine threads[I915_NUM_ENGINES] = {};
 		unsigned long global = i915_reset_count(&i915->gpu_error);
-		unsigned long count = 0;
+		unsigned long count = 0, reported;
 		IGT_TIMEOUT(end_time);
 
-		if (active && !intel_engine_can_store_dword(engine))
+		if (flags & TEST_ACTIVE &&
+		    !intel_engine_can_store_dword(engine))
 			continue;
 
+		if (!wait_for_idle(engine)) {
+			pr_err("i915_reset_engine(%s:%s): failed to idle before reset\n",
+			       engine->name, test_name);
+			err = -EIO;
+			break;
+		}
+
 		memset(threads, 0, sizeof(threads));
 		for_each_engine(other, i915, tmp) {
 			struct task_struct *tsk;
 
-			resets[tmp] = i915_reset_engine_count(&i915->gpu_error,
-							      other);
+			threads[tmp].resets =
+				i915_reset_engine_count(&i915->gpu_error,
+							other);
+
+			if (!(flags & TEST_OTHERS))
+				continue;
 
-			if (other == engine)
+			if (other == engine && !(flags & TEST_SELF))
 				continue;
 
-			tsk = kthread_run(active_engine, other,
+			threads[tmp].engine = other;
+			threads[tmp].flags = flags;
+
+			tsk = kthread_run(active_engine, &threads[tmp],
 					  "igt/%s", other->name);
 			if (IS_ERR(tsk)) {
 				err = PTR_ERR(tsk);
 				goto unwind;
 			}
 
-			threads[tmp] = tsk;
+			threads[tmp].task = tsk;
 			get_task_struct(tsk);
 		}
 
 		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
 		do {
-			if (active) {
-				struct i915_request *rq;
+			u32 seqno = intel_engine_get_seqno(engine);
+			struct i915_request *rq = NULL;
 
+			if (flags & TEST_ACTIVE) {
 				mutex_lock(&i915->drm.struct_mutex);
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
@@ -705,7 +722,7 @@ static int __igt_reset_engine_others(struct drm_i915_private *i915,
 				__i915_request_add(rq, true);
 				mutex_unlock(&i915->drm.struct_mutex);
 
-				if (!wait_for_hang(&h, rq)) {
+				if (!wait_until_running(&h, rq)) {
 					struct drm_printer p = drm_info_printer(i915->drm.dev);
 
 					pr_err("%s: Failed to start request %x, at %x\n",
@@ -718,33 +735,48 @@ static int __igt_reset_engine_others(struct drm_i915_private *i915,
 					break;
 				}
 
-				i915_request_put(rq);
+				GEM_BUG_ON(!rq->global_seqno);
+				seqno = rq->global_seqno - 1;
 			}
 
-			engine->hangcheck.stalled = true;
-			engine->hangcheck.seqno =
-				intel_engine_get_seqno(engine);
-
-			err = i915_reset_engine(engine, I915_RESET_QUIET);
+			err = i915_reset_engine(engine, NULL);
 			if (err) {
-				pr_err("i915_reset_engine(%s:%s) failed, err=%d\n",
-				       engine->name, active ? "active" : "idle", err);
+				pr_err("i915_reset_engine(%s:%s): failed, err=%d\n",
+				       engine->name, test_name, err);
 				break;
 			}
 
-			engine->hangcheck.stalled = false;
 			count++;
+
+			if (rq) {
+				i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+				i915_request_put(rq);
+			}
+
+			if (!(flags & TEST_SELF) && !wait_for_idle(engine)) {
+				struct drm_printer p =
+					drm_info_printer(i915->drm.dev);
+
+				pr_err("i915_reset_engine(%s:%s):"
+				       " failed to idle after reset\n",
+				       engine->name, test_name);
+				intel_engine_dump(engine, &p,
+						  "%s\n", engine->name);
+
+				err = -EIO;
+				break;
+			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
 		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
-			engine->name, active ? "active" : "idle", count);
-
-		if (i915_reset_engine_count(&i915->gpu_error, engine) -
-		    resets[engine->id] != (active ? count : 0)) {
-			pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu\n",
-			       engine->name, active ? "active" : "idle", count,
-			       i915_reset_engine_count(&i915->gpu_error,
-						       engine) - resets[engine->id]);
+			engine->name, test_name, count);
+
+		reported = i915_reset_engine_count(&i915->gpu_error, engine);
+		reported -= threads[engine->id].resets;
+		if (reported != (flags & TEST_ACTIVE ? count : 0)) {
+			pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu, expected %lu reported\n",
+			       engine->name, test_name, count, reported,
+			       (flags & TEST_ACTIVE ? count : 0));
 			if (!err)
 				err = -EINVAL;
 		}
@@ -753,24 +785,26 @@ unwind:
 		for_each_engine(other, i915, tmp) {
 			int ret;
 
-			if (!threads[tmp])
+			if (!threads[tmp].task)
 				continue;
 
-			ret = kthread_stop(threads[tmp]);
+			ret = kthread_stop(threads[tmp].task);
 			if (ret) {
 				pr_err("kthread for other engine %s failed, err=%d\n",
 				       other->name, ret);
 				if (!err)
 					err = ret;
 			}
-			put_task_struct(threads[tmp]);
+			put_task_struct(threads[tmp].task);
 
-			if (resets[tmp] != i915_reset_engine_count(&i915->gpu_error,
-								   other)) {
+			if (other != engine &&
+			    threads[tmp].resets !=
+			    i915_reset_engine_count(&i915->gpu_error, other)) {
 				pr_err("Innocent engine %s was reset (count=%ld)\n",
 				       other->name,
 				       i915_reset_engine_count(&i915->gpu_error,
-							       other) - resets[tmp]);
+							       other) -
+				       threads[tmp].resets);
 				if (!err)
 					err = -EINVAL;
 			}
@@ -786,7 +820,7 @@ unwind:
 		if (err)
 			break;
 
-		err = flush_test(i915, 0);
+		err = igt_flush_test(i915, 0);
 		if (err)
 			break;
 	}
@@ -794,7 +828,7 @@ unwind:
 	if (i915_terminally_wedged(&i915->gpu_error))
 		err = -EIO;
 
-	if (active) {
+	if (flags & TEST_ACTIVE) {
 		mutex_lock(&i915->drm.struct_mutex);
 		hang_fini(&h);
 		mutex_unlock(&i915->drm.struct_mutex);
@@ -803,27 +837,56 @@ unwind:
 	return err;
 }
 
-static int igt_reset_idle_engine_others(void *arg)
+static int igt_reset_engines(void *arg)
 {
-	return __igt_reset_engine_others(arg, false);
-}
+	static const struct {
+		const char *name;
+		unsigned int flags;
+	} phases[] = {
+		{ "idle", 0 },
+		{ "active", TEST_ACTIVE },
+		{ "others-idle", TEST_OTHERS },
+		{ "others-active", TEST_OTHERS | TEST_ACTIVE },
+		{
+			"others-priority",
+			TEST_OTHERS | TEST_ACTIVE | TEST_PRIORITY
+		},
+		{
+			"self-priority",
+			TEST_OTHERS | TEST_ACTIVE | TEST_PRIORITY | TEST_SELF,
+		},
+		{ }
+	};
+	struct drm_i915_private *i915 = arg;
+	typeof(*phases) *p;
+	int err;
 
-static int igt_reset_active_engine_others(void *arg)
-{
-	return __igt_reset_engine_others(arg, true);
+	for (p = phases; p->name; p++) {
+		if (p->flags & TEST_PRIORITY) {
+			if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
+				continue;
+		}
+
+		err = __igt_reset_engines(arg, p->name, p->flags);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
-static u32 fake_hangcheck(struct i915_request *rq)
+static u32 fake_hangcheck(struct i915_request *rq, u32 mask)
 {
-	u32 reset_count;
+	struct i915_gpu_error *error = &rq->i915->gpu_error;
+	u32 reset_count = i915_reset_count(error);
 
-	rq->engine->hangcheck.stalled = true;
-	rq->engine->hangcheck.seqno = intel_engine_get_seqno(rq->engine);
+	error->stalled_mask = mask;
 
-	reset_count = i915_reset_count(&rq->i915->gpu_error);
+	/* set_bit() must be after we have setup the backchannel (mask) */
+	smp_mb__before_atomic();
+	set_bit(I915_RESET_HANDOFF, &error->flags);
 
-	set_bit(I915_RESET_HANDOFF, &rq->i915->gpu_error.flags);
-	wake_up_all(&rq->i915->gpu_error.wait_queue);
+	wake_up_all(&error->wait_queue);
 
 	return reset_count;
 }
@@ -858,21 +921,20 @@ static int igt_wait_reset(void *arg)
 	i915_request_get(rq);
 	__i915_request_add(rq, true);
 
-	if (!wait_for_hang(&h, rq)) {
+	if (!wait_until_running(&h, rq)) {
 		struct drm_printer p = drm_info_printer(i915->drm.dev);
 
 		pr_err("%s: Failed to start request %x, at %x\n",
 		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
 		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
 
-		i915_reset(i915, 0);
 		i915_gem_set_wedged(i915);
 
 		err = -EIO;
 		goto out_rq;
 	}
 
-	reset_count = fake_hangcheck(rq);
+	reset_count = fake_hangcheck(rq, ALL_ENGINES);
 
 	timeout = i915_request_wait(rq, I915_WAIT_LOCKED, 10);
 	if (timeout < 0) {
@@ -903,6 +965,23 @@ unlock:
 	return err;
 }
 
+static int wait_for_others(struct drm_i915_private *i915,
+			   struct intel_engine_cs *exclude)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, i915, id) {
+		if (engine == exclude)
+			continue;
+
+		if (!wait_for_idle(engine))
+			return -EIO;
+	}
+
+	return 0;
+}
+
 static int igt_reset_queue(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -951,27 +1030,49 @@ static int igt_reset_queue(void *arg)
 			i915_request_get(rq);
 			__i915_request_add(rq, true);
 
-			if (!wait_for_hang(&h, prev)) {
+			/*
+			 * XXX We don't handle resetting the kernel context
+			 * very well. If we trigger a device reset twice in
+			 * quick succession while the kernel context is
+			 * executing, we may end up skipping the breadcrumb.
+			 * This is really only a problem for the selftest as
+			 * normally there is a large interlude between resets
+			 * (hangcheck), or we focus on resetting just one
+			 * engine and so avoid repeatedly resetting innocents.
+			 */
+			err = wait_for_others(i915, engine);
+			if (err) {
+				pr_err("%s(%s): Failed to idle other inactive engines after device reset\n",
+				       __func__, engine->name);
+				i915_request_put(rq);
+				i915_request_put(prev);
+
+				GEM_TRACE_DUMP();
+				i915_gem_set_wedged(i915);
+				goto fini;
+			}
+
+			if (!wait_until_running(&h, prev)) {
 				struct drm_printer p = drm_info_printer(i915->drm.dev);
 
-				pr_err("%s: Failed to start request %x, at %x\n",
-				       __func__, prev->fence.seqno, hws_seqno(&h, prev));
-				intel_engine_dump(prev->engine, &p,
-						  "%s\n", prev->engine->name);
+				pr_err("%s(%s): Failed to start request %x, at %x\n",
+				       __func__, engine->name,
+				       prev->fence.seqno, hws_seqno(&h, prev));
+				intel_engine_dump(engine, &p,
+						  "%s\n", engine->name);
 
 				i915_request_put(rq);
 				i915_request_put(prev);
 
-				i915_reset(i915, 0);
 				i915_gem_set_wedged(i915);
 
 				err = -EIO;
 				goto fini;
 			}
 
-			reset_count = fake_hangcheck(prev);
+			reset_count = fake_hangcheck(prev, ENGINE_MASK(id));
 
-			i915_reset(i915, I915_RESET_QUIET);
+			i915_reset(i915, ENGINE_MASK(id), NULL);
 
 			GEM_BUG_ON(test_bit(I915_RESET_HANDOFF,
 					    &i915->gpu_error.flags));
@@ -1013,7 +1114,7 @@ static int igt_reset_queue(void *arg)
 
 		i915_request_put(prev);
 
-		err = flush_test(i915, I915_WAIT_LOCKED);
+		err = igt_flush_test(i915, I915_WAIT_LOCKED);
 		if (err)
 			break;
 	}
@@ -1044,7 +1145,7 @@ static int igt_handle_error(void *arg)
 	if (!intel_has_reset_engine(i915))
 		return 0;
 
-	if (!intel_engine_can_store_dword(i915->engine[RCS]))
+	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
 	mutex_lock(&i915->drm.struct_mutex);
@@ -1062,14 +1163,13 @@ static int igt_handle_error(void *arg)
 	i915_request_get(rq);
 	__i915_request_add(rq, true);
 
-	if (!wait_for_hang(&h, rq)) {
+	if (!wait_until_running(&h, rq)) {
 		struct drm_printer p = drm_info_printer(i915->drm.dev);
 
 		pr_err("%s: Failed to start request %x, at %x\n",
 		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
 		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
 
-		i915_reset(i915, 0);
 		i915_gem_set_wedged(i915);
 
 		err = -EIO;
@@ -1081,10 +1181,7 @@ static int igt_handle_error(void *arg)
 	/* Temporarily disable error capture */
 	error = xchg(&i915->gpu_error.first_error, (void *)-1);
 
-	engine->hangcheck.stalled = true;
-	engine->hangcheck.seqno = intel_engine_get_seqno(engine);
-
-	i915_handle_error(i915, intel_engine_flag(engine), "%s", __func__);
+	i915_handle_error(i915, ENGINE_MASK(engine->id), 0, NULL);
 
 	xchg(&i915->gpu_error.first_error, error);
 
@@ -1112,8 +1209,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_hang_sanitycheck),
 		SUBTEST(igt_reset_idle_engine),
 		SUBTEST(igt_reset_active_engine),
-		SUBTEST(igt_reset_idle_engine_others),
-		SUBTEST(igt_reset_active_engine_others),
+		SUBTEST(igt_reset_engines),
 		SUBTEST(igt_wait_reset),
 		SUBTEST(igt_reset_queue),
 		SUBTEST(igt_handle_error),
@@ -1129,6 +1225,10 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 
 	err = i915_subtests(tests, i915);
 
+	mutex_lock(&i915->drm.struct_mutex);
+	igt_flush_test(i915, I915_WAIT_LOCKED);
+	mutex_unlock(&i915->drm.struct_mutex);
+
 	i915_modparams.enable_hangcheck = saved_hangcheck;
 	intel_runtime_pm_put(i915);
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
new file mode 100644
index 000000000000..1b8a07125150
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -0,0 +1,459 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include "../i915_selftest.h"
+#include "igt_flush_test.h"
+
+#include "mock_context.h"
+
+struct spinner {
+	struct drm_i915_private *i915;
+	struct drm_i915_gem_object *hws;
+	struct drm_i915_gem_object *obj;
+	u32 *batch;
+	void *seqno;
+};
+
+static int spinner_init(struct spinner *spin, struct drm_i915_private *i915)
+{
+	unsigned int mode;
+	void *vaddr;
+	int err;
+
+	GEM_BUG_ON(INTEL_GEN(i915) < 8);
+
+	memset(spin, 0, sizeof(*spin));
+	spin->i915 = i915;
+
+	spin->hws = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(spin->hws)) {
+		err = PTR_ERR(spin->hws);
+		goto err;
+	}
+
+	spin->obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(spin->obj)) {
+		err = PTR_ERR(spin->obj);
+		goto err_hws;
+	}
+
+	i915_gem_object_set_cache_level(spin->hws, I915_CACHE_LLC);
+	vaddr = i915_gem_object_pin_map(spin->hws, I915_MAP_WB);
+	if (IS_ERR(vaddr)) {
+		err = PTR_ERR(vaddr);
+		goto err_obj;
+	}
+	spin->seqno = memset(vaddr, 0xff, PAGE_SIZE);
+
+	mode = HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC;
+	vaddr = i915_gem_object_pin_map(spin->obj, mode);
+	if (IS_ERR(vaddr)) {
+		err = PTR_ERR(vaddr);
+		goto err_unpin_hws;
+	}
+	spin->batch = vaddr;
+
+	return 0;
+
+err_unpin_hws:
+	i915_gem_object_unpin_map(spin->hws);
+err_obj:
+	i915_gem_object_put(spin->obj);
+err_hws:
+	i915_gem_object_put(spin->hws);
+err:
+	return err;
+}
+
+static unsigned int seqno_offset(u64 fence)
+{
+	return offset_in_page(sizeof(u32) * fence);
+}
+
+static u64 hws_address(const struct i915_vma *hws,
+		       const struct i915_request *rq)
+{
+	return hws->node.start + seqno_offset(rq->fence.context);
+}
+
+static int emit_recurse_batch(struct spinner *spin,
+			      struct i915_request *rq,
+			      u32 arbitration_command)
+{
+	struct i915_address_space *vm = &rq->ctx->ppgtt->base;
+	struct i915_vma *hws, *vma;
+	u32 *batch;
+	int err;
+
+	vma = i915_vma_instance(spin->obj, vm, NULL);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	hws = i915_vma_instance(spin->hws, vm, NULL);
+	if (IS_ERR(hws))
+		return PTR_ERR(hws);
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		return err;
+
+	err = i915_vma_pin(hws, 0, 0, PIN_USER);
+	if (err)
+		goto unpin_vma;
+
+	i915_vma_move_to_active(vma, rq, 0);
+	if (!i915_gem_object_has_active_reference(vma->obj)) {
+		i915_gem_object_get(vma->obj);
+		i915_gem_object_set_active_reference(vma->obj);
+	}
+
+	i915_vma_move_to_active(hws, rq, 0);
+	if (!i915_gem_object_has_active_reference(hws->obj)) {
+		i915_gem_object_get(hws->obj);
+		i915_gem_object_set_active_reference(hws->obj);
+	}
+
+	batch = spin->batch;
+
+	*batch++ = MI_STORE_DWORD_IMM_GEN4;
+	*batch++ = lower_32_bits(hws_address(hws, rq));
+	*batch++ = upper_32_bits(hws_address(hws, rq));
+	*batch++ = rq->fence.seqno;
+
+	*batch++ = arbitration_command;
+
+	*batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1;
+	*batch++ = lower_32_bits(vma->node.start);
+	*batch++ = upper_32_bits(vma->node.start);
+	*batch++ = MI_BATCH_BUFFER_END; /* not reached */
+
+	i915_gem_chipset_flush(spin->i915);
+
+	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0);
+
+	i915_vma_unpin(hws);
+unpin_vma:
+	i915_vma_unpin(vma);
+	return err;
+}
+
+static struct i915_request *
+spinner_create_request(struct spinner *spin,
+		       struct i915_gem_context *ctx,
+		       struct intel_engine_cs *engine,
+		       u32 arbitration_command)
+{
+	struct i915_request *rq;
+	int err;
+
+	rq = i915_request_alloc(engine, ctx);
+	if (IS_ERR(rq))
+		return rq;
+
+	err = emit_recurse_batch(spin, rq, arbitration_command);
+	if (err) {
+		__i915_request_add(rq, false);
+		return ERR_PTR(err);
+	}
+
+	return rq;
+}
+
+static u32 hws_seqno(const struct spinner *spin, const struct i915_request *rq)
+{
+	u32 *seqno = spin->seqno + seqno_offset(rq->fence.context);
+
+	return READ_ONCE(*seqno);
+}
+
+static void spinner_end(struct spinner *spin)
+{
+	*spin->batch = MI_BATCH_BUFFER_END;
+	i915_gem_chipset_flush(spin->i915);
+}
+
+static void spinner_fini(struct spinner *spin)
+{
+	spinner_end(spin);
+
+	i915_gem_object_unpin_map(spin->obj);
+	i915_gem_object_put(spin->obj);
+
+	i915_gem_object_unpin_map(spin->hws);
+	i915_gem_object_put(spin->hws);
+}
+
+static bool wait_for_spinner(struct spinner *spin, struct i915_request *rq)
+{
+	if (!wait_event_timeout(rq->execute,
+				READ_ONCE(rq->global_seqno),
+				msecs_to_jiffies(10)))
+		return false;
+
+	return !(wait_for_us(i915_seqno_passed(hws_seqno(spin, rq),
+					       rq->fence.seqno),
+			     10) &&
+		 wait_for(i915_seqno_passed(hws_seqno(spin, rq),
+					    rq->fence.seqno),
+			  1000));
+}
+
+static int live_sanitycheck(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *engine;
+	struct i915_gem_context *ctx;
+	enum intel_engine_id id;
+	struct spinner spin;
+	int err = -ENOMEM;
+
+	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
+		return 0;
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	if (spinner_init(&spin, i915))
+		goto err_unlock;
+
+	ctx = kernel_context(i915);
+	if (!ctx)
+		goto err_spin;
+
+	for_each_engine(engine, i915, id) {
+		struct i915_request *rq;
+
+		rq = spinner_create_request(&spin, ctx, engine, MI_NOOP);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_ctx;
+		}
+
+		i915_request_add(rq);
+		if (!wait_for_spinner(&spin, rq)) {
+			GEM_TRACE("spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx;
+		}
+
+		spinner_end(&spin);
+		if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+			err = -EIO;
+			goto err_ctx;
+		}
+	}
+
+	err = 0;
+err_ctx:
+	kernel_context_close(ctx);
+err_spin:
+	spinner_fini(&spin);
+err_unlock:
+	igt_flush_test(i915, I915_WAIT_LOCKED);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
+static int live_preempt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx_hi, *ctx_lo;
+	struct spinner spin_hi, spin_lo;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = -ENOMEM;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+		return 0;
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	if (spinner_init(&spin_hi, i915))
+		goto err_unlock;
+
+	if (spinner_init(&spin_lo, i915))
+		goto err_spin_hi;
+
+	ctx_hi = kernel_context(i915);
+	if (!ctx_hi)
+		goto err_spin_lo;
+	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
+
+	ctx_lo = kernel_context(i915);
+	if (!ctx_lo)
+		goto err_ctx_hi;
+	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+
+	for_each_engine(engine, i915, id) {
+		struct i915_request *rq;
+
+		rq = spinner_create_request(&spin_lo, ctx_lo, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		i915_request_add(rq);
+		if (!wait_for_spinner(&spin_lo, rq)) {
+			GEM_TRACE("lo spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		rq = spinner_create_request(&spin_hi, ctx_hi, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			spinner_end(&spin_lo);
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		i915_request_add(rq);
+		if (!wait_for_spinner(&spin_hi, rq)) {
+			GEM_TRACE("hi spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		spinner_end(&spin_hi);
+		spinner_end(&spin_lo);
+		if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+	}
+
+	err = 0;
+err_ctx_lo:
+	kernel_context_close(ctx_lo);
+err_ctx_hi:
+	kernel_context_close(ctx_hi);
+err_spin_lo:
+	spinner_fini(&spin_lo);
+err_spin_hi:
+	spinner_fini(&spin_hi);
+err_unlock:
+	igt_flush_test(i915, I915_WAIT_LOCKED);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
+static int live_late_preempt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx_hi, *ctx_lo;
+	struct spinner spin_hi, spin_lo;
+	struct intel_engine_cs *engine;
+	struct i915_sched_attr attr = {};
+	enum intel_engine_id id;
+	int err = -ENOMEM;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+		return 0;
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	if (spinner_init(&spin_hi, i915))
+		goto err_unlock;
+
+	if (spinner_init(&spin_lo, i915))
+		goto err_spin_hi;
+
+	ctx_hi = kernel_context(i915);
+	if (!ctx_hi)
+		goto err_spin_lo;
+
+	ctx_lo = kernel_context(i915);
+	if (!ctx_lo)
+		goto err_ctx_hi;
+
+	for_each_engine(engine, i915, id) {
+		struct i915_request *rq;
+
+		rq = spinner_create_request(&spin_lo, ctx_lo, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		i915_request_add(rq);
+		if (!wait_for_spinner(&spin_lo, rq)) {
+			pr_err("First context failed to start\n");
+			goto err_wedged;
+		}
+
+		rq = spinner_create_request(&spin_hi, ctx_hi, engine, MI_NOOP);
+		if (IS_ERR(rq)) {
+			spinner_end(&spin_lo);
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		i915_request_add(rq);
+		if (wait_for_spinner(&spin_hi, rq)) {
+			pr_err("Second context overtook first?\n");
+			goto err_wedged;
+		}
+
+		attr.priority = I915_PRIORITY_MAX;
+		engine->schedule(rq, &attr);
+
+		if (!wait_for_spinner(&spin_hi, rq)) {
+			pr_err("High priority context failed to preempt the low priority context\n");
+			GEM_TRACE_DUMP();
+			goto err_wedged;
+		}
+
+		spinner_end(&spin_hi);
+		spinner_end(&spin_lo);
+		if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+	}
+
+	err = 0;
+err_ctx_lo:
+	kernel_context_close(ctx_lo);
+err_ctx_hi:
+	kernel_context_close(ctx_hi);
+err_spin_lo:
+	spinner_fini(&spin_lo);
+err_spin_hi:
+	spinner_fini(&spin_hi);
+err_unlock:
+	igt_flush_test(i915, I915_WAIT_LOCKED);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+
+err_wedged:
+	spinner_end(&spin_hi);
+	spinner_end(&spin_lo);
+	i915_gem_set_wedged(i915);
+	err = -EIO;
+	goto err_ctx_lo;
+}
+
+int intel_execlists_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_sanitycheck),
+		SUBTEST(live_preempt),
+		SUBTEST(live_late_preempt),
+	};
+
+	if (!HAS_EXECLISTS(i915))
+		return 0;
+
+	return i915_subtests(tests, i915);
+}
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
new file mode 100644
index 000000000000..17444a3abbb9
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -0,0 +1,291 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include "../i915_selftest.h"
+
+#include "mock_context.h"
+
+static struct drm_i915_gem_object *
+read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
+{
+	struct drm_i915_gem_object *result;
+	struct i915_request *rq;
+	struct i915_vma *vma;
+	const u32 base = engine->mmio_base;
+	u32 srm, *cs;
+	int err;
+	int i;
+
+	result = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
+	if (IS_ERR(result))
+		return result;
+
+	i915_gem_object_set_cache_level(result, I915_CACHE_LLC);
+
+	cs = i915_gem_object_pin_map(result, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_obj;
+	}
+	memset(cs, 0xc5, PAGE_SIZE);
+	i915_gem_object_unpin_map(result);
+
+	vma = i915_vma_instance(result, &engine->i915->ggtt.base, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL);
+	if (err)
+		goto err_obj;
+
+	rq = i915_request_alloc(engine, ctx);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_pin;
+	}
+
+	srm = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	if (INTEL_GEN(ctx->i915) >= 8)
+		srm++;
+
+	cs = intel_ring_begin(rq, 4 * RING_MAX_NONPRIV_SLOTS);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_req;
+	}
+
+	for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) {
+		*cs++ = srm;
+		*cs++ = i915_mmio_reg_offset(RING_FORCE_TO_NONPRIV(base, i));
+		*cs++ = i915_ggtt_offset(vma) + sizeof(u32) * i;
+		*cs++ = 0;
+	}
+	intel_ring_advance(rq, cs);
+
+	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	reservation_object_lock(vma->resv, NULL);
+	reservation_object_add_excl_fence(vma->resv, &rq->fence);
+	reservation_object_unlock(vma->resv);
+
+	i915_gem_object_get(result);
+	i915_gem_object_set_active_reference(result);
+
+	__i915_request_add(rq, true);
+	i915_vma_unpin(vma);
+
+	return result;
+
+err_req:
+	i915_request_add(rq);
+err_pin:
+	i915_vma_unpin(vma);
+err_obj:
+	i915_gem_object_put(result);
+	return ERR_PTR(err);
+}
+
+static u32 get_whitelist_reg(const struct whitelist *w, unsigned int i)
+{
+	return i < w->count ? i915_mmio_reg_offset(w->reg[i]) : w->nopid;
+}
+
+static void print_results(const struct whitelist *w, const u32 *results)
+{
+	unsigned int i;
+
+	for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) {
+		u32 expected = get_whitelist_reg(w, i);
+		u32 actual = results[i];
+
+		pr_info("RING_NONPRIV[%d]: expected 0x%08x, found 0x%08x\n",
+			i, expected, actual);
+	}
+}
+
+static int check_whitelist(const struct whitelist *w,
+			   struct i915_gem_context *ctx,
+			   struct intel_engine_cs *engine)
+{
+	struct drm_i915_gem_object *results;
+	u32 *vaddr;
+	int err;
+	int i;
+
+	results = read_nonprivs(ctx, engine);
+	if (IS_ERR(results))
+		return PTR_ERR(results);
+
+	err = i915_gem_object_set_to_cpu_domain(results, false);
+	if (err)
+		goto out_put;
+
+	vaddr = i915_gem_object_pin_map(results, I915_MAP_WB);
+	if (IS_ERR(vaddr)) {
+		err = PTR_ERR(vaddr);
+		goto out_put;
+	}
+
+	for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) {
+		u32 expected = get_whitelist_reg(w, i);
+		u32 actual = vaddr[i];
+
+		if (expected != actual) {
+			print_results(w, vaddr);
+			pr_err("Invalid RING_NONPRIV[%d], expected 0x%08x, found 0x%08x\n",
+			       i, expected, actual);
+
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	i915_gem_object_unpin_map(results);
+out_put:
+	i915_gem_object_put(results);
+	return err;
+}
+
+static int do_device_reset(struct intel_engine_cs *engine)
+{
+	i915_reset(engine->i915, ENGINE_MASK(engine->id), NULL);
+	return 0;
+}
+
+static int do_engine_reset(struct intel_engine_cs *engine)
+{
+	return i915_reset_engine(engine, NULL);
+}
+
+static int switch_to_scratch_context(struct intel_engine_cs *engine)
+{
+	struct i915_gem_context *ctx;
+	struct i915_request *rq;
+
+	ctx = kernel_context(engine->i915);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	rq = i915_request_alloc(engine, ctx);
+	kernel_context_close(ctx);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_add(rq);
+
+	return 0;
+}
+
+static int check_whitelist_across_reset(struct intel_engine_cs *engine,
+					int (*reset)(struct intel_engine_cs *),
+					const struct whitelist *w,
+					const char *name)
+{
+	struct i915_gem_context *ctx;
+	int err;
+
+	ctx = kernel_context(engine->i915);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	err = check_whitelist(w, ctx, engine);
+	if (err) {
+		pr_err("Invalid whitelist *before* %s reset!\n", name);
+		goto out;
+	}
+
+	err = switch_to_scratch_context(engine);
+	if (err)
+		goto out;
+
+	err = reset(engine);
+	if (err) {
+		pr_err("%s reset failed\n", name);
+		goto out;
+	}
+
+	err = check_whitelist(w, ctx, engine);
+	if (err) {
+		pr_err("Whitelist not preserved in context across %s reset!\n",
+		       name);
+		goto out;
+	}
+
+	kernel_context_close(ctx);
+
+	ctx = kernel_context(engine->i915);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	err = check_whitelist(w, ctx, engine);
+	if (err) {
+		pr_err("Invalid whitelist *after* %s reset in fresh context!\n",
+		       name);
+		goto out;
+	}
+
+out:
+	kernel_context_close(ctx);
+	return err;
+}
+
+static int live_reset_whitelist(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *engine = i915->engine[RCS];
+	struct i915_gpu_error *error = &i915->gpu_error;
+	struct whitelist w;
+	int err = 0;
+
+	/* If we reset the gpu, we should not lose the RING_NONPRIV */
+
+	if (!engine)
+		return 0;
+
+	if (!whitelist_build(engine, &w))
+		return 0;
+
+	pr_info("Checking %d whitelisted registers (RING_NONPRIV)\n", w.count);
+
+	set_bit(I915_RESET_BACKOFF, &error->flags);
+	set_bit(I915_RESET_ENGINE + engine->id, &error->flags);
+
+	if (intel_has_reset_engine(i915)) {
+		err = check_whitelist_across_reset(engine,
+						   do_engine_reset, &w,
+						   "engine");
+		if (err)
+			goto out;
+	}
+
+	if (intel_has_gpu_reset(i915)) {
+		err = check_whitelist_across_reset(engine,
+						   do_device_reset, &w,
+						   "device");
+		if (err)
+			goto out;
+	}
+
+out:
+	clear_bit(I915_RESET_ENGINE + engine->id, &error->flags);
+	clear_bit(I915_RESET_BACKOFF, &error->flags);
+	return err;
+}
+
+int intel_workarounds_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_reset_whitelist),
+	};
+	int err;
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = i915_subtests(tests, i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index 78a89efa1119..26bf29d97007 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -25,6 +25,11 @@
 #include "mock_engine.h"
 #include "mock_request.h"
 
+struct mock_ring {
+	struct intel_ring base;
+	struct i915_timeline timeline;
+};
+
 static struct mock_request *first_request(struct mock_engine *engine)
 {
 	return list_first_entry_or_null(&engine->hw_queue,
@@ -71,14 +76,21 @@ static struct intel_ring *
 mock_context_pin(struct intel_engine_cs *engine,
 		 struct i915_gem_context *ctx)
 {
-	i915_gem_context_get(ctx);
+	struct intel_context *ce = to_intel_context(ctx, engine);
+
+	if (!ce->pin_count++)
+		i915_gem_context_get(ctx);
+
 	return engine->buffer;
 }
 
 static void mock_context_unpin(struct intel_engine_cs *engine,
 			       struct i915_gem_context *ctx)
 {
-	i915_gem_context_put(ctx);
+	struct intel_context *ce = to_intel_context(ctx, engine);
+
+	if (!--ce->pin_count)
+		i915_gem_context_put(ctx);
 }
 
 static int mock_request_alloc(struct i915_request *request)
@@ -125,7 +137,7 @@ static void mock_submit_request(struct i915_request *request)
 static struct intel_ring *mock_ring(struct intel_engine_cs *engine)
 {
 	const unsigned long sz = PAGE_SIZE / 2;
-	struct intel_ring *ring;
+	struct mock_ring *ring;
 
 	BUILD_BUG_ON(MIN_SPACE_FOR_ADD_REQUEST > sz);
 
@@ -133,14 +145,25 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine)
 	if (!ring)
 		return NULL;
 
-	ring->size = sz;
-	ring->effective_size = sz;
-	ring->vaddr = (void *)(ring + 1);
+	i915_timeline_init(engine->i915, &ring->timeline, engine->name);
+
+	ring->base.size = sz;
+	ring->base.effective_size = sz;
+	ring->base.vaddr = (void *)(ring + 1);
+	ring->base.timeline = &ring->timeline;
 
-	INIT_LIST_HEAD(&ring->request_list);
-	intel_ring_update_space(ring);
+	INIT_LIST_HEAD(&ring->base.request_list);
+	intel_ring_update_space(&ring->base);
 
-	return ring;
+	return &ring->base;
+}
+
+static void mock_ring_free(struct intel_ring *base)
+{
+	struct mock_ring *ring = container_of(base, typeof(*ring), base);
+
+	i915_timeline_fini(&ring->timeline);
+	kfree(ring);
 }
 
 struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
@@ -155,12 +178,6 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	if (!engine)
 		return NULL;
 
-	engine->base.buffer = mock_ring(&engine->base);
-	if (!engine->base.buffer) {
-		kfree(engine);
-		return NULL;
-	}
-
 	/* minimal engine setup for requests */
 	engine->base.i915 = i915;
 	snprintf(engine->base.name, sizeof(engine->base.name), "%s", name);
@@ -174,9 +191,7 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.emit_breadcrumb = mock_emit_breadcrumb;
 	engine->base.submit_request = mock_submit_request;
 
-	engine->base.timeline =
-		&i915->gt.global_timeline.engine[engine->base.id];
-
+	i915_timeline_init(i915, &engine->base.timeline, engine->base.name);
 	intel_engine_init_breadcrumbs(&engine->base);
 	engine->base.breadcrumbs.mock = true; /* prevent touching HW for irqs */
 
@@ -185,7 +200,17 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	timer_setup(&engine->hw_delay, hw_delay_complete, 0);
 	INIT_LIST_HEAD(&engine->hw_queue);
 
+	engine->base.buffer = mock_ring(&engine->base);
+	if (!engine->base.buffer)
+		goto err_breadcrumbs;
+
 	return &engine->base;
+
+err_breadcrumbs:
+	intel_engine_fini_breadcrumbs(&engine->base);
+	i915_timeline_fini(&engine->base.timeline);
+	kfree(engine);
+	return NULL;
 }
 
 void mock_engine_flush(struct intel_engine_cs *engine)
@@ -217,10 +242,12 @@ void mock_engine_free(struct intel_engine_cs *engine)
 	GEM_BUG_ON(timer_pending(&mock->hw_delay));
 
 	if (engine->last_retired_context)
-		engine->context_unpin(engine, engine->last_retired_context);
+		intel_context_unpin(engine->last_retired_context, engine);
+
+	mock_ring_free(engine->buffer);
 
 	intel_engine_fini_breadcrumbs(engine);
+	i915_timeline_fini(&engine->timeline);
 
-	kfree(engine->buffer);
 	kfree(engine);
 }
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index e6d4b882599a..94baedfa0f74 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -44,6 +44,7 @@ void mock_device_flush(struct drm_i915_private *i915)
 		mock_engine_flush(engine);
 
 	i915_retire_requests(i915);
+	GEM_BUG_ON(i915->gt.active_requests);
 }
 
 static void mock_device_release(struct drm_device *dev)
@@ -72,8 +73,8 @@ static void mock_device_release(struct drm_device *dev)
 
 	mutex_lock(&i915->drm.struct_mutex);
 	mock_fini_ggtt(i915);
-	i915_gem_timeline_fini(&i915->gt.global_timeline);
 	mutex_unlock(&i915->drm.struct_mutex);
+	WARN_ON(!list_empty(&i915->gt.timelines));
 
 	destroy_workqueue(i915->wq);
 
@@ -223,26 +224,25 @@ struct drm_i915_private *mock_gem_device(void)
 	if (!i915->priorities)
 		goto err_dependencies;
 
-	mutex_lock(&i915->drm.struct_mutex);
 	INIT_LIST_HEAD(&i915->gt.timelines);
-	err = i915_gem_timeline_init__global(i915);
-	if (err) {
-		mutex_unlock(&i915->drm.struct_mutex);
-		goto err_priorities;
-	}
+	INIT_LIST_HEAD(&i915->gt.active_rings);
+	INIT_LIST_HEAD(&i915->gt.closed_vma);
+
+	mutex_lock(&i915->drm.struct_mutex);
 
 	mock_init_ggtt(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	mkwrite_device_info(i915)->ring_mask = BIT(0);
 	i915->engine[RCS] = mock_engine(i915, "mock", RCS);
 	if (!i915->engine[RCS])
-		goto err_priorities;
+		goto err_unlock;
 
 	i915->kernel_context = mock_context(i915, NULL);
 	if (!i915->kernel_context)
 		goto err_engine;
 
+	mutex_unlock(&i915->drm.struct_mutex);
+
 	WARN_ON(i915_gemfs_init(i915));
 
 	return i915;
@@ -250,7 +250,8 @@ struct drm_i915_private *mock_gem_device(void)
 err_engine:
 	for_each_engine(engine, i915, id)
 		mock_engine_free(engine);
-err_priorities:
+err_unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
 	kmem_cache_destroy(i915->priorities);
 err_dependencies:
 	kmem_cache_destroy(i915->dependencies);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index e96873f96116..36c112088940 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -76,7 +76,6 @@ mock_ppgtt(struct drm_i915_private *i915,
 
 	INIT_LIST_HEAD(&ppgtt->base.global_link);
 	drm_mm_init(&ppgtt->base.mm, 0, ppgtt->base.total);
-	i915_gem_timeline_init(i915, &ppgtt->base.timeline, name);
 
 	ppgtt->base.clear_range = nop_clear_range;
 	ppgtt->base.insert_page = mock_insert_page;
diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.c b/drivers/gpu/drm/i915/selftests/mock_timeline.c
index 47b1f47c5812..dcf3b16f5a07 100644
--- a/drivers/gpu/drm/i915/selftests/mock_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/mock_timeline.c
@@ -1,45 +1,28 @@
 /*
- * Copyright © 2017 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
+ * SPDX-License-Identifier: MIT
  *
+ * Copyright © 2017-2018 Intel Corporation
  */
 
+#include "../i915_timeline.h"
+
 #include "mock_timeline.h"
 
-struct intel_timeline *mock_timeline(u64 context)
+void mock_timeline_init(struct i915_timeline *timeline, u64 context)
 {
-	static struct lock_class_key class;
-	struct intel_timeline *tl;
+	timeline->fence_context = context;
+
+	spin_lock_init(&timeline->lock);
 
-	tl = kzalloc(sizeof(*tl), GFP_KERNEL);
-	if (!tl)
-		return NULL;
+	init_request_active(&timeline->last_request, NULL);
+	INIT_LIST_HEAD(&timeline->requests);
 
-	__intel_timeline_init(tl, NULL, context, &class, "mock");
+	i915_syncmap_init(&timeline->sync);
 
-	return tl;
+	INIT_LIST_HEAD(&timeline->link);
 }
 
-void mock_timeline_destroy(struct intel_timeline *tl)
+void mock_timeline_fini(struct i915_timeline *timeline)
 {
-	__intel_timeline_fini(tl);
-	kfree(tl);
+	i915_timeline_fini(timeline);
 }
diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.h b/drivers/gpu/drm/i915/selftests/mock_timeline.h
index c27ff4639b8b..b6deaa61110d 100644
--- a/drivers/gpu/drm/i915/selftests/mock_timeline.h
+++ b/drivers/gpu/drm/i915/selftests/mock_timeline.h
@@ -1,33 +1,15 @@
 /*
- * Copyright © 2017 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
+ * SPDX-License-Identifier: MIT
  *
+ * Copyright © 2017-2018 Intel Corporation
  */
 
 #ifndef __MOCK_TIMELINE__
 #define __MOCK_TIMELINE__
 
-#include "../i915_gem_timeline.h"
+struct i915_timeline;
 
-struct intel_timeline *mock_timeline(u64 context);
-void mock_timeline_destroy(struct intel_timeline *tl);
+void mock_timeline_init(struct i915_timeline *timeline, u64 context);
+void mock_timeline_fini(struct i915_timeline *timeline);
 
 #endif /* !__MOCK_TIMELINE__ */
diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig
index 294de4549922..119ec0a21de2 100644
--- a/drivers/gpu/drm/mediatek/Kconfig
+++ b/drivers/gpu/drm/mediatek/Kconfig
@@ -11,6 +11,7 @@ config DRM_MEDIATEK
 	select DRM_PANEL
 	select MEMORY
 	select MTK_SMI
+	select VIDEOMODE_HELPERS
 	help
 	  Choose this option if you have a Mediatek SoCs.
 	  The module will be called mediatek-drm
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index e80a603e5fb0..6c0ea39d5739 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/clk.h>
+#include <video/videomode.h>
 
 #include "mtk_dpi_regs.h"
 #include "mtk_drm_ddp_comp.h"
@@ -429,34 +430,35 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi,
 	struct mtk_dpi_sync_param vsync_leven = { 0 };
 	struct mtk_dpi_sync_param vsync_rodd = { 0 };
 	struct mtk_dpi_sync_param vsync_reven = { 0 };
-	unsigned long pix_rate;
+	struct videomode vm = { 0 };
 	unsigned long pll_rate;
 	unsigned int factor;
 
 	/* let pll_rate can fix the valid range of tvdpll (1G~2GHz) */
-	pix_rate = 1000UL * mode->clock;
+
 	if (mode->clock <= 27000)
-		factor = 16 * 3;
+		factor = 3 << 4;
 	else if (mode->clock <= 84000)
-		factor = 8 * 3;
+		factor = 3 << 3;
 	else if (mode->clock <= 167000)
-		factor = 4 * 3;
+		factor = 3 << 2;
 	else
-		factor = 2 * 3;
-	pll_rate = pix_rate * factor;
+		factor = 3 << 1;
+	drm_display_mode_to_videomode(mode, &vm);
+	pll_rate = vm.pixelclock * factor;
 
 	dev_dbg(dpi->dev, "Want PLL %lu Hz, pixel clock %lu Hz\n",
-		pll_rate, pix_rate);
+		pll_rate, vm.pixelclock);
 
 	clk_set_rate(dpi->tvd_clk, pll_rate);
 	pll_rate = clk_get_rate(dpi->tvd_clk);
 
-	pix_rate = pll_rate / factor;
-	clk_set_rate(dpi->pixel_clk, pix_rate);
-	pix_rate = clk_get_rate(dpi->pixel_clk);
+	vm.pixelclock = pll_rate / factor;
+	clk_set_rate(dpi->pixel_clk, vm.pixelclock);
+	vm.pixelclock = clk_get_rate(dpi->pixel_clk);
 
 	dev_dbg(dpi->dev, "Got  PLL %lu Hz, pixel clock %lu Hz\n",
-		pll_rate, pix_rate);
+		pll_rate, vm.pixelclock);
 
 	limit.c_bottom = 0x0010;
 	limit.c_top = 0x0FE0;
@@ -465,33 +467,31 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi,
 
 	dpi_pol.ck_pol = MTK_DPI_POLARITY_FALLING;
 	dpi_pol.de_pol = MTK_DPI_POLARITY_RISING;
-	dpi_pol.hsync_pol = mode->flags & DRM_MODE_FLAG_PHSYNC ?
+	dpi_pol.hsync_pol = vm.flags & DISPLAY_FLAGS_HSYNC_HIGH ?
 			    MTK_DPI_POLARITY_FALLING : MTK_DPI_POLARITY_RISING;
-	dpi_pol.vsync_pol = mode->flags & DRM_MODE_FLAG_PVSYNC ?
+	dpi_pol.vsync_pol = vm.flags & DISPLAY_FLAGS_VSYNC_HIGH ?
 			    MTK_DPI_POLARITY_FALLING : MTK_DPI_POLARITY_RISING;
-
-	hsync.sync_width = mode->hsync_end - mode->hsync_start;
-	hsync.back_porch = mode->htotal - mode->hsync_end;
-	hsync.front_porch = mode->hsync_start - mode->hdisplay;
+	hsync.sync_width = vm.hsync_len;
+	hsync.back_porch = vm.hback_porch;
+	hsync.front_porch = vm.hfront_porch;
 	hsync.shift_half_line = false;
-
-	vsync_lodd.sync_width = mode->vsync_end - mode->vsync_start;
-	vsync_lodd.back_porch = mode->vtotal - mode->vsync_end;
-	vsync_lodd.front_porch = mode->vsync_start - mode->vdisplay;
+	vsync_lodd.sync_width = vm.vsync_len;
+	vsync_lodd.back_porch = vm.vback_porch;
+	vsync_lodd.front_porch = vm.vfront_porch;
 	vsync_lodd.shift_half_line = false;
 
-	if (mode->flags & DRM_MODE_FLAG_INTERLACE &&
+	if (vm.flags & DISPLAY_FLAGS_INTERLACED &&
 	    mode->flags & DRM_MODE_FLAG_3D_MASK) {
 		vsync_leven = vsync_lodd;
 		vsync_rodd = vsync_lodd;
 		vsync_reven = vsync_lodd;
 		vsync_leven.shift_half_line = true;
 		vsync_reven.shift_half_line = true;
-	} else if (mode->flags & DRM_MODE_FLAG_INTERLACE &&
+	} else if (vm.flags & DISPLAY_FLAGS_INTERLACED &&
 		   !(mode->flags & DRM_MODE_FLAG_3D_MASK)) {
 		vsync_leven = vsync_lodd;
 		vsync_leven.shift_half_line = true;
-	} else if (!(mode->flags & DRM_MODE_FLAG_INTERLACE) &&
+	} else if (!(vm.flags & DISPLAY_FLAGS_INTERLACED) &&
 		   mode->flags & DRM_MODE_FLAG_3D_MASK) {
 		vsync_rodd = vsync_lodd;
 	}
@@ -505,12 +505,12 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi,
 	mtk_dpi_config_vsync_reven(dpi, &vsync_reven);
 
 	mtk_dpi_config_3d(dpi, !!(mode->flags & DRM_MODE_FLAG_3D_MASK));
-	mtk_dpi_config_interface(dpi, !!(mode->flags &
-					 DRM_MODE_FLAG_INTERLACE));
-	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
-		mtk_dpi_config_fb_size(dpi, mode->hdisplay, mode->vdisplay / 2);
+	mtk_dpi_config_interface(dpi, !!(vm.flags &
+					 DISPLAY_FLAGS_INTERLACED));
+	if (vm.flags & DISPLAY_FLAGS_INTERLACED)
+		mtk_dpi_config_fb_size(dpi, vm.hactive, vm.vactive >> 1);
 	else
-		mtk_dpi_config_fb_size(dpi, mode->hdisplay, mode->vdisplay);
+		mtk_dpi_config_fb_size(dpi, vm.hactive, vm.vactive);
 
 	mtk_dpi_config_channel_limit(dpi, &limit);
 	mtk_dpi_config_bit_num(dpi, dpi->bit_num);
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c
index f595ac816b55..259b7b0de1d2 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c
@@ -220,7 +220,7 @@ struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev,
 	mtk_gem = mtk_drm_gem_init(dev, attach->dmabuf->size);
 
 	if (IS_ERR(mtk_gem))
-		return ERR_PTR(PTR_ERR(mtk_gem));
+		return ERR_CAST(mtk_gem);
 
 	expected = sg_dma_address(sg->sgl);
 	for_each_sg(sg->sgl, s, sg->nents, i) {
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 7e5e24c2152a..aa0943ec32b0 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -551,13 +551,12 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi)
 	}
 
 	/**
-	 * vm.pixelclock is in kHz, pixel_clock unit is Hz, so multiply by 1000
 	 * htotal_time = htotal * byte_per_pixel / num_lanes
 	 * overhead_time = lpx + hs_prepare + hs_zero + hs_trail + hs_exit
 	 * mipi_ratio = (htotal_time + overhead_time) / htotal_time
 	 * data_rate = pixel_clock * bit_per_pixel * mipi_ratio / num_lanes;
 	 */
-	pixel_clock = dsi->vm.pixelclock * 1000;
+	pixel_clock = dsi->vm.pixelclock;
 	htotal = dsi->vm.hactive + dsi->vm.hback_porch + dsi->vm.hfront_porch +
 			dsi->vm.hsync_len;
 	htotal_bits = htotal * bit_per_pixel;
@@ -725,16 +724,7 @@ static void mtk_dsi_encoder_mode_set(struct drm_encoder *encoder,
 {
 	struct mtk_dsi *dsi = encoder_to_dsi(encoder);
 
-	dsi->vm.pixelclock = adjusted->clock;
-	dsi->vm.hactive = adjusted->hdisplay;
-	dsi->vm.hback_porch = adjusted->htotal - adjusted->hsync_end;
-	dsi->vm.hfront_porch = adjusted->hsync_start - adjusted->hdisplay;
-	dsi->vm.hsync_len = adjusted->hsync_end - adjusted->hsync_start;
-
-	dsi->vm.vactive = adjusted->vdisplay;
-	dsi->vm.vback_porch = adjusted->vtotal - adjusted->vsync_end;
-	dsi->vm.vfront_porch = adjusted->vsync_start - adjusted->vdisplay;
-	dsi->vm.vsync_len = adjusted->vsync_end - adjusted->vsync_start;
+	drm_display_mode_to_videomode(adjusted, &dsi->vm);
 }
 
 static void mtk_dsi_encoder_disable(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c
index a393095aac1a..c9ad45686e7a 100644
--- a/drivers/gpu/drm/meson/meson_dw_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c
@@ -529,7 +529,7 @@ static irqreturn_t dw_hdmi_top_thread_irq(int irq, void *dev_id)
 		if (stat & HDMITX_TOP_INTR_HPD_RISE)
 			hpd_connected = true;
 
-		dw_hdmi_setup_rx_sense(dw_hdmi->dev, hpd_connected,
+		dw_hdmi_setup_rx_sense(dw_hdmi->hdmi, hpd_connected,
 				       hpd_connected);
 
 		drm_helper_hpd_irq_event(dw_hdmi->encoder.dev);
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index fb50a9ddaae8..8918539a19aa 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1586,7 +1586,7 @@ static uint32_t mga_vga_calculate_mode_bandwidth(struct drm_display_mode *mode,
 
 #define MODE_BANDWIDTH	MODE_BAD
 
-static int mga_vga_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status mga_vga_mode_valid(struct drm_connector *connector,
 				 struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 8e0cb161754b..0ae5ace65462 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -168,7 +168,6 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 	if (gpu->funcs->debugfs_init) {
 		gpu->funcs->debugfs_init(gpu, dev->primary);
 		gpu->funcs->debugfs_init(gpu, dev->render);
-		gpu->funcs->debugfs_init(gpu, dev->control);
 	}
 #endif
 
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
index 6e5e1aa54ce1..b001699297c4 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
@@ -351,6 +351,7 @@ static void mdp4_crtc_atomic_flush(struct drm_crtc *crtc,
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	mdp4_crtc->event = crtc->state->event;
+	crtc->state->event = NULL;
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
 	blend_setup(crtc);
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 9893e43ba6c5..76b96081916f 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -708,6 +708,7 @@ static void mdp5_crtc_atomic_flush(struct drm_crtc *crtc,
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	mdp5_crtc->event = crtc->state->event;
+	crtc->state->event = NULL;
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
 	/*
diff --git a/drivers/gpu/drm/msm/disp/mdp_format.c b/drivers/gpu/drm/msm/disp/mdp_format.c
index b4a8aa4490ee..005760bee708 100644
--- a/drivers/gpu/drm/msm/disp/mdp_format.c
+++ b/drivers/gpu/drm/msm/disp/mdp_format.c
@@ -171,7 +171,8 @@ uint32_t mdp_get_formats(uint32_t *pixel_formats, uint32_t max_formats,
 	return i;
 }
 
-const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format)
+const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format,
+		uint64_t modifier)
 {
 	int i;
 	for (i = 0; i < ARRAY_SIZE(formats); i++) {
diff --git a/drivers/gpu/drm/msm/disp/mdp_kms.h b/drivers/gpu/drm/msm/disp/mdp_kms.h
index 1185487e7e5e..4fa8dbe4e165 100644
--- a/drivers/gpu/drm/msm/disp/mdp_kms.h
+++ b/drivers/gpu/drm/msm/disp/mdp_kms.h
@@ -98,7 +98,7 @@ struct mdp_format {
 #define MDP_FORMAT_IS_YUV(mdp_format) ((mdp_format)->is_yuv)
 
 uint32_t mdp_get_formats(uint32_t *formats, uint32_t max_formats, bool rgb_only);
-const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format);
+const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier);
 
 /* MDP capabilities */
 #define MDP_CAP_SMP		BIT(0)	/* Shared Memory Pool                 */
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 7a03a9489708..8baba30d6c65 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -173,6 +173,7 @@ struct msm_dsi_host {
 
 	bool registered;
 	bool power_on;
+	bool enabled;
 	int irq;
 };
 
@@ -775,7 +776,7 @@ static inline enum dsi_cmd_dst_format dsi_get_cmd_fmt(
 	switch (mipi_fmt) {
 	case MIPI_DSI_FMT_RGB888:	return CMD_DST_FORMAT_RGB888;
 	case MIPI_DSI_FMT_RGB666_PACKED:
-	case MIPI_DSI_FMT_RGB666:	return VID_DST_FORMAT_RGB666;
+	case MIPI_DSI_FMT_RGB666:	return CMD_DST_FORMAT_RGB666;
 	case MIPI_DSI_FMT_RGB565:	return CMD_DST_FORMAT_RGB565;
 	default:			return CMD_DST_FORMAT_RGB888;
 	}
@@ -986,13 +987,19 @@ static void dsi_set_tx_power_mode(int mode, struct msm_dsi_host *msm_host)
 
 static void dsi_wait4video_done(struct msm_dsi_host *msm_host)
 {
+	u32 ret = 0;
+	struct device *dev = &msm_host->pdev->dev;
+
 	dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 1);
 
 	reinit_completion(&msm_host->video_comp);
 
-	wait_for_completion_timeout(&msm_host->video_comp,
+	ret = wait_for_completion_timeout(&msm_host->video_comp,
 			msecs_to_jiffies(70));
 
+	if (ret <= 0)
+		dev_err(dev, "wait for video done timed out\n");
+
 	dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 0);
 }
 
@@ -1001,7 +1008,7 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host)
 	if (!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO))
 		return;
 
-	if (msm_host->power_on) {
+	if (msm_host->power_on && msm_host->enabled) {
 		dsi_wait4video_done(msm_host);
 		/* delay 4 ms to skip BLLP */
 		usleep_range(2000, 4000);
@@ -2203,7 +2210,7 @@ int msm_dsi_host_enable(struct mipi_dsi_host *host)
 	 *	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 	 * }
 	 */
-
+	msm_host->enabled = true;
 	return 0;
 }
 
@@ -2211,6 +2218,7 @@ int msm_dsi_host_disable(struct mipi_dsi_host *host)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
 
+	msm_host->enabled = false;
 	dsi_op_mode_config(msm_host,
 		!!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO), false);
 
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 8e9d5c255820..9a9fa0c75a13 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -265,6 +265,115 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
 	return 0;
 }
 
+int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
+	struct msm_dsi_phy_clk_request *clk_req)
+{
+	const unsigned long bit_rate = clk_req->bitclk_rate;
+	const unsigned long esc_rate = clk_req->escclk_rate;
+	s32 ui, ui_x8, lpx;
+	s32 tmax, tmin;
+	s32 pcnt0 = 50;
+	s32 pcnt1 = 50;
+	s32 pcnt2 = 10;
+	s32 pcnt3 = 30;
+	s32 pcnt4 = 10;
+	s32 pcnt5 = 2;
+	s32 coeff = 1000; /* Precision, should avoid overflow */
+	s32 hb_en, hb_en_ckln;
+	s32 temp;
+
+	if (!bit_rate || !esc_rate)
+		return -EINVAL;
+
+	timing->hs_halfbyte_en = 0;
+	hb_en = 0;
+	timing->hs_halfbyte_en_ckln = 0;
+	hb_en_ckln = 0;
+
+	ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
+	ui_x8 = ui << 3;
+	lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
+
+	temp = S_DIV_ROUND_UP(38 * coeff, ui_x8);
+	tmin = max_t(s32, temp, 0);
+	temp = (95 * coeff) / ui_x8;
+	tmax = max_t(s32, temp, 0);
+	timing->clk_prepare = linear_inter(tmax, tmin, pcnt0, 0, false);
+
+	temp = 300 * coeff - (timing->clk_prepare << 3) * ui;
+	tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+	tmax = (tmin > 255) ? 511 : 255;
+	timing->clk_zero = linear_inter(tmax, tmin, pcnt5, 0, false);
+
+	tmin = DIV_ROUND_UP(60 * coeff + 3 * ui, ui_x8);
+	temp = 105 * coeff + 12 * ui - 20 * coeff;
+	tmax = (temp + 3 * ui) / ui_x8;
+	timing->clk_trail = linear_inter(tmax, tmin, pcnt3, 0, false);
+
+	temp = S_DIV_ROUND_UP(40 * coeff + 4 * ui, ui_x8);
+	tmin = max_t(s32, temp, 0);
+	temp = (85 * coeff + 6 * ui) / ui_x8;
+	tmax = max_t(s32, temp, 0);
+	timing->hs_prepare = linear_inter(tmax, tmin, pcnt1, 0, false);
+
+	temp = 145 * coeff + 10 * ui - (timing->hs_prepare << 3) * ui;
+	tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+	tmax = 255;
+	timing->hs_zero = linear_inter(tmax, tmin, pcnt4, 0, false);
+
+	tmin = DIV_ROUND_UP(60 * coeff + 4 * ui, ui_x8) - 1;
+	temp = 105 * coeff + 12 * ui - 20 * coeff;
+	tmax = (temp / ui_x8) - 1;
+	timing->hs_trail = linear_inter(tmax, tmin, pcnt3, 0, false);
+
+	temp = 50 * coeff + ((hb_en << 2) - 8) * ui;
+	timing->hs_rqst = S_DIV_ROUND_UP(temp, ui_x8);
+
+	tmin = DIV_ROUND_UP(100 * coeff, ui_x8) - 1;
+	tmax = 255;
+	timing->hs_exit = linear_inter(tmax, tmin, pcnt2, 0, false);
+
+	temp = 50 * coeff + ((hb_en_ckln << 2) - 8) * ui;
+	timing->hs_rqst_ckln = S_DIV_ROUND_UP(temp, ui_x8);
+
+	temp = 60 * coeff + 52 * ui - 43 * ui;
+	tmin = DIV_ROUND_UP(temp, ui_x8) - 1;
+	tmax = 63;
+	timing->shared_timings.clk_post =
+		linear_inter(tmax, tmin, pcnt2, 0, false);
+
+	temp = 8 * ui + (timing->clk_prepare << 3) * ui;
+	temp += (((timing->clk_zero + 3) << 3) + 11) * ui;
+	temp += hb_en_ckln ? (((timing->hs_rqst_ckln << 3) + 4) * ui) :
+		(((timing->hs_rqst_ckln << 3) + 8) * ui);
+	tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+	tmax = 63;
+	if (tmin > tmax) {
+		temp = linear_inter(tmax << 1, tmin, pcnt2, 0, false);
+		timing->shared_timings.clk_pre = temp >> 1;
+		timing->shared_timings.clk_pre_inc_by_2 = 1;
+	} else {
+		timing->shared_timings.clk_pre =
+			linear_inter(tmax, tmin, pcnt2, 0, false);
+			timing->shared_timings.clk_pre_inc_by_2 = 0;
+	}
+
+	timing->ta_go = 3;
+	timing->ta_sure = 0;
+	timing->ta_get = 4;
+
+	DBG("%d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d",
+		timing->shared_timings.clk_pre, timing->shared_timings.clk_post,
+		timing->shared_timings.clk_pre_inc_by_2, timing->clk_zero,
+		timing->clk_trail, timing->clk_prepare, timing->hs_exit,
+		timing->hs_zero, timing->hs_prepare, timing->hs_trail,
+		timing->hs_rqst, timing->hs_rqst_ckln, timing->hs_halfbyte_en,
+		timing->hs_halfbyte_en_ckln, timing->hs_prep_dly,
+		timing->hs_prep_dly_ckln);
+
+	return 0;
+}
+
 void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg,
 				u32 bit_mask)
 {
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index c56268cbdb3d..a24ab80994a3 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -101,6 +101,8 @@ int msm_dsi_dphy_timing_calc(struct msm_dsi_dphy_timing *timing,
 			     struct msm_dsi_phy_clk_request *clk_req);
 int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
 				struct msm_dsi_phy_clk_request *clk_req);
+int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
+				struct msm_dsi_phy_clk_request *clk_req);
 void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg,
 				u32 bit_mask);
 int msm_dsi_phy_init_common(struct msm_dsi_phy *phy);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
index 0af951aaeea1..b3fffc8dbb2a 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
@@ -79,34 +79,6 @@ static void dsi_phy_hw_v3_0_lane_settings(struct msm_dsi_phy *phy)
 	dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_TX_DCTRL(3), 0x04);
 }
 
-static int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
-				       struct msm_dsi_phy_clk_request *clk_req)
-{
-	/*
-	 * TODO: These params need to be computed, they're currently hardcoded
-	 * for a 1440x2560@60Hz panel with a byteclk of 100.618 Mhz, and a
-	 * default escape clock of 19.2 Mhz.
-	 */
-
-	timing->hs_halfbyte_en = 0;
-	timing->clk_zero = 0x1c;
-	timing->clk_prepare = 0x07;
-	timing->clk_trail = 0x07;
-	timing->hs_exit = 0x23;
-	timing->hs_zero = 0x21;
-	timing->hs_prepare = 0x07;
-	timing->hs_trail = 0x07;
-	timing->hs_rqst = 0x05;
-	timing->ta_sure = 0x00;
-	timing->ta_go = 0x03;
-	timing->ta_get = 0x04;
-
-	timing->shared_timings.clk_pre = 0x2d;
-	timing->shared_timings.clk_post = 0x0d;
-
-	return 0;
-}
-
 static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 			       struct msm_dsi_phy_clk_request *clk_req)
 {
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index ba74cb4f94df..1ff3fda245d1 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -140,9 +140,6 @@ int msm_debugfs_late_init(struct drm_device *dev)
 	if (ret)
 		return ret;
 	ret = late_init_minor(dev->render);
-	if (ret)
-		return ret;
-	ret = late_init_minor(dev->control);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index 0e0c87252ab0..7a16242bf8bf 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -183,7 +183,8 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 	hsub = drm_format_horz_chroma_subsampling(mode_cmd->pixel_format);
 	vsub = drm_format_vert_chroma_subsampling(mode_cmd->pixel_format);
 
-	format = kms->funcs->get_format(kms, mode_cmd->pixel_format);
+	format = kms->funcs->get_format(kms, mode_cmd->pixel_format,
+			mode_cmd->modifier[0]);
 	if (!format) {
 		dev_err(dev->dev, "unsupported pixel format: %4.4s\n",
 				(char *)&mode_cmd->pixel_format);
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index c178563fcd4d..456622b46335 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -92,8 +92,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 
 	if (IS_ERR(fb)) {
 		dev_err(dev->dev, "failed to allocate fb\n");
-		ret = PTR_ERR(fb);
-		goto fail;
+		return PTR_ERR(fb);
 	}
 
 	bo = msm_framebuffer_bo(fb, 0);
@@ -151,13 +150,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 
 fail_unlock:
 	mutex_unlock(&dev->struct_mutex);
-fail:
-
-	if (ret) {
-		if (fb)
-			drm_framebuffer_remove(fb);
-	}
-
+	drm_framebuffer_remove(fb);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 95196479f651..f583bb4222f9 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -132,17 +132,19 @@ static void put_pages(struct drm_gem_object *obj)
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
 	if (msm_obj->pages) {
-		/* For non-cached buffers, ensure the new pages are clean
-		 * because display controller, GPU, etc. are not coherent:
-		 */
-		if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
-			dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
-					msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+		if (msm_obj->sgt) {
+			/* For non-cached buffers, ensure the new
+			 * pages are clean because display controller,
+			 * GPU, etc. are not coherent:
+			 */
+			if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
+				dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
+					     msm_obj->sgt->nents,
+					     DMA_BIDIRECTIONAL);
 
-		if (msm_obj->sgt)
 			sg_free_table(msm_obj->sgt);
-
-		kfree(msm_obj->sgt);
+			kfree(msm_obj->sgt);
+		}
 
 		if (use_pages(obj))
 			drm_gem_put_pages(obj, msm_obj->pages, true, false);
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 17d5824417ad..aaa329dc020e 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -48,8 +48,11 @@ struct msm_kms_funcs {
 	/* functions to wait for atomic commit completed on each CRTC */
 	void (*wait_for_crtc_commit_done)(struct msm_kms *kms,
 					struct drm_crtc *crtc);
+	/* get msm_format w/ optional format modifiers from drm_mode_fb_cmd2 */
+	const struct msm_format *(*get_format)(struct msm_kms *kms,
+					const uint32_t format,
+					const uint64_t modifiers);
 	/* misc: */
-	const struct msm_format *(*get_format)(struct msm_kms *kms, uint32_t format);
 	long (*round_pixclk)(struct msm_kms *kms, unsigned long rate,
 			struct drm_encoder *encoder);
 	int (*set_split_display)(struct msm_kms *kms,
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
index 5cae8db9dcd4..ffe5137ccaf8 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
@@ -99,7 +99,8 @@ static const struct drm_mode_config_funcs mxsfb_mode_config_funcs = {
 };
 
 static void mxsfb_pipe_enable(struct drm_simple_display_pipe *pipe,
-			      struct drm_crtc_state *crtc_state)
+			      struct drm_crtc_state *crtc_state,
+			      struct drm_plane_state *plane_state)
 {
 	struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe);
 
@@ -125,12 +126,6 @@ static void mxsfb_pipe_update(struct drm_simple_display_pipe *pipe,
 	mxsfb_plane_atomic_update(mxsfb, plane_state);
 }
 
-static int mxsfb_pipe_prepare_fb(struct drm_simple_display_pipe *pipe,
-				 struct drm_plane_state *plane_state)
-{
-	return drm_gem_fb_prepare_fb(&pipe->plane, plane_state);
-}
-
 static int mxsfb_pipe_enable_vblank(struct drm_simple_display_pipe *pipe)
 {
 	struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe);
@@ -159,7 +154,7 @@ static struct drm_simple_display_pipe_funcs mxsfb_funcs = {
 	.enable		= mxsfb_pipe_enable,
 	.disable	= mxsfb_pipe_disable,
 	.update		= mxsfb_pipe_update,
-	.prepare_fb	= mxsfb_pipe_prepare_fb,
+	.prepare_fb	= drm_gem_fb_simple_display_pipe_prepare_fb,
 	.enable_vblank	= mxsfb_pipe_enable_vblank,
 	.disable_vblank	= mxsfb_pipe_disable_vblank,
 };
diff --git a/drivers/gpu/drm/nouveau/Kbuild b/drivers/gpu/drm/nouveau/Kbuild
index 9c0c650655e9..b17843dd050d 100644
--- a/drivers/gpu/drm/nouveau/Kbuild
+++ b/drivers/gpu/drm/nouveau/Kbuild
@@ -38,14 +38,16 @@ nouveau-y += nouveau_vmm.o
 
 # DRM - modesetting
 nouveau-$(CONFIG_DRM_NOUVEAU_BACKLIGHT) += nouveau_backlight.o
+nouveau-y += nouveau_bios.o
 nouveau-y += nouveau_connector.o
 nouveau-y += nouveau_display.o
-nouveau-y += nv50_display.o
 nouveau-y += nouveau_dp.o
 nouveau-y += nouveau_fbcon.o
 nouveau-y += nv04_fbcon.o
 nouveau-y += nv50_fbcon.o
 nouveau-y += nvc0_fbcon.o
+include $(src)/dispnv04/Kbuild
+include $(src)/dispnv50/Kbuild
 
 # DRM - command submission
 nouveau-y += nouveau_abi16.o
@@ -59,8 +61,4 @@ nouveau-y += nv50_fence.o
 nouveau-y += nv84_fence.o
 nouveau-y += nvc0_fence.o
 
-# DRM - prehistoric modesetting (NV04-G7x)
-nouveau-y += nouveau_bios.o
-include $(src)/dispnv04/Kbuild
-
 obj-$(CONFIG_DRM_NOUVEAU) += nouveau.o
diff --git a/drivers/gpu/drm/nouveau/dispnv50/Kbuild b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
new file mode 100644
index 000000000000..849b0f45afb8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
@@ -0,0 +1,51 @@
+nouveau-y += dispnv50/disp.o
+nouveau-y += dispnv50/lut.o
+
+nouveau-y += dispnv50/core.o
+nouveau-y += dispnv50/core507d.o
+nouveau-y += dispnv50/core827d.o
+nouveau-y += dispnv50/core907d.o
+nouveau-y += dispnv50/core917d.o
+nouveau-y += dispnv50/corec37d.o
+
+nouveau-y += dispnv50/dac507d.o
+nouveau-y += dispnv50/dac907d.o
+
+nouveau-y += dispnv50/pior507d.o
+
+nouveau-y += dispnv50/sor507d.o
+nouveau-y += dispnv50/sor907d.o
+nouveau-y += dispnv50/sorc37d.o
+
+nouveau-y += dispnv50/head.o
+nouveau-y += dispnv50/head507d.o
+nouveau-y += dispnv50/head827d.o
+nouveau-y += dispnv50/head907d.o
+nouveau-y += dispnv50/head917d.o
+nouveau-y += dispnv50/headc37d.o
+
+nouveau-y += dispnv50/wimm.o
+nouveau-y += dispnv50/wimmc37b.o
+
+nouveau-y += dispnv50/wndw.o
+nouveau-y += dispnv50/wndwc37e.o
+
+nouveau-y += dispnv50/base.o
+nouveau-y += dispnv50/base507c.o
+nouveau-y += dispnv50/base827c.o
+nouveau-y += dispnv50/base907c.o
+nouveau-y += dispnv50/base917c.o
+
+nouveau-y += dispnv50/curs.o
+nouveau-y += dispnv50/curs507a.o
+nouveau-y += dispnv50/curs907a.o
+nouveau-y += dispnv50/cursc37a.o
+
+nouveau-y += dispnv50/oimm.o
+nouveau-y += dispnv50/oimm507b.o
+
+nouveau-y += dispnv50/ovly.o
+nouveau-y += dispnv50/ovly507e.o
+nouveau-y += dispnv50/ovly827e.o
+nouveau-y += dispnv50/ovly907e.o
+nouveau-y += dispnv50/ovly917e.o
diff --git a/drivers/gpu/drm/nouveau/dispnv50/atom.h b/drivers/gpu/drm/nouveau/dispnv50/atom.h
new file mode 100644
index 000000000000..908feb1fc60f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/atom.h
@@ -0,0 +1,222 @@
+#ifndef __NV50_KMS_ATOM_H__
+#define __NV50_KMS_ATOM_H__
+#define nv50_atom(p) container_of((p), struct nv50_atom, state)
+#include <drm/drm_atomic.h>
+
+struct nv50_atom {
+	struct drm_atomic_state state;
+
+	struct list_head outp;
+	bool lock_core;
+	bool flush_disable;
+};
+
+#define nv50_head_atom(p) container_of((p), struct nv50_head_atom, state)
+
+struct nv50_head_atom {
+	struct drm_crtc_state state;
+
+	struct {
+		u32 mask;
+		u32 olut;
+	} wndw;
+
+	struct {
+		u16 iW;
+		u16 iH;
+		u16 oW;
+		u16 oH;
+	} view;
+
+	struct nv50_head_mode {
+		bool interlace;
+		u32 clock;
+		struct {
+			u16 active;
+			u16 synce;
+			u16 blanke;
+			u16 blanks;
+		} h;
+		struct {
+			u32 active;
+			u16 synce;
+			u16 blanke;
+			u16 blanks;
+			u16 blank2s;
+			u16 blank2e;
+			u16 blankus;
+		} v;
+	} mode;
+
+	struct {
+		bool visible;
+		u32 handle;
+		u64 offset:40;
+		u8 buffer:1;
+		u8 mode:4;
+		u8 size:2;
+		u8 range:2;
+		u8 output_mode:2;
+	} olut;
+
+	struct {
+		bool visible;
+		u32 handle;
+		u64 offset:40;
+		u8  format;
+		u8  kind:7;
+		u8  layout:1;
+		u8  blockh:4;
+		u16 blocks:12;
+		u32 pitch:20;
+		u16 x;
+		u16 y;
+		u16 w;
+		u16 h;
+	} core;
+
+	struct {
+		bool visible;
+		u32 handle;
+		u64 offset:40;
+		u8  layout:2;
+		u8  format:8;
+	} curs;
+
+	struct {
+		u8  depth;
+		u8  cpp;
+		u16 x;
+		u16 y;
+		u16 w;
+		u16 h;
+	} base;
+
+	struct {
+		u8 cpp;
+	} ovly;
+
+	struct {
+		bool enable:1;
+		u8 bits:2;
+		u8 mode:4;
+	} dither;
+
+	struct {
+		struct {
+			u16 cos:12;
+			u16 sin:12;
+		} sat;
+	} procamp;
+
+	struct {
+		u8 nhsync:1;
+		u8 nvsync:1;
+		u8 depth:4;
+	} or;
+
+	union nv50_head_atom_mask {
+		struct {
+			bool olut:1;
+			bool core:1;
+			bool curs:1;
+			bool view:1;
+			bool mode:1;
+			bool base:1;
+			bool ovly:1;
+			bool dither:1;
+			bool procamp:1;
+			bool or:1;
+		};
+		u16 mask;
+	} set, clr;
+};
+
+static inline struct nv50_head_atom *
+nv50_head_atom_get(struct drm_atomic_state *state, struct drm_crtc *crtc)
+{
+	struct drm_crtc_state *statec = drm_atomic_get_crtc_state(state, crtc);
+	if (IS_ERR(statec))
+		return (void *)statec;
+	return nv50_head_atom(statec);
+}
+
+#define nv50_wndw_atom(p) container_of((p), struct nv50_wndw_atom, state)
+
+struct nv50_wndw_atom {
+	struct drm_plane_state state;
+
+	struct drm_property_blob *ilut;
+	bool visible;
+
+	struct {
+		u32  handle;
+		u16  offset:12;
+		bool awaken:1;
+	} ntfy;
+
+	struct {
+		u32 handle;
+		u16 offset:12;
+		u32 acquire;
+		u32 release;
+	} sema;
+
+	struct {
+		u32 handle;
+		struct {
+			u64 offset:40;
+			u8  buffer:1;
+			u8  enable:2;
+			u8  mode:4;
+			u8  size:2;
+			u8  range:2;
+			u8  output_mode:2;
+		} i;
+	} xlut;
+
+	struct {
+		u8  mode:2;
+		u8  interval:4;
+
+		u8  colorspace:2;
+		u8  format;
+		u8  kind:7;
+		u8  layout:1;
+		u8  blockh:4;
+		u16 blocks[3];
+		u32 pitch[3];
+		u16 w;
+		u16 h;
+
+		u32 handle[6];
+		u64 offset[6];
+	} image;
+
+	struct {
+		u16 sx;
+		u16 sy;
+		u16 sw;
+		u16 sh;
+		u16 dw;
+		u16 dh;
+	} scale;
+
+	struct {
+		u16 x;
+		u16 y;
+	} point;
+
+	union nv50_wndw_atom_mask {
+		struct {
+			bool ntfy:1;
+			bool sema:1;
+			bool xlut:1;
+			bool image:1;
+			bool scale:1;
+			bool point:1;
+		};
+		u8 mask;
+	} set, clr;
+};
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base.c b/drivers/gpu/drm/nouveau/dispnv50/base.c
new file mode 100644
index 000000000000..7c752acf2b48
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/base.c
@@ -0,0 +1,53 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "base.h"
+
+#include <nvif/class.h>
+
+int
+nv50_base_new(struct nouveau_drm *drm, int head, struct nv50_wndw **pwndw)
+{
+	struct {
+		s32 oclass;
+		int version;
+		int (*new)(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+	} bases[] = {
+		{ GK110_DISP_BASE_CHANNEL_DMA, 0, base917c_new },
+		{ GK104_DISP_BASE_CHANNEL_DMA, 0, base917c_new },
+		{ GF110_DISP_BASE_CHANNEL_DMA, 0, base907c_new },
+		{ GT214_DISP_BASE_CHANNEL_DMA, 0, base827c_new },
+		{ GT200_DISP_BASE_CHANNEL_DMA, 0, base827c_new },
+		{   G82_DISP_BASE_CHANNEL_DMA, 0, base827c_new },
+		{  NV50_DISP_BASE_CHANNEL_DMA, 0, base507c_new },
+		{}
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int cid;
+
+	cid = nvif_mclass(&disp->disp->object, bases);
+	if (cid < 0) {
+		NV_ERROR(drm, "No supported base class\n");
+		return cid;
+	}
+
+	return bases[cid].new(drm, head, bases[cid].oclass, pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base.h b/drivers/gpu/drm/nouveau/dispnv50/base.h
new file mode 100644
index 000000000000..e7f14f230f35
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/base.h
@@ -0,0 +1,31 @@
+#ifndef __NV50_KMS_BASE_H__
+#define __NV50_KMS_BASE_H__
+#include "wndw.h"
+
+int base507c_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+int base507c_new_(const struct nv50_wndw_func *, const u32 *format,
+		  struct nouveau_drm *, int head, s32 oclass,
+		  u32 interlock_data, struct nv50_wndw **);
+extern const u32 base507c_format[];
+int base507c_acquire(struct nv50_wndw *, struct nv50_wndw_atom *,
+		     struct nv50_head_atom *);
+void base507c_release(struct nv50_wndw *, struct nv50_wndw_atom *,
+		      struct nv50_head_atom *);
+void base507c_sema_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+void base507c_sema_clr(struct nv50_wndw *);
+void base507c_ntfy_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+void base507c_ntfy_clr(struct nv50_wndw *);
+void base507c_xlut_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+void base507c_xlut_clr(struct nv50_wndw *);
+void base507c_image_clr(struct nv50_wndw *);
+void base507c_update(struct nv50_wndw *, u32 *);
+
+int base827c_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+
+int base907c_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+extern const struct nv50_wndw_func base907c;
+
+int base917c_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+
+int nv50_base_new(struct nouveau_drm *, int head, struct nv50_wndw **);
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base507c.c b/drivers/gpu/drm/nouveau/dispnv50/base507c.c
new file mode 100644
index 000000000000..d5e295ca2caa
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/base507c.c
@@ -0,0 +1,286 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "base.h"
+
+#include <nvif/cl507c.h>
+#include <nvif/event.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include "nouveau_bo.h"
+
+void
+base507c_update(struct nv50_wndw *wndw, u32 *interlock)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x0080, 1);
+		evo_data(push, interlock[NV50_DISP_INTERLOCK_CORE]);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+base507c_image_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 4))) {
+		evo_mthd(push, 0x0084, 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x00c0, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+base507c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 10))) {
+		evo_mthd(push, 0x0084, 1);
+		evo_data(push, asyw->image.mode << 8 |
+			       asyw->image.interval << 4);
+		evo_mthd(push, 0x00c0, 1);
+		evo_data(push, asyw->image.handle[0]);
+		evo_mthd(push, 0x0800, 5);
+		evo_data(push, asyw->image.offset[0] >> 8);
+		evo_data(push, 0x00000000);
+		evo_data(push, asyw->image.h << 16 | asyw->image.w);
+		evo_data(push, asyw->image.layout << 20 |
+			       (asyw->image.pitch[0] >> 8) << 8 |
+			       asyw->image.blocks[0] << 8 |
+			       asyw->image.blockh);
+		evo_data(push, asyw->image.kind << 16 |
+			       asyw->image.format << 8);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+base507c_xlut_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x00e0, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+base507c_xlut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x00e0, 1);
+		evo_data(push, 0x40000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+int
+base507c_ntfy_wait_begun(struct nouveau_bo *bo, u32 offset,
+			 struct nvif_device *device)
+{
+	s64 time = nvif_msec(device, 2000ULL,
+		u32 data = nouveau_bo_rd32(bo, offset / 4);
+		if ((data & 0xc0000000) == 0x40000000)
+			break;
+		usleep_range(1, 2);
+	);
+	return time < 0 ? time : 0;
+}
+
+void
+base507c_ntfy_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x00a4, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+base507c_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 3))) {
+		evo_mthd(push, 0x00a0, 2);
+		evo_data(push, asyw->ntfy.awaken << 30 | asyw->ntfy.offset);
+		evo_data(push, asyw->ntfy.handle);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+base507c_ntfy_reset(struct nouveau_bo *bo, u32 offset)
+{
+	nouveau_bo_wr32(bo, offset / 4, 0x00000000);
+}
+
+void
+base507c_sema_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x0094, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+base507c_sema_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 5))) {
+		evo_mthd(push, 0x0088, 4);
+		evo_data(push, asyw->sema.offset);
+		evo_data(push, asyw->sema.acquire);
+		evo_data(push, asyw->sema.release);
+		evo_data(push, asyw->sema.handle);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+base507c_release(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
+		 struct nv50_head_atom *asyh)
+{
+	asyh->base.cpp = 0;
+}
+
+int
+base507c_acquire(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
+		 struct nv50_head_atom *asyh)
+{
+	const struct drm_framebuffer *fb = asyw->state.fb;
+	int ret;
+
+	if (!fb->format->depth)
+		return -EINVAL;
+
+	ret = drm_atomic_helper_check_plane_state(&asyw->state, &asyh->state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, true);
+	if (ret)
+		return ret;
+
+	if (!wndw->func->ilut) {
+		if ((asyh->base.cpp != 1) ^ (fb->format->cpp[0] != 1))
+			asyh->state.color_mgmt_changed = true;
+	}
+
+	asyh->base.depth = fb->format->depth;
+	asyh->base.cpp = fb->format->cpp[0];
+	asyh->base.x = asyw->state.src.x1 >> 16;
+	asyh->base.y = asyw->state.src.y1 >> 16;
+	asyh->base.w = asyw->state.fb->width;
+	asyh->base.h = asyw->state.fb->height;
+	return 0;
+}
+
+const u32
+base507c_format[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
+	0
+};
+
+static const struct nv50_wndw_func
+base507c = {
+	.acquire = base507c_acquire,
+	.release = base507c_release,
+	.sema_set = base507c_sema_set,
+	.sema_clr = base507c_sema_clr,
+	.ntfy_reset = base507c_ntfy_reset,
+	.ntfy_set = base507c_ntfy_set,
+	.ntfy_clr = base507c_ntfy_clr,
+	.ntfy_wait_begun = base507c_ntfy_wait_begun,
+	.olut_core = 1,
+	.xlut_set = base507c_xlut_set,
+	.xlut_clr = base507c_xlut_clr,
+	.image_set = base507c_image_set,
+	.image_clr = base507c_image_clr,
+	.update = base507c_update,
+};
+
+int
+base507c_new_(const struct nv50_wndw_func *func, const u32 *format,
+	      struct nouveau_drm *drm, int head, s32 oclass, u32 interlock_data,
+	      struct nv50_wndw **pwndw)
+{
+	struct nv50_disp_base_channel_dma_v0 args = {
+		.head = head,
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	struct nv50_wndw *wndw;
+	int ret;
+
+	ret = nv50_wndw_new_(func, drm->dev, DRM_PLANE_TYPE_PRIMARY,
+			     "base", head, format, BIT(head),
+			     NV50_DISP_INTERLOCK_BASE, interlock_data, &wndw);
+	if (*pwndw = wndw, ret)
+		return ret;
+
+	ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
+			       &oclass, head, &args, sizeof(args),
+			       disp->sync->bo.offset, &wndw->wndw);
+	if (ret) {
+		NV_ERROR(drm, "base%04x allocation failed: %d\n", oclass, ret);
+		return ret;
+	}
+
+	ret = nvif_notify_init(&wndw->wndw.base.user, wndw->notify.func,
+			       false, NV50_DISP_BASE_CHANNEL_DMA_V0_NTFY_UEVENT,
+			       &(struct nvif_notify_uevent_req) {},
+			       sizeof(struct nvif_notify_uevent_req),
+			       sizeof(struct nvif_notify_uevent_rep),
+			       &wndw->notify);
+	if (ret)
+		return ret;
+
+	wndw->ntfy = NV50_DISP_BASE_NTFY(wndw->id);
+	wndw->sema = NV50_DISP_BASE_SEM0(wndw->id);
+	wndw->data = 0x00000000;
+	return 0;
+}
+
+int
+base507c_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return base507c_new_(&base507c, base507c_format, drm, head, oclass,
+			     0x00000002 << (head * 8), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base827c.c b/drivers/gpu/drm/nouveau/dispnv50/base827c.c
new file mode 100644
index 000000000000..73646819a0d6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/base827c.c
@@ -0,0 +1,71 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "base.h"
+
+static void
+base827c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 10))) {
+		evo_mthd(push, 0x0084, 1);
+		evo_data(push, asyw->image.mode << 8 |
+			       asyw->image.interval << 4);
+		evo_mthd(push, 0x00c0, 1);
+		evo_data(push, asyw->image.handle[0]);
+		evo_mthd(push, 0x0800, 5);
+		evo_data(push, asyw->image.offset[0] >> 8);
+		evo_data(push, 0x00000000);
+		evo_data(push, asyw->image.h << 16 | asyw->image.w);
+		evo_data(push, asyw->image.layout << 20 |
+			       (asyw->image.pitch[0] >> 8) << 8 |
+			       asyw->image.blocks[0] << 8 |
+			       asyw->image.blockh);
+		evo_data(push, asyw->image.format << 8);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static const struct nv50_wndw_func
+base827c = {
+	.acquire = base507c_acquire,
+	.release = base507c_release,
+	.sema_set = base507c_sema_set,
+	.sema_clr = base507c_sema_clr,
+	.ntfy_reset = base507c_ntfy_reset,
+	.ntfy_set = base507c_ntfy_set,
+	.ntfy_clr = base507c_ntfy_clr,
+	.ntfy_wait_begun = base507c_ntfy_wait_begun,
+	.olut_core = 1,
+	.xlut_set = base507c_xlut_set,
+	.xlut_clr = base507c_xlut_clr,
+	.image_set = base827c_image_set,
+	.image_clr = base507c_image_clr,
+	.update = base507c_update,
+};
+
+int
+base827c_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return base507c_new_(&base827c, base507c_format, drm, head, oclass,
+			     0x00000002 << (head * 8), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base907c.c b/drivers/gpu/drm/nouveau/dispnv50/base907c.c
new file mode 100644
index 000000000000..a562fc94ce59
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/base907c.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "base.h"
+
+static void
+base907c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 10))) {
+		evo_mthd(push, 0x0084, 1);
+		evo_data(push, asyw->image.mode << 8 |
+			       asyw->image.interval << 4);
+		evo_mthd(push, 0x00c0, 1);
+		evo_data(push, asyw->image.handle[0]);
+		evo_mthd(push, 0x0400, 5);
+		evo_data(push, asyw->image.offset[0] >> 8);
+		evo_data(push, 0x00000000);
+		evo_data(push, asyw->image.h << 16 | asyw->image.w);
+		evo_data(push, asyw->image.layout << 24 |
+			       (asyw->image.pitch[0] >> 8) << 8 |
+			       asyw->image.blocks[0] << 8 |
+			       asyw->image.blockh);
+		evo_data(push, asyw->image.format << 8);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+base907c_xlut_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 6))) {
+		evo_mthd(push, 0x00e0, 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x00e8, 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x00fc, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+base907c_xlut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 6))) {
+		evo_mthd(push, 0x00e0, 3);
+		evo_data(push, asyw->xlut.i.enable << 30 |
+			       asyw->xlut.i.mode << 24);
+		evo_data(push, asyw->xlut.i.offset >> 8);
+		evo_data(push, 0x40000000);
+		evo_mthd(push, 0x00fc, 1);
+		evo_data(push, asyw->xlut.handle);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+base907c_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	asyw->xlut.i.mode = 7;
+	asyw->xlut.i.enable = 2;
+}
+
+const struct nv50_wndw_func
+base907c = {
+	.acquire = base507c_acquire,
+	.release = base507c_release,
+	.sema_set = base507c_sema_set,
+	.sema_clr = base507c_sema_clr,
+	.ntfy_reset = base507c_ntfy_reset,
+	.ntfy_set = base507c_ntfy_set,
+	.ntfy_clr = base507c_ntfy_clr,
+	.ntfy_wait_begun = base507c_ntfy_wait_begun,
+	.ilut = base907c_ilut,
+	.olut_core = true,
+	.xlut_set = base907c_xlut_set,
+	.xlut_clr = base907c_xlut_clr,
+	.image_set = base907c_image_set,
+	.image_clr = base507c_image_clr,
+	.update = base507c_update,
+};
+
+int
+base907c_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return base507c_new_(&base907c, base507c_format, drm, head, oclass,
+			     0x00000002 << (head * 4), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base917c.c b/drivers/gpu/drm/nouveau/dispnv50/base917c.c
new file mode 100644
index 000000000000..54d705bb81a5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/base917c.c
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "base.h"
+#include "atom.h"
+
+const u32
+base917c_format[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_ARGB2101010,
+	0
+};
+
+int
+base917c_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return base507c_new_(&base907c, base917c_format, drm, head, oclass,
+			     0x00000002 << (head * 4), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core.c b/drivers/gpu/drm/nouveau/dispnv50/core.c
new file mode 100644
index 000000000000..f3c49adb1bdb
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/core.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "core.h"
+
+#include <nvif/class.h>
+
+void
+nv50_core_del(struct nv50_core **pcore)
+{
+	struct nv50_core *core = *pcore;
+	if (core) {
+		nv50_dmac_destroy(&core->chan);
+		kfree(*pcore);
+		*pcore = NULL;
+	}
+}
+
+int
+nv50_core_new(struct nouveau_drm *drm, struct nv50_core **pcore)
+{
+	struct {
+		s32 oclass;
+		int version;
+		int (*new)(struct nouveau_drm *, s32, struct nv50_core **);
+	} cores[] = {
+		{ GV100_DISP_CORE_CHANNEL_DMA, 0, corec37d_new },
+		{ GP102_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
+		{ GP100_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
+		{ GM200_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
+		{ GM107_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
+		{ GK110_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
+		{ GK104_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
+		{ GF110_DISP_CORE_CHANNEL_DMA, 0, core907d_new },
+		{ GT214_DISP_CORE_CHANNEL_DMA, 0, core827d_new },
+		{ GT206_DISP_CORE_CHANNEL_DMA, 0, core827d_new },
+		{ GT200_DISP_CORE_CHANNEL_DMA, 0, core827d_new },
+		{   G82_DISP_CORE_CHANNEL_DMA, 0, core827d_new },
+		{  NV50_DISP_CORE_CHANNEL_DMA, 0, core507d_new },
+		{}
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int cid;
+
+	cid = nvif_mclass(&disp->disp->object, cores);
+	if (cid < 0) {
+		NV_ERROR(drm, "No supported core channel class\n");
+		return cid;
+	}
+
+	return cores[cid].new(drm, cores[cid].oclass, pcore);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core.h b/drivers/gpu/drm/nouveau/dispnv50/core.h
new file mode 100644
index 000000000000..8470df9dd13d
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/core.h
@@ -0,0 +1,50 @@
+#ifndef __NV50_KMS_CORE_H__
+#define __NV50_KMS_CORE_H__
+#include "disp.h"
+#include "atom.h"
+
+struct nv50_core {
+	const struct nv50_core_func *func;
+	struct nv50_dmac chan;
+};
+
+int nv50_core_new(struct nouveau_drm *, struct nv50_core **);
+void nv50_core_del(struct nv50_core **);
+
+struct nv50_core_func {
+	void (*init)(struct nv50_core *);
+	void (*ntfy_init)(struct nouveau_bo *, u32 offset);
+	int (*ntfy_wait_done)(struct nouveau_bo *, u32 offset,
+			      struct nvif_device *);
+	void (*update)(struct nv50_core *, u32 *interlock, bool ntfy);
+
+	const struct nv50_head_func *head;
+	const struct nv50_outp_func {
+		void (*ctrl)(struct nv50_core *, int or, u32 ctrl,
+			     struct nv50_head_atom *);
+	} *dac, *pior, *sor;
+};
+
+int core507d_new(struct nouveau_drm *, s32, struct nv50_core **);
+int core507d_new_(const struct nv50_core_func *, struct nouveau_drm *, s32,
+		  struct nv50_core **);
+void core507d_init(struct nv50_core *);
+void core507d_ntfy_init(struct nouveau_bo *, u32);
+int core507d_ntfy_wait_done(struct nouveau_bo *, u32, struct nvif_device *);
+void core507d_update(struct nv50_core *, u32 *, bool);
+
+extern const struct nv50_outp_func dac507d;
+extern const struct nv50_outp_func sor507d;
+extern const struct nv50_outp_func pior507d;
+
+int core827d_new(struct nouveau_drm *, s32, struct nv50_core **);
+
+int core907d_new(struct nouveau_drm *, s32, struct nv50_core **);
+extern const struct nv50_outp_func dac907d;
+extern const struct nv50_outp_func sor907d;
+
+int core917d_new(struct nouveau_drm *, s32, struct nv50_core **);
+
+int corec37d_new(struct nouveau_drm *, s32, struct nv50_core **);
+extern const struct nv50_outp_func sorc37d;
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c
new file mode 100644
index 000000000000..e7fcfa6e6467
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "core.h"
+#include "head.h"
+
+#include <nvif/cl507d.h>
+
+#include "nouveau_bo.h"
+
+void
+core507d_update(struct nv50_core *core, u32 *interlock, bool ntfy)
+{
+	u32 *push;
+	if ((push = evo_wait(&core->chan, 5))) {
+		if (ntfy) {
+			evo_mthd(push, 0x0084, 1);
+			evo_data(push, 0x80000000 | NV50_DISP_CORE_NTFY);
+		}
+		evo_mthd(push, 0x0080, 2);
+		evo_data(push, interlock[NV50_DISP_INTERLOCK_BASE] |
+			       interlock[NV50_DISP_INTERLOCK_OVLY]);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &core->chan);
+	}
+}
+
+int
+core507d_ntfy_wait_done(struct nouveau_bo *bo, u32 offset,
+			struct nvif_device *device)
+{
+	s64 time = nvif_msec(device, 2000ULL,
+		if (nouveau_bo_rd32(bo, offset / 4))
+			break;
+		usleep_range(1, 2);
+	);
+	return time < 0 ? time : 0;
+}
+
+void
+core507d_ntfy_init(struct nouveau_bo *bo, u32 offset)
+{
+	nouveau_bo_wr32(bo, offset / 4, 0x00000000);
+}
+
+void
+core507d_init(struct nv50_core *core)
+{
+	u32 *push;
+	if ((push = evo_wait(&core->chan, 2))) {
+		evo_mthd(push, 0x0088, 1);
+		evo_data(push, core->chan.sync.handle);
+		evo_kick(push, &core->chan);
+	}
+}
+
+static const struct nv50_core_func
+core507d = {
+	.init = core507d_init,
+	.ntfy_init = core507d_ntfy_init,
+	.ntfy_wait_done = core507d_ntfy_wait_done,
+	.update = core507d_update,
+	.head = &head507d,
+	.dac = &dac507d,
+	.sor = &sor507d,
+	.pior = &pior507d,
+};
+
+int
+core507d_new_(const struct nv50_core_func *func, struct nouveau_drm *drm,
+	      s32 oclass, struct nv50_core **pcore)
+{
+	struct nv50_disp_core_channel_dma_v0 args = {};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	struct nv50_core *core;
+	int ret;
+
+	if (!(core = *pcore = kzalloc(sizeof(*core), GFP_KERNEL)))
+		return -ENOMEM;
+	core->func = func;
+
+	ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
+			       &oclass, 0, &args, sizeof(args),
+			       disp->sync->bo.offset, &core->chan);
+	if (ret) {
+		NV_ERROR(drm, "core%04x allocation failed: %d\n", oclass, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int
+core507d_new(struct nouveau_drm *drm, s32 oclass, struct nv50_core **pcore)
+{
+	return core507d_new_(&core507d, drm, oclass, pcore);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core827d.c b/drivers/gpu/drm/nouveau/dispnv50/core827d.c
new file mode 100644
index 000000000000..6123a068f836
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/core827d.c
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "core.h"
+#include "head.h"
+
+static const struct nv50_core_func
+core827d = {
+	.init = core507d_init,
+	.ntfy_init = core507d_ntfy_init,
+	.ntfy_wait_done = core507d_ntfy_wait_done,
+	.update = core507d_update,
+	.head = &head827d,
+	.dac = &dac507d,
+	.sor = &sor507d,
+	.pior = &pior507d,
+};
+
+int
+core827d_new(struct nouveau_drm *drm, s32 oclass, struct nv50_core **pcore)
+{
+	return core507d_new_(&core827d, drm, oclass, pcore);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegt215.c b/drivers/gpu/drm/nouveau/dispnv50/core907d.c
index 08e2b1fa3806..ef822f813435 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegt215.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core907d.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,21 +18,23 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "core.h"
+#include "head.h"
 
-const struct nv50_disp_dmac_oclass
-gt215_disp_base_oclass = {
-	.base.oclass = GT214_DISP_BASE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_base_new,
-	.func = &nv50_disp_dmac_func,
-	.mthd = &g84_disp_base_chan_mthd,
-	.chid = 1,
+static const struct nv50_core_func
+core907d = {
+	.init = core507d_init,
+	.ntfy_init = core507d_ntfy_init,
+	.ntfy_wait_done = core507d_ntfy_wait_done,
+	.update = core507d_update,
+	.head = &head907d,
+	.dac = &dac907d,
+	.sor = &sor907d,
 };
+
+int
+core907d_new(struct nouveau_drm *drm, s32 oclass, struct nv50_core **pcore)
+{
+	return core507d_new_(&core907d, drm, oclass, pcore);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegk110.c b/drivers/gpu/drm/nouveau/dispnv50/core917d.c
index d8bdd246c8ed..392338df5bfd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegk110.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core917d.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,21 +18,23 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "core.h"
+#include "head.h"
 
-const struct nv50_disp_dmac_oclass
-gk110_disp_base_oclass = {
-	.base.oclass = GK110_DISP_BASE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_base_new,
-	.func = &gf119_disp_dmac_func,
-	.mthd = &gf119_disp_base_chan_mthd,
-	.chid = 1,
+static const struct nv50_core_func
+core917d = {
+	.init = core507d_init,
+	.ntfy_init = core507d_ntfy_init,
+	.ntfy_wait_done = core507d_ntfy_wait_done,
+	.update = core507d_update,
+	.head = &head917d,
+	.dac = &dac907d,
+	.sor = &sor907d,
 };
+
+int
+core917d_new(struct nouveau_drm *drm, s32 oclass, struct nv50_core **pcore)
+{
+	return core507d_new_(&core917d, drm, oclass, pcore);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/corec37d.c b/drivers/gpu/drm/nouveau/dispnv50/corec37d.c
new file mode 100644
index 000000000000..b5c17c948918
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/corec37d.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "core.h"
+#include "head.h"
+
+#include <nouveau_bo.h>
+
+static void
+corec37d_update(struct nv50_core *core, u32 *interlock, bool ntfy)
+{
+	u32 *push;
+	if ((push = evo_wait(&core->chan, 9))) {
+		if (ntfy) {
+			evo_mthd(push, 0x020c, 1);
+			evo_data(push, 0x00001000 | NV50_DISP_CORE_NTFY);
+		}
+
+		evo_mthd(push, 0x0218, 2);
+		evo_data(push, interlock[NV50_DISP_INTERLOCK_CURS]);
+		evo_data(push, interlock[NV50_DISP_INTERLOCK_WNDW]);
+		evo_mthd(push, 0x0200, 1);
+		evo_data(push, 0x00000001);
+
+		if (ntfy) {
+			evo_mthd(push, 0x020c, 1);
+			evo_data(push, 0x00000000);
+		}
+		evo_kick(push, &core->chan);
+	}
+}
+
+int
+corec37d_ntfy_wait_done(struct nouveau_bo *bo, u32 offset,
+			struct nvif_device *device)
+{
+	u32 data;
+	s64 time = nvif_msec(device, 2000ULL,
+		data = nouveau_bo_rd32(bo, offset / 4 + 0);
+		if ((data & 0xc0000000) == 0x80000000)
+			break;
+		usleep_range(1, 2);
+	);
+	return time < 0 ? time : 0;
+}
+
+void
+corec37d_ntfy_init(struct nouveau_bo *bo, u32 offset)
+{
+	nouveau_bo_wr32(bo, offset / 4 + 0, 0x00000000);
+	nouveau_bo_wr32(bo, offset / 4 + 1, 0x00000000);
+	nouveau_bo_wr32(bo, offset / 4 + 2, 0x00000000);
+	nouveau_bo_wr32(bo, offset / 4 + 3, 0x00000000);
+}
+
+void
+corec37d_init(struct nv50_core *core)
+{
+	const u32 windows = 8; /*XXX*/
+	u32 *push, i;
+	if ((push = evo_wait(&core->chan, 2 + 6 * windows + 2))) {
+		evo_mthd(push, 0x0208, 1);
+		evo_data(push, core->chan.sync.handle);
+		for (i = 0; i < windows; i++) {
+			evo_mthd(push, 0x1000 + (i * 0x080), 3);
+			evo_data(push, i >> 1);
+			evo_data(push, 0x00000017);
+			evo_data(push, 0x00000000);
+			evo_mthd(push, 0x1010 + (i * 0x080), 1);
+			evo_data(push, 0x00127fff);
+		}
+		evo_mthd(push, 0x0200, 1);
+		evo_data(push, 0x00000001);
+		evo_kick(push, &core->chan);
+	}
+}
+
+static const struct nv50_core_func
+corec37d = {
+	.init = corec37d_init,
+	.ntfy_init = corec37d_ntfy_init,
+	.ntfy_wait_done = corec37d_ntfy_wait_done,
+	.update = corec37d_update,
+	.head = &headc37d,
+	.sor = &sorc37d,
+};
+
+int
+corec37d_new(struct nouveau_drm *drm, s32 oclass, struct nv50_core **pcore)
+{
+	return core507d_new_(&corec37d, drm, oclass, pcore);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs.c b/drivers/gpu/drm/nouveau/dispnv50/curs.c
new file mode 100644
index 000000000000..f592087338c4
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/curs.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "curs.h"
+
+#include <nvif/class.h>
+
+int
+nv50_curs_new(struct nouveau_drm *drm, int head, struct nv50_wndw **pwndw)
+{
+	struct {
+		s32 oclass;
+		int version;
+		int (*new)(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+	} curses[] = {
+		{ GV100_DISP_CURSOR, 0, cursc37a_new },
+		{ GK104_DISP_CURSOR, 0, curs907a_new },
+		{ GF110_DISP_CURSOR, 0, curs907a_new },
+		{ GT214_DISP_CURSOR, 0, curs507a_new },
+		{   G82_DISP_CURSOR, 0, curs507a_new },
+		{  NV50_DISP_CURSOR, 0, curs507a_new },
+		{}
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int cid;
+
+	cid = nvif_mclass(&disp->disp->object, curses);
+	if (cid < 0) {
+		NV_ERROR(drm, "No supported cursor immediate class\n");
+		return cid;
+	}
+
+	return curses[cid].new(drm, head, curses[cid].oclass, pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs.h b/drivers/gpu/drm/nouveau/dispnv50/curs.h
new file mode 100644
index 000000000000..23aff5fd6747
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/curs.h
@@ -0,0 +1,14 @@
+#ifndef __NV50_KMS_CURS_H__
+#define __NV50_KMS_CURS_H__
+#include "wndw.h"
+
+int curs507a_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+int curs507a_new_(const struct nv50_wimm_func *, struct nouveau_drm *,
+		  int head, s32 oclass, u32 interlock_data,
+		  struct nv50_wndw **);
+
+int curs907a_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+int cursc37a_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+
+int nv50_curs_new(struct nouveau_drm *, int head, struct nv50_wndw **);
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c
new file mode 100644
index 000000000000..291c08117ab6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c
@@ -0,0 +1,145 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "curs.h"
+#include "core.h"
+#include "head.h"
+
+#include <nvif/cl507a.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+
+static void
+curs507a_update(struct nv50_wndw *wndw, u32 *interlock)
+{
+	nvif_wr32(&wndw->wimm.base.user, 0x0080, 0x00000000);
+}
+
+static void
+curs507a_point(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	nvif_wr32(&wndw->wimm.base.user, 0x0084, asyw->point.y << 16 |
+						 asyw->point.x);
+}
+
+const struct nv50_wimm_func
+curs507a = {
+	.point = curs507a_point,
+	.update = curs507a_update,
+};
+
+static void
+curs507a_prepare(struct nv50_wndw *wndw, struct nv50_head_atom *asyh,
+		 struct nv50_wndw_atom *asyw)
+{
+	u32 handle = nv50_disp(wndw->plane.dev)->core->chan.vram.handle;
+	u32 offset = asyw->image.offset[0];
+	if (asyh->curs.handle != handle || asyh->curs.offset != offset) {
+		asyh->curs.handle = handle;
+		asyh->curs.offset = offset;
+		asyh->set.curs = asyh->curs.visible;
+	}
+}
+
+static void
+curs507a_release(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
+		 struct nv50_head_atom *asyh)
+{
+	asyh->curs.visible = false;
+}
+
+static int
+curs507a_acquire(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
+		 struct nv50_head_atom *asyh)
+{
+	struct nv50_head *head = nv50_head(asyw->state.crtc);
+	int ret;
+
+	ret = drm_atomic_helper_check_plane_state(&asyw->state, &asyh->state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  true, true);
+	asyh->curs.visible = asyw->state.visible;
+	if (ret || !asyh->curs.visible)
+		return ret;
+
+	if (asyw->image.w != asyw->image.h)
+		return -EINVAL;
+
+	ret = head->func->curs_layout(head, asyw, asyh);
+	if (ret)
+		return ret;
+
+	return head->func->curs_format(head, asyw, asyh);
+}
+
+static const u32
+curs507a_format[] = {
+	DRM_FORMAT_ARGB8888,
+	0
+};
+
+static const struct nv50_wndw_func
+curs507a_wndw = {
+	.acquire = curs507a_acquire,
+	.release = curs507a_release,
+	.prepare = curs507a_prepare,
+};
+
+int
+curs507a_new_(const struct nv50_wimm_func *func, struct nouveau_drm *drm,
+	      int head, s32 oclass, u32 interlock_data,
+	      struct nv50_wndw **pwndw)
+{
+	struct nv50_disp_cursor_v0 args = {
+		.head = head,
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	struct nv50_wndw *wndw;
+	int ret;
+
+	ret = nv50_wndw_new_(&curs507a_wndw, drm->dev, DRM_PLANE_TYPE_CURSOR,
+			     "curs", head, curs507a_format, BIT(head),
+			     NV50_DISP_INTERLOCK_CURS, interlock_data, &wndw);
+	if (*pwndw = wndw, ret)
+		return ret;
+
+	ret = nvif_object_init(&disp->disp->object, 0, oclass, &args,
+			       sizeof(args), &wndw->wimm.base.user);
+	if (ret) {
+		NV_ERROR(drm, "curs%04x allocation failed: %d\n", oclass, ret);
+		return ret;
+	}
+
+	nvif_object_map(&wndw->wimm.base.user, NULL, 0);
+	wndw->immd = func;
+	wndw->ctxdma.parent = &disp->core->chan.base.user;
+	return 0;
+}
+
+int
+curs507a_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return curs507a_new_(&curs507a, drm, head, oclass,
+			     0x00000001 << (head * 8), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk110.c b/drivers/gpu/drm/nouveau/dispnv50/curs907a.c
index a9aa69c82e8e..d742362de03e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk110.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/curs907a.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2016 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,17 +18,13 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs
  */
-#include "changk104.h"
-
-#include <nvif/class.h>
+#include "curs.h"
 
-const struct nvkm_fifo_chan_oclass
-gk110_fifo_gpfifo_oclass = {
-	.base.oclass = KEPLER_CHANNEL_GPFIFO_B,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = gk104_fifo_gpfifo_new,
-};
+int
+curs907a_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return curs507a_new_(&curs507a, drm, head, oclass,
+			     0x00000001 << (head * 4), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/cursc37a.c b/drivers/gpu/drm/nouveau/dispnv50/cursc37a.c
new file mode 100644
index 000000000000..23fb29d41efe
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/cursc37a.c
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "curs.h"
+#include "atom.h"
+
+static void
+cursc37a_update(struct nv50_wndw *wndw, u32 *interlock)
+{
+	nvif_wr32(&wndw->wimm.base.user, 0x0200, 0x00000001);
+}
+
+static void
+cursc37a_point(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	nvif_wr32(&wndw->wimm.base.user, 0x0208, asyw->point.y << 16 |
+						 asyw->point.x);
+}
+
+static const struct nv50_wimm_func
+cursc37a = {
+	.point = cursc37a_point,
+	.update = cursc37a_update,
+};
+
+int
+cursc37a_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return curs507a_new_(&cursc37a, drm, head, oclass,
+			     0x00000001 << head, pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/dac507d.c b/drivers/gpu/drm/nouveau/dispnv50/dac507d.c
new file mode 100644
index 000000000000..2a10ef7d30a8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/dac507d.c
@@ -0,0 +1,44 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "core.h"
+
+static void
+dac507d_ctrl(struct nv50_core *core, int or, u32 ctrl,
+	     struct nv50_head_atom *asyh)
+{
+	u32 *push, sync = 0;
+	if ((push = evo_wait(&core->chan, 3))) {
+		if (asyh) {
+			sync |= asyh->or.nvsync << 1;
+			sync |= asyh->or.nhsync;
+		}
+		evo_mthd(push, 0x0400 + (or * 0x080), 2);
+		evo_data(push, ctrl);
+		evo_data(push, sync);
+		evo_kick(push, &core->chan);
+	}
+}
+
+const struct nv50_outp_func
+dac507d = {
+	.ctrl = dac507d_ctrl,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgt215.c b/drivers/gpu/drm/nouveau/dispnv50/dac907d.c
index 00a7f3564450..11e87fa53fac 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgt215.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/dac907d.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,20 +18,22 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "channv50.h"
-#include "rootnv50.h"
+#include "core.h"
 
-#include <nvif/class.h>
+static void
+dac907d_ctrl(struct nv50_core *core, int or, u32 ctrl,
+	     struct nv50_head_atom *asyh)
+{
+	u32 *push;
+	if ((push = evo_wait(&core->chan, 2))) {
+		evo_mthd(push, 0x0180 + (or * 0x020), 1);
+		evo_data(push, ctrl);
+		evo_kick(push, &core->chan);
+	}
+}
 
-const struct nv50_disp_pioc_oclass
-gt215_disp_curs_oclass = {
-	.base.oclass = GT214_DISP_CURSOR,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_curs_new,
-	.func = &nv50_disp_pioc_func,
-	.chid = { 7, 7 },
+const struct nv50_outp_func
+dac907d = {
+	.ctrl = dac907d_ctrl,
 };
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
new file mode 100644
index 000000000000..b83465ae7c1b
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -0,0 +1,2238 @@
+/*
+ * Copyright 2011 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "disp.h"
+#include "atom.h"
+#include "core.h"
+#include "head.h"
+#include "wndw.h"
+
+#include <linux/dma-mapping.h>
+#include <linux/hdmi.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_dp_helper.h>
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_edid.h>
+
+#include <nvif/class.h>
+#include <nvif/cl0002.h>
+#include <nvif/cl5070.h>
+#include <nvif/cl507d.h>
+#include <nvif/event.h>
+
+#include "nouveau_drv.h"
+#include "nouveau_dma.h"
+#include "nouveau_gem.h"
+#include "nouveau_connector.h"
+#include "nouveau_encoder.h"
+#include "nouveau_fence.h"
+#include "nouveau_fbcon.h"
+
+#include <subdev/bios/dp.h>
+
+/******************************************************************************
+ * Atomic state
+ *****************************************************************************/
+
+struct nv50_outp_atom {
+	struct list_head head;
+
+	struct drm_encoder *encoder;
+	bool flush_disable;
+
+	union nv50_outp_atom_mask {
+		struct {
+			bool ctrl:1;
+		};
+		u8 mask;
+	} set, clr;
+};
+
+/******************************************************************************
+ * EVO channel
+ *****************************************************************************/
+
+static int
+nv50_chan_create(struct nvif_device *device, struct nvif_object *disp,
+		 const s32 *oclass, u8 head, void *data, u32 size,
+		 struct nv50_chan *chan)
+{
+	struct nvif_sclass *sclass;
+	int ret, i, n;
+
+	chan->device = device;
+
+	ret = n = nvif_object_sclass_get(disp, &sclass);
+	if (ret < 0)
+		return ret;
+
+	while (oclass[0]) {
+		for (i = 0; i < n; i++) {
+			if (sclass[i].oclass == oclass[0]) {
+				ret = nvif_object_init(disp, 0, oclass[0],
+						       data, size, &chan->user);
+				if (ret == 0)
+					nvif_object_map(&chan->user, NULL, 0);
+				nvif_object_sclass_put(&sclass);
+				return ret;
+			}
+		}
+		oclass++;
+	}
+
+	nvif_object_sclass_put(&sclass);
+	return -ENOSYS;
+}
+
+static void
+nv50_chan_destroy(struct nv50_chan *chan)
+{
+	nvif_object_fini(&chan->user);
+}
+
+/******************************************************************************
+ * DMA EVO channel
+ *****************************************************************************/
+
+void
+nv50_dmac_destroy(struct nv50_dmac *dmac)
+{
+	nvif_object_fini(&dmac->vram);
+	nvif_object_fini(&dmac->sync);
+
+	nv50_chan_destroy(&dmac->base);
+
+	nvif_mem_fini(&dmac->push);
+}
+
+int
+nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
+		 const s32 *oclass, u8 head, void *data, u32 size, u64 syncbuf,
+		 struct nv50_dmac *dmac)
+{
+	struct nouveau_cli *cli = (void *)device->object.client;
+	struct nv50_disp_core_channel_dma_v0 *args = data;
+	int ret;
+
+	mutex_init(&dmac->lock);
+
+	ret = nvif_mem_init_map(&cli->mmu, NVIF_MEM_COHERENT, 0x1000,
+				&dmac->push);
+	if (ret)
+		return ret;
+
+	dmac->ptr = dmac->push.object.map.ptr;
+
+	args->pushbuf = nvif_handle(&dmac->push.object);
+
+	ret = nv50_chan_create(device, disp, oclass, head, data, size,
+			       &dmac->base);
+	if (ret)
+		return ret;
+
+	if (!syncbuf)
+		return 0;
+
+	ret = nvif_object_init(&dmac->base.user, 0xf0000000, NV_DMA_IN_MEMORY,
+			       &(struct nv_dma_v0) {
+					.target = NV_DMA_V0_TARGET_VRAM,
+					.access = NV_DMA_V0_ACCESS_RDWR,
+					.start = syncbuf + 0x0000,
+					.limit = syncbuf + 0x0fff,
+			       }, sizeof(struct nv_dma_v0),
+			       &dmac->sync);
+	if (ret)
+		return ret;
+
+	ret = nvif_object_init(&dmac->base.user, 0xf0000001, NV_DMA_IN_MEMORY,
+			       &(struct nv_dma_v0) {
+					.target = NV_DMA_V0_TARGET_VRAM,
+					.access = NV_DMA_V0_ACCESS_RDWR,
+					.start = 0,
+					.limit = device->info.ram_user - 1,
+			       }, sizeof(struct nv_dma_v0),
+			       &dmac->vram);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+/******************************************************************************
+ * EVO channel helpers
+ *****************************************************************************/
+u32 *
+evo_wait(struct nv50_dmac *evoc, int nr)
+{
+	struct nv50_dmac *dmac = evoc;
+	struct nvif_device *device = dmac->base.device;
+	u32 put = nvif_rd32(&dmac->base.user, 0x0000) / 4;
+
+	mutex_lock(&dmac->lock);
+	if (put + nr >= (PAGE_SIZE / 4) - 8) {
+		dmac->ptr[put] = 0x20000000;
+
+		nvif_wr32(&dmac->base.user, 0x0000, 0x00000000);
+		if (nvif_msec(device, 2000,
+			if (!nvif_rd32(&dmac->base.user, 0x0004))
+				break;
+		) < 0) {
+			mutex_unlock(&dmac->lock);
+			pr_err("nouveau: evo channel stalled\n");
+			return NULL;
+		}
+
+		put = 0;
+	}
+
+	return dmac->ptr + put;
+}
+
+void
+evo_kick(u32 *push, struct nv50_dmac *evoc)
+{
+	struct nv50_dmac *dmac = evoc;
+	nvif_wr32(&dmac->base.user, 0x0000, (push - dmac->ptr) << 2);
+	mutex_unlock(&dmac->lock);
+}
+
+/******************************************************************************
+ * Output path helpers
+ *****************************************************************************/
+static void
+nv50_outp_release(struct nouveau_encoder *nv_encoder)
+{
+	struct nv50_disp *disp = nv50_disp(nv_encoder->base.base.dev);
+	struct {
+		struct nv50_disp_mthd_v1 base;
+	} args = {
+		.base.version = 1,
+		.base.method = NV50_DISP_MTHD_V1_RELEASE,
+		.base.hasht  = nv_encoder->dcb->hasht,
+		.base.hashm  = nv_encoder->dcb->hashm,
+	};
+
+	nvif_mthd(&disp->disp->object, 0, &args, sizeof(args));
+	nv_encoder->or = -1;
+	nv_encoder->link = 0;
+}
+
+static int
+nv50_outp_acquire(struct nouveau_encoder *nv_encoder)
+{
+	struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	struct {
+		struct nv50_disp_mthd_v1 base;
+		struct nv50_disp_acquire_v0 info;
+	} args = {
+		.base.version = 1,
+		.base.method = NV50_DISP_MTHD_V1_ACQUIRE,
+		.base.hasht  = nv_encoder->dcb->hasht,
+		.base.hashm  = nv_encoder->dcb->hashm,
+	};
+	int ret;
+
+	ret = nvif_mthd(&disp->disp->object, 0, &args, sizeof(args));
+	if (ret) {
+		NV_ERROR(drm, "error acquiring output path: %d\n", ret);
+		return ret;
+	}
+
+	nv_encoder->or = args.info.or;
+	nv_encoder->link = args.info.link;
+	return 0;
+}
+
+static int
+nv50_outp_atomic_check_view(struct drm_encoder *encoder,
+			    struct drm_crtc_state *crtc_state,
+			    struct drm_connector_state *conn_state,
+			    struct drm_display_mode *native_mode)
+{
+	struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode;
+	struct drm_display_mode *mode = &crtc_state->mode;
+	struct drm_connector *connector = conn_state->connector;
+	struct nouveau_conn_atom *asyc = nouveau_conn_atom(conn_state);
+	struct nouveau_drm *drm = nouveau_drm(encoder->dev);
+
+	NV_ATOMIC(drm, "%s atomic_check\n", encoder->name);
+	asyc->scaler.full = false;
+	if (!native_mode)
+		return 0;
+
+	if (asyc->scaler.mode == DRM_MODE_SCALE_NONE) {
+		switch (connector->connector_type) {
+		case DRM_MODE_CONNECTOR_LVDS:
+		case DRM_MODE_CONNECTOR_eDP:
+			/* Force use of scaler for non-EDID modes. */
+			if (adjusted_mode->type & DRM_MODE_TYPE_DRIVER)
+				break;
+			mode = native_mode;
+			asyc->scaler.full = true;
+			break;
+		default:
+			break;
+		}
+	} else {
+		mode = native_mode;
+	}
+
+	if (!drm_mode_equal(adjusted_mode, mode)) {
+		drm_mode_copy(adjusted_mode, mode);
+		crtc_state->mode_changed = true;
+	}
+
+	return 0;
+}
+
+static int
+nv50_outp_atomic_check(struct drm_encoder *encoder,
+		       struct drm_crtc_state *crtc_state,
+		       struct drm_connector_state *conn_state)
+{
+	struct nouveau_connector *nv_connector =
+		nouveau_connector(conn_state->connector);
+	return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state,
+					   nv_connector->native_mode);
+}
+
+/******************************************************************************
+ * DAC
+ *****************************************************************************/
+static void
+nv50_dac_disable(struct drm_encoder *encoder)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nv50_core *core = nv50_disp(encoder->dev)->core;
+	if (nv_encoder->crtc)
+		core->func->dac->ctrl(core, nv_encoder->or, 0x00000000, NULL);
+	nv_encoder->crtc = NULL;
+	nv50_outp_release(nv_encoder);
+}
+
+static void
+nv50_dac_enable(struct drm_encoder *encoder)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
+	struct nv50_head_atom *asyh = nv50_head_atom(nv_crtc->base.state);
+	struct nv50_core *core = nv50_disp(encoder->dev)->core;
+
+	nv50_outp_acquire(nv_encoder);
+
+	core->func->dac->ctrl(core, nv_encoder->or, 1 << nv_crtc->index, asyh);
+	asyh->or.depth = 0;
+
+	nv_encoder->crtc = encoder->crtc;
+}
+
+static enum drm_connector_status
+nv50_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nv50_disp *disp = nv50_disp(encoder->dev);
+	struct {
+		struct nv50_disp_mthd_v1 base;
+		struct nv50_disp_dac_load_v0 load;
+	} args = {
+		.base.version = 1,
+		.base.method = NV50_DISP_MTHD_V1_DAC_LOAD,
+		.base.hasht  = nv_encoder->dcb->hasht,
+		.base.hashm  = nv_encoder->dcb->hashm,
+	};
+	int ret;
+
+	args.load.data = nouveau_drm(encoder->dev)->vbios.dactestval;
+	if (args.load.data == 0)
+		args.load.data = 340;
+
+	ret = nvif_mthd(&disp->disp->object, 0, &args, sizeof(args));
+	if (ret || !args.load.load)
+		return connector_status_disconnected;
+
+	return connector_status_connected;
+}
+
+static const struct drm_encoder_helper_funcs
+nv50_dac_help = {
+	.atomic_check = nv50_outp_atomic_check,
+	.enable = nv50_dac_enable,
+	.disable = nv50_dac_disable,
+	.detect = nv50_dac_detect
+};
+
+static void
+nv50_dac_destroy(struct drm_encoder *encoder)
+{
+	drm_encoder_cleanup(encoder);
+	kfree(encoder);
+}
+
+static const struct drm_encoder_funcs
+nv50_dac_func = {
+	.destroy = nv50_dac_destroy,
+};
+
+static int
+nv50_dac_create(struct drm_connector *connector, struct dcb_output *dcbe)
+{
+	struct nouveau_drm *drm = nouveau_drm(connector->dev);
+	struct nvkm_i2c *i2c = nvxx_i2c(&drm->client.device);
+	struct nvkm_i2c_bus *bus;
+	struct nouveau_encoder *nv_encoder;
+	struct drm_encoder *encoder;
+	int type = DRM_MODE_ENCODER_DAC;
+
+	nv_encoder = kzalloc(sizeof(*nv_encoder), GFP_KERNEL);
+	if (!nv_encoder)
+		return -ENOMEM;
+	nv_encoder->dcb = dcbe;
+
+	bus = nvkm_i2c_bus_find(i2c, dcbe->i2c_index);
+	if (bus)
+		nv_encoder->i2c = &bus->i2c;
+
+	encoder = to_drm_encoder(nv_encoder);
+	encoder->possible_crtcs = dcbe->heads;
+	encoder->possible_clones = 0;
+	drm_encoder_init(connector->dev, encoder, &nv50_dac_func, type,
+			 "dac-%04x-%04x", dcbe->hasht, dcbe->hashm);
+	drm_encoder_helper_add(encoder, &nv50_dac_help);
+
+	drm_mode_connector_attach_encoder(connector, encoder);
+	return 0;
+}
+
+/******************************************************************************
+ * Audio
+ *****************************************************************************/
+static void
+nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nv50_disp *disp = nv50_disp(encoder->dev);
+	struct {
+		struct nv50_disp_mthd_v1 base;
+		struct nv50_disp_sor_hda_eld_v0 eld;
+	} args = {
+		.base.version = 1,
+		.base.method  = NV50_DISP_MTHD_V1_SOR_HDA_ELD,
+		.base.hasht   = nv_encoder->dcb->hasht,
+		.base.hashm   = (0xf0ff & nv_encoder->dcb->hashm) |
+				(0x0100 << nv_crtc->index),
+	};
+
+	nvif_mthd(&disp->disp->object, 0, &args, sizeof(args));
+}
+
+static void
+nv50_audio_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
+	struct nouveau_connector *nv_connector;
+	struct nv50_disp *disp = nv50_disp(encoder->dev);
+	struct __packed {
+		struct {
+			struct nv50_disp_mthd_v1 mthd;
+			struct nv50_disp_sor_hda_eld_v0 eld;
+		} base;
+		u8 data[sizeof(nv_connector->base.eld)];
+	} args = {
+		.base.mthd.version = 1,
+		.base.mthd.method  = NV50_DISP_MTHD_V1_SOR_HDA_ELD,
+		.base.mthd.hasht   = nv_encoder->dcb->hasht,
+		.base.mthd.hashm   = (0xf0ff & nv_encoder->dcb->hashm) |
+				     (0x0100 << nv_crtc->index),
+	};
+
+	nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	if (!drm_detect_monitor_audio(nv_connector->edid))
+		return;
+
+	memcpy(args.data, nv_connector->base.eld, sizeof(args.data));
+
+	nvif_mthd(&disp->disp->object, 0, &args,
+		  sizeof(args.base) + drm_eld_size(args.data));
+}
+
+/******************************************************************************
+ * HDMI
+ *****************************************************************************/
+static void
+nv50_hdmi_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nv50_disp *disp = nv50_disp(encoder->dev);
+	struct {
+		struct nv50_disp_mthd_v1 base;
+		struct nv50_disp_sor_hdmi_pwr_v0 pwr;
+	} args = {
+		.base.version = 1,
+		.base.method = NV50_DISP_MTHD_V1_SOR_HDMI_PWR,
+		.base.hasht  = nv_encoder->dcb->hasht,
+		.base.hashm  = (0xf0ff & nv_encoder->dcb->hashm) |
+			       (0x0100 << nv_crtc->index),
+	};
+
+	nvif_mthd(&disp->disp->object, 0, &args, sizeof(args));
+}
+
+static void
+nv50_hdmi_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
+	struct nv50_disp *disp = nv50_disp(encoder->dev);
+	struct {
+		struct nv50_disp_mthd_v1 base;
+		struct nv50_disp_sor_hdmi_pwr_v0 pwr;
+		u8 infoframes[2 * 17]; /* two frames, up to 17 bytes each */
+	} args = {
+		.base.version = 1,
+		.base.method = NV50_DISP_MTHD_V1_SOR_HDMI_PWR,
+		.base.hasht  = nv_encoder->dcb->hasht,
+		.base.hashm  = (0xf0ff & nv_encoder->dcb->hashm) |
+			       (0x0100 << nv_crtc->index),
+		.pwr.state = 1,
+		.pwr.rekey = 56, /* binary driver, and tegra, constant */
+	};
+	struct nouveau_connector *nv_connector;
+	u32 max_ac_packet;
+	union hdmi_infoframe avi_frame;
+	union hdmi_infoframe vendor_frame;
+	int ret;
+	int size;
+
+	nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	if (!drm_detect_hdmi_monitor(nv_connector->edid))
+		return;
+
+	ret = drm_hdmi_avi_infoframe_from_display_mode(&avi_frame.avi, mode,
+						       false);
+	if (!ret) {
+		/* We have an AVI InfoFrame, populate it to the display */
+		args.pwr.avi_infoframe_length
+			= hdmi_infoframe_pack(&avi_frame, args.infoframes, 17);
+	}
+
+	ret = drm_hdmi_vendor_infoframe_from_display_mode(&vendor_frame.vendor.hdmi,
+							  &nv_connector->base, mode);
+	if (!ret) {
+		/* We have a Vendor InfoFrame, populate it to the display */
+		args.pwr.vendor_infoframe_length
+			= hdmi_infoframe_pack(&vendor_frame,
+					      args.infoframes
+					      + args.pwr.avi_infoframe_length,
+					      17);
+	}
+
+	max_ac_packet  = mode->htotal - mode->hdisplay;
+	max_ac_packet -= args.pwr.rekey;
+	max_ac_packet -= 18; /* constant from tegra */
+	args.pwr.max_ac_packet = max_ac_packet / 32;
+
+	size = sizeof(args.base)
+		+ sizeof(args.pwr)
+		+ args.pwr.avi_infoframe_length
+		+ args.pwr.vendor_infoframe_length;
+	nvif_mthd(&disp->disp->object, 0, &args, size);
+	nv50_audio_enable(encoder, mode);
+}
+
+/******************************************************************************
+ * MST
+ *****************************************************************************/
+#define nv50_mstm(p) container_of((p), struct nv50_mstm, mgr)
+#define nv50_mstc(p) container_of((p), struct nv50_mstc, connector)
+#define nv50_msto(p) container_of((p), struct nv50_msto, encoder)
+
+struct nv50_mstm {
+	struct nouveau_encoder *outp;
+
+	struct drm_dp_mst_topology_mgr mgr;
+	struct nv50_msto *msto[4];
+
+	bool modified;
+	bool disabled;
+	int links;
+};
+
+struct nv50_mstc {
+	struct nv50_mstm *mstm;
+	struct drm_dp_mst_port *port;
+	struct drm_connector connector;
+
+	struct drm_display_mode *native;
+	struct edid *edid;
+
+	int pbn;
+};
+
+struct nv50_msto {
+	struct drm_encoder encoder;
+
+	struct nv50_head *head;
+	struct nv50_mstc *mstc;
+	bool disabled;
+};
+
+static struct drm_dp_payload *
+nv50_msto_payload(struct nv50_msto *msto)
+{
+	struct nouveau_drm *drm = nouveau_drm(msto->encoder.dev);
+	struct nv50_mstc *mstc = msto->mstc;
+	struct nv50_mstm *mstm = mstc->mstm;
+	int vcpi = mstc->port->vcpi.vcpi, i;
+
+	NV_ATOMIC(drm, "%s: vcpi %d\n", msto->encoder.name, vcpi);
+	for (i = 0; i < mstm->mgr.max_payloads; i++) {
+		struct drm_dp_payload *payload = &mstm->mgr.payloads[i];
+		NV_ATOMIC(drm, "%s: %d: vcpi %d start 0x%02x slots 0x%02x\n",
+			  mstm->outp->base.base.name, i, payload->vcpi,
+			  payload->start_slot, payload->num_slots);
+	}
+
+	for (i = 0; i < mstm->mgr.max_payloads; i++) {
+		struct drm_dp_payload *payload = &mstm->mgr.payloads[i];
+		if (payload->vcpi == vcpi)
+			return payload;
+	}
+
+	return NULL;
+}
+
+static void
+nv50_msto_cleanup(struct nv50_msto *msto)
+{
+	struct nouveau_drm *drm = nouveau_drm(msto->encoder.dev);
+	struct nv50_mstc *mstc = msto->mstc;
+	struct nv50_mstm *mstm = mstc->mstm;
+
+	NV_ATOMIC(drm, "%s: msto cleanup\n", msto->encoder.name);
+	if (mstc->port && mstc->port->vcpi.vcpi > 0 && !nv50_msto_payload(msto))
+		drm_dp_mst_deallocate_vcpi(&mstm->mgr, mstc->port);
+	if (msto->disabled) {
+		msto->mstc = NULL;
+		msto->head = NULL;
+		msto->disabled = false;
+	}
+}
+
+static void
+nv50_msto_prepare(struct nv50_msto *msto)
+{
+	struct nouveau_drm *drm = nouveau_drm(msto->encoder.dev);
+	struct nv50_mstc *mstc = msto->mstc;
+	struct nv50_mstm *mstm = mstc->mstm;
+	struct {
+		struct nv50_disp_mthd_v1 base;
+		struct nv50_disp_sor_dp_mst_vcpi_v0 vcpi;
+	} args = {
+		.base.version = 1,
+		.base.method = NV50_DISP_MTHD_V1_SOR_DP_MST_VCPI,
+		.base.hasht  = mstm->outp->dcb->hasht,
+		.base.hashm  = (0xf0ff & mstm->outp->dcb->hashm) |
+			       (0x0100 << msto->head->base.index),
+	};
+
+	NV_ATOMIC(drm, "%s: msto prepare\n", msto->encoder.name);
+	if (mstc->port && mstc->port->vcpi.vcpi > 0) {
+		struct drm_dp_payload *payload = nv50_msto_payload(msto);
+		if (payload) {
+			args.vcpi.start_slot = payload->start_slot;
+			args.vcpi.num_slots = payload->num_slots;
+			args.vcpi.pbn = mstc->port->vcpi.pbn;
+			args.vcpi.aligned_pbn = mstc->port->vcpi.aligned_pbn;
+		}
+	}
+
+	NV_ATOMIC(drm, "%s: %s: %02x %02x %04x %04x\n",
+		  msto->encoder.name, msto->head->base.base.name,
+		  args.vcpi.start_slot, args.vcpi.num_slots,
+		  args.vcpi.pbn, args.vcpi.aligned_pbn);
+	nvif_mthd(&drm->display->disp.object, 0, &args, sizeof(args));
+}
+
+static int
+nv50_msto_atomic_check(struct drm_encoder *encoder,
+		       struct drm_crtc_state *crtc_state,
+		       struct drm_connector_state *conn_state)
+{
+	struct nv50_mstc *mstc = nv50_mstc(conn_state->connector);
+	struct nv50_mstm *mstm = mstc->mstm;
+	int bpp = conn_state->connector->display_info.bpc * 3;
+	int slots;
+
+	mstc->pbn = drm_dp_calc_pbn_mode(crtc_state->adjusted_mode.clock, bpp);
+
+	slots = drm_dp_find_vcpi_slots(&mstm->mgr, mstc->pbn);
+	if (slots < 0)
+		return slots;
+
+	return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state,
+					   mstc->native);
+}
+
+static void
+nv50_msto_enable(struct drm_encoder *encoder)
+{
+	struct nv50_head *head = nv50_head(encoder->crtc);
+	struct nv50_msto *msto = nv50_msto(encoder);
+	struct nv50_mstc *mstc = NULL;
+	struct nv50_mstm *mstm = NULL;
+	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
+	u8 proto, depth;
+	int slots;
+	bool r;
+
+	drm_connector_list_iter_begin(encoder->dev, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
+		if (connector->state->best_encoder == &msto->encoder) {
+			mstc = nv50_mstc(connector);
+			mstm = mstc->mstm;
+			break;
+		}
+	}
+	drm_connector_list_iter_end(&conn_iter);
+
+	if (WARN_ON(!mstc))
+		return;
+
+	slots = drm_dp_find_vcpi_slots(&mstm->mgr, mstc->pbn);
+	r = drm_dp_mst_allocate_vcpi(&mstm->mgr, mstc->port, mstc->pbn, slots);
+	WARN_ON(!r);
+
+	if (!mstm->links++)
+		nv50_outp_acquire(mstm->outp);
+
+	if (mstm->outp->link & 1)
+		proto = 0x8;
+	else
+		proto = 0x9;
+
+	switch (mstc->connector.display_info.bpc) {
+	case  6: depth = 0x2; break;
+	case  8: depth = 0x5; break;
+	case 10:
+	default: depth = 0x6; break;
+	}
+
+	mstm->outp->update(mstm->outp, head->base.index,
+			   nv50_head_atom(head->base.base.state), proto, depth);
+
+	msto->head = head;
+	msto->mstc = mstc;
+	mstm->modified = true;
+}
+
+static void
+nv50_msto_disable(struct drm_encoder *encoder)
+{
+	struct nv50_msto *msto = nv50_msto(encoder);
+	struct nv50_mstc *mstc = msto->mstc;
+	struct nv50_mstm *mstm = mstc->mstm;
+
+	if (mstc->port)
+		drm_dp_mst_reset_vcpi_slots(&mstm->mgr, mstc->port);
+
+	mstm->outp->update(mstm->outp, msto->head->base.index, NULL, 0, 0);
+	mstm->modified = true;
+	if (!--mstm->links)
+		mstm->disabled = true;
+	msto->disabled = true;
+}
+
+static const struct drm_encoder_helper_funcs
+nv50_msto_help = {
+	.disable = nv50_msto_disable,
+	.enable = nv50_msto_enable,
+	.atomic_check = nv50_msto_atomic_check,
+};
+
+static void
+nv50_msto_destroy(struct drm_encoder *encoder)
+{
+	struct nv50_msto *msto = nv50_msto(encoder);
+	drm_encoder_cleanup(&msto->encoder);
+	kfree(msto);
+}
+
+static const struct drm_encoder_funcs
+nv50_msto = {
+	.destroy = nv50_msto_destroy,
+};
+
+static int
+nv50_msto_new(struct drm_device *dev, u32 heads, const char *name, int id,
+	      struct nv50_msto **pmsto)
+{
+	struct nv50_msto *msto;
+	int ret;
+
+	if (!(msto = *pmsto = kzalloc(sizeof(*msto), GFP_KERNEL)))
+		return -ENOMEM;
+
+	ret = drm_encoder_init(dev, &msto->encoder, &nv50_msto,
+			       DRM_MODE_ENCODER_DPMST, "%s-mst-%d", name, id);
+	if (ret) {
+		kfree(*pmsto);
+		*pmsto = NULL;
+		return ret;
+	}
+
+	drm_encoder_helper_add(&msto->encoder, &nv50_msto_help);
+	msto->encoder.possible_crtcs = heads;
+	return 0;
+}
+
+static struct drm_encoder *
+nv50_mstc_atomic_best_encoder(struct drm_connector *connector,
+			      struct drm_connector_state *connector_state)
+{
+	struct nv50_head *head = nv50_head(connector_state->crtc);
+	struct nv50_mstc *mstc = nv50_mstc(connector);
+	if (mstc->port) {
+		struct nv50_mstm *mstm = mstc->mstm;
+		return &mstm->msto[head->base.index]->encoder;
+	}
+	return NULL;
+}
+
+static struct drm_encoder *
+nv50_mstc_best_encoder(struct drm_connector *connector)
+{
+	struct nv50_mstc *mstc = nv50_mstc(connector);
+	if (mstc->port) {
+		struct nv50_mstm *mstm = mstc->mstm;
+		return &mstm->msto[0]->encoder;
+	}
+	return NULL;
+}
+
+static enum drm_mode_status
+nv50_mstc_mode_valid(struct drm_connector *connector,
+		     struct drm_display_mode *mode)
+{
+	return MODE_OK;
+}
+
+static int
+nv50_mstc_get_modes(struct drm_connector *connector)
+{
+	struct nv50_mstc *mstc = nv50_mstc(connector);
+	int ret = 0;
+
+	mstc->edid = drm_dp_mst_get_edid(&mstc->connector, mstc->port->mgr, mstc->port);
+	drm_mode_connector_update_edid_property(&mstc->connector, mstc->edid);
+	if (mstc->edid)
+		ret = drm_add_edid_modes(&mstc->connector, mstc->edid);
+
+	if (!mstc->connector.display_info.bpc)
+		mstc->connector.display_info.bpc = 8;
+
+	if (mstc->native)
+		drm_mode_destroy(mstc->connector.dev, mstc->native);
+	mstc->native = nouveau_conn_native_mode(&mstc->connector);
+	return ret;
+}
+
+static const struct drm_connector_helper_funcs
+nv50_mstc_help = {
+	.get_modes = nv50_mstc_get_modes,
+	.mode_valid = nv50_mstc_mode_valid,
+	.best_encoder = nv50_mstc_best_encoder,
+	.atomic_best_encoder = nv50_mstc_atomic_best_encoder,
+};
+
+static enum drm_connector_status
+nv50_mstc_detect(struct drm_connector *connector, bool force)
+{
+	struct nv50_mstc *mstc = nv50_mstc(connector);
+	if (!mstc->port)
+		return connector_status_disconnected;
+	return drm_dp_mst_detect_port(connector, mstc->port->mgr, mstc->port);
+}
+
+static void
+nv50_mstc_destroy(struct drm_connector *connector)
+{
+	struct nv50_mstc *mstc = nv50_mstc(connector);
+	drm_connector_cleanup(&mstc->connector);
+	kfree(mstc);
+}
+
+static const struct drm_connector_funcs
+nv50_mstc = {
+	.reset = nouveau_conn_reset,
+	.detect = nv50_mstc_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = nv50_mstc_destroy,
+	.atomic_duplicate_state = nouveau_conn_atomic_duplicate_state,
+	.atomic_destroy_state = nouveau_conn_atomic_destroy_state,
+	.atomic_set_property = nouveau_conn_atomic_set_property,
+	.atomic_get_property = nouveau_conn_atomic_get_property,
+};
+
+static int
+nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
+	      const char *path, struct nv50_mstc **pmstc)
+{
+	struct drm_device *dev = mstm->outp->base.base.dev;
+	struct nv50_mstc *mstc;
+	int ret, i;
+
+	if (!(mstc = *pmstc = kzalloc(sizeof(*mstc), GFP_KERNEL)))
+		return -ENOMEM;
+	mstc->mstm = mstm;
+	mstc->port = port;
+
+	ret = drm_connector_init(dev, &mstc->connector, &nv50_mstc,
+				 DRM_MODE_CONNECTOR_DisplayPort);
+	if (ret) {
+		kfree(*pmstc);
+		*pmstc = NULL;
+		return ret;
+	}
+
+	drm_connector_helper_add(&mstc->connector, &nv50_mstc_help);
+
+	mstc->connector.funcs->reset(&mstc->connector);
+	nouveau_conn_attach_properties(&mstc->connector);
+
+	for (i = 0; i < ARRAY_SIZE(mstm->msto) && mstm->msto[i]; i++)
+		drm_mode_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
+
+	drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0);
+	drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0);
+	drm_mode_connector_set_path_property(&mstc->connector, path);
+	return 0;
+}
+
+static void
+nv50_mstm_cleanup(struct nv50_mstm *mstm)
+{
+	struct nouveau_drm *drm = nouveau_drm(mstm->outp->base.base.dev);
+	struct drm_encoder *encoder;
+	int ret;
+
+	NV_ATOMIC(drm, "%s: mstm cleanup\n", mstm->outp->base.base.name);
+	ret = drm_dp_check_act_status(&mstm->mgr);
+
+	ret = drm_dp_update_payload_part2(&mstm->mgr);
+
+	drm_for_each_encoder(encoder, mstm->outp->base.base.dev) {
+		if (encoder->encoder_type == DRM_MODE_ENCODER_DPMST) {
+			struct nv50_msto *msto = nv50_msto(encoder);
+			struct nv50_mstc *mstc = msto->mstc;
+			if (mstc && mstc->mstm == mstm)
+				nv50_msto_cleanup(msto);
+		}
+	}
+
+	mstm->modified = false;
+}
+
+static void
+nv50_mstm_prepare(struct nv50_mstm *mstm)
+{
+	struct nouveau_drm *drm = nouveau_drm(mstm->outp->base.base.dev);
+	struct drm_encoder *encoder;
+	int ret;
+
+	NV_ATOMIC(drm, "%s: mstm prepare\n", mstm->outp->base.base.name);
+	ret = drm_dp_update_payload_part1(&mstm->mgr);
+
+	drm_for_each_encoder(encoder, mstm->outp->base.base.dev) {
+		if (encoder->encoder_type == DRM_MODE_ENCODER_DPMST) {
+			struct nv50_msto *msto = nv50_msto(encoder);
+			struct nv50_mstc *mstc = msto->mstc;
+			if (mstc && mstc->mstm == mstm)
+				nv50_msto_prepare(msto);
+		}
+	}
+
+	if (mstm->disabled) {
+		if (!mstm->links)
+			nv50_outp_release(mstm->outp);
+		mstm->disabled = false;
+	}
+}
+
+static void
+nv50_mstm_hotplug(struct drm_dp_mst_topology_mgr *mgr)
+{
+	struct nv50_mstm *mstm = nv50_mstm(mgr);
+	drm_kms_helper_hotplug_event(mstm->outp->base.base.dev);
+}
+
+static void
+nv50_mstm_destroy_connector(struct drm_dp_mst_topology_mgr *mgr,
+			    struct drm_connector *connector)
+{
+	struct nouveau_drm *drm = nouveau_drm(connector->dev);
+	struct nv50_mstc *mstc = nv50_mstc(connector);
+
+	drm_connector_unregister(&mstc->connector);
+
+	drm_fb_helper_remove_one_connector(&drm->fbcon->helper, &mstc->connector);
+
+	drm_modeset_lock(&drm->dev->mode_config.connection_mutex, NULL);
+	mstc->port = NULL;
+	drm_modeset_unlock(&drm->dev->mode_config.connection_mutex);
+
+	drm_connector_unreference(&mstc->connector);
+}
+
+static void
+nv50_mstm_register_connector(struct drm_connector *connector)
+{
+	struct nouveau_drm *drm = nouveau_drm(connector->dev);
+
+	drm_fb_helper_add_one_connector(&drm->fbcon->helper, connector);
+
+	drm_connector_register(connector);
+}
+
+static struct drm_connector *
+nv50_mstm_add_connector(struct drm_dp_mst_topology_mgr *mgr,
+			struct drm_dp_mst_port *port, const char *path)
+{
+	struct nv50_mstm *mstm = nv50_mstm(mgr);
+	struct nv50_mstc *mstc;
+	int ret;
+
+	ret = nv50_mstc_new(mstm, port, path, &mstc);
+	if (ret) {
+		if (mstc)
+			mstc->connector.funcs->destroy(&mstc->connector);
+		return NULL;
+	}
+
+	return &mstc->connector;
+}
+
+static const struct drm_dp_mst_topology_cbs
+nv50_mstm = {
+	.add_connector = nv50_mstm_add_connector,
+	.register_connector = nv50_mstm_register_connector,
+	.destroy_connector = nv50_mstm_destroy_connector,
+	.hotplug = nv50_mstm_hotplug,
+};
+
+void
+nv50_mstm_service(struct nv50_mstm *mstm)
+{
+	struct drm_dp_aux *aux = mstm ? mstm->mgr.aux : NULL;
+	bool handled = true;
+	int ret;
+	u8 esi[8] = {};
+
+	if (!aux)
+		return;
+
+	while (handled) {
+		ret = drm_dp_dpcd_read(aux, DP_SINK_COUNT_ESI, esi, 8);
+		if (ret != 8) {
+			drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
+			return;
+		}
+
+		drm_dp_mst_hpd_irq(&mstm->mgr, esi, &handled);
+		if (!handled)
+			break;
+
+		drm_dp_dpcd_write(aux, DP_SINK_COUNT_ESI + 1, &esi[1], 3);
+	}
+}
+
+void
+nv50_mstm_remove(struct nv50_mstm *mstm)
+{
+	if (mstm)
+		drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
+}
+
+static int
+nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state)
+{
+	struct nouveau_encoder *outp = mstm->outp;
+	struct {
+		struct nv50_disp_mthd_v1 base;
+		struct nv50_disp_sor_dp_mst_link_v0 mst;
+	} args = {
+		.base.version = 1,
+		.base.method = NV50_DISP_MTHD_V1_SOR_DP_MST_LINK,
+		.base.hasht = outp->dcb->hasht,
+		.base.hashm = outp->dcb->hashm,
+		.mst.state = state,
+	};
+	struct nouveau_drm *drm = nouveau_drm(outp->base.base.dev);
+	struct nvif_object *disp = &drm->display->disp.object;
+	int ret;
+
+	if (dpcd >= 0x12) {
+		ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CTRL, &dpcd);
+		if (ret < 0)
+			return ret;
+
+		dpcd &= ~DP_MST_EN;
+		if (state)
+			dpcd |= DP_MST_EN;
+
+		ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, dpcd);
+		if (ret < 0)
+			return ret;
+	}
+
+	return nvif_mthd(disp, 0, &args, sizeof(args));
+}
+
+int
+nv50_mstm_detect(struct nv50_mstm *mstm, u8 dpcd[8], int allow)
+{
+	int ret, state = 0;
+
+	if (!mstm)
+		return 0;
+
+	if (dpcd[0] >= 0x12) {
+		ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CAP, &dpcd[1]);
+		if (ret < 0)
+			return ret;
+
+		if (!(dpcd[1] & DP_MST_CAP))
+			dpcd[0] = 0x11;
+		else
+			state = allow;
+	}
+
+	ret = nv50_mstm_enable(mstm, dpcd[0], state);
+	if (ret)
+		return ret;
+
+	ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, state);
+	if (ret)
+		return nv50_mstm_enable(mstm, dpcd[0], 0);
+
+	return mstm->mgr.mst_state;
+}
+
+static void
+nv50_mstm_fini(struct nv50_mstm *mstm)
+{
+	if (mstm && mstm->mgr.mst_state)
+		drm_dp_mst_topology_mgr_suspend(&mstm->mgr);
+}
+
+static void
+nv50_mstm_init(struct nv50_mstm *mstm)
+{
+	if (mstm && mstm->mgr.mst_state)
+		drm_dp_mst_topology_mgr_resume(&mstm->mgr);
+}
+
+static void
+nv50_mstm_del(struct nv50_mstm **pmstm)
+{
+	struct nv50_mstm *mstm = *pmstm;
+	if (mstm) {
+		kfree(*pmstm);
+		*pmstm = NULL;
+	}
+}
+
+static int
+nv50_mstm_new(struct nouveau_encoder *outp, struct drm_dp_aux *aux, int aux_max,
+	      int conn_base_id, struct nv50_mstm **pmstm)
+{
+	const int max_payloads = hweight8(outp->dcb->heads);
+	struct drm_device *dev = outp->base.base.dev;
+	struct nv50_mstm *mstm;
+	int ret, i;
+	u8 dpcd;
+
+	/* This is a workaround for some monitors not functioning
+	 * correctly in MST mode on initial module load.  I think
+	 * some bad interaction with the VBIOS may be responsible.
+	 *
+	 * A good ol' off and on again seems to work here ;)
+	 */
+	ret = drm_dp_dpcd_readb(aux, DP_DPCD_REV, &dpcd);
+	if (ret >= 0 && dpcd >= 0x12)
+		drm_dp_dpcd_writeb(aux, DP_MSTM_CTRL, 0);
+
+	if (!(mstm = *pmstm = kzalloc(sizeof(*mstm), GFP_KERNEL)))
+		return -ENOMEM;
+	mstm->outp = outp;
+	mstm->mgr.cbs = &nv50_mstm;
+
+	ret = drm_dp_mst_topology_mgr_init(&mstm->mgr, dev, aux, aux_max,
+					   max_payloads, conn_base_id);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < max_payloads; i++) {
+		ret = nv50_msto_new(dev, outp->dcb->heads, outp->base.base.name,
+				    i, &mstm->msto[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/******************************************************************************
+ * SOR
+ *****************************************************************************/
+static void
+nv50_sor_update(struct nouveau_encoder *nv_encoder, u8 head,
+		struct nv50_head_atom *asyh, u8 proto, u8 depth)
+{
+	struct nv50_disp *disp = nv50_disp(nv_encoder->base.base.dev);
+	struct nv50_core *core = disp->core;
+
+	if (!asyh) {
+		nv_encoder->ctrl &= ~BIT(head);
+		if (!(nv_encoder->ctrl & 0x0000000f))
+			nv_encoder->ctrl = 0;
+	} else {
+		nv_encoder->ctrl |= proto << 8;
+		nv_encoder->ctrl |= BIT(head);
+		asyh->or.depth = depth;
+	}
+
+	core->func->sor->ctrl(core, nv_encoder->or, nv_encoder->ctrl, asyh);
+}
+
+static void
+nv50_sor_disable(struct drm_encoder *encoder)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(nv_encoder->crtc);
+
+	nv_encoder->crtc = NULL;
+
+	if (nv_crtc) {
+		struct nvkm_i2c_aux *aux = nv_encoder->aux;
+		u8 pwr;
+
+		if (aux) {
+			int ret = nvkm_rdaux(aux, DP_SET_POWER, &pwr, 1);
+			if (ret == 0) {
+				pwr &= ~DP_SET_POWER_MASK;
+				pwr |=  DP_SET_POWER_D3;
+				nvkm_wraux(aux, DP_SET_POWER, &pwr, 1);
+			}
+		}
+
+		nv_encoder->update(nv_encoder, nv_crtc->index, NULL, 0, 0);
+		nv50_audio_disable(encoder, nv_crtc);
+		nv50_hdmi_disable(&nv_encoder->base.base, nv_crtc);
+		nv50_outp_release(nv_encoder);
+	}
+}
+
+static void
+nv50_sor_enable(struct drm_encoder *encoder)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
+	struct nv50_head_atom *asyh = nv50_head_atom(nv_crtc->base.state);
+	struct drm_display_mode *mode = &asyh->state.adjusted_mode;
+	struct {
+		struct nv50_disp_mthd_v1 base;
+		struct nv50_disp_sor_lvds_script_v0 lvds;
+	} lvds = {
+		.base.version = 1,
+		.base.method  = NV50_DISP_MTHD_V1_SOR_LVDS_SCRIPT,
+		.base.hasht   = nv_encoder->dcb->hasht,
+		.base.hashm   = nv_encoder->dcb->hashm,
+	};
+	struct nv50_disp *disp = nv50_disp(encoder->dev);
+	struct drm_device *dev = encoder->dev;
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nouveau_connector *nv_connector;
+	struct nvbios *bios = &drm->vbios;
+	u8 proto = 0xf;
+	u8 depth = 0x0;
+
+	nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	nv_encoder->crtc = encoder->crtc;
+	nv50_outp_acquire(nv_encoder);
+
+	switch (nv_encoder->dcb->type) {
+	case DCB_OUTPUT_TMDS:
+		if (nv_encoder->link & 1) {
+			proto = 0x1;
+			/* Only enable dual-link if:
+			 *  - Need to (i.e. rate > 165MHz)
+			 *  - DCB says we can
+			 *  - Not an HDMI monitor, since there's no dual-link
+			 *    on HDMI.
+			 */
+			if (mode->clock >= 165000 &&
+			    nv_encoder->dcb->duallink_possible &&
+			    !drm_detect_hdmi_monitor(nv_connector->edid))
+				proto |= 0x4;
+		} else {
+			proto = 0x2;
+		}
+
+		nv50_hdmi_enable(&nv_encoder->base.base, mode);
+		break;
+	case DCB_OUTPUT_LVDS:
+		proto = 0x0;
+
+		if (bios->fp_no_ddc) {
+			if (bios->fp.dual_link)
+				lvds.lvds.script |= 0x0100;
+			if (bios->fp.if_is_24bit)
+				lvds.lvds.script |= 0x0200;
+		} else {
+			if (nv_connector->type == DCB_CONNECTOR_LVDS_SPWG) {
+				if (((u8 *)nv_connector->edid)[121] == 2)
+					lvds.lvds.script |= 0x0100;
+			} else
+			if (mode->clock >= bios->fp.duallink_transition_clk) {
+				lvds.lvds.script |= 0x0100;
+			}
+
+			if (lvds.lvds.script & 0x0100) {
+				if (bios->fp.strapless_is_24bit & 2)
+					lvds.lvds.script |= 0x0200;
+			} else {
+				if (bios->fp.strapless_is_24bit & 1)
+					lvds.lvds.script |= 0x0200;
+			}
+
+			if (nv_connector->base.display_info.bpc == 8)
+				lvds.lvds.script |= 0x0200;
+		}
+
+		nvif_mthd(&disp->disp->object, 0, &lvds, sizeof(lvds));
+		break;
+	case DCB_OUTPUT_DP:
+		if (nv_connector->base.display_info.bpc == 6)
+			depth = 0x2;
+		else
+		if (nv_connector->base.display_info.bpc == 8)
+			depth = 0x5;
+		else
+			depth = 0x6;
+
+		if (nv_encoder->link & 1)
+			proto = 0x8;
+		else
+			proto = 0x9;
+
+		nv50_audio_enable(encoder, mode);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	nv_encoder->update(nv_encoder, nv_crtc->index, asyh, proto, depth);
+}
+
+static const struct drm_encoder_helper_funcs
+nv50_sor_help = {
+	.atomic_check = nv50_outp_atomic_check,
+	.enable = nv50_sor_enable,
+	.disable = nv50_sor_disable,
+};
+
+static void
+nv50_sor_destroy(struct drm_encoder *encoder)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	nv50_mstm_del(&nv_encoder->dp.mstm);
+	drm_encoder_cleanup(encoder);
+	kfree(encoder);
+}
+
+static const struct drm_encoder_funcs
+nv50_sor_func = {
+	.destroy = nv50_sor_destroy,
+};
+
+static int
+nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
+{
+	struct nouveau_connector *nv_connector = nouveau_connector(connector);
+	struct nouveau_drm *drm = nouveau_drm(connector->dev);
+	struct nvkm_bios *bios = nvxx_bios(&drm->client.device);
+	struct nvkm_i2c *i2c = nvxx_i2c(&drm->client.device);
+	struct nouveau_encoder *nv_encoder;
+	struct drm_encoder *encoder;
+	u8 ver, hdr, cnt, len;
+	u32 data;
+	int type, ret;
+
+	switch (dcbe->type) {
+	case DCB_OUTPUT_LVDS: type = DRM_MODE_ENCODER_LVDS; break;
+	case DCB_OUTPUT_TMDS:
+	case DCB_OUTPUT_DP:
+	default:
+		type = DRM_MODE_ENCODER_TMDS;
+		break;
+	}
+
+	nv_encoder = kzalloc(sizeof(*nv_encoder), GFP_KERNEL);
+	if (!nv_encoder)
+		return -ENOMEM;
+	nv_encoder->dcb = dcbe;
+	nv_encoder->update = nv50_sor_update;
+
+	encoder = to_drm_encoder(nv_encoder);
+	encoder->possible_crtcs = dcbe->heads;
+	encoder->possible_clones = 0;
+	drm_encoder_init(connector->dev, encoder, &nv50_sor_func, type,
+			 "sor-%04x-%04x", dcbe->hasht, dcbe->hashm);
+	drm_encoder_helper_add(encoder, &nv50_sor_help);
+
+	drm_mode_connector_attach_encoder(connector, encoder);
+
+	if (dcbe->type == DCB_OUTPUT_DP) {
+		struct nv50_disp *disp = nv50_disp(encoder->dev);
+		struct nvkm_i2c_aux *aux =
+			nvkm_i2c_aux_find(i2c, dcbe->i2c_index);
+		if (aux) {
+			if (disp->disp->object.oclass < GF110_DISP) {
+				/* HW has no support for address-only
+				 * transactions, so we're required to
+				 * use custom I2C-over-AUX code.
+				 */
+				nv_encoder->i2c = &aux->i2c;
+			} else {
+				nv_encoder->i2c = &nv_connector->aux.ddc;
+			}
+			nv_encoder->aux = aux;
+		}
+
+		if ((data = nvbios_dp_table(bios, &ver, &hdr, &cnt, &len)) &&
+		    ver >= 0x40 && (nvbios_rd08(bios, data + 0x08) & 0x04)) {
+			ret = nv50_mstm_new(nv_encoder, &nv_connector->aux, 16,
+					    nv_connector->base.base.id,
+					    &nv_encoder->dp.mstm);
+			if (ret)
+				return ret;
+		}
+	} else {
+		struct nvkm_i2c_bus *bus =
+			nvkm_i2c_bus_find(i2c, dcbe->i2c_index);
+		if (bus)
+			nv_encoder->i2c = &bus->i2c;
+	}
+
+	return 0;
+}
+
+/******************************************************************************
+ * PIOR
+ *****************************************************************************/
+static int
+nv50_pior_atomic_check(struct drm_encoder *encoder,
+		       struct drm_crtc_state *crtc_state,
+		       struct drm_connector_state *conn_state)
+{
+	int ret = nv50_outp_atomic_check(encoder, crtc_state, conn_state);
+	if (ret)
+		return ret;
+	crtc_state->adjusted_mode.clock *= 2;
+	return 0;
+}
+
+static void
+nv50_pior_disable(struct drm_encoder *encoder)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nv50_core *core = nv50_disp(encoder->dev)->core;
+	if (nv_encoder->crtc)
+		core->func->pior->ctrl(core, nv_encoder->or, 0x00000000, NULL);
+	nv_encoder->crtc = NULL;
+	nv50_outp_release(nv_encoder);
+}
+
+static void
+nv50_pior_enable(struct drm_encoder *encoder)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
+	struct nouveau_connector *nv_connector;
+	struct nv50_head_atom *asyh = nv50_head_atom(nv_crtc->base.state);
+	struct nv50_core *core = nv50_disp(encoder->dev)->core;
+	u8 owner = 1 << nv_crtc->index;
+	u8 proto;
+
+	nv50_outp_acquire(nv_encoder);
+
+	nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	switch (nv_connector->base.display_info.bpc) {
+	case 10: asyh->or.depth = 0x6; break;
+	case  8: asyh->or.depth = 0x5; break;
+	case  6: asyh->or.depth = 0x2; break;
+	default: asyh->or.depth = 0x0; break;
+	}
+
+	switch (nv_encoder->dcb->type) {
+	case DCB_OUTPUT_TMDS:
+	case DCB_OUTPUT_DP:
+		proto = 0x0;
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	core->func->pior->ctrl(core, nv_encoder->or, (proto << 8) | owner, asyh);
+	nv_encoder->crtc = encoder->crtc;
+}
+
+static const struct drm_encoder_helper_funcs
+nv50_pior_help = {
+	.atomic_check = nv50_pior_atomic_check,
+	.enable = nv50_pior_enable,
+	.disable = nv50_pior_disable,
+};
+
+static void
+nv50_pior_destroy(struct drm_encoder *encoder)
+{
+	drm_encoder_cleanup(encoder);
+	kfree(encoder);
+}
+
+static const struct drm_encoder_funcs
+nv50_pior_func = {
+	.destroy = nv50_pior_destroy,
+};
+
+static int
+nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe)
+{
+	struct nouveau_drm *drm = nouveau_drm(connector->dev);
+	struct nvkm_i2c *i2c = nvxx_i2c(&drm->client.device);
+	struct nvkm_i2c_bus *bus = NULL;
+	struct nvkm_i2c_aux *aux = NULL;
+	struct i2c_adapter *ddc;
+	struct nouveau_encoder *nv_encoder;
+	struct drm_encoder *encoder;
+	int type;
+
+	switch (dcbe->type) {
+	case DCB_OUTPUT_TMDS:
+		bus  = nvkm_i2c_bus_find(i2c, NVKM_I2C_BUS_EXT(dcbe->extdev));
+		ddc  = bus ? &bus->i2c : NULL;
+		type = DRM_MODE_ENCODER_TMDS;
+		break;
+	case DCB_OUTPUT_DP:
+		aux  = nvkm_i2c_aux_find(i2c, NVKM_I2C_AUX_EXT(dcbe->extdev));
+		ddc  = aux ? &aux->i2c : NULL;
+		type = DRM_MODE_ENCODER_TMDS;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	nv_encoder = kzalloc(sizeof(*nv_encoder), GFP_KERNEL);
+	if (!nv_encoder)
+		return -ENOMEM;
+	nv_encoder->dcb = dcbe;
+	nv_encoder->i2c = ddc;
+	nv_encoder->aux = aux;
+
+	encoder = to_drm_encoder(nv_encoder);
+	encoder->possible_crtcs = dcbe->heads;
+	encoder->possible_clones = 0;
+	drm_encoder_init(connector->dev, encoder, &nv50_pior_func, type,
+			 "pior-%04x-%04x", dcbe->hasht, dcbe->hashm);
+	drm_encoder_helper_add(encoder, &nv50_pior_help);
+
+	drm_mode_connector_attach_encoder(connector, encoder);
+	return 0;
+}
+
+/******************************************************************************
+ * Atomic
+ *****************************************************************************/
+
+static void
+nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock)
+{
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	struct nv50_core *core = disp->core;
+	struct nv50_mstm *mstm;
+	struct drm_encoder *encoder;
+
+	NV_ATOMIC(drm, "commit core %08x\n", interlock[NV50_DISP_INTERLOCK_BASE]);
+
+	drm_for_each_encoder(encoder, drm->dev) {
+		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
+			mstm = nouveau_encoder(encoder)->dp.mstm;
+			if (mstm && mstm->modified)
+				nv50_mstm_prepare(mstm);
+		}
+	}
+
+	core->func->ntfy_init(disp->sync, NV50_DISP_CORE_NTFY);
+	core->func->update(core, interlock, true);
+	if (core->func->ntfy_wait_done(disp->sync, NV50_DISP_CORE_NTFY,
+				       disp->core->chan.base.device))
+		NV_ERROR(drm, "core notifier timeout\n");
+
+	drm_for_each_encoder(encoder, drm->dev) {
+		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
+			mstm = nouveau_encoder(encoder)->dp.mstm;
+			if (mstm && mstm->modified)
+				nv50_mstm_cleanup(mstm);
+		}
+	}
+}
+
+static void
+nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
+{
+	struct drm_device *dev = state->dev;
+	struct drm_crtc_state *new_crtc_state, *old_crtc_state;
+	struct drm_crtc *crtc;
+	struct drm_plane_state *new_plane_state;
+	struct drm_plane *plane;
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nv50_disp *disp = nv50_disp(dev);
+	struct nv50_atom *atom = nv50_atom(state);
+	struct nv50_outp_atom *outp, *outt;
+	u32 interlock[NV50_DISP_INTERLOCK__SIZE] = {};
+	int i;
+
+	NV_ATOMIC(drm, "commit %d %d\n", atom->lock_core, atom->flush_disable);
+	drm_atomic_helper_wait_for_fences(dev, state, false);
+	drm_atomic_helper_wait_for_dependencies(state);
+	drm_atomic_helper_update_legacy_modeset_state(dev, state);
+
+	if (atom->lock_core)
+		mutex_lock(&disp->mutex);
+
+	/* Disable head(s). */
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		struct nv50_head_atom *asyh = nv50_head_atom(new_crtc_state);
+		struct nv50_head *head = nv50_head(crtc);
+
+		NV_ATOMIC(drm, "%s: clr %04x (set %04x)\n", crtc->name,
+			  asyh->clr.mask, asyh->set.mask);
+		if (old_crtc_state->active && !new_crtc_state->active)
+			drm_crtc_vblank_off(crtc);
+
+		if (asyh->clr.mask) {
+			nv50_head_flush_clr(head, asyh, atom->flush_disable);
+			interlock[NV50_DISP_INTERLOCK_CORE] |= 1;
+		}
+	}
+
+	/* Disable plane(s). */
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+
+		NV_ATOMIC(drm, "%s: clr %02x (set %02x)\n", plane->name,
+			  asyw->clr.mask, asyw->set.mask);
+		if (!asyw->clr.mask)
+			continue;
+
+		nv50_wndw_flush_clr(wndw, interlock, atom->flush_disable, asyw);
+	}
+
+	/* Disable output path(s). */
+	list_for_each_entry(outp, &atom->outp, head) {
+		const struct drm_encoder_helper_funcs *help;
+		struct drm_encoder *encoder;
+
+		encoder = outp->encoder;
+		help = encoder->helper_private;
+
+		NV_ATOMIC(drm, "%s: clr %02x (set %02x)\n", encoder->name,
+			  outp->clr.mask, outp->set.mask);
+
+		if (outp->clr.mask) {
+			help->disable(encoder);
+			interlock[NV50_DISP_INTERLOCK_CORE] |= 1;
+			if (outp->flush_disable) {
+				nv50_disp_atomic_commit_core(drm, interlock);
+				memset(interlock, 0x00, sizeof(interlock));
+			}
+		}
+	}
+
+	/* Flush disable. */
+	if (interlock[NV50_DISP_INTERLOCK_CORE]) {
+		if (atom->flush_disable) {
+			for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+				struct nv50_wndw *wndw = nv50_wndw(plane);
+				if (interlock[wndw->interlock.type] & wndw->interlock.data) {
+					if (wndw->func->update)
+						wndw->func->update(wndw, interlock);
+				}
+			}
+
+			nv50_disp_atomic_commit_core(drm, interlock);
+			memset(interlock, 0x00, sizeof(interlock));
+		}
+	}
+
+	/* Update output path(s). */
+	list_for_each_entry_safe(outp, outt, &atom->outp, head) {
+		const struct drm_encoder_helper_funcs *help;
+		struct drm_encoder *encoder;
+
+		encoder = outp->encoder;
+		help = encoder->helper_private;
+
+		NV_ATOMIC(drm, "%s: set %02x (clr %02x)\n", encoder->name,
+			  outp->set.mask, outp->clr.mask);
+
+		if (outp->set.mask) {
+			help->enable(encoder);
+			interlock[NV50_DISP_INTERLOCK_CORE] = 1;
+		}
+
+		list_del(&outp->head);
+		kfree(outp);
+	}
+
+	/* Update head(s). */
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		struct nv50_head_atom *asyh = nv50_head_atom(new_crtc_state);
+		struct nv50_head *head = nv50_head(crtc);
+
+		NV_ATOMIC(drm, "%s: set %04x (clr %04x)\n", crtc->name,
+			  asyh->set.mask, asyh->clr.mask);
+
+		if (asyh->set.mask) {
+			nv50_head_flush_set(head, asyh);
+			interlock[NV50_DISP_INTERLOCK_CORE] = 1;
+		}
+
+		if (new_crtc_state->active) {
+			if (!old_crtc_state->active)
+				drm_crtc_vblank_on(crtc);
+			if (new_crtc_state->event)
+				drm_crtc_vblank_get(crtc);
+		}
+	}
+
+	/* Update plane(s). */
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+
+		NV_ATOMIC(drm, "%s: set %02x (clr %02x)\n", plane->name,
+			  asyw->set.mask, asyw->clr.mask);
+		if ( !asyw->set.mask &&
+		    (!asyw->clr.mask || atom->flush_disable))
+			continue;
+
+		nv50_wndw_flush_set(wndw, interlock, asyw);
+	}
+
+	/* Flush update. */
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+		if (interlock[wndw->interlock.type] & wndw->interlock.data) {
+			if (wndw->func->update)
+				wndw->func->update(wndw, interlock);
+		}
+	}
+
+	if (interlock[NV50_DISP_INTERLOCK_CORE]) {
+		if (interlock[NV50_DISP_INTERLOCK_BASE] ||
+		    !atom->state.legacy_cursor_update)
+			nv50_disp_atomic_commit_core(drm, interlock);
+		else
+			disp->core->func->update(disp->core, interlock, false);
+	}
+
+	if (atom->lock_core)
+		mutex_unlock(&disp->mutex);
+
+	/* Wait for HW to signal completion. */
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+		int ret = nv50_wndw_wait_armed(wndw, asyw);
+		if (ret)
+			NV_ERROR(drm, "%s: timeout\n", plane->name);
+	}
+
+	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (new_crtc_state->event) {
+			unsigned long flags;
+			/* Get correct count/ts if racing with vblank irq */
+			if (new_crtc_state->active)
+				drm_crtc_accurate_vblank_count(crtc);
+			spin_lock_irqsave(&crtc->dev->event_lock, flags);
+			drm_crtc_send_vblank_event(crtc, new_crtc_state->event);
+			spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
+			new_crtc_state->event = NULL;
+			if (new_crtc_state->active)
+				drm_crtc_vblank_put(crtc);
+		}
+	}
+
+	drm_atomic_helper_commit_hw_done(state);
+	drm_atomic_helper_cleanup_planes(dev, state);
+	drm_atomic_helper_commit_cleanup_done(state);
+	drm_atomic_state_put(state);
+}
+
+static void
+nv50_disp_atomic_commit_work(struct work_struct *work)
+{
+	struct drm_atomic_state *state =
+		container_of(work, typeof(*state), commit_work);
+	nv50_disp_atomic_commit_tail(state);
+}
+
+static int
+nv50_disp_atomic_commit(struct drm_device *dev,
+			struct drm_atomic_state *state, bool nonblock)
+{
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct drm_plane_state *new_plane_state;
+	struct drm_plane *plane;
+	struct drm_crtc *crtc;
+	bool active = false;
+	int ret, i;
+
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0 && ret != -EACCES)
+		return ret;
+
+	ret = drm_atomic_helper_setup_commit(state, nonblock);
+	if (ret)
+		goto done;
+
+	INIT_WORK(&state->commit_work, nv50_disp_atomic_commit_work);
+
+	ret = drm_atomic_helper_prepare_planes(dev, state);
+	if (ret)
+		goto done;
+
+	if (!nonblock) {
+		ret = drm_atomic_helper_wait_for_fences(dev, state, true);
+		if (ret)
+			goto err_cleanup;
+	}
+
+	ret = drm_atomic_helper_swap_state(state, true);
+	if (ret)
+		goto err_cleanup;
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+
+		if (asyw->set.image)
+			nv50_wndw_ntfy_enable(wndw, asyw);
+	}
+
+	drm_atomic_state_get(state);
+
+	if (nonblock)
+		queue_work(system_unbound_wq, &state->commit_work);
+	else
+		nv50_disp_atomic_commit_tail(state);
+
+	drm_for_each_crtc(crtc, dev) {
+		if (crtc->state->enable) {
+			if (!drm->have_disp_power_ref) {
+				drm->have_disp_power_ref = true;
+				return 0;
+			}
+			active = true;
+			break;
+		}
+	}
+
+	if (!active && drm->have_disp_power_ref) {
+		pm_runtime_put_autosuspend(dev->dev);
+		drm->have_disp_power_ref = false;
+	}
+
+err_cleanup:
+	if (ret)
+		drm_atomic_helper_cleanup_planes(dev, state);
+done:
+	pm_runtime_put_autosuspend(dev->dev);
+	return ret;
+}
+
+static struct nv50_outp_atom *
+nv50_disp_outp_atomic_add(struct nv50_atom *atom, struct drm_encoder *encoder)
+{
+	struct nv50_outp_atom *outp;
+
+	list_for_each_entry(outp, &atom->outp, head) {
+		if (outp->encoder == encoder)
+			return outp;
+	}
+
+	outp = kzalloc(sizeof(*outp), GFP_KERNEL);
+	if (!outp)
+		return ERR_PTR(-ENOMEM);
+
+	list_add(&outp->head, &atom->outp);
+	outp->encoder = encoder;
+	return outp;
+}
+
+static int
+nv50_disp_outp_atomic_check_clr(struct nv50_atom *atom,
+				struct drm_connector_state *old_connector_state)
+{
+	struct drm_encoder *encoder = old_connector_state->best_encoder;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_crtc *crtc;
+	struct nv50_outp_atom *outp;
+
+	if (!(crtc = old_connector_state->crtc))
+		return 0;
+
+	old_crtc_state = drm_atomic_get_old_crtc_state(&atom->state, crtc);
+	new_crtc_state = drm_atomic_get_new_crtc_state(&atom->state, crtc);
+	if (old_crtc_state->active && drm_atomic_crtc_needs_modeset(new_crtc_state)) {
+		outp = nv50_disp_outp_atomic_add(atom, encoder);
+		if (IS_ERR(outp))
+			return PTR_ERR(outp);
+
+		if (outp->encoder->encoder_type == DRM_MODE_ENCODER_DPMST) {
+			outp->flush_disable = true;
+			atom->flush_disable = true;
+		}
+		outp->clr.ctrl = true;
+		atom->lock_core = true;
+	}
+
+	return 0;
+}
+
+static int
+nv50_disp_outp_atomic_check_set(struct nv50_atom *atom,
+				struct drm_connector_state *connector_state)
+{
+	struct drm_encoder *encoder = connector_state->best_encoder;
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_crtc *crtc;
+	struct nv50_outp_atom *outp;
+
+	if (!(crtc = connector_state->crtc))
+		return 0;
+
+	new_crtc_state = drm_atomic_get_new_crtc_state(&atom->state, crtc);
+	if (new_crtc_state->active && drm_atomic_crtc_needs_modeset(new_crtc_state)) {
+		outp = nv50_disp_outp_atomic_add(atom, encoder);
+		if (IS_ERR(outp))
+			return PTR_ERR(outp);
+
+		outp->set.ctrl = true;
+		atom->lock_core = true;
+	}
+
+	return 0;
+}
+
+static int
+nv50_disp_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
+{
+	struct nv50_atom *atom = nv50_atom(state);
+	struct drm_connector_state *old_connector_state, *new_connector_state;
+	struct drm_connector *connector;
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_crtc *crtc;
+	int ret, i;
+
+	/* We need to handle colour management on a per-plane basis. */
+	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (new_crtc_state->color_mgmt_changed) {
+			ret = drm_atomic_add_affected_planes(state, crtc);
+			if (ret)
+				return ret;
+		}
+	}
+
+	ret = drm_atomic_helper_check(dev, state);
+	if (ret)
+		return ret;
+
+	for_each_oldnew_connector_in_state(state, connector, old_connector_state, new_connector_state, i) {
+		ret = nv50_disp_outp_atomic_check_clr(atom, old_connector_state);
+		if (ret)
+			return ret;
+
+		ret = nv50_disp_outp_atomic_check_set(atom, new_connector_state);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void
+nv50_disp_atomic_state_clear(struct drm_atomic_state *state)
+{
+	struct nv50_atom *atom = nv50_atom(state);
+	struct nv50_outp_atom *outp, *outt;
+
+	list_for_each_entry_safe(outp, outt, &atom->outp, head) {
+		list_del(&outp->head);
+		kfree(outp);
+	}
+
+	drm_atomic_state_default_clear(state);
+}
+
+static void
+nv50_disp_atomic_state_free(struct drm_atomic_state *state)
+{
+	struct nv50_atom *atom = nv50_atom(state);
+	drm_atomic_state_default_release(&atom->state);
+	kfree(atom);
+}
+
+static struct drm_atomic_state *
+nv50_disp_atomic_state_alloc(struct drm_device *dev)
+{
+	struct nv50_atom *atom;
+	if (!(atom = kzalloc(sizeof(*atom), GFP_KERNEL)) ||
+	    drm_atomic_state_init(dev, &atom->state) < 0) {
+		kfree(atom);
+		return NULL;
+	}
+	INIT_LIST_HEAD(&atom->outp);
+	return &atom->state;
+}
+
+static const struct drm_mode_config_funcs
+nv50_disp_func = {
+	.fb_create = nouveau_user_framebuffer_create,
+	.output_poll_changed = drm_fb_helper_output_poll_changed,
+	.atomic_check = nv50_disp_atomic_check,
+	.atomic_commit = nv50_disp_atomic_commit,
+	.atomic_state_alloc = nv50_disp_atomic_state_alloc,
+	.atomic_state_clear = nv50_disp_atomic_state_clear,
+	.atomic_state_free = nv50_disp_atomic_state_free,
+};
+
+/******************************************************************************
+ * Init
+ *****************************************************************************/
+
+void
+nv50_display_fini(struct drm_device *dev)
+{
+	struct nouveau_encoder *nv_encoder;
+	struct drm_encoder *encoder;
+	struct drm_plane *plane;
+
+	drm_for_each_plane(plane, dev) {
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+		if (plane->funcs != &nv50_wndw)
+			continue;
+		nv50_wndw_fini(wndw);
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
+			nv_encoder = nouveau_encoder(encoder);
+			nv50_mstm_fini(nv_encoder->dp.mstm);
+		}
+	}
+}
+
+int
+nv50_display_init(struct drm_device *dev)
+{
+	struct nv50_core *core = nv50_disp(dev)->core;
+	struct drm_encoder *encoder;
+	struct drm_plane *plane;
+
+	core->func->init(core);
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
+			struct nouveau_encoder *nv_encoder =
+				nouveau_encoder(encoder);
+			nv50_mstm_init(nv_encoder->dp.mstm);
+		}
+	}
+
+	drm_for_each_plane(plane, dev) {
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+		if (plane->funcs != &nv50_wndw)
+			continue;
+		nv50_wndw_init(wndw);
+	}
+
+	return 0;
+}
+
+void
+nv50_display_destroy(struct drm_device *dev)
+{
+	struct nv50_disp *disp = nv50_disp(dev);
+
+	nv50_core_del(&disp->core);
+
+	nouveau_bo_unmap(disp->sync);
+	if (disp->sync)
+		nouveau_bo_unpin(disp->sync);
+	nouveau_bo_ref(NULL, &disp->sync);
+
+	nouveau_display(dev)->priv = NULL;
+	kfree(disp);
+}
+
+MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)");
+static int nouveau_atomic = 0;
+module_param_named(atomic, nouveau_atomic, int, 0400);
+
+int
+nv50_display_create(struct drm_device *dev)
+{
+	struct nvif_device *device = &nouveau_drm(dev)->client.device;
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct dcb_table *dcb = &drm->vbios.dcb;
+	struct drm_connector *connector, *tmp;
+	struct nv50_disp *disp;
+	struct dcb_output *dcbe;
+	int crtcs, ret, i;
+
+	disp = kzalloc(sizeof(*disp), GFP_KERNEL);
+	if (!disp)
+		return -ENOMEM;
+
+	mutex_init(&disp->mutex);
+
+	nouveau_display(dev)->priv = disp;
+	nouveau_display(dev)->dtor = nv50_display_destroy;
+	nouveau_display(dev)->init = nv50_display_init;
+	nouveau_display(dev)->fini = nv50_display_fini;
+	disp->disp = &nouveau_display(dev)->disp;
+	dev->mode_config.funcs = &nv50_disp_func;
+	dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP;
+	if (nouveau_atomic)
+		dev->driver->driver_features |= DRIVER_ATOMIC;
+
+	/* small shared memory area we use for notifiers and semaphores */
+	ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM,
+			     0, 0x0000, NULL, NULL, &disp->sync);
+	if (!ret) {
+		ret = nouveau_bo_pin(disp->sync, TTM_PL_FLAG_VRAM, true);
+		if (!ret) {
+			ret = nouveau_bo_map(disp->sync);
+			if (ret)
+				nouveau_bo_unpin(disp->sync);
+		}
+		if (ret)
+			nouveau_bo_ref(NULL, &disp->sync);
+	}
+
+	if (ret)
+		goto out;
+
+	/* allocate master evo channel */
+	ret = nv50_core_new(drm, &disp->core);
+	if (ret)
+		goto out;
+
+	/* create crtc objects to represent the hw heads */
+	if (disp->disp->object.oclass >= GV100_DISP)
+		crtcs = nvif_rd32(&device->object, 0x610060) & 0xff;
+	else
+	if (disp->disp->object.oclass >= GF110_DISP)
+		crtcs = nvif_rd32(&device->object, 0x612004) & 0xf;
+	else
+		crtcs = 0x3;
+
+	for (i = 0; i < fls(crtcs); i++) {
+		if (!(crtcs & (1 << i)))
+			continue;
+		ret = nv50_head_create(dev, i);
+		if (ret)
+			goto out;
+	}
+
+	/* create encoder/connector objects based on VBIOS DCB table */
+	for (i = 0, dcbe = &dcb->entry[0]; i < dcb->entries; i++, dcbe++) {
+		connector = nouveau_connector_create(dev, dcbe->connector);
+		if (IS_ERR(connector))
+			continue;
+
+		if (dcbe->location == DCB_LOC_ON_CHIP) {
+			switch (dcbe->type) {
+			case DCB_OUTPUT_TMDS:
+			case DCB_OUTPUT_LVDS:
+			case DCB_OUTPUT_DP:
+				ret = nv50_sor_create(connector, dcbe);
+				break;
+			case DCB_OUTPUT_ANALOG:
+				ret = nv50_dac_create(connector, dcbe);
+				break;
+			default:
+				ret = -ENODEV;
+				break;
+			}
+		} else {
+			ret = nv50_pior_create(connector, dcbe);
+		}
+
+		if (ret) {
+			NV_WARN(drm, "failed to create encoder %d/%d/%d: %d\n",
+				     dcbe->location, dcbe->type,
+				     ffs(dcbe->or) - 1, ret);
+			ret = 0;
+		}
+	}
+
+	/* cull any connectors we created that don't have an encoder */
+	list_for_each_entry_safe(connector, tmp, &dev->mode_config.connector_list, head) {
+		if (connector->encoder_ids[0])
+			continue;
+
+		NV_WARN(drm, "%s has no encoders, removing\n",
+			connector->name);
+		connector->funcs->destroy(connector);
+	}
+
+out:
+	if (ret)
+		nv50_display_destroy(dev);
+	return ret;
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
new file mode 100644
index 000000000000..e48c5eb35b49
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -0,0 +1,89 @@
+#ifndef __NV50_KMS_H__
+#define __NV50_KMS_H__
+#include <nvif/mem.h>
+
+#include "nouveau_display.h"
+
+struct nv50_disp {
+	struct nvif_disp *disp;
+	struct nv50_core *core;
+
+#define NV50_DISP_SYNC(c, o)                                ((c) * 0x040 + (o))
+#define NV50_DISP_CORE_NTFY                       NV50_DISP_SYNC(0      , 0x00)
+#define NV50_DISP_WNDW_SEM0(c)                    NV50_DISP_SYNC(1 + (c), 0x00)
+#define NV50_DISP_WNDW_SEM1(c)                    NV50_DISP_SYNC(1 + (c), 0x10)
+#define NV50_DISP_WNDW_NTFY(c)                    NV50_DISP_SYNC(1 + (c), 0x20)
+#define NV50_DISP_BASE_SEM0(c)                    NV50_DISP_WNDW_SEM0(0 + (c))
+#define NV50_DISP_BASE_SEM1(c)                    NV50_DISP_WNDW_SEM1(0 + (c))
+#define NV50_DISP_BASE_NTFY(c)                    NV50_DISP_WNDW_NTFY(0 + (c))
+#define NV50_DISP_OVLY_SEM0(c)                    NV50_DISP_WNDW_SEM0(4 + (c))
+#define NV50_DISP_OVLY_SEM1(c)                    NV50_DISP_WNDW_SEM1(4 + (c))
+#define NV50_DISP_OVLY_NTFY(c)                    NV50_DISP_WNDW_NTFY(4 + (c))
+	struct nouveau_bo *sync;
+
+	struct mutex mutex;
+};
+
+static inline struct nv50_disp *
+nv50_disp(struct drm_device *dev)
+{
+	return nouveau_display(dev)->priv;
+}
+
+struct nv50_disp_interlock {
+	enum nv50_disp_interlock_type {
+		NV50_DISP_INTERLOCK_CORE = 0,
+		NV50_DISP_INTERLOCK_CURS,
+		NV50_DISP_INTERLOCK_BASE,
+		NV50_DISP_INTERLOCK_OVLY,
+		NV50_DISP_INTERLOCK_WNDW,
+		NV50_DISP_INTERLOCK_WIMM,
+		NV50_DISP_INTERLOCK__SIZE
+	} type;
+	u32 data;
+};
+
+void corec37d_ntfy_init(struct nouveau_bo *, u32);
+
+struct nv50_chan {
+	struct nvif_object user;
+	struct nvif_device *device;
+};
+
+struct nv50_dmac {
+	struct nv50_chan base;
+
+	struct nvif_mem push;
+	u32 *ptr;
+
+	struct nvif_object sync;
+	struct nvif_object vram;
+
+	/* Protects against concurrent pushbuf access to this channel, lock is
+	 * grabbed by evo_wait (if the pushbuf reservation is successful) and
+	 * dropped again by evo_kick. */
+	struct mutex lock;
+};
+
+int nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
+		     const s32 *oclass, u8 head, void *data, u32 size,
+		     u64 syncbuf, struct nv50_dmac *dmac);
+void nv50_dmac_destroy(struct nv50_dmac *);
+
+u32 *evo_wait(struct nv50_dmac *, int nr);
+void evo_kick(u32 *, struct nv50_dmac *);
+
+#define evo_mthd(p, m, s) do {						\
+	const u32 _m = (m), _s = (s);					\
+	if (drm_debug & DRM_UT_KMS)					\
+		pr_err("%04x %d %s\n", _m, _s, __func__);		\
+	*((p)++) = ((_s << 18) | _m);					\
+} while(0)
+
+#define evo_data(p, d) do {						\
+	const u32 _d = (d);						\
+	if (drm_debug & DRM_UT_KMS)					\
+		pr_err("\t%08x\n", _d);					\
+	*((p)++) = _d;							\
+} while(0)
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c
new file mode 100644
index 000000000000..4f57e5379796
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.c
@@ -0,0 +1,511 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "head.h"
+#include "base.h"
+#include "core.h"
+#include "curs.h"
+#include "ovly.h"
+
+#include <nvif/class.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include "nouveau_connector.h"
+void
+nv50_head_flush_clr(struct nv50_head *head,
+		    struct nv50_head_atom *asyh, bool flush)
+{
+	union nv50_head_atom_mask clr = {
+		.mask = asyh->clr.mask & ~(flush ? 0 : asyh->set.mask),
+	};
+	if (clr.olut) head->func->olut_clr(head);
+	if (clr.core) head->func->core_clr(head);
+	if (clr.curs) head->func->curs_clr(head);
+}
+
+void
+nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	if (asyh->set.view   ) head->func->view    (head, asyh);
+	if (asyh->set.mode   ) head->func->mode    (head, asyh);
+	if (asyh->set.core   ) head->func->core_set(head, asyh);
+	if (asyh->set.olut   ) {
+		asyh->olut.offset = nv50_lut_load(&head->olut,
+						  asyh->olut.mode <= 1,
+						  asyh->olut.buffer,
+						  asyh->state.gamma_lut);
+		head->func->olut_set(head, asyh);
+	}
+	if (asyh->set.curs   ) head->func->curs_set(head, asyh);
+	if (asyh->set.base   ) head->func->base    (head, asyh);
+	if (asyh->set.ovly   ) head->func->ovly    (head, asyh);
+	if (asyh->set.dither ) head->func->dither  (head, asyh);
+	if (asyh->set.procamp) head->func->procamp (head, asyh);
+	if (asyh->set.or     ) head->func->or      (head, asyh);
+}
+
+static void
+nv50_head_atomic_check_procamp(struct nv50_head_atom *armh,
+			       struct nv50_head_atom *asyh,
+			       struct nouveau_conn_atom *asyc)
+{
+	const int vib = asyc->procamp.color_vibrance - 100;
+	const int hue = asyc->procamp.vibrant_hue - 90;
+	const int adj = (vib > 0) ? 50 : 0;
+	asyh->procamp.sat.cos = ((vib * 2047 + adj) / 100) & 0xfff;
+	asyh->procamp.sat.sin = ((hue * 2047) / 100) & 0xfff;
+	asyh->set.procamp = true;
+}
+
+static void
+nv50_head_atomic_check_dither(struct nv50_head_atom *armh,
+			      struct nv50_head_atom *asyh,
+			      struct nouveau_conn_atom *asyc)
+{
+	struct drm_connector *connector = asyc->state.connector;
+	u32 mode = 0x00;
+
+	if (asyc->dither.mode == DITHERING_MODE_AUTO) {
+		if (asyh->base.depth > connector->display_info.bpc * 3)
+			mode = DITHERING_MODE_DYNAMIC2X2;
+	} else {
+		mode = asyc->dither.mode;
+	}
+
+	if (asyc->dither.depth == DITHERING_DEPTH_AUTO) {
+		if (connector->display_info.bpc >= 8)
+			mode |= DITHERING_DEPTH_8BPC;
+	} else {
+		mode |= asyc->dither.depth;
+	}
+
+	asyh->dither.enable = mode;
+	asyh->dither.bits = mode >> 1;
+	asyh->dither.mode = mode >> 3;
+	asyh->set.dither = true;
+}
+
+static void
+nv50_head_atomic_check_view(struct nv50_head_atom *armh,
+			    struct nv50_head_atom *asyh,
+			    struct nouveau_conn_atom *asyc)
+{
+	struct drm_connector *connector = asyc->state.connector;
+	struct drm_display_mode *omode = &asyh->state.adjusted_mode;
+	struct drm_display_mode *umode = &asyh->state.mode;
+	int mode = asyc->scaler.mode;
+	struct edid *edid;
+	int umode_vdisplay, omode_hdisplay, omode_vdisplay;
+
+	if (connector->edid_blob_ptr)
+		edid = (struct edid *)connector->edid_blob_ptr->data;
+	else
+		edid = NULL;
+
+	if (!asyc->scaler.full) {
+		if (mode == DRM_MODE_SCALE_NONE)
+			omode = umode;
+	} else {
+		/* Non-EDID LVDS/eDP mode. */
+		mode = DRM_MODE_SCALE_FULLSCREEN;
+	}
+
+	/* For the user-specified mode, we must ignore doublescan and
+	 * the like, but honor frame packing.
+	 */
+	umode_vdisplay = umode->vdisplay;
+	if ((umode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
+		umode_vdisplay += umode->vtotal;
+	asyh->view.iW = umode->hdisplay;
+	asyh->view.iH = umode_vdisplay;
+	/* For the output mode, we can just use the stock helper. */
+	drm_mode_get_hv_timing(omode, &omode_hdisplay, &omode_vdisplay);
+	asyh->view.oW = omode_hdisplay;
+	asyh->view.oH = omode_vdisplay;
+
+	/* Add overscan compensation if necessary, will keep the aspect
+	 * ratio the same as the backend mode unless overridden by the
+	 * user setting both hborder and vborder properties.
+	 */
+	if ((asyc->scaler.underscan.mode == UNDERSCAN_ON ||
+	    (asyc->scaler.underscan.mode == UNDERSCAN_AUTO &&
+	     drm_detect_hdmi_monitor(edid)))) {
+		u32 bX = asyc->scaler.underscan.hborder;
+		u32 bY = asyc->scaler.underscan.vborder;
+		u32 r = (asyh->view.oH << 19) / asyh->view.oW;
+
+		if (bX) {
+			asyh->view.oW -= (bX * 2);
+			if (bY) asyh->view.oH -= (bY * 2);
+			else    asyh->view.oH  = ((asyh->view.oW * r) + (r / 2)) >> 19;
+		} else {
+			asyh->view.oW -= (asyh->view.oW >> 4) + 32;
+			if (bY) asyh->view.oH -= (bY * 2);
+			else    asyh->view.oH  = ((asyh->view.oW * r) + (r / 2)) >> 19;
+		}
+	}
+
+	/* Handle CENTER/ASPECT scaling, taking into account the areas
+	 * removed already for overscan compensation.
+	 */
+	switch (mode) {
+	case DRM_MODE_SCALE_CENTER:
+		asyh->view.oW = min((u16)umode->hdisplay, asyh->view.oW);
+		asyh->view.oH = min((u16)umode_vdisplay, asyh->view.oH);
+		/* fall-through */
+	case DRM_MODE_SCALE_ASPECT:
+		if (asyh->view.oH < asyh->view.oW) {
+			u32 r = (asyh->view.iW << 19) / asyh->view.iH;
+			asyh->view.oW = ((asyh->view.oH * r) + (r / 2)) >> 19;
+		} else {
+			u32 r = (asyh->view.iH << 19) / asyh->view.iW;
+			asyh->view.oH = ((asyh->view.oW * r) + (r / 2)) >> 19;
+		}
+		break;
+	default:
+		break;
+	}
+
+	asyh->set.view = true;
+}
+
+static int
+nv50_head_atomic_check_lut(struct nv50_head *head,
+			   struct nv50_head_atom *asyh)
+{
+	struct nv50_disp *disp = nv50_disp(head->base.base.dev);
+	struct drm_property_blob *olut = asyh->state.gamma_lut;
+
+	/* Determine whether core output LUT should be enabled. */
+	if (olut) {
+		/* Check if any window(s) have stolen the core output LUT
+		 * to as an input LUT for legacy gamma + I8 colour format.
+		 */
+		if (asyh->wndw.olut) {
+			/* If any window has stolen the core output LUT,
+			 * all of them must.
+			 */
+			if (asyh->wndw.olut != asyh->wndw.mask)
+				return -EINVAL;
+			olut = NULL;
+		}
+	}
+
+	if (!olut) {
+		asyh->olut.handle = 0;
+		return 0;
+	}
+
+	asyh->olut.handle = disp->core->chan.vram.handle;
+	asyh->olut.buffer = !asyh->olut.buffer;
+	head->func->olut(head, asyh);
+	return 0;
+}
+
+static void
+nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct drm_display_mode *mode = &asyh->state.adjusted_mode;
+	struct nv50_head_mode *m = &asyh->mode;
+	u32 blankus;
+
+	drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V | CRTC_STEREO_DOUBLE);
+
+	/*
+	 * DRM modes are defined in terms of a repeating interval
+	 * starting with the active display area.  The hardware modes
+	 * are defined in terms of a repeating interval starting one
+	 * unit (pixel or line) into the sync pulse.  So, add bias.
+	 */
+
+	m->h.active = mode->crtc_htotal;
+	m->h.synce  = mode->crtc_hsync_end - mode->crtc_hsync_start - 1;
+	m->h.blanke = mode->crtc_hblank_end - mode->crtc_hsync_start - 1;
+	m->h.blanks = m->h.blanke + mode->crtc_hdisplay;
+
+	m->v.active = mode->crtc_vtotal;
+	m->v.synce  = mode->crtc_vsync_end - mode->crtc_vsync_start - 1;
+	m->v.blanke = mode->crtc_vblank_end - mode->crtc_vsync_start - 1;
+	m->v.blanks = m->v.blanke + mode->crtc_vdisplay;
+
+	/*XXX: Safe underestimate, even "0" works */
+	blankus = (m->v.active - mode->crtc_vdisplay - 2) * m->h.active;
+	blankus *= 1000;
+	blankus /= mode->crtc_clock;
+	m->v.blankus = blankus;
+
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
+		m->v.blank2e =  m->v.active + m->v.blanke;
+		m->v.blank2s =  m->v.blank2e + mode->crtc_vdisplay;
+		m->v.active  = (m->v.active * 2) + 1;
+		m->interlace = true;
+	} else {
+		m->v.blank2e = 0;
+		m->v.blank2s = 1;
+		m->interlace = false;
+	}
+	m->clock = mode->crtc_clock;
+
+	asyh->or.nhsync = !!(mode->flags & DRM_MODE_FLAG_NHSYNC);
+	asyh->or.nvsync = !!(mode->flags & DRM_MODE_FLAG_NVSYNC);
+	asyh->set.or = head->func->or != NULL;
+	asyh->set.mode = true;
+}
+
+static int
+nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
+{
+	struct nouveau_drm *drm = nouveau_drm(crtc->dev);
+	struct nv50_head *head = nv50_head(crtc);
+	struct nv50_head_atom *armh = nv50_head_atom(crtc->state);
+	struct nv50_head_atom *asyh = nv50_head_atom(state);
+	struct nouveau_conn_atom *asyc = NULL;
+	struct drm_connector_state *conns;
+	struct drm_connector *conn;
+	int i;
+
+	NV_ATOMIC(drm, "%s atomic_check %d\n", crtc->name, asyh->state.active);
+	if (asyh->state.active) {
+		for_each_new_connector_in_state(asyh->state.state, conn, conns, i) {
+			if (conns->crtc == crtc) {
+				asyc = nouveau_conn_atom(conns);
+				break;
+			}
+		}
+
+		if (armh->state.active) {
+			if (asyc) {
+				if (asyh->state.mode_changed)
+					asyc->set.scaler = true;
+				if (armh->base.depth != asyh->base.depth)
+					asyc->set.dither = true;
+			}
+		} else {
+			if (asyc)
+				asyc->set.mask = ~0;
+			asyh->set.mask = ~0;
+			asyh->set.or = head->func->or != NULL;
+		}
+
+		if (asyh->state.mode_changed)
+			nv50_head_atomic_check_mode(head, asyh);
+
+		if (asyh->state.color_mgmt_changed ||
+		    memcmp(&armh->wndw, &asyh->wndw, sizeof(asyh->wndw))) {
+			int ret = nv50_head_atomic_check_lut(head, asyh);
+			if (ret)
+				return ret;
+
+			asyh->olut.visible = asyh->olut.handle != 0;
+		}
+
+		if (asyc) {
+			if (asyc->set.scaler)
+				nv50_head_atomic_check_view(armh, asyh, asyc);
+			if (asyc->set.dither)
+				nv50_head_atomic_check_dither(armh, asyh, asyc);
+			if (asyc->set.procamp)
+				nv50_head_atomic_check_procamp(armh, asyh, asyc);
+		}
+
+		if (head->func->core_calc) {
+			head->func->core_calc(head, asyh);
+			if (!asyh->core.visible)
+				asyh->olut.visible = false;
+		}
+
+		asyh->set.base = armh->base.cpp != asyh->base.cpp;
+		asyh->set.ovly = armh->ovly.cpp != asyh->ovly.cpp;
+	} else {
+		asyh->olut.visible = false;
+		asyh->core.visible = false;
+		asyh->curs.visible = false;
+		asyh->base.cpp = 0;
+		asyh->ovly.cpp = 0;
+	}
+
+	if (!drm_atomic_crtc_needs_modeset(&asyh->state)) {
+		if (asyh->core.visible) {
+			if (memcmp(&armh->core, &asyh->core, sizeof(asyh->core)))
+				asyh->set.core = true;
+		} else
+		if (armh->core.visible) {
+			asyh->clr.core = true;
+		}
+
+		if (asyh->curs.visible) {
+			if (memcmp(&armh->curs, &asyh->curs, sizeof(asyh->curs)))
+				asyh->set.curs = true;
+		} else
+		if (armh->curs.visible) {
+			asyh->clr.curs = true;
+		}
+
+		if (asyh->olut.visible) {
+			if (memcmp(&armh->olut, &asyh->olut, sizeof(asyh->olut)))
+				asyh->set.olut = true;
+		} else
+		if (armh->olut.visible) {
+			asyh->clr.olut = true;
+		}
+	} else {
+		asyh->clr.olut = armh->olut.visible;
+		asyh->clr.core = armh->core.visible;
+		asyh->clr.curs = armh->curs.visible;
+		asyh->set.olut = asyh->olut.visible;
+		asyh->set.core = asyh->core.visible;
+		asyh->set.curs = asyh->curs.visible;
+	}
+
+	if (asyh->clr.mask || asyh->set.mask)
+		nv50_atom(asyh->state.state)->lock_core = true;
+	return 0;
+}
+
+static const struct drm_crtc_helper_funcs
+nv50_head_help = {
+	.atomic_check = nv50_head_atomic_check,
+};
+
+static void
+nv50_head_atomic_destroy_state(struct drm_crtc *crtc,
+			       struct drm_crtc_state *state)
+{
+	struct nv50_head_atom *asyh = nv50_head_atom(state);
+	__drm_atomic_helper_crtc_destroy_state(&asyh->state);
+	kfree(asyh);
+}
+
+static struct drm_crtc_state *
+nv50_head_atomic_duplicate_state(struct drm_crtc *crtc)
+{
+	struct nv50_head_atom *armh = nv50_head_atom(crtc->state);
+	struct nv50_head_atom *asyh;
+	if (!(asyh = kmalloc(sizeof(*asyh), GFP_KERNEL)))
+		return NULL;
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &asyh->state);
+	asyh->wndw = armh->wndw;
+	asyh->view = armh->view;
+	asyh->mode = armh->mode;
+	asyh->olut = armh->olut;
+	asyh->core = armh->core;
+	asyh->curs = armh->curs;
+	asyh->base = armh->base;
+	asyh->ovly = armh->ovly;
+	asyh->dither = armh->dither;
+	asyh->procamp = armh->procamp;
+	asyh->clr.mask = 0;
+	asyh->set.mask = 0;
+	return &asyh->state;
+}
+
+static void
+__drm_atomic_helper_crtc_reset(struct drm_crtc *crtc,
+			       struct drm_crtc_state *state)
+{
+	if (crtc->state)
+		crtc->funcs->atomic_destroy_state(crtc, crtc->state);
+	crtc->state = state;
+	crtc->state->crtc = crtc;
+}
+
+static void
+nv50_head_reset(struct drm_crtc *crtc)
+{
+	struct nv50_head_atom *asyh;
+
+	if (WARN_ON(!(asyh = kzalloc(sizeof(*asyh), GFP_KERNEL))))
+		return;
+
+	__drm_atomic_helper_crtc_reset(crtc, &asyh->state);
+}
+
+static void
+nv50_head_destroy(struct drm_crtc *crtc)
+{
+	struct nv50_head *head = nv50_head(crtc);
+	nv50_lut_fini(&head->olut);
+	drm_crtc_cleanup(crtc);
+	kfree(head);
+}
+
+static const struct drm_crtc_funcs
+nv50_head_func = {
+	.reset = nv50_head_reset,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
+	.destroy = nv50_head_destroy,
+	.set_config = drm_atomic_helper_set_config,
+	.page_flip = drm_atomic_helper_page_flip,
+	.atomic_duplicate_state = nv50_head_atomic_duplicate_state,
+	.atomic_destroy_state = nv50_head_atomic_destroy_state,
+};
+
+int
+nv50_head_create(struct drm_device *dev, int index)
+{
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nv50_disp *disp = nv50_disp(dev);
+	struct nv50_head *head;
+	struct nv50_wndw *curs, *wndw;
+	struct drm_crtc *crtc;
+	int ret;
+
+	head = kzalloc(sizeof(*head), GFP_KERNEL);
+	if (!head)
+		return -ENOMEM;
+
+	head->func = disp->core->func->head;
+	head->base.index = index;
+
+	if (disp->disp->object.oclass < GV100_DISP) {
+		ret = nv50_ovly_new(drm, head->base.index, &wndw);
+		ret = nv50_base_new(drm, head->base.index, &wndw);
+	} else {
+		ret = nv50_wndw_new(drm, DRM_PLANE_TYPE_OVERLAY,
+				    head->base.index * 2 + 1, &wndw);
+		ret = nv50_wndw_new(drm, DRM_PLANE_TYPE_PRIMARY,
+				    head->base.index * 2 + 0, &wndw);
+	}
+	if (ret == 0)
+		ret = nv50_curs_new(drm, head->base.index, &curs);
+	if (ret) {
+		kfree(head);
+		return ret;
+	}
+
+	crtc = &head->base.base;
+	drm_crtc_init_with_planes(dev, crtc, &wndw->plane, &curs->plane,
+				  &nv50_head_func, "head-%d", head->base.index);
+	drm_crtc_helper_add(crtc, &nv50_head_help);
+	drm_mode_crtc_set_gamma_size(crtc, 256);
+
+	if (head->func->olut_set) {
+		ret = nv50_lut_init(disp, &drm->client.mmu, &head->olut);
+		if (ret)
+			goto out;
+	}
+
+out:
+	if (ret)
+		nv50_head_destroy(crtc);
+	return ret;
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.h b/drivers/gpu/drm/nouveau/dispnv50/head.h
new file mode 100644
index 000000000000..37b3248c6dae
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.h
@@ -0,0 +1,78 @@
+#ifndef __NV50_KMS_HEAD_H__
+#define __NV50_KMS_HEAD_H__
+#define nv50_head(c) container_of((c), struct nv50_head, base.base)
+#include "disp.h"
+#include "atom.h"
+#include "lut.h"
+
+#include "nouveau_crtc.h"
+
+struct nv50_head {
+	const struct nv50_head_func *func;
+	struct nouveau_crtc base;
+	struct nv50_lut olut;
+};
+
+int nv50_head_create(struct drm_device *, int index);
+void nv50_head_flush_set(struct nv50_head *, struct nv50_head_atom *);
+void nv50_head_flush_clr(struct nv50_head *, struct nv50_head_atom *, bool y);
+
+struct nv50_head_func {
+	void (*view)(struct nv50_head *, struct nv50_head_atom *);
+	void (*mode)(struct nv50_head *, struct nv50_head_atom *);
+	void (*olut)(struct nv50_head *, struct nv50_head_atom *);
+	void (*olut_set)(struct nv50_head *, struct nv50_head_atom *);
+	void (*olut_clr)(struct nv50_head *);
+	void (*core_calc)(struct nv50_head *, struct nv50_head_atom *);
+	void (*core_set)(struct nv50_head *, struct nv50_head_atom *);
+	void (*core_clr)(struct nv50_head *);
+	int (*curs_layout)(struct nv50_head *, struct nv50_wndw_atom *,
+			   struct nv50_head_atom *);
+	int (*curs_format)(struct nv50_head *, struct nv50_wndw_atom *,
+			   struct nv50_head_atom *);
+	void (*curs_set)(struct nv50_head *, struct nv50_head_atom *);
+	void (*curs_clr)(struct nv50_head *);
+	void (*base)(struct nv50_head *, struct nv50_head_atom *);
+	void (*ovly)(struct nv50_head *, struct nv50_head_atom *);
+	void (*dither)(struct nv50_head *, struct nv50_head_atom *);
+	void (*procamp)(struct nv50_head *, struct nv50_head_atom *);
+	void (*or)(struct nv50_head *, struct nv50_head_atom *);
+};
+
+extern const struct nv50_head_func head507d;
+void head507d_view(struct nv50_head *, struct nv50_head_atom *);
+void head507d_mode(struct nv50_head *, struct nv50_head_atom *);
+void head507d_olut(struct nv50_head *, struct nv50_head_atom *);
+void head507d_core_calc(struct nv50_head *, struct nv50_head_atom *);
+void head507d_core_clr(struct nv50_head *);
+int head507d_curs_layout(struct nv50_head *, struct nv50_wndw_atom *,
+			 struct nv50_head_atom *);
+int head507d_curs_format(struct nv50_head *, struct nv50_wndw_atom *,
+			 struct nv50_head_atom *);
+void head507d_base(struct nv50_head *, struct nv50_head_atom *);
+void head507d_ovly(struct nv50_head *, struct nv50_head_atom *);
+void head507d_dither(struct nv50_head *, struct nv50_head_atom *);
+void head507d_procamp(struct nv50_head *, struct nv50_head_atom *);
+
+extern const struct nv50_head_func head827d;
+
+extern const struct nv50_head_func head907d;
+void head907d_view(struct nv50_head *, struct nv50_head_atom *);
+void head907d_mode(struct nv50_head *, struct nv50_head_atom *);
+void head907d_olut(struct nv50_head *, struct nv50_head_atom *);
+void head907d_olut_set(struct nv50_head *, struct nv50_head_atom *);
+void head907d_olut_clr(struct nv50_head *);
+void head907d_core_set(struct nv50_head *, struct nv50_head_atom *);
+void head907d_core_clr(struct nv50_head *);
+void head907d_curs_set(struct nv50_head *, struct nv50_head_atom *);
+void head907d_curs_clr(struct nv50_head *);
+void head907d_ovly(struct nv50_head *, struct nv50_head_atom *);
+void head907d_procamp(struct nv50_head *, struct nv50_head_atom *);
+void head907d_or(struct nv50_head *, struct nv50_head_atom *);
+
+extern const struct nv50_head_func head917d;
+int head917d_curs_layout(struct nv50_head *, struct nv50_wndw_atom *,
+			 struct nv50_head_atom *);
+
+extern const struct nv50_head_func headc37d;
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head507d.c b/drivers/gpu/drm/nouveau/dispnv50/head507d.c
new file mode 100644
index 000000000000..51bc5996fd37
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/head507d.c
@@ -0,0 +1,325 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "head.h"
+#include "core.h"
+
+void
+head507d_procamp(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x08a8 + (head->base.index * 0x400), 1);
+		evo_data(push, asyh->procamp.sat.sin << 20 |
+			       asyh->procamp.sat.cos << 8);
+		evo_kick(push, core);
+	}
+}
+
+void
+head507d_dither(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x08a0 + (head->base.index * 0x0400), 1);
+		evo_data(push, asyh->dither.mode << 3 |
+			       asyh->dither.bits << 1 |
+			       asyh->dither.enable);
+		evo_kick(push, core);
+	}
+}
+
+void
+head507d_ovly(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 bounds = 0;
+	u32 *push;
+
+	if (asyh->ovly.cpp) {
+		switch (asyh->ovly.cpp) {
+		case 4: bounds |= 0x00000300; break;
+		case 2: bounds |= 0x00000100; break;
+		default:
+			WARN_ON(1);
+			break;
+		}
+		bounds |= 0x00000001;
+	} else {
+		bounds |= 0x00000100;
+	}
+
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x0904 + head->base.index * 0x400, 1);
+		evo_data(push, bounds);
+		evo_kick(push, core);
+	}
+}
+
+void
+head507d_base(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 bounds = 0;
+	u32 *push;
+
+	if (asyh->base.cpp) {
+		switch (asyh->base.cpp) {
+		case 8: bounds |= 0x00000500; break;
+		case 4: bounds |= 0x00000300; break;
+		case 2: bounds |= 0x00000100; break;
+		case 1: bounds |= 0x00000000; break;
+		default:
+			WARN_ON(1);
+			break;
+		}
+		bounds |= 0x00000001;
+	}
+
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x0900 + head->base.index * 0x400, 1);
+		evo_data(push, bounds);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head507d_curs_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x0880 + head->base.index * 0x400, 1);
+		evo_data(push, 0x05000000);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head507d_curs_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 3))) {
+		evo_mthd(push, 0x0880 + head->base.index * 0x400, 2);
+		evo_data(push, 0x80000000 | asyh->curs.layout << 26 |
+					    asyh->curs.format << 24);
+		evo_data(push, asyh->curs.offset >> 8);
+		evo_kick(push, core);
+	}
+}
+
+int
+head507d_curs_format(struct nv50_head *head, struct nv50_wndw_atom *asyw,
+		     struct nv50_head_atom *asyh)
+{
+	switch (asyw->image.format) {
+	case 0xcf: asyh->curs.format = 1; break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int
+head507d_curs_layout(struct nv50_head *head, struct nv50_wndw_atom *asyw,
+		     struct nv50_head_atom *asyh)
+{
+	switch (asyw->image.w) {
+	case 32: asyh->curs.layout = 0; break;
+	case 64: asyh->curs.layout = 1; break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+void
+head507d_core_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x0874 + head->base.index * 0x400, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head507d_core_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 9))) {
+		evo_mthd(push, 0x0860 + head->base.index * 0x400, 1);
+		evo_data(push, asyh->core.offset >> 8);
+		evo_mthd(push, 0x0868 + head->base.index * 0x400, 4);
+		evo_data(push, asyh->core.h << 16 | asyh->core.w);
+		evo_data(push, asyh->core.layout << 20 |
+			       (asyh->core.pitch >> 8) << 8 |
+			       asyh->core.blocks << 8 |
+			       asyh->core.blockh);
+		evo_data(push, asyh->core.kind << 16 |
+			       asyh->core.format << 8);
+		evo_data(push, asyh->core.handle);
+		evo_mthd(push, 0x08c0 + head->base.index * 0x400, 1);
+		evo_data(push, asyh->core.y << 16 | asyh->core.x);
+		evo_kick(push, core);
+
+		/* EVO will complain with INVALID_STATE if we have an
+		 * active cursor and (re)specify HeadSetContextDmaIso
+		 * without also updating HeadSetOffsetCursor.
+		 */
+		asyh->set.curs = asyh->curs.visible;
+		asyh->set.olut = asyh->olut.handle != 0;
+	}
+}
+
+void
+head507d_core_calc(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_disp *disp = nv50_disp(head->base.base.dev);
+	if ((asyh->core.visible = (asyh->base.cpp != 0))) {
+		asyh->core.x = asyh->base.x;
+		asyh->core.y = asyh->base.y;
+		asyh->core.w = asyh->base.w;
+		asyh->core.h = asyh->base.h;
+	} else
+	if ((asyh->core.visible = (asyh->ovly.cpp != 0)) ||
+	    (asyh->core.visible = asyh->curs.visible)) {
+		/*XXX: We need to either find some way of having the
+		 *     primary base layer appear black, while still
+		 *     being able to display the other layers, or we
+		 *     need to allocate a dummy black surface here.
+		 */
+		asyh->core.x = 0;
+		asyh->core.y = 0;
+		asyh->core.w = asyh->state.mode.hdisplay;
+		asyh->core.h = asyh->state.mode.vdisplay;
+	}
+	asyh->core.handle = disp->core->chan.vram.handle;
+	asyh->core.offset = 0;
+	asyh->core.format = 0xcf;
+	asyh->core.kind = 0;
+	asyh->core.layout = 1;
+	asyh->core.blockh = 0;
+	asyh->core.blocks = 0;
+	asyh->core.pitch = ALIGN(asyh->core.w, 64) * 4;
+}
+
+static void
+head507d_olut_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x0840 + (head->base.index * 0x400), 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head507d_olut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 3))) {
+		evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2);
+		evo_data(push, 0x80000000 | asyh->olut.mode << 30);
+		evo_data(push, asyh->olut.offset >> 8);
+		evo_kick(push, core);
+	}
+}
+
+void
+head507d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	if (asyh->base.cpp == 1)
+		asyh->olut.mode = 0;
+	else
+		asyh->olut.mode = 1;
+}
+
+void
+head507d_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	struct nv50_head_mode *m = &asyh->mode;
+	u32 *push;
+	if ((push = evo_wait(core, 13))) {
+		evo_mthd(push, 0x0804 + (head->base.index * 0x400), 2);
+		evo_data(push, 0x00800000 | m->clock);
+		evo_data(push, m->interlace ? 0x00000002 : 0x00000000);
+		evo_mthd(push, 0x0810 + (head->base.index * 0x400), 7);
+		evo_data(push, 0x00000000);
+		evo_data(push, m->v.active  << 16 | m->h.active );
+		evo_data(push, m->v.synce   << 16 | m->h.synce  );
+		evo_data(push, m->v.blanke  << 16 | m->h.blanke );
+		evo_data(push, m->v.blanks  << 16 | m->h.blanks );
+		evo_data(push, m->v.blank2e << 16 | m->v.blank2s);
+		evo_data(push, asyh->mode.v.blankus);
+		evo_mthd(push, 0x082c + (head->base.index * 0x400), 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+void
+head507d_view(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 7))) {
+		evo_mthd(push, 0x08a4 + (head->base.index * 0x400), 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x08c8 + (head->base.index * 0x400), 1);
+		evo_data(push, asyh->view.iH << 16 | asyh->view.iW);
+		evo_mthd(push, 0x08d8 + (head->base.index * 0x400), 2);
+		evo_data(push, asyh->view.oH << 16 | asyh->view.oW);
+		evo_data(push, asyh->view.oH << 16 | asyh->view.oW);
+		evo_kick(push, core);
+	}
+}
+
+const struct nv50_head_func
+head507d = {
+	.view = head507d_view,
+	.mode = head507d_mode,
+	.olut = head507d_olut,
+	.olut_set = head507d_olut_set,
+	.olut_clr = head507d_olut_clr,
+	.core_calc = head507d_core_calc,
+	.core_set = head507d_core_set,
+	.core_clr = head507d_core_clr,
+	.curs_layout = head507d_curs_layout,
+	.curs_format = head507d_curs_format,
+	.curs_set = head507d_curs_set,
+	.curs_clr = head507d_curs_clr,
+	.base = head507d_base,
+	.ovly = head507d_ovly,
+	.dither = head507d_dither,
+	.procamp = head507d_procamp,
+};
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head827d.c b/drivers/gpu/drm/nouveau/dispnv50/head827d.c
new file mode 100644
index 000000000000..af5e7bd5978b
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/head827d.c
@@ -0,0 +1,124 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "head.h"
+#include "core.h"
+
+static void
+head827d_curs_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 4))) {
+		evo_mthd(push, 0x0880 + head->base.index * 0x400, 1);
+		evo_data(push, 0x05000000);
+		evo_mthd(push, 0x089c + head->base.index * 0x400, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head827d_curs_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 5))) {
+		evo_mthd(push, 0x0880 + head->base.index * 0x400, 2);
+		evo_data(push, 0x80000000 | asyh->curs.layout << 26 |
+					    asyh->curs.format << 24);
+		evo_data(push, asyh->curs.offset >> 8);
+		evo_mthd(push, 0x089c + head->base.index * 0x400, 1);
+		evo_data(push, asyh->curs.handle);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head827d_core_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 9))) {
+		evo_mthd(push, 0x0860 + head->base.index * 0x400, 1);
+		evo_data(push, asyh->core.offset >> 8);
+		evo_mthd(push, 0x0868 + head->base.index * 0x400, 4);
+		evo_data(push, asyh->core.h << 16 | asyh->core.w);
+		evo_data(push, asyh->core.layout << 20 |
+			       (asyh->core.pitch >> 8) << 8 |
+			       asyh->core.blocks << 8 |
+			       asyh->core.blockh);
+		evo_data(push, asyh->core.format << 8);
+		evo_data(push, asyh->core.handle);
+		evo_mthd(push, 0x08c0 + head->base.index * 0x400, 1);
+		evo_data(push, asyh->core.y << 16 | asyh->core.x);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head827d_olut_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 4))) {
+		evo_mthd(push, 0x0840 + (head->base.index * 0x400), 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x085c + (head->base.index * 0x400), 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head827d_olut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 5))) {
+		evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2);
+		evo_data(push, 0x80000000 | asyh->olut.mode << 30);
+		evo_data(push, asyh->olut.offset >> 8);
+		evo_mthd(push, 0x085c + (head->base.index * 0x400), 1);
+		evo_data(push, asyh->olut.handle);
+		evo_kick(push, core);
+	}
+}
+
+const struct nv50_head_func
+head827d = {
+	.view = head507d_view,
+	.mode = head507d_mode,
+	.olut = head507d_olut,
+	.olut_set = head827d_olut_set,
+	.olut_clr = head827d_olut_clr,
+	.core_calc = head507d_core_calc,
+	.core_set = head827d_core_set,
+	.core_clr = head507d_core_clr,
+	.curs_layout = head507d_curs_layout,
+	.curs_format = head507d_curs_format,
+	.curs_set = head827d_curs_set,
+	.curs_clr = head827d_curs_clr,
+	.base = head507d_base,
+	.ovly = head507d_ovly,
+	.dither = head507d_dither,
+	.procamp = head507d_procamp,
+};
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head907d.c b/drivers/gpu/drm/nouveau/dispnv50/head907d.c
new file mode 100644
index 000000000000..633907163eb1
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/head907d.c
@@ -0,0 +1,284 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "head.h"
+#include "core.h"
+
+void
+head907d_or(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 3))) {
+		evo_mthd(push, 0x0404 + (head->base.index * 0x300), 2);
+		evo_data(push, 0x00000001 | asyh->or.depth  << 6 |
+					    asyh->or.nvsync << 4 |
+					    asyh->or.nhsync << 3);
+		evo_data(push, 0x31ec6000 | head->base.index << 25 |
+					    asyh->mode.interlace);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_procamp(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x0498 + (head->base.index * 0x300), 1);
+		evo_data(push, asyh->procamp.sat.sin << 20 |
+			       asyh->procamp.sat.cos << 8);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head907d_dither(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x0490 + (head->base.index * 0x0300), 1);
+		evo_data(push, asyh->dither.mode << 3 |
+			       asyh->dither.bits << 1 |
+			       asyh->dither.enable);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_ovly(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 bounds = 0;
+	u32 *push;
+
+	if (asyh->ovly.cpp) {
+		switch (asyh->ovly.cpp) {
+		case 8: bounds |= 0x00000500; break;
+		case 4: bounds |= 0x00000300; break;
+		case 2: bounds |= 0x00000100; break;
+		default:
+			WARN_ON(1);
+			break;
+		}
+		bounds |= 0x00000001;
+	} else {
+		bounds |= 0x00000100;
+	}
+
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x04d4 + head->base.index * 0x300, 1);
+		evo_data(push, bounds);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head907d_base(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 bounds = 0;
+	u32 *push;
+
+	if (asyh->base.cpp) {
+		switch (asyh->base.cpp) {
+		case 8: bounds |= 0x00000500; break;
+		case 4: bounds |= 0x00000300; break;
+		case 2: bounds |= 0x00000100; break;
+		case 1: bounds |= 0x00000000; break;
+		default:
+			WARN_ON(1);
+			break;
+		}
+		bounds |= 0x00000001;
+	}
+
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x04d0 + head->base.index * 0x300, 1);
+		evo_data(push, bounds);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_curs_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 4))) {
+		evo_mthd(push, 0x0480 + head->base.index * 0x300, 1);
+		evo_data(push, 0x05000000);
+		evo_mthd(push, 0x048c + head->base.index * 0x300, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_curs_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 5))) {
+		evo_mthd(push, 0x0480 + head->base.index * 0x300, 2);
+		evo_data(push, 0x80000000 | asyh->curs.layout << 26 |
+					    asyh->curs.format << 24);
+		evo_data(push, asyh->curs.offset >> 8);
+		evo_mthd(push, 0x048c + head->base.index * 0x300, 1);
+		evo_data(push, asyh->curs.handle);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_core_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x0474 + head->base.index * 0x300, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_core_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 9))) {
+		evo_mthd(push, 0x0460 + head->base.index * 0x300, 1);
+		evo_data(push, asyh->core.offset >> 8);
+		evo_mthd(push, 0x0468 + head->base.index * 0x300, 4);
+		evo_data(push, asyh->core.h << 16 | asyh->core.w);
+		evo_data(push, asyh->core.layout << 24 |
+			       (asyh->core.pitch >> 8) << 8 |
+			       asyh->core.blocks << 8 |
+			       asyh->core.blockh);
+		evo_data(push, asyh->core.format << 8);
+		evo_data(push, asyh->core.handle);
+		evo_mthd(push, 0x04b0 + head->base.index * 0x300, 1);
+		evo_data(push, asyh->core.y << 16 | asyh->core.x);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_olut_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 4))) {
+		evo_mthd(push, 0x0448 + (head->base.index * 0x300), 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x045c + (head->base.index * 0x300), 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_olut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 5))) {
+		evo_mthd(push, 0x0448 + (head->base.index * 0x300), 2);
+		evo_data(push, 0x80000000 | asyh->olut.mode << 24);
+		evo_data(push, asyh->olut.offset >> 8);
+		evo_mthd(push, 0x045c + (head->base.index * 0x300), 1);
+		evo_data(push, asyh->olut.handle);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	asyh->olut.mode = 7;
+}
+
+void
+head907d_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	struct nv50_head_mode *m = &asyh->mode;
+	u32 *push;
+	if ((push = evo_wait(core, 14))) {
+		evo_mthd(push, 0x0410 + (head->base.index * 0x300), 6);
+		evo_data(push, 0x00000000);
+		evo_data(push, m->v.active  << 16 | m->h.active );
+		evo_data(push, m->v.synce   << 16 | m->h.synce  );
+		evo_data(push, m->v.blanke  << 16 | m->h.blanke );
+		evo_data(push, m->v.blanks  << 16 | m->h.blanks );
+		evo_data(push, m->v.blank2e << 16 | m->v.blank2s);
+		evo_mthd(push, 0x042c + (head->base.index * 0x300), 2);
+		evo_data(push, 0x00000000); /* ??? */
+		evo_data(push, 0xffffff00);
+		evo_mthd(push, 0x0450 + (head->base.index * 0x300), 3);
+		evo_data(push, m->clock * 1000);
+		evo_data(push, 0x00200000); /* ??? */
+		evo_data(push, m->clock * 1000);
+		evo_kick(push, core);
+	}
+}
+
+void
+head907d_view(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 8))) {
+		evo_mthd(push, 0x0494 + (head->base.index * 0x300), 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x04b8 + (head->base.index * 0x300), 1);
+		evo_data(push, asyh->view.iH << 16 | asyh->view.iW);
+		evo_mthd(push, 0x04c0 + (head->base.index * 0x300), 3);
+		evo_data(push, asyh->view.oH << 16 | asyh->view.oW);
+		evo_data(push, asyh->view.oH << 16 | asyh->view.oW);
+		evo_data(push, asyh->view.oH << 16 | asyh->view.oW);
+		evo_kick(push, core);
+	}
+}
+
+const struct nv50_head_func
+head907d = {
+	.view = head907d_view,
+	.mode = head907d_mode,
+	.olut = head907d_olut,
+	.olut_set = head907d_olut_set,
+	.olut_clr = head907d_olut_clr,
+	.core_calc = head507d_core_calc,
+	.core_set = head907d_core_set,
+	.core_clr = head907d_core_clr,
+	.curs_layout = head507d_curs_layout,
+	.curs_format = head507d_curs_format,
+	.curs_set = head907d_curs_set,
+	.curs_clr = head907d_curs_clr,
+	.base = head907d_base,
+	.ovly = head907d_ovly,
+	.dither = head907d_dither,
+	.procamp = head907d_procamp,
+	.or = head907d_or,
+};
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head917d.c b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
new file mode 100644
index 000000000000..303df8459ca8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "head.h"
+#include "core.h"
+
+static void
+head917d_dither(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x04a0 + (head->base.index * 0x0300), 1);
+		evo_data(push, asyh->dither.mode << 3 |
+			       asyh->dither.bits << 1 |
+			       asyh->dither.enable);
+		evo_kick(push, core);
+	}
+}
+
+static void
+head917d_base(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 bounds = 0;
+	u32 *push;
+
+	if (asyh->base.cpp) {
+		switch (asyh->base.cpp) {
+		case 8: bounds |= 0x00000500; break;
+		case 4: bounds |= 0x00000300; break;
+		case 2: bounds |= 0x00000100; break;
+		case 1: bounds |= 0x00000000; break;
+		default:
+			WARN_ON(1);
+			break;
+		}
+		bounds |= 0x00020001;
+	}
+
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x04d0 + head->base.index * 0x300, 1);
+		evo_data(push, bounds);
+		evo_kick(push, core);
+	}
+}
+
+int
+head917d_curs_layout(struct nv50_head *head, struct nv50_wndw_atom *asyw,
+		     struct nv50_head_atom *asyh)
+{
+	switch (asyw->state.fb->width) {
+	case  32: asyh->curs.layout = 0; break;
+	case  64: asyh->curs.layout = 1; break;
+	case 128: asyh->curs.layout = 2; break;
+	case 256: asyh->curs.layout = 3; break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+const struct nv50_head_func
+head917d = {
+	.view = head907d_view,
+	.mode = head907d_mode,
+	.olut = head907d_olut,
+	.olut_set = head907d_olut_set,
+	.olut_clr = head907d_olut_clr,
+	.core_calc = head507d_core_calc,
+	.core_set = head907d_core_set,
+	.core_clr = head907d_core_clr,
+	.curs_layout = head917d_curs_layout,
+	.curs_format = head507d_curs_format,
+	.curs_set = head907d_curs_set,
+	.curs_clr = head907d_curs_clr,
+	.base = head917d_base,
+	.ovly = head907d_ovly,
+	.dither = head917d_dither,
+	.procamp = head907d_procamp,
+	.or = head907d_or,
+};
diff --git a/drivers/gpu/drm/nouveau/dispnv50/headc37d.c b/drivers/gpu/drm/nouveau/dispnv50/headc37d.c
new file mode 100644
index 000000000000..989c14083066
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/headc37d.c
@@ -0,0 +1,212 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "head.h"
+#include "atom.h"
+#include "core.h"
+
+static void
+headc37d_or(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		/*XXX: This is a dirty hack until OR depth handling is
+		 *     improved later for deep colour etc.
+		 */
+		switch (asyh->or.depth) {
+		case 6: asyh->or.depth = 5; break;
+		case 5: asyh->or.depth = 4; break;
+		case 2: asyh->or.depth = 1; break;
+		case 0:	asyh->or.depth = 4; break;
+		default:
+			WARN_ON(1);
+			break;
+		}
+
+		evo_mthd(push, 0x2004 + (head->base.index * 0x400), 1);
+		evo_data(push, 0x00000001 |
+			       asyh->or.depth << 4 |
+			       asyh->or.nvsync << 3 |
+			       asyh->or.nhsync << 2);
+		evo_kick(push, core);
+	}
+}
+
+static void
+headc37d_procamp(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x2000 + (head->base.index * 0x400), 1);
+		evo_data(push, 0x80000000 |
+			       asyh->procamp.sat.sin << 16 |
+			       asyh->procamp.sat.cos << 4);
+		evo_kick(push, core);
+	}
+}
+
+static void
+headc37d_dither(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x2018 + (head->base.index * 0x0400), 1);
+		evo_data(push, asyh->dither.mode << 8 |
+			       asyh->dither.bits << 4 |
+			       asyh->dither.enable);
+		evo_kick(push, core);
+	}
+}
+
+static void
+headc37d_curs_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 4))) {
+		evo_mthd(push, 0x209c + head->base.index * 0x400, 1);
+		evo_data(push, 0x000000cf);
+		evo_mthd(push, 0x2088 + head->base.index * 0x400, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+static void
+headc37d_curs_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 7))) {
+		evo_mthd(push, 0x209c + head->base.index * 0x400, 2);
+		evo_data(push, 0x80000000 |
+			       asyh->curs.layout << 8 |
+			       asyh->curs.format << 0);
+		evo_data(push, 0x000072ff);
+		evo_mthd(push, 0x2088 + head->base.index * 0x400, 1);
+		evo_data(push, asyh->curs.handle);
+		evo_mthd(push, 0x2090 + head->base.index * 0x400, 1);
+		evo_data(push, asyh->curs.offset >> 8);
+		evo_kick(push, core);
+	}
+}
+
+static int
+headc37d_curs_format(struct nv50_head *head, struct nv50_wndw_atom *asyw,
+		     struct nv50_head_atom *asyh)
+{
+	asyh->curs.format = asyw->image.format;
+	return 0;
+}
+
+static void
+headc37d_olut_clr(struct nv50_head *head)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 2))) {
+		evo_mthd(push, 0x20ac + (head->base.index * 0x400), 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, core);
+	}
+}
+
+static void
+headc37d_olut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 4))) {
+		evo_mthd(push, 0x20a4 + (head->base.index * 0x400), 3);
+		evo_data(push, asyh->olut.output_mode << 8 |
+			       asyh->olut.range << 4 |
+			       asyh->olut.size);
+		evo_data(push, asyh->olut.offset >> 8);
+		evo_data(push, asyh->olut.handle);
+		evo_kick(push, core);
+	}
+}
+
+static void
+headc37d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	asyh->olut.mode = 2;
+	asyh->olut.size = 0;
+	asyh->olut.range = 0;
+	asyh->olut.output_mode = 1;
+}
+
+static void
+headc37d_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	struct nv50_head_mode *m = &asyh->mode;
+	u32 *push;
+	if ((push = evo_wait(core, 12))) {
+		evo_mthd(push, 0x2064 + (head->base.index * 0x400), 5);
+		evo_data(push, (m->v.active  << 16) | m->h.active );
+		evo_data(push, (m->v.synce   << 16) | m->h.synce  );
+		evo_data(push, (m->v.blanke  << 16) | m->h.blanke );
+		evo_data(push, (m->v.blanks  << 16) | m->h.blanks );
+		evo_data(push, (m->v.blank2e << 16) | m->v.blank2s);
+		evo_mthd(push, 0x200c + (head->base.index * 0x400), 1);
+		evo_data(push, m->clock * 1000);
+		evo_mthd(push, 0x2028 + (head->base.index * 0x400), 1);
+		evo_data(push, m->clock * 1000);
+		/*XXX: HEAD_USAGE_BOUNDS, doesn't belong here. */
+		evo_mthd(push, 0x2030 + (head->base.index * 0x400), 1);
+		evo_data(push, 0x00000124);
+		evo_kick(push, core);
+	}
+}
+
+static void
+headc37d_view(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push;
+	if ((push = evo_wait(core, 4))) {
+		evo_mthd(push, 0x204c + (head->base.index * 0x400), 1);
+		evo_data(push, (asyh->view.iH << 16) | asyh->view.iW);
+		evo_mthd(push, 0x2058 + (head->base.index * 0x400), 1);
+		evo_data(push, (asyh->view.oH << 16) | asyh->view.oW);
+		evo_kick(push, core);
+	}
+}
+
+const struct nv50_head_func
+headc37d = {
+	.view = headc37d_view,
+	.mode = headc37d_mode,
+	.olut = headc37d_olut,
+	.olut_set = headc37d_olut_set,
+	.olut_clr = headc37d_olut_clr,
+	.curs_layout = head917d_curs_layout,
+	.curs_format = headc37d_curs_format,
+	.curs_set = headc37d_curs_set,
+	.curs_clr = headc37d_curs_clr,
+	.dither = headc37d_dither,
+	.procamp = headc37d_procamp,
+	.or = headc37d_or,
+};
diff --git a/drivers/gpu/drm/nouveau/dispnv50/lut.c b/drivers/gpu/drm/nouveau/dispnv50/lut.c
new file mode 100644
index 000000000000..a6b96ae2a22f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/lut.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "lut.h"
+#include "disp.h"
+
+#include <drm/drm_color_mgmt.h>
+#include <drm/drm_mode.h>
+#include <drm/drm_property.h>
+
+#include <nvif/class.h>
+
+u32
+nv50_lut_load(struct nv50_lut *lut, bool legacy, int buffer,
+	      struct drm_property_blob *blob)
+{
+	struct drm_color_lut *in = (struct drm_color_lut *)blob->data;
+	void __iomem *mem = lut->mem[buffer].object.map.ptr;
+	const int size = blob->length / sizeof(*in);
+	int bits, shift, i;
+	u16 zero, r, g, b;
+	u32 addr = lut->mem[buffer].addr;
+
+	/* This can't happen.. But it shuts the compiler up. */
+	if (WARN_ON(size != 256))
+		return 0;
+
+	if (legacy) {
+		bits = 11;
+		shift = 3;
+		zero = 0x0000;
+	} else {
+		bits = 14;
+		shift = 0;
+		zero = 0x6000;
+	}
+
+	for (i = 0; i < size; i++) {
+		r = (drm_color_lut_extract(in[i].  red, bits) + zero) << shift;
+		g = (drm_color_lut_extract(in[i].green, bits) + zero) << shift;
+		b = (drm_color_lut_extract(in[i]. blue, bits) + zero) << shift;
+		writew(r, mem + (i * 0x08) + 0);
+		writew(g, mem + (i * 0x08) + 2);
+		writew(b, mem + (i * 0x08) + 4);
+	}
+
+	/* INTERPOLATE modes require a "next" entry to interpolate with,
+	 * so we replicate the last entry to deal with this for now.
+	 */
+	writew(r, mem + (i * 0x08) + 0);
+	writew(g, mem + (i * 0x08) + 2);
+	writew(b, mem + (i * 0x08) + 4);
+	return addr;
+}
+
+void
+nv50_lut_fini(struct nv50_lut *lut)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(lut->mem); i++)
+		nvif_mem_fini(&lut->mem[i]);
+}
+
+int
+nv50_lut_init(struct nv50_disp *disp, struct nvif_mmu *mmu,
+	      struct nv50_lut *lut)
+{
+	const u32 size = disp->disp->object.oclass < GF110_DISP ? 257 : 1025;
+	int i;
+	for (i = 0; i < ARRAY_SIZE(lut->mem); i++) {
+		int ret = nvif_mem_init_map(mmu, NVIF_MEM_VRAM, size * 8,
+					    &lut->mem[i]);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/lut.h b/drivers/gpu/drm/nouveau/dispnv50/lut.h
new file mode 100644
index 000000000000..6d7b8352e4cb
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/lut.h
@@ -0,0 +1,15 @@
+#ifndef __NV50_KMS_LUT_H__
+#define __NV50_KMS_LUT_H__
+#include <nvif/mem.h>
+struct drm_property_blob;
+struct nv50_disp;
+
+struct nv50_lut {
+	struct nvif_mem mem[2];
+};
+
+int nv50_lut_init(struct nv50_disp *, struct nvif_mmu *, struct nv50_lut *);
+void nv50_lut_fini(struct nv50_lut *);
+u32 nv50_lut_load(struct nv50_lut *, bool legacy, int buffer,
+		  struct drm_property_blob *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/oimm.c b/drivers/gpu/drm/nouveau/dispnv50/oimm.c
new file mode 100644
index 000000000000..2a2841d344c8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/oimm.c
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "oimm.h"
+
+#include <nvif/class.h>
+
+int
+nv50_oimm_init(struct nouveau_drm *drm, struct nv50_wndw *wndw)
+{
+	static const struct {
+		s32 oclass;
+		int version;
+		int (*init)(struct nouveau_drm *, s32, struct nv50_wndw *);
+	} oimms[] = {
+		{ GK104_DISP_OVERLAY, 0, oimm507b_init },
+		{ GF110_DISP_OVERLAY, 0, oimm507b_init },
+		{ GT214_DISP_OVERLAY, 0, oimm507b_init },
+		{   G82_DISP_OVERLAY, 0, oimm507b_init },
+		{  NV50_DISP_OVERLAY, 0, oimm507b_init },
+		{}
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int cid;
+
+	cid = nvif_mclass(&disp->disp->object, oimms);
+	if (cid < 0) {
+		NV_ERROR(drm, "No supported overlay immediate class\n");
+		return cid;
+	}
+
+	return oimms[cid].init(drm, oimms[cid].oclass, wndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/oimm.h b/drivers/gpu/drm/nouveau/dispnv50/oimm.h
new file mode 100644
index 000000000000..6fa51f101e94
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/oimm.h
@@ -0,0 +1,8 @@
+#ifndef __NV50_KMS_OIMM_H__
+#define __NV50_KMS_OIMM_H__
+#include "wndw.h"
+
+int oimm507b_init(struct nouveau_drm *, s32, struct nv50_wndw *);
+
+int nv50_oimm_init(struct nouveau_drm *, struct nv50_wndw *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/oimm507b.c b/drivers/gpu/drm/nouveau/dispnv50/oimm507b.c
new file mode 100644
index 000000000000..2ee404b3e19f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/oimm507b.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "oimm.h"
+
+#include <nvif/cl507b.h>
+
+static int
+oimm507b_init_(const struct nv50_wimm_func *func, struct nouveau_drm *drm,
+	       s32 oclass, struct nv50_wndw *wndw)
+{
+	struct nv50_disp_overlay_v0 args = {
+		.head = wndw->id,
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int ret;
+
+	ret = nvif_object_init(&disp->disp->object, 0, oclass, &args,
+			       sizeof(args), &wndw->wimm.base.user);
+	if (ret) {
+		NV_ERROR(drm, "oimm%04x allocation failed: %d\n", oclass, ret);
+		return ret;
+	}
+
+	nvif_object_map(&wndw->wimm.base.user, NULL, 0);
+	wndw->immd = func;
+	return 0;
+}
+
+int
+oimm507b_init(struct nouveau_drm *drm, s32 oclass, struct nv50_wndw *wndw)
+{
+	return oimm507b_init_(&curs507a, drm, oclass, wndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly.c b/drivers/gpu/drm/nouveau/dispnv50/ovly.c
new file mode 100644
index 000000000000..90c246d47604
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/ovly.c
@@ -0,0 +1,57 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ovly.h"
+#include "oimm.h"
+
+#include <nvif/class.h>
+
+int
+nv50_ovly_new(struct nouveau_drm *drm, int head, struct nv50_wndw **pwndw)
+{
+	static const struct {
+		s32 oclass;
+		int version;
+		int (*new)(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+	} ovlys[] = {
+		{ GK104_DISP_OVERLAY_CONTROL_DMA, 0, ovly917e_new },
+		{ GF110_DISP_OVERLAY_CONTROL_DMA, 0, ovly907e_new },
+		{ GT214_DISP_OVERLAY_CHANNEL_DMA, 0, ovly827e_new },
+		{ GT200_DISP_OVERLAY_CHANNEL_DMA, 0, ovly827e_new },
+		{   G82_DISP_OVERLAY_CHANNEL_DMA, 0, ovly827e_new },
+		{  NV50_DISP_OVERLAY_CHANNEL_DMA, 0, ovly507e_new },
+		{}
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int cid, ret;
+
+	cid = nvif_mclass(&disp->disp->object, ovlys);
+	if (cid < 0) {
+		NV_ERROR(drm, "No supported overlay class\n");
+		return cid;
+	}
+
+	ret = ovlys[cid].new(drm, head, ovlys[cid].oclass, pwndw);
+	if (ret)
+		return ret;
+
+	return nv50_oimm_init(drm, *pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly.h b/drivers/gpu/drm/nouveau/dispnv50/ovly.h
new file mode 100644
index 000000000000..4869d52d1786
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/ovly.h
@@ -0,0 +1,30 @@
+#ifndef __NV50_KMS_OVLY_H__
+#define __NV50_KMS_OVLY_H__
+#include "wndw.h"
+
+int ovly507e_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+int ovly507e_new_(const struct nv50_wndw_func *, const u32 *format,
+		  struct nouveau_drm *, int head, s32 oclass,
+		  u32 interlock_data, struct nv50_wndw **);
+int ovly507e_acquire(struct nv50_wndw *, struct nv50_wndw_atom *,
+		     struct nv50_head_atom *);
+void ovly507e_release(struct nv50_wndw *, struct nv50_wndw_atom *,
+		      struct nv50_head_atom *);
+void ovly507e_ntfy_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+void ovly507e_ntfy_clr(struct nv50_wndw *);
+void ovly507e_image_clr(struct nv50_wndw *);
+void ovly507e_scale_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+void ovly507e_update(struct nv50_wndw *, u32 *);
+
+extern const u32 ovly827e_format[];
+void ovly827e_ntfy_reset(struct nouveau_bo *, u32);
+int ovly827e_ntfy_wait_begun(struct nouveau_bo *, u32, struct nvif_device *);
+
+extern const struct nv50_wndw_func ovly907e;
+
+int ovly827e_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+int ovly907e_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+int ovly917e_new(struct nouveau_drm *, int, s32, struct nv50_wndw **);
+
+int nv50_ovly_new(struct nouveau_drm *, int head, struct nv50_wndw **);
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c b/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c
new file mode 100644
index 000000000000..cc417664f823
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c
@@ -0,0 +1,217 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ovly.h"
+#include "atom.h"
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+
+#include <nvif/cl507e.h>
+#include <nvif/event.h>
+
+void
+ovly507e_update(struct nv50_wndw *wndw, u32 *interlock)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x0080, 1);
+		evo_data(push, interlock[NV50_DISP_INTERLOCK_CORE]);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+ovly507e_scale_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 4))) {
+		evo_mthd(push, 0x00e0, 3);
+		evo_data(push, asyw->scale.sy << 16 | asyw->scale.sx);
+		evo_data(push, asyw->scale.sh << 16 | asyw->scale.sw);
+		evo_data(push, asyw->scale.dw);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+ovly507e_image_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 4))) {
+		evo_mthd(push, 0x0084, 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x00c0, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+ovly507e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 12))) {
+		evo_mthd(push, 0x0084, 1);
+		evo_data(push, asyw->image.interval << 4);
+		evo_mthd(push, 0x00c0, 1);
+		evo_data(push, asyw->image.handle[0]);
+		evo_mthd(push, 0x0100, 1);
+		evo_data(push, 0x00000002);
+		evo_mthd(push, 0x0800, 1);
+		evo_data(push, asyw->image.offset[0] >> 8);
+		evo_mthd(push, 0x0808, 3);
+		evo_data(push, asyw->image.h << 16 | asyw->image.w);
+		evo_data(push, asyw->image.layout << 20 |
+			       (asyw->image.pitch[0] >> 8) << 8 |
+			       asyw->image.blocks[0] << 8 |
+			       asyw->image.blockh);
+		evo_data(push, asyw->image.kind << 16 |
+			       asyw->image.format << 8 |
+			       asyw->image.colorspace);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+ovly507e_ntfy_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x00a4, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+ovly507e_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 3))) {
+		evo_mthd(push, 0x00a0, 2);
+		evo_data(push, asyw->ntfy.awaken << 30 | asyw->ntfy.offset);
+		evo_data(push, asyw->ntfy.handle);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+void
+ovly507e_release(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
+		 struct nv50_head_atom *asyh)
+{
+	asyh->ovly.cpp = 0;
+}
+
+int
+ovly507e_acquire(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
+		 struct nv50_head_atom *asyh)
+{
+	const struct drm_framebuffer *fb = asyw->state.fb;
+	int ret;
+
+	ret = drm_atomic_helper_check_plane_state(&asyw->state, &asyh->state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  true, true);
+	if (ret)
+		return ret;
+
+	asyh->ovly.cpp = fb->format->cpp[0];
+	return 0;
+}
+
+#include "nouveau_bo.h"
+
+static const struct nv50_wndw_func
+ovly507e = {
+	.acquire = ovly507e_acquire,
+	.release = ovly507e_release,
+	.ntfy_set = ovly507e_ntfy_set,
+	.ntfy_clr = ovly507e_ntfy_clr,
+	.ntfy_reset = base507c_ntfy_reset,
+	.ntfy_wait_begun = base507c_ntfy_wait_begun,
+	.image_set = ovly507e_image_set,
+	.image_clr = ovly507e_image_clr,
+	.scale_set = ovly507e_scale_set,
+	.update = ovly507e_update,
+};
+
+static const u32
+ovly507e_format[] = {
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ARGB1555,
+	0
+};
+
+int
+ovly507e_new_(const struct nv50_wndw_func *func, const u32 *format,
+	      struct nouveau_drm *drm, int head, s32 oclass, u32 interlock_data,
+	      struct nv50_wndw **pwndw)
+{
+	struct nv50_disp_overlay_channel_dma_v0 args = {
+		.head = head,
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	struct nv50_wndw *wndw;
+	int ret;
+
+	ret = nv50_wndw_new_(func, drm->dev, DRM_PLANE_TYPE_OVERLAY,
+			     "ovly", head, format, BIT(head),
+			     NV50_DISP_INTERLOCK_OVLY, interlock_data,
+			     &wndw);
+	if (*pwndw = wndw, ret)
+		return ret;
+
+	ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
+			       &oclass, 0, &args, sizeof(args),
+			       disp->sync->bo.offset, &wndw->wndw);
+	if (ret) {
+		NV_ERROR(drm, "ovly%04x allocation failed: %d\n", oclass, ret);
+		return ret;
+	}
+
+	ret = nvif_notify_init(&wndw->wndw.base.user, wndw->notify.func, false,
+			       NV50_DISP_OVERLAY_CHANNEL_DMA_V0_NTFY_UEVENT,
+			       &(struct nvif_notify_uevent_req) {},
+			       sizeof(struct nvif_notify_uevent_req),
+			       sizeof(struct nvif_notify_uevent_rep),
+			       &wndw->notify);
+	if (ret)
+		return ret;
+
+	wndw->ntfy = NV50_DISP_OVLY_NTFY(wndw->id);
+	wndw->sema = NV50_DISP_OVLY_SEM0(wndw->id);
+	wndw->data = 0x00000000;
+	return 0;
+}
+
+int
+ovly507e_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return ovly507e_new_(&ovly507e, ovly507e_format, drm, head, oclass,
+			     0x00000004 << (head * 8), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly827e.c b/drivers/gpu/drm/nouveau/dispnv50/ovly827e.c
new file mode 100644
index 000000000000..aaa9fe5a4fc8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/ovly827e.c
@@ -0,0 +1,107 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ovly.h"
+#include "atom.h"
+
+#include <nouveau_bo.h>
+
+static void
+ovly827e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 12))) {
+		evo_mthd(push, 0x0084, 1);
+		evo_data(push, asyw->image.interval << 4);
+		evo_mthd(push, 0x00c0, 1);
+		evo_data(push, asyw->image.handle[0]);
+		evo_mthd(push, 0x0100, 1);
+		evo_data(push, 0x00000002);
+		evo_mthd(push, 0x0800, 1);
+		evo_data(push, asyw->image.offset[0] >> 8);
+		evo_mthd(push, 0x0808, 3);
+		evo_data(push, asyw->image.h << 16 | asyw->image.w);
+		evo_data(push, asyw->image.layout << 20 |
+			       (asyw->image.pitch[0] >> 8) << 8 |
+			       asyw->image.blocks[0] << 8 |
+			       asyw->image.blockh);
+		evo_data(push, asyw->image.format << 8 |
+			       asyw->image.colorspace);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+int
+ovly827e_ntfy_wait_begun(struct nouveau_bo *bo, u32 offset,
+			 struct nvif_device *device)
+{
+	s64 time = nvif_msec(device, 2000ULL,
+		u32 data = nouveau_bo_rd32(bo, offset / 4 + 3);
+		if ((data & 0xffff0000) == 0xffff0000)
+			break;
+		usleep_range(1, 2);
+	);
+	return time < 0 ? time : 0;
+}
+
+void
+ovly827e_ntfy_reset(struct nouveau_bo *bo, u32 offset)
+{
+	nouveau_bo_wr32(bo, offset / 4 + 0, 0x00000000);
+	nouveau_bo_wr32(bo, offset / 4 + 1, 0x00000000);
+	nouveau_bo_wr32(bo, offset / 4 + 2, 0x00000000);
+	nouveau_bo_wr32(bo, offset / 4 + 3, 0x80000000);
+}
+
+static const struct nv50_wndw_func
+ovly827e = {
+	.acquire = ovly507e_acquire,
+	.release = ovly507e_release,
+	.ntfy_set = ovly507e_ntfy_set,
+	.ntfy_clr = ovly507e_ntfy_clr,
+	.ntfy_reset = ovly827e_ntfy_reset,
+	.ntfy_wait_begun = ovly827e_ntfy_wait_begun,
+	.image_set = ovly827e_image_set,
+	.image_clr = ovly507e_image_clr,
+	.scale_set = ovly507e_scale_set,
+	.update = ovly507e_update,
+};
+
+const u32
+ovly827e_format[] = {
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ABGR2101010,
+	0
+};
+
+int
+ovly827e_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return ovly507e_new_(&ovly827e, ovly827e_format, drm, head, oclass,
+			     0x00000004 << (head * 8), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly907e.c b/drivers/gpu/drm/nouveau/dispnv50/ovly907e.c
new file mode 100644
index 000000000000..a3ce53046015
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/ovly907e.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ovly.h"
+#include "atom.h"
+
+static void
+ovly907e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 12))) {
+		evo_mthd(push, 0x0084, 1);
+		evo_data(push, asyw->image.interval << 4);
+		evo_mthd(push, 0x00c0, 1);
+		evo_data(push, asyw->image.handle[0]);
+		evo_mthd(push, 0x0100, 1);
+		evo_data(push, 0x00000002);
+		evo_mthd(push, 0x0400, 1);
+		evo_data(push, asyw->image.offset[0] >> 8);
+		evo_mthd(push, 0x0408, 3);
+		evo_data(push, asyw->image.h << 16 | asyw->image.w);
+		evo_data(push, asyw->image.layout << 24 |
+			       (asyw->image.pitch[0] >> 8) << 8 |
+			       asyw->image.blocks[0] << 8 |
+			       asyw->image.blockh);
+		evo_data(push, asyw->image.format << 8 |
+			       asyw->image.colorspace);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+const struct nv50_wndw_func
+ovly907e = {
+	.acquire = ovly507e_acquire,
+	.release = ovly507e_release,
+	.ntfy_set = ovly507e_ntfy_set,
+	.ntfy_clr = ovly507e_ntfy_clr,
+	.ntfy_reset = ovly827e_ntfy_reset,
+	.ntfy_wait_begun = ovly827e_ntfy_wait_begun,
+	.image_set = ovly907e_image_set,
+	.image_clr = ovly507e_image_clr,
+	.scale_set = ovly507e_scale_set,
+	.update = ovly507e_update,
+};
+
+int
+ovly907e_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return ovly507e_new_(&ovly907e, ovly827e_format, drm, head, oclass,
+			     0x00000004 << (head * 4), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly917e.c b/drivers/gpu/drm/nouveau/dispnv50/ovly917e.c
new file mode 100644
index 000000000000..505fa7e78523
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/ovly917e.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ovly.h"
+
+static const u32
+ovly917e_format[] = {
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_ARGB2101010,
+	0
+};
+
+int
+ovly917e_new(struct nouveau_drm *drm, int head, s32 oclass,
+	     struct nv50_wndw **pwndw)
+{
+	return ovly507e_new_(&ovly907e, ovly917e_format, drm, head, oclass,
+			     0x00000004 << (head * 4), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/pior507d.c b/drivers/gpu/drm/nouveau/dispnv50/pior507d.c
new file mode 100644
index 000000000000..d2bac6a341dc
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/pior507d.c
@@ -0,0 +1,44 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "core.h"
+
+static void
+pior507d_ctrl(struct nv50_core *core, int or, u32 ctrl,
+	      struct nv50_head_atom *asyh)
+{
+	u32 *push;
+	if ((push = evo_wait(&core->chan, 2))) {
+		if (asyh) {
+			ctrl |= asyh->or.depth  << 16;
+			ctrl |= asyh->or.nvsync << 13;
+			ctrl |= asyh->or.nhsync << 12;
+		}
+		evo_mthd(push, 0x0700 + (or * 0x040), 1);
+		evo_data(push, ctrl);
+		evo_kick(push, &core->chan);
+	}
+}
+
+const struct nv50_outp_func
+pior507d = {
+	.ctrl = pior507d_ctrl,
+};
diff --git a/drivers/gpu/drm/nouveau/dispnv50/sor507d.c b/drivers/gpu/drm/nouveau/dispnv50/sor507d.c
new file mode 100644
index 000000000000..5222fe6a9b21
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/sor507d.c
@@ -0,0 +1,44 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "core.h"
+
+static void
+sor507d_ctrl(struct nv50_core *core, int or, u32 ctrl,
+	     struct nv50_head_atom *asyh)
+{
+	u32 *push;
+	if ((push = evo_wait(&core->chan, 2))) {
+		if (asyh) {
+			ctrl |= asyh->or.depth  << 16;
+			ctrl |= asyh->or.nvsync << 13;
+			ctrl |= asyh->or.nhsync << 12;
+		}
+		evo_mthd(push, 0x0600 + (or * 0x40), 1);
+		evo_data(push, ctrl);
+		evo_kick(push, &core->chan);
+	}
+}
+
+const struct nv50_outp_func
+sor507d = {
+	.ctrl = sor507d_ctrl,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregt200.c b/drivers/gpu/drm/nouveau/dispnv50/sor907d.c
index b234547708fc..b0314ec11fb3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregt200.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/sor907d.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,21 +18,24 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "core.h"
 
 #include <nvif/class.h>
 
-const struct nv50_disp_dmac_oclass
-gt200_disp_core_oclass = {
-	.base.oclass = GT200_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &nv50_disp_core_func,
-	.mthd = &g84_disp_core_chan_mthd,
-	.chid = 0,
+static void
+sor907d_ctrl(struct nv50_core *core, int or, u32 ctrl,
+	     struct nv50_head_atom *asyh)
+{
+	u32 *push;
+	if ((push = evo_wait(&core->chan, 2))) {
+		evo_mthd(push, 0x0200 + (or * 0x20), 1);
+		evo_data(push, ctrl);
+		evo_kick(push, &core->chan);
+	}
+}
+
+const struct nv50_outp_func
+sor907d = {
+	.ctrl = sor907d_ctrl,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgk104.c b/drivers/gpu/drm/nouveau/dispnv50/sorc37d.c
index 2a99db4bf8f8..dff059241c5d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgk104.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/sorc37d.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2012 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,20 +18,22 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs
  */
-#include "channv50.h"
-#include "rootnv50.h"
+#include "core.h"
 
-#include <nvif/class.h>
+static void
+sorc37d_ctrl(struct nv50_core *core, int or, u32 ctrl,
+	     struct nv50_head_atom *asyh)
+{
+	u32 *push;
+	if ((push = evo_wait(&core->chan, 2))) {
+		evo_mthd(push, 0x0300 + (or * 0x20), 1);
+		evo_data(push, ctrl);
+		evo_kick(push, &core->chan);
+	}
+}
 
-const struct nv50_disp_pioc_oclass
-gk104_disp_curs_oclass = {
-	.base.oclass = GK104_DISP_CURSOR,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_curs_new,
-	.func = &gf119_disp_pioc_func,
-	.chid = { 13, 13 },
+const struct nv50_outp_func
+sorc37d = {
+	.ctrl = sorc37d_ctrl,
 };
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimm.c b/drivers/gpu/drm/nouveau/dispnv50/wimm.c
new file mode 100644
index 000000000000..fc36e0696407
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimm.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "wimm.h"
+
+#include <nvif/class.h>
+
+int
+nv50_wimm_init(struct nouveau_drm *drm, struct nv50_wndw *wndw)
+{
+	struct {
+		s32 oclass;
+		int version;
+		int (*init)(struct nouveau_drm *, s32, struct nv50_wndw *);
+	} wimms[] = {
+		{ GV100_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
+		{}
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int cid;
+
+	cid = nvif_mclass(&disp->disp->object, wimms);
+	if (cid < 0) {
+		NV_ERROR(drm, "No supported window immediate class\n");
+		return cid;
+	}
+
+	return wimms[cid].init(drm, wimms[cid].oclass, wndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimm.h b/drivers/gpu/drm/nouveau/dispnv50/wimm.h
new file mode 100644
index 000000000000..363052309be9
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimm.h
@@ -0,0 +1,8 @@
+#ifndef __NV50_KMS_WIMM_H__
+#define __NV50_KMS_WIMM_H__
+#include "wndw.h"
+
+int nv50_wimm_init(struct nouveau_drm *drm, struct nv50_wndw *);
+
+int wimmc37b_init(struct nouveau_drm *, s32, struct nv50_wndw *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
new file mode 100644
index 000000000000..9103b8494279
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "wimm.h"
+#include "atom.h"
+#include "wndw.h"
+
+#include <nvif/clc37b.h>
+
+static void
+wimmc37b_update(struct nv50_wndw *wndw, u32 *interlock)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wimm, 2))) {
+		evo_mthd(push, 0x0200, 1);
+		if (interlock[NV50_DISP_INTERLOCK_WNDW] & wndw->interlock.data)
+			evo_data(push, 0x00000003);
+		else
+			evo_data(push, 0x00000001);
+		evo_kick(push, &wndw->wimm);
+	}
+}
+
+static void
+wimmc37b_point(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wimm, 2))) {
+		evo_mthd(push, 0x0208, 1);
+		evo_data(push, asyw->point.y << 16 | asyw->point.x);
+		evo_kick(push, &wndw->wimm);
+	}
+}
+
+static const struct nv50_wimm_func
+wimmc37b = {
+	.point = wimmc37b_point,
+	.update = wimmc37b_update,
+};
+
+static int
+wimmc37b_init_(const struct nv50_wimm_func *func, struct nouveau_drm *drm,
+	       s32 oclass, struct nv50_wndw *wndw)
+{
+	struct nvc37b_window_imm_channel_dma_v0 args = {
+		.pushbuf = 0xb0007b00 | wndw->id,
+		.index = wndw->id,
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int ret;
+
+	ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
+			       &oclass, 0, &args, sizeof(args), 0,
+			       &wndw->wimm);
+	if (ret) {
+		NV_ERROR(drm, "wimm%04x allocation failed: %d\n", oclass, ret);
+		return ret;
+	}
+
+	wndw->immd = func;
+	return 0;
+}
+
+int
+wimmc37b_init(struct nouveau_drm *drm, s32 oclass, struct nv50_wndw *wndw)
+{
+	return wimmc37b_init_(&wimmc37b, drm, oclass, wndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
new file mode 100644
index 000000000000..224963b533a6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -0,0 +1,641 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "wndw.h"
+#include "wimm.h"
+
+#include <nvif/class.h>
+#include <nvif/cl0002.h>
+
+#include <drm/drm_atomic_helper.h>
+#include "nouveau_bo.h"
+
+static void
+nv50_wndw_ctxdma_del(struct nv50_wndw_ctxdma *ctxdma)
+{
+	nvif_object_fini(&ctxdma->object);
+	list_del(&ctxdma->head);
+	kfree(ctxdma);
+}
+
+static struct nv50_wndw_ctxdma *
+nv50_wndw_ctxdma_new(struct nv50_wndw *wndw, struct nouveau_framebuffer *fb)
+{
+	struct nouveau_drm *drm = nouveau_drm(fb->base.dev);
+	struct nv50_wndw_ctxdma *ctxdma;
+	const u8    kind = fb->nvbo->kind;
+	const u32 handle = 0xfb000000 | kind;
+	struct {
+		struct nv_dma_v0 base;
+		union {
+			struct nv50_dma_v0 nv50;
+			struct gf100_dma_v0 gf100;
+			struct gf119_dma_v0 gf119;
+		};
+	} args = {};
+	u32 argc = sizeof(args.base);
+	int ret;
+
+	list_for_each_entry(ctxdma, &wndw->ctxdma.list, head) {
+		if (ctxdma->object.handle == handle)
+			return ctxdma;
+	}
+
+	if (!(ctxdma = kzalloc(sizeof(*ctxdma), GFP_KERNEL)))
+		return ERR_PTR(-ENOMEM);
+	list_add(&ctxdma->head, &wndw->ctxdma.list);
+
+	args.base.target = NV_DMA_V0_TARGET_VRAM;
+	args.base.access = NV_DMA_V0_ACCESS_RDWR;
+	args.base.start  = 0;
+	args.base.limit  = drm->client.device.info.ram_user - 1;
+
+	if (drm->client.device.info.chipset < 0x80) {
+		args.nv50.part = NV50_DMA_V0_PART_256;
+		argc += sizeof(args.nv50);
+	} else
+	if (drm->client.device.info.chipset < 0xc0) {
+		args.nv50.part = NV50_DMA_V0_PART_256;
+		args.nv50.kind = kind;
+		argc += sizeof(args.nv50);
+	} else
+	if (drm->client.device.info.chipset < 0xd0) {
+		args.gf100.kind = kind;
+		argc += sizeof(args.gf100);
+	} else {
+		args.gf119.page = GF119_DMA_V0_PAGE_LP;
+		args.gf119.kind = kind;
+		argc += sizeof(args.gf119);
+	}
+
+	ret = nvif_object_init(wndw->ctxdma.parent, handle, NV_DMA_IN_MEMORY,
+			       &args, argc, &ctxdma->object);
+	if (ret) {
+		nv50_wndw_ctxdma_del(ctxdma);
+		return ERR_PTR(ret);
+	}
+
+	return ctxdma;
+}
+
+int
+nv50_wndw_wait_armed(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	struct nv50_disp *disp = nv50_disp(wndw->plane.dev);
+	if (asyw->set.ntfy) {
+		return wndw->func->ntfy_wait_begun(disp->sync,
+						   asyw->ntfy.offset,
+						   wndw->wndw.base.device);
+	}
+	return 0;
+}
+
+void
+nv50_wndw_flush_clr(struct nv50_wndw *wndw, u32 *interlock, bool flush,
+		    struct nv50_wndw_atom *asyw)
+{
+	union nv50_wndw_atom_mask clr = {
+		.mask = asyw->clr.mask & ~(flush ? 0 : asyw->set.mask),
+	};
+	if (clr.sema ) wndw->func-> sema_clr(wndw);
+	if (clr.ntfy ) wndw->func-> ntfy_clr(wndw);
+	if (clr.xlut ) wndw->func-> xlut_clr(wndw);
+	if (clr.image) wndw->func->image_clr(wndw);
+
+	interlock[wndw->interlock.type] |= wndw->interlock.data;
+}
+
+void
+nv50_wndw_flush_set(struct nv50_wndw *wndw, u32 *interlock,
+		    struct nv50_wndw_atom *asyw)
+{
+	if (interlock) {
+		asyw->image.mode = 0;
+		asyw->image.interval = 1;
+	}
+
+	if (asyw->set.sema ) wndw->func->sema_set (wndw, asyw);
+	if (asyw->set.ntfy ) wndw->func->ntfy_set (wndw, asyw);
+	if (asyw->set.image) wndw->func->image_set(wndw, asyw);
+
+	if (asyw->set.xlut ) {
+		if (asyw->ilut) {
+			asyw->xlut.i.offset =
+				nv50_lut_load(&wndw->ilut,
+					      asyw->xlut.i.mode <= 1,
+					      asyw->xlut.i.buffer,
+					      asyw->ilut);
+		}
+		wndw->func->xlut_set(wndw, asyw);
+	}
+
+	if (asyw->set.scale) wndw->func->scale_set(wndw, asyw);
+	if (asyw->set.point) {
+		if (asyw->set.point = false, asyw->set.mask)
+			interlock[wndw->interlock.type] |= wndw->interlock.data;
+		interlock[NV50_DISP_INTERLOCK_WIMM] |= wndw->interlock.data;
+
+		wndw->immd->point(wndw, asyw);
+		wndw->immd->update(wndw, interlock);
+	} else {
+		interlock[wndw->interlock.type] |= wndw->interlock.data;
+	}
+}
+
+void
+nv50_wndw_ntfy_enable(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	struct nv50_disp *disp = nv50_disp(wndw->plane.dev);
+
+	asyw->ntfy.handle = wndw->wndw.sync.handle;
+	asyw->ntfy.offset = wndw->ntfy;
+	asyw->ntfy.awaken = false;
+	asyw->set.ntfy = true;
+
+	wndw->func->ntfy_reset(disp->sync, wndw->ntfy);
+	wndw->ntfy ^= 0x10;
+}
+
+static void
+nv50_wndw_atomic_check_release(struct nv50_wndw *wndw,
+			       struct nv50_wndw_atom *asyw,
+			       struct nv50_head_atom *asyh)
+{
+	struct nouveau_drm *drm = nouveau_drm(wndw->plane.dev);
+	NV_ATOMIC(drm, "%s release\n", wndw->plane.name);
+	wndw->func->release(wndw, asyw, asyh);
+	asyw->ntfy.handle = 0;
+	asyw->sema.handle = 0;
+}
+
+static int
+nv50_wndw_atomic_check_acquire_yuv(struct nv50_wndw_atom *asyw)
+{
+	switch (asyw->state.fb->format->format) {
+	case DRM_FORMAT_YUYV: asyw->image.format = 0x28; break;
+	case DRM_FORMAT_UYVY: asyw->image.format = 0x29; break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	asyw->image.colorspace = 1;
+	return 0;
+}
+
+static int
+nv50_wndw_atomic_check_acquire_rgb(struct nv50_wndw_atom *asyw)
+{
+	switch (asyw->state.fb->format->format) {
+	case DRM_FORMAT_C8         : asyw->image.format = 0x1e; break;
+	case DRM_FORMAT_XRGB8888   :
+	case DRM_FORMAT_ARGB8888   : asyw->image.format = 0xcf; break;
+	case DRM_FORMAT_RGB565     : asyw->image.format = 0xe8; break;
+	case DRM_FORMAT_XRGB1555   :
+	case DRM_FORMAT_ARGB1555   : asyw->image.format = 0xe9; break;
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ABGR2101010: asyw->image.format = 0xd1; break;
+	case DRM_FORMAT_XBGR8888   :
+	case DRM_FORMAT_ABGR8888   : asyw->image.format = 0xd5; break;
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010: asyw->image.format = 0xdf; break;
+	default:
+		return -EINVAL;
+	}
+	asyw->image.colorspace = 0;
+	return 0;
+}
+
+static int
+nv50_wndw_atomic_check_acquire(struct nv50_wndw *wndw, bool modeset,
+			       struct nv50_wndw_atom *armw,
+			       struct nv50_wndw_atom *asyw,
+			       struct nv50_head_atom *asyh)
+{
+	struct nouveau_framebuffer *fb = nouveau_framebuffer(asyw->state.fb);
+	struct nouveau_drm *drm = nouveau_drm(wndw->plane.dev);
+	int ret;
+
+	NV_ATOMIC(drm, "%s acquire\n", wndw->plane.name);
+
+	if (asyw->state.fb != armw->state.fb || !armw->visible || modeset) {
+		asyw->image.w = fb->base.width;
+		asyw->image.h = fb->base.height;
+		asyw->image.kind = fb->nvbo->kind;
+
+		ret = nv50_wndw_atomic_check_acquire_rgb(asyw);
+		if (ret) {
+			ret = nv50_wndw_atomic_check_acquire_yuv(asyw);
+			if (ret)
+				return ret;
+		}
+
+		if (asyw->image.kind) {
+			asyw->image.layout = 0;
+			if (drm->client.device.info.chipset >= 0xc0)
+				asyw->image.blockh = fb->nvbo->mode >> 4;
+			else
+				asyw->image.blockh = fb->nvbo->mode;
+			asyw->image.blocks[0] = fb->base.pitches[0] / 64;
+			asyw->image.pitch[0] = 0;
+		} else {
+			asyw->image.layout = 1;
+			asyw->image.blockh = 0;
+			asyw->image.blocks[0] = 0;
+			asyw->image.pitch[0] = fb->base.pitches[0];
+		}
+
+		if (!(asyh->state.pageflip_flags & DRM_MODE_PAGE_FLIP_ASYNC))
+			asyw->image.interval = 1;
+		else
+			asyw->image.interval = 0;
+		asyw->image.mode = asyw->image.interval ? 0 : 1;
+		asyw->set.image = wndw->func->image_set != NULL;
+	}
+
+	if (wndw->func->scale_set) {
+		asyw->scale.sx = asyw->state.src_x >> 16;
+		asyw->scale.sy = asyw->state.src_y >> 16;
+		asyw->scale.sw = asyw->state.src_w >> 16;
+		asyw->scale.sh = asyw->state.src_h >> 16;
+		asyw->scale.dw = asyw->state.crtc_w;
+		asyw->scale.dh = asyw->state.crtc_h;
+		if (memcmp(&armw->scale, &asyw->scale, sizeof(asyw->scale)))
+			asyw->set.scale = true;
+	}
+
+	if (wndw->immd) {
+		asyw->point.x = asyw->state.crtc_x;
+		asyw->point.y = asyw->state.crtc_y;
+		if (memcmp(&armw->point, &asyw->point, sizeof(asyw->point)))
+			asyw->set.point = true;
+	}
+
+	return wndw->func->acquire(wndw, asyw, asyh);
+}
+
+static void
+nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
+			   struct nv50_wndw_atom *armw,
+			   struct nv50_wndw_atom *asyw,
+			   struct nv50_head_atom *asyh)
+{
+	struct drm_property_blob *ilut = asyh->state.degamma_lut;
+
+	/* I8 format without an input LUT makes no sense, and the
+	 * HW error-checks for this.
+	 *
+	 * In order to handle legacy gamma, when there's no input
+	 * LUT we need to steal the output LUT and use it instead.
+	 */
+	if (!ilut && asyw->state.fb->format->format == DRM_FORMAT_C8) {
+		/* This should be an error, but there's legacy clients
+		 * that do a modeset before providing a gamma table.
+		 *
+		 * We keep the window disabled to avoid angering HW.
+		 */
+		if (!(ilut = asyh->state.gamma_lut)) {
+			asyw->visible = false;
+			return;
+		}
+
+		if (wndw->func->ilut)
+			asyh->wndw.olut |= BIT(wndw->id);
+	} else {
+		asyh->wndw.olut &= ~BIT(wndw->id);
+	}
+
+	/* Recalculate LUT state. */
+	memset(&asyw->xlut, 0x00, sizeof(asyw->xlut));
+	if ((asyw->ilut = wndw->func->ilut ? ilut : NULL)) {
+		wndw->func->ilut(wndw, asyw);
+		asyw->xlut.handle = wndw->wndw.vram.handle;
+		asyw->xlut.i.buffer = !asyw->xlut.i.buffer;
+		asyw->set.xlut = true;
+	}
+
+	/* Handle setting base SET_OUTPUT_LUT_LO_ENABLE_USE_CORE_LUT. */
+	if (wndw->func->olut_core &&
+	    (!armw->visible || (armw->xlut.handle && !asyw->xlut.handle)))
+		asyw->set.xlut = true;
+
+	/* Can't do an immediate flip while changing the LUT. */
+	asyh->state.pageflip_flags &= ~DRM_MODE_PAGE_FLIP_ASYNC;
+}
+
+static int
+nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state)
+{
+	struct nouveau_drm *drm = nouveau_drm(plane->dev);
+	struct nv50_wndw *wndw = nv50_wndw(plane);
+	struct nv50_wndw_atom *armw = nv50_wndw_atom(wndw->plane.state);
+	struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
+	struct nv50_head_atom *harm = NULL, *asyh = NULL;
+	bool modeset = false;
+	int ret;
+
+	NV_ATOMIC(drm, "%s atomic_check\n", plane->name);
+
+	/* Fetch the assembly state for the head the window will belong to,
+	 * and determine whether the window will be visible.
+	 */
+	if (asyw->state.crtc) {
+		asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc);
+		if (IS_ERR(asyh))
+			return PTR_ERR(asyh);
+		modeset = drm_atomic_crtc_needs_modeset(&asyh->state);
+		asyw->visible = asyh->state.active;
+	} else {
+		asyw->visible = false;
+	}
+
+	/* Fetch assembly state for the head the window used to belong to. */
+	if (armw->state.crtc) {
+		harm = nv50_head_atom_get(asyw->state.state, armw->state.crtc);
+		if (IS_ERR(harm))
+			return PTR_ERR(harm);
+	}
+
+	/* LUT configuration can potentially cause the window to be disabled. */
+	if (asyw->visible && wndw->func->xlut_set &&
+	    (!armw->visible ||
+	     asyh->state.color_mgmt_changed ||
+	     asyw->state.fb->format->format !=
+	     armw->state.fb->format->format))
+		nv50_wndw_atomic_check_lut(wndw, armw, asyw, asyh);
+
+	/* Calculate new window state. */
+	if (asyw->visible) {
+		ret = nv50_wndw_atomic_check_acquire(wndw, modeset,
+						     armw, asyw, asyh);
+		if (ret)
+			return ret;
+
+		asyh->wndw.mask |= BIT(wndw->id);
+	} else
+	if (armw->visible) {
+		nv50_wndw_atomic_check_release(wndw, asyw, harm);
+		harm->wndw.mask &= ~BIT(wndw->id);
+	} else {
+		return 0;
+	}
+
+	/* Aside from the obvious case where the window is actively being
+	 * disabled, we might also need to temporarily disable the window
+	 * when performing certain modeset operations.
+	 */
+	if (!asyw->visible || modeset) {
+		asyw->clr.ntfy = armw->ntfy.handle != 0;
+		asyw->clr.sema = armw->sema.handle != 0;
+		asyw->clr.xlut = armw->xlut.handle != 0;
+		if (wndw->func->image_clr)
+			asyw->clr.image = armw->image.handle[0] != 0;
+	}
+
+	return 0;
+}
+
+static void
+nv50_wndw_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state)
+{
+	struct nouveau_framebuffer *fb = nouveau_framebuffer(old_state->fb);
+	struct nouveau_drm *drm = nouveau_drm(plane->dev);
+
+	NV_ATOMIC(drm, "%s cleanup: %p\n", plane->name, old_state->fb);
+	if (!old_state->fb)
+		return;
+
+	nouveau_bo_unpin(fb->nvbo);
+}
+
+static int
+nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state)
+{
+	struct nouveau_framebuffer *fb = nouveau_framebuffer(state->fb);
+	struct nouveau_drm *drm = nouveau_drm(plane->dev);
+	struct nv50_wndw *wndw = nv50_wndw(plane);
+	struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
+	struct nv50_head_atom *asyh;
+	struct nv50_wndw_ctxdma *ctxdma;
+	int ret;
+
+	NV_ATOMIC(drm, "%s prepare: %p\n", plane->name, state->fb);
+	if (!asyw->state.fb)
+		return 0;
+
+	ret = nouveau_bo_pin(fb->nvbo, TTM_PL_FLAG_VRAM, true);
+	if (ret)
+		return ret;
+
+	ctxdma = nv50_wndw_ctxdma_new(wndw, fb);
+	if (IS_ERR(ctxdma)) {
+		nouveau_bo_unpin(fb->nvbo);
+		return PTR_ERR(ctxdma);
+	}
+
+	asyw->state.fence = reservation_object_get_excl_rcu(fb->nvbo->bo.resv);
+	asyw->image.handle[0] = ctxdma->object.handle;
+	asyw->image.offset[0] = fb->nvbo->bo.offset;
+
+	if (wndw->func->prepare) {
+		asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc);
+		if (IS_ERR(asyh))
+			return PTR_ERR(asyh);
+
+		wndw->func->prepare(wndw, asyh, asyw);
+	}
+
+	return 0;
+}
+
+static const struct drm_plane_helper_funcs
+nv50_wndw_helper = {
+	.prepare_fb = nv50_wndw_prepare_fb,
+	.cleanup_fb = nv50_wndw_cleanup_fb,
+	.atomic_check = nv50_wndw_atomic_check,
+};
+
+static void
+nv50_wndw_atomic_destroy_state(struct drm_plane *plane,
+			       struct drm_plane_state *state)
+{
+	struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
+	__drm_atomic_helper_plane_destroy_state(&asyw->state);
+	kfree(asyw);
+}
+
+static struct drm_plane_state *
+nv50_wndw_atomic_duplicate_state(struct drm_plane *plane)
+{
+	struct nv50_wndw_atom *armw = nv50_wndw_atom(plane->state);
+	struct nv50_wndw_atom *asyw;
+	if (!(asyw = kmalloc(sizeof(*asyw), GFP_KERNEL)))
+		return NULL;
+	__drm_atomic_helper_plane_duplicate_state(plane, &asyw->state);
+	asyw->sema = armw->sema;
+	asyw->ntfy = armw->ntfy;
+	asyw->ilut = NULL;
+	asyw->xlut = armw->xlut;
+	asyw->image = armw->image;
+	asyw->point = armw->point;
+	asyw->clr.mask = 0;
+	asyw->set.mask = 0;
+	return &asyw->state;
+}
+
+static void
+nv50_wndw_reset(struct drm_plane *plane)
+{
+	struct nv50_wndw_atom *asyw;
+
+	if (WARN_ON(!(asyw = kzalloc(sizeof(*asyw), GFP_KERNEL))))
+		return;
+
+	if (plane->state)
+		plane->funcs->atomic_destroy_state(plane, plane->state);
+	plane->state = &asyw->state;
+	plane->state->plane = plane;
+	plane->state->rotation = DRM_MODE_ROTATE_0;
+}
+
+static void
+nv50_wndw_destroy(struct drm_plane *plane)
+{
+	struct nv50_wndw *wndw = nv50_wndw(plane);
+	struct nv50_wndw_ctxdma *ctxdma, *ctxtmp;
+
+	list_for_each_entry_safe(ctxdma, ctxtmp, &wndw->ctxdma.list, head) {
+		nv50_wndw_ctxdma_del(ctxdma);
+	}
+
+	nvif_notify_fini(&wndw->notify);
+	nv50_dmac_destroy(&wndw->wimm);
+	nv50_dmac_destroy(&wndw->wndw);
+
+	nv50_lut_fini(&wndw->ilut);
+
+	drm_plane_cleanup(&wndw->plane);
+	kfree(wndw);
+}
+
+const struct drm_plane_funcs
+nv50_wndw = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = nv50_wndw_destroy,
+	.reset = nv50_wndw_reset,
+	.atomic_duplicate_state = nv50_wndw_atomic_duplicate_state,
+	.atomic_destroy_state = nv50_wndw_atomic_destroy_state,
+};
+
+static int
+nv50_wndw_notify(struct nvif_notify *notify)
+{
+	return NVIF_NOTIFY_KEEP;
+}
+
+void
+nv50_wndw_fini(struct nv50_wndw *wndw)
+{
+	nvif_notify_put(&wndw->notify);
+}
+
+void
+nv50_wndw_init(struct nv50_wndw *wndw)
+{
+	nvif_notify_get(&wndw->notify);
+}
+
+int
+nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
+	       enum drm_plane_type type, const char *name, int index,
+	       const u32 *format, u32 heads,
+	       enum nv50_disp_interlock_type interlock_type, u32 interlock_data,
+	       struct nv50_wndw **pwndw)
+{
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvif_mmu *mmu = &drm->client.mmu;
+	struct nv50_disp *disp = nv50_disp(dev);
+	struct nv50_wndw *wndw;
+	int nformat;
+	int ret;
+
+	if (!(wndw = *pwndw = kzalloc(sizeof(*wndw), GFP_KERNEL)))
+		return -ENOMEM;
+	wndw->func = func;
+	wndw->id = index;
+	wndw->interlock.type = interlock_type;
+	wndw->interlock.data = interlock_data;
+	wndw->ctxdma.parent = &wndw->wndw.base.user;
+
+	wndw->ctxdma.parent = &wndw->wndw.base.user;
+	INIT_LIST_HEAD(&wndw->ctxdma.list);
+
+	for (nformat = 0; format[nformat]; nformat++);
+
+	ret = drm_universal_plane_init(dev, &wndw->plane, heads, &nv50_wndw,
+				       format, nformat, NULL,
+				       type, "%s-%d", name, index);
+	if (ret) {
+		kfree(*pwndw);
+		*pwndw = NULL;
+		return ret;
+	}
+
+	drm_plane_helper_add(&wndw->plane, &nv50_wndw_helper);
+
+	if (wndw->func->ilut) {
+		ret = nv50_lut_init(disp, mmu, &wndw->ilut);
+		if (ret)
+			return ret;
+	}
+
+	wndw->notify.func = nv50_wndw_notify;
+	return 0;
+}
+
+int
+nv50_wndw_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
+	      struct nv50_wndw **pwndw)
+{
+	struct {
+		s32 oclass;
+		int version;
+		int (*new)(struct nouveau_drm *, enum drm_plane_type,
+			   int, s32, struct nv50_wndw **);
+	} wndws[] = {
+		{ GV100_DISP_WINDOW_CHANNEL_DMA, 0, wndwc37e_new },
+		{}
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	int cid, ret;
+
+	cid = nvif_mclass(&disp->disp->object, wndws);
+	if (cid < 0) {
+		NV_ERROR(drm, "No supported window class\n");
+		return cid;
+	}
+
+	ret = wndws[cid].new(drm, type, index, wndws[cid].oclass, pwndw);
+	if (ret)
+		return ret;
+
+	return nv50_wimm_init(drm, *pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
new file mode 100644
index 000000000000..b0b6428034b0
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
@@ -0,0 +1,96 @@
+#ifndef __NV50_KMS_WNDW_H__
+#define __NV50_KMS_WNDW_H__
+#define nv50_wndw(p) container_of((p), struct nv50_wndw, plane)
+#include "disp.h"
+#include "atom.h"
+#include "lut.h"
+
+#include <nvif/notify.h>
+
+struct nv50_wndw_ctxdma {
+	struct list_head head;
+	struct nvif_object object;
+};
+
+struct nv50_wndw {
+	const struct nv50_wndw_func *func;
+	const struct nv50_wimm_func *immd;
+	int id;
+	struct nv50_disp_interlock interlock;
+
+	struct {
+		struct nvif_object *parent;
+		struct list_head list;
+	} ctxdma;
+
+	struct drm_plane plane;
+
+	struct nv50_lut ilut;
+
+	struct nv50_dmac wndw;
+	struct nv50_dmac wimm;
+
+	struct nvif_notify notify;
+	u16 ntfy;
+	u16 sema;
+	u32 data;
+};
+
+int nv50_wndw_new_(const struct nv50_wndw_func *, struct drm_device *,
+		   enum drm_plane_type, const char *name, int index,
+		   const u32 *format, enum nv50_disp_interlock_type,
+		   u32 interlock_data, u32 heads, struct nv50_wndw **);
+void nv50_wndw_init(struct nv50_wndw *);
+void nv50_wndw_fini(struct nv50_wndw *);
+void nv50_wndw_flush_set(struct nv50_wndw *, u32 *interlock,
+			 struct nv50_wndw_atom *);
+void nv50_wndw_flush_clr(struct nv50_wndw *, u32 *interlock, bool flush,
+			 struct nv50_wndw_atom *);
+void nv50_wndw_ntfy_enable(struct nv50_wndw *, struct nv50_wndw_atom *);
+int nv50_wndw_wait_armed(struct nv50_wndw *, struct nv50_wndw_atom *);
+
+struct nv50_wndw_func {
+	int (*acquire)(struct nv50_wndw *, struct nv50_wndw_atom *asyw,
+		       struct nv50_head_atom *asyh);
+	void (*release)(struct nv50_wndw *, struct nv50_wndw_atom *asyw,
+			struct nv50_head_atom *asyh);
+	void (*prepare)(struct nv50_wndw *, struct nv50_head_atom *asyh,
+			struct nv50_wndw_atom *asyw);
+
+	void (*sema_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
+	void (*sema_clr)(struct nv50_wndw *);
+	void (*ntfy_reset)(struct nouveau_bo *, u32 offset);
+	void (*ntfy_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
+	void (*ntfy_clr)(struct nv50_wndw *);
+	int (*ntfy_wait_begun)(struct nouveau_bo *, u32 offset,
+			       struct nvif_device *);
+	void (*ilut)(struct nv50_wndw *, struct nv50_wndw_atom *);
+	bool olut_core;
+	void (*xlut_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
+	void (*xlut_clr)(struct nv50_wndw *);
+	void (*image_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
+	void (*image_clr)(struct nv50_wndw *);
+	void (*scale_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
+
+	void (*update)(struct nv50_wndw *, u32 *interlock);
+};
+
+extern const struct drm_plane_funcs nv50_wndw;
+
+void base507c_ntfy_reset(struct nouveau_bo *, u32);
+int base507c_ntfy_wait_begun(struct nouveau_bo *, u32, struct nvif_device *);
+
+struct nv50_wimm_func {
+	void (*point)(struct nv50_wndw *, struct nv50_wndw_atom *);
+
+	void (*update)(struct nv50_wndw *, u32 *interlock);
+};
+
+extern const struct nv50_wimm_func curs507a;
+
+int wndwc37e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
+		 struct nv50_wndw **);
+
+int nv50_wndw_new(struct nouveau_drm *, enum drm_plane_type, int index,
+		  struct nv50_wndw **);
+#endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c
new file mode 100644
index 000000000000..44afb0f069a5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c
@@ -0,0 +1,278 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "wndw.h"
+#include "atom.h"
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include <nouveau_bo.h>
+
+#include <nvif/clc37e.h>
+
+static void
+wndwc37e_ilut_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x02b8, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+wndwc37e_ilut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 4))) {
+		evo_mthd(push, 0x02b0, 3);
+		evo_data(push, asyw->xlut.i.output_mode << 8 |
+			       asyw->xlut.i.range << 4 |
+			       asyw->xlut.i.size);
+		evo_data(push, asyw->xlut.i.offset >> 8);
+		evo_data(push, asyw->xlut.handle);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+wndwc37e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	asyw->xlut.i.mode = 2;
+	asyw->xlut.i.size = 0;
+	asyw->xlut.i.range = 0;
+	asyw->xlut.i.output_mode = 1;
+}
+
+static void
+wndwc37e_image_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 4))) {
+		evo_mthd(push, 0x0308, 1);
+		evo_data(push, 0x00000000);
+		evo_mthd(push, 0x0240, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+wndwc37e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+
+	if (!(push = evo_wait(&wndw->wndw, 25)))
+		return;
+
+	evo_mthd(push, 0x0308, 1);
+	evo_data(push, asyw->image.mode << 4 | asyw->image.interval);
+	evo_mthd(push, 0x0224, 4);
+	evo_data(push, asyw->image.h << 16 | asyw->image.w);
+	evo_data(push, asyw->image.layout << 4 | asyw->image.blockh);
+	evo_data(push, asyw->image.colorspace << 8 | asyw->image.format);
+	evo_data(push, asyw->image.blocks[0] | (asyw->image.pitch[0] >> 6));
+	evo_mthd(push, 0x0240, 1);
+	evo_data(push, asyw->image.handle[0]);
+	evo_mthd(push, 0x0260, 1);
+	evo_data(push, asyw->image.offset[0] >> 8);
+	evo_mthd(push, 0x0290, 1);
+	evo_data(push, (asyw->state.src_y >> 16) << 16 |
+		       (asyw->state.src_x >> 16));
+	evo_mthd(push, 0x0298, 1);
+	evo_data(push, (asyw->state.src_h >> 16) << 16 |
+		       (asyw->state.src_w >> 16));
+	evo_mthd(push, 0x02a4, 1);
+	evo_data(push, asyw->state.crtc_h << 16 |
+		       asyw->state.crtc_w);
+
+	/*XXX: Composition-related stuff.  Need to implement properly. */
+	evo_mthd(push, 0x02ec, 1);
+	evo_data(push, (2 - (wndw->id & 1)) << 4);
+	evo_mthd(push, 0x02f4, 5);
+	evo_data(push, 0x00000011);
+	evo_data(push, 0xffff0000);
+	evo_data(push, 0xffff0000);
+	evo_data(push, 0xffff0000);
+	evo_data(push, 0xffff0000);
+	evo_kick(push, &wndw->wndw);
+}
+
+static void
+wndwc37e_ntfy_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x021c, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+wndwc37e_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 3))) {
+		evo_mthd(push, 0x021c, 2);
+		evo_data(push, asyw->ntfy.handle);
+		evo_data(push, asyw->ntfy.offset | asyw->ntfy.awaken);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+wndwc37e_sema_clr(struct nv50_wndw *wndw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 2))) {
+		evo_mthd(push, 0x0218, 1);
+		evo_data(push, 0x00000000);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+wndwc37e_sema_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 5))) {
+		evo_mthd(push, 0x020c, 4);
+		evo_data(push, asyw->sema.offset);
+		evo_data(push, asyw->sema.acquire);
+		evo_data(push, asyw->sema.release);
+		evo_data(push, asyw->sema.handle);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+wndwc37e_update(struct nv50_wndw *wndw, u32 *interlock)
+{
+	u32 *push;
+	if ((push = evo_wait(&wndw->wndw, 5))) {
+		evo_mthd(push, 0x0370, 2);
+		evo_data(push, interlock[NV50_DISP_INTERLOCK_CURS] << 1 |
+			       interlock[NV50_DISP_INTERLOCK_CORE]);
+		evo_data(push, interlock[NV50_DISP_INTERLOCK_WNDW]);
+		evo_mthd(push, 0x0200, 1);
+		if (interlock[NV50_DISP_INTERLOCK_WIMM] & wndw->interlock.data)
+			evo_data(push, 0x00001001);
+		else
+			evo_data(push, 0x00000001);
+		evo_kick(push, &wndw->wndw);
+	}
+}
+
+static void
+wndwc37e_release(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
+		 struct nv50_head_atom *asyh)
+{
+}
+
+static int
+wndwc37e_acquire(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
+		 struct nv50_head_atom *asyh)
+{
+	return drm_atomic_helper_check_plane_state(&asyw->state, &asyh->state,
+						   DRM_PLANE_HELPER_NO_SCALING,
+						   DRM_PLANE_HELPER_NO_SCALING,
+						   true, true);
+}
+
+static const u32
+wndwc37e_format[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_ARGB2101010,
+	0
+};
+
+static const struct nv50_wndw_func
+wndwc37e = {
+	.acquire = wndwc37e_acquire,
+	.release = wndwc37e_release,
+	.sema_set = wndwc37e_sema_set,
+	.sema_clr = wndwc37e_sema_clr,
+	.ntfy_set = wndwc37e_ntfy_set,
+	.ntfy_clr = wndwc37e_ntfy_clr,
+	.ntfy_reset = corec37d_ntfy_init,
+	.ntfy_wait_begun = base507c_ntfy_wait_begun,
+	.ilut = wndwc37e_ilut,
+	.xlut_set = wndwc37e_ilut_set,
+	.xlut_clr = wndwc37e_ilut_clr,
+	.image_set = wndwc37e_image_set,
+	.image_clr = wndwc37e_image_clr,
+	.update = wndwc37e_update,
+};
+
+static int
+wndwc37e_new_(const struct nv50_wndw_func *func, struct nouveau_drm *drm,
+	      enum drm_plane_type type, int index, s32 oclass, u32 heads,
+	      struct nv50_wndw **pwndw)
+{
+	struct nvc37e_window_channel_dma_v0 args = {
+		.pushbuf = 0xb0007e00 | index,
+		.index = index,
+	};
+	struct nv50_disp *disp = nv50_disp(drm->dev);
+	struct nv50_wndw *wndw;
+	int ret;
+
+	ret = nv50_wndw_new_(func, drm->dev, type, "wndw", index,
+			     wndwc37e_format, heads, NV50_DISP_INTERLOCK_WNDW,
+			     BIT(index), &wndw);
+	if (*pwndw = wndw, ret)
+		return ret;
+
+	ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
+			       &oclass, 0, &args, sizeof(args),
+			       disp->sync->bo.offset, &wndw->wndw);
+	if (ret) {
+		NV_ERROR(drm, "qndw%04x allocation failed: %d\n", oclass, ret);
+		return ret;
+	}
+
+	wndw->ntfy = NV50_DISP_WNDW_NTFY(wndw->id);
+	wndw->sema = NV50_DISP_WNDW_SEM0(wndw->id);
+	wndw->data = 0x00000000;
+	return 0;
+}
+
+int
+wndwc37e_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
+	     s32 oclass, struct nv50_wndw **pwndw)
+{
+	return wndwc37e_new_(&wndwc37e, drm, type, index, oclass,
+			     BIT(index >> 1), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
index 2740278d226b..4f5233107f5f 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
@@ -31,6 +31,7 @@ struct nv_device_info_v0 {
 #define NV_DEVICE_INFO_V0_KEPLER                                           0x08
 #define NV_DEVICE_INFO_V0_MAXWELL                                          0x09
 #define NV_DEVICE_INFO_V0_PASCAL                                           0x0a
+#define NV_DEVICE_INFO_V0_VOLTA                                            0x0b
 	__u8  family;
 	__u8  pad06[2];
 	__u64 ram_size;
@@ -39,9 +40,55 @@ struct nv_device_info_v0 {
 	char  name[64];
 };
 
+struct nv_device_info_v1 {
+	__u8  version;
+	__u8  count;
+	__u8  pad02[6];
+	struct nv_device_info_v1_data {
+		__u64 mthd; /* NV_DEVICE_INFO_* (see below). */
+		__u64 data;
+	} data[];
+};
+
 struct nv_device_time_v0 {
 	__u8  version;
 	__u8  pad01[7];
 	__u64 time;
 };
+
+#define NV_DEVICE_INFO_UNIT                               (0xffffffffULL << 32)
+#define NV_DEVICE_INFO(n)                          ((n) | (0x00000000ULL << 32))
+#define NV_DEVICE_FIFO(n)                          ((n) | (0x00000001ULL << 32))
+
+/* This will be returned for unsupported queries. */
+#define NV_DEVICE_INFO_INVALID                                           ~0ULL
+
+/* These return a mask of available engines of particular type. */
+#define NV_DEVICE_INFO_ENGINE_SW                     NV_DEVICE_INFO(0x00000000)
+#define NV_DEVICE_INFO_ENGINE_GR                     NV_DEVICE_INFO(0x00000001)
+#define NV_DEVICE_INFO_ENGINE_MPEG                   NV_DEVICE_INFO(0x00000002)
+#define NV_DEVICE_INFO_ENGINE_ME                     NV_DEVICE_INFO(0x00000003)
+#define NV_DEVICE_INFO_ENGINE_CIPHER                 NV_DEVICE_INFO(0x00000004)
+#define NV_DEVICE_INFO_ENGINE_BSP                    NV_DEVICE_INFO(0x00000005)
+#define NV_DEVICE_INFO_ENGINE_VP                     NV_DEVICE_INFO(0x00000006)
+#define NV_DEVICE_INFO_ENGINE_CE                     NV_DEVICE_INFO(0x00000007)
+#define NV_DEVICE_INFO_ENGINE_SEC                    NV_DEVICE_INFO(0x00000008)
+#define NV_DEVICE_INFO_ENGINE_MSVLD                  NV_DEVICE_INFO(0x00000009)
+#define NV_DEVICE_INFO_ENGINE_MSPDEC                 NV_DEVICE_INFO(0x0000000a)
+#define NV_DEVICE_INFO_ENGINE_MSPPP                  NV_DEVICE_INFO(0x0000000b)
+#define NV_DEVICE_INFO_ENGINE_MSENC                  NV_DEVICE_INFO(0x0000000c)
+#define NV_DEVICE_INFO_ENGINE_VIC                    NV_DEVICE_INFO(0x0000000d)
+#define NV_DEVICE_INFO_ENGINE_SEC2                   NV_DEVICE_INFO(0x0000000e)
+#define NV_DEVICE_INFO_ENGINE_NVDEC                  NV_DEVICE_INFO(0x0000000f)
+#define NV_DEVICE_INFO_ENGINE_NVENC                  NV_DEVICE_INFO(0x00000010)
+
+/* Returns the number of available channels. */
+#define NV_DEVICE_FIFO_CHANNELS                      NV_DEVICE_FIFO(0x00000000)
+
+/* Returns a mask of available runlists. */
+#define NV_DEVICE_FIFO_RUNLISTS                      NV_DEVICE_FIFO(0x00000001)
+
+/* These return a mask of engines available on a particular runlist. */
+#define NV_DEVICE_FIFO_RUNLIST_ENGINES(n)     ((n) + NV_DEVICE_FIFO(0x00000010))
+#define NV_DEVICE_FIFO_RUNLIST_ENGINES__SIZE                                64
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/cla06f.h b/drivers/gpu/drm/nouveau/include/nvif/cla06f.h
index 56f5bd81e480..fbfcffc5feb2 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/cla06f.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/cla06f.h
@@ -4,25 +4,11 @@
 
 struct kepler_channel_gpfifo_a_v0 {
 	__u8  version;
-	__u8  pad01[5];
+	__u8  pad01[1];
 	__u16 chid;
-#define NVA06F_V0_ENGINE_SW                                          0x00000001
-#define NVA06F_V0_ENGINE_GR                                          0x00000002
-#define NVA06F_V0_ENGINE_SEC                                         0x00000004
-#define NVA06F_V0_ENGINE_MSVLD                                       0x00000010
-#define NVA06F_V0_ENGINE_MSPDEC                                      0x00000020
-#define NVA06F_V0_ENGINE_MSPPP                                       0x00000040
-#define NVA06F_V0_ENGINE_MSENC                                       0x00000080
-#define NVA06F_V0_ENGINE_VIC                                         0x00000100
-#define NVA06F_V0_ENGINE_NVDEC                                       0x00000200
-#define NVA06F_V0_ENGINE_NVENC0                                      0x00000400
-#define NVA06F_V0_ENGINE_NVENC1                                      0x00000800
-#define NVA06F_V0_ENGINE_CE0                                         0x00010000
-#define NVA06F_V0_ENGINE_CE1                                         0x00020000
-#define NVA06F_V0_ENGINE_CE2                                         0x00040000
-	__u32 engines;
 	__u32 ilength;
 	__u64 ioffset;
+	__u64 runlist;
 	__u64 vmm;
 };
 
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index a7c5bf572788..6db56bd7d67e 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -52,6 +52,8 @@
 
 #define NV04_DISP                                     /* cl0046.h */ 0x00000046
 
+#define VOLTA_USERMODE_A                                             0x0000c361
+
 #define NV03_CHANNEL_DMA                              /* cl506b.h */ 0x0000006b
 #define NV10_CHANNEL_DMA                              /* cl506b.h */ 0x0000006e
 #define NV17_CHANNEL_DMA                              /* cl506b.h */ 0x0000176e
@@ -66,6 +68,7 @@
 #define KEPLER_CHANNEL_GPFIFO_B                       /* cla06f.h */ 0x0000a16f
 #define MAXWELL_CHANNEL_GPFIFO_A                      /* cla06f.h */ 0x0000b06f
 #define PASCAL_CHANNEL_GPFIFO_A                       /* cla06f.h */ 0x0000c06f
+#define VOLTA_CHANNEL_GPFIFO_A                        /* cla06f.h */ 0x0000c36f
 
 #define NV50_DISP                                     /* cl5070.h */ 0x00005070
 #define G82_DISP                                      /* cl5070.h */ 0x00008270
@@ -79,6 +82,7 @@
 #define GM200_DISP                                    /* cl5070.h */ 0x00009570
 #define GP100_DISP                                    /* cl5070.h */ 0x00009770
 #define GP102_DISP                                    /* cl5070.h */ 0x00009870
+#define GV100_DISP                                    /* cl5070.h */ 0x0000c370
 
 #define NV31_MPEG                                                    0x00003174
 #define G82_MPEG                                                     0x00008274
@@ -90,6 +94,7 @@
 #define GT214_DISP_CURSOR                             /* cl507a.h */ 0x0000857a
 #define GF110_DISP_CURSOR                             /* cl507a.h */ 0x0000907a
 #define GK104_DISP_CURSOR                             /* cl507a.h */ 0x0000917a
+#define GV100_DISP_CURSOR                             /* cl507a.h */ 0x0000c37a
 
 #define NV50_DISP_OVERLAY                             /* cl507b.h */ 0x0000507b
 #define G82_DISP_OVERLAY                              /* cl507b.h */ 0x0000827b
@@ -97,6 +102,8 @@
 #define GF110_DISP_OVERLAY                            /* cl507b.h */ 0x0000907b
 #define GK104_DISP_OVERLAY                            /* cl507b.h */ 0x0000917b
 
+#define GV100_DISP_WINDOW_IMM_CHANNEL_DMA             /* clc37b.h */ 0x0000c37b
+
 #define NV50_DISP_BASE_CHANNEL_DMA                    /* cl507c.h */ 0x0000507c
 #define G82_DISP_BASE_CHANNEL_DMA                     /* cl507c.h */ 0x0000827c
 #define GT200_DISP_BASE_CHANNEL_DMA                   /* cl507c.h */ 0x0000837c
@@ -117,6 +124,7 @@
 #define GM200_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000957d
 #define GP100_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000977d
 #define GP102_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000987d
+#define GV100_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000c37d
 
 #define NV50_DISP_OVERLAY_CHANNEL_DMA                 /* cl507e.h */ 0x0000507e
 #define G82_DISP_OVERLAY_CHANNEL_DMA                  /* cl507e.h */ 0x0000827e
@@ -125,6 +133,8 @@
 #define GF110_DISP_OVERLAY_CONTROL_DMA                /* cl507e.h */ 0x0000907e
 #define GK104_DISP_OVERLAY_CONTROL_DMA                /* cl507e.h */ 0x0000917e
 
+#define GV100_DISP_WINDOW_CHANNEL_DMA                 /* clc37e.h */ 0x0000c37e
+
 #define NV50_TESLA                                                   0x00005097
 #define G82_TESLA                                                    0x00008297
 #define GT200_TESLA                                                  0x00008397
@@ -145,6 +155,8 @@
 #define PASCAL_A                                      /* cl9097.h */ 0x0000c097
 #define PASCAL_B                                      /* cl9097.h */ 0x0000c197
 
+#define VOLTA_A                                       /* cl9097.h */ 0x0000c397
+
 #define NV74_BSP                                                     0x000074b0
 
 #define GT212_MSVLD                                                  0x000085b1
@@ -170,6 +182,7 @@
 #define MAXWELL_DMA_COPY_A                                           0x0000b0b5
 #define PASCAL_DMA_COPY_A                                            0x0000c0b5
 #define PASCAL_DMA_COPY_B                                            0x0000c1b5
+#define VOLTA_DMA_COPY_A                                             0x0000c3b5
 
 #define FERMI_DECOMPRESS                                             0x000090b8
 
@@ -183,6 +196,7 @@
 #define MAXWELL_COMPUTE_B                                            0x0000b1c0
 #define PASCAL_COMPUTE_A                                             0x0000c0c0
 #define PASCAL_COMPUTE_B                                             0x0000c1c0
+#define VOLTA_COMPUTE_A                                              0x0000c3c0
 
 #define NV74_CIPHER                                                  0x000074c1
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/clc37b.h b/drivers/gpu/drm/nouveau/include/nvif/clc37b.h
new file mode 100644
index 000000000000..89b18189d43b
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvif/clc37b.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NVIF_CLC37B_H__
+#define __NVIF_CLC37B_H__
+
+struct nvc37b_window_imm_channel_dma_v0 {
+	__u8  version;
+	__u8  index;
+	__u8  pad02[6];
+	__u64 pushbuf;
+};
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/clc37e.h b/drivers/gpu/drm/nouveau/include/nvif/clc37e.h
new file mode 100644
index 000000000000..899db9e915ef
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvif/clc37e.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NVIF_CLC37E_H__
+#define __NVIF_CLC37E_H__
+
+struct nvc37e_window_channel_dma_v0 {
+	__u8  version;
+	__u8  index;
+	__u8  pad02[6];
+	__u64 pushbuf;
+};
+
+#define NVC37E_WINDOW_CHANNEL_DMA_V0_NTFY_UEVENT                           0x00
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/device.h b/drivers/gpu/drm/nouveau/include/nvif/device.h
index 6edb6266857e..ef839bd1d37e 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/device.h
@@ -4,10 +4,18 @@
 
 #include <nvif/object.h>
 #include <nvif/cl0080.h>
+#include <nvif/user.h>
 
 struct nvif_device {
 	struct nvif_object object;
 	struct nv_device_info_v0 info;
+
+	struct nvif_fifo_runlist {
+		u64 engines;
+	} *runlist;
+	int runlists;
+
+	struct nvif_user user;
 };
 
 int  nvif_device_init(struct nvif_object *, u32 handle, s32 oclass, void *, u32,
@@ -67,6 +75,5 @@ u64  nvif_device_time(struct nvif_device *);
 #include <engine/fifo.h>
 #include <engine/gr.h>
 
-#define nvxx_fifo(a) nvxx_device(a)->fifo
 #define nvxx_gr(a) nvxx_device(a)->gr
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/disp.h b/drivers/gpu/drm/nouveau/include/nvif/disp.h
new file mode 100644
index 000000000000..7c0eda375c01
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvif/disp.h
@@ -0,0 +1,12 @@
+#ifndef __NVIF_DISP_H__
+#define __NVIF_DISP_H__
+#include <nvif/object.h>
+struct nvif_device;
+
+struct nvif_disp {
+	struct nvif_object object;
+};
+
+int nvif_disp_ctor(struct nvif_device *, s32 oclass, struct nvif_disp *);
+void nvif_disp_dtor(struct nvif_disp *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/fifo.h b/drivers/gpu/drm/nouveau/include/nvif/fifo.h
new file mode 100644
index 000000000000..e9468c9f9abf
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvif/fifo.h
@@ -0,0 +1,18 @@
+#ifndef __NVIF_FIFO_H__
+#define __NVIF_FIFO_H__
+#include <nvif/device.h>
+
+/* Returns mask of runlists that support a NV_DEVICE_INFO_ENGINE_* type. */
+u64 nvif_fifo_runlist(struct nvif_device *, u64 engine);
+
+/* CE-supporting runlists (excluding GRCE, if others exist). */
+static inline u64
+nvif_fifo_runlist_ce(struct nvif_device *device)
+{
+	u64 runmgr = nvif_fifo_runlist(device, NV_DEVICE_INFO_ENGINE_GR);
+	u64 runmce = nvif_fifo_runlist(device, NV_DEVICE_INFO_ENGINE_CE);
+	if (runmce && !(runmce &= ~runmgr))
+		runmce = runmgr;
+	return runmce;
+}
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/mem.h b/drivers/gpu/drm/nouveau/include/nvif/mem.h
index b542fe38398e..80ee4ab0f016 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/mem.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/mem.h
@@ -15,4 +15,6 @@ int nvif_mem_init_type(struct nvif_mmu *mmu, s32 oclass, int type, u8 page,
 int nvif_mem_init(struct nvif_mmu *mmu, s32 oclass, u8 type, u8 page,
 		  u64 size, void *argv, u32 argc, struct nvif_mem *);
 void nvif_mem_fini(struct nvif_mem *);
+
+int nvif_mem_init_map(struct nvif_mmu *, u8 type, u64 size, struct nvif_mem *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/mmu.h b/drivers/gpu/drm/nouveau/include/nvif/mmu.h
index c8cd5b5b0688..747ecf67e403 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/mmu.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/mmu.h
@@ -8,6 +8,7 @@ struct nvif_mmu {
 	u8  heap_nr;
 	u8  type_nr;
 	u16 kind_nr;
+	s32 mem;
 
 	struct {
 		u64 size;
diff --git a/drivers/gpu/drm/nouveau/include/nvif/object.h b/drivers/gpu/drm/nouveau/include/nvif/object.h
index a2d5244ff2b7..20754d9e6883 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/object.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/object.h
@@ -99,6 +99,22 @@ struct nvif_mclass {
 	ret;                                                                   \
 })
 
+#define nvif_sclass(o,m,u) ({                                                  \
+	const typeof(m[0]) *_mclass = (m);                                     \
+	s32 _oclass = (u);                                                     \
+	int _cid;                                                              \
+	if (_oclass) {                                                         \
+		for (_cid = 0; _mclass[_cid].oclass; _cid++) {                 \
+			if (_mclass[_cid].oclass == _oclass)                   \
+				break;                                         \
+		}                                                              \
+		_cid = _mclass[_cid].oclass ? _cid : -ENOSYS;                  \
+	} else {                                                               \
+		_cid = nvif_mclass((o), _mclass);                              \
+	}                                                                      \
+	_cid;                                                                  \
+})
+
 /*XXX*/
 #include <core/object.h>
 #define nvxx_object(a) ({                                                      \
diff --git a/drivers/gpu/drm/nouveau/include/nvif/user.h b/drivers/gpu/drm/nouveau/include/nvif/user.h
new file mode 100644
index 000000000000..03c11826b693
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvif/user.h
@@ -0,0 +1,19 @@
+#ifndef __NVIF_USER_H__
+#define __NVIF_USER_H__
+#include <nvif/object.h>
+struct nvif_device;
+
+struct nvif_user {
+	const struct nvif_user_func *func;
+	struct nvif_object object;
+};
+
+struct nvif_user_func {
+	void (*doorbell)(struct nvif_user *, u32 token);
+};
+
+int nvif_user_init(struct nvif_device *);
+void nvif_user_fini(struct nvif_device *);
+
+extern const struct nvif_user_func nvif_userc361;
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 560265b15ec2..d83d834b7452 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -22,6 +22,7 @@ enum nvkm_devidx {
 	NVKM_SUBDEV_LTC,
 	NVKM_SUBDEV_MMU,
 	NVKM_SUBDEV_BAR,
+	NVKM_SUBDEV_FAULT,
 	NVKM_SUBDEV_PMU,
 	NVKM_SUBDEV_VOLT,
 	NVKM_SUBDEV_ICCSENSE,
@@ -37,7 +38,10 @@ enum nvkm_devidx {
 	NVKM_ENGINE_CE3,
 	NVKM_ENGINE_CE4,
 	NVKM_ENGINE_CE5,
-	NVKM_ENGINE_CE_LAST = NVKM_ENGINE_CE5,
+	NVKM_ENGINE_CE6,
+	NVKM_ENGINE_CE7,
+	NVKM_ENGINE_CE8,
+	NVKM_ENGINE_CE_LAST = NVKM_ENGINE_CE8,
 
 	NVKM_ENGINE_CIPHER,
 	NVKM_ENGINE_DISP,
@@ -109,6 +113,7 @@ struct nvkm_device {
 		NV_E0    = 0xe0,
 		GM100    = 0x110,
 		GP100    = 0x130,
+		GV100    = 0x140,
 	} card_type;
 	u32 chipset;
 	u8  chiprev;
@@ -123,6 +128,7 @@ struct nvkm_device {
 	struct nvkm_bus *bus;
 	struct nvkm_clk *clk;
 	struct nvkm_devinit *devinit;
+	struct nvkm_fault *fault;
 	struct nvkm_fb *fb;
 	struct nvkm_fuse *fuse;
 	struct nvkm_gpio *gpio;
@@ -143,7 +149,7 @@ struct nvkm_device {
 	struct nvkm_volt *volt;
 
 	struct nvkm_engine *bsp;
-	struct nvkm_engine *ce[6];
+	struct nvkm_engine *ce[9];
 	struct nvkm_engine *cipher;
 	struct nvkm_disp *disp;
 	struct nvkm_dma *dma;
@@ -194,6 +200,7 @@ struct nvkm_device_chip {
 	int (*bus     )(struct nvkm_device *, int idx, struct nvkm_bus **);
 	int (*clk     )(struct nvkm_device *, int idx, struct nvkm_clk **);
 	int (*devinit )(struct nvkm_device *, int idx, struct nvkm_devinit **);
+	int (*fault   )(struct nvkm_device *, int idx, struct nvkm_fault **);
 	int (*fb      )(struct nvkm_device *, int idx, struct nvkm_fb **);
 	int (*fuse    )(struct nvkm_device *, int idx, struct nvkm_fuse **);
 	int (*gpio    )(struct nvkm_device *, int idx, struct nvkm_gpio **);
@@ -214,7 +221,7 @@ struct nvkm_device_chip {
 	int (*volt    )(struct nvkm_device *, int idx, struct nvkm_volt **);
 
 	int (*bsp     )(struct nvkm_device *, int idx, struct nvkm_engine **);
-	int (*ce[6]   )(struct nvkm_device *, int idx, struct nvkm_engine **);
+	int (*ce[9]   )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*cipher  )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*disp    )(struct nvkm_device *, int idx, struct nvkm_disp **);
 	int (*dma     )(struct nvkm_device *, int idx, struct nvkm_dma **);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/engine.h b/drivers/gpu/drm/nouveau/include/nvkm/core/engine.h
index ebf8473a39fe..8a2be5b635e2 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/engine.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/engine.h
@@ -18,6 +18,7 @@ struct nvkm_engine_func {
 	void *(*dtor)(struct nvkm_engine *);
 	void (*preinit)(struct nvkm_engine *);
 	int (*oneinit)(struct nvkm_engine *);
+	int (*info)(struct nvkm_engine *, u64 mthd, u64 *data);
 	int (*init)(struct nvkm_engine *);
 	int (*fini)(struct nvkm_engine *, bool suspend);
 	void (*intr)(struct nvkm_engine *);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
index 63df2290177f..85a0777c2ce4 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h
@@ -17,6 +17,7 @@ struct nvkm_subdev_func {
 	void *(*dtor)(struct nvkm_subdev *);
 	int (*preinit)(struct nvkm_subdev *);
 	int (*oneinit)(struct nvkm_subdev *);
+	int (*info)(struct nvkm_subdev *, u64 mthd, u64 *data);
 	int (*init)(struct nvkm_subdev *);
 	int (*fini)(struct nvkm_subdev *, bool suspend);
 	void (*intr)(struct nvkm_subdev *);
@@ -29,6 +30,7 @@ void nvkm_subdev_del(struct nvkm_subdev **);
 int  nvkm_subdev_preinit(struct nvkm_subdev *);
 int  nvkm_subdev_init(struct nvkm_subdev *);
 int  nvkm_subdev_fini(struct nvkm_subdev *, bool suspend);
+int  nvkm_subdev_info(struct nvkm_subdev *, u64, u64 *);
 void nvkm_subdev_intr(struct nvkm_subdev *);
 
 /* subdev logging */
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/ce.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/ce.h
index 553245994450..fc295e1faa19 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/ce.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/ce.h
@@ -10,4 +10,5 @@ int gm107_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
 int gm200_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
 int gp100_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
 int gp102_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
+int gv100_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
index e83193d3ccab..ef7dc0844d26 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
@@ -35,4 +35,5 @@ int gm107_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gm200_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gp100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gp102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
+int gv100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/dma.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/dma.h
index 0f9c1c702ed6..f0c1b2c8c78c 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/dma.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/dma.h
@@ -27,4 +27,5 @@ int nv04_dma_new(struct nvkm_device *, int, struct nvkm_dma **);
 int nv50_dma_new(struct nvkm_device *, int, struct nvkm_dma **);
 int gf100_dma_new(struct nvkm_device *, int, struct nvkm_dma **);
 int gf119_dma_new(struct nvkm_device *, int, struct nvkm_dma **);
+int gv100_dma_new(struct nvkm_device *, int, struct nvkm_dma **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
index c17b3a9bf8fb..7e39fbed2519 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
@@ -4,6 +4,7 @@
 #include <core/engine.h>
 #include <core/object.h>
 #include <core/event.h>
+struct nvkm_fault_data;
 
 #define NVKM_FIFO_CHID_NR 4096
 
@@ -45,6 +46,7 @@ struct nvkm_fifo {
 	struct nvkm_event kevent; /* channel killed */
 };
 
+void nvkm_fifo_fault(struct nvkm_fifo *, struct nvkm_fault_data *);
 void nvkm_fifo_pause(struct nvkm_fifo *, unsigned long *);
 void nvkm_fifo_start(struct nvkm_fifo *, unsigned long *);
 
@@ -71,4 +73,5 @@ int gm200_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
 int gm20b_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
 int gp100_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
 int gp10b_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
+int gv100_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
index fb18f105fc43..ba1518ff8b66 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
@@ -45,6 +45,8 @@ int gm200_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gm20b_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp100_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp102_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
+int gp104_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp107_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp10b_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
+int gv100_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/dp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/dp.h
index df34b41838d6..512e25a41803 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/dp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/dp.h
@@ -1,6 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __NVBIOS_DP_H__
 #define __NVBIOS_DP_H__
+
+u16
+nvbios_dp_table(struct nvkm_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
+
 struct nvbios_dpout {
 	u16 type;
 	u16 mask;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
index 40558064d589..486e7635c29d 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
@@ -30,4 +30,5 @@ int mcp89_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int gf100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int gm107_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int gm200_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
+int gv100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h
new file mode 100644
index 000000000000..5a77498fe6a0
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h
@@ -0,0 +1,33 @@
+#ifndef __NVKM_FAULT_H__
+#define __NVKM_FAULT_H__
+#include <core/subdev.h>
+#include <core/notify.h>
+
+struct nvkm_fault {
+	const struct nvkm_fault_func *func;
+	struct nvkm_subdev subdev;
+
+	struct nvkm_fault_buffer *buffer[2];
+	int buffer_nr;
+
+	struct nvkm_event event;
+
+	struct nvkm_notify nrpfb;
+};
+
+struct nvkm_fault_data {
+	u64  addr;
+	u64  inst;
+	u64  time;
+	u8 engine;
+	u8  valid;
+	u8    gpc;
+	u8    hub;
+	u8 access;
+	u8 client;
+	u8 reason;
+};
+
+int gp100_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
+int gv100_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
index 92be0e5269c6..96ccc624ee81 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
@@ -83,6 +83,7 @@ int gm20b_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gp100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gp102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gp10b_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int gv100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 
 #include <subdev/bios.h>
 #include <subdev/bios/ramcfg.h>
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
index 95b611554d53..9db5f8293198 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
@@ -21,12 +21,14 @@ struct nvkm_ltc {
 	int zbc_max;
 	u32 zbc_color[NVKM_LTC_MAX_ZBC_CNT][4];
 	u32 zbc_depth[NVKM_LTC_MAX_ZBC_CNT];
+	u32 zbc_stencil[NVKM_LTC_MAX_ZBC_CNT];
 };
 
 void nvkm_ltc_tags_clear(struct nvkm_device *, u32 first, u32 count);
 
 int nvkm_ltc_zbc_color_get(struct nvkm_ltc *, int index, const u32[4]);
 int nvkm_ltc_zbc_depth_get(struct nvkm_ltc *, int index, const u32);
+int nvkm_ltc_zbc_stencil_get(struct nvkm_ltc *, int index, const u32);
 
 void nvkm_ltc_invalidate(struct nvkm_ltc *);
 void nvkm_ltc_flush(struct nvkm_ltc *);
@@ -37,4 +39,5 @@ int gk20a_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gm107_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gm200_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gp100_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
+int gp102_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
index baab93398e54..688595545e21 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
@@ -129,4 +129,5 @@ int gm200_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int gm20b_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int gp100_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int gp10b_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int gv100_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index ece650a0c5f9..e2211bb2cf79 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -23,6 +23,7 @@
 
 #include <nvif/client.h>
 #include <nvif/driver.h>
+#include <nvif/fifo.h>
 #include <nvif/ioctl.h>
 #include <nvif/class.h>
 #include <nvif/cl0002.h>
@@ -102,6 +103,7 @@ nouveau_abi16_swclass(struct nouveau_drm *drm)
 	case NV_DEVICE_INFO_V0_KEPLER:
 	case NV_DEVICE_INFO_V0_MAXWELL:
 	case NV_DEVICE_INFO_V0_PASCAL:
+	case NV_DEVICE_INFO_V0_VOLTA:
 		return NVIF_CLASS_SW_GF100;
 	}
 
@@ -256,6 +258,7 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 	struct nouveau_abi16 *abi16 = nouveau_abi16_get(file_priv);
 	struct nouveau_abi16_chan *chan;
 	struct nvif_device *device;
+	u64 engine;
 	int ret;
 
 	if (unlikely(!abi16))
@@ -268,25 +271,26 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 
 	/* hack to allow channel engine type specification on kepler */
 	if (device->info.family >= NV_DEVICE_INFO_V0_KEPLER) {
-		if (init->fb_ctxdma_handle != ~0)
-			init->fb_ctxdma_handle = NVA06F_V0_ENGINE_GR;
-		else {
-			init->fb_ctxdma_handle = 0;
-#define _(A,B) if (init->tt_ctxdma_handle & (A)) init->fb_ctxdma_handle |= (B)
-			_(0x01, NVA06F_V0_ENGINE_GR);
-			_(0x02, NVA06F_V0_ENGINE_MSPDEC);
-			_(0x04, NVA06F_V0_ENGINE_MSPPP);
-			_(0x08, NVA06F_V0_ENGINE_MSVLD);
-			_(0x10, NVA06F_V0_ENGINE_CE0);
-			_(0x20, NVA06F_V0_ENGINE_CE1);
-			_(0x40, NVA06F_V0_ENGINE_MSENC);
-#undef _
+		if (init->fb_ctxdma_handle == ~0) {
+			switch (init->tt_ctxdma_handle) {
+			case 0x01: engine = NV_DEVICE_INFO_ENGINE_GR    ; break;
+			case 0x02: engine = NV_DEVICE_INFO_ENGINE_MSPDEC; break;
+			case 0x04: engine = NV_DEVICE_INFO_ENGINE_MSPPP ; break;
+			case 0x08: engine = NV_DEVICE_INFO_ENGINE_MSVLD ; break;
+			case 0x30: engine = NV_DEVICE_INFO_ENGINE_CE    ; break;
+			default:
+				return nouveau_abi16_put(abi16, -ENOSYS);
+			}
+		} else {
+			engine = NV_DEVICE_INFO_ENGINE_GR;
 		}
 
-		/* allow flips to be executed if this is a graphics channel */
+		if (engine != NV_DEVICE_INFO_ENGINE_CE)
+			engine = nvif_fifo_runlist(device, engine);
+		else
+			engine = nvif_fifo_runlist_ce(device);
+		init->fb_ctxdma_handle = engine;
 		init->tt_ctxdma_handle = 0;
-		if (init->fb_ctxdma_handle == NVA06F_V0_ENGINE_GR)
-			init->tt_ctxdma_handle = 1;
 	}
 
 	if (init->fb_ctxdma_handle == ~0 || init->tt_ctxdma_handle == ~0)
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 5ffcb6683776..ffb195850314 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -193,7 +193,7 @@ static int nouveau_dsm_power_state(enum vga_switcheroo_client_id id,
 	return nouveau_dsm_set_discrete_state(nouveau_dsm_priv.dhandle, state);
 }
 
-static int nouveau_dsm_get_client_id(struct pci_dev *pdev)
+static enum vga_switcheroo_client_id nouveau_dsm_get_client_id(struct pci_dev *pdev)
 {
 	/* easy option one - intel vendor ID means Integrated */
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL)
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 6f402c4f2bdd..7214022dfb91 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -214,7 +214,6 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
 	INIT_LIST_HEAD(&nvbo->entry);
 	INIT_LIST_HEAD(&nvbo->vma_list);
 	nvbo->bo.bdev = &drm->ttm.bdev;
-	nvbo->cli = cli;
 
 	/* This is confusing, and doesn't actually mean we want an uncached
 	 * mapping, but is what NOUVEAU_GEM_DOMAIN_COHERENT gets translated
@@ -1142,6 +1141,8 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 			    struct ttm_mem_reg *, struct ttm_mem_reg *);
 		int (*init)(struct nouveau_channel *, u32 handle);
 	} _methods[] = {
+		{  "COPY", 4, 0xc3b5, nve0_bo_move_copy, nve0_bo_move_init },
+		{  "GRCE", 0, 0xc3b5, nve0_bo_move_copy, nvc0_bo_move_init },
 		{  "COPY", 4, 0xc1b5, nve0_bo_move_copy, nve0_bo_move_init },
 		{  "GRCE", 0, 0xc1b5, nve0_bo_move_copy, nvc0_bo_move_init },
 		{  "COPY", 4, 0xc0b5, nve0_bo_move_copy, nve0_bo_move_init },
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h
index be8e00b49cde..73c48440d4d7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.h
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.h
@@ -26,8 +26,6 @@ struct nouveau_bo {
 
 	struct list_head vma_list;
 
-	struct nouveau_cli *cli;
-
 	unsigned contig:1;
 	unsigned page:5;
 	unsigned kind:8;
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index af1116655910..92d3115f96b5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -163,12 +163,15 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device,
 			return ret;
 		}
 
+		chan->push.addr = chan->push.vma->addr;
+
+		if (device->info.family >= NV_DEVICE_INFO_V0_FERMI)
+			return 0;
+
 		args.target = NV_DMA_V0_TARGET_VM;
 		args.access = NV_DMA_V0_ACCESS_VM;
 		args.start = 0;
 		args.limit = cli->vmm.vmm.limit - 1;
-
-		chan->push.addr = chan->push.vma->addr;
 	} else
 	if (chan->push.buffer->bo.mem.mem_type == TTM_PL_VRAM) {
 		if (device->info.family == NV_DEVICE_INFO_V0_TNT) {
@@ -214,10 +217,11 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device,
 
 static int
 nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device,
-		    u32 engine, struct nouveau_channel **pchan)
+		    u64 runlist, struct nouveau_channel **pchan)
 {
 	struct nouveau_cli *cli = (void *)device->object.client;
-	static const u16 oclasses[] = { PASCAL_CHANNEL_GPFIFO_A,
+	static const u16 oclasses[] = { VOLTA_CHANNEL_GPFIFO_A,
+					PASCAL_CHANNEL_GPFIFO_A,
 					MAXWELL_CHANNEL_GPFIFO_A,
 					KEPLER_CHANNEL_GPFIFO_B,
 					KEPLER_CHANNEL_GPFIFO_A,
@@ -245,9 +249,9 @@ nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device,
 	do {
 		if (oclass[0] >= KEPLER_CHANNEL_GPFIFO_A) {
 			args.kepler.version = 0;
-			args.kepler.engines = engine;
 			args.kepler.ilength = 0x02000;
 			args.kepler.ioffset = 0x10000 + chan->push.addr;
+			args.kepler.runlist = runlist;
 			args.kepler.vmm = nvif_handle(&cli->vmm.vmm.object);
 			size = sizeof(args.kepler);
 		} else
@@ -474,3 +478,28 @@ done:
 	cli->base.super = super;
 	return ret;
 }
+
+int
+nouveau_channels_init(struct nouveau_drm *drm)
+{
+	struct {
+		struct nv_device_info_v1 m;
+		struct {
+			struct nv_device_info_v1_data channels;
+		} v;
+	} args = {
+		.m.version = 1,
+		.m.count = sizeof(args.v) / sizeof(args.v.channels),
+		.v.channels.mthd = NV_DEVICE_FIFO_CHANNELS,
+	};
+	struct nvif_object *device = &drm->client.device.object;
+	int ret;
+
+	ret = nvif_object_mthd(device, NV_DEVICE_V0_INFO, &args, sizeof(args));
+	if (ret || args.v.channels.mthd == NV_DEVICE_INFO_INVALID)
+		return -ENODEV;
+
+	drm->chan.nr = args.v.channels.data;
+	drm->chan.context_base = dma_fence_context_alloc(drm->chan.nr);
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.h b/drivers/gpu/drm/nouveau/nouveau_chan.h
index 14607c16a2bd..64454c2ebd90 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.h
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.h
@@ -45,6 +45,7 @@ struct nouveau_channel {
 	atomic_t killed;
 };
 
+int nouveau_channels_init(struct nouveau_drm *);
 
 int  nouveau_channel_new(struct nouveau_drm *, struct nvif_device *,
 			 u32 arg0, u32 arg1, struct nouveau_channel **);
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 6ed9cb053dfa..7b557c354307 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -151,7 +151,7 @@ nouveau_conn_atomic_set_property(struct drm_connector *connector,
 				/* ... except prior to G80, where the code
 				 * doesn't support such things.
 				 */
-				if (disp->disp.oclass < NV50_DISP)
+				if (disp->disp.object.oclass < NV50_DISP)
 					return -EINVAL;
 				break;
 			default:
@@ -260,7 +260,7 @@ nouveau_conn_reset(struct drm_connector *connector)
 	asyc->procamp.color_vibrance = 150;
 	asyc->procamp.vibrant_hue = 90;
 
-	if (nouveau_display(connector->dev)->disp.oclass < NV50_DISP) {
+	if (nouveau_display(connector->dev)->disp.object.oclass < NV50_DISP) {
 		switch (connector->connector_type) {
 		case DRM_MODE_CONNECTOR_LVDS:
 			/* See note in nouveau_conn_atomic_set_property(). */
@@ -314,7 +314,7 @@ nouveau_conn_attach_properties(struct drm_connector *connector)
 	case DRM_MODE_CONNECTOR_TV:
 		break;
 	case DRM_MODE_CONNECTOR_VGA:
-		if (disp->disp.oclass < NV50_DISP)
+		if (disp->disp.object.oclass < NV50_DISP)
 			break; /* Can only scale on DFPs. */
 		/* Fall-through. */
 	default:
@@ -1005,7 +1005,7 @@ get_tmds_link_bandwidth(struct drm_connector *connector, bool hdmi)
 		return 112000;
 }
 
-static int
+static enum drm_mode_status
 nouveau_connector_mode_valid(struct drm_connector *connector,
 			     struct drm_display_mode *mode)
 {
@@ -1321,7 +1321,7 @@ nouveau_connector_create(struct drm_device *dev, int index)
 	}
 
 	/* HDMI 3D support */
-	if ((disp->disp.oclass >= G82_DISP)
+	if ((disp->disp.object.oclass >= G82_DISP)
 	    && ((type == DRM_MODE_CONNECTOR_DisplayPort)
 		|| (type == DRM_MODE_CONNECTOR_eDP)
 		|| (type == DRM_MODE_CONNECTOR_HDMIA)))
@@ -1343,7 +1343,7 @@ nouveau_connector_create(struct drm_device *dev, int index)
 	case DCB_CONNECTOR_LVDS_SPWG:
 	case DCB_CONNECTOR_eDP:
 		/* see note in nouveau_connector_set_property() */
-		if (disp->disp.oclass < NV50_DISP) {
+		if (disp->disp.object.oclass < NV50_DISP) {
 			nv_connector->scaling_mode = DRM_MODE_SCALE_FULLSCREEN;
 			break;
 		}
@@ -1366,8 +1366,8 @@ nouveau_connector_create(struct drm_device *dev, int index)
 		break;
 	}
 
-	ret = nvif_notify_init(&disp->disp, nouveau_connector_hotplug, true,
-			       NV04_DISP_NTFY_CONN,
+	ret = nvif_notify_init(&disp->disp.object, nouveau_connector_hotplug,
+			       true, NV04_DISP_NTFY_CONN,
 			       &(struct nvif_notify_conn_req_v0) {
 				.mask = NVIF_NOTIFY_CONN_V0_ANY,
 				.conn = index,
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 009713404cc4..774b429142bc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -116,7 +116,7 @@ nouveau_display_scanoutpos_head(struct drm_crtc *crtc, int *vpos, int *hpos,
 	bool ret = false;
 
 	do {
-		ret = nvif_mthd(&disp->disp, 0, &args, sizeof(args));
+		ret = nvif_mthd(&disp->disp.object, 0, &args, sizeof(args));
 		if (ret != 0)
 			return false;
 
@@ -175,7 +175,7 @@ nouveau_display_vblank_init(struct drm_device *dev)
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
-		ret = nvif_notify_init(&disp->disp,
+		ret = nvif_notify_init(&disp->disp.object,
 				       nouveau_display_vblank_handler, false,
 				       NV04_DISP_NTFY_VBLANK,
 				       &(struct nvif_notify_head_req_v0) {
@@ -338,11 +338,9 @@ static struct nouveau_drm_prop_enum_list dither_depth[] = {
 	if (c) {                                                               \
 		p = drm_property_create(dev, DRM_MODE_PROP_ENUM, n, c);        \
 		l = (list);                                                    \
-		c = 0;                                                         \
 		while (p && l->gen_mask) {                                     \
 			if (l->gen_mask & (1 << (gen))) {                      \
-				drm_property_add_enum(p, c, l->type, l->name); \
-				c++;                                           \
+				drm_property_add_enum(p, l->type, l->name);    \
 			}                                                      \
 			l++;                                                   \
 		}                                                              \
@@ -456,10 +454,10 @@ nouveau_display_create_properties(struct drm_device *dev)
 	struct nouveau_display *disp = nouveau_display(dev);
 	int gen;
 
-	if (disp->disp.oclass < NV50_DISP)
+	if (disp->disp.object.oclass < NV50_DISP)
 		gen = 0;
 	else
-	if (disp->disp.oclass < GF110_DISP)
+	if (disp->disp.object.oclass < GF110_DISP)
 		gen = 1;
 	else
 		gen = 2;
@@ -535,31 +533,10 @@ nouveau_display_create(struct drm_device *dev)
 	drm_kms_helper_poll_disable(dev);
 
 	if (nouveau_modeset != 2 && drm->vbios.dcb.entries) {
-		static const u16 oclass[] = {
-			GP102_DISP,
-			GP100_DISP,
-			GM200_DISP,
-			GM107_DISP,
-			GK110_DISP,
-			GK104_DISP,
-			GF110_DISP,
-			GT214_DISP,
-			GT206_DISP,
-			GT200_DISP,
-			G82_DISP,
-			NV50_DISP,
-			NV04_DISP,
-		};
-		int i;
-
-		for (i = 0, ret = -ENODEV; ret && i < ARRAY_SIZE(oclass); i++) {
-			ret = nvif_object_init(&drm->client.device.object, 0,
-					       oclass[i], NULL, 0, &disp->disp);
-		}
-
+		ret = nvif_disp_ctor(&drm->client.device, 0, &disp->disp);
 		if (ret == 0) {
 			nouveau_display_create_properties(dev);
-			if (disp->disp.oclass < NV50_DISP)
+			if (disp->disp.object.oclass < NV50_DISP)
 				ret = nv04_display_create(dev);
 			else
 				ret = nv50_display_create(dev);
@@ -613,7 +590,7 @@ nouveau_display_destroy(struct drm_device *dev)
 	if (disp->dtor)
 		disp->dtor(dev);
 
-	nvif_object_fini(&disp->disp);
+	nvif_disp_dtor(&disp->disp);
 
 	nouveau_drm(dev)->display = NULL;
 	kfree(disp);
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h
index 270ba56f2756..54aa7c3fa42d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.h
+++ b/drivers/gpu/drm/nouveau/nouveau_display.h
@@ -2,6 +2,7 @@
 #ifndef __NOUVEAU_DISPLAY_H__
 #define __NOUVEAU_DISPLAY_H__
 #include "nouveau_drv.h"
+#include <nvif/disp.h>
 
 struct nouveau_framebuffer {
 	struct drm_framebuffer base;
@@ -38,7 +39,7 @@ struct nouveau_display {
 	int  (*init)(struct drm_device *);
 	void (*fini)(struct drm_device *);
 
-	struct nvif_object disp;
+	struct nvif_disp disp;
 
 	struct drm_property *dithering_mode;
 	struct drm_property *dithering_depth;
diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.c b/drivers/gpu/drm/nouveau/nouveau_dma.c
index 10e84f6ca2b7..945afd34138e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dma.c
@@ -28,6 +28,8 @@
 #include "nouveau_dma.h"
 #include "nouveau_vmm.h"
 
+#include <nvif/user.h>
+
 void
 OUT_RINGp(struct nouveau_channel *chan, const void *data, unsigned nr_dwords)
 {
@@ -80,18 +82,11 @@ READ_GET(struct nouveau_channel *chan, uint64_t *prev_get, int *timeout)
 }
 
 void
-nv50_dma_push(struct nouveau_channel *chan, struct nouveau_bo *bo,
-	      int delta, int length)
+nv50_dma_push(struct nouveau_channel *chan, u64 offset, int length)
 {
-	struct nouveau_cli *cli = (void *)chan->user.client;
+	struct nvif_user *user = &chan->drm->client.device.user;
 	struct nouveau_bo *pb = chan->push.buffer;
-	struct nouveau_vma *vma;
 	int ip = (chan->dma.ib_put * 2) + chan->dma.ib_base;
-	u64 offset;
-
-	vma = nouveau_vma_find(bo, &cli->vmm);
-	BUG_ON(!vma);
-	offset = vma->addr + delta;
 
 	BUG_ON(chan->dma.ib_free < 1);
 
@@ -105,6 +100,8 @@ nv50_dma_push(struct nouveau_channel *chan, struct nouveau_bo *bo,
 	nouveau_bo_rd32(pb, 0);
 
 	nvif_wr32(&chan->user, 0x8c, chan->dma.ib_put);
+	if (user->func && user->func->doorbell)
+		user->func->doorbell(user, chan->chid);
 	chan->dma.ib_free--;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.h b/drivers/gpu/drm/nouveau/nouveau_dma.h
index 74e10b14a7da..fc5e3f41282d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dma.h
+++ b/drivers/gpu/drm/nouveau/nouveau_dma.h
@@ -31,8 +31,7 @@
 #include "nouveau_chan.h"
 
 int nouveau_dma_wait(struct nouveau_channel *, int slots, int size);
-void nv50_dma_push(struct nouveau_channel *, struct nouveau_bo *,
-		   int delta, int length);
+void nv50_dma_push(struct nouveau_channel *, u64 addr, int length);
 
 /*
  * There's a hw race condition where you can't jump to your PUT offset,
@@ -55,7 +54,6 @@ enum {
 
 	NvSub2D		= 3, /* DO NOT CHANGE - hardcoded for kepler gr fifo */
 	NvSubCopy	= 4, /* DO NOT CHANGE - hardcoded for kepler gr fifo */
-	FermiSw		= 5, /* DO NOT CHANGE (well.. 6/7 will work...) */
 };
 
 /* Object handles - for stuff that's doesn't use handle == oclass. */
@@ -151,7 +149,7 @@ FIRE_RING(struct nouveau_channel *chan)
 	chan->accel_done = true;
 
 	if (chan->dma.ib_max) {
-		nv50_dma_push(chan, chan->push.buffer, chan->dma.put << 2,
+		nv50_dma_push(chan, chan->push.addr + (chan->dma.put << 2),
 			      (chan->dma.cur - chan->dma.put) << 2);
 	} else {
 		WRITE_PUT(chan->dma.cur);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index bbbf353682e1..775443c9af94 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -38,6 +38,8 @@
 #include <core/tegra.h>
 
 #include <nvif/driver.h>
+#include <nvif/fifo.h>
+#include <nvif/user.h>
 
 #include <nvif/class.h>
 #include <nvif/cl0002.h>
@@ -112,24 +114,22 @@ nouveau_name(struct drm_device *dev)
 }
 
 static inline bool
-nouveau_cli_work_ready(struct dma_fence *fence, bool wait)
+nouveau_cli_work_ready(struct dma_fence *fence)
 {
-	if (!dma_fence_is_signaled(fence)) {
-		if (!wait)
-			return false;
-		WARN_ON(dma_fence_wait_timeout(fence, false, 2 * HZ) <= 0);
-	}
+	if (!dma_fence_is_signaled(fence))
+		return false;
 	dma_fence_put(fence);
 	return true;
 }
 
 static void
-nouveau_cli_work_flush(struct nouveau_cli *cli, bool wait)
+nouveau_cli_work(struct work_struct *w)
 {
+	struct nouveau_cli *cli = container_of(w, typeof(*cli), work);
 	struct nouveau_cli_work *work, *wtmp;
 	mutex_lock(&cli->lock);
 	list_for_each_entry_safe(work, wtmp, &cli->worker, head) {
-		if (!work->fence || nouveau_cli_work_ready(work->fence, wait)) {
+		if (!work->fence || nouveau_cli_work_ready(work->fence)) {
 			list_del(&work->head);
 			work->func(work);
 		}
@@ -158,16 +158,16 @@ nouveau_cli_work_queue(struct nouveau_cli *cli, struct dma_fence *fence,
 }
 
 static void
-nouveau_cli_work(struct work_struct *w)
-{
-	struct nouveau_cli *cli = container_of(w, typeof(*cli), work);
-	nouveau_cli_work_flush(cli, false);
-}
-
-static void
 nouveau_cli_fini(struct nouveau_cli *cli)
 {
-	nouveau_cli_work_flush(cli, true);
+	/* All our channels are dead now, which means all the fences they
+	 * own are signalled, and all callback functions have been called.
+	 *
+	 * So, after flushing the workqueue, there should be nothing left.
+	 */
+	flush_work(&cli->work);
+	WARN_ON(!list_empty(&cli->worker));
+
 	usif_client_fini(cli);
 	nouveau_vmm_fini(&cli->vmm);
 	nvif_mmu_fini(&cli->mmu);
@@ -307,6 +307,16 @@ nouveau_accel_init(struct nouveau_drm *drm)
 	if (nouveau_noaccel)
 		return;
 
+	ret = nouveau_channels_init(drm);
+	if (ret)
+		return;
+
+	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_VOLTA) {
+		ret = nvif_user_init(device);
+		if (ret)
+			return;
+	}
+
 	/* initialise synchronisation routines */
 	/*XXX: this is crap, but the fence/channel stuff is a little
 	 *     backwards in some places.  this will be fixed.
@@ -338,6 +348,7 @@ nouveau_accel_init(struct nouveau_drm *drm)
 		case KEPLER_CHANNEL_GPFIFO_B:
 		case MAXWELL_CHANNEL_GPFIFO_A:
 		case PASCAL_CHANNEL_GPFIFO_A:
+		case VOLTA_CHANNEL_GPFIFO_A:
 			ret = nvc0_fence_create(drm);
 			break;
 		default:
@@ -354,13 +365,12 @@ nouveau_accel_init(struct nouveau_drm *drm)
 
 	if (device->info.family >= NV_DEVICE_INFO_V0_KEPLER) {
 		ret = nouveau_channel_new(drm, &drm->client.device,
-					  NVA06F_V0_ENGINE_CE0 |
-					  NVA06F_V0_ENGINE_CE1,
-					  0, &drm->cechan);
+					  nvif_fifo_runlist_ce(device), 0,
+					  &drm->cechan);
 		if (ret)
 			NV_ERROR(drm, "failed to create ce channel, %d\n", ret);
 
-		arg0 = NVA06F_V0_ENGINE_GR;
+		arg0 = nvif_fifo_runlist(device, NV_DEVICE_INFO_ENGINE_GR);
 		arg1 = 1;
 	} else
 	if (device->info.chipset >= 0xa3 &&
@@ -386,38 +396,36 @@ nouveau_accel_init(struct nouveau_drm *drm)
 		return;
 	}
 
-	ret = nvif_object_init(&drm->channel->user, NVDRM_NVSW,
-			       nouveau_abi16_swclass(drm), NULL, 0, &drm->nvsw);
-	if (ret == 0) {
-		ret = RING_SPACE(drm->channel, 2);
+	if (device->info.family < NV_DEVICE_INFO_V0_TESLA) {
+		ret = nvif_object_init(&drm->channel->user, NVDRM_NVSW,
+				       nouveau_abi16_swclass(drm), NULL, 0,
+				       &drm->nvsw);
 		if (ret == 0) {
-			if (device->info.family < NV_DEVICE_INFO_V0_FERMI) {
+			ret = RING_SPACE(drm->channel, 2);
+			if (ret == 0) {
 				BEGIN_NV04(drm->channel, NvSubSw, 0, 1);
-				OUT_RING  (drm->channel, NVDRM_NVSW);
-			} else
-			if (device->info.family < NV_DEVICE_INFO_V0_KEPLER) {
-				BEGIN_NVC0(drm->channel, FermiSw, 0, 1);
-				OUT_RING  (drm->channel, 0x001f0000);
+				OUT_RING  (drm->channel, drm->nvsw.handle);
+			}
+
+			ret = nvif_notify_init(&drm->nvsw,
+					       nouveau_flip_complete,
+					       false, NV04_NVSW_NTFY_UEVENT,
+					       NULL, 0, 0, &drm->flip);
+			if (ret == 0)
+				ret = nvif_notify_get(&drm->flip);
+			if (ret) {
+				nouveau_accel_fini(drm);
+				return;
 			}
 		}
 
-		ret = nvif_notify_init(&drm->nvsw, nouveau_flip_complete,
-				       false, NV04_NVSW_NTFY_UEVENT,
-				       NULL, 0, 0, &drm->flip);
-		if (ret == 0)
-			ret = nvif_notify_get(&drm->flip);
 		if (ret) {
+			NV_ERROR(drm, "failed to allocate sw class, %d\n", ret);
 			nouveau_accel_fini(drm);
 			return;
 		}
 	}
 
-	if (ret) {
-		NV_ERROR(drm, "failed to allocate software object, %d\n", ret);
-		nouveau_accel_fini(drm);
-		return;
-	}
-
 	if (device->info.family < NV_DEVICE_INFO_V0_FERMI) {
 		ret = nvkm_gpuobj_new(nvxx_device(&drm->client.device), 32, 0,
 				      false, NULL, &drm->notify);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 881b44b89a01..6e1acaec3400 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -170,6 +170,12 @@ struct nouveau_drm {
 	/* synchronisation */
 	void *fence;
 
+	/* Global channel management. */
+	struct {
+		int nr;
+		u64 context_base;
+	} chan;
+
 	/* context for accelerated drm-internal operations */
 	struct nouveau_channel *cechan;
 	struct nouveau_channel *channel;
diff --git a/drivers/gpu/drm/nouveau/nouveau_encoder.h b/drivers/gpu/drm/nouveau/nouveau_encoder.h
index e28d966946a1..3517f920bf89 100644
--- a/drivers/gpu/drm/nouveau/nouveau_encoder.h
+++ b/drivers/gpu/drm/nouveau/nouveau_encoder.h
@@ -32,6 +32,7 @@
 #include <drm/drm_encoder_slave.h>
 #include <drm/drm_dp_mst_helper.h>
 #include "dispnv04/disp.h"
+struct nv50_head_atom;
 
 #define NV_DPMS_CLEARED 0x80
 
@@ -68,7 +69,7 @@ struct nouveau_encoder {
 	void (*enc_save)(struct drm_encoder *encoder);
 	void (*enc_restore)(struct drm_encoder *encoder);
 	void (*update)(struct nouveau_encoder *, u8 head,
-		       struct drm_display_mode *, u8 proto, u8 depth);
+		       struct nv50_head_atom *, u8 proto, u8 depth);
 };
 
 struct nouveau_encoder *
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 503fa94dc06d..412d49bc6e56 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -74,15 +74,14 @@ nouveau_fence_signal(struct nouveau_fence *fence)
 }
 
 static struct nouveau_fence *
-nouveau_local_fence(struct dma_fence *fence, struct nouveau_drm *drm) {
-	struct nouveau_fence_priv *priv = (void*)drm->fence;
-
+nouveau_local_fence(struct dma_fence *fence, struct nouveau_drm *drm)
+{
 	if (fence->ops != &nouveau_fence_ops_legacy &&
 	    fence->ops != &nouveau_fence_ops_uevent)
 		return NULL;
 
-	if (fence->context < priv->context_base ||
-	    fence->context >= priv->context_base + priv->contexts)
+	if (fence->context < drm->chan.context_base ||
+	    fence->context >= drm->chan.context_base + drm->chan.nr)
 		return NULL;
 
 	return from_fence(fence);
@@ -176,7 +175,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
-	fctx->context = priv->context_base + chan->chid;
+	fctx->context = chan->drm->chan.context_base + chan->chid;
 
 	if (chan == chan->drm->cechan)
 		strcpy(fctx->name, "copy engine channel");
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 5bd8d30d1657..b999e6058046 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -55,8 +55,6 @@ struct nouveau_fence_priv {
 	int  (*context_new)(struct nouveau_channel *);
 	void (*context_del)(struct nouveau_channel *);
 
-	u32 contexts;
-	u64 context_base;
 	bool uevent;
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index e72a7e37eb0a..300daee74209 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -99,6 +99,7 @@ struct nouveau_gem_object_unmap {
 static void
 nouveau_gem_object_delete(struct nouveau_vma *vma)
 {
+	nouveau_fence_unref(&vma->fence);
 	nouveau_vma_del(&vma);
 }
 
@@ -114,25 +115,12 @@ nouveau_gem_object_delete_work(struct nouveau_cli_work *w)
 static void
 nouveau_gem_object_unmap(struct nouveau_bo *nvbo, struct nouveau_vma *vma)
 {
-	const bool mapped = nvbo->bo.mem.mem_type != TTM_PL_SYSTEM;
-	struct reservation_object *resv = nvbo->bo.resv;
-	struct reservation_object_list *fobj;
+	struct dma_fence *fence = vma->fence ? &vma->fence->base : NULL;
 	struct nouveau_gem_object_unmap *work;
-	struct dma_fence *fence = NULL;
-
-	fobj = reservation_object_get_list(resv);
 
 	list_del_init(&vma->head);
 
-	if (fobj && fobj->shared_count > 1)
-		ttm_bo_wait(&nvbo->bo, false, false);
-	else if (fobj && fobj->shared_count == 1)
-		fence = rcu_dereference_protected(fobj->shared[0],
-						reservation_object_held(resv));
-	else
-		fence = reservation_object_get_excl(nvbo->bo.resv);
-
-	if (!fence || !mapped) {
+	if (!fence) {
 		nouveau_gem_object_delete(vma);
 		return;
 	}
@@ -344,9 +332,20 @@ validate_fini_no_ticket(struct validate_op *op, struct nouveau_fence *fence,
 		nvbo = list_entry(op->list.next, struct nouveau_bo, entry);
 		b = &pbbo[nvbo->pbbo_index];
 
-		if (likely(fence))
+		if (likely(fence)) {
+			struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
+			struct nouveau_vma *vma;
+
 			nouveau_bo_fence(nvbo, fence, !!b->write_domains);
 
+			if (drm->client.vmm.vmm.object.oclass >= NVIF_CLASS_VMM_NV50) {
+				vma = (void *)(unsigned long)b->user_priv;
+				nouveau_fence_unref(&vma->fence);
+				dma_fence_get(&fence->base);
+				vma->fence = fence;
+			}
+		}
+
 		if (unlikely(nvbo->validate_mapped)) {
 			ttm_bo_kunmap(&nvbo->kmap);
 			nvbo->validate_mapped = false;
@@ -432,7 +431,20 @@ retry:
 			}
 		}
 
-		b->user_priv = (uint64_t)(unsigned long)nvbo;
+		if (cli->vmm.vmm.object.oclass >= NVIF_CLASS_VMM_NV50) {
+			struct nouveau_vmm *vmm = &cli->vmm;
+			struct nouveau_vma *vma = nouveau_vma_find(nvbo, vmm);
+			if (!vma) {
+				NV_PRINTK(err, cli, "vma not found!\n");
+				ret = -EINVAL;
+				break;
+			}
+
+			b->user_priv = (uint64_t)(unsigned long)vma;
+		} else {
+			b->user_priv = (uint64_t)(unsigned long)nvbo;
+		}
+
 		nvbo->reserved_by = file_priv;
 		nvbo->pbbo_index = i;
 		if ((b->valid_domains & NOUVEAU_GEM_DOMAIN_VRAM) &&
@@ -763,10 +775,10 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 		}
 
 		for (i = 0; i < req->nr_push; i++) {
-			struct nouveau_bo *nvbo = (void *)(unsigned long)
+			struct nouveau_vma *vma = (void *)(unsigned long)
 				bo[push[i].bo_index].user_priv;
 
-			nv50_dma_push(chan, nvbo, push[i].offset,
+			nv50_dma_push(chan, vma->addr + push[i].offset,
 				      push[i].length);
 		}
 	} else
diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
index 7c965648df80..44178b4c3599 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hwmon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
@@ -327,7 +327,7 @@ nouveau_temp_is_visible(const void *data, u32 attr, int channel)
 	struct nouveau_drm *drm = nouveau_drm((struct drm_device *)data);
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
 
-	if (therm && therm->attr_get && nvkm_therm_temp_get(therm) < 0)
+	if (!therm || !therm->attr_get || nvkm_therm_temp_get(therm) < 0)
 		return 0;
 
 	switch (attr) {
@@ -351,8 +351,8 @@ nouveau_pwm_is_visible(const void *data, u32 attr, int channel)
 	struct nouveau_drm *drm = nouveau_drm((struct drm_device *)data);
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
 
-	if (therm && therm->attr_get && therm->fan_get &&
-				therm->fan_get(therm) < 0)
+	if (!therm || !therm->attr_get || !therm->fan_get ||
+	    therm->fan_get(therm) < 0)
 		return 0;
 
 	switch (attr) {
@@ -707,13 +707,20 @@ nouveau_hwmon_init(struct drm_device *dev)
 {
 #if defined(CONFIG_HWMON) || (defined(MODULE) && defined(CONFIG_HWMON_MODULE))
 	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_iccsense *iccsense = nvxx_iccsense(&drm->client.device);
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	struct nvkm_volt *volt = nvxx_volt(&drm->client.device);
 	const struct attribute_group *special_groups[N_ATTR_GROUPS];
 	struct nouveau_hwmon *hwmon;
 	struct device *hwmon_dev;
 	int ret = 0;
 	int i = 0;
 
+	if (!iccsense && !therm && !volt) {
+		NV_DEBUG(drm, "Skipping hwmon registration\n");
+		return 0;
+	}
+
 	hwmon = drm->hwmon = kzalloc(sizeof(*hwmon), GFP_KERNEL);
 	if (!hwmon)
 		return -ENOMEM;
@@ -749,6 +756,9 @@ nouveau_hwmon_fini(struct drm_device *dev)
 #if defined(CONFIG_HWMON) || (defined(MODULE) && defined(CONFIG_HWMON_MODULE))
 	struct nouveau_hwmon *hwmon = nouveau_hwmon(dev);
 
+	if (!hwmon)
+		return;
+
 	if (hwmon->hwmon)
 		hwmon_device_unregister(hwmon->hwmon);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index dff51a0ee028..8c093ca4222e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -63,7 +63,7 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
 			 struct ttm_mem_reg *reg)
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
-	struct nouveau_drm *drm = nvbo->cli->drm;
+	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct nouveau_mem *mem;
 	int ret;
 
@@ -103,7 +103,7 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 			 struct ttm_mem_reg *reg)
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
-	struct nouveau_drm *drm = nvbo->cli->drm;
+	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct nouveau_mem *mem;
 	int ret;
 
@@ -131,7 +131,7 @@ nv04_gart_manager_new(struct ttm_mem_type_manager *man,
 		      struct ttm_mem_reg *reg)
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
-	struct nouveau_drm *drm = nvbo->cli->drm;
+	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct nouveau_mem *mem;
 	int ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c
index f5371d96b003..2032c3e4f6e5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c
@@ -92,6 +92,7 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm,
 	vma->refs = 1;
 	vma->addr = ~0ULL;
 	vma->mem = NULL;
+	vma->fence = NULL;
 	list_add_tail(&vma->head, &nvbo->vma_list);
 
 	if (nvbo->bo.mem.mem_type != TTM_PL_SYSTEM &&
diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.h b/drivers/gpu/drm/nouveau/nouveau_vmm.h
index 5c31f43678d3..7e3b118cf7c4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vmm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_vmm.h
@@ -11,6 +11,8 @@ struct nouveau_vma {
 	u64 addr;
 
 	struct nouveau_mem *mem;
+
+	struct nouveau_fence *fence;
 };
 
 struct nouveau_vma *nouveau_vma_find(struct nouveau_bo *, struct nouveau_vmm *);
diff --git a/drivers/gpu/drm/nouveau/nv04_fence.c b/drivers/gpu/drm/nouveau/nv04_fence.c
index fa8f2375c398..c41e82be4893 100644
--- a/drivers/gpu/drm/nouveau/nv04_fence.c
+++ b/drivers/gpu/drm/nouveau/nv04_fence.c
@@ -109,7 +109,5 @@ nv04_fence_create(struct nouveau_drm *drm)
 	priv->base.dtor = nv04_fence_destroy;
 	priv->base.context_new = nv04_fence_context_new;
 	priv->base.context_del = nv04_fence_context_del;
-	priv->base.contexts = 15;
-	priv->base.context_base = dma_fence_context_alloc(priv->base.contexts);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nv10_fence.c b/drivers/gpu/drm/nouveau/nv10_fence.c
index 2998bde29211..4476b712dc84 100644
--- a/drivers/gpu/drm/nouveau/nv10_fence.c
+++ b/drivers/gpu/drm/nouveau/nv10_fence.c
@@ -103,8 +103,6 @@ nv10_fence_create(struct nouveau_drm *drm)
 	priv->base.dtor = nv10_fence_destroy;
 	priv->base.context_new = nv10_fence_context_new;
 	priv->base.context_del = nv10_fence_context_del;
-	priv->base.contexts = 31;
-	priv->base.context_base = dma_fence_context_alloc(priv->base.contexts);
 	spin_lock_init(&priv->lock);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c
index 6477b7069e14..5d613d43b84d 100644
--- a/drivers/gpu/drm/nouveau/nv17_fence.c
+++ b/drivers/gpu/drm/nouveau/nv17_fence.c
@@ -125,8 +125,6 @@ nv17_fence_create(struct nouveau_drm *drm)
 	priv->base.resume = nv17_fence_resume;
 	priv->base.context_new = nv17_fence_context_new;
 	priv->base.context_del = nv10_fence_context_del;
-	priv->base.contexts = 31;
-	priv->base.context_base = dma_fence_context_alloc(priv->base.contexts);
 	spin_lock_init(&priv->lock);
 
 	ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM,
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
deleted file mode 100644
index 8bd739cfd00d..000000000000
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ /dev/null
@@ -1,4559 +0,0 @@
-/*
- * Copyright 2011 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/hdmi.h>
-
-#include <drm/drmP.h>
-#include <drm/drm_atomic.h>
-#include <drm/drm_atomic_helper.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_dp_helper.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_plane_helper.h>
-#include <drm/drm_edid.h>
-
-#include <nvif/class.h>
-#include <nvif/cl0002.h>
-#include <nvif/cl5070.h>
-#include <nvif/cl507a.h>
-#include <nvif/cl507b.h>
-#include <nvif/cl507c.h>
-#include <nvif/cl507d.h>
-#include <nvif/cl507e.h>
-#include <nvif/event.h>
-
-#include "nouveau_drv.h"
-#include "nouveau_dma.h"
-#include "nouveau_gem.h"
-#include "nouveau_connector.h"
-#include "nouveau_encoder.h"
-#include "nouveau_crtc.h"
-#include "nouveau_fence.h"
-#include "nouveau_fbcon.h"
-#include "nv50_display.h"
-
-#define EVO_DMA_NR 9
-
-#define EVO_MASTER  (0x00)
-#define EVO_FLIP(c) (0x01 + (c))
-#define EVO_OVLY(c) (0x05 + (c))
-#define EVO_OIMM(c) (0x09 + (c))
-#define EVO_CURS(c) (0x0d + (c))
-
-/* offsets in shared sync bo of various structures */
-#define EVO_SYNC(c, o) ((c) * 0x0100 + (o))
-#define EVO_MAST_NTFY     EVO_SYNC(      0, 0x00)
-#define EVO_FLIP_SEM0(c)  EVO_SYNC((c) + 1, 0x00)
-#define EVO_FLIP_SEM1(c)  EVO_SYNC((c) + 1, 0x10)
-#define EVO_FLIP_NTFY0(c) EVO_SYNC((c) + 1, 0x20)
-#define EVO_FLIP_NTFY1(c) EVO_SYNC((c) + 1, 0x30)
-
-/******************************************************************************
- * Atomic state
- *****************************************************************************/
-#define nv50_atom(p) container_of((p), struct nv50_atom, state)
-
-struct nv50_atom {
-	struct drm_atomic_state state;
-
-	struct list_head outp;
-	bool lock_core;
-	bool flush_disable;
-};
-
-struct nv50_outp_atom {
-	struct list_head head;
-
-	struct drm_encoder *encoder;
-	bool flush_disable;
-
-	union {
-		struct {
-			bool ctrl:1;
-		};
-		u8 mask;
-	} clr;
-
-	union {
-		struct {
-			bool ctrl:1;
-		};
-		u8 mask;
-	} set;
-};
-
-#define nv50_head_atom(p) container_of((p), struct nv50_head_atom, state)
-
-struct nv50_head_atom {
-	struct drm_crtc_state state;
-
-	struct {
-		u16 iW;
-		u16 iH;
-		u16 oW;
-		u16 oH;
-	} view;
-
-	struct nv50_head_mode {
-		bool interlace;
-		u32 clock;
-		struct {
-			u16 active;
-			u16 synce;
-			u16 blanke;
-			u16 blanks;
-		} h;
-		struct {
-			u32 active;
-			u16 synce;
-			u16 blanke;
-			u16 blanks;
-			u16 blank2s;
-			u16 blank2e;
-			u16 blankus;
-		} v;
-	} mode;
-
-	struct {
-		bool visible;
-		u32 handle;
-		u64 offset:40;
-		u8  mode:4;
-	} lut;
-
-	struct {
-		bool visible;
-		u32 handle;
-		u64 offset:40;
-		u8  format;
-		u8  kind:7;
-		u8  layout:1;
-		u8  block:4;
-		u32 pitch:20;
-		u16 x;
-		u16 y;
-		u16 w;
-		u16 h;
-	} core;
-
-	struct {
-		bool visible;
-		u32 handle;
-		u64 offset:40;
-		u8  layout:1;
-		u8  format:1;
-	} curs;
-
-	struct {
-		u8  depth;
-		u8  cpp;
-		u16 x;
-		u16 y;
-		u16 w;
-		u16 h;
-	} base;
-
-	struct {
-		u8 cpp;
-	} ovly;
-
-	struct {
-		bool enable:1;
-		u8 bits:2;
-		u8 mode:4;
-	} dither;
-
-	struct {
-		struct {
-			u16 cos:12;
-			u16 sin:12;
-		} sat;
-	} procamp;
-
-	union {
-		struct {
-			bool ilut:1;
-			bool core:1;
-			bool curs:1;
-		};
-		u8 mask;
-	} clr;
-
-	union {
-		struct {
-			bool ilut:1;
-			bool core:1;
-			bool curs:1;
-			bool view:1;
-			bool mode:1;
-			bool base:1;
-			bool ovly:1;
-			bool dither:1;
-			bool procamp:1;
-		};
-		u16 mask;
-	} set;
-};
-
-static inline struct nv50_head_atom *
-nv50_head_atom_get(struct drm_atomic_state *state, struct drm_crtc *crtc)
-{
-	struct drm_crtc_state *statec = drm_atomic_get_crtc_state(state, crtc);
-	if (IS_ERR(statec))
-		return (void *)statec;
-	return nv50_head_atom(statec);
-}
-
-#define nv50_wndw_atom(p) container_of((p), struct nv50_wndw_atom, state)
-
-struct nv50_wndw_atom {
-	struct drm_plane_state state;
-	u8 interval;
-
-	struct {
-		u32  handle;
-		u16  offset:12;
-		bool awaken:1;
-	} ntfy;
-
-	struct {
-		u32 handle;
-		u16 offset:12;
-		u32 acquire;
-		u32 release;
-	} sema;
-
-	struct {
-		u8 enable:2;
-	} lut;
-
-	struct {
-		u8  mode:2;
-		u8  interval:4;
-
-		u8  format;
-		u8  kind:7;
-		u8  layout:1;
-		u8  block:4;
-		u32 pitch:20;
-		u16 w;
-		u16 h;
-
-		u32 handle;
-		u64 offset;
-	} image;
-
-	struct {
-		u16 x;
-		u16 y;
-	} point;
-
-	union {
-		struct {
-			bool ntfy:1;
-			bool sema:1;
-			bool image:1;
-		};
-		u8 mask;
-	} clr;
-
-	union {
-		struct {
-			bool ntfy:1;
-			bool sema:1;
-			bool image:1;
-			bool lut:1;
-			bool point:1;
-		};
-		u8 mask;
-	} set;
-};
-
-/******************************************************************************
- * EVO channel
- *****************************************************************************/
-
-struct nv50_chan {
-	struct nvif_object user;
-	struct nvif_device *device;
-};
-
-static int
-nv50_chan_create(struct nvif_device *device, struct nvif_object *disp,
-		 const s32 *oclass, u8 head, void *data, u32 size,
-		 struct nv50_chan *chan)
-{
-	struct nvif_sclass *sclass;
-	int ret, i, n;
-
-	chan->device = device;
-
-	ret = n = nvif_object_sclass_get(disp, &sclass);
-	if (ret < 0)
-		return ret;
-
-	while (oclass[0]) {
-		for (i = 0; i < n; i++) {
-			if (sclass[i].oclass == oclass[0]) {
-				ret = nvif_object_init(disp, 0, oclass[0],
-						       data, size, &chan->user);
-				if (ret == 0)
-					nvif_object_map(&chan->user, NULL, 0);
-				nvif_object_sclass_put(&sclass);
-				return ret;
-			}
-		}
-		oclass++;
-	}
-
-	nvif_object_sclass_put(&sclass);
-	return -ENOSYS;
-}
-
-static void
-nv50_chan_destroy(struct nv50_chan *chan)
-{
-	nvif_object_fini(&chan->user);
-}
-
-/******************************************************************************
- * PIO EVO channel
- *****************************************************************************/
-
-struct nv50_pioc {
-	struct nv50_chan base;
-};
-
-static void
-nv50_pioc_destroy(struct nv50_pioc *pioc)
-{
-	nv50_chan_destroy(&pioc->base);
-}
-
-static int
-nv50_pioc_create(struct nvif_device *device, struct nvif_object *disp,
-		 const s32 *oclass, u8 head, void *data, u32 size,
-		 struct nv50_pioc *pioc)
-{
-	return nv50_chan_create(device, disp, oclass, head, data, size,
-				&pioc->base);
-}
-
-/******************************************************************************
- * Overlay Immediate
- *****************************************************************************/
-
-struct nv50_oimm {
-	struct nv50_pioc base;
-};
-
-static int
-nv50_oimm_create(struct nvif_device *device, struct nvif_object *disp,
-		 int head, struct nv50_oimm *oimm)
-{
-	struct nv50_disp_cursor_v0 args = {
-		.head = head,
-	};
-	static const s32 oclass[] = {
-		GK104_DISP_OVERLAY,
-		GF110_DISP_OVERLAY,
-		GT214_DISP_OVERLAY,
-		G82_DISP_OVERLAY,
-		NV50_DISP_OVERLAY,
-		0
-	};
-
-	return nv50_pioc_create(device, disp, oclass, head, &args, sizeof(args),
-				&oimm->base);
-}
-
-/******************************************************************************
- * DMA EVO channel
- *****************************************************************************/
-
-struct nv50_dmac_ctxdma {
-	struct list_head head;
-	struct nvif_object object;
-};
-
-struct nv50_dmac {
-	struct nv50_chan base;
-	dma_addr_t handle;
-	u32 *ptr;
-
-	struct nvif_object sync;
-	struct nvif_object vram;
-	struct list_head ctxdma;
-
-	/* Protects against concurrent pushbuf access to this channel, lock is
-	 * grabbed by evo_wait (if the pushbuf reservation is successful) and
-	 * dropped again by evo_kick. */
-	struct mutex lock;
-};
-
-static void
-nv50_dmac_ctxdma_del(struct nv50_dmac_ctxdma *ctxdma)
-{
-	nvif_object_fini(&ctxdma->object);
-	list_del(&ctxdma->head);
-	kfree(ctxdma);
-}
-
-static struct nv50_dmac_ctxdma *
-nv50_dmac_ctxdma_new(struct nv50_dmac *dmac, struct nouveau_framebuffer *fb)
-{
-	struct nouveau_drm *drm = nouveau_drm(fb->base.dev);
-	struct nv50_dmac_ctxdma *ctxdma;
-	const u8    kind = fb->nvbo->kind;
-	const u32 handle = 0xfb000000 | kind;
-	struct {
-		struct nv_dma_v0 base;
-		union {
-			struct nv50_dma_v0 nv50;
-			struct gf100_dma_v0 gf100;
-			struct gf119_dma_v0 gf119;
-		};
-	} args = {};
-	u32 argc = sizeof(args.base);
-	int ret;
-
-	list_for_each_entry(ctxdma, &dmac->ctxdma, head) {
-		if (ctxdma->object.handle == handle)
-			return ctxdma;
-	}
-
-	if (!(ctxdma = kzalloc(sizeof(*ctxdma), GFP_KERNEL)))
-		return ERR_PTR(-ENOMEM);
-	list_add(&ctxdma->head, &dmac->ctxdma);
-
-	args.base.target = NV_DMA_V0_TARGET_VRAM;
-	args.base.access = NV_DMA_V0_ACCESS_RDWR;
-	args.base.start  = 0;
-	args.base.limit  = drm->client.device.info.ram_user - 1;
-
-	if (drm->client.device.info.chipset < 0x80) {
-		args.nv50.part = NV50_DMA_V0_PART_256;
-		argc += sizeof(args.nv50);
-	} else
-	if (drm->client.device.info.chipset < 0xc0) {
-		args.nv50.part = NV50_DMA_V0_PART_256;
-		args.nv50.kind = kind;
-		argc += sizeof(args.nv50);
-	} else
-	if (drm->client.device.info.chipset < 0xd0) {
-		args.gf100.kind = kind;
-		argc += sizeof(args.gf100);
-	} else {
-		args.gf119.page = GF119_DMA_V0_PAGE_LP;
-		args.gf119.kind = kind;
-		argc += sizeof(args.gf119);
-	}
-
-	ret = nvif_object_init(&dmac->base.user, handle, NV_DMA_IN_MEMORY,
-			       &args, argc, &ctxdma->object);
-	if (ret) {
-		nv50_dmac_ctxdma_del(ctxdma);
-		return ERR_PTR(ret);
-	}
-
-	return ctxdma;
-}
-
-static void
-nv50_dmac_destroy(struct nv50_dmac *dmac, struct nvif_object *disp)
-{
-	struct nvif_device *device = dmac->base.device;
-	struct nv50_dmac_ctxdma *ctxdma, *ctxtmp;
-
-	list_for_each_entry_safe(ctxdma, ctxtmp, &dmac->ctxdma, head) {
-		nv50_dmac_ctxdma_del(ctxdma);
-	}
-
-	nvif_object_fini(&dmac->vram);
-	nvif_object_fini(&dmac->sync);
-
-	nv50_chan_destroy(&dmac->base);
-
-	if (dmac->ptr) {
-		struct device *dev = nvxx_device(device)->dev;
-		dma_free_coherent(dev, PAGE_SIZE, dmac->ptr, dmac->handle);
-	}
-}
-
-static int
-nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
-		 const s32 *oclass, u8 head, void *data, u32 size, u64 syncbuf,
-		 struct nv50_dmac *dmac)
-{
-	struct nv50_disp_core_channel_dma_v0 *args = data;
-	struct nvif_object pushbuf;
-	int ret;
-
-	mutex_init(&dmac->lock);
-	INIT_LIST_HEAD(&dmac->ctxdma);
-
-	dmac->ptr = dma_alloc_coherent(nvxx_device(device)->dev, PAGE_SIZE,
-				       &dmac->handle, GFP_KERNEL);
-	if (!dmac->ptr)
-		return -ENOMEM;
-
-	ret = nvif_object_init(&device->object, 0, NV_DMA_FROM_MEMORY,
-			       &(struct nv_dma_v0) {
-					.target = NV_DMA_V0_TARGET_PCI_US,
-					.access = NV_DMA_V0_ACCESS_RD,
-					.start = dmac->handle + 0x0000,
-					.limit = dmac->handle + 0x0fff,
-			       }, sizeof(struct nv_dma_v0), &pushbuf);
-	if (ret)
-		return ret;
-
-	args->pushbuf = nvif_handle(&pushbuf);
-
-	ret = nv50_chan_create(device, disp, oclass, head, data, size,
-			       &dmac->base);
-	nvif_object_fini(&pushbuf);
-	if (ret)
-		return ret;
-
-	ret = nvif_object_init(&dmac->base.user, 0xf0000000, NV_DMA_IN_MEMORY,
-			       &(struct nv_dma_v0) {
-					.target = NV_DMA_V0_TARGET_VRAM,
-					.access = NV_DMA_V0_ACCESS_RDWR,
-					.start = syncbuf + 0x0000,
-					.limit = syncbuf + 0x0fff,
-			       }, sizeof(struct nv_dma_v0),
-			       &dmac->sync);
-	if (ret)
-		return ret;
-
-	ret = nvif_object_init(&dmac->base.user, 0xf0000001, NV_DMA_IN_MEMORY,
-			       &(struct nv_dma_v0) {
-					.target = NV_DMA_V0_TARGET_VRAM,
-					.access = NV_DMA_V0_ACCESS_RDWR,
-					.start = 0,
-					.limit = device->info.ram_user - 1,
-			       }, sizeof(struct nv_dma_v0),
-			       &dmac->vram);
-	if (ret)
-		return ret;
-
-	return ret;
-}
-
-/******************************************************************************
- * Core
- *****************************************************************************/
-
-struct nv50_mast {
-	struct nv50_dmac base;
-};
-
-static int
-nv50_core_create(struct nvif_device *device, struct nvif_object *disp,
-		 u64 syncbuf, struct nv50_mast *core)
-{
-	struct nv50_disp_core_channel_dma_v0 args = {
-		.pushbuf = 0xb0007d00,
-	};
-	static const s32 oclass[] = {
-		GP102_DISP_CORE_CHANNEL_DMA,
-		GP100_DISP_CORE_CHANNEL_DMA,
-		GM200_DISP_CORE_CHANNEL_DMA,
-		GM107_DISP_CORE_CHANNEL_DMA,
-		GK110_DISP_CORE_CHANNEL_DMA,
-		GK104_DISP_CORE_CHANNEL_DMA,
-		GF110_DISP_CORE_CHANNEL_DMA,
-		GT214_DISP_CORE_CHANNEL_DMA,
-		GT206_DISP_CORE_CHANNEL_DMA,
-		GT200_DISP_CORE_CHANNEL_DMA,
-		G82_DISP_CORE_CHANNEL_DMA,
-		NV50_DISP_CORE_CHANNEL_DMA,
-		0
-	};
-
-	return nv50_dmac_create(device, disp, oclass, 0, &args, sizeof(args),
-				syncbuf, &core->base);
-}
-
-/******************************************************************************
- * Base
- *****************************************************************************/
-
-struct nv50_sync {
-	struct nv50_dmac base;
-	u32 addr;
-	u32 data;
-};
-
-static int
-nv50_base_create(struct nvif_device *device, struct nvif_object *disp,
-		 int head, u64 syncbuf, struct nv50_sync *base)
-{
-	struct nv50_disp_base_channel_dma_v0 args = {
-		.pushbuf = 0xb0007c00 | head,
-		.head = head,
-	};
-	static const s32 oclass[] = {
-		GK110_DISP_BASE_CHANNEL_DMA,
-		GK104_DISP_BASE_CHANNEL_DMA,
-		GF110_DISP_BASE_CHANNEL_DMA,
-		GT214_DISP_BASE_CHANNEL_DMA,
-		GT200_DISP_BASE_CHANNEL_DMA,
-		G82_DISP_BASE_CHANNEL_DMA,
-		NV50_DISP_BASE_CHANNEL_DMA,
-		0
-	};
-
-	return nv50_dmac_create(device, disp, oclass, head, &args, sizeof(args),
-				syncbuf, &base->base);
-}
-
-/******************************************************************************
- * Overlay
- *****************************************************************************/
-
-struct nv50_ovly {
-	struct nv50_dmac base;
-};
-
-static int
-nv50_ovly_create(struct nvif_device *device, struct nvif_object *disp,
-		 int head, u64 syncbuf, struct nv50_ovly *ovly)
-{
-	struct nv50_disp_overlay_channel_dma_v0 args = {
-		.pushbuf = 0xb0007e00 | head,
-		.head = head,
-	};
-	static const s32 oclass[] = {
-		GK104_DISP_OVERLAY_CONTROL_DMA,
-		GF110_DISP_OVERLAY_CONTROL_DMA,
-		GT214_DISP_OVERLAY_CHANNEL_DMA,
-		GT200_DISP_OVERLAY_CHANNEL_DMA,
-		G82_DISP_OVERLAY_CHANNEL_DMA,
-		NV50_DISP_OVERLAY_CHANNEL_DMA,
-		0
-	};
-
-	return nv50_dmac_create(device, disp, oclass, head, &args, sizeof(args),
-				syncbuf, &ovly->base);
-}
-
-struct nv50_head {
-	struct nouveau_crtc base;
-	struct {
-		struct nouveau_bo *nvbo[2];
-		int next;
-	} lut;
-	struct nv50_ovly ovly;
-	struct nv50_oimm oimm;
-};
-
-#define nv50_head(c) ((struct nv50_head *)nouveau_crtc(c))
-#define nv50_ovly(c) (&nv50_head(c)->ovly)
-#define nv50_oimm(c) (&nv50_head(c)->oimm)
-#define nv50_chan(c) (&(c)->base.base)
-#define nv50_vers(c) nv50_chan(c)->user.oclass
-
-struct nv50_disp {
-	struct nvif_object *disp;
-	struct nv50_mast mast;
-
-	struct nouveau_bo *sync;
-
-	struct mutex mutex;
-};
-
-static struct nv50_disp *
-nv50_disp(struct drm_device *dev)
-{
-	return nouveau_display(dev)->priv;
-}
-
-#define nv50_mast(d) (&nv50_disp(d)->mast)
-
-/******************************************************************************
- * EVO channel helpers
- *****************************************************************************/
-static u32 *
-evo_wait(void *evoc, int nr)
-{
-	struct nv50_dmac *dmac = evoc;
-	struct nvif_device *device = dmac->base.device;
-	u32 put = nvif_rd32(&dmac->base.user, 0x0000) / 4;
-
-	mutex_lock(&dmac->lock);
-	if (put + nr >= (PAGE_SIZE / 4) - 8) {
-		dmac->ptr[put] = 0x20000000;
-
-		nvif_wr32(&dmac->base.user, 0x0000, 0x00000000);
-		if (nvif_msec(device, 2000,
-			if (!nvif_rd32(&dmac->base.user, 0x0004))
-				break;
-		) < 0) {
-			mutex_unlock(&dmac->lock);
-			pr_err("nouveau: evo channel stalled\n");
-			return NULL;
-		}
-
-		put = 0;
-	}
-
-	return dmac->ptr + put;
-}
-
-static void
-evo_kick(u32 *push, void *evoc)
-{
-	struct nv50_dmac *dmac = evoc;
-	nvif_wr32(&dmac->base.user, 0x0000, (push - dmac->ptr) << 2);
-	mutex_unlock(&dmac->lock);
-}
-
-#define evo_mthd(p, m, s) do {						\
-	const u32 _m = (m), _s = (s);					\
-	if (drm_debug & DRM_UT_KMS)					\
-		pr_err("%04x %d %s\n", _m, _s, __func__);		\
-	*((p)++) = ((_s << 18) | _m);					\
-} while(0)
-
-#define evo_data(p, d) do {						\
-	const u32 _d = (d);						\
-	if (drm_debug & DRM_UT_KMS)					\
-		pr_err("\t%08x\n", _d);					\
-	*((p)++) = _d;							\
-} while(0)
-
-/******************************************************************************
- * Plane
- *****************************************************************************/
-#define nv50_wndw(p) container_of((p), struct nv50_wndw, plane)
-
-struct nv50_wndw {
-	const struct nv50_wndw_func *func;
-	struct nv50_dmac *dmac;
-
-	struct drm_plane plane;
-
-	struct nvif_notify notify;
-	u16 ntfy;
-	u16 sema;
-	u32 data;
-};
-
-struct nv50_wndw_func {
-	void *(*dtor)(struct nv50_wndw *);
-	int (*acquire)(struct nv50_wndw *, struct nv50_wndw_atom *asyw,
-		       struct nv50_head_atom *asyh);
-	void (*release)(struct nv50_wndw *, struct nv50_wndw_atom *asyw,
-			struct nv50_head_atom *asyh);
-	void (*prepare)(struct nv50_wndw *, struct nv50_head_atom *asyh,
-			struct nv50_wndw_atom *asyw);
-
-	void (*sema_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
-	void (*sema_clr)(struct nv50_wndw *);
-	void (*ntfy_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
-	void (*ntfy_clr)(struct nv50_wndw *);
-	int (*ntfy_wait_begun)(struct nv50_wndw *, struct nv50_wndw_atom *);
-	void (*image_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
-	void (*image_clr)(struct nv50_wndw *);
-	void (*lut)(struct nv50_wndw *, struct nv50_wndw_atom *);
-	void (*point)(struct nv50_wndw *, struct nv50_wndw_atom *);
-
-	u32 (*update)(struct nv50_wndw *, u32 interlock);
-};
-
-static int
-nv50_wndw_wait_armed(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
-{
-	if (asyw->set.ntfy)
-		return wndw->func->ntfy_wait_begun(wndw, asyw);
-	return 0;
-}
-
-static u32
-nv50_wndw_flush_clr(struct nv50_wndw *wndw, u32 interlock, bool flush,
-		    struct nv50_wndw_atom *asyw)
-{
-	if (asyw->clr.sema && (!asyw->set.sema || flush))
-		wndw->func->sema_clr(wndw);
-	if (asyw->clr.ntfy && (!asyw->set.ntfy || flush))
-		wndw->func->ntfy_clr(wndw);
-	if (asyw->clr.image && (!asyw->set.image || flush))
-		wndw->func->image_clr(wndw);
-
-	return flush ? wndw->func->update(wndw, interlock) : 0;
-}
-
-static u32
-nv50_wndw_flush_set(struct nv50_wndw *wndw, u32 interlock,
-		    struct nv50_wndw_atom *asyw)
-{
-	if (interlock) {
-		asyw->image.mode = 0;
-		asyw->image.interval = 1;
-	}
-
-	if (asyw->set.sema ) wndw->func->sema_set (wndw, asyw);
-	if (asyw->set.ntfy ) wndw->func->ntfy_set (wndw, asyw);
-	if (asyw->set.image) wndw->func->image_set(wndw, asyw);
-	if (asyw->set.lut  ) wndw->func->lut      (wndw, asyw);
-	if (asyw->set.point) wndw->func->point    (wndw, asyw);
-
-	return wndw->func->update(wndw, interlock);
-}
-
-static void
-nv50_wndw_atomic_check_release(struct nv50_wndw *wndw,
-			       struct nv50_wndw_atom *asyw,
-			       struct nv50_head_atom *asyh)
-{
-	struct nouveau_drm *drm = nouveau_drm(wndw->plane.dev);
-	NV_ATOMIC(drm, "%s release\n", wndw->plane.name);
-	wndw->func->release(wndw, asyw, asyh);
-	asyw->ntfy.handle = 0;
-	asyw->sema.handle = 0;
-}
-
-static int
-nv50_wndw_atomic_check_acquire(struct nv50_wndw *wndw,
-			       struct nv50_wndw_atom *asyw,
-			       struct nv50_head_atom *asyh)
-{
-	struct nouveau_framebuffer *fb = nouveau_framebuffer(asyw->state.fb);
-	struct nouveau_drm *drm = nouveau_drm(wndw->plane.dev);
-	int ret;
-
-	NV_ATOMIC(drm, "%s acquire\n", wndw->plane.name);
-
-	asyw->image.w = fb->base.width;
-	asyw->image.h = fb->base.height;
-	asyw->image.kind = fb->nvbo->kind;
-
-	if (asyh->state.pageflip_flags & DRM_MODE_PAGE_FLIP_ASYNC)
-		asyw->interval = 0;
-	else
-		asyw->interval = 1;
-
-	if (asyw->image.kind) {
-		asyw->image.layout = 0;
-		if (drm->client.device.info.chipset >= 0xc0)
-			asyw->image.block = fb->nvbo->mode >> 4;
-		else
-			asyw->image.block = fb->nvbo->mode;
-		asyw->image.pitch = (fb->base.pitches[0] / 4) << 4;
-	} else {
-		asyw->image.layout = 1;
-		asyw->image.block  = 0;
-		asyw->image.pitch  = fb->base.pitches[0];
-	}
-
-	ret = wndw->func->acquire(wndw, asyw, asyh);
-	if (ret)
-		return ret;
-
-	if (asyw->set.image) {
-		if (!(asyw->image.mode = asyw->interval ? 0 : 1))
-			asyw->image.interval = asyw->interval;
-		else
-			asyw->image.interval = 0;
-	}
-
-	return 0;
-}
-
-static int
-nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state)
-{
-	struct nouveau_drm *drm = nouveau_drm(plane->dev);
-	struct nv50_wndw *wndw = nv50_wndw(plane);
-	struct nv50_wndw_atom *armw = nv50_wndw_atom(wndw->plane.state);
-	struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
-	struct nv50_head_atom *harm = NULL, *asyh = NULL;
-	bool varm = false, asyv = false, asym = false;
-	int ret;
-
-	NV_ATOMIC(drm, "%s atomic_check\n", plane->name);
-	if (asyw->state.crtc) {
-		asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc);
-		if (IS_ERR(asyh))
-			return PTR_ERR(asyh);
-		asym = drm_atomic_crtc_needs_modeset(&asyh->state);
-		asyv = asyh->state.active;
-	}
-
-	if (armw->state.crtc) {
-		harm = nv50_head_atom_get(asyw->state.state, armw->state.crtc);
-		if (IS_ERR(harm))
-			return PTR_ERR(harm);
-		varm = harm->state.crtc->state->active;
-	}
-
-	if (asyv) {
-		asyw->point.x = asyw->state.crtc_x;
-		asyw->point.y = asyw->state.crtc_y;
-		if (memcmp(&armw->point, &asyw->point, sizeof(asyw->point)))
-			asyw->set.point = true;
-
-		ret = nv50_wndw_atomic_check_acquire(wndw, asyw, asyh);
-		if (ret)
-			return ret;
-	} else
-	if (varm) {
-		nv50_wndw_atomic_check_release(wndw, asyw, harm);
-	} else {
-		return 0;
-	}
-
-	if (!asyv || asym) {
-		asyw->clr.ntfy = armw->ntfy.handle != 0;
-		asyw->clr.sema = armw->sema.handle != 0;
-		if (wndw->func->image_clr)
-			asyw->clr.image = armw->image.handle != 0;
-		asyw->set.lut = wndw->func->lut && asyv;
-	}
-
-	return 0;
-}
-
-static void
-nv50_wndw_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state)
-{
-	struct nouveau_framebuffer *fb = nouveau_framebuffer(old_state->fb);
-	struct nouveau_drm *drm = nouveau_drm(plane->dev);
-
-	NV_ATOMIC(drm, "%s cleanup: %p\n", plane->name, old_state->fb);
-	if (!old_state->fb)
-		return;
-
-	nouveau_bo_unpin(fb->nvbo);
-}
-
-static int
-nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state)
-{
-	struct nouveau_framebuffer *fb = nouveau_framebuffer(state->fb);
-	struct nouveau_drm *drm = nouveau_drm(plane->dev);
-	struct nv50_wndw *wndw = nv50_wndw(plane);
-	struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
-	struct nv50_head_atom *asyh;
-	struct nv50_dmac_ctxdma *ctxdma;
-	int ret;
-
-	NV_ATOMIC(drm, "%s prepare: %p\n", plane->name, state->fb);
-	if (!asyw->state.fb)
-		return 0;
-
-	ret = nouveau_bo_pin(fb->nvbo, TTM_PL_FLAG_VRAM, true);
-	if (ret)
-		return ret;
-
-	ctxdma = nv50_dmac_ctxdma_new(wndw->dmac, fb);
-	if (IS_ERR(ctxdma)) {
-		nouveau_bo_unpin(fb->nvbo);
-		return PTR_ERR(ctxdma);
-	}
-
-	asyw->state.fence = reservation_object_get_excl_rcu(fb->nvbo->bo.resv);
-	asyw->image.handle = ctxdma->object.handle;
-	asyw->image.offset = fb->nvbo->bo.offset;
-
-	if (wndw->func->prepare) {
-		asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc);
-		if (IS_ERR(asyh))
-			return PTR_ERR(asyh);
-
-		wndw->func->prepare(wndw, asyh, asyw);
-	}
-
-	return 0;
-}
-
-static const struct drm_plane_helper_funcs
-nv50_wndw_helper = {
-	.prepare_fb = nv50_wndw_prepare_fb,
-	.cleanup_fb = nv50_wndw_cleanup_fb,
-	.atomic_check = nv50_wndw_atomic_check,
-};
-
-static void
-nv50_wndw_atomic_destroy_state(struct drm_plane *plane,
-			       struct drm_plane_state *state)
-{
-	struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
-	__drm_atomic_helper_plane_destroy_state(&asyw->state);
-	kfree(asyw);
-}
-
-static struct drm_plane_state *
-nv50_wndw_atomic_duplicate_state(struct drm_plane *plane)
-{
-	struct nv50_wndw_atom *armw = nv50_wndw_atom(plane->state);
-	struct nv50_wndw_atom *asyw;
-	if (!(asyw = kmalloc(sizeof(*asyw), GFP_KERNEL)))
-		return NULL;
-	__drm_atomic_helper_plane_duplicate_state(plane, &asyw->state);
-	asyw->interval = 1;
-	asyw->sema = armw->sema;
-	asyw->ntfy = armw->ntfy;
-	asyw->image = armw->image;
-	asyw->point = armw->point;
-	asyw->lut = armw->lut;
-	asyw->clr.mask = 0;
-	asyw->set.mask = 0;
-	return &asyw->state;
-}
-
-static void
-nv50_wndw_reset(struct drm_plane *plane)
-{
-	struct nv50_wndw_atom *asyw;
-
-	if (WARN_ON(!(asyw = kzalloc(sizeof(*asyw), GFP_KERNEL))))
-		return;
-
-	if (plane->state)
-		plane->funcs->atomic_destroy_state(plane, plane->state);
-	plane->state = &asyw->state;
-	plane->state->plane = plane;
-	plane->state->rotation = DRM_MODE_ROTATE_0;
-}
-
-static void
-nv50_wndw_destroy(struct drm_plane *plane)
-{
-	struct nv50_wndw *wndw = nv50_wndw(plane);
-	void *data;
-	nvif_notify_fini(&wndw->notify);
-	data = wndw->func->dtor(wndw);
-	drm_plane_cleanup(&wndw->plane);
-	kfree(data);
-}
-
-static const struct drm_plane_funcs
-nv50_wndw = {
-	.update_plane = drm_atomic_helper_update_plane,
-	.disable_plane = drm_atomic_helper_disable_plane,
-	.destroy = nv50_wndw_destroy,
-	.reset = nv50_wndw_reset,
-	.atomic_duplicate_state = nv50_wndw_atomic_duplicate_state,
-	.atomic_destroy_state = nv50_wndw_atomic_destroy_state,
-};
-
-static void
-nv50_wndw_fini(struct nv50_wndw *wndw)
-{
-	nvif_notify_put(&wndw->notify);
-}
-
-static void
-nv50_wndw_init(struct nv50_wndw *wndw)
-{
-	nvif_notify_get(&wndw->notify);
-}
-
-static int
-nv50_wndw_ctor(const struct nv50_wndw_func *func, struct drm_device *dev,
-	       enum drm_plane_type type, const char *name, int index,
-	       struct nv50_dmac *dmac, const u32 *format, int nformat,
-	       struct nv50_wndw *wndw)
-{
-	int ret;
-
-	wndw->func = func;
-	wndw->dmac = dmac;
-
-	ret = drm_universal_plane_init(dev, &wndw->plane, 0, &nv50_wndw,
-				       format, nformat, NULL,
-				       type, "%s-%d", name, index);
-	if (ret)
-		return ret;
-
-	drm_plane_helper_add(&wndw->plane, &nv50_wndw_helper);
-	return 0;
-}
-
-/******************************************************************************
- * Cursor plane
- *****************************************************************************/
-#define nv50_curs(p) container_of((p), struct nv50_curs, wndw)
-
-struct nv50_curs {
-	struct nv50_wndw wndw;
-	struct nvif_object chan;
-};
-
-static u32
-nv50_curs_update(struct nv50_wndw *wndw, u32 interlock)
-{
-	struct nv50_curs *curs = nv50_curs(wndw);
-	nvif_wr32(&curs->chan, 0x0080, 0x00000000);
-	return 0;
-}
-
-static void
-nv50_curs_point(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
-{
-	struct nv50_curs *curs = nv50_curs(wndw);
-	nvif_wr32(&curs->chan, 0x0084, (asyw->point.y << 16) | asyw->point.x);
-}
-
-static void
-nv50_curs_prepare(struct nv50_wndw *wndw, struct nv50_head_atom *asyh,
-		  struct nv50_wndw_atom *asyw)
-{
-	u32 handle = nv50_disp(wndw->plane.dev)->mast.base.vram.handle;
-	u32 offset = asyw->image.offset;
-	if (asyh->curs.handle != handle || asyh->curs.offset != offset) {
-		asyh->curs.handle = handle;
-		asyh->curs.offset = offset;
-		asyh->set.curs = asyh->curs.visible;
-	}
-}
-
-static void
-nv50_curs_release(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
-		  struct nv50_head_atom *asyh)
-{
-	asyh->curs.visible = false;
-}
-
-static int
-nv50_curs_acquire(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
-		  struct nv50_head_atom *asyh)
-{
-	int ret;
-
-	ret = drm_atomic_helper_check_plane_state(&asyw->state, &asyh->state,
-						  DRM_PLANE_HELPER_NO_SCALING,
-						  DRM_PLANE_HELPER_NO_SCALING,
-						  true, true);
-	asyh->curs.visible = asyw->state.visible;
-	if (ret || !asyh->curs.visible)
-		return ret;
-
-	switch (asyw->state.fb->width) {
-	case 32: asyh->curs.layout = 0; break;
-	case 64: asyh->curs.layout = 1; break;
-	default:
-		return -EINVAL;
-	}
-
-	if (asyw->state.fb->width != asyw->state.fb->height)
-		return -EINVAL;
-
-	switch (asyw->state.fb->format->format) {
-	case DRM_FORMAT_ARGB8888: asyh->curs.format = 1; break;
-	default:
-		WARN_ON(1);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static void *
-nv50_curs_dtor(struct nv50_wndw *wndw)
-{
-	struct nv50_curs *curs = nv50_curs(wndw);
-	nvif_object_fini(&curs->chan);
-	return curs;
-}
-
-static const u32
-nv50_curs_format[] = {
-	DRM_FORMAT_ARGB8888,
-};
-
-static const struct nv50_wndw_func
-nv50_curs = {
-	.dtor = nv50_curs_dtor,
-	.acquire = nv50_curs_acquire,
-	.release = nv50_curs_release,
-	.prepare = nv50_curs_prepare,
-	.point = nv50_curs_point,
-	.update = nv50_curs_update,
-};
-
-static int
-nv50_curs_new(struct nouveau_drm *drm, struct nv50_head *head,
-	      struct nv50_curs **pcurs)
-{
-	static const struct nvif_mclass curses[] = {
-		{ GK104_DISP_CURSOR, 0 },
-		{ GF110_DISP_CURSOR, 0 },
-		{ GT214_DISP_CURSOR, 0 },
-		{   G82_DISP_CURSOR, 0 },
-		{  NV50_DISP_CURSOR, 0 },
-		{}
-	};
-	struct nv50_disp_cursor_v0 args = {
-		.head = head->base.index,
-	};
-	struct nv50_disp *disp = nv50_disp(drm->dev);
-	struct nv50_curs *curs;
-	int cid, ret;
-
-	cid = nvif_mclass(disp->disp, curses);
-	if (cid < 0) {
-		NV_ERROR(drm, "No supported cursor immediate class\n");
-		return cid;
-	}
-
-	if (!(curs = *pcurs = kzalloc(sizeof(*curs), GFP_KERNEL)))
-		return -ENOMEM;
-
-	ret = nv50_wndw_ctor(&nv50_curs, drm->dev, DRM_PLANE_TYPE_CURSOR,
-			     "curs", head->base.index, &disp->mast.base,
-			     nv50_curs_format, ARRAY_SIZE(nv50_curs_format),
-			     &curs->wndw);
-	if (ret) {
-		kfree(curs);
-		return ret;
-	}
-
-	ret = nvif_object_init(disp->disp, 0, curses[cid].oclass, &args,
-			       sizeof(args), &curs->chan);
-	if (ret) {
-		NV_ERROR(drm, "curs%04x allocation failed: %d\n",
-			 curses[cid].oclass, ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-/******************************************************************************
- * Primary plane
- *****************************************************************************/
-#define nv50_base(p) container_of((p), struct nv50_base, wndw)
-
-struct nv50_base {
-	struct nv50_wndw wndw;
-	struct nv50_sync chan;
-	int id;
-};
-
-static int
-nv50_base_notify(struct nvif_notify *notify)
-{
-	return NVIF_NOTIFY_KEEP;
-}
-
-static void
-nv50_base_lut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
-{
-	struct nv50_base *base = nv50_base(wndw);
-	u32 *push;
-	if ((push = evo_wait(&base->chan, 2))) {
-		evo_mthd(push, 0x00e0, 1);
-		evo_data(push, asyw->lut.enable << 30);
-		evo_kick(push, &base->chan);
-	}
-}
-
-static void
-nv50_base_image_clr(struct nv50_wndw *wndw)
-{
-	struct nv50_base *base = nv50_base(wndw);
-	u32 *push;
-	if ((push = evo_wait(&base->chan, 4))) {
-		evo_mthd(push, 0x0084, 1);
-		evo_data(push, 0x00000000);
-		evo_mthd(push, 0x00c0, 1);
-		evo_data(push, 0x00000000);
-		evo_kick(push, &base->chan);
-	}
-}
-
-static void
-nv50_base_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
-{
-	struct nv50_base *base = nv50_base(wndw);
-	const s32 oclass = base->chan.base.base.user.oclass;
-	u32 *push;
-	if ((push = evo_wait(&base->chan, 10))) {
-		evo_mthd(push, 0x0084, 1);
-		evo_data(push, (asyw->image.mode << 8) |
-			       (asyw->image.interval << 4));
-		evo_mthd(push, 0x00c0, 1);
-		evo_data(push, asyw->image.handle);
-		if (oclass < G82_DISP_BASE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0800, 5);
-			evo_data(push, asyw->image.offset >> 8);
-			evo_data(push, 0x00000000);
-			evo_data(push, (asyw->image.h << 16) | asyw->image.w);
-			evo_data(push, (asyw->image.layout << 20) |
-					asyw->image.pitch |
-					asyw->image.block);
-			evo_data(push, (asyw->image.kind << 16) |
-				       (asyw->image.format << 8));
-		} else
-		if (oclass < GF110_DISP_BASE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0800, 5);
-			evo_data(push, asyw->image.offset >> 8);
-			evo_data(push, 0x00000000);
-			evo_data(push, (asyw->image.h << 16) | asyw->image.w);
-			evo_data(push, (asyw->image.layout << 20) |
-					asyw->image.pitch |
-					asyw->image.block);
-			evo_data(push, asyw->image.format << 8);
-		} else {
-			evo_mthd(push, 0x0400, 5);
-			evo_data(push, asyw->image.offset >> 8);
-			evo_data(push, 0x00000000);
-			evo_data(push, (asyw->image.h << 16) | asyw->image.w);
-			evo_data(push, (asyw->image.layout << 24) |
-					asyw->image.pitch |
-					asyw->image.block);
-			evo_data(push, asyw->image.format << 8);
-		}
-		evo_kick(push, &base->chan);
-	}
-}
-
-static void
-nv50_base_ntfy_clr(struct nv50_wndw *wndw)
-{
-	struct nv50_base *base = nv50_base(wndw);
-	u32 *push;
-	if ((push = evo_wait(&base->chan, 2))) {
-		evo_mthd(push, 0x00a4, 1);
-		evo_data(push, 0x00000000);
-		evo_kick(push, &base->chan);
-	}
-}
-
-static void
-nv50_base_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
-{
-	struct nv50_base *base = nv50_base(wndw);
-	u32 *push;
-	if ((push = evo_wait(&base->chan, 3))) {
-		evo_mthd(push, 0x00a0, 2);
-		evo_data(push, (asyw->ntfy.awaken << 30) | asyw->ntfy.offset);
-		evo_data(push, asyw->ntfy.handle);
-		evo_kick(push, &base->chan);
-	}
-}
-
-static void
-nv50_base_sema_clr(struct nv50_wndw *wndw)
-{
-	struct nv50_base *base = nv50_base(wndw);
-	u32 *push;
-	if ((push = evo_wait(&base->chan, 2))) {
-		evo_mthd(push, 0x0094, 1);
-		evo_data(push, 0x00000000);
-		evo_kick(push, &base->chan);
-	}
-}
-
-static void
-nv50_base_sema_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
-{
-	struct nv50_base *base = nv50_base(wndw);
-	u32 *push;
-	if ((push = evo_wait(&base->chan, 5))) {
-		evo_mthd(push, 0x0088, 4);
-		evo_data(push, asyw->sema.offset);
-		evo_data(push, asyw->sema.acquire);
-		evo_data(push, asyw->sema.release);
-		evo_data(push, asyw->sema.handle);
-		evo_kick(push, &base->chan);
-	}
-}
-
-static u32
-nv50_base_update(struct nv50_wndw *wndw, u32 interlock)
-{
-	struct nv50_base *base = nv50_base(wndw);
-	u32 *push;
-
-	if (!(push = evo_wait(&base->chan, 2)))
-		return 0;
-	evo_mthd(push, 0x0080, 1);
-	evo_data(push, interlock);
-	evo_kick(push, &base->chan);
-
-	if (base->chan.base.base.user.oclass < GF110_DISP_BASE_CHANNEL_DMA)
-		return interlock ? 2 << (base->id * 8) : 0;
-	return interlock ? 2 << (base->id * 4) : 0;
-}
-
-static int
-nv50_base_ntfy_wait_begun(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
-{
-	struct nouveau_drm *drm = nouveau_drm(wndw->plane.dev);
-	struct nv50_disp *disp = nv50_disp(wndw->plane.dev);
-	if (nvif_msec(&drm->client.device, 2000ULL,
-		u32 data = nouveau_bo_rd32(disp->sync, asyw->ntfy.offset / 4);
-		if ((data & 0xc0000000) == 0x40000000)
-			break;
-		usleep_range(1, 2);
-	) < 0)
-		return -ETIMEDOUT;
-	return 0;
-}
-
-static void
-nv50_base_release(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
-		  struct nv50_head_atom *asyh)
-{
-	asyh->base.cpp = 0;
-}
-
-static int
-nv50_base_acquire(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
-		  struct nv50_head_atom *asyh)
-{
-	const struct drm_framebuffer *fb = asyw->state.fb;
-	int ret;
-
-	if (!fb->format->depth)
-		return -EINVAL;
-
-	ret = drm_atomic_helper_check_plane_state(&asyw->state, &asyh->state,
-						  DRM_PLANE_HELPER_NO_SCALING,
-						  DRM_PLANE_HELPER_NO_SCALING,
-						  false, true);
-	if (ret)
-		return ret;
-
-	asyh->base.depth = fb->format->depth;
-	asyh->base.cpp = fb->format->cpp[0];
-	asyh->base.x = asyw->state.src.x1 >> 16;
-	asyh->base.y = asyw->state.src.y1 >> 16;
-	asyh->base.w = asyw->state.fb->width;
-	asyh->base.h = asyw->state.fb->height;
-
-	switch (fb->format->format) {
-	case DRM_FORMAT_C8         : asyw->image.format = 0x1e; break;
-	case DRM_FORMAT_RGB565     : asyw->image.format = 0xe8; break;
-	case DRM_FORMAT_XRGB1555   :
-	case DRM_FORMAT_ARGB1555   : asyw->image.format = 0xe9; break;
-	case DRM_FORMAT_XRGB8888   :
-	case DRM_FORMAT_ARGB8888   : asyw->image.format = 0xcf; break;
-	case DRM_FORMAT_XBGR2101010:
-	case DRM_FORMAT_ABGR2101010: asyw->image.format = 0xd1; break;
-	case DRM_FORMAT_XBGR8888   :
-	case DRM_FORMAT_ABGR8888   : asyw->image.format = 0xd5; break;
-	default:
-		WARN_ON(1);
-		return -EINVAL;
-	}
-
-	asyw->lut.enable = 1;
-	asyw->set.image = true;
-	return 0;
-}
-
-static void *
-nv50_base_dtor(struct nv50_wndw *wndw)
-{
-	struct nv50_disp *disp = nv50_disp(wndw->plane.dev);
-	struct nv50_base *base = nv50_base(wndw);
-	nv50_dmac_destroy(&base->chan.base, disp->disp);
-	return base;
-}
-
-static const u32
-nv50_base_format[] = {
-	DRM_FORMAT_C8,
-	DRM_FORMAT_RGB565,
-	DRM_FORMAT_XRGB1555,
-	DRM_FORMAT_ARGB1555,
-	DRM_FORMAT_XRGB8888,
-	DRM_FORMAT_ARGB8888,
-	DRM_FORMAT_XBGR2101010,
-	DRM_FORMAT_ABGR2101010,
-	DRM_FORMAT_XBGR8888,
-	DRM_FORMAT_ABGR8888,
-};
-
-static const struct nv50_wndw_func
-nv50_base = {
-	.dtor = nv50_base_dtor,
-	.acquire = nv50_base_acquire,
-	.release = nv50_base_release,
-	.sema_set = nv50_base_sema_set,
-	.sema_clr = nv50_base_sema_clr,
-	.ntfy_set = nv50_base_ntfy_set,
-	.ntfy_clr = nv50_base_ntfy_clr,
-	.ntfy_wait_begun = nv50_base_ntfy_wait_begun,
-	.image_set = nv50_base_image_set,
-	.image_clr = nv50_base_image_clr,
-	.lut = nv50_base_lut,
-	.update = nv50_base_update,
-};
-
-static int
-nv50_base_new(struct nouveau_drm *drm, struct nv50_head *head,
-	      struct nv50_base **pbase)
-{
-	struct nv50_disp *disp = nv50_disp(drm->dev);
-	struct nv50_base *base;
-	int ret;
-
-	if (!(base = *pbase = kzalloc(sizeof(*base), GFP_KERNEL)))
-		return -ENOMEM;
-	base->id = head->base.index;
-	base->wndw.ntfy = EVO_FLIP_NTFY0(base->id);
-	base->wndw.sema = EVO_FLIP_SEM0(base->id);
-	base->wndw.data = 0x00000000;
-
-	ret = nv50_wndw_ctor(&nv50_base, drm->dev, DRM_PLANE_TYPE_PRIMARY,
-			     "base", base->id, &base->chan.base,
-			     nv50_base_format, ARRAY_SIZE(nv50_base_format),
-			     &base->wndw);
-	if (ret) {
-		kfree(base);
-		return ret;
-	}
-
-	ret = nv50_base_create(&drm->client.device, disp->disp, base->id,
-			       disp->sync->bo.offset, &base->chan);
-	if (ret)
-		return ret;
-
-	return nvif_notify_init(&base->chan.base.base.user, nv50_base_notify,
-				false,
-				NV50_DISP_BASE_CHANNEL_DMA_V0_NTFY_UEVENT,
-				&(struct nvif_notify_uevent_req) {},
-				sizeof(struct nvif_notify_uevent_req),
-				sizeof(struct nvif_notify_uevent_rep),
-				&base->wndw.notify);
-}
-
-/******************************************************************************
- * Head
- *****************************************************************************/
-static void
-nv50_head_procamp(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 2))) {
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA)
-			evo_mthd(push, 0x08a8 + (head->base.index * 0x400), 1);
-		else
-			evo_mthd(push, 0x0498 + (head->base.index * 0x300), 1);
-		evo_data(push, (asyh->procamp.sat.sin << 20) |
-			       (asyh->procamp.sat.cos << 8));
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_dither(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 2))) {
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA)
-			evo_mthd(push, 0x08a0 + (head->base.index * 0x0400), 1);
-		else
-		if (core->base.user.oclass < GK104_DISP_CORE_CHANNEL_DMA)
-			evo_mthd(push, 0x0490 + (head->base.index * 0x0300), 1);
-		else
-			evo_mthd(push, 0x04a0 + (head->base.index * 0x0300), 1);
-		evo_data(push, (asyh->dither.mode << 3) |
-			       (asyh->dither.bits << 1) |
-			        asyh->dither.enable);
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_ovly(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 bounds = 0;
-	u32 *push;
-
-	if (asyh->base.cpp) {
-		switch (asyh->base.cpp) {
-		case 8: bounds |= 0x00000500; break;
-		case 4: bounds |= 0x00000300; break;
-		case 2: bounds |= 0x00000100; break;
-		default:
-			WARN_ON(1);
-			break;
-		}
-		bounds |= 0x00000001;
-	}
-
-	if ((push = evo_wait(core, 2))) {
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA)
-			evo_mthd(push, 0x0904 + head->base.index * 0x400, 1);
-		else
-			evo_mthd(push, 0x04d4 + head->base.index * 0x300, 1);
-		evo_data(push, bounds);
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_base(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 bounds = 0;
-	u32 *push;
-
-	if (asyh->base.cpp) {
-		switch (asyh->base.cpp) {
-		case 8: bounds |= 0x00000500; break;
-		case 4: bounds |= 0x00000300; break;
-		case 2: bounds |= 0x00000100; break;
-		case 1: bounds |= 0x00000000; break;
-		default:
-			WARN_ON(1);
-			break;
-		}
-		bounds |= 0x00000001;
-	}
-
-	if ((push = evo_wait(core, 2))) {
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA)
-			evo_mthd(push, 0x0900 + head->base.index * 0x400, 1);
-		else
-			evo_mthd(push, 0x04d0 + head->base.index * 0x300, 1);
-		evo_data(push, bounds);
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_curs_clr(struct nv50_head *head)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 4))) {
-		if (core->base.user.oclass < G82_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0880 + head->base.index * 0x400, 1);
-			evo_data(push, 0x05000000);
-		} else
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0880 + head->base.index * 0x400, 1);
-			evo_data(push, 0x05000000);
-			evo_mthd(push, 0x089c + head->base.index * 0x400, 1);
-			evo_data(push, 0x00000000);
-		} else {
-			evo_mthd(push, 0x0480 + head->base.index * 0x300, 1);
-			evo_data(push, 0x05000000);
-			evo_mthd(push, 0x048c + head->base.index * 0x300, 1);
-			evo_data(push, 0x00000000);
-		}
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_curs_set(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 5))) {
-		if (core->base.user.oclass < G82_DISP_BASE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0880 + head->base.index * 0x400, 2);
-			evo_data(push, 0x80000000 | (asyh->curs.layout << 26) |
-						    (asyh->curs.format << 24));
-			evo_data(push, asyh->curs.offset >> 8);
-		} else
-		if (core->base.user.oclass < GF110_DISP_BASE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0880 + head->base.index * 0x400, 2);
-			evo_data(push, 0x80000000 | (asyh->curs.layout << 26) |
-						    (asyh->curs.format << 24));
-			evo_data(push, asyh->curs.offset >> 8);
-			evo_mthd(push, 0x089c + head->base.index * 0x400, 1);
-			evo_data(push, asyh->curs.handle);
-		} else {
-			evo_mthd(push, 0x0480 + head->base.index * 0x300, 2);
-			evo_data(push, 0x80000000 | (asyh->curs.layout << 26) |
-						    (asyh->curs.format << 24));
-			evo_data(push, asyh->curs.offset >> 8);
-			evo_mthd(push, 0x048c + head->base.index * 0x300, 1);
-			evo_data(push, asyh->curs.handle);
-		}
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_core_clr(struct nv50_head *head)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 2))) {
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA)
-			evo_mthd(push, 0x0874 + head->base.index * 0x400, 1);
-		else
-			evo_mthd(push, 0x0474 + head->base.index * 0x300, 1);
-		evo_data(push, 0x00000000);
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_core_set(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 9))) {
-		if (core->base.user.oclass < G82_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0860 + head->base.index * 0x400, 1);
-			evo_data(push, asyh->core.offset >> 8);
-			evo_mthd(push, 0x0868 + head->base.index * 0x400, 4);
-			evo_data(push, (asyh->core.h << 16) | asyh->core.w);
-			evo_data(push, asyh->core.layout << 20 |
-				       (asyh->core.pitch >> 8) << 8 |
-				       asyh->core.block);
-			evo_data(push, asyh->core.kind << 16 |
-				       asyh->core.format << 8);
-			evo_data(push, asyh->core.handle);
-			evo_mthd(push, 0x08c0 + head->base.index * 0x400, 1);
-			evo_data(push, (asyh->core.y << 16) | asyh->core.x);
-			/* EVO will complain with INVALID_STATE if we have an
-			 * active cursor and (re)specify HeadSetContextDmaIso
-			 * without also updating HeadSetOffsetCursor.
-			 */
-			asyh->set.curs = asyh->curs.visible;
-		} else
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0860 + head->base.index * 0x400, 1);
-			evo_data(push, asyh->core.offset >> 8);
-			evo_mthd(push, 0x0868 + head->base.index * 0x400, 4);
-			evo_data(push, (asyh->core.h << 16) | asyh->core.w);
-			evo_data(push, asyh->core.layout << 20 |
-				       (asyh->core.pitch >> 8) << 8 |
-				       asyh->core.block);
-			evo_data(push, asyh->core.format << 8);
-			evo_data(push, asyh->core.handle);
-			evo_mthd(push, 0x08c0 + head->base.index * 0x400, 1);
-			evo_data(push, (asyh->core.y << 16) | asyh->core.x);
-		} else {
-			evo_mthd(push, 0x0460 + head->base.index * 0x300, 1);
-			evo_data(push, asyh->core.offset >> 8);
-			evo_mthd(push, 0x0468 + head->base.index * 0x300, 4);
-			evo_data(push, (asyh->core.h << 16) | asyh->core.w);
-			evo_data(push, asyh->core.layout << 24 |
-				       (asyh->core.pitch >> 8) << 8 |
-				       asyh->core.block);
-			evo_data(push, asyh->core.format << 8);
-			evo_data(push, asyh->core.handle);
-			evo_mthd(push, 0x04b0 + head->base.index * 0x300, 1);
-			evo_data(push, (asyh->core.y << 16) | asyh->core.x);
-		}
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_lut_clr(struct nv50_head *head)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 4))) {
-		if (core->base.user.oclass < G82_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0840 + (head->base.index * 0x400), 1);
-			evo_data(push, 0x40000000);
-		} else
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0840 + (head->base.index * 0x400), 1);
-			evo_data(push, 0x40000000);
-			evo_mthd(push, 0x085c + (head->base.index * 0x400), 1);
-			evo_data(push, 0x00000000);
-		} else {
-			evo_mthd(push, 0x0440 + (head->base.index * 0x300), 1);
-			evo_data(push, 0x03000000);
-			evo_mthd(push, 0x045c + (head->base.index * 0x300), 1);
-			evo_data(push, 0x00000000);
-		}
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_lut_load(struct drm_property_blob *blob, int mode,
-		   struct nouveau_bo *nvbo)
-{
-	struct drm_color_lut *in = (struct drm_color_lut *)blob->data;
-	void __iomem *lut = (u8 *)nvbo_kmap_obj_iovirtual(nvbo);
-	const int size = blob->length / sizeof(*in);
-	int bits, shift, i;
-	u16 zero, r, g, b;
-
-	/* This can't happen.. But it shuts the compiler up. */
-	if (WARN_ON(size != 256))
-		return;
-
-	switch (mode) {
-	case 0: /* LORES. */
-	case 1: /* HIRES. */
-		bits = 11;
-		shift = 3;
-		zero = 0x0000;
-		break;
-	case 7: /* INTERPOLATE_257_UNITY_RANGE. */
-		bits = 14;
-		shift = 0;
-		zero = 0x6000;
-		break;
-	default:
-		WARN_ON(1);
-		return;
-	}
-
-	for (i = 0; i < size; i++) {
-		r = (drm_color_lut_extract(in[i].  red, bits) + zero) << shift;
-		g = (drm_color_lut_extract(in[i].green, bits) + zero) << shift;
-		b = (drm_color_lut_extract(in[i]. blue, bits) + zero) << shift;
-		writew(r, lut + (i * 0x08) + 0);
-		writew(g, lut + (i * 0x08) + 2);
-		writew(b, lut + (i * 0x08) + 4);
-	}
-
-	/* INTERPOLATE modes require a "next" entry to interpolate with,
-	 * so we replicate the last entry to deal with this for now.
-	 */
-	writew(r, lut + (i * 0x08) + 0);
-	writew(g, lut + (i * 0x08) + 2);
-	writew(b, lut + (i * 0x08) + 4);
-}
-
-static void
-nv50_head_lut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 7))) {
-		if (core->base.user.oclass < G82_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2);
-			evo_data(push, 0x80000000 | asyh->lut.mode << 30);
-			evo_data(push, asyh->lut.offset >> 8);
-		} else
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2);
-			evo_data(push, 0x80000000 | asyh->lut.mode << 30);
-			evo_data(push, asyh->lut.offset >> 8);
-			evo_mthd(push, 0x085c + (head->base.index * 0x400), 1);
-			evo_data(push, asyh->lut.handle);
-		} else {
-			evo_mthd(push, 0x0440 + (head->base.index * 0x300), 4);
-			evo_data(push, 0x80000000 | asyh->lut.mode << 24);
-			evo_data(push, asyh->lut.offset >> 8);
-			evo_data(push, 0x00000000);
-			evo_data(push, 0x00000000);
-			evo_mthd(push, 0x045c + (head->base.index * 0x300), 1);
-			evo_data(push, asyh->lut.handle);
-		}
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	struct nv50_head_mode *m = &asyh->mode;
-	u32 *push;
-	if ((push = evo_wait(core, 14))) {
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x0804 + (head->base.index * 0x400), 2);
-			evo_data(push, 0x00800000 | m->clock);
-			evo_data(push, m->interlace ? 0x00000002 : 0x00000000);
-			evo_mthd(push, 0x0810 + (head->base.index * 0x400), 7);
-			evo_data(push, 0x00000000);
-			evo_data(push, (m->v.active  << 16) | m->h.active );
-			evo_data(push, (m->v.synce   << 16) | m->h.synce  );
-			evo_data(push, (m->v.blanke  << 16) | m->h.blanke );
-			evo_data(push, (m->v.blanks  << 16) | m->h.blanks );
-			evo_data(push, (m->v.blank2e << 16) | m->v.blank2s);
-			evo_data(push, asyh->mode.v.blankus);
-			evo_mthd(push, 0x082c + (head->base.index * 0x400), 1);
-			evo_data(push, 0x00000000);
-		} else {
-			evo_mthd(push, 0x0410 + (head->base.index * 0x300), 6);
-			evo_data(push, 0x00000000);
-			evo_data(push, (m->v.active  << 16) | m->h.active );
-			evo_data(push, (m->v.synce   << 16) | m->h.synce  );
-			evo_data(push, (m->v.blanke  << 16) | m->h.blanke );
-			evo_data(push, (m->v.blanks  << 16) | m->h.blanks );
-			evo_data(push, (m->v.blank2e << 16) | m->v.blank2s);
-			evo_mthd(push, 0x042c + (head->base.index * 0x300), 2);
-			evo_data(push, 0x00000000); /* ??? */
-			evo_data(push, 0xffffff00);
-			evo_mthd(push, 0x0450 + (head->base.index * 0x300), 3);
-			evo_data(push, m->clock * 1000);
-			evo_data(push, 0x00200000); /* ??? */
-			evo_data(push, m->clock * 1000);
-		}
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_view(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
-	u32 *push;
-	if ((push = evo_wait(core, 10))) {
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
-			evo_mthd(push, 0x08a4 + (head->base.index * 0x400), 1);
-			evo_data(push, 0x00000000);
-			evo_mthd(push, 0x08c8 + (head->base.index * 0x400), 1);
-			evo_data(push, (asyh->view.iH << 16) | asyh->view.iW);
-			evo_mthd(push, 0x08d8 + (head->base.index * 0x400), 2);
-			evo_data(push, (asyh->view.oH << 16) | asyh->view.oW);
-			evo_data(push, (asyh->view.oH << 16) | asyh->view.oW);
-		} else {
-			evo_mthd(push, 0x0494 + (head->base.index * 0x300), 1);
-			evo_data(push, 0x00000000);
-			evo_mthd(push, 0x04b8 + (head->base.index * 0x300), 1);
-			evo_data(push, (asyh->view.iH << 16) | asyh->view.iW);
-			evo_mthd(push, 0x04c0 + (head->base.index * 0x300), 3);
-			evo_data(push, (asyh->view.oH << 16) | asyh->view.oW);
-			evo_data(push, (asyh->view.oH << 16) | asyh->view.oW);
-			evo_data(push, (asyh->view.oH << 16) | asyh->view.oW);
-		}
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_head_flush_clr(struct nv50_head *head, struct nv50_head_atom *asyh, bool y)
-{
-	if (asyh->clr.ilut && (!asyh->set.ilut || y))
-		nv50_head_lut_clr(head);
-	if (asyh->clr.core && (!asyh->set.core || y))
-		nv50_head_core_clr(head);
-	if (asyh->clr.curs && (!asyh->set.curs || y))
-		nv50_head_curs_clr(head);
-}
-
-static void
-nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	if (asyh->set.view   ) nv50_head_view    (head, asyh);
-	if (asyh->set.mode   ) nv50_head_mode    (head, asyh);
-	if (asyh->set.ilut   ) {
-		struct nouveau_bo *nvbo = head->lut.nvbo[head->lut.next];
-		struct drm_property_blob *blob = asyh->state.gamma_lut;
-		if (blob)
-			nv50_head_lut_load(blob, asyh->lut.mode, nvbo);
-		asyh->lut.offset = nvbo->bo.offset;
-		head->lut.next ^= 1;
-		nv50_head_lut_set(head, asyh);
-	}
-	if (asyh->set.core   ) nv50_head_core_set(head, asyh);
-	if (asyh->set.curs   ) nv50_head_curs_set(head, asyh);
-	if (asyh->set.base   ) nv50_head_base    (head, asyh);
-	if (asyh->set.ovly   ) nv50_head_ovly    (head, asyh);
-	if (asyh->set.dither ) nv50_head_dither  (head, asyh);
-	if (asyh->set.procamp) nv50_head_procamp (head, asyh);
-}
-
-static void
-nv50_head_atomic_check_procamp(struct nv50_head_atom *armh,
-			       struct nv50_head_atom *asyh,
-			       struct nouveau_conn_atom *asyc)
-{
-	const int vib = asyc->procamp.color_vibrance - 100;
-	const int hue = asyc->procamp.vibrant_hue - 90;
-	const int adj = (vib > 0) ? 50 : 0;
-	asyh->procamp.sat.cos = ((vib * 2047 + adj) / 100) & 0xfff;
-	asyh->procamp.sat.sin = ((hue * 2047) / 100) & 0xfff;
-	asyh->set.procamp = true;
-}
-
-static void
-nv50_head_atomic_check_dither(struct nv50_head_atom *armh,
-			      struct nv50_head_atom *asyh,
-			      struct nouveau_conn_atom *asyc)
-{
-	struct drm_connector *connector = asyc->state.connector;
-	u32 mode = 0x00;
-
-	if (asyc->dither.mode == DITHERING_MODE_AUTO) {
-		if (asyh->base.depth > connector->display_info.bpc * 3)
-			mode = DITHERING_MODE_DYNAMIC2X2;
-	} else {
-		mode = asyc->dither.mode;
-	}
-
-	if (asyc->dither.depth == DITHERING_DEPTH_AUTO) {
-		if (connector->display_info.bpc >= 8)
-			mode |= DITHERING_DEPTH_8BPC;
-	} else {
-		mode |= asyc->dither.depth;
-	}
-
-	asyh->dither.enable = mode;
-	asyh->dither.bits = mode >> 1;
-	asyh->dither.mode = mode >> 3;
-	asyh->set.dither = true;
-}
-
-static void
-nv50_head_atomic_check_view(struct nv50_head_atom *armh,
-			    struct nv50_head_atom *asyh,
-			    struct nouveau_conn_atom *asyc)
-{
-	struct drm_connector *connector = asyc->state.connector;
-	struct drm_display_mode *omode = &asyh->state.adjusted_mode;
-	struct drm_display_mode *umode = &asyh->state.mode;
-	int mode = asyc->scaler.mode;
-	struct edid *edid;
-	int umode_vdisplay, omode_hdisplay, omode_vdisplay;
-
-	if (connector->edid_blob_ptr)
-		edid = (struct edid *)connector->edid_blob_ptr->data;
-	else
-		edid = NULL;
-
-	if (!asyc->scaler.full) {
-		if (mode == DRM_MODE_SCALE_NONE)
-			omode = umode;
-	} else {
-		/* Non-EDID LVDS/eDP mode. */
-		mode = DRM_MODE_SCALE_FULLSCREEN;
-	}
-
-	/* For the user-specified mode, we must ignore doublescan and
-	 * the like, but honor frame packing.
-	 */
-	umode_vdisplay = umode->vdisplay;
-	if ((umode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
-		umode_vdisplay += umode->vtotal;
-	asyh->view.iW = umode->hdisplay;
-	asyh->view.iH = umode_vdisplay;
-	/* For the output mode, we can just use the stock helper. */
-	drm_mode_get_hv_timing(omode, &omode_hdisplay, &omode_vdisplay);
-	asyh->view.oW = omode_hdisplay;
-	asyh->view.oH = omode_vdisplay;
-
-	/* Add overscan compensation if necessary, will keep the aspect
-	 * ratio the same as the backend mode unless overridden by the
-	 * user setting both hborder and vborder properties.
-	 */
-	if ((asyc->scaler.underscan.mode == UNDERSCAN_ON ||
-	    (asyc->scaler.underscan.mode == UNDERSCAN_AUTO &&
-	     drm_detect_hdmi_monitor(edid)))) {
-		u32 bX = asyc->scaler.underscan.hborder;
-		u32 bY = asyc->scaler.underscan.vborder;
-		u32 r = (asyh->view.oH << 19) / asyh->view.oW;
-
-		if (bX) {
-			asyh->view.oW -= (bX * 2);
-			if (bY) asyh->view.oH -= (bY * 2);
-			else    asyh->view.oH  = ((asyh->view.oW * r) + (r / 2)) >> 19;
-		} else {
-			asyh->view.oW -= (asyh->view.oW >> 4) + 32;
-			if (bY) asyh->view.oH -= (bY * 2);
-			else    asyh->view.oH  = ((asyh->view.oW * r) + (r / 2)) >> 19;
-		}
-	}
-
-	/* Handle CENTER/ASPECT scaling, taking into account the areas
-	 * removed already for overscan compensation.
-	 */
-	switch (mode) {
-	case DRM_MODE_SCALE_CENTER:
-		asyh->view.oW = min((u16)umode->hdisplay, asyh->view.oW);
-		asyh->view.oH = min((u16)umode_vdisplay, asyh->view.oH);
-		/* fall-through */
-	case DRM_MODE_SCALE_ASPECT:
-		if (asyh->view.oH < asyh->view.oW) {
-			u32 r = (asyh->view.iW << 19) / asyh->view.iH;
-			asyh->view.oW = ((asyh->view.oH * r) + (r / 2)) >> 19;
-		} else {
-			u32 r = (asyh->view.iH << 19) / asyh->view.iW;
-			asyh->view.oH = ((asyh->view.oW * r) + (r / 2)) >> 19;
-		}
-		break;
-	default:
-		break;
-	}
-
-	asyh->set.view = true;
-}
-
-static void
-nv50_head_atomic_check_lut(struct nv50_head *head,
-			   struct nv50_head_atom *armh,
-			   struct nv50_head_atom *asyh)
-{
-	struct nv50_disp *disp = nv50_disp(head->base.base.dev);
-
-	/* An I8 surface without an input LUT makes no sense, and
-	 * EVO will throw an error if you try.
-	 *
-	 * Legacy clients actually cause this due to the order in
-	 * which they call ioctls, so we will enable the LUT with
-	 * whatever contents the buffer already contains to avoid
-	 * triggering the error check.
-	 */
-	if (!asyh->state.gamma_lut && asyh->base.cpp != 1) {
-		asyh->lut.handle = 0;
-		asyh->clr.ilut = armh->lut.visible;
-		return;
-	}
-
-	if (disp->disp->oclass < GF110_DISP) {
-		asyh->lut.mode = (asyh->base.cpp == 1) ? 0 : 1;
-		asyh->set.ilut = true;
-	} else {
-		asyh->lut.mode = 7;
-		asyh->set.ilut = asyh->state.color_mgmt_changed;
-	}
-	asyh->lut.handle = disp->mast.base.vram.handle;
-}
-
-static void
-nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
-{
-	struct drm_display_mode *mode = &asyh->state.adjusted_mode;
-	struct nv50_head_mode *m = &asyh->mode;
-	u32 blankus;
-
-	drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V | CRTC_STEREO_DOUBLE);
-
-	/*
-	 * DRM modes are defined in terms of a repeating interval
-	 * starting with the active display area.  The hardware modes
-	 * are defined in terms of a repeating interval starting one
-	 * unit (pixel or line) into the sync pulse.  So, add bias.
-	 */
-
-	m->h.active = mode->crtc_htotal;
-	m->h.synce  = mode->crtc_hsync_end - mode->crtc_hsync_start - 1;
-	m->h.blanke = mode->crtc_hblank_end - mode->crtc_hsync_start - 1;
-	m->h.blanks = m->h.blanke + mode->crtc_hdisplay;
-
-	m->v.active = mode->crtc_vtotal;
-	m->v.synce  = mode->crtc_vsync_end - mode->crtc_vsync_start - 1;
-	m->v.blanke = mode->crtc_vblank_end - mode->crtc_vsync_start - 1;
-	m->v.blanks = m->v.blanke + mode->crtc_vdisplay;
-
-	/*XXX: Safe underestimate, even "0" works */
-	blankus = (m->v.active - mode->crtc_vdisplay - 2) * m->h.active;
-	blankus *= 1000;
-	blankus /= mode->crtc_clock;
-	m->v.blankus = blankus;
-
-	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
-		m->v.blank2e =  m->v.active + m->v.blanke;
-		m->v.blank2s =  m->v.blank2e + mode->crtc_vdisplay;
-		m->v.active  = (m->v.active * 2) + 1;
-		m->interlace = true;
-	} else {
-		m->v.blank2e = 0;
-		m->v.blank2s = 1;
-		m->interlace = false;
-	}
-	m->clock = mode->crtc_clock;
-
-	asyh->set.mode = true;
-}
-
-static int
-nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
-{
-	struct nouveau_drm *drm = nouveau_drm(crtc->dev);
-	struct nv50_disp *disp = nv50_disp(crtc->dev);
-	struct nv50_head *head = nv50_head(crtc);
-	struct nv50_head_atom *armh = nv50_head_atom(crtc->state);
-	struct nv50_head_atom *asyh = nv50_head_atom(state);
-	struct nouveau_conn_atom *asyc = NULL;
-	struct drm_connector_state *conns;
-	struct drm_connector *conn;
-	int i;
-
-	NV_ATOMIC(drm, "%s atomic_check %d\n", crtc->name, asyh->state.active);
-	if (asyh->state.active) {
-		for_each_new_connector_in_state(asyh->state.state, conn, conns, i) {
-			if (conns->crtc == crtc) {
-				asyc = nouveau_conn_atom(conns);
-				break;
-			}
-		}
-
-		if (armh->state.active) {
-			if (asyc) {
-				if (asyh->state.mode_changed)
-					asyc->set.scaler = true;
-				if (armh->base.depth != asyh->base.depth)
-					asyc->set.dither = true;
-			}
-		} else {
-			if (asyc)
-				asyc->set.mask = ~0;
-			asyh->set.mask = ~0;
-		}
-
-		if (asyh->state.mode_changed)
-			nv50_head_atomic_check_mode(head, asyh);
-
-		if (asyh->state.color_mgmt_changed ||
-		    asyh->base.cpp != armh->base.cpp)
-			nv50_head_atomic_check_lut(head, armh, asyh);
-		asyh->lut.visible = asyh->lut.handle != 0;
-
-		if (asyc) {
-			if (asyc->set.scaler)
-				nv50_head_atomic_check_view(armh, asyh, asyc);
-			if (asyc->set.dither)
-				nv50_head_atomic_check_dither(armh, asyh, asyc);
-			if (asyc->set.procamp)
-				nv50_head_atomic_check_procamp(armh, asyh, asyc);
-		}
-
-		if ((asyh->core.visible = (asyh->base.cpp != 0))) {
-			asyh->core.x = asyh->base.x;
-			asyh->core.y = asyh->base.y;
-			asyh->core.w = asyh->base.w;
-			asyh->core.h = asyh->base.h;
-		} else
-		if ((asyh->core.visible = asyh->curs.visible) ||
-		    (asyh->core.visible = asyh->lut.visible)) {
-			/*XXX: We need to either find some way of having the
-			 *     primary base layer appear black, while still
-			 *     being able to display the other layers, or we
-			 *     need to allocate a dummy black surface here.
-			 */
-			asyh->core.x = 0;
-			asyh->core.y = 0;
-			asyh->core.w = asyh->state.mode.hdisplay;
-			asyh->core.h = asyh->state.mode.vdisplay;
-		}
-		asyh->core.handle = disp->mast.base.vram.handle;
-		asyh->core.offset = 0;
-		asyh->core.format = 0xcf;
-		asyh->core.kind = 0;
-		asyh->core.layout = 1;
-		asyh->core.block = 0;
-		asyh->core.pitch = ALIGN(asyh->core.w, 64) * 4;
-		asyh->set.base = armh->base.cpp != asyh->base.cpp;
-		asyh->set.ovly = armh->ovly.cpp != asyh->ovly.cpp;
-	} else {
-		asyh->lut.visible = false;
-		asyh->core.visible = false;
-		asyh->curs.visible = false;
-		asyh->base.cpp = 0;
-		asyh->ovly.cpp = 0;
-	}
-
-	if (!drm_atomic_crtc_needs_modeset(&asyh->state)) {
-		if (asyh->core.visible) {
-			if (memcmp(&armh->core, &asyh->core, sizeof(asyh->core)))
-				asyh->set.core = true;
-		} else
-		if (armh->core.visible) {
-			asyh->clr.core = true;
-		}
-
-		if (asyh->curs.visible) {
-			if (memcmp(&armh->curs, &asyh->curs, sizeof(asyh->curs)))
-				asyh->set.curs = true;
-		} else
-		if (armh->curs.visible) {
-			asyh->clr.curs = true;
-		}
-	} else {
-		asyh->clr.ilut = armh->lut.visible;
-		asyh->clr.core = armh->core.visible;
-		asyh->clr.curs = armh->curs.visible;
-		asyh->set.ilut = asyh->lut.visible;
-		asyh->set.core = asyh->core.visible;
-		asyh->set.curs = asyh->curs.visible;
-	}
-
-	if (asyh->clr.mask || asyh->set.mask)
-		nv50_atom(asyh->state.state)->lock_core = true;
-	return 0;
-}
-
-static const struct drm_crtc_helper_funcs
-nv50_head_help = {
-	.atomic_check = nv50_head_atomic_check,
-};
-
-static void
-nv50_head_atomic_destroy_state(struct drm_crtc *crtc,
-			       struct drm_crtc_state *state)
-{
-	struct nv50_head_atom *asyh = nv50_head_atom(state);
-	__drm_atomic_helper_crtc_destroy_state(&asyh->state);
-	kfree(asyh);
-}
-
-static struct drm_crtc_state *
-nv50_head_atomic_duplicate_state(struct drm_crtc *crtc)
-{
-	struct nv50_head_atom *armh = nv50_head_atom(crtc->state);
-	struct nv50_head_atom *asyh;
-	if (!(asyh = kmalloc(sizeof(*asyh), GFP_KERNEL)))
-		return NULL;
-	__drm_atomic_helper_crtc_duplicate_state(crtc, &asyh->state);
-	asyh->view = armh->view;
-	asyh->mode = armh->mode;
-	asyh->lut  = armh->lut;
-	asyh->core = armh->core;
-	asyh->curs = armh->curs;
-	asyh->base = armh->base;
-	asyh->ovly = armh->ovly;
-	asyh->dither = armh->dither;
-	asyh->procamp = armh->procamp;
-	asyh->clr.mask = 0;
-	asyh->set.mask = 0;
-	return &asyh->state;
-}
-
-static void
-__drm_atomic_helper_crtc_reset(struct drm_crtc *crtc,
-			       struct drm_crtc_state *state)
-{
-	if (crtc->state)
-		crtc->funcs->atomic_destroy_state(crtc, crtc->state);
-	crtc->state = state;
-	crtc->state->crtc = crtc;
-}
-
-static void
-nv50_head_reset(struct drm_crtc *crtc)
-{
-	struct nv50_head_atom *asyh;
-
-	if (WARN_ON(!(asyh = kzalloc(sizeof(*asyh), GFP_KERNEL))))
-		return;
-
-	__drm_atomic_helper_crtc_reset(crtc, &asyh->state);
-}
-
-static void
-nv50_head_destroy(struct drm_crtc *crtc)
-{
-	struct nv50_disp *disp = nv50_disp(crtc->dev);
-	struct nv50_head *head = nv50_head(crtc);
-	int i;
-
-	nv50_dmac_destroy(&head->ovly.base, disp->disp);
-	nv50_pioc_destroy(&head->oimm.base);
-
-	for (i = 0; i < ARRAY_SIZE(head->lut.nvbo); i++)
-		nouveau_bo_unmap_unpin_unref(&head->lut.nvbo[i]);
-
-	drm_crtc_cleanup(crtc);
-	kfree(crtc);
-}
-
-static const struct drm_crtc_funcs
-nv50_head_func = {
-	.reset = nv50_head_reset,
-	.gamma_set = drm_atomic_helper_legacy_gamma_set,
-	.destroy = nv50_head_destroy,
-	.set_config = drm_atomic_helper_set_config,
-	.page_flip = drm_atomic_helper_page_flip,
-	.atomic_duplicate_state = nv50_head_atomic_duplicate_state,
-	.atomic_destroy_state = nv50_head_atomic_destroy_state,
-};
-
-static int
-nv50_head_create(struct drm_device *dev, int index)
-{
-	struct nouveau_drm *drm = nouveau_drm(dev);
-	struct nvif_device *device = &drm->client.device;
-	struct nv50_disp *disp = nv50_disp(dev);
-	struct nv50_head *head;
-	struct nv50_base *base;
-	struct nv50_curs *curs;
-	struct drm_crtc *crtc;
-	int ret, i;
-
-	head = kzalloc(sizeof(*head), GFP_KERNEL);
-	if (!head)
-		return -ENOMEM;
-
-	head->base.index = index;
-	ret = nv50_base_new(drm, head, &base);
-	if (ret == 0)
-		ret = nv50_curs_new(drm, head, &curs);
-	if (ret) {
-		kfree(head);
-		return ret;
-	}
-
-	crtc = &head->base.base;
-	drm_crtc_init_with_planes(dev, crtc, &base->wndw.plane,
-				  &curs->wndw.plane, &nv50_head_func,
-				  "head-%d", head->base.index);
-	drm_crtc_helper_add(crtc, &nv50_head_help);
-	drm_mode_crtc_set_gamma_size(crtc, 256);
-
-	for (i = 0; i < ARRAY_SIZE(head->lut.nvbo); i++) {
-		ret = nouveau_bo_new_pin_map(&drm->client, 1025 * 8, 0x100,
-					     TTM_PL_FLAG_VRAM,
-					     &head->lut.nvbo[i]);
-		if (ret)
-			goto out;
-	}
-
-	/* allocate overlay resources */
-	ret = nv50_oimm_create(device, disp->disp, index, &head->oimm);
-	if (ret)
-		goto out;
-
-	ret = nv50_ovly_create(device, disp->disp, index, disp->sync->bo.offset,
-			       &head->ovly);
-	if (ret)
-		goto out;
-
-out:
-	if (ret)
-		nv50_head_destroy(crtc);
-	return ret;
-}
-
-/******************************************************************************
- * Output path helpers
- *****************************************************************************/
-static void
-nv50_outp_release(struct nouveau_encoder *nv_encoder)
-{
-	struct nv50_disp *disp = nv50_disp(nv_encoder->base.base.dev);
-	struct {
-		struct nv50_disp_mthd_v1 base;
-	} args = {
-		.base.version = 1,
-		.base.method = NV50_DISP_MTHD_V1_RELEASE,
-		.base.hasht  = nv_encoder->dcb->hasht,
-		.base.hashm  = nv_encoder->dcb->hashm,
-	};
-
-	nvif_mthd(disp->disp, 0, &args, sizeof(args));
-	nv_encoder->or = -1;
-	nv_encoder->link = 0;
-}
-
-static int
-nv50_outp_acquire(struct nouveau_encoder *nv_encoder)
-{
-	struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
-	struct nv50_disp *disp = nv50_disp(drm->dev);
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_acquire_v0 info;
-	} args = {
-		.base.version = 1,
-		.base.method = NV50_DISP_MTHD_V1_ACQUIRE,
-		.base.hasht  = nv_encoder->dcb->hasht,
-		.base.hashm  = nv_encoder->dcb->hashm,
-	};
-	int ret;
-
-	ret = nvif_mthd(disp->disp, 0, &args, sizeof(args));
-	if (ret) {
-		NV_ERROR(drm, "error acquiring output path: %d\n", ret);
-		return ret;
-	}
-
-	nv_encoder->or = args.info.or;
-	nv_encoder->link = args.info.link;
-	return 0;
-}
-
-static int
-nv50_outp_atomic_check_view(struct drm_encoder *encoder,
-			    struct drm_crtc_state *crtc_state,
-			    struct drm_connector_state *conn_state,
-			    struct drm_display_mode *native_mode)
-{
-	struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode;
-	struct drm_display_mode *mode = &crtc_state->mode;
-	struct drm_connector *connector = conn_state->connector;
-	struct nouveau_conn_atom *asyc = nouveau_conn_atom(conn_state);
-	struct nouveau_drm *drm = nouveau_drm(encoder->dev);
-
-	NV_ATOMIC(drm, "%s atomic_check\n", encoder->name);
-	asyc->scaler.full = false;
-	if (!native_mode)
-		return 0;
-
-	if (asyc->scaler.mode == DRM_MODE_SCALE_NONE) {
-		switch (connector->connector_type) {
-		case DRM_MODE_CONNECTOR_LVDS:
-		case DRM_MODE_CONNECTOR_eDP:
-			/* Force use of scaler for non-EDID modes. */
-			if (adjusted_mode->type & DRM_MODE_TYPE_DRIVER)
-				break;
-			mode = native_mode;
-			asyc->scaler.full = true;
-			break;
-		default:
-			break;
-		}
-	} else {
-		mode = native_mode;
-	}
-
-	if (!drm_mode_equal(adjusted_mode, mode)) {
-		drm_mode_copy(adjusted_mode, mode);
-		crtc_state->mode_changed = true;
-	}
-
-	return 0;
-}
-
-static int
-nv50_outp_atomic_check(struct drm_encoder *encoder,
-		       struct drm_crtc_state *crtc_state,
-		       struct drm_connector_state *conn_state)
-{
-	struct nouveau_connector *nv_connector =
-		nouveau_connector(conn_state->connector);
-	return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state,
-					   nv_connector->native_mode);
-}
-
-/******************************************************************************
- * DAC
- *****************************************************************************/
-static void
-nv50_dac_disable(struct drm_encoder *encoder)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nv50_mast *mast = nv50_mast(encoder->dev);
-	const int or = nv_encoder->or;
-	u32 *push;
-
-	if (nv_encoder->crtc) {
-		push = evo_wait(mast, 4);
-		if (push) {
-			if (nv50_vers(mast) < GF110_DISP_CORE_CHANNEL_DMA) {
-				evo_mthd(push, 0x0400 + (or * 0x080), 1);
-				evo_data(push, 0x00000000);
-			} else {
-				evo_mthd(push, 0x0180 + (or * 0x020), 1);
-				evo_data(push, 0x00000000);
-			}
-			evo_kick(push, mast);
-		}
-	}
-
-	nv_encoder->crtc = NULL;
-	nv50_outp_release(nv_encoder);
-}
-
-static void
-nv50_dac_enable(struct drm_encoder *encoder)
-{
-	struct nv50_mast *mast = nv50_mast(encoder->dev);
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
-	struct drm_display_mode *mode = &nv_crtc->base.state->adjusted_mode;
-	u32 *push;
-
-	nv50_outp_acquire(nv_encoder);
-
-	push = evo_wait(mast, 8);
-	if (push) {
-		if (nv50_vers(mast) < GF110_DISP_CORE_CHANNEL_DMA) {
-			u32 syncs = 0x00000000;
-
-			if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-				syncs |= 0x00000001;
-			if (mode->flags & DRM_MODE_FLAG_NVSYNC)
-				syncs |= 0x00000002;
-
-			evo_mthd(push, 0x0400 + (nv_encoder->or * 0x080), 2);
-			evo_data(push, 1 << nv_crtc->index);
-			evo_data(push, syncs);
-		} else {
-			u32 magic = 0x31ec6000 | (nv_crtc->index << 25);
-			u32 syncs = 0x00000001;
-
-			if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-				syncs |= 0x00000008;
-			if (mode->flags & DRM_MODE_FLAG_NVSYNC)
-				syncs |= 0x00000010;
-
-			if (mode->flags & DRM_MODE_FLAG_INTERLACE)
-				magic |= 0x00000001;
-
-			evo_mthd(push, 0x0404 + (nv_crtc->index * 0x300), 2);
-			evo_data(push, syncs);
-			evo_data(push, magic);
-			evo_mthd(push, 0x0180 + (nv_encoder->or * 0x020), 1);
-			evo_data(push, 1 << nv_crtc->index);
-		}
-
-		evo_kick(push, mast);
-	}
-
-	nv_encoder->crtc = encoder->crtc;
-}
-
-static enum drm_connector_status
-nv50_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nv50_disp *disp = nv50_disp(encoder->dev);
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_dac_load_v0 load;
-	} args = {
-		.base.version = 1,
-		.base.method = NV50_DISP_MTHD_V1_DAC_LOAD,
-		.base.hasht  = nv_encoder->dcb->hasht,
-		.base.hashm  = nv_encoder->dcb->hashm,
-	};
-	int ret;
-
-	args.load.data = nouveau_drm(encoder->dev)->vbios.dactestval;
-	if (args.load.data == 0)
-		args.load.data = 340;
-
-	ret = nvif_mthd(disp->disp, 0, &args, sizeof(args));
-	if (ret || !args.load.load)
-		return connector_status_disconnected;
-
-	return connector_status_connected;
-}
-
-static const struct drm_encoder_helper_funcs
-nv50_dac_help = {
-	.atomic_check = nv50_outp_atomic_check,
-	.enable = nv50_dac_enable,
-	.disable = nv50_dac_disable,
-	.detect = nv50_dac_detect
-};
-
-static void
-nv50_dac_destroy(struct drm_encoder *encoder)
-{
-	drm_encoder_cleanup(encoder);
-	kfree(encoder);
-}
-
-static const struct drm_encoder_funcs
-nv50_dac_func = {
-	.destroy = nv50_dac_destroy,
-};
-
-static int
-nv50_dac_create(struct drm_connector *connector, struct dcb_output *dcbe)
-{
-	struct nouveau_drm *drm = nouveau_drm(connector->dev);
-	struct nvkm_i2c *i2c = nvxx_i2c(&drm->client.device);
-	struct nvkm_i2c_bus *bus;
-	struct nouveau_encoder *nv_encoder;
-	struct drm_encoder *encoder;
-	int type = DRM_MODE_ENCODER_DAC;
-
-	nv_encoder = kzalloc(sizeof(*nv_encoder), GFP_KERNEL);
-	if (!nv_encoder)
-		return -ENOMEM;
-	nv_encoder->dcb = dcbe;
-
-	bus = nvkm_i2c_bus_find(i2c, dcbe->i2c_index);
-	if (bus)
-		nv_encoder->i2c = &bus->i2c;
-
-	encoder = to_drm_encoder(nv_encoder);
-	encoder->possible_crtcs = dcbe->heads;
-	encoder->possible_clones = 0;
-	drm_encoder_init(connector->dev, encoder, &nv50_dac_func, type,
-			 "dac-%04x-%04x", dcbe->hasht, dcbe->hashm);
-	drm_encoder_helper_add(encoder, &nv50_dac_help);
-
-	drm_mode_connector_attach_encoder(connector, encoder);
-	return 0;
-}
-
-/******************************************************************************
- * Audio
- *****************************************************************************/
-static void
-nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nv50_disp *disp = nv50_disp(encoder->dev);
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_sor_hda_eld_v0 eld;
-	} args = {
-		.base.version = 1,
-		.base.method  = NV50_DISP_MTHD_V1_SOR_HDA_ELD,
-		.base.hasht   = nv_encoder->dcb->hasht,
-		.base.hashm   = (0xf0ff & nv_encoder->dcb->hashm) |
-				(0x0100 << nv_crtc->index),
-	};
-
-	nvif_mthd(disp->disp, 0, &args, sizeof(args));
-}
-
-static void
-nv50_audio_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
-	struct nouveau_connector *nv_connector;
-	struct nv50_disp *disp = nv50_disp(encoder->dev);
-	struct __packed {
-		struct {
-			struct nv50_disp_mthd_v1 mthd;
-			struct nv50_disp_sor_hda_eld_v0 eld;
-		} base;
-		u8 data[sizeof(nv_connector->base.eld)];
-	} args = {
-		.base.mthd.version = 1,
-		.base.mthd.method  = NV50_DISP_MTHD_V1_SOR_HDA_ELD,
-		.base.mthd.hasht   = nv_encoder->dcb->hasht,
-		.base.mthd.hashm   = (0xf0ff & nv_encoder->dcb->hashm) |
-				     (0x0100 << nv_crtc->index),
-	};
-
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
-	if (!drm_detect_monitor_audio(nv_connector->edid))
-		return;
-
-	memcpy(args.data, nv_connector->base.eld, sizeof(args.data));
-
-	nvif_mthd(disp->disp, 0, &args,
-		  sizeof(args.base) + drm_eld_size(args.data));
-}
-
-/******************************************************************************
- * HDMI
- *****************************************************************************/
-static void
-nv50_hdmi_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nv50_disp *disp = nv50_disp(encoder->dev);
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_sor_hdmi_pwr_v0 pwr;
-	} args = {
-		.base.version = 1,
-		.base.method = NV50_DISP_MTHD_V1_SOR_HDMI_PWR,
-		.base.hasht  = nv_encoder->dcb->hasht,
-		.base.hashm  = (0xf0ff & nv_encoder->dcb->hashm) |
-			       (0x0100 << nv_crtc->index),
-	};
-
-	nvif_mthd(disp->disp, 0, &args, sizeof(args));
-}
-
-static void
-nv50_hdmi_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
-	struct nv50_disp *disp = nv50_disp(encoder->dev);
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_sor_hdmi_pwr_v0 pwr;
-		u8 infoframes[2 * 17]; /* two frames, up to 17 bytes each */
-	} args = {
-		.base.version = 1,
-		.base.method = NV50_DISP_MTHD_V1_SOR_HDMI_PWR,
-		.base.hasht  = nv_encoder->dcb->hasht,
-		.base.hashm  = (0xf0ff & nv_encoder->dcb->hashm) |
-			       (0x0100 << nv_crtc->index),
-		.pwr.state = 1,
-		.pwr.rekey = 56, /* binary driver, and tegra, constant */
-	};
-	struct nouveau_connector *nv_connector;
-	u32 max_ac_packet;
-	union hdmi_infoframe avi_frame;
-	union hdmi_infoframe vendor_frame;
-	int ret;
-	int size;
-
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
-	if (!drm_detect_hdmi_monitor(nv_connector->edid))
-		return;
-
-	ret = drm_hdmi_avi_infoframe_from_display_mode(&avi_frame.avi, mode,
-						       false);
-	if (!ret) {
-		/* We have an AVI InfoFrame, populate it to the display */
-		args.pwr.avi_infoframe_length
-			= hdmi_infoframe_pack(&avi_frame, args.infoframes, 17);
-	}
-
-	ret = drm_hdmi_vendor_infoframe_from_display_mode(&vendor_frame.vendor.hdmi,
-							  &nv_connector->base, mode);
-	if (!ret) {
-		/* We have a Vendor InfoFrame, populate it to the display */
-		args.pwr.vendor_infoframe_length
-			= hdmi_infoframe_pack(&vendor_frame,
-					      args.infoframes
-					      + args.pwr.avi_infoframe_length,
-					      17);
-	}
-
-	max_ac_packet  = mode->htotal - mode->hdisplay;
-	max_ac_packet -= args.pwr.rekey;
-	max_ac_packet -= 18; /* constant from tegra */
-	args.pwr.max_ac_packet = max_ac_packet / 32;
-
-	size = sizeof(args.base)
-		+ sizeof(args.pwr)
-		+ args.pwr.avi_infoframe_length
-		+ args.pwr.vendor_infoframe_length;
-	nvif_mthd(disp->disp, 0, &args, size);
-	nv50_audio_enable(encoder, mode);
-}
-
-/******************************************************************************
- * MST
- *****************************************************************************/
-#define nv50_mstm(p) container_of((p), struct nv50_mstm, mgr)
-#define nv50_mstc(p) container_of((p), struct nv50_mstc, connector)
-#define nv50_msto(p) container_of((p), struct nv50_msto, encoder)
-
-struct nv50_mstm {
-	struct nouveau_encoder *outp;
-
-	struct drm_dp_mst_topology_mgr mgr;
-	struct nv50_msto *msto[4];
-
-	bool modified;
-	bool disabled;
-	int links;
-};
-
-struct nv50_mstc {
-	struct nv50_mstm *mstm;
-	struct drm_dp_mst_port *port;
-	struct drm_connector connector;
-
-	struct drm_display_mode *native;
-	struct edid *edid;
-
-	int pbn;
-};
-
-struct nv50_msto {
-	struct drm_encoder encoder;
-
-	struct nv50_head *head;
-	struct nv50_mstc *mstc;
-	bool disabled;
-};
-
-static struct drm_dp_payload *
-nv50_msto_payload(struct nv50_msto *msto)
-{
-	struct nouveau_drm *drm = nouveau_drm(msto->encoder.dev);
-	struct nv50_mstc *mstc = msto->mstc;
-	struct nv50_mstm *mstm = mstc->mstm;
-	int vcpi = mstc->port->vcpi.vcpi, i;
-
-	NV_ATOMIC(drm, "%s: vcpi %d\n", msto->encoder.name, vcpi);
-	for (i = 0; i < mstm->mgr.max_payloads; i++) {
-		struct drm_dp_payload *payload = &mstm->mgr.payloads[i];
-		NV_ATOMIC(drm, "%s: %d: vcpi %d start 0x%02x slots 0x%02x\n",
-			  mstm->outp->base.base.name, i, payload->vcpi,
-			  payload->start_slot, payload->num_slots);
-	}
-
-	for (i = 0; i < mstm->mgr.max_payloads; i++) {
-		struct drm_dp_payload *payload = &mstm->mgr.payloads[i];
-		if (payload->vcpi == vcpi)
-			return payload;
-	}
-
-	return NULL;
-}
-
-static void
-nv50_msto_cleanup(struct nv50_msto *msto)
-{
-	struct nouveau_drm *drm = nouveau_drm(msto->encoder.dev);
-	struct nv50_mstc *mstc = msto->mstc;
-	struct nv50_mstm *mstm = mstc->mstm;
-
-	NV_ATOMIC(drm, "%s: msto cleanup\n", msto->encoder.name);
-	if (mstc->port && mstc->port->vcpi.vcpi > 0 && !nv50_msto_payload(msto))
-		drm_dp_mst_deallocate_vcpi(&mstm->mgr, mstc->port);
-	if (msto->disabled) {
-		msto->mstc = NULL;
-		msto->head = NULL;
-		msto->disabled = false;
-	}
-}
-
-static void
-nv50_msto_prepare(struct nv50_msto *msto)
-{
-	struct nouveau_drm *drm = nouveau_drm(msto->encoder.dev);
-	struct nv50_mstc *mstc = msto->mstc;
-	struct nv50_mstm *mstm = mstc->mstm;
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_sor_dp_mst_vcpi_v0 vcpi;
-	} args = {
-		.base.version = 1,
-		.base.method = NV50_DISP_MTHD_V1_SOR_DP_MST_VCPI,
-		.base.hasht  = mstm->outp->dcb->hasht,
-		.base.hashm  = (0xf0ff & mstm->outp->dcb->hashm) |
-			       (0x0100 << msto->head->base.index),
-	};
-
-	NV_ATOMIC(drm, "%s: msto prepare\n", msto->encoder.name);
-	if (mstc->port && mstc->port->vcpi.vcpi > 0) {
-		struct drm_dp_payload *payload = nv50_msto_payload(msto);
-		if (payload) {
-			args.vcpi.start_slot = payload->start_slot;
-			args.vcpi.num_slots = payload->num_slots;
-			args.vcpi.pbn = mstc->port->vcpi.pbn;
-			args.vcpi.aligned_pbn = mstc->port->vcpi.aligned_pbn;
-		}
-	}
-
-	NV_ATOMIC(drm, "%s: %s: %02x %02x %04x %04x\n",
-		  msto->encoder.name, msto->head->base.base.name,
-		  args.vcpi.start_slot, args.vcpi.num_slots,
-		  args.vcpi.pbn, args.vcpi.aligned_pbn);
-	nvif_mthd(&drm->display->disp, 0, &args, sizeof(args));
-}
-
-static int
-nv50_msto_atomic_check(struct drm_encoder *encoder,
-		       struct drm_crtc_state *crtc_state,
-		       struct drm_connector_state *conn_state)
-{
-	struct nv50_mstc *mstc = nv50_mstc(conn_state->connector);
-	struct nv50_mstm *mstm = mstc->mstm;
-	int bpp = conn_state->connector->display_info.bpc * 3;
-	int slots;
-
-	mstc->pbn = drm_dp_calc_pbn_mode(crtc_state->adjusted_mode.clock, bpp);
-
-	slots = drm_dp_find_vcpi_slots(&mstm->mgr, mstc->pbn);
-	if (slots < 0)
-		return slots;
-
-	return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state,
-					   mstc->native);
-}
-
-static void
-nv50_msto_enable(struct drm_encoder *encoder)
-{
-	struct nv50_head *head = nv50_head(encoder->crtc);
-	struct nv50_msto *msto = nv50_msto(encoder);
-	struct nv50_mstc *mstc = NULL;
-	struct nv50_mstm *mstm = NULL;
-	struct drm_connector *connector;
-	struct drm_connector_list_iter conn_iter;
-	u8 proto, depth;
-	int slots;
-	bool r;
-
-	drm_connector_list_iter_begin(encoder->dev, &conn_iter);
-	drm_for_each_connector_iter(connector, &conn_iter) {
-		if (connector->state->best_encoder == &msto->encoder) {
-			mstc = nv50_mstc(connector);
-			mstm = mstc->mstm;
-			break;
-		}
-	}
-	drm_connector_list_iter_end(&conn_iter);
-
-	if (WARN_ON(!mstc))
-		return;
-
-	slots = drm_dp_find_vcpi_slots(&mstm->mgr, mstc->pbn);
-	r = drm_dp_mst_allocate_vcpi(&mstm->mgr, mstc->port, mstc->pbn, slots);
-	WARN_ON(!r);
-
-	if (!mstm->links++)
-		nv50_outp_acquire(mstm->outp);
-
-	if (mstm->outp->link & 1)
-		proto = 0x8;
-	else
-		proto = 0x9;
-
-	switch (mstc->connector.display_info.bpc) {
-	case  6: depth = 0x2; break;
-	case  8: depth = 0x5; break;
-	case 10:
-	default: depth = 0x6; break;
-	}
-
-	mstm->outp->update(mstm->outp, head->base.index,
-			   &head->base.base.state->adjusted_mode, proto, depth);
-
-	msto->head = head;
-	msto->mstc = mstc;
-	mstm->modified = true;
-}
-
-static void
-nv50_msto_disable(struct drm_encoder *encoder)
-{
-	struct nv50_msto *msto = nv50_msto(encoder);
-	struct nv50_mstc *mstc = msto->mstc;
-	struct nv50_mstm *mstm = mstc->mstm;
-
-	if (mstc->port)
-		drm_dp_mst_reset_vcpi_slots(&mstm->mgr, mstc->port);
-
-	mstm->outp->update(mstm->outp, msto->head->base.index, NULL, 0, 0);
-	mstm->modified = true;
-	if (!--mstm->links)
-		mstm->disabled = true;
-	msto->disabled = true;
-}
-
-static const struct drm_encoder_helper_funcs
-nv50_msto_help = {
-	.disable = nv50_msto_disable,
-	.enable = nv50_msto_enable,
-	.atomic_check = nv50_msto_atomic_check,
-};
-
-static void
-nv50_msto_destroy(struct drm_encoder *encoder)
-{
-	struct nv50_msto *msto = nv50_msto(encoder);
-	drm_encoder_cleanup(&msto->encoder);
-	kfree(msto);
-}
-
-static const struct drm_encoder_funcs
-nv50_msto = {
-	.destroy = nv50_msto_destroy,
-};
-
-static int
-nv50_msto_new(struct drm_device *dev, u32 heads, const char *name, int id,
-	      struct nv50_msto **pmsto)
-{
-	struct nv50_msto *msto;
-	int ret;
-
-	if (!(msto = *pmsto = kzalloc(sizeof(*msto), GFP_KERNEL)))
-		return -ENOMEM;
-
-	ret = drm_encoder_init(dev, &msto->encoder, &nv50_msto,
-			       DRM_MODE_ENCODER_DPMST, "%s-mst-%d", name, id);
-	if (ret) {
-		kfree(*pmsto);
-		*pmsto = NULL;
-		return ret;
-	}
-
-	drm_encoder_helper_add(&msto->encoder, &nv50_msto_help);
-	msto->encoder.possible_crtcs = heads;
-	return 0;
-}
-
-static struct drm_encoder *
-nv50_mstc_atomic_best_encoder(struct drm_connector *connector,
-			      struct drm_connector_state *connector_state)
-{
-	struct nv50_head *head = nv50_head(connector_state->crtc);
-	struct nv50_mstc *mstc = nv50_mstc(connector);
-	if (mstc->port) {
-		struct nv50_mstm *mstm = mstc->mstm;
-		return &mstm->msto[head->base.index]->encoder;
-	}
-	return NULL;
-}
-
-static struct drm_encoder *
-nv50_mstc_best_encoder(struct drm_connector *connector)
-{
-	struct nv50_mstc *mstc = nv50_mstc(connector);
-	if (mstc->port) {
-		struct nv50_mstm *mstm = mstc->mstm;
-		return &mstm->msto[0]->encoder;
-	}
-	return NULL;
-}
-
-static enum drm_mode_status
-nv50_mstc_mode_valid(struct drm_connector *connector,
-		     struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
-static int
-nv50_mstc_get_modes(struct drm_connector *connector)
-{
-	struct nv50_mstc *mstc = nv50_mstc(connector);
-	int ret = 0;
-
-	mstc->edid = drm_dp_mst_get_edid(&mstc->connector, mstc->port->mgr, mstc->port);
-	drm_mode_connector_update_edid_property(&mstc->connector, mstc->edid);
-	if (mstc->edid)
-		ret = drm_add_edid_modes(&mstc->connector, mstc->edid);
-
-	if (!mstc->connector.display_info.bpc)
-		mstc->connector.display_info.bpc = 8;
-
-	if (mstc->native)
-		drm_mode_destroy(mstc->connector.dev, mstc->native);
-	mstc->native = nouveau_conn_native_mode(&mstc->connector);
-	return ret;
-}
-
-static const struct drm_connector_helper_funcs
-nv50_mstc_help = {
-	.get_modes = nv50_mstc_get_modes,
-	.mode_valid = nv50_mstc_mode_valid,
-	.best_encoder = nv50_mstc_best_encoder,
-	.atomic_best_encoder = nv50_mstc_atomic_best_encoder,
-};
-
-static enum drm_connector_status
-nv50_mstc_detect(struct drm_connector *connector, bool force)
-{
-	struct nv50_mstc *mstc = nv50_mstc(connector);
-	if (!mstc->port)
-		return connector_status_disconnected;
-	return drm_dp_mst_detect_port(connector, mstc->port->mgr, mstc->port);
-}
-
-static void
-nv50_mstc_destroy(struct drm_connector *connector)
-{
-	struct nv50_mstc *mstc = nv50_mstc(connector);
-	drm_connector_cleanup(&mstc->connector);
-	kfree(mstc);
-}
-
-static const struct drm_connector_funcs
-nv50_mstc = {
-	.reset = nouveau_conn_reset,
-	.detect = nv50_mstc_detect,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = nv50_mstc_destroy,
-	.atomic_duplicate_state = nouveau_conn_atomic_duplicate_state,
-	.atomic_destroy_state = nouveau_conn_atomic_destroy_state,
-	.atomic_set_property = nouveau_conn_atomic_set_property,
-	.atomic_get_property = nouveau_conn_atomic_get_property,
-};
-
-static int
-nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
-	      const char *path, struct nv50_mstc **pmstc)
-{
-	struct drm_device *dev = mstm->outp->base.base.dev;
-	struct nv50_mstc *mstc;
-	int ret, i;
-
-	if (!(mstc = *pmstc = kzalloc(sizeof(*mstc), GFP_KERNEL)))
-		return -ENOMEM;
-	mstc->mstm = mstm;
-	mstc->port = port;
-
-	ret = drm_connector_init(dev, &mstc->connector, &nv50_mstc,
-				 DRM_MODE_CONNECTOR_DisplayPort);
-	if (ret) {
-		kfree(*pmstc);
-		*pmstc = NULL;
-		return ret;
-	}
-
-	drm_connector_helper_add(&mstc->connector, &nv50_mstc_help);
-
-	mstc->connector.funcs->reset(&mstc->connector);
-	nouveau_conn_attach_properties(&mstc->connector);
-
-	for (i = 0; i < ARRAY_SIZE(mstm->msto) && mstm->msto[i]; i++)
-		drm_mode_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
-
-	drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0);
-	drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0);
-	drm_mode_connector_set_path_property(&mstc->connector, path);
-	return 0;
-}
-
-static void
-nv50_mstm_cleanup(struct nv50_mstm *mstm)
-{
-	struct nouveau_drm *drm = nouveau_drm(mstm->outp->base.base.dev);
-	struct drm_encoder *encoder;
-	int ret;
-
-	NV_ATOMIC(drm, "%s: mstm cleanup\n", mstm->outp->base.base.name);
-	ret = drm_dp_check_act_status(&mstm->mgr);
-
-	ret = drm_dp_update_payload_part2(&mstm->mgr);
-
-	drm_for_each_encoder(encoder, mstm->outp->base.base.dev) {
-		if (encoder->encoder_type == DRM_MODE_ENCODER_DPMST) {
-			struct nv50_msto *msto = nv50_msto(encoder);
-			struct nv50_mstc *mstc = msto->mstc;
-			if (mstc && mstc->mstm == mstm)
-				nv50_msto_cleanup(msto);
-		}
-	}
-
-	mstm->modified = false;
-}
-
-static void
-nv50_mstm_prepare(struct nv50_mstm *mstm)
-{
-	struct nouveau_drm *drm = nouveau_drm(mstm->outp->base.base.dev);
-	struct drm_encoder *encoder;
-	int ret;
-
-	NV_ATOMIC(drm, "%s: mstm prepare\n", mstm->outp->base.base.name);
-	ret = drm_dp_update_payload_part1(&mstm->mgr);
-
-	drm_for_each_encoder(encoder, mstm->outp->base.base.dev) {
-		if (encoder->encoder_type == DRM_MODE_ENCODER_DPMST) {
-			struct nv50_msto *msto = nv50_msto(encoder);
-			struct nv50_mstc *mstc = msto->mstc;
-			if (mstc && mstc->mstm == mstm)
-				nv50_msto_prepare(msto);
-		}
-	}
-
-	if (mstm->disabled) {
-		if (!mstm->links)
-			nv50_outp_release(mstm->outp);
-		mstm->disabled = false;
-	}
-}
-
-static void
-nv50_mstm_hotplug(struct drm_dp_mst_topology_mgr *mgr)
-{
-	struct nv50_mstm *mstm = nv50_mstm(mgr);
-	drm_kms_helper_hotplug_event(mstm->outp->base.base.dev);
-}
-
-static void
-nv50_mstm_destroy_connector(struct drm_dp_mst_topology_mgr *mgr,
-			    struct drm_connector *connector)
-{
-	struct nouveau_drm *drm = nouveau_drm(connector->dev);
-	struct nv50_mstc *mstc = nv50_mstc(connector);
-
-	drm_connector_unregister(&mstc->connector);
-
-	drm_modeset_lock_all(drm->dev);
-	drm_fb_helper_remove_one_connector(&drm->fbcon->helper, &mstc->connector);
-	mstc->port = NULL;
-	drm_modeset_unlock_all(drm->dev);
-
-	drm_connector_unreference(&mstc->connector);
-}
-
-static void
-nv50_mstm_register_connector(struct drm_connector *connector)
-{
-	struct nouveau_drm *drm = nouveau_drm(connector->dev);
-
-	drm_modeset_lock_all(drm->dev);
-	drm_fb_helper_add_one_connector(&drm->fbcon->helper, connector);
-	drm_modeset_unlock_all(drm->dev);
-
-	drm_connector_register(connector);
-}
-
-static struct drm_connector *
-nv50_mstm_add_connector(struct drm_dp_mst_topology_mgr *mgr,
-			struct drm_dp_mst_port *port, const char *path)
-{
-	struct nv50_mstm *mstm = nv50_mstm(mgr);
-	struct nv50_mstc *mstc;
-	int ret;
-
-	ret = nv50_mstc_new(mstm, port, path, &mstc);
-	if (ret) {
-		if (mstc)
-			mstc->connector.funcs->destroy(&mstc->connector);
-		return NULL;
-	}
-
-	return &mstc->connector;
-}
-
-static const struct drm_dp_mst_topology_cbs
-nv50_mstm = {
-	.add_connector = nv50_mstm_add_connector,
-	.register_connector = nv50_mstm_register_connector,
-	.destroy_connector = nv50_mstm_destroy_connector,
-	.hotplug = nv50_mstm_hotplug,
-};
-
-void
-nv50_mstm_service(struct nv50_mstm *mstm)
-{
-	struct drm_dp_aux *aux = mstm ? mstm->mgr.aux : NULL;
-	bool handled = true;
-	int ret;
-	u8 esi[8] = {};
-
-	if (!aux)
-		return;
-
-	while (handled) {
-		ret = drm_dp_dpcd_read(aux, DP_SINK_COUNT_ESI, esi, 8);
-		if (ret != 8) {
-			drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
-			return;
-		}
-
-		drm_dp_mst_hpd_irq(&mstm->mgr, esi, &handled);
-		if (!handled)
-			break;
-
-		drm_dp_dpcd_write(aux, DP_SINK_COUNT_ESI + 1, &esi[1], 3);
-	}
-}
-
-void
-nv50_mstm_remove(struct nv50_mstm *mstm)
-{
-	if (mstm)
-		drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
-}
-
-static int
-nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state)
-{
-	struct nouveau_encoder *outp = mstm->outp;
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_sor_dp_mst_link_v0 mst;
-	} args = {
-		.base.version = 1,
-		.base.method = NV50_DISP_MTHD_V1_SOR_DP_MST_LINK,
-		.base.hasht = outp->dcb->hasht,
-		.base.hashm = outp->dcb->hashm,
-		.mst.state = state,
-	};
-	struct nouveau_drm *drm = nouveau_drm(outp->base.base.dev);
-	struct nvif_object *disp = &drm->display->disp;
-	int ret;
-
-	if (dpcd >= 0x12) {
-		ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CTRL, &dpcd);
-		if (ret < 0)
-			return ret;
-
-		dpcd &= ~DP_MST_EN;
-		if (state)
-			dpcd |= DP_MST_EN;
-
-		ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, dpcd);
-		if (ret < 0)
-			return ret;
-	}
-
-	return nvif_mthd(disp, 0, &args, sizeof(args));
-}
-
-int
-nv50_mstm_detect(struct nv50_mstm *mstm, u8 dpcd[8], int allow)
-{
-	int ret, state = 0;
-
-	if (!mstm)
-		return 0;
-
-	if (dpcd[0] >= 0x12) {
-		ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CAP, &dpcd[1]);
-		if (ret < 0)
-			return ret;
-
-		if (!(dpcd[1] & DP_MST_CAP))
-			dpcd[0] = 0x11;
-		else
-			state = allow;
-	}
-
-	ret = nv50_mstm_enable(mstm, dpcd[0], state);
-	if (ret)
-		return ret;
-
-	ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, state);
-	if (ret)
-		return nv50_mstm_enable(mstm, dpcd[0], 0);
-
-	return mstm->mgr.mst_state;
-}
-
-static void
-nv50_mstm_fini(struct nv50_mstm *mstm)
-{
-	if (mstm && mstm->mgr.mst_state)
-		drm_dp_mst_topology_mgr_suspend(&mstm->mgr);
-}
-
-static void
-nv50_mstm_init(struct nv50_mstm *mstm)
-{
-	if (mstm && mstm->mgr.mst_state)
-		drm_dp_mst_topology_mgr_resume(&mstm->mgr);
-}
-
-static void
-nv50_mstm_del(struct nv50_mstm **pmstm)
-{
-	struct nv50_mstm *mstm = *pmstm;
-	if (mstm) {
-		kfree(*pmstm);
-		*pmstm = NULL;
-	}
-}
-
-static int
-nv50_mstm_new(struct nouveau_encoder *outp, struct drm_dp_aux *aux, int aux_max,
-	      int conn_base_id, struct nv50_mstm **pmstm)
-{
-	const int max_payloads = hweight8(outp->dcb->heads);
-	struct drm_device *dev = outp->base.base.dev;
-	struct nv50_mstm *mstm;
-	int ret, i;
-	u8 dpcd;
-
-	/* This is a workaround for some monitors not functioning
-	 * correctly in MST mode on initial module load.  I think
-	 * some bad interaction with the VBIOS may be responsible.
-	 *
-	 * A good ol' off and on again seems to work here ;)
-	 */
-	ret = drm_dp_dpcd_readb(aux, DP_DPCD_REV, &dpcd);
-	if (ret >= 0 && dpcd >= 0x12)
-		drm_dp_dpcd_writeb(aux, DP_MSTM_CTRL, 0);
-
-	if (!(mstm = *pmstm = kzalloc(sizeof(*mstm), GFP_KERNEL)))
-		return -ENOMEM;
-	mstm->outp = outp;
-	mstm->mgr.cbs = &nv50_mstm;
-
-	ret = drm_dp_mst_topology_mgr_init(&mstm->mgr, dev, aux, aux_max,
-					   max_payloads, conn_base_id);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < max_payloads; i++) {
-		ret = nv50_msto_new(dev, outp->dcb->heads, outp->base.base.name,
-				    i, &mstm->msto[i]);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/******************************************************************************
- * SOR
- *****************************************************************************/
-static void
-nv50_sor_update(struct nouveau_encoder *nv_encoder, u8 head,
-		struct drm_display_mode *mode, u8 proto, u8 depth)
-{
-	struct nv50_dmac *core = &nv50_mast(nv_encoder->base.base.dev)->base;
-	u32 *push;
-
-	if (!mode) {
-		nv_encoder->ctrl &= ~BIT(head);
-		if (!(nv_encoder->ctrl & 0x0000000f))
-			nv_encoder->ctrl = 0;
-	} else {
-		nv_encoder->ctrl |= proto << 8;
-		nv_encoder->ctrl |= BIT(head);
-	}
-
-	if ((push = evo_wait(core, 6))) {
-		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
-			if (mode) {
-				if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-					nv_encoder->ctrl |= 0x00001000;
-				if (mode->flags & DRM_MODE_FLAG_NVSYNC)
-					nv_encoder->ctrl |= 0x00002000;
-				nv_encoder->ctrl |= depth << 16;
-			}
-			evo_mthd(push, 0x0600 + (nv_encoder->or * 0x40), 1);
-		} else {
-			if (mode) {
-				u32 magic = 0x31ec6000 | (head << 25);
-				u32 syncs = 0x00000001;
-				if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-					syncs |= 0x00000008;
-				if (mode->flags & DRM_MODE_FLAG_NVSYNC)
-					syncs |= 0x00000010;
-				if (mode->flags & DRM_MODE_FLAG_INTERLACE)
-					magic |= 0x00000001;
-
-				evo_mthd(push, 0x0404 + (head * 0x300), 2);
-				evo_data(push, syncs | (depth << 6));
-				evo_data(push, magic);
-			}
-			evo_mthd(push, 0x0200 + (nv_encoder->or * 0x20), 1);
-		}
-		evo_data(push, nv_encoder->ctrl);
-		evo_kick(push, core);
-	}
-}
-
-static void
-nv50_sor_disable(struct drm_encoder *encoder)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(nv_encoder->crtc);
-
-	nv_encoder->crtc = NULL;
-
-	if (nv_crtc) {
-		struct nvkm_i2c_aux *aux = nv_encoder->aux;
-		u8 pwr;
-
-		if (aux) {
-			int ret = nvkm_rdaux(aux, DP_SET_POWER, &pwr, 1);
-			if (ret == 0) {
-				pwr &= ~DP_SET_POWER_MASK;
-				pwr |=  DP_SET_POWER_D3;
-				nvkm_wraux(aux, DP_SET_POWER, &pwr, 1);
-			}
-		}
-
-		nv_encoder->update(nv_encoder, nv_crtc->index, NULL, 0, 0);
-		nv50_audio_disable(encoder, nv_crtc);
-		nv50_hdmi_disable(&nv_encoder->base.base, nv_crtc);
-		nv50_outp_release(nv_encoder);
-	}
-}
-
-static void
-nv50_sor_enable(struct drm_encoder *encoder)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
-	struct drm_display_mode *mode = &nv_crtc->base.state->adjusted_mode;
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_sor_lvds_script_v0 lvds;
-	} lvds = {
-		.base.version = 1,
-		.base.method  = NV50_DISP_MTHD_V1_SOR_LVDS_SCRIPT,
-		.base.hasht   = nv_encoder->dcb->hasht,
-		.base.hashm   = nv_encoder->dcb->hashm,
-	};
-	struct nv50_disp *disp = nv50_disp(encoder->dev);
-	struct drm_device *dev = encoder->dev;
-	struct nouveau_drm *drm = nouveau_drm(dev);
-	struct nouveau_connector *nv_connector;
-	struct nvbios *bios = &drm->vbios;
-	u8 proto = 0xf;
-	u8 depth = 0x0;
-
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
-	nv_encoder->crtc = encoder->crtc;
-	nv50_outp_acquire(nv_encoder);
-
-	switch (nv_encoder->dcb->type) {
-	case DCB_OUTPUT_TMDS:
-		if (nv_encoder->link & 1) {
-			proto = 0x1;
-			/* Only enable dual-link if:
-			 *  - Need to (i.e. rate > 165MHz)
-			 *  - DCB says we can
-			 *  - Not an HDMI monitor, since there's no dual-link
-			 *    on HDMI.
-			 */
-			if (mode->clock >= 165000 &&
-			    nv_encoder->dcb->duallink_possible &&
-			    !drm_detect_hdmi_monitor(nv_connector->edid))
-				proto |= 0x4;
-		} else {
-			proto = 0x2;
-		}
-
-		nv50_hdmi_enable(&nv_encoder->base.base, mode);
-		break;
-	case DCB_OUTPUT_LVDS:
-		proto = 0x0;
-
-		if (bios->fp_no_ddc) {
-			if (bios->fp.dual_link)
-				lvds.lvds.script |= 0x0100;
-			if (bios->fp.if_is_24bit)
-				lvds.lvds.script |= 0x0200;
-		} else {
-			if (nv_connector->type == DCB_CONNECTOR_LVDS_SPWG) {
-				if (((u8 *)nv_connector->edid)[121] == 2)
-					lvds.lvds.script |= 0x0100;
-			} else
-			if (mode->clock >= bios->fp.duallink_transition_clk) {
-				lvds.lvds.script |= 0x0100;
-			}
-
-			if (lvds.lvds.script & 0x0100) {
-				if (bios->fp.strapless_is_24bit & 2)
-					lvds.lvds.script |= 0x0200;
-			} else {
-				if (bios->fp.strapless_is_24bit & 1)
-					lvds.lvds.script |= 0x0200;
-			}
-
-			if (nv_connector->base.display_info.bpc == 8)
-				lvds.lvds.script |= 0x0200;
-		}
-
-		nvif_mthd(disp->disp, 0, &lvds, sizeof(lvds));
-		break;
-	case DCB_OUTPUT_DP:
-		if (nv_connector->base.display_info.bpc == 6)
-			depth = 0x2;
-		else
-		if (nv_connector->base.display_info.bpc == 8)
-			depth = 0x5;
-		else
-			depth = 0x6;
-
-		if (nv_encoder->link & 1)
-			proto = 0x8;
-		else
-			proto = 0x9;
-
-		nv50_audio_enable(encoder, mode);
-		break;
-	default:
-		BUG();
-		break;
-	}
-
-	nv_encoder->update(nv_encoder, nv_crtc->index, mode, proto, depth);
-}
-
-static const struct drm_encoder_helper_funcs
-nv50_sor_help = {
-	.atomic_check = nv50_outp_atomic_check,
-	.enable = nv50_sor_enable,
-	.disable = nv50_sor_disable,
-};
-
-static void
-nv50_sor_destroy(struct drm_encoder *encoder)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	nv50_mstm_del(&nv_encoder->dp.mstm);
-	drm_encoder_cleanup(encoder);
-	kfree(encoder);
-}
-
-static const struct drm_encoder_funcs
-nv50_sor_func = {
-	.destroy = nv50_sor_destroy,
-};
-
-static int
-nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
-{
-	struct nouveau_connector *nv_connector = nouveau_connector(connector);
-	struct nouveau_drm *drm = nouveau_drm(connector->dev);
-	struct nvkm_i2c *i2c = nvxx_i2c(&drm->client.device);
-	struct nouveau_encoder *nv_encoder;
-	struct drm_encoder *encoder;
-	int type, ret;
-
-	switch (dcbe->type) {
-	case DCB_OUTPUT_LVDS: type = DRM_MODE_ENCODER_LVDS; break;
-	case DCB_OUTPUT_TMDS:
-	case DCB_OUTPUT_DP:
-	default:
-		type = DRM_MODE_ENCODER_TMDS;
-		break;
-	}
-
-	nv_encoder = kzalloc(sizeof(*nv_encoder), GFP_KERNEL);
-	if (!nv_encoder)
-		return -ENOMEM;
-	nv_encoder->dcb = dcbe;
-	nv_encoder->update = nv50_sor_update;
-
-	encoder = to_drm_encoder(nv_encoder);
-	encoder->possible_crtcs = dcbe->heads;
-	encoder->possible_clones = 0;
-	drm_encoder_init(connector->dev, encoder, &nv50_sor_func, type,
-			 "sor-%04x-%04x", dcbe->hasht, dcbe->hashm);
-	drm_encoder_helper_add(encoder, &nv50_sor_help);
-
-	drm_mode_connector_attach_encoder(connector, encoder);
-
-	if (dcbe->type == DCB_OUTPUT_DP) {
-		struct nv50_disp *disp = nv50_disp(encoder->dev);
-		struct nvkm_i2c_aux *aux =
-			nvkm_i2c_aux_find(i2c, dcbe->i2c_index);
-		if (aux) {
-			if (disp->disp->oclass < GF110_DISP) {
-				/* HW has no support for address-only
-				 * transactions, so we're required to
-				 * use custom I2C-over-AUX code.
-				 */
-				nv_encoder->i2c = &aux->i2c;
-			} else {
-				nv_encoder->i2c = &nv_connector->aux.ddc;
-			}
-			nv_encoder->aux = aux;
-		}
-
-		/*TODO: Use DP Info Table to check for support. */
-		if (disp->disp->oclass >= GF110_DISP) {
-			ret = nv50_mstm_new(nv_encoder, &nv_connector->aux, 16,
-					    nv_connector->base.base.id,
-					    &nv_encoder->dp.mstm);
-			if (ret)
-				return ret;
-		}
-	} else {
-		struct nvkm_i2c_bus *bus =
-			nvkm_i2c_bus_find(i2c, dcbe->i2c_index);
-		if (bus)
-			nv_encoder->i2c = &bus->i2c;
-	}
-
-	return 0;
-}
-
-/******************************************************************************
- * PIOR
- *****************************************************************************/
-static int
-nv50_pior_atomic_check(struct drm_encoder *encoder,
-		       struct drm_crtc_state *crtc_state,
-		       struct drm_connector_state *conn_state)
-{
-	int ret = nv50_outp_atomic_check(encoder, crtc_state, conn_state);
-	if (ret)
-		return ret;
-	crtc_state->adjusted_mode.clock *= 2;
-	return 0;
-}
-
-static void
-nv50_pior_disable(struct drm_encoder *encoder)
-{
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nv50_mast *mast = nv50_mast(encoder->dev);
-	const int or = nv_encoder->or;
-	u32 *push;
-
-	if (nv_encoder->crtc) {
-		push = evo_wait(mast, 4);
-		if (push) {
-			if (nv50_vers(mast) < GF110_DISP_CORE_CHANNEL_DMA) {
-				evo_mthd(push, 0x0700 + (or * 0x040), 1);
-				evo_data(push, 0x00000000);
-			}
-			evo_kick(push, mast);
-		}
-	}
-
-	nv_encoder->crtc = NULL;
-	nv50_outp_release(nv_encoder);
-}
-
-static void
-nv50_pior_enable(struct drm_encoder *encoder)
-{
-	struct nv50_mast *mast = nv50_mast(encoder->dev);
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
-	struct nouveau_connector *nv_connector;
-	struct drm_display_mode *mode = &nv_crtc->base.state->adjusted_mode;
-	u8 owner = 1 << nv_crtc->index;
-	u8 proto, depth;
-	u32 *push;
-
-	nv50_outp_acquire(nv_encoder);
-
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
-	switch (nv_connector->base.display_info.bpc) {
-	case 10: depth = 0x6; break;
-	case  8: depth = 0x5; break;
-	case  6: depth = 0x2; break;
-	default: depth = 0x0; break;
-	}
-
-	switch (nv_encoder->dcb->type) {
-	case DCB_OUTPUT_TMDS:
-	case DCB_OUTPUT_DP:
-		proto = 0x0;
-		break;
-	default:
-		BUG();
-		break;
-	}
-
-	push = evo_wait(mast, 8);
-	if (push) {
-		if (nv50_vers(mast) < GF110_DISP_CORE_CHANNEL_DMA) {
-			u32 ctrl = (depth << 16) | (proto << 8) | owner;
-			if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-				ctrl |= 0x00001000;
-			if (mode->flags & DRM_MODE_FLAG_NVSYNC)
-				ctrl |= 0x00002000;
-			evo_mthd(push, 0x0700 + (nv_encoder->or * 0x040), 1);
-			evo_data(push, ctrl);
-		}
-
-		evo_kick(push, mast);
-	}
-
-	nv_encoder->crtc = encoder->crtc;
-}
-
-static const struct drm_encoder_helper_funcs
-nv50_pior_help = {
-	.atomic_check = nv50_pior_atomic_check,
-	.enable = nv50_pior_enable,
-	.disable = nv50_pior_disable,
-};
-
-static void
-nv50_pior_destroy(struct drm_encoder *encoder)
-{
-	drm_encoder_cleanup(encoder);
-	kfree(encoder);
-}
-
-static const struct drm_encoder_funcs
-nv50_pior_func = {
-	.destroy = nv50_pior_destroy,
-};
-
-static int
-nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe)
-{
-	struct nouveau_connector *nv_connector = nouveau_connector(connector);
-	struct nouveau_drm *drm = nouveau_drm(connector->dev);
-	struct nvkm_i2c *i2c = nvxx_i2c(&drm->client.device);
-	struct nvkm_i2c_bus *bus = NULL;
-	struct nvkm_i2c_aux *aux = NULL;
-	struct i2c_adapter *ddc;
-	struct nouveau_encoder *nv_encoder;
-	struct drm_encoder *encoder;
-	int type;
-
-	switch (dcbe->type) {
-	case DCB_OUTPUT_TMDS:
-		bus  = nvkm_i2c_bus_find(i2c, NVKM_I2C_BUS_EXT(dcbe->extdev));
-		ddc  = bus ? &bus->i2c : NULL;
-		type = DRM_MODE_ENCODER_TMDS;
-		break;
-	case DCB_OUTPUT_DP:
-		aux  = nvkm_i2c_aux_find(i2c, NVKM_I2C_AUX_EXT(dcbe->extdev));
-		ddc  = aux ? &nv_connector->aux.ddc : NULL;
-		type = DRM_MODE_ENCODER_TMDS;
-		break;
-	default:
-		return -ENODEV;
-	}
-
-	nv_encoder = kzalloc(sizeof(*nv_encoder), GFP_KERNEL);
-	if (!nv_encoder)
-		return -ENOMEM;
-	nv_encoder->dcb = dcbe;
-	nv_encoder->i2c = ddc;
-	nv_encoder->aux = aux;
-
-	encoder = to_drm_encoder(nv_encoder);
-	encoder->possible_crtcs = dcbe->heads;
-	encoder->possible_clones = 0;
-	drm_encoder_init(connector->dev, encoder, &nv50_pior_func, type,
-			 "pior-%04x-%04x", dcbe->hasht, dcbe->hashm);
-	drm_encoder_helper_add(encoder, &nv50_pior_help);
-
-	drm_mode_connector_attach_encoder(connector, encoder);
-	return 0;
-}
-
-/******************************************************************************
- * Atomic
- *****************************************************************************/
-
-static void
-nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 interlock)
-{
-	struct nv50_disp *disp = nv50_disp(drm->dev);
-	struct nv50_dmac *core = &disp->mast.base;
-	struct nv50_mstm *mstm;
-	struct drm_encoder *encoder;
-	u32 *push;
-
-	NV_ATOMIC(drm, "commit core %08x\n", interlock);
-
-	drm_for_each_encoder(encoder, drm->dev) {
-		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
-			mstm = nouveau_encoder(encoder)->dp.mstm;
-			if (mstm && mstm->modified)
-				nv50_mstm_prepare(mstm);
-		}
-	}
-
-	if ((push = evo_wait(core, 5))) {
-		evo_mthd(push, 0x0084, 1);
-		evo_data(push, 0x80000000);
-		evo_mthd(push, 0x0080, 2);
-		evo_data(push, interlock);
-		evo_data(push, 0x00000000);
-		nouveau_bo_wr32(disp->sync, 0, 0x00000000);
-		evo_kick(push, core);
-		if (nvif_msec(&drm->client.device, 2000ULL,
-			if (nouveau_bo_rd32(disp->sync, 0))
-				break;
-			usleep_range(1, 2);
-		) < 0)
-			NV_ERROR(drm, "EVO timeout\n");
-	}
-
-	drm_for_each_encoder(encoder, drm->dev) {
-		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
-			mstm = nouveau_encoder(encoder)->dp.mstm;
-			if (mstm && mstm->modified)
-				nv50_mstm_cleanup(mstm);
-		}
-	}
-}
-
-static void
-nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
-{
-	struct drm_device *dev = state->dev;
-	struct drm_crtc_state *new_crtc_state, *old_crtc_state;
-	struct drm_crtc *crtc;
-	struct drm_plane_state *new_plane_state;
-	struct drm_plane *plane;
-	struct nouveau_drm *drm = nouveau_drm(dev);
-	struct nv50_disp *disp = nv50_disp(dev);
-	struct nv50_atom *atom = nv50_atom(state);
-	struct nv50_outp_atom *outp, *outt;
-	u32 interlock_core = 0;
-	u32 interlock_chan = 0;
-	int i;
-
-	NV_ATOMIC(drm, "commit %d %d\n", atom->lock_core, atom->flush_disable);
-	drm_atomic_helper_wait_for_fences(dev, state, false);
-	drm_atomic_helper_wait_for_dependencies(state);
-	drm_atomic_helper_update_legacy_modeset_state(dev, state);
-
-	if (atom->lock_core)
-		mutex_lock(&disp->mutex);
-
-	/* Disable head(s). */
-	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-		struct nv50_head_atom *asyh = nv50_head_atom(new_crtc_state);
-		struct nv50_head *head = nv50_head(crtc);
-
-		NV_ATOMIC(drm, "%s: clr %04x (set %04x)\n", crtc->name,
-			  asyh->clr.mask, asyh->set.mask);
-		if (old_crtc_state->active && !new_crtc_state->active)
-			drm_crtc_vblank_off(crtc);
-
-		if (asyh->clr.mask) {
-			nv50_head_flush_clr(head, asyh, atom->flush_disable);
-			interlock_core |= 1;
-		}
-	}
-
-	/* Disable plane(s). */
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
-		struct nv50_wndw *wndw = nv50_wndw(plane);
-
-		NV_ATOMIC(drm, "%s: clr %02x (set %02x)\n", plane->name,
-			  asyw->clr.mask, asyw->set.mask);
-		if (!asyw->clr.mask)
-			continue;
-
-		interlock_chan |= nv50_wndw_flush_clr(wndw, interlock_core,
-						      atom->flush_disable,
-						      asyw);
-	}
-
-	/* Disable output path(s). */
-	list_for_each_entry(outp, &atom->outp, head) {
-		const struct drm_encoder_helper_funcs *help;
-		struct drm_encoder *encoder;
-
-		encoder = outp->encoder;
-		help = encoder->helper_private;
-
-		NV_ATOMIC(drm, "%s: clr %02x (set %02x)\n", encoder->name,
-			  outp->clr.mask, outp->set.mask);
-
-		if (outp->clr.mask) {
-			help->disable(encoder);
-			interlock_core |= 1;
-			if (outp->flush_disable) {
-				nv50_disp_atomic_commit_core(drm, interlock_chan);
-				interlock_core = 0;
-				interlock_chan = 0;
-			}
-		}
-	}
-
-	/* Flush disable. */
-	if (interlock_core) {
-		if (atom->flush_disable) {
-			nv50_disp_atomic_commit_core(drm, interlock_chan);
-			interlock_core = 0;
-			interlock_chan = 0;
-		}
-	}
-
-	/* Update output path(s). */
-	list_for_each_entry_safe(outp, outt, &atom->outp, head) {
-		const struct drm_encoder_helper_funcs *help;
-		struct drm_encoder *encoder;
-
-		encoder = outp->encoder;
-		help = encoder->helper_private;
-
-		NV_ATOMIC(drm, "%s: set %02x (clr %02x)\n", encoder->name,
-			  outp->set.mask, outp->clr.mask);
-
-		if (outp->set.mask) {
-			help->enable(encoder);
-			interlock_core = 1;
-		}
-
-		list_del(&outp->head);
-		kfree(outp);
-	}
-
-	/* Update head(s). */
-	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-		struct nv50_head_atom *asyh = nv50_head_atom(new_crtc_state);
-		struct nv50_head *head = nv50_head(crtc);
-
-		NV_ATOMIC(drm, "%s: set %04x (clr %04x)\n", crtc->name,
-			  asyh->set.mask, asyh->clr.mask);
-
-		if (asyh->set.mask) {
-			nv50_head_flush_set(head, asyh);
-			interlock_core = 1;
-		}
-
-		if (new_crtc_state->active) {
-			if (!old_crtc_state->active)
-				drm_crtc_vblank_on(crtc);
-			if (new_crtc_state->event)
-				drm_crtc_vblank_get(crtc);
-		}
-	}
-
-	/* Update plane(s). */
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
-		struct nv50_wndw *wndw = nv50_wndw(plane);
-
-		NV_ATOMIC(drm, "%s: set %02x (clr %02x)\n", plane->name,
-			  asyw->set.mask, asyw->clr.mask);
-		if ( !asyw->set.mask &&
-		    (!asyw->clr.mask || atom->flush_disable))
-			continue;
-
-		interlock_chan |= nv50_wndw_flush_set(wndw, interlock_core, asyw);
-	}
-
-	/* Flush update. */
-	if (interlock_core) {
-		if (!interlock_chan && atom->state.legacy_cursor_update) {
-			u32 *push = evo_wait(&disp->mast, 2);
-			if (push) {
-				evo_mthd(push, 0x0080, 1);
-				evo_data(push, 0x00000000);
-				evo_kick(push, &disp->mast);
-			}
-		} else {
-			nv50_disp_atomic_commit_core(drm, interlock_chan);
-		}
-	}
-
-	if (atom->lock_core)
-		mutex_unlock(&disp->mutex);
-
-	/* Wait for HW to signal completion. */
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
-		struct nv50_wndw *wndw = nv50_wndw(plane);
-		int ret = nv50_wndw_wait_armed(wndw, asyw);
-		if (ret)
-			NV_ERROR(drm, "%s: timeout\n", plane->name);
-	}
-
-	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
-		if (new_crtc_state->event) {
-			unsigned long flags;
-			/* Get correct count/ts if racing with vblank irq */
-			if (new_crtc_state->active)
-				drm_crtc_accurate_vblank_count(crtc);
-			spin_lock_irqsave(&crtc->dev->event_lock, flags);
-			drm_crtc_send_vblank_event(crtc, new_crtc_state->event);
-			spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
-
-			new_crtc_state->event = NULL;
-			if (new_crtc_state->active)
-				drm_crtc_vblank_put(crtc);
-		}
-	}
-
-	drm_atomic_helper_commit_hw_done(state);
-	drm_atomic_helper_cleanup_planes(dev, state);
-	drm_atomic_helper_commit_cleanup_done(state);
-	drm_atomic_state_put(state);
-}
-
-static void
-nv50_disp_atomic_commit_work(struct work_struct *work)
-{
-	struct drm_atomic_state *state =
-		container_of(work, typeof(*state), commit_work);
-	nv50_disp_atomic_commit_tail(state);
-}
-
-static int
-nv50_disp_atomic_commit(struct drm_device *dev,
-			struct drm_atomic_state *state, bool nonblock)
-{
-	struct nouveau_drm *drm = nouveau_drm(dev);
-	struct nv50_disp *disp = nv50_disp(dev);
-	struct drm_plane_state *new_plane_state;
-	struct drm_plane *plane;
-	struct drm_crtc *crtc;
-	bool active = false;
-	int ret, i;
-
-	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0 && ret != -EACCES)
-		return ret;
-
-	ret = drm_atomic_helper_setup_commit(state, nonblock);
-	if (ret)
-		goto done;
-
-	INIT_WORK(&state->commit_work, nv50_disp_atomic_commit_work);
-
-	ret = drm_atomic_helper_prepare_planes(dev, state);
-	if (ret)
-		goto done;
-
-	if (!nonblock) {
-		ret = drm_atomic_helper_wait_for_fences(dev, state, true);
-		if (ret)
-			goto err_cleanup;
-	}
-
-	ret = drm_atomic_helper_swap_state(state, true);
-	if (ret)
-		goto err_cleanup;
-
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
-		struct nv50_wndw *wndw = nv50_wndw(plane);
-
-		if (asyw->set.image) {
-			asyw->ntfy.handle = wndw->dmac->sync.handle;
-			asyw->ntfy.offset = wndw->ntfy;
-			asyw->ntfy.awaken = false;
-			asyw->set.ntfy = true;
-			nouveau_bo_wr32(disp->sync, wndw->ntfy / 4, 0x00000000);
-			wndw->ntfy ^= 0x10;
-		}
-	}
-
-	drm_atomic_state_get(state);
-
-	if (nonblock)
-		queue_work(system_unbound_wq, &state->commit_work);
-	else
-		nv50_disp_atomic_commit_tail(state);
-
-	drm_for_each_crtc(crtc, dev) {
-		if (crtc->state->enable) {
-			if (!drm->have_disp_power_ref) {
-				drm->have_disp_power_ref = true;
-				return 0;
-			}
-			active = true;
-			break;
-		}
-	}
-
-	if (!active && drm->have_disp_power_ref) {
-		pm_runtime_put_autosuspend(dev->dev);
-		drm->have_disp_power_ref = false;
-	}
-
-err_cleanup:
-	if (ret)
-		drm_atomic_helper_cleanup_planes(dev, state);
-done:
-	pm_runtime_put_autosuspend(dev->dev);
-	return ret;
-}
-
-static struct nv50_outp_atom *
-nv50_disp_outp_atomic_add(struct nv50_atom *atom, struct drm_encoder *encoder)
-{
-	struct nv50_outp_atom *outp;
-
-	list_for_each_entry(outp, &atom->outp, head) {
-		if (outp->encoder == encoder)
-			return outp;
-	}
-
-	outp = kzalloc(sizeof(*outp), GFP_KERNEL);
-	if (!outp)
-		return ERR_PTR(-ENOMEM);
-
-	list_add(&outp->head, &atom->outp);
-	outp->encoder = encoder;
-	return outp;
-}
-
-static int
-nv50_disp_outp_atomic_check_clr(struct nv50_atom *atom,
-				struct drm_connector_state *old_connector_state)
-{
-	struct drm_encoder *encoder = old_connector_state->best_encoder;
-	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
-	struct drm_crtc *crtc;
-	struct nv50_outp_atom *outp;
-
-	if (!(crtc = old_connector_state->crtc))
-		return 0;
-
-	old_crtc_state = drm_atomic_get_old_crtc_state(&atom->state, crtc);
-	new_crtc_state = drm_atomic_get_new_crtc_state(&atom->state, crtc);
-	if (old_crtc_state->active && drm_atomic_crtc_needs_modeset(new_crtc_state)) {
-		outp = nv50_disp_outp_atomic_add(atom, encoder);
-		if (IS_ERR(outp))
-			return PTR_ERR(outp);
-
-		if (outp->encoder->encoder_type == DRM_MODE_ENCODER_DPMST) {
-			outp->flush_disable = true;
-			atom->flush_disable = true;
-		}
-		outp->clr.ctrl = true;
-		atom->lock_core = true;
-	}
-
-	return 0;
-}
-
-static int
-nv50_disp_outp_atomic_check_set(struct nv50_atom *atom,
-				struct drm_connector_state *connector_state)
-{
-	struct drm_encoder *encoder = connector_state->best_encoder;
-	struct drm_crtc_state *new_crtc_state;
-	struct drm_crtc *crtc;
-	struct nv50_outp_atom *outp;
-
-	if (!(crtc = connector_state->crtc))
-		return 0;
-
-	new_crtc_state = drm_atomic_get_new_crtc_state(&atom->state, crtc);
-	if (new_crtc_state->active && drm_atomic_crtc_needs_modeset(new_crtc_state)) {
-		outp = nv50_disp_outp_atomic_add(atom, encoder);
-		if (IS_ERR(outp))
-			return PTR_ERR(outp);
-
-		outp->set.ctrl = true;
-		atom->lock_core = true;
-	}
-
-	return 0;
-}
-
-static int
-nv50_disp_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
-{
-	struct nv50_atom *atom = nv50_atom(state);
-	struct drm_connector_state *old_connector_state, *new_connector_state;
-	struct drm_connector *connector;
-	int ret, i;
-
-	ret = drm_atomic_helper_check(dev, state);
-	if (ret)
-		return ret;
-
-	for_each_oldnew_connector_in_state(state, connector, old_connector_state, new_connector_state, i) {
-		ret = nv50_disp_outp_atomic_check_clr(atom, old_connector_state);
-		if (ret)
-			return ret;
-
-		ret = nv50_disp_outp_atomic_check_set(atom, new_connector_state);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-static void
-nv50_disp_atomic_state_clear(struct drm_atomic_state *state)
-{
-	struct nv50_atom *atom = nv50_atom(state);
-	struct nv50_outp_atom *outp, *outt;
-
-	list_for_each_entry_safe(outp, outt, &atom->outp, head) {
-		list_del(&outp->head);
-		kfree(outp);
-	}
-
-	drm_atomic_state_default_clear(state);
-}
-
-static void
-nv50_disp_atomic_state_free(struct drm_atomic_state *state)
-{
-	struct nv50_atom *atom = nv50_atom(state);
-	drm_atomic_state_default_release(&atom->state);
-	kfree(atom);
-}
-
-static struct drm_atomic_state *
-nv50_disp_atomic_state_alloc(struct drm_device *dev)
-{
-	struct nv50_atom *atom;
-	if (!(atom = kzalloc(sizeof(*atom), GFP_KERNEL)) ||
-	    drm_atomic_state_init(dev, &atom->state) < 0) {
-		kfree(atom);
-		return NULL;
-	}
-	INIT_LIST_HEAD(&atom->outp);
-	return &atom->state;
-}
-
-static const struct drm_mode_config_funcs
-nv50_disp_func = {
-	.fb_create = nouveau_user_framebuffer_create,
-	.output_poll_changed = drm_fb_helper_output_poll_changed,
-	.atomic_check = nv50_disp_atomic_check,
-	.atomic_commit = nv50_disp_atomic_commit,
-	.atomic_state_alloc = nv50_disp_atomic_state_alloc,
-	.atomic_state_clear = nv50_disp_atomic_state_clear,
-	.atomic_state_free = nv50_disp_atomic_state_free,
-};
-
-/******************************************************************************
- * Init
- *****************************************************************************/
-
-void
-nv50_display_fini(struct drm_device *dev)
-{
-	struct nouveau_encoder *nv_encoder;
-	struct drm_encoder *encoder;
-	struct drm_plane *plane;
-
-	drm_for_each_plane(plane, dev) {
-		struct nv50_wndw *wndw = nv50_wndw(plane);
-		if (plane->funcs != &nv50_wndw)
-			continue;
-		nv50_wndw_fini(wndw);
-	}
-
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
-			nv_encoder = nouveau_encoder(encoder);
-			nv50_mstm_fini(nv_encoder->dp.mstm);
-		}
-	}
-}
-
-int
-nv50_display_init(struct drm_device *dev)
-{
-	struct drm_encoder *encoder;
-	struct drm_plane *plane;
-	u32 *push;
-
-	push = evo_wait(nv50_mast(dev), 32);
-	if (!push)
-		return -EBUSY;
-
-	evo_mthd(push, 0x0088, 1);
-	evo_data(push, nv50_mast(dev)->base.sync.handle);
-	evo_kick(push, nv50_mast(dev));
-
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
-			struct nouveau_encoder *nv_encoder =
-				nouveau_encoder(encoder);
-			nv50_mstm_init(nv_encoder->dp.mstm);
-		}
-	}
-
-	drm_for_each_plane(plane, dev) {
-		struct nv50_wndw *wndw = nv50_wndw(plane);
-		if (plane->funcs != &nv50_wndw)
-			continue;
-		nv50_wndw_init(wndw);
-	}
-
-	return 0;
-}
-
-void
-nv50_display_destroy(struct drm_device *dev)
-{
-	struct nv50_disp *disp = nv50_disp(dev);
-
-	nv50_dmac_destroy(&disp->mast.base, disp->disp);
-
-	nouveau_bo_unmap(disp->sync);
-	if (disp->sync)
-		nouveau_bo_unpin(disp->sync);
-	nouveau_bo_ref(NULL, &disp->sync);
-
-	nouveau_display(dev)->priv = NULL;
-	kfree(disp);
-}
-
-MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)");
-static int nouveau_atomic = 0;
-module_param_named(atomic, nouveau_atomic, int, 0400);
-
-int
-nv50_display_create(struct drm_device *dev)
-{
-	struct nvif_device *device = &nouveau_drm(dev)->client.device;
-	struct nouveau_drm *drm = nouveau_drm(dev);
-	struct dcb_table *dcb = &drm->vbios.dcb;
-	struct drm_connector *connector, *tmp;
-	struct nv50_disp *disp;
-	struct dcb_output *dcbe;
-	int crtcs, ret, i;
-
-	disp = kzalloc(sizeof(*disp), GFP_KERNEL);
-	if (!disp)
-		return -ENOMEM;
-
-	mutex_init(&disp->mutex);
-
-	nouveau_display(dev)->priv = disp;
-	nouveau_display(dev)->dtor = nv50_display_destroy;
-	nouveau_display(dev)->init = nv50_display_init;
-	nouveau_display(dev)->fini = nv50_display_fini;
-	disp->disp = &nouveau_display(dev)->disp;
-	dev->mode_config.funcs = &nv50_disp_func;
-	dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP;
-	if (nouveau_atomic)
-		dev->driver->driver_features |= DRIVER_ATOMIC;
-
-	/* small shared memory area we use for notifiers and semaphores */
-	ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM,
-			     0, 0x0000, NULL, NULL, &disp->sync);
-	if (!ret) {
-		ret = nouveau_bo_pin(disp->sync, TTM_PL_FLAG_VRAM, true);
-		if (!ret) {
-			ret = nouveau_bo_map(disp->sync);
-			if (ret)
-				nouveau_bo_unpin(disp->sync);
-		}
-		if (ret)
-			nouveau_bo_ref(NULL, &disp->sync);
-	}
-
-	if (ret)
-		goto out;
-
-	/* allocate master evo channel */
-	ret = nv50_core_create(device, disp->disp, disp->sync->bo.offset,
-			      &disp->mast);
-	if (ret)
-		goto out;
-
-	/* create crtc objects to represent the hw heads */
-	if (disp->disp->oclass >= GF110_DISP)
-		crtcs = nvif_rd32(&device->object, 0x612004) & 0xf;
-	else
-		crtcs = 0x3;
-
-	for (i = 0; i < fls(crtcs); i++) {
-		if (!(crtcs & (1 << i)))
-			continue;
-		ret = nv50_head_create(dev, i);
-		if (ret)
-			goto out;
-	}
-
-	/* create encoder/connector objects based on VBIOS DCB table */
-	for (i = 0, dcbe = &dcb->entry[0]; i < dcb->entries; i++, dcbe++) {
-		connector = nouveau_connector_create(dev, dcbe->connector);
-		if (IS_ERR(connector))
-			continue;
-
-		if (dcbe->location == DCB_LOC_ON_CHIP) {
-			switch (dcbe->type) {
-			case DCB_OUTPUT_TMDS:
-			case DCB_OUTPUT_LVDS:
-			case DCB_OUTPUT_DP:
-				ret = nv50_sor_create(connector, dcbe);
-				break;
-			case DCB_OUTPUT_ANALOG:
-				ret = nv50_dac_create(connector, dcbe);
-				break;
-			default:
-				ret = -ENODEV;
-				break;
-			}
-		} else {
-			ret = nv50_pior_create(connector, dcbe);
-		}
-
-		if (ret) {
-			NV_WARN(drm, "failed to create encoder %d/%d/%d: %d\n",
-				     dcbe->location, dcbe->type,
-				     ffs(dcbe->or) - 1, ret);
-			ret = 0;
-		}
-	}
-
-	/* cull any connectors we created that don't have an encoder */
-	list_for_each_entry_safe(connector, tmp, &dev->mode_config.connector_list, head) {
-		if (connector->encoder_ids[0])
-			continue;
-
-		NV_WARN(drm, "%s has no encoders, removing\n",
-			connector->name);
-		connector->funcs->destroy(connector);
-	}
-
-out:
-	if (ret)
-		nv50_display_destroy(dev);
-	return ret;
-}
diff --git a/drivers/gpu/drm/nouveau/nv50_display.h b/drivers/gpu/drm/nouveau/nv50_display.h
index 918187cee84b..fbd3b15583bc 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.h
+++ b/drivers/gpu/drm/nouveau/nv50_display.h
@@ -28,7 +28,6 @@
 #define __NV50_DISPLAY_H__
 
 #include "nouveau_display.h"
-#include "nouveau_crtc.h"
 #include "nouveau_reg.h"
 
 int  nv50_display_create(struct drm_device *);
diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c
index a369d978e267..a00ecc3de053 100644
--- a/drivers/gpu/drm/nouveau/nv50_fence.c
+++ b/drivers/gpu/drm/nouveau/nv50_fence.c
@@ -78,8 +78,6 @@ nv50_fence_create(struct nouveau_drm *drm)
 	priv->base.resume = nv17_fence_resume;
 	priv->base.context_new = nv50_fence_context_new;
 	priv->base.context_del = nv10_fence_context_del;
-	priv->base.contexts = 127;
-	priv->base.context_base = dma_fence_context_alloc(priv->base.contexts);
 	spin_lock_init(&priv->lock);
 
 	ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM,
diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c
index 5f0c0c27d5dc..090664899247 100644
--- a/drivers/gpu/drm/nouveau/nv84_fence.c
+++ b/drivers/gpu/drm/nouveau/nv84_fence.c
@@ -141,9 +141,9 @@ nv84_fence_suspend(struct nouveau_drm *drm)
 	struct nv84_fence_priv *priv = drm->fence;
 	int i;
 
-	priv->suspend = vmalloc(priv->base.contexts * sizeof(u32));
+	priv->suspend = vmalloc(drm->chan.nr * sizeof(u32));
 	if (priv->suspend) {
-		for (i = 0; i < priv->base.contexts; i++)
+		for (i = 0; i < drm->chan.nr; i++)
 			priv->suspend[i] = nouveau_bo_rd32(priv->bo, i*4);
 	}
 
@@ -157,7 +157,7 @@ nv84_fence_resume(struct nouveau_drm *drm)
 	int i;
 
 	if (priv->suspend) {
-		for (i = 0; i < priv->base.contexts; i++)
+		for (i = 0; i < drm->chan.nr; i++)
 			nouveau_bo_wr32(priv->bo, i*4, priv->suspend[i]);
 		vfree(priv->suspend);
 		priv->suspend = NULL;
@@ -179,7 +179,6 @@ nv84_fence_destroy(struct nouveau_drm *drm)
 int
 nv84_fence_create(struct nouveau_drm *drm)
 {
-	struct nvkm_fifo *fifo = nvxx_fifo(&drm->client.device);
 	struct nv84_fence_priv *priv;
 	u32 domain;
 	int ret;
@@ -194,8 +193,6 @@ nv84_fence_create(struct nouveau_drm *drm)
 	priv->base.context_new = nv84_fence_context_new;
 	priv->base.context_del = nv84_fence_context_del;
 
-	priv->base.contexts = fifo->nr;
-	priv->base.context_base = dma_fence_context_alloc(priv->base.contexts);
 	priv->base.uevent = true;
 
 	mutex_init(&priv->mutex);
@@ -207,7 +204,7 @@ nv84_fence_create(struct nouveau_drm *drm)
 			  * will lose CPU/GPU coherency!
 			  */
 			 TTM_PL_FLAG_TT | TTM_PL_FLAG_UNCACHED;
-	ret = nouveau_bo_new(&drm->client, 16 * priv->base.contexts, 0,
+	ret = nouveau_bo_new(&drm->client, 16 * drm->chan.nr, 0,
 			     domain, 0, 0, NULL, NULL, &priv->bo);
 	if (ret == 0) {
 		ret = nouveau_bo_pin(priv->bo, domain, false);
diff --git a/drivers/gpu/drm/nouveau/nvif/Kbuild b/drivers/gpu/drm/nouveau/nvif/Kbuild
index f1675a4ab6fa..42e8c85caa33 100644
--- a/drivers/gpu/drm/nouveau/nvif/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvif/Kbuild
@@ -1,8 +1,14 @@
 nvif-y := nvif/object.o
 nvif-y += nvif/client.o
 nvif-y += nvif/device.o
+nvif-y += nvif/disp.o
 nvif-y += nvif/driver.o
+nvif-y += nvif/fifo.o
 nvif-y += nvif/mem.o
 nvif-y += nvif/mmu.o
 nvif-y += nvif/notify.o
 nvif-y += nvif/vmm.o
+
+# Usermode classes
+nvif-y += nvif/user.o
+nvif-y += nvif/userc361.o
diff --git a/drivers/gpu/drm/nouveau/nvif/device.c b/drivers/gpu/drm/nouveau/nvif/device.c
index 252d8c33215b..1ec101ba3b42 100644
--- a/drivers/gpu/drm/nouveau/nvif/device.c
+++ b/drivers/gpu/drm/nouveau/nvif/device.c
@@ -37,6 +37,9 @@ nvif_device_time(struct nvif_device *device)
 void
 nvif_device_fini(struct nvif_device *device)
 {
+	nvif_user_fini(device);
+	kfree(device->runlist);
+	device->runlist = NULL;
 	nvif_object_fini(&device->object);
 }
 
@@ -46,6 +49,8 @@ nvif_device_init(struct nvif_object *parent, u32 handle, s32 oclass,
 {
 	int ret = nvif_object_init(parent, handle, oclass, data, size,
 				   &device->object);
+	device->runlist = NULL;
+	device->user.func = NULL;
 	if (ret == 0) {
 		device->info.version = 0;
 		ret = nvif_object_mthd(&device->object, NV_DEVICE_V0_INFO,
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_soc15.h b/drivers/gpu/drm/nouveau/nvif/disp.c
index 214f370c5efd..18c7d064f75c 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_soc15.h
+++ b/drivers/gpu/drm/nouveau/nvif/disp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2016 Advanced Micro Devices, Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,35 +18,43 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
  */
-#ifndef PP_SOC15_H
-#define PP_SOC15_H
+#include <nvif/disp.h>
+#include <nvif/device.h>
 
-#include "soc15_hw_ip.h"
-#include "vega10_ip_offset.h"
+#include <nvif/class.h>
 
-inline static uint32_t soc15_get_register_offset(
-		uint32_t hw_id,
-		uint32_t inst,
-		uint32_t segment,
-		uint32_t offset)
+void
+nvif_disp_dtor(struct nvif_disp *disp)
 {
-	uint32_t reg = 0;
-
-	if (hw_id == THM_HWID)
-		reg = THM_BASE.instance[inst].segment[segment] + offset;
-	else if (hw_id == NBIF_HWID)
-		reg = NBIF_BASE.instance[inst].segment[segment] + offset;
-	else if (hw_id == MP1_HWID)
-		reg = MP1_BASE.instance[inst].segment[segment] + offset;
-	else if (hw_id == DF_HWID)
-		reg = DF_BASE.instance[inst].segment[segment] + offset;
-	else if (hw_id == GC_HWID)
-		reg = GC_BASE.instance[inst].segment[segment] + offset;
-	else if (hw_id == SMUIO_HWID)
-		reg = SMUIO_BASE.instance[inst].segment[segment] + offset;
-	return reg;
+	nvif_object_fini(&disp->object);
 }
 
-#endif
+int
+nvif_disp_ctor(struct nvif_device *device, s32 oclass, struct nvif_disp *disp)
+{
+	static const struct nvif_mclass disps[] = {
+		{ GV100_DISP, -1 },
+		{ GP102_DISP, -1 },
+		{ GP100_DISP, -1 },
+		{ GM200_DISP, -1 },
+		{ GM107_DISP, -1 },
+		{ GK110_DISP, -1 },
+		{ GK104_DISP, -1 },
+		{ GF110_DISP, -1 },
+		{ GT214_DISP, -1 },
+		{ GT206_DISP, -1 },
+		{ GT200_DISP, -1 },
+		{   G82_DISP, -1 },
+		{  NV50_DISP, -1 },
+		{  NV04_DISP, -1 },
+		{}
+	};
+	int cid = nvif_sclass(&device->object, disps, oclass);
+	disp->object.client = NULL;
+	if (cid < 0)
+		return cid;
+
+	return nvif_object_init(&device->object, 0, disps[cid].oclass,
+				NULL, 0, &disp->object);
+}
diff --git a/drivers/gpu/drm/nouveau/nvif/fifo.c b/drivers/gpu/drm/nouveau/nvif/fifo.c
new file mode 100644
index 000000000000..99d4fd17543c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvif/fifo.c
@@ -0,0 +1,99 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <nvif/fifo.h>
+
+static int
+nvif_fifo_runlists(struct nvif_device *device)
+{
+	struct nvif_object *object = &device->object;
+	struct {
+		struct nv_device_info_v1 m;
+		struct {
+			struct nv_device_info_v1_data runlists;
+			struct nv_device_info_v1_data runlist[64];
+		} v;
+	} *a;
+	int ret, i;
+
+	if (device->runlist)
+		return 0;
+
+	if (!(a = kmalloc(sizeof(*a), GFP_KERNEL)))
+		return -ENOMEM;
+	a->m.version = 1;
+	a->m.count = sizeof(a->v) / sizeof(a->v.runlists);
+	a->v.runlists.mthd = NV_DEVICE_FIFO_RUNLISTS;
+	for (i = 0; i < ARRAY_SIZE(a->v.runlist); i++)
+		a->v.runlist[i].mthd = NV_DEVICE_FIFO_RUNLIST_ENGINES(i);
+
+	ret = nvif_object_mthd(object, NV_DEVICE_V0_INFO, a, sizeof(*a));
+	if (ret)
+		goto done;
+
+	device->runlists = fls64(a->v.runlists.data);
+	device->runlist = kzalloc(sizeof(*device->runlist) *
+				  device->runlists, GFP_KERNEL);
+	if (!device->runlist) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	for (i = 0; i < device->runlists; i++) {
+		if (a->v.runlists.data & BIT_ULL(i))
+			device->runlist[i].engines = a->v.runlist[i].data;
+	}
+
+done:
+	kfree(a);
+	return ret;
+}
+
+u64
+nvif_fifo_runlist(struct nvif_device *device, u64 engine)
+{
+	struct nvif_object *object = &device->object;
+	struct {
+		struct nv_device_info_v1 m;
+		struct {
+			struct nv_device_info_v1_data engine;
+		} v;
+	} a = {
+		.m.version = 1,
+		.m.count = sizeof(a.v) / sizeof(a.v.engine),
+		.v.engine.mthd = engine,
+	};
+	u64 runm = 0;
+	int ret, i;
+
+	if ((ret = nvif_fifo_runlists(device)))
+		return runm;
+
+	ret = nvif_object_mthd(object, NV_DEVICE_V0_INFO, &a, sizeof(a));
+	if (ret == 0) {
+		for (i = 0; i < device->runlists; i++) {
+			if (device->runlist[i].engines & a.v.engine.data)
+				runm |= BIT_ULL(i);
+		}
+	}
+
+	return runm;
+}
diff --git a/drivers/gpu/drm/nouveau/nvif/mem.c b/drivers/gpu/drm/nouveau/nvif/mem.c
index 0f9382c60145..b6ebb3b58673 100644
--- a/drivers/gpu/drm/nouveau/nvif/mem.c
+++ b/drivers/gpu/drm/nouveau/nvif/mem.c
@@ -24,6 +24,19 @@
 
 #include <nvif/if000a.h>
 
+int
+nvif_mem_init_map(struct nvif_mmu *mmu, u8 type, u64 size, struct nvif_mem *mem)
+{
+	int ret = nvif_mem_init(mmu, mmu->mem, NVIF_MEM_MAPPABLE | type, 0,
+				size, NULL, 0, mem);
+	if (ret == 0) {
+		ret = nvif_object_map(&mem->object, NULL, 0);
+		if (ret)
+			nvif_mem_fini(mem);
+	}
+	return ret;
+}
+
 void
 nvif_mem_fini(struct nvif_mem *mem)
 {
diff --git a/drivers/gpu/drm/nouveau/nvif/mmu.c b/drivers/gpu/drm/nouveau/nvif/mmu.c
index 15d0dcbf7ab4..358ac4f3cf91 100644
--- a/drivers/gpu/drm/nouveau/nvif/mmu.c
+++ b/drivers/gpu/drm/nouveau/nvif/mmu.c
@@ -36,6 +36,12 @@ nvif_mmu_fini(struct nvif_mmu *mmu)
 int
 nvif_mmu_init(struct nvif_object *parent, s32 oclass, struct nvif_mmu *mmu)
 {
+	static const struct nvif_mclass mems[] = {
+		{ NVIF_CLASS_MEM_GF100, -1 },
+		{ NVIF_CLASS_MEM_NV50 , -1 },
+		{ NVIF_CLASS_MEM_NV04 , -1 },
+		{}
+	};
 	struct nvif_mmu_v0 args;
 	int ret, i;
 
@@ -54,6 +60,11 @@ nvif_mmu_init(struct nvif_object *parent, s32 oclass, struct nvif_mmu *mmu)
 	mmu->type_nr = args.type_nr;
 	mmu->kind_nr = args.kind_nr;
 
+	ret = nvif_mclass(&mmu->object, mems);
+	if (ret < 0)
+		goto done;
+	mmu->mem = mems[ret].oclass;
+
 	mmu->heap = kmalloc(sizeof(*mmu->heap) * mmu->heap_nr, GFP_KERNEL);
 	mmu->type = kmalloc(sizeof(*mmu->type) * mmu->type_nr, GFP_KERNEL);
 	if (ret = -ENOMEM, !mmu->heap || !mmu->type)
diff --git a/drivers/gpu/drm/nouveau/nvif/user.c b/drivers/gpu/drm/nouveau/nvif/user.c
new file mode 100644
index 000000000000..10da3cdca647
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvif/user.c
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <nvif/user.h>
+#include <nvif/device.h>
+
+#include <nvif/class.h>
+
+void
+nvif_user_fini(struct nvif_device *device)
+{
+	if (device->user.func) {
+		nvif_object_fini(&device->user.object);
+		device->user.func = NULL;
+	}
+}
+
+int
+nvif_user_init(struct nvif_device *device)
+{
+	struct {
+		s32 oclass;
+		int version;
+		const struct nvif_user_func *func;
+	} users[] = {
+		{ VOLTA_USERMODE_A, -1, &nvif_userc361 },
+		{}
+	};
+	int cid, ret;
+
+	if (device->user.func)
+		return 0;
+
+	cid = nvif_mclass(&device->object, users);
+	if (cid < 0)
+		return cid;
+
+	ret = nvif_object_init(&device->object, 0, users[cid].oclass, NULL, 0,
+			       &device->user.object);
+	if (ret)
+		return ret;
+
+	nvif_object_map(&device->user.object, NULL, 0);
+	device->user.func = users[cid].func;
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogp100.c b/drivers/gpu/drm/nouveau/nvif/userc361.c
index 1530a9217aea..19f9958e7e01 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogp100.c
+++ b/drivers/gpu/drm/nouveau/nvif/userc361.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2016 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,17 +18,16 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs
  */
-#include "changk104.h"
+#include <nvif/user.h>
 
-#include <nvif/class.h>
+static void
+nvif_userc361_doorbell(struct nvif_user *user, u32 token)
+{
+	nvif_wr32(&user->object, 0x90, token);
+}
 
-const struct nvkm_fifo_chan_oclass
-gp100_fifo_gpfifo_oclass = {
-	.base.oclass = PASCAL_CHANNEL_GPFIFO_A,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = gk104_fifo_gpfifo_new,
+const struct nvif_user_func
+nvif_userc361 = {
+	.doorbell = nvif_userc361_doorbell,
 };
diff --git a/drivers/gpu/drm/nouveau/nvif/vmm.c b/drivers/gpu/drm/nouveau/nvif/vmm.c
index 31cdb2d2e1ff..191832be6c65 100644
--- a/drivers/gpu/drm/nouveau/nvif/vmm.c
+++ b/drivers/gpu/drm/nouveau/nvif/vmm.c
@@ -37,7 +37,7 @@ nvif_vmm_map(struct nvif_vmm *vmm, u64 addr, u64 size, void *argv, u32 argc,
 	     struct nvif_mem *mem, u64 offset)
 {
 	struct nvif_vmm_map_v0 *args;
-	u8 stack[16];
+	u8 stack[48];
 	int ret;
 
 	if (sizeof(*args) + argc > sizeof(stack)) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/engine.c b/drivers/gpu/drm/nouveau/nvkm/core/engine.c
index 657231c3c098..d0322ce85172 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/engine.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/engine.c
@@ -83,6 +83,20 @@ nvkm_engine_intr(struct nvkm_subdev *subdev)
 }
 
 static int
+nvkm_engine_info(struct nvkm_subdev *subdev, u64 mthd, u64 *data)
+{
+	struct nvkm_engine *engine = nvkm_engine(subdev);
+	if (engine->func->info) {
+		if ((engine = nvkm_engine_ref(engine))) {
+			int ret = engine->func->info(engine, mthd, data);
+			nvkm_engine_unref(&engine);
+			return ret;
+		}
+	}
+	return -ENOSYS;
+}
+
+static int
 nvkm_engine_fini(struct nvkm_subdev *subdev, bool suspend)
 {
 	struct nvkm_engine *engine = nvkm_engine(subdev);
@@ -150,6 +164,7 @@ nvkm_engine_func = {
 	.preinit = nvkm_engine_preinit,
 	.init = nvkm_engine_init,
 	.fini = nvkm_engine_fini,
+	.info = nvkm_engine_info,
 	.intr = nvkm_engine_intr,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
index a134d225f958..03f676c18aad 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
@@ -35,6 +35,7 @@ nvkm_subdev_name[NVKM_SUBDEV_NR] = {
 	[NVKM_SUBDEV_BUS     ] = "bus",
 	[NVKM_SUBDEV_CLK     ] = "clk",
 	[NVKM_SUBDEV_DEVINIT ] = "devinit",
+	[NVKM_SUBDEV_FAULT   ] = "fault",
 	[NVKM_SUBDEV_FB      ] = "fb",
 	[NVKM_SUBDEV_FUSE    ] = "fuse",
 	[NVKM_SUBDEV_GPIO    ] = "gpio",
@@ -60,6 +61,9 @@ nvkm_subdev_name[NVKM_SUBDEV_NR] = {
 	[NVKM_ENGINE_CE3     ] = "ce3",
 	[NVKM_ENGINE_CE4     ] = "ce4",
 	[NVKM_ENGINE_CE5     ] = "ce5",
+	[NVKM_ENGINE_CE6     ] = "ce6",
+	[NVKM_ENGINE_CE7     ] = "ce7",
+	[NVKM_ENGINE_CE8     ] = "ce8",
 	[NVKM_ENGINE_CIPHER  ] = "cipher",
 	[NVKM_ENGINE_DISP    ] = "disp",
 	[NVKM_ENGINE_DMAOBJ  ] = "dma",
@@ -92,6 +96,14 @@ nvkm_subdev_intr(struct nvkm_subdev *subdev)
 }
 
 int
+nvkm_subdev_info(struct nvkm_subdev *subdev, u64 mthd, u64 *data)
+{
+	if (subdev->func->info)
+		return subdev->func->info(subdev, mthd, data);
+	return -ENOSYS;
+}
+
+int
 nvkm_subdev_fini(struct nvkm_subdev *subdev, bool suspend)
 {
 	struct nvkm_device *device = subdev->device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
index 255d81ccf916..80d784441904 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
@@ -5,3 +5,4 @@ nvkm-y += nvkm/engine/ce/gm107.o
 nvkm-y += nvkm/engine/ce/gm200.o
 nvkm-y += nvkm/engine/ce/gp100.o
 nvkm-y += nvkm/engine/ce/gp102.o
+nvkm-y += nvkm/engine/ce/gv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gv100.c
index fa781b5a7e07..fcda3de45857 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gv100.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,20 +18,23 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "channv50.h"
-#include "rootnv50.h"
+#include "priv.h"
 
 #include <nvif/class.h>
 
-const struct nv50_disp_pioc_oclass
-g84_disp_curs_oclass = {
-	.base.oclass = G82_DISP_CURSOR,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_curs_new,
-	.func = &nv50_disp_pioc_func,
-	.chid = { 7, 7 },
+static const struct nvkm_engine_func
+gv100_ce = {
+	.intr = gp100_ce_intr,
+	.sclass = {
+		{ -1, -1, VOLTA_DMA_COPY_A },
+		{}
+	}
 };
+
+int
+gv100_ce_new(struct nvkm_device *device, int index,
+	     struct nvkm_engine **pengine)
+{
+	return nvkm_engine_new_(&gv100_ce, device, index, true, pengine);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 05cd674326a6..e294013426ce 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2161,6 +2161,7 @@ nv130_chipset = {
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
 	.devinit = gm200_devinit_new,
+	.fault = gp100_fault_new,
 	.fb = gp100_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
@@ -2196,13 +2197,14 @@ nv132_chipset = {
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
 	.devinit = gm200_devinit_new,
+	.fault = gp100_fault_new,
 	.fb = gp102_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gm200_i2c_new,
 	.ibus = gm200_ibus_new,
 	.imem = nv50_instmem_new,
-	.ltc = gp100_ltc_new,
+	.ltc = gp102_ltc_new,
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
@@ -2231,13 +2233,14 @@ nv134_chipset = {
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
 	.devinit = gm200_devinit_new,
+	.fault = gp100_fault_new,
 	.fb = gp102_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gm200_i2c_new,
 	.ibus = gm200_ibus_new,
 	.imem = nv50_instmem_new,
-	.ltc = gp100_ltc_new,
+	.ltc = gp102_ltc_new,
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
@@ -2253,7 +2256,7 @@ nv134_chipset = {
 	.disp = gp102_disp_new,
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
-	.gr = gp102_gr_new,
+	.gr = gp104_gr_new,
 	.nvdec = gp102_nvdec_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
@@ -2266,13 +2269,14 @@ nv136_chipset = {
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
 	.devinit = gm200_devinit_new,
+	.fault = gp100_fault_new,
 	.fb = gp102_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gm200_i2c_new,
 	.ibus = gm200_ibus_new,
 	.imem = nv50_instmem_new,
-	.ltc = gp100_ltc_new,
+	.ltc = gp102_ltc_new,
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
@@ -2288,7 +2292,7 @@ nv136_chipset = {
 	.disp = gp102_disp_new,
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
-	.gr = gp102_gr_new,
+	.gr = gp104_gr_new,
 	.nvdec = gp102_nvdec_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
@@ -2301,13 +2305,14 @@ nv137_chipset = {
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
 	.devinit = gm200_devinit_new,
+	.fault = gp100_fault_new,
 	.fb = gp102_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gm200_i2c_new,
 	.ibus = gm200_ibus_new,
 	.imem = nv50_instmem_new,
-	.ltc = gp100_ltc_new,
+	.ltc = gp102_ltc_new,
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
@@ -2336,13 +2341,14 @@ nv138_chipset = {
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
 	.devinit = gm200_devinit_new,
+	.fault = gp100_fault_new,
 	.fb = gp102_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gm200_i2c_new,
 	.ibus = gm200_ibus_new,
 	.imem = nv50_instmem_new,
-	.ltc = gp100_ltc_new,
+	.ltc = gp102_ltc_new,
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
@@ -2369,11 +2375,12 @@ nv13b_chipset = {
 	.name = "GP10B",
 	.bar = gm20b_bar_new,
 	.bus = gf100_bus_new,
+	.fault = gp100_fault_new,
 	.fb = gp10b_fb_new,
 	.fuse = gm107_fuse_new,
 	.ibus = gp10b_ibus_new,
 	.imem = gk20a_instmem_new,
-	.ltc = gp100_ltc_new,
+	.ltc = gp102_ltc_new,
 	.mc = gp10b_mc_new,
 	.mmu = gp10b_mmu_new,
 	.secboot = gp10b_secboot_new,
@@ -2387,6 +2394,46 @@ nv13b_chipset = {
 	.sw = gf100_sw_new,
 };
 
+static const struct nvkm_device_chip
+nv140_chipset = {
+	.name = "GV100",
+	.bar = gm107_bar_new,
+	.bios = nvkm_bios_new,
+	.bus = gf100_bus_new,
+	.devinit = gv100_devinit_new,
+	.fault = gv100_fault_new,
+	.fb = gv100_fb_new,
+	.fuse = gm107_fuse_new,
+	.gpio = gk104_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.ltc = gp102_ltc_new,
+	.mc = gp100_mc_new,
+	.mmu = gv100_mmu_new,
+	.pci = gp100_pci_new,
+	.pmu = gp102_pmu_new,
+	.secboot = gp108_secboot_new,
+	.therm = gp100_therm_new,
+	.timer = gk20a_timer_new,
+	.top = gk104_top_new,
+	.disp = gv100_disp_new,
+	.ce[0] = gv100_ce_new,
+	.ce[1] = gv100_ce_new,
+	.ce[2] = gv100_ce_new,
+	.ce[3] = gv100_ce_new,
+	.ce[4] = gv100_ce_new,
+	.ce[5] = gv100_ce_new,
+	.ce[6] = gv100_ce_new,
+	.ce[7] = gv100_ce_new,
+	.ce[8] = gv100_ce_new,
+	.dma = gv100_dma_new,
+	.fifo = gv100_fifo_new,
+	.gr = gv100_gr_new,
+	.nvdec = gp102_nvdec_new,
+	.sec2 = gp102_sec2_new,
+};
+
 static int
 nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
 		       struct nvkm_notify *notify)
@@ -2420,6 +2467,7 @@ nvkm_device_subdev(struct nvkm_device *device, int index)
 	_(BUS     , device->bus     , &device->bus->subdev);
 	_(CLK     , device->clk     , &device->clk->subdev);
 	_(DEVINIT , device->devinit , &device->devinit->subdev);
+	_(FAULT   , device->fault   , &device->fault->subdev);
 	_(FB      , device->fb      , &device->fb->subdev);
 	_(FUSE    , device->fuse    , &device->fuse->subdev);
 	_(GPIO    , device->gpio    , &device->gpio->subdev);
@@ -2463,6 +2511,9 @@ nvkm_device_engine(struct nvkm_device *device, int index)
 	_(CE3    , device->ce[3]   ,  device->ce[3]);
 	_(CE4    , device->ce[4]   ,  device->ce[4]);
 	_(CE5    , device->ce[5]   ,  device->ce[5]);
+	_(CE6    , device->ce[6]   ,  device->ce[6]);
+	_(CE7    , device->ce[7]   ,  device->ce[7]);
+	_(CE8    , device->ce[8]   ,  device->ce[8]);
 	_(CIPHER , device->cipher  ,  device->cipher);
 	_(DISP   , device->disp    , &device->disp->engine);
 	_(DMAOBJ , device->dma     , &device->dma->engine);
@@ -2739,6 +2790,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 			case 0x110:
 			case 0x120: device->card_type = GM100; break;
 			case 0x130: device->card_type = GP100; break;
+			case 0x140: device->card_type = GV100; break;
 			default:
 				break;
 			}
@@ -2830,6 +2882,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x137: device->chip = &nv137_chipset; break;
 		case 0x138: device->chip = &nv138_chipset; break;
 		case 0x13b: device->chip = &nv13b_chipset; break;
+		case 0x140: device->chip = &nv140_chipset; break;
 		default:
 			nvdev_error(device, "unknown chipset (%08x)\n", boot0);
 			goto done;
@@ -2891,6 +2944,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		_(NVKM_SUBDEV_BUS     ,      bus);
 		_(NVKM_SUBDEV_CLK     ,      clk);
 		_(NVKM_SUBDEV_DEVINIT ,  devinit);
+		_(NVKM_SUBDEV_FAULT   ,    fault);
 		_(NVKM_SUBDEV_FB      ,       fb);
 		_(NVKM_SUBDEV_FUSE    ,     fuse);
 		_(NVKM_SUBDEV_GPIO    ,     gpio);
@@ -2916,6 +2970,9 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		_(NVKM_ENGINE_CE3     ,    ce[3]);
 		_(NVKM_ENGINE_CE4     ,    ce[4]);
 		_(NVKM_ENGINE_CE5     ,    ce[5]);
+		_(NVKM_ENGINE_CE6     ,    ce[6]);
+		_(NVKM_ENGINE_CE7     ,    ce[7]);
+		_(NVKM_ENGINE_CE8     ,    ce[8]);
 		_(NVKM_ENGINE_CIPHER  ,   cipher);
 		_(NVKM_ENGINE_DISP    ,     disp);
 		_(NVKM_ENGINE_DMAOBJ  ,      dma);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
index 08d0bf605722..253ab914a8ef 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
@@ -8,6 +8,7 @@
 #include <subdev/bus.h>
 #include <subdev/clk.h>
 #include <subdev/devinit.h>
+#include <subdev/fault.h>
 #include <subdev/fb.h>
 #include <subdev/fuse.h>
 #include <subdev/gpio.h>
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
index 17adcb4e8854..dde6bbafa709 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
@@ -40,6 +40,66 @@ struct nvkm_udevice {
 };
 
 static int
+nvkm_udevice_info_subdev(struct nvkm_device *device, u64 mthd, u64 *data)
+{
+	struct nvkm_subdev *subdev;
+	enum nvkm_devidx subidx;
+
+	switch (mthd & NV_DEVICE_INFO_UNIT) {
+	case NV_DEVICE_FIFO(0): subidx = NVKM_ENGINE_FIFO; break;
+	default:
+		return -EINVAL;
+	}
+
+	subdev = nvkm_device_subdev(device, subidx);
+	if (subdev)
+		return nvkm_subdev_info(subdev, mthd, data);
+	return -ENODEV;
+}
+
+static void
+nvkm_udevice_info_v1(struct nvkm_device *device,
+		     struct nv_device_info_v1_data *args)
+{
+	if (args->mthd & NV_DEVICE_INFO_UNIT) {
+		if (nvkm_udevice_info_subdev(device, args->mthd, &args->data))
+			args->mthd = NV_DEVICE_INFO_INVALID;
+		return;
+	}
+
+	switch (args->mthd) {
+#define ENGINE__(A,B,C) NV_DEVICE_INFO_ENGINE_##A: { int _i;                   \
+	for (_i = (B), args->data = 0ULL; _i <= (C); _i++) {                   \
+		if (nvkm_device_engine(device, _i))                            \
+			args->data |= BIT_ULL(_i);                             \
+	}                                                                      \
+}
+#define ENGINE_A(A) ENGINE__(A, NVKM_ENGINE_##A   , NVKM_ENGINE_##A)
+#define ENGINE_B(A) ENGINE__(A, NVKM_ENGINE_##A##0, NVKM_ENGINE_##A##_LAST)
+	case ENGINE_A(SW    ); break;
+	case ENGINE_A(GR    ); break;
+	case ENGINE_A(MPEG  ); break;
+	case ENGINE_A(ME    ); break;
+	case ENGINE_A(CIPHER); break;
+	case ENGINE_A(BSP   ); break;
+	case ENGINE_A(VP    ); break;
+	case ENGINE_B(CE    ); break;
+	case ENGINE_A(SEC   ); break;
+	case ENGINE_A(MSVLD ); break;
+	case ENGINE_A(MSPDEC); break;
+	case ENGINE_A(MSPPP ); break;
+	case ENGINE_A(MSENC ); break;
+	case ENGINE_A(VIC   ); break;
+	case ENGINE_A(SEC2  ); break;
+	case ENGINE_A(NVDEC ); break;
+	case ENGINE_B(NVENC ); break;
+	default:
+		args->mthd = NV_DEVICE_INFO_INVALID;
+		break;
+	}
+}
+
+static int
 nvkm_udevice_info(struct nvkm_udevice *udev, void *data, u32 size)
 {
 	struct nvkm_object *object = &udev->object;
@@ -48,10 +108,21 @@ nvkm_udevice_info(struct nvkm_udevice *udev, void *data, u32 size)
 	struct nvkm_instmem *imem = device->imem;
 	union {
 		struct nv_device_info_v0 v0;
+		struct nv_device_info_v1 v1;
 	} *args = data;
-	int ret = -ENOSYS;
+	int ret = -ENOSYS, i;
 
 	nvif_ioctl(object, "device info size %d\n", size);
+	if (!(ret = nvif_unpack(ret, &data, &size, args->v1, 1, 1, true))) {
+		nvif_ioctl(object, "device info vers %d count %d\n",
+			   args->v1.version, args->v1.count);
+		if (args->v1.count * sizeof(args->v1.data[0]) == size) {
+			for (i = 0; i < args->v1.count; i++)
+				nvkm_udevice_info_v1(device, &args->v1.data[i]);
+			return 0;
+		}
+		return -EINVAL;
+	} else
 	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
 		nvif_ioctl(object, "device info vers %d\n", args->v0.version);
 	} else
@@ -103,6 +174,7 @@ nvkm_udevice_info(struct nvkm_udevice *udev, void *data, u32 size)
 	case NV_E0: args->v0.family = NV_DEVICE_INFO_V0_KEPLER; break;
 	case GM100: args->v0.family = NV_DEVICE_INFO_V0_MAXWELL; break;
 	case GP100: args->v0.family = NV_DEVICE_INFO_V0_PASCAL; break;
+	case GV100: args->v0.family = NV_DEVICE_INFO_V0_VOLTA; break;
 	default:
 		args->v0.family = 0;
 		break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index 48ce6699183e..3d485dbf310a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -14,12 +14,14 @@ nvkm-y += nvkm/engine/disp/gm107.o
 nvkm-y += nvkm/engine/disp/gm200.o
 nvkm-y += nvkm/engine/disp/gp100.o
 nvkm-y += nvkm/engine/disp/gp102.o
+nvkm-y += nvkm/engine/disp/gv100.o
 nvkm-y += nvkm/engine/disp/vga.o
 
 nvkm-y += nvkm/engine/disp/head.o
 nvkm-y += nvkm/engine/disp/headnv04.o
 nvkm-y += nvkm/engine/disp/headnv50.o
 nvkm-y += nvkm/engine/disp/headgf119.o
+nvkm-y += nvkm/engine/disp/headgv100.o
 
 nvkm-y += nvkm/engine/disp/ior.o
 nvkm-y += nvkm/engine/disp/dacnv50.o
@@ -35,6 +37,7 @@ nvkm-y += nvkm/engine/disp/sorgf119.o
 nvkm-y += nvkm/engine/disp/sorgk104.o
 nvkm-y += nvkm/engine/disp/sorgm107.o
 nvkm-y += nvkm/engine/disp/sorgm200.o
+nvkm-y += nvkm/engine/disp/sorgv100.o
 
 nvkm-y += nvkm/engine/disp/outp.o
 nvkm-y += nvkm/engine/disp/dp.o
@@ -47,6 +50,7 @@ nvkm-y += nvkm/engine/disp/hdmig84.o
 nvkm-y += nvkm/engine/disp/hdmigt215.o
 nvkm-y += nvkm/engine/disp/hdmigf119.o
 nvkm-y += nvkm/engine/disp/hdmigk104.o
+nvkm-y += nvkm/engine/disp/hdmigv100.o
 
 nvkm-y += nvkm/engine/disp/conn.o
 
@@ -63,57 +67,49 @@ nvkm-y += nvkm/engine/disp/rootgm107.o
 nvkm-y += nvkm/engine/disp/rootgm200.o
 nvkm-y += nvkm/engine/disp/rootgp100.o
 nvkm-y += nvkm/engine/disp/rootgp102.o
+nvkm-y += nvkm/engine/disp/rootgv100.o
 
 nvkm-y += nvkm/engine/disp/channv50.o
 nvkm-y += nvkm/engine/disp/changf119.o
+nvkm-y += nvkm/engine/disp/changv100.o
 
 nvkm-y += nvkm/engine/disp/dmacnv50.o
 nvkm-y += nvkm/engine/disp/dmacgf119.o
 nvkm-y += nvkm/engine/disp/dmacgp102.o
+nvkm-y += nvkm/engine/disp/dmacgv100.o
 
 nvkm-y += nvkm/engine/disp/basenv50.o
 nvkm-y += nvkm/engine/disp/baseg84.o
-nvkm-y += nvkm/engine/disp/basegt200.o
-nvkm-y += nvkm/engine/disp/basegt215.o
 nvkm-y += nvkm/engine/disp/basegf119.o
-nvkm-y += nvkm/engine/disp/basegk104.o
-nvkm-y += nvkm/engine/disp/basegk110.o
 nvkm-y += nvkm/engine/disp/basegp102.o
 
 nvkm-y += nvkm/engine/disp/corenv50.o
 nvkm-y += nvkm/engine/disp/coreg84.o
 nvkm-y += nvkm/engine/disp/coreg94.o
-nvkm-y += nvkm/engine/disp/coregt200.o
-nvkm-y += nvkm/engine/disp/coregt215.o
 nvkm-y += nvkm/engine/disp/coregf119.o
 nvkm-y += nvkm/engine/disp/coregk104.o
-nvkm-y += nvkm/engine/disp/coregk110.o
-nvkm-y += nvkm/engine/disp/coregm107.o
-nvkm-y += nvkm/engine/disp/coregm200.o
-nvkm-y += nvkm/engine/disp/coregp100.o
 nvkm-y += nvkm/engine/disp/coregp102.o
+nvkm-y += nvkm/engine/disp/coregv100.o
 
 nvkm-y += nvkm/engine/disp/ovlynv50.o
 nvkm-y += nvkm/engine/disp/ovlyg84.o
 nvkm-y += nvkm/engine/disp/ovlygt200.o
-nvkm-y += nvkm/engine/disp/ovlygt215.o
 nvkm-y += nvkm/engine/disp/ovlygf119.o
 nvkm-y += nvkm/engine/disp/ovlygk104.o
 nvkm-y += nvkm/engine/disp/ovlygp102.o
 
+nvkm-y += nvkm/engine/disp/wimmgv100.o
+
+nvkm-y += nvkm/engine/disp/wndwgv100.o
+
 nvkm-y += nvkm/engine/disp/piocnv50.o
 nvkm-y += nvkm/engine/disp/piocgf119.o
 
 nvkm-y += nvkm/engine/disp/cursnv50.o
-nvkm-y += nvkm/engine/disp/cursg84.o
-nvkm-y += nvkm/engine/disp/cursgt215.o
 nvkm-y += nvkm/engine/disp/cursgf119.o
-nvkm-y += nvkm/engine/disp/cursgk104.o
 nvkm-y += nvkm/engine/disp/cursgp102.o
+nvkm-y += nvkm/engine/disp/cursgv100.o
 
 nvkm-y += nvkm/engine/disp/oimmnv50.o
-nvkm-y += nvkm/engine/disp/oimmg84.o
-nvkm-y += nvkm/engine/disp/oimmgt215.o
 nvkm-y += nvkm/engine/disp/oimmgf119.o
-nvkm-y += nvkm/engine/disp/oimmgk104.o
 nvkm-y += nvkm/engine/disp/oimmgp102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
index 93a75e5b2791..32fa94a9773f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c
@@ -220,6 +220,9 @@ nvkm_disp_fini(struct nvkm_engine *engine, bool suspend)
 	struct nvkm_conn *conn;
 	struct nvkm_outp *outp;
 
+	if (disp->func->fini)
+		disp->func->fini(disp);
+
 	list_for_each_entry(outp, &disp->outp, head) {
 		nvkm_outp_fini(outp);
 	}
@@ -237,6 +240,7 @@ nvkm_disp_init(struct nvkm_engine *engine)
 	struct nvkm_disp *disp = nvkm_disp(engine);
 	struct nvkm_conn *conn;
 	struct nvkm_outp *outp;
+	struct nvkm_ior *ior;
 
 	list_for_each_entry(conn, &disp->conn, head) {
 		nvkm_conn_init(conn);
@@ -246,6 +250,19 @@ nvkm_disp_init(struct nvkm_engine *engine)
 		nvkm_outp_init(outp);
 	}
 
+	if (disp->func->init) {
+		int ret = disp->func->init(disp);
+		if (ret)
+			return ret;
+	}
+
+	/* Set 'normal' (ie. when it's attached to a head) state for
+	 * each output resource to 'fully enabled'.
+	 */
+	list_for_each_entry(ior, &disp->ior, head) {
+		ior->func->power(ior, true, true, true, true, true);
+	}
+
 	return 0;
 }
 
@@ -376,6 +393,12 @@ nvkm_disp_oneinit(struct nvkm_engine *engine)
 	if (ret)
 		return ret;
 
+	if (disp->func->oneinit) {
+		ret = disp->func->oneinit(disp);
+		if (ret)
+			return ret;
+	}
+
 	i = 0;
 	list_for_each_entry(head, &disp->head, head)
 		i = max(i, head->id + 1);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/baseg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/baseg84.c
index 6d17630a3dee..01253f4a9946 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/baseg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/baseg84.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 static const struct nv50_disp_mthd_list
 g84_disp_base_mthd_base = {
@@ -56,8 +53,8 @@ g84_disp_base_mthd_base = {
 	}
 };
 
-const struct nv50_disp_chan_mthd
-g84_disp_base_chan_mthd = {
+static const struct nv50_disp_chan_mthd
+g84_disp_base_mthd = {
 	.name = "Base",
 	.addr = 0x000540,
 	.prev = 0x000004,
@@ -68,13 +65,10 @@ g84_disp_base_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-g84_disp_base_oclass = {
-	.base.oclass = G82_DISP_BASE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_base_new,
-	.func = &nv50_disp_dmac_func,
-	.mthd = &g84_disp_base_chan_mthd,
-	.chid = 1,
-};
+int
+g84_disp_base_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		  struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_base_new_(&nv50_disp_dmac_func, &g84_disp_base_mthd,
+				   disp, 1, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegf119.c
index ebcb925e9d90..389e19dfc514 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegf119.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 static const struct nv50_disp_mthd_list
 gf119_disp_base_mthd_base = {
@@ -91,7 +88,7 @@ gf119_disp_base_mthd_image = {
 };
 
 const struct nv50_disp_chan_mthd
-gf119_disp_base_chan_mthd = {
+gf119_disp_base_mthd = {
 	.name = "Base",
 	.addr = 0x001000,
 	.prev = -0x020000,
@@ -102,13 +99,10 @@ gf119_disp_base_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-gf119_disp_base_oclass = {
-	.base.oclass = GF110_DISP_BASE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_base_new,
-	.func = &gf119_disp_dmac_func,
-	.mthd = &gf119_disp_base_chan_mthd,
-	.chid = 1,
-};
+int
+gf119_disp_base_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_base_new_(&gf119_disp_dmac_func, &gf119_disp_base_mthd,
+				   disp, 1, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegp102.c
index 8a3cdeef8d2c..0cb23d673aa0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegp102.c
@@ -21,18 +21,12 @@
  *
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "channv50.h"
 
-#include <nvif/class.h>
-
-const struct nv50_disp_dmac_oclass
-gp102_disp_base_oclass = {
-	.base.oclass = GK110_DISP_BASE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_base_new,
-	.func = &gp102_disp_dmac_func,
-	.mthd = &gf119_disp_base_chan_mthd,
-	.chid = 1,
-};
+int
+gp102_disp_base_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_base_new_(&gp102_disp_dmac_func, &gf119_disp_base_mthd,
+				   disp, 1, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basenv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/basenv50.c
index f1d6b820d482..19eb7dde01f2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basenv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/basenv50.c
@@ -21,33 +21,30 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
+#include "channv50.h"
 #include "head.h"
-#include "rootnv50.h"
 
 #include <core/client.h>
 
-#include <nvif/class.h>
 #include <nvif/cl507c.h>
 #include <nvif/unpack.h>
 
 int
-nv50_disp_base_new(const struct nv50_disp_dmac_func *func,
-		   const struct nv50_disp_chan_mthd *mthd,
-		   struct nv50_disp_root *root, int chid,
-		   const struct nvkm_oclass *oclass, void *data, u32 size,
-		   struct nvkm_object **pobject)
+nv50_disp_base_new_(const struct nv50_disp_chan_func *func,
+		    const struct nv50_disp_chan_mthd *mthd,
+		    struct nv50_disp *disp, int chid,
+		    const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nvkm_object **pobject)
 {
 	union {
 		struct nv50_disp_base_channel_dma_v0 v0;
-	} *args = data;
+	} *args = argv;
 	struct nvkm_object *parent = oclass->parent;
-	struct nv50_disp *disp = root->disp;
 	int head, ret = -ENOSYS;
 	u64 push;
 
-	nvif_ioctl(parent, "create disp base channel dma size %d\n", size);
-	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
+	nvif_ioctl(parent, "create disp base channel dma size %d\n", argc);
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
 		nvif_ioctl(parent, "create disp base channel dma vers %d "
 				   "pushbuf %016llx head %d\n",
 			   args->v0.version, args->v0.pushbuf, args->v0.head);
@@ -58,7 +55,7 @@ nv50_disp_base_new(const struct nv50_disp_dmac_func *func,
 	} else
 		return ret;
 
-	return nv50_disp_dmac_new_(func, mthd, root, chid + head,
+	return nv50_disp_dmac_new_(func, mthd, disp, chid + head,
 				   head, push, oclass, pobject);
 }
 
@@ -102,7 +99,7 @@ nv50_disp_base_mthd_image = {
 };
 
 static const struct nv50_disp_chan_mthd
-nv50_disp_base_chan_mthd = {
+nv50_disp_base_mthd = {
 	.name = "Base",
 	.addr = 0x000540,
 	.prev = 0x000004,
@@ -113,13 +110,10 @@ nv50_disp_base_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-nv50_disp_base_oclass = {
-	.base.oclass = NV50_DISP_BASE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_base_new,
-	.func = &nv50_disp_dmac_func,
-	.mthd = &nv50_disp_base_chan_mthd,
-	.chid = 1,
-};
+int
+nv50_disp_base_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		   struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_base_new_(&nv50_disp_dmac_func, &nv50_disp_base_mthd,
+				   disp, 1, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
index 17a3d835cb42..29e6dd58ac48 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
@@ -47,3 +47,16 @@ gf119_disp_chan_uevent = {
 	.init = gf119_disp_chan_uevent_init,
 	.fini = gf119_disp_chan_uevent_fini,
 };
+
+void
+gf119_disp_chan_intr(struct nv50_disp_chan *chan, bool en)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u64 mask = 0x00000001 << chan->chid.user;
+	if (!en) {
+		nvkm_mask(device, 0x610090, mask, 0x00000000);
+		nvkm_mask(device, 0x6100a0, mask, 0x00000000);
+	} else {
+		nvkm_mask(device, 0x6100a0, mask, mask);
+	}
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changv100.c
index a13315147391..75247c9c7e10 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changv100.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,17 +18,17 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs
  */
-#include "changk104.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
-const struct nvkm_fifo_chan_oclass
-gm200_fifo_gpfifo_oclass = {
-	.base.oclass = MAXWELL_CHANNEL_GPFIFO_A,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = gk104_fifo_gpfifo_new,
+const struct nvkm_event_func
+gv100_disp_chan_uevent = {
+	.ctor = nv50_disp_chan_uevent_ctor,
 };
+
+u64
+gv100_disp_chan_user(struct nv50_disp_chan *chan, u64 *psize)
+{
+	*psize = 0x1000;
+	return 0x690000 + ((chan->chid.user - 1) * 0x1000);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index 723dcbde2ac2..57719f675eec 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -26,6 +26,7 @@
 
 #include <core/client.h>
 #include <core/notify.h>
+#include <core/oproxy.h>
 #include <core/ramht.h>
 #include <engine/dma.h>
 
@@ -65,7 +66,7 @@ nv50_disp_mthd_list(struct nv50_disp *disp, int debug, u32 base, int c,
 void
 nv50_disp_chan_mthd(struct nv50_disp_chan *chan, int debug)
 {
-	struct nv50_disp *disp = chan->root->disp;
+	struct nv50_disp *disp = chan->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	const struct nv50_disp_chan_mthd *mthd = chan->mthd;
 	const struct nv50_disp_mthd_list *list;
@@ -154,13 +155,29 @@ nv50_disp_chan_uevent = {
 	.fini = nv50_disp_chan_uevent_fini,
 };
 
+u64
+nv50_disp_chan_user(struct nv50_disp_chan *chan, u64 *psize)
+{
+	*psize = 0x1000;
+	return 0x640000 + (chan->chid.user * 0x1000);
+}
+
+void
+nv50_disp_chan_intr(struct nv50_disp_chan *chan, bool en)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u64 mask = 0x00010001 << chan->chid.user;
+	const u64 data = en ? 0x00010000 : 0x00000000;
+	nvkm_mask(device, 0x610028, mask, data);
+}
+
 static int
 nv50_disp_chan_rd32(struct nvkm_object *object, u64 addr, u32 *data)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
-	struct nv50_disp *disp = chan->root->disp;
-	struct nvkm_device *device = disp->base.engine.subdev.device;
-	*data = nvkm_rd32(device, 0x640000 + (chan->chid.user * 0x1000) + addr);
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	u64 size, base = chan->func->user(chan, &size);
+	*data = nvkm_rd32(device, base + addr);
 	return 0;
 }
 
@@ -168,9 +185,9 @@ static int
 nv50_disp_chan_wr32(struct nvkm_object *object, u64 addr, u32 data)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
-	struct nv50_disp *disp = chan->root->disp;
-	struct nvkm_device *device = disp->base.engine.subdev.device;
-	nvkm_wr32(device, 0x640000 + (chan->chid.user * 0x1000) + addr, data);
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	u64 size, base = chan->func->user(chan, &size);
+	nvkm_wr32(device, base + addr, data);
 	return 0;
 }
 
@@ -179,7 +196,7 @@ nv50_disp_chan_ntfy(struct nvkm_object *object, u32 type,
 		    struct nvkm_event **pevent)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
-	struct nv50_disp *disp = chan->root->disp;
+	struct nv50_disp *disp = chan->disp;
 	switch (type) {
 	case NV50_DISP_CORE_CHANNEL_DMA_V0_NTFY_UEVENT:
 		*pevent = &disp->uevent;
@@ -195,34 +212,83 @@ nv50_disp_chan_map(struct nvkm_object *object, void *argv, u32 argc,
 		   enum nvkm_object_map *type, u64 *addr, u64 *size)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
-	struct nv50_disp *disp = chan->root->disp;
-	struct nvkm_device *device = disp->base.engine.subdev.device;
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u64 base = device->func->resource_addr(device, 0);
 	*type = NVKM_OBJECT_MAP_IO;
-	*addr = device->func->resource_addr(device, 0) +
-		0x640000 + (chan->chid.user * 0x1000);
-	*size = 0x001000;
+	*addr = base + chan->func->user(chan, size);
 	return 0;
 }
 
+struct nv50_disp_chan_object {
+	struct nvkm_oproxy oproxy;
+	struct nv50_disp *disp;
+	int hash;
+};
+
+static void
+nv50_disp_chan_child_del_(struct nvkm_oproxy *base)
+{
+	struct nv50_disp_chan_object *object =
+		container_of(base, typeof(*object), oproxy);
+	nvkm_ramht_remove(object->disp->ramht, object->hash);
+}
+
+static const struct nvkm_oproxy_func
+nv50_disp_chan_child_func_ = {
+	.dtor[0] = nv50_disp_chan_child_del_,
+};
+
 static int
 nv50_disp_chan_child_new(const struct nvkm_oclass *oclass,
-			 void *data, u32 size, struct nvkm_object **pobject)
+			 void *argv, u32 argc, struct nvkm_object **pobject)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(oclass->parent);
-	return chan->func->child_new(chan, oclass, data, size, pobject);
+	struct nv50_disp *disp = chan->disp;
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	const struct nvkm_device_oclass *sclass = oclass->priv;
+	struct nv50_disp_chan_object *object;
+	int ret;
+
+	if (!(object = kzalloc(sizeof(*object), GFP_KERNEL)))
+		return -ENOMEM;
+	nvkm_oproxy_ctor(&nv50_disp_chan_child_func_, oclass, &object->oproxy);
+	object->disp = disp;
+	*pobject = &object->oproxy.base;
+
+	ret = sclass->ctor(device, oclass, argv, argc, &object->oproxy.object);
+	if (ret)
+		return ret;
+
+	object->hash = chan->func->bind(chan, object->oproxy.object,
+					      oclass->handle);
+	if (object->hash < 0)
+		return object->hash;
+
+	return 0;
 }
 
 static int
 nv50_disp_chan_child_get(struct nvkm_object *object, int index,
-			 struct nvkm_oclass *oclass)
+			 struct nvkm_oclass *sclass)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
-	if (chan->func->child_get) {
-		int ret = chan->func->child_get(chan, index, oclass);
-		if (ret == 0)
-			oclass->ctor = nv50_disp_chan_child_new;
-		return ret;
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const struct nvkm_device_oclass *oclass = NULL;
+
+	if (chan->func->bind)
+		sclass->engine = nvkm_device_engine(device, NVKM_ENGINE_DMAOBJ);
+	else
+		sclass->engine = NULL;
+
+	if (sclass->engine && sclass->engine->func->base.sclass) {
+		sclass->engine->func->base.sclass(sclass, index, &oclass);
+		if (oclass) {
+			sclass->ctor = nv50_disp_chan_child_new,
+			sclass->priv = oclass;
+			return 0;
+		}
 	}
+
 	return -EINVAL;
 }
 
@@ -231,6 +297,7 @@ nv50_disp_chan_fini(struct nvkm_object *object, bool suspend)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
 	chan->func->fini(chan);
+	chan->func->intr(chan, false);
 	return 0;
 }
 
@@ -238,6 +305,7 @@ static int
 nv50_disp_chan_init(struct nvkm_object *object)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
+	chan->func->intr(chan, true);
 	return chan->func->init(chan);
 }
 
@@ -245,10 +313,11 @@ static void *
 nv50_disp_chan_dtor(struct nvkm_object *object)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
-	struct nv50_disp *disp = chan->root->disp;
+	struct nv50_disp *disp = chan->disp;
 	if (chan->chid.user >= 0)
 		disp->chan[chan->chid.user] = NULL;
-	return chan->func->dtor ? chan->func->dtor(chan) : chan;
+	nvkm_memory_unref(&chan->memory);
+	return chan;
 }
 
 static const struct nvkm_object_func
@@ -264,18 +333,22 @@ nv50_disp_chan = {
 };
 
 int
-nv50_disp_chan_ctor(const struct nv50_disp_chan_func *func,
+nv50_disp_chan_new_(const struct nv50_disp_chan_func *func,
 		    const struct nv50_disp_chan_mthd *mthd,
-		    struct nv50_disp_root *root, int ctrl, int user, int head,
+		    struct nv50_disp *disp, int ctrl, int user, int head,
 		    const struct nvkm_oclass *oclass,
-		    struct nv50_disp_chan *chan)
+		    struct nvkm_object **pobject)
 {
-	struct nv50_disp *disp = root->disp;
+	struct nv50_disp_chan *chan;
+
+	if (!(chan = kzalloc(sizeof(*chan), GFP_KERNEL)))
+		return -ENOMEM;
+	*pobject = &chan->object;
 
 	nvkm_object_ctor(&nv50_disp_chan, oclass, &chan->object);
 	chan->func = func;
 	chan->mthd = mthd;
-	chan->root = root;
+	chan->disp = disp;
 	chan->chid.ctrl = ctrl;
 	chan->chid.user = user;
 	chan->head = head;
@@ -287,20 +360,3 @@ nv50_disp_chan_ctor(const struct nv50_disp_chan_func *func,
 	disp->chan[chan->chid.user] = chan;
 	return 0;
 }
-
-int
-nv50_disp_chan_new_(const struct nv50_disp_chan_func *func,
-		    const struct nv50_disp_chan_mthd *mthd,
-		    struct nv50_disp_root *root, int ctrl, int user, int head,
-		    const struct nvkm_oclass *oclass,
-		    struct nvkm_object **pobject)
-{
-	struct nv50_disp_chan *chan;
-
-	if (!(chan = kzalloc(sizeof(*chan), GFP_KERNEL)))
-		return -ENOMEM;
-	*pobject = &chan->object;
-
-	return nv50_disp_chan_ctor(func, mthd, root, ctrl, user,
-				   head, oclass, chan);
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
index 40681db91a02..adc9d76d09cc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
@@ -4,11 +4,12 @@
 #define nv50_disp_chan(p) container_of((p), struct nv50_disp_chan, object)
 #include <core/object.h>
 #include "nv50.h"
+struct nv50_disp_root;
 
 struct nv50_disp_chan {
 	const struct nv50_disp_chan_func *func;
 	const struct nv50_disp_chan_mthd *mthd;
-	struct nv50_disp_root *root;
+	struct nv50_disp *disp;
 
 	struct {
 		int ctrl;
@@ -17,36 +18,133 @@ struct nv50_disp_chan {
 	int head;
 
 	struct nvkm_object object;
+
+	struct nvkm_memory *memory;
+	u64 push;
 };
 
 struct nv50_disp_chan_func {
-	void *(*dtor)(struct nv50_disp_chan *);
 	int (*init)(struct nv50_disp_chan *);
 	void (*fini)(struct nv50_disp_chan *);
-	int (*child_get)(struct nv50_disp_chan *, int index,
-			 struct nvkm_oclass *);
-	int (*child_new)(struct nv50_disp_chan *, const struct nvkm_oclass *,
-			 void *data, u32 size, struct nvkm_object **);
+	void (*intr)(struct nv50_disp_chan *, bool en);
+	u64 (*user)(struct nv50_disp_chan *, u64 *size);
+	int (*bind)(struct nv50_disp_chan *, struct nvkm_object *, u32 handle);
 };
 
-int nv50_disp_chan_ctor(const struct nv50_disp_chan_func *,
-			const struct nv50_disp_chan_mthd *,
-			struct nv50_disp_root *, int ctrl, int user, int head,
-			const struct nvkm_oclass *, struct nv50_disp_chan *);
 int nv50_disp_chan_new_(const struct nv50_disp_chan_func *,
 			const struct nv50_disp_chan_mthd *,
-			struct nv50_disp_root *, int ctrl, int user, int head,
+			struct nv50_disp *, int ctrl, int user, int head,
+			const struct nvkm_oclass *, struct nvkm_object **);
+int nv50_disp_dmac_new_(const struct nv50_disp_chan_func *,
+			const struct nv50_disp_chan_mthd *,
+			struct nv50_disp *, int chid, int head, u64 push,
 			const struct nvkm_oclass *, struct nvkm_object **);
 
+void nv50_disp_chan_intr(struct nv50_disp_chan *, bool);
+u64 nv50_disp_chan_user(struct nv50_disp_chan *, u64 *);
 extern const struct nv50_disp_chan_func nv50_disp_pioc_func;
-extern const struct nv50_disp_chan_func gf119_disp_pioc_func;
-
-extern const struct nvkm_event_func nv50_disp_chan_uevent;
-int  nv50_disp_chan_uevent_ctor(struct nvkm_object *, void *, u32,
-				struct nvkm_notify *);
-void nv50_disp_chan_uevent_send(struct nv50_disp *, int);
+extern const struct nv50_disp_chan_func nv50_disp_dmac_func;
+int nv50_disp_dmac_bind(struct nv50_disp_chan *, struct nvkm_object *, u32);
+extern const struct nv50_disp_chan_func nv50_disp_core_func;
 
-extern const struct nvkm_event_func gf119_disp_chan_uevent;
+void gf119_disp_chan_intr(struct nv50_disp_chan *, bool);
+extern const struct nv50_disp_chan_func gf119_disp_pioc_func;
+extern const struct nv50_disp_chan_func gf119_disp_dmac_func;
+void gf119_disp_dmac_fini(struct nv50_disp_chan *);
+int gf119_disp_dmac_bind(struct nv50_disp_chan *, struct nvkm_object *, u32);
+extern const struct nv50_disp_chan_func gf119_disp_core_func;
+void gf119_disp_core_fini(struct nv50_disp_chan *);
+
+extern const struct nv50_disp_chan_func gp102_disp_dmac_func;
+
+u64 gv100_disp_chan_user(struct nv50_disp_chan *, u64 *);
+int gv100_disp_dmac_init(struct nv50_disp_chan *);
+void gv100_disp_dmac_fini(struct nv50_disp_chan *);
+int gv100_disp_dmac_bind(struct nv50_disp_chan *, struct nvkm_object *, u32);
+
+int nv50_disp_curs_new_(const struct nv50_disp_chan_func *,
+			struct nv50_disp *, int ctrl, int user,
+			const struct nvkm_oclass *, void *argv, u32 argc,
+			struct nvkm_object **);
+int nv50_disp_oimm_new_(const struct nv50_disp_chan_func *,
+			struct nv50_disp *, int ctrl, int user,
+			const struct nvkm_oclass *, void *argv, u32 argc,
+			struct nvkm_object **);
+int nv50_disp_base_new_(const struct nv50_disp_chan_func *,
+			const struct nv50_disp_chan_mthd *,
+			struct nv50_disp *, int chid,
+			const struct nvkm_oclass *, void *argv, u32 argc,
+			struct nvkm_object **);
+int nv50_disp_core_new_(const struct nv50_disp_chan_func *,
+			const struct nv50_disp_chan_mthd *,
+			struct nv50_disp *, int chid,
+			const struct nvkm_oclass *oclass, void *argv, u32 argc,
+			struct nvkm_object **);
+int nv50_disp_ovly_new_(const struct nv50_disp_chan_func *,
+			const struct nv50_disp_chan_mthd *,
+			struct nv50_disp *, int chid,
+			const struct nvkm_oclass *, void *argv, u32 argc,
+			struct nvkm_object **);
+
+int nv50_disp_curs_new(const struct nvkm_oclass *, void *, u32,
+		       struct nv50_disp *, struct nvkm_object **);
+int nv50_disp_oimm_new(const struct nvkm_oclass *, void *, u32,
+		       struct nv50_disp *, struct nvkm_object **);
+int nv50_disp_base_new(const struct nvkm_oclass *, void *, u32,
+		       struct nv50_disp *, struct nvkm_object **);
+int nv50_disp_core_new(const struct nvkm_oclass *, void *, u32,
+		       struct nv50_disp *, struct nvkm_object **);
+int nv50_disp_ovly_new(const struct nvkm_oclass *, void *, u32,
+		       struct nv50_disp *, struct nvkm_object **);
+
+int g84_disp_base_new(const struct nvkm_oclass *, void *, u32,
+		      struct nv50_disp *, struct nvkm_object **);
+int g84_disp_core_new(const struct nvkm_oclass *, void *, u32,
+		      struct nv50_disp *, struct nvkm_object **);
+int g84_disp_ovly_new(const struct nvkm_oclass *, void *, u32,
+		      struct nv50_disp *, struct nvkm_object **);
+
+int g94_disp_core_new(const struct nvkm_oclass *, void *, u32,
+		      struct nv50_disp *, struct nvkm_object **);
+
+int gt200_disp_ovly_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+
+int gf119_disp_curs_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gf119_disp_oimm_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gf119_disp_base_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gf119_disp_core_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gf119_disp_ovly_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+
+int gk104_disp_core_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gk104_disp_ovly_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+
+int gp102_disp_curs_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gp102_disp_oimm_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gp102_disp_base_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gp102_disp_core_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gp102_disp_ovly_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+
+int gv100_disp_curs_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gv100_disp_wimm_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gv100_disp_core_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
+int gv100_disp_wndw_new(const struct nvkm_oclass *, void *, u32,
+			struct nv50_disp *, struct nvkm_object **);
 
 struct nv50_disp_mthd_list {
 	u32 mthd;
@@ -76,64 +174,18 @@ extern const struct nv50_disp_mthd_list nv50_disp_core_mthd_sor;
 extern const struct nv50_disp_mthd_list nv50_disp_core_mthd_pior;
 extern const struct nv50_disp_mthd_list nv50_disp_base_mthd_image;
 
-extern const struct nv50_disp_chan_mthd g84_disp_core_chan_mthd;
+extern const struct nv50_disp_chan_mthd g84_disp_core_mthd;
 extern const struct nv50_disp_mthd_list g84_disp_core_mthd_dac;
 extern const struct nv50_disp_mthd_list g84_disp_core_mthd_head;
-extern const struct nv50_disp_chan_mthd g84_disp_base_chan_mthd;
-extern const struct nv50_disp_chan_mthd g84_disp_ovly_chan_mthd;
 
-extern const struct nv50_disp_chan_mthd g94_disp_core_chan_mthd;
+extern const struct nv50_disp_chan_mthd g94_disp_core_mthd;
 
 extern const struct nv50_disp_mthd_list gf119_disp_core_mthd_base;
 extern const struct nv50_disp_mthd_list gf119_disp_core_mthd_dac;
 extern const struct nv50_disp_mthd_list gf119_disp_core_mthd_sor;
 extern const struct nv50_disp_mthd_list gf119_disp_core_mthd_pior;
-extern const struct nv50_disp_chan_mthd gf119_disp_base_chan_mthd;
-
-extern const struct nv50_disp_chan_mthd gk104_disp_core_chan_mthd;
-extern const struct nv50_disp_chan_mthd gk104_disp_ovly_chan_mthd;
-
-struct nv50_disp_pioc_oclass {
-	int (*ctor)(const struct nv50_disp_chan_func *,
-		    const struct nv50_disp_chan_mthd *,
-		    struct nv50_disp_root *, int ctrl, int user,
-		    const struct nvkm_oclass *, void *data, u32 size,
-		    struct nvkm_object **);
-	struct nvkm_sclass base;
-	const struct nv50_disp_chan_func *func;
-	const struct nv50_disp_chan_mthd *mthd;
-	struct {
-		int ctrl;
-		int user;
-	} chid;
-};
-
-extern const struct nv50_disp_pioc_oclass nv50_disp_oimm_oclass;
-extern const struct nv50_disp_pioc_oclass nv50_disp_curs_oclass;
-
-extern const struct nv50_disp_pioc_oclass g84_disp_oimm_oclass;
-extern const struct nv50_disp_pioc_oclass g84_disp_curs_oclass;
-
-extern const struct nv50_disp_pioc_oclass gt215_disp_oimm_oclass;
-extern const struct nv50_disp_pioc_oclass gt215_disp_curs_oclass;
-
-extern const struct nv50_disp_pioc_oclass gf119_disp_oimm_oclass;
-extern const struct nv50_disp_pioc_oclass gf119_disp_curs_oclass;
-
-extern const struct nv50_disp_pioc_oclass gk104_disp_oimm_oclass;
-extern const struct nv50_disp_pioc_oclass gk104_disp_curs_oclass;
-
-extern const struct nv50_disp_pioc_oclass gp102_disp_oimm_oclass;
-extern const struct nv50_disp_pioc_oclass gp102_disp_curs_oclass;
+extern const struct nv50_disp_chan_mthd gf119_disp_base_mthd;
 
-int nv50_disp_curs_new(const struct nv50_disp_chan_func *,
-		       const struct nv50_disp_chan_mthd *,
-		       struct nv50_disp_root *, int ctrl, int user,
-		       const struct nvkm_oclass *, void *data, u32 size,
-		       struct nvkm_object **);
-int nv50_disp_oimm_new(const struct nv50_disp_chan_func *,
-		       const struct nv50_disp_chan_mthd *,
-		       struct nv50_disp_root *, int ctrl, int user,
-		       const struct nvkm_oclass *, void *data, u32 size,
-		       struct nvkm_object **);
+extern const struct nv50_disp_chan_mthd gk104_disp_core_mthd;
+extern const struct nv50_disp_chan_mthd gk104_disp_ovly_mthd;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coreg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coreg84.c
index 1baa5c34b327..cfc54aad3e7c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coreg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coreg84.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 const struct nv50_disp_mthd_list
 g84_disp_core_mthd_dac = {
@@ -91,7 +88,7 @@ g84_disp_core_mthd_head = {
 };
 
 const struct nv50_disp_chan_mthd
-g84_disp_core_chan_mthd = {
+g84_disp_core_mthd = {
 	.name = "Core",
 	.addr = 0x000000,
 	.prev = 0x000004,
@@ -105,13 +102,10 @@ g84_disp_core_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-g84_disp_core_oclass = {
-	.base.oclass = G82_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &nv50_disp_core_func,
-	.mthd = &g84_disp_core_chan_mthd,
-	.chid = 0,
-};
+int
+g84_disp_core_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		  struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_core_new_(&nv50_disp_core_func, &g84_disp_core_mthd,
+				   disp, 0, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coreg94.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coreg94.c
index c65c9f3ff69f..e911925f1182 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coreg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coreg94.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 static const struct nv50_disp_mthd_list
 g94_disp_core_mthd_sor = {
@@ -37,7 +34,7 @@ g94_disp_core_mthd_sor = {
 };
 
 const struct nv50_disp_chan_mthd
-g94_disp_core_chan_mthd = {
+g94_disp_core_mthd = {
 	.name = "Core",
 	.addr = 0x000000,
 	.prev = 0x000004,
@@ -51,13 +48,10 @@ g94_disp_core_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-g94_disp_core_oclass = {
-	.base.oclass = GT206_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &nv50_disp_core_func,
-	.mthd = &g94_disp_core_chan_mthd,
-	.chid = 0,
-};
+int
+g94_disp_core_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		  struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_core_new_(&nv50_disp_core_func, &g94_disp_core_mthd,
+				   disp, 0, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregf119.c
index 21fbf89b6319..d162b9cf4eac 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregf119.c
@@ -21,15 +21,10 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "channv50.h"
 
-#include <core/client.h>
 #include <subdev/timer.h>
 
-#include <nvif/class.h>
-#include <nvif/unpack.h>
-
 const struct nv50_disp_mthd_list
 gf119_disp_core_mthd_base = {
 	.mthd = 0x0000,
@@ -157,7 +152,7 @@ gf119_disp_core_mthd_head = {
 };
 
 static const struct nv50_disp_chan_mthd
-gf119_disp_core_chan_mthd = {
+gf119_disp_core_mthd = {
 	.name = "Core",
 	.addr = 0x000000,
 	.prev = -0x020000,
@@ -172,10 +167,9 @@ gf119_disp_core_chan_mthd = {
 };
 
 void
-gf119_disp_core_fini(struct nv50_disp_dmac *chan)
+gf119_disp_core_fini(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 
 	/* deactivate channel */
@@ -188,22 +182,14 @@ gf119_disp_core_fini(struct nv50_disp_dmac *chan)
 		nvkm_error(subdev, "core fini: %08x\n",
 			   nvkm_rd32(device, 0x610490));
 	}
-
-	/* disable error reporting and completion notification */
-	nvkm_mask(device, 0x610090, 0x00000001, 0x00000000);
-	nvkm_mask(device, 0x6100a0, 0x00000001, 0x00000000);
 }
 
 static int
-gf119_disp_core_init(struct nv50_disp_dmac *chan)
+gf119_disp_core_init(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 
-	/* enable error reporting */
-	nvkm_mask(device, 0x6100a0, 0x00000001, 0x00000001);
-
 	/* initialise channel for dma command submission */
 	nvkm_wr32(device, 0x610494, chan->push);
 	nvkm_wr32(device, 0x610498, 0x00010000);
@@ -225,20 +211,19 @@ gf119_disp_core_init(struct nv50_disp_dmac *chan)
 	return 0;
 }
 
-const struct nv50_disp_dmac_func
+const struct nv50_disp_chan_func
 gf119_disp_core_func = {
 	.init = gf119_disp_core_init,
 	.fini = gf119_disp_core_fini,
+	.intr = gf119_disp_chan_intr,
+	.user = nv50_disp_chan_user,
 	.bind = gf119_disp_dmac_bind,
 };
 
-const struct nv50_disp_dmac_oclass
-gf119_disp_core_oclass = {
-	.base.oclass = GF110_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &gf119_disp_core_func,
-	.mthd = &gf119_disp_core_chan_mthd,
-	.chid = 0,
-};
+int
+gf119_disp_core_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_core_new_(&gf119_disp_core_func, &gf119_disp_core_mthd,
+				   disp, 0, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregk104.c
index 088ab222e823..5c800174e079 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregk104.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 static const struct nv50_disp_mthd_list
 gk104_disp_core_mthd_head = {
@@ -106,7 +103,7 @@ gk104_disp_core_mthd_head = {
 };
 
 const struct nv50_disp_chan_mthd
-gk104_disp_core_chan_mthd = {
+gk104_disp_core_mthd = {
 	.name = "Core",
 	.addr = 0x000000,
 	.prev = -0x020000,
@@ -120,13 +117,10 @@ gk104_disp_core_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-gk104_disp_core_oclass = {
-	.base.oclass = GK104_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &gf119_disp_core_func,
-	.mthd = &gk104_disp_core_chan_mthd,
-	.chid = 0,
-};
+int
+gk104_disp_core_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_core_new_(&gf119_disp_core_func, &gk104_disp_core_mthd,
+				   disp, 0, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregk110.c
deleted file mode 100644
index df0f45c20108..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregk110.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright 2015 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
- */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
-
-const struct nv50_disp_dmac_oclass
-gk110_disp_core_oclass = {
-	.base.oclass = GK110_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &gf119_disp_core_func,
-	.mthd = &gk104_disp_core_chan_mthd,
-	.chid = 0,
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregm107.c
deleted file mode 100644
index 9e27f8fd98b6..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregm107.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright 2015 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
- */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
-
-const struct nv50_disp_dmac_oclass
-gm107_disp_core_oclass = {
-	.base.oclass = GM107_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &gf119_disp_core_func,
-	.mthd = &gk104_disp_core_chan_mthd,
-	.chid = 0,
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregm200.c
deleted file mode 100644
index bb23a8658ac0..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregm200.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright 2015 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
- */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
-
-const struct nv50_disp_dmac_oclass
-gm200_disp_core_oclass = {
-	.base.oclass = GM200_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &gf119_disp_core_func,
-	.mthd = &gk104_disp_core_chan_mthd,
-	.chid = 0,
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp100.c
deleted file mode 100644
index d5dff6619d4d..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp100.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright 2015 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
- */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
-
-const struct nv50_disp_dmac_oclass
-gp100_disp_core_oclass = {
-	.base.oclass = GP100_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &gf119_disp_core_func,
-	.mthd = &gk104_disp_core_chan_mthd,
-	.chid = 0,
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp102.c
index b0df4b752b8c..5b7f993c73c7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp102.c
@@ -21,23 +21,16 @@
  *
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "channv50.h"
 
 #include <subdev/timer.h>
 
-#include <nvif/class.h>
-
 static int
-gp102_disp_core_init(struct nv50_disp_dmac *chan)
+gp102_disp_core_init(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 
-	/* enable error reporting */
-	nvkm_mask(device, 0x6100a0, 0x00000001, 0x00000001);
-
 	/* initialise channel for dma command submission */
 	nvkm_wr32(device, 0x611494, chan->push);
 	nvkm_wr32(device, 0x611498, 0x00010000);
@@ -59,20 +52,19 @@ gp102_disp_core_init(struct nv50_disp_dmac *chan)
 	return 0;
 }
 
-static const struct nv50_disp_dmac_func
+static const struct nv50_disp_chan_func
 gp102_disp_core_func = {
 	.init = gp102_disp_core_init,
 	.fini = gf119_disp_core_fini,
+	.intr = gf119_disp_chan_intr,
+	.user = nv50_disp_chan_user,
 	.bind = gf119_disp_dmac_bind,
 };
 
-const struct nv50_disp_dmac_oclass
-gp102_disp_core_oclass = {
-	.base.oclass = GP102_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &gp102_disp_core_func,
-	.mthd = &gk104_disp_core_chan_mthd,
-	.chid = 0,
-};
+int
+gp102_disp_core_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_core_new_(&gp102_disp_core_func, &gk104_disp_core_mthd,
+				   disp, 0, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregt215.c
deleted file mode 100644
index 8f5ba2018975..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregt215.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright 2015 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
- */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
-
-const struct nv50_disp_dmac_oclass
-gt215_disp_core_oclass = {
-	.base.oclass = GT214_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &nv50_disp_core_func,
-	.mthd = &g94_disp_core_chan_mthd,
-	.chid = 0,
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregv100.c
new file mode 100644
index 000000000000..4592d0e69fec
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregv100.c
@@ -0,0 +1,204 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "channv50.h"
+
+#include <subdev/timer.h>
+
+const struct nv50_disp_mthd_list
+gv100_disp_core_mthd_base = {
+	.mthd = 0x0000,
+	.addr = 0x000000,
+	.data = {
+		{ 0x0200, 0x680200 },
+		{ 0x0208, 0x680208 },
+		{ 0x020c, 0x68020c },
+		{ 0x0210, 0x680210 },
+		{ 0x0214, 0x680214 },
+		{ 0x0218, 0x680218 },
+		{ 0x021c, 0x68021c },
+		{}
+	}
+};
+
+const struct nv50_disp_mthd_list
+gv100_disp_core_mthd_sor = {
+	.mthd = 0x0020,
+	.addr = 0x000020,
+	.data = {
+		{ 0x0300, 0x680300 },
+		{ 0x0304, 0x680304 },
+		{ 0x0308, 0x680308 },
+		{ 0x030c, 0x68030c },
+		{}
+	}
+};
+
+static const struct nv50_disp_mthd_list
+gv100_disp_core_mthd_wndw = {
+	.mthd = 0x0080,
+	.addr = 0x000080,
+	.data = {
+		{ 0x1000, 0x681000 },
+		{ 0x1004, 0x681004 },
+		{ 0x1008, 0x681008 },
+		{ 0x100c, 0x68100c },
+		{ 0x1010, 0x681010 },
+		{}
+	}
+};
+
+static const struct nv50_disp_mthd_list
+gv100_disp_core_mthd_head = {
+	.mthd = 0x0400,
+	.addr = 0x000400,
+	.data = {
+		{ 0x2000, 0x682000 },
+		{ 0x2004, 0x682004 },
+		{ 0x2008, 0x682008 },
+		{ 0x200c, 0x68200c },
+		{ 0x2014, 0x682014 },
+		{ 0x2018, 0x682018 },
+		{ 0x201c, 0x68201c },
+		{ 0x2020, 0x682020 },
+		{ 0x2028, 0x682028 },
+		{ 0x202c, 0x68202c },
+		{ 0x2030, 0x682030 },
+		{ 0x2038, 0x682038 },
+		{ 0x203c, 0x68203c },
+		{ 0x2048, 0x682048 },
+		{ 0x204c, 0x68204c },
+		{ 0x2050, 0x682050 },
+		{ 0x2054, 0x682054 },
+		{ 0x2058, 0x682058 },
+		{ 0x205c, 0x68205c },
+		{ 0x2060, 0x682060 },
+		{ 0x2064, 0x682064 },
+		{ 0x2068, 0x682068 },
+		{ 0x206c, 0x68206c },
+		{ 0x2070, 0x682070 },
+		{ 0x2074, 0x682074 },
+		{ 0x2078, 0x682078 },
+		{ 0x207c, 0x68207c },
+		{ 0x2080, 0x682080 },
+		{ 0x2088, 0x682088 },
+		{ 0x2090, 0x682090 },
+		{ 0x209c, 0x68209c },
+		{ 0x20a0, 0x6820a0 },
+		{ 0x20a4, 0x6820a4 },
+		{ 0x20a8, 0x6820a8 },
+		{ 0x20ac, 0x6820ac },
+		{ 0x218c, 0x68218c },
+		{ 0x2194, 0x682194 },
+		{ 0x2198, 0x682198 },
+		{ 0x219c, 0x68219c },
+		{ 0x21a0, 0x6821a0 },
+		{ 0x21a4, 0x6821a4 },
+		{ 0x2214, 0x682214 },
+		{ 0x2218, 0x682218 },
+		{}
+	}
+};
+
+static const struct nv50_disp_chan_mthd
+gv100_disp_core_mthd = {
+	.name = "Core",
+	.addr = 0x000000,
+	.prev = 0x008000,
+	.data = {
+		{ "Global", 1, &gv100_disp_core_mthd_base },
+		{    "SOR", 4, &gv100_disp_core_mthd_sor  },
+		{ "WINDOW", 8, &gv100_disp_core_mthd_wndw },
+		{   "HEAD", 4, &gv100_disp_core_mthd_head },
+		{}
+	}
+};
+
+static int
+gv100_disp_core_idle(struct nv50_disp_chan *chan)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	nvkm_msec(device, 2000,
+		u32 stat = nvkm_rd32(device, 0x610630);
+		if ((stat & 0x001f0000) == 0x000b0000)
+			return 0;
+	);
+	return -EBUSY;
+}
+
+static u64
+gv100_disp_core_user(struct nv50_disp_chan *chan, u64 *psize)
+{
+	*psize = 0x10000;
+	return 0x680000;
+}
+
+static void
+gv100_disp_core_intr(struct nv50_disp_chan *chan, bool en)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u32 mask = 0x00000001;
+	const u32 data = en ? mask : 0;
+	nvkm_mask(device, 0x611dac, mask, data);
+}
+
+static void
+gv100_disp_core_fini(struct nv50_disp_chan *chan)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	nvkm_mask(device, 0x6104e0, 0x00000010, 0x00000000);
+	gv100_disp_core_idle(chan);
+	nvkm_mask(device, 0x6104e0, 0x00000002, 0x00000000);
+}
+
+static int
+gv100_disp_core_init(struct nv50_disp_chan *chan)
+{
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+
+	nvkm_wr32(device, 0x610b24, lower_32_bits(chan->push));
+	nvkm_wr32(device, 0x610b20, upper_32_bits(chan->push));
+	nvkm_wr32(device, 0x610b28, 0x00000001);
+	nvkm_wr32(device, 0x610b2c, 0x00000040);
+
+	nvkm_mask(device, 0x6104e0, 0x00000010, 0x00000010);
+	nvkm_wr32(device, 0x680000, 0x00000000);
+	nvkm_wr32(device, 0x6104e0, 0x00000013);
+	return gv100_disp_core_idle(chan);
+}
+
+static const struct nv50_disp_chan_func
+gv100_disp_core = {
+	.init = gv100_disp_core_init,
+	.fini = gv100_disp_core_fini,
+	.intr = gv100_disp_core_intr,
+	.user = gv100_disp_core_user,
+	.bind = gv100_disp_dmac_bind,
+};
+
+int
+gv100_disp_core_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_core_new_(&gv100_disp_core, &gv100_disp_core_mthd,
+				   disp, 0, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/corenv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/corenv50.c
index b547c8b833ca..55db9a22b4be 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/corenv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/corenv50.c
@@ -21,32 +21,30 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "channv50.h"
 
 #include <core/client.h>
 #include <subdev/timer.h>
 
-#include <nvif/class.h>
 #include <nvif/cl507d.h>
 #include <nvif/unpack.h>
 
 int
-nv50_disp_core_new(const struct nv50_disp_dmac_func *func,
-		   const struct nv50_disp_chan_mthd *mthd,
-		   struct nv50_disp_root *root, int chid,
-		   const struct nvkm_oclass *oclass, void *data, u32 size,
-		   struct nvkm_object **pobject)
+nv50_disp_core_new_(const struct nv50_disp_chan_func *func,
+		    const struct nv50_disp_chan_mthd *mthd,
+		    struct nv50_disp *disp, int chid,
+		    const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nvkm_object **pobject)
 {
 	union {
 		struct nv50_disp_core_channel_dma_v0 v0;
-	} *args = data;
+	} *args = argv;
 	struct nvkm_object *parent = oclass->parent;
 	u64 push;
 	int ret = -ENOSYS;
 
-	nvif_ioctl(parent, "create disp core channel dma size %d\n", size);
-	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
+	nvif_ioctl(parent, "create disp core channel dma size %d\n", argc);
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
 		nvif_ioctl(parent, "create disp core channel dma vers %d "
 				   "pushbuf %016llx\n",
 			   args->v0.version, args->v0.pushbuf);
@@ -54,7 +52,7 @@ nv50_disp_core_new(const struct nv50_disp_dmac_func *func,
 	} else
 		return ret;
 
-	return nv50_disp_dmac_new_(func, mthd, root, chid, 0,
+	return nv50_disp_dmac_new_(func, mthd, disp, chid, 0,
 				   push, oclass, pobject);
 }
 
@@ -151,7 +149,7 @@ nv50_disp_core_mthd_head = {
 };
 
 static const struct nv50_disp_chan_mthd
-nv50_disp_core_chan_mthd = {
+nv50_disp_core_mthd = {
 	.name = "Core",
 	.addr = 0x000000,
 	.prev = 0x000004,
@@ -166,10 +164,9 @@ nv50_disp_core_chan_mthd = {
 };
 
 static void
-nv50_disp_core_fini(struct nv50_disp_dmac *chan)
+nv50_disp_core_fini(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 
 	/* deactivate channel */
@@ -182,21 +179,14 @@ nv50_disp_core_fini(struct nv50_disp_dmac *chan)
 		nvkm_error(subdev, "core fini: %08x\n",
 			   nvkm_rd32(device, 0x610200));
 	}
-
-	/* disable error reporting and completion notifications */
-	nvkm_mask(device, 0x610028, 0x00010001, 0x00000000);
 }
 
 static int
-nv50_disp_core_init(struct nv50_disp_dmac *chan)
+nv50_disp_core_init(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 
-	/* enable error reporting */
-	nvkm_mask(device, 0x610028, 0x00010000, 0x00010000);
-
 	/* attempt to unstick channel from some unknown state */
 	if ((nvkm_rd32(device, 0x610200) & 0x009f0000) == 0x00020000)
 		nvkm_mask(device, 0x610200, 0x00800000, 0x00800000);
@@ -224,20 +214,19 @@ nv50_disp_core_init(struct nv50_disp_dmac *chan)
 	return 0;
 }
 
-const struct nv50_disp_dmac_func
+const struct nv50_disp_chan_func
 nv50_disp_core_func = {
 	.init = nv50_disp_core_init,
 	.fini = nv50_disp_core_fini,
+	.intr = nv50_disp_chan_intr,
+	.user = nv50_disp_chan_user,
 	.bind = nv50_disp_dmac_bind,
 };
 
-const struct nv50_disp_dmac_oclass
-nv50_disp_core_oclass = {
-	.base.oclass = NV50_DISP_CORE_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_core_new,
-	.func = &nv50_disp_core_func,
-	.mthd = &nv50_disp_core_chan_mthd,
-	.chid = 0,
-};
+int
+nv50_disp_core_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		   struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_core_new_(&nv50_disp_core_func, &nv50_disp_core_mthd,
+				   disp, 0, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c
index 2be6fb052c65..cdda3658dcb3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c
@@ -22,16 +22,11 @@
  * Authors: Ben Skeggs
  */
 #include "channv50.h"
-#include "rootnv50.h"
 
-#include <nvif/class.h>
-
-const struct nv50_disp_pioc_oclass
-gf119_disp_curs_oclass = {
-	.base.oclass = GF110_DISP_CURSOR,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_curs_new,
-	.func = &gf119_disp_pioc_func,
-	.chid = { 13, 13 },
-};
+int
+gf119_disp_curs_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_curs_new_(&gf119_disp_pioc_func, disp, 13, 13,
+				   oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c
index e958210d8105..1a4601f975e6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c
@@ -22,16 +22,11 @@
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
 #include "channv50.h"
-#include "rootnv50.h"
 
-#include <nvif/class.h>
-
-const struct nv50_disp_pioc_oclass
-gp102_disp_curs_oclass = {
-	.base.oclass = GK104_DISP_CURSOR,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_curs_new,
-	.func = &gf119_disp_pioc_func,
-	.chid = { 13, 17 },
-};
+int
+gp102_disp_curs_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_curs_new_(&gf119_disp_pioc_func, disp, 13, 17,
+				   oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgv100.c
new file mode 100644
index 000000000000..a3e4f6900245
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgv100.c
@@ -0,0 +1,81 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "channv50.h"
+
+#include <subdev/timer.h>
+
+static int
+gv100_disp_curs_idle(struct nv50_disp_chan *chan)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u32 soff = (chan->chid.ctrl - 1) * 0x04;
+	nvkm_msec(device, 2000,
+		u32 stat = nvkm_rd32(device, 0x610664 + soff);
+		if ((stat & 0x00070000) == 0x00040000)
+			return 0;
+	);
+	return -EBUSY;
+}
+
+static void
+gv100_disp_curs_intr(struct nv50_disp_chan *chan, bool en)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u32 mask = 0x00010000 << chan->head;
+	const u32 data = en ? mask : 0;
+	nvkm_mask(device, 0x611dac, mask, data);
+}
+
+static void
+gv100_disp_curs_fini(struct nv50_disp_chan *chan)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u32 hoff = chan->chid.ctrl * 4;
+	nvkm_mask(device, 0x6104e0 + hoff, 0x00000010, 0x00000010);
+	gv100_disp_curs_idle(chan);
+	nvkm_mask(device, 0x6104e0 + hoff, 0x00000001, 0x00000000);
+}
+
+static int
+gv100_disp_curs_init(struct nv50_disp_chan *chan)
+{
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	nvkm_wr32(device, 0x6104e0 + chan->chid.ctrl * 4, 0x00000001);
+	return gv100_disp_curs_idle(chan);
+}
+
+static const struct nv50_disp_chan_func
+gv100_disp_curs = {
+	.init = gv100_disp_curs_init,
+	.fini = gv100_disp_curs_fini,
+	.intr = gv100_disp_curs_intr,
+	.user = gv100_disp_chan_user,
+};
+
+int
+gv100_disp_curs_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_curs_new_(&gv100_disp_curs, disp, 73, 73,
+				   oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c
index ab51121b7982..d29758504a5f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c
@@ -23,30 +23,26 @@
  */
 #include "channv50.h"
 #include "head.h"
-#include "rootnv50.h"
 
 #include <core/client.h>
 
-#include <nvif/class.h>
 #include <nvif/cl507a.h>
 #include <nvif/unpack.h>
 
 int
-nv50_disp_curs_new(const struct nv50_disp_chan_func *func,
-		   const struct nv50_disp_chan_mthd *mthd,
-		   struct nv50_disp_root *root, int ctrl, int user,
-		   const struct nvkm_oclass *oclass, void *data, u32 size,
-		   struct nvkm_object **pobject)
+nv50_disp_curs_new_(const struct nv50_disp_chan_func *func,
+		    struct nv50_disp *disp, int ctrl, int user,
+		    const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nvkm_object **pobject)
 {
 	union {
 		struct nv50_disp_cursor_v0 v0;
-	} *args = data;
+	} *args = argv;
 	struct nvkm_object *parent = oclass->parent;
-	struct nv50_disp *disp = root->disp;
 	int head, ret = -ENOSYS;
 
-	nvif_ioctl(parent, "create disp cursor size %d\n", size);
-	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
+	nvif_ioctl(parent, "create disp cursor size %d\n", argc);
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
 		nvif_ioctl(parent, "create disp cursor vers %d head %d\n",
 			   args->v0.version, args->v0.head);
 		if (!nvkm_head_find(&disp->base, args->v0.head))
@@ -55,16 +51,14 @@ nv50_disp_curs_new(const struct nv50_disp_chan_func *func,
 	} else
 		return ret;
 
-	return nv50_disp_chan_new_(func, mthd, root, ctrl + head, user + head,
+	return nv50_disp_chan_new_(func, NULL, disp, ctrl + head, user + head,
 				   head, oclass, pobject);
 }
 
-const struct nv50_disp_pioc_oclass
-nv50_disp_curs_oclass = {
-	.base.oclass = NV50_DISP_CURSOR,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_curs_new,
-	.func = &nv50_disp_pioc_func,
-	.chid = { 7, 7 },
-};
+int
+nv50_disp_curs_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		   struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_curs_new_(&nv50_disp_pioc_func, disp, 7, 7,
+				   oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dacgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dacgf119.c
index dbd032ef352a..71a94777ea2e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dacgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dacgf119.c
@@ -58,8 +58,13 @@ gf119_dac = {
 int
 gf119_dac_new(struct nvkm_disp *disp, int id)
 {
-	struct nvkm_device *device = disp->engine.subdev.device;
-	if (!(nvkm_rd32(device, 0x612004) & (0x00000010 << id)))
-		return 0;
 	return nvkm_ior_new_(&gf119_dac, disp, DAC, id);
 }
+
+int
+gf119_dac_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = (nvkm_rd32(device, 0x612004) & 0x000000f0) >> 4;
+	return 4;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dacnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dacnv50.c
index 85e692b12260..558012db35f8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dacnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dacnv50.c
@@ -109,8 +109,13 @@ nv50_dac = {
 int
 nv50_dac_new(struct nvkm_disp *disp, int id)
 {
-	struct nvkm_device *device = disp->engine.subdev.device;
-	if (!(nvkm_rd32(device, 0x610184) & (0x00100000 << id)))
-		return 0;
 	return nvkm_ior_new_(&nv50_dac, disp, DAC, id);
 }
+
+int
+nv50_dac_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = (nvkm_rd32(device, 0x610184) & 0x00700000) >> 20;
+	return 3;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
index ce7cd74fbd5d..edf7dd0d931d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
@@ -21,29 +21,27 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "channv50.h"
 
 #include <core/ramht.h>
 #include <subdev/timer.h>
 
 int
-gf119_disp_dmac_bind(struct nv50_disp_dmac *chan,
+gf119_disp_dmac_bind(struct nv50_disp_chan *chan,
 		     struct nvkm_object *object, u32 handle)
 {
-	return nvkm_ramht_insert(chan->base.root->ramht, object,
-				 chan->base.chid.user, -9, handle,
-				 chan->base.chid.user << 27 | 0x00000001);
+	return nvkm_ramht_insert(chan->disp->ramht, object,
+				 chan->chid.user, -9, handle,
+				 chan->chid.user << 27 | 0x00000001);
 }
 
 void
-gf119_disp_dmac_fini(struct nv50_disp_dmac *chan)
+gf119_disp_dmac_fini(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int ctrl = chan->base.chid.ctrl;
-	int user = chan->base.chid.user;
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
 	/* deactivate channel */
 	nvkm_mask(device, 0x610490 + (ctrl * 0x0010), 0x00001010, 0x00001000);
@@ -55,23 +53,15 @@ gf119_disp_dmac_fini(struct nv50_disp_dmac *chan)
 		nvkm_error(subdev, "ch %d fini: %08x\n", user,
 			   nvkm_rd32(device, 0x610490 + (ctrl * 0x10)));
 	}
-
-	/* disable error reporting and completion notification */
-	nvkm_mask(device, 0x610090, 0x00000001 << user, 0x00000000);
-	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000000);
 }
 
 static int
-gf119_disp_dmac_init(struct nv50_disp_dmac *chan)
+gf119_disp_dmac_init(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int ctrl = chan->base.chid.ctrl;
-	int user = chan->base.chid.user;
-
-	/* enable error reporting */
-	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000001 << user);
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
 	/* initialise channel for dma command submission */
 	nvkm_wr32(device, 0x610494 + (ctrl * 0x0010), chan->push);
@@ -94,9 +84,11 @@ gf119_disp_dmac_init(struct nv50_disp_dmac *chan)
 	return 0;
 }
 
-const struct nv50_disp_dmac_func
+const struct nv50_disp_chan_func
 gf119_disp_dmac_func = {
 	.init = gf119_disp_dmac_init,
 	.fini = gf119_disp_dmac_fini,
+	.intr = gf119_disp_chan_intr,
+	.user = nv50_disp_chan_user,
 	.bind = gf119_disp_dmac_bind,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp102.c
index cdead9500343..f21a433199aa 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp102.c
@@ -21,22 +21,17 @@
  *
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "channv50.h"
 
 #include <subdev/timer.h>
 
 static int
-gp102_disp_dmac_init(struct nv50_disp_dmac *chan)
+gp102_disp_dmac_init(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int ctrl = chan->base.chid.ctrl;
-	int user = chan->base.chid.user;
-
-	/* enable error reporting */
-	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000001 << user);
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
 	/* initialise channel for dma command submission */
 	nvkm_wr32(device, 0x611494 + (ctrl * 0x0010), chan->push);
@@ -59,9 +54,11 @@ gp102_disp_dmac_init(struct nv50_disp_dmac *chan)
 	return 0;
 }
 
-const struct nv50_disp_dmac_func
+const struct nv50_disp_chan_func
 gp102_disp_dmac_func = {
 	.init = gp102_disp_dmac_init,
 	.fini = gf119_disp_dmac_fini,
+	.intr = gf119_disp_chan_intr,
+	.user = nv50_disp_chan_user,
 	.bind = gf119_disp_dmac_bind,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgv100.c
new file mode 100644
index 000000000000..eac0e42da354
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgv100.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "channv50.h"
+
+#include <core/ramht.h>
+#include <subdev/timer.h>
+
+static int
+gv100_disp_dmac_idle(struct nv50_disp_chan *chan)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u32 soff = (chan->chid.ctrl - 1) * 0x04;
+	nvkm_msec(device, 2000,
+		u32 stat = nvkm_rd32(device, 0x610664 + soff);
+		if ((stat & 0x000f0000) == 0x00040000)
+			return 0;
+	);
+	return -EBUSY;
+}
+
+int
+gv100_disp_dmac_bind(struct nv50_disp_chan *chan,
+		     struct nvkm_object *object, u32 handle)
+{
+	return nvkm_ramht_insert(chan->disp->ramht, object,
+				 chan->chid.user, -9, handle,
+				 chan->chid.user << 25 | 0x00000040);
+}
+
+void
+gv100_disp_dmac_fini(struct nv50_disp_chan *chan)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u32 coff = chan->chid.ctrl * 0x04;
+	nvkm_mask(device, 0x6104e0 + coff, 0x00000010, 0x00000000);
+	gv100_disp_dmac_idle(chan);
+	nvkm_mask(device, 0x6104e0 + coff, 0x00000002, 0x00000000);
+}
+
+int
+gv100_disp_dmac_init(struct nv50_disp_chan *chan)
+{
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	const u32 uoff = (chan->chid.ctrl - 1) * 0x1000;
+	const u32 poff = chan->chid.ctrl * 0x10;
+	const u32 coff = chan->chid.ctrl * 0x04;
+
+	nvkm_wr32(device, 0x610b24 + poff, lower_32_bits(chan->push));
+	nvkm_wr32(device, 0x610b20 + poff, upper_32_bits(chan->push));
+	nvkm_wr32(device, 0x610b28 + poff, 0x00000001);
+	nvkm_wr32(device, 0x610b2c + poff, 0x00000040);
+
+	nvkm_mask(device, 0x6104e0 + coff, 0x00000010, 0x00000010);
+	nvkm_wr32(device, 0x690000 + uoff, 0x00000000);
+	nvkm_wr32(device, 0x6104e0 + coff, 0x00000013);
+	return gv100_disp_dmac_idle(chan);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
index 070ec5e18fdb..9e8a9d7a9b68 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
@@ -21,176 +21,68 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "channv50.h"
 
 #include <core/client.h>
-#include <core/oproxy.h>
 #include <core/ramht.h>
 #include <subdev/fb.h>
+#include <subdev/mmu.h>
 #include <subdev/timer.h>
 #include <engine/dma.h>
 
-struct nv50_disp_dmac_object {
-	struct nvkm_oproxy oproxy;
-	struct nv50_disp_root *root;
-	int hash;
-};
-
-static void
-nv50_disp_dmac_child_del_(struct nvkm_oproxy *base)
-{
-	struct nv50_disp_dmac_object *object =
-		container_of(base, typeof(*object), oproxy);
-	nvkm_ramht_remove(object->root->ramht, object->hash);
-}
-
-static const struct nvkm_oproxy_func
-nv50_disp_dmac_child_func_ = {
-	.dtor[0] = nv50_disp_dmac_child_del_,
-};
-
-static int
-nv50_disp_dmac_child_new_(struct nv50_disp_chan *base,
-			  const struct nvkm_oclass *oclass,
-			  void *data, u32 size, struct nvkm_object **pobject)
-{
-	struct nv50_disp_dmac *chan = nv50_disp_dmac(base);
-	struct nv50_disp_root *root = chan->base.root;
-	struct nvkm_device *device = root->disp->base.engine.subdev.device;
-	const struct nvkm_device_oclass *sclass = oclass->priv;
-	struct nv50_disp_dmac_object *object;
-	int ret;
-
-	if (!(object = kzalloc(sizeof(*object), GFP_KERNEL)))
-		return -ENOMEM;
-	nvkm_oproxy_ctor(&nv50_disp_dmac_child_func_, oclass, &object->oproxy);
-	object->root = root;
-	*pobject = &object->oproxy.base;
-
-	ret = sclass->ctor(device, oclass, data, size, &object->oproxy.object);
-	if (ret)
-		return ret;
-
-	object->hash = chan->func->bind(chan, object->oproxy.object,
-					      oclass->handle);
-	if (object->hash < 0)
-		return object->hash;
-
-	return 0;
-}
-
-static int
-nv50_disp_dmac_child_get_(struct nv50_disp_chan *base, int index,
-			  struct nvkm_oclass *sclass)
-{
-	struct nv50_disp_dmac *chan = nv50_disp_dmac(base);
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_device *device = disp->base.engine.subdev.device;
-	const struct nvkm_device_oclass *oclass = NULL;
-
-	sclass->engine = nvkm_device_engine(device, NVKM_ENGINE_DMAOBJ);
-	if (sclass->engine && sclass->engine->func->base.sclass) {
-		sclass->engine->func->base.sclass(sclass, index, &oclass);
-		if (oclass) {
-			sclass->priv = oclass;
-			return 0;
-		}
-	}
-
-	return -EINVAL;
-}
-
-static void
-nv50_disp_dmac_fini_(struct nv50_disp_chan *base)
-{
-	struct nv50_disp_dmac *chan = nv50_disp_dmac(base);
-	chan->func->fini(chan);
-}
-
-static int
-nv50_disp_dmac_init_(struct nv50_disp_chan *base)
-{
-	struct nv50_disp_dmac *chan = nv50_disp_dmac(base);
-	return chan->func->init(chan);
-}
-
-static void *
-nv50_disp_dmac_dtor_(struct nv50_disp_chan *base)
-{
-	return nv50_disp_dmac(base);
-}
-
-static const struct nv50_disp_chan_func
-nv50_disp_dmac_func_ = {
-	.dtor = nv50_disp_dmac_dtor_,
-	.init = nv50_disp_dmac_init_,
-	.fini = nv50_disp_dmac_fini_,
-	.child_get = nv50_disp_dmac_child_get_,
-	.child_new = nv50_disp_dmac_child_new_,
-};
-
 int
-nv50_disp_dmac_new_(const struct nv50_disp_dmac_func *func,
+nv50_disp_dmac_new_(const struct nv50_disp_chan_func *func,
 		    const struct nv50_disp_chan_mthd *mthd,
-		    struct nv50_disp_root *root, int chid, int head, u64 push,
+		    struct nv50_disp *disp, int chid, int head, u64 push,
 		    const struct nvkm_oclass *oclass,
 		    struct nvkm_object **pobject)
 {
 	struct nvkm_client *client = oclass->client;
-	struct nvkm_dmaobj *dmaobj;
-	struct nv50_disp_dmac *chan;
+	struct nv50_disp_chan *chan;
 	int ret;
 
-	if (!(chan = kzalloc(sizeof(*chan), GFP_KERNEL)))
-		return -ENOMEM;
-	*pobject = &chan->base.object;
-	chan->func = func;
-
-	ret = nv50_disp_chan_ctor(&nv50_disp_dmac_func_, mthd, root,
-				  chid, chid, head, oclass, &chan->base);
+	ret = nv50_disp_chan_new_(func, mthd, disp, chid, chid, head, oclass,
+				  pobject);
+	chan = nv50_disp_chan(*pobject);
 	if (ret)
 		return ret;
 
-	dmaobj = nvkm_dmaobj_search(client, push);
-	if (IS_ERR(dmaobj))
-		return PTR_ERR(dmaobj);
+	chan->memory = nvkm_umem_search(client, push);
+	if (IS_ERR(chan->memory))
+		return PTR_ERR(chan->memory);
 
-	if (dmaobj->limit - dmaobj->start != 0xfff)
+	if (nvkm_memory_size(chan->memory) < 0x1000)
 		return -EINVAL;
 
-	switch (dmaobj->target) {
-	case NV_MEM_TARGET_VRAM:
-		chan->push = 0x00000001 | dmaobj->start >> 8;
-		break;
-	case NV_MEM_TARGET_PCI_NOSNOOP:
-		chan->push = 0x00000003 | dmaobj->start >> 8;
-		break;
+	switch (nvkm_memory_target(chan->memory)) {
+	case NVKM_MEM_TARGET_VRAM: chan->push = 0x00000001; break;
+	case NVKM_MEM_TARGET_NCOH: chan->push = 0x00000002; break;
+	case NVKM_MEM_TARGET_HOST: chan->push = 0x00000003; break;
 	default:
 		return -EINVAL;
 	}
 
+	chan->push |= nvkm_memory_addr(chan->memory) >> 8;
 	return 0;
 }
 
 int
-nv50_disp_dmac_bind(struct nv50_disp_dmac *chan,
+nv50_disp_dmac_bind(struct nv50_disp_chan *chan,
 		    struct nvkm_object *object, u32 handle)
 {
-	return nvkm_ramht_insert(chan->base.root->ramht, object,
-				 chan->base.chid.user, -10, handle,
-				 chan->base.chid.user << 28 |
-				 chan->base.chid.user);
+	return nvkm_ramht_insert(chan->disp->ramht, object,
+				 chan->chid.user, -10, handle,
+				 chan->chid.user << 28 |
+				 chan->chid.user);
 }
 
 static void
-nv50_disp_dmac_fini(struct nv50_disp_dmac *chan)
+nv50_disp_dmac_fini(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int ctrl = chan->base.chid.ctrl;
-	int user = chan->base.chid.user;
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
 	/* deactivate channel */
 	nvkm_mask(device, 0x610200 + (ctrl * 0x0010), 0x00001010, 0x00001000);
@@ -202,22 +94,15 @@ nv50_disp_dmac_fini(struct nv50_disp_dmac *chan)
 		nvkm_error(subdev, "ch %d fini timeout, %08x\n", user,
 			   nvkm_rd32(device, 0x610200 + (ctrl * 0x10)));
 	}
-
-	/* disable error reporting and completion notifications */
-	nvkm_mask(device, 0x610028, 0x00010001 << user, 0x00000000 << user);
 }
 
 static int
-nv50_disp_dmac_init(struct nv50_disp_dmac *chan)
+nv50_disp_dmac_init(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->base.root->disp;
-	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_subdev *subdev = &chan->disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int ctrl = chan->base.chid.ctrl;
-	int user = chan->base.chid.user;
-
-	/* enable error reporting */
-	nvkm_mask(device, 0x610028, 0x00010000 << user, 0x00010000 << user);
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
 	/* initialise channel for dma command submission */
 	nvkm_wr32(device, 0x610204 + (ctrl * 0x0010), chan->push);
@@ -240,9 +125,11 @@ nv50_disp_dmac_init(struct nv50_disp_dmac *chan)
 	return 0;
 }
 
-const struct nv50_disp_dmac_func
+const struct nv50_disp_chan_func
 nv50_disp_dmac_func = {
 	.init = nv50_disp_dmac_init,
 	.fini = nv50_disp_dmac_fini,
+	.intr = nv50_disp_chan_intr,
+	.user = nv50_disp_chan_user,
 	.bind = nv50_disp_dmac_bind,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.h
deleted file mode 100644
index f9b98211da6a..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NV50_DISP_DMAC_H__
-#define __NV50_DISP_DMAC_H__
-#define nv50_disp_dmac(p) container_of((p), struct nv50_disp_dmac, base)
-#include "channv50.h"
-
-struct nv50_disp_dmac {
-	const struct nv50_disp_dmac_func *func;
-	struct nv50_disp_chan base;
-	u32 push;
-};
-
-struct nv50_disp_dmac_func {
-	int  (*init)(struct nv50_disp_dmac *);
-	void (*fini)(struct nv50_disp_dmac *);
-	int  (*bind)(struct nv50_disp_dmac *, struct nvkm_object *, u32 handle);
-};
-
-int nv50_disp_dmac_new_(const struct nv50_disp_dmac_func *,
-			const struct nv50_disp_chan_mthd *,
-			struct nv50_disp_root *, int chid, int head, u64 push,
-			const struct nvkm_oclass *, struct nvkm_object **);
-
-extern const struct nv50_disp_dmac_func nv50_disp_dmac_func;
-int nv50_disp_dmac_bind(struct nv50_disp_dmac *, struct nvkm_object *, u32);
-extern const struct nv50_disp_dmac_func nv50_disp_core_func;
-
-extern const struct nv50_disp_dmac_func gf119_disp_dmac_func;
-void gf119_disp_dmac_fini(struct nv50_disp_dmac *);
-int gf119_disp_dmac_bind(struct nv50_disp_dmac *, struct nvkm_object *, u32);
-extern const struct nv50_disp_dmac_func gf119_disp_core_func;
-void gf119_disp_core_fini(struct nv50_disp_dmac *);
-
-extern const struct nv50_disp_dmac_func gp102_disp_dmac_func;
-
-struct nv50_disp_dmac_oclass {
-	int (*ctor)(const struct nv50_disp_dmac_func *,
-		    const struct nv50_disp_chan_mthd *,
-		    struct nv50_disp_root *, int chid,
-		    const struct nvkm_oclass *, void *data, u32 size,
-		    struct nvkm_object **);
-	struct nvkm_sclass base;
-	const struct nv50_disp_dmac_func *func;
-	const struct nv50_disp_chan_mthd *mthd;
-	int chid;
-};
-
-int nv50_disp_core_new(const struct nv50_disp_dmac_func *,
-		       const struct nv50_disp_chan_mthd *,
-		       struct nv50_disp_root *, int chid,
-		       const struct nvkm_oclass *oclass, void *data, u32 size,
-		       struct nvkm_object **);
-int nv50_disp_base_new(const struct nv50_disp_dmac_func *,
-		       const struct nv50_disp_chan_mthd *,
-		       struct nv50_disp_root *, int chid,
-		       const struct nvkm_oclass *oclass, void *data, u32 size,
-		       struct nvkm_object **);
-int nv50_disp_ovly_new(const struct nv50_disp_dmac_func *,
-		       const struct nv50_disp_chan_mthd *,
-		       struct nv50_disp_root *, int chid,
-		       const struct nvkm_oclass *oclass, void *data, u32 size,
-		       struct nvkm_object **);
-
-extern const struct nv50_disp_dmac_oclass nv50_disp_core_oclass;
-extern const struct nv50_disp_dmac_oclass nv50_disp_base_oclass;
-extern const struct nv50_disp_dmac_oclass nv50_disp_ovly_oclass;
-
-extern const struct nv50_disp_dmac_oclass g84_disp_core_oclass;
-extern const struct nv50_disp_dmac_oclass g84_disp_base_oclass;
-extern const struct nv50_disp_dmac_oclass g84_disp_ovly_oclass;
-
-extern const struct nv50_disp_dmac_oclass g94_disp_core_oclass;
-
-extern const struct nv50_disp_dmac_oclass gt200_disp_core_oclass;
-extern const struct nv50_disp_dmac_oclass gt200_disp_base_oclass;
-extern const struct nv50_disp_dmac_oclass gt200_disp_ovly_oclass;
-
-extern const struct nv50_disp_dmac_oclass gt215_disp_core_oclass;
-extern const struct nv50_disp_dmac_oclass gt215_disp_base_oclass;
-extern const struct nv50_disp_dmac_oclass gt215_disp_ovly_oclass;
-
-extern const struct nv50_disp_dmac_oclass gf119_disp_core_oclass;
-extern const struct nv50_disp_dmac_oclass gf119_disp_base_oclass;
-extern const struct nv50_disp_dmac_oclass gf119_disp_ovly_oclass;
-
-extern const struct nv50_disp_dmac_oclass gk104_disp_core_oclass;
-extern const struct nv50_disp_dmac_oclass gk104_disp_base_oclass;
-extern const struct nv50_disp_dmac_oclass gk104_disp_ovly_oclass;
-
-extern const struct nv50_disp_dmac_oclass gk110_disp_core_oclass;
-extern const struct nv50_disp_dmac_oclass gk110_disp_base_oclass;
-
-extern const struct nv50_disp_dmac_oclass gm107_disp_core_oclass;
-
-extern const struct nv50_disp_dmac_oclass gm200_disp_core_oclass;
-
-extern const struct nv50_disp_dmac_oclass gp100_disp_core_oclass;
-
-extern const struct nv50_disp_dmac_oclass gp102_disp_core_oclass;
-extern const struct nv50_disp_dmac_oclass gp102_disp_base_oclass;
-extern const struct nv50_disp_dmac_oclass gp102_disp_ovly_oclass;
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/g84.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/g84.c
index 842e1b72ee42..731f188fc1ee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/g84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/g84.c
@@ -28,18 +28,20 @@
 
 static const struct nv50_disp_func
 g84_disp = {
+	.init = nv50_disp_init,
+	.fini = nv50_disp_fini,
 	.intr = nv50_disp_intr,
 	.uevent = &nv50_disp_chan_uevent,
 	.super = nv50_disp_super,
 	.root = &g84_disp_root_oclass,
-	.head.new = nv50_head_new,
-	.dac = { .nr = 3, .new = nv50_dac_new },
-	.sor = { .nr = 2, .new = g84_sor_new },
-	.pior = { .nr = 3, .new = nv50_pior_new },
+	.head = { .cnt = nv50_head_cnt, .new = nv50_head_new },
+	.dac = { .cnt = nv50_dac_cnt, .new = nv50_dac_new },
+	.sor = { .cnt = nv50_sor_cnt, .new = g84_sor_new },
+	.pior = { .cnt = nv50_pior_cnt, .new = nv50_pior_new },
 };
 
 int
 g84_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return nv50_disp_new_(&g84_disp, device, index, 2, pdisp);
+	return nv50_disp_new_(&g84_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/g94.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/g94.c
index d184e6ab8918..def54fe1951e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/g94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/g94.c
@@ -28,18 +28,20 @@
 
 static const struct nv50_disp_func
 g94_disp = {
+	.init = nv50_disp_init,
+	.fini = nv50_disp_fini,
 	.intr = nv50_disp_intr,
 	.uevent = &nv50_disp_chan_uevent,
 	.super = nv50_disp_super,
 	.root = &g94_disp_root_oclass,
-	.head.new = nv50_head_new,
-	.dac = { .nr = 3, .new = nv50_dac_new },
-	.sor = { .nr = 4, .new = g94_sor_new },
-	.pior = { .nr = 3, .new = nv50_pior_new },
+	.head = { .cnt = nv50_head_cnt, .new = nv50_head_new },
+	.dac = { .cnt = nv50_dac_cnt, .new = nv50_dac_new },
+	.sor = { .cnt = g94_sor_cnt, .new = g94_sor_new },
+	.pior = { .cnt = nv50_pior_cnt, .new = nv50_pior_new },
 };
 
 int
 g94_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return nv50_disp_new_(&g94_disp, device, index, 2, pdisp);
+	return nv50_disp_new_(&g94_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
index d8765b57180b..794e90982641 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
@@ -24,8 +24,12 @@
 #include "nv50.h"
 #include "head.h"
 #include "ior.h"
+#include "channv50.h"
 #include "rootnv50.h"
 
+#include <core/ramht.h>
+#include <subdev/timer.h>
+
 void
 gf119_disp_super(struct work_struct *work)
 {
@@ -164,28 +168,99 @@ gf119_disp_intr(struct nv50_disp *disp)
 	}
 }
 
+void
+gf119_disp_fini(struct nv50_disp *disp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	/* disable all interrupts */
+	nvkm_wr32(device, 0x6100b0, 0x00000000);
+}
+
 int
-gf119_disp_new_(const struct nv50_disp_func *func, struct nvkm_device *device,
-		int index, struct nvkm_disp **pdisp)
+gf119_disp_init(struct nv50_disp *disp)
 {
-	u32 heads = nvkm_rd32(device, 0x022448);
-	return nv50_disp_new_(func, device, index, heads, pdisp);
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	struct nvkm_head *head;
+	u32 tmp;
+	int i;
+
+	/* The below segments of code copying values from one register to
+	 * another appear to inform EVO of the display capabilities or
+	 * something similar.
+	 */
+
+	/* ... CRTC caps */
+	list_for_each_entry(head, &disp->base.head, head) {
+		const u32 hoff = head->id * 0x800;
+		tmp = nvkm_rd32(device, 0x616104 + hoff);
+		nvkm_wr32(device, 0x6101b4 + hoff, tmp);
+		tmp = nvkm_rd32(device, 0x616108 + hoff);
+		nvkm_wr32(device, 0x6101b8 + hoff, tmp);
+		tmp = nvkm_rd32(device, 0x61610c + hoff);
+		nvkm_wr32(device, 0x6101bc + hoff, tmp);
+	}
+
+	/* ... DAC caps */
+	for (i = 0; i < disp->dac.nr; i++) {
+		tmp = nvkm_rd32(device, 0x61a000 + (i * 0x800));
+		nvkm_wr32(device, 0x6101c0 + (i * 0x800), tmp);
+	}
+
+	/* ... SOR caps */
+	for (i = 0; i < disp->sor.nr; i++) {
+		tmp = nvkm_rd32(device, 0x61c000 + (i * 0x800));
+		nvkm_wr32(device, 0x6301c4 + (i * 0x800), tmp);
+	}
+
+	/* steal display away from vbios, or something like that */
+	if (nvkm_rd32(device, 0x6100ac) & 0x00000100) {
+		nvkm_wr32(device, 0x6100ac, 0x00000100);
+		nvkm_mask(device, 0x6194e8, 0x00000001, 0x00000000);
+		if (nvkm_msec(device, 2000,
+			if (!(nvkm_rd32(device, 0x6194e8) & 0x00000002))
+				break;
+		) < 0)
+			return -EBUSY;
+	}
+
+	/* point at display engine memory area (hash table, objects) */
+	nvkm_wr32(device, 0x610010, (disp->inst->addr >> 8) | 9);
+
+	/* enable supervisor interrupts, disable everything else */
+	nvkm_wr32(device, 0x610090, 0x00000000);
+	nvkm_wr32(device, 0x6100a0, 0x00000000);
+	nvkm_wr32(device, 0x6100b0, 0x00000307);
+
+	/* disable underflow reporting, preventing an intermittent issue
+	 * on some gk104 boards where the production vbios left this
+	 * setting enabled by default.
+	 *
+	 * ftp://download.nvidia.com/open-gpu-doc/gk104-disable-underflow-reporting/1/gk104-disable-underflow-reporting.txt
+	 */
+	list_for_each_entry(head, &disp->base.head, head) {
+		const u32 hoff = head->id * 0x800;
+		nvkm_mask(device, 0x616308 + hoff, 0x00000111, 0x00000010);
+	}
+
+	return 0;
 }
 
 static const struct nv50_disp_func
 gf119_disp = {
+	.init = gf119_disp_init,
+	.fini = gf119_disp_fini,
 	.intr = gf119_disp_intr,
 	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_super,
 	.root = &gf119_disp_root_oclass,
-	.head.new = gf119_head_new,
-	.dac = { .nr = 3, .new = gf119_dac_new },
-	.sor = { .nr = 4, .new = gf119_sor_new },
+	.head = { .cnt = gf119_head_cnt, .new = gf119_head_new },
+	.dac = { .cnt = gf119_dac_cnt, .new = gf119_dac_new },
+	.sor = { .cnt = gf119_sor_cnt, .new = gf119_sor_new },
 };
 
 int
 gf119_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return gf119_disp_new_(&gf119_disp, device, index, pdisp);
+	return nv50_disp_new_(&gf119_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk104.c
index e8fe9f315d64..4c3439b1a62d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk104.c
@@ -28,18 +28,20 @@
 
 static const struct nv50_disp_func
 gk104_disp = {
+	.init = gf119_disp_init,
+	.fini = gf119_disp_fini,
 	.intr = gf119_disp_intr,
 	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_super,
 	.root = &gk104_disp_root_oclass,
-	.head.new = gf119_head_new,
-	.dac = { .nr = 3, .new = gf119_dac_new },
-	.sor = { .nr = 4, .new = gk104_sor_new },
+	.head = { .cnt = gf119_head_cnt, .new = gf119_head_new },
+	.dac = { .cnt = gf119_dac_cnt, .new = gf119_dac_new },
+	.sor = { .cnt = gf119_sor_cnt, .new = gk104_sor_new },
 };
 
 int
 gk104_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return gf119_disp_new_(&gk104_disp, device, index, pdisp);
+	return nv50_disp_new_(&gk104_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk110.c
index 769687502e7a..bc6f4750c942 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk110.c
@@ -28,18 +28,20 @@
 
 static const struct nv50_disp_func
 gk110_disp = {
+	.init = gf119_disp_init,
+	.fini = gf119_disp_fini,
 	.intr = gf119_disp_intr,
 	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_super,
 	.root = &gk110_disp_root_oclass,
-	.head.new = gf119_head_new,
-	.dac = { .nr = 3, .new = gf119_dac_new },
-	.sor = { .nr = 4, .new = gk104_sor_new },
+	.head = { .cnt = gf119_head_cnt, .new = gf119_head_new },
+	.dac = { .cnt = gf119_dac_cnt, .new = gf119_dac_new },
+	.sor = { .cnt = gf119_sor_cnt, .new = gk104_sor_new },
 };
 
 int
 gk110_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return gf119_disp_new_(&gk110_disp, device, index, pdisp);
+	return nv50_disp_new_(&gk110_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
index ede70e5d188e..031cf6b03a76 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
@@ -28,18 +28,20 @@
 
 static const struct nv50_disp_func
 gm107_disp = {
+	.init = gf119_disp_init,
+	.fini = gf119_disp_fini,
 	.intr = gf119_disp_intr,
 	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_super,
 	.root = &gm107_disp_root_oclass,
-	.head.new = gf119_head_new,
-	.dac = { .nr = 3, .new = gf119_dac_new },
-	.sor = { .nr = 4, .new = gm107_sor_new },
+	.head = { .cnt = gf119_head_cnt, .new = gf119_head_new },
+	.dac = { .cnt = gf119_dac_cnt, .new = gf119_dac_new },
+	.sor = { .cnt = gf119_sor_cnt, .new = gm107_sor_new },
 };
 
 int
 gm107_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return gf119_disp_new_(&gm107_disp, device, index, pdisp);
+	return nv50_disp_new_(&gm107_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm200.c
index 292d3b5f9704..ec9c33a5162d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm200.c
@@ -28,18 +28,20 @@
 
 static const struct nv50_disp_func
 gm200_disp = {
+	.init = gf119_disp_init,
+	.fini = gf119_disp_fini,
 	.intr = gf119_disp_intr,
 	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_super,
 	.root = &gm200_disp_root_oclass,
-	.head.new = gf119_head_new,
-	.dac = { .nr = 3, .new = gf119_dac_new },
-	.sor = { .nr = 4, .new = gm200_sor_new },
+	.head = { .cnt = gf119_head_cnt, .new = gf119_head_new },
+	.dac = { .cnt = gf119_dac_cnt, .new = gf119_dac_new },
+	.sor = { .cnt = gf119_sor_cnt, .new = gm200_sor_new },
 };
 
 int
 gm200_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return gf119_disp_new_(&gm200_disp, device, index, pdisp);
+	return nv50_disp_new_(&gm200_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp100.c
index 39eb98b2c3a2..fd6216684f6d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp100.c
@@ -28,17 +28,19 @@
 
 static const struct nv50_disp_func
 gp100_disp = {
+	.init = gf119_disp_init,
+	.fini = gf119_disp_fini,
 	.intr = gf119_disp_intr,
 	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_super,
 	.root = &gp100_disp_root_oclass,
-	.head.new = gf119_head_new,
-	.sor = { .nr = 4, .new = gm200_sor_new },
+	.head = { .cnt = gf119_head_cnt, .new = gf119_head_new },
+	.sor = { .cnt = gf119_sor_cnt, .new = gm200_sor_new },
 };
 
 int
 gp100_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return gf119_disp_new_(&gp100_disp, device, index, pdisp);
+	return nv50_disp_new_(&gp100_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp102.c
index 91d70fe18275..3468ddec1270 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp102.c
@@ -24,6 +24,7 @@
 #include "nv50.h"
 #include "head.h"
 #include "ior.h"
+#include "channv50.h"
 #include "rootnv50.h"
 
 static void
@@ -54,17 +55,19 @@ gp102_disp_intr_error(struct nv50_disp *disp, int chid)
 
 static const struct nv50_disp_func
 gp102_disp = {
+	.init = gf119_disp_init,
+	.fini = gf119_disp_fini,
 	.intr = gf119_disp_intr,
 	.intr_error = gp102_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_super,
 	.root = &gp102_disp_root_oclass,
-	.head.new = gf119_head_new,
-	.sor = { .nr = 4, .new = gm200_sor_new },
+	.head = { .cnt = gf119_head_cnt, .new = gf119_head_new },
+	.sor = { .cnt = gf119_sor_cnt, .new = gm200_sor_new },
 };
 
 int
 gp102_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return gf119_disp_new_(&gp102_disp, device, index, pdisp);
+	return nv50_disp_new_(&gp102_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt200.c
index bf00c4e3be3a..f80183701f44 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt200.c
@@ -28,18 +28,20 @@
 
 static const struct nv50_disp_func
 gt200_disp = {
+	.init = nv50_disp_init,
+	.fini = nv50_disp_fini,
 	.intr = nv50_disp_intr,
 	.uevent = &nv50_disp_chan_uevent,
 	.super = nv50_disp_super,
 	.root = &gt200_disp_root_oclass,
-	.head.new = nv50_head_new,
-	.dac = { .nr = 3, .new = nv50_dac_new },
-	.sor = { .nr = 2, .new = g84_sor_new },
-	.pior = { .nr = 3, .new = nv50_pior_new },
+	.head = { .cnt = nv50_head_cnt, .new = nv50_head_new },
+	.dac = { .cnt = nv50_dac_cnt, .new = nv50_dac_new },
+	.sor = { .cnt = nv50_sor_cnt, .new = g84_sor_new },
+	.pior = { .cnt = nv50_pior_cnt, .new = nv50_pior_new },
 };
 
 int
 gt200_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return nv50_disp_new_(&gt200_disp, device, index, 2, pdisp);
+	return nv50_disp_new_(&gt200_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt215.c
index 2cdd4d7a98d3..7581efc1357e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt215.c
@@ -28,18 +28,20 @@
 
 static const struct nv50_disp_func
 gt215_disp = {
+	.init = nv50_disp_init,
+	.fini = nv50_disp_fini,
 	.intr = nv50_disp_intr,
 	.uevent = &nv50_disp_chan_uevent,
 	.super = nv50_disp_super,
 	.root = &gt215_disp_root_oclass,
-	.head.new = nv50_head_new,
-	.dac = { .nr = 3, .new = nv50_dac_new },
-	.sor = { .nr = 4, .new = gt215_sor_new },
-	.pior = { .nr = 3, .new = nv50_pior_new },
+	.head = { .cnt = nv50_head_cnt, .new = nv50_head_new },
+	.dac = { .cnt = nv50_dac_cnt, .new = nv50_dac_new },
+	.sor = { .cnt = g94_sor_cnt, .new = gt215_sor_new },
+	.pior = { .cnt = nv50_pior_cnt, .new = nv50_pior_new },
 };
 
 int
 gt215_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return nv50_disp_new_(&gt215_disp, device, index, 2, pdisp);
+	return nv50_disp_new_(&gt215_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c
new file mode 100644
index 000000000000..d0a7e3456da1
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c
@@ -0,0 +1,427 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "nv50.h"
+#include "head.h"
+#include "ior.h"
+#include "channv50.h"
+#include "rootnv50.h"
+
+#include <core/gpuobj.h>
+#include <subdev/timer.h>
+
+static int
+gv100_disp_wndw_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = nvkm_rd32(device, 0x610064);
+	return (nvkm_rd32(device, 0x610074) & 0x03f00000) >> 20;
+}
+
+static void
+gv100_disp_super(struct work_struct *work)
+{
+	struct nv50_disp *disp =
+		container_of(work, struct nv50_disp, supervisor);
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_head *head;
+	u32 stat = nvkm_rd32(device, 0x6107a8);
+	u32 mask[4];
+
+	nvkm_debug(subdev, "supervisor %d: %08x\n", ffs(disp->super), stat);
+	list_for_each_entry(head, &disp->base.head, head) {
+		mask[head->id] = nvkm_rd32(device, 0x6107ac + (head->id * 4));
+		HEAD_DBG(head, "%08x", mask[head->id]);
+	}
+
+	if (disp->super & 0x00000001) {
+		nv50_disp_chan_mthd(disp->chan[0], NV_DBG_DEBUG);
+		nv50_disp_super_1(disp);
+		list_for_each_entry(head, &disp->base.head, head) {
+			if (!(mask[head->id] & 0x00001000))
+				continue;
+			nv50_disp_super_1_0(disp, head);
+		}
+	} else
+	if (disp->super & 0x00000002) {
+		list_for_each_entry(head, &disp->base.head, head) {
+			if (!(mask[head->id] & 0x00001000))
+				continue;
+			nv50_disp_super_2_0(disp, head);
+		}
+		nvkm_outp_route(&disp->base);
+		list_for_each_entry(head, &disp->base.head, head) {
+			if (!(mask[head->id] & 0x00010000))
+				continue;
+			nv50_disp_super_2_1(disp, head);
+		}
+		list_for_each_entry(head, &disp->base.head, head) {
+			if (!(mask[head->id] & 0x00001000))
+				continue;
+			nv50_disp_super_2_2(disp, head);
+		}
+	} else
+	if (disp->super & 0x00000004) {
+		list_for_each_entry(head, &disp->base.head, head) {
+			if (!(mask[head->id] & 0x00001000))
+				continue;
+			nv50_disp_super_3_0(disp, head);
+		}
+	}
+
+	list_for_each_entry(head, &disp->base.head, head)
+		nvkm_wr32(device, 0x6107ac + (head->id * 4), 0x00000000);
+	nvkm_wr32(device, 0x6107a8, 0x80000000);
+}
+
+static void
+gv100_disp_exception(struct nv50_disp *disp, int chid)
+{
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 stat = nvkm_rd32(device, 0x611020 + (chid * 12));
+	u32 type = (stat & 0x00007000) >> 12;
+	u32 mthd = (stat & 0x00000fff) << 2;
+	u32 data = nvkm_rd32(device, 0x611024 + (chid * 12));
+	u32 code = nvkm_rd32(device, 0x611028 + (chid * 12));
+
+	nvkm_error(subdev, "chid %d %08x [type %d mthd %04x] "
+			   "data %08x code %08x\n",
+		   chid, stat, type, mthd, data, code);
+
+	if (chid < ARRAY_SIZE(disp->chan) && disp->chan[chid]) {
+		switch (mthd) {
+		case 0x0200:
+			nv50_disp_chan_mthd(disp->chan[chid], NV_DBG_ERROR);
+			break;
+		default:
+			break;
+		}
+	}
+
+	nvkm_wr32(device, 0x611020 + (chid * 12), 0x90000000);
+}
+
+static void
+gv100_disp_intr_ctrl_disp(struct nv50_disp *disp)
+{
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 stat = nvkm_rd32(device, 0x611c30);
+
+	if (stat & 0x00000007) {
+		disp->super = (stat & 0x00000007);
+		queue_work(disp->wq, &disp->supervisor);
+		nvkm_wr32(device, 0x611860, disp->super);
+		stat &= ~0x00000007;
+	}
+
+	/*TODO: I would guess this is VBIOS_RELEASE, however, NFI how to
+	 *      ACK it, nor does RM appear to bother.
+	 */
+	if (stat & 0x00000008)
+		stat &= ~0x00000008;
+
+	if (stat & 0x00000100) {
+		unsigned long wndws = nvkm_rd32(device, 0x611858);
+		unsigned long other = nvkm_rd32(device, 0x61185c);
+		int wndw;
+
+		nvkm_wr32(device, 0x611858, wndws);
+		nvkm_wr32(device, 0x61185c, other);
+
+		/* AWAKEN_OTHER_CORE. */
+		if (other & 0x00000001)
+			nv50_disp_chan_uevent_send(disp, 0);
+
+		/* AWAKEN_WIN_CH(n). */
+		for_each_set_bit(wndw, &wndws, disp->wndw.nr) {
+			nv50_disp_chan_uevent_send(disp, 1 + wndw);
+		}
+	}
+
+	if (stat)
+		nvkm_warn(subdev, "ctrl %08x\n", stat);
+}
+
+static void
+gv100_disp_intr_exc_other(struct nv50_disp *disp)
+{
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 stat = nvkm_rd32(device, 0x611854);
+	unsigned long mask;
+	int head;
+
+	if (stat & 0x00000001) {
+		nvkm_wr32(device, 0x611854, 0x00000001);
+		gv100_disp_exception(disp, 0);
+		stat &= ~0x00000001;
+	}
+
+	if ((mask = (stat & 0x00ff0000) >> 16)) {
+		for_each_set_bit(head, &mask, disp->wndw.nr) {
+			nvkm_wr32(device, 0x611854, 0x00010000 << head);
+			gv100_disp_exception(disp, 73 + head);
+			stat &= ~(0x00010000 << head);
+		}
+	}
+
+	if (stat) {
+		nvkm_warn(subdev, "exception %08x\n", stat);
+		nvkm_wr32(device, 0x611854, stat);
+	}
+}
+
+static void
+gv100_disp_intr_exc_winim(struct nv50_disp *disp)
+{
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	unsigned long stat = nvkm_rd32(device, 0x611850);
+	int wndw;
+
+	for_each_set_bit(wndw, &stat, disp->wndw.nr) {
+		nvkm_wr32(device, 0x611850, BIT(wndw));
+		gv100_disp_exception(disp, 33 + wndw);
+		stat &= ~BIT(wndw);
+	}
+
+	if (stat) {
+		nvkm_warn(subdev, "wimm %08x\n", (u32)stat);
+		nvkm_wr32(device, 0x611850, stat);
+	}
+}
+
+static void
+gv100_disp_intr_exc_win(struct nv50_disp *disp)
+{
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	unsigned long stat = nvkm_rd32(device, 0x61184c);
+	int wndw;
+
+	for_each_set_bit(wndw, &stat, disp->wndw.nr) {
+		nvkm_wr32(device, 0x61184c, BIT(wndw));
+		gv100_disp_exception(disp, 1 + wndw);
+		stat &= ~BIT(wndw);
+	}
+
+	if (stat) {
+		nvkm_warn(subdev, "wndw %08x\n", (u32)stat);
+		nvkm_wr32(device, 0x61184c, stat);
+	}
+}
+
+static void
+gv100_disp_intr_head_timing(struct nv50_disp *disp, int head)
+{
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 stat = nvkm_rd32(device, 0x611800 + (head * 0x04));
+
+	/* LAST_DATA, LOADV. */
+	if (stat & 0x00000003) {
+		nvkm_wr32(device, 0x611800 + (head * 0x04), stat & 0x00000003);
+		stat &= ~0x00000003;
+	}
+
+	if (stat & 0x00000004) {
+		nvkm_disp_vblank(&disp->base, head);
+		nvkm_wr32(device, 0x611800 + (head * 0x04), 0x00000004);
+		stat &= ~0x00000004;
+	}
+
+	if (stat) {
+		nvkm_warn(subdev, "head %08x\n", stat);
+		nvkm_wr32(device, 0x611800 + (head * 0x04), stat);
+	}
+}
+
+static void
+gv100_disp_intr(struct nv50_disp *disp)
+{
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 stat = nvkm_rd32(device, 0x611ec0);
+	unsigned long mask;
+	int head;
+
+	if ((mask = (stat & 0x000000ff))) {
+		for_each_set_bit(head, &mask, 8) {
+			gv100_disp_intr_head_timing(disp, head);
+			stat &= ~BIT(head);
+		}
+	}
+
+	if (stat & 0x00000200) {
+		gv100_disp_intr_exc_win(disp);
+		stat &= ~0x00000200;
+	}
+
+	if (stat & 0x00000400) {
+		gv100_disp_intr_exc_winim(disp);
+		stat &= ~0x00000400;
+	}
+
+	if (stat & 0x00000800) {
+		gv100_disp_intr_exc_other(disp);
+		stat &= ~0x00000800;
+	}
+
+	if (stat & 0x00001000) {
+		gv100_disp_intr_ctrl_disp(disp);
+		stat &= ~0x00001000;
+	}
+
+	if (stat)
+		nvkm_warn(subdev, "intr %08x\n", stat);
+}
+
+static void
+gv100_disp_fini(struct nv50_disp *disp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	nvkm_wr32(device, 0x611db0, 0x00000000);
+}
+
+static int
+gv100_disp_init(struct nv50_disp *disp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	struct nvkm_head *head;
+	int i, j;
+	u32 tmp;
+
+	/* Claim ownership of display. */
+	if (nvkm_rd32(device, 0x6254e8) & 0x00000002) {
+		nvkm_mask(device, 0x6254e8, 0x00000001, 0x00000000);
+		if (nvkm_msec(device, 2000,
+			if (!(nvkm_rd32(device, 0x6254e8) & 0x00000002))
+				break;
+		) < 0)
+			return -EBUSY;
+	}
+
+	/* Lock pin capabilities. */
+	tmp = nvkm_rd32(device, 0x610068);
+	nvkm_wr32(device, 0x640008, tmp);
+
+	/* SOR capabilities. */
+	for (i = 0; i < disp->sor.nr; i++) {
+		tmp = nvkm_rd32(device, 0x61c000 + (i * 0x800));
+		nvkm_mask(device, 0x640000, 0x00000100 << i, 0x00000100 << i);
+		nvkm_wr32(device, 0x640144 + (i * 0x08), tmp);
+	}
+
+	/* Head capabilities. */
+	list_for_each_entry(head, &disp->base.head, head) {
+		const int id = head->id;
+
+		/* RG. */
+		tmp = nvkm_rd32(device, 0x616300 + (id * 0x800));
+		nvkm_wr32(device, 0x640048 + (id * 0x020), tmp);
+
+		/* POSTCOMP. */
+		for (j = 0; j < 6 * 4; j += 4) {
+			tmp = nvkm_rd32(device, 0x616100 + (id * 0x800) + j);
+			nvkm_wr32(device, 0x640030 + (id * 0x20) + j, tmp);
+		}
+	}
+
+	/* Window capabilities. */
+	for (i = 0; i < disp->wndw.nr; i++) {
+		nvkm_mask(device, 0x640004, 1 << i, 1 << i);
+		for (j = 0; j < 6 * 4; j += 4) {
+			tmp = nvkm_rd32(device, 0x630050 + (i * 0x800) + j);
+			nvkm_wr32(device, 0x6401e4 + (i * 0x20) + j, tmp);
+		}
+	}
+
+	/* IHUB capabilities. */
+	for (i = 0; i < 4; i++) {
+		tmp = nvkm_rd32(device, 0x62e000 + (i * 0x04));
+		nvkm_wr32(device, 0x640010 + (i * 0x04), tmp);
+	}
+
+	nvkm_mask(device, 0x610078, 0x00000001, 0x00000001);
+
+	/* Setup instance memory. */
+	switch (nvkm_memory_target(disp->inst->memory)) {
+	case NVKM_MEM_TARGET_VRAM: tmp = 0x00000001; break;
+	case NVKM_MEM_TARGET_NCOH: tmp = 0x00000002; break;
+	case NVKM_MEM_TARGET_HOST: tmp = 0x00000003; break;
+	default:
+		break;
+	}
+	nvkm_wr32(device, 0x610010, 0x00000008 | tmp);
+	nvkm_wr32(device, 0x610014, disp->inst->addr >> 16);
+
+	/* CTRL_DISP: AWAKEN, ERROR, SUPERVISOR[1-3]. */
+	nvkm_wr32(device, 0x611cf0, 0x00000187); /* MSK. */
+	nvkm_wr32(device, 0x611db0, 0x00000187); /* EN. */
+
+	/* EXC_OTHER: CURSn, CORE. */
+	nvkm_wr32(device, 0x611cec, disp->head.mask << 16 |
+				    0x00000001); /* MSK. */
+	nvkm_wr32(device, 0x611dac, 0x00000000); /* EN. */
+
+	/* EXC_WINIM. */
+	nvkm_wr32(device, 0x611ce8, disp->wndw.mask); /* MSK. */
+	nvkm_wr32(device, 0x611da8, 0x00000000); /* EN. */
+
+	/* EXC_WIN. */
+	nvkm_wr32(device, 0x611ce4, disp->wndw.mask); /* MSK. */
+	nvkm_wr32(device, 0x611da4, 0x00000000); /* EN. */
+
+	/* HEAD_TIMING(n): VBLANK. */
+	list_for_each_entry(head, &disp->base.head, head) {
+		const u32 hoff = head->id * 4;
+		nvkm_wr32(device, 0x611cc0 + hoff, 0x00000004); /* MSK. */
+		nvkm_wr32(device, 0x611d80 + hoff, 0x00000000); /* EN. */
+	}
+
+	/* OR. */
+	nvkm_wr32(device, 0x611cf4, 0x00000000); /* MSK. */
+	nvkm_wr32(device, 0x611db4, 0x00000000); /* EN. */
+	return 0;
+}
+
+static const struct nv50_disp_func
+gv100_disp = {
+	.init = gv100_disp_init,
+	.fini = gv100_disp_fini,
+	.intr = gv100_disp_intr,
+	.uevent = &gv100_disp_chan_uevent,
+	.super = gv100_disp_super,
+	.root = &gv100_disp_root_oclass,
+	.wndw = { .cnt = gv100_disp_wndw_cnt },
+	.head = { .cnt = gv100_head_cnt, .new = gv100_head_new },
+	.sor = { .cnt = gv100_sor_cnt, .new = gv100_sor_new },
+	.ramht_size = 0x2000,
+};
+
+int
+gv100_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
+{
+	return nv50_disp_new_(&gv100_disp, device, index, pdisp);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c
new file mode 100644
index 000000000000..6e3c450eaace
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c
@@ -0,0 +1,85 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "hdmi.h"
+
+void
+gv100_hdmi_ctrl(struct nvkm_ior *ior, int head, bool enable, u8 max_ac_packet,
+		u8 rekey, u8 *avi, u8 avi_size, u8 *vendor, u8 vendor_size)
+{
+	struct nvkm_device *device = ior->disp->engine.subdev.device;
+	const u32 ctrl = 0x40000000 * enable |
+			 max_ac_packet << 16 |
+			 rekey;
+	const u32 hoff = head * 0x800;
+	const u32 hdmi = head * 0x400;
+	struct packed_hdmi_infoframe avi_infoframe;
+	struct packed_hdmi_infoframe vendor_infoframe;
+
+	pack_hdmi_infoframe(&avi_infoframe, avi, avi_size);
+	pack_hdmi_infoframe(&vendor_infoframe, vendor, vendor_size);
+
+	if (!(ctrl & 0x40000000)) {
+		nvkm_mask(device, 0x6165c0 + hoff, 0x40000000, 0x00000000);
+		nvkm_mask(device, 0x6f0100 + hdmi, 0x00000001, 0x00000000);
+		nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000000);
+		nvkm_mask(device, 0x6f0000 + hdmi, 0x00000001, 0x00000000);
+		return;
+	}
+
+	/* AVI InfoFrame (AVI). */
+	nvkm_mask(device, 0x6f0000 + hdmi, 0x00000001, 0x00000000);
+	if (avi_size) {
+		nvkm_wr32(device, 0x6f0008 + hdmi, avi_infoframe.header);
+		nvkm_wr32(device, 0x6f000c + hdmi, avi_infoframe.subpack0_low);
+		nvkm_wr32(device, 0x6f0010 + hdmi, avi_infoframe.subpack0_high);
+		nvkm_wr32(device, 0x6f0014 + hdmi, avi_infoframe.subpack1_low);
+		nvkm_wr32(device, 0x6f0018 + hdmi, avi_infoframe.subpack1_high);
+		nvkm_mask(device, 0x6f0000 + hdmi, 0x00000001, 0x00000001);
+	}
+
+	/* Vendor-specific InfoFrame (VSI). */
+	nvkm_mask(device, 0x6f0100 + hdmi, 0x00010001, 0x00000000);
+	if (vendor_size) {
+		nvkm_wr32(device, 0x6f0108 + hdmi, vendor_infoframe.header);
+		nvkm_wr32(device, 0x6f010c + hdmi, vendor_infoframe.subpack0_low);
+		nvkm_wr32(device, 0x6f0110 + hdmi, vendor_infoframe.subpack0_high);
+		nvkm_wr32(device, 0x6f0110 + hdmi, 0x00000000);
+		nvkm_wr32(device, 0x6f0114 + hdmi, 0x00000000);
+		nvkm_wr32(device, 0x6f0118 + hdmi, 0x00000000);
+		nvkm_wr32(device, 0x6f011c + hdmi, 0x00000000);
+		nvkm_wr32(device, 0x6f0120 + hdmi, 0x00000000);
+		nvkm_wr32(device, 0x6f0124 + hdmi, 0x00000000);
+		nvkm_mask(device, 0x6f0100 + hdmi, 0x00000001, 0x00000001);
+	}
+
+
+	/* General Control (GCP). */
+	nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000000);
+	nvkm_wr32(device, 0x6f00cc + hdmi, 0x00000010);
+	nvkm_mask(device, 0x6f00c0 + hdmi, 0x00000001, 0x00000001);
+
+	/* Audio Clock Regeneration (ACR). */
+	nvkm_wr32(device, 0x6f0080 + hdmi, 0x82000000);
+
+	/* NV_PDISP_SF_HDMI_CTRL. */
+	nvkm_mask(device, 0x6165c0 + hoff, 0x401f007f, ctrl);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h
index 57030b3a4a75..7d55faf52fcb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/head.h
@@ -52,6 +52,14 @@ void nv50_head_rgpos(struct nvkm_head *, u16 *, u16 *);
 #define HEAD_DBG(h,f,a...) HEAD_MSG((h), debug, f, ##a)
 
 int nv04_head_new(struct nvkm_disp *, int id);
+
+int nv50_head_cnt(struct nvkm_disp *, unsigned long *);
 int nv50_head_new(struct nvkm_disp *, int id);
+
+int gf119_head_cnt(struct nvkm_disp *, unsigned long *);
 int gf119_head_new(struct nvkm_disp *, int id);
+void gf119_head_rgclk(struct nvkm_head *, int);
+
+int gv100_head_cnt(struct nvkm_disp *, unsigned long *);
+int gv100_head_new(struct nvkm_disp *, int id);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/headgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/headgf119.c
index 9fd7ae331308..e86298b35902 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/headgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/headgf119.c
@@ -39,7 +39,7 @@ gf119_head_vblank_get(struct nvkm_head *head)
 	nvkm_mask(device, 0x6100c0 + hoff, 0x00000001, 0x00000001);
 }
 
-static void
+void
 gf119_head_rgclk(struct nvkm_head *head, int div)
 {
 	struct nvkm_device *device = head->disp->engine.subdev.device;
@@ -92,8 +92,13 @@ gf119_head = {
 int
 gf119_head_new(struct nvkm_disp *disp, int id)
 {
-	struct nvkm_device *device = disp->engine.subdev.device;
-	if (!(nvkm_rd32(device, 0x612004) & (0x00000001 << id)))
-		return 0;
 	return nvkm_head_new_(&gf119_head, disp, id);
 }
+
+int
+gf119_head_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = nvkm_rd32(device, 0x612004) & 0x0000000f;
+	return nvkm_rd32(device, 0x022448);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/headgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/headgv100.c
new file mode 100644
index 000000000000..1a061b42ae5c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/headgv100.c
@@ -0,0 +1,105 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "head.h"
+
+static void
+gv100_head_vblank_put(struct nvkm_head *head)
+{
+	struct nvkm_device *device = head->disp->engine.subdev.device;
+	nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000004, 0x00000000);
+}
+
+static void
+gv100_head_vblank_get(struct nvkm_head *head)
+{
+	struct nvkm_device *device = head->disp->engine.subdev.device;
+	nvkm_mask(device, 0x611d80 + (head->id * 4), 0x00000004, 0x00000004);
+}
+
+static void
+gv100_head_rgpos(struct nvkm_head *head, u16 *hline, u16 *vline)
+{
+	struct nvkm_device *device = head->disp->engine.subdev.device;
+	const u32 hoff = head->id * 0x800;
+	/* vline read locks hline. */
+	*vline = nvkm_rd32(device, 0x616330 + hoff) & 0x0000ffff;
+	*hline = nvkm_rd32(device, 0x616334 + hoff) & 0x0000ffff;
+}
+
+static void
+gv100_head_state(struct nvkm_head *head, struct nvkm_head_state *state)
+{
+	struct nvkm_device *device = head->disp->engine.subdev.device;
+	const u32 hoff = (state == &head->arm) * 0x8000 + head->id * 0x400;
+	u32 data;
+
+	data = nvkm_rd32(device, 0x682064 + hoff);
+	state->vtotal = (data & 0xffff0000) >> 16;
+	state->htotal = (data & 0x0000ffff);
+	data = nvkm_rd32(device, 0x682068 + hoff);
+	state->vsynce = (data & 0xffff0000) >> 16;
+	state->hsynce = (data & 0x0000ffff);
+	data = nvkm_rd32(device, 0x68206c + hoff);
+	state->vblanke = (data & 0xffff0000) >> 16;
+	state->hblanke = (data & 0x0000ffff);
+	data = nvkm_rd32(device, 0x682070 + hoff);
+	state->vblanks = (data & 0xffff0000) >> 16;
+	state->hblanks = (data & 0x0000ffff);
+	state->hz = nvkm_rd32(device, 0x68200c + hoff);
+
+	data = nvkm_rd32(device, 0x682004 + hoff);
+	switch ((data & 0x000000f0) >> 4) {
+	case 5: state->or.depth = 30; break;
+	case 4: state->or.depth = 24; break;
+	case 1: state->or.depth = 18; break;
+	default:
+		state->or.depth = 18;
+		WARN_ON(1);
+		break;
+	}
+}
+
+static const struct nvkm_head_func
+gv100_head = {
+	.state = gv100_head_state,
+	.rgpos = gv100_head_rgpos,
+	.rgclk = gf119_head_rgclk,
+	.vblank_get = gv100_head_vblank_get,
+	.vblank_put = gv100_head_vblank_put,
+};
+
+int
+gv100_head_new(struct nvkm_disp *disp, int id)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	if (!(nvkm_rd32(device, 0x610060) & (0x00000001 << id)))
+		return 0;
+	return nvkm_head_new_(&gv100_head, disp, id);
+}
+
+int
+gv100_head_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = nvkm_rd32(device, 0x610060) & 0x000000ff;
+	return nvkm_rd32(device, 0x610074) & 0x0000000f;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/headnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/headnv50.c
index c80d06d5168f..e7d5c397cd29 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/headnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/headnv50.c
@@ -90,3 +90,10 @@ nv50_head_new(struct nvkm_disp *disp, int id)
 {
 	return nvkm_head_new_(&nv50_head, disp, id);
 }
+
+int
+nv50_head_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	*pmask = 3;
+	return 2;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
index 4548c031b937..e0b4e0c5704e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
@@ -30,7 +30,7 @@ struct nvkm_ior {
 			UNKNOWN
 		} proto:3;
 		unsigned link:2;
-		unsigned head:4;
+		unsigned head:8;
 	} arm, asy;
 
 	/* Armed DP state. */
@@ -106,7 +106,6 @@ nv50_sor_link(struct nvkm_ior *ior)
 	return nv50_ior_base(ior) + ((ior->asy.link == 2) * 0x80);
 }
 
-int nv50_sor_new_(const struct nvkm_ior_func *, struct nvkm_disp *, int id);
 void nv50_sor_state(struct nvkm_ior *, struct nvkm_ior_state *);
 void nv50_sor_power(struct nvkm_ior *, bool, bool, bool, bool, bool);
 void nv50_sor_clock(struct nvkm_ior *);
@@ -122,7 +121,6 @@ void g94_sor_dp_watermark(struct nvkm_ior *, int, u8);
 
 void gt215_sor_dp_audio(struct nvkm_ior *, int, bool);
 
-int gf119_sor_new_(const struct nvkm_ior_func *, struct nvkm_disp *, int id);
 void gf119_sor_state(struct nvkm_ior *, struct nvkm_ior_state *);
 void gf119_sor_clock(struct nvkm_ior *);
 int gf119_sor_dp_links(struct nvkm_ior *, struct nvkm_i2c_aux *);
@@ -135,10 +133,15 @@ void gf119_sor_dp_watermark(struct nvkm_ior *, int, u8);
 
 void gm107_sor_dp_pattern(struct nvkm_ior *, int);
 
+void gm200_sor_route_set(struct nvkm_outp *, struct nvkm_ior *);
+int gm200_sor_route_get(struct nvkm_outp *, int *);
+void gm200_sor_dp_drive(struct nvkm_ior *, int, int, int, int, int);
+
 void g84_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
 void gt215_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
 void gf119_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
 void gk104_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
+void gv100_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
 
 void gt215_hda_hpd(struct nvkm_ior *, int, bool);
 void gt215_hda_eld(struct nvkm_ior *, u8 *, u8);
@@ -153,19 +156,34 @@ void gf119_hda_eld(struct nvkm_ior *, u8 *, u8);
 #define IOR_WARN(i,f,a...) IOR_MSG((i), warn, f, ##a)
 #define IOR_DBG(i,f,a...) IOR_MSG((i), debug, f, ##a)
 
+int nv50_dac_cnt(struct nvkm_disp *, unsigned long *);
 int nv50_dac_new(struct nvkm_disp *, int);
+
+int gf119_dac_cnt(struct nvkm_disp *, unsigned long *);
 int gf119_dac_new(struct nvkm_disp *, int);
 
+int nv50_pior_cnt(struct nvkm_disp *, unsigned long *);
 int nv50_pior_new(struct nvkm_disp *, int);
 
+int nv50_sor_cnt(struct nvkm_disp *, unsigned long *);
 int nv50_sor_new(struct nvkm_disp *, int);
+
 int g84_sor_new(struct nvkm_disp *, int);
+
+int g94_sor_cnt(struct nvkm_disp *, unsigned long *);
 int g94_sor_new(struct nvkm_disp *, int);
+
 int mcp77_sor_new(struct nvkm_disp *, int);
 int gt215_sor_new(struct nvkm_disp *, int);
 int mcp89_sor_new(struct nvkm_disp *, int);
+
+int gf119_sor_cnt(struct nvkm_disp *, unsigned long *);
 int gf119_sor_new(struct nvkm_disp *, int);
+
 int gk104_sor_new(struct nvkm_disp *, int);
 int gm107_sor_new(struct nvkm_disp *, int);
 int gm200_sor_new(struct nvkm_disp *, int);
+
+int gv100_sor_cnt(struct nvkm_disp *, unsigned long *);
+int gv100_sor_new(struct nvkm_disp *, int);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp77.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp77.c
index d7e0fbb12bf1..cfdce23ab83a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp77.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp77.c
@@ -26,18 +26,20 @@
 
 static const struct nv50_disp_func
 mcp77_disp = {
+	.init = nv50_disp_init,
+	.fini = nv50_disp_fini,
 	.intr = nv50_disp_intr,
 	.uevent = &nv50_disp_chan_uevent,
 	.super = nv50_disp_super,
 	.root = &g94_disp_root_oclass,
-	.head.new = nv50_head_new,
-	.dac = { .nr = 3, .new = nv50_dac_new },
-	.sor = { .nr = 4, .new = mcp77_sor_new },
-	.pior = { .nr = 3, .new = nv50_pior_new },
+	.head = { .cnt = nv50_head_cnt, .new = nv50_head_new },
+	.dac = { .cnt = nv50_dac_cnt, .new = nv50_dac_new },
+	.sor = { .cnt = g94_sor_cnt, .new = mcp77_sor_new },
+	.pior = { .cnt = nv50_pior_cnt, .new = nv50_pior_new },
 };
 
 int
 mcp77_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return nv50_disp_new_(&mcp77_disp, device, index, 2, pdisp);
+	return nv50_disp_new_(&mcp77_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp89.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp89.c
index 7b75c57c12ed..85d9329cfa0e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp89.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/mcp89.c
@@ -26,18 +26,20 @@
 
 static const struct nv50_disp_func
 mcp89_disp = {
+	.init = nv50_disp_init,
+	.fini = nv50_disp_fini,
 	.intr = nv50_disp_intr,
 	.uevent = &nv50_disp_chan_uevent,
 	.super = nv50_disp_super,
 	.root = &gt215_disp_root_oclass,
-	.head.new = nv50_head_new,
-	.dac = { .nr = 3, .new = nv50_dac_new },
-	.sor = { .nr = 4, .new = mcp89_sor_new },
-	.pior = { .nr = 3, .new = nv50_pior_new },
+	.head = { .cnt = nv50_head_cnt, .new = nv50_head_new },
+	.dac = { .cnt = nv50_dac_cnt, .new = nv50_dac_new },
+	.sor = { .cnt = g94_sor_cnt, .new = mcp89_sor_new },
+	.pior = { .cnt = nv50_pior_cnt, .new = nv50_pior_new },
 };
 
 int
 mcp89_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return nv50_disp_new_(&mcp89_disp, device, index, 2, pdisp);
+	return nv50_disp_new_(&mcp89_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
index 0c570dbd3021..f89c7b977aa5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
@@ -24,11 +24,12 @@
 #include "nv50.h"
 #include "head.h"
 #include "ior.h"
+#include "channv50.h"
 #include "rootnv50.h"
 
 #include <core/client.h>
 #include <core/enum.h>
-#include <core/gpuobj.h>
+#include <core/ramht.h>
 #include <subdev/bios.h>
 #include <subdev/bios/disp.h>
 #include <subdev/bios/init.h>
@@ -49,29 +50,115 @@ nv50_disp_intr_(struct nvkm_disp *base)
 	disp->func->intr(disp);
 }
 
+static void
+nv50_disp_fini_(struct nvkm_disp *base)
+{
+	struct nv50_disp *disp = nv50_disp(base);
+	disp->func->fini(disp);
+}
+
+static int
+nv50_disp_init_(struct nvkm_disp *base)
+{
+	struct nv50_disp *disp = nv50_disp(base);
+	return disp->func->init(disp);
+}
+
 static void *
 nv50_disp_dtor_(struct nvkm_disp *base)
 {
 	struct nv50_disp *disp = nv50_disp(base);
+
+	nvkm_ramht_del(&disp->ramht);
+	nvkm_gpuobj_del(&disp->inst);
+
 	nvkm_event_fini(&disp->uevent);
 	if (disp->wq)
 		destroy_workqueue(disp->wq);
+
 	return disp;
 }
 
+static int
+nv50_disp_oneinit_(struct nvkm_disp *base)
+{
+	struct nv50_disp *disp = nv50_disp(base);
+	const struct nv50_disp_func *func = disp->func;
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	int ret, i;
+
+	if (func->wndw.cnt) {
+		disp->wndw.nr = func->wndw.cnt(&disp->base, &disp->wndw.mask);
+		nvkm_debug(subdev, "Window(s): %d (%08lx)\n",
+			   disp->wndw.nr, disp->wndw.mask);
+	}
+
+	disp->head.nr = func->head.cnt(&disp->base, &disp->head.mask);
+	nvkm_debug(subdev, "  Head(s): %d (%02lx)\n",
+		   disp->head.nr, disp->head.mask);
+	for_each_set_bit(i, &disp->head.mask, disp->head.nr) {
+		ret = func->head.new(&disp->base, i);
+		if (ret)
+			return ret;
+	}
+
+	if (func->dac.cnt) {
+		disp->dac.nr = func->dac.cnt(&disp->base, &disp->dac.mask);
+		nvkm_debug(subdev, "   DAC(s): %d (%02lx)\n",
+			   disp->dac.nr, disp->dac.mask);
+		for_each_set_bit(i, &disp->dac.mask, disp->dac.nr) {
+			ret = func->dac.new(&disp->base, i);
+			if (ret)
+				return ret;
+		}
+	}
+
+	if (func->pior.cnt) {
+		disp->pior.nr = func->pior.cnt(&disp->base, &disp->pior.mask);
+		nvkm_debug(subdev, "  PIOR(s): %d (%02lx)\n",
+			   disp->pior.nr, disp->pior.mask);
+		for_each_set_bit(i, &disp->pior.mask, disp->pior.nr) {
+			ret = func->pior.new(&disp->base, i);
+			if (ret)
+				return ret;
+		}
+	}
+
+	disp->sor.nr = func->sor.cnt(&disp->base, &disp->sor.mask);
+	nvkm_debug(subdev, "   SOR(s): %d (%02lx)\n",
+		   disp->sor.nr, disp->sor.mask);
+	for_each_set_bit(i, &disp->sor.mask, disp->sor.nr) {
+		ret = func->sor.new(&disp->base, i);
+		if (ret)
+			return ret;
+	}
+
+	ret = nvkm_gpuobj_new(device, 0x10000, 0x10000, false, NULL,
+			      &disp->inst);
+	if (ret)
+		return ret;
+
+	return nvkm_ramht_new(device, func->ramht_size ? func->ramht_size :
+			      0x1000, 0, disp->inst, &disp->ramht);
+}
+
 static const struct nvkm_disp_func
 nv50_disp_ = {
 	.dtor = nv50_disp_dtor_,
+	.oneinit = nv50_disp_oneinit_,
+	.init = nv50_disp_init_,
+	.fini = nv50_disp_fini_,
 	.intr = nv50_disp_intr_,
 	.root = nv50_disp_root_,
 };
 
 int
 nv50_disp_new_(const struct nv50_disp_func *func, struct nvkm_device *device,
-	       int index, int heads, struct nvkm_disp **pdisp)
+	       int index, struct nvkm_disp **pdisp)
 {
 	struct nv50_disp *disp;
-	int ret, i;
+	int ret;
 
 	if (!(disp = kzalloc(sizeof(*disp), GFP_KERNEL)))
 		return -ENOMEM;
@@ -85,33 +172,11 @@ nv50_disp_new_(const struct nv50_disp_func *func, struct nvkm_device *device,
 	disp->wq = create_singlethread_workqueue("nvkm-disp");
 	if (!disp->wq)
 		return -ENOMEM;
-	INIT_WORK(&disp->supervisor, func->super);
-
-	for (i = 0; func->head.new && i < heads; i++) {
-		ret = func->head.new(&disp->base, i);
-		if (ret)
-			return ret;
-	}
-
-	for (i = 0; func->dac.new && i < func->dac.nr; i++) {
-		ret = func->dac.new(&disp->base, i);
-		if (ret)
-			return ret;
-	}
-
-	for (i = 0; func->pior.new && i < func->pior.nr; i++) {
-		ret = func->pior.new(&disp->base, i);
-		if (ret)
-			return ret;
-	}
 
-	for (i = 0; func->sor.new && i < func->sor.nr; i++) {
-		ret = func->sor.new(&disp->base, i);
-		if (ret)
-			return ret;
-	}
+	INIT_WORK(&disp->supervisor, func->super);
 
-	return nvkm_event_init(func->uevent, 1, 1 + (heads * 4), &disp->uevent);
+	return nvkm_event_init(func->uevent, 1, ARRAY_SIZE(disp->chan),
+			       &disp->uevent);
 }
 
 static u32
@@ -613,20 +678,96 @@ nv50_disp_intr(struct nv50_disp *disp)
 	}
 }
 
+void
+nv50_disp_fini(struct nv50_disp *disp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	/* disable all interrupts */
+	nvkm_wr32(device, 0x610024, 0x00000000);
+	nvkm_wr32(device, 0x610020, 0x00000000);
+}
+
+int
+nv50_disp_init(struct nv50_disp *disp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	struct nvkm_head *head;
+	u32 tmp;
+	int i;
+
+	/* The below segments of code copying values from one register to
+	 * another appear to inform EVO of the display capabilities or
+	 * something similar.  NFI what the 0x614004 caps are for..
+	 */
+	tmp = nvkm_rd32(device, 0x614004);
+	nvkm_wr32(device, 0x610184, tmp);
+
+	/* ... CRTC caps */
+	list_for_each_entry(head, &disp->base.head, head) {
+		tmp = nvkm_rd32(device, 0x616100 + (head->id * 0x800));
+		nvkm_wr32(device, 0x610190 + (head->id * 0x10), tmp);
+		tmp = nvkm_rd32(device, 0x616104 + (head->id * 0x800));
+		nvkm_wr32(device, 0x610194 + (head->id * 0x10), tmp);
+		tmp = nvkm_rd32(device, 0x616108 + (head->id * 0x800));
+		nvkm_wr32(device, 0x610198 + (head->id * 0x10), tmp);
+		tmp = nvkm_rd32(device, 0x61610c + (head->id * 0x800));
+		nvkm_wr32(device, 0x61019c + (head->id * 0x10), tmp);
+	}
+
+	/* ... DAC caps */
+	for (i = 0; i < disp->dac.nr; i++) {
+		tmp = nvkm_rd32(device, 0x61a000 + (i * 0x800));
+		nvkm_wr32(device, 0x6101d0 + (i * 0x04), tmp);
+	}
+
+	/* ... SOR caps */
+	for (i = 0; i < disp->sor.nr; i++) {
+		tmp = nvkm_rd32(device, 0x61c000 + (i * 0x800));
+		nvkm_wr32(device, 0x6101e0 + (i * 0x04), tmp);
+	}
+
+	/* ... PIOR caps */
+	for (i = 0; i < disp->pior.nr; i++) {
+		tmp = nvkm_rd32(device, 0x61e000 + (i * 0x800));
+		nvkm_wr32(device, 0x6101f0 + (i * 0x04), tmp);
+	}
+
+	/* steal display away from vbios, or something like that */
+	if (nvkm_rd32(device, 0x610024) & 0x00000100) {
+		nvkm_wr32(device, 0x610024, 0x00000100);
+		nvkm_mask(device, 0x6194e8, 0x00000001, 0x00000000);
+		if (nvkm_msec(device, 2000,
+			if (!(nvkm_rd32(device, 0x6194e8) & 0x00000002))
+				break;
+		) < 0)
+			return -EBUSY;
+	}
+
+	/* point at display engine memory area (hash table, objects) */
+	nvkm_wr32(device, 0x610010, (disp->inst->addr >> 8) | 9);
+
+	/* enable supervisor interrupts, disable everything else */
+	nvkm_wr32(device, 0x61002c, 0x00000370);
+	nvkm_wr32(device, 0x610028, 0x00000000);
+	return 0;
+}
+
 static const struct nv50_disp_func
 nv50_disp = {
+	.init = nv50_disp_init,
+	.fini = nv50_disp_fini,
 	.intr = nv50_disp_intr,
 	.uevent = &nv50_disp_chan_uevent,
 	.super = nv50_disp_super,
 	.root = &nv50_disp_root_oclass,
-	.head.new = nv50_head_new,
-	.dac = { .nr = 3, .new = nv50_dac_new },
-	.sor = { .nr = 2, .new = nv50_sor_new },
-	.pior = { .nr = 3, .new = nv50_pior_new },
+	.head = { .cnt = nv50_head_cnt, .new = nv50_head_new },
+	.dac = { .cnt = nv50_dac_cnt, .new = nv50_dac_new },
+	.sor = { .cnt = nv50_sor_cnt, .new = nv50_sor_new },
+	.pior = { .cnt = nv50_pior_cnt, .new = nv50_pior_new },
 };
 
 int
 nv50_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
 {
-	return nv50_disp_new_(&nv50_disp, device, index, 2, pdisp);
+	return nv50_disp_new_(&nv50_disp, device, index, pdisp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
index eb0b8acb1c5b..8580382ab248 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
@@ -16,14 +16,26 @@ struct nv50_disp {
 	struct nvkm_event uevent;
 
 	struct {
+		unsigned long mask;
+		int nr;
+	} wndw, head, dac;
+
+	struct {
+		unsigned long mask;
+		int nr;
 		u32 lvdsconf;
 	} sor;
 
 	struct {
+		unsigned long mask;
+		int nr;
 		u8 type[3];
 	} pior;
 
-	struct nv50_disp_chan *chan[21];
+	struct nvkm_gpuobj *inst;
+	struct nvkm_ramht *ramht;
+
+	struct nv50_disp_chan *chan[81];
 };
 
 void nv50_disp_super_1(struct nv50_disp *);
@@ -34,11 +46,11 @@ void nv50_disp_super_2_2(struct nv50_disp *, struct nvkm_head *);
 void nv50_disp_super_3_0(struct nv50_disp *, struct nvkm_head *);
 
 int nv50_disp_new_(const struct nv50_disp_func *, struct nvkm_device *,
-		   int index, int heads, struct nvkm_disp **);
-int gf119_disp_new_(const struct nv50_disp_func *, struct nvkm_device *,
-		    int index, struct nvkm_disp **);
+		   int index, struct nvkm_disp **);
 
 struct nv50_disp_func {
+	int (*init)(struct nv50_disp *);
+	void (*fini)(struct nv50_disp *);
 	void (*intr)(struct nv50_disp *);
 	void (*intr_error)(struct nv50_disp *, int chid);
 
@@ -48,28 +60,20 @@ struct nv50_disp_func {
 	const struct nvkm_disp_oclass *root;
 
 	struct {
+		int (*cnt)(struct nvkm_disp *, unsigned long *mask);
 		int (*new)(struct nvkm_disp *, int id);
-	} head;
+	} wndw, head, dac, sor, pior;
 
-	struct {
-		int nr;
-		int (*new)(struct nvkm_disp *, int id);
-	} dac;
-
-	struct {
-		int nr;
-		int (*new)(struct nvkm_disp *, int id);
-	} sor;
-
-	struct {
-		int nr;
-		int (*new)(struct nvkm_disp *, int id);
-	} pior;
+	u16 ramht_size;
 };
 
+int nv50_disp_init(struct nv50_disp *);
+void nv50_disp_fini(struct nv50_disp *);
 void nv50_disp_intr(struct nv50_disp *);
 void nv50_disp_super(struct work_struct *);
 
+int gf119_disp_init(struct nv50_disp *);
+void gf119_disp_fini(struct nv50_disp *);
 void gf119_disp_intr(struct nv50_disp *);
 void gf119_disp_super(struct work_struct *);
 void gf119_disp_intr_error(struct nv50_disp *, int);
@@ -77,4 +81,12 @@ void gf119_disp_intr_error(struct nv50_disp *, int);
 void nv50_disp_dptmds_war_2(struct nv50_disp *, struct dcb_output *);
 void nv50_disp_dptmds_war_3(struct nv50_disp *, struct dcb_output *);
 void nv50_disp_update_sppll1(struct nv50_disp *);
+
+extern const struct nvkm_event_func nv50_disp_chan_uevent;
+int  nv50_disp_chan_uevent_ctor(struct nvkm_object *, void *, u32,
+				struct nvkm_notify *);
+void nv50_disp_chan_uevent_send(struct nv50_disp *, int);
+
+extern const struct nvkm_event_func gf119_disp_chan_uevent;
+extern const struct nvkm_event_func gv100_disp_chan_uevent;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c
index 1f9fd3403f07..1ae0bcfc89b9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c
@@ -22,16 +22,11 @@
  * Authors: Ben Skeggs
  */
 #include "channv50.h"
-#include "rootnv50.h"
 
-#include <nvif/class.h>
-
-const struct nv50_disp_pioc_oclass
-gf119_disp_oimm_oclass = {
-	.base.oclass = GF110_DISP_OVERLAY,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_oimm_new,
-	.func = &gf119_disp_pioc_func,
-	.chid = { 9, 9 },
-};
+int
+gf119_disp_oimm_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_oimm_new_(&gf119_disp_pioc_func, disp, 9, 9,
+				   oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgk104.c
deleted file mode 100644
index 0c09fe85e952..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgk104.c
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright 2012 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs
- */
-#include "channv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
-
-const struct nv50_disp_pioc_oclass
-gk104_disp_oimm_oclass = {
-	.base.oclass = GK104_DISP_OVERLAY,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_oimm_new,
-	.func = &gf119_disp_pioc_func,
-	.chid = { 9, 9 },
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c
index abf82365c671..30ffb1008505 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c
@@ -22,16 +22,11 @@
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
 #include "channv50.h"
-#include "rootnv50.h"
 
-#include <nvif/class.h>
-
-const struct nv50_disp_pioc_oclass
-gp102_disp_oimm_oclass = {
-	.base.oclass = GK104_DISP_OVERLAY,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_oimm_new,
-	.func = &gf119_disp_pioc_func,
-	.chid = { 9, 13 },
-};
+int
+gp102_disp_oimm_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_oimm_new_(&gf119_disp_pioc_func, disp, 9, 13,
+				   oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgt215.c
deleted file mode 100644
index 1281db28aebd..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgt215.c
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright 2012 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs
- */
-#include "channv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
-
-const struct nv50_disp_pioc_oclass
-gt215_disp_oimm_oclass = {
-	.base.oclass = GT214_DISP_OVERLAY,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_oimm_new,
-	.func = &nv50_disp_pioc_func,
-	.chid = { 5, 5 },
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c
index f3b0fa2c5924..0db99bfe9db9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c
@@ -23,30 +23,26 @@
  */
 #include "channv50.h"
 #include "head.h"
-#include "rootnv50.h"
 
 #include <core/client.h>
 
-#include <nvif/class.h>
 #include <nvif/cl507b.h>
 #include <nvif/unpack.h>
 
 int
-nv50_disp_oimm_new(const struct nv50_disp_chan_func *func,
-		   const struct nv50_disp_chan_mthd *mthd,
-		   struct nv50_disp_root *root, int ctrl, int user,
-		   const struct nvkm_oclass *oclass, void *data, u32 size,
-		   struct nvkm_object **pobject)
+nv50_disp_oimm_new_(const struct nv50_disp_chan_func *func,
+		    struct nv50_disp *disp, int ctrl, int user,
+		    const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nvkm_object **pobject)
 {
 	union {
 		struct nv50_disp_overlay_v0 v0;
-	} *args = data;
+	} *args = argv;
 	struct nvkm_object *parent = oclass->parent;
-	struct nv50_disp *disp = root->disp;
 	int head, ret = -ENOSYS;
 
-	nvif_ioctl(parent, "create disp overlay size %d\n", size);
-	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
+	nvif_ioctl(parent, "create disp overlay size %d\n", argc);
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
 		nvif_ioctl(parent, "create disp overlay vers %d head %d\n",
 			   args->v0.version, args->v0.head);
 		if (!nvkm_head_find(&disp->base, args->v0.head))
@@ -55,16 +51,14 @@ nv50_disp_oimm_new(const struct nv50_disp_chan_func *func,
 	} else
 		return ret;
 
-	return nv50_disp_chan_new_(func, mthd, root, ctrl + head, user + head,
+	return nv50_disp_chan_new_(func, NULL, disp, ctrl + head, user + head,
 				   head, oclass, pobject);
 }
 
-const struct nv50_disp_pioc_oclass
-nv50_disp_oimm_oclass = {
-	.base.oclass = NV50_DISP_OVERLAY,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_oimm_new,
-	.func = &nv50_disp_pioc_func,
-	.chid = { 5, 5 },
-};
+int
+nv50_disp_oimm_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		   struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_oimm_new_(&nv50_disp_pioc_func, disp, 5, 5,
+				   oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlyg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlyg84.c
index db6234eebc61..31b915d48699 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlyg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlyg84.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 static const struct nv50_disp_mthd_list
 g84_disp_ovly_mthd_base = {
@@ -54,8 +51,8 @@ g84_disp_ovly_mthd_base = {
 	}
 };
 
-const struct nv50_disp_chan_mthd
-g84_disp_ovly_chan_mthd = {
+static const struct nv50_disp_chan_mthd
+g84_disp_ovly_mthd = {
 	.name = "Overlay",
 	.addr = 0x000540,
 	.prev = 0x000004,
@@ -65,13 +62,10 @@ g84_disp_ovly_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-g84_disp_ovly_oclass = {
-	.base.oclass = G82_DISP_OVERLAY_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_ovly_new,
-	.func = &nv50_disp_dmac_func,
-	.mthd = &g84_disp_ovly_chan_mthd,
-	.chid = 3,
-};
+int
+g84_disp_ovly_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		  struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_ovly_new_(&nv50_disp_dmac_func, &g84_disp_ovly_mthd,
+				   disp, 3, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygf119.c
index 5985879abd23..83fd534c44da 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygf119.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 static const struct nv50_disp_mthd_list
 gf119_disp_ovly_mthd_base = {
@@ -79,7 +76,7 @@ gf119_disp_ovly_mthd_base = {
 };
 
 static const struct nv50_disp_chan_mthd
-gf119_disp_ovly_chan_mthd = {
+gf119_disp_ovly_mthd = {
 	.name = "Overlay",
 	.addr = 0x001000,
 	.prev = -0x020000,
@@ -89,13 +86,10 @@ gf119_disp_ovly_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-gf119_disp_ovly_oclass = {
-	.base.oclass = GF110_DISP_OVERLAY_CONTROL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_ovly_new,
-	.func = &gf119_disp_dmac_func,
-	.mthd = &gf119_disp_ovly_chan_mthd,
-	.chid = 5,
-};
+int
+gf119_disp_ovly_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_ovly_new_(&gf119_disp_dmac_func, &gf119_disp_ovly_mthd,
+				   disp, 5, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygk104.c
index 2f0220b39f34..a7acacbc92c1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygk104.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 static const struct nv50_disp_mthd_list
 gk104_disp_ovly_mthd_base = {
@@ -81,7 +78,7 @@ gk104_disp_ovly_mthd_base = {
 };
 
 const struct nv50_disp_chan_mthd
-gk104_disp_ovly_chan_mthd = {
+gk104_disp_ovly_mthd = {
 	.name = "Overlay",
 	.addr = 0x001000,
 	.prev = -0x020000,
@@ -91,13 +88,10 @@ gk104_disp_ovly_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-gk104_disp_ovly_oclass = {
-	.base.oclass = GK104_DISP_OVERLAY_CONTROL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_ovly_new,
-	.func = &gf119_disp_dmac_func,
-	.mthd = &gk104_disp_ovly_chan_mthd,
-	.chid = 5,
-};
+int
+gk104_disp_ovly_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_ovly_new_(&gf119_disp_dmac_func, &gk104_disp_ovly_mthd,
+				   disp, 5, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygp102.c
index 589bd2f12b41..e0eca6ea914c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygp102.c
@@ -21,18 +21,12 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
+#include "channv50.h"
 
-#include <nvif/class.h>
-
-const struct nv50_disp_dmac_oclass
-gp102_disp_ovly_oclass = {
-	.base.oclass = GK104_DISP_OVERLAY_CONTROL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_ovly_new,
-	.func = &gp102_disp_dmac_func,
-	.mthd = &gk104_disp_ovly_chan_mthd,
-	.chid = 5,
-};
+int
+gp102_disp_ovly_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_ovly_new_(&gp102_disp_dmac_func, &gk104_disp_ovly_mthd,
+				   disp, 5, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygt200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygt200.c
index f858053db83d..dc60cd00dc16 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygt200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygt200.c
@@ -21,10 +21,7 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "channv50.h"
 
 static const struct nv50_disp_mthd_list
 gt200_disp_ovly_mthd_base = {
@@ -58,7 +55,7 @@ gt200_disp_ovly_mthd_base = {
 };
 
 static const struct nv50_disp_chan_mthd
-gt200_disp_ovly_chan_mthd = {
+gt200_disp_ovly_mthd = {
 	.name = "Overlay",
 	.addr = 0x000540,
 	.prev = 0x000004,
@@ -68,13 +65,10 @@ gt200_disp_ovly_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-gt200_disp_ovly_oclass = {
-	.base.oclass = GT200_DISP_OVERLAY_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_ovly_new,
-	.func = &nv50_disp_dmac_func,
-	.mthd = &gt200_disp_ovly_chan_mthd,
-	.chid = 3,
-};
+int
+gt200_disp_ovly_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_ovly_new_(&nv50_disp_dmac_func, &gt200_disp_ovly_mthd,
+				   disp, 3, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygt215.c
deleted file mode 100644
index c947e1e16a37..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygt215.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * Copyright 2015 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs <bskeggs@redhat.com>
- */
-#include "dmacnv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
-
-const struct nv50_disp_dmac_oclass
-gt215_disp_ovly_oclass = {
-	.base.oclass = GT214_DISP_OVERLAY_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_ovly_new,
-	.func = &nv50_disp_dmac_func,
-	.mthd = &g84_disp_ovly_chan_mthd,
-	.chid = 3,
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlynv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlynv50.c
index 9ebaaa6e9e33..6974c12c4518 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlynv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlynv50.c
@@ -21,33 +21,30 @@
  *
  * Authors: Ben Skeggs
  */
-#include "dmacnv50.h"
+#include "channv50.h"
 #include "head.h"
-#include "rootnv50.h"
 
 #include <core/client.h>
 
-#include <nvif/class.h>
 #include <nvif/cl507e.h>
 #include <nvif/unpack.h>
 
 int
-nv50_disp_ovly_new(const struct nv50_disp_dmac_func *func,
-		   const struct nv50_disp_chan_mthd *mthd,
-		   struct nv50_disp_root *root, int chid,
-		   const struct nvkm_oclass *oclass, void *data, u32 size,
-		   struct nvkm_object **pobject)
+nv50_disp_ovly_new_(const struct nv50_disp_chan_func *func,
+		    const struct nv50_disp_chan_mthd *mthd,
+		    struct nv50_disp *disp, int chid,
+		    const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nvkm_object **pobject)
 {
 	union {
 		struct nv50_disp_overlay_channel_dma_v0 v0;
-	} *args = data;
+	} *args = argv;
 	struct nvkm_object *parent = oclass->parent;
-	struct nv50_disp *disp = root->disp;
 	int head, ret = -ENOSYS;
 	u64 push;
 
-	nvif_ioctl(parent, "create disp overlay channel dma size %d\n", size);
-	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
+	nvif_ioctl(parent, "create disp overlay channel dma size %d\n", argc);
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
 		nvif_ioctl(parent, "create disp overlay channel dma vers %d "
 				   "pushbuf %016llx head %d\n",
 			   args->v0.version, args->v0.pushbuf, args->v0.head);
@@ -58,7 +55,7 @@ nv50_disp_ovly_new(const struct nv50_disp_dmac_func *func,
 	} else
 		return ret;
 
-	return nv50_disp_dmac_new_(func, mthd, root, chid + head,
+	return nv50_disp_dmac_new_(func, mthd, disp, chid + head,
 				   head, push, oclass, pobject);
 }
 
@@ -91,7 +88,7 @@ nv50_disp_ovly_mthd_base = {
 };
 
 static const struct nv50_disp_chan_mthd
-nv50_disp_ovly_chan_mthd = {
+nv50_disp_ovly_mthd = {
 	.name = "Overlay",
 	.addr = 0x000540,
 	.prev = 0x000004,
@@ -101,13 +98,10 @@ nv50_disp_ovly_chan_mthd = {
 	}
 };
 
-const struct nv50_disp_dmac_oclass
-nv50_disp_ovly_oclass = {
-	.base.oclass = NV50_DISP_OVERLAY_CHANNEL_DMA,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_ovly_new,
-	.func = &nv50_disp_dmac_func,
-	.mthd = &nv50_disp_ovly_chan_mthd,
-	.chid = 3,
-};
+int
+nv50_disp_ovly_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		   struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return nv50_disp_ovly_new_(&nv50_disp_dmac_func, &nv50_disp_ovly_mthd,
+				   disp, 3, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c
index 0abaa6431943..5296e7bee813 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c
@@ -29,7 +29,7 @@
 static void
 gf119_disp_pioc_fini(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->root->disp;
+	struct nv50_disp *disp = chan->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	int ctrl = chan->chid.ctrl;
@@ -43,24 +43,17 @@ gf119_disp_pioc_fini(struct nv50_disp_chan *chan)
 		nvkm_error(subdev, "ch %d fini: %08x\n", user,
 			   nvkm_rd32(device, 0x610490 + (ctrl * 0x10)));
 	}
-
-	/* disable error reporting and completion notification */
-	nvkm_mask(device, 0x610090, 0x00000001 << user, 0x00000000);
-	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000000);
 }
 
 static int
 gf119_disp_pioc_init(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->root->disp;
+	struct nv50_disp *disp = chan->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	int ctrl = chan->chid.ctrl;
 	int user = chan->chid.user;
 
-	/* enable error reporting */
-	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000001 << user);
-
 	/* activate channel */
 	nvkm_wr32(device, 0x610490 + (ctrl * 0x10), 0x00000001);
 	if (nvkm_msec(device, 2000,
@@ -80,4 +73,6 @@ const struct nv50_disp_chan_func
 gf119_disp_pioc_func = {
 	.init = gf119_disp_pioc_init,
 	.fini = gf119_disp_pioc_fini,
+	.intr = gf119_disp_chan_intr,
+	.user = nv50_disp_chan_user,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c
index 0211e0e8a35f..4faed6fce682 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c
@@ -29,7 +29,7 @@
 static void
 nv50_disp_pioc_fini(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->root->disp;
+	struct nv50_disp *disp = chan->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	int ctrl = chan->chid.ctrl;
@@ -48,7 +48,7 @@ nv50_disp_pioc_fini(struct nv50_disp_chan *chan)
 static int
 nv50_disp_pioc_init(struct nv50_disp_chan *chan)
 {
-	struct nv50_disp *disp = chan->root->disp;
+	struct nv50_disp *disp = chan->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	int ctrl = chan->chid.ctrl;
@@ -82,4 +82,6 @@ const struct nv50_disp_chan_func
 nv50_disp_pioc_func = {
 	.init = nv50_disp_pioc_init,
 	.fini = nv50_disp_pioc_fini,
+	.intr = nv50_disp_chan_intr,
+	.user = nv50_disp_chan_user,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piornv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piornv50.c
index 99b3b9050635..e997a207f546 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piornv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piornv50.c
@@ -127,8 +127,13 @@ nv50_pior = {
 int
 nv50_pior_new(struct nvkm_disp *disp, int id)
 {
-	struct nvkm_device *device = disp->engine.subdev.device;
-	if (!(nvkm_rd32(device, 0x610184) & (0x10000000 << id)))
-		return 0;
 	return nvkm_ior_new_(&nv50_pior, disp, PIOR, id);
 }
+
+int
+nv50_pior_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = (nvkm_rd32(device, 0x610184) & 0x70000000) >> 28;
+	return 3;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h
index 6c9bfff6d043..ef66c5f38ad5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/priv.h
@@ -12,6 +12,9 @@ void nvkm_disp_vblank(struct nvkm_disp *, int head);
 
 struct nvkm_disp_func {
 	void *(*dtor)(struct nvkm_disp *);
+	int (*oneinit)(struct nvkm_disp *);
+	int (*init)(struct nvkm_disp *);
+	void (*fini)(struct nvkm_disp *);
 	void (*intr)(struct nvkm_disp *);
 
 	const struct nvkm_disp_oclass *(*root)(struct nvkm_disp *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootg84.c
index 721e4f74d1fc..1ed371fd7ddf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootg84.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 g84_disp_root = {
-	.init = nv50_disp_root_init,
-	.fini = nv50_disp_root_fini,
-	.dmac = {
-		&g84_disp_core_oclass,
-		&g84_disp_base_oclass,
-		&g84_disp_ovly_oclass,
-	},
-	.pioc = {
-		&g84_disp_oimm_oclass,
-		&g84_disp_curs_oclass,
+	.user = {
+		{{0,0,G82_DISP_CURSOR             }, nv50_disp_curs_new },
+		{{0,0,G82_DISP_OVERLAY            }, nv50_disp_oimm_new },
+		{{0,0,G82_DISP_BASE_CHANNEL_DMA   },  g84_disp_base_new },
+		{{0,0,G82_DISP_CORE_CHANNEL_DMA   },  g84_disp_core_new },
+		{{0,0,G82_DISP_OVERLAY_CHANNEL_DMA},  g84_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootg94.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootg94.c
index 9493f6edf62b..ef579eb00238 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootg94.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 g94_disp_root = {
-	.init = nv50_disp_root_init,
-	.fini = nv50_disp_root_fini,
-	.dmac = {
-		&g94_disp_core_oclass,
-		&gt200_disp_base_oclass,
-		&gt200_disp_ovly_oclass,
-	},
-	.pioc = {
-		&g84_disp_oimm_oclass,
-		&g84_disp_curs_oclass,
+	.user = {
+		{{0,0,  G82_DISP_CURSOR             },  nv50_disp_curs_new },
+		{{0,0,  G82_DISP_OVERLAY            },  nv50_disp_oimm_new },
+		{{0,0,GT200_DISP_BASE_CHANNEL_DMA   },   g84_disp_base_new },
+		{{0,0,GT206_DISP_CORE_CHANNEL_DMA   },   g94_disp_core_new },
+		{{0,0,GT200_DISP_OVERLAY_CHANNEL_DMA}, gt200_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgf119.c
index 333c8424b413..fe011165dc02 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgf119.c
@@ -22,104 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "head.h"
-#include "dmacnv50.h"
-
-#include <core/ramht.h>
-#include <subdev/timer.h>
+#include "channv50.h"
 
 #include <nvif/class.h>
 
-void
-gf119_disp_root_fini(struct nv50_disp_root *root)
-{
-	struct nvkm_device *device = root->disp->base.engine.subdev.device;
-	/* disable all interrupts */
-	nvkm_wr32(device, 0x6100b0, 0x00000000);
-}
-
-int
-gf119_disp_root_init(struct nv50_disp_root *root)
-{
-	struct nv50_disp *disp = root->disp;
-	struct nvkm_head *head;
-	struct nvkm_device *device = disp->base.engine.subdev.device;
-	u32 tmp;
-	int i;
-
-	/* The below segments of code copying values from one register to
-	 * another appear to inform EVO of the display capabilities or
-	 * something similar.
-	 */
-
-	/* ... CRTC caps */
-	list_for_each_entry(head, &disp->base.head, head) {
-		const u32 hoff = head->id * 0x800;
-		tmp = nvkm_rd32(device, 0x616104 + hoff);
-		nvkm_wr32(device, 0x6101b4 + hoff, tmp);
-		tmp = nvkm_rd32(device, 0x616108 + hoff);
-		nvkm_wr32(device, 0x6101b8 + hoff, tmp);
-		tmp = nvkm_rd32(device, 0x61610c + hoff);
-		nvkm_wr32(device, 0x6101bc + hoff, tmp);
-	}
-
-	/* ... DAC caps */
-	for (i = 0; i < disp->func->dac.nr; i++) {
-		tmp = nvkm_rd32(device, 0x61a000 + (i * 0x800));
-		nvkm_wr32(device, 0x6101c0 + (i * 0x800), tmp);
-	}
-
-	/* ... SOR caps */
-	for (i = 0; i < disp->func->sor.nr; i++) {
-		tmp = nvkm_rd32(device, 0x61c000 + (i * 0x800));
-		nvkm_wr32(device, 0x6301c4 + (i * 0x800), tmp);
-	}
-
-	/* steal display away from vbios, or something like that */
-	if (nvkm_rd32(device, 0x6100ac) & 0x00000100) {
-		nvkm_wr32(device, 0x6100ac, 0x00000100);
-		nvkm_mask(device, 0x6194e8, 0x00000001, 0x00000000);
-		if (nvkm_msec(device, 2000,
-			if (!(nvkm_rd32(device, 0x6194e8) & 0x00000002))
-				break;
-		) < 0)
-			return -EBUSY;
-	}
-
-	/* point at display engine memory area (hash table, objects) */
-	nvkm_wr32(device, 0x610010, (root->instmem->addr >> 8) | 9);
-
-	/* enable supervisor interrupts, disable everything else */
-	nvkm_wr32(device, 0x610090, 0x00000000);
-	nvkm_wr32(device, 0x6100a0, 0x00000000);
-	nvkm_wr32(device, 0x6100b0, 0x00000307);
-
-	/* disable underflow reporting, preventing an intermittent issue
-	 * on some gk104 boards where the production vbios left this
-	 * setting enabled by default.
-	 *
-	 * ftp://download.nvidia.com/open-gpu-doc/gk104-disable-underflow-reporting/1/gk104-disable-underflow-reporting.txt
-	 */
-	list_for_each_entry(head, &disp->base.head, head) {
-		const u32 hoff = head->id * 0x800;
-		nvkm_mask(device, 0x616308 + hoff, 0x00000111, 0x00000010);
-	}
-
-	return 0;
-}
-
 static const struct nv50_disp_root_func
 gf119_disp_root = {
-	.init = gf119_disp_root_init,
-	.fini = gf119_disp_root_fini,
-	.dmac = {
-		&gf119_disp_core_oclass,
-		&gf119_disp_base_oclass,
-		&gf119_disp_ovly_oclass,
-	},
-	.pioc = {
-		&gf119_disp_oimm_oclass,
-		&gf119_disp_curs_oclass,
+	.user = {
+		{{0,0,GF110_DISP_CURSOR             }, gf119_disp_curs_new },
+		{{0,0,GF110_DISP_OVERLAY            }, gf119_disp_oimm_new },
+		{{0,0,GF110_DISP_BASE_CHANNEL_DMA   }, gf119_disp_base_new },
+		{{0,0,GF110_DISP_CORE_CHANNEL_DMA   }, gf119_disp_core_new },
+		{{0,0,GF110_DISP_OVERLAY_CONTROL_DMA}, gf119_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgk104.c
index 0bfdb1d1c6ab..9e8ffd348b50 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgk104.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 gk104_disp_root = {
-	.init = gf119_disp_root_init,
-	.fini = gf119_disp_root_fini,
-	.dmac = {
-		&gk104_disp_core_oclass,
-		&gk104_disp_base_oclass,
-		&gk104_disp_ovly_oclass,
-	},
-	.pioc = {
-		&gk104_disp_oimm_oclass,
-		&gk104_disp_curs_oclass,
+	.user = {
+		{{0,0,GK104_DISP_CURSOR             }, gf119_disp_curs_new },
+		{{0,0,GK104_DISP_OVERLAY            }, gf119_disp_oimm_new },
+		{{0,0,GK104_DISP_BASE_CHANNEL_DMA   }, gf119_disp_base_new },
+		{{0,0,GK104_DISP_CORE_CHANNEL_DMA   }, gk104_disp_core_new },
+		{{0,0,GK104_DISP_OVERLAY_CONTROL_DMA}, gk104_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgk110.c
index 1e8dbed8a67c..dc85cc1c9490 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgk110.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 gk110_disp_root = {
-	.init = gf119_disp_root_init,
-	.fini = gf119_disp_root_fini,
-	.dmac = {
-		&gk110_disp_core_oclass,
-		&gk110_disp_base_oclass,
-		&gk104_disp_ovly_oclass,
-	},
-	.pioc = {
-		&gk104_disp_oimm_oclass,
-		&gk104_disp_curs_oclass,
+	.user = {
+		{{0,0,GK104_DISP_CURSOR             }, gf119_disp_curs_new },
+		{{0,0,GK104_DISP_OVERLAY            }, gf119_disp_oimm_new },
+		{{0,0,GK110_DISP_BASE_CHANNEL_DMA   }, gf119_disp_base_new },
+		{{0,0,GK110_DISP_CORE_CHANNEL_DMA   }, gk104_disp_core_new },
+		{{0,0,GK104_DISP_OVERLAY_CONTROL_DMA}, gk104_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgm107.c
index 44c55be69e99..e0181ca08840 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgm107.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 gm107_disp_root = {
-	.init = gf119_disp_root_init,
-	.fini = gf119_disp_root_fini,
-	.dmac = {
-		&gm107_disp_core_oclass,
-		&gk110_disp_base_oclass,
-		&gk104_disp_ovly_oclass,
-	},
-	.pioc = {
-		&gk104_disp_oimm_oclass,
-		&gk104_disp_curs_oclass,
+	.user = {
+		{{0,0,GK104_DISP_CURSOR             }, gf119_disp_curs_new },
+		{{0,0,GK104_DISP_OVERLAY            }, gf119_disp_oimm_new },
+		{{0,0,GK110_DISP_BASE_CHANNEL_DMA   }, gf119_disp_base_new },
+		{{0,0,GM107_DISP_CORE_CHANNEL_DMA   }, gk104_disp_core_new },
+		{{0,0,GK104_DISP_OVERLAY_CONTROL_DMA}, gk104_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgm200.c
index 38f5ee1dfc58..e5e590e19f62 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgm200.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 gm200_disp_root = {
-	.init = gf119_disp_root_init,
-	.fini = gf119_disp_root_fini,
-	.dmac = {
-		&gm200_disp_core_oclass,
-		&gk110_disp_base_oclass,
-		&gk104_disp_ovly_oclass,
-	},
-	.pioc = {
-		&gk104_disp_oimm_oclass,
-		&gk104_disp_curs_oclass,
+	.user = {
+		{{0,0,GK104_DISP_CURSOR             }, gf119_disp_curs_new },
+		{{0,0,GK104_DISP_OVERLAY            }, gf119_disp_oimm_new },
+		{{0,0,GK110_DISP_BASE_CHANNEL_DMA   }, gf119_disp_base_new },
+		{{0,0,GM200_DISP_CORE_CHANNEL_DMA   }, gk104_disp_core_new },
+		{{0,0,GK104_DISP_OVERLAY_CONTROL_DMA}, gk104_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp100.c
index ac8fdd728ec6..762a1a922e05 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp100.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 gp100_disp_root = {
-	.init = gf119_disp_root_init,
-	.fini = gf119_disp_root_fini,
-	.dmac = {
-		&gp100_disp_core_oclass,
-		&gk110_disp_base_oclass,
-		&gk104_disp_ovly_oclass,
-	},
-	.pioc = {
-		&gk104_disp_oimm_oclass,
-		&gk104_disp_curs_oclass,
+	.user = {
+		{{0,0,GK104_DISP_CURSOR             }, gf119_disp_curs_new },
+		{{0,0,GK104_DISP_OVERLAY            }, gf119_disp_oimm_new },
+		{{0,0,GK110_DISP_BASE_CHANNEL_DMA   }, gf119_disp_base_new },
+		{{0,0,GP100_DISP_CORE_CHANNEL_DMA   }, gk104_disp_core_new },
+		{{0,0,GK104_DISP_OVERLAY_CONTROL_DMA}, gk104_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp102.c
index 37122ca579ad..c7f00946c9af 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp102.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 gp102_disp_root = {
-	.init = gf119_disp_root_init,
-	.fini = gf119_disp_root_fini,
-	.dmac = {
-		&gp102_disp_core_oclass,
-		&gp102_disp_base_oclass,
-		&gp102_disp_ovly_oclass,
-	},
-	.pioc = {
-		&gp102_disp_oimm_oclass,
-		&gp102_disp_curs_oclass,
+	.user = {
+		{{0,0,GK104_DISP_CURSOR             }, gp102_disp_curs_new },
+		{{0,0,GK104_DISP_OVERLAY            }, gp102_disp_oimm_new },
+		{{0,0,GK110_DISP_BASE_CHANNEL_DMA   }, gp102_disp_base_new },
+		{{0,0,GP102_DISP_CORE_CHANNEL_DMA   }, gp102_disp_core_new },
+		{{0,0,GK104_DISP_OVERLAY_CONTROL_DMA}, gp102_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgt200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgt200.c
index 124a0c24f92c..a6963654087c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgt200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgt200.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 gt200_disp_root = {
-	.init = nv50_disp_root_init,
-	.fini = nv50_disp_root_fini,
-	.dmac = {
-		&gt200_disp_core_oclass,
-		&gt200_disp_base_oclass,
-		&gt200_disp_ovly_oclass,
-	},
-	.pioc = {
-		&g84_disp_oimm_oclass,
-		&g84_disp_curs_oclass,
+	.user = {
+		{{0,0,  G82_DISP_CURSOR             },  nv50_disp_curs_new },
+		{{0,0,  G82_DISP_OVERLAY            },  nv50_disp_oimm_new },
+		{{0,0,GT200_DISP_BASE_CHANNEL_DMA   },   g84_disp_base_new },
+		{{0,0,GT200_DISP_CORE_CHANNEL_DMA   },   g84_disp_core_new },
+		{{0,0,GT200_DISP_OVERLAY_CHANNEL_DMA}, gt200_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgt215.c
index dff52f30668b..4fe0a3ae8891 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgt215.c
@@ -22,22 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 
 #include <nvif/class.h>
 
 static const struct nv50_disp_root_func
 gt215_disp_root = {
-	.init = nv50_disp_root_init,
-	.fini = nv50_disp_root_fini,
-	.dmac = {
-		&gt215_disp_core_oclass,
-		&gt215_disp_base_oclass,
-		&gt215_disp_ovly_oclass,
-	},
-	.pioc = {
-		&gt215_disp_oimm_oclass,
-		&gt215_disp_curs_oclass,
+	.user = {
+		{{0,0,GT214_DISP_CURSOR             },  nv50_disp_curs_new },
+		{{0,0,GT214_DISP_OVERLAY            },  nv50_disp_oimm_new },
+		{{0,0,GT214_DISP_BASE_CHANNEL_DMA   },   g84_disp_base_new },
+		{{0,0,GT214_DISP_CORE_CHANNEL_DMA   },   g94_disp_core_new },
+		{{0,0,GT214_DISP_OVERLAY_CHANNEL_DMA},   g84_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgv100.c
new file mode 100644
index 000000000000..9c658d632d37
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgv100.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "rootnv50.h"
+#include "channv50.h"
+
+#include <nvif/class.h>
+
+static const struct nv50_disp_root_func
+gv100_disp_root = {
+	.user = {
+		{{0,0,GV100_DISP_CURSOR                }, gv100_disp_curs_new },
+		{{0,0,GV100_DISP_WINDOW_IMM_CHANNEL_DMA}, gv100_disp_wimm_new },
+		{{0,0,GV100_DISP_CORE_CHANNEL_DMA      }, gv100_disp_core_new },
+		{{0,0,GV100_DISP_WINDOW_CHANNEL_DMA    }, gv100_disp_wndw_new },
+		{}
+	},
+};
+
+static int
+gv100_disp_root_new(struct nvkm_disp *disp, const struct nvkm_oclass *oclass,
+		    void *data, u32 size, struct nvkm_object **pobject)
+{
+	return nv50_disp_root_new_(&gv100_disp_root, disp, oclass,
+				   data, size, pobject);
+}
+
+const struct nvkm_disp_oclass
+gv100_disp_root_oclass = {
+	.base.oclass = GV100_DISP,
+	.base.minver = -1,
+	.base.maxver = -1,
+	.ctor = gv100_disp_root_new,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c
index 1208524aae14..3aa5a2879239 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c
@@ -22,14 +22,12 @@
  * Authors: Ben Skeggs
  */
 #include "rootnv50.h"
-#include "dmacnv50.h"
+#include "channv50.h"
 #include "dp.h"
 #include "head.h"
 #include "ior.h"
 
 #include <core/client.h>
-#include <core/ramht.h>
-#include <subdev/timer.h>
 
 #include <nvif/class.h>
 #include <nvif/cl5070.h>
@@ -271,23 +269,12 @@ nv50_disp_root_mthd_(struct nvkm_object *object, u32 mthd, void *data, u32 size)
 }
 
 static int
-nv50_disp_root_dmac_new_(const struct nvkm_oclass *oclass,
-			 void *data, u32 size, struct nvkm_object **pobject)
+nv50_disp_root_child_new_(const struct nvkm_oclass *oclass,
+			  void *argv, u32 argc, struct nvkm_object **pobject)
 {
-	const struct nv50_disp_dmac_oclass *sclass = oclass->priv;
-	struct nv50_disp_root *root = nv50_disp_root(oclass->parent);
-	return sclass->ctor(sclass->func, sclass->mthd, root, sclass->chid,
-			    oclass, data, size, pobject);
-}
-
-static int
-nv50_disp_root_pioc_new_(const struct nvkm_oclass *oclass,
-			 void *data, u32 size, struct nvkm_object **pobject)
-{
-	const struct nv50_disp_pioc_oclass *sclass = oclass->priv;
-	struct nv50_disp_root *root = nv50_disp_root(oclass->parent);
-	return sclass->ctor(sclass->func, sclass->mthd, root, sclass->chid.ctrl,
-			    sclass->chid.user, oclass, data, size, pobject);
+	struct nv50_disp *disp = nv50_disp_root(oclass->parent)->disp;
+	const struct nv50_disp_user *user = oclass->priv;
+	return user->ctor(oclass, argv, argc, disp, pobject);
 }
 
 static int
@@ -296,68 +283,26 @@ nv50_disp_root_child_get_(struct nvkm_object *object, int index,
 {
 	struct nv50_disp_root *root = nv50_disp_root(object);
 
-	if (index < ARRAY_SIZE(root->func->dmac)) {
-		sclass->base = root->func->dmac[index]->base;
-		sclass->priv = root->func->dmac[index];
-		sclass->ctor = nv50_disp_root_dmac_new_;
-		return 0;
-	}
-
-	index -= ARRAY_SIZE(root->func->dmac);
-
-	if (index < ARRAY_SIZE(root->func->pioc)) {
-		sclass->base = root->func->pioc[index]->base;
-		sclass->priv = root->func->pioc[index];
-		sclass->ctor = nv50_disp_root_pioc_new_;
+	if (root->func->user[index].ctor) {
+		sclass->base = root->func->user[index].base;
+		sclass->priv = root->func->user + index;
+		sclass->ctor = nv50_disp_root_child_new_;
 		return 0;
 	}
 
 	return -EINVAL;
 }
 
-static int
-nv50_disp_root_fini_(struct nvkm_object *object, bool suspend)
-{
-	struct nv50_disp_root *root = nv50_disp_root(object);
-	root->func->fini(root);
-	return 0;
-}
-
-static int
-nv50_disp_root_init_(struct nvkm_object *object)
-{
-	struct nv50_disp_root *root = nv50_disp_root(object);
-	struct nvkm_ior *ior;
-	int ret;
-
-	ret = root->func->init(root);
-	if (ret)
-		return ret;
-
-	/* Set 'normal' (ie. when it's attached to a head) state for
-	 * each output resource to 'fully enabled'.
-	 */
-	list_for_each_entry(ior, &root->disp->base.ior, head) {
-		ior->func->power(ior, true, true, true, true, true);
-	}
-
-	return 0;
-}
-
 static void *
 nv50_disp_root_dtor_(struct nvkm_object *object)
 {
 	struct nv50_disp_root *root = nv50_disp_root(object);
-	nvkm_ramht_del(&root->ramht);
-	nvkm_gpuobj_del(&root->instmem);
 	return root;
 }
 
 static const struct nvkm_object_func
 nv50_disp_root_ = {
 	.dtor = nv50_disp_root_dtor_,
-	.init = nv50_disp_root_init_,
-	.fini = nv50_disp_root_fini_,
 	.mthd = nv50_disp_root_mthd_,
 	.ntfy = nvkm_disp_ntfy,
 	.sclass = nv50_disp_root_child_get_,
@@ -370,8 +315,6 @@ nv50_disp_root_new_(const struct nv50_disp_root_func *func,
 {
 	struct nv50_disp *disp = nv50_disp(base);
 	struct nv50_disp_root *root;
-	struct nvkm_device *device = disp->base.engine.subdev.device;
-	int ret;
 
 	if (!(root = kzalloc(sizeof(*root), GFP_KERNEL)))
 		return -ENOMEM;
@@ -380,102 +323,18 @@ nv50_disp_root_new_(const struct nv50_disp_root_func *func,
 	nvkm_object_ctor(&nv50_disp_root_, oclass, &root->object);
 	root->func = func;
 	root->disp = disp;
-
-	ret = nvkm_gpuobj_new(disp->base.engine.subdev.device, 0x10000, 0x10000,
-			      false, NULL, &root->instmem);
-	if (ret)
-		return ret;
-
-	return nvkm_ramht_new(device, 0x1000, 0, root->instmem, &root->ramht);
-}
-
-void
-nv50_disp_root_fini(struct nv50_disp_root *root)
-{
-	struct nvkm_device *device = root->disp->base.engine.subdev.device;
-	/* disable all interrupts */
-	nvkm_wr32(device, 0x610024, 0x00000000);
-	nvkm_wr32(device, 0x610020, 0x00000000);
-}
-
-int
-nv50_disp_root_init(struct nv50_disp_root *root)
-{
-	struct nv50_disp *disp = root->disp;
-	struct nvkm_head *head;
-	struct nvkm_device *device = disp->base.engine.subdev.device;
-	u32 tmp;
-	int i;
-
-	/* The below segments of code copying values from one register to
-	 * another appear to inform EVO of the display capabilities or
-	 * something similar.  NFI what the 0x614004 caps are for..
-	 */
-	tmp = nvkm_rd32(device, 0x614004);
-	nvkm_wr32(device, 0x610184, tmp);
-
-	/* ... CRTC caps */
-	list_for_each_entry(head, &disp->base.head, head) {
-		tmp = nvkm_rd32(device, 0x616100 + (head->id * 0x800));
-		nvkm_wr32(device, 0x610190 + (head->id * 0x10), tmp);
-		tmp = nvkm_rd32(device, 0x616104 + (head->id * 0x800));
-		nvkm_wr32(device, 0x610194 + (head->id * 0x10), tmp);
-		tmp = nvkm_rd32(device, 0x616108 + (head->id * 0x800));
-		nvkm_wr32(device, 0x610198 + (head->id * 0x10), tmp);
-		tmp = nvkm_rd32(device, 0x61610c + (head->id * 0x800));
-		nvkm_wr32(device, 0x61019c + (head->id * 0x10), tmp);
-	}
-
-	/* ... DAC caps */
-	for (i = 0; i < disp->func->dac.nr; i++) {
-		tmp = nvkm_rd32(device, 0x61a000 + (i * 0x800));
-		nvkm_wr32(device, 0x6101d0 + (i * 0x04), tmp);
-	}
-
-	/* ... SOR caps */
-	for (i = 0; i < disp->func->sor.nr; i++) {
-		tmp = nvkm_rd32(device, 0x61c000 + (i * 0x800));
-		nvkm_wr32(device, 0x6101e0 + (i * 0x04), tmp);
-	}
-
-	/* ... PIOR caps */
-	for (i = 0; i < disp->func->pior.nr; i++) {
-		tmp = nvkm_rd32(device, 0x61e000 + (i * 0x800));
-		nvkm_wr32(device, 0x6101f0 + (i * 0x04), tmp);
-	}
-
-	/* steal display away from vbios, or something like that */
-	if (nvkm_rd32(device, 0x610024) & 0x00000100) {
-		nvkm_wr32(device, 0x610024, 0x00000100);
-		nvkm_mask(device, 0x6194e8, 0x00000001, 0x00000000);
-		if (nvkm_msec(device, 2000,
-			if (!(nvkm_rd32(device, 0x6194e8) & 0x00000002))
-				break;
-		) < 0)
-			return -EBUSY;
-	}
-
-	/* point at display engine memory area (hash table, objects) */
-	nvkm_wr32(device, 0x610010, (root->instmem->addr >> 8) | 9);
-
-	/* enable supervisor interrupts, disable everything else */
-	nvkm_wr32(device, 0x61002c, 0x00000370);
-	nvkm_wr32(device, 0x610028, 0x00000000);
 	return 0;
 }
 
 static const struct nv50_disp_root_func
 nv50_disp_root = {
-	.init = nv50_disp_root_init,
-	.fini = nv50_disp_root_fini,
-	.dmac = {
-		&nv50_disp_core_oclass,
-		&nv50_disp_base_oclass,
-		&nv50_disp_ovly_oclass,
-	},
-	.pioc = {
-		&nv50_disp_oimm_oclass,
-		&nv50_disp_curs_oclass,
+	.user = {
+		{{0,0,NV50_DISP_CURSOR             }, nv50_disp_curs_new },
+		{{0,0,NV50_DISP_OVERLAY            }, nv50_disp_oimm_new },
+		{{0,0,NV50_DISP_BASE_CHANNEL_DMA   }, nv50_disp_base_new },
+		{{0,0,NV50_DISP_CORE_CHANNEL_DMA   }, nv50_disp_core_new },
+		{{0,0,NV50_DISP_OVERLAY_CHANNEL_DMA}, nv50_disp_ovly_new },
+		{}
 	},
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
index 4818fa69ae6c..6ca4f9184b51 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
@@ -2,34 +2,27 @@
 #ifndef __NV50_DISP_ROOT_H__
 #define __NV50_DISP_ROOT_H__
 #define nv50_disp_root(p) container_of((p), struct nv50_disp_root, object)
+#include <core/object.h>
 #include "nv50.h"
-#include "channv50.h"
-#include "dmacnv50.h"
 
 struct nv50_disp_root {
 	const struct nv50_disp_root_func *func;
 	struct nv50_disp *disp;
 	struct nvkm_object object;
-
-	struct nvkm_gpuobj *instmem;
-	struct nvkm_ramht *ramht;
 };
 
 struct nv50_disp_root_func {
-	int (*init)(struct nv50_disp_root *);
-	void (*fini)(struct nv50_disp_root *);
-	const struct nv50_disp_dmac_oclass *dmac[3];
-	const struct nv50_disp_pioc_oclass *pioc[2];
+	int blah;
+	struct nv50_disp_user {
+		struct nvkm_sclass base;
+		int (*ctor)(const struct nvkm_oclass *, void *argv, u32 argc,
+			    struct nv50_disp *, struct nvkm_object **);
+	} user[];
 };
 
 int  nv50_disp_root_new_(const struct nv50_disp_root_func *, struct nvkm_disp *,
 			 const struct nvkm_oclass *, void *data, u32 size,
 			 struct nvkm_object **);
-int  nv50_disp_root_init(struct nv50_disp_root *);
-void nv50_disp_root_fini(struct nv50_disp_root *);
-
-int  gf119_disp_root_init(struct nv50_disp_root *);
-void gf119_disp_root_fini(struct nv50_disp_root *);
 
 extern const struct nvkm_disp_oclass nv50_disp_root_oclass;
 extern const struct nvkm_disp_oclass g84_disp_root_oclass;
@@ -43,4 +36,5 @@ extern const struct nvkm_disp_oclass gm107_disp_root_oclass;
 extern const struct nvkm_disp_oclass gm200_disp_root_oclass;
 extern const struct nvkm_disp_oclass gp100_disp_root_oclass;
 extern const struct nvkm_disp_oclass gp102_disp_root_oclass;
+extern const struct nvkm_disp_oclass gv100_disp_root_oclass;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorg84.c
index f40b909b4ca2..ec3a7db08118 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorg84.c
@@ -34,5 +34,5 @@ g84_sor = {
 int
 g84_sor_new(struct nvkm_disp *disp, int id)
 {
-	return nv50_sor_new_(&g84_sor, disp, id);
+	return nvkm_ior_new_(&g84_sor, disp, SOR, id);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorg94.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorg94.c
index 49aeafde0031..4d59d02525d9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorg94.c
@@ -279,5 +279,13 @@ g94_sor = {
 int
 g94_sor_new(struct nvkm_disp *disp, int id)
 {
-	return nv50_sor_new_(&g94_sor, disp, id);
+	return nvkm_ior_new_(&g94_sor, disp, SOR, id);
+}
+
+int
+g94_sor_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = (nvkm_rd32(device, 0x610184) & 0x0f000000) >> 24;
+	return 4;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
index 700fc754f28a..e6e6dfbb1283 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
@@ -152,15 +152,6 @@ gf119_sor_state(struct nvkm_ior *sor, struct nvkm_ior_state *state)
 	state->head = ctrl & 0x0000000f;
 }
 
-int
-gf119_sor_new_(const struct nvkm_ior_func *func, struct nvkm_disp *disp, int id)
-{
-	struct nvkm_device *device = disp->engine.subdev.device;
-	if (!(nvkm_rd32(device, 0x612004) & (0x00000100 << id)))
-		return 0;
-	return nvkm_ior_new_(func, disp, SOR, id);
-}
-
 static const struct nvkm_ior_func
 gf119_sor = {
 	.state = gf119_sor_state,
@@ -189,5 +180,13 @@ gf119_sor = {
 int
 gf119_sor_new(struct nvkm_disp *disp, int id)
 {
-	return gf119_sor_new_(&gf119_sor, disp, id);
+	return nvkm_ior_new_(&gf119_sor, disp, SOR, id);
+}
+
+int
+gf119_sor_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = (nvkm_rd32(device, 0x612004) & 0x0000ff00) >> 8;
+	return 8;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgk104.c
index a1547bdf490b..b94090edaebf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgk104.c
@@ -49,5 +49,5 @@ gk104_sor = {
 int
 gk104_sor_new(struct nvkm_disp *disp, int id)
 {
-	return gf119_sor_new_(&gk104_sor, disp, id);
+	return nvkm_ior_new_(&gk104_sor, disp, SOR, id);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c
index 60230957d82b..e6965dec09c9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c
@@ -63,5 +63,5 @@ gm107_sor = {
 int
 gm107_sor_new(struct nvkm_disp *disp, int id)
 {
-	return gf119_sor_new_(&gm107_sor, disp, id);
+	return nvkm_ior_new_(&gm107_sor, disp, SOR, id);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
index f9b8107aa2a2..d892bdf04034 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
@@ -23,7 +23,7 @@
  */
 #include "ior.h"
 
-static void
+void
 gm200_sor_dp_drive(struct nvkm_ior *sor, int ln, int pc, int dc, int pe, int pu)
 {
 	struct nvkm_device *device = sor->disp->engine.subdev.device;
@@ -45,7 +45,7 @@ gm200_sor_dp_drive(struct nvkm_ior *sor, int ln, int pc, int dc, int pe, int pu)
 	nvkm_wr32(device, 0x61c13c + loff, data[3] | (pc << shift));
 }
 
-static void
+void
 gm200_sor_route_set(struct nvkm_outp *outp, struct nvkm_ior *ior)
 {
 	struct nvkm_device *device = outp->disp->engine.subdev.device;
@@ -62,7 +62,7 @@ gm200_sor_route_set(struct nvkm_outp *outp, struct nvkm_ior *ior)
 		nvkm_mask(device, 0x612388 + moff, 0x0000001f, link << 4 | sor);
 }
 
-static int
+int
 gm200_sor_route_get(struct nvkm_outp *outp, int *link)
 {
 	struct nvkm_device *device = outp->disp->engine.subdev.device;
@@ -120,5 +120,5 @@ gm200_sor = {
 int
 gm200_sor_new(struct nvkm_disp *disp, int id)
 {
-	return gf119_sor_new_(&gm200_sor, disp, id);
+	return nvkm_ior_new_(&gm200_sor, disp, SOR, id);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgt215.c
index da228b54b43e..54d134d4ca1d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgt215.c
@@ -65,5 +65,5 @@ gt215_sor = {
 int
 gt215_sor_new(struct nvkm_disp *disp, int id)
 {
-	return nv50_sor_new_(&gt215_sor, disp, id);
+	return nvkm_ior_new_(&gt215_sor, disp, SOR, id);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgv100.c
new file mode 100644
index 000000000000..040db8a338de
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgv100.c
@@ -0,0 +1,120 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ior.h"
+
+#include <subdev/timer.h>
+
+static void
+gv100_sor_dp_watermark(struct nvkm_ior *sor, int head, u8 watermark)
+{
+	struct nvkm_device *device = sor->disp->engine.subdev.device;
+	const u32 hoff = head * 0x800;
+	nvkm_mask(device, 0x616550 + hoff, 0x0c00003f, 0x08000000 | watermark);
+}
+
+static void
+gv100_sor_dp_audio_sym(struct nvkm_ior *sor, int head, u16 h, u32 v)
+{
+	struct nvkm_device *device = sor->disp->engine.subdev.device;
+	const u32 hoff = head * 0x800;
+	nvkm_mask(device, 0x616568 + hoff, 0x0000ffff, h);
+	nvkm_mask(device, 0x61656c + hoff, 0x00ffffff, v);
+}
+
+static void
+gv100_sor_dp_audio(struct nvkm_ior *sor, int head, bool enable)
+{
+	struct nvkm_device *device = sor->disp->engine.subdev.device;
+	const u32 hoff = 0x800 * head;
+	const u32 data = 0x80000000 | (0x00000001 * enable);
+	const u32 mask = 0x8000000d;
+	nvkm_mask(device, 0x616560 + hoff, mask, data);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x616560 + hoff) & 0x80000000))
+			break;
+	);
+}
+
+static void
+gv100_sor_state(struct nvkm_ior *sor, struct nvkm_ior_state *state)
+{
+	struct nvkm_device *device = sor->disp->engine.subdev.device;
+	const u32 coff = (state == &sor->arm) * 0x8000 + sor->id * 0x20;
+	u32 ctrl = nvkm_rd32(device, 0x680300 + coff);
+
+	state->proto_evo = (ctrl & 0x00000f00) >> 8;
+	switch (state->proto_evo) {
+	case 0: state->proto = LVDS; state->link = 1; break;
+	case 1: state->proto = TMDS; state->link = 1; break;
+	case 2: state->proto = TMDS; state->link = 2; break;
+	case 5: state->proto = TMDS; state->link = 3; break;
+	case 8: state->proto =   DP; state->link = 1; break;
+	case 9: state->proto =   DP; state->link = 2; break;
+	default:
+		state->proto = UNKNOWN;
+		break;
+	}
+
+	state->head = ctrl & 0x000000ff;
+}
+
+static const struct nvkm_ior_func
+gv100_sor = {
+	.route = {
+		.get = gm200_sor_route_get,
+		.set = gm200_sor_route_set,
+	},
+	.state = gv100_sor_state,
+	.power = nv50_sor_power,
+	.clock = gf119_sor_clock,
+	.hdmi = {
+		.ctrl = gv100_hdmi_ctrl,
+	},
+	.dp = {
+		.lanes = { 0, 1, 2, 3 },
+		.links = gf119_sor_dp_links,
+		.power = g94_sor_dp_power,
+		.pattern = gm107_sor_dp_pattern,
+		.drive = gm200_sor_dp_drive,
+		.audio = gv100_sor_dp_audio,
+		.audio_sym = gv100_sor_dp_audio_sym,
+		.watermark = gv100_sor_dp_watermark,
+	},
+	.hda = {
+		.hpd = gf119_hda_hpd,
+		.eld = gf119_hda_eld,
+	},
+};
+
+int
+gv100_sor_new(struct nvkm_disp *disp, int id)
+{
+	return nvkm_ior_new_(&gv100_sor, disp, SOR, id);
+}
+
+int
+gv100_sor_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = (nvkm_rd32(device, 0x610060) & 0x0000ff00) >> 8;
+	return (nvkm_rd32(device, 0x610074) & 0x00000f00) >> 8;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp77.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp77.c
index c0179ccb956d..8a70dd25b13a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp77.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp77.c
@@ -44,5 +44,5 @@ mcp77_sor = {
 int
 mcp77_sor_new(struct nvkm_disp *disp, int id)
 {
-	return nv50_sor_new_(&mcp77_sor, disp, id);
+	return nvkm_ior_new_(&mcp77_sor, disp, SOR, id);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp89.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp89.c
index 9bb01cd96697..eac9c5be9166 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp89.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp89.c
@@ -49,5 +49,5 @@ mcp89_sor = {
 int
 mcp89_sor_new(struct nvkm_disp *disp, int id)
 {
-	return nv50_sor_new_(&mcp89_sor, disp, id);
+	return nvkm_ior_new_(&mcp89_sor, disp, SOR, id);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sornv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sornv50.c
index f3ebd0c22e7d..b4729f8798af 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sornv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sornv50.c
@@ -84,15 +84,6 @@ nv50_sor_state(struct nvkm_ior *sor, struct nvkm_ior_state *state)
 	state->head = ctrl & 0x00000003;
 }
 
-int
-nv50_sor_new_(const struct nvkm_ior_func *func, struct nvkm_disp *disp, int id)
-{
-	struct nvkm_device *device = disp->engine.subdev.device;
-	if (!(nvkm_rd32(device, 0x610184) & (0x01000000 << id)))
-		return 0;
-	return nvkm_ior_new_(func, disp, SOR, id);
-}
-
 static const struct nvkm_ior_func
 nv50_sor = {
 	.state = nv50_sor_state,
@@ -103,5 +94,13 @@ nv50_sor = {
 int
 nv50_sor_new(struct nvkm_disp *disp, int id)
 {
-	return nv50_sor_new_(&nv50_sor, disp, id);
+	return nvkm_ior_new_(&nv50_sor, disp, SOR, id);
+}
+
+int
+nv50_sor_cnt(struct nvkm_disp *disp, unsigned long *pmask)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	*pmask = (nvkm_rd32(device, 0x610184) & 0x03000000) >> 24;
+	return 2;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/wimmgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/wimmgv100.c
new file mode 100644
index 000000000000..89d783368b4f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/wimmgv100.c
@@ -0,0 +1,82 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "channv50.h"
+
+#include <core/client.h>
+
+#include <nvif/clc37b.h>
+#include <nvif/unpack.h>
+
+static void
+gv100_disp_wimm_intr(struct nv50_disp_chan *chan, bool en)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u32 mask = 0x00000001 << chan->head;
+	const u32 data = en ? mask : 0;
+	nvkm_mask(device, 0x611da8, mask, data);
+}
+
+const struct nv50_disp_chan_func
+gv100_disp_wimm = {
+	.init = gv100_disp_dmac_init,
+	.fini = gv100_disp_dmac_fini,
+	.intr = gv100_disp_wimm_intr,
+	.user = gv100_disp_chan_user,
+};
+
+static int
+gv100_disp_wimm_new_(const struct nv50_disp_chan_func *func,
+		     const struct nv50_disp_chan_mthd *mthd,
+		     struct nv50_disp *disp, int chid,
+		     const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		     struct nvkm_object **pobject)
+{
+	union {
+		struct nvc37b_window_imm_channel_dma_v0 v0;
+	} *args = argv;
+	struct nvkm_object *parent = oclass->parent;
+	int wndw, ret = -ENOSYS;
+	u64 push;
+
+	nvif_ioctl(parent, "create window imm channel dma size %d\n", argc);
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
+		nvif_ioctl(parent, "create window imm channel dma vers %d "
+				   "pushbuf %016llx index %d\n",
+			   args->v0.version, args->v0.pushbuf, args->v0.index);
+		if (!(disp->wndw.mask & BIT(args->v0.index)))
+			return -EINVAL;
+		push = args->v0.pushbuf;
+		wndw = args->v0.index;
+	} else
+		return ret;
+
+	return nv50_disp_dmac_new_(func, mthd, disp, chid + wndw,
+				   wndw, push, oclass, pobject);
+}
+
+int
+gv100_disp_wimm_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return gv100_disp_wimm_new_(&gv100_disp_wimm, NULL, disp, 33,
+				    oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/wndwgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/wndwgv100.c
new file mode 100644
index 000000000000..98911805aabf
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/wndwgv100.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "channv50.h"
+
+#include <core/client.h>
+
+#include <nvif/clc37e.h>
+#include <nvif/unpack.h>
+
+static const struct nv50_disp_mthd_list
+gv100_disp_wndw_mthd_base = {
+	.mthd = 0x0000,
+	.addr = 0x000000,
+	.data = {
+		{ 0x0200, 0x690200 },
+		{ 0x020c, 0x69020c },
+		{ 0x0210, 0x690210 },
+		{ 0x0214, 0x690214 },
+		{ 0x0218, 0x690218 },
+		{ 0x021c, 0x69021c },
+		{ 0x0220, 0x690220 },
+		{ 0x0224, 0x690224 },
+		{ 0x0228, 0x690228 },
+		{ 0x022c, 0x69022c },
+		{ 0x0230, 0x690230 },
+		{ 0x0234, 0x690234 },
+		{ 0x0238, 0x690238 },
+		{ 0x0240, 0x690240 },
+		{ 0x0244, 0x690244 },
+		{ 0x0248, 0x690248 },
+		{ 0x024c, 0x69024c },
+		{ 0x0250, 0x690250 },
+		{ 0x0254, 0x690254 },
+		{ 0x0260, 0x690260 },
+		{ 0x0264, 0x690264 },
+		{ 0x0268, 0x690268 },
+		{ 0x026c, 0x69026c },
+		{ 0x0270, 0x690270 },
+		{ 0x0274, 0x690274 },
+		{ 0x0280, 0x690280 },
+		{ 0x0284, 0x690284 },
+		{ 0x0288, 0x690288 },
+		{ 0x028c, 0x69028c },
+		{ 0x0290, 0x690290 },
+		{ 0x0298, 0x690298 },
+		{ 0x029c, 0x69029c },
+		{ 0x02a0, 0x6902a0 },
+		{ 0x02a4, 0x6902a4 },
+		{ 0x02a8, 0x6902a8 },
+		{ 0x02ac, 0x6902ac },
+		{ 0x02b0, 0x6902b0 },
+		{ 0x02b4, 0x6902b4 },
+		{ 0x02b8, 0x6902b8 },
+		{ 0x02bc, 0x6902bc },
+		{ 0x02c0, 0x6902c0 },
+		{ 0x02c4, 0x6902c4 },
+		{ 0x02c8, 0x6902c8 },
+		{ 0x02cc, 0x6902cc },
+		{ 0x02d0, 0x6902d0 },
+		{ 0x02d4, 0x6902d4 },
+		{ 0x02d8, 0x6902d8 },
+		{ 0x02dc, 0x6902dc },
+		{ 0x02e0, 0x6902e0 },
+		{ 0x02e4, 0x6902e4 },
+		{ 0x02e8, 0x6902e8 },
+		{ 0x02ec, 0x6902ec },
+		{ 0x02f0, 0x6902f0 },
+		{ 0x02f4, 0x6902f4 },
+		{ 0x02f8, 0x6902f8 },
+		{ 0x02fc, 0x6902fc },
+		{ 0x0300, 0x690300 },
+		{ 0x0304, 0x690304 },
+		{ 0x0308, 0x690308 },
+		{ 0x0310, 0x690310 },
+		{ 0x0314, 0x690314 },
+		{ 0x0318, 0x690318 },
+		{ 0x031c, 0x69031c },
+		{ 0x0320, 0x690320 },
+		{ 0x0324, 0x690324 },
+		{ 0x0328, 0x690328 },
+		{ 0x032c, 0x69032c },
+		{ 0x033c, 0x69033c },
+		{ 0x0340, 0x690340 },
+		{ 0x0344, 0x690344 },
+		{ 0x0348, 0x690348 },
+		{ 0x034c, 0x69034c },
+		{ 0x0350, 0x690350 },
+		{ 0x0354, 0x690354 },
+		{ 0x0358, 0x690358 },
+		{ 0x0364, 0x690364 },
+		{ 0x0368, 0x690368 },
+		{ 0x036c, 0x69036c },
+		{ 0x0370, 0x690370 },
+		{ 0x0374, 0x690374 },
+		{ 0x0380, 0x690380 },
+		{}
+	}
+};
+
+const struct nv50_disp_chan_mthd
+gv100_disp_wndw_mthd = {
+	.name = "Base",
+	.addr = 0x001000,
+	.prev = 0x000800,
+	.data = {
+		{ "Global", 1, &gv100_disp_wndw_mthd_base },
+		{}
+	}
+};
+
+static void
+gv100_disp_wndw_intr(struct nv50_disp_chan *chan, bool en)
+{
+	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
+	const u32 mask = 0x00000001 << chan->head;
+	const u32 data = en ? mask : 0;
+	nvkm_mask(device, 0x611da4, mask, data);
+}
+
+const struct nv50_disp_chan_func
+gv100_disp_wndw = {
+	.init = gv100_disp_dmac_init,
+	.fini = gv100_disp_dmac_fini,
+	.intr = gv100_disp_wndw_intr,
+	.user = gv100_disp_chan_user,
+	.bind = gv100_disp_dmac_bind,
+};
+
+static int
+gv100_disp_wndw_new_(const struct nv50_disp_chan_func *func,
+		     const struct nv50_disp_chan_mthd *mthd,
+		     struct nv50_disp *disp, int chid,
+		     const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		     struct nvkm_object **pobject)
+{
+	union {
+		struct nvc37e_window_channel_dma_v0 v0;
+	} *args = argv;
+	struct nvkm_object *parent = oclass->parent;
+	int wndw, ret = -ENOSYS;
+	u64 push;
+
+	nvif_ioctl(parent, "create window channel dma size %d\n", argc);
+	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
+		nvif_ioctl(parent, "create window channel dma vers %d "
+				   "pushbuf %016llx index %d\n",
+			   args->v0.version, args->v0.pushbuf, args->v0.index);
+		if (!(disp->wndw.mask & BIT(args->v0.index)))
+			return -EINVAL;
+		push = args->v0.pushbuf;
+		wndw = args->v0.index;
+	} else
+		return ret;
+
+	return nv50_disp_dmac_new_(func, mthd, disp, chid + wndw,
+				   wndw, push, oclass, pobject);
+}
+
+int
+gv100_disp_wndw_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nv50_disp *disp, struct nvkm_object **pobject)
+{
+	return gv100_disp_wndw_new_(&gv100_disp_wndw, &gv100_disp_wndw_mthd,
+				    disp, 1, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/dma/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/dma/Kbuild
index c4a2ce9b0d71..e96d1f57f9f9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/dma/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/dma/Kbuild
@@ -3,9 +3,11 @@ nvkm-y += nvkm/engine/dma/nv04.o
 nvkm-y += nvkm/engine/dma/nv50.o
 nvkm-y += nvkm/engine/dma/gf100.o
 nvkm-y += nvkm/engine/dma/gf119.o
+nvkm-y += nvkm/engine/dma/gv100.o
 
 nvkm-y += nvkm/engine/dma/user.o
 nvkm-y += nvkm/engine/dma/usernv04.o
 nvkm-y += nvkm/engine/dma/usernv50.o
 nvkm-y += nvkm/engine/dma/usergf100.o
 nvkm-y += nvkm/engine/dma/usergf119.o
+nvkm-y += nvkm/engine/dma/usergv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/dma/gv100.c
index 5ad5d0f5db05..c65a4c2ea93d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/dma/gv100.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2012 Red Hat Inc.
+ * Copyright 2018 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,20 +18,17 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Ben Skeggs
  */
-#include "channv50.h"
-#include "rootnv50.h"
-
-#include <nvif/class.h>
+#include "priv.h"
+#include "user.h"
 
-const struct nv50_disp_pioc_oclass
-g84_disp_oimm_oclass = {
-	.base.oclass = G82_DISP_OVERLAY,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = nv50_disp_oimm_new,
-	.func = &nv50_disp_pioc_func,
-	.chid = { 5, 5 },
+static const struct nvkm_dma_func
+gv100_dma = {
+	.class_new = gv100_dmaobj_new,
 };
+
+int
+gv100_dma_new(struct nvkm_device *device, int index, struct nvkm_dma **pdma)
+{
+	return nvkm_dma_new_(&gv100_dma, device, index, pdma);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/dma/user.h b/drivers/gpu/drm/nouveau/nvkm/engine/dma/user.h
index 4bbac8a21c71..9fe01fd75474 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/dma/user.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/dma/user.h
@@ -16,4 +16,6 @@ int gf100_dmaobj_new(struct nvkm_dma *, const struct nvkm_oclass *, void *, u32,
 		     struct nvkm_dmaobj **);
 int gf119_dmaobj_new(struct nvkm_dma *, const struct nvkm_oclass *, void *, u32,
 		     struct nvkm_dmaobj **);
+int gv100_dmaobj_new(struct nvkm_dma *, const struct nvkm_oclass *, void *, u32,
+		     struct nvkm_dmaobj **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/dma/usergv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/dma/usergv100.c
new file mode 100644
index 000000000000..39eba9fc82be
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/dma/usergv100.c
@@ -0,0 +1,119 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#define gv100_dmaobj(p) container_of((p), struct gv100_dmaobj, base)
+#include "user.h"
+
+#include <core/client.h>
+#include <core/gpuobj.h>
+#include <subdev/fb.h>
+
+#include <nvif/cl0002.h>
+#include <nvif/unpack.h>
+
+struct gv100_dmaobj {
+	struct nvkm_dmaobj base;
+	u32 flags0;
+};
+
+static int
+gv100_dmaobj_bind(struct nvkm_dmaobj *base, struct nvkm_gpuobj *parent,
+		  int align, struct nvkm_gpuobj **pgpuobj)
+{
+	struct gv100_dmaobj *dmaobj = gv100_dmaobj(base);
+	struct nvkm_device *device = dmaobj->base.dma->engine.subdev.device;
+	u64 start = dmaobj->base.start >> 8;
+	u64 limit = dmaobj->base.limit >> 8;
+	int ret;
+
+	ret = nvkm_gpuobj_new(device, 24, align, false, parent, pgpuobj);
+	if (ret == 0) {
+		nvkm_kmap(*pgpuobj);
+		nvkm_wo32(*pgpuobj, 0x00, dmaobj->flags0);
+		nvkm_wo32(*pgpuobj, 0x04, lower_32_bits(start));
+		nvkm_wo32(*pgpuobj, 0x08, upper_32_bits(start));
+		nvkm_wo32(*pgpuobj, 0x0c, lower_32_bits(limit));
+		nvkm_wo32(*pgpuobj, 0x10, upper_32_bits(limit));
+		nvkm_done(*pgpuobj);
+	}
+
+	return ret;
+}
+
+static const struct nvkm_dmaobj_func
+gv100_dmaobj_func = {
+	.bind = gv100_dmaobj_bind,
+};
+
+int
+gv100_dmaobj_new(struct nvkm_dma *dma, const struct nvkm_oclass *oclass,
+		 void *data, u32 size, struct nvkm_dmaobj **pdmaobj)
+{
+	union {
+		struct gf119_dma_v0 v0;
+	} *args;
+	struct nvkm_object *parent = oclass->parent;
+	struct gv100_dmaobj *dmaobj;
+	u32 kind, page;
+	int ret;
+
+	if (!(dmaobj = kzalloc(sizeof(*dmaobj), GFP_KERNEL)))
+		return -ENOMEM;
+	*pdmaobj = &dmaobj->base;
+
+	ret = nvkm_dmaobj_ctor(&gv100_dmaobj_func, dma, oclass,
+			       &data, &size, &dmaobj->base);
+	if (ret)
+		return ret;
+
+	ret  = -ENOSYS;
+	args = data;
+
+	nvif_ioctl(parent, "create gv100 dma size %d\n", size);
+	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
+		nvif_ioctl(parent,
+			   "create gv100 dma vers %d page %d kind %02x\n",
+			   args->v0.version, args->v0.page, args->v0.kind);
+		kind = args->v0.kind != 0;
+		page = args->v0.page != 0;
+	} else
+	if (size == 0) {
+		kind = 0;
+		page = GF119_DMA_V0_PAGE_SP;
+	} else
+		return ret;
+
+	if (kind)
+		dmaobj->flags0 |= 0x00100000;
+	if (page)
+		dmaobj->flags0 |= 0x00000040;
+	dmaobj->flags0 |= 0x00000004; /* rw */
+
+	switch (dmaobj->base.target) {
+	case NV_MEM_TARGET_VRAM       : dmaobj->flags0 |= 0x00000001; break;
+	case NV_MEM_TARGET_PCI        : dmaobj->flags0 |= 0x00000002; break;
+	case NV_MEM_TARGET_PCI_NOSNOOP: dmaobj->flags0 |= 0x00000003; break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
index 64e51838edf8..f00408577a6a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
@@ -15,6 +15,7 @@ nvkm-y += nvkm/engine/fifo/gm200.o
 nvkm-y += nvkm/engine/fifo/gm20b.o
 nvkm-y += nvkm/engine/fifo/gp100.o
 nvkm-y += nvkm/engine/fifo/gp10b.o
+nvkm-y += nvkm/engine/fifo/gv100.o
 
 nvkm-y += nvkm/engine/fifo/chan.o
 nvkm-y += nvkm/engine/fifo/channv50.o
@@ -31,6 +32,6 @@ nvkm-y += nvkm/engine/fifo/gpfifonv50.o
 nvkm-y += nvkm/engine/fifo/gpfifog84.o
 nvkm-y += nvkm/engine/fifo/gpfifogf100.o
 nvkm-y += nvkm/engine/fifo/gpfifogk104.o
-nvkm-y += nvkm/engine/fifo/gpfifogk110.o
-nvkm-y += nvkm/engine/fifo/gpfifogm200.o
-nvkm-y += nvkm/engine/fifo/gpfifogp100.o
+nvkm-y += nvkm/engine/fifo/gpfifogv100.o
+
+nvkm-y += nvkm/engine/fifo/usergv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
index 64f6b7654a08..c773caf21f6b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
@@ -30,6 +30,7 @@
 #include <subdev/mc.h>
 
 #include <nvif/event.h>
+#include <nvif/cl0080.h>
 #include <nvif/unpack.h>
 
 void
@@ -56,6 +57,12 @@ nvkm_fifo_start(struct nvkm_fifo *fifo, unsigned long *flags)
 }
 
 void
+nvkm_fifo_fault(struct nvkm_fifo *fifo, struct nvkm_fault_data *info)
+{
+	return fifo->func->fault(fifo, info);
+}
+
+void
 nvkm_fifo_chan_put(struct nvkm_fifo *fifo, unsigned long flags,
 		   struct nvkm_fifo_chan **pchan)
 {
@@ -209,6 +216,20 @@ nvkm_fifo_uevent(struct nvkm_fifo *fifo)
 }
 
 static int
+nvkm_fifo_class_new_(struct nvkm_device *device,
+		     const struct nvkm_oclass *oclass, void *data, u32 size,
+		     struct nvkm_object **pobject)
+{
+	struct nvkm_fifo *fifo = nvkm_fifo(oclass->engine);
+	return fifo->func->class_new(fifo, oclass, data, size, pobject);
+}
+
+static const struct nvkm_device_oclass
+nvkm_fifo_class_ = {
+	.ctor = nvkm_fifo_class_new_,
+};
+
+static int
 nvkm_fifo_class_new(struct nvkm_device *device,
 		    const struct nvkm_oclass *oclass, void *data, u32 size,
 		    struct nvkm_object **pobject)
@@ -232,13 +253,9 @@ nvkm_fifo_class_get(struct nvkm_oclass *oclass, int index,
 	int c = 0;
 
 	if (fifo->func->class_get) {
-		int ret = fifo->func->class_get(fifo, index, &sclass);
-		if (ret == 0) {
-			oclass->base = sclass->base;
-			oclass->engn = sclass;
-			*class = &nvkm_fifo_class;
-			return 0;
-		}
+		int ret = fifo->func->class_get(fifo, index, oclass);
+		if (ret == 0)
+			*class = &nvkm_fifo_class_;
 		return ret;
 	}
 
@@ -271,6 +288,20 @@ nvkm_fifo_fini(struct nvkm_engine *engine, bool suspend)
 }
 
 static int
+nvkm_fifo_info(struct nvkm_engine *engine, u64 mthd, u64 *data)
+{
+	struct nvkm_fifo *fifo = nvkm_fifo(engine);
+	switch (mthd) {
+	case NV_DEVICE_FIFO_CHANNELS: *data = fifo->nr; return 0;
+	default:
+		if (fifo->func->info)
+			return fifo->func->info(fifo, mthd, data);
+		break;
+	}
+	return -ENOSYS;
+}
+
+static int
 nvkm_fifo_oneinit(struct nvkm_engine *engine)
 {
 	struct nvkm_fifo *fifo = nvkm_fifo(engine);
@@ -311,6 +342,7 @@ nvkm_fifo = {
 	.dtor = nvkm_fifo_dtor,
 	.preinit = nvkm_fifo_preinit,
 	.oneinit = nvkm_fifo_oneinit,
+	.info = nvkm_fifo_info,
 	.init = nvkm_fifo_init,
 	.fini = nvkm_fifo_fini,
 	.intr = nvkm_fifo_intr,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/cgrp.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/cgrp.h
new file mode 100644
index 000000000000..d0ac60b06720
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/cgrp.h
@@ -0,0 +1,11 @@
+#ifndef __NVKM_FIFO_CGRP_H__
+#define __NVKM_FIFO_CGRP_H__
+#include "priv.h"
+
+struct nvkm_fifo_cgrp {
+	int id;
+	struct list_head head;
+	struct list_head chan;
+	int chan_nr;
+};
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h
index 1208e3d9dbe2..8e28ba6b2307 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h
@@ -10,6 +10,7 @@ struct gk104_fifo_chan {
 	struct gk104_fifo *fifo;
 	int runl;
 
+	struct nvkm_fifo_cgrp *cgrp;
 	struct list_head head;
 	bool killed;
 
@@ -19,11 +20,20 @@ struct gk104_fifo_chan {
 	} engn[NVKM_SUBDEV_NR];
 };
 
-int gk104_fifo_gpfifo_new(struct nvkm_fifo *, const struct nvkm_oclass *,
+extern const struct nvkm_fifo_chan_func gk104_fifo_gpfifo_func;
+
+int gk104_fifo_gpfifo_new(struct gk104_fifo *, const struct nvkm_oclass *,
 			  void *data, u32 size, struct nvkm_object **);
+void *gk104_fifo_gpfifo_dtor(struct nvkm_fifo_chan *);
+void gk104_fifo_gpfifo_init(struct nvkm_fifo_chan *);
+void gk104_fifo_gpfifo_fini(struct nvkm_fifo_chan *);
+int gk104_fifo_gpfifo_engine_ctor(struct nvkm_fifo_chan *, struct nvkm_engine *,
+				  struct nvkm_object *);
+void gk104_fifo_gpfifo_engine_dtor(struct nvkm_fifo_chan *,
+				   struct nvkm_engine *);
+int gk104_fifo_gpfifo_kick(struct gk104_fifo_chan *);
+int gk104_fifo_gpfifo_kick_locked(struct gk104_fifo_chan *);
 
-extern const struct nvkm_fifo_chan_oclass gk104_fifo_gpfifo_oclass;
-extern const struct nvkm_fifo_chan_oclass gk110_fifo_gpfifo_oclass;
-extern const struct nvkm_fifo_chan_oclass gm200_fifo_gpfifo_oclass;
-extern const struct nvkm_fifo_chan_oclass gp100_fifo_gpfifo_oclass;
+int gv100_fifo_gpfifo_new(struct gk104_fifo *, const struct nvkm_oclass *,
+			  void *data, u32 size, struct nvkm_object **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
index 84bd703dd897..a99046414a18 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
@@ -22,16 +22,19 @@
  * Authors: Ben Skeggs
  */
 #include "gk104.h"
+#include "cgrp.h"
 #include "changk104.h"
 
 #include <core/client.h>
 #include <core/gpuobj.h>
 #include <subdev/bar.h>
+#include <subdev/fault.h>
 #include <subdev/timer.h>
 #include <subdev/top.h>
 #include <engine/sw.h>
 
 #include <nvif/class.h>
+#include <nvif/cl0080.h>
 
 struct gk104_fifo_engine_status {
 	bool busy;
@@ -93,15 +96,39 @@ gk104_fifo_engine_status(struct gk104_fifo *fifo, int engn,
 }
 
 static int
+gk104_fifo_class_new(struct nvkm_fifo *base, const struct nvkm_oclass *oclass,
+		     void *argv, u32 argc, struct nvkm_object **pobject)
+{
+	struct gk104_fifo *fifo = gk104_fifo(base);
+	if (oclass->engn == &fifo->func->chan) {
+		const struct gk104_fifo_chan_user *user = oclass->engn;
+		return user->ctor(fifo, oclass, argv, argc, pobject);
+	} else
+	if (oclass->engn == &fifo->func->user) {
+		const struct gk104_fifo_user_user *user = oclass->engn;
+		return user->ctor(oclass, argv, argc, pobject);
+	}
+	WARN_ON(1);
+	return -EINVAL;
+}
+
+static int
 gk104_fifo_class_get(struct nvkm_fifo *base, int index,
-		     const struct nvkm_fifo_chan_oclass **psclass)
+		     struct nvkm_oclass *oclass)
 {
 	struct gk104_fifo *fifo = gk104_fifo(base);
 	int c = 0;
 
-	while ((*psclass = fifo->func->chan[c])) {
-		if (c++ == index)
-			return 0;
+	if (fifo->func->user.ctor && c++ == index) {
+		oclass->base =  fifo->func->user.user;
+		oclass->engn = &fifo->func->user;
+		return 0;
+	}
+
+	if (fifo->func->chan.ctor && c++ == index) {
+		oclass->base =  fifo->func->chan.user;
+		oclass->engn = &fifo->func->chan;
+		return 0;
 	}
 
 	return c;
@@ -124,10 +151,12 @@ gk104_fifo_uevent_init(struct nvkm_fifo *fifo)
 void
 gk104_fifo_runlist_commit(struct gk104_fifo *fifo, int runl)
 {
+	const struct gk104_fifo_runlist_func *func = fifo->func->runlist;
 	struct gk104_fifo_chan *chan;
 	struct nvkm_subdev *subdev = &fifo->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	struct nvkm_memory *mem;
+	struct nvkm_fifo_cgrp *cgrp;
 	int nr = 0;
 	int target;
 
@@ -137,9 +166,14 @@ gk104_fifo_runlist_commit(struct gk104_fifo *fifo, int runl)
 
 	nvkm_kmap(mem);
 	list_for_each_entry(chan, &fifo->runlist[runl].chan, head) {
-		nvkm_wo32(mem, (nr * 8) + 0, chan->base.chid);
-		nvkm_wo32(mem, (nr * 8) + 4, 0x00000000);
-		nr++;
+		func->chan(chan, mem, nr++ * func->size);
+	}
+
+	list_for_each_entry(cgrp, &fifo->runlist[runl].cgrp, head) {
+		func->cgrp(cgrp, mem, nr++ * func->size);
+		list_for_each_entry(chan, &cgrp->chan, head) {
+			func->chan(chan, mem, nr++ * func->size);
+		}
 	}
 	nvkm_done(mem);
 
@@ -155,10 +189,10 @@ gk104_fifo_runlist_commit(struct gk104_fifo *fifo, int runl)
 				    (target << 28));
 	nvkm_wr32(device, 0x002274, (runl << 20) | nr);
 
-	if (wait_event_timeout(fifo->runlist[runl].wait,
-			       !(nvkm_rd32(device, 0x002284 + (runl * 0x08))
-				       & 0x00100000),
-			       msecs_to_jiffies(2000)) == 0)
+	if (nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x002284 + (runl * 0x08)) & 0x00100000))
+			break;
+	) < 0)
 		nvkm_error(subdev, "runlist %d update timeout\n", runl);
 unlock:
 	mutex_unlock(&subdev->mutex);
@@ -167,19 +201,45 @@ unlock:
 void
 gk104_fifo_runlist_remove(struct gk104_fifo *fifo, struct gk104_fifo_chan *chan)
 {
+	struct nvkm_fifo_cgrp *cgrp = chan->cgrp;
 	mutex_lock(&fifo->base.engine.subdev.mutex);
-	list_del_init(&chan->head);
+	if (!list_empty(&chan->head)) {
+		list_del_init(&chan->head);
+		if (cgrp && !--cgrp->chan_nr)
+			list_del_init(&cgrp->head);
+	}
 	mutex_unlock(&fifo->base.engine.subdev.mutex);
 }
 
 void
 gk104_fifo_runlist_insert(struct gk104_fifo *fifo, struct gk104_fifo_chan *chan)
 {
+	struct nvkm_fifo_cgrp *cgrp = chan->cgrp;
 	mutex_lock(&fifo->base.engine.subdev.mutex);
-	list_add_tail(&chan->head, &fifo->runlist[chan->runl].chan);
+	if (cgrp) {
+		if (!cgrp->chan_nr++)
+			list_add_tail(&cgrp->head, &fifo->runlist[chan->runl].cgrp);
+		list_add_tail(&chan->head, &cgrp->chan);
+	} else {
+		list_add_tail(&chan->head, &fifo->runlist[chan->runl].chan);
+	}
 	mutex_unlock(&fifo->base.engine.subdev.mutex);
 }
 
+void
+gk104_fifo_runlist_chan(struct gk104_fifo_chan *chan,
+			struct nvkm_memory *memory, u32 offset)
+{
+	nvkm_wo32(memory, offset + 0, chan->base.chid);
+	nvkm_wo32(memory, offset + 4, 0x00000000);
+}
+
+const struct gk104_fifo_runlist_func
+gk104_fifo_runlist = {
+	.size = 8,
+	.chan = gk104_fifo_runlist_chan,
+};
+
 static void
 gk104_fifo_recover_work(struct work_struct *w)
 {
@@ -235,6 +295,32 @@ gk104_fifo_recover_runl(struct gk104_fifo *fifo, int runl)
 	schedule_work(&fifo->recover.work);
 }
 
+static struct gk104_fifo_chan *
+gk104_fifo_recover_chid(struct gk104_fifo *fifo, int runl, int chid)
+{
+	struct gk104_fifo_chan *chan;
+	struct nvkm_fifo_cgrp *cgrp;
+
+	list_for_each_entry(chan, &fifo->runlist[runl].chan, head) {
+		if (chan->base.chid == chid) {
+			list_del_init(&chan->head);
+			return chan;
+		}
+	}
+
+	list_for_each_entry(cgrp, &fifo->runlist[runl].cgrp, head) {
+		if (cgrp->id == chid) {
+			chan = list_first_entry(&cgrp->chan, typeof(*chan), head);
+			list_del_init(&chan->head);
+			if (!--cgrp->chan_nr)
+				list_del_init(&cgrp->head);
+			return chan;
+		}
+	}
+
+	return NULL;
+}
+
 static void
 gk104_fifo_recover_chan(struct nvkm_fifo *base, int chid)
 {
@@ -252,13 +338,10 @@ gk104_fifo_recover_chan(struct nvkm_fifo *base, int chid)
 		return;
 
 	/* Lookup SW state for channel, and mark it as dead. */
-	list_for_each_entry(chan, &fifo->runlist[runl].chan, head) {
-		if (chan->base.chid == chid) {
-			list_del_init(&chan->head);
-			chan->killed = true;
-			nvkm_fifo_kevent(&fifo->base, chid);
-			break;
-		}
+	chan = gk104_fifo_recover_chid(fifo, runl, chid);
+	if (chan) {
+		chan->killed = true;
+		nvkm_fifo_kevent(&fifo->base, chid);
 	}
 
 	/* Disable channel. */
@@ -347,6 +430,90 @@ gk104_fifo_recover_engn(struct gk104_fifo *fifo, int engn)
 	schedule_work(&fifo->recover.work);
 }
 
+static void
+gk104_fifo_fault(struct nvkm_fifo *base, struct nvkm_fault_data *info)
+{
+	struct gk104_fifo *fifo = gk104_fifo(base);
+	struct nvkm_subdev *subdev = &fifo->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	const struct nvkm_enum *er, *ee, *ec, *ea;
+	struct nvkm_engine *engine = NULL;
+	struct nvkm_fifo_chan *chan;
+	unsigned long flags;
+	char ct[8] = "HUB/", en[16] = "";
+	int engn;
+
+	er = nvkm_enum_find(fifo->func->fault.reason, info->reason);
+	ee = nvkm_enum_find(fifo->func->fault.engine, info->engine);
+	if (info->hub) {
+		ec = nvkm_enum_find(fifo->func->fault.hubclient, info->client);
+	} else {
+		ec = nvkm_enum_find(fifo->func->fault.gpcclient, info->client);
+		snprintf(ct, sizeof(ct), "GPC%d/", info->gpc);
+	}
+	ea = nvkm_enum_find(fifo->func->fault.access, info->access);
+
+	if (ee && ee->data2) {
+		switch (ee->data2) {
+		case NVKM_SUBDEV_BAR:
+			nvkm_mask(device, 0x001704, 0x00000000, 0x00000000);
+			break;
+		case NVKM_SUBDEV_INSTMEM:
+			nvkm_mask(device, 0x001714, 0x00000000, 0x00000000);
+			break;
+		case NVKM_ENGINE_IFB:
+			nvkm_mask(device, 0x001718, 0x00000000, 0x00000000);
+			break;
+		default:
+			engine = nvkm_device_engine(device, ee->data2);
+			break;
+		}
+	}
+
+	if (ee == NULL) {
+		enum nvkm_devidx engidx = nvkm_top_fault(device, info->engine);
+		if (engidx < NVKM_SUBDEV_NR) {
+			const char *src = nvkm_subdev_name[engidx];
+			char *dst = en;
+			do {
+				*dst++ = toupper(*src++);
+			} while(*src);
+			engine = nvkm_device_engine(device, engidx);
+		}
+	} else {
+		snprintf(en, sizeof(en), "%s", ee->name);
+	}
+
+	spin_lock_irqsave(&fifo->base.lock, flags);
+	chan = nvkm_fifo_chan_inst_locked(&fifo->base, info->inst);
+
+	nvkm_error(subdev,
+		   "fault %02x [%s] at %016llx engine %02x [%s] client %02x "
+		   "[%s%s] reason %02x [%s] on channel %d [%010llx %s]\n",
+		   info->access, ea ? ea->name : "", info->addr,
+		   info->engine, ee ? ee->name : en,
+		   info->client, ct, ec ? ec->name : "",
+		   info->reason, er ? er->name : "", chan ? chan->chid : -1,
+		   info->inst, chan ? chan->object.client->name : "unknown");
+
+	/* Kill the channel that caused the fault. */
+	if (chan)
+		gk104_fifo_recover_chan(&fifo->base, chan->chid);
+
+	/* Channel recovery will probably have already done this for the
+	 * correct engine(s), but just in case we can't find the channel
+	 * information...
+	 */
+	for (engn = 0; engn < fifo->engine_nr && engine; engn++) {
+		if (fifo->engine[engn].engine == engine) {
+			gk104_fifo_recover_engn(fifo, engn);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&fifo->base.lock, flags);
+}
+
 static const struct nvkm_enum
 gk104_fifo_bind_reason[] = {
 	{ 0x01, "BIND_NOT_UNBOUND" },
@@ -456,88 +623,21 @@ gk104_fifo_intr_fault(struct gk104_fifo *fifo, int unit)
 	u32 inst = nvkm_rd32(device, 0x002800 + (unit * 0x10));
 	u32 valo = nvkm_rd32(device, 0x002804 + (unit * 0x10));
 	u32 vahi = nvkm_rd32(device, 0x002808 + (unit * 0x10));
-	u32 stat = nvkm_rd32(device, 0x00280c + (unit * 0x10));
-	u32 gpc    = (stat & 0x1f000000) >> 24;
-	u32 client = (stat & 0x00001f00) >> 8;
-	u32 write  = (stat & 0x00000080);
-	u32 hub    = (stat & 0x00000040);
-	u32 reason = (stat & 0x0000000f);
-	const struct nvkm_enum *er, *eu, *ec;
-	struct nvkm_engine *engine = NULL;
-	struct nvkm_fifo_chan *chan;
-	unsigned long flags;
-	char gpcid[8] = "", en[16] = "";
-	int engn;
-
-	er = nvkm_enum_find(fifo->func->fault.reason, reason);
-	eu = nvkm_enum_find(fifo->func->fault.engine, unit);
-	if (hub) {
-		ec = nvkm_enum_find(fifo->func->fault.hubclient, client);
-	} else {
-		ec = nvkm_enum_find(fifo->func->fault.gpcclient, client);
-		snprintf(gpcid, sizeof(gpcid), "GPC%d/", gpc);
-	}
-
-	if (eu && eu->data2) {
-		switch (eu->data2) {
-		case NVKM_SUBDEV_BAR:
-			nvkm_mask(device, 0x001704, 0x00000000, 0x00000000);
-			break;
-		case NVKM_SUBDEV_INSTMEM:
-			nvkm_mask(device, 0x001714, 0x00000000, 0x00000000);
-			break;
-		case NVKM_ENGINE_IFB:
-			nvkm_mask(device, 0x001718, 0x00000000, 0x00000000);
-			break;
-		default:
-			engine = nvkm_device_engine(device, eu->data2);
-			break;
-		}
-	}
-
-	if (eu == NULL) {
-		enum nvkm_devidx engidx = nvkm_top_fault(device, unit);
-		if (engidx < NVKM_SUBDEV_NR) {
-			const char *src = nvkm_subdev_name[engidx];
-			char *dst = en;
-			do {
-				*dst++ = toupper(*src++);
-			} while(*src);
-			engine = nvkm_device_engine(device, engidx);
-		}
-	} else {
-		snprintf(en, sizeof(en), "%s", eu->name);
-	}
-
-	spin_lock_irqsave(&fifo->base.lock, flags);
-	chan = nvkm_fifo_chan_inst_locked(&fifo->base, (u64)inst << 12);
-
-	nvkm_error(subdev,
-		   "%s fault at %010llx engine %02x [%s] client %02x [%s%s] "
-		   "reason %02x [%s] on channel %d [%010llx %s]\n",
-		   write ? "write" : "read", (u64)vahi << 32 | valo,
-		   unit, en, client, gpcid, ec ? ec->name : "",
-		   reason, er ? er->name : "", chan ? chan->chid : -1,
-		   (u64)inst << 12,
-		   chan ? chan->object.client->name : "unknown");
-
-
-	/* Kill the channel that caused the fault. */
-	if (chan)
-		gk104_fifo_recover_chan(&fifo->base, chan->chid);
-
-	/* Channel recovery will probably have already done this for the
-	 * correct engine(s), but just in case we can't find the channel
-	 * information...
-	 */
-	for (engn = 0; engn < fifo->engine_nr && engine; engn++) {
-		if (fifo->engine[engn].engine == engine) {
-			gk104_fifo_recover_engn(fifo, engn);
-			break;
-		}
-	}
-
-	spin_unlock_irqrestore(&fifo->base.lock, flags);
+	u32 type = nvkm_rd32(device, 0x00280c + (unit * 0x10));
+	struct nvkm_fault_data info;
+
+	info.inst   =  (u64)inst << 12;
+	info.addr   = ((u64)vahi << 32) | valo;
+	info.time   = 0;
+	info.engine = unit;
+	info.valid  = 1;
+	info.gpc    = (type & 0x1f000000) >> 24;
+	info.client = (type & 0x00001f00) >> 8;
+	info.access = (type & 0x00000080) >> 7;
+	info.hub    = (type & 0x00000040) >> 6;
+	info.reason = (type & 0x000000ff);
+
+	nvkm_fifo_fault(&fifo->base, &info);
 }
 
 static const struct nvkm_bitfield gk104_fifo_pbdma_intr_0[] = {
@@ -766,6 +866,34 @@ gk104_fifo_fini(struct nvkm_fifo *base)
 }
 
 static int
+gk104_fifo_info(struct nvkm_fifo *base, u64 mthd, u64 *data)
+{
+	struct gk104_fifo *fifo = gk104_fifo(base);
+	switch (mthd) {
+	case NV_DEVICE_FIFO_RUNLISTS:
+		*data = (1ULL << fifo->runlist_nr) - 1;
+		return 0;
+	case NV_DEVICE_FIFO_RUNLIST_ENGINES(0)...
+	     NV_DEVICE_FIFO_RUNLIST_ENGINES(63): {
+		int runl = mthd - NV_DEVICE_FIFO_RUNLIST_ENGINES(0), engn;
+		if (runl < fifo->runlist_nr) {
+			unsigned long engm = fifo->runlist[runl].engm;
+			struct nvkm_engine *engine;
+			*data = 0;
+			for_each_set_bit(engn, &engm, fifo->engine_nr) {
+				if ((engine = fifo->engine[engn].engine))
+					*data |= BIT_ULL(engine->subdev.index);
+			}
+			return 0;
+		}
+	}
+		return -EINVAL;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int
 gk104_fifo_oneinit(struct nvkm_fifo *base)
 {
 	struct gk104_fifo *fifo = gk104_fifo(base);
@@ -813,19 +941,18 @@ gk104_fifo_oneinit(struct nvkm_fifo *base)
 	kfree(map);
 
 	for (i = 0; i < fifo->runlist_nr; i++) {
-		ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST,
-				      0x8000, 0x1000, false,
-				      &fifo->runlist[i].mem[0]);
-		if (ret)
-			return ret;
-
-		ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST,
-				      0x8000, 0x1000, false,
-				      &fifo->runlist[i].mem[1]);
-		if (ret)
-			return ret;
+		for (j = 0; j < ARRAY_SIZE(fifo->runlist[i].mem); j++) {
+			ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST,
+					      fifo->base.nr * 2/* TSG+chan */ *
+					      fifo->func->runlist->size,
+					      0x1000, false,
+					      &fifo->runlist[i].mem[j]);
+			if (ret)
+				return ret;
+		}
 
 		init_waitqueue_head(&fifo->runlist[i].wait);
+		INIT_LIST_HEAD(&fifo->runlist[i].cgrp);
 		INIT_LIST_HEAD(&fifo->runlist[i].chan);
 	}
 
@@ -868,6 +995,9 @@ gk104_fifo_init(struct nvkm_fifo *base)
 
 	nvkm_wr32(device, 0x002254, 0x10000000 | fifo->user.bar->addr >> 12);
 
+	if (fifo->func->init_pbdma_timeout)
+		fifo->func->init_pbdma_timeout(fifo);
+
 	nvkm_wr32(device, 0x002100, 0xffffffff);
 	nvkm_wr32(device, 0x002140, 0x7fffffff);
 }
@@ -894,13 +1024,16 @@ static const struct nvkm_fifo_func
 gk104_fifo_ = {
 	.dtor = gk104_fifo_dtor,
 	.oneinit = gk104_fifo_oneinit,
+	.info = gk104_fifo_info,
 	.init = gk104_fifo_init,
 	.fini = gk104_fifo_fini,
 	.intr = gk104_fifo_intr,
+	.fault = gk104_fifo_fault,
 	.uevent_init = gk104_fifo_uevent_init,
 	.uevent_fini = gk104_fifo_uevent_fini,
 	.recover_chan = gk104_fifo_recover_chan,
 	.class_get = gk104_fifo_class_get,
+	.class_new = gk104_fifo_class_new,
 };
 
 int
@@ -919,6 +1052,13 @@ gk104_fifo_new_(const struct gk104_fifo_func *func, struct nvkm_device *device,
 }
 
 const struct nvkm_enum
+gk104_fifo_fault_access[] = {
+	{ 0x0, "READ" },
+	{ 0x1, "WRITE" },
+	{}
+};
+
+const struct nvkm_enum
 gk104_fifo_fault_engine[] = {
 	{ 0x00, "GR", NULL, NVKM_ENGINE_GR },
 	{ 0x01, "DISPLAY" },
@@ -1035,14 +1175,13 @@ gk104_fifo_fault_gpcclient[] = {
 
 static const struct gk104_fifo_func
 gk104_fifo = {
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gk104_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gk104_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gk104_fifo_runlist,
+	.chan = {{0,0,KEPLER_CHANNEL_GPFIFO_A}, gk104_fifo_gpfifo_new },
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.h
index 1579785cf941..d295b81e18d6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.h
@@ -3,6 +3,7 @@
 #define __GK104_FIFO_H__
 #define gk104_fifo(p) container_of((p), struct gk104_fifo, base)
 #include "priv.h"
+struct nvkm_fifo_cgrp;
 
 #include <core/enum.h>
 #include <subdev/mmu.h>
@@ -31,6 +32,7 @@ struct gk104_fifo {
 		struct nvkm_memory *mem[2];
 		int next;
 		wait_queue_head_t wait;
+		struct list_head cgrp;
 		struct list_head chan;
 		u32 engm;
 	} runlist[16];
@@ -43,14 +45,36 @@ struct gk104_fifo {
 };
 
 struct gk104_fifo_func {
+	void (*init_pbdma_timeout)(struct gk104_fifo *);
+
 	struct {
+		const struct nvkm_enum *access;
 		const struct nvkm_enum *engine;
 		const struct nvkm_enum *reason;
 		const struct nvkm_enum *hubclient;
 		const struct nvkm_enum *gpcclient;
 	} fault;
 
-	const struct nvkm_fifo_chan_oclass *chan[];
+	const struct gk104_fifo_runlist_func {
+		u8 size;
+		void (*cgrp)(struct nvkm_fifo_cgrp *,
+			     struct nvkm_memory *, u32 offset);
+		void (*chan)(struct gk104_fifo_chan *,
+			     struct nvkm_memory *, u32 offset);
+	} *runlist;
+
+	struct gk104_fifo_user_user {
+		struct nvkm_sclass user;
+		int (*ctor)(const struct nvkm_oclass *, void *, u32,
+			    struct nvkm_object **);
+	} user;
+
+	struct gk104_fifo_chan_user {
+		struct nvkm_sclass user;
+		int (*ctor)(struct gk104_fifo *, const struct nvkm_oclass *,
+			    void *, u32, struct nvkm_object **);
+	} chan;
+	bool cgrp_force;
 };
 
 int gk104_fifo_new_(const struct gk104_fifo_func *, struct nvkm_device *,
@@ -59,30 +83,23 @@ void gk104_fifo_runlist_insert(struct gk104_fifo *, struct gk104_fifo_chan *);
 void gk104_fifo_runlist_remove(struct gk104_fifo *, struct gk104_fifo_chan *);
 void gk104_fifo_runlist_commit(struct gk104_fifo *, int runl);
 
-static inline u64
-gk104_fifo_engine_subdev(int engine)
-{
-	switch (engine) {
-	case 0: return (1ULL << NVKM_ENGINE_GR) |
-		       (1ULL << NVKM_ENGINE_SW) |
-		       (1ULL << NVKM_ENGINE_CE2);
-	case 1: return (1ULL << NVKM_ENGINE_MSPDEC);
-	case 2: return (1ULL << NVKM_ENGINE_MSPPP);
-	case 3: return (1ULL << NVKM_ENGINE_MSVLD);
-	case 4: return (1ULL << NVKM_ENGINE_CE0);
-	case 5: return (1ULL << NVKM_ENGINE_CE1);
-	case 6: return (1ULL << NVKM_ENGINE_MSENC);
-	default:
-		WARN_ON(1);
-		return 0;
-	}
-}
-
+extern const struct nvkm_enum gk104_fifo_fault_access[];
 extern const struct nvkm_enum gk104_fifo_fault_engine[];
 extern const struct nvkm_enum gk104_fifo_fault_reason[];
 extern const struct nvkm_enum gk104_fifo_fault_hubclient[];
 extern const struct nvkm_enum gk104_fifo_fault_gpcclient[];
+extern const struct gk104_fifo_runlist_func gk104_fifo_runlist;
+void gk104_fifo_runlist_chan(struct gk104_fifo_chan *,
+			     struct nvkm_memory *, u32);
+
+extern const struct gk104_fifo_runlist_func gk110_fifo_runlist;
+void gk110_fifo_runlist_cgrp(struct nvkm_fifo_cgrp *,
+			     struct nvkm_memory *, u32);
+
+void gk208_fifo_init_pbdma_timeout(struct gk104_fifo *);
 
 extern const struct nvkm_enum gm107_fifo_fault_engine[];
+extern const struct gk104_fifo_runlist_func gm107_fifo_runlist;
+
 extern const struct nvkm_enum gp100_fifo_fault_engine[];
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk110.c
index b2f8ab7bf847..ac7655a130fb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk110.c
@@ -22,18 +22,38 @@
  * Authors: Ben Skeggs
  */
 #include "gk104.h"
+#include "cgrp.h"
 #include "changk104.h"
 
+#include <core/memory.h>
+
+#include <nvif/class.h>
+
+void
+gk110_fifo_runlist_cgrp(struct nvkm_fifo_cgrp *cgrp,
+			struct nvkm_memory *memory, u32 offset)
+{
+	nvkm_wo32(memory, offset + 0, (cgrp->chan_nr << 26) | (128 << 18) |
+				      (3 << 14) | 0x00002000 | cgrp->id);
+	nvkm_wo32(memory, offset + 4, 0x00000000);
+}
+
+const struct gk104_fifo_runlist_func
+gk110_fifo_runlist = {
+	.size = 8,
+	.cgrp = gk110_fifo_runlist_cgrp,
+	.chan = gk104_fifo_runlist_chan,
+};
+
 static const struct gk104_fifo_func
 gk110_fifo = {
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gk104_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gk110_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gk110_fifo_runlist,
+	.chan = {{0,0,KEPLER_CHANNEL_GPFIFO_B}, gk104_fifo_gpfifo_new },
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk208.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk208.c
index 160617d376e4..5ea7e452cc66 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk208.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk208.c
@@ -24,16 +24,28 @@
 #include "gk104.h"
 #include "changk104.h"
 
+#include <nvif/class.h>
+
+void
+gk208_fifo_init_pbdma_timeout(struct gk104_fifo *fifo)
+{
+	struct nvkm_device *device = fifo->base.engine.subdev.device;
+	int i;
+
+	for (i = 0; i < fifo->pbdma_nr; i++)
+		nvkm_wr32(device, 0x04012c + (i * 0x2000), 0x0000ffff);
+}
+
 static const struct gk104_fifo_func
 gk208_fifo = {
+	.init_pbdma_timeout = gk208_fifo_init_pbdma_timeout,
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gk104_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gk104_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gk110_fifo_runlist,
+	.chan = {{0,0,KEPLER_CHANNEL_GPFIFO_A}, gk104_fifo_gpfifo_new },
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk20a.c
index be9f5c16ed7d..535a0eb67a5f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk20a.c
@@ -22,16 +22,18 @@
 #include "gk104.h"
 #include "changk104.h"
 
+#include <nvif/class.h>
+
 static const struct gk104_fifo_func
 gk20a_fifo = {
+	.init_pbdma_timeout = gk208_fifo_init_pbdma_timeout,
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gk104_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gk104_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gk110_fifo_runlist,
+	.chan = {{0,0,KEPLER_CHANNEL_GPFIFO_A}, gk104_fifo_gpfifo_new },
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm107.c
index 29c080683b32..79ae19b1db67 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm107.c
@@ -24,6 +24,25 @@
 #include "gk104.h"
 #include "changk104.h"
 
+#include <core/gpuobj.h>
+
+#include <nvif/class.h>
+
+static void
+gm107_fifo_runlist_chan(struct gk104_fifo_chan *chan,
+			struct nvkm_memory *memory, u32 offset)
+{
+	nvkm_wo32(memory, offset + 0, chan->base.chid);
+	nvkm_wo32(memory, offset + 4, chan->base.inst->addr >> 12);
+}
+
+const struct gk104_fifo_runlist_func
+gm107_fifo_runlist = {
+	.size = 8,
+	.cgrp = gk110_fifo_runlist_cgrp,
+	.chan = gm107_fifo_runlist_chan,
+};
+
 const struct nvkm_enum
 gm107_fifo_fault_engine[] = {
 	{ 0x01, "DISPLAY" },
@@ -49,14 +68,14 @@ gm107_fifo_fault_engine[] = {
 
 static const struct gk104_fifo_func
 gm107_fifo = {
+	.init_pbdma_timeout = gk208_fifo_init_pbdma_timeout,
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gm107_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gk110_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gm107_fifo_runlist,
+	.chan = {{0,0,KEPLER_CHANNEL_GPFIFO_B}, gk104_fifo_gpfifo_new },
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm200.c
index b069f785c5d8..49565faa854d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm200.c
@@ -24,16 +24,18 @@
 #include "gk104.h"
 #include "changk104.h"
 
+#include <nvif/class.h>
+
 static const struct gk104_fifo_func
 gm200_fifo = {
+	.init_pbdma_timeout = gk208_fifo_init_pbdma_timeout,
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gm107_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gm200_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gm107_fifo_runlist,
+	.chan = {{0,0,MAXWELL_CHANNEL_GPFIFO_A}, gk104_fifo_gpfifo_new },
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm20b.c
index 2ed87c2e8299..46736513bd11 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gm20b.c
@@ -22,16 +22,18 @@
 #include "gk104.h"
 #include "changk104.h"
 
+#include <nvif/class.h>
+
 static const struct gk104_fifo_func
 gm20b_fifo = {
+	.init_pbdma_timeout = gk208_fifo_init_pbdma_timeout,
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gm107_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gm200_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gm107_fifo_runlist,
+	.chan = {{0,0,MAXWELL_CHANNEL_GPFIFO_A}, gk104_fifo_gpfifo_new },
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp100.c
index 41f16cf5a918..e2f8f9087d7c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp100.c
@@ -24,6 +24,8 @@
 #include "gk104.h"
 #include "changk104.h"
 
+#include <nvif/class.h>
+
 const struct nvkm_enum
 gp100_fifo_fault_engine[] = {
 	{ 0x01, "DISPLAY" },
@@ -50,14 +52,15 @@ gp100_fifo_fault_engine[] = {
 
 static const struct gk104_fifo_func
 gp100_fifo = {
+	.init_pbdma_timeout = gk208_fifo_init_pbdma_timeout,
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gp100_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gp100_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gm107_fifo_runlist,
+	.chan = {{0,0,PASCAL_CHANNEL_GPFIFO_A}, gk104_fifo_gpfifo_new },
+	.cgrp_force = true,
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp10b.c
index 4af96c3e69ff..7733bf7c6545 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp10b.c
@@ -22,16 +22,19 @@
 #include "gk104.h"
 #include "changk104.h"
 
+#include <nvif/class.h>
+
 static const struct gk104_fifo_func
 gp10b_fifo = {
+	.init_pbdma_timeout = gk208_fifo_init_pbdma_timeout,
+	.fault.access = gk104_fifo_fault_access,
 	.fault.engine = gp100_fifo_fault_engine,
 	.fault.reason = gk104_fifo_fault_reason,
 	.fault.hubclient = gk104_fifo_fault_hubclient,
 	.fault.gpcclient = gk104_fifo_fault_gpcclient,
-	.chan = {
-		&gp100_fifo_gpfifo_oclass,
-		NULL
-	},
+	.runlist = &gm107_fifo_runlist,
+	.chan = {{0,0,PASCAL_CHANNEL_GPFIFO_A}, gk104_fifo_gpfifo_new },
+	.cgrp_force = true,
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c
index 80c87521bebe..118b37aea318 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "changk104.h"
+#include "cgrp.h"
 
 #include <core/client.h>
 #include <core/gpuobj.h>
@@ -33,27 +34,40 @@
 #include <nvif/cla06f.h>
 #include <nvif/unpack.h>
 
-static int
-gk104_fifo_gpfifo_kick(struct gk104_fifo_chan *chan)
+int
+gk104_fifo_gpfifo_kick_locked(struct gk104_fifo_chan *chan)
 {
 	struct gk104_fifo *fifo = chan->fifo;
 	struct nvkm_subdev *subdev = &fifo->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	struct nvkm_client *client = chan->base.object.client;
+	struct nvkm_fifo_cgrp *cgrp = chan->cgrp;
 	int ret = 0;
 
-	mutex_lock(&subdev->mutex);
-	nvkm_wr32(device, 0x002634, chan->base.chid);
+	if (cgrp)
+		nvkm_wr32(device, 0x002634, cgrp->id | 0x01000000);
+	else
+		nvkm_wr32(device, 0x002634, chan->base.chid);
 	if (nvkm_msec(device, 2000,
 		if (!(nvkm_rd32(device, 0x002634) & 0x00100000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "channel %d [%s] kick timeout\n",
-			   chan->base.chid, client->name);
+		nvkm_error(subdev, "%s %d [%s] kick timeout\n",
+			   cgrp ? "tsg" : "channel",
+			   cgrp ? cgrp->id : chan->base.chid, client->name);
 		nvkm_fifo_recover_chan(&fifo->base, chan->base.chid);
 		ret = -ETIMEDOUT;
 	}
-	mutex_unlock(&subdev->mutex);
+	return ret;
+}
+
+int
+gk104_fifo_gpfifo_kick(struct gk104_fifo_chan *chan)
+{
+	int ret;
+	mutex_lock(&chan->base.fifo->engine.subdev.mutex);
+	ret = gk104_fifo_gpfifo_kick_locked(chan);
+	mutex_unlock(&chan->base.fifo->engine.subdev.mutex);
 	return ret;
 }
 
@@ -62,9 +76,8 @@ gk104_fifo_gpfifo_engine_addr(struct nvkm_engine *engine)
 {
 	switch (engine->subdev.index) {
 	case NVKM_ENGINE_SW    :
-	case NVKM_ENGINE_CE0   :
-	case NVKM_ENGINE_CE1   :
-	case NVKM_ENGINE_CE2   : return 0x0000;
+	case NVKM_ENGINE_CE0...NVKM_ENGINE_CE_LAST:
+		return 0;
 	case NVKM_ENGINE_GR    : return 0x0210;
 	case NVKM_ENGINE_SEC   : return 0x0220;
 	case NVKM_ENGINE_MSPDEC: return 0x0250;
@@ -133,7 +146,7 @@ gk104_fifo_gpfifo_engine_init(struct nvkm_fifo_chan *base,
 	return 0;
 }
 
-static void
+void
 gk104_fifo_gpfifo_engine_dtor(struct nvkm_fifo_chan *base,
 			      struct nvkm_engine *engine)
 {
@@ -142,7 +155,7 @@ gk104_fifo_gpfifo_engine_dtor(struct nvkm_fifo_chan *base,
 	nvkm_gpuobj_del(&chan->engn[engine->subdev.index].inst);
 }
 
-static int
+int
 gk104_fifo_gpfifo_engine_ctor(struct nvkm_fifo_chan *base,
 			      struct nvkm_engine *engine,
 			      struct nvkm_object *object)
@@ -167,7 +180,7 @@ gk104_fifo_gpfifo_engine_ctor(struct nvkm_fifo_chan *base,
 			       chan->engn[engn].vma, NULL, 0);
 }
 
-static void
+void
 gk104_fifo_gpfifo_fini(struct nvkm_fifo_chan *base)
 {
 	struct gk104_fifo_chan *chan = gk104_fifo_chan(base);
@@ -185,7 +198,7 @@ gk104_fifo_gpfifo_fini(struct nvkm_fifo_chan *base)
 	nvkm_wr32(device, 0x800000 + coff, 0x00000000);
 }
 
-static void
+void
 gk104_fifo_gpfifo_init(struct nvkm_fifo_chan *base)
 {
 	struct gk104_fifo_chan *chan = gk104_fifo_chan(base);
@@ -205,13 +218,15 @@ gk104_fifo_gpfifo_init(struct nvkm_fifo_chan *base)
 	}
 }
 
-static void *
+void *
 gk104_fifo_gpfifo_dtor(struct nvkm_fifo_chan *base)
 {
-	return gk104_fifo_chan(base);
+	struct gk104_fifo_chan *chan = gk104_fifo_chan(base);
+	kfree(chan->cgrp);
+	return chan;
 }
 
-static const struct nvkm_fifo_chan_func
+const struct nvkm_fifo_chan_func
 gk104_fifo_gpfifo_func = {
 	.dtor = gk104_fifo_gpfifo_dtor,
 	.init = gk104_fifo_gpfifo_init,
@@ -223,62 +238,30 @@ gk104_fifo_gpfifo_func = {
 	.engine_fini = gk104_fifo_gpfifo_engine_fini,
 };
 
-struct gk104_fifo_chan_func {
-	u32 engine;
-	u64 subdev;
-};
-
 static int
-gk104_fifo_gpfifo_new_(const struct gk104_fifo_chan_func *func,
-		       struct gk104_fifo *fifo, u32 *engmask, u16 *chid,
+gk104_fifo_gpfifo_new_(struct gk104_fifo *fifo, u64 *runlists, u16 *chid,
 		       u64 vmm, u64 ioffset, u64 ilength,
 		       const struct nvkm_oclass *oclass,
 		       struct nvkm_object **pobject)
 {
 	struct gk104_fifo_chan *chan;
-	int runlist = -1, ret = -ENOSYS, i, j;
-	u32 engines = 0, present = 0;
+	int runlist = ffs(*runlists) -1, ret, i;
+	unsigned long engm;
 	u64 subdevs = 0;
 	u64 usermem;
 
-	if (!vmm)
+	if (!vmm || runlist < 0 || runlist >= fifo->runlist_nr)
 		return -EINVAL;
+	*runlists = BIT_ULL(runlist);
 
-	/* Determine which downstream engines are present */
-	for (i = 0; i < fifo->engine_nr; i++) {
-		struct nvkm_engine *engine = fifo->engine[i].engine;
-		if (engine) {
-			u64 submask = BIT_ULL(engine->subdev.index);
-			for (j = 0; func[j].subdev; j++) {
-				if (func[j].subdev & submask) {
-					present |= func[j].engine;
-					break;
-				}
-			}
-
-			if (!func[j].subdev)
-				continue;
-
-			if (runlist < 0 && (*engmask & present))
-				runlist = fifo->engine[i].runl;
-			if (runlist == fifo->engine[i].runl) {
-				engines |= func[j].engine;
-				subdevs |= func[j].subdev;
-			}
-		}
-	}
-
-	/* Just an engine mask query?  All done here! */
-	if (!*engmask) {
-		*engmask = present;
-		return nvkm_object_new(oclass, NULL, 0, pobject);
+	engm = fifo->runlist[runlist].engm;
+	for_each_set_bit(i, &engm, fifo->engine_nr) {
+		if (fifo->engine[i].engine)
+			subdevs |= BIT_ULL(fifo->engine[i].engine->subdev.index);
 	}
 
-	/* No runlist?  No supported engines. */
-	*engmask = present;
-	if (runlist < 0)
-		return -ENODEV;
-	*engmask = engines;
+	if (subdevs & BIT_ULL(NVKM_ENGINE_GR))
+		subdevs |= BIT_ULL(NVKM_ENGINE_SW);
 
 	/* Allocate the channel. */
 	if (!(chan = kzalloc(sizeof(*chan), GFP_KERNEL)))
@@ -297,6 +280,18 @@ gk104_fifo_gpfifo_new_(const struct gk104_fifo_chan_func *func,
 
 	*chid = chan->base.chid;
 
+	/* Hack to support GPUs where even individual channels should be
+	 * part of a channel group.
+	 */
+	if (fifo->func->cgrp_force) {
+		if (!(chan->cgrp = kmalloc(sizeof(*chan->cgrp), GFP_KERNEL)))
+			return -ENOMEM;
+		chan->cgrp->id = chan->base.chid;
+		INIT_LIST_HEAD(&chan->cgrp->head);
+		INIT_LIST_HEAD(&chan->cgrp->chan);
+		chan->cgrp->chan_nr = 0;
+	}
+
 	/* Clear channel control registers. */
 	usermem = chan->base.chid * 0x200;
 	ilength = order_base_2(ilength / 8);
@@ -328,45 +323,25 @@ gk104_fifo_gpfifo_new_(const struct gk104_fifo_chan_func *func,
 	return 0;
 }
 
-static const struct gk104_fifo_chan_func
-gk104_fifo_gpfifo[] = {
-	{ NVA06F_V0_ENGINE_SW | NVA06F_V0_ENGINE_GR,
-		BIT_ULL(NVKM_ENGINE_SW) | BIT_ULL(NVKM_ENGINE_GR)
-	},
-	{ NVA06F_V0_ENGINE_SEC   , BIT_ULL(NVKM_ENGINE_SEC   ) },
-	{ NVA06F_V0_ENGINE_MSVLD , BIT_ULL(NVKM_ENGINE_MSVLD ) },
-	{ NVA06F_V0_ENGINE_MSPDEC, BIT_ULL(NVKM_ENGINE_MSPDEC) },
-	{ NVA06F_V0_ENGINE_MSPPP , BIT_ULL(NVKM_ENGINE_MSPPP ) },
-	{ NVA06F_V0_ENGINE_MSENC , BIT_ULL(NVKM_ENGINE_MSENC ) },
-	{ NVA06F_V0_ENGINE_VIC   , BIT_ULL(NVKM_ENGINE_VIC   ) },
-	{ NVA06F_V0_ENGINE_NVDEC , BIT_ULL(NVKM_ENGINE_NVDEC ) },
-	{ NVA06F_V0_ENGINE_NVENC0, BIT_ULL(NVKM_ENGINE_NVENC0) },
-	{ NVA06F_V0_ENGINE_NVENC1, BIT_ULL(NVKM_ENGINE_NVENC1) },
-	{ NVA06F_V0_ENGINE_CE0   , BIT_ULL(NVKM_ENGINE_CE0   ) },
-	{ NVA06F_V0_ENGINE_CE1   , BIT_ULL(NVKM_ENGINE_CE1   ) },
-	{ NVA06F_V0_ENGINE_CE2   , BIT_ULL(NVKM_ENGINE_CE2   ) },
-	{}
-};
-
 int
-gk104_fifo_gpfifo_new(struct nvkm_fifo *base, const struct nvkm_oclass *oclass,
+gk104_fifo_gpfifo_new(struct gk104_fifo *fifo, const struct nvkm_oclass *oclass,
 		      void *data, u32 size, struct nvkm_object **pobject)
 {
 	struct nvkm_object *parent = oclass->parent;
 	union {
 		struct kepler_channel_gpfifo_a_v0 v0;
 	} *args = data;
-	struct gk104_fifo *fifo = gk104_fifo(base);
 	int ret = -ENOSYS;
 
 	nvif_ioctl(parent, "create channel gpfifo size %d\n", size);
 	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
 		nvif_ioctl(parent, "create channel gpfifo vers %d vmm %llx "
-				   "ioffset %016llx ilength %08x engine %08x\n",
+				   "ioffset %016llx ilength %08x "
+				   "runlist %016llx\n",
 			   args->v0.version, args->v0.vmm, args->v0.ioffset,
-			   args->v0.ilength, args->v0.engines);
-		return gk104_fifo_gpfifo_new_(gk104_fifo_gpfifo, fifo,
-					      &args->v0.engines,
+			   args->v0.ilength, args->v0.runlist);
+		return gk104_fifo_gpfifo_new_(fifo,
+					      &args->v0.runlist,
 					      &args->v0.chid,
 					       args->v0.vmm,
 					       args->v0.ioffset,
@@ -376,11 +351,3 @@ gk104_fifo_gpfifo_new(struct nvkm_fifo *base, const struct nvkm_oclass *oclass,
 
 	return ret;
 }
-
-const struct nvkm_fifo_chan_oclass
-gk104_fifo_gpfifo_oclass = {
-	.base.oclass = KEPLER_CHANNEL_GPFIFO_A,
-	.base.minver = 0,
-	.base.maxver = 0,
-	.ctor = gk104_fifo_gpfifo_new,
-};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogv100.c
new file mode 100644
index 000000000000..9598853ced56
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogv100.c
@@ -0,0 +1,225 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "changk104.h"
+#include "cgrp.h"
+
+#include <core/client.h>
+#include <core/gpuobj.h>
+
+#include <nvif/cla06f.h>
+#include <nvif/unpack.h>
+
+static int
+gv100_fifo_gpfifo_engine_valid(struct gk104_fifo_chan *chan, bool ce, bool valid)
+{
+	struct nvkm_subdev *subdev = &chan->base.fifo->engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	const u32 mask = ce ? 0x00020000 : 0x00010000;
+	const u32 data = valid ? mask : 0x00000000;
+	int ret;
+
+	/* Block runlist to prevent the channel from being rescheduled. */
+	mutex_lock(&subdev->mutex);
+	nvkm_mask(device, 0x002630, BIT(chan->runl), BIT(chan->runl));
+
+	/* Preempt the channel. */
+	ret = gk104_fifo_gpfifo_kick_locked(chan);
+	if (ret == 0) {
+		/* Update engine context validity. */
+		nvkm_kmap(chan->base.inst);
+		nvkm_mo32(chan->base.inst, 0x0ac, mask, data);
+		nvkm_done(chan->base.inst);
+	}
+
+	/* Resume runlist. */
+	nvkm_mask(device, 0x002630, BIT(chan->runl), 0);
+	mutex_unlock(&subdev->mutex);
+	return ret;
+}
+
+static int
+gv100_fifo_gpfifo_engine_fini(struct nvkm_fifo_chan *base,
+			      struct nvkm_engine *engine, bool suspend)
+{
+	struct gk104_fifo_chan *chan = gk104_fifo_chan(base);
+	struct nvkm_gpuobj *inst = chan->base.inst;
+	int ret;
+
+	if (engine->subdev.index >= NVKM_ENGINE_CE0 &&
+	    engine->subdev.index <= NVKM_ENGINE_CE_LAST)
+		return gk104_fifo_gpfifo_kick(chan);
+
+	ret = gv100_fifo_gpfifo_engine_valid(chan, false, false);
+	if (ret && suspend)
+		return ret;
+
+	nvkm_kmap(inst);
+	nvkm_wo32(inst, 0x0210, 0x00000000);
+	nvkm_wo32(inst, 0x0214, 0x00000000);
+	nvkm_done(inst);
+	return ret;
+}
+
+static int
+gv100_fifo_gpfifo_engine_init(struct nvkm_fifo_chan *base,
+			      struct nvkm_engine *engine)
+{
+	struct gk104_fifo_chan *chan = gk104_fifo_chan(base);
+	struct nvkm_gpuobj *inst = chan->base.inst;
+	u64 addr;
+
+	if (engine->subdev.index >= NVKM_ENGINE_CE0 &&
+	    engine->subdev.index <= NVKM_ENGINE_CE_LAST)
+		return 0;
+
+	addr = chan->engn[engine->subdev.index].vma->addr;
+	nvkm_kmap(inst);
+	nvkm_wo32(inst, 0x210, lower_32_bits(addr) | 0x00000004);
+	nvkm_wo32(inst, 0x214, upper_32_bits(addr));
+	nvkm_done(inst);
+
+	return gv100_fifo_gpfifo_engine_valid(chan, false, true);
+}
+
+const struct nvkm_fifo_chan_func
+gv100_fifo_gpfifo_func = {
+	.dtor = gk104_fifo_gpfifo_dtor,
+	.init = gk104_fifo_gpfifo_init,
+	.fini = gk104_fifo_gpfifo_fini,
+	.ntfy = gf100_fifo_chan_ntfy,
+	.engine_ctor = gk104_fifo_gpfifo_engine_ctor,
+	.engine_dtor = gk104_fifo_gpfifo_engine_dtor,
+	.engine_init = gv100_fifo_gpfifo_engine_init,
+	.engine_fini = gv100_fifo_gpfifo_engine_fini,
+};
+
+static int
+gv100_fifo_gpfifo_new_(struct gk104_fifo *fifo, u64 *runlists, u16 *chid,
+		       u64 vmm, u64 ioffset, u64 ilength,
+		       const struct nvkm_oclass *oclass,
+		       struct nvkm_object **pobject)
+{
+	struct gk104_fifo_chan *chan;
+	int runlist = ffs(*runlists) -1, ret, i;
+	unsigned long engm;
+	u64 subdevs = 0;
+	u64 usermem;
+
+	if (!vmm || runlist < 0 || runlist >= fifo->runlist_nr)
+		return -EINVAL;
+	*runlists = BIT_ULL(runlist);
+
+	engm = fifo->runlist[runlist].engm;
+	for_each_set_bit(i, &engm, fifo->engine_nr) {
+		if (fifo->engine[i].engine)
+			subdevs |= BIT_ULL(fifo->engine[i].engine->subdev.index);
+	}
+
+	/* Allocate the channel. */
+	if (!(chan = kzalloc(sizeof(*chan), GFP_KERNEL)))
+		return -ENOMEM;
+	*pobject = &chan->base.object;
+	chan->fifo = fifo;
+	chan->runl = runlist;
+	INIT_LIST_HEAD(&chan->head);
+
+	ret = nvkm_fifo_chan_ctor(&gv100_fifo_gpfifo_func, &fifo->base,
+				  0x1000, 0x1000, true, vmm, 0, subdevs,
+				  1, fifo->user.bar->addr, 0x200,
+				  oclass, &chan->base);
+	if (ret)
+		return ret;
+
+	*chid = chan->base.chid;
+
+	/* Hack to support GPUs where even individual channels should be
+	 * part of a channel group.
+	 */
+	if (fifo->func->cgrp_force) {
+		if (!(chan->cgrp = kmalloc(sizeof(*chan->cgrp), GFP_KERNEL)))
+			return -ENOMEM;
+		chan->cgrp->id = chan->base.chid;
+		INIT_LIST_HEAD(&chan->cgrp->head);
+		INIT_LIST_HEAD(&chan->cgrp->chan);
+		chan->cgrp->chan_nr = 0;
+	}
+
+	/* Clear channel control registers. */
+	usermem = chan->base.chid * 0x200;
+	ilength = order_base_2(ilength / 8);
+
+	nvkm_kmap(fifo->user.mem);
+	for (i = 0; i < 0x200; i += 4)
+		nvkm_wo32(fifo->user.mem, usermem + i, 0x00000000);
+	nvkm_done(fifo->user.mem);
+	usermem = nvkm_memory_addr(fifo->user.mem) + usermem;
+
+	/* RAMFC */
+	nvkm_kmap(chan->base.inst);
+	nvkm_wo32(chan->base.inst, 0x008, lower_32_bits(usermem));
+	nvkm_wo32(chan->base.inst, 0x00c, upper_32_bits(usermem));
+	nvkm_wo32(chan->base.inst, 0x010, 0x0000face);
+	nvkm_wo32(chan->base.inst, 0x030, 0x7ffff902);
+	nvkm_wo32(chan->base.inst, 0x048, lower_32_bits(ioffset));
+	nvkm_wo32(chan->base.inst, 0x04c, upper_32_bits(ioffset) |
+					  (ilength << 16));
+	nvkm_wo32(chan->base.inst, 0x084, 0x20400000);
+	nvkm_wo32(chan->base.inst, 0x094, 0x30000001);
+	nvkm_wo32(chan->base.inst, 0x0e4, 0x00000020);
+	nvkm_wo32(chan->base.inst, 0x0e8, chan->base.chid);
+	nvkm_wo32(chan->base.inst, 0x0f4, 0x00001100);
+	nvkm_wo32(chan->base.inst, 0x0f8, 0x10003080);
+	nvkm_mo32(chan->base.inst, 0x218, 0x00000000, 0x00000000);
+	nvkm_wo32(chan->base.inst, 0x220, 0x020a1000);
+	nvkm_wo32(chan->base.inst, 0x224, 0x00000000);
+	nvkm_done(chan->base.inst);
+	return gv100_fifo_gpfifo_engine_valid(chan, true, true);
+}
+
+int
+gv100_fifo_gpfifo_new(struct gk104_fifo *fifo, const struct nvkm_oclass *oclass,
+		      void *data, u32 size, struct nvkm_object **pobject)
+{
+	struct nvkm_object *parent = oclass->parent;
+	union {
+		struct kepler_channel_gpfifo_a_v0 v0;
+	} *args = data;
+	int ret = -ENOSYS;
+
+	nvif_ioctl(parent, "create channel gpfifo size %d\n", size);
+	if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) {
+		nvif_ioctl(parent, "create channel gpfifo vers %d vmm %llx "
+				   "ioffset %016llx ilength %08x "
+				   "runlist %016llx\n",
+			   args->v0.version, args->v0.vmm, args->v0.ioffset,
+			   args->v0.ilength, args->v0.runlist);
+		return gv100_fifo_gpfifo_new_(fifo,
+					      &args->v0.runlist,
+					      &args->v0.chid,
+					       args->v0.vmm,
+					       args->v0.ioffset,
+					       args->v0.ilength,
+					      oclass, pobject);
+	}
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gv100.c
new file mode 100644
index 000000000000..4e1d159c0ae7
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gv100.c
@@ -0,0 +1,306 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gk104.h"
+#include "cgrp.h"
+#include "changk104.h"
+#include "user.h"
+
+#include <core/gpuobj.h>
+
+#include <nvif/class.h>
+
+static void
+gv100_fifo_runlist_chan(struct gk104_fifo_chan *chan,
+			struct nvkm_memory *memory, u32 offset)
+{
+	struct nvkm_memory *usermem = chan->fifo->user.mem;
+	const u64 user = nvkm_memory_addr(usermem) + (chan->base.chid * 0x200);
+	const u64 inst = chan->base.inst->addr;
+
+	nvkm_wo32(memory, offset + 0x0, lower_32_bits(user));
+	nvkm_wo32(memory, offset + 0x4, upper_32_bits(user));
+	nvkm_wo32(memory, offset + 0x8, lower_32_bits(inst) | chan->base.chid);
+	nvkm_wo32(memory, offset + 0xc, upper_32_bits(inst));
+}
+
+static void
+gv100_fifo_runlist_cgrp(struct nvkm_fifo_cgrp *cgrp,
+			struct nvkm_memory *memory, u32 offset)
+{
+	nvkm_wo32(memory, offset + 0x0, (128 << 24) | (3 << 16) | 0x00000001);
+	nvkm_wo32(memory, offset + 0x4, cgrp->chan_nr);
+	nvkm_wo32(memory, offset + 0x8, cgrp->id);
+	nvkm_wo32(memory, offset + 0xc, 0x00000000);
+}
+
+const struct gk104_fifo_runlist_func
+gv100_fifo_runlist = {
+	.size = 16,
+	.cgrp = gv100_fifo_runlist_cgrp,
+	.chan = gv100_fifo_runlist_chan,
+};
+
+static const struct nvkm_enum
+gv100_fifo_fault_gpcclient[] = {
+	{ 0x00, "T1_0" },
+	{ 0x01, "T1_1" },
+	{ 0x02, "T1_2" },
+	{ 0x03, "T1_3" },
+	{ 0x04, "T1_4" },
+	{ 0x05, "T1_5" },
+	{ 0x06, "T1_6" },
+	{ 0x07, "T1_7" },
+	{ 0x08, "PE_0" },
+	{ 0x09, "PE_1" },
+	{ 0x0a, "PE_2" },
+	{ 0x0b, "PE_3" },
+	{ 0x0c, "PE_4" },
+	{ 0x0d, "PE_5" },
+	{ 0x0e, "PE_6" },
+	{ 0x0f, "PE_7" },
+	{ 0x10, "RAST" },
+	{ 0x11, "GCC" },
+	{ 0x12, "GPCCS" },
+	{ 0x13, "PROP_0" },
+	{ 0x14, "PROP_1" },
+	{ 0x15, "PROP_2" },
+	{ 0x16, "PROP_3" },
+	{ 0x17, "GPM" },
+	{ 0x18, "LTP_UTLB_0" },
+	{ 0x19, "LTP_UTLB_1" },
+	{ 0x1a, "LTP_UTLB_2" },
+	{ 0x1b, "LTP_UTLB_3" },
+	{ 0x1c, "LTP_UTLB_4" },
+	{ 0x1d, "LTP_UTLB_5" },
+	{ 0x1e, "LTP_UTLB_6" },
+	{ 0x1f, "LTP_UTLB_7" },
+	{ 0x20, "RGG_UTLB" },
+	{ 0x21, "T1_8" },
+	{ 0x22, "T1_9" },
+	{ 0x23, "T1_10" },
+	{ 0x24, "T1_11" },
+	{ 0x25, "T1_12" },
+	{ 0x26, "T1_13" },
+	{ 0x27, "T1_14" },
+	{ 0x28, "T1_15" },
+	{ 0x29, "TPCCS_0" },
+	{ 0x2a, "TPCCS_1" },
+	{ 0x2b, "TPCCS_2" },
+	{ 0x2c, "TPCCS_3" },
+	{ 0x2d, "TPCCS_4" },
+	{ 0x2e, "TPCCS_5" },
+	{ 0x2f, "TPCCS_6" },
+	{ 0x30, "TPCCS_7" },
+	{ 0x31, "PE_8" },
+	{ 0x32, "PE_9" },
+	{ 0x33, "TPCCS_8" },
+	{ 0x34, "TPCCS_9" },
+	{ 0x35, "T1_16" },
+	{ 0x36, "T1_17" },
+	{ 0x37, "T1_18" },
+	{ 0x38, "T1_19" },
+	{ 0x39, "PE_10" },
+	{ 0x3a, "PE_11" },
+	{ 0x3b, "TPCCS_10" },
+	{ 0x3c, "TPCCS_11" },
+	{ 0x3d, "T1_20" },
+	{ 0x3e, "T1_21" },
+	{ 0x3f, "T1_22" },
+	{ 0x40, "T1_23" },
+	{ 0x41, "PE_12" },
+	{ 0x42, "PE_13" },
+	{ 0x43, "TPCCS_12" },
+	{ 0x44, "TPCCS_13" },
+	{ 0x45, "T1_24" },
+	{ 0x46, "T1_25" },
+	{ 0x47, "T1_26" },
+	{ 0x48, "T1_27" },
+	{ 0x49, "PE_14" },
+	{ 0x4a, "PE_15" },
+	{ 0x4b, "TPCCS_14" },
+	{ 0x4c, "TPCCS_15" },
+	{ 0x4d, "T1_28" },
+	{ 0x4e, "T1_29" },
+	{ 0x4f, "T1_30" },
+	{ 0x50, "T1_31" },
+	{ 0x51, "PE_16" },
+	{ 0x52, "PE_17" },
+	{ 0x53, "TPCCS_16" },
+	{ 0x54, "TPCCS_17" },
+	{ 0x55, "T1_32" },
+	{ 0x56, "T1_33" },
+	{ 0x57, "T1_34" },
+	{ 0x58, "T1_35" },
+	{ 0x59, "PE_18" },
+	{ 0x5a, "PE_19" },
+	{ 0x5b, "TPCCS_18" },
+	{ 0x5c, "TPCCS_19" },
+	{ 0x5d, "T1_36" },
+	{ 0x5e, "T1_37" },
+	{ 0x5f, "T1_38" },
+	{ 0x60, "T1_39" },
+	{}
+};
+
+static const struct nvkm_enum
+gv100_fifo_fault_hubclient[] = {
+	{ 0x00, "VIP" },
+	{ 0x01, "CE0" },
+	{ 0x02, "CE1" },
+	{ 0x03, "DNISO" },
+	{ 0x04, "FE" },
+	{ 0x05, "FECS" },
+	{ 0x06, "HOST" },
+	{ 0x07, "HOST_CPU" },
+	{ 0x08, "HOST_CPU_NB" },
+	{ 0x09, "ISO" },
+	{ 0x0a, "MMU" },
+	{ 0x0b, "NVDEC" },
+	{ 0x0d, "NVENC1" },
+	{ 0x0e, "NISO" },
+	{ 0x0f, "P2P" },
+	{ 0x10, "PD" },
+	{ 0x11, "PERF" },
+	{ 0x12, "PMU" },
+	{ 0x13, "RASTERTWOD" },
+	{ 0x14, "SCC" },
+	{ 0x15, "SCC_NB" },
+	{ 0x16, "SEC" },
+	{ 0x17, "SSYNC" },
+	{ 0x18, "CE2" },
+	{ 0x19, "XV" },
+	{ 0x1a, "MMU_NB" },
+	{ 0x1b, "NVENC0" },
+	{ 0x1c, "DFALCON" },
+	{ 0x1d, "SKED" },
+	{ 0x1e, "AFALCON" },
+	{ 0x1f, "DONT_CARE" },
+	{ 0x20, "HSCE0" },
+	{ 0x21, "HSCE1" },
+	{ 0x22, "HSCE2" },
+	{ 0x23, "HSCE3" },
+	{ 0x24, "HSCE4" },
+	{ 0x25, "HSCE5" },
+	{ 0x26, "HSCE6" },
+	{ 0x27, "HSCE7" },
+	{ 0x28, "HSCE8" },
+	{ 0x29, "HSCE9" },
+	{ 0x2a, "HSHUB" },
+	{ 0x2b, "PTP_X0" },
+	{ 0x2c, "PTP_X1" },
+	{ 0x2d, "PTP_X2" },
+	{ 0x2e, "PTP_X3" },
+	{ 0x2f, "PTP_X4" },
+	{ 0x30, "PTP_X5" },
+	{ 0x31, "PTP_X6" },
+	{ 0x32, "PTP_X7" },
+	{ 0x33, "NVENC2" },
+	{ 0x34, "VPR_SCRUBBER0" },
+	{ 0x35, "VPR_SCRUBBER1" },
+	{ 0x36, "DWBIF" },
+	{ 0x37, "FBFALCON" },
+	{ 0x38, "CE_SHIM" },
+	{ 0x39, "GSP" },
+	{}
+};
+
+static const struct nvkm_enum
+gv100_fifo_fault_reason[] = {
+	{ 0x00, "PDE" },
+	{ 0x01, "PDE_SIZE" },
+	{ 0x02, "PTE" },
+	{ 0x03, "VA_LIMIT_VIOLATION" },
+	{ 0x04, "UNBOUND_INST_BLOCK" },
+	{ 0x05, "PRIV_VIOLATION" },
+	{ 0x06, "RO_VIOLATION" },
+	{ 0x07, "WO_VIOLATION" },
+	{ 0x08, "PITCH_MASK_VIOLATION" },
+	{ 0x09, "WORK_CREATION" },
+	{ 0x0a, "UNSUPPORTED_APERTURE" },
+	{ 0x0b, "COMPRESSION_FAILURE" },
+	{ 0x0c, "UNSUPPORTED_KIND" },
+	{ 0x0d, "REGION_VIOLATION" },
+	{ 0x0e, "POISONED" },
+	{ 0x0f, "ATOMIC_VIOLATION" },
+	{}
+};
+
+static const struct nvkm_enum
+gv100_fifo_fault_engine[] = {
+	{ 0x01, "DISPLAY" },
+	{ 0x03, "PTP" },
+	{ 0x04, "BAR1", NULL, NVKM_SUBDEV_BAR },
+	{ 0x05, "BAR2", NULL, NVKM_SUBDEV_INSTMEM },
+	{ 0x06, "PWR_PMU" },
+	{ 0x08, "IFB", NULL, NVKM_ENGINE_IFB },
+	{ 0x09, "PERF" },
+	{ 0x1f, "PHYSICAL" },
+	{ 0x20, "HOST0" },
+	{ 0x21, "HOST1" },
+	{ 0x22, "HOST2" },
+	{ 0x23, "HOST3" },
+	{ 0x24, "HOST4" },
+	{ 0x25, "HOST5" },
+	{ 0x26, "HOST6" },
+	{ 0x27, "HOST7" },
+	{ 0x28, "HOST8" },
+	{ 0x29, "HOST9" },
+	{ 0x2a, "HOST10" },
+	{ 0x2b, "HOST11" },
+	{ 0x2c, "HOST12" },
+	{ 0x2d, "HOST13" },
+	{}
+};
+
+static const struct nvkm_enum
+gv100_fifo_fault_access[] = {
+	{ 0x0, "VIRT_READ" },
+	{ 0x1, "VIRT_WRITE" },
+	{ 0x2, "VIRT_ATOMIC" },
+	{ 0x3, "VIRT_PREFETCH" },
+	{ 0x4, "VIRT_ATOMIC_WEAK" },
+	{ 0x8, "PHYS_READ" },
+	{ 0x9, "PHYS_WRITE" },
+	{ 0xa, "PHYS_ATOMIC" },
+	{ 0xb, "PHYS_PREFETCH" },
+	{}
+};
+
+static const struct gk104_fifo_func
+gv100_fifo = {
+	.init_pbdma_timeout = gk208_fifo_init_pbdma_timeout,
+	.fault.access = gv100_fifo_fault_access,
+	.fault.engine = gv100_fifo_fault_engine,
+	.fault.reason = gv100_fifo_fault_reason,
+	.fault.hubclient = gv100_fifo_fault_hubclient,
+	.fault.gpcclient = gv100_fifo_fault_gpcclient,
+	.runlist = &gv100_fifo_runlist,
+	.user = {{-1,-1,VOLTA_USERMODE_A      }, gv100_fifo_user_new   },
+	.chan = {{ 0, 0,VOLTA_CHANNEL_GPFIFO_A}, gv100_fifo_gpfifo_new },
+	.cgrp_force = true,
+};
+
+int
+gv100_fifo_new(struct nvkm_device *device, int index, struct nvkm_fifo **pfifo)
+{
+	return gk104_fifo_new_(&gv100_fifo, device, index, 4096, pfifo);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
index ae76b1aaccd4..d5acbba293f4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
@@ -18,16 +18,19 @@ struct nvkm_fifo_chan_oclass;
 struct nvkm_fifo_func {
 	void *(*dtor)(struct nvkm_fifo *);
 	int (*oneinit)(struct nvkm_fifo *);
+	int (*info)(struct nvkm_fifo *, u64 mthd, u64 *data);
 	void (*init)(struct nvkm_fifo *);
 	void (*fini)(struct nvkm_fifo *);
 	void (*intr)(struct nvkm_fifo *);
+	void (*fault)(struct nvkm_fifo *, struct nvkm_fault_data *);
 	void (*pause)(struct nvkm_fifo *, unsigned long *);
 	void (*start)(struct nvkm_fifo *, unsigned long *);
 	void (*uevent_init)(struct nvkm_fifo *);
 	void (*uevent_fini)(struct nvkm_fifo *);
 	void (*recover_chan)(struct nvkm_fifo *, int chid);
-	int (*class_get)(struct nvkm_fifo *, int index,
-			 const struct nvkm_fifo_chan_oclass **);
+	int (*class_get)(struct nvkm_fifo *, int index, struct nvkm_oclass *);
+	int (*class_new)(struct nvkm_fifo *, const struct nvkm_oclass *,
+			 void *, u32, struct nvkm_object **);
 	const struct nvkm_fifo_chan_oclass *chan[];
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/user.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/user.h
new file mode 100644
index 000000000000..ed840921ebe8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/user.h
@@ -0,0 +1,6 @@
+#ifndef __NVKM_FIFO_USER_H__
+#define __NVKM_FIFO_USER_H__
+#include "priv.h"
+int gv100_fifo_user_new(const struct nvkm_oclass *, void *, u32,
+			struct nvkm_object **);
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/usergv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/usergv100.c
new file mode 100644
index 000000000000..3dc3b8b312de
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/usergv100.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "user.h"
+
+static int
+gv100_fifo_user_map(struct nvkm_object *object, void *argv, u32 argc,
+		    enum nvkm_object_map *type, u64 *addr, u64 *size)
+{
+	struct nvkm_device *device = object->engine->subdev.device;
+	*addr = 0x810000 + device->func->resource_addr(device, 0);
+	*size = 0x010000;
+	*type = NVKM_OBJECT_MAP_IO;
+	return 0;
+}
+
+static const struct nvkm_object_func
+gv100_fifo_user = {
+	.map = gv100_fifo_user_map,
+};
+
+int
+gv100_fifo_user_new(const struct nvkm_oclass *oclass, void *argv, u32 argc,
+		    struct nvkm_object **pobject)
+{
+	return nvkm_object_new_(&gv100_fifo_user, oclass, argv, argc, pobject);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
index 8a22558b7b52..93e3733f54e2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
@@ -33,8 +33,10 @@ nvkm-y += nvkm/engine/gr/gm200.o
 nvkm-y += nvkm/engine/gr/gm20b.o
 nvkm-y += nvkm/engine/gr/gp100.o
 nvkm-y += nvkm/engine/gr/gp102.o
+nvkm-y += nvkm/engine/gr/gp104.o
 nvkm-y += nvkm/engine/gr/gp107.o
 nvkm-y += nvkm/engine/gr/gp10b.o
+nvkm-y += nvkm/engine/gr/gv100.o
 
 nvkm-y += nvkm/engine/gr/ctxnv40.o
 nvkm-y += nvkm/engine/gr/ctxnv50.o
@@ -54,4 +56,6 @@ nvkm-y += nvkm/engine/gr/ctxgm200.o
 nvkm-y += nvkm/engine/gr/ctxgm20b.o
 nvkm-y += nvkm/engine/gr/ctxgp100.o
 nvkm-y += nvkm/engine/gr/ctxgp102.o
+nvkm-y += nvkm/engine/gr/ctxgp104.o
 nvkm-y += nvkm/engine/gr/ctxgp107.o
+nvkm-y += nvkm/engine/gr/ctxgv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
index 881015080d83..e813a3f8ea93 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
@@ -850,12 +850,17 @@ gf100_grctx_init_gcc_0[] = {
 };
 
 const struct gf100_gr_pack
-gf100_grctx_pack_gpc[] = {
+gf100_grctx_pack_gpc_0[] = {
 	{ gf100_grctx_init_gpc_unk_0 },
 	{ gf100_grctx_init_prop_0 },
 	{ gf100_grctx_init_gpc_unk_1 },
 	{ gf100_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
+	{}
+};
+
+const struct gf100_gr_pack
+gf100_grctx_pack_gpc_1[] = {
 	{ gf100_grctx_init_crstr_0 },
 	{ gf100_grctx_init_gpm_0 },
 	{ gf100_grctx_init_gcc_0 },
@@ -1025,6 +1030,13 @@ gf100_grctx_mmio_item(struct gf100_grctx *info, u32 addr, u32 data,
 }
 
 void
+gf100_grctx_generate_r419cb8(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x419cb8, 0x00007c00, 0x00000000);
+}
+
+void
 gf100_grctx_generate_bundle(struct gf100_grctx *info)
 {
 	const struct gf100_grctx_func *grctx = info->gr->func->grctx;
@@ -1080,89 +1092,38 @@ gf100_grctx_generate_unkn(struct gf100_gr *gr)
 }
 
 void
-gf100_grctx_generate_tpcid(struct gf100_gr *gr)
-{
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-	int gpc, tpc, id;
-
-	for (tpc = 0, id = 0; tpc < 4; tpc++) {
-		for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-			if (tpc < gr->tpc_nr[gpc]) {
-				nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x698), id);
-				nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x4e8), id);
-				nvkm_wr32(device, GPC_UNIT(gpc, 0x0c10 + tpc * 4), id);
-				nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), id);
-				id++;
-			}
-
-			nvkm_wr32(device, GPC_UNIT(gpc, 0x0c08), gr->tpc_nr[gpc]);
-			nvkm_wr32(device, GPC_UNIT(gpc, 0x0c8c), gr->tpc_nr[gpc]);
-		}
-	}
-}
-
-void
-gf100_grctx_generate_r406028(struct gf100_gr *gr)
-{
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-	u32 tmp[GPC_MAX / 8] = {}, i = 0;
-	for (i = 0; i < gr->gpc_nr; i++)
-		tmp[i / 8] |= gr->tpc_nr[i] << ((i % 8) * 4);
-	for (i = 0; i < 4; i++) {
-		nvkm_wr32(device, 0x406028 + (i * 4), tmp[i]);
-		nvkm_wr32(device, 0x405870 + (i * 4), tmp[i]);
-	}
-}
-
-void
 gf100_grctx_generate_r4060a8(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	u8  tpcnr[GPC_MAX], data[TPC_MAX];
-	int gpc, tpc, i;
-
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-	memset(data, 0x1f, sizeof(data));
-
-	gpc = -1;
-	for (tpc = 0; tpc < gr->tpc_total; tpc++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpcnr[gpc]--;
-		data[tpc] = gpc;
+	const u8 gpcmax = nvkm_rd32(device, 0x022430);
+	const u8 tpcmax = nvkm_rd32(device, 0x022434) * gpcmax;
+	int i, j, sm = 0;
+	u32 data;
+
+	for (i = 0; i < DIV_ROUND_UP(tpcmax, 4); i++) {
+		for (data = 0, j = 0; j < 4; j++) {
+			if (sm < gr->sm_nr)
+				data |= gr->sm[sm++].gpc << (j * 8);
+			else
+				data |= 0x1f << (j * 8);
+		}
+		nvkm_wr32(device, 0x4060a8 + (i * 4), data);
 	}
-
-	for (i = 0; i < 4; i++)
-		nvkm_wr32(device, 0x4060a8 + (i * 4), ((u32 *)data)[i]);
 }
 
 void
-gf100_grctx_generate_r418bb8(struct gf100_gr *gr)
+gf100_grctx_generate_rop_mapping(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
 	u32 data[6] = {}, data2[2] = {};
-	u8  tpcnr[GPC_MAX];
 	u8  shift, ntpcv;
-	int gpc, tpc, i;
-
-	/* calculate first set of magics */
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-
-	gpc = -1;
-	for (tpc = 0; tpc < gr->tpc_total; tpc++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpcnr[gpc]--;
-
-		data[tpc / 6] |= gpc << ((tpc % 6) * 5);
-	}
+	int i;
 
-	for (; tpc < 32; tpc++)
-		data[tpc / 6] |= 7 << ((tpc % 6) * 5);
+	/* Pack tile map into register format. */
+	for (i = 0; i < 32; i++)
+		data[i / 6] |= (gr->tile[i] & 0x07) << ((i % 6) * 5);
 
-	/* and the second... */
+	/* Magic. */
 	shift = 0;
 	ntpcv = gr->tpc_total;
 	while (!(ntpcv & (1 << 4))) {
@@ -1197,40 +1158,214 @@ gf100_grctx_generate_r418bb8(struct gf100_gr *gr)
 }
 
 void
-gf100_grctx_generate_r406800(struct gf100_gr *gr)
+gf100_grctx_generate_max_ways_evict(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	u64 tpc_mask = 0, tpc_set = 0;
-	u8  tpcnr[GPC_MAX];
-	int gpc, tpc;
-	int i, a, b;
-
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++)
-		tpc_mask |= ((1ULL << gr->tpc_nr[gpc]) - 1) << (gpc * 8);
-
-	for (i = 0, gpc = -1, b = -1; i < 32; i++) {
-		a = (i * (gr->tpc_total - 1)) / 32;
-		if (a != b) {
-			b = a;
-			do {
-				gpc = (gpc + 1) % gr->gpc_nr;
-			} while (!tpcnr[gpc]);
-			tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
-
-			tpc_set |= 1ULL << ((gpc * 8) + tpc);
+	u32 fbps = nvkm_rd32(device, 0x121c74);
+	if (fbps == 1)
+		nvkm_mask(device, 0x17e91c, 0x001f0000, 0x00090000);
+}
+
+static const u32
+gf100_grctx_alpha_beta_map[17][32] = {
+	[1] = {
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+	},
+	[2] = {
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+	},
+	//XXX: 3
+	[4] = {
+		1, 1, 1, 1, 1, 1, 1, 1,
+		2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+		3, 3, 3, 3, 3, 3, 3, 3,
+	},
+	//XXX: 5
+	//XXX: 6
+	[7] = {
+		1, 1, 1, 1,
+		2, 2, 2, 2, 2, 2,
+		3, 3, 3, 3, 3, 3,
+		4, 4, 4, 4, 4, 4,
+		5, 5, 5, 5, 5, 5,
+		6, 6, 6, 6,
+	},
+	[8] = {
+		1, 1, 1,
+		2, 2, 2, 2, 2,
+		3, 3, 3, 3, 3,
+		4, 4, 4, 4, 4, 4,
+		5, 5, 5, 5, 5,
+		6, 6, 6, 6, 6,
+		7, 7, 7,
+	},
+	//XXX: 9
+	//XXX: 10
+	[11] = {
+		1, 1,
+		2, 2, 2, 2,
+		3, 3, 3,
+		4, 4, 4, 4,
+		5, 5, 5,
+		6, 6, 6,
+		7, 7, 7, 7,
+		8, 8, 8,
+		9, 9, 9, 9,
+		10, 10,
+	},
+	//XXX: 12
+	//XXX: 13
+	[14] = {
+		1, 1,
+		2, 2,
+		3, 3, 3,
+		4, 4, 4,
+		5, 5,
+		6, 6, 6,
+		7, 7,
+		8, 8, 8,
+		9, 9,
+		10, 10, 10,
+		11, 11, 11,
+		12, 12,
+		13, 13,
+	},
+	[15] = {
+		1, 1,
+		2, 2,
+		3, 3,
+		4, 4, 4,
+		5, 5,
+		6, 6, 6,
+		7, 7,
+		8, 8,
+		9, 9, 9,
+		10, 10,
+		11, 11, 11,
+		12, 12,
+		13, 13,
+		14, 14,
+	},
+	[16] = {
+		1, 1,
+		2, 2,
+		3, 3,
+		4, 4,
+		5, 5,
+		6, 6, 6,
+		7, 7,
+		8, 8,
+		9, 9,
+		10, 10, 10,
+		11, 11,
+		12, 12,
+		13, 13,
+		14, 14,
+		15, 15,
+	},
+};
+
+void
+gf100_grctx_generate_alpha_beta_tables(struct gf100_gr *gr)
+{
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	int i, gpc;
+
+	for (i = 0; i < 32; i++) {
+		u32 atarget = gf100_grctx_alpha_beta_map[gr->tpc_total][i];
+		u32 abits[GPC_MAX] = {}, amask = 0, bmask = 0;
+
+		if (!atarget) {
+			nvkm_warn(subdev, "missing alpha/beta mapping table\n");
+			atarget = max_t(u32, gr->tpc_total * i / 32, 1);
+		}
+
+		while (atarget) {
+			for (gpc = 0; atarget && gpc < gr->gpc_nr; gpc++) {
+				if (abits[gpc] < gr->tpc_nr[gpc]) {
+					abits[gpc]++;
+					atarget--;
+				}
+			}
 		}
 
-		nvkm_wr32(device, 0x406800 + (i * 0x20), lower_32_bits(tpc_set));
-		nvkm_wr32(device, 0x406c00 + (i * 0x20), lower_32_bits(tpc_set ^ tpc_mask));
-		if (gr->gpc_nr > 4) {
-			nvkm_wr32(device, 0x406804 + (i * 0x20), upper_32_bits(tpc_set));
-			nvkm_wr32(device, 0x406c04 + (i * 0x20), upper_32_bits(tpc_set ^ tpc_mask));
+		for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+			u32 bbits = gr->tpc_nr[gpc] - abits[gpc];
+			amask |= ((1 << abits[gpc]) - 1) << (gpc * 8);
+			bmask |= ((1 << bbits) - 1) << abits[gpc] << (gpc * 8);
 		}
+
+		nvkm_wr32(device, 0x406800 + (i * 0x20), amask);
+		nvkm_wr32(device, 0x406c00 + (i * 0x20), bmask);
 	}
 }
 
 void
+gf100_grctx_generate_tpc_nr(struct gf100_gr *gr, int gpc)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, GPC_UNIT(gpc, 0x0c08), gr->tpc_nr[gpc]);
+	nvkm_wr32(device, GPC_UNIT(gpc, 0x0c8c), gr->tpc_nr[gpc]);
+}
+
+void
+gf100_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x698), sm);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x4e8), sm);
+	nvkm_wr32(device, GPC_UNIT(gpc, 0x0c10 + tpc * 4), sm);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), sm);
+}
+
+void
+gf100_grctx_generate_floorsweep(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const struct gf100_grctx_func *func = gr->func->grctx;
+	int gpc, sm, i, j;
+	u32 data;
+
+	for (sm = 0; sm < gr->sm_nr; sm++) {
+		func->sm_id(gr, gr->sm[sm].gpc, gr->sm[sm].tpc, sm);
+		if (func->tpc_nr)
+			func->tpc_nr(gr, gr->sm[sm].gpc);
+	}
+
+	for (gpc = 0, i = 0; i < 4; i++) {
+		for (data = 0, j = 0; j < 8 && gpc < gr->gpc_nr; j++, gpc++)
+			data |= gr->tpc_nr[gpc] << (j * 4);
+		nvkm_wr32(device, 0x406028 + (i * 4), data);
+		nvkm_wr32(device, 0x405870 + (i * 4), data);
+	}
+
+	if (func->r4060a8)
+		func->r4060a8(gr);
+
+	func->rop_mapping(gr);
+
+	if (func->alpha_beta_tables)
+		func->alpha_beta_tables(gr);
+	if (func->max_ways_evict)
+		func->max_ways_evict(gr);
+	if (func->dist_skip_table)
+		func->dist_skip_table(gr);
+	if (func->r406500)
+		func->r406500(gr);
+	if (func->gpc_tpc_nr)
+		func->gpc_tpc_nr(gr);
+	if (func->r419f78)
+		func->r419f78(gr);
+	if (func->tpc_mask)
+		func->tpc_mask(gr);
+	if (func->smid_config)
+		func->smid_config(gr);
+}
+
+void
 gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -1239,29 +1374,63 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 
 	nvkm_mc_unk260(device, 0);
 
-	gf100_gr_mmio(gr, grctx->hub);
-	gf100_gr_mmio(gr, grctx->gpc);
-	gf100_gr_mmio(gr, grctx->zcull);
-	gf100_gr_mmio(gr, grctx->tpc);
-	gf100_gr_mmio(gr, grctx->ppc);
+	if (!gr->fuc_sw_ctx) {
+		gf100_gr_mmio(gr, grctx->hub);
+		gf100_gr_mmio(gr, grctx->gpc_0);
+		gf100_gr_mmio(gr, grctx->zcull);
+		gf100_gr_mmio(gr, grctx->gpc_1);
+		gf100_gr_mmio(gr, grctx->tpc);
+		gf100_gr_mmio(gr, grctx->ppc);
+	} else {
+		gf100_gr_mmio(gr, gr->fuc_sw_ctx);
+	}
+
+	gf100_gr_wait_idle(gr);
 
 	idle_timeout = nvkm_mask(device, 0x404154, 0xffffffff, 0x00000000);
 
-	grctx->bundle(info);
 	grctx->pagepool(info);
+	grctx->bundle(info);
 	grctx->attrib(info);
+	if (grctx->patch_ltc)
+		grctx->patch_ltc(info);
 	grctx->unkn(gr);
 
-	gf100_grctx_generate_tpcid(gr);
-	gf100_grctx_generate_r406028(gr);
-	gf100_grctx_generate_r4060a8(gr);
-	gf100_grctx_generate_r418bb8(gr);
-	gf100_grctx_generate_r406800(gr);
+	gf100_grctx_generate_floorsweep(gr);
+
+	gf100_gr_wait_idle(gr);
+
+	if (grctx->r400088) grctx->r400088(gr, false);
+	if (gr->fuc_bundle)
+		gf100_gr_icmd(gr, gr->fuc_bundle);
+	else
+		gf100_gr_icmd(gr, grctx->icmd);
+	if (grctx->sw_veid_bundle_init)
+		gf100_gr_icmd(gr, grctx->sw_veid_bundle_init);
+	if (grctx->r400088) grctx->r400088(gr, true);
 
-	gf100_gr_icmd(gr, grctx->icmd);
 	nvkm_wr32(device, 0x404154, idle_timeout);
-	gf100_gr_mthd(gr, grctx->mthd);
+
+	if (gr->fuc_method)
+		gf100_gr_mthd(gr, gr->fuc_method);
+	else
+		gf100_gr_mthd(gr, grctx->mthd);
 	nvkm_mc_unk260(device, 1);
+
+	if (grctx->r419cb8)
+		grctx->r419cb8(gr);
+	if (grctx->r418800)
+		grctx->r418800(gr);
+	if (grctx->r419eb0)
+		grctx->r419eb0(gr);
+	if (grctx->r419e00)
+		grctx->r419e00(gr);
+	if (grctx->r418e94)
+		grctx->r418e94(gr);
+	if (grctx->r419a3c)
+		grctx->r419a3c(gr);
+	if (grctx->r408840)
+		grctx->r408840(gr);
 }
 
 #define CB_RESERVED 0x80000
@@ -1280,6 +1449,32 @@ gf100_grctx_generate(struct gf100_gr *gr)
 	int ret, i;
 	u64 addr;
 
+	/* NV_PGRAPH_FE_PWR_MODE_FORCE_ON. */
+	nvkm_wr32(device, 0x404170, 0x00000012);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x404170) & 0x00000010))
+			break;
+	);
+
+	if (grctx->unkn88c)
+		grctx->unkn88c(gr, true);
+
+	/* Reset FECS. */
+	nvkm_wr32(device, 0x409614, 0x00000070);
+	nvkm_usec(device, 10, NVKM_DELAY);
+	nvkm_mask(device, 0x409614, 0x00000700, 0x00000700);
+	nvkm_usec(device, 10, NVKM_DELAY);
+	nvkm_rd32(device, 0x409614);
+
+	if (grctx->unkn88c)
+		grctx->unkn88c(gr, false);
+
+	/* NV_PGRAPH_FE_PWR_MODE_AUTO. */
+	nvkm_wr32(device, 0x404170, 0x00000010);
+
+	/* Init SCC RAM. */
+	nvkm_wr32(device, 0x40802c, 0x00000001);
+
 	/* Allocate memory to for a "channel", which we'll use to generate
 	 * the default context values.
 	 */
@@ -1392,7 +1587,8 @@ gf100_grctx = {
 	.main  = gf100_grctx_generate_main,
 	.unkn  = gf100_grctx_generate_unkn,
 	.hub   = gf100_grctx_pack_hub,
-	.gpc   = gf100_grctx_pack_gpc,
+	.gpc_0 = gf100_grctx_pack_gpc_0,
+	.gpc_1 = gf100_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gf100_grctx_pack_tpc,
 	.icmd  = gf100_grctx_pack_icmd,
@@ -1404,4 +1600,11 @@ gf100_grctx = {
 	.attrib = gf100_grctx_generate_attrib,
 	.attrib_nr_max = 0x324,
 	.attrib_nr = 0x218,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.r4060a8 = gf100_grctx_generate_r4060a8,
+	.rop_mapping = gf100_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gf100_grctx_generate_alpha_beta_tables,
+	.max_ways_evict = gf100_grctx_generate_max_ways_evict,
+	.r419cb8 = gf100_grctx_generate_r419cb8,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
index 5199e5aa0cb7..33e932bd73b1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
@@ -21,19 +21,22 @@ void gf100_grctx_mmio_item(struct gf100_grctx *, u32 addr, u32 data, int s, int)
 #define mmio_wr32(a,b,c) mmio_refn((a), (b), (c),  0, -1)
 
 struct gf100_grctx_func {
+	void (*unkn88c)(struct gf100_gr *, bool on);
 	/* main context generation function */
 	void  (*main)(struct gf100_gr *, struct gf100_grctx *);
 	/* context-specific modify-on-first-load list generation function */
 	void  (*unkn)(struct gf100_gr *);
 	/* mmio context data */
 	const struct gf100_gr_pack *hub;
-	const struct gf100_gr_pack *gpc;
+	const struct gf100_gr_pack *gpc_0;
+	const struct gf100_gr_pack *gpc_1;
 	const struct gf100_gr_pack *zcull;
 	const struct gf100_gr_pack *tpc;
 	const struct gf100_gr_pack *ppc;
 	/* indirect context data, generated with icmds/mthds */
 	const struct gf100_gr_pack *icmd;
 	const struct gf100_gr_pack *mthd;
+	const struct gf100_gr_pack *sw_veid_bundle_init;
 	/* bundle circular buffer */
 	void (*bundle)(struct gf100_grctx *);
 	u32 bundle_size;
@@ -48,6 +51,31 @@ struct gf100_grctx_func {
 	u32 attrib_nr;
 	u32 alpha_nr_max;
 	u32 alpha_nr;
+	u32 gfxp_nr;
+	/* other patch buffer stuff */
+	void (*patch_ltc)(struct gf100_grctx *);
+	/* floorsweeping */
+	void (*sm_id)(struct gf100_gr *, int gpc, int tpc, int sm);
+	void (*tpc_nr)(struct gf100_gr *, int gpc);
+	void (*r4060a8)(struct gf100_gr *);
+	void (*rop_mapping)(struct gf100_gr *);
+	void (*alpha_beta_tables)(struct gf100_gr *);
+	void (*max_ways_evict)(struct gf100_gr *);
+	void (*dist_skip_table)(struct gf100_gr *);
+	void (*r406500)(struct gf100_gr *);
+	void (*gpc_tpc_nr)(struct gf100_gr *);
+	void (*r419f78)(struct gf100_gr *);
+	void (*tpc_mask)(struct gf100_gr *);
+	void (*smid_config)(struct gf100_gr *);
+	/* misc other things */
+	void (*r400088)(struct gf100_gr *, bool);
+	void (*r419cb8)(struct gf100_gr *);
+	void (*r418800)(struct gf100_gr *);
+	void (*r419eb0)(struct gf100_gr *);
+	void (*r419e00)(struct gf100_gr *);
+	void (*r418e94)(struct gf100_gr *);
+	void (*r419a3c)(struct gf100_gr *);
+	void (*r408840)(struct gf100_gr *);
 };
 
 extern const struct gf100_grctx_func gf100_grctx;
@@ -57,11 +85,14 @@ void gf100_grctx_generate_bundle(struct gf100_grctx *);
 void gf100_grctx_generate_pagepool(struct gf100_grctx *);
 void gf100_grctx_generate_attrib(struct gf100_grctx *);
 void gf100_grctx_generate_unkn(struct gf100_gr *);
-void gf100_grctx_generate_tpcid(struct gf100_gr *);
-void gf100_grctx_generate_r406028(struct gf100_gr *);
+void gf100_grctx_generate_floorsweep(struct gf100_gr *);
+void gf100_grctx_generate_sm_id(struct gf100_gr *, int, int, int);
+void gf100_grctx_generate_tpc_nr(struct gf100_gr *, int);
 void gf100_grctx_generate_r4060a8(struct gf100_gr *);
-void gf100_grctx_generate_r418bb8(struct gf100_gr *);
-void gf100_grctx_generate_r406800(struct gf100_gr *);
+void gf100_grctx_generate_rop_mapping(struct gf100_gr *);
+void gf100_grctx_generate_alpha_beta_tables(struct gf100_gr *);
+void gf100_grctx_generate_max_ways_evict(struct gf100_gr *);
+void gf100_grctx_generate_r419cb8(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gf108_grctx;
 void gf108_grctx_generate_attrib(struct gf100_grctx *);
@@ -72,22 +103,25 @@ extern const struct gf100_grctx_func gf110_grctx;
 
 extern const struct gf100_grctx_func gf117_grctx;
 void gf117_grctx_generate_attrib(struct gf100_grctx *);
+void gf117_grctx_generate_rop_mapping(struct gf100_gr *);
+void gf117_grctx_generate_dist_skip_table(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gf119_grctx;
 
 extern const struct gf100_grctx_func gk104_grctx;
+void gk104_grctx_generate_alpha_beta_tables(struct gf100_gr *);
+void gk104_grctx_generate_gpc_tpc_nr(struct gf100_gr *);
+
 extern const struct gf100_grctx_func gk20a_grctx;
-void gk104_grctx_generate_main(struct gf100_gr *, struct gf100_grctx *);
 void gk104_grctx_generate_bundle(struct gf100_grctx *);
 void gk104_grctx_generate_pagepool(struct gf100_grctx *);
+void gk104_grctx_generate_patch_ltc(struct gf100_grctx *);
 void gk104_grctx_generate_unkn(struct gf100_gr *);
-void gk104_grctx_generate_r418bb8(struct gf100_gr *);
-
-void gm107_grctx_generate_bundle(struct gf100_grctx *);
-void gm107_grctx_generate_pagepool(struct gf100_grctx *);
-void gm107_grctx_generate_attrib(struct gf100_grctx *);
+void gk104_grctx_generate_r418800(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gk110_grctx;
+void gk110_grctx_generate_r419eb0(struct gf100_gr *);
+
 extern const struct gf100_grctx_func gk110b_grctx;
 extern const struct gf100_grctx_func gk208_grctx;
 
@@ -95,22 +129,30 @@ extern const struct gf100_grctx_func gm107_grctx;
 void gm107_grctx_generate_bundle(struct gf100_grctx *);
 void gm107_grctx_generate_pagepool(struct gf100_grctx *);
 void gm107_grctx_generate_attrib(struct gf100_grctx *);
+void gm107_grctx_generate_sm_id(struct gf100_gr *, int, int, int);
 
 extern const struct gf100_grctx_func gm200_grctx;
-void gm200_grctx_generate_tpcid(struct gf100_gr *);
-void gm200_grctx_generate_405b60(struct gf100_gr *);
+void gm200_grctx_generate_dist_skip_table(struct gf100_gr *);
+void gm200_grctx_generate_r406500(struct gf100_gr *);
+void gm200_grctx_generate_tpc_mask(struct gf100_gr *);
+void gm200_grctx_generate_smid_config(struct gf100_gr *);
+void gm200_grctx_generate_r419a3c(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gm20b_grctx;
 
 extern const struct gf100_grctx_func gp100_grctx;
-void gp100_grctx_generate_main(struct gf100_gr *, struct gf100_grctx *);
 void gp100_grctx_generate_pagepool(struct gf100_grctx *);
+void gp100_grctx_generate_smid_config(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gp102_grctx;
 void gp102_grctx_generate_attrib(struct gf100_grctx *);
 
+extern const struct gf100_grctx_func gp104_grctx;
+
 extern const struct gf100_grctx_func gp107_grctx;
 
+extern const struct gf100_grctx_func gv100_grctx;
+
 /* context init value lists */
 
 extern const struct gf100_gr_pack gf100_grctx_pack_icmd[];
@@ -128,7 +170,8 @@ extern const struct gf100_gr_init gf100_grctx_init_memfmt_0[];
 extern const struct gf100_gr_init gf100_grctx_init_rstr2d_0[];
 extern const struct gf100_gr_init gf100_grctx_init_scc_0[];
 
-extern const struct gf100_gr_pack gf100_grctx_pack_gpc[];
+extern const struct gf100_gr_pack gf100_grctx_pack_gpc_0[];
+extern const struct gf100_gr_pack gf100_grctx_pack_gpc_1[];
 extern const struct gf100_gr_init gf100_grctx_init_gpc_unk_0[];
 extern const struct gf100_gr_init gf100_grctx_init_prop_0[];
 extern const struct gf100_gr_init gf100_grctx_init_gpc_unk_1[];
@@ -177,6 +220,8 @@ extern const struct gf100_gr_init gf117_grctx_init_pe_0[];
 
 extern const struct gf100_gr_init gf117_grctx_init_wwdx_0[];
 
+extern const struct gf100_gr_pack gf117_grctx_pack_gpc_1[];
+
 extern const struct gf100_gr_init gk104_grctx_init_memfmt_0[];
 extern const struct gf100_gr_init gk104_grctx_init_ds_0[];
 extern const struct gf100_gr_init gk104_grctx_init_scc_0[];
@@ -186,7 +231,6 @@ extern const struct gf100_gr_init gk104_grctx_init_gpm_0[];
 extern const struct gf100_gr_init gk104_grctx_init_pes_0[];
 
 extern const struct gf100_gr_pack gk104_grctx_pack_hub[];
-extern const struct gf100_gr_pack gk104_grctx_pack_gpc[];
 extern const struct gf100_gr_pack gk104_grctx_pack_tpc[];
 extern const struct gf100_gr_pack gk104_grctx_pack_ppc[];
 extern const struct gf100_gr_pack gk104_grctx_pack_icmd[];
@@ -200,7 +244,8 @@ extern const struct gf100_gr_pack gk110_grctx_pack_hub[];
 extern const struct gf100_gr_init gk110_grctx_init_pri_0[];
 extern const struct gf100_gr_init gk110_grctx_init_cwd_0[];
 
-extern const struct gf100_gr_pack gk110_grctx_pack_gpc[];
+extern const struct gf100_gr_pack gk110_grctx_pack_gpc_0[];
+extern const struct gf100_gr_pack gk110_grctx_pack_gpc_1[];
 extern const struct gf100_gr_init gk110_grctx_init_gpc_unk_2[];
 
 extern const struct gf100_gr_init gk110_grctx_init_tex_0[];
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf104.c
index 54fd74e9cca0..7a0564b6e3c7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf104.c
@@ -84,7 +84,8 @@ gf104_grctx = {
 	.main  = gf100_grctx_generate_main,
 	.unkn  = gf100_grctx_generate_unkn,
 	.hub   = gf100_grctx_pack_hub,
-	.gpc   = gf100_grctx_pack_gpc,
+	.gpc_0 = gf100_grctx_pack_gpc_0,
+	.gpc_1 = gf100_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gf104_grctx_pack_tpc,
 	.icmd  = gf100_grctx_pack_icmd,
@@ -96,4 +97,11 @@ gf104_grctx = {
 	.attrib = gf100_grctx_generate_attrib,
 	.attrib_nr_max = 0x324,
 	.attrib_nr = 0x218,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.r4060a8 = gf100_grctx_generate_r4060a8,
+	.rop_mapping = gf100_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gf100_grctx_generate_alpha_beta_tables,
+	.max_ways_evict = gf100_grctx_generate_max_ways_evict,
+	.r419cb8 = gf100_grctx_generate_r419cb8,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf108.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf108.c
index 82f71b10c06e..dda2c32e6232 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf108.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf108.c
@@ -667,12 +667,17 @@ gf108_grctx_init_gpm_0[] = {
 };
 
 static const struct gf100_gr_pack
-gf108_grctx_pack_gpc[] = {
+gf108_grctx_pack_gpc_0[] = {
 	{ gf100_grctx_init_gpc_unk_0 },
 	{ gf100_grctx_init_prop_0 },
 	{ gf100_grctx_init_gpc_unk_1 },
 	{ gf108_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
+	{}
+};
+
+static const struct gf100_gr_pack
+gf108_grctx_pack_gpc_1[] = {
 	{ gf100_grctx_init_crstr_0 },
 	{ gf108_grctx_init_gpm_0 },
 	{ gf100_grctx_init_gcc_0 },
@@ -780,7 +785,8 @@ gf108_grctx = {
 	.main  = gf100_grctx_generate_main,
 	.unkn  = gf108_grctx_generate_unkn,
 	.hub   = gf108_grctx_pack_hub,
-	.gpc   = gf108_grctx_pack_gpc,
+	.gpc_0 = gf108_grctx_pack_gpc_0,
+	.gpc_1 = gf108_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gf108_grctx_pack_tpc,
 	.icmd  = gf108_grctx_pack_icmd,
@@ -794,4 +800,11 @@ gf108_grctx = {
 	.attrib_nr = 0x218,
 	.alpha_nr_max = 0x324,
 	.alpha_nr = 0x218,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.r4060a8 = gf100_grctx_generate_r4060a8,
+	.rop_mapping = gf100_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gf100_grctx_generate_alpha_beta_tables,
+	.max_ways_evict = gf100_grctx_generate_max_ways_evict,
+	.r419cb8 = gf100_grctx_generate_r419cb8,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf110.c
index 7df398b53f8f..f5cca5e6a4f2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf110.c
@@ -314,15 +314,12 @@ gf110_grctx_init_setup_0[] = {
 };
 
 static const struct gf100_gr_pack
-gf110_grctx_pack_gpc[] = {
+gf110_grctx_pack_gpc_0[] = {
 	{ gf100_grctx_init_gpc_unk_0 },
 	{ gf100_grctx_init_prop_0 },
 	{ gf100_grctx_init_gpc_unk_1 },
 	{ gf110_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
-	{ gf100_grctx_init_crstr_0 },
-	{ gf100_grctx_init_gpm_0 },
-	{ gf100_grctx_init_gcc_0 },
 	{}
 };
 
@@ -335,7 +332,8 @@ gf110_grctx = {
 	.main  = gf100_grctx_generate_main,
 	.unkn  = gf100_grctx_generate_unkn,
 	.hub   = gf100_grctx_pack_hub,
-	.gpc   = gf110_grctx_pack_gpc,
+	.gpc_0 = gf110_grctx_pack_gpc_0,
+	.gpc_1 = gf100_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gf100_grctx_pack_tpc,
 	.icmd  = gf110_grctx_pack_icmd,
@@ -347,4 +345,11 @@ gf110_grctx = {
 	.attrib = gf100_grctx_generate_attrib,
 	.attrib_nr_max = 0x324,
 	.attrib_nr = 0x218,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.r4060a8 = gf100_grctx_generate_r4060a8,
+	.rop_mapping = gf100_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gf100_grctx_generate_alpha_beta_tables,
+	.max_ways_evict = gf100_grctx_generate_max_ways_evict,
+	.r419cb8 = gf100_grctx_generate_r419cb8,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
index 19301d88577d..276c282d19aa 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
@@ -84,12 +84,17 @@ gf117_grctx_init_setup_0[] = {
 };
 
 static const struct gf100_gr_pack
-gf117_grctx_pack_gpc[] = {
+gf117_grctx_pack_gpc_0[] = {
 	{ gf100_grctx_init_gpc_unk_0 },
 	{ gf119_grctx_init_prop_0 },
 	{ gf119_grctx_init_gpc_unk_1 },
 	{ gf117_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
+	{}
+};
+
+const struct gf100_gr_pack
+gf117_grctx_pack_gpc_1[] = {
 	{ gf119_grctx_init_crstr_0 },
 	{ gf108_grctx_init_gpm_0 },
 	{ gf100_grctx_init_gcc_0 },
@@ -180,6 +185,62 @@ gf117_grctx_pack_ppc[] = {
  ******************************************************************************/
 
 void
+gf117_grctx_generate_dist_skip_table(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
+}
+
+void
+gf117_grctx_generate_rop_mapping(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	u32 data[6] = {}, data2[2] = {};
+	u8  shift, ntpcv;
+	int i;
+
+	/* Pack tile map into register format. */
+	for (i = 0; i < 32; i++)
+		data[i / 6] |= (gr->tile[i] & 0x07) << ((i % 6) * 5);
+
+	/* Magic. */
+	shift = 0;
+	ntpcv = gr->tpc_total;
+	while (!(ntpcv & (1 << 4))) {
+		ntpcv <<= 1;
+		shift++;
+	}
+
+	data2[0]  = (ntpcv << 16);
+	data2[0] |= (shift << 21);
+	data2[0] |= (((1 << (0 + 5)) % ntpcv) << 24);
+	for (i = 1; i < 7; i++)
+		data2[1] |= ((1 << (i + 5)) % ntpcv) << ((i - 1) * 5);
+
+	/* GPC_BROADCAST */
+	nvkm_wr32(device, 0x418bb8, (gr->tpc_total << 8) |
+				     gr->screen_tile_row_offset);
+	for (i = 0; i < 6; i++)
+		nvkm_wr32(device, 0x418b08 + (i * 4), data[i]);
+
+	/* GPC_BROADCAST.TP_BROADCAST */
+	nvkm_wr32(device, 0x41bfd0, (gr->tpc_total << 8) |
+				     gr->screen_tile_row_offset | data2[0]);
+	nvkm_wr32(device, 0x41bfe4, data2[1]);
+	for (i = 0; i < 6; i++)
+		nvkm_wr32(device, 0x41bf00 + (i * 4), data[i]);
+
+	/* UNK78xx */
+	nvkm_wr32(device, 0x4078bc, (gr->tpc_total << 8) |
+				     gr->screen_tile_row_offset);
+	for (i = 0; i < 6; i++)
+		nvkm_wr32(device, 0x40780c + (i * 4), data[i]);
+}
+
+void
 gf117_grctx_generate_attrib(struct gf100_grctx *info)
 {
 	struct gf100_gr *gr = info->gr;
@@ -217,50 +278,13 @@ gf117_grctx_generate_attrib(struct gf100_grctx *info)
 	}
 }
 
-static void
-gf117_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
-{
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const struct gf100_grctx_func *grctx = gr->func->grctx;
-	u32 idle_timeout;
-	int i;
-
-	nvkm_mc_unk260(device, 0);
-
-	gf100_gr_mmio(gr, grctx->hub);
-	gf100_gr_mmio(gr, grctx->gpc);
-	gf100_gr_mmio(gr, grctx->zcull);
-	gf100_gr_mmio(gr, grctx->tpc);
-	gf100_gr_mmio(gr, grctx->ppc);
-
-	idle_timeout = nvkm_mask(device, 0x404154, 0xffffffff, 0x00000000);
-
-	grctx->bundle(info);
-	grctx->pagepool(info);
-	grctx->attrib(info);
-	grctx->unkn(gr);
-
-	gf100_grctx_generate_tpcid(gr);
-	gf100_grctx_generate_r406028(gr);
-	gf100_grctx_generate_r4060a8(gr);
-	gk104_grctx_generate_r418bb8(gr);
-	gf100_grctx_generate_r406800(gr);
-
-	for (i = 0; i < 8; i++)
-		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
-
-	gf100_gr_icmd(gr, grctx->icmd);
-	nvkm_wr32(device, 0x404154, idle_timeout);
-	gf100_gr_mthd(gr, grctx->mthd);
-	nvkm_mc_unk260(device, 1);
-}
-
 const struct gf100_grctx_func
 gf117_grctx = {
-	.main  = gf117_grctx_generate_main,
+	.main  = gf100_grctx_generate_main,
 	.unkn  = gk104_grctx_generate_unkn,
 	.hub   = gf117_grctx_pack_hub,
-	.gpc   = gf117_grctx_pack_gpc,
+	.gpc_0 = gf117_grctx_pack_gpc_0,
+	.gpc_1 = gf117_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gf117_grctx_pack_tpc,
 	.ppc   = gf117_grctx_pack_ppc,
@@ -275,4 +299,12 @@ gf117_grctx = {
 	.attrib_nr = 0x218,
 	.alpha_nr_max = 0x7ff,
 	.alpha_nr = 0x324,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.r4060a8 = gf100_grctx_generate_r4060a8,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gf100_grctx_generate_alpha_beta_tables,
+	.max_ways_evict = gf100_grctx_generate_max_ways_evict,
+	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
+	.r419cb8 = gf100_grctx_generate_r419cb8,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf119.c
index 605185b078be..0cfe46366af6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf119.c
@@ -431,15 +431,12 @@ gf119_grctx_init_crstr_0[] = {
 };
 
 static const struct gf100_gr_pack
-gf119_grctx_pack_gpc[] = {
+gf119_grctx_pack_gpc_0[] = {
 	{ gf100_grctx_init_gpc_unk_0 },
 	{ gf119_grctx_init_prop_0 },
 	{ gf119_grctx_init_gpc_unk_1 },
 	{ gf119_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
-	{ gf119_grctx_init_crstr_0 },
-	{ gf108_grctx_init_gpm_0 },
-	{ gf100_grctx_init_gcc_0 },
 	{}
 };
 
@@ -503,7 +500,8 @@ gf119_grctx = {
 	.main  = gf100_grctx_generate_main,
 	.unkn  = gf108_grctx_generate_unkn,
 	.hub   = gf119_grctx_pack_hub,
-	.gpc   = gf119_grctx_pack_gpc,
+	.gpc_0 = gf119_grctx_pack_gpc_0,
+	.gpc_1 = gf117_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gf119_grctx_pack_tpc,
 	.icmd  = gf119_grctx_pack_icmd,
@@ -517,4 +515,11 @@ gf119_grctx = {
 	.attrib_nr = 0x218,
 	.alpha_nr_max = 0x324,
 	.alpha_nr = 0x218,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.r4060a8 = gf100_grctx_generate_r4060a8,
+	.rop_mapping = gf100_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gf100_grctx_generate_alpha_beta_tables,
+	.max_ways_evict = gf100_grctx_generate_max_ways_evict,
+	.r419cb8 = gf100_grctx_generate_r419cb8,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
index 825c8fd500bc..304e9d268bad 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
@@ -739,13 +739,18 @@ gk104_grctx_init_gpm_0[] = {
 	{}
 };
 
-const struct gf100_gr_pack
-gk104_grctx_pack_gpc[] = {
+static const struct gf100_gr_pack
+gk104_grctx_pack_gpc_0[] = {
 	{ gf100_grctx_init_gpc_unk_0 },
 	{ gf119_grctx_init_prop_0 },
 	{ gf119_grctx_init_gpc_unk_1 },
 	{ gk104_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
+	{}
+};
+
+static const struct gf100_gr_pack
+gk104_grctx_pack_gpc_1[] = {
 	{ gf119_grctx_init_crstr_0 },
 	{ gk104_grctx_init_gpm_0 },
 	{ gf100_grctx_init_gcc_0 },
@@ -841,6 +846,32 @@ gk104_grctx_pack_ppc[] = {
  ******************************************************************************/
 
 void
+gk104_grctx_generate_r418800(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	/*XXX: Not real sure where to apply these, there doesn't seem
+	 *     to be any pattern to which chipsets it's done on.
+	 *
+	 *     Perhaps a VBIOS tweak?
+	 */
+	if (0) {
+		nvkm_mask(device, 0x418800, 0x00200000, 0x00200000);
+		nvkm_mask(device, 0x41be10, 0x00800000, 0x00800000);
+	}
+}
+
+void
+gk104_grctx_generate_patch_ltc(struct gf100_grctx *info)
+{
+	struct nvkm_device *device = info->gr->base.engine.subdev.device;
+	u32 data0 = nvkm_rd32(device, 0x17e91c);
+	u32 data1 = nvkm_rd32(device, 0x17e920);
+	/*XXX: Figure out how to modify this correctly! */
+	mmio_wr32(info, 0x17e91c, data0);
+	mmio_wr32(info, 0x17e920, data1);
+}
+
+void
 gk104_grctx_generate_bundle(struct gf100_grctx *info)
 {
 	const struct gf100_grctx_func *grctx = info->gr->func->grctx;
@@ -881,114 +912,74 @@ gk104_grctx_generate_unkn(struct gf100_gr *gr)
 	nvkm_mask(device, 0x419c00, 0x00000008, 0x00000008);
 }
 
-void
-gk104_grctx_generate_r418bb8(struct gf100_gr *gr)
+static void
+gk104_grctx_generate_r419f78(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	u32 data[6] = {}, data2[2] = {};
-	u8  tpcnr[GPC_MAX];
-	u8  shift, ntpcv;
-	int gpc, tpc, i;
-
-	/* calculate first set of magics */
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-
-	gpc = -1;
-	for (tpc = 0; tpc < gr->tpc_total; tpc++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpcnr[gpc]--;
-
-		data[tpc / 6] |= gpc << ((tpc % 6) * 5);
-	}
-
-	for (; tpc < 32; tpc++)
-		data[tpc / 6] |= 7 << ((tpc % 6) * 5);
-
-	/* and the second... */
-	shift = 0;
-	ntpcv = gr->tpc_total;
-	while (!(ntpcv & (1 << 4))) {
-		ntpcv <<= 1;
-		shift++;
-	}
-
-	data2[0]  = (ntpcv << 16);
-	data2[0] |= (shift << 21);
-	data2[0] |= (((1 << (0 + 5)) % ntpcv) << 24);
-	for (i = 1; i < 7; i++)
-		data2[1] |= ((1 << (i + 5)) % ntpcv) << ((i - 1) * 5);
-
-	/* GPC_BROADCAST */
-	nvkm_wr32(device, 0x418bb8, (gr->tpc_total << 8) |
-				     gr->screen_tile_row_offset);
-	for (i = 0; i < 6; i++)
-		nvkm_wr32(device, 0x418b08 + (i * 4), data[i]);
-
-	/* GPC_BROADCAST.TP_BROADCAST */
-	nvkm_wr32(device, 0x41bfd0, (gr->tpc_total << 8) |
-				     gr->screen_tile_row_offset | data2[0]);
-	nvkm_wr32(device, 0x41bfe4, data2[1]);
-	for (i = 0; i < 6; i++)
-		nvkm_wr32(device, 0x41bf00 + (i * 4), data[i]);
-
-	/* UNK78xx */
-	nvkm_wr32(device, 0x4078bc, (gr->tpc_total << 8) |
-				     gr->screen_tile_row_offset);
-	for (i = 0; i < 6; i++)
-		nvkm_wr32(device, 0x40780c + (i * 4), data[i]);
+	nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000);
 }
 
 void
-gk104_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
+gk104_grctx_generate_gpc_tpc_nr(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const struct gf100_grctx_func *grctx = gr->func->grctx;
-	u32 idle_timeout;
-	int i;
-
-	nvkm_mc_unk260(device, 0);
-
-	gf100_gr_mmio(gr, grctx->hub);
-	gf100_gr_mmio(gr, grctx->gpc);
-	gf100_gr_mmio(gr, grctx->zcull);
-	gf100_gr_mmio(gr, grctx->tpc);
-	gf100_gr_mmio(gr, grctx->ppc);
-
-	idle_timeout = nvkm_mask(device, 0x404154, 0xffffffff, 0x00000000);
-
-	grctx->bundle(info);
-	grctx->pagepool(info);
-	grctx->attrib(info);
-	grctx->unkn(gr);
-
-	gf100_grctx_generate_tpcid(gr);
-	gf100_grctx_generate_r406028(gr);
-	gk104_grctx_generate_r418bb8(gr);
-	gf100_grctx_generate_r406800(gr);
-
-	for (i = 0; i < 8; i++)
-		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
-
 	nvkm_wr32(device, 0x405b00, (gr->tpc_total << 8) | gr->gpc_nr);
-	nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000);
-
-	gf100_gr_icmd(gr, grctx->icmd);
-	nvkm_wr32(device, 0x404154, idle_timeout);
-	gf100_gr_mthd(gr, grctx->mthd);
-	nvkm_mc_unk260(device, 1);
+}
 
-	nvkm_mask(device, 0x418800, 0x00200000, 0x00200000);
-	nvkm_mask(device, 0x41be10, 0x00800000, 0x00800000);
+void
+gk104_grctx_generate_alpha_beta_tables(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	int i, j, gpc, ppc;
+
+	for (i = 0; i < 32; i++) {
+		u32 atarget = max_t(u32, gr->tpc_total * i / 32, 1);
+		u32 btarget = gr->tpc_total - atarget;
+		bool alpha = atarget < btarget;
+		u64 amask = 0, bmask = 0;
+
+		for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+			for (ppc = 0; ppc < gr->func->ppc_nr; ppc++) {
+				u32 ppc_tpcs = gr->ppc_tpc_nr[gpc][ppc];
+				u32 abits, bbits, pmask;
+
+				if (alpha) {
+					abits = atarget ? ppc_tpcs : 0;
+					bbits = ppc_tpcs - abits;
+				} else {
+					bbits = btarget ? ppc_tpcs : 0;
+					abits = ppc_tpcs - bbits;
+				}
+
+				pmask = gr->ppc_tpc_mask[gpc][ppc];
+				while (ppc_tpcs-- > abits)
+					pmask &= pmask - 1;
+				amask |= (u64)pmask << (gpc * 8);
+
+				pmask ^= gr->ppc_tpc_mask[gpc][ppc];
+				bmask |= (u64)pmask << (gpc * 8);
+
+				atarget -= min(abits, atarget);
+				btarget -= min(bbits, btarget);
+				if ((abits > 0) || (bbits > 0))
+					alpha = !alpha;
+			}
+		}
+
+		for (j = 0; j < gr->gpc_nr; j += 4, amask >>= 32, bmask >>= 32) {
+			nvkm_wr32(device, 0x406800 + (i * 0x20) + j, amask);
+			nvkm_wr32(device, 0x406c00 + (i * 0x20) + j, bmask);
+		}
+	}
 }
 
 const struct gf100_grctx_func
 gk104_grctx = {
-	.main  = gk104_grctx_generate_main,
+	.main  = gf100_grctx_generate_main,
 	.unkn  = gk104_grctx_generate_unkn,
 	.hub   = gk104_grctx_pack_hub,
-	.gpc   = gk104_grctx_pack_gpc,
+	.gpc_0 = gk104_grctx_pack_gpc_0,
+	.gpc_1 = gk104_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gk104_grctx_pack_tpc,
 	.ppc   = gk104_grctx_pack_ppc,
@@ -1005,4 +996,13 @@ gk104_grctx = {
 	.attrib_nr = 0x218,
 	.alpha_nr_max = 0x7ff,
 	.alpha_nr = 0x648,
+	.patch_ltc = gk104_grctx_generate_patch_ltc,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gk104_grctx_generate_alpha_beta_tables,
+	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.r419f78 = gk104_grctx_generate_r419f78,
+	.r418800 = gk104_grctx_generate_r418800,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c
index 7b95ec2fe453..86547cfc38dc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c
@@ -704,12 +704,17 @@ gk110_grctx_init_gpc_unk_2[] = {
 };
 
 const struct gf100_gr_pack
-gk110_grctx_pack_gpc[] = {
+gk110_grctx_pack_gpc_0[] = {
 	{ gf100_grctx_init_gpc_unk_0 },
 	{ gf119_grctx_init_prop_0 },
 	{ gf119_grctx_init_gpc_unk_1 },
 	{ gk110_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
+	{}
+};
+
+const struct gf100_gr_pack
+gk110_grctx_pack_gpc_1[] = {
 	{ gf119_grctx_init_crstr_0 },
 	{ gk104_grctx_init_gpm_0 },
 	{ gk110_grctx_init_gpc_unk_2 },
@@ -808,12 +813,20 @@ gk110_grctx_pack_ppc[] = {
  * PGRAPH context implementation
  ******************************************************************************/
 
+void
+gk110_grctx_generate_r419eb0(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000);
+}
+
 const struct gf100_grctx_func
 gk110_grctx = {
-	.main  = gk104_grctx_generate_main,
+	.main  = gf100_grctx_generate_main,
 	.unkn  = gk104_grctx_generate_unkn,
 	.hub   = gk110_grctx_pack_hub,
-	.gpc   = gk110_grctx_pack_gpc,
+	.gpc_0 = gk110_grctx_pack_gpc_0,
+	.gpc_1 = gk110_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gk110_grctx_pack_tpc,
 	.ppc   = gk110_grctx_pack_ppc,
@@ -830,4 +843,13 @@ gk110_grctx = {
 	.attrib_nr = 0x218,
 	.alpha_nr_max = 0x7ff,
 	.alpha_nr = 0x648,
+	.patch_ltc = gk104_grctx_generate_patch_ltc,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gk104_grctx_generate_alpha_beta_tables,
+	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.r418800 = gk104_grctx_generate_r418800,
+	.r419eb0 = gk110_grctx_generate_r419eb0,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c
index 048b1152da44..ebb947bd1446 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c
@@ -71,10 +71,11 @@ gk110b_grctx_pack_tpc[] = {
 
 const struct gf100_grctx_func
 gk110b_grctx = {
-	.main  = gk104_grctx_generate_main,
+	.main  = gf100_grctx_generate_main,
 	.unkn  = gk104_grctx_generate_unkn,
 	.hub   = gk110_grctx_pack_hub,
-	.gpc   = gk110_grctx_pack_gpc,
+	.gpc_0 = gk110_grctx_pack_gpc_0,
+	.gpc_1 = gk110_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gk110b_grctx_pack_tpc,
 	.ppc   = gk110_grctx_pack_ppc,
@@ -91,4 +92,13 @@ gk110b_grctx = {
 	.attrib_nr = 0x218,
 	.alpha_nr_max = 0x7ff,
 	.alpha_nr = 0x648,
+	.patch_ltc = gk104_grctx_generate_patch_ltc,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gk104_grctx_generate_alpha_beta_tables,
+	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.r418800 = gk104_grctx_generate_r418800,
+	.r419eb0 = gk110_grctx_generate_r419eb0,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c
index 67b7a1b43617..4d40512b5c99 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c
@@ -443,12 +443,17 @@ gk208_grctx_init_gpm_0[] = {
 };
 
 static const struct gf100_gr_pack
-gk208_grctx_pack_gpc[] = {
+gk208_grctx_pack_gpc_0[] = {
 	{ gf100_grctx_init_gpc_unk_0 },
 	{ gk208_grctx_init_prop_0 },
 	{ gk208_grctx_init_gpc_unk_1 },
 	{ gk208_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
+	{}
+};
+
+static const struct gf100_gr_pack
+gk208_grctx_pack_gpc_1[] = {
 	{ gk208_grctx_init_crstr_0 },
 	{ gk208_grctx_init_gpm_0 },
 	{ gk110_grctx_init_gpc_unk_2 },
@@ -532,10 +537,11 @@ gk208_grctx_pack_ppc[] = {
 
 const struct gf100_grctx_func
 gk208_grctx = {
-	.main  = gk104_grctx_generate_main,
+	.main  = gf100_grctx_generate_main,
 	.unkn  = gk104_grctx_generate_unkn,
 	.hub   = gk208_grctx_pack_hub,
-	.gpc   = gk208_grctx_pack_gpc,
+	.gpc_0 = gk208_grctx_pack_gpc_0,
+	.gpc_1 = gk208_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gk208_grctx_pack_tpc,
 	.ppc   = gk208_grctx_pack_ppc,
@@ -552,4 +558,12 @@ gk208_grctx = {
 	.attrib_nr = 0x218,
 	.alpha_nr_max = 0x7ff,
 	.alpha_nr = 0x648,
+	.patch_ltc = gk104_grctx_generate_patch_ltc,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gk104_grctx_generate_alpha_beta_tables,
+	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.r418800 = gk104_grctx_generate_r418800,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
index da7c35a6a3d2..896d473dcc0f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
@@ -42,10 +42,7 @@ gk20a_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 
 	grctx->unkn(gr);
 
-	gf100_grctx_generate_tpcid(gr);
-	gf100_grctx_generate_r406028(gr);
-	gk104_grctx_generate_r418bb8(gr);
-	gf100_grctx_generate_r406800(gr);
+	gf100_grctx_generate_floorsweep(gr);
 
 	for (i = 0; i < 8; i++)
 		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
@@ -82,4 +79,8 @@ gk20a_grctx = {
 	.attrib_nr = 0x240,
 	.alpha_nr_max = 0x648 + (0x648 / 2),
 	.alpha_nr = 0x648,
+	.sm_id = gf100_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gk104_grctx_generate_alpha_beta_tables,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
index 9b43d4ce3eaa..0b3964e6b36e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
@@ -744,12 +744,17 @@ gm107_grctx_init_gpc_unk_2[] = {
 };
 
 static const struct gf100_gr_pack
-gm107_grctx_pack_gpc[] = {
+gm107_grctx_pack_gpc_0[] = {
 	{ gm107_grctx_init_gpc_unk_0 },
 	{ gk208_grctx_init_prop_0 },
 	{ gm107_grctx_init_gpc_unk_1 },
 	{ gm107_grctx_init_setup_0 },
 	{ gf100_grctx_init_zcull_0 },
+	{}
+};
+
+static const struct gf100_gr_pack
+gm107_grctx_pack_gpc_1[] = {
 	{ gk208_grctx_init_crstr_0 },
 	{ gk104_grctx_init_gpm_0 },
 	{ gm107_grctx_init_gpc_unk_2 },
@@ -860,6 +865,16 @@ gm107_grctx_pack_ppc[] = {
  * PGRAPH context implementation
  ******************************************************************************/
 
+static void
+gm107_grctx_generate_r419e00(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x419e00, 0x00808080, 0x00808080);
+	nvkm_mask(device, 0x419ccc, 0x80000000, 0x80000000);
+	nvkm_mask(device, 0x419f80, 0x80000000, 0x80000000);
+	nvkm_mask(device, 0x419f88, 0x80000000, 0x80000000);
+}
+
 void
 gm107_grctx_generate_bundle(struct gf100_grctx *info)
 {
@@ -931,75 +946,27 @@ gm107_grctx_generate_attrib(struct gf100_grctx *info)
 }
 
 static void
-gm107_grctx_generate_tpcid(struct gf100_gr *gr)
+gm107_grctx_generate_r406500(struct gf100_gr *gr)
 {
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-	int gpc, tpc, id;
-
-	for (tpc = 0, id = 0; tpc < 4; tpc++) {
-		for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-			if (tpc < gr->tpc_nr[gpc]) {
-				nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x698), id);
-				nvkm_wr32(device, GPC_UNIT(gpc, 0x0c10 + tpc * 4), id);
-				nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), id);
-				id++;
-			}
-
-			nvkm_wr32(device, GPC_UNIT(gpc, 0x0c08), gr->tpc_nr[gpc]);
-			nvkm_wr32(device, GPC_UNIT(gpc, 0x0c8c), gr->tpc_nr[gpc]);
-		}
-	}
+	nvkm_wr32(gr->base.engine.subdev.device, 0x406500, 0x00000001);
 }
 
-static void
-gm107_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
+void
+gm107_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const struct gf100_grctx_func *grctx = gr->func->grctx;
-	u32 idle_timeout;
-	int i;
-
-	gf100_gr_mmio(gr, grctx->hub);
-	gf100_gr_mmio(gr, grctx->gpc);
-	gf100_gr_mmio(gr, grctx->zcull);
-	gf100_gr_mmio(gr, grctx->tpc);
-	gf100_gr_mmio(gr, grctx->ppc);
-
-	idle_timeout = nvkm_mask(device, 0x404154, 0xffffffff, 0x00000000);
-
-	grctx->bundle(info);
-	grctx->pagepool(info);
-	grctx->attrib(info);
-	grctx->unkn(gr);
-
-	gm107_grctx_generate_tpcid(gr);
-	gf100_grctx_generate_r406028(gr);
-	gk104_grctx_generate_r418bb8(gr);
-	gf100_grctx_generate_r406800(gr);
-
-	nvkm_wr32(device, 0x4064d0, 0x00000001);
-	for (i = 1; i < 8; i++)
-		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
-	nvkm_wr32(device, 0x406500, 0x00000001);
-
-	nvkm_wr32(device, 0x405b00, (gr->tpc_total << 8) | gr->gpc_nr);
-
-	gf100_gr_icmd(gr, grctx->icmd);
-	nvkm_wr32(device, 0x404154, idle_timeout);
-	gf100_gr_mthd(gr, grctx->mthd);
-
-	nvkm_mask(device, 0x419e00, 0x00808080, 0x00808080);
-	nvkm_mask(device, 0x419ccc, 0x80000000, 0x80000000);
-	nvkm_mask(device, 0x419f80, 0x80000000, 0x80000000);
-	nvkm_mask(device, 0x419f88, 0x80000000, 0x80000000);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x698), sm);
+	nvkm_wr32(device, GPC_UNIT(gpc, 0x0c10 + tpc * 4), sm);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), sm);
 }
 
 const struct gf100_grctx_func
 gm107_grctx = {
-	.main  = gm107_grctx_generate_main,
+	.main  = gf100_grctx_generate_main,
 	.unkn  = gk104_grctx_generate_unkn,
 	.hub   = gm107_grctx_pack_hub,
-	.gpc   = gm107_grctx_pack_gpc,
+	.gpc_0 = gm107_grctx_pack_gpc_0,
+	.gpc_1 = gm107_grctx_pack_gpc_1,
 	.zcull = gf100_grctx_pack_zcull,
 	.tpc   = gm107_grctx_pack_tpc,
 	.ppc   = gm107_grctx_pack_ppc,
@@ -1016,4 +983,12 @@ gm107_grctx = {
 	.attrib_nr = 0xaa0,
 	.alpha_nr_max = 0x1800,
 	.alpha_nr = 0x1000,
+	.sm_id = gm107_grctx_generate_sm_id,
+	.tpc_nr = gf100_grctx_generate_tpc_nr,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.alpha_beta_tables = gk104_grctx_generate_alpha_beta_tables,
+	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
+	.r406500 = gm107_grctx_generate_r406500,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.r419e00 = gm107_grctx_generate_r419e00,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm200.c
index db209d33f486..013d05a0f0f6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm200.c
@@ -28,47 +28,34 @@
  ******************************************************************************/
 
 void
-gm200_grctx_generate_tpcid(struct gf100_gr *gr)
+gm200_grctx_generate_r419a3c(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	int gpc, tpc, id;
+	nvkm_mask(device, 0x419a3c, 0x00000014, 0x00000000);
+}
 
-	for (tpc = 0, id = 0; tpc < TPC_MAX_PER_GPC; tpc++) {
-		for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-			if (tpc < gr->tpc_nr[gpc]) {
-				nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x698), id);
-				nvkm_wr32(device, GPC_UNIT(gpc, 0x0c10 + tpc * 4), id);
-				nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), id);
-				id++;
-			}
-		}
-	}
+static void
+gm200_grctx_generate_r418e94(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x418e94, 0xffffffff, 0xc4230000);
+	nvkm_mask(device, 0x418e4c, 0xffffffff, 0x70000000);
 }
 
 void
-gm200_grctx_generate_405b60(struct gf100_gr *gr)
+gm200_grctx_generate_smid_config(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
 	const u32 dist_nr = DIV_ROUND_UP(gr->tpc_total, 4);
 	u32 dist[TPC_MAX / 4] = {};
 	u32 gpcs[GPC_MAX] = {};
-	u8  tpcnr[GPC_MAX];
-	int tpc, gpc, i;
+	u8  sm, i;
 
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-
-	/* won't result in the same distribution as the binary driver where
-	 * some of the gpcs have more tpcs than others, but this shall do
-	 * for the moment.  the code for earlier gpus has this issue too.
-	 */
-	for (gpc = -1, i = 0; i < gr->tpc_total; i++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while(!tpcnr[gpc]);
-		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
-
-		dist[i / 4] |= ((gpc << 4) | tpc) << ((i % 4) * 8);
-		gpcs[gpc] |= i << (tpc * 8);
+	for (sm = 0; sm < gr->sm_nr; sm++) {
+		const u8 gpc = gr->sm[sm].gpc;
+		const u8 tpc = gr->sm[sm].tpc;
+		dist[sm / 4] |= ((gpc << 4) | tpc) << ((sm % 4) * 8);
+		gpcs[gpc] |= sm << (tpc * 8);
 	}
 
 	for (i = 0; i < dist_nr; i++)
@@ -77,50 +64,46 @@ gm200_grctx_generate_405b60(struct gf100_gr *gr)
 		nvkm_wr32(device, 0x405ba0 + (i * 4), gpcs[i]);
 }
 
-static void
-gm200_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
+void
+gm200_grctx_generate_tpc_mask(struct gf100_gr *gr)
 {
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const struct gf100_grctx_func *grctx = gr->func->grctx;
-	u32 idle_timeout, tmp;
-	int i;
-
-	gf100_gr_mmio(gr, gr->fuc_sw_ctx);
-
-	idle_timeout = nvkm_mask(device, 0x404154, 0xffffffff, 0x00000000);
-
-	grctx->bundle(info);
-	grctx->pagepool(info);
-	grctx->attrib(info);
-	grctx->unkn(gr);
-
-	gm200_grctx_generate_tpcid(gr);
-	gf100_grctx_generate_r406028(gr);
-	gk104_grctx_generate_r418bb8(gr);
-
-	for (i = 0; i < 8; i++)
-		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
-	nvkm_wr32(device, 0x406500, 0x00000000);
-
-	nvkm_wr32(device, 0x405b00, (gr->tpc_total << 8) | gr->gpc_nr);
-
+	u32 tmp, i;
 	for (tmp = 0, i = 0; i < gr->gpc_nr; i++)
-		tmp |= ((1 << gr->tpc_nr[i]) - 1) << (i * 4);
-	nvkm_wr32(device, 0x4041c4, tmp);
+		tmp |= ((1 << gr->tpc_nr[i]) - 1) << (i * gr->func->tpc_nr);
+	nvkm_wr32(gr->base.engine.subdev.device, 0x4041c4, tmp);
+}
 
-	gm200_grctx_generate_405b60(gr);
+void
+gm200_grctx_generate_r406500(struct gf100_gr *gr)
+{
+	nvkm_wr32(gr->base.engine.subdev.device, 0x406500, 0x00000000);
+}
 
-	gf100_gr_icmd(gr, gr->fuc_bundle);
-	nvkm_wr32(device, 0x404154, idle_timeout);
-	gf100_gr_mthd(gr, gr->fuc_method);
+void
+gm200_grctx_generate_dist_skip_table(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	u32 data[8] = {};
+	int gpc, ppc, i;
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+		for (ppc = 0; ppc < gr->ppc_nr[gpc]; ppc++) {
+			u8 ppc_tpcs = gr->ppc_tpc_nr[gpc][ppc];
+			u8 ppc_tpcm = gr->ppc_tpc_mask[gpc][ppc];
+			while (ppc_tpcs-- > gr->ppc_tpc_min)
+				ppc_tpcm &= ppc_tpcm - 1;
+			ppc_tpcm ^= gr->ppc_tpc_mask[gpc][ppc];
+			((u8 *)data)[gpc] |= ppc_tpcm;
+		}
+	}
 
-	nvkm_mask(device, 0x418e94, 0xffffffff, 0xc4230000);
-	nvkm_mask(device, 0x418e4c, 0xffffffff, 0x70000000);
+	for (i = 0; i < ARRAY_SIZE(data); i++)
+		nvkm_wr32(device, 0x4064d0 + (i * 0x04), data[i]);
 }
 
 const struct gf100_grctx_func
 gm200_grctx = {
-	.main  = gm200_grctx_generate_main,
+	.main  = gf100_grctx_generate_main,
 	.unkn  = gk104_grctx_generate_unkn,
 	.bundle = gm107_grctx_generate_bundle,
 	.bundle_size = 0x3000,
@@ -133,4 +116,13 @@ gm200_grctx = {
 	.attrib_nr = 0x400,
 	.alpha_nr_max = 0x1800,
 	.alpha_nr = 0x1000,
+	.sm_id = gm107_grctx_generate_sm_id,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.dist_skip_table = gm200_grctx_generate_dist_skip_table,
+	.r406500 = gm200_grctx_generate_r406500,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.tpc_mask = gm200_grctx_generate_tpc_mask,
+	.smid_config = gm200_grctx_generate_smid_config,
+	.r418e94 = gm200_grctx_generate_r418e94,
+	.r419a3c = gm200_grctx_generate_r419a3c,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
index e5702e3e0a5a..a1d9e114ebeb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
@@ -22,20 +22,6 @@
 #include "ctxgf100.h"
 
 static void
-gm20b_grctx_generate_r406028(struct gf100_gr *gr)
-{
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-	u32 tpc_per_gpc = 0;
-	int i;
-
-	for (i = 0; i < gr->gpc_nr; i++)
-		tpc_per_gpc |= gr->tpc_nr[i] << (4 * i);
-
-	nvkm_wr32(device, 0x406028, tpc_per_gpc);
-	nvkm_wr32(device, 0x405870, tpc_per_gpc);
-}
-
-static void
 gm20b_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -53,9 +39,7 @@ gm20b_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 
 	grctx->unkn(gr);
 
-	gm200_grctx_generate_tpcid(gr);
-	gm20b_grctx_generate_r406028(gr);
-	gk104_grctx_generate_r418bb8(gr);
+	gf100_grctx_generate_floorsweep(gr);
 
 	for (i = 0; i < 8; i++)
 		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
@@ -68,7 +52,7 @@ gm20b_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 		tmp |= ((1 << gr->tpc_nr[i]) - 1) << (i * 4);
 	nvkm_wr32(device, 0x4041c4, tmp);
 
-	gm200_grctx_generate_405b60(gr);
+	gm200_grctx_generate_smid_config(gr);
 
 	gf100_gr_wait_idle(gr);
 
@@ -98,4 +82,6 @@ gm20b_grctx = {
 	.attrib_nr = 0x400,
 	.alpha_nr_max = 0xc00,
 	.alpha_nr = 0x800,
+	.sm_id = gm107_grctx_generate_sm_id,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp100.c
index 88ea322d956c..0b3326262e12 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp100.c
@@ -36,7 +36,7 @@ gp100_grctx_generate_pagepool(struct gf100_grctx *info)
 	const int s = 8;
 	const int b = mmio_vram(info, grctx->pagepool_size, (1 << s), true);
 	mmio_refn(info, 0x40800c, 0x00000000, s, b);
-	mmio_wr32(info, 0x408010, 0x80000000);
+	mmio_wr32(info, 0x408010, 0x8007d800);
 	mmio_refn(info, 0x419004, 0x00000000, s, b);
 	mmio_wr32(info, 0x419008, 0x00000000);
 }
@@ -48,14 +48,17 @@ gp100_grctx_generate_attrib(struct gf100_grctx *info)
 	const struct gf100_grctx_func *grctx = gr->func->grctx;
 	const u32  alpha = grctx->alpha_nr;
 	const u32 attrib = grctx->attrib_nr;
-	const u32 pertpc = 0x20 * (grctx->attrib_nr_max + grctx->alpha_nr_max);
-	const u32   size = roundup(gr->tpc_total * pertpc, 0x80);
 	const int s = 12;
-	const int b = mmio_vram(info, size, (1 << s), false);
 	const int max_batches = 0xffff;
+	u32 size = grctx->alpha_nr_max * gr->tpc_total;
 	u32 ao = 0;
-	u32 bo = ao + grctx->alpha_nr_max * gr->tpc_total;
-	int gpc, ppc, n = 0;
+	u32 bo = ao + size;
+	int gpc, ppc, b, n = 0;
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++)
+		size += grctx->attrib_nr_max * gr->ppc_nr[gpc] * gr->ppc_tpc_max;
+	size = ((size * 0x20) + 128) & ~127;
+	b = mmio_vram(info, size, (1 << s), false);
 
 	mmio_refn(info, 0x418810, 0x80000000, s, b);
 	mmio_refn(info, 0x419848, 0x10000000, s, b);
@@ -69,7 +72,7 @@ gp100_grctx_generate_attrib(struct gf100_grctx *info)
 	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
 		for (ppc = 0; ppc < gr->ppc_nr[gpc]; ppc++, n++) {
 			const u32 as =  alpha * gr->ppc_tpc_nr[gpc][ppc];
-			const u32 bs = attrib * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 bs = attrib * gr->ppc_tpc_max;
 			const u32 u = 0x418ea0 + (n * 0x04);
 			const u32 o = PPC_UNIT(gpc, ppc, 0);
 			if (!(gr->ppc_mask[gpc] & (1 << ppc)))
@@ -77,7 +80,7 @@ gp100_grctx_generate_attrib(struct gf100_grctx *info)
 			mmio_wr32(info, o + 0xc0, bs);
 			mmio_wr32(info, o + 0xf4, bo);
 			mmio_wr32(info, o + 0xf0, bs);
-			bo += grctx->attrib_nr_max * gr->ppc_tpc_nr[gpc][ppc];
+			bo += grctx->attrib_nr_max * gr->ppc_tpc_max;
 			mmio_wr32(info, o + 0xe4, as);
 			mmio_wr32(info, o + 0xf8, ao);
 			ao += grctx->alpha_nr_max * gr->ppc_tpc_nr[gpc][ppc];
@@ -89,79 +92,30 @@ gp100_grctx_generate_attrib(struct gf100_grctx *info)
 	mmio_wr32(info, 0x41befc, 0x00000000);
 }
 
-static void
-gp100_grctx_generate_405b60(struct gf100_gr *gr)
+void
+gp100_grctx_generate_smid_config(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
 	const u32 dist_nr = DIV_ROUND_UP(gr->tpc_total, 4);
-	u32 dist[TPC_MAX / 4] = {};
-	u32 gpcs[GPC_MAX * 2] = {};
-	u8  tpcnr[GPC_MAX];
-	int tpc, gpc, i;
-
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-
-	/* won't result in the same distribution as the binary driver where
-	 * some of the gpcs have more tpcs than others, but this shall do
-	 * for the moment.  the code for earlier gpus has this issue too.
-	 */
-	for (gpc = -1, i = 0; i < gr->tpc_total; i++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while(!tpcnr[gpc]);
-		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
-
-		dist[i / 4] |= ((gpc << 4) | tpc) << ((i % 4) * 8);
-		gpcs[gpc + (gr->gpc_nr * (tpc / 4))] |= i << (tpc * 8);
+	u32 dist[TPC_MAX / 4] = {}, gpcs[16] = {};
+	u8  sm, i;
+
+	for (sm = 0; sm < gr->sm_nr; sm++) {
+		const u8 gpc = gr->sm[sm].gpc;
+		const u8 tpc = gr->sm[sm].tpc;
+		dist[sm / 4] |= ((gpc << 4) | tpc) << ((sm % 4) * 8);
+		gpcs[gpc + (gr->func->gpc_nr * (tpc / 4))] |= sm << ((tpc % 4) * 8);
 	}
 
 	for (i = 0; i < dist_nr; i++)
 		nvkm_wr32(device, 0x405b60 + (i * 4), dist[i]);
-	for (i = 0; i < gr->gpc_nr * 2; i++)
+	for (i = 0; i < ARRAY_SIZE(gpcs); i++)
 		nvkm_wr32(device, 0x405ba0 + (i * 4), gpcs[i]);
 }
 
-void
-gp100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
-{
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const struct gf100_grctx_func *grctx = gr->func->grctx;
-	u32 idle_timeout, tmp;
-	int i;
-
-	gf100_gr_mmio(gr, gr->fuc_sw_ctx);
-
-	idle_timeout = nvkm_mask(device, 0x404154, 0xffffffff, 0x00000000);
-
-	grctx->pagepool(info);
-	grctx->bundle(info);
-	grctx->attrib(info);
-	grctx->unkn(gr);
-
-	gm200_grctx_generate_tpcid(gr);
-	gf100_grctx_generate_r406028(gr);
-	gk104_grctx_generate_r418bb8(gr);
-
-	for (i = 0; i < 8; i++)
-		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
-	nvkm_wr32(device, 0x406500, 0x00000000);
-
-	nvkm_wr32(device, 0x405b00, (gr->tpc_total << 8) | gr->gpc_nr);
-
-	for (tmp = 0, i = 0; i < gr->gpc_nr; i++)
-		tmp |= ((1 << gr->tpc_nr[i]) - 1) << (i * 5);
-	nvkm_wr32(device, 0x4041c4, tmp);
-
-	gp100_grctx_generate_405b60(gr);
-
-	gf100_gr_icmd(gr, gr->fuc_bundle);
-	nvkm_wr32(device, 0x404154, idle_timeout);
-	gf100_gr_mthd(gr, gr->fuc_method);
-}
-
 const struct gf100_grctx_func
 gp100_grctx = {
-	.main  = gp100_grctx_generate_main,
+	.main  = gf100_grctx_generate_main,
 	.unkn  = gk104_grctx_generate_unkn,
 	.bundle = gm107_grctx_generate_bundle,
 	.bundle_size = 0x3000,
@@ -174,4 +128,12 @@ gp100_grctx = {
 	.attrib_nr = 0x440,
 	.alpha_nr_max = 0xc00,
 	.alpha_nr = 0x800,
+	.sm_id = gm107_grctx_generate_sm_id,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.dist_skip_table = gm200_grctx_generate_dist_skip_table,
+	.r406500 = gm200_grctx_generate_r406500,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.tpc_mask = gm200_grctx_generate_tpc_mask,
+	.smid_config = gp100_grctx_generate_smid_config,
+	.r419a3c = gm200_grctx_generate_r419a3c,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp102.c
index 7a66b4c2eb18..daee17bf7d0d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp102.c
@@ -29,6 +29,13 @@
  * PGRAPH context implementation
  ******************************************************************************/
 
+static void
+gp102_grctx_generate_r408840(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x408840, 0x00000003, 0x00000000);
+}
+
 void
 gp102_grctx_generate_attrib(struct gf100_grctx *info)
 {
@@ -36,14 +43,18 @@ gp102_grctx_generate_attrib(struct gf100_grctx *info)
 	const struct gf100_grctx_func *grctx = gr->func->grctx;
 	const u32  alpha = grctx->alpha_nr;
 	const u32 attrib = grctx->attrib_nr;
-	const u32 pertpc = 0x20 * (grctx->attrib_nr_max + grctx->alpha_nr_max);
-	const u32   size = roundup(gr->tpc_total * pertpc, 0x80);
+	const u32   gfxp = grctx->gfxp_nr;
 	const int s = 12;
-	const int b = mmio_vram(info, size, (1 << s), false);
 	const int max_batches = 0xffff;
+	u32 size = grctx->alpha_nr_max * gr->tpc_total;
 	u32 ao = 0;
-	u32 bo = ao + grctx->alpha_nr_max * gr->tpc_total;
-	int gpc, ppc, n = 0;
+	u32 bo = ao + size;
+	int gpc, ppc, b, n = 0;
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++)
+		size += grctx->gfxp_nr * gr->ppc_nr[gpc] * gr->ppc_tpc_max;
+	size = ((size * 0x20) + 128) & ~127;
+	b = mmio_vram(info, size, (1 << s), false);
 
 	mmio_refn(info, 0x418810, 0x80000000, s, b);
 	mmio_refn(info, 0x419848, 0x10000000, s, b);
@@ -57,17 +68,18 @@ gp102_grctx_generate_attrib(struct gf100_grctx *info)
 	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
 		for (ppc = 0; ppc < gr->ppc_nr[gpc]; ppc++, n++) {
 			const u32 as =  alpha * gr->ppc_tpc_nr[gpc][ppc];
-			const u32 bs = attrib * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 bs = attrib * gr->ppc_tpc_max;
+			const u32 gs =   gfxp * gr->ppc_tpc_max;
 			const u32 u = 0x418ea0 + (n * 0x04);
 			const u32 o = PPC_UNIT(gpc, ppc, 0);
 			const u32 p = GPC_UNIT(gpc, 0xc44 + (ppc * 4));
 			if (!(gr->ppc_mask[gpc] & (1 << ppc)))
 				continue;
-			mmio_wr32(info, o + 0xc0, bs);
+			mmio_wr32(info, o + 0xc0, gs);
 			mmio_wr32(info, p, bs);
 			mmio_wr32(info, o + 0xf4, bo);
 			mmio_wr32(info, o + 0xf0, bs);
-			bo += grctx->attrib_nr_max * gr->ppc_tpc_nr[gpc][ppc];
+			bo += gs;
 			mmio_wr32(info, o + 0xe4, as);
 			mmio_wr32(info, o + 0xf8, ao);
 			ao += grctx->alpha_nr_max * gr->ppc_tpc_nr[gpc][ppc];
@@ -81,7 +93,7 @@ gp102_grctx_generate_attrib(struct gf100_grctx *info)
 
 const struct gf100_grctx_func
 gp102_grctx = {
-	.main = gp100_grctx_generate_main,
+	.main = gf100_grctx_generate_main,
 	.unkn = gk104_grctx_generate_unkn,
 	.bundle = gm107_grctx_generate_bundle,
 	.bundle_size = 0x3000,
@@ -90,8 +102,18 @@ gp102_grctx = {
 	.pagepool = gp100_grctx_generate_pagepool,
 	.pagepool_size = 0x20000,
 	.attrib = gp102_grctx_generate_attrib,
-	.attrib_nr_max = 0x5d4,
+	.attrib_nr_max = 0x4b0,
 	.attrib_nr = 0x320,
 	.alpha_nr_max = 0xc00,
 	.alpha_nr = 0x800,
+	.gfxp_nr = 0xba8,
+	.sm_id = gm107_grctx_generate_sm_id,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.dist_skip_table = gm200_grctx_generate_dist_skip_table,
+	.r406500 = gm200_grctx_generate_r406500,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.tpc_mask = gm200_grctx_generate_tpc_mask,
+	.smid_config = gp100_grctx_generate_smid_config,
+	.r419a3c = gm200_grctx_generate_r419a3c,
+	.r408840 = gp102_grctx_generate_r408840,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp104.c
new file mode 100644
index 000000000000..3b85e3d326b2
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp104.c
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ctxgf100.h"
+
+const struct gf100_grctx_func
+gp104_grctx = {
+	.main = gf100_grctx_generate_main,
+	.unkn = gk104_grctx_generate_unkn,
+	.bundle = gm107_grctx_generate_bundle,
+	.bundle_size = 0x3000,
+	.bundle_min_gpm_fifo_depth = 0x180,
+	.bundle_token_limit = 0x900,
+	.pagepool = gp100_grctx_generate_pagepool,
+	.pagepool_size = 0x20000,
+	.attrib = gp102_grctx_generate_attrib,
+	.attrib_nr_max = 0x4b0,
+	.attrib_nr = 0x320,
+	.alpha_nr_max = 0xc00,
+	.alpha_nr = 0x800,
+	.gfxp_nr = 0xba8,
+	.sm_id = gm107_grctx_generate_sm_id,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.dist_skip_table = gm200_grctx_generate_dist_skip_table,
+	.r406500 = gm200_grctx_generate_r406500,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.tpc_mask = gm200_grctx_generate_tpc_mask,
+	.smid_config = gp100_grctx_generate_smid_config,
+	.r419a3c = gm200_grctx_generate_r419a3c,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp107.c
index 8da91a0b3bd2..5060c5ee5ce0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp107.c
@@ -31,7 +31,7 @@
 
 const struct gf100_grctx_func
 gp107_grctx = {
-	.main = gp100_grctx_generate_main,
+	.main = gf100_grctx_generate_main,
 	.unkn = gk104_grctx_generate_unkn,
 	.bundle = gm107_grctx_generate_bundle,
 	.bundle_size = 0x3000,
@@ -44,4 +44,13 @@ gp107_grctx = {
 	.attrib_nr = 0x540,
 	.alpha_nr_max = 0xc00,
 	.alpha_nr = 0x800,
+	.gfxp_nr = 0xe94,
+	.sm_id = gm107_grctx_generate_sm_id,
+	.rop_mapping = gf117_grctx_generate_rop_mapping,
+	.dist_skip_table = gm200_grctx_generate_dist_skip_table,
+	.r406500 = gm200_grctx_generate_r406500,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.tpc_mask = gm200_grctx_generate_tpc_mask,
+	.smid_config = gp100_grctx_generate_smid_config,
+	.r419a3c = gm200_grctx_generate_r419a3c,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c
new file mode 100644
index 000000000000..0990765ef191
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c
@@ -0,0 +1,215 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ctxgf100.h"
+
+/*******************************************************************************
+ * PGRAPH context implementation
+ ******************************************************************************/
+
+static const struct gf100_gr_init
+gv100_grctx_init_sw_veid_bundle_init_0[] = {
+	{ 0x00001000, 64, 0x00100000, 0x00000008 },
+	{ 0x00000941, 64, 0x00100000, 0x00000000 },
+	{ 0x0000097e, 64, 0x00100000, 0x00000000 },
+	{ 0x0000097f, 64, 0x00100000, 0x00000100 },
+	{ 0x0000035c, 64, 0x00100000, 0x00000000 },
+	{ 0x0000035d, 64, 0x00100000, 0x00000000 },
+	{ 0x00000a08, 64, 0x00100000, 0x00000000 },
+	{ 0x00000a09, 64, 0x00100000, 0x00000000 },
+	{ 0x00000a0a, 64, 0x00100000, 0x00000000 },
+	{ 0x00000352, 64, 0x00100000, 0x00000000 },
+	{ 0x00000353, 64, 0x00100000, 0x00000000 },
+	{ 0x00000358, 64, 0x00100000, 0x00000000 },
+	{ 0x00000359, 64, 0x00100000, 0x00000000 },
+	{ 0x00000370, 64, 0x00100000, 0x00000000 },
+	{ 0x00000371, 64, 0x00100000, 0x00000000 },
+	{ 0x00000372, 64, 0x00100000, 0x000fffff },
+	{ 0x00000366, 64, 0x00100000, 0x00000000 },
+	{ 0x00000367, 64, 0x00100000, 0x00000000 },
+	{ 0x00000368, 64, 0x00100000, 0x00000fff },
+	{ 0x00000623, 64, 0x00100000, 0x00000000 },
+	{ 0x00000624, 64, 0x00100000, 0x00000000 },
+	{ 0x0001e100,  1, 0x00000001, 0x02000001 },
+	{}
+};
+
+static const struct gf100_gr_pack
+gv100_grctx_pack_sw_veid_bundle_init[] = {
+	{ gv100_grctx_init_sw_veid_bundle_init_0 },
+	{}
+};
+
+static void
+gv100_grctx_generate_attrib(struct gf100_grctx *info)
+{
+	struct gf100_gr *gr = info->gr;
+	const struct gf100_grctx_func *grctx = gr->func->grctx;
+	const u32  alpha = grctx->alpha_nr;
+	const u32 attrib = grctx->attrib_nr;
+	const u32   gfxp = grctx->gfxp_nr;
+	const int s = 12;
+	const int max_batches = 0xffff;
+	u32 size = grctx->alpha_nr_max * gr->tpc_total;
+	u32 ao = 0;
+	u32 bo = ao + size;
+	int gpc, ppc, b, n = 0;
+
+	size += grctx->gfxp_nr * gr->tpc_total;
+	size = ((size * 0x20) + 128) & ~127;
+	b = mmio_vram(info, size, (1 << s), false);
+
+	mmio_refn(info, 0x418810, 0x80000000, s, b);
+	mmio_refn(info, 0x419848, 0x10000000, s, b);
+	mmio_refn(info, 0x419c2c, 0x10000000, s, b);
+	mmio_refn(info, 0x419e00, 0x00000000, s, b);
+	mmio_wr32(info, 0x419e04, 0x80000000 | size >> 7);
+	mmio_wr32(info, 0x405830, attrib);
+	mmio_wr32(info, 0x40585c, alpha);
+	mmio_wr32(info, 0x4064c4, ((alpha / 4) << 16) | max_batches);
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+		for (ppc = 0; ppc < gr->ppc_nr[gpc]; ppc++, n++) {
+			const u32 as =  alpha * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 bs = attrib * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 gs =   gfxp * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 u = 0x418ea0 + (n * 0x04);
+			const u32 o = PPC_UNIT(gpc, ppc, 0);
+			if (!(gr->ppc_mask[gpc] & (1 << ppc)))
+				continue;
+			mmio_wr32(info, o + 0xc0, gs);
+			mmio_wr32(info, o + 0xf4, bo);
+			mmio_wr32(info, o + 0xf0, bs);
+			bo += gs;
+			mmio_wr32(info, o + 0xe4, as);
+			mmio_wr32(info, o + 0xf8, ao);
+			ao += grctx->alpha_nr_max * gr->ppc_tpc_nr[gpc][ppc];
+			mmio_wr32(info, u, bs);
+		}
+	}
+
+	mmio_wr32(info, 0x4181e4, 0x00000100);
+	mmio_wr32(info, 0x41befc, 0x00000100);
+}
+
+static void
+gv100_grctx_generate_rop_mapping(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	u32 data;
+	int i, j;
+
+	/* Pack tile map into register format. */
+	nvkm_wr32(device, 0x418bb8, (gr->tpc_total << 8) |
+				     gr->screen_tile_row_offset);
+	for (i = 0; i < 11; i++) {
+		for (data = 0, j = 0; j < 6; j++)
+			data |= (gr->tile[i * 6 + j] & 0x1f) << (j * 5);
+		nvkm_wr32(device, 0x418b08 + (i * 4), data);
+		nvkm_wr32(device, 0x41bf00 + (i * 4), data);
+		nvkm_wr32(device, 0x40780c + (i * 4), data);
+	}
+
+	/* GPC_BROADCAST.TP_BROADCAST */
+	nvkm_wr32(device, 0x41bfd0, (gr->tpc_total << 8) |
+				     gr->screen_tile_row_offset);
+	for (i = 0, j = 1; i < 5; i++, j += 4) {
+		u8 v19 = (1 << (j + 0)) % gr->tpc_total;
+		u8 v20 = (1 << (j + 1)) % gr->tpc_total;
+		u8 v21 = (1 << (j + 2)) % gr->tpc_total;
+		u8 v22 = (1 << (j + 3)) % gr->tpc_total;
+		nvkm_wr32(device, 0x41bfb0 + (i * 4), (v22 << 24) |
+						      (v21 << 16) |
+						      (v20 <<  8) |
+						       v19);
+	}
+
+	/* UNK78xx */
+	nvkm_wr32(device, 0x4078bc, (gr->tpc_total << 8) |
+				     gr->screen_tile_row_offset);
+}
+
+static void
+gv100_grctx_generate_r400088(struct gf100_gr *gr, bool on)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x400088, 0x00060000, on ? 0x00060000 : 0x00000000);
+}
+
+static void
+gv100_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x608), sm);
+	nvkm_wr32(device, GPC_UNIT(gpc, 0x0c10 + tpc * 4), sm);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), sm);
+}
+
+static void
+gv100_grctx_generate_unkn(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x41980c, 0x00000010, 0x00000010);
+	nvkm_mask(device, 0x41be08, 0x00000004, 0x00000004);
+	nvkm_mask(device, 0x4064c0, 0x80000000, 0x80000000);
+	nvkm_mask(device, 0x405800, 0x08000000, 0x08000000);
+	nvkm_mask(device, 0x419c00, 0x00000008, 0x00000008);
+}
+
+static void
+gv100_grctx_unkn88c(struct gf100_gr *gr, bool on)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const u32 mask = 0x00000010, data = on ? mask : 0x00000000;
+	nvkm_mask(device, 0x40988c, mask, data);
+	nvkm_rd32(device, 0x40988c);
+	nvkm_mask(device, 0x41a88c, mask, data);
+	nvkm_rd32(device, 0x41a88c);
+	nvkm_mask(device, 0x408a14, mask, data);
+	nvkm_rd32(device, 0x408a14);
+}
+
+const struct gf100_grctx_func
+gv100_grctx = {
+	.unkn88c = gv100_grctx_unkn88c,
+	.main = gf100_grctx_generate_main,
+	.unkn = gv100_grctx_generate_unkn,
+	.sw_veid_bundle_init = gv100_grctx_pack_sw_veid_bundle_init,
+	.bundle = gm107_grctx_generate_bundle,
+	.bundle_size = 0x3000,
+	.bundle_min_gpm_fifo_depth = 0x180,
+	.bundle_token_limit = 0x1680,
+	.pagepool = gp100_grctx_generate_pagepool,
+	.pagepool_size = 0x20000,
+	.attrib = gv100_grctx_generate_attrib,
+	.attrib_nr_max = 0x6c0,
+	.attrib_nr = 0x480,
+	.alpha_nr_max = 0xc00,
+	.alpha_nr = 0x800,
+	.gfxp_nr = 0xd10,
+	.sm_id = gv100_grctx_generate_sm_id,
+	.rop_mapping = gv100_grctx_generate_rop_mapping,
+	.dist_skip_table = gm200_grctx_generate_dist_skip_table,
+	.r406500 = gm200_grctx_generate_r406500,
+	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
+	.smid_config = gp100_grctx_generate_smid_config,
+	.r400088 = gv100_grctx_generate_r400088,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 2f8dc107047d..70d3d41e616c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -32,6 +32,7 @@
 #include <subdev/fb.h>
 #include <subdev/mc.h>
 #include <subdev/pmu.h>
+#include <subdev/therm.h>
 #include <subdev/timer.h>
 #include <engine/fifo.h>
 
@@ -91,7 +92,7 @@ gf100_gr_zbc_color_get(struct gf100_gr *gr, int format,
 	memcpy(gr->zbc_color[zbc].l2, l2, sizeof(gr->zbc_color[zbc].l2));
 	gr->zbc_color[zbc].format = format;
 	nvkm_ltc_zbc_color_get(ltc, zbc, l2);
-	gf100_gr_zbc_clear_color(gr, zbc);
+	gr->func->zbc->clear_color(gr, zbc);
 	return zbc;
 }
 
@@ -136,10 +137,16 @@ gf100_gr_zbc_depth_get(struct gf100_gr *gr, int format,
 	gr->zbc_depth[zbc].ds = ds;
 	gr->zbc_depth[zbc].l2 = l2;
 	nvkm_ltc_zbc_depth_get(ltc, zbc, l2);
-	gf100_gr_zbc_clear_depth(gr, zbc);
+	gr->func->zbc->clear_depth(gr, zbc);
 	return zbc;
 }
 
+const struct gf100_gr_func_zbc
+gf100_gr_zbc = {
+	.clear_color = gf100_gr_zbc_clear_color,
+	.clear_depth = gf100_gr_zbc_clear_depth,
+};
+
 /*******************************************************************************
  * Graphics object classes
  ******************************************************************************/
@@ -743,21 +750,31 @@ gf100_gr_zbc_init(struct gf100_gr *gr)
 	const u32 f32_1[] = { 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000,
 			      0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 };
 	struct nvkm_ltc *ltc = gr->base.engine.subdev.device->ltc;
-	int index;
+	int index, c = ltc->zbc_min, d = ltc->zbc_min, s = ltc->zbc_min;
 
 	if (!gr->zbc_color[0].format) {
-		gf100_gr_zbc_color_get(gr, 1,  & zero[0],   &zero[4]);
-		gf100_gr_zbc_color_get(gr, 2,  &  one[0],    &one[4]);
-		gf100_gr_zbc_color_get(gr, 4,  &f32_0[0],  &f32_0[4]);
-		gf100_gr_zbc_color_get(gr, 4,  &f32_1[0],  &f32_1[4]);
-		gf100_gr_zbc_depth_get(gr, 1, 0x00000000, 0x00000000);
-		gf100_gr_zbc_depth_get(gr, 1, 0x3f800000, 0x3f800000);
-	}
-
-	for (index = ltc->zbc_min; index <= ltc->zbc_max; index++)
-		gf100_gr_zbc_clear_color(gr, index);
-	for (index = ltc->zbc_min; index <= ltc->zbc_max; index++)
-		gf100_gr_zbc_clear_depth(gr, index);
+		gf100_gr_zbc_color_get(gr, 1,  & zero[0],   &zero[4]); c++;
+		gf100_gr_zbc_color_get(gr, 2,  &  one[0],    &one[4]); c++;
+		gf100_gr_zbc_color_get(gr, 4,  &f32_0[0],  &f32_0[4]); c++;
+		gf100_gr_zbc_color_get(gr, 4,  &f32_1[0],  &f32_1[4]); c++;
+		gf100_gr_zbc_depth_get(gr, 1, 0x00000000, 0x00000000); d++;
+		gf100_gr_zbc_depth_get(gr, 1, 0x3f800000, 0x3f800000); d++;
+		if (gr->func->zbc->stencil_get) {
+			gr->func->zbc->stencil_get(gr, 1, 0x00, 0x00); s++;
+			gr->func->zbc->stencil_get(gr, 1, 0x01, 0x01); s++;
+			gr->func->zbc->stencil_get(gr, 1, 0xff, 0xff); s++;
+		}
+	}
+
+	for (index = c; index <= ltc->zbc_max; index++)
+		gr->func->zbc->clear_color(gr, index);
+	for (index = d; index <= ltc->zbc_max; index++)
+		gr->func->zbc->clear_depth(gr, index);
+
+	if (gr->func->zbc->clear_stencil) {
+		for (index = s; index <= ltc->zbc_max; index++)
+			gr->func->zbc->clear_stencil(gr, index);
+	}
 }
 
 /**
@@ -970,7 +987,7 @@ gf100_gr_trap_gpc_rop(struct gf100_gr *gr, int gpc)
 	nvkm_wr32(device, GPC_UNIT(gpc, 0x0420), 0xc0000000);
 }
 
-static const struct nvkm_enum gf100_mp_warp_error[] = {
+const struct nvkm_enum gf100_mp_warp_error[] = {
 	{ 0x01, "STACK_ERROR" },
 	{ 0x02, "API_STACK_ERROR" },
 	{ 0x03, "RET_EMPTY_STACK_ERROR" },
@@ -995,7 +1012,7 @@ static const struct nvkm_enum gf100_mp_warp_error[] = {
 	{}
 };
 
-static const struct nvkm_bitfield gf100_mp_global_error[] = {
+const struct nvkm_bitfield gf100_mp_global_error[] = {
 	{ 0x00000001, "SM_TO_SM_FAULT" },
 	{ 0x00000002, "L1_ERROR" },
 	{ 0x00000004, "MULTIPLE_WARP_ERRORS" },
@@ -1009,7 +1026,7 @@ static const struct nvkm_bitfield gf100_mp_global_error[] = {
 	{}
 };
 
-static void
+void
 gf100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
 {
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
@@ -1045,7 +1062,7 @@ gf100_gr_trap_tpc(struct gf100_gr *gr, int gpc, int tpc)
 	}
 
 	if (stat & 0x00000002) {
-		gf100_gr_trap_mp(gr, gpc, tpc);
+		gr->func->trap_mp(gr, gpc, tpc);
 		stat &= ~0x00000002;
 	}
 
@@ -1611,7 +1628,8 @@ gf100_gr_init_ctxctl_int(struct gf100_gr *gr)
 
 	/* load register lists */
 	gf100_gr_init_csdata(gr, grctx->hub, 0x409000, 0x000, 0x000000);
-	gf100_gr_init_csdata(gr, grctx->gpc, 0x41a000, 0x000, 0x418000);
+	gf100_gr_init_csdata(gr, grctx->gpc_0, 0x41a000, 0x000, 0x418000);
+	gf100_gr_init_csdata(gr, grctx->gpc_1, 0x41a000, 0x000, 0x418000);
 	gf100_gr_init_csdata(gr, grctx->tpc, 0x41a000, 0x004, 0x419800);
 	gf100_gr_init_csdata(gr, grctx->ppc, 0x41a000, 0x008, 0x41be00);
 
@@ -1651,6 +1669,97 @@ gf100_gr_init_ctxctl(struct gf100_gr *gr)
 	return ret;
 }
 
+void
+gf100_gr_oneinit_sm_id(struct gf100_gr *gr)
+{
+	int tpc, gpc;
+	for (tpc = 0; tpc < gr->tpc_max; tpc++) {
+		for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+			if (tpc < gr->tpc_nr[gpc]) {
+				gr->sm[gr->sm_nr].gpc = gpc;
+				gr->sm[gr->sm_nr].tpc = tpc;
+				gr->sm_nr++;
+			}
+		}
+	}
+}
+
+void
+gf100_gr_oneinit_tiles(struct gf100_gr *gr)
+{
+	static const u8 primes[] = {
+		3, 5, 7, 11, 13, 17, 19, 23, 29, 31, 37, 41, 43, 47, 53, 59, 61
+	};
+	int init_frac[GPC_MAX], init_err[GPC_MAX], run_err[GPC_MAX], i, j;
+	u32 mul_factor, comm_denom;
+	u8  gpc_map[GPC_MAX];
+	bool sorted;
+
+	switch (gr->tpc_total) {
+	case 15: gr->screen_tile_row_offset = 0x06; break;
+	case 14: gr->screen_tile_row_offset = 0x05; break;
+	case 13: gr->screen_tile_row_offset = 0x02; break;
+	case 11: gr->screen_tile_row_offset = 0x07; break;
+	case 10: gr->screen_tile_row_offset = 0x06; break;
+	case  7:
+	case  5: gr->screen_tile_row_offset = 0x01; break;
+	case  3: gr->screen_tile_row_offset = 0x02; break;
+	case  2:
+	case  1: gr->screen_tile_row_offset = 0x01; break;
+	default: gr->screen_tile_row_offset = 0x03;
+		for (i = 0; i < ARRAY_SIZE(primes); i++) {
+			if (gr->tpc_total % primes[i]) {
+				gr->screen_tile_row_offset = primes[i];
+				break;
+			}
+		}
+		break;
+	}
+
+	/* Sort GPCs by TPC count, highest-to-lowest. */
+	for (i = 0; i < gr->gpc_nr; i++)
+		gpc_map[i] = i;
+	sorted = false;
+
+	while (!sorted) {
+		for (sorted = true, i = 0; i < gr->gpc_nr - 1; i++) {
+			if (gr->tpc_nr[gpc_map[i + 1]] >
+			    gr->tpc_nr[gpc_map[i + 0]]) {
+				u8 swap = gpc_map[i];
+				gpc_map[i + 0] = gpc_map[i + 1];
+				gpc_map[i + 1] = swap;
+				sorted = false;
+			}
+		}
+	}
+
+	/* Determine tile->GPC mapping */
+	mul_factor = gr->gpc_nr * gr->tpc_max;
+	if (mul_factor & 1)
+		mul_factor = 2;
+	else
+		mul_factor = 1;
+
+	comm_denom = gr->gpc_nr * gr->tpc_max * mul_factor;
+
+	for (i = 0; i < gr->gpc_nr; i++) {
+		init_frac[i] = gr->tpc_nr[gpc_map[i]] * gr->gpc_nr * mul_factor;
+		 init_err[i] = i * gr->tpc_max * mul_factor - comm_denom/2;
+		  run_err[i] = init_frac[i] + init_err[i];
+	}
+
+	for (i = 0; i < gr->tpc_total;) {
+		for (j = 0; j < gr->gpc_nr; j++) {
+			if ((run_err[j] * 2) >= comm_denom) {
+				gr->tile[i++] = gpc_map[j];
+				run_err[j] += init_frac[j] - comm_denom;
+			} else {
+				run_err[j] += init_frac[j];
+			}
+		}
+	}
+}
+
 static int
 gf100_gr_oneinit(struct nvkm_gr *base)
 {
@@ -1674,55 +1783,27 @@ gf100_gr_oneinit(struct nvkm_gr *base)
 	gr->gpc_nr = nvkm_rd32(device, 0x409604) & 0x0000001f;
 	for (i = 0; i < gr->gpc_nr; i++) {
 		gr->tpc_nr[i]  = nvkm_rd32(device, GPC_UNIT(i, 0x2608));
+		gr->tpc_max = max(gr->tpc_max, gr->tpc_nr[i]);
 		gr->tpc_total += gr->tpc_nr[i];
 		gr->ppc_nr[i]  = gr->func->ppc_nr;
 		for (j = 0; j < gr->ppc_nr[i]; j++) {
-			u8 mask = nvkm_rd32(device, GPC_UNIT(i, 0x0c30 + (j * 4)));
-			if (mask)
-				gr->ppc_mask[i] |= (1 << j);
-			gr->ppc_tpc_nr[i][j] = hweight8(mask);
-		}
-	}
-
-	/*XXX: these need figuring out... though it might not even matter */
-	switch (device->chipset) {
-	case 0xc0:
-		if (gr->tpc_total == 11) { /* 465, 3/4/4/0, 4 */
-			gr->screen_tile_row_offset = 0x07;
-		} else
-		if (gr->tpc_total == 14) { /* 470, 3/3/4/4, 5 */
-			gr->screen_tile_row_offset = 0x05;
-		} else
-		if (gr->tpc_total == 15) { /* 480, 3/4/4/4, 6 */
-			gr->screen_tile_row_offset = 0x06;
+			gr->ppc_tpc_mask[i][j] =
+				nvkm_rd32(device, GPC_UNIT(i, 0x0c30 + (j * 4)));
+			if (gr->ppc_tpc_mask[i][j] == 0)
+				continue;
+			gr->ppc_mask[i] |= (1 << j);
+			gr->ppc_tpc_nr[i][j] = hweight8(gr->ppc_tpc_mask[i][j]);
+			if (gr->ppc_tpc_min == 0 ||
+			    gr->ppc_tpc_min > gr->ppc_tpc_nr[i][j])
+				gr->ppc_tpc_min = gr->ppc_tpc_nr[i][j];
+			if (gr->ppc_tpc_max < gr->ppc_tpc_nr[i][j])
+				gr->ppc_tpc_max = gr->ppc_tpc_nr[i][j];
 		}
-		break;
-	case 0xc3: /* 450, 4/0/0/0, 2 */
-		gr->screen_tile_row_offset = 0x03;
-		break;
-	case 0xc4: /* 460, 3/4/0/0, 4 */
-		gr->screen_tile_row_offset = 0x01;
-		break;
-	case 0xc1: /* 2/0/0/0, 1 */
-		gr->screen_tile_row_offset = 0x01;
-		break;
-	case 0xc8: /* 4/4/3/4, 5 */
-		gr->screen_tile_row_offset = 0x06;
-		break;
-	case 0xce: /* 4/4/0/0, 4 */
-		gr->screen_tile_row_offset = 0x03;
-		break;
-	case 0xcf: /* 4/0/0/0, 3 */
-		gr->screen_tile_row_offset = 0x03;
-		break;
-	case 0xd7:
-	case 0xd9: /* 1/0/0/0, 1 */
-	case 0xea: /* gk20a */
-	case 0x12b: /* gm20b */
-		gr->screen_tile_row_offset = 0x01;
-		break;
 	}
 
+	memset(gr->tile, 0xff, sizeof(gr->tile));
+	gr->func->oneinit_tiles(gr);
+	gr->func->oneinit_sm_id(gr);
 	return 0;
 }
 
@@ -1914,13 +1995,68 @@ gf100_gr_new_(const struct gf100_gr_func *func, struct nvkm_device *device,
 }
 
 void
+gf100_gr_init_400054(struct gf100_gr *gr)
+{
+	nvkm_wr32(gr->base.engine.subdev.device, 0x400054, 0x34ce3464);
+}
+
+void
+gf100_gr_init_shader_exceptions(struct gf100_gr *gr, int gpc, int tpc)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x001ffffe);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x0000000f);
+}
+
+void
+gf100_gr_init_tex_hww_esr(struct gf100_gr *gr, int gpc, int tpc)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x224), 0xc0000000);
+}
+
+void
+gf100_gr_init_419eb4(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x419eb4, 0x00001000, 0x00001000);
+}
+
+void
+gf100_gr_init_419cc0(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	int gpc, tpc;
+
+	nvkm_mask(device, 0x419cc0, 0x00000008, 0x00000008);
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+		for (tpc = 0; tpc < gr->tpc_nr[gpc]; tpc++)
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x48c), 0xc0000000);
+	}
+}
+
+void
+gf100_gr_init_40601c(struct gf100_gr *gr)
+{
+	nvkm_wr32(gr->base.engine.subdev.device, 0x40601c, 0xc0000000);
+}
+
+void
+gf100_gr_init_fecs_exceptions(struct gf100_gr *gr)
+{
+	const u32 data = gr->firmware ? 0x000e0000 : 0x000e0001;
+	nvkm_wr32(gr->base.engine.subdev.device, 0x409c24, data);
+}
+
+void
 gf100_gr_init_gpc_mmu(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
 	struct nvkm_fb *fb = device->fb;
 
 	nvkm_wr32(device, 0x418880, nvkm_rd32(device, 0x100c80) & 0x00000001);
-	nvkm_wr32(device, 0x4188a4, 0x00000000);
+	nvkm_wr32(device, 0x4188a4, 0x03000000);
 	nvkm_wr32(device, 0x418888, 0x00000000);
 	nvkm_wr32(device, 0x41888c, 0x00000000);
 	nvkm_wr32(device, 0x418890, 0x00000000);
@@ -1929,37 +2065,30 @@ gf100_gr_init_gpc_mmu(struct gf100_gr *gr)
 	nvkm_wr32(device, 0x4188b8, nvkm_memory_addr(fb->mmu_rd) >> 8);
 }
 
-int
-gf100_gr_init(struct gf100_gr *gr)
+void
+gf100_gr_init_num_active_ltcs(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
-	u32 data[TPC_MAX / 8] = {};
-	u8  tpcnr[GPC_MAX];
-	int gpc, tpc, rop;
-	int i;
-
-	gr->func->init_gpc_mmu(gr);
-
-	gf100_gr_mmio(gr, gr->func->mmio);
-
-	nvkm_mask(device, TPC_UNIT(0, 0, 0x05c), 0x00000001, 0x00000001);
-
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-	for (i = 0, gpc = -1; i < gr->tpc_total; i++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
+	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
+}
 
-		data[i / 8] |= tpc << ((i % 8) * 4);
+void
+gf100_gr_init_zcull(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
+	const u8 tile_nr = ALIGN(gr->tpc_total, 32);
+	u8 bank[GPC_MAX] = {}, gpc, i, j;
+	u32 data;
+
+	for (i = 0; i < tile_nr; i += 8) {
+		for (data = 0, j = 0; j < 8 && i + j < gr->tpc_total; j++) {
+			data |= bank[gr->tile[i + j]] << (j * 4);
+			bank[gr->tile[i + j]]++;
+		}
+		nvkm_wr32(device, GPC_BCAST(0x0980 + ((i / 8) * 4)), data);
 	}
 
-	nvkm_wr32(device, GPC_BCAST(0x0980), data[0]);
-	nvkm_wr32(device, GPC_BCAST(0x0984), data[1]);
-	nvkm_wr32(device, GPC_BCAST(0x0988), data[2]);
-	nvkm_wr32(device, GPC_BCAST(0x098c), data[3]);
-
 	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
 		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
 			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
@@ -1968,29 +2097,88 @@ gf100_gr_init(struct gf100_gr *gr)
 		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
 	}
 
-	if (device->chipset != 0xd7)
-		nvkm_wr32(device, GPC_BCAST(0x1bd4), magicgpc918);
+	nvkm_wr32(device, GPC_BCAST(0x1bd4), magicgpc918);
+}
+
+void
+gf100_gr_init_vsc_stream_master(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, TPC_UNIT(0, 0, 0x05c), 0x00000001, 0x00000001);
+}
+
+int
+gf100_gr_init(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	int gpc, tpc, rop;
+
+	if (gr->func->init_419bd8)
+		gr->func->init_419bd8(gr);
+
+	gr->func->init_gpc_mmu(gr);
+
+	if (gr->fuc_sw_nonctx)
+		gf100_gr_mmio(gr, gr->fuc_sw_nonctx);
 	else
-		nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
+		gf100_gr_mmio(gr, gr->func->mmio);
 
-	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
+	gf100_gr_wait_idle(gr);
+
+	if (gr->func->init_r405a14)
+		gr->func->init_r405a14(gr);
+
+	if (gr->func->clkgate_pack)
+		nvkm_therm_clkgate_init(device->therm, gr->func->clkgate_pack);
+
+	if (gr->func->init_bios)
+		gr->func->init_bios(gr);
+
+	gr->func->init_vsc_stream_master(gr);
+	gr->func->init_zcull(gr);
+	gr->func->init_num_active_ltcs(gr);
+	if (gr->func->init_rop_active_fbps)
+		gr->func->init_rop_active_fbps(gr);
+	if (gr->func->init_bios_2)
+		gr->func->init_bios_2(gr);
+	if (gr->func->init_swdx_pes_mask)
+		gr->func->init_swdx_pes_mask(gr);
 
 	nvkm_wr32(device, 0x400500, 0x00010001);
 
 	nvkm_wr32(device, 0x400100, 0xffffffff);
 	nvkm_wr32(device, 0x40013c, 0xffffffff);
+	nvkm_wr32(device, 0x400124, 0x00000002);
+
+	gr->func->init_fecs_exceptions(gr);
+	if (gr->func->init_ds_hww_esr_2)
+		gr->func->init_ds_hww_esr_2(gr);
 
-	nvkm_wr32(device, 0x409c24, 0x000f0000);
 	nvkm_wr32(device, 0x404000, 0xc0000000);
 	nvkm_wr32(device, 0x404600, 0xc0000000);
 	nvkm_wr32(device, 0x408030, 0xc0000000);
-	nvkm_wr32(device, 0x40601c, 0xc0000000);
+
+	if (gr->func->init_40601c)
+		gr->func->init_40601c(gr);
+
 	nvkm_wr32(device, 0x404490, 0xc0000000);
 	nvkm_wr32(device, 0x406018, 0xc0000000);
+
+	if (gr->func->init_sked_hww_esr)
+		gr->func->init_sked_hww_esr(gr);
+
 	nvkm_wr32(device, 0x405840, 0xc0000000);
 	nvkm_wr32(device, 0x405844, 0x00ffffff);
-	nvkm_mask(device, 0x419cc0, 0x00000008, 0x00000008);
-	nvkm_mask(device, 0x419eb4, 0x00001000, 0x00001000);
+
+	if (gr->func->init_419cc0)
+		gr->func->init_419cc0(gr);
+	if (gr->func->init_419eb4)
+		gr->func->init_419eb4(gr);
+	if (gr->func->init_419c9c)
+		gr->func->init_419c9c(gr);
+
+	if (gr->func->init_ppc_exceptions)
+		gr->func->init_ppc_exceptions(gr);
 
 	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
 		nvkm_wr32(device, GPC_UNIT(gpc, 0x0420), 0xc0000000);
@@ -2000,19 +2188,20 @@ gf100_gr_init(struct gf100_gr *gr)
 		for (tpc = 0; tpc < gr->tpc_nr[gpc]; tpc++) {
 			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x508), 0xffffffff);
 			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x50c), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x224), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x48c), 0xc0000000);
+			if (gr->func->init_tex_hww_esr)
+				gr->func->init_tex_hww_esr(gr, gpc, tpc);
 			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x084), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x001ffffe);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x0000000f);
+			if (gr->func->init_504430)
+				gr->func->init_504430(gr, gpc, tpc);
+			gr->func->init_shader_exceptions(gr, gpc, tpc);
 		}
 		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c90), 0xffffffff);
 		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c94), 0xffffffff);
 	}
 
 	for (rop = 0; rop < gr->rop_nr; rop++) {
-		nvkm_wr32(device, ROP_UNIT(rop, 0x144), 0xc0000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x070), 0xc0000000);
+		nvkm_wr32(device, ROP_UNIT(rop, 0x144), 0x40000000);
+		nvkm_wr32(device, ROP_UNIT(rop, 0x070), 0x40000000);
 		nvkm_wr32(device, ROP_UNIT(rop, 0x204), 0xffffffff);
 		nvkm_wr32(device, ROP_UNIT(rop, 0x208), 0xffffffff);
 	}
@@ -2024,10 +2213,14 @@ gf100_gr_init(struct gf100_gr *gr)
 	nvkm_wr32(device, 0x40011c, 0xffffffff);
 	nvkm_wr32(device, 0x400134, 0xffffffff);
 
-	nvkm_wr32(device, 0x400054, 0x34ce3464);
+	if (gr->func->init_400054)
+		gr->func->init_400054(gr);
 
 	gf100_gr_zbc_init(gr);
 
+	if (gr->func->init_4188a4)
+		gr->func->init_4188a4(gr);
+
 	return gf100_gr_init_ctxctl(gr);
 }
 
@@ -2053,13 +2246,27 @@ gf100_gr_gpccs_ucode = {
 
 static const struct gf100_gr_func
 gf100_gr = {
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
 	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gf100_gr_init_vsc_stream_master,
+	.init_zcull = gf100_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_40601c = gf100_gr_init_40601c,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gf100_gr_init_419eb4,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gf100_gr_pack_mmio,
 	.fecs.ucode = &gf100_gr_fecs_ucode,
 	.gpccs.ucode = &gf100_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.grctx = &gf100_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, FERMI_MEMORY_TO_MEMORY_FORMAT_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index c8ec3fd97155..dc46cf0131db 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -72,6 +72,12 @@ struct gf100_gr_zbc_depth {
 	u32 l2;
 };
 
+struct gf100_gr_zbc_stencil {
+	u32 format;
+	u32 ds;
+	u32 l2;
+};
+
 struct gf100_gr {
 	const struct gf100_gr_func *func;
 	struct nvkm_gr base;
@@ -95,21 +101,33 @@ struct gf100_gr {
 
 	struct gf100_gr_zbc_color zbc_color[NVKM_LTC_MAX_ZBC_CNT];
 	struct gf100_gr_zbc_depth zbc_depth[NVKM_LTC_MAX_ZBC_CNT];
+	struct gf100_gr_zbc_stencil zbc_stencil[NVKM_LTC_MAX_ZBC_CNT];
 
 	u8 rop_nr;
 	u8 gpc_nr;
 	u8 tpc_nr[GPC_MAX];
+	u8 tpc_max;
 	u8 tpc_total;
 	u8 ppc_nr[GPC_MAX];
 	u8 ppc_mask[GPC_MAX];
+	u8 ppc_tpc_mask[GPC_MAX][4];
 	u8 ppc_tpc_nr[GPC_MAX][4];
+	u8 ppc_tpc_min;
+	u8 ppc_tpc_max;
+
+	u8 screen_tile_row_offset;
+	u8 tile[TPC_MAX];
+
+	struct {
+		u8 gpc;
+		u8 tpc;
+	} sm[TPC_MAX];
+	u8 sm_nr;
 
 	struct gf100_gr_data mmio_data[4];
 	struct gf100_gr_mmio mmio_list[4096/8];
 	u32  size;
 	u32 *data;
-
-	u8 screen_tile_row_offset;
 };
 
 int gf100_gr_ctor(const struct gf100_gr_func *, struct nvkm_device *,
@@ -118,14 +136,43 @@ int gf100_gr_new_(const struct gf100_gr_func *, struct nvkm_device *,
 		  int, struct nvkm_gr **);
 void *gf100_gr_dtor(struct nvkm_gr *);
 
+struct gf100_gr_func_zbc {
+	void (*clear_color)(struct gf100_gr *, int zbc);
+	void (*clear_depth)(struct gf100_gr *, int zbc);
+	int (*stencil_get)(struct gf100_gr *, int format,
+			   const u32 ds, const u32 l2);
+	void (*clear_stencil)(struct gf100_gr *, int zbc);
+};
+
 struct gf100_gr_func {
 	void (*dtor)(struct gf100_gr *);
+	void (*oneinit_tiles)(struct gf100_gr *);
+	void (*oneinit_sm_id)(struct gf100_gr *);
 	int (*init)(struct gf100_gr *);
+	void (*init_419bd8)(struct gf100_gr *);
 	void (*init_gpc_mmu)(struct gf100_gr *);
+	void (*init_r405a14)(struct gf100_gr *);
+	void (*init_bios)(struct gf100_gr *);
+	void (*init_vsc_stream_master)(struct gf100_gr *);
+	void (*init_zcull)(struct gf100_gr *);
+	void (*init_num_active_ltcs)(struct gf100_gr *);
 	void (*init_rop_active_fbps)(struct gf100_gr *);
-	void (*init_ppc_exceptions)(struct gf100_gr *);
+	void (*init_bios_2)(struct gf100_gr *);
 	void (*init_swdx_pes_mask)(struct gf100_gr *);
-	void (*init_num_active_ltcs)(struct gf100_gr *);
+	void (*init_fecs_exceptions)(struct gf100_gr *);
+	void (*init_ds_hww_esr_2)(struct gf100_gr *);
+	void (*init_40601c)(struct gf100_gr *);
+	void (*init_sked_hww_esr)(struct gf100_gr *);
+	void (*init_419cc0)(struct gf100_gr *);
+	void (*init_419eb4)(struct gf100_gr *);
+	void (*init_419c9c)(struct gf100_gr *);
+	void (*init_ppc_exceptions)(struct gf100_gr *);
+	void (*init_tex_hww_esr)(struct gf100_gr *, int gpc, int tpc);
+	void (*init_504430)(struct gf100_gr *, int gpc, int tpc);
+	void (*init_shader_exceptions)(struct gf100_gr *, int gpc, int tpc);
+	void (*init_400054)(struct gf100_gr *);
+	void (*init_4188a4)(struct gf100_gr *);
+	void (*trap_mp)(struct gf100_gr *, int gpc, int tpc);
 	void (*set_hww_esr_report_mask)(struct gf100_gr *);
 	const struct gf100_gr_pack *mmio;
 	struct {
@@ -135,26 +182,60 @@ struct gf100_gr_func {
 		struct gf100_gr_ucode *ucode;
 	} gpccs;
 	int (*rops)(struct gf100_gr *);
+	int gpc_nr;
+	int tpc_nr;
 	int ppc_nr;
 	const struct gf100_grctx_func *grctx;
 	const struct nvkm_therm_clkgate_pack *clkgate_pack;
+	const struct gf100_gr_func_zbc *zbc;
 	struct nvkm_sclass sclass[];
 };
 
-int gf100_gr_init(struct gf100_gr *);
 int gf100_gr_rops(struct gf100_gr *);
-
-int gk104_gr_init(struct gf100_gr *);
+void gf100_gr_oneinit_tiles(struct gf100_gr *);
+void gf100_gr_oneinit_sm_id(struct gf100_gr *);
+int gf100_gr_init(struct gf100_gr *);
+void gf100_gr_init_vsc_stream_master(struct gf100_gr *);
+void gf100_gr_init_zcull(struct gf100_gr *);
+void gf100_gr_init_num_active_ltcs(struct gf100_gr *);
+void gf100_gr_init_fecs_exceptions(struct gf100_gr *);
+void gf100_gr_init_40601c(struct gf100_gr *);
+void gf100_gr_init_419cc0(struct gf100_gr *);
+void gf100_gr_init_419eb4(struct gf100_gr *);
+void gf100_gr_init_tex_hww_esr(struct gf100_gr *, int, int);
+void gf100_gr_init_shader_exceptions(struct gf100_gr *, int, int);
+void gf100_gr_init_400054(struct gf100_gr *);
+extern const struct gf100_gr_func_zbc gf100_gr_zbc;
+
+void gf117_gr_init_zcull(struct gf100_gr *);
+
+void gk104_gr_init_vsc_stream_master(struct gf100_gr *);
 void gk104_gr_init_rop_active_fbps(struct gf100_gr *);
 void gk104_gr_init_ppc_exceptions(struct gf100_gr *);
+void gk104_gr_init_sked_hww_esr(struct gf100_gr *);
+
+void gk110_gr_init_419eb4(struct gf100_gr *);
+
+void gm107_gr_init_504430(struct gf100_gr *, int, int);
+void gm107_gr_init_shader_exceptions(struct gf100_gr *, int, int);
+void gm107_gr_init_400054(struct gf100_gr *);
 
 int gk20a_gr_init(struct gf100_gr *);
 
-int gm200_gr_init(struct gf100_gr *);
+void gm200_gr_oneinit_tiles(struct gf100_gr *);
+void gm200_gr_oneinit_sm_id(struct gf100_gr *);
 int gm200_gr_rops(struct gf100_gr *);
+void gm200_gr_init_num_active_ltcs(struct gf100_gr *);
+void gm200_gr_init_ds_hww_esr_2(struct gf100_gr *);
 
-int gp100_gr_init(struct gf100_gr *);
 void gp100_gr_init_rop_active_fbps(struct gf100_gr *);
+void gp100_gr_init_fecs_exceptions(struct gf100_gr *);
+void gp100_gr_init_shader_exceptions(struct gf100_gr *, int, int);
+void gp100_gr_zbc_clear_color(struct gf100_gr *, int);
+void gp100_gr_zbc_clear_depth(struct gf100_gr *, int);
+
+void gp102_gr_init_swdx_pes_mask(struct gf100_gr *);
+extern const struct gf100_gr_func_zbc gp102_gr_zbc;
 
 #define gf100_gr_chan(p) container_of((p), struct gf100_gr_chan, object)
 #include <core/object.h>
@@ -187,7 +268,7 @@ extern const struct nvkm_object_func gf100_fermi;
 struct gf100_gr_init {
 	u32 addr;
 	u8  count;
-	u8  pitch;
+	u32 pitch;
 	u32 data;
 };
 
@@ -257,6 +338,9 @@ extern const struct gf100_gr_init gf100_gr_init_be_0[];
 extern const struct gf100_gr_init gf100_gr_init_fe_1[];
 extern const struct gf100_gr_init gf100_gr_init_pe_1[];
 void gf100_gr_init_gpc_mmu(struct gf100_gr *);
+void gf100_gr_trap_mp(struct gf100_gr *, int, int);
+extern const struct nvkm_bitfield gf100_mp_global_error[];
+extern const struct nvkm_enum gf100_mp_warp_error[];
 
 extern const struct gf100_gr_init gf104_gr_init_ds_0[];
 extern const struct gf100_gr_init gf104_gr_init_tex_0[];
@@ -279,6 +363,7 @@ extern const struct gf100_gr_init gf117_gr_init_wwdx_0[];
 extern const struct gf100_gr_init gf117_gr_init_cbm_0[];
 
 extern const struct gf100_gr_init gk104_gr_init_main_0[];
+extern const struct gf100_gr_init gk104_gr_init_gpc_unk_2[];
 extern const struct gf100_gr_init gk104_gr_init_tpccs_0[];
 extern const struct gf100_gr_init gk104_gr_init_pe_0[];
 extern const struct gf100_gr_init gk104_gr_init_be_0[];
@@ -306,8 +391,4 @@ extern const struct gf100_gr_init gm107_gr_init_cbm_0[];
 void gm107_gr_init_bios(struct gf100_gr *);
 
 void gm200_gr_init_gpc_mmu(struct gf100_gr *);
-
-void gp100_gr_init_num_active_ltcs(struct gf100_gr *gr);
-
-void gp102_gr_init_swdx_pes_mask(struct gf100_gr *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c
index ec0f11983b23..42c2fd9fc04e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c
@@ -114,13 +114,27 @@ gf104_gr_pack_mmio[] = {
 
 static const struct gf100_gr_func
 gf104_gr = {
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
 	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gf100_gr_init_vsc_stream_master,
+	.init_zcull = gf100_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_40601c = gf100_gr_init_40601c,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gf100_gr_init_419eb4,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gf104_gr_pack_mmio,
 	.fecs.ucode = &gf100_gr_fecs_ucode,
 	.gpccs.ucode = &gf100_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.grctx = &gf104_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, FERMI_MEMORY_TO_MEMORY_FORMAT_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c
index cc152eb74123..4731a460adc7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c
@@ -103,15 +103,36 @@ gf108_gr_pack_mmio[] = {
  * PGRAPH engine/subdev functions
  ******************************************************************************/
 
+static void
+gf108_gr_init_r405a14(struct gf100_gr *gr)
+{
+	nvkm_wr32(gr->base.engine.subdev.device, 0x405a14, 0x80000000);
+}
+
 static const struct gf100_gr_func
 gf108_gr = {
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
 	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_r405a14 = gf108_gr_init_r405a14,
+	.init_vsc_stream_master = gf100_gr_init_vsc_stream_master,
+	.init_zcull = gf100_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_40601c = gf100_gr_init_40601c,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gf100_gr_init_419eb4,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gf108_gr_pack_mmio,
 	.fecs.ucode = &gf100_gr_fecs_ucode,
 	.gpccs.ucode = &gf100_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.grctx = &gf108_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, FERMI_MEMORY_TO_MEMORY_FORMAT_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c
index 10d2d73ca8c3..cdf759c8cd7f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c
@@ -86,13 +86,27 @@ gf110_gr_pack_mmio[] = {
 
 static const struct gf100_gr_func
 gf110_gr = {
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
 	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gf100_gr_init_vsc_stream_master,
+	.init_zcull = gf100_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_40601c = gf100_gr_init_40601c,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gf100_gr_init_419eb4,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gf110_gr_pack_mmio,
 	.fecs.ucode = &gf100_gr_fecs_ucode,
 	.gpccs.ucode = &gf100_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.grctx = &gf110_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, FERMI_MEMORY_TO_MEMORY_FORMAT_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c
index ac09a07c4150..a4158f84c649 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c
@@ -120,16 +120,58 @@ gf117_gr_gpccs_ucode = {
 	.data.size = sizeof(gf117_grgpc_data),
 };
 
+void
+gf117_gr_init_zcull(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
+	const u8 tile_nr = ALIGN(gr->tpc_total, 32);
+	u8 bank[GPC_MAX] = {}, gpc, i, j;
+	u32 data;
+
+	for (i = 0; i < tile_nr; i += 8) {
+		for (data = 0, j = 0; j < 8 && i + j < gr->tpc_total; j++) {
+			data |= bank[gr->tile[i + j]] << (j * 4);
+			bank[gr->tile[i + j]]++;
+		}
+		nvkm_wr32(device, GPC_BCAST(0x0980 + ((i / 8) * 4)), data);
+	}
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
+			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0910), 0x00040000 |
+							 gr->tpc_total);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
+	}
+
+	nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
+}
+
 static const struct gf100_gr_func
 gf117_gr = {
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
 	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gf100_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_40601c = gf100_gr_init_40601c,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gf100_gr_init_419eb4,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gf117_gr_pack_mmio,
 	.fecs.ucode = &gf117_gr_fecs_ucode,
 	.gpccs.ucode = &gf117_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.ppc_nr = 1,
 	.grctx = &gf117_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, FERMI_MEMORY_TO_MEMORY_FORMAT_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c
index 7f449ec6f760..4197844870b3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c
@@ -177,13 +177,27 @@ gf119_gr_pack_mmio[] = {
 
 static const struct gf100_gr_func
 gf119_gr = {
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
 	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gf100_gr_init_vsc_stream_master,
+	.init_zcull = gf100_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_40601c = gf100_gr_init_40601c,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gf100_gr_init_419eb4,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gf119_gr_pack_mmio,
 	.fecs.ucode = &gf100_gr_fecs_ucode,
 	.gpccs.ucode = &gf100_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.grctx = &gf119_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, FERMI_MEMORY_TO_MEMORY_FORMAT_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
index 1b52fcb2c49a..477fee3e3715 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
@@ -83,6 +83,12 @@ gk104_gr_init_gpc_unk_1[] = {
 };
 
 const struct gf100_gr_init
+gk104_gr_init_gpc_unk_2[] = {
+	{ 0x418884,   1, 0x04, 0x00000000 },
+	{}
+};
+
+const struct gf100_gr_init
 gk104_gr_init_tpccs_0[] = {
 	{ 0x419d0c,   1, 0x04, 0x00000000 },
 	{ 0x419d10,   1, 0x04, 0x00000014 },
@@ -160,6 +166,7 @@ gk104_gr_pack_mmio[] = {
 	{ gf119_gr_init_gpm_0 },
 	{ gk104_gr_init_gpc_unk_1 },
 	{ gf100_gr_init_gcc_0 },
+	{ gk104_gr_init_gpc_unk_2 },
 	{ gk104_gr_init_tpccs_0 },
 	{ gf119_gr_init_tex_0 },
 	{ gk104_gr_init_pe_0 },
@@ -381,6 +388,21 @@ gk104_clkgate_pack[] = {
  ******************************************************************************/
 
 void
+gk104_gr_init_sked_hww_esr(struct gf100_gr *gr)
+{
+	nvkm_wr32(gr->base.engine.subdev.device, 0x407020, 0x40000000);
+}
+
+static void
+gk104_gr_init_fecs_exceptions(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, 0x409ffc, 0x00000000);
+	nvkm_wr32(device, 0x409c14, 0x00003e3e);
+	nvkm_wr32(device, 0x409c24, 0x000f0001);
+}
+
+void
 gk104_gr_init_rop_active_fbps(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -404,112 +426,11 @@ gk104_gr_init_ppc_exceptions(struct gf100_gr *gr)
 	}
 }
 
-int
-gk104_gr_init(struct gf100_gr *gr)
+void
+gk104_gr_init_vsc_stream_master(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
-	u32 data[TPC_MAX / 8] = {};
-	u8  tpcnr[GPC_MAX];
-	int gpc, tpc, rop;
-	int i;
-
-	gr->func->init_gpc_mmu(gr);
-
-	gf100_gr_mmio(gr, gr->func->mmio);
-	if (gr->func->clkgate_pack)
-		nvkm_therm_clkgate_init(gr->base.engine.subdev.device->therm,
-					gr->func->clkgate_pack);
-
 	nvkm_wr32(device, GPC_UNIT(0, 0x3018), 0x00000001);
-
-	memset(data, 0x00, sizeof(data));
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-	for (i = 0, gpc = -1; i < gr->tpc_total; i++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
-
-		data[i / 8] |= tpc << ((i % 8) * 4);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x0980), data[0]);
-	nvkm_wr32(device, GPC_BCAST(0x0984), data[1]);
-	nvkm_wr32(device, GPC_BCAST(0x0988), data[2]);
-	nvkm_wr32(device, GPC_BCAST(0x098c), data[3]);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
-			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0910), 0x00040000 |
-							 gr->tpc_total);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
-	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
-
-	gr->func->init_rop_active_fbps(gr);
-
-	nvkm_wr32(device, 0x400500, 0x00010001);
-
-	nvkm_wr32(device, 0x400100, 0xffffffff);
-	nvkm_wr32(device, 0x40013c, 0xffffffff);
-
-	nvkm_wr32(device, 0x409ffc, 0x00000000);
-	nvkm_wr32(device, 0x409c14, 0x00003e3e);
-	nvkm_wr32(device, 0x409c24, 0x000f0001);
-	nvkm_wr32(device, 0x404000, 0xc0000000);
-	nvkm_wr32(device, 0x404600, 0xc0000000);
-	nvkm_wr32(device, 0x408030, 0xc0000000);
-	nvkm_wr32(device, 0x404490, 0xc0000000);
-	nvkm_wr32(device, 0x406018, 0xc0000000);
-	nvkm_wr32(device, 0x407020, 0x40000000);
-	nvkm_wr32(device, 0x405840, 0xc0000000);
-	nvkm_wr32(device, 0x405844, 0x00ffffff);
-	nvkm_mask(device, 0x419cc0, 0x00000008, 0x00000008);
-	nvkm_mask(device, 0x419eb4, 0x00001000, 0x00001000);
-
-	gr->func->init_ppc_exceptions(gr);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0420), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0900), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x1028), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0824), 0xc0000000);
-		for (tpc = 0; tpc < gr->tpc_nr[gpc]; tpc++) {
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x508), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x50c), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x224), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x48c), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x084), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x001ffffe);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x0000000f);
-		}
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c90), 0xffffffff);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c94), 0xffffffff);
-	}
-
-	for (rop = 0; rop < gr->rop_nr; rop++) {
-		nvkm_wr32(device, ROP_UNIT(rop, 0x144), 0xc0000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x070), 0xc0000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x204), 0xffffffff);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x208), 0xffffffff);
-	}
-
-	nvkm_wr32(device, 0x400108, 0xffffffff);
-	nvkm_wr32(device, 0x400138, 0xffffffff);
-	nvkm_wr32(device, 0x400118, 0xffffffff);
-	nvkm_wr32(device, 0x400130, 0xffffffff);
-	nvkm_wr32(device, 0x40011c, 0xffffffff);
-	nvkm_wr32(device, 0x400134, 0xffffffff);
-
-	nvkm_wr32(device, 0x400054, 0x34ce3464);
-
-	gf100_gr_zbc_init(gr);
-
-	return gf100_gr_init_ctxctl(gr);
 }
 
 #include "fuc/hubgk104.fuc3.h"
@@ -534,10 +455,23 @@ gk104_gr_gpccs_ucode = {
 
 static const struct gf100_gr_func
 gk104_gr = {
-	.init = gk104_gr_init,
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gk104_gr_init_rop_active_fbps,
+	.init_fecs_exceptions = gk104_gr_init_fecs_exceptions,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gf100_gr_init_419eb4,
 	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gk104_gr_pack_mmio,
 	.fecs.ucode = &gk104_gr_fecs_ucode,
 	.gpccs.ucode = &gk104_gr_gpccs_ucode,
@@ -545,6 +479,7 @@ gk104_gr = {
 	.ppc_nr = 1,
 	.grctx = &gk104_grctx,
 	.clkgate_pack = gk104_clkgate_pack,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
index 4da916a9fc73..7cd628c84e07 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
@@ -143,6 +143,7 @@ gk110_gr_pack_mmio[] = {
 	{ gf119_gr_init_gpm_0 },
 	{ gk110_gr_init_gpc_unk_1 },
 	{ gf100_gr_init_gcc_0 },
+	{ gk104_gr_init_gpc_unk_2 },
 	{ gk104_gr_init_tpccs_0 },
 	{ gk110_gr_init_tex_0 },
 	{ gk104_gr_init_pe_0 },
@@ -334,12 +335,39 @@ gk110_gr_gpccs_ucode = {
 	.data.size = sizeof(gk110_grgpc_data),
 };
 
+void
+gk110_gr_init_419eb4(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x419eb4, 0x00001000, 0x00001000);
+	nvkm_mask(device, 0x419eb4, 0x00002000, 0x00002000);
+	nvkm_mask(device, 0x419eb4, 0x00004000, 0x00004000);
+	nvkm_mask(device, 0x419eb4, 0x00008000, 0x00008000);
+	nvkm_mask(device, 0x419eb4, 0x00001000, 0x00000000);
+	nvkm_mask(device, 0x419eb4, 0x00002000, 0x00000000);
+	nvkm_mask(device, 0x419eb4, 0x00004000, 0x00000000);
+	nvkm_mask(device, 0x419eb4, 0x00008000, 0x00000000);
+}
+
 static const struct gf100_gr_func
 gk110_gr = {
-	.init = gk104_gr_init,
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gk104_gr_init_rop_active_fbps,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gk110_gr_init_419eb4,
 	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gk110_gr_pack_mmio,
 	.fecs.ucode = &gk110_gr_fecs_ucode,
 	.gpccs.ucode = &gk110_gr_gpccs_ucode,
@@ -347,6 +375,7 @@ gk110_gr = {
 	.ppc_nr = 2,
 	.grctx = &gk110_grctx,
 	.clkgate_pack = gk110_clkgate_pack,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c
index 1912c0bfd7ee..a38faa215635 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c
@@ -82,6 +82,7 @@ gk110b_gr_pack_mmio[] = {
 	{ gf119_gr_init_gpm_0 },
 	{ gk110_gr_init_gpc_unk_1 },
 	{ gf100_gr_init_gcc_0 },
+	{ gk104_gr_init_gpc_unk_2 },
 	{ gk104_gr_init_tpccs_0 },
 	{ gk110_gr_init_tex_0 },
 	{ gk104_gr_init_pe_0 },
@@ -102,16 +103,30 @@ gk110b_gr_pack_mmio[] = {
 
 static const struct gf100_gr_func
 gk110b_gr = {
-	.init = gk104_gr_init,
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gk104_gr_init_rop_active_fbps,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419eb4 = gk110_gr_init_419eb4,
 	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gk110b_gr_pack_mmio,
 	.fecs.ucode = &gk110_gr_fecs_ucode,
 	.gpccs.ucode = &gk110_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.ppc_nr = 2,
 	.grctx = &gk110b_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c
index 1fc258163f25..58456660e603 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c
@@ -121,6 +121,7 @@ gk208_gr_pack_mmio[] = {
 	{ gf119_gr_init_gpm_0 },
 	{ gk110_gr_init_gpc_unk_1 },
 	{ gf100_gr_init_gcc_0 },
+	{ gk104_gr_init_gpc_unk_2 },
 	{ gk104_gr_init_tpccs_0 },
 	{ gk208_gr_init_tex_0 },
 	{ gk104_gr_init_pe_0 },
@@ -161,16 +162,29 @@ gk208_gr_gpccs_ucode = {
 
 static const struct gf100_gr_func
 gk208_gr = {
-	.init = gk104_gr_init,
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gf100_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gk104_gr_init_rop_active_fbps,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
 	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_shader_exceptions = gf100_gr_init_shader_exceptions,
+	.init_400054 = gf100_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gk208_gr_pack_mmio,
 	.fecs.ucode = &gk208_gr_fecs_ucode,
 	.gpccs.ucode = &gk208_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.ppc_nr = 1,
 	.grctx = &gk208_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
index de8b806b88fd..500cb08dd608 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
@@ -219,11 +219,7 @@ int
 gk20a_gr_init(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
-	u32 data[TPC_MAX / 8] = {};
-	u8  tpcnr[GPC_MAX];
-	int gpc, tpc;
-	int ret, i;
+	int ret;
 
 	/* Clear SCC RAM */
 	nvkm_wr32(device, 0x40802c, 0x1);
@@ -246,31 +242,7 @@ gk20a_gr_init(struct gf100_gr *gr)
 	nvkm_mask(device, 0x503018, 0x1, 0x1);
 
 	/* Zcull init */
-	memset(data, 0x00, sizeof(data));
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-	for (i = 0, gpc = -1; i < gr->tpc_total; i++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
-
-		data[i / 8] |= tpc << ((i % 8) * 4);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x0980), data[0]);
-	nvkm_wr32(device, GPC_BCAST(0x0984), data[1]);
-	nvkm_wr32(device, GPC_BCAST(0x0988), data[2]);
-	nvkm_wr32(device, GPC_BCAST(0x098c), data[3]);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
-			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0910), 0x00040000 |
-			  gr->tpc_total);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
+	gr->func->init_zcull(gr);
 
 	gr->func->init_rop_active_fbps(gr);
 
@@ -310,12 +282,17 @@ gk20a_gr_init(struct gf100_gr *gr)
 
 static const struct gf100_gr_func
 gk20a_gr = {
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
 	.init = gk20a_gr_init,
+	.init_zcull = gf117_gr_init_zcull,
 	.init_rop_active_fbps = gk104_gr_init_rop_active_fbps,
+	.trap_mp = gf100_gr_trap_mp,
 	.set_hww_esr_report_mask = gk20a_gr_set_hww_esr_report_mask,
 	.rops = gf100_gr_rops,
 	.ppc_nr = 1,
 	.grctx = &gk20a_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm107.c
index 2c67fac576d1..92e31d397207 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm107.c
@@ -25,6 +25,8 @@
 #include "ctxgf100.h"
 
 #include <subdev/bios.h>
+#include <subdev/bios/bit.h>
+#include <subdev/bios/init.h>
 #include <subdev/bios/P0260.h>
 #include <subdev/fb.h>
 
@@ -36,6 +38,10 @@
 
 static const struct gf100_gr_init
 gm107_gr_init_main_0[] = {
+	{ 0x40880c,   1, 0x04, 0x00000000 },
+	{ 0x408910,   1, 0x04, 0x00000000 },
+	{ 0x408984,   1, 0x04, 0x00000000 },
+	{ 0x41a8a0,   1, 0x04, 0x00000000 },
 	{ 0x400080,   1, 0x04, 0x003003c2 },
 	{ 0x400088,   1, 0x04, 0x0001bfe7 },
 	{ 0x40008c,   1, 0x04, 0x00060000 },
@@ -210,14 +216,13 @@ gm107_gr_init_cbm_0[] = {
 static const struct gf100_gr_init
 gm107_gr_init_be_0[] = {
 	{ 0x408890,   1, 0x04, 0x000000ff },
-	{ 0x40880c,   1, 0x04, 0x00000000 },
 	{ 0x408850,   1, 0x04, 0x00000004 },
 	{ 0x408878,   1, 0x04, 0x00c81603 },
 	{ 0x40887c,   1, 0x04, 0x80543432 },
 	{ 0x408880,   1, 0x04, 0x0010581e },
 	{ 0x408884,   1, 0x04, 0x00001205 },
 	{ 0x408974,   1, 0x04, 0x000000ff },
-	{ 0x408910,   9, 0x04, 0x00000000 },
+	{ 0x408914,   8, 0x04, 0x00000000 },
 	{ 0x408950,   1, 0x04, 0x00000000 },
 	{ 0x408954,   1, 0x04, 0x0000ffff },
 	{ 0x408958,   1, 0x04, 0x00000034 },
@@ -227,7 +232,6 @@ gm107_gr_init_be_0[] = {
 	{ 0x408968,   1, 0x04, 0x02808833 },
 	{ 0x40896c,   1, 0x04, 0x01f02438 },
 	{ 0x408970,   1, 0x04, 0x00012c00 },
-	{ 0x408984,   1, 0x04, 0x00000000 },
 	{ 0x408988,   1, 0x04, 0x08040201 },
 	{ 0x40898c,   1, 0x04, 0x80402010 },
 	{}
@@ -260,6 +264,7 @@ gm107_gr_pack_mmio[] = {
 	{ gf100_gr_init_gpm_0 },
 	{ gm107_gr_init_gpc_unk_1 },
 	{ gf100_gr_init_gcc_0 },
+	{ gk104_gr_init_gpc_unk_2 },
 	{ gm107_gr_init_tpccs_0 },
 	{ gm107_gr_init_tex_0 },
 	{ gm107_gr_init_pe_0 },
@@ -280,6 +285,52 @@ gm107_gr_pack_mmio[] = {
  ******************************************************************************/
 
 void
+gm107_gr_init_400054(struct gf100_gr *gr)
+{
+	nvkm_wr32(gr->base.engine.subdev.device, 0x400054, 0x2c350f63);
+}
+
+void
+gm107_gr_init_shader_exceptions(struct gf100_gr *gr, int gpc, int tpc)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x00dffffe);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x00000005);
+}
+
+void
+gm107_gr_init_504430(struct gf100_gr *gr, int gpc, int tpc)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x430), 0xc0000000);
+}
+
+static void
+gm107_gr_init_bios_2(struct gf100_gr *gr)
+{
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_bios *bios = device->bios;
+	struct bit_entry bit_P;
+	if (!bit_entry(bios, 'P', &bit_P) &&
+	    bit_P.version == 2 && bit_P.length >= 0x2c) {
+		u32 data = nvbios_rd32(bios, bit_P.offset + 0x28);
+		if (data) {
+			u8 ver = nvbios_rd08(bios, data + 0x00);
+			u8 hdr = nvbios_rd08(bios, data + 0x01);
+			if (ver == 0x20 && hdr >= 8) {
+				data = nvbios_rd32(bios, data + 0x04);
+				if (data) {
+					u32 save = nvkm_rd32(device, 0x619444);
+					nvbios_init(subdev, data);
+					nvkm_wr32(device, 0x619444, save);
+				}
+			}
+		}
+	}
+}
+
+void
 gm107_gr_init_bios(struct gf100_gr *gr)
 {
 	static const struct {
@@ -308,115 +359,17 @@ gm107_gr_init_bios(struct gf100_gr *gr)
 	}
 }
 
-static int
-gm107_gr_init(struct gf100_gr *gr)
+static void
+gm107_gr_init_gpc_mmu(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
 	struct nvkm_fb *fb = device->fb;
-	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
-	u32 data[TPC_MAX / 8] = {};
-	u8  tpcnr[GPC_MAX];
-	int gpc, tpc, rop;
-	int i;
 
 	nvkm_wr32(device, GPC_BCAST(0x0880), 0x00000000);
 	nvkm_wr32(device, GPC_BCAST(0x0890), 0x00000000);
 	nvkm_wr32(device, GPC_BCAST(0x0894), 0x00000000);
 	nvkm_wr32(device, GPC_BCAST(0x08b4), nvkm_memory_addr(fb->mmu_wr) >> 8);
 	nvkm_wr32(device, GPC_BCAST(0x08b8), nvkm_memory_addr(fb->mmu_rd) >> 8);
-
-	gf100_gr_mmio(gr, gr->func->mmio);
-
-	gm107_gr_init_bios(gr);
-
-	nvkm_wr32(device, GPC_UNIT(0, 0x3018), 0x00000001);
-
-	memset(data, 0x00, sizeof(data));
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-	for (i = 0, gpc = -1; i < gr->tpc_total; i++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
-
-		data[i / 8] |= tpc << ((i % 8) * 4);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x0980), data[0]);
-	nvkm_wr32(device, GPC_BCAST(0x0984), data[1]);
-	nvkm_wr32(device, GPC_BCAST(0x0988), data[2]);
-	nvkm_wr32(device, GPC_BCAST(0x098c), data[3]);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
-			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0910), 0x00040000 |
-							 gr->tpc_total);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
-	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
-
-	gr->func->init_rop_active_fbps(gr);
-
-	nvkm_wr32(device, 0x400500, 0x00010001);
-
-	nvkm_wr32(device, 0x400100, 0xffffffff);
-	nvkm_wr32(device, 0x40013c, 0xffffffff);
-	nvkm_wr32(device, 0x400124, 0x00000002);
-	nvkm_wr32(device, 0x409c24, 0x000e0000);
-
-	nvkm_wr32(device, 0x404000, 0xc0000000);
-	nvkm_wr32(device, 0x404600, 0xc0000000);
-	nvkm_wr32(device, 0x408030, 0xc0000000);
-	nvkm_wr32(device, 0x404490, 0xc0000000);
-	nvkm_wr32(device, 0x406018, 0xc0000000);
-	nvkm_wr32(device, 0x407020, 0x40000000);
-	nvkm_wr32(device, 0x405840, 0xc0000000);
-	nvkm_wr32(device, 0x405844, 0x00ffffff);
-	nvkm_mask(device, 0x419cc0, 0x00000008, 0x00000008);
-
-	gr->func->init_ppc_exceptions(gr);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0420), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0900), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x1028), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0824), 0xc0000000);
-		for (tpc = 0; tpc < gr->tpc_nr[gpc]; tpc++) {
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x508), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x50c), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x224), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x48c), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x084), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x430), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x00dffffe);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x00000005);
-		}
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c90), 0xffffffff);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c94), 0xffffffff);
-	}
-
-	for (rop = 0; rop < gr->rop_nr; rop++) {
-		nvkm_wr32(device, ROP_UNIT(rop, 0x144), 0x40000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x070), 0x40000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x204), 0xffffffff);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x208), 0xffffffff);
-	}
-
-	nvkm_wr32(device, 0x400108, 0xffffffff);
-	nvkm_wr32(device, 0x400138, 0xffffffff);
-	nvkm_wr32(device, 0x400118, 0xffffffff);
-	nvkm_wr32(device, 0x400130, 0xffffffff);
-	nvkm_wr32(device, 0x40011c, 0xffffffff);
-	nvkm_wr32(device, 0x400134, 0xffffffff);
-
-	nvkm_wr32(device, 0x400054, 0x2c350f63);
-
-	gf100_gr_zbc_init(gr);
-
-	return gf100_gr_init_ctxctl(gr);
 }
 
 #include "fuc/hubgm107.fuc5.h"
@@ -441,15 +394,32 @@ gm107_gr_gpccs_ucode = {
 
 static const struct gf100_gr_func
 gm107_gr = {
-	.init = gm107_gr_init,
+	.oneinit_tiles = gf100_gr_oneinit_tiles,
+	.oneinit_sm_id = gf100_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
+	.init_gpc_mmu = gm107_gr_init_gpc_mmu,
+	.init_bios = gm107_gr_init_bios,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gk104_gr_init_rop_active_fbps,
+	.init_bios_2 = gm107_gr_init_bios_2,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
 	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_504430 = gm107_gr_init_504430,
+	.init_shader_exceptions = gm107_gr_init_shader_exceptions,
+	.init_400054 = gm107_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.mmio = gm107_gr_pack_mmio,
 	.fecs.ucode = &gm107_gr_fecs_ucode,
 	.gpccs.ucode = &gm107_gr_gpccs_ucode,
 	.rops = gf100_gr_rops,
 	.ppc_nr = 2,
 	.grctx = &gm107_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
index 6435f1257572..eff30662b984 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
@@ -39,6 +39,22 @@ gm200_gr_rops(struct gf100_gr *gr)
 }
 
 void
+gm200_gr_init_ds_hww_esr_2(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, 0x405848, 0xc0000000);
+	nvkm_mask(device, 0x40584c, 0x00000001, 0x00000001);
+}
+
+void
+gm200_gr_init_num_active_ltcs(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
+	nvkm_wr32(device, GPC_BCAST(0x033c), nvkm_rd32(device, 0x100804));
+}
+
+void
 gm200_gr_init_gpc_mmu(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -61,111 +77,51 @@ gm200_gr_init_rop_active_fbps(struct gf100_gr *gr)
 	nvkm_mask(device, 0x408958, 0x0000000f, fbp_count); /* crop */
 }
 
-int
-gm200_gr_init(struct gf100_gr *gr)
-{
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
-	u32 data[TPC_MAX / 8] = {};
-	u8  tpcnr[GPC_MAX];
-	int gpc, tpc, rop;
-	int i;
-
-	gr->func->init_gpc_mmu(gr);
-
-	gf100_gr_mmio(gr, gr->fuc_sw_nonctx);
-
-	gm107_gr_init_bios(gr);
-
-	nvkm_wr32(device, GPC_UNIT(0, 0x3018), 0x00000001);
-
-	memset(data, 0x00, sizeof(data));
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-	for (i = 0, gpc = -1; i < gr->tpc_total; i++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
-
-		data[i / 8] |= tpc << ((i % 8) * 4);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x0980), data[0]);
-	nvkm_wr32(device, GPC_BCAST(0x0984), data[1]);
-	nvkm_wr32(device, GPC_BCAST(0x0988), data[2]);
-	nvkm_wr32(device, GPC_BCAST(0x098c), data[3]);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
-			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0910), 0x00040000 |
-							 gr->tpc_total);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
-	}
+static u8
+gm200_gr_tile_map_6_24[] = {
+	0, 1, 2, 3, 4, 5, 3, 4, 5, 0, 1, 2, 0, 1, 2, 3, 4, 5, 3, 4, 5, 0, 1, 2,
+};
 
-	nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
-	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
-	nvkm_wr32(device, GPC_BCAST(0x033c), nvkm_rd32(device, 0x100804));
+static u8
+gm200_gr_tile_map_4_16[] = {
+	0, 1, 2, 3, 2, 3, 0, 1, 3, 0, 1, 2, 1, 2, 3, 0,
+};
 
-	gr->func->init_rop_active_fbps(gr);
+static u8
+gm200_gr_tile_map_2_8[] = {
+	0, 1, 1, 0, 0, 1, 1, 0,
+};
 
-	nvkm_wr32(device, 0x400500, 0x00010001);
-	nvkm_wr32(device, 0x400100, 0xffffffff);
-	nvkm_wr32(device, 0x40013c, 0xffffffff);
-	nvkm_wr32(device, 0x400124, 0x00000002);
-	nvkm_wr32(device, 0x409c24, 0x000e0000);
-	nvkm_wr32(device, 0x405848, 0xc0000000);
-	nvkm_wr32(device, 0x40584c, 0x00000001);
-	nvkm_wr32(device, 0x404000, 0xc0000000);
-	nvkm_wr32(device, 0x404600, 0xc0000000);
-	nvkm_wr32(device, 0x408030, 0xc0000000);
-	nvkm_wr32(device, 0x404490, 0xc0000000);
-	nvkm_wr32(device, 0x406018, 0xc0000000);
-	nvkm_wr32(device, 0x407020, 0x40000000);
-	nvkm_wr32(device, 0x405840, 0xc0000000);
-	nvkm_wr32(device, 0x405844, 0x00ffffff);
-	nvkm_mask(device, 0x419cc0, 0x00000008, 0x00000008);
-
-	gr->func->init_ppc_exceptions(gr);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0420), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0900), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x1028), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0824), 0xc0000000);
-		for (tpc = 0; tpc < gr->tpc_nr[gpc]; tpc++) {
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x508), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x50c), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x224), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x48c), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x084), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x430), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x00dffffe);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x00000005);
-		}
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c90), 0xffffffff);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c94), 0xffffffff);
-	}
+void
+gm200_gr_oneinit_sm_id(struct gf100_gr *gr)
+{
+	/*XXX: There's a different algorithm here I've not yet figured out. */
+	gf100_gr_oneinit_sm_id(gr);
+}
 
-	for (rop = 0; rop < gr->rop_nr; rop++) {
-		nvkm_wr32(device, ROP_UNIT(rop, 0x144), 0x40000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x070), 0x40000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x204), 0xffffffff);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x208), 0xffffffff);
+void
+gm200_gr_oneinit_tiles(struct gf100_gr *gr)
+{
+	/*XXX: Not sure what this is about.  The algorithm from NVGPU
+	 *     seems to work for all boards I tried from earlier (and
+	 *     later) GPUs except in these specific configurations.
+	 *
+	 *     Let's just hardcode them for now.
+	 */
+	if (gr->gpc_nr == 2 && gr->tpc_total == 8) {
+		memcpy(gr->tile, gm200_gr_tile_map_2_8, gr->tpc_total);
+		gr->screen_tile_row_offset = 1;
+	} else
+	if (gr->gpc_nr == 4 && gr->tpc_total == 16) {
+		memcpy(gr->tile, gm200_gr_tile_map_4_16, gr->tpc_total);
+		gr->screen_tile_row_offset = 4;
+	} else
+	if (gr->gpc_nr == 6 && gr->tpc_total == 24) {
+		memcpy(gr->tile, gm200_gr_tile_map_6_24, gr->tpc_total);
+		gr->screen_tile_row_offset = 5;
+	} else {
+		gf100_gr_oneinit_tiles(gr);
 	}
-
-	nvkm_wr32(device, 0x400108, 0xffffffff);
-	nvkm_wr32(device, 0x400138, 0xffffffff);
-	nvkm_wr32(device, 0x400118, 0xffffffff);
-	nvkm_wr32(device, 0x400130, 0xffffffff);
-	nvkm_wr32(device, 0x40011c, 0xffffffff);
-	nvkm_wr32(device, 0x400134, 0xffffffff);
-
-	nvkm_wr32(device, 0x400054, 0x2c350f63);
-
-	gf100_gr_zbc_init(gr);
-
-	return gf100_gr_init_ctxctl(gr);
 }
 
 int
@@ -208,13 +164,30 @@ gm200_gr_new_(const struct gf100_gr_func *func, struct nvkm_device *device,
 
 static const struct gf100_gr_func
 gm200_gr = {
-	.init = gm200_gr_init,
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gm200_gr_init_gpc_mmu,
+	.init_bios = gm107_gr_init_bios,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gm200_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gm200_gr_init_rop_active_fbps,
+	.init_fecs_exceptions = gf100_gr_init_fecs_exceptions,
+	.init_ds_hww_esr_2 = gm200_gr_init_ds_hww_esr_2,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
 	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_504430 = gm107_gr_init_504430,
+	.init_shader_exceptions = gm107_gr_init_shader_exceptions,
+	.init_400054 = gm107_gr_init_400054,
+	.trap_mp = gf100_gr_trap_mp,
 	.rops = gm200_gr_rops,
+	.tpc_nr = 4,
 	.ppc_nr = 2,
 	.grctx = &gm200_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm20b.c
index 69479af1d829..a667770ce3cb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm20b.c
@@ -64,13 +64,18 @@ gm20b_gr_set_hww_esr_report_mask(struct gf100_gr *gr)
 
 static const struct gf100_gr_func
 gm20b_gr = {
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
 	.init = gk20a_gr_init,
+	.init_zcull = gf117_gr_init_zcull,
 	.init_gpc_mmu = gm20b_gr_init_gpc_mmu,
 	.init_rop_active_fbps = gk104_gr_init_rop_active_fbps,
+	.trap_mp = gf100_gr_trap_mp,
 	.set_hww_esr_report_mask = gm20b_gr_set_hww_esr_report_mask,
 	.rops = gm200_gr_rops,
 	.ppc_nr = 1,
 	.grctx = &gm20b_grctx,
+	.zbc = &gf100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c
index 867a5f7cc5bc..9d0521ce309a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c
@@ -29,143 +29,103 @@
 /*******************************************************************************
  * PGRAPH engine/subdev functions
  ******************************************************************************/
-
 void
-gp100_gr_init_rop_active_fbps(struct gf100_gr *gr)
+gp100_gr_zbc_clear_color(struct gf100_gr *gr, int zbc)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	/*XXX: otherwise identical to gm200 aside from mask.. do everywhere? */
-	const u32 fbp_count = nvkm_rd32(device, 0x12006c) & 0x0000000f;
-	nvkm_mask(device, 0x408850, 0x0000000f, fbp_count); /* zrop */
-	nvkm_mask(device, 0x408958, 0x0000000f, fbp_count); /* crop */
+	const int znum =  zbc - 1;
+	const u32 zoff = znum * 4;
+
+	if (gr->zbc_color[zbc].format) {
+		nvkm_wr32(device, 0x418010 + zoff, gr->zbc_color[zbc].ds[0]);
+		nvkm_wr32(device, 0x41804c + zoff, gr->zbc_color[zbc].ds[1]);
+		nvkm_wr32(device, 0x418088 + zoff, gr->zbc_color[zbc].ds[2]);
+		nvkm_wr32(device, 0x4180c4 + zoff, gr->zbc_color[zbc].ds[3]);
+	}
+
+	nvkm_mask(device, 0x418100 + ((znum / 4) * 4),
+			  0x0000007f << ((znum % 4) * 7),
+			  gr->zbc_color[zbc].format << ((znum % 4) * 7));
 }
 
 void
-gp100_gr_init_num_active_ltcs(struct gf100_gr *gr)
+gp100_gr_zbc_clear_depth(struct gf100_gr *gr, int zbc)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-
-	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
-	nvkm_wr32(device, GPC_BCAST(0x033c), nvkm_rd32(device, 0x100804));
+	const int znum =  zbc - 1;
+	const u32 zoff = znum * 4;
+
+	if (gr->zbc_depth[zbc].format)
+		nvkm_wr32(device, 0x418110 + zoff, gr->zbc_depth[zbc].ds);
+	nvkm_mask(device, 0x41814c + ((znum / 4) * 4),
+			  0x0000007f << ((znum % 4) * 7),
+			  gr->zbc_depth[zbc].format << ((znum % 4) * 7));
 }
 
-int
-gp100_gr_init(struct gf100_gr *gr)
+static const struct gf100_gr_func_zbc
+gp100_gr_zbc = {
+	.clear_color = gp100_gr_zbc_clear_color,
+	.clear_depth = gp100_gr_zbc_clear_depth,
+};
+
+void
+gp100_gr_init_shader_exceptions(struct gf100_gr *gr, int gpc, int tpc)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
-	u32 data[TPC_MAX / 8] = {};
-	u8  tpcnr[GPC_MAX];
-	int gpc, tpc, rop;
-	int i;
-
-	gr->func->init_gpc_mmu(gr);
-
-	gf100_gr_mmio(gr, gr->fuc_sw_nonctx);
-
-	nvkm_wr32(device, GPC_UNIT(0, 0x3018), 0x00000001);
-
-	memset(data, 0x00, sizeof(data));
-	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
-	for (i = 0, gpc = -1; i < gr->tpc_total; i++) {
-		do {
-			gpc = (gpc + 1) % gr->gpc_nr;
-		} while (!tpcnr[gpc]);
-		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
-
-		data[i / 8] |= tpc << ((i % 8) * 4);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x0980), data[0]);
-	nvkm_wr32(device, GPC_BCAST(0x0984), data[1]);
-	nvkm_wr32(device, GPC_BCAST(0x0988), data[2]);
-	nvkm_wr32(device, GPC_BCAST(0x098c), data[3]);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
-			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0910), 0x00040000 |
-							 gr->tpc_total);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
-	}
-
-	nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
-	gr->func->init_num_active_ltcs(gr);
-
-	gr->func->init_rop_active_fbps(gr);
-	if (gr->func->init_swdx_pes_mask)
-		gr->func->init_swdx_pes_mask(gr);
-
-	nvkm_wr32(device, 0x400500, 0x00010001);
-	nvkm_wr32(device, 0x400100, 0xffffffff);
-	nvkm_wr32(device, 0x40013c, 0xffffffff);
-	nvkm_wr32(device, 0x400124, 0x00000002);
-	nvkm_wr32(device, 0x409c24, 0x000f0002);
-	nvkm_wr32(device, 0x405848, 0xc0000000);
-	nvkm_mask(device, 0x40584c, 0x00000000, 0x00000001);
-	nvkm_wr32(device, 0x404000, 0xc0000000);
-	nvkm_wr32(device, 0x404600, 0xc0000000);
-	nvkm_wr32(device, 0x408030, 0xc0000000);
-	nvkm_wr32(device, 0x404490, 0xc0000000);
-	nvkm_wr32(device, 0x406018, 0xc0000000);
-	nvkm_wr32(device, 0x407020, 0x40000000);
-	nvkm_wr32(device, 0x405840, 0xc0000000);
-	nvkm_wr32(device, 0x405844, 0x00ffffff);
-	nvkm_mask(device, 0x419cc0, 0x00000008, 0x00000008);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x00dffffe);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x00000105);
+}
 
+static void
+gp100_gr_init_419c9c(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
 	nvkm_mask(device, 0x419c9c, 0x00010000, 0x00010000);
 	nvkm_mask(device, 0x419c9c, 0x00020000, 0x00020000);
+}
 
-	gr->func->init_ppc_exceptions(gr);
-
-	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0420), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0900), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x1028), 0xc0000000);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x0824), 0xc0000000);
-		for (tpc = 0; tpc < gr->tpc_nr[gpc]; tpc++) {
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x508), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x50c), 0xffffffff);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x224), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x48c), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x084), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x430), 0xc0000000);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x00dffffe);
-			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x00000105);
-		}
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c90), 0xffffffff);
-		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c94), 0xffffffff);
-	}
-
-	for (rop = 0; rop < gr->rop_nr; rop++) {
-		nvkm_wr32(device, ROP_UNIT(rop, 0x144), 0x40000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x070), 0x40000000);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x204), 0xffffffff);
-		nvkm_wr32(device, ROP_UNIT(rop, 0x208), 0xffffffff);
-	}
-
-	nvkm_wr32(device, 0x400108, 0xffffffff);
-	nvkm_wr32(device, 0x400138, 0xffffffff);
-	nvkm_wr32(device, 0x400118, 0xffffffff);
-	nvkm_wr32(device, 0x400130, 0xffffffff);
-	nvkm_wr32(device, 0x40011c, 0xffffffff);
-	nvkm_wr32(device, 0x400134, 0xffffffff);
-
-	gf100_gr_zbc_init(gr);
+void
+gp100_gr_init_fecs_exceptions(struct gf100_gr *gr)
+{
+	nvkm_wr32(gr->base.engine.subdev.device, 0x409c24, 0x000f0002);
+}
 
-	return gf100_gr_init_ctxctl(gr);
+void
+gp100_gr_init_rop_active_fbps(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	/*XXX: otherwise identical to gm200 aside from mask.. do everywhere? */
+	const u32 fbp_count = nvkm_rd32(device, 0x12006c) & 0x0000000f;
+	nvkm_mask(device, 0x408850, 0x0000000f, fbp_count); /* zrop */
+	nvkm_mask(device, 0x408958, 0x0000000f, fbp_count); /* crop */
 }
 
 static const struct gf100_gr_func
 gp100_gr = {
-	.init = gp100_gr_init,
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gm200_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gm200_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gp100_gr_init_rop_active_fbps,
+	.init_fecs_exceptions = gp100_gr_init_fecs_exceptions,
+	.init_ds_hww_esr_2 = gm200_gr_init_ds_hww_esr_2,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_419c9c = gp100_gr_init_419c9c,
 	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
-	.init_num_active_ltcs = gp100_gr_init_num_active_ltcs,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_504430 = gm107_gr_init_504430,
+	.init_shader_exceptions = gp100_gr_init_shader_exceptions,
+	.trap_mp = gf100_gr_trap_mp,
 	.rops = gm200_gr_rops,
+	.gpc_nr = 6,
+	.tpc_nr = 5,
 	.ppc_nr = 2,
 	.grctx = &gp100_grctx,
+	.zbc = &gp100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp102.c
index 61e3a0b08559..37f7d739bf80 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp102.c
@@ -26,6 +26,62 @@
 
 #include <nvif/class.h>
 
+static void
+gp102_gr_zbc_clear_stencil(struct gf100_gr *gr, int zbc)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const int znum =  zbc - 1;
+	const u32 zoff = znum * 4;
+
+	if (gr->zbc_stencil[zbc].format)
+		nvkm_wr32(device, 0x41815c + zoff, gr->zbc_stencil[zbc].ds);
+	nvkm_mask(device, 0x418198 + ((znum / 4) * 4),
+			  0x0000007f << ((znum % 4) * 7),
+			  gr->zbc_stencil[zbc].format << ((znum % 4) * 7));
+}
+
+static int
+gp102_gr_zbc_stencil_get(struct gf100_gr *gr, int format,
+			 const u32 ds, const u32 l2)
+{
+	struct nvkm_ltc *ltc = gr->base.engine.subdev.device->ltc;
+	int zbc = -ENOSPC, i;
+
+	for (i = ltc->zbc_min; i <= ltc->zbc_max; i++) {
+		if (gr->zbc_stencil[i].format) {
+			if (gr->zbc_stencil[i].format != format)
+				continue;
+			if (gr->zbc_stencil[i].ds != ds)
+				continue;
+			if (gr->zbc_stencil[i].l2 != l2) {
+				WARN_ON(1);
+				return -EINVAL;
+			}
+			return i;
+		} else {
+			zbc = (zbc < 0) ? i : zbc;
+		}
+	}
+
+	if (zbc < 0)
+		return zbc;
+
+	gr->zbc_stencil[zbc].format = format;
+	gr->zbc_stencil[zbc].ds = ds;
+	gr->zbc_stencil[zbc].l2 = l2;
+	nvkm_ltc_zbc_stencil_get(ltc, zbc, l2);
+	gr->func->zbc->clear_stencil(gr, zbc);
+	return zbc;
+}
+
+const struct gf100_gr_func_zbc
+gp102_gr_zbc = {
+	.clear_color = gp100_gr_zbc_clear_color,
+	.clear_depth = gp100_gr_zbc_clear_depth,
+	.stencil_get = gp102_gr_zbc_stencil_get,
+	.clear_stencil = gp102_gr_zbc_clear_stencil,
+};
+
 void
 gp102_gr_init_swdx_pes_mask(struct gf100_gr *gr)
 {
@@ -42,15 +98,30 @@ gp102_gr_init_swdx_pes_mask(struct gf100_gr *gr)
 
 static const struct gf100_gr_func
 gp102_gr = {
-	.init = gp100_gr_init,
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gm200_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gm200_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gp100_gr_init_rop_active_fbps,
-	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
 	.init_swdx_pes_mask = gp102_gr_init_swdx_pes_mask,
-	.init_num_active_ltcs = gp100_gr_init_num_active_ltcs,
+	.init_fecs_exceptions = gp100_gr_init_fecs_exceptions,
+	.init_ds_hww_esr_2 = gm200_gr_init_ds_hww_esr_2,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_504430 = gm107_gr_init_504430,
+	.init_shader_exceptions = gp100_gr_init_shader_exceptions,
+	.trap_mp = gf100_gr_trap_mp,
 	.rops = gm200_gr_rops,
+	.gpc_nr = 6,
+	.tpc_nr = 5,
 	.ppc_nr = 3,
 	.grctx = &gp102_grctx,
+	.zbc = &gp102_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp104.c
new file mode 100644
index 000000000000..4573c914c021
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp104.c
@@ -0,0 +1,66 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ctxgf100.h"
+
+#include <nvif/class.h>
+
+static const struct gf100_gr_func
+gp104_gr = {
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
+	.init_gpc_mmu = gm200_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gm200_gr_init_num_active_ltcs,
+	.init_rop_active_fbps = gp100_gr_init_rop_active_fbps,
+	.init_swdx_pes_mask = gp102_gr_init_swdx_pes_mask,
+	.init_fecs_exceptions = gp100_gr_init_fecs_exceptions,
+	.init_ds_hww_esr_2 = gm200_gr_init_ds_hww_esr_2,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_504430 = gm107_gr_init_504430,
+	.init_shader_exceptions = gp100_gr_init_shader_exceptions,
+	.trap_mp = gf100_gr_trap_mp,
+	.rops = gm200_gr_rops,
+	.gpc_nr = 6,
+	.tpc_nr = 5,
+	.ppc_nr = 3,
+	.grctx = &gp104_grctx,
+	.zbc = &gp102_gr_zbc,
+	.sclass = {
+		{ -1, -1, FERMI_TWOD_A },
+		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
+		{ -1, -1, PASCAL_B, &gf100_fermi },
+		{ -1, -1, PASCAL_COMPUTE_B },
+		{}
+	}
+};
+
+int
+gp104_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
+{
+	return gm200_gr_new_(&gp104_gr, device, index, pgr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp107.c
index f7272323f694..812aba91653f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp107.c
@@ -28,15 +28,30 @@
 
 static const struct gf100_gr_func
 gp107_gr = {
-	.init = gp100_gr_init,
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gm200_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gm200_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gp100_gr_init_rop_active_fbps,
-	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
 	.init_swdx_pes_mask = gp102_gr_init_swdx_pes_mask,
-	.init_num_active_ltcs = gp100_gr_init_num_active_ltcs,
+	.init_fecs_exceptions = gp100_gr_init_fecs_exceptions,
+	.init_ds_hww_esr_2 = gm200_gr_init_ds_hww_esr_2,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
+	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_504430 = gm107_gr_init_504430,
+	.init_shader_exceptions = gp100_gr_init_shader_exceptions,
+	.trap_mp = gf100_gr_trap_mp,
 	.rops = gm200_gr_rops,
+	.gpc_nr = 2,
+	.tpc_nr = 3,
 	.ppc_nr = 1,
 	.grctx = &gp107_grctx,
+	.zbc = &gp102_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp10b.c
index 5f3d161a0842..303dceddd4a8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp10b.c
@@ -25,24 +25,31 @@
 
 #include <nvif/class.h>
 
-static void
-gp10b_gr_init_num_active_ltcs(struct gf100_gr *gr)
-{
-	struct nvkm_device *device = gr->base.engine.subdev.device;
-
-	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
-}
-
 static const struct gf100_gr_func
 gp10b_gr = {
-	.init = gp100_gr_init,
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
 	.init_gpc_mmu = gm200_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
 	.init_rop_active_fbps = gp100_gr_init_rop_active_fbps,
+	.init_fecs_exceptions = gp100_gr_init_fecs_exceptions,
+	.init_ds_hww_esr_2 = gm200_gr_init_ds_hww_esr_2,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_419cc0 = gf100_gr_init_419cc0,
 	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
-	.init_num_active_ltcs = gp10b_gr_init_num_active_ltcs,
+	.init_tex_hww_esr = gf100_gr_init_tex_hww_esr,
+	.init_504430 = gm107_gr_init_504430,
+	.init_shader_exceptions = gp100_gr_init_shader_exceptions,
+	.trap_mp = gf100_gr_trap_mp,
 	.rops = gm200_gr_rops,
+	.gpc_nr = 1,
+	.tpc_nr = 2,
 	.ppc_nr = 1,
 	.grctx = &gp102_grctx,
+	.zbc = &gp102_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
new file mode 100644
index 000000000000..19173ea19096
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
@@ -0,0 +1,120 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ctxgf100.h"
+
+#include <nvif/class.h>
+
+static void
+gv100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
+{
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 werr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x730));
+	u32 gerr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x734));
+	const struct nvkm_enum *warp;
+	char glob[128];
+
+	nvkm_snprintbf(glob, sizeof(glob), gf100_mp_global_error, gerr);
+	warp = nvkm_enum_find(gf100_mp_warp_error, werr & 0xffff);
+
+	nvkm_error(subdev, "GPC%i/TPC%i/MP trap: "
+			   "global %08x [%s] warp %04x [%s]\n",
+		   gpc, tpc, gerr, glob, werr, warp ? warp->name : "");
+
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x730), 0x00000000);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x734), gerr);
+}
+
+static void
+gv100_gr_init_4188a4(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x4188a4, 0x03000000, 0x03000000);
+}
+
+static void
+gv100_gr_init_shader_exceptions(struct gf100_gr *gr, int gpc, int tpc)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	int sm;
+	for (sm = 0; sm < 0x100; sm += 0x80) {
+		nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x728 + sm), 0x0085eb64);
+		nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x610), 0x00000001);
+		nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x72c + sm), 0x00000004);
+	}
+}
+
+static void
+gv100_gr_init_504430(struct gf100_gr *gr, int gpc, int tpc)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x430), 0x403f0000);
+}
+
+static void
+gv100_gr_init_419bd8(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x419bd8, 0x00000700, 0x00000000);
+}
+
+static const struct gf100_gr_func
+gv100_gr = {
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
+	.init_419bd8 = gv100_gr_init_419bd8,
+	.init_gpc_mmu = gm200_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = gf117_gr_init_zcull,
+	.init_num_active_ltcs = gm200_gr_init_num_active_ltcs,
+	.init_rop_active_fbps = gp100_gr_init_rop_active_fbps,
+	.init_swdx_pes_mask = gp102_gr_init_swdx_pes_mask,
+	.init_fecs_exceptions = gp100_gr_init_fecs_exceptions,
+	.init_ds_hww_esr_2 = gm200_gr_init_ds_hww_esr_2,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_504430 = gv100_gr_init_504430,
+	.init_shader_exceptions = gv100_gr_init_shader_exceptions,
+	.init_4188a4 = gv100_gr_init_4188a4,
+	.trap_mp = gv100_gr_trap_mp,
+	.rops = gm200_gr_rops,
+	.gpc_nr = 6,
+	.tpc_nr = 5,
+	.ppc_nr = 3,
+	.grctx = &gv100_grctx,
+	.zbc = &gp102_gr_zbc,
+	.sclass = {
+		{ -1, -1, FERMI_TWOD_A },
+		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
+		{ -1, -1, VOLTA_A, &gf100_fermi },
+		{ -1, -1, VOLTA_COMPUTE_A },
+		{}
+	}
+};
+
+int
+gv100_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
+{
+	return gm200_gr_new_(&gv100_gr, device, index, pgr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c
index 58a59b7db2e5..771e16a16267 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c
@@ -506,6 +506,7 @@ nvkm_msgqueue_new(u32 version, struct nvkm_falcon *falcon,
 		break;
 	case 0x0148cdec:
 	case 0x015ccf3e:
+	case 0x0167d263:
 		ret = msgqueue_0148cdec_new(falcon, sb, queue);
 		break;
 	default:
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
index 3f5d38d74fba..cfdffef1afb9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
@@ -3,6 +3,7 @@ include $(src)/nvkm/subdev/bios/Kbuild
 include $(src)/nvkm/subdev/bus/Kbuild
 include $(src)/nvkm/subdev/clk/Kbuild
 include $(src)/nvkm/subdev/devinit/Kbuild
+include $(src)/nvkm/subdev/fault/Kbuild
 include $(src)/nvkm/subdev/fb/Kbuild
 include $(src)/nvkm/subdev/fuse/Kbuild
 include $(src)/nvkm/subdev/gpio/Kbuild
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
index 7c7efa4ea0d0..3133b28f849c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
@@ -25,7 +25,7 @@
 #include <subdev/bios/bit.h>
 #include <subdev/bios/dp.h>
 
-static u16
+u16
 nvbios_dp_table(struct nvkm_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 {
 	struct bit_entry d;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
index 2ca23a9157ab..e6e804cee2bc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
@@ -193,7 +193,10 @@ pll_map_type(struct nvkm_bios *bios, u8 type, u32 *reg, u8 *ver, u8 *len)
 		data += hdr;
 		while (cnt--) {
 			if (nvbios_rd08(bios, data + 0) == type) {
-				*reg = nvbios_rd32(bios, data + 3);
+				if (*ver < 0x50)
+					*reg = nvbios_rd32(bios, data + 3);
+				else
+					*reg = 0;
 				return data;
 			}
 			data += *len;
@@ -361,6 +364,20 @@ nvbios_pll_parse(struct nvkm_bios *bios, u32 type, struct nvbios_pll *info)
 		info->min_p = nvbios_rd08(bios, data + 12);
 		info->max_p = nvbios_rd08(bios, data + 13);
 		break;
+	case 0x50:
+		info->refclk = nvbios_rd16(bios, data + 1) * 1000;
+		/* info->refclk_alt = nvbios_rd16(bios, data + 3) * 1000; */
+		info->vco1.min_freq = nvbios_rd16(bios, data + 5) * 1000;
+		info->vco1.max_freq = nvbios_rd16(bios, data + 7) * 1000;
+		info->vco1.min_inputfreq = nvbios_rd16(bios, data + 9) * 1000;
+		info->vco1.max_inputfreq = nvbios_rd16(bios, data + 11) * 1000;
+		info->vco1.min_m = nvbios_rd08(bios, data + 13);
+		info->vco1.max_m = nvbios_rd08(bios, data + 14);
+		info->vco1.min_n = nvbios_rd08(bios, data + 15);
+		info->vco1.max_n = nvbios_rd08(bios, data + 16);
+		info->min_p = nvbios_rd08(bios, data + 17);
+		info->max_p = nvbios_rd08(bios, data + 18);
+		break;
 	default:
 		nvkm_error(subdev, "unknown pll limits version 0x%02x\n", ver);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
index 0f537c22804c..3634cd0630b8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
@@ -78,7 +78,10 @@ pramin_init(struct nvkm_bios *bios, const char *name)
 	 * important as we don't want to be touching vram on an
 	 * uninitialised board
 	 */
-	addr = nvkm_rd32(device, 0x619f04);
+	if (device->card_type >= GV100)
+		addr = nvkm_rd32(device, 0x625f04);
+	else
+		addr = nvkm_rd32(device, 0x619f04);
 	if (!(addr & 0x00000008)) {
 		nvkm_debug(subdev, "... not enabled\n");
 		return ERR_PTR(-ENODEV);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c
index e4c8d310d870..ba6a868d4c95 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c
@@ -109,18 +109,17 @@ nvkm_cstate_valid(struct nvkm_clk *clk, struct nvkm_cstate *cstate,
 
 static struct nvkm_cstate *
 nvkm_cstate_find_best(struct nvkm_clk *clk, struct nvkm_pstate *pstate,
-		      struct nvkm_cstate *start)
+		      struct nvkm_cstate *cstate)
 {
 	struct nvkm_device *device = clk->subdev.device;
 	struct nvkm_volt *volt = device->volt;
-	struct nvkm_cstate *cstate;
 	int max_volt;
 
-	if (!pstate || !start)
+	if (!pstate || !cstate)
 		return NULL;
 
 	if (!volt)
-		return start;
+		return cstate;
 
 	max_volt = volt->max_uv;
 	if (volt->max0_id != 0xff)
@@ -133,8 +132,7 @@ nvkm_cstate_find_best(struct nvkm_clk *clk, struct nvkm_pstate *pstate,
 		max_volt = min(max_volt,
 			       nvkm_volt_map(volt, volt->max2_id, clk->temp));
 
-	for (cstate = start; &cstate->head != &pstate->list;
-	     cstate = list_entry(cstate->head.prev, typeof(*cstate), head)) {
+	list_for_each_entry_from_reverse(cstate, &pstate->list, head) {
 		if (nvkm_cstate_valid(clk, cstate, max_volt, clk->temp))
 			break;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
index eac88e3dc6e5..50a436926484 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
@@ -12,3 +12,4 @@ nvkm-y += nvkm/subdev/devinit/mcp89.o
 nvkm-y += nvkm/subdev/devinit/gf100.o
 nvkm-y += nvkm/subdev/devinit/gm107.o
 nvkm-y += nvkm/subdev/devinit/gm200.o
+nvkm-y += nvkm/subdev/devinit/gv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c
index 1730371933df..b80618e35491 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c
@@ -107,7 +107,7 @@ pmu_load(struct nv50_devinit *init, u8 type, bool post,
 	return pmu_exec(init, pmu.init_addr_pmu), 0;
 }
 
-static int
+int
 gm200_devinit_post(struct nvkm_devinit *base, bool post)
 {
 	struct nv50_devinit *init = nv50_devinit(base);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gv100.c
new file mode 100644
index 000000000000..fbde6828bd38
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gv100.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "nv50.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/pll.h>
+#include <subdev/clk/pll.h>
+
+static int
+gv100_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq)
+{
+	struct nvkm_subdev *subdev = &init->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvbios_pll info;
+	int head = type - PLL_VPLL0;
+	int N, fN, M, P;
+	int ret;
+
+	ret = nvbios_pll_parse(device->bios, type, &info);
+	if (ret)
+		return ret;
+
+	ret = gt215_pll_calc(subdev, &info, freq, &N, &fN, &M, &P);
+	if (ret < 0)
+		return ret;
+
+	switch (info.type) {
+	case PLL_VPLL0:
+	case PLL_VPLL1:
+	case PLL_VPLL2:
+	case PLL_VPLL3:
+		nvkm_wr32(device, 0x00ef10 + (head * 0x40), fN << 16);
+		nvkm_wr32(device, 0x00ef04 + (head * 0x40), (P << 16) |
+							    (N <<  8) |
+							    (M <<  0));
+		break;
+	default:
+		nvkm_warn(subdev, "%08x/%dKhz unimplemented\n", type, freq);
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static const struct nvkm_devinit_func
+gv100_devinit = {
+	.preinit = gf100_devinit_preinit,
+	.init = nv50_devinit_init,
+	.post = gm200_devinit_post,
+	.pll_set = gv100_devinit_pll_set,
+	.disable = gm107_devinit_disable,
+};
+
+int
+gv100_devinit_new(struct nvkm_device *device, int index,
+		struct nvkm_devinit **pinit)
+{
+	return nv50_devinit_new_(&gv100_devinit, device, index, pinit);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
index 315ebaff1165..9b9f0dc1e192 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
@@ -24,4 +24,6 @@ int  gf100_devinit_pll_set(struct nvkm_devinit *, u32, u32);
 void gf100_devinit_preinit(struct nvkm_devinit *);
 
 u64  gm107_devinit_disable(struct nvkm_devinit *);
+
+int gm200_devinit_post(struct nvkm_devinit *, bool);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild
new file mode 100644
index 000000000000..45bb46fb0929
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild
@@ -0,0 +1,3 @@
+nvkm-y += nvkm/subdev/fault/base.o
+nvkm-y += nvkm/subdev/fault/gp100.o
+nvkm-y += nvkm/subdev/fault/gv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
new file mode 100644
index 000000000000..007bf4af33b9
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
@@ -0,0 +1,179 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <core/memory.h>
+#include <core/notify.h>
+#include <subdev/bar.h>
+#include <subdev/mmu.h>
+
+static void
+nvkm_fault_ntfy_fini(struct nvkm_event *event, int type, int index)
+{
+	struct nvkm_fault *fault = container_of(event, typeof(*fault), event);
+	fault->func->buffer.fini(fault->buffer[index]);
+}
+
+static void
+nvkm_fault_ntfy_init(struct nvkm_event *event, int type, int index)
+{
+	struct nvkm_fault *fault = container_of(event, typeof(*fault), event);
+	fault->func->buffer.init(fault->buffer[index]);
+}
+
+static int
+nvkm_fault_ntfy_ctor(struct nvkm_object *object, void *argv, u32 argc,
+		     struct nvkm_notify *notify)
+{
+	struct nvkm_fault_buffer *buffer = nvkm_fault_buffer(object);
+	if (argc == 0) {
+		notify->size  = 0;
+		notify->types = 1;
+		notify->index = buffer->id;
+		return 0;
+	}
+	return -ENOSYS;
+}
+
+static const struct nvkm_event_func
+nvkm_fault_ntfy = {
+	.ctor = nvkm_fault_ntfy_ctor,
+	.init = nvkm_fault_ntfy_init,
+	.fini = nvkm_fault_ntfy_fini,
+};
+
+static void
+nvkm_fault_intr(struct nvkm_subdev *subdev)
+{
+	struct nvkm_fault *fault = nvkm_fault(subdev);
+	return fault->func->intr(fault);
+}
+
+static int
+nvkm_fault_fini(struct nvkm_subdev *subdev, bool suspend)
+{
+	struct nvkm_fault *fault = nvkm_fault(subdev);
+	if (fault->func->fini)
+		fault->func->fini(fault);
+	return 0;
+}
+
+static int
+nvkm_fault_init(struct nvkm_subdev *subdev)
+{
+	struct nvkm_fault *fault = nvkm_fault(subdev);
+	if (fault->func->init)
+		fault->func->init(fault);
+	return 0;
+}
+
+static int
+nvkm_fault_oneinit_buffer(struct nvkm_fault *fault, int id)
+{
+	struct nvkm_subdev *subdev = &fault->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_vmm *bar2 = nvkm_bar_bar2_vmm(device);
+	struct nvkm_fault_buffer *buffer;
+	int ret;
+
+	if (!(buffer = kzalloc(sizeof(*buffer), GFP_KERNEL)))
+		return -ENOMEM;
+	buffer->fault = fault;
+	buffer->id = id;
+	buffer->entries = fault->func->buffer.entries(buffer);
+	fault->buffer[id] = buffer;
+
+	nvkm_debug(subdev, "buffer %d: %d entries\n", id, buffer->entries);
+
+	ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, buffer->entries *
+			      fault->func->buffer.entry_size, 0x1000, true,
+			      &buffer->mem);
+	if (ret)
+		return ret;
+
+	ret = nvkm_vmm_get(bar2, 12, nvkm_memory_size(buffer->mem),
+			   &buffer->vma);
+	if (ret)
+		return ret;
+
+	return nvkm_memory_map(buffer->mem, 0, bar2, buffer->vma, NULL, 0);
+}
+
+static int
+nvkm_fault_oneinit(struct nvkm_subdev *subdev)
+{
+	struct nvkm_fault *fault = nvkm_fault(subdev);
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(fault->buffer); i++) {
+		if (i < fault->func->buffer.nr) {
+			ret = nvkm_fault_oneinit_buffer(fault, i);
+			if (ret)
+				return ret;
+			fault->buffer_nr = i + 1;
+		}
+	}
+
+	return nvkm_event_init(&nvkm_fault_ntfy, 1, fault->buffer_nr,
+			       &fault->event);
+}
+
+static void *
+nvkm_fault_dtor(struct nvkm_subdev *subdev)
+{
+	struct nvkm_vmm *bar2 = nvkm_bar_bar2_vmm(subdev->device);
+	struct nvkm_fault *fault = nvkm_fault(subdev);
+	int i;
+
+	nvkm_event_fini(&fault->event);
+
+	for (i = 0; i < fault->buffer_nr; i++) {
+		if (fault->buffer[i]) {
+			nvkm_vmm_put(bar2, &fault->buffer[i]->vma);
+			nvkm_memory_unref(&fault->buffer[i]->mem);
+			kfree(fault->buffer[i]);
+		}
+	}
+
+	return fault;
+}
+
+static const struct nvkm_subdev_func
+nvkm_fault = {
+	.dtor = nvkm_fault_dtor,
+	.oneinit = nvkm_fault_oneinit,
+	.init = nvkm_fault_init,
+	.fini = nvkm_fault_fini,
+	.intr = nvkm_fault_intr,
+};
+
+int
+nvkm_fault_new_(const struct nvkm_fault_func *func, struct nvkm_device *device,
+		int index, struct nvkm_fault **pfault)
+{
+	struct nvkm_fault *fault;
+	if (!(fault = *pfault = kzalloc(sizeof(*fault), GFP_KERNEL)))
+		return -ENOMEM;
+	nvkm_subdev_ctor(&nvkm_fault, device, index, &fault->subdev);
+	fault->func = func;
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp100.c
new file mode 100644
index 000000000000..5e71db2e8d75
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp100.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <subdev/mmu.h>
+
+static void
+gp100_fault_buffer_fini(struct nvkm_fault_buffer *buffer)
+{
+	struct nvkm_device *device = buffer->fault->subdev.device;
+	nvkm_mask(device, 0x002a70, 0x00000001, 0x00000000);
+}
+
+static void
+gp100_fault_buffer_init(struct nvkm_fault_buffer *buffer)
+{
+	struct nvkm_device *device = buffer->fault->subdev.device;
+	nvkm_wr32(device, 0x002a74, upper_32_bits(buffer->vma->addr));
+	nvkm_wr32(device, 0x002a70, lower_32_bits(buffer->vma->addr));
+	nvkm_mask(device, 0x002a70, 0x00000001, 0x00000001);
+}
+
+static u32
+gp100_fault_buffer_entries(struct nvkm_fault_buffer *buffer)
+{
+	return nvkm_rd32(buffer->fault->subdev.device, 0x002a78);
+}
+
+static void
+gp100_fault_intr(struct nvkm_fault *fault)
+{
+	nvkm_event_send(&fault->event, 1, 0, NULL, 0);
+}
+
+static const struct nvkm_fault_func
+gp100_fault = {
+	.intr = gp100_fault_intr,
+	.buffer.nr = 1,
+	.buffer.entry_size = 32,
+	.buffer.entries = gp100_fault_buffer_entries,
+	.buffer.init = gp100_fault_buffer_init,
+	.buffer.fini = gp100_fault_buffer_fini,
+};
+
+int
+gp100_fault_new(struct nvkm_device *device, int index,
+		struct nvkm_fault **pfault)
+{
+	return nvkm_fault_new_(&gp100_fault, device, index, pfault);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
new file mode 100644
index 000000000000..73c7728b5969
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
@@ -0,0 +1,206 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <core/memory.h>
+#include <subdev/mmu.h>
+#include <engine/fifo.h>
+
+static void
+gv100_fault_buffer_process(struct nvkm_fault_buffer *buffer)
+{
+	struct nvkm_device *device = buffer->fault->subdev.device;
+	struct nvkm_memory *mem = buffer->mem;
+	const u32 foff = buffer->id * 0x14;
+	u32 get = nvkm_rd32(device, 0x100e2c + foff);
+	u32 put = nvkm_rd32(device, 0x100e30 + foff);
+	if (put == get)
+		return;
+
+	nvkm_kmap(mem);
+	while (get != put) {
+		const u32   base = get * buffer->fault->func->buffer.entry_size;
+		const u32 instlo = nvkm_ro32(mem, base + 0x00);
+		const u32 insthi = nvkm_ro32(mem, base + 0x04);
+		const u32 addrlo = nvkm_ro32(mem, base + 0x08);
+		const u32 addrhi = nvkm_ro32(mem, base + 0x0c);
+		const u32 timelo = nvkm_ro32(mem, base + 0x10);
+		const u32 timehi = nvkm_ro32(mem, base + 0x14);
+		const u32  info0 = nvkm_ro32(mem, base + 0x18);
+		const u32  info1 = nvkm_ro32(mem, base + 0x1c);
+		struct nvkm_fault_data info;
+
+		if (++get == buffer->entries)
+			get = 0;
+		nvkm_wr32(device, 0x100e2c + foff, get);
+
+		info.addr   = ((u64)addrhi << 32) | addrlo;
+		info.inst   = ((u64)insthi << 32) | instlo;
+		info.time   = ((u64)timehi << 32) | timelo;
+		info.engine = (info0 & 0x000000ff);
+		info.valid  = (info1 & 0x80000000) >> 31;
+		info.gpc    = (info1 & 0x1f000000) >> 24;
+		info.hub    = (info1 & 0x00100000) >> 20;
+		info.access = (info1 & 0x000f0000) >> 16;
+		info.client = (info1 & 0x00007f00) >> 8;
+		info.reason = (info1 & 0x0000001f);
+
+		nvkm_fifo_fault(device->fifo, &info);
+	}
+	nvkm_done(mem);
+}
+
+static void
+gv100_fault_buffer_fini(struct nvkm_fault_buffer *buffer)
+{
+	struct nvkm_device *device = buffer->fault->subdev.device;
+	const u32 intr = buffer->id ? 0x08000000 : 0x20000000;
+	const u32 foff = buffer->id * 0x14;
+
+	nvkm_mask(device, 0x100a34, intr, intr);
+	nvkm_mask(device, 0x100e34 + foff, 0x80000000, 0x00000000);
+}
+
+static void
+gv100_fault_buffer_init(struct nvkm_fault_buffer *buffer)
+{
+	struct nvkm_device *device = buffer->fault->subdev.device;
+	const u32 intr = buffer->id ? 0x08000000 : 0x20000000;
+	const u32 foff = buffer->id * 0x14;
+
+	nvkm_mask(device, 0x100e34 + foff, 0xc0000000, 0x40000000);
+	nvkm_wr32(device, 0x100e28 + foff, upper_32_bits(buffer->vma->addr));
+	nvkm_wr32(device, 0x100e24 + foff, lower_32_bits(buffer->vma->addr));
+	nvkm_mask(device, 0x100e34 + foff, 0x80000000, 0x80000000);
+	nvkm_mask(device, 0x100a2c, intr, intr);
+}
+
+static u32
+gv100_fault_buffer_entries(struct nvkm_fault_buffer *buffer)
+{
+	struct nvkm_device *device = buffer->fault->subdev.device;
+	const u32 foff = buffer->id * 0x14;
+	nvkm_mask(device, 0x100e34 + foff, 0x40000000, 0x40000000);
+	return nvkm_rd32(device, 0x100e34 + foff) & 0x000fffff;
+}
+
+static int
+gv100_fault_ntfy_nrpfb(struct nvkm_notify *notify)
+{
+	struct nvkm_fault *fault = container_of(notify, typeof(*fault), nrpfb);
+	gv100_fault_buffer_process(fault->buffer[0]);
+	return NVKM_NOTIFY_KEEP;
+}
+
+static void
+gv100_fault_intr_fault(struct nvkm_fault *fault)
+{
+	struct nvkm_subdev *subdev = &fault->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_fault_data info;
+	const u32 addrlo = nvkm_rd32(device, 0x100e4c);
+	const u32 addrhi = nvkm_rd32(device, 0x100e50);
+	const u32  info0 = nvkm_rd32(device, 0x100e54);
+	const u32 insthi = nvkm_rd32(device, 0x100e58);
+	const u32  info1 = nvkm_rd32(device, 0x100e5c);
+
+	info.addr = ((u64)addrhi << 32) | addrlo;
+	info.inst = ((u64)insthi << 32) | (info0 & 0xfffff000);
+	info.time = 0;
+	info.engine = (info0 & 0x000000ff);
+	info.valid  = (info1 & 0x80000000) >> 31;
+	info.gpc    = (info1 & 0x1f000000) >> 24;
+	info.hub    = (info1 & 0x00100000) >> 20;
+	info.access = (info1 & 0x000f0000) >> 16;
+	info.client = (info1 & 0x00007f00) >> 8;
+	info.reason = (info1 & 0x0000001f);
+
+	nvkm_fifo_fault(device->fifo, &info);
+}
+
+static void
+gv100_fault_intr(struct nvkm_fault *fault)
+{
+	struct nvkm_subdev *subdev = &fault->subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 stat = nvkm_rd32(device, 0x100a20);
+
+	if (stat & 0x80000000) {
+		gv100_fault_intr_fault(fault);
+		nvkm_wr32(device, 0x100e60, 0x80000000);
+		stat &= ~0x80000000;
+	}
+
+	if (stat & 0x20000000) {
+		if (fault->buffer[0]) {
+			nvkm_event_send(&fault->event, 1, 0, NULL, 0);
+			stat &= ~0x20000000;
+		}
+	}
+
+	if (stat) {
+		nvkm_debug(subdev, "intr %08x\n", stat);
+	}
+}
+
+static void
+gv100_fault_fini(struct nvkm_fault *fault)
+{
+	nvkm_notify_put(&fault->nrpfb);
+	nvkm_mask(fault->subdev.device, 0x100a34, 0x80000000, 0x80000000);
+}
+
+static void
+gv100_fault_init(struct nvkm_fault *fault)
+{
+	nvkm_mask(fault->subdev.device, 0x100a2c, 0x80000000, 0x80000000);
+	nvkm_notify_get(&fault->nrpfb);
+}
+
+static const struct nvkm_fault_func
+gv100_fault = {
+	.init = gv100_fault_init,
+	.fini = gv100_fault_fini,
+	.intr = gv100_fault_intr,
+	.buffer.nr = 2,
+	.buffer.entry_size = 32,
+	.buffer.entries = gv100_fault_buffer_entries,
+	.buffer.init = gv100_fault_buffer_init,
+	.buffer.fini = gv100_fault_buffer_fini,
+};
+
+int
+gv100_fault_new(struct nvkm_device *device, int index,
+		struct nvkm_fault **pfault)
+{
+	struct nvkm_fault *fault;
+	int ret;
+
+	ret = nvkm_fault_new_(&gv100_fault, device, index, &fault);
+	*pfault = fault;
+	if (ret)
+		return ret;
+
+	return nvkm_notify_init(&fault->buffer[0]->object, &fault->event,
+				gv100_fault_ntfy_nrpfb, false, NULL, 0, 0,
+				&fault->nrpfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
new file mode 100644
index 000000000000..44843ecf12b0
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
@@ -0,0 +1,34 @@
+#ifndef __NVKM_FAULT_PRIV_H__
+#define __NVKM_FAULT_PRIV_H__
+#define nvkm_fault_buffer(p) container_of((p), struct nvkm_fault_buffer, object)
+#define nvkm_fault(p) container_of((p), struct nvkm_fault, subdev)
+#include <subdev/fault.h>
+
+#include <core/event.h>
+#include <core/object.h>
+
+struct nvkm_fault_buffer {
+	struct nvkm_object object;
+	struct nvkm_fault *fault;
+	int id;
+	int entries;
+	struct nvkm_memory *mem;
+	struct nvkm_vma *vma;
+};
+
+int nvkm_fault_new_(const struct nvkm_fault_func *, struct nvkm_device *,
+		    int index, struct nvkm_fault **);
+
+struct nvkm_fault_func {
+	void (*init)(struct nvkm_fault *);
+	void (*fini)(struct nvkm_fault *);
+	void (*intr)(struct nvkm_fault *);
+	struct {
+		int nr;
+		u32 entry_size;
+		u32 (*entries)(struct nvkm_fault_buffer *);
+		void (*init)(struct nvkm_fault_buffer *);
+		void (*fini)(struct nvkm_fault_buffer *);
+	} buffer;
+};
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
index b4f22cce5d43..969610951263 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
@@ -30,6 +30,7 @@ nvkm-y += nvkm/subdev/fb/gm20b.o
 nvkm-y += nvkm/subdev/fb/gp100.o
 nvkm-y += nvkm/subdev/fb/gp102.o
 nvkm-y += nvkm/subdev/fb/gp10b.o
+nvkm-y += nvkm/subdev/fb/gv100.o
 
 nvkm-y += nvkm/subdev/fb/ram.o
 nvkm-y += nvkm/subdev/fb/ramnv04.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
index cdc4e0a2cc6b..e8dc4e913494 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
@@ -46,10 +46,10 @@ gf100_fb_oneinit(struct nvkm_fb *base)
 {
 	struct gf100_fb *fb = gf100_fb(base);
 	struct nvkm_device *device = fb->base.subdev.device;
-	int ret, size = 0x1000;
+	int ret, size = 1 << (fb->base.page ? fb->base.page : 17);
 
 	size = nvkm_longopt(device->cfgopt, "MmuDebugBufferSize", size);
-	size = min(size, 0x1000);
+	size = max(size, 0x1000);
 
 	ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, size, 0x1000,
 			      true, &fb->base.mmu_rd);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c
index 8137e19d3292..d3b8c3367152 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c
@@ -49,8 +49,6 @@ gm200_fb_init(struct nvkm_fb *base)
 	if (fb->r100c10_page)
 		nvkm_wr32(device, 0x100c10, fb->r100c10 >> 8);
 
-	nvkm_mask(device, 0x100c80, 0x00000001, 0x00000000); /* 128KiB lpg */
-
 	nvkm_wr32(device, 0x100cc8, nvkm_memory_addr(fb->base.mmu_wr) >> 8);
 	nvkm_wr32(device, 0x100ccc, nvkm_memory_addr(fb->base.mmu_rd) >> 8);
 	nvkm_mask(device, 0x100cc4, 0x00060000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
index 147f69b30cd8..dffe1f5e1071 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
@@ -26,7 +26,7 @@
 
 #include <core/memory.h>
 
-static void
+void
 gp100_fb_init_unkn(struct nvkm_fb *base)
 {
 	struct nvkm_device *device = gf100_fb(base)->base.subdev.device;
@@ -48,7 +48,7 @@ gp100_fb_init(struct nvkm_fb *base)
 	nvkm_wr32(device, 0x100cc8, nvkm_memory_addr(fb->base.mmu_wr) >> 8);
 	nvkm_wr32(device, 0x100ccc, nvkm_memory_addr(fb->base.mmu_rd) >> 8);
 	nvkm_mask(device, 0x100cc4, 0x00060000,
-		  max(nvkm_memory_size(fb->base.mmu_rd) >> 16, (u64)2) << 17);
+		  min(nvkm_memory_size(fb->base.mmu_rd) >> 16, (u64)2) << 17);
 }
 
 static const struct nvkm_fb_func
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
new file mode 100644
index 000000000000..3c5e02e9794a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
@@ -0,0 +1,46 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static int
+gv100_fb_init_page(struct nvkm_fb *fb)
+{
+	return (fb->page == 16) ? 0 : -EINVAL;
+}
+
+static const struct nvkm_fb_func
+gv100_fb = {
+	.dtor = gf100_fb_dtor,
+	.oneinit = gf100_fb_oneinit,
+	.init = gp100_fb_init,
+	.init_page = gv100_fb_init_page,
+	.init_unkn = gp100_fb_init_unkn,
+	.ram_new = gp100_ram_new,
+	.default_bigpage = 16,
+};
+
+int
+gv100_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+	return gf100_fb_new_(&gv100_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index 414a423e0e55..2857f31466bf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -68,4 +68,6 @@ int gf100_fb_oneinit(struct nvkm_fb *);
 int gf100_fb_init_page(struct nvkm_fb *);
 
 int gm200_fb_init_page(struct nvkm_fb *);
+
+void gp100_fb_init_unkn(struct nvkm_fb *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
index 12d6f4f102cb..290ff1c425a9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
@@ -4,3 +4,4 @@ nvkm-y += nvkm/subdev/ltc/gk104.o
 nvkm-y += nvkm/subdev/ltc/gm107.o
 nvkm-y += nvkm/subdev/ltc/gm200.o
 nvkm-y += nvkm/subdev/ltc/gp100.o
+nvkm-y += nvkm/subdev/ltc/gp102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c
index 1f185274d3e6..23242179e600 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c
@@ -55,6 +55,14 @@ nvkm_ltc_zbc_depth_get(struct nvkm_ltc *ltc, int index, const u32 depth)
 	return index;
 }
 
+int
+nvkm_ltc_zbc_stencil_get(struct nvkm_ltc *ltc, int index, const u32 stencil)
+{
+	ltc->zbc_stencil[index] = stencil;
+	ltc->func->zbc_clear_stencil(ltc, index, stencil);
+	return index;
+}
+
 void
 nvkm_ltc_invalidate(struct nvkm_ltc *ltc)
 {
@@ -92,6 +100,8 @@ nvkm_ltc_init(struct nvkm_subdev *subdev)
 	for (i = ltc->zbc_min; i <= ltc->zbc_max; i++) {
 		ltc->func->zbc_clear_color(ltc, i, ltc->zbc_color[i]);
 		ltc->func->zbc_clear_depth(ltc, i, ltc->zbc_depth[i]);
+		if (ltc->func->zbc_clear_stencil)
+			ltc->func->zbc_clear_stencil(ltc, i, ltc->zbc_stencil[i]);
 	}
 
 	ltc->func->init(ltc);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp100.c
index e34d42108019..e923ed76d37a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp100.c
@@ -23,7 +23,7 @@
  */
 #include "priv.h"
 
-static void
+void
 gp100_ltc_intr(struct nvkm_ltc *ltc)
 {
 	struct nvkm_device *device = ltc->subdev.device;
@@ -38,7 +38,7 @@ gp100_ltc_intr(struct nvkm_ltc *ltc)
 	}
 }
 
-static int
+int
 gp100_ltc_oneinit(struct nvkm_ltc *ltc)
 {
 	struct nvkm_device *device = ltc->subdev.device;
@@ -48,7 +48,7 @@ gp100_ltc_oneinit(struct nvkm_ltc *ltc)
 	return 0;
 }
 
-static void
+void
 gp100_ltc_init(struct nvkm_ltc *ltc)
 {
 	/*XXX: PMU LS call to setup tagram address */
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp102.c
new file mode 100644
index 000000000000..601747ada655
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp102.c
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+void
+gp102_ltc_zbc_clear_stencil(struct nvkm_ltc *ltc, int i, const u32 stencil)
+{
+	struct nvkm_device *device = ltc->subdev.device;
+	nvkm_mask(device, 0x17e338, 0x0000000f, i);
+	nvkm_wr32(device, 0x17e204, stencil);
+}
+
+static const struct nvkm_ltc_func
+gp102_ltc = {
+	.oneinit = gp100_ltc_oneinit,
+	.init = gp100_ltc_init,
+	.intr = gp100_ltc_intr,
+	.cbc_clear = gm107_ltc_cbc_clear,
+	.cbc_wait = gm107_ltc_cbc_wait,
+	.zbc = 16,
+	.zbc_clear_color = gm107_ltc_zbc_clear_color,
+	.zbc_clear_depth = gm107_ltc_zbc_clear_depth,
+	.zbc_clear_stencil = gp102_ltc_zbc_clear_stencil,
+	.invalidate = gf100_ltc_invalidate,
+	.flush = gf100_ltc_flush,
+};
+
+int
+gp102_ltc_new(struct nvkm_device *device, int index, struct nvkm_ltc **pltc)
+{
+	return nvkm_ltc_new_(&gp102_ltc, device, index, pltc);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
index e71cc25cc775..9dcde43c0f3c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
@@ -19,6 +19,7 @@ struct nvkm_ltc_func {
 	int zbc;
 	void (*zbc_clear_color)(struct nvkm_ltc *, int, const u32[4]);
 	void (*zbc_clear_depth)(struct nvkm_ltc *, int, const u32);
+	void (*zbc_clear_stencil)(struct nvkm_ltc *, int, const u32);
 
 	void (*invalidate)(struct nvkm_ltc *);
 	void (*flush)(struct nvkm_ltc *);
@@ -41,4 +42,8 @@ void gm107_ltc_cbc_clear(struct nvkm_ltc *, u32, u32);
 void gm107_ltc_cbc_wait(struct nvkm_ltc *);
 void gm107_ltc_zbc_clear_color(struct nvkm_ltc *, int, const u32[4]);
 void gm107_ltc_zbc_clear_depth(struct nvkm_ltc *, int, const u32);
+
+int gp100_ltc_oneinit(struct nvkm_ltc *);
+void gp100_ltc_init(struct nvkm_ltc *);
+void gp100_ltc_intr(struct nvkm_ltc *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp100.c
index 7321ad3758c3..43db245eec9a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp100.c
@@ -75,10 +75,28 @@ gp100_mc_intr_mask(struct nvkm_mc *base, u32 mask, u32 intr)
 	spin_unlock_irqrestore(&mc->lock, flags);
 }
 
+const struct nvkm_mc_map
+gp100_mc_intr[] = {
+	{ 0x04000000, NVKM_ENGINE_DISP },
+	{ 0x00000100, NVKM_ENGINE_FIFO },
+	{ 0x00000200, NVKM_SUBDEV_FAULT },
+	{ 0x40000000, NVKM_SUBDEV_IBUS },
+	{ 0x10000000, NVKM_SUBDEV_BUS },
+	{ 0x08000000, NVKM_SUBDEV_FB },
+	{ 0x02000000, NVKM_SUBDEV_LTC },
+	{ 0x01000000, NVKM_SUBDEV_PMU },
+	{ 0x00200000, NVKM_SUBDEV_GPIO },
+	{ 0x00200000, NVKM_SUBDEV_I2C },
+	{ 0x00100000, NVKM_SUBDEV_TIMER },
+	{ 0x00040000, NVKM_SUBDEV_THERM },
+	{ 0x00002000, NVKM_SUBDEV_FB },
+	{},
+};
+
 static const struct nvkm_mc_func
 gp100_mc = {
 	.init = nv50_mc_init,
-	.intr = gk104_mc_intr,
+	.intr = gp100_mc_intr,
 	.intr_unarm = gp100_mc_intr_unarm,
 	.intr_rearm = gp100_mc_intr_rearm,
 	.intr_mask = gp100_mc_intr_mask,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp10b.c
index 2283e3b74277..ff8629de97d6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp10b.c
@@ -34,7 +34,7 @@ gp10b_mc_init(struct nvkm_mc *mc)
 static const struct nvkm_mc_func
 gp10b_mc = {
 	.init = gp10b_mc_init,
-	.intr = gk104_mc_intr,
+	.intr = gp100_mc_intr,
 	.intr_unarm = gp100_mc_intr_unarm,
 	.intr_rearm = gp100_mc_intr_rearm,
 	.intr_mask = gp100_mc_intr_mask,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/priv.h
index 8869d79c2b59..d9e3691d45b7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/priv.h
@@ -57,4 +57,6 @@ int gp100_mc_new_(const struct nvkm_mc_func *, struct nvkm_device *, int,
 
 extern const struct nvkm_mc_map gk104_mc_intr[];
 extern const struct nvkm_mc_map gk104_mc_reset[];
+
+extern const struct nvkm_mc_map gp100_mc_intr[];
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
index 67ee983bb026..58a24e3a0598 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
@@ -12,6 +12,7 @@ nvkm-y += nvkm/subdev/mmu/gm200.o
 nvkm-y += nvkm/subdev/mmu/gm20b.o
 nvkm-y += nvkm/subdev/mmu/gp100.o
 nvkm-y += nvkm/subdev/mmu/gp10b.o
+nvkm-y += nvkm/subdev/mmu/gv100.o
 
 nvkm-y += nvkm/subdev/mmu/mem.o
 nvkm-y += nvkm/subdev/mmu/memnv04.o
@@ -31,6 +32,7 @@ nvkm-y += nvkm/subdev/mmu/vmmgm200.o
 nvkm-y += nvkm/subdev/mmu/vmmgm20b.o
 nvkm-y += nvkm/subdev/mmu/vmmgp100.o
 nvkm-y += nvkm/subdev/mmu/vmmgp10b.o
+nvkm-y += nvkm/subdev/mmu/vmmgv100.o
 
 nvkm-y += nvkm/subdev/mmu/umem.o
 nvkm-y += nvkm/subdev/mmu/ummu.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gv100.c
new file mode 100644
index 000000000000..f666cb57f69e
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gv100.c
@@ -0,0 +1,43 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "mem.h"
+#include "vmm.h"
+
+#include <core/option.h>
+
+#include <nvif/class.h>
+
+static const struct nvkm_mmu_func
+gv100_mmu = {
+	.dma_bits = 47,
+	.mmu = {{ -1, -1, NVIF_CLASS_MMU_GF100}},
+	.mem = {{ -1,  0, NVIF_CLASS_MEM_GF100}, gf100_mem_new, gf100_mem_map },
+	.vmm = {{ -1, -1, NVIF_CLASS_VMM_GP100}, gv100_vmm_new },
+	.kind = gm200_mmu_kind,
+	.kind_sys = true,
+};
+
+int
+gv100_mmu_new(struct nvkm_device *device, int index, struct nvkm_mmu **pmmu)
+{
+	return nvkm_mmu_new_(&gv100_mmu, device, index, pmmu);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h
index da06e64d8a7d..1a3b0a3724ca 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h
@@ -236,6 +236,9 @@ int gp100_vmm_new(struct nvkm_mmu *, u64, u64, void *, u32,
 int gp10b_vmm_new(struct nvkm_mmu *, u64, u64, void *, u32,
 		  struct lock_class_key *, const char *,
 		  struct nvkm_vmm **);
+int gv100_vmm_new(struct nvkm_mmu *, u64, u64, void *, u32,
+		  struct lock_class_key *, const char *,
+		  struct nvkm_vmm **);
 
 #define VMM_PRINT(l,v,p,f,a...) do {                                           \
 	struct nvkm_vmm *_vmm = (v);                                           \
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgv100.c
new file mode 100644
index 000000000000..2fa40c16e6d2
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgv100.c
@@ -0,0 +1,87 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "vmm.h"
+
+#include <subdev/fb.h>
+#include <subdev/ltc.h>
+
+#include <nvif/ifc00d.h>
+#include <nvif/unpack.h>
+
+int
+gv100_vmm_join(struct nvkm_vmm *vmm, struct nvkm_memory *inst)
+{
+	u64 data[2], mask;
+	int ret = gp100_vmm_join(vmm, inst), i;
+	if (ret)
+		return ret;
+
+	nvkm_kmap(inst);
+	data[0] = nvkm_ro32(inst, 0x200);
+	data[1] = nvkm_ro32(inst, 0x204);
+	mask = BIT_ULL(0);
+
+	nvkm_wo32(inst, 0x21c, 0x00000000);
+
+	for (i = 0; i < 64; i++) {
+		if (mask & BIT_ULL(i)) {
+			nvkm_wo32(inst, 0x2a4 + (i * 0x10), data[1]);
+			nvkm_wo32(inst, 0x2a0 + (i * 0x10), data[0]);
+		} else {
+			nvkm_wo32(inst, 0x2a4 + (i * 0x10), 0x00000001);
+			nvkm_wo32(inst, 0x2a0 + (i * 0x10), 0x00000001);
+		}
+		nvkm_wo32(inst, 0x2a8 + (i * 0x10), 0x00000000);
+	}
+
+	nvkm_wo32(inst, 0x298, lower_32_bits(mask));
+	nvkm_wo32(inst, 0x29c, upper_32_bits(mask));
+	nvkm_done(inst);
+	return 0;
+}
+
+static const struct nvkm_vmm_func
+gv100_vmm = {
+	.join = gv100_vmm_join,
+	.part = gf100_vmm_part,
+	.aper = gf100_vmm_aper,
+	.valid = gp100_vmm_valid,
+	.flush = gp100_vmm_flush,
+	.page = {
+		{ 47, &gp100_vmm_desc_16[4], NVKM_VMM_PAGE_Sxxx },
+		{ 38, &gp100_vmm_desc_16[3], NVKM_VMM_PAGE_Sxxx },
+		{ 29, &gp100_vmm_desc_16[2], NVKM_VMM_PAGE_Sxxx },
+		{ 21, &gp100_vmm_desc_16[1], NVKM_VMM_PAGE_SVxC },
+		{ 16, &gp100_vmm_desc_16[0], NVKM_VMM_PAGE_SVxC },
+		{ 12, &gp100_vmm_desc_12[0], NVKM_VMM_PAGE_SVHx },
+		{}
+	}
+};
+
+int
+gv100_vmm_new(struct nvkm_mmu *mmu, u64 addr, u64 size, void *argv, u32 argc,
+	      struct lock_class_key *key, const char *name,
+	      struct nvkm_vmm **pvmm)
+{
+	return nv04_vmm_new_(&gv100_vmm, mmu, 0, addr, size,
+			     argv, argc, key, name, pvmm);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c
index e8c27ec700de..737a8d50a1f2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c
@@ -65,3 +65,24 @@ MODULE_FIRMWARE("nvidia/gp108/nvdec/scrubber.bin");
 MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin");
 MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin");
 MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin");
+
+MODULE_FIRMWARE("nvidia/gv100/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gv100/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gv100/acr/ucode_load.bin");
+MODULE_FIRMWARE("nvidia/gv100/acr/ucode_unload.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/sw_method_init.bin");
+MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/gv100/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gv100/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gv100/sec2/sig.bin");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_msgqueue.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_msgqueue.c
index 6f10b098676c..1e1f1c635cab 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_msgqueue.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_msgqueue.c
@@ -80,12 +80,11 @@ acr_ls_msgqueue_post_run(struct nvkm_msgqueue *queue,
 			 struct nvkm_falcon *falcon, u32 addr_args)
 {
 	struct nvkm_device *device = falcon->owner->device;
-	u32 cmdline_size = NVKM_MSGQUEUE_CMDLINE_SIZE;
-	u8 buf[cmdline_size];
+	u8 buf[NVKM_MSGQUEUE_CMDLINE_SIZE];
 
-	memset(buf, 0, cmdline_size);
+	memset(buf, 0, sizeof(buf));
 	nvkm_msgqueue_write_cmdline(queue, buf);
-	nvkm_falcon_load_dmem(falcon, buf, addr_args, cmdline_size, 0);
+	nvkm_falcon_load_dmem(falcon, buf, addr_args, sizeof(buf), 0);
 	/* rearm the queue so it will wait for the init message */
 	nvkm_msgqueue_reinit(queue);
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/top/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/top/gk104.c
index fea4957291da..4f1f3e890650 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/top/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/top/gk104.c
@@ -48,7 +48,8 @@ gk104_top_oneinit(struct nvkm_top *top)
 		case 0x00000001: /* DATA */
 			inst        = (data & 0x3c000000) >> 26;
 			info->addr  = (data & 0x00fff000);
-			info->fault = (data & 0x000000f8) >> 3;
+			if (data & 0x00000004)
+				info->fault = (data & 0x000003f8) >> 3;
 			break;
 		case 0x00000002: /* ENUM */
 			if (data & 0x00000020)
diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c
index 5e2e65e88847..7f3ac6b13b56 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc.c
+++ b/drivers/gpu/drm/omapdrm/dss/dispc.c
@@ -828,6 +828,12 @@ static void dispc_ovl_set_scale_coef(struct dispc_device *dispc,
 	h_coef = dispc_ovl_get_scale_coef(fir_hinc, true);
 	v_coef = dispc_ovl_get_scale_coef(fir_vinc, five_taps);
 
+	if (!h_coef || !v_coef) {
+		dev_err(&dispc->pdev->dev, "%s: failed to find scale coefs\n",
+			__func__);
+		return;
+	}
+
 	for (i = 0; i < 8; i++) {
 		u32 h, hv;
 
@@ -2342,7 +2348,7 @@ static int dispc_ovl_calc_scaling_24xx(struct dispc_device *dispc,
 	}
 
 	if (in_width > maxsinglelinewidth) {
-		DSSERR("Cannot scale max input width exceeded");
+		DSSERR("Cannot scale max input width exceeded\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -2424,13 +2430,13 @@ again:
 	}
 
 	if (in_width > (maxsinglelinewidth * 2)) {
-		DSSERR("Cannot setup scaling");
-		DSSERR("width exceeds maximum width possible");
+		DSSERR("Cannot setup scaling\n");
+		DSSERR("width exceeds maximum width possible\n");
 		return -EINVAL;
 	}
 
 	if (in_width > maxsinglelinewidth && *five_taps) {
-		DSSERR("cannot setup scaling with five taps");
+		DSSERR("cannot setup scaling with five taps\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -2472,7 +2478,7 @@ static int dispc_ovl_calc_scaling_44xx(struct dispc_device *dispc,
 			in_width > maxsinglelinewidth && ++*decim_x);
 
 	if (in_width > maxsinglelinewidth) {
-		DSSERR("Cannot scale width exceeds max line width");
+		DSSERR("Cannot scale width exceeds max line width\n");
 		return -EINVAL;
 	}
 
@@ -2490,7 +2496,7 @@ static int dispc_ovl_calc_scaling_44xx(struct dispc_device *dispc,
 		 * bandwidth. Despite what theory says this appears to
 		 * be true also for 16-bit color formats.
 		 */
-		DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)", *decim_x);
+		DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)\n", *decim_x);
 
 		return -EINVAL;
 	}
@@ -4633,7 +4639,7 @@ static int dispc_errata_i734_wa_init(struct dispc_device *dispc)
 						i734_buf.size, &i734_buf.paddr,
 						GFP_KERNEL);
 	if (!i734_buf.vaddr) {
-		dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed",
+		dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed\n",
 			__func__);
 		return -ENOMEM;
 	}
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
index 97c88861d67a..5879f45f6fc9 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
@@ -679,7 +679,7 @@ static int hdmi_audio_config(struct device *dev,
 			     struct omap_dss_audio *dss_audio)
 {
 	struct omap_hdmi *hd = dev_get_drvdata(dev);
-	int ret;
+	int ret = 0;
 
 	mutex_lock(&hd->lock);
 
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
index 35ed2add6189..813ba42f2753 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
@@ -922,8 +922,13 @@ int hdmi4_core_init(struct platform_device *pdev, struct hdmi_core_data *core)
 {
 	const struct hdmi4_features *features;
 	struct resource *res;
+	const struct soc_device_attribute *soc;
 
-	features = soc_device_match(hdmi4_soc_devices)->data;
+	soc = soc_device_match(hdmi4_soc_devices);
+	if (!soc)
+		return -ENODEV;
+
+	features = soc->data;
 	core->cts_swmode = features->cts_swmode;
 	core->audio_use_mclk = features->audio_use_mclk;
 
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
index d28da9ac3e90..ae1a001d1b83 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
@@ -671,7 +671,7 @@ static int hdmi_audio_config(struct device *dev,
 			     struct omap_dss_audio *dss_audio)
 {
 	struct omap_hdmi *hd = dev_get_drvdata(dev);
-	int ret;
+	int ret = 0;
 
 	mutex_lock(&hd->lock);
 
diff --git a/drivers/gpu/drm/omapdrm/dss/sdi.c b/drivers/gpu/drm/omapdrm/dss/sdi.c
index 68a40ae26f5b..1e2c931f6acf 100644
--- a/drivers/gpu/drm/omapdrm/dss/sdi.c
+++ b/drivers/gpu/drm/omapdrm/dss/sdi.c
@@ -82,7 +82,7 @@ static int sdi_calc_clock_div(struct sdi_device *sdi, unsigned long pclk,
 			      struct dispc_clock_info *dispc_cinfo)
 {
 	int i;
-	struct sdi_clk_calc_ctx ctx = { .sdi = sdi };
+	struct sdi_clk_calc_ctx ctx;
 
 	/*
 	 * DSS fclk gives us very few possibilities, so finding a good pixel
@@ -95,6 +95,9 @@ static int sdi_calc_clock_div(struct sdi_device *sdi, unsigned long pclk,
 		bool ok;
 
 		memset(&ctx, 0, sizeof(ctx));
+
+		ctx.sdi = sdi;
+
 		if (pclk > 1000 * i * i * i)
 			ctx.pck_min = max(pclk - 1000 * i * i * i, 0lu);
 		else
diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c
index a0d7b1d905e8..5cde26ac937b 100644
--- a/drivers/gpu/drm/omapdrm/omap_connector.c
+++ b/drivers/gpu/drm/omapdrm/omap_connector.c
@@ -121,6 +121,9 @@ static int omap_connector_get_modes(struct drm_connector *connector)
 	if (dssdrv->read_edid) {
 		void *edid = kzalloc(MAX_EDID, GFP_KERNEL);
 
+		if (!edid)
+			return 0;
+
 		if ((dssdrv->read_edid(dssdev, edid, MAX_EDID) > 0) &&
 				drm_edid_is_valid(edid)) {
 			drm_mode_connector_update_edid_property(
@@ -139,6 +142,9 @@ static int omap_connector_get_modes(struct drm_connector *connector)
 		struct drm_display_mode *mode = drm_mode_create(dev);
 		struct videomode vm = {0};
 
+		if (!mode)
+			return 0;
+
 		dssdrv->get_timings(dssdev, &vm);
 
 		drm_display_mode_from_videomode(&vm, mode);
@@ -200,6 +206,10 @@ static int omap_connector_mode_valid(struct drm_connector *connector,
 	if (!r) {
 		/* check if vrefresh is still valid */
 		new_mode = drm_mode_duplicate(dev, mode);
+
+		if (!new_mode)
+			return MODE_BAD;
+
 		new_mode->clock = vm.pixelclock / 1000;
 		new_mode->vrefresh = 0;
 		if (mode->vrefresh == drm_mode_vrefresh(new_mode))
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index f9fa1c90b35c..401c02e9e6b2 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -401,12 +401,16 @@ int tiler_unpin(struct tiler_block *block)
 struct tiler_block *tiler_reserve_2d(enum tiler_fmt fmt, u16 w,
 		u16 h, u16 align)
 {
-	struct tiler_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
+	struct tiler_block *block;
 	u32 min_align = 128;
 	int ret;
 	unsigned long flags;
 	u32 slot_bytes;
 
+	block = kzalloc(sizeof(*block), GFP_KERNEL);
+	if (!block)
+		return ERR_PTR(-ENOMEM);
+
 	BUG_ON(!validfmt(fmt));
 
 	/* convert width/height to slots */
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 3632854c2b91..ef3b0e3571ec 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -319,6 +319,9 @@ static int omap_modeset_init(struct drm_device *dev)
 	dev->mode_config.max_width = 8192;
 	dev->mode_config.max_height = 8192;
 
+	/* We want the zpos to be normalized */
+	dev->mode_config.normalize_zpos = true;
+
 	dev->mode_config.funcs = &omap_mode_config_funcs;
 	dev->mode_config.helper_private = &omap_mode_config_helper_funcs;
 
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index 2899435cad6e..161233cbc9a0 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -65,7 +65,7 @@ static void omap_plane_atomic_update(struct drm_plane *plane,
 	info.rotation_type = OMAP_DSS_ROT_NONE;
 	info.rotation = DRM_MODE_ROTATE_0;
 	info.global_alpha = 0xff;
-	info.zorder = state->zpos;
+	info.zorder = state->normalized_zpos;
 
 	/* update scanout: */
 	omap_framebuffer_update_scanout(state->fb, state, &info);
diff --git a/drivers/gpu/drm/omapdrm/tcm-sita.c b/drivers/gpu/drm/omapdrm/tcm-sita.c
index d7f7bc9f061a..817be3c41863 100644
--- a/drivers/gpu/drm/omapdrm/tcm-sita.c
+++ b/drivers/gpu/drm/omapdrm/tcm-sita.c
@@ -90,7 +90,7 @@ static int l2r_t2b(u16 w, u16 h, u16 a, s16 offset,
 {
 	int i;
 	unsigned long index;
-	bool area_free;
+	bool area_free = false;
 	unsigned long slots_per_band = PAGE_SIZE / slot_bytes;
 	unsigned long bit_offset = (offset > 0) ? offset / slot_bytes : 0;
 	unsigned long curr_bit = bit_offset;
diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
index d964d454e4ae..2c9c9722734f 100644
--- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
+++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
@@ -238,12 +238,6 @@ static void rpi_touchscreen_i2c_write(struct rpi_touchscreen *ts,
 
 static int rpi_touchscreen_write(struct rpi_touchscreen *ts, u16 reg, u32 val)
 {
-#if 0
-	/* The firmware uses LP DSI transactions like this to bring up
-	 * the hardware, which should be faster than using I2C to then
-	 * pass to the Toshiba.  However, I was unable to get it to
-	 * work.
-	 */
 	u8 msg[] = {
 		reg,
 		reg >> 8,
@@ -253,13 +247,7 @@ static int rpi_touchscreen_write(struct rpi_touchscreen *ts, u16 reg, u32 val)
 		val >> 24,
 	};
 
-	mipi_dsi_dcs_write_buffer(ts->dsi, msg, sizeof(msg));
-#else
-	rpi_touchscreen_i2c_write(ts, REG_WR_ADDRH, reg >> 8);
-	rpi_touchscreen_i2c_write(ts, REG_WR_ADDRL, reg);
-	rpi_touchscreen_i2c_write(ts, REG_WRITEH, val >> 8);
-	rpi_touchscreen_i2c_write(ts, REG_WRITEL, val);
-#endif
+	mipi_dsi_generic_write(ts->dsi, msg, sizeof(msg));
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/pl111/Makefile b/drivers/gpu/drm/pl111/Makefile
index 9c5e8dba8ac6..19a8189dc54f 100644
--- a/drivers/gpu/drm/pl111/Makefile
+++ b/drivers/gpu/drm/pl111/Makefile
@@ -3,6 +3,7 @@ pl111_drm-y +=	pl111_display.o \
 		pl111_versatile.o \
 		pl111_drv.o
 
+pl111_drm-$(CONFIG_ARCH_VEXPRESS) += pl111_vexpress.o
 pl111_drm-$(CONFIG_DEBUG_FS) += pl111_debugfs.o
 
 obj-$(CONFIG_DRM_PL111) += pl111_drm.o
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 310646427907..19b0d006a54a 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -120,7 +120,8 @@ static int pl111_display_check(struct drm_simple_display_pipe *pipe,
 }
 
 static void pl111_display_enable(struct drm_simple_display_pipe *pipe,
-				 struct drm_crtc_state *cstate)
+				 struct drm_crtc_state *cstate,
+				 struct drm_plane_state *plane_state)
 {
 	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_plane *plane = &pipe->plane;
@@ -376,19 +377,13 @@ static void pl111_display_disable_vblank(struct drm_simple_display_pipe *pipe)
 	writel(0, priv->regs + priv->ienb);
 }
 
-static int pl111_display_prepare_fb(struct drm_simple_display_pipe *pipe,
-				    struct drm_plane_state *plane_state)
-{
-	return drm_gem_fb_prepare_fb(&pipe->plane, plane_state);
-}
-
 static struct drm_simple_display_pipe_funcs pl111_display_funcs = {
 	.mode_valid = pl111_mode_valid,
 	.check = pl111_display_check,
 	.enable = pl111_display_enable,
 	.disable = pl111_display_disable,
 	.update = pl111_display_update,
-	.prepare_fb = pl111_display_prepare_fb,
+	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
 };
 
 static int pl111_clk_div_choose_div(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h
index 8639b2d4ddf7..ce4501d0ab48 100644
--- a/drivers/gpu/drm/pl111/pl111_drm.h
+++ b/drivers/gpu/drm/pl111/pl111_drm.h
@@ -79,6 +79,7 @@ struct pl111_drm_dev_private {
 	const struct pl111_variant_data *variant;
 	void (*variant_display_enable) (struct drm_device *drm, u32 format);
 	void (*variant_display_disable) (struct drm_device *drm);
+	bool use_device_memory;
 };
 
 int pl111_display_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index 4621259d5387..454ff0804642 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -60,6 +60,7 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_graph.h>
+#include <linux/of_reserved_mem.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic_helper.h>
@@ -207,6 +208,24 @@ finish:
 	return ret;
 }
 
+static struct drm_gem_object *
+pl111_gem_import_sg_table(struct drm_device *dev,
+			  struct dma_buf_attachment *attach,
+			  struct sg_table *sgt)
+{
+	struct pl111_drm_dev_private *priv = dev->dev_private;
+
+	/*
+	 * When using device-specific reserved memory we can't import
+	 * DMA buffers: those are passed by reference in any global
+	 * memory and we can only handle a specific range of memory.
+	 */
+	if (priv->use_device_memory)
+		return ERR_PTR(-EINVAL);
+
+	return drm_gem_cma_prime_import_sg_table(dev, attach, sgt);
+}
+
 DEFINE_DRM_GEM_CMA_FOPS(drm_fops);
 
 static struct drm_driver pl111_drm_driver = {
@@ -227,7 +246,7 @@ static struct drm_driver pl111_drm_driver = {
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_import = drm_gem_prime_import,
-	.gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table,
+	.gem_prime_import_sg_table = pl111_gem_import_sg_table,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_get_sg_table	= drm_gem_cma_prime_get_sg_table,
 
@@ -257,6 +276,12 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 	drm->dev_private = priv;
 	priv->variant = variant;
 
+	ret = of_reserved_mem_device_init(dev);
+	if (!ret) {
+		dev_info(dev, "using device-specific reserved memory\n");
+		priv->use_device_memory = true;
+	}
+
 	if (of_property_read_u32(dev->of_node, "max-memory-bandwidth",
 				 &priv->memory_bw)) {
 		dev_info(dev, "no max memory bandwidth specified, assume unlimited\n");
@@ -275,7 +300,8 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 	priv->regs = devm_ioremap_resource(dev, &amba_dev->res);
 	if (IS_ERR(priv->regs)) {
 		dev_err(dev, "%s failed mmio\n", __func__);
-		return PTR_ERR(priv->regs);
+		ret = PTR_ERR(priv->regs);
+		goto dev_unref;
 	}
 
 	/* This may override some variant settings */
@@ -305,11 +331,14 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 
 dev_unref:
 	drm_dev_unref(drm);
+	of_reserved_mem_device_release(dev);
+
 	return ret;
 }
 
 static int pl111_amba_remove(struct amba_device *amba_dev)
 {
+	struct device *dev = &amba_dev->dev;
 	struct drm_device *drm = amba_get_drvdata(amba_dev);
 	struct pl111_drm_dev_private *priv = drm->dev_private;
 
@@ -319,6 +348,7 @@ static int pl111_amba_remove(struct amba_device *amba_dev)
 		drm_panel_bridge_remove(priv->bridge);
 	drm_mode_config_cleanup(drm);
 	drm_dev_unref(drm);
+	of_reserved_mem_device_release(dev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/pl111/pl111_versatile.c b/drivers/gpu/drm/pl111/pl111_versatile.c
index 9302f516045e..b9baefdba38a 100644
--- a/drivers/gpu/drm/pl111/pl111_versatile.c
+++ b/drivers/gpu/drm/pl111/pl111_versatile.c
@@ -1,12 +1,14 @@
 #include <linux/amba/clcd-regs.h>
 #include <linux/device.h>
 #include <linux/of.h>
+#include <linux/of_platform.h>
 #include <linux/regmap.h>
 #include <linux/mfd/syscon.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <drm/drmP.h>
 #include "pl111_versatile.h"
+#include "pl111_vexpress.h"
 #include "pl111_drm.h"
 
 static struct regmap *versatile_syscon_map;
@@ -22,6 +24,7 @@ enum versatile_clcd {
 	REALVIEW_CLCD_PB11MP,
 	REALVIEW_CLCD_PBA8,
 	REALVIEW_CLCD_PBX,
+	VEXPRESS_CLCD_V2M,
 };
 
 static const struct of_device_id versatile_clcd_of_match[] = {
@@ -53,6 +56,10 @@ static const struct of_device_id versatile_clcd_of_match[] = {
 		.compatible = "arm,realview-pbx-syscon",
 		.data = (void *)REALVIEW_CLCD_PBX,
 	},
+	{
+		.compatible = "arm,vexpress-muxfpga",
+		.data = (void *)VEXPRESS_CLCD_V2M,
+	},
 	{},
 };
 
@@ -286,12 +293,26 @@ static const struct pl111_variant_data pl111_realview = {
 	.fb_bpp = 16,
 };
 
+/*
+ * Versatile Express PL111 variant, again we just push the maximum
+ * BPP to 16 to be able to get 1024x768 without saturating the memory
+ * bus. The clockdivider also seems broken on the Versatile Express.
+ */
+static const struct pl111_variant_data pl111_vexpress = {
+	.name = "PL111 Versatile Express",
+	.formats = pl111_realview_pixel_formats,
+	.nformats = ARRAY_SIZE(pl111_realview_pixel_formats),
+	.fb_bpp = 16,
+	.broken_clockdivider = true,
+};
+
 int pl111_versatile_init(struct device *dev, struct pl111_drm_dev_private *priv)
 {
 	const struct of_device_id *clcd_id;
 	enum versatile_clcd versatile_clcd_type;
 	struct device_node *np;
 	struct regmap *map;
+	int ret;
 
 	np = of_find_matching_node_and_match(NULL, versatile_clcd_of_match,
 					     &clcd_id);
@@ -301,7 +322,33 @@ int pl111_versatile_init(struct device *dev, struct pl111_drm_dev_private *priv)
 	}
 	versatile_clcd_type = (enum versatile_clcd)clcd_id->data;
 
-	map = syscon_node_to_regmap(np);
+	/* Versatile Express special handling */
+	if (versatile_clcd_type == VEXPRESS_CLCD_V2M) {
+		struct platform_device *pdev;
+
+		/* Registers a driver for the muxfpga */
+		ret = vexpress_muxfpga_init();
+		if (ret) {
+			dev_err(dev, "unable to initialize muxfpga driver\n");
+			return ret;
+		}
+
+		/* Call into deep Vexpress configuration API */
+		pdev = of_find_device_by_node(np);
+		if (!pdev) {
+			dev_err(dev, "can't find the sysreg device, deferring\n");
+			return -EPROBE_DEFER;
+		}
+		map = dev_get_drvdata(&pdev->dev);
+		if (!map) {
+			dev_err(dev, "sysreg has not yet probed\n");
+			platform_device_put(pdev);
+			return -EPROBE_DEFER;
+		}
+	} else {
+		map = syscon_node_to_regmap(np);
+	}
+
 	if (IS_ERR(map)) {
 		dev_err(dev, "no Versatile syscon regmap\n");
 		return PTR_ERR(map);
@@ -340,6 +387,13 @@ int pl111_versatile_init(struct device *dev, struct pl111_drm_dev_private *priv)
 		priv->variant_display_disable = pl111_realview_clcd_disable;
 		dev_info(dev, "set up callbacks for RealView PL111\n");
 		break;
+	case VEXPRESS_CLCD_V2M:
+		priv->variant = &pl111_vexpress;
+		dev_info(dev, "initializing Versatile Express PL111\n");
+		ret = pl111_vexpress_clcd_init(dev, priv, map);
+		if (ret)
+			return ret;
+		break;
 	default:
 		dev_info(dev, "unknown Versatile system controller\n");
 		break;
diff --git a/drivers/gpu/drm/pl111/pl111_vexpress.c b/drivers/gpu/drm/pl111/pl111_vexpress.c
new file mode 100644
index 000000000000..a534b225e31b
--- /dev/null
+++ b/drivers/gpu/drm/pl111/pl111_vexpress.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Versatile Express PL111 handling
+ * Copyright (C) 2018 Linus Walleij
+ *
+ * This module binds to the "arm,vexpress-muxfpga" device on the
+ * Versatile Express configuration bus and sets up which CLCD instance
+ * gets muxed out on the DVI bridge.
+ */
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/vexpress.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include "pl111_drm.h"
+#include "pl111_vexpress.h"
+
+#define VEXPRESS_FPGAMUX_MOTHERBOARD		0x00
+#define VEXPRESS_FPGAMUX_DAUGHTERBOARD_1	0x01
+#define VEXPRESS_FPGAMUX_DAUGHTERBOARD_2	0x02
+
+int pl111_vexpress_clcd_init(struct device *dev,
+			     struct pl111_drm_dev_private *priv,
+			     struct regmap *map)
+{
+	struct device_node *root;
+	struct device_node *child;
+	struct device_node *ct_clcd = NULL;
+	bool has_coretile_clcd = false;
+	bool has_coretile_hdlcd = false;
+	bool mux_motherboard = true;
+	u32 val;
+	int ret;
+
+	/*
+	 * Check if we have a CLCD or HDLCD on the core tile by checking if a
+	 * CLCD or HDLCD is available in the root of the device tree.
+	 */
+	root = of_find_node_by_path("/");
+	if (!root)
+		return -EINVAL;
+
+	for_each_available_child_of_node(root, child) {
+		if (of_device_is_compatible(child, "arm,pl111")) {
+			has_coretile_clcd = true;
+			ct_clcd = child;
+			break;
+		}
+		if (of_device_is_compatible(child, "arm,hdlcd")) {
+			has_coretile_hdlcd = true;
+			break;
+		}
+	}
+
+	/*
+	 * If there is a coretile HDLCD and it has a driver,
+	 * do not mux the CLCD on the motherboard to the DVI.
+	 */
+	if (has_coretile_hdlcd && IS_ENABLED(CONFIG_DRM_HDLCD))
+		mux_motherboard = false;
+
+	/*
+	 * On the Vexpress CA9 we let the CLCD on the coretile
+	 * take precedence, so also in this case do not mux the
+	 * motherboard to the DVI.
+	 */
+	if (has_coretile_clcd)
+		mux_motherboard = false;
+
+	if (mux_motherboard) {
+		dev_info(dev, "DVI muxed to motherboard CLCD\n");
+		val = VEXPRESS_FPGAMUX_MOTHERBOARD;
+	} else if (ct_clcd == dev->of_node) {
+		dev_info(dev,
+			 "DVI muxed to daughterboard 1 (core tile) CLCD\n");
+		val = VEXPRESS_FPGAMUX_DAUGHTERBOARD_1;
+	} else {
+		dev_info(dev, "core tile graphics present\n");
+		dev_info(dev, "this device will be deactivated\n");
+		return -ENODEV;
+	}
+
+	ret = regmap_write(map, 0, val);
+	if (ret) {
+		dev_err(dev, "error setting DVI muxmode\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+/*
+ * This sets up the regmap pointer that will then be retrieved by
+ * the detection code in pl111_versatile.c and passed in to the
+ * pl111_vexpress_clcd_init() function above.
+ */
+static int vexpress_muxfpga_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct regmap *map;
+
+	map = devm_regmap_init_vexpress_config(&pdev->dev);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+	dev_set_drvdata(dev, map);
+
+	return 0;
+}
+
+static const struct of_device_id vexpress_muxfpga_match[] = {
+	{ .compatible = "arm,vexpress-muxfpga", }
+};
+
+static struct platform_driver vexpress_muxfpga_driver = {
+	.driver = {
+		.name = "vexpress-muxfpga",
+		.of_match_table = of_match_ptr(vexpress_muxfpga_match),
+	},
+	.probe = vexpress_muxfpga_probe,
+};
+
+int vexpress_muxfpga_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&vexpress_muxfpga_driver);
+	/* -EBUSY just means this driver is already registered */
+	if (ret == -EBUSY)
+		ret = 0;
+	return ret;
+}
diff --git a/drivers/gpu/drm/pl111/pl111_vexpress.h b/drivers/gpu/drm/pl111/pl111_vexpress.h
new file mode 100644
index 000000000000..5d3681bb4c00
--- /dev/null
+++ b/drivers/gpu/drm/pl111/pl111_vexpress.h
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+
+struct device;
+struct pl111_drm_dev_private;
+struct regmap;
+
+#ifdef CONFIG_ARCH_VEXPRESS
+
+int pl111_vexpress_clcd_init(struct device *dev,
+			     struct pl111_drm_dev_private *priv,
+			     struct regmap *map);
+
+int vexpress_muxfpga_init(void);
+
+#else
+
+static inline int pl111_vexpress_clcd_init(struct device *dev,
+					   struct pl111_drm_dev_private *priv,
+					   struct regmap *map)
+{
+	return -ENODEV;
+}
+
+static inline int vexpress_muxfpga_init(void)
+{
+	return 0;
+}
+
+#endif
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index c0fb52c6d4ca..208af9f37914 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -179,10 +179,9 @@ qxl_push_command_ring_release(struct qxl_device *qdev, struct qxl_release *relea
 			      uint32_t type, bool interruptible)
 {
 	struct qxl_command cmd;
-	struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
 
 	cmd.type = type;
-	cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset);
+	cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset);
 
 	return qxl_ring_push(qdev->command_ring, &cmd, interruptible);
 }
@@ -192,10 +191,9 @@ qxl_push_cursor_ring_release(struct qxl_device *qdev, struct qxl_release *releas
 			     uint32_t type, bool interruptible)
 {
 	struct qxl_command cmd;
-	struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
 
 	cmd.type = type;
-	cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset);
+	cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset);
 
 	return qxl_ring_push(qdev->cursor_ring, &cmd, interruptible);
 }
@@ -341,12 +339,9 @@ int qxl_io_update_area(struct qxl_device *qdev, struct qxl_bo *surf,
 	surface_height = surf->surf.height;
 
 	if (area->left < 0 || area->top < 0 ||
-	    area->right > surface_width || area->bottom > surface_height) {
-		qxl_io_log(qdev, "%s: not doing area update for "
-			   "%d, (%d,%d,%d,%d) (%d,%d)\n", __func__, surface_id, area->left,
-			   area->top, area->right, area->bottom, surface_width, surface_height);
+	    area->right > surface_width || area->bottom > surface_height)
 		return -EINVAL;
-	}
+
 	mutex_lock(&qdev->update_area_mutex);
 	qdev->ram_header->update_area = *area;
 	qdev->ram_header->update_surface = surface_id;
@@ -374,6 +369,7 @@ void qxl_io_flush_surfaces(struct qxl_device *qdev)
 void qxl_io_destroy_primary(struct qxl_device *qdev)
 {
 	wait_for_io_cmd(qdev, 0, QXL_IO_DESTROY_PRIMARY_ASYNC);
+	qdev->primary_created = false;
 }
 
 void qxl_io_create_primary(struct qxl_device *qdev,
@@ -399,6 +395,7 @@ void qxl_io_create_primary(struct qxl_device *qdev,
 	create->type = QXL_SURF_TYPE_PRIMARY;
 
 	wait_for_io_cmd(qdev, 0, QXL_IO_CREATE_PRIMARY_ASYNC);
+	qdev->primary_created = true;
 }
 
 void qxl_io_memslot_add(struct qxl_device *qdev, uint8_t id)
@@ -407,20 +404,6 @@ void qxl_io_memslot_add(struct qxl_device *qdev, uint8_t id)
 	wait_for_io_cmd(qdev, id, QXL_IO_MEMSLOT_ADD_ASYNC);
 }
 
-void qxl_io_log(struct qxl_device *qdev, const char *fmt, ...)
-{
-	va_list args;
-
-	va_start(args, fmt);
-	vsnprintf(qdev->ram_header->log_buf, QXL_LOG_BUF_SIZE, fmt, args);
-	va_end(args);
-	/*
-	 * DO not do a DRM output here - this will call printk, which will
-	 * call back into qxl for rendering (qxl_fb)
-	 */
-	outb(0, qdev->io_base + QXL_IO_LOG);
-}
-
 void qxl_io_reset(struct qxl_device *qdev)
 {
 	outb(0, qdev->io_base + QXL_IO_RESET);
@@ -428,19 +411,6 @@ void qxl_io_reset(struct qxl_device *qdev)
 
 void qxl_io_monitors_config(struct qxl_device *qdev)
 {
-	qxl_io_log(qdev, "%s: %d [%dx%d+%d+%d]\n", __func__,
-		   qdev->monitors_config ?
-		   qdev->monitors_config->count : -1,
-		   qdev->monitors_config && qdev->monitors_config->count ?
-		   qdev->monitors_config->heads[0].width : -1,
-		   qdev->monitors_config && qdev->monitors_config->count ?
-		   qdev->monitors_config->heads[0].height : -1,
-		   qdev->monitors_config && qdev->monitors_config->count ?
-		   qdev->monitors_config->heads[0].x : -1,
-		   qdev->monitors_config && qdev->monitors_config->count ?
-		   qdev->monitors_config->heads[0].y : -1
-		   );
-
 	wait_for_io_cmd(qdev, 0, QXL_IO_MONITORS_CONFIG_ASYNC);
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index ecb35ed0eac8..b8cda9449241 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -48,12 +48,8 @@ static void qxl_alloc_client_monitors_config(struct qxl_device *qdev, unsigned c
 		qdev->client_monitors_config = kzalloc(
 				sizeof(struct qxl_monitors_config) +
 				sizeof(struct qxl_head) * count, GFP_KERNEL);
-		if (!qdev->client_monitors_config) {
-			qxl_io_log(qdev,
-				   "%s: allocation failure for %u heads\n",
-				   __func__, count);
+		if (!qdev->client_monitors_config)
 			return;
-		}
 	}
 	qdev->client_monitors_config->count = count;
 }
@@ -74,12 +70,8 @@ static int qxl_display_copy_rom_client_monitors_config(struct qxl_device *qdev)
 	num_monitors = qdev->rom->client_monitors_config.count;
 	crc = crc32(0, (const uint8_t *)&qdev->rom->client_monitors_config,
 		  sizeof(qdev->rom->client_monitors_config));
-	if (crc != qdev->rom->client_monitors_config_crc) {
-		qxl_io_log(qdev, "crc mismatch: have %X (%zd) != %X\n", crc,
-			   sizeof(qdev->rom->client_monitors_config),
-			   qdev->rom->client_monitors_config_crc);
+	if (crc != qdev->rom->client_monitors_config_crc)
 		return MONITORS_CONFIG_BAD_CRC;
-	}
 	if (!num_monitors) {
 		DRM_DEBUG_KMS("no client monitors configured\n");
 		return status;
@@ -170,12 +162,10 @@ void qxl_display_read_client_monitors_config(struct qxl_device *qdev)
 		udelay(5);
 	}
 	if (status == MONITORS_CONFIG_BAD_CRC) {
-		qxl_io_log(qdev, "config: bad crc\n");
 		DRM_DEBUG_KMS("ignoring client monitors config: bad crc");
 		return;
 	}
 	if (status == MONITORS_CONFIG_UNCHANGED) {
-		qxl_io_log(qdev, "config: unchanged\n");
 		DRM_DEBUG_KMS("ignoring client monitors config: unchanged");
 		return;
 	}
@@ -268,6 +258,89 @@ static int qxl_add_common_modes(struct drm_connector *connector,
 	return i - 1;
 }
 
+static void qxl_send_monitors_config(struct qxl_device *qdev)
+{
+	int i;
+
+	BUG_ON(!qdev->ram_header->monitors_config);
+
+	if (qdev->monitors_config->count == 0)
+		return;
+
+	for (i = 0 ; i < qdev->monitors_config->count ; ++i) {
+		struct qxl_head *head = &qdev->monitors_config->heads[i];
+
+		if (head->y > 8192 || head->x > 8192 ||
+		    head->width > 8192 || head->height > 8192) {
+			DRM_ERROR("head %d wrong: %dx%d+%d+%d\n",
+				  i, head->width, head->height,
+				  head->x, head->y);
+			return;
+		}
+	}
+	qxl_io_monitors_config(qdev);
+}
+
+static void qxl_crtc_update_monitors_config(struct drm_crtc *crtc,
+					    const char *reason)
+{
+	struct drm_device *dev = crtc->dev;
+	struct qxl_device *qdev = dev->dev_private;
+	struct qxl_crtc *qcrtc = to_qxl_crtc(crtc);
+	struct qxl_head head;
+	int oldcount, i = qcrtc->index;
+
+	if (!qdev->primary_created) {
+		DRM_DEBUG_KMS("no primary surface, skip (%s)\n", reason);
+		return;
+	}
+
+	if (!qdev->monitors_config ||
+	    qdev->monitors_config->max_allowed <= i)
+		return;
+
+	head.id = i;
+	head.flags = 0;
+	oldcount = qdev->monitors_config->count;
+	if (crtc->state->active) {
+		struct drm_display_mode *mode = &crtc->mode;
+		head.width = mode->hdisplay;
+		head.height = mode->vdisplay;
+		head.x = crtc->x;
+		head.y = crtc->y;
+		if (qdev->monitors_config->count < i + 1)
+			qdev->monitors_config->count = i + 1;
+	} else if (i > 0) {
+		head.width = 0;
+		head.height = 0;
+		head.x = 0;
+		head.y = 0;
+		if (qdev->monitors_config->count == i + 1)
+			qdev->monitors_config->count = i;
+	} else {
+		DRM_DEBUG_KMS("inactive head 0, skip (%s)\n", reason);
+		return;
+	}
+
+	if (head.width  == qdev->monitors_config->heads[i].width  &&
+	    head.height == qdev->monitors_config->heads[i].height &&
+	    head.x      == qdev->monitors_config->heads[i].x      &&
+	    head.y      == qdev->monitors_config->heads[i].y      &&
+	    oldcount    == qdev->monitors_config->count)
+		return;
+
+	DRM_DEBUG_KMS("head %d, %dx%d, at +%d+%d, %s (%s)\n",
+		      i, head.width, head.height, head.x, head.y,
+		      crtc->state->active ? "on" : "off", reason);
+	if (oldcount != qdev->monitors_config->count)
+		DRM_DEBUG_KMS("active heads %d -> %d (%d total)\n",
+			      oldcount, qdev->monitors_config->count,
+			      qdev->monitors_config->max_allowed);
+
+	qdev->monitors_config->heads[i] = head;
+	qxl_send_monitors_config(qdev);
+}
+
 static void qxl_crtc_atomic_flush(struct drm_crtc *crtc,
 				  struct drm_crtc_state *old_crtc_state)
 {
@@ -283,6 +356,8 @@ static void qxl_crtc_atomic_flush(struct drm_crtc *crtc,
 		drm_crtc_send_vblank_event(crtc, event);
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
+
+	qxl_crtc_update_monitors_config(crtc, "flush");
 }
 
 static void qxl_crtc_destroy(struct drm_crtc *crtc)
@@ -381,95 +456,19 @@ qxl_framebuffer_init(struct drm_device *dev,
 	return 0;
 }
 
-static bool qxl_crtc_mode_fixup(struct drm_crtc *crtc,
-				  const struct drm_display_mode *mode,
-				  struct drm_display_mode *adjusted_mode)
-{
-	struct drm_device *dev = crtc->dev;
-	struct qxl_device *qdev = dev->dev_private;
-
-	qxl_io_log(qdev, "%s: (%d,%d) => (%d,%d)\n",
-		   __func__,
-		   mode->hdisplay, mode->vdisplay,
-		   adjusted_mode->hdisplay,
-		   adjusted_mode->vdisplay);
-	return true;
-}
-
-static void
-qxl_send_monitors_config(struct qxl_device *qdev)
-{
-	int i;
-
-	BUG_ON(!qdev->ram_header->monitors_config);
-
-	if (qdev->monitors_config->count == 0) {
-		qxl_io_log(qdev, "%s: 0 monitors??\n", __func__);
-		return;
-	}
-	for (i = 0 ; i < qdev->monitors_config->count ; ++i) {
-		struct qxl_head *head = &qdev->monitors_config->heads[i];
-
-		if (head->y > 8192 || head->x > 8192 ||
-		    head->width > 8192 || head->height > 8192) {
-			DRM_ERROR("head %d wrong: %dx%d+%d+%d\n",
-				  i, head->width, head->height,
-				  head->x, head->y);
-			return;
-		}
-	}
-	qxl_io_monitors_config(qdev);
-}
-
-static void qxl_monitors_config_set(struct qxl_device *qdev,
-				    int index,
-				    unsigned x, unsigned y,
-				    unsigned width, unsigned height,
-				    unsigned surf_id)
-{
-	DRM_DEBUG_KMS("%d:%dx%d+%d+%d\n", index, width, height, x, y);
-	qdev->monitors_config->heads[index].x = x;
-	qdev->monitors_config->heads[index].y = y;
-	qdev->monitors_config->heads[index].width = width;
-	qdev->monitors_config->heads[index].height = height;
-	qdev->monitors_config->heads[index].surface_id = surf_id;
-
-}
-
-static void qxl_mode_set_nofb(struct drm_crtc *crtc)
-{
-	struct qxl_device *qdev = crtc->dev->dev_private;
-	struct qxl_crtc *qcrtc = to_qxl_crtc(crtc);
-	struct drm_display_mode *mode = &crtc->mode;
-
-	DRM_DEBUG("Mode set (%d,%d)\n",
-		  mode->hdisplay, mode->vdisplay);
-
-	qxl_monitors_config_set(qdev, qcrtc->index, 0, 0,
-				mode->hdisplay,	mode->vdisplay, 0);
-
-}
-
 static void qxl_crtc_atomic_enable(struct drm_crtc *crtc,
 				   struct drm_crtc_state *old_state)
 {
-	DRM_DEBUG("\n");
+	qxl_crtc_update_monitors_config(crtc, "enable");
 }
 
 static void qxl_crtc_atomic_disable(struct drm_crtc *crtc,
 				    struct drm_crtc_state *old_state)
 {
-	struct qxl_crtc *qcrtc = to_qxl_crtc(crtc);
-	struct qxl_device *qdev = crtc->dev->dev_private;
-
-	qxl_monitors_config_set(qdev, qcrtc->index, 0, 0, 0, 0, 0);
-
-	qxl_send_monitors_config(qdev);
+	qxl_crtc_update_monitors_config(crtc, "disable");
 }
 
 static const struct drm_crtc_helper_funcs qxl_crtc_helper_funcs = {
-	.mode_fixup = qxl_crtc_mode_fixup,
-	.mode_set_nofb = qxl_mode_set_nofb,
 	.atomic_flush = qxl_crtc_atomic_flush,
 	.atomic_enable = qxl_crtc_atomic_enable,
 	.atomic_disable = qxl_crtc_atomic_disable,
@@ -613,12 +612,6 @@ static void qxl_primary_atomic_disable(struct drm_plane *plane,
 	}
 }
 
-static int qxl_plane_atomic_check(struct drm_plane *plane,
-				  struct drm_plane_state *state)
-{
-	return 0;
-}
-
 static void qxl_cursor_atomic_update(struct drm_plane *plane,
 				     struct drm_plane_state *old_state)
 {
@@ -824,7 +817,6 @@ static const uint32_t qxl_cursor_plane_formats[] = {
 };
 
 static const struct drm_plane_helper_funcs qxl_cursor_helper_funcs = {
-	.atomic_check = qxl_plane_atomic_check,
 	.atomic_update = qxl_cursor_atomic_update,
 	.atomic_disable = qxl_cursor_atomic_disable,
 	.prepare_fb = qxl_plane_prepare_fb,
@@ -949,81 +941,6 @@ free_mem:
 	return r;
 }
 
-static void qxl_enc_dpms(struct drm_encoder *encoder, int mode)
-{
-	DRM_DEBUG("\n");
-}
-
-static void qxl_enc_prepare(struct drm_encoder *encoder)
-{
-	DRM_DEBUG("\n");
-}
-
-static void qxl_write_monitors_config_for_encoder(struct qxl_device *qdev,
-		struct drm_encoder *encoder)
-{
-	int i;
-	struct qxl_output *output = drm_encoder_to_qxl_output(encoder);
-	struct qxl_head *head;
-	struct drm_display_mode *mode;
-
-	BUG_ON(!encoder);
-	/* TODO: ugly, do better */
-	i = output->index;
-	if (!qdev->monitors_config ||
-	    qdev->monitors_config->max_allowed <= i) {
-		DRM_ERROR(
-		"head number too large or missing monitors config: %p, %d",
-		qdev->monitors_config,
-		qdev->monitors_config ?
-			qdev->monitors_config->max_allowed : -1);
-		return;
-	}
-	if (!encoder->crtc) {
-		DRM_ERROR("missing crtc on encoder %p\n", encoder);
-		return;
-	}
-	if (i != 0)
-		DRM_DEBUG("missing for multiple monitors: no head holes\n");
-	head = &qdev->monitors_config->heads[i];
-	head->id = i;
-	if (encoder->crtc->enabled) {
-		mode = &encoder->crtc->mode;
-		head->width = mode->hdisplay;
-		head->height = mode->vdisplay;
-		head->x = encoder->crtc->x;
-		head->y = encoder->crtc->y;
-		if (qdev->monitors_config->count < i + 1)
-			qdev->monitors_config->count = i + 1;
-	} else {
-		head->width = 0;
-		head->height = 0;
-		head->x = 0;
-		head->y = 0;
-	}
-	DRM_DEBUG_KMS("setting head %d to +%d+%d %dx%d out of %d\n",
-		      i, head->x, head->y, head->width, head->height, qdev->monitors_config->count);
-	head->flags = 0;
-	/* TODO - somewhere else to call this for multiple monitors
-	 * (config_commit?) */
-	qxl_send_monitors_config(qdev);
-}
-
-static void qxl_enc_commit(struct drm_encoder *encoder)
-{
-	struct qxl_device *qdev = encoder->dev->dev_private;
-
-	qxl_write_monitors_config_for_encoder(qdev, encoder);
-	DRM_DEBUG("\n");
-}
-
-static void qxl_enc_mode_set(struct drm_encoder *encoder,
-				struct drm_display_mode *mode,
-				struct drm_display_mode *adjusted_mode)
-{
-	DRM_DEBUG("\n");
-}
-
 static int qxl_conn_get_modes(struct drm_connector *connector)
 {
 	unsigned pwidth = 1024;
@@ -1037,7 +954,7 @@ static int qxl_conn_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static int qxl_conn_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status qxl_conn_mode_valid(struct drm_connector *connector,
 			       struct drm_display_mode *mode)
 {
 	struct drm_device *ddev = connector->dev;
@@ -1069,10 +986,6 @@ static struct drm_encoder *qxl_best_encoder(struct drm_connector *connector)
 
 
 static const struct drm_encoder_helper_funcs qxl_enc_helper_funcs = {
-	.dpms = qxl_enc_dpms,
-	.prepare = qxl_enc_prepare,
-	.mode_set = qxl_enc_mode_set,
-	.commit = qxl_enc_commit,
 };
 
 static const struct drm_connector_helper_funcs qxl_connector_helper_funcs = {
@@ -1100,21 +1013,11 @@ static enum drm_connector_status qxl_conn_detect(
 		     qxl_head_enabled(&qdev->client_monitors_config->heads[output->index]);
 
 	DRM_DEBUG("#%d connected: %d\n", output->index, connected);
-	if (!connected)
-		qxl_monitors_config_set(qdev, output->index, 0, 0, 0, 0, 0);
 
 	return connected ? connector_status_connected
 			 : connector_status_disconnected;
 }
 
-static int qxl_conn_set_property(struct drm_connector *connector,
-				   struct drm_property *property,
-				   uint64_t value)
-{
-	DRM_DEBUG("\n");
-	return 0;
-}
-
 static void qxl_conn_destroy(struct drm_connector *connector)
 {
 	struct qxl_output *qxl_output =
@@ -1129,7 +1032,6 @@ static const struct drm_connector_funcs qxl_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.detect = qxl_conn_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
-	.set_property = qxl_conn_set_property,
 	.destroy = qxl_conn_destroy,
 	.reset = drm_atomic_helper_connector_reset,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 00a1a66b052a..01220d386b0a 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -167,6 +167,7 @@ struct qxl_release {
 
 	int id;
 	int type;
+	struct qxl_bo *release_bo;
 	uint32_t release_offset;
 	uint32_t surface_release_id;
 	struct ww_acquire_ctx ticket;
@@ -298,9 +299,6 @@ struct qxl_device {
 	int monitors_config_height;
 };
 
-/* forward declaration for QXL_INFO_IO */
-__printf(2,3) void qxl_io_log(struct qxl_device *qdev, const char *fmt, ...);
-
 extern const struct drm_ioctl_desc qxl_ioctls[];
 extern int qxl_max_ioctl;
 
diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c
index 338891401f35..9a6752606079 100644
--- a/drivers/gpu/drm/qxl/qxl_fb.c
+++ b/drivers/gpu/drm/qxl/qxl_fb.c
@@ -185,8 +185,6 @@ static int qxlfb_framebuffer_dirty(struct drm_framebuffer *fb,
 	/*
 	 * we are using a shadow draw buffer, at qdev->surface0_shadow
 	 */
-	qxl_io_log(qdev, "dirty x[%d, %d], y[%d, %d]\n", clips->x1, clips->x2,
-		   clips->y1, clips->y2);
 	image->dx = clips->x1;
 	image->dy = clips->y1;
 	image->width = clips->x2 - clips->x1;
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index e238a1a2eca1..6cc9f3367fa0 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -182,9 +182,9 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 		goto out_free_reloc;
 
 	/* TODO copy slow path code from i915 */
-	fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_SIZE));
+	fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_MASK));
 	unwritten = __copy_from_user_inatomic_nocache
-		(fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_SIZE),
+		(fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_MASK),
 		 u64_to_user_ptr(cmd->command), cmd->command_size);
 
 	{
diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c
index 23a40106ab53..3bb31add6350 100644
--- a/drivers/gpu/drm/qxl/qxl_irq.c
+++ b/drivers/gpu/drm/qxl/qxl_irq.c
@@ -57,10 +57,9 @@ irqreturn_t qxl_irq_handler(int irq, void *arg)
 		 * to avoid endless loops).
 		 */
 		qdev->irq_received_error++;
-		qxl_io_log(qdev, "%s: driver is in bug mode.\n", __func__);
+		DRM_WARN("driver is in bug mode\n");
 	}
 	if (pending & QXL_INTERRUPT_CLIENT_MONITORS_CONFIG) {
-		qxl_io_log(qdev, "QXL_INTERRUPT_CLIENT_MONITORS_CONFIG\n");
 		schedule_work(&qdev->client_monitors_config_work);
 	}
 	qdev->ram_header->int_mask = QXL_INTERRUPT_MASK;
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 5d84a66fed36..7cb214577275 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -173,6 +173,7 @@ qxl_release_free_list(struct qxl_release *release)
 		list_del(&entry->tv.head);
 		kfree(entry);
 	}
+	release->release_bo = NULL;
 }
 
 void
@@ -296,7 +297,6 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev,
 {
 	if (surface_cmd_type == QXL_SURFACE_CMD_DESTROY && create_rel) {
 		int idr_ret;
-		struct qxl_bo_list *entry = list_first_entry(&create_rel->bos, struct qxl_bo_list, tv.head);
 		struct qxl_bo *bo;
 		union qxl_release_info *info;
 
@@ -304,8 +304,9 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev,
 		idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release);
 		if (idr_ret < 0)
 			return idr_ret;
-		bo = to_qxl_bo(entry->tv.bo);
+		bo = create_rel->release_bo;
 
+		(*release)->release_bo = bo;
 		(*release)->release_offset = create_rel->release_offset + 64;
 
 		qxl_release_list_add(*release, bo);
@@ -365,6 +366,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 
 	bo = qxl_bo_ref(qdev->current_release_bo[cur_idx]);
 
+	(*release)->release_bo = bo;
 	(*release)->release_offset = qdev->current_release_bo_offset[cur_idx] * release_size_per_bo[cur_idx];
 	qdev->current_release_bo_offset[cur_idx]++;
 
@@ -408,13 +410,12 @@ union qxl_release_info *qxl_release_map(struct qxl_device *qdev,
 {
 	void *ptr;
 	union qxl_release_info *info;
-	struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
-	struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
+	struct qxl_bo *bo = release->release_bo;
 
-	ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_SIZE);
+	ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_MASK);
 	if (!ptr)
 		return NULL;
-	info = ptr + (release->release_offset & ~PAGE_SIZE);
+	info = ptr + (release->release_offset & ~PAGE_MASK);
 	return info;
 }
 
@@ -422,11 +423,10 @@ void qxl_release_unmap(struct qxl_device *qdev,
 		       struct qxl_release *release,
 		       union qxl_release_info *info)
 {
-	struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
-	struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
+	struct qxl_bo *bo = release->release_bo;
 	void *ptr;
 
-	ptr = ((void *)info) - (release->release_offset & ~PAGE_SIZE);
+	ptr = ((void *)info) - (release->release_offset & ~PAGE_MASK);
 	qxl_bo_kunmap_atomic_page(qdev, bo, ptr);
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index ee2340e31f06..86a1fb32f6db 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -105,16 +105,16 @@ static void qxl_ttm_global_fini(struct qxl_device *qdev)
 static struct vm_operations_struct qxl_ttm_vm_ops;
 static const struct vm_operations_struct *ttm_vm_ops;
 
-static int qxl_ttm_fault(struct vm_fault *vmf)
+static vm_fault_t qxl_ttm_fault(struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *bo;
-	int r;
+	vm_fault_t ret;
 
 	bo = (struct ttm_buffer_object *)vmf->vma->vm_private_data;
 	if (bo == NULL)
 		return VM_FAULT_NOPAGE;
-	r = ttm_vm_ops->fault(vmf);
-	return r;
+	ret = ttm_vm_ops->fault(vmf);
+	return ret;
 }
 
 int qxl_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 02baaaf20e9d..efbd5816082d 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1145,7 +1145,6 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct radeon_framebuffer *radeon_fb;
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct radeon_bo *rbo;
@@ -1164,19 +1163,15 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 		return 0;
 	}
 
-	if (atomic) {
-		radeon_fb = to_radeon_framebuffer(fb);
+	if (atomic)
 		target_fb = fb;
-	}
-	else {
-		radeon_fb = to_radeon_framebuffer(crtc->primary->fb);
+	else
 		target_fb = crtc->primary->fb;
-	}
 
 	/* If atomic, assume fb object is pinned & idle & fenced and
 	 * just update base pointers
 	 */
-	obj = radeon_fb->obj;
+	obj = target_fb->obj[0];
 	rbo = gem_to_radeon_bo(obj);
 	r = radeon_bo_reserve(rbo, false);
 	if (unlikely(r != 0))
@@ -1441,8 +1436,7 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(EVERGREEN_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 0);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
-		radeon_fb = to_radeon_framebuffer(fb);
-		rbo = gem_to_radeon_bo(radeon_fb->obj);
+		rbo = gem_to_radeon_bo(fb->obj[0]);
 		r = radeon_bo_reserve(rbo, false);
 		if (unlikely(r != 0))
 			return r;
@@ -1463,7 +1457,6 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct radeon_framebuffer *radeon_fb;
 	struct drm_gem_object *obj;
 	struct radeon_bo *rbo;
 	struct drm_framebuffer *target_fb;
@@ -1481,16 +1474,12 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 		return 0;
 	}
 
-	if (atomic) {
-		radeon_fb = to_radeon_framebuffer(fb);
+	if (atomic)
 		target_fb = fb;
-	}
-	else {
-		radeon_fb = to_radeon_framebuffer(crtc->primary->fb);
+	else
 		target_fb = crtc->primary->fb;
-	}
 
-	obj = radeon_fb->obj;
+	obj = target_fb->obj[0];
 	rbo = gem_to_radeon_bo(obj);
 	r = radeon_bo_reserve(rbo, false);
 	if (unlikely(r != 0))
@@ -1641,8 +1630,7 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 3);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
-		radeon_fb = to_radeon_framebuffer(fb);
-		rbo = gem_to_radeon_bo(radeon_fb->obj);
+		rbo = gem_to_radeon_bo(fb->obj[0]);
 		r = radeon_bo_reserve(rbo, false);
 		if (unlikely(r != 0))
 			return r;
@@ -2149,11 +2137,9 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 	if (crtc->primary->fb) {
 		int r;
-		struct radeon_framebuffer *radeon_fb;
 		struct radeon_bo *rbo;
 
-		radeon_fb = to_radeon_framebuffer(crtc->primary->fb);
-		rbo = gem_to_radeon_bo(radeon_fb->obj);
+		rbo = gem_to_radeon_bo(crtc->primary->fb->obj[0]);
 		r = radeon_bo_reserve(rbo, false);
 		if (unlikely(r))
 			DRM_ERROR("failed to reserve rbo before unpin\n");
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 40be4068ca69..fa5fadaa9bbb 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -526,7 +526,7 @@ static int radeon_atpx_init(void)
  * look up whether we are the integrated or discrete GPU (all asics).
  * Returns the client id.
  */
-static int radeon_atpx_get_client_id(struct pci_dev *pdev)
+static enum vga_switcheroo_client_id radeon_atpx_get_client_id(struct pci_dev *pdev)
 {
 	if (radeon_atpx_priv.dhandle == ACPI_HANDLE(&pdev->dev))
 		return VGA_SWITCHEROO_IGD;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index df9469a8fdb1..2aea2bdff99b 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -852,7 +852,7 @@ static int radeon_lvds_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static int radeon_lvds_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status radeon_lvds_mode_valid(struct drm_connector *connector,
 				  struct drm_display_mode *mode)
 {
 	struct drm_encoder *encoder = radeon_best_single_encoder(connector);
@@ -1012,7 +1012,7 @@ static int radeon_vga_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static int radeon_vga_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status radeon_vga_mode_valid(struct drm_connector *connector,
 				  struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
@@ -1156,7 +1156,7 @@ static int radeon_tv_get_modes(struct drm_connector *connector)
 	return 1;
 }
 
-static int radeon_tv_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status radeon_tv_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
 	if ((mode->hdisplay > 1024) || (mode->vdisplay > 768))
@@ -1498,7 +1498,7 @@ static void radeon_dvi_force(struct drm_connector *connector)
 		radeon_connector->use_digital = true;
 }
 
-static int radeon_dvi_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status radeon_dvi_mode_valid(struct drm_connector *connector,
 				  struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
@@ -1800,7 +1800,7 @@ out:
 	return ret;
 }
 
-static int radeon_dp_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status radeon_dp_mode_valid(struct drm_connector *connector,
 				  struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 48d0e6bd0508..59c8a6647ff2 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1591,7 +1591,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
 	/* unpin the front buffers and cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-		struct radeon_framebuffer *rfb = to_radeon_framebuffer(crtc->primary->fb);
+		struct drm_framebuffer *fb = crtc->primary->fb;
 		struct radeon_bo *robj;
 
 		if (radeon_crtc->cursor_bo) {
@@ -1603,10 +1603,10 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
 			}
 		}
 
-		if (rfb == NULL || rfb->obj == NULL) {
+		if (fb == NULL || fb->obj[0] == NULL) {
 			continue;
 		}
-		robj = gem_to_radeon_bo(rfb->obj);
+		robj = gem_to_radeon_bo(fb->obj[0]);
 		/* don't unpin kernel fb objects */
 		if (!radeon_fbdev_robj_is_fb(rdev, robj)) {
 			r = radeon_bo_reserve(robj, false);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 26129b2b082d..9d3ac8b981da 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -32,6 +32,7 @@
 
 #include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_edid.h>
@@ -478,8 +479,6 @@ static int radeon_crtc_page_flip_target(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-	struct radeon_framebuffer *old_radeon_fb;
-	struct radeon_framebuffer *new_radeon_fb;
 	struct drm_gem_object *obj;
 	struct radeon_flip_work *work;
 	struct radeon_bo *new_rbo;
@@ -501,15 +500,13 @@ static int radeon_crtc_page_flip_target(struct drm_crtc *crtc,
 	work->async = (page_flip_flags & DRM_MODE_PAGE_FLIP_ASYNC) != 0;
 
 	/* schedule unpin of the old buffer */
-	old_radeon_fb = to_radeon_framebuffer(crtc->primary->fb);
-	obj = old_radeon_fb->obj;
+	obj = crtc->primary->fb->obj[0];
 
 	/* take a reference to the old object */
 	drm_gem_object_get(obj);
 	work->old_rbo = gem_to_radeon_bo(obj);
 
-	new_radeon_fb = to_radeon_framebuffer(fb);
-	obj = new_radeon_fb->obj;
+	obj = fb->obj[0];
 	new_rbo = gem_to_radeon_bo(obj);
 
 	/* pin the new buffer */
@@ -1285,41 +1282,23 @@ void radeon_compute_pll_legacy(struct radeon_pll *pll,
 
 }
 
-static void radeon_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct radeon_framebuffer *radeon_fb = to_radeon_framebuffer(fb);
-
-	drm_gem_object_put_unlocked(radeon_fb->obj);
-	drm_framebuffer_cleanup(fb);
-	kfree(radeon_fb);
-}
-
-static int radeon_user_framebuffer_create_handle(struct drm_framebuffer *fb,
-						  struct drm_file *file_priv,
-						  unsigned int *handle)
-{
-	struct radeon_framebuffer *radeon_fb = to_radeon_framebuffer(fb);
-
-	return drm_gem_handle_create(file_priv, radeon_fb->obj, handle);
-}
-
 static const struct drm_framebuffer_funcs radeon_fb_funcs = {
-	.destroy = radeon_user_framebuffer_destroy,
-	.create_handle = radeon_user_framebuffer_create_handle,
+	.destroy = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
 };
 
 int
 radeon_framebuffer_init(struct drm_device *dev,
-			struct radeon_framebuffer *rfb,
+			struct drm_framebuffer *fb,
 			const struct drm_mode_fb_cmd2 *mode_cmd,
 			struct drm_gem_object *obj)
 {
 	int ret;
-	rfb->obj = obj;
-	drm_helper_mode_fill_fb_struct(dev, &rfb->base, mode_cmd);
-	ret = drm_framebuffer_init(dev, &rfb->base, &radeon_fb_funcs);
+	fb->obj[0] = obj;
+	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
+	ret = drm_framebuffer_init(dev, fb, &radeon_fb_funcs);
 	if (ret) {
-		rfb->obj = NULL;
+		fb->obj[0] = NULL;
 		return ret;
 	}
 	return 0;
@@ -1331,7 +1310,7 @@ radeon_user_framebuffer_create(struct drm_device *dev,
 			       const struct drm_mode_fb_cmd2 *mode_cmd)
 {
 	struct drm_gem_object *obj;
-	struct radeon_framebuffer *radeon_fb;
+	struct drm_framebuffer *fb;
 	int ret;
 
 	obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[0]);
@@ -1347,20 +1326,20 @@ radeon_user_framebuffer_create(struct drm_device *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	radeon_fb = kzalloc(sizeof(*radeon_fb), GFP_KERNEL);
-	if (radeon_fb == NULL) {
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (fb == NULL) {
 		drm_gem_object_put_unlocked(obj);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	ret = radeon_framebuffer_init(dev, radeon_fb, mode_cmd, obj);
+	ret = radeon_framebuffer_init(dev, fb, mode_cmd, obj);
 	if (ret) {
-		kfree(radeon_fb);
+		kfree(fb);
 		drm_gem_object_put_unlocked(obj);
 		return ERR_PTR(ret);
 	}
 
-	return &radeon_fb->base;
+	return fb;
 }
 
 static const struct drm_mode_config_funcs radeon_mode_funcs = {
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index b28288a781ef..2a7977a23b31 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -168,7 +168,12 @@ int radeon_no_wb;
 int radeon_modeset = -1;
 int radeon_dynclks = -1;
 int radeon_r4xx_atom = 0;
+#ifdef __powerpc__
+/* Default to PCI on PowerPC (fdo #95017) */
+int radeon_agpmode = -1;
+#else
 int radeon_agpmode = 0;
+#endif
 int radeon_vram_limit = 0;
 int radeon_gart_size = -1; /* auto */
 int radeon_benchmarking = 0;
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 57c5404a1654..1179034024ae 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -43,7 +43,7 @@
  */
 struct radeon_fbdev {
 	struct drm_fb_helper helper;
-	struct radeon_framebuffer rfb;
+	struct drm_framebuffer fb;
 	struct radeon_device *rdev;
 };
 
@@ -246,13 +246,13 @@ static int radeonfb_create(struct drm_fb_helper *helper,
 
 	info->par = rfbdev;
 
-	ret = radeon_framebuffer_init(rdev->ddev, &rfbdev->rfb, &mode_cmd, gobj);
+	ret = radeon_framebuffer_init(rdev->ddev, &rfbdev->fb, &mode_cmd, gobj);
 	if (ret) {
 		DRM_ERROR("failed to initialize framebuffer %d\n", ret);
 		goto out;
 	}
 
-	fb = &rfbdev->rfb.base;
+	fb = &rfbdev->fb;
 
 	/* setup helper */
 	rfbdev->helper.fb = fb;
@@ -308,15 +308,15 @@ out:
 
 static int radeon_fbdev_destroy(struct drm_device *dev, struct radeon_fbdev *rfbdev)
 {
-	struct radeon_framebuffer *rfb = &rfbdev->rfb;
+	struct drm_framebuffer *fb = &rfbdev->fb;
 
 	drm_fb_helper_unregister_fbi(&rfbdev->helper);
 
-	if (rfb->obj) {
-		radeonfb_destroy_pinned_object(rfb->obj);
-		rfb->obj = NULL;
-		drm_framebuffer_unregister_private(&rfb->base);
-		drm_framebuffer_cleanup(&rfb->base);
+	if (fb->obj[0]) {
+		radeonfb_destroy_pinned_object(fb->obj[0]);
+		fb->obj[0] = NULL;
+		drm_framebuffer_unregister_private(fb);
+		drm_framebuffer_cleanup(fb);
 	}
 	drm_fb_helper_fini(&rfbdev->helper);
 
@@ -400,7 +400,7 @@ bool radeon_fbdev_robj_is_fb(struct radeon_device *rdev, struct radeon_bo *robj)
 	if (!rdev->mode_info.rfbdev)
 		return false;
 
-	if (robj == gem_to_radeon_bo(rdev->mode_info.rfbdev->rfb.obj))
+	if (robj == gem_to_radeon_bo(rdev->mode_info.rfbdev->fb.obj[0]))
 		return true;
 	return false;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index 1f1856e0b1e0..35a205ae4318 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -374,7 +374,6 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-	struct radeon_framebuffer *radeon_fb;
 	struct drm_framebuffer *target_fb;
 	struct drm_gem_object *obj;
 	struct radeon_bo *rbo;
@@ -393,14 +392,10 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 		return 0;
 	}
 
-	if (atomic) {
-		radeon_fb = to_radeon_framebuffer(fb);
+	if (atomic)
 		target_fb = fb;
-	}
-	else {
-		radeon_fb = to_radeon_framebuffer(crtc->primary->fb);
+	else
 		target_fb = crtc->primary->fb;
-	}
 
 	switch (target_fb->format->cpp[0] * 8) {
 	case 8:
@@ -423,7 +418,7 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 	}
 
 	/* Pin framebuffer & get tilling informations */
-	obj = radeon_fb->obj;
+	obj = target_fb->obj[0];
 	rbo = gem_to_radeon_bo(obj);
 retry:
 	r = radeon_bo_reserve(rbo, false);
@@ -451,7 +446,7 @@ retry:
 			struct radeon_bo *old_rbo;
 			unsigned long nsize, osize;
 
-			old_rbo = gem_to_radeon_bo(to_radeon_framebuffer(fb)->obj);
+			old_rbo = gem_to_radeon_bo(fb->obj[0]);
 			osize = radeon_bo_size(old_rbo);
 			nsize = radeon_bo_size(rbo);
 			if (nsize <= osize && !radeon_bo_reserve(old_rbo, false)) {
@@ -558,8 +553,7 @@ retry:
 	WREG32(RADEON_CRTC_PITCH + radeon_crtc->crtc_offset, crtc_pitch);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
-		radeon_fb = to_radeon_framebuffer(fb);
-		rbo = gem_to_radeon_bo(radeon_fb->obj);
+		rbo = gem_to_radeon_bo(fb->obj[0]);
 		r = radeon_bo_reserve(rbo, false);
 		if (unlikely(r != 0))
 			return r;
@@ -1093,11 +1087,9 @@ static void radeon_crtc_disable(struct drm_crtc *crtc)
 	radeon_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 	if (crtc->primary->fb) {
 		int r;
-		struct radeon_framebuffer *radeon_fb;
 		struct radeon_bo *rbo;
 
-		radeon_fb = to_radeon_framebuffer(crtc->primary->fb);
-		rbo = gem_to_radeon_bo(radeon_fb->obj);
+		rbo = gem_to_radeon_bo(crtc->primary->fb->obj[0]);
 		r = radeon_bo_reserve(rbo, false);
 		if (unlikely(r))
 			DRM_ERROR("failed to reserve rbo before unpin\n");
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 3243e5e01432..fd470d6bf3f4 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -46,7 +46,6 @@ struct radeon_device;
 #define to_radeon_crtc(x) container_of(x, struct radeon_crtc, base)
 #define to_radeon_connector(x) container_of(x, struct radeon_connector, base)
 #define to_radeon_encoder(x) container_of(x, struct radeon_encoder, base)
-#define to_radeon_framebuffer(x) container_of(x, struct radeon_framebuffer, base)
 
 #define RADEON_MAX_HPD_PINS 7
 #define RADEON_MAX_CRTCS 6
@@ -574,11 +573,6 @@ struct radeon_connector {
 	int enabled_attribs;
 };
 
-struct radeon_framebuffer {
-	struct drm_framebuffer base;
-	struct drm_gem_object *obj;
-};
-
 #define ENCODER_MODE_IS_DP(em) (((em) == ATOM_ENCODER_MODE_DP) || \
 				((em) == ATOM_ENCODER_MODE_DP_MST))
 
@@ -932,7 +926,7 @@ radeon_combios_encoder_crtc_scratch_regs(struct drm_encoder *encoder, int crtc);
 extern void
 radeon_combios_encoder_dpms_scratch_regs(struct drm_encoder *encoder, bool on);
 int radeon_framebuffer_init(struct drm_device *dev,
-			     struct radeon_framebuffer *rfb,
+			     struct drm_framebuffer *rfb,
 			     const struct drm_mode_fb_cmd2 *mode_cmd,
 			     struct drm_gem_object *obj);
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index c4420538ec85..f2a0bd1e5119 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -767,7 +767,8 @@ static irqreturn_t rcar_du_crtc_irq(int irq, void *arg)
  * Initialization
  */
 
-int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
+int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int swindex,
+			unsigned int hwindex)
 {
 	static const unsigned int mmio_offsets[] = {
 		DU0_REG_OFFSET, DU1_REG_OFFSET, DU2_REG_OFFSET, DU3_REG_OFFSET
@@ -775,7 +776,7 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 
 	struct rcar_du_device *rcdu = rgrp->dev;
 	struct platform_device *pdev = to_platform_device(rcdu->dev);
-	struct rcar_du_crtc *rcrtc = &rcdu->crtcs[index];
+	struct rcar_du_crtc *rcrtc = &rcdu->crtcs[swindex];
 	struct drm_crtc *crtc = &rcrtc->crtc;
 	struct drm_plane *primary;
 	unsigned int irqflags;
@@ -787,7 +788,7 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 
 	/* Get the CRTC clock and the optional external clock. */
 	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_CRTC_IRQ_CLOCK)) {
-		sprintf(clk_name, "du.%u", index);
+		sprintf(clk_name, "du.%u", hwindex);
 		name = clk_name;
 	} else {
 		name = NULL;
@@ -795,16 +796,16 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 
 	rcrtc->clock = devm_clk_get(rcdu->dev, name);
 	if (IS_ERR(rcrtc->clock)) {
-		dev_err(rcdu->dev, "no clock for CRTC %u\n", index);
+		dev_err(rcdu->dev, "no clock for DU channel %u\n", hwindex);
 		return PTR_ERR(rcrtc->clock);
 	}
 
-	sprintf(clk_name, "dclkin.%u", index);
+	sprintf(clk_name, "dclkin.%u", hwindex);
 	clk = devm_clk_get(rcdu->dev, clk_name);
 	if (!IS_ERR(clk)) {
 		rcrtc->extclock = clk;
 	} else if (PTR_ERR(rcrtc->clock) == -EPROBE_DEFER) {
-		dev_info(rcdu->dev, "can't get external clock %u\n", index);
+		dev_info(rcdu->dev, "can't get external clock %u\n", hwindex);
 		return -EPROBE_DEFER;
 	}
 
@@ -813,13 +814,13 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 	spin_lock_init(&rcrtc->vblank_lock);
 
 	rcrtc->group = rgrp;
-	rcrtc->mmio_offset = mmio_offsets[index];
-	rcrtc->index = index;
+	rcrtc->mmio_offset = mmio_offsets[hwindex];
+	rcrtc->index = hwindex;
 
 	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_VSP1_SOURCE))
 		primary = &rcrtc->vsp->planes[rcrtc->vsp_pipe].plane;
 	else
-		primary = &rgrp->planes[index % 2].plane;
+		primary = &rgrp->planes[swindex % 2].plane;
 
 	ret = drm_crtc_init_with_planes(rcdu->ddev, crtc, primary,
 					NULL, &crtc_funcs, NULL);
@@ -833,7 +834,8 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 
 	/* Register the interrupt handler. */
 	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_CRTC_IRQ_CLOCK)) {
-		irq = platform_get_irq(pdev, index);
+		/* The IRQ's are associated with the CRTC (sw)index. */
+		irq = platform_get_irq(pdev, swindex);
 		irqflags = 0;
 	} else {
 		irq = platform_get_irq(pdev, 0);
@@ -841,7 +843,7 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 	}
 
 	if (irq < 0) {
-		dev_err(rcdu->dev, "no IRQ for CRTC %u\n", index);
+		dev_err(rcdu->dev, "no IRQ for CRTC %u\n", swindex);
 		return irq;
 	}
 
@@ -849,7 +851,7 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 			       dev_name(rcdu->dev), rcrtc);
 	if (ret < 0) {
 		dev_err(rcdu->dev,
-			"failed to register IRQ for CRTC %u\n", index);
+			"failed to register IRQ for CRTC %u\n", swindex);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
index fdc2bf99bda1..84b5e23a85b1 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
@@ -80,7 +80,8 @@ enum rcar_du_output {
 	RCAR_DU_OUTPUT_MAX,
 };
 
-int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index);
+int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int swindex,
+			unsigned int hwindex);
 void rcar_du_crtc_suspend(struct rcar_du_crtc *rcrtc);
 void rcar_du_crtc_resume(struct rcar_du_crtc *rcrtc);
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index 3917d839c04c..02aee6cb0e53 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -40,7 +40,7 @@ static const struct rcar_du_device_info rzg1_du_r8a7743_info = {
 	.gen = 2,
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS,
-	.num_crtcs = 2,
+	.channels_mask = BIT(1) | BIT(0),
 	.routes = {
 		/*
 		 * R8A7743 has one RGB output and one LVDS output
@@ -61,7 +61,7 @@ static const struct rcar_du_device_info rzg1_du_r8a7745_info = {
 	.gen = 2,
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS,
-	.num_crtcs = 2,
+	.channels_mask = BIT(1) | BIT(0),
 	.routes = {
 		/*
 		 * R8A7745 has two RGB outputs
@@ -80,7 +80,7 @@ static const struct rcar_du_device_info rzg1_du_r8a7745_info = {
 static const struct rcar_du_device_info rcar_du_r8a7779_info = {
 	.gen = 2,
 	.features = 0,
-	.num_crtcs = 2,
+	.channels_mask = BIT(1) | BIT(0),
 	.routes = {
 		/*
 		 * R8A7779 has two RGB outputs and one (currently unsupported)
@@ -102,7 +102,7 @@ static const struct rcar_du_device_info rcar_du_r8a7790_info = {
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS,
 	.quirks = RCAR_DU_QUIRK_ALIGN_128B,
-	.num_crtcs = 3,
+	.channels_mask = BIT(2) | BIT(1) | BIT(0),
 	.routes = {
 		/*
 		 * R8A7790 has one RGB output, two LVDS outputs and one
@@ -129,7 +129,7 @@ static const struct rcar_du_device_info rcar_du_r8a7791_info = {
 	.gen = 2,
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS,
-	.num_crtcs = 2,
+	.channels_mask = BIT(1) | BIT(0),
 	.routes = {
 		/*
 		 * R8A779[13] has one RGB output, one LVDS output and one
@@ -151,7 +151,7 @@ static const struct rcar_du_device_info rcar_du_r8a7792_info = {
 	.gen = 2,
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS,
-	.num_crtcs = 2,
+	.channels_mask = BIT(1) | BIT(0),
 	.routes = {
 		/* R8A7792 has two RGB outputs. */
 		[RCAR_DU_OUTPUT_DPAD0] = {
@@ -169,7 +169,7 @@ static const struct rcar_du_device_info rcar_du_r8a7794_info = {
 	.gen = 2,
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS,
-	.num_crtcs = 2,
+	.channels_mask = BIT(1) | BIT(0),
 	.routes = {
 		/*
 		 * R8A7794 has two RGB outputs and one (currently unsupported)
@@ -191,7 +191,7 @@ static const struct rcar_du_device_info rcar_du_r8a7795_info = {
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS
 		  | RCAR_DU_FEATURE_VSP1_SOURCE,
-	.num_crtcs = 4,
+	.channels_mask = BIT(3) | BIT(2) | BIT(1) | BIT(0),
 	.routes = {
 		/*
 		 * R8A7795 has one RGB output, two HDMI outputs and one
@@ -215,7 +215,7 @@ static const struct rcar_du_device_info rcar_du_r8a7795_info = {
 		},
 	},
 	.num_lvds = 1,
-	.dpll_ch =  BIT(1) | BIT(2),
+	.dpll_ch =  BIT(2) | BIT(1),
 };
 
 static const struct rcar_du_device_info rcar_du_r8a7796_info = {
@@ -223,7 +223,7 @@ static const struct rcar_du_device_info rcar_du_r8a7796_info = {
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS
 		  | RCAR_DU_FEATURE_VSP1_SOURCE,
-	.num_crtcs = 3,
+	.channels_mask = BIT(2) | BIT(1) | BIT(0),
 	.routes = {
 		/*
 		 * R8A7796 has one RGB output, one LVDS output and one HDMI
@@ -246,12 +246,40 @@ static const struct rcar_du_device_info rcar_du_r8a7796_info = {
 	.dpll_ch =  BIT(1),
 };
 
+static const struct rcar_du_device_info rcar_du_r8a77965_info = {
+	.gen = 3,
+	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
+		  | RCAR_DU_FEATURE_EXT_CTRL_REGS
+		  | RCAR_DU_FEATURE_VSP1_SOURCE,
+	.channels_mask = BIT(3) | BIT(1) | BIT(0),
+	.routes = {
+		/*
+		 * R8A77965 has one RGB output, one LVDS output and one HDMI
+		 * output.
+		 */
+		[RCAR_DU_OUTPUT_DPAD0] = {
+			.possible_crtcs = BIT(2),
+			.port = 0,
+		},
+		[RCAR_DU_OUTPUT_HDMI0] = {
+			.possible_crtcs = BIT(1),
+			.port = 1,
+		},
+		[RCAR_DU_OUTPUT_LVDS0] = {
+			.possible_crtcs = BIT(0),
+			.port = 2,
+		},
+	},
+	.num_lvds = 1,
+	.dpll_ch =  BIT(1),
+};
+
 static const struct rcar_du_device_info rcar_du_r8a77970_info = {
 	.gen = 3,
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS
 		  | RCAR_DU_FEATURE_VSP1_SOURCE,
-	.num_crtcs = 1,
+	.channels_mask = BIT(0),
 	.routes = {
 		/* R8A77970 has one RGB output and one LVDS output. */
 		[RCAR_DU_OUTPUT_DPAD0] = {
@@ -277,6 +305,7 @@ static const struct of_device_id rcar_du_of_table[] = {
 	{ .compatible = "renesas,du-r8a7794", .data = &rcar_du_r8a7794_info },
 	{ .compatible = "renesas,du-r8a7795", .data = &rcar_du_r8a7795_info },
 	{ .compatible = "renesas,du-r8a7796", .data = &rcar_du_r8a7796_info },
+	{ .compatible = "renesas,du-r8a77965", .data = &rcar_du_r8a77965_info },
 	{ .compatible = "renesas,du-r8a77970", .data = &rcar_du_r8a77970_info },
 	{ }
 };
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.h b/drivers/gpu/drm/rcar-du/rcar_du_drv.h
index 5c7ec15818c7..b3a25e8e07d0 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.h
@@ -52,7 +52,7 @@ struct rcar_du_output_routing {
  * @gen: device generation (2 or 3)
  * @features: device features (RCAR_DU_FEATURE_*)
  * @quirks: device quirks (RCAR_DU_QUIRK_*)
- * @num_crtcs: total number of CRTCs
+ * @channels_mask: bit mask of available DU channels
  * @routes: array of CRTC to output routes, indexed by output (RCAR_DU_OUTPUT_*)
  * @num_lvds: number of internal LVDS encoders
  */
@@ -60,7 +60,7 @@ struct rcar_du_device_info {
 	unsigned int gen;
 	unsigned int features;
 	unsigned int quirks;
-	unsigned int num_crtcs;
+	unsigned int channels_mask;
 	struct rcar_du_output_routing routes[RCAR_DU_OUTPUT_MAX];
 	unsigned int num_lvds;
 	unsigned int dpll_ch;
@@ -87,7 +87,6 @@ struct rcar_du_device {
 	struct rcar_du_vsp vsps[RCAR_DU_MAX_VSPS];
 
 	struct {
-		struct drm_property *alpha;
 		struct drm_property *colorkey;
 	} props;
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.c b/drivers/gpu/drm/rcar-du/rcar_du_group.c
index 2f37ea901873..d539cb290a35 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_group.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.c
@@ -46,10 +46,13 @@ void rcar_du_group_write(struct rcar_du_group *rgrp, u32 reg, u32 data)
 
 static void rcar_du_group_setup_pins(struct rcar_du_group *rgrp)
 {
-	u32 defr6 = DEFR6_CODE | DEFR6_ODPM12_DISP;
+	u32 defr6 = DEFR6_CODE;
 
-	if (rgrp->num_crtcs > 1)
-		defr6 |= DEFR6_ODPM22_DISP;
+	if (rgrp->channels_mask & BIT(0))
+		defr6 |= DEFR6_ODPM02_DISP;
+
+	if (rgrp->channels_mask & BIT(1))
+		defr6 |= DEFR6_ODPM12_DISP;
 
 	rcar_du_group_write(rgrp, DEFR6, defr6);
 }
@@ -80,10 +83,11 @@ static void rcar_du_group_setup_defr8(struct rcar_du_group *rgrp)
 		 * On Gen3 VSPD routing can't be configured, but DPAD routing
 		 * needs to be set despite having a single option available.
 		 */
-		u32 crtc = ffs(possible_crtcs) - 1;
+		unsigned int rgb_crtc = ffs(possible_crtcs) - 1;
+		struct rcar_du_crtc *crtc = &rcdu->crtcs[rgb_crtc];
 
-		if (crtc / 2 == rgrp->index)
-			defr8 |= DEFR8_DRGBS_DU(crtc);
+		if (crtc->index / 2 == rgrp->index)
+			defr8 |= DEFR8_DRGBS_DU(crtc->index);
 	}
 
 	rcar_du_group_write(rgrp, DEFR8, defr8);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.h b/drivers/gpu/drm/rcar-du/rcar_du_group.h
index 5e3adc6b31b5..42105aedecc8 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_group.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.h
@@ -25,6 +25,7 @@ struct rcar_du_device;
  * @dev: the DU device
  * @mmio_offset: registers offset in the device memory map
  * @index: group index
+ * @channels_mask: bitmask of populated DU channels in this group
  * @num_crtcs: number of CRTCs in this group (1 or 2)
  * @use_count: number of users of the group (rcar_du_group_(get|put))
  * @used_crtcs: number of CRTCs currently in use
@@ -39,6 +40,7 @@ struct rcar_du_group {
 	unsigned int mmio_offset;
 	unsigned int index;
 
+	unsigned int channels_mask;
 	unsigned int num_crtcs;
 	unsigned int use_count;
 	unsigned int used_crtcs;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index 0329b354bfa0..f0bc7cc0e913 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -233,15 +233,7 @@ static int rcar_du_atomic_check(struct drm_device *dev,
 	struct rcar_du_device *rcdu = dev->dev_private;
 	int ret;
 
-	ret = drm_atomic_helper_check_modeset(dev, state);
-	if (ret)
-		return ret;
-
-	ret = drm_atomic_normalize_zpos(dev, state);
-	if (ret)
-		return ret;
-
-	ret = drm_atomic_helper_check_planes(dev, state);
+	ret = drm_atomic_helper_check(dev, state);
 	if (ret)
 		return ret;
 
@@ -415,11 +407,6 @@ static int rcar_du_encoders_init(struct rcar_du_device *rcdu)
 
 static int rcar_du_properties_init(struct rcar_du_device *rcdu)
 {
-	rcdu->props.alpha =
-		drm_property_create_range(rcdu->ddev, 0, "alpha", 0, 255);
-	if (rcdu->props.alpha == NULL)
-		return -ENOMEM;
-
 	/*
 	 * The color key is expressed as an RGB888 triplet stored in a 32-bit
 	 * integer in XRGB8888 format. Bit 24 is used as a flag to disable (0)
@@ -441,7 +428,7 @@ static int rcar_du_vsps_init(struct rcar_du_device *rcdu)
 	struct {
 		struct device_node *np;
 		unsigned int crtcs_mask;
-	} vsps[RCAR_DU_MAX_VSPS] = { { 0, }, };
+	} vsps[RCAR_DU_MAX_VSPS] = { { NULL, }, };
 	unsigned int vsps_count = 0;
 	unsigned int cells;
 	unsigned int i;
@@ -520,6 +507,8 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 	struct drm_fbdev_cma *fbdev;
 	unsigned int num_encoders;
 	unsigned int num_groups;
+	unsigned int swindex;
+	unsigned int hwindex;
 	unsigned int i;
 	int ret;
 
@@ -529,10 +518,11 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 	dev->mode_config.min_height = 0;
 	dev->mode_config.max_width = 4095;
 	dev->mode_config.max_height = 2047;
+	dev->mode_config.normalize_zpos = true;
 	dev->mode_config.funcs = &rcar_du_mode_config_funcs;
 	dev->mode_config.helper_private = &rcar_du_mode_config_helper;
 
-	rcdu->num_crtcs = rcdu->info->num_crtcs;
+	rcdu->num_crtcs = hweight8(rcdu->info->channels_mask);
 
 	ret = rcar_du_properties_init(rcdu);
 	if (ret < 0)
@@ -542,7 +532,7 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 	 * Initialize vertical blanking interrupts handling. Start with vblank
 	 * disabled for all CRTCs.
 	 */
-	ret = drm_vblank_init(dev, (1 << rcdu->info->num_crtcs) - 1);
+	ret = drm_vblank_init(dev, (1 << rcdu->num_crtcs) - 1);
 	if (ret < 0)
 		return ret;
 
@@ -557,7 +547,10 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 		rgrp->dev = rcdu;
 		rgrp->mmio_offset = mmio_offsets[i];
 		rgrp->index = i;
-		rgrp->num_crtcs = min(rcdu->num_crtcs - 2 * i, 2U);
+		/* Extract the channel mask for this group only. */
+		rgrp->channels_mask = (rcdu->info->channels_mask >> (2 * i))
+				   & GENMASK(1, 0);
+		rgrp->num_crtcs = hweight8(rgrp->channels_mask);
 
 		/*
 		 * If we have more than one CRTCs in this group pre-associate
@@ -584,10 +577,16 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 	}
 
 	/* Create the CRTCs. */
-	for (i = 0; i < rcdu->num_crtcs; ++i) {
-		struct rcar_du_group *rgrp = &rcdu->groups[i / 2];
+	for (swindex = 0, hwindex = 0; swindex < rcdu->num_crtcs; ++hwindex) {
+		struct rcar_du_group *rgrp;
+
+		/* Skip unpopulated DU channels. */
+		if (!(rcdu->info->channels_mask & BIT(hwindex)))
+			continue;
+
+		rgrp = &rcdu->groups[hwindex / 2];
 
-		ret = rcar_du_crtc_create(rgrp, i);
+		ret = rcar_du_crtc_create(rgrp, swindex++, hwindex);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of.c b/drivers/gpu/drm/rcar-du/rcar_du_of.c
index 68a0b82cb17e..afef69669bb4 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_of.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_of.c
@@ -18,6 +18,7 @@
 
 #include "rcar_du_crtc.h"
 #include "rcar_du_drv.h"
+#include "rcar_du_of.h"
 
 /* -----------------------------------------------------------------------------
  * Generic Overlay Handling
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of.h b/drivers/gpu/drm/rcar-du/rcar_du_of.h
index c2e65a727e91..8dd3fbe96650 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_of.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_of.h
@@ -11,7 +11,7 @@
 
 struct of_device_id;
 
-#ifdef CONFIG_DRM_RCAR_LVDS
+#if IS_ENABLED(CONFIG_DRM_RCAR_LVDS)
 void __init rcar_du_of_init(const struct of_device_id *of_ids);
 #else
 static inline void rcar_du_of_init(const struct of_device_id *of_ids) { }
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
index 68556bd9dad2..c20f7ed48c8d 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
@@ -423,7 +423,7 @@ static void rcar_du_plane_setup_mode(struct rcar_du_group *rgrp,
 		rcar_du_plane_write(rgrp, index, PnALPHAR, PnALPHAR_ABIT_0);
 	else
 		rcar_du_plane_write(rgrp, index, PnALPHAR,
-				    PnALPHAR_ABIT_X | state->alpha);
+				    PnALPHAR_ABIT_X | state->state.alpha >> 8);
 
 	pnmr = PnMR_BM_MD | state->format->pnmr;
 
@@ -692,11 +692,11 @@ static void rcar_du_plane_reset(struct drm_plane *plane)
 
 	state->hwindex = -1;
 	state->source = RCAR_DU_PLANE_MEMORY;
-	state->alpha = 255;
 	state->colorkey = RCAR_DU_COLORKEY_NONE;
 	state->state.zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1;
 
 	plane->state = &state->state;
+	plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE;
 	plane->state->plane = plane;
 }
 
@@ -708,9 +708,7 @@ static int rcar_du_plane_atomic_set_property(struct drm_plane *plane,
 	struct rcar_du_plane_state *rstate = to_rcar_plane_state(state);
 	struct rcar_du_device *rcdu = to_rcar_plane(plane)->group->dev;
 
-	if (property == rcdu->props.alpha)
-		rstate->alpha = val;
-	else if (property == rcdu->props.colorkey)
+	if (property == rcdu->props.colorkey)
 		rstate->colorkey = val;
 	else
 		return -EINVAL;
@@ -726,9 +724,7 @@ static int rcar_du_plane_atomic_get_property(struct drm_plane *plane,
 		container_of(state, const struct rcar_du_plane_state, state);
 	struct rcar_du_device *rcdu = to_rcar_plane(plane)->group->dev;
 
-	if (property == rcdu->props.alpha)
-		*val = rstate->alpha;
-	else if (property == rcdu->props.colorkey)
+	if (property == rcdu->props.colorkey)
 		*val = rstate->colorkey;
 	else
 		return -EINVAL;
@@ -797,10 +793,9 @@ int rcar_du_planes_init(struct rcar_du_group *rgrp)
 			continue;
 
 		drm_object_attach_property(&plane->plane.base,
-					   rcdu->props.alpha, 255);
-		drm_object_attach_property(&plane->plane.base,
 					   rcdu->props.colorkey,
 					   RCAR_DU_COLORKEY_NONE);
+		drm_plane_create_alpha_property(&plane->plane);
 		drm_plane_create_zpos_property(&plane->plane, 1, 1, 7);
 	}
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.h b/drivers/gpu/drm/rcar-du/rcar_du_plane.h
index 890321b4665d..5c19c69e4691 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.h
@@ -50,7 +50,6 @@ static inline struct rcar_du_plane *to_rcar_plane(struct drm_plane *plane)
  * @state: base DRM plane state
  * @format: information about the pixel format used by the plane
  * @hwindex: 0-based hardware plane index, -1 means unused
- * @alpha: value of the plane alpha property
  * @colorkey: value of the plane colorkey property
  */
 struct rcar_du_plane_state {
@@ -60,7 +59,6 @@ struct rcar_du_plane_state {
 	int hwindex;
 	enum rcar_du_plane_source source;
 
-	unsigned int alpha;
 	unsigned int colorkey;
 };
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_regs.h b/drivers/gpu/drm/rcar-du/rcar_du_regs.h
index d5bae99d3cfe..9dfd220ceda1 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_regs.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_regs.h
@@ -187,14 +187,14 @@
 
 #define DEFR6			0x000e8
 #define DEFR6_CODE		(0x7778 << 16)
-#define DEFR6_ODPM22_DSMR	(0 << 10)
-#define DEFR6_ODPM22_DISP	(2 << 10)
-#define DEFR6_ODPM22_CDE	(3 << 10)
-#define DEFR6_ODPM22_MASK	(3 << 10)
-#define DEFR6_ODPM12_DSMR	(0 << 8)
-#define DEFR6_ODPM12_DISP	(2 << 8)
-#define DEFR6_ODPM12_CDE	(3 << 8)
-#define DEFR6_ODPM12_MASK	(3 << 8)
+#define DEFR6_ODPM12_DSMR	(0 << 10)
+#define DEFR6_ODPM12_DISP	(2 << 10)
+#define DEFR6_ODPM12_CDE	(3 << 10)
+#define DEFR6_ODPM12_MASK	(3 << 10)
+#define DEFR6_ODPM02_DSMR	(0 << 8)
+#define DEFR6_ODPM02_DISP	(2 << 8)
+#define DEFR6_ODPM02_CDE	(3 << 8)
+#define DEFR6_ODPM02_MASK	(3 << 8)
 #define DEFR6_TCNE1		(1 << 6)
 #define DEFR6_TCNE0		(1 << 4)
 #define DEFR6_MLOS1		(1 << 2)
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index 2c260c33840b..c59f0cfabd33 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -17,6 +17,7 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_plane_helper.h>
 
 #include <linux/bitops.h>
@@ -54,6 +55,7 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc)
 	};
 	struct rcar_du_plane_state state = {
 		.state = {
+			.alpha = DRM_BLEND_ALPHA_OPAQUE,
 			.crtc = &crtc->crtc,
 			.dst.x1 = 0,
 			.dst.y1 = 0,
@@ -67,7 +69,6 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc)
 		},
 		.format = rcar_du_format_info(DRM_FORMAT_ARGB8888),
 		.source = RCAR_DU_PLANE_VSPD1,
-		.alpha = 255,
 		.colorkey = 0,
 	};
 
@@ -173,7 +174,7 @@ static void rcar_du_vsp_plane_setup(struct rcar_du_vsp_plane *plane)
 	struct vsp1_du_atomic_config cfg = {
 		.pixelformat = 0,
 		.pitch = fb->pitches[0],
-		.alpha = state->alpha,
+		.alpha = state->state.alpha >> 8,
 		.zpos = state->state.zpos,
 	};
 	unsigned int i;
@@ -237,6 +238,10 @@ static int rcar_du_vsp_plane_prepare_fb(struct drm_plane *plane,
 		}
 	}
 
+	ret = drm_gem_fb_prepare_fb(plane, state);
+	if (ret)
+		goto fail;
+
 	return 0;
 
 fail:
@@ -299,14 +304,12 @@ static const struct drm_plane_helper_funcs rcar_du_vsp_plane_helper_funcs = {
 static struct drm_plane_state *
 rcar_du_vsp_plane_atomic_duplicate_state(struct drm_plane *plane)
 {
-	struct rcar_du_vsp_plane_state *state;
 	struct rcar_du_vsp_plane_state *copy;
 
 	if (WARN_ON(!plane->state))
 		return NULL;
 
-	state = to_rcar_vsp_plane_state(plane->state);
-	copy = kmemdup(state, sizeof(*state), GFP_KERNEL);
+	copy = kzalloc(sizeof(*copy), GFP_KERNEL);
 	if (copy == NULL)
 		return NULL;
 
@@ -335,44 +338,13 @@ static void rcar_du_vsp_plane_reset(struct drm_plane *plane)
 	if (state == NULL)
 		return;
 
-	state->alpha = 255;
+	state->state.alpha = DRM_BLEND_ALPHA_OPAQUE;
 	state->state.zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1;
 
 	plane->state = &state->state;
 	plane->state->plane = plane;
 }
 
-static int rcar_du_vsp_plane_atomic_set_property(struct drm_plane *plane,
-	struct drm_plane_state *state, struct drm_property *property,
-	uint64_t val)
-{
-	struct rcar_du_vsp_plane_state *rstate = to_rcar_vsp_plane_state(state);
-	struct rcar_du_device *rcdu = to_rcar_vsp_plane(plane)->vsp->dev;
-
-	if (property == rcdu->props.alpha)
-		rstate->alpha = val;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-
-static int rcar_du_vsp_plane_atomic_get_property(struct drm_plane *plane,
-	const struct drm_plane_state *state, struct drm_property *property,
-	uint64_t *val)
-{
-	const struct rcar_du_vsp_plane_state *rstate =
-		container_of(state, const struct rcar_du_vsp_plane_state, state);
-	struct rcar_du_device *rcdu = to_rcar_vsp_plane(plane)->vsp->dev;
-
-	if (property == rcdu->props.alpha)
-		*val = rstate->alpha;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-
 static const struct drm_plane_funcs rcar_du_vsp_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
@@ -380,8 +352,6 @@ static const struct drm_plane_funcs rcar_du_vsp_plane_funcs = {
 	.destroy = drm_plane_cleanup,
 	.atomic_duplicate_state = rcar_du_vsp_plane_atomic_duplicate_state,
 	.atomic_destroy_state = rcar_du_vsp_plane_atomic_destroy_state,
-	.atomic_set_property = rcar_du_vsp_plane_atomic_set_property,
-	.atomic_get_property = rcar_du_vsp_plane_atomic_get_property,
 };
 
 int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np,
@@ -438,8 +408,7 @@ int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np,
 		if (type == DRM_PLANE_TYPE_PRIMARY)
 			continue;
 
-		drm_object_attach_property(&plane->plane.base,
-					   rcdu->props.alpha, 255);
+		drm_plane_create_alpha_property(&plane->plane);
 		drm_plane_create_zpos_property(&plane->plane, 1, 1,
 					       vsp->num_planes - 1);
 	}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.h b/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
index 4c5d7bbce6aa..8a8a25c8c8e8 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
@@ -44,15 +44,12 @@ static inline struct rcar_du_vsp_plane *to_rcar_vsp_plane(struct drm_plane *p)
  * @state: base DRM plane state
  * @format: information about the pixel format used by the plane
  * @sg_tables: scatter-gather tables for the frame buffer memory
- * @alpha: value of the plane alpha property
  */
 struct rcar_du_vsp_plane_state {
 	struct drm_plane_state state;
 
 	const struct rcar_du_format_info *format;
 	struct sg_table sg_tables[3];
-
-	unsigned int alpha;
 };
 
 static inline struct rcar_du_vsp_plane_state *
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 3d2d3bbd1342..155ad840f3c5 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -88,6 +88,9 @@ static int rcar_lvds_connector_atomic_check(struct drm_connector *connector,
 	const struct drm_display_mode *panel_mode;
 	struct drm_crtc_state *crtc_state;
 
+	if (!state->crtc)
+		return 0;
+
 	if (list_empty(&connector->modes)) {
 		dev_dbg(lvds->dev, "connector: empty modes list\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
index 3e8bf79bea58..080f05352195 100644
--- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
@@ -77,13 +77,13 @@ struct rockchip_dp_device {
 	struct analogix_dp_plat_data plat_data;
 };
 
-static void analogix_dp_psr_set(struct drm_encoder *encoder, bool enabled)
+static int analogix_dp_psr_set(struct drm_encoder *encoder, bool enabled)
 {
 	struct rockchip_dp_device *dp = to_dp(encoder);
 	int ret;
 
 	if (!analogix_dp_psr_enabled(dp->adp))
-		return;
+		return 0;
 
 	DRM_DEV_DEBUG(dp->dev, "%s PSR...\n", enabled ? "Entry" : "Exit");
 
@@ -91,13 +91,13 @@ static void analogix_dp_psr_set(struct drm_encoder *encoder, bool enabled)
 					 PSR_WAIT_LINE_FLAG_TIMEOUT_MS);
 	if (ret) {
 		DRM_DEV_ERROR(dp->dev, "line flag interrupt did not arrive\n");
-		return;
+		return -ETIMEDOUT;
 	}
 
 	if (enabled)
-		analogix_dp_enable_psr(dp->adp);
+		return analogix_dp_enable_psr(dp->adp);
 	else
-		analogix_dp_disable_psr(dp->adp);
+		return analogix_dp_disable_psr(dp->adp);
 }
 
 static int rockchip_dp_pre_init(struct rockchip_dp_device *dp)
@@ -109,7 +109,7 @@ static int rockchip_dp_pre_init(struct rockchip_dp_device *dp)
 	return 0;
 }
 
-static int rockchip_dp_poweron(struct analogix_dp_plat_data *plat_data)
+static int rockchip_dp_poweron_start(struct analogix_dp_plat_data *plat_data)
 {
 	struct rockchip_dp_device *dp = to_dp(plat_data);
 	int ret;
@@ -127,7 +127,14 @@ static int rockchip_dp_poweron(struct analogix_dp_plat_data *plat_data)
 		return ret;
 	}
 
-	return rockchip_drm_psr_activate(&dp->encoder);
+	return ret;
+}
+
+static int rockchip_dp_poweron_end(struct analogix_dp_plat_data *plat_data)
+{
+	struct rockchip_dp_device *dp = to_dp(plat_data);
+
+	return rockchip_drm_psr_inhibit_put(&dp->encoder);
 }
 
 static int rockchip_dp_powerdown(struct analogix_dp_plat_data *plat_data)
@@ -135,7 +142,7 @@ static int rockchip_dp_powerdown(struct analogix_dp_plat_data *plat_data)
 	struct rockchip_dp_device *dp = to_dp(plat_data);
 	int ret;
 
-	ret = rockchip_drm_psr_deactivate(&dp->encoder);
+	ret = rockchip_drm_psr_inhibit_get(&dp->encoder);
 	if (ret != 0)
 		return ret;
 
@@ -218,6 +225,7 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder,
 				      struct drm_connector_state *conn_state)
 {
 	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state);
+	struct drm_display_info *di = &conn_state->connector->display_info;
 
 	/*
 	 * The hardware IC designed that VOP must output the RGB10 video
@@ -229,6 +237,7 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder,
 
 	s->output_mode = ROCKCHIP_OUT_MODE_AAAA;
 	s->output_type = DRM_MODE_CONNECTOR_eDP;
+	s->output_bpc = di->bpc;
 
 	return 0;
 }
@@ -328,7 +337,8 @@ static int rockchip_dp_bind(struct device *dev, struct device *master,
 	dp->plat_data.encoder = &dp->encoder;
 
 	dp->plat_data.dev_type = dp->data->chip_type;
-	dp->plat_data.power_on = rockchip_dp_poweron;
+	dp->plat_data.power_on_start = rockchip_dp_poweron_start;
+	dp->plat_data.power_on_end = rockchip_dp_poweron_end;
 	dp->plat_data.power_off = rockchip_dp_powerdown;
 	dp->plat_data.get_modes = rockchip_dp_get_modes;
 
@@ -358,6 +368,8 @@ static void rockchip_dp_unbind(struct device *dev, struct device *master,
 	analogix_dp_unbind(dp->adp);
 	rockchip_drm_psr_unregister(&dp->encoder);
 	dp->encoder.funcs->destroy(&dp->encoder);
+
+	dp->adp = ERR_PTR(-ENODEV);
 }
 
 static const struct component_ops rockchip_dp_component_ops = {
@@ -381,6 +393,7 @@ static int rockchip_dp_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	dp->dev = dev;
+	dp->adp = ERR_PTR(-ENODEV);
 	dp->plat_data.panel = panel;
 
 	ret = rockchip_dp_of_probe(dp);
@@ -404,6 +417,9 @@ static int rockchip_dp_suspend(struct device *dev)
 {
 	struct rockchip_dp_device *dp = dev_get_drvdata(dev);
 
+	if (IS_ERR(dp->adp))
+		return 0;
+
 	return analogix_dp_suspend(dp->adp);
 }
 
@@ -411,6 +427,9 @@ static int rockchip_dp_resume(struct device *dev)
 {
 	struct rockchip_dp_device *dp = dev_get_drvdata(dev);
 
+	if (IS_ERR(dp->adp))
+		return 0;
+
 	return analogix_dp_resume(dp->adp);
 }
 #endif
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h
index 9c064a40458b..3a6ebfc26036 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h
@@ -36,6 +36,7 @@ struct rockchip_crtc_state {
 	struct drm_crtc_state base;
 	int output_type;
 	int output_mode;
+	int output_bpc;
 };
 #define to_rockchip_crtc_state(s) \
 		container_of(s, struct rockchip_crtc_state, base)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index e266539e04e5..d4f4118b482d 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -167,8 +167,67 @@ err_gem_object_unreference:
 	return ERR_PTR(ret);
 }
 
+static void
+rockchip_drm_psr_inhibit_get_state(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_encoder *encoder;
+	u32 encoder_mask = 0;
+	int i;
+
+	for_each_old_crtc_in_state(state, crtc, crtc_state, i) {
+		encoder_mask |= crtc_state->encoder_mask;
+		encoder_mask |= crtc->state->encoder_mask;
+	}
+
+	drm_for_each_encoder_mask(encoder, state->dev, encoder_mask)
+		rockchip_drm_psr_inhibit_get(encoder);
+}
+
+static void
+rockchip_drm_psr_inhibit_put_state(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_encoder *encoder;
+	u32 encoder_mask = 0;
+	int i;
+
+	for_each_old_crtc_in_state(state, crtc, crtc_state, i) {
+		encoder_mask |= crtc_state->encoder_mask;
+		encoder_mask |= crtc->state->encoder_mask;
+	}
+
+	drm_for_each_encoder_mask(encoder, state->dev, encoder_mask)
+		rockchip_drm_psr_inhibit_put(encoder);
+}
+
+static void
+rockchip_atomic_helper_commit_tail_rpm(struct drm_atomic_state *old_state)
+{
+	struct drm_device *dev = old_state->dev;
+
+	rockchip_drm_psr_inhibit_get_state(old_state);
+
+	drm_atomic_helper_commit_modeset_disables(dev, old_state);
+
+	drm_atomic_helper_commit_modeset_enables(dev, old_state);
+
+	drm_atomic_helper_commit_planes(dev, old_state,
+					DRM_PLANE_COMMIT_ACTIVE_ONLY);
+
+	rockchip_drm_psr_inhibit_put_state(old_state);
+
+	drm_atomic_helper_commit_hw_done(old_state);
+
+	drm_atomic_helper_wait_for_vblanks(dev, old_state);
+
+	drm_atomic_helper_cleanup_planes(dev, old_state);
+}
+
 static const struct drm_mode_config_helper_funcs rockchip_mode_config_helpers = {
-	.atomic_commit_tail = drm_atomic_helper_commit_tail_rpm,
+	.atomic_commit_tail = rockchip_atomic_helper_commit_tail_rpm,
 };
 
 static const struct drm_mode_config_funcs rockchip_drm_mode_config_funcs = {
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index 074db7a92809..a8db758d523e 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -357,8 +357,8 @@ err_free_rk_obj:
 }
 
 /*
- * rockchip_gem_free_object - (struct drm_driver)->gem_free_object callback
- * function
+ * rockchip_gem_free_object - (struct drm_driver)->gem_free_object_unlocked
+ * callback function
  */
 void rockchip_gem_free_object(struct drm_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_psr.c b/drivers/gpu/drm/rockchip/rockchip_drm_psr.c
index b339ca943139..79d00d861a31 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_psr.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_psr.c
@@ -20,42 +20,19 @@
 
 #define PSR_FLUSH_TIMEOUT_MS	100
 
-enum psr_state {
-	PSR_FLUSH,
-	PSR_ENABLE,
-	PSR_DISABLE,
-};
-
 struct psr_drv {
 	struct list_head	list;
 	struct drm_encoder	*encoder;
 
 	struct mutex		lock;
-	bool			active;
-	enum psr_state		state;
+	int			inhibit_count;
+	bool			enabled;
 
 	struct delayed_work	flush_work;
 
-	void (*set)(struct drm_encoder *encoder, bool enable);
+	int (*set)(struct drm_encoder *encoder, bool enable);
 };
 
-static struct psr_drv *find_psr_by_crtc(struct drm_crtc *crtc)
-{
-	struct rockchip_drm_private *drm_drv = crtc->dev->dev_private;
-	struct psr_drv *psr;
-
-	mutex_lock(&drm_drv->psr_list_lock);
-	list_for_each_entry(psr, &drm_drv->psr_list, list) {
-		if (psr->encoder->crtc == crtc)
-			goto out;
-	}
-	psr = ERR_PTR(-ENODEV);
-
-out:
-	mutex_unlock(&drm_drv->psr_list_lock);
-	return psr;
-}
-
 static struct psr_drv *find_psr_by_encoder(struct drm_encoder *encoder)
 {
 	struct rockchip_drm_private *drm_drv = encoder->dev->dev_private;
@@ -73,46 +50,22 @@ out:
 	return psr;
 }
 
-static void psr_set_state_locked(struct psr_drv *psr, enum psr_state state)
+static int psr_set_state_locked(struct psr_drv *psr, bool enable)
 {
-	/*
-	 * Allowed finite state machine:
-	 *
-	 *   PSR_ENABLE  < = = = = = >  PSR_FLUSH
-	 *       | ^                        |
-	 *       | |                        |
-	 *       v |                        |
-	 *   PSR_DISABLE < - - - - - - - - -
-	 */
-	if (state == psr->state || !psr->active)
-		return;
-
-	/* Already disabled in flush, change the state, but not the hardware */
-	if (state == PSR_DISABLE && psr->state == PSR_FLUSH) {
-		psr->state = state;
-		return;
-	}
+	int ret;
 
-	psr->state = state;
+	if (psr->inhibit_count > 0)
+		return -EINVAL;
 
-	/* Actually commit the state change to hardware */
-	switch (psr->state) {
-	case PSR_ENABLE:
-		psr->set(psr->encoder, true);
-		break;
+	if (enable == psr->enabled)
+		return 0;
 
-	case PSR_DISABLE:
-	case PSR_FLUSH:
-		psr->set(psr->encoder, false);
-		break;
-	}
-}
+	ret = psr->set(psr->encoder, enable);
+	if (ret)
+		return ret;
 
-static void psr_set_state(struct psr_drv *psr, enum psr_state state)
-{
-	mutex_lock(&psr->lock);
-	psr_set_state_locked(psr, state);
-	mutex_unlock(&psr->lock);
+	psr->enabled = enable;
+	return 0;
 }
 
 static void psr_flush_handler(struct work_struct *work)
@@ -120,21 +73,24 @@ static void psr_flush_handler(struct work_struct *work)
 	struct psr_drv *psr = container_of(to_delayed_work(work),
 					   struct psr_drv, flush_work);
 
-	/* If the state has changed since we initiated the flush, do nothing */
 	mutex_lock(&psr->lock);
-	if (psr->state == PSR_FLUSH)
-		psr_set_state_locked(psr, PSR_ENABLE);
+	psr_set_state_locked(psr, true);
 	mutex_unlock(&psr->lock);
 }
 
 /**
- * rockchip_drm_psr_activate - activate PSR on the given pipe
+ * rockchip_drm_psr_inhibit_put - release PSR inhibit on given encoder
  * @encoder: encoder to obtain the PSR encoder
  *
+ * Decrements PSR inhibit count on given encoder. Should be called only
+ * for a PSR inhibit count increment done before. If PSR inhibit counter
+ * reaches zero, PSR flush work is scheduled to make the hardware enter
+ * PSR mode in PSR_FLUSH_TIMEOUT_MS.
+ *
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int rockchip_drm_psr_activate(struct drm_encoder *encoder)
+int rockchip_drm_psr_inhibit_put(struct drm_encoder *encoder)
 {
 	struct psr_drv *psr = find_psr_by_encoder(encoder);
 
@@ -142,21 +98,30 @@ int rockchip_drm_psr_activate(struct drm_encoder *encoder)
 		return PTR_ERR(psr);
 
 	mutex_lock(&psr->lock);
-	psr->active = true;
+	--psr->inhibit_count;
+	WARN_ON(psr->inhibit_count < 0);
+	if (!psr->inhibit_count)
+		mod_delayed_work(system_wq, &psr->flush_work,
+				 PSR_FLUSH_TIMEOUT_MS);
 	mutex_unlock(&psr->lock);
 
 	return 0;
 }
-EXPORT_SYMBOL(rockchip_drm_psr_activate);
+EXPORT_SYMBOL(rockchip_drm_psr_inhibit_put);
 
 /**
- * rockchip_drm_psr_deactivate - deactivate PSR on the given pipe
+ * rockchip_drm_psr_inhibit_get - acquire PSR inhibit on given encoder
  * @encoder: encoder to obtain the PSR encoder
  *
+ * Increments PSR inhibit count on given encoder. This function guarantees
+ * that after it returns PSR is turned off on given encoder and no PSR-related
+ * hardware state change occurs at least until a matching call to
+ * rockchip_drm_psr_inhibit_put() is done.
+ *
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int rockchip_drm_psr_deactivate(struct drm_encoder *encoder)
+int rockchip_drm_psr_inhibit_get(struct drm_encoder *encoder)
 {
 	struct psr_drv *psr = find_psr_by_encoder(encoder);
 
@@ -164,37 +129,25 @@ int rockchip_drm_psr_deactivate(struct drm_encoder *encoder)
 		return PTR_ERR(psr);
 
 	mutex_lock(&psr->lock);
-	psr->active = false;
+	psr_set_state_locked(psr, false);
+	++psr->inhibit_count;
 	mutex_unlock(&psr->lock);
 	cancel_delayed_work_sync(&psr->flush_work);
 
 	return 0;
 }
-EXPORT_SYMBOL(rockchip_drm_psr_deactivate);
+EXPORT_SYMBOL(rockchip_drm_psr_inhibit_get);
 
 static void rockchip_drm_do_flush(struct psr_drv *psr)
 {
-	psr_set_state(psr, PSR_FLUSH);
-	mod_delayed_work(system_wq, &psr->flush_work, PSR_FLUSH_TIMEOUT_MS);
-}
-
-/**
- * rockchip_drm_psr_flush - flush a single pipe
- * @crtc: CRTC of the pipe to flush
- *
- * Returns:
- * 0 on success, -errno on fail
- */
-int rockchip_drm_psr_flush(struct drm_crtc *crtc)
-{
-	struct psr_drv *psr = find_psr_by_crtc(crtc);
-	if (IS_ERR(psr))
-		return PTR_ERR(psr);
+	cancel_delayed_work_sync(&psr->flush_work);
 
-	rockchip_drm_do_flush(psr);
-	return 0;
+	mutex_lock(&psr->lock);
+	if (!psr_set_state_locked(psr, false))
+		mod_delayed_work(system_wq, &psr->flush_work,
+				 PSR_FLUSH_TIMEOUT_MS);
+	mutex_unlock(&psr->lock);
 }
-EXPORT_SYMBOL(rockchip_drm_psr_flush);
 
 /**
  * rockchip_drm_psr_flush_all - force to flush all registered PSR encoders
@@ -225,11 +178,16 @@ EXPORT_SYMBOL(rockchip_drm_psr_flush_all);
  * @encoder: encoder that obtain the PSR function
  * @psr_set: call back to set PSR state
  *
+ * The function returns with PSR inhibit counter initialized with one
+ * and the caller (typically encoder driver) needs to call
+ * rockchip_drm_psr_inhibit_put() when it becomes ready to accept PSR
+ * enable request.
+ *
  * Returns:
  * Zero on success, negative errno on failure.
  */
 int rockchip_drm_psr_register(struct drm_encoder *encoder,
-			void (*psr_set)(struct drm_encoder *, bool enable))
+			int (*psr_set)(struct drm_encoder *, bool enable))
 {
 	struct rockchip_drm_private *drm_drv = encoder->dev->dev_private;
 	struct psr_drv *psr;
@@ -244,8 +202,8 @@ int rockchip_drm_psr_register(struct drm_encoder *encoder,
 	INIT_DELAYED_WORK(&psr->flush_work, psr_flush_handler);
 	mutex_init(&psr->lock);
 
-	psr->active = true;
-	psr->state = PSR_DISABLE;
+	psr->inhibit_count = 1;
+	psr->enabled = false;
 	psr->encoder = encoder;
 	psr->set = psr_set;
 
@@ -262,6 +220,11 @@ EXPORT_SYMBOL(rockchip_drm_psr_register);
  * @encoder: encoder that obtain the PSR function
  * @psr_set: call back to set PSR state
  *
+ * It is expected that the PSR inhibit counter is 1 when this function is
+ * called, which corresponds to a state when related encoder has been
+ * disconnected from any CRTCs and its driver called
+ * rockchip_drm_psr_inhibit_get() to stop the PSR logic.
+ *
  * Returns:
  * Zero on success, negative errno on failure.
  */
@@ -273,7 +236,12 @@ void rockchip_drm_psr_unregister(struct drm_encoder *encoder)
 	mutex_lock(&drm_drv->psr_list_lock);
 	list_for_each_entry_safe(psr, n, &drm_drv->psr_list, list) {
 		if (psr->encoder == encoder) {
-			cancel_delayed_work_sync(&psr->flush_work);
+			/*
+			 * Any other value would mean that the encoder
+			 * is still in use.
+			 */
+			WARN_ON(psr->inhibit_count != 1);
+
 			list_del(&psr->list);
 			kfree(psr);
 		}
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_psr.h b/drivers/gpu/drm/rockchip/rockchip_drm_psr.h
index b1ea0155e57c..860c62494496 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_psr.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_psr.h
@@ -16,13 +16,12 @@
 #define __ROCKCHIP_DRM_PSR___
 
 void rockchip_drm_psr_flush_all(struct drm_device *dev);
-int rockchip_drm_psr_flush(struct drm_crtc *crtc);
 
-int rockchip_drm_psr_activate(struct drm_encoder *encoder);
-int rockchip_drm_psr_deactivate(struct drm_encoder *encoder);
+int rockchip_drm_psr_inhibit_put(struct drm_encoder *encoder);
+int rockchip_drm_psr_inhibit_get(struct drm_encoder *encoder);
 
 int rockchip_drm_psr_register(struct drm_encoder *encoder,
-			void (*psr_set)(struct drm_encoder *, bool enable));
+			int (*psr_set)(struct drm_encoder *, bool enable));
 void rockchip_drm_psr_unregister(struct drm_encoder *encoder);
 
 #endif /* __ROCKCHIP_DRM_PSR__ */
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 53d4afe15278..2121345a61af 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -76,6 +76,9 @@
 #define VOP_WIN_GET_YRGBADDR(vop, win) \
 		vop_readl(vop, win->base + win->phy->yrgb_mst.offset)
 
+#define VOP_WIN_TO_INDEX(vop_win) \
+	((vop_win) - (vop_win)->vop->win)
+
 #define to_vop(x) container_of(x, struct vop, crtc)
 #define to_vop_win(x) container_of(x, struct vop_win, base)
 
@@ -708,6 +711,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	dma_addr_t dma_addr;
 	uint32_t val;
 	bool rb_swap;
+	int win_index = VOP_WIN_TO_INDEX(vop_win);
 	int format;
 
 	/*
@@ -777,7 +781,14 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	rb_swap = has_rb_swapped(fb->format->format);
 	VOP_WIN_SET(vop, win, rb_swap, rb_swap);
 
-	if (fb->format->has_alpha) {
+	/*
+	 * Blending win0 with the background color doesn't seem to work
+	 * correctly. We only get the background color, no matter the contents
+	 * of the win0 framebuffer.  However, blending pre-multiplied color
+	 * with the default opaque black default background color is a no-op,
+	 * so we can just disable blending to get the correct result.
+	 */
+	if (fb->format->has_alpha && win_index > 0) {
 		VOP_WIN_SET(vop, win, dst_alpha_ctl,
 			    DST_FACTOR_M0(ALPHA_SRC_INVERSE));
 		val = SRC_ALPHA_EN(1) | SRC_COLOR_M0(ALPHA_SRC_PRE_MUL) |
@@ -925,6 +936,12 @@ static void vop_crtc_atomic_enable(struct drm_crtc *crtc,
 	if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
 	    !(vop_data->feature & VOP_FEATURE_OUTPUT_RGB10))
 		s->output_mode = ROCKCHIP_OUT_MODE_P888;
+
+	if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA && s->output_bpc == 8)
+		VOP_REG_SET(vop, common, pre_dither_down, 1);
+	else
+		VOP_REG_SET(vop, common, pre_dither_down, 0);
+
 	VOP_REG_SET(vop, common, out_mode, s->output_mode);
 
 	VOP_REG_SET(vop, modeset, htotal_pw, (htotal << 16) | hsync_len);
@@ -1017,22 +1034,15 @@ static void vop_crtc_atomic_flush(struct drm_crtc *crtc,
 			continue;
 
 		drm_framebuffer_get(old_plane_state->fb);
+		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 		drm_flip_work_queue(&vop->fb_unref_work, old_plane_state->fb);
 		set_bit(VOP_PENDING_FB_UNREF, &vop->pending);
-		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 	}
 }
 
-static void vop_crtc_atomic_begin(struct drm_crtc *crtc,
-				  struct drm_crtc_state *old_crtc_state)
-{
-	rockchip_drm_psr_flush(crtc);
-}
-
 static const struct drm_crtc_helper_funcs vop_crtc_helper_funcs = {
 	.mode_fixup = vop_crtc_mode_fixup,
 	.atomic_flush = vop_crtc_atomic_flush,
-	.atomic_begin = vop_crtc_atomic_begin,
 	.atomic_enable = vop_crtc_atomic_enable,
 	.atomic_disable = vop_crtc_atomic_disable,
 };
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
index 56bbd2e2a8ef..084acdd0019a 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
@@ -67,6 +67,7 @@ struct vop_common {
 	struct vop_reg cfg_done;
 	struct vop_reg dsp_blank;
 	struct vop_reg data_blank;
+	struct vop_reg pre_dither_down;
 	struct vop_reg dither_down;
 	struct vop_reg dither_up;
 	struct vop_reg gate_en;
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
index 2e4eea3459fe..08023d3ecb76 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
@@ -264,6 +264,7 @@ static const struct vop_common rk3288_common = {
 	.standby = VOP_REG_SYNC(RK3288_SYS_CTRL, 0x1, 22),
 	.gate_en = VOP_REG(RK3288_SYS_CTRL, 0x1, 23),
 	.mmu_en = VOP_REG(RK3288_SYS_CTRL, 0x1, 20),
+	.pre_dither_down = VOP_REG(RK3288_DSP_CTRL1, 0x1, 1),
 	.dither_down = VOP_REG(RK3288_DSP_CTRL1, 0xf, 1),
 	.dither_up = VOP_REG(RK3288_DSP_CTRL1, 0x1, 6),
 	.data_blank = VOP_REG(RK3288_DSP_CTRL0, 0x1, 19),
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 0d95888ccc3e..df1578d6f42e 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -30,7 +30,7 @@
 #include <drm/spsc_queue.h>
 
 #define CREATE_TRACE_POINTS
-#include <drm/gpu_scheduler_trace.h>
+#include "gpu_scheduler_trace.h"
 
 #define to_drm_sched_job(sched_job)		\
 		container_of((sched_job), struct drm_sched_job, queue_node)
@@ -117,15 +117,15 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
  * @sched	The pointer to the scheduler
  * @entity	The pointer to a valid drm_sched_entity
  * @rq		The run queue this entity belongs
- * @kernel	If this is an entity for the kernel
- * @jobs	The max number of jobs in the job queue
+ * @guilty      atomic_t set to 1 when a job on this queue
+ *              is found to be guilty causing a timeout
  *
  * return 0 if succeed. negative error code on failure
 */
 int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 			  struct drm_sched_entity *entity,
 			  struct drm_sched_rq *rq,
-			  uint32_t jobs, atomic_t *guilty)
+			  atomic_t *guilty)
 {
 	if (!(sched && entity && rq))
 		return -EINVAL;
@@ -135,9 +135,10 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 	entity->rq = rq;
 	entity->sched = sched;
 	entity->guilty = guilty;
+	entity->fini_status = 0;
+	entity->last_scheduled = NULL;
 
 	spin_lock_init(&entity->rq_lock);
-	spin_lock_init(&entity->queue_lock);
 	spsc_queue_init(&entity->job_queue);
 
 	atomic_set(&entity->fence_seq, 0);
@@ -196,19 +197,30 @@ static bool drm_sched_entity_is_ready(struct drm_sched_entity *entity)
 	return true;
 }
 
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+				    struct dma_fence_cb *cb)
+{
+	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
+						 finish_cb);
+	drm_sched_fence_finished(job->s_fence);
+	WARN_ON(job->s_fence->parent);
+	dma_fence_put(&job->s_fence->finished);
+	job->sched->ops->free_job(job);
+}
+
+
 /**
  * Destroy a context entity
  *
  * @sched       Pointer to scheduler instance
  * @entity	The pointer to a valid scheduler entity
  *
- * Cleanup and free the allocated resources.
+ * Splitting drm_sched_entity_fini() into two functions, The first one is does the waiting,
+ * removes the entity from the runqueue and returns an error when the process was killed.
  */
-void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
+void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity)
 {
-	int r;
-
 	if (!drm_sched_entity_is_initialized(sched, entity))
 		return;
 	/**
@@ -216,13 +228,28 @@ void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
 	 * queued IBs or discard them on SIGKILL
 	*/
 	if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL)
-		r = -ERESTARTSYS;
+		entity->fini_status = -ERESTARTSYS;
 	else
-		r = wait_event_killable(sched->job_scheduled,
+		entity->fini_status = wait_event_killable(sched->job_scheduled,
 					drm_sched_entity_is_idle(entity));
 	drm_sched_entity_set_rq(entity, NULL);
-	if (r) {
+}
+EXPORT_SYMBOL(drm_sched_entity_do_release);
+
+/**
+ * Destroy a context entity
+ *
+ * @sched       Pointer to scheduler instance
+ * @entity	The pointer to a valid scheduler entity
+ *
+ * The second one then goes over the entity and signals all jobs with an error code.
+ */
+void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
+			   struct drm_sched_entity *entity)
+{
+	if (entity->fini_status) {
 		struct drm_sched_job *job;
+		int r;
 
 		/* Park the kernel for a moment to make sure it isn't processing
 		 * our enity.
@@ -240,12 +267,25 @@ void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
 			struct drm_sched_fence *s_fence = job->s_fence;
 			drm_sched_fence_scheduled(s_fence);
 			dma_fence_set_error(&s_fence->finished, -ESRCH);
-			drm_sched_fence_finished(s_fence);
-			WARN_ON(s_fence->parent);
-			dma_fence_put(&s_fence->finished);
-			sched->ops->free_job(job);
+			r = dma_fence_add_callback(entity->last_scheduled, &job->finish_cb,
+							drm_sched_entity_kill_jobs_cb);
+			if (r == -ENOENT)
+				drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
+			else if (r)
+				DRM_ERROR("fence add callback failed (%d)\n", r);
 		}
 	}
+
+	dma_fence_put(entity->last_scheduled);
+	entity->last_scheduled = NULL;
+}
+EXPORT_SYMBOL(drm_sched_entity_cleanup);
+
+void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
+				struct drm_sched_entity *entity)
+{
+	drm_sched_entity_do_release(sched, entity);
+	drm_sched_entity_cleanup(sched, entity);
 }
 EXPORT_SYMBOL(drm_sched_entity_fini);
 
@@ -360,6 +400,9 @@ drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 	if (entity->guilty && atomic_read(entity->guilty))
 		dma_fence_set_error(&sched_job->s_fence->finished, -ECANCELED);
 
+	dma_fence_put(entity->last_scheduled);
+	entity->last_scheduled = dma_fence_get(&sched_job->s_fence->finished);
+
 	spsc_queue_pop(&entity->job_queue);
 	return sched_job;
 }
@@ -369,6 +412,10 @@ drm_sched_entity_pop_job(struct drm_sched_entity *entity)
  *
  * @sched_job		The pointer to job required to submit
  *
+ * Note: To guarantee that the order of insertion to queue matches
+ * the job's fence sequence number this function should be
+ * called with drm_sched_job_init under common lock.
+ *
  * Returns 0 for success, negative error code otherwise.
  */
 void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
@@ -379,11 +426,8 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 
 	trace_drm_sched_job(sched_job, entity);
 
-	spin_lock(&entity->queue_lock);
 	first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
 
-	spin_unlock(&entity->queue_lock);
-
 	/* first job wakes up scheduler */
 	if (first) {
 		/* Add the entity to the run queue */
@@ -529,6 +573,7 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 		spin_unlock(&sched->job_list_lock);
 		fence = sched->ops->run_job(s_job);
 		atomic_inc(&sched->hw_rq_count);
+
 		if (fence) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &s_fence->cb,
@@ -548,13 +593,19 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 }
 EXPORT_SYMBOL(drm_sched_job_recovery);
 
-/* init a sched_job with basic field */
+/**
+ * Init a sched_job with basic field
+ *
+ * Note: Refer to drm_sched_entity_push_job documentation
+ * for locking considerations.
+ */
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_gpu_scheduler *sched,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
 	job->sched = sched;
+	job->entity = entity;
 	job->s_priority = entity->rq - sched->sched_rq;
 	job->s_fence = drm_sched_fence_create(entity, owner);
 	if (!job->s_fence)
diff --git a/include/drm/gpu_scheduler_trace.h b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
index 0789e8d0a0e1..4998ad950a48 100644
--- a/include/drm/gpu_scheduler_trace.h
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
@@ -78,5 +78,5 @@ TRACE_EVENT(drm_sched_process_job,
 
 /* This part must be outside protection */
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/scheduler
 #include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
index 69aab086b913..df4461648e3f 100644
--- a/drivers/gpu/drm/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/scheduler/sched_fence.c
@@ -87,7 +87,7 @@ static bool drm_sched_fence_enable_signaling(struct dma_fence *f)
 }
 
 /**
- * amd_sched_fence_free - free up the fence memory
+ * drm_sched_fence_free - free up the fence memory
  *
  * @rcu: RCU callback head
  *
@@ -98,12 +98,11 @@ static void drm_sched_fence_free(struct rcu_head *rcu)
 	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
 	struct drm_sched_fence *fence = to_drm_sched_fence(f);
 
-	dma_fence_put(fence->parent);
 	kmem_cache_free(sched_fence_slab, fence);
 }
 
 /**
- * amd_sched_fence_release_scheduled - callback that fence can be freed
+ * drm_sched_fence_release_scheduled - callback that fence can be freed
  *
  * @fence: fence
  *
@@ -114,11 +113,12 @@ static void drm_sched_fence_release_scheduled(struct dma_fence *f)
 {
 	struct drm_sched_fence *fence = to_drm_sched_fence(f);
 
+	dma_fence_put(fence->parent);
 	call_rcu(&fence->finished.rcu, drm_sched_fence_free);
 }
 
 /**
- * amd_sched_fence_release_finished - drop extra reference
+ * drm_sched_fence_release_finished - drop extra reference
  *
  * @f: fence
  *
diff --git a/drivers/gpu/drm/selftests/Makefile b/drivers/gpu/drm/selftests/Makefile
index 4aebfc7f27d4..9fc349fa18e9 100644
--- a/drivers/gpu/drm/selftests/Makefile
+++ b/drivers/gpu/drm/selftests/Makefile
@@ -1 +1 @@
-obj-$(CONFIG_DRM_DEBUG_MM_SELFTEST) += test-drm_mm.o
+obj-$(CONFIG_DRM_DEBUG_SELFTEST) += test-drm_mm.o test-drm-helper.o
diff --git a/drivers/gpu/drm/selftests/drm_helper_selftests.h b/drivers/gpu/drm/selftests/drm_helper_selftests.h
new file mode 100644
index 000000000000..9771290ed228
--- /dev/null
+++ b/drivers/gpu/drm/selftests/drm_helper_selftests.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* List each unit test as selftest(name, function)
+ *
+ * The name is used as both an enum and expanded as igt__name to create
+ * a module parameter. It must be unique and legal for a C identifier.
+ *
+ * Tests are executed in order by igt/drm_selftests_helper
+ */
+selftest(check_plane_state, igt_check_plane_state)
diff --git a/drivers/gpu/drm/selftests/test-drm-helper.c b/drivers/gpu/drm/selftests/test-drm-helper.c
new file mode 100644
index 000000000000..a015712b43e8
--- /dev/null
+++ b/drivers/gpu/drm/selftests/test-drm-helper.c
@@ -0,0 +1,247 @@
+/*
+ * Test cases for the drm_kms_helper functions
+ */
+
+#define pr_fmt(fmt) "drm_kms_helper: " fmt
+
+#include <linux/module.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_modes.h>
+
+#define TESTS "drm_helper_selftests.h"
+#include "drm_selftest.h"
+
+#define FAIL(test, msg, ...) \
+	do { \
+		if (test) { \
+			pr_err("%s/%u: " msg, __FUNCTION__, __LINE__, ##__VA_ARGS__); \
+			return -EINVAL; \
+		} \
+	} while (0)
+
+#define FAIL_ON(x) FAIL((x), "%s", "FAIL_ON(" __stringify(x) ")\n")
+
+static void set_src(struct drm_plane_state *plane_state,
+		    unsigned src_x, unsigned src_y,
+		    unsigned src_w, unsigned src_h)
+{
+	plane_state->src_x = src_x;
+	plane_state->src_y = src_y;
+	plane_state->src_w = src_w;
+	plane_state->src_h = src_h;
+}
+
+static bool check_src_eq(struct drm_plane_state *plane_state,
+			 unsigned src_x, unsigned src_y,
+			 unsigned src_w, unsigned src_h)
+{
+	if (plane_state->src.x1 < 0) {
+		pr_err("src x coordinate %x should never be below 0.\n", plane_state->src.x1);
+		drm_rect_debug_print("src: ", &plane_state->src, true);
+		return false;
+	}
+	if (plane_state->src.y1 < 0) {
+		pr_err("src y coordinate %x should never be below 0.\n", plane_state->src.y1);
+		drm_rect_debug_print("src: ", &plane_state->src, true);
+		return false;
+	}
+
+	if (plane_state->src.x1 != src_x ||
+	    plane_state->src.y1 != src_y ||
+	    drm_rect_width(&plane_state->src) != src_w ||
+	    drm_rect_height(&plane_state->src) != src_h) {
+		drm_rect_debug_print("src: ", &plane_state->src, true);
+		return false;
+	}
+
+	return true;
+}
+
+static void set_crtc(struct drm_plane_state *plane_state,
+		     int crtc_x, int crtc_y,
+		     unsigned crtc_w, unsigned crtc_h)
+{
+	plane_state->crtc_x = crtc_x;
+	plane_state->crtc_y = crtc_y;
+	plane_state->crtc_w = crtc_w;
+	plane_state->crtc_h = crtc_h;
+}
+
+static bool check_crtc_eq(struct drm_plane_state *plane_state,
+			  int crtc_x, int crtc_y,
+			  unsigned crtc_w, unsigned crtc_h)
+{
+	if (plane_state->dst.x1 != crtc_x ||
+	    plane_state->dst.y1 != crtc_y ||
+	    drm_rect_width(&plane_state->dst) != crtc_w ||
+	    drm_rect_height(&plane_state->dst) != crtc_h) {
+		drm_rect_debug_print("dst: ", &plane_state->dst, false);
+
+		return false;
+	}
+
+	return true;
+}
+
+static int igt_check_plane_state(void *ignored)
+{
+	int ret;
+
+	const struct drm_crtc_state crtc_state = {
+		.crtc = ZERO_SIZE_PTR,
+		.enable = true,
+		.active = true,
+		.mode = {
+			DRM_MODE("1024x768", 0, 65000, 1024, 1048,
+				1184, 1344, 0, 768, 771, 777, 806, 0,
+				DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC)
+		},
+	};
+	struct drm_framebuffer fb = {
+		.width = 2048,
+		.height = 2048
+	};
+	struct drm_plane_state plane_state = {
+		.crtc = ZERO_SIZE_PTR,
+		.fb = &fb,
+		.rotation = DRM_MODE_ROTATE_0
+	};
+
+	/* Simple clipping, no scaling. */
+	set_src(&plane_state, 0, 0, fb.width << 16, fb.height << 16);
+	set_crtc(&plane_state, 0, 0, fb.width, fb.height);
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, false);
+	FAIL(ret < 0, "Simple clipping check should pass\n");
+	FAIL_ON(!plane_state.visible);
+	FAIL_ON(!check_src_eq(&plane_state, 0, 0, 1024 << 16, 768 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 0, 0, 1024, 768));
+
+	/* Rotated clipping + reflection, no scaling. */
+	plane_state.rotation = DRM_MODE_ROTATE_90 | DRM_MODE_REFLECT_X;
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, false);
+	FAIL(ret < 0, "Rotated clipping check should pass\n");
+	FAIL_ON(!plane_state.visible);
+	FAIL_ON(!check_src_eq(&plane_state, 0, 0, 768 << 16, 1024 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 0, 0, 1024, 768));
+	plane_state.rotation = DRM_MODE_ROTATE_0;
+
+	/* Check whether positioning works correctly. */
+	set_src(&plane_state, 0, 0, 1023 << 16, 767 << 16);
+	set_crtc(&plane_state, 0, 0, 1023, 767);
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, false);
+	FAIL(!ret, "Should not be able to position on the crtc with can_position=false\n");
+
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  true, false);
+	FAIL(ret < 0, "Simple positioning should work\n");
+	FAIL_ON(!plane_state.visible);
+	FAIL_ON(!check_src_eq(&plane_state, 0, 0, 1023 << 16, 767 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 0, 0, 1023, 767));
+
+	/* Simple scaling tests. */
+	set_src(&plane_state, 0, 0, 512 << 16, 384 << 16);
+	set_crtc(&plane_state, 0, 0, 1024, 768);
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  0x8001,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, false);
+	FAIL(!ret, "Upscaling out of range should fail.\n");
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  0x8000,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, false);
+	FAIL(ret < 0, "Upscaling exactly 2x should work\n");
+	FAIL_ON(!plane_state.visible);
+	FAIL_ON(!check_src_eq(&plane_state, 0, 0, 512 << 16, 384 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 0, 0, 1024, 768));
+
+	set_src(&plane_state, 0, 0, 2048 << 16, 1536 << 16);
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  0x1ffff, false, false);
+	FAIL(!ret, "Downscaling out of range should fail.\n");
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  0x20000, false, false);
+	FAIL(ret < 0, "Should succeed with exact scaling limit\n");
+	FAIL_ON(!plane_state.visible);
+	FAIL_ON(!check_src_eq(&plane_state, 0, 0, 2048 << 16, 1536 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 0, 0, 1024, 768));
+
+	/* Testing rounding errors. */
+	set_src(&plane_state, 0, 0, 0x40001, 0x40001);
+	set_crtc(&plane_state, 1022, 766, 4, 4);
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  0x10001,
+						  true, false);
+	FAIL(ret < 0, "Should succeed by clipping to exact multiple");
+	FAIL_ON(!plane_state.visible);
+	FAIL_ON(!check_src_eq(&plane_state, 0, 0, 2 << 16, 2 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 1022, 766, 2, 2));
+
+	set_src(&plane_state, 0x20001, 0x20001, 0x4040001, 0x3040001);
+	set_crtc(&plane_state, -2, -2, 1028, 772);
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  0x10001,
+						  false, false);
+	FAIL(ret < 0, "Should succeed by clipping to exact multiple");
+	FAIL_ON(!plane_state.visible);
+	FAIL_ON(!check_src_eq(&plane_state, 0x40002, 0x40002, 1024 << 16, 768 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 0, 0, 1024, 768));
+
+	set_src(&plane_state, 0, 0, 0x3ffff, 0x3ffff);
+	set_crtc(&plane_state, 1022, 766, 4, 4);
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  0xffff,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  true, false);
+	FAIL(ret < 0, "Should succeed by clipping to exact multiple");
+	FAIL_ON(!plane_state.visible);
+	/* Should not be rounded to 0x20001, which would be upscaling. */
+	FAIL_ON(!check_src_eq(&plane_state, 0, 0, 2 << 16, 2 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 1022, 766, 2, 2));
+
+	set_src(&plane_state, 0x1ffff, 0x1ffff, 0x403ffff, 0x303ffff);
+	set_crtc(&plane_state, -2, -2, 1028, 772);
+	ret = drm_atomic_helper_check_plane_state(&plane_state, &crtc_state,
+						  0xffff,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, false);
+	FAIL(ret < 0, "Should succeed by clipping to exact multiple");
+	FAIL_ON(!plane_state.visible);
+	FAIL_ON(!check_src_eq(&plane_state, 0x3fffe, 0x3fffe, 1024 << 16, 768 << 16));
+	FAIL_ON(!check_crtc_eq(&plane_state, 0, 0, 1024, 768));
+
+	return 0;
+}
+
+#include "drm_selftest.c"
+
+static int __init test_drm_helper_init(void)
+{
+	int err;
+
+	err = run_selftests(selftests, ARRAY_SIZE(selftests), NULL);
+
+	return err > 0 ? 0 : err;
+}
+
+module_init(test_drm_helper_init);
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/sti/Kconfig b/drivers/gpu/drm/sti/Kconfig
index cca4b3c9aeb5..1963cc1b1cc5 100644
--- a/drivers/gpu/drm/sti/Kconfig
+++ b/drivers/gpu/drm/sti/Kconfig
@@ -1,6 +1,6 @@
 config DRM_STI
 	tristate "DRM Support for STMicroelectronics SoC stiH4xx Series"
-	depends on DRM && (ARCH_STI || ARCH_MULTIPLATFORM)
+	depends on OF && DRM && (ARCH_STI || ARCH_MULTIPLATFORM)
 	select RESET_CONTROLLER
 	select DRM_KMS_HELPER
 	select DRM_GEM_CMA_HELPER
@@ -8,6 +8,5 @@ config DRM_STI
 	select DRM_PANEL
 	select FW_LOADER
 	select SND_SOC_HDMI_CODEC if SND_SOC
-	select OF
 	help
 	  Choose this option to enable DRM on STM stiH4xx chipset
diff --git a/drivers/gpu/drm/sti/sti_crtc.c b/drivers/gpu/drm/sti/sti_crtc.c
index 21e50d7b1f86..5824e6aca8f4 100644
--- a/drivers/gpu/drm/sti/sti_crtc.c
+++ b/drivers/gpu/drm/sti/sti_crtc.c
@@ -357,7 +357,7 @@ int sti_crtc_init(struct drm_device *drm_dev, struct sti_mixer *mixer,
 	res = drm_crtc_init_with_planes(drm_dev, crtc, primary, cursor,
 					&sti_crtc_funcs, NULL);
 	if (res) {
-		DRM_ERROR("Can't initialze CRTC\n");
+		DRM_ERROR("Can't initialize CRTC\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c
index 55b6967d27e1..90c46b49c931 100644
--- a/drivers/gpu/drm/sti/sti_drv.c
+++ b/drivers/gpu/drm/sti/sti_drv.c
@@ -119,30 +119,10 @@ err:
 	return ret;
 }
 
-static int sti_atomic_check(struct drm_device *dev,
-			    struct drm_atomic_state *state)
-{
-	int ret;
-
-	ret = drm_atomic_helper_check_modeset(dev, state);
-	if (ret)
-		return ret;
-
-	ret = drm_atomic_normalize_zpos(dev, state);
-	if (ret)
-		return ret;
-
-	ret = drm_atomic_helper_check_planes(dev, state);
-	if (ret)
-		return ret;
-
-	return ret;
-}
-
 static const struct drm_mode_config_funcs sti_mode_config_funcs = {
 	.fb_create = drm_gem_fb_create,
 	.output_poll_changed = drm_fb_helper_output_poll_changed,
-	.atomic_check = sti_atomic_check,
+	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
 };
 
@@ -160,6 +140,8 @@ static void sti_mode_config_init(struct drm_device *dev)
 	dev->mode_config.max_height = STI_MAX_FB_HEIGHT;
 
 	dev->mode_config.funcs = &sti_mode_config_funcs;
+
+	dev->mode_config.normalize_zpos = true;
 }
 
 DEFINE_DRM_GEM_CMA_FOPS(sti_driver_fops);
diff --git a/drivers/gpu/drm/sti/sti_plane.c b/drivers/gpu/drm/sti/sti_plane.c
index b074609c960a..b48cd86e0250 100644
--- a/drivers/gpu/drm/sti/sti_plane.c
+++ b/drivers/gpu/drm/sti/sti_plane.c
@@ -40,6 +40,7 @@ void sti_plane_update_fps(struct sti_plane *plane,
 			  bool new_frame,
 			  bool new_field)
 {
+	struct drm_plane_state *state = plane->drm_plane.state;
 	ktime_t now;
 	struct sti_fps_info *fps;
 	int fpks, fipks, ms_since_last, num_frames, num_fields;
@@ -66,14 +67,14 @@ void sti_plane_update_fps(struct sti_plane *plane,
 	fps->last_timestamp = now;
 	fps->last_frame_counter = fps->curr_frame_counter;
 
-	if (plane->drm_plane.fb) {
+	if (state->fb) {
 		fpks = (num_frames * 1000000) / ms_since_last;
 		snprintf(plane->fps_info.fps_str, FPS_LENGTH,
 			 "%-8s %4dx%-4d %.4s @ %3d.%-3.3d fps (%s)",
 			 plane->drm_plane.name,
-			 plane->drm_plane.fb->width,
-			 plane->drm_plane.fb->height,
-			 (char *)&plane->drm_plane.fb->format->format,
+			 state->fb->width,
+			 state->fb->height,
+			 (char *)&state->fb->format->format,
 			 fpks / 1000, fpks % 1000,
 			 sti_plane_to_str(plane));
 	}
diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c
index 9ab00a87f7cc..8698e08313e1 100644
--- a/drivers/gpu/drm/stm/drv.c
+++ b/drivers/gpu/drm/stm/drv.c
@@ -72,8 +72,6 @@ static struct drm_driver drv_driver = {
 	.gem_prime_vmap = drm_gem_cma_prime_vmap,
 	.gem_prime_vunmap = drm_gem_cma_prime_vunmap,
 	.gem_prime_mmap = drm_gem_cma_prime_mmap,
-	.enable_vblank = ltdc_crtc_enable_vblank,
-	.disable_vblank = ltdc_crtc_disable_vblank,
 };
 
 static int drv_load(struct drm_device *ddev)
diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index 1a3277e483d5..d997a6014d6c 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -392,9 +392,6 @@ static void ltdc_crtc_update_clut(struct drm_crtc *crtc)
 	u32 val;
 	int i;
 
-	if (!crtc || !crtc->state)
-		return;
-
 	if (!crtc->state->color_mgmt_changed || !crtc->state->gamma_lut)
 		return;
 
@@ -448,6 +445,43 @@ static void ltdc_crtc_atomic_disable(struct drm_crtc *crtc,
 	reg_set(ldev->regs, LTDC_SRCR, SRCR_IMR);
 }
 
+#define CLK_TOLERANCE_HZ 50
+
+static enum drm_mode_status
+ltdc_crtc_mode_valid(struct drm_crtc *crtc,
+		     const struct drm_display_mode *mode)
+{
+	struct ltdc_device *ldev = crtc_to_ltdc(crtc);
+	int target = mode->clock * 1000;
+	int target_min = target - CLK_TOLERANCE_HZ;
+	int target_max = target + CLK_TOLERANCE_HZ;
+	int result;
+
+	/*
+	 * Accept all "preferred" modes:
+	 * - this is important for panels because panel clock tolerances are
+	 *   bigger than hdmi ones and there is no reason to not accept them
+	 *   (the fps may vary a little but it is not a problem).
+	 * - the hdmi preferred mode will be accepted too, but userland will
+	 *   be able to use others hdmi "valid" modes if necessary.
+	 */
+	if (mode->type & DRM_MODE_TYPE_PREFERRED)
+		return MODE_OK;
+
+	result = clk_round_rate(ldev->pixel_clk, target);
+
+	DRM_DEBUG_DRIVER("clk rate target %d, available %d\n", target, result);
+
+	/*
+	 * Filter modes according to the clock value, particularly useful for
+	 * hdmi modes that require precise pixel clocks.
+	 */
+	if (result < target_min || result > target_max)
+		return MODE_CLOCK_RANGE;
+
+	return MODE_OK;
+}
+
 static bool ltdc_crtc_mode_fixup(struct drm_crtc *crtc,
 				 const struct drm_display_mode *mode,
 				 struct drm_display_mode *adjusted_mode)
@@ -562,6 +596,7 @@ static void ltdc_crtc_atomic_flush(struct drm_crtc *crtc,
 }
 
 static const struct drm_crtc_helper_funcs ltdc_crtc_helper_funcs = {
+	.mode_valid = ltdc_crtc_mode_valid,
 	.mode_fixup = ltdc_crtc_mode_fixup,
 	.mode_set_nofb = ltdc_crtc_mode_set_nofb,
 	.atomic_flush = ltdc_crtc_atomic_flush,
@@ -569,9 +604,9 @@ static const struct drm_crtc_helper_funcs ltdc_crtc_helper_funcs = {
 	.atomic_disable = ltdc_crtc_atomic_disable,
 };
 
-int ltdc_crtc_enable_vblank(struct drm_device *ddev, unsigned int pipe)
+static int ltdc_crtc_enable_vblank(struct drm_crtc *crtc)
 {
-	struct ltdc_device *ldev = ddev->dev_private;
+	struct ltdc_device *ldev = crtc_to_ltdc(crtc);
 
 	DRM_DEBUG_DRIVER("\n");
 	reg_set(ldev->regs, LTDC_IER, IER_LIE);
@@ -579,9 +614,9 @@ int ltdc_crtc_enable_vblank(struct drm_device *ddev, unsigned int pipe)
 	return 0;
 }
 
-void ltdc_crtc_disable_vblank(struct drm_device *ddev, unsigned int pipe)
+static void ltdc_crtc_disable_vblank(struct drm_crtc *crtc)
 {
-	struct ltdc_device *ldev = ddev->dev_private;
+	struct ltdc_device *ldev = crtc_to_ltdc(crtc);
 
 	DRM_DEBUG_DRIVER("\n");
 	reg_clear(ldev->regs, LTDC_IER, IER_LIE);
@@ -594,6 +629,8 @@ static const struct drm_crtc_funcs ltdc_crtc_funcs = {
 	.reset = drm_atomic_helper_crtc_reset,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
+	.enable_vblank = ltdc_crtc_enable_vblank,
+	.disable_vblank = ltdc_crtc_disable_vblank,
 	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 };
 
@@ -727,6 +764,8 @@ static void ltdc_plane_atomic_update(struct drm_plane *plane,
 	reg_update_bits(ldev->regs, LTDC_L1CR + lofs,
 			LXCR_LEN | LXCR_CLUTEN, val);
 
+	ldev->plane_fpsi[plane->index].counter++;
+
 	mutex_lock(&ldev->err_lock);
 	if (ldev->error_status & ISR_FUIF) {
 		DRM_DEBUG_DRIVER("Fifo underrun\n");
@@ -752,6 +791,25 @@ static void ltdc_plane_atomic_disable(struct drm_plane *plane,
 			 oldstate->crtc->base.id, plane->base.id);
 }
 
+static void ltdc_plane_atomic_print_state(struct drm_printer *p,
+					  const struct drm_plane_state *state)
+{
+	struct drm_plane *plane = state->plane;
+	struct ltdc_device *ldev = plane_to_ltdc(plane);
+	struct fps_info *fpsi = &ldev->plane_fpsi[plane->index];
+	int ms_since_last;
+	ktime_t now;
+
+	now = ktime_get();
+	ms_since_last = ktime_to_ms(ktime_sub(now, fpsi->last_timestamp));
+
+	drm_printf(p, "\tuser_updates=%dfps\n",
+		   DIV_ROUND_CLOSEST(fpsi->counter * 1000, ms_since_last));
+
+	fpsi->last_timestamp = now;
+	fpsi->counter = 0;
+}
+
 static const struct drm_plane_funcs ltdc_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
@@ -759,6 +817,7 @@ static const struct drm_plane_funcs ltdc_plane_funcs = {
 	.reset = drm_atomic_helper_plane_reset,
 	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+	.atomic_print_state = ltdc_plane_atomic_print_state,
 };
 
 static const struct drm_plane_helper_funcs ltdc_plane_helper_funcs = {
@@ -801,13 +860,13 @@ static struct drm_plane *ltdc_plane_create(struct drm_device *ddev,
 
 	plane = devm_kzalloc(dev, sizeof(*plane), GFP_KERNEL);
 	if (!plane)
-		return 0;
+		return NULL;
 
 	ret = drm_universal_plane_init(ddev, plane, possible_crtcs,
 				       &ltdc_plane_funcs, formats, nb_fmt,
 				       NULL, type, NULL);
 	if (ret < 0)
-		return 0;
+		return NULL;
 
 	drm_plane_helper_add(plane, &ltdc_plane_helper_funcs);
 
@@ -966,14 +1025,13 @@ int ltdc_load(struct drm_device *ddev)
 						  &bridge[i]);
 
 		/*
-		 * If at least one endpoint is ready, continue probing,
-		 * else if at least one endpoint is -EPROBE_DEFER and
-		 * there is no previous ready endpoints, defer probing.
+		 * If at least one endpoint is -EPROBE_DEFER, defer probing,
+		 * else if at least one endpoint is ready, continue probing.
 		 */
-		if (!ret)
+		if (ret == -EPROBE_DEFER)
+			return ret;
+		else if (!ret)
 			endpoint_not_ready = 0;
-		else if (ret == -EPROBE_DEFER && endpoint_not_ready)
-			endpoint_not_ready = -EPROBE_DEFER;
 	}
 
 	if (endpoint_not_ready)
diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h
index edb268129c54..1e16d6afb0d2 100644
--- a/drivers/gpu/drm/stm/ltdc.h
+++ b/drivers/gpu/drm/stm/ltdc.h
@@ -20,6 +20,13 @@ struct ltdc_caps {
 	bool non_alpha_only_l1; /* non-native no-alpha formats on layer 1 */
 };
 
+#define LTDC_MAX_LAYER	4
+
+struct fps_info {
+	unsigned int counter;
+	ktime_t last_timestamp;
+};
+
 struct ltdc_device {
 	void __iomem *regs;
 	struct clk *pixel_clk;	/* lcd pixel clock */
@@ -27,10 +34,9 @@ struct ltdc_device {
 	struct ltdc_caps caps;
 	u32 error_status;
 	u32 irq_status;
+	struct fps_info plane_fpsi[LTDC_MAX_LAYER];
 };
 
-int ltdc_crtc_enable_vblank(struct drm_device *dev, unsigned int pipe);
-void ltdc_crtc_disable_vblank(struct drm_device *dev, unsigned int pipe);
 int ltdc_load(struct drm_device *ddev);
 void ltdc_unload(struct drm_device *ddev);
 
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index eee6bc0eaf97..156a865c3e6d 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -40,6 +40,16 @@ config DRM_SUN4I_BACKEND
 	  do some alpha blending and feed graphics to TCON. If M is
 	  selected the module will be called sun4i-backend.
 
+config DRM_SUN6I_DSI
+	tristate "Allwinner A31 MIPI-DSI Controller Support"
+	default MACH_SUN8I
+	select CRC_CCITT
+	select DRM_MIPI_DSI
+	help
+	  Choose this option if you want have an Allwinner SoC with
+	  MIPI-DSI support. If M is selected the module will be called
+	  sun6i-dsi
+
 config DRM_SUN8I_DW_HDMI
 	tristate "Support for Allwinner version of DesignWare HDMI"
 	depends on DRM_SUN4I
diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile
index 330843ce4280..2589f4acd5ae 100644
--- a/drivers/gpu/drm/sun4i/Makefile
+++ b/drivers/gpu/drm/sun4i/Makefile
@@ -24,6 +24,9 @@ sun4i-tcon-y			+= sun4i_lvds.o
 sun4i-tcon-y			+= sun4i_tcon.o
 sun4i-tcon-y			+= sun4i_rgb.o
 
+sun6i-dsi-y			+= sun6i_mipi_dphy.o
+sun6i-dsi-y			+= sun6i_mipi_dsi.o
+
 obj-$(CONFIG_DRM_SUN4I)		+= sun4i-drm.o
 obj-$(CONFIG_DRM_SUN4I)		+= sun4i-tcon.o
 obj-$(CONFIG_DRM_SUN4I)		+= sun4i_tv.o
@@ -31,5 +34,6 @@ obj-$(CONFIG_DRM_SUN4I)		+= sun6i_drc.o
 
 obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o sun4i-frontend.o
 obj-$(CONFIG_DRM_SUN4I_HDMI)	+= sun4i-drm-hdmi.o
+obj-$(CONFIG_DRM_SUN6I_DSI)	+= sun6i-dsi.o
 obj-$(CONFIG_DRM_SUN8I_DW_HDMI)	+= sun8i-drm-hdmi.o
 obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 9bad54f3de38..de0a76dfa1a2 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -295,6 +295,15 @@ int sun4i_backend_update_layer_formats(struct sun4i_backend *backend,
 	DRM_DEBUG_DRIVER("Switching display backend interlaced mode %s\n",
 			 interlaced ? "on" : "off");
 
+	val = SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA(state->alpha >> 8);
+	if (state->alpha != DRM_BLEND_ALPHA_OPAQUE)
+		val |= SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN;
+	regmap_update_bits(backend->engine.regs,
+			   SUN4I_BACKEND_ATTCTL_REG0(layer),
+			   SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_MASK |
+			   SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN,
+			   val);
+
 	if (sun4i_backend_format_is_yuv(fb->format->format))
 		return sun4i_backend_update_yuv_format(backend, layer, plane);
 
@@ -490,7 +499,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
 		DRM_DEBUG_DRIVER("Plane FB format is %s\n",
 				 drm_get_format_name(fb->format->format,
 						     &format_name));
-		if (fb->format->has_alpha)
+		if (fb->format->has_alpha || (plane_state->alpha != DRM_BLEND_ALPHA_OPAQUE))
 			num_alpha_planes++;
 
 		if (sun4i_backend_format_is_yuv(fb->format->format)) {
@@ -548,7 +557,8 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
 	}
 
 	/* We can't have an alpha plane at the lowest position */
-	if (plane_states[0]->fb->format->has_alpha)
+	if (plane_states[0]->fb->format->has_alpha ||
+	    (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE))
 		return -EINVAL;
 
 	for (i = 1; i < num_planes; i++) {
@@ -560,7 +570,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
 		 * The only alpha position is the lowest plane of the
 		 * second pipe.
 		 */
-		if (fb->format->has_alpha)
+		if (fb->format->has_alpha || (p_state->alpha != DRM_BLEND_ALPHA_OPAQUE))
 			current_pipe++;
 
 		s_state->pipe = current_pipe;
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.h b/drivers/gpu/drm/sun4i/sun4i_backend.h
index 316f2179e9e1..4caee0392fa4 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.h
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.h
@@ -68,12 +68,15 @@
 #define SUN4I_BACKEND_CKMIN_REG			0x884
 #define SUN4I_BACKEND_CKCFG_REG			0x888
 #define SUN4I_BACKEND_ATTCTL_REG0(l)		(0x890 + (0x4 * (l)))
+#define SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_MASK	GENMASK(31, 24)
+#define SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA(x)		((x) << 24)
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PIPESEL_MASK	BIT(15)
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PIPESEL(x)		((x) << 15)
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PRISEL_MASK	GENMASK(11, 10)
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PRISEL(x)			((x) << 10)
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_YUVEN		BIT(2)
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_VDOEN		BIT(1)
+#define SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN	BIT(0)
 
 #define SUN4I_BACKEND_ATTCTL_REG1(l)		(0x8a0 + (0x4 * (l)))
 #define SUN4I_BACKEND_ATTCTL_REG1_LAY_HSCAFCT		GENMASK(15, 14)
diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.c b/drivers/gpu/drm/sun4i/sun4i_layer.c
index 2949a3c912c1..750ad24de1d7 100644
--- a/drivers/gpu/drm/sun4i/sun4i_layer.c
+++ b/drivers/gpu/drm/sun4i/sun4i_layer.c
@@ -37,6 +37,7 @@ static void sun4i_backend_layer_reset(struct drm_plane *plane)
 	if (state) {
 		plane->state = &state->state;
 		plane->state->plane = plane;
+		plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE;
 		plane->state->zpos = layer->id;
 	}
 }
@@ -167,6 +168,7 @@ static struct sun4i_layer *sun4i_layer_init_one(struct drm_device *drm,
 			     &sun4i_backend_layer_helper_funcs);
 	layer->backend = backend;
 
+	drm_plane_create_alpha_property(&layer->plane);
 	drm_plane_create_zpos_property(&layer->plane, 0, 0,
 				       SUN4I_BACKEND_NUM_LAYERS - 1);
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index bffff4c9fbf5..be3f14d7746d 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -94,64 +94,9 @@ static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder)
 	}
 }
 
-static enum drm_mode_status sun4i_lvds_encoder_mode_valid(struct drm_encoder *crtc,
-							  const struct drm_display_mode *mode)
-{
-	struct sun4i_lvds *lvds = drm_encoder_to_sun4i_lvds(crtc);
-	struct sun4i_tcon *tcon = lvds->tcon;
-	u32 hsync = mode->hsync_end - mode->hsync_start;
-	u32 vsync = mode->vsync_end - mode->vsync_start;
-	unsigned long rate = mode->clock * 1000;
-	long rounded_rate;
-
-	DRM_DEBUG_DRIVER("Validating modes...\n");
-
-	if (hsync < 1)
-		return MODE_HSYNC_NARROW;
-
-	if (hsync > 0x3ff)
-		return MODE_HSYNC_WIDE;
-
-	if ((mode->hdisplay < 1) || (mode->htotal < 1))
-		return MODE_H_ILLEGAL;
-
-	if ((mode->hdisplay > 0x7ff) || (mode->htotal > 0xfff))
-		return MODE_BAD_HVALUE;
-
-	DRM_DEBUG_DRIVER("Horizontal parameters OK\n");
-
-	if (vsync < 1)
-		return MODE_VSYNC_NARROW;
-
-	if (vsync > 0x3ff)
-		return MODE_VSYNC_WIDE;
-
-	if ((mode->vdisplay < 1) || (mode->vtotal < 1))
-		return MODE_V_ILLEGAL;
-
-	if ((mode->vdisplay > 0x7ff) || (mode->vtotal > 0xfff))
-		return MODE_BAD_VVALUE;
-
-	DRM_DEBUG_DRIVER("Vertical parameters OK\n");
-
-	tcon->dclk_min_div = 7;
-	tcon->dclk_max_div = 7;
-	rounded_rate = clk_round_rate(tcon->dclk, rate);
-	if (rounded_rate < rate)
-		return MODE_CLOCK_LOW;
-
-	if (rounded_rate > rate)
-		return MODE_CLOCK_HIGH;
-
-	DRM_DEBUG_DRIVER("Clock rate OK\n");
-
-	return MODE_OK;
-}
-
 static const struct drm_encoder_helper_funcs sun4i_lvds_enc_helper_funcs = {
 	.disable	= sun4i_lvds_encoder_disable,
 	.enable		= sun4i_lvds_encoder_enable,
-	.mode_valid	= sun4i_lvds_encoder_mode_valid,
 };
 
 static const struct drm_encoder_funcs sun4i_lvds_enc_funcs = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index c3d92d537240..08747fc3ee71 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -35,6 +35,7 @@
 #include "sun4i_lvds.h"
 #include "sun4i_rgb.h"
 #include "sun4i_tcon.h"
+#include "sun6i_mipi_dsi.h"
 #include "sunxi_engine.h"
 
 static struct drm_connector *sun4i_tcon_get_connector(const struct drm_encoder *encoder)
@@ -169,6 +170,7 @@ void sun4i_tcon_set_status(struct sun4i_tcon *tcon,
 	case DRM_MODE_ENCODER_LVDS:
 		is_lvds = true;
 		/* Fallthrough */
+	case DRM_MODE_ENCODER_DSI:
 	case DRM_MODE_ENCODER_NONE:
 		channel = 0;
 		break;
@@ -201,7 +203,8 @@ void sun4i_tcon_enable_vblank(struct sun4i_tcon *tcon, bool enable)
 	DRM_DEBUG_DRIVER("%sabling VBLANK interrupt\n", enable ? "En" : "Dis");
 
 	mask = SUN4I_TCON_GINT0_VBLANK_ENABLE(0) |
-	       SUN4I_TCON_GINT0_VBLANK_ENABLE(1);
+		SUN4I_TCON_GINT0_VBLANK_ENABLE(1) |
+		SUN4I_TCON_GINT0_TCON0_TRI_FINISH_ENABLE;
 
 	if (enable)
 		val = mask;
@@ -273,6 +276,71 @@ static void sun4i_tcon0_mode_set_common(struct sun4i_tcon *tcon,
 		     SUN4I_TCON0_BASIC0_Y(mode->crtc_vdisplay));
 }
 
+static void sun4i_tcon0_mode_set_cpu(struct sun4i_tcon *tcon,
+				     struct mipi_dsi_device *device,
+				     const struct drm_display_mode *mode)
+{
+	u8 bpp = mipi_dsi_pixel_format_to_bpp(device->format);
+	u8 lanes = device->lanes;
+	u32 block_space, start_delay;
+	u32 tcon_div;
+
+	tcon->dclk_min_div = 4;
+	tcon->dclk_max_div = 127;
+
+	sun4i_tcon0_mode_set_common(tcon, mode);
+
+	regmap_update_bits(tcon->regs, SUN4I_TCON0_CTL_REG,
+			   SUN4I_TCON0_CTL_IF_MASK,
+			   SUN4I_TCON0_CTL_IF_8080);
+
+	regmap_write(tcon->regs, SUN4I_TCON_ECC_FIFO_REG,
+		     SUN4I_TCON_ECC_FIFO_EN);
+
+	regmap_write(tcon->regs, SUN4I_TCON0_CPU_IF_REG,
+		     SUN4I_TCON0_CPU_IF_MODE_DSI |
+		     SUN4I_TCON0_CPU_IF_TRI_FIFO_FLUSH |
+		     SUN4I_TCON0_CPU_IF_TRI_FIFO_EN |
+		     SUN4I_TCON0_CPU_IF_TRI_EN);
+
+	/*
+	 * This looks suspicious, but it works...
+	 *
+	 * The datasheet says that this should be set higher than 20 *
+	 * pixel cycle, but it's not clear what a pixel cycle is.
+	 */
+	regmap_read(tcon->regs, SUN4I_TCON0_DCLK_REG, &tcon_div);
+	tcon_div &= GENMASK(6, 0);
+	block_space = mode->htotal * bpp / (tcon_div * lanes);
+	block_space -= mode->hdisplay + 40;
+
+	regmap_write(tcon->regs, SUN4I_TCON0_CPU_TRI0_REG,
+		     SUN4I_TCON0_CPU_TRI0_BLOCK_SPACE(block_space) |
+		     SUN4I_TCON0_CPU_TRI0_BLOCK_SIZE(mode->hdisplay));
+
+	regmap_write(tcon->regs, SUN4I_TCON0_CPU_TRI1_REG,
+		     SUN4I_TCON0_CPU_TRI1_BLOCK_NUM(mode->vdisplay));
+
+	start_delay = (mode->crtc_vtotal - mode->crtc_vdisplay - 10 - 1);
+	start_delay = start_delay * mode->crtc_htotal * 149;
+	start_delay = start_delay / (mode->crtc_clock / 1000) / 8;
+	regmap_write(tcon->regs, SUN4I_TCON0_CPU_TRI2_REG,
+		     SUN4I_TCON0_CPU_TRI2_TRANS_START_SET(10) |
+		     SUN4I_TCON0_CPU_TRI2_START_DELAY(start_delay));
+
+	/*
+	 * The Allwinner BSP has a comment that the period should be
+	 * the display clock * 15, but uses an hardcoded 3000...
+	 */
+	regmap_write(tcon->regs, SUN4I_TCON_SAFE_PERIOD_REG,
+		     SUN4I_TCON_SAFE_PERIOD_NUM(3000) |
+		     SUN4I_TCON_SAFE_PERIOD_MODE(3));
+
+	/* Enable the output on the pins */
+	regmap_write(tcon->regs, SUN4I_TCON0_IO_TRI_REG,
+		     0xe0000000);
+}
+
 static void sun4i_tcon0_mode_set_lvds(struct sun4i_tcon *tcon,
 				      const struct drm_encoder *encoder,
 				      const struct drm_display_mode *mode)
@@ -538,7 +606,17 @@ void sun4i_tcon_mode_set(struct sun4i_tcon *tcon,
 			 const struct drm_encoder *encoder,
 			 const struct drm_display_mode *mode)
 {
+	struct sun6i_dsi *dsi;
+
 	switch (encoder->encoder_type) {
+	case DRM_MODE_ENCODER_DSI:
+		/*
+		 * This is not really elegant, but it's the "cleaner"
+		 * way I could think of...
+		 */
+		dsi = encoder_to_sun6i_dsi(encoder);
+		sun4i_tcon0_mode_set_cpu(tcon, dsi->device, mode);
+		break;
 	case DRM_MODE_ENCODER_LVDS:
 		sun4i_tcon0_mode_set_lvds(tcon, encoder, mode);
 		break;
@@ -582,7 +660,8 @@ static irqreturn_t sun4i_tcon_handler(int irq, void *private)
 	regmap_read(tcon->regs, SUN4I_TCON_GINT0_REG, &status);
 
 	if (!(status & (SUN4I_TCON_GINT0_VBLANK_INT(0) |
-			SUN4I_TCON_GINT0_VBLANK_INT(1))))
+			SUN4I_TCON_GINT0_VBLANK_INT(1) |
+			SUN4I_TCON_GINT0_TCON0_TRI_FINISH_INT)))
 		return IRQ_NONE;
 
 	drm_crtc_handle_vblank(&scrtc->crtc);
@@ -591,7 +670,8 @@ static irqreturn_t sun4i_tcon_handler(int irq, void *private)
 	/* Acknowledge the interrupt */
 	regmap_update_bits(tcon->regs, SUN4I_TCON_GINT0_REG,
 			   SUN4I_TCON_GINT0_VBLANK_INT(0) |
-			   SUN4I_TCON_GINT0_VBLANK_INT(1),
+			   SUN4I_TCON_GINT0_VBLANK_INT(1) |
+			   SUN4I_TCON_GINT0_TCON0_TRI_FINISH_INT,
 			   0);
 
 	if (engine->ops->vblank_quirk)
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h
index 161e09427124..f6a071cd5a6f 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.h
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h
@@ -28,13 +28,32 @@
 
 #define SUN4I_TCON_GINT0_REG			0x4
 #define SUN4I_TCON_GINT0_VBLANK_ENABLE(pipe)		BIT(31 - (pipe))
+#define SUN4I_TCON_GINT0_TCON0_TRI_FINISH_ENABLE	BIT(27)
+#define SUN4I_TCON_GINT0_TCON0_TRI_COUNTER_ENABLE	BIT(26)
 #define SUN4I_TCON_GINT0_VBLANK_INT(pipe)		BIT(15 - (pipe))
+#define SUN4I_TCON_GINT0_TCON0_TRI_FINISH_INT		BIT(11)
+#define SUN4I_TCON_GINT0_TCON0_TRI_COUNTER_INT		BIT(10)
 
 #define SUN4I_TCON_GINT1_REG			0x8
+
 #define SUN4I_TCON_FRM_CTL_REG			0x10
+#define SUN4I_TCON_FRM_CTL_EN				BIT(31)
+
+#define SUN4I_TCON_FRM_SEED_PR_REG		0x14
+#define SUN4I_TCON_FRM_SEED_PG_REG		0x18
+#define SUN4I_TCON_FRM_SEED_PB_REG		0x1c
+#define SUN4I_TCON_FRM_SEED_LR_REG		0x20
+#define SUN4I_TCON_FRM_SEED_LG_REG		0x24
+#define SUN4I_TCON_FRM_SEED_LB_REG		0x28
+#define SUN4I_TCON_FRM_TBL0_REG			0x2c
+#define SUN4I_TCON_FRM_TBL1_REG			0x30
+#define SUN4I_TCON_FRM_TBL2_REG			0x34
+#define SUN4I_TCON_FRM_TBL3_REG			0x38
 
 #define SUN4I_TCON0_CTL_REG			0x40
 #define SUN4I_TCON0_CTL_TCON_ENABLE			BIT(31)
+#define SUN4I_TCON0_CTL_IF_MASK				GENMASK(25, 24)
+#define SUN4I_TCON0_CTL_IF_8080				(1 << 24)
 #define SUN4I_TCON0_CTL_CLK_DELAY_MASK			GENMASK(8, 4)
 #define SUN4I_TCON0_CTL_CLK_DELAY(delay)		((delay << 4) & SUN4I_TCON0_CTL_CLK_DELAY_MASK)
 #define SUN4I_TCON0_CTL_SRC_SEL_MASK			GENMASK(2, 0)
@@ -61,7 +80,14 @@
 #define SUN4I_TCON0_BASIC3_V_SYNC(height)		(((height) - 1) & 0x7ff)
 
 #define SUN4I_TCON0_HV_IF_REG			0x58
+
 #define SUN4I_TCON0_CPU_IF_REG			0x60
+#define SUN4I_TCON0_CPU_IF_MODE_MASK			GENMASK(31, 28)
+#define SUN4I_TCON0_CPU_IF_MODE_DSI			(1 << 28)
+#define SUN4I_TCON0_CPU_IF_TRI_FIFO_FLUSH		BIT(16)
+#define SUN4I_TCON0_CPU_IF_TRI_FIFO_EN			BIT(2)
+#define SUN4I_TCON0_CPU_IF_TRI_EN			BIT(0)
+
 #define SUN4I_TCON0_CPU_WR_REG			0x64
 #define SUN4I_TCON0_CPU_RD0_REG			0x68
 #define SUN4I_TCON0_CPU_RDA_REG			0x6c
@@ -128,6 +154,10 @@
 
 #define SUN4I_TCON1_IO_POL_REG			0xf0
 #define SUN4I_TCON1_IO_TRI_REG			0xf4
+
+#define SUN4I_TCON_ECC_FIFO_REG			0xf8
+#define SUN4I_TCON_ECC_FIFO_EN				BIT(3)
+
 #define SUN4I_TCON_CEU_CTL_REG			0x100
 #define SUN4I_TCON_CEU_MUL_RR_REG		0x110
 #define SUN4I_TCON_CEU_MUL_RG_REG		0x114
@@ -144,6 +174,22 @@
 #define SUN4I_TCON_CEU_RANGE_R_REG		0x140
 #define SUN4I_TCON_CEU_RANGE_G_REG		0x144
 #define SUN4I_TCON_CEU_RANGE_B_REG		0x148
+
+#define SUN4I_TCON0_CPU_TRI0_REG		0x160
+#define SUN4I_TCON0_CPU_TRI0_BLOCK_SPACE(space)		((((space) - 1) & 0xfff) << 16)
+#define SUN4I_TCON0_CPU_TRI0_BLOCK_SIZE(size)		(((size) - 1) & 0xfff)
+
+#define SUN4I_TCON0_CPU_TRI1_REG		0x164
+#define SUN4I_TCON0_CPU_TRI1_BLOCK_NUM(num)		(((num) - 1) & 0xffff)
+
+#define SUN4I_TCON0_CPU_TRI2_REG		0x168
+#define SUN4I_TCON0_CPU_TRI2_START_DELAY(delay)		(((delay) & 0xffff) << 16)
+#define SUN4I_TCON0_CPU_TRI2_TRANS_START_SET(set)	((set) & 0xfff)
+
+#define SUN4I_TCON_SAFE_PERIOD_REG		0x1f0
+#define SUN4I_TCON_SAFE_PERIOD_NUM(num)			(((num) & 0xfff) << 16)
+#define SUN4I_TCON_SAFE_PERIOD_MODE(mode)		((mode) & 0x3)
+
 #define SUN4I_TCON_MUX_CTRL_REG			0x200
 
 #define SUN4I_TCON0_LVDS_ANA0_REG		0x220
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dphy.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dphy.c
new file mode 100644
index 000000000000..e4d19431fa0e
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dphy.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2016 Allwinnertech Co., Ltd.
+ * Copyright (C) 2017-2018 Bootlin
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/of_address.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+
+#include "sun6i_mipi_dsi.h"
+
+#define SUN6I_DPHY_GCTL_REG		0x00
+#define SUN6I_DPHY_GCTL_LANE_NUM(n)		((((n) - 1) & 3) << 4)
+#define SUN6I_DPHY_GCTL_EN			BIT(0)
+
+#define SUN6I_DPHY_TX_CTL_REG		0x04
+#define SUN6I_DPHY_TX_CTL_HS_TX_CLK_CONT	BIT(28)
+
+#define SUN6I_DPHY_TX_TIME0_REG		0x10
+#define SUN6I_DPHY_TX_TIME0_HS_TRAIL(n)		(((n) & 0xff) << 24)
+#define SUN6I_DPHY_TX_TIME0_HS_PREPARE(n)	(((n) & 0xff) << 16)
+#define SUN6I_DPHY_TX_TIME0_LP_CLK_DIV(n)	((n) & 0xff)
+
+#define SUN6I_DPHY_TX_TIME1_REG		0x14
+#define SUN6I_DPHY_TX_TIME1_CLK_POST(n)		(((n) & 0xff) << 24)
+#define SUN6I_DPHY_TX_TIME1_CLK_PRE(n)		(((n) & 0xff) << 16)
+#define SUN6I_DPHY_TX_TIME1_CLK_ZERO(n)		(((n) & 0xff) << 8)
+#define SUN6I_DPHY_TX_TIME1_CLK_PREPARE(n)	((n) & 0xff)
+
+#define SUN6I_DPHY_TX_TIME2_REG		0x18
+#define SUN6I_DPHY_TX_TIME2_CLK_TRAIL(n)	((n) & 0xff)
+
+#define SUN6I_DPHY_TX_TIME3_REG		0x1c
+
+#define SUN6I_DPHY_TX_TIME4_REG		0x20
+#define SUN6I_DPHY_TX_TIME4_HS_TX_ANA1(n)	(((n) & 0xff) << 8)
+#define SUN6I_DPHY_TX_TIME4_HS_TX_ANA0(n)	((n) & 0xff)
+
+#define SUN6I_DPHY_ANA0_REG		0x4c
+#define SUN6I_DPHY_ANA0_REG_PWS			BIT(31)
+#define SUN6I_DPHY_ANA0_REG_DMPC		BIT(28)
+#define SUN6I_DPHY_ANA0_REG_DMPD(n)		(((n) & 0xf) << 24)
+#define SUN6I_DPHY_ANA0_REG_SLV(n)		(((n) & 7) << 12)
+#define SUN6I_DPHY_ANA0_REG_DEN(n)		(((n) & 0xf) << 8)
+
+#define SUN6I_DPHY_ANA1_REG		0x50
+#define SUN6I_DPHY_ANA1_REG_VTTMODE		BIT(31)
+#define SUN6I_DPHY_ANA1_REG_CSMPS(n)		(((n) & 3) << 28)
+#define SUN6I_DPHY_ANA1_REG_SVTT(n)		(((n) & 0xf) << 24)
+
+#define SUN6I_DPHY_ANA2_REG		0x54
+#define SUN6I_DPHY_ANA2_EN_P2S_CPU(n)		(((n) & 0xf) << 24)
+#define SUN6I_DPHY_ANA2_EN_P2S_CPU_MASK		GENMASK(27, 24)
+#define SUN6I_DPHY_ANA2_EN_CK_CPU		BIT(4)
+#define SUN6I_DPHY_ANA2_REG_ENIB		BIT(1)
+
+#define SUN6I_DPHY_ANA3_REG		0x58
+#define SUN6I_DPHY_ANA3_EN_VTTD(n)		(((n) & 0xf) << 28)
+#define SUN6I_DPHY_ANA3_EN_VTTD_MASK		GENMASK(31, 28)
+#define SUN6I_DPHY_ANA3_EN_VTTC			BIT(27)
+#define SUN6I_DPHY_ANA3_EN_DIV			BIT(26)
+#define SUN6I_DPHY_ANA3_EN_LDOC			BIT(25)
+#define SUN6I_DPHY_ANA3_EN_LDOD			BIT(24)
+#define SUN6I_DPHY_ANA3_EN_LDOR			BIT(18)
+
+#define SUN6I_DPHY_ANA4_REG		0x5c
+#define SUN6I_DPHY_ANA4_REG_DMPLVC		BIT(24)
+#define SUN6I_DPHY_ANA4_REG_DMPLVD(n)		(((n) & 0xf) << 20)
+#define SUN6I_DPHY_ANA4_REG_CKDV(n)		(((n) & 0x1f) << 12)
+#define SUN6I_DPHY_ANA4_REG_TMSC(n)		(((n) & 3) << 10)
+#define SUN6I_DPHY_ANA4_REG_TMSD(n)		(((n) & 3) << 8)
+#define SUN6I_DPHY_ANA4_REG_TXDNSC(n)		(((n) & 3) << 6)
+#define SUN6I_DPHY_ANA4_REG_TXDNSD(n)		(((n) & 3) << 4)
+#define SUN6I_DPHY_ANA4_REG_TXPUSC(n)		(((n) & 3) << 2)
+#define SUN6I_DPHY_ANA4_REG_TXPUSD(n)		((n) & 3)
+
+#define SUN6I_DPHY_DBG5_REG		0xf4
+
+int sun6i_dphy_init(struct sun6i_dphy *dphy, unsigned int lanes)
+{
+	reset_control_deassert(dphy->reset);
+	clk_prepare_enable(dphy->mod_clk);
+	clk_set_rate_exclusive(dphy->mod_clk, 150000000);
+
+	regmap_write(dphy->regs, SUN6I_DPHY_TX_CTL_REG,
+		     SUN6I_DPHY_TX_CTL_HS_TX_CLK_CONT);
+
+	regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME0_REG,
+		     SUN6I_DPHY_TX_TIME0_LP_CLK_DIV(14) |
+		     SUN6I_DPHY_TX_TIME0_HS_PREPARE(6) |
+		     SUN6I_DPHY_TX_TIME0_HS_TRAIL(10));
+
+	regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME1_REG,
+		     SUN6I_DPHY_TX_TIME1_CLK_PREPARE(7) |
+		     SUN6I_DPHY_TX_TIME1_CLK_ZERO(50) |
+		     SUN6I_DPHY_TX_TIME1_CLK_PRE(3) |
+		     SUN6I_DPHY_TX_TIME1_CLK_POST(10));
+
+	regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME2_REG,
+		     SUN6I_DPHY_TX_TIME2_CLK_TRAIL(30));
+
+	regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME3_REG, 0);
+
+	regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME4_REG,
+		     SUN6I_DPHY_TX_TIME4_HS_TX_ANA0(3) |
+		     SUN6I_DPHY_TX_TIME4_HS_TX_ANA1(3));
+
+	regmap_write(dphy->regs, SUN6I_DPHY_GCTL_REG,
+		     SUN6I_DPHY_GCTL_LANE_NUM(lanes) |
+		     SUN6I_DPHY_GCTL_EN);
+
+	return 0;
+}
+
+int sun6i_dphy_power_on(struct sun6i_dphy *dphy, unsigned int lanes)
+{
+	u8 lanes_mask = GENMASK(lanes - 1, 0);
+
+	regmap_write(dphy->regs, SUN6I_DPHY_ANA0_REG,
+		     SUN6I_DPHY_ANA0_REG_PWS |
+		     SUN6I_DPHY_ANA0_REG_DMPC |
+		     SUN6I_DPHY_ANA0_REG_SLV(7) |
+		     SUN6I_DPHY_ANA0_REG_DMPD(lanes_mask) |
+		     SUN6I_DPHY_ANA0_REG_DEN(lanes_mask));
+
+	regmap_write(dphy->regs, SUN6I_DPHY_ANA1_REG,
+		     SUN6I_DPHY_ANA1_REG_CSMPS(1) |
+		     SUN6I_DPHY_ANA1_REG_SVTT(7));
+
+	regmap_write(dphy->regs, SUN6I_DPHY_ANA4_REG,
+		     SUN6I_DPHY_ANA4_REG_CKDV(1) |
+		     SUN6I_DPHY_ANA4_REG_TMSC(1) |
+		     SUN6I_DPHY_ANA4_REG_TMSD(1) |
+		     SUN6I_DPHY_ANA4_REG_TXDNSC(1) |
+		     SUN6I_DPHY_ANA4_REG_TXDNSD(1) |
+		     SUN6I_DPHY_ANA4_REG_TXPUSC(1) |
+		     SUN6I_DPHY_ANA4_REG_TXPUSD(1) |
+		     SUN6I_DPHY_ANA4_REG_DMPLVC |
+		     SUN6I_DPHY_ANA4_REG_DMPLVD(lanes_mask));
+
+	regmap_write(dphy->regs, SUN6I_DPHY_ANA2_REG,
+		     SUN6I_DPHY_ANA2_REG_ENIB);
+	udelay(5);
+
+	regmap_write(dphy->regs, SUN6I_DPHY_ANA3_REG,
+		     SUN6I_DPHY_ANA3_EN_LDOR |
+		     SUN6I_DPHY_ANA3_EN_LDOC |
+		     SUN6I_DPHY_ANA3_EN_LDOD);
+	udelay(1);
+
+	regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA3_REG,
+			   SUN6I_DPHY_ANA3_EN_VTTC |
+			   SUN6I_DPHY_ANA3_EN_VTTD_MASK,
+			   SUN6I_DPHY_ANA3_EN_VTTC |
+			   SUN6I_DPHY_ANA3_EN_VTTD(lanes_mask));
+	udelay(1);
+
+	regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA3_REG,
+			   SUN6I_DPHY_ANA3_EN_DIV,
+			   SUN6I_DPHY_ANA3_EN_DIV);
+	udelay(1);
+
+	regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA2_REG,
+			   SUN6I_DPHY_ANA2_EN_CK_CPU,
+			   SUN6I_DPHY_ANA2_EN_CK_CPU);
+	udelay(1);
+
+	regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA1_REG,
+			   SUN6I_DPHY_ANA1_REG_VTTMODE,
+			   SUN6I_DPHY_ANA1_REG_VTTMODE);
+
+	regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA2_REG,
+			   SUN6I_DPHY_ANA2_EN_P2S_CPU_MASK,
+			   SUN6I_DPHY_ANA2_EN_P2S_CPU(lanes_mask));
+
+	return 0;
+}
+
+int sun6i_dphy_power_off(struct sun6i_dphy *dphy)
+{
+	regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA1_REG,
+			   SUN6I_DPHY_ANA1_REG_VTTMODE, 0);
+
+	return 0;
+}
+
+int sun6i_dphy_exit(struct sun6i_dphy *dphy)
+{
+	clk_rate_exclusive_put(dphy->mod_clk);
+	clk_disable_unprepare(dphy->mod_clk);
+	reset_control_assert(dphy->reset);
+
+	return 0;
+}
+
+static struct regmap_config sun6i_dphy_regmap_config = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= SUN6I_DPHY_DBG5_REG,
+	.name		= "mipi-dphy",
+};
+
+static const struct of_device_id sun6i_dphy_of_table[] = {
+	{ .compatible = "allwinner,sun6i-a31-mipi-dphy" },
+	{ }
+};
+
+int sun6i_dphy_probe(struct sun6i_dsi *dsi, struct device_node *node)
+{
+	struct sun6i_dphy *dphy;
+	struct resource res;
+	void __iomem *regs;
+	int ret;
+
+	if (!of_match_node(sun6i_dphy_of_table, node)) {
+		dev_err(dsi->dev, "Incompatible D-PHY\n");
+		return -EINVAL;
+	}
+
+	dphy = devm_kzalloc(dsi->dev, sizeof(*dphy), GFP_KERNEL);
+	if (!dphy)
+		return -ENOMEM;
+
+	ret = of_address_to_resource(node, 0, &res);
+	if (ret) {
+		dev_err(dsi->dev, "phy: Couldn't get our resources\n");
+		return ret;
+	}
+
+	regs = devm_ioremap_resource(dsi->dev, &res);
+	if (IS_ERR(regs)) {
+		dev_err(dsi->dev, "Couldn't map the DPHY encoder registers\n");
+		return PTR_ERR(regs);
+	}
+
+	dphy->regs = devm_regmap_init_mmio(dsi->dev, regs,
+					   &sun6i_dphy_regmap_config);
+	if (IS_ERR(dphy->regs)) {
+		dev_err(dsi->dev, "Couldn't create the DPHY encoder regmap\n");
+		return PTR_ERR(dphy->regs);
+	}
+
+	dphy->reset = of_reset_control_get_shared(node, NULL);
+	if (IS_ERR(dphy->reset)) {
+		dev_err(dsi->dev, "Couldn't get our reset line\n");
+		return PTR_ERR(dphy->reset);
+	}
+
+	dphy->bus_clk = of_clk_get_by_name(node, "bus");
+	if (IS_ERR(dphy->bus_clk)) {
+		dev_err(dsi->dev, "Couldn't get the DPHY bus clock\n");
+		ret = PTR_ERR(dphy->bus_clk);
+		goto err_free_reset;
+	}
+	regmap_mmio_attach_clk(dphy->regs, dphy->bus_clk);
+
+	dphy->mod_clk = of_clk_get_by_name(node, "mod");
+	if (IS_ERR(dphy->mod_clk)) {
+		dev_err(dsi->dev, "Couldn't get the DPHY mod clock\n");
+		ret = PTR_ERR(dphy->mod_clk);
+		goto err_free_bus;
+	}
+
+	dsi->dphy = dphy;
+
+	return 0;
+
+err_free_bus:
+	regmap_mmio_detach_clk(dphy->regs);
+	clk_put(dphy->bus_clk);
+err_free_reset:
+	reset_control_put(dphy->reset);
+	return ret;
+}
+
+int sun6i_dphy_remove(struct sun6i_dsi *dsi)
+{
+	struct sun6i_dphy *dphy = dsi->dphy;
+
+	regmap_mmio_detach_clk(dphy->regs);
+	clk_put(dphy->mod_clk);
+	clk_put(dphy->bus_clk);
+	reset_control_put(dphy->reset);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
new file mode 100644
index 000000000000..bfbf761f0c1d
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -0,0 +1,1107 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2016 Allwinnertech Co., Ltd.
+ * Copyright (C) 2017-2018 Bootlin
+ *
+ * Maxime Ripard <maxime.ripard@bootlin.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/crc-ccitt.h>
+#include <linux/of_address.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+
+#include <linux/phy/phy.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_panel.h>
+
+#include "sun4i_drv.h"
+#include "sun6i_mipi_dsi.h"
+
+#include <video/mipi_display.h>
+
+#define SUN6I_DSI_CTL_REG		0x000
+#define SUN6I_DSI_CTL_EN			BIT(0)
+
+#define SUN6I_DSI_BASIC_CTL_REG		0x00c
+#define SUN6I_DSI_BASIC_CTL_HBP_DIS		BIT(2)
+#define SUN6I_DSI_BASIC_CTL_HSA_HSE_DIS		BIT(1)
+#define SUN6I_DSI_BASIC_CTL_VIDEO_BURST		BIT(0)
+
+#define SUN6I_DSI_BASIC_CTL0_REG	0x010
+#define SUN6I_DSI_BASIC_CTL0_HS_EOTP_EN		BIT(18)
+#define SUN6I_DSI_BASIC_CTL0_CRC_EN		BIT(17)
+#define SUN6I_DSI_BASIC_CTL0_ECC_EN		BIT(16)
+#define SUN6I_DSI_BASIC_CTL0_INST_ST		BIT(0)
+
+#define SUN6I_DSI_BASIC_CTL1_REG	0x014
+#define SUN6I_DSI_BASIC_CTL1_VIDEO_ST_DELAY(n)	(((n) & 0x1fff) << 4)
+#define SUN6I_DSI_BASIC_CTL1_VIDEO_FILL		BIT(2)
+#define SUN6I_DSI_BASIC_CTL1_VIDEO_PRECISION	BIT(1)
+#define SUN6I_DSI_BASIC_CTL1_VIDEO_MODE		BIT(0)
+
+#define SUN6I_DSI_BASIC_SIZE0_REG	0x018
+#define SUN6I_DSI_BASIC_SIZE0_VBP(n)		(((n) & 0xfff) << 16)
+#define SUN6I_DSI_BASIC_SIZE0_VSA(n)		((n) & 0xfff)
+
+#define SUN6I_DSI_BASIC_SIZE1_REG	0x01c
+#define SUN6I_DSI_BASIC_SIZE1_VT(n)		(((n) & 0xfff) << 16)
+#define SUN6I_DSI_BASIC_SIZE1_VACT(n)		((n) & 0xfff)
+
+#define SUN6I_DSI_INST_FUNC_REG(n)	(0x020 + (n) * 0x04)
+#define SUN6I_DSI_INST_FUNC_INST_MODE(n)	(((n) & 0xf) << 28)
+#define SUN6I_DSI_INST_FUNC_ESCAPE_ENTRY(n)	(((n) & 0xf) << 24)
+#define SUN6I_DSI_INST_FUNC_TRANS_PACKET(n)	(((n) & 0xf) << 20)
+#define SUN6I_DSI_INST_FUNC_LANE_CEN		BIT(4)
+#define SUN6I_DSI_INST_FUNC_LANE_DEN(n)		((n) & 0xf)
+
+#define SUN6I_DSI_INST_LOOP_SEL_REG	0x040
+
+#define SUN6I_DSI_INST_LOOP_NUM_REG(n)	(0x044 + (n) * 0x10)
+#define SUN6I_DSI_INST_LOOP_NUM_N1(n)		(((n) & 0xfff) << 16)
+#define SUN6I_DSI_INST_LOOP_NUM_N0(n)		((n) & 0xfff)
+
+#define SUN6I_DSI_INST_JUMP_SEL_REG	0x048
+
+#define SUN6I_DSI_INST_JUMP_CFG_REG(n)	(0x04c + (n) * 0x04)
+#define SUN6I_DSI_INST_JUMP_CFG_TO(n)		(((n) & 0xf) << 20)
+#define SUN6I_DSI_INST_JUMP_CFG_POINT(n)	(((n) & 0xf) << 16)
+#define SUN6I_DSI_INST_JUMP_CFG_NUM(n)		((n) & 0xffff)
+
+#define SUN6I_DSI_TRANS_START_REG	0x060
+
+#define SUN6I_DSI_TRANS_ZERO_REG	0x078
+
+#define SUN6I_DSI_TCON_DRQ_REG		0x07c
+#define SUN6I_DSI_TCON_DRQ_ENABLE_MODE		BIT(28)
+#define SUN6I_DSI_TCON_DRQ_SET(n)		((n) & 0x3ff)
+
+#define SUN6I_DSI_PIXEL_CTL0_REG	0x080
+#define SUN6I_DSI_PIXEL_CTL0_PD_PLUG_DISABLE	BIT(16)
+#define SUN6I_DSI_PIXEL_CTL0_FORMAT(n)		((n) & 0xf)
+
+#define SUN6I_DSI_PIXEL_CTL1_REG	0x084
+
+#define SUN6I_DSI_PIXEL_PH_REG		0x090
+#define SUN6I_DSI_PIXEL_PH_ECC(n)		(((n) & 0xff) << 24)
+#define SUN6I_DSI_PIXEL_PH_WC(n)		(((n) & 0xffff) << 8)
+#define SUN6I_DSI_PIXEL_PH_VC(n)		(((n) & 3) << 6)
+#define SUN6I_DSI_PIXEL_PH_DT(n)		((n) & 0x3f)
+
+#define SUN6I_DSI_PIXEL_PF0_REG		0x098
+#define SUN6I_DSI_PIXEL_PF0_CRC_FORCE(n)	((n) & 0xffff)
+
+#define SUN6I_DSI_PIXEL_PF1_REG		0x09c
+#define SUN6I_DSI_PIXEL_PF1_CRC_INIT_LINEN(n)	(((n) & 0xffff) << 16)
+#define SUN6I_DSI_PIXEL_PF1_CRC_INIT_LINE0(n)	((n) & 0xffff)
+
+#define SUN6I_DSI_SYNC_HSS_REG		0x0b0
+
+#define SUN6I_DSI_SYNC_HSE_REG		0x0b4
+
+#define SUN6I_DSI_SYNC_VSS_REG		0x0b8
+
+#define SUN6I_DSI_SYNC_VSE_REG		0x0bc
+
+#define SUN6I_DSI_BLK_HSA0_REG		0x0c0
+
+#define SUN6I_DSI_BLK_HSA1_REG		0x0c4
+#define SUN6I_DSI_BLK_PF(n)			(((n) & 0xffff) << 16)
+#define SUN6I_DSI_BLK_PD(n)			((n) & 0xff)
+
+#define SUN6I_DSI_BLK_HBP0_REG		0x0c8
+
+#define SUN6I_DSI_BLK_HBP1_REG		0x0cc
+
+#define SUN6I_DSI_BLK_HFP0_REG		0x0d0
+
+#define SUN6I_DSI_BLK_HFP1_REG		0x0d4
+
+#define SUN6I_DSI_BLK_HBLK0_REG		0x0e0
+
+#define SUN6I_DSI_BLK_HBLK1_REG		0x0e4
+
+#define SUN6I_DSI_BLK_VBLK0_REG		0x0e8
+
+#define SUN6I_DSI_BLK_VBLK1_REG		0x0ec
+
+#define SUN6I_DSI_BURST_LINE_REG	0x0f0
+#define SUN6I_DSI_BURST_LINE_SYNC_POINT(n)	(((n) & 0xffff) << 16)
+#define SUN6I_DSI_BURST_LINE_NUM(n)		((n) & 0xffff)
+
+#define SUN6I_DSI_BURST_DRQ_REG		0x0f4
+#define SUN6I_DSI_BURST_DRQ_EDGE1(n)		(((n) & 0xffff) << 16)
+#define SUN6I_DSI_BURST_DRQ_EDGE0(n)		((n) & 0xffff)
+
+#define SUN6I_DSI_CMD_CTL_REG		0x200
+#define SUN6I_DSI_CMD_CTL_RX_OVERFLOW		BIT(26)
+#define SUN6I_DSI_CMD_CTL_RX_FLAG		BIT(25)
+#define SUN6I_DSI_CMD_CTL_TX_FLAG		BIT(9)
+
+#define SUN6I_DSI_CMD_RX_REG(n)		(0x240 + (n) * 0x04)
+
+#define SUN6I_DSI_DEBUG_DATA_REG	0x2f8
+
+#define SUN6I_DSI_CMD_TX_REG(n)		(0x300 + (n) * 0x04)
+
+enum sun6i_dsi_start_inst {
+	DSI_START_LPRX,
+	DSI_START_LPTX,
+	DSI_START_HSC,
+	DSI_START_HSD,
+};
+
+enum sun6i_dsi_inst_id {
+	DSI_INST_ID_LP11	= 0,
+	DSI_INST_ID_TBA,
+	DSI_INST_ID_HSC,
+	DSI_INST_ID_HSD,
+	DSI_INST_ID_LPDT,
+	DSI_INST_ID_HSCEXIT,
+	DSI_INST_ID_NOP,
+	DSI_INST_ID_DLY,
+	DSI_INST_ID_END		= 15,
+};
+
+enum sun6i_dsi_inst_mode {
+	DSI_INST_MODE_STOP	= 0,
+	DSI_INST_MODE_TBA,
+	DSI_INST_MODE_HS,
+	DSI_INST_MODE_ESCAPE,
+	DSI_INST_MODE_HSCEXIT,
+	DSI_INST_MODE_NOP,
+};
+
+enum sun6i_dsi_inst_escape {
+	DSI_INST_ESCA_LPDT	= 0,
+	DSI_INST_ESCA_ULPS,
+	DSI_INST_ESCA_UN1,
+	DSI_INST_ESCA_UN2,
+	DSI_INST_ESCA_RESET,
+	DSI_INST_ESCA_UN3,
+	DSI_INST_ESCA_UN4,
+	DSI_INST_ESCA_UN5,
+};
+
+enum sun6i_dsi_inst_packet {
+	DSI_INST_PACK_PIXEL	= 0,
+	DSI_INST_PACK_COMMAND,
+};
+
+static const u32 sun6i_dsi_ecc_array[] = {
+	[0] = (BIT(0) | BIT(1) | BIT(2) | BIT(4) | BIT(5) | BIT(7) | BIT(10) |
+	       BIT(11) | BIT(13) | BIT(16) | BIT(20) | BIT(21) | BIT(22) |
+	       BIT(23)),
+	[1] = (BIT(0) | BIT(1) | BIT(3) | BIT(4) | BIT(6) | BIT(8) | BIT(10) |
+	       BIT(12) | BIT(14) | BIT(17) | BIT(20) | BIT(21) | BIT(22) |
+	       BIT(23)),
+	[2] = (BIT(0) | BIT(2) | BIT(3) | BIT(5) | BIT(6) | BIT(9) | BIT(11) |
+	       BIT(12) | BIT(15) | BIT(18) | BIT(20) | BIT(21) | BIT(22)),
+	[3] = (BIT(1) | BIT(2) | BIT(3) | BIT(7) | BIT(8) | BIT(9) | BIT(13) |
+	       BIT(14) | BIT(15) | BIT(19) | BIT(20) | BIT(21) | BIT(23)),
+	[4] = (BIT(4) | BIT(5) | BIT(6) | BIT(7) | BIT(8) | BIT(9) | BIT(16) |
+	       BIT(17) | BIT(18) | BIT(19) | BIT(20) | BIT(22) | BIT(23)),
+	[5] = (BIT(10) | BIT(11) | BIT(12) | BIT(13) | BIT(14) | BIT(15) |
+	       BIT(16) | BIT(17) | BIT(18) | BIT(19) | BIT(21) | BIT(22) |
+	       BIT(23)),
+};
+
+static u32 sun6i_dsi_ecc_compute(unsigned int data)
+{
+	int i;
+	u8 ecc = 0;
+
+	for (i = 0; i < ARRAY_SIZE(sun6i_dsi_ecc_array); i++) {
+		u32 field = sun6i_dsi_ecc_array[i];
+		bool init = false;
+		u8 val = 0;
+		int j;
+
+		for (j = 0; j < 24; j++) {
+			if (!(BIT(j) & field))
+				continue;
+
+			if (!init) {
+				val = (BIT(j) & data) ? 1 : 0;
+				init = true;
+			} else {
+				val ^= (BIT(j) & data) ? 1 : 0;
+			}
+		}
+
+		ecc |= val << i;
+	}
+
+	return ecc;
+}
+
+static u16 sun6i_dsi_crc_compute(u8 const *buffer, size_t len)
+{
+	return crc_ccitt(0xffff, buffer, len);
+}
+
+static u16 sun6i_dsi_crc_repeat_compute(u8 pd, size_t len)
+{
+	u8 buffer[len];
+
+	memset(buffer, pd, len);
+
+	return sun6i_dsi_crc_compute(buffer, len);
+}
+
+static u32 sun6i_dsi_build_sync_pkt(u8 dt, u8 vc, u8 d0, u8 d1)
+{
+	u32 val = dt & 0x3f;
+
+	val |= (vc & 3) << 6;
+	val |= (d0 & 0xff) << 8;
+	val |= (d1 & 0xff) << 16;
+	val |= sun6i_dsi_ecc_compute(val) << 24;
+
+	return val;
+}
+
+static u32 sun6i_dsi_build_blk0_pkt(u8 vc, u16 wc)
+{
+	return sun6i_dsi_build_sync_pkt(MIPI_DSI_BLANKING_PACKET, vc,
+					wc & 0xff, wc >> 8);
+}
+
+static u32 sun6i_dsi_build_blk1_pkt(u16 pd, size_t len)
+{
+	u32 val = SUN6I_DSI_BLK_PD(pd);
+
+	return val | SUN6I_DSI_BLK_PF(sun6i_dsi_crc_repeat_compute(pd, len));
+}
+
+static void sun6i_dsi_inst_abort(struct sun6i_dsi *dsi)
+{
+	regmap_update_bits(dsi->regs, SUN6I_DSI_BASIC_CTL0_REG,
+			   SUN6I_DSI_BASIC_CTL0_INST_ST, 0);
+}
+
+static void sun6i_dsi_inst_commit(struct sun6i_dsi *dsi)
+{
+	regmap_update_bits(dsi->regs, SUN6I_DSI_BASIC_CTL0_REG,
+			   SUN6I_DSI_BASIC_CTL0_INST_ST,
+			   SUN6I_DSI_BASIC_CTL0_INST_ST);
+}
+
+static int sun6i_dsi_inst_wait_for_completion(struct sun6i_dsi *dsi)
+{
+	u32 val;
+
+	return regmap_read_poll_timeout(dsi->regs, SUN6I_DSI_BASIC_CTL0_REG,
+					val,
+					!(val & SUN6I_DSI_BASIC_CTL0_INST_ST),
+					100, 5000);
+}
+
+static void sun6i_dsi_inst_setup(struct sun6i_dsi *dsi,
+				 enum sun6i_dsi_inst_id id,
+				 enum sun6i_dsi_inst_mode mode,
+				 bool clock, u8 data,
+				 enum sun6i_dsi_inst_packet packet,
+				 enum sun6i_dsi_inst_escape escape)
+{
+	regmap_write(dsi->regs, SUN6I_DSI_INST_FUNC_REG(id),
+		     SUN6I_DSI_INST_FUNC_INST_MODE(mode) |
+		     SUN6I_DSI_INST_FUNC_ESCAPE_ENTRY(escape) |
+		     SUN6I_DSI_INST_FUNC_TRANS_PACKET(packet) |
+		     (clock ? SUN6I_DSI_INST_FUNC_LANE_CEN : 0) |
+		     SUN6I_DSI_INST_FUNC_LANE_DEN(data));
+}
+
+static void sun6i_dsi_inst_init(struct sun6i_dsi *dsi,
+				struct mipi_dsi_device *device)
+{
+	u8 lanes_mask = GENMASK(device->lanes - 1, 0);
+
+	sun6i_dsi_inst_setup(dsi, DSI_INST_ID_LP11, DSI_INST_MODE_STOP,
+			     true, lanes_mask, 0, 0);
+
+	sun6i_dsi_inst_setup(dsi, DSI_INST_ID_TBA, DSI_INST_MODE_TBA,
+			     false, 1, 0, 0);
+
+	sun6i_dsi_inst_setup(dsi, DSI_INST_ID_HSC, DSI_INST_MODE_HS,
+			     true, 0, DSI_INST_PACK_PIXEL, 0);
+
+	sun6i_dsi_inst_setup(dsi, DSI_INST_ID_HSD, DSI_INST_MODE_HS,
+			     false, lanes_mask, DSI_INST_PACK_PIXEL, 0);
+
+	sun6i_dsi_inst_setup(dsi, DSI_INST_ID_LPDT, DSI_INST_MODE_ESCAPE,
+			     false, 1, DSI_INST_PACK_COMMAND,
+			     DSI_INST_ESCA_LPDT);
+
+	sun6i_dsi_inst_setup(dsi, DSI_INST_ID_HSCEXIT, DSI_INST_MODE_HSCEXIT,
+			     true, 0, 0, 0);
+
+	sun6i_dsi_inst_setup(dsi, DSI_INST_ID_NOP, DSI_INST_MODE_STOP,
+			     false, lanes_mask, 0, 0);
+
+	sun6i_dsi_inst_setup(dsi, DSI_INST_ID_DLY, DSI_INST_MODE_NOP,
+			     true, lanes_mask, 0, 0);
+
+	regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_CFG_REG(0),
+		     SUN6I_DSI_INST_JUMP_CFG_POINT(DSI_INST_ID_NOP) |
+		     SUN6I_DSI_INST_JUMP_CFG_TO(DSI_INST_ID_HSCEXIT) |
+		     SUN6I_DSI_INST_JUMP_CFG_NUM(1));
+};
+
+static u16 sun6i_dsi_get_video_start_delay(struct sun6i_dsi *dsi,
+					   struct drm_display_mode *mode)
+{
+	return mode->vtotal - (mode->vsync_end - mode->vdisplay) + 1;
+}
+
+static void sun6i_dsi_setup_burst(struct sun6i_dsi *dsi,
+				  struct drm_display_mode *mode)
+{
+	struct mipi_dsi_device *device = dsi->device;
+	u32 val = 0;
+
+	if ((mode->hsync_end - mode->hdisplay) > 20) {
+		/* Maaaaaagic */
+		u16 drq = (mode->hsync_end - mode->hdisplay) - 20;
+
+		drq *= mipi_dsi_pixel_format_to_bpp(device->format);
+		drq /= 32;
+
+		val = (SUN6I_DSI_TCON_DRQ_ENABLE_MODE |
+		       SUN6I_DSI_TCON_DRQ_SET(drq));
+	}
+
+	regmap_write(dsi->regs, SUN6I_DSI_TCON_DRQ_REG, val);
+}
+
+static void sun6i_dsi_setup_inst_loop(struct sun6i_dsi *dsi,
+				      struct drm_display_mode *mode)
+{
+	u16 delay = 50 - 1;
+
+	regmap_write(dsi->regs, SUN6I_DSI_INST_LOOP_NUM_REG(0),
+		     SUN6I_DSI_INST_LOOP_NUM_N0(50 - 1) |
+		     SUN6I_DSI_INST_LOOP_NUM_N1(delay));
+	regmap_write(dsi->regs, SUN6I_DSI_INST_LOOP_NUM_REG(1),
+		     SUN6I_DSI_INST_LOOP_NUM_N0(50 - 1) |
+		     SUN6I_DSI_INST_LOOP_NUM_N1(delay));
+}
+
+static void sun6i_dsi_setup_format(struct sun6i_dsi *dsi,
+				   struct drm_display_mode *mode)
+{
+	struct mipi_dsi_device *device = dsi->device;
+	u32 val = SUN6I_DSI_PIXEL_PH_VC(device->channel);
+	u8 dt, fmt;
+	u16 wc;
+
+	/*
+	 * TODO: The format defines are only valid in video mode and
+	 * change in command mode.
+	 */
+	switch (device->format) {
+	case MIPI_DSI_FMT_RGB888:
+		dt = MIPI_DSI_PACKED_PIXEL_STREAM_24;
+		fmt = 8;
+		break;
+	case MIPI_DSI_FMT_RGB666:
+		dt = MIPI_DSI_PIXEL_STREAM_3BYTE_18;
+		fmt = 9;
+		break;
+	case MIPI_DSI_FMT_RGB666_PACKED:
+		dt = MIPI_DSI_PACKED_PIXEL_STREAM_18;
+		fmt = 10;
+		break;
+	case MIPI_DSI_FMT_RGB565:
+		dt = MIPI_DSI_PACKED_PIXEL_STREAM_16;
+		fmt = 11;
+		break;
+	default:
+		return;
+	}
+	val |= SUN6I_DSI_PIXEL_PH_DT(dt);
+
+	wc = mode->hdisplay * mipi_dsi_pixel_format_to_bpp(device->format) / 8;
+	val |= SUN6I_DSI_PIXEL_PH_WC(wc);
+	val |= SUN6I_DSI_PIXEL_PH_ECC(sun6i_dsi_ecc_compute(val));
+
+	regmap_write(dsi->regs, SUN6I_DSI_PIXEL_PH_REG, val);
+
+	regmap_write(dsi->regs, SUN6I_DSI_PIXEL_PF0_REG,
+		     SUN6I_DSI_PIXEL_PF0_CRC_FORCE(0xffff));
+
+	regmap_write(dsi->regs, SUN6I_DSI_PIXEL_PF1_REG,
+		     SUN6I_DSI_PIXEL_PF1_CRC_INIT_LINE0(0xffff) |
+		     SUN6I_DSI_PIXEL_PF1_CRC_INIT_LINEN(0xffff));
+
+	regmap_write(dsi->regs, SUN6I_DSI_PIXEL_CTL0_REG,
+		     SUN6I_DSI_PIXEL_CTL0_PD_PLUG_DISABLE |
+		     SUN6I_DSI_PIXEL_CTL0_FORMAT(fmt));
+}
+
+static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
+				    struct drm_display_mode *mode)
+{
+	struct mipi_dsi_device *device = dsi->device;
+	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
+	u16 hbp, hfp, hsa, hblk, vblk;
+
+	regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL_REG, 0);
+
+	regmap_write(dsi->regs, SUN6I_DSI_SYNC_HSS_REG,
+		     sun6i_dsi_build_sync_pkt(MIPI_DSI_H_SYNC_START,
+					      device->channel,
+					      0, 0));
+
+	regmap_write(dsi->regs, SUN6I_DSI_SYNC_HSE_REG,
+		     sun6i_dsi_build_sync_pkt(MIPI_DSI_H_SYNC_END,
+					      device->channel,
+					      0, 0));
+
+	regmap_write(dsi->regs, SUN6I_DSI_SYNC_VSS_REG,
+		     sun6i_dsi_build_sync_pkt(MIPI_DSI_V_SYNC_START,
+					      device->channel,
+					      0, 0));
+
+	regmap_write(dsi->regs, SUN6I_DSI_SYNC_VSE_REG,
+		     sun6i_dsi_build_sync_pkt(MIPI_DSI_V_SYNC_END,
+					      device->channel,
+					      0, 0));
+
+	regmap_write(dsi->regs, SUN6I_DSI_BASIC_SIZE0_REG,
+		     SUN6I_DSI_BASIC_SIZE0_VSA(mode->vsync_end -
+					       mode->vsync_start) |
+		     SUN6I_DSI_BASIC_SIZE0_VBP(mode->vsync_start -
+					       mode->vdisplay));
+
+	regmap_write(dsi->regs, SUN6I_DSI_BASIC_SIZE1_REG,
+		     SUN6I_DSI_BASIC_SIZE1_VACT(mode->vdisplay) |
+		     SUN6I_DSI_BASIC_SIZE1_VT(mode->vtotal));
+
+	/*
+	 * A sync period is composed of a blanking packet (4 bytes +
+	 * payload + 2 bytes) and a sync event packet (4 bytes). Its
+	 * minimal size is therefore 10 bytes
+	 */
+#define HSA_PACKET_OVERHEAD	10
+	hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
+		  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA0_REG,
+		     sun6i_dsi_build_blk0_pkt(device->channel, hsa));
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA1_REG,
+		     sun6i_dsi_build_blk1_pkt(0, hsa));
+
+	/*
+	 * The backporch is set using a blanking packet (4 bytes +
+	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
+	 */
+#define HBP_PACKET_OVERHEAD	6
+	hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
+		  (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD);
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP0_REG,
+		     sun6i_dsi_build_blk0_pkt(device->channel, hbp));
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP1_REG,
+		     sun6i_dsi_build_blk1_pkt(0, hbp));
+
+	/*
+	 * The frontporch is set using a blanking packet (4 bytes +
+	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
+	 */
+#define HFP_PACKET_OVERHEAD	6
+	hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
+		  (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD);
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP0_REG,
+		     sun6i_dsi_build_blk0_pkt(device->channel, hfp));
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP1_REG,
+		     sun6i_dsi_build_blk1_pkt(0, hfp));
+
+	/*
+	 * hblk seems to be the line + porches length.
+	 */
+	hblk = mode->htotal * Bpp - hsa;
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK0_REG,
+		     sun6i_dsi_build_blk0_pkt(device->channel, hblk));
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK1_REG,
+		     sun6i_dsi_build_blk1_pkt(0, hblk));
+
+	/*
+	 * And I'm not entirely sure what vblk is about. The driver in
+	 * Allwinner BSP is using a rather convoluted calculation
+	 * there only for 4 lanes. However, using 0 (the !4 lanes
+	 * case) even with a 4 lanes screen seems to work...
+	 */
+	vblk = 0;
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK0_REG,
+		     sun6i_dsi_build_blk0_pkt(device->channel, vblk));
+	regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK1_REG,
+		     sun6i_dsi_build_blk1_pkt(0, vblk));
+}
+
+static int sun6i_dsi_start(struct sun6i_dsi *dsi,
+			   enum sun6i_dsi_start_inst func)
+{
+	switch (func) {
+	case DSI_START_LPTX:
+		regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG,
+			     DSI_INST_ID_LPDT << (4 * DSI_INST_ID_LP11) |
+			     DSI_INST_ID_END  << (4 * DSI_INST_ID_LPDT));
+		break;
+	case DSI_START_LPRX:
+		regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG,
+			     DSI_INST_ID_LPDT << (4 * DSI_INST_ID_LP11) |
+			     DSI_INST_ID_DLY  << (4 * DSI_INST_ID_LPDT) |
+			     DSI_INST_ID_TBA  << (4 * DSI_INST_ID_DLY) |
+			     DSI_INST_ID_END  << (4 * DSI_INST_ID_TBA));
+		break;
+	case DSI_START_HSC:
+		regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG,
+			     DSI_INST_ID_HSC  << (4 * DSI_INST_ID_LP11) |
+			     DSI_INST_ID_END  << (4 * DSI_INST_ID_HSC));
+		break;
+	case DSI_START_HSD:
+		regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG,
+			     DSI_INST_ID_NOP  << (4 * DSI_INST_ID_LP11) |
+			     DSI_INST_ID_HSD  << (4 * DSI_INST_ID_NOP) |
+			     DSI_INST_ID_DLY  << (4 * DSI_INST_ID_HSD) |
+			     DSI_INST_ID_NOP  << (4 * DSI_INST_ID_DLY) |
+			     DSI_INST_ID_END  << (4 * DSI_INST_ID_HSCEXIT));
+		break;
+	default:
+		regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG,
+			     DSI_INST_ID_END  << (4 * DSI_INST_ID_LP11));
+		break;
+	}
+
+	sun6i_dsi_inst_abort(dsi);
+	sun6i_dsi_inst_commit(dsi);
+
+	if (func == DSI_START_HSC)
+		regmap_write_bits(dsi->regs,
+				  SUN6I_DSI_INST_FUNC_REG(DSI_INST_ID_LP11),
+				  SUN6I_DSI_INST_FUNC_LANE_CEN, 0);
+
+	return 0;
+}
+
+static void sun6i_dsi_encoder_enable(struct drm_encoder *encoder)
+{
+	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
+	struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder);
+	struct mipi_dsi_device *device = dsi->device;
+	u16 delay;
+
+	DRM_DEBUG_DRIVER("Enabling DSI output\n");
+
+	pm_runtime_get_sync(dsi->dev);
+
+	delay = sun6i_dsi_get_video_start_delay(dsi, mode);
+	regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL1_REG,
+		     SUN6I_DSI_BASIC_CTL1_VIDEO_ST_DELAY(delay) |
+		     SUN6I_DSI_BASIC_CTL1_VIDEO_FILL |
+		     SUN6I_DSI_BASIC_CTL1_VIDEO_PRECISION |
+		     SUN6I_DSI_BASIC_CTL1_VIDEO_MODE);
+
+	sun6i_dsi_setup_burst(dsi, mode);
+	sun6i_dsi_setup_inst_loop(dsi, mode);
+	sun6i_dsi_setup_format(dsi, mode);
+	sun6i_dsi_setup_timings(dsi, mode);
+
+	sun6i_dphy_init(dsi->dphy, device->lanes);
+	sun6i_dphy_power_on(dsi->dphy, device->lanes);
+
+	if (!IS_ERR(dsi->panel))
+		drm_panel_prepare(dsi->panel);
+
+	/*
+	 * FIXME: This should be moved after the switch to HS mode.
+	 *
+	 * Unfortunately, once in HS mode, it seems like we're not
+	 * able to send DCS commands anymore, which would prevent any
+	 * panel to send any DCS command as part as their enable
+	 * method, which is quite common.
+	 *
+	 * I haven't seen any artifact due to that sub-optimal
+	 * ordering on the panels I've tested it with, so I guess this
+	 * will do for now, until that IP is better understood.
+	 */
+	if (!IS_ERR(dsi->panel))
+		drm_panel_enable(dsi->panel);
+
+	sun6i_dsi_start(dsi, DSI_START_HSC);
+
+	udelay(1000);
+
+	sun6i_dsi_start(dsi, DSI_START_HSD);
+}
+
+static void sun6i_dsi_encoder_disable(struct drm_encoder *encoder)
+{
+	struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder);
+
+	DRM_DEBUG_DRIVER("Disabling DSI output\n");
+
+	if (!IS_ERR(dsi->panel)) {
+		drm_panel_disable(dsi->panel);
+		drm_panel_unprepare(dsi->panel);
+	}
+
+	sun6i_dphy_power_off(dsi->dphy);
+	sun6i_dphy_exit(dsi->dphy);
+
+	pm_runtime_put(dsi->dev);
+}
+
+static int sun6i_dsi_get_modes(struct drm_connector *connector)
+{
+	struct sun6i_dsi *dsi = connector_to_sun6i_dsi(connector);
+
+	return drm_panel_get_modes(dsi->panel);
+}
+
+static struct drm_connector_helper_funcs sun6i_dsi_connector_helper_funcs = {
+	.get_modes	= sun6i_dsi_get_modes,
+};
+
+static enum drm_connector_status
+sun6i_dsi_connector_detect(struct drm_connector *connector, bool force)
+{
+	return connector_status_connected;
+}
+
+static const struct drm_connector_funcs sun6i_dsi_connector_funcs = {
+	.detect			= sun6i_dsi_connector_detect,
+	.fill_modes		= drm_helper_probe_single_connector_modes,
+	.destroy		= drm_connector_cleanup,
+	.reset			= drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state	= drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_connector_destroy_state,
+};
+
+static const struct drm_encoder_helper_funcs sun6i_dsi_enc_helper_funcs = {
+	.disable	= sun6i_dsi_encoder_disable,
+	.enable		= sun6i_dsi_encoder_enable,
+};
+
+static const struct drm_encoder_funcs sun6i_dsi_enc_funcs = {
+	.destroy	= drm_encoder_cleanup,
+};
+
+static u32 sun6i_dsi_dcs_build_pkt_hdr(struct sun6i_dsi *dsi,
+				       const struct mipi_dsi_msg *msg)
+{
+	u32 pkt = msg->type;
+
+	if (msg->type == MIPI_DSI_DCS_LONG_WRITE) {
+		pkt |= ((msg->tx_len + 1) & 0xffff) << 8;
+		pkt |= (((msg->tx_len + 1) >> 8) & 0xffff) << 16;
+	} else {
+		pkt |= (((u8 *)msg->tx_buf)[0] << 8);
+		if (msg->tx_len > 1)
+			pkt |= (((u8 *)msg->tx_buf)[1] << 16);
+	}
+
+	pkt |= sun6i_dsi_ecc_compute(pkt) << 24;
+
+	return pkt;
+}
+
+static int sun6i_dsi_dcs_write_short(struct sun6i_dsi *dsi,
+				     const struct mipi_dsi_msg *msg)
+{
+	regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0),
+		     sun6i_dsi_dcs_build_pkt_hdr(dsi, msg));
+	regmap_write_bits(dsi->regs, SUN6I_DSI_CMD_CTL_REG,
+			  0xff, (4 - 1));
+
+	sun6i_dsi_start(dsi, DSI_START_LPTX);
+
+	return msg->tx_len;
+}
+
+static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi,
+				    const struct mipi_dsi_msg *msg)
+{
+	int ret, len = 0;
+	u8 *bounce;
+	u16 crc;
+
+	regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0),
+		     sun6i_dsi_dcs_build_pkt_hdr(dsi, msg));
+
+	bounce = kzalloc(msg->tx_len + sizeof(crc), GFP_KERNEL);
+	if (!bounce)
+		return -ENOMEM;
+
+	memcpy(bounce, msg->tx_buf, msg->tx_len);
+	len += msg->tx_len;
+
+	crc = sun6i_dsi_crc_compute(bounce, msg->tx_len);
+	memcpy((u8 *)bounce + msg->tx_len, &crc, sizeof(crc));
+	len += sizeof(crc);
+
+	regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, len);
+	regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, len + 4 - 1);
+	kfree(bounce);
+
+	sun6i_dsi_start(dsi, DSI_START_LPTX);
+
+	ret = sun6i_dsi_inst_wait_for_completion(dsi);
+	if (ret < 0) {
+		sun6i_dsi_inst_abort(dsi);
+		return ret;
+	}
+
+	/*
+	 * TODO: There's some bits (reg 0x200, bits 8/9) that
+	 * apparently can be used to check whether the data have been
+	 * sent, but I couldn't get it to work reliably.
+	 */
+	return msg->tx_len;
+}
+
+static int sun6i_dsi_dcs_read(struct sun6i_dsi *dsi,
+			      const struct mipi_dsi_msg *msg)
+{
+	u32 val;
+	int ret;
+	u8 byte0;
+
+	regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0),
+		     sun6i_dsi_dcs_build_pkt_hdr(dsi, msg));
+	regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG,
+		     (4 - 1));
+
+	sun6i_dsi_start(dsi, DSI_START_LPRX);
+
+	ret = sun6i_dsi_inst_wait_for_completion(dsi);
+	if (ret < 0) {
+		sun6i_dsi_inst_abort(dsi);
+		return ret;
+	}
+
+	/*
+	 * TODO: There's some bits (reg 0x200, bits 24/25) that
+	 * apparently can be used to check whether the data have been
+	 * received, but I couldn't get it to work reliably.
+	 */
+	regmap_read(dsi->regs, SUN6I_DSI_CMD_CTL_REG, &val);
+	if (val & SUN6I_DSI_CMD_CTL_RX_OVERFLOW)
+		return -EIO;
+
+	regmap_read(dsi->regs, SUN6I_DSI_CMD_RX_REG(0), &val);
+	byte0 = val & 0xff;
+	if (byte0 == MIPI_DSI_RX_ACKNOWLEDGE_AND_ERROR_REPORT)
+		return -EIO;
+
+	((u8 *)msg->rx_buf)[0] = (val >> 8);
+
+	return 1;
+}
+
+static int sun6i_dsi_attach(struct mipi_dsi_host *host,
+			    struct mipi_dsi_device *device)
+{
+	struct sun6i_dsi *dsi = host_to_sun6i_dsi(host);
+
+	dsi->device = device;
+	dsi->panel = of_drm_find_panel(device->dev.of_node);
+	if (!dsi->panel)
+		return -EINVAL;
+
+	dev_info(host->dev, "Attached device %s\n", device->name);
+
+	return 0;
+}
+
+static int sun6i_dsi_detach(struct mipi_dsi_host *host,
+			    struct mipi_dsi_device *device)
+{
+	struct sun6i_dsi *dsi = host_to_sun6i_dsi(host);
+
+	dsi->panel = NULL;
+	dsi->device = NULL;
+
+	return 0;
+}
+
+static ssize_t sun6i_dsi_transfer(struct mipi_dsi_host *host,
+				  const struct mipi_dsi_msg *msg)
+{
+	struct sun6i_dsi *dsi = host_to_sun6i_dsi(host);
+	int ret;
+
+	ret = sun6i_dsi_inst_wait_for_completion(dsi);
+	if (ret < 0)
+		sun6i_dsi_inst_abort(dsi);
+
+	regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG,
+		     SUN6I_DSI_CMD_CTL_RX_OVERFLOW |
+		     SUN6I_DSI_CMD_CTL_RX_FLAG |
+		     SUN6I_DSI_CMD_CTL_TX_FLAG);
+
+	switch (msg->type) {
+	case MIPI_DSI_DCS_SHORT_WRITE:
+	case MIPI_DSI_DCS_SHORT_WRITE_PARAM:
+		ret = sun6i_dsi_dcs_write_short(dsi, msg);
+		break;
+
+	case MIPI_DSI_DCS_LONG_WRITE:
+		ret = sun6i_dsi_dcs_write_long(dsi, msg);
+		break;
+
+	case MIPI_DSI_DCS_READ:
+		if (msg->rx_len == 1) {
+			ret = sun6i_dsi_dcs_read(dsi, msg);
+			break;
+		}
+
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static const struct mipi_dsi_host_ops sun6i_dsi_host_ops = {
+	.attach		= sun6i_dsi_attach,
+	.detach		= sun6i_dsi_detach,
+	.transfer	= sun6i_dsi_transfer,
+};
+
+static const struct regmap_config sun6i_dsi_regmap_config = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= SUN6I_DSI_CMD_TX_REG(255),
+	.name		= "mipi-dsi",
+};
+
+static int sun6i_dsi_bind(struct device *dev, struct device *master,
+			 void *data)
+{
+	struct drm_device *drm = data;
+	struct sun4i_drv *drv = drm->dev_private;
+	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
+	int ret;
+
+	if (!dsi->panel)
+		return -EPROBE_DEFER;
+
+	dsi->drv = drv;
+
+	drm_encoder_helper_add(&dsi->encoder,
+			       &sun6i_dsi_enc_helper_funcs);
+	ret = drm_encoder_init(drm,
+			       &dsi->encoder,
+			       &sun6i_dsi_enc_funcs,
+			       DRM_MODE_ENCODER_DSI,
+			       NULL);
+	if (ret) {
+		dev_err(dsi->dev, "Couldn't initialise the DSI encoder\n");
+		return ret;
+	}
+	dsi->encoder.possible_crtcs = BIT(0);
+
+	drm_connector_helper_add(&dsi->connector,
+				 &sun6i_dsi_connector_helper_funcs);
+	ret = drm_connector_init(drm, &dsi->connector,
+				 &sun6i_dsi_connector_funcs,
+				 DRM_MODE_CONNECTOR_DSI);
+	if (ret) {
+		dev_err(dsi->dev,
+			"Couldn't initialise the DSI connector\n");
+		goto err_cleanup_connector;
+	}
+
+	drm_mode_connector_attach_encoder(&dsi->connector, &dsi->encoder);
+	drm_panel_attach(dsi->panel, &dsi->connector);
+
+	return 0;
+
+err_cleanup_connector:
+	drm_encoder_cleanup(&dsi->encoder);
+	return ret;
+}
+
+static void sun6i_dsi_unbind(struct device *dev, struct device *master,
+			    void *data)
+{
+	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
+
+	drm_panel_detach(dsi->panel);
+}
+
+static const struct component_ops sun6i_dsi_ops = {
+	.bind	= sun6i_dsi_bind,
+	.unbind	= sun6i_dsi_unbind,
+};
+
+static int sun6i_dsi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *dphy_node;
+	struct sun6i_dsi *dsi;
+	struct resource *res;
+	void __iomem *base;
+	int ret;
+
+	dsi = devm_kzalloc(dev, sizeof(*dsi), GFP_KERNEL);
+	if (!dsi)
+		return -ENOMEM;
+	dev_set_drvdata(dev, dsi);
+	dsi->dev = dev;
+	dsi->host.ops = &sun6i_dsi_host_ops;
+	dsi->host.dev = dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base)) {
+		dev_err(dev, "Couldn't map the DSI encoder registers\n");
+		return PTR_ERR(base);
+	}
+
+	dsi->regs = devm_regmap_init_mmio_clk(dev, "bus", base,
+					      &sun6i_dsi_regmap_config);
+	if (IS_ERR(dsi->regs)) {
+		dev_err(dev, "Couldn't create the DSI encoder regmap\n");
+		return PTR_ERR(dsi->regs);
+	}
+
+	dsi->reset = devm_reset_control_get_shared(dev, NULL);
+	if (IS_ERR(dsi->reset)) {
+		dev_err(dev, "Couldn't get our reset line\n");
+		return PTR_ERR(dsi->reset);
+	}
+
+	dsi->mod_clk = devm_clk_get(dev, "mod");
+	if (IS_ERR(dsi->mod_clk)) {
+		dev_err(dev, "Couldn't get the DSI mod clock\n");
+		return PTR_ERR(dsi->mod_clk);
+	}
+
+	/*
+	 * In order to operate properly, that clock seems to be always
+	 * set to 297MHz.
+	 */
+	clk_set_rate_exclusive(dsi->mod_clk, 297000000);
+
+	dphy_node = of_parse_phandle(dev->of_node, "phys", 0);
+	ret = sun6i_dphy_probe(dsi, dphy_node);
+	of_node_put(dphy_node);
+	if (ret) {
+		dev_err(dev, "Couldn't get the MIPI D-PHY\n");
+		goto err_unprotect_clk;
+	}
+
+	pm_runtime_enable(dev);
+
+	ret = mipi_dsi_host_register(&dsi->host);
+	if (ret) {
+		dev_err(dev, "Couldn't register MIPI-DSI host\n");
+		goto err_remove_phy;
+	}
+
+	ret = component_add(&pdev->dev, &sun6i_dsi_ops);
+	if (ret) {
+		dev_err(dev, "Couldn't register our component\n");
+		goto err_remove_dsi_host;
+	}
+
+	return 0;
+
+err_remove_dsi_host:
+	mipi_dsi_host_unregister(&dsi->host);
+err_remove_phy:
+	pm_runtime_disable(dev);
+	sun6i_dphy_remove(dsi);
+err_unprotect_clk:
+	clk_rate_exclusive_put(dsi->mod_clk);
+	return ret;
+}
+
+static int sun6i_dsi_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
+
+	component_del(&pdev->dev, &sun6i_dsi_ops);
+	mipi_dsi_host_unregister(&dsi->host);
+	pm_runtime_disable(dev);
+	sun6i_dphy_remove(dsi);
+	clk_rate_exclusive_put(dsi->mod_clk);
+
+	return 0;
+}
+
+static int sun6i_dsi_runtime_resume(struct device *dev)
+{
+	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
+
+	reset_control_deassert(dsi->reset);
+	clk_prepare_enable(dsi->mod_clk);
+
+	/*
+	 * Enable the DSI block.
+	 *
+	 * Some part of it can only be done once we get a number of
+	 * lanes, see sun6i_dsi_inst_init
+	 */
+	regmap_write(dsi->regs, SUN6I_DSI_CTL_REG, SUN6I_DSI_CTL_EN);
+
+	regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL0_REG,
+		     SUN6I_DSI_BASIC_CTL0_ECC_EN | SUN6I_DSI_BASIC_CTL0_CRC_EN);
+
+	regmap_write(dsi->regs, SUN6I_DSI_TRANS_START_REG, 10);
+	regmap_write(dsi->regs, SUN6I_DSI_TRANS_ZERO_REG, 0);
+
+	if (dsi->device)
+		sun6i_dsi_inst_init(dsi, dsi->device);
+
+	regmap_write(dsi->regs, SUN6I_DSI_DEBUG_DATA_REG, 0xff);
+
+	return 0;
+}
+
+static int sun6i_dsi_runtime_suspend(struct device *dev)
+{
+	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(dsi->mod_clk);
+	reset_control_assert(dsi->reset);
+
+	return 0;
+}
+
+static const struct dev_pm_ops sun6i_dsi_pm_ops = {
+	SET_RUNTIME_PM_OPS(sun6i_dsi_runtime_suspend,
+			   sun6i_dsi_runtime_resume,
+			   NULL)
+};
+
+static const struct of_device_id sun6i_dsi_of_table[] = {
+	{ .compatible = "allwinner,sun6i-a31-mipi-dsi" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sun6i_dsi_of_table);
+
+static struct platform_driver sun6i_dsi_platform_driver = {
+	.probe		= sun6i_dsi_probe,
+	.remove		= sun6i_dsi_remove,
+	.driver		= {
+		.name		= "sun6i-mipi-dsi",
+		.of_match_table	= sun6i_dsi_of_table,
+		.pm		= &sun6i_dsi_pm_ops,
+	},
+};
+module_platform_driver(sun6i_dsi_platform_driver);
+
+MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A31 DSI Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h
new file mode 100644
index 000000000000..dbbc5b3ecbda
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2016 Allwinnertech Co., Ltd.
+ * Copyright (C) 2017-2018 Bootlin
+ *
+ * Maxime Ripard <maxime.ripard@bootlin.com>
+ */
+
+#ifndef _SUN6I_MIPI_DSI_H_
+#define _SUN6I_MIPI_DSI_H_
+
+#include <drm/drm_connector.h>
+#include <drm/drm_encoder.h>
+#include <drm/drm_mipi_dsi.h>
+
+struct sun6i_dphy {
+	struct clk		*bus_clk;
+	struct clk		*mod_clk;
+	struct regmap		*regs;
+	struct reset_control	*reset;
+};
+
+struct sun6i_dsi {
+	struct drm_connector	connector;
+	struct drm_encoder	encoder;
+	struct mipi_dsi_host	host;
+
+	struct clk		*bus_clk;
+	struct clk		*mod_clk;
+	struct regmap		*regs;
+	struct reset_control	*reset;
+	struct sun6i_dphy	*dphy;
+
+	struct device		*dev;
+	struct sun4i_drv	*drv;
+	struct mipi_dsi_device	*device;
+	struct drm_panel	*panel;
+};
+
+static inline struct sun6i_dsi *host_to_sun6i_dsi(struct mipi_dsi_host *host)
+{
+	return container_of(host, struct sun6i_dsi, host);
+};
+
+static inline struct sun6i_dsi *connector_to_sun6i_dsi(struct drm_connector *connector)
+{
+	return container_of(connector, struct sun6i_dsi, connector);
+};
+
+static inline struct sun6i_dsi *encoder_to_sun6i_dsi(const struct drm_encoder *encoder)
+{
+	return container_of(encoder, struct sun6i_dsi, encoder);
+};
+
+int sun6i_dphy_probe(struct sun6i_dsi *dsi, struct device_node *node);
+int sun6i_dphy_remove(struct sun6i_dsi *dsi);
+
+int sun6i_dphy_init(struct sun6i_dphy *dphy, unsigned int lanes);
+int sun6i_dphy_power_on(struct sun6i_dphy *dphy, unsigned int lanes);
+int sun6i_dphy_power_off(struct sun6i_dphy *dphy);
+int sun6i_dphy_exit(struct sun6i_dphy *dphy);
+
+#endif /* _SUN6I_MIPI_DSI_H_ */
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 9f83a65b5ea9..c3afe7b2237e 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -163,28 +163,89 @@ static void tegra_plane_setup_blending_legacy(struct tegra_plane *plane)
 			 BLEND_COLOR_KEY_NONE;
 	u32 blendnokey = BLEND_WEIGHT1(255) | BLEND_WEIGHT0(255);
 	struct tegra_plane_state *state;
+	u32 blending[2];
 	unsigned int i;
 
+	/* disable blending for non-overlapping case */
+	tegra_plane_writel(plane, blendnokey, DC_WIN_BLEND_NOKEY);
+	tegra_plane_writel(plane, foreground, DC_WIN_BLEND_1WIN);
+
 	state = to_tegra_plane_state(plane->base.state);
 
-	/* alpha contribution is 1 minus sum of overlapping windows */
-	for (i = 0; i < 3; i++) {
-		if (state->dependent[i])
-			background[i] |= BLEND_CONTROL_DEPENDENT;
-	}
+	if (state->opaque) {
+		/*
+		 * Since custom fix-weight blending isn't utilized and weight
+		 * of top window is set to max, we can enforce dependent
+		 * blending which in this case results in transparent bottom
+		 * window if top window is opaque and if top window enables
+		 * alpha blending, then bottom window is getting alpha value
+		 * of 1 minus the sum of alpha components of the overlapping
+		 * plane.
+		 */
+		background[0] |= BLEND_CONTROL_DEPENDENT;
+		background[1] |= BLEND_CONTROL_DEPENDENT;
 
-	/* enable alpha blending if pixel format has an alpha component */
-	if (!state->opaque)
+		/*
+		 * The region where three windows overlap is the intersection
+		 * of the two regions where two windows overlap. It contributes
+		 * to the area if all of the windows on top of it have an alpha
+		 * component.
+		 */
+		switch (state->base.normalized_zpos) {
+		case 0:
+			if (state->blending[0].alpha &&
+			    state->blending[1].alpha)
+				background[2] |= BLEND_CONTROL_DEPENDENT;
+			break;
+
+		case 1:
+			background[2] |= BLEND_CONTROL_DEPENDENT;
+			break;
+		}
+	} else {
+		/*
+		 * Enable alpha blending if pixel format has an alpha
+		 * component.
+		 */
 		foreground |= BLEND_CONTROL_ALPHA;
 
-	/*
-	 * Disable blending and assume Window A is the bottom-most window,
-	 * Window C is the top-most window and Window B is in the middle.
-	 */
-	tegra_plane_writel(plane, blendnokey, DC_WIN_BLEND_NOKEY);
-	tegra_plane_writel(plane, foreground, DC_WIN_BLEND_1WIN);
+		/*
+		 * If any of the windows on top of this window is opaque, it
+		 * will completely conceal this window within that area. If
+		 * top window has an alpha component, it is blended over the
+		 * bottom window.
+		 */
+		for (i = 0; i < 2; i++) {
+			if (state->blending[i].alpha &&
+			    state->blending[i].top)
+				background[i] |= BLEND_CONTROL_DEPENDENT;
+		}
+
+		switch (state->base.normalized_zpos) {
+		case 0:
+			if (state->blending[0].alpha &&
+			    state->blending[1].alpha)
+				background[2] |= BLEND_CONTROL_DEPENDENT;
+			break;
 
-	switch (plane->index) {
+		case 1:
+			/*
+			 * When both middle and topmost windows have an alpha,
+			 * these windows a mixed together and then the result
+			 * is blended over the bottom window.
+			 */
+			if (state->blending[0].alpha &&
+			    state->blending[0].top)
+				background[2] |= BLEND_CONTROL_ALPHA;
+
+			if (state->blending[1].alpha &&
+			    state->blending[1].top)
+				background[2] |= BLEND_CONTROL_ALPHA;
+			break;
+		}
+	}
+
+	switch (state->base.normalized_zpos) {
 	case 0:
 		tegra_plane_writel(plane, background[0], DC_WIN_BLEND_2WIN_X);
 		tegra_plane_writel(plane, background[1], DC_WIN_BLEND_2WIN_Y);
@@ -192,8 +253,21 @@ static void tegra_plane_setup_blending_legacy(struct tegra_plane *plane)
 		break;
 
 	case 1:
-		tegra_plane_writel(plane, foreground, DC_WIN_BLEND_2WIN_X);
-		tegra_plane_writel(plane, background[1], DC_WIN_BLEND_2WIN_Y);
+		/*
+		 * If window B / C is topmost, then X / Y registers are
+		 * matching the order of blending[...] state indices,
+		 * otherwise a swap is required.
+		 */
+		if (!state->blending[0].top && state->blending[1].top) {
+			blending[0] = foreground;
+			blending[1] = background[1];
+		} else {
+			blending[0] = background[0];
+			blending[1] = foreground;
+		}
+
+		tegra_plane_writel(plane, blending[0], DC_WIN_BLEND_2WIN_X);
+		tegra_plane_writel(plane, blending[1], DC_WIN_BLEND_2WIN_Y);
 		tegra_plane_writel(plane, background[2], DC_WIN_BLEND_3WIN_XY);
 		break;
 
@@ -224,6 +298,39 @@ static void tegra_plane_setup_blending(struct tegra_plane *plane,
 	tegra_plane_writel(plane, value, DC_WIN_BLEND_LAYER_CONTROL);
 }
 
+static bool
+tegra_plane_use_horizontal_filtering(struct tegra_plane *plane,
+				     const struct tegra_dc_window *window)
+{
+	struct tegra_dc *dc = plane->dc;
+
+	if (window->src.w == window->dst.w)
+		return false;
+
+	if (plane->index == 0 && dc->soc->has_win_a_without_filters)
+		return false;
+
+	return true;
+}
+
+static bool
+tegra_plane_use_vertical_filtering(struct tegra_plane *plane,
+				   const struct tegra_dc_window *window)
+{
+	struct tegra_dc *dc = plane->dc;
+
+	if (window->src.h == window->dst.h)
+		return false;
+
+	if (plane->index == 0 && dc->soc->has_win_a_without_filters)
+		return false;
+
+	if (plane->index == 2 && dc->soc->has_win_c_without_vert_filter)
+		return false;
+
+	return true;
+}
+
 static void tegra_dc_setup_window(struct tegra_plane *plane,
 				  const struct tegra_dc_window *window)
 {
@@ -361,12 +468,50 @@ static void tegra_dc_setup_window(struct tegra_plane *plane,
 	if (window->bottom_up)
 		value |= V_DIRECTION;
 
+	if (tegra_plane_use_horizontal_filtering(plane, window)) {
+		/*
+		 * Enable horizontal 6-tap filter and set filtering
+		 * coefficients to the default values defined in TRM.
+		 */
+		tegra_plane_writel(plane, 0x00008000, DC_WIN_H_FILTER_P(0));
+		tegra_plane_writel(plane, 0x3e087ce1, DC_WIN_H_FILTER_P(1));
+		tegra_plane_writel(plane, 0x3b117ac1, DC_WIN_H_FILTER_P(2));
+		tegra_plane_writel(plane, 0x591b73aa, DC_WIN_H_FILTER_P(3));
+		tegra_plane_writel(plane, 0x57256d9a, DC_WIN_H_FILTER_P(4));
+		tegra_plane_writel(plane, 0x552f668b, DC_WIN_H_FILTER_P(5));
+		tegra_plane_writel(plane, 0x73385e8b, DC_WIN_H_FILTER_P(6));
+		tegra_plane_writel(plane, 0x72435583, DC_WIN_H_FILTER_P(7));
+		tegra_plane_writel(plane, 0x714c4c8b, DC_WIN_H_FILTER_P(8));
+		tegra_plane_writel(plane, 0x70554393, DC_WIN_H_FILTER_P(9));
+		tegra_plane_writel(plane, 0x715e389b, DC_WIN_H_FILTER_P(10));
+		tegra_plane_writel(plane, 0x71662faa, DC_WIN_H_FILTER_P(11));
+		tegra_plane_writel(plane, 0x536d25ba, DC_WIN_H_FILTER_P(12));
+		tegra_plane_writel(plane, 0x55731bca, DC_WIN_H_FILTER_P(13));
+		tegra_plane_writel(plane, 0x387a11d9, DC_WIN_H_FILTER_P(14));
+		tegra_plane_writel(plane, 0x3c7c08f1, DC_WIN_H_FILTER_P(15));
+
+		value |= H_FILTER;
+	}
+
+	if (tegra_plane_use_vertical_filtering(plane, window)) {
+		unsigned int i, k;
+
+		/*
+		 * Enable vertical 2-tap filter and set filtering
+		 * coefficients to the default values defined in TRM.
+		 */
+		for (i = 0, k = 128; i < 16; i++, k -= 8)
+			tegra_plane_writel(plane, k, DC_WIN_V_FILTER_P(i));
+
+		value |= V_FILTER;
+	}
+
 	tegra_plane_writel(plane, value, DC_WIN_WIN_OPTIONS);
 
-	if (dc->soc->supports_blending)
-		tegra_plane_setup_blending(plane, window);
-	else
+	if (dc->soc->has_legacy_blending)
 		tegra_plane_setup_blending_legacy(plane);
+	else
+		tegra_plane_setup_blending(plane, window);
 }
 
 static const u32 tegra20_primary_formats[] = {
@@ -451,17 +596,18 @@ static int tegra_plane_atomic_check(struct drm_plane *plane,
 				    struct drm_plane_state *state)
 {
 	struct tegra_plane_state *plane_state = to_tegra_plane_state(state);
+	unsigned int rotation = DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_Y;
 	struct tegra_bo_tiling *tiling = &plane_state->tiling;
 	struct tegra_plane *tegra = to_tegra_plane(plane);
 	struct tegra_dc *dc = to_tegra_dc(state->crtc);
-	unsigned int format;
 	int err;
 
 	/* no need for further checks if the plane is being disabled */
 	if (!state->crtc)
 		return 0;
 
-	err = tegra_plane_format(state->fb->format->format, &format,
+	err = tegra_plane_format(state->fb->format->format,
+				 &plane_state->format,
 				 &plane_state->swap);
 	if (err < 0)
 		return err;
@@ -472,22 +618,12 @@ static int tegra_plane_atomic_check(struct drm_plane *plane,
 	 * the corresponding opaque formats. However, the opaque formats can
 	 * be emulated by disabling alpha blending for the plane.
 	 */
-	if (!dc->soc->supports_blending) {
-		if (!tegra_plane_format_has_alpha(format)) {
-			err = tegra_plane_format_get_alpha(format, &format);
-			if (err < 0)
-				return err;
-
-			plane_state->opaque = true;
-		} else {
-			plane_state->opaque = false;
-		}
-
-		tegra_plane_check_dependent(tegra, plane_state);
+	if (dc->soc->has_legacy_blending) {
+		err = tegra_plane_setup_legacy_state(tegra, plane_state);
+		if (err < 0)
+			return err;
 	}
 
-	plane_state->format = format;
-
 	err = tegra_fb_get_tiling(state->fb, tiling);
 	if (err < 0)
 		return err;
@@ -498,6 +634,13 @@ static int tegra_plane_atomic_check(struct drm_plane *plane,
 		return -EINVAL;
 	}
 
+	rotation = drm_rotation_simplify(state->rotation, rotation);
+
+	if (rotation & DRM_MODE_REFLECT_Y)
+		plane_state->bottom_up = true;
+	else
+		plane_state->bottom_up = false;
+
 	/*
 	 * Tegra doesn't support different strides for U and V planes so we
 	 * error out if the user tries to display a framebuffer with such a
@@ -558,7 +701,7 @@ static void tegra_plane_atomic_update(struct drm_plane *plane,
 	window.dst.w = drm_rect_width(&plane->state->dst);
 	window.dst.h = drm_rect_height(&plane->state->dst);
 	window.bits_per_pixel = fb->format->cpp[0] * 8;
-	window.bottom_up = tegra_fb_is_bottom_up(fb);
+	window.bottom_up = tegra_fb_is_bottom_up(fb) || state->bottom_up;
 
 	/* copy from state */
 	window.zpos = plane->state->normalized_zpos;
@@ -639,9 +782,15 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm,
 	}
 
 	drm_plane_helper_add(&plane->base, &tegra_plane_helper_funcs);
+	drm_plane_create_zpos_property(&plane->base, plane->index, 0, 255);
 
-	if (dc->soc->supports_blending)
-		drm_plane_create_zpos_property(&plane->base, 0, 0, 255);
+	err = drm_plane_create_rotation_property(&plane->base,
+						 DRM_MODE_ROTATE_0,
+						 DRM_MODE_ROTATE_0 |
+						 DRM_MODE_REFLECT_Y);
+	if (err < 0)
+		dev_err(dc->dev, "failed to create rotation property: %d\n",
+			err);
 
 	return &plane->base;
 }
@@ -918,9 +1067,15 @@ static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm,
 	}
 
 	drm_plane_helper_add(&plane->base, &tegra_plane_helper_funcs);
+	drm_plane_create_zpos_property(&plane->base, plane->index, 0, 255);
 
-	if (dc->soc->supports_blending)
-		drm_plane_create_zpos_property(&plane->base, 0, 0, 255);
+	err = drm_plane_create_rotation_property(&plane->base,
+						 DRM_MODE_ROTATE_0,
+						 DRM_MODE_ROTATE_0 |
+						 DRM_MODE_REFLECT_Y);
+	if (err < 0)
+		dev_err(dc->dev, "failed to create rotation property: %d\n",
+			err);
 
 	return &plane->base;
 }
@@ -1826,7 +1981,6 @@ static irqreturn_t tegra_dc_irq(int irq, void *data)
 static int tegra_dc_init(struct host1x_client *client)
 {
 	struct drm_device *drm = dev_get_drvdata(client->parent);
-	struct iommu_group *group = iommu_group_get(client->dev);
 	unsigned long flags = HOST1X_SYNCPT_CLIENT_MANAGED;
 	struct tegra_dc *dc = host1x_client_to_dc(client);
 	struct tegra_drm *tegra = drm->dev_private;
@@ -1838,20 +1992,11 @@ static int tegra_dc_init(struct host1x_client *client)
 	if (!dc->syncpt)
 		dev_warn(dc->dev, "failed to allocate syncpoint\n");
 
-	if (group && tegra->domain) {
-		if (group != tegra->group) {
-			err = iommu_attach_group(tegra->domain, group);
-			if (err < 0) {
-				dev_err(dc->dev,
-					"failed to attach to domain: %d\n",
-					err);
-				return err;
-			}
-
-			tegra->group = group;
-		}
-
-		dc->domain = tegra->domain;
+	dc->group = host1x_client_iommu_attach(client, true);
+	if (IS_ERR(dc->group)) {
+		err = PTR_ERR(dc->group);
+		dev_err(client->dev, "failed to attach to domain: %d\n", err);
+		return err;
 	}
 
 	if (dc->soc->wgrps)
@@ -1916,24 +2061,15 @@ cleanup:
 	if (!IS_ERR(primary))
 		drm_plane_cleanup(primary);
 
-	if (group && dc->domain) {
-		if (group == tegra->group) {
-			iommu_detach_group(dc->domain, group);
-			tegra->group = NULL;
-		}
-
-		dc->domain = NULL;
-	}
+	host1x_client_iommu_detach(client, dc->group);
+	host1x_syncpt_free(dc->syncpt);
 
 	return err;
 }
 
 static int tegra_dc_exit(struct host1x_client *client)
 {
-	struct drm_device *drm = dev_get_drvdata(client->parent);
-	struct iommu_group *group = iommu_group_get(client->dev);
 	struct tegra_dc *dc = host1x_client_to_dc(client);
-	struct tegra_drm *tegra = drm->dev_private;
 	int err;
 
 	devm_free_irq(dc->dev, dc->irq, dc);
@@ -1944,15 +2080,7 @@ static int tegra_dc_exit(struct host1x_client *client)
 		return err;
 	}
 
-	if (group && dc->domain) {
-		if (group == tegra->group) {
-			iommu_detach_group(dc->domain, group);
-			tegra->group = NULL;
-		}
-
-		dc->domain = NULL;
-	}
-
+	host1x_client_iommu_detach(client, dc->group);
 	host1x_syncpt_free(dc->syncpt);
 
 	return 0;
@@ -1968,7 +2096,7 @@ static const struct tegra_dc_soc_info tegra20_dc_soc_info = {
 	.supports_interlacing = false,
 	.supports_cursor = false,
 	.supports_block_linear = false,
-	.supports_blending = false,
+	.has_legacy_blending = true,
 	.pitch_align = 8,
 	.has_powergate = false,
 	.coupled_pm = true,
@@ -1978,6 +2106,8 @@ static const struct tegra_dc_soc_info tegra20_dc_soc_info = {
 	.num_overlay_formats = ARRAY_SIZE(tegra20_overlay_formats),
 	.overlay_formats = tegra20_overlay_formats,
 	.modifiers = tegra20_modifiers,
+	.has_win_a_without_filters = true,
+	.has_win_c_without_vert_filter = true,
 };
 
 static const struct tegra_dc_soc_info tegra30_dc_soc_info = {
@@ -1985,7 +2115,7 @@ static const struct tegra_dc_soc_info tegra30_dc_soc_info = {
 	.supports_interlacing = false,
 	.supports_cursor = false,
 	.supports_block_linear = false,
-	.supports_blending = false,
+	.has_legacy_blending = true,
 	.pitch_align = 8,
 	.has_powergate = false,
 	.coupled_pm = false,
@@ -1995,6 +2125,8 @@ static const struct tegra_dc_soc_info tegra30_dc_soc_info = {
 	.num_overlay_formats = ARRAY_SIZE(tegra20_overlay_formats),
 	.overlay_formats = tegra20_overlay_formats,
 	.modifiers = tegra20_modifiers,
+	.has_win_a_without_filters = false,
+	.has_win_c_without_vert_filter = false,
 };
 
 static const struct tegra_dc_soc_info tegra114_dc_soc_info = {
@@ -2002,7 +2134,7 @@ static const struct tegra_dc_soc_info tegra114_dc_soc_info = {
 	.supports_interlacing = false,
 	.supports_cursor = false,
 	.supports_block_linear = false,
-	.supports_blending = false,
+	.has_legacy_blending = true,
 	.pitch_align = 64,
 	.has_powergate = true,
 	.coupled_pm = false,
@@ -2012,6 +2144,8 @@ static const struct tegra_dc_soc_info tegra114_dc_soc_info = {
 	.num_overlay_formats = ARRAY_SIZE(tegra114_overlay_formats),
 	.overlay_formats = tegra114_overlay_formats,
 	.modifiers = tegra20_modifiers,
+	.has_win_a_without_filters = false,
+	.has_win_c_without_vert_filter = false,
 };
 
 static const struct tegra_dc_soc_info tegra124_dc_soc_info = {
@@ -2019,7 +2153,7 @@ static const struct tegra_dc_soc_info tegra124_dc_soc_info = {
 	.supports_interlacing = true,
 	.supports_cursor = true,
 	.supports_block_linear = true,
-	.supports_blending = true,
+	.has_legacy_blending = false,
 	.pitch_align = 64,
 	.has_powergate = true,
 	.coupled_pm = false,
@@ -2029,6 +2163,8 @@ static const struct tegra_dc_soc_info tegra124_dc_soc_info = {
 	.num_overlay_formats = ARRAY_SIZE(tegra124_overlay_formats),
 	.overlay_formats = tegra124_overlay_formats,
 	.modifiers = tegra124_modifiers,
+	.has_win_a_without_filters = false,
+	.has_win_c_without_vert_filter = false,
 };
 
 static const struct tegra_dc_soc_info tegra210_dc_soc_info = {
@@ -2036,7 +2172,7 @@ static const struct tegra_dc_soc_info tegra210_dc_soc_info = {
 	.supports_interlacing = true,
 	.supports_cursor = true,
 	.supports_block_linear = true,
-	.supports_blending = true,
+	.has_legacy_blending = false,
 	.pitch_align = 64,
 	.has_powergate = true,
 	.coupled_pm = false,
@@ -2046,6 +2182,8 @@ static const struct tegra_dc_soc_info tegra210_dc_soc_info = {
 	.num_overlay_formats = ARRAY_SIZE(tegra114_overlay_formats),
 	.overlay_formats = tegra114_overlay_formats,
 	.modifiers = tegra124_modifiers,
+	.has_win_a_without_filters = false,
+	.has_win_c_without_vert_filter = false,
 };
 
 static const struct tegra_windowgroup_soc tegra186_dc_wgrps[] = {
@@ -2087,7 +2225,7 @@ static const struct tegra_dc_soc_info tegra186_dc_soc_info = {
 	.supports_interlacing = true,
 	.supports_cursor = true,
 	.supports_block_linear = true,
-	.supports_blending = true,
+	.has_legacy_blending = false,
 	.pitch_align = 64,
 	.has_powergate = false,
 	.coupled_pm = false,
diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h
index d2b50d32de4d..e96f582ca692 100644
--- a/drivers/gpu/drm/tegra/dc.h
+++ b/drivers/gpu/drm/tegra/dc.h
@@ -55,7 +55,7 @@ struct tegra_dc_soc_info {
 	bool supports_interlacing;
 	bool supports_cursor;
 	bool supports_block_linear;
-	bool supports_blending;
+	bool has_legacy_blending;
 	unsigned int pitch_align;
 	bool has_powergate;
 	bool coupled_pm;
@@ -67,6 +67,8 @@ struct tegra_dc_soc_info {
 	const u32 *overlay_formats;
 	unsigned int num_overlay_formats;
 	const u64 *modifiers;
+	bool has_win_a_without_filters;
+	bool has_win_c_without_vert_filter;
 };
 
 struct tegra_dc {
@@ -92,7 +94,7 @@ struct tegra_dc {
 
 	const struct tegra_dc_soc_info *soc;
 
-	struct iommu_domain *domain;
+	struct iommu_group *group;
 };
 
 static inline struct tegra_dc *
@@ -553,6 +555,9 @@ int tegra_dc_rgb_exit(struct tegra_dc *dc);
 #define  THREAD_NUM(x) (((x) & 0x1f) << 1)
 #define  THREAD_GROUP_ENABLE (1 << 0)
 
+#define DC_WIN_H_FILTER_P(p)			(0x601 + (p))
+#define DC_WIN_V_FILTER_P(p)			(0x619 + (p))
+
 #define DC_WIN_CSC_YOF				0x611
 #define DC_WIN_CSC_KYRGB			0x612
 #define DC_WIN_CSC_KUR				0x613
@@ -566,6 +571,8 @@ int tegra_dc_rgb_exit(struct tegra_dc *dc);
 #define H_DIRECTION  (1 <<  0)
 #define V_DIRECTION  (1 <<  2)
 #define COLOR_EXPAND (1 <<  6)
+#define H_FILTER     (1 <<  8)
+#define V_FILTER     (1 << 10)
 #define CSC_ENABLE   (1 << 18)
 #define WIN_ENABLE   (1 << 30)
 
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 7afe2f635f74..776c1513e582 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -38,26 +38,11 @@ static int tegra_atomic_check(struct drm_device *drm,
 {
 	int err;
 
-	err = drm_atomic_helper_check_modeset(drm, state);
+	err = drm_atomic_helper_check(drm, state);
 	if (err < 0)
 		return err;
 
-	err = tegra_display_hub_atomic_check(drm, state);
-	if (err < 0)
-		return err;
-
-	err = drm_atomic_normalize_zpos(drm, state);
-	if (err < 0)
-		return err;
-
-	err = drm_atomic_helper_check_planes(drm, state);
-	if (err < 0)
-		return err;
-
-	if (state->legacy_cursor_update)
-		state->async_update = !drm_atomic_helper_async_check(drm, state);
-
-	return 0;
+	return tegra_display_hub_atomic_check(drm, state);
 }
 
 static const struct drm_mode_config_funcs tegra_drm_mode_config_funcs = {
@@ -113,6 +98,10 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 			goto free;
 		}
 
+		err = iova_cache_get();
+		if (err < 0)
+			goto domain;
+
 		geometry = &tegra->domain->geometry;
 		gem_start = geometry->aperture_start;
 		gem_end = geometry->aperture_end - CARVEOUT_SZ;
@@ -151,6 +140,8 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 
 	drm->mode_config.allow_fb_modifiers = true;
 
+	drm->mode_config.normalize_zpos = true;
+
 	drm->mode_config.funcs = &tegra_drm_mode_config_funcs;
 	drm->mode_config.helper_private = &tegra_drm_mode_config_helpers;
 
@@ -204,11 +195,14 @@ config:
 	drm_mode_config_cleanup(drm);
 
 	if (tegra->domain) {
-		iommu_domain_free(tegra->domain);
-		drm_mm_takedown(&tegra->mm);
 		mutex_destroy(&tegra->mm_lock);
+		drm_mm_takedown(&tegra->mm);
 		put_iova_domain(&tegra->carveout.domain);
+		iova_cache_put();
 	}
+domain:
+	if (tegra->domain)
+		iommu_domain_free(tegra->domain);
 free:
 	kfree(tegra);
 	return err;
@@ -230,10 +224,11 @@ static void tegra_drm_unload(struct drm_device *drm)
 		return;
 
 	if (tegra->domain) {
-		iommu_domain_free(tegra->domain);
-		drm_mm_takedown(&tegra->mm);
 		mutex_destroy(&tegra->mm_lock);
+		drm_mm_takedown(&tegra->mm);
 		put_iova_domain(&tegra->carveout.domain);
+		iova_cache_put();
+		iommu_domain_free(tegra->domain);
 	}
 
 	kfree(tegra);
@@ -313,46 +308,15 @@ static int host1x_reloc_copy_from_user(struct host1x_reloc *dest,
 	return 0;
 }
 
-static int host1x_waitchk_copy_from_user(struct host1x_waitchk *dest,
-					 struct drm_tegra_waitchk __user *src,
-					 struct drm_file *file)
-{
-	u32 cmdbuf;
-	int err;
-
-	err = get_user(cmdbuf, &src->handle);
-	if (err < 0)
-		return err;
-
-	err = get_user(dest->offset, &src->offset);
-	if (err < 0)
-		return err;
-
-	err = get_user(dest->syncpt_id, &src->syncpt);
-	if (err < 0)
-		return err;
-
-	err = get_user(dest->thresh, &src->thresh);
-	if (err < 0)
-		return err;
-
-	dest->bo = host1x_bo_lookup(file, cmdbuf);
-	if (!dest->bo)
-		return -ENOENT;
-
-	return 0;
-}
-
 int tegra_drm_submit(struct tegra_drm_context *context,
 		     struct drm_tegra_submit *args, struct drm_device *drm,
 		     struct drm_file *file)
 {
+	struct host1x_client *client = &context->client->base;
 	unsigned int num_cmdbufs = args->num_cmdbufs;
 	unsigned int num_relocs = args->num_relocs;
-	unsigned int num_waitchks = args->num_waitchks;
 	struct drm_tegra_cmdbuf __user *user_cmdbufs;
 	struct drm_tegra_reloc __user *user_relocs;
-	struct drm_tegra_waitchk __user *user_waitchks;
 	struct drm_tegra_syncpt __user *user_syncpt;
 	struct drm_tegra_syncpt syncpt;
 	struct host1x *host1x = dev_get_drvdata(drm->dev->parent);
@@ -364,7 +328,6 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 
 	user_cmdbufs = u64_to_user_ptr(args->cmdbufs);
 	user_relocs = u64_to_user_ptr(args->relocs);
-	user_waitchks = u64_to_user_ptr(args->waitchks);
 	user_syncpt = u64_to_user_ptr(args->syncpts);
 
 	/* We don't yet support other than one syncpt_incr struct per submit */
@@ -376,21 +339,20 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		return -EINVAL;
 
 	job = host1x_job_alloc(context->channel, args->num_cmdbufs,
-			       args->num_relocs, args->num_waitchks);
+			       args->num_relocs);
 	if (!job)
 		return -ENOMEM;
 
 	job->num_relocs = args->num_relocs;
-	job->num_waitchk = args->num_waitchks;
-	job->client = (u32)args->context;
-	job->class = context->client->base.class;
+	job->client = client;
+	job->class = client->class;
 	job->serialize = true;
 
 	/*
 	 * Track referenced BOs so that they can be unreferenced after the
 	 * submission is complete.
 	 */
-	num_refs = num_cmdbufs + num_relocs * 2 + num_waitchks;
+	num_refs = num_cmdbufs + num_relocs * 2;
 
 	refs = kmalloc_array(num_refs, sizeof(*refs), GFP_KERNEL);
 	if (!refs) {
@@ -451,13 +413,13 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		struct host1x_reloc *reloc;
 		struct tegra_bo *obj;
 
-		err = host1x_reloc_copy_from_user(&job->relocarray[num_relocs],
+		err = host1x_reloc_copy_from_user(&job->relocs[num_relocs],
 						  &user_relocs[num_relocs], drm,
 						  file);
 		if (err < 0)
 			goto fail;
 
-		reloc = &job->relocarray[num_relocs];
+		reloc = &job->relocs[num_relocs];
 		obj = host1x_to_tegra_bo(reloc->cmdbuf.bo);
 		refs[num_refs++] = &obj->gem;
 
@@ -481,30 +443,6 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		}
 	}
 
-	/* copy and resolve waitchks from submit */
-	while (num_waitchks--) {
-		struct host1x_waitchk *wait = &job->waitchk[num_waitchks];
-		struct tegra_bo *obj;
-
-		err = host1x_waitchk_copy_from_user(
-			wait, &user_waitchks[num_waitchks], file);
-		if (err < 0)
-			goto fail;
-
-		obj = host1x_to_tegra_bo(wait->bo);
-		refs[num_refs++] = &obj->gem;
-
-		/*
-		 * The unaligned offset will cause an unaligned write during
-		 * of the waitchks patching, corrupting the commands stream.
-		 */
-		if (wait->offset & 3 ||
-		    wait->offset >= obj->gem.size) {
-			err = -EINVAL;
-			goto fail;
-		}
-	}
-
 	if (copy_from_user(&syncpt, user_syncpt, sizeof(syncpt))) {
 		err = -EFAULT;
 		goto fail;
@@ -1114,6 +1052,52 @@ int tegra_drm_unregister_client(struct tegra_drm *tegra,
 	return 0;
 }
 
+struct iommu_group *host1x_client_iommu_attach(struct host1x_client *client,
+					       bool shared)
+{
+	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct tegra_drm *tegra = drm->dev_private;
+	struct iommu_group *group = NULL;
+	int err;
+
+	if (tegra->domain) {
+		group = iommu_group_get(client->dev);
+		if (!group) {
+			dev_err(client->dev, "failed to get IOMMU group\n");
+			return ERR_PTR(-ENODEV);
+		}
+
+		if (!shared || (shared && (group != tegra->group))) {
+			err = iommu_attach_group(tegra->domain, group);
+			if (err < 0) {
+				iommu_group_put(group);
+				return ERR_PTR(err);
+			}
+
+			if (shared && !tegra->group)
+				tegra->group = group;
+		}
+	}
+
+	return group;
+}
+
+void host1x_client_iommu_detach(struct host1x_client *client,
+				struct iommu_group *group)
+{
+	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct tegra_drm *tegra = drm->dev_private;
+
+	if (group) {
+		if (group == tegra->group) {
+			iommu_detach_group(tegra->domain, group);
+			tegra->group = NULL;
+		}
+
+		iommu_group_put(group);
+	}
+}
+
 void *tegra_drm_alloc(struct tegra_drm *tegra, size_t size, dma_addr_t *dma)
 {
 	struct iova *alloc;
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index 4f41aaec8530..92d248784396 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -29,16 +29,10 @@
 
 struct reset_control;
 
-struct tegra_fb {
-	struct drm_framebuffer base;
-	struct tegra_bo **planes;
-	unsigned int num_planes;
-};
-
 #ifdef CONFIG_DRM_FBDEV_EMULATION
 struct tegra_fbdev {
 	struct drm_fb_helper base;
-	struct tegra_fb *fb;
+	struct drm_framebuffer *fb;
 };
 #endif
 
@@ -97,6 +91,7 @@ struct tegra_drm_client {
 	struct host1x_client base;
 	struct list_head list;
 
+	unsigned int version;
 	const struct tegra_drm_client_ops *ops;
 };
 
@@ -110,6 +105,10 @@ int tegra_drm_register_client(struct tegra_drm *tegra,
 			      struct tegra_drm_client *client);
 int tegra_drm_unregister_client(struct tegra_drm *tegra,
 				struct tegra_drm_client *client);
+struct iommu_group *host1x_client_iommu_attach(struct host1x_client *client,
+					       bool shared);
+void host1x_client_iommu_detach(struct host1x_client *client,
+				struct iommu_group *group);
 
 int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm);
 int tegra_drm_exit(struct tegra_drm *tegra);
diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c
index e69434909a42..4c22cdded3c2 100644
--- a/drivers/gpu/drm/tegra/fb.c
+++ b/drivers/gpu/drm/tegra/fb.c
@@ -14,11 +14,7 @@
 
 #include "drm.h"
 #include "gem.h"
-
-static inline struct tegra_fb *to_tegra_fb(struct drm_framebuffer *fb)
-{
-	return container_of(fb, struct tegra_fb, base);
-}
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
 static inline struct tegra_fbdev *to_tegra_fbdev(struct drm_fb_helper *helper)
@@ -30,19 +26,14 @@ static inline struct tegra_fbdev *to_tegra_fbdev(struct drm_fb_helper *helper)
 struct tegra_bo *tegra_fb_get_plane(struct drm_framebuffer *framebuffer,
 				    unsigned int index)
 {
-	struct tegra_fb *fb = to_tegra_fb(framebuffer);
-
-	if (index >= framebuffer->format->num_planes)
-		return NULL;
-
-	return fb->planes[index];
+	return to_tegra_bo(drm_gem_fb_get_obj(framebuffer, index));
 }
 
 bool tegra_fb_is_bottom_up(struct drm_framebuffer *framebuffer)
 {
-	struct tegra_fb *fb = to_tegra_fb(framebuffer);
+	struct tegra_bo *bo = tegra_fb_get_plane(framebuffer, 0);
 
-	if (fb->planes[0]->flags & TEGRA_BO_BOTTOM_UP)
+	if (bo->flags & TEGRA_BO_BOTTOM_UP)
 		return true;
 
 	return false;
@@ -51,8 +42,7 @@ bool tegra_fb_is_bottom_up(struct drm_framebuffer *framebuffer)
 int tegra_fb_get_tiling(struct drm_framebuffer *framebuffer,
 			struct tegra_bo_tiling *tiling)
 {
-	struct tegra_fb *fb = to_tegra_fb(framebuffer);
-	uint64_t modifier = fb->base.modifier;
+	uint64_t modifier = framebuffer->modifier;
 
 	switch (modifier) {
 	case DRM_FORMAT_MOD_LINEAR:
@@ -102,46 +92,17 @@ int tegra_fb_get_tiling(struct drm_framebuffer *framebuffer,
 	return 0;
 }
 
-static void tegra_fb_destroy(struct drm_framebuffer *framebuffer)
-{
-	struct tegra_fb *fb = to_tegra_fb(framebuffer);
-	unsigned int i;
-
-	for (i = 0; i < fb->num_planes; i++) {
-		struct tegra_bo *bo = fb->planes[i];
-
-		if (bo) {
-			if (bo->pages)
-				vunmap(bo->vaddr);
-
-			drm_gem_object_put_unlocked(&bo->gem);
-		}
-	}
-
-	drm_framebuffer_cleanup(framebuffer);
-	kfree(fb->planes);
-	kfree(fb);
-}
-
-static int tegra_fb_create_handle(struct drm_framebuffer *framebuffer,
-				  struct drm_file *file, unsigned int *handle)
-{
-	struct tegra_fb *fb = to_tegra_fb(framebuffer);
-
-	return drm_gem_handle_create(file, &fb->planes[0]->gem, handle);
-}
-
 static const struct drm_framebuffer_funcs tegra_fb_funcs = {
-	.destroy = tegra_fb_destroy,
-	.create_handle = tegra_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
 };
 
-static struct tegra_fb *tegra_fb_alloc(struct drm_device *drm,
-				       const struct drm_mode_fb_cmd2 *mode_cmd,
-				       struct tegra_bo **planes,
-				       unsigned int num_planes)
+static struct drm_framebuffer *tegra_fb_alloc(struct drm_device *drm,
+					      const struct drm_mode_fb_cmd2 *mode_cmd,
+					      struct tegra_bo **planes,
+					      unsigned int num_planes)
 {
-	struct tegra_fb *fb;
+	struct drm_framebuffer *fb;
 	unsigned int i;
 	int err;
 
@@ -149,24 +110,15 @@ static struct tegra_fb *tegra_fb_alloc(struct drm_device *drm,
 	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
-	fb->planes = kzalloc(num_planes * sizeof(*planes), GFP_KERNEL);
-	if (!fb->planes) {
-		kfree(fb);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	fb->num_planes = num_planes;
+	drm_helper_mode_fill_fb_struct(drm, fb, mode_cmd);
 
-	drm_helper_mode_fill_fb_struct(drm, &fb->base, mode_cmd);
+	for (i = 0; i < fb->format->num_planes; i++)
+		fb->obj[i] = &planes[i]->gem;
 
-	for (i = 0; i < fb->num_planes; i++)
-		fb->planes[i] = planes[i];
-
-	err = drm_framebuffer_init(drm, &fb->base, &tegra_fb_funcs);
+	err = drm_framebuffer_init(drm, fb, &tegra_fb_funcs);
 	if (err < 0) {
 		dev_err(drm->dev, "failed to initialize framebuffer: %d\n",
 			err);
-		kfree(fb->planes);
 		kfree(fb);
 		return ERR_PTR(err);
 	}
@@ -181,7 +133,7 @@ struct drm_framebuffer *tegra_fb_create(struct drm_device *drm,
 	unsigned int hsub, vsub, i;
 	struct tegra_bo *planes[4];
 	struct drm_gem_object *gem;
-	struct tegra_fb *fb;
+	struct drm_framebuffer *fb;
 	int err;
 
 	hsub = drm_format_horz_chroma_subsampling(cmd->pixel_format);
@@ -217,7 +169,7 @@ struct drm_framebuffer *tegra_fb_create(struct drm_device *drm,
 		goto unreference;
 	}
 
-	return &fb->base;
+	return fb;
 
 unreference:
 	while (i--)
@@ -298,7 +250,7 @@ static int tegra_fbdev_probe(struct drm_fb_helper *helper,
 		return PTR_ERR(fbdev->fb);
 	}
 
-	fb = &fbdev->fb->base;
+	fb = fbdev->fb;
 	helper->fb = fb;
 	helper->fbdev = info;
 
@@ -398,8 +350,17 @@ static void tegra_fbdev_exit(struct tegra_fbdev *fbdev)
 {
 	drm_fb_helper_unregister_fbi(&fbdev->base);
 
-	if (fbdev->fb)
-		drm_framebuffer_remove(&fbdev->fb->base);
+	if (fbdev->fb) {
+		struct tegra_bo *bo = tegra_fb_get_plane(fbdev->fb, 0);
+
+		/* Undo the special mapping we made in fbdev probe. */
+		if (bo && bo->pages) {
+			vunmap(bo->vaddr);
+			bo->vaddr = 0;
+		}
+
+		drm_framebuffer_remove(fbdev->fb);
+	}
 
 	drm_fb_helper_fini(&fbdev->base);
 	tegra_fbdev_free(fbdev);
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 8b0b4ff64bb4..00a5c9f32254 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -422,14 +422,13 @@ int tegra_bo_dumb_create(struct drm_file *file, struct drm_device *drm,
 	return 0;
 }
 
-static int tegra_bo_fault(struct vm_fault *vmf)
+static vm_fault_t tegra_bo_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *gem = vma->vm_private_data;
 	struct tegra_bo *bo = to_tegra_bo(gem);
 	struct page *page;
 	pgoff_t offset;
-	int err;
 
 	if (!bo->pages)
 		return VM_FAULT_SIGBUS;
@@ -437,20 +436,7 @@ static int tegra_bo_fault(struct vm_fault *vmf)
 	offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 	page = bo->pages[offset];
 
-	err = vm_insert_page(vma, vmf->address, page);
-	switch (err) {
-	case -EAGAIN:
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		return VM_FAULT_NOPAGE;
-
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	}
-
-	return VM_FAULT_SIGBUS;
+	return vmf_insert_page(vma, vmf->address, page);
 }
 
 const struct vm_operations_struct tegra_bo_vm_ops = {
@@ -663,6 +649,8 @@ struct dma_buf *tegra_gem_prime_export(struct drm_device *drm,
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 
+	exp_info.exp_name = KBUILD_MODNAME;
+	exp_info.owner = drm->driver->fops->owner;
 	exp_info.ops = &tegra_gem_prime_dmabuf_ops;
 	exp_info.size = gem->size;
 	exp_info.flags = flags;
diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c
index 9a8ea93016a9..673059fd2fcb 100644
--- a/drivers/gpu/drm/tegra/gr2d.c
+++ b/drivers/gpu/drm/tegra/gr2d.c
@@ -7,16 +7,25 @@
  */
 
 #include <linux/clk.h>
+#include <linux/iommu.h>
+#include <linux/of_device.h>
 
 #include "drm.h"
 #include "gem.h"
 #include "gr2d.h"
 
+struct gr2d_soc {
+	unsigned int version;
+};
+
 struct gr2d {
+	struct iommu_group *group;
 	struct tegra_drm_client client;
 	struct host1x_channel *channel;
 	struct clk *clk;
 
+	const struct gr2d_soc *soc;
+
 	DECLARE_BITMAP(addr_regs, GR2D_NUM_REGS);
 };
 
@@ -31,6 +40,7 @@ static int gr2d_init(struct host1x_client *client)
 	struct drm_device *dev = dev_get_drvdata(client->parent);
 	unsigned long flags = HOST1X_SYNCPT_HAS_BASE;
 	struct gr2d *gr2d = to_gr2d(drm);
+	int err;
 
 	gr2d->channel = host1x_channel_request(client->dev);
 	if (!gr2d->channel)
@@ -38,24 +48,48 @@ static int gr2d_init(struct host1x_client *client)
 
 	client->syncpts[0] = host1x_syncpt_request(client, flags);
 	if (!client->syncpts[0]) {
-		host1x_channel_put(gr2d->channel);
-		return -ENOMEM;
+		err = -ENOMEM;
+		dev_err(client->dev, "failed to request syncpoint: %d\n", err);
+		goto put;
+	}
+
+	gr2d->group = host1x_client_iommu_attach(client, false);
+	if (IS_ERR(gr2d->group)) {
+		err = PTR_ERR(gr2d->group);
+		dev_err(client->dev, "failed to attach to domain: %d\n", err);
+		goto free;
+	}
+
+	err = tegra_drm_register_client(dev->dev_private, drm);
+	if (err < 0) {
+		dev_err(client->dev, "failed to register client: %d\n", err);
+		goto detach;
 	}
 
-	return tegra_drm_register_client(dev->dev_private, drm);
+	return 0;
+
+detach:
+	host1x_client_iommu_detach(client, gr2d->group);
+free:
+	host1x_syncpt_free(client->syncpts[0]);
+put:
+	host1x_channel_put(gr2d->channel);
+	return err;
 }
 
 static int gr2d_exit(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
 	struct drm_device *dev = dev_get_drvdata(client->parent);
+	struct tegra_drm *tegra = dev->dev_private;
 	struct gr2d *gr2d = to_gr2d(drm);
 	int err;
 
-	err = tegra_drm_unregister_client(dev->dev_private, drm);
+	err = tegra_drm_unregister_client(tegra, drm);
 	if (err < 0)
 		return err;
 
+	host1x_client_iommu_detach(client, gr2d->group);
 	host1x_syncpt_free(client->syncpts[0]);
 	host1x_channel_put(gr2d->channel);
 
@@ -123,9 +157,17 @@ static const struct tegra_drm_client_ops gr2d_ops = {
 	.submit = tegra_drm_submit,
 };
 
+static const struct gr2d_soc tegra20_gr2d_soc = {
+	.version = 0x20,
+};
+
+static const struct gr2d_soc tegra30_gr2d_soc = {
+	.version = 0x30,
+};
+
 static const struct of_device_id gr2d_match[] = {
-	{ .compatible = "nvidia,tegra30-gr2d" },
-	{ .compatible = "nvidia,tegra20-gr2d" },
+	{ .compatible = "nvidia,tegra30-gr2d", .data = &tegra20_gr2d_soc },
+	{ .compatible = "nvidia,tegra20-gr2d", .data = &tegra30_gr2d_soc },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, gr2d_match);
@@ -158,6 +200,8 @@ static int gr2d_probe(struct platform_device *pdev)
 	if (!gr2d)
 		return -ENOMEM;
 
+	gr2d->soc = of_device_get_match_data(dev);
+
 	syncpts = devm_kzalloc(dev, sizeof(*syncpts), GFP_KERNEL);
 	if (!syncpts)
 		return -ENOMEM;
@@ -182,6 +226,7 @@ static int gr2d_probe(struct platform_device *pdev)
 	gr2d->client.base.num_syncpts = 1;
 
 	INIT_LIST_HEAD(&gr2d->client.list);
+	gr2d->client.version = gr2d->soc->version;
 	gr2d->client.ops = &gr2d_ops;
 
 	err = host1x_client_register(&gr2d->client.base);
diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c
index 28c4ef63065b..4778ae999668 100644
--- a/drivers/gpu/drm/tegra/gr3d.c
+++ b/drivers/gpu/drm/tegra/gr3d.c
@@ -9,7 +9,9 @@
 
 #include <linux/clk.h>
 #include <linux/host1x.h>
+#include <linux/iommu.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 
@@ -19,7 +21,12 @@
 #include "gem.h"
 #include "gr3d.h"
 
+struct gr3d_soc {
+	unsigned int version;
+};
+
 struct gr3d {
+	struct iommu_group *group;
 	struct tegra_drm_client client;
 	struct host1x_channel *channel;
 	struct clk *clk_secondary;
@@ -27,6 +34,8 @@ struct gr3d {
 	struct reset_control *rst_secondary;
 	struct reset_control *rst;
 
+	const struct gr3d_soc *soc;
+
 	DECLARE_BITMAP(addr_regs, GR3D_NUM_REGS);
 };
 
@@ -41,6 +50,7 @@ static int gr3d_init(struct host1x_client *client)
 	struct drm_device *dev = dev_get_drvdata(client->parent);
 	unsigned long flags = HOST1X_SYNCPT_HAS_BASE;
 	struct gr3d *gr3d = to_gr3d(drm);
+	int err;
 
 	gr3d->channel = host1x_channel_request(client->dev);
 	if (!gr3d->channel)
@@ -48,11 +58,33 @@ static int gr3d_init(struct host1x_client *client)
 
 	client->syncpts[0] = host1x_syncpt_request(client, flags);
 	if (!client->syncpts[0]) {
-		host1x_channel_put(gr3d->channel);
-		return -ENOMEM;
+		err = -ENOMEM;
+		dev_err(client->dev, "failed to request syncpoint: %d\n", err);
+		goto put;
 	}
 
-	return tegra_drm_register_client(dev->dev_private, drm);
+	gr3d->group = host1x_client_iommu_attach(client, false);
+	if (IS_ERR(gr3d->group)) {
+		err = PTR_ERR(gr3d->group);
+		dev_err(client->dev, "failed to attach to domain: %d\n", err);
+		goto free;
+	}
+
+	err = tegra_drm_register_client(dev->dev_private, drm);
+	if (err < 0) {
+		dev_err(client->dev, "failed to register client: %d\n", err);
+		goto detach;
+	}
+
+	return 0;
+
+detach:
+	host1x_client_iommu_detach(client, gr3d->group);
+free:
+	host1x_syncpt_free(client->syncpts[0]);
+put:
+	host1x_channel_put(gr3d->channel);
+	return err;
 }
 
 static int gr3d_exit(struct host1x_client *client)
@@ -66,6 +98,7 @@ static int gr3d_exit(struct host1x_client *client)
 	if (err < 0)
 		return err;
 
+	host1x_client_iommu_detach(client, gr3d->group);
 	host1x_syncpt_free(client->syncpts[0]);
 	host1x_channel_put(gr3d->channel);
 
@@ -125,10 +158,22 @@ static const struct tegra_drm_client_ops gr3d_ops = {
 	.submit = tegra_drm_submit,
 };
 
+static const struct gr3d_soc tegra20_gr3d_soc = {
+	.version = 0x20,
+};
+
+static const struct gr3d_soc tegra30_gr3d_soc = {
+	.version = 0x30,
+};
+
+static const struct gr3d_soc tegra114_gr3d_soc = {
+	.version = 0x35,
+};
+
 static const struct of_device_id tegra_gr3d_match[] = {
-	{ .compatible = "nvidia,tegra114-gr3d" },
-	{ .compatible = "nvidia,tegra30-gr3d" },
-	{ .compatible = "nvidia,tegra20-gr3d" },
+	{ .compatible = "nvidia,tegra114-gr3d", .data = &tegra114_gr3d_soc },
+	{ .compatible = "nvidia,tegra30-gr3d", .data = &tegra30_gr3d_soc },
+	{ .compatible = "nvidia,tegra20-gr3d", .data = &tegra20_gr3d_soc },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, tegra_gr3d_match);
@@ -250,6 +295,8 @@ static int gr3d_probe(struct platform_device *pdev)
 	if (!gr3d)
 		return -ENOMEM;
 
+	gr3d->soc = of_device_get_match_data(&pdev->dev);
+
 	syncpts = devm_kzalloc(&pdev->dev, sizeof(*syncpts), GFP_KERNEL);
 	if (!syncpts)
 		return -ENOMEM;
@@ -307,6 +354,7 @@ static int gr3d_probe(struct platform_device *pdev)
 	gr3d->client.base.num_syncpts = 1;
 
 	INIT_LIST_HEAD(&gr3d->client.list);
+	gr3d->client.version = gr3d->soc->version;
 	gr3d->client.ops = &gr3d_ops;
 
 	err = host1x_client_register(&gr3d->client.base);
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index 9a3f23d4780f..8f4fcbb515fb 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -687,7 +687,7 @@ void tegra_display_hub_atomic_commit(struct drm_device *drm,
 	struct device *dev = hub->client.dev;
 	int err;
 
-	hub_state = tegra_display_hub_get_state(hub, state);
+	hub_state = to_tegra_display_hub_state(hub->base.state);
 
 	if (hub_state->clk) {
 		err = clk_set_rate(hub_state->clk, hub_state->rate);
diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c
index 176ef46c615c..d068e8aa3553 100644
--- a/drivers/gpu/drm/tegra/plane.c
+++ b/drivers/gpu/drm/tegra/plane.c
@@ -23,6 +23,7 @@ static void tegra_plane_destroy(struct drm_plane *plane)
 
 static void tegra_plane_reset(struct drm_plane *plane)
 {
+	struct tegra_plane *p = to_tegra_plane(plane);
 	struct tegra_plane_state *state;
 
 	if (plane->state)
@@ -35,6 +36,8 @@ static void tegra_plane_reset(struct drm_plane *plane)
 	if (state) {
 		plane->state = &state->base;
 		plane->state->plane = plane;
+		plane->state->zpos = p->index;
+		plane->state->normalized_zpos = p->index;
 	}
 }
 
@@ -53,10 +56,11 @@ tegra_plane_atomic_duplicate_state(struct drm_plane *plane)
 	copy->tiling = state->tiling;
 	copy->format = state->format;
 	copy->swap = state->swap;
+	copy->bottom_up = state->bottom_up;
 	copy->opaque = state->opaque;
 
-	for (i = 0; i < 3; i++)
-		copy->dependent[i] = state->dependent[i];
+	for (i = 0; i < 2; i++)
+		copy->blending[i] = state->blending[i];
 
 	return &copy->base;
 }
@@ -267,24 +271,8 @@ static bool __drm_format_has_alpha(u32 format)
 	return false;
 }
 
-/*
- * This is applicable to Tegra20 and Tegra30 only where the opaque formats can
- * be emulated using the alpha formats and alpha blending disabled.
- */
-bool tegra_plane_format_has_alpha(unsigned int format)
-{
-	switch (format) {
-	case WIN_COLOR_DEPTH_B5G5R5A1:
-	case WIN_COLOR_DEPTH_A1B5G5R5:
-	case WIN_COLOR_DEPTH_R8G8B8A8:
-	case WIN_COLOR_DEPTH_B8G8R8A8:
-		return true;
-	}
-
-	return false;
-}
-
-int tegra_plane_format_get_alpha(unsigned int opaque, unsigned int *alpha)
+static int tegra_plane_format_get_alpha(unsigned int opaque,
+					unsigned int *alpha)
 {
 	if (tegra_plane_format_is_yuv(opaque, NULL)) {
 		*alpha = opaque;
@@ -316,6 +304,67 @@ int tegra_plane_format_get_alpha(unsigned int opaque, unsigned int *alpha)
 	return -EINVAL;
 }
 
+/*
+ * This is applicable to Tegra20 and Tegra30 only where the opaque formats can
+ * be emulated using the alpha formats and alpha blending disabled.
+ */
+static int tegra_plane_setup_opacity(struct tegra_plane *tegra,
+				     struct tegra_plane_state *state)
+{
+	unsigned int format;
+	int err;
+
+	switch (state->format) {
+	case WIN_COLOR_DEPTH_B5G5R5A1:
+	case WIN_COLOR_DEPTH_A1B5G5R5:
+	case WIN_COLOR_DEPTH_R8G8B8A8:
+	case WIN_COLOR_DEPTH_B8G8R8A8:
+		state->opaque = false;
+		break;
+
+	default:
+		err = tegra_plane_format_get_alpha(state->format, &format);
+		if (err < 0)
+			return err;
+
+		state->format = format;
+		state->opaque = true;
+		break;
+	}
+
+	return 0;
+}
+
+static int tegra_plane_check_transparency(struct tegra_plane *tegra,
+					  struct tegra_plane_state *state)
+{
+	struct drm_plane_state *old, *plane_state;
+	struct drm_plane *plane;
+
+	old = drm_atomic_get_old_plane_state(state->base.state, &tegra->base);
+
+	/* check if zpos / transparency changed */
+	if (old->normalized_zpos == state->base.normalized_zpos &&
+	    to_tegra_plane_state(old)->opaque == state->opaque)
+		return 0;
+
+	/* include all sibling planes into this commit */
+	drm_for_each_plane(plane, tegra->base.dev) {
+		struct tegra_plane *p = to_tegra_plane(plane);
+
+		/* skip this plane and planes on different CRTCs */
+		if (p == tegra || p->dc != tegra->dc)
+			continue;
+
+		plane_state = drm_atomic_get_plane_state(state->base.state,
+							 plane);
+		if (IS_ERR(plane_state))
+			return PTR_ERR(plane_state);
+	}
+
+	return 1;
+}
+
 static unsigned int tegra_plane_get_overlap_index(struct tegra_plane *plane,
 						  struct tegra_plane *other)
 {
@@ -336,61 +385,98 @@ static unsigned int tegra_plane_get_overlap_index(struct tegra_plane *plane,
 	return index;
 }
 
-void tegra_plane_check_dependent(struct tegra_plane *tegra,
-				 struct tegra_plane_state *state)
+static void tegra_plane_update_transparency(struct tegra_plane *tegra,
+					    struct tegra_plane_state *state)
 {
-	struct drm_plane_state *old, *new;
+	struct drm_plane_state *new;
 	struct drm_plane *plane;
-	unsigned int zpos[2];
 	unsigned int i;
 
-	for (i = 0; i < 2; i++)
-		zpos[i] = 0;
-
-	for_each_oldnew_plane_in_state(state->base.state, plane, old, new, i) {
+	for_each_new_plane_in_state(state->base.state, plane, new, i) {
 		struct tegra_plane *p = to_tegra_plane(plane);
 		unsigned index;
 
 		/* skip this plane and planes on different CRTCs */
-		if (p == tegra || new->crtc != state->base.crtc)
+		if (p == tegra || p->dc != tegra->dc)
 			continue;
 
 		index = tegra_plane_get_overlap_index(tegra, p);
 
-		state->dependent[index] = false;
+		if (new->fb && __drm_format_has_alpha(new->fb->format->format))
+			state->blending[index].alpha = true;
+		else
+			state->blending[index].alpha = false;
+
+		if (new->normalized_zpos > state->base.normalized_zpos)
+			state->blending[index].top = true;
+		else
+			state->blending[index].top = false;
 
 		/*
-		 * If any of the other planes is on top of this plane and uses
-		 * a format with an alpha component, mark this plane as being
-		 * dependent, meaning it's alpha value will be 1 minus the sum
-		 * of alpha components of the overlapping planes.
+		 * Missing framebuffer means that plane is disabled, in this
+		 * case mark B / C window as top to be able to differentiate
+		 * windows indices order in regards to zPos for the middle
+		 * window X / Y registers programming.
 		 */
-		if (p->index > tegra->index) {
-			if (__drm_format_has_alpha(new->fb->format->format))
-				state->dependent[index] = true;
-
-			/* keep track of the Z position */
-			zpos[index] = p->index;
-		}
+		if (!new->fb)
+			state->blending[index].top = (index == 1);
 	}
+}
+
+static int tegra_plane_setup_transparency(struct tegra_plane *tegra,
+					  struct tegra_plane_state *state)
+{
+	struct tegra_plane_state *tegra_state;
+	struct drm_plane_state *new;
+	struct drm_plane *plane;
+	int err;
 
 	/*
-	 * The region where three windows overlap is the intersection of the
-	 * two regions where two windows overlap. It contributes to the area
-	 * if any of the windows on top of it have an alpha component.
+	 * If planes zpos / transparency changed, sibling planes blending
+	 * state may require adjustment and in this case they will be included
+	 * into this atom commit, otherwise blending state is unchanged.
 	 */
-	for (i = 0; i < 2; i++)
-		state->dependent[2] = state->dependent[2] ||
-				      state->dependent[i];
+	err = tegra_plane_check_transparency(tegra, state);
+	if (err <= 0)
+		return err;
 
 	/*
-	 * However, if any of the windows on top of this window is opaque, it
-	 * will completely conceal this window within that area, so avoid the
-	 * window from contributing to the area.
+	 * All planes are now in the atomic state, walk them up and update
+	 * transparency state for each plane.
 	 */
-	for (i = 0; i < 2; i++) {
-		if (zpos[i] > tegra->index)
-			state->dependent[2] = state->dependent[2] &&
-					      state->dependent[i];
+	drm_for_each_plane(plane, tegra->base.dev) {
+		struct tegra_plane *p = to_tegra_plane(plane);
+
+		/* skip planes on different CRTCs */
+		if (p->dc != tegra->dc)
+			continue;
+
+		new = drm_atomic_get_new_plane_state(state->base.state, plane);
+		tegra_state = to_tegra_plane_state(new);
+
+		/*
+		 * There is no need to update blending state for the disabled
+		 * plane.
+		 */
+		if (new->fb)
+			tegra_plane_update_transparency(p, tegra_state);
 	}
+
+	return 0;
+}
+
+int tegra_plane_setup_legacy_state(struct tegra_plane *tegra,
+				   struct tegra_plane_state *state)
+{
+	int err;
+
+	err = tegra_plane_setup_opacity(tegra, state);
+	if (err < 0)
+		return err;
+
+	err = tegra_plane_setup_transparency(tegra, state);
+	if (err < 0)
+		return err;
+
+	return 0;
 }
diff --git a/drivers/gpu/drm/tegra/plane.h b/drivers/gpu/drm/tegra/plane.h
index 6938719e7e5d..e79e6b4a8e0a 100644
--- a/drivers/gpu/drm/tegra/plane.h
+++ b/drivers/gpu/drm/tegra/plane.h
@@ -34,6 +34,11 @@ static inline struct tegra_plane *to_tegra_plane(struct drm_plane *plane)
 	return container_of(plane, struct tegra_plane, base);
 }
 
+struct tegra_plane_legacy_blending_state {
+	bool alpha;
+	bool top;
+};
+
 struct tegra_plane_state {
 	struct drm_plane_state base;
 
@@ -41,9 +46,11 @@ struct tegra_plane_state {
 	u32 format;
 	u32 swap;
 
+	bool bottom_up;
+
 	/* used for legacy blending support only */
+	struct tegra_plane_legacy_blending_state blending[2];
 	bool opaque;
-	bool dependent[3];
 };
 
 static inline struct tegra_plane_state *
@@ -62,9 +69,7 @@ int tegra_plane_state_add(struct tegra_plane *plane,
 
 int tegra_plane_format(u32 fourcc, u32 *format, u32 *swap);
 bool tegra_plane_format_is_yuv(unsigned int format, bool *planar);
-bool tegra_plane_format_has_alpha(unsigned int format);
-int tegra_plane_format_get_alpha(unsigned int opaque, unsigned int *alpha);
-void tegra_plane_check_dependent(struct tegra_plane *tegra,
-				 struct tegra_plane_state *state);
+int tegra_plane_setup_legacy_state(struct tegra_plane *tegra,
+				   struct tegra_plane_state *state);
 
 #endif /* TEGRA_PLANE_H */
diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c
index f5794dd49f3b..9f657a63b0bb 100644
--- a/drivers/gpu/drm/tegra/vic.c
+++ b/drivers/gpu/drm/tegra/vic.c
@@ -25,6 +25,7 @@
 
 struct vic_config {
 	const char *firmware;
+	unsigned int version;
 };
 
 struct vic {
@@ -264,18 +265,21 @@ static const struct tegra_drm_client_ops vic_ops = {
 
 static const struct vic_config vic_t124_config = {
 	.firmware = NVIDIA_TEGRA_124_VIC_FIRMWARE,
+	.version = 0x40,
 };
 
 #define NVIDIA_TEGRA_210_VIC_FIRMWARE "nvidia/tegra210/vic04_ucode.bin"
 
 static const struct vic_config vic_t210_config = {
 	.firmware = NVIDIA_TEGRA_210_VIC_FIRMWARE,
+	.version = 0x21,
 };
 
 #define NVIDIA_TEGRA_186_VIC_FIRMWARE "nvidia/tegra186/vic04_ucode.bin"
 
 static const struct vic_config vic_t186_config = {
 	.firmware = NVIDIA_TEGRA_186_VIC_FIRMWARE,
+	.version = 0x18,
 };
 
 static const struct of_device_id vic_match[] = {
@@ -342,6 +346,7 @@ static int vic_probe(struct platform_device *pdev)
 	vic->dev = dev;
 
 	INIT_LIST_HEAD(&vic->client.list);
+	vic->client.version = vic->config->version;
 	vic->client.ops = &vic_ops;
 
 	err = host1x_client_register(&vic->client.base);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index 1b278a22c8b7..1067e702c22c 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -224,7 +224,7 @@ static void tilcdc_crtc_set_clk(struct drm_crtc *crtc)
 
 	ret = clk_set_rate(priv->clk, req_rate * clkdiv);
 	clk_rate = clk_get_rate(priv->clk);
-	if (ret < 0) {
+	if (ret < 0 || tilcdc_pclk_diff(req_rate, clk_rate) > 5) {
 		/*
 		 * If we fail to set the clock rate (some architectures don't
 		 * use the common clock framework yet and may not implement
diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
index 4c6616278c48..24a33bf862fa 100644
--- a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
+++ b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
@@ -91,7 +91,7 @@ EXPORT_SYMBOL(tinydrm_gem_cma_prime_import_sg_table);
  * GEM object state and frees the memory used to store the object itself using
  * drm_gem_cma_free_object(). It also handles PRIME buffers which has the kernel
  * virtual address set by tinydrm_gem_cma_prime_import_sg_table(). Drivers
- * can use this as their &drm_driver->gem_free_object callback.
+ * can use this as their &drm_driver->gem_free_object_unlocked callback.
  */
 void tinydrm_gem_cma_free_object(struct drm_gem_object *gem_obj)
 {
diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c b/drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c
index d1c3ce9ab294..dcd390163a4a 100644
--- a/drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c
+++ b/drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c
@@ -78,6 +78,36 @@ bool tinydrm_merge_clips(struct drm_clip_rect *dst,
 }
 EXPORT_SYMBOL(tinydrm_merge_clips);
 
+int tinydrm_fb_dirty(struct drm_framebuffer *fb,
+		     struct drm_file *file_priv,
+		     unsigned int flags, unsigned int color,
+		     struct drm_clip_rect *clips,
+		     unsigned int num_clips)
+{
+	struct tinydrm_device *tdev = fb->dev->dev_private;
+	struct drm_plane *plane = &tdev->pipe.plane;
+	int ret = 0;
+
+	drm_modeset_lock(&plane->mutex, NULL);
+
+	/* fbdev can flush even when we're not interested */
+	if (plane->state->fb == fb) {
+		mutex_lock(&tdev->dirty_lock);
+		ret = tdev->fb_dirty(fb, file_priv, flags,
+				     color, clips, num_clips);
+		mutex_unlock(&tdev->dirty_lock);
+	}
+
+	drm_modeset_unlock(&plane->mutex);
+
+	if (ret)
+		dev_err_once(fb->dev->dev,
+			     "Failed to update display %d\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL(tinydrm_fb_dirty);
+
 /**
  * tinydrm_memcpy - Copy clip buffer
  * @dst: Destination buffer
diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c b/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c
index 11ae950b0fc9..7e8e24d0b7a7 100644
--- a/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c
+++ b/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c
@@ -125,9 +125,8 @@ void tinydrm_display_pipe_update(struct drm_simple_display_pipe *pipe,
 	struct drm_crtc *crtc = &tdev->pipe.crtc;
 
 	if (fb && (fb != old_state->fb)) {
-		pipe->plane.fb = fb;
-		if (fb->funcs->dirty)
-			fb->funcs->dirty(fb, NULL, 0, 0, NULL, 0);
+		if (tdev->fb_dirty)
+			tdev->fb_dirty(fb, NULL, 0, 0, NULL, 0);
 	}
 
 	if (crtc->state->event) {
@@ -139,23 +138,6 @@ void tinydrm_display_pipe_update(struct drm_simple_display_pipe *pipe,
 }
 EXPORT_SYMBOL(tinydrm_display_pipe_update);
 
-/**
- * tinydrm_display_pipe_prepare_fb - Display pipe prepare_fb helper
- * @pipe: Simple display pipe
- * @plane_state: Plane state
- *
- * This function uses drm_gem_fb_prepare_fb() to check if the plane FB has an
- * dma-buf attached, extracts the exclusive fence and attaches it to plane
- * state for the atomic helper to wait on. Drivers can use this as their
- * &drm_simple_display_pipe_funcs->prepare_fb callback.
- */
-int tinydrm_display_pipe_prepare_fb(struct drm_simple_display_pipe *pipe,
-				    struct drm_plane_state *plane_state)
-{
-	return drm_gem_fb_prepare_fb(&pipe->plane, plane_state);
-}
-EXPORT_SYMBOL(tinydrm_display_pipe_prepare_fb);
-
 static int tinydrm_rotate_mode(struct drm_display_mode *mode,
 			       unsigned int rotation)
 {
diff --git a/drivers/gpu/drm/tinydrm/ili9225.c b/drivers/gpu/drm/tinydrm/ili9225.c
index a0759502b81a..841c69aba059 100644
--- a/drivers/gpu/drm/tinydrm/ili9225.c
+++ b/drivers/gpu/drm/tinydrm/ili9225.c
@@ -88,14 +88,8 @@ static int ili9225_fb_dirty(struct drm_framebuffer *fb,
 	bool full;
 	void *tr;
 
-	mutex_lock(&tdev->dirty_lock);
-
 	if (!mipi->enabled)
-		goto out_unlock;
-
-	/* fbdev can flush even when we're not interested */
-	if (tdev->pipe.plane.fb != fb)
-		goto out_unlock;
+		return 0;
 
 	full = tinydrm_merge_clips(&clip, clips, num_clips, flags,
 				   fb->width, fb->height);
@@ -108,7 +102,7 @@ static int ili9225_fb_dirty(struct drm_framebuffer *fb,
 		tr = mipi->tx_buf;
 		ret = mipi_dbi_buf_copy(mipi->tx_buf, fb, &clip, swap);
 		if (ret)
-			goto out_unlock;
+			return ret;
 	} else {
 		tr = cma_obj->vaddr;
 	}
@@ -159,24 +153,18 @@ static int ili9225_fb_dirty(struct drm_framebuffer *fb,
 	ret = mipi_dbi_command_buf(mipi, ILI9225_WRITE_DATA_TO_GRAM, tr,
 				(clip.x2 - clip.x1) * (clip.y2 - clip.y1) * 2);
 
-out_unlock:
-	mutex_unlock(&tdev->dirty_lock);
-
-	if (ret)
-		dev_err_once(fb->dev->dev, "Failed to update display %d\n",
-			     ret);
-
 	return ret;
 }
 
 static const struct drm_framebuffer_funcs ili9225_fb_funcs = {
 	.destroy	= drm_gem_fb_destroy,
 	.create_handle	= drm_gem_fb_create_handle,
-	.dirty		= ili9225_fb_dirty,
+	.dirty		= tinydrm_fb_dirty,
 };
 
 static void ili9225_pipe_enable(struct drm_simple_display_pipe *pipe,
-				struct drm_crtc_state *crtc_state)
+				struct drm_crtc_state *crtc_state,
+				struct drm_plane_state *plane_state)
 {
 	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
 	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
@@ -268,7 +256,7 @@ static void ili9225_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	ili9225_command(mipi, ILI9225_DISPLAY_CONTROL_1, 0x1017);
 
-	mipi_dbi_enable_flush(mipi);
+	mipi_dbi_enable_flush(mipi, crtc_state, plane_state);
 }
 
 static void ili9225_pipe_disable(struct drm_simple_display_pipe *pipe)
@@ -341,6 +329,8 @@ static int ili9225_init(struct device *dev, struct mipi_dbi *mipi,
 	if (ret)
 		return ret;
 
+	tdev->fb_dirty = ili9225_fb_dirty;
+
 	ret = tinydrm_display_pipe_init(tdev, pipe_funcs,
 					DRM_MODE_CONNECTOR_VIRTUAL,
 					ili9225_formats,
@@ -364,7 +354,7 @@ static const struct drm_simple_display_pipe_funcs ili9225_pipe_funcs = {
 	.enable		= ili9225_pipe_enable,
 	.disable	= ili9225_pipe_disable,
 	.update		= tinydrm_display_pipe_update,
-	.prepare_fb	= tinydrm_display_pipe_prepare_fb,
+	.prepare_fb	= drm_gem_fb_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode ili9225_mode = {
diff --git a/drivers/gpu/drm/tinydrm/mi0283qt.c b/drivers/gpu/drm/tinydrm/mi0283qt.c
index d8ed6e6f8e05..015d03f2acba 100644
--- a/drivers/gpu/drm/tinydrm/mi0283qt.c
+++ b/drivers/gpu/drm/tinydrm/mi0283qt.c
@@ -19,6 +19,7 @@
 
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_modeset_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/tinydrm/mipi-dbi.h>
 #include <drm/tinydrm/tinydrm-helpers.h>
 #include <video/mipi_display.h>
@@ -49,7 +50,8 @@
 #define ILI9341_MADCTL_MY	BIT(7)
 
 static void mi0283qt_enable(struct drm_simple_display_pipe *pipe,
-			    struct drm_crtc_state *crtc_state)
+			    struct drm_crtc_state *crtc_state,
+			    struct drm_plane_state *plane_state)
 {
 	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
 	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
@@ -83,24 +85,6 @@ static void mi0283qt_enable(struct drm_simple_display_pipe *pipe,
 	/* Memory Access Control */
 	mipi_dbi_command(mipi, MIPI_DCS_SET_PIXEL_FORMAT, MIPI_DCS_PIXEL_FMT_16BIT);
 
-	switch (mipi->rotation) {
-	default:
-		addr_mode = ILI9341_MADCTL_MV | ILI9341_MADCTL_MY |
-			    ILI9341_MADCTL_MX;
-		break;
-	case 90:
-		addr_mode = ILI9341_MADCTL_MY;
-		break;
-	case 180:
-		addr_mode = ILI9341_MADCTL_MV;
-		break;
-	case 270:
-		addr_mode = ILI9341_MADCTL_MX;
-		break;
-	}
-	addr_mode |= ILI9341_MADCTL_BGR;
-	mipi_dbi_command(mipi, MIPI_DCS_SET_ADDRESS_MODE, addr_mode);
-
 	/* Frame Rate */
 	mipi_dbi_command(mipi, ILI9341_FRMCTR1, 0x00, 0x1b);
 
@@ -126,14 +110,37 @@ static void mi0283qt_enable(struct drm_simple_display_pipe *pipe,
 	msleep(100);
 
 out_enable:
-	mipi_dbi_enable_flush(mipi);
+	/* The PiTFT (ili9340) has a hardware reset circuit that
+	 * resets only on power-on and not on each reboot through
+	 * a gpio like the rpi-display does.
+	 * As a result, we need to always apply the rotation value
+	 * regardless of the display "on/off" state.
+	 */
+	switch (mipi->rotation) {
+	default:
+		addr_mode = ILI9341_MADCTL_MV | ILI9341_MADCTL_MY |
+			    ILI9341_MADCTL_MX;
+		break;
+	case 90:
+		addr_mode = ILI9341_MADCTL_MY;
+		break;
+	case 180:
+		addr_mode = ILI9341_MADCTL_MV;
+		break;
+	case 270:
+		addr_mode = ILI9341_MADCTL_MX;
+		break;
+	}
+	addr_mode |= ILI9341_MADCTL_BGR;
+	mipi_dbi_command(mipi, MIPI_DCS_SET_ADDRESS_MODE, addr_mode);
+	mipi_dbi_enable_flush(mipi, crtc_state, plane_state);
 }
 
 static const struct drm_simple_display_pipe_funcs mi0283qt_pipe_funcs = {
 	.enable = mi0283qt_enable,
 	.disable = mipi_dbi_pipe_disable,
 	.update = tinydrm_display_pipe_update,
-	.prepare_fb = tinydrm_display_pipe_prepare_fb,
+	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode mi0283qt_mode = {
diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c
index 9e903812b573..4d1fb31a781f 100644
--- a/drivers/gpu/drm/tinydrm/mipi-dbi.c
+++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c
@@ -219,14 +219,8 @@ static int mipi_dbi_fb_dirty(struct drm_framebuffer *fb,
 	bool full;
 	void *tr;
 
-	mutex_lock(&tdev->dirty_lock);
-
 	if (!mipi->enabled)
-		goto out_unlock;
-
-	/* fbdev can flush even when we're not interested */
-	if (tdev->pipe.plane.fb != fb)
-		goto out_unlock;
+		return 0;
 
 	full = tinydrm_merge_clips(&clip, clips, num_clips, flags,
 				   fb->width, fb->height);
@@ -239,7 +233,7 @@ static int mipi_dbi_fb_dirty(struct drm_framebuffer *fb,
 		tr = mipi->tx_buf;
 		ret = mipi_dbi_buf_copy(mipi->tx_buf, fb, &clip, swap);
 		if (ret)
-			goto out_unlock;
+			return ret;
 	} else {
 		tr = cma_obj->vaddr;
 	}
@@ -254,20 +248,13 @@ static int mipi_dbi_fb_dirty(struct drm_framebuffer *fb,
 	ret = mipi_dbi_command_buf(mipi, MIPI_DCS_WRITE_MEMORY_START, tr,
 				(clip.x2 - clip.x1) * (clip.y2 - clip.y1) * 2);
 
-out_unlock:
-	mutex_unlock(&tdev->dirty_lock);
-
-	if (ret)
-		dev_err_once(fb->dev->dev, "Failed to update display %d\n",
-			     ret);
-
 	return ret;
 }
 
 static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = {
 	.destroy	= drm_gem_fb_destroy,
 	.create_handle	= drm_gem_fb_create_handle,
-	.dirty		= mipi_dbi_fb_dirty,
+	.dirty		= tinydrm_fb_dirty,
 };
 
 /**
@@ -278,13 +265,16 @@ static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = {
  * enables the backlight. Drivers can use this in their
  * &drm_simple_display_pipe_funcs->enable callback.
  */
-void mipi_dbi_enable_flush(struct mipi_dbi *mipi)
+void mipi_dbi_enable_flush(struct mipi_dbi *mipi,
+			   struct drm_crtc_state *crtc_state,
+			   struct drm_plane_state *plane_state)
 {
-	struct drm_framebuffer *fb = mipi->tinydrm.pipe.plane.fb;
+	struct tinydrm_device *tdev = &mipi->tinydrm;
+	struct drm_framebuffer *fb = plane_state->fb;
 
 	mipi->enabled = true;
 	if (fb)
-		fb->funcs->dirty(fb, NULL, 0, 0, NULL, 0);
+		tdev->fb_dirty(fb, NULL, 0, 0, NULL, 0);
 
 	backlight_enable(mipi->backlight);
 }
@@ -381,6 +371,8 @@ int mipi_dbi_init(struct device *dev, struct mipi_dbi *mipi,
 	if (ret)
 		return ret;
 
+	tdev->fb_dirty = mipi_dbi_fb_dirty;
+
 	/* TODO: Maybe add DRM_MODE_CONNECTOR_SPI */
 	ret = tinydrm_display_pipe_init(tdev, pipe_funcs,
 					DRM_MODE_CONNECTOR_VIRTUAL,
diff --git a/drivers/gpu/drm/tinydrm/repaper.c b/drivers/gpu/drm/tinydrm/repaper.c
index 75740630c410..1ee6855212a0 100644
--- a/drivers/gpu/drm/tinydrm/repaper.c
+++ b/drivers/gpu/drm/tinydrm/repaper.c
@@ -540,14 +540,8 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb,
 	clip.y1 = 0;
 	clip.y2 = fb->height;
 
-	mutex_lock(&tdev->dirty_lock);
-
 	if (!epd->enabled)
-		goto out_unlock;
-
-	/* fbdev can flush even when we're not interested */
-	if (tdev->pipe.plane.fb != fb)
-		goto out_unlock;
+		return 0;
 
 	repaper_get_temperature(epd);
 
@@ -555,16 +549,14 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb,
 		  epd->factored_stage_time);
 
 	buf = kmalloc(fb->width * fb->height, GFP_KERNEL);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
+	if (!buf)
+		return -ENOMEM;
 
 	if (import_attach) {
 		ret = dma_buf_begin_cpu_access(import_attach->dmabuf,
 					       DMA_FROM_DEVICE);
 		if (ret)
-			goto out_unlock;
+			goto out_free;
 	}
 
 	tinydrm_xrgb8888_to_gray8(buf, cma_obj->vaddr, fb, &clip);
@@ -573,7 +565,7 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb,
 		ret = dma_buf_end_cpu_access(import_attach->dmabuf,
 					     DMA_FROM_DEVICE);
 		if (ret)
-			goto out_unlock;
+			goto out_free;
 	}
 
 	repaper_gray8_to_mono_reversed(buf, fb->width, fb->height);
@@ -625,11 +617,7 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb,
 			}
 	}
 
-out_unlock:
-	mutex_unlock(&tdev->dirty_lock);
-
-	if (ret)
-		DRM_DEV_ERROR(fb->dev->dev, "Failed to update display (%d)\n", ret);
+out_free:
 	kfree(buf);
 
 	return ret;
@@ -638,7 +626,7 @@ out_unlock:
 static const struct drm_framebuffer_funcs repaper_fb_funcs = {
 	.destroy	= drm_gem_fb_destroy,
 	.create_handle	= drm_gem_fb_create_handle,
-	.dirty		= repaper_fb_dirty,
+	.dirty		= tinydrm_fb_dirty,
 };
 
 static void power_off(struct repaper_epd *epd)
@@ -659,7 +647,8 @@ static void power_off(struct repaper_epd *epd)
 }
 
 static void repaper_pipe_enable(struct drm_simple_display_pipe *pipe,
-				struct drm_crtc_state *crtc_state)
+				struct drm_crtc_state *crtc_state,
+				struct drm_plane_state *plane_state)
 {
 	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
 	struct repaper_epd *epd = epd_from_tinydrm(tdev);
@@ -852,7 +841,7 @@ static const struct drm_simple_display_pipe_funcs repaper_pipe_funcs = {
 	.enable = repaper_pipe_enable,
 	.disable = repaper_pipe_disable,
 	.update = tinydrm_display_pipe_update,
-	.prepare_fb = tinydrm_display_pipe_prepare_fb,
+	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
 };
 
 static const uint32_t repaper_formats[] = {
@@ -1069,6 +1058,8 @@ static int repaper_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
+	tdev->fb_dirty = repaper_fb_dirty;
+
 	ret = tinydrm_display_pipe_init(tdev, &repaper_pipe_funcs,
 					DRM_MODE_CONNECTOR_VIRTUAL,
 					repaper_formats,
diff --git a/drivers/gpu/drm/tinydrm/st7586.c b/drivers/gpu/drm/tinydrm/st7586.c
index a6396ef9cc4a..5c29e3803ecb 100644
--- a/drivers/gpu/drm/tinydrm/st7586.c
+++ b/drivers/gpu/drm/tinydrm/st7586.c
@@ -120,14 +120,8 @@ static int st7586_fb_dirty(struct drm_framebuffer *fb,
 	int start, end;
 	int ret = 0;
 
-	mutex_lock(&tdev->dirty_lock);
-
 	if (!mipi->enabled)
-		goto out_unlock;
-
-	/* fbdev can flush even when we're not interested */
-	if (tdev->pipe.plane.fb != fb)
-		goto out_unlock;
+		return 0;
 
 	tinydrm_merge_clips(&clip, clips, num_clips, flags, fb->width,
 			    fb->height);
@@ -141,7 +135,7 @@ static int st7586_fb_dirty(struct drm_framebuffer *fb,
 
 	ret = st7586_buf_copy(mipi->tx_buf, fb, &clip);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	/* Pixels are packed 3 per byte */
 	start = clip.x1 / 3;
@@ -158,24 +152,18 @@ static int st7586_fb_dirty(struct drm_framebuffer *fb,
 				   (u8 *)mipi->tx_buf,
 				   (end - start) * (clip.y2 - clip.y1));
 
-out_unlock:
-	mutex_unlock(&tdev->dirty_lock);
-
-	if (ret)
-		dev_err_once(fb->dev->dev, "Failed to update display %d\n",
-			     ret);
-
 	return ret;
 }
 
 static const struct drm_framebuffer_funcs st7586_fb_funcs = {
 	.destroy	= drm_gem_fb_destroy,
 	.create_handle	= drm_gem_fb_create_handle,
-	.dirty		= st7586_fb_dirty,
+	.dirty		= tinydrm_fb_dirty,
 };
 
 static void st7586_pipe_enable(struct drm_simple_display_pipe *pipe,
-			       struct drm_crtc_state *crtc_state)
+			       struct drm_crtc_state *crtc_state,
+			       struct drm_plane_state *plane_state)
 {
 	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
 	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
@@ -237,7 +225,7 @@ static void st7586_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_ON);
 
-	mipi_dbi_enable_flush(mipi);
+	mipi_dbi_enable_flush(mipi, crtc_state, plane_state);
 }
 
 static void st7586_pipe_disable(struct drm_simple_display_pipe *pipe)
@@ -277,6 +265,8 @@ static int st7586_init(struct device *dev, struct mipi_dbi *mipi,
 	if (ret)
 		return ret;
 
+	tdev->fb_dirty = st7586_fb_dirty;
+
 	ret = tinydrm_display_pipe_init(tdev, pipe_funcs,
 					DRM_MODE_CONNECTOR_VIRTUAL,
 					st7586_formats,
@@ -300,7 +290,7 @@ static const struct drm_simple_display_pipe_funcs st7586_pipe_funcs = {
 	.enable		= st7586_pipe_enable,
 	.disable	= st7586_pipe_disable,
 	.update		= tinydrm_display_pipe_update,
-	.prepare_fb	= tinydrm_display_pipe_prepare_fb,
+	.prepare_fb	= drm_gem_fb_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode st7586_mode = {
diff --git a/drivers/gpu/drm/tinydrm/st7735r.c b/drivers/gpu/drm/tinydrm/st7735r.c
index 67d197ecfc4b..6c7b15c9da4f 100644
--- a/drivers/gpu/drm/tinydrm/st7735r.c
+++ b/drivers/gpu/drm/tinydrm/st7735r.c
@@ -37,7 +37,8 @@
 #define ST7735R_MV	BIT(5)
 
 static void jd_t18003_t01_pipe_enable(struct drm_simple_display_pipe *pipe,
-				      struct drm_crtc_state *crtc_state)
+				      struct drm_crtc_state *crtc_state,
+				      struct drm_plane_state *plane_state)
 {
 	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
 	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
@@ -98,14 +99,14 @@ static void jd_t18003_t01_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	msleep(20);
 
-	mipi_dbi_enable_flush(mipi);
+	mipi_dbi_enable_flush(mipi, crtc_state, plane_state);
 }
 
 static const struct drm_simple_display_pipe_funcs jd_t18003_t01_pipe_funcs = {
 	.enable		= jd_t18003_t01_pipe_enable,
 	.disable	= mipi_dbi_pipe_disable,
 	.update		= tinydrm_display_pipe_update,
-	.prepare_fb	= tinydrm_display_pipe_prepare_fb,
+	.prepare_fb	= drm_gem_fb_simple_display_pipe_prepare_fb,
 };
 
 static const struct drm_display_mode jd_t18003_t01_mode = {
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 7c2485fe88d8..ea4d59eb8966 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 98e06f8bf23b..5d8688e522d1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
@@ -1175,7 +1176,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	reservation_object_init(&bo->ttm_resv);
 	atomic_inc(&bo->bdev->glob->bo_count);
 	drm_vma_node_reset(&bo->vma_node);
-	bo->priority = 0;
 
 	/*
 	 * For ttm_bo_type_device buffers, allocate
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index a7c232dc39cb..18d3debcc949 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2007-2010 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 2ebbae6067ab..f2c167702eef 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2007-2009 VMware, Inc., Palo Alto, CA., USA
@@ -39,6 +40,11 @@
 #include <linux/module.h>
 #include <linux/reservation.h>
 
+struct ttm_transfer_obj {
+	struct ttm_buffer_object base;
+	struct ttm_buffer_object *bo;
+};
+
 void ttm_bo_free_old_node(struct ttm_buffer_object *bo)
 {
 	ttm_bo_mem_put(bo, &bo->mem);
@@ -454,7 +460,11 @@ EXPORT_SYMBOL(ttm_bo_move_memcpy);
 
 static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
 {
-	kfree(bo);
+	struct ttm_transfer_obj *fbo;
+
+	fbo = container_of(bo, struct ttm_transfer_obj, base);
+	ttm_bo_unref(&fbo->bo);
+	kfree(fbo);
 }
 
 /**
@@ -475,14 +485,15 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
 static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 				      struct ttm_buffer_object **new_obj)
 {
-	struct ttm_buffer_object *fbo;
+	struct ttm_transfer_obj *fbo;
 	int ret;
 
 	fbo = kmalloc(sizeof(*fbo), GFP_KERNEL);
 	if (!fbo)
 		return -ENOMEM;
 
-	*fbo = *bo;
+	fbo->base = *bo;
+	fbo->bo = ttm_bo_reference(bo);
 
 	/**
 	 * Fix up members that we shouldn't copy directly:
@@ -490,25 +501,25 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	 */
 
 	atomic_inc(&bo->bdev->glob->bo_count);
-	INIT_LIST_HEAD(&fbo->ddestroy);
-	INIT_LIST_HEAD(&fbo->lru);
-	INIT_LIST_HEAD(&fbo->swap);
-	INIT_LIST_HEAD(&fbo->io_reserve_lru);
-	mutex_init(&fbo->wu_mutex);
-	fbo->moving = NULL;
-	drm_vma_node_reset(&fbo->vma_node);
-	atomic_set(&fbo->cpu_writers, 0);
-
-	kref_init(&fbo->list_kref);
-	kref_init(&fbo->kref);
-	fbo->destroy = &ttm_transfered_destroy;
-	fbo->acc_size = 0;
-	fbo->resv = &fbo->ttm_resv;
-	reservation_object_init(fbo->resv);
-	ret = reservation_object_trylock(fbo->resv);
+	INIT_LIST_HEAD(&fbo->base.ddestroy);
+	INIT_LIST_HEAD(&fbo->base.lru);
+	INIT_LIST_HEAD(&fbo->base.swap);
+	INIT_LIST_HEAD(&fbo->base.io_reserve_lru);
+	mutex_init(&fbo->base.wu_mutex);
+	fbo->base.moving = NULL;
+	drm_vma_node_reset(&fbo->base.vma_node);
+	atomic_set(&fbo->base.cpu_writers, 0);
+
+	kref_init(&fbo->base.list_kref);
+	kref_init(&fbo->base.kref);
+	fbo->base.destroy = &ttm_transfered_destroy;
+	fbo->base.acc_size = 0;
+	fbo->base.resv = &fbo->base.ttm_resv;
+	reservation_object_init(fbo->base.resv);
+	ret = reservation_object_trylock(fbo->base.resv);
 	WARN_ON(!ret);
 
-	*new_obj = fbo;
+	*new_obj = &fbo->base;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 8eba95b3c737..c7ece7613a6a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 3dca206e85f7..e73ae0d22897 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/ttm/ttm_lock.c b/drivers/gpu/drm/ttm/ttm_lock.c
index 913f4318cdc0..20694b8a01ca 100644
--- a/drivers/gpu/drm/ttm/ttm_lock.c
+++ b/drivers/gpu/drm/ttm/ttm_lock.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2007-2009 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index 27856c55dc84..450387c92b63 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c
index 66fc6395eb54..6ff40c041d79 100644
--- a/drivers/gpu/drm/ttm/ttm_module.c
+++ b/drivers/gpu/drm/ttm/ttm_module.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index 1aa2baa83959..74f1b1eb1f8e 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2009-2013 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index f0481b7b60c5..06c94e3a5f15 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -910,7 +910,8 @@ static int ttm_get_pages(struct page **pages, unsigned npages, int flags,
 			while (npages >= HPAGE_PMD_NR) {
 				gfp_t huge_flags = gfp_flags;
 
-				huge_flags |= GFP_TRANSHUGE;
+				huge_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+					__GFP_KSWAPD_RECLAIM;
 				huge_flags &= ~__GFP_MOVABLE;
 				huge_flags &= ~__GFP_COMP;
 				p = alloc_pages(huge_flags, HPAGE_PMD_ORDER);
@@ -1027,11 +1028,15 @@ int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages)
 				  GFP_USER | GFP_DMA32, "uc dma", 0);
 
 	ttm_page_pool_init_locked(&_manager->wc_pool_huge,
-				  GFP_TRANSHUGE	& ~(__GFP_MOVABLE | __GFP_COMP),
+				  (GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+				   __GFP_KSWAPD_RECLAIM) &
+				  ~(__GFP_MOVABLE | __GFP_COMP),
 				  "wc huge", order);
 
 	ttm_page_pool_init_locked(&_manager->uc_pool_huge,
-				  GFP_TRANSHUGE	& ~(__GFP_MOVABLE | __GFP_COMP)
+				  (GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+				   __GFP_KSWAPD_RECLAIM) &
+				  ~(__GFP_MOVABLE | __GFP_COMP)
 				  , "uc huge", order);
 
 	_manager->options.max_size = max_pages;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 8a25d1974385..f63d99c302e4 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -910,7 +910,8 @@ static gfp_t ttm_dma_pool_gfp_flags(struct ttm_dma_tt *ttm_dma, bool huge)
 		gfp_flags |= __GFP_ZERO;
 
 	if (huge) {
-		gfp_flags |= GFP_TRANSHUGE;
+		gfp_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+			__GFP_KSWAPD_RECLAIM;
 		gfp_flags &= ~__GFP_MOVABLE;
 		gfp_flags &= ~__GFP_COMP;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 7e672be987b5..a1e543972ca7 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c
index db397fcb345a..e8723a2412a6 100644
--- a/drivers/gpu/drm/tve200/tve200_display.c
+++ b/drivers/gpu/drm/tve200/tve200_display.c
@@ -120,7 +120,8 @@ static int tve200_display_check(struct drm_simple_display_pipe *pipe,
 }
 
 static void tve200_display_enable(struct drm_simple_display_pipe *pipe,
-				 struct drm_crtc_state *cstate)
+				 struct drm_crtc_state *cstate,
+				 struct drm_plane_state *plane_state)
 {
 	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_plane *plane = &pipe->plane;
@@ -292,18 +293,12 @@ static void tve200_display_disable_vblank(struct drm_simple_display_pipe *pipe)
 	writel(0, priv->regs + TVE200_INT_EN);
 }
 
-static int tve200_display_prepare_fb(struct drm_simple_display_pipe *pipe,
-				    struct drm_plane_state *plane_state)
-{
-	return drm_gem_fb_prepare_fb(&pipe->plane, plane_state);
-}
-
 static const struct drm_simple_display_pipe_funcs tve200_display_funcs = {
 	.check = tve200_display_check,
 	.enable = tve200_display_enable,
 	.disable = tve200_display_disable,
 	.update = tve200_display_update,
-	.prepare_fb = tve200_display_prepare_fb,
+	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
 	.enable_vblank = tve200_display_enable_vblank,
 	.disable_vblank = tve200_display_disable_vblank,
 };
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index c3dc1fd20cb4..09dc585aa46f 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -105,7 +105,7 @@ static int udl_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static int udl_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status udl_mode_valid(struct drm_connector *connector,
 			  struct drm_display_mode *mode)
 {
 	struct udl_device *udl = connector->dev->dev_private;
diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c
index 2867ed155ff6..0a20695eb120 100644
--- a/drivers/gpu/drm/udl/udl_dmabuf.c
+++ b/drivers/gpu/drm/udl/udl_dmabuf.c
@@ -76,6 +76,7 @@ static struct sg_table *udl_map_dma_buf(struct dma_buf_attachment *attach,
 	struct udl_drm_dmabuf_attachment *udl_attach = attach->priv;
 	struct udl_gem_object *obj = to_udl_bo(attach->dmabuf->priv);
 	struct drm_device *dev = obj->base.dev;
+	struct udl_device *udl = dev->dev_private;
 	struct scatterlist *rd, *wr;
 	struct sg_table *sgt = NULL;
 	unsigned int i;
@@ -112,7 +113,7 @@ static struct sg_table *udl_map_dma_buf(struct dma_buf_attachment *attach,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&udl->gem_lock);
 
 	rd = obj->sg->sgl;
 	wr = sgt->sgl;
@@ -137,7 +138,7 @@ static struct sg_table *udl_map_dma_buf(struct dma_buf_attachment *attach,
 	attach->priv = udl_attach;
 
 err_unlock:
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&udl->gem_lock);
 	return sgt;
 }
 
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 3c45a3064726..9ef515df724b 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -53,7 +53,7 @@ static struct drm_driver driver = {
 	.unload = udl_driver_unload,
 
 	/* gem hooks */
-	.gem_free_object = udl_gem_free_object,
+	.gem_free_object_unlocked = udl_gem_free_object,
 	.gem_vm_ops = &udl_gem_vm_ops,
 
 	.dumb_create = udl_dumb_create,
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 2a75ab80527a..55c0cc309198 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -54,6 +54,8 @@ struct udl_device {
 	struct usb_device *udev;
 	struct drm_crtc *crtc;
 
+	struct mutex gem_lock;
+
 	int sku_pixel_limit;
 
 	struct urb_list urbs;
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index dee6bd9a3dd1..9a15cce22cce 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -214,9 +214,10 @@ int udl_gem_mmap(struct drm_file *file, struct drm_device *dev,
 {
 	struct udl_gem_object *gobj;
 	struct drm_gem_object *obj;
+	struct udl_device *udl = dev->dev_private;
 	int ret = 0;
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&udl->gem_lock);
 	obj = drm_gem_object_lookup(file, handle);
 	if (obj == NULL) {
 		ret = -ENOENT;
@@ -236,6 +237,6 @@ int udl_gem_mmap(struct drm_file *file, struct drm_device *dev,
 out:
 	drm_gem_object_put(&gobj->base);
 unlock:
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&udl->gem_lock);
 	return ret;
 }
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index f1ec4528a73e..d518de8f496b 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -324,6 +324,8 @@ int udl_driver_load(struct drm_device *dev, unsigned long flags)
 	udl->ddev = dev;
 	dev->dev_private = udl;
 
+	mutex_init(&udl->gem_lock);
+
 	if (!udl_parse_vendor_descriptor(dev, udl->udev)) {
 		ret = -ENODEV;
 		DRM_ERROR("firmware not recognized. Assume incompatible device\n");
diff --git a/drivers/gpu/drm/v3d/Kconfig b/drivers/gpu/drm/v3d/Kconfig
new file mode 100644
index 000000000000..a0c0259355bd
--- /dev/null
+++ b/drivers/gpu/drm/v3d/Kconfig
@@ -0,0 +1,9 @@
+config DRM_V3D
+	tristate "Broadcom V3D 3.x and newer"
+	depends on ARCH_BCM || ARCH_BCMSTB || COMPILE_TEST
+	depends on DRM
+	depends on COMMON_CLK
+	select DRM_SCHED
+	help
+	  Choose this option if you have a system that has a Broadcom
+	  V3D 3.x or newer GPU, such as BCM7268.
diff --git a/drivers/gpu/drm/v3d/Makefile b/drivers/gpu/drm/v3d/Makefile
new file mode 100644
index 000000000000..34446e1de64f
--- /dev/null
+++ b/drivers/gpu/drm/v3d/Makefile
@@ -0,0 +1,18 @@
+# Please keep these build lists sorted!
+
+# core driver code
+v3d-y := \
+	v3d_bo.o \
+	v3d_drv.o \
+	v3d_fence.o \
+	v3d_gem.o \
+	v3d_irq.o \
+	v3d_mmu.o \
+	v3d_trace_points.o \
+	v3d_sched.o
+
+v3d-$(CONFIG_DEBUG_FS) += v3d_debugfs.o
+
+obj-$(CONFIG_DRM_V3D)  += v3d.o
+
+CFLAGS_v3d_trace_points.o := -I$(src)
diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
new file mode 100644
index 000000000000..7b1e2a549a71
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2015-2018 Broadcom */
+
+/**
+ * DOC: V3D GEM BO management support
+ *
+ * Compared to VC4 (V3D 2.x), V3D 3.3 introduces an MMU between the
+ * GPU and the bus, allowing us to use shmem objects for our storage
+ * instead of CMA.
+ *
+ * Physically contiguous objects may still be imported to V3D, but the
+ * driver doesn't allocate physically contiguous objects on its own.
+ * Display engines requiring physically contiguous allocations should
+ * look into Mesa's "renderonly" support (as used by the Mesa pl111
+ * driver) for an example of how to integrate with V3D.
+ *
+ * Long term, we should support evicting pages from the MMU when under
+ * memory pressure (thus the v3d_bo_get_pages() refcounting), but
+ * that's not a high priority since our systems tend to not have swap.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/pfn_t.h>
+
+#include "v3d_drv.h"
+#include "uapi/drm/v3d_drm.h"
+
+/* Pins the shmem pages, fills in the .pages and .sgt fields of the BO, and maps
+ * it for DMA.
+ */
+static int
+v3d_bo_get_pages(struct v3d_bo *bo)
+{
+	struct drm_gem_object *obj = &bo->base;
+	struct drm_device *dev = obj->dev;
+	int npages = obj->size >> PAGE_SHIFT;
+	int ret = 0;
+
+	mutex_lock(&bo->lock);
+	if (bo->pages_refcount++ != 0)
+		goto unlock;
+
+	if (!obj->import_attach) {
+		bo->pages = drm_gem_get_pages(obj);
+		if (IS_ERR(bo->pages)) {
+			ret = PTR_ERR(bo->pages);
+			goto unlock;
+		}
+
+		bo->sgt = drm_prime_pages_to_sg(bo->pages, npages);
+		if (IS_ERR(bo->sgt)) {
+			ret = PTR_ERR(bo->sgt);
+			goto put_pages;
+		}
+
+		/* Map the pages for use by the GPU. */
+		dma_map_sg(dev->dev, bo->sgt->sgl,
+			   bo->sgt->nents, DMA_BIDIRECTIONAL);
+	} else {
+		bo->pages = kcalloc(npages, sizeof(*bo->pages), GFP_KERNEL);
+		if (!bo->pages)
+			goto put_pages;
+
+		drm_prime_sg_to_page_addr_arrays(bo->sgt, bo->pages,
+						 NULL, npages);
+
+		/* Note that dma-bufs come in mapped. */
+	}
+
+	mutex_unlock(&bo->lock);
+
+	return 0;
+
+put_pages:
+	drm_gem_put_pages(obj, bo->pages, true, true);
+	bo->pages = NULL;
+unlock:
+	bo->pages_refcount--;
+	mutex_unlock(&bo->lock);
+	return ret;
+}
+
+static void
+v3d_bo_put_pages(struct v3d_bo *bo)
+{
+	struct drm_gem_object *obj = &bo->base;
+
+	mutex_lock(&bo->lock);
+	if (--bo->pages_refcount == 0) {
+		if (!obj->import_attach) {
+			dma_unmap_sg(obj->dev->dev, bo->sgt->sgl,
+				     bo->sgt->nents, DMA_BIDIRECTIONAL);
+			sg_free_table(bo->sgt);
+			kfree(bo->sgt);
+			drm_gem_put_pages(obj, bo->pages, true, true);
+		} else {
+			kfree(bo->pages);
+		}
+	}
+	mutex_unlock(&bo->lock);
+}
+
+static struct v3d_bo *v3d_bo_create_struct(struct drm_device *dev,
+					   size_t unaligned_size)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct drm_gem_object *obj;
+	struct v3d_bo *bo;
+	size_t size = roundup(unaligned_size, PAGE_SIZE);
+	int ret;
+
+	if (size == 0)
+		return ERR_PTR(-EINVAL);
+
+	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
+	if (!bo)
+		return ERR_PTR(-ENOMEM);
+	obj = &bo->base;
+
+	INIT_LIST_HEAD(&bo->vmas);
+	INIT_LIST_HEAD(&bo->unref_head);
+	mutex_init(&bo->lock);
+
+	ret = drm_gem_object_init(dev, obj, size);
+	if (ret)
+		goto free_bo;
+
+	spin_lock(&v3d->mm_lock);
+	ret = drm_mm_insert_node_generic(&v3d->mm, &bo->node,
+					 obj->size >> PAGE_SHIFT,
+					 GMP_GRANULARITY >> PAGE_SHIFT, 0, 0);
+	spin_unlock(&v3d->mm_lock);
+	if (ret)
+		goto free_obj;
+
+	return bo;
+
+free_obj:
+	drm_gem_object_release(obj);
+free_bo:
+	kfree(bo);
+	return ERR_PTR(ret);
+}
+
+struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
+			     size_t unaligned_size)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct drm_gem_object *obj;
+	struct v3d_bo *bo;
+	int ret;
+
+	bo = v3d_bo_create_struct(dev, unaligned_size);
+	if (IS_ERR(bo))
+		return bo;
+	obj = &bo->base;
+
+	bo->resv = &bo->_resv;
+	reservation_object_init(bo->resv);
+
+	ret = v3d_bo_get_pages(bo);
+	if (ret)
+		goto free_mm;
+
+	v3d_mmu_insert_ptes(bo);
+
+	mutex_lock(&v3d->bo_lock);
+	v3d->bo_stats.num_allocated++;
+	v3d->bo_stats.pages_allocated += obj->size >> PAGE_SHIFT;
+	mutex_unlock(&v3d->bo_lock);
+
+	return bo;
+
+free_mm:
+	spin_lock(&v3d->mm_lock);
+	drm_mm_remove_node(&bo->node);
+	spin_unlock(&v3d->mm_lock);
+
+	drm_gem_object_release(obj);
+	kfree(bo);
+	return ERR_PTR(ret);
+}
+
+/* Called DRM core on the last userspace/kernel unreference of the
+ * BO.
+ */
+void v3d_free_object(struct drm_gem_object *obj)
+{
+	struct v3d_dev *v3d = to_v3d_dev(obj->dev);
+	struct v3d_bo *bo = to_v3d_bo(obj);
+
+	mutex_lock(&v3d->bo_lock);
+	v3d->bo_stats.num_allocated--;
+	v3d->bo_stats.pages_allocated -= obj->size >> PAGE_SHIFT;
+	mutex_unlock(&v3d->bo_lock);
+
+	reservation_object_fini(&bo->_resv);
+
+	v3d_bo_put_pages(bo);
+
+	if (obj->import_attach)
+		drm_prime_gem_destroy(obj, bo->sgt);
+
+	v3d_mmu_remove_ptes(bo);
+	spin_lock(&v3d->mm_lock);
+	drm_mm_remove_node(&bo->node);
+	spin_unlock(&v3d->mm_lock);
+
+	mutex_destroy(&bo->lock);
+
+	drm_gem_object_release(obj);
+	kfree(bo);
+}
+
+struct reservation_object *v3d_prime_res_obj(struct drm_gem_object *obj)
+{
+	struct v3d_bo *bo = to_v3d_bo(obj);
+
+	return bo->resv;
+}
+
+static void
+v3d_set_mmap_vma_flags(struct vm_area_struct *vma)
+{
+	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
+	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+}
+
+int v3d_gem_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct drm_gem_object *obj = vma->vm_private_data;
+	struct v3d_bo *bo = to_v3d_bo(obj);
+	unsigned long pfn;
+	pgoff_t pgoff;
+	int ret;
+
+	/* We don't use vmf->pgoff since that has the fake offset: */
+	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
+	pfn = page_to_pfn(bo->pages[pgoff]);
+
+	ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
+
+	switch (ret) {
+	case -EAGAIN:
+	case 0:
+	case -ERESTARTSYS:
+	case -EINTR:
+	case -EBUSY:
+		/*
+		 * EBUSY is ok: this just means that another thread
+		 * already did the job.
+		 */
+		return VM_FAULT_NOPAGE;
+	case -ENOMEM:
+		return VM_FAULT_OOM;
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+}
+
+int v3d_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	int ret;
+
+	ret = drm_gem_mmap(filp, vma);
+	if (ret)
+		return ret;
+
+	v3d_set_mmap_vma_flags(vma);
+
+	return ret;
+}
+
+int v3d_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+{
+	int ret;
+
+	ret = drm_gem_mmap_obj(obj, obj->size, vma);
+	if (ret < 0)
+		return ret;
+
+	v3d_set_mmap_vma_flags(vma);
+
+	return 0;
+}
+
+struct sg_table *
+v3d_prime_get_sg_table(struct drm_gem_object *obj)
+{
+	struct v3d_bo *bo = to_v3d_bo(obj);
+	int npages = obj->size >> PAGE_SHIFT;
+
+	return drm_prime_pages_to_sg(bo->pages, npages);
+}
+
+struct drm_gem_object *
+v3d_prime_import_sg_table(struct drm_device *dev,
+			  struct dma_buf_attachment *attach,
+			  struct sg_table *sgt)
+{
+	struct drm_gem_object *obj;
+	struct v3d_bo *bo;
+
+	bo = v3d_bo_create_struct(dev, attach->dmabuf->size);
+	if (IS_ERR(bo))
+		return ERR_CAST(bo);
+	obj = &bo->base;
+
+	bo->resv = attach->dmabuf->resv;
+
+	bo->sgt = sgt;
+	v3d_bo_get_pages(bo);
+
+	v3d_mmu_insert_ptes(bo);
+
+	return obj;
+}
+
+int v3d_create_bo_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
+{
+	struct drm_v3d_create_bo *args = data;
+	struct v3d_bo *bo = NULL;
+	int ret;
+
+	if (args->flags != 0) {
+		DRM_INFO("unknown create_bo flags: %d\n", args->flags);
+		return -EINVAL;
+	}
+
+	bo = v3d_bo_create(dev, file_priv, PAGE_ALIGN(args->size));
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
+
+	args->offset = bo->node.start << PAGE_SHIFT;
+
+	ret = drm_gem_handle_create(file_priv, &bo->base, &args->handle);
+	drm_gem_object_put_unlocked(&bo->base);
+
+	return ret;
+}
+
+int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv)
+{
+	struct drm_v3d_mmap_bo *args = data;
+	struct drm_gem_object *gem_obj;
+	int ret;
+
+	if (args->flags != 0) {
+		DRM_INFO("unknown mmap_bo flags: %d\n", args->flags);
+		return -EINVAL;
+	}
+
+	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
+	if (!gem_obj) {
+		DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
+		return -ENOENT;
+	}
+
+	ret = drm_gem_create_mmap_offset(gem_obj);
+	if (ret == 0)
+		args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node);
+	drm_gem_object_put_unlocked(gem_obj);
+
+	return ret;
+}
+
+int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv)
+{
+	struct drm_v3d_get_bo_offset *args = data;
+	struct drm_gem_object *gem_obj;
+	struct v3d_bo *bo;
+
+	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
+	if (!gem_obj) {
+		DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
+		return -ENOENT;
+	}
+	bo = to_v3d_bo(gem_obj);
+
+	args->offset = bo->node.start << PAGE_SHIFT;
+
+	drm_gem_object_put_unlocked(gem_obj);
+	return 0;
+}
diff --git a/drivers/gpu/drm/v3d/v3d_debugfs.c b/drivers/gpu/drm/v3d/v3d_debugfs.c
new file mode 100644
index 000000000000..4db62c545748
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_debugfs.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2014-2018 Broadcom */
+
+#include <linux/circ_buf.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/pm_runtime.h>
+#include <linux/seq_file.h>
+#include <drm/drmP.h>
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define REGDEF(reg) { reg, #reg }
+struct v3d_reg_def {
+	u32 reg;
+	const char *name;
+};
+
+static const struct v3d_reg_def v3d_hub_reg_defs[] = {
+	REGDEF(V3D_HUB_AXICFG),
+	REGDEF(V3D_HUB_UIFCFG),
+	REGDEF(V3D_HUB_IDENT0),
+	REGDEF(V3D_HUB_IDENT1),
+	REGDEF(V3D_HUB_IDENT2),
+	REGDEF(V3D_HUB_IDENT3),
+	REGDEF(V3D_HUB_INT_STS),
+	REGDEF(V3D_HUB_INT_MSK_STS),
+};
+
+static const struct v3d_reg_def v3d_gca_reg_defs[] = {
+	REGDEF(V3D_GCA_SAFE_SHUTDOWN),
+	REGDEF(V3D_GCA_SAFE_SHUTDOWN_ACK),
+};
+
+static const struct v3d_reg_def v3d_core_reg_defs[] = {
+	REGDEF(V3D_CTL_IDENT0),
+	REGDEF(V3D_CTL_IDENT1),
+	REGDEF(V3D_CTL_IDENT2),
+	REGDEF(V3D_CTL_MISCCFG),
+	REGDEF(V3D_CTL_INT_STS),
+	REGDEF(V3D_CTL_INT_MSK_STS),
+	REGDEF(V3D_CLE_CT0CS),
+	REGDEF(V3D_CLE_CT0CA),
+	REGDEF(V3D_CLE_CT0EA),
+	REGDEF(V3D_CLE_CT1CS),
+	REGDEF(V3D_CLE_CT1CA),
+	REGDEF(V3D_CLE_CT1EA),
+
+	REGDEF(V3D_PTB_BPCA),
+	REGDEF(V3D_PTB_BPCS),
+
+	REGDEF(V3D_MMU_CTL),
+	REGDEF(V3D_MMU_VIO_ADDR),
+
+	REGDEF(V3D_GMP_STATUS),
+	REGDEF(V3D_GMP_CFG),
+	REGDEF(V3D_GMP_VIO_ADDR),
+};
+
+static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	int i, core;
+
+	for (i = 0; i < ARRAY_SIZE(v3d_hub_reg_defs); i++) {
+		seq_printf(m, "%s (0x%04x): 0x%08x\n",
+			   v3d_hub_reg_defs[i].name, v3d_hub_reg_defs[i].reg,
+			   V3D_READ(v3d_hub_reg_defs[i].reg));
+	}
+
+	for (i = 0; i < ARRAY_SIZE(v3d_gca_reg_defs); i++) {
+		seq_printf(m, "%s (0x%04x): 0x%08x\n",
+			   v3d_gca_reg_defs[i].name, v3d_gca_reg_defs[i].reg,
+			   V3D_GCA_READ(v3d_gca_reg_defs[i].reg));
+	}
+
+	for (core = 0; core < v3d->cores; core++) {
+		for (i = 0; i < ARRAY_SIZE(v3d_core_reg_defs); i++) {
+			seq_printf(m, "core %d %s (0x%04x): 0x%08x\n",
+				   core,
+				   v3d_core_reg_defs[i].name,
+				   v3d_core_reg_defs[i].reg,
+				   V3D_CORE_READ(core,
+						 v3d_core_reg_defs[i].reg));
+		}
+	}
+
+	return 0;
+}
+
+static int v3d_v3d_debugfs_ident(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	u32 ident0, ident1, ident2, ident3, cores;
+	int ret, core;
+
+	ret = pm_runtime_get_sync(v3d->dev);
+	if (ret < 0)
+		return ret;
+
+	ident0 = V3D_READ(V3D_HUB_IDENT0);
+	ident1 = V3D_READ(V3D_HUB_IDENT1);
+	ident2 = V3D_READ(V3D_HUB_IDENT2);
+	ident3 = V3D_READ(V3D_HUB_IDENT3);
+	cores = V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_NCORES);
+
+	seq_printf(m, "Revision:   %d.%d.%d.%d\n",
+		   V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_TVER),
+		   V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_REV),
+		   V3D_GET_FIELD(ident3, V3D_HUB_IDENT3_IPREV),
+		   V3D_GET_FIELD(ident3, V3D_HUB_IDENT3_IPIDX));
+	seq_printf(m, "MMU:        %s\n",
+		   (ident2 & V3D_HUB_IDENT2_WITH_MMU) ? "yes" : "no");
+	seq_printf(m, "TFU:        %s\n",
+		   (ident1 & V3D_HUB_IDENT1_WITH_TFU) ? "yes" : "no");
+	seq_printf(m, "TSY:        %s\n",
+		   (ident1 & V3D_HUB_IDENT1_WITH_TSY) ? "yes" : "no");
+	seq_printf(m, "MSO:        %s\n",
+		   (ident1 & V3D_HUB_IDENT1_WITH_MSO) ? "yes" : "no");
+	seq_printf(m, "L3C:        %s (%dkb)\n",
+		   (ident1 & V3D_HUB_IDENT1_WITH_L3C) ? "yes" : "no",
+		   V3D_GET_FIELD(ident2, V3D_HUB_IDENT2_L3C_NKB));
+
+	for (core = 0; core < cores; core++) {
+		u32 misccfg;
+		u32 nslc, ntmu, qups;
+
+		ident0 = V3D_CORE_READ(core, V3D_CTL_IDENT0);
+		ident1 = V3D_CORE_READ(core, V3D_CTL_IDENT1);
+		ident2 = V3D_CORE_READ(core, V3D_CTL_IDENT2);
+		misccfg = V3D_CORE_READ(core, V3D_CTL_MISCCFG);
+
+		nslc = V3D_GET_FIELD(ident1, V3D_IDENT1_NSLC);
+		ntmu = V3D_GET_FIELD(ident1, V3D_IDENT1_NTMU);
+		qups = V3D_GET_FIELD(ident1, V3D_IDENT1_QUPS);
+
+		seq_printf(m, "Core %d:\n", core);
+		seq_printf(m, "  Revision:     %d.%d\n",
+			   V3D_GET_FIELD(ident0, V3D_IDENT0_VER),
+			   V3D_GET_FIELD(ident1, V3D_IDENT1_REV));
+		seq_printf(m, "  Slices:       %d\n", nslc);
+		seq_printf(m, "  TMUs:         %d\n", nslc * ntmu);
+		seq_printf(m, "  QPUs:         %d\n", nslc * qups);
+		seq_printf(m, "  Semaphores:   %d\n",
+			   V3D_GET_FIELD(ident1, V3D_IDENT1_NSEM));
+		seq_printf(m, "  BCG int:      %d\n",
+			   (ident2 & V3D_IDENT2_BCG_INT) != 0);
+		seq_printf(m, "  Override TMU: %d\n",
+			   (misccfg & V3D_MISCCFG_OVRTMUOUT) != 0);
+	}
+
+	pm_runtime_mark_last_busy(v3d->dev);
+	pm_runtime_put_autosuspend(v3d->dev);
+
+	return 0;
+}
+
+static int v3d_debugfs_bo_stats(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+
+	mutex_lock(&v3d->bo_lock);
+	seq_printf(m, "allocated bos:          %d\n",
+		   v3d->bo_stats.num_allocated);
+	seq_printf(m, "allocated bo size (kb): %ld\n",
+		   (long)v3d->bo_stats.pages_allocated << (PAGE_SHIFT - 10));
+	mutex_unlock(&v3d->bo_lock);
+
+	return 0;
+}
+
+static const struct drm_info_list v3d_debugfs_list[] = {
+	{"v3d_ident", v3d_v3d_debugfs_ident, 0},
+	{"v3d_regs", v3d_v3d_debugfs_regs, 0},
+	{"bo_stats", v3d_debugfs_bo_stats, 0},
+};
+
+int
+v3d_debugfs_init(struct drm_minor *minor)
+{
+	return drm_debugfs_create_files(v3d_debugfs_list,
+					ARRAY_SIZE(v3d_debugfs_list),
+					minor->debugfs_root, minor);
+}
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
new file mode 100644
index 000000000000..cdb582043b4f
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2014-2018 Broadcom */
+
+/**
+ * DOC: Broadcom V3D Graphics Driver
+ *
+ * This driver supports the Broadcom V3D 3.3 and 4.1 OpenGL ES GPUs.
+ * For V3D 2.x support, see the VC4 driver.
+ *
+ * Currently only single-core rendering using the binner and renderer
+ * is supported.  The TFU (texture formatting unit) and V3D 4.x's CSD
+ * (compute shader dispatch) are not yet supported.
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_fb_helper.h>
+
+#include "uapi/drm/v3d_drm.h"
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define DRIVER_NAME "v3d"
+#define DRIVER_DESC "Broadcom V3D graphics"
+#define DRIVER_DATE "20180419"
+#define DRIVER_MAJOR 1
+#define DRIVER_MINOR 0
+#define DRIVER_PATCHLEVEL 0
+
+#ifdef CONFIG_PM
+static int v3d_runtime_suspend(struct device *dev)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct v3d_dev *v3d = to_v3d_dev(drm);
+
+	v3d_irq_disable(v3d);
+
+	clk_disable_unprepare(v3d->clk);
+
+	return 0;
+}
+
+static int v3d_runtime_resume(struct device *dev)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct v3d_dev *v3d = to_v3d_dev(drm);
+	int ret;
+
+	ret = clk_prepare_enable(v3d->clk);
+	if (ret != 0)
+		return ret;
+
+	/* XXX: VPM base */
+
+	v3d_mmu_set_page_table(v3d);
+	v3d_irq_enable(v3d);
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops v3d_v3d_pm_ops = {
+	SET_RUNTIME_PM_OPS(v3d_runtime_suspend, v3d_runtime_resume, NULL)
+};
+
+static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
+			       struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct drm_v3d_get_param *args = data;
+	int ret;
+	static const u32 reg_map[] = {
+		[DRM_V3D_PARAM_V3D_UIFCFG] = V3D_HUB_UIFCFG,
+		[DRM_V3D_PARAM_V3D_HUB_IDENT1] = V3D_HUB_IDENT1,
+		[DRM_V3D_PARAM_V3D_HUB_IDENT2] = V3D_HUB_IDENT2,
+		[DRM_V3D_PARAM_V3D_HUB_IDENT3] = V3D_HUB_IDENT3,
+		[DRM_V3D_PARAM_V3D_CORE0_IDENT0] = V3D_CTL_IDENT0,
+		[DRM_V3D_PARAM_V3D_CORE0_IDENT1] = V3D_CTL_IDENT1,
+		[DRM_V3D_PARAM_V3D_CORE0_IDENT2] = V3D_CTL_IDENT2,
+	};
+
+	if (args->pad != 0)
+		return -EINVAL;
+
+	/* Note that DRM_V3D_PARAM_V3D_CORE0_IDENT0 is 0, so we need
+	 * to explicitly allow it in the "the register in our
+	 * parameter map" check.
+	 */
+	if (args->param < ARRAY_SIZE(reg_map) &&
+	    (reg_map[args->param] ||
+	     args->param == DRM_V3D_PARAM_V3D_CORE0_IDENT0)) {
+		u32 offset = reg_map[args->param];
+
+		if (args->value != 0)
+			return -EINVAL;
+
+		ret = pm_runtime_get_sync(v3d->dev);
+		if (args->param >= DRM_V3D_PARAM_V3D_CORE0_IDENT0 &&
+		    args->param <= DRM_V3D_PARAM_V3D_CORE0_IDENT2) {
+			args->value = V3D_CORE_READ(0, offset);
+		} else {
+			args->value = V3D_READ(offset);
+		}
+		pm_runtime_mark_last_busy(v3d->dev);
+		pm_runtime_put_autosuspend(v3d->dev);
+		return 0;
+	}
+
+	/* Any params that aren't just register reads would go here. */
+
+	DRM_DEBUG("Unknown parameter %d\n", args->param);
+	return -EINVAL;
+}
+
+static int
+v3d_open(struct drm_device *dev, struct drm_file *file)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv;
+	int i;
+
+	v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL);
+	if (!v3d_priv)
+		return -ENOMEM;
+
+	v3d_priv->v3d = v3d;
+
+	for (i = 0; i < V3D_MAX_QUEUES; i++) {
+		drm_sched_entity_init(&v3d->queue[i].sched,
+				      &v3d_priv->sched_entity[i],
+				      &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL],
+				      NULL);
+	}
+
+	file->driver_priv = v3d_priv;
+
+	return 0;
+}
+
+static void
+v3d_postclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv = file->driver_priv;
+	enum v3d_queue q;
+
+	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+		drm_sched_entity_fini(&v3d->queue[q].sched,
+				      &v3d_priv->sched_entity[q]);
+	}
+
+	kfree(v3d_priv);
+}
+
+static const struct file_operations v3d_drm_fops = {
+	.owner = THIS_MODULE,
+	.open = drm_open,
+	.release = drm_release,
+	.unlocked_ioctl = drm_ioctl,
+	.mmap = v3d_mmap,
+	.poll = drm_poll,
+	.read = drm_read,
+	.compat_ioctl = drm_compat_ioctl,
+	.llseek = noop_llseek,
+};
+
+/* DRM_AUTH is required on SUBMIT_CL for now, while we don't have GMP
+ * protection between clients.  Note that render nodes would be be
+ * able to submit CLs that could access BOs from clients authenticated
+ * with the master node.
+ */
+static const struct drm_ioctl_desc v3d_drm_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CL, v3d_submit_cl_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(V3D_WAIT_BO, v3d_wait_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_CREATE_BO, v3d_create_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_MMAP_BO, v3d_mmap_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_GET_PARAM, v3d_get_param_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_GET_BO_OFFSET, v3d_get_bo_offset_ioctl, DRM_RENDER_ALLOW),
+};
+
+static const struct vm_operations_struct v3d_vm_ops = {
+	.fault = v3d_gem_fault,
+	.open = drm_gem_vm_open,
+	.close = drm_gem_vm_close,
+};
+
+static struct drm_driver v3d_drm_driver = {
+	.driver_features = (DRIVER_GEM |
+			    DRIVER_RENDER |
+			    DRIVER_PRIME |
+			    DRIVER_SYNCOBJ),
+
+	.open = v3d_open,
+	.postclose = v3d_postclose,
+
+#if defined(CONFIG_DEBUG_FS)
+	.debugfs_init = v3d_debugfs_init,
+#endif
+
+	.gem_free_object_unlocked = v3d_free_object,
+	.gem_vm_ops = &v3d_vm_ops,
+
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
+	.gem_prime_import = drm_gem_prime_import,
+	.gem_prime_export = drm_gem_prime_export,
+	.gem_prime_res_obj = v3d_prime_res_obj,
+	.gem_prime_get_sg_table	= v3d_prime_get_sg_table,
+	.gem_prime_import_sg_table = v3d_prime_import_sg_table,
+	.gem_prime_mmap = v3d_prime_mmap,
+
+	.ioctls = v3d_drm_ioctls,
+	.num_ioctls = ARRAY_SIZE(v3d_drm_ioctls),
+	.fops = &v3d_drm_fops,
+
+	.name = DRIVER_NAME,
+	.desc = DRIVER_DESC,
+	.date = DRIVER_DATE,
+	.major = DRIVER_MAJOR,
+	.minor = DRIVER_MINOR,
+	.patchlevel = DRIVER_PATCHLEVEL,
+};
+
+static const struct of_device_id v3d_of_match[] = {
+	{ .compatible = "brcm,7268-v3d" },
+	{ .compatible = "brcm,7278-v3d" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, v3d_of_match);
+
+static int
+map_regs(struct v3d_dev *v3d, void __iomem **regs, const char *name)
+{
+	struct resource *res =
+		platform_get_resource_byname(v3d->pdev, IORESOURCE_MEM, name);
+
+	*regs = devm_ioremap_resource(v3d->dev, res);
+	return PTR_ERR_OR_ZERO(*regs);
+}
+
+static int v3d_platform_drm_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct drm_device *drm;
+	struct v3d_dev *v3d;
+	int ret;
+	u32 ident1;
+
+	dev->coherent_dma_mask = DMA_BIT_MASK(36);
+
+	v3d = kzalloc(sizeof(*v3d), GFP_KERNEL);
+	if (!v3d)
+		return -ENOMEM;
+	v3d->dev = dev;
+	v3d->pdev = pdev;
+	drm = &v3d->drm;
+
+	ret = map_regs(v3d, &v3d->bridge_regs, "bridge");
+	if (ret)
+		goto dev_free;
+
+	ret = map_regs(v3d, &v3d->hub_regs, "hub");
+	if (ret)
+		goto dev_free;
+
+	ret = map_regs(v3d, &v3d->core_regs[0], "core0");
+	if (ret)
+		goto dev_free;
+
+	ident1 = V3D_READ(V3D_HUB_IDENT1);
+	v3d->ver = (V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_TVER) * 10 +
+		    V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_REV));
+	v3d->cores = V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_NCORES);
+	WARN_ON(v3d->cores > 1); /* multicore not yet implemented */
+
+	if (v3d->ver < 41) {
+		ret = map_regs(v3d, &v3d->gca_regs, "gca");
+		if (ret)
+			goto dev_free;
+	}
+
+	v3d->mmu_scratch = dma_alloc_wc(dev, 4096, &v3d->mmu_scratch_paddr,
+					GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+	if (!v3d->mmu_scratch) {
+		dev_err(dev, "Failed to allocate MMU scratch page\n");
+		ret = -ENOMEM;
+		goto dev_free;
+	}
+
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, 50);
+	pm_runtime_enable(dev);
+
+	ret = drm_dev_init(&v3d->drm, &v3d_drm_driver, dev);
+	if (ret)
+		goto dma_free;
+
+	platform_set_drvdata(pdev, drm);
+	drm->dev_private = v3d;
+
+	ret = v3d_gem_init(drm);
+	if (ret)
+		goto dev_destroy;
+
+	v3d_irq_init(v3d);
+
+	ret = drm_dev_register(drm, 0);
+	if (ret)
+		goto gem_destroy;
+
+	return 0;
+
+gem_destroy:
+	v3d_gem_destroy(drm);
+dev_destroy:
+	drm_dev_put(drm);
+dma_free:
+	dma_free_wc(dev, 4096, v3d->mmu_scratch, v3d->mmu_scratch_paddr);
+dev_free:
+	kfree(v3d);
+	return ret;
+}
+
+static int v3d_platform_drm_remove(struct platform_device *pdev)
+{
+	struct drm_device *drm = platform_get_drvdata(pdev);
+	struct v3d_dev *v3d = to_v3d_dev(drm);
+
+	drm_dev_unregister(drm);
+
+	v3d_gem_destroy(drm);
+
+	drm_dev_put(drm);
+
+	dma_free_wc(v3d->dev, 4096, v3d->mmu_scratch, v3d->mmu_scratch_paddr);
+
+	return 0;
+}
+
+static struct platform_driver v3d_platform_driver = {
+	.probe		= v3d_platform_drm_probe,
+	.remove		= v3d_platform_drm_remove,
+	.driver		= {
+		.name	= "v3d",
+		.of_match_table = v3d_of_match,
+	},
+};
+
+static int __init v3d_drm_register(void)
+{
+	return platform_driver_register(&v3d_platform_driver);
+}
+
+static void __exit v3d_drm_unregister(void)
+{
+	platform_driver_unregister(&v3d_platform_driver);
+}
+
+module_init(v3d_drm_register);
+module_exit(v3d_drm_unregister);
+
+MODULE_ALIAS("platform:v3d-drm");
+MODULE_DESCRIPTION("Broadcom V3D DRM Driver");
+MODULE_AUTHOR("Eric Anholt <eric@anholt.net>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
new file mode 100644
index 000000000000..a043ac3aae98
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2015-2018 Broadcom */
+
+#include <linux/reservation.h>
+#include <drm/drmP.h>
+#include <drm/drm_encoder.h>
+#include <drm/drm_gem.h>
+#include <drm/gpu_scheduler.h>
+
+#define GMP_GRANULARITY (128 * 1024)
+
+/* Enum for each of the V3D queues.  We maintain various queue
+ * tracking as an array because at some point we'll want to support
+ * the TFU (texture formatting unit) as another queue.
+ */
+enum v3d_queue {
+	V3D_BIN,
+	V3D_RENDER,
+};
+
+#define V3D_MAX_QUEUES (V3D_RENDER + 1)
+
+struct v3d_queue_state {
+	struct drm_gpu_scheduler sched;
+
+	u64 fence_context;
+	u64 emit_seqno;
+	u64 finished_seqno;
+};
+
+struct v3d_dev {
+	struct drm_device drm;
+
+	/* Short representation (e.g. 33, 41) of the V3D tech version
+	 * and revision.
+	 */
+	int ver;
+
+	struct device *dev;
+	struct platform_device *pdev;
+	void __iomem *hub_regs;
+	void __iomem *core_regs[3];
+	void __iomem *bridge_regs;
+	void __iomem *gca_regs;
+	struct clk *clk;
+
+	/* Virtual and DMA addresses of the single shared page table. */
+	volatile u32 *pt;
+	dma_addr_t pt_paddr;
+
+	/* Virtual and DMA addresses of the MMU's scratch page.  When
+	 * a read or write is invalid in the MMU, it will be
+	 * redirected here.
+	 */
+	void *mmu_scratch;
+	dma_addr_t mmu_scratch_paddr;
+
+	/* Number of V3D cores. */
+	u32 cores;
+
+	/* Allocator managing the address space.  All units are in
+	 * number of pages.
+	 */
+	struct drm_mm mm;
+	spinlock_t mm_lock;
+
+	struct work_struct overflow_mem_work;
+
+	struct v3d_exec_info *bin_job;
+	struct v3d_exec_info *render_job;
+
+	struct v3d_queue_state queue[V3D_MAX_QUEUES];
+
+	/* Spinlock used to synchronize the overflow memory
+	 * management against bin job submission.
+	 */
+	spinlock_t job_lock;
+
+	/* Protects bo_stats */
+	struct mutex bo_lock;
+
+	/* Lock taken when resetting the GPU, to keep multiple
+	 * processes from trying to park the scheduler threads and
+	 * reset at once.
+	 */
+	struct mutex reset_lock;
+
+	struct {
+		u32 num_allocated;
+		u32 pages_allocated;
+	} bo_stats;
+};
+
+static inline struct v3d_dev *
+to_v3d_dev(struct drm_device *dev)
+{
+	return (struct v3d_dev *)dev->dev_private;
+}
+
+/* The per-fd struct, which tracks the MMU mappings. */
+struct v3d_file_priv {
+	struct v3d_dev *v3d;
+
+	struct drm_sched_entity sched_entity[V3D_MAX_QUEUES];
+};
+
+/* Tracks a mapping of a BO into a per-fd address space */
+struct v3d_vma {
+	struct v3d_page_table *pt;
+	struct list_head list; /* entry in v3d_bo.vmas */
+};
+
+struct v3d_bo {
+	struct drm_gem_object base;
+
+	struct mutex lock;
+
+	struct drm_mm_node node;
+
+	u32 pages_refcount;
+	struct page **pages;
+	struct sg_table *sgt;
+	void *vaddr;
+
+	struct list_head vmas;    /* list of v3d_vma */
+
+	/* List entry for the BO's position in
+	 * v3d_exec_info->unref_list
+	 */
+	struct list_head unref_head;
+
+	/* normally (resv == &_resv) except for imported bo's */
+	struct reservation_object *resv;
+	struct reservation_object _resv;
+};
+
+static inline struct v3d_bo *
+to_v3d_bo(struct drm_gem_object *bo)
+{
+	return (struct v3d_bo *)bo;
+}
+
+struct v3d_fence {
+	struct dma_fence base;
+	struct drm_device *dev;
+	/* v3d seqno for signaled() test */
+	u64 seqno;
+	enum v3d_queue queue;
+};
+
+static inline struct v3d_fence *
+to_v3d_fence(struct dma_fence *fence)
+{
+	return (struct v3d_fence *)fence;
+}
+
+#define V3D_READ(offset) readl(v3d->hub_regs + offset)
+#define V3D_WRITE(offset, val) writel(val, v3d->hub_regs + offset)
+
+#define V3D_BRIDGE_READ(offset) readl(v3d->bridge_regs + offset)
+#define V3D_BRIDGE_WRITE(offset, val) writel(val, v3d->bridge_regs + offset)
+
+#define V3D_GCA_READ(offset) readl(v3d->gca_regs + offset)
+#define V3D_GCA_WRITE(offset, val) writel(val, v3d->gca_regs + offset)
+
+#define V3D_CORE_READ(core, offset) readl(v3d->core_regs[core] + offset)
+#define V3D_CORE_WRITE(core, offset, val) writel(val, v3d->core_regs[core] + offset)
+
+struct v3d_job {
+	struct drm_sched_job base;
+
+	struct v3d_exec_info *exec;
+
+	/* An optional fence userspace can pass in for the job to depend on. */
+	struct dma_fence *in_fence;
+
+	/* v3d fence to be signaled by IRQ handler when the job is complete. */
+	struct dma_fence *done_fence;
+
+	/* GPU virtual addresses of the start/end of the CL job. */
+	u32 start, end;
+};
+
+struct v3d_exec_info {
+	struct v3d_dev *v3d;
+
+	struct v3d_job bin, render;
+
+	/* Fence for when the scheduler considers the binner to be
+	 * done, for render to depend on.
+	 */
+	struct dma_fence *bin_done_fence;
+
+	struct kref refcount;
+
+	/* This is the array of BOs that were looked up at the start of exec. */
+	struct v3d_bo **bo;
+	u32 bo_count;
+
+	/* List of overflow BOs used in the job that need to be
+	 * released once the job is complete.
+	 */
+	struct list_head unref_list;
+
+	/* Submitted tile memory allocation start/size, tile state. */
+	u32 qma, qms, qts;
+};
+
+/**
+ * _wait_for - magic (register) wait macro
+ *
+ * Does the right thing for modeset paths when run under kdgb or similar atomic
+ * contexts. Note that it's important that we check the condition again after
+ * having timed out, since the timeout could be due to preemption or similar and
+ * we've never had a chance to check the condition before the timeout.
+ */
+#define wait_for(COND, MS) ({ \
+	unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1;	\
+	int ret__ = 0;							\
+	while (!(COND)) {						\
+		if (time_after(jiffies, timeout__)) {			\
+			if (!(COND))					\
+				ret__ = -ETIMEDOUT;			\
+			break;						\
+		}							\
+		msleep(1);					\
+	}								\
+	ret__;								\
+})
+
+static inline unsigned long nsecs_to_jiffies_timeout(const u64 n)
+{
+	/* nsecs_to_jiffies64() does not guard against overflow */
+	if (NSEC_PER_SEC % HZ &&
+	    div_u64(n, NSEC_PER_SEC) >= MAX_JIFFY_OFFSET / HZ)
+		return MAX_JIFFY_OFFSET;
+
+	return min_t(u64, MAX_JIFFY_OFFSET, nsecs_to_jiffies64(n) + 1);
+}
+
+/* v3d_bo.c */
+void v3d_free_object(struct drm_gem_object *gem_obj);
+struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
+			     size_t size);
+int v3d_create_bo_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv);
+int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv);
+int v3d_gem_fault(struct vm_fault *vmf);
+int v3d_mmap(struct file *filp, struct vm_area_struct *vma);
+struct reservation_object *v3d_prime_res_obj(struct drm_gem_object *obj);
+int v3d_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
+struct sg_table *v3d_prime_get_sg_table(struct drm_gem_object *obj);
+struct drm_gem_object *v3d_prime_import_sg_table(struct drm_device *dev,
+						 struct dma_buf_attachment *attach,
+						 struct sg_table *sgt);
+
+/* v3d_debugfs.c */
+int v3d_debugfs_init(struct drm_minor *minor);
+
+/* v3d_fence.c */
+extern const struct dma_fence_ops v3d_fence_ops;
+struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue);
+
+/* v3d_gem.c */
+int v3d_gem_init(struct drm_device *dev);
+void v3d_gem_destroy(struct drm_device *dev);
+int v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv);
+void v3d_exec_put(struct v3d_exec_info *exec);
+void v3d_reset(struct v3d_dev *v3d);
+void v3d_invalidate_caches(struct v3d_dev *v3d);
+void v3d_flush_caches(struct v3d_dev *v3d);
+
+/* v3d_irq.c */
+void v3d_irq_init(struct v3d_dev *v3d);
+void v3d_irq_enable(struct v3d_dev *v3d);
+void v3d_irq_disable(struct v3d_dev *v3d);
+void v3d_irq_reset(struct v3d_dev *v3d);
+
+/* v3d_mmu.c */
+int v3d_mmu_get_offset(struct drm_file *file_priv, struct v3d_bo *bo,
+		       u32 *offset);
+int v3d_mmu_set_page_table(struct v3d_dev *v3d);
+void v3d_mmu_insert_ptes(struct v3d_bo *bo);
+void v3d_mmu_remove_ptes(struct v3d_bo *bo);
+
+/* v3d_sched.c */
+int v3d_sched_init(struct v3d_dev *v3d);
+void v3d_sched_fini(struct v3d_dev *v3d);
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
new file mode 100644
index 000000000000..087d49c8cb12
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2017-2018 Broadcom */
+
+#include "v3d_drv.h"
+
+struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue)
+{
+	struct v3d_fence *fence;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return ERR_PTR(-ENOMEM);
+
+	fence->dev = &v3d->drm;
+	fence->queue = queue;
+	fence->seqno = ++v3d->queue[queue].emit_seqno;
+	dma_fence_init(&fence->base, &v3d_fence_ops, &v3d->job_lock,
+		       v3d->queue[queue].fence_context, fence->seqno);
+
+	return &fence->base;
+}
+
+static const char *v3d_fence_get_driver_name(struct dma_fence *fence)
+{
+	return "v3d";
+}
+
+static const char *v3d_fence_get_timeline_name(struct dma_fence *fence)
+{
+	struct v3d_fence *f = to_v3d_fence(fence);
+
+	if (f->queue == V3D_BIN)
+		return "v3d-bin";
+	else
+		return "v3d-render";
+}
+
+static bool v3d_fence_enable_signaling(struct dma_fence *fence)
+{
+	return true;
+}
+
+static bool v3d_fence_signaled(struct dma_fence *fence)
+{
+	struct v3d_fence *f = to_v3d_fence(fence);
+	struct v3d_dev *v3d = to_v3d_dev(f->dev);
+
+	return v3d->queue[f->queue].finished_seqno >= f->seqno;
+}
+
+const struct dma_fence_ops v3d_fence_ops = {
+	.get_driver_name = v3d_fence_get_driver_name,
+	.get_timeline_name = v3d_fence_get_timeline_name,
+	.enable_signaling = v3d_fence_enable_signaling,
+	.signaled = v3d_fence_signaled,
+	.wait = dma_fence_default_wait,
+	.release = dma_fence_free,
+};
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
new file mode 100644
index 000000000000..b513f9189caf
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -0,0 +1,668 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2014-2018 Broadcom */
+
+#include <drm/drmP.h>
+#include <drm/drm_syncobj.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/sched/signal.h>
+
+#include "uapi/drm/v3d_drm.h"
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+#include "v3d_trace.h"
+
+static void
+v3d_init_core(struct v3d_dev *v3d, int core)
+{
+	/* Set OVRTMUOUT, which means that the texture sampler uniform
+	 * configuration's tmu output type field is used, instead of
+	 * using the hardware default behavior based on the texture
+	 * type.  If you want the default behavior, you can still put
+	 * "2" in the indirect texture state's output_type field.
+	 */
+	V3D_CORE_WRITE(core, V3D_CTL_MISCCFG, V3D_MISCCFG_OVRTMUOUT);
+
+	/* Whenever we flush the L2T cache, we always want to flush
+	 * the whole thing.
+	 */
+	V3D_CORE_WRITE(core, V3D_CTL_L2TFLSTA, 0);
+	V3D_CORE_WRITE(core, V3D_CTL_L2TFLEND, ~0);
+}
+
+/* Sets invariant state for the HW. */
+static void
+v3d_init_hw_state(struct v3d_dev *v3d)
+{
+	v3d_init_core(v3d, 0);
+}
+
+static void
+v3d_idle_axi(struct v3d_dev *v3d, int core)
+{
+	V3D_CORE_WRITE(core, V3D_GMP_CFG, V3D_GMP_CFG_STOP_REQ);
+
+	if (wait_for((V3D_CORE_READ(core, V3D_GMP_STATUS) &
+		      (V3D_GMP_STATUS_RD_COUNT_MASK |
+		       V3D_GMP_STATUS_WR_COUNT_MASK |
+		       V3D_GMP_STATUS_CFG_BUSY)) == 0, 100)) {
+		DRM_ERROR("Failed to wait for safe GMP shutdown\n");
+	}
+}
+
+static void
+v3d_idle_gca(struct v3d_dev *v3d)
+{
+	if (v3d->ver >= 41)
+		return;
+
+	V3D_GCA_WRITE(V3D_GCA_SAFE_SHUTDOWN, V3D_GCA_SAFE_SHUTDOWN_EN);
+
+	if (wait_for((V3D_GCA_READ(V3D_GCA_SAFE_SHUTDOWN_ACK) &
+		      V3D_GCA_SAFE_SHUTDOWN_ACK_ACKED) ==
+		     V3D_GCA_SAFE_SHUTDOWN_ACK_ACKED, 100)) {
+		DRM_ERROR("Failed to wait for safe GCA shutdown\n");
+	}
+}
+
+static void
+v3d_reset_v3d(struct v3d_dev *v3d)
+{
+	int version = V3D_BRIDGE_READ(V3D_TOP_GR_BRIDGE_REVISION);
+
+	if (V3D_GET_FIELD(version, V3D_TOP_GR_BRIDGE_MAJOR) == 2) {
+		V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_0,
+				 V3D_TOP_GR_BRIDGE_SW_INIT_0_V3D_CLK_108_SW_INIT);
+		V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_0, 0);
+
+		/* GFXH-1383: The SW_INIT may cause a stray write to address 0
+		 * of the unit, so reset it to its power-on value here.
+		 */
+		V3D_WRITE(V3D_HUB_AXICFG, V3D_HUB_AXICFG_MAX_LEN_MASK);
+	} else {
+		WARN_ON_ONCE(V3D_GET_FIELD(version,
+					   V3D_TOP_GR_BRIDGE_MAJOR) != 7);
+		V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_1,
+				 V3D_TOP_GR_BRIDGE_SW_INIT_1_V3D_CLK_108_SW_INIT);
+		V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_1, 0);
+	}
+
+	v3d_init_hw_state(v3d);
+}
+
+void
+v3d_reset(struct v3d_dev *v3d)
+{
+	struct drm_device *dev = &v3d->drm;
+
+	DRM_ERROR("Resetting GPU.\n");
+	trace_v3d_reset_begin(dev);
+
+	/* XXX: only needed for safe powerdown, not reset. */
+	if (false)
+		v3d_idle_axi(v3d, 0);
+
+	v3d_idle_gca(v3d);
+	v3d_reset_v3d(v3d);
+
+	v3d_mmu_set_page_table(v3d);
+	v3d_irq_reset(v3d);
+
+	trace_v3d_reset_end(dev);
+}
+
+static void
+v3d_flush_l3(struct v3d_dev *v3d)
+{
+	if (v3d->ver < 41) {
+		u32 gca_ctrl = V3D_GCA_READ(V3D_GCA_CACHE_CTRL);
+
+		V3D_GCA_WRITE(V3D_GCA_CACHE_CTRL,
+			      gca_ctrl | V3D_GCA_CACHE_CTRL_FLUSH);
+
+		if (v3d->ver < 33) {
+			V3D_GCA_WRITE(V3D_GCA_CACHE_CTRL,
+				      gca_ctrl & ~V3D_GCA_CACHE_CTRL_FLUSH);
+		}
+	}
+}
+
+/* Invalidates the (read-only) L2 cache. */
+static void
+v3d_invalidate_l2(struct v3d_dev *v3d, int core)
+{
+	V3D_CORE_WRITE(core, V3D_CTL_L2CACTL,
+		       V3D_L2CACTL_L2CCLR |
+		       V3D_L2CACTL_L2CENA);
+}
+
+static void
+v3d_invalidate_l1td(struct v3d_dev *v3d, int core)
+{
+	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL, V3D_L2TCACTL_TMUWCF);
+	if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+		       V3D_L2TCACTL_L2TFLS), 100)) {
+		DRM_ERROR("Timeout waiting for L1T write combiner flush\n");
+	}
+}
+
+/* Invalidates texture L2 cachelines */
+static void
+v3d_flush_l2t(struct v3d_dev *v3d, int core)
+{
+	v3d_invalidate_l1td(v3d, core);
+
+	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL,
+		       V3D_L2TCACTL_L2TFLS |
+		       V3D_SET_FIELD(V3D_L2TCACTL_FLM_FLUSH, V3D_L2TCACTL_FLM));
+	if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+		       V3D_L2TCACTL_L2TFLS), 100)) {
+		DRM_ERROR("Timeout waiting for L2T flush\n");
+	}
+}
+
+/* Invalidates the slice caches.  These are read-only caches. */
+static void
+v3d_invalidate_slices(struct v3d_dev *v3d, int core)
+{
+	V3D_CORE_WRITE(core, V3D_CTL_SLCACTL,
+		       V3D_SET_FIELD(0xf, V3D_SLCACTL_TVCCS) |
+		       V3D_SET_FIELD(0xf, V3D_SLCACTL_TDCCS) |
+		       V3D_SET_FIELD(0xf, V3D_SLCACTL_UCC) |
+		       V3D_SET_FIELD(0xf, V3D_SLCACTL_ICC));
+}
+
+/* Invalidates texture L2 cachelines */
+static void
+v3d_invalidate_l2t(struct v3d_dev *v3d, int core)
+{
+	V3D_CORE_WRITE(core,
+		       V3D_CTL_L2TCACTL,
+		       V3D_L2TCACTL_L2TFLS |
+		       V3D_SET_FIELD(V3D_L2TCACTL_FLM_CLEAR, V3D_L2TCACTL_FLM));
+	if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+		       V3D_L2TCACTL_L2TFLS), 100)) {
+		DRM_ERROR("Timeout waiting for L2T invalidate\n");
+	}
+}
+
+void
+v3d_invalidate_caches(struct v3d_dev *v3d)
+{
+	v3d_flush_l3(v3d);
+
+	v3d_invalidate_l2(v3d, 0);
+	v3d_invalidate_slices(v3d, 0);
+	v3d_flush_l2t(v3d, 0);
+}
+
+void
+v3d_flush_caches(struct v3d_dev *v3d)
+{
+	v3d_invalidate_l1td(v3d, 0);
+	v3d_invalidate_l2t(v3d, 0);
+}
+
+static void
+v3d_attach_object_fences(struct v3d_exec_info *exec)
+{
+	struct dma_fence *out_fence = &exec->render.base.s_fence->finished;
+	struct v3d_bo *bo;
+	int i;
+
+	for (i = 0; i < exec->bo_count; i++) {
+		bo = to_v3d_bo(&exec->bo[i]->base);
+
+		/* XXX: Use shared fences for read-only objects. */
+		reservation_object_add_excl_fence(bo->resv, out_fence);
+	}
+}
+
+static void
+v3d_unlock_bo_reservations(struct drm_device *dev,
+			   struct v3d_exec_info *exec,
+			   struct ww_acquire_ctx *acquire_ctx)
+{
+	int i;
+
+	for (i = 0; i < exec->bo_count; i++) {
+		struct v3d_bo *bo = to_v3d_bo(&exec->bo[i]->base);
+
+		ww_mutex_unlock(&bo->resv->lock);
+	}
+
+	ww_acquire_fini(acquire_ctx);
+}
+
+/* Takes the reservation lock on all the BOs being referenced, so that
+ * at queue submit time we can update the reservations.
+ *
+ * We don't lock the RCL the tile alloc/state BOs, or overflow memory
+ * (all of which are on exec->unref_list).  They're entirely private
+ * to v3d, so we don't attach dma-buf fences to them.
+ */
+static int
+v3d_lock_bo_reservations(struct drm_device *dev,
+			 struct v3d_exec_info *exec,
+			 struct ww_acquire_ctx *acquire_ctx)
+{
+	int contended_lock = -1;
+	int i, ret;
+	struct v3d_bo *bo;
+
+	ww_acquire_init(acquire_ctx, &reservation_ww_class);
+
+retry:
+	if (contended_lock != -1) {
+		bo = to_v3d_bo(&exec->bo[contended_lock]->base);
+		ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
+						       acquire_ctx);
+		if (ret) {
+			ww_acquire_done(acquire_ctx);
+			return ret;
+		}
+	}
+
+	for (i = 0; i < exec->bo_count; i++) {
+		if (i == contended_lock)
+			continue;
+
+		bo = to_v3d_bo(&exec->bo[i]->base);
+
+		ret = ww_mutex_lock_interruptible(&bo->resv->lock, acquire_ctx);
+		if (ret) {
+			int j;
+
+			for (j = 0; j < i; j++) {
+				bo = to_v3d_bo(&exec->bo[j]->base);
+				ww_mutex_unlock(&bo->resv->lock);
+			}
+
+			if (contended_lock != -1 && contended_lock >= i) {
+				bo = to_v3d_bo(&exec->bo[contended_lock]->base);
+
+				ww_mutex_unlock(&bo->resv->lock);
+			}
+
+			if (ret == -EDEADLK) {
+				contended_lock = i;
+				goto retry;
+			}
+
+			ww_acquire_done(acquire_ctx);
+			return ret;
+		}
+	}
+
+	ww_acquire_done(acquire_ctx);
+
+	/* Reserve space for our shared (read-only) fence references,
+	 * before we commit the CL to the hardware.
+	 */
+	for (i = 0; i < exec->bo_count; i++) {
+		bo = to_v3d_bo(&exec->bo[i]->base);
+
+		ret = reservation_object_reserve_shared(bo->resv);
+		if (ret) {
+			v3d_unlock_bo_reservations(dev, exec, acquire_ctx);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * v3d_cl_lookup_bos() - Sets up exec->bo[] with the GEM objects
+ * referenced by the job.
+ * @dev: DRM device
+ * @file_priv: DRM file for this fd
+ * @exec: V3D job being set up
+ *
+ * The command validator needs to reference BOs by their index within
+ * the submitted job's BO list.  This does the validation of the job's
+ * BO list and reference counting for the lifetime of the job.
+ *
+ * Note that this function doesn't need to unreference the BOs on
+ * failure, because that will happen at v3d_exec_cleanup() time.
+ */
+static int
+v3d_cl_lookup_bos(struct drm_device *dev,
+		  struct drm_file *file_priv,
+		  struct drm_v3d_submit_cl *args,
+		  struct v3d_exec_info *exec)
+{
+	u32 *handles;
+	int ret = 0;
+	int i;
+
+	exec->bo_count = args->bo_handle_count;
+
+	if (!exec->bo_count) {
+		/* See comment on bo_index for why we have to check
+		 * this.
+		 */
+		DRM_DEBUG("Rendering requires BOs\n");
+		return -EINVAL;
+	}
+
+	exec->bo = kvmalloc_array(exec->bo_count,
+				  sizeof(struct drm_gem_cma_object *),
+				  GFP_KERNEL | __GFP_ZERO);
+	if (!exec->bo) {
+		DRM_DEBUG("Failed to allocate validated BO pointers\n");
+		return -ENOMEM;
+	}
+
+	handles = kvmalloc_array(exec->bo_count, sizeof(u32), GFP_KERNEL);
+	if (!handles) {
+		ret = -ENOMEM;
+		DRM_DEBUG("Failed to allocate incoming GEM handles\n");
+		goto fail;
+	}
+
+	if (copy_from_user(handles,
+			   (void __user *)(uintptr_t)args->bo_handles,
+			   exec->bo_count * sizeof(u32))) {
+		ret = -EFAULT;
+		DRM_DEBUG("Failed to copy in GEM handles\n");
+		goto fail;
+	}
+
+	spin_lock(&file_priv->table_lock);
+	for (i = 0; i < exec->bo_count; i++) {
+		struct drm_gem_object *bo = idr_find(&file_priv->object_idr,
+						     handles[i]);
+		if (!bo) {
+			DRM_DEBUG("Failed to look up GEM BO %d: %d\n",
+				  i, handles[i]);
+			ret = -ENOENT;
+			spin_unlock(&file_priv->table_lock);
+			goto fail;
+		}
+		drm_gem_object_get(bo);
+		exec->bo[i] = to_v3d_bo(bo);
+	}
+	spin_unlock(&file_priv->table_lock);
+
+fail:
+	kvfree(handles);
+	return ret;
+}
+
+static void
+v3d_exec_cleanup(struct kref *ref)
+{
+	struct v3d_exec_info *exec = container_of(ref, struct v3d_exec_info,
+						  refcount);
+	struct v3d_dev *v3d = exec->v3d;
+	unsigned int i;
+	struct v3d_bo *bo, *save;
+
+	dma_fence_put(exec->bin.in_fence);
+	dma_fence_put(exec->render.in_fence);
+
+	dma_fence_put(exec->bin.done_fence);
+	dma_fence_put(exec->render.done_fence);
+
+	dma_fence_put(exec->bin_done_fence);
+
+	for (i = 0; i < exec->bo_count; i++)
+		drm_gem_object_put_unlocked(&exec->bo[i]->base);
+	kvfree(exec->bo);
+
+	list_for_each_entry_safe(bo, save, &exec->unref_list, unref_head) {
+		drm_gem_object_put_unlocked(&bo->base);
+	}
+
+	pm_runtime_mark_last_busy(v3d->dev);
+	pm_runtime_put_autosuspend(v3d->dev);
+
+	kfree(exec);
+}
+
+void v3d_exec_put(struct v3d_exec_info *exec)
+{
+	kref_put(&exec->refcount, v3d_exec_cleanup);
+}
+
+int
+v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
+		  struct drm_file *file_priv)
+{
+	int ret;
+	struct drm_v3d_wait_bo *args = data;
+	struct drm_gem_object *gem_obj;
+	struct v3d_bo *bo;
+	ktime_t start = ktime_get();
+	u64 delta_ns;
+	unsigned long timeout_jiffies =
+		nsecs_to_jiffies_timeout(args->timeout_ns);
+
+	if (args->pad != 0)
+		return -EINVAL;
+
+	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
+	if (!gem_obj) {
+		DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
+		return -EINVAL;
+	}
+	bo = to_v3d_bo(gem_obj);
+
+	ret = reservation_object_wait_timeout_rcu(bo->resv,
+						  true, true,
+						  timeout_jiffies);
+
+	if (ret == 0)
+		ret = -ETIME;
+	else if (ret > 0)
+		ret = 0;
+
+	/* Decrement the user's timeout, in case we got interrupted
+	 * such that the ioctl will be restarted.
+	 */
+	delta_ns = ktime_to_ns(ktime_sub(ktime_get(), start));
+	if (delta_ns < args->timeout_ns)
+		args->timeout_ns -= delta_ns;
+	else
+		args->timeout_ns = 0;
+
+	/* Asked to wait beyond the jiffie/scheduler precision? */
+	if (ret == -ETIME && args->timeout_ns)
+		ret = -EAGAIN;
+
+	drm_gem_object_put_unlocked(gem_obj);
+
+	return ret;
+}
+
+/**
+ * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D.
+ * @dev: DRM device
+ * @data: ioctl argument
+ * @file_priv: DRM file for this fd
+ *
+ * This is the main entrypoint for userspace to submit a 3D frame to
+ * the GPU.  Userspace provides the binner command list (if
+ * applicable), and the kernel sets up the render command list to draw
+ * to the framebuffer described in the ioctl, using the command lists
+ * that the 3D engine's binner will produce.
+ */
+int
+v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_submit_cl *args = data;
+	struct v3d_exec_info *exec;
+	struct ww_acquire_ctx acquire_ctx;
+	struct drm_syncobj *sync_out;
+	int ret = 0;
+
+	if (args->pad != 0) {
+		DRM_INFO("pad must be zero: %d\n", args->pad);
+		return -EINVAL;
+	}
+
+	exec = kcalloc(1, sizeof(*exec), GFP_KERNEL);
+	if (!exec)
+		return -ENOMEM;
+
+	ret = pm_runtime_get_sync(v3d->dev);
+	if (ret < 0) {
+		kfree(exec);
+		return ret;
+	}
+
+	kref_init(&exec->refcount);
+
+	ret = drm_syncobj_find_fence(file_priv, args->in_sync_bcl,
+				     &exec->bin.in_fence);
+	if (ret == -EINVAL)
+		goto fail;
+
+	ret = drm_syncobj_find_fence(file_priv, args->in_sync_rcl,
+				     &exec->render.in_fence);
+	if (ret == -EINVAL)
+		goto fail;
+
+	exec->qma = args->qma;
+	exec->qms = args->qms;
+	exec->qts = args->qts;
+	exec->bin.exec = exec;
+	exec->bin.start = args->bcl_start;
+	exec->bin.end = args->bcl_end;
+	exec->render.exec = exec;
+	exec->render.start = args->rcl_start;
+	exec->render.end = args->rcl_end;
+	exec->v3d = v3d;
+	INIT_LIST_HEAD(&exec->unref_list);
+
+	ret = v3d_cl_lookup_bos(dev, file_priv, args, exec);
+	if (ret)
+		goto fail;
+
+	ret = v3d_lock_bo_reservations(dev, exec, &acquire_ctx);
+	if (ret)
+		goto fail;
+
+	if (exec->bin.start != exec->bin.end) {
+		ret = drm_sched_job_init(&exec->bin.base,
+					 &v3d->queue[V3D_BIN].sched,
+					 &v3d_priv->sched_entity[V3D_BIN],
+					 v3d_priv);
+		if (ret)
+			goto fail_unreserve;
+
+		exec->bin_done_fence =
+			dma_fence_get(&exec->bin.base.s_fence->finished);
+
+		kref_get(&exec->refcount); /* put by scheduler job completion */
+		drm_sched_entity_push_job(&exec->bin.base,
+					  &v3d_priv->sched_entity[V3D_BIN]);
+	}
+
+	ret = drm_sched_job_init(&exec->render.base,
+				 &v3d->queue[V3D_RENDER].sched,
+				 &v3d_priv->sched_entity[V3D_RENDER],
+				 v3d_priv);
+	if (ret)
+		goto fail_unreserve;
+
+	kref_get(&exec->refcount); /* put by scheduler job completion */
+	drm_sched_entity_push_job(&exec->render.base,
+				  &v3d_priv->sched_entity[V3D_RENDER]);
+
+	v3d_attach_object_fences(exec);
+
+	v3d_unlock_bo_reservations(dev, exec, &acquire_ctx);
+
+	/* Update the return sync object for the */
+	sync_out = drm_syncobj_find(file_priv, args->out_sync);
+	if (sync_out) {
+		drm_syncobj_replace_fence(sync_out,
+					  &exec->render.base.s_fence->finished);
+		drm_syncobj_put(sync_out);
+	}
+
+	v3d_exec_put(exec);
+
+	return 0;
+
+fail_unreserve:
+	v3d_unlock_bo_reservations(dev, exec, &acquire_ctx);
+fail:
+	v3d_exec_put(exec);
+
+	return ret;
+}
+
+int
+v3d_gem_init(struct drm_device *dev)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	u32 pt_size = 4096 * 1024;
+	int ret, i;
+
+	for (i = 0; i < V3D_MAX_QUEUES; i++)
+		v3d->queue[i].fence_context = dma_fence_context_alloc(1);
+
+	spin_lock_init(&v3d->mm_lock);
+	spin_lock_init(&v3d->job_lock);
+	mutex_init(&v3d->bo_lock);
+	mutex_init(&v3d->reset_lock);
+
+	/* Note: We don't allocate address 0.  Various bits of HW
+	 * treat 0 as special, such as the occlusion query counters
+	 * where 0 means "disabled".
+	 */
+	drm_mm_init(&v3d->mm, 1, pt_size / sizeof(u32) - 1);
+
+	v3d->pt = dma_alloc_wc(v3d->dev, pt_size,
+			       &v3d->pt_paddr,
+			       GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+	if (!v3d->pt) {
+		drm_mm_takedown(&v3d->mm);
+		dev_err(v3d->dev,
+			"Failed to allocate page tables. "
+			"Please ensure you have CMA enabled.\n");
+		return -ENOMEM;
+	}
+
+	v3d_init_hw_state(v3d);
+	v3d_mmu_set_page_table(v3d);
+
+	ret = v3d_sched_init(v3d);
+	if (ret) {
+		drm_mm_takedown(&v3d->mm);
+		dma_free_coherent(v3d->dev, 4096 * 1024, (void *)v3d->pt,
+				  v3d->pt_paddr);
+	}
+
+	return 0;
+}
+
+void
+v3d_gem_destroy(struct drm_device *dev)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	enum v3d_queue q;
+
+	v3d_sched_fini(v3d);
+
+	/* Waiting for exec to finish would need to be done before
+	 * unregistering V3D.
+	 */
+	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+		WARN_ON(v3d->queue[q].emit_seqno !=
+			v3d->queue[q].finished_seqno);
+	}
+
+	drm_mm_takedown(&v3d->mm);
+
+	dma_free_coherent(v3d->dev, 4096 * 1024, (void *)v3d->pt, v3d->pt_paddr);
+}
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
new file mode 100644
index 000000000000..77e1fa046c10
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2014-2018 Broadcom */
+
+/**
+ * DOC: Interrupt management for the V3D engine
+ *
+ * When we take a binning or rendering flush done interrupt, we need
+ * to signal the fence for that job so that the scheduler can queue up
+ * the next one and unblock any waiters.
+ *
+ * When we take the binner out of memory interrupt, we need to
+ * allocate some new memory and pass it to the binner so that the
+ * current job can make progress.
+ */
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define V3D_CORE_IRQS ((u32)(V3D_INT_OUTOMEM |	\
+			     V3D_INT_FLDONE |	\
+			     V3D_INT_FRDONE |	\
+			     V3D_INT_GMPV))
+
+#define V3D_HUB_IRQS ((u32)(V3D_HUB_INT_MMU_WRV |	\
+			    V3D_HUB_INT_MMU_PTI |	\
+			    V3D_HUB_INT_MMU_CAP))
+
+static void
+v3d_overflow_mem_work(struct work_struct *work)
+{
+	struct v3d_dev *v3d =
+		container_of(work, struct v3d_dev, overflow_mem_work);
+	struct drm_device *dev = &v3d->drm;
+	struct v3d_bo *bo = v3d_bo_create(dev, NULL /* XXX: GMP */, 256 * 1024);
+	unsigned long irqflags;
+
+	if (IS_ERR(bo)) {
+		DRM_ERROR("Couldn't allocate binner overflow mem\n");
+		return;
+	}
+
+	/* We lost a race, and our work task came in after the bin job
+	 * completed and exited.  This can happen because the HW
+	 * signals OOM before it's fully OOM, so the binner might just
+	 * barely complete.
+	 *
+	 * If we lose the race and our work task comes in after a new
+	 * bin job got scheduled, that's fine.  We'll just give them
+	 * some binner pool anyway.
+	 */
+	spin_lock_irqsave(&v3d->job_lock, irqflags);
+	if (!v3d->bin_job) {
+		spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+		goto out;
+	}
+
+	drm_gem_object_get(&bo->base);
+	list_add_tail(&bo->unref_head, &v3d->bin_job->unref_list);
+	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+
+	V3D_CORE_WRITE(0, V3D_PTB_BPOA, bo->node.start << PAGE_SHIFT);
+	V3D_CORE_WRITE(0, V3D_PTB_BPOS, bo->base.size);
+
+out:
+	drm_gem_object_put_unlocked(&bo->base);
+}
+
+static irqreturn_t
+v3d_irq(int irq, void *arg)
+{
+	struct v3d_dev *v3d = arg;
+	u32 intsts;
+	irqreturn_t status = IRQ_NONE;
+
+	intsts = V3D_CORE_READ(0, V3D_CTL_INT_STS);
+
+	/* Acknowledge the interrupts we're handling here. */
+	V3D_CORE_WRITE(0, V3D_CTL_INT_CLR, intsts);
+
+	if (intsts & V3D_INT_OUTOMEM) {
+		/* Note that the OOM status is edge signaled, so the
+		 * interrupt won't happen again until the we actually
+		 * add more memory.
+		 */
+		schedule_work(&v3d->overflow_mem_work);
+		status = IRQ_HANDLED;
+	}
+
+	if (intsts & V3D_INT_FLDONE) {
+		v3d->queue[V3D_BIN].finished_seqno++;
+		dma_fence_signal(v3d->bin_job->bin.done_fence);
+		status = IRQ_HANDLED;
+	}
+
+	if (intsts & V3D_INT_FRDONE) {
+		v3d->queue[V3D_RENDER].finished_seqno++;
+		dma_fence_signal(v3d->render_job->render.done_fence);
+
+		status = IRQ_HANDLED;
+	}
+
+	/* We shouldn't be triggering these if we have GMP in
+	 * always-allowed mode.
+	 */
+	if (intsts & V3D_INT_GMPV)
+		dev_err(v3d->dev, "GMP violation\n");
+
+	return status;
+}
+
+static irqreturn_t
+v3d_hub_irq(int irq, void *arg)
+{
+	struct v3d_dev *v3d = arg;
+	u32 intsts;
+	irqreturn_t status = IRQ_NONE;
+
+	intsts = V3D_READ(V3D_HUB_INT_STS);
+
+	/* Acknowledge the interrupts we're handling here. */
+	V3D_WRITE(V3D_HUB_INT_CLR, intsts);
+
+	if (intsts & (V3D_HUB_INT_MMU_WRV |
+		      V3D_HUB_INT_MMU_PTI |
+		      V3D_HUB_INT_MMU_CAP)) {
+		u32 axi_id = V3D_READ(V3D_MMU_VIO_ID);
+		u64 vio_addr = (u64)V3D_READ(V3D_MMU_VIO_ADDR) << 8;
+
+		dev_err(v3d->dev, "MMU error from client %d at 0x%08llx%s%s%s\n",
+			axi_id, (long long)vio_addr,
+			((intsts & V3D_HUB_INT_MMU_WRV) ?
+			 ", write violation" : ""),
+			((intsts & V3D_HUB_INT_MMU_PTI) ?
+			 ", pte invalid" : ""),
+			((intsts & V3D_HUB_INT_MMU_CAP) ?
+			 ", cap exceeded" : ""));
+		status = IRQ_HANDLED;
+	}
+
+	return status;
+}
+
+void
+v3d_irq_init(struct v3d_dev *v3d)
+{
+	int ret, core;
+
+	INIT_WORK(&v3d->overflow_mem_work, v3d_overflow_mem_work);
+
+	/* Clear any pending interrupts someone might have left around
+	 * for us.
+	 */
+	for (core = 0; core < v3d->cores; core++)
+		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS);
+	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS);
+
+	ret = devm_request_irq(v3d->dev, platform_get_irq(v3d->pdev, 0),
+			       v3d_hub_irq, IRQF_SHARED,
+			       "v3d_hub", v3d);
+	ret = devm_request_irq(v3d->dev, platform_get_irq(v3d->pdev, 1),
+			       v3d_irq, IRQF_SHARED,
+			       "v3d_core0", v3d);
+	if (ret)
+		dev_err(v3d->dev, "IRQ setup failed: %d\n", ret);
+
+	v3d_irq_enable(v3d);
+}
+
+void
+v3d_irq_enable(struct v3d_dev *v3d)
+{
+	int core;
+
+	/* Enable our set of interrupts, masking out any others. */
+	for (core = 0; core < v3d->cores; core++) {
+		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~V3D_CORE_IRQS);
+		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_CLR, V3D_CORE_IRQS);
+	}
+
+	V3D_WRITE(V3D_HUB_INT_MSK_SET, ~V3D_HUB_IRQS);
+	V3D_WRITE(V3D_HUB_INT_MSK_CLR, V3D_HUB_IRQS);
+}
+
+void
+v3d_irq_disable(struct v3d_dev *v3d)
+{
+	int core;
+
+	/* Disable all interrupts. */
+	for (core = 0; core < v3d->cores; core++)
+		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~0);
+	V3D_WRITE(V3D_HUB_INT_MSK_SET, ~0);
+
+	/* Clear any pending interrupts we might have left. */
+	for (core = 0; core < v3d->cores; core++)
+		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS);
+	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS);
+
+	cancel_work_sync(&v3d->overflow_mem_work);
+}
+
+/** Reinitializes interrupt registers when a GPU reset is performed. */
+void v3d_irq_reset(struct v3d_dev *v3d)
+{
+	v3d_irq_enable(v3d);
+}
diff --git a/drivers/gpu/drm/v3d/v3d_mmu.c b/drivers/gpu/drm/v3d/v3d_mmu.c
new file mode 100644
index 000000000000..b00f97c31b70
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_mmu.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2017-2018 Broadcom */
+
+/**
+ * DOC: Broadcom V3D MMU
+ *
+ * The V3D 3.x hardware (compared to VC4) now includes an MMU.  It has
+ * a single level of page tables for the V3D's 4GB address space to
+ * map to AXI bus addresses, thus it could need up to 4MB of
+ * physically contiguous memory to store the PTEs.
+ *
+ * Because the 4MB of contiguous memory for page tables is precious,
+ * and switching between them is expensive, we load all BOs into the
+ * same 4GB address space.
+ *
+ * To protect clients from each other, we should use the GMP to
+ * quickly mask out (at 128kb granularity) what pages are available to
+ * each client.  This is not yet implemented.
+ */
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define V3D_MMU_PAGE_SHIFT 12
+
+/* Note: All PTEs for the 1MB superpage must be filled with the
+ * superpage bit set.
+ */
+#define V3D_PTE_SUPERPAGE BIT(31)
+#define V3D_PTE_WRITEABLE BIT(29)
+#define V3D_PTE_VALID BIT(28)
+
+static int v3d_mmu_flush_all(struct v3d_dev *v3d)
+{
+	int ret;
+
+	/* Make sure that another flush isn't already running when we
+	 * start this one.
+	 */
+	ret = wait_for(!(V3D_READ(V3D_MMU_CTL) &
+			 V3D_MMU_CTL_TLB_CLEARING), 100);
+	if (ret)
+		dev_err(v3d->dev, "TLB clear wait idle pre-wait failed\n");
+
+	V3D_WRITE(V3D_MMU_CTL, V3D_READ(V3D_MMU_CTL) |
+		  V3D_MMU_CTL_TLB_CLEAR);
+
+	V3D_WRITE(V3D_MMUC_CONTROL,
+		  V3D_MMUC_CONTROL_FLUSH |
+		  V3D_MMUC_CONTROL_ENABLE);
+
+	ret = wait_for(!(V3D_READ(V3D_MMU_CTL) &
+			 V3D_MMU_CTL_TLB_CLEARING), 100);
+	if (ret) {
+		dev_err(v3d->dev, "TLB clear wait idle failed\n");
+		return ret;
+	}
+
+	ret = wait_for(!(V3D_READ(V3D_MMUC_CONTROL) &
+			 V3D_MMUC_CONTROL_FLUSHING), 100);
+	if (ret)
+		dev_err(v3d->dev, "MMUC flush wait idle failed\n");
+
+	return ret;
+}
+
+int v3d_mmu_set_page_table(struct v3d_dev *v3d)
+{
+	V3D_WRITE(V3D_MMU_PT_PA_BASE, v3d->pt_paddr >> V3D_MMU_PAGE_SHIFT);
+	V3D_WRITE(V3D_MMU_CTL,
+		  V3D_MMU_CTL_ENABLE |
+		  V3D_MMU_CTL_PT_INVALID |
+		  V3D_MMU_CTL_PT_INVALID_ABORT |
+		  V3D_MMU_CTL_WRITE_VIOLATION_ABORT |
+		  V3D_MMU_CTL_CAP_EXCEEDED_ABORT);
+	V3D_WRITE(V3D_MMU_ILLEGAL_ADDR,
+		  (v3d->mmu_scratch_paddr >> V3D_MMU_PAGE_SHIFT) |
+		  V3D_MMU_ILLEGAL_ADDR_ENABLE);
+	V3D_WRITE(V3D_MMUC_CONTROL, V3D_MMUC_CONTROL_ENABLE);
+
+	return v3d_mmu_flush_all(v3d);
+}
+
+void v3d_mmu_insert_ptes(struct v3d_bo *bo)
+{
+	struct v3d_dev *v3d = to_v3d_dev(bo->base.dev);
+	u32 page = bo->node.start;
+	u32 page_prot = V3D_PTE_WRITEABLE | V3D_PTE_VALID;
+	unsigned int count;
+	struct scatterlist *sgl;
+
+	for_each_sg(bo->sgt->sgl, sgl, bo->sgt->nents, count) {
+		u32 page_address = sg_dma_address(sgl) >> V3D_MMU_PAGE_SHIFT;
+		u32 pte = page_prot | page_address;
+		u32 i;
+
+		BUG_ON(page_address + (sg_dma_len(sgl) >> V3D_MMU_PAGE_SHIFT) >=
+		       BIT(24));
+
+		for (i = 0; i < sg_dma_len(sgl) >> V3D_MMU_PAGE_SHIFT; i++)
+			v3d->pt[page++] = pte + i;
+	}
+
+	WARN_ON_ONCE(page - bo->node.start !=
+		     bo->base.size >> V3D_MMU_PAGE_SHIFT);
+
+	if (v3d_mmu_flush_all(v3d))
+		dev_err(v3d->dev, "MMU flush timeout\n");
+}
+
+void v3d_mmu_remove_ptes(struct v3d_bo *bo)
+{
+	struct v3d_dev *v3d = to_v3d_dev(bo->base.dev);
+	u32 npages = bo->base.size >> V3D_MMU_PAGE_SHIFT;
+	u32 page;
+
+	for (page = bo->node.start; page < bo->node.start + npages; page++)
+		v3d->pt[page] = 0;
+
+	if (v3d_mmu_flush_all(v3d))
+		dev_err(v3d->dev, "MMU flush timeout\n");
+}
diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h
new file mode 100644
index 000000000000..fc13282dfc2f
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_regs.h
@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2017-2018 Broadcom */
+
+#ifndef V3D_REGS_H
+#define V3D_REGS_H
+
+#include <linux/bitops.h>
+
+#define V3D_MASK(high, low) ((u32)GENMASK(high, low))
+/* Using the GNU statement expression extension */
+#define V3D_SET_FIELD(value, field)					\
+	({								\
+		u32 fieldval = (value) << field##_SHIFT;		\
+		WARN_ON((fieldval & ~field##_MASK) != 0);		\
+		fieldval & field##_MASK;				\
+	 })
+
+#define V3D_GET_FIELD(word, field) (((word) & field##_MASK) >>		\
+				    field##_SHIFT)
+
+/* Hub registers for shared hardware between V3D cores. */
+
+#define V3D_HUB_AXICFG                                 0x00000
+# define V3D_HUB_AXICFG_MAX_LEN_MASK                   V3D_MASK(3, 0)
+# define V3D_HUB_AXICFG_MAX_LEN_SHIFT                  0
+#define V3D_HUB_UIFCFG                                 0x00004
+#define V3D_HUB_IDENT0                                 0x00008
+
+#define V3D_HUB_IDENT1                                 0x0000c
+# define V3D_HUB_IDENT1_WITH_MSO                       BIT(19)
+# define V3D_HUB_IDENT1_WITH_TSY                       BIT(18)
+# define V3D_HUB_IDENT1_WITH_TFU                       BIT(17)
+# define V3D_HUB_IDENT1_WITH_L3C                       BIT(16)
+# define V3D_HUB_IDENT1_NHOSTS_MASK                    V3D_MASK(15, 12)
+# define V3D_HUB_IDENT1_NHOSTS_SHIFT                   12
+# define V3D_HUB_IDENT1_NCORES_MASK                    V3D_MASK(11, 8)
+# define V3D_HUB_IDENT1_NCORES_SHIFT                   8
+# define V3D_HUB_IDENT1_REV_MASK                       V3D_MASK(7, 4)
+# define V3D_HUB_IDENT1_REV_SHIFT                      4
+# define V3D_HUB_IDENT1_TVER_MASK                      V3D_MASK(3, 0)
+# define V3D_HUB_IDENT1_TVER_SHIFT                     0
+
+#define V3D_HUB_IDENT2                                 0x00010
+# define V3D_HUB_IDENT2_WITH_MMU                       BIT(8)
+# define V3D_HUB_IDENT2_L3C_NKB_MASK                   V3D_MASK(7, 0)
+# define V3D_HUB_IDENT2_L3C_NKB_SHIFT                  0
+
+#define V3D_HUB_IDENT3                                 0x00014
+# define V3D_HUB_IDENT3_IPREV_MASK                     V3D_MASK(15, 8)
+# define V3D_HUB_IDENT3_IPREV_SHIFT                    8
+# define V3D_HUB_IDENT3_IPIDX_MASK                     V3D_MASK(7, 0)
+# define V3D_HUB_IDENT3_IPIDX_SHIFT                    0
+
+#define V3D_HUB_INT_STS                                0x00050
+#define V3D_HUB_INT_SET                                0x00054
+#define V3D_HUB_INT_CLR                                0x00058
+#define V3D_HUB_INT_MSK_STS                            0x0005c
+#define V3D_HUB_INT_MSK_SET                            0x00060
+#define V3D_HUB_INT_MSK_CLR                            0x00064
+# define V3D_HUB_INT_MMU_WRV                           BIT(5)
+# define V3D_HUB_INT_MMU_PTI                           BIT(4)
+# define V3D_HUB_INT_MMU_CAP                           BIT(3)
+# define V3D_HUB_INT_MSO                               BIT(2)
+# define V3D_HUB_INT_TFUC                              BIT(1)
+# define V3D_HUB_INT_TFUF                              BIT(0)
+
+#define V3D_GCA_CACHE_CTRL                             0x0000c
+# define V3D_GCA_CACHE_CTRL_FLUSH                      BIT(0)
+
+#define V3D_GCA_SAFE_SHUTDOWN                          0x000b0
+# define V3D_GCA_SAFE_SHUTDOWN_EN                      BIT(0)
+
+#define V3D_GCA_SAFE_SHUTDOWN_ACK                      0x000b4
+# define V3D_GCA_SAFE_SHUTDOWN_ACK_ACKED               3
+
+# define V3D_TOP_GR_BRIDGE_REVISION                    0x00000
+# define V3D_TOP_GR_BRIDGE_MAJOR_MASK                  V3D_MASK(15, 8)
+# define V3D_TOP_GR_BRIDGE_MAJOR_SHIFT                 8
+# define V3D_TOP_GR_BRIDGE_MINOR_MASK                  V3D_MASK(7, 0)
+# define V3D_TOP_GR_BRIDGE_MINOR_SHIFT                 0
+
+/* 7268 reset reg */
+# define V3D_TOP_GR_BRIDGE_SW_INIT_0                   0x00008
+# define V3D_TOP_GR_BRIDGE_SW_INIT_0_V3D_CLK_108_SW_INIT BIT(0)
+/* 7278 reset reg */
+# define V3D_TOP_GR_BRIDGE_SW_INIT_1                   0x0000c
+# define V3D_TOP_GR_BRIDGE_SW_INIT_1_V3D_CLK_108_SW_INIT BIT(0)
+
+/* Per-MMU registers. */
+
+#define V3D_MMUC_CONTROL                               0x01000
+# define V3D_MMUC_CONTROL_CLEAR                        BIT(3)
+# define V3D_MMUC_CONTROL_FLUSHING                     BIT(2)
+# define V3D_MMUC_CONTROL_FLUSH                        BIT(1)
+# define V3D_MMUC_CONTROL_ENABLE                       BIT(0)
+
+#define V3D_MMU_CTL                                    0x01200
+# define V3D_MMU_CTL_CAP_EXCEEDED                      BIT(27)
+# define V3D_MMU_CTL_CAP_EXCEEDED_ABORT                BIT(26)
+# define V3D_MMU_CTL_CAP_EXCEEDED_INT                  BIT(25)
+# define V3D_MMU_CTL_CAP_EXCEEDED_EXCEPTION            BIT(24)
+# define V3D_MMU_CTL_PT_INVALID                        BIT(20)
+# define V3D_MMU_CTL_PT_INVALID_ABORT                  BIT(19)
+# define V3D_MMU_CTL_PT_INVALID_INT                    BIT(18)
+# define V3D_MMU_CTL_PT_INVALID_EXCEPTION              BIT(17)
+# define V3D_MMU_CTL_WRITE_VIOLATION                   BIT(16)
+# define V3D_MMU_CTL_WRITE_VIOLATION_ABORT             BIT(11)
+# define V3D_MMU_CTL_WRITE_VIOLATION_INT               BIT(10)
+# define V3D_MMU_CTL_WRITE_VIOLATION_EXCEPTION         BIT(9)
+# define V3D_MMU_CTL_TLB_CLEARING                      BIT(7)
+# define V3D_MMU_CTL_TLB_STATS_CLEAR                   BIT(3)
+# define V3D_MMU_CTL_TLB_CLEAR                         BIT(2)
+# define V3D_MMU_CTL_TLB_STATS_ENABLE                  BIT(1)
+# define V3D_MMU_CTL_ENABLE                            BIT(0)
+
+#define V3D_MMU_PT_PA_BASE                             0x01204
+#define V3D_MMU_HIT                                    0x01208
+#define V3D_MMU_MISSES                                 0x0120c
+#define V3D_MMU_STALLS                                 0x01210
+
+#define V3D_MMU_ADDR_CAP                               0x01214
+# define V3D_MMU_ADDR_CAP_ENABLE                       BIT(31)
+# define V3D_MMU_ADDR_CAP_MPAGE_MASK                   V3D_MASK(11, 0)
+# define V3D_MMU_ADDR_CAP_MPAGE_SHIFT                  0
+
+#define V3D_MMU_SHOOT_DOWN                             0x01218
+# define V3D_MMU_SHOOT_DOWN_SHOOTING                   BIT(29)
+# define V3D_MMU_SHOOT_DOWN_SHOOT                      BIT(28)
+# define V3D_MMU_SHOOT_DOWN_PAGE_MASK                  V3D_MASK(27, 0)
+# define V3D_MMU_SHOOT_DOWN_PAGE_SHIFT                 0
+
+#define V3D_MMU_BYPASS_START                           0x0121c
+#define V3D_MMU_BYPASS_END                             0x01220
+
+/* AXI ID of the access that faulted */
+#define V3D_MMU_VIO_ID                                 0x0122c
+
+/* Address for illegal PTEs to return */
+#define V3D_MMU_ILLEGAL_ADDR                           0x01230
+# define V3D_MMU_ILLEGAL_ADDR_ENABLE                   BIT(31)
+
+/* Address that faulted */
+#define V3D_MMU_VIO_ADDR                               0x01234
+
+/* Per-V3D-core registers */
+
+#define V3D_CTL_IDENT0                                 0x00000
+# define V3D_IDENT0_VER_MASK                           V3D_MASK(31, 24)
+# define V3D_IDENT0_VER_SHIFT                          24
+
+#define V3D_CTL_IDENT1                                 0x00004
+/* Multiples of 1kb */
+# define V3D_IDENT1_VPM_SIZE_MASK                      V3D_MASK(31, 28)
+# define V3D_IDENT1_VPM_SIZE_SHIFT                     28
+# define V3D_IDENT1_NSEM_MASK                          V3D_MASK(23, 16)
+# define V3D_IDENT1_NSEM_SHIFT                         16
+# define V3D_IDENT1_NTMU_MASK                          V3D_MASK(15, 12)
+# define V3D_IDENT1_NTMU_SHIFT                         12
+# define V3D_IDENT1_QUPS_MASK                          V3D_MASK(11, 8)
+# define V3D_IDENT1_QUPS_SHIFT                         8
+# define V3D_IDENT1_NSLC_MASK                          V3D_MASK(7, 4)
+# define V3D_IDENT1_NSLC_SHIFT                         4
+# define V3D_IDENT1_REV_MASK                           V3D_MASK(3, 0)
+# define V3D_IDENT1_REV_SHIFT                          0
+
+#define V3D_CTL_IDENT2                                 0x00008
+# define V3D_IDENT2_BCG_INT                            BIT(28)
+
+#define V3D_CTL_MISCCFG                                0x00018
+# define V3D_MISCCFG_OVRTMUOUT                         BIT(0)
+
+#define V3D_CTL_L2CACTL                                0x00020
+# define V3D_L2CACTL_L2CCLR                            BIT(2)
+# define V3D_L2CACTL_L2CDIS                            BIT(1)
+# define V3D_L2CACTL_L2CENA                            BIT(0)
+
+#define V3D_CTL_SLCACTL                                0x00024
+# define V3D_SLCACTL_TVCCS_MASK                        V3D_MASK(27, 24)
+# define V3D_SLCACTL_TVCCS_SHIFT                       24
+# define V3D_SLCACTL_TDCCS_MASK                        V3D_MASK(19, 16)
+# define V3D_SLCACTL_TDCCS_SHIFT                       16
+# define V3D_SLCACTL_UCC_MASK                          V3D_MASK(11, 8)
+# define V3D_SLCACTL_UCC_SHIFT                         8
+# define V3D_SLCACTL_ICC_MASK                          V3D_MASK(3, 0)
+# define V3D_SLCACTL_ICC_SHIFT                         0
+
+#define V3D_CTL_L2TCACTL                               0x00030
+# define V3D_L2TCACTL_TMUWCF                           BIT(8)
+# define V3D_L2TCACTL_L2T_NO_WM                        BIT(4)
+# define V3D_L2TCACTL_FLM_FLUSH                        0
+# define V3D_L2TCACTL_FLM_CLEAR                        1
+# define V3D_L2TCACTL_FLM_CLEAN                        2
+# define V3D_L2TCACTL_FLM_MASK                         V3D_MASK(2, 1)
+# define V3D_L2TCACTL_FLM_SHIFT                        1
+# define V3D_L2TCACTL_L2TFLS                           BIT(0)
+#define V3D_CTL_L2TFLSTA                               0x00034
+#define V3D_CTL_L2TFLEND                               0x00038
+
+#define V3D_CTL_INT_STS                                0x00050
+#define V3D_CTL_INT_SET                                0x00054
+#define V3D_CTL_INT_CLR                                0x00058
+#define V3D_CTL_INT_MSK_STS                            0x0005c
+#define V3D_CTL_INT_MSK_SET                            0x00060
+#define V3D_CTL_INT_MSK_CLR                            0x00064
+# define V3D_INT_QPU_MASK                              V3D_MASK(27, 16)
+# define V3D_INT_QPU_SHIFT                             16
+# define V3D_INT_GMPV                                  BIT(5)
+# define V3D_INT_TRFB                                  BIT(4)
+# define V3D_INT_SPILLUSE                              BIT(3)
+# define V3D_INT_OUTOMEM                               BIT(2)
+# define V3D_INT_FLDONE                                BIT(1)
+# define V3D_INT_FRDONE                                BIT(0)
+
+#define V3D_CLE_CT0CS                                  0x00100
+#define V3D_CLE_CT1CS                                  0x00104
+#define V3D_CLE_CTNCS(n) (V3D_CLE_CT0CS + 4 * n)
+#define V3D_CLE_CT0EA                                  0x00108
+#define V3D_CLE_CT1EA                                  0x0010c
+#define V3D_CLE_CTNEA(n) (V3D_CLE_CT0EA + 4 * n)
+#define V3D_CLE_CT0CA                                  0x00110
+#define V3D_CLE_CT1CA                                  0x00114
+#define V3D_CLE_CTNCA(n) (V3D_CLE_CT0CA + 4 * n)
+#define V3D_CLE_CT0RA                                  0x00118
+#define V3D_CLE_CT1RA                                  0x0011c
+#define V3D_CLE_CT0LC                                  0x00120
+#define V3D_CLE_CT1LC                                  0x00124
+#define V3D_CLE_CT0PC                                  0x00128
+#define V3D_CLE_CT1PC                                  0x0012c
+#define V3D_CLE_PCS                                    0x00130
+#define V3D_CLE_BFC                                    0x00134
+#define V3D_CLE_RFC                                    0x00138
+#define V3D_CLE_TFBC                                   0x0013c
+#define V3D_CLE_TFIT                                   0x00140
+#define V3D_CLE_CT1CFG                                 0x00144
+#define V3D_CLE_CT1TILECT                              0x00148
+#define V3D_CLE_CT1TSKIP                               0x0014c
+#define V3D_CLE_CT1PTCT                                0x00150
+#define V3D_CLE_CT0SYNC                                0x00154
+#define V3D_CLE_CT1SYNC                                0x00158
+#define V3D_CLE_CT0QTS                                 0x0015c
+# define V3D_CLE_CT0QTS_ENABLE                         BIT(1)
+#define V3D_CLE_CT0QBA                                 0x00160
+#define V3D_CLE_CT1QBA                                 0x00164
+#define V3D_CLE_CTNQBA(n) (V3D_CLE_CT0QBA + 4 * n)
+#define V3D_CLE_CT0QEA                                 0x00168
+#define V3D_CLE_CT1QEA                                 0x0016c
+#define V3D_CLE_CTNQEA(n) (V3D_CLE_CT0QEA + 4 * n)
+#define V3D_CLE_CT0QMA                                 0x00170
+#define V3D_CLE_CT0QMS                                 0x00174
+#define V3D_CLE_CT1QCFG                                0x00178
+/* If set without ETPROC, entirely skip tiles with no primitives. */
+# define V3D_CLE_QCFG_ETFILT                           BIT(7)
+/* If set with ETFILT, just write the clear color to tiles with no
+ * primitives.
+ */
+# define V3D_CLE_QCFG_ETPROC                           BIT(6)
+# define V3D_CLE_QCFG_ETSFLUSH                         BIT(1)
+# define V3D_CLE_QCFG_MCDIS                            BIT(0)
+
+#define V3D_PTB_BPCA                                   0x00300
+#define V3D_PTB_BPCS                                   0x00304
+#define V3D_PTB_BPOA                                   0x00308
+#define V3D_PTB_BPOS                                   0x0030c
+
+#define V3D_PTB_BXCF                                   0x00310
+# define V3D_PTB_BXCF_RWORDERDISA                      BIT(1)
+# define V3D_PTB_BXCF_CLIPDISA                         BIT(0)
+
+#define V3D_GMP_STATUS                                 0x00800
+# define V3D_GMP_STATUS_GMPRST                         BIT(31)
+# define V3D_GMP_STATUS_WR_COUNT_MASK                  V3D_MASK(30, 24)
+# define V3D_GMP_STATUS_WR_COUNT_SHIFT                 24
+# define V3D_GMP_STATUS_RD_COUNT_MASK                  V3D_MASK(22, 16)
+# define V3D_GMP_STATUS_RD_COUNT_SHIFT                 16
+# define V3D_GMP_STATUS_WR_ACTIVE                      BIT(5)
+# define V3D_GMP_STATUS_RD_ACTIVE                      BIT(4)
+# define V3D_GMP_STATUS_CFG_BUSY                       BIT(3)
+# define V3D_GMP_STATUS_CNTOVF                         BIT(2)
+# define V3D_GMP_STATUS_INVPROT                        BIT(1)
+# define V3D_GMP_STATUS_VIO                            BIT(0)
+
+#define V3D_GMP_CFG                                    0x00804
+# define V3D_GMP_CFG_LBURSTEN                          BIT(3)
+# define V3D_GMP_CFG_PGCRSEN                           BIT()
+# define V3D_GMP_CFG_STOP_REQ                          BIT(1)
+# define V3D_GMP_CFG_PROT_ENABLE                       BIT(0)
+
+#define V3D_GMP_VIO_ADDR                               0x00808
+#define V3D_GMP_VIO_TYPE                               0x0080c
+#define V3D_GMP_TABLE_ADDR                             0x00810
+#define V3D_GMP_CLEAR_LOAD                             0x00814
+#define V3D_GMP_PRESERVE_LOAD                          0x00818
+#define V3D_GMP_VALID_LINES                            0x00820
+
+#endif /* V3D_REGS_H */
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
new file mode 100644
index 000000000000..b07bece9417d
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2018 Broadcom */
+
+/**
+ * DOC: Broadcom V3D scheduling
+ *
+ * The shared DRM GPU scheduler is used to coordinate submitting jobs
+ * to the hardware.  Each DRM fd (roughly a client process) gets its
+ * own scheduler entity, which will process jobs in order.  The GPU
+ * scheduler will round-robin between clients to submit the next job.
+ *
+ * For simplicity, and in order to keep latency low for interactive
+ * jobs when bulk background jobs are queued up, we submit a new job
+ * to the HW only when it has completed the last one, instead of
+ * filling up the CT[01]Q FIFOs with jobs.  Similarly, we use
+ * v3d_job_dependency() to manage the dependency between bin and
+ * render, instead of having the clients submit jobs with using the
+ * HW's semaphores to interlock between them.
+ */
+
+#include <linux/kthread.h>
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+#include "v3d_trace.h"
+
+static struct v3d_job *
+to_v3d_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_job, base);
+}
+
+static void
+v3d_job_free(struct drm_sched_job *sched_job)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+
+	v3d_exec_put(job->exec);
+}
+
+/**
+ * Returns the fences that the bin job depends on, one by one.
+ * v3d_job_run() won't be called until all of them have been signaled.
+ */
+static struct dma_fence *
+v3d_job_dependency(struct drm_sched_job *sched_job,
+		   struct drm_sched_entity *s_entity)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+	struct v3d_exec_info *exec = job->exec;
+	enum v3d_queue q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
+	struct dma_fence *fence;
+
+	fence = job->in_fence;
+	if (fence) {
+		job->in_fence = NULL;
+		return fence;
+	}
+
+	if (q == V3D_RENDER) {
+		/* If we had a bin job, the render job definitely depends on
+		 * it. We first have to wait for bin to be scheduled, so that
+		 * its done_fence is created.
+		 */
+		fence = exec->bin_done_fence;
+		if (fence) {
+			exec->bin_done_fence = NULL;
+			return fence;
+		}
+	}
+
+	/* XXX: Wait on a fence for switching the GMP if necessary,
+	 * and then do so.
+	 */
+
+	return fence;
+}
+
+static struct dma_fence *v3d_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+	struct v3d_exec_info *exec = job->exec;
+	enum v3d_queue q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
+	struct v3d_dev *v3d = exec->v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+	unsigned long irqflags;
+
+	if (unlikely(job->base.s_fence->finished.error))
+		return NULL;
+
+	/* Lock required around bin_job update vs
+	 * v3d_overflow_mem_work().
+	 */
+	spin_lock_irqsave(&v3d->job_lock, irqflags);
+	if (q == V3D_BIN) {
+		v3d->bin_job = job->exec;
+
+		/* Clear out the overflow allocation, so we don't
+		 * reuse the overflow attached to a previous job.
+		 */
+		V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
+	} else {
+		v3d->render_job = job->exec;
+	}
+	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+
+	/* Can we avoid this flush when q==RENDER?  We need to be
+	 * careful of scheduling, though -- imagine job0 rendering to
+	 * texture and job1 reading, and them being executed as bin0,
+	 * bin1, render0, render1, so that render1's flush at bin time
+	 * wasn't enough.
+	 */
+	v3d_invalidate_caches(v3d);
+
+	fence = v3d_fence_create(v3d, q);
+	if (!fence)
+		return fence;
+
+	if (job->done_fence)
+		dma_fence_put(job->done_fence);
+	job->done_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_cl(dev, q == V3D_RENDER, to_v3d_fence(fence)->seqno,
+			    job->start, job->end);
+
+	if (q == V3D_BIN) {
+		if (exec->qma) {
+			V3D_CORE_WRITE(0, V3D_CLE_CT0QMA, exec->qma);
+			V3D_CORE_WRITE(0, V3D_CLE_CT0QMS, exec->qms);
+		}
+		if (exec->qts) {
+			V3D_CORE_WRITE(0, V3D_CLE_CT0QTS,
+				       V3D_CLE_CT0QTS_ENABLE |
+				       exec->qts);
+		}
+	} else {
+		/* XXX: Set the QCFG */
+	}
+
+	/* Set the current and end address of the control list.
+	 * Writing the end register is what starts the job.
+	 */
+	V3D_CORE_WRITE(0, V3D_CLE_CTNQBA(q), job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CTNQEA(q), job->end);
+
+	return fence;
+}
+
+static void
+v3d_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+	struct v3d_exec_info *exec = job->exec;
+	struct v3d_dev *v3d = exec->v3d;
+	enum v3d_queue q;
+
+	mutex_lock(&v3d->reset_lock);
+
+	/* block scheduler */
+	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+		struct drm_gpu_scheduler *sched = &v3d->queue[q].sched;
+
+		kthread_park(sched->thread);
+		drm_sched_hw_job_reset(sched, (sched_job->sched == sched ?
+					       sched_job : NULL));
+	}
+
+	/* get the GPU back into the init state */
+	v3d_reset(v3d);
+
+	/* Unblock schedulers and restart their jobs. */
+	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+		drm_sched_job_recovery(&v3d->queue[q].sched);
+		kthread_unpark(v3d->queue[q].sched.thread);
+	}
+
+	mutex_unlock(&v3d->reset_lock);
+}
+
+static const struct drm_sched_backend_ops v3d_sched_ops = {
+	.dependency = v3d_job_dependency,
+	.run_job = v3d_job_run,
+	.timedout_job = v3d_job_timedout,
+	.free_job = v3d_job_free
+};
+
+int
+v3d_sched_init(struct v3d_dev *v3d)
+{
+	int hw_jobs_limit = 1;
+	int job_hang_limit = 0;
+	int hang_limit_ms = 500;
+	int ret;
+
+	ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
+			     &v3d_sched_ops,
+			     hw_jobs_limit, job_hang_limit,
+			     msecs_to_jiffies(hang_limit_ms),
+			     "v3d_bin");
+	if (ret) {
+		dev_err(v3d->dev, "Failed to create bin scheduler: %d.", ret);
+		return ret;
+	}
+
+	ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
+			     &v3d_sched_ops,
+			     hw_jobs_limit, job_hang_limit,
+			     msecs_to_jiffies(hang_limit_ms),
+			     "v3d_render");
+	if (ret) {
+		dev_err(v3d->dev, "Failed to create render scheduler: %d.",
+			ret);
+		drm_sched_fini(&v3d->queue[V3D_BIN].sched);
+		return ret;
+	}
+
+	return 0;
+}
+
+void
+v3d_sched_fini(struct v3d_dev *v3d)
+{
+	enum v3d_queue q;
+
+	for (q = 0; q < V3D_MAX_QUEUES; q++)
+		drm_sched_fini(&v3d->queue[q].sched);
+}
diff --git a/drivers/gpu/drm/v3d/v3d_trace.h b/drivers/gpu/drm/v3d/v3d_trace.h
new file mode 100644
index 000000000000..85dd351e1e09
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_trace.h
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2015-2018 Broadcom */
+
+#if !defined(_V3D_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _V3D_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM v3d
+#define TRACE_INCLUDE_FILE v3d_trace
+
+TRACE_EVENT(v3d_submit_cl,
+	    TP_PROTO(struct drm_device *dev, bool is_render,
+		     uint64_t seqno,
+		     u32 ctnqba, u32 ctnqea),
+	    TP_ARGS(dev, is_render, seqno, ctnqba, ctnqea),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(bool, is_render)
+			     __field(u64, seqno)
+			     __field(u32, ctnqba)
+			     __field(u32, ctnqea)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->is_render = is_render;
+			   __entry->seqno = seqno;
+			   __entry->ctnqba = ctnqba;
+			   __entry->ctnqea = ctnqea;
+			   ),
+
+	    TP_printk("dev=%u, %s, seqno=%llu, 0x%08x..0x%08x",
+		      __entry->dev,
+		      __entry->is_render ? "RCL" : "BCL",
+		      __entry->seqno,
+		      __entry->ctnqba,
+		      __entry->ctnqea)
+);
+
+TRACE_EVENT(v3d_reset_begin,
+	    TP_PROTO(struct drm_device *dev),
+	    TP_ARGS(dev),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   ),
+
+	    TP_printk("dev=%u",
+		      __entry->dev)
+);
+
+TRACE_EVENT(v3d_reset_end,
+	    TP_PROTO(struct drm_device *dev),
+	    TP_ARGS(dev),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   ),
+
+	    TP_printk("dev=%u",
+		      __entry->dev)
+);
+
+#endif /* _V3D_TRACE_H_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/v3d/v3d_trace_points.c b/drivers/gpu/drm/v3d/v3d_trace_points.c
new file mode 100644
index 000000000000..482922d7c7e1
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_trace_points.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2015 Broadcom */
+
+#include "v3d_drv.h"
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "v3d_trace.h"
+#endif
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 2decc8e2c79f..add9cc97a3b6 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -195,6 +195,7 @@ static void vc4_bo_destroy(struct vc4_bo *bo)
 	vc4_bo_set_label(obj, -1);
 
 	if (bo->validated_shader) {
+		kfree(bo->validated_shader->uniform_addr_offsets);
 		kfree(bo->validated_shader->texture_samples);
 		kfree(bo->validated_shader);
 		bo->validated_shader = NULL;
@@ -591,6 +592,7 @@ void vc4_free_object(struct drm_gem_object *gem_bo)
 	}
 
 	if (bo->validated_shader) {
+		kfree(bo->validated_shader->uniform_addr_offsets);
 		kfree(bo->validated_shader->texture_samples);
 		kfree(bo->validated_shader);
 		bo->validated_shader = NULL;
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index bf4667481935..c8650bbcbcb3 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -42,51 +42,18 @@
 #include "vc4_drv.h"
 #include "vc4_regs.h"
 
-struct vc4_crtc {
-	struct drm_crtc base;
-	const struct vc4_crtc_data *data;
-	void __iomem *regs;
-
-	/* Timestamp at start of vblank irq - unaffected by lock delays. */
-	ktime_t t_vblank;
-
-	/* Which HVS channel we're using for our CRTC. */
-	int channel;
-
-	u8 lut_r[256];
-	u8 lut_g[256];
-	u8 lut_b[256];
-	/* Size in pixels of the COB memory allocated to this CRTC. */
-	u32 cob_size;
-
-	struct drm_pending_vblank_event *event;
-};
-
 struct vc4_crtc_state {
 	struct drm_crtc_state base;
 	/* Dlist area for this CRTC configuration. */
 	struct drm_mm_node mm;
 };
 
-static inline struct vc4_crtc *
-to_vc4_crtc(struct drm_crtc *crtc)
-{
-	return (struct vc4_crtc *)crtc;
-}
-
 static inline struct vc4_crtc_state *
 to_vc4_crtc_state(struct drm_crtc_state *crtc_state)
 {
 	return (struct vc4_crtc_state *)crtc_state;
 }
 
-struct vc4_crtc_data {
-	/* Which channel of the HVS this pixelvalve sources from. */
-	int hvs_channel;
-
-	enum vc4_encoder_type encoder_types[4];
-};
-
 #define CRTC_WRITE(offset, val) writel(val, vc4_crtc->regs + (offset))
 #define CRTC_READ(offset) readl(vc4_crtc->regs + (offset))
 
@@ -298,23 +265,21 @@ vc4_crtc_lut_load(struct drm_crtc *crtc)
 		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_b[i]);
 }
 
-static int
-vc4_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
-		   uint32_t size,
-		   struct drm_modeset_acquire_ctx *ctx)
+static void
+vc4_crtc_update_gamma_lut(struct drm_crtc *crtc)
 {
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+	struct drm_color_lut *lut = crtc->state->gamma_lut->data;
+	u32 length = drm_color_lut_size(crtc->state->gamma_lut);
 	u32 i;
 
-	for (i = 0; i < size; i++) {
-		vc4_crtc->lut_r[i] = r[i] >> 8;
-		vc4_crtc->lut_g[i] = g[i] >> 8;
-		vc4_crtc->lut_b[i] = b[i] >> 8;
+	for (i = 0; i < length; i++) {
+		vc4_crtc->lut_r[i] = drm_color_lut_extract(lut[i].red, 8);
+		vc4_crtc->lut_g[i] = drm_color_lut_extract(lut[i].green, 8);
+		vc4_crtc->lut_b[i] = drm_color_lut_extract(lut[i].blue, 8);
 	}
 
 	vc4_crtc_lut_load(crtc);
-
-	return 0;
 }
 
 static u32 vc4_get_fifo_full_level(u32 format)
@@ -699,6 +664,22 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc,
 	if (crtc->state->active && old_state->active)
 		vc4_crtc_update_dlist(crtc);
 
+	if (crtc->state->color_mgmt_changed) {
+		u32 dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(vc4_crtc->channel));
+
+		if (crtc->state->gamma_lut) {
+			vc4_crtc_update_gamma_lut(crtc);
+			dispbkgndx |= SCALER_DISPBKGND_GAMMA;
+		} else {
+			/* Unsetting DISPBKGND_GAMMA skips the gamma lut step
+			 * in hardware, which is the same as a linear lut that
+			 * DRM expects us to use in absence of a user lut.
+			 */
+			dispbkgndx &= ~SCALER_DISPBKGND_GAMMA;
+		}
+		HVS_WRITE(SCALER_DISPBKGNDX(vc4_crtc->channel), dispbkgndx);
+	}
+
 	if (debug_dump_regs) {
 		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
 		vc4_hvs_dump_state(dev);
@@ -760,6 +741,7 @@ static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
 struct vc4_async_flip_state {
 	struct drm_crtc *crtc;
 	struct drm_framebuffer *fb;
+	struct drm_framebuffer *old_fb;
 	struct drm_pending_vblank_event *event;
 
 	struct vc4_seqno_cb cb;
@@ -789,6 +771,23 @@ vc4_async_page_flip_complete(struct vc4_seqno_cb *cb)
 
 	drm_crtc_vblank_put(crtc);
 	drm_framebuffer_put(flip_state->fb);
+
+	/* Decrement the BO usecnt in order to keep the inc/dec calls balanced
+	 * when the planes are updated through the async update path.
+	 * FIXME: we should move to generic async-page-flip when it's
+	 * available, so that we can get rid of this hand-made cleanup_fb()
+	 * logic.
+	 */
+	if (flip_state->old_fb) {
+		struct drm_gem_cma_object *cma_bo;
+		struct vc4_bo *bo;
+
+		cma_bo = drm_fb_cma_get_gem_obj(flip_state->old_fb, 0);
+		bo = to_vc4_bo(&cma_bo->base);
+		vc4_bo_dec_usecnt(bo);
+		drm_framebuffer_put(flip_state->old_fb);
+	}
+
 	kfree(flip_state);
 
 	up(&vc4->async_modeset);
@@ -813,9 +812,22 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
 	struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0);
 	struct vc4_bo *bo = to_vc4_bo(&cma_bo->base);
 
+	/* Increment the BO usecnt here, so that we never end up with an
+	 * unbalanced number of vc4_bo_{dec,inc}_usecnt() calls when the
+	 * plane is later updated through the non-async path.
+	 * FIXME: we should move to generic async-page-flip when it's
+	 * available, so that we can get rid of this hand-made prepare_fb()
+	 * logic.
+	 */
+	ret = vc4_bo_inc_usecnt(bo);
+	if (ret)
+		return ret;
+
 	flip_state = kzalloc(sizeof(*flip_state), GFP_KERNEL);
-	if (!flip_state)
+	if (!flip_state) {
+		vc4_bo_dec_usecnt(bo);
 		return -ENOMEM;
+	}
 
 	drm_framebuffer_get(fb);
 	flip_state->fb = fb;
@@ -826,10 +838,23 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
 	ret = down_interruptible(&vc4->async_modeset);
 	if (ret) {
 		drm_framebuffer_put(fb);
+		vc4_bo_dec_usecnt(bo);
 		kfree(flip_state);
 		return ret;
 	}
 
+	/* Save the current FB before it's replaced by the new one in
+	 * drm_atomic_set_fb_for_plane(). We'll need the old FB in
+	 * vc4_async_page_flip_complete() to decrement the BO usecnt and keep
+	 * it consistent.
+	 * FIXME: we should move to generic async-page-flip when it's
+	 * available, so that we can get rid of this hand-made cleanup_fb()
+	 * logic.
+	 */
+	flip_state->old_fb = plane->state->fb;
+	if (flip_state->old_fb)
+		drm_framebuffer_get(flip_state->old_fb);
+
 	WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 
 	/* Immediately update the plane's legacy fb pointer, so that later
@@ -909,7 +934,7 @@ static const struct drm_crtc_funcs vc4_crtc_funcs = {
 	.reset = vc4_crtc_reset,
 	.atomic_duplicate_state = vc4_crtc_duplicate_state,
 	.atomic_destroy_state = vc4_crtc_destroy_state,
-	.gamma_set = vc4_crtc_gamma_set,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 	.enable_vblank = vc4_enable_vblank,
 	.disable_vblank = vc4_disable_vblank,
 };
@@ -1035,6 +1060,12 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	primary_plane->crtc = crtc;
 	vc4_crtc->channel = vc4_crtc->data->hvs_channel;
 	drm_mode_crtc_set_gamma_size(crtc, ARRAY_SIZE(vc4_crtc->lut_r));
+	drm_crtc_enable_color_mgmt(crtc, 0, false, crtc->gamma_size);
+
+	/* We support CTM, but only for one CRTC at a time. It's therefore
+	 * implemented as private driver state in vc4_kms, not here.
+	 */
+	drm_crtc_enable_color_mgmt(crtc, 0, true, crtc->gamma_size);
 
 	/* Set up some arbitrary number of planes.  We're not limited
 	 * by a set number of physical registers, just the space in
diff --git a/drivers/gpu/drm/vc4/vc4_dpi.c b/drivers/gpu/drm/vc4/vc4_dpi.c
index 72c9dbd81d7f..f185812970da 100644
--- a/drivers/gpu/drm/vc4/vc4_dpi.c
+++ b/drivers/gpu/drm/vc4/vc4_dpi.c
@@ -96,7 +96,6 @@ struct vc4_dpi {
 	struct platform_device *pdev;
 
 	struct drm_encoder *encoder;
-	struct drm_connector *connector;
 
 	void __iomem *regs;
 
@@ -164,14 +163,31 @@ static void vc4_dpi_encoder_disable(struct drm_encoder *encoder)
 
 static void vc4_dpi_encoder_enable(struct drm_encoder *encoder)
 {
+	struct drm_device *dev = encoder->dev;
 	struct drm_display_mode *mode = &encoder->crtc->mode;
 	struct vc4_dpi_encoder *vc4_encoder = to_vc4_dpi_encoder(encoder);
 	struct vc4_dpi *dpi = vc4_encoder->dpi;
+	struct drm_connector_list_iter conn_iter;
+	struct drm_connector *connector = NULL, *connector_scan;
 	u32 dpi_c = DPI_ENABLE | DPI_OUTPUT_ENABLE_MODE;
 	int ret;
 
-	if (dpi->connector->display_info.num_bus_formats) {
-		u32 bus_format = dpi->connector->display_info.bus_formats[0];
+	/* Look up the connector attached to DPI so we can get the
+	 * bus_format.  Ideally the bridge would tell us the
+	 * bus_format we want, but it doesn't yet, so assume that it's
+	 * uniform throughout the bridge chain.
+	 */
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_for_each_connector_iter(connector_scan, &conn_iter) {
+		if (connector_scan->encoder == encoder) {
+			connector = connector_scan;
+			break;
+		}
+	}
+	drm_connector_list_iter_end(&conn_iter);
+
+	if (connector && connector->display_info.num_bus_formats) {
+		u32 bus_format = connector->display_info.bus_formats[0];
 
 		switch (bus_format) {
 		case MEDIA_BUS_FMT_RGB888_1X24:
@@ -199,6 +215,9 @@ static void vc4_dpi_encoder_enable(struct drm_encoder *encoder)
 			DRM_ERROR("Unknown media bus format %d\n", bus_format);
 			break;
 		}
+	} else {
+		/* Default to 24bit if no connector found. */
+		dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, DPI_FORMAT);
 	}
 
 	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 94b99c90425a..466d0a27b415 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -130,6 +130,7 @@ static void vc4_close(struct drm_device *dev, struct drm_file *file)
 	struct vc4_file *vc4file = file->driver_priv;
 
 	vc4_perfmon_close_file(vc4file);
+	kfree(vc4file);
 }
 
 static const struct vm_operations_struct vc4_vm_ops = {
@@ -175,7 +176,8 @@ static struct drm_driver vc4_drm_driver = {
 			    DRIVER_GEM |
 			    DRIVER_HAVE_IRQ |
 			    DRIVER_RENDER |
-			    DRIVER_PRIME),
+			    DRIVER_PRIME |
+			    DRIVER_SYNCOBJ),
 	.lastclose = drm_fb_helper_lastclose,
 	.open = vc4_open,
 	.postclose = vc4_close,
@@ -318,8 +320,8 @@ dev_unref:
 
 static void vc4_drm_unbind(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct drm_device *drm = platform_get_drvdata(pdev);
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
 
 	drm_dev_unregister(drm);
 
@@ -327,6 +329,8 @@ static void vc4_drm_unbind(struct device *dev)
 
 	drm_mode_config_cleanup(drm);
 
+	drm_atomic_private_obj_fini(&vc4->ctm_manager);
+
 	drm_dev_unref(drm);
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 1b4cd1fabf56..554a4e810d5b 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -10,6 +10,8 @@
 #include <drm/drmP.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_syncobj.h>
 
 #include "uapi/drm/vc4_drm.h"
 
@@ -193,6 +195,9 @@ struct vc4_dev {
 	} hangcheck;
 
 	struct semaphore async_modeset;
+
+	struct drm_modeset_lock ctm_state_lock;
+	struct drm_private_obj ctm_manager;
 };
 
 static inline struct vc4_dev *
@@ -392,6 +397,39 @@ to_vc4_encoder(struct drm_encoder *encoder)
 	return container_of(encoder, struct vc4_encoder, base);
 }
 
+struct vc4_crtc_data {
+	/* Which channel of the HVS this pixelvalve sources from. */
+	int hvs_channel;
+
+	enum vc4_encoder_type encoder_types[4];
+};
+
+struct vc4_crtc {
+	struct drm_crtc base;
+	const struct vc4_crtc_data *data;
+	void __iomem *regs;
+
+	/* Timestamp at start of vblank irq - unaffected by lock delays. */
+	ktime_t t_vblank;
+
+	/* Which HVS channel we're using for our CRTC. */
+	int channel;
+
+	u8 lut_r[256];
+	u8 lut_g[256];
+	u8 lut_b[256];
+	/* Size in pixels of the COB memory allocated to this CRTC. */
+	u32 cob_size;
+
+	struct drm_pending_vblank_event *event;
+};
+
+static inline struct vc4_crtc *
+to_vc4_crtc(struct drm_crtc *crtc)
+{
+	return (struct vc4_crtc *)crtc;
+}
+
 #define V3D_READ(offset) readl(vc4->v3d->regs + offset)
 #define V3D_WRITE(offset, val) writel(val, vc4->v3d->regs + offset)
 #define HVS_READ(offset) readl(vc4->hvs->regs + offset)
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index 94085f8bcd68..8aa897835118 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -753,6 +753,11 @@ static void vc4_dsi_ulps(struct vc4_dsi *dsi, bool ulps)
 			 (dsi->lanes > 2 ? DSI1_STAT_PHY_D2_STOP : 0) |
 			 (dsi->lanes > 3 ? DSI1_STAT_PHY_D3_STOP : 0));
 	int ret;
+	bool ulps_currently_enabled = (DSI_PORT_READ(PHY_AFEC0) &
+				       DSI_PORT_BIT(PHY_AFEC0_LATCH_ULPS));
+
+	if (ulps == ulps_currently_enabled)
+		return;
 
 	DSI_PORT_WRITE(STAT, stat_ulps);
 	DSI_PORT_WRITE(PHYC, DSI_PORT_READ(PHYC) | phyc_ulps);
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 2107b0daf8ef..7910b9acedd6 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -27,6 +27,7 @@
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/sched/signal.h>
+#include <linux/dma-fence-array.h>
 
 #include "uapi/drm/vc4_drm.h"
 #include "vc4_drv.h"
@@ -655,7 +656,8 @@ retry:
  */
 static int
 vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
-		 struct ww_acquire_ctx *acquire_ctx)
+		 struct ww_acquire_ctx *acquire_ctx,
+		 struct drm_syncobj *out_sync)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_exec_info *renderjob;
@@ -678,6 +680,9 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
 	fence->seqno = exec->seqno;
 	exec->fence = &fence->base;
 
+	if (out_sync)
+		drm_syncobj_replace_fence(out_sync, exec->fence);
+
 	vc4_update_bo_seqnos(exec, seqno);
 
 	vc4_unlock_bo_reservations(dev, exec, acquire_ctx);
@@ -1113,8 +1118,10 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_file *vc4file = file_priv->driver_priv;
 	struct drm_vc4_submit_cl *args = data;
+	struct drm_syncobj *out_sync = NULL;
 	struct vc4_exec_info *exec;
 	struct ww_acquire_ctx acquire_ctx;
+	struct dma_fence *in_fence;
 	int ret = 0;
 
 	if ((args->flags & ~(VC4_SUBMIT_CL_USE_CLEAR_COLOR |
@@ -1126,7 +1133,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	}
 
 	if (args->pad2 != 0) {
-		DRM_DEBUG("->pad2 must be set to zero\n");
+		DRM_DEBUG("Invalid pad: 0x%08x\n", args->pad2);
 		return -EINVAL;
 	}
 
@@ -1164,6 +1171,29 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 
+	if (args->in_sync) {
+		ret = drm_syncobj_find_fence(file_priv, args->in_sync,
+					     &in_fence);
+		if (ret)
+			goto fail;
+
+		/* When the fence (or fence array) is exclusively from our
+		 * context we can skip the wait since jobs are executed in
+		 * order of their submission through this ioctl and this can
+		 * only have fences from a prior job.
+		 */
+		if (!dma_fence_match_context(in_fence,
+					     vc4->dma_fence_context)) {
+			ret = dma_fence_wait(in_fence, true);
+			if (ret) {
+				dma_fence_put(in_fence);
+				goto fail;
+			}
+		}
+
+		dma_fence_put(in_fence);
+	}
+
 	if (exec->args->bin_cl_size != 0) {
 		ret = vc4_get_bcl(dev, exec);
 		if (ret)
@@ -1181,12 +1211,33 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	if (args->out_sync) {
+		out_sync = drm_syncobj_find(file_priv, args->out_sync);
+		if (!out_sync) {
+			ret = -EINVAL;
+			goto fail;
+		}
+
+		/* We replace the fence in out_sync in vc4_queue_submit since
+		 * the render job could execute immediately after that call.
+		 * If it finishes before our ioctl processing resumes the
+		 * render job fence could already have been freed.
+		 */
+	}
+
 	/* Clear this out of the struct we'll be putting in the queue,
 	 * since it's part of our stack.
 	 */
 	exec->args = NULL;
 
-	ret = vc4_queue_submit(dev, exec, &acquire_ctx);
+	ret = vc4_queue_submit(dev, exec, &acquire_ctx, out_sync);
+
+	/* The syncobj isn't part of the exec data and we need to free our
+	 * reference even if job submission failed.
+	 */
+	if (out_sync)
+		drm_syncobj_put(out_sync);
+
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index 2b62fc5b8d85..5d8c749c9749 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -58,6 +58,10 @@ static const struct {
 	HVS_REG(SCALER_DISPSTAT2),
 	HVS_REG(SCALER_DISPBASE2),
 	HVS_REG(SCALER_DISPALPHA2),
+	HVS_REG(SCALER_OLEDOFFS),
+	HVS_REG(SCALER_OLEDCOEF0),
+	HVS_REG(SCALER_OLEDCOEF1),
+	HVS_REG(SCALER_OLEDCOEF2),
 };
 
 void vc4_hvs_dump_state(struct drm_device *dev)
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index ba60153dddb5..8a411e5f8776 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -23,6 +23,117 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include "vc4_drv.h"
+#include "vc4_regs.h"
+
+struct vc4_ctm_state {
+	struct drm_private_state base;
+	struct drm_color_ctm *ctm;
+	int fifo;
+};
+
+static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv)
+{
+	return container_of(priv, struct vc4_ctm_state, base);
+}
+
+static struct vc4_ctm_state *vc4_get_ctm_state(struct drm_atomic_state *state,
+					       struct drm_private_obj *manager)
+{
+	struct drm_device *dev = state->dev;
+	struct vc4_dev *vc4 = dev->dev_private;
+	struct drm_private_state *priv_state;
+	int ret;
+
+	ret = drm_modeset_lock(&vc4->ctm_state_lock, state->acquire_ctx);
+	if (ret)
+		return ERR_PTR(ret);
+
+	priv_state = drm_atomic_get_private_obj_state(state, manager);
+	if (IS_ERR(priv_state))
+		return ERR_CAST(priv_state);
+
+	return to_vc4_ctm_state(priv_state);
+}
+
+static struct drm_private_state *
+vc4_ctm_duplicate_state(struct drm_private_obj *obj)
+{
+	struct vc4_ctm_state *state;
+
+	state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return NULL;
+
+	__drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
+
+	return &state->base;
+}
+
+static void vc4_ctm_destroy_state(struct drm_private_obj *obj,
+				  struct drm_private_state *state)
+{
+	struct vc4_ctm_state *ctm_state = to_vc4_ctm_state(state);
+
+	kfree(ctm_state);
+}
+
+static const struct drm_private_state_funcs vc4_ctm_state_funcs = {
+	.atomic_duplicate_state = vc4_ctm_duplicate_state,
+	.atomic_destroy_state = vc4_ctm_destroy_state,
+};
+
+/* Converts a DRM S31.32 value to the HW S0.9 format. */
+static u16 vc4_ctm_s31_32_to_s0_9(u64 in)
+{
+	u16 r;
+
+	/* Sign bit. */
+	r = in & BIT_ULL(63) ? BIT(9) : 0;
+
+	if ((in & GENMASK_ULL(62, 32)) > 0) {
+		/* We have zero integer bits so we can only saturate here. */
+		r |= GENMASK(8, 0);
+	} else {
+		/* Otherwise take the 9 most important fractional bits. */
+		r |= (in >> 23) & GENMASK(8, 0);
+	}
+
+	return r;
+}
+
+static void
+vc4_ctm_commit(struct vc4_dev *vc4, struct drm_atomic_state *state)
+{
+	struct vc4_ctm_state *ctm_state = to_vc4_ctm_state(vc4->ctm_manager.state);
+	struct drm_color_ctm *ctm = ctm_state->ctm;
+
+	if (ctm_state->fifo) {
+		HVS_WRITE(SCALER_OLEDCOEF2,
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[0]),
+					SCALER_OLEDCOEF2_R_TO_R) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[3]),
+					SCALER_OLEDCOEF2_R_TO_G) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[6]),
+					SCALER_OLEDCOEF2_R_TO_B));
+		HVS_WRITE(SCALER_OLEDCOEF1,
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[1]),
+					SCALER_OLEDCOEF1_G_TO_R) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[4]),
+					SCALER_OLEDCOEF1_G_TO_G) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[7]),
+					SCALER_OLEDCOEF1_G_TO_B));
+		HVS_WRITE(SCALER_OLEDCOEF0,
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[2]),
+					SCALER_OLEDCOEF0_B_TO_R) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[5]),
+					SCALER_OLEDCOEF0_B_TO_G) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[8]),
+					SCALER_OLEDCOEF0_B_TO_B));
+	}
+
+	HVS_WRITE(SCALER_OLEDOFFS,
+		  VC4_SET_FIELD(ctm_state->fifo, SCALER_OLEDOFFS_DISPFIFO));
+}
 
 static void
 vc4_atomic_complete_commit(struct drm_atomic_state *state)
@@ -36,6 +147,8 @@ vc4_atomic_complete_commit(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_disables(dev, state);
 
+	vc4_ctm_commit(vc4, state);
+
 	drm_atomic_helper_commit_planes(dev, state, 0);
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
@@ -90,6 +203,26 @@ static int vc4_atomic_commit(struct drm_device *dev,
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	int ret;
 
+	if (state->async_update) {
+		ret = down_interruptible(&vc4->async_modeset);
+		if (ret)
+			return ret;
+
+		ret = drm_atomic_helper_prepare_planes(dev, state);
+		if (ret) {
+			up(&vc4->async_modeset);
+			return ret;
+		}
+
+		drm_atomic_helper_async_commit(dev, state);
+
+		drm_atomic_helper_cleanup_planes(dev, state);
+
+		up(&vc4->async_modeset);
+
+		return 0;
+	}
+
 	ret = drm_atomic_helper_setup_commit(state, nonblock);
 	if (ret)
 		return ret;
@@ -187,9 +320,89 @@ static struct drm_framebuffer *vc4_fb_create(struct drm_device *dev,
 	return drm_gem_fb_create(dev, file_priv, mode_cmd);
 }
 
+/* Our CTM has some peculiar limitations: we can only enable it for one CRTC
+ * at a time and the HW only supports S0.9 scalars. To account for the latter,
+ * we don't allow userland to set a CTM that we have no hope of approximating.
+ */
+static int
+vc4_ctm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_ctm_state *ctm_state = NULL;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_color_ctm *ctm;
+	int i;
+
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		/* CTM is being disabled. */
+		if (!new_crtc_state->ctm && old_crtc_state->ctm) {
+			ctm_state = vc4_get_ctm_state(state, &vc4->ctm_manager);
+			if (IS_ERR(ctm_state))
+				return PTR_ERR(ctm_state);
+			ctm_state->fifo = 0;
+		}
+	}
+
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		if (new_crtc_state->ctm == old_crtc_state->ctm)
+			continue;
+
+		if (!ctm_state) {
+			ctm_state = vc4_get_ctm_state(state, &vc4->ctm_manager);
+			if (IS_ERR(ctm_state))
+				return PTR_ERR(ctm_state);
+		}
+
+		/* CTM is being enabled or the matrix changed. */
+		if (new_crtc_state->ctm) {
+			/* fifo is 1-based since 0 disables CTM. */
+			int fifo = to_vc4_crtc(crtc)->channel + 1;
+
+			/* Check userland isn't trying to turn on CTM for more
+			 * than one CRTC at a time.
+			 */
+			if (ctm_state->fifo && ctm_state->fifo != fifo) {
+				DRM_DEBUG_DRIVER("Too many CTM configured\n");
+				return -EINVAL;
+			}
+
+			/* Check we can approximate the specified CTM.
+			 * We disallow scalars |c| > 1.0 since the HW has
+			 * no integer bits.
+			 */
+			ctm = new_crtc_state->ctm->data;
+			for (i = 0; i < ARRAY_SIZE(ctm->matrix); i++) {
+				u64 val = ctm->matrix[i];
+
+				val &= ~BIT_ULL(63);
+				if (val > BIT_ULL(32))
+					return -EINVAL;
+			}
+
+			ctm_state->fifo = fifo;
+			ctm_state->ctm = ctm;
+		}
+	}
+
+	return 0;
+}
+
+static int
+vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
+{
+	int ret;
+
+	ret = vc4_ctm_atomic_check(dev, state);
+	if (ret < 0)
+		return ret;
+
+	return drm_atomic_helper_check(dev, state);
+}
+
 static const struct drm_mode_config_funcs vc4_mode_funcs = {
 	.output_poll_changed = drm_fb_helper_output_poll_changed,
-	.atomic_check = drm_atomic_helper_check,
+	.atomic_check = vc4_atomic_check,
 	.atomic_commit = vc4_atomic_commit,
 	.fb_create = vc4_fb_create,
 };
@@ -197,6 +410,7 @@ static const struct drm_mode_config_funcs vc4_mode_funcs = {
 int vc4_kms_load(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_ctm_state *ctm_state;
 	int ret;
 
 	sema_init(&vc4->async_modeset, 1);
@@ -217,6 +431,14 @@ int vc4_kms_load(struct drm_device *dev)
 	dev->mode_config.async_page_flip = true;
 	dev->mode_config.allow_fb_modifiers = true;
 
+	drm_modeset_lock_init(&vc4->ctm_state_lock);
+
+	ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL);
+	if (!ctm_state)
+		return -ENOMEM;
+	drm_atomic_private_obj_init(&vc4->ctm_manager, &ctm_state->base,
+				    &vc4_ctm_state_funcs);
+
 	drm_mode_config_reset(dev);
 
 	if (dev->mode_config.num_connector)
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index ce39390be389..71d44c357d35 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -201,6 +201,7 @@ static void vc4_plane_reset(struct drm_plane *plane)
 		return;
 
 	plane->state = &vc4_state->base;
+	plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE;
 	vc4_state->base.plane = plane;
 }
 
@@ -467,6 +468,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	u32 ctl0_offset = vc4_state->dlist_count;
 	const struct hvs_format *format = vc4_get_hvs_format(fb->format->format);
 	int num_planes = drm_format_num_planes(format->drm);
+	bool mix_plane_alpha;
 	bool covers_screen;
 	u32 scl0, scl1, pitch0;
 	u32 lbm_size, tiling;
@@ -503,7 +505,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	 * the scl fields here.
 	 */
 	if (num_planes == 1) {
-		scl0 = vc4_get_scl_field(state, 1);
+		scl0 = vc4_get_scl_field(state, 0);
 		scl1 = scl0;
 	} else {
 		scl0 = vc4_get_scl_field(state, 1);
@@ -552,7 +554,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	/* Position Word 0: Image Positions and Alpha Value */
 	vc4_state->pos0_offset = vc4_state->dlist_count;
 	vc4_dlist_write(vc4_state,
-			VC4_SET_FIELD(0xff, SCALER_POS0_FIXED_ALPHA) |
+			VC4_SET_FIELD(state->alpha >> 8, SCALER_POS0_FIXED_ALPHA) |
 			VC4_SET_FIELD(vc4_state->crtc_x, SCALER_POS0_START_X) |
 			VC4_SET_FIELD(vc4_state->crtc_y, SCALER_POS0_START_Y));
 
@@ -565,6 +567,13 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 					      SCALER_POS1_SCL_HEIGHT));
 	}
 
+	/* Don't waste cycles mixing with plane alpha if the set alpha
+	 * is opaque or there is no per-pixel alpha information.
+	 * In any case we use the alpha property value as the fixed alpha.
+	 */
+	mix_plane_alpha = state->alpha != DRM_BLEND_ALPHA_OPAQUE &&
+			  fb->format->has_alpha;
+
 	/* Position Word 2: Source Image Size, Alpha */
 	vc4_state->pos2_offset = vc4_state->dlist_count;
 	vc4_dlist_write(vc4_state,
@@ -572,6 +581,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 				      SCALER_POS2_ALPHA_MODE_PIPELINE :
 				      SCALER_POS2_ALPHA_MODE_FIXED,
 				      SCALER_POS2_ALPHA_MODE) |
+			(mix_plane_alpha ? SCALER_POS2_ALPHA_MIX : 0) |
 			(fb->format->has_alpha ? SCALER_POS2_ALPHA_PREMULT : 0) |
 			VC4_SET_FIELD(vc4_state->src_w[0], SCALER_POS2_WIDTH) |
 			VC4_SET_FIELD(vc4_state->src_h[0], SCALER_POS2_HEIGHT));
@@ -653,10 +663,11 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 			vc4_state->crtc_w == state->crtc->mode.hdisplay &&
 			vc4_state->crtc_h == state->crtc->mode.vdisplay;
 	/* Background fill might be necessary when the plane has per-pixel
-	 * alpha content and blends from the background or does not cover
-	 * the entire screen.
+	 * alpha content or a non-opaque plane alpha and could blend from the
+	 * background or does not cover the entire screen.
 	 */
-	vc4_state->needs_bg_fill = fb->format->has_alpha || !covers_screen;
+	vc4_state->needs_bg_fill = fb->format->has_alpha || !covers_screen ||
+				   state->alpha != DRM_BLEND_ALPHA_OPAQUE;
 
 	return 0;
 }
@@ -741,6 +752,57 @@ void vc4_plane_async_set_fb(struct drm_plane *plane, struct drm_framebuffer *fb)
 	vc4_state->dlist[vc4_state->ptr0_offset] = addr;
 }
 
+static void vc4_plane_atomic_async_update(struct drm_plane *plane,
+					  struct drm_plane_state *state)
+{
+	struct vc4_plane_state *vc4_state = to_vc4_plane_state(plane->state);
+
+	if (plane->state->fb != state->fb) {
+		vc4_plane_async_set_fb(plane, state->fb);
+		drm_atomic_set_fb_for_plane(plane->state, state->fb);
+	}
+
+	/* Set the cursor's position on the screen.  This is the
+	 * expected change from the drm_mode_cursor_universal()
+	 * helper.
+	 */
+	plane->state->crtc_x = state->crtc_x;
+	plane->state->crtc_y = state->crtc_y;
+
+	/* Allow changing the start position within the cursor BO, if
+	 * that matters.
+	 */
+	plane->state->src_x = state->src_x;
+	plane->state->src_y = state->src_y;
+
+	/* Update the display list based on the new crtc_x/y. */
+	vc4_plane_atomic_check(plane, plane->state);
+
+	/* Note that we can't just call vc4_plane_write_dlist()
+	 * because that would smash the context data that the HVS is
+	 * currently using.
+	 */
+	writel(vc4_state->dlist[vc4_state->pos0_offset],
+	       &vc4_state->hw_dlist[vc4_state->pos0_offset]);
+	writel(vc4_state->dlist[vc4_state->pos2_offset],
+	       &vc4_state->hw_dlist[vc4_state->pos2_offset]);
+	writel(vc4_state->dlist[vc4_state->ptr0_offset],
+	       &vc4_state->hw_dlist[vc4_state->ptr0_offset]);
+}
+
+static int vc4_plane_atomic_async_check(struct drm_plane *plane,
+					struct drm_plane_state *state)
+{
+	/* No configuring new scaling in the fast path. */
+	if (plane->state->crtc_w != state->crtc_w ||
+	    plane->state->crtc_h != state->crtc_h ||
+	    plane->state->src_w != state->src_w ||
+	    plane->state->src_h != state->src_h)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int vc4_prepare_fb(struct drm_plane *plane,
 			  struct drm_plane_state *state)
 {
@@ -780,6 +842,8 @@ static const struct drm_plane_helper_funcs vc4_plane_helper_funcs = {
 	.atomic_update = vc4_plane_atomic_update,
 	.prepare_fb = vc4_prepare_fb,
 	.cleanup_fb = vc4_cleanup_fb,
+	.atomic_async_check = vc4_plane_atomic_async_check,
+	.atomic_async_update = vc4_plane_atomic_async_update,
 };
 
 static void vc4_plane_destroy(struct drm_plane *plane)
@@ -788,82 +852,6 @@ static void vc4_plane_destroy(struct drm_plane *plane)
 	drm_plane_cleanup(plane);
 }
 
-/* Implements immediate (non-vblank-synced) updates of the cursor
- * position, or falls back to the atomic helper otherwise.
- */
-static int
-vc4_update_plane(struct drm_plane *plane,
-		 struct drm_crtc *crtc,
-		 struct drm_framebuffer *fb,
-		 int crtc_x, int crtc_y,
-		 unsigned int crtc_w, unsigned int crtc_h,
-		 uint32_t src_x, uint32_t src_y,
-		 uint32_t src_w, uint32_t src_h,
-		 struct drm_modeset_acquire_ctx *ctx)
-{
-	struct drm_plane_state *plane_state;
-	struct vc4_plane_state *vc4_state;
-
-	if (plane != crtc->cursor)
-		goto out;
-
-	plane_state = plane->state;
-	vc4_state = to_vc4_plane_state(plane_state);
-
-	if (!plane_state)
-		goto out;
-
-	/* No configuring new scaling in the fast path. */
-	if (crtc_w != plane_state->crtc_w ||
-	    crtc_h != plane_state->crtc_h ||
-	    src_w != plane_state->src_w ||
-	    src_h != plane_state->src_h) {
-		goto out;
-	}
-
-	if (fb != plane_state->fb) {
-		drm_atomic_set_fb_for_plane(plane->state, fb);
-		vc4_plane_async_set_fb(plane, fb);
-	}
-
-	/* Set the cursor's position on the screen.  This is the
-	 * expected change from the drm_mode_cursor_universal()
-	 * helper.
-	 */
-	plane_state->crtc_x = crtc_x;
-	plane_state->crtc_y = crtc_y;
-
-	/* Allow changing the start position within the cursor BO, if
-	 * that matters.
-	 */
-	plane_state->src_x = src_x;
-	plane_state->src_y = src_y;
-
-	/* Update the display list based on the new crtc_x/y. */
-	vc4_plane_atomic_check(plane, plane_state);
-
-	/* Note that we can't just call vc4_plane_write_dlist()
-	 * because that would smash the context data that the HVS is
-	 * currently using.
-	 */
-	writel(vc4_state->dlist[vc4_state->pos0_offset],
-	       &vc4_state->hw_dlist[vc4_state->pos0_offset]);
-	writel(vc4_state->dlist[vc4_state->pos2_offset],
-	       &vc4_state->hw_dlist[vc4_state->pos2_offset]);
-	writel(vc4_state->dlist[vc4_state->ptr0_offset],
-	       &vc4_state->hw_dlist[vc4_state->ptr0_offset]);
-
-	return 0;
-
-out:
-	return drm_atomic_helper_update_plane(plane, crtc, fb,
-					      crtc_x, crtc_y,
-					      crtc_w, crtc_h,
-					      src_x, src_y,
-					      src_w, src_h,
-					      ctx);
-}
-
 static bool vc4_format_mod_supported(struct drm_plane *plane,
 				     uint32_t format,
 				     uint64_t modifier)
@@ -891,7 +879,7 @@ static bool vc4_format_mod_supported(struct drm_plane *plane,
 }
 
 static const struct drm_plane_funcs vc4_plane_funcs = {
-	.update_plane = vc4_update_plane,
+	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
 	.destroy = vc4_plane_destroy,
 	.set_property = NULL,
@@ -939,5 +927,7 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 
 	drm_plane_helper_add(plane, &vc4_plane_helper_funcs);
 
+	drm_plane_create_alpha_property(plane);
+
 	return plane;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index a141496104a6..d1fb6fec46eb 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -330,6 +330,21 @@
 #define SCALER_DISPCTRL0                        0x00000040
 # define SCALER_DISPCTRLX_ENABLE		BIT(31)
 # define SCALER_DISPCTRLX_RESET			BIT(30)
+/* Generates a single frame when VSTART is seen and stops at the last
+ * pixel read from the FIFO.
+ */
+# define SCALER_DISPCTRLX_ONESHOT		BIT(29)
+/* Processes a single context in the dlist and then task switch,
+ * instead of an entire line.
+ */
+# define SCALER_DISPCTRLX_ONECTX		BIT(28)
+/* Set to have DISPSLAVE return 2 16bpp pixels and no status data. */
+# define SCALER_DISPCTRLX_FIFO32		BIT(27)
+/* Turns on output to the DISPSLAVE register instead of the normal
+ * FIFO.
+ */
+# define SCALER_DISPCTRLX_FIFOREG		BIT(26)
+
 # define SCALER_DISPCTRLX_WIDTH_MASK		VC4_MASK(23, 12)
 # define SCALER_DISPCTRLX_WIDTH_SHIFT		12
 # define SCALER_DISPCTRLX_HEIGHT_MASK		VC4_MASK(11, 0)
@@ -402,6 +417,68 @@
  */
 # define SCALER_GAMADDR_SRAMENB			BIT(30)
 
+#define SCALER_OLEDOFFS                         0x00000080
+/* Clamps R to [16,235] and G/B to [16,240]. */
+# define SCALER_OLEDOFFS_YUVCLAMP               BIT(31)
+
+/* Chooses which display FIFO the matrix applies to. */
+# define SCALER_OLEDOFFS_DISPFIFO_MASK          VC4_MASK(25, 24)
+# define SCALER_OLEDOFFS_DISPFIFO_SHIFT         24
+# define SCALER_OLEDOFFS_DISPFIFO_DISABLED      0
+# define SCALER_OLEDOFFS_DISPFIFO_0             1
+# define SCALER_OLEDOFFS_DISPFIFO_1             2
+# define SCALER_OLEDOFFS_DISPFIFO_2             3
+
+/* Offsets are 8-bit 2s-complement. */
+# define SCALER_OLEDOFFS_RED_MASK               VC4_MASK(23, 16)
+# define SCALER_OLEDOFFS_RED_SHIFT              16
+# define SCALER_OLEDOFFS_GREEN_MASK             VC4_MASK(15, 8)
+# define SCALER_OLEDOFFS_GREEN_SHIFT            8
+# define SCALER_OLEDOFFS_BLUE_MASK              VC4_MASK(7, 0)
+# define SCALER_OLEDOFFS_BLUE_SHIFT             0
+
+/* The coefficients are S0.9 fractions. */
+#define SCALER_OLEDCOEF0                        0x00000084
+# define SCALER_OLEDCOEF0_B_TO_R_MASK           VC4_MASK(29, 20)
+# define SCALER_OLEDCOEF0_B_TO_R_SHIFT          20
+# define SCALER_OLEDCOEF0_B_TO_G_MASK           VC4_MASK(19, 10)
+# define SCALER_OLEDCOEF0_B_TO_G_SHIFT          10
+# define SCALER_OLEDCOEF0_B_TO_B_MASK           VC4_MASK(9, 0)
+# define SCALER_OLEDCOEF0_B_TO_B_SHIFT          0
+
+#define SCALER_OLEDCOEF1                        0x00000088
+# define SCALER_OLEDCOEF1_G_TO_R_MASK           VC4_MASK(29, 20)
+# define SCALER_OLEDCOEF1_G_TO_R_SHIFT          20
+# define SCALER_OLEDCOEF1_G_TO_G_MASK           VC4_MASK(19, 10)
+# define SCALER_OLEDCOEF1_G_TO_G_SHIFT          10
+# define SCALER_OLEDCOEF1_G_TO_B_MASK           VC4_MASK(9, 0)
+# define SCALER_OLEDCOEF1_G_TO_B_SHIFT          0
+
+#define SCALER_OLEDCOEF2                        0x0000008c
+# define SCALER_OLEDCOEF2_R_TO_R_MASK           VC4_MASK(29, 20)
+# define SCALER_OLEDCOEF2_R_TO_R_SHIFT          20
+# define SCALER_OLEDCOEF2_R_TO_G_MASK           VC4_MASK(19, 10)
+# define SCALER_OLEDCOEF2_R_TO_G_SHIFT          10
+# define SCALER_OLEDCOEF2_R_TO_B_MASK           VC4_MASK(9, 0)
+# define SCALER_OLEDCOEF2_R_TO_B_SHIFT          0
+
+/* Slave addresses for DMAing from HVS composition output to other
+ * devices.  The top bits are valid only in !FIFO32 mode.
+ */
+#define SCALER_DISPSLAVE0                       0x000000c0
+#define SCALER_DISPSLAVE1                       0x000000c9
+#define SCALER_DISPSLAVE2                       0x000000d0
+# define SCALER_DISPSLAVE_ISSUE_VSTART          BIT(31)
+# define SCALER_DISPSLAVE_ISSUE_HSTART          BIT(30)
+/* Set when the current line has been read and an HSTART is required. */
+# define SCALER_DISPSLAVE_EOL                   BIT(26)
+/* Set when the display FIFO is empty. */
+# define SCALER_DISPSLAVE_EMPTY                 BIT(25)
+/* Set when there is RGB data ready to read. */
+# define SCALER_DISPSLAVE_VALID                 BIT(24)
+# define SCALER_DISPSLAVE_RGB_MASK              VC4_MASK(23, 0)
+# define SCALER_DISPSLAVE_RGB_SHIFT             0
+
 #define SCALER_GAMDATA                          0x000000e0
 #define SCALER_DLIST_START                      0x00002000
 #define SCALER_DLIST_SIZE                       0x00004000
@@ -767,6 +844,10 @@ enum hvs_pixel_format {
 	HVS_PIXEL_FORMAT_YCBCR_YUV420_2PLANE = 9,
 	HVS_PIXEL_FORMAT_YCBCR_YUV422_3PLANE = 10,
 	HVS_PIXEL_FORMAT_YCBCR_YUV422_2PLANE = 11,
+	HVS_PIXEL_FORMAT_H264 = 12,
+	HVS_PIXEL_FORMAT_PALETTE = 13,
+	HVS_PIXEL_FORMAT_YUV444_RGB = 14,
+	HVS_PIXEL_FORMAT_AYUV444_RGB = 15,
 };
 
 /* Note: the LSB is the rightmost character shown.  Only valid for
@@ -800,12 +881,27 @@ enum hvs_pixel_format {
 #define SCALER_CTL0_TILING_128B			2
 #define SCALER_CTL0_TILING_256B_OR_T		3
 
+#define SCALER_CTL0_ALPHA_MASK                  BIT(19)
 #define SCALER_CTL0_HFLIP                       BIT(16)
 #define SCALER_CTL0_VFLIP                       BIT(15)
 
+#define SCALER_CTL0_KEY_MODE_MASK		VC4_MASK(18, 17)
+#define SCALER_CTL0_KEY_MODE_SHIFT		17
+#define SCALER_CTL0_KEY_DISABLED		0
+#define SCALER_CTL0_KEY_LUMA_OR_COMMON_RGB	1
+#define SCALER_CTL0_KEY_MATCH			2 /* turn transparent */
+#define SCALER_CTL0_KEY_REPLACE			3 /* replace with value from key mask word 2 */
+
 #define SCALER_CTL0_ORDER_MASK			VC4_MASK(14, 13)
 #define SCALER_CTL0_ORDER_SHIFT			13
 
+#define SCALER_CTL0_RGBA_EXPAND_MASK		VC4_MASK(12, 11)
+#define SCALER_CTL0_RGBA_EXPAND_SHIFT		11
+#define SCALER_CTL0_RGBA_EXPAND_ZERO		0
+#define SCALER_CTL0_RGBA_EXPAND_LSB		1
+#define SCALER_CTL0_RGBA_EXPAND_MSB		2
+#define SCALER_CTL0_RGBA_EXPAND_ROUND		3
+
 #define SCALER_CTL0_SCL1_MASK			VC4_MASK(10, 8)
 #define SCALER_CTL0_SCL1_SHIFT			8
 
@@ -849,6 +945,7 @@ enum hvs_pixel_format {
 #define SCALER_POS2_ALPHA_MODE_FIXED_NONZERO	2
 #define SCALER_POS2_ALPHA_MODE_FIXED_OVER_0x07	3
 #define SCALER_POS2_ALPHA_PREMULT		BIT(29)
+#define SCALER_POS2_ALPHA_MIX			BIT(28)
 
 #define SCALER_POS2_HEIGHT_MASK			VC4_MASK(27, 16)
 #define SCALER_POS2_HEIGHT_SHIFT		16
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index bfc2fa73d2ae..e47e29426078 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -218,8 +218,7 @@ try_again:
  * overall CMA pool before they make scenes complicated enough to run
  * out of bin space.
  */
-int
-vc4_allocate_bin_bo(struct drm_device *drm)
+static int vc4_allocate_bin_bo(struct drm_device *drm)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_v3d *v3d = vc4->v3d;
diff --git a/drivers/gpu/drm/vc4/vc4_validate_shaders.c b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
index d3f15bf60900..7cf82b071de2 100644
--- a/drivers/gpu/drm/vc4/vc4_validate_shaders.c
+++ b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
@@ -942,6 +942,7 @@ vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
 fail:
 	kfree(validation_state.branch_targets);
 	if (validated_shader) {
+		kfree(validated_shader->uniform_addr_offsets);
 		kfree(validated_shader->texture_samples);
 		kfree(validated_shader);
 	}
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index 8cc8c34d67f5..a5edd86603d9 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -208,7 +208,7 @@ static int virtio_gpu_conn_get_modes(struct drm_connector *connector)
 	return count;
 }
 
-static int virtio_gpu_conn_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status virtio_gpu_conn_mode_valid(struct drm_connector *connector,
 				      struct drm_display_mode *mode)
 {
 	struct virtio_gpu_output *output =
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 48e4f1df6e5d..020070d483d3 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -293,7 +293,7 @@ retry:
 	ret = virtqueue_add_sgs(vq, sgs, outcnt, incnt, vbuf, GFP_ATOMIC);
 	if (ret == -ENOSPC) {
 		spin_unlock(&vgdev->ctrlq.qlock);
-		wait_event(vgdev->ctrlq.ack_queue, vq->num_free);
+		wait_event(vgdev->ctrlq.ack_queue, vq->num_free >= outcnt + incnt);
 		spin_lock(&vgdev->ctrlq.qlock);
 		goto retry;
 	} else {
@@ -368,7 +368,7 @@ retry:
 	ret = virtqueue_add_sgs(vq, sgs, outcnt, 0, vbuf, GFP_ATOMIC);
 	if (ret == -ENOSPC) {
 		spin_unlock(&vgdev->cursorq.qlock);
-		wait_event(vgdev->cursorq.ack_queue, vq->num_free);
+		wait_event(vgdev->cursorq.ack_queue, vq->num_free >= outcnt);
 		spin_lock(&vgdev->cursorq.qlock);
 		goto retry;
 	} else {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 70e1a8820a7c..09cc721160c4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -159,14 +159,14 @@ static const struct drm_ioctl_desc vmw_ioctls[] = {
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CURSOR_BYPASS,
 		      vmw_kms_cursor_bypass_ioctl,
-		      DRM_MASTER | DRM_CONTROL_ALLOW),
+		      DRM_MASTER),
 
 	VMW_IOCTL_DEF(VMW_CONTROL_STREAM, vmw_overlay_ioctl,
-		      DRM_MASTER | DRM_CONTROL_ALLOW),
+		      DRM_MASTER),
 	VMW_IOCTL_DEF(VMW_CLAIM_STREAM, vmw_stream_claim_ioctl,
-		      DRM_MASTER | DRM_CONTROL_ALLOW),
+		      DRM_MASTER),
 	VMW_IOCTL_DEF(VMW_UNREF_STREAM, vmw_stream_unref_ioctl,
-		      DRM_MASTER | DRM_CONTROL_ALLOW),
+		      DRM_MASTER),
 
 	VMW_IOCTL_DEF(VMW_CREATE_CONTEXT, vmw_context_define_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
@@ -1278,8 +1278,6 @@ static void vmw_master_drop(struct drm_device *dev,
 	dev_priv->active_master = &dev_priv->fbdev_master;
 	ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM);
 	ttm_vt_unlock(&dev_priv->fbdev_master.lock);
-
-	vmw_fb_refresh(dev_priv);
 }
 
 /**
@@ -1483,7 +1481,6 @@ static int vmw_pm_freeze(struct device *kdev)
 			vmw_kms_resume(dev);
 		if (dev_priv->enable_fb)
 			vmw_fb_on(dev_priv);
-		vmw_fb_refresh(dev_priv);
 		return -EBUSY;
 	}
 
@@ -1523,8 +1520,6 @@ static int vmw_pm_restore(struct device *kdev)
 	if (dev_priv->enable_fb)
 		vmw_fb_on(dev_priv);
 
-	vmw_fb_refresh(dev_priv);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index f34f368c1a2e..5fcbe1620d50 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -910,7 +910,6 @@ int vmw_fb_init(struct vmw_private *vmw_priv);
 int vmw_fb_close(struct vmw_private *dev_priv);
 int vmw_fb_off(struct vmw_private *vmw_priv);
 int vmw_fb_on(struct vmw_private *vmw_priv);
-void vmw_fb_refresh(struct vmw_private *vmw_priv);
 
 /**
  * Kernel modesetting - vmwgfx_kms.c
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 2582ffd36bb5..54e300365a5c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -441,11 +441,11 @@ static int vmwgfx_set_config_internal(struct drm_mode_set *set)
 	struct drm_crtc *crtc = set->crtc;
 	struct drm_framebuffer *fb;
 	struct drm_crtc *tmp;
-	struct drm_modeset_acquire_ctx *ctx;
 	struct drm_device *dev = set->crtc->dev;
+	struct drm_modeset_acquire_ctx ctx;
 	int ret;
 
-	ctx = dev->mode_config.acquire_ctx;
+	drm_modeset_acquire_init(&ctx, 0);
 
 restart:
 	/*
@@ -458,7 +458,7 @@ restart:
 
 	fb = set->fb;
 
-	ret = crtc->funcs->set_config(set, ctx);
+	ret = crtc->funcs->set_config(set, &ctx);
 	if (ret == 0) {
 		crtc->primary->crtc = crtc;
 		crtc->primary->fb = fb;
@@ -473,20 +473,13 @@ restart:
 	}
 
 	if (ret == -EDEADLK) {
-		dev->mode_config.acquire_ctx = NULL;
-
-retry_locking:
-		drm_modeset_backoff(ctx);
-
-		ret = drm_modeset_lock_all_ctx(dev, ctx);
-		if (ret)
-			goto retry_locking;
-
-		dev->mode_config.acquire_ctx = ctx;
-
+		drm_modeset_backoff(&ctx);
 		goto restart;
 	}
 
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+
 	return ret;
 }
 
@@ -624,7 +617,6 @@ static int vmw_fb_set_par(struct fb_info *info)
 	}
 
 	mutex_lock(&par->bo_mutex);
-	drm_modeset_lock_all(vmw_priv->dev);
 	ret = vmw_fb_kms_framebuffer(info);
 	if (ret)
 		goto out_unlock;
@@ -657,7 +649,6 @@ out_unlock:
 		drm_mode_destroy(vmw_priv->dev, old_mode);
 	par->set_mode = mode;
 
-	drm_modeset_unlock_all(vmw_priv->dev);
 	mutex_unlock(&par->bo_mutex);
 
 	return ret;
@@ -713,18 +704,14 @@ int vmw_fb_init(struct vmw_private *vmw_priv)
 	par->max_width = fb_width;
 	par->max_height = fb_height;
 
-	drm_modeset_lock_all(vmw_priv->dev);
 	ret = vmw_kms_fbdev_init_data(vmw_priv, 0, par->max_width,
 				      par->max_height, &par->con,
 				      &par->crtc, &init_mode);
-	if (ret) {
-		drm_modeset_unlock_all(vmw_priv->dev);
+	if (ret)
 		goto err_kms;
-	}
 
 	info->var.xres = init_mode->hdisplay;
 	info->var.yres = init_mode->vdisplay;
-	drm_modeset_unlock_all(vmw_priv->dev);
 
 	/*
 	 * Create buffers and alloc memory
@@ -832,7 +819,9 @@ int vmw_fb_close(struct vmw_private *vmw_priv)
 	cancel_delayed_work_sync(&par->local_work);
 	unregister_framebuffer(info);
 
+	mutex_lock(&par->bo_mutex);
 	(void) vmw_fb_kms_detach(par, true, true);
+	mutex_unlock(&par->bo_mutex);
 
 	vfree(par->vmalloc);
 	framebuffer_release(info);
@@ -877,21 +866,13 @@ int vmw_fb_on(struct vmw_private *vmw_priv)
 	spin_lock_irqsave(&par->dirty.lock, flags);
 	par->dirty.active = true;
 	spin_unlock_irqrestore(&par->dirty.lock, flags);
- 
-	return 0;
-}
 
-/**
- * vmw_fb_refresh - Refresh fb display
- *
- * @vmw_priv: Pointer to device private
- *
- * Call into kms to show the fbdev display(s).
- */
-void vmw_fb_refresh(struct vmw_private *vmw_priv)
-{
-	if (!vmw_priv->fb_info)
-		return;
+	/*
+	 * Need to reschedule a dirty update, because otherwise that's
+	 * only done in dirty_mark() if the previous coalesced
+	 * dirty region was empty.
+	 */
+	schedule_delayed_work(&par->local_work, 0);
 
-	vmw_fb_set_par(vmw_priv->fb_info);
+	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index f11601b6fd74..01f2dc9e6f52 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -384,9 +384,9 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 	hotspot_x = du->hotspot_x;
 	hotspot_y = du->hotspot_y;
 
-	if (plane->fb) {
-		hotspot_x += plane->fb->hot_x;
-		hotspot_y += plane->fb->hot_y;
+	if (plane->state->fb) {
+		hotspot_x += plane->state->fb->hot_x;
+		hotspot_y += plane->state->fb->hot_y;
 	}
 
 	du->cursor_surface = vps->surf;
@@ -2595,6 +2595,7 @@ void vmw_kms_helper_resource_finish(struct vmw_validation_ctx *ctx,
 		vmw_kms_helper_buffer_finish(res->dev_priv, NULL, ctx->buf,
 					     out_fence, NULL);
 
+	vmw_dmabuf_unreference(&ctx->buf);
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
 }
@@ -2680,7 +2681,9 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 	struct vmw_display_unit *du;
 	struct drm_display_mode *mode;
 	int i = 0;
+	int ret = 0;
 
+	mutex_lock(&dev_priv->dev->mode_config.mutex);
 	list_for_each_entry(con, &dev_priv->dev->mode_config.connector_list,
 			    head) {
 		if (i == unit)
@@ -2691,7 +2694,8 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 
 	if (i != unit) {
 		DRM_ERROR("Could not find initial display unit.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	if (list_empty(&con->modes))
@@ -2699,7 +2703,8 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 
 	if (list_empty(&con->modes)) {
 		DRM_ERROR("Could not find initial display mode.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	du = vmw_connector_to_du(con);
@@ -2720,7 +2725,10 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 					   head);
 	}
 
-	return 0;
+ out_unlock:
+	mutex_unlock(&dev_priv->dev->mode_config.mutex);
+
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 3824595fece1..4a5907e3f560 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -281,39 +281,6 @@ drm_connector_helper_funcs vmw_ldu_connector_helper_funcs = {
  * Legacy Display Plane Functions
  */
 
-/**
- * vmw_ldu_primary_plane_cleanup_fb - Noop
- *
- * @plane:  display plane
- * @old_state: Contains the FB to clean up
- *
- * Unpins the display surface
- *
- * Returns 0 on success
- */
-static void
-vmw_ldu_primary_plane_cleanup_fb(struct drm_plane *plane,
-				 struct drm_plane_state *old_state)
-{
-}
-
-
-/**
- * vmw_ldu_primary_plane_prepare_fb - Noop
- *
- * @plane:  display plane
- * @new_state: info on the new plane state, including the FB
- *
- * Returns 0 on success
- */
-static int
-vmw_ldu_primary_plane_prepare_fb(struct drm_plane *plane,
-				 struct drm_plane_state *new_state)
-{
-	return 0;
-}
-
-
 static void
 vmw_ldu_primary_plane_atomic_update(struct drm_plane *plane,
 				    struct drm_plane_state *old_state)
@@ -373,8 +340,6 @@ static const struct
 drm_plane_helper_funcs vmw_ldu_primary_plane_helper_funcs = {
 	.atomic_check = vmw_du_primary_plane_atomic_check,
 	.atomic_update = vmw_ldu_primary_plane_atomic_update,
-	.prepare_fb = vmw_ldu_primary_plane_prepare_fb,
-	.cleanup_fb = vmw_ldu_primary_plane_cleanup_fb,
 };
 
 static const struct drm_crtc_helper_funcs vmw_ldu_crtc_helper_funcs = {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index cdff99211602..21d746bdc922 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -329,8 +329,6 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
 	struct rpc_channel channel;
 	char *msg, *reply = NULL;
 	size_t reply_len = 0;
-	int ret = 0;
-
 
 	if (!vmw_msg_enabled)
 		return -ENODEV;
@@ -344,15 +342,14 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
 		return -ENOMEM;
 	}
 
-	if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM) ||
-	    vmw_send_msg(&channel, msg) ||
-	    vmw_recv_msg(&channel, (void *) &reply, &reply_len) ||
-	    vmw_close_channel(&channel)) {
-		DRM_ERROR("Failed to get %s", guest_info_param);
+	if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM))
+		goto out_open;
 
-		ret = -EINVAL;
-	}
+	if (vmw_send_msg(&channel, msg) ||
+	    vmw_recv_msg(&channel, (void *) &reply, &reply_len))
+		goto out_msg;
 
+	vmw_close_channel(&channel);
 	if (buffer && reply && reply_len > 0) {
 		/* Remove reply code, which are the first 2 characters of
 		 * the reply
@@ -369,7 +366,17 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
 	kfree(reply);
 	kfree(msg);
 
-	return ret;
+	return 0;
+
+out_msg:
+	vmw_close_channel(&channel);
+	kfree(reply);
+out_open:
+	*length = 0;
+	kfree(msg);
+	DRM_ERROR("Failed to get %s", guest_info_param);
+
+	return -EINVAL;
 }
 
 
@@ -400,15 +407,22 @@ int vmw_host_log(const char *log)
 		return -ENOMEM;
 	}
 
-	if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM) ||
-	    vmw_send_msg(&channel, msg) ||
-	    vmw_close_channel(&channel)) {
-		DRM_ERROR("Failed to send log\n");
+	if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM))
+		goto out_open;
 
-		ret = -EINVAL;
-	}
+	if (vmw_send_msg(&channel, msg))
+		goto out_msg;
 
+	vmw_close_channel(&channel);
 	kfree(msg);
 
-	return ret;
+	return 0;
+
+out_msg:
+	vmw_close_channel(&channel);
+out_open:
+	kfree(msg);
+	DRM_ERROR("Failed to send log\n");
+
+	return -EINVAL;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
index 557a033fb610..8545488aa0cf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
@@ -135,17 +135,24 @@
 
 #else
 
-/* In the 32-bit version of this macro, we use "m" because there is no
- * more register left for bp
+/*
+ * In the 32-bit version of this macro, we store bp in a memory location
+ * because we've ran out of registers.
+ * Now we can't reference that memory location while we've modified
+ * %esp or %ebp, so we first push it on the stack, just before we push
+ * %ebp, and then when we need it we read it from the stack where we
+ * just pushed it.
  */
 #define VMW_PORT_HB_OUT(cmd, in_ecx, in_si, in_di,	\
 			port_num, magic, bp,		\
 			eax, ebx, ecx, edx, si, di)	\
 ({							\
-	asm volatile ("push %%ebp;"			\
-		"mov %12, %%ebp;"			\
+	asm volatile ("push %12;"			\
+		"push %%ebp;"				\
+		"mov 0x04(%%esp), %%ebp;"		\
 		"rep outsb;"				\
-		"pop %%ebp;" :				\
+		"pop %%ebp;"				\
+		"add $0x04, %%esp;" :			\
 		"=a"(eax),				\
 		"=b"(ebx),				\
 		"=c"(ecx),				\
@@ -167,10 +174,12 @@
 		       port_num, magic, bp,		\
 		       eax, ebx, ecx, edx, si, di)	\
 ({							\
-	asm volatile ("push %%ebp;"			\
-		"mov %12, %%ebp;"			\
+	asm volatile ("push %12;"			\
+		"push %%ebp;"				\
+		"mov 0x04(%%esp), %%ebp;"		\
 		"rep insb;"				\
-		"pop %%ebp" :				\
+		"pop %%ebp;"				\
+		"add $0x04, %%esp;" :			\
 		"=a"(eax),				\
 		"=b"(ebx),				\
 		"=c"(ecx),				\
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 648f8127f65a..3d667e903beb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -482,6 +482,8 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 		return ret;
 	}
 
+	vps->dmabuf_size = size;
+
 	/*
 	 * TTM already thinks the buffer is pinned, but make sure the
 	 * pin_count is upped.
diff --git a/drivers/gpu/drm/xen/Kconfig b/drivers/gpu/drm/xen/Kconfig
new file mode 100644
index 000000000000..4cca160782ab
--- /dev/null
+++ b/drivers/gpu/drm/xen/Kconfig
@@ -0,0 +1,17 @@
+config DRM_XEN
+	bool "DRM Support for Xen guest OS"
+	depends on XEN
+	help
+	  Choose this option if you want to enable DRM support
+	  for Xen.
+
+config DRM_XEN_FRONTEND
+	tristate "Para-virtualized frontend driver for Xen guest OS"
+	depends on DRM_XEN
+	depends on DRM
+	select DRM_KMS_HELPER
+	select VIDEOMODE_HELPERS
+	select XEN_XENBUS_FRONTEND
+	help
+	  Choose this option if you want to enable a para-virtualized
+	  frontend DRM/KMS driver for Xen guest OSes.
diff --git a/drivers/gpu/drm/xen/Makefile b/drivers/gpu/drm/xen/Makefile
new file mode 100644
index 000000000000..712afff5ffc3
--- /dev/null
+++ b/drivers/gpu/drm/xen/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0 OR MIT
+
+drm_xen_front-objs := xen_drm_front.o \
+		      xen_drm_front_kms.o \
+		      xen_drm_front_conn.o \
+		      xen_drm_front_evtchnl.o \
+		      xen_drm_front_shbuf.o \
+		      xen_drm_front_cfg.o \
+		      xen_drm_front_gem.o
+
+obj-$(CONFIG_DRM_XEN_FRONTEND) += drm_xen_front.o
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
new file mode 100644
index 000000000000..b3786c1a4e80
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -0,0 +1,839 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem.h>
+
+#include <linux/of_device.h>
+
+#include <xen/platform_pci.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+
+#include <xen/interface/io/displif.h>
+
+#include "xen_drm_front.h"
+#include "xen_drm_front_cfg.h"
+#include "xen_drm_front_evtchnl.h"
+#include "xen_drm_front_gem.h"
+#include "xen_drm_front_kms.h"
+#include "xen_drm_front_shbuf.h"
+
+struct xen_drm_front_dbuf {
+	struct list_head list;
+	u64 dbuf_cookie;
+	u64 fb_cookie;
+	struct xen_drm_front_shbuf *shbuf;
+};
+
+static int dbuf_add_to_list(struct xen_drm_front_info *front_info,
+			    struct xen_drm_front_shbuf *shbuf, u64 dbuf_cookie)
+{
+	struct xen_drm_front_dbuf *dbuf;
+
+	dbuf = kzalloc(sizeof(*dbuf), GFP_KERNEL);
+	if (!dbuf)
+		return -ENOMEM;
+
+	dbuf->dbuf_cookie = dbuf_cookie;
+	dbuf->shbuf = shbuf;
+	list_add(&dbuf->list, &front_info->dbuf_list);
+	return 0;
+}
+
+static struct xen_drm_front_dbuf *dbuf_get(struct list_head *dbuf_list,
+					   u64 dbuf_cookie)
+{
+	struct xen_drm_front_dbuf *buf, *q;
+
+	list_for_each_entry_safe(buf, q, dbuf_list, list)
+		if (buf->dbuf_cookie == dbuf_cookie)
+			return buf;
+
+	return NULL;
+}
+
+static void dbuf_flush_fb(struct list_head *dbuf_list, u64 fb_cookie)
+{
+	struct xen_drm_front_dbuf *buf, *q;
+
+	list_for_each_entry_safe(buf, q, dbuf_list, list)
+		if (buf->fb_cookie == fb_cookie)
+			xen_drm_front_shbuf_flush(buf->shbuf);
+}
+
+static void dbuf_free(struct list_head *dbuf_list, u64 dbuf_cookie)
+{
+	struct xen_drm_front_dbuf *buf, *q;
+
+	list_for_each_entry_safe(buf, q, dbuf_list, list)
+		if (buf->dbuf_cookie == dbuf_cookie) {
+			list_del(&buf->list);
+			xen_drm_front_shbuf_unmap(buf->shbuf);
+			xen_drm_front_shbuf_free(buf->shbuf);
+			kfree(buf);
+			break;
+		}
+}
+
+static void dbuf_free_all(struct list_head *dbuf_list)
+{
+	struct xen_drm_front_dbuf *buf, *q;
+
+	list_for_each_entry_safe(buf, q, dbuf_list, list) {
+		list_del(&buf->list);
+		xen_drm_front_shbuf_unmap(buf->shbuf);
+		xen_drm_front_shbuf_free(buf->shbuf);
+		kfree(buf);
+	}
+}
+
+static struct xendispl_req *
+be_prepare_req(struct xen_drm_front_evtchnl *evtchnl, u8 operation)
+{
+	struct xendispl_req *req;
+
+	req = RING_GET_REQUEST(&evtchnl->u.req.ring,
+			       evtchnl->u.req.ring.req_prod_pvt);
+	req->operation = operation;
+	req->id = evtchnl->evt_next_id++;
+	evtchnl->evt_id = req->id;
+	return req;
+}
+
+static int be_stream_do_io(struct xen_drm_front_evtchnl *evtchnl,
+			   struct xendispl_req *req)
+{
+	reinit_completion(&evtchnl->u.req.completion);
+	if (unlikely(evtchnl->state != EVTCHNL_STATE_CONNECTED))
+		return -EIO;
+
+	xen_drm_front_evtchnl_flush(evtchnl);
+	return 0;
+}
+
+static int be_stream_wait_io(struct xen_drm_front_evtchnl *evtchnl)
+{
+	if (wait_for_completion_timeout(&evtchnl->u.req.completion,
+			msecs_to_jiffies(XEN_DRM_FRONT_WAIT_BACK_MS)) <= 0)
+		return -ETIMEDOUT;
+
+	return evtchnl->u.req.resp_status;
+}
+
+int xen_drm_front_mode_set(struct xen_drm_front_drm_pipeline *pipeline,
+			   u32 x, u32 y, u32 width, u32 height,
+			   u32 bpp, u64 fb_cookie)
+{
+	struct xen_drm_front_evtchnl *evtchnl;
+	struct xen_drm_front_info *front_info;
+	struct xendispl_req *req;
+	unsigned long flags;
+	int ret;
+
+	front_info = pipeline->drm_info->front_info;
+	evtchnl = &front_info->evt_pairs[pipeline->index].req;
+	if (unlikely(!evtchnl))
+		return -EIO;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+	req = be_prepare_req(evtchnl, XENDISPL_OP_SET_CONFIG);
+	req->op.set_config.x = x;
+	req->op.set_config.y = y;
+	req->op.set_config.width = width;
+	req->op.set_config.height = height;
+	req->op.set_config.bpp = bpp;
+	req->op.set_config.fb_cookie = fb_cookie;
+
+	ret = be_stream_do_io(evtchnl, req);
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_drm_front_dbuf_create(struct xen_drm_front_info *front_info,
+			      u64 dbuf_cookie, u32 width, u32 height,
+			      u32 bpp, u64 size, struct page **pages)
+{
+	struct xen_drm_front_evtchnl *evtchnl;
+	struct xen_drm_front_shbuf *shbuf;
+	struct xendispl_req *req;
+	struct xen_drm_front_shbuf_cfg buf_cfg;
+	unsigned long flags;
+	int ret;
+
+	evtchnl = &front_info->evt_pairs[GENERIC_OP_EVT_CHNL].req;
+	if (unlikely(!evtchnl))
+		return -EIO;
+
+	memset(&buf_cfg, 0, sizeof(buf_cfg));
+	buf_cfg.xb_dev = front_info->xb_dev;
+	buf_cfg.pages = pages;
+	buf_cfg.size = size;
+	buf_cfg.be_alloc = front_info->cfg.be_alloc;
+
+	shbuf = xen_drm_front_shbuf_alloc(&buf_cfg);
+	if (IS_ERR(shbuf))
+		return PTR_ERR(shbuf);
+
+	ret = dbuf_add_to_list(front_info, shbuf, dbuf_cookie);
+	if (ret < 0) {
+		xen_drm_front_shbuf_free(shbuf);
+		return ret;
+	}
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+	req = be_prepare_req(evtchnl, XENDISPL_OP_DBUF_CREATE);
+	req->op.dbuf_create.gref_directory =
+			xen_drm_front_shbuf_get_dir_start(shbuf);
+	req->op.dbuf_create.buffer_sz = size;
+	req->op.dbuf_create.dbuf_cookie = dbuf_cookie;
+	req->op.dbuf_create.width = width;
+	req->op.dbuf_create.height = height;
+	req->op.dbuf_create.bpp = bpp;
+	if (buf_cfg.be_alloc)
+		req->op.dbuf_create.flags |= XENDISPL_DBUF_FLG_REQ_ALLOC;
+
+	ret = be_stream_do_io(evtchnl, req);
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+
+	if (ret < 0)
+		goto fail;
+
+	ret = be_stream_wait_io(evtchnl);
+	if (ret < 0)
+		goto fail;
+
+	ret = xen_drm_front_shbuf_map(shbuf);
+	if (ret < 0)
+		goto fail;
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return 0;
+
+fail:
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	dbuf_free(&front_info->dbuf_list, dbuf_cookie);
+	return ret;
+}
+
+static int xen_drm_front_dbuf_destroy(struct xen_drm_front_info *front_info,
+				      u64 dbuf_cookie)
+{
+	struct xen_drm_front_evtchnl *evtchnl;
+	struct xendispl_req *req;
+	unsigned long flags;
+	bool be_alloc;
+	int ret;
+
+	evtchnl = &front_info->evt_pairs[GENERIC_OP_EVT_CHNL].req;
+	if (unlikely(!evtchnl))
+		return -EIO;
+
+	be_alloc = front_info->cfg.be_alloc;
+
+	/*
+	 * For the backend allocated buffer release references now, so backend
+	 * can free the buffer.
+	 */
+	if (be_alloc)
+		dbuf_free(&front_info->dbuf_list, dbuf_cookie);
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+	req = be_prepare_req(evtchnl, XENDISPL_OP_DBUF_DESTROY);
+	req->op.dbuf_destroy.dbuf_cookie = dbuf_cookie;
+
+	ret = be_stream_do_io(evtchnl, req);
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	/*
+	 * Do this regardless of communication status with the backend:
+	 * if we cannot remove remote resources remove what we can locally.
+	 */
+	if (!be_alloc)
+		dbuf_free(&front_info->dbuf_list, dbuf_cookie);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_drm_front_fb_attach(struct xen_drm_front_info *front_info,
+			    u64 dbuf_cookie, u64 fb_cookie, u32 width,
+			    u32 height, u32 pixel_format)
+{
+	struct xen_drm_front_evtchnl *evtchnl;
+	struct xen_drm_front_dbuf *buf;
+	struct xendispl_req *req;
+	unsigned long flags;
+	int ret;
+
+	evtchnl = &front_info->evt_pairs[GENERIC_OP_EVT_CHNL].req;
+	if (unlikely(!evtchnl))
+		return -EIO;
+
+	buf = dbuf_get(&front_info->dbuf_list, dbuf_cookie);
+	if (!buf)
+		return -EINVAL;
+
+	buf->fb_cookie = fb_cookie;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+	req = be_prepare_req(evtchnl, XENDISPL_OP_FB_ATTACH);
+	req->op.fb_attach.dbuf_cookie = dbuf_cookie;
+	req->op.fb_attach.fb_cookie = fb_cookie;
+	req->op.fb_attach.width = width;
+	req->op.fb_attach.height = height;
+	req->op.fb_attach.pixel_format = pixel_format;
+
+	ret = be_stream_do_io(evtchnl, req);
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_drm_front_fb_detach(struct xen_drm_front_info *front_info,
+			    u64 fb_cookie)
+{
+	struct xen_drm_front_evtchnl *evtchnl;
+	struct xendispl_req *req;
+	unsigned long flags;
+	int ret;
+
+	evtchnl = &front_info->evt_pairs[GENERIC_OP_EVT_CHNL].req;
+	if (unlikely(!evtchnl))
+		return -EIO;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+	req = be_prepare_req(evtchnl, XENDISPL_OP_FB_DETACH);
+	req->op.fb_detach.fb_cookie = fb_cookie;
+
+	ret = be_stream_do_io(evtchnl, req);
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_drm_front_page_flip(struct xen_drm_front_info *front_info,
+			    int conn_idx, u64 fb_cookie)
+{
+	struct xen_drm_front_evtchnl *evtchnl;
+	struct xendispl_req *req;
+	unsigned long flags;
+	int ret;
+
+	if (unlikely(conn_idx >= front_info->num_evt_pairs))
+		return -EINVAL;
+
+	dbuf_flush_fb(&front_info->dbuf_list, fb_cookie);
+	evtchnl = &front_info->evt_pairs[conn_idx].req;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+	req = be_prepare_req(evtchnl, XENDISPL_OP_PG_FLIP);
+	req->op.pg_flip.fb_cookie = fb_cookie;
+
+	ret = be_stream_do_io(evtchnl, req);
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+void xen_drm_front_on_frame_done(struct xen_drm_front_info *front_info,
+				 int conn_idx, u64 fb_cookie)
+{
+	struct xen_drm_front_drm_info *drm_info = front_info->drm_info;
+
+	if (unlikely(conn_idx >= front_info->cfg.num_connectors))
+		return;
+
+	xen_drm_front_kms_on_frame_done(&drm_info->pipeline[conn_idx],
+					fb_cookie);
+}
+
+static int xen_drm_drv_dumb_create(struct drm_file *filp,
+				   struct drm_device *dev,
+				   struct drm_mode_create_dumb *args)
+{
+	struct xen_drm_front_drm_info *drm_info = dev->dev_private;
+	struct drm_gem_object *obj;
+	int ret;
+
+	/*
+	 * Dumb creation is a two stage process: first we create a fully
+	 * constructed GEM object which is communicated to the backend, and
+	 * only after that we can create GEM's handle. This is done so,
+	 * because of the possible races: once you create a handle it becomes
+	 * immediately visible to user-space, so the latter can try accessing
+	 * object without pages etc.
+	 * For details also see drm_gem_handle_create
+	 */
+	args->pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+	args->size = args->pitch * args->height;
+
+	obj = xen_drm_front_gem_create(dev, args->size);
+	if (IS_ERR_OR_NULL(obj)) {
+		ret = PTR_ERR(obj);
+		goto fail;
+	}
+
+	ret = xen_drm_front_dbuf_create(drm_info->front_info,
+					xen_drm_front_dbuf_to_cookie(obj),
+					args->width, args->height, args->bpp,
+					args->size,
+					xen_drm_front_gem_get_pages(obj));
+	if (ret)
+		goto fail_backend;
+
+	/* This is the tail of GEM object creation */
+	ret = drm_gem_handle_create(filp, obj, &args->handle);
+	if (ret)
+		goto fail_handle;
+
+	/* Drop reference from allocate - handle holds it now */
+	drm_gem_object_put_unlocked(obj);
+	return 0;
+
+fail_handle:
+	xen_drm_front_dbuf_destroy(drm_info->front_info,
+				   xen_drm_front_dbuf_to_cookie(obj));
+fail_backend:
+	/* drop reference from allocate */
+	drm_gem_object_put_unlocked(obj);
+fail:
+	DRM_ERROR("Failed to create dumb buffer: %d\n", ret);
+	return ret;
+}
+
+static void xen_drm_drv_free_object_unlocked(struct drm_gem_object *obj)
+{
+	struct xen_drm_front_drm_info *drm_info = obj->dev->dev_private;
+	int idx;
+
+	if (drm_dev_enter(obj->dev, &idx)) {
+		xen_drm_front_dbuf_destroy(drm_info->front_info,
+					   xen_drm_front_dbuf_to_cookie(obj));
+		drm_dev_exit(idx);
+	} else {
+		dbuf_free(&drm_info->front_info->dbuf_list,
+			  xen_drm_front_dbuf_to_cookie(obj));
+	}
+
+	xen_drm_front_gem_free_object_unlocked(obj);
+}
+
+static void xen_drm_drv_release(struct drm_device *dev)
+{
+	struct xen_drm_front_drm_info *drm_info = dev->dev_private;
+	struct xen_drm_front_info *front_info = drm_info->front_info;
+
+	xen_drm_front_kms_fini(drm_info);
+
+	drm_atomic_helper_shutdown(dev);
+	drm_mode_config_cleanup(dev);
+
+	drm_dev_fini(dev);
+	kfree(dev);
+
+	if (front_info->cfg.be_alloc)
+		xenbus_switch_state(front_info->xb_dev,
+				    XenbusStateInitialising);
+
+	kfree(drm_info);
+}
+
+static const struct file_operations xen_drm_dev_fops = {
+	.owner          = THIS_MODULE,
+	.open           = drm_open,
+	.release        = drm_release,
+	.unlocked_ioctl = drm_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = drm_compat_ioctl,
+#endif
+	.poll           = drm_poll,
+	.read           = drm_read,
+	.llseek         = no_llseek,
+	.mmap           = xen_drm_front_gem_mmap,
+};
+
+static const struct vm_operations_struct xen_drm_drv_vm_ops = {
+	.open           = drm_gem_vm_open,
+	.close          = drm_gem_vm_close,
+};
+
+static struct drm_driver xen_drm_driver = {
+	.driver_features           = DRIVER_GEM | DRIVER_MODESET |
+				     DRIVER_PRIME | DRIVER_ATOMIC,
+	.release                   = xen_drm_drv_release,
+	.gem_vm_ops                = &xen_drm_drv_vm_ops,
+	.gem_free_object_unlocked  = xen_drm_drv_free_object_unlocked,
+	.prime_handle_to_fd        = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle        = drm_gem_prime_fd_to_handle,
+	.gem_prime_import          = drm_gem_prime_import,
+	.gem_prime_export          = drm_gem_prime_export,
+	.gem_prime_import_sg_table = xen_drm_front_gem_import_sg_table,
+	.gem_prime_get_sg_table    = xen_drm_front_gem_get_sg_table,
+	.gem_prime_vmap            = xen_drm_front_gem_prime_vmap,
+	.gem_prime_vunmap          = xen_drm_front_gem_prime_vunmap,
+	.gem_prime_mmap            = xen_drm_front_gem_prime_mmap,
+	.dumb_create               = xen_drm_drv_dumb_create,
+	.fops                      = &xen_drm_dev_fops,
+	.name                      = "xendrm-du",
+	.desc                      = "Xen PV DRM Display Unit",
+	.date                      = "20180221",
+	.major                     = 1,
+	.minor                     = 0,
+
+};
+
+static int xen_drm_drv_init(struct xen_drm_front_info *front_info)
+{
+	struct device *dev = &front_info->xb_dev->dev;
+	struct xen_drm_front_drm_info *drm_info;
+	struct drm_device *drm_dev;
+	int ret;
+
+	DRM_INFO("Creating %s\n", xen_drm_driver.desc);
+
+	drm_info = kzalloc(sizeof(*drm_info), GFP_KERNEL);
+	if (!drm_info) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	drm_info->front_info = front_info;
+	front_info->drm_info = drm_info;
+
+	drm_dev = drm_dev_alloc(&xen_drm_driver, dev);
+	if (IS_ERR(drm_dev)) {
+		ret = PTR_ERR(drm_dev);
+		goto fail;
+	}
+
+	drm_info->drm_dev = drm_dev;
+
+	drm_dev->dev_private = drm_info;
+
+	ret = xen_drm_front_kms_init(drm_info);
+	if (ret) {
+		DRM_ERROR("Failed to initialize DRM/KMS, ret %d\n", ret);
+		goto fail_modeset;
+	}
+
+	ret = drm_dev_register(drm_dev, 0);
+	if (ret)
+		goto fail_register;
+
+	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n",
+		 xen_drm_driver.name, xen_drm_driver.major,
+		 xen_drm_driver.minor, xen_drm_driver.patchlevel,
+		 xen_drm_driver.date, drm_dev->primary->index);
+
+	return 0;
+
+fail_register:
+	drm_dev_unregister(drm_dev);
+fail_modeset:
+	drm_kms_helper_poll_fini(drm_dev);
+	drm_mode_config_cleanup(drm_dev);
+fail:
+	kfree(drm_info);
+	return ret;
+}
+
+static void xen_drm_drv_fini(struct xen_drm_front_info *front_info)
+{
+	struct xen_drm_front_drm_info *drm_info = front_info->drm_info;
+	struct drm_device *dev;
+
+	if (!drm_info)
+		return;
+
+	dev = drm_info->drm_dev;
+	if (!dev)
+		return;
+
+	/* Nothing to do if device is already unplugged */
+	if (drm_dev_is_unplugged(dev))
+		return;
+
+	drm_kms_helper_poll_fini(dev);
+	drm_dev_unplug(dev);
+
+	front_info->drm_info = NULL;
+
+	xen_drm_front_evtchnl_free_all(front_info);
+	dbuf_free_all(&front_info->dbuf_list);
+
+	/*
+	 * If we are not using backend allocated buffers, then tell the
+	 * backend we are ready to (re)initialize. Otherwise, wait for
+	 * drm_driver.release.
+	 */
+	if (!front_info->cfg.be_alloc)
+		xenbus_switch_state(front_info->xb_dev,
+				    XenbusStateInitialising);
+}
+
+static int displback_initwait(struct xen_drm_front_info *front_info)
+{
+	struct xen_drm_front_cfg *cfg = &front_info->cfg;
+	int ret;
+
+	cfg->front_info = front_info;
+	ret = xen_drm_front_cfg_card(front_info, cfg);
+	if (ret < 0)
+		return ret;
+
+	DRM_INFO("Have %d conector(s)\n", cfg->num_connectors);
+	/* Create event channels for all connectors and publish */
+	ret = xen_drm_front_evtchnl_create_all(front_info);
+	if (ret < 0)
+		return ret;
+
+	return xen_drm_front_evtchnl_publish_all(front_info);
+}
+
+static int displback_connect(struct xen_drm_front_info *front_info)
+{
+	xen_drm_front_evtchnl_set_state(front_info, EVTCHNL_STATE_CONNECTED);
+	return xen_drm_drv_init(front_info);
+}
+
+static void displback_disconnect(struct xen_drm_front_info *front_info)
+{
+	if (!front_info->drm_info)
+		return;
+
+	/* Tell the backend to wait until we release the DRM driver. */
+	xenbus_switch_state(front_info->xb_dev, XenbusStateReconfiguring);
+
+	xen_drm_drv_fini(front_info);
+}
+
+static void displback_changed(struct xenbus_device *xb_dev,
+			      enum xenbus_state backend_state)
+{
+	struct xen_drm_front_info *front_info = dev_get_drvdata(&xb_dev->dev);
+	int ret;
+
+	DRM_DEBUG("Backend state is %s, front is %s\n",
+		  xenbus_strstate(backend_state),
+		  xenbus_strstate(xb_dev->state));
+
+	switch (backend_state) {
+	case XenbusStateReconfiguring:
+		/* fall through */
+	case XenbusStateReconfigured:
+		/* fall through */
+	case XenbusStateInitialised:
+		break;
+
+	case XenbusStateInitialising:
+		if (xb_dev->state == XenbusStateReconfiguring)
+			break;
+
+		/* recovering after backend unexpected closure */
+		displback_disconnect(front_info);
+		break;
+
+	case XenbusStateInitWait:
+		if (xb_dev->state == XenbusStateReconfiguring)
+			break;
+
+		/* recovering after backend unexpected closure */
+		displback_disconnect(front_info);
+		if (xb_dev->state != XenbusStateInitialising)
+			break;
+
+		ret = displback_initwait(front_info);
+		if (ret < 0)
+			xenbus_dev_fatal(xb_dev, ret, "initializing frontend");
+		else
+			xenbus_switch_state(xb_dev, XenbusStateInitialised);
+		break;
+
+	case XenbusStateConnected:
+		if (xb_dev->state != XenbusStateInitialised)
+			break;
+
+		ret = displback_connect(front_info);
+		if (ret < 0) {
+			displback_disconnect(front_info);
+			xenbus_dev_fatal(xb_dev, ret, "connecting backend");
+		} else {
+			xenbus_switch_state(xb_dev, XenbusStateConnected);
+		}
+		break;
+
+	case XenbusStateClosing:
+		/*
+		 * in this state backend starts freeing resources,
+		 * so let it go into closed state, so we can also
+		 * remove ours
+		 */
+		break;
+
+	case XenbusStateUnknown:
+		/* fall through */
+	case XenbusStateClosed:
+		if (xb_dev->state == XenbusStateClosed)
+			break;
+
+		displback_disconnect(front_info);
+		break;
+	}
+}
+
+static int xen_drv_probe(struct xenbus_device *xb_dev,
+			 const struct xenbus_device_id *id)
+{
+	struct xen_drm_front_info *front_info;
+	struct device *dev = &xb_dev->dev;
+	int ret;
+
+	/*
+	 * The device is not spawn from a device tree, so arch_setup_dma_ops
+	 * is not called, thus leaving the device with dummy DMA ops.
+	 * This makes the device return error on PRIME buffer import, which
+	 * is not correct: to fix this call of_dma_configure() with a NULL
+	 * node to set default DMA ops.
+	 */
+	dev->coherent_dma_mask = DMA_BIT_MASK(32);
+	ret = of_dma_configure(dev, NULL, true);
+	if (ret < 0) {
+		DRM_ERROR("Cannot setup DMA ops, ret %d", ret);
+		return ret;
+	}
+
+	front_info = devm_kzalloc(&xb_dev->dev,
+				  sizeof(*front_info), GFP_KERNEL);
+	if (!front_info)
+		return -ENOMEM;
+
+	front_info->xb_dev = xb_dev;
+	spin_lock_init(&front_info->io_lock);
+	INIT_LIST_HEAD(&front_info->dbuf_list);
+	dev_set_drvdata(&xb_dev->dev, front_info);
+
+	return xenbus_switch_state(xb_dev, XenbusStateInitialising);
+}
+
+static int xen_drv_remove(struct xenbus_device *dev)
+{
+	struct xen_drm_front_info *front_info = dev_get_drvdata(&dev->dev);
+	int to = 100;
+
+	xenbus_switch_state(dev, XenbusStateClosing);
+
+	/*
+	 * On driver removal it is disconnected from XenBus,
+	 * so no backend state change events come via .otherend_changed
+	 * callback. This prevents us from exiting gracefully, e.g.
+	 * signaling the backend to free event channels, waiting for its
+	 * state to change to XenbusStateClosed and cleaning at our end.
+	 * Normally when front driver removed backend will finally go into
+	 * XenbusStateInitWait state.
+	 *
+	 * Workaround: read backend's state manually and wait with time-out.
+	 */
+	while ((xenbus_read_unsigned(front_info->xb_dev->otherend, "state",
+				     XenbusStateUnknown) != XenbusStateInitWait) &&
+				     --to)
+		msleep(10);
+
+	if (!to) {
+		unsigned int state;
+
+		state = xenbus_read_unsigned(front_info->xb_dev->otherend,
+					     "state", XenbusStateUnknown);
+		DRM_ERROR("Backend state is %s while removing driver\n",
+			  xenbus_strstate(state));
+	}
+
+	xen_drm_drv_fini(front_info);
+	xenbus_frontend_closed(dev);
+	return 0;
+}
+
+static const struct xenbus_device_id xen_driver_ids[] = {
+	{ XENDISPL_DRIVER_NAME },
+	{ "" }
+};
+
+static struct xenbus_driver xen_driver = {
+	.ids = xen_driver_ids,
+	.probe = xen_drv_probe,
+	.remove = xen_drv_remove,
+	.otherend_changed = displback_changed,
+};
+
+static int __init xen_drv_init(void)
+{
+	/* At the moment we only support case with XEN_PAGE_SIZE == PAGE_SIZE */
+	if (XEN_PAGE_SIZE != PAGE_SIZE) {
+		DRM_ERROR(XENDISPL_DRIVER_NAME ": different kernel and Xen page sizes are not supported: XEN_PAGE_SIZE (%lu) != PAGE_SIZE (%lu)\n",
+			  XEN_PAGE_SIZE, PAGE_SIZE);
+		return -ENODEV;
+	}
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
+	DRM_INFO("Registering XEN PV " XENDISPL_DRIVER_NAME "\n");
+	return xenbus_register_frontend(&xen_driver);
+}
+
+static void __exit xen_drv_fini(void)
+{
+	DRM_INFO("Unregistering XEN PV " XENDISPL_DRIVER_NAME "\n");
+	xenbus_unregister_driver(&xen_driver);
+}
+
+module_init(xen_drv_init);
+module_exit(xen_drv_fini);
+
+MODULE_DESCRIPTION("Xen para-virtualized display device frontend");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:" XENDISPL_DRIVER_NAME);
diff --git a/drivers/gpu/drm/xen/xen_drm_front.h b/drivers/gpu/drm/xen/xen_drm_front.h
new file mode 100644
index 000000000000..2c2479b571ae
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_DRM_FRONT_H_
+#define __XEN_DRM_FRONT_H_
+
+#include <drm/drmP.h>
+#include <drm/drm_simple_kms_helper.h>
+
+#include <linux/scatterlist.h>
+
+#include "xen_drm_front_cfg.h"
+
+/**
+ * DOC: Driver modes of operation in terms of display buffers used
+ *
+ * Depending on the requirements for the para-virtualized environment, namely
+ * requirements dictated by the accompanying DRM/(v)GPU drivers running in both
+ * host and guest environments, display buffers can be allocated by either
+ * frontend driver or backend.
+ */
+
+/**
+ * DOC: Buffers allocated by the frontend driver
+ *
+ * In this mode of operation driver allocates buffers from system memory.
+ *
+ * Note! If used with accompanying DRM/(v)GPU drivers this mode of operation
+ * may require IOMMU support on the platform, so accompanying DRM/vGPU
+ * hardware can still reach display buffer memory while importing PRIME
+ * buffers from the frontend driver.
+ */
+
+/**
+ * DOC: Buffers allocated by the backend
+ *
+ * This mode of operation is run-time configured via guest domain configuration
+ * through XenStore entries.
+ *
+ * For systems which do not provide IOMMU support, but having specific
+ * requirements for display buffers it is possible to allocate such buffers
+ * at backend side and share those with the frontend.
+ * For example, if host domain is 1:1 mapped and has DRM/GPU hardware expecting
+ * physically contiguous memory, this allows implementing zero-copying
+ * use-cases.
+ *
+ * Note, while using this scenario the following should be considered:
+ *
+ * #. If guest domain dies then pages/grants received from the backend
+ *    cannot be claimed back
+ *
+ * #. Misbehaving guest may send too many requests to the
+ *    backend exhausting its grant references and memory
+ *    (consider this from security POV)
+ */
+
+/**
+ * DOC: Driver limitations
+ *
+ * #. Only primary plane without additional properties is supported.
+ *
+ * #. Only one video mode per connector supported which is configured
+ *    via XenStore.
+ *
+ * #. All CRTCs operate at fixed frequency of 60Hz.
+ */
+
+/* timeout in ms to wait for backend to respond */
+#define XEN_DRM_FRONT_WAIT_BACK_MS	3000
+
+#ifndef GRANT_INVALID_REF
+/*
+ * Note on usage of grant reference 0 as invalid grant reference:
+ * grant reference 0 is valid, but never exposed to a PV driver,
+ * because of the fact it is already in use/reserved by the PV console.
+ */
+#define GRANT_INVALID_REF	0
+#endif
+
+struct xen_drm_front_info {
+	struct xenbus_device *xb_dev;
+	struct xen_drm_front_drm_info *drm_info;
+
+	/* to protect data between backend IO code and interrupt handler */
+	spinlock_t io_lock;
+
+	int num_evt_pairs;
+	struct xen_drm_front_evtchnl_pair *evt_pairs;
+	struct xen_drm_front_cfg cfg;
+
+	/* display buffers */
+	struct list_head dbuf_list;
+};
+
+struct xen_drm_front_drm_pipeline {
+	struct xen_drm_front_drm_info *drm_info;
+
+	int index;
+
+	struct drm_simple_display_pipe pipe;
+
+	struct drm_connector conn;
+	/* These are only for connector mode checking */
+	int width, height;
+
+	struct drm_pending_vblank_event *pending_event;
+
+	struct delayed_work pflip_to_worker;
+
+	bool conn_connected;
+};
+
+struct xen_drm_front_drm_info {
+	struct xen_drm_front_info *front_info;
+	struct drm_device *drm_dev;
+
+	struct xen_drm_front_drm_pipeline pipeline[XEN_DRM_FRONT_MAX_CRTCS];
+};
+
+static inline u64 xen_drm_front_fb_to_cookie(struct drm_framebuffer *fb)
+{
+	return (u64)fb;
+}
+
+static inline u64 xen_drm_front_dbuf_to_cookie(struct drm_gem_object *gem_obj)
+{
+	return (u64)gem_obj;
+}
+
+int xen_drm_front_mode_set(struct xen_drm_front_drm_pipeline *pipeline,
+			   u32 x, u32 y, u32 width, u32 height,
+			   u32 bpp, u64 fb_cookie);
+
+int xen_drm_front_dbuf_create(struct xen_drm_front_info *front_info,
+			      u64 dbuf_cookie, u32 width, u32 height,
+			      u32 bpp, u64 size, struct page **pages);
+
+int xen_drm_front_fb_attach(struct xen_drm_front_info *front_info,
+			    u64 dbuf_cookie, u64 fb_cookie, u32 width,
+			    u32 height, u32 pixel_format);
+
+int xen_drm_front_fb_detach(struct xen_drm_front_info *front_info,
+			    u64 fb_cookie);
+
+int xen_drm_front_page_flip(struct xen_drm_front_info *front_info,
+			    int conn_idx, u64 fb_cookie);
+
+void xen_drm_front_on_frame_done(struct xen_drm_front_info *front_info,
+				 int conn_idx, u64 fb_cookie);
+
+#endif /* __XEN_DRM_FRONT_H_ */
diff --git a/drivers/gpu/drm/xen/xen_drm_front_cfg.c b/drivers/gpu/drm/xen/xen_drm_front_cfg.c
new file mode 100644
index 000000000000..5baf2b9de93c
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_cfg.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <drm/drmP.h>
+
+#include <linux/device.h>
+
+#include <xen/interface/io/displif.h>
+#include <xen/xenbus.h>
+
+#include "xen_drm_front.h"
+#include "xen_drm_front_cfg.h"
+
+static int cfg_connector(struct xen_drm_front_info *front_info,
+			 struct xen_drm_front_cfg_connector *connector,
+			 const char *path, int index)
+{
+	char *connector_path;
+
+	connector_path = devm_kasprintf(&front_info->xb_dev->dev,
+					GFP_KERNEL, "%s/%d", path, index);
+	if (!connector_path)
+		return -ENOMEM;
+
+	if (xenbus_scanf(XBT_NIL, connector_path, XENDISPL_FIELD_RESOLUTION,
+			 "%d" XENDISPL_RESOLUTION_SEPARATOR "%d",
+			 &connector->width, &connector->height) < 0) {
+		/* either no entry configured or wrong resolution set */
+		connector->width = 0;
+		connector->height = 0;
+		return -EINVAL;
+	}
+
+	connector->xenstore_path = connector_path;
+
+	DRM_INFO("Connector %s: resolution %dx%d\n",
+		 connector_path, connector->width, connector->height);
+	return 0;
+}
+
+int xen_drm_front_cfg_card(struct xen_drm_front_info *front_info,
+			   struct xen_drm_front_cfg *cfg)
+{
+	struct xenbus_device *xb_dev = front_info->xb_dev;
+	int ret, i;
+
+	if (xenbus_read_unsigned(front_info->xb_dev->nodename,
+				 XENDISPL_FIELD_BE_ALLOC, 0)) {
+		DRM_INFO("Backend can provide display buffers\n");
+		cfg->be_alloc = true;
+	}
+
+	cfg->num_connectors = 0;
+	for (i = 0; i < ARRAY_SIZE(cfg->connectors); i++) {
+		ret = cfg_connector(front_info, &cfg->connectors[i],
+				    xb_dev->nodename, i);
+		if (ret < 0)
+			break;
+		cfg->num_connectors++;
+	}
+
+	if (!cfg->num_connectors) {
+		DRM_ERROR("No connector(s) configured at %s\n",
+			  xb_dev->nodename);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
diff --git a/drivers/gpu/drm/xen/xen_drm_front_cfg.h b/drivers/gpu/drm/xen/xen_drm_front_cfg.h
new file mode 100644
index 000000000000..aa8490ba9146
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_cfg.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_DRM_FRONT_CFG_H_
+#define __XEN_DRM_FRONT_CFG_H_
+
+#include <linux/types.h>
+
+#define XEN_DRM_FRONT_MAX_CRTCS	4
+
+struct xen_drm_front_cfg_connector {
+	int width;
+	int height;
+	char *xenstore_path;
+};
+
+struct xen_drm_front_cfg {
+	struct xen_drm_front_info *front_info;
+	/* number of connectors in this configuration */
+	int num_connectors;
+	/* connector configurations */
+	struct xen_drm_front_cfg_connector connectors[XEN_DRM_FRONT_MAX_CRTCS];
+	/* set if dumb buffers are allocated externally on backend side */
+	bool be_alloc;
+};
+
+int xen_drm_front_cfg_card(struct xen_drm_front_info *front_info,
+			   struct xen_drm_front_cfg *cfg);
+
+#endif /* __XEN_DRM_FRONT_CFG_H_ */
diff --git a/drivers/gpu/drm/xen/xen_drm_front_conn.c b/drivers/gpu/drm/xen/xen_drm_front_conn.c
new file mode 100644
index 000000000000..c91ae532fa55
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_conn.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+
+#include <video/videomode.h>
+
+#include "xen_drm_front.h"
+#include "xen_drm_front_conn.h"
+#include "xen_drm_front_kms.h"
+
+static struct xen_drm_front_drm_pipeline *
+to_xen_drm_pipeline(struct drm_connector *connector)
+{
+	return container_of(connector, struct xen_drm_front_drm_pipeline, conn);
+}
+
+static const u32 plane_formats[] = {
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB4444,
+	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ARGB1555,
+};
+
+const u32 *xen_drm_front_conn_get_formats(int *format_count)
+{
+	*format_count = ARRAY_SIZE(plane_formats);
+	return plane_formats;
+}
+
+static int connector_detect(struct drm_connector *connector,
+			    struct drm_modeset_acquire_ctx *ctx,
+			    bool force)
+{
+	struct xen_drm_front_drm_pipeline *pipeline =
+			to_xen_drm_pipeline(connector);
+
+	if (drm_dev_is_unplugged(connector->dev))
+		pipeline->conn_connected = false;
+
+	return pipeline->conn_connected ? connector_status_connected :
+			connector_status_disconnected;
+}
+
+#define XEN_DRM_CRTC_VREFRESH_HZ	60
+
+static int connector_get_modes(struct drm_connector *connector)
+{
+	struct xen_drm_front_drm_pipeline *pipeline =
+			to_xen_drm_pipeline(connector);
+	struct drm_display_mode *mode;
+	struct videomode videomode;
+	int width, height;
+
+	mode = drm_mode_create(connector->dev);
+	if (!mode)
+		return 0;
+
+	memset(&videomode, 0, sizeof(videomode));
+	videomode.hactive = pipeline->width;
+	videomode.vactive = pipeline->height;
+	width = videomode.hactive + videomode.hfront_porch +
+			videomode.hback_porch + videomode.hsync_len;
+	height = videomode.vactive + videomode.vfront_porch +
+			videomode.vback_porch + videomode.vsync_len;
+	videomode.pixelclock = width * height * XEN_DRM_CRTC_VREFRESH_HZ;
+	mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER;
+
+	drm_display_mode_from_videomode(&videomode, mode);
+	drm_mode_probed_add(connector, mode);
+	return 1;
+}
+
+static const struct drm_connector_helper_funcs connector_helper_funcs = {
+	.get_modes = connector_get_modes,
+	.detect_ctx = connector_detect,
+};
+
+static const struct drm_connector_funcs connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info,
+			    struct drm_connector *connector)
+{
+	struct xen_drm_front_drm_pipeline *pipeline =
+			to_xen_drm_pipeline(connector);
+
+	drm_connector_helper_add(connector, &connector_helper_funcs);
+
+	pipeline->conn_connected = true;
+
+	connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			DRM_CONNECTOR_POLL_DISCONNECT;
+
+	return drm_connector_init(drm_info->drm_dev, connector,
+				  &connector_funcs, DRM_MODE_CONNECTOR_VIRTUAL);
+}
diff --git a/drivers/gpu/drm/xen/xen_drm_front_conn.h b/drivers/gpu/drm/xen/xen_drm_front_conn.h
new file mode 100644
index 000000000000..39de7cf5adbe
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_conn.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_DRM_FRONT_CONN_H_
+#define __XEN_DRM_FRONT_CONN_H_
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_encoder.h>
+
+#include <linux/wait.h>
+
+struct xen_drm_front_drm_info;
+
+int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info,
+			    struct drm_connector *connector);
+
+const u32 *xen_drm_front_conn_get_formats(int *format_count);
+
+#endif /* __XEN_DRM_FRONT_CONN_H_ */
diff --git a/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c
new file mode 100644
index 000000000000..945226a95e9b
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <drm/drmP.h>
+
+#include <linux/errno.h>
+#include <linux/irq.h>
+
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+
+#include "xen_drm_front.h"
+#include "xen_drm_front_evtchnl.h"
+
+static irqreturn_t evtchnl_interrupt_ctrl(int irq, void *dev_id)
+{
+	struct xen_drm_front_evtchnl *evtchnl = dev_id;
+	struct xen_drm_front_info *front_info = evtchnl->front_info;
+	struct xendispl_resp *resp;
+	RING_IDX i, rp;
+	unsigned long flags;
+
+	if (unlikely(evtchnl->state != EVTCHNL_STATE_CONNECTED))
+		return IRQ_HANDLED;
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+
+again:
+	rp = evtchnl->u.req.ring.sring->rsp_prod;
+	/* ensure we see queued responses up to rp */
+	virt_rmb();
+
+	for (i = evtchnl->u.req.ring.rsp_cons; i != rp; i++) {
+		resp = RING_GET_RESPONSE(&evtchnl->u.req.ring, i);
+		if (unlikely(resp->id != evtchnl->evt_id))
+			continue;
+
+		switch (resp->operation) {
+		case XENDISPL_OP_PG_FLIP:
+		case XENDISPL_OP_FB_ATTACH:
+		case XENDISPL_OP_FB_DETACH:
+		case XENDISPL_OP_DBUF_CREATE:
+		case XENDISPL_OP_DBUF_DESTROY:
+		case XENDISPL_OP_SET_CONFIG:
+			evtchnl->u.req.resp_status = resp->status;
+			complete(&evtchnl->u.req.completion);
+			break;
+
+		default:
+			DRM_ERROR("Operation %d is not supported\n",
+				  resp->operation);
+			break;
+		}
+	}
+
+	evtchnl->u.req.ring.rsp_cons = i;
+
+	if (i != evtchnl->u.req.ring.req_prod_pvt) {
+		int more_to_do;
+
+		RING_FINAL_CHECK_FOR_RESPONSES(&evtchnl->u.req.ring,
+					       more_to_do);
+		if (more_to_do)
+			goto again;
+	} else {
+		evtchnl->u.req.ring.sring->rsp_event = i + 1;
+	}
+
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t evtchnl_interrupt_evt(int irq, void *dev_id)
+{
+	struct xen_drm_front_evtchnl *evtchnl = dev_id;
+	struct xen_drm_front_info *front_info = evtchnl->front_info;
+	struct xendispl_event_page *page = evtchnl->u.evt.page;
+	u32 cons, prod;
+	unsigned long flags;
+
+	if (unlikely(evtchnl->state != EVTCHNL_STATE_CONNECTED))
+		return IRQ_HANDLED;
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+
+	prod = page->in_prod;
+	/* ensure we see ring contents up to prod */
+	virt_rmb();
+	if (prod == page->in_cons)
+		goto out;
+
+	for (cons = page->in_cons; cons != prod; cons++) {
+		struct xendispl_evt *event;
+
+		event = &XENDISPL_IN_RING_REF(page, cons);
+		if (unlikely(event->id != evtchnl->evt_id++))
+			continue;
+
+		switch (event->type) {
+		case XENDISPL_EVT_PG_FLIP:
+			xen_drm_front_on_frame_done(front_info, evtchnl->index,
+						    event->op.pg_flip.fb_cookie);
+			break;
+		}
+	}
+	page->in_cons = cons;
+	/* ensure ring contents */
+	virt_wmb();
+
+out:
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+	return IRQ_HANDLED;
+}
+
+static void evtchnl_free(struct xen_drm_front_info *front_info,
+			 struct xen_drm_front_evtchnl *evtchnl)
+{
+	unsigned long page = 0;
+
+	if (evtchnl->type == EVTCHNL_TYPE_REQ)
+		page = (unsigned long)evtchnl->u.req.ring.sring;
+	else if (evtchnl->type == EVTCHNL_TYPE_EVT)
+		page = (unsigned long)evtchnl->u.evt.page;
+	if (!page)
+		return;
+
+	evtchnl->state = EVTCHNL_STATE_DISCONNECTED;
+
+	if (evtchnl->type == EVTCHNL_TYPE_REQ) {
+		/* release all who still waits for response if any */
+		evtchnl->u.req.resp_status = -EIO;
+		complete_all(&evtchnl->u.req.completion);
+	}
+
+	if (evtchnl->irq)
+		unbind_from_irqhandler(evtchnl->irq, evtchnl);
+
+	if (evtchnl->port)
+		xenbus_free_evtchn(front_info->xb_dev, evtchnl->port);
+
+	/* end access and free the page */
+	if (evtchnl->gref != GRANT_INVALID_REF)
+		gnttab_end_foreign_access(evtchnl->gref, 0, page);
+
+	memset(evtchnl, 0, sizeof(*evtchnl));
+}
+
+static int evtchnl_alloc(struct xen_drm_front_info *front_info, int index,
+			 struct xen_drm_front_evtchnl *evtchnl,
+			 enum xen_drm_front_evtchnl_type type)
+{
+	struct xenbus_device *xb_dev = front_info->xb_dev;
+	unsigned long page;
+	grant_ref_t gref;
+	irq_handler_t handler;
+	int ret;
+
+	memset(evtchnl, 0, sizeof(*evtchnl));
+	evtchnl->type = type;
+	evtchnl->index = index;
+	evtchnl->front_info = front_info;
+	evtchnl->state = EVTCHNL_STATE_DISCONNECTED;
+	evtchnl->gref = GRANT_INVALID_REF;
+
+	page = get_zeroed_page(GFP_NOIO | __GFP_HIGH);
+	if (!page) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	if (type == EVTCHNL_TYPE_REQ) {
+		struct xen_displif_sring *sring;
+
+		init_completion(&evtchnl->u.req.completion);
+		mutex_init(&evtchnl->u.req.req_io_lock);
+		sring = (struct xen_displif_sring *)page;
+		SHARED_RING_INIT(sring);
+		FRONT_RING_INIT(&evtchnl->u.req.ring, sring, XEN_PAGE_SIZE);
+
+		ret = xenbus_grant_ring(xb_dev, sring, 1, &gref);
+		if (ret < 0) {
+			evtchnl->u.req.ring.sring = NULL;
+			free_page(page);
+			goto fail;
+		}
+
+		handler = evtchnl_interrupt_ctrl;
+	} else {
+		ret = gnttab_grant_foreign_access(xb_dev->otherend_id,
+						  virt_to_gfn((void *)page), 0);
+		if (ret < 0) {
+			free_page(page);
+			goto fail;
+		}
+
+		evtchnl->u.evt.page = (struct xendispl_event_page *)page;
+		gref = ret;
+		handler = evtchnl_interrupt_evt;
+	}
+	evtchnl->gref = gref;
+
+	ret = xenbus_alloc_evtchn(xb_dev, &evtchnl->port);
+	if (ret < 0)
+		goto fail;
+
+	ret = bind_evtchn_to_irqhandler(evtchnl->port,
+					handler, 0, xb_dev->devicetype,
+					evtchnl);
+	if (ret < 0)
+		goto fail;
+
+	evtchnl->irq = ret;
+	return 0;
+
+fail:
+	DRM_ERROR("Failed to allocate ring: %d\n", ret);
+	return ret;
+}
+
+int xen_drm_front_evtchnl_create_all(struct xen_drm_front_info *front_info)
+{
+	struct xen_drm_front_cfg *cfg;
+	int ret, conn;
+
+	cfg = &front_info->cfg;
+
+	front_info->evt_pairs =
+			kcalloc(cfg->num_connectors,
+				sizeof(struct xen_drm_front_evtchnl_pair),
+				GFP_KERNEL);
+	if (!front_info->evt_pairs) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	for (conn = 0; conn < cfg->num_connectors; conn++) {
+		ret = evtchnl_alloc(front_info, conn,
+				    &front_info->evt_pairs[conn].req,
+				    EVTCHNL_TYPE_REQ);
+		if (ret < 0) {
+			DRM_ERROR("Error allocating control channel\n");
+			goto fail;
+		}
+
+		ret = evtchnl_alloc(front_info, conn,
+				    &front_info->evt_pairs[conn].evt,
+				    EVTCHNL_TYPE_EVT);
+		if (ret < 0) {
+			DRM_ERROR("Error allocating in-event channel\n");
+			goto fail;
+		}
+	}
+	front_info->num_evt_pairs = cfg->num_connectors;
+	return 0;
+
+fail:
+	xen_drm_front_evtchnl_free_all(front_info);
+	return ret;
+}
+
+static int evtchnl_publish(struct xenbus_transaction xbt,
+			   struct xen_drm_front_evtchnl *evtchnl,
+			   const char *path, const char *node_ring,
+			   const char *node_chnl)
+{
+	struct xenbus_device *xb_dev = evtchnl->front_info->xb_dev;
+	int ret;
+
+	/* write control channel ring reference */
+	ret = xenbus_printf(xbt, path, node_ring, "%u", evtchnl->gref);
+	if (ret < 0) {
+		xenbus_dev_error(xb_dev, ret, "writing ring-ref");
+		return ret;
+	}
+
+	/* write event channel ring reference */
+	ret = xenbus_printf(xbt, path, node_chnl, "%u", evtchnl->port);
+	if (ret < 0) {
+		xenbus_dev_error(xb_dev, ret, "writing event channel");
+		return ret;
+	}
+
+	return 0;
+}
+
+int xen_drm_front_evtchnl_publish_all(struct xen_drm_front_info *front_info)
+{
+	struct xenbus_transaction xbt;
+	struct xen_drm_front_cfg *plat_data;
+	int ret, conn;
+
+	plat_data = &front_info->cfg;
+
+again:
+	ret = xenbus_transaction_start(&xbt);
+	if (ret < 0) {
+		xenbus_dev_fatal(front_info->xb_dev, ret,
+				 "starting transaction");
+		return ret;
+	}
+
+	for (conn = 0; conn < plat_data->num_connectors; conn++) {
+		ret = evtchnl_publish(xbt, &front_info->evt_pairs[conn].req,
+				      plat_data->connectors[conn].xenstore_path,
+				      XENDISPL_FIELD_REQ_RING_REF,
+				      XENDISPL_FIELD_REQ_CHANNEL);
+		if (ret < 0)
+			goto fail;
+
+		ret = evtchnl_publish(xbt, &front_info->evt_pairs[conn].evt,
+				      plat_data->connectors[conn].xenstore_path,
+				      XENDISPL_FIELD_EVT_RING_REF,
+				      XENDISPL_FIELD_EVT_CHANNEL);
+		if (ret < 0)
+			goto fail;
+	}
+
+	ret = xenbus_transaction_end(xbt, 0);
+	if (ret < 0) {
+		if (ret == -EAGAIN)
+			goto again;
+
+		xenbus_dev_fatal(front_info->xb_dev, ret,
+				 "completing transaction");
+		goto fail_to_end;
+	}
+
+	return 0;
+
+fail:
+	xenbus_transaction_end(xbt, 1);
+
+fail_to_end:
+	xenbus_dev_fatal(front_info->xb_dev, ret, "writing Xen store");
+	return ret;
+}
+
+void xen_drm_front_evtchnl_flush(struct xen_drm_front_evtchnl *evtchnl)
+{
+	int notify;
+
+	evtchnl->u.req.ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&evtchnl->u.req.ring, notify);
+	if (notify)
+		notify_remote_via_irq(evtchnl->irq);
+}
+
+void xen_drm_front_evtchnl_set_state(struct xen_drm_front_info *front_info,
+				     enum xen_drm_front_evtchnl_state state)
+{
+	unsigned long flags;
+	int i;
+
+	if (!front_info->evt_pairs)
+		return;
+
+	spin_lock_irqsave(&front_info->io_lock, flags);
+	for (i = 0; i < front_info->num_evt_pairs; i++) {
+		front_info->evt_pairs[i].req.state = state;
+		front_info->evt_pairs[i].evt.state = state;
+	}
+	spin_unlock_irqrestore(&front_info->io_lock, flags);
+}
+
+void xen_drm_front_evtchnl_free_all(struct xen_drm_front_info *front_info)
+{
+	int i;
+
+	if (!front_info->evt_pairs)
+		return;
+
+	for (i = 0; i < front_info->num_evt_pairs; i++) {
+		evtchnl_free(front_info, &front_info->evt_pairs[i].req);
+		evtchnl_free(front_info, &front_info->evt_pairs[i].evt);
+	}
+
+	kfree(front_info->evt_pairs);
+	front_info->evt_pairs = NULL;
+}
diff --git a/drivers/gpu/drm/xen/xen_drm_front_evtchnl.h b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.h
new file mode 100644
index 000000000000..b0af6994332b
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_DRM_FRONT_EVTCHNL_H_
+#define __XEN_DRM_FRONT_EVTCHNL_H_
+
+#include <linux/completion.h>
+#include <linux/types.h>
+
+#include <xen/interface/io/ring.h>
+#include <xen/interface/io/displif.h>
+
+/*
+ * All operations which are not connector oriented use this ctrl event channel,
+ * e.g. fb_attach/destroy which belong to a DRM device, not to a CRTC.
+ */
+#define GENERIC_OP_EVT_CHNL	0
+
+enum xen_drm_front_evtchnl_state {
+	EVTCHNL_STATE_DISCONNECTED,
+	EVTCHNL_STATE_CONNECTED,
+};
+
+enum xen_drm_front_evtchnl_type {
+	EVTCHNL_TYPE_REQ,
+	EVTCHNL_TYPE_EVT,
+};
+
+struct xen_drm_front_drm_info;
+
+struct xen_drm_front_evtchnl {
+	struct xen_drm_front_info *front_info;
+	int gref;
+	int port;
+	int irq;
+	int index;
+	enum xen_drm_front_evtchnl_state state;
+	enum xen_drm_front_evtchnl_type type;
+	/* either response id or incoming event id */
+	u16 evt_id;
+	/* next request id or next expected event id */
+	u16 evt_next_id;
+	union {
+		struct {
+			struct xen_displif_front_ring ring;
+			struct completion completion;
+			/* latest response status */
+			int resp_status;
+			/* serializer for backend IO: request/response */
+			struct mutex req_io_lock;
+		} req;
+		struct {
+			struct xendispl_event_page *page;
+		} evt;
+	} u;
+};
+
+struct xen_drm_front_evtchnl_pair {
+	struct xen_drm_front_evtchnl req;
+	struct xen_drm_front_evtchnl evt;
+};
+
+int xen_drm_front_evtchnl_create_all(struct xen_drm_front_info *front_info);
+
+int xen_drm_front_evtchnl_publish_all(struct xen_drm_front_info *front_info);
+
+void xen_drm_front_evtchnl_flush(struct xen_drm_front_evtchnl *evtchnl);
+
+void xen_drm_front_evtchnl_set_state(struct xen_drm_front_info *front_info,
+				     enum xen_drm_front_evtchnl_state state);
+
+void xen_drm_front_evtchnl_free_all(struct xen_drm_front_info *front_info);
+
+#endif /* __XEN_DRM_FRONT_EVTCHNL_H_ */
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
new file mode 100644
index 000000000000..c85bfe7571cb
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include "xen_drm_front_gem.h"
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_gem.h>
+
+#include <linux/dma-buf.h>
+#include <linux/scatterlist.h>
+#include <linux/shmem_fs.h>
+
+#include <xen/balloon.h>
+
+#include "xen_drm_front.h"
+#include "xen_drm_front_shbuf.h"
+
+struct xen_gem_object {
+	struct drm_gem_object base;
+
+	size_t num_pages;
+	struct page **pages;
+
+	/* set for buffers allocated by the backend */
+	bool be_alloc;
+
+	/* this is for imported PRIME buffer */
+	struct sg_table *sgt_imported;
+};
+
+static inline struct xen_gem_object *
+to_xen_gem_obj(struct drm_gem_object *gem_obj)
+{
+	return container_of(gem_obj, struct xen_gem_object, base);
+}
+
+static int gem_alloc_pages_array(struct xen_gem_object *xen_obj,
+				 size_t buf_size)
+{
+	xen_obj->num_pages = DIV_ROUND_UP(buf_size, PAGE_SIZE);
+	xen_obj->pages = kvmalloc_array(xen_obj->num_pages,
+					sizeof(struct page *), GFP_KERNEL);
+	return !xen_obj->pages ? -ENOMEM : 0;
+}
+
+static void gem_free_pages_array(struct xen_gem_object *xen_obj)
+{
+	kvfree(xen_obj->pages);
+	xen_obj->pages = NULL;
+}
+
+static struct xen_gem_object *gem_create_obj(struct drm_device *dev,
+					     size_t size)
+{
+	struct xen_gem_object *xen_obj;
+	int ret;
+
+	xen_obj = kzalloc(sizeof(*xen_obj), GFP_KERNEL);
+	if (!xen_obj)
+		return ERR_PTR(-ENOMEM);
+
+	ret = drm_gem_object_init(dev, &xen_obj->base, size);
+	if (ret < 0) {
+		kfree(xen_obj);
+		return ERR_PTR(ret);
+	}
+
+	return xen_obj;
+}
+
+static struct xen_gem_object *gem_create(struct drm_device *dev, size_t size)
+{
+	struct xen_drm_front_drm_info *drm_info = dev->dev_private;
+	struct xen_gem_object *xen_obj;
+	int ret;
+
+	size = round_up(size, PAGE_SIZE);
+	xen_obj = gem_create_obj(dev, size);
+	if (IS_ERR_OR_NULL(xen_obj))
+		return xen_obj;
+
+	if (drm_info->front_info->cfg.be_alloc) {
+		/*
+		 * backend will allocate space for this buffer, so
+		 * only allocate array of pointers to pages
+		 */
+		ret = gem_alloc_pages_array(xen_obj, size);
+		if (ret < 0)
+			goto fail;
+
+		/*
+		 * allocate ballooned pages which will be used to map
+		 * grant references provided by the backend
+		 */
+		ret = alloc_xenballooned_pages(xen_obj->num_pages,
+					       xen_obj->pages);
+		if (ret < 0) {
+			DRM_ERROR("Cannot allocate %zu ballooned pages: %d\n",
+				  xen_obj->num_pages, ret);
+			gem_free_pages_array(xen_obj);
+			goto fail;
+		}
+
+		xen_obj->be_alloc = true;
+		return xen_obj;
+	}
+	/*
+	 * need to allocate backing pages now, so we can share those
+	 * with the backend
+	 */
+	xen_obj->num_pages = DIV_ROUND_UP(size, PAGE_SIZE);
+	xen_obj->pages = drm_gem_get_pages(&xen_obj->base);
+	if (IS_ERR_OR_NULL(xen_obj->pages)) {
+		ret = PTR_ERR(xen_obj->pages);
+		xen_obj->pages = NULL;
+		goto fail;
+	}
+
+	return xen_obj;
+
+fail:
+	DRM_ERROR("Failed to allocate buffer with size %zu\n", size);
+	return ERR_PTR(ret);
+}
+
+struct drm_gem_object *xen_drm_front_gem_create(struct drm_device *dev,
+						size_t size)
+{
+	struct xen_gem_object *xen_obj;
+
+	xen_obj = gem_create(dev, size);
+	if (IS_ERR_OR_NULL(xen_obj))
+		return ERR_CAST(xen_obj);
+
+	return &xen_obj->base;
+}
+
+void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj)
+{
+	struct xen_gem_object *xen_obj = to_xen_gem_obj(gem_obj);
+
+	if (xen_obj->base.import_attach) {
+		drm_prime_gem_destroy(&xen_obj->base, xen_obj->sgt_imported);
+		gem_free_pages_array(xen_obj);
+	} else {
+		if (xen_obj->pages) {
+			if (xen_obj->be_alloc) {
+				free_xenballooned_pages(xen_obj->num_pages,
+							xen_obj->pages);
+				gem_free_pages_array(xen_obj);
+			} else {
+				drm_gem_put_pages(&xen_obj->base,
+						  xen_obj->pages, true, false);
+			}
+		}
+	}
+	drm_gem_object_release(gem_obj);
+	kfree(xen_obj);
+}
+
+struct page **xen_drm_front_gem_get_pages(struct drm_gem_object *gem_obj)
+{
+	struct xen_gem_object *xen_obj = to_xen_gem_obj(gem_obj);
+
+	return xen_obj->pages;
+}
+
+struct sg_table *xen_drm_front_gem_get_sg_table(struct drm_gem_object *gem_obj)
+{
+	struct xen_gem_object *xen_obj = to_xen_gem_obj(gem_obj);
+
+	if (!xen_obj->pages)
+		return NULL;
+
+	return drm_prime_pages_to_sg(xen_obj->pages, xen_obj->num_pages);
+}
+
+struct drm_gem_object *
+xen_drm_front_gem_import_sg_table(struct drm_device *dev,
+				  struct dma_buf_attachment *attach,
+				  struct sg_table *sgt)
+{
+	struct xen_drm_front_drm_info *drm_info = dev->dev_private;
+	struct xen_gem_object *xen_obj;
+	size_t size;
+	int ret;
+
+	size = attach->dmabuf->size;
+	xen_obj = gem_create_obj(dev, size);
+	if (IS_ERR_OR_NULL(xen_obj))
+		return ERR_CAST(xen_obj);
+
+	ret = gem_alloc_pages_array(xen_obj, size);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	xen_obj->sgt_imported = sgt;
+
+	ret = drm_prime_sg_to_page_addr_arrays(sgt, xen_obj->pages,
+					       NULL, xen_obj->num_pages);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	ret = xen_drm_front_dbuf_create(drm_info->front_info,
+					xen_drm_front_dbuf_to_cookie(&xen_obj->base),
+					0, 0, 0, size, xen_obj->pages);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	DRM_DEBUG("Imported buffer of size %zu with nents %u\n",
+		  size, sgt->nents);
+
+	return &xen_obj->base;
+}
+
+static int gem_mmap_obj(struct xen_gem_object *xen_obj,
+			struct vm_area_struct *vma)
+{
+	unsigned long addr = vma->vm_start;
+	int i;
+
+	/*
+	 * clear the VM_PFNMAP flag that was set by drm_gem_mmap(), and set the
+	 * vm_pgoff (used as a fake buffer offset by DRM) to 0 as we want to map
+	 * the whole buffer.
+	 */
+	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
+	vma->vm_pgoff = 0;
+	vma->vm_page_prot =
+			pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+
+	/*
+	 * vm_operations_struct.fault handler will be called if CPU access
+	 * to VM is here. For GPUs this isn't the case, because CPU
+	 * doesn't touch the memory. Insert pages now, so both CPU and GPU are
+	 * happy.
+	 * FIXME: as we insert all the pages now then no .fault handler must
+	 * be called, so don't provide one
+	 */
+	for (i = 0; i < xen_obj->num_pages; i++) {
+		int ret;
+
+		ret = vm_insert_page(vma, addr, xen_obj->pages[i]);
+		if (ret < 0) {
+			DRM_ERROR("Failed to insert pages into vma: %d\n", ret);
+			return ret;
+		}
+
+		addr += PAGE_SIZE;
+	}
+	return 0;
+}
+
+int xen_drm_front_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct xen_gem_object *xen_obj;
+	struct drm_gem_object *gem_obj;
+	int ret;
+
+	ret = drm_gem_mmap(filp, vma);
+	if (ret < 0)
+		return ret;
+
+	gem_obj = vma->vm_private_data;
+	xen_obj = to_xen_gem_obj(gem_obj);
+	return gem_mmap_obj(xen_obj, vma);
+}
+
+void *xen_drm_front_gem_prime_vmap(struct drm_gem_object *gem_obj)
+{
+	struct xen_gem_object *xen_obj = to_xen_gem_obj(gem_obj);
+
+	if (!xen_obj->pages)
+		return NULL;
+
+	return vmap(xen_obj->pages, xen_obj->num_pages,
+		    VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+}
+
+void xen_drm_front_gem_prime_vunmap(struct drm_gem_object *gem_obj,
+				    void *vaddr)
+{
+	vunmap(vaddr);
+}
+
+int xen_drm_front_gem_prime_mmap(struct drm_gem_object *gem_obj,
+				 struct vm_area_struct *vma)
+{
+	struct xen_gem_object *xen_obj;
+	int ret;
+
+	ret = drm_gem_mmap_obj(gem_obj, gem_obj->size, vma);
+	if (ret < 0)
+		return ret;
+
+	xen_obj = to_xen_gem_obj(gem_obj);
+	return gem_mmap_obj(xen_obj, vma);
+}
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.h b/drivers/gpu/drm/xen/xen_drm_front_gem.h
new file mode 100644
index 000000000000..d5ab734fdafe
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_DRM_FRONT_GEM_H
+#define __XEN_DRM_FRONT_GEM_H
+
+#include <drm/drmP.h>
+
+struct drm_gem_object *xen_drm_front_gem_create(struct drm_device *dev,
+						size_t size);
+
+struct drm_gem_object *
+xen_drm_front_gem_import_sg_table(struct drm_device *dev,
+				  struct dma_buf_attachment *attach,
+				  struct sg_table *sgt);
+
+struct sg_table *xen_drm_front_gem_get_sg_table(struct drm_gem_object *gem_obj);
+
+struct page **xen_drm_front_gem_get_pages(struct drm_gem_object *obj);
+
+void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj);
+
+int xen_drm_front_gem_mmap(struct file *filp, struct vm_area_struct *vma);
+
+void *xen_drm_front_gem_prime_vmap(struct drm_gem_object *gem_obj);
+
+void xen_drm_front_gem_prime_vunmap(struct drm_gem_object *gem_obj,
+				    void *vaddr);
+
+int xen_drm_front_gem_prime_mmap(struct drm_gem_object *gem_obj,
+				 struct vm_area_struct *vma);
+
+#endif /* __XEN_DRM_FRONT_GEM_H */
diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.c b/drivers/gpu/drm/xen/xen_drm_front_kms.c
new file mode 100644
index 000000000000..a3479eb72d79
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_kms.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include "xen_drm_front_kms.h"
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+
+#include "xen_drm_front.h"
+#include "xen_drm_front_conn.h"
+
+/*
+ * Timeout in ms to wait for frame done event from the backend:
+ * must be a bit more than IO time-out
+ */
+#define FRAME_DONE_TO_MS	(XEN_DRM_FRONT_WAIT_BACK_MS + 100)
+
+static struct xen_drm_front_drm_pipeline *
+to_xen_drm_pipeline(struct drm_simple_display_pipe *pipe)
+{
+	return container_of(pipe, struct xen_drm_front_drm_pipeline, pipe);
+}
+
+static void fb_destroy(struct drm_framebuffer *fb)
+{
+	struct xen_drm_front_drm_info *drm_info = fb->dev->dev_private;
+	int idx;
+
+	if (drm_dev_enter(fb->dev, &idx)) {
+		xen_drm_front_fb_detach(drm_info->front_info,
+					xen_drm_front_fb_to_cookie(fb));
+		drm_dev_exit(idx);
+	}
+	drm_gem_fb_destroy(fb);
+}
+
+static struct drm_framebuffer_funcs fb_funcs = {
+	.destroy = fb_destroy,
+};
+
+static struct drm_framebuffer *
+fb_create(struct drm_device *dev, struct drm_file *filp,
+	  const struct drm_mode_fb_cmd2 *mode_cmd)
+{
+	struct xen_drm_front_drm_info *drm_info = dev->dev_private;
+	static struct drm_framebuffer *fb;
+	struct drm_gem_object *gem_obj;
+	int ret;
+
+	fb = drm_gem_fb_create_with_funcs(dev, filp, mode_cmd, &fb_funcs);
+	if (IS_ERR_OR_NULL(fb))
+		return fb;
+
+	gem_obj = drm_gem_object_lookup(filp, mode_cmd->handles[0]);
+	if (!gem_obj) {
+		DRM_ERROR("Failed to lookup GEM object\n");
+		ret = -ENOENT;
+		goto fail;
+	}
+
+	drm_gem_object_put_unlocked(gem_obj);
+
+	ret = xen_drm_front_fb_attach(drm_info->front_info,
+				      xen_drm_front_dbuf_to_cookie(gem_obj),
+				      xen_drm_front_fb_to_cookie(fb),
+				      fb->width, fb->height,
+				      fb->format->format);
+	if (ret < 0) {
+		DRM_ERROR("Back failed to attach FB %p: %d\n", fb, ret);
+		goto fail;
+	}
+
+	return fb;
+
+fail:
+	drm_gem_fb_destroy(fb);
+	return ERR_PTR(ret);
+}
+
+static const struct drm_mode_config_funcs mode_config_funcs = {
+	.fb_create = fb_create,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static void send_pending_event(struct xen_drm_front_drm_pipeline *pipeline)
+{
+	struct drm_crtc *crtc = &pipeline->pipe.crtc;
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	if (pipeline->pending_event)
+		drm_crtc_send_vblank_event(crtc, pipeline->pending_event);
+	pipeline->pending_event = NULL;
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+static void display_enable(struct drm_simple_display_pipe *pipe,
+			   struct drm_crtc_state *crtc_state,
+			   struct drm_plane_state *plane_state)
+{
+	struct xen_drm_front_drm_pipeline *pipeline =
+			to_xen_drm_pipeline(pipe);
+	struct drm_crtc *crtc = &pipe->crtc;
+	struct drm_framebuffer *fb = plane_state->fb;
+	int ret, idx;
+
+	if (!drm_dev_enter(pipe->crtc.dev, &idx))
+		return;
+
+	ret = xen_drm_front_mode_set(pipeline, crtc->x, crtc->y,
+				     fb->width, fb->height,
+				     fb->format->cpp[0] * 8,
+				     xen_drm_front_fb_to_cookie(fb));
+
+	if (ret) {
+		DRM_ERROR("Failed to enable display: %d\n", ret);
+		pipeline->conn_connected = false;
+	}
+
+	drm_dev_exit(idx);
+}
+
+static void display_disable(struct drm_simple_display_pipe *pipe)
+{
+	struct xen_drm_front_drm_pipeline *pipeline =
+			to_xen_drm_pipeline(pipe);
+	int ret = 0, idx;
+
+	if (drm_dev_enter(pipe->crtc.dev, &idx)) {
+		ret = xen_drm_front_mode_set(pipeline, 0, 0, 0, 0, 0,
+					     xen_drm_front_fb_to_cookie(NULL));
+		drm_dev_exit(idx);
+	}
+	if (ret)
+		DRM_ERROR("Failed to disable display: %d\n", ret);
+
+	/* Make sure we can restart with enabled connector next time */
+	pipeline->conn_connected = true;
+
+	/* release stalled event if any */
+	send_pending_event(pipeline);
+}
+
+void xen_drm_front_kms_on_frame_done(struct xen_drm_front_drm_pipeline *pipeline,
+				     u64 fb_cookie)
+{
+	/*
+	 * This runs in interrupt context, e.g. under
+	 * drm_info->front_info->io_lock, so we cannot call _sync version
+	 * to cancel the work
+	 */
+	cancel_delayed_work(&pipeline->pflip_to_worker);
+
+	send_pending_event(pipeline);
+}
+
+static void pflip_to_worker(struct work_struct *work)
+{
+	struct delayed_work *delayed_work = to_delayed_work(work);
+	struct xen_drm_front_drm_pipeline *pipeline =
+			container_of(delayed_work,
+				     struct xen_drm_front_drm_pipeline,
+				     pflip_to_worker);
+
+	DRM_ERROR("Frame done timed-out, releasing");
+	send_pending_event(pipeline);
+}
+
+static bool display_send_page_flip(struct drm_simple_display_pipe *pipe,
+				   struct drm_plane_state *old_plane_state)
+{
+	struct drm_plane_state *plane_state =
+			drm_atomic_get_new_plane_state(old_plane_state->state,
+						       &pipe->plane);
+
+	/*
+	 * If old_plane_state->fb is NULL and plane_state->fb is not,
+	 * then this is an atomic commit which will enable display.
+	 * If old_plane_state->fb is not NULL and plane_state->fb is,
+	 * then this is an atomic commit which will disable display.
+	 * Ignore these and do not send page flip as this framebuffer will be
+	 * sent to the backend as a part of display_set_config call.
+	 */
+	if (old_plane_state->fb && plane_state->fb) {
+		struct xen_drm_front_drm_pipeline *pipeline =
+				to_xen_drm_pipeline(pipe);
+		struct xen_drm_front_drm_info *drm_info = pipeline->drm_info;
+		int ret;
+
+		schedule_delayed_work(&pipeline->pflip_to_worker,
+				      msecs_to_jiffies(FRAME_DONE_TO_MS));
+
+		ret = xen_drm_front_page_flip(drm_info->front_info,
+					      pipeline->index,
+					      xen_drm_front_fb_to_cookie(plane_state->fb));
+		if (ret) {
+			DRM_ERROR("Failed to send page flip request to backend: %d\n", ret);
+
+			pipeline->conn_connected = false;
+			/*
+			 * Report the flip not handled, so pending event is
+			 * sent, unblocking user-space.
+			 */
+			return false;
+		}
+		/*
+		 * Signal that page flip was handled, pending event will be sent
+		 * on frame done event from the backend.
+		 */
+		return true;
+	}
+
+	return false;
+}
+
+static void display_update(struct drm_simple_display_pipe *pipe,
+			   struct drm_plane_state *old_plane_state)
+{
+	struct xen_drm_front_drm_pipeline *pipeline =
+			to_xen_drm_pipeline(pipe);
+	struct drm_crtc *crtc = &pipe->crtc;
+	struct drm_pending_vblank_event *event;
+	int idx;
+
+	event = crtc->state->event;
+	if (event) {
+		struct drm_device *dev = crtc->dev;
+		unsigned long flags;
+
+		WARN_ON(pipeline->pending_event);
+
+		spin_lock_irqsave(&dev->event_lock, flags);
+		crtc->state->event = NULL;
+
+		pipeline->pending_event = event;
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+
+	if (!drm_dev_enter(pipe->crtc.dev, &idx)) {
+		send_pending_event(pipeline);
+		return;
+	}
+
+	/*
+	 * Send page flip request to the backend *after* we have event cached
+	 * above, so on page flip done event from the backend we can
+	 * deliver it and there is no race condition between this code and
+	 * event from the backend.
+	 * If this is not a page flip, e.g. no flip done event from the backend
+	 * is expected, then send now.
+	 */
+	if (!display_send_page_flip(pipe, old_plane_state))
+		send_pending_event(pipeline);
+
+	drm_dev_exit(idx);
+}
+
+static enum drm_mode_status
+display_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode)
+{
+	struct xen_drm_front_drm_pipeline *pipeline =
+			container_of(crtc, struct xen_drm_front_drm_pipeline,
+				     pipe.crtc);
+
+	if (mode->hdisplay != pipeline->width)
+		return MODE_ERROR;
+
+	if (mode->vdisplay != pipeline->height)
+		return MODE_ERROR;
+
+	return MODE_OK;
+}
+
+static const struct drm_simple_display_pipe_funcs display_funcs = {
+	.mode_valid = display_mode_valid,
+	.enable = display_enable,
+	.disable = display_disable,
+	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
+	.update = display_update,
+};
+
+static int display_pipe_init(struct xen_drm_front_drm_info *drm_info,
+			     int index, struct xen_drm_front_cfg_connector *cfg,
+			     struct xen_drm_front_drm_pipeline *pipeline)
+{
+	struct drm_device *dev = drm_info->drm_dev;
+	const u32 *formats;
+	int format_count;
+	int ret;
+
+	pipeline->drm_info = drm_info;
+	pipeline->index = index;
+	pipeline->height = cfg->height;
+	pipeline->width = cfg->width;
+
+	INIT_DELAYED_WORK(&pipeline->pflip_to_worker, pflip_to_worker);
+
+	ret = xen_drm_front_conn_init(drm_info, &pipeline->conn);
+	if (ret)
+		return ret;
+
+	formats = xen_drm_front_conn_get_formats(&format_count);
+
+	return drm_simple_display_pipe_init(dev, &pipeline->pipe,
+					    &display_funcs, formats,
+					    format_count, NULL,
+					    &pipeline->conn);
+}
+
+int xen_drm_front_kms_init(struct xen_drm_front_drm_info *drm_info)
+{
+	struct drm_device *dev = drm_info->drm_dev;
+	int i, ret;
+
+	drm_mode_config_init(dev);
+
+	dev->mode_config.min_width = 0;
+	dev->mode_config.min_height = 0;
+	dev->mode_config.max_width = 4095;
+	dev->mode_config.max_height = 2047;
+	dev->mode_config.funcs = &mode_config_funcs;
+
+	for (i = 0; i < drm_info->front_info->cfg.num_connectors; i++) {
+		struct xen_drm_front_cfg_connector *cfg =
+				&drm_info->front_info->cfg.connectors[i];
+		struct xen_drm_front_drm_pipeline *pipeline =
+				&drm_info->pipeline[i];
+
+		ret = display_pipe_init(drm_info, i, cfg, pipeline);
+		if (ret) {
+			drm_mode_config_cleanup(dev);
+			return ret;
+		}
+	}
+
+	drm_mode_config_reset(dev);
+	drm_kms_helper_poll_init(dev);
+	return 0;
+}
+
+void xen_drm_front_kms_fini(struct xen_drm_front_drm_info *drm_info)
+{
+	int i;
+
+	for (i = 0; i < drm_info->front_info->cfg.num_connectors; i++) {
+		struct xen_drm_front_drm_pipeline *pipeline =
+				&drm_info->pipeline[i];
+
+		cancel_delayed_work_sync(&pipeline->pflip_to_worker);
+
+		send_pending_event(pipeline);
+	}
+}
diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.h b/drivers/gpu/drm/xen/xen_drm_front_kms.h
new file mode 100644
index 000000000000..ab2fbad4fbbf
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_kms.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_DRM_FRONT_KMS_H_
+#define __XEN_DRM_FRONT_KMS_H_
+
+#include <linux/types.h>
+
+struct xen_drm_front_drm_info;
+struct xen_drm_front_drm_pipeline;
+
+int xen_drm_front_kms_init(struct xen_drm_front_drm_info *drm_info);
+
+void xen_drm_front_kms_fini(struct xen_drm_front_drm_info *drm_info);
+
+void xen_drm_front_kms_on_frame_done(struct xen_drm_front_drm_pipeline *pipeline,
+				     u64 fb_cookie);
+
+#endif /* __XEN_DRM_FRONT_KMS_H_ */
diff --git a/drivers/gpu/drm/xen/xen_drm_front_shbuf.c b/drivers/gpu/drm/xen/xen_drm_front_shbuf.c
new file mode 100644
index 000000000000..8099cb343ae3
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_shbuf.c
@@ -0,0 +1,414 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <drm/drmP.h>
+
+#if defined(CONFIG_X86)
+#include <drm/drm_cache.h>
+#endif
+#include <linux/errno.h>
+#include <linux/mm.h>
+
+#include <asm/xen/hypervisor.h>
+#include <xen/balloon.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/ring.h>
+#include <xen/interface/io/displif.h>
+
+#include "xen_drm_front.h"
+#include "xen_drm_front_shbuf.h"
+
+struct xen_drm_front_shbuf_ops {
+	/*
+	 * Calculate number of grefs required to handle this buffer,
+	 * e.g. if grefs are required for page directory only or the buffer
+	 * pages as well.
+	 */
+	void (*calc_num_grefs)(struct xen_drm_front_shbuf *buf);
+	/* Fill page directory according to para-virtual display protocol. */
+	void (*fill_page_dir)(struct xen_drm_front_shbuf *buf);
+	/* Claim grant references for the pages of the buffer. */
+	int (*grant_refs_for_buffer)(struct xen_drm_front_shbuf *buf,
+				     grant_ref_t *priv_gref_head, int gref_idx);
+	/* Map grant references of the buffer. */
+	int (*map)(struct xen_drm_front_shbuf *buf);
+	/* Unmap grant references of the buffer. */
+	int (*unmap)(struct xen_drm_front_shbuf *buf);
+};
+
+grant_ref_t xen_drm_front_shbuf_get_dir_start(struct xen_drm_front_shbuf *buf)
+{
+	if (!buf->grefs)
+		return GRANT_INVALID_REF;
+
+	return buf->grefs[0];
+}
+
+int xen_drm_front_shbuf_map(struct xen_drm_front_shbuf *buf)
+{
+	if (buf->ops->map)
+		return buf->ops->map(buf);
+
+	/* no need to map own grant references */
+	return 0;
+}
+
+int xen_drm_front_shbuf_unmap(struct xen_drm_front_shbuf *buf)
+{
+	if (buf->ops->unmap)
+		return buf->ops->unmap(buf);
+
+	/* no need to unmap own grant references */
+	return 0;
+}
+
+void xen_drm_front_shbuf_flush(struct xen_drm_front_shbuf *buf)
+{
+#if defined(CONFIG_X86)
+	drm_clflush_pages(buf->pages, buf->num_pages);
+#endif
+}
+
+void xen_drm_front_shbuf_free(struct xen_drm_front_shbuf *buf)
+{
+	if (buf->grefs) {
+		int i;
+
+		for (i = 0; i < buf->num_grefs; i++)
+			if (buf->grefs[i] != GRANT_INVALID_REF)
+				gnttab_end_foreign_access(buf->grefs[i],
+							  0, 0UL);
+	}
+	kfree(buf->grefs);
+	kfree(buf->directory);
+	kfree(buf);
+}
+
+/*
+ * number of grefs a page can hold with respect to the
+ * struct xendispl_page_directory header
+ */
+#define XEN_DRM_NUM_GREFS_PER_PAGE ((PAGE_SIZE - \
+		offsetof(struct xendispl_page_directory, gref)) / \
+		sizeof(grant_ref_t))
+
+static int get_num_pages_dir(struct xen_drm_front_shbuf *buf)
+{
+	/* number of pages the page directory consumes itself */
+	return DIV_ROUND_UP(buf->num_pages, XEN_DRM_NUM_GREFS_PER_PAGE);
+}
+
+static void backend_calc_num_grefs(struct xen_drm_front_shbuf *buf)
+{
+	/* only for pages the page directory consumes itself */
+	buf->num_grefs = get_num_pages_dir(buf);
+}
+
+static void guest_calc_num_grefs(struct xen_drm_front_shbuf *buf)
+{
+	/*
+	 * number of pages the page directory consumes itself
+	 * plus grefs for the buffer pages
+	 */
+	buf->num_grefs = get_num_pages_dir(buf) + buf->num_pages;
+}
+
+#define xen_page_to_vaddr(page) \
+		((phys_addr_t)pfn_to_kaddr(page_to_xen_pfn(page)))
+
+static int backend_unmap(struct xen_drm_front_shbuf *buf)
+{
+	struct gnttab_unmap_grant_ref *unmap_ops;
+	int i, ret;
+
+	if (!buf->pages || !buf->backend_map_handles || !buf->grefs)
+		return 0;
+
+	unmap_ops = kcalloc(buf->num_pages, sizeof(*unmap_ops),
+			    GFP_KERNEL);
+	if (!unmap_ops) {
+		DRM_ERROR("Failed to get memory while unmapping\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < buf->num_pages; i++) {
+		phys_addr_t addr;
+
+		addr = xen_page_to_vaddr(buf->pages[i]);
+		gnttab_set_unmap_op(&unmap_ops[i], addr, GNTMAP_host_map,
+				    buf->backend_map_handles[i]);
+	}
+
+	ret = gnttab_unmap_refs(unmap_ops, NULL, buf->pages,
+				buf->num_pages);
+
+	for (i = 0; i < buf->num_pages; i++) {
+		if (unlikely(unmap_ops[i].status != GNTST_okay))
+			DRM_ERROR("Failed to unmap page %d: %d\n",
+				  i, unmap_ops[i].status);
+	}
+
+	if (ret)
+		DRM_ERROR("Failed to unmap grant references, ret %d", ret);
+
+	kfree(unmap_ops);
+	kfree(buf->backend_map_handles);
+	buf->backend_map_handles = NULL;
+	return ret;
+}
+
+static int backend_map(struct xen_drm_front_shbuf *buf)
+{
+	struct gnttab_map_grant_ref *map_ops = NULL;
+	unsigned char *ptr;
+	int ret, cur_gref, cur_dir_page, cur_page, grefs_left;
+
+	map_ops = kcalloc(buf->num_pages, sizeof(*map_ops), GFP_KERNEL);
+	if (!map_ops)
+		return -ENOMEM;
+
+	buf->backend_map_handles = kcalloc(buf->num_pages,
+					   sizeof(*buf->backend_map_handles),
+					   GFP_KERNEL);
+	if (!buf->backend_map_handles) {
+		kfree(map_ops);
+		return -ENOMEM;
+	}
+
+	/*
+	 * read page directory to get grefs from the backend: for external
+	 * buffer we only allocate buf->grefs for the page directory,
+	 * so buf->num_grefs has number of pages in the page directory itself
+	 */
+	ptr = buf->directory;
+	grefs_left = buf->num_pages;
+	cur_page = 0;
+	for (cur_dir_page = 0; cur_dir_page < buf->num_grefs; cur_dir_page++) {
+		struct xendispl_page_directory *page_dir =
+				(struct xendispl_page_directory *)ptr;
+		int to_copy = XEN_DRM_NUM_GREFS_PER_PAGE;
+
+		if (to_copy > grefs_left)
+			to_copy = grefs_left;
+
+		for (cur_gref = 0; cur_gref < to_copy; cur_gref++) {
+			phys_addr_t addr;
+
+			addr = xen_page_to_vaddr(buf->pages[cur_page]);
+			gnttab_set_map_op(&map_ops[cur_page], addr,
+					  GNTMAP_host_map,
+					  page_dir->gref[cur_gref],
+					  buf->xb_dev->otherend_id);
+			cur_page++;
+		}
+
+		grefs_left -= to_copy;
+		ptr += PAGE_SIZE;
+	}
+	ret = gnttab_map_refs(map_ops, NULL, buf->pages, buf->num_pages);
+
+	/* save handles even if error, so we can unmap */
+	for (cur_page = 0; cur_page < buf->num_pages; cur_page++) {
+		buf->backend_map_handles[cur_page] = map_ops[cur_page].handle;
+		if (unlikely(map_ops[cur_page].status != GNTST_okay))
+			DRM_ERROR("Failed to map page %d: %d\n",
+				  cur_page, map_ops[cur_page].status);
+	}
+
+	if (ret) {
+		DRM_ERROR("Failed to map grant references, ret %d", ret);
+		backend_unmap(buf);
+	}
+
+	kfree(map_ops);
+	return ret;
+}
+
+static void backend_fill_page_dir(struct xen_drm_front_shbuf *buf)
+{
+	struct xendispl_page_directory *page_dir;
+	unsigned char *ptr;
+	int i, num_pages_dir;
+
+	ptr = buf->directory;
+	num_pages_dir = get_num_pages_dir(buf);
+
+	/* fill only grefs for the page directory itself */
+	for (i = 0; i < num_pages_dir - 1; i++) {
+		page_dir = (struct xendispl_page_directory *)ptr;
+
+		page_dir->gref_dir_next_page = buf->grefs[i + 1];
+		ptr += PAGE_SIZE;
+	}
+	/* last page must say there is no more pages */
+	page_dir = (struct xendispl_page_directory *)ptr;
+	page_dir->gref_dir_next_page = GRANT_INVALID_REF;
+}
+
+static void guest_fill_page_dir(struct xen_drm_front_shbuf *buf)
+{
+	unsigned char *ptr;
+	int cur_gref, grefs_left, to_copy, i, num_pages_dir;
+
+	ptr = buf->directory;
+	num_pages_dir = get_num_pages_dir(buf);
+
+	/*
+	 * while copying, skip grefs at start, they are for pages
+	 * granted for the page directory itself
+	 */
+	cur_gref = num_pages_dir;
+	grefs_left = buf->num_pages;
+	for (i = 0; i < num_pages_dir; i++) {
+		struct xendispl_page_directory *page_dir =
+				(struct xendispl_page_directory *)ptr;
+
+		if (grefs_left <= XEN_DRM_NUM_GREFS_PER_PAGE) {
+			to_copy = grefs_left;
+			page_dir->gref_dir_next_page = GRANT_INVALID_REF;
+		} else {
+			to_copy = XEN_DRM_NUM_GREFS_PER_PAGE;
+			page_dir->gref_dir_next_page = buf->grefs[i + 1];
+		}
+		memcpy(&page_dir->gref, &buf->grefs[cur_gref],
+		       to_copy * sizeof(grant_ref_t));
+		ptr += PAGE_SIZE;
+		grefs_left -= to_copy;
+		cur_gref += to_copy;
+	}
+}
+
+static int guest_grant_refs_for_buffer(struct xen_drm_front_shbuf *buf,
+				       grant_ref_t *priv_gref_head,
+				       int gref_idx)
+{
+	int i, cur_ref, otherend_id;
+
+	otherend_id = buf->xb_dev->otherend_id;
+	for (i = 0; i < buf->num_pages; i++) {
+		cur_ref = gnttab_claim_grant_reference(priv_gref_head);
+		if (cur_ref < 0)
+			return cur_ref;
+
+		gnttab_grant_foreign_access_ref(cur_ref, otherend_id,
+						xen_page_to_gfn(buf->pages[i]),
+						0);
+		buf->grefs[gref_idx++] = cur_ref;
+	}
+	return 0;
+}
+
+static int grant_references(struct xen_drm_front_shbuf *buf)
+{
+	grant_ref_t priv_gref_head;
+	int ret, i, j, cur_ref;
+	int otherend_id, num_pages_dir;
+
+	ret = gnttab_alloc_grant_references(buf->num_grefs, &priv_gref_head);
+	if (ret < 0) {
+		DRM_ERROR("Cannot allocate grant references\n");
+		return ret;
+	}
+
+	otherend_id = buf->xb_dev->otherend_id;
+	j = 0;
+	num_pages_dir = get_num_pages_dir(buf);
+	for (i = 0; i < num_pages_dir; i++) {
+		unsigned long frame;
+
+		cur_ref = gnttab_claim_grant_reference(&priv_gref_head);
+		if (cur_ref < 0)
+			return cur_ref;
+
+		frame = xen_page_to_gfn(virt_to_page(buf->directory +
+					PAGE_SIZE * i));
+		gnttab_grant_foreign_access_ref(cur_ref, otherend_id, frame, 0);
+		buf->grefs[j++] = cur_ref;
+	}
+
+	if (buf->ops->grant_refs_for_buffer) {
+		ret = buf->ops->grant_refs_for_buffer(buf, &priv_gref_head, j);
+		if (ret)
+			return ret;
+	}
+
+	gnttab_free_grant_references(priv_gref_head);
+	return 0;
+}
+
+static int alloc_storage(struct xen_drm_front_shbuf *buf)
+{
+	buf->grefs = kcalloc(buf->num_grefs, sizeof(*buf->grefs), GFP_KERNEL);
+	if (!buf->grefs)
+		return -ENOMEM;
+
+	buf->directory = kcalloc(get_num_pages_dir(buf), PAGE_SIZE, GFP_KERNEL);
+	if (!buf->directory)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/*
+ * For be allocated buffers we don't need grant_refs_for_buffer as those
+ * grant references are allocated at backend side
+ */
+static const struct xen_drm_front_shbuf_ops backend_ops = {
+	.calc_num_grefs = backend_calc_num_grefs,
+	.fill_page_dir = backend_fill_page_dir,
+	.map = backend_map,
+	.unmap = backend_unmap
+};
+
+/* For locally granted references we do not need to map/unmap the references */
+static const struct xen_drm_front_shbuf_ops local_ops = {
+	.calc_num_grefs = guest_calc_num_grefs,
+	.fill_page_dir = guest_fill_page_dir,
+	.grant_refs_for_buffer = guest_grant_refs_for_buffer,
+};
+
+struct xen_drm_front_shbuf *
+xen_drm_front_shbuf_alloc(struct xen_drm_front_shbuf_cfg *cfg)
+{
+	struct xen_drm_front_shbuf *buf;
+	int ret;
+
+	buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+
+	if (cfg->be_alloc)
+		buf->ops = &backend_ops;
+	else
+		buf->ops = &local_ops;
+
+	buf->xb_dev = cfg->xb_dev;
+	buf->num_pages = DIV_ROUND_UP(cfg->size, PAGE_SIZE);
+	buf->pages = cfg->pages;
+
+	buf->ops->calc_num_grefs(buf);
+
+	ret = alloc_storage(buf);
+	if (ret)
+		goto fail;
+
+	ret = grant_references(buf);
+	if (ret)
+		goto fail;
+
+	buf->ops->fill_page_dir(buf);
+
+	return buf;
+
+fail:
+	xen_drm_front_shbuf_free(buf);
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/xen/xen_drm_front_shbuf.h b/drivers/gpu/drm/xen/xen_drm_front_shbuf.h
new file mode 100644
index 000000000000..7545c692539e
--- /dev/null
+++ b/drivers/gpu/drm/xen/xen_drm_front_shbuf.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ *  Xen para-virtual DRM device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_DRM_FRONT_SHBUF_H_
+#define __XEN_DRM_FRONT_SHBUF_H_
+
+#include <linux/kernel.h>
+#include <linux/scatterlist.h>
+
+#include <xen/grant_table.h>
+
+struct xen_drm_front_shbuf {
+	/*
+	 * number of references granted for the backend use:
+	 *  - for allocated/imported dma-buf's this holds number of grant
+	 *    references for the page directory and pages of the buffer
+	 *  - for the buffer provided by the backend this holds number of
+	 *    grant references for the page directory as grant references for
+	 *    the buffer will be provided by the backend
+	 */
+	int num_grefs;
+	grant_ref_t *grefs;
+	unsigned char *directory;
+
+	int num_pages;
+	struct page **pages;
+
+	struct xenbus_device *xb_dev;
+
+	/* these are the ops used internally depending on be_alloc mode */
+	const struct xen_drm_front_shbuf_ops *ops;
+
+	/* Xen map handles for the buffer allocated by the backend */
+	grant_handle_t *backend_map_handles;
+};
+
+struct xen_drm_front_shbuf_cfg {
+	struct xenbus_device *xb_dev;
+	size_t size;
+	struct page **pages;
+	bool be_alloc;
+};
+
+struct xen_drm_front_shbuf *
+xen_drm_front_shbuf_alloc(struct xen_drm_front_shbuf_cfg *cfg);
+
+grant_ref_t xen_drm_front_shbuf_get_dir_start(struct xen_drm_front_shbuf *buf);
+
+int xen_drm_front_shbuf_map(struct xen_drm_front_shbuf *buf);
+
+int xen_drm_front_shbuf_unmap(struct xen_drm_front_shbuf *buf);
+
+void xen_drm_front_shbuf_flush(struct xen_drm_front_shbuf *buf);
+
+void xen_drm_front_shbuf_free(struct xen_drm_front_shbuf *buf);
+
+#endif /* __XEN_DRM_FRONT_SHBUF_H_ */
diff --git a/drivers/gpu/drm/zte/zx_plane.c b/drivers/gpu/drm/zte/zx_plane.c
index 94545adac50d..d1931f5ea0b2 100644
--- a/drivers/gpu/drm/zte/zx_plane.c
+++ b/drivers/gpu/drm/zte/zx_plane.c
@@ -268,7 +268,7 @@ static void zx_plane_atomic_disable(struct drm_plane *plane,
 	struct zx_plane *zplane = to_zx_plane(plane);
 	void __iomem *hbsc = zplane->hbsc;
 
-	zx_vou_layer_disable(plane);
+	zx_vou_layer_disable(plane, old_state);
 
 	/* Disable HBSC block */
 	zx_writel_mask(hbsc + HBSC_CTRL0, HBSC_CTRL_EN, 0);
diff --git a/drivers/gpu/drm/zte/zx_vou.c b/drivers/gpu/drm/zte/zx_vou.c
index 7491813131f3..442311d31110 100644
--- a/drivers/gpu/drm/zte/zx_vou.c
+++ b/drivers/gpu/drm/zte/zx_vou.c
@@ -627,9 +627,10 @@ void zx_vou_layer_enable(struct drm_plane *plane)
 	zx_writel_mask(vou->osd + OSD_CTRL0, bits->enable, bits->enable);
 }
 
-void zx_vou_layer_disable(struct drm_plane *plane)
+void zx_vou_layer_disable(struct drm_plane *plane,
+			  struct drm_plane_state *old_state)
 {
-	struct zx_crtc *zcrtc = to_zx_crtc(plane->crtc);
+	struct zx_crtc *zcrtc = to_zx_crtc(old_state->crtc);
 	struct zx_vou_hw *vou = zcrtc->vou;
 	struct zx_plane *zplane = to_zx_plane(plane);
 	const struct vou_layer_bits *bits = zplane->bits;
diff --git a/drivers/gpu/drm/zte/zx_vou.h b/drivers/gpu/drm/zte/zx_vou.h
index 97d72bfce982..5b7f84fbb112 100644
--- a/drivers/gpu/drm/zte/zx_vou.h
+++ b/drivers/gpu/drm/zte/zx_vou.h
@@ -62,6 +62,7 @@ void zx_vou_config_dividers(struct drm_crtc *crtc,
 			    struct vou_div_config *configs, int num);
 
 void zx_vou_layer_enable(struct drm_plane *plane);
-void zx_vou_layer_disable(struct drm_plane *plane);
+void zx_vou_layer_disable(struct drm_plane *plane,
+			  struct drm_plane_state *old_state);
 
 #endif /* __ZX_VOU_H__ */
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 88a3558b7916..815bdb42e3f0 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -314,6 +314,11 @@ static int host1x_device_match(struct device *dev, struct device_driver *drv)
 	return strcmp(dev_name(dev), drv->name) == 0;
 }
 
+static int host1x_dma_configure(struct device *dev)
+{
+	return of_dma_configure(dev, dev->of_node, true);
+}
+
 static const struct dev_pm_ops host1x_device_pm_ops = {
 	.suspend = pm_generic_suspend,
 	.resume = pm_generic_resume,
@@ -326,8 +331,8 @@ static const struct dev_pm_ops host1x_device_pm_ops = {
 struct bus_type host1x_bus_type = {
 	.name = "host1x",
 	.match = host1x_device_match,
+	.dma_configure	= host1x_dma_configure,
 	.pm = &host1x_device_pm_ops,
-	.force_dma = true,
 };
 
 static void __host1x_device_del(struct host1x_device *device)
@@ -416,7 +421,7 @@ static int host1x_device_add(struct host1x *host1x,
 	device->dev.bus = &host1x_bus_type;
 	device->dev.parent = host1x->dev;
 
-	of_dma_configure(&device->dev, host1x->dev->of_node);
+	of_dma_configure(&device->dev, host1x->dev->of_node, true);
 
 	err = host1x_device_parse_dt(device, driver);
 	if (err < 0) {
diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index 28541b280739..91df51e631b2 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -51,7 +51,7 @@ static void host1x_pushbuffer_destroy(struct push_buffer *pb)
 	struct host1x_cdma *cdma = pb_to_cdma(pb);
 	struct host1x *host1x = cdma_to_host1x(cdma);
 
-	if (!pb->phys)
+	if (!pb->mapped)
 		return;
 
 	if (host1x->domain) {
@@ -127,7 +127,7 @@ static int host1x_pushbuffer_init(struct push_buffer *pb)
 iommu_free_iova:
 	__free_iova(&host1x->iova, alloc);
 iommu_free_mem:
-	dma_free_wc(host1x->dev, pb->alloc_size, pb->mapped, pb->phys);
+	dma_free_wc(host1x->dev, size, pb->mapped, pb->phys);
 
 	return err;
 }
@@ -247,7 +247,7 @@ static void cdma_start_timer_locked(struct host1x_cdma *cdma,
 static void stop_cdma_timer_locked(struct host1x_cdma *cdma)
 {
 	cancel_delayed_work(&cdma->timeout.wq);
-	cdma->timeout.client = 0;
+	cdma->timeout.client = NULL;
 }
 
 /*
diff --git a/drivers/gpu/host1x/cdma.h b/drivers/gpu/host1x/cdma.h
index 286d49386be9..e97e17b82370 100644
--- a/drivers/gpu/host1x/cdma.h
+++ b/drivers/gpu/host1x/cdma.h
@@ -44,7 +44,7 @@ struct host1x_job;
 struct push_buffer {
 	void *mapped;			/* mapped pushbuffer memory */
 	dma_addr_t dma;			/* device address of pushbuffer */
-	phys_addr_t phys;		/* physical address of pushbuffer */
+	dma_addr_t phys;		/* physical address of pushbuffer */
 	u32 fence;			/* index we've written */
 	u32 pos;			/* index to write to */
 	u32 size;
@@ -58,7 +58,7 @@ struct buffer_timeout {
 	u32 syncpt_val;			/* syncpt value when completed */
 	ktime_t start_ktime;		/* starting time */
 	/* context timeout information */
-	int client;
+	struct host1x_client *client;
 };
 
 enum cdma_event {
diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c
index dc77ec452ffc..329e4a3d8ae7 100644
--- a/drivers/gpu/host1x/debug.c
+++ b/drivers/gpu/host1x/debug.c
@@ -103,7 +103,7 @@ static void show_syncpts(struct host1x *m, struct output *o)
 
 static void show_all(struct host1x *m, struct output *o, bool show_fifo)
 {
-	int i;
+	unsigned int i;
 
 	host1x_hw_show_mlocks(m, o);
 	show_syncpts(m, o);
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 03db71173f5d..f1d5f76e9c33 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -223,10 +223,14 @@ static int host1x_probe(struct platform_device *pdev)
 		struct iommu_domain_geometry *geometry;
 		unsigned long order;
 
+		err = iova_cache_get();
+		if (err < 0)
+			goto put_group;
+
 		host->domain = iommu_domain_alloc(&platform_bus_type);
 		if (!host->domain) {
 			err = -ENOMEM;
-			goto put_group;
+			goto put_cache;
 		}
 
 		err = iommu_attach_group(host->domain, host->group);
@@ -234,6 +238,7 @@ static int host1x_probe(struct platform_device *pdev)
 			if (err == -ENODEV) {
 				iommu_domain_free(host->domain);
 				host->domain = NULL;
+				iova_cache_put();
 				iommu_group_put(host->group);
 				host->group = NULL;
 				goto skip_iommu;
@@ -308,6 +313,9 @@ fail_detach_device:
 fail_free_domain:
 	if (host->domain)
 		iommu_domain_free(host->domain);
+put_cache:
+	if (host->group)
+		iova_cache_put();
 put_group:
 	iommu_group_put(host->group);
 
@@ -328,6 +336,7 @@ static int host1x_remove(struct platform_device *pdev)
 		put_iova_domain(&host->iova);
 		iommu_detach_group(host->domain, host->group);
 		iommu_domain_free(host->domain);
+		iova_cache_put();
 		iommu_group_put(host->group);
 	}
 
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index 43e9fabb43a1..36f44ffebe73 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -78,7 +78,6 @@ struct host1x_syncpt_ops {
 	void (*load_wait_base)(struct host1x_syncpt *syncpt);
 	u32 (*load)(struct host1x_syncpt *syncpt);
 	int (*cpu_incr)(struct host1x_syncpt *syncpt);
-	int (*patch_wait)(struct host1x_syncpt *syncpt, void *patch_addr);
 	void (*assign_to_channel)(struct host1x_syncpt *syncpt,
 	                          struct host1x_channel *channel);
 	void (*enable_protection)(struct host1x *host);
@@ -183,13 +182,6 @@ static inline int host1x_hw_syncpt_cpu_incr(struct host1x *host,
 	return host->syncpt_op->cpu_incr(sp);
 }
 
-static inline int host1x_hw_syncpt_patch_wait(struct host1x *host,
-					      struct host1x_syncpt *sp,
-					      void *patch_addr)
-{
-	return host->syncpt_op->patch_wait(sp, patch_addr);
-}
-
 static inline void host1x_hw_syncpt_assign_to_channel(
 	struct host1x *host, struct host1x_syncpt *sp,
 	struct host1x_channel *ch)
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 9af758785a11..d188f9068b91 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -104,8 +104,7 @@ static int channel_submit(struct host1x_job *job)
 	sp = host->syncpt + job->syncpt_id;
 	trace_host1x_channel_submit(dev_name(ch->dev),
 				    job->num_gathers, job->num_relocs,
-				    job->num_waitchk, job->syncpt_id,
-				    job->syncpt_incrs);
+				    job->syncpt_id, job->syncpt_incrs);
 
 	/* before error checks, return current max */
 	prev_max = job->syncpt_end = host1x_syncpt_read_max(sp);
@@ -165,7 +164,7 @@ static int channel_submit(struct host1x_job *job)
 	trace_host1x_channel_submitted(dev_name(ch->dev), prev_max, syncval);
 
 	/* schedule a submit complete interrupt */
-	err = host1x_intr_add_action(host, job->syncpt_id, syncval,
+	err = host1x_intr_add_action(host, sp, syncval,
 				     HOST1X_INTR_ACTION_SUBMIT_COMPLETE, ch,
 				     completed_waiter, NULL);
 	completed_waiter = NULL;
diff --git a/drivers/gpu/host1x/hw/syncpt_hw.c b/drivers/gpu/host1x/hw/syncpt_hw.c
index 7dfd47d74f89..a23bb3352d02 100644
--- a/drivers/gpu/host1x/hw/syncpt_hw.c
+++ b/drivers/gpu/host1x/hw/syncpt_hw.c
@@ -96,16 +96,6 @@ static int syncpt_cpu_incr(struct host1x_syncpt *sp)
 	return 0;
 }
 
-/* remove a wait pointed to by patch_addr */
-static int syncpt_patch_wait(struct host1x_syncpt *sp, void *patch_addr)
-{
-	u32 override = host1x_class_host_wait_syncpt(HOST1X_SYNCPT_RESERVED, 0);
-
-	*((u32 *)patch_addr) = override;
-
-	return 0;
-}
-
 /**
  * syncpt_assign_to_channel() - Assign syncpoint to channel
  * @sp: syncpoint
@@ -156,7 +146,6 @@ static const struct host1x_syncpt_ops host1x_syncpt_ops = {
 	.load_wait_base = syncpt_read_wait_base,
 	.load = syncpt_load,
 	.cpu_incr = syncpt_cpu_incr,
-	.patch_wait = syncpt_patch_wait,
 	.assign_to_channel = syncpt_assign_to_channel,
 	.enable_protection = syncpt_enable_protection,
 };
diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c
index 8b4fad0ab35d..9629c009d10f 100644
--- a/drivers/gpu/host1x/intr.c
+++ b/drivers/gpu/host1x/intr.c
@@ -144,7 +144,7 @@ static const action_handler action_handlers[HOST1X_INTR_ACTION_COUNT] = {
 static void run_handlers(struct list_head completed[HOST1X_INTR_ACTION_COUNT])
 {
 	struct list_head *head = completed;
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < HOST1X_INTR_ACTION_COUNT; ++i, ++head) {
 		action_handler handler = action_handlers[i];
@@ -211,11 +211,11 @@ static void syncpt_thresh_work(struct work_struct *work)
 				host1x_syncpt_load(host->syncpt + id));
 }
 
-int host1x_intr_add_action(struct host1x *host, unsigned int id, u32 thresh,
-			   enum host1x_intr_action action, void *data,
-			   struct host1x_waitlist *waiter, void **ref)
+int host1x_intr_add_action(struct host1x *host, struct host1x_syncpt *syncpt,
+			   u32 thresh, enum host1x_intr_action action,
+			   void *data, struct host1x_waitlist *waiter,
+			   void **ref)
 {
-	struct host1x_syncpt *syncpt;
 	int queue_was_empty;
 
 	if (waiter == NULL) {
@@ -234,19 +234,17 @@ int host1x_intr_add_action(struct host1x *host, unsigned int id, u32 thresh,
 	waiter->data = data;
 	waiter->count = 1;
 
-	syncpt = host->syncpt + id;
-
 	spin_lock(&syncpt->intr.lock);
 
 	queue_was_empty = list_empty(&syncpt->intr.wait_head);
 
 	if (add_waiter_to_queue(waiter, &syncpt->intr.wait_head)) {
 		/* added at head of list - new threshold value */
-		host1x_hw_intr_set_syncpt_threshold(host, id, thresh);
+		host1x_hw_intr_set_syncpt_threshold(host, syncpt->id, thresh);
 
 		/* added as first waiter - enable interrupt */
 		if (queue_was_empty)
-			host1x_hw_intr_enable_syncpt_intr(host, id);
+			host1x_hw_intr_enable_syncpt_intr(host, syncpt->id);
 	}
 
 	spin_unlock(&syncpt->intr.lock);
diff --git a/drivers/gpu/host1x/intr.h b/drivers/gpu/host1x/intr.h
index 1370c2bb75b8..6db96af484fe 100644
--- a/drivers/gpu/host1x/intr.h
+++ b/drivers/gpu/host1x/intr.h
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/workqueue.h>
 
+struct host1x_syncpt;
 struct host1x;
 
 enum host1x_intr_action {
@@ -75,9 +76,10 @@ struct host1x_waitlist {
  *
  * This is a non-blocking api.
  */
-int host1x_intr_add_action(struct host1x *host, unsigned int id, u32 thresh,
-	enum host1x_intr_action action, void *data,
-	struct host1x_waitlist *waiter, void **ref);
+int host1x_intr_add_action(struct host1x *host, struct host1x_syncpt *syncpt,
+			   u32 thresh, enum host1x_intr_action action,
+			   void *data, struct host1x_waitlist *waiter,
+			   void **ref);
 
 /*
  * Unreference an action submitted to host1x_intr_add_action().
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index db509ab8874e..e2f4a4d93d20 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -34,8 +34,7 @@
 #define HOST1X_WAIT_SYNCPT_OFFSET 0x8
 
 struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
-				    u32 num_cmdbufs, u32 num_relocs,
-				    u32 num_waitchks)
+				    u32 num_cmdbufs, u32 num_relocs)
 {
 	struct host1x_job *job = NULL;
 	unsigned int num_unpins = num_cmdbufs + num_relocs;
@@ -46,7 +45,6 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
 	total = sizeof(struct host1x_job) +
 		(u64)num_relocs * sizeof(struct host1x_reloc) +
 		(u64)num_unpins * sizeof(struct host1x_job_unpin_data) +
-		(u64)num_waitchks * sizeof(struct host1x_waitchk) +
 		(u64)num_cmdbufs * sizeof(struct host1x_job_gather) +
 		(u64)num_unpins * sizeof(dma_addr_t) +
 		(u64)num_unpins * sizeof(u32 *);
@@ -62,12 +60,10 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
 
 	/* Redistribute memory to the structs  */
 	mem += sizeof(struct host1x_job);
-	job->relocarray = num_relocs ? mem : NULL;
+	job->relocs = num_relocs ? mem : NULL;
 	mem += num_relocs * sizeof(struct host1x_reloc);
 	job->unpins = num_unpins ? mem : NULL;
 	mem += num_unpins * sizeof(struct host1x_job_unpin_data);
-	job->waitchk = num_waitchks ? mem : NULL;
-	mem += num_waitchks * sizeof(struct host1x_waitchk);
 	job->gathers = num_cmdbufs ? mem : NULL;
 	mem += num_cmdbufs * sizeof(struct host1x_job_gather);
 	job->addr_phys = num_unpins ? mem : NULL;
@@ -100,84 +96,18 @@ void host1x_job_put(struct host1x_job *job)
 EXPORT_SYMBOL(host1x_job_put);
 
 void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *bo,
-			   u32 words, u32 offset)
+			   unsigned int words, unsigned int offset)
 {
-	struct host1x_job_gather *cur_gather = &job->gathers[job->num_gathers];
+	struct host1x_job_gather *gather = &job->gathers[job->num_gathers];
+
+	gather->words = words;
+	gather->bo = bo;
+	gather->offset = offset;
 
-	cur_gather->words = words;
-	cur_gather->bo = bo;
-	cur_gather->offset = offset;
 	job->num_gathers++;
 }
 EXPORT_SYMBOL(host1x_job_add_gather);
 
-/*
- * NULL an already satisfied WAIT_SYNCPT host method, by patching its
- * args in the command stream. The method data is changed to reference
- * a reserved (never given out or incr) HOST1X_SYNCPT_RESERVED syncpt
- * with a matching threshold value of 0, so is guaranteed to be popped
- * by the host HW.
- */
-static void host1x_syncpt_patch_offset(struct host1x_syncpt *sp,
-				       struct host1x_bo *h, u32 offset)
-{
-	void *patch_addr = NULL;
-
-	/* patch the wait */
-	patch_addr = host1x_bo_kmap(h, offset >> PAGE_SHIFT);
-	if (patch_addr) {
-		host1x_syncpt_patch_wait(sp,
-					 patch_addr + (offset & ~PAGE_MASK));
-		host1x_bo_kunmap(h, offset >> PAGE_SHIFT, patch_addr);
-	} else
-		pr_err("Could not map cmdbuf for wait check\n");
-}
-
-/*
- * Check driver supplied waitchk structs for syncpt thresholds
- * that have already been satisfied and NULL the comparison (to
- * avoid a wrap condition in the HW).
- */
-static int do_waitchks(struct host1x_job *job, struct host1x *host,
-		       struct host1x_job_gather *g)
-{
-	struct host1x_bo *patch = g->bo;
-	int i;
-
-	/* compare syncpt vs wait threshold */
-	for (i = 0; i < job->num_waitchk; i++) {
-		struct host1x_waitchk *wait = &job->waitchk[i];
-		struct host1x_syncpt *sp =
-			host1x_syncpt_get(host, wait->syncpt_id);
-
-		/* validate syncpt id */
-		if (wait->syncpt_id > host1x_syncpt_nb_pts(host))
-			continue;
-
-		/* skip all other gathers */
-		if (patch != wait->bo)
-			continue;
-
-		trace_host1x_syncpt_wait_check(wait->bo, wait->offset,
-					       wait->syncpt_id, wait->thresh,
-					       host1x_syncpt_read_min(sp));
-
-		if (host1x_syncpt_is_expired(sp, wait->thresh)) {
-			dev_dbg(host->dev,
-				"drop WAIT id %u (%s) thresh 0x%x, min 0x%x\n",
-				wait->syncpt_id, sp->name, wait->thresh,
-				host1x_syncpt_read_min(sp));
-
-			host1x_syncpt_patch_offset(sp, patch,
-						   g->offset + wait->offset);
-		}
-
-		wait->bo = NULL;
-	}
-
-	return 0;
-}
-
 static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 {
 	unsigned int i;
@@ -186,7 +116,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 	job->num_unpins = 0;
 
 	for (i = 0; i < job->num_relocs; i++) {
-		struct host1x_reloc *reloc = &job->relocarray[i];
+		struct host1x_reloc *reloc = &job->relocs[i];
 		struct sg_table *sgt;
 		dma_addr_t phys_addr;
 
@@ -267,14 +197,14 @@ unpin:
 
 static int do_relocs(struct host1x_job *job, struct host1x_job_gather *g)
 {
-	int i = 0;
 	u32 last_page = ~0;
 	void *cmdbuf_page_addr = NULL;
 	struct host1x_bo *cmdbuf = g->bo;
+	unsigned int i;
 
 	/* pin & patch the relocs for one gather */
 	for (i = 0; i < job->num_relocs; i++) {
-		struct host1x_reloc *reloc = &job->relocarray[i];
+		struct host1x_reloc *reloc = &job->relocs[i];
 		u32 reloc_addr = (job->reloc_addr_phys[i] +
 				  reloc->target.offset) >> reloc->shift;
 		u32 *target;
@@ -331,17 +261,6 @@ static bool check_reloc(struct host1x_reloc *reloc, struct host1x_bo *cmdbuf,
 	return true;
 }
 
-static bool check_wait(struct host1x_waitchk *wait, struct host1x_bo *cmdbuf,
-		       unsigned int offset)
-{
-	offset *= sizeof(u32);
-
-	if (wait->bo != cmdbuf || wait->offset != offset)
-		return false;
-
-	return true;
-}
-
 struct host1x_firewall {
 	struct host1x_job *job;
 	struct device *dev;
@@ -349,9 +268,6 @@ struct host1x_firewall {
 	unsigned int num_relocs;
 	struct host1x_reloc *reloc;
 
-	unsigned int num_waitchks;
-	struct host1x_waitchk *waitchk;
-
 	struct host1x_bo *cmdbuf;
 	unsigned int offset;
 
@@ -378,20 +294,6 @@ static int check_register(struct host1x_firewall *fw, unsigned long offset)
 		fw->reloc++;
 	}
 
-	if (offset == HOST1X_WAIT_SYNCPT_OFFSET) {
-		if (fw->class != HOST1X_CLASS_HOST1X)
-			return -EINVAL;
-
-		if (!fw->num_waitchks)
-			return -EINVAL;
-
-		if (!check_wait(fw->waitchk, fw->cmdbuf, fw->offset))
-			return -EINVAL;
-
-		fw->num_waitchks--;
-		fw->waitchk++;
-	}
-
 	return 0;
 }
 
@@ -550,14 +452,12 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev)
 	struct host1x_firewall fw;
 	size_t size = 0;
 	size_t offset = 0;
-	int i;
+	unsigned int i;
 
 	fw.job = job;
 	fw.dev = dev;
-	fw.reloc = job->relocarray;
+	fw.reloc = job->relocs;
 	fw.num_relocs = job->num_relocs;
-	fw.waitchk = job->waitchk;
-	fw.num_waitchks = job->num_waitchk;
 	fw.class = job->class;
 
 	for (i = 0; i < job->num_gathers; i++) {
@@ -604,8 +504,8 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev)
 		offset += g->words * sizeof(u32);
 	}
 
-	/* No relocs and waitchks should remain at this point */
-	if (fw.num_relocs || fw.num_waitchks)
+	/* No relocs should remain at this point */
+	if (fw.num_relocs)
 		return -EINVAL;
 
 	return 0;
@@ -616,19 +516,6 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev)
 	int err;
 	unsigned int i, j;
 	struct host1x *host = dev_get_drvdata(dev->parent);
-	DECLARE_BITMAP(waitchk_mask, host1x_syncpt_nb_pts(host));
-
-	bitmap_zero(waitchk_mask, host1x_syncpt_nb_pts(host));
-	for (i = 0; i < job->num_waitchk; i++) {
-		u32 syncpt_id = job->waitchk[i].syncpt_id;
-
-		if (syncpt_id < host1x_syncpt_nb_pts(host))
-			set_bit(syncpt_id, waitchk_mask);
-	}
-
-	/* get current syncpt values for waitchk */
-	for_each_set_bit(i, waitchk_mask, host1x_syncpt_nb_pts(host))
-		host1x_syncpt_load(host->syncpt + i);
 
 	/* pin memory */
 	err = pin_job(host, job);
@@ -663,10 +550,6 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev)
 		err = do_relocs(job, g);
 		if (err)
 			break;
-
-		err = do_waitchks(job, host, g);
-		if (err)
-			break;
 	}
 
 out:
diff --git a/drivers/gpu/host1x/job.h b/drivers/gpu/host1x/job.h
index 4bda51d503ec..188400e00192 100644
--- a/drivers/gpu/host1x/job.h
+++ b/drivers/gpu/host1x/job.h
@@ -20,10 +20,10 @@
 #define __HOST1X_JOB_H
 
 struct host1x_job_gather {
-	u32 words;
+	unsigned int words;
 	dma_addr_t base;
 	struct host1x_bo *bo;
-	u32 offset;
+	unsigned int offset;
 	bool handled;
 };
 
diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index a2a952adc136..a5dbf1ba4645 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -57,8 +57,8 @@ static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host,
 						 struct host1x_client *client,
 						 unsigned long flags)
 {
-	int i;
 	struct host1x_syncpt *sp = host->syncpt;
+	unsigned int i;
 	char *name;
 
 	mutex_lock(&host->syncpt_mutex);
@@ -255,7 +255,7 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 	}
 
 	/* schedule a wakeup when the syncpoint value is reached */
-	err = host1x_intr_add_action(sp->host, sp->id, thresh,
+	err = host1x_intr_add_action(sp->host, sp, thresh,
 				     HOST1X_INTR_ACTION_WAKEUP_INTERRUPTIBLE,
 				     &wq, waiter, &ref);
 	if (err)
@@ -373,12 +373,6 @@ bool host1x_syncpt_is_expired(struct host1x_syncpt *sp, u32 thresh)
 		return (s32)(current_val - thresh) >= 0;
 }
 
-/* remove a wait pointed to by patch_addr */
-int host1x_syncpt_patch_wait(struct host1x_syncpt *sp, void *patch_addr)
-{
-	return host1x_hw_syncpt_patch_wait(sp->host, sp, patch_addr);
-}
-
 int host1x_syncpt_init(struct host1x *host)
 {
 	struct host1x_syncpt_base *bases;
diff --git a/drivers/gpu/host1x/syncpt.h b/drivers/gpu/host1x/syncpt.h
index 9d88d37c2397..d98e22325e9d 100644
--- a/drivers/gpu/host1x/syncpt.h
+++ b/drivers/gpu/host1x/syncpt.h
@@ -124,7 +124,4 @@ static inline int host1x_syncpt_is_valid(struct host1x_syncpt *sp)
 	return sp->id < host1x_syncpt_nb_pts(sp->host);
 }
 
-/* Patch a wait by replacing it with a wait for syncpt 0 value 0 */
-int host1x_syncpt_patch_wait(struct host1x_syncpt *sp, void *patch_addr);
-
 #endif
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 60252fd796f6..0000434a1fbd 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -462,10 +462,11 @@ config HID_LENOVO
 	select NEW_LEDS
 	select LEDS_CLASS
 	---help---
-	Support for Lenovo devices that are not fully compliant with HID standard.
+	Support for IBM/Lenovo devices that are not fully compliant with HID standard.
 
-	Say Y if you want support for the non-compliant features of the Lenovo
-	Thinkpad standalone keyboards, e.g:
+	Say Y if you want support for horizontal scrolling of the IBM/Lenovo
+	Scrollpoint mice or the non-compliant features of the Lenovo Thinkpad
+	standalone keyboards, e.g:
 	- ThinkPad USB Keyboard with TrackPoint (supports extra LEDs and trackpoint
 	  configuration)
 	- ThinkPad Compact Bluetooth Keyboard with TrackPoint (supports Fn keys)
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5a3a7ead3012..46f5ecd11bf7 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -525,6 +525,9 @@
 #define I2C_VENDOR_ID_HANTICK		0x0911
 #define I2C_PRODUCT_ID_HANTICK_5288	0x5288
 
+#define I2C_VENDOR_ID_RAYD		0x2386
+#define I2C_PRODUCT_ID_RAYD_3118	0x3118
+
 #define USB_VENDOR_ID_HANWANG		0x0b57
 #define USB_DEVICE_ID_HANWANG_TABLET_FIRST	0x5000
 #define USB_DEVICE_ID_HANWANG_TABLET_LAST	0x8fff
@@ -549,6 +552,13 @@
 #define USB_VENDOR_ID_HUION		0x256c
 #define USB_DEVICE_ID_HUION_TABLET	0x006e
 
+#define USB_VENDOR_ID_IBM					0x04b3
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_III			0x3100
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_PRO			0x3103
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL			0x3105
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL		0x3108
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO	0x3109
+
 #define USB_VENDOR_ID_IDEACOM		0x1cb6
 #define USB_DEVICE_ID_IDEACOM_IDC6650	0x6650
 #define USB_DEVICE_ID_IDEACOM_IDC6651	0x6651
@@ -681,6 +691,7 @@
 #define USB_DEVICE_ID_LENOVO_TPKBD	0x6009
 #define USB_DEVICE_ID_LENOVO_CUSBKBD	0x6047
 #define USB_DEVICE_ID_LENOVO_CBTKBD	0x6048
+#define USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL	0x6049
 #define USB_DEVICE_ID_LENOVO_TPPRODOCK	0x6067
 #define USB_DEVICE_ID_LENOVO_X1_COVER	0x6085
 #define USB_DEVICE_ID_LENOVO_X1_TAB	0x60a3
@@ -961,6 +972,7 @@
 #define USB_DEVICE_ID_SIS817_TOUCH	0x0817
 #define USB_DEVICE_ID_SIS_TS		0x1013
 #define USB_DEVICE_ID_SIS1030_TOUCH	0x1030
+#define USB_DEVICE_ID_SIS10FB_TOUCH	0x10fb
 
 #define USB_VENDOR_ID_SKYCABLE			0x1223
 #define	USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER	0x3F07
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 6836a856c243..930652c25120 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -387,7 +387,8 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 		break;
 
 	case POWER_SUPPLY_PROP_CAPACITY:
-		if (dev->battery_report_type == HID_FEATURE_REPORT) {
+		if (dev->battery_status != HID_BATTERY_REPORTED &&
+		    !dev->battery_avoid_query) {
 			value = hidinput_query_battery_capacity(dev);
 			if (value < 0)
 				return value;
@@ -403,17 +404,17 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 		break;
 
 	case POWER_SUPPLY_PROP_STATUS:
-		if (!dev->battery_reported &&
-		    dev->battery_report_type == HID_FEATURE_REPORT) {
+		if (dev->battery_status != HID_BATTERY_REPORTED &&
+		    !dev->battery_avoid_query) {
 			value = hidinput_query_battery_capacity(dev);
 			if (value < 0)
 				return value;
 
 			dev->battery_capacity = value;
-			dev->battery_reported = true;
+			dev->battery_status = HID_BATTERY_QUERIED;
 		}
 
-		if (!dev->battery_reported)
+		if (dev->battery_status == HID_BATTERY_UNKNOWN)
 			val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
 		else if (dev->battery_capacity == 100)
 			val->intval = POWER_SUPPLY_STATUS_FULL;
@@ -486,6 +487,14 @@ static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
 	dev->battery_report_type = report_type;
 	dev->battery_report_id = field->report->id;
 
+	/*
+	 * Stylus is normally not connected to the device and thus we
+	 * can't query the device and get meaningful battery strength.
+	 * We have to wait for the device to report it on its own.
+	 */
+	dev->battery_avoid_query = report_type == HID_INPUT_REPORT &&
+				   field->physical == HID_DG_STYLUS;
+
 	dev->battery = power_supply_register(&dev->dev, psy_desc, &psy_cfg);
 	if (IS_ERR(dev->battery)) {
 		error = PTR_ERR(dev->battery);
@@ -530,9 +539,10 @@ static void hidinput_update_battery(struct hid_device *dev, int value)
 
 	capacity = hidinput_scale_battery_capacity(dev, value);
 
-	if (!dev->battery_reported || capacity != dev->battery_capacity) {
+	if (dev->battery_status != HID_BATTERY_REPORTED ||
+	    capacity != dev->battery_capacity) {
 		dev->battery_capacity = capacity;
-		dev->battery_reported = true;
+		dev->battery_status = HID_BATTERY_REPORTED;
 		power_supply_changed(dev->battery);
 	}
 }
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 1ac4ff4d57a6..643b6eb54442 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -6,6 +6,17 @@
  *
  *  Copyright (c) 2012 Bernhard Seibold
  *  Copyright (c) 2014 Jamie Lentin <jm@lentin.co.uk>
+ *
+ * Linux IBM/Lenovo Scrollpoint mouse driver:
+ * - IBM Scrollpoint III
+ * - IBM Scrollpoint Pro
+ * - IBM Scrollpoint Optical
+ * - IBM Scrollpoint Optical 800dpi
+ * - IBM Scrollpoint Optical 800dpi Pro
+ * - Lenovo Scrollpoint Optical
+ *
+ *  Copyright (c) 2012 Peter De Wachter <pdewacht@gmail.com>
+ *  Copyright (c) 2018 Peter Ganzhorn <peter.ganzhorn@gmail.com>
  */
 
 /*
@@ -160,6 +171,17 @@ static int lenovo_input_mapping_cptkbd(struct hid_device *hdev,
 	return 0;
 }
 
+static int lenovo_input_mapping_scrollpoint(struct hid_device *hdev,
+		struct hid_input *hi, struct hid_field *field,
+		struct hid_usage *usage, unsigned long **bit, int *max)
+{
+	if (usage->hid == HID_GD_Z) {
+		hid_map_usage(hi, usage, bit, max, EV_REL, REL_HWHEEL);
+		return 1;
+	}
+	return 0;
+}
+
 static int lenovo_input_mapping(struct hid_device *hdev,
 		struct hid_input *hi, struct hid_field *field,
 		struct hid_usage *usage, unsigned long **bit, int *max)
@@ -172,6 +194,14 @@ static int lenovo_input_mapping(struct hid_device *hdev,
 	case USB_DEVICE_ID_LENOVO_CBTKBD:
 		return lenovo_input_mapping_cptkbd(hdev, hi, field,
 							usage, bit, max);
+	case USB_DEVICE_ID_IBM_SCROLLPOINT_III:
+	case USB_DEVICE_ID_IBM_SCROLLPOINT_PRO:
+	case USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL:
+	case USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL:
+	case USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO:
+	case USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL:
+		return lenovo_input_mapping_scrollpoint(hdev, hi, field,
+							usage, bit, max);
 	default:
 		return 0;
 	}
@@ -883,6 +913,12 @@ static const struct hid_device_id lenovo_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_III) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_PRO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL) },
 	{ }
 };
 
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index fbfcc8009432..b39844adea47 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -192,6 +192,11 @@ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t
 	int ret = 0, len;
 	unsigned char report_number;
 
+	if (!hidraw_table[minor] || !hidraw_table[minor]->exist) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	dev = hidraw_table[minor]->hid;
 
 	if (!dev->ll_driver->raw_request) {
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 97689e98e53f..cc33622253aa 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -47,6 +47,7 @@
 /* quirks to control the device */
 #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV	BIT(0)
 #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET	BIT(1)
+#define I2C_HID_QUIRK_RESEND_REPORT_DESCR	BIT(2)
 
 /* flags */
 #define I2C_HID_STARTED		0
@@ -171,6 +172,10 @@ static const struct i2c_hid_quirks {
 		I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV },
 	{ I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288,
 		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET },
+	{ I2C_VENDOR_ID_RAYD, I2C_PRODUCT_ID_RAYD_3118,
+		I2C_HID_QUIRK_RESEND_REPORT_DESCR },
+	{ USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH,
+		I2C_HID_QUIRK_RESEND_REPORT_DESCR },
 	{ 0, 0 }
 };
 
@@ -1220,6 +1225,16 @@ static int i2c_hid_resume(struct device *dev)
 	if (ret)
 		return ret;
 
+	/* RAYDIUM device (2386:3118) need to re-send report descr cmd
+	 * after resume, after this it will be back normal.
+	 * otherwise it issues too many incomplete reports.
+	 */
+	if (ihid->quirks & I2C_HID_QUIRK_RESEND_REPORT_DESCR) {
+		ret = i2c_hid_command(client, &hid_report_descr_cmd, NULL, 0);
+		if (ret)
+			return ret;
+	}
+
 	if (hid->driver && hid->driver->reset_resume) {
 		ret = hid->driver->reset_resume(hid);
 		return ret;
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index 157b44aacdff..acc2536c8094 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -77,21 +77,21 @@ static void process_recv(struct ishtp_cl *hid_ishtp_cl, void *recv_buf,
 	struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data;
 	int curr_hid_dev = client_data->cur_hid_dev;
 
-	if (data_len < sizeof(struct hostif_msg_hdr)) {
-		dev_err(&client_data->cl_device->dev,
-			"[hid-ish]: error, received %u which is less than data header %u\n",
-			(unsigned int)data_len,
-			(unsigned int)sizeof(struct hostif_msg_hdr));
-		++client_data->bad_recv_cnt;
-		ish_hw_reset(hid_ishtp_cl->dev);
-		return;
-	}
-
 	payload = recv_buf + sizeof(struct hostif_msg_hdr);
 	total_len = data_len;
 	cur_pos = 0;
 
 	do {
+		if (cur_pos + sizeof(struct hostif_msg) > total_len) {
+			dev_err(&client_data->cl_device->dev,
+				"[hid-ish]: error, received %u which is less than data header %u\n",
+				(unsigned int)data_len,
+				(unsigned int)sizeof(struct hostif_msg_hdr));
+			++client_data->bad_recv_cnt;
+			ish_hw_reset(hid_ishtp_cl->dev);
+			break;
+		}
+
 		recv_msg = (struct hostif_msg *)(recv_buf + cur_pos);
 		payload_len = recv_msg->hdr.size;
 
@@ -412,9 +412,7 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id,
 {
 	struct ishtp_hid_data *hid_data =  hid->driver_data;
 	struct ishtp_cl_data *client_data = hid_data->client_data;
-	static unsigned char	buf[10];
-	unsigned int	len;
-	struct hostif_msg_to_sensor *msg = (struct hostif_msg_to_sensor *)buf;
+	struct hostif_msg_to_sensor msg = {};
 	int	rv;
 	int	i;
 
@@ -426,14 +424,11 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id,
 		return;
 	}
 
-	len = sizeof(struct hostif_msg_to_sensor);
-
-	memset(msg, 0, sizeof(struct hostif_msg_to_sensor));
-	msg->hdr.command = (report_type == HID_FEATURE_REPORT) ?
+	msg.hdr.command = (report_type == HID_FEATURE_REPORT) ?
 		HOSTIF_GET_FEATURE_REPORT : HOSTIF_GET_INPUT_REPORT;
 	for (i = 0; i < client_data->num_hid_devices; ++i) {
 		if (hid == client_data->hid_sensor_hubs[i]) {
-			msg->hdr.device_id =
+			msg.hdr.device_id =
 				client_data->hid_devices[i].dev_id;
 			break;
 		}
@@ -442,8 +437,9 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id,
 	if (i == client_data->num_hid_devices)
 		return;
 
-	msg->report_id = report_id;
-	rv = ishtp_cl_send(client_data->hid_ishtp_cl, buf, len);
+	msg.report_id = report_id;
+	rv = ishtp_cl_send(client_data->hid_ishtp_cl, (uint8_t *)&msg,
+			    sizeof(msg));
 	if (rv)
 		hid_ishtp_trace(client_data,  "%s hid %p send failed\n",
 				__func__, hid);
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index f272cdd9bd55..2623a567ffba 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -418,7 +418,7 @@ static struct ishtp_cl_device *ishtp_bus_add_device(struct ishtp_device *dev,
 		list_del(&device->device_link);
 		spin_unlock_irqrestore(&dev->device_list_lock, flags);
 		dev_err(dev->devc, "Failed to register ISHTP client device\n");
-		kfree(device);
+		put_device(&device->dev);
 		return NULL;
 	}
 
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index b54ef1ffcbec..ee7a37eb159a 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -1213,8 +1213,10 @@ static int __wacom_devm_sysfs_create_group(struct wacom *wacom,
 	devres->root = root;
 
 	error = sysfs_create_group(devres->root, group);
-	if (error)
+	if (error) {
+		devres_free(devres);
 		return error;
+	}
 
 	devres_add(&wacom->hdev->dev, devres);
 
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 6da16a879c9f..5f947ec20dcb 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -689,6 +689,45 @@ static int wacom_intuos_get_tool_type(int tool_id)
 	return tool_type;
 }
 
+static void wacom_exit_report(struct wacom_wac *wacom)
+{
+	struct input_dev *input = wacom->pen_input;
+	struct wacom_features *features = &wacom->features;
+	unsigned char *data = wacom->data;
+	int idx = (features->type == INTUOS) ? (data[1] & 0x01) : 0;
+
+	/*
+	 * Reset all states otherwise we lose the initial states
+	 * when in-prox next time
+	 */
+	input_report_abs(input, ABS_X, 0);
+	input_report_abs(input, ABS_Y, 0);
+	input_report_abs(input, ABS_DISTANCE, 0);
+	input_report_abs(input, ABS_TILT_X, 0);
+	input_report_abs(input, ABS_TILT_Y, 0);
+	if (wacom->tool[idx] >= BTN_TOOL_MOUSE) {
+		input_report_key(input, BTN_LEFT, 0);
+		input_report_key(input, BTN_MIDDLE, 0);
+		input_report_key(input, BTN_RIGHT, 0);
+		input_report_key(input, BTN_SIDE, 0);
+		input_report_key(input, BTN_EXTRA, 0);
+		input_report_abs(input, ABS_THROTTLE, 0);
+		input_report_abs(input, ABS_RZ, 0);
+	} else {
+		input_report_abs(input, ABS_PRESSURE, 0);
+		input_report_key(input, BTN_STYLUS, 0);
+		input_report_key(input, BTN_STYLUS2, 0);
+		input_report_key(input, BTN_TOUCH, 0);
+		input_report_abs(input, ABS_WHEEL, 0);
+		if (features->type >= INTUOS3S)
+			input_report_abs(input, ABS_Z, 0);
+	}
+	input_report_key(input, wacom->tool[idx], 0);
+	input_report_abs(input, ABS_MISC, 0); /* reset tool id */
+	input_event(input, EV_MSC, MSC_SERIAL, wacom->serial[idx]);
+	wacom->id[idx] = 0;
+}
+
 static int wacom_intuos_inout(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
@@ -741,36 +780,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom)
 		if (!wacom->id[idx])
 			return 1;
 
-		/*
-		 * Reset all states otherwise we lose the initial states
-		 * when in-prox next time
-		 */
-		input_report_abs(input, ABS_X, 0);
-		input_report_abs(input, ABS_Y, 0);
-		input_report_abs(input, ABS_DISTANCE, 0);
-		input_report_abs(input, ABS_TILT_X, 0);
-		input_report_abs(input, ABS_TILT_Y, 0);
-		if (wacom->tool[idx] >= BTN_TOOL_MOUSE) {
-			input_report_key(input, BTN_LEFT, 0);
-			input_report_key(input, BTN_MIDDLE, 0);
-			input_report_key(input, BTN_RIGHT, 0);
-			input_report_key(input, BTN_SIDE, 0);
-			input_report_key(input, BTN_EXTRA, 0);
-			input_report_abs(input, ABS_THROTTLE, 0);
-			input_report_abs(input, ABS_RZ, 0);
-		} else {
-			input_report_abs(input, ABS_PRESSURE, 0);
-			input_report_key(input, BTN_STYLUS, 0);
-			input_report_key(input, BTN_STYLUS2, 0);
-			input_report_key(input, BTN_TOUCH, 0);
-			input_report_abs(input, ABS_WHEEL, 0);
-			if (features->type >= INTUOS3S)
-				input_report_abs(input, ABS_Z, 0);
-		}
-		input_report_key(input, wacom->tool[idx], 0);
-		input_report_abs(input, ABS_MISC, 0); /* reset tool id */
-		input_event(input, EV_MSC, MSC_SERIAL, wacom->serial[idx]);
-		wacom->id[idx] = 0;
+		wacom_exit_report(wacom);
 		return 2;
 	}
 
@@ -1235,6 +1245,12 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom)
 		if (!valid)
 			continue;
 
+		if (!prox) {
+			wacom->shared->stylus_in_proximity = false;
+			wacom_exit_report(wacom);
+			input_sync(pen_input);
+			return;
+		}
 		if (range) {
 			input_report_abs(pen_input, ABS_X, get_unaligned_le16(&frame[1]));
 			input_report_abs(pen_input, ABS_Y, get_unaligned_le16(&frame[3]));
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 72855182b191..ced041899456 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -63,6 +63,9 @@ static __u32 vmbus_get_next_version(__u32 current_version)
 	case (VERSION_WIN10):
 		return VERSION_WIN8_1;
 
+	case (VERSION_WIN10_V5):
+		return VERSION_WIN10;
+
 	case (VERSION_WS2008):
 	default:
 		return VERSION_INVAL;
@@ -80,9 +83,29 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 
 	msg = (struct vmbus_channel_initiate_contact *)msginfo->msg;
 
+	memset(msg, 0, sizeof(*msg));
 	msg->header.msgtype = CHANNELMSG_INITIATE_CONTACT;
 	msg->vmbus_version_requested = version;
-	msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
+
+	/*
+	 * VMBus protocol 5.0 (VERSION_WIN10_V5) requires that we must use
+	 * VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate Contact Message,
+	 * and for subsequent messages, we must use the Message Connection ID
+	 * field in the host-returned Version Response Message. And, with
+	 * VERSION_WIN10_V5, we don't use msg->interrupt_page, but we tell
+	 * the host explicitly that we still use VMBUS_MESSAGE_SINT(2) for
+	 * compatibility.
+	 *
+	 * On old hosts, we should always use VMBUS_MESSAGE_CONNECTION_ID (1).
+	 */
+	if (version >= VERSION_WIN10_V5) {
+		msg->msg_sint = VMBUS_MESSAGE_SINT;
+		vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID_4;
+	} else {
+		msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
+		vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID;
+	}
+
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
 	/*
@@ -137,6 +160,10 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	/* Check if successful */
 	if (msginfo->response.version_response.version_supported) {
 		vmbus_connection.conn_state = CONNECTED;
+
+		if (version >= VERSION_WIN10_V5)
+			vmbus_connection.msg_conn_id =
+				msginfo->response.version_response.msg_conn_id;
 	} else {
 		return -ECONNREFUSED;
 	}
@@ -354,13 +381,14 @@ void vmbus_on_event(unsigned long data)
  */
 int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep)
 {
+	struct vmbus_channel_message_header *hdr;
 	union hv_connection_id conn_id;
 	int ret = 0;
 	int retries = 0;
 	u32 usec = 1;
 
 	conn_id.asu32 = 0;
-	conn_id.u.id = VMBUS_MESSAGE_CONNECTION_ID;
+	conn_id.u.id = vmbus_connection.msg_conn_id;
 
 	/*
 	 * hv_post_message() can have transient failures because of
@@ -373,6 +401,18 @@ int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep)
 		switch (ret) {
 		case HV_STATUS_INVALID_CONNECTION_ID:
 			/*
+			 * See vmbus_negotiate_version(): VMBus protocol 5.0
+			 * requires that we must use
+			 * VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate
+			 * Contact message, but on old hosts that only
+			 * support VMBus protocol 4.0 or lower, here we get
+			 * HV_STATUS_INVALID_CONNECTION_ID and we should
+			 * return an error immediately without retrying.
+			 */
+			hdr = buffer;
+			if (hdr->msgtype == CHANNELMSG_INITIATE_CONTACT)
+				return -EINVAL;
+			/*
 			 * We could get this if we send messages too
 			 * frequently.
 			 */
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index f761bef36e77..72eaba3d50fc 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -187,6 +187,7 @@ struct hv_input_post_message {
 
 enum {
 	VMBUS_MESSAGE_CONNECTION_ID	= 1,
+	VMBUS_MESSAGE_CONNECTION_ID_4	= 4,
 	VMBUS_MESSAGE_PORT_ID		= 1,
 	VMBUS_EVENT_CONNECTION_ID	= 2,
 	VMBUS_EVENT_PORT_ID		= 2,
@@ -302,6 +303,8 @@ struct vmbus_connection {
 	 */
 	int connect_cpu;
 
+	u32 msg_conn_id;
+
 	atomic_t offer_in_progress;
 
 	enum vmbus_connect_state conn_state;
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f249a4428458..f10840ad465c 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -272,7 +272,7 @@ config SENSORS_K8TEMP
 
 config SENSORS_K10TEMP
 	tristate "AMD Family 10h+ temperature sensor"
-	depends on X86 && PCI
+	depends on X86 && PCI && AMD_NB
 	help
 	  If you say yes here you get support for the temperature
 	  sensor(s) inside your CPU. Supported are later revisions of
@@ -717,15 +717,12 @@ config SENSORS_LTC2945
 	  be called ltc2945.
 
 config SENSORS_LTC2990
-	tristate "Linear Technology LTC2990 (current monitoring mode only)"
+	tristate "Linear Technology LTC2990"
 	depends on I2C
 	help
 	  If you say yes here you get support for Linear Technology LTC2990
 	  I2C System Monitor. The LTC2990 supports a combination of voltage,
-	  current and temperature monitoring, but in addition to the Vcc supply
-	  voltage and chip temperature, this driver currently only supports
-	  reading two currents by measuring two differential voltages across
-	  series resistors.
+	  current and temperature monitoring.
 
 	  This driver can also be built as a module. If so, the module will
 	  be called ltc2990.
diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c
index 975c43d446f8..a6636fe42189 100644
--- a/drivers/hwmon/asus_atk0110.c
+++ b/drivers/hwmon/asus_atk0110.c
@@ -125,6 +125,8 @@ struct atk_data {
 	int temperature_count;
 	int fan_count;
 	struct list_head sensor_list;
+	struct attribute_group attr_group;
+	const struct attribute_group *attr_groups[2];
 
 	struct {
 		struct dentry *root;
@@ -188,7 +190,6 @@ static int atk_add(struct acpi_device *device);
 static int atk_remove(struct acpi_device *device);
 static void atk_print_sensor(struct atk_data *data, union acpi_object *obj);
 static int atk_read_value(struct atk_sensor_data *sensor, u64 *value);
-static void atk_free_sensors(struct atk_data *data);
 
 static struct acpi_driver atk_driver = {
 	.name	= ATK_HID,
@@ -262,14 +263,6 @@ static ssize_t atk_limit2_show(struct device *dev,
 	return sprintf(buf, "%lld\n", value);
 }
 
-static ssize_t atk_name_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "atk0110\n");
-}
-static struct device_attribute atk_name_attr =
-		__ATTR(name, 0444, atk_name_show, NULL);
-
 static void atk_init_attribute(struct device_attribute *attr, char *name,
 		sysfs_show_func show)
 {
@@ -912,15 +905,13 @@ static int atk_add_sensor(struct atk_data *data, union acpi_object *obj)
 	limit1 = atk_get_pack_member(data, obj, HWMON_PACK_LIMIT1);
 	limit2 = atk_get_pack_member(data, obj, HWMON_PACK_LIMIT2);
 
-	sensor = kzalloc(sizeof(*sensor), GFP_KERNEL);
+	sensor = devm_kzalloc(dev, sizeof(*sensor), GFP_KERNEL);
 	if (!sensor)
 		return -ENOMEM;
 
-	sensor->acpi_name = kstrdup(name->string.pointer, GFP_KERNEL);
-	if (!sensor->acpi_name) {
-		err = -ENOMEM;
-		goto out;
-	}
+	sensor->acpi_name = devm_kstrdup(dev, name->string.pointer, GFP_KERNEL);
+	if (!sensor->acpi_name)
+		return -ENOMEM;
 
 	INIT_LIST_HEAD(&sensor->list);
 	sensor->type = type;
@@ -961,9 +952,6 @@ static int atk_add_sensor(struct atk_data *data, union acpi_object *obj)
 	(*num)++;
 
 	return 1;
-out:
-	kfree(sensor);
-	return err;
 }
 
 static int atk_enumerate_old_hwmon(struct atk_data *data)
@@ -1004,8 +992,7 @@ static int atk_enumerate_old_hwmon(struct atk_data *data)
 		dev_warn(dev, METHOD_OLD_ENUM_TMP ": ACPI exception: %s\n",
 				acpi_format_exception(status));
 
-		ret = -ENODEV;
-		goto cleanup;
+		return -ENODEV;
 	}
 
 	pack = buf.pointer;
@@ -1026,8 +1013,7 @@ static int atk_enumerate_old_hwmon(struct atk_data *data)
 		dev_warn(dev, METHOD_OLD_ENUM_FAN ": ACPI exception: %s\n",
 				acpi_format_exception(status));
 
-		ret = -ENODEV;
-		goto cleanup;
+		return -ENODEV;
 	}
 
 	pack = buf.pointer;
@@ -1041,9 +1027,6 @@ static int atk_enumerate_old_hwmon(struct atk_data *data)
 	ACPI_FREE(buf.pointer);
 
 	return count;
-cleanup:
-	atk_free_sensors(data);
-	return ret;
 }
 
 static int atk_ec_present(struct atk_data *data)
@@ -1193,76 +1176,44 @@ static int atk_enumerate_new_hwmon(struct atk_data *data)
 	return err;
 }
 
-static int atk_create_files(struct atk_data *data)
+static int atk_init_attribute_groups(struct atk_data *data)
 {
+	struct device *dev = &data->acpi_dev->dev;
 	struct atk_sensor_data *s;
-	int err;
+	struct attribute **attrs;
+	int i = 0;
+	int len = (data->voltage_count + data->temperature_count
+			+ data->fan_count) * 4 + 1;
 
-	list_for_each_entry(s, &data->sensor_list, list) {
-		err = device_create_file(data->hwmon_dev, &s->input_attr);
-		if (err)
-			return err;
-		err = device_create_file(data->hwmon_dev, &s->label_attr);
-		if (err)
-			return err;
-		err = device_create_file(data->hwmon_dev, &s->limit1_attr);
-		if (err)
-			return err;
-		err = device_create_file(data->hwmon_dev, &s->limit2_attr);
-		if (err)
-			return err;
-	}
-
-	err = device_create_file(data->hwmon_dev, &atk_name_attr);
-
-	return err;
-}
-
-static void atk_remove_files(struct atk_data *data)
-{
-	struct atk_sensor_data *s;
+	attrs = devm_kcalloc(dev, len, sizeof(struct attribute *), GFP_KERNEL);
+	if (!attrs)
+		return -ENOMEM;
 
 	list_for_each_entry(s, &data->sensor_list, list) {
-		device_remove_file(data->hwmon_dev, &s->input_attr);
-		device_remove_file(data->hwmon_dev, &s->label_attr);
-		device_remove_file(data->hwmon_dev, &s->limit1_attr);
-		device_remove_file(data->hwmon_dev, &s->limit2_attr);
+		attrs[i++] = &s->input_attr.attr;
+		attrs[i++] = &s->label_attr.attr;
+		attrs[i++] = &s->limit1_attr.attr;
+		attrs[i++] = &s->limit2_attr.attr;
 	}
-	device_remove_file(data->hwmon_dev, &atk_name_attr);
-}
 
-static void atk_free_sensors(struct atk_data *data)
-{
-	struct list_head *head = &data->sensor_list;
-	struct atk_sensor_data *s, *tmp;
+	data->attr_group.attrs = attrs;
+	data->attr_groups[0] = &data->attr_group;
 
-	list_for_each_entry_safe(s, tmp, head, list) {
-		kfree(s->acpi_name);
-		kfree(s);
-	}
+	return 0;
 }
 
 static int atk_register_hwmon(struct atk_data *data)
 {
 	struct device *dev = &data->acpi_dev->dev;
-	int err;
 
 	dev_dbg(dev, "registering hwmon device\n");
-	data->hwmon_dev = hwmon_device_register(dev);
+	data->hwmon_dev = hwmon_device_register_with_groups(dev, "atk0110",
+							    data,
+							    data->attr_groups);
 	if (IS_ERR(data->hwmon_dev))
 		return PTR_ERR(data->hwmon_dev);
 
-	dev_dbg(dev, "populating sysfs directory\n");
-	err = atk_create_files(data);
-	if (err)
-		goto remove;
-
 	return 0;
-remove:
-	/* Cleanup the registered files */
-	atk_remove_files(data);
-	hwmon_device_unregister(data->hwmon_dev);
-	return err;
 }
 
 static int atk_probe_if(struct atk_data *data)
@@ -1350,7 +1301,7 @@ static int atk_add(struct acpi_device *device)
 
 	dev_dbg(&device->dev, "adding...\n");
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = devm_kzalloc(&device->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
@@ -1397,20 +1348,20 @@ static int atk_add(struct acpi_device *device)
 		goto out;
 	}
 
+	err = atk_init_attribute_groups(data);
+	if (err)
+		goto out;
 	err = atk_register_hwmon(data);
 	if (err)
-		goto cleanup;
+		goto out;
 
 	atk_debugfs_init(data);
 
 	device->driver_data = data;
 	return 0;
-cleanup:
-	atk_free_sensors(data);
 out:
 	if (data->disable_ec)
 		atk_ec_ctl(data, 0);
-	kfree(data);
 	return err;
 }
 
@@ -1423,8 +1374,6 @@ static int atk_remove(struct acpi_device *device)
 
 	atk_debugfs_cleanup(data);
 
-	atk_remove_files(data);
-	atk_free_sensors(data);
 	hwmon_device_unregister(data->hwmon_dev);
 
 	if (data->disable_ec) {
@@ -1432,8 +1381,6 @@ static int atk_remove(struct acpi_device *device)
 			dev_err(&device->dev, "Failed to disable EC\n");
 	}
 
-	kfree(data);
-
 	return 0;
 }
 
diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c
index 5e78229ade04..22d3a84f13ef 100644
--- a/drivers/hwmon/fschmd.c
+++ b/drivers/hwmon/fschmd.c
@@ -105,7 +105,7 @@ static const u8 FSCHMD_REG_VOLT[7][6] = {
 static const int FSCHMD_NO_VOLT_SENSORS[7] = { 3, 3, 3, 3, 3, 3, 6 };
 
 /*
- * minimum pwm at which the fan is driven (pwm can by increased depending on
+ * minimum pwm at which the fan is driven (pwm can be increased depending on
  * the temp. Notice that for the scy some fans share there minimum speed.
  * Also notice that with the scy the sensor order is different than with the
  * other chips, this order was in the 2.4 driver and kept for consistency.
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 32083e452cde..e88c01961948 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -698,6 +698,9 @@ hwmon_device_register_with_info(struct device *dev, const char *name,
 	if (chip && (!chip->ops || !chip->ops->is_visible || !chip->info))
 		return ERR_PTR(-EINVAL);
 
+	if (chip && !dev)
+		return ERR_PTR(-EINVAL);
+
 	return __hwmon_device_register(dev, name, drvdata, chip, extra_groups);
 }
 EXPORT_SYMBOL_GPL(hwmon_device_register_with_info);
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 051a72eecb24..17c6460ae351 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -23,6 +23,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <asm/amd_nb.h>
 #include <asm/processor.h>
 
 MODULE_DESCRIPTION("AMD Family 10h+ CPU core temperature monitor");
@@ -36,10 +37,18 @@ MODULE_PARM_DESC(force, "force loading on processors with erratum 319");
 /* Provide lock for writing to NB_SMU_IND_ADDR */
 static DEFINE_MUTEX(nb_smu_ind_mutex);
 
+#ifndef PCI_DEVICE_ID_AMD_15H_M70H_NB_F3
+#define PCI_DEVICE_ID_AMD_15H_M70H_NB_F3	0x15b3
+#endif
+
 #ifndef PCI_DEVICE_ID_AMD_17H_DF_F3
 #define PCI_DEVICE_ID_AMD_17H_DF_F3	0x1463
 #endif
 
+#ifndef PCI_DEVICE_ID_AMD_17H_M10H_DF_F3
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3	0x15eb
+#endif
+
 /* CPUID function 0x80000001, ebx */
 #define CPUID_PKGTYPE_MASK	0xf0000000
 #define CPUID_PKGTYPE_F		0x00000000
@@ -59,10 +68,12 @@ static DEFINE_MUTEX(nb_smu_ind_mutex);
 #define  NB_CAP_HTC			0x00000400
 
 /*
- * For F15h M60h, functionality of REG_REPORTED_TEMPERATURE
- * has been moved to D0F0xBC_xD820_0CA4 [Reported Temperature
- * Control]
+ * For F15h M60h and M70h, REG_HARDWARE_THERMAL_CONTROL
+ * and REG_REPORTED_TEMPERATURE have been moved to
+ * D0F0xBC_xD820_0C64 [Hardware Temperature Control]
+ * D0F0xBC_xD820_0CA4 [Reported Temperature Control]
  */
+#define F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET	0xd8200c64
 #define F15H_M60H_REPORTED_TEMP_CTRL_OFFSET	0xd8200ca4
 
 /* F17h M01h Access througn SMN */
@@ -70,8 +81,11 @@ static DEFINE_MUTEX(nb_smu_ind_mutex);
 
 struct k10temp_data {
 	struct pci_dev *pdev;
+	void (*read_htcreg)(struct pci_dev *pdev, u32 *regval);
 	void (*read_tempreg)(struct pci_dev *pdev, u32 *regval);
 	int temp_offset;
+	u32 temp_adjust_mask;
+	bool show_tdie;
 };
 
 struct tctl_offset {
@@ -84,6 +98,7 @@ static const struct tctl_offset tctl_offset_table[] = {
 	{ 0x17, "AMD Ryzen 5 1600X", 20000 },
 	{ 0x17, "AMD Ryzen 7 1700X", 20000 },
 	{ 0x17, "AMD Ryzen 7 1800X", 20000 },
+	{ 0x17, "AMD Ryzen 7 2700X", 10000 },
 	{ 0x17, "AMD Ryzen Threadripper 1950X", 27000 },
 	{ 0x17, "AMD Ryzen Threadripper 1920X", 27000 },
 	{ 0x17, "AMD Ryzen Threadripper 1900X", 27000 },
@@ -92,6 +107,11 @@ static const struct tctl_offset tctl_offset_table[] = {
 	{ 0x17, "AMD Ryzen Threadripper 1910", 10000 },
 };
 
+static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
+{
+	pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, regval);
+}
+
 static void read_tempreg_pci(struct pci_dev *pdev, u32 *regval)
 {
 	pci_read_config_dword(pdev, REG_REPORTED_TEMPERATURE, regval);
@@ -108,6 +128,12 @@ static void amd_nb_index_read(struct pci_dev *pdev, unsigned int devfn,
 	mutex_unlock(&nb_smu_ind_mutex);
 }
 
+static void read_htcreg_nb_f15(struct pci_dev *pdev, u32 *regval)
+{
+	amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8,
+			  F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET, regval);
+}
+
 static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval)
 {
 	amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8,
@@ -116,19 +142,28 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval)
 
 static void read_tempreg_nb_f17(struct pci_dev *pdev, u32 *regval)
 {
-	amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0x60,
-			  F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval);
+	amd_smn_read(amd_pci_dev_to_node_id(pdev),
+		     F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval);
 }
 
-static ssize_t temp1_input_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static unsigned int get_raw_temp(struct k10temp_data *data)
 {
-	struct k10temp_data *data = dev_get_drvdata(dev);
-	u32 regval;
 	unsigned int temp;
+	u32 regval;
 
 	data->read_tempreg(data->pdev, &regval);
 	temp = (regval >> 21) * 125;
+	if (regval & data->temp_adjust_mask)
+		temp -= 49000;
+	return temp;
+}
+
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct k10temp_data *data = dev_get_drvdata(dev);
+	unsigned int temp = get_raw_temp(data);
+
 	if (temp > data->temp_offset)
 		temp -= data->temp_offset;
 	else
@@ -137,6 +172,23 @@ static ssize_t temp1_input_show(struct device *dev,
 	return sprintf(buf, "%u\n", temp);
 }
 
+static ssize_t temp2_input_show(struct device *dev,
+				struct device_attribute *devattr, char *buf)
+{
+	struct k10temp_data *data = dev_get_drvdata(dev);
+	unsigned int temp = get_raw_temp(data);
+
+	return sprintf(buf, "%u\n", temp);
+}
+
+static ssize_t temp_label_show(struct device *dev,
+			       struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+
+	return sprintf(buf, "%s\n", attr->index ? "Tctl" : "Tdie");
+}
+
 static ssize_t temp1_max_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
@@ -152,8 +204,7 @@ static ssize_t show_temp_crit(struct device *dev,
 	u32 regval;
 	int value;
 
-	pci_read_config_dword(data->pdev,
-			      REG_HARDWARE_THERMAL_CONTROL, &regval);
+	data->read_htcreg(data->pdev, &regval);
 	value = ((regval >> 16) & 0x7f) * 500 + 52000;
 	if (show_hyst)
 		value -= ((regval >> 24) & 0xf) * 500;
@@ -165,22 +216,39 @@ static DEVICE_ATTR_RO(temp1_max);
 static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, show_temp_crit, NULL, 1);
 
+static SENSOR_DEVICE_ATTR(temp1_label, 0444, temp_label_show, NULL, 0);
+static DEVICE_ATTR_RO(temp2_input);
+static SENSOR_DEVICE_ATTR(temp2_label, 0444, temp_label_show, NULL, 1);
+
 static umode_t k10temp_is_visible(struct kobject *kobj,
 				  struct attribute *attr, int index)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct k10temp_data *data = dev_get_drvdata(dev);
 	struct pci_dev *pdev = data->pdev;
-
-	if (index >= 2) {
-		u32 reg_caps, reg_htc;
+	u32 reg;
+
+	switch (index) {
+	case 0 ... 1:	/* temp1_input, temp1_max */
+	default:
+		break;
+	case 2 ... 3:	/* temp1_crit, temp1_crit_hyst */
+		if (!data->read_htcreg)
+			return 0;
 
 		pci_read_config_dword(pdev, REG_NORTHBRIDGE_CAPABILITIES,
-				      &reg_caps);
-		pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL,
-				      &reg_htc);
-		if (!(reg_caps & NB_CAP_HTC) || !(reg_htc & HTC_ENABLE))
+				      &reg);
+		if (!(reg & NB_CAP_HTC))
 			return 0;
+
+		data->read_htcreg(data->pdev, &reg);
+		if (!(reg & HTC_ENABLE))
+			return 0;
+		break;
+	case 4 ... 6:	/* temp1_label, temp2_input, temp2_label */
+		if (!data->show_tdie)
+			return 0;
+		break;
 	}
 	return attr->mode;
 }
@@ -190,6 +258,9 @@ static struct attribute *k10temp_attrs[] = {
 	&dev_attr_temp1_max.attr,
 	&sensor_dev_attr_temp1_crit.dev_attr.attr,
 	&sensor_dev_attr_temp1_crit_hyst.dev_attr.attr,
+	&sensor_dev_attr_temp1_label.dev_attr.attr,
+	&dev_attr_temp2_input.attr,
+	&sensor_dev_attr_temp2_label.dev_attr.attr,
 	NULL
 };
 
@@ -259,12 +330,17 @@ static int k10temp_probe(struct pci_dev *pdev,
 	data->pdev = pdev;
 
 	if (boot_cpu_data.x86 == 0x15 && (boot_cpu_data.x86_model == 0x60 ||
-					  boot_cpu_data.x86_model == 0x70))
+					  boot_cpu_data.x86_model == 0x70)) {
+		data->read_htcreg = read_htcreg_nb_f15;
 		data->read_tempreg = read_tempreg_nb_f15;
-	else if (boot_cpu_data.x86 == 0x17)
+	} else if (boot_cpu_data.x86 == 0x17) {
+		data->temp_adjust_mask = 0x80000;
 		data->read_tempreg = read_tempreg_nb_f17;
-	else
+		data->show_tdie = true;
+	} else {
+		data->read_htcreg = read_htcreg_pci;
 		data->read_tempreg = read_tempreg_pci;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(tctl_offset_table); i++) {
 		const struct tctl_offset *entry = &tctl_offset_table[i];
@@ -289,9 +365,11 @@ static const struct pci_device_id k10temp_id_table[] = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M70H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, k10temp_id_table);
diff --git a/drivers/hwmon/ltc2990.c b/drivers/hwmon/ltc2990.c
index 8f8fe059ab48..2aefdc58b242 100644
--- a/drivers/hwmon/ltc2990.c
+++ b/drivers/hwmon/ltc2990.c
@@ -5,18 +5,16 @@
  * Author: Mike Looijmans <mike.looijmans@topic.nl>
  *
  * License: GPLv2
- *
- * This driver assumes the chip is wired as a dual current monitor, and
- * reports the voltage drop across two series resistors. It also reports
- * the chip's internal temperature and Vcc power supply voltage.
  */
 
+#include <linux/bitops.h>
 #include <linux/err.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/i2c.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of.h>
 
 #define LTC2990_STATUS	0x00
 #define LTC2990_CONTROL	0x01
@@ -28,45 +26,108 @@
 #define LTC2990_V4_MSB	0x0C
 #define LTC2990_VCC_MSB	0x0E
 
-#define LTC2990_CONTROL_KELVIN		BIT(7)
-#define LTC2990_CONTROL_SINGLE		BIT(6)
-#define LTC2990_CONTROL_MEASURE_ALL	(0x3 << 3)
-#define LTC2990_CONTROL_MODE_CURRENT	0x06
-#define LTC2990_CONTROL_MODE_VOLTAGE	0x07
+#define LTC2990_IN0	BIT(0)
+#define LTC2990_IN1	BIT(1)
+#define LTC2990_IN2	BIT(2)
+#define LTC2990_IN3	BIT(3)
+#define LTC2990_IN4	BIT(4)
+#define LTC2990_CURR1	BIT(5)
+#define LTC2990_CURR2	BIT(6)
+#define LTC2990_TEMP1	BIT(7)
+#define LTC2990_TEMP2	BIT(8)
+#define LTC2990_TEMP3	BIT(9)
+#define LTC2990_NONE	0
+#define LTC2990_ALL	GENMASK(9, 0)
 
-/* convert raw register value to sign-extended integer in 16-bit range */
-static int ltc2990_voltage_to_int(int raw)
-{
-	if (raw & BIT(14))
-		return -(0x4000 - (raw & 0x3FFF)) << 2;
-	else
-		return (raw & 0x3FFF) << 2;
-}
+#define LTC2990_MODE0_SHIFT	0
+#define LTC2990_MODE0_MASK	GENMASK(2, 0)
+#define LTC2990_MODE1_SHIFT	3
+#define LTC2990_MODE1_MASK	GENMASK(1, 0)
+
+/* Enabled measurements for mode bits 2..0 */
+static const int ltc2990_attrs_ena_0[] = {
+	LTC2990_IN1 | LTC2990_IN2 | LTC2990_TEMP3,
+	LTC2990_CURR1 | LTC2990_TEMP3,
+	LTC2990_CURR1 | LTC2990_IN3 | LTC2990_IN4,
+	LTC2990_TEMP2 | LTC2990_IN3 | LTC2990_IN4,
+	LTC2990_TEMP2 | LTC2990_CURR2,
+	LTC2990_TEMP2 | LTC2990_TEMP3,
+	LTC2990_CURR1 | LTC2990_CURR2,
+	LTC2990_IN1 | LTC2990_IN2 | LTC2990_IN3 | LTC2990_IN4
+};
+
+/* Enabled measurements for mode bits 4..3 */
+static const int ltc2990_attrs_ena_1[] = {
+	LTC2990_NONE,
+	LTC2990_TEMP2 | LTC2990_IN1 | LTC2990_CURR1,
+	LTC2990_TEMP3 | LTC2990_IN3 | LTC2990_CURR2,
+	LTC2990_ALL
+};
+
+struct ltc2990_data {
+	struct i2c_client *i2c;
+	u32 mode[2];
+};
 
 /* Return the converted value from the given register in uV or mC */
-static int ltc2990_get_value(struct i2c_client *i2c, u8 reg, int *result)
+static int ltc2990_get_value(struct i2c_client *i2c, int index, int *result)
 {
 	int val;
+	u8 reg;
+
+	switch (index) {
+	case LTC2990_IN0:
+		reg = LTC2990_VCC_MSB;
+		break;
+	case LTC2990_IN1:
+	case LTC2990_CURR1:
+	case LTC2990_TEMP2:
+		reg = LTC2990_V1_MSB;
+		break;
+	case LTC2990_IN2:
+		reg = LTC2990_V2_MSB;
+		break;
+	case LTC2990_IN3:
+	case LTC2990_CURR2:
+	case LTC2990_TEMP3:
+		reg = LTC2990_V3_MSB;
+		break;
+	case LTC2990_IN4:
+		reg = LTC2990_V4_MSB;
+		break;
+	case LTC2990_TEMP1:
+		reg = LTC2990_TINT_MSB;
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	val = i2c_smbus_read_word_swapped(i2c, reg);
 	if (unlikely(val < 0))
 		return val;
 
-	switch (reg) {
-	case LTC2990_TINT_MSB:
-		/* internal temp, 0.0625 degrees/LSB, 13-bit  */
-		val = (val & 0x1FFF) << 3;
-		*result = (val * 1000) >> 7;
+	switch (index) {
+	case LTC2990_TEMP1:
+	case LTC2990_TEMP2:
+	case LTC2990_TEMP3:
+		/* temp, 0.0625 degrees/LSB */
+		*result = sign_extend32(val, 12) * 1000 / 16;
 		break;
-	case LTC2990_V1_MSB:
-	case LTC2990_V3_MSB:
-		 /* Vx-Vy, 19.42uV/LSB. Depends on mode. */
-		*result = ltc2990_voltage_to_int(val) * 1942 / (4 * 100);
+	case LTC2990_CURR1:
+	case LTC2990_CURR2:
+		 /* Vx-Vy, 19.42uV/LSB */
+		*result = sign_extend32(val, 14) * 1942 / 100;
 		break;
-	case LTC2990_VCC_MSB:
-		/* Vcc, 305.18μV/LSB, 2.5V offset */
-		*result = (ltc2990_voltage_to_int(val) * 30518 /
-			   (4 * 100 * 1000)) + 2500;
+	case LTC2990_IN0:
+		/* Vcc, 305.18uV/LSB, 2.5V offset */
+		*result = sign_extend32(val, 14) * 30518 / (100 * 1000) + 2500;
+		break;
+	case LTC2990_IN1:
+	case LTC2990_IN2:
+	case LTC2990_IN3:
+	case LTC2990_IN4:
+		/* Vx, 305.18uV/LSB */
+		*result = sign_extend32(val, 14) * 30518 / (100 * 1000);
 		break;
 	default:
 		return -EINVAL; /* won't happen, keep compiler happy */
@@ -79,48 +140,117 @@ static ssize_t ltc2990_show_value(struct device *dev,
 				  struct device_attribute *da, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	struct ltc2990_data *data = dev_get_drvdata(dev);
 	int value;
 	int ret;
 
-	ret = ltc2990_get_value(dev_get_drvdata(dev), attr->index, &value);
+	ret = ltc2990_get_value(data->i2c, attr->index, &value);
 	if (unlikely(ret < 0))
 		return ret;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", value);
 }
 
+static umode_t ltc2990_attrs_visible(struct kobject *kobj,
+				     struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct ltc2990_data *data = dev_get_drvdata(dev);
+	struct device_attribute *da =
+			container_of(a, struct device_attribute, attr);
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+
+	int attrs_mask = LTC2990_IN0 | LTC2990_TEMP1 |
+			 (ltc2990_attrs_ena_0[data->mode[0]] &
+			  ltc2990_attrs_ena_1[data->mode[1]]);
+
+	if (attr->index & attrs_mask)
+		return a->mode;
+
+	return 0;
+}
+
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, ltc2990_show_value, NULL,
-			  LTC2990_TINT_MSB);
+			  LTC2990_TEMP1);
+static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_TEMP2);
+static SENSOR_DEVICE_ATTR(temp3_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_TEMP3);
 static SENSOR_DEVICE_ATTR(curr1_input, S_IRUGO, ltc2990_show_value, NULL,
-			  LTC2990_V1_MSB);
+			  LTC2990_CURR1);
 static SENSOR_DEVICE_ATTR(curr2_input, S_IRUGO, ltc2990_show_value, NULL,
-			  LTC2990_V3_MSB);
+			  LTC2990_CURR2);
 static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, ltc2990_show_value, NULL,
-			  LTC2990_VCC_MSB);
+			  LTC2990_IN0);
+static SENSOR_DEVICE_ATTR(in1_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_IN1);
+static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_IN2);
+static SENSOR_DEVICE_ATTR(in3_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_IN3);
+static SENSOR_DEVICE_ATTR(in4_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_IN4);
 
 static struct attribute *ltc2990_attrs[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	&sensor_dev_attr_temp2_input.dev_attr.attr,
+	&sensor_dev_attr_temp3_input.dev_attr.attr,
 	&sensor_dev_attr_curr1_input.dev_attr.attr,
 	&sensor_dev_attr_curr2_input.dev_attr.attr,
 	&sensor_dev_attr_in0_input.dev_attr.attr,
+	&sensor_dev_attr_in1_input.dev_attr.attr,
+	&sensor_dev_attr_in2_input.dev_attr.attr,
+	&sensor_dev_attr_in3_input.dev_attr.attr,
+	&sensor_dev_attr_in4_input.dev_attr.attr,
 	NULL,
 };
-ATTRIBUTE_GROUPS(ltc2990);
+
+static const struct attribute_group ltc2990_group = {
+	.attrs = ltc2990_attrs,
+	.is_visible = ltc2990_attrs_visible,
+};
+__ATTRIBUTE_GROUPS(ltc2990);
 
 static int ltc2990_i2c_probe(struct i2c_client *i2c,
 			     const struct i2c_device_id *id)
 {
 	int ret;
 	struct device *hwmon_dev;
+	struct ltc2990_data *data;
+	struct device_node *of_node = i2c->dev.of_node;
 
 	if (!i2c_check_functionality(i2c->adapter, I2C_FUNC_SMBUS_BYTE_DATA |
 				     I2C_FUNC_SMBUS_WORD_DATA))
 		return -ENODEV;
 
-	/* Setup continuous mode, current monitor */
+	data = devm_kzalloc(&i2c->dev, sizeof(struct ltc2990_data), GFP_KERNEL);
+	if (unlikely(!data))
+		return -ENOMEM;
+
+	data->i2c = i2c;
+
+	if (of_node) {
+		ret = of_property_read_u32_array(of_node, "lltc,meas-mode",
+						 data->mode, 2);
+		if (ret < 0)
+			return ret;
+
+		if (data->mode[0] & ~LTC2990_MODE0_MASK ||
+		    data->mode[1] & ~LTC2990_MODE1_MASK)
+			return -EINVAL;
+	} else {
+		ret = i2c_smbus_read_byte_data(i2c, LTC2990_CONTROL);
+		if (ret < 0)
+			return ret;
+
+		data->mode[0] = ret >> LTC2990_MODE0_SHIFT & LTC2990_MODE0_MASK;
+		data->mode[1] = ret >> LTC2990_MODE1_SHIFT & LTC2990_MODE1_MASK;
+	}
+
+	/* Setup continuous mode */
 	ret = i2c_smbus_write_byte_data(i2c, LTC2990_CONTROL,
-					LTC2990_CONTROL_MEASURE_ALL |
-					LTC2990_CONTROL_MODE_CURRENT);
+					data->mode[0] << LTC2990_MODE0_SHIFT |
+					data->mode[1] << LTC2990_MODE1_SHIFT);
 	if (ret < 0) {
 		dev_err(&i2c->dev, "Error: Failed to set control mode.\n");
 		return ret;
@@ -134,7 +264,7 @@ static int ltc2990_i2c_probe(struct i2c_client *i2c,
 
 	hwmon_dev = devm_hwmon_device_register_with_groups(&i2c->dev,
 							   i2c->name,
-							   i2c,
+							   data,
 							   ltc2990_groups);
 
 	return PTR_ERR_OR_ZERO(hwmon_dev);
diff --git a/drivers/hwmon/mc13783-adc.c b/drivers/hwmon/mc13783-adc.c
index 960a1db6f269..67860ad2e3d9 100644
--- a/drivers/hwmon/mc13783-adc.c
+++ b/drivers/hwmon/mc13783-adc.c
@@ -63,6 +63,10 @@ static int mc13783_adc_read(struct device *dev,
 	if (ret)
 		return ret;
 
+	/* ADIN7 subchannels */
+	if (channel >= 16)
+		channel = 7;
+
 	channel &= 0x7;
 
 	*val = (sample[channel % 4] >> (channel > 3 ? 14 : 2)) & 0x3ff;
@@ -111,6 +115,57 @@ static ssize_t mc13783_adc_read_gp(struct device *dev,
 	return sprintf(buf, "%u\n", val);
 }
 
+static ssize_t mc13783_adc_read_uid(struct device *dev,
+		struct device_attribute *devattr, char *buf)
+{
+	unsigned int val;
+	struct platform_device *pdev = to_platform_device(dev);
+	kernel_ulong_t driver_data = platform_get_device_id(pdev)->driver_data;
+	int ret = mc13783_adc_read(dev, devattr, &val);
+
+	if (ret)
+		return ret;
+
+	if (driver_data & MC13783_ADC_BPDIV2)
+		/* MC13892 have 1/2 divider, input range is [0, 4.800V] */
+		val = DIV_ROUND_CLOSEST(val * 4800, 1024);
+	else
+		/* MC13783 have 0.9 divider, input range is [0, 2.555V] */
+		val = DIV_ROUND_CLOSEST(val * 2555, 1024);
+
+	return sprintf(buf, "%u\n", val);
+}
+
+static ssize_t mc13783_adc_read_temp(struct device *dev,
+		struct device_attribute *devattr, char *buf)
+{
+	unsigned int val;
+	struct platform_device *pdev = to_platform_device(dev);
+	kernel_ulong_t driver_data = platform_get_device_id(pdev)->driver_data;
+	int ret = mc13783_adc_read(dev, devattr, &val);
+
+	if (ret)
+		return ret;
+
+	if (driver_data & MC13783_ADC_BPDIV2) {
+		/*
+		 * MC13892:
+		 * Die Temperature Read Out Code at 25C 680
+		 * Temperature change per LSB +0.4244C
+		 */
+		ret = DIV_ROUND_CLOSEST(-2635920 + val * 4244, 10);
+	} else {
+		/*
+		 * MC13783:
+		 * Die Temperature Read Out Code at 25C 282
+		 * Temperature change per LSB -1.14C
+		 */
+		ret = 346480 - 1140 * val;
+	}
+
+	return sprintf(buf, "%d\n", ret);
+}
+
 static DEVICE_ATTR_RO(name);
 static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, mc13783_adc_read_bp, NULL, 2);
 static SENSOR_DEVICE_ATTR(in5_input, S_IRUGO, mc13783_adc_read_gp, NULL, 5);
@@ -124,6 +179,9 @@ static SENSOR_DEVICE_ATTR(in12_input, S_IRUGO, mc13783_adc_read_gp, NULL, 12);
 static SENSOR_DEVICE_ATTR(in13_input, S_IRUGO, mc13783_adc_read_gp, NULL, 13);
 static SENSOR_DEVICE_ATTR(in14_input, S_IRUGO, mc13783_adc_read_gp, NULL, 14);
 static SENSOR_DEVICE_ATTR(in15_input, S_IRUGO, mc13783_adc_read_gp, NULL, 15);
+static SENSOR_DEVICE_ATTR(in16_input, S_IRUGO, mc13783_adc_read_uid, NULL, 16);
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO,
+			  mc13783_adc_read_temp, NULL, 17);
 
 static struct attribute *mc13783_attr_base[] = {
 	&dev_attr_name.attr,
@@ -131,6 +189,8 @@ static struct attribute *mc13783_attr_base[] = {
 	&sensor_dev_attr_in5_input.dev_attr.attr,
 	&sensor_dev_attr_in6_input.dev_attr.attr,
 	&sensor_dev_attr_in7_input.dev_attr.attr,
+	&sensor_dev_attr_in16_input.dev_attr.attr,
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
 	NULL
 };
 
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index 8b0bc4fc06e8..b0bc77bf2cd9 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -1380,8 +1380,8 @@ static int __init nct6683_find(int sioaddr, struct nct6683_sio_data *sio_data)
 	/* Activate logical device if needed */
 	val = superio_inb(sioaddr, SIO_REG_ENABLE);
 	if (!(val & 0x01)) {
-		pr_err("EC is disabled\n");
-		goto fail;
+		pr_warn("Forcibly enabling EC access. Data may be unusable.\n");
+		superio_outb(sioaddr, SIO_REG_ENABLE, val | 0x01);
 	}
 
 	superio_exit(sioaddr);
diff --git a/drivers/hwmon/scmi-hwmon.c b/drivers/hwmon/scmi-hwmon.c
index 363bf56eb0f2..91976b6ca300 100644
--- a/drivers/hwmon/scmi-hwmon.c
+++ b/drivers/hwmon/scmi-hwmon.c
@@ -170,7 +170,10 @@ static int scmi_hwmon_probe(struct scmi_device *sdev)
 	scmi_chip_info.info = ptr_scmi_ci;
 	chip_info = &scmi_chip_info;
 
-	for (type = 0; type < hwmon_max && nr_count[type]; type++) {
+	for (type = 0; type < hwmon_max; type++) {
+		if (!nr_count[type])
+			continue;
+
 		scmi_hwmon_add_chan_info(scmi_hwmon_chan, dev, nr_count[type],
 					 type, hwmon_attributes[type]);
 		*ptr_scmi_ci++ = scmi_hwmon_chan++;
diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c
index 9cdb3fbc8c1f..45b2460f3166 100644
--- a/drivers/hwtracing/coresight/coresight-cpu-debug.c
+++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2017 Linaro Limited. All rights reserved.
  *
  * Author: Leo Yan <leo.yan@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
- *
  */
 #include <linux/amba/bus.h>
 #include <linux/coresight.h>
@@ -315,7 +303,7 @@ static void debug_dump_regs(struct debug_drvdata *drvdata)
 	}
 
 	pc = debug_adjust_pc(drvdata);
-	dev_emerg(dev, " EDPCSR:  [<%px>] %pS\n", (void *)pc, (void *)pc);
+	dev_emerg(dev, " EDPCSR:  %pS\n", (void *)pc);
 
 	if (drvdata->edcidsr_present)
 		dev_emerg(dev, " EDCIDSR: %08x\n", drvdata->edcidsr);
diff --git a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c
index 043da86b0fe9..f6d0571ab9dd 100644
--- a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/amba/bus.h>
diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index 580cd381adf3..9b6c55523c58 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -1,15 +1,8 @@
-/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
  * Description: CoreSight Embedded Trace Buffer driver
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <asm/local.h>
diff --git a/drivers/hwtracing/coresight/coresight-etm-cp14.c b/drivers/hwtracing/coresight/coresight-etm-cp14.c
index 12a220682117..4174a8d355d2 100644
--- a/drivers/hwtracing/coresight/coresight-etm-cp14.c
+++ b/drivers/hwtracing/coresight/coresight-etm-cp14.c
@@ -1,13 +1,6 @@
-/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2012, The Linux Foundation. All rights reserved.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 4e5ed6597f2f..677695635211 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/coresight.h>
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h
index 3ffc9feb2d64..4197df4faf5e 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.h
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _CORESIGHT_ETM_PERF_H
diff --git a/drivers/hwtracing/coresight/coresight-etm.h b/drivers/hwtracing/coresight/coresight-etm.h
index 70b0a248c321..e8b4549e30e2 100644
--- a/drivers/hwtracing/coresight/coresight-etm.h
+++ b/drivers/hwtracing/coresight/coresight-etm.h
@@ -1,13 +1,6 @@
-/* Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
  */
 
 #ifndef _CORESIGHT_CORESIGHT_ETM_H
diff --git a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c
index 6e547ec6fead..9435c1481f61 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/pm_runtime.h>
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index 39f42fdd503d..15ed64d51a5b 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -1,15 +1,8 @@
-/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
  * Description: CoreSight Program Flow Trace driver
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
index d21961710713..4eb8da785ce0 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/pm_runtime.h>
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index cf364a514c12..9bc04c50d45b 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -1,13 +1,6 @@
-/* Copyright (c) 2014, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h
index b3b5ea7b7fb3..b7c4a6f6c6b9 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.h
+++ b/drivers/hwtracing/coresight/coresight-etm4x.h
@@ -1,13 +1,6 @@
-/* Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
  */
 
 #ifndef _CORESIGHT_CORESIGHT_ETM_H
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index 9f8ac0bef853..448145a36675 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -1,15 +1,8 @@
-/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
  * Description: CoreSight Funnel driver
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index f1d0e21d8cab..0e5a74dae6a6 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -1,13 +1,6 @@
-/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  */
 
 #ifndef _CORESIGHT_PRIV_H
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index 3756e71cb8f5..8d2eaaab6c2f 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -1,15 +1,8 @@
-/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
  * Description: CoreSight Replicator driver
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c
index 15e7ef3891f5..c46c70aec1d5 100644
--- a/drivers/hwtracing/coresight/coresight-stm.c
+++ b/drivers/hwtracing/coresight/coresight-stm.c
@@ -1,16 +1,9 @@
-/* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
  *
  * Description: CoreSight System Trace Macrocell driver
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * Initial implementation by Pratik Patel
  * (C) 2014-2015 Pratik Patel <pratikp@codeaurora.org>
  *
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index e2513b786242..61d849b11c26 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2016 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/circ_buf.h>
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 68fbc8f7450e..02f747afa2ba 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2016 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/coresight.h>
@@ -124,10 +113,9 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
 	bool used = false;
 	unsigned long flags;
 	void __iomem *vaddr = NULL;
-	dma_addr_t paddr;
+	dma_addr_t paddr = 0;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-
 	/*
 	 * If we don't have a buffer release the lock and allocate memory.
 	 * Otherwise keep the lock and move along.
@@ -164,11 +152,11 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
 		goto out;
 
 	/*
-	 * If drvdata::buf == NULL, use the memory allocated above.
+	 * If drvdata::vaddr == NULL, use the memory allocated above.
 	 * Otherwise a buffer still exists from a previous session, so
 	 * simply use that.
 	 */
-	if (drvdata->buf == NULL) {
+	if (drvdata->vaddr == NULL) {
 		used = true;
 		drvdata->vaddr = vaddr;
 		drvdata->paddr = paddr;
diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c
index 0ea04f588de0..456f122df74f 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.c
+++ b/drivers/hwtracing/coresight/coresight-tmc.c
@@ -1,15 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2012, The Linux Foundation. All rights reserved.
  *
  * Description: CoreSight Trace Memory Controller driver
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h
index 8df7a813f537..dfaff077a7fc 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.h
+++ b/drivers/hwtracing/coresight/coresight-tmc.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _CORESIGHT_TMC_H
diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c
index 805f7c2210fe..01b7457fe8fc 100644
--- a/drivers/hwtracing/coresight/coresight-tpiu.c
+++ b/drivers/hwtracing/coresight/coresight-tpiu.c
@@ -1,15 +1,8 @@
-/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
  * Description: CoreSight Trace Port Interface Unit driver
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 389c4baeca9d..29e834aab539 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -1,13 +1,6 @@
-/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2012, The Linux Foundation. All rights reserved.
  */
 
 #include <linux/kernel.h>
@@ -1026,8 +1019,10 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 	dev_set_name(&csdev->dev, "%s", desc->pdata->name);
 
 	ret = device_register(&csdev->dev);
-	if (ret)
-		goto err_device_register;
+	if (ret) {
+		put_device(&csdev->dev);
+		goto err_kzalloc_csdev;
+	}
 
 	mutex_lock(&coresight_mutex);
 
@@ -1038,8 +1033,6 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 
 	return csdev;
 
-err_device_register:
-	kfree(conns);
 err_kzalloc_conns:
 	kfree(refcnts);
 err_kzalloc_refcnts:
diff --git a/drivers/hwtracing/coresight/of_coresight.c b/drivers/hwtracing/coresight/of_coresight.c
index 7c375443ede6..a33a92ebe74b 100644
--- a/drivers/hwtracing/coresight/of_coresight.c
+++ b/drivers/hwtracing/coresight/of_coresight.c
@@ -1,13 +1,6 @@
-/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2012, The Linux Foundation. All rights reserved.
  */
 
 #include <linux/types.h>
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index ede388309376..634f58042c77 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -733,8 +733,8 @@ err_nomem:
 		/* Reset the page to write-back before releasing */
 		set_memory_wb((unsigned long)win->block[i].bdesc, 1);
 #endif
-		dma_free_coherent(msc_dev(msc), size, win->block[i].bdesc,
-				  win->block[i].addr);
+		dma_free_coherent(msc_dev(msc)->parent->parent, size,
+				  win->block[i].bdesc, win->block[i].addr);
 	}
 	kfree(win);
 
@@ -769,7 +769,7 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win)
 		/* Reset the page to write-back before releasing */
 		set_memory_wb((unsigned long)win->block[i].bdesc, 1);
 #endif
-		dma_free_coherent(msc_dev(win->msc), PAGE_SIZE,
+		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
 				  win->block[i].bdesc, win->block[i].addr);
 	}
 
diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c
index 05386b76465e..10bcb5d73f90 100644
--- a/drivers/hwtracing/stm/core.c
+++ b/drivers/hwtracing/stm/core.c
@@ -19,6 +19,7 @@
 #include <linux/stm.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/vmalloc.h>
 #include "stm.h"
 
 #include <uapi/linux/stm.h>
@@ -674,7 +675,7 @@ static void stm_device_release(struct device *dev)
 {
 	struct stm_device *stm = to_stm_device(dev);
 
-	kfree(stm);
+	vfree(stm);
 }
 
 int stm_register_device(struct device *parent, struct stm_data *stm_data,
@@ -691,7 +692,7 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data,
 		return -EINVAL;
 
 	nmasters = stm_data->sw_end - stm_data->sw_start + 1;
-	stm = kzalloc(sizeof(*stm) + nmasters * sizeof(void *), GFP_KERNEL);
+	stm = vzalloc(sizeof(*stm) + nmasters * sizeof(void *));
 	if (!stm)
 		return -ENOMEM;
 
@@ -744,7 +745,7 @@ err_device:
 	/* matches device_initialize() above */
 	put_device(&stm->dev);
 err_free:
-	kfree(stm);
+	vfree(stm);
 
 	return err;
 }
diff --git a/drivers/hwtracing/stm/ftrace.c b/drivers/hwtracing/stm/ftrace.c
index 7da75644c750..ce868e095410 100644
--- a/drivers/hwtracing/stm/ftrace.c
+++ b/drivers/hwtracing/stm/ftrace.c
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Simple kernel driver to link kernel Ftrace and an STM device
  * Copyright (c) 2016, Linaro Ltd.
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  * STM Ftrace will be registered as a trace_export.
  */
 
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index c4865b08d7fb..fce9f2ca0570 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -202,8 +202,7 @@ config I2C_CHT_WC
 
 	  Note this controller is hooked up to a TI bq24292i charger-IC,
 	  combined with a FUSB302 Type-C port-controller as such it is advised
-	  to also select CONFIG_CHARGER_BQ24190=m and CONFIG_TYPEC_FUSB302=m
-	  (the fusb302 driver currently is in drivers/staging).
+	  to also select CONFIG_TYPEC_FUSB302=m.
 
 config I2C_NFORCE2
 	tristate "Nvidia nForce2, nForce3 and nForce4"
@@ -707,7 +706,6 @@ config I2C_MPC
 config I2C_MT65XX
 	tristate "MediaTek I2C adapter"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
-	depends on HAS_DMA
 	help
 	  This selects the MediaTek(R) Integrated Inter Circuit bus driver
 	  for MT65xx and MT81xx.
@@ -885,7 +883,6 @@ config I2C_SH7760
 
 config I2C_SH_MOBILE
 	tristate "SuperH Mobile I2C Controller"
-	depends on HAS_DMA
 	depends on ARCH_SHMOBILE || ARCH_RENESAS || COMPILE_TEST
 	help
 	  If you say yes to this option, support will be included for the
@@ -1098,7 +1095,6 @@ config I2C_XLP9XX
 
 config I2C_RCAR
 	tristate "Renesas R-Car I2C Controller"
-	depends on HAS_DMA
 	depends on ARCH_RENESAS || COMPILE_TEST
 	select I2C_SLAVE
 	help
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index fd36c39ddf4e..0cdba29ae0a9 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -209,7 +209,10 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev)
 	i2c_dw_disable_int(dev);
 
 	/* Enable the adapter */
-	__i2c_dw_enable_and_wait(dev, true);
+	__i2c_dw_enable(dev, true);
+
+	/* Dummy read to avoid the register getting stuck on Bay Trail */
+	dw_readl(dev, DW_IC_ENABLE_STATUS);
 
 	/* Clear and enable interrupts */
 	dw_readl(dev, DW_IC_CLR_INTR);
diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c
index 8c42ca7107b2..45ae3c025bf6 100644
--- a/drivers/i2c/busses/i2c-ocores.c
+++ b/drivers/i2c/busses/i2c-ocores.c
@@ -1,6 +1,6 @@
 /*
  * i2c-ocores.c: I2C bus driver for OpenCores I2C controller
- * (http://www.opencores.org/projects.cgi/web/i2c/overview).
+ * (https://opencores.org/project/i2c/overview)
  *
  * Peter Korsgaard <jacmet@sunsite.dk>
  *
diff --git a/drivers/i2c/busses/i2c-pmcmsp.c b/drivers/i2c/busses/i2c-pmcmsp.c
index 2aa0e83174c5..dae8ac618a52 100644
--- a/drivers/i2c/busses/i2c-pmcmsp.c
+++ b/drivers/i2c/busses/i2c-pmcmsp.c
@@ -564,10 +564,10 @@ static int pmcmsptwi_master_xfer(struct i2c_adapter *adap,
 		 * TODO: We could potentially loop and retry in the case
 		 * of MSP_TWI_XFER_TIMEOUT.
 		 */
-		return -1;
+		return -EIO;
 	}
 
-	return 0;
+	return num;
 }
 
 static u32 pmcmsptwi_i2c_func(struct i2c_adapter *adapter)
diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c
index 25fcc3c1e32b..4053259bccb8 100644
--- a/drivers/i2c/busses/i2c-sprd.c
+++ b/drivers/i2c/busses/i2c-sprd.c
@@ -86,6 +86,7 @@ struct sprd_i2c {
 	u32 count;
 	int irq;
 	int err;
+	bool is_suspended;
 };
 
 static void sprd_i2c_set_count(struct sprd_i2c *i2c_dev, u32 count)
@@ -283,6 +284,9 @@ static int sprd_i2c_master_xfer(struct i2c_adapter *i2c_adap,
 	struct sprd_i2c *i2c_dev = i2c_adap->algo_data;
 	int im, ret;
 
+	if (i2c_dev->is_suspended)
+		return -EBUSY;
+
 	ret = pm_runtime_get_sync(i2c_dev->dev);
 	if (ret < 0)
 		return ret;
@@ -364,13 +368,12 @@ static irqreturn_t sprd_i2c_isr_thread(int irq, void *dev_id)
 	struct sprd_i2c *i2c_dev = dev_id;
 	struct i2c_msg *msg = i2c_dev->msg;
 	bool ack = !(readl(i2c_dev->base + I2C_STATUS) & I2C_RX_ACK);
-	u32 i2c_count = readl(i2c_dev->base + I2C_COUNT);
 	u32 i2c_tran;
 
 	if (msg->flags & I2C_M_RD)
 		i2c_tran = i2c_dev->count >= I2C_FIFO_FULL_THLD;
 	else
-		i2c_tran = i2c_count;
+		i2c_tran = i2c_dev->count;
 
 	/*
 	 * If we got one ACK from slave when writing data, and we did not
@@ -408,14 +411,13 @@ static irqreturn_t sprd_i2c_isr(int irq, void *dev_id)
 {
 	struct sprd_i2c *i2c_dev = dev_id;
 	struct i2c_msg *msg = i2c_dev->msg;
-	u32 i2c_count = readl(i2c_dev->base + I2C_COUNT);
 	bool ack = !(readl(i2c_dev->base + I2C_STATUS) & I2C_RX_ACK);
 	u32 i2c_tran;
 
 	if (msg->flags & I2C_M_RD)
 		i2c_tran = i2c_dev->count >= I2C_FIFO_FULL_THLD;
 	else
-		i2c_tran = i2c_count;
+		i2c_tran = i2c_dev->count;
 
 	/*
 	 * If we did not get one ACK from slave when writing data, then we
@@ -586,11 +588,23 @@ static int sprd_i2c_remove(struct platform_device *pdev)
 
 static int __maybe_unused sprd_i2c_suspend_noirq(struct device *pdev)
 {
+	struct sprd_i2c *i2c_dev = dev_get_drvdata(pdev);
+
+	i2c_lock_adapter(&i2c_dev->adap);
+	i2c_dev->is_suspended = true;
+	i2c_unlock_adapter(&i2c_dev->adap);
+
 	return pm_runtime_force_suspend(pdev);
 }
 
 static int __maybe_unused sprd_i2c_resume_noirq(struct device *pdev)
 {
+	struct sprd_i2c *i2c_dev = dev_get_drvdata(pdev);
+
+	i2c_lock_adapter(&i2c_dev->adap);
+	i2c_dev->is_suspended = false;
+	i2c_unlock_adapter(&i2c_dev->adap);
+
 	return pm_runtime_force_resume(pdev);
 }
 
diff --git a/drivers/i2c/busses/i2c-viperboard.c b/drivers/i2c/busses/i2c-viperboard.c
index e4be86b3de9a..7235c7302bb7 100644
--- a/drivers/i2c/busses/i2c-viperboard.c
+++ b/drivers/i2c/busses/i2c-viperboard.c
@@ -337,7 +337,7 @@ static int vprbrd_i2c_xfer(struct i2c_adapter *i2c, struct i2c_msg *msgs,
 		}
 		mutex_unlock(&vb->lock);
 	}
-	return 0;
+	return num;
 error:
 	mutex_unlock(&vb->lock);
 	return error;
diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c
index a9126b3cda61..7c3b4740b94b 100644
--- a/drivers/i2c/i2c-core-acpi.c
+++ b/drivers/i2c/i2c-core-acpi.c
@@ -445,10 +445,17 @@ static int acpi_gsb_i2c_read_bytes(struct i2c_client *client,
 	msgs[1].buf = buffer;
 
 	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
-	if (ret < 0)
-		dev_err(&client->adapter->dev, "i2c read failed\n");
-	else
+	if (ret < 0) {
+		/* Getting a NACK is unfortunately normal with some DSTDs */
+		if (ret == -EREMOTEIO)
+			dev_dbg(&client->adapter->dev, "i2c read %d bytes from client@%#x starting at reg %#x failed, error: %d\n",
+				data_len, client->addr, cmd, ret);
+		else
+			dev_err(&client->adapter->dev, "i2c read %d bytes from client@%#x starting at reg %#x failed, error: %d\n",
+				data_len, client->addr, cmd, ret);
+	} else {
 		memcpy(data, buffer, data_len);
+	}
 
 	kfree(buffer);
 	return ret;
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 1ba40bb2b966..a17f46a95f73 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -363,7 +363,7 @@ static int i2c_device_probe(struct device *dev)
 		goto err_clear_wakeup_irq;
 
 	status = dev_pm_domain_attach(&client->dev, true);
-	if (status == -EPROBE_DEFER)
+	if (status)
 		goto err_clear_wakeup_irq;
 
 	/*
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 036a03f0d0a6..1667b6e7674f 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -280,7 +280,7 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client,
 		 */
 		if (msgs[i].flags & I2C_M_RECV_LEN) {
 			if (!(msgs[i].flags & I2C_M_RD) ||
-			    msgs[i].buf[0] < 1 ||
+			    msgs[i].len < 1 || msgs[i].buf[0] < 1 ||
 			    msgs[i].len < msgs[i].buf[0] +
 					     I2C_SMBUS_BLOCK_MAX) {
 				res = -EINVAL;
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index 0e6bc631a1ca..8b2b72b93885 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -92,7 +92,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	struct request *rq;
 	int error;
 
-	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->special = (char *)pc;
 
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 5a8e8e3c22cd..5f178384876f 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -437,7 +437,7 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		bool delay = false;
 
 		rq = blk_get_request(drive->queue,
-			write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,  __GFP_RECLAIM);
+			write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 		memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB);
 		ide_req(rq)->type = ATA_PRIV_PC;
 		rq->rq_flags |= rq_flags;
@@ -1426,21 +1426,8 @@ static int idecd_capacity_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int idecd_capacity_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, idecd_capacity_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idecd_capacity_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= idecd_capacity_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static ide_proc_entry_t idecd_proc[] = {
-	{ "capacity", S_IFREG|S_IRUGO, &idecd_capacity_proc_fops },
+	{ "capacity", S_IFREG|S_IRUGO, idecd_capacity_proc_show },
 	{}
 };
 
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 2acca12b9c94..b1322400887b 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -304,7 +304,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	struct request *rq;
 	int ret;
 
-	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->rq_flags = RQF_QUIET;
 	blk_execute_rq(drive->queue, cd->disk, rq, 0);
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index 4e20747af32e..f4f8afdf8bbe 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -166,7 +166,7 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 	if (!(setting->flags & DS_SYNC))
 		return setting->set(drive, arg);
 
-	rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(q, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	scsi_req(rq)->cmd_len = 5;
 	scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC;
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index f1a7c58fe418..e3b4e659082d 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -478,7 +478,7 @@ static int set_multcount(ide_drive_t *drive, int arg)
 	if (drive->special_flags & IDE_SFLAG_SET_MULTMODE)
 		return -EBUSY;
 
-	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 
 	drive->mult_req = arg;
diff --git a/drivers/ide/ide-disk_proc.c b/drivers/ide/ide-disk_proc.c
index 82a36ced4e96..95d239b2f646 100644
--- a/drivers/ide/ide-disk_proc.c
+++ b/drivers/ide/ide-disk_proc.c
@@ -52,19 +52,6 @@ static int idedisk_cache_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int idedisk_cache_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, idedisk_cache_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idedisk_cache_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= idedisk_cache_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int idedisk_capacity_proc_show(struct seq_file *m, void *v)
 {
 	ide_drive_t*drive = (ide_drive_t *)m->private;
@@ -73,19 +60,6 @@ static int idedisk_capacity_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int idedisk_capacity_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, idedisk_capacity_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idedisk_capacity_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= idedisk_capacity_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __idedisk_proc_show(struct seq_file *m, ide_drive_t *drive, u8 sub_cmd)
 {
 	u8 *buf;
@@ -114,43 +88,17 @@ static int idedisk_sv_proc_show(struct seq_file *m, void *v)
 	return __idedisk_proc_show(m, m->private, ATA_SMART_READ_VALUES);
 }
 
-static int idedisk_sv_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, idedisk_sv_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idedisk_sv_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= idedisk_sv_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int idedisk_st_proc_show(struct seq_file *m, void *v)
 {
 	return __idedisk_proc_show(m, m->private, ATA_SMART_READ_THRESHOLDS);
 }
 
-static int idedisk_st_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, idedisk_st_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idedisk_st_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= idedisk_st_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 ide_proc_entry_t ide_disk_proc[] = {
-	{ "cache",	  S_IFREG|S_IRUGO, &idedisk_cache_proc_fops	},
-	{ "capacity",	  S_IFREG|S_IRUGO, &idedisk_capacity_proc_fops	},
-	{ "geometry",	  S_IFREG|S_IRUGO, &ide_geometry_proc_fops	},
-	{ "smart_values", S_IFREG|S_IRUSR, &idedisk_sv_proc_fops	},
-	{ "smart_thresholds", S_IFREG|S_IRUSR, &idedisk_st_proc_fops	},
+	{ "cache",	  S_IFREG|S_IRUGO, idedisk_cache_proc_show	},
+	{ "capacity",	  S_IFREG|S_IRUGO, idedisk_capacity_proc_show	},
+	{ "geometry",	  S_IFREG|S_IRUGO, ide_geometry_proc_show	},
+	{ "smart_values", S_IFREG|S_IRUSR, idedisk_sv_proc_show		},
+	{ "smart_thresholds", S_IFREG|S_IRUSR, idedisk_st_proc_show	},
 	{}
 };
 
diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c
index 54d4d78ca46a..6f344654ef22 100644
--- a/drivers/ide/ide-dma.c
+++ b/drivers/ide/ide-dma.c
@@ -180,7 +180,6 @@ EXPORT_SYMBOL_GPL(ide_dma_unmap_sg);
 void ide_dma_off_quietly(ide_drive_t *drive)
 {
 	drive->dev_flags &= ~IDE_DFLAG_USING_DMA;
-	ide_toggle_bounce(drive, 0);
 
 	drive->hwif->dma_ops->dma_host_set(drive, 0);
 }
@@ -211,7 +210,6 @@ EXPORT_SYMBOL(ide_dma_off);
 void ide_dma_on(ide_drive_t *drive)
 {
 	drive->dev_flags |= IDE_DFLAG_USING_DMA;
-	ide_toggle_bounce(drive, 1);
 
 	drive->hwif->dma_ops->dma_host_set(drive, 1);
 }
diff --git a/drivers/ide/ide-floppy_proc.c b/drivers/ide/ide-floppy_proc.c
index 471457ebea67..7f697ddb5fe5 100644
--- a/drivers/ide/ide-floppy_proc.c
+++ b/drivers/ide/ide-floppy_proc.c
@@ -14,22 +14,9 @@ static int idefloppy_capacity_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int idefloppy_capacity_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, idefloppy_capacity_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idefloppy_capacity_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= idefloppy_capacity_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 ide_proc_entry_t ide_floppy_proc[] = {
-	{ "capacity",	S_IFREG|S_IRUGO, &idefloppy_capacity_proc_fops	},
-	{ "geometry",	S_IFREG|S_IRUGO, &ide_geometry_proc_fops	},
+	{ "capacity",	S_IFREG|S_IRUGO, idefloppy_capacity_proc_show	},
+	{ "geometry",	S_IFREG|S_IRUGO, ide_geometry_proc_show		},
 	{}
 };
 
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index 3661abb16a5f..af5119a73689 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -125,7 +125,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 	if (NULL == (void *) arg) {
 		struct request *rq;
 
-		rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+		rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 		ide_req(rq)->type = ATA_PRIV_TASKFILE;
 		blk_execute_rq(drive->queue, NULL, rq, 0);
 		err = scsi_req(rq)->result ? -EIO : 0;
@@ -222,7 +222,7 @@ static int generic_drive_reset(ide_drive_t *drive)
 	struct request *rq;
 	int ret = 0;
 
-	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	scsi_req(rq)->cmd_len = 1;
 	scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
diff --git a/drivers/ide/ide-lib.c b/drivers/ide/ide-lib.c
index e1180fa46196..78cb79eddc8b 100644
--- a/drivers/ide/ide-lib.c
+++ b/drivers/ide/ide-lib.c
@@ -6,32 +6,6 @@
 #include <linux/ide.h>
 #include <linux/bitops.h>
 
-/**
- *	ide_toggle_bounce	-	handle bounce buffering
- *	@drive: drive to update
- *	@on: on/off boolean
- *
- *	Enable or disable bounce buffering for the device. Drives move
- *	between PIO and DMA and that changes the rules we need.
- */
-
-void ide_toggle_bounce(ide_drive_t *drive, int on)
-{
-	u64 addr = BLK_BOUNCE_HIGH;	/* dma64_addr_t */
-
-	if (!PCI_DMA_BUS_IS_PHYS) {
-		addr = BLK_BOUNCE_ANY;
-	} else if (on && drive->media == ide_disk) {
-		struct device *dev = drive->hwif->dev;
-
-		if (dev && dev->dma_mask)
-			addr = *dev->dma_mask;
-	}
-
-	if (drive->queue)
-		blk_queue_bounce_limit(drive->queue, addr);
-}
-
 u64 ide_get_lba_addr(struct ide_cmd *cmd, int lba48)
 {
 	struct ide_taskfile *tf = &cmd->tf;
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 6465bcc7cea6..622f0edb3945 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -32,7 +32,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	}
 	spin_unlock_irq(&hwif->lock);
 
-	rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(q, REQ_OP_DRV_IN, 0);
 	scsi_req(rq)->cmd[0] = REQ_PARK_HEADS;
 	scsi_req(rq)->cmd_len = 1;
 	ide_req(rq)->type = ATA_PRIV_MISC;
@@ -47,7 +47,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	 * Make sure that *some* command is sent to the drive after the
 	 * timeout has expired, so power management will be reenabled.
 	 */
-	rq = blk_get_request(q, REQ_OP_DRV_IN, GFP_NOWAIT);
+	rq = blk_get_request(q, REQ_OP_DRV_IN, BLK_MQ_REQ_NOWAIT);
 	if (IS_ERR(rq))
 		goto out;
 
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index ad8a125defdd..59217aa1d1fb 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -19,7 +19,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_PM_SUSPEND;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
@@ -90,8 +90,7 @@ int generic_ide_resume(struct device *dev)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request_flags(drive->queue, REQ_OP_DRV_IN,
-				   BLK_MQ_REQ_PREEMPT);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PREEMPT);
 	ide_req(rq)->type = ATA_PRIV_PM_RESUME;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_RESUME;
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 2019e66eada7..56d7bc228cb3 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -796,8 +796,7 @@ static int ide_init_queue(ide_drive_t *drive)
 	 * This will be fixed once we teach pci_map_sg() about our boundary
 	 * requirements, hopefully soon. *FIXME*
 	 */
-	if (!PCI_DMA_BUS_IS_PHYS)
-		max_sg_entries >>= 1;
+	max_sg_entries >>= 1;
 #endif /* CONFIG_PCI */
 
 	blk_queue_max_segments(q, max_sg_entries);
@@ -805,9 +804,6 @@ static int ide_init_queue(ide_drive_t *drive)
 	/* assign drive queue */
 	drive->queue = q;
 
-	/* needs drive->queue to be set */
-	ide_toggle_bounce(drive, 1);
-
 	return 0;
 }
 
diff --git a/drivers/ide/ide-proc.c b/drivers/ide/ide-proc.c
index 863db44c7916..45c997430332 100644
--- a/drivers/ide/ide-proc.c
+++ b/drivers/ide/ide-proc.c
@@ -56,19 +56,6 @@ static int ide_imodel_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ide_imodel_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ide_imodel_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_imodel_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_imodel_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int ide_mate_proc_show(struct seq_file *m, void *v)
 {
 	ide_hwif_t	*hwif = (ide_hwif_t *) m->private;
@@ -80,19 +67,6 @@ static int ide_mate_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ide_mate_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ide_mate_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_mate_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_mate_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int ide_channel_proc_show(struct seq_file *m, void *v)
 {
 	ide_hwif_t	*hwif = (ide_hwif_t *) m->private;
@@ -101,19 +75,6 @@ static int ide_channel_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ide_channel_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ide_channel_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_channel_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_channel_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int ide_identify_proc_show(struct seq_file *m, void *v)
 {
 	ide_drive_t *drive = (ide_drive_t *)m->private;
@@ -141,19 +102,6 @@ static int ide_identify_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ide_identify_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ide_identify_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_identify_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_identify_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /**
  *	ide_find_setting	-	find a specific setting
  *	@st: setting table pointer
@@ -441,27 +389,14 @@ static const struct file_operations ide_settings_proc_fops = {
 	.write		= ide_settings_proc_write,
 };
 
-static int ide_capacity_proc_show(struct seq_file *m, void *v)
+int ide_capacity_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "%llu\n", (long long)0x7fffffff);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ide_capacity_proc_show);
 
-static int ide_capacity_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ide_capacity_proc_show, NULL);
-}
-
-const struct file_operations ide_capacity_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_capacity_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-EXPORT_SYMBOL_GPL(ide_capacity_proc_fops);
-
-static int ide_geometry_proc_show(struct seq_file *m, void *v)
+int ide_geometry_proc_show(struct seq_file *m, void *v)
 {
 	ide_drive_t	*drive = (ide_drive_t *) m->private;
 
@@ -471,20 +406,7 @@ static int ide_geometry_proc_show(struct seq_file *m, void *v)
 			drive->bios_cyl, drive->bios_head, drive->bios_sect);
 	return 0;
 }
-
-static int ide_geometry_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ide_geometry_proc_show, PDE_DATA(inode));
-}
-
-const struct file_operations ide_geometry_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_geometry_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-EXPORT_SYMBOL(ide_geometry_proc_fops);
+EXPORT_SYMBOL(ide_geometry_proc_show);
 
 static int ide_dmodel_proc_show(struct seq_file *seq, void *v)
 {
@@ -495,19 +417,6 @@ static int ide_dmodel_proc_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int ide_dmodel_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ide_dmodel_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_dmodel_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_dmodel_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int ide_driver_proc_show(struct seq_file *m, void *v)
 {
 	ide_drive_t		*drive = (ide_drive_t *)m->private;
@@ -523,65 +432,6 @@ static int ide_driver_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ide_driver_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ide_driver_proc_show, PDE_DATA(inode));
-}
-
-static int ide_replace_subdriver(ide_drive_t *drive, const char *driver)
-{
-	struct device *dev = &drive->gendev;
-	int ret = 1;
-	int err;
-
-	device_release_driver(dev);
-	/* FIXME: device can still be in use by previous driver */
-	strlcpy(drive->driver_req, driver, sizeof(drive->driver_req));
-	err = device_attach(dev);
-	if (err < 0)
-		printk(KERN_WARNING "IDE: %s: device_attach error: %d\n",
-			__func__, err);
-	drive->driver_req[0] = 0;
-	if (dev->driver == NULL) {
-		err = device_attach(dev);
-		if (err < 0)
-			printk(KERN_WARNING
-				"IDE: %s: device_attach(2) error: %d\n",
-				__func__, err);
-	}
-	if (dev->driver && !strcmp(dev->driver->name, driver))
-		ret = 0;
-
-	return ret;
-}
-
-static ssize_t ide_driver_proc_write(struct file *file, const char __user *buffer,
-				     size_t count, loff_t *pos)
-{
-	ide_drive_t	*drive = PDE_DATA(file_inode(file));
-	char name[32];
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EACCES;
-	if (count > 31)
-		count = 31;
-	if (copy_from_user(name, buffer, count))
-		return -EFAULT;
-	name[count] = '\0';
-	if (ide_replace_subdriver(drive, name))
-		return -EINVAL;
-	return count;
-}
-
-static const struct file_operations ide_driver_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_driver_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= ide_driver_proc_write,
-};
-
 static int ide_media_proc_show(struct seq_file *m, void *v)
 {
 	ide_drive_t	*drive = (ide_drive_t *) m->private;
@@ -613,11 +463,10 @@ static const struct file_operations ide_media_proc_fops = {
 };
 
 static ide_proc_entry_t generic_drive_entries[] = {
-	{ "driver",	S_IFREG|S_IRUGO,	 &ide_driver_proc_fops	},
-	{ "identify",	S_IFREG|S_IRUSR,	 &ide_identify_proc_fops},
-	{ "media",	S_IFREG|S_IRUGO,	 &ide_media_proc_fops	},
-	{ "model",	S_IFREG|S_IRUGO,	 &ide_dmodel_proc_fops	},
-	{ "settings",	S_IFREG|S_IRUSR|S_IWUSR, &ide_settings_proc_fops},
+	{ "driver",	S_IFREG|S_IRUGO,	 ide_driver_proc_show	},
+	{ "identify",	S_IFREG|S_IRUSR,	 ide_identify_proc_show	},
+	{ "media",	S_IFREG|S_IRUGO,	 ide_media_proc_show	},
+	{ "model",	S_IFREG|S_IRUGO,	 ide_dmodel_proc_show	},
 	{}
 };
 
@@ -628,7 +477,7 @@ static void ide_add_proc_entries(struct proc_dir_entry *dir, ide_proc_entry_t *p
 	if (!dir || !p)
 		return;
 	while (p->name != NULL) {
-		ent = proc_create_data(p->name, p->mode, dir, p->proc_fops, data);
+		ent = proc_create_single_data(p->name, p->mode, dir, p->show, data);
 		if (!ent) return;
 		p++;
 	}
@@ -693,8 +542,12 @@ void ide_proc_port_register_devices(ide_hwif_t *hwif)
 			continue;
 
 		drive->proc = proc_mkdir(drive->name, parent);
-		if (drive->proc)
+		if (drive->proc) {
 			ide_add_proc_entries(drive->proc, generic_drive_entries, drive);
+			proc_create_data("setting", S_IFREG|S_IRUSR|S_IWUSR,
+					drive->proc, &ide_settings_proc_fops,
+					drive);
+		}
 		sprintf(name, "ide%d/%s", (drive->name[2]-'a')/2, drive->name);
 		ent = proc_symlink(drive->name, proc_ide_root, name);
 		if (!ent) return;
@@ -704,6 +557,7 @@ void ide_proc_port_register_devices(ide_hwif_t *hwif)
 void ide_proc_unregister_device(ide_drive_t *drive)
 {
 	if (drive->proc) {
+		remove_proc_entry("settings", drive->proc);
 		ide_remove_proc_entries(drive->proc, generic_drive_entries);
 		remove_proc_entry(drive->name, proc_ide_root);
 		remove_proc_entry(drive->name, drive->hwif->proc);
@@ -712,9 +566,9 @@ void ide_proc_unregister_device(ide_drive_t *drive)
 }
 
 static ide_proc_entry_t hwif_entries[] = {
-	{ "channel",	S_IFREG|S_IRUGO,	&ide_channel_proc_fops	},
-	{ "mate",	S_IFREG|S_IRUGO,	&ide_mate_proc_fops	},
-	{ "model",	S_IFREG|S_IRUGO,	&ide_imodel_proc_fops	},
+	{ "channel",	S_IFREG|S_IRUGO,	ide_channel_proc_show	},
+	{ "mate",	S_IFREG|S_IRUGO,	ide_mate_proc_show	},
+	{ "model",	S_IFREG|S_IRUGO,	ide_imodel_proc_show	},
 	{}
 };
 
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index fd57e8ccc47a..aee7b46d2330 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -854,7 +854,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE);
 	BUG_ON(size < 0 || size % tape->blk_size);
 
-	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	scsi_req(rq)->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;
@@ -862,7 +862,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 
 	if (size) {
 		ret = blk_rq_map_kern(drive->queue, rq, tape->buf, size,
-				      __GFP_RECLAIM);
+				      GFP_NOIO);
 		if (ret)
 			goto out_put;
 	}
@@ -1847,22 +1847,9 @@ static int idetape_name_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int idetape_name_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, idetape_name_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idetape_name_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= idetape_name_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static ide_proc_entry_t idetape_proc[] = {
-	{ "capacity",	S_IFREG|S_IRUGO,	&ide_capacity_proc_fops	},
-	{ "name",	S_IFREG|S_IRUGO,	&idetape_name_proc_fops	},
+	{ "capacity",	S_IFREG|S_IRUGO,	ide_capacity_proc_show	},
+	{ "name",	S_IFREG|S_IRUGO,	idetape_name_proc_show	},
 	{}
 };
 
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index abe0822dd429..c034cd965831 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -431,7 +431,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 
 	rq = blk_get_request(drive->queue,
 		(cmd->tf_flags & IDE_TFLAG_WRITE) ?
-			REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM);
+			REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 
 	/*
@@ -442,7 +442,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 	 */
 	if (nsect) {
 		error = blk_rq_map_kern(drive->queue, rq, buf,
-					nsect * SECTOR_SIZE, __GFP_RECLAIM);
+					nsect * SECTOR_SIZE, GFP_NOIO);
 		if (error)
 			goto put_req;
 	}
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 15606f237480..9da79070357c 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -158,6 +158,7 @@ config AT91_SAMA5D2_ADC
 	depends on ARCH_AT91 || COMPILE_TEST
 	depends on HAS_IOMEM
 	depends on HAS_DMA
+	select IIO_BUFFER
 	select IIO_TRIGGERED_BUFFER
 	help
 	  Say yes here to build support for Atmel SAMA5D2 ADC which is
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
index 801afb61310b..d4bbe5b53318 100644
--- a/drivers/iio/adc/ad7793.c
+++ b/drivers/iio/adc/ad7793.c
@@ -348,55 +348,6 @@ static const u16 ad7793_sample_freq_avail[16] = {0, 470, 242, 123, 62, 50, 39,
 static const u16 ad7797_sample_freq_avail[16] = {0, 0, 0, 123, 62, 50, 0,
 					33, 0, 17, 16, 12, 10, 8, 6, 4};
 
-static ssize_t ad7793_read_frequency(struct device *dev,
-		struct device_attribute *attr,
-		char *buf)
-{
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct ad7793_state *st = iio_priv(indio_dev);
-
-	return sprintf(buf, "%d\n",
-	       st->chip_info->sample_freq_avail[AD7793_MODE_RATE(st->mode)]);
-}
-
-static ssize_t ad7793_write_frequency(struct device *dev,
-		struct device_attribute *attr,
-		const char *buf,
-		size_t len)
-{
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct ad7793_state *st = iio_priv(indio_dev);
-	long lval;
-	int i, ret;
-
-	ret = kstrtol(buf, 10, &lval);
-	if (ret)
-		return ret;
-
-	if (lval == 0)
-		return -EINVAL;
-
-	for (i = 0; i < 16; i++)
-		if (lval == st->chip_info->sample_freq_avail[i])
-			break;
-	if (i == 16)
-		return -EINVAL;
-
-	ret = iio_device_claim_direct_mode(indio_dev);
-	if (ret)
-		return ret;
-	st->mode &= ~AD7793_MODE_RATE(-1);
-	st->mode |= AD7793_MODE_RATE(i);
-	ad_sd_write_reg(&st->sd, AD7793_REG_MODE, sizeof(st->mode), st->mode);
-	iio_device_release_direct_mode(indio_dev);
-
-	return len;
-}
-
-static IIO_DEV_ATTR_SAMP_FREQ(S_IWUSR | S_IRUGO,
-		ad7793_read_frequency,
-		ad7793_write_frequency);
-
 static IIO_CONST_ATTR_SAMP_FREQ_AVAIL(
 	"470 242 123 62 50 39 33 19 17 16 12 10 8 6 4");
 
@@ -424,7 +375,6 @@ static IIO_DEVICE_ATTR_NAMED(in_m_in_scale_available,
 		ad7793_show_scale_available, NULL, 0);
 
 static struct attribute *ad7793_attributes[] = {
-	&iio_dev_attr_sampling_frequency.dev_attr.attr,
 	&iio_const_attr_sampling_frequency_available.dev_attr.attr,
 	&iio_dev_attr_in_m_in_scale_available.dev_attr.attr,
 	NULL
@@ -435,7 +385,6 @@ static const struct attribute_group ad7793_attribute_group = {
 };
 
 static struct attribute *ad7797_attributes[] = {
-	&iio_dev_attr_sampling_frequency.dev_attr.attr,
 	&iio_const_attr_sampling_frequency_available_ad7797.dev_attr.attr,
 	NULL
 };
@@ -505,6 +454,10 @@ static int ad7793_read_raw(struct iio_dev *indio_dev,
 			*val -= offset;
 		}
 		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		*val = st->chip_info
+			       ->sample_freq_avail[AD7793_MODE_RATE(st->mode)];
+		return IIO_VAL_INT;
 	}
 	return -EINVAL;
 }
@@ -542,6 +495,26 @@ static int ad7793_write_raw(struct iio_dev *indio_dev,
 				break;
 			}
 		break;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		if (!val) {
+			ret = -EINVAL;
+			break;
+		}
+
+		for (i = 0; i < 16; i++)
+			if (val == st->chip_info->sample_freq_avail[i])
+				break;
+
+		if (i == 16) {
+			ret = -EINVAL;
+			break;
+		}
+
+		st->mode &= ~AD7793_MODE_RATE(-1);
+		st->mode |= AD7793_MODE_RATE(i);
+		ad_sd_write_reg(&st->sd, AD7793_REG_MODE, sizeof(st->mode),
+				st->mode);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index 4eff8351ce29..8729d6524b4d 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -333,6 +333,27 @@ static const struct iio_chan_spec at91_adc_channels[] = {
 				+ AT91_SAMA5D2_DIFF_CHAN_CNT + 1),
 };
 
+static int at91_adc_chan_xlate(struct iio_dev *indio_dev, int chan)
+{
+	int i;
+
+	for (i = 0; i < indio_dev->num_channels; i++) {
+		if (indio_dev->channels[i].scan_index == chan)
+			return i;
+	}
+	return -EINVAL;
+}
+
+static inline struct iio_chan_spec const *
+at91_adc_chan_get(struct iio_dev *indio_dev, int chan)
+{
+	int index = at91_adc_chan_xlate(indio_dev, chan);
+
+	if (index < 0)
+		return NULL;
+	return indio_dev->channels + index;
+}
+
 static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 {
 	struct iio_dev *indio = iio_trigger_get_drvdata(trig);
@@ -350,8 +371,10 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 	at91_adc_writel(st, AT91_SAMA5D2_TRGR, status);
 
 	for_each_set_bit(bit, indio->active_scan_mask, indio->num_channels) {
-		struct iio_chan_spec const *chan = indio->channels + bit;
+		struct iio_chan_spec const *chan = at91_adc_chan_get(indio, bit);
 
+		if (!chan)
+			continue;
 		if (state) {
 			at91_adc_writel(st, AT91_SAMA5D2_CHER,
 					BIT(chan->channel));
@@ -448,7 +471,11 @@ static int at91_adc_dma_start(struct iio_dev *indio_dev)
 
 	for_each_set_bit(bit, indio_dev->active_scan_mask,
 			 indio_dev->num_channels) {
-		struct iio_chan_spec const *chan = indio_dev->channels + bit;
+		struct iio_chan_spec const *chan =
+					 at91_adc_chan_get(indio_dev, bit);
+
+		if (!chan)
+			continue;
 
 		st->dma_st.rx_buf_sz += chan->scan_type.storagebits / 8;
 	}
@@ -526,8 +553,11 @@ static int at91_adc_buffer_predisable(struct iio_dev *indio_dev)
 	 */
 	for_each_set_bit(bit, indio_dev->active_scan_mask,
 			 indio_dev->num_channels) {
-		struct iio_chan_spec const *chan = indio_dev->channels + bit;
+		struct iio_chan_spec const *chan =
+					at91_adc_chan_get(indio_dev, bit);
 
+		if (!chan)
+			continue;
 		if (st->dma_st.dma_chan)
 			at91_adc_readl(st, chan->address);
 	}
@@ -587,8 +617,11 @@ static void at91_adc_trigger_handler_nodma(struct iio_dev *indio_dev,
 
 	for_each_set_bit(bit, indio_dev->active_scan_mask,
 			 indio_dev->num_channels) {
-		struct iio_chan_spec const *chan = indio_dev->channels + bit;
+		struct iio_chan_spec const *chan =
+					at91_adc_chan_get(indio_dev, bit);
 
+		if (!chan)
+			continue;
 		st->buffer[i] = at91_adc_readl(st, chan->address);
 		i++;
 	}
diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c
index 01422d11753c..b28a716a23b2 100644
--- a/drivers/iio/adc/stm32-dfsdm-adc.c
+++ b/drivers/iio/adc/stm32-dfsdm-adc.c
@@ -144,6 +144,7 @@ static int stm32_dfsdm_set_osrs(struct stm32_dfsdm_filter *fl,
 	 * Leave as soon as if exact resolution if reached.
 	 * Otherwise the higher resolution below 32 bits is kept.
 	 */
+	fl->res = 0;
 	for (fosr = 1; fosr <= DFSDM_MAX_FL_OVERSAMPLING; fosr++) {
 		for (iosr = 1; iosr <= DFSDM_MAX_INT_OVERSAMPLING; iosr++) {
 			if (fast)
@@ -193,7 +194,7 @@ static int stm32_dfsdm_set_osrs(struct stm32_dfsdm_filter *fl,
 		}
 	}
 
-	if (!fl->fosr)
+	if (!fl->res)
 		return -EINVAL;
 
 	return 0;
@@ -770,7 +771,7 @@ static int stm32_dfsdm_write_raw(struct iio_dev *indio_dev,
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
 	struct stm32_dfsdm_filter *fl = &adc->dfsdm->fl_list[adc->fl_id];
 	struct stm32_dfsdm_channel *ch = &adc->dfsdm->ch_list[chan->channel];
-	unsigned int spi_freq = adc->spi_freq;
+	unsigned int spi_freq;
 	int ret = -EINVAL;
 
 	switch (mask) {
@@ -784,8 +785,18 @@ static int stm32_dfsdm_write_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_SAMP_FREQ:
 		if (!val)
 			return -EINVAL;
-		if (ch->src != DFSDM_CHANNEL_SPI_CLOCK_EXTERNAL)
+
+		switch (ch->src) {
+		case DFSDM_CHANNEL_SPI_CLOCK_INTERNAL:
 			spi_freq = adc->dfsdm->spi_master_freq;
+			break;
+		case DFSDM_CHANNEL_SPI_CLOCK_INTERNAL_DIV2_FALLING:
+		case DFSDM_CHANNEL_SPI_CLOCK_INTERNAL_DIV2_RISING:
+			spi_freq = adc->dfsdm->spi_master_freq / 2;
+			break;
+		default:
+			spi_freq = adc->spi_freq;
+		}
 
 		if (spi_freq % val)
 			dev_warn(&indio_dev->dev,
diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c
index 05e0c353e089..b32bf57910ca 100644
--- a/drivers/iio/buffer/industrialio-buffer-dma.c
+++ b/drivers/iio/buffer/industrialio-buffer-dma.c
@@ -587,7 +587,7 @@ EXPORT_SYMBOL_GPL(iio_dma_buffer_set_bytes_per_datum);
  * Should be used as the set_length callback for iio_buffer_access_ops
  * struct for DMA buffers.
  */
-int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length)
+int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length)
 {
 	/* Avoid an invalid state */
 	if (length < 2)
diff --git a/drivers/iio/buffer/kfifo_buf.c b/drivers/iio/buffer/kfifo_buf.c
index 047fe757ab97..70c302a93d7f 100644
--- a/drivers/iio/buffer/kfifo_buf.c
+++ b/drivers/iio/buffer/kfifo_buf.c
@@ -22,11 +22,18 @@ struct iio_kfifo {
 #define iio_to_kfifo(r) container_of(r, struct iio_kfifo, buffer)
 
 static inline int __iio_allocate_kfifo(struct iio_kfifo *buf,
-				int bytes_per_datum, int length)
+			size_t bytes_per_datum, unsigned int length)
 {
 	if ((length == 0) || (bytes_per_datum == 0))
 		return -EINVAL;
 
+	/*
+	 * Make sure we don't overflow an unsigned int after kfifo rounds up to
+	 * the next power of 2.
+	 */
+	if (roundup_pow_of_two(length) > UINT_MAX / bytes_per_datum)
+		return -EINVAL;
+
 	return __kfifo_alloc((struct __kfifo *)&buf->kf, length,
 			     bytes_per_datum, GFP_KERNEL);
 }
@@ -67,7 +74,7 @@ static int iio_set_bytes_per_datum_kfifo(struct iio_buffer *r, size_t bpd)
 	return 0;
 }
 
-static int iio_set_length_kfifo(struct iio_buffer *r, int length)
+static int iio_set_length_kfifo(struct iio_buffer *r, unsigned int length)
 {
 	/* Avoid an invalid state */
 	if (length < 2)
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index cfb6588565ba..4905a997a7ec 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -178,14 +178,14 @@ int hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 #ifdef CONFIG_PM
 	int ret;
 
-	atomic_set(&st->user_requested_state, state);
-
 	if (atomic_add_unless(&st->runtime_pm_enable, 1, 1))
 		pm_runtime_enable(&st->pdev->dev);
 
-	if (state)
+	if (state) {
+		atomic_inc(&st->user_requested_state);
 		ret = pm_runtime_get_sync(&st->pdev->dev);
-	else {
+	} else {
+		atomic_dec(&st->user_requested_state);
 		pm_runtime_mark_last_busy(&st->pdev->dev);
 		pm_runtime_use_autosuspend(&st->pdev->dev);
 		ret = pm_runtime_put_autosuspend(&st->pdev->dev);
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index ee270e065ba9..2a972ed6851b 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -61,9 +61,12 @@ config INFINIBAND_ON_DEMAND_PAGING
 	  pages on demand instead.
 
 config INFINIBAND_ADDR_TRANS
-	bool
+	bool "RDMA/CM"
 	depends on INFINIBAND
 	default y
+	---help---
+	  Support for RDMA communication manager (CM).
+	  This allows for a generic connection abstraction over RDMA.
 
 config INFINIBAND_ADDR_TRANS_CONFIGFS
 	bool
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index e337b08de2ff..ecc55e98ddd3 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -291,14 +291,18 @@ static int find_gid(struct ib_gid_table *table, const union ib_gid *gid,
 		 * so lookup free slot only if requested.
 		 */
 		if (pempty && empty < 0) {
-			if (data->props & GID_TABLE_ENTRY_INVALID) {
-				/* Found an invalid (free) entry; allocate it */
-				if (data->props & GID_TABLE_ENTRY_DEFAULT) {
-					if (default_gid)
-						empty = curr_index;
-				} else {
-					empty = curr_index;
-				}
+			if (data->props & GID_TABLE_ENTRY_INVALID &&
+			    (default_gid ==
+			     !!(data->props & GID_TABLE_ENTRY_DEFAULT))) {
+				/*
+				 * Found an invalid (free) entry; allocate it.
+				 * If default GID is requested, then our
+				 * found slot must be one of the DEFAULT
+				 * reserved slots or we fail.
+				 * This ensures that only DEFAULT reserved
+				 * slots are used for default property GIDs.
+				 */
+				empty = curr_index;
 			}
 		}
 
@@ -420,8 +424,10 @@ int ib_cache_gid_add(struct ib_device *ib_dev, u8 port,
 	return ret;
 }
 
-int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
-		     union ib_gid *gid, struct ib_gid_attr *attr)
+static int
+_ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
+		  union ib_gid *gid, struct ib_gid_attr *attr,
+		  unsigned long mask, bool default_gid)
 {
 	struct ib_gid_table *table;
 	int ret = 0;
@@ -431,11 +437,7 @@ int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
 
 	mutex_lock(&table->lock);
 
-	ix = find_gid(table, gid, attr, false,
-		      GID_ATTR_FIND_MASK_GID	  |
-		      GID_ATTR_FIND_MASK_GID_TYPE |
-		      GID_ATTR_FIND_MASK_NETDEV,
-		      NULL);
+	ix = find_gid(table, gid, attr, default_gid, mask, NULL);
 	if (ix < 0) {
 		ret = -EINVAL;
 		goto out_unlock;
@@ -452,6 +454,17 @@ out_unlock:
 	return ret;
 }
 
+int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
+		     union ib_gid *gid, struct ib_gid_attr *attr)
+{
+	unsigned long mask = GID_ATTR_FIND_MASK_GID	  |
+			     GID_ATTR_FIND_MASK_GID_TYPE |
+			     GID_ATTR_FIND_MASK_DEFAULT  |
+			     GID_ATTR_FIND_MASK_NETDEV;
+
+	return _ib_cache_gid_del(ib_dev, port, gid, attr, mask, false);
+}
+
 int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port,
 				     struct net_device *ndev)
 {
@@ -489,7 +502,7 @@ static int __ib_cache_gid_get(struct ib_device *ib_dev, u8 port, int index,
 		return -EINVAL;
 
 	if (table->data_vec[index].props & GID_TABLE_ENTRY_INVALID)
-		return -EAGAIN;
+		return -EINVAL;
 
 	memcpy(gid, &table->data_vec[index].gid, sizeof(*gid));
 	if (attr) {
@@ -728,7 +741,7 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port,
 				  unsigned long gid_type_mask,
 				  enum ib_cache_gid_default_mode mode)
 {
-	union ib_gid gid;
+	union ib_gid gid = { };
 	struct ib_gid_attr gid_attr;
 	struct ib_gid_table *table;
 	unsigned int gid_type;
@@ -736,7 +749,9 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port,
 
 	table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
 
-	make_default_gid(ndev, &gid);
+	mask = GID_ATTR_FIND_MASK_GID_TYPE |
+	       GID_ATTR_FIND_MASK_DEFAULT |
+	       GID_ATTR_FIND_MASK_NETDEV;
 	memset(&gid_attr, 0, sizeof(gid_attr));
 	gid_attr.ndev = ndev;
 
@@ -747,12 +762,12 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port,
 		gid_attr.gid_type = gid_type;
 
 		if (mode == IB_CACHE_GID_DEFAULT_MODE_SET) {
-			mask = GID_ATTR_FIND_MASK_GID_TYPE |
-			       GID_ATTR_FIND_MASK_DEFAULT;
+			make_default_gid(ndev, &gid);
 			__ib_cache_gid_add(ib_dev, port, &gid,
 					   &gid_attr, mask, true);
 		} else if (mode == IB_CACHE_GID_DEFAULT_MODE_DELETE) {
-			ib_cache_gid_del(ib_dev, port, &gid, &gid_attr);
+			_ib_cache_gid_del(ib_dev, port, &gid,
+					  &gid_attr, mask, true);
 		}
 	}
 }
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 51a641002e10..a693fcd4c513 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -382,6 +382,8 @@ struct cma_hdr {
 #define CMA_VERSION 0x00
 
 struct cma_req_info {
+	struct sockaddr_storage listen_addr_storage;
+	struct sockaddr_storage src_addr_storage;
 	struct ib_device *device;
 	int port;
 	union ib_gid local_gid;
@@ -866,7 +868,6 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 {
 	struct ib_qp_attr qp_attr;
 	int qp_attr_mask, ret;
-	union ib_gid sgid;
 
 	mutex_lock(&id_priv->qp_mutex);
 	if (!id_priv->id.qp) {
@@ -889,12 +890,6 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 	if (ret)
 		goto out;
 
-	ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num,
-			   rdma_ah_read_grh(&qp_attr.ah_attr)->sgid_index,
-			   &sgid, NULL);
-	if (ret)
-		goto out;
-
 	BUG_ON(id_priv->cma_dev->device != id_priv->id.device);
 
 	if (conn_param)
@@ -1340,11 +1335,11 @@ static bool validate_net_dev(struct net_device *net_dev,
 }
 
 static struct net_device *cma_get_net_dev(struct ib_cm_event *ib_event,
-					  const struct cma_req_info *req)
+					  struct cma_req_info *req)
 {
-	struct sockaddr_storage listen_addr_storage, src_addr_storage;
-	struct sockaddr *listen_addr = (struct sockaddr *)&listen_addr_storage,
-			*src_addr = (struct sockaddr *)&src_addr_storage;
+	struct sockaddr *listen_addr =
+			(struct sockaddr *)&req->listen_addr_storage;
+	struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage;
 	struct net_device *net_dev;
 	const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL;
 	int err;
@@ -1359,11 +1354,6 @@ static struct net_device *cma_get_net_dev(struct ib_cm_event *ib_event,
 	if (!net_dev)
 		return ERR_PTR(-ENODEV);
 
-	if (!validate_net_dev(net_dev, listen_addr, src_addr)) {
-		dev_put(net_dev);
-		return ERR_PTR(-EHOSTUNREACH);
-	}
-
 	return net_dev;
 }
 
@@ -1490,15 +1480,51 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id,
 		}
 	}
 
+	/*
+	 * Net namespace might be getting deleted while route lookup,
+	 * cm_id lookup is in progress. Therefore, perform netdevice
+	 * validation, cm_id lookup under rcu lock.
+	 * RCU lock along with netdevice state check, synchronizes with
+	 * netdevice migrating to different net namespace and also avoids
+	 * case where net namespace doesn't get deleted while lookup is in
+	 * progress.
+	 * If the device state is not IFF_UP, its properties such as ifindex
+	 * and nd_net cannot be trusted to remain valid without rcu lock.
+	 * net/core/dev.c change_net_namespace() ensures to synchronize with
+	 * ongoing operations on net device after device is closed using
+	 * synchronize_net().
+	 */
+	rcu_read_lock();
+	if (*net_dev) {
+		/*
+		 * If netdevice is down, it is likely that it is administratively
+		 * down or it might be migrating to different namespace.
+		 * In that case avoid further processing, as the net namespace
+		 * or ifindex may change.
+		 */
+		if (((*net_dev)->flags & IFF_UP) == 0) {
+			id_priv = ERR_PTR(-EHOSTUNREACH);
+			goto err;
+		}
+
+		if (!validate_net_dev(*net_dev,
+				 (struct sockaddr *)&req.listen_addr_storage,
+				 (struct sockaddr *)&req.src_addr_storage)) {
+			id_priv = ERR_PTR(-EHOSTUNREACH);
+			goto err;
+		}
+	}
+
 	bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net,
 				rdma_ps_from_service_id(req.service_id),
 				cma_port_from_service_id(req.service_id));
 	id_priv = cma_find_listener(bind_list, cm_id, ib_event, &req, *net_dev);
+err:
+	rcu_read_unlock();
 	if (IS_ERR(id_priv) && *net_dev) {
 		dev_put(*net_dev);
 		*net_dev = NULL;
 	}
-
 	return id_priv;
 }
 
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index 9821ae900f6d..da12da1c36f6 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -114,7 +114,7 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
 			struct sockaddr_storage *mapped_sockaddr,
 			u8 nl_client)
 {
-	struct hlist_head *hash_bucket_head;
+	struct hlist_head *hash_bucket_head = NULL;
 	struct iwpm_mapping_info *map_info;
 	unsigned long flags;
 	int ret = -EINVAL;
@@ -142,6 +142,9 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
 		}
 	}
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
+
+	if (!hash_bucket_head)
+		kfree(map_info);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index c50596f7f98a..b28452a55a08 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -59,7 +59,7 @@ module_param_named(recv_queue_size, mad_recvq_size, int, 0444);
 MODULE_PARM_DESC(recv_queue_size, "Size of receive queue in number of work requests");
 
 static struct list_head ib_mad_port_list;
-static u32 ib_mad_client_id = 0;
+static atomic_t ib_mad_client_id = ATOMIC_INIT(0);
 
 /* Port list lock */
 static DEFINE_SPINLOCK(ib_mad_port_list_lock);
@@ -377,7 +377,7 @@ struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
 	}
 
 	spin_lock_irqsave(&port_priv->reg_lock, flags);
-	mad_agent_priv->agent.hi_tid = ++ib_mad_client_id;
+	mad_agent_priv->agent.hi_tid = atomic_inc_return(&ib_mad_client_id);
 
 	/*
 	 * Make sure MAD registration (if supplied)
diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c
index cc2966380c0c..c0e4fd55e2cc 100644
--- a/drivers/infiniband/core/roce_gid_mgmt.c
+++ b/drivers/infiniband/core/roce_gid_mgmt.c
@@ -255,6 +255,7 @@ static void bond_delete_netdev_default_gids(struct ib_device *ib_dev,
 					    struct net_device *rdma_ndev)
 {
 	struct net_device *real_dev = rdma_vlan_dev_real_dev(event_ndev);
+	unsigned long gid_type_mask;
 
 	if (!rdma_ndev)
 		return;
@@ -264,21 +265,22 @@ static void bond_delete_netdev_default_gids(struct ib_device *ib_dev,
 
 	rcu_read_lock();
 
-	if (rdma_is_upper_dev_rcu(rdma_ndev, event_ndev) &&
-	    is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) ==
-	    BONDING_SLAVE_STATE_INACTIVE) {
-		unsigned long gid_type_mask;
-
+	if (((rdma_ndev != event_ndev &&
+	      !rdma_is_upper_dev_rcu(rdma_ndev, event_ndev)) ||
+	     is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev)
+						 ==
+	     BONDING_SLAVE_STATE_INACTIVE)) {
 		rcu_read_unlock();
+		return;
+	}
 
-		gid_type_mask = roce_gid_type_mask_support(ib_dev, port);
+	rcu_read_unlock();
 
-		ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev,
-					     gid_type_mask,
-					     IB_CACHE_GID_DEFAULT_MODE_DELETE);
-	} else {
-		rcu_read_unlock();
-	}
+	gid_type_mask = roce_gid_type_mask_support(ib_dev, port);
+
+	ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev,
+				     gid_type_mask,
+				     IB_CACHE_GID_DEFAULT_MODE_DELETE);
 }
 
 static void enum_netdev_ipv4_ips(struct ib_device *ib_dev,
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 74329483af6d..eab43b17e9cf 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -159,6 +159,23 @@ static void ucma_put_ctx(struct ucma_context *ctx)
 		complete(&ctx->comp);
 }
 
+/*
+ * Same as ucm_get_ctx but requires that ->cm_id->device is valid, eg that the
+ * CM_ID is bound.
+ */
+static struct ucma_context *ucma_get_ctx_dev(struct ucma_file *file, int id)
+{
+	struct ucma_context *ctx = ucma_get_ctx(file, id);
+
+	if (IS_ERR(ctx))
+		return ctx;
+	if (!ctx->cm_id->device) {
+		ucma_put_ctx(ctx);
+		return ERR_PTR(-EINVAL);
+	}
+	return ctx;
+}
+
 static void ucma_close_event_id(struct work_struct *work)
 {
 	struct ucma_event *uevent_close =  container_of(work, struct ucma_event, close_work);
@@ -683,7 +700,7 @@ static ssize_t ucma_resolve_ip(struct ucma_file *file,
 	if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
 		return -EFAULT;
 
-	if (!rdma_addr_size_in6(&cmd.src_addr) ||
+	if ((cmd.src_addr.sin6_family && !rdma_addr_size_in6(&cmd.src_addr)) ||
 	    !rdma_addr_size_in6(&cmd.dst_addr))
 		return -EINVAL;
 
@@ -734,7 +751,7 @@ static ssize_t ucma_resolve_route(struct ucma_file *file,
 	if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
 		return -EFAULT;
 
-	ctx = ucma_get_ctx(file, cmd.id);
+	ctx = ucma_get_ctx_dev(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
@@ -1050,7 +1067,7 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf,
 	if (!cmd.conn_param.valid)
 		return -EINVAL;
 
-	ctx = ucma_get_ctx(file, cmd.id);
+	ctx = ucma_get_ctx_dev(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
@@ -1092,7 +1109,7 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf,
 	if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
 		return -EFAULT;
 
-	ctx = ucma_get_ctx(file, cmd.id);
+	ctx = ucma_get_ctx_dev(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
@@ -1120,7 +1137,7 @@ static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf,
 	if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
 		return -EFAULT;
 
-	ctx = ucma_get_ctx(file, cmd.id);
+	ctx = ucma_get_ctx_dev(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
@@ -1139,7 +1156,7 @@ static ssize_t ucma_disconnect(struct ucma_file *file, const char __user *inbuf,
 	if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
 		return -EFAULT;
 
-	ctx = ucma_get_ctx(file, cmd.id);
+	ctx = ucma_get_ctx_dev(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
@@ -1167,15 +1184,10 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file,
 	if (cmd.qp_state > IB_QPS_ERR)
 		return -EINVAL;
 
-	ctx = ucma_get_ctx(file, cmd.id);
+	ctx = ucma_get_ctx_dev(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	if (!ctx->cm_id->device) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	resp.qp_attr_mask = 0;
 	memset(&qp_attr, 0, sizeof qp_attr);
 	qp_attr.qp_state = cmd.qp_state;
@@ -1316,13 +1328,13 @@ static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf,
 	if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
 		return -EFAULT;
 
+	if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE))
+		return -EINVAL;
+
 	ctx = ucma_get_ctx(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE))
-		return -EINVAL;
-
 	optval = memdup_user(u64_to_user_ptr(cmd.optval),
 			     cmd.optlen);
 	if (IS_ERR(optval)) {
@@ -1384,7 +1396,7 @@ static ssize_t ucma_process_join(struct ucma_file *file,
 	else
 		return -EINVAL;
 
-	ctx = ucma_get_ctx(file, cmd->id);
+	ctx = ucma_get_ctx_dev(file, cmd->id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 9a4e899d94b3..2b6c9b516070 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -119,7 +119,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	umem->length     = size;
 	umem->address    = addr;
 	umem->page_shift = PAGE_SHIFT;
-	umem->pid	 = get_task_pid(current, PIDTYPE_PID);
 	/*
 	 * We ask for writable memory if any of the following
 	 * access flags are set.  "Local write" and "remote write"
@@ -132,7 +131,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
 
 	if (access & IB_ACCESS_ON_DEMAND) {
-		put_pid(umem->pid);
 		ret = ib_umem_odp_get(context, umem, access);
 		if (ret) {
 			kfree(umem);
@@ -148,7 +146,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	page_list = (struct page **) __get_free_page(GFP_KERNEL);
 	if (!page_list) {
-		put_pid(umem->pid);
 		kfree(umem);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -231,7 +228,6 @@ out:
 	if (ret < 0) {
 		if (need_release)
 			__ib_umem_release(context->device, umem, 0);
-		put_pid(umem->pid);
 		kfree(umem);
 	} else
 		current->mm->pinned_vm = locked;
@@ -274,8 +270,7 @@ void ib_umem_release(struct ib_umem *umem)
 
 	__ib_umem_release(umem->context->device, umem, 1);
 
-	task = get_pid_task(umem->pid, PIDTYPE_PID);
-	put_pid(umem->pid);
+	task = get_pid_task(umem->context->tgid, PIDTYPE_PID);
 	if (!task)
 		goto out;
 	mm = get_task_mm(task);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 13cb5e4deb86..21a887c9523b 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -691,6 +691,7 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 
 	mr->device  = pd->device;
 	mr->pd      = pd;
+	mr->dm	    = NULL;
 	mr->uobject = uobj;
 	atomic_inc(&pd->usecnt);
 	mr->res.type = RDMA_RESTRACK_MR;
@@ -765,6 +766,11 @@ ssize_t ib_uverbs_rereg_mr(struct ib_uverbs_file *file,
 
 	mr = uobj->object;
 
+	if (mr->dm) {
+		ret = -EINVAL;
+		goto put_uobjs;
+	}
+
 	if (cmd.flags & IB_MR_REREG_ACCESS) {
 		ret = ib_check_mr_access(cmd.access_flags);
 		if (ret)
diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c
index 8c93970dc8f1..8d32c4ae368c 100644
--- a/drivers/infiniband/core/uverbs_ioctl.c
+++ b/drivers/infiniband/core/uverbs_ioctl.c
@@ -234,6 +234,15 @@ static int uverbs_validate_kernel_mandatory(const struct uverbs_method_spec *met
 			return -EINVAL;
 	}
 
+	for (; i < method_spec->num_buckets; i++) {
+		struct uverbs_attr_spec_hash *attr_spec_bucket =
+			method_spec->attr_buckets[i];
+
+		if (!bitmap_empty(attr_spec_bucket->mandatory_attrs_bitmask,
+				  attr_spec_bucket->num_attrs))
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/core/uverbs_std_types_flow_action.c b/drivers/infiniband/core/uverbs_std_types_flow_action.c
index cbcec3da12f6..b4f016dfa23d 100644
--- a/drivers/infiniband/core/uverbs_std_types_flow_action.c
+++ b/drivers/infiniband/core/uverbs_std_types_flow_action.c
@@ -363,28 +363,28 @@ static int UVERBS_HANDLER(UVERBS_METHOD_FLOW_ACTION_ESP_MODIFY)(struct ib_device
 
 static const struct uverbs_attr_spec uverbs_flow_action_esp_keymat[] = {
 	[IB_UVERBS_FLOW_ACTION_ESP_KEYMAT_AES_GCM] = {
-		.ptr = {
+		{ .ptr = {
 			.type = UVERBS_ATTR_TYPE_PTR_IN,
 			UVERBS_ATTR_TYPE(struct ib_uverbs_flow_action_esp_keymat_aes_gcm),
 			.flags = UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO,
-		},
+		} },
 	},
 };
 
 static const struct uverbs_attr_spec uverbs_flow_action_esp_replay[] = {
 	[IB_UVERBS_FLOW_ACTION_ESP_REPLAY_NONE] = {
-		.ptr = {
+		{ .ptr = {
 			.type = UVERBS_ATTR_TYPE_PTR_IN,
 			/* No need to specify any data */
 			.len = 0,
-		}
+		} }
 	},
 	[IB_UVERBS_FLOW_ACTION_ESP_REPLAY_BMP] = {
-		.ptr = {
+		{ .ptr = {
 			.type = UVERBS_ATTR_TYPE_PTR_IN,
 			UVERBS_ATTR_STRUCT(struct ib_uverbs_flow_action_esp_replay_bmp, size),
 			.flags = UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO,
-		}
+		} }
 	},
 };
 
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 7eff3aeffe01..6ddfb1fade79 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1656,6 +1656,7 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
 	if (!IS_ERR(mr)) {
 		mr->device  = pd->device;
 		mr->pd      = pd;
+		mr->dm      = NULL;
 		mr->uobject = NULL;
 		atomic_inc(&pd->usecnt);
 		mr->need_inval = false;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index f6c739ec8b62..20b9f31052bf 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -185,12 +185,65 @@ static void bnxt_re_shutdown(void *p)
 	bnxt_re_ib_unreg(rdev, false);
 }
 
+static void bnxt_re_stop_irq(void *handle)
+{
+	struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+	struct bnxt_qplib_rcfw *rcfw = &rdev->rcfw;
+	struct bnxt_qplib_nq *nq;
+	int indx;
+
+	for (indx = BNXT_RE_NQ_IDX; indx < rdev->num_msix; indx++) {
+		nq = &rdev->nq[indx - 1];
+		bnxt_qplib_nq_stop_irq(nq, false);
+	}
+
+	bnxt_qplib_rcfw_stop_irq(rcfw, false);
+}
+
+static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
+{
+	struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+	struct bnxt_msix_entry *msix_ent = rdev->msix_entries;
+	struct bnxt_qplib_rcfw *rcfw = &rdev->rcfw;
+	struct bnxt_qplib_nq *nq;
+	int indx, rc;
+
+	if (!ent) {
+		/* Not setting the f/w timeout bit in rcfw.
+		 * During the driver unload the first command
+		 * to f/w will timeout and that will set the
+		 * timeout bit.
+		 */
+		dev_err(rdev_to_dev(rdev), "Failed to re-start IRQs\n");
+		return;
+	}
+
+	/* Vectors may change after restart, so update with new vectors
+	 * in device sctructure.
+	 */
+	for (indx = 0; indx < rdev->num_msix; indx++)
+		rdev->msix_entries[indx].vector = ent[indx].vector;
+
+	bnxt_qplib_rcfw_start_irq(rcfw, msix_ent[BNXT_RE_AEQ_IDX].vector,
+				  false);
+	for (indx = BNXT_RE_NQ_IDX ; indx < rdev->num_msix; indx++) {
+		nq = &rdev->nq[indx - 1];
+		rc = bnxt_qplib_nq_start_irq(nq, indx - 1,
+					     msix_ent[indx].vector, false);
+		if (rc)
+			dev_warn(rdev_to_dev(rdev),
+				 "Failed to reinit NQ index %d\n", indx - 1);
+	}
+}
+
 static struct bnxt_ulp_ops bnxt_re_ulp_ops = {
 	.ulp_async_notifier = NULL,
 	.ulp_stop = bnxt_re_stop,
 	.ulp_start = bnxt_re_start,
 	.ulp_sriov_config = bnxt_re_sriov_config,
-	.ulp_shutdown = bnxt_re_shutdown
+	.ulp_shutdown = bnxt_re_shutdown,
+	.ulp_irq_stop = bnxt_re_stop_irq,
+	.ulp_irq_restart = bnxt_re_start_irq
 };
 
 /* RoCE -> Net driver */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 3a78faba8d91..50d8f1fc98d5 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -336,22 +336,32 @@ static irqreturn_t bnxt_qplib_nq_irq(int irq, void *dev_instance)
 	return IRQ_HANDLED;
 }
 
+void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill)
+{
+	tasklet_disable(&nq->worker);
+	/* Mask h/w interrupt */
+	NQ_DB(nq->bar_reg_iomem, nq->hwq.cons, nq->hwq.max_elements);
+	/* Sync with last running IRQ handler */
+	synchronize_irq(nq->vector);
+	if (kill)
+		tasklet_kill(&nq->worker);
+	if (nq->requested) {
+		irq_set_affinity_hint(nq->vector, NULL);
+		free_irq(nq->vector, nq);
+		nq->requested = false;
+	}
+}
+
 void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
 {
 	if (nq->cqn_wq) {
 		destroy_workqueue(nq->cqn_wq);
 		nq->cqn_wq = NULL;
 	}
+
 	/* Make sure the HW is stopped! */
-	synchronize_irq(nq->vector);
-	tasklet_disable(&nq->worker);
-	tasklet_kill(&nq->worker);
+	bnxt_qplib_nq_stop_irq(nq, true);
 
-	if (nq->requested) {
-		irq_set_affinity_hint(nq->vector, NULL);
-		free_irq(nq->vector, nq);
-		nq->requested = false;
-	}
 	if (nq->bar_reg_iomem)
 		iounmap(nq->bar_reg_iomem);
 	nq->bar_reg_iomem = NULL;
@@ -361,6 +371,40 @@ void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
 	nq->vector = 0;
 }
 
+int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx,
+			    int msix_vector, bool need_init)
+{
+	int rc;
+
+	if (nq->requested)
+		return -EFAULT;
+
+	nq->vector = msix_vector;
+	if (need_init)
+		tasklet_init(&nq->worker, bnxt_qplib_service_nq,
+			     (unsigned long)nq);
+	else
+		tasklet_enable(&nq->worker);
+
+	snprintf(nq->name, sizeof(nq->name), "bnxt_qplib_nq-%d", nq_indx);
+	rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, nq->name, nq);
+	if (rc)
+		return rc;
+
+	cpumask_clear(&nq->mask);
+	cpumask_set_cpu(nq_indx, &nq->mask);
+	rc = irq_set_affinity_hint(nq->vector, &nq->mask);
+	if (rc) {
+		dev_warn(&nq->pdev->dev,
+			 "QPLIB: set affinity failed; vector: %d nq_idx: %d\n",
+			 nq->vector, nq_indx);
+	}
+	nq->requested = true;
+	NQ_DB_REARM(nq->bar_reg_iomem, nq->hwq.cons, nq->hwq.max_elements);
+
+	return rc;
+}
+
 int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 			 int nq_idx, int msix_vector, int bar_reg_offset,
 			 int (*cqn_handler)(struct bnxt_qplib_nq *nq,
@@ -372,41 +416,17 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 	resource_size_t nq_base;
 	int rc = -1;
 
-	nq->pdev = pdev;
-	nq->vector = msix_vector;
 	if (cqn_handler)
 		nq->cqn_handler = cqn_handler;
 
 	if (srqn_handler)
 		nq->srqn_handler = srqn_handler;
 
-	tasklet_init(&nq->worker, bnxt_qplib_service_nq, (unsigned long)nq);
-
 	/* Have a task to schedule CQ notifiers in post send case */
 	nq->cqn_wq  = create_singlethread_workqueue("bnxt_qplib_nq");
 	if (!nq->cqn_wq)
-		goto fail;
-
-	nq->requested = false;
-	memset(nq->name, 0, 32);
-	sprintf(nq->name, "bnxt_qplib_nq-%d", nq_idx);
-	rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, nq->name, nq);
-	if (rc) {
-		dev_err(&nq->pdev->dev,
-			"Failed to request IRQ for NQ: %#x", rc);
-		goto fail;
-	}
-
-	cpumask_clear(&nq->mask);
-	cpumask_set_cpu(nq_idx, &nq->mask);
-	rc = irq_set_affinity_hint(nq->vector, &nq->mask);
-	if (rc) {
-		dev_warn(&nq->pdev->dev,
-			 "QPLIB: set affinity failed; vector: %d nq_idx: %d\n",
-			 nq->vector, nq_idx);
-	}
+		return -ENOMEM;
 
-	nq->requested = true;
 	nq->bar_reg = NQ_CONS_PCI_BAR_REGION;
 	nq->bar_reg_off = bar_reg_offset;
 	nq_base = pci_resource_start(pdev, nq->bar_reg);
@@ -419,7 +439,13 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 		rc = -ENOMEM;
 		goto fail;
 	}
-	NQ_DB_REARM(nq->bar_reg_iomem, nq->hwq.cons, nq->hwq.max_elements);
+
+	rc = bnxt_qplib_nq_start_irq(nq, nq_idx, msix_vector, true);
+	if (rc) {
+		dev_err(&nq->pdev->dev,
+			"QPLIB: Failed to request irq for nq-idx %d", nq_idx);
+		goto fail;
+	}
 
 	return 0;
 fail:
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
index ade9f13c0fd1..72352ca80ace 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -467,7 +467,10 @@ struct bnxt_qplib_nq_work {
 	struct bnxt_qplib_cq    *cq;
 };
 
+void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill);
 void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq);
+int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx,
+			    int msix_vector, bool need_init);
 int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 			 int nq_idx, int msix_vector, int bar_reg_offset,
 			 int (*cqn_handler)(struct bnxt_qplib_nq *nq,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 80027a494730..2852d350ada1 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -582,19 +582,29 @@ fail:
 	return -ENOMEM;
 }
 
-void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
+void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill)
 {
-	unsigned long indx;
-
-	/* Make sure the HW channel is stopped! */
-	synchronize_irq(rcfw->vector);
 	tasklet_disable(&rcfw->worker);
-	tasklet_kill(&rcfw->worker);
+	/* Mask h/w interrupts */
+	CREQ_DB(rcfw->creq_bar_reg_iomem, rcfw->creq.cons,
+		rcfw->creq.max_elements);
+	/* Sync with last running IRQ-handler */
+	synchronize_irq(rcfw->vector);
+	if (kill)
+		tasklet_kill(&rcfw->worker);
 
 	if (rcfw->requested) {
 		free_irq(rcfw->vector, rcfw);
 		rcfw->requested = false;
 	}
+}
+
+void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
+{
+	unsigned long indx;
+
+	bnxt_qplib_rcfw_stop_irq(rcfw, true);
+
 	if (rcfw->cmdq_bar_reg_iomem)
 		iounmap(rcfw->cmdq_bar_reg_iomem);
 	rcfw->cmdq_bar_reg_iomem = NULL;
@@ -614,6 +624,31 @@ void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
 	rcfw->vector = 0;
 }
 
+int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector,
+			      bool need_init)
+{
+	int rc;
+
+	if (rcfw->requested)
+		return -EFAULT;
+
+	rcfw->vector = msix_vector;
+	if (need_init)
+		tasklet_init(&rcfw->worker,
+			     bnxt_qplib_service_creq, (unsigned long)rcfw);
+	else
+		tasklet_enable(&rcfw->worker);
+	rc = request_irq(rcfw->vector, bnxt_qplib_creq_irq, 0,
+			 "bnxt_qplib_creq", rcfw);
+	if (rc)
+		return rc;
+	rcfw->requested = true;
+	CREQ_DB_REARM(rcfw->creq_bar_reg_iomem, rcfw->creq.cons,
+		      rcfw->creq.max_elements);
+
+	return 0;
+}
+
 int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev,
 				   struct bnxt_qplib_rcfw *rcfw,
 				   int msix_vector,
@@ -675,27 +710,17 @@ int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev,
 	rcfw->creq_qp_event_processed = 0;
 	rcfw->creq_func_event_processed = 0;
 
-	rcfw->vector = msix_vector;
 	if (aeq_handler)
 		rcfw->aeq_handler = aeq_handler;
+	init_waitqueue_head(&rcfw->waitq);
 
-	tasklet_init(&rcfw->worker, bnxt_qplib_service_creq,
-		     (unsigned long)rcfw);
-
-	rcfw->requested = false;
-	rc = request_irq(rcfw->vector, bnxt_qplib_creq_irq, 0,
-			 "bnxt_qplib_creq", rcfw);
+	rc = bnxt_qplib_rcfw_start_irq(rcfw, msix_vector, true);
 	if (rc) {
 		dev_err(&rcfw->pdev->dev,
 			"QPLIB: Failed to request IRQ for CREQ rc = 0x%x", rc);
 		bnxt_qplib_disable_rcfw_channel(rcfw);
 		return rc;
 	}
-	rcfw->requested = true;
-
-	init_waitqueue_head(&rcfw->waitq);
-
-	CREQ_DB_REARM(rcfw->creq_bar_reg_iomem, 0, rcfw->creq.max_elements);
 
 	init.cmdq_pbl = cpu_to_le64(rcfw->cmdq.pbl[PBL_LVL_0].pg_map_arr[0]);
 	init.cmdq_size_cmdq_lvl = cpu_to_le16(
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index c7cce2e4185e..46416dfe8830 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -195,7 +195,10 @@ struct bnxt_qplib_rcfw {
 void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev,
 				  struct bnxt_qplib_rcfw *rcfw, int qp_tbl_sz);
+void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill);
 void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
+int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector,
+			      bool need_init);
 int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev,
 				   struct bnxt_qplib_rcfw *rcfw,
 				   int msix_vector,
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 6f2b26126c64..2be2e1ac1b5f 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -315,7 +315,7 @@ static void advance_oldest_read(struct t4_wq *wq)
  * Deal with out-of-order and/or completions that complete
  * prior unsignalled WRs.
  */
-void c4iw_flush_hw_cq(struct c4iw_cq *chp)
+void c4iw_flush_hw_cq(struct c4iw_cq *chp, struct c4iw_qp *flush_qhp)
 {
 	struct t4_cqe *hw_cqe, *swcqe, read_cqe;
 	struct c4iw_qp *qhp;
@@ -339,6 +339,13 @@ void c4iw_flush_hw_cq(struct c4iw_cq *chp)
 		if (qhp == NULL)
 			goto next_cqe;
 
+		if (flush_qhp != qhp) {
+			spin_lock(&qhp->lock);
+
+			if (qhp->wq.flushed == 1)
+				goto next_cqe;
+		}
+
 		if (CQE_OPCODE(hw_cqe) == FW_RI_TERMINATE)
 			goto next_cqe;
 
@@ -390,6 +397,8 @@ void c4iw_flush_hw_cq(struct c4iw_cq *chp)
 next_cqe:
 		t4_hwcq_consume(&chp->cq);
 		ret = t4_next_hw_cqe(&chp->cq, &hw_cqe);
+		if (qhp && flush_qhp != qhp)
+			spin_unlock(&qhp->lock);
 	}
 }
 
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index feeb8ee6f4a2..44161ca4d2a8 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -875,6 +875,11 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 
 	rdev->status_page->db_off = 0;
 
+	init_completion(&rdev->rqt_compl);
+	init_completion(&rdev->pbl_compl);
+	kref_init(&rdev->rqt_kref);
+	kref_init(&rdev->pbl_kref);
+
 	return 0;
 err_free_status_page_and_wr_log:
 	if (c4iw_wr_log && rdev->wr_log)
@@ -893,13 +898,15 @@ destroy_resource:
 
 static void c4iw_rdev_close(struct c4iw_rdev *rdev)
 {
-	destroy_workqueue(rdev->free_workq);
 	kfree(rdev->wr_log);
 	c4iw_release_dev_ucontext(rdev, &rdev->uctx);
 	free_page((unsigned long)rdev->status_page);
 	c4iw_pblpool_destroy(rdev);
 	c4iw_rqtpool_destroy(rdev);
+	wait_for_completion(&rdev->pbl_compl);
+	wait_for_completion(&rdev->rqt_compl);
 	c4iw_ocqp_pool_destroy(rdev);
+	destroy_workqueue(rdev->free_workq);
 	c4iw_destroy_resource(&rdev->resource);
 }
 
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index cc929002c05e..831027717121 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -185,6 +185,10 @@ struct c4iw_rdev {
 	struct wr_log_entry *wr_log;
 	int wr_log_size;
 	struct workqueue_struct *free_workq;
+	struct completion rqt_compl;
+	struct completion pbl_compl;
+	struct kref rqt_kref;
+	struct kref pbl_kref;
 };
 
 static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
@@ -1049,7 +1053,7 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size);
 void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size);
 u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size);
 void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size);
-void c4iw_flush_hw_cq(struct c4iw_cq *chp);
+void c4iw_flush_hw_cq(struct c4iw_cq *chp, struct c4iw_qp *flush_qhp);
 void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count);
 int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp);
 int c4iw_flush_rq(struct t4_wq *wq, struct t4_cq *cq, int count);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index e90f2fd8dc16..1445918e3239 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -489,10 +489,10 @@ struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc)
 err_dereg_mem:
 	dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
 		  mhp->attr.pbl_addr, mhp->dereg_skb, mhp->wr_waitp);
-err_free_wr_wait:
-	c4iw_put_wr_wait(mhp->wr_waitp);
 err_free_skb:
 	kfree_skb(mhp->dereg_skb);
+err_free_wr_wait:
+	c4iw_put_wr_wait(mhp->wr_waitp);
 err_free_mhp:
 	kfree(mhp);
 	return ERR_PTR(ret);
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index de77b6027d69..ae167b686608 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1343,12 +1343,12 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
 	qhp->wq.flushed = 1;
 	t4_set_wq_in_error(&qhp->wq);
 
-	c4iw_flush_hw_cq(rchp);
+	c4iw_flush_hw_cq(rchp, qhp);
 	c4iw_count_rcqes(&rchp->cq, &qhp->wq, &count);
 	rq_flushed = c4iw_flush_rq(&qhp->wq, &rchp->cq, count);
 
 	if (schp != rchp)
-		c4iw_flush_hw_cq(schp);
+		c4iw_flush_hw_cq(schp, qhp);
 	sq_flushed = c4iw_flush_sq(qhp);
 
 	spin_unlock(&qhp->lock);
diff --git a/drivers/infiniband/hw/cxgb4/resource.c b/drivers/infiniband/hw/cxgb4/resource.c
index 3cf25997ed2b..0ef25ae05e6f 100644
--- a/drivers/infiniband/hw/cxgb4/resource.c
+++ b/drivers/infiniband/hw/cxgb4/resource.c
@@ -260,12 +260,22 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size)
 		rdev->stats.pbl.cur += roundup(size, 1 << MIN_PBL_SHIFT);
 		if (rdev->stats.pbl.cur > rdev->stats.pbl.max)
 			rdev->stats.pbl.max = rdev->stats.pbl.cur;
+		kref_get(&rdev->pbl_kref);
 	} else
 		rdev->stats.pbl.fail++;
 	mutex_unlock(&rdev->stats.lock);
 	return (u32)addr;
 }
 
+static void destroy_pblpool(struct kref *kref)
+{
+	struct c4iw_rdev *rdev;
+
+	rdev = container_of(kref, struct c4iw_rdev, pbl_kref);
+	gen_pool_destroy(rdev->pbl_pool);
+	complete(&rdev->pbl_compl);
+}
+
 void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 {
 	pr_debug("addr 0x%x size %d\n", addr, size);
@@ -273,6 +283,7 @@ void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 	rdev->stats.pbl.cur -= roundup(size, 1 << MIN_PBL_SHIFT);
 	mutex_unlock(&rdev->stats.lock);
 	gen_pool_free(rdev->pbl_pool, (unsigned long)addr, size);
+	kref_put(&rdev->pbl_kref, destroy_pblpool);
 }
 
 int c4iw_pblpool_create(struct c4iw_rdev *rdev)
@@ -310,7 +321,7 @@ int c4iw_pblpool_create(struct c4iw_rdev *rdev)
 
 void c4iw_pblpool_destroy(struct c4iw_rdev *rdev)
 {
-	gen_pool_destroy(rdev->pbl_pool);
+	kref_put(&rdev->pbl_kref, destroy_pblpool);
 }
 
 /*
@@ -331,12 +342,22 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size)
 		rdev->stats.rqt.cur += roundup(size << 6, 1 << MIN_RQT_SHIFT);
 		if (rdev->stats.rqt.cur > rdev->stats.rqt.max)
 			rdev->stats.rqt.max = rdev->stats.rqt.cur;
+		kref_get(&rdev->rqt_kref);
 	} else
 		rdev->stats.rqt.fail++;
 	mutex_unlock(&rdev->stats.lock);
 	return (u32)addr;
 }
 
+static void destroy_rqtpool(struct kref *kref)
+{
+	struct c4iw_rdev *rdev;
+
+	rdev = container_of(kref, struct c4iw_rdev, rqt_kref);
+	gen_pool_destroy(rdev->rqt_pool);
+	complete(&rdev->rqt_compl);
+}
+
 void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 {
 	pr_debug("addr 0x%x size %d\n", addr, size << 6);
@@ -344,6 +365,7 @@ void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 	rdev->stats.rqt.cur -= roundup(size << 6, 1 << MIN_RQT_SHIFT);
 	mutex_unlock(&rdev->stats.lock);
 	gen_pool_free(rdev->rqt_pool, (unsigned long)addr, size << 6);
+	kref_put(&rdev->rqt_kref, destroy_rqtpool);
 }
 
 int c4iw_rqtpool_create(struct c4iw_rdev *rdev)
@@ -380,7 +402,7 @@ int c4iw_rqtpool_create(struct c4iw_rdev *rdev)
 
 void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev)
 {
-	gen_pool_destroy(rdev->rqt_pool);
+	kref_put(&rdev->rqt_kref, destroy_rqtpool);
 }
 
 /*
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index a97055dd4fbd..b5fab55cc275 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -412,7 +412,6 @@ static void hfi1_cleanup_sdma_notifier(struct hfi1_msix_entry *msix)
 static int get_irq_affinity(struct hfi1_devdata *dd,
 			    struct hfi1_msix_entry *msix)
 {
-	int ret;
 	cpumask_var_t diff;
 	struct hfi1_affinity_node *entry;
 	struct cpu_mask_set *set = NULL;
@@ -424,10 +423,6 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 	extra[0] = '\0';
 	cpumask_clear(&msix->mask);
 
-	ret = zalloc_cpumask_var(&diff, GFP_KERNEL);
-	if (!ret)
-		return -ENOMEM;
-
 	entry = node_affinity_lookup(dd->node);
 
 	switch (msix->type) {
@@ -458,6 +453,9 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 	 * finds its CPU here.
 	 */
 	if (cpu == -1 && set) {
+		if (!zalloc_cpumask_var(&diff, GFP_KERNEL))
+			return -ENOMEM;
+
 		if (cpumask_equal(&set->mask, &set->used)) {
 			/*
 			 * We've used up all the CPUs, bump up the generation
@@ -469,6 +467,8 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 		cpumask_andnot(diff, &set->mask, &set->used);
 		cpu = cpumask_first(diff);
 		cpumask_set_cpu(cpu, &set->used);
+
+		free_cpumask_var(diff);
 	}
 
 	cpumask_set_cpu(cpu, &msix->mask);
@@ -482,7 +482,6 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 		hfi1_setup_sdma_notifier(msix);
 	}
 
-	free_cpumask_var(diff);
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index e6a60fa59f2b..e6bdd0c1e80a 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -5944,6 +5944,7 @@ static void is_sendctxt_err_int(struct hfi1_devdata *dd,
 	u64 status;
 	u32 sw_index;
 	int i = 0;
+	unsigned long irq_flags;
 
 	sw_index = dd->hw_to_sw[hw_context];
 	if (sw_index >= dd->num_send_contexts) {
@@ -5953,10 +5954,12 @@ static void is_sendctxt_err_int(struct hfi1_devdata *dd,
 		return;
 	}
 	sci = &dd->send_contexts[sw_index];
+	spin_lock_irqsave(&dd->sc_lock, irq_flags);
 	sc = sci->sc;
 	if (!sc) {
 		dd_dev_err(dd, "%s: context %u(%u): no sc?\n", __func__,
 			   sw_index, hw_context);
+		spin_unlock_irqrestore(&dd->sc_lock, irq_flags);
 		return;
 	}
 
@@ -5978,6 +5981,7 @@ static void is_sendctxt_err_int(struct hfi1_devdata *dd,
 	 */
 	if (sc->type != SC_USER)
 		queue_work(dd->pport->hfi1_wq, &sc->halt_work);
+	spin_unlock_irqrestore(&dd->sc_lock, irq_flags);
 
 	/*
 	 * Update the counters for the corresponding status bits.
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 46d1475b2154..bd837a048bf4 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -433,31 +433,43 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp)
 {
 	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct ib_other_headers *ohdr = pkt->ohdr;
 	struct ib_grh *grh = pkt->grh;
 	u32 rqpn = 0, bth1;
-	u16 pkey, rlid, dlid = ib_get_dlid(pkt->hdr);
+	u16 pkey;
+	u32 rlid, slid, dlid = 0;
 	u8 hdr_type, sc, svc_type;
 	bool is_mcast = false;
 
+	/* can be called from prescan */
 	if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
 		is_mcast = hfi1_is_16B_mcast(dlid);
 		pkey = hfi1_16B_get_pkey(pkt->hdr);
 		sc = hfi1_16B_get_sc(pkt->hdr);
+		dlid = hfi1_16B_get_dlid(pkt->hdr);
+		slid = hfi1_16B_get_slid(pkt->hdr);
 		hdr_type = HFI1_PKT_TYPE_16B;
 	} else {
 		is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
 			   (dlid != be16_to_cpu(IB_LID_PERMISSIVE));
 		pkey = ib_bth_get_pkey(ohdr);
 		sc = hfi1_9B_get_sc5(pkt->hdr, pkt->rhf);
+		dlid = ib_get_dlid(pkt->hdr);
+		slid = ib_get_slid(pkt->hdr);
 		hdr_type = HFI1_PKT_TYPE_9B;
 	}
 
 	switch (qp->ibqp.qp_type) {
+	case IB_QPT_UD:
+		dlid = ppd->lid;
+		rlid = slid;
+		rqpn = ib_get_sqpn(pkt->ohdr);
+		svc_type = IB_CC_SVCTYPE_UD;
+		break;
 	case IB_QPT_SMI:
 	case IB_QPT_GSI:
-	case IB_QPT_UD:
-		rlid = ib_get_slid(pkt->hdr);
+		rlid = slid;
 		rqpn = ib_get_sqpn(pkt->ohdr);
 		svc_type = IB_CC_SVCTYPE_UD;
 		break;
@@ -482,7 +494,6 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 					      dlid, rlid, sc, grh);
 
 	if (!is_mcast && (bth1 & IB_BECN_SMASK)) {
-		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 		u32 lqpn = bth1 & RVT_QPN_MASK;
 		u8 sl = ibp->sc_to_sl[sc];
 
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 32c48265405e..cac2c62bc42d 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1537,13 +1537,13 @@ void set_link_ipg(struct hfi1_pportdata *ppd);
 void process_becn(struct hfi1_pportdata *ppd, u8 sl, u32 rlid, u32 lqpn,
 		  u32 rqpn, u8 svc_type);
 void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
-		u32 pkey, u32 slid, u32 dlid, u8 sc5,
+		u16 pkey, u32 slid, u32 dlid, u8 sc5,
 		const struct ib_grh *old_grh);
 void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
-		    u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+		    u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
 		    u8 sc5, const struct ib_grh *old_grh);
 typedef void (*hfi1_handle_cnp)(struct hfi1_ibport *ibp, struct rvt_qp *qp,
-				u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+				u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
 				u8 sc5, const struct ib_grh *old_grh);
 
 #define PKEY_CHECK_INVALID -1
@@ -2437,7 +2437,7 @@ static inline void hfi1_make_16b_hdr(struct hfi1_16b_header *hdr,
 		((slid >> OPA_16B_SLID_SHIFT) << OPA_16B_SLID_HIGH_SHIFT);
 	lrh2 = (lrh2 & ~OPA_16B_DLID_MASK) |
 		((dlid >> OPA_16B_DLID_SHIFT) << OPA_16B_DLID_HIGH_SHIFT);
-	lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | (pkey << OPA_16B_PKEY_SHIFT);
+	lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | ((u32)pkey << OPA_16B_PKEY_SHIFT);
 	lrh2 = (lrh2 & ~OPA_16B_L4_MASK) | l4;
 
 	hdr->lrh[0] = lrh0;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 33eba2356742..6309edf811df 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -88,9 +88,9 @@
  * pio buffers per ctxt, etc.)  Zero means use one user context per CPU.
  */
 int num_user_contexts = -1;
-module_param_named(num_user_contexts, num_user_contexts, uint, S_IRUGO);
+module_param_named(num_user_contexts, num_user_contexts, int, 0444);
 MODULE_PARM_DESC(
-	num_user_contexts, "Set max number of user contexts to use");
+	num_user_contexts, "Set max number of user contexts to use (default: -1 will use the real (non-HT) CPU count)");
 
 uint krcvqs[RXE_NUM_DATA_VL];
 int krcvqsset;
@@ -1209,30 +1209,49 @@ static void finalize_asic_data(struct hfi1_devdata *dd,
 	kfree(ad);
 }
 
-static void __hfi1_free_devdata(struct kobject *kobj)
+/**
+ * hfi1_clean_devdata - cleans up per-unit data structure
+ * @dd: pointer to a valid devdata structure
+ *
+ * It cleans up all data structures set up by
+ * by hfi1_alloc_devdata().
+ */
+static void hfi1_clean_devdata(struct hfi1_devdata *dd)
 {
-	struct hfi1_devdata *dd =
-		container_of(kobj, struct hfi1_devdata, kobj);
 	struct hfi1_asic_data *ad;
 	unsigned long flags;
 
 	spin_lock_irqsave(&hfi1_devs_lock, flags);
-	idr_remove(&hfi1_unit_table, dd->unit);
-	list_del(&dd->list);
+	if (!list_empty(&dd->list)) {
+		idr_remove(&hfi1_unit_table, dd->unit);
+		list_del_init(&dd->list);
+	}
 	ad = release_asic_data(dd);
 	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
-	if (ad)
-		finalize_asic_data(dd, ad);
+
+	finalize_asic_data(dd, ad);
 	free_platform_config(dd);
 	rcu_barrier(); /* wait for rcu callbacks to complete */
 	free_percpu(dd->int_counter);
 	free_percpu(dd->rcv_limit);
 	free_percpu(dd->send_schedule);
 	free_percpu(dd->tx_opstats);
+	dd->int_counter   = NULL;
+	dd->rcv_limit     = NULL;
+	dd->send_schedule = NULL;
+	dd->tx_opstats    = NULL;
 	sdma_clean(dd, dd->num_sdma);
 	rvt_dealloc_device(&dd->verbs_dev.rdi);
 }
 
+static void __hfi1_free_devdata(struct kobject *kobj)
+{
+	struct hfi1_devdata *dd =
+		container_of(kobj, struct hfi1_devdata, kobj);
+
+	hfi1_clean_devdata(dd);
+}
+
 static struct kobj_type hfi1_devdata_type = {
 	.release = __hfi1_free_devdata,
 };
@@ -1265,6 +1284,8 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
 		return ERR_PTR(-ENOMEM);
 	dd->num_pports = nports;
 	dd->pport = (struct hfi1_pportdata *)(dd + 1);
+	dd->pcidev = pdev;
+	pci_set_drvdata(pdev, dd);
 
 	INIT_LIST_HEAD(&dd->list);
 	idr_preload(GFP_KERNEL);
@@ -1331,9 +1352,7 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
 	return dd;
 
 bail:
-	if (!list_empty(&dd->list))
-		list_del_init(&dd->list);
-	rvt_dealloc_device(&dd->verbs_dev.rdi);
+	hfi1_clean_devdata(dd);
 	return ERR_PTR(ret);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 83d66e862207..c1c982908b4b 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -163,9 +163,6 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
 	resource_size_t addr;
 	int ret = 0;
 
-	dd->pcidev = pdev;
-	pci_set_drvdata(pdev, dd);
-
 	addr = pci_resource_start(pdev, 0);
 	len = pci_resource_len(pdev, 0);
 
diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index d486355880cb..cbf7faa5038c 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -199,6 +199,7 @@ void free_platform_config(struct hfi1_devdata *dd)
 {
 	/* Release memory allocated for eprom or fallback file read. */
 	kfree(dd->platform_config.data);
+	dd->platform_config.data = NULL;
 }
 
 void get_port_type(struct hfi1_pportdata *ppd)
diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c
index 1869f639c3ae..b5966991d647 100644
--- a/drivers/infiniband/hw/hfi1/qsfp.c
+++ b/drivers/infiniband/hw/hfi1/qsfp.c
@@ -204,6 +204,8 @@ static void clean_i2c_bus(struct hfi1_i2c_bus *bus)
 
 void clean_up_i2c(struct hfi1_devdata *dd, struct hfi1_asic_data *ad)
 {
+	if (!ad)
+		return;
 	clean_i2c_bus(ad->i2c_bus0);
 	ad->i2c_bus0 = NULL;
 	clean_i2c_bus(ad->i2c_bus1);
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 3daa94bdae3a..c0071ca4147a 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -733,6 +733,20 @@ static inline void hfi1_make_ruc_bth(struct rvt_qp *qp,
 	ohdr->bth[2] = cpu_to_be32(bth2);
 }
 
+/**
+ * hfi1_make_ruc_header_16B - build a 16B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
 static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 					    struct ib_other_headers *ohdr,
 					    u32 bth0, u32 bth2, int middle,
@@ -777,6 +791,12 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 	else
 		middle = 0;
 
+	if (qp->s_flags & RVT_S_ECN) {
+		qp->s_flags &= ~RVT_S_ECN;
+		/* we recently received a FECN, so return a BECN */
+		becn = true;
+		middle = 0;
+	}
 	if (middle)
 		build_ahg(qp, bth2);
 	else
@@ -784,11 +804,6 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 
 	bth0 |= pkey;
 	bth0 |= extra_bytes << 20;
-	if (qp->s_flags & RVT_S_ECN) {
-		qp->s_flags &= ~RVT_S_ECN;
-		/* we recently received a FECN, so return a BECN */
-		becn = true;
-	}
 	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
 
 	if (!ppd->lid)
@@ -806,6 +821,20 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 			  pkey, becn, 0, l4, priv->s_sc);
 }
 
+/**
+ * hfi1_make_ruc_header_9B - build a 9B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
 static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 					   struct ib_other_headers *ohdr,
 					   u32 bth0, u32 bth2, int middle,
@@ -839,6 +868,12 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 	else
 		middle = 0;
 
+	if (qp->s_flags & RVT_S_ECN) {
+		qp->s_flags &= ~RVT_S_ECN;
+		/* we recently received a FECN, so return a BECN */
+		bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
+		middle = 0;
+	}
 	if (middle)
 		build_ahg(qp, bth2);
 	else
@@ -846,11 +881,6 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 
 	bth0 |= pkey;
 	bth0 |= extra_bytes << 20;
-	if (qp->s_flags & RVT_S_ECN) {
-		qp->s_flags &= ~RVT_S_ECN;
-		/* we recently received a FECN, so return a BECN */
-		bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
-	}
 	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
 	hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
 			 lrh0,
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index bcf3b0bebac8..69c17a5ef038 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -628,7 +628,7 @@ int hfi1_lookup_pkey_idx(struct hfi1_ibport *ibp, u16 pkey)
 }
 
 void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
-		    u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+		    u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
 		    u8 sc5, const struct ib_grh *old_grh)
 {
 	u64 pbc, pbc_flags = 0;
@@ -687,7 +687,7 @@ void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
 }
 
 void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
-		u32 pkey, u32 slid, u32 dlid, u8 sc5,
+		u16 pkey, u32 slid, u32 dlid, u8 sc5,
 		const struct ib_grh *old_grh)
 {
 	u64 pbc, pbc_flags = 0;
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index 14734d0d0b76..3a485f50fede 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -377,6 +377,7 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev,
 
 			hr_cq->set_ci_db = hr_cq->db.db_record;
 			*hr_cq->set_ci_db = 0;
+			hr_cq->db_en = 1;
 		}
 
 		/* Init mmt table and write buff address to mtt table */
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index 0eeabfbee192..63b5b3edabcb 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -912,7 +912,7 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev,
 		obj_per_chunk = buf_chunk_size / obj_size;
 		num_hem = (nobj + obj_per_chunk - 1) / obj_per_chunk;
 		bt_chunk_num = bt_chunk_size / 8;
-		if (table->type >= HEM_TYPE_MTT)
+		if (type >= HEM_TYPE_MTT)
 			num_bt_l0 = bt_chunk_num;
 
 		table->hem = kcalloc(num_hem, sizeof(*table->hem),
@@ -920,7 +920,7 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev,
 		if (!table->hem)
 			goto err_kcalloc_hem_buf;
 
-		if (check_whether_bt_num_3(table->type, hop_num)) {
+		if (check_whether_bt_num_3(type, hop_num)) {
 			unsigned long num_bt_l1;
 
 			num_bt_l1 = (num_hem + bt_chunk_num - 1) /
@@ -939,8 +939,8 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev,
 				goto err_kcalloc_l1_dma;
 		}
 
-		if (check_whether_bt_num_2(table->type, hop_num) ||
-			check_whether_bt_num_3(table->type, hop_num)) {
+		if (check_whether_bt_num_2(type, hop_num) ||
+			check_whether_bt_num_3(type, hop_num)) {
 			table->bt_l0 = kcalloc(num_bt_l0, sizeof(*table->bt_l0),
 					       GFP_KERNEL);
 			if (!table->bt_l0)
@@ -1039,14 +1039,14 @@ void hns_roce_cleanup_hem_table(struct hns_roce_dev *hr_dev,
 void hns_roce_cleanup_hem(struct hns_roce_dev *hr_dev)
 {
 	hns_roce_cleanup_hem_table(hr_dev, &hr_dev->cq_table.table);
-	hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.irrl_table);
 	if (hr_dev->caps.trrl_entry_sz)
 		hns_roce_cleanup_hem_table(hr_dev,
 					   &hr_dev->qp_table.trrl_table);
+	hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.irrl_table);
 	hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.qp_table);
 	hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtpt_table);
-	hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table);
 	if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE))
 		hns_roce_cleanup_hem_table(hr_dev,
 					   &hr_dev->mr_table.mtt_cqe_table);
+	hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table);
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 47e1b6ac1e1a..8013d69c5ac4 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -722,6 +722,7 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev)
 	free_mr->mr_free_pd = to_hr_pd(pd);
 	free_mr->mr_free_pd->ibpd.device  = &hr_dev->ib_dev;
 	free_mr->mr_free_pd->ibpd.uobject = NULL;
+	free_mr->mr_free_pd->ibpd.__internal_mr = NULL;
 	atomic_set(&free_mr->mr_free_pd->ibpd.usecnt, 0);
 
 	attr.qp_access_flags	= IB_ACCESS_REMOTE_WRITE;
@@ -1036,7 +1037,7 @@ static void hns_roce_v1_mr_free_work_fn(struct work_struct *work)
 
 	do {
 		ret = hns_roce_v1_poll_cq(&mr_free_cq->ib_cq, ne, wc);
-		if (ret < 0) {
+		if (ret < 0 && hr_qp) {
 			dev_err(dev,
 			   "(qp:0x%lx) starts, Poll cqe failed(%d) for mr 0x%x free! Remain %d cqe\n",
 			   hr_qp->qpn, ret, hr_mr->key, ne);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 8b84ab7800d8..1f0965bb64ee 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -71,6 +71,11 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			return -EINVAL;
 		}
 
+		if (wr->opcode == IB_WR_RDMA_READ) {
+			dev_err(hr_dev->dev, "Not support inline data!\n");
+			return -EINVAL;
+		}
+
 		for (i = 0; i < wr->num_sge; i++) {
 			memcpy(wqe, ((void *)wr->sg_list[i].addr),
 			       wr->sg_list[i].length);
@@ -137,8 +142,8 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	unsigned long flags;
 	unsigned int ind;
 	void *wqe = NULL;
-	u32 tmp_len = 0;
 	bool loopback;
+	u32 tmp_len;
 	int ret = 0;
 	u8 *smac;
 	int nreq;
@@ -148,7 +153,7 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		     ibqp->qp_type != IB_QPT_GSI &&
 		     ibqp->qp_type != IB_QPT_UD)) {
 		dev_err(dev, "Not supported QP(0x%x)type!\n", ibqp->qp_type);
-		*bad_wr = NULL;
+		*bad_wr = wr;
 		return -EOPNOTSUPP;
 	}
 
@@ -182,7 +187,9 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] =
 								      wr->wr_id;
 
-		owner_bit = ~(qp->sq.head >> ilog2(qp->sq.wqe_cnt)) & 0x1;
+		owner_bit =
+		       ~(((qp->sq.head + nreq) >> ilog2(qp->sq.wqe_cnt)) & 0x1);
+		tmp_len = 0;
 
 		/* Corresponding to the QP type, wqe process separately */
 		if (ibqp->qp_type == IB_QPT_GSI) {
@@ -456,6 +463,7 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		} else {
 			dev_err(dev, "Illegal qp_type(0x%x)\n", ibqp->qp_type);
 			spin_unlock_irqrestore(&qp->sq.lock, flags);
+			*bad_wr = wr;
 			return -EOPNOTSUPP;
 		}
 	}
@@ -540,16 +548,20 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 		}
 
 		if (i < hr_qp->rq.max_gs) {
-			dseg[i].lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY);
-			dseg[i].addr = 0;
+			dseg->lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY);
+			dseg->addr = 0;
 		}
 
 		/* rq support inline data */
-		sge_list = hr_qp->rq_inl_buf.wqe_list[ind].sg_list;
-		hr_qp->rq_inl_buf.wqe_list[ind].sge_cnt = (u32)wr->num_sge;
-		for (i = 0; i < wr->num_sge; i++) {
-			sge_list[i].addr = (void *)(u64)wr->sg_list[i].addr;
-			sge_list[i].len = wr->sg_list[i].length;
+		if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE) {
+			sge_list = hr_qp->rq_inl_buf.wqe_list[ind].sg_list;
+			hr_qp->rq_inl_buf.wqe_list[ind].sge_cnt =
+							       (u32)wr->num_sge;
+			for (i = 0; i < wr->num_sge; i++) {
+				sge_list[i].addr =
+					       (void *)(u64)wr->sg_list[i].addr;
+				sge_list[i].len = wr->sg_list[i].length;
+			}
 		}
 
 		hr_qp->rq.wrid[ind] = wr->wr_id;
@@ -606,6 +618,8 @@ static void hns_roce_free_cmq_desc(struct hns_roce_dev *hr_dev,
 	dma_unmap_single(hr_dev->dev, ring->desc_dma_addr,
 			 ring->desc_num * sizeof(struct hns_roce_cmq_desc),
 			 DMA_BIDIRECTIONAL);
+
+	ring->desc_dma_addr = 0;
 	kfree(ring->desc);
 }
 
@@ -1074,6 +1088,7 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
 	if (ret) {
 		dev_err(hr_dev->dev, "Configure global param fail, ret = %d.\n",
 			ret);
+		return ret;
 	}
 
 	/* Get pf resource owned by every pf */
@@ -1365,6 +1380,8 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
 
 	roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S,
 		     mr->type == MR_TYPE_MR ? 0 : 1);
+	roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_INNER_PA_VLD_S,
+		     1);
 	mpt_entry->byte_12_mw_pa = cpu_to_le32(mpt_entry->byte_12_mw_pa);
 
 	mpt_entry->len_l = cpu_to_le32(lower_32_bits(mr->size));
@@ -2162,6 +2179,7 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp,
 				    struct hns_roce_v2_qp_context *context,
 				    struct hns_roce_v2_qp_context *qpc_mask)
 {
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
 
 	/*
@@ -2274,7 +2292,8 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp,
 	context->rq_db_record_addr = hr_qp->rdb.dma >> 32;
 	qpc_mask->rq_db_record_addr = 0;
 
-	roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RQIE_S, 1);
+	roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RQIE_S,
+		    (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE) ? 1 : 0);
 	roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RQIE_S, 0);
 
 	roce_set_field(context->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M,
@@ -2592,10 +2611,12 @@ static void modify_qp_init_to_init(struct ib_qp *ibqp,
 	roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_SQPN_M,
 		       V2_QPC_BYTE_4_SQPN_S, 0);
 
-	roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
-		       V2_QPC_BYTE_56_DQPN_S, hr_qp->qpn);
-	roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
-		       V2_QPC_BYTE_56_DQPN_S, 0);
+	if (attr_mask & IB_QP_DEST_QPN) {
+		roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
+			       V2_QPC_BYTE_56_DQPN_S, hr_qp->qpn);
+		roce_set_field(qpc_mask->byte_56_dqpn_err,
+			       V2_QPC_BYTE_56_DQPN_M, V2_QPC_BYTE_56_DQPN_S, 0);
+	}
 	roce_set_field(context->byte_168_irrl_idx,
 		       V2_QPC_BYTE_168_SQ_SHIFT_BAK_M,
 		       V2_QPC_BYTE_168_SQ_SHIFT_BAK_S,
@@ -2650,8 +2671,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 		return -EINVAL;
 	}
 
-	if ((attr_mask & IB_QP_ALT_PATH) || (attr_mask & IB_QP_ACCESS_FLAGS) ||
-	    (attr_mask & IB_QP_PKEY_INDEX) || (attr_mask & IB_QP_QKEY)) {
+	if (attr_mask & IB_QP_ALT_PATH) {
 		dev_err(dev, "INIT2RTR attr_mask (0x%x) error\n", attr_mask);
 		return -EINVAL;
 	}
@@ -2800,10 +2820,12 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 			       V2_QPC_BYTE_140_RR_MAX_S, 0);
 	}
 
-	roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
-		       V2_QPC_BYTE_56_DQPN_S, attr->dest_qp_num);
-	roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
-		       V2_QPC_BYTE_56_DQPN_S, 0);
+	if (attr_mask & IB_QP_DEST_QPN) {
+		roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
+			       V2_QPC_BYTE_56_DQPN_S, attr->dest_qp_num);
+		roce_set_field(qpc_mask->byte_56_dqpn_err,
+			       V2_QPC_BYTE_56_DQPN_M, V2_QPC_BYTE_56_DQPN_S, 0);
+	}
 
 	/* Configure GID index */
 	port_num = rdma_ah_get_port_num(&attr->ah_attr);
@@ -2845,7 +2867,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 	if (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_UD)
 		roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M,
 			       V2_QPC_BYTE_24_MTU_S, IB_MTU_4096);
-	else
+	else if (attr_mask & IB_QP_PATH_MTU)
 		roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M,
 			       V2_QPC_BYTE_24_MTU_S, attr->path_mtu);
 
@@ -2922,11 +2944,9 @@ static int modify_qp_rtr_to_rts(struct ib_qp *ibqp,
 		return -EINVAL;
 	}
 
-	/* If exist optional param, return error */
-	if ((attr_mask & IB_QP_ALT_PATH) || (attr_mask & IB_QP_ACCESS_FLAGS) ||
-	    (attr_mask & IB_QP_QKEY) || (attr_mask & IB_QP_PATH_MIG_STATE) ||
-	    (attr_mask & IB_QP_CUR_STATE) ||
-	    (attr_mask & IB_QP_MIN_RNR_TIMER)) {
+	/* Not support alternate path and path migration */
+	if ((attr_mask & IB_QP_ALT_PATH) ||
+	    (attr_mask & IB_QP_PATH_MIG_STATE)) {
 		dev_err(dev, "RTR2RTS attr_mask (0x%x)error\n", attr_mask);
 		return -EINVAL;
 	}
@@ -3161,7 +3181,8 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 		   (cur_state == IB_QPS_RTR && new_state == IB_QPS_ERR) ||
 		   (cur_state == IB_QPS_RTS && new_state == IB_QPS_ERR) ||
 		   (cur_state == IB_QPS_SQD && new_state == IB_QPS_ERR) ||
-		   (cur_state == IB_QPS_SQE && new_state == IB_QPS_ERR)) {
+		   (cur_state == IB_QPS_SQE && new_state == IB_QPS_ERR) ||
+		   (cur_state == IB_QPS_ERR && new_state == IB_QPS_ERR)) {
 		/* Nothing */
 		;
 	} else {
@@ -4478,7 +4499,7 @@ static int hns_roce_v2_create_eq(struct hns_roce_dev *hr_dev,
 	ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, eq->eqn, 0,
 				eq_cmd, HNS_ROCE_CMD_TIMEOUT_MSECS);
 	if (ret) {
-		dev_err(dev, "[mailbox cmd] creat eqc failed.\n");
+		dev_err(dev, "[mailbox cmd] create eqc failed.\n");
 		goto err_cmd_mbox;
 	}
 
@@ -4694,6 +4715,8 @@ static const struct pci_device_id hns_roce_hw_v2_pci_tbl[] = {
 	{0, }
 };
 
+MODULE_DEVICE_TABLE(pci, hns_roce_hw_v2_pci_tbl);
+
 static int hns_roce_hw_v2_get_cfg(struct hns_roce_dev *hr_dev,
 				  struct hnae3_handle *handle)
 {
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 9d48bc07a9e6..96fb6a9ed93c 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -199,7 +199,7 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
 
 	memset(props, 0, sizeof(*props));
 
-	props->sys_image_guid = cpu_to_be32(hr_dev->sys_image_guid);
+	props->sys_image_guid = cpu_to_be64(hr_dev->sys_image_guid);
 	props->max_mr_size = (u64)(~(0ULL));
 	props->page_size_cap = hr_dev->caps.page_size_cap;
 	props->vendor_id = hr_dev->vendor_id;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index e289a924e789..baaf906f7c2e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -620,7 +620,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
 					to_hr_ucontext(ib_pd->uobject->context),
 					ucmd.db_addr, &hr_qp->rdb);
 			if (ret) {
-				dev_err(dev, "rp record doorbell map failed!\n");
+				dev_err(dev, "rq record doorbell map failed!\n");
 				goto err_mtt;
 			}
 		}
@@ -660,6 +660,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
 				goto err_rq_sge_list;
 			}
 			*hr_qp->rdb.db_record = 0;
+			hr_qp->rdb_en = 1;
 		}
 
 		/* Allocate QP buf */
@@ -955,7 +956,14 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	}
 
 	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
-		ret = 0;
+		if (hr_dev->caps.min_wqes) {
+			ret = -EPERM;
+			dev_err(dev, "cur_state=%d new_state=%d\n", cur_state,
+				new_state);
+		} else {
+			ret = 0;
+		}
+
 		goto out;
 	}
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index d5d8c1be345a..2f2b4426ded7 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -207,6 +207,7 @@ struct i40iw_msix_vector {
 	u32 irq;
 	u32 cpu_affinity;
 	u32 ceq_id;
+	cpumask_t mask;
 };
 
 struct l2params_work {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 4cfa8f4647e2..f7c6fd9ff6e2 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -2093,7 +2093,7 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev,
 	if (netif_is_bond_slave(netdev))
 		netdev = netdev_master_upper_dev_get(netdev);
 
-	neigh = dst_neigh_lookup(dst, &dst_addr);
+	neigh = dst_neigh_lookup(dst, dst_addr.sin6_addr.in6_u.u6_addr32);
 
 	rcu_read_lock();
 	if (neigh) {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c
index 6139836fb533..c9f62ca7643c 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_hw.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c
@@ -331,7 +331,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
 		switch (info->ae_id) {
 		case I40IW_AE_LLP_FIN_RECEIVED:
 			if (qp->term_flags)
-				continue;
+				break;
 			if (atomic_inc_return(&iwqp->close_timer_started) == 1) {
 				iwqp->hw_tcp_state = I40IW_TCP_STATE_CLOSE_WAIT;
 				if ((iwqp->hw_tcp_state == I40IW_TCP_STATE_CLOSE_WAIT) &&
@@ -360,7 +360,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
 			break;
 		case I40IW_AE_LLP_CONNECTION_RESET:
 			if (atomic_read(&iwqp->close_timer_started))
-				continue;
+				break;
 			i40iw_cm_disconn(iwqp);
 			break;
 		case I40IW_AE_QP_SUSPEND_COMPLETE:
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index 9cd0d3ef9057..05001e6da1f8 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -687,7 +687,6 @@ static enum i40iw_status_code i40iw_configure_ceq_vector(struct i40iw_device *iw
 							 struct i40iw_msix_vector *msix_vec)
 {
 	enum i40iw_status_code status;
-	cpumask_t mask;
 
 	if (iwdev->msix_shared && !ceq_id) {
 		tasklet_init(&iwdev->dpc_tasklet, i40iw_dpc, (unsigned long)iwdev);
@@ -697,9 +696,9 @@ static enum i40iw_status_code i40iw_configure_ceq_vector(struct i40iw_device *iw
 		status = request_irq(msix_vec->irq, i40iw_ceq_handler, 0, "CEQ", iwceq);
 	}
 
-	cpumask_clear(&mask);
-	cpumask_set_cpu(msix_vec->cpu_affinity, &mask);
-	irq_set_affinity_hint(msix_vec->irq, &mask);
+	cpumask_clear(&msix_vec->mask);
+	cpumask_set_cpu(msix_vec->cpu_affinity, &msix_vec->mask);
+	irq_set_affinity_hint(msix_vec->irq, &msix_vec->mask);
 
 	if (status) {
 		i40iw_pr_err("ceq irq config fail\n");
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 40e4f5ab2b46..68679ad4c6da 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -394,6 +394,7 @@ static struct i40iw_pbl *i40iw_get_pbl(unsigned long va,
 
 	list_for_each_entry(iwpbl, pbl_list, list) {
 		if (iwpbl->user_base == va) {
+			iwpbl->on_list = false;
 			list_del(&iwpbl->list);
 			return iwpbl;
 		}
@@ -614,6 +615,7 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd,
 		return ERR_PTR(-ENOMEM);
 
 	iwqp = (struct i40iw_qp *)mem;
+	iwqp->allocated_buffer = mem;
 	qp = &iwqp->sc_qp;
 	qp->back_qp = (void *)iwqp;
 	qp->push_idx = I40IW_INVALID_PUSH_PAGE_INDEX;
@@ -642,7 +644,6 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd,
 		goto error;
 	}
 
-	iwqp->allocated_buffer = mem;
 	iwqp->iwdev = iwdev;
 	iwqp->iwpd = iwpd;
 	iwqp->ibqp.qp_num = qp_num;
@@ -1898,6 +1899,7 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
 			goto error;
 		spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags);
 		list_add_tail(&iwpbl->list, &ucontext->qp_reg_mem_list);
+		iwpbl->on_list = true;
 		spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags);
 		break;
 	case IW_MEMREG_TYPE_CQ:
@@ -1908,6 +1910,7 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
 
 		spin_lock_irqsave(&ucontext->cq_reg_mem_list_lock, flags);
 		list_add_tail(&iwpbl->list, &ucontext->cq_reg_mem_list);
+		iwpbl->on_list = true;
 		spin_unlock_irqrestore(&ucontext->cq_reg_mem_list_lock, flags);
 		break;
 	case IW_MEMREG_TYPE_MEM:
@@ -2045,14 +2048,18 @@ static void i40iw_del_memlist(struct i40iw_mr *iwmr,
 	switch (iwmr->type) {
 	case IW_MEMREG_TYPE_CQ:
 		spin_lock_irqsave(&ucontext->cq_reg_mem_list_lock, flags);
-		if (!list_empty(&ucontext->cq_reg_mem_list))
+		if (iwpbl->on_list) {
+			iwpbl->on_list = false;
 			list_del(&iwpbl->list);
+		}
 		spin_unlock_irqrestore(&ucontext->cq_reg_mem_list_lock, flags);
 		break;
 	case IW_MEMREG_TYPE_QP:
 		spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags);
-		if (!list_empty(&ucontext->qp_reg_mem_list))
+		if (iwpbl->on_list) {
+			iwpbl->on_list = false;
 			list_del(&iwpbl->list);
+		}
 		spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags);
 		break;
 	default:
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.h b/drivers/infiniband/hw/i40iw/i40iw_verbs.h
index 9067443cd311..76cf173377ab 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.h
@@ -78,6 +78,7 @@ struct i40iw_pbl {
 	};
 
 	bool pbl_allocated;
+	bool on_list;
 	u64 user_base;
 	struct i40iw_pble_alloc pble_alloc;
 	struct i40iw_mr *iwmr;
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 17f4f151a97f..61d8b06375bb 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -346,7 +346,7 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
 	/* Add to the first block the misalignment that it suffers from. */
 	total_len += (first_block_start & ((1ULL << block_shift) - 1ULL));
 	last_block_end = current_block_start + current_block_len;
-	last_block_aligned_end = round_up(last_block_end, 1 << block_shift);
+	last_block_aligned_end = round_up(last_block_end, 1ULL << block_shift);
 	total_len += (last_block_aligned_end - last_block_end);
 
 	if (total_len & ((1ULL << block_shift) - 1ULL))
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 50af8915e7ec..199648adac74 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -673,7 +673,8 @@ static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx,
 					  MLX4_IB_RX_HASH_SRC_PORT_TCP	|
 					  MLX4_IB_RX_HASH_DST_PORT_TCP	|
 					  MLX4_IB_RX_HASH_SRC_PORT_UDP	|
-					  MLX4_IB_RX_HASH_DST_PORT_UDP)) {
+					  MLX4_IB_RX_HASH_DST_PORT_UDP  |
+					  MLX4_IB_RX_HASH_INNER)) {
 		pr_debug("RX Hash fields_mask has unsupported mask (0x%llx)\n",
 			 ucmd->rx_hash_fields_mask);
 		return (-EOPNOTSUPP);
diff --git a/drivers/infiniband/hw/mlx5/Kconfig b/drivers/infiniband/hw/mlx5/Kconfig
index bce263b92821..fb4d77be019b 100644
--- a/drivers/infiniband/hw/mlx5/Kconfig
+++ b/drivers/infiniband/hw/mlx5/Kconfig
@@ -1,6 +1,7 @@
 config MLX5_INFINIBAND
 	tristate "Mellanox Connect-IB HCA support"
 	depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+	depends on INFINIBAND_USER_ACCESS || INFINIBAND_USER_ACCESS=n
 	---help---
 	  This driver provides low-level InfiniBand support for
 	  Mellanox Connect-IB PCI Express host channel adapters (HCAs).
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index daa919e5a442..69716a7ea993 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -52,7 +52,6 @@
 #include <linux/mlx5/port.h>
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
-#include <linux/mlx5/fs_helpers.h>
 #include <linux/list.h>
 #include <rdma/ib_smi.h>
 #include <rdma/ib_umem.h>
@@ -180,7 +179,7 @@ static int mlx5_netdev_event(struct notifier_block *this,
 			if (rep_ndev == ndev)
 				roce->netdev = (event == NETDEV_UNREGISTER) ?
 					NULL : ndev;
-		} else if (ndev->dev.parent == &ibdev->mdev->pdev->dev) {
+		} else if (ndev->dev.parent == &mdev->pdev->dev) {
 			roce->netdev = (event == NETDEV_UNREGISTER) ?
 				NULL : ndev;
 		}
@@ -2417,7 +2416,7 @@ static void set_proto(void *outer_c, void *outer_v, u8 mask, u8 val)
 	MLX5_SET(fte_match_set_lyr_2_4, outer_v, ip_protocol, val);
 }
 
-static void set_flow_label(void *misc_c, void *misc_v, u8 mask, u8 val,
+static void set_flow_label(void *misc_c, void *misc_v, u32 mask, u32 val,
 			   bool inner)
 {
 	if (inner) {
@@ -4757,7 +4756,7 @@ mlx5_ib_get_vector_affinity(struct ib_device *ibdev, int comp_vector)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 
-	return mlx5_get_vector_affinity(dev->mdev, comp_vector);
+	return mlx5_get_vector_affinity_hint(dev->mdev, comp_vector);
 }
 
 /* The mlx5_ib_multiport_mutex should be held when calling this function */
@@ -5427,9 +5426,7 @@ static void mlx5_ib_stage_cong_debugfs_cleanup(struct mlx5_ib_dev *dev)
 static int mlx5_ib_stage_uar_init(struct mlx5_ib_dev *dev)
 {
 	dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev);
-	if (!dev->mdev->priv.uar)
-		return -ENOMEM;
-	return 0;
+	return PTR_ERR_OR_ZERO(dev->mdev->priv.uar);
 }
 
 static void mlx5_ib_stage_uar_cleanup(struct mlx5_ib_dev *dev)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 1520a2f20f98..90a9c461cedc 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -866,25 +866,28 @@ static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length,
 		       int *order)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct ib_umem *u;
 	int err;
 
-	*umem = ib_umem_get(pd->uobject->context, start, length,
-			    access_flags, 0);
-	err = PTR_ERR_OR_ZERO(*umem);
+	*umem = NULL;
+
+	u = ib_umem_get(pd->uobject->context, start, length, access_flags, 0);
+	err = PTR_ERR_OR_ZERO(u);
 	if (err) {
-		*umem = NULL;
-		mlx5_ib_err(dev, "umem get failed (%d)\n", err);
+		mlx5_ib_dbg(dev, "umem get failed (%d)\n", err);
 		return err;
 	}
 
-	mlx5_ib_cont_pages(*umem, start, MLX5_MKEY_PAGE_SHIFT_MASK, npages,
+	mlx5_ib_cont_pages(u, start, MLX5_MKEY_PAGE_SHIFT_MASK, npages,
 			   page_shift, ncont, order);
 	if (!*npages) {
 		mlx5_ib_warn(dev, "avoid zero region\n");
-		ib_umem_release(*umem);
+		ib_umem_release(u);
 		return -EINVAL;
 	}
 
+	*umem = u;
+
 	mlx5_ib_dbg(dev, "npages %d, ncont %d, order %d, page_shift %d\n",
 		    *npages, *ncont, *order, *page_shift);
 
@@ -1458,13 +1461,12 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 	int access_flags = flags & IB_MR_REREG_ACCESS ?
 			    new_access_flags :
 			    mr->access_flags;
-	u64 addr = (flags & IB_MR_REREG_TRANS) ? virt_addr : mr->umem->address;
-	u64 len = (flags & IB_MR_REREG_TRANS) ? length : mr->umem->length;
 	int page_shift = 0;
 	int upd_flags = 0;
 	int npages = 0;
 	int ncont = 0;
 	int order = 0;
+	u64 addr, len;
 	int err;
 
 	mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n",
@@ -1472,6 +1474,17 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 
 	atomic_sub(mr->npages, &dev->mdev->priv.reg_pages);
 
+	if (!mr->umem)
+		return -EINVAL;
+
+	if (flags & IB_MR_REREG_TRANS) {
+		addr = virt_addr;
+		len = length;
+	} else {
+		addr = mr->umem->address;
+		len = mr->umem->length;
+	}
+
 	if (flags != IB_MR_REREG_PD) {
 		/*
 		 * Replace umem. This needs to be done whether or not UMR is
@@ -1479,6 +1492,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		 */
 		flags |= IB_MR_REREG_TRANS;
 		ib_umem_release(mr->umem);
+		mr->umem = NULL;
 		err = mr_umem_get(pd, addr, len, access_flags, &mr->umem,
 				  &npages, &page_shift, &ncont, &order);
 		if (err)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7ed4b70f6447..2193dc1765fb 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -259,7 +259,11 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 	} else {
 		if (ucmd) {
 			qp->rq.wqe_cnt = ucmd->rq_wqe_count;
+			if (ucmd->rq_wqe_shift > BITS_PER_BYTE * sizeof(ucmd->rq_wqe_shift))
+				return -EINVAL;
 			qp->rq.wqe_shift = ucmd->rq_wqe_shift;
+			if ((1 << qp->rq.wqe_shift) / sizeof(struct mlx5_wqe_data_seg) < qp->wq_sig)
+				return -EINVAL;
 			qp->rq.max_gs = (1 << qp->rq.wqe_shift) / sizeof(struct mlx5_wqe_data_seg) - qp->wq_sig;
 			qp->rq.max_post = qp->rq.wqe_cnt;
 		} else {
@@ -480,11 +484,6 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
 	return 1;
 }
 
-static int first_med_bfreg(void)
-{
-	return 1;
-}
-
 enum {
 	/* this is the first blue flame register in the array of bfregs assigned
 	 * to a processes. Since we do not use it for blue flame but rather
@@ -510,6 +509,12 @@ static int num_med_bfreg(struct mlx5_ib_dev *dev,
 	return n >= 0 ? n : 0;
 }
 
+static int first_med_bfreg(struct mlx5_ib_dev *dev,
+			   struct mlx5_bfreg_info *bfregi)
+{
+	return num_med_bfreg(dev, bfregi) ? 1 : -ENOMEM;
+}
+
 static int first_hi_bfreg(struct mlx5_ib_dev *dev,
 			  struct mlx5_bfreg_info *bfregi)
 {
@@ -537,10 +542,13 @@ static int alloc_high_class_bfreg(struct mlx5_ib_dev *dev,
 static int alloc_med_class_bfreg(struct mlx5_ib_dev *dev,
 				 struct mlx5_bfreg_info *bfregi)
 {
-	int minidx = first_med_bfreg();
+	int minidx = first_med_bfreg(dev, bfregi);
 	int i;
 
-	for (i = first_med_bfreg(); i < first_hi_bfreg(dev, bfregi); i++) {
+	if (minidx < 0)
+		return minidx;
+
+	for (i = minidx; i < first_hi_bfreg(dev, bfregi); i++) {
 		if (bfregi->count[i] < bfregi->count[minidx])
 			minidx = i;
 		if (!bfregi->count[minidx])
@@ -2451,18 +2459,18 @@ enum {
 
 static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
 {
-	if (rate == IB_RATE_PORT_CURRENT) {
+	if (rate == IB_RATE_PORT_CURRENT)
 		return 0;
-	} else if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS) {
+
+	if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS)
 		return -EINVAL;
-	} else {
-		while (rate != IB_RATE_2_5_GBPS &&
-		       !(1 << (rate + MLX5_STAT_RATE_OFFSET) &
-			 MLX5_CAP_GEN(dev->mdev, stat_rate_support)))
-			--rate;
-	}
 
-	return rate + MLX5_STAT_RATE_OFFSET;
+	while (rate != IB_RATE_PORT_CURRENT &&
+	       !(1 << (rate + MLX5_STAT_RATE_OFFSET) &
+		 MLX5_CAP_GEN(dev->mdev, stat_rate_support)))
+		--rate;
+
+	return rate ? rate + MLX5_STAT_RATE_OFFSET : rate;
 }
 
 static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev,
diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c
index 0a75164cedea..007d5e8a0121 100644
--- a/drivers/infiniband/hw/nes/nes_nic.c
+++ b/drivers/infiniband/hw/nes/nes_nic.c
@@ -461,7 +461,7 @@ static bool nes_nic_send(struct sk_buff *skb, struct net_device *netdev)
 /**
  * nes_netdev_start_xmit
  */
-static int nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct nes_vnic *nesvnic = netdev_priv(netdev);
 	struct nes_device *nesdev = nesvnic->nesdev;
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 7d3763b2e01c..3f9afc02d166 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -401,49 +401,47 @@ int qedr_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 {
 	struct qedr_ucontext *ucontext = get_qedr_ucontext(context);
 	struct qedr_dev *dev = get_qedr_dev(context->device);
-	unsigned long vm_page = vma->vm_pgoff << PAGE_SHIFT;
-	u64 unmapped_db = dev->db_phys_addr;
+	unsigned long phys_addr = vma->vm_pgoff << PAGE_SHIFT;
 	unsigned long len = (vma->vm_end - vma->vm_start);
-	int rc = 0;
-	bool found;
+	unsigned long dpi_start;
+
+	dpi_start = dev->db_phys_addr + (ucontext->dpi * ucontext->dpi_size);
 
 	DP_DEBUG(dev, QEDR_MSG_INIT,
-		 "qedr_mmap called vm_page=0x%lx vm_pgoff=0x%lx unmapped_db=0x%llx db_size=%x, len=%lx\n",
-		 vm_page, vma->vm_pgoff, unmapped_db, dev->db_size, len);
-	if (vma->vm_start & (PAGE_SIZE - 1)) {
-		DP_ERR(dev, "Vma_start not page aligned = %ld\n",
-		       vma->vm_start);
+		 "mmap invoked with vm_start=0x%pK, vm_end=0x%pK,vm_pgoff=0x%pK; dpi_start=0x%pK dpi_size=0x%x\n",
+		 (void *)vma->vm_start, (void *)vma->vm_end,
+		 (void *)vma->vm_pgoff, (void *)dpi_start, ucontext->dpi_size);
+
+	if ((vma->vm_start & (PAGE_SIZE - 1)) || (len & (PAGE_SIZE - 1))) {
+		DP_ERR(dev,
+		       "failed mmap, adrresses must be page aligned: start=0x%pK, end=0x%pK\n",
+		       (void *)vma->vm_start, (void *)vma->vm_end);
 		return -EINVAL;
 	}
 
-	found = qedr_search_mmap(ucontext, vm_page, len);
-	if (!found) {
-		DP_ERR(dev, "Vma_pgoff not found in mapped array = %ld\n",
+	if (!qedr_search_mmap(ucontext, phys_addr, len)) {
+		DP_ERR(dev, "failed mmap, vm_pgoff=0x%lx is not authorized\n",
 		       vma->vm_pgoff);
 		return -EINVAL;
 	}
 
-	DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping doorbell bar\n");
-
-	if ((vm_page >= unmapped_db) && (vm_page <= (unmapped_db +
-						     dev->db_size))) {
-		DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping doorbell bar\n");
-		if (vma->vm_flags & VM_READ) {
-			DP_ERR(dev, "Trying to map doorbell bar for read\n");
-			return -EPERM;
-		}
-
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	if (phys_addr < dpi_start ||
+	    ((phys_addr + len) > (dpi_start + ucontext->dpi_size))) {
+		DP_ERR(dev,
+		       "failed mmap, pages are outside of dpi; page address=0x%pK, dpi_start=0x%pK, dpi_size=0x%x\n",
+		       (void *)phys_addr, (void *)dpi_start,
+		       ucontext->dpi_size);
+		return -EINVAL;
+	}
 
-		rc = io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-					PAGE_SIZE, vma->vm_page_prot);
-	} else {
-		DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping chains\n");
-		rc = remap_pfn_range(vma, vma->vm_start,
-				     vma->vm_pgoff, len, vma->vm_page_prot);
+	if (vma->vm_flags & VM_READ) {
+		DP_ERR(dev, "failed mmap, cannot map doorbell bar for read\n");
+		return -EINVAL;
 	}
-	DP_DEBUG(dev, QEDR_MSG_INIT, "qedr_mmap return code: %d\n", rc);
-	return rc;
+
+	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, len,
+				  vma->vm_page_prot);
 }
 
 struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
diff --git a/drivers/infiniband/sw/rxe/rxe_opcode.c b/drivers/infiniband/sw/rxe/rxe_opcode.c
index 61927c165b59..4cf11063e0b5 100644
--- a/drivers/infiniband/sw/rxe/rxe_opcode.c
+++ b/drivers/infiniband/sw/rxe/rxe_opcode.c
@@ -390,7 +390,7 @@ struct rxe_opcode_info rxe_opcode[RXE_NUM_OPCODE] = {
 		.name	= "IB_OPCODE_RC_SEND_ONLY_INV",
 		.mask	= RXE_IETH_MASK | RXE_PAYLOAD_MASK | RXE_REQ_MASK
 				| RXE_COMP_MASK | RXE_RWR_MASK | RXE_SEND_MASK
-				| RXE_END_MASK,
+				| RXE_END_MASK  | RXE_START_MASK,
 		.length = RXE_BTH_BYTES + RXE_IETH_BYTES,
 		.offset = {
 			[RXE_BTH]	= 0,
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 7bdaf71b8221..785199990457 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -728,7 +728,6 @@ next_wqe:
 		rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
 
 		if (ret == -EAGAIN) {
-			kfree_skb(skb);
 			rxe_run_task(&qp->req.task, 1);
 			goto exit;
 		}
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index a65c9969f7fc..955ff3b6da9c 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -742,7 +742,6 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 	err = rxe_xmit_packet(rxe, qp, &ack_pkt, skb);
 	if (err) {
 		pr_err("Failed sending RDMA reply.\n");
-		kfree_skb(skb);
 		return RESPST_ERR_RNR;
 	}
 
@@ -954,10 +953,8 @@ static int send_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
 	}
 
 	err = rxe_xmit_packet(rxe, qp, &ack_pkt, skb);
-	if (err) {
+	if (err)
 		pr_err_ratelimited("Failed sending ack\n");
-		kfree_skb(skb);
-	}
 
 err1:
 	return err;
@@ -1141,7 +1138,6 @@ static enum resp_states duplicate_request(struct rxe_qp *qp,
 			if (rc) {
 				pr_err("Failed resending result. This flow is not handled - skb ignored\n");
 				rxe_drop_ref(qp);
-				kfree_skb(skb_copy);
 				rc = RESPST_CLEANUP;
 				goto out;
 			}
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 2cb52fd48cf1..73a00a1c06f6 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -761,7 +761,6 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, struct ib_send_wr *wr,
 	unsigned int mask;
 	unsigned int length = 0;
 	int i;
-	int must_sched;
 
 	while (wr) {
 		mask = wr_opcode_mask(wr->opcode, qp);
@@ -791,14 +790,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, struct ib_send_wr *wr,
 		wr = wr->next;
 	}
 
-	/*
-	 * Must sched in case of GSI QP because ib_send_mad() hold irq lock,
-	 * and the requester call ip_local_out_sk() that takes spin_lock_bh.
-	 */
-	must_sched = (qp_type(qp) == IB_QPT_GSI) ||
-			(queue_count(qp->sq.queue) > 1);
-
-	rxe_run_task(&qp->req.task, must_sched);
+	rxe_run_task(&qp->req.task, 1);
 	if (unlikely(qp->req.state == QP_STATE_ERROR))
 		rxe_run_task(&qp->comp.task, 1);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 161ba8c76285..cf291f90b58f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1094,7 +1094,7 @@ drop_and_unlock:
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
-static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 	struct rdma_netdev *rn = netdev_priv(dev);
diff --git a/drivers/infiniband/ulp/srp/Kconfig b/drivers/infiniband/ulp/srp/Kconfig
index c74ee9633041..99db8fe5173a 100644
--- a/drivers/infiniband/ulp/srp/Kconfig
+++ b/drivers/infiniband/ulp/srp/Kconfig
@@ -1,6 +1,6 @@
 config INFINIBAND_SRP
 	tristate "InfiniBand SCSI RDMA Protocol"
-	depends on SCSI
+	depends on SCSI && INFINIBAND_ADDR_TRANS
 	select SCSI_SRP_ATTRS
 	---help---
 	  Support for the SCSI RDMA Protocol over InfiniBand.  This
diff --git a/drivers/infiniband/ulp/srpt/Kconfig b/drivers/infiniband/ulp/srpt/Kconfig
index 31ee83d528d9..fb8b7182f05e 100644
--- a/drivers/infiniband/ulp/srpt/Kconfig
+++ b/drivers/infiniband/ulp/srpt/Kconfig
@@ -1,6 +1,6 @@
 config INFINIBAND_SRPT
 	tristate "InfiniBand SCSI RDMA Protocol target support"
-	depends on INFINIBAND && TARGET_CORE
+	depends on INFINIBAND && INFINIBAND_ADDR_TRANS && TARGET_CORE
 	---help---
 
 	  Support for the SCSI RDMA Protocol (SRP) Target driver. The
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index 46115a392098..c81c79d01d93 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -31,6 +31,7 @@
 enum evdev_clock_type {
 	EV_CLK_REAL = 0,
 	EV_CLK_MONO,
+	EV_CLK_BOOT,
 	EV_CLK_MAX
 };
 
@@ -197,10 +198,12 @@ static int evdev_set_clk_type(struct evdev_client *client, unsigned int clkid)
 	case CLOCK_REALTIME:
 		clk_type = EV_CLK_REAL;
 		break;
-	case CLOCK_BOOTTIME:
 	case CLOCK_MONOTONIC:
 		clk_type = EV_CLK_MONO;
 		break;
+	case CLOCK_BOOTTIME:
+		clk_type = EV_CLK_BOOT;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -311,6 +314,8 @@ static void evdev_events(struct input_handle *handle,
 
 	ev_time[EV_CLK_MONO] = ktime_get();
 	ev_time[EV_CLK_REAL] = ktime_mono_to_real(ev_time[EV_CLK_MONO]);
+	ev_time[EV_CLK_BOOT] = ktime_mono_to_any(ev_time[EV_CLK_MONO],
+						 TK_OFFS_BOOT);
 
 	rcu_read_lock();
 
diff --git a/drivers/input/input-leds.c b/drivers/input/input-leds.c
index 766bf2660116..5f04b2d94635 100644
--- a/drivers/input/input-leds.c
+++ b/drivers/input/input-leds.c
@@ -88,6 +88,7 @@ static int input_leds_connect(struct input_handler *handler,
 			      const struct input_device_id *id)
 {
 	struct input_leds *leds;
+	struct input_led *led;
 	unsigned int num_leds;
 	unsigned int led_code;
 	int led_no;
@@ -119,14 +120,13 @@ static int input_leds_connect(struct input_handler *handler,
 
 	led_no = 0;
 	for_each_set_bit(led_code, dev->ledbit, LED_CNT) {
-		struct input_led *led = &leds->leds[led_no];
+		if (!input_led_info[led_code].name)
+			continue;
 
+		led = &leds->leds[led_no];
 		led->handle = &leds->handle;
 		led->code = led_code;
 
-		if (!input_led_info[led_code].name)
-			continue;
-
 		led->cdev.name = kasprintf(GFP_KERNEL, "%s::%s",
 					   dev_name(&dev->dev),
 					   input_led_info[led_code].name);
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 9785546420a7..6365c1958264 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1943,8 +1943,7 @@ void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int
 		break;
 
 	default:
-		pr_err("input_set_capability: unknown type %u (code %u)\n",
-		       type, code);
+		pr_err("%s: unknown type %u (code %u)\n", __func__, type, code);
 		dump_stack();
 		return;
 	}
diff --git a/drivers/input/joystick/as5011.c b/drivers/input/joystick/as5011.c
index 005d852a06e9..f051993c568e 100644
--- a/drivers/input/joystick/as5011.c
+++ b/drivers/input/joystick/as5011.c
@@ -269,9 +269,7 @@ static int as5011_probe(struct i2c_client *client,
 	input_dev->id.bustype = BUS_I2C;
 	input_dev->dev.parent = &client->dev;
 
-	__set_bit(EV_KEY, input_dev->evbit);
-	__set_bit(EV_ABS, input_dev->evbit);
-	__set_bit(BTN_JOYSTICK, input_dev->keybit);
+	input_set_capability(input_dev, EV_KEY, BTN_JOYSTICK);
 
 	input_set_abs_params(input_dev, ABS_X,
 		AS5011_MIN_AXIS, AS5011_MAX_AXIS, AS5011_FUZZ, AS5011_FLAT);
diff --git a/drivers/input/joystick/gamecon.c b/drivers/input/joystick/gamecon.c
index 2ffb2e8bdc3b..4e10ffdf8a36 100644
--- a/drivers/input/joystick/gamecon.c
+++ b/drivers/input/joystick/gamecon.c
@@ -862,7 +862,7 @@ static int gc_setup_pad(struct gc *gc, int idx, int pad_type)
 
 	case GC_N64:
 		for (i = 0; i < 10; i++)
-			__set_bit(gc_n64_btn[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY, gc_n64_btn[i]);
 
 		for (i = 0; i < 2; i++) {
 			input_set_abs_params(input_dev, ABS_X + i, -127, 126, 0, 2);
@@ -879,26 +879,27 @@ static int gc_setup_pad(struct gc *gc, int idx, int pad_type)
 		break;
 
 	case GC_SNESMOUSE:
-		__set_bit(BTN_LEFT, input_dev->keybit);
-		__set_bit(BTN_RIGHT, input_dev->keybit);
-		__set_bit(REL_X, input_dev->relbit);
-		__set_bit(REL_Y, input_dev->relbit);
+		input_set_capability(input_dev, EV_KEY, BTN_LEFT);
+		input_set_capability(input_dev, EV_KEY, BTN_RIGHT);
+		input_set_capability(input_dev, EV_REL, REL_X);
+		input_set_capability(input_dev, EV_REL, REL_Y);
 		break;
 
 	case GC_SNES:
 		for (i = 4; i < 8; i++)
-			__set_bit(gc_snes_btn[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY, gc_snes_btn[i]);
 		/* fall through */
 	case GC_NES:
 		for (i = 0; i < 4; i++)
-			__set_bit(gc_snes_btn[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY, gc_snes_btn[i]);
 		break;
 
 	case GC_MULTI2:
-		__set_bit(BTN_THUMB, input_dev->keybit);
+		input_set_capability(input_dev, EV_KEY, BTN_THUMB);
 		/* fall through */
 	case GC_MULTI:
-		__set_bit(BTN_TRIGGER, input_dev->keybit);
+		input_set_capability(input_dev, EV_KEY, BTN_TRIGGER);
+		/* fall through */
 		break;
 
 	case GC_PSX:
@@ -906,15 +907,17 @@ static int gc_setup_pad(struct gc *gc, int idx, int pad_type)
 			input_set_abs_params(input_dev,
 					     gc_psx_abs[i], 4, 252, 0, 2);
 		for (i = 0; i < 12; i++)
-			__set_bit(gc_psx_btn[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY, gc_psx_btn[i]);
+		break;
 
 		break;
 
 	case GC_DDR:
 		for (i = 0; i < 4; i++)
-			__set_bit(gc_psx_ddr_btn[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY,
+					     gc_psx_ddr_btn[i]);
 		for (i = 0; i < 12; i++)
-			__set_bit(gc_psx_btn[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY, gc_psx_btn[i]);
 
 		break;
 	}
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 06e9650b3b30..48e36acbeb49 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -86,8 +86,10 @@
 
 #define XPAD_PKT_LEN 64
 
-/* xbox d-pads should map to buttons, as is required for DDR pads
-   but we map them to axes when possible to simplify things */
+/*
+ * xbox d-pads should map to buttons, as is required for DDR pads
+ * but we map them to axes when possible to simplify things
+ */
 #define MAP_DPAD_TO_BUTTONS		(1 << 0)
 #define MAP_TRIGGERS_TO_BUTTONS		(1 << 1)
 #define MAP_STICKS_TO_NULL		(1 << 2)
@@ -123,6 +125,7 @@ static const struct xpad_device {
 	u8 mapping;
 	u8 xtype;
 } xpad_device[] = {
+	{ 0x0079, 0x18d4, "GPD Win 2 Controller", 0, XTYPE_XBOX360 },
 	{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
@@ -387,15 +390,15 @@ static const signed short xpad_abs_triggers[] = {
  * match against vendor id as well. Wired Xbox 360 devices have protocol 1,
  * wireless controllers have protocol 129.
  */
-#define XPAD_XBOX360_VENDOR_PROTOCOL(vend,pr) \
+#define XPAD_XBOX360_VENDOR_PROTOCOL(vend, pr) \
 	.match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_INFO, \
 	.idVendor = (vend), \
 	.bInterfaceClass = USB_CLASS_VENDOR_SPEC, \
 	.bInterfaceSubClass = 93, \
 	.bInterfaceProtocol = (pr)
 #define XPAD_XBOX360_VENDOR(vend) \
-	{ XPAD_XBOX360_VENDOR_PROTOCOL(vend,1) }, \
-	{ XPAD_XBOX360_VENDOR_PROTOCOL(vend,129) }
+	{ XPAD_XBOX360_VENDOR_PROTOCOL((vend), 1) }, \
+	{ XPAD_XBOX360_VENDOR_PROTOCOL((vend), 129) }
 
 /* The Xbox One controller uses subclass 71 and protocol 208. */
 #define XPAD_XBOXONE_VENDOR_PROTOCOL(vend, pr) \
@@ -405,10 +408,11 @@ static const signed short xpad_abs_triggers[] = {
 	.bInterfaceSubClass = 71, \
 	.bInterfaceProtocol = (pr)
 #define XPAD_XBOXONE_VENDOR(vend) \
-	{ XPAD_XBOXONE_VENDOR_PROTOCOL(vend, 208) }
+	{ XPAD_XBOXONE_VENDOR_PROTOCOL((vend), 208) }
 
 static const struct usb_device_id xpad_table[] = {
 	{ USB_INTERFACE_INFO('X', 'B', 0) },	/* X-Box USB-IF not approved class */
+	XPAD_XBOX360_VENDOR(0x0079),		/* GPD Win 2 Controller */
 	XPAD_XBOX360_VENDOR(0x044f),		/* Thrustmaster X-Box 360 controllers */
 	XPAD_XBOX360_VENDOR(0x045e),		/* Microsoft X-Box 360 controllers */
 	XPAD_XBOXONE_VENDOR(0x045e),		/* Microsoft X-Box One controllers */
@@ -1573,7 +1577,6 @@ static void xpad_close(struct input_dev *dev)
 static void xpad_set_up_abs(struct input_dev *input_dev, signed short abs)
 {
 	struct usb_xpad *xpad = input_get_drvdata(input_dev);
-	set_bit(abs, input_dev->absbit);
 
 	switch (abs) {
 	case ABS_X:
@@ -1593,6 +1596,9 @@ static void xpad_set_up_abs(struct input_dev *input_dev, signed short abs)
 	case ABS_HAT0Y:	/* the d-pad (only if dpad is mapped to axes */
 		input_set_abs_params(input_dev, abs, -1, 1, 0, 0);
 		break;
+	default:
+		input_set_abs_params(input_dev, abs, 0, 0, 0, 0);
+		break;
 	}
 }
 
@@ -1633,10 +1639,7 @@ static int xpad_init_input(struct usb_xpad *xpad)
 		input_dev->close = xpad_close;
 	}
 
-	__set_bit(EV_KEY, input_dev->evbit);
-
 	if (!(xpad->mapping & MAP_STICKS_TO_NULL)) {
-		__set_bit(EV_ABS, input_dev->evbit);
 		/* set up axes */
 		for (i = 0; xpad_abs[i] >= 0; i++)
 			xpad_set_up_abs(input_dev, xpad_abs[i]);
@@ -1644,21 +1647,22 @@ static int xpad_init_input(struct usb_xpad *xpad)
 
 	/* set up standard buttons */
 	for (i = 0; xpad_common_btn[i] >= 0; i++)
-		__set_bit(xpad_common_btn[i], input_dev->keybit);
+		input_set_capability(input_dev, EV_KEY, xpad_common_btn[i]);
 
 	/* set up model-specific ones */
 	if (xpad->xtype == XTYPE_XBOX360 || xpad->xtype == XTYPE_XBOX360W ||
 	    xpad->xtype == XTYPE_XBOXONE) {
 		for (i = 0; xpad360_btn[i] >= 0; i++)
-			__set_bit(xpad360_btn[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY, xpad360_btn[i]);
 	} else {
 		for (i = 0; xpad_btn[i] >= 0; i++)
-			__set_bit(xpad_btn[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY, xpad_btn[i]);
 	}
 
 	if (xpad->mapping & MAP_DPAD_TO_BUTTONS) {
 		for (i = 0; xpad_btn_pad[i] >= 0; i++)
-			__set_bit(xpad_btn_pad[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY,
+					     xpad_btn_pad[i]);
 	}
 
 	/*
@@ -1675,7 +1679,8 @@ static int xpad_init_input(struct usb_xpad *xpad)
 
 	if (xpad->mapping & MAP_TRIGGERS_TO_BUTTONS) {
 		for (i = 0; xpad_btn_triggers[i] >= 0; i++)
-			__set_bit(xpad_btn_triggers[i], input_dev->keybit);
+			input_set_capability(input_dev, EV_KEY,
+					     xpad_btn_triggers[i]);
 	} else {
 		for (i = 0; xpad_abs_triggers[i] >= 0; i++)
 			xpad_set_up_abs(input_dev, xpad_abs_triggers[i]);
diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c
index 79eb29550c34..489ddd37bd4e 100644
--- a/drivers/input/keyboard/cros_ec_keyb.c
+++ b/drivers/input/keyboard/cros_ec_keyb.c
@@ -244,24 +244,35 @@ static int cros_ec_keyb_work(struct notifier_block *nb,
 
 	switch (ckdev->ec->event_data.event_type) {
 	case EC_MKBP_EVENT_KEY_MATRIX:
-		/*
-		 * If EC is not the wake source, discard key state changes
-		 * during suspend.
-		 */
-		if (queued_during_suspend)
-			return NOTIFY_OK;
+		if (device_may_wakeup(ckdev->dev)) {
+			pm_wakeup_event(ckdev->dev, 0);
+		} else {
+			/*
+			 * If keyboard is not wake enabled, discard key state
+			 * changes during suspend. Switches will be re-checked
+			 * in cros_ec_keyb_resume() to be sure nothing is lost.
+			 */
+			if (queued_during_suspend)
+				return NOTIFY_OK;
+		}
 
 		if (ckdev->ec->event_size != ckdev->cols) {
 			dev_err(ckdev->dev,
 				"Discarded incomplete key matrix event.\n");
 			return NOTIFY_OK;
 		}
+
 		cros_ec_keyb_process(ckdev,
 				     ckdev->ec->event_data.data.key_matrix,
 				     ckdev->ec->event_size);
 		break;
 
 	case EC_MKBP_EVENT_SYSRQ:
+		if (device_may_wakeup(ckdev->dev))
+			pm_wakeup_event(ckdev->dev, 0);
+		else if (queued_during_suspend)
+			return NOTIFY_OK;
+
 		val = get_unaligned_le32(&ckdev->ec->event_data.data.sysrq);
 		dev_dbg(ckdev->dev, "sysrq code from EC: %#x\n", val);
 		handle_sysrq(val);
@@ -269,12 +280,9 @@ static int cros_ec_keyb_work(struct notifier_block *nb,
 
 	case EC_MKBP_EVENT_BUTTON:
 	case EC_MKBP_EVENT_SWITCH:
-		/*
-		 * If EC is not the wake source, discard key state
-		 * changes during suspend. Switches will be re-checked in
-		 * cros_ec_keyb_resume() to be sure nothing is lost.
-		 */
-		if (queued_during_suspend)
+		if (device_may_wakeup(ckdev->dev))
+			pm_wakeup_event(ckdev->dev, 0);
+		else if (queued_during_suspend)
 			return NOTIFY_OK;
 
 		if (ckdev->ec->event_data.event_type == EC_MKBP_EVENT_BUTTON) {
@@ -639,6 +647,7 @@ static int cros_ec_keyb_probe(struct platform_device *pdev)
 		return err;
 	}
 
+	device_init_wakeup(ckdev->dev, true);
 	return 0;
 }
 
diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c
index ded5b84e336d..d8fd58fdf050 100644
--- a/drivers/input/misc/ati_remote2.c
+++ b/drivers/input/misc/ati_remote2.c
@@ -22,7 +22,7 @@ MODULE_LICENSE("GPL");
 /*
  * ATI Remote Wonder II Channel Configuration
  *
- * The remote control can by assigned one of sixteen "channels" in order to facilitate
+ * The remote control can be assigned one of sixteen "channels" in order to facilitate
  * the use of multiple remote controls within range of each other.
  * A remote's "channel" may be altered by pressing and holding the "PC" button for
  * approximately 3 seconds, after which the button will slowly flash the count of the
diff --git a/drivers/input/misc/hp_sdc_rtc.c b/drivers/input/misc/hp_sdc_rtc.c
index 49b34de0aed4..47eb8ca729fe 100644
--- a/drivers/input/misc/hp_sdc_rtc.c
+++ b/drivers/input/misc/hp_sdc_rtc.c
@@ -509,18 +509,6 @@ static int hp_sdc_rtc_proc_show(struct seq_file *m, void *v)
 #undef NY
 }
 
-static int hp_sdc_rtc_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hp_sdc_rtc_proc_show, NULL);
-}
-
-static const struct file_operations hp_sdc_rtc_proc_fops = {
-	.open		= hp_sdc_rtc_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int hp_sdc_rtc_ioctl(struct file *file, 
 			    unsigned int cmd, unsigned long arg)
 {
@@ -713,7 +701,7 @@ static int __init hp_sdc_rtc_init(void)
 	if (misc_register(&hp_sdc_rtc_dev) != 0)
 		printk(KERN_INFO "Could not register misc. dev for i8042 rtc\n");
 
-        proc_create("driver/rtc", 0, NULL, &hp_sdc_rtc_proc_fops);
+        proc_create_single("driver/rtc", 0, NULL, hp_sdc_rtc_proc_show);
 
 	printk(KERN_INFO "HP i8042 SDC + MSM-58321 RTC support loaded "
 			 "(RTC v " RTC_VERSION ")\n");
diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig
index 89ebb8f39fee..f27f23f2d99a 100644
--- a/drivers/input/mouse/Kconfig
+++ b/drivers/input/mouse/Kconfig
@@ -133,6 +133,18 @@ config MOUSE_PS2_ELANTECH
 
 	  If unsure, say N.
 
+config MOUSE_PS2_ELANTECH_SMBUS
+	bool "Elantech PS/2 SMbus companion" if EXPERT
+	default y
+	depends on MOUSE_PS2 && MOUSE_PS2_ELANTECH
+	depends on I2C=y || I2C=MOUSE_PS2
+	select MOUSE_PS2_SMBUS
+	help
+	  Say Y here if you have a Elantech touchpad connected to
+	  to an SMBus, but enumerated through PS/2.
+
+	  If unsure, say Y.
+
 config MOUSE_PS2_SENTELIC
 	bool "Sentelic Finger Sensing Pad PS/2 protocol extension"
 	depends on MOUSE_PS2
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 0a67f235ba88..cb5579716dba 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -583,7 +583,7 @@ static void alps_process_trackstick_packet_v3(struct psmouse *psmouse)
 
 	x = (s8)(((packet[0] & 0x20) << 2) | (packet[1] & 0x7f));
 	y = (s8)(((packet[0] & 0x10) << 3) | (packet[2] & 0x7f));
-	z = packet[4] & 0x7c;
+	z = packet[4] & 0x7f;
 
 	/*
 	 * The x and y values tend to be quite large, and when used
@@ -2049,14 +2049,11 @@ static int alps_hw_init_v1_v2(struct psmouse *psmouse)
 	return 0;
 }
 
-static int alps_hw_init_v6(struct psmouse *psmouse)
+/* Must be in passthrough mode when calling this function */
+static int alps_trackstick_enter_extended_mode_v3_v6(struct psmouse *psmouse)
 {
 	unsigned char param[2] = {0xC8, 0x14};
 
-	/* Enter passthrough mode to let trackpoint enter 6byte raw mode */
-	if (alps_passthrough_mode_v2(psmouse, true))
-		return -1;
-
 	if (ps2_command(&psmouse->ps2dev, NULL, PSMOUSE_CMD_SETSCALE11) ||
 	    ps2_command(&psmouse->ps2dev, NULL, PSMOUSE_CMD_SETSCALE11) ||
 	    ps2_command(&psmouse->ps2dev, NULL, PSMOUSE_CMD_SETSCALE11) ||
@@ -2064,9 +2061,25 @@ static int alps_hw_init_v6(struct psmouse *psmouse)
 	    ps2_command(&psmouse->ps2dev, &param[1], PSMOUSE_CMD_SETRATE))
 		return -1;
 
+	return 0;
+}
+
+static int alps_hw_init_v6(struct psmouse *psmouse)
+{
+	int ret;
+
+	/* Enter passthrough mode to let trackpoint enter 6byte raw mode */
+	if (alps_passthrough_mode_v2(psmouse, true))
+		return -1;
+
+	ret = alps_trackstick_enter_extended_mode_v3_v6(psmouse);
+
 	if (alps_passthrough_mode_v2(psmouse, false))
 		return -1;
 
+	if (ret)
+		return ret;
+
 	if (alps_absolute_mode_v6(psmouse)) {
 		psmouse_err(psmouse, "Failed to enable absolute mode\n");
 		return -1;
@@ -2140,10 +2153,18 @@ error:
 
 static int alps_setup_trackstick_v3(struct psmouse *psmouse, int reg_base)
 {
-	struct ps2dev *ps2dev = &psmouse->ps2dev;
 	int ret = 0;
+	int reg_val;
 	unsigned char param[4];
 
+	/*
+	 * We need to configure trackstick to report data for touchpad in
+	 * extended format. And also we need to tell touchpad to expect data
+	 * from trackstick in extended format. Without this configuration
+	 * trackstick packets sent from touchpad are in basic format which is
+	 * different from what we expect.
+	 */
+
 	if (alps_passthrough_mode_v3(psmouse, reg_base, true))
 		return -EIO;
 
@@ -2161,39 +2182,36 @@ static int alps_setup_trackstick_v3(struct psmouse *psmouse, int reg_base)
 		ret = -ENODEV;
 	} else {
 		psmouse_dbg(psmouse, "trackstick E7 report: %3ph\n", param);
-
-		/*
-		 * Not sure what this does, but it is absolutely
-		 * essential. Without it, the touchpad does not
-		 * work at all and the trackstick just emits normal
-		 * PS/2 packets.
-		 */
-		if (ps2_command(ps2dev, NULL, PSMOUSE_CMD_SETSCALE11) ||
-		    ps2_command(ps2dev, NULL, PSMOUSE_CMD_SETSCALE11) ||
-		    ps2_command(ps2dev, NULL, PSMOUSE_CMD_SETSCALE11) ||
-		    alps_command_mode_send_nibble(psmouse, 0x9) ||
-		    alps_command_mode_send_nibble(psmouse, 0x4)) {
-			psmouse_err(psmouse,
-				    "Error sending magic E6 sequence\n");
+		if (alps_trackstick_enter_extended_mode_v3_v6(psmouse)) {
+			psmouse_err(psmouse, "Failed to enter into trackstick extended mode\n");
 			ret = -EIO;
-			goto error;
 		}
+	}
+
+	if (alps_passthrough_mode_v3(psmouse, reg_base, false))
+		return -EIO;
+
+	if (ret)
+		return ret;
 
+	if (alps_enter_command_mode(psmouse))
+		return -EIO;
+
+	reg_val = alps_command_mode_read_reg(psmouse, reg_base + 0x08);
+	if (reg_val == -1) {
+		ret = -EIO;
+	} else {
 		/*
-		 * This ensures the trackstick packets are in the format
-		 * supported by this driver. If bit 1 isn't set the packet
-		 * format is different.
+		 * Tell touchpad that trackstick is now in extended mode.
+		 * If bit 1 isn't set the packet format is different.
 		 */
-		if (alps_enter_command_mode(psmouse) ||
-		    alps_command_mode_write_reg(psmouse,
-						reg_base + 0x08, 0x82) ||
-		    alps_exit_command_mode(psmouse))
+		reg_val |= BIT(1);
+		if (__alps_command_mode_write_reg(psmouse, reg_val))
 			ret = -EIO;
 	}
 
-error:
-	if (alps_passthrough_mode_v3(psmouse, reg_base, false))
-		ret = -EIO;
+	if (alps_exit_command_mode(psmouse))
+		return -EIO;
 
 	return ret;
 }
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 75e757520ef0..8ff75114e762 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -36,6 +36,7 @@
 #include <linux/jiffies.h>
 #include <linux/completion.h>
 #include <linux/of.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <asm/unaligned.h>
 
@@ -51,6 +52,7 @@
 #define ETP_MAX_FINGERS		5
 #define ETP_FINGER_DATA_LEN	5
 #define ETP_REPORT_ID		0x5D
+#define ETP_TP_REPORT_ID	0x5E
 #define ETP_REPORT_ID_OFFSET	2
 #define ETP_TOUCH_INFO_OFFSET	3
 #define ETP_FINGER_DATA_OFFSET	4
@@ -61,6 +63,7 @@
 struct elan_tp_data {
 	struct i2c_client	*client;
 	struct input_dev	*input;
+	struct input_dev	*tp_input; /* trackpoint input node */
 	struct regulator	*vcc;
 
 	const struct elan_transport_ops *ops;
@@ -930,6 +933,33 @@ static void elan_report_absolute(struct elan_tp_data *data, u8 *packet)
 	input_sync(input);
 }
 
+static void elan_report_trackpoint(struct elan_tp_data *data, u8 *report)
+{
+	struct input_dev *input = data->tp_input;
+	u8 *packet = &report[ETP_REPORT_ID_OFFSET + 1];
+	int x, y;
+
+	if (!data->tp_input) {
+		dev_warn_once(&data->client->dev,
+			      "received a trackpoint report while no trackpoint device has been created. Please report upstream.\n");
+		return;
+	}
+
+	input_report_key(input, BTN_LEFT, packet[0] & 0x01);
+	input_report_key(input, BTN_RIGHT, packet[0] & 0x02);
+	input_report_key(input, BTN_MIDDLE, packet[0] & 0x04);
+
+	if ((packet[3] & 0x0F) == 0x06) {
+		x = packet[4] - (int)((packet[1] ^ 0x80) << 1);
+		y = (int)((packet[2] ^ 0x80) << 1) - packet[5];
+
+		input_report_rel(input, REL_X, x);
+		input_report_rel(input, REL_Y, y);
+	}
+
+	input_sync(input);
+}
+
 static irqreturn_t elan_isr(int irq, void *dev_id)
 {
 	struct elan_tp_data *data = dev_id;
@@ -951,11 +981,17 @@ static irqreturn_t elan_isr(int irq, void *dev_id)
 	if (error)
 		goto out;
 
-	if (report[ETP_REPORT_ID_OFFSET] != ETP_REPORT_ID)
+	switch (report[ETP_REPORT_ID_OFFSET]) {
+	case ETP_REPORT_ID:
+		elan_report_absolute(data, report);
+		break;
+	case ETP_TP_REPORT_ID:
+		elan_report_trackpoint(data, report);
+		break;
+	default:
 		dev_err(dev, "invalid report id data (%x)\n",
 			report[ETP_REPORT_ID_OFFSET]);
-	else
-		elan_report_absolute(data, report);
+	}
 
 out:
 	return IRQ_HANDLED;
@@ -966,6 +1002,36 @@ out:
  * Elan initialization functions
  ******************************************************************
  */
+
+static int elan_setup_trackpoint_input_device(struct elan_tp_data *data)
+{
+	struct device *dev = &data->client->dev;
+	struct input_dev *input;
+
+	input = devm_input_allocate_device(dev);
+	if (!input)
+		return -ENOMEM;
+
+	input->name = "Elan TrackPoint";
+	input->id.bustype = BUS_I2C;
+	input->id.vendor = ELAN_VENDOR_ID;
+	input->id.product = data->product_id;
+	input_set_drvdata(input, data);
+
+	input_set_capability(input, EV_REL, REL_X);
+	input_set_capability(input, EV_REL, REL_Y);
+	input_set_capability(input, EV_KEY, BTN_LEFT);
+	input_set_capability(input, EV_KEY, BTN_RIGHT);
+	input_set_capability(input, EV_KEY, BTN_MIDDLE);
+
+	__set_bit(INPUT_PROP_POINTER, input->propbit);
+	__set_bit(INPUT_PROP_POINTING_STICK, input->propbit);
+
+	data->tp_input = input;
+
+	return 0;
+}
+
 static int elan_setup_input_device(struct elan_tp_data *data)
 {
 	struct device *dev = &data->client->dev;
@@ -1140,6 +1206,12 @@ static int elan_probe(struct i2c_client *client,
 	if (error)
 		return error;
 
+	if (device_property_read_bool(&client->dev, "elan,trackpoint")) {
+		error = elan_setup_trackpoint_input_device(data);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * Platform code (ACPI, DTS) should normally set up interrupt
 	 * for us, but in case it did not let's fall back to using falling
@@ -1177,6 +1249,16 @@ static int elan_probe(struct i2c_client *client,
 		return error;
 	}
 
+	if (data->tp_input) {
+		error = input_register_device(data->tp_input);
+		if (error) {
+			dev_err(&client->dev,
+				"failed to register TrackPoint input device: %d\n",
+				error);
+			return error;
+		}
+	}
+
 	/*
 	 * Systems using device tree should set up wakeup via DTS,
 	 * the rest will configure device as wakeup source by default.
@@ -1262,6 +1344,7 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN060B", 0 },
 	{ "ELAN060C", 0 },
 	{ "ELAN0611", 0 },
+	{ "ELAN0612", 0 },
 	{ "ELAN1000", 0 },
 	{ }
 };
diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c
index 29f99529b187..cfcb32559925 100644
--- a/drivers/input/mouse/elan_i2c_smbus.c
+++ b/drivers/input/mouse/elan_i2c_smbus.c
@@ -130,7 +130,7 @@ static int elan_smbus_get_baseline_data(struct i2c_client *client,
 					bool max_baseline, u8 *value)
 {
 	int error;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	error = i2c_smbus_read_block_data(client,
 					  max_baseline ?
@@ -149,7 +149,7 @@ static int elan_smbus_get_version(struct i2c_client *client,
 				  bool iap, u8 *version)
 {
 	int error;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	error = i2c_smbus_read_block_data(client,
 					  iap ? ETP_SMBUS_IAP_VERSION_CMD :
@@ -170,7 +170,7 @@ static int elan_smbus_get_sm_version(struct i2c_client *client,
 				     u8 *clickpad)
 {
 	int error;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	error = i2c_smbus_read_block_data(client,
 					  ETP_SMBUS_SM_VERSION_CMD, val);
@@ -188,7 +188,7 @@ static int elan_smbus_get_sm_version(struct i2c_client *client,
 static int elan_smbus_get_product_id(struct i2c_client *client, u16 *id)
 {
 	int error;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	error = i2c_smbus_read_block_data(client,
 					  ETP_SMBUS_UNIQUEID_CMD, val);
@@ -205,7 +205,7 @@ static int elan_smbus_get_checksum(struct i2c_client *client,
 				   bool iap, u16 *csum)
 {
 	int error;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	error = i2c_smbus_read_block_data(client,
 					  iap ? ETP_SMBUS_FW_CHECKSUM_CMD :
@@ -226,7 +226,7 @@ static int elan_smbus_get_max(struct i2c_client *client,
 {
 	int ret;
 	int error;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	ret = i2c_smbus_read_block_data(client, ETP_SMBUS_RANGE_CMD, val);
 	if (ret != 3) {
@@ -246,7 +246,7 @@ static int elan_smbus_get_resolution(struct i2c_client *client,
 {
 	int ret;
 	int error;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	ret = i2c_smbus_read_block_data(client, ETP_SMBUS_RESOLUTION_CMD, val);
 	if (ret != 3) {
@@ -267,7 +267,7 @@ static int elan_smbus_get_num_traces(struct i2c_client *client,
 {
 	int ret;
 	int error;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	ret = i2c_smbus_read_block_data(client, ETP_SMBUS_XY_TRACENUM_CMD, val);
 	if (ret != 3) {
@@ -294,7 +294,7 @@ static int elan_smbus_iap_get_mode(struct i2c_client *client,
 {
 	int error;
 	u16 constant;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	error = i2c_smbus_read_block_data(client, ETP_SMBUS_IAP_CTRL_CMD, val);
 	if (error < 0) {
@@ -345,7 +345,7 @@ static int elan_smbus_prepare_fw_update(struct i2c_client *client)
 	int len;
 	int error;
 	enum tp_mode mode;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 	u8 cmd[4] = {0x0F, 0x78, 0x00, 0x06};
 	u16 password;
 
@@ -419,7 +419,7 @@ static int elan_smbus_write_fw_block(struct i2c_client *client,
 	struct device *dev = &client->dev;
 	int error;
 	u16 result;
-	u8 val[3];
+	u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
 	/*
 	 * Due to the limitation of smbus protocol limiting
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index db47a5e1d114..fb4d902c4403 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -14,17 +14,20 @@
 #include <linux/dmi.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/i2c.h>
 #include <linux/input.h>
 #include <linux/input/mt.h>
+#include <linux/platform_device.h>
 #include <linux/serio.h>
 #include <linux/libps2.h>
 #include <asm/unaligned.h>
 #include "psmouse.h"
 #include "elantech.h"
+#include "elan_i2c.h"
 
 #define elantech_debug(fmt, ...)					\
 	do {								\
-		if (etd->debug)						\
+		if (etd->info.debug)					\
 			psmouse_printk(KERN_DEBUG, psmouse,		\
 					fmt, ##__VA_ARGS__);		\
 	} while (0)
@@ -105,7 +108,7 @@ static int elantech_read_reg(struct psmouse *psmouse, unsigned char reg,
 	if (reg > 0x11 && reg < 0x20)
 		return -1;
 
-	switch (etd->hw_version) {
+	switch (etd->info.hw_version) {
 	case 1:
 		if (ps2_sliced_command(&psmouse->ps2dev, ETP_REGISTER_READ) ||
 		    ps2_sliced_command(&psmouse->ps2dev, reg) ||
@@ -137,7 +140,7 @@ static int elantech_read_reg(struct psmouse *psmouse, unsigned char reg,
 
 	if (rc)
 		psmouse_err(psmouse, "failed to read register 0x%02x.\n", reg);
-	else if (etd->hw_version != 4)
+	else if (etd->info.hw_version != 4)
 		*val = param[0];
 	else
 		*val = param[1];
@@ -160,7 +163,7 @@ static int elantech_write_reg(struct psmouse *psmouse, unsigned char reg,
 	if (reg > 0x11 && reg < 0x20)
 		return -1;
 
-	switch (etd->hw_version) {
+	switch (etd->info.hw_version) {
 	case 1:
 		if (ps2_sliced_command(&psmouse->ps2dev, ETP_REGISTER_WRITE) ||
 		    ps2_sliced_command(&psmouse->ps2dev, reg) ||
@@ -237,7 +240,7 @@ static void elantech_report_absolute_v1(struct psmouse *psmouse)
 	unsigned char *packet = psmouse->packet;
 	int fingers;
 
-	if (etd->fw_version < 0x020000) {
+	if (etd->info.fw_version < 0x020000) {
 		/*
 		 * byte 0:  D   U  p1  p2   1  p3   R   L
 		 * byte 1:  f   0  th  tw  x9  x8  y9  y8
@@ -252,7 +255,7 @@ static void elantech_report_absolute_v1(struct psmouse *psmouse)
 		fingers = (packet[0] & 0xc0) >> 6;
 	}
 
-	if (etd->jumpy_cursor) {
+	if (etd->info.jumpy_cursor) {
 		if (fingers != 1) {
 			etd->single_finger_reports = 0;
 		} else if (etd->single_finger_reports < 2) {
@@ -282,8 +285,8 @@ static void elantech_report_absolute_v1(struct psmouse *psmouse)
 
 	psmouse_report_standard_buttons(dev, packet[0]);
 
-	if (etd->fw_version < 0x020000 &&
-	    (etd->capabilities[0] & ETP_CAP_HAS_ROCKER)) {
+	if (etd->info.fw_version < 0x020000 &&
+	    (etd->info.capabilities[0] & ETP_CAP_HAS_ROCKER)) {
 		/* rocker up */
 		input_report_key(dev, BTN_FORWARD, packet[0] & 0x40);
 		/* rocker down */
@@ -391,7 +394,7 @@ static void elantech_report_absolute_v2(struct psmouse *psmouse)
 	input_report_key(dev, BTN_TOOL_TRIPLETAP, fingers == 3);
 	input_report_key(dev, BTN_TOOL_QUADTAP, fingers == 4);
 	psmouse_report_standard_buttons(dev, packet[0]);
-	if (etd->reports_pressure) {
+	if (etd->info.reports_pressure) {
 		input_report_abs(dev, ABS_PRESSURE, pres);
 		input_report_abs(dev, ABS_TOOL_WIDTH, width);
 	}
@@ -444,7 +447,7 @@ static void elantech_report_trackpoint(struct psmouse *psmouse,
 
 	default:
 		/* Dump unexpected packet sequences if debug=1 (default) */
-		if (etd->debug == 1)
+		if (etd->info.debug == 1)
 			elantech_packet_dump(psmouse);
 
 		break;
@@ -523,7 +526,7 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 	input_report_key(dev, BTN_TOOL_TRIPLETAP, fingers == 3);
 
 	/* For clickpads map both buttons to BTN_LEFT */
-	if (etd->fw_version & 0x001000)
+	if (etd->info.fw_version & 0x001000)
 		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
 	else
 		psmouse_report_standard_buttons(dev, packet[0]);
@@ -541,7 +544,7 @@ static void elantech_input_sync_v4(struct psmouse *psmouse)
 	unsigned char *packet = psmouse->packet;
 
 	/* For clickpads map both buttons to BTN_LEFT */
-	if (etd->fw_version & 0x001000)
+	if (etd->info.fw_version & 0x001000)
 		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
 	else
 		psmouse_report_standard_buttons(dev, packet[0]);
@@ -669,7 +672,7 @@ static int elantech_packet_check_v1(struct psmouse *psmouse)
 	unsigned char p1, p2, p3;
 
 	/* Parity bits are placed differently */
-	if (etd->fw_version < 0x020000) {
+	if (etd->info.fw_version < 0x020000) {
 		/* byte 0:  D   U  p1  p2   1  p3   R   L */
 		p1 = (packet[0] & 0x20) >> 5;
 		p2 = (packet[0] & 0x10) >> 4;
@@ -714,7 +717,7 @@ static int elantech_packet_check_v2(struct psmouse *psmouse)
 	 * With all three cases, if the constant bits are not exactly what I
 	 * expected, I consider them invalid.
 	 */
-	if (etd->reports_pressure)
+	if (etd->info.reports_pressure)
 		return (packet[0] & 0x0c) == 0x04 &&
 		       (packet[3] & 0x0f) == 0x02;
 
@@ -751,7 +754,7 @@ static int elantech_packet_check_v3(struct psmouse *psmouse)
 	 * If the hardware flag 'crc_enabled' is set the packets have
 	 * different signatures.
 	 */
-	if (etd->crc_enabled) {
+	if (etd->info.crc_enabled) {
 		if ((packet[3] & 0x09) == 0x08)
 			return PACKET_V3_HEAD;
 
@@ -782,7 +785,7 @@ static int elantech_packet_check_v4(struct psmouse *psmouse)
 		return PACKET_TRACKPOINT;
 
 	/* This represents the version of IC body. */
-	ic_version = (etd->fw_version & 0x0f0000) >> 16;
+	ic_version = (etd->info.fw_version & 0x0f0000) >> 16;
 
 	/*
 	 * Sanity check based on the constant bits of a packet.
@@ -791,9 +794,9 @@ static int elantech_packet_check_v4(struct psmouse *psmouse)
 	 * the IC body, but are the same for every packet,
 	 * regardless of the type.
 	 */
-	if (etd->crc_enabled)
+	if (etd->info.crc_enabled)
 		sanity_check = ((packet[3] & 0x08) == 0x00);
-	else if (ic_version == 7 && etd->samples[1] == 0x2A)
+	else if (ic_version == 7 && etd->info.samples[1] == 0x2A)
 		sanity_check = ((packet[3] & 0x1c) == 0x10);
 	else
 		sanity_check = ((packet[0] & 0x0c) == 0x04 &&
@@ -827,12 +830,12 @@ static psmouse_ret_t elantech_process_byte(struct psmouse *psmouse)
 	if (psmouse->pktcnt < psmouse->pktsize)
 		return PSMOUSE_GOOD_DATA;
 
-	if (etd->debug > 1)
+	if (etd->info.debug > 1)
 		elantech_packet_dump(psmouse);
 
-	switch (etd->hw_version) {
+	switch (etd->info.hw_version) {
 	case 1:
-		if (etd->paritycheck && !elantech_packet_check_v1(psmouse))
+		if (etd->info.paritycheck && !elantech_packet_check_v1(psmouse))
 			return PSMOUSE_BAD_DATA;
 
 		elantech_report_absolute_v1(psmouse);
@@ -843,7 +846,7 @@ static psmouse_ret_t elantech_process_byte(struct psmouse *psmouse)
 		if (elantech_debounce_check_v2(psmouse))
 			return PSMOUSE_FULL_PACKET;
 
-		if (etd->paritycheck && !elantech_packet_check_v2(psmouse))
+		if (etd->info.paritycheck && !elantech_packet_check_v2(psmouse))
 			return PSMOUSE_BAD_DATA;
 
 		elantech_report_absolute_v2(psmouse);
@@ -916,7 +919,7 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse)
 	int tries = ETP_READ_BACK_TRIES;
 	int rc = 0;
 
-	switch (etd->hw_version) {
+	switch (etd->info.hw_version) {
 	case 1:
 		etd->reg_10 = 0x16;
 		etd->reg_11 = 0x8f;
@@ -939,7 +942,7 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse)
 		break;
 
 	case 3:
-		if (etd->set_hw_resolution)
+		if (etd->info.set_hw_resolution)
 			etd->reg_10 = 0x0b;
 		else
 			etd->reg_10 = 0x01;
@@ -976,7 +979,7 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse)
 		if (rc) {
 			psmouse_err(psmouse,
 				    "failed to read back register 0x10.\n");
-		} else if (etd->hw_version == 1 &&
+		} else if (etd->info.hw_version == 1 &&
 			   !(val & ETP_R10_ABSOLUTE_MODE)) {
 			psmouse_err(psmouse,
 				    "touchpad refuses to switch to absolute mode.\n");
@@ -997,10 +1000,11 @@ static int elantech_set_range(struct psmouse *psmouse,
 			      unsigned int *width)
 {
 	struct elantech_data *etd = psmouse->private;
+	struct elantech_device_info *info = &etd->info;
 	unsigned char param[3];
 	unsigned char traces;
 
-	switch (etd->hw_version) {
+	switch (info->hw_version) {
 	case 1:
 		*x_min = ETP_XMIN_V1;
 		*y_min = ETP_YMIN_V1;
@@ -1009,9 +1013,9 @@ static int elantech_set_range(struct psmouse *psmouse,
 		break;
 
 	case 2:
-		if (etd->fw_version == 0x020800 ||
-		    etd->fw_version == 0x020b00 ||
-		    etd->fw_version == 0x020030) {
+		if (info->fw_version == 0x020800 ||
+		    info->fw_version == 0x020b00 ||
+		    info->fw_version == 0x020030) {
 			*x_min = ETP_XMIN_V2;
 			*y_min = ETP_YMIN_V2;
 			*x_max = ETP_XMAX_V2;
@@ -1020,35 +1024,35 @@ static int elantech_set_range(struct psmouse *psmouse,
 			int i;
 			int fixed_dpi;
 
-			i = (etd->fw_version > 0x020800 &&
-			     etd->fw_version < 0x020900) ? 1 : 2;
+			i = (info->fw_version > 0x020800 &&
+			     info->fw_version < 0x020900) ? 1 : 2;
 
-			if (etd->send_cmd(psmouse, ETP_FW_ID_QUERY, param))
+			if (info->send_cmd(psmouse, ETP_FW_ID_QUERY, param))
 				return -1;
 
 			fixed_dpi = param[1] & 0x10;
 
-			if (((etd->fw_version >> 16) == 0x14) && fixed_dpi) {
-				if (etd->send_cmd(psmouse, ETP_SAMPLE_QUERY, param))
+			if (((info->fw_version >> 16) == 0x14) && fixed_dpi) {
+				if (info->send_cmd(psmouse, ETP_SAMPLE_QUERY, param))
 					return -1;
 
-				*x_max = (etd->capabilities[1] - i) * param[1] / 2;
-				*y_max = (etd->capabilities[2] - i) * param[2] / 2;
-			} else if (etd->fw_version == 0x040216) {
+				*x_max = (info->capabilities[1] - i) * param[1] / 2;
+				*y_max = (info->capabilities[2] - i) * param[2] / 2;
+			} else if (info->fw_version == 0x040216) {
 				*x_max = 819;
 				*y_max = 405;
-			} else if (etd->fw_version == 0x040219 || etd->fw_version == 0x040215) {
+			} else if (info->fw_version == 0x040219 || info->fw_version == 0x040215) {
 				*x_max = 900;
 				*y_max = 500;
 			} else {
-				*x_max = (etd->capabilities[1] - i) * 64;
-				*y_max = (etd->capabilities[2] - i) * 64;
+				*x_max = (info->capabilities[1] - i) * 64;
+				*y_max = (info->capabilities[2] - i) * 64;
 			}
 		}
 		break;
 
 	case 3:
-		if (etd->send_cmd(psmouse, ETP_FW_ID_QUERY, param))
+		if (info->send_cmd(psmouse, ETP_FW_ID_QUERY, param))
 			return -1;
 
 		*x_max = (0x0f & param[0]) << 8 | param[1];
@@ -1056,12 +1060,12 @@ static int elantech_set_range(struct psmouse *psmouse,
 		break;
 
 	case 4:
-		if (etd->send_cmd(psmouse, ETP_FW_ID_QUERY, param))
+		if (info->send_cmd(psmouse, ETP_FW_ID_QUERY, param))
 			return -1;
 
 		*x_max = (0x0f & param[0]) << 8 | param[1];
 		*y_max = (0xf0 & param[0]) << 4 | param[2];
-		traces = etd->capabilities[1];
+		traces = info->capabilities[1];
 		if ((traces < 2) || (traces > *x_max))
 			return -1;
 
@@ -1083,7 +1087,8 @@ static unsigned int elantech_convert_res(unsigned int val)
 
 static int elantech_get_resolution_v4(struct psmouse *psmouse,
 				      unsigned int *x_res,
-				      unsigned int *y_res)
+				      unsigned int *y_res,
+				      unsigned int *bus)
 {
 	unsigned char param[3];
 
@@ -1092,6 +1097,7 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse,
 
 	*x_res = elantech_convert_res(param[1] & 0x0f);
 	*y_res = elantech_convert_res((param[1] & 0xf0) >> 4);
+	*bus = param[2];
 
 	return 0;
 }
@@ -1140,7 +1146,7 @@ static void elantech_set_buttonpad_prop(struct psmouse *psmouse)
 	struct input_dev *dev = psmouse->dev;
 	struct elantech_data *etd = psmouse->private;
 
-	if (etd->fw_version & 0x001000) {
+	if (etd->info.fw_version & 0x001000) {
 		__set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
 		__clear_bit(BTN_RIGHT, dev->keybit);
 	}
@@ -1176,8 +1182,8 @@ static int elantech_set_input_params(struct psmouse *psmouse)
 {
 	struct input_dev *dev = psmouse->dev;
 	struct elantech_data *etd = psmouse->private;
+	struct elantech_device_info *info = &etd->info;
 	unsigned int x_min = 0, y_min = 0, x_max = 0, y_max = 0, width = 0;
-	unsigned int x_res = 31, y_res = 31;
 
 	if (elantech_set_range(psmouse, &x_min, &y_min, &x_max, &y_max, &width))
 		return -1;
@@ -1197,11 +1203,11 @@ static int elantech_set_input_params(struct psmouse *psmouse)
 	__set_bit(BTN_TOOL_DOUBLETAP, dev->keybit);
 	__set_bit(BTN_TOOL_TRIPLETAP, dev->keybit);
 
-	switch (etd->hw_version) {
+	switch (info->hw_version) {
 	case 1:
 		/* Rocker button */
-		if (etd->fw_version < 0x020000 &&
-		    (etd->capabilities[0] & ETP_CAP_HAS_ROCKER)) {
+		if (info->fw_version < 0x020000 &&
+		    (info->capabilities[0] & ETP_CAP_HAS_ROCKER)) {
 			__set_bit(BTN_FORWARD, dev->keybit);
 			__set_bit(BTN_BACK, dev->keybit);
 		}
@@ -1214,11 +1220,11 @@ static int elantech_set_input_params(struct psmouse *psmouse)
 		__set_bit(INPUT_PROP_SEMI_MT, dev->propbit);
 		/* fall through */
 	case 3:
-		if (etd->hw_version == 3)
+		if (info->hw_version == 3)
 			elantech_set_buttonpad_prop(psmouse);
 		input_set_abs_params(dev, ABS_X, x_min, x_max, 0, 0);
 		input_set_abs_params(dev, ABS_Y, y_min, y_max, 0, 0);
-		if (etd->reports_pressure) {
+		if (info->reports_pressure) {
 			input_set_abs_params(dev, ABS_PRESSURE, ETP_PMIN_V2,
 					     ETP_PMAX_V2, 0, 0);
 			input_set_abs_params(dev, ABS_TOOL_WIDTH, ETP_WMIN_V2,
@@ -1230,13 +1236,6 @@ static int elantech_set_input_params(struct psmouse *psmouse)
 		break;
 
 	case 4:
-		if (elantech_get_resolution_v4(psmouse, &x_res, &y_res)) {
-			/*
-			 * if query failed, print a warning and leave the values
-			 * zero to resemble synaptics.c behavior.
-			 */
-			psmouse_warn(psmouse, "couldn't query resolution data.\n");
-		}
 		elantech_set_buttonpad_prop(psmouse);
 		__set_bit(BTN_TOOL_QUADTAP, dev->keybit);
 		/* For X to recognize me as touchpad. */
@@ -1265,11 +1264,11 @@ static int elantech_set_input_params(struct psmouse *psmouse)
 		break;
 	}
 
-	input_abs_set_res(dev, ABS_X, x_res);
-	input_abs_set_res(dev, ABS_Y, y_res);
-	if (etd->hw_version > 1) {
-		input_abs_set_res(dev, ABS_MT_POSITION_X, x_res);
-		input_abs_set_res(dev, ABS_MT_POSITION_Y, y_res);
+	input_abs_set_res(dev, ABS_X, info->x_res);
+	input_abs_set_res(dev, ABS_Y, info->y_res);
+	if (info->hw_version > 1) {
+		input_abs_set_res(dev, ABS_MT_POSITION_X, info->x_res);
+		input_abs_set_res(dev, ABS_MT_POSITION_Y, info->y_res);
 	}
 
 	etd->y_max = y_max;
@@ -1317,7 +1316,7 @@ static ssize_t elantech_set_int_attr(struct psmouse *psmouse,
 		return err;
 
 	/* Do we need to preserve some bits for version 2 hardware too? */
-	if (etd->hw_version == 1) {
+	if (etd->info.hw_version == 1) {
 		if (attr->reg == 0x10)
 			/* Force absolute mode always on */
 			value |= ETP_R10_ABSOLUTE_MODE;
@@ -1337,11 +1336,22 @@ static ssize_t elantech_set_int_attr(struct psmouse *psmouse,
 		.field_offset = offsetof(struct elantech_data, _name),	\
 		.reg = _register,					\
 	};								\
-	PSMOUSE_DEFINE_ATTR(_name, S_IWUSR | S_IRUGO,			\
+	PSMOUSE_DEFINE_ATTR(_name, 0644,				\
 			    &elantech_attr_##_name,			\
 			    elantech_show_int_attr,			\
 			    elantech_set_int_attr)
 
+#define ELANTECH_INFO_ATTR(_name)					       \
+	static struct elantech_attr_data elantech_attr_##_name = {	       \
+		.field_offset = offsetof(struct elantech_data, info) +	       \
+				offsetof(struct elantech_device_info, _name),  \
+		.reg = 0,						       \
+	};								       \
+	PSMOUSE_DEFINE_ATTR(_name, 0644,				       \
+			    &elantech_attr_##_name,			       \
+			    elantech_show_int_attr,			       \
+			    elantech_set_int_attr)
+
 ELANTECH_INT_ATTR(reg_07, 0x07);
 ELANTECH_INT_ATTR(reg_10, 0x10);
 ELANTECH_INT_ATTR(reg_11, 0x11);
@@ -1352,9 +1362,9 @@ ELANTECH_INT_ATTR(reg_23, 0x23);
 ELANTECH_INT_ATTR(reg_24, 0x24);
 ELANTECH_INT_ATTR(reg_25, 0x25);
 ELANTECH_INT_ATTR(reg_26, 0x26);
-ELANTECH_INT_ATTR(debug, 0);
-ELANTECH_INT_ATTR(paritycheck, 0);
-ELANTECH_INT_ATTR(crc_enabled, 0);
+ELANTECH_INFO_ATTR(debug);
+ELANTECH_INFO_ATTR(paritycheck);
+ELANTECH_INFO_ATTR(crc_enabled);
 
 static struct attribute *elantech_attrs[] = {
 	&psmouse_attr_reg_07.dattr.attr,
@@ -1469,6 +1479,12 @@ static void elantech_disconnect(struct psmouse *psmouse)
 {
 	struct elantech_data *etd = psmouse->private;
 
+	/*
+	 * We might have left a breadcrumb when trying to
+	 * set up SMbus companion.
+	 */
+	psmouse_smbus_cleanup(psmouse);
+
 	if (etd->tp_dev)
 		input_unregister_device(etd->tp_dev);
 	sysfs_remove_group(&psmouse->ps2dev.serio->dev.kobj,
@@ -1588,25 +1604,25 @@ static const struct dmi_system_id no_hw_res_dmi_table[] = {
 /*
  * determine hardware version and set some properties according to it.
  */
-static int elantech_set_properties(struct elantech_data *etd)
+static int elantech_set_properties(struct elantech_device_info *info)
 {
 	/* This represents the version of IC body. */
-	int ver = (etd->fw_version & 0x0f0000) >> 16;
+	int ver = (info->fw_version & 0x0f0000) >> 16;
 
 	/* Early version of Elan touchpads doesn't obey the rule. */
-	if (etd->fw_version < 0x020030 || etd->fw_version == 0x020600)
-		etd->hw_version = 1;
+	if (info->fw_version < 0x020030 || info->fw_version == 0x020600)
+		info->hw_version = 1;
 	else {
 		switch (ver) {
 		case 2:
 		case 4:
-			etd->hw_version = 2;
+			info->hw_version = 2;
 			break;
 		case 5:
-			etd->hw_version = 3;
+			info->hw_version = 3;
 			break;
 		case 6 ... 15:
-			etd->hw_version = 4;
+			info->hw_version = 4;
 			break;
 		default:
 			return -1;
@@ -1614,100 +1630,88 @@ static int elantech_set_properties(struct elantech_data *etd)
 	}
 
 	/* decide which send_cmd we're gonna use early */
-	etd->send_cmd = etd->hw_version >= 3 ? elantech_send_cmd :
-					       synaptics_send_cmd;
+	info->send_cmd = info->hw_version >= 3 ? elantech_send_cmd :
+						 synaptics_send_cmd;
 
 	/* Turn on packet checking by default */
-	etd->paritycheck = 1;
+	info->paritycheck = 1;
 
 	/*
 	 * This firmware suffers from misreporting coordinates when
 	 * a touch action starts causing the mouse cursor or scrolled page
 	 * to jump. Enable a workaround.
 	 */
-	etd->jumpy_cursor =
-		(etd->fw_version == 0x020022 || etd->fw_version == 0x020600);
+	info->jumpy_cursor =
+		(info->fw_version == 0x020022 || info->fw_version == 0x020600);
 
-	if (etd->hw_version > 1) {
+	if (info->hw_version > 1) {
 		/* For now show extra debug information */
-		etd->debug = 1;
+		info->debug = 1;
 
-		if (etd->fw_version >= 0x020800)
-			etd->reports_pressure = true;
+		if (info->fw_version >= 0x020800)
+			info->reports_pressure = true;
 	}
 
 	/*
 	 * The signatures of v3 and v4 packets change depending on the
 	 * value of this hardware flag.
 	 */
-	etd->crc_enabled = (etd->fw_version & 0x4000) == 0x4000 ||
-			   dmi_check_system(elantech_dmi_force_crc_enabled);
+	info->crc_enabled = (info->fw_version & 0x4000) == 0x4000 ||
+			     dmi_check_system(elantech_dmi_force_crc_enabled);
 
 	/* Enable real hardware resolution on hw_version 3 ? */
-	etd->set_hw_resolution = !dmi_check_system(no_hw_res_dmi_table);
+	info->set_hw_resolution = !dmi_check_system(no_hw_res_dmi_table);
 
 	return 0;
 }
 
-/*
- * Initialize the touchpad and create sysfs entries
- */
-int elantech_init(struct psmouse *psmouse)
+static int elantech_query_info(struct psmouse *psmouse,
+			       struct elantech_device_info *info)
 {
-	struct elantech_data *etd;
-	int i;
-	int error = -EINVAL;
 	unsigned char param[3];
-	struct input_dev *tp_dev;
 
-	psmouse->private = etd = kzalloc(sizeof(struct elantech_data), GFP_KERNEL);
-	if (!etd)
-		return -ENOMEM;
-
-	psmouse_reset(psmouse);
-
-	etd->parity[0] = 1;
-	for (i = 1; i < 256; i++)
-		etd->parity[i] = etd->parity[i & (i - 1)] ^ 1;
+	memset(info, 0, sizeof(*info));
 
 	/*
 	 * Do the version query again so we can store the result
 	 */
 	if (synaptics_send_cmd(psmouse, ETP_FW_VERSION_QUERY, param)) {
 		psmouse_err(psmouse, "failed to query firmware version.\n");
-		goto init_fail;
+		return -EINVAL;
 	}
-	etd->fw_version = (param[0] << 16) | (param[1] << 8) | param[2];
+	info->fw_version = (param[0] << 16) | (param[1] << 8) | param[2];
 
-	if (elantech_set_properties(etd)) {
+	if (elantech_set_properties(info)) {
 		psmouse_err(psmouse, "unknown hardware version, aborting...\n");
-		goto init_fail;
+		return -EINVAL;
 	}
 	psmouse_info(psmouse,
 		     "assuming hardware version %d (with firmware version 0x%02x%02x%02x)\n",
-		     etd->hw_version, param[0], param[1], param[2]);
+		     info->hw_version, param[0], param[1], param[2]);
 
-	if (etd->send_cmd(psmouse, ETP_CAPABILITIES_QUERY,
-	    etd->capabilities)) {
+	if (info->send_cmd(psmouse, ETP_CAPABILITIES_QUERY,
+	    info->capabilities)) {
 		psmouse_err(psmouse, "failed to query capabilities.\n");
-		goto init_fail;
+		return -EINVAL;
 	}
 	psmouse_info(psmouse,
 		     "Synaptics capabilities query result 0x%02x, 0x%02x, 0x%02x.\n",
-		     etd->capabilities[0], etd->capabilities[1],
-		     etd->capabilities[2]);
+		     info->capabilities[0], info->capabilities[1],
+		     info->capabilities[2]);
 
-	if (etd->hw_version != 1) {
-		if (etd->send_cmd(psmouse, ETP_SAMPLE_QUERY, etd->samples)) {
+	if (info->hw_version != 1) {
+		if (info->send_cmd(psmouse, ETP_SAMPLE_QUERY, info->samples)) {
 			psmouse_err(psmouse, "failed to query sample data\n");
-			goto init_fail;
+			return -EINVAL;
 		}
 		psmouse_info(psmouse,
 			     "Elan sample query result %02x, %02x, %02x\n",
-			     etd->samples[0], etd->samples[1], etd->samples[2]);
+			     info->samples[0],
+			     info->samples[1],
+			     info->samples[2]);
 	}
 
-	if (etd->samples[1] == 0x74 && etd->hw_version == 0x03) {
+	if (info->samples[1] == 0x74 && info->hw_version == 0x03) {
 		/*
 		 * This module has a bug which makes absolute mode
 		 * unusable, so let's abort so we'll be using standard
@@ -1715,16 +1719,181 @@ int elantech_init(struct psmouse *psmouse)
 		 */
 		psmouse_info(psmouse,
 			     "absolute mode broken, forcing standard PS/2 protocol\n");
+		return -ENODEV;
+	}
+
+	/* The MSB indicates the presence of the trackpoint */
+	info->has_trackpoint = (info->capabilities[0] & 0x80) == 0x80;
+
+	info->x_res = 31;
+	info->y_res = 31;
+	if (info->hw_version == 4) {
+		if (elantech_get_resolution_v4(psmouse,
+					       &info->x_res,
+					       &info->y_res,
+					       &info->bus)) {
+			psmouse_warn(psmouse,
+				     "failed to query resolution data.\n");
+		}
+	}
+
+	return 0;
+}
+
+#if defined(CONFIG_MOUSE_PS2_ELANTECH_SMBUS)
+
+/*
+ * The newest Elantech device can use a secondary bus (over SMBus) which
+ * provides a better bandwidth and allow a better control of the touchpads.
+ * This is used to decide if we need to use this bus or not.
+ */
+enum {
+	ELANTECH_SMBUS_NOT_SET = -1,
+	ELANTECH_SMBUS_OFF,
+	ELANTECH_SMBUS_ON,
+};
+
+static int elantech_smbus = IS_ENABLED(CONFIG_MOUSE_ELAN_I2C_SMBUS) ?
+		ELANTECH_SMBUS_NOT_SET : ELANTECH_SMBUS_OFF;
+module_param_named(elantech_smbus, elantech_smbus, int, 0644);
+MODULE_PARM_DESC(elantech_smbus, "Use a secondary bus for the Elantech device.");
+
+static int elantech_create_smbus(struct psmouse *psmouse,
+				 struct elantech_device_info *info,
+				 bool leave_breadcrumbs)
+{
+	const struct property_entry i2c_properties[] = {
+		PROPERTY_ENTRY_BOOL("elan,trackpoint"),
+		{ },
+	};
+	struct i2c_board_info smbus_board = {
+		I2C_BOARD_INFO("elan_i2c", 0x15),
+		.flags = I2C_CLIENT_HOST_NOTIFY,
+	};
+
+	if (info->has_trackpoint)
+		smbus_board.properties = i2c_properties;
+
+	return psmouse_smbus_init(psmouse, &smbus_board, NULL, 0, false,
+				  leave_breadcrumbs);
+}
+
+/**
+ * elantech_setup_smbus - called once the PS/2 devices are enumerated
+ * and decides to instantiate a SMBus InterTouch device.
+ */
+static int elantech_setup_smbus(struct psmouse *psmouse,
+				struct elantech_device_info *info,
+				bool leave_breadcrumbs)
+{
+	int error;
+
+	if (elantech_smbus == ELANTECH_SMBUS_OFF)
+		return -ENXIO;
+
+	if (elantech_smbus == ELANTECH_SMBUS_NOT_SET) {
+		/*
+		 * New ICs are enabled by default.
+		 * Old ICs are up to the user to decide.
+		 */
+		if (!ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version))
+			return -ENXIO;
+	}
+
+	psmouse_info(psmouse, "Trying to set up SMBus access\n");
+
+	error = elantech_create_smbus(psmouse, info, leave_breadcrumbs);
+	if (error) {
+		if (error == -EAGAIN)
+			psmouse_info(psmouse, "SMbus companion is not ready yet\n");
+		else
+			psmouse_err(psmouse, "unable to create intertouch device\n");
+
+		return error;
+	}
+
+	return 0;
+}
+
+static bool elantech_use_host_notify(struct psmouse *psmouse,
+				     struct elantech_device_info *info)
+{
+	if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version))
+		return true;
+
+	switch (info->bus) {
+	case ETP_BUS_PS2_ONLY:
+		/* expected case */
+		break;
+	case ETP_BUS_SMB_ALERT_ONLY:
+		/* fall-through  */
+	case ETP_BUS_PS2_SMB_ALERT:
+		psmouse_dbg(psmouse, "Ignoring SMBus provider through alert protocol.\n");
+		break;
+	case ETP_BUS_SMB_HST_NTFY_ONLY:
+		/* fall-through  */
+	case ETP_BUS_PS2_SMB_HST_NTFY:
+		return true;
+	default:
+		psmouse_dbg(psmouse,
+			    "Ignoring SMBus bus provider %d.\n",
+			    info->bus);
+	}
+
+	return false;
+}
+
+int elantech_init_smbus(struct psmouse *psmouse)
+{
+	struct elantech_device_info info;
+	int error = -EINVAL;
+
+	psmouse_reset(psmouse);
+
+	error = elantech_query_info(psmouse, &info);
+	if (error)
+		goto init_fail;
+
+	if (info.hw_version < 4) {
+		error = -ENXIO;
 		goto init_fail;
 	}
 
+	return elantech_create_smbus(psmouse, &info, false);
+ init_fail:
+	psmouse_reset(psmouse);
+	return error;
+}
+#endif /* CONFIG_MOUSE_PS2_ELANTECH_SMBUS */
+
+/*
+ * Initialize the touchpad and create sysfs entries
+ */
+static int elantech_setup_ps2(struct psmouse *psmouse,
+			      struct elantech_device_info *info)
+{
+	struct elantech_data *etd;
+	int i;
+	int error = -EINVAL;
+	struct input_dev *tp_dev;
+
+	psmouse->private = etd = kzalloc(sizeof(*etd), GFP_KERNEL);
+	if (!etd)
+		return -ENOMEM;
+
+	etd->info = *info;
+
+	etd->parity[0] = 1;
+	for (i = 1; i < 256; i++)
+		etd->parity[i] = etd->parity[i & (i - 1)] ^ 1;
+
 	if (elantech_set_absolute_mode(psmouse)) {
 		psmouse_err(psmouse,
 			    "failed to put touchpad into absolute mode.\n");
 		goto init_fail;
 	}
 
-	if (etd->fw_version == 0x381f17) {
+	if (info->fw_version == 0x381f17) {
 		etd->original_set_rate = psmouse->set_rate;
 		psmouse->set_rate = elantech_set_rate_restore_reg_07;
 	}
@@ -1743,8 +1912,7 @@ int elantech_init(struct psmouse *psmouse)
 		goto init_fail;
 	}
 
-	/* The MSB indicates the presence of the trackpoint */
-	if ((etd->capabilities[0] & 0x80) == 0x80) {
+	if (info->has_trackpoint) {
 		tp_dev = input_allocate_device();
 
 		if (!tp_dev) {
@@ -1780,7 +1948,7 @@ int elantech_init(struct psmouse *psmouse)
 	psmouse->protocol_handler = elantech_process_byte;
 	psmouse->disconnect = elantech_disconnect;
 	psmouse->reconnect = elantech_reconnect;
-	psmouse->pktsize = etd->hw_version > 1 ? 6 : 4;
+	psmouse->pktsize = info->hw_version > 1 ? 6 : 4;
 
 	return 0;
  init_fail_tp_reg:
@@ -1789,7 +1957,70 @@ int elantech_init(struct psmouse *psmouse)
 	sysfs_remove_group(&psmouse->ps2dev.serio->dev.kobj,
 			   &elantech_attr_group);
  init_fail:
-	psmouse_reset(psmouse);
 	kfree(etd);
 	return error;
 }
+
+int elantech_init_ps2(struct psmouse *psmouse)
+{
+	struct elantech_device_info info;
+	int error = -EINVAL;
+
+	psmouse_reset(psmouse);
+
+	error = elantech_query_info(psmouse, &info);
+	if (error)
+		goto init_fail;
+
+	error = elantech_setup_ps2(psmouse, &info);
+	if (error)
+		goto init_fail;
+
+	return 0;
+ init_fail:
+	psmouse_reset(psmouse);
+	return error;
+}
+
+int elantech_init(struct psmouse *psmouse)
+{
+	struct elantech_device_info info;
+	int error = -EINVAL;
+
+	psmouse_reset(psmouse);
+
+	error = elantech_query_info(psmouse, &info);
+	if (error)
+		goto init_fail;
+
+#if defined(CONFIG_MOUSE_PS2_ELANTECH_SMBUS)
+
+	if (elantech_use_host_notify(psmouse, &info)) {
+		if (!IS_ENABLED(CONFIG_MOUSE_ELAN_I2C_SMBUS) ||
+		    !IS_ENABLED(CONFIG_MOUSE_PS2_ELANTECH_SMBUS)) {
+			psmouse_warn(psmouse,
+				     "The touchpad can support a better bus than the too old PS/2 protocol. "
+				     "Make sure MOUSE_PS2_ELANTECH_SMBUS and MOUSE_ELAN_I2C_SMBUS are enabled to get a better touchpad experience.\n");
+		}
+		error = elantech_setup_smbus(psmouse, &info, true);
+		if (!error)
+			return PSMOUSE_ELANTECH_SMBUS;
+	}
+
+#endif /* CONFIG_MOUSE_PS2_ELANTECH_SMBUS */
+
+	error = elantech_setup_ps2(psmouse, &info);
+	if (error < 0) {
+		/*
+		 * Not using any flavor of Elantech support, so clean up
+		 * SMbus breadcrumbs, if any.
+		 */
+		psmouse_smbus_cleanup(psmouse);
+		goto init_fail;
+	}
+
+	return PSMOUSE_ELANTECH;
+ init_fail:
+	psmouse_reset(psmouse);
+	return error;
+}
diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h
index e1cbf409d9c8..119727085a60 100644
--- a/drivers/input/mouse/elantech.h
+++ b/drivers/input/mouse/elantech.h
@@ -107,6 +107,30 @@
 #define ETP_WEIGHT_VALUE		5
 
 /*
+ * Bus information on 3rd byte of query ETP_RESOLUTION_QUERY(0x04)
+ */
+#define ETP_BUS_PS2_ONLY		0
+#define ETP_BUS_SMB_ALERT_ONLY		1
+#define ETP_BUS_SMB_HST_NTFY_ONLY	2
+#define ETP_BUS_PS2_SMB_ALERT		3
+#define ETP_BUS_PS2_SMB_HST_NTFY	4
+
+/*
+ * New ICs are either using SMBus Host Notify or just plain PS2.
+ *
+ * ETP_FW_VERSION_QUERY is:
+ * Byte 1:
+ *  - bit 0..3: IC BODY
+ * Byte 2:
+ *  - bit 4: HiddenButton
+ *  - bit 5: PS2_SMBUS_NOTIFY
+ *  - bit 6: PS2CRCCheck
+ */
+#define ETP_NEW_IC_SMBUS_HOST_NOTIFY(fw_version)	\
+		((((fw_version) & 0x0f2000) == 0x0f2000) && \
+		 ((fw_version) & 0x0000ff) > 0)
+
+/*
  * The base position for one finger, v4 hardware
  */
 struct finger_pos {
@@ -114,6 +138,25 @@ struct finger_pos {
 	unsigned int y;
 };
 
+struct elantech_device_info {
+	unsigned char capabilities[3];
+	unsigned char samples[3];
+	unsigned char debug;
+	unsigned char hw_version;
+	unsigned int fw_version;
+	unsigned int x_res;
+	unsigned int y_res;
+	unsigned int bus;
+	bool paritycheck;
+	bool jumpy_cursor;
+	bool reports_pressure;
+	bool crc_enabled;
+	bool set_hw_resolution;
+	bool has_trackpoint;
+	int (*send_cmd)(struct psmouse *psmouse, unsigned char c,
+			unsigned char *param);
+};
+
 struct elantech_data {
 	struct input_dev *tp_dev;	/* Relative device for trackpoint */
 	char tp_phys[32];
@@ -127,27 +170,18 @@ struct elantech_data {
 	unsigned char reg_24;
 	unsigned char reg_25;
 	unsigned char reg_26;
-	unsigned char debug;
-	unsigned char capabilities[3];
-	unsigned char samples[3];
-	bool paritycheck;
-	bool jumpy_cursor;
-	bool reports_pressure;
-	bool crc_enabled;
-	bool set_hw_resolution;
-	unsigned char hw_version;
-	unsigned int fw_version;
 	unsigned int single_finger_reports;
 	unsigned int y_max;
 	unsigned int width;
 	struct finger_pos mt[ETP_MAX_FINGERS];
 	unsigned char parity[256];
-	int (*send_cmd)(struct psmouse *psmouse, unsigned char c, unsigned char *param);
+	struct elantech_device_info info;
 	void (*original_set_rate)(struct psmouse *psmouse, unsigned int rate);
 };
 
 #ifdef CONFIG_MOUSE_PS2_ELANTECH
 int elantech_detect(struct psmouse *psmouse, bool set_properties);
+int elantech_init_ps2(struct psmouse *psmouse);
 int elantech_init(struct psmouse *psmouse);
 #else
 static inline int elantech_detect(struct psmouse *psmouse, bool set_properties)
@@ -158,6 +192,19 @@ static inline int elantech_init(struct psmouse *psmouse)
 {
 	return -ENOSYS;
 }
+static inline int elantech_init_ps2(struct psmouse *psmouse)
+{
+	return -ENOSYS;
+}
 #endif /* CONFIG_MOUSE_PS2_ELANTECH */
 
+#if defined(CONFIG_MOUSE_PS2_ELANTECH_SMBUS)
+int elantech_init_smbus(struct psmouse *psmouse);
+#else
+static inline int elantech_init_smbus(struct psmouse *psmouse)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_MOUSE_PS2_ELANTECH_SMBUS */
+
 #endif
diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c
index 8900c3166ebf..5ff5b1952be0 100644
--- a/drivers/input/mouse/psmouse-base.c
+++ b/drivers/input/mouse/psmouse-base.c
@@ -856,7 +856,17 @@ static const struct psmouse_protocol psmouse_protocols[] = {
 		.name		= "ETPS/2",
 		.alias		= "elantech",
 		.detect		= elantech_detect,
-		.init		= elantech_init,
+		.init		= elantech_init_ps2,
+	},
+#endif
+#ifdef CONFIG_MOUSE_PS2_ELANTECH_SMBUS
+	{
+		.type		= PSMOUSE_ELANTECH_SMBUS,
+		.name		= "ETSMBus",
+		.alias		= "elantech-smbus",
+		.detect		= elantech_detect,
+		.init		= elantech_init_smbus,
+		.smbus_companion = true,
 	},
 #endif
 #ifdef CONFIG_MOUSE_PS2_SENTELIC
@@ -1158,8 +1168,13 @@ static int psmouse_extensions(struct psmouse *psmouse,
 	/* Try Elantech touchpad */
 	if (max_proto > PSMOUSE_IMEX &&
 	    psmouse_try_protocol(psmouse, PSMOUSE_ELANTECH,
-				 &max_proto, set_properties, true)) {
-		return PSMOUSE_ELANTECH;
+				 &max_proto, set_properties, false)) {
+		if (!set_properties)
+			return PSMOUSE_ELANTECH;
+
+		ret = elantech_init(psmouse);
+		if (ret >= 0)
+			return ret;
 	}
 
 	if (max_proto > PSMOUSE_IMEX) {
diff --git a/drivers/input/mouse/psmouse-smbus.c b/drivers/input/mouse/psmouse-smbus.c
index c7ac24d119c1..852d4b486ddb 100644
--- a/drivers/input/mouse/psmouse-smbus.c
+++ b/drivers/input/mouse/psmouse-smbus.c
@@ -23,6 +23,7 @@ struct psmouse_smbus_dev {
 	struct i2c_client *client;
 	struct list_head node;
 	bool dead;
+	bool need_deactivate;
 };
 
 static LIST_HEAD(psmouse_smbus_list);
@@ -118,7 +119,10 @@ static psmouse_ret_t psmouse_smbus_process_byte(struct psmouse *psmouse)
 
 static int psmouse_smbus_reconnect(struct psmouse *psmouse)
 {
-	psmouse_deactivate(psmouse);
+	struct psmouse_smbus_dev *smbdev = psmouse->private;
+
+	if (smbdev->need_deactivate)
+		psmouse_deactivate(psmouse);
 
 	return 0;
 }
@@ -225,6 +229,7 @@ void psmouse_smbus_cleanup(struct psmouse *psmouse)
 int psmouse_smbus_init(struct psmouse *psmouse,
 		       const struct i2c_board_info *board,
 		       const void *pdata, size_t pdata_size,
+		       bool need_deactivate,
 		       bool leave_breadcrumbs)
 {
 	struct psmouse_smbus_dev *smbdev;
@@ -236,13 +241,20 @@ int psmouse_smbus_init(struct psmouse *psmouse,
 
 	smbdev->psmouse = psmouse;
 	smbdev->board = *board;
+	smbdev->need_deactivate = need_deactivate;
 
-	smbdev->board.platform_data = kmemdup(pdata, pdata_size, GFP_KERNEL);
-	if (!smbdev->board.platform_data) {
-		kfree(smbdev);
-		return -ENOMEM;
+	if (pdata) {
+		smbdev->board.platform_data = kmemdup(pdata, pdata_size,
+						      GFP_KERNEL);
+		if (!smbdev->board.platform_data) {
+			kfree(smbdev);
+			return -ENOMEM;
+		}
 	}
 
+	if (need_deactivate)
+		psmouse_deactivate(psmouse);
+
 	psmouse->private = smbdev;
 	psmouse->protocol_handler = psmouse_smbus_process_byte;
 	psmouse->reconnect = psmouse_smbus_reconnect;
@@ -250,8 +262,6 @@ int psmouse_smbus_init(struct psmouse *psmouse,
 	psmouse->disconnect = psmouse_smbus_disconnect;
 	psmouse->resync_time = 0;
 
-	psmouse_deactivate(psmouse);
-
 	mutex_lock(&psmouse_smbus_mutex);
 	list_add_tail(&smbdev->node, &psmouse_smbus_list);
 	mutex_unlock(&psmouse_smbus_mutex);
diff --git a/drivers/input/mouse/psmouse.h b/drivers/input/mouse/psmouse.h
index 71ac50082c8b..64c3a5d3fb3e 100644
--- a/drivers/input/mouse/psmouse.h
+++ b/drivers/input/mouse/psmouse.h
@@ -68,6 +68,7 @@ enum psmouse_type {
 	PSMOUSE_VMMOUSE,
 	PSMOUSE_BYD,
 	PSMOUSE_SYNAPTICS_SMBUS,
+	PSMOUSE_ELANTECH_SMBUS,
 	PSMOUSE_AUTO		/* This one should always be last */
 };
 
@@ -224,6 +225,7 @@ struct i2c_board_info;
 int psmouse_smbus_init(struct psmouse *psmouse,
 		       const struct i2c_board_info *board,
 		       const void *pdata, size_t pdata_size,
+		       bool need_deactivate,
 		       bool leave_breadcrumbs);
 void psmouse_smbus_cleanup(struct psmouse *psmouse);
 
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 60f2c463d1cc..55d33500d55e 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -172,6 +172,12 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN0048", /* X1 Carbon 3 */
 	"LEN0046", /* X250 */
 	"LEN004a", /* W541 */
+	"LEN0071", /* T480 */
+	"LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */
+	"LEN0073", /* X1 Carbon G5 (Elantech) */
+	"LEN0092", /* X1 Carbon 6 */
+	"LEN0096", /* X280 */
+	"LEN0097", /* X280 -> ALPS trackpoint */
 	"LEN200f", /* T450s */
 	NULL
 };
@@ -1748,7 +1754,7 @@ static int synaptics_create_intertouch(struct psmouse *psmouse,
 	};
 
 	return psmouse_smbus_init(psmouse, &intertouch_board,
-				  &pdata, sizeof(pdata),
+				  &pdata, sizeof(pdata), true,
 				  leave_breadcrumbs);
 }
 
diff --git a/drivers/input/rmi4/rmi_spi.c b/drivers/input/rmi4/rmi_spi.c
index 76edbf2c1bce..082defc329a8 100644
--- a/drivers/input/rmi4/rmi_spi.c
+++ b/drivers/input/rmi4/rmi_spi.c
@@ -147,8 +147,11 @@ static int rmi_spi_xfer(struct rmi_spi_xport *rmi_spi,
 	if (len > RMI_SPI_XFER_SIZE_LIMIT)
 		return -EINVAL;
 
-	if (rmi_spi->xfer_buf_size < len)
-		rmi_spi_manage_pools(rmi_spi, len);
+	if (rmi_spi->xfer_buf_size < len) {
+		ret = rmi_spi_manage_pools(rmi_spi, len);
+		if (ret < 0)
+			return ret;
+	}
 
 	if (addr == 0)
 		/*
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index 4f15496fec8b..32267c1afebc 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -164,6 +164,17 @@ config TOUCHSCREEN_CHIPONE_ICN8318
 	  To compile this driver as a module, choose M here: the
 	  module will be called chipone_icn8318.
 
+config TOUCHSCREEN_CHIPONE_ICN8505
+	tristate "chipone icn8505 touchscreen controller"
+	depends on I2C && ACPI
+	help
+	  Say Y here if you have a ChipOne icn8505 based I2C touchscreen.
+
+	  If unsure, say N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called chipone_icn8505.
+
 config TOUCHSCREEN_CY8CTMG110
 	tristate "cy8ctmg110 touchscreen"
 	depends on I2C
@@ -362,7 +373,7 @@ config TOUCHSCREEN_HIDEEP
 
 	  If unsure, say N.
 
-	  To compile this driver as a moudle, choose M here : the
+	  To compile this driver as a module, choose M here : the
 	  module will be called hideep_ts.
 
 config TOUCHSCREEN_ILI210X
diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile
index dddae7973436..fd4fd32fb73f 100644
--- a/drivers/input/touchscreen/Makefile
+++ b/drivers/input/touchscreen/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_TOUCHSCREEN_ATMEL_MXT)	+= atmel_mxt_ts.o
 obj-$(CONFIG_TOUCHSCREEN_AUO_PIXCIR)	+= auo-pixcir-ts.o
 obj-$(CONFIG_TOUCHSCREEN_BU21013)	+= bu21013_ts.o
 obj-$(CONFIG_TOUCHSCREEN_CHIPONE_ICN8318)	+= chipone_icn8318.o
+obj-$(CONFIG_TOUCHSCREEN_CHIPONE_ICN8505)	+= chipone_icn8505.o
 obj-$(CONFIG_TOUCHSCREEN_CY8CTMG110)	+= cy8ctmg110_ts.o
 obj-$(CONFIG_TOUCHSCREEN_CYTTSP_CORE)	+= cyttsp_core.o
 obj-$(CONFIG_TOUCHSCREEN_CYTTSP_I2C)	+= cyttsp_i2c.o cyttsp_i2c_common.o
diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index 5d9699fe1b55..54fe190fd4bc 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -194,6 +194,8 @@ enum t100_type {
 
 /* Delay times */
 #define MXT_BACKUP_TIME		50	/* msec */
+#define MXT_RESET_GPIO_TIME	20	/* msec */
+#define MXT_RESET_INVALID_CHG	100	/* msec */
 #define MXT_RESET_TIME		200	/* msec */
 #define MXT_RESET_TIMEOUT	3000	/* msec */
 #define MXT_CRC_TIMEOUT		1000	/* msec */
@@ -280,7 +282,8 @@ struct mxt_data {
 	struct input_dev *input_dev;
 	char phys[64];		/* device physical location */
 	struct mxt_object *object_table;
-	struct mxt_info info;
+	struct mxt_info *info;
+	void *raw_info_block;
 	unsigned int irq;
 	unsigned int max_x;
 	unsigned int max_y;
@@ -460,12 +463,13 @@ static int mxt_lookup_bootloader_address(struct mxt_data *data, bool retry)
 {
 	u8 appmode = data->client->addr;
 	u8 bootloader;
+	u8 family_id = data->info ? data->info->family_id : 0;
 
 	switch (appmode) {
 	case 0x4a:
 	case 0x4b:
 		/* Chips after 1664S use different scheme */
-		if (retry || data->info.family_id >= 0xa2) {
+		if (retry || family_id >= 0xa2) {
 			bootloader = appmode - 0x24;
 			break;
 		}
@@ -692,7 +696,7 @@ mxt_get_object(struct mxt_data *data, u8 type)
 	struct mxt_object *object;
 	int i;
 
-	for (i = 0; i < data->info.object_num; i++) {
+	for (i = 0; i < data->info->object_num; i++) {
 		object = data->object_table + i;
 		if (object->type == type)
 			return object;
@@ -1206,7 +1210,7 @@ static int mxt_soft_reset(struct mxt_data *data)
 		return ret;
 
 	/* Ignore CHG line for 100ms after reset */
-	msleep(100);
+	msleep(MXT_RESET_INVALID_CHG);
 
 	mxt_acquire_irq(data);
 
@@ -1462,12 +1466,12 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *cfg)
 		data_pos += offset;
 	}
 
-	if (cfg_info.family_id != data->info.family_id) {
+	if (cfg_info.family_id != data->info->family_id) {
 		dev_err(dev, "Family ID mismatch!\n");
 		return -EINVAL;
 	}
 
-	if (cfg_info.variant_id != data->info.variant_id) {
+	if (cfg_info.variant_id != data->info->variant_id) {
 		dev_err(dev, "Variant ID mismatch!\n");
 		return -EINVAL;
 	}
@@ -1512,7 +1516,7 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *cfg)
 
 	/* Malloc memory to store configuration */
 	cfg_start_ofs = MXT_OBJECT_START +
-			data->info.object_num * sizeof(struct mxt_object) +
+			data->info->object_num * sizeof(struct mxt_object) +
 			MXT_INFO_CHECKSUM_SIZE;
 	config_mem_size = data->mem_size - cfg_start_ofs;
 	config_mem = kzalloc(config_mem_size, GFP_KERNEL);
@@ -1563,20 +1567,6 @@ release_mem:
 	return ret;
 }
 
-static int mxt_get_info(struct mxt_data *data)
-{
-	struct i2c_client *client = data->client;
-	struct mxt_info *info = &data->info;
-	int error;
-
-	/* Read 7-byte info block starting at address 0 */
-	error = __mxt_read_reg(client, 0, sizeof(*info), info);
-	if (error)
-		return error;
-
-	return 0;
-}
-
 static void mxt_free_input_device(struct mxt_data *data)
 {
 	if (data->input_dev) {
@@ -1591,9 +1581,10 @@ static void mxt_free_object_table(struct mxt_data *data)
 	video_unregister_device(&data->dbg.vdev);
 	v4l2_device_unregister(&data->dbg.v4l2);
 #endif
-
-	kfree(data->object_table);
 	data->object_table = NULL;
+	data->info = NULL;
+	kfree(data->raw_info_block);
+	data->raw_info_block = NULL;
 	kfree(data->msg_buf);
 	data->msg_buf = NULL;
 	data->T5_address = 0;
@@ -1609,34 +1600,18 @@ static void mxt_free_object_table(struct mxt_data *data)
 	data->max_reportid = 0;
 }
 
-static int mxt_get_object_table(struct mxt_data *data)
+static int mxt_parse_object_table(struct mxt_data *data,
+				  struct mxt_object *object_table)
 {
 	struct i2c_client *client = data->client;
-	size_t table_size;
-	struct mxt_object *object_table;
-	int error;
 	int i;
 	u8 reportid;
 	u16 end_address;
 
-	table_size = data->info.object_num * sizeof(struct mxt_object);
-	object_table = kzalloc(table_size, GFP_KERNEL);
-	if (!object_table) {
-		dev_err(&data->client->dev, "Failed to allocate memory\n");
-		return -ENOMEM;
-	}
-
-	error = __mxt_read_reg(client, MXT_OBJECT_START, table_size,
-			object_table);
-	if (error) {
-		kfree(object_table);
-		return error;
-	}
-
 	/* Valid Report IDs start counting from 1 */
 	reportid = 1;
 	data->mem_size = 0;
-	for (i = 0; i < data->info.object_num; i++) {
+	for (i = 0; i < data->info->object_num; i++) {
 		struct mxt_object *object = object_table + i;
 		u8 min_id, max_id;
 
@@ -1660,8 +1635,8 @@ static int mxt_get_object_table(struct mxt_data *data)
 
 		switch (object->type) {
 		case MXT_GEN_MESSAGE_T5:
-			if (data->info.family_id == 0x80 &&
-			    data->info.version < 0x20) {
+			if (data->info->family_id == 0x80 &&
+			    data->info->version < 0x20) {
 				/*
 				 * On mXT224 firmware versions prior to V2.0
 				 * read and discard unused CRC byte otherwise
@@ -1716,24 +1691,102 @@ static int mxt_get_object_table(struct mxt_data *data)
 	/* If T44 exists, T5 position has to be directly after */
 	if (data->T44_address && (data->T5_address != data->T44_address + 1)) {
 		dev_err(&client->dev, "Invalid T44 position\n");
-		error = -EINVAL;
-		goto free_object_table;
+		return -EINVAL;
 	}
 
 	data->msg_buf = kcalloc(data->max_reportid,
 				data->T5_msg_size, GFP_KERNEL);
-	if (!data->msg_buf) {
-		dev_err(&client->dev, "Failed to allocate message buffer\n");
+	if (!data->msg_buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int mxt_read_info_block(struct mxt_data *data)
+{
+	struct i2c_client *client = data->client;
+	int error;
+	size_t size;
+	void *id_buf, *buf;
+	uint8_t num_objects;
+	u32 calculated_crc;
+	u8 *crc_ptr;
+
+	/* If info block already allocated, free it */
+	if (data->raw_info_block)
+		mxt_free_object_table(data);
+
+	/* Read 7-byte ID information block starting at address 0 */
+	size = sizeof(struct mxt_info);
+	id_buf = kzalloc(size, GFP_KERNEL);
+	if (!id_buf)
+		return -ENOMEM;
+
+	error = __mxt_read_reg(client, 0, size, id_buf);
+	if (error)
+		goto err_free_mem;
+
+	/* Resize buffer to give space for rest of info block */
+	num_objects = ((struct mxt_info *)id_buf)->object_num;
+	size += (num_objects * sizeof(struct mxt_object))
+		+ MXT_INFO_CHECKSUM_SIZE;
+
+	buf = krealloc(id_buf, size, GFP_KERNEL);
+	if (!buf) {
 		error = -ENOMEM;
-		goto free_object_table;
+		goto err_free_mem;
+	}
+	id_buf = buf;
+
+	/* Read rest of info block */
+	error = __mxt_read_reg(client, MXT_OBJECT_START,
+			       size - MXT_OBJECT_START,
+			       id_buf + MXT_OBJECT_START);
+	if (error)
+		goto err_free_mem;
+
+	/* Extract & calculate checksum */
+	crc_ptr = id_buf + size - MXT_INFO_CHECKSUM_SIZE;
+	data->info_crc = crc_ptr[0] | (crc_ptr[1] << 8) | (crc_ptr[2] << 16);
+
+	calculated_crc = mxt_calculate_crc(id_buf, 0,
+					   size - MXT_INFO_CHECKSUM_SIZE);
+
+	/*
+	 * CRC mismatch can be caused by data corruption due to I2C comms
+	 * issue or else device is not using Object Based Protocol (eg i2c-hid)
+	 */
+	if ((data->info_crc == 0) || (data->info_crc != calculated_crc)) {
+		dev_err(&client->dev,
+			"Info Block CRC error calculated=0x%06X read=0x%06X\n",
+			calculated_crc, data->info_crc);
+		error = -EIO;
+		goto err_free_mem;
+	}
+
+	data->raw_info_block = id_buf;
+	data->info = (struct mxt_info *)id_buf;
+
+	dev_info(&client->dev,
+		 "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n",
+		 data->info->family_id, data->info->variant_id,
+		 data->info->version >> 4, data->info->version & 0xf,
+		 data->info->build, data->info->object_num);
+
+	/* Parse object table information */
+	error = mxt_parse_object_table(data, id_buf + MXT_OBJECT_START);
+	if (error) {
+		dev_err(&client->dev, "Error %d parsing object table\n", error);
+		mxt_free_object_table(data);
+		goto err_free_mem;
 	}
 
-	data->object_table = object_table;
+	data->object_table = (struct mxt_object *)(id_buf + MXT_OBJECT_START);
 
 	return 0;
 
-free_object_table:
-	mxt_free_object_table(data);
+err_free_mem:
+	kfree(id_buf);
 	return error;
 }
 
@@ -2046,7 +2099,7 @@ static int mxt_initialize(struct mxt_data *data)
 	int error;
 
 	while (1) {
-		error = mxt_get_info(data);
+		error = mxt_read_info_block(data);
 		if (!error)
 			break;
 
@@ -2077,16 +2130,9 @@ static int mxt_initialize(struct mxt_data *data)
 		msleep(MXT_FW_RESET_TIME);
 	}
 
-	/* Get object table information */
-	error = mxt_get_object_table(data);
-	if (error) {
-		dev_err(&client->dev, "Error %d reading object table\n", error);
-		return error;
-	}
-
 	error = mxt_acquire_irq(data);
 	if (error)
-		goto err_free_object_table;
+		return error;
 
 	error = request_firmware_nowait(THIS_MODULE, true, MXT_CFG_NAME,
 					&client->dev, GFP_KERNEL, data,
@@ -2094,14 +2140,10 @@ static int mxt_initialize(struct mxt_data *data)
 	if (error) {
 		dev_err(&client->dev, "Failed to invoke firmware loader: %d\n",
 			error);
-		goto err_free_object_table;
+		return error;
 	}
 
 	return 0;
-
-err_free_object_table:
-	mxt_free_object_table(data);
-	return error;
 }
 
 static int mxt_set_t7_power_cfg(struct mxt_data *data, u8 sleep)
@@ -2162,7 +2204,7 @@ recheck:
 static u16 mxt_get_debug_value(struct mxt_data *data, unsigned int x,
 			       unsigned int y)
 {
-	struct mxt_info *info = &data->info;
+	struct mxt_info *info = data->info;
 	struct mxt_dbg *dbg = &data->dbg;
 	unsigned int ofs, page;
 	unsigned int col = 0;
@@ -2490,7 +2532,7 @@ static const struct video_device mxt_video_device = {
 
 static void mxt_debug_init(struct mxt_data *data)
 {
-	struct mxt_info *info = &data->info;
+	struct mxt_info *info = data->info;
 	struct mxt_dbg *dbg = &data->dbg;
 	struct mxt_object *object;
 	int error;
@@ -2576,7 +2618,6 @@ static int mxt_configure_objects(struct mxt_data *data,
 				 const struct firmware *cfg)
 {
 	struct device *dev = &data->client->dev;
-	struct mxt_info *info = &data->info;
 	int error;
 
 	error = mxt_init_t7_power_cfg(data);
@@ -2601,11 +2642,6 @@ static int mxt_configure_objects(struct mxt_data *data,
 
 	mxt_debug_init(data);
 
-	dev_info(dev,
-		 "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n",
-		 info->family_id, info->variant_id, info->version >> 4,
-		 info->version & 0xf, info->build, info->object_num);
-
 	return 0;
 }
 
@@ -2614,7 +2650,7 @@ static ssize_t mxt_fw_version_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
-	struct mxt_info *info = &data->info;
+	struct mxt_info *info = data->info;
 	return scnprintf(buf, PAGE_SIZE, "%u.%u.%02X\n",
 			 info->version >> 4, info->version & 0xf, info->build);
 }
@@ -2624,7 +2660,7 @@ static ssize_t mxt_hw_version_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
-	struct mxt_info *info = &data->info;
+	struct mxt_info *info = data->info;
 	return scnprintf(buf, PAGE_SIZE, "%u.%u\n",
 			 info->family_id, info->variant_id);
 }
@@ -2663,7 +2699,7 @@ static ssize_t mxt_object_show(struct device *dev,
 		return -ENOMEM;
 
 	error = 0;
-	for (i = 0; i < data->info.object_num; i++) {
+	for (i = 0; i < data->info->object_num; i++) {
 		object = data->object_table + i;
 
 		if (!mxt_object_readable(object->type))
@@ -2965,133 +3001,6 @@ static int mxt_parse_device_properties(struct mxt_data *data)
 	return 0;
 }
 
-#ifdef CONFIG_ACPI
-
-struct mxt_acpi_platform_data {
-	const char *hid;
-	const struct property_entry *props;
-};
-
-static unsigned int samus_touchpad_buttons[] = {
-	KEY_RESERVED,
-	KEY_RESERVED,
-	KEY_RESERVED,
-	BTN_LEFT
-};
-
-static const struct property_entry samus_touchpad_props[] = {
-	PROPERTY_ENTRY_U32_ARRAY("linux,gpio-keymap", samus_touchpad_buttons),
-	{ }
-};
-
-static struct mxt_acpi_platform_data samus_platform_data[] = {
-	{
-		/* Touchpad */
-		.hid	= "ATML0000",
-		.props	= samus_touchpad_props,
-	},
-	{
-		/* Touchscreen */
-		.hid	= "ATML0001",
-	},
-	{ }
-};
-
-static unsigned int chromebook_tp_buttons[] = {
-	KEY_RESERVED,
-	KEY_RESERVED,
-	KEY_RESERVED,
-	KEY_RESERVED,
-	KEY_RESERVED,
-	BTN_LEFT
-};
-
-static const struct property_entry chromebook_tp_props[] = {
-	PROPERTY_ENTRY_U32_ARRAY("linux,gpio-keymap", chromebook_tp_buttons),
-	{ }
-};
-
-static struct mxt_acpi_platform_data chromebook_platform_data[] = {
-	{
-		/* Touchpad */
-		.hid	= "ATML0000",
-		.props	= chromebook_tp_props,
-	},
-	{
-		/* Touchscreen */
-		.hid	= "ATML0001",
-	},
-	{ }
-};
-
-static const struct dmi_system_id mxt_dmi_table[] = {
-	{
-		/* 2015 Google Pixel */
-		.ident = "Chromebook Pixel 2",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Samus"),
-		},
-		.driver_data = samus_platform_data,
-	},
-	{
-		/* Other Google Chromebooks */
-		.ident = "Chromebook",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
-		},
-		.driver_data = chromebook_platform_data,
-	},
-	{ }
-};
-
-static int mxt_prepare_acpi_properties(struct i2c_client *client)
-{
-	struct acpi_device *adev;
-	const struct dmi_system_id *system_id;
-	const struct mxt_acpi_platform_data *acpi_pdata;
-
-	adev = ACPI_COMPANION(&client->dev);
-	if (!adev)
-		return -ENOENT;
-
-	system_id = dmi_first_match(mxt_dmi_table);
-	if (!system_id)
-		return -ENOENT;
-
-	acpi_pdata = system_id->driver_data;
-	if (!acpi_pdata)
-		return -ENOENT;
-
-	while (acpi_pdata->hid) {
-		if (!strcmp(acpi_device_hid(adev), acpi_pdata->hid)) {
-			/*
-			 * Remove previously installed properties if we
-			 * are probing this device not for the very first
-			 * time.
-			 */
-			device_remove_properties(&client->dev);
-
-			/*
-			 * Now install the platform-specific properties
-			 * that are missing from ACPI.
-			 */
-			device_add_properties(&client->dev, acpi_pdata->props);
-			break;
-		}
-
-		acpi_pdata++;
-	}
-
-	return 0;
-}
-#else
-static int mxt_prepare_acpi_properties(struct i2c_client *client)
-{
-	return -ENOENT;
-}
-#endif
-
 static const struct dmi_system_id chromebook_T9_suspend_dmi[] = {
 	{
 		.matches = {
@@ -3113,6 +3022,18 @@ static int mxt_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	int error;
 
 	/*
+	 * Ignore devices that do not have device properties attached to
+	 * them, as we need help determining whether we are dealing with
+	 * touch screen or touchpad.
+	 *
+	 * So far on x86 the only users of Atmel touch controllers are
+	 * Chromebooks, and chromeos_laptop driver will ensure that
+	 * necessary properties are provided (if firmware does not do that).
+	 */
+	if (!device_property_present(&client->dev, "compatible"))
+		return -ENXIO;
+
+	/*
 	 * Ignore ACPI devices representing bootloader mode.
 	 *
 	 * This is a bit of a hack: Google Chromebook BIOS creates ACPI
@@ -3143,10 +3064,6 @@ static int mxt_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	data->suspend_mode = dmi_check_system(chromebook_T9_suspend_dmi) ?
 		MXT_SUSPEND_T9_CTRL : MXT_SUSPEND_DEEP_SLEEP;
 
-	error = mxt_prepare_acpi_properties(client);
-	if (error && error != -ENOENT)
-		return error;
-
 	error = mxt_parse_device_properties(data);
 	if (error)
 		return error;
@@ -3167,20 +3084,14 @@ static int mxt_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		return error;
 	}
 
+	disable_irq(client->irq);
+
 	if (data->reset_gpio) {
-		data->in_bootloader = true;
-		msleep(MXT_RESET_TIME);
-		reinit_completion(&data->bl_completion);
+		msleep(MXT_RESET_GPIO_TIME);
 		gpiod_set_value(data->reset_gpio, 1);
-		error = mxt_wait_for_completion(data, &data->bl_completion,
-						MXT_RESET_TIMEOUT);
-		if (error)
-			return error;
-		data->in_bootloader = false;
+		msleep(MXT_RESET_INVALID_CHG);
 	}
 
-	disable_irq(client->irq);
-
 	error = mxt_initialize(data);
 	if (error)
 		return error;
@@ -3254,6 +3165,11 @@ static SIMPLE_DEV_PM_OPS(mxt_pm_ops, mxt_suspend, mxt_resume);
 
 static const struct of_device_id mxt_of_match[] = {
 	{ .compatible = "atmel,maxtouch", },
+	/* Compatibles listed below are deprecated */
+	{ .compatible = "atmel,qt602240_ts", },
+	{ .compatible = "atmel,atmel_mxt_ts", },
+	{ .compatible = "atmel,atmel_mxt_tp", },
+	{ .compatible = "atmel,mXT224", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, mxt_of_match);
diff --git a/drivers/input/touchscreen/chipone_icn8505.c b/drivers/input/touchscreen/chipone_icn8505.c
new file mode 100644
index 000000000000..c768186ce856
--- /dev/null
+++ b/drivers/input/touchscreen/chipone_icn8505.c
@@ -0,0 +1,520 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Driver for ChipOne icn8505 i2c touchscreen controller
+ *
+ * Copyright (c) 2015-2018 Red Hat Inc.
+ *
+ * Red Hat authors:
+ * Hans de Goede <hdegoede@redhat.com>
+ */
+
+#include <asm/unaligned.h>
+#include <linux/acpi.h>
+#include <linux/crc32.h>
+#include <linux/delay.h>
+#include <linux/firmware.h>
+#include <linux/interrupt.h>
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/input/mt.h>
+#include <linux/input/touchscreen.h>
+#include <linux/module.h>
+
+/* Normal operation mode defines */
+#define ICN8505_REG_ADDR_WIDTH		16
+
+#define ICN8505_REG_POWER		0x0004
+#define ICN8505_REG_TOUCHDATA		0x1000
+#define ICN8505_REG_CONFIGDATA		0x8000
+
+/* ICN8505_REG_POWER commands */
+#define ICN8505_POWER_ACTIVE		0x00
+#define ICN8505_POWER_MONITOR		0x01
+#define ICN8505_POWER_HIBERNATE		0x02
+/*
+ * The Android driver uses these to turn on/off the charger filter, but the
+ * filter is way too aggressive making e.g. onscreen keyboards unusable.
+ */
+#define ICN8505_POWER_ENA_CHARGER_MODE	0x55
+#define ICN8505_POWER_DIS_CHARGER_MODE	0x66
+
+#define ICN8505_MAX_TOUCHES		10
+
+/* Programming mode defines */
+#define ICN8505_PROG_I2C_ADDR		0x30
+#define ICN8505_PROG_REG_ADDR_WIDTH	24
+
+#define MAX_FW_UPLOAD_TRIES		3
+
+struct icn8505_touch {
+	u8 slot;
+	u8 x[2];
+	u8 y[2];
+	u8 pressure;	/* Seems more like finger width then pressure really */
+	u8 event;
+/* The difference between 2 and 3 is unclear */
+#define ICN8505_EVENT_NO_DATA	1 /* No finger seen yet since wakeup */
+#define ICN8505_EVENT_UPDATE1	2 /* New or updated coordinates */
+#define ICN8505_EVENT_UPDATE2	3 /* New or updated coordinates */
+#define ICN8505_EVENT_END	4 /* Finger lifted */
+} __packed;
+
+struct icn8505_touch_data {
+	u8 softbutton;
+	u8 touch_count;
+	struct icn8505_touch touches[ICN8505_MAX_TOUCHES];
+} __packed;
+
+struct icn8505_data {
+	struct i2c_client *client;
+	struct input_dev *input;
+	struct gpio_desc *wake_gpio;
+	struct touchscreen_properties prop;
+	char firmware_name[32];
+};
+
+static int icn8505_read_xfer(struct i2c_client *client, u16 i2c_addr,
+			     int reg_addr, int reg_addr_width,
+			     void *data, int len, bool silent)
+{
+	u8 buf[3];
+	int i, ret;
+	struct i2c_msg msg[2] = {
+		{
+			.addr = i2c_addr,
+			.buf = buf,
+			.len = reg_addr_width / 8,
+		},
+		{
+			.addr = i2c_addr,
+			.flags = I2C_M_RD,
+			.buf = data,
+			.len = len,
+		}
+	};
+
+	for (i = 0; i < (reg_addr_width / 8); i++)
+		buf[i] = (reg_addr >> (reg_addr_width - (i + 1) * 8)) & 0xff;
+
+	ret = i2c_transfer(client->adapter, msg, 2);
+	if (ret != ARRAY_SIZE(msg)) {
+		if (ret >= 0)
+			ret = -EIO;
+		if (!silent)
+			dev_err(&client->dev,
+				"Error reading addr %#x reg %#x: %d\n",
+				i2c_addr, reg_addr, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int icn8505_write_xfer(struct i2c_client *client, u16 i2c_addr,
+			      int reg_addr, int reg_addr_width,
+			      const void *data, int len, bool silent)
+{
+	u8 buf[3 + 32]; /* 3 bytes for 24 bit reg-addr + 32 bytes max len */
+	int i, ret;
+	struct i2c_msg msg = {
+		.addr = i2c_addr,
+		.buf = buf,
+		.len = reg_addr_width / 8 + len,
+	};
+
+	if (WARN_ON(len > 32))
+		return -EINVAL;
+
+	for (i = 0; i < (reg_addr_width / 8); i++)
+		buf[i] = (reg_addr >> (reg_addr_width - (i + 1) * 8)) & 0xff;
+
+	memcpy(buf + reg_addr_width / 8, data, len);
+
+	ret = i2c_transfer(client->adapter, &msg, 1);
+	if (ret != 1) {
+		if (ret >= 0)
+			ret = -EIO;
+		if (!silent)
+			dev_err(&client->dev,
+				"Error writing addr %#x reg %#x: %d\n",
+				i2c_addr, reg_addr, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int icn8505_read_data(struct icn8505_data *icn8505, int reg,
+			     void *buf, int len)
+{
+	return icn8505_read_xfer(icn8505->client, icn8505->client->addr, reg,
+				 ICN8505_REG_ADDR_WIDTH, buf, len, false);
+}
+
+static int icn8505_read_reg_silent(struct icn8505_data *icn8505, int reg)
+{
+	u8 buf;
+	int error;
+
+	error = icn8505_read_xfer(icn8505->client, icn8505->client->addr, reg,
+				  ICN8505_REG_ADDR_WIDTH, &buf, 1, true);
+	if (error)
+		return error;
+
+	return buf;
+}
+
+static int icn8505_write_reg(struct icn8505_data *icn8505, int reg, u8 val)
+{
+	return icn8505_write_xfer(icn8505->client, icn8505->client->addr, reg,
+				  ICN8505_REG_ADDR_WIDTH, &val, 1, false);
+}
+
+static int icn8505_read_prog_data(struct icn8505_data *icn8505, int reg,
+				  void *buf, int len)
+{
+	return icn8505_read_xfer(icn8505->client, ICN8505_PROG_I2C_ADDR, reg,
+				 ICN8505_PROG_REG_ADDR_WIDTH, buf, len, false);
+}
+
+static int icn8505_write_prog_data(struct icn8505_data *icn8505, int reg,
+				   const void *buf, int len)
+{
+	return icn8505_write_xfer(icn8505->client, ICN8505_PROG_I2C_ADDR, reg,
+				  ICN8505_PROG_REG_ADDR_WIDTH, buf, len, false);
+}
+
+static int icn8505_write_prog_reg(struct icn8505_data *icn8505, int reg, u8 val)
+{
+	return icn8505_write_xfer(icn8505->client, ICN8505_PROG_I2C_ADDR, reg,
+				  ICN8505_PROG_REG_ADDR_WIDTH, &val, 1, false);
+}
+
+/*
+ * Note this function uses a number of magic register addresses and values,
+ * there are deliberately no defines for these because the algorithm is taken
+ * from the icn85xx Android driver and I do not want to make up possibly wrong
+ * names for the addresses and/or values.
+ */
+static int icn8505_try_fw_upload(struct icn8505_data *icn8505,
+				 const struct firmware *fw)
+{
+	struct device *dev = &icn8505->client->dev;
+	size_t offset, count;
+	int error;
+	u8 buf[4];
+	u32 crc;
+
+	/* Put the controller in programming mode */
+	error = icn8505_write_prog_reg(icn8505, 0xcc3355, 0x5a);
+	if (error)
+		return error;
+
+	usleep_range(2000, 5000);
+
+	error = icn8505_write_prog_reg(icn8505, 0x040400, 0x01);
+	if (error)
+		return error;
+
+	usleep_range(2000, 5000);
+
+	error = icn8505_read_prog_data(icn8505, 0x040002, buf, 1);
+	if (error)
+		return error;
+
+	if (buf[0] != 0x85) {
+		dev_err(dev, "Failed to enter programming mode\n");
+		return -ENODEV;
+	}
+
+	usleep_range(1000, 5000);
+
+	/* Enable CRC mode */
+	error = icn8505_write_prog_reg(icn8505, 0x40028, 1);
+	if (error)
+		return error;
+
+	/* Send the firmware to SRAM */
+	for (offset = 0; offset < fw->size; offset += count) {
+		count = min_t(size_t, fw->size - offset, 32);
+		error = icn8505_write_prog_data(icn8505, offset,
+					      fw->data + offset, count);
+		if (error)
+			return error;
+	}
+
+	/* Disable CRC mode */
+	error = icn8505_write_prog_reg(icn8505, 0x40028, 0);
+	if (error)
+		return error;
+
+	/* Get and check length and CRC */
+	error = icn8505_read_prog_data(icn8505, 0x40034, buf, 2);
+	if (error)
+		return error;
+
+	if (get_unaligned_le16(buf) != fw->size) {
+		dev_warn(dev, "Length mismatch after uploading fw\n");
+		return -EIO;
+	}
+
+	error = icn8505_read_prog_data(icn8505, 0x4002c, buf, 4);
+	if (error)
+		return error;
+
+	crc = crc32_be(0, fw->data, fw->size);
+	if (get_unaligned_le32(buf) != crc) {
+		dev_warn(dev, "CRC mismatch after uploading fw\n");
+		return -EIO;
+	}
+
+	/* Boot controller from SRAM */
+	error = icn8505_write_prog_reg(icn8505, 0x40400, 0x03);
+	if (error)
+		return error;
+
+	usleep_range(2000, 5000);
+	return 0;
+}
+
+static int icn8505_upload_fw(struct icn8505_data *icn8505)
+{
+	struct device *dev = &icn8505->client->dev;
+	const struct firmware *fw;
+	int i, error;
+
+	/*
+	 * Always load the firmware, even if we don't need it at boot, we
+	 * we may need it at resume. Having loaded it once will make the
+	 * firmware class code cache it at suspend/resume.
+	 */
+	error = request_firmware(&fw, icn8505->firmware_name, dev);
+	if (error) {
+		dev_err(dev, "Firmware request error %d\n", error);
+		return error;
+	}
+
+	/* Check if the controller is not already up and running */
+	if (icn8505_read_reg_silent(icn8505, 0x000a) == 0x85)
+		goto success;
+
+	for (i = 1; i <= MAX_FW_UPLOAD_TRIES; i++) {
+		error = icn8505_try_fw_upload(icn8505, fw);
+		if (!error)
+			goto success;
+
+		dev_err(dev, "Failed to upload firmware: %d (attempt %d/%d)\n",
+			error, i, MAX_FW_UPLOAD_TRIES);
+		usleep_range(2000, 5000);
+	}
+
+success:
+	release_firmware(fw);
+	return error;
+}
+
+static bool icn8505_touch_active(u8 event)
+{
+	return event == ICN8505_EVENT_UPDATE1 ||
+	       event == ICN8505_EVENT_UPDATE2;
+}
+
+static irqreturn_t icn8505_irq(int irq, void *dev_id)
+{
+	struct icn8505_data *icn8505 = dev_id;
+	struct device *dev = &icn8505->client->dev;
+	struct icn8505_touch_data touch_data;
+	int i, error;
+
+	error = icn8505_read_data(icn8505, ICN8505_REG_TOUCHDATA,
+				  &touch_data, sizeof(touch_data));
+	if (error) {
+		dev_err(dev, "Error reading touch data: %d\n", error);
+		return IRQ_HANDLED;
+	}
+
+	if (touch_data.touch_count > ICN8505_MAX_TOUCHES) {
+		dev_warn(dev, "Too many touches %d > %d\n",
+			 touch_data.touch_count, ICN8505_MAX_TOUCHES);
+		touch_data.touch_count = ICN8505_MAX_TOUCHES;
+	}
+
+	for (i = 0; i < touch_data.touch_count; i++) {
+		struct icn8505_touch *touch = &touch_data.touches[i];
+		bool act = icn8505_touch_active(touch->event);
+
+		input_mt_slot(icn8505->input, touch->slot);
+		input_mt_report_slot_state(icn8505->input, MT_TOOL_FINGER, act);
+		if (!act)
+			continue;
+
+		touchscreen_report_pos(icn8505->input, &icn8505->prop,
+				       get_unaligned_le16(touch->x),
+				       get_unaligned_le16(touch->y),
+				       true);
+	}
+
+	input_mt_sync_frame(icn8505->input);
+	input_report_key(icn8505->input, KEY_LEFTMETA,
+			 touch_data.softbutton == 1);
+	input_sync(icn8505->input);
+
+	return IRQ_HANDLED;
+}
+
+static int icn8505_probe_acpi(struct icn8505_data *icn8505, struct device *dev)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	const char *subsys = "unknown";
+	struct acpi_device *adev;
+	union acpi_object *obj;
+	acpi_status status;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return -ENODEV;
+
+	status = acpi_evaluate_object(adev->handle, "_SUB", NULL, &buffer);
+	if (ACPI_SUCCESS(status)) {
+		obj = buffer.pointer;
+		if (obj->type == ACPI_TYPE_STRING)
+			subsys = obj->string.pointer;
+		else
+			dev_warn(dev, "Warning ACPI _SUB did not return a string\n");
+	} else {
+		dev_warn(dev, "Warning ACPI _SUB failed: %#x\n", status);
+		buffer.pointer = NULL;
+	}
+
+	snprintf(icn8505->firmware_name, sizeof(icn8505->firmware_name),
+		 "chipone/icn8505-%s.fw", subsys);
+
+	kfree(buffer.pointer);
+	return 0;
+}
+
+static int icn8505_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct icn8505_data *icn8505;
+	struct input_dev *input;
+	__le16 resolution[2];
+	int error;
+
+	if (!client->irq) {
+		dev_err(dev, "No irq specified\n");
+		return -EINVAL;
+	}
+
+	icn8505 = devm_kzalloc(dev, sizeof(*icn8505), GFP_KERNEL);
+	if (!icn8505)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(dev);
+	if (!input)
+		return -ENOMEM;
+
+	input->name = client->name;
+	input->id.bustype = BUS_I2C;
+
+	input_set_capability(input, EV_ABS, ABS_MT_POSITION_X);
+	input_set_capability(input, EV_ABS, ABS_MT_POSITION_Y);
+	input_set_capability(input, EV_KEY, KEY_LEFTMETA);
+
+	icn8505->client = client;
+	icn8505->input = input;
+	input_set_drvdata(input, icn8505);
+
+	error = icn8505_probe_acpi(icn8505, dev);
+	if (error)
+		return error;
+
+	error = icn8505_upload_fw(icn8505);
+	if (error)
+		return error;
+
+	error = icn8505_read_data(icn8505, ICN8505_REG_CONFIGDATA,
+				resolution, sizeof(resolution));
+	if (error) {
+		dev_err(dev, "Error reading resolution: %d\n", error);
+		return error;
+	}
+
+	input_set_abs_params(input, ABS_MT_POSITION_X, 0,
+			     le16_to_cpu(resolution[0]) - 1, 0, 0);
+	input_set_abs_params(input, ABS_MT_POSITION_Y, 0,
+			     le16_to_cpu(resolution[1]) - 1, 0, 0);
+
+	touchscreen_parse_properties(input, true, &icn8505->prop);
+	if (!input_abs_get_max(input, ABS_MT_POSITION_X) ||
+	    !input_abs_get_max(input, ABS_MT_POSITION_Y)) {
+		dev_err(dev, "Error touchscreen-size-x and/or -y missing\n");
+		return -EINVAL;
+	}
+
+	error = input_mt_init_slots(input, ICN8505_MAX_TOUCHES,
+				  INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED);
+	if (error)
+		return error;
+
+	error = devm_request_threaded_irq(dev, client->irq, NULL, icn8505_irq,
+					IRQF_ONESHOT, client->name, icn8505);
+	if (error) {
+		dev_err(dev, "Error requesting irq: %d\n", error);
+		return error;
+	}
+
+	error = input_register_device(input);
+	if (error)
+		return error;
+
+	i2c_set_clientdata(client, icn8505);
+	return 0;
+}
+
+static int __maybe_unused icn8505_suspend(struct device *dev)
+{
+	struct icn8505_data *icn8505 = i2c_get_clientdata(to_i2c_client(dev));
+
+	disable_irq(icn8505->client->irq);
+
+	icn8505_write_reg(icn8505, ICN8505_REG_POWER, ICN8505_POWER_HIBERNATE);
+
+	return 0;
+}
+
+static int __maybe_unused icn8505_resume(struct device *dev)
+{
+	struct icn8505_data *icn8505 = i2c_get_clientdata(to_i2c_client(dev));
+	int error;
+
+	error = icn8505_upload_fw(icn8505);
+	if (error)
+		return error;
+
+	enable_irq(icn8505->client->irq);
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(icn8505_pm_ops, icn8505_suspend, icn8505_resume);
+
+static const struct acpi_device_id icn8505_acpi_match[] = {
+	{ "CHPN0001" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, icn8505_acpi_match);
+
+static struct i2c_driver icn8505_driver = {
+	.driver = {
+		.name	= "chipone_icn8505",
+		.pm	= &icn8505_pm_ops,
+		.acpi_match_table = icn8505_acpi_match,
+	},
+	.probe_new = icn8505_probe,
+};
+
+module_i2c_driver(icn8505_driver);
+
+MODULE_DESCRIPTION("ChipOne icn8505 I2C Touchscreen Driver");
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index 9736c83dd418..f2d9c2c41885 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -933,6 +933,7 @@ MODULE_DEVICE_TABLE(i2c, goodix_ts_id);
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id goodix_acpi_match[] = {
 	{ "GDIX1001", 0 },
+	{ "GDIX1002", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, goodix_acpi_match);
diff --git a/drivers/input/touchscreen/mk712.c b/drivers/input/touchscreen/mk712.c
index bd5352824f77..c179060525ae 100644
--- a/drivers/input/touchscreen/mk712.c
+++ b/drivers/input/touchscreen/mk712.c
@@ -17,7 +17,7 @@
  * found in Gateway AOL Connected Touchpad computers.
  *
  * Documentation for ICS MK712 can be found at:
- *	http://www.idt.com/products/getDoc.cfm?docID=18713923
+ *	https://www.idt.com/general-parts/mk712-touch-screen-controller
  */
 
 /*
diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c
index f1043ae71dcc..b86c1e5fbc11 100644
--- a/drivers/input/touchscreen/ti_am335x_tsc.c
+++ b/drivers/input/touchscreen/ti_am335x_tsc.c
@@ -34,6 +34,8 @@
 #define SEQ_SETTLE		275
 #define MAX_12BIT		((1 << 12) - 1)
 
+#define TSC_IRQENB_MASK		(IRQENB_FIFO0THRES | IRQENB_EOS | IRQENB_HW_PEN)
+
 static const int config_pins[] = {
 	STEPCONFIG_XPP,
 	STEPCONFIG_XNN,
@@ -274,6 +276,7 @@ static irqreturn_t titsc_irq(int irq, void *dev)
 	if (status & IRQENB_HW_PEN) {
 		ts_dev->pen_down = true;
 		irqclr |= IRQENB_HW_PEN;
+		pm_stay_awake(ts_dev->mfd_tscadc->dev);
 	}
 
 	if (status & IRQENB_PENUP) {
@@ -283,6 +286,7 @@ static irqreturn_t titsc_irq(int irq, void *dev)
 			input_report_key(input_dev, BTN_TOUCH, 0);
 			input_report_abs(input_dev, ABS_PRESSURE, 0);
 			input_sync(input_dev);
+			pm_relax(ts_dev->mfd_tscadc->dev);
 		} else {
 			ts_dev->pen_down = true;
 		}
@@ -432,6 +436,7 @@ static int titsc_probe(struct platform_device *pdev)
 		goto err_free_mem;
 	}
 
+	titsc_writel(ts_dev, REG_IRQSTATUS, TSC_IRQENB_MASK);
 	titsc_writel(ts_dev, REG_IRQENABLE, IRQENB_FIFO0THRES);
 	titsc_writel(ts_dev, REG_IRQENABLE, IRQENB_EOS);
 	err = titsc_config_wires(ts_dev);
@@ -495,6 +500,7 @@ static int __maybe_unused titsc_suspend(struct device *dev)
 
 	tscadc_dev = ti_tscadc_dev_get(to_platform_device(dev));
 	if (device_may_wakeup(tscadc_dev->dev)) {
+		titsc_writel(ts_dev, REG_IRQSTATUS, TSC_IRQENB_MASK);
 		idle = titsc_readl(ts_dev, REG_IRQENABLE);
 		titsc_writel(ts_dev, REG_IRQENABLE,
 				(idle | IRQENB_HW_PEN));
@@ -513,6 +519,7 @@ static int __maybe_unused titsc_resume(struct device *dev)
 		titsc_writel(ts_dev, REG_IRQWAKEUP,
 				0x00);
 		titsc_writel(ts_dev, REG_IRQCLR, IRQENB_HW_PEN);
+		pm_relax(ts_dev->mfd_tscadc->dev);
 	}
 	titsc_step_config(ts_dev);
 	titsc_writel(ts_dev, REG_FIFO0THR,
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index c6cf90868503..d61570d64ee7 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -440,6 +440,8 @@ static int panjit_read_data(struct usbtouch_usb *dev, unsigned char *pkt)
 #define MTOUCHUSB_RESET                 7
 #define MTOUCHUSB_REQ_CTRLLR_ID         10
 
+#define MTOUCHUSB_REQ_CTRLLR_ID_LEN	16
+
 static int mtouch_read_data(struct usbtouch_usb *dev, unsigned char *pkt)
 {
 	if (hwcalib_xy) {
@@ -454,11 +456,93 @@ static int mtouch_read_data(struct usbtouch_usb *dev, unsigned char *pkt)
 	return 1;
 }
 
+struct mtouch_priv {
+	u8 fw_rev_major;
+	u8 fw_rev_minor;
+};
+
+static ssize_t mtouch_firmware_rev_show(struct device *dev,
+				struct device_attribute *attr, char *output)
+{
+	struct usb_interface *intf = to_usb_interface(dev);
+	struct usbtouch_usb *usbtouch = usb_get_intfdata(intf);
+	struct mtouch_priv *priv = usbtouch->priv;
+
+	return scnprintf(output, PAGE_SIZE, "%1x.%1x\n",
+			 priv->fw_rev_major, priv->fw_rev_minor);
+}
+static DEVICE_ATTR(firmware_rev, 0444, mtouch_firmware_rev_show, NULL);
+
+static struct attribute *mtouch_attrs[] = {
+	&dev_attr_firmware_rev.attr,
+	NULL
+};
+
+static const struct attribute_group mtouch_attr_group = {
+	.attrs = mtouch_attrs,
+};
+
+static int mtouch_get_fw_revision(struct usbtouch_usb *usbtouch)
+{
+	struct usb_device *udev = interface_to_usbdev(usbtouch->interface);
+	struct mtouch_priv *priv = usbtouch->priv;
+	u8 *buf;
+	int ret;
+
+	buf = kzalloc(MTOUCHUSB_REQ_CTRLLR_ID_LEN, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
+			      MTOUCHUSB_REQ_CTRLLR_ID,
+			      USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+			      0, 0, buf, MTOUCHUSB_REQ_CTRLLR_ID_LEN,
+			      USB_CTRL_SET_TIMEOUT);
+	if (ret != MTOUCHUSB_REQ_CTRLLR_ID_LEN) {
+		dev_warn(&usbtouch->interface->dev,
+			 "Failed to read FW rev: %d\n", ret);
+		ret = ret < 0 ? ret : -EIO;
+		goto free;
+	}
+
+	priv->fw_rev_major = buf[3];
+	priv->fw_rev_minor = buf[4];
+
+	ret = 0;
+
+free:
+	kfree(buf);
+	return ret;
+}
+
+static int mtouch_alloc(struct usbtouch_usb *usbtouch)
+{
+	int ret;
+
+	usbtouch->priv = kmalloc(sizeof(struct mtouch_priv), GFP_KERNEL);
+	if (!usbtouch->priv)
+		return -ENOMEM;
+
+	ret = sysfs_create_group(&usbtouch->interface->dev.kobj,
+				 &mtouch_attr_group);
+	if (ret) {
+		kfree(usbtouch->priv);
+		usbtouch->priv = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
 static int mtouch_init(struct usbtouch_usb *usbtouch)
 {
 	int ret, i;
 	struct usb_device *udev = interface_to_usbdev(usbtouch->interface);
 
+	ret = mtouch_get_fw_revision(usbtouch);
+	if (ret)
+		return ret;
+
 	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
 	                      MTOUCHUSB_RESET,
 	                      USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
@@ -492,6 +576,14 @@ static int mtouch_init(struct usbtouch_usb *usbtouch)
 
 	return 0;
 }
+
+static void mtouch_exit(struct usbtouch_usb *usbtouch)
+{
+	struct mtouch_priv *priv = usbtouch->priv;
+
+	sysfs_remove_group(&usbtouch->interface->dev.kobj, &mtouch_attr_group);
+	kfree(priv);
+}
 #endif
 
 
@@ -1119,7 +1211,9 @@ static struct usbtouch_device_info usbtouch_dev_info[] = {
 		.max_yc		= 0x4000,
 		.rept_size	= 11,
 		.read_data	= mtouch_read_data,
+		.alloc		= mtouch_alloc,
 		.init		= mtouch_init,
+		.exit		= mtouch_exit,
 	},
 #endif
 
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index df171cb85822..5b714a062fa7 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -146,6 +146,7 @@ config INTEL_IOMMU
 	select DMA_DIRECT_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
+	select NEED_DMA_MAP_STATE
 	select DMAR_TABLE
 	help
 	  DMA remapping (DMAR) devices support enables independent address
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 2a99f0f14795..8fb8c737fffe 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -83,7 +83,6 @@
 
 static DEFINE_SPINLOCK(amd_iommu_devtable_lock);
 static DEFINE_SPINLOCK(pd_bitmap_lock);
-static DEFINE_SPINLOCK(iommu_table_lock);
 
 /* List of all available dev_data structures */
 static LLIST_HEAD(dev_data_list);
@@ -3562,6 +3561,7 @@ EXPORT_SYMBOL(amd_iommu_device_info);
  *****************************************************************************/
 
 static struct irq_chip amd_ir_chip;
+static DEFINE_SPINLOCK(iommu_table_lock);
 
 static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
 {
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f05f3cf90756..ddcbbdb5d658 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -167,40 +167,16 @@ EXPORT_SYMBOL(iommu_put_dma_cookie);
  * @list: Reserved region list from iommu_get_resv_regions()
  *
  * IOMMU drivers can use this to implement their .get_resv_regions callback
- * for general non-IOMMU-specific reservations. Currently, this covers host
- * bridge windows for PCI devices and GICv3 ITS region reservation on ACPI
- * based ARM platforms that may require HW MSI reservation.
+ * for general non-IOMMU-specific reservations. Currently, this covers GICv3
+ * ITS region reservation on ACPI based ARM platforms that may require HW MSI
+ * reservation.
  */
 void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
 {
-	struct pci_host_bridge *bridge;
-	struct resource_entry *window;
-
-	if (!is_of_node(dev->iommu_fwspec->iommu_fwnode) &&
-		iort_iommu_msi_get_resv_regions(dev, list) < 0)
-		return;
-
-	if (!dev_is_pci(dev))
-		return;
-
-	bridge = pci_find_host_bridge(to_pci_dev(dev)->bus);
-	resource_list_for_each_entry(window, &bridge->windows) {
-		struct iommu_resv_region *region;
-		phys_addr_t start;
-		size_t length;
-
-		if (resource_type(window->res) != IORESOURCE_MEM)
-			continue;
 
-		start = window->res->start - window->offset;
-		length = window->res->end - window->res->start + 1;
-		region = iommu_alloc_resv_region(start, length, 0,
-				IOMMU_RESV_RESERVED);
-		if (!region)
-			return;
+	if (!is_of_node(dev->iommu_fwspec->iommu_fwnode))
+		iort_iommu_msi_get_resv_regions(dev, list);
 
-		list_add_tail(&region->list, list);
-	}
 }
 EXPORT_SYMBOL(iommu_dma_get_resv_regions);
 
@@ -229,6 +205,23 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
 	return 0;
 }
 
+static void iova_reserve_pci_windows(struct pci_dev *dev,
+		struct iova_domain *iovad)
+{
+	struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
+	struct resource_entry *window;
+	unsigned long lo, hi;
+
+	resource_list_for_each_entry(window, &bridge->windows) {
+		if (resource_type(window->res) != IORESOURCE_MEM)
+			continue;
+
+		lo = iova_pfn(iovad, window->res->start - window->offset);
+		hi = iova_pfn(iovad, window->res->end - window->offset);
+		reserve_iova(iovad, lo, hi);
+	}
+}
+
 static int iova_reserve_iommu_regions(struct device *dev,
 		struct iommu_domain *domain)
 {
@@ -238,6 +231,9 @@ static int iova_reserve_iommu_regions(struct device *dev,
 	LIST_HEAD(resv_regions);
 	int ret = 0;
 
+	if (dev_is_pci(dev))
+		iova_reserve_pci_windows(to_pci_dev(dev), iovad);
+
 	iommu_get_resv_regions(dev, &resv_regions);
 	list_for_each_entry(region, &resv_regions, list) {
 		unsigned long lo, hi;
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index accf58388bdb..460bed4fc5b1 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1345,7 +1345,7 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
 	struct qi_desc desc;
 
 	if (mask) {
-		BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
+		WARN_ON_ONCE(addr & ((1ULL << (VTD_PAGE_SHIFT + mask)) - 1));
 		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
 		desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
 	} else
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 66f69af2c219..3062a154a9fb 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -1136,7 +1136,7 @@ static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
 	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
 
 	/* Update the hardware only if the interrupt is in remapped mode. */
-	if (!force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+	if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
 		modify_irte(&ir_data->irq_2_iommu, irte);
 }
 
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 5fc8656c60f9..0468acfa131f 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -1098,7 +1098,7 @@ static int rk_iommu_of_xlate(struct device *dev,
 	data->iommu = platform_get_drvdata(iommu_dev);
 	dev->archdata.iommu = data;
 
-	of_dev_put(iommu_dev);
+	platform_device_put(iommu_dev);
 
 	return 0;
 }
@@ -1175,8 +1175,15 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	for (i = 0; i < iommu->num_clocks; ++i)
 		iommu->clocks[i].id = rk_iommu_clocks[i];
 
+	/*
+	 * iommu clocks should be present for all new devices and devicetrees
+	 * but there are older devicetrees without clocks out in the wild.
+	 * So clocks as optional for the time being.
+	 */
 	err = devm_clk_bulk_get(iommu->dev, iommu->num_clocks, iommu->clocks);
-	if (err)
+	if (err == -ENOENT)
+		iommu->num_clocks = 0;
+	else if (err)
 		return err;
 
 	err = clk_bulk_prepare(iommu->num_clocks, iommu->clocks);
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 5ed465ab1c76..15f268f646bf 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -27,7 +27,7 @@ obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
 obj-$(CONFIG_ARM_GIC_PM)		+= irq-gic-pm.o
 obj-$(CONFIG_ARCH_REALVIEW)		+= irq-gic-realview.o
 obj-$(CONFIG_ARM_GIC_V2M)		+= irq-gic-v2m.o
-obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-v3-mbi.o irq-gic-common.o
 obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o irq-gic-v3-its-platform-msi.o irq-gic-v4.o
 obj-$(CONFIG_ARM_GIC_V3_ITS_PCI)	+= irq-gic-v3-its-pci-msi.o
 obj-$(CONFIG_ARM_GIC_V3_ITS_FSL_MC)	+= irq-gic-v3-its-fsl-mc-msi.o
diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c
new file mode 100644
index 000000000000..ad70e7c416e3
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3-mbi.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#define pr_fmt(fmt) "GICv3: " fmt
+
+#include <linux/dma-iommu.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+struct mbi_range {
+	u32			spi_start;
+	u32			nr_spis;
+	unsigned long		*bm;
+};
+
+static struct mutex		mbi_lock;
+static phys_addr_t		mbi_phys_base;
+static struct mbi_range		*mbi_ranges;
+static unsigned int		mbi_range_nr;
+
+static struct irq_chip mbi_irq_chip = {
+	.name			= "MBI",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_type		= irq_chip_set_type_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+};
+
+static int mbi_irq_gic_domain_alloc(struct irq_domain *domain,
+				       unsigned int virq,
+				       irq_hw_number_t hwirq)
+{
+	struct irq_fwspec fwspec;
+	struct irq_data *d;
+	int err;
+
+	/*
+	 * Using ACPI? There is no MBI support in the spec, you
+	 * shouldn't even be here.
+	 */
+	if (!is_of_node(domain->parent->fwnode))
+		return -EINVAL;
+
+	/*
+	 * Let's default to edge. This is consistent with traditional
+	 * MSIs, and systems requiring level signaling will just
+	 * enforce the trigger on their own.
+	 */
+	fwspec.fwnode = domain->parent->fwnode;
+	fwspec.param_count = 3;
+	fwspec.param[0] = 0;
+	fwspec.param[1] = hwirq - 32;
+	fwspec.param[2] = IRQ_TYPE_EDGE_RISING;
+
+	err = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
+	if (err)
+		return err;
+
+	d = irq_domain_get_irq_data(domain->parent, virq);
+	return d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING);
+}
+
+static void mbi_free_msi(struct mbi_range *mbi, unsigned int hwirq,
+			 int nr_irqs)
+{
+	mutex_lock(&mbi_lock);
+	bitmap_release_region(mbi->bm, hwirq - mbi->spi_start,
+			      get_count_order(nr_irqs));
+	mutex_unlock(&mbi_lock);
+}
+
+static int mbi_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				   unsigned int nr_irqs, void *args)
+{
+	struct mbi_range *mbi = NULL;
+	int hwirq, offset, i, err = 0;
+
+	mutex_lock(&mbi_lock);
+	for (i = 0; i < mbi_range_nr; i++) {
+		offset = bitmap_find_free_region(mbi_ranges[i].bm,
+						 mbi_ranges[i].nr_spis,
+						 get_count_order(nr_irqs));
+		if (offset >= 0) {
+			mbi = &mbi_ranges[i];
+			break;
+		}
+	}
+	mutex_unlock(&mbi_lock);
+
+	if (!mbi)
+		return -ENOSPC;
+
+	hwirq = mbi->spi_start + offset;
+
+	for (i = 0; i < nr_irqs; i++) {
+		err = mbi_irq_gic_domain_alloc(domain, virq + i, hwirq + i);
+		if (err)
+			goto fail;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+					      &mbi_irq_chip, mbi);
+	}
+
+	return 0;
+
+fail:
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+	mbi_free_msi(mbi, hwirq, nr_irqs);
+	return err;
+}
+
+static void mbi_irq_domain_free(struct irq_domain *domain,
+				unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct mbi_range *mbi = irq_data_get_irq_chip_data(d);
+
+	mbi_free_msi(mbi, d->hwirq, nr_irqs);
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops mbi_domain_ops = {
+	.alloc			= mbi_irq_domain_alloc,
+	.free			= mbi_irq_domain_free,
+};
+
+static void mbi_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	msg[0].address_hi = upper_32_bits(mbi_phys_base + GICD_SETSPI_NSR);
+	msg[0].address_lo = lower_32_bits(mbi_phys_base + GICD_SETSPI_NSR);
+	msg[0].data = data->parent_data->hwirq;
+
+	iommu_dma_map_msi_msg(data->irq, msg);
+}
+
+#ifdef CONFIG_PCI_MSI
+/* PCI-specific irqchip */
+static void mbi_mask_msi_irq(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void mbi_unmask_msi_irq(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip mbi_msi_irq_chip = {
+	.name			= "MSI",
+	.irq_mask		= mbi_mask_msi_irq,
+	.irq_unmask		= mbi_unmask_msi_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_compose_msi_msg	= mbi_compose_msi_msg,
+	.irq_write_msi_msg	= pci_msi_domain_write_msg,
+};
+
+static struct msi_domain_info mbi_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI),
+	.chip	= &mbi_msi_irq_chip,
+};
+
+static int mbi_allocate_pci_domain(struct irq_domain *nexus_domain,
+				   struct irq_domain **pci_domain)
+{
+	*pci_domain = pci_msi_create_irq_domain(nexus_domain->parent->fwnode,
+						&mbi_msi_domain_info,
+						nexus_domain);
+	if (!*pci_domain)
+		return -ENOMEM;
+
+	return 0;
+}
+#else
+static int mbi_allocate_pci_domain(struct irq_domain *nexus_domain,
+				   struct irq_domain **pci_domain)
+{
+	*pci_domain = NULL;
+	return 0;
+}
+#endif
+
+static void mbi_compose_mbi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	mbi_compose_msi_msg(data, msg);
+
+	msg[1].address_hi = upper_32_bits(mbi_phys_base + GICD_CLRSPI_NSR);
+	msg[1].address_lo = lower_32_bits(mbi_phys_base + GICD_CLRSPI_NSR);
+	msg[1].data = data->parent_data->hwirq;
+
+	iommu_dma_map_msi_msg(data->irq, &msg[1]);
+}
+
+/* Platform-MSI specific irqchip */
+static struct irq_chip mbi_pmsi_irq_chip = {
+	.name			= "pMSI",
+	.irq_set_type		= irq_chip_set_type_parent,
+	.irq_compose_msi_msg	= mbi_compose_mbi_msg,
+	.flags			= IRQCHIP_SUPPORTS_LEVEL_MSI,
+};
+
+static struct msi_domain_ops mbi_pmsi_ops = {
+};
+
+static struct msi_domain_info mbi_pmsi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_LEVEL_CAPABLE),
+	.ops	= &mbi_pmsi_ops,
+	.chip	= &mbi_pmsi_irq_chip,
+};
+
+static int mbi_allocate_domains(struct irq_domain *parent)
+{
+	struct irq_domain *nexus_domain, *pci_domain, *plat_domain;
+	int err;
+
+	nexus_domain = irq_domain_create_tree(parent->fwnode,
+					      &mbi_domain_ops, NULL);
+	if (!nexus_domain)
+		return -ENOMEM;
+
+	irq_domain_update_bus_token(nexus_domain, DOMAIN_BUS_NEXUS);
+	nexus_domain->parent = parent;
+
+	err = mbi_allocate_pci_domain(nexus_domain, &pci_domain);
+
+	plat_domain = platform_msi_create_irq_domain(parent->fwnode,
+						     &mbi_pmsi_domain_info,
+						     nexus_domain);
+
+	if (err || !plat_domain) {
+		if (plat_domain)
+			irq_domain_remove(plat_domain);
+		if (pci_domain)
+			irq_domain_remove(pci_domain);
+		irq_domain_remove(nexus_domain);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int __init mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent)
+{
+	struct device_node *np;
+	const __be32 *reg;
+	int ret, n;
+
+	np = to_of_node(fwnode);
+
+	if (!of_property_read_bool(np, "msi-controller"))
+		return 0;
+
+	n = of_property_count_elems_of_size(np, "mbi-ranges", sizeof(u32));
+	if (n <= 0 || n % 2)
+		return -EINVAL;
+
+	mbi_range_nr = n / 2;
+	mbi_ranges = kcalloc(mbi_range_nr, sizeof(*mbi_ranges), GFP_KERNEL);
+	if (!mbi_ranges)
+		return -ENOMEM;
+
+	for (n = 0; n < mbi_range_nr; n++) {
+		ret = of_property_read_u32_index(np, "mbi-ranges", n * 2,
+						 &mbi_ranges[n].spi_start);
+		if (ret)
+			goto err_free_mbi;
+		ret = of_property_read_u32_index(np, "mbi-ranges", n * 2 + 1,
+						 &mbi_ranges[n].nr_spis);
+		if (ret)
+			goto err_free_mbi;
+
+		mbi_ranges[n].bm = kcalloc(BITS_TO_LONGS(mbi_ranges[n].nr_spis),
+					   sizeof(long), GFP_KERNEL);
+		if (!mbi_ranges[n].bm) {
+			ret = -ENOMEM;
+			goto err_free_mbi;
+		}
+		pr_info("MBI range [%d:%d]\n", mbi_ranges[n].spi_start,
+			mbi_ranges[n].spi_start + mbi_ranges[n].nr_spis - 1);
+	}
+
+	reg = of_get_property(np, "mbi-alias", NULL);
+	if (reg) {
+		mbi_phys_base = of_translate_address(np, reg);
+		if (mbi_phys_base == OF_BAD_ADDR) {
+			ret = -ENXIO;
+			goto err_free_mbi;
+		}
+	} else {
+		struct resource res;
+
+		if (of_address_to_resource(np, 0, &res)) {
+			ret = -ENXIO;
+			goto err_free_mbi;
+		}
+
+		mbi_phys_base = res.start;
+	}
+
+	pr_info("Using MBI frame %pa\n", &mbi_phys_base);
+
+	ret = mbi_allocate_domains(parent);
+	if (ret)
+		goto err_free_mbi;
+
+	return 0;
+
+err_free_mbi:
+	if (mbi_ranges) {
+		for (n = 0; n < mbi_range_nr; n++)
+			kfree(mbi_ranges[n].bm);
+		kfree(mbi_ranges);
+	}
+
+	return ret;
+}
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index e5d101418390..5a67ec084588 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1099,6 +1099,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 
 	gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
 						 &gic_data);
+	irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);
 	gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
 	gic_data.rdists.has_vlpis = true;
 	gic_data.rdists.has_direct_lpi = true;
@@ -1112,6 +1113,12 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	pr_info("Distributor has %sRange Selector support\n",
 		gic_data.has_rss ? "" : "no ");
 
+	if (typer & GICD_TYPER_MBIS) {
+		err = mbi_init(handle, gic_data.domain);
+		if (err)
+			pr_err("Failed to initialize MBIs\n");
+	}
+
 	set_handle_irq(gic_handle_irq);
 
 	gic_update_vlpi_properties();
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index a59bdbc0b9bb..7b531fd075b8 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -63,11 +63,16 @@ static const struct meson_gpio_irq_params gxl_params = {
 	.nr_hwirq = 110,
 };
 
+static const struct meson_gpio_irq_params axg_params = {
+	.nr_hwirq = 100,
+};
+
 static const struct of_device_id meson_irq_gpio_matches[] = {
 	{ .compatible = "amlogic,meson8-gpio-intc", .data = &meson8_params },
 	{ .compatible = "amlogic,meson8b-gpio-intc", .data = &meson8b_params },
 	{ .compatible = "amlogic,meson-gxbb-gpio-intc", .data = &gxbb_params },
 	{ .compatible = "amlogic,meson-gxl-gpio-intc", .data = &gxl_params },
+	{ .compatible = "amlogic,meson-axg-gpio-intc", .data = &axg_params },
 	{ }
 };
 
diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c
index 17a4a7b6cdbb..4e17f7081efc 100644
--- a/drivers/irqchip/irq-mvebu-gicp.c
+++ b/drivers/irqchip/irq-mvebu-gicp.c
@@ -19,8 +19,6 @@
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 
-#include "irq-mvebu-gicp.h"
-
 #define GICP_SETSPI_NSR_OFFSET	0x0
 #define GICP_CLRSPI_NSR_OFFSET	0x8
 
@@ -55,34 +53,18 @@ static int gicp_idx_to_spi(struct mvebu_gicp *gicp, int idx)
 	return -EINVAL;
 }
 
-int mvebu_gicp_get_doorbells(struct device_node *dn, phys_addr_t *setspi,
-			     phys_addr_t *clrspi)
-{
-	struct platform_device *pdev;
-	struct mvebu_gicp *gicp;
-
-	pdev = of_find_device_by_node(dn);
-	if (!pdev)
-		return -ENODEV;
-
-	gicp = platform_get_drvdata(pdev);
-	if (!gicp)
-		return -ENODEV;
-
-	*setspi = gicp->res->start + GICP_SETSPI_NSR_OFFSET;
-	*clrspi = gicp->res->start + GICP_CLRSPI_NSR_OFFSET;
-
-	return 0;
-}
-
 static void gicp_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
 	struct mvebu_gicp *gicp = data->chip_data;
 	phys_addr_t setspi = gicp->res->start + GICP_SETSPI_NSR_OFFSET;
-
-	msg->data = data->hwirq;
-	msg->address_lo = lower_32_bits(setspi);
-	msg->address_hi = upper_32_bits(setspi);
+	phys_addr_t clrspi = gicp->res->start + GICP_CLRSPI_NSR_OFFSET;
+
+	msg[0].data = data->hwirq;
+	msg[0].address_lo = lower_32_bits(setspi);
+	msg[0].address_hi = upper_32_bits(setspi);
+	msg[1].data = data->hwirq;
+	msg[1].address_lo = lower_32_bits(clrspi);
+	msg[1].address_hi = upper_32_bits(clrspi);
 }
 
 static struct irq_chip gicp_irq_chip = {
@@ -170,13 +152,15 @@ static const struct irq_domain_ops gicp_domain_ops = {
 static struct irq_chip gicp_msi_irq_chip = {
 	.name		= "GICP",
 	.irq_set_type	= irq_chip_set_type_parent,
+	.flags		= IRQCHIP_SUPPORTS_LEVEL_MSI,
 };
 
 static struct msi_domain_ops gicp_msi_ops = {
 };
 
 static struct msi_domain_info gicp_msi_domain_info = {
-	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS),
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_LEVEL_CAPABLE),
 	.ops	= &gicp_msi_ops,
 	.chip	= &gicp_msi_irq_chip,
 };
diff --git a/drivers/irqchip/irq-mvebu-gicp.h b/drivers/irqchip/irq-mvebu-gicp.h
deleted file mode 100644
index eaa12fb72102..000000000000
--- a/drivers/irqchip/irq-mvebu-gicp.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __MVEBU_GICP_H__
-#define __MVEBU_GICP_H__
-
-#include <linux/types.h>
-
-struct device_node;
-
-int mvebu_gicp_get_doorbells(struct device_node *dn, phys_addr_t *setspi,
-			     phys_addr_t *clrspi);
-
-#endif /* __MVEBU_GICP_H__ */
diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c
index e18c48d3a92e..13063339b416 100644
--- a/drivers/irqchip/irq-mvebu-icu.c
+++ b/drivers/irqchip/irq-mvebu-icu.c
@@ -21,8 +21,6 @@
 
 #include <dt-bindings/interrupt-controller/mvebu-icu.h>
 
-#include "irq-mvebu-gicp.h"
-
 /* ICU registers */
 #define ICU_SETSPI_NSR_AL	0x10
 #define ICU_SETSPI_NSR_AH	0x14
@@ -43,6 +41,7 @@ struct mvebu_icu {
 	void __iomem *base;
 	struct irq_domain *domain;
 	struct device *dev;
+	atomic_t initialized;
 };
 
 struct mvebu_icu_irq_data {
@@ -51,6 +50,18 @@ struct mvebu_icu_irq_data {
 	unsigned int type;
 };
 
+static void mvebu_icu_init(struct mvebu_icu *icu, struct msi_msg *msg)
+{
+	if (atomic_cmpxchg(&icu->initialized, false, true))
+		return;
+
+	/* Set Clear/Set ICU SPI message address in AP */
+	writel_relaxed(msg[0].address_hi, icu->base + ICU_SETSPI_NSR_AH);
+	writel_relaxed(msg[0].address_lo, icu->base + ICU_SETSPI_NSR_AL);
+	writel_relaxed(msg[1].address_hi, icu->base + ICU_CLRSPI_NSR_AH);
+	writel_relaxed(msg[1].address_lo, icu->base + ICU_CLRSPI_NSR_AL);
+}
+
 static void mvebu_icu_write_msg(struct msi_desc *desc, struct msi_msg *msg)
 {
 	struct irq_data *d = irq_get_irq_data(desc->irq);
@@ -59,6 +70,8 @@ static void mvebu_icu_write_msg(struct msi_desc *desc, struct msi_msg *msg)
 	unsigned int icu_int;
 
 	if (msg->address_lo || msg->address_hi) {
+		/* One off initialization */
+		mvebu_icu_init(icu, msg);
 		/* Configure the ICU with irq number & type */
 		icu_int = msg->data | ICU_INT_ENABLE;
 		if (icu_irqd->type & IRQ_TYPE_EDGE_RISING)
@@ -197,9 +210,7 @@ static int mvebu_icu_probe(struct platform_device *pdev)
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *gicp_dn;
 	struct resource *res;
-	phys_addr_t setspi, clrspi;
-	u32 i, icu_int;
-	int ret;
+	int i;
 
 	icu = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_icu),
 			   GFP_KERNEL);
@@ -242,22 +253,12 @@ static int mvebu_icu_probe(struct platform_device *pdev)
 	if (!gicp_dn)
 		return -ENODEV;
 
-	ret = mvebu_gicp_get_doorbells(gicp_dn, &setspi, &clrspi);
-	if (ret)
-		return ret;
-
-	/* Set Clear/Set ICU SPI message address in AP */
-	writel_relaxed(upper_32_bits(setspi), icu->base + ICU_SETSPI_NSR_AH);
-	writel_relaxed(lower_32_bits(setspi), icu->base + ICU_SETSPI_NSR_AL);
-	writel_relaxed(upper_32_bits(clrspi), icu->base + ICU_CLRSPI_NSR_AH);
-	writel_relaxed(lower_32_bits(clrspi), icu->base + ICU_CLRSPI_NSR_AL);
-
 	/*
 	 * Clean all ICU interrupts with type SPI_NSR, required to
 	 * avoid unpredictable SPI assignments done by firmware.
 	 */
 	for (i = 0 ; i < ICU_MAX_IRQS ; i++) {
-		icu_int = readl(icu->base + ICU_INT_CFG(i));
+		u32 icu_int = readl_relaxed(icu->base + ICU_INT_CFG(i));
 		if ((icu_int >> ICU_GROUP_SHIFT) == ICU_GRP_NSR)
 			writel_relaxed(0x0, icu->base + ICU_INT_CFG(i));
 	}
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 36f0fbe36c35..5089c1e2838d 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -14,6 +14,9 @@
 #include <linux/irqdomain.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/syscore_ops.h>
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
 
 #define IRQS_PER_BANK 32
 
@@ -23,29 +26,69 @@ struct stm32_exti_bank {
 	u32 rtsr_ofst;
 	u32 ftsr_ofst;
 	u32 swier_ofst;
-	u32 pr_ofst;
+	u32 rpr_ofst;
+	u32 fpr_ofst;
+};
+
+#define UNDEF_REG ~0
+
+struct stm32_desc_irq {
+	u32 exti;
+	u32 irq_parent;
+};
+
+struct stm32_exti_drv_data {
+	const struct stm32_exti_bank **exti_banks;
+	const struct stm32_desc_irq *desc_irqs;
+	u32 bank_nr;
+	u32 irq_nr;
+};
+
+struct stm32_exti_chip_data {
+	struct stm32_exti_host_data *host_data;
+	const struct stm32_exti_bank *reg_bank;
+	struct raw_spinlock rlock;
+	u32 wake_active;
+	u32 mask_cache;
+	u32 rtsr_cache;
+	u32 ftsr_cache;
 };
 
+struct stm32_exti_host_data {
+	void __iomem *base;
+	struct stm32_exti_chip_data *chips_data;
+	const struct stm32_exti_drv_data *drv_data;
+};
+
+static struct stm32_exti_host_data *stm32_host_data;
+
 static const struct stm32_exti_bank stm32f4xx_exti_b1 = {
 	.imr_ofst	= 0x00,
 	.emr_ofst	= 0x04,
 	.rtsr_ofst	= 0x08,
 	.ftsr_ofst	= 0x0C,
 	.swier_ofst	= 0x10,
-	.pr_ofst	= 0x14,
+	.rpr_ofst	= 0x14,
+	.fpr_ofst	= UNDEF_REG,
 };
 
 static const struct stm32_exti_bank *stm32f4xx_exti_banks[] = {
 	&stm32f4xx_exti_b1,
 };
 
+static const struct stm32_exti_drv_data stm32f4xx_drv_data = {
+	.exti_banks = stm32f4xx_exti_banks,
+	.bank_nr = ARRAY_SIZE(stm32f4xx_exti_banks),
+};
+
 static const struct stm32_exti_bank stm32h7xx_exti_b1 = {
 	.imr_ofst	= 0x80,
 	.emr_ofst	= 0x84,
 	.rtsr_ofst	= 0x00,
 	.ftsr_ofst	= 0x04,
 	.swier_ofst	= 0x08,
-	.pr_ofst	= 0x88,
+	.rpr_ofst	= 0x88,
+	.fpr_ofst	= UNDEF_REG,
 };
 
 static const struct stm32_exti_bank stm32h7xx_exti_b2 = {
@@ -54,7 +97,8 @@ static const struct stm32_exti_bank stm32h7xx_exti_b2 = {
 	.rtsr_ofst	= 0x20,
 	.ftsr_ofst	= 0x24,
 	.swier_ofst	= 0x28,
-	.pr_ofst	= 0x98,
+	.rpr_ofst	= 0x98,
+	.fpr_ofst	= UNDEF_REG,
 };
 
 static const struct stm32_exti_bank stm32h7xx_exti_b3 = {
@@ -63,7 +107,8 @@ static const struct stm32_exti_bank stm32h7xx_exti_b3 = {
 	.rtsr_ofst	= 0x40,
 	.ftsr_ofst	= 0x44,
 	.swier_ofst	= 0x48,
-	.pr_ofst	= 0xA8,
+	.rpr_ofst	= 0xA8,
+	.fpr_ofst	= UNDEF_REG,
 };
 
 static const struct stm32_exti_bank *stm32h7xx_exti_banks[] = {
@@ -72,18 +117,105 @@ static const struct stm32_exti_bank *stm32h7xx_exti_banks[] = {
 	&stm32h7xx_exti_b3,
 };
 
-static unsigned long stm32_exti_pending(struct irq_chip_generic *gc)
+static const struct stm32_exti_drv_data stm32h7xx_drv_data = {
+	.exti_banks = stm32h7xx_exti_banks,
+	.bank_nr = ARRAY_SIZE(stm32h7xx_exti_banks),
+};
+
+static const struct stm32_exti_bank stm32mp1_exti_b1 = {
+	.imr_ofst	= 0x80,
+	.emr_ofst	= 0x84,
+	.rtsr_ofst	= 0x00,
+	.ftsr_ofst	= 0x04,
+	.swier_ofst	= 0x08,
+	.rpr_ofst	= 0x0C,
+	.fpr_ofst	= 0x10,
+};
+
+static const struct stm32_exti_bank stm32mp1_exti_b2 = {
+	.imr_ofst	= 0x90,
+	.emr_ofst	= 0x94,
+	.rtsr_ofst	= 0x20,
+	.ftsr_ofst	= 0x24,
+	.swier_ofst	= 0x28,
+	.rpr_ofst	= 0x2C,
+	.fpr_ofst	= 0x30,
+};
+
+static const struct stm32_exti_bank stm32mp1_exti_b3 = {
+	.imr_ofst	= 0xA0,
+	.emr_ofst	= 0xA4,
+	.rtsr_ofst	= 0x40,
+	.ftsr_ofst	= 0x44,
+	.swier_ofst	= 0x48,
+	.rpr_ofst	= 0x4C,
+	.fpr_ofst	= 0x50,
+};
+
+static const struct stm32_exti_bank *stm32mp1_exti_banks[] = {
+	&stm32mp1_exti_b1,
+	&stm32mp1_exti_b2,
+	&stm32mp1_exti_b3,
+};
+
+static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
+	{ .exti = 1, .irq_parent = 7 },
+	{ .exti = 2, .irq_parent = 8 },
+	{ .exti = 3, .irq_parent = 9 },
+	{ .exti = 4, .irq_parent = 10 },
+	{ .exti = 5, .irq_parent = 23 },
+	{ .exti = 6, .irq_parent = 64 },
+	{ .exti = 7, .irq_parent = 65 },
+	{ .exti = 8, .irq_parent = 66 },
+	{ .exti = 9, .irq_parent = 67 },
+	{ .exti = 10, .irq_parent = 40 },
+	{ .exti = 11, .irq_parent = 42 },
+	{ .exti = 12, .irq_parent = 76 },
+	{ .exti = 13, .irq_parent = 77 },
+	{ .exti = 14, .irq_parent = 121 },
+	{ .exti = 15, .irq_parent = 127 },
+	{ .exti = 16, .irq_parent = 1 },
+	{ .exti = 65, .irq_parent = 144 },
+	{ .exti = 68, .irq_parent = 143 },
+	{ .exti = 73, .irq_parent = 129 },
+};
+
+static const struct stm32_exti_drv_data stm32mp1_drv_data = {
+	.exti_banks = stm32mp1_exti_banks,
+	.bank_nr = ARRAY_SIZE(stm32mp1_exti_banks),
+	.desc_irqs = stm32mp1_desc_irq,
+	.irq_nr = ARRAY_SIZE(stm32mp1_desc_irq),
+};
+
+static int stm32_exti_to_irq(const struct stm32_exti_drv_data *drv_data,
+			     irq_hw_number_t hwirq)
 {
-	const struct stm32_exti_bank *stm32_bank = gc->private;
+	const struct stm32_desc_irq *desc_irq;
+	int i;
 
-	return irq_reg_readl(gc, stm32_bank->pr_ofst);
+	if (!drv_data->desc_irqs)
+		return -EINVAL;
+
+	for (i = 0; i < drv_data->irq_nr; i++) {
+		desc_irq = &drv_data->desc_irqs[i];
+		if (desc_irq->exti == hwirq)
+			return desc_irq->irq_parent;
+	}
+
+	return -EINVAL;
 }
 
-static void stm32_exti_irq_ack(struct irq_chip_generic *gc, u32 mask)
+static unsigned long stm32_exti_pending(struct irq_chip_generic *gc)
 {
-	const struct stm32_exti_bank *stm32_bank = gc->private;
+	struct stm32_exti_chip_data *chip_data = gc->private;
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+	unsigned long pending;
+
+	pending = irq_reg_readl(gc, stm32_bank->rpr_ofst);
+	if (stm32_bank->fpr_ofst != UNDEF_REG)
+		pending |= irq_reg_readl(gc, stm32_bank->fpr_ofst);
 
-	irq_reg_writel(gc, mask, stm32_bank->pr_ofst);
+	return pending;
 }
 
 static void stm32_irq_handler(struct irq_desc *desc)
@@ -92,7 +224,6 @@ static void stm32_irq_handler(struct irq_desc *desc)
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int virq, nbanks = domain->gc->num_chips;
 	struct irq_chip_generic *gc;
-	const struct stm32_exti_bank *stm32_bank;
 	unsigned long pending;
 	int n, i, irq_base = 0;
 
@@ -100,13 +231,11 @@ static void stm32_irq_handler(struct irq_desc *desc)
 
 	for (i = 0; i < nbanks; i++, irq_base += IRQS_PER_BANK) {
 		gc = irq_get_domain_generic_chip(domain, irq_base);
-		stm32_bank = gc->private;
 
 		while ((pending = stm32_exti_pending(gc))) {
 			for_each_set_bit(n, &pending, IRQS_PER_BANK) {
 				virq = irq_find_mapping(domain, irq_base + n);
 				generic_handle_irq(virq);
-				stm32_exti_irq_ack(gc, BIT(n));
 			}
 		}
 	}
@@ -114,36 +243,50 @@ static void stm32_irq_handler(struct irq_desc *desc)
 	chained_irq_exit(chip, desc);
 }
 
-static int stm32_irq_set_type(struct irq_data *data, unsigned int type)
+static int stm32_exti_set_type(struct irq_data *d,
+			       unsigned int type, u32 *rtsr, u32 *ftsr)
 {
-	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
-	const struct stm32_exti_bank *stm32_bank = gc->private;
-	int pin = data->hwirq % IRQS_PER_BANK;
-	u32 rtsr, ftsr;
-
-	irq_gc_lock(gc);
-
-	rtsr = irq_reg_readl(gc, stm32_bank->rtsr_ofst);
-	ftsr = irq_reg_readl(gc, stm32_bank->ftsr_ofst);
+	u32 mask = BIT(d->hwirq % IRQS_PER_BANK);
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_RISING:
-		rtsr |= BIT(pin);
-		ftsr &= ~BIT(pin);
+		*rtsr |= mask;
+		*ftsr &= ~mask;
 		break;
 	case IRQ_TYPE_EDGE_FALLING:
-		rtsr &= ~BIT(pin);
-		ftsr |= BIT(pin);
+		*rtsr &= ~mask;
+		*ftsr |= mask;
 		break;
 	case IRQ_TYPE_EDGE_BOTH:
-		rtsr |= BIT(pin);
-		ftsr |= BIT(pin);
+		*rtsr |= mask;
+		*ftsr |= mask;
 		break;
 	default:
-		irq_gc_unlock(gc);
 		return -EINVAL;
 	}
 
+	return 0;
+}
+
+static int stm32_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct stm32_exti_chip_data *chip_data = gc->private;
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+	u32 rtsr, ftsr;
+	int err;
+
+	irq_gc_lock(gc);
+
+	rtsr = irq_reg_readl(gc, stm32_bank->rtsr_ofst);
+	ftsr = irq_reg_readl(gc, stm32_bank->ftsr_ofst);
+
+	err = stm32_exti_set_type(d, type, &rtsr, &ftsr);
+	if (err) {
+		irq_gc_unlock(gc);
+		return err;
+	}
+
 	irq_reg_writel(gc, rtsr, stm32_bank->rtsr_ofst);
 	irq_reg_writel(gc, ftsr, stm32_bank->ftsr_ofst);
 
@@ -152,40 +295,59 @@ static int stm32_irq_set_type(struct irq_data *data, unsigned int type)
 	return 0;
 }
 
-static int stm32_irq_set_wake(struct irq_data *data, unsigned int on)
+static void stm32_chip_suspend(struct stm32_exti_chip_data *chip_data,
+			       u32 wake_active)
 {
-	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
-	const struct stm32_exti_bank *stm32_bank = gc->private;
-	int pin = data->hwirq % IRQS_PER_BANK;
-	u32 imr;
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+	void __iomem *base = chip_data->host_data->base;
 
-	irq_gc_lock(gc);
+	/* save rtsr, ftsr registers */
+	chip_data->rtsr_cache = readl_relaxed(base + stm32_bank->rtsr_ofst);
+	chip_data->ftsr_cache = readl_relaxed(base + stm32_bank->ftsr_ofst);
 
-	imr = irq_reg_readl(gc, stm32_bank->imr_ofst);
-	if (on)
-		imr |= BIT(pin);
-	else
-		imr &= ~BIT(pin);
-	irq_reg_writel(gc, imr, stm32_bank->imr_ofst);
+	writel_relaxed(wake_active, base + stm32_bank->imr_ofst);
+}
+
+static void stm32_chip_resume(struct stm32_exti_chip_data *chip_data,
+			      u32 mask_cache)
+{
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+	void __iomem *base = chip_data->host_data->base;
+
+	/* restore rtsr, ftsr, registers */
+	writel_relaxed(chip_data->rtsr_cache, base + stm32_bank->rtsr_ofst);
+	writel_relaxed(chip_data->ftsr_cache, base + stm32_bank->ftsr_ofst);
 
+	writel_relaxed(mask_cache, base + stm32_bank->imr_ofst);
+}
+
+static void stm32_irq_suspend(struct irq_chip_generic *gc)
+{
+	struct stm32_exti_chip_data *chip_data = gc->private;
+
+	irq_gc_lock(gc);
+	stm32_chip_suspend(chip_data, gc->wake_active);
 	irq_gc_unlock(gc);
+}
 
-	return 0;
+static void stm32_irq_resume(struct irq_chip_generic *gc)
+{
+	struct stm32_exti_chip_data *chip_data = gc->private;
+
+	irq_gc_lock(gc);
+	stm32_chip_resume(chip_data, gc->mask_cache);
+	irq_gc_unlock(gc);
 }
 
 static int stm32_exti_alloc(struct irq_domain *d, unsigned int virq,
 			    unsigned int nr_irqs, void *data)
 {
-	struct irq_chip_generic *gc;
 	struct irq_fwspec *fwspec = data;
 	irq_hw_number_t hwirq;
 
 	hwirq = fwspec->param[0];
-	gc = irq_get_domain_generic_chip(d, hwirq);
 
 	irq_map_generic_chip(d, virq, hwirq);
-	irq_domain_set_info(d, virq, hwirq, &gc->chip_types->chip, gc,
-			    handle_simple_irq, NULL, NULL);
 
 	return 0;
 }
@@ -198,30 +360,318 @@ static void stm32_exti_free(struct irq_domain *d, unsigned int virq,
 	irq_domain_reset_irq_data(data);
 }
 
-struct irq_domain_ops irq_exti_domain_ops = {
+static const struct irq_domain_ops irq_exti_domain_ops = {
 	.map	= irq_map_generic_chip,
-	.xlate	= irq_domain_xlate_onetwocell,
 	.alloc  = stm32_exti_alloc,
 	.free	= stm32_exti_free,
 };
 
-static int
-__init stm32_exti_init(const struct stm32_exti_bank **stm32_exti_banks,
-		       int bank_nr, struct device_node *node)
+static void stm32_irq_ack(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct stm32_exti_chip_data *chip_data = gc->private;
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+
+	irq_gc_lock(gc);
+
+	irq_reg_writel(gc, d->mask, stm32_bank->rpr_ofst);
+	if (stm32_bank->fpr_ofst != UNDEF_REG)
+		irq_reg_writel(gc, d->mask, stm32_bank->fpr_ofst);
+
+	irq_gc_unlock(gc);
+}
+
+static inline u32 stm32_exti_set_bit(struct irq_data *d, u32 reg)
 {
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	void __iomem *base = chip_data->host_data->base;
+	u32 val;
+
+	val = readl_relaxed(base + reg);
+	val |= BIT(d->hwirq % IRQS_PER_BANK);
+	writel_relaxed(val, base + reg);
+
+	return val;
+}
+
+static inline u32 stm32_exti_clr_bit(struct irq_data *d, u32 reg)
+{
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	void __iomem *base = chip_data->host_data->base;
+	u32 val;
+
+	val = readl_relaxed(base + reg);
+	val &= ~BIT(d->hwirq % IRQS_PER_BANK);
+	writel_relaxed(val, base + reg);
+
+	return val;
+}
+
+static void stm32_exti_h_eoi(struct irq_data *d)
+{
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+
+	raw_spin_lock(&chip_data->rlock);
+
+	stm32_exti_set_bit(d, stm32_bank->rpr_ofst);
+	if (stm32_bank->fpr_ofst != UNDEF_REG)
+		stm32_exti_set_bit(d, stm32_bank->fpr_ofst);
+
+	raw_spin_unlock(&chip_data->rlock);
+
+	if (d->parent_data->chip)
+		irq_chip_eoi_parent(d);
+}
+
+static void stm32_exti_h_mask(struct irq_data *d)
+{
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+
+	raw_spin_lock(&chip_data->rlock);
+	chip_data->mask_cache = stm32_exti_clr_bit(d, stm32_bank->imr_ofst);
+	raw_spin_unlock(&chip_data->rlock);
+
+	if (d->parent_data->chip)
+		irq_chip_mask_parent(d);
+}
+
+static void stm32_exti_h_unmask(struct irq_data *d)
+{
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+
+	raw_spin_lock(&chip_data->rlock);
+	chip_data->mask_cache = stm32_exti_set_bit(d, stm32_bank->imr_ofst);
+	raw_spin_unlock(&chip_data->rlock);
+
+	if (d->parent_data->chip)
+		irq_chip_unmask_parent(d);
+}
+
+static int stm32_exti_h_set_type(struct irq_data *d, unsigned int type)
+{
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+	void __iomem *base = chip_data->host_data->base;
+	u32 rtsr, ftsr;
+	int err;
+
+	raw_spin_lock(&chip_data->rlock);
+	rtsr = readl_relaxed(base + stm32_bank->rtsr_ofst);
+	ftsr = readl_relaxed(base + stm32_bank->ftsr_ofst);
+
+	err = stm32_exti_set_type(d, type, &rtsr, &ftsr);
+	if (err) {
+		raw_spin_unlock(&chip_data->rlock);
+		return err;
+	}
+
+	writel_relaxed(rtsr, base + stm32_bank->rtsr_ofst);
+	writel_relaxed(ftsr, base + stm32_bank->ftsr_ofst);
+	raw_spin_unlock(&chip_data->rlock);
+
+	return 0;
+}
+
+static int stm32_exti_h_set_wake(struct irq_data *d, unsigned int on)
+{
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	u32 mask = BIT(d->hwirq % IRQS_PER_BANK);
+
+	raw_spin_lock(&chip_data->rlock);
+
+	if (on)
+		chip_data->wake_active |= mask;
+	else
+		chip_data->wake_active &= ~mask;
+
+	raw_spin_unlock(&chip_data->rlock);
+
+	return 0;
+}
+
+static int stm32_exti_h_set_affinity(struct irq_data *d,
+				     const struct cpumask *dest, bool force)
+{
+	if (d->parent_data->chip)
+		return irq_chip_set_affinity_parent(d, dest, force);
+
+	return -EINVAL;
+}
+
+#ifdef CONFIG_PM
+static int stm32_exti_h_suspend(void)
+{
+	struct stm32_exti_chip_data *chip_data;
+	int i;
+
+	for (i = 0; i < stm32_host_data->drv_data->bank_nr; i++) {
+		chip_data = &stm32_host_data->chips_data[i];
+		raw_spin_lock(&chip_data->rlock);
+		stm32_chip_suspend(chip_data, chip_data->wake_active);
+		raw_spin_unlock(&chip_data->rlock);
+	}
+
+	return 0;
+}
+
+static void stm32_exti_h_resume(void)
+{
+	struct stm32_exti_chip_data *chip_data;
+	int i;
+
+	for (i = 0; i < stm32_host_data->drv_data->bank_nr; i++) {
+		chip_data = &stm32_host_data->chips_data[i];
+		raw_spin_lock(&chip_data->rlock);
+		stm32_chip_resume(chip_data, chip_data->mask_cache);
+		raw_spin_unlock(&chip_data->rlock);
+	}
+}
+
+static struct syscore_ops stm32_exti_h_syscore_ops = {
+	.suspend	= stm32_exti_h_suspend,
+	.resume		= stm32_exti_h_resume,
+};
+
+static void stm32_exti_h_syscore_init(void)
+{
+	register_syscore_ops(&stm32_exti_h_syscore_ops);
+}
+#else
+static inline void stm32_exti_h_syscore_init(void) {}
+#endif
+
+static struct irq_chip stm32_exti_h_chip = {
+	.name			= "stm32-exti-h",
+	.irq_eoi		= stm32_exti_h_eoi,
+	.irq_mask		= stm32_exti_h_mask,
+	.irq_unmask		= stm32_exti_h_unmask,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_type		= stm32_exti_h_set_type,
+	.irq_set_wake		= stm32_exti_h_set_wake,
+	.flags			= IRQCHIP_MASK_ON_SUSPEND,
+#ifdef CONFIG_SMP
+	.irq_set_affinity	= stm32_exti_h_set_affinity,
+#endif
+};
+
+static int stm32_exti_h_domain_alloc(struct irq_domain *dm,
+				     unsigned int virq,
+				     unsigned int nr_irqs, void *data)
+{
+	struct stm32_exti_host_data *host_data = dm->host_data;
+	struct stm32_exti_chip_data *chip_data;
+	struct irq_fwspec *fwspec = data;
+	struct irq_fwspec p_fwspec;
+	irq_hw_number_t hwirq;
+	int p_irq, bank;
+
+	hwirq = fwspec->param[0];
+	bank  = hwirq / IRQS_PER_BANK;
+	chip_data = &host_data->chips_data[bank];
+
+	irq_domain_set_hwirq_and_chip(dm, virq, hwirq,
+				      &stm32_exti_h_chip, chip_data);
+
+	p_irq = stm32_exti_to_irq(host_data->drv_data, hwirq);
+	if (p_irq >= 0) {
+		p_fwspec.fwnode = dm->parent->fwnode;
+		p_fwspec.param_count = 3;
+		p_fwspec.param[0] = GIC_SPI;
+		p_fwspec.param[1] = p_irq;
+		p_fwspec.param[2] = IRQ_TYPE_LEVEL_HIGH;
+
+		return irq_domain_alloc_irqs_parent(dm, virq, 1, &p_fwspec);
+	}
+
+	return 0;
+}
+
+static struct
+stm32_exti_host_data *stm32_exti_host_init(const struct stm32_exti_drv_data *dd,
+					   struct device_node *node)
+{
+	struct stm32_exti_host_data *host_data;
+
+	host_data = kzalloc(sizeof(*host_data), GFP_KERNEL);
+	if (!host_data)
+		return NULL;
+
+	host_data->drv_data = dd;
+	host_data->chips_data = kcalloc(dd->bank_nr,
+					sizeof(struct stm32_exti_chip_data),
+					GFP_KERNEL);
+	if (!host_data->chips_data)
+		return NULL;
+
+	host_data->base = of_iomap(node, 0);
+	if (!host_data->base) {
+		pr_err("%pOF: Unable to map registers\n", node);
+		return NULL;
+	}
+
+	stm32_host_data = host_data;
+
+	return host_data;
+}
+
+static struct
+stm32_exti_chip_data *stm32_exti_chip_init(struct stm32_exti_host_data *h_data,
+					   u32 bank_idx,
+					   struct device_node *node)
+{
+	const struct stm32_exti_bank *stm32_bank;
+	struct stm32_exti_chip_data *chip_data;
+	void __iomem *base = h_data->base;
+	u32 irqs_mask;
+
+	stm32_bank = h_data->drv_data->exti_banks[bank_idx];
+	chip_data = &h_data->chips_data[bank_idx];
+	chip_data->host_data = h_data;
+	chip_data->reg_bank = stm32_bank;
+
+	raw_spin_lock_init(&chip_data->rlock);
+
+	/* Determine number of irqs supported */
+	writel_relaxed(~0UL, base + stm32_bank->rtsr_ofst);
+	irqs_mask = readl_relaxed(base + stm32_bank->rtsr_ofst);
+
+	/*
+	 * This IP has no reset, so after hot reboot we should
+	 * clear registers to avoid residue
+	 */
+	writel_relaxed(0, base + stm32_bank->imr_ofst);
+	writel_relaxed(0, base + stm32_bank->emr_ofst);
+	writel_relaxed(0, base + stm32_bank->rtsr_ofst);
+	writel_relaxed(0, base + stm32_bank->ftsr_ofst);
+	writel_relaxed(~0UL, base + stm32_bank->rpr_ofst);
+	if (stm32_bank->fpr_ofst != UNDEF_REG)
+		writel_relaxed(~0UL, base + stm32_bank->fpr_ofst);
+
+	pr_info("%s: bank%d, External IRQs available:%#x\n",
+		node->full_name, bank_idx, irqs_mask);
+
+	return chip_data;
+}
+
+static int __init stm32_exti_init(const struct stm32_exti_drv_data *drv_data,
+				  struct device_node *node)
+{
+	struct stm32_exti_host_data *host_data;
 	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
-	int nr_irqs, nr_exti, ret, i;
+	int nr_irqs, ret, i;
 	struct irq_chip_generic *gc;
 	struct irq_domain *domain;
-	void *base;
 
-	base = of_iomap(node, 0);
-	if (!base) {
-		pr_err("%pOF: Unable to map registers\n", node);
-		return -ENOMEM;
+	host_data = stm32_exti_host_init(drv_data, node);
+	if (!host_data) {
+		ret = -ENOMEM;
+		goto out_free_mem;
 	}
 
-	domain = irq_domain_add_linear(node, bank_nr * IRQS_PER_BANK,
+	domain = irq_domain_add_linear(node, drv_data->bank_nr * IRQS_PER_BANK,
 				       &irq_exti_domain_ops, NULL);
 	if (!domain) {
 		pr_err("%s: Could not register interrupt domain.\n",
@@ -234,44 +684,32 @@ __init stm32_exti_init(const struct stm32_exti_bank **stm32_exti_banks,
 					     handle_edge_irq, clr, 0, 0);
 	if (ret) {
 		pr_err("%pOF: Could not allocate generic interrupt chip.\n",
-			node);
+		       node);
 		goto out_free_domain;
 	}
 
-	for (i = 0; i < bank_nr; i++) {
-		const struct stm32_exti_bank *stm32_bank = stm32_exti_banks[i];
-		u32 irqs_mask;
+	for (i = 0; i < drv_data->bank_nr; i++) {
+		const struct stm32_exti_bank *stm32_bank;
+		struct stm32_exti_chip_data *chip_data;
+
+		stm32_bank = drv_data->exti_banks[i];
+		chip_data = stm32_exti_chip_init(host_data, i, node);
 
 		gc = irq_get_domain_generic_chip(domain, i * IRQS_PER_BANK);
 
-		gc->reg_base = base;
+		gc->reg_base = host_data->base;
 		gc->chip_types->type = IRQ_TYPE_EDGE_BOTH;
-		gc->chip_types->chip.irq_ack = irq_gc_ack_set_bit;
+		gc->chip_types->chip.irq_ack = stm32_irq_ack;
 		gc->chip_types->chip.irq_mask = irq_gc_mask_clr_bit;
 		gc->chip_types->chip.irq_unmask = irq_gc_mask_set_bit;
 		gc->chip_types->chip.irq_set_type = stm32_irq_set_type;
-		gc->chip_types->chip.irq_set_wake = stm32_irq_set_wake;
-		gc->chip_types->regs.ack = stm32_bank->pr_ofst;
+		gc->chip_types->chip.irq_set_wake = irq_gc_set_wake;
+		gc->suspend = stm32_irq_suspend;
+		gc->resume = stm32_irq_resume;
+		gc->wake_enabled = IRQ_MSK(IRQS_PER_BANK);
+
 		gc->chip_types->regs.mask = stm32_bank->imr_ofst;
-		gc->private = (void *)stm32_bank;
-
-		/* Determine number of irqs supported */
-		writel_relaxed(~0UL, base + stm32_bank->rtsr_ofst);
-		irqs_mask = readl_relaxed(base + stm32_bank->rtsr_ofst);
-		nr_exti = fls(readl_relaxed(base + stm32_bank->rtsr_ofst));
-
-		/*
-		 * This IP has no reset, so after hot reboot we should
-		 * clear registers to avoid residue
-		 */
-		writel_relaxed(0, base + stm32_bank->imr_ofst);
-		writel_relaxed(0, base + stm32_bank->emr_ofst);
-		writel_relaxed(0, base + stm32_bank->rtsr_ofst);
-		writel_relaxed(0, base + stm32_bank->ftsr_ofst);
-		writel_relaxed(~0UL, base + stm32_bank->pr_ofst);
-
-		pr_info("%s: bank%d, External IRQs available:%#x\n",
-			node->full_name, i, irqs_mask);
+		gc->private = (void *)chip_data;
 	}
 
 	nr_irqs = of_irq_count(node);
@@ -287,15 +725,69 @@ __init stm32_exti_init(const struct stm32_exti_bank **stm32_exti_banks,
 out_free_domain:
 	irq_domain_remove(domain);
 out_unmap:
-	iounmap(base);
+	iounmap(host_data->base);
+out_free_mem:
+	kfree(host_data->chips_data);
+	kfree(host_data);
+	return ret;
+}
+
+static const struct irq_domain_ops stm32_exti_h_domain_ops = {
+	.alloc	= stm32_exti_h_domain_alloc,
+	.free	= irq_domain_free_irqs_common,
+};
+
+static int
+__init stm32_exti_hierarchy_init(const struct stm32_exti_drv_data *drv_data,
+				 struct device_node *node,
+				 struct device_node *parent)
+{
+	struct irq_domain *parent_domain, *domain;
+	struct stm32_exti_host_data *host_data;
+	int ret, i;
+
+	parent_domain = irq_find_host(parent);
+	if (!parent_domain) {
+		pr_err("interrupt-parent not found\n");
+		return -EINVAL;
+	}
+
+	host_data = stm32_exti_host_init(drv_data, node);
+	if (!host_data) {
+		ret = -ENOMEM;
+		goto out_free_mem;
+	}
+
+	for (i = 0; i < drv_data->bank_nr; i++)
+		stm32_exti_chip_init(host_data, i, node);
+
+	domain = irq_domain_add_hierarchy(parent_domain, 0,
+					  drv_data->bank_nr * IRQS_PER_BANK,
+					  node, &stm32_exti_h_domain_ops,
+					  host_data);
+
+	if (!domain) {
+		pr_err("%s: Could not register exti domain.\n", node->name);
+		ret = -ENOMEM;
+		goto out_unmap;
+	}
+
+	stm32_exti_h_syscore_init();
+
+	return 0;
+
+out_unmap:
+	iounmap(host_data->base);
+out_free_mem:
+	kfree(host_data->chips_data);
+	kfree(host_data);
 	return ret;
 }
 
 static int __init stm32f4_exti_of_init(struct device_node *np,
 				       struct device_node *parent)
 {
-	return stm32_exti_init(stm32f4xx_exti_banks,
-			ARRAY_SIZE(stm32f4xx_exti_banks), np);
+	return stm32_exti_init(&stm32f4xx_drv_data, np);
 }
 
 IRQCHIP_DECLARE(stm32f4_exti, "st,stm32-exti", stm32f4_exti_of_init);
@@ -303,8 +795,15 @@ IRQCHIP_DECLARE(stm32f4_exti, "st,stm32-exti", stm32f4_exti_of_init);
 static int __init stm32h7_exti_of_init(struct device_node *np,
 				       struct device_node *parent)
 {
-	return stm32_exti_init(stm32h7xx_exti_banks,
-			ARRAY_SIZE(stm32h7xx_exti_banks), np);
+	return stm32_exti_init(&stm32h7xx_drv_data, np);
 }
 
 IRQCHIP_DECLARE(stm32h7_exti, "st,stm32h7-exti", stm32h7_exti_of_init);
+
+static int __init stm32mp1_exti_of_init(struct device_node *np,
+					struct device_node *parent)
+{
+	return stm32_exti_hierarchy_init(&stm32mp1_drv_data, np, parent);
+}
+
+IRQCHIP_DECLARE(stm32mp1_exti, "st,stm32mp1-exti", stm32mp1_exti_of_init);
diff --git a/drivers/irqchip/qcom-irq-combiner.c b/drivers/irqchip/qcom-irq-combiner.c
index f31265937439..7f0c0be322e0 100644
--- a/drivers/irqchip/qcom-irq-combiner.c
+++ b/drivers/irqchip/qcom-irq-combiner.c
@@ -1,4 +1,4 @@
-/* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 and
@@ -68,7 +68,7 @@ static void combiner_handle_irq(struct irq_desc *desc)
 
 		bit = readl_relaxed(combiner->regs[reg].addr);
 		status = bit & combiner->regs[reg].enabled;
-		if (!status)
+		if (bit && !status)
 			pr_warn_ratelimited("Unexpected IRQ on CPU%d: (%08x %08lx %p)\n",
 					    smp_processor_id(), bit,
 					    combiner->regs[reg].enabled,
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 19cd93783c87..baa1ee2bc2ac 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -1340,19 +1340,6 @@ static int capi20_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int capi20_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, capi20_proc_show, NULL);
-}
-
-static const struct file_operations capi20_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= capi20_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /*
  * /proc/capi/capi20ncci:
  *  applid ncci
@@ -1373,23 +1360,10 @@ static int capi20ncci_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int capi20ncci_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, capi20ncci_proc_show, NULL);
-}
-
-static const struct file_operations capi20ncci_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= capi20ncci_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static void __init proc_init(void)
 {
-	proc_create("capi/capi20", 0, NULL, &capi20_proc_fops);
-	proc_create("capi/capi20ncci", 0, NULL, &capi20ncci_proc_fops);
+	proc_create_single("capi/capi20", 0, NULL, capi20_proc_show);
+	proc_create_single("capi/capi20ncci", 0, NULL, capi20ncci_proc_show);
 }
 
 static void __exit proc_exit(void)
diff --git a/drivers/isdn/capi/capidrv.c b/drivers/isdn/capi/capidrv.c
index 49fef08858c5..7ac51798949d 100644
--- a/drivers/isdn/capi/capidrv.c
+++ b/drivers/isdn/capi/capidrv.c
@@ -2460,22 +2460,9 @@ static int capidrv_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int capidrv_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, capidrv_proc_show, NULL);
-}
-
-static const struct file_operations capidrv_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= capidrv_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static void __init proc_init(void)
 {
-	proc_create("capi/capidrv", 0, NULL, &capidrv_proc_fops);
+	proc_create_single("capi/capidrv", 0, NULL, capidrv_proc_show);
 }
 
 static void __exit proc_exit(void)
diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 46c189ad8d94..0ff517d3c98f 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -534,7 +534,8 @@ int attach_capi_ctr(struct capi_ctr *ctr)
 	init_waitqueue_head(&ctr->state_wait_queue);
 
 	sprintf(ctr->procfn, "capi/controllers/%d", ctr->cnr);
-	ctr->procent = proc_create_data(ctr->procfn, 0, NULL, ctr->proc_fops, ctr);
+	ctr->procent = proc_create_single_data(ctr->procfn, 0, NULL,
+			ctr->proc_show, ctr);
 
 	ncontrollers++;
 
diff --git a/drivers/isdn/capi/kcapi_proc.c b/drivers/isdn/capi/kcapi_proc.c
index 68db3c5a1063..c94bd12c0f7c 100644
--- a/drivers/isdn/capi/kcapi_proc.c
+++ b/drivers/isdn/capi/kcapi_proc.c
@@ -108,32 +108,6 @@ static const struct seq_operations seq_contrstats_ops = {
 	.show	= contrstats_show,
 };
 
-static int seq_controller_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &seq_controller_ops);
-}
-
-static int seq_contrstats_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &seq_contrstats_ops);
-}
-
-static const struct file_operations proc_controller_ops = {
-	.owner		= THIS_MODULE,
-	.open		= seq_controller_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations proc_contrstats_ops = {
-	.owner		= THIS_MODULE,
-	.open		= seq_contrstats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 // /proc/capi/applications:
 //      applid l3cnt dblkcnt dblklen #ncci recvqueuelen
 // /proc/capi/applstats:
@@ -216,34 +190,6 @@ static const struct seq_operations seq_applstats_ops = {
 	.show	= applstats_show,
 };
 
-static int
-seq_applications_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &seq_applications_ops);
-}
-
-static int
-seq_applstats_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &seq_applstats_ops);
-}
-
-static const struct file_operations proc_applications_ops = {
-	.owner		= THIS_MODULE,
-	.open		= seq_applications_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations proc_applstats_ops = {
-	.owner		= THIS_MODULE,
-	.open		= seq_applstats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 // ---------------------------------------------------------------------------
 
 static void *capi_driver_start(struct seq_file *seq, loff_t *pos)
@@ -279,22 +225,6 @@ static const struct seq_operations seq_capi_driver_ops = {
 	.show	= capi_driver_show,
 };
 
-static int
-seq_capi_driver_open(struct inode *inode, struct file *file)
-{
-	int err;
-	err = seq_open(file, &seq_capi_driver_ops);
-	return err;
-}
-
-static const struct file_operations proc_driver_ops = {
-	.owner		= THIS_MODULE,
-	.open		= seq_capi_driver_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 // ---------------------------------------------------------------------------
 
 void __init
@@ -302,11 +232,11 @@ kcapi_proc_init(void)
 {
 	proc_mkdir("capi",             NULL);
 	proc_mkdir("capi/controllers", NULL);
-	proc_create("capi/controller",   0, NULL, &proc_controller_ops);
-	proc_create("capi/contrstats",   0, NULL, &proc_contrstats_ops);
-	proc_create("capi/applications", 0, NULL, &proc_applications_ops);
-	proc_create("capi/applstats",    0, NULL, &proc_applstats_ops);
-	proc_create("capi/driver",       0, NULL, &proc_driver_ops);
+	proc_create_seq("capi/controller",   0, NULL, &seq_controller_ops);
+	proc_create_seq("capi/contrstats",   0, NULL, &seq_contrstats_ops);
+	proc_create_seq("capi/applications", 0, NULL, &seq_applications_ops);
+	proc_create_seq("capi/applstats",    0, NULL, &seq_applstats_ops);
+	proc_create_seq("capi/driver",       0, NULL, &seq_capi_driver_ops);
 }
 
 void __exit
diff --git a/drivers/isdn/gigaset/capi.c b/drivers/isdn/gigaset/capi.c
index ccec7778cad2..56748af78c04 100644
--- a/drivers/isdn/gigaset/capi.c
+++ b/drivers/isdn/gigaset/capi.c
@@ -2437,19 +2437,6 @@ static int gigaset_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int gigaset_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, gigaset_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations gigaset_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= gigaset_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /**
  * gigaset_isdn_regdev() - register device to LL
  * @cs:		device descriptor structure.
@@ -2479,7 +2466,7 @@ int gigaset_isdn_regdev(struct cardstate *cs, const char *isdnid)
 	iif->ctr.release_appl  = gigaset_release_appl;
 	iif->ctr.send_message  = gigaset_send_message;
 	iif->ctr.procinfo      = gigaset_procinfo;
-	iif->ctr.proc_fops = &gigaset_proc_fops;
+	iif->ctr.proc_show     = gigaset_proc_show,
 	INIT_LIST_HEAD(&iif->appls);
 	skb_queue_head_init(&iif->sendqueue);
 	atomic_set(&iif->sendqlen, 0);
diff --git a/drivers/isdn/hardware/avm/avmcard.h b/drivers/isdn/hardware/avm/avmcard.h
index c95712dbfa9f..cdfa89c71997 100644
--- a/drivers/isdn/hardware/avm/avmcard.h
+++ b/drivers/isdn/hardware/avm/avmcard.h
@@ -556,7 +556,7 @@ u16  b1_send_message(struct capi_ctr *ctrl, struct sk_buff *skb);
 void b1_parse_version(avmctrl_info *card);
 irqreturn_t b1_interrupt(int interrupt, void *devptr);
 
-extern const struct file_operations b1ctl_proc_fops;
+int b1_proc_show(struct seq_file *m, void *v);
 
 avmcard_dmainfo *avmcard_dma_alloc(char *name, struct pci_dev *,
 				   long rsize, long ssize);
@@ -576,6 +576,6 @@ void b1dma_register_appl(struct capi_ctr *ctrl,
 			 capi_register_params *rp);
 void b1dma_release_appl(struct capi_ctr *ctrl, u16 appl);
 u16  b1dma_send_message(struct capi_ctr *ctrl, struct sk_buff *skb);
-extern const struct file_operations b1dmactl_proc_fops;
+int b1dma_proc_show(struct seq_file *m, void *v);
 
 #endif /* _AVMCARD_H_ */
diff --git a/drivers/isdn/hardware/avm/b1.c b/drivers/isdn/hardware/avm/b1.c
index b1833d08a5fe..5ee5489d3f15 100644
--- a/drivers/isdn/hardware/avm/b1.c
+++ b/drivers/isdn/hardware/avm/b1.c
@@ -637,7 +637,7 @@ irqreturn_t b1_interrupt(int interrupt, void *devptr)
 }
 
 /* ------------------------------------------------------------- */
-static int b1ctl_proc_show(struct seq_file *m, void *v)
+int b1_proc_show(struct seq_file *m, void *v)
 {
 	struct capi_ctr *ctrl = m->private;
 	avmctrl_info *cinfo = (avmctrl_info *)(ctrl->driverdata);
@@ -699,20 +699,7 @@ static int b1ctl_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int b1ctl_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, b1ctl_proc_show, PDE_DATA(inode));
-}
-
-const struct file_operations b1ctl_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= b1ctl_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-EXPORT_SYMBOL(b1ctl_proc_fops);
+EXPORT_SYMBOL(b1_proc_show);
 
 /* ------------------------------------------------------------- */
 
diff --git a/drivers/isdn/hardware/avm/b1dma.c b/drivers/isdn/hardware/avm/b1dma.c
index 9538a9e5e1a8..6a3dc9937ce5 100644
--- a/drivers/isdn/hardware/avm/b1dma.c
+++ b/drivers/isdn/hardware/avm/b1dma.c
@@ -858,7 +858,7 @@ u16 b1dma_send_message(struct capi_ctr *ctrl, struct sk_buff *skb)
 
 /* ------------------------------------------------------------- */
 
-static int b1dmactl_proc_show(struct seq_file *m, void *v)
+int b1dma_proc_show(struct seq_file *m, void *v)
 {
 	struct capi_ctr *ctrl = m->private;
 	avmctrl_info *cinfo = (avmctrl_info *)(ctrl->driverdata);
@@ -941,20 +941,7 @@ static int b1dmactl_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int b1dmactl_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, b1dmactl_proc_show, PDE_DATA(inode));
-}
-
-const struct file_operations b1dmactl_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= b1dmactl_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-EXPORT_SYMBOL(b1dmactl_proc_fops);
+EXPORT_SYMBOL(b1dma_proc_show);
 
 /* ------------------------------------------------------------- */
 
diff --git a/drivers/isdn/hardware/avm/b1isa.c b/drivers/isdn/hardware/avm/b1isa.c
index 54e871a47387..cdfea72e0ef6 100644
--- a/drivers/isdn/hardware/avm/b1isa.c
+++ b/drivers/isdn/hardware/avm/b1isa.c
@@ -121,7 +121,7 @@ static int b1isa_probe(struct pci_dev *pdev)
 	cinfo->capi_ctrl.load_firmware = b1_load_firmware;
 	cinfo->capi_ctrl.reset_ctr     = b1_reset_ctr;
 	cinfo->capi_ctrl.procinfo      = b1isa_procinfo;
-	cinfo->capi_ctrl.proc_fops = &b1ctl_proc_fops;
+	cinfo->capi_ctrl.proc_show     = b1_proc_show;
 	strcpy(cinfo->capi_ctrl.name, card->name);
 
 	retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/b1pci.c b/drivers/isdn/hardware/avm/b1pci.c
index ac4863c2ecbc..b76b57a82c02 100644
--- a/drivers/isdn/hardware/avm/b1pci.c
+++ b/drivers/isdn/hardware/avm/b1pci.c
@@ -112,7 +112,7 @@ static int b1pci_probe(struct capicardparams *p, struct pci_dev *pdev)
 	cinfo->capi_ctrl.load_firmware = b1_load_firmware;
 	cinfo->capi_ctrl.reset_ctr     = b1_reset_ctr;
 	cinfo->capi_ctrl.procinfo      = b1pci_procinfo;
-	cinfo->capi_ctrl.proc_fops = &b1ctl_proc_fops;
+	cinfo->capi_ctrl.proc_show     = b1_proc_show;
 	strcpy(cinfo->capi_ctrl.name, card->name);
 	cinfo->capi_ctrl.owner         = THIS_MODULE;
 
@@ -251,7 +251,7 @@ static int b1pciv4_probe(struct capicardparams *p, struct pci_dev *pdev)
 	cinfo->capi_ctrl.load_firmware = b1dma_load_firmware;
 	cinfo->capi_ctrl.reset_ctr     = b1dma_reset_ctr;
 	cinfo->capi_ctrl.procinfo      = b1pciv4_procinfo;
-	cinfo->capi_ctrl.proc_fops = &b1dmactl_proc_fops;
+	cinfo->capi_ctrl.proc_show     = b1dma_proc_show;
 	strcpy(cinfo->capi_ctrl.name, card->name);
 
 	retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/b1pcmcia.c b/drivers/isdn/hardware/avm/b1pcmcia.c
index 6b0d19d963d5..3aca16e62902 100644
--- a/drivers/isdn/hardware/avm/b1pcmcia.c
+++ b/drivers/isdn/hardware/avm/b1pcmcia.c
@@ -108,7 +108,7 @@ static int b1pcmcia_add_card(unsigned int port, unsigned irq,
 	cinfo->capi_ctrl.load_firmware = b1_load_firmware;
 	cinfo->capi_ctrl.reset_ctr     = b1_reset_ctr;
 	cinfo->capi_ctrl.procinfo      = b1pcmcia_procinfo;
-	cinfo->capi_ctrl.proc_fops = &b1ctl_proc_fops;
+	cinfo->capi_ctrl.proc_show     = b1_proc_show;
 	strcpy(cinfo->capi_ctrl.name, card->name);
 
 	retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/c4.c b/drivers/isdn/hardware/avm/c4.c
index 034cabac699d..ac72cd204c4d 100644
--- a/drivers/isdn/hardware/avm/c4.c
+++ b/drivers/isdn/hardware/avm/c4.c
@@ -1127,19 +1127,6 @@ static int c4_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int c4_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, c4_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations c4_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= c4_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /* ------------------------------------------------------------- */
 
 static int c4_add_card(struct capicardparams *p, struct pci_dev *dev,
@@ -1211,7 +1198,7 @@ static int c4_add_card(struct capicardparams *p, struct pci_dev *dev,
 		cinfo->capi_ctrl.load_firmware = c4_load_firmware;
 		cinfo->capi_ctrl.reset_ctr     = c4_reset_ctr;
 		cinfo->capi_ctrl.procinfo      = c4_procinfo;
-		cinfo->capi_ctrl.proc_fops = &c4_proc_fops;
+		cinfo->capi_ctrl.proc_show     = c4_proc_show;
 		strcpy(cinfo->capi_ctrl.name, card->name);
 
 		retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/t1isa.c b/drivers/isdn/hardware/avm/t1isa.c
index 9f80d20ced87..2153619c5b31 100644
--- a/drivers/isdn/hardware/avm/t1isa.c
+++ b/drivers/isdn/hardware/avm/t1isa.c
@@ -430,7 +430,7 @@ static int t1isa_probe(struct pci_dev *pdev, int cardnr)
 	cinfo->capi_ctrl.load_firmware = t1isa_load_firmware;
 	cinfo->capi_ctrl.reset_ctr     = t1isa_reset_ctr;
 	cinfo->capi_ctrl.procinfo      = t1isa_procinfo;
-	cinfo->capi_ctrl.proc_fops = &b1ctl_proc_fops;
+	cinfo->capi_ctrl.proc_show     = b1_proc_show;
 	strcpy(cinfo->capi_ctrl.name, card->name);
 
 	retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/t1pci.c b/drivers/isdn/hardware/avm/t1pci.c
index 2180b1685691..f5ed1d5004c9 100644
--- a/drivers/isdn/hardware/avm/t1pci.c
+++ b/drivers/isdn/hardware/avm/t1pci.c
@@ -119,7 +119,7 @@ static int t1pci_add_card(struct capicardparams *p, struct pci_dev *pdev)
 	cinfo->capi_ctrl.load_firmware = b1dma_load_firmware;
 	cinfo->capi_ctrl.reset_ctr     = b1dma_reset_ctr;
 	cinfo->capi_ctrl.procinfo      = t1pci_procinfo;
-	cinfo->capi_ctrl.proc_fops = &b1dmactl_proc_fops;
+	cinfo->capi_ctrl.proc_show     = b1dma_proc_show;
 	strcpy(cinfo->capi_ctrl.name, card->name);
 
 	retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/eicon/capimain.c b/drivers/isdn/hardware/eicon/capimain.c
index be36d82004d6..f9244dc1c3c9 100644
--- a/drivers/isdn/hardware/eicon/capimain.c
+++ b/drivers/isdn/hardware/eicon/capimain.c
@@ -90,19 +90,6 @@ static int diva_ctl_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int diva_ctl_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, diva_ctl_proc_show, NULL);
-}
-
-static const struct file_operations diva_ctl_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= diva_ctl_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /*
  * set additional os settings in capi_ctr struct
  */
@@ -111,7 +98,7 @@ void diva_os_set_controller_struct(struct capi_ctr *ctrl)
 	ctrl->driver_name = DRIVERLNAME;
 	ctrl->load_firmware = NULL;
 	ctrl->reset_ctr = NULL;
-	ctrl->proc_fops = &diva_ctl_proc_fops;
+	ctrl->proc_show = diva_ctl_proc_show;
 	ctrl->owner = THIS_MODULE;
 }
 
diff --git a/drivers/isdn/hardware/eicon/diva.c b/drivers/isdn/hardware/eicon/diva.c
index 944a7f338099..1b25d8bc153a 100644
--- a/drivers/isdn/hardware/eicon/diva.c
+++ b/drivers/isdn/hardware/eicon/diva.c
@@ -388,10 +388,10 @@ void divasa_xdi_driver_unload(void)
 **  Receive and process command from user mode utility
 */
 void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
-			    int length,
+			    int length, void *mptr,
 			    divas_xdi_copy_from_user_fn_t cp_fn)
 {
-	diva_xdi_um_cfg_cmd_t msg;
+	diva_xdi_um_cfg_cmd_t *msg = (diva_xdi_um_cfg_cmd_t *)mptr;
 	diva_os_xdi_adapter_t *a = NULL;
 	diva_os_spin_lock_magic_t old_irql;
 	struct list_head *tmp;
@@ -401,21 +401,21 @@ void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
 			 length, sizeof(diva_xdi_um_cfg_cmd_t)))
 			return NULL;
 	}
-	if ((*cp_fn) (os_handle, &msg, src, sizeof(msg)) <= 0) {
+	if ((*cp_fn) (os_handle, msg, src, sizeof(*msg)) <= 0) {
 		DBG_ERR(("A: A(?) open, write error"))
 			return NULL;
 	}
 	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "open_adapter");
 	list_for_each(tmp, &adapter_queue) {
 		a = list_entry(tmp, diva_os_xdi_adapter_t, link);
-		if (a->controller == (int)msg.adapter)
+		if (a->controller == (int)msg->adapter)
 			break;
 		a = NULL;
 	}
 	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "open_adapter");
 
 	if (!a) {
-		DBG_ERR(("A: A(%d) open, adapter not found", msg.adapter))
+		DBG_ERR(("A: A(%d) open, adapter not found", msg->adapter))
 			}
 
 	return (a);
@@ -437,8 +437,10 @@ void diva_xdi_close_adapter(void *adapter, void *os_handle)
 
 int
 diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
-	       int length, divas_xdi_copy_from_user_fn_t cp_fn)
+	       int length, void *mptr,
+	       divas_xdi_copy_from_user_fn_t cp_fn)
 {
+	diva_xdi_um_cfg_cmd_t *msg = (diva_xdi_um_cfg_cmd_t *)mptr;
 	diva_os_xdi_adapter_t *a = (diva_os_xdi_adapter_t *) adapter;
 	void *data;
 
@@ -459,7 +461,13 @@ diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
 			return (-2);
 	}
 
-	length = (*cp_fn) (os_handle, data, src, length);
+	if (msg) {
+		*(diva_xdi_um_cfg_cmd_t *)data = *msg;
+		length = (*cp_fn) (os_handle, (char *)data + sizeof(*msg),
+				   src + sizeof(*msg), length - sizeof(*msg));
+	} else {
+		length = (*cp_fn) (os_handle, data, src, length);
+	}
 	if (length > 0) {
 		if ((*(a->interface.cmd_proc))
 		    (a, (diva_xdi_um_cfg_cmd_t *) data, length)) {
diff --git a/drivers/isdn/hardware/eicon/diva.h b/drivers/isdn/hardware/eicon/diva.h
index b067032093a8..1ad76650fbf9 100644
--- a/drivers/isdn/hardware/eicon/diva.h
+++ b/drivers/isdn/hardware/eicon/diva.h
@@ -20,10 +20,11 @@ int diva_xdi_read(void *adapter, void *os_handle, void __user *dst,
 		  int max_length, divas_xdi_copy_to_user_fn_t cp_fn);
 
 int diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
-		   int length, divas_xdi_copy_from_user_fn_t cp_fn);
+		   int length, void *msg,
+		   divas_xdi_copy_from_user_fn_t cp_fn);
 
 void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
-			    int length,
+			    int length, void *msg,
 			    divas_xdi_copy_from_user_fn_t cp_fn);
 
 void diva_xdi_close_adapter(void *adapter, void *os_handle);
diff --git a/drivers/isdn/hardware/eicon/diva_didd.c b/drivers/isdn/hardware/eicon/diva_didd.c
index fab6ccfb00d5..60e79257dd5f 100644
--- a/drivers/isdn/hardware/eicon/diva_didd.c
+++ b/drivers/isdn/hardware/eicon/diva_didd.c
@@ -78,26 +78,13 @@ static int divadidd_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int divadidd_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, divadidd_proc_show, NULL);
-}
-
-static const struct file_operations divadidd_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= divadidd_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init create_proc(void)
 {
 	proc_net_eicon = proc_mkdir("eicon", init_net.proc_net);
 
 	if (proc_net_eicon) {
-		proc_didd = proc_create(DRIVERLNAME, S_IRUGO, proc_net_eicon,
-					&divadidd_proc_fops);
+		proc_didd = proc_create_single(DRIVERLNAME, S_IRUGO,
+				proc_net_eicon, divadidd_proc_show);
 		return (1);
 	}
 	return (0);
diff --git a/drivers/isdn/hardware/eicon/divasi.c b/drivers/isdn/hardware/eicon/divasi.c
index 525518c945fe..e7081e0c0e35 100644
--- a/drivers/isdn/hardware/eicon/divasi.c
+++ b/drivers/isdn/hardware/eicon/divasi.c
@@ -101,23 +101,10 @@ static int um_idi_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int um_idi_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, um_idi_proc_show, NULL);
-}
-
-static const struct file_operations um_idi_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= um_idi_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init create_um_idi_proc(void)
 {
-	um_idi_proc_entry = proc_create(DRIVERLNAME, S_IRUGO, proc_net_eicon,
-					&um_idi_proc_fops);
+	um_idi_proc_entry = proc_create_single(DRIVERLNAME, S_IRUGO,
+			proc_net_eicon, um_idi_proc_show);
 	if (!um_idi_proc_entry)
 		return (0);
 	return (1);
diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c
index b9980e84f9db..b6a3950b2564 100644
--- a/drivers/isdn/hardware/eicon/divasmain.c
+++ b/drivers/isdn/hardware/eicon/divasmain.c
@@ -591,19 +591,22 @@ static int divas_release(struct inode *inode, struct file *file)
 static ssize_t divas_write(struct file *file, const char __user *buf,
 			   size_t count, loff_t *ppos)
 {
+	diva_xdi_um_cfg_cmd_t msg;
 	int ret = -EINVAL;
 
 	if (!file->private_data) {
 		file->private_data = diva_xdi_open_adapter(file, buf,
-							   count,
+							   count, &msg,
 							   xdi_copy_from_user);
-	}
-	if (!file->private_data) {
-		return (-ENODEV);
+		if (!file->private_data)
+			return (-ENODEV);
+		ret = diva_xdi_write(file->private_data, file,
+				     buf, count, &msg, xdi_copy_from_user);
+	} else {
+		ret = diva_xdi_write(file->private_data, file,
+				     buf, count, NULL, xdi_copy_from_user);
 	}
 
-	ret = diva_xdi_write(file->private_data, file,
-			     buf, count, xdi_copy_from_user);
 	switch (ret) {
 	case -1:		/* Message should be removed from rx mailbox first */
 		ret = -EBUSY;
@@ -622,11 +625,12 @@ static ssize_t divas_write(struct file *file, const char __user *buf,
 static ssize_t divas_read(struct file *file, char __user *buf,
 			  size_t count, loff_t *ppos)
 {
+	diva_xdi_um_cfg_cmd_t msg;
 	int ret = -EINVAL;
 
 	if (!file->private_data) {
 		file->private_data = diva_xdi_open_adapter(file, buf,
-							   count,
+							   count, &msg,
 							   xdi_copy_from_user);
 	}
 	if (!file->private_data) {
diff --git a/drivers/isdn/hysdn/hycapi.c b/drivers/isdn/hysdn/hycapi.c
index eac0f51a0f60..a2c15cd7bf67 100644
--- a/drivers/isdn/hysdn/hycapi.c
+++ b/drivers/isdn/hysdn/hycapi.c
@@ -467,19 +467,6 @@ static int hycapi_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int hycapi_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hycapi_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations hycapi_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= hycapi_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /**************************************************************
 hycapi_load_firmware
 
@@ -774,7 +761,7 @@ hycapi_capi_create(hysdn_card *card)
 		ctrl->load_firmware = hycapi_load_firmware;
 		ctrl->reset_ctr     = hycapi_reset_ctr;
 		ctrl->procinfo      = hycapi_procinfo;
-		ctrl->proc_fops = &hycapi_proc_fops;
+		ctrl->proc_show     = hycapi_proc_show;
 		strcpy(ctrl->name, cinfo->cardname);
 		ctrl->owner = THIS_MODULE;
 
diff --git a/drivers/isdn/mISDN/dsp_hwec.c b/drivers/isdn/mISDN/dsp_hwec.c
index a6e87076acc2..5336bbdbfdc5 100644
--- a/drivers/isdn/mISDN/dsp_hwec.c
+++ b/drivers/isdn/mISDN/dsp_hwec.c
@@ -68,12 +68,12 @@ void dsp_hwec_enable(struct dsp *dsp, const char *arg)
 		goto _do;
 
 	{
-		char _dup[len + 1];
 		char *dup, *tok, *name, *val;
 		int tmp;
 
-		strcpy(_dup, arg);
-		dup = _dup;
+		dup = kstrdup(arg, GFP_ATOMIC);
+		if (!dup)
+			return;
 
 		while ((tok = strsep(&dup, ","))) {
 			if (!strlen(tok))
@@ -89,6 +89,8 @@ void dsp_hwec_enable(struct dsp *dsp, const char *arg)
 					deftaps = tmp;
 			}
 		}
+
+		kfree(dup);
 	}
 
 _do:
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index 21d50e4cc5e1..b05022f94f18 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -279,7 +279,7 @@ l1oip_socket_send(struct l1oip *hc, u8 localcodec, u8 channel, u32 chanmask,
 		  u16 timebase, u8 *buf, int len)
 {
 	u8 *p;
-	u8 frame[len + 32];
+	u8 frame[MAX_DFRAME_LEN_L1 + 32];
 	struct socket *socket = NULL;
 
 	if (debug & DEBUG_L1OIP_MSG)
@@ -902,7 +902,11 @@ handle_dmsg(struct mISDNchannel *ch, struct sk_buff *skb)
 		p = skb->data;
 		l = skb->len;
 		while (l) {
-			ll = (l < L1OIP_MAX_PERFRAME) ? l : L1OIP_MAX_PERFRAME;
+			/*
+			 * This is technically bounded by L1OIP_MAX_PERFRAME but
+			 * MAX_DFRAME_LEN_L1 < L1OIP_MAX_PERFRAME
+			 */
+			ll = (l < MAX_DFRAME_LEN_L1) ? l : MAX_DFRAME_LEN_L1;
 			l1oip_socket_send(hc, 0, dch->slot, 0,
 					  hc->chan[dch->slot].tx_counter++, p, ll);
 			p += ll;
@@ -1140,7 +1144,11 @@ handle_bmsg(struct mISDNchannel *ch, struct sk_buff *skb)
 		p = skb->data;
 		l = skb->len;
 		while (l) {
-			ll = (l < L1OIP_MAX_PERFRAME) ? l : L1OIP_MAX_PERFRAME;
+			/*
+			 * This is technically bounded by L1OIP_MAX_PERFRAME but
+			 * MAX_DFRAME_LEN_L1 < L1OIP_MAX_PERFRAME
+			 */
+			ll = (l < MAX_DFRAME_LEN_L1) ? l : MAX_DFRAME_LEN_L1;
 			l1oip_socket_send(hc, hc->codec, bch->slot, 0,
 					  hc->chan[bch->slot].tx_counter, p, ll);
 			hc->chan[bch->slot].tx_counter += ll;
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 1f8f489b4167..98f90aadd141 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -588,7 +588,7 @@ static const struct proto_ops data_sock_ops = {
 	.getname	= data_sock_getname,
 	.sendmsg	= mISDN_sock_sendmsg,
 	.recvmsg	= mISDN_sock_recvmsg,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= data_sock_setsockopt,
@@ -745,7 +745,6 @@ static const struct proto_ops base_sock_ops = {
 	.getname	= sock_no_getname,
 	.sendmsg	= sock_no_sendmsg,
 	.recvmsg	= sock_no_recvmsg,
-	.poll		= sock_no_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 2c896c0e69e1..6e3a998f3370 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -104,6 +104,19 @@ config LEDS_CPCAP
 	  This option enables support for LEDs offered by Motorola's
 	  CPCAP PMIC.
 
+config LEDS_CR0014114
+	tristate "LED Support for Crane CR0014114"
+	depends on LEDS_CLASS
+	depends on SPI
+	depends on OF
+	help
+	  This option enables support for CR0014114 LED Board which
+	  is widely used in vending machines produced by
+	  Crane Merchandising Systems.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called leds-cr0014114.
+
 config LEDS_LM3530
 	tristate "LCD Backlight driver for LM3530"
 	depends on LEDS_CLASS
@@ -145,6 +158,15 @@ config LEDS_LM3692X
 	  This option enables support for the TI LM3692x family
 	  of white LED string drivers used for backlighting.
 
+config LEDS_LM3601X
+	tristate "LED support for LM3601x Chips"
+	depends on LEDS_CLASS && I2C
+	depends on LEDS_CLASS_FLASH
+	select REGMAP_I2C
+	help
+	  This option enables support for the TI LM3601x family
+	  of flash, torch and indicator classes.
+
 config LEDS_LOCOMO
 	tristate "LED Support for Locomo device"
 	depends on LEDS_CLASS
@@ -647,6 +669,17 @@ config LEDS_IS31FL32XX
 	  LED controllers. They are I2C devices with multiple constant-current
 	  channels, each with independent 256-level PWM control.
 
+config LEDS_SC27XX_BLTC
+	tristate "LED support for the SC27xx breathing light controller"
+	depends on LEDS_CLASS && MFD_SC27XX_PMIC
+	depends on OF
+	help
+	  Say Y here to include support for the SC27xx breathing light controller
+	  LEDs.
+
+	  This driver can also be built as a module. If so the module will be
+	  called leds-sc27xx-bltc.
+
 comment "LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM)"
 
 config LEDS_BLINKM
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 91eca81cae82..420b5d2cfa62 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -76,8 +76,11 @@ obj-$(CONFIG_LEDS_MLXREG)		+= leds-mlxreg.o
 obj-$(CONFIG_LEDS_NIC78BX)		+= leds-nic78bx.o
 obj-$(CONFIG_LEDS_MT6323)		+= leds-mt6323.o
 obj-$(CONFIG_LEDS_LM3692X)		+= leds-lm3692x.o
+obj-$(CONFIG_LEDS_SC27XX_BLTC)		+= leds-sc27xx-bltc.o
+obj-$(CONFIG_LEDS_LM3601X)		+= leds-lm3601x.o
 
 # LED SPI Drivers
+obj-$(CONFIG_LEDS_CR0014114)		+= leds-cr0014114.o
 obj-$(CONFIG_LEDS_DAC124S085)		+= leds-dac124s085.o
 
 # LED Userspace Drivers
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index b0e2d55acbd6..3c7e3487b373 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -260,10 +260,14 @@ int of_led_classdev_register(struct device *parent, struct device_node *np,
 	if (ret < 0)
 		return ret;
 
+	mutex_init(&led_cdev->led_access);
+	mutex_lock(&led_cdev->led_access);
 	led_cdev->dev = device_create_with_groups(leds_class, parent, 0,
 				led_cdev, led_cdev->groups, "%s", name);
-	if (IS_ERR(led_cdev->dev))
+	if (IS_ERR(led_cdev->dev)) {
+		mutex_unlock(&led_cdev->led_access);
 		return PTR_ERR(led_cdev->dev);
+	}
 	led_cdev->dev->of_node = np;
 
 	if (ret)
@@ -274,6 +278,7 @@ int of_led_classdev_register(struct device *parent, struct device_node *np,
 		ret = led_add_brightness_hw_changed(led_cdev);
 		if (ret) {
 			device_unregister(led_cdev->dev);
+			mutex_unlock(&led_cdev->led_access);
 			return ret;
 		}
 	}
@@ -285,7 +290,6 @@ int of_led_classdev_register(struct device *parent, struct device_node *np,
 #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED
 	led_cdev->brightness_hw_changed = -1;
 #endif
-	mutex_init(&led_cdev->led_access);
 	/* add to the list of leds */
 	down_write(&leds_list_lock);
 	list_add_tail(&led_cdev->node, &leds_list);
@@ -302,6 +306,8 @@ int of_led_classdev_register(struct device *parent, struct device_node *np,
 	led_trigger_set_default(led_cdev);
 #endif
 
+	mutex_unlock(&led_cdev->led_access);
+
 	dev_dbg(parent, "Registered led device: %s\n",
 			led_cdev->name);
 
diff --git a/drivers/leds/leds-cr0014114.c b/drivers/leds/leds-cr0014114.c
new file mode 100644
index 000000000000..a4b1c1dcce7f
--- /dev/null
+++ b/drivers/leds/leds-cr0014114.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Crane Merchandising Systems. All rights reserved.
+// Copyright (C) 2018 Oleh Kravchenko <oleg@kaa.org.ua>
+
+#include <linux/delay.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+#include <linux/workqueue.h>
+#include <uapi/linux/uleds.h>
+
+/*
+ *  CR0014114 SPI protocol descrtiption:
+ *  +----+-----------------------------------+----+
+ *  | CMD|             BRIGHTNESS            |CRC |
+ *  +----+-----------------------------------+----+
+ *  |    | LED0| LED1| LED2| LED3| LED4| LED5|    |
+ *  |    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+    |
+ *  |    |R|G|B|R|G|B|R|G|B|R|G|B|R|G|B|R|G|B|    |
+ *  | 1  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 1  |
+ *  |    |1|1|1|1|1|1|1|1|1|1|1|1|1|1|1|1|1|1|    |
+ *  |    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+    |
+ *  |    |               18                  |    |
+ *  +----+-----------------------------------+----+
+ *  |                    20                       |
+ *  +---------------------------------------------+
+ *
+ *  PS: Boards can be connected to the chain:
+ *      SPI -> board0 -> board1 -> board2 ..
+ */
+
+/* CR0014114 SPI commands */
+#define CR_SET_BRIGHTNESS	0x80
+#define CR_INIT_REENUMERATE	0x81
+#define CR_NEXT_REENUMERATE	0x82
+
+/* CR0014114 default settings */
+#define CR_MAX_BRIGHTNESS	GENMASK(6, 0)
+#define CR_FW_DELAY_MSEC	10
+#define CR_RECOUNT_DELAY	(HZ * 3600)
+
+struct cr0014114_led {
+	char			name[LED_MAX_NAME_SIZE];
+	struct cr0014114	*priv;
+	struct led_classdev	ldev;
+	u8			brightness;
+};
+
+struct cr0014114 {
+	bool			do_recount;
+	size_t			count;
+	struct delayed_work	work;
+	struct device		*dev;
+	struct mutex		lock;
+	struct spi_device	*spi;
+	u8			*buf;
+	unsigned long		delay;
+	struct cr0014114_led	leds[];
+};
+
+static void cr0014114_calc_crc(u8 *buf, const size_t len)
+{
+	size_t	i;
+	u8	crc;
+
+	for (i = 1, crc = 1; i < len - 1; i++)
+		crc += buf[i];
+	crc |= BIT(7);
+
+	/* special case when CRC matches the SPI commands */
+	if (crc == CR_SET_BRIGHTNESS ||
+	    crc == CR_INIT_REENUMERATE ||
+	    crc == CR_NEXT_REENUMERATE)
+		crc = 0xfe;
+
+	buf[len - 1] = crc;
+}
+
+static int cr0014114_recount(struct cr0014114 *priv)
+{
+	int	ret;
+	size_t	i;
+	u8	cmd;
+
+	dev_dbg(priv->dev, "LEDs recount is started\n");
+
+	cmd = CR_INIT_REENUMERATE;
+	ret = spi_write(priv->spi, &cmd, sizeof(cmd));
+	if (ret)
+		goto err;
+
+	cmd = CR_NEXT_REENUMERATE;
+	for (i = 0; i < priv->count; i++) {
+		msleep(CR_FW_DELAY_MSEC);
+
+		ret = spi_write(priv->spi, &cmd, sizeof(cmd));
+		if (ret)
+			goto err;
+	}
+
+err:
+	dev_dbg(priv->dev, "LEDs recount is finished\n");
+
+	if (ret)
+		dev_err(priv->dev, "with error %d", ret);
+
+	return ret;
+}
+
+static int cr0014114_sync(struct cr0014114 *priv)
+{
+	int		ret;
+	size_t		i;
+	unsigned long	udelay, now = jiffies;
+
+	/* to avoid SPI mistiming with firmware we should wait some time */
+	if (time_after(priv->delay, now)) {
+		udelay = jiffies_to_usecs(priv->delay - now);
+		usleep_range(udelay, udelay + 1);
+	}
+
+	if (unlikely(priv->do_recount)) {
+		ret = cr0014114_recount(priv);
+		if (ret)
+			goto err;
+
+		priv->do_recount = false;
+		msleep(CR_FW_DELAY_MSEC);
+	}
+
+	priv->buf[0] = CR_SET_BRIGHTNESS;
+	for (i = 0; i < priv->count; i++)
+		priv->buf[i + 1] = priv->leds[i].brightness;
+	cr0014114_calc_crc(priv->buf, priv->count + 2);
+	ret = spi_write(priv->spi, priv->buf, priv->count + 2);
+
+err:
+	priv->delay = jiffies + msecs_to_jiffies(CR_FW_DELAY_MSEC);
+
+	return ret;
+}
+
+static void cr0014114_recount_work(struct work_struct *work)
+{
+	int			ret;
+	struct cr0014114	*priv = container_of(work,
+						     struct cr0014114,
+						     work.work);
+
+	mutex_lock(&priv->lock);
+	priv->do_recount = true;
+	ret = cr0014114_sync(priv);
+	mutex_unlock(&priv->lock);
+
+	if (ret)
+		dev_warn(priv->dev, "sync of LEDs failed %d\n", ret);
+
+	schedule_delayed_work(&priv->work, CR_RECOUNT_DELAY);
+}
+
+static int cr0014114_set_sync(struct led_classdev *ldev,
+			      enum led_brightness brightness)
+{
+	int			ret;
+	struct cr0014114_led    *led = container_of(ldev,
+						    struct cr0014114_led,
+						    ldev);
+
+	dev_dbg(led->priv->dev, "Set brightness of %s to %d\n",
+		led->name, brightness);
+
+	mutex_lock(&led->priv->lock);
+	led->brightness = (u8)brightness;
+	ret = cr0014114_sync(led->priv);
+	mutex_unlock(&led->priv->lock);
+
+	return ret;
+}
+
+static int cr0014114_probe_dt(struct cr0014114 *priv)
+{
+	size_t			i = 0;
+	struct cr0014114_led	*led;
+	struct fwnode_handle	*child;
+	struct device_node	*np;
+	int			ret;
+	const char		*str;
+
+	device_for_each_child_node(priv->dev, child) {
+		np = to_of_node(child);
+		led = &priv->leds[i];
+
+		ret = fwnode_property_read_string(child, "label", &str);
+		if (ret)
+			snprintf(led->name, sizeof(led->name),
+				 "cr0014114::");
+		else
+			snprintf(led->name, sizeof(led->name),
+				 "cr0014114:%s", str);
+
+		fwnode_property_read_string(child, "linux,default-trigger",
+					    &led->ldev.default_trigger);
+
+		led->priv			  = priv;
+		led->ldev.name			  = led->name;
+		led->ldev.max_brightness	  = CR_MAX_BRIGHTNESS;
+		led->ldev.brightness_set_blocking = cr0014114_set_sync;
+
+		ret = devm_of_led_classdev_register(priv->dev, np,
+						    &led->ldev);
+		if (ret) {
+			dev_err(priv->dev,
+				"failed to register LED device %s, err %d",
+				led->name, ret);
+			fwnode_handle_put(child);
+			return ret;
+		}
+
+		led->ldev.dev->of_node = np;
+
+		i++;
+	}
+
+	return 0;
+}
+
+static int cr0014114_probe(struct spi_device *spi)
+{
+	struct cr0014114	*priv;
+	size_t			count;
+	int			ret;
+
+	count = device_get_child_node_count(&spi->dev);
+	if (!count) {
+		dev_err(&spi->dev, "LEDs are not defined in device tree!");
+		return -ENODEV;
+	}
+
+	priv = devm_kzalloc(&spi->dev,
+			    sizeof(*priv) + sizeof(*priv->leds) * count,
+			    GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->buf = devm_kzalloc(&spi->dev, count + 2, GFP_KERNEL);
+	if (!priv->buf)
+		return -ENOMEM;
+
+	mutex_init(&priv->lock);
+	INIT_DELAYED_WORK(&priv->work, cr0014114_recount_work);
+	priv->count	= count;
+	priv->dev	= &spi->dev;
+	priv->spi	= spi;
+	priv->delay	= jiffies -
+			  msecs_to_jiffies(CR_FW_DELAY_MSEC);
+
+	priv->do_recount = true;
+	ret = cr0014114_sync(priv);
+	if (ret) {
+		dev_err(priv->dev, "first recount failed %d\n", ret);
+		return ret;
+	}
+
+	priv->do_recount = true;
+	ret = cr0014114_sync(priv);
+	if (ret) {
+		dev_err(priv->dev, "second recount failed %d\n", ret);
+		return ret;
+	}
+
+	ret = cr0014114_probe_dt(priv);
+	if (ret)
+		return ret;
+
+	/* setup recount work to workaround buggy firmware */
+	schedule_delayed_work(&priv->work, CR_RECOUNT_DELAY);
+
+	spi_set_drvdata(spi, priv);
+
+	return 0;
+}
+
+static int cr0014114_remove(struct spi_device *spi)
+{
+	struct cr0014114 *priv = spi_get_drvdata(spi);
+
+	cancel_delayed_work_sync(&priv->work);
+	mutex_destroy(&priv->lock);
+
+	return 0;
+}
+
+static const struct of_device_id cr0014114_dt_ids[] = {
+	{ .compatible = "crane,cr0014114", },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, cr0014114_dt_ids);
+
+static struct spi_driver cr0014114_driver = {
+	.probe		= cr0014114_probe,
+	.remove		= cr0014114_remove,
+	.driver = {
+		.name		= KBUILD_MODNAME,
+		.of_match_table	= cr0014114_dt_ids,
+	},
+};
+
+module_spi_driver(cr0014114_driver);
+
+MODULE_AUTHOR("Oleh Kravchenko <oleg@kaa.org.ua>");
+MODULE_DESCRIPTION("cr0014114 LED driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("spi:cr0014114");
diff --git a/drivers/leds/leds-lm3601x.c b/drivers/leds/leds-lm3601x.c
new file mode 100644
index 000000000000..081aa71e43a3
--- /dev/null
+++ b/drivers/leds/leds-lm3601x.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0
+// Flash and torch driver for Texas Instruments LM3601X LED
+// Flash driver chip family
+// Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com/
+
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/leds.h>
+#include <linux/led-class-flash.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <uapi/linux/uleds.h>
+
+#define LM3601X_LED_IR		0x0
+#define LM3601X_LED_TORCH	0x1
+
+/* Registers */
+#define LM3601X_ENABLE_REG	0x01
+#define LM3601X_CFG_REG		0x02
+#define LM3601X_LED_FLASH_REG	0x03
+#define LM3601X_LED_TORCH_REG	0x04
+#define LM3601X_FLAGS_REG	0x05
+#define LM3601X_DEV_ID_REG	0x06
+
+#define LM3601X_SW_RESET	BIT(7)
+
+/* Enable Mode bits */
+#define LM3601X_MODE_STANDBY	0x00
+#define LM3601X_MODE_IR_DRV	BIT(0)
+#define LM3601X_MODE_TORCH	BIT(1)
+#define LM3601X_MODE_STROBE	(BIT(0) | BIT(1))
+#define LM3601X_STRB_EN		BIT(2)
+#define LM3601X_STRB_EDGE_TRIG	BIT(3)
+#define LM3601X_IVFM_EN		BIT(4)
+
+#define LM36010_BOOST_LIMIT_28	BIT(5)
+#define LM36010_BOOST_FREQ_4MHZ	BIT(6)
+#define LM36010_BOOST_MODE_PASS	BIT(7)
+
+/* Flag Mask */
+#define LM3601X_FLASH_TIME_OUT	BIT(0)
+#define LM3601X_UVLO_FAULT	BIT(1)
+#define LM3601X_THERM_SHUTDOWN	BIT(2)
+#define LM3601X_THERM_CURR	BIT(3)
+#define LM36010_CURR_LIMIT	BIT(4)
+#define LM3601X_SHORT_FAULT	BIT(5)
+#define LM3601X_IVFM_TRIP	BIT(6)
+#define LM36010_OVP_FAULT	BIT(7)
+
+#define LM3601X_MAX_TORCH_I_UA	376000
+#define LM3601X_MIN_TORCH_I_UA	2400
+#define LM3601X_TORCH_REG_DIV	2965
+
+#define LM3601X_MAX_STROBE_I_UA	1500000
+#define LM3601X_MIN_STROBE_I_UA	11000
+#define LM3601X_STROBE_REG_DIV	11800
+
+#define LM3601X_TIMEOUT_MASK	0x1e
+#define LM3601X_ENABLE_MASK	(LM3601X_MODE_IR_DRV | LM3601X_MODE_TORCH)
+
+#define LM3601X_LOWER_STEP_US	40000
+#define LM3601X_UPPER_STEP_US	200000
+#define LM3601X_MIN_TIMEOUT_US	40000
+#define LM3601X_MAX_TIMEOUT_US	1600000
+#define LM3601X_TIMEOUT_XOVER_US 400000
+
+enum lm3601x_type {
+	CHIP_LM36010 = 0,
+	CHIP_LM36011,
+};
+
+/**
+ * struct lm3601x_led -
+ * @fled_cdev: flash LED class device pointer
+ * @client: Pointer to the I2C client
+ * @regmap: Devices register map
+ * @lock: Lock for reading/writing the device
+ * @led_name: LED label for the Torch or IR LED
+ * @flash_timeout: the timeout for the flash
+ * @last_flag: last known flags register value
+ * @torch_current_max: maximum current for the torch
+ * @flash_current_max: maximum current for the flash
+ * @max_flash_timeout: maximum timeout for the flash
+ * @led_mode: The mode to enable either IR or Torch
+ */
+struct lm3601x_led {
+	struct led_classdev_flash fled_cdev;
+	struct i2c_client *client;
+	struct regmap *regmap;
+	struct mutex lock;
+
+	char led_name[LED_MAX_NAME_SIZE];
+
+	unsigned int flash_timeout;
+	unsigned int last_flag;
+
+	u32 torch_current_max;
+	u32 flash_current_max;
+	u32 max_flash_timeout;
+
+	u32 led_mode;
+};
+
+static const struct reg_default lm3601x_regmap_defs[] = {
+	{ LM3601X_ENABLE_REG, 0x20 },
+	{ LM3601X_CFG_REG, 0x15 },
+	{ LM3601X_LED_FLASH_REG, 0x00 },
+	{ LM3601X_LED_TORCH_REG, 0x00 },
+};
+
+static bool lm3601x_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case LM3601X_FLAGS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config lm3601x_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = LM3601X_DEV_ID_REG,
+	.reg_defaults = lm3601x_regmap_defs,
+	.num_reg_defaults = ARRAY_SIZE(lm3601x_regmap_defs),
+	.cache_type = REGCACHE_RBTREE,
+	.volatile_reg = lm3601x_volatile_reg,
+};
+
+static struct lm3601x_led *fled_cdev_to_led(struct led_classdev_flash *fled_cdev)
+{
+	return container_of(fled_cdev, struct lm3601x_led, fled_cdev);
+}
+
+static int lm3601x_read_faults(struct lm3601x_led *led)
+{
+	int flags_val;
+	int ret;
+
+	ret = regmap_read(led->regmap, LM3601X_FLAGS_REG, &flags_val);
+	if (ret < 0)
+		return -EIO;
+
+	led->last_flag = 0;
+
+	if (flags_val & LM36010_OVP_FAULT)
+		led->last_flag |= LED_FAULT_OVER_VOLTAGE;
+
+	if (flags_val & (LM3601X_THERM_SHUTDOWN | LM3601X_THERM_CURR))
+		led->last_flag |= LED_FAULT_OVER_TEMPERATURE;
+
+	if (flags_val & LM3601X_SHORT_FAULT)
+		led->last_flag |= LED_FAULT_SHORT_CIRCUIT;
+
+	if (flags_val & LM36010_CURR_LIMIT)
+		led->last_flag |= LED_FAULT_OVER_CURRENT;
+
+	if (flags_val & LM3601X_UVLO_FAULT)
+		led->last_flag |= LED_FAULT_UNDER_VOLTAGE;
+
+	if (flags_val & LM3601X_IVFM_TRIP)
+		led->last_flag |= LED_FAULT_INPUT_VOLTAGE;
+
+	if (flags_val & LM3601X_THERM_SHUTDOWN)
+		led->last_flag |= LED_FAULT_LED_OVER_TEMPERATURE;
+
+	return led->last_flag;
+}
+
+static int lm3601x_brightness_set(struct led_classdev *cdev,
+					enum led_brightness brightness)
+{
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(cdev);
+	struct lm3601x_led *led = fled_cdev_to_led(fled_cdev);
+	int ret, led_mode_val;
+
+	mutex_lock(&led->lock);
+
+	ret = lm3601x_read_faults(led);
+	if (ret < 0)
+		goto out;
+
+	if (led->led_mode == LM3601X_LED_TORCH)
+		led_mode_val = LM3601X_MODE_TORCH;
+	else
+		led_mode_val = LM3601X_MODE_IR_DRV;
+
+	if (brightness == LED_OFF) {
+		ret = regmap_update_bits(led->regmap, LM3601X_ENABLE_REG,
+					led_mode_val, LED_OFF);
+		goto out;
+	}
+
+	ret = regmap_write(led->regmap, LM3601X_LED_TORCH_REG, brightness);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(led->regmap, LM3601X_ENABLE_REG,
+				LM3601X_MODE_TORCH | LM3601X_MODE_IR_DRV,
+				led_mode_val);
+out:
+	mutex_unlock(&led->lock);
+	return ret;
+}
+
+static int lm3601x_strobe_set(struct led_classdev_flash *fled_cdev,
+				bool state)
+{
+	struct lm3601x_led *led = fled_cdev_to_led(fled_cdev);
+	int timeout_reg_val;
+	int current_timeout;
+	int ret;
+
+	mutex_lock(&led->lock);
+
+	ret = regmap_read(led->regmap, LM3601X_CFG_REG, &current_timeout);
+	if (ret < 0)
+		goto out;
+
+	if (led->flash_timeout >= LM3601X_TIMEOUT_XOVER_US)
+		timeout_reg_val = led->flash_timeout / LM3601X_UPPER_STEP_US + 0x07;
+	else
+		timeout_reg_val = led->flash_timeout / LM3601X_LOWER_STEP_US - 0x01;
+
+	if (led->flash_timeout != current_timeout)
+		ret = regmap_update_bits(led->regmap, LM3601X_CFG_REG,
+					LM3601X_TIMEOUT_MASK, timeout_reg_val);
+
+	if (state)
+		ret = regmap_update_bits(led->regmap, LM3601X_ENABLE_REG,
+					LM3601X_MODE_TORCH | LM3601X_MODE_IR_DRV,
+					LM3601X_MODE_STROBE);
+	else
+		ret = regmap_update_bits(led->regmap, LM3601X_ENABLE_REG,
+					LM3601X_MODE_STROBE, LED_OFF);
+
+	ret = lm3601x_read_faults(led);
+out:
+	mutex_unlock(&led->lock);
+	return ret;
+}
+
+static int lm3601x_flash_brightness_set(struct led_classdev_flash *fled_cdev,
+					u32 brightness)
+{
+	struct lm3601x_led *led = fled_cdev_to_led(fled_cdev);
+	u8 brightness_val;
+	int ret;
+
+	mutex_lock(&led->lock);
+	ret = lm3601x_read_faults(led);
+	if (ret < 0)
+		goto out;
+
+	if (brightness == LED_OFF) {
+		ret = regmap_update_bits(led->regmap, LM3601X_ENABLE_REG,
+					LM3601X_MODE_STROBE, LED_OFF);
+		goto out;
+	}
+
+	brightness_val = brightness / LM3601X_STROBE_REG_DIV;
+
+	ret = regmap_write(led->regmap, LM3601X_LED_FLASH_REG, brightness_val);
+out:
+	mutex_unlock(&led->lock);
+	return ret;
+}
+
+static int lm3601x_flash_timeout_set(struct led_classdev_flash *fled_cdev,
+				u32 timeout)
+{
+	struct lm3601x_led *led = fled_cdev_to_led(fled_cdev);
+
+	mutex_lock(&led->lock);
+
+	led->flash_timeout = timeout;
+
+	mutex_unlock(&led->lock);
+
+	return 0;
+}
+
+static int lm3601x_strobe_get(struct led_classdev_flash *fled_cdev, bool *state)
+{
+	struct lm3601x_led *led = fled_cdev_to_led(fled_cdev);
+	int strobe_state;
+	int ret;
+
+	mutex_lock(&led->lock);
+
+	ret = regmap_read(led->regmap, LM3601X_ENABLE_REG, &strobe_state);
+	if (ret < 0)
+		goto out;
+
+	*state = strobe_state & LM3601X_MODE_STROBE;
+
+out:
+	mutex_unlock(&led->lock);
+	return ret;
+}
+
+static int lm3601x_flash_fault_get(struct led_classdev_flash *fled_cdev,
+				u32 *fault)
+{
+	struct lm3601x_led *led = fled_cdev_to_led(fled_cdev);
+
+	lm3601x_read_faults(led);
+
+	*fault = led->last_flag;
+
+	return 0;
+}
+
+static const struct led_flash_ops flash_ops = {
+	.flash_brightness_set	= lm3601x_flash_brightness_set,
+	.strobe_set		= lm3601x_strobe_set,
+	.strobe_get		= lm3601x_strobe_get,
+	.timeout_set		= lm3601x_flash_timeout_set,
+	.fault_get		= lm3601x_flash_fault_get,
+};
+
+static int lm3601x_register_leds(struct lm3601x_led *led)
+{
+	struct led_classdev *led_cdev;
+	struct led_flash_setting *setting;
+
+	led->fled_cdev.ops = &flash_ops;
+
+	setting = &led->fled_cdev.timeout;
+	setting->min = LM3601X_MIN_TIMEOUT_US;
+	setting->max = led->max_flash_timeout;
+	setting->step = LM3601X_LOWER_STEP_US;
+	setting->val = led->max_flash_timeout;
+
+	setting = &led->fled_cdev.brightness;
+	setting->min = LM3601X_MIN_STROBE_I_UA;
+	setting->max = led->flash_current_max;
+	setting->step = LM3601X_TORCH_REG_DIV;
+	setting->val = led->flash_current_max;
+
+	led_cdev = &led->fled_cdev.led_cdev;
+	led_cdev->name = led->led_name;
+	led_cdev->brightness_set_blocking = lm3601x_brightness_set;
+	led_cdev->max_brightness = DIV_ROUND_UP(led->torch_current_max,
+						LM3601X_TORCH_REG_DIV);
+	led_cdev->flags |= LED_DEV_CAP_FLASH;
+
+	return led_classdev_flash_register(&led->client->dev, &led->fled_cdev);
+}
+
+static int lm3601x_parse_node(struct lm3601x_led *led)
+{
+	struct fwnode_handle *child = NULL;
+	int ret = -ENODEV;
+	const char *name;
+
+	child = device_get_next_child_node(&led->client->dev, child);
+	if (!child) {
+		dev_err(&led->client->dev, "No LED Child node\n");
+		return ret;
+	}
+
+	ret = fwnode_property_read_u32(child, "reg", &led->led_mode);
+	if (ret) {
+		dev_err(&led->client->dev, "reg DT property missing\n");
+		goto out_err;
+	}
+
+	if (led->led_mode > LM3601X_LED_TORCH ||
+	    led->led_mode < LM3601X_LED_IR) {
+		dev_warn(&led->client->dev, "Invalid led mode requested\n");
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	ret = fwnode_property_read_string(child, "label", &name);
+	if (ret) {
+		if (led->led_mode == LM3601X_LED_TORCH)
+			name = "torch";
+		else
+			name = "infrared";
+	}
+
+	snprintf(led->led_name, sizeof(led->led_name),
+		"%s:%s", led->client->name, name);
+
+	ret = fwnode_property_read_u32(child, "led-max-microamp",
+					&led->torch_current_max);
+	if (ret) {
+		dev_warn(&led->client->dev,
+			"led-max-microamp DT property missing\n");
+		goto out_err;
+	}
+
+	ret = fwnode_property_read_u32(child, "flash-max-microamp",
+				&led->flash_current_max);
+	if (ret) {
+		dev_warn(&led->client->dev,
+			 "flash-max-microamp DT property missing\n");
+		goto out_err;
+	}
+
+	ret = fwnode_property_read_u32(child, "flash-max-timeout-us",
+				&led->max_flash_timeout);
+	if (ret) {
+		dev_warn(&led->client->dev,
+			 "flash-max-timeout-us DT property missing\n");
+		goto out_err;
+	}
+
+out_err:
+	fwnode_handle_put(child);
+	return ret;
+}
+
+static int lm3601x_probe(struct i2c_client *client)
+{
+	struct lm3601x_led *led;
+	int ret;
+
+	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	led->client = client;
+	i2c_set_clientdata(client, led);
+
+	ret = lm3601x_parse_node(led);
+	if (ret)
+		return -ENODEV;
+
+	led->regmap = devm_regmap_init_i2c(client, &lm3601x_regmap);
+	if (IS_ERR(led->regmap)) {
+		ret = PTR_ERR(led->regmap);
+		dev_err(&client->dev,
+			"Failed to allocate register map: %d\n", ret);
+		return ret;
+	}
+
+	mutex_init(&led->lock);
+
+	return lm3601x_register_leds(led);
+}
+
+static int lm3601x_remove(struct i2c_client *client)
+{
+	struct lm3601x_led *led = i2c_get_clientdata(client);
+
+	led_classdev_flash_unregister(&led->fled_cdev);
+	mutex_destroy(&led->lock);
+
+	return regmap_update_bits(led->regmap, LM3601X_ENABLE_REG,
+			   LM3601X_ENABLE_MASK,
+			   LM3601X_MODE_STANDBY);
+}
+
+static const struct i2c_device_id lm3601x_id[] = {
+	{ "LM36010", CHIP_LM36010 },
+	{ "LM36011", CHIP_LM36011 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, lm3601x_id);
+
+static const struct of_device_id of_lm3601x_leds_match[] = {
+	{ .compatible = "ti,lm36010", },
+	{ .compatible = "ti,lm36011", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, of_lm3601x_leds_match);
+
+static struct i2c_driver lm3601x_i2c_driver = {
+	.driver = {
+		.name = "lm3601x",
+		.of_match_table = of_lm3601x_leds_match,
+	},
+	.probe_new = lm3601x_probe,
+	.remove = lm3601x_remove,
+	.id_table = lm3601x_id,
+};
+module_i2c_driver(lm3601x_i2c_driver);
+
+MODULE_DESCRIPTION("Texas Instruments Flash Lighting driver for LM3601X");
+MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-sc27xx-bltc.c b/drivers/leds/leds-sc27xx-bltc.c
new file mode 100644
index 000000000000..9d9b7aab843f
--- /dev/null
+++ b/drivers/leds/leds-sc27xx-bltc.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Spreadtrum Communications Inc.
+
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <uapi/linux/uleds.h>
+
+/* PMIC global control register definition */
+#define SC27XX_MODULE_EN0	0xc08
+#define SC27XX_CLK_EN0		0xc18
+#define SC27XX_RGB_CTRL		0xebc
+
+#define SC27XX_BLTC_EN		BIT(9)
+#define SC27XX_RTC_EN		BIT(7)
+#define SC27XX_RGB_PD		BIT(0)
+
+/* Breathing light controller register definition */
+#define SC27XX_LEDS_CTRL	0x00
+#define SC27XX_LEDS_PRESCALE	0x04
+#define SC27XX_LEDS_DUTY	0x08
+#define SC27XX_LEDS_CURVE0	0x0c
+#define SC27XX_LEDS_CURVE1	0x10
+
+#define SC27XX_CTRL_SHIFT	4
+#define SC27XX_LED_RUN		BIT(0)
+#define SC27XX_LED_TYPE		BIT(1)
+
+#define SC27XX_DUTY_SHIFT	8
+#define SC27XX_DUTY_MASK	GENMASK(15, 0)
+#define SC27XX_MOD_MASK		GENMASK(7, 0)
+
+#define SC27XX_LEDS_OFFSET	0x10
+#define SC27XX_LEDS_MAX		3
+
+struct sc27xx_led {
+	char name[LED_MAX_NAME_SIZE];
+	struct led_classdev ldev;
+	struct sc27xx_led_priv *priv;
+	u8 line;
+	bool active;
+};
+
+struct sc27xx_led_priv {
+	struct sc27xx_led leds[SC27XX_LEDS_MAX];
+	struct regmap *regmap;
+	struct mutex lock;
+	u32 base;
+};
+
+#define to_sc27xx_led(ldev) \
+	container_of(ldev, struct sc27xx_led, ldev)
+
+static int sc27xx_led_init(struct regmap *regmap)
+{
+	int err;
+
+	err = regmap_update_bits(regmap, SC27XX_MODULE_EN0, SC27XX_BLTC_EN,
+				 SC27XX_BLTC_EN);
+	if (err)
+		return err;
+
+	err = regmap_update_bits(regmap, SC27XX_CLK_EN0, SC27XX_RTC_EN,
+				 SC27XX_RTC_EN);
+	if (err)
+		return err;
+
+	return regmap_update_bits(regmap, SC27XX_RGB_CTRL, SC27XX_RGB_PD, 0);
+}
+
+static u32 sc27xx_led_get_offset(struct sc27xx_led *leds)
+{
+	return leds->priv->base + SC27XX_LEDS_OFFSET * leds->line;
+}
+
+static int sc27xx_led_enable(struct sc27xx_led *leds, enum led_brightness value)
+{
+	u32 base = sc27xx_led_get_offset(leds);
+	u32 ctrl_base = leds->priv->base + SC27XX_LEDS_CTRL;
+	u8 ctrl_shift = SC27XX_CTRL_SHIFT * leds->line;
+	struct regmap *regmap = leds->priv->regmap;
+	int err;
+
+	err = regmap_update_bits(regmap, base + SC27XX_LEDS_DUTY,
+				 SC27XX_DUTY_MASK,
+				 (value << SC27XX_DUTY_SHIFT) |
+				 SC27XX_MOD_MASK);
+	if (err)
+		return err;
+
+	return regmap_update_bits(regmap, ctrl_base,
+			(SC27XX_LED_RUN | SC27XX_LED_TYPE) << ctrl_shift,
+			(SC27XX_LED_RUN | SC27XX_LED_TYPE) << ctrl_shift);
+}
+
+static int sc27xx_led_disable(struct sc27xx_led *leds)
+{
+	struct regmap *regmap = leds->priv->regmap;
+	u32 ctrl_base = leds->priv->base + SC27XX_LEDS_CTRL;
+	u8 ctrl_shift = SC27XX_CTRL_SHIFT * leds->line;
+
+	return regmap_update_bits(regmap, ctrl_base,
+			(SC27XX_LED_RUN | SC27XX_LED_TYPE) << ctrl_shift, 0);
+}
+
+static int sc27xx_led_set(struct led_classdev *ldev, enum led_brightness value)
+{
+	struct sc27xx_led *leds = to_sc27xx_led(ldev);
+	int err;
+
+	mutex_lock(&leds->priv->lock);
+
+	if (value == LED_OFF)
+		err = sc27xx_led_disable(leds);
+	else
+		err = sc27xx_led_enable(leds, value);
+
+	mutex_unlock(&leds->priv->lock);
+
+	return err;
+}
+
+static int sc27xx_led_register(struct device *dev, struct sc27xx_led_priv *priv)
+{
+	int i, err;
+
+	err = sc27xx_led_init(priv->regmap);
+	if (err)
+		return err;
+
+	for (i = 0; i < SC27XX_LEDS_MAX; i++) {
+		struct sc27xx_led *led = &priv->leds[i];
+
+		if (!led->active)
+			continue;
+
+		led->line = i;
+		led->priv = priv;
+		led->ldev.name = led->name;
+		led->ldev.brightness_set_blocking = sc27xx_led_set;
+
+		err = devm_led_classdev_register(dev, &led->ldev);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int sc27xx_led_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node, *child;
+	struct sc27xx_led_priv *priv;
+	const char *str;
+	u32 base, count, reg;
+	int err;
+
+	count = of_get_child_count(np);
+	if (!count || count > SC27XX_LEDS_MAX)
+		return -EINVAL;
+
+	err = of_property_read_u32(np, "reg", &base);
+	if (err) {
+		dev_err(dev, "fail to get reg of property\n");
+		return err;
+	}
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, priv);
+	mutex_init(&priv->lock);
+	priv->base = base;
+	priv->regmap = dev_get_regmap(dev->parent, NULL);
+	if (!priv->regmap) {
+		err = -ENODEV;
+		dev_err(dev, "failed to get regmap: %d\n", err);
+		return err;
+	}
+
+	for_each_child_of_node(np, child) {
+		err = of_property_read_u32(child, "reg", &reg);
+		if (err) {
+			of_node_put(child);
+			mutex_destroy(&priv->lock);
+			return err;
+		}
+
+		if (reg >= SC27XX_LEDS_MAX || priv->leds[reg].active) {
+			of_node_put(child);
+			mutex_destroy(&priv->lock);
+			return -EINVAL;
+		}
+
+		priv->leds[reg].active = true;
+
+		err = of_property_read_string(child, "label", &str);
+		if (err)
+			snprintf(priv->leds[reg].name, LED_MAX_NAME_SIZE,
+				 "sc27xx::");
+		else
+			snprintf(priv->leds[reg].name, LED_MAX_NAME_SIZE,
+				 "sc27xx:%s", str);
+	}
+
+	err = sc27xx_led_register(dev, priv);
+	if (err)
+		mutex_destroy(&priv->lock);
+
+	return err;
+}
+
+static int sc27xx_led_remove(struct platform_device *pdev)
+{
+	struct sc27xx_led_priv *priv = platform_get_drvdata(pdev);
+
+	mutex_destroy(&priv->lock);
+	return 0;
+}
+
+static const struct of_device_id sc27xx_led_of_match[] = {
+	{ .compatible = "sprd,sc2731-bltc", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sc27xx_led_of_match);
+
+static struct platform_driver sc27xx_led_driver = {
+	.driver = {
+		.name = "sprd-bltc",
+		.of_match_table = sc27xx_led_of_match,
+	},
+	.probe = sc27xx_led_probe,
+	.remove = sc27xx_led_remove,
+};
+
+module_platform_driver(sc27xx_led_driver);
+
+MODULE_DESCRIPTION("Spreadtrum SC27xx breathing light controller driver");
+MODULE_AUTHOR("Xiaotong Lu <xiaotong.lu@spreadtrum.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c
index be93b20e792a..c5798b92e4d3 100644
--- a/drivers/leds/leds-wm831x-status.c
+++ b/drivers/leds/leds-wm831x-status.c
@@ -188,24 +188,14 @@ static ssize_t wm831x_status_src_store(struct device *dev,
 {
 	struct led_classdev *led_cdev = dev_get_drvdata(dev);
 	struct wm831x_status *led = to_wm831x_status(led_cdev);
-	char name[20];
 	int i;
-	size_t len;
 
-	name[sizeof(name) - 1] = '\0';
-	strncpy(name, buf, sizeof(name) - 1);
-	len = strlen(name);
-
-	if (len && name[len - 1] == '\n')
-		name[len - 1] = '\0';
-
-	for (i = 0; i < ARRAY_SIZE(led_src_texts); i++) {
-		if (!strcmp(name, led_src_texts[i])) {
-			mutex_lock(&led->mutex);
-			led->src = i;
-			mutex_unlock(&led->mutex);
-			wm831x_status_set(led);
-		}
+	i = sysfs_match_string(led_src_texts, buf);
+	if (i >= 0) {
+		mutex_lock(&led->mutex);
+		led->src = i;
+		mutex_unlock(&led->mutex);
+		wm831x_status_set(led);
 	}
 
 	return size;
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 63171cdce270..60aa7bc5a630 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -431,7 +431,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
 	return 0;
 err_sysfs:
 	if (tt->exit)
-		tt->exit(targetdata);
+		tt->exit(targetdata, true);
 err_init:
 	blk_cleanup_queue(tqueue);
 	tdisk->queue = NULL;
@@ -446,7 +446,7 @@ err_reserve:
 	return ret;
 }
 
-static void __nvm_remove_target(struct nvm_target *t)
+static void __nvm_remove_target(struct nvm_target *t, bool graceful)
 {
 	struct nvm_tgt_type *tt = t->type;
 	struct gendisk *tdisk = t->disk;
@@ -459,7 +459,7 @@ static void __nvm_remove_target(struct nvm_target *t)
 		tt->sysfs_exit(tdisk);
 
 	if (tt->exit)
-		tt->exit(tdisk->private_data);
+		tt->exit(tdisk->private_data, graceful);
 
 	nvm_remove_tgt_dev(t->dev, 1);
 	put_disk(tdisk);
@@ -489,7 +489,7 @@ static int nvm_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
 		mutex_unlock(&dev->mlock);
 		return 1;
 	}
-	__nvm_remove_target(t);
+	__nvm_remove_target(t, true);
 	mutex_unlock(&dev->mlock);
 
 	return 0;
@@ -963,7 +963,7 @@ void nvm_unregister(struct nvm_dev *dev)
 	list_for_each_entry_safe(t, tmp, &dev->targets, list) {
 		if (t->dev->parent != dev)
 			continue;
-		__nvm_remove_target(t);
+		__nvm_remove_target(t, false);
 	}
 	mutex_unlock(&dev->mlock);
 
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
index 29a23111b31c..b1c6d7eb6115 100644
--- a/drivers/lightnvm/pblk-cache.c
+++ b/drivers/lightnvm/pblk-cache.c
@@ -44,13 +44,15 @@ retry:
 		goto out;
 	}
 
-	if (unlikely(!bio_has_data(bio)))
-		goto out;
-
 	pblk_ppa_set_empty(&w_ctx.ppa);
 	w_ctx.flags = flags;
-	if (bio->bi_opf & REQ_PREFLUSH)
+	if (bio->bi_opf & REQ_PREFLUSH) {
 		w_ctx.flags |= PBLK_FLUSH_ENTRY;
+		pblk_write_kick(pblk);
+	}
+
+	if (unlikely(!bio_has_data(bio)))
+		goto out;
 
 	for (i = 0; i < nr_entries; i++) {
 		void *data = bio_data(bio);
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 94d5d97c9d8a..ed9cc977c8b3 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -40,7 +40,7 @@ static void pblk_line_mark_bb(struct work_struct *work)
 	}
 
 	kfree(ppa);
-	mempool_free(line_ws, pblk->gen_ws_pool);
+	mempool_free(line_ws, &pblk->gen_ws_pool);
 }
 
 static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
@@ -102,7 +102,7 @@ static void pblk_end_io_erase(struct nvm_rq *rqd)
 	struct pblk *pblk = rqd->private;
 
 	__pblk_end_io_erase(pblk, rqd);
-	mempool_free(rqd, pblk->e_rq_pool);
+	mempool_free(rqd, &pblk->e_rq_pool);
 }
 
 /*
@@ -237,15 +237,15 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type)
 	switch (type) {
 	case PBLK_WRITE:
 	case PBLK_WRITE_INT:
-		pool = pblk->w_rq_pool;
+		pool = &pblk->w_rq_pool;
 		rq_size = pblk_w_rq_size;
 		break;
 	case PBLK_READ:
-		pool = pblk->r_rq_pool;
+		pool = &pblk->r_rq_pool;
 		rq_size = pblk_g_rq_size;
 		break;
 	default:
-		pool = pblk->e_rq_pool;
+		pool = &pblk->e_rq_pool;
 		rq_size = pblk_g_rq_size;
 	}
 
@@ -265,20 +265,22 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 	case PBLK_WRITE:
 		kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
 	case PBLK_WRITE_INT:
-		pool = pblk->w_rq_pool;
+		pool = &pblk->w_rq_pool;
 		break;
 	case PBLK_READ:
-		pool = pblk->r_rq_pool;
+		pool = &pblk->r_rq_pool;
 		break;
 	case PBLK_ERASE:
-		pool = pblk->e_rq_pool;
+		pool = &pblk->e_rq_pool;
 		break;
 	default:
 		pr_err("pblk: trying to free unknown rqd type\n");
 		return;
 	}
 
-	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
+	if (rqd->meta_list)
+		nvm_dev_dma_free(dev->parent, rqd->meta_list,
+				rqd->dma_meta_list);
 	mempool_free(rqd, pool);
 }
 
@@ -292,7 +294,7 @@ void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
 
 	for (i = off; i < nr_pages + off; i++) {
 		bv = bio->bi_io_vec[i];
-		mempool_free(bv.bv_page, pblk->page_bio_pool);
+		mempool_free(bv.bv_page, &pblk->page_bio_pool);
 	}
 }
 
@@ -304,23 +306,23 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
 	int i, ret;
 
 	for (i = 0; i < nr_pages; i++) {
-		page = mempool_alloc(pblk->page_bio_pool, flags);
+		page = mempool_alloc(&pblk->page_bio_pool, flags);
 
 		ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
 		if (ret != PBLK_EXPOSED_PAGE_SIZE) {
 			pr_err("pblk: could not add page to bio\n");
-			mempool_free(page, pblk->page_bio_pool);
+			mempool_free(page, &pblk->page_bio_pool);
 			goto err;
 		}
 	}
 
 	return 0;
 err:
-	pblk_bio_free_pages(pblk, bio, 0, i - 1);
+	pblk_bio_free_pages(pblk, bio, (bio->bi_vcnt - i), i);
 	return -1;
 }
 
-static void pblk_write_kick(struct pblk *pblk)
+void pblk_write_kick(struct pblk *pblk)
 {
 	wake_up_process(pblk->writer_ts);
 	mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(1000));
@@ -342,13 +344,6 @@ void pblk_write_should_kick(struct pblk *pblk)
 		pblk_write_kick(pblk);
 }
 
-void pblk_end_io_sync(struct nvm_rq *rqd)
-{
-	struct completion *waiting = rqd->private;
-
-	complete(waiting);
-}
-
 static void pblk_wait_for_meta(struct pblk *pblk)
 {
 	do {
@@ -380,7 +375,13 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 
 	lockdep_assert_held(&line->lock);
 
-	if (!vsc) {
+	if (line->w_err_gc->has_write_err) {
+		if (line->gc_group != PBLK_LINEGC_WERR) {
+			line->gc_group = PBLK_LINEGC_WERR;
+			move_list = &l_mg->gc_werr_list;
+			pblk_rl_werr_line_in(&pblk->rl);
+		}
+	} else if (!vsc) {
 		if (line->gc_group != PBLK_LINEGC_FULL) {
 			line->gc_group = PBLK_LINEGC_FULL;
 			move_list = &l_mg->gc_full_list;
@@ -467,16 +468,13 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 
-#ifdef CONFIG_NVM_DEBUG
-	int ret;
+	atomic_inc(&pblk->inflight_io);
 
-	ret = pblk_check_io(pblk, rqd);
-	if (ret)
-		return ret;
+#ifdef CONFIG_NVM_DEBUG
+	if (pblk_check_io(pblk, rqd))
+		return NVM_IO_ERR;
 #endif
 
-	atomic_inc(&pblk->inflight_io);
-
 	return nvm_submit_io(dev, rqd);
 }
 
@@ -484,16 +482,13 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 
-#ifdef CONFIG_NVM_DEBUG
-	int ret;
+	atomic_inc(&pblk->inflight_io);
 
-	ret = pblk_check_io(pblk, rqd);
-	if (ret)
-		return ret;
+#ifdef CONFIG_NVM_DEBUG
+	if (pblk_check_io(pblk, rqd))
+		return NVM_IO_ERR;
 #endif
 
-	atomic_inc(&pblk->inflight_io);
-
 	return nvm_submit_io_sync(dev, rqd);
 }
 
@@ -856,9 +851,10 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	atomic_dec(&pblk->inflight_io);
 
 	if (rqd.error) {
-		if (dir == PBLK_WRITE)
+		if (dir == PBLK_WRITE) {
 			pblk_log_write_err(pblk, &rqd);
-		else if (dir == PBLK_READ)
+			ret = 1;
+		} else if (dir == PBLK_READ)
 			pblk_log_read_err(pblk, &rqd);
 	}
 
@@ -1071,6 +1067,25 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 	return 1;
 }
 
+static int pblk_line_alloc_bitmaps(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+
+	line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+	if (!line->map_bitmap)
+		return -ENOMEM;
+
+	/* will be initialized using bb info from map_bitmap */
+	line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_KERNEL);
+	if (!line->invalid_bitmap) {
+		kfree(line->map_bitmap);
+		line->map_bitmap = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 /* For now lines are always assumed full lines. Thus, smeta former and current
  * lun bitmaps are omitted.
  */
@@ -1108,7 +1123,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 
 	if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) {
 		pr_debug("pblk: line smeta I/O failed. Retry\n");
-		return 1;
+		return 0;
 	}
 
 	bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
@@ -1174,19 +1189,9 @@ static int pblk_prepare_new_line(struct pblk *pblk, struct pblk_line *line)
 static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 {
 	struct pblk_line_meta *lm = &pblk->lm;
+	int blk_in_line = atomic_read(&line->blk_in_line);
 	int blk_to_erase;
 
-	line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_ATOMIC);
-	if (!line->map_bitmap)
-		return -ENOMEM;
-
-	/* will be initialized using bb info from map_bitmap */
-	line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_ATOMIC);
-	if (!line->invalid_bitmap) {
-		kfree(line->map_bitmap);
-		return -ENOMEM;
-	}
-
 	/* Bad blocks do not need to be erased */
 	bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line);
 
@@ -1199,16 +1204,19 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 		blk_to_erase = pblk_prepare_new_line(pblk, line);
 		line->state = PBLK_LINESTATE_FREE;
 	} else {
-		blk_to_erase = atomic_read(&line->blk_in_line);
+		blk_to_erase = blk_in_line;
 	}
 
-	if (line->state != PBLK_LINESTATE_FREE) {
-		kfree(line->map_bitmap);
-		kfree(line->invalid_bitmap);
+	if (blk_in_line < lm->min_blk_line) {
 		spin_unlock(&line->lock);
+		return -EAGAIN;
+	}
+
+	if (line->state != PBLK_LINESTATE_FREE) {
 		WARN(1, "pblk: corrupted line %d, state %d\n",
 							line->id, line->state);
-		return -EAGAIN;
+		spin_unlock(&line->lock);
+		return -EINTR;
 	}
 
 	line->state = PBLK_LINESTATE_OPEN;
@@ -1241,13 +1249,16 @@ int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line)
 	}
 	spin_unlock(&l_mg->free_lock);
 
-	pblk_rl_free_lines_dec(&pblk->rl, line, true);
+	ret = pblk_line_alloc_bitmaps(pblk, line);
+	if (ret)
+		return ret;
 
 	if (!pblk_line_init_bb(pblk, line, 0)) {
 		list_add(&line->list, &l_mg->free_list);
 		return -EINTR;
 	}
 
+	pblk_rl_free_lines_dec(&pblk->rl, line, true);
 	return 0;
 }
 
@@ -1259,6 +1270,24 @@ void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line)
 	line->emeta = NULL;
 }
 
+static void pblk_line_reinit(struct pblk_line *line)
+{
+	*line->vsc = cpu_to_le32(EMPTY_ENTRY);
+
+	line->map_bitmap = NULL;
+	line->invalid_bitmap = NULL;
+	line->smeta = NULL;
+	line->emeta = NULL;
+}
+
+void pblk_line_free(struct pblk_line *line)
+{
+	kfree(line->map_bitmap);
+	kfree(line->invalid_bitmap);
+
+	pblk_line_reinit(line);
+}
+
 struct pblk_line *pblk_line_get(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1292,10 +1321,14 @@ retry:
 
 	ret = pblk_line_prepare(pblk, line);
 	if (ret) {
-		if (ret == -EAGAIN) {
+		switch (ret) {
+		case -EAGAIN:
+			list_add(&line->list, &l_mg->bad_list);
+			goto retry;
+		case -EINTR:
 			list_add(&line->list, &l_mg->corrupt_list);
 			goto retry;
-		} else {
+		default:
 			pr_err("pblk: failed to prepare line %d\n", line->id);
 			list_add(&line->list, &l_mg->free_list);
 			l_mg->nr_free_lines++;
@@ -1321,11 +1354,14 @@ retry:
 		return NULL;
 	}
 
+	retry_line->map_bitmap = line->map_bitmap;
+	retry_line->invalid_bitmap = line->invalid_bitmap;
 	retry_line->smeta = line->smeta;
 	retry_line->emeta = line->emeta;
 	retry_line->meta_line = line->meta_line;
 
-	pblk_line_free(pblk, line);
+	pblk_line_reinit(line);
+
 	l_mg->data_line = retry_line;
 	spin_unlock(&l_mg->free_lock);
 
@@ -1378,6 +1414,9 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
 	}
 	spin_unlock(&l_mg->free_lock);
 
+	if (pblk_line_alloc_bitmaps(pblk, line))
+		return NULL;
+
 	if (pblk_line_erase(pblk, line)) {
 		line = pblk_line_retry(pblk, line);
 		if (!line)
@@ -1449,7 +1488,7 @@ static void pblk_line_close_meta_sync(struct pblk *pblk)
 	flush_workqueue(pblk->close_wq);
 }
 
-void pblk_pipeline_stop(struct pblk *pblk)
+void __pblk_pipeline_flush(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	int ret;
@@ -1474,6 +1513,11 @@ void pblk_pipeline_stop(struct pblk *pblk)
 
 	flush_workqueue(pblk->bb_wq);
 	pblk_line_close_meta_sync(pblk);
+}
+
+void __pblk_pipeline_stop(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 
 	spin_lock(&l_mg->free_lock);
 	pblk->state = PBLK_STATE_STOPPED;
@@ -1482,6 +1526,12 @@ void pblk_pipeline_stop(struct pblk *pblk)
 	spin_unlock(&l_mg->free_lock);
 }
 
+void pblk_pipeline_stop(struct pblk *pblk)
+{
+	__pblk_pipeline_flush(pblk);
+	__pblk_pipeline_stop(pblk);
+}
+
 struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1511,6 +1561,9 @@ retry_erase:
 		goto retry_erase;
 	}
 
+	if (pblk_line_alloc_bitmaps(pblk, new))
+		return NULL;
+
 retry_setup:
 	if (!pblk_line_init_metadata(pblk, new, cur)) {
 		new = pblk_line_retry(pblk, new);
@@ -1550,19 +1603,6 @@ out:
 	return new;
 }
 
-void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
-{
-	kfree(line->map_bitmap);
-	kfree(line->invalid_bitmap);
-
-	*line->vsc = cpu_to_le32(EMPTY_ENTRY);
-
-	line->map_bitmap = NULL;
-	line->invalid_bitmap = NULL;
-	line->smeta = NULL;
-	line->emeta = NULL;
-}
-
 static void __pblk_line_put(struct pblk *pblk, struct pblk_line *line)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1572,9 +1612,14 @@ static void __pblk_line_put(struct pblk *pblk, struct pblk_line *line)
 	WARN_ON(line->state != PBLK_LINESTATE_GC);
 	line->state = PBLK_LINESTATE_FREE;
 	line->gc_group = PBLK_LINEGC_NONE;
-	pblk_line_free(pblk, line);
-	spin_unlock(&line->lock);
+	pblk_line_free(line);
+
+	if (line->w_err_gc->has_write_err) {
+		pblk_rl_werr_line_out(&pblk->rl);
+		line->w_err_gc->has_write_err = 0;
+	}
 
+	spin_unlock(&line->lock);
 	atomic_dec(&gc->pipeline_gc);
 
 	spin_lock(&l_mg->free_lock);
@@ -1593,7 +1638,7 @@ static void pblk_line_put_ws(struct work_struct *work)
 	struct pblk_line *line = line_put_ws->line;
 
 	__pblk_line_put(pblk, line);
-	mempool_free(line_put_ws, pblk->gen_ws_pool);
+	mempool_free(line_put_ws, &pblk->gen_ws_pool);
 }
 
 void pblk_line_put(struct kref *ref)
@@ -1610,7 +1655,7 @@ void pblk_line_put_wq(struct kref *ref)
 	struct pblk *pblk = line->pblk;
 	struct pblk_line_ws *line_put_ws;
 
-	line_put_ws = mempool_alloc(pblk->gen_ws_pool, GFP_ATOMIC);
+	line_put_ws = mempool_alloc(&pblk->gen_ws_pool, GFP_ATOMIC);
 	if (!line_put_ws)
 		return;
 
@@ -1737,11 +1782,34 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line)
 
 	spin_lock(&l_mg->close_lock);
 	spin_lock(&line->lock);
+
+	/* Update the in-memory start address for emeta, in case it has
+	 * shifted due to write errors
+	 */
+	if (line->emeta_ssec != line->cur_sec)
+		line->emeta_ssec = line->cur_sec;
+
 	list_add_tail(&line->list, &l_mg->emeta_list);
 	spin_unlock(&line->lock);
 	spin_unlock(&l_mg->close_lock);
 
 	pblk_line_should_sync_meta(pblk);
+
+
+}
+
+static void pblk_save_lba_list(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	unsigned int lba_list_size = lm->emeta_len[2];
+	struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
+	struct pblk_emeta *emeta = line->emeta;
+
+	w_err_gc->lba_list = pblk_malloc(lba_list_size,
+					 l_mg->emeta_alloc_type, GFP_KERNEL);
+	memcpy(w_err_gc->lba_list, emeta_to_lbas(pblk, emeta->buf),
+				lba_list_size);
 }
 
 void pblk_line_close_ws(struct work_struct *work)
@@ -1750,9 +1818,16 @@ void pblk_line_close_ws(struct work_struct *work)
 									ws);
 	struct pblk *pblk = line_ws->pblk;
 	struct pblk_line *line = line_ws->line;
+	struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
+
+	/* Write errors makes the emeta start address stored in smeta invalid,
+	 * so keep a copy of the lba list until we've gc'd the line
+	 */
+	if (w_err_gc->has_write_err)
+		pblk_save_lba_list(pblk, line);
 
 	pblk_line_close(pblk, line);
-	mempool_free(line_ws, pblk->gen_ws_pool);
+	mempool_free(line_ws, &pblk->gen_ws_pool);
 }
 
 void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
@@ -1761,7 +1836,7 @@ void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
 {
 	struct pblk_line_ws *line_ws;
 
-	line_ws = mempool_alloc(pblk->gen_ws_pool, gfp_mask);
+	line_ws = mempool_alloc(&pblk->gen_ws_pool, gfp_mask);
 
 	line_ws->pblk = pblk;
 	line_ws->line = line;
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 6851a5c67189..df88f1bdd921 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -129,6 +129,53 @@ out:
 	kfree(gc_rq_ws);
 }
 
+static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
+				       struct pblk_line *line)
+{
+	struct line_emeta *emeta_buf;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line_meta *lm = &pblk->lm;
+	unsigned int lba_list_size = lm->emeta_len[2];
+	__le64 *lba_list;
+	int ret;
+
+	emeta_buf = pblk_malloc(lm->emeta_len[0],
+				l_mg->emeta_alloc_type, GFP_KERNEL);
+	if (!emeta_buf)
+		return NULL;
+
+	ret = pblk_line_read_emeta(pblk, line, emeta_buf);
+	if (ret) {
+		pr_err("pblk: line %d read emeta failed (%d)\n",
+				line->id, ret);
+		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+		return NULL;
+	}
+
+	/* If this read fails, it means that emeta is corrupted.
+	 * For now, leave the line untouched.
+	 * TODO: Implement a recovery routine that scans and moves
+	 * all sectors on the line.
+	 */
+
+	ret = pblk_recov_check_emeta(pblk, emeta_buf);
+	if (ret) {
+		pr_err("pblk: inconsistent emeta (line %d)\n",
+				line->id);
+		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+		return NULL;
+	}
+
+	lba_list = pblk_malloc(lba_list_size,
+			       l_mg->emeta_alloc_type, GFP_KERNEL);
+	if (lba_list)
+		memcpy(lba_list, emeta_to_lbas(pblk, emeta_buf), lba_list_size);
+
+	pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+
+	return lba_list;
+}
+
 static void pblk_gc_line_prepare_ws(struct work_struct *work)
 {
 	struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
@@ -138,46 +185,26 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_gc *gc = &pblk->gc;
-	struct line_emeta *emeta_buf;
 	struct pblk_line_ws *gc_rq_ws;
 	struct pblk_gc_rq *gc_rq;
 	__le64 *lba_list;
 	unsigned long *invalid_bitmap;
 	int sec_left, nr_secs, bit;
-	int ret;
 
 	invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_KERNEL);
 	if (!invalid_bitmap)
 		goto fail_free_ws;
 
-	emeta_buf = pblk_malloc(lm->emeta_len[0], l_mg->emeta_alloc_type,
-								GFP_KERNEL);
-	if (!emeta_buf) {
-		pr_err("pblk: cannot use GC emeta\n");
-		goto fail_free_bitmap;
-	}
-
-	ret = pblk_line_read_emeta(pblk, line, emeta_buf);
-	if (ret) {
-		pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret);
-		goto fail_free_emeta;
-	}
-
-	/* If this read fails, it means that emeta is corrupted. For now, leave
-	 * the line untouched. TODO: Implement a recovery routine that scans and
-	 * moves all sectors on the line.
-	 */
-
-	ret = pblk_recov_check_emeta(pblk, emeta_buf);
-	if (ret) {
-		pr_err("pblk: inconsistent emeta (line %d)\n", line->id);
-		goto fail_free_emeta;
-	}
-
-	lba_list = emeta_to_lbas(pblk, emeta_buf);
-	if (!lba_list) {
-		pr_err("pblk: could not interpret emeta (line %d)\n", line->id);
-		goto fail_free_emeta;
+	if (line->w_err_gc->has_write_err) {
+		lba_list = line->w_err_gc->lba_list;
+		line->w_err_gc->lba_list = NULL;
+	} else {
+		lba_list = get_lba_list_from_emeta(pblk, line);
+		if (!lba_list) {
+			pr_err("pblk: could not interpret emeta (line %d)\n",
+					line->id);
+			goto fail_free_ws;
+		}
 	}
 
 	spin_lock(&line->lock);
@@ -187,14 +214,14 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 
 	if (sec_left < 0) {
 		pr_err("pblk: corrupted GC line (%d)\n", line->id);
-		goto fail_free_emeta;
+		goto fail_free_lba_list;
 	}
 
 	bit = -1;
 next_rq:
 	gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL);
 	if (!gc_rq)
-		goto fail_free_emeta;
+		goto fail_free_lba_list;
 
 	nr_secs = 0;
 	do {
@@ -240,7 +267,7 @@ next_rq:
 		goto next_rq;
 
 out:
-	pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+	pblk_mfree(lba_list, l_mg->emeta_alloc_type);
 	kfree(line_ws);
 	kfree(invalid_bitmap);
 
@@ -251,9 +278,8 @@ out:
 
 fail_free_gc_rq:
 	kfree(gc_rq);
-fail_free_emeta:
-	pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
-fail_free_bitmap:
+fail_free_lba_list:
+	pblk_mfree(lba_list, l_mg->emeta_alloc_type);
 	kfree(invalid_bitmap);
 fail_free_ws:
 	kfree(line_ws);
@@ -349,12 +375,14 @@ static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk,
 static bool pblk_gc_should_run(struct pblk_gc *gc, struct pblk_rl *rl)
 {
 	unsigned int nr_blocks_free, nr_blocks_need;
+	unsigned int werr_lines = atomic_read(&rl->werr_lines);
 
 	nr_blocks_need = pblk_rl_high_thrs(rl);
 	nr_blocks_free = pblk_rl_nr_free_blks(rl);
 
 	/* This is not critical, no need to take lock here */
-	return ((gc->gc_active) && (nr_blocks_need > nr_blocks_free));
+	return ((werr_lines > 0) ||
+		((gc->gc_active) && (nr_blocks_need > nr_blocks_free)));
 }
 
 void pblk_gc_free_full_lines(struct pblk *pblk)
@@ -649,7 +677,7 @@ fail_free_main_kthread:
 	return ret;
 }
 
-void pblk_gc_exit(struct pblk *pblk)
+void pblk_gc_exit(struct pblk *pblk, bool graceful)
 {
 	struct pblk_gc *gc = &pblk->gc;
 
@@ -663,10 +691,12 @@ void pblk_gc_exit(struct pblk *pblk)
 	if (gc->gc_reader_ts)
 		kthread_stop(gc->gc_reader_ts);
 
-	flush_workqueue(gc->gc_reader_wq);
-	destroy_workqueue(gc->gc_reader_wq);
+	if (graceful) {
+		flush_workqueue(gc->gc_reader_wq);
+		flush_workqueue(gc->gc_line_reader_wq);
+	}
 
-	flush_workqueue(gc->gc_line_reader_wq);
+	destroy_workqueue(gc->gc_reader_wq);
 	destroy_workqueue(gc->gc_line_reader_wq);
 
 	if (gc->gc_writer_ts)
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 91a5bc2556a3..ce561f5d48ce 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -20,10 +20,15 @@
 
 #include "pblk.h"
 
+unsigned int write_buffer_size;
+
+module_param(write_buffer_size, uint, 0644);
+MODULE_PARM_DESC(write_buffer_size, "number of entries in a write buffer");
+
 static struct kmem_cache *pblk_ws_cache, *pblk_rec_cache, *pblk_g_rq_cache,
 				*pblk_w_rq_cache;
 static DECLARE_RWSEM(pblk_lock);
-struct bio_set *pblk_bio_set;
+struct bio_set pblk_bio_set;
 
 static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
 			  struct bio *bio)
@@ -127,10 +132,8 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init)
 	if (!line) {
 		/* Configure next line for user data */
 		line = pblk_line_get_first_data(pblk);
-		if (!line) {
-			pr_err("pblk: line list corrupted\n");
+		if (!line)
 			return -EFAULT;
-		}
 	}
 
 	return 0;
@@ -141,6 +144,7 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)
 	sector_t i;
 	struct ppa_addr ppa;
 	size_t map_size;
+	int ret = 0;
 
 	map_size = pblk_trans_map_size(pblk);
 	pblk->trans_map = vmalloc(map_size);
@@ -152,7 +156,11 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)
 	for (i = 0; i < pblk->rl.nr_secs; i++)
 		pblk_trans_map_set(pblk, i, ppa);
 
-	return pblk_l2p_recover(pblk, factory_init);
+	ret = pblk_l2p_recover(pblk, factory_init);
+	if (ret)
+		vfree(pblk->trans_map);
+
+	return ret;
 }
 
 static void pblk_rwb_free(struct pblk *pblk)
@@ -169,10 +177,15 @@ static int pblk_rwb_init(struct pblk *pblk)
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
 	struct pblk_rb_entry *entries;
-	unsigned long nr_entries;
+	unsigned long nr_entries, buffer_size;
 	unsigned int power_size, power_seg_sz;
 
-	nr_entries = pblk_rb_calculate_size(pblk->pgs_in_buffer);
+	if (write_buffer_size && (write_buffer_size > pblk->pgs_in_buffer))
+		buffer_size = write_buffer_size;
+	else
+		buffer_size = pblk->pgs_in_buffer;
+
+	nr_entries = pblk_rb_calculate_size(buffer_size);
 
 	entries = vzalloc(nr_entries * sizeof(struct pblk_rb_entry));
 	if (!entries)
@@ -341,7 +354,7 @@ static int pblk_core_init(struct pblk *pblk)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
-	int max_write_ppas;
+	int ret, max_write_ppas;
 
 	atomic64_set(&pblk->user_wa, 0);
 	atomic64_set(&pblk->pad_wa, 0);
@@ -375,33 +388,33 @@ static int pblk_core_init(struct pblk *pblk)
 		goto fail_free_pad_dist;
 
 	/* Internal bios can be at most the sectors signaled by the device. */
-	pblk->page_bio_pool = mempool_create_page_pool(NVM_MAX_VLBA, 0);
-	if (!pblk->page_bio_pool)
+	ret = mempool_init_page_pool(&pblk->page_bio_pool, NVM_MAX_VLBA, 0);
+	if (ret)
 		goto free_global_caches;
 
-	pblk->gen_ws_pool = mempool_create_slab_pool(PBLK_GEN_WS_POOL_SIZE,
-							pblk_ws_cache);
-	if (!pblk->gen_ws_pool)
+	ret = mempool_init_slab_pool(&pblk->gen_ws_pool, PBLK_GEN_WS_POOL_SIZE,
+				     pblk_ws_cache);
+	if (ret)
 		goto free_page_bio_pool;
 
-	pblk->rec_pool = mempool_create_slab_pool(geo->all_luns,
-							pblk_rec_cache);
-	if (!pblk->rec_pool)
+	ret = mempool_init_slab_pool(&pblk->rec_pool, geo->all_luns,
+				     pblk_rec_cache);
+	if (ret)
 		goto free_gen_ws_pool;
 
-	pblk->r_rq_pool = mempool_create_slab_pool(geo->all_luns,
-							pblk_g_rq_cache);
-	if (!pblk->r_rq_pool)
+	ret = mempool_init_slab_pool(&pblk->r_rq_pool, geo->all_luns,
+				     pblk_g_rq_cache);
+	if (ret)
 		goto free_rec_pool;
 
-	pblk->e_rq_pool = mempool_create_slab_pool(geo->all_luns,
-							pblk_g_rq_cache);
-	if (!pblk->e_rq_pool)
+	ret = mempool_init_slab_pool(&pblk->e_rq_pool, geo->all_luns,
+				     pblk_g_rq_cache);
+	if (ret)
 		goto free_r_rq_pool;
 
-	pblk->w_rq_pool = mempool_create_slab_pool(geo->all_luns,
-							pblk_w_rq_cache);
-	if (!pblk->w_rq_pool)
+	ret = mempool_init_slab_pool(&pblk->w_rq_pool, geo->all_luns,
+				     pblk_w_rq_cache);
+	if (ret)
 		goto free_e_rq_pool;
 
 	pblk->close_wq = alloc_workqueue("pblk-close-wq",
@@ -423,6 +436,7 @@ static int pblk_core_init(struct pblk *pblk)
 		goto free_r_end_wq;
 
 	INIT_LIST_HEAD(&pblk->compl_list);
+	INIT_LIST_HEAD(&pblk->resubmit_list);
 
 	return 0;
 
@@ -433,17 +447,17 @@ free_bb_wq:
 free_close_wq:
 	destroy_workqueue(pblk->close_wq);
 free_w_rq_pool:
-	mempool_destroy(pblk->w_rq_pool);
+	mempool_exit(&pblk->w_rq_pool);
 free_e_rq_pool:
-	mempool_destroy(pblk->e_rq_pool);
+	mempool_exit(&pblk->e_rq_pool);
 free_r_rq_pool:
-	mempool_destroy(pblk->r_rq_pool);
+	mempool_exit(&pblk->r_rq_pool);
 free_rec_pool:
-	mempool_destroy(pblk->rec_pool);
+	mempool_exit(&pblk->rec_pool);
 free_gen_ws_pool:
-	mempool_destroy(pblk->gen_ws_pool);
+	mempool_exit(&pblk->gen_ws_pool);
 free_page_bio_pool:
-	mempool_destroy(pblk->page_bio_pool);
+	mempool_exit(&pblk->page_bio_pool);
 free_global_caches:
 	pblk_free_global_caches(pblk);
 fail_free_pad_dist:
@@ -462,12 +476,12 @@ static void pblk_core_free(struct pblk *pblk)
 	if (pblk->bb_wq)
 		destroy_workqueue(pblk->bb_wq);
 
-	mempool_destroy(pblk->page_bio_pool);
-	mempool_destroy(pblk->gen_ws_pool);
-	mempool_destroy(pblk->rec_pool);
-	mempool_destroy(pblk->r_rq_pool);
-	mempool_destroy(pblk->e_rq_pool);
-	mempool_destroy(pblk->w_rq_pool);
+	mempool_exit(&pblk->page_bio_pool);
+	mempool_exit(&pblk->gen_ws_pool);
+	mempool_exit(&pblk->rec_pool);
+	mempool_exit(&pblk->r_rq_pool);
+	mempool_exit(&pblk->e_rq_pool);
+	mempool_exit(&pblk->w_rq_pool);
 
 	pblk_free_global_caches(pblk);
 	kfree(pblk->pad_dist);
@@ -489,11 +503,17 @@ static void pblk_line_mg_free(struct pblk *pblk)
 	}
 }
 
-static void pblk_line_meta_free(struct pblk_line *line)
+static void pblk_line_meta_free(struct pblk_line_mgmt *l_mg,
+				struct pblk_line *line)
 {
+	struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
+
 	kfree(line->blk_bitmap);
 	kfree(line->erase_bitmap);
 	kfree(line->chks);
+
+	pblk_mfree(w_err_gc->lba_list, l_mg->emeta_alloc_type);
+	kfree(w_err_gc);
 }
 
 static void pblk_lines_free(struct pblk *pblk)
@@ -506,8 +526,8 @@ static void pblk_lines_free(struct pblk *pblk)
 	for (i = 0; i < l_mg->nr_lines; i++) {
 		line = &pblk->lines[i];
 
-		pblk_line_free(pblk, line);
-		pblk_line_meta_free(line);
+		pblk_line_free(line);
+		pblk_line_meta_free(l_mg, line);
 	}
 	spin_unlock(&l_mg->free_lock);
 
@@ -748,14 +768,14 @@ static int pblk_setup_line_meta_20(struct pblk *pblk, struct pblk_line *line,
 		chunk->cnlb = chunk_meta->cnlb;
 		chunk->wp = chunk_meta->wp;
 
-		if (!(chunk->state & NVM_CHK_ST_OFFLINE))
-			continue;
-
 		if (chunk->type & NVM_CHK_TP_SZ_SPEC) {
 			WARN_ONCE(1, "pblk: custom-sized chunks unsupported\n");
 			continue;
 		}
 
+		if (!(chunk->state & NVM_CHK_ST_OFFLINE))
+			continue;
+
 		set_bit(pos, line->blk_bitmap);
 		nr_bad_chks++;
 	}
@@ -809,20 +829,28 @@ static int pblk_alloc_line_meta(struct pblk *pblk, struct pblk_line *line)
 		return -ENOMEM;
 
 	line->erase_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
-	if (!line->erase_bitmap) {
-		kfree(line->blk_bitmap);
-		return -ENOMEM;
-	}
+	if (!line->erase_bitmap)
+		goto free_blk_bitmap;
+
 
 	line->chks = kmalloc(lm->blk_per_line * sizeof(struct nvm_chk_meta),
 								GFP_KERNEL);
-	if (!line->chks) {
-		kfree(line->erase_bitmap);
-		kfree(line->blk_bitmap);
-		return -ENOMEM;
-	}
+	if (!line->chks)
+		goto free_erase_bitmap;
+
+	line->w_err_gc = kzalloc(sizeof(struct pblk_w_err_gc), GFP_KERNEL);
+	if (!line->w_err_gc)
+		goto free_chks;
 
 	return 0;
+
+free_chks:
+	kfree(line->chks);
+free_erase_bitmap:
+	kfree(line->erase_bitmap);
+free_blk_bitmap:
+	kfree(line->blk_bitmap);
+	return -ENOMEM;
 }
 
 static int pblk_line_mg_init(struct pblk *pblk)
@@ -847,12 +875,14 @@ static int pblk_line_mg_init(struct pblk *pblk)
 	INIT_LIST_HEAD(&l_mg->gc_mid_list);
 	INIT_LIST_HEAD(&l_mg->gc_low_list);
 	INIT_LIST_HEAD(&l_mg->gc_empty_list);
+	INIT_LIST_HEAD(&l_mg->gc_werr_list);
 
 	INIT_LIST_HEAD(&l_mg->emeta_list);
 
-	l_mg->gc_lists[0] = &l_mg->gc_high_list;
-	l_mg->gc_lists[1] = &l_mg->gc_mid_list;
-	l_mg->gc_lists[2] = &l_mg->gc_low_list;
+	l_mg->gc_lists[0] = &l_mg->gc_werr_list;
+	l_mg->gc_lists[1] = &l_mg->gc_high_list;
+	l_mg->gc_lists[2] = &l_mg->gc_mid_list;
+	l_mg->gc_lists[3] = &l_mg->gc_low_list;
 
 	spin_lock_init(&l_mg->free_lock);
 	spin_lock_init(&l_mg->close_lock);
@@ -1047,6 +1077,11 @@ static int pblk_lines_init(struct pblk *pblk)
 		nr_free_chks += pblk_setup_line_meta(pblk, line, chunk_meta, i);
 	}
 
+	if (!nr_free_chks) {
+		pr_err("pblk: too many bad blocks prevent for sane instance\n");
+		return -EINTR;
+	}
+
 	pblk_set_provision(pblk, nr_free_chks);
 
 	kfree(chunk_meta);
@@ -1054,7 +1089,7 @@ static int pblk_lines_init(struct pblk *pblk)
 
 fail_free_lines:
 	while (--i >= 0)
-		pblk_line_meta_free(&pblk->lines[i]);
+		pblk_line_meta_free(l_mg, &pblk->lines[i]);
 	kfree(pblk->lines);
 fail_free_chunk_meta:
 	kfree(chunk_meta);
@@ -1110,23 +1145,25 @@ static void pblk_free(struct pblk *pblk)
 	kfree(pblk);
 }
 
-static void pblk_tear_down(struct pblk *pblk)
+static void pblk_tear_down(struct pblk *pblk, bool graceful)
 {
-	pblk_pipeline_stop(pblk);
+	if (graceful)
+		__pblk_pipeline_flush(pblk);
+	__pblk_pipeline_stop(pblk);
 	pblk_writer_stop(pblk);
 	pblk_rb_sync_l2p(&pblk->rwb);
 	pblk_rl_free(&pblk->rl);
 
-	pr_debug("pblk: consistent tear down\n");
+	pr_debug("pblk: consistent tear down (graceful:%d)\n", graceful);
 }
 
-static void pblk_exit(void *private)
+static void pblk_exit(void *private, bool graceful)
 {
 	struct pblk *pblk = private;
 
 	down_write(&pblk_lock);
-	pblk_gc_exit(pblk);
-	pblk_tear_down(pblk);
+	pblk_gc_exit(pblk, graceful);
+	pblk_tear_down(pblk, graceful);
 
 #ifdef CONFIG_NVM_DEBUG
 	pr_info("pblk exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
@@ -1175,6 +1212,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	pblk->state = PBLK_STATE_RUNNING;
 	pblk->gc.gc_enabled = 0;
 
+	spin_lock_init(&pblk->resubmit_lock);
 	spin_lock_init(&pblk->trans_lock);
 	spin_lock_init(&pblk->lock);
 
@@ -1297,18 +1335,18 @@ static int __init pblk_module_init(void)
 {
 	int ret;
 
-	pblk_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
-	if (!pblk_bio_set)
-		return -ENOMEM;
+	ret = bioset_init(&pblk_bio_set, BIO_POOL_SIZE, 0, 0);
+	if (ret)
+		return ret;
 	ret = nvm_register_tgt_type(&tt_pblk);
 	if (ret)
-		bioset_free(pblk_bio_set);
+		bioset_exit(&pblk_bio_set);
 	return ret;
 }
 
 static void pblk_module_exit(void)
 {
-	bioset_free(pblk_bio_set);
+	bioset_exit(&pblk_bio_set);
 	nvm_unregister_tgt_type(&tt_pblk);
 }
 
diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
index 20dbaa89c9df..953ca31dda68 100644
--- a/drivers/lightnvm/pblk-map.c
+++ b/drivers/lightnvm/pblk-map.c
@@ -18,11 +18,11 @@
 
 #include "pblk.h"
 
-static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
-			       struct ppa_addr *ppa_list,
-			       unsigned long *lun_bitmap,
-			       struct pblk_sec_meta *meta_list,
-			       unsigned int valid_secs)
+static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
+			      struct ppa_addr *ppa_list,
+			      unsigned long *lun_bitmap,
+			      struct pblk_sec_meta *meta_list,
+			      unsigned int valid_secs)
 {
 	struct pblk_line *line = pblk_line_get_data(pblk);
 	struct pblk_emeta *emeta;
@@ -35,8 +35,14 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
 	if (pblk_line_is_full(line)) {
 		struct pblk_line *prev_line = line;
 
+		/* If we cannot allocate a new line, make sure to store metadata
+		 * on current line and then fail
+		 */
 		line = pblk_line_replace_data(pblk);
 		pblk_line_close_meta(pblk, prev_line);
+
+		if (!line)
+			return -EINTR;
 	}
 
 	emeta = line->emeta;
@@ -74,6 +80,7 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
 	}
 
 	pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap);
+	return 0;
 }
 
 void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
@@ -87,8 +94,12 @@ void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
 
 	for (i = off; i < rqd->nr_ppas; i += min) {
 		map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
-		pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
-					lun_bitmap, &meta_list[i], map_secs);
+		if (pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+					lun_bitmap, &meta_list[i], map_secs)) {
+			bio_put(rqd->bio);
+			pblk_free_rqd(pblk, rqd, PBLK_WRITE);
+			pblk_pipeline_stop(pblk);
+		}
 	}
 }
 
@@ -108,8 +119,12 @@ void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
 
 	for (i = 0; i < rqd->nr_ppas; i += min) {
 		map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
-		pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
-					lun_bitmap, &meta_list[i], map_secs);
+		if (pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+					lun_bitmap, &meta_list[i], map_secs)) {
+			bio_put(rqd->bio);
+			pblk_free_rqd(pblk, rqd, PBLK_WRITE);
+			pblk_pipeline_stop(pblk);
+		}
 
 		erase_lun = pblk_ppa_to_pos(geo, rqd->ppa_list[i]);
 
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 52fdd85dbc97..00cd1f20a196 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -142,10 +142,9 @@ static void clean_wctx(struct pblk_w_ctx *w_ctx)
 {
 	int flags;
 
-try:
 	flags = READ_ONCE(w_ctx->flags);
-	if (!(flags & PBLK_SUBMITTED_ENTRY))
-		goto try;
+	WARN_ONCE(!(flags & PBLK_SUBMITTED_ENTRY),
+			"pblk: overwriting unsubmitted data\n");
 
 	/* Release flags on context. Protect from writes and reads */
 	smp_store_release(&w_ctx->flags, PBLK_WRITABLE_ENTRY);
@@ -350,7 +349,7 @@ void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
 }
 
 static int pblk_rb_flush_point_set(struct pblk_rb *rb, struct bio *bio,
-				  unsigned int pos)
+				   unsigned int pos)
 {
 	struct pblk_rb_entry *entry;
 	unsigned int sync, flush_point;
@@ -420,7 +419,7 @@ void pblk_rb_flush(struct pblk_rb *rb)
 	if (pblk_rb_flush_point_set(rb, NULL, mem))
 		return;
 
-	pblk_write_should_kick(pblk);
+	pblk_write_kick(pblk);
 }
 
 static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries,
@@ -504,45 +503,6 @@ int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
 }
 
 /*
- * The caller of this function must ensure that the backpointer will not
- * overwrite the entries passed on the list.
- */
-unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
-				      struct list_head *list,
-				      unsigned int max)
-{
-	struct pblk_rb_entry *entry, *tentry;
-	struct page *page;
-	unsigned int read = 0;
-	int ret;
-
-	list_for_each_entry_safe(entry, tentry, list, index) {
-		if (read > max) {
-			pr_err("pblk: too many entries on list\n");
-			goto out;
-		}
-
-		page = virt_to_page(entry->data);
-		if (!page) {
-			pr_err("pblk: could not allocate write bio page\n");
-			goto out;
-		}
-
-		ret = bio_add_page(bio, page, rb->seg_size, 0);
-		if (ret != rb->seg_size) {
-			pr_err("pblk: could not add page to write bio\n");
-			goto out;
-		}
-
-		list_del(&entry->index);
-		read++;
-	}
-
-out:
-	return read;
-}
-
-/*
  * Read available entries on rb and add them to the given bio. To avoid a memory
  * copy, a page reference to the write buffer is used to be added to the bio.
  *
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 9eee10f69df0..18694694e5f0 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -39,10 +39,10 @@ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
 }
 
 static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
-				 sector_t blba, unsigned long *read_bitmap)
+				 struct bio *bio, sector_t blba,
+				 unsigned long *read_bitmap)
 {
 	struct pblk_sec_meta *meta_list = rqd->meta_list;
-	struct bio *bio = rqd->bio;
 	struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
 	int nr_secs = rqd->nr_ppas;
 	bool advanced_bio = false;
@@ -102,32 +102,69 @@ next:
 #endif
 }
 
-static int pblk_submit_read_io(struct pblk *pblk, struct nvm_rq *rqd)
+
+static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
+				sector_t blba)
 {
-	int err;
+	struct pblk_sec_meta *meta_lba_list = rqd->meta_list;
+	int nr_lbas = rqd->nr_ppas;
+	int i;
 
-	err = pblk_submit_io(pblk, rqd);
-	if (err)
-		return NVM_IO_ERR;
+	for (i = 0; i < nr_lbas; i++) {
+		u64 lba = le64_to_cpu(meta_lba_list[i].lba);
+
+		if (lba == ADDR_EMPTY)
+			continue;
+
+		if (lba != blba + i) {
+#ifdef CONFIG_NVM_DEBUG
+			struct ppa_addr *p;
 
-	return NVM_IO_OK;
+			p = (nr_lbas == 1) ? &rqd->ppa_list[i] : &rqd->ppa_addr;
+			print_ppa(&pblk->dev->geo, p, "seq", i);
+#endif
+			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+							lba, (u64)blba + i);
+			WARN_ON(1);
+		}
+	}
 }
 
-static void pblk_read_check(struct pblk *pblk, struct nvm_rq *rqd,
-			   sector_t blba)
+/*
+ * There can be holes in the lba list.
+ */
+static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
+				 u64 *lba_list, int nr_lbas)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
-	int nr_lbas = rqd->nr_ppas;
-	int i;
+	struct pblk_sec_meta *meta_lba_list = rqd->meta_list;
+	int i, j;
 
-	for (i = 0; i < nr_lbas; i++) {
-		u64 lba = le64_to_cpu(meta_list[i].lba);
+	for (i = 0, j = 0; i < nr_lbas; i++) {
+		u64 lba = lba_list[i];
+		u64 meta_lba;
 
 		if (lba == ADDR_EMPTY)
 			continue;
 
-		WARN(lba != blba + i, "pblk: corrupted read LBA\n");
+		meta_lba = le64_to_cpu(meta_lba_list[j].lba);
+
+		if (lba != meta_lba) {
+#ifdef CONFIG_NVM_DEBUG
+			struct ppa_addr *p;
+			int nr_ppas = rqd->nr_ppas;
+
+			p = (nr_ppas == 1) ? &rqd->ppa_list[j] : &rqd->ppa_addr;
+			print_ppa(&pblk->dev->geo, p, "seq", j);
+#endif
+			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+								lba, meta_lba);
+			WARN_ON(1);
+		}
+
+		j++;
 	}
+
+	WARN_ONCE(j != rqd->nr_ppas, "pblk: corrupted random request\n");
 }
 
 static void pblk_read_put_rqd_kref(struct pblk *pblk, struct nvm_rq *rqd)
@@ -152,7 +189,6 @@ static void pblk_end_user_read(struct bio *bio)
 	WARN_ONCE(bio->bi_status, "pblk: corrupted read bio\n");
 #endif
 	bio_endio(bio);
-	bio_put(bio);
 }
 
 static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
@@ -160,23 +196,18 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
-	struct bio *bio = rqd->bio;
+	struct bio *int_bio = rqd->bio;
 	unsigned long start_time = r_ctx->start_time;
 
 	generic_end_io_acct(dev->q, READ, &pblk->disk->part0, start_time);
 
 	if (rqd->error)
 		pblk_log_read_err(pblk, rqd);
-#ifdef CONFIG_NVM_DEBUG
-	else
-		WARN_ONCE(bio->bi_status, "pblk: corrupted read error\n");
-#endif
 
-	pblk_read_check(pblk, rqd, r_ctx->lba);
+	pblk_read_check_seq(pblk, rqd, r_ctx->lba);
 
-	bio_put(bio);
-	if (r_ctx->private)
-		pblk_end_user_read((struct bio *)r_ctx->private);
+	if (int_bio)
+		bio_put(int_bio);
 
 	if (put_line)
 		pblk_read_put_rqd_kref(pblk, rqd);
@@ -193,16 +224,19 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 static void pblk_end_io_read(struct nvm_rq *rqd)
 {
 	struct pblk *pblk = rqd->private;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct bio *bio = (struct bio *)r_ctx->private;
 
+	pblk_end_user_read(bio);
 	__pblk_end_io_read(pblk, rqd, true);
 }
 
-static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
-				 unsigned int bio_init_idx,
-				 unsigned long *read_bitmap)
+static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
+			     struct bio *orig_bio, unsigned int bio_init_idx,
+			     unsigned long *read_bitmap)
 {
-	struct bio *new_bio, *bio = rqd->bio;
 	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	struct bio *new_bio;
 	struct bio_vec src_bv, dst_bv;
 	void *ppa_ptr = NULL;
 	void *src_p, *dst_p;
@@ -219,11 +253,11 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
 	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
 
 	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
-		goto err;
+		goto fail_add_pages;
 
 	if (nr_holes != new_bio->bi_vcnt) {
 		pr_err("pblk: malformed bio\n");
-		goto err;
+		goto fail;
 	}
 
 	for (i = 0; i < nr_secs; i++)
@@ -246,7 +280,7 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
 	if (ret) {
 		bio_put(rqd->bio);
 		pr_err("pblk: sync read IO submission failed\n");
-		goto err;
+		goto fail;
 	}
 
 	if (rqd->error) {
@@ -282,7 +316,7 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_list[hole].lba = lba_list_media[i];
 
 		src_bv = new_bio->bi_io_vec[i++];
-		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
+		dst_bv = orig_bio->bi_io_vec[bio_init_idx + hole];
 
 		src_p = kmap_atomic(src_bv.bv_page);
 		dst_p = kmap_atomic(dst_bv.bv_page);
@@ -294,35 +328,33 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
 		kunmap_atomic(src_p);
 		kunmap_atomic(dst_p);
 
-		mempool_free(src_bv.bv_page, pblk->page_bio_pool);
+		mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
 
 		hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
 	} while (hole < nr_secs);
 
 	bio_put(new_bio);
 
-	/* Complete the original bio and associated request */
-	bio_endio(bio);
-	rqd->bio = bio;
+	/* restore original request */
+	rqd->bio = NULL;
 	rqd->nr_ppas = nr_secs;
 
 	__pblk_end_io_read(pblk, rqd, false);
-	return NVM_IO_OK;
-
-err:
-	pr_err("pblk: failed to perform partial read\n");
+	return NVM_IO_DONE;
 
+fail:
 	/* Free allocated pages in new bio */
-	pblk_bio_free_pages(pblk, bio, 0, new_bio->bi_vcnt);
+	pblk_bio_free_pages(pblk, new_bio, 0, new_bio->bi_vcnt);
+fail_add_pages:
+	pr_err("pblk: failed to perform partial read\n");
 	__pblk_end_io_read(pblk, rqd, false);
 	return NVM_IO_ERR;
 }
 
-static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd,
+static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
 			 sector_t lba, unsigned long *read_bitmap)
 {
 	struct pblk_sec_meta *meta_list = rqd->meta_list;
-	struct bio *bio = rqd->bio;
 	struct ppa_addr ppa;
 
 	pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
@@ -386,14 +418,15 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	rqd = pblk_alloc_rqd(pblk, PBLK_READ);
 
 	rqd->opcode = NVM_OP_PREAD;
-	rqd->bio = bio;
 	rqd->nr_ppas = nr_secs;
+	rqd->bio = NULL; /* cloned bio if needed */
 	rqd->private = pblk;
 	rqd->end_io = pblk_end_io_read;
 
 	r_ctx = nvm_rq_to_pdu(rqd);
 	r_ctx->start_time = jiffies;
 	r_ctx->lba = blba;
+	r_ctx->private = bio; /* original bio */
 
 	/* Save the index for this bio's start. This is needed in case
 	 * we need to fill a partial read.
@@ -411,17 +444,15 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
 		rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
 
-		pblk_read_ppalist_rq(pblk, rqd, blba, &read_bitmap);
+		pblk_read_ppalist_rq(pblk, rqd, bio, blba, &read_bitmap);
 	} else {
-		pblk_read_rq(pblk, rqd, blba, &read_bitmap);
+		pblk_read_rq(pblk, rqd, bio, blba, &read_bitmap);
 	}
 
-	bio_get(bio);
 	if (bitmap_full(&read_bitmap, nr_secs)) {
-		bio_endio(bio);
 		atomic_inc(&pblk->inflight_io);
 		__pblk_end_io_read(pblk, rqd, false);
-		return NVM_IO_OK;
+		return NVM_IO_DONE;
 	}
 
 	/* All sectors are to be read from the device */
@@ -429,20 +460,17 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		struct bio *int_bio = NULL;
 
 		/* Clone read bio to deal with read errors internally */
-		int_bio = bio_clone_fast(bio, GFP_KERNEL, pblk_bio_set);
+		int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
 		if (!int_bio) {
 			pr_err("pblk: could not clone read bio\n");
 			goto fail_end_io;
 		}
 
 		rqd->bio = int_bio;
-		r_ctx->private = bio;
 
-		ret = pblk_submit_read_io(pblk, rqd);
-		if (ret) {
+		if (pblk_submit_io(pblk, rqd)) {
 			pr_err("pblk: read IO submission failed\n");
-			if (int_bio)
-				bio_put(int_bio);
+			ret = NVM_IO_ERR;
 			goto fail_end_io;
 		}
 
@@ -452,7 +480,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	/* The read bio request could be partially filled by the write buffer,
 	 * but there are some holes that need to be read from the drive.
 	 */
-	return pblk_partial_read_bio(pblk, rqd, bio_init_idx, &read_bitmap);
+	return pblk_partial_read(pblk, rqd, bio, bio_init_idx, &read_bitmap);
 
 fail_rqd_free:
 	pblk_free_rqd(pblk, rqd, PBLK_READ);
@@ -585,6 +613,8 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 		goto err_free_bio;
 	}
 
+	pblk_read_check_rand(pblk, &rqd, gc_rq->lba_list, gc_rq->nr_secs);
+
 	atomic_dec(&pblk->inflight_io);
 
 	if (rqd.error) {
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 3e079c2afa6e..598342833d0d 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -16,97 +16,6 @@
 
 #include "pblk.h"
 
-void pblk_submit_rec(struct work_struct *work)
-{
-	struct pblk_rec_ctx *recovery =
-			container_of(work, struct pblk_rec_ctx, ws_rec);
-	struct pblk *pblk = recovery->pblk;
-	struct nvm_rq *rqd = recovery->rqd;
-	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
-	struct bio *bio;
-	unsigned int nr_rec_secs;
-	unsigned int pgs_read;
-	int ret;
-
-	nr_rec_secs = bitmap_weight((unsigned long int *)&rqd->ppa_status,
-								NVM_MAX_VLBA);
-
-	bio = bio_alloc(GFP_KERNEL, nr_rec_secs);
-
-	bio->bi_iter.bi_sector = 0;
-	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-	rqd->bio = bio;
-	rqd->nr_ppas = nr_rec_secs;
-
-	pgs_read = pblk_rb_read_to_bio_list(&pblk->rwb, bio, &recovery->failed,
-								nr_rec_secs);
-	if (pgs_read != nr_rec_secs) {
-		pr_err("pblk: could not read recovery entries\n");
-		goto err;
-	}
-
-	if (pblk_setup_w_rec_rq(pblk, rqd, c_ctx)) {
-		pr_err("pblk: could not setup recovery request\n");
-		goto err;
-	}
-
-#ifdef CONFIG_NVM_DEBUG
-	atomic_long_add(nr_rec_secs, &pblk->recov_writes);
-#endif
-
-	ret = pblk_submit_io(pblk, rqd);
-	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
-		goto err;
-	}
-
-	mempool_free(recovery, pblk->rec_pool);
-	return;
-
-err:
-	bio_put(bio);
-	pblk_free_rqd(pblk, rqd, PBLK_WRITE);
-}
-
-int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
-			struct pblk_rec_ctx *recovery, u64 *comp_bits,
-			unsigned int comp)
-{
-	struct nvm_rq *rec_rqd;
-	struct pblk_c_ctx *rec_ctx;
-	int nr_entries = c_ctx->nr_valid + c_ctx->nr_padded;
-
-	rec_rqd = pblk_alloc_rqd(pblk, PBLK_WRITE);
-	rec_ctx = nvm_rq_to_pdu(rec_rqd);
-
-	/* Copy completion bitmap, but exclude the first X completed entries */
-	bitmap_shift_right((unsigned long int *)&rec_rqd->ppa_status,
-				(unsigned long int *)comp_bits,
-				comp, NVM_MAX_VLBA);
-
-	/* Save the context for the entries that need to be re-written and
-	 * update current context with the completed entries.
-	 */
-	rec_ctx->sentry = pblk_rb_wrap_pos(&pblk->rwb, c_ctx->sentry + comp);
-	if (comp >= c_ctx->nr_valid) {
-		rec_ctx->nr_valid = 0;
-		rec_ctx->nr_padded = nr_entries - comp;
-
-		c_ctx->nr_padded = comp - c_ctx->nr_valid;
-	} else {
-		rec_ctx->nr_valid = c_ctx->nr_valid - comp;
-		rec_ctx->nr_padded = c_ctx->nr_padded;
-
-		c_ctx->nr_valid = comp;
-		c_ctx->nr_padded = 0;
-	}
-
-	recovery->rqd = rec_rqd;
-	recovery->pblk = pblk;
-
-	return 0;
-}
-
 int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta_buf)
 {
 	u32 crc;
@@ -865,18 +774,30 @@ static void pblk_recov_wa_counters(struct pblk *pblk,
 }
 
 static int pblk_line_was_written(struct pblk_line *line,
-			    struct pblk_line_meta *lm)
+			    struct pblk *pblk)
 {
 
-	int i;
-	int state_mask = NVM_CHK_ST_OFFLINE | NVM_CHK_ST_FREE;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct nvm_chk_meta *chunk;
+	struct ppa_addr bppa;
+	int smeta_blk;
 
-	for (i = 0; i < lm->blk_per_line; i++) {
-		if (!(line->chks[i].state & state_mask))
-			return 1;
-	}
+	if (line->state == PBLK_LINESTATE_BAD)
+		return 0;
 
-	return 0;
+	smeta_blk = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+	if (smeta_blk >= lm->blk_per_line)
+		return 0;
+
+	bppa = pblk->luns[smeta_blk].bppa;
+	chunk = &line->chks[pblk_ppa_to_pos(geo, bppa)];
+
+	if (chunk->state & NVM_CHK_ST_FREE)
+		return 0;
+
+	return 1;
 }
 
 struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
@@ -915,7 +836,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 		line->lun_bitmap = ((void *)(smeta_buf)) +
 						sizeof(struct line_smeta);
 
-		if (!pblk_line_was_written(line, lm))
+		if (!pblk_line_was_written(line, pblk))
 			continue;
 
 		/* Lines that cannot be read are assumed as not written here */
diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c
index 883a7113b19d..6a0616a6fcaf 100644
--- a/drivers/lightnvm/pblk-rl.c
+++ b/drivers/lightnvm/pblk-rl.c
@@ -73,6 +73,16 @@ void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries)
 	pblk_rl_kick_u_timer(rl);
 }
 
+void pblk_rl_werr_line_in(struct pblk_rl *rl)
+{
+	atomic_inc(&rl->werr_lines);
+}
+
+void pblk_rl_werr_line_out(struct pblk_rl *rl)
+{
+	atomic_dec(&rl->werr_lines);
+}
+
 void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries)
 {
 	atomic_add(nr_entries, &rl->rb_gc_cnt);
@@ -99,11 +109,21 @@ static void __pblk_rl_update_rates(struct pblk_rl *rl,
 {
 	struct pblk *pblk = container_of(rl, struct pblk, rl);
 	int max = rl->rb_budget;
+	int werr_gc_needed = atomic_read(&rl->werr_lines);
 
 	if (free_blocks >= rl->high) {
-		rl->rb_user_max = max;
-		rl->rb_gc_max = 0;
-		rl->rb_state = PBLK_RL_HIGH;
+		if (werr_gc_needed) {
+			/* Allocate a small budget for recovering
+			 * lines with write errors
+			 */
+			rl->rb_gc_max = 1 << rl->rb_windows_pw;
+			rl->rb_user_max = max - rl->rb_gc_max;
+			rl->rb_state = PBLK_RL_WERR;
+		} else {
+			rl->rb_user_max = max;
+			rl->rb_gc_max = 0;
+			rl->rb_state = PBLK_RL_OFF;
+		}
 	} else if (free_blocks < rl->high) {
 		int shift = rl->high_pw - rl->rb_windows_pw;
 		int user_windows = free_blocks >> shift;
@@ -124,7 +144,7 @@ static void __pblk_rl_update_rates(struct pblk_rl *rl,
 		rl->rb_state = PBLK_RL_LOW;
 	}
 
-	if (rl->rb_state == (PBLK_RL_MID | PBLK_RL_LOW))
+	if (rl->rb_state != PBLK_RL_OFF)
 		pblk_gc_should_start(pblk);
 	else
 		pblk_gc_should_stop(pblk);
@@ -221,6 +241,7 @@ void pblk_rl_init(struct pblk_rl *rl, int budget)
 	atomic_set(&rl->rb_user_cnt, 0);
 	atomic_set(&rl->rb_gc_cnt, 0);
 	atomic_set(&rl->rb_space, -1);
+	atomic_set(&rl->werr_lines, 0);
 
 	timer_setup(&rl->u_timer, pblk_rl_u_timer, 0);
 
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index e61909af23a5..88a0a7c407aa 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -173,6 +173,8 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
 	int free_line_cnt = 0, closed_line_cnt = 0, emeta_line_cnt = 0;
 	int d_line_cnt = 0, l_line_cnt = 0;
 	int gc_full = 0, gc_high = 0, gc_mid = 0, gc_low = 0, gc_empty = 0;
+	int gc_werr = 0;
+
 	int bad = 0, cor = 0;
 	int msecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0;
 	int map_weight = 0, meta_weight = 0;
@@ -237,6 +239,15 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
 		gc_empty++;
 	}
 
+	list_for_each_entry(line, &l_mg->gc_werr_list, list) {
+		if (line->type == PBLK_LINETYPE_DATA)
+			d_line_cnt++;
+		else if (line->type == PBLK_LINETYPE_LOG)
+			l_line_cnt++;
+		closed_line_cnt++;
+		gc_werr++;
+	}
+
 	list_for_each_entry(line, &l_mg->bad_list, list)
 		bad++;
 	list_for_each_entry(line, &l_mg->corrupt_list, list)
@@ -275,8 +286,8 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
 					l_mg->nr_lines);
 
 	sz += snprintf(page + sz, PAGE_SIZE - sz,
-		"GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, queue:%d\n",
-			gc_full, gc_high, gc_mid, gc_low, gc_empty,
+		"GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, werr: %d, queue:%d\n",
+			gc_full, gc_high, gc_mid, gc_low, gc_empty, gc_werr,
 			atomic_read(&pblk->gc.read_inflight_gc));
 
 	sz += snprintf(page + sz, PAGE_SIZE - sz,
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 3e6f1ebd743a..f353e52941f5 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -103,68 +103,150 @@ retry:
 	pblk_rb_sync_end(&pblk->rwb, &flags);
 }
 
-/* When a write fails, we are not sure whether the block has grown bad or a page
- * range is more susceptible to write errors. If a high number of pages fail, we
- * assume that the block is bad and we mark it accordingly. In all cases, we
- * remap and resubmit the failed entries as fast as possible; if a flush is
- * waiting on a completion, the whole stack would stall otherwise.
- */
-static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
+/* Map remaining sectors in chunk, starting from ppa */
+static void pblk_map_remaining(struct pblk *pblk, struct ppa_addr *ppa)
 {
-	void *comp_bits = &rqd->ppa_status;
-	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
-	struct pblk_rec_ctx *recovery;
-	struct ppa_addr *ppa_list = rqd->ppa_list;
-	int nr_ppas = rqd->nr_ppas;
-	unsigned int c_entries;
-	int bit, ret;
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line *line;
+	struct ppa_addr map_ppa = *ppa;
+	u64 paddr;
+	int done = 0;
 
-	if (unlikely(nr_ppas == 1))
-		ppa_list = &rqd->ppa_addr;
+	line = &pblk->lines[pblk_ppa_to_line(*ppa)];
+	spin_lock(&line->lock);
 
-	recovery = mempool_alloc(pblk->rec_pool, GFP_ATOMIC);
+	while (!done)  {
+		paddr = pblk_dev_ppa_to_line_addr(pblk, map_ppa);
 
-	INIT_LIST_HEAD(&recovery->failed);
+		if (!test_and_set_bit(paddr, line->map_bitmap))
+			line->left_msecs--;
 
-	bit = -1;
-	while ((bit = find_next_bit(comp_bits, nr_ppas, bit + 1)) < nr_ppas) {
-		struct pblk_rb_entry *entry;
-		struct ppa_addr ppa;
+		if (!test_and_set_bit(paddr, line->invalid_bitmap))
+			le32_add_cpu(line->vsc, -1);
 
-		/* Logic error */
-		if (bit > c_ctx->nr_valid) {
-			WARN_ONCE(1, "pblk: corrupted write request\n");
-			mempool_free(recovery, pblk->rec_pool);
-			goto out;
+		if (geo->version == NVM_OCSSD_SPEC_12) {
+			map_ppa.ppa++;
+			if (map_ppa.g.pg == geo->num_pg)
+				done = 1;
+		} else {
+			map_ppa.m.sec++;
+			if (map_ppa.m.sec == geo->clba)
+				done = 1;
 		}
+	}
 
-		ppa = ppa_list[bit];
-		entry = pblk_rb_sync_scan_entry(&pblk->rwb, &ppa);
-		if (!entry) {
-			pr_err("pblk: could not scan entry on write failure\n");
-			mempool_free(recovery, pblk->rec_pool);
-			goto out;
-		}
+	line->w_err_gc->has_write_err = 1;
+	spin_unlock(&line->lock);
+}
 
-		/* The list is filled first and emptied afterwards. No need for
-		 * protecting it with a lock
+static void pblk_prepare_resubmit(struct pblk *pblk, unsigned int sentry,
+				  unsigned int nr_entries)
+{
+	struct pblk_rb *rb = &pblk->rwb;
+	struct pblk_rb_entry *entry;
+	struct pblk_line *line;
+	struct pblk_w_ctx *w_ctx;
+	struct ppa_addr ppa_l2p;
+	int flags;
+	unsigned int pos, i;
+
+	spin_lock(&pblk->trans_lock);
+	pos = sentry;
+	for (i = 0; i < nr_entries; i++) {
+		entry = &rb->entries[pos];
+		w_ctx = &entry->w_ctx;
+
+		/* Check if the lba has been overwritten */
+		ppa_l2p = pblk_trans_map_get(pblk, w_ctx->lba);
+		if (!pblk_ppa_comp(ppa_l2p, entry->cacheline))
+			w_ctx->lba = ADDR_EMPTY;
+
+		/* Mark up the entry as submittable again */
+		flags = READ_ONCE(w_ctx->flags);
+		flags |= PBLK_WRITTEN_DATA;
+		/* Release flags on write context. Protect from writes */
+		smp_store_release(&w_ctx->flags, flags);
+
+		/* Decrese the reference count to the line as we will
+		 * re-map these entries
 		 */
-		list_add_tail(&entry->index, &recovery->failed);
+		line = &pblk->lines[pblk_ppa_to_line(w_ctx->ppa)];
+		kref_put(&line->ref, pblk_line_put);
+
+		pos = (pos + 1) & (rb->nr_entries - 1);
 	}
+	spin_unlock(&pblk->trans_lock);
+}
 
-	c_entries = find_first_bit(comp_bits, nr_ppas);
-	ret = pblk_recov_setup_rq(pblk, c_ctx, recovery, comp_bits, c_entries);
-	if (ret) {
-		pr_err("pblk: could not recover from write failure\n");
-		mempool_free(recovery, pblk->rec_pool);
-		goto out;
+static void pblk_queue_resubmit(struct pblk *pblk, struct pblk_c_ctx *c_ctx)
+{
+	struct pblk_c_ctx *r_ctx;
+
+	r_ctx = kzalloc(sizeof(struct pblk_c_ctx), GFP_KERNEL);
+	if (!r_ctx)
+		return;
+
+	r_ctx->lun_bitmap = NULL;
+	r_ctx->sentry = c_ctx->sentry;
+	r_ctx->nr_valid = c_ctx->nr_valid;
+	r_ctx->nr_padded = c_ctx->nr_padded;
+
+	spin_lock(&pblk->resubmit_lock);
+	list_add_tail(&r_ctx->list, &pblk->resubmit_list);
+	spin_unlock(&pblk->resubmit_lock);
+
+#ifdef CONFIG_NVM_DEBUG
+	atomic_long_add(c_ctx->nr_valid, &pblk->recov_writes);
+#endif
+}
+
+static void pblk_submit_rec(struct work_struct *work)
+{
+	struct pblk_rec_ctx *recovery =
+			container_of(work, struct pblk_rec_ctx, ws_rec);
+	struct pblk *pblk = recovery->pblk;
+	struct nvm_rq *rqd = recovery->rqd;
+	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+	struct ppa_addr *ppa_list;
+
+	pblk_log_write_err(pblk, rqd);
+
+	if (rqd->nr_ppas == 1)
+		ppa_list = &rqd->ppa_addr;
+	else
+		ppa_list = rqd->ppa_list;
+
+	pblk_map_remaining(pblk, ppa_list);
+	pblk_queue_resubmit(pblk, c_ctx);
+
+	pblk_up_rq(pblk, rqd->ppa_list, rqd->nr_ppas, c_ctx->lun_bitmap);
+	if (c_ctx->nr_padded)
+		pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid,
+							c_ctx->nr_padded);
+	bio_put(rqd->bio);
+	pblk_free_rqd(pblk, rqd, PBLK_WRITE);
+	mempool_free(recovery, &pblk->rec_pool);
+
+	atomic_dec(&pblk->inflight_io);
+}
+
+
+static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	struct pblk_rec_ctx *recovery;
+
+	recovery = mempool_alloc(&pblk->rec_pool, GFP_ATOMIC);
+	if (!recovery) {
+		pr_err("pblk: could not allocate recovery work\n");
+		return;
 	}
 
+	recovery->pblk = pblk;
+	recovery->rqd = rqd;
+
 	INIT_WORK(&recovery->ws_rec, pblk_submit_rec);
 	queue_work(pblk->close_wq, &recovery->ws_rec);
-
-out:
-	pblk_complete_write(pblk, rqd, c_ctx);
 }
 
 static void pblk_end_io_write(struct nvm_rq *rqd)
@@ -173,8 +255,8 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
 	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
 
 	if (rqd->error) {
-		pblk_log_write_err(pblk, rqd);
-		return pblk_end_w_fail(pblk, rqd);
+		pblk_end_w_fail(pblk, rqd);
+		return;
 	}
 #ifdef CONFIG_NVM_DEBUG
 	else
@@ -198,6 +280,7 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 	if (rqd->error) {
 		pblk_log_write_err(pblk, rqd);
 		pr_err("pblk: metadata I/O failed. Line %d\n", line->id);
+		line->w_err_gc->has_write_err = 1;
 	}
 
 	sync = atomic_add_return(rqd->nr_ppas, &emeta->sync);
@@ -266,31 +349,6 @@ static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	return 0;
 }
 
-int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
-			struct pblk_c_ctx *c_ctx)
-{
-	struct pblk_line_meta *lm = &pblk->lm;
-	unsigned long *lun_bitmap;
-	int ret;
-
-	lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
-	if (!lun_bitmap)
-		return -ENOMEM;
-
-	c_ctx->lun_bitmap = lun_bitmap;
-
-	ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas, pblk_end_io_write);
-	if (ret)
-		return ret;
-
-	pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, c_ctx->nr_valid, 0);
-
-	rqd->ppa_status = (u64)0;
-	rqd->flags = pblk_set_progr_mode(pblk, PBLK_WRITE);
-
-	return ret;
-}
-
 static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
 				  unsigned int secs_to_flush)
 {
@@ -339,6 +397,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 	bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
 					l_mg->emeta_alloc_type, GFP_KERNEL);
 	if (IS_ERR(bio)) {
+		pr_err("pblk: failed to map emeta io");
 		ret = PTR_ERR(bio);
 		goto fail_free_rqd;
 	}
@@ -515,26 +574,54 @@ static int pblk_submit_write(struct pblk *pblk)
 	unsigned int secs_avail, secs_to_sync, secs_to_com;
 	unsigned int secs_to_flush;
 	unsigned long pos;
+	unsigned int resubmit;
 
-	/* If there are no sectors in the cache, flushes (bios without data)
-	 * will be cleared on the cache threads
-	 */
-	secs_avail = pblk_rb_read_count(&pblk->rwb);
-	if (!secs_avail)
-		return 1;
-
-	secs_to_flush = pblk_rb_flush_point_count(&pblk->rwb);
-	if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
-		return 1;
-
-	secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, secs_to_flush);
-	if (secs_to_sync > pblk->max_write_pgs) {
-		pr_err("pblk: bad buffer sync calculation\n");
-		return 1;
-	}
+	spin_lock(&pblk->resubmit_lock);
+	resubmit = !list_empty(&pblk->resubmit_list);
+	spin_unlock(&pblk->resubmit_lock);
+
+	/* Resubmit failed writes first */
+	if (resubmit) {
+		struct pblk_c_ctx *r_ctx;
+
+		spin_lock(&pblk->resubmit_lock);
+		r_ctx = list_first_entry(&pblk->resubmit_list,
+					struct pblk_c_ctx, list);
+		list_del(&r_ctx->list);
+		spin_unlock(&pblk->resubmit_lock);
+
+		secs_avail = r_ctx->nr_valid;
+		pos = r_ctx->sentry;
+
+		pblk_prepare_resubmit(pblk, pos, secs_avail);
+		secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
+				secs_avail);
 
-	secs_to_com = (secs_to_sync > secs_avail) ? secs_avail : secs_to_sync;
-	pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
+		kfree(r_ctx);
+	} else {
+		/* If there are no sectors in the cache,
+		 * flushes (bios without data) will be cleared on
+		 * the cache threads
+		 */
+		secs_avail = pblk_rb_read_count(&pblk->rwb);
+		if (!secs_avail)
+			return 1;
+
+		secs_to_flush = pblk_rb_flush_point_count(&pblk->rwb);
+		if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
+			return 1;
+
+		secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
+					secs_to_flush);
+		if (secs_to_sync > pblk->max_write_pgs) {
+			pr_err("pblk: bad buffer sync calculation\n");
+			return 1;
+		}
+
+		secs_to_com = (secs_to_sync > secs_avail) ?
+			secs_avail : secs_to_sync;
+		pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
+	}
 
 	bio = bio_alloc(GFP_KERNEL, secs_to_sync);
 
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 9c682acfc5d1..34cc1d64a9d4 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -89,12 +89,14 @@ struct pblk_sec_meta {
 /* The number of GC lists and the rate-limiter states go together. This way the
  * rate-limiter can dictate how much GC is needed based on resource utilization.
  */
-#define PBLK_GC_NR_LISTS 3
+#define PBLK_GC_NR_LISTS 4
 
 enum {
-	PBLK_RL_HIGH = 1,
-	PBLK_RL_MID = 2,
-	PBLK_RL_LOW = 3,
+	PBLK_RL_OFF = 0,
+	PBLK_RL_WERR = 1,
+	PBLK_RL_HIGH = 2,
+	PBLK_RL_MID = 3,
+	PBLK_RL_LOW = 4
 };
 
 #define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * PBLK_MAX_REQ_ADDRS)
@@ -128,7 +130,6 @@ struct pblk_pad_rq {
 struct pblk_rec_ctx {
 	struct pblk *pblk;
 	struct nvm_rq *rqd;
-	struct list_head failed;
 	struct work_struct ws_rec;
 };
 
@@ -279,6 +280,8 @@ struct pblk_rl {
 	int rb_user_active;
 	int rb_gc_active;
 
+	atomic_t werr_lines;	/* Number of write error lines that needs gc */
+
 	struct timer_list u_timer;
 
 	unsigned long long nr_secs;
@@ -312,6 +315,7 @@ enum {
 	PBLK_LINEGC_MID = 23,
 	PBLK_LINEGC_HIGH = 24,
 	PBLK_LINEGC_FULL = 25,
+	PBLK_LINEGC_WERR = 26
 };
 
 #define PBLK_MAGIC 0x70626c6b /*pblk*/
@@ -413,6 +417,11 @@ struct pblk_smeta {
 	struct line_smeta *buf;		/* smeta buffer in persistent format */
 };
 
+struct pblk_w_err_gc {
+	int has_write_err;
+	__le64 *lba_list;
+};
+
 struct pblk_line {
 	struct pblk *pblk;
 	unsigned int id;		/* Line number corresponds to the
@@ -458,6 +467,8 @@ struct pblk_line {
 
 	struct kref ref;		/* Write buffer L2P references */
 
+	struct pblk_w_err_gc *w_err_gc;	/* Write error gc recovery metadata */
+
 	spinlock_t lock;		/* Necessary for invalid_bitmap only */
 };
 
@@ -489,6 +500,8 @@ struct pblk_line_mgmt {
 	struct list_head gc_mid_list;	/* Full lines ready to GC, mid isc */
 	struct list_head gc_low_list;	/* Full lines ready to GC, low isc */
 
+	struct list_head gc_werr_list;  /* Write err recovery list */
+
 	struct list_head gc_full_list;	/* Full lines ready to GC, no valid */
 	struct list_head gc_empty_list;	/* Full lines close, all valid */
 
@@ -664,12 +677,15 @@ struct pblk {
 
 	struct list_head compl_list;
 
-	mempool_t *page_bio_pool;
-	mempool_t *gen_ws_pool;
-	mempool_t *rec_pool;
-	mempool_t *r_rq_pool;
-	mempool_t *w_rq_pool;
-	mempool_t *e_rq_pool;
+	spinlock_t resubmit_lock;	 /* Resubmit list lock */
+	struct list_head resubmit_list; /* Resubmit list for failed writes*/
+
+	mempool_t page_bio_pool;
+	mempool_t gen_ws_pool;
+	mempool_t rec_pool;
+	mempool_t r_rq_pool;
+	mempool_t w_rq_pool;
+	mempool_t e_rq_pool;
 
 	struct workqueue_struct *close_wq;
 	struct workqueue_struct *bb_wq;
@@ -713,9 +729,6 @@ void pblk_rb_sync_l2p(struct pblk_rb *rb);
 unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
 				 unsigned int pos, unsigned int nr_entries,
 				 unsigned int count);
-unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
-				      struct list_head *list,
-				      unsigned int max);
 int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
 			struct ppa_addr ppa, int bio_iter, bool advanced_bio);
 unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries);
@@ -766,11 +779,13 @@ struct pblk_line *pblk_line_get_data(struct pblk *pblk);
 struct pblk_line *pblk_line_get_erase(struct pblk *pblk);
 int pblk_line_erase(struct pblk *pblk, struct pblk_line *line);
 int pblk_line_is_full(struct pblk_line *line);
-void pblk_line_free(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_free(struct pblk_line *line);
 void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line);
 void pblk_line_close(struct pblk *pblk, struct pblk_line *line);
 void pblk_line_close_ws(struct work_struct *work);
 void pblk_pipeline_stop(struct pblk *pblk);
+void __pblk_pipeline_stop(struct pblk *pblk);
+void __pblk_pipeline_flush(struct pblk *pblk);
 void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
 		     void (*work)(struct work_struct *), gfp_t gfp_mask,
 		     struct workqueue_struct *wq);
@@ -794,7 +809,6 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
 void pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas);
 void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
 		unsigned long *lun_bitmap);
-void pblk_end_io_sync(struct nvm_rq *rqd);
 int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
 		       int nr_pages);
 void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
@@ -837,23 +851,20 @@ void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
 int pblk_write_ts(void *data);
 void pblk_write_timer_fn(struct timer_list *t);
 void pblk_write_should_kick(struct pblk *pblk);
+void pblk_write_kick(struct pblk *pblk);
 
 /*
  * pblk read path
  */
-extern struct bio_set *pblk_bio_set;
+extern struct bio_set pblk_bio_set;
 int pblk_submit_read(struct pblk *pblk, struct bio *bio);
 int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq);
 /*
  * pblk recovery
  */
-void pblk_submit_rec(struct work_struct *work);
 struct pblk_line *pblk_recov_l2p(struct pblk *pblk);
 int pblk_recov_pad(struct pblk *pblk);
 int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta);
-int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
-			struct pblk_rec_ctx *recovery, u64 *comp_bits,
-			unsigned int comp);
 
 /*
  * pblk gc
@@ -864,7 +875,7 @@ int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
 #define PBLK_GC_RSV_LINE 1	/* Reserved lines for GC */
 
 int pblk_gc_init(struct pblk *pblk);
-void pblk_gc_exit(struct pblk *pblk);
+void pblk_gc_exit(struct pblk *pblk, bool graceful);
 void pblk_gc_should_start(struct pblk *pblk);
 void pblk_gc_should_stop(struct pblk *pblk);
 void pblk_gc_should_kick(struct pblk *pblk);
@@ -894,6 +905,9 @@ void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line,
 			    bool used);
 int pblk_rl_is_limit(struct pblk_rl *rl);
 
+void pblk_rl_werr_line_in(struct pblk_rl *rl);
+void pblk_rl_werr_line_out(struct pblk_rl *rl);
+
 /*
  * pblk sysfs
  */
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 433dbeddfcf9..6663893f41c4 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -191,10 +191,10 @@ static int init_pmu(void);
 static void pmu_start(void);
 static irqreturn_t via_pmu_interrupt(int irq, void *arg);
 static irqreturn_t gpio1_interrupt(int irq, void *arg);
-static const struct file_operations pmu_info_proc_fops;
-static const struct file_operations pmu_irqstats_proc_fops;
+static int pmu_info_proc_show(struct seq_file *m, void *v);
+static int pmu_irqstats_proc_show(struct seq_file *m, void *v);
+static int pmu_battery_proc_show(struct seq_file *m, void *v);
 static void pmu_pass_intr(unsigned char *data, int len);
-static const struct file_operations pmu_battery_proc_fops;
 static const struct file_operations pmu_options_proc_fops;
 
 #ifdef CONFIG_ADB
@@ -511,13 +511,15 @@ static int __init via_pmu_dev_init(void)
 		for (i=0; i<pmu_battery_count; i++) {
 			char title[16];
 			sprintf(title, "battery_%ld", i);
-			proc_pmu_batt[i] = proc_create_data(title, 0, proc_pmu_root,
-					&pmu_battery_proc_fops, (void *)i);
+			proc_pmu_batt[i] = proc_create_single_data(title, 0,
+					proc_pmu_root, pmu_battery_proc_show,
+					(void *)i);
 		}
 
-		proc_pmu_info = proc_create("info", 0, proc_pmu_root, &pmu_info_proc_fops);
-		proc_pmu_irqstats = proc_create("interrupts", 0, proc_pmu_root,
-						&pmu_irqstats_proc_fops);
+		proc_pmu_info = proc_create_single("info", 0, proc_pmu_root,
+				pmu_info_proc_show);
+		proc_pmu_irqstats = proc_create_single("interrupts", 0,
+				proc_pmu_root, pmu_irqstats_proc_show);
 		proc_pmu_options = proc_create("options", 0600, proc_pmu_root,
 						&pmu_options_proc_fops);
 	}
@@ -811,19 +813,6 @@ static int pmu_info_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int pmu_info_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pmu_info_proc_show, NULL);
-}
-
-static const struct file_operations pmu_info_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pmu_info_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int pmu_irqstats_proc_show(struct seq_file *m, void *v)
 {
 	int i;
@@ -848,19 +837,6 @@ static int pmu_irqstats_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int pmu_irqstats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pmu_irqstats_proc_show, NULL);
-}
-
-static const struct file_operations pmu_irqstats_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pmu_irqstats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int pmu_battery_proc_show(struct seq_file *m, void *v)
 {
 	long batnum = (long)m->private;
@@ -875,19 +851,6 @@ static int pmu_battery_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int pmu_battery_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pmu_battery_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations pmu_battery_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pmu_battery_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int pmu_options_proc_show(struct seq_file *m, void *v)
 {
 #if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC32)
diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
index 3ef7f036ceea..fc3c237daef2 100644
--- a/drivers/mailbox/pcc.c
+++ b/drivers/mailbox/pcc.c
@@ -373,33 +373,24 @@ static const struct mbox_chan_ops pcc_chan_ops = {
 };
 
 /**
- * parse_pcc_subspace - Parse the PCC table and verify PCC subspace
- *		entries. There should be one entry per PCC client.
+ * parse_pcc_subspaces -- Count PCC subspaces defined
  * @header: Pointer to the ACPI subtable header under the PCCT.
  * @end: End of subtable entry.
  *
- * Return: 0 for Success, else errno.
+ * Return: If we find a PCC subspace entry of a valid type, return 0.
+ *	Otherwise, return -EINVAL.
  *
  * This gets called for each entry in the PCC table.
  */
 static int parse_pcc_subspace(struct acpi_subtable_header *header,
 		const unsigned long end)
 {
-	struct acpi_pcct_hw_reduced *pcct_ss;
-
-	if (pcc_mbox_ctrl.num_chans <= MAX_PCC_SUBSPACES) {
-		pcct_ss = (struct acpi_pcct_hw_reduced *) header;
+	struct acpi_pcct_subspace *ss = (struct acpi_pcct_subspace *) header;
 
-		if ((pcct_ss->header.type !=
-				ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE)
-		    && (pcct_ss->header.type !=
-				ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE_TYPE2)) {
-			pr_err("Incorrect PCC Subspace type detected\n");
-			return -EINVAL;
-		}
-	}
+	if (ss->header.type < ACPI_PCCT_TYPE_RESERVED)
+		return 0;
 
-	return 0;
+	return -EINVAL;
 }
 
 /**
@@ -449,8 +440,8 @@ static int __init acpi_pcc_probe(void)
 	struct acpi_table_header *pcct_tbl;
 	struct acpi_subtable_header *pcct_entry;
 	struct acpi_table_pcct *acpi_pcct_tbl;
+	struct acpi_subtable_proc proc[ACPI_PCCT_TYPE_RESERVED];
 	int count, i, rc;
-	int sum = 0;
 	acpi_status status = AE_OK;
 
 	/* Search for PCCT */
@@ -459,43 +450,41 @@ static int __init acpi_pcc_probe(void)
 	if (ACPI_FAILURE(status) || !pcct_tbl)
 		return -ENODEV;
 
-	count = acpi_table_parse_entries(ACPI_SIG_PCCT,
-			sizeof(struct acpi_table_pcct),
-			ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE,
-			parse_pcc_subspace, MAX_PCC_SUBSPACES);
-	sum += (count > 0) ? count : 0;
-
-	count = acpi_table_parse_entries(ACPI_SIG_PCCT,
-			sizeof(struct acpi_table_pcct),
-			ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE_TYPE2,
-			parse_pcc_subspace, MAX_PCC_SUBSPACES);
-	sum += (count > 0) ? count : 0;
+	/* Set up the subtable handlers */
+	for (i = ACPI_PCCT_TYPE_GENERIC_SUBSPACE;
+	     i < ACPI_PCCT_TYPE_RESERVED; i++) {
+		proc[i].id = i;
+		proc[i].count = 0;
+		proc[i].handler = parse_pcc_subspace;
+	}
 
-	if (sum == 0 || sum >= MAX_PCC_SUBSPACES) {
-		pr_err("Error parsing PCC subspaces from PCCT\n");
+	count = acpi_table_parse_entries_array(ACPI_SIG_PCCT,
+			sizeof(struct acpi_table_pcct), proc,
+			ACPI_PCCT_TYPE_RESERVED, MAX_PCC_SUBSPACES);
+	if (count == 0 || count > MAX_PCC_SUBSPACES) {
+		pr_warn("Invalid PCCT: %d PCC subspaces\n", count);
 		return -EINVAL;
 	}
 
-	pcc_mbox_channels = kzalloc(sizeof(struct mbox_chan) *
-			sum, GFP_KERNEL);
+	pcc_mbox_channels = kzalloc(sizeof(struct mbox_chan) * count, GFP_KERNEL);
 	if (!pcc_mbox_channels) {
 		pr_err("Could not allocate space for PCC mbox channels\n");
 		return -ENOMEM;
 	}
 
-	pcc_doorbell_vaddr = kcalloc(sum, sizeof(void *), GFP_KERNEL);
+	pcc_doorbell_vaddr = kcalloc(count, sizeof(void *), GFP_KERNEL);
 	if (!pcc_doorbell_vaddr) {
 		rc = -ENOMEM;
 		goto err_free_mbox;
 	}
 
-	pcc_doorbell_ack_vaddr = kcalloc(sum, sizeof(void *), GFP_KERNEL);
+	pcc_doorbell_ack_vaddr = kcalloc(count, sizeof(void *), GFP_KERNEL);
 	if (!pcc_doorbell_ack_vaddr) {
 		rc = -ENOMEM;
 		goto err_free_db_vaddr;
 	}
 
-	pcc_doorbell_irq = kcalloc(sum, sizeof(int), GFP_KERNEL);
+	pcc_doorbell_irq = kcalloc(count, sizeof(int), GFP_KERNEL);
 	if (!pcc_doorbell_irq) {
 		rc = -ENOMEM;
 		goto err_free_db_ack_vaddr;
@@ -509,18 +498,24 @@ static int __init acpi_pcc_probe(void)
 	if (acpi_pcct_tbl->flags & ACPI_PCCT_DOORBELL)
 		pcc_mbox_ctrl.txdone_irq = true;
 
-	for (i = 0; i < sum; i++) {
+	for (i = 0; i < count; i++) {
 		struct acpi_generic_address *db_reg;
-		struct acpi_pcct_hw_reduced *pcct_ss;
+		struct acpi_pcct_subspace *pcct_ss;
 		pcc_mbox_channels[i].con_priv = pcct_entry;
 
-		pcct_ss = (struct acpi_pcct_hw_reduced *) pcct_entry;
+		if (pcct_entry->type == ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE ||
+		    pcct_entry->type == ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE_TYPE2) {
+			struct acpi_pcct_hw_reduced *pcct_hrss;
+
+			pcct_hrss = (struct acpi_pcct_hw_reduced *) pcct_entry;
 
-		if (pcc_mbox_ctrl.txdone_irq) {
-			rc = pcc_parse_subspace_irq(i, pcct_ss);
-			if (rc < 0)
-				goto err;
+			if (pcc_mbox_ctrl.txdone_irq) {
+				rc = pcc_parse_subspace_irq(i, pcct_hrss);
+				if (rc < 0)
+					goto err;
+			}
 		}
+		pcct_ss = (struct acpi_pcct_subspace *) pcct_entry;
 
 		/* If doorbell is in system memory cache the virt address */
 		db_reg = &pcct_ss->doorbell_register;
@@ -531,7 +526,7 @@ static int __init acpi_pcc_probe(void)
 			((unsigned long) pcct_entry + pcct_entry->length);
 	}
 
-	pcc_mbox_ctrl.num_chans = sum;
+	pcc_mbox_ctrl.num_chans = count;
 
 	pr_info("Detected %d PCC Subspaces\n", pcc_mbox_ctrl.num_chans);
 
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 004cc3cc6123..7fa2631b422c 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -290,7 +290,7 @@ do {									\
 		if (kthread_should_stop() ||				\
 		    test_bit(CACHE_SET_IO_DISABLE, &ca->set->flags)) {	\
 			set_current_state(TASK_RUNNING);		\
-			return 0;					\
+			goto out;					\
 		}							\
 									\
 		schedule();						\
@@ -378,6 +378,9 @@ retry_invalidate:
 			bch_prio_write(ca);
 		}
 	}
+out:
+	wait_for_kthread_stop();
+	return 0;
 }
 
 /* Allocation */
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d338b7086013..d6bf294f3907 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -269,7 +269,7 @@ struct bcache_device {
 	atomic_t		*stripe_sectors_dirty;
 	unsigned long		*full_dirty_stripes;
 
-	struct bio_set		*bio_split;
+	struct bio_set		bio_split;
 
 	unsigned		data_csum:1;
 
@@ -345,6 +345,7 @@ struct cached_dev {
 
 	struct keybuf		writeback_keys;
 
+	struct task_struct	*status_update_thread;
 	/*
 	 * Order the write-half of writeback operations strongly in dispatch
 	 * order.  (Maintain LBA order; don't allow reads completing out of
@@ -392,6 +393,9 @@ struct cached_dev {
 #define DEFAULT_CACHED_DEV_ERROR_LIMIT	64
 	atomic_t		io_errors;
 	unsigned		error_limit;
+	unsigned		offline_seconds;
+
+	char			backing_dev_name[BDEVNAME_SIZE];
 };
 
 enum alloc_reserve {
@@ -464,6 +468,8 @@ struct cache {
 	atomic_long_t		meta_sectors_written;
 	atomic_long_t		btree_sectors_written;
 	atomic_long_t		sectors_written;
+
+	char			cache_dev_name[BDEVNAME_SIZE];
 };
 
 struct gc_stat {
@@ -524,9 +530,9 @@ struct cache_set {
 	struct closure		sb_write;
 	struct semaphore	sb_write_mutex;
 
-	mempool_t		*search;
-	mempool_t		*bio_meta;
-	struct bio_set		*bio_split;
+	mempool_t		search;
+	mempool_t		bio_meta;
+	struct bio_set		bio_split;
 
 	/* For the btree cache */
 	struct shrinker		shrink;
@@ -651,7 +657,7 @@ struct cache_set {
 	 * A btree node on disk could have too many bsets for an iterator to fit
 	 * on the stack - have to dynamically allocate them
 	 */
-	mempool_t		*fill_iter;
+	mempool_t		fill_iter;
 
 	struct bset_sort_state	sort;
 
@@ -952,8 +958,6 @@ void bch_prio_write(struct cache *);
 void bch_write_bdev_super(struct cached_dev *, struct closure *);
 
 extern struct workqueue_struct *bcache_wq;
-extern const char * const bch_cache_modes[];
-extern const char * const bch_stop_on_failure_modes[];
 extern struct mutex bch_register_lock;
 extern struct list_head bch_cache_sets;
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 579c696a5fe0..f3403b45bc28 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -1118,8 +1118,7 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 
 void bch_bset_sort_state_free(struct bset_sort_state *state)
 {
-	if (state->pool)
-		mempool_destroy(state->pool);
+	mempool_exit(&state->pool);
 }
 
 int bch_bset_sort_state_init(struct bset_sort_state *state, unsigned page_order)
@@ -1129,11 +1128,7 @@ int bch_bset_sort_state_init(struct bset_sort_state *state, unsigned page_order)
 	state->page_order = page_order;
 	state->crit_factor = int_sqrt(1 << page_order);
 
-	state->pool = mempool_create_page_pool(1, page_order);
-	if (!state->pool)
-		return -ENOMEM;
-
-	return 0;
+	return mempool_init_page_pool(&state->pool, 1, page_order);
 }
 EXPORT_SYMBOL(bch_bset_sort_state_init);
 
@@ -1191,7 +1186,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
 
 		BUG_ON(order > state->page_order);
 
-		outp = mempool_alloc(state->pool, GFP_NOIO);
+		outp = mempool_alloc(&state->pool, GFP_NOIO);
 		out = page_address(outp);
 		used_mempool = true;
 		order = state->page_order;
@@ -1220,7 +1215,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
 	}
 
 	if (used_mempool)
-		mempool_free(virt_to_page(out), state->pool);
+		mempool_free(virt_to_page(out), &state->pool);
 	else
 		free_pages((unsigned long) out, order);
 
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index 0c24280f3b98..b867f2200495 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -347,7 +347,7 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
 /* Sorting */
 
 struct bset_sort_state {
-	mempool_t		*pool;
+	mempool_t		pool;
 
 	unsigned		page_order;
 	unsigned		crit_factor;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 17936b2dc7d6..2a0968c04e21 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -204,7 +204,7 @@ void bch_btree_node_read_done(struct btree *b)
 	struct bset *i = btree_bset_first(b);
 	struct btree_iter *iter;
 
-	iter = mempool_alloc(b->c->fill_iter, GFP_NOIO);
+	iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
 	iter->size = b->c->sb.bucket_size / b->c->sb.block_size;
 	iter->used = 0;
 
@@ -271,7 +271,7 @@ void bch_btree_node_read_done(struct btree *b)
 		bch_bset_init_next(&b->keys, write_block(b),
 				   bset_magic(&b->c->sb));
 out:
-	mempool_free(iter, b->c->fill_iter);
+	mempool_free(iter, &b->c->fill_iter);
 	return;
 err:
 	set_btree_node_io_error(b);
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 028f7b386e01..d030ce3025a6 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -106,7 +106,6 @@ void bch_btree_verify(struct btree *b)
 
 void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 {
-	char name[BDEVNAME_SIZE];
 	struct bio *check;
 	struct bio_vec bv, cbv;
 	struct bvec_iter iter, citer = { 0 };
@@ -134,7 +133,7 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 					bv.bv_len),
 				 dc->disk.c,
 				 "verify failed at dev %s sector %llu",
-				 bdevname(dc->bdev, name),
+				 dc->backing_dev_name,
 				 (uint64_t) bio->bi_iter.bi_sector);
 
 		kunmap_atomic(p1);
@@ -251,7 +250,9 @@ void bch_debug_exit(void)
 
 int __init bch_debug_init(struct kobject *kobj)
 {
-	bcache_debug = debugfs_create_dir("bcache", NULL);
+	if (!IS_ENABLED(CONFIG_DEBUG_FS))
+		return 0;
 
+	bcache_debug = debugfs_create_dir("bcache", NULL);
 	return IS_ERR_OR_NULL(bcache_debug);
 }
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 7fac97ae036e..9612873afee2 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -17,12 +17,12 @@
 void bch_bbio_free(struct bio *bio, struct cache_set *c)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
-	mempool_free(b, c->bio_meta);
+	mempool_free(b, &c->bio_meta);
 }
 
 struct bio *bch_bbio_alloc(struct cache_set *c)
 {
-	struct bbio *b = mempool_alloc(c->bio_meta, GFP_NOIO);
+	struct bbio *b = mempool_alloc(&c->bio_meta, GFP_NOIO);
 	struct bio *bio = &b->bio;
 
 	bio_init(bio, bio->bi_inline_vecs, bucket_pages(c));
@@ -52,7 +52,6 @@ void bch_submit_bbio(struct bio *bio, struct cache_set *c,
 /* IO errors */
 void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
 {
-	char buf[BDEVNAME_SIZE];
 	unsigned errors;
 
 	WARN_ONCE(!dc, "NULL pointer of struct cached_dev");
@@ -60,7 +59,7 @@ void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
 	errors = atomic_add_return(1, &dc->io_errors);
 	if (errors < dc->error_limit)
 		pr_err("%s: IO error on backing device, unrecoverable",
-			bio_devname(bio, buf));
+			dc->backing_dev_name);
 	else
 		bch_cached_dev_error(dc);
 }
@@ -105,19 +104,18 @@ void bch_count_io_errors(struct cache *ca,
 	}
 
 	if (error) {
-		char buf[BDEVNAME_SIZE];
 		unsigned errors = atomic_add_return(1 << IO_ERROR_SHIFT,
 						    &ca->io_errors);
 		errors >>= IO_ERROR_SHIFT;
 
 		if (errors < ca->set->error_limit)
 			pr_err("%s: IO error on %s%s",
-			       bdevname(ca->bdev, buf), m,
+			       ca->cache_dev_name, m,
 			       is_read ? ", recovering." : ".");
 		else
 			bch_cache_set_error(ca->set,
 					    "%s: too many IO errors %s",
-					    bdevname(ca->bdev, buf), m);
+					    ca->cache_dev_name, m);
 	}
 }
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index a65e3365eeb9..ae67f5fa8047 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -213,7 +213,7 @@ static void bch_data_insert_start(struct closure *cl)
 	do {
 		unsigned i;
 		struct bkey *k;
-		struct bio_set *split = op->c->bio_split;
+		struct bio_set *split = &op->c->bio_split;
 
 		/* 1 for the device pointer and 1 for the chksum */
 		if (bch_keylist_realloc(&op->insert_keys,
@@ -548,7 +548,7 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 
 	n = bio_next_split(bio, min_t(uint64_t, INT_MAX,
 				      KEY_OFFSET(k) - bio->bi_iter.bi_sector),
-			   GFP_NOIO, s->d->bio_split);
+			   GFP_NOIO, &s->d->bio_split);
 
 	bio_key = &container_of(n, struct bbio, bio)->key;
 	bch_bkey_copy_single_ptr(bio_key, k, ptr);
@@ -649,11 +649,8 @@ static void backing_request_endio(struct bio *bio)
 		 */
 		if (unlikely(s->iop.writeback &&
 			     bio->bi_opf & REQ_PREFLUSH)) {
-			char buf[BDEVNAME_SIZE];
-
-			bio_devname(bio, buf);
 			pr_err("Can't flush %s: returned bi_status %i",
-				buf, bio->bi_status);
+				dc->backing_dev_name, bio->bi_status);
 		} else {
 			/* set to orig_bio->bi_status in bio_complete() */
 			s->iop.status = bio->bi_status;
@@ -710,7 +707,7 @@ static void search_free(struct closure *cl)
 
 	bio_complete(s);
 	closure_debug_destroy(cl);
-	mempool_free(s, s->d->c->search);
+	mempool_free(s, &s->d->c->search);
 }
 
 static inline struct search *search_alloc(struct bio *bio,
@@ -718,7 +715,7 @@ static inline struct search *search_alloc(struct bio *bio,
 {
 	struct search *s;
 
-	s = mempool_alloc(d->c->search, GFP_NOIO);
+	s = mempool_alloc(&d->c->search, GFP_NOIO);
 
 	closure_init(&s->cl, NULL);
 	do_bio_hook(s, bio, request_endio);
@@ -867,7 +864,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	s->cache_missed = 1;
 
 	if (s->cache_miss || s->iop.bypass) {
-		miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+		miss = bio_next_split(bio, sectors, GFP_NOIO, &s->d->bio_split);
 		ret = miss == bio ? MAP_DONE : MAP_CONTINUE;
 		goto out_submit;
 	}
@@ -890,14 +887,14 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 
 	s->iop.replace = true;
 
-	miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+	miss = bio_next_split(bio, sectors, GFP_NOIO, &s->d->bio_split);
 
 	/* btree_search_recurse()'s btree iterator is no good anymore */
 	ret = miss == bio ? MAP_DONE : -EINTR;
 
 	cache_bio = bio_alloc_bioset(GFP_NOWAIT,
 			DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS),
-			dc->disk.bio_split);
+			&dc->disk.bio_split);
 	if (!cache_bio)
 		goto out_submit;
 
@@ -1011,7 +1008,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 			struct bio *flush;
 
 			flush = bio_alloc_bioset(GFP_NOIO, 0,
-						 dc->disk.bio_split);
+						 &dc->disk.bio_split);
 			if (!flush) {
 				s->iop.status = BLK_STS_RESOURCE;
 				goto insert_data;
@@ -1024,7 +1021,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 			closure_bio_submit(s->iop.c, flush, cl);
 		}
 	} else {
-		s->iop.bio = bio_clone_fast(bio, GFP_NOIO, dc->disk.bio_split);
+		s->iop.bio = bio_clone_fast(bio, GFP_NOIO, &dc->disk.bio_split);
 		/* I/O request sent to backing device */
 		bio->bi_end_io = backing_request_endio;
 		closure_bio_submit(s->iop.c, bio, cl);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index d90d9e59ca00..a31e55bcc4e5 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -37,24 +37,6 @@ static const char invalid_uuid[] = {
 	0xc8, 0x50, 0xfc, 0x5e, 0xcb, 0x16, 0xcd, 0x99
 };
 
-/* Default is -1; we skip past it for struct cached_dev's cache mode */
-const char * const bch_cache_modes[] = {
-	"default",
-	"writethrough",
-	"writeback",
-	"writearound",
-	"none",
-	NULL
-};
-
-/* Default is -1; we skip past it for stop_when_cache_set_failed */
-const char * const bch_stop_on_failure_modes[] = {
-	"default",
-	"auto",
-	"always",
-	NULL
-};
-
 static struct kobject *bcache_kobj;
 struct mutex bch_register_lock;
 LIST_HEAD(bch_cache_sets);
@@ -654,6 +636,11 @@ static int ioctl_dev(struct block_device *b, fmode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct bcache_device *d = b->bd_disk->private_data;
+	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+
+	if (dc->io_disable)
+		return -EIO;
+
 	return d->ioctl(d, mode, cmd, arg);
 }
 
@@ -766,8 +753,7 @@ static void bcache_device_free(struct bcache_device *d)
 		put_disk(d->disk);
 	}
 
-	if (d->bio_split)
-		bioset_free(d->bio_split);
+	bioset_exit(&d->bio_split);
 	kvfree(d->full_dirty_stripes);
 	kvfree(d->stripe_sectors_dirty);
 
@@ -809,9 +795,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	if (idx < 0)
 		return idx;
 
-	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio),
-					   BIOSET_NEED_BVECS |
-					   BIOSET_NEED_RESCUER)) ||
+	if (bioset_init(&d->bio_split, 4, offsetof(struct bbio, bio),
+			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
 	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
 		ida_simple_remove(&bcache_device_idx, idx);
 		return -ENOMEM;
@@ -864,6 +849,44 @@ static void calc_cached_dev_sectors(struct cache_set *c)
 	c->cached_dev_sectors = sectors;
 }
 
+#define BACKING_DEV_OFFLINE_TIMEOUT 5
+static int cached_dev_status_update(void *arg)
+{
+	struct cached_dev *dc = arg;
+	struct request_queue *q;
+
+	/*
+	 * If this delayed worker is stopping outside, directly quit here.
+	 * dc->io_disable might be set via sysfs interface, so check it
+	 * here too.
+	 */
+	while (!kthread_should_stop() && !dc->io_disable) {
+		q = bdev_get_queue(dc->bdev);
+		if (blk_queue_dying(q))
+			dc->offline_seconds++;
+		else
+			dc->offline_seconds = 0;
+
+		if (dc->offline_seconds >= BACKING_DEV_OFFLINE_TIMEOUT) {
+			pr_err("%s: device offline for %d seconds",
+			       dc->backing_dev_name,
+			       BACKING_DEV_OFFLINE_TIMEOUT);
+			pr_err("%s: disable I/O request due to backing "
+			       "device offline", dc->disk.name);
+			dc->io_disable = true;
+			/* let others know earlier that io_disable is true */
+			smp_mb();
+			bcache_device_stop(&dc->disk);
+			break;
+		}
+		schedule_timeout_interruptible(HZ);
+	}
+
+	wait_for_kthread_stop();
+	return 0;
+}
+
+
 void bch_cached_dev_run(struct cached_dev *dc)
 {
 	struct bcache_device *d = &dc->disk;
@@ -906,6 +929,14 @@ void bch_cached_dev_run(struct cached_dev *dc)
 	if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
 	    sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache"))
 		pr_debug("error creating sysfs link");
+
+	dc->status_update_thread = kthread_run(cached_dev_status_update,
+					       dc, "bcache_status_update");
+	if (IS_ERR(dc->status_update_thread)) {
+		pr_warn("failed to create bcache_status_update kthread, "
+			"continue to run without monitoring backing "
+			"device status");
+	}
 }
 
 /*
@@ -936,7 +967,6 @@ static void cancel_writeback_rate_update_dwork(struct cached_dev *dc)
 static void cached_dev_detach_finish(struct work_struct *w)
 {
 	struct cached_dev *dc = container_of(w, struct cached_dev, detach);
-	char buf[BDEVNAME_SIZE];
 	struct closure cl;
 	closure_init_stack(&cl);
 
@@ -967,7 +997,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
 
 	mutex_unlock(&bch_register_lock);
 
-	pr_info("Caching disabled for %s", bdevname(dc->bdev, buf));
+	pr_info("Caching disabled for %s", dc->backing_dev_name);
 
 	/* Drop ref we took in cached_dev_detach() */
 	closure_put(&dc->disk.cl);
@@ -999,29 +1029,28 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 {
 	uint32_t rtime = cpu_to_le32(get_seconds());
 	struct uuid_entry *u;
-	char buf[BDEVNAME_SIZE];
 	struct cached_dev *exist_dc, *t;
 
-	bdevname(dc->bdev, buf);
-
 	if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
 	    (!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
 		return -ENOENT;
 
 	if (dc->disk.c) {
-		pr_err("Can't attach %s: already attached", buf);
+		pr_err("Can't attach %s: already attached",
+		       dc->backing_dev_name);
 		return -EINVAL;
 	}
 
 	if (test_bit(CACHE_SET_STOPPING, &c->flags)) {
-		pr_err("Can't attach %s: shutting down", buf);
+		pr_err("Can't attach %s: shutting down",
+		       dc->backing_dev_name);
 		return -EINVAL;
 	}
 
 	if (dc->sb.block_size < c->sb.block_size) {
 		/* Will die */
 		pr_err("Couldn't attach %s: block size less than set's block size",
-		       buf);
+		       dc->backing_dev_name);
 		return -EINVAL;
 	}
 
@@ -1029,7 +1058,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) {
 		if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) {
 			pr_err("Tried to attach %s but duplicate UUID already attached",
-				buf);
+				dc->backing_dev_name);
 
 			return -EINVAL;
 		}
@@ -1047,13 +1076,15 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 
 	if (!u) {
 		if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
-			pr_err("Couldn't find uuid for %s in set", buf);
+			pr_err("Couldn't find uuid for %s in set",
+			       dc->backing_dev_name);
 			return -ENOENT;
 		}
 
 		u = uuid_find_empty(c);
 		if (!u) {
-			pr_err("Not caching %s, no room for UUID", buf);
+			pr_err("Not caching %s, no room for UUID",
+			       dc->backing_dev_name);
 			return -EINVAL;
 		}
 	}
@@ -1112,7 +1143,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	up_write(&dc->writeback_lock);
 
 	pr_info("Caching %s as %s on set %pU",
-		bdevname(dc->bdev, buf), dc->disk.disk->disk_name,
+		dc->backing_dev_name,
+		dc->disk.disk->disk_name,
 		dc->disk.c->sb.set_uuid);
 	return 0;
 }
@@ -1138,6 +1170,8 @@ static void cached_dev_free(struct closure *cl)
 		kthread_stop(dc->writeback_thread);
 	if (dc->writeback_write_wq)
 		destroy_workqueue(dc->writeback_write_wq);
+	if (!IS_ERR_OR_NULL(dc->status_update_thread))
+		kthread_stop(dc->status_update_thread);
 
 	if (atomic_read(&dc->running))
 		bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
@@ -1225,10 +1259,10 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 				 struct block_device *bdev,
 				 struct cached_dev *dc)
 {
-	char name[BDEVNAME_SIZE];
 	const char *err = "cannot allocate memory";
 	struct cache_set *c;
 
+	bdevname(bdev, dc->backing_dev_name);
 	memcpy(&dc->sb, sb, sizeof(struct cache_sb));
 	dc->bdev = bdev;
 	dc->bdev->bd_holder = dc;
@@ -1237,6 +1271,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 	bio_first_bvec_all(&dc->sb_bio)->bv_page = sb_page;
 	get_page(sb_page);
 
+
 	if (cached_dev_init(dc, sb->block_size << 9))
 		goto err;
 
@@ -1247,7 +1282,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 	if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
 		goto err;
 
-	pr_info("registered backing device %s", bdevname(bdev, name));
+	pr_info("registered backing device %s", dc->backing_dev_name);
 
 	list_add(&dc->list, &uncached_devices);
 	list_for_each_entry(c, &bch_cache_sets, list)
@@ -1259,7 +1294,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 
 	return;
 err:
-	pr_notice("error %s: %s", bdevname(bdev, name), err);
+	pr_notice("error %s: %s", dc->backing_dev_name, err);
 	bcache_device_stop(&dc->disk);
 }
 
@@ -1367,7 +1402,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size)
 
 bool bch_cached_dev_error(struct cached_dev *dc)
 {
-	char name[BDEVNAME_SIZE];
+	struct cache_set *c;
 
 	if (!dc || test_bit(BCACHE_DEV_CLOSING, &dc->disk.flags))
 		return false;
@@ -1377,7 +1412,22 @@ bool bch_cached_dev_error(struct cached_dev *dc)
 	smp_mb();
 
 	pr_err("stop %s: too many IO errors on backing device %s\n",
-		dc->disk.disk->disk_name, bdevname(dc->bdev, name));
+		dc->disk.disk->disk_name, dc->backing_dev_name);
+
+	/*
+	 * If the cached device is still attached to a cache set,
+	 * even dc->io_disable is true and no more I/O requests
+	 * accepted, cache device internal I/O (writeback scan or
+	 * garbage collection) may still prevent bcache device from
+	 * being stopped. So here CACHE_SET_IO_DISABLE should be
+	 * set to c->flags too, to make the internal I/O to cache
+	 * device rejected and stopped immediately.
+	 * If c is NULL, that means the bcache device is not attached
+	 * to any cache set, then no CACHE_SET_IO_DISABLE bit to set.
+	 */
+	c = dc->disk.c;
+	if (c && test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
+		pr_info("CACHE_SET_IO_DISABLE already set");
 
 	bcache_device_stop(&dc->disk);
 	return true;
@@ -1395,7 +1445,7 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
 		return false;
 
 	if (test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
-		pr_warn("CACHE_SET_IO_DISABLE already set");
+		pr_info("CACHE_SET_IO_DISABLE already set");
 
 	/* XXX: we can be called from atomic context
 	acquire_console_sem();
@@ -1448,14 +1498,10 @@ static void cache_set_free(struct closure *cl)
 
 	if (c->moving_gc_wq)
 		destroy_workqueue(c->moving_gc_wq);
-	if (c->bio_split)
-		bioset_free(c->bio_split);
-	if (c->fill_iter)
-		mempool_destroy(c->fill_iter);
-	if (c->bio_meta)
-		mempool_destroy(c->bio_meta);
-	if (c->search)
-		mempool_destroy(c->search);
+	bioset_exit(&c->bio_split);
+	mempool_exit(&c->fill_iter);
+	mempool_exit(&c->bio_meta);
+	mempool_exit(&c->search);
 	kfree(c->devices);
 
 	mutex_lock(&bch_register_lock);
@@ -1539,6 +1585,20 @@ static void conditional_stop_bcache_device(struct cache_set *c,
 		 */
 		pr_warn("stop_when_cache_set_failed of %s is \"auto\" and cache is dirty, stop it to avoid potential data corruption.",
 			d->disk->disk_name);
+			/*
+			 * There might be a small time gap that cache set is
+			 * released but bcache device is not. Inside this time
+			 * gap, regular I/O requests will directly go into
+			 * backing device as no cache set attached to. This
+			 * behavior may also introduce potential inconsistence
+			 * data in writeback mode while cache is dirty.
+			 * Therefore before calling bcache_device_stop() due
+			 * to a broken cache device, dc->io_disable should be
+			 * explicitly set to true.
+			 */
+			dc->io_disable = true;
+			/* make others know io_disable is true earlier */
+			smp_mb();
 			bcache_device_stop(d);
 	} else {
 		/*
@@ -1652,21 +1712,17 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	INIT_LIST_HEAD(&c->btree_cache_freed);
 	INIT_LIST_HEAD(&c->data_buckets);
 
-	c->search = mempool_create_slab_pool(32, bch_search_cache);
-	if (!c->search)
-		goto err;
-
 	iter_size = (sb->bucket_size / sb->block_size + 1) *
 		sizeof(struct btree_iter_set);
 
 	if (!(c->devices = kzalloc(c->nr_uuids * sizeof(void *), GFP_KERNEL)) ||
-	    !(c->bio_meta = mempool_create_kmalloc_pool(2,
-				sizeof(struct bbio) + sizeof(struct bio_vec) *
-				bucket_pages(c))) ||
-	    !(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
-	    !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio),
-					   BIOSET_NEED_BVECS |
-					   BIOSET_NEED_RESCUER)) ||
+	    mempool_init_slab_pool(&c->search, 32, bch_search_cache) ||
+	    mempool_init_kmalloc_pool(&c->bio_meta, 2,
+				      sizeof(struct bbio) + sizeof(struct bio_vec) *
+				      bucket_pages(c)) ||
+	    mempool_init_kmalloc_pool(&c->fill_iter, 1, iter_size) ||
+	    bioset_init(&c->bio_split, 4, offsetof(struct bbio, bio),
+			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
 	    !(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
 	    !(c->moving_gc_wq = alloc_workqueue("bcache_gc",
 						WQ_MEM_RECLAIM, 0)) ||
@@ -2003,12 +2059,10 @@ static int cache_alloc(struct cache *ca)
 static int register_cache(struct cache_sb *sb, struct page *sb_page,
 				struct block_device *bdev, struct cache *ca)
 {
-	char name[BDEVNAME_SIZE];
 	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
-	bdevname(bdev, name);
-
+	bdevname(bdev, ca->cache_dev_name);
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
 	ca->bdev = bdev;
 	ca->bdev->bd_holder = ca;
@@ -2045,14 +2099,14 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 		goto out;
 	}
 
-	pr_info("registered cache device %s", name);
+	pr_info("registered cache device %s", ca->cache_dev_name);
 
 out:
 	kobject_put(&ca->kobj);
 
 err:
 	if (err)
-		pr_notice("error %s: %s", name, err);
+		pr_notice("error %s: %s", ca->cache_dev_name, err);
 
 	return ret;
 }
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index dfeef583ee50..8ccbc8f3b3af 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -16,6 +16,22 @@
 #include <linux/sort.h>
 #include <linux/sched/clock.h>
 
+/* Default is -1; we skip past it for struct cached_dev's cache mode */
+static const char * const bch_cache_modes[] = {
+	"writethrough",
+	"writeback",
+	"writearound",
+	"none",
+	NULL
+};
+
+/* Default is -1; we skip past it for stop_when_cache_set_failed */
+static const char * const bch_stop_on_failure_modes[] = {
+	"auto",
+	"always",
+	NULL
+};
+
 static const char * const cache_replacement_policies[] = {
 	"lru",
 	"fifo",
@@ -114,6 +130,20 @@ rw_attribute(btree_shrinker_disabled);
 rw_attribute(copy_gc_enabled);
 rw_attribute(size);
 
+static ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
+			    size_t selected)
+{
+	char *out = buf;
+	size_t i;
+
+	for (i = 0; list[i]; i++)
+		out += snprintf(out, buf + size - out,
+				i == selected ? "[%s] " : "%s ", list[i]);
+
+	out[-1] = '\n';
+	return out - buf;
+}
+
 SHOW(__bch_cached_dev)
 {
 	struct cached_dev *dc = container_of(kobj, struct cached_dev,
@@ -124,12 +154,12 @@ SHOW(__bch_cached_dev)
 
 	if (attr == &sysfs_cache_mode)
 		return bch_snprint_string_list(buf, PAGE_SIZE,
-					       bch_cache_modes + 1,
+					       bch_cache_modes,
 					       BDEV_CACHE_MODE(&dc->sb));
 
 	if (attr == &sysfs_stop_when_cache_set_failed)
 		return bch_snprint_string_list(buf, PAGE_SIZE,
-					       bch_stop_on_failure_modes + 1,
+					       bch_stop_on_failure_modes,
 					       dc->stop_when_cache_set_failed);
 
 
@@ -253,8 +283,7 @@ STORE(__cached_dev)
 		bch_cached_dev_run(dc);
 
 	if (attr == &sysfs_cache_mode) {
-		v = bch_read_string_list(buf, bch_cache_modes + 1);
-
+		v = __sysfs_match_string(bch_cache_modes, -1, buf);
 		if (v < 0)
 			return v;
 
@@ -265,8 +294,7 @@ STORE(__cached_dev)
 	}
 
 	if (attr == &sysfs_stop_when_cache_set_failed) {
-		v = bch_read_string_list(buf, bch_stop_on_failure_modes + 1);
-
+		v = __sysfs_match_string(bch_stop_on_failure_modes, -1, buf);
 		if (v < 0)
 			return v;
 
@@ -635,6 +663,7 @@ SHOW_LOCKED(bch_cache_set)
 STORE(__bch_cache_set)
 {
 	struct cache_set *c = container_of(kobj, struct cache_set, kobj);
+	ssize_t v;
 
 	if (attr == &sysfs_unregister)
 		bch_cache_set_unregister(c);
@@ -698,8 +727,7 @@ STORE(__bch_cache_set)
 		      c->congested_write_threshold_us);
 
 	if (attr == &sysfs_errors) {
-		ssize_t v = bch_read_string_list(buf, error_actions);
-
+		v = __sysfs_match_string(error_actions, -1, buf);
 		if (v < 0)
 			return v;
 
@@ -714,8 +742,7 @@ STORE(__bch_cache_set)
 		c->error_decay = strtoul_or_return(buf) / 88;
 
 	if (attr == &sysfs_io_disable) {
-		int v = strtoul_or_return(buf);
-
+		v = strtoul_or_return(buf);
 		if (v) {
 			if (test_and_set_bit(CACHE_SET_IO_DISABLE,
 					     &c->flags))
@@ -929,6 +956,7 @@ SHOW_LOCKED(bch_cache)
 STORE(__bch_cache)
 {
 	struct cache *ca = container_of(kobj, struct cache, kobj);
+	ssize_t v;
 
 	if (attr == &sysfs_discard) {
 		bool v = strtoul_or_return(buf);
@@ -943,8 +971,7 @@ STORE(__bch_cache)
 	}
 
 	if (attr == &sysfs_cache_replacement_policy) {
-		ssize_t v = bch_read_string_list(buf, cache_replacement_policies);
-
+		v = __sysfs_match_string(cache_replacement_policies, -1, buf);
 		if (v < 0)
 			return v;
 
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index 74febd5230df..fc479b026d6d 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -120,41 +120,6 @@ ssize_t bch_hprint(char *buf, int64_t v)
 		return sprintf(buf, "%llu.%i%c", q, t * 10 / 1024, units[u]);
 }
 
-ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
-			    size_t selected)
-{
-	char *out = buf;
-	size_t i;
-
-	for (i = 0; list[i]; i++)
-		out += snprintf(out, buf + size - out,
-				i == selected ? "[%s] " : "%s ", list[i]);
-
-	out[-1] = '\n';
-	return out - buf;
-}
-
-ssize_t bch_read_string_list(const char *buf, const char * const list[])
-{
-	size_t i;
-	char *s, *d = kstrndup(buf, PAGE_SIZE - 1, GFP_KERNEL);
-	if (!d)
-		return -ENOMEM;
-
-	s = strim(d);
-
-	for (i = 0; list[i]; i++)
-		if (!strcmp(list[i], s))
-			break;
-
-	kfree(d);
-
-	if (!list[i])
-		return -EINVAL;
-
-	return i;
-}
-
 bool bch_is_zero(const char *p, size_t n)
 {
 	size_t i;
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 268024529edd..cced87f8eb27 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -365,11 +365,6 @@ ssize_t bch_hprint(char *buf, int64_t v);
 bool bch_is_zero(const char *p, size_t n);
 int bch_parse_uuid(const char *s, char *uuid);
 
-ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
-			    size_t selected);
-
-ssize_t bch_read_string_list(const char *buf, const char * const list[]);
-
 struct time_stats {
 	spinlock_t	lock;
 	/*
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 4a9547cdcdc5..ad45ebe1a74b 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -244,8 +244,10 @@ static void dirty_endio(struct bio *bio)
 	struct keybuf_key *w = bio->bi_private;
 	struct dirty_io *io = w->private;
 
-	if (bio->bi_status)
+	if (bio->bi_status) {
 		SET_KEY_DIRTY(&w->key, false);
+		bch_count_backing_io_errors(io->dc, bio);
+	}
 
 	closure_put(&io->cl);
 }
diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index 874841f0fc83..e794e3662fdd 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -19,7 +19,7 @@
 
 struct dm_bio_prison {
 	spinlock_t lock;
-	mempool_t *cell_pool;
+	mempool_t cell_pool;
 	struct rb_root cells;
 };
 
@@ -33,15 +33,16 @@ static struct kmem_cache *_cell_cache;
  */
 struct dm_bio_prison *dm_bio_prison_create(void)
 {
-	struct dm_bio_prison *prison = kmalloc(sizeof(*prison), GFP_KERNEL);
+	struct dm_bio_prison *prison = kzalloc(sizeof(*prison), GFP_KERNEL);
+	int ret;
 
 	if (!prison)
 		return NULL;
 
 	spin_lock_init(&prison->lock);
 
-	prison->cell_pool = mempool_create_slab_pool(MIN_CELLS, _cell_cache);
-	if (!prison->cell_pool) {
+	ret = mempool_init_slab_pool(&prison->cell_pool, MIN_CELLS, _cell_cache);
+	if (ret) {
 		kfree(prison);
 		return NULL;
 	}
@@ -54,21 +55,21 @@ EXPORT_SYMBOL_GPL(dm_bio_prison_create);
 
 void dm_bio_prison_destroy(struct dm_bio_prison *prison)
 {
-	mempool_destroy(prison->cell_pool);
+	mempool_exit(&prison->cell_pool);
 	kfree(prison);
 }
 EXPORT_SYMBOL_GPL(dm_bio_prison_destroy);
 
 struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison, gfp_t gfp)
 {
-	return mempool_alloc(prison->cell_pool, gfp);
+	return mempool_alloc(&prison->cell_pool, gfp);
 }
 EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell);
 
 void dm_bio_prison_free_cell(struct dm_bio_prison *prison,
 			     struct dm_bio_prison_cell *cell)
 {
-	mempool_free(cell, prison->cell_pool);
+	mempool_free(cell, &prison->cell_pool);
 }
 EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell);
 
diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c
index 8ce3a1a588cf..f866bc97b032 100644
--- a/drivers/md/dm-bio-prison-v2.c
+++ b/drivers/md/dm-bio-prison-v2.c
@@ -21,7 +21,7 @@ struct dm_bio_prison_v2 {
 	struct workqueue_struct *wq;
 
 	spinlock_t lock;
-	mempool_t *cell_pool;
+	mempool_t cell_pool;
 	struct rb_root cells;
 };
 
@@ -35,7 +35,8 @@ static struct kmem_cache *_cell_cache;
  */
 struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq)
 {
-	struct dm_bio_prison_v2 *prison = kmalloc(sizeof(*prison), GFP_KERNEL);
+	struct dm_bio_prison_v2 *prison = kzalloc(sizeof(*prison), GFP_KERNEL);
+	int ret;
 
 	if (!prison)
 		return NULL;
@@ -43,8 +44,8 @@ struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq)
 	prison->wq = wq;
 	spin_lock_init(&prison->lock);
 
-	prison->cell_pool = mempool_create_slab_pool(MIN_CELLS, _cell_cache);
-	if (!prison->cell_pool) {
+	ret = mempool_init_slab_pool(&prison->cell_pool, MIN_CELLS, _cell_cache);
+	if (ret) {
 		kfree(prison);
 		return NULL;
 	}
@@ -57,21 +58,21 @@ EXPORT_SYMBOL_GPL(dm_bio_prison_create_v2);
 
 void dm_bio_prison_destroy_v2(struct dm_bio_prison_v2 *prison)
 {
-	mempool_destroy(prison->cell_pool);
+	mempool_exit(&prison->cell_pool);
 	kfree(prison);
 }
 EXPORT_SYMBOL_GPL(dm_bio_prison_destroy_v2);
 
 struct dm_bio_prison_cell_v2 *dm_bio_prison_alloc_cell_v2(struct dm_bio_prison_v2 *prison, gfp_t gfp)
 {
-	return mempool_alloc(prison->cell_pool, gfp);
+	return mempool_alloc(&prison->cell_pool, gfp);
 }
 EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell_v2);
 
 void dm_bio_prison_free_cell_v2(struct dm_bio_prison_v2 *prison,
 				struct dm_bio_prison_cell_v2 *cell)
 {
-	mempool_free(cell, prison->cell_pool);
+	mempool_free(cell, &prison->cell_pool);
 }
 EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell_v2);
 
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 12aa9ca21d8c..dc385b70e4c3 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1681,8 +1681,9 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 
 	if (block_size <= KMALLOC_MAX_SIZE &&
 	    (block_size < PAGE_SIZE || !is_power_of_2(block_size))) {
-		snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", c->block_size);
-		c->slab_cache = kmem_cache_create(slab_name, c->block_size, ARCH_KMALLOC_MINALIGN,
+		unsigned align = min(1U << __ffs(block_size), (unsigned)PAGE_SIZE);
+		snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", block_size);
+		c->slab_cache = kmem_cache_create(slab_name, block_size, align,
 						  SLAB_RECLAIM_ACCOUNT, NULL);
 		if (!c->slab_cache) {
 			r = -ENOMEM;
diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c
index 1d0af0a21fc7..84814e819e4c 100644
--- a/drivers/md/dm-cache-background-tracker.c
+++ b/drivers/md/dm-cache-background-tracker.c
@@ -166,7 +166,7 @@ static bool max_work_reached(struct background_tracker *b)
 		atomic_read(&b->pending_demotes) >= b->max_work;
 }
 
-struct bt_work *alloc_work(struct background_tracker *b)
+static struct bt_work *alloc_work(struct background_tracker *b)
 {
 	if (max_work_reached(b))
 		return NULL;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index da208638fba4..001c71248246 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -447,9 +447,9 @@ struct cache {
 	struct work_struct migration_worker;
 	struct delayed_work waker;
 	struct dm_bio_prison_v2 *prison;
-	struct bio_set *bs;
+	struct bio_set bs;
 
-	mempool_t *migration_pool;
+	mempool_t migration_pool;
 
 	struct dm_cache_policy *policy;
 	unsigned policy_nr_args;
@@ -550,7 +550,7 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache)
 {
 	struct dm_cache_migration *mg;
 
-	mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT);
+	mg = mempool_alloc(&cache->migration_pool, GFP_NOWAIT);
 	if (!mg)
 		return NULL;
 
@@ -569,7 +569,7 @@ static void free_migration(struct dm_cache_migration *mg)
 	if (atomic_dec_and_test(&cache->nr_allocated_migrations))
 		wake_up(&cache->migration_wait);
 
-	mempool_free(mg, cache->migration_pool);
+	mempool_free(mg, &cache->migration_pool);
 }
 
 /*----------------------------------------------------------------*/
@@ -924,7 +924,7 @@ static void issue_op(struct bio *bio, void *context)
 static void remap_to_origin_and_cache(struct cache *cache, struct bio *bio,
 				      dm_oblock_t oblock, dm_cblock_t cblock)
 {
-	struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, cache->bs);
+	struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, &cache->bs);
 
 	BUG_ON(!origin_bio);
 
@@ -2011,7 +2011,7 @@ static void destroy(struct cache *cache)
 {
 	unsigned i;
 
-	mempool_destroy(cache->migration_pool);
+	mempool_exit(&cache->migration_pool);
 
 	if (cache->prison)
 		dm_bio_prison_destroy_v2(cache->prison);
@@ -2047,8 +2047,7 @@ static void destroy(struct cache *cache)
 		kfree(cache->ctr_args[i]);
 	kfree(cache->ctr_args);
 
-	if (cache->bs)
-		bioset_free(cache->bs);
+	bioset_exit(&cache->bs);
 
 	kfree(cache);
 }
@@ -2498,8 +2497,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	cache->features = ca->features;
 	if (writethrough_mode(cache)) {
 		/* Create bioset for writethrough bios issued to origin */
-		cache->bs = bioset_create(BIO_POOL_SIZE, 0, 0);
-		if (!cache->bs)
+		r = bioset_init(&cache->bs, BIO_POOL_SIZE, 0, 0);
+		if (r)
 			goto bad;
 	}
 
@@ -2630,9 +2629,9 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 		goto bad;
 	}
 
-	cache->migration_pool = mempool_create_slab_pool(MIGRATION_POOL_SIZE,
-							 migration_cache);
-	if (!cache->migration_pool) {
+	r = mempool_init_slab_pool(&cache->migration_pool, MIGRATION_POOL_SIZE,
+				   migration_cache);
+	if (r) {
 		*error = "Error creating cache's migration mempool";
 		goto bad;
 	}
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 3222e21cbbf8..f21c5d21bf1b 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -91,8 +91,8 @@ struct mapped_device {
 	/*
 	 * io objects are allocated from here.
 	 */
-	struct bio_set *io_bs;
-	struct bio_set *bs;
+	struct bio_set io_bs;
+	struct bio_set bs;
 
 	/*
 	 * freeze/thaw support require holding onto a super block
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 44ff473dab3e..da02f4d8e4b9 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -143,14 +143,14 @@ struct crypt_config {
 	 * pool for per bio private data, crypto requests,
 	 * encryption requeusts/buffer pages and integrity tags
 	 */
-	mempool_t *req_pool;
-	mempool_t *page_pool;
-	mempool_t *tag_pool;
+	mempool_t req_pool;
+	mempool_t page_pool;
+	mempool_t tag_pool;
 	unsigned tag_pool_max_sectors;
 
 	struct percpu_counter n_allocated_pages;
 
-	struct bio_set *bs;
+	struct bio_set bs;
 	struct mutex bio_alloc_lock;
 
 	struct workqueue_struct *io_queue;
@@ -1245,7 +1245,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc,
 	unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
 
 	if (!ctx->r.req)
-		ctx->r.req = mempool_alloc(cc->req_pool, GFP_NOIO);
+		ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO);
 
 	skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]);
 
@@ -1262,7 +1262,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc,
 				 struct convert_context *ctx)
 {
 	if (!ctx->r.req_aead)
-		ctx->r.req_aead = mempool_alloc(cc->req_pool, GFP_NOIO);
+		ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO);
 
 	aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]);
 
@@ -1290,7 +1290,7 @@ static void crypt_free_req_skcipher(struct crypt_config *cc,
 	struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
 
 	if ((struct skcipher_request *)(io + 1) != req)
-		mempool_free(req, cc->req_pool);
+		mempool_free(req, &cc->req_pool);
 }
 
 static void crypt_free_req_aead(struct crypt_config *cc,
@@ -1299,7 +1299,7 @@ static void crypt_free_req_aead(struct crypt_config *cc,
 	struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
 
 	if ((struct aead_request *)(io + 1) != req)
-		mempool_free(req, cc->req_pool);
+		mempool_free(req, &cc->req_pool);
 }
 
 static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_bio)
@@ -1409,7 +1409,7 @@ retry:
 	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
 		mutex_lock(&cc->bio_alloc_lock);
 
-	clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
+	clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, &cc->bs);
 	if (!clone)
 		goto out;
 
@@ -1418,7 +1418,7 @@ retry:
 	remaining_size = size;
 
 	for (i = 0; i < nr_iovecs; i++) {
-		page = mempool_alloc(cc->page_pool, gfp_mask);
+		page = mempool_alloc(&cc->page_pool, gfp_mask);
 		if (!page) {
 			crypt_free_buffer_pages(cc, clone);
 			bio_put(clone);
@@ -1453,7 +1453,7 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
 
 	bio_for_each_segment_all(bv, clone, i) {
 		BUG_ON(!bv->bv_page);
-		mempool_free(bv->bv_page, cc->page_pool);
+		mempool_free(bv->bv_page, &cc->page_pool);
 	}
 }
 
@@ -1492,7 +1492,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 		crypt_free_req(cc, io->ctx.r.req, base_bio);
 
 	if (unlikely(io->integrity_metadata_from_pool))
-		mempool_free(io->integrity_metadata, io->cc->tag_pool);
+		mempool_free(io->integrity_metadata, &io->cc->tag_pool);
 	else
 		kfree(io->integrity_metadata);
 
@@ -1565,7 +1565,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	 * biovecs we don't need to worry about the block layer
 	 * modifying the biovec array; so leverage bio_clone_fast().
 	 */
-	clone = bio_clone_fast(io->base_bio, gfp, cc->bs);
+	clone = bio_clone_fast(io->base_bio, gfp, &cc->bs);
 	if (!clone)
 		return 1;
 
@@ -2219,15 +2219,13 @@ static void crypt_dtr(struct dm_target *ti)
 
 	crypt_free_tfms(cc);
 
-	if (cc->bs)
-		bioset_free(cc->bs);
+	bioset_exit(&cc->bs);
 
-	mempool_destroy(cc->page_pool);
-	mempool_destroy(cc->req_pool);
-	mempool_destroy(cc->tag_pool);
+	mempool_exit(&cc->page_pool);
+	mempool_exit(&cc->req_pool);
+	mempool_exit(&cc->tag_pool);
 
-	if (cc->page_pool)
-		WARN_ON(percpu_counter_sum(&cc->n_allocated_pages) != 0);
+	WARN_ON(percpu_counter_sum(&cc->n_allocated_pages) != 0);
 	percpu_counter_destroy(&cc->n_allocated_pages);
 
 	if (cc->iv_gen_ops && cc->iv_gen_ops->dtr)
@@ -2743,8 +2741,6 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		iv_size_padding = align_mask;
 	}
 
-	ret = -ENOMEM;
-
 	/*  ...| IV + padding | original IV | original sec. number | bio tag offset | */
 	additional_req_size = sizeof(struct dm_crypt_request) +
 		iv_size_padding + cc->iv_size +
@@ -2752,8 +2748,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		sizeof(uint64_t) +
 		sizeof(unsigned int);
 
-	cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start + additional_req_size);
-	if (!cc->req_pool) {
+	ret = mempool_init_kmalloc_pool(&cc->req_pool, MIN_IOS, cc->dmreq_start + additional_req_size);
+	if (ret) {
 		ti->error = "Cannot allocate crypt request mempool";
 		goto bad;
 	}
@@ -2762,14 +2758,14 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size,
 		      ARCH_KMALLOC_MINALIGN);
 
-	cc->page_pool = mempool_create(BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
-	if (!cc->page_pool) {
+	ret = mempool_init(&cc->page_pool, BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
+	if (ret) {
 		ti->error = "Cannot allocate page mempool";
 		goto bad;
 	}
 
-	cc->bs = bioset_create(MIN_IOS, 0, BIOSET_NEED_BVECS);
-	if (!cc->bs) {
+	ret = bioset_init(&cc->bs, MIN_IOS, 0, BIOSET_NEED_BVECS);
+	if (ret) {
 		ti->error = "Cannot allocate crypt bioset";
 		goto bad;
 	}
@@ -2806,11 +2802,10 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		if (!cc->tag_pool_max_sectors)
 			cc->tag_pool_max_sectors = 1;
 
-		cc->tag_pool = mempool_create_kmalloc_pool(MIN_IOS,
+		ret = mempool_init_kmalloc_pool(&cc->tag_pool, MIN_IOS,
 			cc->tag_pool_max_sectors * cc->on_disk_tag_size);
-		if (!cc->tag_pool) {
+		if (ret) {
 			ti->error = "Cannot allocate integrity tags mempool";
-			ret = -ENOMEM;
 			goto bad;
 		}
 
@@ -2903,7 +2898,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 				GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
 			if (bio_sectors(bio) > cc->tag_pool_max_sectors)
 				dm_accept_partial_bio(bio, cc->tag_pool_max_sectors);
-			io->integrity_metadata = mempool_alloc(cc->tag_pool, GFP_NOIO);
+			io->integrity_metadata = mempool_alloc(&cc->tag_pool, GFP_NOIO);
 			io->integrity_metadata_from_pool = true;
 		}
 	}
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 77d9fe58dae2..fc68c7aaef8e 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -142,7 +142,7 @@ struct dm_integrity_c {
 	unsigned tag_size;
 	__s8 log2_tag_size;
 	sector_t start;
-	mempool_t *journal_io_mempool;
+	mempool_t journal_io_mempool;
 	struct dm_io_client *io;
 	struct dm_bufio_client *bufio;
 	struct workqueue_struct *metadata_wq;
@@ -1817,7 +1817,7 @@ static void complete_copy_from_journal(unsigned long error, void *context)
 	struct journal_completion *comp = io->comp;
 	struct dm_integrity_c *ic = comp->ic;
 	remove_range(ic, &io->range);
-	mempool_free(io, ic->journal_io_mempool);
+	mempool_free(io, &ic->journal_io_mempool);
 	if (unlikely(error != 0))
 		dm_integrity_io_error(ic, "copying from journal", -EIO);
 	complete_journal_op(comp);
@@ -1886,7 +1886,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start,
 			}
 			next_loop = k - 1;
 
-			io = mempool_alloc(ic->journal_io_mempool, GFP_NOIO);
+			io = mempool_alloc(&ic->journal_io_mempool, GFP_NOIO);
 			io->comp = &comp;
 			io->range.logical_sector = sec;
 			io->range.n_sectors = (k - j) << ic->sb->log2_sectors_per_block;
@@ -1918,7 +1918,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start,
 				if (j == k) {
 					remove_range_unlocked(ic, &io->range);
 					spin_unlock_irq(&ic->endio_wait.lock);
-					mempool_free(io, ic->journal_io_mempool);
+					mempool_free(io, &ic->journal_io_mempool);
 					goto skip_io;
 				}
 				for (l = j; l < k; l++) {
@@ -2440,7 +2440,7 @@ static void dm_integrity_free_journal_scatterlist(struct dm_integrity_c *ic, str
 	unsigned i;
 	for (i = 0; i < ic->journal_sections; i++)
 		kvfree(sl[i]);
-	kfree(sl);
+	kvfree(sl);
 }
 
 static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_integrity_c *ic, struct page_list *pl)
@@ -2980,9 +2980,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
-	ic->journal_io_mempool = mempool_create_slab_pool(JOURNAL_IO_MEMPOOL, journal_io_cache);
-	if (!ic->journal_io_mempool) {
-		r = -ENOMEM;
+	r = mempool_init_slab_pool(&ic->journal_io_mempool, JOURNAL_IO_MEMPOOL, journal_io_cache);
+	if (r) {
 		ti->error = "Cannot allocate mempool";
 		goto bad;
 	}
@@ -3196,7 +3195,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 		destroy_workqueue(ic->writer_wq);
 	if (ic->bufio)
 		dm_bufio_client_destroy(ic->bufio);
-	mempool_destroy(ic->journal_io_mempool);
+	mempool_exit(&ic->journal_io_mempool);
 	if (ic->io)
 		dm_io_client_destroy(ic->io);
 	if (ic->dev)
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index a8d914d5abbe..81ffc59d05c9 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -22,8 +22,8 @@
 #define DM_IO_MAX_REGIONS	BITS_PER_LONG
 
 struct dm_io_client {
-	mempool_t *pool;
-	struct bio_set *bios;
+	mempool_t pool;
+	struct bio_set bios;
 };
 
 /*
@@ -49,32 +49,33 @@ struct dm_io_client *dm_io_client_create(void)
 {
 	struct dm_io_client *client;
 	unsigned min_ios = dm_get_reserved_bio_based_ios();
+	int ret;
 
-	client = kmalloc(sizeof(*client), GFP_KERNEL);
+	client = kzalloc(sizeof(*client), GFP_KERNEL);
 	if (!client)
 		return ERR_PTR(-ENOMEM);
 
-	client->pool = mempool_create_slab_pool(min_ios, _dm_io_cache);
-	if (!client->pool)
+	ret = mempool_init_slab_pool(&client->pool, min_ios, _dm_io_cache);
+	if (ret)
 		goto bad;
 
-	client->bios = bioset_create(min_ios, 0, BIOSET_NEED_BVECS);
-	if (!client->bios)
+	ret = bioset_init(&client->bios, min_ios, 0, BIOSET_NEED_BVECS);
+	if (ret)
 		goto bad;
 
 	return client;
 
    bad:
-	mempool_destroy(client->pool);
+	mempool_exit(&client->pool);
 	kfree(client);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL(dm_io_client_create);
 
 void dm_io_client_destroy(struct dm_io_client *client)
 {
-	mempool_destroy(client->pool);
-	bioset_free(client->bios);
+	mempool_exit(&client->pool);
+	bioset_exit(&client->bios);
 	kfree(client);
 }
 EXPORT_SYMBOL(dm_io_client_destroy);
@@ -120,7 +121,7 @@ static void complete_io(struct io *io)
 		invalidate_kernel_vmap_range(io->vma_invalidate_address,
 					     io->vma_invalidate_size);
 
-	mempool_free(io, io->client->pool);
+	mempool_free(io, &io->client->pool);
 	fn(error_bits, context);
 }
 
@@ -344,7 +345,7 @@ static void do_region(int op, int op_flags, unsigned region,
 					  dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
 		}
 
-		bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
+		bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, &io->client->bios);
 		bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
 		bio_set_dev(bio, where->bdev);
 		bio->bi_end_io = endio;
@@ -442,7 +443,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 
 	init_completion(&sio.wait);
 
-	io = mempool_alloc(client->pool, GFP_NOIO);
+	io = mempool_alloc(&client->pool, GFP_NOIO);
 	io->error_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->client = client;
@@ -474,7 +475,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 		return -EIO;
 	}
 
-	io = mempool_alloc(client->pool, GFP_NOIO);
+	io = mempool_alloc(&client->pool, GFP_NOIO);
 	io->error_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->client = client;
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index e6e7c686646d..ce7efc7434be 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -47,7 +47,7 @@ struct dm_kcopyd_client {
 	wait_queue_head_t destroyq;
 	atomic_t nr_jobs;
 
-	mempool_t *job_pool;
+	mempool_t job_pool;
 
 	struct workqueue_struct *kcopyd_wq;
 	struct work_struct kcopyd_work;
@@ -479,7 +479,7 @@ static int run_complete_job(struct kcopyd_job *job)
 	 */
 	if (job->master_job == job) {
 		mutex_destroy(&job->lock);
-		mempool_free(job, kc->job_pool);
+		mempool_free(job, &kc->job_pool);
 	}
 	fn(read_err, write_err, context);
 
@@ -751,7 +751,7 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 	 * Allocate an array of jobs consisting of one master job
 	 * followed by SPLIT_COUNT sub jobs.
 	 */
-	job = mempool_alloc(kc->job_pool, GFP_NOIO);
+	job = mempool_alloc(&kc->job_pool, GFP_NOIO);
 	mutex_init(&job->lock);
 
 	/*
@@ -835,7 +835,7 @@ void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc,
 {
 	struct kcopyd_job *job;
 
-	job = mempool_alloc(kc->job_pool, GFP_NOIO);
+	job = mempool_alloc(&kc->job_pool, GFP_NOIO);
 
 	memset(job, 0, sizeof(struct kcopyd_job));
 	job->kc = kc;
@@ -879,10 +879,10 @@ int kcopyd_cancel(struct kcopyd_job *job, int block)
  *---------------------------------------------------------------*/
 struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle)
 {
-	int r = -ENOMEM;
+	int r;
 	struct dm_kcopyd_client *kc;
 
-	kc = kmalloc(sizeof(*kc), GFP_KERNEL);
+	kc = kzalloc(sizeof(*kc), GFP_KERNEL);
 	if (!kc)
 		return ERR_PTR(-ENOMEM);
 
@@ -892,14 +892,16 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro
 	INIT_LIST_HEAD(&kc->pages_jobs);
 	kc->throttle = throttle;
 
-	kc->job_pool = mempool_create_slab_pool(MIN_JOBS, _job_cache);
-	if (!kc->job_pool)
+	r = mempool_init_slab_pool(&kc->job_pool, MIN_JOBS, _job_cache);
+	if (r)
 		goto bad_slab;
 
 	INIT_WORK(&kc->kcopyd_work, do_work);
 	kc->kcopyd_wq = alloc_workqueue("kcopyd", WQ_MEM_RECLAIM, 0);
-	if (!kc->kcopyd_wq)
+	if (!kc->kcopyd_wq) {
+		r = -ENOMEM;
 		goto bad_workqueue;
+	}
 
 	kc->pages = NULL;
 	kc->nr_reserved_pages = kc->nr_free_pages = 0;
@@ -923,7 +925,7 @@ bad_io_client:
 bad_client_pages:
 	destroy_workqueue(kc->kcopyd_wq);
 bad_workqueue:
-	mempool_destroy(kc->job_pool);
+	mempool_exit(&kc->job_pool);
 bad_slab:
 	kfree(kc);
 
@@ -942,7 +944,7 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc)
 	destroy_workqueue(kc->kcopyd_wq);
 	dm_io_client_destroy(kc->io_client);
 	client_free_pages(kc);
-	mempool_destroy(kc->job_pool);
+	mempool_exit(&kc->job_pool);
 	kfree(kc);
 }
 EXPORT_SYMBOL(dm_kcopyd_client_destroy);
diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
index 53b7b06d0aa8..52090bee17c2 100644
--- a/drivers/md/dm-log-userspace-base.c
+++ b/drivers/md/dm-log-userspace-base.c
@@ -76,7 +76,7 @@ struct log_c {
 	 */
 	uint32_t integrated_flush;
 
-	mempool_t *flush_entry_pool;
+	mempool_t flush_entry_pool;
 };
 
 static struct kmem_cache *_flush_entry_cache;
@@ -249,11 +249,10 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 		goto out;
 	}
 
-	lc->flush_entry_pool = mempool_create_slab_pool(FLUSH_ENTRY_POOL_SIZE,
-							_flush_entry_cache);
-	if (!lc->flush_entry_pool) {
+	r = mempool_init_slab_pool(&lc->flush_entry_pool, FLUSH_ENTRY_POOL_SIZE,
+				   _flush_entry_cache);
+	if (r) {
 		DMERR("Failed to create flush_entry_pool");
-		r = -ENOMEM;
 		goto out;
 	}
 
@@ -313,7 +312,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 out:
 	kfree(devices_rdata);
 	if (r) {
-		mempool_destroy(lc->flush_entry_pool);
+		mempool_exit(&lc->flush_entry_pool);
 		kfree(lc);
 		kfree(ctr_str);
 	} else {
@@ -342,7 +341,7 @@ static void userspace_dtr(struct dm_dirty_log *log)
 	if (lc->log_dev)
 		dm_put_device(lc->ti, lc->log_dev);
 
-	mempool_destroy(lc->flush_entry_pool);
+	mempool_exit(&lc->flush_entry_pool);
 
 	kfree(lc->usr_argv_str);
 	kfree(lc);
@@ -570,7 +569,7 @@ static int userspace_flush(struct dm_dirty_log *log)
 	int mark_list_is_empty;
 	int clear_list_is_empty;
 	struct dm_dirty_log_flush_entry *fe, *tmp_fe;
-	mempool_t *flush_entry_pool = lc->flush_entry_pool;
+	mempool_t *flush_entry_pool = &lc->flush_entry_pool;
 
 	spin_lock_irqsave(&lc->flush_lock, flags);
 	list_splice_init(&lc->mark_list, &mark_list);
@@ -653,7 +652,7 @@ static void userspace_mark_region(struct dm_dirty_log *log, region_t region)
 	struct dm_dirty_log_flush_entry *fe;
 
 	/* Wait for an allocation, but _never_ fail */
-	fe = mempool_alloc(lc->flush_entry_pool, GFP_NOIO);
+	fe = mempool_alloc(&lc->flush_entry_pool, GFP_NOIO);
 	BUG_ON(!fe);
 
 	spin_lock_irqsave(&lc->flush_lock, flags);
@@ -687,7 +686,7 @@ static void userspace_clear_region(struct dm_dirty_log *log, region_t region)
 	 * to cause the region to be resync'ed when the
 	 * device is activated next time.
 	 */
-	fe = mempool_alloc(lc->flush_entry_pool, GFP_ATOMIC);
+	fe = mempool_alloc(&lc->flush_entry_pool, GFP_ATOMIC);
 	if (!fe) {
 		DMERR("Failed to allocate memory to clear region.");
 		return;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 203a0419d2b0..d94ba6f72ff5 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -520,7 +520,8 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 
 	bdev = pgpath->path.dev->bdev;
 	q = bdev_get_queue(bdev);
-	clone = blk_get_request(q, rq->cmd_flags | REQ_NOMERGE, GFP_ATOMIC);
+	clone = blk_get_request(q, rq->cmd_flags | REQ_NOMERGE,
+			BLK_MQ_REQ_NOWAIT);
 	if (IS_ERR(clone)) {
 		/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
 		if (blk_queue_dying(q)) {
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 580c49cc8079..5903e492bb34 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -23,6 +23,8 @@
 
 #define MAX_RECOVERY 1	/* Maximum number of regions recovered in parallel. */
 
+#define MAX_NR_MIRRORS	(DM_KCOPYD_MAX_REGIONS + 1)
+
 #define DM_RAID1_HANDLE_ERRORS	0x01
 #define DM_RAID1_KEEP_LOG	0x02
 #define errors_handled(p)	((p)->features & DM_RAID1_HANDLE_ERRORS)
@@ -255,7 +257,7 @@ static int mirror_flush(struct dm_target *ti)
 	unsigned long error_bits;
 
 	unsigned int i;
-	struct dm_io_region io[ms->nr_mirrors];
+	struct dm_io_region io[MAX_NR_MIRRORS];
 	struct mirror *m;
 	struct dm_io_request io_req = {
 		.bi_op = REQ_OP_WRITE,
@@ -651,7 +653,7 @@ static void write_callback(unsigned long error, void *context)
 static void do_write(struct mirror_set *ms, struct bio *bio)
 {
 	unsigned int i;
-	struct dm_io_region io[ms->nr_mirrors], *dest = io;
+	struct dm_io_region io[MAX_NR_MIRRORS], *dest = io;
 	struct mirror *m;
 	struct dm_io_request io_req = {
 		.bi_op = REQ_OP_WRITE,
@@ -1083,7 +1085,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	argc -= args_used;
 
 	if (!argc || sscanf(argv[0], "%u%c", &nr_mirrors, &dummy) != 1 ||
-	    nr_mirrors < 2 || nr_mirrors > DM_KCOPYD_MAX_REGIONS + 1) {
+	    nr_mirrors < 2 || nr_mirrors > MAX_NR_MIRRORS) {
 		ti->error = "Invalid number of mirrors";
 		dm_dirty_log_destroy(dl);
 		return -EINVAL;
@@ -1404,7 +1406,7 @@ static void mirror_status(struct dm_target *ti, status_type_t type,
 	int num_feature_args = 0;
 	struct mirror_set *ms = (struct mirror_set *) ti->private;
 	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
-	char buffer[ms->nr_mirrors + 1];
+	char buffer[MAX_NR_MIRRORS + 1];
 
 	switch (type) {
 	case STATUSTYPE_INFO:
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index 85c32b22a420..abf3521b80a8 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -63,7 +63,7 @@ struct dm_region_hash {
 
 	/* hash table */
 	rwlock_t hash_lock;
-	mempool_t *region_pool;
+	mempool_t region_pool;
 	unsigned mask;
 	unsigned nr_buckets;
 	unsigned prime;
@@ -169,6 +169,7 @@ struct dm_region_hash *dm_region_hash_create(
 	struct dm_region_hash *rh;
 	unsigned nr_buckets, max_buckets;
 	size_t i;
+	int ret;
 
 	/*
 	 * Calculate a suitable number of buckets for our hash
@@ -179,7 +180,7 @@ struct dm_region_hash *dm_region_hash_create(
 		;
 	nr_buckets >>= 1;
 
-	rh = kmalloc(sizeof(*rh), GFP_KERNEL);
+	rh = kzalloc(sizeof(*rh), GFP_KERNEL);
 	if (!rh) {
 		DMERR("unable to allocate region hash memory");
 		return ERR_PTR(-ENOMEM);
@@ -220,9 +221,9 @@ struct dm_region_hash *dm_region_hash_create(
 	INIT_LIST_HEAD(&rh->failed_recovered_regions);
 	rh->flush_failure = 0;
 
-	rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
-						      sizeof(struct dm_region));
-	if (!rh->region_pool) {
+	ret = mempool_init_kmalloc_pool(&rh->region_pool, MIN_REGIONS,
+					sizeof(struct dm_region));
+	if (ret) {
 		vfree(rh->buckets);
 		kfree(rh);
 		rh = ERR_PTR(-ENOMEM);
@@ -242,14 +243,14 @@ void dm_region_hash_destroy(struct dm_region_hash *rh)
 		list_for_each_entry_safe(reg, nreg, rh->buckets + h,
 					 hash_list) {
 			BUG_ON(atomic_read(&reg->pending));
-			mempool_free(reg, rh->region_pool);
+			mempool_free(reg, &rh->region_pool);
 		}
 	}
 
 	if (rh->log)
 		dm_dirty_log_destroy(rh->log);
 
-	mempool_destroy(rh->region_pool);
+	mempool_exit(&rh->region_pool);
 	vfree(rh->buckets);
 	kfree(rh);
 }
@@ -287,7 +288,7 @@ static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region)
 {
 	struct dm_region *reg, *nreg;
 
-	nreg = mempool_alloc(rh->region_pool, GFP_ATOMIC);
+	nreg = mempool_alloc(&rh->region_pool, GFP_ATOMIC);
 	if (unlikely(!nreg))
 		nreg = kmalloc(sizeof(*nreg), GFP_NOIO | __GFP_NOFAIL);
 
@@ -303,7 +304,7 @@ static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region)
 	reg = __rh_lookup(rh, region);
 	if (reg)
 		/* We lost the race. */
-		mempool_free(nreg, rh->region_pool);
+		mempool_free(nreg, &rh->region_pool);
 	else {
 		__rh_insert(rh, nreg);
 		if (nreg->state == DM_RH_CLEAN) {
@@ -481,17 +482,17 @@ void dm_rh_update_states(struct dm_region_hash *rh, int errors_handled)
 	list_for_each_entry_safe(reg, next, &recovered, list) {
 		rh->log->type->clear_region(rh->log, reg->key);
 		complete_resync_work(reg, 1);
-		mempool_free(reg, rh->region_pool);
+		mempool_free(reg, &rh->region_pool);
 	}
 
 	list_for_each_entry_safe(reg, next, &failed_recovered, list) {
 		complete_resync_work(reg, errors_handled ? 0 : 1);
-		mempool_free(reg, rh->region_pool);
+		mempool_free(reg, &rh->region_pool);
 	}
 
 	list_for_each_entry_safe(reg, next, &clean, list) {
 		rh->log->type->clear_region(rh->log, reg->key);
-		mempool_free(reg, rh->region_pool);
+		mempool_free(reg, &rh->region_pool);
 	}
 
 	rh->log->type->flush(rh->log);
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index bf0b840645cc..6e547b8dd298 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -406,7 +406,7 @@ static blk_status_t dm_dispatch_clone_request(struct request *clone, struct requ
 	if (blk_queue_io_stat(clone->q))
 		clone->rq_flags |= RQF_IO_STAT;
 
-	clone->start_time = jiffies;
+	clone->start_time_ns = ktime_get_ns();
 	r = blk_insert_cloned_request(clone->q, clone);
 	if (r != BLK_STS_OK && r != BLK_STS_RESOURCE && r != BLK_STS_DEV_RESOURCE)
 		/* must complete clone in terms of original request */
@@ -433,7 +433,7 @@ static int setup_clone(struct request *clone, struct request *rq,
 {
 	int r;
 
-	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
+	r = blk_rq_prep_clone(clone, rq, &tio->md->bs, gfp_mask,
 			      dm_rq_bio_constructor, tio);
 	if (r)
 		return r;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 216035be5661..f745404da721 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -87,7 +87,7 @@ struct dm_snapshot {
 	 */
 	struct list_head out_of_order_list;
 
-	mempool_t *pending_pool;
+	mempool_t pending_pool;
 
 	struct dm_exception_table pending;
 	struct dm_exception_table complete;
@@ -682,7 +682,7 @@ static void free_completed_exception(struct dm_exception *e)
 
 static struct dm_snap_pending_exception *alloc_pending_exception(struct dm_snapshot *s)
 {
-	struct dm_snap_pending_exception *pe = mempool_alloc(s->pending_pool,
+	struct dm_snap_pending_exception *pe = mempool_alloc(&s->pending_pool,
 							     GFP_NOIO);
 
 	atomic_inc(&s->pending_exceptions_count);
@@ -695,7 +695,7 @@ static void free_pending_exception(struct dm_snap_pending_exception *pe)
 {
 	struct dm_snapshot *s = pe->snap;
 
-	mempool_free(pe, s->pending_pool);
+	mempool_free(pe, &s->pending_pool);
 	smp_mb__before_atomic();
 	atomic_dec(&s->pending_exceptions_count);
 }
@@ -1120,7 +1120,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		origin_mode = FMODE_WRITE;
 	}
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
 	if (!s) {
 		ti->error = "Cannot allocate private snapshot structure";
 		r = -ENOMEM;
@@ -1196,10 +1196,9 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad_kcopyd;
 	}
 
-	s->pending_pool = mempool_create_slab_pool(MIN_IOS, pending_cache);
-	if (!s->pending_pool) {
+	r = mempool_init_slab_pool(&s->pending_pool, MIN_IOS, pending_cache);
+	if (r) {
 		ti->error = "Could not allocate mempool for pending exceptions";
-		r = -ENOMEM;
 		goto bad_pending_pool;
 	}
 
@@ -1259,7 +1258,7 @@ bad_read_metadata:
 	unregister_snapshot(s);
 
 bad_load_and_register:
-	mempool_destroy(s->pending_pool);
+	mempool_exit(&s->pending_pool);
 
 bad_pending_pool:
 	dm_kcopyd_client_destroy(s->kcopyd_client);
@@ -1355,7 +1354,7 @@ static void snapshot_dtr(struct dm_target *ti)
 	while (atomic_read(&s->pending_exceptions_count))
 		msleep(1);
 	/*
-	 * Ensure instructions in mempool_destroy aren't reordered
+	 * Ensure instructions in mempool_exit aren't reordered
 	 * before atomic_read.
 	 */
 	smp_mb();
@@ -1367,7 +1366,7 @@ static void snapshot_dtr(struct dm_target *ti)
 
 	__free_exceptions(s);
 
-	mempool_destroy(s->pending_pool);
+	mempool_exit(&s->pending_pool);
 
 	dm_exception_store_destroy(s->store);
 
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index b11107497d2e..5772756c63c1 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -260,7 +260,7 @@ struct pool {
 	struct dm_deferred_set *all_io_ds;
 
 	struct dm_thin_new_mapping *next_mapping;
-	mempool_t *mapping_pool;
+	mempool_t mapping_pool;
 
 	process_bio_fn process_bio;
 	process_bio_fn process_discard;
@@ -917,7 +917,7 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
 {
 	cell_error(m->tc->pool, m->cell);
 	list_del(&m->list);
-	mempool_free(m, m->tc->pool->mapping_pool);
+	mempool_free(m, &m->tc->pool->mapping_pool);
 }
 
 static void process_prepared_mapping(struct dm_thin_new_mapping *m)
@@ -961,7 +961,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 
 out:
 	list_del(&m->list);
-	mempool_free(m, pool->mapping_pool);
+	mempool_free(m, &pool->mapping_pool);
 }
 
 /*----------------------------------------------------------------*/
@@ -971,7 +971,7 @@ static void free_discard_mapping(struct dm_thin_new_mapping *m)
 	struct thin_c *tc = m->tc;
 	if (m->cell)
 		cell_defer_no_holder(tc, m->cell);
-	mempool_free(m, tc->pool->mapping_pool);
+	mempool_free(m, &tc->pool->mapping_pool);
 }
 
 static void process_prepared_discard_fail(struct dm_thin_new_mapping *m)
@@ -999,7 +999,7 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m)
 		bio_endio(m->bio);
 
 	cell_defer_no_holder(tc, m->cell);
-	mempool_free(m, tc->pool->mapping_pool);
+	mempool_free(m, &tc->pool->mapping_pool);
 }
 
 /*----------------------------------------------------------------*/
@@ -1092,7 +1092,7 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
 		metadata_operation_failed(pool, "dm_thin_remove_range", r);
 		bio_io_error(m->bio);
 		cell_defer_no_holder(tc, m->cell);
-		mempool_free(m, pool->mapping_pool);
+		mempool_free(m, &pool->mapping_pool);
 		return;
 	}
 
@@ -1105,7 +1105,7 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
 		metadata_operation_failed(pool, "dm_pool_inc_data_range", r);
 		bio_io_error(m->bio);
 		cell_defer_no_holder(tc, m->cell);
-		mempool_free(m, pool->mapping_pool);
+		mempool_free(m, &pool->mapping_pool);
 		return;
 	}
 
@@ -1150,7 +1150,7 @@ static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m)
 		bio_endio(m->bio);
 
 	cell_defer_no_holder(tc, m->cell);
-	mempool_free(m, pool->mapping_pool);
+	mempool_free(m, &pool->mapping_pool);
 }
 
 static void process_prepared(struct pool *pool, struct list_head *head,
@@ -1196,7 +1196,7 @@ static int ensure_next_mapping(struct pool *pool)
 	if (pool->next_mapping)
 		return 0;
 
-	pool->next_mapping = mempool_alloc(pool->mapping_pool, GFP_ATOMIC);
+	pool->next_mapping = mempool_alloc(&pool->mapping_pool, GFP_ATOMIC);
 
 	return pool->next_mapping ? 0 : -ENOMEM;
 }
@@ -2835,8 +2835,8 @@ static void __pool_destroy(struct pool *pool)
 		destroy_workqueue(pool->wq);
 
 	if (pool->next_mapping)
-		mempool_free(pool->next_mapping, pool->mapping_pool);
-	mempool_destroy(pool->mapping_pool);
+		mempool_free(pool->next_mapping, &pool->mapping_pool);
+	mempool_exit(&pool->mapping_pool);
 	dm_deferred_set_destroy(pool->shared_read_ds);
 	dm_deferred_set_destroy(pool->all_io_ds);
 	kfree(pool);
@@ -2861,7 +2861,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 		return (struct pool *)pmd;
 	}
 
-	pool = kmalloc(sizeof(*pool), GFP_KERNEL);
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool) {
 		*error = "Error allocating memory for pool";
 		err_p = ERR_PTR(-ENOMEM);
@@ -2931,11 +2931,11 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	}
 
 	pool->next_mapping = NULL;
-	pool->mapping_pool = mempool_create_slab_pool(MAPPING_POOL_SIZE,
-						      _new_mapping_cache);
-	if (!pool->mapping_pool) {
+	r = mempool_init_slab_pool(&pool->mapping_pool, MAPPING_POOL_SIZE,
+				   _new_mapping_cache);
+	if (r) {
 		*error = "Error creating pool's mapping mempool";
-		err_p = ERR_PTR(-ENOMEM);
+		err_p = ERR_PTR(r);
 		goto bad_mapping_pool;
 	}
 
@@ -2955,7 +2955,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	return pool;
 
 bad_sort_array:
-	mempool_destroy(pool->mapping_pool);
+	mempool_exit(&pool->mapping_pool);
 bad_mapping_pool:
 	dm_deferred_set_destroy(pool->all_io_ds);
 bad_all_io_ds:
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index e13f90832b6b..684af08d0747 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -309,13 +309,13 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
 	unsigned n;
 
 	if (!fio->rs)
-		fio->rs = mempool_alloc(v->fec->rs_pool, GFP_NOIO);
+		fio->rs = mempool_alloc(&v->fec->rs_pool, GFP_NOIO);
 
 	fec_for_each_prealloc_buffer(n) {
 		if (fio->bufs[n])
 			continue;
 
-		fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOWAIT);
+		fio->bufs[n] = mempool_alloc(&v->fec->prealloc_pool, GFP_NOWAIT);
 		if (unlikely(!fio->bufs[n])) {
 			DMERR("failed to allocate FEC buffer");
 			return -ENOMEM;
@@ -327,7 +327,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
 		if (fio->bufs[n])
 			continue;
 
-		fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOWAIT);
+		fio->bufs[n] = mempool_alloc(&v->fec->extra_pool, GFP_NOWAIT);
 		/* we can manage with even one buffer if necessary */
 		if (unlikely(!fio->bufs[n]))
 			break;
@@ -335,7 +335,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
 	fio->nbufs = n;
 
 	if (!fio->output)
-		fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO);
+		fio->output = mempool_alloc(&v->fec->output_pool, GFP_NOIO);
 
 	return 0;
 }
@@ -493,15 +493,15 @@ void verity_fec_finish_io(struct dm_verity_io *io)
 	if (!verity_fec_is_enabled(io->v))
 		return;
 
-	mempool_free(fio->rs, f->rs_pool);
+	mempool_free(fio->rs, &f->rs_pool);
 
 	fec_for_each_prealloc_buffer(n)
-		mempool_free(fio->bufs[n], f->prealloc_pool);
+		mempool_free(fio->bufs[n], &f->prealloc_pool);
 
 	fec_for_each_extra_buffer(fio, n)
-		mempool_free(fio->bufs[n], f->extra_pool);
+		mempool_free(fio->bufs[n], &f->extra_pool);
 
-	mempool_free(fio->output, f->output_pool);
+	mempool_free(fio->output, &f->output_pool);
 }
 
 /*
@@ -549,9 +549,9 @@ void verity_fec_dtr(struct dm_verity *v)
 	if (!verity_fec_is_enabled(v))
 		goto out;
 
-	mempool_destroy(f->rs_pool);
-	mempool_destroy(f->prealloc_pool);
-	mempool_destroy(f->extra_pool);
+	mempool_exit(&f->rs_pool);
+	mempool_exit(&f->prealloc_pool);
+	mempool_exit(&f->extra_pool);
 	kmem_cache_destroy(f->cache);
 
 	if (f->data_bufio)
@@ -570,7 +570,7 @@ static void *fec_rs_alloc(gfp_t gfp_mask, void *pool_data)
 {
 	struct dm_verity *v = (struct dm_verity *)pool_data;
 
-	return init_rs(8, 0x11d, 0, 1, v->fec->roots);
+	return init_rs_gfp(8, 0x11d, 0, 1, v->fec->roots, gfp_mask);
 }
 
 static void fec_rs_free(void *element, void *pool_data)
@@ -675,6 +675,7 @@ int verity_fec_ctr(struct dm_verity *v)
 	struct dm_verity_fec *f = v->fec;
 	struct dm_target *ti = v->ti;
 	u64 hash_blocks;
+	int ret;
 
 	if (!verity_fec_is_enabled(v)) {
 		verity_fec_dtr(v);
@@ -770,11 +771,11 @@ int verity_fec_ctr(struct dm_verity *v)
 	}
 
 	/* Preallocate an rs_control structure for each worker thread */
-	f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc,
-				    fec_rs_free, (void *) v);
-	if (!f->rs_pool) {
+	ret = mempool_init(&f->rs_pool, num_online_cpus(), fec_rs_alloc,
+			   fec_rs_free, (void *) v);
+	if (ret) {
 		ti->error = "Cannot allocate RS pool";
-		return -ENOMEM;
+		return ret;
 	}
 
 	f->cache = kmem_cache_create("dm_verity_fec_buffers",
@@ -786,26 +787,26 @@ int verity_fec_ctr(struct dm_verity *v)
 	}
 
 	/* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */
-	f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() *
-						    DM_VERITY_FEC_BUF_PREALLOC,
-						    f->cache);
-	if (!f->prealloc_pool) {
+	ret = mempool_init_slab_pool(&f->prealloc_pool, num_online_cpus() *
+				     DM_VERITY_FEC_BUF_PREALLOC,
+				     f->cache);
+	if (ret) {
 		ti->error = "Cannot allocate FEC buffer prealloc pool";
-		return -ENOMEM;
+		return ret;
 	}
 
-	f->extra_pool = mempool_create_slab_pool(0, f->cache);
-	if (!f->extra_pool) {
+	ret = mempool_init_slab_pool(&f->extra_pool, 0, f->cache);
+	if (ret) {
 		ti->error = "Cannot allocate FEC buffer extra pool";
-		return -ENOMEM;
+		return ret;
 	}
 
 	/* Preallocate an output buffer for each thread */
-	f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(),
-						     1 << v->data_dev_block_bits);
-	if (!f->output_pool) {
+	ret = mempool_init_kmalloc_pool(&f->output_pool, num_online_cpus(),
+					1 << v->data_dev_block_bits);
+	if (ret) {
 		ti->error = "Cannot allocate FEC output pool";
-		return -ENOMEM;
+		return ret;
 	}
 
 	/* Reserve space for our per-bio data */
diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h
index bb31ce87a933..6ad803b2b36c 100644
--- a/drivers/md/dm-verity-fec.h
+++ b/drivers/md/dm-verity-fec.h
@@ -46,10 +46,10 @@ struct dm_verity_fec {
 	sector_t hash_blocks;	/* blocks covered after v->hash_start */
 	unsigned char roots;	/* number of parity bytes, M-N of RS(M, N) */
 	unsigned char rsn;	/* N of RS(M, N) */
-	mempool_t *rs_pool;	/* mempool for fio->rs */
-	mempool_t *prealloc_pool;	/* mempool for preallocated buffers */
-	mempool_t *extra_pool;	/* mempool for extra buffers */
-	mempool_t *output_pool;	/* mempool for output */
+	mempool_t rs_pool;	/* mempool for fio->rs */
+	mempool_t prealloc_pool;	/* mempool for preallocated buffers */
+	mempool_t extra_pool;	/* mempool for extra buffers */
+	mempool_t output_pool;	/* mempool for output */
 	struct kmem_cache *cache;	/* cache for buffers */
 };
 
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index e73b0776683c..30602d15ad9a 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -57,7 +57,7 @@ struct dmz_target {
 	struct workqueue_struct *chunk_wq;
 
 	/* For cloned BIOs to zones */
-	struct bio_set		*bio_set;
+	struct bio_set		bio_set;
 
 	/* For flush */
 	spinlock_t		flush_lock;
@@ -121,7 +121,7 @@ static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone,
 	}
 
 	/* Partial BIO: we need to clone the BIO */
-	clone = bio_clone_fast(bio, GFP_NOIO, dmz->bio_set);
+	clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set);
 	if (!clone)
 		return -ENOMEM;
 
@@ -779,10 +779,9 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << dev->zone_nr_sectors_shift;
 
 	/* Zone BIO */
-	dmz->bio_set = bioset_create(DMZ_MIN_BIOS, 0, 0);
-	if (!dmz->bio_set) {
+	ret = bioset_init(&dmz->bio_set, DMZ_MIN_BIOS, 0, 0);
+	if (ret) {
 		ti->error = "Create BIO set failed";
-		ret = -ENOMEM;
 		goto err_meta;
 	}
 
@@ -828,7 +827,7 @@ err_cwq:
 	destroy_workqueue(dmz->chunk_wq);
 err_bio:
 	mutex_destroy(&dmz->chunk_lock);
-	bioset_free(dmz->bio_set);
+	bioset_exit(&dmz->bio_set);
 err_meta:
 	dmz_dtr_metadata(dmz->metadata);
 err_dev:
@@ -858,7 +857,7 @@ static void dmz_dtr(struct dm_target *ti)
 
 	dmz_dtr_metadata(dmz->metadata);
 
-	bioset_free(dmz->bio_set);
+	bioset_exit(&dmz->bio_set);
 
 	dmz_put_zoned_device(ti);
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4ea404dbcf0b..98dff36b89a3 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -148,8 +148,8 @@ static int dm_numa_node = DM_NUMA_NODE;
  * For mempools pre-allocation at the table loading time.
  */
 struct dm_md_mempools {
-	struct bio_set *bs;
-	struct bio_set *io_bs;
+	struct bio_set bs;
+	struct bio_set io_bs;
 };
 
 struct table_device {
@@ -537,7 +537,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
 	struct dm_target_io *tio;
 	struct bio *clone;
 
-	clone = bio_alloc_bioset(GFP_NOIO, 0, md->io_bs);
+	clone = bio_alloc_bioset(GFP_NOIO, 0, &md->io_bs);
 	if (!clone)
 		return NULL;
 
@@ -572,7 +572,7 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci, struct dm_target *t
 		/* the dm_target_io embedded in ci->io is available */
 		tio = &ci->io->tio;
 	} else {
-		struct bio *clone = bio_alloc_bioset(gfp_mask, 0, ci->io->md->bs);
+		struct bio *clone = bio_alloc_bioset(gfp_mask, 0, &ci->io->md->bs);
 		if (!clone)
 			return NULL;
 
@@ -1020,7 +1020,8 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
 EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
 
 static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
-		sector_t sector, int *srcu_idx)
+						sector_t sector, int *srcu_idx)
+	__acquires(md->io_barrier)
 {
 	struct dm_table *map;
 	struct dm_target *ti;
@@ -1037,7 +1038,7 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
 }
 
 static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+				 long nr_pages, void **kaddr, pfn_t *pfn)
 {
 	struct mapped_device *md = dax_get_private(dax_dev);
 	sector_t sector = pgoff * PAGE_SECTORS;
@@ -1065,7 +1066,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 
 static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
+				    void *addr, size_t bytes, struct iov_iter *i)
 {
 	struct mapped_device *md = dax_get_private(dax_dev);
 	sector_t sector = pgoff * PAGE_SECTORS;
@@ -1582,7 +1583,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 				 * won't be affected by this reassignment.
 				 */
 				struct bio *b = bio_clone_bioset(bio, GFP_NOIO,
-								 md->queue->bio_split);
+								 &md->queue->bio_split);
 				ci.io->orig_bio = b;
 				bio_advance(bio, (bio_sectors(bio) - ci.sector_count) << 9);
 				bio_chain(b, bio);
@@ -1784,10 +1785,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		destroy_workqueue(md->wq);
 	if (md->kworker_task)
 		kthread_stop(md->kworker_task);
-	if (md->bs)
-		bioset_free(md->bs);
-	if (md->io_bs)
-		bioset_free(md->io_bs);
+	bioset_exit(&md->bs);
+	bioset_exit(&md->io_bs);
 
 	if (md->dax_dev) {
 		kill_dax(md->dax_dev);
@@ -1964,16 +1963,10 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 		 * If so, reload bioset because front_pad may have changed
 		 * because a different table was loaded.
 		 */
-		if (md->bs) {
-			bioset_free(md->bs);
-			md->bs = NULL;
-		}
-		if (md->io_bs) {
-			bioset_free(md->io_bs);
-			md->io_bs = NULL;
-		}
+		bioset_exit(&md->bs);
+		bioset_exit(&md->io_bs);
 
-	} else if (md->bs) {
+	} else if (bioset_initialized(&md->bs)) {
 		/*
 		 * There's no need to reload with request-based dm
 		 * because the size of front_pad doesn't change.
@@ -1985,12 +1978,14 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 		goto out;
 	}
 
-	BUG_ON(!p || md->bs || md->io_bs);
+	BUG_ON(!p ||
+	       bioset_initialized(&md->bs) ||
+	       bioset_initialized(&md->io_bs));
 
 	md->bs = p->bs;
-	p->bs = NULL;
+	memset(&p->bs, 0, sizeof(p->bs));
 	md->io_bs = p->io_bs;
-	p->io_bs = NULL;
+	memset(&p->io_bs, 0, sizeof(p->io_bs));
 out:
 	/* mempool bind completed, no longer need any mempools in the table */
 	dm_table_free_md_mempools(t);
@@ -2904,6 +2899,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
 	struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
 	unsigned int pool_size = 0;
 	unsigned int front_pad, io_front_pad;
+	int ret;
 
 	if (!pools)
 		return NULL;
@@ -2915,10 +2911,10 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
 		pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
 		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
 		io_front_pad = roundup(front_pad,  __alignof__(struct dm_io)) + offsetof(struct dm_io, tio);
-		pools->io_bs = bioset_create(pool_size, io_front_pad, 0);
-		if (!pools->io_bs)
+		ret = bioset_init(&pools->io_bs, pool_size, io_front_pad, 0);
+		if (ret)
 			goto out;
-		if (integrity && bioset_integrity_create(pools->io_bs, pool_size))
+		if (integrity && bioset_integrity_create(&pools->io_bs, pool_size))
 			goto out;
 		break;
 	case DM_TYPE_REQUEST_BASED:
@@ -2931,11 +2927,11 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
 		BUG();
 	}
 
-	pools->bs = bioset_create(pool_size, front_pad, 0);
-	if (!pools->bs)
+	ret = bioset_init(&pools->bs, pool_size, front_pad, 0);
+	if (ret)
 		goto out;
 
-	if (integrity && bioset_integrity_create(pools->bs, pool_size))
+	if (integrity && bioset_integrity_create(&pools->bs, pool_size))
 		goto out;
 
 	return pools;
@@ -2951,10 +2947,8 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
 	if (!pools)
 		return;
 
-	if (pools->bs)
-		bioset_free(pools->bs);
-	if (pools->io_bs)
-		bioset_free(pools->io_bs);
+	bioset_exit(&pools->bs);
+	bioset_exit(&pools->io_bs);
 
 	kfree(pools);
 }
diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c
index 38264b38420f..c2fdf899de14 100644
--- a/drivers/md/md-faulty.c
+++ b/drivers/md/md-faulty.c
@@ -214,7 +214,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
 		}
 	}
 	if (failit) {
-		struct bio *b = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+		struct bio *b = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
 
 		bio_set_dev(b, conf->rdev->bdev);
 		b->bi_private = bio;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 4964323d936b..d45c697c0ebe 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -269,7 +269,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 	if (unlikely(bio_end_sector(bio) > end_sector)) {
 		/* This bio crosses a device boundary, so we have to split it */
 		struct bio *split = bio_split(bio, end_sector - bio_sector,
-					      GFP_NOIO, mddev->bio_set);
+					      GFP_NOIO, &mddev->bio_set);
 		bio_chain(split, bio);
 		generic_make_request(bio);
 		bio = split;
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 0a7e99d62c69..f71fcdb9b39c 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -80,7 +80,7 @@ static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status)
 
 	bio->bi_status = status;
 	bio_endio(bio);
-	mempool_free(mp_bh, conf->pool);
+	mempool_free(mp_bh, &conf->pool);
 }
 
 static void multipath_end_request(struct bio *bio)
@@ -117,7 +117,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
 		return true;
 	}
 
-	mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
+	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
 
 	mp_bh->master_bio = bio;
 	mp_bh->mddev = mddev;
@@ -125,7 +125,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
 	mp_bh->path = multipath_map(conf);
 	if (mp_bh->path < 0) {
 		bio_io_error(bio);
-		mempool_free(mp_bh, conf->pool);
+		mempool_free(mp_bh, &conf->pool);
 		return true;
 	}
 	multipath = conf->multipaths + mp_bh->path;
@@ -378,6 +378,7 @@ static int multipath_run (struct mddev *mddev)
 	struct multipath_info *disk;
 	struct md_rdev *rdev;
 	int working_disks;
+	int ret;
 
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
@@ -431,9 +432,9 @@ static int multipath_run (struct mddev *mddev)
 	}
 	mddev->degraded = conf->raid_disks - working_disks;
 
-	conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS,
-						 sizeof(struct multipath_bh));
-	if (conf->pool == NULL)
+	ret = mempool_init_kmalloc_pool(&conf->pool, NR_RESERVED_BUFS,
+					sizeof(struct multipath_bh));
+	if (ret)
 		goto out_free_conf;
 
 	mddev->thread = md_register_thread(multipathd, mddev,
@@ -455,7 +456,7 @@ static int multipath_run (struct mddev *mddev)
 	return 0;
 
 out_free_conf:
-	mempool_destroy(conf->pool);
+	mempool_exit(&conf->pool);
 	kfree(conf->multipaths);
 	kfree(conf);
 	mddev->private = NULL;
@@ -467,7 +468,7 @@ static void multipath_free(struct mddev *mddev, void *priv)
 {
 	struct mpconf *conf = priv;
 
-	mempool_destroy(conf->pool);
+	mempool_exit(&conf->pool);
 	kfree(conf->multipaths);
 	kfree(conf);
 }
diff --git a/drivers/md/md-multipath.h b/drivers/md/md-multipath.h
index 0adb941f485a..b3099e5fc4d7 100644
--- a/drivers/md/md-multipath.h
+++ b/drivers/md/md-multipath.h
@@ -13,7 +13,7 @@ struct mpconf {
 	spinlock_t		device_lock;
 	struct list_head	retry_list;
 
-	mempool_t		*pool;
+	mempool_t		pool;
 };
 
 /*
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3bea45e8ccff..fc692b7128bb 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -193,10 +193,10 @@ struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 {
 	struct bio *b;
 
-	if (!mddev || !mddev->bio_set)
+	if (!mddev || !bioset_initialized(&mddev->bio_set))
 		return bio_alloc(gfp_mask, nr_iovecs);
 
-	b = bio_alloc_bioset(gfp_mask, nr_iovecs, mddev->bio_set);
+	b = bio_alloc_bioset(gfp_mask, nr_iovecs, &mddev->bio_set);
 	if (!b)
 		return NULL;
 	return b;
@@ -205,10 +205,10 @@ EXPORT_SYMBOL_GPL(bio_alloc_mddev);
 
 static struct bio *md_bio_alloc_sync(struct mddev *mddev)
 {
-	if (!mddev || !mddev->sync_set)
+	if (!mddev || !bioset_initialized(&mddev->sync_set))
 		return bio_alloc(GFP_NOIO, 1);
 
-	return bio_alloc_bioset(GFP_NOIO, 1, mddev->sync_set);
+	return bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
 }
 
 /*
@@ -510,7 +510,10 @@ static void mddev_delayed_delete(struct work_struct *ws);
 
 static void mddev_put(struct mddev *mddev)
 {
-	struct bio_set *bs = NULL, *sync_bs = NULL;
+	struct bio_set bs, sync_bs;
+
+	memset(&bs, 0, sizeof(bs));
+	memset(&sync_bs, 0, sizeof(sync_bs));
 
 	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
 		return;
@@ -521,8 +524,8 @@ static void mddev_put(struct mddev *mddev)
 		list_del_init(&mddev->all_mddevs);
 		bs = mddev->bio_set;
 		sync_bs = mddev->sync_set;
-		mddev->bio_set = NULL;
-		mddev->sync_set = NULL;
+		memset(&mddev->bio_set, 0, sizeof(mddev->bio_set));
+		memset(&mddev->sync_set, 0, sizeof(mddev->sync_set));
 		if (mddev->gendisk) {
 			/* We did a probe so need to clean up.  Call
 			 * queue_work inside the spinlock so that
@@ -535,10 +538,8 @@ static void mddev_put(struct mddev *mddev)
 			kfree(mddev);
 	}
 	spin_unlock(&all_mddevs_lock);
-	if (bs)
-		bioset_free(bs);
-	if (sync_bs)
-		bioset_free(sync_bs);
+	bioset_exit(&bs);
+	bioset_exit(&sync_bs);
 }
 
 static void md_safemode_timeout(struct timer_list *t);
@@ -2123,7 +2124,7 @@ int md_integrity_register(struct mddev *mddev)
 			       bdev_get_integrity(reference->bdev));
 
 	pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
-	if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) {
+	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) {
 		pr_err("md: failed to create integrity pool for %s\n",
 		       mdname(mddev));
 		return -EINVAL;
@@ -5497,17 +5498,15 @@ int md_run(struct mddev *mddev)
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	}
 
-	if (mddev->bio_set == NULL) {
-		mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-		if (!mddev->bio_set)
-			return -ENOMEM;
+	if (!bioset_initialized(&mddev->bio_set)) {
+		err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+		if (err)
+			return err;
 	}
-	if (mddev->sync_set == NULL) {
-		mddev->sync_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-		if (!mddev->sync_set) {
-			err = -ENOMEM;
+	if (!bioset_initialized(&mddev->sync_set)) {
+		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+		if (err)
 			goto abort;
-		}
 	}
 
 	spin_lock(&pers_lock);
@@ -5668,14 +5667,8 @@ int md_run(struct mddev *mddev)
 	return 0;
 
 abort:
-	if (mddev->bio_set) {
-		bioset_free(mddev->bio_set);
-		mddev->bio_set = NULL;
-	}
-	if (mddev->sync_set) {
-		bioset_free(mddev->sync_set);
-		mddev->sync_set = NULL;
-	}
+	bioset_exit(&mddev->bio_set);
+	bioset_exit(&mddev->sync_set);
 
 	return err;
 }
@@ -5888,14 +5881,8 @@ void md_stop(struct mddev *mddev)
 	 * This is called from dm-raid
 	 */
 	__md_stop(mddev);
-	if (mddev->bio_set) {
-		bioset_free(mddev->bio_set);
-		mddev->bio_set = NULL;
-	}
-	if (mddev->sync_set) {
-		bioset_free(mddev->sync_set);
-		mddev->sync_set = NULL;
-	}
+	bioset_exit(&mddev->bio_set);
+	bioset_exit(&mddev->sync_set);
 }
 
 EXPORT_SYMBOL_GPL(md_stop);
@@ -9256,8 +9243,10 @@ void md_reload_sb(struct mddev *mddev, int nr)
 	check_sb_changes(mddev, rdev);
 
 	/* Read all rdev's to update recovery_offset */
-	rdev_for_each_rcu(rdev, mddev)
-		read_rdev(mddev, rdev);
+	rdev_for_each_rcu(rdev, mddev) {
+		if (!test_bit(Faulty, &rdev->flags))
+			read_rdev(mddev, rdev);
+	}
 }
 EXPORT_SYMBOL(md_reload_sb);
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index fbc925cce810..3507cab22cb6 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -452,8 +452,8 @@ struct mddev {
 
 	struct attribute_group		*to_remove;
 
-	struct bio_set			*bio_set;
-	struct bio_set			*sync_set; /* for sync operations like
+	struct bio_set			bio_set;
+	struct bio_set			sync_set; /* for sync operations like
 						   * metadata and bitmap writes
 						   */
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 584c10347267..65ae47a02218 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -479,7 +479,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 	if (bio_end_sector(bio) > zone->zone_end) {
 		struct bio *split = bio_split(bio,
 			zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
-			mddev->bio_set);
+			&mddev->bio_set);
 		bio_chain(split, bio);
 		generic_make_request(bio);
 		bio = split;
@@ -582,7 +582,8 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 	sector = bio_sector;
 
 	if (sectors < bio_sectors(bio)) {
-		struct bio *split = bio_split(bio, sectors, GFP_NOIO, mddev->bio_set);
+		struct bio *split = bio_split(bio, sectors, GFP_NOIO,
+					      &mddev->bio_set);
 		bio_chain(split, bio);
 		generic_make_request(bio);
 		bio = split;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e2943fb74056..bad28520719b 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -221,7 +221,7 @@ static void free_r1bio(struct r1bio *r1_bio)
 	struct r1conf *conf = r1_bio->mddev->private;
 
 	put_all_bios(conf, r1_bio);
-	mempool_free(r1_bio, conf->r1bio_pool);
+	mempool_free(r1_bio, &conf->r1bio_pool);
 }
 
 static void put_buf(struct r1bio *r1_bio)
@@ -236,7 +236,7 @@ static void put_buf(struct r1bio *r1_bio)
 			rdev_dec_pending(conf->mirrors[i].rdev, r1_bio->mddev);
 	}
 
-	mempool_free(r1_bio, conf->r1buf_pool);
+	mempool_free(r1_bio, &conf->r1buf_pool);
 
 	lower_barrier(conf, sect);
 }
@@ -854,7 +854,7 @@ static void flush_pending_writes(struct r1conf *conf)
  *    there is no normal IO happeing.  It must arrange to call
  *    lower_barrier when the particular background IO completes.
  */
-static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
+static sector_t raise_barrier(struct r1conf *conf, sector_t sector_nr)
 {
 	int idx = sector_to_idx(sector_nr);
 
@@ -885,13 +885,23 @@ static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
 	 *    max resync count which allowed on current I/O barrier bucket.
 	 */
 	wait_event_lock_irq(conf->wait_barrier,
-			    !conf->array_frozen &&
+			    (!conf->array_frozen &&
 			     !atomic_read(&conf->nr_pending[idx]) &&
-			     atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH,
+			     atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH) ||
+				test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery),
 			    conf->resync_lock);
 
+	if (test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
+		atomic_dec(&conf->barrier[idx]);
+		spin_unlock_irq(&conf->resync_lock);
+		wake_up(&conf->wait_barrier);
+		return -EINTR;
+	}
+
 	atomic_inc(&conf->nr_sync_pending);
 	spin_unlock_irq(&conf->resync_lock);
+
+	return 0;
 }
 
 static void lower_barrier(struct r1conf *conf, sector_t sector_nr)
@@ -1092,6 +1102,8 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
 		goto skip_copy;
 	}
 
+	behind_bio->bi_write_hint = bio->bi_write_hint;
+
 	while (i < vcnt && size) {
 		struct page *page;
 		int len = min_t(int, PAGE_SIZE, size);
@@ -1166,7 +1178,7 @@ alloc_r1bio(struct mddev *mddev, struct bio *bio)
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 
-	r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+	r1_bio = mempool_alloc(&conf->r1bio_pool, GFP_NOIO);
 	/* Ensure no bio records IO_BLOCKED */
 	memset(r1_bio->bios, 0, conf->raid_disks * sizeof(r1_bio->bios[0]));
 	init_r1bio(r1_bio, mddev, bio);
@@ -1256,7 +1268,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
-					      gfp, conf->bio_split);
+					      gfp, &conf->bio_split);
 		bio_chain(split, bio);
 		generic_make_request(bio);
 		bio = split;
@@ -1266,7 +1278,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 
 	r1_bio->read_disk = rdisk;
 
-	read_bio = bio_clone_fast(bio, gfp, mddev->bio_set);
+	read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
 
 	r1_bio->bios[rdisk] = read_bio;
 
@@ -1427,7 +1439,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
-					      GFP_NOIO, conf->bio_split);
+					      GFP_NOIO, &conf->bio_split);
 		bio_chain(split, bio);
 		generic_make_request(bio);
 		bio = split;
@@ -1467,9 +1479,9 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 		if (r1_bio->behind_master_bio)
 			mbio = bio_clone_fast(r1_bio->behind_master_bio,
-					      GFP_NOIO, mddev->bio_set);
+					      GFP_NOIO, &mddev->bio_set);
 		else
-			mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+			mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
 
 		if (r1_bio->behind_master_bio) {
 			if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
@@ -1645,8 +1657,7 @@ static void close_sync(struct r1conf *conf)
 		_allow_barrier(conf, idx);
 	}
 
-	mempool_destroy(conf->r1buf_pool);
-	conf->r1buf_pool = NULL;
+	mempool_exit(&conf->r1buf_pool);
 }
 
 static int raid1_spare_active(struct mddev *mddev)
@@ -2336,10 +2347,10 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
 			wbio = bio_clone_fast(r1_bio->behind_master_bio,
 					      GFP_NOIO,
-					      mddev->bio_set);
+					      &mddev->bio_set);
 		} else {
 			wbio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO,
-					      mddev->bio_set);
+					      &mddev->bio_set);
 		}
 
 		bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
@@ -2552,17 +2563,15 @@ static int init_resync(struct r1conf *conf)
 	int buffs;
 
 	buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
-	BUG_ON(conf->r1buf_pool);
-	conf->r1buf_pool = mempool_create(buffs, r1buf_pool_alloc, r1buf_pool_free,
-					  conf->poolinfo);
-	if (!conf->r1buf_pool)
-		return -ENOMEM;
-	return 0;
+	BUG_ON(mempool_initialized(&conf->r1buf_pool));
+
+	return mempool_init(&conf->r1buf_pool, buffs, r1buf_pool_alloc,
+			    r1buf_pool_free, conf->poolinfo);
 }
 
 static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
 {
-	struct r1bio *r1bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
+	struct r1bio *r1bio = mempool_alloc(&conf->r1buf_pool, GFP_NOIO);
 	struct resync_pages *rps;
 	struct bio *bio;
 	int i;
@@ -2605,7 +2614,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	int idx = sector_to_idx(sector_nr);
 	int page_idx = 0;
 
-	if (!conf->r1buf_pool)
+	if (!mempool_initialized(&conf->r1buf_pool))
 		if (init_resync(conf))
 			return 0;
 
@@ -2662,9 +2671,12 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 	bitmap_cond_end_sync(mddev->bitmap, sector_nr,
 		mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
-	r1_bio = raid1_alloc_init_r1buf(conf);
 
-	raise_barrier(conf, sector_nr);
+
+	if (raise_barrier(conf, sector_nr))
+		return 0;
+
+	r1_bio = raid1_alloc_init_r1buf(conf);
 
 	rcu_read_lock();
 	/*
@@ -2938,14 +2950,13 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	if (!conf->poolinfo)
 		goto abort;
 	conf->poolinfo->raid_disks = mddev->raid_disks * 2;
-	conf->r1bio_pool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
-					  r1bio_pool_free,
-					  conf->poolinfo);
-	if (!conf->r1bio_pool)
+	err = mempool_init(&conf->r1bio_pool, NR_RAID1_BIOS, r1bio_pool_alloc,
+			   r1bio_pool_free, conf->poolinfo);
+	if (err)
 		goto abort;
 
-	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
-	if (!conf->bio_split)
+	err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+	if (err)
 		goto abort;
 
 	conf->poolinfo->mddev = mddev;
@@ -3018,7 +3029,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
  abort:
 	if (conf) {
-		mempool_destroy(conf->r1bio_pool);
+		mempool_exit(&conf->r1bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
 		kfree(conf->poolinfo);
@@ -3026,8 +3037,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 		kfree(conf->nr_waiting);
 		kfree(conf->nr_queued);
 		kfree(conf->barrier);
-		if (conf->bio_split)
-			bioset_free(conf->bio_split);
+		bioset_exit(&conf->bio_split);
 		kfree(conf);
 	}
 	return ERR_PTR(err);
@@ -3129,7 +3139,7 @@ static void raid1_free(struct mddev *mddev, void *priv)
 {
 	struct r1conf *conf = priv;
 
-	mempool_destroy(conf->r1bio_pool);
+	mempool_exit(&conf->r1bio_pool);
 	kfree(conf->mirrors);
 	safe_put_page(conf->tmppage);
 	kfree(conf->poolinfo);
@@ -3137,8 +3147,7 @@ static void raid1_free(struct mddev *mddev, void *priv)
 	kfree(conf->nr_waiting);
 	kfree(conf->nr_queued);
 	kfree(conf->barrier);
-	if (conf->bio_split)
-		bioset_free(conf->bio_split);
+	bioset_exit(&conf->bio_split);
 	kfree(conf);
 }
 
@@ -3184,13 +3193,17 @@ static int raid1_reshape(struct mddev *mddev)
 	 * At the same time, we "pack" the devices so that all the missing
 	 * devices have the higher raid_disk numbers.
 	 */
-	mempool_t *newpool, *oldpool;
+	mempool_t newpool, oldpool;
 	struct pool_info *newpoolinfo;
 	struct raid1_info *newmirrors;
 	struct r1conf *conf = mddev->private;
 	int cnt, raid_disks;
 	unsigned long flags;
 	int d, d2;
+	int ret;
+
+	memset(&newpool, 0, sizeof(newpool));
+	memset(&oldpool, 0, sizeof(oldpool));
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
@@ -3222,17 +3235,17 @@ static int raid1_reshape(struct mddev *mddev)
 	newpoolinfo->mddev = mddev;
 	newpoolinfo->raid_disks = raid_disks * 2;
 
-	newpool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
-				 r1bio_pool_free, newpoolinfo);
-	if (!newpool) {
+	ret = mempool_init(&newpool, NR_RAID1_BIOS, r1bio_pool_alloc,
+			   r1bio_pool_free, newpoolinfo);
+	if (ret) {
 		kfree(newpoolinfo);
-		return -ENOMEM;
+		return ret;
 	}
 	newmirrors = kzalloc(sizeof(struct raid1_info) * raid_disks * 2,
 			     GFP_KERNEL);
 	if (!newmirrors) {
 		kfree(newpoolinfo);
-		mempool_destroy(newpool);
+		mempool_exit(&newpool);
 		return -ENOMEM;
 	}
 
@@ -3272,7 +3285,7 @@ static int raid1_reshape(struct mddev *mddev)
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 
-	mempool_destroy(oldpool);
+	mempool_exit(&oldpool);
 	return 0;
 }
 
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index eb84bc68e2fd..e7ccad898736 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -118,10 +118,10 @@ struct r1conf {
 	 * mempools - it changes when the array grows or shrinks
 	 */
 	struct pool_info	*poolinfo;
-	mempool_t		*r1bio_pool;
-	mempool_t		*r1buf_pool;
+	mempool_t		r1bio_pool;
+	mempool_t		r1buf_pool;
 
-	struct bio_set		*bio_split;
+	struct bio_set		bio_split;
 
 	/* temporary buffer to synchronous IO when attempting to repair
 	 * a read error.
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3c60774c8430..37d4b236b81b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -291,14 +291,14 @@ static void free_r10bio(struct r10bio *r10_bio)
 	struct r10conf *conf = r10_bio->mddev->private;
 
 	put_all_bios(conf, r10_bio);
-	mempool_free(r10_bio, conf->r10bio_pool);
+	mempool_free(r10_bio, &conf->r10bio_pool);
 }
 
 static void put_buf(struct r10bio *r10_bio)
 {
 	struct r10conf *conf = r10_bio->mddev->private;
 
-	mempool_free(r10_bio, conf->r10buf_pool);
+	mempool_free(r10_bio, &conf->r10buf_pool);
 
 	lower_barrier(conf);
 }
@@ -1204,7 +1204,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 				   (unsigned long long)r10_bio->sector);
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
-					      gfp, conf->bio_split);
+					      gfp, &conf->bio_split);
 		bio_chain(split, bio);
 		generic_make_request(bio);
 		bio = split;
@@ -1213,7 +1213,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	}
 	slot = r10_bio->read_slot;
 
-	read_bio = bio_clone_fast(bio, gfp, mddev->bio_set);
+	read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
 
 	r10_bio->devs[slot].bio = read_bio;
 	r10_bio->devs[slot].rdev = rdev;
@@ -1261,7 +1261,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	} else
 		rdev = conf->mirrors[devnum].rdev;
 
-	mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+	mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
 	if (replacement)
 		r10_bio->devs[n_copy].repl_bio = mbio;
 	else
@@ -1509,7 +1509,7 @@ retry_write:
 
 	if (r10_bio->sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, r10_bio->sectors,
-					      GFP_NOIO, conf->bio_split);
+					      GFP_NOIO, &conf->bio_split);
 		bio_chain(split, bio);
 		generic_make_request(bio);
 		bio = split;
@@ -1533,7 +1533,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 	struct r10conf *conf = mddev->private;
 	struct r10bio *r10_bio;
 
-	r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
+	r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
 
 	r10_bio->master_bio = bio;
 	r10_bio->sectors = sectors;
@@ -1732,8 +1732,7 @@ static void close_sync(struct r10conf *conf)
 	wait_barrier(conf);
 	allow_barrier(conf);
 
-	mempool_destroy(conf->r10buf_pool);
-	conf->r10buf_pool = NULL;
+	mempool_exit(&conf->r10buf_pool);
 }
 
 static int raid10_spare_active(struct mddev *mddev)
@@ -2583,7 +2582,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 		if (sectors > sect_to_write)
 			sectors = sect_to_write;
 		/* Write at 'sector' for 'sectors' */
-		wbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+		wbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
 		bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
 		wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
 		wbio->bi_iter.bi_sector = wsector +
@@ -2816,25 +2815,25 @@ static void raid10d(struct md_thread *thread)
 
 static int init_resync(struct r10conf *conf)
 {
-	int buffs;
-	int i;
+	int ret, buffs, i;
 
 	buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
-	BUG_ON(conf->r10buf_pool);
+	BUG_ON(mempool_initialized(&conf->r10buf_pool));
 	conf->have_replacement = 0;
 	for (i = 0; i < conf->geo.raid_disks; i++)
 		if (conf->mirrors[i].replacement)
 			conf->have_replacement = 1;
-	conf->r10buf_pool = mempool_create(buffs, r10buf_pool_alloc, r10buf_pool_free, conf);
-	if (!conf->r10buf_pool)
-		return -ENOMEM;
+	ret = mempool_init(&conf->r10buf_pool, buffs,
+			   r10buf_pool_alloc, r10buf_pool_free, conf);
+	if (ret)
+		return ret;
 	conf->next_resync = 0;
 	return 0;
 }
 
 static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf)
 {
-	struct r10bio *r10bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+	struct r10bio *r10bio = mempool_alloc(&conf->r10buf_pool, GFP_NOIO);
 	struct rsync_pages *rp;
 	struct bio *bio;
 	int nalloc;
@@ -2945,7 +2944,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 	sector_t chunk_mask = conf->geo.chunk_mask;
 	int page_idx = 0;
 
-	if (!conf->r10buf_pool)
+	if (!mempool_initialized(&conf->r10buf_pool))
 		if (init_resync(conf))
 			return 0;
 
@@ -3699,13 +3698,13 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 
 	conf->geo = geo;
 	conf->copies = copies;
-	conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
-					   r10bio_pool_free, conf);
-	if (!conf->r10bio_pool)
+	err = mempool_init(&conf->r10bio_pool, NR_RAID10_BIOS, r10bio_pool_alloc,
+			   r10bio_pool_free, conf);
+	if (err)
 		goto out;
 
-	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
-	if (!conf->bio_split)
+	err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+	if (err)
 		goto out;
 
 	calc_sectors(conf, mddev->dev_sectors);
@@ -3733,6 +3732,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	init_waitqueue_head(&conf->wait_barrier);
 	atomic_set(&conf->nr_pending, 0);
 
+	err = -ENOMEM;
 	conf->thread = md_register_thread(raid10d, mddev, "raid10");
 	if (!conf->thread)
 		goto out;
@@ -3742,11 +3742,10 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 
  out:
 	if (conf) {
-		mempool_destroy(conf->r10bio_pool);
+		mempool_exit(&conf->r10bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
-		if (conf->bio_split)
-			bioset_free(conf->bio_split);
+		bioset_exit(&conf->bio_split);
 		kfree(conf);
 	}
 	return ERR_PTR(err);
@@ -3953,7 +3952,7 @@ static int raid10_run(struct mddev *mddev)
 
 out_free_conf:
 	md_unregister_thread(&mddev->thread);
-	mempool_destroy(conf->r10bio_pool);
+	mempool_exit(&conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf);
@@ -3966,13 +3965,12 @@ static void raid10_free(struct mddev *mddev, void *priv)
 {
 	struct r10conf *conf = priv;
 
-	mempool_destroy(conf->r10bio_pool);
+	mempool_exit(&conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf->mirrors_old);
 	kfree(conf->mirrors_new);
-	if (conf->bio_split)
-		bioset_free(conf->bio_split);
+	bioset_exit(&conf->bio_split);
 	kfree(conf);
 }
 
@@ -4543,7 +4541,7 @@ read_more:
 		 * on all the target devices.
 		 */
 		// FIXME
-		mempool_free(r10_bio, conf->r10buf_pool);
+		mempool_free(r10_bio, &conf->r10buf_pool);
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		return sectors_done;
 	}
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index e2e8840de9bf..d3eaaf3eb1bc 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -93,10 +93,10 @@ struct r10conf {
 						   */
 	wait_queue_head_t	wait_barrier;
 
-	mempool_t		*r10bio_pool;
-	mempool_t		*r10buf_pool;
+	mempool_t		r10bio_pool;
+	mempool_t		r10buf_pool;
 	struct page		*tmppage;
-	struct bio_set		*bio_split;
+	struct bio_set		bio_split;
 
 	/* When taking over an array from a different personality, we store
 	 * the new thread here until we fully activate the array.
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 3c65f52b68f5..2b775abf377b 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -125,9 +125,9 @@ struct r5l_log {
 	struct list_head no_mem_stripes;   /* pending stripes, -ENOMEM */
 
 	struct kmem_cache *io_kc;
-	mempool_t *io_pool;
-	struct bio_set *bs;
-	mempool_t *meta_pool;
+	mempool_t io_pool;
+	struct bio_set bs;
+	mempool_t meta_pool;
 
 	struct md_thread *reclaim_thread;
 	unsigned long reclaim_target;	/* number of space that need to be
@@ -579,7 +579,7 @@ static void r5l_log_endio(struct bio *bio)
 		md_error(log->rdev->mddev, log->rdev);
 
 	bio_put(bio);
-	mempool_free(io->meta_page, log->meta_pool);
+	mempool_free(io->meta_page, &log->meta_pool);
 
 	spin_lock_irqsave(&log->io_list_lock, flags);
 	__r5l_set_io_unit_state(io, IO_UNIT_IO_END);
@@ -748,7 +748,7 @@ static void r5l_submit_current_io(struct r5l_log *log)
 
 static struct bio *r5l_bio_alloc(struct r5l_log *log)
 {
-	struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, log->bs);
+	struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, &log->bs);
 
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	bio_set_dev(bio, log->rdev->bdev);
@@ -780,7 +780,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
 	struct r5l_io_unit *io;
 	struct r5l_meta_block *block;
 
-	io = mempool_alloc(log->io_pool, GFP_ATOMIC);
+	io = mempool_alloc(&log->io_pool, GFP_ATOMIC);
 	if (!io)
 		return NULL;
 	memset(io, 0, sizeof(*io));
@@ -791,7 +791,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
 	bio_list_init(&io->flush_barriers);
 	io->state = IO_UNIT_RUNNING;
 
-	io->meta_page = mempool_alloc(log->meta_pool, GFP_NOIO);
+	io->meta_page = mempool_alloc(&log->meta_pool, GFP_NOIO);
 	block = page_address(io->meta_page);
 	clear_page(block);
 	block->magic = cpu_to_le32(R5LOG_MAGIC);
@@ -1223,7 +1223,7 @@ static bool r5l_complete_finished_ios(struct r5l_log *log)
 		log->next_checkpoint = io->log_start;
 
 		list_del(&io->log_sibling);
-		mempool_free(io, log->io_pool);
+		mempool_free(io, &log->io_pool);
 		r5l_run_no_mem_stripe(log);
 
 		found = true;
@@ -1647,7 +1647,7 @@ static int r5l_recovery_allocate_ra_pool(struct r5l_log *log,
 {
 	struct page *page;
 
-	ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, log->bs);
+	ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, &log->bs);
 	if (!ctx->ra_bio)
 		return -ENOMEM;
 
@@ -3066,6 +3066,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 	struct request_queue *q = bdev_get_queue(rdev->bdev);
 	struct r5l_log *log;
 	char b[BDEVNAME_SIZE];
+	int ret;
 
 	pr_debug("md/raid:%s: using device %s as journal\n",
 		 mdname(conf->mddev), bdevname(rdev->bdev, b));
@@ -3111,16 +3112,16 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 	if (!log->io_kc)
 		goto io_kc;
 
-	log->io_pool = mempool_create_slab_pool(R5L_POOL_SIZE, log->io_kc);
-	if (!log->io_pool)
+	ret = mempool_init_slab_pool(&log->io_pool, R5L_POOL_SIZE, log->io_kc);
+	if (ret)
 		goto io_pool;
 
-	log->bs = bioset_create(R5L_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-	if (!log->bs)
+	ret = bioset_init(&log->bs, R5L_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	if (ret)
 		goto io_bs;
 
-	log->meta_pool = mempool_create_page_pool(R5L_POOL_SIZE, 0);
-	if (!log->meta_pool)
+	ret = mempool_init_page_pool(&log->meta_pool, R5L_POOL_SIZE, 0);
+	if (ret)
 		goto out_mempool;
 
 	spin_lock_init(&log->tree_lock);
@@ -3155,11 +3156,11 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 	rcu_assign_pointer(conf->log, NULL);
 	md_unregister_thread(&log->reclaim_thread);
 reclaim_thread:
-	mempool_destroy(log->meta_pool);
+	mempool_exit(&log->meta_pool);
 out_mempool:
-	bioset_free(log->bs);
+	bioset_exit(&log->bs);
 io_bs:
-	mempool_destroy(log->io_pool);
+	mempool_exit(&log->io_pool);
 io_pool:
 	kmem_cache_destroy(log->io_kc);
 io_kc:
@@ -3178,9 +3179,9 @@ void r5l_exit_log(struct r5conf *conf)
 	wake_up(&conf->mddev->sb_wait);
 	flush_work(&log->disable_writeback_work);
 	md_unregister_thread(&log->reclaim_thread);
-	mempool_destroy(log->meta_pool);
-	bioset_free(log->bs);
-	mempool_destroy(log->io_pool);
+	mempool_exit(&log->meta_pool);
+	bioset_exit(&log->bs);
+	mempool_exit(&log->io_pool);
 	kmem_cache_destroy(log->io_kc);
 	kfree(log);
 }
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 42890a08375b..3a7c36326589 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -105,9 +105,9 @@ struct ppl_conf {
 	atomic64_t seq;		/* current log write sequence number */
 
 	struct kmem_cache *io_kc;
-	mempool_t *io_pool;
-	struct bio_set *bs;
-	struct bio_set *flush_bs;
+	mempool_t io_pool;
+	struct bio_set bs;
+	struct bio_set flush_bs;
 
 	/* used only for recovery */
 	int recovered_entries;
@@ -244,7 +244,7 @@ static struct ppl_io_unit *ppl_new_iounit(struct ppl_log *log,
 	struct ppl_header *pplhdr;
 	struct page *header_page;
 
-	io = mempool_alloc(ppl_conf->io_pool, GFP_NOWAIT);
+	io = mempool_alloc(&ppl_conf->io_pool, GFP_NOWAIT);
 	if (!io)
 		return NULL;
 
@@ -503,7 +503,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io)
 			struct bio *prev = bio;
 
 			bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES,
-					       ppl_conf->bs);
+					       &ppl_conf->bs);
 			bio->bi_opf = prev->bi_opf;
 			bio_copy_dev(bio, prev);
 			bio->bi_iter.bi_sector = bio_end_sector(prev);
@@ -570,7 +570,7 @@ static void ppl_io_unit_finished(struct ppl_io_unit *io)
 	list_del(&io->log_sibling);
 	spin_unlock(&log->io_list_lock);
 
-	mempool_free(io, ppl_conf->io_pool);
+	mempool_free(io, &ppl_conf->io_pool);
 
 	spin_lock(&ppl_conf->no_mem_stripes_lock);
 	if (!list_empty(&ppl_conf->no_mem_stripes)) {
@@ -642,7 +642,7 @@ static void ppl_do_flush(struct ppl_io_unit *io)
 			struct bio *bio;
 			char b[BDEVNAME_SIZE];
 
-			bio = bio_alloc_bioset(GFP_NOIO, 0, ppl_conf->flush_bs);
+			bio = bio_alloc_bioset(GFP_NOIO, 0, &ppl_conf->flush_bs);
 			bio_set_dev(bio, bdev);
 			bio->bi_private = io;
 			bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
@@ -1246,11 +1246,9 @@ static void __ppl_exit_log(struct ppl_conf *ppl_conf)
 
 	kfree(ppl_conf->child_logs);
 
-	if (ppl_conf->bs)
-		bioset_free(ppl_conf->bs);
-	if (ppl_conf->flush_bs)
-		bioset_free(ppl_conf->flush_bs);
-	mempool_destroy(ppl_conf->io_pool);
+	bioset_exit(&ppl_conf->bs);
+	bioset_exit(&ppl_conf->flush_bs);
+	mempool_exit(&ppl_conf->io_pool);
 	kmem_cache_destroy(ppl_conf->io_kc);
 
 	kfree(ppl_conf);
@@ -1387,24 +1385,18 @@ int ppl_init_log(struct r5conf *conf)
 		goto err;
 	}
 
-	ppl_conf->io_pool = mempool_create(conf->raid_disks, ppl_io_pool_alloc,
-					   ppl_io_pool_free, ppl_conf->io_kc);
-	if (!ppl_conf->io_pool) {
-		ret = -ENOMEM;
+	ret = mempool_init(&ppl_conf->io_pool, conf->raid_disks, ppl_io_pool_alloc,
+			   ppl_io_pool_free, ppl_conf->io_kc);
+	if (ret)
 		goto err;
-	}
 
-	ppl_conf->bs = bioset_create(conf->raid_disks, 0, BIOSET_NEED_BVECS);
-	if (!ppl_conf->bs) {
-		ret = -ENOMEM;
+	ret = bioset_init(&ppl_conf->bs, conf->raid_disks, 0, BIOSET_NEED_BVECS);
+	if (ret)
 		goto err;
-	}
 
-	ppl_conf->flush_bs = bioset_create(conf->raid_disks, 0, 0);
-	if (!ppl_conf->flush_bs) {
-		ret = -ENOMEM;
+	ret = bioset_init(&ppl_conf->flush_bs, conf->raid_disks, 0, 0);
+	if (ret)
 		goto err;
-	}
 
 	ppl_conf->count = conf->raid_disks;
 	ppl_conf->child_logs = kcalloc(ppl_conf->count, sizeof(struct ppl_log),
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index be117d0a65a8..a2e64989b01f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5192,7 +5192,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 	/*
 	 * use bio_clone_fast to make a copy of the bio
 	 */
-	align_bi = bio_clone_fast(raid_bio, GFP_NOIO, mddev->bio_set);
+	align_bi = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
 	if (!align_bi)
 		return 0;
 	/*
@@ -5277,7 +5277,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
 
 	if (sectors < bio_sectors(raid_bio)) {
 		struct r5conf *conf = mddev->private;
-		split = bio_split(raid_bio, sectors, GFP_NOIO, conf->bio_split);
+		split = bio_split(raid_bio, sectors, GFP_NOIO, &conf->bio_split);
 		bio_chain(split, raid_bio);
 		generic_make_request(raid_bio);
 		raid_bio = split;
@@ -6773,8 +6773,7 @@ static void free_conf(struct r5conf *conf)
 		if (conf->disks[i].extra_page)
 			put_page(conf->disks[i].extra_page);
 	kfree(conf->disks);
-	if (conf->bio_split)
-		bioset_free(conf->bio_split);
+	bioset_exit(&conf->bio_split);
 	kfree(conf->stripe_hashtbl);
 	kfree(conf->pending_data);
 	kfree(conf);
@@ -6853,6 +6852,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	int i;
 	int group_cnt, worker_cnt_per_group;
 	struct r5worker_group *new_group;
+	int ret;
 
 	if (mddev->new_level != 5
 	    && mddev->new_level != 4
@@ -6950,8 +6950,8 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 			goto abort;
 	}
 
-	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
-	if (!conf->bio_split)
+	ret = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+	if (ret)
 		goto abort;
 	conf->mddev = mddev;
 
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 3f8da26032ac..72e75ba6abf0 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -669,7 +669,7 @@ struct r5conf {
 	int			pool_size; /* number of disks in stripeheads in pool */
 	spinlock_t		device_lock;
 	struct disk_info	*disks;
-	struct bio_set		*bio_split;
+	struct bio_set		bio_split;
 
 	/* When taking over an array from a different personality, we store
 	 * the new thread here until we fully activate the array.
diff --git a/drivers/media/i2c/saa7115.c b/drivers/media/i2c/saa7115.c
index e216cd768409..b07114b5efb2 100644
--- a/drivers/media/i2c/saa7115.c
+++ b/drivers/media/i2c/saa7115.c
@@ -20,7 +20,7 @@
 //
 // VBI support (2004) and cleanups (2005) by Hans Verkuil <hverkuil@xs4all.nl>
 //
-// Copyright (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
 //	SAA7111, SAA7113 and SAA7118 support
 
 #include "saa711x_regs.h"
diff --git a/drivers/media/i2c/saa711x_regs.h b/drivers/media/i2c/saa711x_regs.h
index a50d480e101a..44fabe08234d 100644
--- a/drivers/media/i2c/saa711x_regs.h
+++ b/drivers/media/i2c/saa711x_regs.h
@@ -2,7 +2,7 @@
  * SPDX-License-Identifier: GPL-2.0+
  * saa711x - Philips SAA711x video decoder register specifications
  *
- * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 #define R_00_CHIP_VERSION                             0x00
diff --git a/drivers/media/i2c/tda1997x.c b/drivers/media/i2c/tda1997x.c
index 3021913c28fa..33d7fcf541fc 100644
--- a/drivers/media/i2c/tda1997x.c
+++ b/drivers/media/i2c/tda1997x.c
@@ -2444,7 +2444,7 @@ static int tda1997x_pcm_startup(struct snd_pcm_substream *substream,
 				struct snd_soc_dai *dai)
 {
 	struct tda1997x_state *state = snd_soc_dai_get_drvdata(dai);
-	struct snd_soc_codec *codec = dai->codec;
+	struct snd_soc_component *component = dai->component;
 	struct snd_pcm_runtime *rtd = substream->runtime;
 	int rate, err;
 
@@ -2452,11 +2452,11 @@ static int tda1997x_pcm_startup(struct snd_pcm_substream *substream,
 	err = snd_pcm_hw_constraint_minmax(rtd, SNDRV_PCM_HW_PARAM_RATE,
 					   rate, rate);
 	if (err < 0) {
-		dev_err(codec->dev, "failed to constrain samplerate to %dHz\n",
+		dev_err(component->dev, "failed to constrain samplerate to %dHz\n",
 			rate);
 		return err;
 	}
-	dev_info(codec->dev, "set samplerate constraint to %dHz\n", rate);
+	dev_info(component->dev, "set samplerate constraint to %dHz\n", rate);
 
 	return 0;
 }
@@ -2479,20 +2479,22 @@ static struct snd_soc_dai_driver tda1997x_audio_dai = {
 	.ops = &tda1997x_dai_ops,
 };
 
-static int tda1997x_codec_probe(struct snd_soc_codec *codec)
+static int tda1997x_codec_probe(struct snd_soc_component *component)
 {
 	return 0;
 }
 
-static int tda1997x_codec_remove(struct snd_soc_codec *codec)
+static void tda1997x_codec_remove(struct snd_soc_component *component)
 {
-	return 0;
 }
 
-static struct snd_soc_codec_driver tda1997x_codec_driver = {
-	.probe = tda1997x_codec_probe,
-	.remove = tda1997x_codec_remove,
-	.reg_word_size = sizeof(u16),
+static struct snd_soc_component_driver tda1997x_codec_driver = {
+	.probe			= tda1997x_codec_probe,
+	.remove			= tda1997x_codec_remove,
+	.idle_bias_on		= 1,
+	.use_pmdown_time	= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
 };
 
 static int tda1997x_probe(struct i2c_client *client,
@@ -2737,7 +2739,7 @@ static int tda1997x_probe(struct i2c_client *client,
 		else
 			formats = SNDRV_PCM_FMTBIT_S16_LE;
 		tda1997x_audio_dai.capture.formats = formats;
-		ret = snd_soc_register_codec(&state->client->dev,
+		ret = devm_snd_soc_register_component(&state->client->dev,
 					     &tda1997x_codec_driver,
 					     &tda1997x_audio_dai, 1);
 		if (ret) {
@@ -2782,7 +2784,6 @@ static int tda1997x_remove(struct i2c_client *client)
 	struct tda1997x_platform_data *pdata = &state->pdata;
 
 	if (pdata->audout_format) {
-		snd_soc_unregister_codec(&client->dev);
 		mutex_destroy(&state->audio_lock);
 	}
 
diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c
index 1c5c61d829d6..9b4f21237810 100644
--- a/drivers/media/i2c/tda7432.c
+++ b/drivers/media/i2c/tda7432.c
@@ -8,7 +8,7 @@
  * Muting and tone control by Jonathan Isom <jisom@ematic.com>
  *
  * Copyright (c) 2000 Eric Sandeen <eric_sandeen@bigfoot.com>
- * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
  * This code is placed under the terms of the GNU General Public License
  * Based on tda9855.c by Steve VanDeBogart (vandebo@uclink.berkeley.edu)
  * Which was based on tda8425.c by Greg Alexander (c) 1998
diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index 2476d812f669..1734ed4ede33 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -2,7 +2,7 @@
 //
 // tvp5150 - Texas Instruments TVP5150A/AM1 and TVP5151 video decoder driver
 //
-// Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@kernel.org>
 
 #include <dt-bindings/media/tvp5150.h>
 #include <linux/i2c.h>
diff --git a/drivers/media/i2c/tvp5150_reg.h b/drivers/media/i2c/tvp5150_reg.h
index c43b7b844021..d3a764cae1a0 100644
--- a/drivers/media/i2c/tvp5150_reg.h
+++ b/drivers/media/i2c/tvp5150_reg.h
@@ -3,7 +3,7 @@
  *
  * tvp5150 - Texas Instruments TVP5150A/AM1 video decoder registers
  *
- * Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 #define TVP5150_VD_IN_SRC_SEL_1      0x00 /* Video input source selection #1 */
diff --git a/drivers/media/i2c/tvp7002.c b/drivers/media/i2c/tvp7002.c
index a26c1a3f7183..4599b7e28a8d 100644
--- a/drivers/media/i2c/tvp7002.c
+++ b/drivers/media/i2c/tvp7002.c
@@ -5,7 +5,7 @@
  * Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
  *
  * This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
  * the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
  * and the TVP7002 driver in the TI LSP 2.10.00.14. Revisions by
  * Muralidharan Karicheri and Snehaprabha Narnakaje (TI).
diff --git a/drivers/media/i2c/tvp7002_reg.h b/drivers/media/i2c/tvp7002_reg.h
index 3c8c8b0a6a4c..7f56ba689dfe 100644
--- a/drivers/media/i2c/tvp7002_reg.h
+++ b/drivers/media/i2c/tvp7002_reg.h
@@ -5,7 +5,7 @@
  * Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
  *
  * This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
  * the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
  * and the TVP7002 driver in the TI LSP 2.10.00.14
  *
diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c
index 67ac51eff15c..6b87a721dc49 100644
--- a/drivers/media/media-devnode.c
+++ b/drivers/media/media-devnode.c
@@ -4,7 +4,7 @@
  * Copyright (C) 2010 Nokia Corporation
  *
  * Based on drivers/media/video/v4l2_dev.c code authored by
- *	Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ *	Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
  *	Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
  *
  * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
diff --git a/drivers/media/pci/bt8xx/bttv-audio-hook.c b/drivers/media/pci/bt8xx/bttv-audio-hook.c
index 9f1f9169fb5b..346fc7f58839 100644
--- a/drivers/media/pci/bt8xx/bttv-audio-hook.c
+++ b/drivers/media/pci/bt8xx/bttv-audio-hook.c
@@ -1,7 +1,7 @@
 /*
  * Handlers for board audio hooks, splitted from bttv-cards
  *
- * Copyright (c) 2006 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
  * This code is placed under the terms of the GNU General Public License
  */
 
diff --git a/drivers/media/pci/bt8xx/bttv-audio-hook.h b/drivers/media/pci/bt8xx/bttv-audio-hook.h
index 159d07adeff8..be16a537a03a 100644
--- a/drivers/media/pci/bt8xx/bttv-audio-hook.h
+++ b/drivers/media/pci/bt8xx/bttv-audio-hook.h
@@ -1,7 +1,7 @@
 /*
  * Handlers for board audio hooks, splitted from bttv-cards
  *
- * Copyright (c) 2006 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
  * This code is placed under the terms of the GNU General Public License
  */
 
diff --git a/drivers/media/pci/bt8xx/bttv-cards.c b/drivers/media/pci/bt8xx/bttv-cards.c
index 1902732f90e1..2616243b2c49 100644
--- a/drivers/media/pci/bt8xx/bttv-cards.c
+++ b/drivers/media/pci/bt8xx/bttv-cards.c
@@ -2447,7 +2447,7 @@ struct tvcard bttv_tvcards[] = {
 	},
 		/* ---- card 0x88---------------------------------- */
 	[BTTV_BOARD_ACORP_Y878F] = {
-		/* Mauro Carvalho Chehab <mchehab@infradead.org> */
+		/* Mauro Carvalho Chehab <mchehab@kernel.org> */
 		.name		= "Acorp Y878F",
 		.video_inputs	= 3,
 		/* .audio_inputs= 1, */
@@ -2688,7 +2688,7 @@ struct tvcard bttv_tvcards[] = {
 	},
 	[BTTV_BOARD_ENLTV_FM_2] = {
 		/* Encore TV Tuner Pro ENL TV-FM-2
-		   Mauro Carvalho Chehab <mchehab@infradead.org */
+		   Mauro Carvalho Chehab <mchehab@kernel.org> */
 		.name           = "Encore ENL TV-FM-2",
 		.video_inputs   = 3,
 		/* .audio_inputs= 1, */
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index 707f57a9f940..de3f44b8dec6 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -13,7 +13,7 @@
     (c) 2005-2006 Nickolay V. Shmyrev <nshmyrev@yandex.ru>
 
     Fixes to be fully V4L2 compliant by
-    (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+    (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
 
     Cropping and overscan support
     Copyright (C) 2005, 2006 Michael H. Schimek <mschimek@gmx.at>
diff --git a/drivers/media/pci/bt8xx/bttv-i2c.c b/drivers/media/pci/bt8xx/bttv-i2c.c
index eccd1e3d717a..c76823eb399d 100644
--- a/drivers/media/pci/bt8xx/bttv-i2c.c
+++ b/drivers/media/pci/bt8xx/bttv-i2c.c
@@ -8,7 +8,7 @@
 			   & Marcus Metzler (mocm@thp.uni-koeln.de)
     (c) 1999-2003 Gerd Knorr <kraxel@bytesex.org>
 
-    (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+    (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
 	- Multituner support and i2c address binding
 
     This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/pci/cx23885/cx23885-input.c b/drivers/media/pci/cx23885/cx23885-input.c
index be49589a61d2..395ff9bba759 100644
--- a/drivers/media/pci/cx23885/cx23885-input.c
+++ b/drivers/media/pci/cx23885/cx23885-input.c
@@ -13,7 +13,7 @@
  *  Copyright (C) 2008 <srinivasa.deevi at conexant dot com>
  *  Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
  *		       Markus Rechberger <mrechberger@gmail.com>
- *		       Mauro Carvalho Chehab <mchehab@infradead.org>
+ *		       Mauro Carvalho Chehab <mchehab@kernel.org>
  *		       Sascha Sommer <saschasommer@freenet.de>
  *  Copyright (C) 2004, 2005 Chris Pascoe
  *  Copyright (C) 2003, 2004 Gerd Knorr
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index ab09bb55cf45..8a28fda703a2 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -4,7 +4,7 @@
  *
  *    (c) 2007 Trent Piepho <xyzzy@speakeasy.org>
  *    (c) 2005,2006 Ricardo Cerqueira <v4l@cerqueira.org>
- *    (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+ *    (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
  *    Based on a dummy cx88 module by Gerd Knorr <kraxel@bytesex.org>
  *    Based on dummy.c by Jaroslav Kysela <perex@perex.cz>
  *
@@ -103,7 +103,7 @@ MODULE_PARM_DESC(index, "Index value for cx88x capture interface(s).");
 
 MODULE_DESCRIPTION("ALSA driver module for cx2388x based TV cards");
 MODULE_AUTHOR("Ricardo Cerqueira");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(CX88_VERSION);
 
diff --git a/drivers/media/pci/cx88/cx88-blackbird.c b/drivers/media/pci/cx88/cx88-blackbird.c
index 0e0952e60795..7a4876cf9f08 100644
--- a/drivers/media/pci/cx88/cx88-blackbird.c
+++ b/drivers/media/pci/cx88/cx88-blackbird.c
@@ -5,7 +5,7 @@
  *    (c) 2004 Jelle Foks <jelle@foks.us>
  *    (c) 2004 Gerd Knorr <kraxel@bytesex.org>
  *
- *    (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ *    (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
  *        - video_ioctl2 conversion
  *
  *  Includes parts from the ivtv driver <http://sourceforge.net/projects/ivtv/>
diff --git a/drivers/media/pci/cx88/cx88-core.c b/drivers/media/pci/cx88/cx88-core.c
index 8bfa5b7ed91b..60988e95b637 100644
--- a/drivers/media/pci/cx88/cx88-core.c
+++ b/drivers/media/pci/cx88/cx88-core.c
@@ -4,7 +4,7 @@
  *
  * (c) 2003 Gerd Knorr <kraxel@bytesex.org> [SuSE Labs]
  *
- * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
  *     - Multituner support
  *     - video_ioctl2 conversion
  *     - PAL/M fixes
diff --git a/drivers/media/pci/cx88/cx88-i2c.c b/drivers/media/pci/cx88/cx88-i2c.c
index f7692775fb5a..99f88a05a7c9 100644
--- a/drivers/media/pci/cx88/cx88-i2c.c
+++ b/drivers/media/pci/cx88/cx88-i2c.c
@@ -8,7 +8,7 @@
  * (c) 2002 Yurij Sysoev <yurij@naturesoft.net>
  * (c) 1999-2003 Gerd Knorr <kraxel@bytesex.org>
  *
- * (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
  *	- Multituner support and i2c address binding
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index 9be682cdb644..7b113bad70d2 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -5,7 +5,7 @@
  *
  * (c) 2003-04 Gerd Knorr <kraxel@bytesex.org> [SuSE Labs]
  *
- * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
  *	- Multituner support
  *	- video_ioctl2 conversion
  *	- PAL/M fixes
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index fca36a4910c2..d697e1ad929c 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -1122,23 +1122,11 @@ static int saa7164_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int saa7164_proc_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, saa7164_proc_show, NULL);
-}
-
-static const struct file_operations saa7164_proc_fops = {
-	.open		= saa7164_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int saa7164_proc_create(void)
 {
 	struct proc_dir_entry *pe;
 
-	pe = proc_create("saa7164", S_IRUGO, NULL, &saa7164_proc_fops);
+	pe = proc_create_single("saa7164", S_IRUGO, NULL, saa7164_proc_show);
 	if (!pe)
 		return -ENOMEM;
 
diff --git a/drivers/media/pci/zoran/videocodec.c b/drivers/media/pci/zoran/videocodec.c
index 5ff23ef89215..4427ae7126e2 100644
--- a/drivers/media/pci/zoran/videocodec.c
+++ b/drivers/media/pci/zoran/videocodec.c
@@ -344,19 +344,6 @@ static int proc_videocodecs_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int proc_videocodecs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_videocodecs_show, NULL);
-}
-
-static const struct file_operations videocodecs_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_videocodecs_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 /* ===================== */
@@ -373,7 +360,8 @@ videocodec_init (void)
 	       VIDEOCODEC_VERSION);
 
 #ifdef CONFIG_PROC_FS
-	videocodec_proc_entry = proc_create("videocodecs", 0, NULL, &videocodecs_proc_fops);
+	videocodec_proc_entry = proc_create_single("videocodecs", 0, NULL,
+			proc_videocodecs_show);
 	if (!videocodec_proc_entry) {
 		dprintk(1, KERN_ERR "videocodec: can't init procfs.\n");
 	}
diff --git a/drivers/media/radio/radio-aimslab.c b/drivers/media/radio/radio-aimslab.c
index 5ef635e72e10..4c52ac6d8bc5 100644
--- a/drivers/media/radio/radio-aimslab.c
+++ b/drivers/media/radio/radio-aimslab.c
@@ -4,7 +4,7 @@
  * Copyright 1997 M. Kirkwood
  *
  * Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
  * Converted to new API by Alan Cox <alan@lxorguk.ukuu.org.uk>
  * Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
  *
diff --git a/drivers/media/radio/radio-aztech.c b/drivers/media/radio/radio-aztech.c
index 9e12c6027359..840b7d60462b 100644
--- a/drivers/media/radio/radio-aztech.c
+++ b/drivers/media/radio/radio-aztech.c
@@ -2,7 +2,7 @@
  * radio-aztech.c - Aztech radio card driver
  *
  * Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@xs4all.nl>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
  * Adapted to support the Video for Linux API by
  * Russell Kroll <rkroll@exploits.org>.  Based on original tuner code by:
  *
diff --git a/drivers/media/radio/radio-gemtek.c b/drivers/media/radio/radio-gemtek.c
index 3ff4c4e1435f..f051f8694ab9 100644
--- a/drivers/media/radio/radio-gemtek.c
+++ b/drivers/media/radio/radio-gemtek.c
@@ -15,7 +15,7 @@
  *    Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
  *
  * Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
  *
  * Note: this card seems to swap the left and right audio channels!
  *
diff --git a/drivers/media/radio/radio-maxiradio.c b/drivers/media/radio/radio-maxiradio.c
index 95f06f3b35dc..e4e758739246 100644
--- a/drivers/media/radio/radio-maxiradio.c
+++ b/drivers/media/radio/radio-maxiradio.c
@@ -27,7 +27,7 @@
  * BUGS:
  *   - card unmutes if you change frequency
  *
- * (c) 2006, 2007 by Mauro Carvalho Chehab <mchehab@infradead.org>:
+ * (c) 2006, 2007 by Mauro Carvalho Chehab <mchehab@kernel.org>:
  *	- Conversion to V4L2 API
  *      - Uses video_ioctl2 for parsing and to add debug support
  */
diff --git a/drivers/media/radio/radio-rtrack2.c b/drivers/media/radio/radio-rtrack2.c
index abeaedd8d437..5a1470eb753e 100644
--- a/drivers/media/radio/radio-rtrack2.c
+++ b/drivers/media/radio/radio-rtrack2.c
@@ -7,7 +7,7 @@
  * Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
  *
  * Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
  *
  * Fully tested with actual hardware and the v4l2-compliance tool.
  */
diff --git a/drivers/media/radio/radio-sf16fmi.c b/drivers/media/radio/radio-sf16fmi.c
index fc4e63d36e4c..4f9b97edd9eb 100644
--- a/drivers/media/radio/radio-sf16fmi.c
+++ b/drivers/media/radio/radio-sf16fmi.c
@@ -13,7 +13,7 @@
  *  No volume control - only mute/unmute - you have to use line volume
  *  control on SB-part of SF16-FMI/SF16-FMP/SF16-FMD
  *
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 #include <linux/kernel.h>	/* __setup			*/
diff --git a/drivers/media/radio/radio-terratec.c b/drivers/media/radio/radio-terratec.c
index 4f116ea294fb..1af8f29cc7d1 100644
--- a/drivers/media/radio/radio-terratec.c
+++ b/drivers/media/radio/radio-terratec.c
@@ -17,7 +17,7 @@
  *  Volume Control is done digitally
  *
  * Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 #include <linux/module.h>	/* Modules			*/
diff --git a/drivers/media/radio/radio-trust.c b/drivers/media/radio/radio-trust.c
index 26a8c6002121..a4bad322ffff 100644
--- a/drivers/media/radio/radio-trust.c
+++ b/drivers/media/radio/radio-trust.c
@@ -12,7 +12,7 @@
  * Scott McGrath    (smcgrath@twilight.vtc.vsc.edu)
  * William McGrath  (wmcgrath@twilight.vtc.vsc.edu)
  *
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 #include <stdarg.h>
diff --git a/drivers/media/radio/radio-typhoon.c b/drivers/media/radio/radio-typhoon.c
index eb72a4d13758..d0d67ad85b8f 100644
--- a/drivers/media/radio/radio-typhoon.c
+++ b/drivers/media/radio/radio-typhoon.c
@@ -25,7 +25,7 @@
  * The frequency change is necessary since the card never seems to be
  * completely silent.
  *
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 #include <linux/module.h>	/* Modules                        */
diff --git a/drivers/media/radio/radio-zoltrix.c b/drivers/media/radio/radio-zoltrix.c
index 026e88eef29c..6007cd09b328 100644
--- a/drivers/media/radio/radio-zoltrix.c
+++ b/drivers/media/radio/radio-zoltrix.c
@@ -27,7 +27,7 @@
  * 2002-07-15 - Fix Stereo typo
  *
  * 2006-07-24 - Converted to V4L2 API
- *		by Mauro Carvalho Chehab <mchehab@infradead.org>
+ *		by Mauro Carvalho Chehab <mchehab@kernel.org>
  *
  * Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
  *
diff --git a/drivers/media/rc/keymaps/rc-avermedia-m135a.c b/drivers/media/rc/keymaps/rc-avermedia-m135a.c
index f6977df1a75b..d275d98d066a 100644
--- a/drivers/media/rc/keymaps/rc-avermedia-m135a.c
+++ b/drivers/media/rc/keymaps/rc-avermedia-m135a.c
@@ -12,7 +12,7 @@
  *
  * On Avermedia M135A with IR model RM-JX, the same codes exist on both
  * Positivo (BR) and original IR, initial version and remote control codes
- * added by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * added by Mauro Carvalho Chehab <mchehab@kernel.org>
  *
  * Positivo also ships Avermedia M135A with model RM-K6, extra control
  * codes added by Herton Ronaldo Krzesinski <herton@mandriva.com.br>
diff --git a/drivers/media/rc/keymaps/rc-encore-enltv-fm53.c b/drivers/media/rc/keymaps/rc-encore-enltv-fm53.c
index e4e78c1f4123..057c13b765ef 100644
--- a/drivers/media/rc/keymaps/rc-encore-enltv-fm53.c
+++ b/drivers/media/rc/keymaps/rc-encore-enltv-fm53.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 
 /* Encore ENLTV-FM v5.3
-   Mauro Carvalho Chehab <mchehab@infradead.org>
+   Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 static struct rc_map_table encore_enltv_fm53[] = {
diff --git a/drivers/media/rc/keymaps/rc-encore-enltv2.c b/drivers/media/rc/keymaps/rc-encore-enltv2.c
index c3d4437a6fda..cd0555924456 100644
--- a/drivers/media/rc/keymaps/rc-encore-enltv2.c
+++ b/drivers/media/rc/keymaps/rc-encore-enltv2.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 
 /* Encore ENLTV2-FM  - silver plastic - "Wand Media" written at the botton
-    Mauro Carvalho Chehab <mchehab@infradead.org> */
+    Mauro Carvalho Chehab <mchehab@kernel.org> */
 
 static struct rc_map_table encore_enltv2[] = {
 	{ 0x4c, KEY_POWER2 },
diff --git a/drivers/media/rc/keymaps/rc-kaiomy.c b/drivers/media/rc/keymaps/rc-kaiomy.c
index f0f88df18606..a00051339842 100644
--- a/drivers/media/rc/keymaps/rc-kaiomy.c
+++ b/drivers/media/rc/keymaps/rc-kaiomy.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 
 /* Kaiomy TVnPC U2
-   Mauro Carvalho Chehab <mchehab@infradead.org>
+   Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 static struct rc_map_table kaiomy[] = {
diff --git a/drivers/media/rc/keymaps/rc-kworld-plus-tv-analog.c b/drivers/media/rc/keymaps/rc-kworld-plus-tv-analog.c
index 453e04377de7..db5edde3eeb1 100644
--- a/drivers/media/rc/keymaps/rc-kworld-plus-tv-analog.c
+++ b/drivers/media/rc/keymaps/rc-kworld-plus-tv-analog.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 
 /* Kworld Plus TV Analog Lite PCI IR
-   Mauro Carvalho Chehab <mchehab@infradead.org>
+   Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 static struct rc_map_table kworld_plus_tv_analog[] = {
diff --git a/drivers/media/rc/keymaps/rc-pixelview-new.c b/drivers/media/rc/keymaps/rc-pixelview-new.c
index 791130f108ff..e4e34f2ccf74 100644
--- a/drivers/media/rc/keymaps/rc-pixelview-new.c
+++ b/drivers/media/rc/keymaps/rc-pixelview-new.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 
 /*
-   Mauro Carvalho Chehab <mchehab@infradead.org>
+   Mauro Carvalho Chehab <mchehab@kernel.org>
    present on PV MPEG 8000GT
  */
 
diff --git a/drivers/media/tuners/tea5761.c b/drivers/media/tuners/tea5761.c
index 88b3e80c38ad..d78a2bdb3e36 100644
--- a/drivers/media/tuners/tea5761.c
+++ b/drivers/media/tuners/tea5761.c
@@ -2,7 +2,7 @@
 // For Philips TEA5761 FM Chip
 // I2C address is always 0x20 (0x10 at 7-bit mode).
 //
-// Copyright (c) 2005-2007 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2005-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
 
 #include <linux/i2c.h>
 #include <linux/slab.h>
@@ -337,5 +337,5 @@ EXPORT_SYMBOL_GPL(tea5761_attach);
 EXPORT_SYMBOL_GPL(tea5761_autodetection);
 
 MODULE_DESCRIPTION("Philips TEA5761 FM tuner driver");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/tuners/tea5767.c b/drivers/media/tuners/tea5767.c
index 2b2c064d7dc3..016d0d5ec50b 100644
--- a/drivers/media/tuners/tea5767.c
+++ b/drivers/media/tuners/tea5767.c
@@ -2,7 +2,7 @@
 // For Philips TEA5767 FM Chip used on some TV Cards like Prolink Pixelview
 // I2C address is always 0xC0.
 //
-// Copyright (c) 2005 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
 //
 // tea5767 autodetection thanks to Torsten Seeboth and Atsushi Nakagawa
 // from their contributions on DScaler.
@@ -469,5 +469,5 @@ EXPORT_SYMBOL_GPL(tea5767_attach);
 EXPORT_SYMBOL_GPL(tea5767_autodetection);
 
 MODULE_DESCRIPTION("Philips TEA5767 FM tuner driver");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/tuners/tuner-xc2028-types.h b/drivers/media/tuners/tuner-xc2028-types.h
index bb0437c36c03..50d017a4822a 100644
--- a/drivers/media/tuners/tuner-xc2028-types.h
+++ b/drivers/media/tuners/tuner-xc2028-types.h
@@ -5,7 +5,7 @@
  * This file includes internal tipes to be used inside tuner-xc2028.
  * Shouldn't be included outside tuner-xc2028
  *
- * Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 /* xc3028 firmware types */
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index fca85e08ebd7..84744e138982 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // tuner-xc2028
 //
-// Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
 //
 // Copyright (c) 2007 Michel Ludwig (michel.ludwig@gmail.com)
 //       - frontend interface
@@ -1518,7 +1518,7 @@ EXPORT_SYMBOL(xc2028_attach);
 
 MODULE_DESCRIPTION("Xceive xc2028/xc3028 tuner driver");
 MODULE_AUTHOR("Michel Ludwig <michel.ludwig@gmail.com>");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL v2");
 MODULE_FIRMWARE(XC2028_DEFAULT_FIRMWARE);
 MODULE_FIRMWARE(XC3028L_DEFAULT_FIRMWARE);
diff --git a/drivers/media/tuners/tuner-xc2028.h b/drivers/media/tuners/tuner-xc2028.h
index 03fd6d4233a4..7b58bc06e35c 100644
--- a/drivers/media/tuners/tuner-xc2028.h
+++ b/drivers/media/tuners/tuner-xc2028.h
@@ -2,7 +2,7 @@
  * SPDX-License-Identifier: GPL-2.0
  * tuner-xc2028
  *
- * Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 #ifndef __TUNER_XC2028_H__
diff --git a/drivers/media/usb/em28xx/em28xx-camera.c b/drivers/media/usb/em28xx/em28xx-camera.c
index 3c2694a16ed1..d1e66b503f4d 100644
--- a/drivers/media/usb/em28xx/em28xx-camera.c
+++ b/drivers/media/usb/em28xx/em28xx-camera.c
@@ -2,7 +2,7 @@
 //
 // em28xx-camera.c - driver for Empia EM25xx/27xx/28xx USB video capture devices
 //
-// Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@kernel.org>
 // Copyright (C) 2013 Frank Schäfer <fschaefer.oss@googlemail.com>
 //
 // This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 6e0e67d23876..7c3203d7044b 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -5,7 +5,7 @@
 //
 // Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
 //		      Markus Rechberger <mrechberger@gmail.com>
-//		      Mauro Carvalho Chehab <mchehab@infradead.org>
+//		      Mauro Carvalho Chehab <mchehab@kernel.org>
 //		      Sascha Sommer <saschasommer@freenet.de>
 // Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
 //
diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c
index 36d341fb65dd..f28995383090 100644
--- a/drivers/media/usb/em28xx/em28xx-core.c
+++ b/drivers/media/usb/em28xx/em28xx-core.c
@@ -4,7 +4,7 @@
 //
 // Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
 //		      Markus Rechberger <mrechberger@gmail.com>
-//		      Mauro Carvalho Chehab <mchehab@infradead.org>
+//		      Mauro Carvalho Chehab <mchehab@kernel.org>
 //		      Sascha Sommer <saschasommer@freenet.de>
 // Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
 //
@@ -32,7 +32,7 @@
 
 #define DRIVER_AUTHOR "Ludovico Cavedon <cavedon@sssup.it>, " \
 		      "Markus Rechberger <mrechberger@gmail.com>, " \
-		      "Mauro Carvalho Chehab <mchehab@infradead.org>, " \
+		      "Mauro Carvalho Chehab <mchehab@kernel.org>, " \
 		      "Sascha Sommer <saschasommer@freenet.de>"
 
 MODULE_AUTHOR(DRIVER_AUTHOR);
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index a54cb8dc52c9..3f493e0b0716 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -2,7 +2,7 @@
 //
 // DVB device driver for em28xx
 //
-// (c) 2008-2011 Mauro Carvalho Chehab <mchehab@infradead.org>
+// (c) 2008-2011 Mauro Carvalho Chehab <mchehab@kernel.org>
 //
 // (c) 2008 Devin Heitmueller <devin.heitmueller@gmail.com>
 //	- Fixes for the driver to properly work with HVR-950
@@ -63,7 +63,7 @@
 #include "tc90522.h"
 #include "qm1d1c0042.h"
 
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION(DRIVER_DESC " - digital TV interface");
 MODULE_VERSION(EM28XX_VERSION);
diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index 9151bccd859a..6458682bc6e2 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -4,7 +4,7 @@
 //
 // Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
 //		      Markus Rechberger <mrechberger@gmail.com>
-//		      Mauro Carvalho Chehab <mchehab@infradead.org>
+//		      Mauro Carvalho Chehab <mchehab@kernel.org>
 //		      Sascha Sommer <saschasommer@freenet.de>
 // Copyright (C) 2013 Frank Schäfer <fschaefer.oss@googlemail.com>
 //
diff --git a/drivers/media/usb/em28xx/em28xx-input.c b/drivers/media/usb/em28xx/em28xx-input.c
index 2dc1be00b8b8..f84a1208d5d3 100644
--- a/drivers/media/usb/em28xx/em28xx-input.c
+++ b/drivers/media/usb/em28xx/em28xx-input.c
@@ -4,7 +4,7 @@
 //
 // Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
 //		      Markus Rechberger <mrechberger@gmail.com>
-//		      Mauro Carvalho Chehab <mchehab@infradead.org>
+//		      Mauro Carvalho Chehab <mchehab@kernel.org>
 //		      Sascha Sommer <saschasommer@freenet.de>
 //
 // This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index d70ee13cc52e..68571bf36d28 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -5,7 +5,7 @@
 //
 // Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
 //		      Markus Rechberger <mrechberger@gmail.com>
-//		      Mauro Carvalho Chehab <mchehab@infradead.org>
+//		      Mauro Carvalho Chehab <mchehab@kernel.org>
 //		      Sascha Sommer <saschasommer@freenet.de>
 // Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
 //
@@ -44,7 +44,7 @@
 
 #define DRIVER_AUTHOR "Ludovico Cavedon <cavedon@sssup.it>, " \
 		      "Markus Rechberger <mrechberger@gmail.com>, " \
-		      "Mauro Carvalho Chehab <mchehab@infradead.org>, " \
+		      "Mauro Carvalho Chehab <mchehab@kernel.org>, " \
 		      "Sascha Sommer <saschasommer@freenet.de>"
 
 static unsigned int isoc_debug;
diff --git a/drivers/media/usb/em28xx/em28xx.h b/drivers/media/usb/em28xx/em28xx.h
index 63c7c6124707..b0378e77ddff 100644
--- a/drivers/media/usb/em28xx/em28xx.h
+++ b/drivers/media/usb/em28xx/em28xx.h
@@ -4,7 +4,7 @@
  *
  * Copyright (C) 2005 Markus Rechberger <mrechberger@gmail.com>
  *		      Ludovico Cavedon <cavedon@sssup.it>
- *		      Mauro Carvalho Chehab <mchehab@infradead.org>
+ *		      Mauro Carvalho Chehab <mchehab@kernel.org>
  * Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
  *
  * Based on the em2800 driver from Sascha Sommer <saschasommer@freenet.de>
diff --git a/drivers/media/usb/gspca/zc3xx-reg.h b/drivers/media/usb/gspca/zc3xx-reg.h
index a1bd94e8ce52..71fda38e85e0 100644
--- a/drivers/media/usb/gspca/zc3xx-reg.h
+++ b/drivers/media/usb/gspca/zc3xx-reg.h
@@ -1,7 +1,7 @@
 /*
  * zc030x registers
  *
- * Copyright (c) 2008 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2008 Mauro Carvalho Chehab <mchehab@kernel.org>
  *
  * The register aliases used here came from this driver:
  *	http://zc0302.sourceforge.net/zc0302.php
diff --git a/drivers/media/usb/tm6000/tm6000-cards.c b/drivers/media/usb/tm6000/tm6000-cards.c
index 70939e96b856..23df50aa0a4a 100644
--- a/drivers/media/usb/tm6000/tm6000-cards.c
+++ b/drivers/media/usb/tm6000/tm6000-cards.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // tm6000-cards.c - driver for TM5600/TM6000/TM6010 USB video capture devices
 //
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
 
 #include <linux/init.h>
 #include <linux/module.h>
diff --git a/drivers/media/usb/tm6000/tm6000-core.c b/drivers/media/usb/tm6000/tm6000-core.c
index 23a1332d98e6..d3229aa45fcb 100644
--- a/drivers/media/usb/tm6000/tm6000-core.c
+++ b/drivers/media/usb/tm6000/tm6000-core.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // tm6000-core.c - driver for TM5600/TM6000/TM6010 USB video capture devices
 //
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
 //
 // Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
 //     - DVB-T support
diff --git a/drivers/media/usb/tm6000/tm6000-i2c.c b/drivers/media/usb/tm6000/tm6000-i2c.c
index c9a62bbff27a..659b63febf85 100644
--- a/drivers/media/usb/tm6000/tm6000-i2c.c
+++ b/drivers/media/usb/tm6000/tm6000-i2c.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // tm6000-i2c.c - driver for TM5600/TM6000/TM6010 USB video capture devices
 //
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
 //
 // Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
 //	- Fix SMBus Read Byte command
diff --git a/drivers/media/usb/tm6000/tm6000-regs.h b/drivers/media/usb/tm6000/tm6000-regs.h
index 21587fcf11e3..d10424673db9 100644
--- a/drivers/media/usb/tm6000/tm6000-regs.h
+++ b/drivers/media/usb/tm6000/tm6000-regs.h
@@ -2,7 +2,7 @@
  * SPDX-License-Identifier: GPL-2.0
  * tm6000-regs.h - driver for TM5600/TM6000/TM6010 USB video capture devices
  *
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 /*
diff --git a/drivers/media/usb/tm6000/tm6000-usb-isoc.h b/drivers/media/usb/tm6000/tm6000-usb-isoc.h
index 5c615b0a7a46..b275dbce3a1b 100644
--- a/drivers/media/usb/tm6000/tm6000-usb-isoc.h
+++ b/drivers/media/usb/tm6000/tm6000-usb-isoc.h
@@ -2,7 +2,7 @@
  * SPDX-License-Identifier: GPL-2.0
  * tm6000-buf.c - driver for TM5600/TM6000/TM6010 USB video capture devices
  *
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
  */
 
 #include <linux/videodev2.h>
diff --git a/drivers/media/usb/tm6000/tm6000-video.c b/drivers/media/usb/tm6000/tm6000-video.c
index b2399d4266da..aa85fe31c835 100644
--- a/drivers/media/usb/tm6000/tm6000-video.c
+++ b/drivers/media/usb/tm6000/tm6000-video.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // tm6000-video.c - driver for TM5600/TM6000/TM6010 USB video capture devices
 //
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
 //
 // Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
 //	- Fixed module load/unload
diff --git a/drivers/media/usb/tm6000/tm6000.h b/drivers/media/usb/tm6000/tm6000.h
index e1e45770e28d..0864ed7314eb 100644
--- a/drivers/media/usb/tm6000/tm6000.h
+++ b/drivers/media/usb/tm6000/tm6000.h
@@ -2,7 +2,7 @@
  * SPDX-License-Identifier: GPL-2.0
  * tm6000.h - driver for TM5600/TM6000/TM6010 USB video capture devices
  *
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
  *
  * Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
  *	- DVB-T support
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 1d0b2208e8fb..c080dcc75393 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -10,7 +10,7 @@
  *	2 of the License, or (at your option) any later version.
  *
  * Authors:	Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
- *              Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ *              Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
  *
  * Fixes:	20000516  Claudio Matsuoka <claudio@conectiva.com>
  *		- Added procfs support
@@ -1072,7 +1072,7 @@ static void __exit videodev_exit(void)
 subsys_initcall(videodev_init);
 module_exit(videodev_exit)
 
-MODULE_AUTHOR("Alan Cox, Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Alan Cox, Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_DESCRIPTION("Device registrar for Video4Linux drivers v2");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_CHARDEV_MAJOR(VIDEO_MAJOR);
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index f48c505550e0..de5d96dbe69e 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -9,7 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  *
  * Authors:	Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
- *              Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ *              Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
  */
 
 #include <linux/mm.h>
diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c
index 2b3981842b4b..7491b337002c 100644
--- a/drivers/media/v4l2-core/videobuf-core.c
+++ b/drivers/media/v4l2-core/videobuf-core.c
@@ -1,11 +1,11 @@
 /*
  * generic helper functions for handling video4linux capture buffers
  *
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
  *
  * Highly based on video-buf written originally by:
  * (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
  * (c) 2006 Ted Walther and John Sokol
  *
  * This program is free software; you can redistribute it and/or modify
@@ -38,7 +38,7 @@ static int debug;
 module_param(debug, int, 0644);
 
 MODULE_DESCRIPTION("helper module to manage video4linux buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL");
 
 #define dprintk(level, fmt, arg...)					\
diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c
index e02353e340dd..f46132504d88 100644
--- a/drivers/media/v4l2-core/videobuf-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf-dma-contig.c
@@ -7,7 +7,7 @@
  * Copyright (c) 2008 Magnus Damm
  *
  * Based on videobuf-vmalloc.c,
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index add2edb23eac..7770034aae28 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -6,11 +6,11 @@
  * into PAGE_SIZE chunks).  They also assume the driver does not need
  * to touch the video data.
  *
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
  *
  * Highly based on video-buf written originally by:
  * (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
  * (c) 2006 Ted Walther and John Sokol
  *
  * This program is free software; you can redistribute it and/or modify
@@ -48,7 +48,7 @@ static int debug;
 module_param(debug, int, 0644);
 
 MODULE_DESCRIPTION("helper module to manage video4linux dma sg buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL");
 
 #define dprintk(level, fmt, arg...)					\
diff --git a/drivers/media/v4l2-core/videobuf-vmalloc.c b/drivers/media/v4l2-core/videobuf-vmalloc.c
index 2ff7fcc77b11..45fe781aeeec 100644
--- a/drivers/media/v4l2-core/videobuf-vmalloc.c
+++ b/drivers/media/v4l2-core/videobuf-vmalloc.c
@@ -6,7 +6,7 @@
  * into PAGE_SIZE chunks).  They also assume the driver does not need
  * to touch the video data.
  *
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -41,7 +41,7 @@ static int debug;
 module_param(debug, int, 0644);
 
 MODULE_DESCRIPTION("helper module to manage video4linux vmalloc buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
 MODULE_LICENSE("GPL");
 
 #define dprintk(level, fmt, arg...)					\
diff --git a/drivers/memory/emif-asm-offsets.c b/drivers/memory/emif-asm-offsets.c
index 71a89d5d3efd..db8043019ec6 100644
--- a/drivers/memory/emif-asm-offsets.c
+++ b/drivers/memory/emif-asm-offsets.c
@@ -16,77 +16,7 @@
 
 int main(void)
 {
-	DEFINE(EMIF_SDCFG_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_sdcfg_val));
-	DEFINE(EMIF_TIMING1_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_timing1_val));
-	DEFINE(EMIF_TIMING2_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_timing2_val));
-	DEFINE(EMIF_TIMING3_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_timing3_val));
-	DEFINE(EMIF_REF_CTRL_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_ref_ctrl_val));
-	DEFINE(EMIF_ZQCFG_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_zqcfg_val));
-	DEFINE(EMIF_PMCR_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_pmcr_val));
-	DEFINE(EMIF_PMCR_SHDW_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_pmcr_shdw_val));
-	DEFINE(EMIF_RD_WR_LEVEL_RAMP_CTRL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_rd_wr_level_ramp_ctrl));
-	DEFINE(EMIF_RD_WR_EXEC_THRESH_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_rd_wr_exec_thresh));
-	DEFINE(EMIF_COS_CONFIG_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_cos_config));
-	DEFINE(EMIF_PRIORITY_TO_COS_MAPPING_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_priority_to_cos_mapping));
-	DEFINE(EMIF_CONNECT_ID_SERV_1_MAP_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_connect_id_serv_1_map));
-	DEFINE(EMIF_CONNECT_ID_SERV_2_MAP_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_connect_id_serv_2_map));
-	DEFINE(EMIF_OCP_CONFIG_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_ocp_config_val));
-	DEFINE(EMIF_LPDDR2_NVM_TIM_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim));
-	DEFINE(EMIF_LPDDR2_NVM_TIM_SHDW_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim_shdw));
-	DEFINE(EMIF_DLL_CALIB_CTRL_VAL_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val));
-	DEFINE(EMIF_DLL_CALIB_CTRL_VAL_SHDW_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val_shdw));
-	DEFINE(EMIF_DDR_PHY_CTLR_1_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_ddr_phy_ctlr_1));
-	DEFINE(EMIF_EXT_PHY_CTRL_VALS_OFFSET,
-	       offsetof(struct emif_regs_amx3, emif_ext_phy_ctrl_vals));
-	DEFINE(EMIF_REGS_AMX3_SIZE, sizeof(struct emif_regs_amx3));
-
-	BLANK();
-
-	DEFINE(EMIF_PM_BASE_ADDR_VIRT_OFFSET,
-	       offsetof(struct ti_emif_pm_data, ti_emif_base_addr_virt));
-	DEFINE(EMIF_PM_BASE_ADDR_PHYS_OFFSET,
-	       offsetof(struct ti_emif_pm_data, ti_emif_base_addr_phys));
-	DEFINE(EMIF_PM_CONFIG_OFFSET,
-	       offsetof(struct ti_emif_pm_data, ti_emif_sram_config));
-	DEFINE(EMIF_PM_REGS_VIRT_OFFSET,
-	       offsetof(struct ti_emif_pm_data, regs_virt));
-	DEFINE(EMIF_PM_REGS_PHYS_OFFSET,
-	       offsetof(struct ti_emif_pm_data, regs_phys));
-	DEFINE(EMIF_PM_DATA_SIZE, sizeof(struct ti_emif_pm_data));
-
-	BLANK();
-
-	DEFINE(EMIF_PM_SAVE_CONTEXT_OFFSET,
-	       offsetof(struct ti_emif_pm_functions, save_context));
-	DEFINE(EMIF_PM_RESTORE_CONTEXT_OFFSET,
-	       offsetof(struct ti_emif_pm_functions, restore_context));
-	DEFINE(EMIF_PM_ENTER_SR_OFFSET,
-	       offsetof(struct ti_emif_pm_functions, enter_sr));
-	DEFINE(EMIF_PM_EXIT_SR_OFFSET,
-	       offsetof(struct ti_emif_pm_functions, exit_sr));
-	DEFINE(EMIF_PM_ABORT_SR_OFFSET,
-	       offsetof(struct ti_emif_pm_functions, abort_sr));
-	DEFINE(EMIF_PM_FUNCTIONS_SIZE, sizeof(struct ti_emif_pm_functions));
+	ti_emif_asm_offsets();
 
 	return 0;
 }
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 57b13dfbd21e..a15181fa45f7 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -2094,14 +2094,9 @@ static const struct block_device_operations msb_bdops = {
 static int msb_init_disk(struct memstick_dev *card)
 {
 	struct msb_data *msb = memstick_get_drvdata(card);
-	struct memstick_host *host = card->host;
 	int rc;
-	u64 limit = BLK_BOUNCE_HIGH;
 	unsigned long capacity;
 
-	if (host->dev.dma_mask && *(host->dev.dma_mask))
-		limit = *(host->dev.dma_mask);
-
 	mutex_lock(&msb_disk_lock);
 	msb->disk_id = idr_alloc(&msb_disk_idr, card, 0, 256, GFP_KERNEL);
 	mutex_unlock(&msb_disk_lock);
@@ -2123,7 +2118,6 @@ static int msb_init_disk(struct memstick_dev *card)
 
 	msb->queue->queuedata = card;
 
-	blk_queue_bounce_limit(msb->queue, limit);
 	blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);
 	blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS);
 	blk_queue_max_segment_size(msb->queue,
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index 8897962781bb..5ee932631fae 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -1170,17 +1170,12 @@ static int mspro_block_init_card(struct memstick_dev *card)
 static int mspro_block_init_disk(struct memstick_dev *card)
 {
 	struct mspro_block_data *msb = memstick_get_drvdata(card);
-	struct memstick_host *host = card->host;
 	struct mspro_devinfo *dev_info = NULL;
 	struct mspro_sys_info *sys_info = NULL;
 	struct mspro_sys_attr *s_attr = NULL;
 	int rc, disk_id;
-	u64 limit = BLK_BOUNCE_HIGH;
 	unsigned long capacity;
 
-	if (host->dev.dma_mask && *(host->dev.dma_mask))
-		limit = *(host->dev.dma_mask);
-
 	for (rc = 0; msb->attr_group.attrs[rc]; ++rc) {
 		s_attr = mspro_from_sysfs_attr(msb->attr_group.attrs[rc]);
 
@@ -1219,7 +1214,6 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 
 	msb->queue->queuedata = card;
 
-	blk_queue_bounce_limit(msb->queue, limit);
 	blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);
 	blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS);
 	blk_queue_max_segment_size(msb->queue,
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 51eb1b027963..a746ccdd630a 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -197,9 +197,9 @@ static int	mpt_host_page_access_control(MPT_ADAPTER *ioc, u8 access_control_valu
 static int	mpt_host_page_alloc(MPT_ADAPTER *ioc, pIOCInit_t ioc_init);
 
 #ifdef CONFIG_PROC_FS
-static const struct file_operations mpt_summary_proc_fops;
-static const struct file_operations mpt_version_proc_fops;
-static const struct file_operations mpt_iocinfo_proc_fops;
+static int mpt_summary_proc_show(struct seq_file *m, void *v);
+static int mpt_version_proc_show(struct seq_file *m, void *v);
+static int mpt_iocinfo_proc_show(struct seq_file *m, void *v);
 #endif
 static void	mpt_get_fw_exp_ver(char *buf, MPT_ADAPTER *ioc);
 
@@ -2040,8 +2040,10 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 	 */
 	dent = proc_mkdir(ioc->name, mpt_proc_root_dir);
 	if (dent) {
-		proc_create_data("info", S_IRUGO, dent, &mpt_iocinfo_proc_fops, ioc);
-		proc_create_data("summary", S_IRUGO, dent, &mpt_summary_proc_fops, ioc);
+		proc_create_single_data("info", S_IRUGO, dent,
+				mpt_iocinfo_proc_show, ioc);
+		proc_create_single_data("summary", S_IRUGO, dent,
+				mpt_summary_proc_show, ioc);
 	}
 #endif
 
@@ -6606,8 +6608,10 @@ procmpt_create(void)
 	if (mpt_proc_root_dir == NULL)
 		return -ENOTDIR;
 
-	proc_create("summary", S_IRUGO, mpt_proc_root_dir, &mpt_summary_proc_fops);
-	proc_create("version", S_IRUGO, mpt_proc_root_dir, &mpt_version_proc_fops);
+	proc_create_single("summary", S_IRUGO, mpt_proc_root_dir,
+			mpt_summary_proc_show);
+	proc_create_single("version", S_IRUGO, mpt_proc_root_dir,
+			mpt_version_proc_show);
 	return 0;
 }
 
@@ -6646,19 +6650,6 @@ static int mpt_summary_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int mpt_summary_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mpt_summary_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations mpt_summary_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= mpt_summary_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int mpt_version_proc_show(struct seq_file *m, void *v)
 {
 	u8	 cb_idx;
@@ -6701,19 +6692,6 @@ static int mpt_version_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int mpt_version_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mpt_version_proc_show, NULL);
-}
-
-static const struct file_operations mpt_version_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= mpt_version_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int mpt_iocinfo_proc_show(struct seq_file *m, void *v)
 {
 	MPT_ADAPTER	*ioc = m->private;
@@ -6793,19 +6771,6 @@ static int mpt_iocinfo_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int mpt_iocinfo_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mpt_iocinfo_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations mpt_iocinfo_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= mpt_iocinfo_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif		/* CONFIG_PROC_FS } */
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 231f3a1e27bf..19a5aa70ecda 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -1929,7 +1929,7 @@ static enum blk_eh_timer_return mptsas_eh_timed_out(struct scsi_cmnd *sc)
 	MPT_SCSI_HOST *hd;
 	MPT_ADAPTER   *ioc;
 	VirtDevice    *vdevice;
-	enum blk_eh_timer_return rc = BLK_EH_NOT_HANDLED;
+	enum blk_eh_timer_return rc = BLK_EH_DONE;
 
 	hd = shost_priv(sc->device->host);
 	if (hd == NULL) {
@@ -1994,6 +1994,7 @@ static struct scsi_host_template mptsas_driver_template = {
 	.cmd_per_lun			= 7,
 	.use_clustering			= ENABLE_CLUSTERING,
 	.shost_attrs			= mptscsih_host_attrs,
+	.no_write_same			= 1,
 };
 
 static int mptsas_get_linkerrors(struct sas_phy *phy)
diff --git a/drivers/mfd/cros_ec.c b/drivers/mfd/cros_ec.c
index d61024141e2b..36156a41499c 100644
--- a/drivers/mfd/cros_ec.c
+++ b/drivers/mfd/cros_ec.c
@@ -229,7 +229,7 @@ int cros_ec_suspend(struct cros_ec_device *ec_dev)
 }
 EXPORT_SYMBOL(cros_ec_suspend);
 
-static void cros_ec_drain_events(struct cros_ec_device *ec_dev)
+static void cros_ec_report_events_during_suspend(struct cros_ec_device *ec_dev)
 {
 	while (cros_ec_get_next_event(ec_dev, NULL) > 0)
 		blocking_notifier_call_chain(&ec_dev->event_notifier,
@@ -253,21 +253,16 @@ int cros_ec_resume(struct cros_ec_device *ec_dev)
 		dev_dbg(ec_dev->dev, "Error %d sending resume event to ec",
 			ret);
 
-	/*
-	 * In some cases, we need to distinguish between events that occur
-	 * during suspend if the EC is not a wake source. For example,
-	 * keypresses during suspend should be discarded if it does not wake
-	 * the system.
-	 *
-	 * If the EC is not a wake source, drain the event queue and mark them
-	 * as "queued during suspend".
-	 */
 	if (ec_dev->wake_enabled) {
 		disable_irq_wake(ec_dev->irq);
 		ec_dev->wake_enabled = 0;
-	} else {
-		cros_ec_drain_events(ec_dev);
 	}
+	/*
+	 * Let the mfd devices know about events that occur during
+	 * suspend. This way the clients know what to do with them.
+	 */
+	cros_ec_report_events_during_suspend(ec_dev);
+
 
 	return 0;
 }
diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c
index 1b52b8557034..2060d1483043 100644
--- a/drivers/mfd/cros_ec_spi.c
+++ b/drivers/mfd/cros_ec_spi.c
@@ -419,10 +419,25 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev,
 		/* Verify that EC can process command */
 		for (i = 0; i < len; i++) {
 			rx_byte = rx_buf[i];
+			/*
+			 * Seeing the PAST_END, RX_BAD_DATA, or NOT_READY
+			 * markers are all signs that the EC didn't fully
+			 * receive our command. e.g., if the EC is flashing
+			 * itself, it can't respond to any commands and instead
+			 * clocks out EC_SPI_PAST_END from its SPI hardware
+			 * buffer. Similar occurrences can happen if the AP is
+			 * too slow to clock out data after asserting CS -- the
+			 * EC will abort and fill its buffer with
+			 * EC_SPI_RX_BAD_DATA.
+			 *
+			 * In all cases, these errors should be safe to retry.
+			 * Report -EAGAIN and let the caller decide what to do
+			 * about that.
+			 */
 			if (rx_byte == EC_SPI_PAST_END  ||
 			    rx_byte == EC_SPI_RX_BAD_DATA ||
 			    rx_byte == EC_SPI_NOT_READY) {
-				ret = -EREMOTEIO;
+				ret = -EAGAIN;
 				break;
 			}
 		}
@@ -431,7 +446,7 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev,
 	if (!ret)
 		ret = cros_ec_spi_receive_packet(ec_dev,
 				ec_msg->insize + sizeof(*response));
-	else
+	else if (ret != -EAGAIN)
 		dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
 
 	final_ret = terminate_request(ec_dev);
@@ -537,10 +552,11 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 		/* Verify that EC can process command */
 		for (i = 0; i < len; i++) {
 			rx_byte = rx_buf[i];
+			/* See comments in cros_ec_pkt_xfer_spi() */
 			if (rx_byte == EC_SPI_PAST_END  ||
 			    rx_byte == EC_SPI_RX_BAD_DATA ||
 			    rx_byte == EC_SPI_NOT_READY) {
-				ret = -EREMOTEIO;
+				ret = -EAGAIN;
 				break;
 			}
 		}
@@ -549,7 +565,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 	if (!ret)
 		ret = cros_ec_spi_receive_response(ec_dev,
 				ec_msg->insize + EC_MSG_TX_PROTO_BYTES);
-	else
+	else if (ret != -EAGAIN)
 		dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
 
 	final_ret = terminate_request(ec_dev);
diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c
index d7f54e492aa6..c63e331738c1 100644
--- a/drivers/mfd/mc13xxx-core.c
+++ b/drivers/mfd/mc13xxx-core.c
@@ -279,8 +279,21 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode,
 	adc0 = MC13XXX_ADC0_ADINC1 | MC13XXX_ADC0_ADINC2;
 	adc1 = MC13XXX_ADC1_ADEN | MC13XXX_ADC1_ADTRIGIGN | MC13XXX_ADC1_ASC;
 
-	if (channel > 7)
+	/*
+	 * Channels mapped through ADIN7:
+	 * 7  - General purpose ADIN7
+	 * 16 - UID
+	 * 17 - Die temperature
+	 */
+	if (channel > 7 && channel < 16) {
 		adc1 |= MC13XXX_ADC1_ADSEL;
+	} else if (channel == 16) {
+		adc0 |= MC13XXX_ADC0_ADIN7SEL_UID;
+		channel = 7;
+	} else if (channel == 17) {
+		adc0 |= MC13XXX_ADC0_ADIN7SEL_DIE;
+		channel = 7;
+	}
 
 	switch (mode) {
 	case MC13XXX_ADC_MODE_TS:
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 5d713008749b..3726eacdf65d 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -113,6 +113,20 @@ config IBM_ASM
 	  for information on the specific driver level and support statement
 	  for your IBM server.
 
+config IBMVMC
+	tristate "IBM Virtual Management Channel support"
+	depends on PPC_PSERIES
+	help
+	  This is the IBM POWER Virtual Management Channel
+
+	  This driver is to be used for the POWER Virtual
+	  Management Channel virtual adapter on the PowerVM
+	  platform. It provides both request/response and
+	  async message support through the /dev/ibmvmc node.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ibmvmc.
+
 config PHANTOM
 	tristate "Sensable PHANToM (PCI)"
 	depends on PCI
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 20be70c3f118..af22bbc3d00c 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -4,6 +4,7 @@
 #
 
 obj-$(CONFIG_IBM_ASM)		+= ibmasm/
+obj-$(CONFIG_IBMVMC)		+= ibmvmc.o
 obj-$(CONFIG_AD525X_DPOT)	+= ad525x_dpot.o
 obj-$(CONFIG_AD525X_DPOT_I2C)	+= ad525x_dpot-i2c.o
 obj-$(CONFIG_AD525X_DPOT_SPI)	+= ad525x_dpot-spi.o
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 7ff315ad3692..c6ec872800a2 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -128,11 +128,12 @@ void cxl_context_set_mapping(struct cxl_context *ctx,
 	mutex_unlock(&ctx->mapping_lock);
 }
 
-static int cxl_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t cxl_mmap_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct cxl_context *ctx = vma->vm_file->private_data;
 	u64 area, offset;
+	vm_fault_t ret;
 
 	offset = vmf->pgoff << PAGE_SHIFT;
 
@@ -169,11 +170,11 @@ static int cxl_mmap_fault(struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 	}
 
-	vm_insert_pfn(vma, vmf->address, (area + offset) >> PAGE_SHIFT);
+	ret = vmf_insert_pfn(vma, vmf->address, (area + offset) >> PAGE_SHIFT);
 
 	mutex_unlock(&ctx->status_mutex);
 
-	return VM_FAULT_NOPAGE;
+	return ret;
 }
 
 static const struct vm_operations_struct cxl_mmap_vmops = {
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index a4c9c8297a6d..918d4fb742d1 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -717,6 +717,7 @@ struct cxl {
 	bool perst_select_user;
 	bool perst_same_image;
 	bool psl_timebase_synced;
+	bool tunneled_ops_supported;
 
 	/*
 	 * number of contexts mapped on to this card. Possible values are:
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 83f1d08058fc..4d6736f9d463 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1742,6 +1742,15 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
 	/* Required for devices using CAPP DMA mode, harmless for others */
 	pci_set_master(dev);
 
+	adapter->tunneled_ops_supported = false;
+
+	if (cxl_is_power9()) {
+		if (pnv_pci_set_tunnel_bar(dev, 0x00020000E0000000ull, 1))
+			dev_info(&dev->dev, "Tunneled operations unsupported\n");
+		else
+			adapter->tunneled_ops_supported = true;
+	}
+
 	if ((rc = pnv_phb_to_cxl_mode(dev, adapter->native->sl_ops->capi_mode)))
 		goto err;
 
@@ -1768,6 +1777,9 @@ static void cxl_deconfigure_adapter(struct cxl *adapter)
 {
 	struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);
 
+	if (cxl_is_power9())
+		pnv_pci_set_tunnel_bar(pdev, 0x00020000E0000000ull, 0);
+
 	cxl_native_release_psl_err_irq(adapter);
 	cxl_unmap_adapter_regs(adapter);
 
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 95285b7f636f..4b5a4c5d3c01 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -78,6 +78,15 @@ static ssize_t psl_timebase_synced_show(struct device *device,
 	return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_timebase_synced);
 }
 
+static ssize_t tunneled_ops_supported_show(struct device *device,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct cxl *adapter = to_cxl_adapter(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->tunneled_ops_supported);
+}
+
 static ssize_t reset_adapter_store(struct device *device,
 				   struct device_attribute *attr,
 				   const char *buf, size_t count)
@@ -183,6 +192,7 @@ static struct device_attribute adapter_attrs[] = {
 	__ATTR_RO(base_image),
 	__ATTR_RO(image_loaded),
 	__ATTR_RO(psl_timebase_synced),
+	__ATTR_RO(tunneled_ops_supported),
 	__ATTR_RW(load_image_on_perst),
 	__ATTR_RW(perst_reloads_same_image),
 	__ATTR(reset, S_IWUSR, NULL, reset_adapter_store),
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 0c125f207aea..33053b0d1fdf 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -518,7 +518,7 @@ static int at24_get_pdata(struct device *dev, struct at24_platform_data *pdata)
 	if (of_node && of_match_device(at24_of_match, dev))
 		cdata = of_device_get_match_data(dev);
 	else if (id)
-		cdata = (void *)&id->driver_data;
+		cdata = (void *)id->driver_data;
 	else
 		cdata = acpi_device_get_match_data(dev);
 
diff --git a/drivers/misc/ibmvmc.c b/drivers/misc/ibmvmc.c
new file mode 100644
index 000000000000..fb83d1375638
--- /dev/null
+++ b/drivers/misc/ibmvmc.c
@@ -0,0 +1,2418 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * IBM Power Systems Virtual Management Channel Support.
+ *
+ * Copyright (c) 2004, 2018 IBM Corp.
+ *   Dave Engebretsen engebret@us.ibm.com
+ *   Steven Royer seroyer@linux.vnet.ibm.com
+ *   Adam Reznechek adreznec@linux.vnet.ibm.com
+ *   Bryant G. Ly <bryantly@linux.vnet.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/major.h>
+#include <linux/string.h>
+#include <linux/fcntl.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/miscdevice.h>
+#include <linux/sched/signal.h>
+
+#include <asm/byteorder.h>
+#include <asm/irq.h>
+#include <asm/vio.h>
+
+#include "ibmvmc.h"
+
+#define IBMVMC_DRIVER_VERSION "1.0"
+
+/*
+ * Static global variables
+ */
+static DECLARE_WAIT_QUEUE_HEAD(ibmvmc_read_wait);
+
+static const char ibmvmc_driver_name[] = "ibmvmc";
+
+static struct ibmvmc_struct ibmvmc;
+static struct ibmvmc_hmc hmcs[MAX_HMCS];
+static struct crq_server_adapter ibmvmc_adapter;
+
+static int ibmvmc_max_buf_pool_size = DEFAULT_BUF_POOL_SIZE;
+static int ibmvmc_max_hmcs = DEFAULT_HMCS;
+static int ibmvmc_max_mtu = DEFAULT_MTU;
+
+static inline long h_copy_rdma(s64 length, u64 sliobn, u64 slioba,
+			       u64 dliobn, u64 dlioba)
+{
+	long rc = 0;
+
+	/* Ensure all writes to source memory are visible before hcall */
+	dma_wmb();
+	pr_debug("ibmvmc: h_copy_rdma(0x%llx, 0x%llx, 0x%llx, 0x%llx, 0x%llx\n",
+		 length, sliobn, slioba, dliobn, dlioba);
+	rc = plpar_hcall_norets(H_COPY_RDMA, length, sliobn, slioba,
+				dliobn, dlioba);
+	pr_debug("ibmvmc: h_copy_rdma rc = 0x%lx\n", rc);
+
+	return rc;
+}
+
+static inline void h_free_crq(uint32_t unit_address)
+{
+	long rc = 0;
+
+	do {
+		if (H_IS_LONG_BUSY(rc))
+			msleep(get_longbusy_msecs(rc));
+
+		rc = plpar_hcall_norets(H_FREE_CRQ, unit_address);
+	} while ((rc == H_BUSY) || (H_IS_LONG_BUSY(rc)));
+}
+
+/**
+ * h_request_vmc: - request a hypervisor virtual management channel device
+ * @vmc_index: drc index of the vmc device created
+ *
+ * Requests the hypervisor create a new virtual management channel device,
+ * allowing this partition to send hypervisor virtualization control
+ * commands.
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static inline long h_request_vmc(u32 *vmc_index)
+{
+	long rc = 0;
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+	do {
+		if (H_IS_LONG_BUSY(rc))
+			msleep(get_longbusy_msecs(rc));
+
+		/* Call to request the VMC device from phyp */
+		rc = plpar_hcall(H_REQUEST_VMC, retbuf);
+		pr_debug("ibmvmc: %s rc = 0x%lx\n", __func__, rc);
+		*vmc_index = retbuf[0];
+	} while ((rc == H_BUSY) || (H_IS_LONG_BUSY(rc)));
+
+	return rc;
+}
+
+/* routines for managing a command/response queue */
+/**
+ * ibmvmc_handle_event: - Interrupt handler for crq events
+ * @irq:        number of irq to handle, not used
+ * @dev_instance: crq_server_adapter that received interrupt
+ *
+ * Disables interrupts and schedules ibmvmc_task
+ *
+ * Always returns IRQ_HANDLED
+ */
+static irqreturn_t ibmvmc_handle_event(int irq, void *dev_instance)
+{
+	struct crq_server_adapter *adapter =
+		(struct crq_server_adapter *)dev_instance;
+
+	vio_disable_interrupts(to_vio_dev(adapter->dev));
+	tasklet_schedule(&adapter->work_task);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ibmvmc_release_crq_queue - Release CRQ Queue
+ *
+ * @adapter:	crq_server_adapter struct
+ *
+ * Return:
+ *	0 - Success
+ *	Non-Zero - Failure
+ */
+static void ibmvmc_release_crq_queue(struct crq_server_adapter *adapter)
+{
+	struct vio_dev *vdev = to_vio_dev(adapter->dev);
+	struct crq_queue *queue = &adapter->queue;
+
+	free_irq(vdev->irq, (void *)adapter);
+	tasklet_kill(&adapter->work_task);
+
+	if (adapter->reset_task)
+		kthread_stop(adapter->reset_task);
+
+	h_free_crq(vdev->unit_address);
+	dma_unmap_single(adapter->dev,
+			 queue->msg_token,
+			 queue->size * sizeof(*queue->msgs), DMA_BIDIRECTIONAL);
+	free_page((unsigned long)queue->msgs);
+}
+
+/**
+ * ibmvmc_reset_crq_queue - Reset CRQ Queue
+ *
+ * @adapter:	crq_server_adapter struct
+ *
+ * This function calls h_free_crq and then calls H_REG_CRQ and does all the
+ * bookkeeping to get us back to where we can communicate.
+ *
+ * Return:
+ *	0 - Success
+ *	Non-Zero - Failure
+ */
+static int ibmvmc_reset_crq_queue(struct crq_server_adapter *adapter)
+{
+	struct vio_dev *vdev = to_vio_dev(adapter->dev);
+	struct crq_queue *queue = &adapter->queue;
+	int rc = 0;
+
+	/* Close the CRQ */
+	h_free_crq(vdev->unit_address);
+
+	/* Clean out the queue */
+	memset(queue->msgs, 0x00, PAGE_SIZE);
+	queue->cur = 0;
+
+	/* And re-open it again */
+	rc = plpar_hcall_norets(H_REG_CRQ,
+				vdev->unit_address,
+				queue->msg_token, PAGE_SIZE);
+	if (rc == 2)
+		/* Adapter is good, but other end is not ready */
+		dev_warn(adapter->dev, "Partner adapter not ready\n");
+	else if (rc != 0)
+		dev_err(adapter->dev, "couldn't register crq--rc 0x%x\n", rc);
+
+	return rc;
+}
+
+/**
+ * crq_queue_next_crq: - Returns the next entry in message queue
+ * @queue:      crq_queue to use
+ *
+ * Returns pointer to next entry in queue, or NULL if there are no new
+ * entried in the CRQ.
+ */
+static struct ibmvmc_crq_msg *crq_queue_next_crq(struct crq_queue *queue)
+{
+	struct ibmvmc_crq_msg *crq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&queue->lock, flags);
+	crq = &queue->msgs[queue->cur];
+	if (crq->valid & 0x80) {
+		if (++queue->cur == queue->size)
+			queue->cur = 0;
+
+		/* Ensure the read of the valid bit occurs before reading any
+		 * other bits of the CRQ entry
+		 */
+		dma_rmb();
+	} else {
+		crq = NULL;
+	}
+
+	spin_unlock_irqrestore(&queue->lock, flags);
+
+	return crq;
+}
+
+/**
+ * ibmvmc_send_crq - Send CRQ
+ *
+ * @adapter:	crq_server_adapter struct
+ * @word1:	Word1 Data field
+ * @word2:	Word2 Data field
+ *
+ * Return:
+ *	0 - Success
+ *	Non-Zero - Failure
+ */
+static long ibmvmc_send_crq(struct crq_server_adapter *adapter,
+			    u64 word1, u64 word2)
+{
+	struct vio_dev *vdev = to_vio_dev(adapter->dev);
+	long rc = 0;
+
+	dev_dbg(adapter->dev, "(0x%x, 0x%016llx, 0x%016llx)\n",
+		vdev->unit_address, word1, word2);
+
+	/*
+	 * Ensure the command buffer is flushed to memory before handing it
+	 * over to the other side to prevent it from fetching any stale data.
+	 */
+	dma_wmb();
+	rc = plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, word1, word2);
+	dev_dbg(adapter->dev, "rc = 0x%lx\n", rc);
+
+	return rc;
+}
+
+/**
+ * alloc_dma_buffer - Create DMA Buffer
+ *
+ * @vdev:	vio_dev struct
+ * @size:	Size field
+ * @dma_handle:	DMA address field
+ *
+ * Allocates memory for the command queue and maps remote memory into an
+ * ioba.
+ *
+ * Returns a pointer to the buffer
+ */
+static void *alloc_dma_buffer(struct vio_dev *vdev, size_t size,
+			      dma_addr_t *dma_handle)
+{
+	/* allocate memory */
+	void *buffer = kzalloc(size, GFP_KERNEL);
+
+	if (!buffer) {
+		*dma_handle = 0;
+		return NULL;
+	}
+
+	/* DMA map */
+	*dma_handle = dma_map_single(&vdev->dev, buffer, size,
+				     DMA_BIDIRECTIONAL);
+
+	if (dma_mapping_error(&vdev->dev, *dma_handle)) {
+		*dma_handle = 0;
+		kzfree(buffer);
+		return NULL;
+	}
+
+	return buffer;
+}
+
+/**
+ * free_dma_buffer - Free DMA Buffer
+ *
+ * @vdev:	vio_dev struct
+ * @size:	Size field
+ * @vaddr:	Address field
+ * @dma_handle:	DMA address field
+ *
+ * Releases memory for a command queue and unmaps mapped remote memory.
+ */
+static void free_dma_buffer(struct vio_dev *vdev, size_t size, void *vaddr,
+			    dma_addr_t dma_handle)
+{
+	/* DMA unmap */
+	dma_unmap_single(&vdev->dev, dma_handle, size, DMA_BIDIRECTIONAL);
+
+	/* deallocate memory */
+	kzfree(vaddr);
+}
+
+/**
+ * ibmvmc_get_valid_hmc_buffer - Retrieve Valid HMC Buffer
+ *
+ * @hmc_index:	HMC Index Field
+ *
+ * Return:
+ *	Pointer to ibmvmc_buffer
+ */
+static struct ibmvmc_buffer *ibmvmc_get_valid_hmc_buffer(u8 hmc_index)
+{
+	struct ibmvmc_buffer *buffer;
+	struct ibmvmc_buffer *ret_buf = NULL;
+	unsigned long i;
+
+	if (hmc_index > ibmvmc.max_hmc_index)
+		return NULL;
+
+	buffer = hmcs[hmc_index].buffer;
+
+	for (i = 0; i < ibmvmc_max_buf_pool_size; i++) {
+		if (buffer[i].valid && buffer[i].free &&
+		    buffer[i].owner == VMC_BUF_OWNER_ALPHA) {
+			buffer[i].free = 0;
+			ret_buf = &buffer[i];
+			break;
+		}
+	}
+
+	return ret_buf;
+}
+
+/**
+ * ibmvmc_get_free_hmc_buffer - Get Free HMC Buffer
+ *
+ * @adapter:	crq_server_adapter struct
+ * @hmc_index:	Hmc Index field
+ *
+ * Return:
+ *	Pointer to ibmvmc_buffer
+ */
+static struct ibmvmc_buffer *ibmvmc_get_free_hmc_buffer(struct crq_server_adapter *adapter,
+							u8 hmc_index)
+{
+	struct ibmvmc_buffer *buffer;
+	struct ibmvmc_buffer *ret_buf = NULL;
+	unsigned long i;
+
+	if (hmc_index > ibmvmc.max_hmc_index) {
+		dev_info(adapter->dev, "get_free_hmc_buffer: invalid hmc_index=0x%x\n",
+			 hmc_index);
+		return NULL;
+	}
+
+	buffer = hmcs[hmc_index].buffer;
+
+	for (i = 0; i < ibmvmc_max_buf_pool_size; i++) {
+		if (buffer[i].free &&
+		    buffer[i].owner == VMC_BUF_OWNER_ALPHA) {
+			buffer[i].free = 0;
+			ret_buf = &buffer[i];
+			break;
+		}
+	}
+
+	return ret_buf;
+}
+
+/**
+ * ibmvmc_free_hmc_buffer - Free an HMC Buffer
+ *
+ * @hmc:	ibmvmc_hmc struct
+ * @buffer:	ibmvmc_buffer struct
+ *
+ */
+static void ibmvmc_free_hmc_buffer(struct ibmvmc_hmc *hmc,
+				   struct ibmvmc_buffer *buffer)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&hmc->lock, flags);
+	buffer->free = 1;
+	spin_unlock_irqrestore(&hmc->lock, flags);
+}
+
+/**
+ * ibmvmc_count_hmc_buffers - Count HMC Buffers
+ *
+ * @hmc_index:	HMC Index field
+ * @valid:	Valid number of buffers field
+ * @free:	Free number of buffers field
+ *
+ */
+static void ibmvmc_count_hmc_buffers(u8 hmc_index, unsigned int *valid,
+				     unsigned int *free)
+{
+	struct ibmvmc_buffer *buffer;
+	unsigned long i;
+	unsigned long flags;
+
+	if (hmc_index > ibmvmc.max_hmc_index)
+		return;
+
+	if (!valid || !free)
+		return;
+
+	*valid = 0; *free = 0;
+
+	buffer = hmcs[hmc_index].buffer;
+	spin_lock_irqsave(&hmcs[hmc_index].lock, flags);
+
+	for (i = 0; i < ibmvmc_max_buf_pool_size; i++) {
+		if (buffer[i].valid) {
+			*valid = *valid + 1;
+			if (buffer[i].free)
+				*free = *free + 1;
+		}
+	}
+
+	spin_unlock_irqrestore(&hmcs[hmc_index].lock, flags);
+}
+
+/**
+ * ibmvmc_get_free_hmc - Get Free HMC
+ *
+ * Return:
+ *	Pointer to an available HMC Connection
+ *	Null otherwise
+ */
+static struct ibmvmc_hmc *ibmvmc_get_free_hmc(void)
+{
+	unsigned long i;
+	unsigned long flags;
+
+	/*
+	 * Find an available HMC connection.
+	 */
+	for (i = 0; i <= ibmvmc.max_hmc_index; i++) {
+		spin_lock_irqsave(&hmcs[i].lock, flags);
+		if (hmcs[i].state == ibmhmc_state_free) {
+			hmcs[i].index = i;
+			hmcs[i].state = ibmhmc_state_initial;
+			spin_unlock_irqrestore(&hmcs[i].lock, flags);
+			return &hmcs[i];
+		}
+		spin_unlock_irqrestore(&hmcs[i].lock, flags);
+	}
+
+	return NULL;
+}
+
+/**
+ * ibmvmc_return_hmc - Return an HMC Connection
+ *
+ * @hmc:		ibmvmc_hmc struct
+ * @release_readers:	Number of readers connected to session
+ *
+ * This function releases the HMC connections back into the pool.
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvmc_return_hmc(struct ibmvmc_hmc *hmc, bool release_readers)
+{
+	struct ibmvmc_buffer *buffer;
+	struct crq_server_adapter *adapter;
+	struct vio_dev *vdev;
+	unsigned long i;
+	unsigned long flags;
+
+	if (!hmc || !hmc->adapter)
+		return -EIO;
+
+	if (release_readers) {
+		if (hmc->file_session) {
+			struct ibmvmc_file_session *session = hmc->file_session;
+
+			session->valid = 0;
+			wake_up_interruptible(&ibmvmc_read_wait);
+		}
+	}
+
+	adapter = hmc->adapter;
+	vdev = to_vio_dev(adapter->dev);
+
+	spin_lock_irqsave(&hmc->lock, flags);
+	hmc->index = 0;
+	hmc->state = ibmhmc_state_free;
+	hmc->queue_head = 0;
+	hmc->queue_tail = 0;
+	buffer = hmc->buffer;
+	for (i = 0; i < ibmvmc_max_buf_pool_size; i++) {
+		if (buffer[i].valid) {
+			free_dma_buffer(vdev,
+					ibmvmc.max_mtu,
+					buffer[i].real_addr_local,
+					buffer[i].dma_addr_local);
+			dev_dbg(adapter->dev, "Forgot buffer id 0x%lx\n", i);
+		}
+		memset(&buffer[i], 0, sizeof(struct ibmvmc_buffer));
+
+		hmc->queue_outbound_msgs[i] = VMC_INVALID_BUFFER_ID;
+	}
+
+	spin_unlock_irqrestore(&hmc->lock, flags);
+
+	return 0;
+}
+
+/**
+ * ibmvmc_send_open - Interface Open
+ * @buffer: Pointer to ibmvmc_buffer struct
+ * @hmc: Pointer to ibmvmc_hmc struct
+ *
+ * This command is sent by the management partition as the result of a
+ * management partition device request. It causes the hypervisor to
+ * prepare a set of data buffers for the management application connection
+ * indicated HMC idx. A unique HMC Idx would be used if multiple management
+ * applications running concurrently were desired. Before responding to this
+ * command, the hypervisor must provide the management partition with at
+ * least one of these new buffers via the Add Buffer. This indicates whether
+ * the messages are inbound or outbound from the hypervisor.
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvmc_send_open(struct ibmvmc_buffer *buffer,
+			    struct ibmvmc_hmc *hmc)
+{
+	struct ibmvmc_crq_msg crq_msg;
+	struct crq_server_adapter *adapter;
+	__be64 *crq_as_u64 = (__be64 *)&crq_msg;
+	int rc = 0;
+
+	if (!hmc || !hmc->adapter)
+		return -EIO;
+
+	adapter = hmc->adapter;
+
+	dev_dbg(adapter->dev, "send_open: 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
+		(unsigned long)buffer->size, (unsigned long)adapter->liobn,
+		(unsigned long)buffer->dma_addr_local,
+		(unsigned long)adapter->riobn,
+		(unsigned long)buffer->dma_addr_remote);
+
+	rc = h_copy_rdma(buffer->size,
+			 adapter->liobn,
+			 buffer->dma_addr_local,
+			 adapter->riobn,
+			 buffer->dma_addr_remote);
+	if (rc) {
+		dev_err(adapter->dev, "Error: In send_open, h_copy_rdma rc 0x%x\n",
+			rc);
+		return -EIO;
+	}
+
+	hmc->state = ibmhmc_state_opening;
+
+	crq_msg.valid = 0x80;
+	crq_msg.type = VMC_MSG_OPEN;
+	crq_msg.status = 0;
+	crq_msg.var1.rsvd = 0;
+	crq_msg.hmc_session = hmc->session;
+	crq_msg.hmc_index = hmc->index;
+	crq_msg.var2.buffer_id = cpu_to_be16(buffer->id);
+	crq_msg.rsvd = 0;
+	crq_msg.var3.rsvd = 0;
+
+	ibmvmc_send_crq(adapter, be64_to_cpu(crq_as_u64[0]),
+			be64_to_cpu(crq_as_u64[1]));
+
+	return rc;
+}
+
+/**
+ * ibmvmc_send_close - Interface Close
+ * @hmc: Pointer to ibmvmc_hmc struct
+ *
+ * This command is sent by the management partition to terminate a
+ * management application to hypervisor connection. When this command is
+ * sent, the management partition has quiesced all I/O operations to all
+ * buffers associated with this management application connection, and
+ * has freed any storage for these buffers.
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvmc_send_close(struct ibmvmc_hmc *hmc)
+{
+	struct ibmvmc_crq_msg crq_msg;
+	struct crq_server_adapter *adapter;
+	__be64 *crq_as_u64 = (__be64 *)&crq_msg;
+	int rc = 0;
+
+	if (!hmc || !hmc->adapter)
+		return -EIO;
+
+	adapter = hmc->adapter;
+
+	dev_info(adapter->dev, "CRQ send: close\n");
+
+	crq_msg.valid = 0x80;
+	crq_msg.type = VMC_MSG_CLOSE;
+	crq_msg.status = 0;
+	crq_msg.var1.rsvd = 0;
+	crq_msg.hmc_session = hmc->session;
+	crq_msg.hmc_index = hmc->index;
+	crq_msg.var2.rsvd = 0;
+	crq_msg.rsvd = 0;
+	crq_msg.var3.rsvd = 0;
+
+	ibmvmc_send_crq(adapter, be64_to_cpu(crq_as_u64[0]),
+			be64_to_cpu(crq_as_u64[1]));
+
+	return rc;
+}
+
+/**
+ * ibmvmc_send_capabilities - Send VMC Capabilities
+ *
+ * @adapter:	crq_server_adapter struct
+ *
+ * The capabilities message is an administrative message sent after the CRQ
+ * initialization sequence of messages and is used to exchange VMC capabilities
+ * between the management partition and the hypervisor. The management
+ * partition must send this message and the hypervisor must respond with VMC
+ * capabilities Response message before HMC interface message can begin. Any
+ * HMC interface messages received before the exchange of capabilities has
+ * complete are dropped.
+ *
+ * Return:
+ *	0 - Success
+ */
+static int ibmvmc_send_capabilities(struct crq_server_adapter *adapter)
+{
+	struct ibmvmc_admin_crq_msg crq_msg;
+	__be64 *crq_as_u64 = (__be64 *)&crq_msg;
+
+	dev_dbg(adapter->dev, "ibmvmc: CRQ send: capabilities\n");
+	crq_msg.valid = 0x80;
+	crq_msg.type = VMC_MSG_CAP;
+	crq_msg.status = 0;
+	crq_msg.rsvd[0] = 0;
+	crq_msg.rsvd[1] = 0;
+	crq_msg.max_hmc = ibmvmc_max_hmcs;
+	crq_msg.max_mtu = cpu_to_be32(ibmvmc_max_mtu);
+	crq_msg.pool_size = cpu_to_be16(ibmvmc_max_buf_pool_size);
+	crq_msg.crq_size = cpu_to_be16(adapter->queue.size);
+	crq_msg.version = cpu_to_be16(IBMVMC_PROTOCOL_VERSION);
+
+	ibmvmc_send_crq(adapter, be64_to_cpu(crq_as_u64[0]),
+			be64_to_cpu(crq_as_u64[1]));
+
+	ibmvmc.state = ibmvmc_state_capabilities;
+
+	return 0;
+}
+
+/**
+ * ibmvmc_send_add_buffer_resp - Add Buffer Response
+ *
+ * @adapter:	crq_server_adapter struct
+ * @status:	Status field
+ * @hmc_session: HMC Session field
+ * @hmc_index:	HMC Index field
+ * @buffer_id:	Buffer Id field
+ *
+ * This command is sent by the management partition to the hypervisor in
+ * response to the Add Buffer message. The Status field indicates the result of
+ * the command.
+ *
+ * Return:
+ *	0 - Success
+ */
+static int ibmvmc_send_add_buffer_resp(struct crq_server_adapter *adapter,
+				       u8 status, u8 hmc_session,
+				       u8 hmc_index, u16 buffer_id)
+{
+	struct ibmvmc_crq_msg crq_msg;
+	__be64 *crq_as_u64 = (__be64 *)&crq_msg;
+
+	dev_dbg(adapter->dev, "CRQ send: add_buffer_resp\n");
+	crq_msg.valid = 0x80;
+	crq_msg.type = VMC_MSG_ADD_BUF_RESP;
+	crq_msg.status = status;
+	crq_msg.var1.rsvd = 0;
+	crq_msg.hmc_session = hmc_session;
+	crq_msg.hmc_index = hmc_index;
+	crq_msg.var2.buffer_id = cpu_to_be16(buffer_id);
+	crq_msg.rsvd = 0;
+	crq_msg.var3.rsvd = 0;
+
+	ibmvmc_send_crq(adapter, be64_to_cpu(crq_as_u64[0]),
+			be64_to_cpu(crq_as_u64[1]));
+
+	return 0;
+}
+
+/**
+ * ibmvmc_send_rem_buffer_resp - Remove Buffer Response
+ *
+ * @adapter:	crq_server_adapter struct
+ * @status:	Status field
+ * @hmc_session: HMC Session field
+ * @hmc_index:	HMC Index field
+ * @buffer_id:	Buffer Id field
+ *
+ * This command is sent by the management partition to the hypervisor in
+ * response to the Remove Buffer message. The Buffer ID field indicates
+ * which buffer the management partition selected to remove. The Status
+ * field indicates the result of the command.
+ *
+ * Return:
+ *	0 - Success
+ */
+static int ibmvmc_send_rem_buffer_resp(struct crq_server_adapter *adapter,
+				       u8 status, u8 hmc_session,
+				       u8 hmc_index, u16 buffer_id)
+{
+	struct ibmvmc_crq_msg crq_msg;
+	__be64 *crq_as_u64 = (__be64 *)&crq_msg;
+
+	dev_dbg(adapter->dev, "CRQ send: rem_buffer_resp\n");
+	crq_msg.valid = 0x80;
+	crq_msg.type = VMC_MSG_REM_BUF_RESP;
+	crq_msg.status = status;
+	crq_msg.var1.rsvd = 0;
+	crq_msg.hmc_session = hmc_session;
+	crq_msg.hmc_index = hmc_index;
+	crq_msg.var2.buffer_id = cpu_to_be16(buffer_id);
+	crq_msg.rsvd = 0;
+	crq_msg.var3.rsvd = 0;
+
+	ibmvmc_send_crq(adapter, be64_to_cpu(crq_as_u64[0]),
+			be64_to_cpu(crq_as_u64[1]));
+
+	return 0;
+}
+
+/**
+ * ibmvmc_send_msg - Signal Message
+ *
+ * @adapter:	crq_server_adapter struct
+ * @buffer:	ibmvmc_buffer struct
+ * @hmc:	ibmvmc_hmc struct
+ * @msg_length:	message length field
+ *
+ * This command is sent between the management partition and the hypervisor
+ * in order to signal the arrival of an HMC protocol message. The command
+ * can be sent by both the management partition and the hypervisor. It is
+ * used for all traffic between the management application and the hypervisor,
+ * regardless of who initiated the communication.
+ *
+ * There is no response to this message.
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvmc_send_msg(struct crq_server_adapter *adapter,
+			   struct ibmvmc_buffer *buffer,
+			   struct ibmvmc_hmc *hmc, int msg_len)
+{
+	struct ibmvmc_crq_msg crq_msg;
+	__be64 *crq_as_u64 = (__be64 *)&crq_msg;
+	int rc = 0;
+
+	dev_dbg(adapter->dev, "CRQ send: rdma to HV\n");
+	rc = h_copy_rdma(msg_len,
+			 adapter->liobn,
+			 buffer->dma_addr_local,
+			 adapter->riobn,
+			 buffer->dma_addr_remote);
+	if (rc) {
+		dev_err(adapter->dev, "Error in send_msg, h_copy_rdma rc 0x%x\n",
+			rc);
+		return rc;
+	}
+
+	crq_msg.valid = 0x80;
+	crq_msg.type = VMC_MSG_SIGNAL;
+	crq_msg.status = 0;
+	crq_msg.var1.rsvd = 0;
+	crq_msg.hmc_session = hmc->session;
+	crq_msg.hmc_index = hmc->index;
+	crq_msg.var2.buffer_id = cpu_to_be16(buffer->id);
+	crq_msg.var3.msg_len = cpu_to_be32(msg_len);
+	dev_dbg(adapter->dev, "CRQ send: msg to HV 0x%llx 0x%llx\n",
+		be64_to_cpu(crq_as_u64[0]), be64_to_cpu(crq_as_u64[1]));
+
+	buffer->owner = VMC_BUF_OWNER_HV;
+	ibmvmc_send_crq(adapter, be64_to_cpu(crq_as_u64[0]),
+			be64_to_cpu(crq_as_u64[1]));
+
+	return rc;
+}
+
+/**
+ * ibmvmc_open - Open Session
+ *
+ * @inode:	inode struct
+ * @file:	file struct
+ *
+ * Return:
+ *	0 - Success
+ */
+static int ibmvmc_open(struct inode *inode, struct file *file)
+{
+	struct ibmvmc_file_session *session;
+	int rc = 0;
+
+	pr_debug("%s: inode = 0x%lx, file = 0x%lx, state = 0x%x\n", __func__,
+		 (unsigned long)inode, (unsigned long)file,
+		 ibmvmc.state);
+
+	session = kzalloc(sizeof(*session), GFP_KERNEL);
+	session->file = file;
+	file->private_data = session;
+
+	return rc;
+}
+
+/**
+ * ibmvmc_close - Close Session
+ *
+ * @inode:	inode struct
+ * @file:	file struct
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvmc_close(struct inode *inode, struct file *file)
+{
+	struct ibmvmc_file_session *session;
+	struct ibmvmc_hmc *hmc;
+	int rc = 0;
+	unsigned long flags;
+
+	pr_debug("%s: file = 0x%lx, state = 0x%x\n", __func__,
+		 (unsigned long)file, ibmvmc.state);
+
+	session = file->private_data;
+	if (!session)
+		return -EIO;
+
+	hmc = session->hmc;
+	if (hmc) {
+		if (!hmc->adapter)
+			return -EIO;
+
+		if (ibmvmc.state == ibmvmc_state_failed) {
+			dev_warn(hmc->adapter->dev, "close: state_failed\n");
+			return -EIO;
+		}
+
+		spin_lock_irqsave(&hmc->lock, flags);
+		if (hmc->state >= ibmhmc_state_opening) {
+			rc = ibmvmc_send_close(hmc);
+			if (rc)
+				dev_warn(hmc->adapter->dev, "close: send_close failed.\n");
+		}
+		spin_unlock_irqrestore(&hmc->lock, flags);
+	}
+
+	kzfree(session);
+
+	return rc;
+}
+
+/**
+ * ibmvmc_read - Read
+ *
+ * @file:	file struct
+ * @buf:	Character buffer
+ * @nbytes:	Size in bytes
+ * @ppos:	Offset
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static ssize_t ibmvmc_read(struct file *file, char *buf, size_t nbytes,
+			   loff_t *ppos)
+{
+	struct ibmvmc_file_session *session;
+	struct ibmvmc_hmc *hmc;
+	struct crq_server_adapter *adapter;
+	struct ibmvmc_buffer *buffer;
+	ssize_t n;
+	ssize_t retval = 0;
+	unsigned long flags;
+	DEFINE_WAIT(wait);
+
+	pr_debug("ibmvmc: read: file = 0x%lx, buf = 0x%lx, nbytes = 0x%lx\n",
+		 (unsigned long)file, (unsigned long)buf,
+		 (unsigned long)nbytes);
+
+	if (nbytes == 0)
+		return 0;
+
+	if (nbytes > ibmvmc.max_mtu) {
+		pr_warn("ibmvmc: read: nbytes invalid 0x%x\n",
+			(unsigned int)nbytes);
+		return -EINVAL;
+	}
+
+	session = file->private_data;
+	if (!session) {
+		pr_warn("ibmvmc: read: no session\n");
+		return -EIO;
+	}
+
+	hmc = session->hmc;
+	if (!hmc) {
+		pr_warn("ibmvmc: read: no hmc\n");
+		return -EIO;
+	}
+
+	adapter = hmc->adapter;
+	if (!adapter) {
+		pr_warn("ibmvmc: read: no adapter\n");
+		return -EIO;
+	}
+
+	do {
+		prepare_to_wait(&ibmvmc_read_wait, &wait, TASK_INTERRUPTIBLE);
+
+		spin_lock_irqsave(&hmc->lock, flags);
+		if (hmc->queue_tail != hmc->queue_head)
+			/* Data is available */
+			break;
+
+		spin_unlock_irqrestore(&hmc->lock, flags);
+
+		if (!session->valid) {
+			retval = -EBADFD;
+			goto out;
+		}
+		if (file->f_flags & O_NONBLOCK) {
+			retval = -EAGAIN;
+			goto out;
+		}
+
+		schedule();
+
+		if (signal_pending(current)) {
+			retval = -ERESTARTSYS;
+			goto out;
+		}
+	} while (1);
+
+	buffer = &(hmc->buffer[hmc->queue_outbound_msgs[hmc->queue_tail]]);
+	hmc->queue_tail++;
+	if (hmc->queue_tail == ibmvmc_max_buf_pool_size)
+		hmc->queue_tail = 0;
+	spin_unlock_irqrestore(&hmc->lock, flags);
+
+	nbytes = min_t(size_t, nbytes, buffer->msg_len);
+	n = copy_to_user((void *)buf, buffer->real_addr_local, nbytes);
+	dev_dbg(adapter->dev, "read: copy to user nbytes = 0x%lx.\n", nbytes);
+	ibmvmc_free_hmc_buffer(hmc, buffer);
+	retval = nbytes;
+
+	if (n) {
+		dev_warn(adapter->dev, "read: copy to user failed.\n");
+		retval = -EFAULT;
+	}
+
+ out:
+	finish_wait(&ibmvmc_read_wait, &wait);
+	dev_dbg(adapter->dev, "read: out %ld\n", retval);
+	return retval;
+}
+
+/**
+ * ibmvmc_poll - Poll
+ *
+ * @file:	file struct
+ * @wait:	Poll Table
+ *
+ * Return:
+ *	poll.h return values
+ */
+static unsigned int ibmvmc_poll(struct file *file, poll_table *wait)
+{
+	struct ibmvmc_file_session *session;
+	struct ibmvmc_hmc *hmc;
+	unsigned int mask = 0;
+
+	session = file->private_data;
+	if (!session)
+		return 0;
+
+	hmc = session->hmc;
+	if (!hmc)
+		return 0;
+
+	poll_wait(file, &ibmvmc_read_wait, wait);
+
+	if (hmc->queue_head != hmc->queue_tail)
+		mask |= POLLIN | POLLRDNORM;
+
+	return mask;
+}
+
+/**
+ * ibmvmc_write - Write
+ *
+ * @file:	file struct
+ * @buf:	Character buffer
+ * @count:	Count field
+ * @ppos:	Offset
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static ssize_t ibmvmc_write(struct file *file, const char *buffer,
+			    size_t count, loff_t *ppos)
+{
+	struct ibmvmc_buffer *vmc_buffer;
+	struct ibmvmc_file_session *session;
+	struct crq_server_adapter *adapter;
+	struct ibmvmc_hmc *hmc;
+	unsigned char *buf;
+	unsigned long flags;
+	size_t bytes;
+	const char *p = buffer;
+	size_t c = count;
+	int ret = 0;
+
+	session = file->private_data;
+	if (!session)
+		return -EIO;
+
+	hmc = session->hmc;
+	if (!hmc)
+		return -EIO;
+
+	spin_lock_irqsave(&hmc->lock, flags);
+	if (hmc->state == ibmhmc_state_free) {
+		/* HMC connection is not valid (possibly was reset under us). */
+		ret = -EIO;
+		goto out;
+	}
+
+	adapter = hmc->adapter;
+	if (!adapter) {
+		ret = -EIO;
+		goto out;
+	}
+
+	if (count > ibmvmc.max_mtu) {
+		dev_warn(adapter->dev, "invalid buffer size 0x%lx\n",
+			 (unsigned long)count);
+		ret = -EIO;
+		goto out;
+	}
+
+	/* Waiting for the open resp message to the ioctl(1) - retry */
+	if (hmc->state == ibmhmc_state_opening) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* Make sure the ioctl() was called & the open msg sent, and that
+	 * the HMC connection has not failed.
+	 */
+	if (hmc->state != ibmhmc_state_ready) {
+		ret = -EIO;
+		goto out;
+	}
+
+	vmc_buffer = ibmvmc_get_valid_hmc_buffer(hmc->index);
+	if (!vmc_buffer) {
+		/* No buffer available for the msg send, or we have not yet
+		 * completed the open/open_resp sequence.  Retry until this is
+		 * complete.
+		 */
+		ret = -EBUSY;
+		goto out;
+	}
+	if (!vmc_buffer->real_addr_local) {
+		dev_err(adapter->dev, "no buffer storage assigned\n");
+		ret = -EIO;
+		goto out;
+	}
+	buf = vmc_buffer->real_addr_local;
+
+	while (c > 0) {
+		bytes = min_t(size_t, c, vmc_buffer->size);
+
+		bytes -= copy_from_user(buf, p, bytes);
+		if (!bytes) {
+			ret = -EFAULT;
+			goto out;
+		}
+		c -= bytes;
+		p += bytes;
+	}
+	if (p == buffer)
+		goto out;
+
+	file->f_path.dentry->d_inode->i_mtime = current_time(file_inode(file));
+	mark_inode_dirty(file->f_path.dentry->d_inode);
+
+	dev_dbg(adapter->dev, "write: file = 0x%lx, count = 0x%lx\n",
+		(unsigned long)file, (unsigned long)count);
+
+	ibmvmc_send_msg(adapter, vmc_buffer, hmc, count);
+	ret = p - buffer;
+ out:
+	spin_unlock_irqrestore(&hmc->lock, flags);
+	return (ssize_t)(ret);
+}
+
+/**
+ * ibmvmc_setup_hmc - Setup the HMC
+ *
+ * @session:	ibmvmc_file_session struct
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static long ibmvmc_setup_hmc(struct ibmvmc_file_session *session)
+{
+	struct ibmvmc_hmc *hmc;
+	unsigned int valid, free, index;
+
+	if (ibmvmc.state == ibmvmc_state_failed) {
+		pr_warn("ibmvmc: Reserve HMC: state_failed\n");
+		return -EIO;
+	}
+
+	if (ibmvmc.state < ibmvmc_state_ready) {
+		pr_warn("ibmvmc: Reserve HMC: not state_ready\n");
+		return -EAGAIN;
+	}
+
+	/* Device is busy until capabilities have been exchanged and we
+	 * have a generic buffer for each possible HMC connection.
+	 */
+	for (index = 0; index <= ibmvmc.max_hmc_index; index++) {
+		valid = 0;
+		ibmvmc_count_hmc_buffers(index, &valid, &free);
+		if (valid == 0) {
+			pr_warn("ibmvmc: buffers not ready for index %d\n",
+				index);
+			return -ENOBUFS;
+		}
+	}
+
+	/* Get an hmc object, and transition to ibmhmc_state_initial */
+	hmc = ibmvmc_get_free_hmc();
+	if (!hmc) {
+		pr_warn("%s: free hmc not found\n", __func__);
+		return -EBUSY;
+	}
+
+	hmc->session = hmc->session + 1;
+	if (hmc->session == 0xff)
+		hmc->session = 1;
+
+	session->hmc = hmc;
+	hmc->adapter = &ibmvmc_adapter;
+	hmc->file_session = session;
+	session->valid = 1;
+
+	return 0;
+}
+
+/**
+ * ibmvmc_ioctl_sethmcid - IOCTL Set HMC ID
+ *
+ * @session:	ibmvmc_file_session struct
+ * @new_hmc_id:	HMC id field
+ *
+ * IOCTL command to setup the hmc id
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static long ibmvmc_ioctl_sethmcid(struct ibmvmc_file_session *session,
+				  unsigned char __user *new_hmc_id)
+{
+	struct ibmvmc_hmc *hmc;
+	struct ibmvmc_buffer *buffer;
+	size_t bytes;
+	char print_buffer[HMC_ID_LEN + 1];
+	unsigned long flags;
+	long rc = 0;
+
+	/* Reserve HMC session */
+	hmc = session->hmc;
+	if (!hmc) {
+		rc = ibmvmc_setup_hmc(session);
+		if (rc)
+			return rc;
+
+		hmc = session->hmc;
+		if (!hmc) {
+			pr_err("ibmvmc: setup_hmc success but no hmc\n");
+			return -EIO;
+		}
+	}
+
+	if (hmc->state != ibmhmc_state_initial) {
+		pr_warn("ibmvmc: sethmcid: invalid state to send open 0x%x\n",
+			hmc->state);
+		return -EIO;
+	}
+
+	bytes = copy_from_user(hmc->hmc_id, new_hmc_id, HMC_ID_LEN);
+	if (bytes)
+		return -EFAULT;
+
+	/* Send Open Session command */
+	spin_lock_irqsave(&hmc->lock, flags);
+	buffer = ibmvmc_get_valid_hmc_buffer(hmc->index);
+	spin_unlock_irqrestore(&hmc->lock, flags);
+
+	if (!buffer || !buffer->real_addr_local) {
+		pr_warn("ibmvmc: sethmcid: no buffer available\n");
+		return -EIO;
+	}
+
+	/* Make sure buffer is NULL terminated before trying to print it */
+	memset(print_buffer, 0, HMC_ID_LEN + 1);
+	strncpy(print_buffer, hmc->hmc_id, HMC_ID_LEN);
+	pr_info("ibmvmc: sethmcid: Set HMC ID: \"%s\"\n", print_buffer);
+
+	memcpy(buffer->real_addr_local, hmc->hmc_id, HMC_ID_LEN);
+	/* RDMA over ID, send open msg, change state to ibmhmc_state_opening */
+	rc = ibmvmc_send_open(buffer, hmc);
+
+	return rc;
+}
+
+/**
+ * ibmvmc_ioctl_query - IOCTL Query
+ *
+ * @session:	ibmvmc_file_session struct
+ * @ret_struct:	ibmvmc_query_struct
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static long ibmvmc_ioctl_query(struct ibmvmc_file_session *session,
+			       struct ibmvmc_query_struct __user *ret_struct)
+{
+	struct ibmvmc_query_struct query_struct;
+	size_t bytes;
+
+	memset(&query_struct, 0, sizeof(query_struct));
+	query_struct.have_vmc = (ibmvmc.state > ibmvmc_state_initial);
+	query_struct.state = ibmvmc.state;
+	query_struct.vmc_drc_index = ibmvmc.vmc_drc_index;
+
+	bytes = copy_to_user(ret_struct, &query_struct,
+			     sizeof(query_struct));
+	if (bytes)
+		return -EFAULT;
+
+	return 0;
+}
+
+/**
+ * ibmvmc_ioctl_requestvmc - IOCTL Request VMC
+ *
+ * @session:	ibmvmc_file_session struct
+ * @ret_vmc_index:	VMC Index
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static long ibmvmc_ioctl_requestvmc(struct ibmvmc_file_session *session,
+				    u32 __user *ret_vmc_index)
+{
+	/* TODO: (adreznec) Add locking to control multiple process access */
+	size_t bytes;
+	long rc;
+	u32 vmc_drc_index;
+
+	/* Call to request the VMC device from phyp*/
+	rc = h_request_vmc(&vmc_drc_index);
+	pr_debug("ibmvmc: requestvmc: H_REQUEST_VMC rc = 0x%lx\n", rc);
+
+	if (rc == H_SUCCESS) {
+		rc = 0;
+	} else if (rc == H_FUNCTION) {
+		pr_err("ibmvmc: requestvmc: h_request_vmc not supported\n");
+		return -EPERM;
+	} else if (rc == H_AUTHORITY) {
+		pr_err("ibmvmc: requestvmc: hypervisor denied vmc request\n");
+		return -EPERM;
+	} else if (rc == H_HARDWARE) {
+		pr_err("ibmvmc: requestvmc: hypervisor hardware fault\n");
+		return -EIO;
+	} else if (rc == H_RESOURCE) {
+		pr_err("ibmvmc: requestvmc: vmc resource unavailable\n");
+		return -ENODEV;
+	} else if (rc == H_NOT_AVAILABLE) {
+		pr_err("ibmvmc: requestvmc: system cannot be vmc managed\n");
+		return -EPERM;
+	} else if (rc == H_PARAMETER) {
+		pr_err("ibmvmc: requestvmc: invalid parameter\n");
+		return -EINVAL;
+	}
+
+	/* Success, set the vmc index in global struct */
+	ibmvmc.vmc_drc_index = vmc_drc_index;
+
+	bytes = copy_to_user(ret_vmc_index, &vmc_drc_index,
+			     sizeof(*ret_vmc_index));
+	if (bytes) {
+		pr_warn("ibmvmc: requestvmc: copy to user failed.\n");
+		return -EFAULT;
+	}
+	return rc;
+}
+
+/**
+ * ibmvmc_ioctl - IOCTL
+ *
+ * @session:	ibmvmc_file_session struct
+ * @cmd:	cmd field
+ * @arg:	Argument field
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static long ibmvmc_ioctl(struct file *file,
+			 unsigned int cmd, unsigned long arg)
+{
+	struct ibmvmc_file_session *session = file->private_data;
+
+	pr_debug("ibmvmc: ioctl file=0x%lx, cmd=0x%x, arg=0x%lx, ses=0x%lx\n",
+		 (unsigned long)file, cmd, arg,
+		 (unsigned long)session);
+
+	if (!session) {
+		pr_warn("ibmvmc: ioctl: no session\n");
+		return -EIO;
+	}
+
+	switch (cmd) {
+	case VMC_IOCTL_SETHMCID:
+		return ibmvmc_ioctl_sethmcid(session,
+			(unsigned char __user *)arg);
+	case VMC_IOCTL_QUERY:
+		return ibmvmc_ioctl_query(session,
+			(struct ibmvmc_query_struct __user *)arg);
+	case VMC_IOCTL_REQUESTVMC:
+		return ibmvmc_ioctl_requestvmc(session,
+			(unsigned int __user *)arg);
+	default:
+		pr_warn("ibmvmc: unknown ioctl 0x%x\n", cmd);
+		return -EINVAL;
+	}
+}
+
+static const struct file_operations ibmvmc_fops = {
+	.owner		= THIS_MODULE,
+	.read		= ibmvmc_read,
+	.write		= ibmvmc_write,
+	.poll		= ibmvmc_poll,
+	.unlocked_ioctl	= ibmvmc_ioctl,
+	.open           = ibmvmc_open,
+	.release        = ibmvmc_close,
+};
+
+/**
+ * ibmvmc_add_buffer - Add Buffer
+ *
+ * @adapter: crq_server_adapter struct
+ * @crq:	ibmvmc_crq_msg struct
+ *
+ * This message transfers a buffer from hypervisor ownership to management
+ * partition ownership. The LIOBA is obtained from the virtual TCE table
+ * associated with the hypervisor side of the VMC device, and points to a
+ * buffer of size MTU (as established in the capabilities exchange).
+ *
+ * Typical flow for ading buffers:
+ * 1. A new management application connection is opened by the management
+ *	partition.
+ * 2. The hypervisor assigns new buffers for the traffic associated with
+ *	that connection.
+ * 3. The hypervisor sends VMC Add Buffer messages to the management
+ *	partition, informing it of the new buffers.
+ * 4. The hypervisor sends an HMC protocol message (to the management
+ *	application) notifying it of the new buffers. This informs the
+ *	application that it has buffers available for sending HMC
+ *	commands.
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvmc_add_buffer(struct crq_server_adapter *adapter,
+			     struct ibmvmc_crq_msg *crq)
+{
+	struct ibmvmc_buffer *buffer;
+	u8 hmc_index;
+	u8 hmc_session;
+	u16 buffer_id;
+	unsigned long flags;
+	int rc = 0;
+
+	if (!crq)
+		return -1;
+
+	hmc_session = crq->hmc_session;
+	hmc_index = crq->hmc_index;
+	buffer_id = be16_to_cpu(crq->var2.buffer_id);
+
+	if (hmc_index > ibmvmc.max_hmc_index) {
+		dev_err(adapter->dev, "add_buffer: invalid hmc_index = 0x%x\n",
+			hmc_index);
+		ibmvmc_send_add_buffer_resp(adapter, VMC_MSG_INVALID_HMC_INDEX,
+					    hmc_session, hmc_index, buffer_id);
+		return -1;
+	}
+
+	if (buffer_id >= ibmvmc.max_buffer_pool_size) {
+		dev_err(adapter->dev, "add_buffer: invalid buffer_id = 0x%x\n",
+			buffer_id);
+		ibmvmc_send_add_buffer_resp(adapter, VMC_MSG_INVALID_BUFFER_ID,
+					    hmc_session, hmc_index, buffer_id);
+		return -1;
+	}
+
+	spin_lock_irqsave(&hmcs[hmc_index].lock, flags);
+	buffer = &hmcs[hmc_index].buffer[buffer_id];
+
+	if (buffer->real_addr_local || buffer->dma_addr_local) {
+		dev_warn(adapter->dev, "add_buffer: already allocated id = 0x%lx\n",
+			 (unsigned long)buffer_id);
+		spin_unlock_irqrestore(&hmcs[hmc_index].lock, flags);
+		ibmvmc_send_add_buffer_resp(adapter, VMC_MSG_INVALID_BUFFER_ID,
+					    hmc_session, hmc_index, buffer_id);
+		return -1;
+	}
+
+	buffer->real_addr_local = alloc_dma_buffer(to_vio_dev(adapter->dev),
+						   ibmvmc.max_mtu,
+						   &buffer->dma_addr_local);
+
+	if (!buffer->real_addr_local) {
+		dev_err(adapter->dev, "add_buffer: alloc_dma_buffer failed.\n");
+		spin_unlock_irqrestore(&hmcs[hmc_index].lock, flags);
+		ibmvmc_send_add_buffer_resp(adapter, VMC_MSG_INTERFACE_FAILURE,
+					    hmc_session, hmc_index, buffer_id);
+		return -1;
+	}
+
+	buffer->dma_addr_remote = be32_to_cpu(crq->var3.lioba);
+	buffer->size = ibmvmc.max_mtu;
+	buffer->owner = crq->var1.owner;
+	buffer->free = 1;
+	/* Must ensure valid==1 is observable only after all other fields are */
+	dma_wmb();
+	buffer->valid = 1;
+	buffer->id = buffer_id;
+
+	dev_dbg(adapter->dev, "add_buffer: successfully added a buffer:\n");
+	dev_dbg(adapter->dev, "   index: %d, session: %d, buffer: 0x%x, owner: %d\n",
+		hmc_index, hmc_session, buffer_id, buffer->owner);
+	dev_dbg(adapter->dev, "   local: 0x%x, remote: 0x%x\n",
+		(u32)buffer->dma_addr_local,
+		(u32)buffer->dma_addr_remote);
+	spin_unlock_irqrestore(&hmcs[hmc_index].lock, flags);
+
+	ibmvmc_send_add_buffer_resp(adapter, VMC_MSG_SUCCESS, hmc_session,
+				    hmc_index, buffer_id);
+
+	return rc;
+}
+
+/**
+ * ibmvmc_rem_buffer - Remove Buffer
+ *
+ * @adapter: crq_server_adapter struct
+ * @crq:	ibmvmc_crq_msg struct
+ *
+ * This message requests an HMC buffer to be transferred from management
+ * partition ownership to hypervisor ownership. The management partition may
+ * not be able to satisfy the request at a particular point in time if all its
+ * buffers are in use. The management partition requires a depth of at least
+ * one inbound buffer to allow management application commands to flow to the
+ * hypervisor. It is, therefore, an interface error for the hypervisor to
+ * attempt to remove the management partition's last buffer.
+ *
+ * The hypervisor is expected to manage buffer usage with the management
+ * application directly and inform the management partition when buffers may be
+ * removed. The typical flow for removing buffers:
+ *
+ * 1. The management application no longer needs a communication path to a
+ *	particular hypervisor function. That function is closed.
+ * 2. The hypervisor and the management application quiesce all traffic to that
+ *	function. The hypervisor requests a reduction in buffer pool size.
+ * 3. The management application acknowledges the reduction in buffer pool size.
+ * 4. The hypervisor sends a Remove Buffer message to the management partition,
+ *	informing it of the reduction in buffers.
+ * 5. The management partition verifies it can remove the buffer. This is
+ *	possible if buffers have been quiesced.
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+/*
+ * The hypervisor requested that we pick an unused buffer, and return it.
+ * Before sending the buffer back, we free any storage associated with the
+ * buffer.
+ */
+static int ibmvmc_rem_buffer(struct crq_server_adapter *adapter,
+			     struct ibmvmc_crq_msg *crq)
+{
+	struct ibmvmc_buffer *buffer;
+	u8 hmc_index;
+	u8 hmc_session;
+	u16 buffer_id = 0;
+	unsigned long flags;
+	int rc = 0;
+
+	if (!crq)
+		return -1;
+
+	hmc_session = crq->hmc_session;
+	hmc_index = crq->hmc_index;
+
+	if (hmc_index > ibmvmc.max_hmc_index) {
+		dev_warn(adapter->dev, "rem_buffer: invalid hmc_index = 0x%x\n",
+			 hmc_index);
+		ibmvmc_send_rem_buffer_resp(adapter, VMC_MSG_INVALID_HMC_INDEX,
+					    hmc_session, hmc_index, buffer_id);
+		return -1;
+	}
+
+	spin_lock_irqsave(&hmcs[hmc_index].lock, flags);
+	buffer = ibmvmc_get_free_hmc_buffer(adapter, hmc_index);
+	if (!buffer) {
+		dev_info(adapter->dev, "rem_buffer: no buffer to remove\n");
+		spin_unlock_irqrestore(&hmcs[hmc_index].lock, flags);
+		ibmvmc_send_rem_buffer_resp(adapter, VMC_MSG_NO_BUFFER,
+					    hmc_session, hmc_index,
+					    VMC_INVALID_BUFFER_ID);
+		return -1;
+	}
+
+	buffer_id = buffer->id;
+
+	if (buffer->valid)
+		free_dma_buffer(to_vio_dev(adapter->dev),
+				ibmvmc.max_mtu,
+				buffer->real_addr_local,
+				buffer->dma_addr_local);
+
+	memset(buffer, 0, sizeof(struct ibmvmc_buffer));
+	spin_unlock_irqrestore(&hmcs[hmc_index].lock, flags);
+
+	dev_dbg(adapter->dev, "rem_buffer: removed buffer 0x%x.\n", buffer_id);
+	ibmvmc_send_rem_buffer_resp(adapter, VMC_MSG_SUCCESS, hmc_session,
+				    hmc_index, buffer_id);
+
+	return rc;
+}
+
+static int ibmvmc_recv_msg(struct crq_server_adapter *adapter,
+			   struct ibmvmc_crq_msg *crq)
+{
+	struct ibmvmc_buffer *buffer;
+	struct ibmvmc_hmc *hmc;
+	unsigned long msg_len;
+	u8 hmc_index;
+	u8 hmc_session;
+	u16 buffer_id;
+	unsigned long flags;
+	int rc = 0;
+
+	if (!crq)
+		return -1;
+
+	/* Hypervisor writes CRQs directly into our memory in big endian */
+	dev_dbg(adapter->dev, "Recv_msg: msg from HV 0x%016llx 0x%016llx\n",
+		be64_to_cpu(*((unsigned long *)crq)),
+		be64_to_cpu(*(((unsigned long *)crq) + 1)));
+
+	hmc_session = crq->hmc_session;
+	hmc_index = crq->hmc_index;
+	buffer_id = be16_to_cpu(crq->var2.buffer_id);
+	msg_len = be32_to_cpu(crq->var3.msg_len);
+
+	if (hmc_index > ibmvmc.max_hmc_index) {
+		dev_err(adapter->dev, "Recv_msg: invalid hmc_index = 0x%x\n",
+			hmc_index);
+		ibmvmc_send_add_buffer_resp(adapter, VMC_MSG_INVALID_HMC_INDEX,
+					    hmc_session, hmc_index, buffer_id);
+		return -1;
+	}
+
+	if (buffer_id >= ibmvmc.max_buffer_pool_size) {
+		dev_err(adapter->dev, "Recv_msg: invalid buffer_id = 0x%x\n",
+			buffer_id);
+		ibmvmc_send_add_buffer_resp(adapter, VMC_MSG_INVALID_BUFFER_ID,
+					    hmc_session, hmc_index, buffer_id);
+		return -1;
+	}
+
+	hmc = &hmcs[hmc_index];
+	spin_lock_irqsave(&hmc->lock, flags);
+
+	if (hmc->state == ibmhmc_state_free) {
+		dev_err(adapter->dev, "Recv_msg: invalid hmc state = 0x%x\n",
+			hmc->state);
+		/* HMC connection is not valid (possibly was reset under us). */
+		spin_unlock_irqrestore(&hmc->lock, flags);
+		return -1;
+	}
+
+	buffer = &hmc->buffer[buffer_id];
+
+	if (buffer->valid == 0 || buffer->owner == VMC_BUF_OWNER_ALPHA) {
+		dev_err(adapter->dev, "Recv_msg: not valid, or not HV.  0x%x 0x%x\n",
+			buffer->valid, buffer->owner);
+		spin_unlock_irqrestore(&hmc->lock, flags);
+		return -1;
+	}
+
+	/* RDMA the data into the partition. */
+	rc = h_copy_rdma(msg_len,
+			 adapter->riobn,
+			 buffer->dma_addr_remote,
+			 adapter->liobn,
+			 buffer->dma_addr_local);
+
+	dev_dbg(adapter->dev, "Recv_msg: msg_len = 0x%x, buffer_id = 0x%x, queue_head = 0x%x, hmc_idx = 0x%x\n",
+		(unsigned int)msg_len, (unsigned int)buffer_id,
+		(unsigned int)hmc->queue_head, (unsigned int)hmc_index);
+	buffer->msg_len = msg_len;
+	buffer->free = 0;
+	buffer->owner = VMC_BUF_OWNER_ALPHA;
+
+	if (rc) {
+		dev_err(adapter->dev, "Failure in recv_msg: h_copy_rdma = 0x%x\n",
+			rc);
+		spin_unlock_irqrestore(&hmc->lock, flags);
+		return -1;
+	}
+
+	/* Must be locked because read operates on the same data */
+	hmc->queue_outbound_msgs[hmc->queue_head] = buffer_id;
+	hmc->queue_head++;
+	if (hmc->queue_head == ibmvmc_max_buf_pool_size)
+		hmc->queue_head = 0;
+
+	if (hmc->queue_head == hmc->queue_tail)
+		dev_err(adapter->dev, "outbound buffer queue wrapped.\n");
+
+	spin_unlock_irqrestore(&hmc->lock, flags);
+
+	wake_up_interruptible(&ibmvmc_read_wait);
+
+	return 0;
+}
+
+/**
+ * ibmvmc_process_capabilities - Process Capabilities
+ *
+ * @adapter:	crq_server_adapter struct
+ * @crqp:	ibmvmc_crq_msg struct
+ *
+ */
+static void ibmvmc_process_capabilities(struct crq_server_adapter *adapter,
+					struct ibmvmc_crq_msg *crqp)
+{
+	struct ibmvmc_admin_crq_msg *crq = (struct ibmvmc_admin_crq_msg *)crqp;
+
+	if ((be16_to_cpu(crq->version) >> 8) !=
+			(IBMVMC_PROTOCOL_VERSION >> 8)) {
+		dev_err(adapter->dev, "init failed, incompatible versions 0x%x 0x%x\n",
+			be16_to_cpu(crq->version),
+			IBMVMC_PROTOCOL_VERSION);
+		ibmvmc.state = ibmvmc_state_failed;
+		return;
+	}
+
+	ibmvmc.max_mtu = min_t(u32, ibmvmc_max_mtu, be32_to_cpu(crq->max_mtu));
+	ibmvmc.max_buffer_pool_size = min_t(u16, ibmvmc_max_buf_pool_size,
+					    be16_to_cpu(crq->pool_size));
+	ibmvmc.max_hmc_index = min_t(u8, ibmvmc_max_hmcs, crq->max_hmc) - 1;
+	ibmvmc.state = ibmvmc_state_ready;
+
+	dev_info(adapter->dev, "Capabilities: mtu=0x%x, pool_size=0x%x, max_hmc=0x%x\n",
+		 ibmvmc.max_mtu, ibmvmc.max_buffer_pool_size,
+		 ibmvmc.max_hmc_index);
+}
+
+/**
+ * ibmvmc_validate_hmc_session - Validate HMC Session
+ *
+ * @adapter:	crq_server_adapter struct
+ * @crq:	ibmvmc_crq_msg struct
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvmc_validate_hmc_session(struct crq_server_adapter *adapter,
+				       struct ibmvmc_crq_msg *crq)
+{
+	unsigned char hmc_index;
+
+	hmc_index = crq->hmc_index;
+
+	if (crq->hmc_session == 0)
+		return 0;
+
+	if (hmc_index > ibmvmc.max_hmc_index)
+		return -1;
+
+	if (hmcs[hmc_index].session != crq->hmc_session) {
+		dev_warn(adapter->dev, "Drop, bad session: expected 0x%x, recv 0x%x\n",
+			 hmcs[hmc_index].session, crq->hmc_session);
+		return -1;
+	}
+
+	return 0;
+}
+
+/**
+ * ibmvmc_reset - Reset
+ *
+ * @adapter:	crq_server_adapter struct
+ * @xport_event:	export_event field
+ *
+ * Closes all HMC sessions and conditionally schedules a CRQ reset.
+ * @xport_event: If true, the partner closed their CRQ; we don't need to reset.
+ *               If false, we need to schedule a CRQ reset.
+ */
+static void ibmvmc_reset(struct crq_server_adapter *adapter, bool xport_event)
+{
+	int i;
+
+	if (ibmvmc.state != ibmvmc_state_sched_reset) {
+		dev_info(adapter->dev, "*** Reset to initial state.\n");
+		for (i = 0; i < ibmvmc_max_hmcs; i++)
+			ibmvmc_return_hmc(&hmcs[i], xport_event);
+
+		if (xport_event) {
+			/* CRQ was closed by the partner.  We don't need to do
+			 * anything except set ourself to the correct state to
+			 * handle init msgs.
+			 */
+			ibmvmc.state = ibmvmc_state_crqinit;
+		} else {
+			/* The partner did not close their CRQ - instead, we're
+			 * closing the CRQ on our end. Need to schedule this
+			 * for process context, because CRQ reset may require a
+			 * sleep.
+			 *
+			 * Setting ibmvmc.state here immediately prevents
+			 * ibmvmc_open from completing until the reset
+			 * completes in process context.
+			 */
+			ibmvmc.state = ibmvmc_state_sched_reset;
+			dev_dbg(adapter->dev, "Device reset scheduled");
+			wake_up_interruptible(&adapter->reset_wait_queue);
+		}
+	}
+}
+
+/**
+ * ibmvmc_reset_task - Reset Task
+ *
+ * @data:	Data field
+ *
+ * Performs a CRQ reset of the VMC device in process context.
+ * NOTE: This function should not be called directly, use ibmvmc_reset.
+ */
+static int ibmvmc_reset_task(void *data)
+{
+	struct crq_server_adapter *adapter = data;
+	int rc;
+
+	set_user_nice(current, -20);
+
+	while (!kthread_should_stop()) {
+		wait_event_interruptible(adapter->reset_wait_queue,
+			(ibmvmc.state == ibmvmc_state_sched_reset) ||
+			kthread_should_stop());
+
+		if (kthread_should_stop())
+			break;
+
+		dev_dbg(adapter->dev, "CRQ resetting in process context");
+		tasklet_disable(&adapter->work_task);
+
+		rc = ibmvmc_reset_crq_queue(adapter);
+
+		if (rc != H_SUCCESS && rc != H_RESOURCE) {
+			dev_err(adapter->dev, "Error initializing CRQ.  rc = 0x%x\n",
+				rc);
+			ibmvmc.state = ibmvmc_state_failed;
+		} else {
+			ibmvmc.state = ibmvmc_state_crqinit;
+
+			if (ibmvmc_send_crq(adapter, 0xC001000000000000LL, 0)
+			    != 0 && rc != H_RESOURCE)
+				dev_warn(adapter->dev, "Failed to send initialize CRQ message\n");
+		}
+
+		vio_enable_interrupts(to_vio_dev(adapter->dev));
+		tasklet_enable(&adapter->work_task);
+	}
+
+	return 0;
+}
+
+/**
+ * ibmvmc_process_open_resp - Process Open Response
+ *
+ * @crq: ibmvmc_crq_msg struct
+ * @adapter:    crq_server_adapter struct
+ *
+ * This command is sent by the hypervisor in response to the Interface
+ * Open message. When this message is received, the indicated buffer is
+ * again available for management partition use.
+ */
+static void ibmvmc_process_open_resp(struct ibmvmc_crq_msg *crq,
+				     struct crq_server_adapter *adapter)
+{
+	unsigned char hmc_index;
+	unsigned short buffer_id;
+
+	hmc_index = crq->hmc_index;
+	if (hmc_index > ibmvmc.max_hmc_index) {
+		/* Why would PHYP give an index > max negotiated? */
+		ibmvmc_reset(adapter, false);
+		return;
+	}
+
+	if (crq->status) {
+		dev_warn(adapter->dev, "open_resp: failed - status 0x%x\n",
+			 crq->status);
+		ibmvmc_return_hmc(&hmcs[hmc_index], false);
+		return;
+	}
+
+	if (hmcs[hmc_index].state == ibmhmc_state_opening) {
+		buffer_id = be16_to_cpu(crq->var2.buffer_id);
+		if (buffer_id >= ibmvmc.max_buffer_pool_size) {
+			dev_err(adapter->dev, "open_resp: invalid buffer_id = 0x%x\n",
+				buffer_id);
+			hmcs[hmc_index].state = ibmhmc_state_failed;
+		} else {
+			ibmvmc_free_hmc_buffer(&hmcs[hmc_index],
+					       &hmcs[hmc_index].buffer[buffer_id]);
+			hmcs[hmc_index].state = ibmhmc_state_ready;
+			dev_dbg(adapter->dev, "open_resp: set hmc state = ready\n");
+		}
+	} else {
+		dev_warn(adapter->dev, "open_resp: invalid hmc state (0x%x)\n",
+			 hmcs[hmc_index].state);
+	}
+}
+
+/**
+ * ibmvmc_process_close_resp - Process Close Response
+ *
+ * @crq: ibmvmc_crq_msg struct
+ * @adapter:    crq_server_adapter struct
+ *
+ * This command is sent by the hypervisor in response to the managemant
+ * application Interface Close message.
+ *
+ * If the close fails, simply reset the entire driver as the state of the VMC
+ * must be in tough shape.
+ */
+static void ibmvmc_process_close_resp(struct ibmvmc_crq_msg *crq,
+				      struct crq_server_adapter *adapter)
+{
+	unsigned char hmc_index;
+
+	hmc_index = crq->hmc_index;
+	if (hmc_index > ibmvmc.max_hmc_index) {
+		ibmvmc_reset(adapter, false);
+		return;
+	}
+
+	if (crq->status) {
+		dev_warn(adapter->dev, "close_resp: failed - status 0x%x\n",
+			 crq->status);
+		ibmvmc_reset(adapter, false);
+		return;
+	}
+
+	ibmvmc_return_hmc(&hmcs[hmc_index], false);
+}
+
+/**
+ * ibmvmc_crq_process - Process CRQ
+ *
+ * @adapter:    crq_server_adapter struct
+ * @crq:	ibmvmc_crq_msg struct
+ *
+ * Process the CRQ message based upon the type of message received.
+ *
+ */
+static void ibmvmc_crq_process(struct crq_server_adapter *adapter,
+			       struct ibmvmc_crq_msg *crq)
+{
+	switch (crq->type) {
+	case VMC_MSG_CAP_RESP:
+		dev_dbg(adapter->dev, "CRQ recv: capabilities resp (0x%x)\n",
+			crq->type);
+		if (ibmvmc.state == ibmvmc_state_capabilities)
+			ibmvmc_process_capabilities(adapter, crq);
+		else
+			dev_warn(adapter->dev, "caps msg invalid in state 0x%x\n",
+				 ibmvmc.state);
+		break;
+	case VMC_MSG_OPEN_RESP:
+		dev_dbg(adapter->dev, "CRQ recv: open resp (0x%x)\n",
+			crq->type);
+		if (ibmvmc_validate_hmc_session(adapter, crq) == 0)
+			ibmvmc_process_open_resp(crq, adapter);
+		break;
+	case VMC_MSG_ADD_BUF:
+		dev_dbg(adapter->dev, "CRQ recv: add buf (0x%x)\n",
+			crq->type);
+		if (ibmvmc_validate_hmc_session(adapter, crq) == 0)
+			ibmvmc_add_buffer(adapter, crq);
+		break;
+	case VMC_MSG_REM_BUF:
+		dev_dbg(adapter->dev, "CRQ recv: rem buf (0x%x)\n",
+			crq->type);
+		if (ibmvmc_validate_hmc_session(adapter, crq) == 0)
+			ibmvmc_rem_buffer(adapter, crq);
+		break;
+	case VMC_MSG_SIGNAL:
+		dev_dbg(adapter->dev, "CRQ recv: signal msg (0x%x)\n",
+			crq->type);
+		if (ibmvmc_validate_hmc_session(adapter, crq) == 0)
+			ibmvmc_recv_msg(adapter, crq);
+		break;
+	case VMC_MSG_CLOSE_RESP:
+		dev_dbg(adapter->dev, "CRQ recv: close resp (0x%x)\n",
+			crq->type);
+		if (ibmvmc_validate_hmc_session(adapter, crq) == 0)
+			ibmvmc_process_close_resp(crq, adapter);
+		break;
+	case VMC_MSG_CAP:
+	case VMC_MSG_OPEN:
+	case VMC_MSG_CLOSE:
+	case VMC_MSG_ADD_BUF_RESP:
+	case VMC_MSG_REM_BUF_RESP:
+		dev_warn(adapter->dev, "CRQ recv: unexpected msg (0x%x)\n",
+			 crq->type);
+		break;
+	default:
+		dev_warn(adapter->dev, "CRQ recv: unknown msg (0x%x)\n",
+			 crq->type);
+		break;
+	}
+}
+
+/**
+ * ibmvmc_handle_crq_init - Handle CRQ Init
+ *
+ * @crq:	ibmvmc_crq_msg struct
+ * @adapter:	crq_server_adapter struct
+ *
+ * Handle the type of crq initialization based on whether
+ * it is a message or a response.
+ *
+ */
+static void ibmvmc_handle_crq_init(struct ibmvmc_crq_msg *crq,
+				   struct crq_server_adapter *adapter)
+{
+	switch (crq->type) {
+	case 0x01:	/* Initialization message */
+		dev_dbg(adapter->dev, "CRQ recv: CRQ init msg - state 0x%x\n",
+			ibmvmc.state);
+		if (ibmvmc.state == ibmvmc_state_crqinit) {
+			/* Send back a response */
+			if (ibmvmc_send_crq(adapter, 0xC002000000000000,
+					    0) == 0)
+				ibmvmc_send_capabilities(adapter);
+			else
+				dev_err(adapter->dev, " Unable to send init rsp\n");
+		} else {
+			dev_err(adapter->dev, "Invalid state 0x%x mtu = 0x%x\n",
+				ibmvmc.state, ibmvmc.max_mtu);
+		}
+
+		break;
+	case 0x02:	/* Initialization response */
+		dev_dbg(adapter->dev, "CRQ recv: initialization resp msg - state 0x%x\n",
+			ibmvmc.state);
+		if (ibmvmc.state == ibmvmc_state_crqinit)
+			ibmvmc_send_capabilities(adapter);
+		break;
+	default:
+		dev_warn(adapter->dev, "Unknown crq message type 0x%lx\n",
+			 (unsigned long)crq->type);
+	}
+}
+
+/**
+ * ibmvmc_handle_crq - Handle CRQ
+ *
+ * @crq:	ibmvmc_crq_msg struct
+ * @adapter:	crq_server_adapter struct
+ *
+ * Read the command elements from the command queue and execute the
+ * requests based upon the type of crq message.
+ *
+ */
+static void ibmvmc_handle_crq(struct ibmvmc_crq_msg *crq,
+			      struct crq_server_adapter *adapter)
+{
+	switch (crq->valid) {
+	case 0xC0:		/* initialization */
+		ibmvmc_handle_crq_init(crq, adapter);
+		break;
+	case 0xFF:	/* Hypervisor telling us the connection is closed */
+		dev_warn(adapter->dev, "CRQ recv: virtual adapter failed - resetting.\n");
+		ibmvmc_reset(adapter, true);
+		break;
+	case 0x80:	/* real payload */
+		ibmvmc_crq_process(adapter, crq);
+		break;
+	default:
+		dev_warn(adapter->dev, "CRQ recv: unknown msg 0x%02x.\n",
+			 crq->valid);
+		break;
+	}
+}
+
+static void ibmvmc_task(unsigned long data)
+{
+	struct crq_server_adapter *adapter =
+		(struct crq_server_adapter *)data;
+	struct vio_dev *vdev = to_vio_dev(adapter->dev);
+	struct ibmvmc_crq_msg *crq;
+	int done = 0;
+
+	while (!done) {
+		/* Pull all the valid messages off the CRQ */
+		while ((crq = crq_queue_next_crq(&adapter->queue)) != NULL) {
+			ibmvmc_handle_crq(crq, adapter);
+			crq->valid = 0x00;
+			/* CRQ reset was requested, stop processing CRQs.
+			 * Interrupts will be re-enabled by the reset task.
+			 */
+			if (ibmvmc.state == ibmvmc_state_sched_reset)
+				return;
+		}
+
+		vio_enable_interrupts(vdev);
+		crq = crq_queue_next_crq(&adapter->queue);
+		if (crq) {
+			vio_disable_interrupts(vdev);
+			ibmvmc_handle_crq(crq, adapter);
+			crq->valid = 0x00;
+			/* CRQ reset was requested, stop processing CRQs.
+			 * Interrupts will be re-enabled by the reset task.
+			 */
+			if (ibmvmc.state == ibmvmc_state_sched_reset)
+				return;
+		} else {
+			done = 1;
+		}
+	}
+}
+
+/**
+ * ibmvmc_init_crq_queue - Init CRQ Queue
+ *
+ * @adapter:	crq_server_adapter struct
+ *
+ * Return:
+ *	0 - Success
+ *	Non-zero - Failure
+ */
+static int ibmvmc_init_crq_queue(struct crq_server_adapter *adapter)
+{
+	struct vio_dev *vdev = to_vio_dev(adapter->dev);
+	struct crq_queue *queue = &adapter->queue;
+	int rc = 0;
+	int retrc = 0;
+
+	queue->msgs = (struct ibmvmc_crq_msg *)get_zeroed_page(GFP_KERNEL);
+
+	if (!queue->msgs)
+		goto malloc_failed;
+
+	queue->size = PAGE_SIZE / sizeof(*queue->msgs);
+
+	queue->msg_token = dma_map_single(adapter->dev, queue->msgs,
+					  queue->size * sizeof(*queue->msgs),
+					  DMA_BIDIRECTIONAL);
+
+	if (dma_mapping_error(adapter->dev, queue->msg_token))
+		goto map_failed;
+
+	retrc = plpar_hcall_norets(H_REG_CRQ,
+				   vdev->unit_address,
+				   queue->msg_token, PAGE_SIZE);
+	retrc = rc;
+
+	if (rc == H_RESOURCE)
+		rc = ibmvmc_reset_crq_queue(adapter);
+
+	if (rc == 2) {
+		dev_warn(adapter->dev, "Partner adapter not ready\n");
+		retrc = 0;
+	} else if (rc != 0) {
+		dev_err(adapter->dev, "Error %d opening adapter\n", rc);
+		goto reg_crq_failed;
+	}
+
+	queue->cur = 0;
+	spin_lock_init(&queue->lock);
+
+	tasklet_init(&adapter->work_task, ibmvmc_task, (unsigned long)adapter);
+
+	if (request_irq(vdev->irq,
+			ibmvmc_handle_event,
+			0, "ibmvmc", (void *)adapter) != 0) {
+		dev_err(adapter->dev, "couldn't register irq 0x%x\n",
+			vdev->irq);
+		goto req_irq_failed;
+	}
+
+	rc = vio_enable_interrupts(vdev);
+	if (rc != 0) {
+		dev_err(adapter->dev, "Error %d enabling interrupts!!!\n", rc);
+		goto req_irq_failed;
+	}
+
+	return retrc;
+
+req_irq_failed:
+	/* Cannot have any work since we either never got our IRQ registered,
+	 * or never got interrupts enabled
+	 */
+	tasklet_kill(&adapter->work_task);
+	h_free_crq(vdev->unit_address);
+reg_crq_failed:
+	dma_unmap_single(adapter->dev,
+			 queue->msg_token,
+			 queue->size * sizeof(*queue->msgs), DMA_BIDIRECTIONAL);
+map_failed:
+	free_page((unsigned long)queue->msgs);
+malloc_failed:
+	return -ENOMEM;
+}
+
+/* Fill in the liobn and riobn fields on the adapter */
+static int read_dma_window(struct vio_dev *vdev,
+			   struct crq_server_adapter *adapter)
+{
+	const __be32 *dma_window;
+	const __be32 *prop;
+
+	/* TODO Using of_parse_dma_window would be better, but it doesn't give
+	 * a way to read multiple windows without already knowing the size of
+	 * a window or the number of windows
+	 */
+	dma_window =
+		(const __be32 *)vio_get_attribute(vdev, "ibm,my-dma-window",
+						NULL);
+	if (!dma_window) {
+		dev_warn(adapter->dev, "Couldn't find ibm,my-dma-window property\n");
+		return -1;
+	}
+
+	adapter->liobn = be32_to_cpu(*dma_window);
+	dma_window++;
+
+	prop = (const __be32 *)vio_get_attribute(vdev, "ibm,#dma-address-cells",
+						NULL);
+	if (!prop) {
+		dev_warn(adapter->dev, "Couldn't find ibm,#dma-address-cells property\n");
+		dma_window++;
+	} else {
+		dma_window += be32_to_cpu(*prop);
+	}
+
+	prop = (const __be32 *)vio_get_attribute(vdev, "ibm,#dma-size-cells",
+						NULL);
+	if (!prop) {
+		dev_warn(adapter->dev, "Couldn't find ibm,#dma-size-cells property\n");
+		dma_window++;
+	} else {
+		dma_window += be32_to_cpu(*prop);
+	}
+
+	/* dma_window should point to the second window now */
+	adapter->riobn = be32_to_cpu(*dma_window);
+
+	return 0;
+}
+
+static int ibmvmc_probe(struct vio_dev *vdev, const struct vio_device_id *id)
+{
+	struct crq_server_adapter *adapter = &ibmvmc_adapter;
+	int rc;
+
+	dev_set_drvdata(&vdev->dev, NULL);
+	memset(adapter, 0, sizeof(*adapter));
+	adapter->dev = &vdev->dev;
+
+	dev_info(adapter->dev, "Probe for UA 0x%x\n", vdev->unit_address);
+
+	rc = read_dma_window(vdev, adapter);
+	if (rc != 0) {
+		ibmvmc.state = ibmvmc_state_failed;
+		return -1;
+	}
+
+	dev_dbg(adapter->dev, "Probe: liobn 0x%x, riobn 0x%x\n",
+		adapter->liobn, adapter->riobn);
+
+	init_waitqueue_head(&adapter->reset_wait_queue);
+	adapter->reset_task = kthread_run(ibmvmc_reset_task, adapter, "ibmvmc");
+	if (IS_ERR(adapter->reset_task)) {
+		dev_err(adapter->dev, "Failed to start reset thread\n");
+		ibmvmc.state = ibmvmc_state_failed;
+		rc = PTR_ERR(adapter->reset_task);
+		adapter->reset_task = NULL;
+		return rc;
+	}
+
+	rc = ibmvmc_init_crq_queue(adapter);
+	if (rc != 0 && rc != H_RESOURCE) {
+		dev_err(adapter->dev, "Error initializing CRQ.  rc = 0x%x\n",
+			rc);
+		ibmvmc.state = ibmvmc_state_failed;
+		goto crq_failed;
+	}
+
+	ibmvmc.state = ibmvmc_state_crqinit;
+
+	/* Try to send an initialization message.  Note that this is allowed
+	 * to fail if the other end is not acive.  In that case we just wait
+	 * for the other side to initialize.
+	 */
+	if (ibmvmc_send_crq(adapter, 0xC001000000000000LL, 0) != 0 &&
+	    rc != H_RESOURCE)
+		dev_warn(adapter->dev, "Failed to send initialize CRQ message\n");
+
+	dev_set_drvdata(&vdev->dev, adapter);
+
+	return 0;
+
+crq_failed:
+	kthread_stop(adapter->reset_task);
+	adapter->reset_task = NULL;
+	return -EPERM;
+}
+
+static int ibmvmc_remove(struct vio_dev *vdev)
+{
+	struct crq_server_adapter *adapter = dev_get_drvdata(&vdev->dev);
+
+	dev_info(adapter->dev, "Entering remove for UA 0x%x\n",
+		 vdev->unit_address);
+	ibmvmc_release_crq_queue(adapter);
+
+	return 0;
+}
+
+static struct vio_device_id ibmvmc_device_table[] = {
+	{ "ibm,vmc", "IBM,vmc" },
+	{ "", "" }
+};
+MODULE_DEVICE_TABLE(vio, ibmvmc_device_table);
+
+static struct vio_driver ibmvmc_driver = {
+	.name        = ibmvmc_driver_name,
+	.id_table    = ibmvmc_device_table,
+	.probe       = ibmvmc_probe,
+	.remove      = ibmvmc_remove,
+};
+
+static void __init ibmvmc_scrub_module_parms(void)
+{
+	if (ibmvmc_max_mtu > MAX_MTU) {
+		pr_warn("ibmvmc: Max MTU reduced to %d\n", MAX_MTU);
+		ibmvmc_max_mtu = MAX_MTU;
+	} else if (ibmvmc_max_mtu < MIN_MTU) {
+		pr_warn("ibmvmc: Max MTU increased to %d\n", MIN_MTU);
+		ibmvmc_max_mtu = MIN_MTU;
+	}
+
+	if (ibmvmc_max_buf_pool_size > MAX_BUF_POOL_SIZE) {
+		pr_warn("ibmvmc: Max buffer pool size reduced to %d\n",
+			MAX_BUF_POOL_SIZE);
+		ibmvmc_max_buf_pool_size = MAX_BUF_POOL_SIZE;
+	} else if (ibmvmc_max_buf_pool_size < MIN_BUF_POOL_SIZE) {
+		pr_warn("ibmvmc: Max buffer pool size increased to %d\n",
+			MIN_BUF_POOL_SIZE);
+		ibmvmc_max_buf_pool_size = MIN_BUF_POOL_SIZE;
+	}
+
+	if (ibmvmc_max_hmcs > MAX_HMCS) {
+		pr_warn("ibmvmc: Max HMCs reduced to %d\n", MAX_HMCS);
+		ibmvmc_max_hmcs = MAX_HMCS;
+	} else if (ibmvmc_max_hmcs < MIN_HMCS) {
+		pr_warn("ibmvmc: Max HMCs increased to %d\n", MIN_HMCS);
+		ibmvmc_max_hmcs = MIN_HMCS;
+	}
+}
+
+static struct miscdevice ibmvmc_miscdev = {
+	.name = ibmvmc_driver_name,
+	.minor = MISC_DYNAMIC_MINOR,
+	.fops = &ibmvmc_fops,
+};
+
+static int __init ibmvmc_module_init(void)
+{
+	int rc, i, j;
+
+	ibmvmc.state = ibmvmc_state_initial;
+	pr_info("ibmvmc: version %s\n", IBMVMC_DRIVER_VERSION);
+
+	rc = misc_register(&ibmvmc_miscdev);
+	if (rc) {
+		pr_err("ibmvmc: misc registration failed\n");
+		goto misc_register_failed;
+	}
+	pr_info("ibmvmc: node %d:%d\n", MISC_MAJOR,
+		ibmvmc_miscdev.minor);
+
+	/* Initialize data structures */
+	memset(hmcs, 0, sizeof(struct ibmvmc_hmc) * MAX_HMCS);
+	for (i = 0; i < MAX_HMCS; i++) {
+		spin_lock_init(&hmcs[i].lock);
+		hmcs[i].state = ibmhmc_state_free;
+		for (j = 0; j < MAX_BUF_POOL_SIZE; j++)
+			hmcs[i].queue_outbound_msgs[j] = VMC_INVALID_BUFFER_ID;
+	}
+
+	/* Sanity check module parms */
+	ibmvmc_scrub_module_parms();
+
+	/*
+	 * Initialize some reasonable values.  Might be negotiated smaller
+	 * values during the capabilities exchange.
+	 */
+	ibmvmc.max_mtu = ibmvmc_max_mtu;
+	ibmvmc.max_buffer_pool_size = ibmvmc_max_buf_pool_size;
+	ibmvmc.max_hmc_index = ibmvmc_max_hmcs - 1;
+
+	rc = vio_register_driver(&ibmvmc_driver);
+
+	if (rc) {
+		pr_err("ibmvmc: rc %d from vio_register_driver\n", rc);
+		goto vio_reg_failed;
+	}
+
+	return 0;
+
+vio_reg_failed:
+	misc_deregister(&ibmvmc_miscdev);
+misc_register_failed:
+	return rc;
+}
+
+static void __exit ibmvmc_module_exit(void)
+{
+	pr_info("ibmvmc: module exit\n");
+	vio_unregister_driver(&ibmvmc_driver);
+	misc_deregister(&ibmvmc_miscdev);
+}
+
+module_init(ibmvmc_module_init);
+module_exit(ibmvmc_module_exit);
+
+module_param_named(buf_pool_size, ibmvmc_max_buf_pool_size,
+		   int, 0644);
+MODULE_PARM_DESC(buf_pool_size, "Buffer pool size");
+module_param_named(max_hmcs, ibmvmc_max_hmcs, int, 0644);
+MODULE_PARM_DESC(max_hmcs, "Max HMCs");
+module_param_named(max_mtu, ibmvmc_max_mtu, int, 0644);
+MODULE_PARM_DESC(max_mtu, "Max MTU");
+
+MODULE_AUTHOR("Steven Royer <seroyer@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("IBM VMC");
+MODULE_VERSION(IBMVMC_DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/ibmvmc.h b/drivers/misc/ibmvmc.h
new file mode 100644
index 000000000000..e140ada8fe2c
--- /dev/null
+++ b/drivers/misc/ibmvmc.h
@@ -0,0 +1,209 @@
+/* SPDX-License-Identifier: GPL-2.0+
+ *
+ * linux/drivers/misc/ibmvmc.h
+ *
+ * IBM Power Systems Virtual Management Channel Support.
+ *
+ * Copyright (c) 2004, 2018 IBM Corp.
+ *   Dave Engebretsen engebret@us.ibm.com
+ *   Steven Royer seroyer@linux.vnet.ibm.com
+ *   Adam Reznechek adreznec@linux.vnet.ibm.com
+ *   Bryant G. Ly <bryantly@linux.vnet.ibm.com>
+ */
+#ifndef IBMVMC_H
+#define IBMVMC_H
+
+#include <linux/types.h>
+#include <linux/cdev.h>
+
+#include <asm/vio.h>
+
+#define IBMVMC_PROTOCOL_VERSION    0x0101
+
+#define MIN_BUF_POOL_SIZE 16
+#define MIN_HMCS          1
+#define MIN_MTU           4096
+#define MAX_BUF_POOL_SIZE 64
+#define MAX_HMCS          2
+#define MAX_MTU           (4 * 4096)
+#define DEFAULT_BUF_POOL_SIZE 32
+#define DEFAULT_HMCS          1
+#define DEFAULT_MTU           4096
+#define HMC_ID_LEN        32
+
+#define VMC_INVALID_BUFFER_ID 0xFFFF
+
+/* ioctl numbers */
+#define VMC_BASE	     0xCC
+#define VMC_IOCTL_SETHMCID   _IOW(VMC_BASE, 0x00, unsigned char *)
+#define VMC_IOCTL_QUERY      _IOR(VMC_BASE, 0x01, struct ibmvmc_query_struct)
+#define VMC_IOCTL_REQUESTVMC _IOR(VMC_BASE, 0x02, u32)
+
+#define VMC_MSG_CAP          0x01
+#define VMC_MSG_CAP_RESP     0x81
+#define VMC_MSG_OPEN         0x02
+#define VMC_MSG_OPEN_RESP    0x82
+#define VMC_MSG_CLOSE        0x03
+#define VMC_MSG_CLOSE_RESP   0x83
+#define VMC_MSG_ADD_BUF      0x04
+#define VMC_MSG_ADD_BUF_RESP 0x84
+#define VMC_MSG_REM_BUF      0x05
+#define VMC_MSG_REM_BUF_RESP 0x85
+#define VMC_MSG_SIGNAL       0x06
+
+#define VMC_MSG_SUCCESS 0
+#define VMC_MSG_INVALID_HMC_INDEX 1
+#define VMC_MSG_INVALID_BUFFER_ID 2
+#define VMC_MSG_CLOSED_HMC        3
+#define VMC_MSG_INTERFACE_FAILURE 4
+#define VMC_MSG_NO_BUFFER         5
+
+#define VMC_BUF_OWNER_ALPHA 0
+#define VMC_BUF_OWNER_HV    1
+
+enum ibmvmc_states {
+	ibmvmc_state_sched_reset  = -1,
+	ibmvmc_state_initial      = 0,
+	ibmvmc_state_crqinit      = 1,
+	ibmvmc_state_capabilities = 2,
+	ibmvmc_state_ready        = 3,
+	ibmvmc_state_failed       = 4,
+};
+
+enum ibmhmc_states {
+	/* HMC connection not established */
+	ibmhmc_state_free    = 0,
+
+	/* HMC connection established (open called) */
+	ibmhmc_state_initial = 1,
+
+	/* open msg sent to HV, due to ioctl(1) call */
+	ibmhmc_state_opening = 2,
+
+	/* HMC connection ready, open resp msg from HV */
+	ibmhmc_state_ready   = 3,
+
+	/* HMC connection failure */
+	ibmhmc_state_failed  = 4,
+};
+
+struct ibmvmc_buffer {
+	u8 valid;	/* 1 when DMA storage allocated to buffer          */
+	u8 free;	/* 1 when buffer available for the Alpha Partition */
+	u8 owner;
+	u16 id;
+	u32 size;
+	u32 msg_len;
+	dma_addr_t dma_addr_local;
+	dma_addr_t dma_addr_remote;
+	void *real_addr_local;
+};
+
+struct ibmvmc_admin_crq_msg {
+	u8 valid;	/* RPA Defined           */
+	u8 type;	/* ibmvmc msg type       */
+	u8 status;	/* Response msg status. Zero is success and on failure,
+			 * either 1 - General Failure, or 2 - Invalid Version is
+			 * returned.
+			 */
+	u8 rsvd[2];
+	u8 max_hmc;	/* Max # of independent HMC connections supported */
+	__be16 pool_size;	/* Maximum number of buffers supported per HMC
+				 * connection
+				 */
+	__be32 max_mtu;		/* Maximum message size supported (bytes) */
+	__be16 crq_size;	/* # of entries available in the CRQ for the
+				 * source partition. The target partition must
+				 * limit the number of outstanding messages to
+				 * one half or less.
+				 */
+	__be16 version;	/* Indicates the code level of the management partition
+			 * or the hypervisor with the high-order byte
+			 * indicating a major version and the low-order byte
+			 * indicating a minor version.
+			 */
+};
+
+struct ibmvmc_crq_msg {
+	u8 valid;     /* RPA Defined           */
+	u8 type;      /* ibmvmc msg type       */
+	u8 status;    /* Response msg status   */
+	union {
+		u8 rsvd;  /* Reserved              */
+		u8 owner;
+	} var1;
+	u8 hmc_session;	/* Session Identifier for the current VMC connection */
+	u8 hmc_index;	/* A unique HMC Idx would be used if multiple management
+			 * applications running concurrently were desired
+			 */
+	union {
+		__be16 rsvd;
+		__be16 buffer_id;
+	} var2;
+	__be32 rsvd;
+	union {
+		__be32 rsvd;
+		__be32 lioba;
+		__be32 msg_len;
+	} var3;
+};
+
+/* an RPA command/response transport queue */
+struct crq_queue {
+	struct ibmvmc_crq_msg *msgs;
+	int size, cur;
+	dma_addr_t msg_token;
+	spinlock_t lock;
+};
+
+/* VMC server adapter settings */
+struct crq_server_adapter {
+	struct device *dev;
+	struct crq_queue queue;
+	u32 liobn;
+	u32 riobn;
+	struct tasklet_struct work_task;
+	wait_queue_head_t reset_wait_queue;
+	struct task_struct *reset_task;
+};
+
+/* Driver wide settings */
+struct ibmvmc_struct {
+	u32 state;
+	u32 max_mtu;
+	u32 max_buffer_pool_size;
+	u32 max_hmc_index;
+	struct crq_server_adapter *adapter;
+	struct cdev cdev;
+	u32 vmc_drc_index;
+};
+
+struct ibmvmc_file_session;
+
+/* Connection specific settings */
+struct ibmvmc_hmc {
+	u8 session;
+	u8 index;
+	u32 state;
+	struct crq_server_adapter *adapter;
+	spinlock_t lock;
+	unsigned char hmc_id[HMC_ID_LEN];
+	struct ibmvmc_buffer buffer[MAX_BUF_POOL_SIZE];
+	unsigned short queue_outbound_msgs[MAX_BUF_POOL_SIZE];
+	int queue_head, queue_tail;
+	struct ibmvmc_file_session *file_session;
+};
+
+struct ibmvmc_file_session {
+	struct file *file;
+	struct ibmvmc_hmc *hmc;
+	bool valid;
+};
+
+struct ibmvmc_query_struct {
+	int have_vmc;
+	int state;
+	int vmc_drc_index;
+};
+
+#endif /* __IBMVMC_H */
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index 3641f1334cf0..ab174f28e3be 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -926,7 +926,7 @@ again:
  *
  * 	Note: gru segments alway mmaped on GRU_GSEG_PAGESIZE boundaries.
  */
-int gru_fault(struct vm_fault *vmf)
+vm_fault_t gru_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct gru_thread_state *gts;
diff --git a/drivers/misc/sgi-gru/gruprocfs.c b/drivers/misc/sgi-gru/gruprocfs.c
index 4f7635922394..42ea2eccaee9 100644
--- a/drivers/misc/sgi-gru/gruprocfs.c
+++ b/drivers/misc/sgi-gru/gruprocfs.c
@@ -270,16 +270,6 @@ static int options_open(struct inode *inode, struct file *file)
 	return single_open(file, options_show, NULL);
 }
 
-static int cch_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &cch_seq_ops);
-}
-
-static int gru_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &gru_seq_ops);
-}
-
 /* *INDENT-OFF* */
 static const struct file_operations statistics_fops = {
 	.open 		= statistics_open,
@@ -305,73 +295,30 @@ static const struct file_operations options_fops = {
 	.release 	= single_release,
 };
 
-static const struct file_operations cch_fops = {
-	.open 		= cch_open,
-	.read 		= seq_read,
-	.llseek 	= seq_lseek,
-	.release 	= seq_release,
-};
-static const struct file_operations gru_fops = {
-	.open 		= gru_open,
-	.read 		= seq_read,
-	.llseek 	= seq_lseek,
-	.release 	= seq_release,
-};
-
-static struct proc_entry {
-	char *name;
-	umode_t mode;
-	const struct file_operations *fops;
-	struct proc_dir_entry *entry;
-} proc_files[] = {
-	{"statistics", 0644, &statistics_fops},
-	{"mcs_statistics", 0644, &mcs_statistics_fops},
-	{"debug_options", 0644, &options_fops},
-	{"cch_status", 0444, &cch_fops},
-	{"gru_status", 0444, &gru_fops},
-	{NULL}
-};
-/* *INDENT-ON* */
-
 static struct proc_dir_entry *proc_gru __read_mostly;
 
-static int create_proc_file(struct proc_entry *p)
-{
-	p->entry = proc_create(p->name, p->mode, proc_gru, p->fops);
-	if (!p->entry)
-		return -1;
-	return 0;
-}
-
-static void delete_proc_files(void)
-{
-	struct proc_entry *p;
-
-	if (proc_gru) {
-		for (p = proc_files; p->name; p++)
-			if (p->entry)
-				remove_proc_entry(p->name, proc_gru);
-		proc_remove(proc_gru);
-	}
-}
-
 int gru_proc_init(void)
 {
-	struct proc_entry *p;
-
 	proc_gru = proc_mkdir("sgi_uv/gru", NULL);
-
-	for (p = proc_files; p->name; p++)
-		if (create_proc_file(p))
-			goto err;
+	if (!proc_gru)
+		return -1;
+	if (!proc_create("statistics", 0644, proc_gru, &statistics_fops))
+		goto err;
+	if (!proc_create("mcs_statistics", 0644, proc_gru, &mcs_statistics_fops))
+		goto err;
+	if (!proc_create("debug_options", 0644, proc_gru, &options_fops))
+		goto err;
+	if (!proc_create_seq("cch_status", 0444, proc_gru, &cch_seq_ops))
+		goto err;
+	if (!proc_create_seq("gru_status", 0444, proc_gru, &gru_seq_ops))
+		goto err;
 	return 0;
-
 err:
-	delete_proc_files();
+	remove_proc_subtree("sgi_uv/gru", NULL);
 	return -1;
 }
 
 void gru_proc_exit(void)
 {
-	delete_proc_files();
+	remove_proc_subtree("sgi_uv/gru", NULL);
 }
diff --git a/drivers/misc/sgi-gru/grutables.h b/drivers/misc/sgi-gru/grutables.h
index b5e308b50ed1..3e041b6f7a68 100644
--- a/drivers/misc/sgi-gru/grutables.h
+++ b/drivers/misc/sgi-gru/grutables.h
@@ -147,6 +147,7 @@
 #include <linux/mutex.h>
 #include <linux/wait.h>
 #include <linux/mmu_notifier.h>
+#include <linux/mm_types.h>
 #include "gru.h"
 #include "grulib.h"
 #include "gruhandles.h"
@@ -665,7 +666,7 @@ extern unsigned long gru_reserve_cb_resources(struct gru_state *gru,
 		int cbr_au_count, char *cbmap);
 extern unsigned long gru_reserve_ds_resources(struct gru_state *gru,
 		int dsr_au_count, char *dsmap);
-extern int gru_fault(struct vm_fault *vmf);
+extern vm_fault_t gru_fault(struct vm_fault *vmf);
 extern struct gru_mm_struct *gru_register_mmu_notifier(void);
 extern void gru_drop_mmu_notifier(struct gru_mm_struct *gms);
 
diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c
index 0c26eaf5f62b..216d5c756236 100644
--- a/drivers/misc/sgi-xp/xpnet.c
+++ b/drivers/misc/sgi-xp/xpnet.c
@@ -407,7 +407,7 @@ xpnet_send(struct sk_buff *skb, struct xpnet_pending_msg *queued_msg,
  * destination partid.  If the destination partid octets are 0xffff,
  * this packet is to be broadcast to all connected partitions.
  */
-static int
+static netdev_tx_t
 xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct xpnet_pending_msg *queued_msg;
diff --git a/drivers/misc/ti-st/st_kim.c b/drivers/misc/ti-st/st_kim.c
index b77aacafc3fc..5ec3f5a43718 100644
--- a/drivers/misc/ti-st/st_kim.c
+++ b/drivers/misc/ti-st/st_kim.c
@@ -735,7 +735,7 @@ static int kim_probe(struct platform_device *pdev)
 		st_kim_devices[0] = pdev;
 	}
 
-	kim_gdata = kzalloc(sizeof(struct kim_data_s), GFP_ATOMIC);
+	kim_gdata = kzalloc(sizeof(struct kim_data_s), GFP_KERNEL);
 	if (!kim_gdata) {
 		pr_err("no mem to allocate");
 		return -ENOMEM;
diff --git a/drivers/misc/tifm_7xx1.c b/drivers/misc/tifm_7xx1.c
index e5f108713dd8..9ac95b48ef92 100644
--- a/drivers/misc/tifm_7xx1.c
+++ b/drivers/misc/tifm_7xx1.c
@@ -239,9 +239,13 @@ static int tifm_7xx1_resume(struct pci_dev *dev)
 	unsigned long timeout;
 	unsigned int good_sockets = 0, bad_sockets = 0;
 	unsigned long flags;
-	unsigned char new_ids[fm->num_sockets];
+	/* Maximum number of entries is 4 */
+	unsigned char new_ids[4];
 	DECLARE_COMPLETION_ONSTACK(finish_resume);
 
+	if (WARN_ON(fm->num_sockets > ARRAY_SIZE(new_ids)))
+		return -ENXIO;
+
 	pci_set_power_state(dev, PCI_D0);
 	pci_restore_state(dev);
 	rc = pci_enable_device(dev);
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index 9047c0a529b2..efd733472a35 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -576,15 +576,9 @@ static void vmballoon_pop(struct vmballoon *b)
 		}
 	}
 
-	if (b->batch_page) {
-		vunmap(b->batch_page);
-		b->batch_page = NULL;
-	}
-
-	if (b->page) {
-		__free_page(b->page);
-		b->page = NULL;
-	}
+	/* Clearing the batch_page unconditionally has no adverse effect */
+	free_page((unsigned long)b->batch_page);
+	b->batch_page = NULL;
 }
 
 /*
@@ -991,16 +985,13 @@ static const struct vmballoon_ops vmballoon_batched_ops = {
 
 static bool vmballoon_init_batching(struct vmballoon *b)
 {
-	b->page = alloc_page(VMW_PAGE_ALLOC_NOSLEEP);
-	if (!b->page)
-		return false;
+	struct page *page;
 
-	b->batch_page = vmap(&b->page, 1, VM_MAP, PAGE_KERNEL);
-	if (!b->batch_page) {
-		__free_page(b->page);
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page)
 		return false;
-	}
 
+	b->batch_page = page_address(page);
 	return true;
 }
 
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 9e923cd1d80e..a0b9102c4c6e 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -244,7 +244,7 @@ static ssize_t power_ro_lock_store(struct device *dev,
 	mq = &md->queue;
 
 	/* Dispatch locking to the block layer */
-	req = blk_get_request(mq->queue, REQ_OP_DRV_OUT, __GFP_RECLAIM);
+	req = blk_get_request(mq->queue, REQ_OP_DRV_OUT, 0);
 	if (IS_ERR(req)) {
 		count = PTR_ERR(req);
 		goto out_put;
@@ -650,8 +650,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md,
 	 */
 	mq = &md->queue;
 	req = blk_get_request(mq->queue,
-		idata->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,
-		__GFP_RECLAIM);
+		idata->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto cmd_done;
@@ -721,8 +720,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md,
 	 */
 	mq = &md->queue;
 	req = blk_get_request(mq->queue,
-		idata[0]->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,
-		__GFP_RECLAIM);
+		idata[0]->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto cmd_err;
@@ -2353,7 +2351,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	set_disk_ro(md->disk, md->read_only || default_ro);
 	md->disk->flags = GENHD_FL_EXT_DEVT;
 	if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT))
-		md->disk->flags |= GENHD_FL_NO_PART_SCAN;
+		md->disk->flags |= GENHD_FL_NO_PART_SCAN
+				   | GENHD_FL_SUPPRESS_PARTITION_INFO;
 
 	/*
 	 * As discussed on lkml, GENHD_FL_REMOVABLE should:
@@ -2485,7 +2484,7 @@ static long mmc_rpmb_ioctl(struct file *filp, unsigned int cmd,
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT
@@ -2750,7 +2749,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
 	int ret;
 
 	/* Ask the block layer about the card status */
-	req = blk_get_request(mq->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	req = blk_get_request(mq->queue, REQ_OP_DRV_IN, 0);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 	req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS;
@@ -2786,7 +2785,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
 		return -ENOMEM;
 
 	/* Ask the block layer for the EXT CSD */
-	req = blk_get_request(mq->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	req = blk_get_request(mq->queue, REQ_OP_DRV_IN, 0);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out_free;
@@ -2967,9 +2966,11 @@ static void mmc_blk_remove(struct mmc_card *card)
 	mmc_blk_remove_debugfs(card, md);
 	mmc_blk_remove_parts(card, md);
 	pm_runtime_get_sync(&card->dev);
-	mmc_claim_host(card->host);
-	mmc_blk_part_switch(card, md->part_type);
-	mmc_release_host(card->host);
+	if (md->part_curr != md->part_type) {
+		mmc_claim_host(card->host);
+		mmc_blk_part_switch(card, md->part_type);
+		mmc_release_host(card->host);
+	}
 	if (card->type != MMC_TYPE_SD_COMBO)
 		pm_runtime_disable(&card->dev);
 	pm_runtime_put_noidle(&card->dev);
diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h
index 9c821eedd156..1170feb8f969 100644
--- a/drivers/mmc/core/card.h
+++ b/drivers/mmc/core/card.h
@@ -149,6 +149,12 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
 	card->quirks &= ~data;
 }
 
+static inline void __maybe_unused add_limit_rate_quirk(struct mmc_card *card,
+						       int data)
+{
+	card->quirk_max_rate = data;
+}
+
 /*
  * Quirk add/remove for MMC products.
  */
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 121ce50b6d5e..281826d1fcca 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -50,9 +50,6 @@
 #include "sd_ops.h"
 #include "sdio_ops.h"
 
-/* If the device is not responding */
-#define MMC_CORE_TIMEOUT_MS	(10 * 60 * 1000) /* 10 minute timeout */
-
 /* The max erase timeout, used when host->max_busy_timeout isn't specified */
 #define MMC_ERASE_TIMEOUT_MS	(60 * 1000) /* 60 s */
 
@@ -1484,6 +1481,17 @@ int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage)
 
 }
 
+void mmc_set_initial_signal_voltage(struct mmc_host *host)
+{
+	/* Try to set signal voltage to 3.3V but fall back to 1.8v or 1.2v */
+	if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330))
+		dev_dbg(mmc_dev(host), "Initial signal voltage of 3.3v\n");
+	else if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180))
+		dev_dbg(mmc_dev(host), "Initial signal voltage of 1.8v\n");
+	else if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120))
+		dev_dbg(mmc_dev(host), "Initial signal voltage of 1.2v\n");
+}
+
 int mmc_host_set_uhs_voltage(struct mmc_host *host)
 {
 	u32 clock;
@@ -1646,19 +1654,13 @@ void mmc_power_up(struct mmc_host *host, u32 ocr)
 	/* Set initial state and call mmc_set_ios */
 	mmc_set_initial_state(host);
 
-	/* Try to set signal voltage to 3.3V but fall back to 1.8v or 1.2v */
-	if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330))
-		dev_dbg(mmc_dev(host), "Initial signal voltage of 3.3v\n");
-	else if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180))
-		dev_dbg(mmc_dev(host), "Initial signal voltage of 1.8v\n");
-	else if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120))
-		dev_dbg(mmc_dev(host), "Initial signal voltage of 1.2v\n");
+	mmc_set_initial_signal_voltage(host);
 
 	/*
 	 * This delay should be sufficient to allow the power supply
 	 * to reach the minimum voltage.
 	 */
-	mmc_delay(10);
+	mmc_delay(host->ios.power_delay_ms);
 
 	mmc_pwrseq_post_power_on(host);
 
@@ -1671,7 +1673,7 @@ void mmc_power_up(struct mmc_host *host, u32 ocr)
 	 * This delay must be at least 74 clock sizes, or 1 ms, or the
 	 * time required to reach a stable voltage.
 	 */
-	mmc_delay(10);
+	mmc_delay(host->ios.power_delay_ms);
 }
 
 void mmc_power_off(struct mmc_host *host)
@@ -1967,6 +1969,7 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	unsigned int qty = 0, busy_timeout = 0;
 	bool use_r1b_resp = false;
 	unsigned long timeout;
+	int loop_udelay=64, udelay_max=32768;
 	int err;
 
 	mmc_retune_hold(card->host);
@@ -2091,9 +2094,15 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 			err =  -EIO;
 			goto out;
 		}
+		if ((cmd.resp[0] & R1_READY_FOR_DATA) &&
+		    R1_CURRENT_STATE(cmd.resp[0]) != R1_STATE_PRG)
+			break;
+
+		usleep_range(loop_udelay, loop_udelay*2);
+		if (loop_udelay < udelay_max)
+			loop_udelay *= 2;
+	} while (1);
 
-	} while (!(cmd.resp[0] & R1_READY_FOR_DATA) ||
-		 (R1_CURRENT_STATE(cmd.resp[0]) == R1_STATE_PRG));
 out:
 	mmc_retune_release(card->host);
 	return err;
@@ -2435,22 +2444,46 @@ int mmc_hw_reset(struct mmc_host *host)
 		return -EINVAL;
 
 	mmc_bus_get(host);
-	if (!host->bus_ops || host->bus_dead || !host->bus_ops->reset) {
+	if (!host->bus_ops || host->bus_dead || !host->bus_ops->hw_reset) {
 		mmc_bus_put(host);
 		return -EOPNOTSUPP;
 	}
 
-	ret = host->bus_ops->reset(host);
+	ret = host->bus_ops->hw_reset(host);
 	mmc_bus_put(host);
 
 	if (ret)
-		pr_warn("%s: tried to reset card, got error %d\n",
+		pr_warn("%s: tried to HW reset card, got error %d\n",
 			mmc_hostname(host), ret);
 
 	return ret;
 }
 EXPORT_SYMBOL(mmc_hw_reset);
 
+int mmc_sw_reset(struct mmc_host *host)
+{
+	int ret;
+
+	if (!host->card)
+		return -EINVAL;
+
+	mmc_bus_get(host);
+	if (!host->bus_ops || host->bus_dead || !host->bus_ops->sw_reset) {
+		mmc_bus_put(host);
+		return -EOPNOTSUPP;
+	}
+
+	ret = host->bus_ops->sw_reset(host);
+	mmc_bus_put(host);
+
+	if (ret)
+		pr_warn("%s: tried to SW reset card, got error %d\n",
+			mmc_hostname(host), ret);
+
+	return ret;
+}
+EXPORT_SYMBOL(mmc_sw_reset);
+
 static int mmc_rescan_try_freq(struct mmc_host *host, unsigned freq)
 {
 	host->f_init = freq;
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index d6303d69071b..9d8f09ac0821 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -32,7 +32,8 @@ struct mmc_bus_ops {
 	int (*power_restore)(struct mmc_host *);
 	int (*alive)(struct mmc_host *);
 	int (*shutdown)(struct mmc_host *);
-	int (*reset)(struct mmc_host *);
+	int (*hw_reset)(struct mmc_host *);
+	int (*sw_reset)(struct mmc_host *);
 };
 
 void mmc_attach_bus(struct mmc_host *host, const struct mmc_bus_ops *ops);
@@ -51,6 +52,7 @@ u32 mmc_select_voltage(struct mmc_host *host, u32 ocr);
 int mmc_set_uhs_voltage(struct mmc_host *host, u32 ocr);
 int mmc_host_set_uhs_voltage(struct mmc_host *host);
 int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage);
+void mmc_set_initial_signal_voltage(struct mmc_host *host);
 void mmc_set_timing(struct mmc_host *host, unsigned int timing);
 void mmc_set_driver_type(struct mmc_host *host, unsigned int drv_type);
 int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 64b03d6eaf18..abf9e884386c 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -143,9 +143,6 @@ int mmc_retune(struct mmc_host *host)
 			goto out;
 
 		return_to_hs400 = true;
-
-		if (host->ops->prepare_hs400_tuning)
-			host->ops->prepare_hs400_tuning(host, &host->ios);
 	}
 
 	err = mmc_execute_tuning(host->card);
@@ -179,7 +176,7 @@ static void mmc_retune_timer(struct timer_list *t)
 int mmc_of_parse(struct mmc_host *host)
 {
 	struct device *dev = host->parent;
-	u32 bus_width, drv_type;
+	u32 bus_width, drv_type, cd_debounce_delay_ms;
 	int ret;
 	bool cd_cap_invert, cd_gpio_invert = false;
 	bool ro_cap_invert, ro_gpio_invert = false;
@@ -230,11 +227,16 @@ int mmc_of_parse(struct mmc_host *host)
 	} else {
 		cd_cap_invert = device_property_read_bool(dev, "cd-inverted");
 
+		if (device_property_read_u32(dev, "cd-debounce-delay-ms",
+					     &cd_debounce_delay_ms))
+			cd_debounce_delay_ms = 200;
+
 		if (device_property_read_bool(dev, "broken-cd"))
 			host->caps |= MMC_CAP_NEEDS_POLL;
 
 		ret = mmc_gpiod_request_cd(host, "cd", 0, true,
-					   0, &cd_gpio_invert);
+					   cd_debounce_delay_ms,
+					   &cd_gpio_invert);
 		if (!ret)
 			dev_info(host->parent, "Got CD GPIO\n");
 		else if (ret != -ENOENT && ret != -ENOSYS)
@@ -338,6 +340,9 @@ int mmc_of_parse(struct mmc_host *host)
 		host->dsr_req = 0;
 	}
 
+	device_property_read_u32(dev, "post-power-on-delay-ms",
+				 &host->ios.power_delay_ms);
+
 	return mmc_pwrseq_alloc(host);
 }
 
@@ -403,6 +408,7 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 	host->max_blk_count = PAGE_SIZE / 512;
 
 	host->fixed_drv_type = -EINVAL;
+	host->ios.power_delay_ms = 10;
 
 	return host;
 }
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 6f8ebd6caa4c..4466f5de54d4 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1282,6 +1282,10 @@ int mmc_hs400_to_hs200(struct mmc_card *card)
 
 	mmc_set_bus_speed(card);
 
+	/* Prepare tuning for HS400 mode. */
+	if (host->ops->prepare_hs400_tuning)
+		host->ops->prepare_hs400_tuning(host, &host->ios);
+
 	return 0;
 
 out_err:
@@ -1830,6 +1834,14 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		}
 	}
 
+	if (host->caps2 & MMC_CAP2_AVOID_3_3V &&
+	    host->ios.signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+		pr_err("%s: Host failed to negotiate down from 3.3V\n",
+			mmc_hostname(host));
+		err = -EINVAL;
+		goto free_card;
+	}
+
 	if (!oldcard)
 		host->card = card;
 
@@ -2117,7 +2129,7 @@ static int mmc_can_reset(struct mmc_card *card)
 	return 1;
 }
 
-static int mmc_reset(struct mmc_host *host)
+static int _mmc_hw_reset(struct mmc_host *host)
 {
 	struct mmc_card *card = host->card;
 
@@ -2151,7 +2163,7 @@ static const struct mmc_bus_ops mmc_ops = {
 	.runtime_resume = mmc_runtime_resume,
 	.alive = mmc_alive,
 	.shutdown = mmc_shutdown,
-	.reset = mmc_reset,
+	.hw_reset = _mmc_hw_reset,
 };
 
 /*
diff --git a/drivers/mmc/core/pwrseq_simple.c b/drivers/mmc/core/pwrseq_simple.c
index 13ef162cf066..a8b9fee4d62a 100644
--- a/drivers/mmc/core/pwrseq_simple.c
+++ b/drivers/mmc/core/pwrseq_simple.c
@@ -40,14 +40,18 @@ static void mmc_pwrseq_simple_set_gpios_value(struct mmc_pwrseq_simple *pwrseq,
 	struct gpio_descs *reset_gpios = pwrseq->reset_gpios;
 
 	if (!IS_ERR(reset_gpios)) {
-		int i;
-		int values[reset_gpios->ndescs];
+		int i, *values;
+		int nvalues = reset_gpios->ndescs;
 
-		for (i = 0; i < reset_gpios->ndescs; i++)
+		values = kmalloc_array(nvalues, sizeof(int), GFP_KERNEL);
+		if (!values)
+			return;
+
+		for (i = 0; i < nvalues; i++)
 			values[i] = value;
 
-		gpiod_set_array_value_cansleep(
-			reset_gpios->ndescs, reset_gpios->desc, values);
+		gpiod_set_array_value_cansleep(nvalues, reset_gpios->desc, values);
+		kfree(values);
 	}
 }
 
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 56e9a803db21..648eb6743ed5 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -111,8 +111,9 @@ static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
 				__mmc_cqe_recovery_notifier(mq);
 			return BLK_EH_RESET_TIMER;
 		}
-		/* No timeout */
-		return BLK_EH_HANDLED;
+		/* No timeout (XXX: huh? comment doesn't make much sense) */
+		blk_mq_complete_request(req);
+		return BLK_EH_DONE;
 	default:
 		/* Timeout is handled by mmc core */
 		return BLK_EH_RESET_TIMER;
diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h
index 5153577754f0..dd2f73af8f2c 100644
--- a/drivers/mmc/core/quirks.h
+++ b/drivers/mmc/core/quirks.h
@@ -132,6 +132,9 @@ static const struct mmc_fixup sdio_fixup_methods[] = {
 	SDIO_FIXUP(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8797_F0,
 		   add_quirk, MMC_QUIRK_BROKEN_IRQ_POLLING),
 
+	SDIO_FIXUP(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8887WLAN,
+		   add_limit_rate_quirk, 150000000),
+
 	END_FIXUP
 };
 
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index baf3d5da4ccb..d0d9f90e7cdf 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -1058,6 +1058,14 @@ retry:
 			mmc_set_bus_width(host, MMC_BUS_WIDTH_4);
 		}
 	}
+
+	if (host->caps2 & MMC_CAP2_AVOID_3_3V &&
+	    host->ios.signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+		pr_err("%s: Host failed to negotiate down from 3.3V\n",
+			mmc_hostname(host));
+		err = -EINVAL;
+		goto free_card;
+	}
 done:
 	host->card = card;
 	return 0;
@@ -1214,7 +1222,7 @@ static int mmc_sd_runtime_resume(struct mmc_host *host)
 	return 0;
 }
 
-static int mmc_sd_reset(struct mmc_host *host)
+static int mmc_sd_hw_reset(struct mmc_host *host)
 {
 	mmc_power_cycle(host, host->card->ocr);
 	return mmc_sd_init_card(host, host->card->ocr, host->card);
@@ -1229,7 +1237,7 @@ static const struct mmc_bus_ops mmc_sd_ops = {
 	.resume = mmc_sd_resume,
 	.alive = mmc_sd_alive,
 	.shutdown = mmc_sd_suspend,
-	.reset = mmc_sd_reset,
+	.hw_reset = mmc_sd_hw_reset,
 };
 
 /*
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index c599a628a387..a86490dbca70 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -444,6 +444,7 @@ static int sdio_set_bus_speed_mode(struct mmc_card *card)
 	unsigned int bus_speed, timing;
 	int err;
 	unsigned char speed;
+	unsigned int max_rate;
 
 	/*
 	 * If the host doesn't support any of the UHS-I modes, fallback on
@@ -500,9 +501,12 @@ static int sdio_set_bus_speed_mode(struct mmc_card *card)
 	if (err)
 		return err;
 
+	max_rate = min_not_zero(card->quirk_max_rate,
+				card->sw_caps.uhs_max_dtr);
+
 	if (bus_speed) {
 		mmc_set_timing(card->host, timing);
-		mmc_set_clock(card->host, card->sw_caps.uhs_max_dtr);
+		mmc_set_clock(card->host, max_rate);
 	}
 
 	return 0;
@@ -788,6 +792,14 @@ try_again:
 		if (err)
 			goto remove;
 	}
+
+	if (host->caps2 & MMC_CAP2_AVOID_3_3V &&
+	    host->ios.signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+		pr_err("%s: Host failed to negotiate down from 3.3V\n",
+			mmc_hostname(host));
+		err = -EINVAL;
+		goto remove;
+	}
 finish:
 	if (!oldcard)
 		host->card = card;
@@ -801,6 +813,22 @@ err:
 	return err;
 }
 
+static int mmc_sdio_reinit_card(struct mmc_host *host, bool powered_resume)
+{
+	int ret;
+
+	sdio_reset(host);
+	mmc_go_idle(host);
+	mmc_send_if_cond(host, host->card->ocr);
+
+	ret = mmc_send_io_op_cond(host, 0, NULL);
+	if (ret)
+		return ret;
+
+	return mmc_sdio_init_card(host, host->card->ocr, host->card,
+				  powered_resume);
+}
+
 /*
  * Host is being removed. Free up the current card.
  */
@@ -948,14 +976,7 @@ static int mmc_sdio_resume(struct mmc_host *host)
 
 	/* No need to reinitialize powered-resumed nonremovable cards */
 	if (mmc_card_is_removable(host) || !mmc_card_keep_power(host)) {
-		sdio_reset(host);
-		mmc_go_idle(host);
-		mmc_send_if_cond(host, host->card->ocr);
-		err = mmc_send_io_op_cond(host, 0, NULL);
-		if (!err)
-			err = mmc_sdio_init_card(host, host->card->ocr,
-						 host->card,
-						 mmc_card_keep_power(host));
+		err = mmc_sdio_reinit_card(host, mmc_card_keep_power(host));
 	} else if (mmc_card_keep_power(host) && mmc_card_wake_sdio_irq(host)) {
 		/* We may have switched to 1-bit mode during suspend */
 		err = sdio_enable_4bit_bus(host->card);
@@ -978,8 +999,6 @@ static int mmc_sdio_power_restore(struct mmc_host *host)
 {
 	int ret;
 
-	mmc_claim_host(host);
-
 	/*
 	 * Reset the card by performing the same steps that are taken by
 	 * mmc_rescan_try_freq() and mmc_attach_sdio() during a "normal" probe.
@@ -997,20 +1016,12 @@ static int mmc_sdio_power_restore(struct mmc_host *host)
 	 *
 	 */
 
-	sdio_reset(host);
-	mmc_go_idle(host);
-	mmc_send_if_cond(host, host->card->ocr);
-
-	ret = mmc_send_io_op_cond(host, 0, NULL);
-	if (ret)
-		goto out;
+	mmc_claim_host(host);
 
-	ret = mmc_sdio_init_card(host, host->card->ocr, host->card,
-				mmc_card_keep_power(host));
+	ret = mmc_sdio_reinit_card(host, mmc_card_keep_power(host));
 	if (!ret && host->sdio_irqs)
 		mmc_signal_sdio_irq(host);
 
-out:
 	mmc_release_host(host);
 
 	return ret;
@@ -1039,12 +1050,24 @@ static int mmc_sdio_runtime_resume(struct mmc_host *host)
 	return ret;
 }
 
-static int mmc_sdio_reset(struct mmc_host *host)
+static int mmc_sdio_hw_reset(struct mmc_host *host)
 {
 	mmc_power_cycle(host, host->card->ocr);
 	return mmc_sdio_power_restore(host);
 }
 
+static int mmc_sdio_sw_reset(struct mmc_host *host)
+{
+	mmc_set_clock(host, host->f_init);
+	sdio_reset(host);
+	mmc_go_idle(host);
+
+	mmc_set_initial_state(host);
+	mmc_set_initial_signal_voltage(host);
+
+	return mmc_sdio_reinit_card(host, 0);
+}
+
 static const struct mmc_bus_ops mmc_sdio_ops = {
 	.remove = mmc_sdio_remove,
 	.detect = mmc_sdio_detect,
@@ -1055,7 +1078,8 @@ static const struct mmc_bus_ops mmc_sdio_ops = {
 	.runtime_resume = mmc_sdio_runtime_resume,
 	.power_restore = mmc_sdio_power_restore,
 	.alive = mmc_sdio_alive,
-	.reset = mmc_sdio_reset,
+	.hw_reset = mmc_sdio_hw_reset,
+	.sw_reset = mmc_sdio_sw_reset,
 };
 
 
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 2b32b88949ba..b6d8203e46eb 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -139,7 +139,7 @@ static int sdio_bus_probe(struct device *dev)
 		return -ENODEV;
 
 	ret = dev_pm_domain_attach(dev, false);
-	if (ret == -EPROBE_DEFER)
+	if (ret)
 		return ret;
 
 	/* Unbound SDIO functions are always suspended.
diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c
index d3c91f412b69..25e113001a3c 100644
--- a/drivers/mmc/core/sdio_uart.c
+++ b/drivers/mmc/core/sdio_uart.c
@@ -1008,19 +1008,6 @@ static int sdio_uart_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int sdio_uart_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sdio_uart_proc_show, NULL);
-}
-
-static const struct file_operations sdio_uart_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= sdio_uart_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static const struct tty_port_operations sdio_uart_port_ops = {
 	.dtr_rts = uart_dtr_rts,
 	.carrier_raised = uart_carrier_raised,
@@ -1045,7 +1032,7 @@ static const struct tty_operations sdio_uart_ops = {
 	.tiocmset		= sdio_uart_tiocmset,
 	.install		= sdio_uart_install,
 	.cleanup		= sdio_uart_cleanup,
-	.proc_fops		= &sdio_uart_proc_fops,
+	.proc_show		= sdio_uart_proc_show,
 };
 
 static struct tty_driver *sdio_uart_tty_driver;
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 31f7dbb15668..ef05e0039378 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -28,15 +28,17 @@ struct mmc_gpio {
 	irqreturn_t (*cd_gpio_isr)(int irq, void *dev_id);
 	char *ro_label;
 	char cd_label[0];
+	u32 cd_debounce_delay_ms;
 };
 
 static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id)
 {
 	/* Schedule a card detection after a debounce timeout */
 	struct mmc_host *host = dev_id;
+	struct mmc_gpio *ctx = host->slot.handler_priv;
 
 	host->trigger_card_event = true;
-	mmc_detect_change(host, msecs_to_jiffies(200));
+	mmc_detect_change(host, msecs_to_jiffies(ctx->cd_debounce_delay_ms));
 
 	return IRQ_HANDLED;
 }
@@ -49,6 +51,7 @@ int mmc_gpio_alloc(struct mmc_host *host)
 
 	if (ctx) {
 		ctx->ro_label = ctx->cd_label + len;
+		ctx->cd_debounce_delay_ms = 200;
 		snprintf(ctx->cd_label, len, "%s cd", dev_name(host->parent));
 		snprintf(ctx->ro_label, len, "%s ro", dev_name(host->parent));
 		host->slot.handler_priv = ctx;
@@ -76,15 +79,22 @@ EXPORT_SYMBOL(mmc_gpio_get_ro);
 int mmc_gpio_get_cd(struct mmc_host *host)
 {
 	struct mmc_gpio *ctx = host->slot.handler_priv;
+	int cansleep;
 
 	if (!ctx || !ctx->cd_gpio)
 		return -ENOSYS;
 
-	if (ctx->override_cd_active_level)
-		return !gpiod_get_raw_value_cansleep(ctx->cd_gpio) ^
-			!!(host->caps2 & MMC_CAP2_CD_ACTIVE_HIGH);
+	cansleep = gpiod_cansleep(ctx->cd_gpio);
+	if (ctx->override_cd_active_level) {
+		int value = cansleep ?
+				gpiod_get_raw_value_cansleep(ctx->cd_gpio) :
+				gpiod_get_raw_value(ctx->cd_gpio);
+		return !value ^ !!(host->caps2 & MMC_CAP2_CD_ACTIVE_HIGH);
+	}
 
-	return gpiod_get_value_cansleep(ctx->cd_gpio);
+	return cansleep ?
+		gpiod_get_value_cansleep(ctx->cd_gpio) :
+		gpiod_get_value(ctx->cd_gpio);
 }
 EXPORT_SYMBOL(mmc_gpio_get_cd);
 
@@ -261,7 +271,7 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 	if (debounce) {
 		ret = gpiod_set_debounce(desc, debounce);
 		if (ret < 0)
-			return ret;
+			ctx->cd_debounce_delay_ms = debounce;
 	}
 
 	if (gpio_invert)
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 9589f9c9046f..0581c199c996 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -345,11 +345,11 @@ config MMC_SDHCI_IPROC
 	  If unsure, say N.
 
 config MMC_MESON_GX
-	tristate "Amlogic S905/GX* SD/MMC Host Controller support"
+	tristate "Amlogic S905/GX*/AXG SD/MMC Host Controller support"
 	depends on ARCH_MESON && MMC
 	help
 	  This selects support for the Amlogic SD/MMC Host Controller
-	  found on the S905/GX* family of SoCs.  This controller is
+	  found on the S905/GX*/AXG family of SoCs.  This controller is
 	  MMC 5.1 compliant and supports SD, eMMC and SDIO interfaces.
 
 	  If you have a controller with this interface, say Y here.
@@ -358,7 +358,6 @@ config MMC_MESON_MX_SDIO
 	tristate "Amlogic Meson6/Meson8/Meson8b SD/MMC Host Controller support"
 	depends on ARCH_MESON || COMPILE_TEST
 	depends on COMMON_CLK
-	depends on HAS_DMA
 	depends on OF
 	help
 	  This selects support for the SD/MMC Host Controller on
@@ -401,7 +400,6 @@ config MMC_OMAP
 
 config MMC_OMAP_HS
 	tristate "TI OMAP High Speed Multimedia Card Interface support"
-	depends on HAS_DMA
 	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
 	help
 	  This selects the TI OMAP High Speed Multimedia card Interface.
@@ -511,7 +509,6 @@ config MMC_DAVINCI
 
 config MMC_GOLDFISH
 	tristate "goldfish qemu Multimedia Card Interface support"
-	depends on HAS_DMA
 	depends on GOLDFISH || COMPILE_TEST
 	help
 	  This selects the Goldfish Multimedia card Interface emulation
@@ -605,7 +602,7 @@ config MMC_SDHI
 
 config MMC_SDHI_SYS_DMAC
 	tristate "DMA for SDHI SD/SDIO controllers using SYS-DMAC"
-	depends on MMC_SDHI && HAS_DMA
+	depends on MMC_SDHI
 	default MMC_SDHI if (SUPERH || ARM)
 	help
 	  This provides DMA support for SDHI SD/SDIO controllers
@@ -615,7 +612,7 @@ config MMC_SDHI_SYS_DMAC
 config MMC_SDHI_INTERNAL_DMAC
 	tristate "DMA for SDHI SD/SDIO controllers using on-chip bus mastering"
 	depends on ARM64 || COMPILE_TEST
-	depends on MMC_SDHI && HAS_DMA
+	depends on MMC_SDHI
 	default MMC_SDHI if ARM64
 	help
 	  This provides DMA support for SDHI SD/SDIO controllers
@@ -669,7 +666,6 @@ config MMC_CAVIUM_THUNDERX
 
 config MMC_DW
 	tristate "Synopsys DesignWare Memory Card Interface"
-	depends on HAS_DMA
 	depends on ARC || ARM || ARM64 || MIPS || COMPILE_TEST
 	help
 	  This selects support for the Synopsys DesignWare Mobile Storage IP
@@ -690,6 +686,15 @@ config MMC_DW_PLTFM
 
 	  If unsure, say Y.
 
+config MMC_DW_BLUEFIELD
+	tristate "BlueField specific extensions for Synopsys DW Memory Card Interface"
+	depends on MMC_DW
+	select MMC_DW_PLTFM
+	help
+	  This selects support for Mellanox BlueField SoC specific extensions to
+	  the Synopsys DesignWare Memory Card Interface driver. Select this
+	  option for platforms based on Mellanox BlueField SoC's.
+
 config MMC_DW_EXYNOS
 	tristate "Exynos specific extensions for Synopsys DW Memory Card Interface"
 	depends on MMC_DW
@@ -748,7 +753,6 @@ config MMC_DW_ZX
 
 config MMC_SH_MMCIF
 	tristate "SuperH Internal MMCIF support"
-	depends on HAS_DMA
 	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 	help
 	  This selects the MMC Host Interface controller (MMCIF) found in various
@@ -756,11 +760,12 @@ config MMC_SH_MMCIF
 
 
 config MMC_JZ4740
-	tristate "JZ4740 SD/Multimedia Card Interface support"
-	depends on MACH_JZ4740
+	tristate "Ingenic JZ47xx SD/Multimedia Card Interface support"
+	depends on MACH_JZ4740 || MACH_JZ4780
 	help
-	  This selects support for the SD/MMC controller on Ingenic JZ4740
-	  SoCs.
+	  This selects support for the SD/MMC controller on Ingenic
+	  JZ4740, JZ4750, JZ4770 and JZ4780 SoCs.
+
 	  If you have a board based on such a SoC and with a SD/MMC slot,
 	  say Y or M here.
 
@@ -868,7 +873,6 @@ config MMC_TOSHIBA_PCI
 config MMC_BCM2835
 	tristate "Broadcom BCM2835 SDHOST MMC Controller support"
 	depends on ARCH_BCM2835 || COMPILE_TEST
-	depends on HAS_DMA
 	help
 	  This selects the BCM2835 SDHOST MMC controller. If you have
 	  a BCM2835 platform with SD or MMC devices, say Y or M here.
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index 6aead24879b4..85dc1322c3de 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -49,6 +49,7 @@ thunderx-mmc-objs := cavium.o cavium-thunderx.o
 obj-$(CONFIG_MMC_CAVIUM_THUNDERX) += thunderx-mmc.o
 obj-$(CONFIG_MMC_DW)		+= dw_mmc.o
 obj-$(CONFIG_MMC_DW_PLTFM)	+= dw_mmc-pltfm.o
+obj-$(CONFIG_MMC_DW_BLUEFIELD)	+= dw_mmc-bluefield.o
 obj-$(CONFIG_MMC_DW_EXYNOS)	+= dw_mmc-exynos.o
 obj-$(CONFIG_MMC_DW_HI3798CV200) += dw_mmc-hi3798cv200.o
 obj-$(CONFIG_MMC_DW_K3)		+= dw_mmc-k3.o
diff --git a/drivers/mmc/host/android-goldfish.c b/drivers/mmc/host/android-goldfish.c
index 63d27589cd89..294de177632c 100644
--- a/drivers/mmc/host/android-goldfish.c
+++ b/drivers/mmc/host/android-goldfish.c
@@ -217,8 +217,8 @@ static void goldfish_mmc_xfer_done(struct goldfish_mmc_host *host,
 			 * We don't really have DMA, so we need
 			 * to copy from our platform driver buffer
 			 */
-			uint8_t *dest = (uint8_t *)sg_virt(data->sg);
-			memcpy(dest, host->virt_base, data->sg->length);
+			sg_copy_to_buffer(data->sg, 1, host->virt_base,
+					data->sg->length);
 		}
 		host->data->bytes_xfered += data->sg->length;
 		dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->sg_len,
@@ -393,8 +393,8 @@ static void goldfish_mmc_prepare_data(struct goldfish_mmc_host *host,
 		 * We don't really have DMA, so we need to copy to our
 		 * platform driver buffer
 		 */
-		const uint8_t *src = (uint8_t *)sg_virt(data->sg);
-		memcpy(host->virt_base, src, data->sg->length);
+		sg_copy_from_buffer(data->sg, 1, host->virt_base,
+				data->sg->length);
 	}
 }
 
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index e55f3932d580..5aa2c9404e92 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -1967,7 +1967,6 @@ static void atmci_tasklet_func(unsigned long priv)
 static void atmci_read_data_pio(struct atmel_mci *host)
 {
 	struct scatterlist	*sg = host->sg;
-	void			*buf = sg_virt(sg);
 	unsigned int		offset = host->pio_offset;
 	struct mmc_data		*data = host->data;
 	u32			value;
@@ -1977,7 +1976,7 @@ static void atmci_read_data_pio(struct atmel_mci *host)
 	do {
 		value = atmci_readl(host, ATMCI_RDR);
 		if (likely(offset + 4 <= sg->length)) {
-			put_unaligned(value, (u32 *)(buf + offset));
+			sg_pcopy_to_buffer(sg, 1, &value, sizeof(u32), offset);
 
 			offset += 4;
 			nbytes += 4;
@@ -1990,11 +1989,11 @@ static void atmci_read_data_pio(struct atmel_mci *host)
 					goto done;
 
 				offset = 0;
-				buf = sg_virt(sg);
 			}
 		} else {
 			unsigned int remaining = sg->length - offset;
-			memcpy(buf + offset, &value, remaining);
+
+			sg_pcopy_to_buffer(sg, 1, &value, remaining, offset);
 			nbytes += remaining;
 
 			flush_dcache_page(sg_page(sg));
@@ -2004,8 +2003,8 @@ static void atmci_read_data_pio(struct atmel_mci *host)
 				goto done;
 
 			offset = 4 - remaining;
-			buf = sg_virt(sg);
-			memcpy(buf, (u8 *)&value + remaining, offset);
+			sg_pcopy_to_buffer(sg, 1, (u8 *)&value + remaining,
+					offset, 0);
 			nbytes += offset;
 		}
 
@@ -2035,7 +2034,6 @@ done:
 static void atmci_write_data_pio(struct atmel_mci *host)
 {
 	struct scatterlist	*sg = host->sg;
-	void			*buf = sg_virt(sg);
 	unsigned int		offset = host->pio_offset;
 	struct mmc_data		*data = host->data;
 	u32			value;
@@ -2044,7 +2042,7 @@ static void atmci_write_data_pio(struct atmel_mci *host)
 
 	do {
 		if (likely(offset + 4 <= sg->length)) {
-			value = get_unaligned((u32 *)(buf + offset));
+			sg_pcopy_from_buffer(sg, 1, &value, sizeof(u32), offset);
 			atmci_writel(host, ATMCI_TDR, value);
 
 			offset += 4;
@@ -2056,13 +2054,12 @@ static void atmci_write_data_pio(struct atmel_mci *host)
 					goto done;
 
 				offset = 0;
-				buf = sg_virt(sg);
 			}
 		} else {
 			unsigned int remaining = sg->length - offset;
 
 			value = 0;
-			memcpy(&value, buf + offset, remaining);
+			sg_pcopy_from_buffer(sg, 1, &value, remaining, offset);
 			nbytes += remaining;
 
 			host->sg = sg = sg_next(sg);
@@ -2073,8 +2070,8 @@ static void atmci_write_data_pio(struct atmel_mci *host)
 			}
 
 			offset = 4 - remaining;
-			buf = sg_virt(sg);
-			memcpy((u8 *)&value + remaining, buf, offset);
+			sg_pcopy_from_buffer(sg, 1, (u8 *)&value + remaining,
+					offset, 0);
 			atmci_writel(host, ATMCI_TDR, value);
 			nbytes += offset;
 		}
diff --git a/drivers/mmc/host/au1xmmc.c b/drivers/mmc/host/au1xmmc.c
index ed77fbfa4774..9b4be67330dd 100644
--- a/drivers/mmc/host/au1xmmc.c
+++ b/drivers/mmc/host/au1xmmc.c
@@ -40,6 +40,7 @@
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
+#include <linux/highmem.h>
 #include <linux/leds.h>
 #include <linux/mmc/host.h>
 #include <linux/slab.h>
@@ -405,7 +406,7 @@ static void au1xmmc_send_pio(struct au1xmmc_host *host)
 
 	/* This is the pointer to the data buffer */
 	sg = &data->sg[host->pio.index];
-	sg_ptr = sg_virt(sg) + host->pio.offset;
+	sg_ptr = kmap_atomic(sg_page(sg)) + sg->offset + host->pio.offset;
 
 	/* This is the space left inside the buffer */
 	sg_len = data->sg[host->pio.index].length - host->pio.offset;
@@ -421,11 +422,12 @@ static void au1xmmc_send_pio(struct au1xmmc_host *host)
 		if (!(status & SD_STATUS_TH))
 			break;
 
-		val = *sg_ptr++;
+		val = sg_ptr[count];
 
 		__raw_writel((unsigned long)val, HOST_TXPORT(host));
 		wmb(); /* drain writebuffer */
 	}
+	kunmap_atomic(sg_ptr);
 
 	host->pio.len -= count;
 	host->pio.offset += count;
@@ -462,7 +464,7 @@ static void au1xmmc_receive_pio(struct au1xmmc_host *host)
 
 	if (host->pio.index < host->dma.len) {
 		sg = &data->sg[host->pio.index];
-		sg_ptr = sg_virt(sg) + host->pio.offset;
+		sg_ptr = kmap_atomic(sg_page(sg)) + sg->offset + host->pio.offset;
 
 		/* This is the space left inside the buffer */
 		sg_len = sg_dma_len(&data->sg[host->pio.index]) - host->pio.offset;
@@ -501,8 +503,10 @@ static void au1xmmc_receive_pio(struct au1xmmc_host *host)
 		val = __raw_readl(HOST_RXPORT(host));
 
 		if (sg_ptr)
-			*sg_ptr++ = (unsigned char)(val & 0xFF);
+			sg_ptr[count] = (unsigned char)(val & 0xFF);
 	}
+	if (sg_ptr)
+		kunmap_atomic(sg_ptr);
 
 	host->pio.len -= count;
 	host->pio.offset += count;
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 8e363174f9d6..9e68c3645e22 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -1377,8 +1377,7 @@ static int __exit davinci_mmcsd_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM
 static int davinci_mmcsd_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct mmc_davinci_host *host = platform_get_drvdata(pdev);
+	struct mmc_davinci_host *host = dev_get_drvdata(dev);
 
 	writel(0, host->base + DAVINCI_MMCIM);
 	mmc_davinci_reset_ctrl(host, 1);
@@ -1389,8 +1388,7 @@ static int davinci_mmcsd_suspend(struct device *dev)
 
 static int davinci_mmcsd_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct mmc_davinci_host *host = platform_get_drvdata(pdev);
+	struct mmc_davinci_host *host = dev_get_drvdata(dev);
 
 	clk_enable(host->clk);
 	mmc_davinci_reset_ctrl(host, 0);
diff --git a/drivers/mmc/host/dw_mmc-bluefield.c b/drivers/mmc/host/dw_mmc-bluefield.c
new file mode 100644
index 000000000000..54c3fbb4a391
--- /dev/null
+++ b/drivers/mmc/host/dw_mmc-bluefield.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Mellanox Technologies.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include "dw_mmc.h"
+#include "dw_mmc-pltfm.h"
+
+#define UHS_REG_EXT_SAMPLE_MASK		GENMASK(22, 16)
+#define UHS_REG_EXT_DRIVE_MASK		GENMASK(29, 23)
+#define BLUEFIELD_UHS_REG_EXT_SAMPLE	2
+#define BLUEFIELD_UHS_REG_EXT_DRIVE	4
+
+static void dw_mci_bluefield_set_ios(struct dw_mci *host, struct mmc_ios *ios)
+{
+	u32 reg;
+
+	/* Update the Drive and Sample fields in register UHS_REG_EXT. */
+	reg = mci_readl(host, UHS_REG_EXT);
+	reg &= ~UHS_REG_EXT_SAMPLE_MASK;
+	reg |= FIELD_PREP(UHS_REG_EXT_SAMPLE_MASK,
+			  BLUEFIELD_UHS_REG_EXT_SAMPLE);
+	reg &= ~UHS_REG_EXT_DRIVE_MASK;
+	reg |= FIELD_PREP(UHS_REG_EXT_DRIVE_MASK, BLUEFIELD_UHS_REG_EXT_DRIVE);
+	mci_writel(host, UHS_REG_EXT, reg);
+}
+
+static const struct dw_mci_drv_data bluefield_drv_data = {
+	.set_ios		= dw_mci_bluefield_set_ios
+};
+
+static const struct of_device_id dw_mci_bluefield_match[] = {
+	{ .compatible = "mellanox,bluefield-dw-mshc",
+	  .data = &bluefield_drv_data },
+	{},
+};
+MODULE_DEVICE_TABLE(of, dw_mci_bluefield_match);
+
+static int dw_mci_bluefield_probe(struct platform_device *pdev)
+{
+	const struct dw_mci_drv_data *drv_data = NULL;
+	const struct of_device_id *match;
+
+	if (pdev->dev.of_node) {
+		match = of_match_node(dw_mci_bluefield_match,
+				      pdev->dev.of_node);
+		drv_data = match->data;
+	}
+
+	return dw_mci_pltfm_register(pdev, drv_data);
+}
+
+static struct platform_driver dw_mci_bluefield_pltfm_driver = {
+	.probe		= dw_mci_bluefield_probe,
+	.remove		= dw_mci_pltfm_remove,
+	.driver		= {
+		.name		= "dwmmc_bluefield",
+		.of_match_table	= dw_mci_bluefield_match,
+		.pm		= &dw_mci_pltfm_pmops,
+	},
+};
+
+module_platform_driver(dw_mci_bluefield_pltfm_driver);
+
+MODULE_DESCRIPTION("BlueField DW Multimedia Card driver");
+MODULE_AUTHOR("Mellanox Technologies");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index 40d7de2eea12..8c86a800a8fd 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -44,9 +44,8 @@ static void dw_mci_rk3288_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 	 * bus_hz = cclkin / RK3288_CLKGEN_DIV
 	 * ios->clock = (div == 0) ? bus_hz : (bus_hz / (2 * div))
 	 *
-	 * Note: div can only be 0 or 1
-	 *       if DDR50 8bit mode(only emmc work in 8bit mode),
-	 *       div must be set 1
+	 * Note: div can only be 0 or 1, but div must be set to 1 for eMMC
+	 * DDR52 8-bit mode.
 	 */
 	if (ios->bus_width == MMC_BUS_WIDTH_8 &&
 	    ios->timing == MMC_TIMING_MMC_DDR52)
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 29a1afa81f66..623f4d27fa01 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -1230,6 +1230,8 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 	if (host->state == STATE_WAITING_CMD11_DONE)
 		sdmmc_cmd_bits |= SDMMC_CMD_VOLT_SWITCH;
 
+	slot->mmc->actual_clock = 0;
+
 	if (!clock) {
 		mci_writel(host, CLKENA, 0);
 		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
@@ -1288,6 +1290,8 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 
 		/* keep the last clock value that was requested from core */
 		slot->__clk_old = clock;
+		slot->mmc->actual_clock = div ? ((host->bus_hz / div) >> 1) :
+					  host->bus_hz;
 	}
 
 	host->current_speed = clock;
diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c
index a0168e9e4fce..993386c9ea50 100644
--- a/drivers/mmc/host/jz4740_mmc.c
+++ b/drivers/mmc/host/jz4740_mmc.c
@@ -1,5 +1,7 @@
 /*
  *  Copyright (C) 2009-2010, Lars-Peter Clausen <lars@metafoo.de>
+ *  Copyright (C) 2013, Imagination Technologies
+ *
  *  JZ4740 SD/MMC controller driver
  *
  *  This program is free software; you can redistribute  it and/or modify it
@@ -13,24 +15,25 @@
  *
  */
 
-#include <linux/mmc/host.h>
-#include <linux/mmc/slot-gpio.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
-#include <linux/interrupt.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/slot-gpio.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
-#include <linux/delay.h>
 #include <linux/scatterlist.h>
-#include <linux/clk.h>
 
-#include <linux/bitops.h>
-#include <linux/gpio.h>
 #include <asm/cacheflush.h>
-#include <linux/dma-mapping.h>
-#include <linux/dmaengine.h>
 
 #include <asm/mach-jz4740/dma.h>
 #include <asm/mach-jz4740/jz4740_mmc.h>
@@ -51,6 +54,7 @@
 #define JZ_REG_MMC_RESP_FIFO	0x34
 #define JZ_REG_MMC_RXFIFO	0x38
 #define JZ_REG_MMC_TXFIFO	0x3C
+#define JZ_REG_MMC_DMAC		0x44
 
 #define JZ_MMC_STRPCL_EXIT_MULTIPLE BIT(7)
 #define JZ_MMC_STRPCL_EXIT_TRANSFER BIT(6)
@@ -104,9 +108,17 @@
 #define JZ_MMC_IRQ_PRG_DONE BIT(1)
 #define JZ_MMC_IRQ_DATA_TRAN_DONE BIT(0)
 
+#define JZ_MMC_DMAC_DMA_SEL BIT(1)
+#define JZ_MMC_DMAC_DMA_EN BIT(0)
 
 #define JZ_MMC_CLK_RATE 24000000
 
+enum jz4740_mmc_version {
+	JZ_MMC_JZ4740,
+	JZ_MMC_JZ4750,
+	JZ_MMC_JZ4780,
+};
+
 enum jz4740_mmc_state {
 	JZ4740_MMC_STATE_READ_RESPONSE,
 	JZ4740_MMC_STATE_TRANSFER_DATA,
@@ -125,6 +137,8 @@ struct jz4740_mmc_host {
 	struct jz4740_mmc_platform_data *pdata;
 	struct clk *clk;
 
+	enum jz4740_mmc_version version;
+
 	int irq;
 	int card_detect_irq;
 
@@ -137,7 +151,7 @@ struct jz4740_mmc_host {
 
 	uint32_t cmdat;
 
-	uint16_t irq_mask;
+	uint32_t irq_mask;
 
 	spinlock_t lock;
 
@@ -159,6 +173,32 @@ struct jz4740_mmc_host {
 #define JZ4740_MMC_FIFO_HALF_SIZE 8
 };
 
+static void jz4740_mmc_write_irq_mask(struct jz4740_mmc_host *host,
+				      uint32_t val)
+{
+	if (host->version >= JZ_MMC_JZ4750)
+		return writel(val, host->base + JZ_REG_MMC_IMASK);
+	else
+		return writew(val, host->base + JZ_REG_MMC_IMASK);
+}
+
+static void jz4740_mmc_write_irq_reg(struct jz4740_mmc_host *host,
+				     uint32_t val)
+{
+	if (host->version >= JZ_MMC_JZ4780)
+		return writel(val, host->base + JZ_REG_MMC_IREG);
+	else
+		return writew(val, host->base + JZ_REG_MMC_IREG);
+}
+
+static uint32_t jz4740_mmc_read_irq_reg(struct jz4740_mmc_host *host)
+{
+	if (host->version >= JZ_MMC_JZ4780)
+		return readl(host->base + JZ_REG_MMC_IREG);
+	else
+		return readw(host->base + JZ_REG_MMC_IREG);
+}
+
 /*----------------------------------------------------------------------------*/
 /* DMA infrastructure */
 
@@ -173,31 +213,23 @@ static void jz4740_mmc_release_dma_channels(struct jz4740_mmc_host *host)
 
 static int jz4740_mmc_acquire_dma_channels(struct jz4740_mmc_host *host)
 {
-	dma_cap_mask_t mask;
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-
-	host->dma_tx = dma_request_channel(mask, NULL, host);
-	if (!host->dma_tx) {
+	host->dma_tx = dma_request_chan(mmc_dev(host->mmc), "tx");
+	if (IS_ERR(host->dma_tx)) {
 		dev_err(mmc_dev(host->mmc), "Failed to get dma_tx channel\n");
-		return -ENODEV;
+		return PTR_ERR(host->dma_tx);
 	}
 
-	host->dma_rx = dma_request_channel(mask, NULL, host);
-	if (!host->dma_rx) {
+	host->dma_rx = dma_request_chan(mmc_dev(host->mmc), "rx");
+	if (IS_ERR(host->dma_rx)) {
 		dev_err(mmc_dev(host->mmc), "Failed to get dma_rx channel\n");
-		goto free_master_write;
+		dma_release_channel(host->dma_tx);
+		return PTR_ERR(host->dma_rx);
 	}
 
 	/* Initialize DMA pre request cookie */
 	host->next_data.cookie = 1;
 
 	return 0;
-
-free_master_write:
-	dma_release_channel(host->dma_tx);
-	return -ENODEV;
 }
 
 static inline struct dma_chan *jz4740_mmc_get_dma_chan(struct jz4740_mmc_host *host,
@@ -363,7 +395,7 @@ static void jz4740_mmc_set_irq_enabled(struct jz4740_mmc_host *host,
 	else
 		host->irq_mask |= irq;
 
-	writew(host->irq_mask, host->base + JZ_REG_MMC_IMASK);
+	jz4740_mmc_write_irq_mask(host, host->irq_mask);
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -415,10 +447,10 @@ static unsigned int jz4740_mmc_poll_irq(struct jz4740_mmc_host *host,
 	unsigned int irq)
 {
 	unsigned int timeout = 0x800;
-	uint16_t status;
+	uint32_t status;
 
 	do {
-		status = readw(host->base + JZ_REG_MMC_IREG);
+		status = jz4740_mmc_read_irq_reg(host);
 	} while (!(status & irq) && --timeout);
 
 	if (timeout == 0) {
@@ -518,7 +550,7 @@ static bool jz4740_mmc_read_data(struct jz4740_mmc_host *host,
 	void __iomem *fifo_addr = host->base + JZ_REG_MMC_RXFIFO;
 	uint32_t *buf;
 	uint32_t d;
-	uint16_t status;
+	uint32_t status;
 	size_t i, j;
 	unsigned int timeout;
 
@@ -654,8 +686,25 @@ static void jz4740_mmc_send_command(struct jz4740_mmc_host *host,
 		cmdat |= JZ_MMC_CMDAT_DATA_EN;
 		if (cmd->data->flags & MMC_DATA_WRITE)
 			cmdat |= JZ_MMC_CMDAT_WRITE;
-		if (host->use_dma)
-			cmdat |= JZ_MMC_CMDAT_DMA_EN;
+		if (host->use_dma) {
+			/*
+			 * The 4780's MMC controller has integrated DMA ability
+			 * in addition to being able to use the external DMA
+			 * controller. It moves DMA control bits to a separate
+			 * register. The DMA_SEL bit chooses the external
+			 * controller over the integrated one. Earlier SoCs
+			 * can only use the external controller, and have a
+			 * single DMA enable bit in CMDAT.
+			 */
+			if (host->version >= JZ_MMC_JZ4780) {
+				writel(JZ_MMC_DMAC_DMA_EN | JZ_MMC_DMAC_DMA_SEL,
+				       host->base + JZ_REG_MMC_DMAC);
+			} else {
+				cmdat |= JZ_MMC_CMDAT_DMA_EN;
+			}
+		} else if (host->version >= JZ_MMC_JZ4780) {
+			writel(0, host->base + JZ_REG_MMC_DMAC);
+		}
 
 		writew(cmd->data->blksz, host->base + JZ_REG_MMC_BLKLEN);
 		writew(cmd->data->blocks, host->base + JZ_REG_MMC_NOB);
@@ -736,7 +785,7 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid)
 			host->state = JZ4740_MMC_STATE_SEND_STOP;
 			break;
 		}
-		writew(JZ_MMC_IRQ_DATA_TRAN_DONE, host->base + JZ_REG_MMC_IREG);
+		jz4740_mmc_write_irq_reg(host, JZ_MMC_IRQ_DATA_TRAN_DONE);
 
 	case JZ4740_MMC_STATE_SEND_STOP:
 		if (!req->stop)
@@ -766,9 +815,10 @@ static irqreturn_t jz_mmc_irq(int irq, void *devid)
 {
 	struct jz4740_mmc_host *host = devid;
 	struct mmc_command *cmd = host->cmd;
-	uint16_t irq_reg, status, tmp;
+	uint32_t irq_reg, status, tmp;
 
-	irq_reg = readw(host->base + JZ_REG_MMC_IREG);
+	status = readl(host->base + JZ_REG_MMC_STATUS);
+	irq_reg = jz4740_mmc_read_irq_reg(host);
 
 	tmp = irq_reg;
 	irq_reg &= ~host->irq_mask;
@@ -777,10 +827,10 @@ static irqreturn_t jz_mmc_irq(int irq, void *devid)
 		JZ_MMC_IRQ_PRG_DONE | JZ_MMC_IRQ_DATA_TRAN_DONE);
 
 	if (tmp != irq_reg)
-		writew(tmp & ~irq_reg, host->base + JZ_REG_MMC_IREG);
+		jz4740_mmc_write_irq_reg(host, tmp & ~irq_reg);
 
 	if (irq_reg & JZ_MMC_IRQ_SDIO) {
-		writew(JZ_MMC_IRQ_SDIO, host->base + JZ_REG_MMC_IREG);
+		jz4740_mmc_write_irq_reg(host, JZ_MMC_IRQ_SDIO);
 		mmc_signal_sdio_irq(host->mmc);
 		irq_reg &= ~JZ_MMC_IRQ_SDIO;
 	}
@@ -789,8 +839,6 @@ static irqreturn_t jz_mmc_irq(int irq, void *devid)
 		if (test_and_clear_bit(0, &host->waiting)) {
 			del_timer(&host->timeout_timer);
 
-			status = readl(host->base + JZ_REG_MMC_STATUS);
-
 			if (status & JZ_MMC_STATUS_TIMEOUT_RES) {
 					cmd->error = -ETIMEDOUT;
 			} else if (status & JZ_MMC_STATUS_CRC_RES_ERR) {
@@ -803,7 +851,7 @@ static irqreturn_t jz_mmc_irq(int irq, void *devid)
 			}
 
 			jz4740_mmc_set_irq_enabled(host, irq_reg, false);
-			writew(irq_reg, host->base + JZ_REG_MMC_IREG);
+			jz4740_mmc_write_irq_reg(host, irq_reg);
 
 			return IRQ_WAKE_THREAD;
 		}
@@ -818,7 +866,7 @@ static int jz4740_mmc_set_clock_rate(struct jz4740_mmc_host *host, int rate)
 	int real_rate;
 
 	jz4740_mmc_clock_disable(host);
-	clk_set_rate(host->clk, JZ_MMC_CLK_RATE);
+	clk_set_rate(host->clk, host->mmc->f_max);
 
 	real_rate = clk_get_rate(host->clk);
 
@@ -837,9 +885,7 @@ static void jz4740_mmc_request(struct mmc_host *mmc, struct mmc_request *req)
 
 	host->req = req;
 
-	writew(0xffff, host->base + JZ_REG_MMC_IREG);
-
-	writew(JZ_MMC_IRQ_END_CMD_RES, host->base + JZ_REG_MMC_IREG);
+	jz4740_mmc_write_irq_reg(host, ~0);
 	jz4740_mmc_set_irq_enabled(host, JZ_MMC_IRQ_END_CMD_RES, true);
 
 	host->state = JZ4740_MMC_STATE_READ_RESPONSE;
@@ -857,7 +903,7 @@ static void jz4740_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	switch (ios->power_mode) {
 	case MMC_POWER_UP:
 		jz4740_mmc_reset(host);
-		if (gpio_is_valid(host->pdata->gpio_power))
+		if (host->pdata && gpio_is_valid(host->pdata->gpio_power))
 			gpio_set_value(host->pdata->gpio_power,
 					!host->pdata->power_active_low);
 		host->cmdat |= JZ_MMC_CMDAT_INIT;
@@ -866,7 +912,7 @@ static void jz4740_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	case MMC_POWER_ON:
 		break;
 	default:
-		if (gpio_is_valid(host->pdata->gpio_power))
+		if (host->pdata && gpio_is_valid(host->pdata->gpio_power))
 			gpio_set_value(host->pdata->gpio_power,
 					host->pdata->power_active_low);
 		clk_disable_unprepare(host->clk);
@@ -926,7 +972,7 @@ static int jz4740_mmc_request_gpio(struct device *dev, int gpio,
 static int jz4740_mmc_request_gpios(struct mmc_host *mmc,
 	struct platform_device *pdev)
 {
-	struct jz4740_mmc_platform_data *pdata = pdev->dev.platform_data;
+	struct jz4740_mmc_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	int ret = 0;
 
 	if (!pdata)
@@ -955,7 +1001,7 @@ static int jz4740_mmc_request_gpios(struct mmc_host *mmc,
 
 static void jz4740_mmc_free_gpios(struct platform_device *pdev)
 {
-	struct jz4740_mmc_platform_data *pdata = pdev->dev.platform_data;
+	struct jz4740_mmc_platform_data *pdata = dev_get_platdata(&pdev->dev);
 
 	if (!pdata)
 		return;
@@ -964,14 +1010,22 @@ static void jz4740_mmc_free_gpios(struct platform_device *pdev)
 		gpio_free(pdata->gpio_power);
 }
 
+static const struct of_device_id jz4740_mmc_of_match[] = {
+	{ .compatible = "ingenic,jz4740-mmc", .data = (void *) JZ_MMC_JZ4740 },
+	{ .compatible = "ingenic,jz4780-mmc", .data = (void *) JZ_MMC_JZ4780 },
+	{},
+};
+MODULE_DEVICE_TABLE(of, jz4740_mmc_of_match);
+
 static int jz4740_mmc_probe(struct platform_device* pdev)
 {
 	int ret;
 	struct mmc_host *mmc;
 	struct jz4740_mmc_host *host;
+	const struct of_device_id *match;
 	struct jz4740_mmc_platform_data *pdata;
 
-	pdata = pdev->dev.platform_data;
+	pdata = dev_get_platdata(&pdev->dev);
 
 	mmc = mmc_alloc_host(sizeof(struct jz4740_mmc_host), &pdev->dev);
 	if (!mmc) {
@@ -982,6 +1036,27 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 	host = mmc_priv(mmc);
 	host->pdata = pdata;
 
+	match = of_match_device(jz4740_mmc_of_match, &pdev->dev);
+	if (match) {
+		host->version = (enum jz4740_mmc_version)match->data;
+		ret = mmc_of_parse(mmc);
+		if (ret) {
+			if (ret != -EPROBE_DEFER)
+				dev_err(&pdev->dev,
+					"could not parse of data: %d\n", ret);
+			goto err_free_host;
+		}
+	} else {
+		/* JZ4740 should be the only one using legacy probe */
+		host->version = JZ_MMC_JZ4740;
+		mmc->caps |= MMC_CAP_SDIO_IRQ;
+		if (!(pdata && pdata->data_1bit))
+			mmc->caps |= MMC_CAP_4_BIT_DATA;
+		ret = jz4740_mmc_request_gpios(mmc, pdev);
+		if (ret)
+			goto err_free_host;
+	}
+
 	host->irq = platform_get_irq(pdev, 0);
 	if (host->irq < 0) {
 		ret = host->irq;
@@ -1004,16 +1079,11 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 		goto err_free_host;
 	}
 
-	ret = jz4740_mmc_request_gpios(mmc, pdev);
-	if (ret)
-		goto err_release_dma;
-
 	mmc->ops = &jz4740_mmc_ops;
-	mmc->f_min = JZ_MMC_CLK_RATE / 128;
-	mmc->f_max = JZ_MMC_CLK_RATE;
+	if (!mmc->f_max)
+		mmc->f_max = JZ_MMC_CLK_RATE;
+	mmc->f_min = mmc->f_max / 128;
 	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
-	mmc->caps = (pdata && pdata->data_1bit) ? 0 : MMC_CAP_4_BIT_DATA;
-	mmc->caps |= MMC_CAP_SDIO_IRQ;
 
 	mmc->max_blk_size = (1 << 10) - 1;
 	mmc->max_blk_count = (1 << 15) - 1;
@@ -1025,7 +1095,9 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 	host->mmc = mmc;
 	host->pdev = pdev;
 	spin_lock_init(&host->lock);
-	host->irq_mask = 0xffff;
+	host->irq_mask = ~0;
+
+	jz4740_mmc_reset(host);
 
 	ret = request_threaded_irq(host->irq, jz_mmc_irq, jz_mmc_irq_worker, 0,
 			dev_name(&pdev->dev), host);
@@ -1034,20 +1106,20 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 		goto err_free_gpios;
 	}
 
-	jz4740_mmc_reset(host);
 	jz4740_mmc_clock_disable(host);
 	timer_setup(&host->timeout_timer, jz4740_mmc_timeout, 0);
 
-	host->use_dma = true;
-	if (host->use_dma && jz4740_mmc_acquire_dma_channels(host) != 0)
-		host->use_dma = false;
+	ret = jz4740_mmc_acquire_dma_channels(host);
+	if (ret == -EPROBE_DEFER)
+		goto err_free_irq;
+	host->use_dma = !ret;
 
 	platform_set_drvdata(pdev, host);
 	ret = mmc_add_host(mmc);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to add mmc host: %d\n", ret);
-		goto err_free_irq;
+		goto err_release_dma;
 	}
 	dev_info(&pdev->dev, "JZ SD/MMC card driver registered\n");
 
@@ -1057,13 +1129,13 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 
 	return 0;
 
+err_release_dma:
+	if (host->use_dma)
+		jz4740_mmc_release_dma_channels(host);
 err_free_irq:
 	free_irq(host->irq, host);
 err_free_gpios:
 	jz4740_mmc_free_gpios(pdev);
-err_release_dma:
-	if (host->use_dma)
-		jz4740_mmc_release_dma_channels(host);
 err_free_host:
 	mmc_free_host(mmc);
 
@@ -1116,6 +1188,7 @@ static struct platform_driver jz4740_mmc_driver = {
 	.remove = jz4740_mmc_remove,
 	.driver = {
 		.name = "jz4740-mmc",
+		.of_match_table = of_match_ptr(jz4740_mmc_of_match),
 		.pm = JZ4740_MMC_PM_OPS,
 	},
 };
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index 4f972b879fe6..c201c378537e 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -35,6 +35,7 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/regulator/consumer.h>
+#include <linux/reset.h>
 #include <linux/interrupt.h>
 #include <linux/bitfield.h>
 #include <linux/pinctrl/consumer.h>
@@ -47,15 +48,29 @@
 #define   CLK_CORE_PHASE_MASK GENMASK(9, 8)
 #define   CLK_TX_PHASE_MASK GENMASK(11, 10)
 #define   CLK_RX_PHASE_MASK GENMASK(13, 12)
-#define   CLK_TX_DELAY_MASK GENMASK(19, 16)
-#define   CLK_RX_DELAY_MASK GENMASK(23, 20)
+#define   CLK_V2_TX_DELAY_MASK GENMASK(19, 16)
+#define   CLK_V2_RX_DELAY_MASK GENMASK(23, 20)
+#define   CLK_V2_ALWAYS_ON BIT(24)
+
+#define   CLK_V3_TX_DELAY_MASK GENMASK(21, 16)
+#define   CLK_V3_RX_DELAY_MASK GENMASK(27, 22)
+#define   CLK_V3_ALWAYS_ON BIT(28)
+
 #define   CLK_DELAY_STEP_PS 200
 #define   CLK_PHASE_STEP 30
 #define   CLK_PHASE_POINT_NUM (360 / CLK_PHASE_STEP)
-#define   CLK_ALWAYS_ON BIT(24)
+
+#define   CLK_TX_DELAY_MASK(h)		(h->data->tx_delay_mask)
+#define   CLK_RX_DELAY_MASK(h)		(h->data->rx_delay_mask)
+#define   CLK_ALWAYS_ON(h)		(h->data->always_on)
 
 #define SD_EMMC_DELAY 0x4
 #define SD_EMMC_ADJUST 0x8
+
+#define SD_EMMC_DELAY1 0x4
+#define SD_EMMC_DELAY2 0x8
+#define SD_EMMC_V3_ADJUST 0xc
+
 #define SD_EMMC_CALOUT 0x10
 #define SD_EMMC_START 0x40
 #define   START_DESC_INIT BIT(0)
@@ -122,6 +137,12 @@
 
 #define MUX_CLK_NUM_PARENTS 2
 
+struct meson_mmc_data {
+	unsigned int tx_delay_mask;
+	unsigned int rx_delay_mask;
+	unsigned int always_on;
+};
+
 struct sd_emmc_desc {
 	u32 cmd_cfg;
 	u32 cmd_arg;
@@ -131,6 +152,7 @@ struct sd_emmc_desc {
 
 struct meson_host {
 	struct	device		*dev;
+	struct	meson_mmc_data *data;
 	struct	mmc_host	*mmc;
 	struct	mmc_command	*cmd;
 
@@ -474,7 +496,7 @@ static int meson_mmc_clk_init(struct meson_host *host)
 
 	/* init SD_EMMC_CLOCK to sane defaults w/min clock rate */
 	clk_reg = 0;
-	clk_reg |= CLK_ALWAYS_ON;
+	clk_reg |= CLK_ALWAYS_ON(host);
 	clk_reg |= CLK_DIV_MASK;
 	writel(clk_reg, host->regs + SD_EMMC_CLOCK);
 
@@ -574,7 +596,7 @@ static int meson_mmc_clk_init(struct meson_host *host)
 
 	tx->reg = host->regs + SD_EMMC_CLOCK;
 	tx->phase_mask = CLK_TX_PHASE_MASK;
-	tx->delay_mask = CLK_TX_DELAY_MASK;
+	tx->delay_mask = CLK_TX_DELAY_MASK(host);
 	tx->delay_step_ps = CLK_DELAY_STEP_PS;
 	tx->hw.init = &init;
 
@@ -597,7 +619,7 @@ static int meson_mmc_clk_init(struct meson_host *host)
 
 	rx->reg = host->regs + SD_EMMC_CLOCK;
 	rx->phase_mask = CLK_RX_PHASE_MASK;
-	rx->delay_mask = CLK_RX_DELAY_MASK;
+	rx->delay_mask = CLK_RX_DELAY_MASK(host);
 	rx->delay_step_ps = CLK_DELAY_STEP_PS;
 	rx->hw.init = &init;
 
@@ -1184,6 +1206,21 @@ static int meson_mmc_probe(struct platform_device *pdev)
 		goto free_host;
 	}
 
+	host->data = (struct meson_mmc_data *)
+		of_device_get_match_data(&pdev->dev);
+	if (!host->data) {
+		ret = -EINVAL;
+		goto free_host;
+	}
+
+	ret = device_reset_optional(&pdev->dev);
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "device reset failed: %d\n", ret);
+
+		return ret;
+	}
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->regs = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(host->regs)) {
@@ -1315,11 +1352,24 @@ static int meson_mmc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct meson_mmc_data meson_gx_data = {
+	.tx_delay_mask	= CLK_V2_TX_DELAY_MASK,
+	.rx_delay_mask	= CLK_V2_RX_DELAY_MASK,
+	.always_on	= CLK_V2_ALWAYS_ON,
+};
+
+static const struct meson_mmc_data meson_axg_data = {
+	.tx_delay_mask	= CLK_V3_TX_DELAY_MASK,
+	.rx_delay_mask	= CLK_V3_RX_DELAY_MASK,
+	.always_on	= CLK_V3_ALWAYS_ON,
+};
+
 static const struct of_device_id meson_mmc_of_match[] = {
-	{ .compatible = "amlogic,meson-gx-mmc", },
-	{ .compatible = "amlogic,meson-gxbb-mmc", },
-	{ .compatible = "amlogic,meson-gxl-mmc", },
-	{ .compatible = "amlogic,meson-gxm-mmc", },
+	{ .compatible = "amlogic,meson-gx-mmc",		.data = &meson_gx_data },
+	{ .compatible = "amlogic,meson-gxbb-mmc", 	.data = &meson_gx_data },
+	{ .compatible = "amlogic,meson-gxl-mmc",	.data = &meson_gx_data },
+	{ .compatible = "amlogic,meson-gxm-mmc",	.data = &meson_gx_data },
+	{ .compatible = "amlogic,meson-axg-mmc",	.data = &meson_axg_data },
 	{}
 };
 MODULE_DEVICE_TABLE(of, meson_mmc_of_match);
@@ -1335,6 +1385,6 @@ static struct platform_driver meson_mmc_driver = {
 
 module_platform_driver(meson_mmc_driver);
 
-MODULE_DESCRIPTION("Amlogic S905*/GX* SD/eMMC driver");
+MODULE_DESCRIPTION("Amlogic S905*/GX*/AXG SD/eMMC driver");
 MODULE_AUTHOR("Kevin Hilman <khilman@baylibre.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 70b0df8b9c78..f1849775e47e 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1253,15 +1253,12 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
 	struct sg_mapping_iter *sg_miter = &host->sg_miter;
 	struct variant_data *variant = host->variant;
 	void __iomem *base = host->base;
-	unsigned long flags;
 	u32 status;
 
 	status = readl(base + MMCISTATUS);
 
 	dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status);
 
-	local_irq_save(flags);
-
 	do {
 		unsigned int remain, len;
 		char *buffer;
@@ -1301,8 +1298,6 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
 
 	sg_miter_stop(sg_miter);
 
-	local_irq_restore(flags);
-
 	/*
 	 * If we have less than the fifo 'half-full' threshold to transfer,
 	 * trigger a PIO interrupt as soon as any data is available.
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index cb274e822293..04841386b65d 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -19,6 +19,7 @@
 #include <linux/ioport.h>
 #include <linux/irq.h>
 #include <linux/of_address.h>
+#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/of_gpio.h>
 #include <linux/pinctrl/consumer.h>
@@ -70,6 +71,7 @@
 #define SDC_ADV_CFG0     0x64
 #define EMMC_IOCON       0x7c
 #define SDC_ACMD_RESP    0x80
+#define DMA_SA_H4BIT     0x8c
 #define MSDC_DMA_SA      0x90
 #define MSDC_DMA_CTRL    0x98
 #define MSDC_DMA_CFG     0x9c
@@ -194,6 +196,9 @@
 /* SDC_ADV_CFG0 mask */
 #define SDC_RX_ENHANCE_EN	(0x1 << 20)	/* RW */
 
+/* DMA_SA_H4BIT mask */
+#define DMA_ADDR_HIGH_4BIT      (0xf << 0)      /* RW */
+
 /* MSDC_DMA_CTRL mask */
 #define MSDC_DMA_CTRL_START     (0x1 << 0)	/* W */
 #define MSDC_DMA_CTRL_STOP      (0x1 << 1)	/* W */
@@ -227,6 +232,7 @@
 
 #define MSDC_PATCH_BIT2_CFGRESP   (0x1 << 15)   /* RW */
 #define MSDC_PATCH_BIT2_CFGCRCSTS (0x1 << 28)   /* RW */
+#define MSDC_PB2_SUPPORT_64G      (0x1 << 1)    /* RW */
 #define MSDC_PB2_RESPWAIT         (0x3 << 2)    /* RW */
 #define MSDC_PB2_RESPSTSENSEL     (0x7 << 16)   /* RW */
 #define MSDC_PB2_CRCSTSENSEL      (0x7 << 29)   /* RW */
@@ -280,6 +286,8 @@ struct mt_gpdma_desc {
 #define GPDMA_DESC_BDP		(0x1 << 1)
 #define GPDMA_DESC_CHECKSUM	(0xff << 8) /* bit8 ~ bit15 */
 #define GPDMA_DESC_INT		(0x1 << 16)
+#define GPDMA_DESC_NEXT_H4	(0xf << 24)
+#define GPDMA_DESC_PTR_H4	(0xf << 28)
 	u32 next;
 	u32 ptr;
 	u32 gpd_data_len;
@@ -296,6 +304,8 @@ struct mt_bdma_desc {
 #define BDMA_DESC_CHECKSUM	(0xff << 8) /* bit8 ~ bit15 */
 #define BDMA_DESC_BLKPAD	(0x1 << 17)
 #define BDMA_DESC_DWPAD		(0x1 << 18)
+#define BDMA_DESC_NEXT_H4	(0xf << 24)
+#define BDMA_DESC_PTR_H4	(0xf << 28)
 	u32 next;
 	u32 ptr;
 	u32 bd_data_len;
@@ -334,6 +344,7 @@ struct mtk_mmc_compatible {
 	bool busy_check;
 	bool stop_clk_fix;
 	bool enhance_rx;
+	bool support_64g;
 };
 
 struct msdc_tune_para {
@@ -403,6 +414,7 @@ static const struct mtk_mmc_compatible mt8135_compat = {
 	.busy_check = false,
 	.stop_clk_fix = false,
 	.enhance_rx = false,
+	.support_64g = false,
 };
 
 static const struct mtk_mmc_compatible mt8173_compat = {
@@ -414,6 +426,7 @@ static const struct mtk_mmc_compatible mt8173_compat = {
 	.busy_check = false,
 	.stop_clk_fix = false,
 	.enhance_rx = false,
+	.support_64g = false,
 };
 
 static const struct mtk_mmc_compatible mt2701_compat = {
@@ -425,6 +438,7 @@ static const struct mtk_mmc_compatible mt2701_compat = {
 	.busy_check = false,
 	.stop_clk_fix = false,
 	.enhance_rx = false,
+	.support_64g = false,
 };
 
 static const struct mtk_mmc_compatible mt2712_compat = {
@@ -436,6 +450,7 @@ static const struct mtk_mmc_compatible mt2712_compat = {
 	.busy_check = true,
 	.stop_clk_fix = true,
 	.enhance_rx = true,
+	.support_64g = true,
 };
 
 static const struct mtk_mmc_compatible mt7622_compat = {
@@ -447,6 +462,7 @@ static const struct mtk_mmc_compatible mt7622_compat = {
 	.busy_check = true,
 	.stop_clk_fix = true,
 	.enhance_rx = true,
+	.support_64g = false,
 };
 
 static const struct of_device_id msdc_of_ids[] = {
@@ -556,7 +572,12 @@ static inline void msdc_dma_setup(struct msdc_host *host, struct msdc_dma *dma,
 		/* init bd */
 		bd[j].bd_info &= ~BDMA_DESC_BLKPAD;
 		bd[j].bd_info &= ~BDMA_DESC_DWPAD;
-		bd[j].ptr = (u32)dma_address;
+		bd[j].ptr = lower_32_bits(dma_address);
+		if (host->dev_comp->support_64g) {
+			bd[j].bd_info &= ~BDMA_DESC_PTR_H4;
+			bd[j].bd_info |= (upper_32_bits(dma_address) & 0xf)
+					 << 28;
+		}
 		bd[j].bd_data_len &= ~BDMA_DESC_BUFLEN;
 		bd[j].bd_data_len |= (dma_len & BDMA_DESC_BUFLEN);
 
@@ -575,7 +596,10 @@ static inline void msdc_dma_setup(struct msdc_host *host, struct msdc_dma *dma,
 	dma_ctrl &= ~(MSDC_DMA_CTRL_BRUSTSZ | MSDC_DMA_CTRL_MODE);
 	dma_ctrl |= (MSDC_BURST_64B << 12 | 1 << 8);
 	writel_relaxed(dma_ctrl, host->base + MSDC_DMA_CTRL);
-	writel((u32)dma->gpd_addr, host->base + MSDC_DMA_SA);
+	if (host->dev_comp->support_64g)
+		sdr_set_field(host->base + DMA_SA_H4BIT, DMA_ADDR_HIGH_4BIT,
+			      upper_32_bits(dma->gpd_addr) & 0xf);
+	writel(lower_32_bits(dma->gpd_addr), host->base + MSDC_DMA_SA);
 }
 
 static void msdc_prepare_data(struct msdc_host *host, struct mmc_request *mrq)
@@ -1366,6 +1390,9 @@ static void msdc_init_hw(struct msdc_host *host)
 			     MSDC_PATCH_BIT2_CFGCRCSTS);
 	}
 
+	if (host->dev_comp->support_64g)
+		sdr_set_bits(host->base + MSDC_PATCH_BIT2,
+			     MSDC_PB2_SUPPORT_64G);
 	if (host->dev_comp->data_tune) {
 		sdr_set_bits(host->base + tune_reg,
 			     MSDC_PAD_TUNE_RD_SEL | MSDC_PAD_TUNE_CMD_SEL);
@@ -1407,19 +1434,32 @@ static void msdc_init_gpd_bd(struct msdc_host *host, struct msdc_dma *dma)
 {
 	struct mt_gpdma_desc *gpd = dma->gpd;
 	struct mt_bdma_desc *bd = dma->bd;
+	dma_addr_t dma_addr;
 	int i;
 
 	memset(gpd, 0, sizeof(struct mt_gpdma_desc) * 2);
 
+	dma_addr = dma->gpd_addr + sizeof(struct mt_gpdma_desc);
 	gpd->gpd_info = GPDMA_DESC_BDP; /* hwo, cs, bd pointer */
-	gpd->ptr = (u32)dma->bd_addr; /* physical address */
 	/* gpd->next is must set for desc DMA
 	 * That's why must alloc 2 gpd structure.
 	 */
-	gpd->next = (u32)dma->gpd_addr + sizeof(struct mt_gpdma_desc);
+	gpd->next = lower_32_bits(dma_addr);
+	if (host->dev_comp->support_64g)
+		gpd->gpd_info |= (upper_32_bits(dma_addr) & 0xf) << 24;
+
+	dma_addr = dma->bd_addr;
+	gpd->ptr = lower_32_bits(dma->bd_addr); /* physical address */
+	if (host->dev_comp->support_64g)
+		gpd->gpd_info |= (upper_32_bits(dma_addr) & 0xf) << 28;
+
 	memset(bd, 0, sizeof(struct mt_bdma_desc) * MAX_BD_NUM);
-	for (i = 0; i < (MAX_BD_NUM - 1); i++)
-		bd[i].next = (u32)dma->bd_addr + sizeof(*bd) * (i + 1);
+	for (i = 0; i < (MAX_BD_NUM - 1); i++) {
+		dma_addr = dma->bd_addr + sizeof(*bd) * (i + 1);
+		bd[i].next = lower_32_bits(dma_addr);
+		if (host->dev_comp->support_64g)
+			bd[i].bd_info |= (upper_32_bits(dma_addr) & 0xf) << 24;
+	}
 }
 
 static void msdc_ops_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
@@ -1820,7 +1860,6 @@ static int msdc_drv_probe(struct platform_device *pdev)
 	struct mmc_host *mmc;
 	struct msdc_host *host;
 	struct resource *res;
-	const struct of_device_id *of_id;
 	int ret;
 
 	if (!pdev->dev.of_node) {
@@ -1828,9 +1867,6 @@ static int msdc_drv_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	of_id = of_match_node(msdc_of_ids, pdev->dev.of_node);
-	if (!of_id)
-		return -EINVAL;
 	/* Allocate MMC host for this device */
 	mmc = mmc_alloc_host(sizeof(struct msdc_host), &pdev->dev);
 	if (!mmc)
@@ -1899,7 +1935,7 @@ static int msdc_drv_probe(struct platform_device *pdev)
 	msdc_of_property_parse(pdev, host);
 
 	host->dev = &pdev->dev;
-	host->dev_comp = of_id->data;
+	host->dev_comp = of_device_get_match_data(&pdev->dev);
 	host->mmc = mmc;
 	host->src_clk_freq = clk_get_rate(host->src_clk);
 	/* Set host parameters to mmc */
@@ -1916,7 +1952,10 @@ static int msdc_drv_probe(struct platform_device *pdev)
 	mmc->max_blk_size = 2048;
 	mmc->max_req_size = 512 * 1024;
 	mmc->max_blk_count = mmc->max_req_size / 512;
-	host->dma_mask = DMA_BIT_MASK(32);
+	if (host->dev_comp->support_64g)
+		host->dma_mask = DMA_BIT_MASK(36);
+	else
+		host->dma_mask = DMA_BIT_MASK(32);
 	mmc_dev(mmc)->dma_mask = &host->dma_mask;
 
 	host->timeout_clks = 3 * 1048576;
diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c
index 210247b3d11a..e22bbff89c8d 100644
--- a/drivers/mmc/host/mvsdio.c
+++ b/drivers/mmc/host/mvsdio.c
@@ -143,6 +143,7 @@ static void mvsd_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	struct mmc_command *cmd = mrq->cmd;
 	u32 cmdreg = 0, xfer = 0, intr = 0;
 	unsigned long flags;
+	unsigned int timeout;
 
 	BUG_ON(host->mrq != NULL);
 	host->mrq = mrq;
@@ -234,7 +235,8 @@ static void mvsd_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	mvsd_write(MVSD_NOR_INTR_EN, host->intr_en);
 	mvsd_write(MVSD_ERR_INTR_EN, 0xffff);
 
-	mod_timer(&host->timer, jiffies + 5 * HZ);
+	timeout = cmd->busy_timeout ? cmd->busy_timeout : 5000;
+	mod_timer(&host->timer, jiffies + msecs_to_jiffies(timeout));
 
 	spin_unlock_irqrestore(&host->lock, flags);
 }
@@ -755,6 +757,8 @@ static int mvsd_probe(struct platform_device *pdev)
 	if (maxfreq)
 		mmc->f_max = maxfreq;
 
+	mmc->caps |= MMC_CAP_ERASE;
+
 	spin_lock_init(&host->lock);
 
 	host->base = devm_ioremap_resource(&pdev->dev, r);
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 5ff8ef7223cc..75f781c11e89 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
+#include <linux/highmem.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/blkdev.h>
@@ -291,8 +292,10 @@ static void mxcmci_swap_buffers(struct mmc_data *data)
 	struct scatterlist *sg;
 	int i;
 
-	for_each_sg(data->sg, sg, data->sg_len, i)
-		buffer_swap32(sg_virt(sg), sg->length);
+	for_each_sg(data->sg, sg, data->sg_len, i) {
+		void *buf = kmap_atomic(sg_page(sg) + sg->offset;
+		buffer_swap32(buf, sg->length);
+		kunmap_atomic(buf);
 }
 #else
 static inline void mxcmci_swap_buffers(struct mmc_data *data) {}
@@ -609,6 +612,7 @@ static int mxcmci_transfer_data(struct mxcmci_host *host)
 {
 	struct mmc_data *data = host->req->data;
 	struct scatterlist *sg;
+	void *buf;
 	int stat, i;
 
 	host->data = data;
@@ -616,14 +620,18 @@ static int mxcmci_transfer_data(struct mxcmci_host *host)
 
 	if (data->flags & MMC_DATA_READ) {
 		for_each_sg(data->sg, sg, data->sg_len, i) {
-			stat = mxcmci_pull(host, sg_virt(sg), sg->length);
+			buf = kmap_atomic(sg_page(sg) + sg->offset);
+			stat = mxcmci_pull(host, buf, sg->length);
+			kunmap(buf);
 			if (stat)
 				return stat;
 			host->datasize += sg->length;
 		}
 	} else {
 		for_each_sg(data->sg, sg, data->sg_len, i) {
-			stat = mxcmci_push(host, sg_virt(sg), sg->length);
+			buf = kmap_atomic(sg_page(sg) + sg->offset);
+			stat = mxcmci_push(host, buf, sg->length);
+			kunmap(buf);
 			if (stat)
 				return stat;
 			host->datasize += sg->length;
@@ -1206,7 +1214,8 @@ static int mxcmci_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int __maybe_unused mxcmci_suspend(struct device *dev)
+#ifdef CONFIG_PM_SLEEP
+static int mxcmci_suspend(struct device *dev)
 {
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct mxcmci_host *host = mmc_priv(mmc);
@@ -1216,7 +1225,7 @@ static int __maybe_unused mxcmci_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused mxcmci_resume(struct device *dev)
+static int mxcmci_resume(struct device *dev)
 {
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct mxcmci_host *host = mmc_priv(mmc);
@@ -1232,6 +1241,7 @@ static int __maybe_unused mxcmci_resume(struct device *dev)
 
 	return ret;
 }
+#endif
 
 static SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume);
 
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 51e01f03fb99..45c015da2e75 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -28,6 +28,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/mmc/host.h>
+#include <linux/mmc/slot-gpio.h>
 #include <linux/mfd/tmio.h>
 #include <linux/sh_dma.h>
 #include <linux/delay.h>
@@ -534,6 +535,10 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	host->multi_io_quirk	= renesas_sdhi_multi_io_quirk;
 	host->dma_ops		= dma_ops;
 
+	/* For some SoC, we disable internal WP. GPIO may override this */
+	if (mmc_can_gpio_ro(host->mmc))
+		mmc_data->capabilities2 &= ~MMC_CAP2_NO_WRITE_PROTECT;
+
 	/* SDR speeds are only available on Gen2+ */
 	if (mmc_data->flags & TMIO_MMC_MIN_RCAR2) {
 		/* card_busy caused issues on r8a73a4 (pre-Gen2) CD-less SDHI */
diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index 8e0acd197c43..f7f9773d161f 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -9,6 +9,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/io-64-nonatomic-hi-lo.h>
@@ -62,6 +63,17 @@
  *   need a custom accessor.
  */
 
+static unsigned long global_flags;
+/*
+ * Workaround for avoiding to use RX DMAC by multiple channels.
+ * On R-Car H3 ES1.* and M3-W ES1.0, when multiple SDHI channels use
+ * RX DMAC simultaneously, sometimes hundreds of bytes data are not
+ * stored into the system memory even if the DMAC interrupt happened.
+ * So, this driver then uses one RX DMAC channel only.
+ */
+#define SDHI_INTERNAL_DMAC_ONE_RX_ONLY	0
+#define SDHI_INTERNAL_DMAC_RX_IN_USE	1
+
 /* Definitions for sampling clocks */
 static struct renesas_sdhi_scc rcar_gen3_scc_taps[] = {
 	{
@@ -75,11 +87,12 @@ static const struct renesas_sdhi_of_data of_rcar_gen3_compatible = {
 			  TMIO_MMC_HAVE_CBSY | TMIO_MMC_MIN_RCAR2,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_CMD23,
+	.capabilities2	= MMC_CAP2_NO_WRITE_PROTECT,
 	.bus_shift	= 2,
 	.scc_offset	= 0x1000,
 	.taps		= rcar_gen3_scc_taps,
 	.taps_num	= ARRAY_SIZE(rcar_gen3_scc_taps),
-	/* Gen3 SDHI DMAC can handle 0xffffffff blk count, but seg = 1 */
+	/* DMAC can handle 0xffffffff blk count but only 1 segment */
 	.max_blk_count	= 0xffffffff,
 	.max_segs	= 1,
 };
@@ -126,6 +139,9 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) {
 	renesas_sdhi_internal_dmac_dm_write(host, DM_CM_RST,
 					    RST_RESERVED_BITS | val);
 
+	if (host->data && host->data->flags & MMC_DATA_READ)
+		clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+
 	renesas_sdhi_internal_dmac_enable_dma(host, true);
 }
 
@@ -142,35 +158,34 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 {
 	struct scatterlist *sg = host->sg_ptr;
 	u32 dtran_mode = DTRAN_MODE_BUS_WID_TH | DTRAN_MODE_ADDR_MODE;
-	enum dma_data_direction dir;
-	int ret;
 
-	/* This DMAC cannot handle if sg_len is not 1 */
-	WARN_ON(host->sg_len > 1);
+	if (!dma_map_sg(&host->pdev->dev, sg, host->sg_len,
+			mmc_get_dma_dir(data)))
+		goto force_pio;
 
 	/* This DMAC cannot handle if buffer is not 8-bytes alignment */
-	if (!IS_ALIGNED(sg->offset, 8))
+	if (!IS_ALIGNED(sg_dma_address(sg), 8)) {
+		dma_unmap_sg(&host->pdev->dev, sg, host->sg_len,
+			     mmc_get_dma_dir(data));
 		goto force_pio;
+	}
 
 	if (data->flags & MMC_DATA_READ) {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH1;
-		dir = DMA_FROM_DEVICE;
+		if (test_bit(SDHI_INTERNAL_DMAC_ONE_RX_ONLY, &global_flags) &&
+		    test_and_set_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags))
+			goto force_pio;
 	} else {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH0;
-		dir = DMA_TO_DEVICE;
 	}
 
-	ret = dma_map_sg(&host->pdev->dev, sg, host->sg_len, dir);
-	if (ret == 0)
-		goto force_pio;
-
 	renesas_sdhi_internal_dmac_enable_dma(host, true);
 
 	/* set dma parameters */
 	renesas_sdhi_internal_dmac_dm_write(host, DM_CM_DTRAN_MODE,
 					    dtran_mode);
 	renesas_sdhi_internal_dmac_dm_write(host, DM_DTRAN_ADDR,
-					    sg->dma_address);
+					    sg_dma_address(sg));
 
 	return;
 
@@ -208,6 +223,9 @@ static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg)
 	renesas_sdhi_internal_dmac_enable_dma(host, false);
 	dma_unmap_sg(&host->pdev->dev, host->sg_ptr, host->sg_len, dir);
 
+	if (dir == DMA_FROM_DEVICE)
+		clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+
 	tmio_mmc_do_data_irq(host);
 out:
 	spin_unlock_irq(&host->lock);
@@ -251,18 +269,29 @@ static const struct tmio_mmc_dma_ops renesas_sdhi_internal_dmac_dma_ops = {
  * implementation as others may use a different implementation.
  */
 static const struct soc_device_attribute gen3_soc_whitelist[] = {
-        { .soc_id = "r8a7795", .revision = "ES1.*" },
-        { .soc_id = "r8a7795", .revision = "ES2.0" },
-        { .soc_id = "r8a7796", .revision = "ES1.0" },
-        { .soc_id = "r8a77995", .revision = "ES1.0" },
-        { /* sentinel */ }
+	/* specific ones */
+	{ .soc_id = "r8a7795", .revision = "ES1.*",
+	  .data = (void *)BIT(SDHI_INTERNAL_DMAC_ONE_RX_ONLY) },
+	{ .soc_id = "r8a7796", .revision = "ES1.0",
+	  .data = (void *)BIT(SDHI_INTERNAL_DMAC_ONE_RX_ONLY) },
+	/* generic ones */
+	{ .soc_id = "r8a7795" },
+	{ .soc_id = "r8a7796" },
+	{ .soc_id = "r8a77965" },
+	{ .soc_id = "r8a77980" },
+	{ .soc_id = "r8a77995" },
+	{ /* sentinel */ }
 };
 
 static int renesas_sdhi_internal_dmac_probe(struct platform_device *pdev)
 {
-	if (!soc_device_match(gen3_soc_whitelist))
+	const struct soc_device_attribute *soc = soc_device_match(gen3_soc_whitelist);
+
+	if (!soc)
 		return -ENODEV;
 
+	global_flags |= (unsigned long)soc->data;
+
 	return renesas_sdhi_probe(pdev, &renesas_sdhi_internal_dmac_dma_ops);
 }
 
diff --git a/drivers/mmc/host/renesas_sdhi_sys_dmac.c b/drivers/mmc/host/renesas_sdhi_sys_dmac.c
index 848e50c1638a..4bb46c489d71 100644
--- a/drivers/mmc/host/renesas_sdhi_sys_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_sys_dmac.c
@@ -42,6 +42,7 @@ static const struct renesas_sdhi_of_data of_rz_compatible = {
 static const struct renesas_sdhi_of_data of_rcar_gen1_compatible = {
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_CLK_ACTUAL,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ,
+	.capabilities2	= MMC_CAP2_NO_WRITE_PROTECT,
 };
 
 /* Definitions for sampling clocks */
@@ -61,6 +62,7 @@ static const struct renesas_sdhi_of_data of_rcar_gen2_compatible = {
 			  TMIO_MMC_HAVE_CBSY | TMIO_MMC_MIN_RCAR2,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_CMD23,
+	.capabilities2	= MMC_CAP2_NO_WRITE_PROTECT,
 	.dma_buswidth	= DMA_SLAVE_BUSWIDTH_4_BYTES,
 	.dma_rx_offset	= 0x2000,
 	.scc_offset	= 0x0300,
@@ -81,6 +83,7 @@ static const struct renesas_sdhi_of_data of_rcar_gen3_compatible = {
 			  TMIO_MMC_HAVE_CBSY | TMIO_MMC_MIN_RCAR2,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_CMD23,
+	.capabilities2	= MMC_CAP2_NO_WRITE_PROTECT,
 	.bus_shift	= 2,
 	.scc_offset	= 0x1000,
 	.taps		= rcar_gen3_scc_taps,
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 78422079ecfa..9a3ff22dd0fe 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -26,7 +26,6 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
 #include <linux/mmc/sd.h>
-#include <linux/mmc/sdio.h>
 #include <linux/mmc/card.h>
 #include <linux/scatterlist.h>
 #include <linux/pm_runtime.h>
@@ -343,7 +342,7 @@ static void sd_send_cmd_get_rsp(struct rtsx_usb_sdmmc *host,
 	}
 
 	if (rsp_type == SD_RSP_TYPE_R1b)
-		timeout = 3000;
+		timeout = cmd->busy_timeout ? cmd->busy_timeout : 3000;
 
 	if (cmd->opcode == SD_SWITCH_VOLTAGE) {
 		err = rtsx_usb_write_register(ucr, SD_BUS_STAT,
@@ -839,17 +838,6 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		goto finish_detect_card;
 	}
 
-	/*
-	 * Reject SDIO CMDs to speed up card identification
-	 * since unsupported
-	 */
-	if (cmd->opcode == SD_IO_SEND_OP_COND ||
-	    cmd->opcode == SD_IO_RW_DIRECT ||
-	    cmd->opcode == SD_IO_RW_EXTENDED) {
-		cmd->error = -EINVAL;
-		goto finish;
-	}
-
 	mutex_lock(&ucr->dev_mutex);
 
 	mutex_lock(&host->host_mutex);
@@ -1332,8 +1320,9 @@ static void rtsx_usb_init_host(struct rtsx_usb_sdmmc *host)
 	mmc->caps = MMC_CAP_4_BIT_DATA | MMC_CAP_SD_HIGHSPEED |
 		MMC_CAP_MMC_HIGHSPEED | MMC_CAP_BUS_WIDTH_TEST |
 		MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | MMC_CAP_UHS_SDR50 |
-		MMC_CAP_NEEDS_POLL;
-	mmc->caps2 = MMC_CAP2_NO_PRESCAN_POWERUP | MMC_CAP2_FULL_PWR_CYCLE;
+		MMC_CAP_NEEDS_POLL | MMC_CAP_ERASE;
+	mmc->caps2 = MMC_CAP2_NO_PRESCAN_POWERUP | MMC_CAP2_FULL_PWR_CYCLE |
+		MMC_CAP2_NO_SDIO;
 
 	mmc->max_current_330 = 400;
 	mmc->max_current_180 = 800;
diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c
index 11ca95c60bcf..bdbd4897c0f7 100644
--- a/drivers/mmc/host/sdhci-bcm-kona.c
+++ b/drivers/mmc/host/sdhci-bcm-kona.c
@@ -284,10 +284,8 @@ static int sdhci_bcm_kona_probe(struct platform_device *pdev)
 	sdhci_bcm_kona_sd_init(host);
 
 	ret = sdhci_add_host(host);
-	if (ret) {
-		dev_err(dev, "Failed sdhci_add_host\n");
+	if (ret)
 		goto err_reset;
-	}
 
 	/* if device is eMMC, emulate card insert right here */
 	if (!mmc_card_is_removable(host->mmc)) {
diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c
index 0f589e26ee63..7a343b87b5e5 100644
--- a/drivers/mmc/host/sdhci-cadence.c
+++ b/drivers/mmc/host/sdhci-cadence.c
@@ -253,6 +253,7 @@ static int sdhci_cdns_set_tune_val(struct sdhci_host *host, unsigned int val)
 	struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host);
 	void __iomem *reg = priv->hrs_addr + SDHCI_CDNS_HRS06;
 	u32 tmp;
+	int i, ret;
 
 	if (WARN_ON(!FIELD_FIT(SDHCI_CDNS_HRS06_TUNE, val)))
 		return -EINVAL;
@@ -260,11 +261,24 @@ static int sdhci_cdns_set_tune_val(struct sdhci_host *host, unsigned int val)
 	tmp = readl(reg);
 	tmp &= ~SDHCI_CDNS_HRS06_TUNE;
 	tmp |= FIELD_PREP(SDHCI_CDNS_HRS06_TUNE, val);
-	tmp |= SDHCI_CDNS_HRS06_TUNE_UP;
-	writel(tmp, reg);
 
-	return readl_poll_timeout(reg, tmp, !(tmp & SDHCI_CDNS_HRS06_TUNE_UP),
-				  0, 1);
+	/*
+	 * Workaround for IP errata:
+	 * The IP6116 SD/eMMC PHY design has a timing issue on receive data
+	 * path. Send tune request twice.
+	 */
+	for (i = 0; i < 2; i++) {
+		tmp |= SDHCI_CDNS_HRS06_TUNE_UP;
+		writel(tmp, reg);
+
+		ret = readl_poll_timeout(reg, tmp,
+					 !(tmp & SDHCI_CDNS_HRS06_TUNE_UP),
+					 0, 1);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static int sdhci_cdns_execute_tuning(struct mmc_host *mmc, u32 opcode)
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index cd2b5f643a15..d6aef70d34fa 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -41,6 +41,12 @@
 #define  ESDHC_VENDOR_SPEC_FRC_SDCLK_ON	(1 << 8)
 #define ESDHC_WTMK_LVL			0x44
 #define  ESDHC_WTMK_DEFAULT_VAL		0x10401040
+#define  ESDHC_WTMK_LVL_RD_WML_MASK	0x000000FF
+#define  ESDHC_WTMK_LVL_RD_WML_SHIFT	0
+#define  ESDHC_WTMK_LVL_WR_WML_MASK	0x00FF0000
+#define  ESDHC_WTMK_LVL_WR_WML_SHIFT	16
+#define  ESDHC_WTMK_LVL_WML_VAL_DEF	64
+#define  ESDHC_WTMK_LVL_WML_VAL_MAX	128
 #define ESDHC_MIX_CTRL			0x48
 #define  ESDHC_MIX_CTRL_DDREN		(1 << 3)
 #define  ESDHC_MIX_CTRL_AC23EN		(1 << 7)
@@ -516,6 +522,7 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg)
 		}
 
 		if (esdhc_is_usdhc(imx_data)) {
+			u32 wml;
 			u32 m = readl(host->ioaddr + ESDHC_MIX_CTRL);
 			/* Swap AC23 bit */
 			if (val & SDHCI_TRNS_AUTO_CMD23) {
@@ -524,6 +531,21 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg)
 			}
 			m = val | (m & ~ESDHC_MIX_CTRL_SDHCI_MASK);
 			writel(m, host->ioaddr + ESDHC_MIX_CTRL);
+
+			/* Set watermark levels for PIO access to maximum value
+			 * (128 words) to accommodate full 512 bytes buffer.
+			 * For DMA access restore the levels to default value.
+			 */
+			m = readl(host->ioaddr + ESDHC_WTMK_LVL);
+			if (val & SDHCI_TRNS_DMA)
+				wml = ESDHC_WTMK_LVL_WML_VAL_DEF;
+			else
+				wml = ESDHC_WTMK_LVL_WML_VAL_MAX;
+			m &= ~(ESDHC_WTMK_LVL_RD_WML_MASK |
+			       ESDHC_WTMK_LVL_WR_WML_MASK);
+			m |= (wml << ESDHC_WTMK_LVL_RD_WML_SHIFT) |
+			     (wml << ESDHC_WTMK_LVL_WR_WML_SHIFT);
+			writel(m, host->ioaddr + ESDHC_WTMK_LVL);
 		} else {
 			/*
 			 * Postpone this write, we must do it together with a
diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c
index 0ef741bc515d..d0e83db42ae5 100644
--- a/drivers/mmc/host/sdhci-iproc.c
+++ b/drivers/mmc/host/sdhci-iproc.c
@@ -33,6 +33,8 @@ struct sdhci_iproc_host {
 	const struct sdhci_iproc_data *data;
 	u32 shadow_cmd;
 	u32 shadow_blk;
+	bool is_cmd_shadowed;
+	bool is_blk_shadowed;
 };
 
 #define REG_OFFSET_IN_BITS(reg) ((reg) << 3 & 0x18)
@@ -48,8 +50,22 @@ static inline u32 sdhci_iproc_readl(struct sdhci_host *host, int reg)
 
 static u16 sdhci_iproc_readw(struct sdhci_host *host, int reg)
 {
-	u32 val = sdhci_iproc_readl(host, (reg & ~3));
-	u16 word = val >> REG_OFFSET_IN_BITS(reg) & 0xffff;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_iproc_host *iproc_host = sdhci_pltfm_priv(pltfm_host);
+	u32 val;
+	u16 word;
+
+	if ((reg == SDHCI_TRANSFER_MODE) && iproc_host->is_cmd_shadowed) {
+		/* Get the saved transfer mode */
+		val = iproc_host->shadow_cmd;
+	} else if ((reg == SDHCI_BLOCK_SIZE || reg == SDHCI_BLOCK_COUNT) &&
+		   iproc_host->is_blk_shadowed) {
+		/* Get the saved block info */
+		val = iproc_host->shadow_blk;
+	} else {
+		val = sdhci_iproc_readl(host, (reg & ~3));
+	}
+	word = val >> REG_OFFSET_IN_BITS(reg) & 0xffff;
 	return word;
 }
 
@@ -105,13 +121,15 @@ static void sdhci_iproc_writew(struct sdhci_host *host, u16 val, int reg)
 
 	if (reg == SDHCI_COMMAND) {
 		/* Write the block now as we are issuing a command */
-		if (iproc_host->shadow_blk != 0) {
+		if (iproc_host->is_blk_shadowed) {
 			sdhci_iproc_writel(host, iproc_host->shadow_blk,
 				SDHCI_BLOCK_SIZE);
-			iproc_host->shadow_blk = 0;
+			iproc_host->is_blk_shadowed = false;
 		}
 		oldval = iproc_host->shadow_cmd;
-	} else if (reg == SDHCI_BLOCK_SIZE || reg == SDHCI_BLOCK_COUNT) {
+		iproc_host->is_cmd_shadowed = false;
+	} else if ((reg == SDHCI_BLOCK_SIZE || reg == SDHCI_BLOCK_COUNT) &&
+		   iproc_host->is_blk_shadowed) {
 		/* Block size and count are stored in shadow reg */
 		oldval = iproc_host->shadow_blk;
 	} else {
@@ -123,9 +141,11 @@ static void sdhci_iproc_writew(struct sdhci_host *host, u16 val, int reg)
 	if (reg == SDHCI_TRANSFER_MODE) {
 		/* Save the transfer mode until the command is issued */
 		iproc_host->shadow_cmd = newval;
+		iproc_host->is_cmd_shadowed = true;
 	} else if (reg == SDHCI_BLOCK_SIZE || reg == SDHCI_BLOCK_COUNT) {
 		/* Save the block info until the command is issued */
 		iproc_host->shadow_blk = newval;
+		iproc_host->is_blk_shadowed = true;
 	} else {
 		/* Command or other regular 32-bit write */
 		sdhci_iproc_writel(host, newval, reg & ~3);
@@ -166,7 +186,7 @@ static const struct sdhci_ops sdhci_iproc_32only_ops = {
 
 static const struct sdhci_pltfm_data sdhci_iproc_cygnus_pltfm_data = {
 	.quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK,
-	.quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN | SDHCI_QUIRK2_HOST_OFF_CARD_ON,
 	.ops = &sdhci_iproc_32only_ops,
 };
 
@@ -206,7 +226,6 @@ static const struct sdhci_iproc_data iproc_data = {
 	.caps1 = SDHCI_DRIVER_TYPE_C |
 		 SDHCI_DRIVER_TYPE_D |
 		 SDHCI_SUPPORT_DDR50,
-	.mmc_caps = MMC_CAP_1_8V_DDR,
 };
 
 static const struct sdhci_pltfm_data sdhci_bcm2835_pltfm_data = {
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index c283291db705..646bf377ba77 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -21,6 +21,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/iopoll.h>
+#include <linux/regulator/consumer.h>
 
 #include "sdhci-pltfm.h"
 
@@ -77,10 +78,16 @@
 #define CORE_HC_MCLK_SEL_DFLT	(2 << 8)
 #define CORE_HC_MCLK_SEL_HS400	(3 << 8)
 #define CORE_HC_MCLK_SEL_MASK	(3 << 8)
+#define CORE_IO_PAD_PWR_SWITCH_EN	(1 << 15)
+#define CORE_IO_PAD_PWR_SWITCH  (1 << 16)
 #define CORE_HC_SELECT_IN_EN	BIT(18)
 #define CORE_HC_SELECT_IN_HS400	(6 << 19)
 #define CORE_HC_SELECT_IN_MASK	(7 << 19)
 
+#define CORE_3_0V_SUPPORT	(1 << 25)
+#define CORE_1_8V_SUPPORT	(1 << 26)
+#define CORE_VOLT_SUPPORT	(CORE_3_0V_SUPPORT | CORE_1_8V_SUPPORT)
+
 #define CORE_CSR_CDC_CTLR_CFG0		0x130
 #define CORE_SW_TRIG_FULL_CALIB		BIT(16)
 #define CORE_HW_AUTOCAL_ENA		BIT(17)
@@ -148,6 +155,7 @@ struct sdhci_msm_host {
 	u32 curr_io_level;
 	wait_queue_head_t pwr_irq_wait;
 	bool pwr_irq_flag;
+	u32 caps_0;
 };
 
 static unsigned int msm_get_clock_rate_for_bus_mode(struct sdhci_host *host,
@@ -1103,8 +1111,8 @@ static void sdhci_msm_handle_pwr_irq(struct sdhci_host *host, int irq)
 	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
 	u32 irq_status, irq_ack = 0;
 	int retry = 10;
-	int pwr_state = 0, io_level = 0;
-
+	u32 pwr_state = 0, io_level = 0;
+	u32 config;
 
 	irq_status = readl_relaxed(msm_host->core_mem + CORE_PWRCTL_STATUS);
 	irq_status &= INT_MASK;
@@ -1161,6 +1169,38 @@ static void sdhci_msm_handle_pwr_irq(struct sdhci_host *host, int irq)
 	 */
 	writel_relaxed(irq_ack, msm_host->core_mem + CORE_PWRCTL_CTL);
 
+	/*
+	 * If we don't have info regarding the voltage levels supported by
+	 * regulators, don't change the IO PAD PWR SWITCH.
+	 */
+	if (msm_host->caps_0 & CORE_VOLT_SUPPORT) {
+		u32 new_config;
+		/*
+		 * We should unset IO PAD PWR switch only if the register write
+		 * can set IO lines high and the regulator also switches to 3 V.
+		 * Else, we should keep the IO PAD PWR switch set.
+		 * This is applicable to certain targets where eMMC vccq supply
+		 * is only 1.8V. In such targets, even during REQ_IO_HIGH, the
+		 * IO PAD PWR switch must be kept set to reflect actual
+		 * regulator voltage. This way, during initialization of
+		 * controllers with only 1.8V, we will set the IO PAD bit
+		 * without waiting for a REQ_IO_LOW.
+		 */
+		config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
+		new_config = config;
+
+		if ((io_level & REQ_IO_HIGH) &&
+				(msm_host->caps_0 & CORE_3_0V_SUPPORT))
+			new_config &= ~CORE_IO_PAD_PWR_SWITCH;
+		else if ((io_level & REQ_IO_LOW) ||
+				(msm_host->caps_0 & CORE_1_8V_SUPPORT))
+			new_config |= CORE_IO_PAD_PWR_SWITCH;
+
+		if (config ^ new_config)
+			writel_relaxed(new_config,
+					host->ioaddr + CORE_VENDOR_SPEC);
+	}
+
 	if (pwr_state)
 		msm_host->curr_pwr_state = pwr_state;
 	if (io_level)
@@ -1313,6 +1353,45 @@ static void sdhci_msm_writeb(struct sdhci_host *host, u8 val, int reg)
 		sdhci_msm_check_power_status(host, req_type);
 }
 
+static void sdhci_msm_set_regulator_caps(struct sdhci_msm_host *msm_host)
+{
+	struct mmc_host *mmc = msm_host->mmc;
+	struct regulator *supply = mmc->supply.vqmmc;
+	u32 caps = 0, config;
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+		if (regulator_is_supported_voltage(supply, 1700000, 1950000))
+			caps |= CORE_1_8V_SUPPORT;
+		if (regulator_is_supported_voltage(supply, 2700000, 3600000))
+			caps |= CORE_3_0V_SUPPORT;
+
+		if (!caps)
+			pr_warn("%s: 1.8/3V not supported for vqmmc\n",
+					mmc_hostname(mmc));
+	}
+
+	if (caps) {
+		/*
+		 * Set the PAD_PWR_SWITCH_EN bit so that the PAD_PWR_SWITCH
+		 * bit can be used as required later on.
+		 */
+		u32 io_level = msm_host->curr_io_level;
+
+		config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
+		config |= CORE_IO_PAD_PWR_SWITCH_EN;
+
+		if ((io_level & REQ_IO_HIGH) && (caps &	CORE_3_0V_SUPPORT))
+			config &= ~CORE_IO_PAD_PWR_SWITCH;
+		else if ((io_level & REQ_IO_LOW) || (caps & CORE_1_8V_SUPPORT))
+			config |= CORE_IO_PAD_PWR_SWITCH;
+
+		writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
+	}
+	msm_host->caps_0 |= caps;
+	pr_debug("%s: supported caps: 0x%08x\n", mmc_hostname(mmc), caps);
+}
+
 static const struct of_device_id sdhci_msm_dt_match[] = {
 	{ .compatible = "qcom,sdhci-msm-v4" },
 	{},
@@ -1333,7 +1412,6 @@ static const struct sdhci_ops sdhci_msm_ops = {
 
 static const struct sdhci_pltfm_data sdhci_msm_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_CARD_DETECTION |
-		  SDHCI_QUIRK_NO_CARD_NO_RESET |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
 		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
@@ -1530,6 +1608,7 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 	ret = sdhci_add_host(host);
 	if (ret)
 		goto pm_runtime_disable;
+	sdhci_msm_set_regulator_caps(msm_host);
 
 	pm_runtime_mark_last_busy(&pdev->dev);
 	pm_runtime_put_autosuspend(&pdev->dev);
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index c33a5f7393bd..e3332a522a5d 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -290,7 +290,8 @@ static const struct sdhci_pltfm_data sdhci_arasan_pdata = {
 	.ops = &sdhci_arasan_ops,
 	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
-			SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN,
+			SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN |
+			SDHCI_QUIRK2_STOP_WITH_TC,
 };
 
 static u32 sdhci_arasan_cqhci_irq(struct sdhci_host *host, u32 intmask)
@@ -359,8 +360,7 @@ static const struct sdhci_pltfm_data sdhci_arasan_cqe_pdata = {
  */
 static int sdhci_arasan_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct sdhci_host *host = platform_get_drvdata(pdev);
+	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
 	int ret;
@@ -403,8 +403,7 @@ static int sdhci_arasan_suspend(struct device *dev)
  */
 static int sdhci_arasan_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct sdhci_host *host = platform_get_drvdata(pdev);
+	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
 	int ret;
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index 1456abd5eeb9..f3a7c8ece4be 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -26,6 +26,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/sys_soc.h>
 
 #include "sdhci-pltfm.h"
 
@@ -35,6 +36,7 @@
 #define CON_DDR			BIT(19)
 #define CON_CLKEXTFREE		BIT(16)
 #define CON_PADEN		BIT(15)
+#define CON_CTPL		BIT(11)
 #define CON_INIT		BIT(1)
 #define CON_OD			BIT(0)
 
@@ -100,6 +102,7 @@ struct sdhci_omap_data {
 };
 
 struct sdhci_omap_host {
+	char			*version;
 	void __iomem		*base;
 	struct device		*dev;
 	struct	regulator	*pbias;
@@ -224,6 +227,23 @@ static void sdhci_omap_conf_bus_power(struct sdhci_omap_host *omap_host,
 	}
 }
 
+static void sdhci_omap_enable_sdio_irq(struct mmc_host *mmc, int enable)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host);
+	u32 reg;
+
+	reg = sdhci_omap_readl(omap_host, SDHCI_OMAP_CON);
+	if (enable)
+		reg |= (CON_CTPL | CON_CLKEXTFREE);
+	else
+		reg &= ~(CON_CTPL | CON_CLKEXTFREE);
+	sdhci_omap_writel(omap_host, SDHCI_OMAP_CON, reg);
+
+	sdhci_enable_sdio_irq(mmc, enable);
+}
+
 static inline void sdhci_omap_set_dll(struct sdhci_omap_host *omap_host,
 				      int count)
 {
@@ -713,10 +733,15 @@ static const struct sdhci_pltfm_data sdhci_omap_pdata = {
 		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC,
 	.quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN |
 		   SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
-		   SDHCI_QUIRK2_RSP_136_HAS_CRC,
+		   SDHCI_QUIRK2_RSP_136_HAS_CRC |
+		   SDHCI_QUIRK2_DISABLE_HW_TIMEOUT,
 	.ops = &sdhci_omap_ops,
 };
 
+static const struct sdhci_omap_data k2g_data = {
+	.offset = 0x200,
+};
+
 static const struct sdhci_omap_data dra7_data = {
 	.offset = 0x200,
 	.flags	= SDHCI_OMAP_REQUIRE_IODELAY,
@@ -724,6 +749,7 @@ static const struct sdhci_omap_data dra7_data = {
 
 static const struct of_device_id omap_sdhci_match[] = {
 	{ .compatible = "ti,dra7-sdhci", .data = &dra7_data },
+	{ .compatible = "ti,k2g-sdhci", .data = &k2g_data },
 	{},
 };
 MODULE_DEVICE_TABLE(of, omap_sdhci_match);
@@ -733,12 +759,21 @@ static struct pinctrl_state
 				  u32 *caps, u32 capmask)
 {
 	struct device *dev = omap_host->dev;
+	char *version = omap_host->version;
 	struct pinctrl_state *pinctrl_state = ERR_PTR(-ENODEV);
+	char str[20];
 
 	if (!(*caps & capmask))
 		goto ret;
 
-	pinctrl_state = pinctrl_lookup_state(omap_host->pinctrl, mode);
+	if (version) {
+		snprintf(str, 20, "%s-%s", mode, version);
+		pinctrl_state = pinctrl_lookup_state(omap_host->pinctrl, str);
+	}
+
+	if (IS_ERR(pinctrl_state))
+		pinctrl_state = pinctrl_lookup_state(omap_host->pinctrl, mode);
+
 	if (IS_ERR(pinctrl_state)) {
 		dev_err(dev, "no pinctrl state for %s mode", mode);
 		*caps &= ~capmask;
@@ -807,8 +842,15 @@ static int sdhci_omap_config_iodelay_pinctrl_state(struct sdhci_omap_host
 
 	state = sdhci_omap_iodelay_pinctrl_state(omap_host, "ddr_1_8v", caps,
 						 MMC_CAP_1_8V_DDR);
-	if (!IS_ERR(state))
+	if (!IS_ERR(state)) {
 		pinctrl_state[MMC_TIMING_MMC_DDR52] = state;
+	} else {
+		state = sdhci_omap_iodelay_pinctrl_state(omap_host, "ddr_3_3v",
+							 caps,
+							 MMC_CAP_3_3V_DDR);
+		if (!IS_ERR(state))
+			pinctrl_state[MMC_TIMING_MMC_DDR52] = state;
+	}
 
 	state = sdhci_omap_iodelay_pinctrl_state(omap_host, "hs", caps,
 						 MMC_CAP_SD_HIGHSPEED);
@@ -830,6 +872,16 @@ static int sdhci_omap_config_iodelay_pinctrl_state(struct sdhci_omap_host
 	return 0;
 }
 
+static const struct soc_device_attribute sdhci_omap_soc_devices[] = {
+	{
+		.machine = "DRA7[45]*",
+		.revision = "ES1.[01]",
+	},
+	{
+		/* sentinel */
+	}
+};
+
 static int sdhci_omap_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -841,6 +893,7 @@ static int sdhci_omap_probe(struct platform_device *pdev)
 	struct mmc_host *mmc;
 	const struct of_device_id *match;
 	struct sdhci_omap_data *data;
+	const struct soc_device_attribute *soc;
 
 	match = of_match_device(omap_sdhci_match, dev);
 	if (!match)
@@ -871,10 +924,22 @@ static int sdhci_omap_probe(struct platform_device *pdev)
 	host->ioaddr += offset;
 
 	mmc = host->mmc;
+	sdhci_get_of_property(pdev);
 	ret = mmc_of_parse(mmc);
 	if (ret)
 		goto err_pltfm_free;
 
+	soc = soc_device_match(sdhci_omap_soc_devices);
+	if (soc) {
+		omap_host->version = "rev11";
+		if (!strcmp(dev_name(dev), "4809c000.mmc"))
+			mmc->f_max = 96000000;
+		if (!strcmp(dev_name(dev), "480b4000.mmc"))
+			mmc->f_max = 48000000;
+		if (!strcmp(dev_name(dev), "480ad000.mmc"))
+			mmc->f_max = 48000000;
+	}
+
 	pltfm_host->clk = devm_clk_get(dev, "fck");
 	if (IS_ERR(pltfm_host->clk)) {
 		ret = PTR_ERR(pltfm_host->clk);
@@ -916,26 +981,31 @@ static int sdhci_omap_probe(struct platform_device *pdev)
 		goto err_put_sync;
 	}
 
-	ret = sdhci_omap_config_iodelay_pinctrl_state(omap_host);
-	if (ret)
-		goto err_put_sync;
-
 	host->mmc_host_ops.get_ro = mmc_gpio_get_ro;
 	host->mmc_host_ops.start_signal_voltage_switch =
 					sdhci_omap_start_signal_voltage_switch;
 	host->mmc_host_ops.set_ios = sdhci_omap_set_ios;
 	host->mmc_host_ops.card_busy = sdhci_omap_card_busy;
 	host->mmc_host_ops.execute_tuning = sdhci_omap_execute_tuning;
+	host->mmc_host_ops.enable_sdio_irq = sdhci_omap_enable_sdio_irq;
 
-	sdhci_read_caps(host);
-	host->caps |= SDHCI_CAN_DO_ADMA2;
-
-	ret = sdhci_add_host(host);
+	ret = sdhci_setup_host(host);
 	if (ret)
 		goto err_put_sync;
 
+	ret = sdhci_omap_config_iodelay_pinctrl_state(omap_host);
+	if (ret)
+		goto err_cleanup_host;
+
+	ret = __sdhci_add_host(host);
+	if (ret)
+		goto err_cleanup_host;
+
 	return 0;
 
+err_cleanup_host:
+	sdhci_cleanup_host(host);
+
 err_put_sync:
 	pm_runtime_put_sync(dev);
 
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 787434e5589d..77dd3521daae 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -453,6 +453,7 @@ static const struct sdhci_pci_fixes sdhci_intel_pch_sdio = {
 enum {
 	INTEL_DSM_FNS		=  0,
 	INTEL_DSM_V18_SWITCH	=  3,
+	INTEL_DSM_V33_SWITCH	=  4,
 	INTEL_DSM_DRV_STRENGTH	=  9,
 	INTEL_DSM_D3_RETUNE	= 10,
 };
@@ -620,17 +621,37 @@ static void intel_hs400_enhanced_strobe(struct mmc_host *mmc,
 	sdhci_writel(host, val, INTEL_HS400_ES_REG);
 }
 
-static void sdhci_intel_voltage_switch(struct sdhci_host *host)
+static int intel_start_signal_voltage_switch(struct mmc_host *mmc,
+					     struct mmc_ios *ios)
 {
+	struct device *dev = mmc_dev(mmc);
+	struct sdhci_host *host = mmc_priv(mmc);
 	struct sdhci_pci_slot *slot = sdhci_priv(host);
 	struct intel_host *intel_host = sdhci_pci_priv(slot);
-	struct device *dev = &slot->chip->pdev->dev;
+	unsigned int fn;
 	u32 result = 0;
 	int err;
 
-	err = intel_dsm(intel_host, dev, INTEL_DSM_V18_SWITCH, &result);
-	pr_debug("%s: %s DSM error %d result %u\n",
-		 mmc_hostname(host->mmc), __func__, err, result);
+	err = sdhci_start_signal_voltage_switch(mmc, ios);
+	if (err)
+		return err;
+
+	switch (ios->signal_voltage) {
+	case MMC_SIGNAL_VOLTAGE_330:
+		fn = INTEL_DSM_V33_SWITCH;
+		break;
+	case MMC_SIGNAL_VOLTAGE_180:
+		fn = INTEL_DSM_V18_SWITCH;
+		break;
+	default:
+		return 0;
+	}
+
+	err = intel_dsm(intel_host, dev, fn, &result);
+	pr_debug("%s: %s DSM fn %u error %d result %u\n",
+		 mmc_hostname(mmc), __func__, fn, err, result);
+
+	return 0;
 }
 
 static const struct sdhci_ops sdhci_intel_byt_ops = {
@@ -641,7 +662,6 @@ static const struct sdhci_ops sdhci_intel_byt_ops = {
 	.reset			= sdhci_reset,
 	.set_uhs_signaling	= sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
-	.voltage_switch		= sdhci_intel_voltage_switch,
 };
 
 static const struct sdhci_ops sdhci_intel_glk_ops = {
@@ -652,7 +672,6 @@ static const struct sdhci_ops sdhci_intel_glk_ops = {
 	.reset			= sdhci_reset,
 	.set_uhs_signaling	= sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
-	.voltage_switch		= sdhci_intel_voltage_switch,
 	.irq			= sdhci_cqhci_irq,
 };
 
@@ -691,6 +710,7 @@ static void byt_probe_slot(struct sdhci_pci_slot *slot)
 	byt_read_dsm(slot);
 
 	ops->execute_tuning = intel_execute_tuning;
+	ops->start_signal_voltage_switch = intel_start_signal_voltage_switch;
 }
 
 static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
@@ -832,6 +852,10 @@ static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
 	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_SD)
 		slot->host->mmc_host_ops.get_cd = bxt_get_cd;
 
+	if (slot->chip->pdev->subsystem_vendor == PCI_VENDOR_ID_NI &&
+	    slot->chip->pdev->subsystem_device == PCI_SUBDEVICE_ID_NI_78E3)
+		slot->host->mmc->caps2 |= MMC_CAP2_AVOID_3_3V;
+
 	return 0;
 }
 
@@ -1312,7 +1336,7 @@ static void amd_enable_manual_tuning(struct pci_dev *pdev)
 	pci_write_config_dword(pdev, AMD_SD_MISC_CONTROL, val);
 }
 
-static int amd_execute_tuning(struct sdhci_host *host, u32 opcode)
+static int amd_execute_tuning_hs200(struct sdhci_host *host, u32 opcode)
 {
 	struct sdhci_pci_slot *slot = sdhci_priv(host);
 	struct pci_dev *pdev = slot->chip->pdev;
@@ -1351,6 +1375,27 @@ static int amd_execute_tuning(struct sdhci_host *host, u32 opcode)
 	return 0;
 }
 
+static int amd_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	/* AMD requires custom HS200 tuning */
+	if (host->timing == MMC_TIMING_MMC_HS200)
+		return amd_execute_tuning_hs200(host, opcode);
+
+	/* Otherwise perform standard SDHCI tuning */
+	return sdhci_execute_tuning(mmc, opcode);
+}
+
+static int amd_probe_slot(struct sdhci_pci_slot *slot)
+{
+	struct mmc_host_ops *ops = &slot->host->mmc_host_ops;
+
+	ops->execute_tuning = amd_execute_tuning;
+
+	return 0;
+}
+
 static int amd_probe(struct sdhci_pci_chip *chip)
 {
 	struct pci_dev	*smbus_dev;
@@ -1385,12 +1430,12 @@ static const struct sdhci_ops amd_sdhci_pci_ops = {
 	.set_bus_width			= sdhci_set_bus_width,
 	.reset				= sdhci_reset,
 	.set_uhs_signaling		= sdhci_set_uhs_signaling,
-	.platform_execute_tuning	= amd_execute_tuning,
 };
 
 static const struct sdhci_pci_fixes sdhci_amd = {
 	.probe		= amd_probe,
 	.ops		= &amd_sdhci_pci_ops,
+	.probe_slot	= amd_probe_slot,
 };
 
 static const struct pci_device_id pci_ids[] = {
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 5cbcdc448f98..db9cb54ef700 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -54,6 +54,7 @@
 #define PCI_DEVICE_ID_REALTEK_5250	0x5250
 
 #define PCI_SUBDEVICE_ID_NI_7884	0x7884
+#define PCI_SUBDEVICE_ID_NI_78E3	0x78e3
 
 #define PCI_VENDOR_ID_ARASAN		0x16e6
 #define PCI_DEVICE_ID_ARASAN_PHY_EMMC	0x0670
diff --git a/drivers/mmc/host/sdhci-pic32.c b/drivers/mmc/host/sdhci-pic32.c
index a6caa49ca25a..a11e6397d4ff 100644
--- a/drivers/mmc/host/sdhci-pic32.c
+++ b/drivers/mmc/host/sdhci-pic32.c
@@ -200,10 +200,8 @@ static int pic32_sdhci_probe(struct platform_device *pdev)
 	}
 
 	ret = sdhci_add_host(host);
-	if (ret) {
-		dev_err(&pdev->dev, "error adding host\n");
+	if (ret)
 		goto err_base_clk;
-	}
 
 	dev_info(&pdev->dev, "Successfully added sdhci host\n");
 	return 0;
diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c
index 8986f9d9cf98..2c3827f54927 100644
--- a/drivers/mmc/host/sdhci-pxav2.c
+++ b/drivers/mmc/host/sdhci-pxav2.c
@@ -221,10 +221,8 @@ static int sdhci_pxav2_probe(struct platform_device *pdev)
 	host->ops = &pxav2_sdhci_ops;
 
 	ret = sdhci_add_host(host);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to add host\n");
+	if (ret)
 		goto disable_clk;
-	}
 
 	return 0;
 
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index a34434166ca7..b8e96f392428 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -472,10 +472,8 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 	pm_suspend_ignore_children(&pdev->dev, 1);
 
 	ret = sdhci_add_host(host);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to add host\n");
+	if (ret)
 		goto err_add_host;
-	}
 
 	if (host->mmc->pm_caps & MMC_PM_WAKE_SDIO_IRQ)
 		device_init_wakeup(&pdev->dev, 1);
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index cda83ccb2702..9ef89d00970e 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -655,10 +655,8 @@ static int sdhci_s3c_probe(struct platform_device *pdev)
 		goto err_req_regs;
 
 	ret = sdhci_add_host(host);
-	if (ret) {
-		dev_err(dev, "sdhci_add_host() failed\n");
+	if (ret)
 		goto err_req_regs;
-	}
 
 #ifdef CONFIG_PM
 	if (pdata->cd_type != S3C_SDHCI_CD_INTERNAL)
diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c
index 14511526a3a8..9247d51f2eed 100644
--- a/drivers/mmc/host/sdhci-spear.c
+++ b/drivers/mmc/host/sdhci-spear.c
@@ -126,10 +126,8 @@ static int sdhci_probe(struct platform_device *pdev)
 	}
 
 	ret = sdhci_add_host(host);
-	if (ret) {
-		dev_dbg(&pdev->dev, "error adding host\n");
+	if (ret)
 		goto disable_clk;
-	}
 
 	platform_set_drvdata(pdev, host);
 
diff --git a/drivers/mmc/host/sdhci-st.c b/drivers/mmc/host/sdhci-st.c
index c32daed0d418..8f95647195d9 100644
--- a/drivers/mmc/host/sdhci-st.c
+++ b/drivers/mmc/host/sdhci-st.c
@@ -422,10 +422,8 @@ static int sdhci_st_probe(struct platform_device *pdev)
 	st_mmcss_cconfig(np, host);
 
 	ret = sdhci_add_host(host);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed sdhci_add_host\n");
+	if (ret)
 		goto err_out;
-	}
 
 	host_version = readw_relaxed((host->ioaddr + SDHCI_HOST_VERSION));
 
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index b877c13184c2..970d38f68939 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -231,7 +231,7 @@ static void tegra_sdhci_set_uhs_signaling(struct sdhci_host *host,
 	if (timing == MMC_TIMING_UHS_DDR50)
 		tegra_host->ddr_signaling = true;
 
-	return sdhci_set_uhs_signaling(host, timing);
+	sdhci_set_uhs_signaling(host, timing);
 }
 
 static unsigned int tegra_sdhci_get_max_clock(struct sdhci_host *host)
diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c
index ec8794335241..a35804b203a7 100644
--- a/drivers/mmc/host/sdhci-xenon-phy.c
+++ b/drivers/mmc/host/sdhci-xenon-phy.c
@@ -814,15 +814,10 @@ static int xenon_add_phy(struct device_node *np, struct sdhci_host *host,
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
-	int i, ret;
+	int ret;
 
-	for (i = 0; i < NR_PHY_TYPES; i++) {
-		if (!strcmp(phy_name, phy_types[i])) {
-			priv->phy_type = i;
-			break;
-		}
-	}
-	if (i == NR_PHY_TYPES) {
+	priv->phy_type = match_string(phy_types, NR_PHY_TYPES, phy_name);
+	if (priv->phy_type < 0) {
 		dev_err(mmc_dev(host->mmc),
 			"Unable to determine PHY name %s. Use default eMMC 5.1 PHY\n",
 			phy_name);
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 2ededa7f43df..1c828e0e9905 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -709,29 +709,16 @@ static u32 sdhci_sdma_address(struct sdhci_host *host)
 		return sg_dma_address(host->data->sg);
 }
 
-static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
+static unsigned int sdhci_target_timeout(struct sdhci_host *host,
+					 struct mmc_command *cmd,
+					 struct mmc_data *data)
 {
-	u8 count;
-	struct mmc_data *data = cmd->data;
-	unsigned target_timeout, current_timeout;
-
-	/*
-	 * If the host controller provides us with an incorrect timeout
-	 * value, just skip the check and use 0xE.  The hardware may take
-	 * longer to time out, but that's much better than having a too-short
-	 * timeout value.
-	 */
-	if (host->quirks & SDHCI_QUIRK_BROKEN_TIMEOUT_VAL)
-		return 0xE;
-
-	/* Unspecified timeout, assume max */
-	if (!data && !cmd->busy_timeout)
-		return 0xE;
+	unsigned int target_timeout;
 
 	/* timeout in us */
-	if (!data)
+	if (!data) {
 		target_timeout = cmd->busy_timeout * 1000;
-	else {
+	} else {
 		target_timeout = DIV_ROUND_UP(data->timeout_ns, 1000);
 		if (host->clock && data->timeout_clks) {
 			unsigned long long val;
@@ -748,6 +735,67 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 		}
 	}
 
+	return target_timeout;
+}
+
+static void sdhci_calc_sw_timeout(struct sdhci_host *host,
+				  struct mmc_command *cmd)
+{
+	struct mmc_data *data = cmd->data;
+	struct mmc_host *mmc = host->mmc;
+	struct mmc_ios *ios = &mmc->ios;
+	unsigned char bus_width = 1 << ios->bus_width;
+	unsigned int blksz;
+	unsigned int freq;
+	u64 target_timeout;
+	u64 transfer_time;
+
+	target_timeout = sdhci_target_timeout(host, cmd, data);
+	target_timeout *= NSEC_PER_USEC;
+
+	if (data) {
+		blksz = data->blksz;
+		freq = host->mmc->actual_clock ? : host->clock;
+		transfer_time = (u64)blksz * NSEC_PER_SEC * (8 / bus_width);
+		do_div(transfer_time, freq);
+		/* multiply by '2' to account for any unknowns */
+		transfer_time = transfer_time * 2;
+		/* calculate timeout for the entire data */
+		host->data_timeout = data->blocks * target_timeout +
+				     transfer_time;
+	} else {
+		host->data_timeout = target_timeout;
+	}
+
+	if (host->data_timeout)
+		host->data_timeout += MMC_CMD_TRANSFER_TIME;
+}
+
+static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd,
+			     bool *too_big)
+{
+	u8 count;
+	struct mmc_data *data = cmd->data;
+	unsigned target_timeout, current_timeout;
+
+	*too_big = true;
+
+	/*
+	 * If the host controller provides us with an incorrect timeout
+	 * value, just skip the check and use 0xE.  The hardware may take
+	 * longer to time out, but that's much better than having a too-short
+	 * timeout value.
+	 */
+	if (host->quirks & SDHCI_QUIRK_BROKEN_TIMEOUT_VAL)
+		return 0xE;
+
+	/* Unspecified timeout, assume max */
+	if (!data && !cmd->busy_timeout)
+		return 0xE;
+
+	/* timeout in us */
+	target_timeout = sdhci_target_timeout(host, cmd, data);
+
 	/*
 	 * Figure out needed cycles.
 	 * We do this in steps in order to fit inside a 32 bit int.
@@ -768,9 +816,12 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 	}
 
 	if (count >= 0xF) {
-		DBG("Too large timeout 0x%x requested for CMD%d!\n",
-		    count, cmd->opcode);
+		if (!(host->quirks2 & SDHCI_QUIRK2_DISABLE_HW_TIMEOUT))
+			DBG("Too large timeout 0x%x requested for CMD%d!\n",
+			    count, cmd->opcode);
 		count = 0xE;
+	} else {
+		*too_big = false;
 	}
 
 	return count;
@@ -790,6 +841,16 @@ static void sdhci_set_transfer_irqs(struct sdhci_host *host)
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
+static void sdhci_set_data_timeout_irq(struct sdhci_host *host, bool enable)
+{
+	if (enable)
+		host->ier |= SDHCI_INT_DATA_TIMEOUT;
+	else
+		host->ier &= ~SDHCI_INT_DATA_TIMEOUT;
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+}
+
 static void sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 {
 	u8 count;
@@ -797,7 +858,18 @@ static void sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 	if (host->ops->set_timeout) {
 		host->ops->set_timeout(host, cmd);
 	} else {
-		count = sdhci_calc_timeout(host, cmd);
+		bool too_big = false;
+
+		count = sdhci_calc_timeout(host, cmd, &too_big);
+
+		if (too_big &&
+		    host->quirks2 & SDHCI_QUIRK2_DISABLE_HW_TIMEOUT) {
+			sdhci_calc_sw_timeout(host, cmd);
+			sdhci_set_data_timeout_irq(host, false);
+		} else if (!(host->ier & SDHCI_INT_DATA_TIMEOUT)) {
+			sdhci_set_data_timeout_irq(host, true);
+		}
+
 		sdhci_writeb(host, count, SDHCI_TIMEOUT_CONTROL);
 	}
 }
@@ -807,6 +879,8 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 	u8 ctrl;
 	struct mmc_data *data = cmd->data;
 
+	host->data_timeout = 0;
+
 	if (sdhci_data_line_cmd(cmd))
 		sdhci_set_timeout(host, cmd);
 
@@ -1160,13 +1234,6 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 		mdelay(1);
 	}
 
-	timeout = jiffies;
-	if (!cmd->data && cmd->busy_timeout > 9000)
-		timeout += DIV_ROUND_UP(cmd->busy_timeout, 1000) * HZ + HZ;
-	else
-		timeout += 10 * HZ;
-	sdhci_mod_timer(host, cmd->mrq, timeout);
-
 	host->cmd = cmd;
 	if (sdhci_data_line_cmd(cmd)) {
 		WARN_ON(host->data_cmd);
@@ -1206,6 +1273,15 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 	    cmd->opcode == MMC_SEND_TUNING_BLOCK_HS200)
 		flags |= SDHCI_CMD_DATA;
 
+	timeout = jiffies;
+	if (host->data_timeout)
+		timeout += nsecs_to_jiffies(host->data_timeout);
+	else if (!cmd->data && cmd->busy_timeout > 9000)
+		timeout += DIV_ROUND_UP(cmd->busy_timeout, 1000) * HZ + HZ;
+	else
+		timeout += 10 * HZ;
+	sdhci_mod_timer(host, cmd->mrq, timeout);
+
 	sdhci_writew(host, SDHCI_MAKE_CMD(cmd->opcode, flags), SDHCI_COMMAND);
 }
 EXPORT_SYMBOL_GPL(sdhci_send_command);
@@ -3616,6 +3692,10 @@ int sdhci_setup_host(struct sdhci_host *host)
 		mmc->max_busy_timeout /= host->timeout_clk;
 	}
 
+	if (host->quirks2 & SDHCI_QUIRK2_DISABLE_HW_TIMEOUT &&
+	    !host->ops->get_max_timeout_count)
+		mmc->max_busy_timeout = 0;
+
 	mmc->caps |= MMC_CAP_SDIO_IRQ | MMC_CAP_ERASE | MMC_CAP_CMD23;
 	mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
 
@@ -3672,6 +3752,16 @@ int sdhci_setup_host(struct sdhci_host *host)
 	if (host->quirks2 & SDHCI_QUIRK2_NO_1_8_V) {
 		host->caps1 &= ~(SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_SDR50 |
 				 SDHCI_SUPPORT_DDR50);
+		/*
+		 * The SDHCI controller in a SoC might support HS200/HS400
+		 * (indicated using mmc-hs200-1_8v/mmc-hs400-1_8v dt property),
+		 * but if the board is modeled such that the IO lines are not
+		 * connected to 1.8v then HS200/HS400 cannot be supported.
+		 * Disable HS200/HS400 if the board does not have 1.8v connected
+		 * to the IO lines. (Applicable for other modes in 1.8v)
+		 */
+		mmc->caps2 &= ~(MMC_CAP2_HSX00_1_8V | MMC_CAP2_HS400_ES);
+		mmc->caps &= ~(MMC_CAP_1_8V_DDR | MMC_CAP_UHS);
 	}
 
 	/* Any UHS-I mode in caps implies SDR12 and SDR25 support. */
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index c95b0a4a7594..23966f887da6 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -332,6 +332,14 @@ struct sdhci_adma2_64_desc {
 /* Allow for a a command request and a data request at the same time */
 #define SDHCI_MAX_MRQS		2
 
+/*
+ * 48bit command and 136 bit response in 100KHz clock could take upto 2.48ms.
+ * However since the start time of the command, the time between
+ * command and response, and the time between response and start of data is
+ * not known, set the command transfer time to 10ms.
+ */
+#define MMC_CMD_TRANSFER_TIME	(10 * NSEC_PER_MSEC) /* max 10 ms */
+
 enum sdhci_cookie {
 	COOKIE_UNMAPPED,
 	COOKIE_PRE_MAPPED,	/* mapped by sdhci_pre_req() */
@@ -437,6 +445,11 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN		(1<<15)
 /* Controller has CRC in 136 bit Command Response */
 #define SDHCI_QUIRK2_RSP_136_HAS_CRC			(1<<16)
+/*
+ * Disable HW timeout if the requested timeout is more than the maximum
+ * obtainable timeout.
+ */
+#define SDHCI_QUIRK2_DISABLE_HW_TIMEOUT			(1<<17)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
@@ -550,6 +563,8 @@ struct sdhci_host {
 	/* Host SDMA buffer boundary. */
 	u32			sdma_boundary;
 
+	u64			data_timeout;
+
 	unsigned long private[0] ____cacheline_aligned;
 };
 
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 20cfb20418f3..e7472590f2ed 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -13,36 +13,34 @@
  * the License, or (at your option) any later version.
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/device.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-
 #include <linux/clk.h>
 #include <linux/clk/sunxi-ng.h>
-#include <linux/gpio.h>
-#include <linux/platform_device.h>
-#include <linux/spinlock.h>
-#include <linux/scatterlist.h>
+#include <linux/delay.h>
+#include <linux/device.h>
 #include <linux/dma-mapping.h>
-#include <linux/slab.h>
-#include <linux/reset.h>
-#include <linux/regulator/consumer.h>
-
-#include <linux/of_address.h>
-#include <linux/of_gpio.h>
-#include <linux/of_platform.h>
-
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mmc/card.h>
+#include <linux/mmc/core.h>
 #include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
 #include <linux/mmc/sd.h>
 #include <linux/mmc/sdio.h>
-#include <linux/mmc/mmc.h>
-#include <linux/mmc/core.h>
-#include <linux/mmc/card.h>
 #include <linux/mmc/slot-gpio.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_gpio.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+#include <linux/reset.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
 
 /* register offset definitions */
 #define SDXC_REG_GCTRL	(0x00) /* SMC Global Control Register */
@@ -322,10 +320,9 @@ static int sunxi_mmc_reset_host(struct sunxi_mmc_host *host)
 	return 0;
 }
 
-static int sunxi_mmc_init_host(struct mmc_host *mmc)
+static int sunxi_mmc_init_host(struct sunxi_mmc_host *host)
 {
 	u32 rval;
-	struct sunxi_mmc_host *host = mmc_priv(mmc);
 
 	if (sunxi_mmc_reset_host(host))
 		return -EIO;
@@ -859,17 +856,48 @@ static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 	return 0;
 }
 
-static void sunxi_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+static void sunxi_mmc_set_bus_width(struct sunxi_mmc_host *host,
+				   unsigned char width)
+{
+	switch (width) {
+	case MMC_BUS_WIDTH_1:
+		mmc_writel(host, REG_WIDTH, SDXC_WIDTH1);
+		break;
+	case MMC_BUS_WIDTH_4:
+		mmc_writel(host, REG_WIDTH, SDXC_WIDTH4);
+		break;
+	case MMC_BUS_WIDTH_8:
+		mmc_writel(host, REG_WIDTH, SDXC_WIDTH8);
+		break;
+	}
+}
+
+static void sunxi_mmc_set_clk(struct sunxi_mmc_host *host, struct mmc_ios *ios)
 {
-	struct sunxi_mmc_host *host = mmc_priv(mmc);
 	u32 rval;
 
-	/* Set the power state */
-	switch (ios->power_mode) {
-	case MMC_POWER_ON:
-		break;
+	/* set ddr mode */
+	rval = mmc_readl(host, REG_GCTRL);
+	if (ios->timing == MMC_TIMING_UHS_DDR50 ||
+	    ios->timing == MMC_TIMING_MMC_DDR52)
+		rval |= SDXC_DDR_MODE;
+	else
+		rval &= ~SDXC_DDR_MODE;
+	mmc_writel(host, REG_GCTRL, rval);
+
+	host->ferror = sunxi_mmc_clk_set_rate(host, ios);
+	/* Android code had a usleep_range(50000, 55000); here */
+}
 
+static void sunxi_mmc_card_power(struct sunxi_mmc_host *host,
+				 struct mmc_ios *ios)
+{
+	struct mmc_host *mmc = host->mmc;
+
+	switch (ios->power_mode) {
 	case MMC_POWER_UP:
+		dev_dbg(mmc_dev(mmc), "Powering card up\n");
+
 		if (!IS_ERR(mmc->supply.vmmc)) {
 			host->ferror = mmc_regulator_set_ocr(mmc,
 							     mmc->supply.vmmc,
@@ -887,53 +915,33 @@ static void sunxi_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 			}
 			host->vqmmc_enabled = true;
 		}
-
-		host->ferror = sunxi_mmc_init_host(mmc);
-		if (host->ferror)
-			return;
-
-		dev_dbg(mmc_dev(mmc), "power on!\n");
 		break;
 
 	case MMC_POWER_OFF:
-		dev_dbg(mmc_dev(mmc), "power off!\n");
-		sunxi_mmc_reset_host(host);
+		dev_dbg(mmc_dev(mmc), "Powering card off\n");
+
 		if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
 
 		if (!IS_ERR(mmc->supply.vqmmc) && host->vqmmc_enabled)
 			regulator_disable(mmc->supply.vqmmc);
+
 		host->vqmmc_enabled = false;
 		break;
-	}
 
-	/* set bus width */
-	switch (ios->bus_width) {
-	case MMC_BUS_WIDTH_1:
-		mmc_writel(host, REG_WIDTH, SDXC_WIDTH1);
-		break;
-	case MMC_BUS_WIDTH_4:
-		mmc_writel(host, REG_WIDTH, SDXC_WIDTH4);
-		break;
-	case MMC_BUS_WIDTH_8:
-		mmc_writel(host, REG_WIDTH, SDXC_WIDTH8);
+	default:
+		dev_dbg(mmc_dev(mmc), "Ignoring unknown card power state\n");
 		break;
 	}
+}
 
-	/* set ddr mode */
-	rval = mmc_readl(host, REG_GCTRL);
-	if (ios->timing == MMC_TIMING_UHS_DDR50 ||
-	    ios->timing == MMC_TIMING_MMC_DDR52)
-		rval |= SDXC_DDR_MODE;
-	else
-		rval &= ~SDXC_DDR_MODE;
-	mmc_writel(host, REG_GCTRL, rval);
+static void sunxi_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct sunxi_mmc_host *host = mmc_priv(mmc);
 
-	/* set up clock */
-	if (ios->power_mode) {
-		host->ferror = sunxi_mmc_clk_set_rate(host, ios);
-		/* Android code had a usleep_range(50000, 55000); here */
-	}
+	sunxi_mmc_card_power(host, ios);
+	sunxi_mmc_set_bus_width(host, ios->bus_width);
+	sunxi_mmc_set_clk(host, ios);
 }
 
 static int sunxi_mmc_volt_switch(struct mmc_host *mmc, struct mmc_ios *ios)
@@ -955,6 +963,9 @@ static void sunxi_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 	unsigned long flags;
 	u32 imask;
 
+	if (enable)
+		pm_runtime_get_noresume(host->dev);
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	imask = mmc_readl(host, REG_IMASK);
@@ -967,6 +978,9 @@ static void sunxi_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 	}
 	mmc_writel(host, REG_IMASK, imask);
 	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (!enable)
+		pm_runtime_put_noidle(host->mmc->parent);
 }
 
 static void sunxi_mmc_hw_reset(struct mmc_host *mmc)
@@ -1380,6 +1394,15 @@ static int sunxi_mmc_probe(struct platform_device *pdev)
 	if (ret)
 		goto error_free_dma;
 
+	ret = sunxi_mmc_init_host(host);
+	if (ret)
+		goto error_free_dma;
+
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 50);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
 	ret = mmc_add_host(mmc);
 	if (ret)
 		goto error_free_dma;
@@ -1400,6 +1423,7 @@ static int sunxi_mmc_remove(struct platform_device *pdev)
 	struct sunxi_mmc_host *host = mmc_priv(mmc);
 
 	mmc_remove_host(mmc);
+	pm_runtime_force_suspend(&pdev->dev);
 	disable_irq(host->irq);
 	sunxi_mmc_disable(host);
 	dma_free_coherent(&pdev->dev, PAGE_SIZE, host->sg_cpu, host->sg_dma);
@@ -1408,10 +1432,47 @@ static int sunxi_mmc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int sunxi_mmc_runtime_resume(struct device *dev)
+{
+	struct mmc_host	*mmc = dev_get_drvdata(dev);
+	struct sunxi_mmc_host *host = mmc_priv(mmc);
+	int ret;
+
+	ret = sunxi_mmc_enable(host);
+	if (ret)
+		return ret;
+
+	sunxi_mmc_init_host(host);
+	sunxi_mmc_set_bus_width(host, mmc->ios.bus_width);
+	sunxi_mmc_set_clk(host, &mmc->ios);
+
+	return 0;
+}
+
+static int sunxi_mmc_runtime_suspend(struct device *dev)
+{
+	struct mmc_host	*mmc = dev_get_drvdata(dev);
+	struct sunxi_mmc_host *host = mmc_priv(mmc);
+
+	sunxi_mmc_reset_host(host);
+	sunxi_mmc_disable(host);
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops sunxi_mmc_pm_ops = {
+	SET_RUNTIME_PM_OPS(sunxi_mmc_runtime_suspend,
+			   sunxi_mmc_runtime_resume,
+			   NULL)
+};
+
 static struct platform_driver sunxi_mmc_driver = {
 	.driver = {
 		.name	= "sunxi-mmc",
 		.of_match_table = of_match_ptr(sunxi_mmc_of_match),
+		.pm = &sunxi_mmc_pm_ops,
 	},
 	.probe		= sunxi_mmc_probe,
 	.remove		= sunxi_mmc_remove,
diff --git a/drivers/mmc/host/ushc.c b/drivers/mmc/host/ushc.c
index 81dac17064d7..b2b379b10dfa 100644
--- a/drivers/mmc/host/ushc.c
+++ b/drivers/mmc/host/ushc.c
@@ -300,8 +300,10 @@ static void ushc_request(struct mmc_host *mmc, struct mmc_request *req)
 			pipe = usb_sndbulkpipe(ushc->usb_dev, 2);
 
 		usb_fill_bulk_urb(ushc->data_urb, ushc->usb_dev, pipe,
-				  sg_virt(data->sg), data->sg->length,
+				  NULL, data->sg->length,
 				  data_callback, ushc);
+		ushc->data_urb->num_sgs = 1;
+		ushc->data_urb->sg = data->sg;
 		ret = usb_submit_urb(ushc->data_urb, GFP_ATOMIC);
 		if (ret < 0)
 			goto out;
diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c
index f4233576153b..1e54bbf13d75 100644
--- a/drivers/mmc/host/wbsd.c
+++ b/drivers/mmc/host/wbsd.c
@@ -268,43 +268,29 @@ static inline int wbsd_next_sg(struct wbsd_host *host)
 	return host->num_sg;
 }
 
-static inline char *wbsd_sg_to_buffer(struct wbsd_host *host)
+static inline char *wbsd_map_sg(struct wbsd_host *host)
 {
-	return sg_virt(host->cur_sg);
+	return kmap_atomic(sg_page(host->cur_sg)) + host->cur_sg->offset;
 }
 
 static inline void wbsd_sg_to_dma(struct wbsd_host *host, struct mmc_data *data)
 {
-	unsigned int len, i;
-	struct scatterlist *sg;
-	char *dmabuf = host->dma_buffer;
-	char *sgbuf;
-
-	sg = data->sg;
-	len = data->sg_len;
-
-	for (i = 0; i < len; i++) {
-		sgbuf = sg_virt(&sg[i]);
-		memcpy(dmabuf, sgbuf, sg[i].length);
-		dmabuf += sg[i].length;
-	}
+	size_t len = 0;
+	int i;
+
+	for (i = 0; i < data->sg_len; i++)
+		len += data->sg[i].length;
+	sg_copy_to_buffer(data->sg, data->sg_len, host->dma_buffer, len);
 }
 
 static inline void wbsd_dma_to_sg(struct wbsd_host *host, struct mmc_data *data)
 {
-	unsigned int len, i;
-	struct scatterlist *sg;
-	char *dmabuf = host->dma_buffer;
-	char *sgbuf;
-
-	sg = data->sg;
-	len = data->sg_len;
-
-	for (i = 0; i < len; i++) {
-		sgbuf = sg_virt(&sg[i]);
-		memcpy(sgbuf, dmabuf, sg[i].length);
-		dmabuf += sg[i].length;
-	}
+	size_t len = 0;
+	int i;
+
+	for (i = 0; i < data->sg_len; i++)
+		len += data->sg[i].length;
+	sg_copy_from_buffer(data->sg, data->sg_len, host->dma_buffer, len);
 }
 
 /*
@@ -418,7 +404,7 @@ static void wbsd_empty_fifo(struct wbsd_host *host)
 {
 	struct mmc_data *data = host->mrq->cmd->data;
 	char *buffer;
-	int i, fsr, fifo;
+	int i, idx, fsr, fifo;
 
 	/*
 	 * Handle excessive data.
@@ -426,7 +412,8 @@ static void wbsd_empty_fifo(struct wbsd_host *host)
 	if (host->num_sg == 0)
 		return;
 
-	buffer = wbsd_sg_to_buffer(host) + host->offset;
+	buffer = wbsd_map_sg(host) + host->offset;
+	idx = 0;
 
 	/*
 	 * Drain the fifo. This has a tendency to loop longer
@@ -445,8 +432,7 @@ static void wbsd_empty_fifo(struct wbsd_host *host)
 			fifo = 1;
 
 		for (i = 0; i < fifo; i++) {
-			*buffer = inb(host->base + WBSD_DFR);
-			buffer++;
+			buffer[idx++] = inb(host->base + WBSD_DFR);
 			host->offset++;
 			host->remain--;
 
@@ -456,16 +442,19 @@ static void wbsd_empty_fifo(struct wbsd_host *host)
 			 * End of scatter list entry?
 			 */
 			if (host->remain == 0) {
+				kunmap_atomic(buffer);
 				/*
 				 * Get next entry. Check if last.
 				 */
 				if (!wbsd_next_sg(host))
 					return;
 
-				buffer = wbsd_sg_to_buffer(host);
+				buffer = wbsd_map_sg(host);
+				idx = 0;
 			}
 		}
 	}
+	kunmap_atomic(buffer);
 
 	/*
 	 * This is a very dirty hack to solve a
@@ -480,7 +469,7 @@ static void wbsd_fill_fifo(struct wbsd_host *host)
 {
 	struct mmc_data *data = host->mrq->cmd->data;
 	char *buffer;
-	int i, fsr, fifo;
+	int i, idx, fsr, fifo;
 
 	/*
 	 * Check that we aren't being called after the
@@ -489,7 +478,8 @@ static void wbsd_fill_fifo(struct wbsd_host *host)
 	if (host->num_sg == 0)
 		return;
 
-	buffer = wbsd_sg_to_buffer(host) + host->offset;
+	buffer = wbsd_map_sg(host) + host->offset;
+	idx = 0;
 
 	/*
 	 * Fill the fifo. This has a tendency to loop longer
@@ -508,8 +498,7 @@ static void wbsd_fill_fifo(struct wbsd_host *host)
 			fifo = 15;
 
 		for (i = 16; i > fifo; i--) {
-			outb(*buffer, host->base + WBSD_DFR);
-			buffer++;
+			outb(buffer[idx], host->base + WBSD_DFR);
 			host->offset++;
 			host->remain--;
 
@@ -519,16 +508,19 @@ static void wbsd_fill_fifo(struct wbsd_host *host)
 			 * End of scatter list entry?
 			 */
 			if (host->remain == 0) {
+				kunmap_atomic(buffer);
 				/*
 				 * Get next entry. Check if last.
 				 */
 				if (!wbsd_next_sg(host))
 					return;
 
-				buffer = wbsd_sg_to_buffer(host);
+				buffer = wbsd_map_sg(host);
+				idx = 0;
 			}
 		}
 	}
+	kunmap_atomic(buffer);
 
 	/*
 	 * The controller stops sending interrupts for
diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c
index fd30ac7da5e5..3ba42f508014 100644
--- a/drivers/mmc/host/wmt-sdmmc.c
+++ b/drivers/mmc/host/wmt-sdmmc.c
@@ -928,8 +928,7 @@ static int wmt_mci_remove(struct platform_device *pdev)
 static int wmt_mci_suspend(struct device *dev)
 {
 	u32 reg_tmp;
-	struct platform_device *pdev = to_platform_device(dev);
-	struct mmc_host *mmc = platform_get_drvdata(pdev);
+	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct wmt_mci_priv *priv;
 
 	if (!mmc)
@@ -953,8 +952,7 @@ static int wmt_mci_suspend(struct device *dev)
 static int wmt_mci_resume(struct device *dev)
 {
 	u32 reg_tmp;
-	struct platform_device *pdev = to_platform_device(dev);
-	struct mmc_host *mmc = platform_get_drvdata(pdev);
+	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct wmt_mci_priv *priv;
 
 	if (mmc) {
diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index d4c07b85f18e..f5695be14499 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -45,6 +45,7 @@
 #define I82802AB	0x00ad
 #define I82802AC	0x00ac
 #define PF38F4476	0x881c
+#define M28F00AP30	0x8963
 /* STMicroelectronics chips */
 #define M50LPW080       0x002F
 #define M50FLW080A	0x0080
@@ -375,6 +376,17 @@ static void cfi_fixup_major_minor(struct cfi_private *cfi,
 		extp->MinorVersion = '1';
 }
 
+static int cfi_is_micron_28F00AP30(struct cfi_private *cfi, struct flchip *chip)
+{
+	/*
+	 * Micron(was Numonyx) 1Gbit bottom boot are buggy w.r.t
+	 * Erase Supend for their small Erase Blocks(0x8000)
+	 */
+	if (cfi->mfr == CFI_MFR_INTEL && cfi->id == M28F00AP30)
+		return 1;
+	return 0;
+}
+
 static inline struct cfi_pri_intelext *
 read_pri_intelext(struct map_info *map, __u16 adr)
 {
@@ -831,21 +843,30 @@ static int chip_ready (struct map_info *map, struct flchip *chip, unsigned long
 		     (mode == FL_WRITING && (cfip->SuspendCmdSupport & 1))))
 			goto sleep;
 
+		/* Do not allow suspend iff read/write to EB address */
+		if ((adr & chip->in_progress_block_mask) ==
+		    chip->in_progress_block_addr)
+			goto sleep;
+
+		/* do not suspend small EBs, buggy Micron Chips */
+		if (cfi_is_micron_28F00AP30(cfi, chip) &&
+		    (chip->in_progress_block_mask == ~(0x8000-1)))
+			goto sleep;
 
 		/* Erase suspend */
-		map_write(map, CMD(0xB0), adr);
+		map_write(map, CMD(0xB0), chip->in_progress_block_addr);
 
 		/* If the flash has finished erasing, then 'erase suspend'
 		 * appears to make some (28F320) flash devices switch to
 		 * 'read' mode.  Make sure that we switch to 'read status'
 		 * mode so we get the right data. --rmk
 		 */
-		map_write(map, CMD(0x70), adr);
+		map_write(map, CMD(0x70), chip->in_progress_block_addr);
 		chip->oldstate = FL_ERASING;
 		chip->state = FL_ERASE_SUSPENDING;
 		chip->erase_suspended = 1;
 		for (;;) {
-			status = map_read(map, adr);
+			status = map_read(map, chip->in_progress_block_addr);
 			if (map_word_andequal(map, status, status_OK, status_OK))
 			        break;
 
@@ -1041,8 +1062,8 @@ static void put_chip(struct map_info *map, struct flchip *chip, unsigned long ad
 		   sending the 0x70 (Read Status) command to an erasing
 		   chip and expecting it to be ignored, that's what we
 		   do. */
-		map_write(map, CMD(0xd0), adr);
-		map_write(map, CMD(0x70), adr);
+		map_write(map, CMD(0xd0), chip->in_progress_block_addr);
+		map_write(map, CMD(0x70), chip->in_progress_block_addr);
 		chip->oldstate = FL_READY;
 		chip->state = FL_ERASING;
 		break;
@@ -1933,6 +1954,8 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 	map_write(map, CMD(0xD0), adr);
 	chip->state = FL_ERASING;
 	chip->erase_suspended = 0;
+	chip->in_progress_block_addr = adr;
+	chip->in_progress_block_mask = ~(len - 1);
 
 	ret = INVAL_CACHE_AND_WAIT(map, chip, adr,
 				   adr, len,
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 668e2cbc155b..692902df2598 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -816,9 +816,10 @@ static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr
 		    (mode == FL_WRITING && (cfip->EraseSuspend & 0x2))))
 			goto sleep;
 
-		/* We could check to see if we're trying to access the sector
-		 * that is currently being erased. However, no user will try
-		 * anything like that so we just wait for the timeout. */
+		/* Do not allow suspend iff read/write to EB address */
+		if ((adr & chip->in_progress_block_mask) ==
+		    chip->in_progress_block_addr)
+			goto sleep;
 
 		/* Erase suspend */
 		/* It's harmless to issue the Erase-Suspend and Erase-Resume
@@ -2267,6 +2268,7 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
 	chip->state = FL_ERASING;
 	chip->erase_suspended = 0;
 	chip->in_progress_block_addr = adr;
+	chip->in_progress_block_mask = ~(map->size - 1);
 
 	INVALIDATE_CACHE_UDELAY(map, chip,
 				adr, map->size,
@@ -2356,6 +2358,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 	chip->state = FL_ERASING;
 	chip->erase_suspended = 0;
 	chip->in_progress_block_addr = adr;
+	chip->in_progress_block_mask = ~(len - 1);
 
 	INVALIDATE_CACHE_UDELAY(map, chip,
 				adr, len,
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 6def5445e03e..57b02c4b3f63 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -81,6 +81,7 @@ config MTD_DATAFLASH_OTP
 config MTD_M25P80
 	tristate "Support most SPI Flash chips (AT26DF, M25P, W25X, ...)"
 	depends on SPI_MASTER && MTD_SPI_NOR
+	select SPI_MEM
 	help
 	  This enables access to most modern SPI flash chips, used for
 	  program and data storage.   Series supported include Atmel AT26DF,
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index a4e18f6aaa33..e84563d2067f 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -24,12 +24,13 @@
 #include <linux/mtd/partitions.h>
 
 #include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
 #include <linux/spi/flash.h>
 #include <linux/mtd/spi-nor.h>
 
 #define	MAX_CMD_SIZE		6
 struct m25p {
-	struct spi_device	*spi;
+	struct spi_mem		*spimem;
 	struct spi_nor		spi_nor;
 	u8			command[MAX_CMD_SIZE];
 };
@@ -37,97 +38,68 @@ struct m25p {
 static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len)
 {
 	struct m25p *flash = nor->priv;
-	struct spi_device *spi = flash->spi;
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(code, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_NO_DUMMY,
+					  SPI_MEM_OP_DATA_IN(len, val, 1));
 	int ret;
 
-	ret = spi_write_then_read(spi, &code, 1, val, len);
+	ret = spi_mem_exec_op(flash->spimem, &op);
 	if (ret < 0)
-		dev_err(&spi->dev, "error %d reading %x\n", ret, code);
+		dev_err(&flash->spimem->spi->dev, "error %d reading %x\n", ret,
+			code);
 
 	return ret;
 }
 
-static void m25p_addr2cmd(struct spi_nor *nor, unsigned int addr, u8 *cmd)
-{
-	/* opcode is in cmd[0] */
-	cmd[1] = addr >> (nor->addr_width * 8 -  8);
-	cmd[2] = addr >> (nor->addr_width * 8 - 16);
-	cmd[3] = addr >> (nor->addr_width * 8 - 24);
-	cmd[4] = addr >> (nor->addr_width * 8 - 32);
-}
-
-static int m25p_cmdsz(struct spi_nor *nor)
-{
-	return 1 + nor->addr_width;
-}
-
 static int m25p80_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 {
 	struct m25p *flash = nor->priv;
-	struct spi_device *spi = flash->spi;
-
-	flash->command[0] = opcode;
-	if (buf)
-		memcpy(&flash->command[1], buf, len);
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_NO_DUMMY,
+					  SPI_MEM_OP_DATA_OUT(len, buf, 1));
 
-	return spi_write(spi, flash->command, len + 1);
+	return spi_mem_exec_op(flash->spimem, &op);
 }
 
 static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 			    const u_char *buf)
 {
 	struct m25p *flash = nor->priv;
-	struct spi_device *spi = flash->spi;
-	unsigned int inst_nbits, addr_nbits, data_nbits, data_idx;
-	struct spi_transfer t[3] = {};
-	struct spi_message m;
-	int cmd_sz = m25p_cmdsz(nor);
-	ssize_t ret;
+	struct spi_mem_op op =
+			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 1),
+				   SPI_MEM_OP_ADDR(nor->addr_width, to, 1),
+				   SPI_MEM_OP_DUMMY(0, 1),
+				   SPI_MEM_OP_DATA_OUT(len, buf, 1));
+	size_t remaining = len;
+	int ret;
 
 	/* get transfer protocols. */
-	inst_nbits = spi_nor_get_protocol_inst_nbits(nor->write_proto);
-	addr_nbits = spi_nor_get_protocol_addr_nbits(nor->write_proto);
-	data_nbits = spi_nor_get_protocol_data_nbits(nor->write_proto);
-
-	spi_message_init(&m);
+	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->write_proto);
+	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->write_proto);
+	op.dummy.buswidth = op.addr.buswidth;
+	op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
 
 	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
-		cmd_sz = 1;
-
-	flash->command[0] = nor->program_opcode;
-	m25p_addr2cmd(nor, to, flash->command);
+		op.addr.nbytes = 0;
 
-	t[0].tx_buf = flash->command;
-	t[0].tx_nbits = inst_nbits;
-	t[0].len = cmd_sz;
-	spi_message_add_tail(&t[0], &m);
-
-	/* split the op code and address bytes into two transfers if needed. */
-	data_idx = 1;
-	if (addr_nbits != inst_nbits) {
-		t[0].len = 1;
+	while (remaining) {
+		op.data.nbytes = remaining < UINT_MAX ? remaining : UINT_MAX;
+		ret = spi_mem_adjust_op_size(flash->spimem, &op);
+		if (ret)
+			return ret;
 
-		t[1].tx_buf = &flash->command[1];
-		t[1].tx_nbits = addr_nbits;
-		t[1].len = cmd_sz - 1;
-		spi_message_add_tail(&t[1], &m);
+		ret = spi_mem_exec_op(flash->spimem, &op);
+		if (ret)
+			return ret;
 
-		data_idx = 2;
+		op.addr.val += op.data.nbytes;
+		remaining -= op.data.nbytes;
+		op.data.buf.out += op.data.nbytes;
 	}
 
-	t[data_idx].tx_buf = buf;
-	t[data_idx].tx_nbits = data_nbits;
-	t[data_idx].len = len;
-	spi_message_add_tail(&t[data_idx], &m);
-
-	ret = spi_sync(spi, &m);
-	if (ret)
-		return ret;
-
-	ret = m.actual_length - cmd_sz;
-	if (ret < 0)
-		return -EIO;
-	return ret;
+	return len;
 }
 
 /*
@@ -138,92 +110,39 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
 			   u_char *buf)
 {
 	struct m25p *flash = nor->priv;
-	struct spi_device *spi = flash->spi;
-	unsigned int inst_nbits, addr_nbits, data_nbits, data_idx;
-	struct spi_transfer t[3];
-	struct spi_message m;
-	unsigned int dummy = nor->read_dummy;
-	ssize_t ret;
-	int cmd_sz;
+	struct spi_mem_op op =
+			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->read_opcode, 1),
+				   SPI_MEM_OP_ADDR(nor->addr_width, from, 1),
+				   SPI_MEM_OP_DUMMY(nor->read_dummy, 1),
+				   SPI_MEM_OP_DATA_IN(len, buf, 1));
+	size_t remaining = len;
+	int ret;
 
 	/* get transfer protocols. */
-	inst_nbits = spi_nor_get_protocol_inst_nbits(nor->read_proto);
-	addr_nbits = spi_nor_get_protocol_addr_nbits(nor->read_proto);
-	data_nbits = spi_nor_get_protocol_data_nbits(nor->read_proto);
+	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->read_proto);
+	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->read_proto);
+	op.dummy.buswidth = op.addr.buswidth;
+	op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->read_proto);
 
 	/* convert the dummy cycles to the number of bytes */
-	dummy = (dummy * addr_nbits) / 8;
-
-	if (spi_flash_read_supported(spi)) {
-		struct spi_flash_read_message msg;
-
-		memset(&msg, 0, sizeof(msg));
+	op.dummy.nbytes = (nor->read_dummy * op.dummy.buswidth) / 8;
 
-		msg.buf = buf;
-		msg.from = from;
-		msg.len = len;
-		msg.read_opcode = nor->read_opcode;
-		msg.addr_width = nor->addr_width;
-		msg.dummy_bytes = dummy;
-		msg.opcode_nbits = inst_nbits;
-		msg.addr_nbits = addr_nbits;
-		msg.data_nbits = data_nbits;
-
-		ret = spi_flash_read(spi, &msg);
-		if (ret < 0)
+	while (remaining) {
+		op.data.nbytes = remaining < UINT_MAX ? remaining : UINT_MAX;
+		ret = spi_mem_adjust_op_size(flash->spimem, &op);
+		if (ret)
 			return ret;
-		return msg.retlen;
-	}
 
-	spi_message_init(&m);
-	memset(t, 0, (sizeof t));
-
-	flash->command[0] = nor->read_opcode;
-	m25p_addr2cmd(nor, from, flash->command);
-
-	t[0].tx_buf = flash->command;
-	t[0].tx_nbits = inst_nbits;
-	t[0].len = m25p_cmdsz(nor) + dummy;
-	spi_message_add_tail(&t[0], &m);
-
-	/*
-	 * Set all dummy/mode cycle bits to avoid sending some manufacturer
-	 * specific pattern, which might make the memory enter its Continuous
-	 * Read mode by mistake.
-	 * Based on the different mode cycle bit patterns listed and described
-	 * in the JESD216B specification, the 0xff value works for all memories
-	 * and all manufacturers.
-	 */
-	cmd_sz = t[0].len;
-	memset(flash->command + cmd_sz - dummy, 0xff, dummy);
-
-	/* split the op code and address bytes into two transfers if needed. */
-	data_idx = 1;
-	if (addr_nbits != inst_nbits) {
-		t[0].len = 1;
-
-		t[1].tx_buf = &flash->command[1];
-		t[1].tx_nbits = addr_nbits;
-		t[1].len = cmd_sz - 1;
-		spi_message_add_tail(&t[1], &m);
+		ret = spi_mem_exec_op(flash->spimem, &op);
+		if (ret)
+			return ret;
 
-		data_idx = 2;
+		op.addr.val += op.data.nbytes;
+		remaining -= op.data.nbytes;
+		op.data.buf.in += op.data.nbytes;
 	}
 
-	t[data_idx].rx_buf = buf;
-	t[data_idx].rx_nbits = data_nbits;
-	t[data_idx].len = min3(len, spi_max_transfer_size(spi),
-			       spi_max_message_size(spi) - cmd_sz);
-	spi_message_add_tail(&t[data_idx], &m);
-
-	ret = spi_sync(spi, &m);
-	if (ret)
-		return ret;
-
-	ret = m.actual_length - cmd_sz;
-	if (ret < 0)
-		return -EIO;
-	return ret;
+	return len;
 }
 
 /*
@@ -231,8 +150,9 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
  * matches what the READ command supports, at least until this driver
  * understands FAST_READ (for clocks over 25 MHz).
  */
-static int m25p_probe(struct spi_device *spi)
+static int m25p_probe(struct spi_mem *spimem)
 {
+	struct spi_device *spi = spimem->spi;
 	struct flash_platform_data	*data;
 	struct m25p *flash;
 	struct spi_nor *nor;
@@ -244,9 +164,9 @@ static int m25p_probe(struct spi_device *spi)
 	char *flash_name;
 	int ret;
 
-	data = dev_get_platdata(&spi->dev);
+	data = dev_get_platdata(&spimem->spi->dev);
 
-	flash = devm_kzalloc(&spi->dev, sizeof(*flash), GFP_KERNEL);
+	flash = devm_kzalloc(&spimem->spi->dev, sizeof(*flash), GFP_KERNEL);
 	if (!flash)
 		return -ENOMEM;
 
@@ -258,12 +178,12 @@ static int m25p_probe(struct spi_device *spi)
 	nor->write_reg = m25p80_write_reg;
 	nor->read_reg = m25p80_read_reg;
 
-	nor->dev = &spi->dev;
+	nor->dev = &spimem->spi->dev;
 	spi_nor_set_flash_node(nor, spi->dev.of_node);
 	nor->priv = flash;
 
-	spi_set_drvdata(spi, flash);
-	flash->spi = spi;
+	spi_mem_set_drvdata(spimem, flash);
+	flash->spimem = spimem;
 
 	if (spi->mode & SPI_RX_QUAD) {
 		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
@@ -303,9 +223,9 @@ static int m25p_probe(struct spi_device *spi)
 }
 
 
-static int m25p_remove(struct spi_device *spi)
+static int m25p_remove(struct spi_mem *spimem)
 {
-	struct m25p	*flash = spi_get_drvdata(spi);
+	struct m25p	*flash = spi_mem_get_drvdata(spimem);
 
 	spi_nor_restore(&flash->spi_nor);
 
@@ -313,9 +233,9 @@ static int m25p_remove(struct spi_device *spi)
 	return mtd_device_unregister(&flash->spi_nor.mtd);
 }
 
-static void m25p_shutdown(struct spi_device *spi)
+static void m25p_shutdown(struct spi_mem *spimem)
 {
-	struct m25p *flash = spi_get_drvdata(spi);
+	struct m25p *flash = spi_mem_get_drvdata(spimem);
 
 	spi_nor_restore(&flash->spi_nor);
 }
@@ -386,12 +306,14 @@ static const struct of_device_id m25p_of_table[] = {
 };
 MODULE_DEVICE_TABLE(of, m25p_of_table);
 
-static struct spi_driver m25p80_driver = {
-	.driver = {
-		.name	= "m25p80",
-		.of_match_table = m25p_of_table,
+static struct spi_mem_driver m25p80_driver = {
+	.spidrv = {
+		.driver = {
+			.name	= "m25p80",
+			.of_match_table = m25p_of_table,
+		},
+		.id_table	= m25p_ids,
 	},
-	.id_table	= m25p_ids,
 	.probe	= m25p_probe,
 	.remove	= m25p_remove,
 	.shutdown	= m25p_shutdown,
@@ -402,7 +324,7 @@ static struct spi_driver m25p80_driver = {
 	 */
 };
 
-module_spi_driver(m25p80_driver);
+module_spi_mem_driver(m25p80_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Mike Lavender");
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 16ae4ae8e8f9..29c0bfd74e8a 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -82,7 +82,6 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
 
 	block = blk_rq_pos(req) << 9 >> tr->blkshift;
 	nsect = blk_rq_cur_bytes(req) >> tr->blkshift;
-	buf = bio_data(req->bio);
 
 	if (req_op(req) == REQ_OP_FLUSH) {
 		if (tr->flush(dev))
@@ -100,9 +99,14 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
 			return BLK_STS_IOERR;
 		return BLK_STS_OK;
 	case REQ_OP_READ:
-		for (; nsect > 0; nsect--, block++, buf += tr->blksize)
-			if (tr->readsect(dev, block, buf))
+		buf = kmap(bio_page(req->bio)) + bio_offset(req->bio);
+		for (; nsect > 0; nsect--, block++, buf += tr->blksize) {
+			if (tr->readsect(dev, block, buf)) {
+				kunmap(bio_page(req->bio));
 				return BLK_STS_IOERR;
+			}
+		}
+		kunmap(bio_page(req->bio));
 		rq_flush_dcache_pages(req);
 		return BLK_STS_OK;
 	case REQ_OP_WRITE:
@@ -110,9 +114,14 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
 			return BLK_STS_IOERR;
 
 		rq_flush_dcache_pages(req);
-		for (; nsect > 0; nsect--, block++, buf += tr->blksize)
-			if (tr->writesect(dev, block, buf))
+		buf = kmap(bio_page(req->bio)) + bio_offset(req->bio);
+		for (; nsect > 0; nsect--, block++, buf += tr->blksize) {
+			if (tr->writesect(dev, block, buf)) {
+				kunmap(bio_page(req->bio));
 				return BLK_STS_IOERR;
+			}
+		}
+		kunmap(bio_page(req->bio));
 		return BLK_STS_OK;
 	default:
 		return BLK_STS_IOERR;
@@ -418,7 +427,6 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	new->rq->queuedata = new;
 	blk_queue_logical_block_size(new->rq, tr->blksize);
 
-	blk_queue_bounce_limit(new->rq, BLK_BOUNCE_HIGH);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
 
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 807d17d863b3..64a1fcaafd9a 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1829,18 +1829,6 @@ static int mtd_proc_show(struct seq_file *m, void *v)
 	mutex_unlock(&mtd_table_mutex);
 	return 0;
 }
-
-static int mtd_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mtd_proc_show, NULL);
-}
-
-static const struct file_operations mtd_proc_ops = {
-	.open		= mtd_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif /* CONFIG_PROC_FS */
 
 /*====================================================================*/
@@ -1883,7 +1871,7 @@ static int __init init_mtd(void)
 		goto err_bdi;
 	}
 
-	proc_mtd = proc_create("mtd", 0, NULL, &mtd_proc_ops);
+	proc_mtd = proc_create_single("mtd", 0, NULL, mtd_proc_show);
 
 	ret = init_mtdchar();
 	if (ret)
diff --git a/drivers/mtd/nand/core.c b/drivers/mtd/nand/core.c
index d0cd6f8635d7..9c9f8936b63b 100644
--- a/drivers/mtd/nand/core.c
+++ b/drivers/mtd/nand/core.c
@@ -162,7 +162,6 @@ int nanddev_mtd_erase(struct mtd_info *mtd, struct erase_info *einfo)
 		ret = nanddev_erase(nand, &pos);
 		if (ret) {
 			einfo->fail_addr = nanddev_pos_to_offs(nand, &pos);
-			einfo->state = MTD_ERASE_FAILED;
 
 			return ret;
 		}
@@ -170,8 +169,6 @@ int nanddev_mtd_erase(struct mtd_info *mtd, struct erase_info *einfo)
 		nanddev_pos_next_eraseblock(nand, &pos);
 	}
 
-	einfo->state = MTD_ERASE_DONE;
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nanddev_mtd_erase);
diff --git a/drivers/mtd/nand/onenand/omap2.c b/drivers/mtd/nand/onenand/omap2.c
index 9c159f0dd9a6..321137158ff3 100644
--- a/drivers/mtd/nand/onenand/omap2.c
+++ b/drivers/mtd/nand/onenand/omap2.c
@@ -375,56 +375,42 @@ static int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area,
 {
 	struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
 	struct onenand_chip *this = mtd->priv;
-	dma_addr_t dma_src, dma_dst;
-	int bram_offset;
+	struct device *dev = &c->pdev->dev;
 	void *buf = (void *)buffer;
+	dma_addr_t dma_src, dma_dst;
+	int bram_offset, err;
 	size_t xtra;
-	int ret;
 
 	bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
-	if (bram_offset & 3 || (size_t)buf & 3 || count < 384)
-		goto out_copy;
-
-	/* panic_write() may be in an interrupt context */
-	if (in_interrupt() || oops_in_progress)
+	/*
+	 * If the buffer address is not DMA-able, len is not long enough to make
+	 * DMA transfers profitable or panic_write() may be in an interrupt
+	 * context fallback to PIO mode.
+	 */
+	if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 ||
+	    count < 384 || in_interrupt() || oops_in_progress )
 		goto out_copy;
 
-	if (buf >= high_memory) {
-		struct page *p1;
-
-		if (((size_t)buf & PAGE_MASK) !=
-		    ((size_t)(buf + count - 1) & PAGE_MASK))
-			goto out_copy;
-		p1 = vmalloc_to_page(buf);
-		if (!p1)
-			goto out_copy;
-		buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK);
-	}
-
 	xtra = count & 3;
 	if (xtra) {
 		count -= xtra;
 		memcpy(buf + count, this->base + bram_offset + count, xtra);
 	}
 
+	dma_dst = dma_map_single(dev, buf, count, DMA_FROM_DEVICE);
 	dma_src = c->phys_base + bram_offset;
-	dma_dst = dma_map_single(&c->pdev->dev, buf, count, DMA_FROM_DEVICE);
-	if (dma_mapping_error(&c->pdev->dev, dma_dst)) {
-		dev_err(&c->pdev->dev,
-			"Couldn't DMA map a %d byte buffer\n",
-			count);
-		goto out_copy;
-	}
 
-	ret = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
-	dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_FROM_DEVICE);
-
-	if (ret) {
-		dev_err(&c->pdev->dev, "timeout waiting for DMA\n");
+	if (dma_mapping_error(dev, dma_dst)) {
+		dev_err(dev, "Couldn't DMA map a %d byte buffer\n", count);
 		goto out_copy;
 	}
 
-	return 0;
+	err = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
+	dma_unmap_single(dev, dma_dst, count, DMA_FROM_DEVICE);
+	if (!err)
+		return 0;
+
+	dev_err(dev, "timeout waiting for DMA\n");
 
 out_copy:
 	memcpy(buf, this->base + bram_offset, count);
@@ -437,49 +423,34 @@ static int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area,
 {
 	struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
 	struct onenand_chip *this = mtd->priv;
-	dma_addr_t dma_src, dma_dst;
-	int bram_offset;
+	struct device *dev = &c->pdev->dev;
 	void *buf = (void *)buffer;
-	int ret;
+	dma_addr_t dma_src, dma_dst;
+	int bram_offset, err;
 
 	bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
-	if (bram_offset & 3 || (size_t)buf & 3 || count < 384)
-		goto out_copy;
-
-	/* panic_write() may be in an interrupt context */
-	if (in_interrupt() || oops_in_progress)
+	/*
+	 * If the buffer address is not DMA-able, len is not long enough to make
+	 * DMA transfers profitable or panic_write() may be in an interrupt
+	 * context fallback to PIO mode.
+	 */
+	if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 ||
+	    count < 384 || in_interrupt() || oops_in_progress )
 		goto out_copy;
 
-	if (buf >= high_memory) {
-		struct page *p1;
-
-		if (((size_t)buf & PAGE_MASK) !=
-		    ((size_t)(buf + count - 1) & PAGE_MASK))
-			goto out_copy;
-		p1 = vmalloc_to_page(buf);
-		if (!p1)
-			goto out_copy;
-		buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK);
-	}
-
-	dma_src = dma_map_single(&c->pdev->dev, buf, count, DMA_TO_DEVICE);
+	dma_src = dma_map_single(dev, buf, count, DMA_TO_DEVICE);
 	dma_dst = c->phys_base + bram_offset;
-	if (dma_mapping_error(&c->pdev->dev, dma_src)) {
-		dev_err(&c->pdev->dev,
-			"Couldn't DMA map a %d byte buffer\n",
-			count);
-		return -1;
-	}
-
-	ret = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
-	dma_unmap_single(&c->pdev->dev, dma_src, count, DMA_TO_DEVICE);
-
-	if (ret) {
-		dev_err(&c->pdev->dev, "timeout waiting for DMA\n");
+	if (dma_mapping_error(dev, dma_src)) {
+		dev_err(dev, "Couldn't DMA map a %d byte buffer\n", count);
 		goto out_copy;
 	}
 
-	return 0;
+	err = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
+	dma_unmap_page(dev, dma_src, count, DMA_TO_DEVICE);
+	if (!err)
+		return 0;
+
+	dev_err(dev, "timeout waiting for DMA\n");
 
 out_copy:
 	memcpy(this->base + bram_offset, buf, count);
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index d8c8c9d1e640..d721f489b38b 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -394,12 +394,13 @@ static int cafe_nand_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 
 		for (i=0; i<8; i+=2) {
 			uint32_t tmp = cafe_readl(cafe, NAND_ECC_SYN01 + (i*2));
-			syn[i] = cafe->rs->index_of[tmp & 0xfff];
-			syn[i+1] = cafe->rs->index_of[(tmp >> 16) & 0xfff];
+
+			syn[i] = cafe->rs->codec->index_of[tmp & 0xfff];
+			syn[i+1] = cafe->rs->codec->index_of[(tmp >> 16) & 0xfff];
 		}
 
 		n = decode_rs16(cafe->rs, NULL, NULL, 1367, syn, 0, pos, 0,
-		                pat);
+				pat);
 
 		for (i = 0; i < n; i++) {
 			int p = pos[i];
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 86a258de0b75..2b7b2b982b77 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -66,6 +66,7 @@ struct doc_priv {
 	int curchip;
 	int mh0_page;
 	int mh1_page;
+	struct rs_control *rs_decoder;
 	struct mtd_info *nextdoc;
 
 	/* Handle the last stage of initialization (BBT scan, partitioning) */
@@ -123,9 +124,6 @@ MODULE_PARM_DESC(doc_config_location, "Physical memory address at which to probe
 /* Number of symbols */
 #define NN 1023
 
-/* the Reed Solomon control structure */
-static struct rs_control *rs_decoder;
-
 /*
  * The HW decoder in the DoC ASIC's provides us a error syndrome,
  * which we must convert to a standard syndrome usable by the generic
@@ -140,6 +138,7 @@ static int doc_ecc_decode(struct rs_control *rs, uint8_t *data, uint8_t *ecc)
 	int i, j, nerr, errpos[8];
 	uint8_t parity;
 	uint16_t ds[4], s[5], tmp, errval[8], syn[4];
+	struct rs_codec *cd = rs->codec;
 
 	memset(syn, 0, sizeof(syn));
 	/* Convert the ecc bytes into words */
@@ -160,15 +159,15 @@ static int doc_ecc_decode(struct rs_control *rs, uint8_t *data, uint8_t *ecc)
 	for (j = 1; j < NROOTS; j++) {
 		if (ds[j] == 0)
 			continue;
-		tmp = rs->index_of[ds[j]];
+		tmp = cd->index_of[ds[j]];
 		for (i = 0; i < NROOTS; i++)
-			s[i] ^= rs->alpha_to[rs_modnn(rs, tmp + (FCR + i) * j)];
+			s[i] ^= cd->alpha_to[rs_modnn(cd, tmp + (FCR + i) * j)];
 	}
 
 	/* Calc syn[i] = s[i] / alpha^(v + i) */
 	for (i = 0; i < NROOTS; i++) {
 		if (s[i])
-			syn[i] = rs_modnn(rs, rs->index_of[s[i]] + (NN - FCR - i));
+			syn[i] = rs_modnn(cd, cd->index_of[s[i]] + (NN - FCR - i));
 	}
 	/* Call the decoder library */
 	nerr = decode_rs16(rs, NULL, NULL, 1019, syn, 0, errpos, 0, errval);
@@ -930,7 +929,7 @@ static int doc200x_correct_data(struct mtd_info *mtd, u_char *dat,
 				calc_ecc[i] = ReadDOC_(docptr, DoC_ECCSyndrome0 + i);
 		}
 
-		ret = doc_ecc_decode(rs_decoder, dat, calc_ecc);
+		ret = doc_ecc_decode(doc->rs_decoder, dat, calc_ecc);
 		if (ret > 0)
 			pr_err("doc200x_correct_data corrected %d errors\n",
 			       ret);
@@ -1421,10 +1420,10 @@ static inline int __init doc2001plus_init(struct mtd_info *mtd)
 
 static int __init doc_probe(unsigned long physadr)
 {
+	struct nand_chip *nand = NULL;
+	struct doc_priv *doc = NULL;
 	unsigned char ChipID;
 	struct mtd_info *mtd;
-	struct nand_chip *nand;
-	struct doc_priv *doc;
 	void __iomem *virtadr;
 	unsigned char save_control;
 	unsigned char tmp, tmpb, tmpc;
@@ -1561,8 +1560,25 @@ static int __init doc_probe(unsigned long physadr)
 		goto fail;
 	}
 
+
+	/*
+	 * Allocate a RS codec instance
+	 *
+	 * Symbolsize is 10 (bits)
+	 * Primitve polynomial is x^10+x^3+1
+	 * First consecutive root is 510
+	 * Primitve element to generate roots = 1
+	 * Generator polinomial degree = 4
+	 */
+	doc = (struct doc_priv *) (nand + 1);
+	doc->rs_decoder = init_rs(10, 0x409, FCR, 1, NROOTS);
+	if (!doc->rs_decoder) {
+		pr_err("DiskOnChip: Could not create a RS codec\n");
+		ret = -ENOMEM;
+		goto fail;
+	}
+
 	mtd			= nand_to_mtd(nand);
-	doc			= (struct doc_priv *) (nand + 1);
 	nand->bbt_td		= (struct nand_bbt_descr *) (doc + 1);
 	nand->bbt_md		= nand->bbt_td + 1;
 
@@ -1612,7 +1628,6 @@ static int __init doc_probe(unsigned long physadr)
 		   haven't yet added it.  This is handled without incident by
 		   mtd_device_unregister, as far as I can tell. */
 		nand_release(mtd);
-		kfree(nand);
 		goto fail;
 	}
 
@@ -1625,6 +1640,9 @@ static int __init doc_probe(unsigned long physadr)
 	   actually a DiskOnChip.  */
 	WriteDOC(save_control, virtadr, DOCControl);
  fail:
+	if (doc)
+		free_rs(doc->rs_decoder);
+	kfree(nand);
 	iounmap(virtadr);
 
 error_ioremap:
@@ -1647,6 +1665,7 @@ static void release_nanddoc(void)
 		nand_release(mtd);
 		iounmap(doc->virtadr);
 		release_mem_region(doc->physadr, DOC_IOREMAP_LEN);
+		free_rs(doc->rs_decoder);
 		kfree(nand);
 	}
 }
@@ -1655,27 +1674,12 @@ static int __init init_nanddoc(void)
 {
 	int i, ret = 0;
 
-	/* We could create the decoder on demand, if memory is a concern.
-	 * This way we have it handy, if an error happens
-	 *
-	 * Symbolsize is 10 (bits)
-	 * Primitve polynomial is x^10+x^3+1
-	 * first consecutive root is 510
-	 * primitve element to generate roots = 1
-	 * generator polinomial degree = 4
-	 */
-	rs_decoder = init_rs(10, 0x409, FCR, 1, NROOTS);
-	if (!rs_decoder) {
-		pr_err("DiskOnChip: Could not create a RS decoder\n");
-		return -ENOMEM;
-	}
-
 	if (doc_config_location) {
 		pr_info("Using configured DiskOnChip probe address 0x%lx\n",
 			doc_config_location);
 		ret = doc_probe(doc_config_location);
 		if (ret < 0)
-			goto outerr;
+			return ret;
 	} else {
 		for (i = 0; (doc_locations[i] != 0xffffffff); i++) {
 			doc_probe(doc_locations[i]);
@@ -1686,11 +1690,7 @@ static int __init init_nanddoc(void)
 	if (!doclist) {
 		pr_info("No valid DiskOnChip devices found\n");
 		ret = -ENODEV;
-		goto outerr;
 	}
-	return 0;
- outerr:
-	free_rs(rs_decoder);
 	return ret;
 }
 
@@ -1698,11 +1698,6 @@ static void __exit cleanup_nanddoc(void)
 {
 	/* Cleanup the nand/DoC resources */
 	release_nanddoc();
-
-	/* Free the reed solomon resources */
-	if (rs_decoder) {
-		free_rs(rs_decoder);
-	}
 }
 
 module_init(init_nanddoc);
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index 10e953218948..ebb1d141b900 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -1074,7 +1074,7 @@ static int marvell_nfc_hw_ecc_hmg_do_write_page(struct nand_chip *chip,
 		return ret;
 
 	ret = marvell_nfc_wait_op(chip,
-				  chip->data_interface.timings.sdr.tPROG_max);
+				  PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max));
 	return ret;
 }
 
@@ -1194,11 +1194,13 @@ static void marvell_nfc_hw_ecc_bch_read_chunk(struct nand_chip *chip, int chunk,
 				  NDCB0_CMD2(NAND_CMD_READSTART);
 
 	/*
-	 * Trigger the naked read operation only on the last chunk.
-	 * Otherwise, use monolithic read.
+	 * Trigger the monolithic read on the first chunk, then naked read on
+	 * intermediate chunks and finally a last naked read on the last chunk.
 	 */
-	if (lt->nchunks == 1 || (chunk < lt->nchunks - 1))
+	if (chunk == 0)
 		nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW);
+	else if (chunk < lt->nchunks - 1)
+		nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_NAKED_RW);
 	else
 		nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_LAST_NAKED_RW);
 
@@ -1408,6 +1410,7 @@ marvell_nfc_hw_ecc_bch_write_chunk(struct nand_chip *chip, int chunk,
 	struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
 	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
 	const struct marvell_hw_ecc_layout *lt = to_marvell_nand(chip)->layout;
+	u32 xtype;
 	int ret;
 	struct marvell_nfc_op nfc_op = {
 		.ndcb[0] = NDCB0_CMD_TYPE(TYPE_WRITE) | NDCB0_LEN_OVRD,
@@ -1423,7 +1426,12 @@ marvell_nfc_hw_ecc_bch_write_chunk(struct nand_chip *chip, int chunk,
 	 * last naked write.
 	 */
 	if (chunk == 0) {
-		nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_WRITE_DISPATCH) |
+		if (lt->nchunks == 1)
+			xtype = XTYPE_MONOLITHIC_RW;
+		else
+			xtype = XTYPE_WRITE_DISPATCH;
+
+		nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(xtype) |
 				  NDCB0_ADDR_CYC(marvell_nand->addr_cyc) |
 				  NDCB0_CMD1(NAND_CMD_SEQIN);
 		nfc_op.ndcb[1] |= NDCB1_ADDRS_PAGE(page);
@@ -1494,7 +1502,7 @@ static int marvell_nfc_hw_ecc_bch_write_page(struct mtd_info *mtd,
 	}
 
 	ret = marvell_nfc_wait_op(chip,
-				  chip->data_interface.timings.sdr.tPROG_max);
+				  PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max));
 
 	marvell_nfc_disable_hw_ecc(chip);
 
@@ -2299,29 +2307,20 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	/*
 	 * The legacy "num-cs" property indicates the number of CS on the only
 	 * chip connected to the controller (legacy bindings does not support
-	 * more than one chip). CS are only incremented one by one while the RB
-	 * pin is always the #0.
+	 * more than one chip). The CS and RB pins are always the #0.
 	 *
 	 * When not using legacy bindings, a couple of "reg" and "nand-rb"
 	 * properties must be filled. For each chip, expressed as a subnode,
 	 * "reg" points to the CS lines and "nand-rb" to the RB line.
 	 */
-	if (pdata) {
+	if (pdata || nfc->caps->legacy_of_bindings) {
 		nsels = 1;
-	} else if (nfc->caps->legacy_of_bindings &&
-		   !of_get_property(np, "num-cs", &nsels)) {
-		dev_err(dev, "missing num-cs property\n");
-		return -EINVAL;
-	} else if (!of_get_property(np, "reg", &nsels)) {
-		dev_err(dev, "missing reg property\n");
-		return -EINVAL;
-	}
-
-	if (!pdata)
-		nsels /= sizeof(u32);
-	if (!nsels) {
-		dev_err(dev, "invalid reg property size\n");
-		return -EINVAL;
+	} else {
+		nsels = of_property_count_elems_of_size(np, "reg", sizeof(u32));
+		if (nsels <= 0) {
+			dev_err(dev, "missing/invalid reg property\n");
+			return -EINVAL;
+		}
 	}
 
 	/* Alloc the nand chip structure */
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 72f3a89da513..f28c3a555861 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -706,12 +706,17 @@ static void nand_wait_status_ready(struct mtd_info *mtd, unsigned long timeo)
  */
 int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms)
 {
+	const struct nand_sdr_timings *timings;
 	u8 status = 0;
 	int ret;
 
 	if (!chip->exec_op)
 		return -ENOTSUPP;
 
+	/* Wait tWB before polling the STATUS reg. */
+	timings = nand_get_sdr_timings(&chip->data_interface);
+	ndelay(PSEC_TO_NSEC(timings->tWB_max));
+
 	ret = nand_status_op(chip, NULL);
 	if (ret)
 		return ret;
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index f54518ffb36a..f2052fae21c7 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -645,7 +645,7 @@ static int tango_nand_probe(struct platform_device *pdev)
 
 	writel_relaxed(MODE_RAW, nfc->pbus_base + PBUS_PAD_MODE);
 
-	clk = clk_get(&pdev->dev, NULL);
+	clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index 4b8e9183489a..5872f31eaa60 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -501,7 +501,9 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, u8 *rxbuf,
 	void __iomem *reg_base = cqspi->iobase;
 	void __iomem *ahb_base = cqspi->ahb_base;
 	unsigned int remaining = n_rx;
+	unsigned int mod_bytes = n_rx % 4;
 	unsigned int bytes_to_read = 0;
+	u8 *rxbuf_end = rxbuf + n_rx;
 	int ret = 0;
 
 	writel(from_addr, reg_base + CQSPI_REG_INDIRECTRDSTARTADDR);
@@ -530,11 +532,24 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, u8 *rxbuf,
 		}
 
 		while (bytes_to_read != 0) {
+			unsigned int word_remain = round_down(remaining, 4);
+
 			bytes_to_read *= cqspi->fifo_width;
 			bytes_to_read = bytes_to_read > remaining ?
 					remaining : bytes_to_read;
-			ioread32_rep(ahb_base, rxbuf,
-				     DIV_ROUND_UP(bytes_to_read, 4));
+			bytes_to_read = round_down(bytes_to_read, 4);
+			/* Read 4 byte word chunks then single bytes */
+			if (bytes_to_read) {
+				ioread32_rep(ahb_base, rxbuf,
+					     (bytes_to_read / 4));
+			} else if (!word_remain && mod_bytes) {
+				unsigned int temp = ioread32(ahb_base);
+
+				bytes_to_read = mod_bytes;
+				memcpy(rxbuf, &temp, min((unsigned int)
+							 (rxbuf_end - rxbuf),
+							 bytes_to_read));
+			}
 			rxbuf += bytes_to_read;
 			remaining -= bytes_to_read;
 			bytes_to_read = cqspi_get_rd_sram_level(cqspi);
diff --git a/drivers/mux/adg792a.c b/drivers/mux/adg792a.c
index 6a8725cf3d71..e8fc2fc1ab09 100644
--- a/drivers/mux/adg792a.c
+++ b/drivers/mux/adg792a.c
@@ -58,8 +58,7 @@ static const struct mux_control_ops adg792a_ops = {
 	.set = adg792a_set,
 };
 
-static int adg792a_probe(struct i2c_client *i2c,
-			 const struct i2c_device_id *id)
+static int adg792a_probe(struct i2c_client *i2c)
 {
 	struct device *dev = &i2c->dev;
 	struct mux_chip *mux_chip;
@@ -144,7 +143,7 @@ static struct i2c_driver adg792a_driver = {
 		.name		= "adg792a",
 		.of_match_table = of_match_ptr(adg792a_of_match),
 	},
-	.probe		= adg792a_probe,
+	.probe_new	= adg792a_probe,
 	.id_table	= adg792a_id,
 };
 module_i2c_driver(adg792a_driver);
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 1ed9529e7bd1..5eb0df2e5464 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -450,7 +450,7 @@ static void rlb_update_client(struct rlb_client_info *client_info)
 {
 	int i;
 
-	if (!client_info->slave)
+	if (!client_info->slave || !is_valid_ether_addr(client_info->mac_dst))
 		return;
 
 	for (i = 0; i < RLB_ARP_BURST_SIZE; i++) {
@@ -943,6 +943,10 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = slave->dev;
 
+	netdev_dbg(slave->bond->dev,
+		   "Send learning packet: dev %s mac %pM vlan %d\n",
+		   slave->dev->name, mac_addr, vid);
+
 	if (vid)
 		__vlan_hwaccel_put_tag(skb, vlan_proto, vid);
 
@@ -965,14 +969,13 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data)
 	u8 *mac_addr = data->mac_addr;
 	struct bond_vlan_tag *tags;
 
-	if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
-		if (strict_match &&
-		    ether_addr_equal_64bits(mac_addr,
-					    upper->dev_addr)) {
+	if (is_vlan_dev(upper) &&
+	    bond->nest_level == vlan_get_encap_level(upper) - 1) {
+		if (upper->addr_assign_type == NET_ADDR_STOLEN) {
 			alb_send_lp_vid(slave, mac_addr,
 					vlan_dev_vlan_proto(upper),
 					vlan_dev_vlan_id(upper));
-		} else if (!strict_match) {
+		} else {
 			alb_send_lp_vid(slave, upper->dev_addr,
 					vlan_dev_vlan_proto(upper),
 					vlan_dev_vlan_id(upper));
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b7b113018853..1f1e97b26f95 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1660,8 +1660,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	} /* switch(bond_mode) */
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	slave_dev->npinfo = bond->dev->npinfo;
-	if (slave_dev->npinfo) {
+	if (bond->dev->npinfo) {
 		if (slave_enable_netpoll(new_slave)) {
 			netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
 			res = -EBUSY;
@@ -1739,6 +1738,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	if (bond_mode_uses_xmit_hash(bond))
 		bond_update_slave_arr(bond, NULL);
 
+	bond->nest_level = dev_get_nest_level(bond_dev);
+
 	netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
 		    slave_dev->name,
 		    bond_is_active_slave(new_slave) ? "an active" : "a backup",
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index 01059f1a7bca..9f7d83e827c3 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -10,7 +10,7 @@
 static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
-	struct bonding *bond = seq->private;
+	struct bonding *bond = PDE_DATA(file_inode(seq->file));
 	struct list_head *iter;
 	struct slave *slave;
 	loff_t off = 0;
@@ -29,7 +29,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
 
 static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct bonding *bond = seq->private;
+	struct bonding *bond = PDE_DATA(file_inode(seq->file));
 	struct list_head *iter;
 	struct slave *slave;
 	bool found = false;
@@ -56,7 +56,7 @@ static void bond_info_seq_stop(struct seq_file *seq, void *v)
 
 static void bond_info_show_master(struct seq_file *seq)
 {
-	struct bonding *bond = seq->private;
+	struct bonding *bond = PDE_DATA(file_inode(seq->file));
 	const struct bond_opt_value *optval;
 	struct slave *curr, *primary;
 	int i;
@@ -167,7 +167,7 @@ static void bond_info_show_master(struct seq_file *seq)
 static void bond_info_show_slave(struct seq_file *seq,
 				 const struct slave *slave)
 {
-	struct bonding *bond = seq->private;
+	struct bonding *bond = PDE_DATA(file_inode(seq->file));
 
 	seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name);
 	seq_printf(seq, "MII Status: %s\n", bond_slave_link_status(slave->link));
@@ -257,38 +257,14 @@ static const struct seq_operations bond_info_seq_ops = {
 	.show  = bond_info_seq_show,
 };
 
-static int bond_info_open(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq;
-	int res;
-
-	res = seq_open(file, &bond_info_seq_ops);
-	if (!res) {
-		/* recover the pointer buried in proc_dir_entry data */
-		seq = file->private_data;
-		seq->private = PDE_DATA(inode);
-	}
-
-	return res;
-}
-
-static const struct file_operations bond_info_fops = {
-	.owner   = THIS_MODULE,
-	.open    = bond_info_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-};
-
 void bond_create_proc_entry(struct bonding *bond)
 {
 	struct net_device *bond_dev = bond->dev;
 	struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
 
 	if (bn->proc_dir) {
-		bond->proc_entry = proc_create_data(bond_dev->name,
-						    0444, bn->proc_dir,
-						    &bond_info_fops, bond);
+		bond->proc_entry = proc_create_seq_data(bond_dev->name, 0444,
+				bn->proc_dir, &bond_info_seq_ops, bond);
 		if (bond->proc_entry == NULL)
 			netdev_warn(bond_dev, "Cannot create /proc/net/%s/%s\n",
 				    DRV_NAME, bond_dev->name);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index b1779566c5bb..3c71f1cb205f 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -605,7 +605,7 @@ void can_bus_off(struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
 
-	netdev_dbg(dev, "bus-off\n");
+	netdev_info(dev, "bus-off\n");
 
 	netif_carrier_off(dev);
 
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 634c51e6b8ae..d53a45bf2a72 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -200,6 +200,7 @@
 #define FLEXCAN_QUIRK_DISABLE_MECR	BIT(4) /* Disable Memory error detection */
 #define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP	BIT(5) /* Use timestamp based offloading */
 #define FLEXCAN_QUIRK_BROKEN_PERR_STATE	BIT(6) /* No interrupt for error passive */
+#define FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN	BIT(7) /* default to BE register access */
 
 /* Structure of the message buffer */
 struct flexcan_mb {
@@ -288,6 +289,12 @@ struct flexcan_priv {
 
 static const struct flexcan_devtype_data fsl_p1010_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
+		FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+		FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN,
+};
+
+static const struct flexcan_devtype_data fsl_imx25_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
 		FLEXCAN_QUIRK_BROKEN_PERR_STATE,
 };
 
@@ -1251,9 +1258,9 @@ static void unregister_flexcandev(struct net_device *dev)
 static const struct of_device_id flexcan_of_match[] = {
 	{ .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, },
 	{ .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
-	{ .compatible = "fsl,imx53-flexcan", .data = &fsl_p1010_devtype_data, },
-	{ .compatible = "fsl,imx35-flexcan", .data = &fsl_p1010_devtype_data, },
-	{ .compatible = "fsl,imx25-flexcan", .data = &fsl_p1010_devtype_data, },
+	{ .compatible = "fsl,imx53-flexcan", .data = &fsl_imx25_devtype_data, },
+	{ .compatible = "fsl,imx35-flexcan", .data = &fsl_imx25_devtype_data, },
+	{ .compatible = "fsl,imx25-flexcan", .data = &fsl_imx25_devtype_data, },
 	{ .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, },
 	{ .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, },
 	{ .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, },
@@ -1337,18 +1344,13 @@ static int flexcan_probe(struct platform_device *pdev)
 
 	priv = netdev_priv(dev);
 
-	if (of_property_read_bool(pdev->dev.of_node, "big-endian")) {
+	if (of_property_read_bool(pdev->dev.of_node, "big-endian") ||
+	    devtype_data->quirks & FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN) {
 		priv->read = flexcan_read_be;
 		priv->write = flexcan_write_be;
 	} else {
-		if (of_device_is_compatible(pdev->dev.of_node,
-					    "fsl,p1010-flexcan")) {
-			priv->read = flexcan_read_be;
-			priv->write = flexcan_write_be;
-		} else {
-			priv->read = flexcan_read_le;
-			priv->write = flexcan_write_le;
-		}
+		priv->read = flexcan_read_le;
+		priv->write = flexcan_write_le;
 	}
 
 	priv->can.clock.freq = clock_freq;
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index 5590c559a8ca..53e320c92a8b 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -91,6 +91,7 @@
 #define HI3110_STAT_BUSOFF BIT(2)
 #define HI3110_STAT_ERRP BIT(3)
 #define HI3110_STAT_ERRW BIT(4)
+#define HI3110_STAT_TXMTY BIT(7)
 
 #define HI3110_BTR0_SJW_SHIFT 6
 #define HI3110_BTR0_BRP_SHIFT 0
@@ -427,8 +428,10 @@ static int hi3110_get_berr_counter(const struct net_device *net,
 	struct hi3110_priv *priv = netdev_priv(net);
 	struct spi_device *spi = priv->spi;
 
+	mutex_lock(&priv->hi3110_lock);
 	bec->txerr = hi3110_read(spi, HI3110_READ_TEC);
 	bec->rxerr = hi3110_read(spi, HI3110_READ_REC);
+	mutex_unlock(&priv->hi3110_lock);
 
 	return 0;
 }
@@ -735,10 +738,7 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
 			}
 		}
 
-		if (intf == 0)
-			break;
-
-		if (intf & HI3110_INT_TXCPLT) {
+		if (priv->tx_len && statf & HI3110_STAT_TXMTY) {
 			net->stats.tx_packets++;
 			net->stats.tx_bytes += priv->tx_len - 1;
 			can_led_event(net, CAN_LED_EVENT_TX);
@@ -748,6 +748,9 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
 			}
 			netif_wake_queue(net);
 		}
+
+		if (intf == 0)
+			break;
 	}
 	mutex_unlock(&priv->hi3110_lock);
 	return IRQ_HANDLED;
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 63587b8e6825..daed57d3d209 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -1179,7 +1179,7 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
 
 	skb = alloc_can_skb(priv->netdev, &cf);
 	if (!skb) {
-		stats->tx_dropped++;
+		stats->rx_dropped++;
 		return;
 	}
 
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 78616787f2a3..3da5fca77cbd 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1712,6 +1712,18 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.duplex_reg = B53_DUPLEX_STAT_FE,
 	},
 	{
+		.chip_id = BCM5389_DEVICE_ID,
+		.dev_name = "BCM5389",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
 		.chip_id = BCM5395_DEVICE_ID,
 		.dev_name = "BCM5395",
 		.vlans = 4096,
@@ -2034,6 +2046,7 @@ int b53_switch_detect(struct b53_device *dev)
 		else
 			dev->chip_id = BCM5365_DEVICE_ID;
 		break;
+	case BCM5389_DEVICE_ID:
 	case BCM5395_DEVICE_ID:
 	case BCM5397_DEVICE_ID:
 	case BCM5398_DEVICE_ID:
diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c
index fa7556f5d4fb..a533a90e3904 100644
--- a/drivers/net/dsa/b53/b53_mdio.c
+++ b/drivers/net/dsa/b53/b53_mdio.c
@@ -285,6 +285,7 @@ static const struct b53_io_ops b53_mdio_ops = {
 #define B53_BRCM_OUI_1	0x0143bc00
 #define B53_BRCM_OUI_2	0x03625c00
 #define B53_BRCM_OUI_3	0x00406000
+#define B53_BRCM_OUI_4	0x01410c00
 
 static int b53_mdio_probe(struct mdio_device *mdiodev)
 {
@@ -311,7 +312,8 @@ static int b53_mdio_probe(struct mdio_device *mdiodev)
 	 */
 	if ((phy_id & 0xfffffc00) != B53_BRCM_OUI_1 &&
 	    (phy_id & 0xfffffc00) != B53_BRCM_OUI_2 &&
-	    (phy_id & 0xfffffc00) != B53_BRCM_OUI_3) {
+	    (phy_id & 0xfffffc00) != B53_BRCM_OUI_3 &&
+	    (phy_id & 0xfffffc00) != B53_BRCM_OUI_4) {
 		dev_err(&mdiodev->dev, "Unsupported device: 0x%08x\n", phy_id);
 		return -ENODEV;
 	}
@@ -360,6 +362,7 @@ static const struct of_device_id b53_of_match[] = {
 	{ .compatible = "brcm,bcm53125" },
 	{ .compatible = "brcm,bcm53128" },
 	{ .compatible = "brcm,bcm5365" },
+	{ .compatible = "brcm,bcm5389" },
 	{ .compatible = "brcm,bcm5395" },
 	{ .compatible = "brcm,bcm5397" },
 	{ .compatible = "brcm,bcm5398" },
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 1187ebd79287..3b57f47d0e79 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -48,6 +48,7 @@ struct b53_io_ops {
 enum {
 	BCM5325_DEVICE_ID = 0x25,
 	BCM5365_DEVICE_ID = 0x65,
+	BCM5389_DEVICE_ID = 0x89,
 	BCM5395_DEVICE_ID = 0x95,
 	BCM5397_DEVICE_ID = 0x97,
 	BCM5398_DEVICE_ID = 0x98,
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 23b45da784cb..b89acaee12d4 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -354,10 +354,13 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port,
 	/* Locate the first rule available */
 	if (fs->location == RX_CLS_LOC_ANY)
 		rule_index = find_first_zero_bit(priv->cfp.used,
-						 bcm_sf2_cfp_rule_size(priv));
+						 priv->num_cfp_rules);
 	else
 		rule_index = fs->location;
 
+	if (rule_index > bcm_sf2_cfp_rule_size(priv))
+		return -ENOSPC;
+
 	layout = &udf_tcpip4_layout;
 	/* We only use one UDF slice for now */
 	slice_num = bcm_sf2_get_slice_number(layout, 0);
@@ -562,19 +565,21 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 	 * first half because the HW search is by incrementing addresses.
 	 */
 	if (fs->location == RX_CLS_LOC_ANY)
-		rule_index[0] = find_first_zero_bit(priv->cfp.used,
-						    bcm_sf2_cfp_rule_size(priv));
+		rule_index[1] = find_first_zero_bit(priv->cfp.used,
+						    priv->num_cfp_rules);
 	else
-		rule_index[0] = fs->location;
+		rule_index[1] = fs->location;
+	if (rule_index[1] > bcm_sf2_cfp_rule_size(priv))
+		return -ENOSPC;
 
 	/* Flag it as used (cleared on error path) such that we can immediately
 	 * obtain a second one to chain from.
 	 */
-	set_bit(rule_index[0], priv->cfp.used);
+	set_bit(rule_index[1], priv->cfp.used);
 
-	rule_index[1] = find_first_zero_bit(priv->cfp.used,
-					    bcm_sf2_cfp_rule_size(priv));
-	if (rule_index[1] > bcm_sf2_cfp_rule_size(priv)) {
+	rule_index[0] = find_first_zero_bit(priv->cfp.used,
+					    priv->num_cfp_rules);
+	if (rule_index[0] > bcm_sf2_cfp_rule_size(priv)) {
 		ret = -ENOSPC;
 		goto out_err;
 	}
@@ -712,14 +717,14 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 	/* Flag the second half rule as being used now, return it as the
 	 * location, and flag it as unique while dumping rules
 	 */
-	set_bit(rule_index[1], priv->cfp.used);
+	set_bit(rule_index[0], priv->cfp.used);
 	set_bit(rule_index[1], priv->cfp.unique);
 	fs->location = rule_index[1];
 
 	return ret;
 
 out_err:
-	clear_bit(rule_index[0], priv->cfp.used);
+	clear_bit(rule_index[1], priv->cfp.used);
 	return ret;
 }
 
@@ -785,10 +790,6 @@ static int bcm_sf2_cfp_rule_del_one(struct bcm_sf2_priv *priv, int port,
 	int ret;
 	u32 reg;
 
-	/* Refuse deletion of unused rules, and the default reserved rule */
-	if (!test_bit(loc, priv->cfp.used) || loc == 0)
-		return -EINVAL;
-
 	/* Indicate which rule we want to read */
 	bcm_sf2_cfp_rule_addr_set(priv, loc);
 
@@ -826,6 +827,13 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	u32 next_loc = 0;
 	int ret;
 
+	/* Refuse deleting unused rules, and those that are not unique since
+	 * that could leave IPv6 rules with one of the chained rule in the
+	 * table.
+	 */
+	if (!test_bit(loc, priv->cfp.unique) || loc == 0)
+		return -EINVAL;
+
 	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
 	if (ret)
 		return ret;
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 3d2091099f7f..5b4374f21d76 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3370,6 +3370,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3391,6 +3392,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 0,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3410,6 +3412,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 8,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3431,6 +3434,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3452,6 +3456,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 0,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3472,6 +3477,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 11,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
@@ -3493,6 +3499,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3514,6 +3521,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 0,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3535,6 +3543,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3557,6 +3566,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 15,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3578,6 +3588,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3600,6 +3611,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 15,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3621,6 +3633,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 0,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3641,6 +3654,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
@@ -3663,6 +3677,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
@@ -3684,6 +3699,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 11,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
@@ -3707,6 +3723,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 15,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3730,6 +3747,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
@@ -3753,6 +3771,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 15,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3776,6 +3795,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 15,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3798,6 +3818,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 11,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
@@ -3820,6 +3841,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3841,6 +3863,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3863,6 +3886,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 15,
 		.max_vid = 4095,
 		.port_base_addr = 0x10,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 15000,
@@ -3885,6 +3909,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
@@ -3907,6 +3932,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
+		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 80490f66bc06..12b7f4649b25 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -114,6 +114,7 @@ struct mv88e6xxx_info {
 	unsigned int num_gpio;
 	unsigned int max_vid;
 	unsigned int port_base_addr;
+	unsigned int phy_base_addr;
 	unsigned int global1_addr;
 	unsigned int global2_addr;
 	unsigned int age_time_coeff;
diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index 0ce627fded48..8d22d66d84b7 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -1118,7 +1118,7 @@ int mv88e6xxx_g2_irq_mdio_setup(struct mv88e6xxx_chip *chip,
 			err = irq;
 			goto out;
 		}
-		bus->irq[chip->info->port_base_addr + phy] = irq;
+		bus->irq[chip->info->phy_base_addr + phy] = irq;
 	}
 	return 0;
 out:
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index ac7694c71266..a036c490b7ce 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -285,10 +285,18 @@ static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip,
 			       struct sk_buff_head *rxq)
 {
 	u16 buf[4] = { 0 }, status, seq_id;
-	u64 ns, timelo, timehi;
 	struct skb_shared_hwtstamps *shwt;
+	struct sk_buff_head received;
+	u64 ns, timelo, timehi;
+	unsigned long flags;
 	int err;
 
+	/* The latched timestamp belongs to one of the received frames. */
+	__skb_queue_head_init(&received);
+	spin_lock_irqsave(&rxq->lock, flags);
+	skb_queue_splice_tail_init(rxq, &received);
+	spin_unlock_irqrestore(&rxq->lock, flags);
+
 	mutex_lock(&chip->reg_lock);
 	err = mv88e6xxx_port_ptp_read(chip, ps->port_id,
 				      reg, buf, ARRAY_SIZE(buf));
@@ -311,7 +319,7 @@ static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip,
 	/* Since the device can only handle one time stamp at a time,
 	 * we purge any extra frames from the queue.
 	 */
-	for ( ; skb; skb = skb_dequeue(rxq)) {
+	for ( ; skb; skb = __skb_dequeue(&received)) {
 		if (mv88e6xxx_ts_valid(status) && seq_match(skb, seq_id)) {
 			ns = timehi << 16 | timelo;
 
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 36c8950dbd2d..176861bd2252 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1212,9 +1212,9 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
 	vp->mii.reg_num_mask = 0x1f;
 
 	/* Makes sure rings are at least 16 byte aligned. */
-	vp->rx_ring = pci_alloc_consistent(pdev, sizeof(struct boom_rx_desc) * RX_RING_SIZE
+	vp->rx_ring = dma_alloc_coherent(gendev, sizeof(struct boom_rx_desc) * RX_RING_SIZE
 					   + sizeof(struct boom_tx_desc) * TX_RING_SIZE,
-					   &vp->rx_ring_dma);
+					   &vp->rx_ring_dma, GFP_KERNEL);
 	retval = -ENOMEM;
 	if (!vp->rx_ring)
 		goto free_device;
@@ -1476,11 +1476,10 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
 		return 0;
 
 free_ring:
-	pci_free_consistent(pdev,
-						sizeof(struct boom_rx_desc) * RX_RING_SIZE
-							+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
-						vp->rx_ring,
-						vp->rx_ring_dma);
+	dma_free_coherent(&pdev->dev,
+		sizeof(struct boom_rx_desc) * RX_RING_SIZE +
+		sizeof(struct boom_tx_desc) * TX_RING_SIZE,
+		vp->rx_ring, vp->rx_ring_dma);
 free_device:
 	free_netdev(dev);
 	pr_err(PFX "vortex_probe1 fails.  Returns %d\n", retval);
@@ -1751,9 +1750,9 @@ vortex_open(struct net_device *dev)
 				break;			/* Bad news!  */
 
 			skb_reserve(skb, NET_IP_ALIGN);	/* Align IP on 16 byte boundaries */
-			dma = pci_map_single(VORTEX_PCI(vp), skb->data,
-					     PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
-			if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma))
+			dma = dma_map_single(vp->gendev, skb->data,
+					     PKT_BUF_SZ, DMA_FROM_DEVICE);
+			if (dma_mapping_error(vp->gendev, dma))
 				break;
 			vp->rx_ring[i].addr = cpu_to_le32(dma);
 		}
@@ -2067,9 +2066,9 @@ vortex_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (vp->bus_master) {
 		/* Set the bus-master controller to transfer the packet. */
 		int len = (skb->len + 3) & ~3;
-		vp->tx_skb_dma = pci_map_single(VORTEX_PCI(vp), skb->data, len,
-						PCI_DMA_TODEVICE);
-		if (dma_mapping_error(&VORTEX_PCI(vp)->dev, vp->tx_skb_dma)) {
+		vp->tx_skb_dma = dma_map_single(vp->gendev, skb->data, len,
+						DMA_TO_DEVICE);
+		if (dma_mapping_error(vp->gendev, vp->tx_skb_dma)) {
 			dev_kfree_skb_any(skb);
 			dev->stats.tx_dropped++;
 			return NETDEV_TX_OK;
@@ -2168,9 +2167,9 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			vp->tx_ring[entry].status = cpu_to_le32(skb->len | TxIntrUploaded | AddTCPChksum | AddUDPChksum);
 
 	if (!skb_shinfo(skb)->nr_frags) {
-		dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data, skb->len,
-					  PCI_DMA_TODEVICE);
-		if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+		dma_addr = dma_map_single(vp->gendev, skb->data, skb->len,
+					  DMA_TO_DEVICE);
+		if (dma_mapping_error(vp->gendev, dma_addr))
 			goto out_dma_err;
 
 		vp->tx_ring[entry].frag[0].addr = cpu_to_le32(dma_addr);
@@ -2178,9 +2177,9 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 		int i;
 
-		dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data,
-					  skb_headlen(skb), PCI_DMA_TODEVICE);
-		if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+		dma_addr = dma_map_single(vp->gendev, skb->data,
+					  skb_headlen(skb), DMA_TO_DEVICE);
+		if (dma_mapping_error(vp->gendev, dma_addr))
 			goto out_dma_err;
 
 		vp->tx_ring[entry].frag[0].addr = cpu_to_le32(dma_addr);
@@ -2189,21 +2188,21 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
-			dma_addr = skb_frag_dma_map(&VORTEX_PCI(vp)->dev, frag,
+			dma_addr = skb_frag_dma_map(vp->gendev, frag,
 						    0,
 						    frag->size,
 						    DMA_TO_DEVICE);
-			if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr)) {
+			if (dma_mapping_error(vp->gendev, dma_addr)) {
 				for(i = i-1; i >= 0; i--)
-					dma_unmap_page(&VORTEX_PCI(vp)->dev,
+					dma_unmap_page(vp->gendev,
 						       le32_to_cpu(vp->tx_ring[entry].frag[i+1].addr),
 						       le32_to_cpu(vp->tx_ring[entry].frag[i+1].length),
 						       DMA_TO_DEVICE);
 
-				pci_unmap_single(VORTEX_PCI(vp),
+				dma_unmap_single(vp->gendev,
 						 le32_to_cpu(vp->tx_ring[entry].frag[0].addr),
 						 le32_to_cpu(vp->tx_ring[entry].frag[0].length),
-						 PCI_DMA_TODEVICE);
+						 DMA_TO_DEVICE);
 
 				goto out_dma_err;
 			}
@@ -2218,8 +2217,8 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 #else
-	dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data, skb->len, PCI_DMA_TODEVICE);
-	if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+	dma_addr = dma_map_single(vp->gendev, skb->data, skb->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(vp->gendev, dma_addr))
 		goto out_dma_err;
 	vp->tx_ring[entry].addr = cpu_to_le32(dma_addr);
 	vp->tx_ring[entry].length = cpu_to_le32(skb->len | LAST_FRAG);
@@ -2254,7 +2253,7 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
 out:
 	return NETDEV_TX_OK;
 out_dma_err:
-	dev_err(&VORTEX_PCI(vp)->dev, "Error mapping dma buffer\n");
+	dev_err(vp->gendev, "Error mapping dma buffer\n");
 	goto out;
 }
 
@@ -2322,7 +2321,7 @@ vortex_interrupt(int irq, void *dev_id)
 		if (status & DMADone) {
 			if (ioread16(ioaddr + Wn7_MasterStatus) & 0x1000) {
 				iowrite16(0x1000, ioaddr + Wn7_MasterStatus); /* Ack the event. */
-				pci_unmap_single(VORTEX_PCI(vp), vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, PCI_DMA_TODEVICE);
+				dma_unmap_single(vp->gendev, vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, DMA_TO_DEVICE);
 				pkts_compl++;
 				bytes_compl += vp->tx_skb->len;
 				dev_kfree_skb_irq(vp->tx_skb); /* Release the transferred buffer */
@@ -2459,19 +2458,19 @@ boomerang_interrupt(int irq, void *dev_id)
 					struct sk_buff *skb = vp->tx_skbuff[entry];
 #if DO_ZEROCOPY
 					int i;
-					pci_unmap_single(VORTEX_PCI(vp),
+					dma_unmap_single(vp->gendev,
 							le32_to_cpu(vp->tx_ring[entry].frag[0].addr),
 							le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF,
-							PCI_DMA_TODEVICE);
+							DMA_TO_DEVICE);
 
 					for (i=1; i<=skb_shinfo(skb)->nr_frags; i++)
-							pci_unmap_page(VORTEX_PCI(vp),
+							dma_unmap_page(vp->gendev,
 											 le32_to_cpu(vp->tx_ring[entry].frag[i].addr),
 											 le32_to_cpu(vp->tx_ring[entry].frag[i].length)&0xFFF,
-											 PCI_DMA_TODEVICE);
+											 DMA_TO_DEVICE);
 #else
-					pci_unmap_single(VORTEX_PCI(vp),
-						le32_to_cpu(vp->tx_ring[entry].addr), skb->len, PCI_DMA_TODEVICE);
+					dma_unmap_single(vp->gendev,
+						le32_to_cpu(vp->tx_ring[entry].addr), skb->len, DMA_TO_DEVICE);
 #endif
 					pkts_compl++;
 					bytes_compl += skb->len;
@@ -2561,14 +2560,14 @@ static int vortex_rx(struct net_device *dev)
 				/* 'skb_put()' points to the start of sk_buff data area. */
 				if (vp->bus_master &&
 					! (ioread16(ioaddr + Wn7_MasterStatus) & 0x8000)) {
-					dma_addr_t dma = pci_map_single(VORTEX_PCI(vp), skb_put(skb, pkt_len),
-									   pkt_len, PCI_DMA_FROMDEVICE);
+					dma_addr_t dma = dma_map_single(vp->gendev, skb_put(skb, pkt_len),
+									   pkt_len, DMA_FROM_DEVICE);
 					iowrite32(dma, ioaddr + Wn7_MasterAddr);
 					iowrite16((skb->len + 3) & ~3, ioaddr + Wn7_MasterLen);
 					iowrite16(StartDMAUp, ioaddr + EL3_CMD);
 					while (ioread16(ioaddr + Wn7_MasterStatus) & 0x8000)
 						;
-					pci_unmap_single(VORTEX_PCI(vp), dma, pkt_len, PCI_DMA_FROMDEVICE);
+					dma_unmap_single(vp->gendev, dma, pkt_len, DMA_FROM_DEVICE);
 				} else {
 					ioread32_rep(ioaddr + RX_FIFO,
 					             skb_put(skb, pkt_len),
@@ -2635,11 +2634,11 @@ boomerang_rx(struct net_device *dev)
 			if (pkt_len < rx_copybreak &&
 			    (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) {
 				skb_reserve(skb, 2);	/* Align IP on 16 byte boundaries */
-				pci_dma_sync_single_for_cpu(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+				dma_sync_single_for_cpu(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
 				/* 'skb_put()' points to the start of sk_buff data area. */
 				skb_put_data(skb, vp->rx_skbuff[entry]->data,
 					     pkt_len);
-				pci_dma_sync_single_for_device(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+				dma_sync_single_for_device(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
 				vp->rx_copy++;
 			} else {
 				/* Pre-allocate the replacement skb.  If it or its
@@ -2651,9 +2650,9 @@ boomerang_rx(struct net_device *dev)
 					dev->stats.rx_dropped++;
 					goto clear_complete;
 				}
-				newdma = pci_map_single(VORTEX_PCI(vp), newskb->data,
-							PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
-				if (dma_mapping_error(&VORTEX_PCI(vp)->dev, newdma)) {
+				newdma = dma_map_single(vp->gendev, newskb->data,
+							PKT_BUF_SZ, DMA_FROM_DEVICE);
+				if (dma_mapping_error(vp->gendev, newdma)) {
 					dev->stats.rx_dropped++;
 					consume_skb(newskb);
 					goto clear_complete;
@@ -2664,7 +2663,7 @@ boomerang_rx(struct net_device *dev)
 				vp->rx_skbuff[entry] = newskb;
 				vp->rx_ring[entry].addr = cpu_to_le32(newdma);
 				skb_put(skb, pkt_len);
-				pci_unmap_single(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+				dma_unmap_single(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
 				vp->rx_nocopy++;
 			}
 			skb->protocol = eth_type_trans(skb, dev);
@@ -2761,8 +2760,8 @@ vortex_close(struct net_device *dev)
 	if (vp->full_bus_master_rx) { /* Free Boomerang bus master Rx buffers. */
 		for (i = 0; i < RX_RING_SIZE; i++)
 			if (vp->rx_skbuff[i]) {
-				pci_unmap_single(	VORTEX_PCI(vp), le32_to_cpu(vp->rx_ring[i].addr),
-									PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+				dma_unmap_single(vp->gendev, le32_to_cpu(vp->rx_ring[i].addr),
+									PKT_BUF_SZ, DMA_FROM_DEVICE);
 				dev_kfree_skb(vp->rx_skbuff[i]);
 				vp->rx_skbuff[i] = NULL;
 			}
@@ -2775,12 +2774,12 @@ vortex_close(struct net_device *dev)
 				int k;
 
 				for (k=0; k<=skb_shinfo(skb)->nr_frags; k++)
-						pci_unmap_single(VORTEX_PCI(vp),
+						dma_unmap_single(vp->gendev,
 										 le32_to_cpu(vp->tx_ring[i].frag[k].addr),
 										 le32_to_cpu(vp->tx_ring[i].frag[k].length)&0xFFF,
-										 PCI_DMA_TODEVICE);
+										 DMA_TO_DEVICE);
 #else
-				pci_unmap_single(VORTEX_PCI(vp), le32_to_cpu(vp->tx_ring[i].addr), skb->len, PCI_DMA_TODEVICE);
+				dma_unmap_single(vp->gendev, le32_to_cpu(vp->tx_ring[i].addr), skb->len, DMA_TO_DEVICE);
 #endif
 				dev_kfree_skb(skb);
 				vp->tx_skbuff[i] = NULL;
@@ -3288,11 +3287,10 @@ static void vortex_remove_one(struct pci_dev *pdev)
 
 	pci_iounmap(pdev, vp->ioaddr);
 
-	pci_free_consistent(pdev,
-						sizeof(struct boom_rx_desc) * RX_RING_SIZE
-							+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
-						vp->rx_ring,
-						vp->rx_ring_dma);
+	dma_free_coherent(&pdev->dev,
+			sizeof(struct boom_rx_desc) * RX_RING_SIZE +
+			sizeof(struct boom_tx_desc) * TX_RING_SIZE,
+			vp->rx_ring, vp->rx_ring_dma);
 
 	pci_release_regions(pdev);
 
diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c
index ac99d089ac72..1c97e39b478e 100644
--- a/drivers/net/ethernet/8390/ne.c
+++ b/drivers/net/ethernet/8390/ne.c
@@ -164,7 +164,9 @@ bad_clone_list[] __initdata = {
 #define NESM_START_PG	0x40	/* First page of TX buffer */
 #define NESM_STOP_PG	0x80	/* Last page +1 of RX ring */
 
-#if defined(CONFIG_ATARI)	/* 8-bit mode on Atari, normal on Q40 */
+#if defined(CONFIG_MACH_TX49XX)
+#  define DCR_VAL 0x48		/* 8-bit mode */
+#elif defined(CONFIG_ATARI)	/* 8-bit mode on Atari, normal on Q40 */
 #  define DCR_VAL (MACH_IS_ATARI ? 0x48 : 0x49)
 #else
 #  define DCR_VAL 0x49
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index a561705f232c..be198cc0b10c 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1552,22 +1552,26 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!ioaddr) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
 			pr_err("card has no PCI IO resources, aborting\n");
-		return -ENODEV;
+		err = -ENODEV;
+		goto err_disable_dev;
 	}
 
 	err = pci_set_dma_mask(pdev, PCNET32_DMA_MASK);
 	if (err) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
 			pr_err("architecture does not support 32bit PCI busmaster DMA\n");
-		return err;
+		goto err_disable_dev;
 	}
 	if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
 			pr_err("io address range already allocated\n");
-		return -EBUSY;
+		err = -EBUSY;
+		goto err_disable_dev;
 	}
 
 	err = pcnet32_probe1(ioaddr, 1, pdev);
+
+err_disable_dev:
 	if (err < 0)
 		pci_disable_device(pdev);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 7ea72ef11a55..d272dc6984ac 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1321,6 +1321,10 @@
 #define MDIO_VEND2_AN_STAT		0x8002
 #endif
 
+#ifndef MDIO_VEND2_PMA_CDR_CONTROL
+#define MDIO_VEND2_PMA_CDR_CONTROL	0x8056
+#endif
+
 #ifndef MDIO_CTRL1_SPEED1G
 #define MDIO_CTRL1_SPEED1G		(MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
 #endif
@@ -1369,6 +1373,10 @@
 #define XGBE_AN_CL37_TX_CONFIG_MASK	0x08
 #define XGBE_AN_CL37_MII_CTRL_8BIT	0x0100
 
+#define XGBE_PMA_CDR_TRACK_EN_MASK	0x01
+#define XGBE_PMA_CDR_TRACK_EN_OFF	0x00
+#define XGBE_PMA_CDR_TRACK_EN_ON	0x01
+
 /* Bit setting and getting macros
  *  The get macro will extract the current bit field value from within
  *  the variable
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index 7d128be61310..b91143947ed2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -519,6 +519,22 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
 				   "debugfs_create_file failed\n");
 	}
 
+	if (pdata->vdata->an_cdr_workaround) {
+		pfile = debugfs_create_bool("an_cdr_workaround", 0600,
+					    pdata->xgbe_debugfs,
+					    &pdata->debugfs_an_cdr_workaround);
+		if (!pfile)
+			netdev_err(pdata->netdev,
+				   "debugfs_create_bool failed\n");
+
+		pfile = debugfs_create_bool("an_cdr_track_early", 0600,
+					    pdata->xgbe_debugfs,
+					    &pdata->debugfs_an_cdr_track_early);
+		if (!pfile)
+			netdev_err(pdata->netdev,
+				   "debugfs_create_bool failed\n");
+	}
+
 	kfree(buf);
 }
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index 795e556d4a3f..441d0973957b 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -349,6 +349,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata)
 	XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
 
 	/* Call MDIO/PHY initialization routine */
+	pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround;
 	ret = pdata->phy_if.phy_init(pdata);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 072b9f664597..1b45cd73a258 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -432,11 +432,16 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
 	xgbe_an73_set(pdata, false, false);
 	xgbe_an73_disable_interrupts(pdata);
 
+	pdata->an_start = 0;
+
 	netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
 }
 
 static void xgbe_an_restart(struct xgbe_prv_data *pdata)
 {
+	if (pdata->phy_if.phy_impl.an_pre)
+		pdata->phy_if.phy_impl.an_pre(pdata);
+
 	switch (pdata->an_mode) {
 	case XGBE_AN_MODE_CL73:
 	case XGBE_AN_MODE_CL73_REDRV:
@@ -453,6 +458,9 @@ static void xgbe_an_restart(struct xgbe_prv_data *pdata)
 
 static void xgbe_an_disable(struct xgbe_prv_data *pdata)
 {
+	if (pdata->phy_if.phy_impl.an_post)
+		pdata->phy_if.phy_impl.an_post(pdata);
+
 	switch (pdata->an_mode) {
 	case XGBE_AN_MODE_CL73:
 	case XGBE_AN_MODE_CL73_REDRV:
@@ -505,11 +513,11 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata,
 		XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
 			    reg);
 
-		if (pdata->phy_if.phy_impl.kr_training_post)
-			pdata->phy_if.phy_impl.kr_training_post(pdata);
-
 		netif_dbg(pdata, link, pdata->netdev,
 			  "KR training initiated\n");
+
+		if (pdata->phy_if.phy_impl.kr_training_post)
+			pdata->phy_if.phy_impl.kr_training_post(pdata);
 	}
 
 	return XGBE_AN_PAGE_RECEIVED;
@@ -637,11 +645,11 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)
 			return XGBE_AN_NO_LINK;
 	}
 
-	xgbe_an73_disable(pdata);
+	xgbe_an_disable(pdata);
 
 	xgbe_switch_mode(pdata);
 
-	xgbe_an73_restart(pdata);
+	xgbe_an_restart(pdata);
 
 	return XGBE_AN_INCOMPAT_LINK;
 }
@@ -820,6 +828,9 @@ static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata)
 		pdata->an_result = pdata->an_state;
 		pdata->an_state = XGBE_AN_READY;
 
+		if (pdata->phy_if.phy_impl.an_post)
+			pdata->phy_if.phy_impl.an_post(pdata);
+
 		netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
 			  xgbe_state_as_string(pdata->an_result));
 	}
@@ -903,6 +914,9 @@ again:
 		pdata->kx_state = XGBE_RX_BPA;
 		pdata->an_start = 0;
 
+		if (pdata->phy_if.phy_impl.an_post)
+			pdata->phy_if.phy_impl.an_post(pdata);
+
 		netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
 			  xgbe_state_as_string(pdata->an_result));
 	}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index eb23f9ba1a9a..82d1f416ee2a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -456,6 +456,7 @@ static const struct xgbe_version_data xgbe_v2a = {
 	.irq_reissue_support		= 1,
 	.tx_desc_prefetch		= 5,
 	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 1,
 };
 
 static const struct xgbe_version_data xgbe_v2b = {
@@ -470,6 +471,7 @@ static const struct xgbe_version_data xgbe_v2b = {
 	.irq_reissue_support		= 1,
 	.tx_desc_prefetch		= 5,
 	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 1,
 };
 
 static const struct pci_device_id xgbe_pci_table[] = {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 3304a291aa96..aac884314000 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -147,6 +147,14 @@
 /* Rate-change complete wait/retry count */
 #define XGBE_RATECHANGE_COUNT		500
 
+/* CDR delay values for KR support (in usec) */
+#define XGBE_CDR_DELAY_INIT		10000
+#define XGBE_CDR_DELAY_INC		10000
+#define XGBE_CDR_DELAY_MAX		100000
+
+/* RRC frequency during link status check */
+#define XGBE_RRC_FREQUENCY		10
+
 enum xgbe_port_mode {
 	XGBE_PORT_MODE_RSVD = 0,
 	XGBE_PORT_MODE_BACKPLANE,
@@ -245,6 +253,10 @@ enum xgbe_sfp_speed {
 #define XGBE_SFP_BASE_VENDOR_SN			4
 #define XGBE_SFP_BASE_VENDOR_SN_LEN		16
 
+#define XGBE_SFP_EXTD_OPT1			1
+#define XGBE_SFP_EXTD_OPT1_RX_LOS		BIT(1)
+#define XGBE_SFP_EXTD_OPT1_TX_FAULT		BIT(3)
+
 #define XGBE_SFP_EXTD_DIAG			28
 #define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE		BIT(2)
 
@@ -324,6 +336,7 @@ struct xgbe_phy_data {
 
 	unsigned int sfp_gpio_address;
 	unsigned int sfp_gpio_mask;
+	unsigned int sfp_gpio_inputs;
 	unsigned int sfp_gpio_rx_los;
 	unsigned int sfp_gpio_tx_fault;
 	unsigned int sfp_gpio_mod_absent;
@@ -355,6 +368,10 @@ struct xgbe_phy_data {
 	unsigned int redrv_addr;
 	unsigned int redrv_lane;
 	unsigned int redrv_model;
+
+	/* KR AN support */
+	unsigned int phy_cdr_notrack;
+	unsigned int phy_cdr_delay;
 };
 
 /* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
@@ -974,6 +991,49 @@ static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata)
 	phy_data->sfp_phy_avail = 1;
 }
 
+static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data)
+{
+	u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+	if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS))
+		return false;
+
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los))
+		return true;
+
+	return false;
+}
+
+static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data)
+{
+	u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+	if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT))
+		return false;
+
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault))
+		return true;
+
+	return false;
+}
+
+static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data)
+{
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent))
+		return true;
+
+	return false;
+}
+
 static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -1019,6 +1079,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
 	if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
 		return;
 
+	/* Update transceiver signals (eeprom extd/options) */
+	phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data);
+	phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data);
+
 	if (xgbe_phy_sfp_parse_quirks(pdata))
 		return;
 
@@ -1184,7 +1248,6 @@ put:
 static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int gpio_input;
 	u8 gpio_reg, gpio_ports[2];
 	int ret;
 
@@ -1199,23 +1262,9 @@ static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
 		return;
 	}
 
-	gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
-
-	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
-		/* No GPIO, just assume the module is present for now */
-		phy_data->sfp_mod_absent = 0;
-	} else {
-		if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
-			phy_data->sfp_mod_absent = 0;
-	}
-
-	if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
-	    (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
-		phy_data->sfp_rx_los = 1;
+	phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0];
 
-	if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
-	    (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
-		phy_data->sfp_tx_fault = 1;
+	phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data);
 }
 
 static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
@@ -2361,7 +2410,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 		return 1;
 
 	/* No link, attempt a receiver reset cycle */
-	if (phy_data->rrc_count++) {
+	if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
 		phy_data->rrc_count = 0;
 		xgbe_phy_rrc(pdata);
 	}
@@ -2669,6 +2718,103 @@ static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata)
 	return true;
 }
 
+static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	if (!pdata->debugfs_an_cdr_workaround)
+		return;
+
+	if (!phy_data->phy_cdr_notrack)
+		return;
+
+	usleep_range(phy_data->phy_cdr_delay,
+		     phy_data->phy_cdr_delay + 500);
+
+	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+			 XGBE_PMA_CDR_TRACK_EN_MASK,
+			 XGBE_PMA_CDR_TRACK_EN_ON);
+
+	phy_data->phy_cdr_notrack = 0;
+}
+
+static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	if (!pdata->debugfs_an_cdr_workaround)
+		return;
+
+	if (phy_data->phy_cdr_notrack)
+		return;
+
+	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+			 XGBE_PMA_CDR_TRACK_EN_MASK,
+			 XGBE_PMA_CDR_TRACK_EN_OFF);
+
+	xgbe_phy_rrc(pdata);
+
+	phy_data->phy_cdr_notrack = 1;
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+	if (!pdata->debugfs_an_cdr_track_early)
+		xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+	if (pdata->debugfs_an_cdr_track_early)
+		xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_an_post(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	switch (pdata->an_mode) {
+	case XGBE_AN_MODE_CL73:
+	case XGBE_AN_MODE_CL73_REDRV:
+		if (phy_data->cur_mode != XGBE_MODE_KR)
+			break;
+
+		xgbe_phy_cdr_track(pdata);
+
+		switch (pdata->an_result) {
+		case XGBE_AN_READY:
+		case XGBE_AN_COMPLETE:
+			break;
+		default:
+			if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX)
+				phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC;
+			else
+				phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	switch (pdata->an_mode) {
+	case XGBE_AN_MODE_CL73:
+	case XGBE_AN_MODE_CL73_REDRV:
+		if (phy_data->cur_mode != XGBE_MODE_KR)
+			break;
+
+		xgbe_phy_cdr_notrack(pdata);
+		break;
+	default:
+		break;
+	}
+}
+
 static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -2680,6 +2826,9 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
 	xgbe_phy_sfp_reset(phy_data);
 	xgbe_phy_sfp_mod_absent(pdata);
 
+	/* Reset CDR support */
+	xgbe_phy_cdr_track(pdata);
+
 	/* Power off the PHY */
 	xgbe_phy_power_off(pdata);
 
@@ -2712,6 +2861,9 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
 	/* Start in highest supported mode */
 	xgbe_phy_set_mode(pdata, phy_data->start_mode);
 
+	/* Reset CDR support */
+	xgbe_phy_cdr_track(pdata);
+
 	/* After starting the I2C controller, we can check for an SFP */
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_SFP:
@@ -3019,6 +3171,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
 		}
 	}
 
+	phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+
 	/* Register for driving external PHYs */
 	mii = devm_mdiobus_alloc(pdata->dev);
 	if (!mii) {
@@ -3071,4 +3225,10 @@ void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if)
 	phy_impl->an_advertising	= xgbe_phy_an_advertising;
 
 	phy_impl->an_outcome		= xgbe_phy_an_outcome;
+
+	phy_impl->an_pre		= xgbe_phy_an_pre;
+	phy_impl->an_post		= xgbe_phy_an_post;
+
+	phy_impl->kr_training_pre	= xgbe_phy_kr_training_pre;
+	phy_impl->kr_training_post	= xgbe_phy_kr_training_post;
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index ad102c8bac7b..95d4b56448c6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -833,6 +833,7 @@ struct xgbe_hw_if {
 /* This structure represents implementation specific routines for an
  * implementation of a PHY. All routines are required unless noted below.
  *   Optional routines:
+ *     an_pre, an_post
  *     kr_training_pre, kr_training_post
  */
 struct xgbe_phy_impl_if {
@@ -875,6 +876,10 @@ struct xgbe_phy_impl_if {
 	/* Process results of auto-negotiation */
 	enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
 
+	/* Pre/Post auto-negotiation support */
+	void (*an_pre)(struct xgbe_prv_data *);
+	void (*an_post)(struct xgbe_prv_data *);
+
 	/* Pre/Post KR training enablement support */
 	void (*kr_training_pre)(struct xgbe_prv_data *);
 	void (*kr_training_post)(struct xgbe_prv_data *);
@@ -989,6 +994,7 @@ struct xgbe_version_data {
 	unsigned int irq_reissue_support;
 	unsigned int tx_desc_prefetch;
 	unsigned int rx_desc_prefetch;
+	unsigned int an_cdr_workaround;
 };
 
 struct xgbe_vxlan_data {
@@ -1257,6 +1263,9 @@ struct xgbe_prv_data {
 	unsigned int debugfs_xprop_reg;
 
 	unsigned int debugfs_xi2c_reg;
+
+	bool debugfs_an_cdr_workaround;
+	bool debugfs_an_cdr_track_early;
 };
 
 /* Function prototypes*/
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 32f6d2e24d66..1a1a6380c128 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -95,6 +95,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	/*rss rings */
 	cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
 	cfg->vecs = min(cfg->vecs, num_online_cpus());
+	cfg->vecs = min(cfg->vecs, self->irqvecs);
 	/* cfg->vecs should be power of 2 for RSS */
 	if (cfg->vecs >= 8U)
 		cfg->vecs = 8U;
@@ -246,6 +247,8 @@ void aq_nic_ndev_init(struct aq_nic_s *self)
 
 	self->ndev->hw_features |= aq_hw_caps->hw_features;
 	self->ndev->features = aq_hw_caps->hw_features;
+	self->ndev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
+				     NETIF_F_RXHASH | NETIF_F_SG | NETIF_F_LRO;
 	self->ndev->priv_flags = aq_hw_caps->hw_priv_flags;
 	self->ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 219b550d1665..faa533a0ec47 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -80,6 +80,7 @@ struct aq_nic_s {
 
 	struct pci_dev *pdev;
 	unsigned int msix_entry_mask;
+	u32 irqvecs;
 };
 
 static inline struct device *aq_nic_get_dev(struct aq_nic_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index ecc6306f940f..a50e08bb4748 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -267,16 +267,16 @@ static int aq_pci_probe(struct pci_dev *pdev,
 	numvecs = min(numvecs, num_online_cpus());
 	/*enable interrupts */
 #if !AQ_CFG_FORCE_LEGACY_INT
-	err = pci_alloc_irq_vectors(self->pdev, numvecs, numvecs,
-				    PCI_IRQ_MSIX);
-
-	if (err < 0) {
-		err = pci_alloc_irq_vectors(self->pdev, 1, 1,
-					    PCI_IRQ_MSI | PCI_IRQ_LEGACY);
-		if (err < 0)
-			goto err_hwinit;
+	numvecs = pci_alloc_irq_vectors(self->pdev, 1, numvecs,
+					PCI_IRQ_MSIX | PCI_IRQ_MSI |
+					PCI_IRQ_LEGACY);
+
+	if (numvecs < 0) {
+		err = numvecs;
+		goto err_hwinit;
 	}
 #endif
+	self->irqvecs = numvecs;
 
 	/* net device init */
 	aq_nic_cfg_start(self);
@@ -298,9 +298,9 @@ err_free_aq_hw:
 	kfree(self->aq_hw);
 err_ioremap:
 	free_netdev(ndev);
-err_pci_func:
-	pci_release_regions(pdev);
 err_ndev:
+	pci_release_regions(pdev);
+err_pci_func:
 	pci_disable_device(pdev);
 	return err;
 }
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index f9a3c1a76d5d..f33b25fbca63 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2144,14 +2144,21 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
 	.ndo_select_queue	= bcm_sysport_select_queue,
 };
 
-static int bcm_sysport_map_queues(struct net_device *dev,
+static int bcm_sysport_map_queues(struct notifier_block *nb,
 				  struct dsa_notifier_register_info *info)
 {
-	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct bcm_sysport_tx_ring *ring;
+	struct bcm_sysport_priv *priv;
 	struct net_device *slave_dev;
 	unsigned int num_tx_queues;
 	unsigned int q, start, port;
+	struct net_device *dev;
+
+	priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
+	if (priv->netdev != info->master)
+		return 0;
+
+	dev = info->master;
 
 	/* We can't be setting up queue inspection for non directly attached
 	 * switches
@@ -2174,11 +2181,12 @@ static int bcm_sysport_map_queues(struct net_device *dev,
 	if (priv->is_lite)
 		netif_set_real_num_tx_queues(slave_dev,
 					     slave_dev->num_tx_queues / 2);
+
 	num_tx_queues = slave_dev->real_num_tx_queues;
 
 	if (priv->per_port_num_tx_queues &&
 	    priv->per_port_num_tx_queues != num_tx_queues)
-		netdev_warn(slave_dev, "asymetric number of per-port queues\n");
+		netdev_warn(slave_dev, "asymmetric number of per-port queues\n");
 
 	priv->per_port_num_tx_queues = num_tx_queues;
 
@@ -2201,7 +2209,7 @@ static int bcm_sysport_map_queues(struct net_device *dev,
 	return 0;
 }
 
-static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
+static int bcm_sysport_dsa_notifier(struct notifier_block *nb,
 				    unsigned long event, void *ptr)
 {
 	struct dsa_notifier_register_info *info;
@@ -2211,7 +2219,7 @@ static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
 
 	info = ptr;
 
-	return notifier_from_errno(bcm_sysport_map_queues(info->master, info));
+	return notifier_from_errno(bcm_sysport_map_queues(nb, info));
 }
 
 #define REV_FMT	"v%2x.%02x"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1f622ca2a64f..8ba14ae00e8f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1927,22 +1927,39 @@ static char *bnxt_parse_pkglog(int desired_field, u8 *data, size_t datalen)
 	return retval;
 }
 
-static char *bnxt_get_pkgver(struct net_device *dev, char *buf, size_t buflen)
+static void bnxt_get_pkgver(struct net_device *dev)
 {
+	struct bnxt *bp = netdev_priv(dev);
 	u16 index = 0;
-	u32 datalen;
+	char *pkgver;
+	u32 pkglen;
+	u8 *pkgbuf;
+	int len;
 
 	if (bnxt_find_nvram_item(dev, BNX_DIR_TYPE_PKG_LOG,
 				 BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE,
-				 &index, NULL, &datalen) != 0)
-		return NULL;
+				 &index, NULL, &pkglen) != 0)
+		return;
 
-	memset(buf, 0, buflen);
-	if (bnxt_get_nvram_item(dev, index, 0, datalen, buf) != 0)
-		return NULL;
+	pkgbuf = kzalloc(pkglen, GFP_KERNEL);
+	if (!pkgbuf) {
+		dev_err(&bp->pdev->dev, "Unable to allocate memory for pkg version, length = %u\n",
+			pkglen);
+		return;
+	}
+
+	if (bnxt_get_nvram_item(dev, index, 0, pkglen, pkgbuf))
+		goto err;
 
-	return bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, buf,
-		datalen);
+	pkgver = bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, pkgbuf,
+				   pkglen);
+	if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
+		len = strlen(bp->fw_ver_str);
+		snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
+			 "/pkg %s", pkgver);
+	}
+err:
+	kfree(pkgbuf);
 }
 
 static int bnxt_get_eeprom(struct net_device *dev,
@@ -2615,22 +2632,10 @@ void bnxt_ethtool_init(struct bnxt *bp)
 	struct hwrm_selftest_qlist_input req = {0};
 	struct bnxt_test_info *test_info;
 	struct net_device *dev = bp->dev;
-	char *pkglog;
 	int i, rc;
 
-	pkglog = kzalloc(BNX_PKG_LOG_MAX_LENGTH, GFP_KERNEL);
-	if (pkglog) {
-		char *pkgver;
-		int len;
+	bnxt_get_pkgver(dev);
 
-		pkgver = bnxt_get_pkgver(dev, pkglog, BNX_PKG_LOG_MAX_LENGTH);
-		if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
-			len = strlen(bp->fw_ver_str);
-			snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
-				 "/pkg %s", pkgver);
-		}
-		kfree(pkglog);
-	}
 	if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
 		return;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
index 73f2249555b5..83444811d3c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
@@ -59,8 +59,6 @@ enum bnxt_nvm_directory_type {
 #define BNX_DIR_ATTR_NO_CHKSUM			(1 << 0)
 #define BNX_DIR_ATTR_PROP_STREAM		(1 << 1)
 
-#define BNX_PKG_LOG_MAX_LENGTH			4096
-
 enum bnxnvm_pkglog_field_index {
 	BNX_PKG_LOG_FIELD_IDX_INSTALLED_TIMESTAMP	= 0,
 	BNX_PKG_LOG_FIELD_IDX_PKG_DESCRIPTION		= 1,
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 08bbb639be1a..9f59b1270a7c 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -8733,14 +8733,15 @@ static void tg3_free_consistent(struct tg3 *tp)
 	tg3_mem_rx_release(tp);
 	tg3_mem_tx_release(tp);
 
-	/* Protect tg3_get_stats64() from reading freed tp->hw_stats. */
-	tg3_full_lock(tp, 0);
+	/* tp->hw_stats can be referenced safely:
+	 *     1. under rtnl_lock
+	 *     2. or under tp->lock if TG3_FLAG_INIT_COMPLETE is set.
+	 */
 	if (tp->hw_stats) {
 		dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats),
 				  tp->hw_stats, tp->stats_mapping);
 		tp->hw_stats = NULL;
 	}
-	tg3_full_unlock(tp);
 }
 
 /*
@@ -14178,7 +14179,7 @@ static void tg3_get_stats64(struct net_device *dev,
 	struct tg3 *tp = netdev_priv(dev);
 
 	spin_lock_bh(&tp->lock);
-	if (!tp->hw_stats) {
+	if (!tp->hw_stats || !tg3_flag(tp, INIT_COMPLETE)) {
 		*stats = tp->net_stats_prev;
 		spin_unlock_bh(&tp->lock);
 		return;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
index b57acb8dc35b..dc25066c59a1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
@@ -419,15 +419,15 @@ static const u32 t6_up_cim_reg_array[][IREG_NUM_ELEM + 1] = {
 	{0x7b50, 0x7b54, 0x280, 0x20, 0}, /* up_cim_280_to_2fc */
 	{0x7b50, 0x7b54, 0x300, 0x20, 0}, /* up_cim_300_to_37c */
 	{0x7b50, 0x7b54, 0x380, 0x14, 0}, /* up_cim_380_to_3cc */
-	{0x7b50, 0x7b54, 0x2900, 0x4, 0x4}, /* up_cim_2900_to_3d40 */
-	{0x7b50, 0x7b54, 0x2904, 0x4, 0x4}, /* up_cim_2904_to_3d44 */
-	{0x7b50, 0x7b54, 0x2908, 0x4, 0x4}, /* up_cim_2908_to_3d48 */
-	{0x7b50, 0x7b54, 0x2910, 0x4, 0x4}, /* up_cim_2910_to_3d4c */
-	{0x7b50, 0x7b54, 0x2914, 0x4, 0x4}, /* up_cim_2914_to_3d50 */
-	{0x7b50, 0x7b54, 0x2920, 0x10, 0x10}, /* up_cim_2920_to_2a10 */
-	{0x7b50, 0x7b54, 0x2924, 0x10, 0x10}, /* up_cim_2924_to_2a14 */
-	{0x7b50, 0x7b54, 0x2928, 0x10, 0x10}, /* up_cim_2928_to_2a18 */
-	{0x7b50, 0x7b54, 0x292c, 0x10, 0x10}, /* up_cim_292c_to_2a1c */
+	{0x7b50, 0x7b54, 0x4900, 0x4, 0x4}, /* up_cim_4900_to_4c60 */
+	{0x7b50, 0x7b54, 0x4904, 0x4, 0x4}, /* up_cim_4904_to_4c64 */
+	{0x7b50, 0x7b54, 0x4908, 0x4, 0x4}, /* up_cim_4908_to_4c68 */
+	{0x7b50, 0x7b54, 0x4910, 0x4, 0x4}, /* up_cim_4910_to_4c70 */
+	{0x7b50, 0x7b54, 0x4914, 0x4, 0x4}, /* up_cim_4914_to_4c74 */
+	{0x7b50, 0x7b54, 0x4920, 0x10, 0x10}, /* up_cim_4920_to_4a10 */
+	{0x7b50, 0x7b54, 0x4924, 0x10, 0x10}, /* up_cim_4924_to_4a14 */
+	{0x7b50, 0x7b54, 0x4928, 0x10, 0x10}, /* up_cim_4928_to_4a18 */
+	{0x7b50, 0x7b54, 0x492c, 0x10, 0x10}, /* up_cim_492c_to_4a1c */
 };
 
 static const u32 t5_up_cim_reg_array[][IREG_NUM_ELEM + 1] = {
@@ -444,16 +444,6 @@ static const u32 t5_up_cim_reg_array[][IREG_NUM_ELEM + 1] = {
 	{0x7b50, 0x7b54, 0x280, 0x20, 0}, /* up_cim_280_to_2fc */
 	{0x7b50, 0x7b54, 0x300, 0x20, 0}, /* up_cim_300_to_37c */
 	{0x7b50, 0x7b54, 0x380, 0x14, 0}, /* up_cim_380_to_3cc */
-	{0x7b50, 0x7b54, 0x2900, 0x4, 0x4}, /* up_cim_2900_to_3d40 */
-	{0x7b50, 0x7b54, 0x2904, 0x4, 0x4}, /* up_cim_2904_to_3d44 */
-	{0x7b50, 0x7b54, 0x2908, 0x4, 0x4}, /* up_cim_2908_to_3d48 */
-	{0x7b50, 0x7b54, 0x2910, 0x4, 0x4}, /* up_cim_2910_to_3d4c */
-	{0x7b50, 0x7b54, 0x2914, 0x4, 0x4}, /* up_cim_2914_to_3d50 */
-	{0x7b50, 0x7b54, 0x2918, 0x4, 0x4}, /* up_cim_2918_to_3d54 */
-	{0x7b50, 0x7b54, 0x291c, 0x4, 0x4}, /* up_cim_291c_to_3d58 */
-	{0x7b50, 0x7b54, 0x2924, 0x10, 0x10}, /* up_cim_2924_to_2914 */
-	{0x7b50, 0x7b54, 0x2928, 0x10, 0x10}, /* up_cim_2928_to_2a18 */
-	{0x7b50, 0x7b54, 0x292c, 0x10, 0x10}, /* up_cim_292c_to_2a1c */
 };
 
 static const u32 t6_hma_ireg_array[][IREG_NUM_ELEM] = {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index db92f1858060..b76447baccaf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -836,7 +836,7 @@ bool is_filter_exact_match(struct adapter *adap,
 {
 	struct tp_params *tp = &adap->params.tp;
 	u64 hash_filter_mask = tp->hash_filter_mask;
-	u32 mask;
+	u64 ntuple_mask = 0;
 
 	if (!is_hashfilter(adap))
 		return false;
@@ -865,73 +865,45 @@ bool is_filter_exact_match(struct adapter *adap,
 	if (!fs->val.fport || fs->mask.fport != 0xffff)
 		return false;
 
-	if (tp->fcoe_shift >= 0) {
-		mask = (hash_filter_mask >> tp->fcoe_shift) & FT_FCOE_W;
-		if (mask && !fs->mask.fcoe)
-			return false;
-	}
+	/* calculate tuple mask and compare with mask configured in hw */
+	if (tp->fcoe_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.fcoe << tp->fcoe_shift;
 
-	if (tp->port_shift >= 0) {
-		mask = (hash_filter_mask >> tp->port_shift) & FT_PORT_W;
-		if (mask && !fs->mask.iport)
-			return false;
-	}
+	if (tp->port_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.iport << tp->port_shift;
 
 	if (tp->vnic_shift >= 0) {
-		mask = (hash_filter_mask >> tp->vnic_shift) & FT_VNIC_ID_W;
-
-		if ((adap->params.tp.ingress_config & VNIC_F)) {
-			if (mask && !fs->mask.pfvf_vld)
-				return false;
-		} else {
-			if (mask && !fs->mask.ovlan_vld)
-				return false;
-		}
+		if ((adap->params.tp.ingress_config & VNIC_F))
+			ntuple_mask |= (u64)fs->mask.pfvf_vld << tp->vnic_shift;
+		else
+			ntuple_mask |= (u64)fs->mask.ovlan_vld <<
+				tp->vnic_shift;
 	}
 
-	if (tp->vlan_shift >= 0) {
-		mask = (hash_filter_mask >> tp->vlan_shift) & FT_VLAN_W;
-		if (mask && !fs->mask.ivlan)
-			return false;
-	}
+	if (tp->vlan_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.ivlan << tp->vlan_shift;
 
-	if (tp->tos_shift >= 0) {
-		mask = (hash_filter_mask >> tp->tos_shift) & FT_TOS_W;
-		if (mask && !fs->mask.tos)
-			return false;
-	}
+	if (tp->tos_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.tos << tp->tos_shift;
 
-	if (tp->protocol_shift >= 0) {
-		mask = (hash_filter_mask >> tp->protocol_shift) & FT_PROTOCOL_W;
-		if (mask && !fs->mask.proto)
-			return false;
-	}
+	if (tp->protocol_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.proto << tp->protocol_shift;
 
-	if (tp->ethertype_shift >= 0) {
-		mask = (hash_filter_mask >> tp->ethertype_shift) &
-			FT_ETHERTYPE_W;
-		if (mask && !fs->mask.ethtype)
-			return false;
-	}
+	if (tp->ethertype_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.ethtype << tp->ethertype_shift;
 
-	if (tp->macmatch_shift >= 0) {
-		mask = (hash_filter_mask >> tp->macmatch_shift) & FT_MACMATCH_W;
-		if (mask && !fs->mask.macidx)
-			return false;
-	}
+	if (tp->macmatch_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.macidx << tp->macmatch_shift;
+
+	if (tp->matchtype_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.matchtype << tp->matchtype_shift;
+
+	if (tp->frag_shift >= 0)
+		ntuple_mask |= (u64)fs->mask.frag << tp->frag_shift;
+
+	if (ntuple_mask != hash_filter_mask)
+		return false;
 
-	if (tp->matchtype_shift >= 0) {
-		mask = (hash_filter_mask >> tp->matchtype_shift) &
-			FT_MPSHITTYPE_W;
-		if (mask && !fs->mask.matchtype)
-			return false;
-	}
-	if (tp->frag_shift >= 0) {
-		mask = (hash_filter_mask >> tp->frag_shift) &
-			FT_FRAGMENTATION_W;
-		if (mask && !fs->mask.frag)
-			return false;
-	}
 	return true;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 24d2865b8806..005283c7cdfe 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3433,8 +3433,8 @@ static int adap_config_hma(struct adapter *adapter)
 	sgl = adapter->hma.sgt->sgl;
 	node = dev_to_node(adapter->pdev_dev);
 	for_each_sg(sgl, iter, sgt->orig_nents, i) {
-		newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL,
-					   page_order);
+		newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL |
+					   __GFP_ZERO, page_order);
 		if (!newpage) {
 			dev_err(adapter->pdev_dev,
 				"Not enough memory for HMA page allocation\n");
@@ -5474,6 +5474,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	spin_lock_init(&adapter->mbox_lock);
 	INIT_LIST_HEAD(&adapter->mlist.list);
+	adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS;
 	pci_set_drvdata(pdev, adapter);
 
 	if (func != ent->driver_data) {
@@ -5508,8 +5509,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_free_adapter;
 	}
 
-	adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS;
-
 	/* PCI device has been enabled */
 	adapter->flags |= DEV_ENABLED;
 	memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 81684acf52af..8a8b12b720ef 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2747,11 +2747,11 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_master(pdev);
 
 	/* Query PCI controller on system for DMA addressing
-	 * limitation for the device.  Try 64-bit first, and
+	 * limitation for the device.  Try 47-bit first, and
 	 * fail to 32-bit.
 	 */
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(47));
 	if (err) {
 		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
 		if (err) {
@@ -2765,10 +2765,10 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			goto err_out_release_regions;
 		}
 	} else {
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(47));
 		if (err) {
 			dev_err(dev, "Unable to obtain %u-bit DMA "
-				"for consistent allocations, aborting\n", 64);
+				"for consistent allocations, aborting\n", 47);
 			goto err_out_release_regions;
 		}
 		using_dac = 1;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index c697e79e491e..8f755009ff38 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3309,7 +3309,9 @@ void be_detect_error(struct be_adapter *adapter)
 				if ((val & POST_STAGE_FAT_LOG_START)
 				     != POST_STAGE_FAT_LOG_START &&
 				    (val & POST_STAGE_ARMFW_UE)
-				     != POST_STAGE_ARMFW_UE)
+				     != POST_STAGE_ARMFW_UE &&
+				    (val & POST_STAGE_RECOVERABLE_ERR)
+				     != POST_STAGE_RECOVERABLE_ERR)
 					return;
 			}
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d4604bc8eb5b..9d3eed46830d 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Fast Ethernet Controller (FEC) driver for Motorola MPC8xx.
  * Copyright (c) 1997 Dan Malek (dmalek@jlc.net)
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index f81439796ac7..43d973215040 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Fast Ethernet Controller (ENET) PTP driver for MX6x.
  *
  * Copyright (C) 2012 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 4df282ed22c7..0beee2cc2ddd 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -61,7 +61,7 @@ static const char hw_stat_gstrings[][ETH_GSTRING_LEN] = {
 static const char tx_fw_stat_gstrings[][ETH_GSTRING_LEN] = {
 	"tx-single-collision",
 	"tx-multiple-collision",
-	"tx-late-collsion",
+	"tx-late-collision",
 	"tx-aborted-frames",
 	"tx-lost-frames",
 	"tx-carrier-sense-errors",
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 3e62692af011..fa5b30f547f6 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -87,7 +87,7 @@ do { \
 
 #define HNAE_AE_REGISTER 0x1
 
-#define RCB_RING_NAME_LEN 16
+#define RCB_RING_NAME_LEN (IFNAMSIZ + 4)
 
 #define HNAE_LOWEST_LATENCY_COAL_PARAM	30
 #define HNAE_LOW_LATENCY_COAL_PARAM	80
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index aad5658d79d5..5ec1185808e5 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -192,6 +192,7 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
 	if (adapter->fw_done_rc) {
 		dev_err(dev, "Couldn't map long term buffer,rc = %d\n",
 			adapter->fw_done_rc);
+		dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
 		return -1;
 	}
 	return 0;
@@ -794,46 +795,66 @@ static int ibmvnic_login(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	unsigned long timeout = msecs_to_jiffies(30000);
-	struct device *dev = &adapter->vdev->dev;
+	int retry_count = 0;
+	bool retry;
 	int rc;
 
 	do {
-		if (adapter->renegotiate) {
-			adapter->renegotiate = false;
+		retry = false;
+		if (retry_count > IBMVNIC_MAX_QUEUES) {
+			netdev_warn(netdev, "Login attempts exceeded\n");
+			return -1;
+		}
+
+		adapter->init_done_rc = 0;
+		reinit_completion(&adapter->init_done);
+		rc = send_login(adapter);
+		if (rc) {
+			netdev_warn(netdev, "Unable to login\n");
+			return rc;
+		}
+
+		if (!wait_for_completion_timeout(&adapter->init_done,
+						 timeout)) {
+			netdev_warn(netdev, "Login timed out\n");
+			return -1;
+		}
+
+		if (adapter->init_done_rc == PARTIALSUCCESS) {
+			retry_count++;
 			release_sub_crqs(adapter, 1);
 
+			retry = true;
+			netdev_dbg(netdev,
+				   "Received partial success, retrying...\n");
+			adapter->init_done_rc = 0;
 			reinit_completion(&adapter->init_done);
 			send_cap_queries(adapter);
 			if (!wait_for_completion_timeout(&adapter->init_done,
 							 timeout)) {
-				dev_err(dev, "Capabilities query timeout\n");
+				netdev_warn(netdev,
+					    "Capabilities query timed out\n");
 				return -1;
 			}
+
 			rc = init_sub_crqs(adapter);
 			if (rc) {
-				dev_err(dev,
-					"Initialization of SCRQ's failed\n");
+				netdev_warn(netdev,
+					    "SCRQ initialization failed\n");
 				return -1;
 			}
+
 			rc = init_sub_crq_irqs(adapter);
 			if (rc) {
-				dev_err(dev,
-					"Initialization of SCRQ's irqs failed\n");
+				netdev_warn(netdev,
+					    "SCRQ irq initialization failed\n");
 				return -1;
 			}
-		}
-
-		reinit_completion(&adapter->init_done);
-		rc = send_login(adapter);
-		if (rc) {
-			dev_err(dev, "Unable to attempt device login\n");
-			return rc;
-		} else if (!wait_for_completion_timeout(&adapter->init_done,
-						 timeout)) {
-			dev_err(dev, "Login timeout\n");
+		} else if (adapter->init_done_rc) {
+			netdev_warn(netdev, "Adapter login failed\n");
 			return -1;
 		}
-	} while (adapter->renegotiate);
+	} while (retry);
 
 	/* handle pending MAC address changes after successful login */
 	if (adapter->mac_change_pending) {
@@ -1034,16 +1055,14 @@ static int __ibmvnic_open(struct net_device *netdev)
 		netdev_dbg(netdev, "Enabling rx_scrq[%d] irq\n", i);
 		if (prev_state == VNIC_CLOSED)
 			enable_irq(adapter->rx_scrq[i]->irq);
-		else
-			enable_scrq_irq(adapter, adapter->rx_scrq[i]);
+		enable_scrq_irq(adapter, adapter->rx_scrq[i]);
 	}
 
 	for (i = 0; i < adapter->req_tx_queues; i++) {
 		netdev_dbg(netdev, "Enabling tx_scrq[%d] irq\n", i);
 		if (prev_state == VNIC_CLOSED)
 			enable_irq(adapter->tx_scrq[i]->irq);
-		else
-			enable_scrq_irq(adapter, adapter->tx_scrq[i]);
+		enable_scrq_irq(adapter, adapter->tx_scrq[i]);
 	}
 
 	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
@@ -1115,7 +1134,7 @@ static void clean_rx_pools(struct ibmvnic_adapter *adapter)
 	if (!adapter->rx_pool)
 		return;
 
-	rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+	rx_scrqs = adapter->num_active_rx_pools;
 	rx_entries = adapter->req_rx_add_entries_per_subcrq;
 
 	/* Free any remaining skbs in the rx buffer pools */
@@ -1164,7 +1183,7 @@ static void clean_tx_pools(struct ibmvnic_adapter *adapter)
 	if (!adapter->tx_pool || !adapter->tso_pool)
 		return;
 
-	tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+	tx_scrqs = adapter->num_active_tx_pools;
 
 	/* Free any remaining skbs in the tx buffer pools */
 	for (i = 0; i < tx_scrqs; i++) {
@@ -1184,6 +1203,7 @@ static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
 			if (adapter->tx_scrq[i]->irq) {
 				netdev_dbg(netdev,
 					   "Disabling tx_scrq[%d] irq\n", i);
+				disable_scrq_irq(adapter, adapter->tx_scrq[i]);
 				disable_irq(adapter->tx_scrq[i]->irq);
 			}
 	}
@@ -1193,6 +1213,7 @@ static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
 			if (adapter->rx_scrq[i]->irq) {
 				netdev_dbg(netdev,
 					   "Disabling rx_scrq[%d] irq\n", i);
+				disable_scrq_irq(adapter, adapter->rx_scrq[i]);
 				disable_irq(adapter->rx_scrq[i]->irq);
 			}
 		}
@@ -1806,9 +1827,8 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 			if (rc)
 				return rc;
 		}
+		ibmvnic_disable_irqs(adapter);
 	}
-
-	ibmvnic_disable_irqs(adapter);
 	adapter->state = VNIC_CLOSED;
 
 	if (reset_state == VNIC_CLOSED)
@@ -1828,7 +1848,8 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		napi_schedule(&adapter->napi[i]);
 
-	if (adapter->reset_reason != VNIC_RESET_FAILOVER)
+	if (adapter->reset_reason != VNIC_RESET_FAILOVER &&
+	    adapter->reset_reason != VNIC_RESET_CHANGE_PARAM)
 		netdev_notify_peers(netdev);
 
 	netif_carrier_on(netdev);
@@ -2607,6 +2628,16 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
 		return 1;
 	}
 
+	if (adapter->resetting &&
+	    adapter->reset_reason == VNIC_RESET_MOBILITY) {
+		u64 val = (0xff000000) | scrq->hw_irq;
+
+		rc = plpar_hcall_norets(H_EOI, val);
+		if (rc)
+			dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n",
+				val, rc);
+	}
+
 	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
 				H_ENABLE_VIO_INTERRUPT, scrq->hw_irq, 0, 0);
 	if (rc)
@@ -3170,7 +3201,7 @@ static int send_version_xchg(struct ibmvnic_adapter *adapter)
 struct vnic_login_client_data {
 	u8	type;
 	__be16	len;
-	char	name;
+	char	name[];
 } __packed;
 
 static int vnic_client_data_len(struct ibmvnic_adapter *adapter)
@@ -3199,21 +3230,21 @@ static void vnic_add_client_data(struct ibmvnic_adapter *adapter,
 	vlcd->type = 1;
 	len = strlen(os_name) + 1;
 	vlcd->len = cpu_to_be16(len);
-	strncpy(&vlcd->name, os_name, len);
-	vlcd = (struct vnic_login_client_data *)((char *)&vlcd->name + len);
+	strncpy(vlcd->name, os_name, len);
+	vlcd = (struct vnic_login_client_data *)(vlcd->name + len);
 
 	/* Type 2 - LPAR name */
 	vlcd->type = 2;
 	len = strlen(utsname()->nodename) + 1;
 	vlcd->len = cpu_to_be16(len);
-	strncpy(&vlcd->name, utsname()->nodename, len);
-	vlcd = (struct vnic_login_client_data *)((char *)&vlcd->name + len);
+	strncpy(vlcd->name, utsname()->nodename, len);
+	vlcd = (struct vnic_login_client_data *)(vlcd->name + len);
 
 	/* Type 3 - device name */
 	vlcd->type = 3;
 	len = strlen(adapter->netdev->name) + 1;
 	vlcd->len = cpu_to_be16(len);
-	strncpy(&vlcd->name, adapter->netdev->name, len);
+	strncpy(vlcd->name, adapter->netdev->name, len);
 }
 
 static int send_login(struct ibmvnic_adapter *adapter)
@@ -3942,7 +3973,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	 * to resend the login buffer with fewer queues requested.
 	 */
 	if (login_rsp_crq->generic.rc.code) {
-		adapter->renegotiate = true;
+		adapter->init_done_rc = login_rsp_crq->generic.rc.code;
 		complete(&adapter->init_done);
 		return 0;
 	}
@@ -4563,14 +4594,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 		release_crq_queue(adapter);
 	}
 
-	rc = init_stats_buffers(adapter);
-	if (rc)
-		return rc;
-
-	rc = init_stats_token(adapter);
-	if (rc)
-		return rc;
-
 	return rc;
 }
 
@@ -4639,13 +4662,21 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 			goto ibmvnic_init_fail;
 	} while (rc == EAGAIN);
 
+	rc = init_stats_buffers(adapter);
+	if (rc)
+		goto ibmvnic_init_fail;
+
+	rc = init_stats_token(adapter);
+	if (rc)
+		goto ibmvnic_stats_fail;
+
 	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 	netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
 	netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
 
 	rc = device_create_file(&dev->dev, &dev_attr_failover);
 	if (rc)
-		goto ibmvnic_init_fail;
+		goto ibmvnic_dev_file_err;
 
 	netif_carrier_off(netdev);
 	rc = register_netdev(netdev);
@@ -4664,6 +4695,12 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 ibmvnic_register_fail:
 	device_remove_file(&dev->dev, &dev_attr_failover);
 
+ibmvnic_dev_file_err:
+	release_stats_token(adapter);
+
+ibmvnic_stats_fail:
+	release_stats_buffers(adapter);
+
 ibmvnic_init_fail:
 	release_sub_crqs(adapter, 1);
 	release_crq_queue(adapter);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 99c0b58c2c39..22391e8805f6 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -1035,7 +1035,6 @@ struct ibmvnic_adapter {
 
 	struct ibmvnic_sub_crq_queue **tx_scrq;
 	struct ibmvnic_sub_crq_queue **rx_scrq;
-	bool renegotiate;
 
 	/* rx structs */
 	struct napi_struct *napi;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 5b13ca1bd85f..7dc5f045e969 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -586,7 +586,7 @@ struct ice_sw_rule_lg_act {
 #define ICE_LG_ACT_MIRROR_VSI_ID_S	3
 #define ICE_LG_ACT_MIRROR_VSI_ID_M	(0x3FF << ICE_LG_ACT_MIRROR_VSI_ID_S)
 
-	/* Action type = 5 - Large Action */
+	/* Action type = 5 - Generic Value */
 #define ICE_LG_ACT_GENERIC		0x5
 #define ICE_LG_ACT_GENERIC_VALUE_S	3
 #define ICE_LG_ACT_GENERIC_VALUE_M	(0xFFFF << ICE_LG_ACT_GENERIC_VALUE_S)
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 21977ec984c4..71d032cc5fa7 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -78,6 +78,7 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size,
 	struct ice_aq_desc desc;
 	enum ice_status status;
 	u16 flags;
+	u8 i;
 
 	cmd = &desc.params.mac_read;
 
@@ -98,8 +99,16 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size,
 		return ICE_ERR_CFG;
 	}
 
-	ether_addr_copy(hw->port_info->mac.lan_addr, resp->mac_addr);
-	ether_addr_copy(hw->port_info->mac.perm_addr, resp->mac_addr);
+	/* A single port can report up to two (LAN and WoL) addresses */
+	for (i = 0; i < cmd->num_addr; i++)
+		if (resp[i].addr_type == ICE_AQC_MAN_MAC_ADDR_TYPE_LAN) {
+			ether_addr_copy(hw->port_info->mac.lan_addr,
+					resp[i].mac_addr);
+			ether_addr_copy(hw->port_info->mac.perm_addr,
+					resp[i].mac_addr);
+			break;
+		}
+
 	return 0;
 }
 
@@ -464,9 +473,12 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_sched;
 
-	/* Get port MAC information */
-	mac_buf_len = sizeof(struct ice_aqc_manage_mac_read_resp);
-	mac_buf = devm_kzalloc(ice_hw_to_dev(hw), mac_buf_len, GFP_KERNEL);
+	/* Get MAC information */
+	/* A single port can report up to two (LAN and WoL) addresses */
+	mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2,
+			       sizeof(struct ice_aqc_manage_mac_read_resp),
+			       GFP_KERNEL);
+	mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp);
 
 	if (!mac_buf) {
 		status = ICE_ERR_NO_MEMORY;
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 5909a4407e38..7c511f144ed6 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -1014,10 +1014,10 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	desc = ICE_CTL_Q_DESC(cq->rq, ntc);
 	desc_idx = ntc;
 
+	cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
 	flags = le16_to_cpu(desc->flags);
 	if (flags & ICE_AQ_FLAG_ERR) {
 		ret_code = ICE_ERR_AQ_ERROR;
-		cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
 		ice_debug(hw, ICE_DBG_AQ_MSG,
 			  "Control Receive Queue Event received with error 0x%x\n",
 			  cq->rq_last_status);
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 1b9e2ef48a9d..499904874b3f 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -121,8 +121,6 @@
 #define PFINT_FW_CTL_CAUSE_ENA_S	30
 #define PFINT_FW_CTL_CAUSE_ENA_M	BIT(PFINT_FW_CTL_CAUSE_ENA_S)
 #define PFINT_OICR			0x0016CA00
-#define PFINT_OICR_INTEVENT_S		0
-#define PFINT_OICR_INTEVENT_M		BIT(PFINT_OICR_INTEVENT_S)
 #define PFINT_OICR_HLP_RDY_S		14
 #define PFINT_OICR_HLP_RDY_M		BIT(PFINT_OICR_HLP_RDY_S)
 #define PFINT_OICR_CPM_RDY_S		15
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 210b7910f1cd..5299caf55a7f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1722,9 +1722,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 	oicr = rd32(hw, PFINT_OICR);
 	ena_mask = rd32(hw, PFINT_OICR_ENA);
 
-	if (!(oicr & PFINT_OICR_INTEVENT_M))
-		goto ena_intr;
-
 	if (oicr & PFINT_OICR_GRST_M) {
 		u32 reset;
 		/* we have a reset warning */
@@ -1782,7 +1779,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 	}
 	ret = IRQ_HANDLED;
 
-ena_intr:
 	/* re-enable interrupt causes that are not handled during this pass */
 	wr32(hw, PFINT_OICR_ENA, ena_mask);
 	if (!test_bit(__ICE_DOWN, pf->state)) {
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index f16ff3e4a840..2e6c1d92cc88 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -751,14 +751,14 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 	u16 num_added = 0;
 	u32 temp;
 
+	*num_nodes_added = 0;
+
 	if (!num_nodes)
 		return status;
 
 	if (!parent || layer < hw->sw_entry_point_layer)
 		return ICE_ERR_PARAM;
 
-	*num_nodes_added = 0;
-
 	/* max children per node per layer */
 	max_child_nodes =
 	    le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index c1c0bc30a16d..cce7ada89255 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1700,7 +1700,22 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 	WARN_ON(hw->mac.type != e1000_i210);
 	WARN_ON(queue < 0 || queue > 1);
 
-	if (enable) {
+	if (enable || queue == 0) {
+		/* i210 does not allow the queue 0 to be in the Strict
+		 * Priority mode while the Qav mode is enabled, so,
+		 * instead of disabling strict priority mode, we give
+		 * queue 0 the maximum of credits possible.
+		 *
+		 * See section 8.12.19 of the i210 datasheet, "Note:
+		 * Queue0 QueueMode must be set to 1b when
+		 * TransmitMode is set to Qav."
+		 */
+		if (queue == 0 && !enable) {
+			/* max "linkspeed" idleslope in kbps */
+			idleslope = 1000000;
+			hicredit = ETH_FRAME_LEN;
+		}
+
 		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
 		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 68af127987bc..cead23e3db0c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -943,8 +943,8 @@ err2:
 	kfree(ipsec->ip_tbl);
 	kfree(ipsec->rx_tbl);
 	kfree(ipsec->tx_tbl);
+	kfree(ipsec);
 err1:
-	kfree(adapter->ipsec);
 	netdev_err(adapter->netdev, "Unable to allocate memory for SA tables");
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index afadba99f7b8..2ecd55856c50 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9054,7 +9054,6 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter,
 {
 	const struct tc_action *a;
 	LIST_HEAD(actions);
-	int err;
 
 	if (!tcf_exts_has_actions(exts))
 		return -EINVAL;
@@ -9075,11 +9074,11 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter,
 
 			if (!dev)
 				return -EINVAL;
-			err = handle_redirect_action(adapter, dev->ifindex, queue,
-						     action);
-			if (err == 0)
-				return err;
+			return handle_redirect_action(adapter, dev->ifindex,
+						      queue, action);
 		}
+
+		return -EINVAL;
 	}
 
 	return -EINVAL;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 3123267dfba9..9592f3e3e42e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -3427,6 +3427,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
 		hw->phy.sfp_setup_needed = false;
 	}
 
+	if (status == IXGBE_ERR_SFP_NOT_SUPPORTED)
+		return status;
+
 	/* Reset PHY */
 	if (!hw->phy.reset_disable && hw->phy.ops.reset)
 		hw->phy.ops.reset(hw);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 3d9033f26eff..850f8af95e49 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3420,7 +3420,7 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter)
 		if (!err)
 			continue;
 		hw_dbg(&adapter->hw, "Allocation for XDP Queue %u failed\n", j);
-		break;
+		goto err_setup_tx;
 	}
 
 	return 0;
@@ -4137,7 +4137,7 @@ out_drop:
 	return NETDEV_TX_OK;
 }
 
-static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	struct ixgbevf_ring *tx_ring;
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 54a038943c06..6f410235987c 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -663,7 +663,7 @@ enum mvpp2_tag_type {
 #define MVPP2_PE_VID_FILT_RANGE_END     (MVPP2_PRS_TCAM_SRAM_SIZE - 31)
 #define MVPP2_PE_VID_FILT_RANGE_START   (MVPP2_PE_VID_FILT_RANGE_END - \
 					 MVPP2_PRS_VLAN_FILT_RANGE_SIZE + 1)
-#define MVPP2_PE_LAST_FREE_TID          (MVPP2_PE_VID_FILT_RANGE_START - 1)
+#define MVPP2_PE_LAST_FREE_TID          (MVPP2_PE_MAC_RANGE_START - 1)
 #define MVPP2_PE_IP6_EXT_PROTO_UN	(MVPP2_PRS_TCAM_SRAM_SIZE - 30)
 #define MVPP2_PE_IP6_ADDR_UN		(MVPP2_PRS_TCAM_SRAM_SIZE - 29)
 #define MVPP2_PE_IP4_ADDR_UN		(MVPP2_PRS_TCAM_SRAM_SIZE - 28)
@@ -916,6 +916,8 @@ static struct {
 
 #define MVPP2_MIB_COUNTERS_STATS_DELAY		(1 * HZ)
 
+#define MVPP2_DESC_DMA_MASK	DMA_BIT_MASK(40)
+
 /* Definitions */
 
 /* Shared Packet Processor resources */
@@ -940,6 +942,7 @@ struct mvpp2 {
 	struct clk *pp_clk;
 	struct clk *gop_clk;
 	struct clk *mg_clk;
+	struct clk *mg_core_clk;
 	struct clk *axi_clk;
 
 	/* List of pointers to port structures */
@@ -1429,7 +1432,7 @@ static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
 	if (port->priv->hw_version == MVPP21)
 		return tx_desc->pp21.buf_dma_addr;
 	else
-		return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0);
+		return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK;
 }
 
 static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
@@ -1447,7 +1450,7 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
 	} else {
 		u64 val = (u64)addr;
 
-		tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0);
+		tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK;
 		tx_desc->pp22.buf_dma_addr_ptp |= val;
 		tx_desc->pp22.packet_offset = offset;
 	}
@@ -1507,7 +1510,7 @@ static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
 	if (port->priv->hw_version == MVPP21)
 		return rx_desc->pp21.buf_dma_addr;
 	else
-		return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0);
+		return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK;
 }
 
 static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
@@ -1516,7 +1519,7 @@ static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
 	if (port->priv->hw_version == MVPP21)
 		return rx_desc->pp21.buf_cookie;
 	else
-		return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0);
+		return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK;
 }
 
 static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
@@ -8766,18 +8769,27 @@ static int mvpp2_probe(struct platform_device *pdev)
 			err = clk_prepare_enable(priv->mg_clk);
 			if (err < 0)
 				goto err_gop_clk;
+
+			priv->mg_core_clk = devm_clk_get(&pdev->dev, "mg_core_clk");
+			if (IS_ERR(priv->mg_core_clk)) {
+				priv->mg_core_clk = NULL;
+			} else {
+				err = clk_prepare_enable(priv->mg_core_clk);
+				if (err < 0)
+					goto err_mg_clk;
+			}
 		}
 
 		priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk");
 		if (IS_ERR(priv->axi_clk)) {
 			err = PTR_ERR(priv->axi_clk);
 			if (err == -EPROBE_DEFER)
-				goto err_gop_clk;
+				goto err_mg_core_clk;
 			priv->axi_clk = NULL;
 		} else {
 			err = clk_prepare_enable(priv->axi_clk);
 			if (err < 0)
-				goto err_gop_clk;
+				goto err_mg_core_clk;
 		}
 
 		/* Get system's tclk rate */
@@ -8789,9 +8801,9 @@ static int mvpp2_probe(struct platform_device *pdev)
 	}
 
 	if (priv->hw_version == MVPP22) {
-		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+		err = dma_set_mask(&pdev->dev, MVPP2_DESC_DMA_MASK);
 		if (err)
-			goto err_mg_clk;
+			goto err_axi_clk;
 		/* Sadly, the BM pools all share the same register to
 		 * store the high 32 bits of their address. So they
 		 * must all have the same high 32 bits, which forces
@@ -8799,14 +8811,14 @@ static int mvpp2_probe(struct platform_device *pdev)
 		 */
 		err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
 		if (err)
-			goto err_mg_clk;
+			goto err_axi_clk;
 	}
 
 	/* Initialize network controller */
 	err = mvpp2_init(pdev, priv);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to initialize controller\n");
-		goto err_mg_clk;
+		goto err_axi_clk;
 	}
 
 	/* Initialize ports */
@@ -8819,7 +8831,7 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (priv->port_count == 0) {
 		dev_err(&pdev->dev, "no ports enabled\n");
 		err = -ENODEV;
-		goto err_mg_clk;
+		goto err_axi_clk;
 	}
 
 	/* Statistics must be gathered regularly because some of them (like
@@ -8847,8 +8859,13 @@ err_port_probe:
 			mvpp2_port_remove(priv->port_list[i]);
 		i++;
 	}
-err_mg_clk:
+err_axi_clk:
 	clk_disable_unprepare(priv->axi_clk);
+
+err_mg_core_clk:
+	if (priv->hw_version == MVPP22)
+		clk_disable_unprepare(priv->mg_core_clk);
+err_mg_clk:
 	if (priv->hw_version == MVPP22)
 		clk_disable_unprepare(priv->mg_clk);
 err_gop_clk:
@@ -8895,6 +8912,7 @@ static int mvpp2_remove(struct platform_device *pdev)
 		return 0;
 
 	clk_disable_unprepare(priv->axi_clk);
+	clk_disable_unprepare(priv->mg_core_clk);
 	clk_disable_unprepare(priv->mg_clk);
 	clk_disable_unprepare(priv->pp_clk);
 	clk_disable_unprepare(priv->gop_clk);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index a30a2e95d13f..f11b45001cad 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1027,6 +1027,22 @@ static int mlx4_en_set_coalesce(struct net_device *dev,
 	if (!coal->tx_max_coalesced_frames_irq)
 		return -EINVAL;
 
+	if (coal->tx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs_low > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs_high > MLX4_EN_MAX_COAL_TIME) {
+		netdev_info(dev, "%s: maximum coalesce time supported is %d usecs\n",
+			    __func__, MLX4_EN_MAX_COAL_TIME);
+		return -ERANGE;
+	}
+
+	if (coal->tx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS ||
+	    coal->rx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS) {
+		netdev_info(dev, "%s: maximum coalesced frames supported is %d\n",
+			    __func__, MLX4_EN_MAX_COAL_PKTS);
+		return -ERANGE;
+	}
+
 	priv->rx_frames = (coal->rx_max_coalesced_frames ==
 			   MLX4_EN_AUTO_CONF) ?
 				MLX4_EN_RX_COAL_TARGET :
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index e0adac4a9a19..9670b33fc9b1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3324,12 +3324,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 					   MAX_TX_RINGS, GFP_KERNEL);
 		if (!priv->tx_ring[t]) {
 			err = -ENOMEM;
-			goto err_free_tx;
+			goto out;
 		}
 		priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
 					 MAX_TX_RINGS, GFP_KERNEL);
 		if (!priv->tx_cq[t]) {
-			kfree(priv->tx_ring[t]);
 			err = -ENOMEM;
 			goto out;
 		}
@@ -3582,11 +3581,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 
 	return 0;
 
-err_free_tx:
-	while (t--) {
-		kfree(priv->tx_ring[t]);
-		kfree(priv->tx_cq[t]);
-	}
 out:
 	mlx4_en_destroy_netdev(dev);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index a822f7a56bc5..685337d58276 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -43,12 +43,12 @@
 #include "fw.h"
 
 /*
- * We allocate in as big chunks as we can, up to a maximum of 256 KB
- * per chunk.
+ * We allocate in page size (default 4KB on many archs) chunks to avoid high
+ * order memory allocations in fragmented/high usage memory situation.
  */
 enum {
-	MLX4_ICM_ALLOC_SIZE	= 1 << 18,
-	MLX4_TABLE_CHUNK_SIZE	= 1 << 18
+	MLX4_ICM_ALLOC_SIZE	= PAGE_SIZE,
+	MLX4_TABLE_CHUNK_SIZE	= PAGE_SIZE,
 };
 
 static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
@@ -398,9 +398,11 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 	u64 size;
 
 	obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size;
+	if (WARN_ON(!obj_per_chunk))
+		return -EINVAL;
 	num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk;
 
-	table->icm      = kcalloc(num_icm, sizeof(*table->icm), GFP_KERNEL);
+	table->icm      = kvzalloc(num_icm * sizeof(*table->icm), GFP_KERNEL);
 	if (!table->icm)
 		return -ENOMEM;
 	table->virt     = virt;
@@ -446,7 +448,7 @@ err:
 			mlx4_free_icm(dev, table->icm[i], use_coherent);
 		}
 
-	kfree(table->icm);
+	kvfree(table->icm);
 
 	return -ENOMEM;
 }
@@ -462,5 +464,5 @@ void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table)
 			mlx4_free_icm(dev, table->icm[i], table->coherent);
 		}
 
-	kfree(table->icm);
+	kvfree(table->icm);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 2edcce98ab2d..65482f004e50 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -172,7 +172,7 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
 		spin_unlock_irqrestore(&priv->ctx_lock, flags);
 
-		mlx4_dbg(dev, "Inrerface for protocol %d restarted with when bonded mode is %s\n",
+		mlx4_dbg(dev, "Interface for protocol %d restarted with bonded mode %s\n",
 			 dev_ctx->intf->protocol, enable ?
 			 "enabled" : "disabled");
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index bfef69235d71..60172a38c4a4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1317,7 +1317,7 @@ static int mlx4_mf_unbond(struct mlx4_dev *dev)
 
 	ret = mlx4_unbond_fs_rules(dev);
 	if (ret)
-		mlx4_warn(dev, "multifunction unbond for flow rules failedi (%d)\n", ret);
+		mlx4_warn(dev, "multifunction unbond for flow rules failed (%d)\n", ret);
 	ret1 = mlx4_unbond_mac_table(dev);
 	if (ret1) {
 		mlx4_warn(dev, "multifunction unbond for MAC table failed (%d)\n", ret1);
@@ -2929,6 +2929,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 		mlx4_err(dev, "Failed to create file for port %d\n", port);
 		devlink_port_unregister(&info->devlink_port);
 		info->port = -1;
+		return err;
 	}
 
 	sprintf(info->dev_mtu_name, "mlx4_port%d_mtu", port);
@@ -2950,9 +2951,10 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 				   &info->port_attr);
 		devlink_port_unregister(&info->devlink_port);
 		info->port = -1;
+		return err;
 	}
 
-	return err;
+	return 0;
 }
 
 static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f7c81133594f..ace6545f82e6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -132,6 +132,9 @@
 #define MLX4_EN_TX_COAL_PKTS	16
 #define MLX4_EN_TX_COAL_TIME	0x10
 
+#define MLX4_EN_MAX_COAL_PKTS	U16_MAX
+#define MLX4_EN_MAX_COAL_TIME	U16_MAX
+
 #define MLX4_EN_RX_RATE_LOW		400000
 #define MLX4_EN_RX_COAL_TIME_LOW	0
 #define MLX4_EN_RX_RATE_HIGH		450000
@@ -552,8 +555,8 @@ struct mlx4_en_priv {
 	u16 rx_usecs_low;
 	u32 pkt_rate_high;
 	u16 rx_usecs_high;
-	u16 sample_interval;
-	u16 adaptive_rx_coal;
+	u32 sample_interval;
+	u32 adaptive_rx_coal;
 	u32 msg_enable;
 	u32 loopback_ok;
 	u32 validate_loopback;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 3aaf4bad6c5a..427e7a31862c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -393,11 +393,11 @@ struct mlx4_qp *mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn)
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
 	struct mlx4_qp *qp;
 
-	spin_lock(&qp_table->lock);
+	spin_lock_irq(&qp_table->lock);
 
 	qp = __mlx4_qp_lookup(dev, qpn);
 
-	spin_unlock(&qp_table->lock);
+	spin_unlock_irq(&qp_table->lock);
 	return qp;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 3d46ef48d5b8..c641d5656b2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1007,12 +1007,14 @@ static void mlx5e_trust_update_sq_inline_mode(struct mlx5e_priv *priv)
 
 	mutex_lock(&priv->state_lock);
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto out;
-
 	new_channels.params = priv->channels.params;
 	mlx5e_trust_update_tx_min_inline_mode(priv, &new_channels.params);
 
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
+
 	/* Skip if tx_min_inline is the same */
 	if (new_channels.params.tx_min_inline_mode ==
 	    priv->channels.params.tx_min_inline_mode)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index d8f68e4d1018..876c3e4c6193 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -877,13 +877,14 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 };
 
 static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params)
+				   struct mlx5e_params *params, u16 mtu)
 {
 	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
 	params->hard_mtu    = MLX5E_ETH_HARD_MTU;
+	params->sw_mtu      = mtu;
 	params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
 	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
 	params->log_rq_mtu_frames = MLX5E_REP_PARAMS_LOG_RQ_SIZE;
@@ -931,7 +932,7 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
 
 	priv->channels.params.num_channels = profile->max_nch(mdev);
 
-	mlx5e_build_rep_params(mdev, &priv->channels.params);
+	mlx5e_build_rep_params(mdev, &priv->channels.params, netdev->mtu);
 	mlx5e_build_rep_netdev(netdev);
 
 	mlx5e_timestamp_init(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 176645762e49..1ff0b0e93804 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -615,6 +615,45 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth)
 	return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
 }
 
+static __be32 mlx5e_get_fcs(struct sk_buff *skb)
+{
+	int last_frag_sz, bytes_in_prev, nr_frags;
+	u8 *fcs_p1, *fcs_p2;
+	skb_frag_t *last_frag;
+	__be32 fcs_bytes;
+
+	if (!skb_is_nonlinear(skb))
+		return *(__be32 *)(skb->data + skb->len - ETH_FCS_LEN);
+
+	nr_frags = skb_shinfo(skb)->nr_frags;
+	last_frag = &skb_shinfo(skb)->frags[nr_frags - 1];
+	last_frag_sz = skb_frag_size(last_frag);
+
+	/* If all FCS data is in last frag */
+	if (last_frag_sz >= ETH_FCS_LEN)
+		return *(__be32 *)(skb_frag_address(last_frag) +
+				   last_frag_sz - ETH_FCS_LEN);
+
+	fcs_p2 = (u8 *)skb_frag_address(last_frag);
+	bytes_in_prev = ETH_FCS_LEN - last_frag_sz;
+
+	/* Find where the other part of the FCS is - Linear or another frag */
+	if (nr_frags == 1) {
+		fcs_p1 = skb_tail_pointer(skb);
+	} else {
+		skb_frag_t *prev_frag = &skb_shinfo(skb)->frags[nr_frags - 2];
+
+		fcs_p1 = skb_frag_address(prev_frag) +
+			    skb_frag_size(prev_frag);
+	}
+	fcs_p1 -= bytes_in_prev;
+
+	memcpy(&fcs_bytes, fcs_p1, bytes_in_prev);
+	memcpy(((u8 *)&fcs_bytes) + bytes_in_prev, fcs_p2, last_frag_sz);
+
+	return fcs_bytes;
+}
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -643,6 +682,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum = csum_partial(skb->data + ETH_HLEN,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
+		if (unlikely(netdev->features & NETIF_F_RXFCS))
+			skb->csum = csum_add(skb->csum,
+					     (__force __wsum)mlx5e_get_fcs(skb));
 		rq->stats.csum_complete++;
 		return;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 707976482c09..027f54ac1ca2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -290,7 +290,7 @@ static int mlx5e_test_loopback(struct mlx5e_priv *priv)
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 		netdev_err(priv->netdev,
-			   "\tCan't perform loobpack test while device is down\n");
+			   "\tCan't perform loopback test while device is down\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4197001f9801..b94276db3ce9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1261,6 +1261,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 						  f->mask);
 		addr_type = key->addr_type;
 
+		/* the HW doesn't support frag first/later */
+		if (mask->flags & FLOW_DIS_FIRST_FRAG)
+			return -EOPNOTSUPP;
+
 		if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
@@ -1864,7 +1868,8 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 	}
 
 	ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
-	if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+	if (modify_ip_header && ip_proto != IPPROTO_TCP &&
+	    ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) {
 		pr_info("can't offload re-write of ip proto %d\n", ip_proto);
 		return false;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 20297108528a..5532aa3675c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -255,7 +255,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		dma_addr = dma_map_single(sq->pdev, skb_data, headlen,
 					  DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
-			return -ENOMEM;
+			goto dma_unmap_wqe_err;
 
 		dseg->addr       = cpu_to_be64(dma_addr);
 		dseg->lkey       = sq->mkey_be;
@@ -273,7 +273,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
 					    DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
-			return -ENOMEM;
+			goto dma_unmap_wqe_err;
 
 		dseg->addr       = cpu_to_be64(dma_addr);
 		dseg->lkey       = sq->mkey_be;
@@ -285,6 +285,10 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	}
 
 	return num_dma;
+
+dma_unmap_wqe_err:
+	mlx5e_dma_unmap_wqe_err(sq, num_dma);
+	return -ENOMEM;
 }
 
 static inline void
@@ -380,17 +384,15 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
 					  (struct mlx5_wqe_data_seg *)cseg + ds_cnt);
 	if (unlikely(num_dma < 0))
-		goto dma_unmap_wqe_err;
+		goto err_drop;
 
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
 			     num_bytes, num_dma, wi, cseg);
 
 	return NETDEV_TX_OK;
 
-dma_unmap_wqe_err:
+err_drop:
 	sq->stats.dropped++;
-	mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
 	dev_kfree_skb_any(skb);
 
 	return NETDEV_TX_OK;
@@ -645,17 +647,15 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
 					  (struct mlx5_wqe_data_seg *)cseg + ds_cnt);
 	if (unlikely(num_dma < 0))
-		goto dma_unmap_wqe_err;
+		goto err_drop;
 
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
 			     num_bytes, num_dma, wi, cseg);
 
 	return NETDEV_TX_OK;
 
-dma_unmap_wqe_err:
+err_drop:
 	sq->stats.dropped++;
-	mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
 	dev_kfree_skb_any(skb);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index c1c94974e16b..1814f803bd2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -34,6 +34,9 @@
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
 #include "mlx5_core.h"
 #include "fpga/core.h"
 #include "eswitch.h"
@@ -923,3 +926,28 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
+
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq *eq;
+
+#ifdef CONFIG_RFS_ACCEL
+	if (dev->rmap) {
+		free_irq_cpu_rmap(dev->rmap);
+		dev->rmap = NULL;
+	}
+#endif
+	list_for_each_entry(eq, &table->comp_eqs_list, list)
+		free_irq(eq->irqn, eq);
+
+	free_irq(table->pages_eq.irqn, &table->pages_eq);
+	free_irq(table->async_eq.irqn, &table->async_eq);
+	free_irq(table->cmd_eq.irqn, &table->cmd_eq);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (MLX5_CAP_GEN(dev, pg))
+		free_irq(table->pfault_eq.irqn, &table->pfault_eq);
+#endif
+	pci_free_irq_vectors(dev->pdev);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 332bc56306bf..1352d13eedb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2175,26 +2175,35 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 	memset(vf_stats, 0, sizeof(*vf_stats));
 	vf_stats->rx_packets =
 		MLX5_GET_CTR(out, received_eth_unicast.packets) +
+		MLX5_GET_CTR(out, received_ib_unicast.packets) +
 		MLX5_GET_CTR(out, received_eth_multicast.packets) +
+		MLX5_GET_CTR(out, received_ib_multicast.packets) +
 		MLX5_GET_CTR(out, received_eth_broadcast.packets);
 
 	vf_stats->rx_bytes =
 		MLX5_GET_CTR(out, received_eth_unicast.octets) +
+		MLX5_GET_CTR(out, received_ib_unicast.octets) +
 		MLX5_GET_CTR(out, received_eth_multicast.octets) +
+		MLX5_GET_CTR(out, received_ib_multicast.octets) +
 		MLX5_GET_CTR(out, received_eth_broadcast.octets);
 
 	vf_stats->tx_packets =
 		MLX5_GET_CTR(out, transmitted_eth_unicast.packets) +
+		MLX5_GET_CTR(out, transmitted_ib_unicast.packets) +
 		MLX5_GET_CTR(out, transmitted_eth_multicast.packets) +
+		MLX5_GET_CTR(out, transmitted_ib_multicast.packets) +
 		MLX5_GET_CTR(out, transmitted_eth_broadcast.packets);
 
 	vf_stats->tx_bytes =
 		MLX5_GET_CTR(out, transmitted_eth_unicast.octets) +
+		MLX5_GET_CTR(out, transmitted_ib_unicast.octets) +
 		MLX5_GET_CTR(out, transmitted_eth_multicast.octets) +
+		MLX5_GET_CTR(out, transmitted_ib_multicast.octets) +
 		MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
 
 	vf_stats->multicast =
-		MLX5_GET_CTR(out, received_eth_multicast.packets);
+		MLX5_GET_CTR(out, received_eth_multicast.packets) +
+		MLX5_GET_CTR(out, received_ib_multicast.packets);
 
 	vf_stats->broadcast =
 		MLX5_GET_CTR(out, received_eth_broadcast.packets);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 0f5da499a223..fad8c2e3804e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -237,19 +237,17 @@ static void *mlx5_fpga_ipsec_cmd_exec(struct mlx5_core_dev *mdev,
 	context->buf.sg[0].data = &context->command;
 
 	spin_lock_irqsave(&fdev->ipsec->pending_cmds_lock, flags);
-	list_add_tail(&context->list, &fdev->ipsec->pending_cmds);
+	res = mlx5_fpga_sbu_conn_sendmsg(fdev->ipsec->conn, &context->buf);
+	if (!res)
+		list_add_tail(&context->list, &fdev->ipsec->pending_cmds);
 	spin_unlock_irqrestore(&fdev->ipsec->pending_cmds_lock, flags);
 
-	res = mlx5_fpga_sbu_conn_sendmsg(fdev->ipsec->conn, &context->buf);
 	if (res) {
-		mlx5_fpga_warn(fdev, "Failure sending IPSec command: %d\n",
-			       res);
-		spin_lock_irqsave(&fdev->ipsec->pending_cmds_lock, flags);
-		list_del(&context->list);
-		spin_unlock_irqrestore(&fdev->ipsec->pending_cmds_lock, flags);
+		mlx5_fpga_warn(fdev, "Failed to send IPSec command: %d\n", res);
 		kfree(context);
 		return ERR_PTR(res);
 	}
+
 	/* Context will be freed by wait func after completion */
 	return context;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index de51e7c39bc8..c39c1692e674 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -187,6 +187,7 @@ static void del_sw_ns(struct fs_node *node);
 static void del_sw_hw_rule(struct fs_node *node);
 static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 				struct mlx5_flow_destination *d2);
+static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns);
 static struct mlx5_flow_rule *
 find_flow_rule(struct fs_fte *fte,
 	       struct mlx5_flow_destination *dest);
@@ -481,7 +482,8 @@ static void del_sw_hw_rule(struct fs_node *node)
 
 	if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER  &&
 	    --fte->dests_size) {
-		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
+			      BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
 		fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
 		update_fte = true;
 		goto out;
@@ -2351,23 +2353,27 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
 
 static int init_root_ns(struct mlx5_flow_steering *steering)
 {
+	int err;
+
 	steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX);
 	if (!steering->root_ns)
-		goto cleanup;
+		return -ENOMEM;
 
-	if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node))
-		goto cleanup;
+	err = init_root_tree(steering, &root_fs, &steering->root_ns->ns.node);
+	if (err)
+		goto out_err;
 
 	set_prio_attrs(steering->root_ns);
-
-	if (create_anchor_flow_table(steering))
-		goto cleanup;
+	err = create_anchor_flow_table(steering);
+	if (err)
+		goto out_err;
 
 	return 0;
 
-cleanup:
-	mlx5_cleanup_fs(steering->dev);
-	return -ENOMEM;
+out_err:
+	cleanup_root_ns(steering->root_ns);
+	steering->root_ns = NULL;
+	return err;
 }
 
 static void clean_tree(struct fs_node *node)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 63a8ea31601c..e2c465b0b3f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1587,6 +1587,14 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
 
 	mlx5_enter_error_state(dev, true);
 
+	/* Some platforms requiring freeing the IRQ's in the shutdown
+	 * flow. If they aren't freed they can't be allocated after
+	 * kexec. There is no need to cleanup the mlx5_core software
+	 * contexts.
+	 */
+	mlx5_irq_clear_affinity_hints(dev);
+	mlx5_core_eq_free_irqs(dev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 7d001fe6e631..023882d9a22e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -128,6 +128,8 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 		       u32 *out, int outlen);
 int mlx5_start_eqs(struct mlx5_core_dev *dev);
 void mlx5_stop_eqs(struct mlx5_core_dev *dev);
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
 u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
 void mlx5_cq_tasklet_cb(unsigned long data);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 93ea56620a24..e13ac3b8dff7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1100,11 +1100,11 @@ err_emad_init:
 err_alloc_lag_mapping:
 	mlxsw_ports_fini(mlxsw_core);
 err_ports_init:
-	mlxsw_bus->fini(bus_priv);
-err_bus_init:
 	if (!reload)
 		devlink_resources_unregister(devlink, NULL);
 err_register_resources:
+	mlxsw_bus->fini(bus_priv);
+err_bus_init:
 	if (!reload)
 		devlink_free(devlink);
 err_devlink_alloc:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ca38a30fbe91..adc6ab2cf429 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4433,6 +4433,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on an OVS port");
 			return -EINVAL;
 		}
+		if (is_vlan_dev(upper_dev) &&
+		    vlan_dev_vlan_id(upper_dev) == 1) {
+			NL_SET_ERR_MSG_MOD(extack, "Creating a VLAN device with VID 1 is unsupported: VLAN 1 carries untagged traffic");
+			return -EINVAL;
+		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index c11c9a635866..4ed01182a82c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1718,13 +1718,11 @@ __mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct net_device *dev = mlxsw_sp_port->dev;
 	int err;
 
-	if (bridge_port->bridge_device->multicast_enabled) {
-		if (bridge_port->bridge_device->multicast_enabled) {
-			err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid,
-						     false);
-			if (err)
-				netdev_err(dev, "Unable to remove port from SMID\n");
-		}
+	if (bridge_port->bridge_device->multicast_enabled &&
+	    !bridge_port->mrouter) {
+		err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, false);
+		if (err)
+			netdev_err(dev, "Unable to remove port from SMID\n");
 	}
 
 	err = mlxsw_sp_port_remove_from_mid(mlxsw_sp_port, mid);
diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 7ed08486ae23..c805dcbebd02 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -84,7 +84,7 @@ static int sonic_open(struct net_device *dev)
 	for (i = 0; i < SONIC_NUM_RRS; i++) {
 		dma_addr_t laddr = dma_map_single(lp->device, skb_put(lp->rx_skb[i], SONIC_RBSIZE),
 		                                  SONIC_RBSIZE, DMA_FROM_DEVICE);
-		if (!laddr) {
+		if (dma_mapping_error(lp->device, laddr)) {
 			while(i > 0) { /* free any that were mapped successfully */
 				i--;
 				dma_unmap_single(lp->device, lp->rx_laddr[i], SONIC_RBSIZE, DMA_FROM_DEVICE);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 1dc424685f4e..35fb31f682af 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -335,7 +335,7 @@ static int nfp_bpf_parse_capabilities(struct nfp_app *app)
 		return PTR_ERR(mem) == -ENOENT ? 0 : PTR_ERR(mem);
 
 	start = mem;
-	while (mem - start + 8 < nfp_cpp_area_size(area)) {
+	while (mem - start + 8 <= nfp_cpp_area_size(area)) {
 		u8 __iomem *value;
 		u32 type, length;
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index b3567a596fc1..80df9a5d4217 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -183,17 +183,21 @@ static int
 nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 			const struct tc_action *action,
 			struct nfp_fl_pre_tunnel *pre_tun,
-			enum nfp_flower_tun_type tun_type)
+			enum nfp_flower_tun_type tun_type,
+			struct net_device *netdev)
 {
 	size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
 	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
 	u32 tmp_set_ip_tun_type_index = 0;
 	/* Currently support one pre-tunnel so index is always 0. */
 	int pretun_idx = 0;
+	struct net *net;
 
 	if (ip_tun->options_len)
 		return -EOPNOTSUPP;
 
+	net = dev_net(netdev);
+
 	set_tun->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
 	set_tun->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 
@@ -204,6 +208,7 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 
 	set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
 	set_tun->tun_id = ip_tun->key.tun_id;
+	set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
 
 	/* Complete pre_tunnel action. */
 	pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
@@ -511,7 +516,8 @@ nfp_flower_loop_action(const struct tc_action *a,
 		*a_len += sizeof(struct nfp_fl_pre_tunnel);
 
 		set_tun = (void *)&nfp_fl->action_data[*a_len];
-		err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type);
+		err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type,
+					      netdev);
 		if (err)
 			return err;
 		*a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
index 3735c09d2112..577659f332e4 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
@@ -258,9 +258,6 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
 	case NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS:
 		nfp_tunnel_keep_alive(app, skb);
 		break;
-	case NFP_FLOWER_CMSG_TYPE_TUN_NEIGH:
-		/* Acks from the NFP that the route is added - ignore. */
-		break;
 	default:
 		nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n",
 				     type);
@@ -275,18 +272,49 @@ out:
 
 void nfp_flower_cmsg_process_rx(struct work_struct *work)
 {
+	struct sk_buff_head cmsg_joined;
 	struct nfp_flower_priv *priv;
 	struct sk_buff *skb;
 
 	priv = container_of(work, struct nfp_flower_priv, cmsg_work);
+	skb_queue_head_init(&cmsg_joined);
+
+	spin_lock_bh(&priv->cmsg_skbs_high.lock);
+	skb_queue_splice_tail_init(&priv->cmsg_skbs_high, &cmsg_joined);
+	spin_unlock_bh(&priv->cmsg_skbs_high.lock);
 
-	while ((skb = skb_dequeue(&priv->cmsg_skbs)))
+	spin_lock_bh(&priv->cmsg_skbs_low.lock);
+	skb_queue_splice_tail_init(&priv->cmsg_skbs_low, &cmsg_joined);
+	spin_unlock_bh(&priv->cmsg_skbs_low.lock);
+
+	while ((skb = __skb_dequeue(&cmsg_joined)))
 		nfp_flower_cmsg_process_one_rx(priv->app, skb);
 }
 
-void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb)
+static void
+nfp_flower_queue_ctl_msg(struct nfp_app *app, struct sk_buff *skb, int type)
 {
 	struct nfp_flower_priv *priv = app->priv;
+	struct sk_buff_head *skb_head;
+
+	if (type == NFP_FLOWER_CMSG_TYPE_PORT_REIFY ||
+	    type == NFP_FLOWER_CMSG_TYPE_PORT_MOD)
+		skb_head = &priv->cmsg_skbs_high;
+	else
+		skb_head = &priv->cmsg_skbs_low;
+
+	if (skb_queue_len(skb_head) >= NFP_FLOWER_WORKQ_MAX_SKBS) {
+		nfp_flower_cmsg_warn(app, "Dropping queued control messages\n");
+		dev_kfree_skb_any(skb);
+		return;
+	}
+
+	skb_queue_tail(skb_head, skb);
+	schedule_work(&priv->cmsg_work);
+}
+
+void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb)
+{
 	struct nfp_flower_cmsg_hdr *cmsg_hdr;
 
 	cmsg_hdr = nfp_flower_cmsg_get_hdr(skb);
@@ -306,8 +334,10 @@ void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb)
 		   nfp_flower_process_mtu_ack(app, skb)) {
 		/* Handle MTU acks outside wq to prevent RTNL conflict. */
 		dev_consume_skb_any(skb);
+	} else if (cmsg_hdr->type == NFP_FLOWER_CMSG_TYPE_TUN_NEIGH) {
+		/* Acks from the NFP that the route is added - ignore. */
+		dev_consume_skb_any(skb);
 	} else {
-		skb_queue_tail(&priv->cmsg_skbs, skb);
-		schedule_work(&priv->cmsg_work);
+		nfp_flower_queue_ctl_msg(app, skb, cmsg_hdr->type);
 	}
 }
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 96bc0e33980c..bee4367a2c38 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -108,6 +108,8 @@
 #define NFP_FL_IPV4_TUNNEL_TYPE		GENMASK(7, 4)
 #define NFP_FL_IPV4_PRE_TUN_INDEX	GENMASK(2, 0)
 
+#define NFP_FLOWER_WORKQ_MAX_SKBS	30000
+
 #define nfp_flower_cmsg_warn(app, fmt, args...)                         \
 	do {                                                            \
 		if (net_ratelimit())                                    \
@@ -188,7 +190,10 @@ struct nfp_fl_set_ipv4_udp_tun {
 	__be16 reserved;
 	__be64 tun_id __packed;
 	__be32 tun_type_index;
-	__be32 extra[3];
+	__be16 reserved2;
+	u8 ttl;
+	u8 reserved3;
+	__be32 extra[2];
 };
 
 /* Metadata with L2 (1W/4B)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 6357e0720f43..84e3b9f5abb1 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -52,8 +52,6 @@
 
 #define NFP_FLOWER_ALLOWED_VER 0x0001000000010000UL
 
-#define NFP_FLOWER_FRAME_HEADROOM	158
-
 static const char *nfp_flower_extra_cap(struct nfp_app *app, struct nfp_net *nn)
 {
 	return "FLOWER";
@@ -360,7 +358,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 		}
 
 		SET_NETDEV_DEV(repr, &priv->nn->pdev->dev);
-		nfp_net_get_mac_addr(app->pf, port);
+		nfp_net_get_mac_addr(app->pf, repr, port);
 
 		cmsg_port_id = nfp_flower_cmsg_phys_port(phys_port);
 		err = nfp_repr_init(app, repr,
@@ -519,7 +517,8 @@ static int nfp_flower_init(struct nfp_app *app)
 
 	app->priv = app_priv;
 	app_priv->app = app;
-	skb_queue_head_init(&app_priv->cmsg_skbs);
+	skb_queue_head_init(&app_priv->cmsg_skbs_high);
+	skb_queue_head_init(&app_priv->cmsg_skbs_low);
 	INIT_WORK(&app_priv->cmsg_work, nfp_flower_cmsg_process_rx);
 	init_waitqueue_head(&app_priv->reify_wait_queue);
 
@@ -549,7 +548,8 @@ static void nfp_flower_clean(struct nfp_app *app)
 {
 	struct nfp_flower_priv *app_priv = app->priv;
 
-	skb_queue_purge(&app_priv->cmsg_skbs);
+	skb_queue_purge(&app_priv->cmsg_skbs_high);
+	skb_queue_purge(&app_priv->cmsg_skbs_low);
 	flush_work(&app_priv->cmsg_work);
 
 	nfp_flower_metadata_cleanup(app);
@@ -557,22 +557,6 @@ static void nfp_flower_clean(struct nfp_app *app)
 	app->priv = NULL;
 }
 
-static int
-nfp_flower_check_mtu(struct nfp_app *app, struct net_device *netdev,
-		     int new_mtu)
-{
-	/* The flower fw reserves NFP_FLOWER_FRAME_HEADROOM bytes of the
-	 * supported max MTU to allow for appending tunnel headers. To prevent
-	 * unexpected behaviour this needs to be accounted for.
-	 */
-	if (new_mtu > netdev->max_mtu - NFP_FLOWER_FRAME_HEADROOM) {
-		nfp_err(app->cpp, "New MTU (%d) is not valid\n", new_mtu);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static bool nfp_flower_check_ack(struct nfp_flower_priv *app_priv)
 {
 	bool ret;
@@ -654,7 +638,6 @@ const struct nfp_app_type app_flower = {
 	.init		= nfp_flower_init,
 	.clean		= nfp_flower_clean,
 
-	.check_mtu	= nfp_flower_check_mtu,
 	.repr_change_mtu  = nfp_flower_repr_change_mtu,
 
 	.vnic_alloc	= nfp_flower_vnic_alloc,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index e030b3ce4510..c67e1b54c614 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -107,7 +107,10 @@ struct nfp_mtu_conf {
  * @mask_table:		Hash table used to store masks
  * @flow_table:		Hash table used to store flower rules
  * @cmsg_work:		Workqueue for control messages processing
- * @cmsg_skbs:		List of skbs for control message processing
+ * @cmsg_skbs_high:	List of higher priority skbs for control message
+ *			processing
+ * @cmsg_skbs_low:	List of lower priority skbs for control message
+ *			processing
  * @nfp_mac_off_list:	List of MAC addresses to offload
  * @nfp_mac_index_list:	List of unique 8-bit indexes for non NFP netdevs
  * @nfp_ipv4_off_list:	List of IPv4 addresses to offload
@@ -136,7 +139,8 @@ struct nfp_flower_priv {
 	DECLARE_HASHTABLE(mask_table, NFP_FLOWER_MASK_HASH_BITS);
 	DECLARE_HASHTABLE(flow_table, NFP_FLOWER_HASH_BITS);
 	struct work_struct cmsg_work;
-	struct sk_buff_head cmsg_skbs;
+	struct sk_buff_head cmsg_skbs_high;
+	struct sk_buff_head cmsg_skbs_low;
 	struct list_head nfp_mac_off_list;
 	struct list_head nfp_mac_index_list;
 	struct list_head nfp_ipv4_off_list;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c b/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c
index 2a2f2fbc8850..b9618c37403f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c
@@ -69,7 +69,7 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn,
 	if (err)
 		return err < 0 ? err : 0;
 
-	nfp_net_get_mac_addr(app->pf, nn->port);
+	nfp_net_get_mac_addr(app->pf, nn->dp.netdev, nn->port);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h
index add46e28212b..42211083b51f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h
@@ -171,7 +171,9 @@ void nfp_net_pci_remove(struct nfp_pf *pf);
 int nfp_hwmon_register(struct nfp_pf *pf);
 void nfp_hwmon_unregister(struct nfp_pf *pf);
 
-void nfp_net_get_mac_addr(struct nfp_pf *pf, struct nfp_port *port);
+void
+nfp_net_get_mac_addr(struct nfp_pf *pf, struct net_device *netdev,
+		     struct nfp_port *port);
 
 bool nfp_ctrl_tx(struct nfp_net *nn, struct sk_buff *skb);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 15fa47f622aa..45cd2092e498 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -67,23 +67,26 @@
 /**
  * nfp_net_get_mac_addr() - Get the MAC address.
  * @pf:       NFP PF handle
+ * @netdev:   net_device to set MAC address on
  * @port:     NFP port structure
  *
  * First try to get the MAC address from NSP ETH table. If that
  * fails generate a random address.
  */
-void nfp_net_get_mac_addr(struct nfp_pf *pf, struct nfp_port *port)
+void
+nfp_net_get_mac_addr(struct nfp_pf *pf, struct net_device *netdev,
+		     struct nfp_port *port)
 {
 	struct nfp_eth_table_port *eth_port;
 
 	eth_port = __nfp_port_get_eth_port(port);
 	if (!eth_port) {
-		eth_hw_addr_random(port->netdev);
+		eth_hw_addr_random(netdev);
 		return;
 	}
 
-	ether_addr_copy(port->netdev->dev_addr, eth_port->mac_addr);
-	ether_addr_copy(port->netdev->perm_addr, eth_port->mac_addr);
+	ether_addr_copy(netdev->dev_addr, eth_port->mac_addr);
+	ether_addr_copy(netdev->perm_addr, eth_port->mac_addr);
 }
 
 static struct nfp_eth_table_port *
@@ -511,16 +514,18 @@ static int nfp_net_pci_map_mem(struct nfp_pf *pf)
 		return PTR_ERR(mem);
 	}
 
-	min_size =  NFP_MAC_STATS_SIZE * (pf->eth_tbl->max_index + 1);
-	pf->mac_stats_mem = nfp_rtsym_map(pf->rtbl, "_mac_stats",
-					  "net.macstats", min_size,
-					  &pf->mac_stats_bar);
-	if (IS_ERR(pf->mac_stats_mem)) {
-		if (PTR_ERR(pf->mac_stats_mem) != -ENOENT) {
-			err = PTR_ERR(pf->mac_stats_mem);
-			goto err_unmap_ctrl;
+	if (pf->eth_tbl) {
+		min_size =  NFP_MAC_STATS_SIZE * (pf->eth_tbl->max_index + 1);
+		pf->mac_stats_mem = nfp_rtsym_map(pf->rtbl, "_mac_stats",
+						  "net.macstats", min_size,
+						  &pf->mac_stats_bar);
+		if (IS_ERR(pf->mac_stats_mem)) {
+			if (PTR_ERR(pf->mac_stats_mem) != -ENOENT) {
+				err = PTR_ERR(pf->mac_stats_mem);
+				goto err_unmap_ctrl;
+			}
+			pf->mac_stats_mem = NULL;
 		}
-		pf->mac_stats_mem = NULL;
 	}
 
 	pf->vf_cfg_mem = nfp_net_pf_map_rtsym(pf, "net.vfcfg",
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
index f7b958181126..cb28ac03e4ca 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
@@ -211,8 +211,11 @@ int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex)
 			break;
 
 		err = msleep_interruptible(timeout_ms);
-		if (err != 0)
+		if (err != 0) {
+			nfp_info(mutex->cpp,
+				 "interrupted waiting for NFP mutex\n");
 			return -ERESTARTSYS;
+		}
 
 		if (time_is_before_eq_jiffies(warn_at)) {
 			warn_at = jiffies + NFP_MUTEX_WAIT_NEXT_WARN * HZ;
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 99bb679a9801..2abee0fe3a7c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -281,8 +281,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg, u32 nsp_cpp, u64 addr,
 		if ((*reg & mask) == val)
 			return 0;
 
-		if (msleep_interruptible(25))
-			return -ERESTARTSYS;
+		msleep(25);
 
 		if (time_after(start_time, wait_until))
 			return -ETIMEDOUT;
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 27364b7572fc..b092894dd128 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -1170,7 +1170,7 @@ static void *nixge_get_nvmem_address(struct device *dev)
 
 	cell = nvmem_cell_get(dev, "address");
 	if (IS_ERR(cell))
-		return cell;
+		return NULL;
 
 	mac = nvmem_cell_read(cell, &cell_size);
 	nvmem_cell_put(cell);
@@ -1183,7 +1183,7 @@ static int nixge_probe(struct platform_device *pdev)
 	struct nixge_priv *priv;
 	struct net_device *ndev;
 	struct resource *dmares;
-	const char *mac_addr;
+	const u8 *mac_addr;
 	int err;
 
 	ndev = alloc_etherdev(sizeof(*priv));
@@ -1202,10 +1202,12 @@ static int nixge_probe(struct platform_device *pdev)
 	ndev->max_mtu = NIXGE_JUMBO_MTU;
 
 	mac_addr = nixge_get_nvmem_address(&pdev->dev);
-	if (mac_addr && is_valid_ether_addr(mac_addr))
+	if (mac_addr && is_valid_ether_addr(mac_addr)) {
 		ether_addr_copy(ndev->dev_addr, mac_addr);
-	else
+		kfree(mac_addr);
+	} else {
 		eth_hw_addr_random(ndev);
+	}
 
 	priv = netdev_priv(ndev);
 	priv->ndev = ndev;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 00f41c145d4d..820b226d6ff8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -77,7 +77,7 @@
 #define ILT_CFG_REG(cli, reg)	PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
 
 /* ILT entry structure */
-#define ILT_ENTRY_PHY_ADDR_MASK		0x000FFFFFFFFFFFULL
+#define ILT_ENTRY_PHY_ADDR_MASK		(~0ULL >> 12)
 #define ILT_ENTRY_PHY_ADDR_SHIFT	0
 #define ILT_ENTRY_VALID_MASK		0x1ULL
 #define ILT_ENTRY_VALID_SHIFT		52
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index e874504e8b28..8667799d0069 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -115,8 +115,7 @@ int qed_l2_alloc(struct qed_hwfn *p_hwfn)
 
 void qed_l2_setup(struct qed_hwfn *p_hwfn)
 {
-	if (p_hwfn->hw_info.personality != QED_PCI_ETH &&
-	    p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+	if (!QED_IS_L2_PERSONALITY(p_hwfn))
 		return;
 
 	mutex_init(&p_hwfn->p_l2_info->lock);
@@ -126,8 +125,7 @@ void qed_l2_free(struct qed_hwfn *p_hwfn)
 {
 	u32 i;
 
-	if (p_hwfn->hw_info.personality != QED_PCI_ETH &&
-	    p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+	if (!QED_IS_L2_PERSONALITY(p_hwfn))
 		return;
 
 	if (!p_hwfn->p_l2_info)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 74fc626b1ec1..468c59d2e491 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -292,6 +292,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 	struct qed_ll2_tx_packet *p_pkt = NULL;
 	struct qed_ll2_info *p_ll2_conn;
 	struct qed_ll2_tx_queue *p_tx;
+	unsigned long flags = 0;
 	dma_addr_t tx_frag;
 
 	p_ll2_conn = qed_ll2_handle_sanity_inactive(p_hwfn, connection_handle);
@@ -300,6 +301,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 
 	p_tx = &p_ll2_conn->tx_queue;
 
+	spin_lock_irqsave(&p_tx->lock, flags);
 	while (!list_empty(&p_tx->active_descq)) {
 		p_pkt = list_first_entry(&p_tx->active_descq,
 					 struct qed_ll2_tx_packet, list_entry);
@@ -309,6 +311,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 		list_del(&p_pkt->list_entry);
 		b_last_packet = list_empty(&p_tx->active_descq);
 		list_add_tail(&p_pkt->list_entry, &p_tx->free_descq);
+		spin_unlock_irqrestore(&p_tx->lock, flags);
 		if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO) {
 			struct qed_ooo_buffer *p_buffer;
 
@@ -328,7 +331,9 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 						      b_last_frag,
 						      b_last_packet);
 		}
+		spin_lock_irqsave(&p_tx->lock, flags);
 	}
+	spin_unlock_irqrestore(&p_tx->lock, flags);
 }
 
 static int qed_ll2_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
@@ -556,6 +561,7 @@ static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 	struct qed_ll2_info *p_ll2_conn = NULL;
 	struct qed_ll2_rx_packet *p_pkt = NULL;
 	struct qed_ll2_rx_queue *p_rx;
+	unsigned long flags = 0;
 
 	p_ll2_conn = qed_ll2_handle_sanity_inactive(p_hwfn, connection_handle);
 	if (!p_ll2_conn)
@@ -563,13 +569,14 @@ static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 
 	p_rx = &p_ll2_conn->rx_queue;
 
+	spin_lock_irqsave(&p_rx->lock, flags);
 	while (!list_empty(&p_rx->active_descq)) {
 		p_pkt = list_first_entry(&p_rx->active_descq,
 					 struct qed_ll2_rx_packet, list_entry);
 		if (!p_pkt)
 			break;
-
 		list_move_tail(&p_pkt->list_entry, &p_rx->free_descq);
+		spin_unlock_irqrestore(&p_rx->lock, flags);
 
 		if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO) {
 			struct qed_ooo_buffer *p_buffer;
@@ -588,7 +595,30 @@ static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 						      cookie,
 						      rx_buf_addr, b_last);
 		}
+		spin_lock_irqsave(&p_rx->lock, flags);
 	}
+	spin_unlock_irqrestore(&p_rx->lock, flags);
+}
+
+static bool
+qed_ll2_lb_rxq_handler_slowpath(struct qed_hwfn *p_hwfn,
+				struct core_rx_slow_path_cqe *p_cqe)
+{
+	struct ooo_opaque *iscsi_ooo;
+	u32 cid;
+
+	if (p_cqe->ramrod_cmd_id != CORE_RAMROD_RX_QUEUE_FLUSH)
+		return false;
+
+	iscsi_ooo = (struct ooo_opaque *)&p_cqe->opaque_data;
+	if (iscsi_ooo->ooo_opcode != TCP_EVENT_DELETE_ISLES)
+		return false;
+
+	/* Need to make a flush */
+	cid = le32_to_cpu(iscsi_ooo->cid);
+	qed_ooo_release_connection_isles(p_hwfn, p_hwfn->p_ooo_info, cid);
+
+	return true;
 }
 
 static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn,
@@ -617,6 +647,11 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn,
 		cq_old_idx = qed_chain_get_cons_idx(&p_rx->rcq_chain);
 		cqe_type = cqe->rx_cqe_sp.type;
 
+		if (cqe_type == CORE_RX_CQE_TYPE_SLOW_PATH)
+			if (qed_ll2_lb_rxq_handler_slowpath(p_hwfn,
+							    &cqe->rx_cqe_sp))
+				continue;
+
 		if (cqe_type != CORE_RX_CQE_TYPE_REGULAR) {
 			DP_NOTICE(p_hwfn,
 				  "Got a non-regular LB LL2 completion [type 0x%02x]\n",
@@ -794,6 +829,9 @@ static int qed_ll2_lb_rxq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
 	struct qed_ll2_info *p_ll2_conn = (struct qed_ll2_info *)p_cookie;
 	int rc;
 
+	if (!QED_LL2_RX_REGISTERED(p_ll2_conn))
+		return 0;
+
 	rc = qed_ll2_lb_rxq_handler(p_hwfn, p_ll2_conn);
 	if (rc)
 		return rc;
@@ -814,6 +852,9 @@ static int qed_ll2_lb_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
 	u16 new_idx = 0, num_bds = 0;
 	int rc;
 
+	if (!QED_LL2_TX_REGISTERED(p_ll2_conn))
+		return 0;
+
 	new_idx = le16_to_cpu(*p_tx->p_fw_cons);
 	num_bds = ((s16)new_idx - (s16)p_tx->bds_idx);
 
@@ -1867,17 +1908,25 @@ int qed_ll2_terminate_connection(void *cxt, u8 connection_handle)
 
 	/* Stop Tx & Rx of connection, if needed */
 	if (QED_LL2_TX_REGISTERED(p_ll2_conn)) {
+		p_ll2_conn->tx_queue.b_cb_registred = false;
+		smp_wmb(); /* Make sure this is seen by ll2_lb_rxq_completion */
 		rc = qed_sp_ll2_tx_queue_stop(p_hwfn, p_ll2_conn);
 		if (rc)
 			goto out;
+
 		qed_ll2_txq_flush(p_hwfn, connection_handle);
+		qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index);
 	}
 
 	if (QED_LL2_RX_REGISTERED(p_ll2_conn)) {
+		p_ll2_conn->rx_queue.b_cb_registred = false;
+		smp_wmb(); /* Make sure this is seen by ll2_lb_rxq_completion */
 		rc = qed_sp_ll2_rx_queue_stop(p_hwfn, p_ll2_conn);
 		if (rc)
 			goto out;
+
 		qed_ll2_rxq_flush(p_hwfn, connection_handle);
+		qed_int_unregister_cb(p_hwfn, p_ll2_conn->rx_queue.rx_sb_index);
 	}
 
 	if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO)
@@ -1925,16 +1974,6 @@ void qed_ll2_release_connection(void *cxt, u8 connection_handle)
 	if (!p_ll2_conn)
 		return;
 
-	if (QED_LL2_RX_REGISTERED(p_ll2_conn)) {
-		p_ll2_conn->rx_queue.b_cb_registred = false;
-		qed_int_unregister_cb(p_hwfn, p_ll2_conn->rx_queue.rx_sb_index);
-	}
-
-	if (QED_LL2_TX_REGISTERED(p_ll2_conn)) {
-		p_ll2_conn->tx_queue.b_cb_registred = false;
-		qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index);
-	}
-
 	kfree(p_ll2_conn->tx_queue.descq_mem);
 	qed_chain_free(p_hwfn->cdev, &p_ll2_conn->tx_queue.txq_chain);
 
@@ -2370,7 +2409,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb)
 	u8 flags = 0;
 
 	if (unlikely(skb->ip_summed != CHECKSUM_NONE)) {
-		DP_INFO(cdev, "Cannot transmit a checksumed packet\n");
+		DP_INFO(cdev, "Cannot transmit a checksummed packet\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 9854aa9139af..7870ae2a6f7e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -680,7 +680,7 @@ static int qed_nic_stop(struct qed_dev *cdev)
 			tasklet_disable(p_hwfn->sp_dpc);
 			p_hwfn->b_sp_dpc_enabled = false;
 			DP_VERBOSE(cdev, NETIF_MSG_IFDOWN,
-				   "Disabled sp taskelt [hwfn %d] at %p\n",
+				   "Disabled sp tasklet [hwfn %d] at %p\n",
 				   i, p_hwfn->sp_dpc);
 		}
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index fb7c2d1562ae..6acfd43c1a4f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -848,7 +848,7 @@ int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
 
 	if (!(qp->resp_offloaded)) {
 		DP_NOTICE(p_hwfn,
-			  "The responder's qp should be offloded before requester's\n");
+			  "The responder's qp should be offloaded before requester's\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index a01e7d6e5442..f6655e251bbd 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1066,13 +1066,12 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 
 	DP_INFO(edev, "Starting qede_remove\n");
 
+	qede_rdma_dev_remove(edev);
 	unregister_netdev(ndev);
 	cancel_delayed_work_sync(&edev->sp_task);
 
 	qede_ptp_disable(edev);
 
-	qede_rdma_dev_remove(edev);
-
 	edev->ops->common->set_power_state(cdev, PCI_D0);
 
 	pci_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index 50b142fad6b8..1900bf7e67d1 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -238,7 +238,7 @@ qede_rdma_get_free_event_node(struct qede_dev *edev)
 	}
 
 	if (!found) {
-		event_node = kzalloc(sizeof(*event_node), GFP_KERNEL);
+		event_node = kzalloc(sizeof(*event_node), GFP_ATOMIC);
 		if (!event_node) {
 			DP_NOTICE(edev,
 				  "qedr: Could not allocate memory for rdma work\n");
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index d33988570217..5f4e447c5dce 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -350,15 +350,16 @@ static int rmnet_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	real_dev = priv->real_dev;
 
-	if (!rmnet_is_real_dev_registered(real_dev))
-		return -ENODEV;
-
 	if (nla_put_u16(skb, IFLA_RMNET_MUX_ID, priv->mux_id))
 		goto nla_put_failure;
 
-	port = rmnet_get_port_rtnl(real_dev);
+	if (rmnet_is_real_dev_registered(real_dev)) {
+		port = rmnet_get_port_rtnl(real_dev);
+		f.flags = port->data_format;
+	} else {
+		f.flags = 0;
+	}
 
-	f.flags = port->data_format;
 	f.mask  = ~0;
 
 	if (nla_put(skb, IFLA_RMNET_FLAGS, sizeof(f), &f))
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index d24b47b8e0b2..d118da5a10a2 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2224,7 +2224,7 @@ static void rtl8139_poll_controller(struct net_device *dev)
 	struct rtl8139_private *tp = netdev_priv(dev);
 	const int irq = tp->pci_dev->irq;
 
-	disable_irq(irq);
+	disable_irq_nosync(irq);
 	rtl8139_interrupt(irq, dev);
 	enable_irq(irq);
 }
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 604ae78381ae..c7aac1fc99e8 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4981,6 +4981,9 @@ static void rtl_pll_power_down(struct rtl8169_private *tp)
 static void rtl_pll_power_up(struct rtl8169_private *tp)
 {
 	rtl_generic_op(tp, tp->pll_power_ops.up);
+
+	/* give MAC/PHY some time to resume */
+	msleep(20);
 }
 
 static void rtl_init_pll_power_ops(struct rtl8169_private *tp)
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index a5b792ce2ae7..1bf930d4a1e5 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -163,7 +163,7 @@ enum {
 };
 
 /* Driver's parameters */
-#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_RENESAS)
 #define SH_ETH_RX_ALIGN		32
 #else
 #define SH_ETH_RX_ALIGN		2
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 50daad0a1482..d90a7b1f4088 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3999,29 +3999,6 @@ static void efx_ef10_prepare_flr(struct efx_nic *efx)
 	atomic_set(&efx->active_queues, 0);
 }
 
-static bool efx_ef10_filter_equal(const struct efx_filter_spec *left,
-				  const struct efx_filter_spec *right)
-{
-	if ((left->match_flags ^ right->match_flags) |
-	    ((left->flags ^ right->flags) &
-	     (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
-		return false;
-
-	return memcmp(&left->outer_vid, &right->outer_vid,
-		      sizeof(struct efx_filter_spec) -
-		      offsetof(struct efx_filter_spec, outer_vid)) == 0;
-}
-
-static unsigned int efx_ef10_filter_hash(const struct efx_filter_spec *spec)
-{
-	BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
-	return jhash2((const u32 *)&spec->outer_vid,
-		      (sizeof(struct efx_filter_spec) -
-		       offsetof(struct efx_filter_spec, outer_vid)) / 4,
-		      0);
-	/* XXX should we randomise the initval? */
-}
-
 /* Decide whether a filter should be exclusive or else should allow
  * delivery to additional recipients.  Currently we decide that
  * filters for specific local unicast MAC and IP addresses are
@@ -4346,7 +4323,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
 		goto out_unlock;
 	match_pri = rc;
 
-	hash = efx_ef10_filter_hash(spec);
+	hash = efx_filter_spec_hash(spec);
 	is_mc_recip = efx_filter_is_mc_recipient(spec);
 	if (is_mc_recip)
 		bitmap_zero(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
@@ -4378,7 +4355,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
 		if (!saved_spec) {
 			if (ins_index < 0)
 				ins_index = i;
-		} else if (efx_ef10_filter_equal(spec, saved_spec)) {
+		} else if (efx_filter_spec_equal(spec, saved_spec)) {
 			if (spec->priority < saved_spec->priority &&
 			    spec->priority != EFX_FILTER_PRI_AUTO) {
 				rc = -EPERM;
@@ -4762,28 +4739,63 @@ static s32 efx_ef10_filter_get_rx_ids(struct efx_nic *efx,
 static bool efx_ef10_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
 					   unsigned int filter_idx)
 {
+	struct efx_filter_spec *spec, saved_spec;
 	struct efx_ef10_filter_table *table;
-	struct efx_filter_spec *spec;
-	bool ret;
+	struct efx_arfs_rule *rule = NULL;
+	bool ret = true, force = false;
+	u16 arfs_id;
 
 	down_read(&efx->filter_sem);
 	table = efx->filter_state;
 	down_write(&table->lock);
 	spec = efx_ef10_filter_entry_spec(table, filter_idx);
 
-	if (!spec || spec->priority != EFX_FILTER_PRI_HINT) {
-		ret = true;
+	if (!spec || spec->priority != EFX_FILTER_PRI_HINT)
 		goto out_unlock;
-	}
 
-	if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id,
-				 flow_id, filter_idx)) {
+	spin_lock_bh(&efx->rps_hash_lock);
+	if (!efx->rps_hash_table) {
+		/* In the absence of the table, we always return 0 to ARFS. */
+		arfs_id = 0;
+	} else {
+		rule = efx_rps_hash_find(efx, spec);
+		if (!rule)
+			/* ARFS table doesn't know of this filter, so remove it */
+			goto expire;
+		arfs_id = rule->arfs_id;
+		ret = efx_rps_check_rule(rule, filter_idx, &force);
+		if (force)
+			goto expire;
+		if (!ret) {
+			spin_unlock_bh(&efx->rps_hash_lock);
+			goto out_unlock;
+		}
+	}
+	if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, arfs_id))
 		ret = false;
-		goto out_unlock;
+	else if (rule)
+		rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+expire:
+	saved_spec = *spec; /* remove operation will kfree spec */
+	spin_unlock_bh(&efx->rps_hash_lock);
+	/* At this point (since we dropped the lock), another thread might queue
+	 * up a fresh insertion request (but the actual insertion will be held
+	 * up by our possession of the filter table lock).  In that case, it
+	 * will set rule->filter_id to EFX_ARFS_FILTER_ID_PENDING, meaning that
+	 * the rule is not removed by efx_rps_hash_del() below.
+	 */
+	if (ret)
+		ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority,
+						      filter_idx, true) == 0;
+	/* While we can't safely dereference rule (we dropped the lock), we can
+	 * still test it for NULL.
+	 */
+	if (ret && rule) {
+		/* Expiring, so remove entry from ARFS table */
+		spin_lock_bh(&efx->rps_hash_lock);
+		efx_rps_hash_del(efx, &saved_spec);
+		spin_unlock_bh(&efx->rps_hash_lock);
 	}
-
-	ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority,
-					      filter_idx, true) == 0;
 out_unlock:
 	up_write(&table->lock);
 	up_read(&efx->filter_sem);
@@ -5265,7 +5277,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 		ids = vlan->uc;
 	}
 
-	filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0;
+	filter_flags = efx_rss_active(&efx->rss_context) ? EFX_FILTER_FLAG_RX_RSS : 0;
 
 	/* Insert/renew filters */
 	for (i = 0; i < addr_count; i++) {
@@ -5334,7 +5346,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx,
 	int rc;
 	u16 *id;
 
-	filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0;
+	filter_flags = efx_rss_active(&efx->rss_context) ? EFX_FILTER_FLAG_RX_RSS : 0;
 
 	efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
 
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 692dd729ee2a..661828e8fdcf 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1289,9 +1289,8 @@ static int efx_init_io(struct efx_nic *efx)
 
 	pci_set_master(pci_dev);
 
-	/* Set the PCI DMA mask.  Try all possibilities from our
-	 * genuine mask down to 32 bits, because some architectures
-	 * (e.g. x86_64 with iommu_sac_force set) will allow 40 bit
+	/* Set the PCI DMA mask.  Try all possibilities from our genuine mask
+	 * down to 32 bits, because some architectures will allow 40 bit
 	 * masks event though they reject 46 bit masks.
 	 */
 	while (dma_mask > 0x7fffffffUL) {
@@ -3027,6 +3026,10 @@ static int efx_init_struct(struct efx_nic *efx,
 	mutex_init(&efx->mac_lock);
 #ifdef CONFIG_RFS_ACCEL
 	mutex_init(&efx->rps_mutex);
+	spin_lock_init(&efx->rps_hash_lock);
+	/* Failure to allocate is not fatal, but may degrade ARFS performance */
+	efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE,
+				      sizeof(*efx->rps_hash_table), GFP_KERNEL);
 #endif
 	efx->phy_op = &efx_dummy_phy_operations;
 	efx->mdio.dev = net_dev;
@@ -3070,6 +3073,10 @@ static void efx_fini_struct(struct efx_nic *efx)
 {
 	int i;
 
+#ifdef CONFIG_RFS_ACCEL
+	kfree(efx->rps_hash_table);
+#endif
+
 	for (i = 0; i < EFX_MAX_CHANNELS; i++)
 		kfree(efx->channel[i]);
 
@@ -3092,6 +3099,141 @@ void efx_update_sw_stats(struct efx_nic *efx, u64 *stats)
 	stats[GENERIC_STAT_rx_noskb_drops] = atomic_read(&efx->n_rx_noskb_drops);
 }
 
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+			   const struct efx_filter_spec *right)
+{
+	if ((left->match_flags ^ right->match_flags) |
+	    ((left->flags ^ right->flags) &
+	     (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
+		return false;
+
+	return memcmp(&left->outer_vid, &right->outer_vid,
+		      sizeof(struct efx_filter_spec) -
+		      offsetof(struct efx_filter_spec, outer_vid)) == 0;
+}
+
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec)
+{
+	BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
+	return jhash2((const u32 *)&spec->outer_vid,
+		      (sizeof(struct efx_filter_spec) -
+		       offsetof(struct efx_filter_spec, outer_vid)) / 4,
+		      0);
+}
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+			bool *force)
+{
+	if (rule->filter_id == EFX_ARFS_FILTER_ID_PENDING) {
+		/* ARFS is currently updating this entry, leave it */
+		return false;
+	}
+	if (rule->filter_id == EFX_ARFS_FILTER_ID_ERROR) {
+		/* ARFS tried and failed to update this, so it's probably out
+		 * of date.  Remove the filter and the ARFS rule entry.
+		 */
+		rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+		*force = true;
+		return true;
+	} else if (WARN_ON(rule->filter_id != filter_idx)) { /* can't happen */
+		/* ARFS has moved on, so old filter is not needed.  Since we did
+		 * not mark the rule with EFX_ARFS_FILTER_ID_REMOVING, it will
+		 * not be removed by efx_rps_hash_del() subsequently.
+		 */
+		*force = true;
+		return true;
+	}
+	/* Remove it iff ARFS wants to. */
+	return true;
+}
+
+struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
+				       const struct efx_filter_spec *spec)
+{
+	u32 hash = efx_filter_spec_hash(spec);
+
+	WARN_ON(!spin_is_locked(&efx->rps_hash_lock));
+	if (!efx->rps_hash_table)
+		return NULL;
+	return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
+}
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+					const struct efx_filter_spec *spec)
+{
+	struct efx_arfs_rule *rule;
+	struct hlist_head *head;
+	struct hlist_node *node;
+
+	head = efx_rps_hash_bucket(efx, spec);
+	if (!head)
+		return NULL;
+	hlist_for_each(node, head) {
+		rule = container_of(node, struct efx_arfs_rule, node);
+		if (efx_filter_spec_equal(spec, &rule->spec))
+			return rule;
+	}
+	return NULL;
+}
+
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+				       const struct efx_filter_spec *spec,
+				       bool *new)
+{
+	struct efx_arfs_rule *rule;
+	struct hlist_head *head;
+	struct hlist_node *node;
+
+	head = efx_rps_hash_bucket(efx, spec);
+	if (!head)
+		return NULL;
+	hlist_for_each(node, head) {
+		rule = container_of(node, struct efx_arfs_rule, node);
+		if (efx_filter_spec_equal(spec, &rule->spec)) {
+			*new = false;
+			return rule;
+		}
+	}
+	rule = kmalloc(sizeof(*rule), GFP_ATOMIC);
+	*new = true;
+	if (rule) {
+		memcpy(&rule->spec, spec, sizeof(rule->spec));
+		hlist_add_head(&rule->node, head);
+	}
+	return rule;
+}
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec)
+{
+	struct efx_arfs_rule *rule;
+	struct hlist_head *head;
+	struct hlist_node *node;
+
+	head = efx_rps_hash_bucket(efx, spec);
+	if (WARN_ON(!head))
+		return;
+	hlist_for_each(node, head) {
+		rule = container_of(node, struct efx_arfs_rule, node);
+		if (efx_filter_spec_equal(spec, &rule->spec)) {
+			/* Someone already reused the entry.  We know that if
+			 * this check doesn't fire (i.e. filter_id == REMOVING)
+			 * then the REMOVING mark was put there by our caller,
+			 * because caller is holding a lock on filter table and
+			 * only holders of that lock set REMOVING.
+			 */
+			if (rule->filter_id != EFX_ARFS_FILTER_ID_REMOVING)
+				return;
+			hlist_del(node);
+			kfree(rule);
+			return;
+		}
+	}
+	/* We didn't find it. */
+	WARN_ON(1);
+}
+#endif
+
 /* RSS contexts.  We're using linked lists and crappy O(n) algorithms, because
  * (a) this is an infrequent control-plane operation and (b) n is small (max 64)
  */
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index a3140e16fcef..3f759ebdcf10 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -186,6 +186,27 @@ static inline void efx_filter_rfs_expire(struct work_struct *data) {}
 #endif
 bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec);
 
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+			   const struct efx_filter_spec *right);
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec);
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+			bool *force);
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+					const struct efx_filter_spec *spec);
+
+/* @new is written to indicate if entry was newly added (true) or if an old
+ * entry was found and returned (false).
+ */
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+				       const struct efx_filter_spec *spec,
+				       bool *new);
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec);
+#endif
+
 /* RSS contexts */
 struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx);
 struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id);
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index 3d6c91e96589..dd5530a4f8c8 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -1242,9 +1242,8 @@ static int ef4_init_io(struct ef4_nic *efx)
 
 	pci_set_master(pci_dev);
 
-	/* Set the PCI DMA mask.  Try all possibilities from our
-	 * genuine mask down to 32 bits, because some architectures
-	 * (e.g. x86_64 with iommu_sac_force set) will allow 40 bit
+	/* Set the PCI DMA mask.  Try all possibilities from our genuine mask
+	 * down to 32 bits, because some architectures will allow 40 bit
 	 * masks event though they reject 46 bit masks.
 	 */
 	while (dma_mask > 0x7fffffffUL) {
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 4a19c7efdf8d..c72adf8b52ea 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -2905,18 +2905,45 @@ bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
 {
 	struct efx_farch_filter_state *state = efx->filter_state;
 	struct efx_farch_filter_table *table;
-	bool ret = false;
+	bool ret = false, force = false;
+	u16 arfs_id;
 
 	down_write(&state->lock);
+	spin_lock_bh(&efx->rps_hash_lock);
 	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
 	if (test_bit(index, table->used_bitmap) &&
-	    table->spec[index].priority == EFX_FILTER_PRI_HINT &&
-	    rps_may_expire_flow(efx->net_dev, table->spec[index].dmaq_id,
-				flow_id, index)) {
-		efx_farch_filter_table_clear_entry(efx, table, index);
-		ret = true;
+	    table->spec[index].priority == EFX_FILTER_PRI_HINT) {
+		struct efx_arfs_rule *rule = NULL;
+		struct efx_filter_spec spec;
+
+		efx_farch_filter_to_gen_spec(&spec, &table->spec[index]);
+		if (!efx->rps_hash_table) {
+			/* In the absence of the table, we always returned 0 to
+			 * ARFS, so use the same to query it.
+			 */
+			arfs_id = 0;
+		} else {
+			rule = efx_rps_hash_find(efx, &spec);
+			if (!rule) {
+				/* ARFS table doesn't know of this filter, remove it */
+				force = true;
+			} else {
+				arfs_id = rule->arfs_id;
+				if (!efx_rps_check_rule(rule, index, &force))
+					goto out_unlock;
+			}
+		}
+		if (force || rps_may_expire_flow(efx->net_dev, spec.dmaq_id,
+						 flow_id, arfs_id)) {
+			if (rule)
+				rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+			efx_rps_hash_del(efx, &spec);
+			efx_farch_filter_table_clear_entry(efx, table, index);
+			ret = true;
+		}
 	}
-
+out_unlock:
+	spin_unlock_bh(&efx->rps_hash_lock);
 	up_write(&state->lock);
 	return ret;
 }
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 5e379a83c729..65568925c3ef 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -733,6 +733,56 @@ struct efx_rss_context {
 	u32 rx_indir_table[128];
 };
 
+#ifdef CONFIG_RFS_ACCEL
+/* Order of these is important, since filter_id >= %EFX_ARFS_FILTER_ID_PENDING
+ * is used to test if filter does or will exist.
+ */
+#define EFX_ARFS_FILTER_ID_PENDING	-1
+#define EFX_ARFS_FILTER_ID_ERROR	-2
+#define EFX_ARFS_FILTER_ID_REMOVING	-3
+/**
+ * struct efx_arfs_rule - record of an ARFS filter and its IDs
+ * @node: linkage into hash table
+ * @spec: details of the filter (used as key for hash table).  Use efx->type to
+ *	determine which member to use.
+ * @rxq_index: channel to which the filter will steer traffic.
+ * @arfs_id: filter ID which was returned to ARFS
+ * @filter_id: index in software filter table.  May be
+ *	%EFX_ARFS_FILTER_ID_PENDING if filter was not inserted yet,
+ *	%EFX_ARFS_FILTER_ID_ERROR if filter insertion failed, or
+ *	%EFX_ARFS_FILTER_ID_REMOVING if expiry is currently removing the filter.
+ */
+struct efx_arfs_rule {
+	struct hlist_node node;
+	struct efx_filter_spec spec;
+	u16 rxq_index;
+	u16 arfs_id;
+	s32 filter_id;
+};
+
+/* Size chosen so that the table is one page (4kB) */
+#define EFX_ARFS_HASH_TABLE_SIZE	512
+
+/**
+ * struct efx_async_filter_insertion - Request to asynchronously insert a filter
+ * @net_dev: Reference to the netdevice
+ * @spec: The filter to insert
+ * @work: Workitem for this request
+ * @rxq_index: Identifies the channel for which this request was made
+ * @flow_id: Identifies the kernel-side flow for which this request was made
+ */
+struct efx_async_filter_insertion {
+	struct net_device *net_dev;
+	struct efx_filter_spec spec;
+	struct work_struct work;
+	u16 rxq_index;
+	u32 flow_id;
+};
+
+/* Maximum number of ARFS workitems that may be in flight on an efx_nic */
+#define EFX_RPS_MAX_IN_FLIGHT	8
+#endif /* CONFIG_RFS_ACCEL */
+
 /**
  * struct efx_nic - an Efx NIC
  * @name: Device name (net device name or bus id before net device registered)
@@ -850,6 +900,12 @@ struct efx_rss_context {
  * @rps_expire_channel: Next channel to check for expiry
  * @rps_expire_index: Next index to check for expiry in
  *	@rps_expire_channel's @rps_flow_id
+ * @rps_slot_map: bitmap of in-flight entries in @rps_slot
+ * @rps_slot: array of ARFS insertion requests for efx_filter_rfs_work()
+ * @rps_hash_lock: Protects ARFS filter mapping state (@rps_hash_table and
+ *	@rps_next_id).
+ * @rps_hash_table: Mapping between ARFS filters and their various IDs
+ * @rps_next_id: next arfs_id for an ARFS filter
  * @active_queues: Count of RX and TX queues that haven't been flushed and drained.
  * @rxq_flush_pending: Count of number of receive queues that need to be flushed.
  *	Decremented when the efx_flush_rx_queue() is called.
@@ -1004,6 +1060,11 @@ struct efx_nic {
 	struct mutex rps_mutex;
 	unsigned int rps_expire_channel;
 	unsigned int rps_expire_index;
+	unsigned long rps_slot_map;
+	struct efx_async_filter_insertion rps_slot[EFX_RPS_MAX_IN_FLIGHT];
+	spinlock_t rps_hash_lock;
+	struct hlist_head *rps_hash_table;
+	u32 rps_next_id;
 #endif
 
 	atomic_t active_queues;
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 95682831484e..d2e254f2f72b 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -827,31 +827,38 @@ MODULE_PARM_DESC(rx_refill_threshold,
 
 #ifdef CONFIG_RFS_ACCEL
 
-/**
- * struct efx_async_filter_insertion - Request to asynchronously insert a filter
- * @net_dev: Reference to the netdevice
- * @spec: The filter to insert
- * @work: Workitem for this request
- * @rxq_index: Identifies the channel for which this request was made
- * @flow_id: Identifies the kernel-side flow for which this request was made
- */
-struct efx_async_filter_insertion {
-	struct net_device *net_dev;
-	struct efx_filter_spec spec;
-	struct work_struct work;
-	u16 rxq_index;
-	u32 flow_id;
-};
-
 static void efx_filter_rfs_work(struct work_struct *data)
 {
 	struct efx_async_filter_insertion *req = container_of(data, struct efx_async_filter_insertion,
 							      work);
 	struct efx_nic *efx = netdev_priv(req->net_dev);
 	struct efx_channel *channel = efx_get_channel(efx, req->rxq_index);
+	int slot_idx = req - efx->rps_slot;
+	struct efx_arfs_rule *rule;
+	u16 arfs_id = 0;
 	int rc;
 
-	rc = efx->type->filter_insert(efx, &req->spec, false);
+	rc = efx->type->filter_insert(efx, &req->spec, true);
+	if (rc >= 0)
+		rc %= efx->type->max_rx_ip_filters;
+	if (efx->rps_hash_table) {
+		spin_lock_bh(&efx->rps_hash_lock);
+		rule = efx_rps_hash_find(efx, &req->spec);
+		/* The rule might have already gone, if someone else's request
+		 * for the same spec was already worked and then expired before
+		 * we got around to our work.  In that case we have nothing
+		 * tying us to an arfs_id, meaning that as soon as the filter
+		 * is considered for expiry it will be removed.
+		 */
+		if (rule) {
+			if (rc < 0)
+				rule->filter_id = EFX_ARFS_FILTER_ID_ERROR;
+			else
+				rule->filter_id = rc;
+			arfs_id = rule->arfs_id;
+		}
+		spin_unlock_bh(&efx->rps_hash_lock);
+	}
 	if (rc >= 0) {
 		/* Remember this so we can check whether to expire the filter
 		 * later.
@@ -863,23 +870,23 @@ static void efx_filter_rfs_work(struct work_struct *data)
 
 		if (req->spec.ether_type == htons(ETH_P_IP))
 			netif_info(efx, rx_status, efx->net_dev,
-				   "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
+				   "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d id %u]\n",
 				   (req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
 				   req->spec.rem_host, ntohs(req->spec.rem_port),
 				   req->spec.loc_host, ntohs(req->spec.loc_port),
-				   req->rxq_index, req->flow_id, rc);
+				   req->rxq_index, req->flow_id, rc, arfs_id);
 		else
 			netif_info(efx, rx_status, efx->net_dev,
-				   "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n",
+				   "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d id %u]\n",
 				   (req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
 				   req->spec.rem_host, ntohs(req->spec.rem_port),
 				   req->spec.loc_host, ntohs(req->spec.loc_port),
-				   req->rxq_index, req->flow_id, rc);
+				   req->rxq_index, req->flow_id, rc, arfs_id);
 	}
 
 	/* Release references */
+	clear_bit(slot_idx, &efx->rps_slot_map);
 	dev_put(req->net_dev);
-	kfree(req);
 }
 
 int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
@@ -887,23 +894,39 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_async_filter_insertion *req;
+	struct efx_arfs_rule *rule;
 	struct flow_keys fk;
+	int slot_idx;
+	bool new;
+	int rc;
 
-	if (flow_id == RPS_FLOW_ID_INVALID)
-		return -EINVAL;
+	/* find a free slot */
+	for (slot_idx = 0; slot_idx < EFX_RPS_MAX_IN_FLIGHT; slot_idx++)
+		if (!test_and_set_bit(slot_idx, &efx->rps_slot_map))
+			break;
+	if (slot_idx >= EFX_RPS_MAX_IN_FLIGHT)
+		return -EBUSY;
 
-	if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
-		return -EPROTONOSUPPORT;
+	if (flow_id == RPS_FLOW_ID_INVALID) {
+		rc = -EINVAL;
+		goto out_clear;
+	}
 
-	if (fk.basic.n_proto != htons(ETH_P_IP) && fk.basic.n_proto != htons(ETH_P_IPV6))
-		return -EPROTONOSUPPORT;
-	if (fk.control.flags & FLOW_DIS_IS_FRAGMENT)
-		return -EPROTONOSUPPORT;
+	if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) {
+		rc = -EPROTONOSUPPORT;
+		goto out_clear;
+	}
 
-	req = kmalloc(sizeof(*req), GFP_ATOMIC);
-	if (!req)
-		return -ENOMEM;
+	if (fk.basic.n_proto != htons(ETH_P_IP) && fk.basic.n_proto != htons(ETH_P_IPV6)) {
+		rc = -EPROTONOSUPPORT;
+		goto out_clear;
+	}
+	if (fk.control.flags & FLOW_DIS_IS_FRAGMENT) {
+		rc = -EPROTONOSUPPORT;
+		goto out_clear;
+	}
 
+	req = efx->rps_slot + slot_idx;
 	efx_filter_init_rx(&req->spec, EFX_FILTER_PRI_HINT,
 			   efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0,
 			   rxq_index);
@@ -927,12 +950,45 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 	req->spec.rem_port = fk.ports.src;
 	req->spec.loc_port = fk.ports.dst;
 
+	if (efx->rps_hash_table) {
+		/* Add it to ARFS hash table */
+		spin_lock(&efx->rps_hash_lock);
+		rule = efx_rps_hash_add(efx, &req->spec, &new);
+		if (!rule) {
+			rc = -ENOMEM;
+			goto out_unlock;
+		}
+		if (new)
+			rule->arfs_id = efx->rps_next_id++ % RPS_NO_FILTER;
+		rc = rule->arfs_id;
+		/* Skip if existing or pending filter already does the right thing */
+		if (!new && rule->rxq_index == rxq_index &&
+		    rule->filter_id >= EFX_ARFS_FILTER_ID_PENDING)
+			goto out_unlock;
+		rule->rxq_index = rxq_index;
+		rule->filter_id = EFX_ARFS_FILTER_ID_PENDING;
+		spin_unlock(&efx->rps_hash_lock);
+	} else {
+		/* Without an ARFS hash table, we just use arfs_id 0 for all
+		 * filters.  This means if multiple flows hash to the same
+		 * flow_id, all but the most recently touched will be eligible
+		 * for expiry.
+		 */
+		rc = 0;
+	}
+
+	/* Queue the request */
 	dev_hold(req->net_dev = net_dev);
 	INIT_WORK(&req->work, efx_filter_rfs_work);
 	req->rxq_index = rxq_index;
 	req->flow_id = flow_id;
 	schedule_work(&req->work);
-	return 0;
+	return rc;
+out_unlock:
+	spin_unlock(&efx->rps_hash_lock);
+out_clear:
+	clear_bit(slot_idx, &efx->rps_slot_map);
+	return rc;
 }
 
 bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned int quota)
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index f4c0b02ddad8..59fbf74dcada 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1674,8 +1674,8 @@ static int netsec_probe(struct platform_device *pdev)
 	if (ret)
 		goto unreg_napi;
 
-	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)))
-		dev_warn(&pdev->dev, "Failed to enable 64-bit DMA\n");
+	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)))
+		dev_warn(&pdev->dev, "Failed to set DMA mask\n");
 
 	ret = register_netdev(ndev);
 	if (ret) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index c7bff596c665..dedd40613090 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -347,7 +347,7 @@ enum power_event {
 #define MTL_RX_OVERFLOW_INT		BIT(16)
 
 /* Default operating mode of the MAC */
-#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | GMAC_CONFIG_ACS | \
+#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | \
 			GMAC_CONFIG_BE | GMAC_CONFIG_DCRS)
 
 /* To dump the core regs excluding  the Address Registers */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index a3af92ebbca8..517b1f6736a8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -31,13 +31,6 @@ static void dwmac4_core_init(struct mac_device_info *hw,
 
 	value |= GMAC_CORE_INIT;
 
-	/* Clear ACS bit because Ethernet switch tagging formats such as
-	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
-	 * hardware to truncate packets on reception.
-	 */
-	if (netdev_uses_dsa(dev))
-		value &= ~GMAC_CONFIG_ACS;
-
 	if (mtu > 1500)
 		value |= GMAC_CONFIG_2K;
 	if (mtu > 2000)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9a16931ce39d..b65e2d144698 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3495,8 +3495,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 
 			/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
 			 * Type frames (LLC/LLC-SNAP)
+			 *
+			 * llc_snap is never checked in GMAC >= 4, so this ACS
+			 * feature is always disabled and packets need to be
+			 * stripped manually.
 			 */
-			if (unlikely(status != llc_snap))
+			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) ||
+			    unlikely(status != llc_snap))
 				frame_len -= ETH_FCS_LEN;
 
 			if (netif_msg_rx_status(priv)) {
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index f081de4f38d7..88c12474a0c3 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3443,7 +3443,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 
 		len = (val & RCR_ENTRY_L2_LEN) >>
 			RCR_ENTRY_L2_LEN_SHIFT;
-		len -= ETH_FCS_LEN;
+		append_size = len + ETH_HLEN + ETH_FCS_LEN;
 
 		addr = (val & RCR_ENTRY_PKT_BUF_ADDR) <<
 			RCR_ENTRY_PKT_BUF_ADDR_SHIFT;
@@ -3453,7 +3453,6 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 					 RCR_ENTRY_PKTBUFSZ_SHIFT];
 
 		off = addr & ~PAGE_MASK;
-		append_size = rcr_size;
 		if (num_rcr == 1) {
 			int ptype;
 
@@ -3466,7 +3465,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 			else
 				skb_checksum_none_assert(skb);
 		} else if (!(val & RCR_ENTRY_MULTI))
-			append_size = len - skb->len;
+			append_size = append_size - skb->len;
 
 		niu_rx_skb_append(skb, page, off, append_size, rcr_size);
 		if ((page->index + rp->rbr_block_size) - rcr_size == addr) {
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 30371274409d..28d893b93d30 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -129,7 +129,7 @@ do {								\
 
 #define RX_PRIORITY_MAPPING	0x76543210
 #define TX_PRIORITY_MAPPING	0x33221100
-#define CPDMA_TX_PRIORITY_MAP	0x01234567
+#define CPDMA_TX_PRIORITY_MAP	0x76543210
 
 #define CPSW_VLAN_AWARE		BIT(1)
 #define CPSW_RX_VLAN_ENCAP	BIT(2)
@@ -1340,6 +1340,8 @@ static inline void cpsw_add_dual_emac_def_ale_entries(
 	cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
 			   HOST_PORT_NUM, ALE_VLAN |
 			   ALE_SECURE, slave->port_vlan);
+	cpsw_ale_control_set(cpsw->ale, slave_port,
+			     ALE_PORT_DROP_UNKNOWN_VLAN, 1);
 }
 
 static void soft_reset_slave(struct cpsw_slave *slave)
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index abceea802ea1..38828ab77eb9 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1873,7 +1873,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->txchan)) {
 		dev_err(&pdev->dev, "error initializing tx dma channel\n");
 		rc = PTR_ERR(priv->txchan);
-		goto no_cpdma_chan;
+		goto err_free_dma;
 	}
 
 	priv->rxchan = cpdma_chan_create(priv->dma, EMAC_DEF_RX_CH,
@@ -1881,14 +1881,14 @@ static int davinci_emac_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->rxchan)) {
 		dev_err(&pdev->dev, "error initializing rx dma channel\n");
 		rc = PTR_ERR(priv->rxchan);
-		goto no_cpdma_chan;
+		goto err_free_txchan;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!res) {
 		dev_err(&pdev->dev, "error getting irq res\n");
 		rc = -ENOENT;
-		goto no_cpdma_chan;
+		goto err_free_rxchan;
 	}
 	ndev->irq = res->start;
 
@@ -1914,7 +1914,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		pm_runtime_put_noidle(&pdev->dev);
 		dev_err(&pdev->dev, "%s: failed to get_sync(%d)\n",
 			__func__, rc);
-		goto no_cpdma_chan;
+		goto err_napi_del;
 	}
 
 	/* register the network device */
@@ -1924,7 +1924,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "error in register_netdev\n");
 		rc = -ENODEV;
 		pm_runtime_put(&pdev->dev);
-		goto no_cpdma_chan;
+		goto err_napi_del;
 	}
 
 
@@ -1937,11 +1937,13 @@ static int davinci_emac_probe(struct platform_device *pdev)
 
 	return 0;
 
-no_cpdma_chan:
-	if (priv->txchan)
-		cpdma_chan_destroy(priv->txchan);
-	if (priv->rxchan)
-		cpdma_chan_destroy(priv->rxchan);
+err_napi_del:
+	netif_napi_del(&priv->napi);
+err_free_rxchan:
+	cpdma_chan_destroy(priv->rxchan);
+err_free_txchan:
+	cpdma_chan_destroy(priv->txchan);
+err_free_dma:
 	cpdma_ctlr_destroy(priv->dma);
 no_pdata:
 	if (of_phy_is_fixed_link(np))
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index dfabbae72efd..f347fd9c5b28 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -449,20 +449,6 @@ static const struct seq_operations bpq_seqops = {
 	.show = bpq_seq_show,
 };
 
-static int bpq_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &bpq_seqops);
-}
-
-static const struct file_operations bpq_info_fops = {
-	.owner = THIS_MODULE,
-	.open = bpq_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
-
 /* ------------------------------------------------------------------------ */
 
 static const struct net_device_ops bpq_netdev_ops = {
@@ -590,7 +576,7 @@ static int bpq_device_event(struct notifier_block *this,
 static int __init bpq_init_driver(void)
 {
 #ifdef CONFIG_PROC_FS
-	if (!proc_create("bpqether", 0444, init_net.proc_net, &bpq_info_fops)) {
+	if (!proc_create_seq("bpqether", 0444, init_net.proc_net, &bpq_seqops)) {
 		printk(KERN_ERR
 			"bpq: cannot create /proc/net/bpqether entry.\n");
 		return -ENOENT;
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 3de272959090..6c03932d8a6b 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -2084,21 +2084,6 @@ static const struct seq_operations scc_net_seq_ops = {
 	.stop   = scc_net_seq_stop,
 	.show   = scc_net_seq_show,
 };
-
-
-static int scc_net_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scc_net_seq_ops);
-}
-
-static const struct file_operations scc_net_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scc_net_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_private,
-};
-
 #endif /* CONFIG_PROC_FS */
 
  
@@ -2122,7 +2107,7 @@ static int __init scc_init_driver (void)
 	}
 	rtnl_unlock();
 
-	proc_create("z8530drv", 0, init_net.proc_net, &scc_net_seq_fops);
+	proc_create_seq("z8530drv", 0, init_net.proc_net, &scc_net_seq_ops);
 
 	return 0;
 }
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 83034eb7ed4f..16ec7af6ab7b 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -841,20 +841,6 @@ static const struct seq_operations yam_seqops = {
 	.stop = yam_seq_stop,
 	.show = yam_seq_show,
 };
-
-static int yam_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &yam_seqops);
-}
-
-static const struct file_operations yam_info_fops = {
-	.owner = THIS_MODULE,
-	.open = yam_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 #endif
 
 
@@ -1168,7 +1154,7 @@ static int __init yam_init_driver(void)
 	yam_timer.expires = jiffies + HZ / 100;
 	add_timer(&yam_timer);
 
-	proc_create("yam", 0444, init_net.proc_net, &yam_info_fops);
+	proc_create_seq("yam", 0444, init_net.proc_net, &yam_seqops);
 	return 0;
  error:
 	while (--i >= 0) {
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index ecc84954c511..da07ccdf84bf 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1840,7 +1840,8 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto rx_handler_failed;
 	}
 
-	ret = netdev_upper_dev_link(vf_netdev, ndev, NULL);
+	ret = netdev_master_upper_dev_link(vf_netdev, ndev,
+					   NULL, NULL, NULL);
 	if (ret != 0) {
 		netdev_err(vf_netdev,
 			   "can not set master device %s (err = %d)\n",
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 6b127be781d9..e7ca5b5f39ed 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1288,7 +1288,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		   rndis_device->link_state ? "down" : "up");
 
 	if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_5)
-		return net_device;
+		goto out;
 
 	rndis_filter_query_link_speed(rndis_device, net_device);
 
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index 9fb9b565a002..4f684cbcdc57 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -1045,7 +1045,7 @@ static int atusb_probe(struct usb_interface *interface,
 	atusb->tx_dr.bRequest = ATUSB_TX;
 	atusb->tx_dr.wValue = cpu_to_le16(0);
 
-	atusb->tx_urb = usb_alloc_urb(0, GFP_ATOMIC);
+	atusb->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!atusb->tx_urb)
 		goto fail;
 
diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index 55a22c761808..de0d7f28a181 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -1267,7 +1267,7 @@ mcr20a_probe(struct spi_device *spi)
 	ret = mcr20a_get_platform_data(spi, pdata);
 	if (ret < 0) {
 		dev_crit(&spi->dev, "mcr20a_get_platform_data failed.\n");
-		return ret;
+		goto free_pdata;
 	}
 
 	/* init reset gpio */
@@ -1275,7 +1275,7 @@ mcr20a_probe(struct spi_device *spi)
 		ret = devm_gpio_request_one(&spi->dev, pdata->rst_gpio,
 					    GPIOF_OUT_INIT_HIGH, "reset");
 		if (ret)
-			return ret;
+			goto free_pdata;
 	}
 
 	/* reset mcr20a */
@@ -1291,7 +1291,8 @@ mcr20a_probe(struct spi_device *spi)
 	hw = ieee802154_alloc_hw(sizeof(*lp), &mcr20a_hw_ops);
 	if (!hw) {
 		dev_crit(&spi->dev, "ieee802154_alloc_hw failed\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto free_pdata;
 	}
 
 	/* init mcr20a local data */
@@ -1308,8 +1309,10 @@ mcr20a_probe(struct spi_device *spi)
 	/* init buf */
 	lp->buf = devm_kzalloc(&spi->dev, SPI_COMMAND_BUFFER, GFP_KERNEL);
 
-	if (!lp->buf)
-		return -ENOMEM;
+	if (!lp->buf) {
+		ret = -ENOMEM;
+		goto free_dev;
+	}
 
 	mcr20a_setup_tx_spi_messages(lp);
 	mcr20a_setup_rx_spi_messages(lp);
@@ -1366,6 +1369,8 @@ mcr20a_probe(struct spi_device *spi)
 
 free_dev:
 	ieee802154_free_hw(lp->hw);
+free_pdata:
+	kfree(pdata);
 
 	return ret;
 }
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 450eec264a5e..4377c26f714d 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -792,8 +792,10 @@ static int ipvlan_device_event(struct notifier_block *unused,
 		break;
 
 	case NETDEV_CHANGEADDR:
-		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
 			ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
+			call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev);
+		}
 		break;
 
 	case NETDEV_PRE_TYPE_CHANGE:
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 9cbb0c8a896a..7de88b33d5b9 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3277,7 +3277,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 
 	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err < 0)
-		goto put_dev;
+		goto unregister;
 
 	/* need to be already registered so that ->init has run and
 	 * the MAC addr is set
@@ -3316,8 +3316,7 @@ del_dev:
 	macsec_del_dev(macsec);
 unlink:
 	netdev_upper_dev_unlink(real_dev, dev);
-put_dev:
-	dev_put(real_dev);
+unregister:
 	unregister_netdevice(dev);
 	return err;
 }
diff --git a/drivers/net/phy/bcm-cygnus.c b/drivers/net/phy/bcm-cygnus.c
index 6838129839ca..e757b09f1889 100644
--- a/drivers/net/phy/bcm-cygnus.c
+++ b/drivers/net/phy/bcm-cygnus.c
@@ -61,17 +61,17 @@ static int bcm_cygnus_afe_config(struct phy_device *phydev)
 		return rc;
 
 	/* make rcal=100, since rdb default is 000 */
-	rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB1, 0x10);
+	rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB1, 0x10);
 	if (rc < 0)
 		return rc;
 
 	/* CORE_EXPB0, Reset R_CAL/RC_CAL Engine */
-	rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB0, 0x10);
+	rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB0, 0x10);
 	if (rc < 0)
 		return rc;
 
 	/* CORE_EXPB0, Disable Reset R_CAL/RC_CAL Engine */
-	rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB0, 0x00);
+	rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB0, 0x00);
 
 	return 0;
 }
diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c
index 5ad130c3da43..d5e0833d69b9 100644
--- a/drivers/net/phy/bcm-phy-lib.c
+++ b/drivers/net/phy/bcm-phy-lib.c
@@ -56,7 +56,7 @@ int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum)
 	/* The register must be written to both the Shadow Register Select and
 	 * the Shadow Read Register Selector
 	 */
-	phy_write(phydev, MII_BCM54XX_AUX_CTL, regnum |
+	phy_write(phydev, MII_BCM54XX_AUX_CTL, MII_BCM54XX_AUXCTL_SHDWSEL_MASK |
 		  regnum << MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT);
 	return phy_read(phydev, MII_BCM54XX_AUX_CTL);
 }
diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h
index 7c73808cbbde..81cceaa412fe 100644
--- a/drivers/net/phy/bcm-phy-lib.h
+++ b/drivers/net/phy/bcm-phy-lib.h
@@ -14,11 +14,18 @@
 #ifndef _LINUX_BCM_PHY_LIB_H
 #define _LINUX_BCM_PHY_LIB_H
 
+#include <linux/brcmphy.h>
 #include <linux/phy.h>
 
 int bcm_phy_write_exp(struct phy_device *phydev, u16 reg, u16 val);
 int bcm_phy_read_exp(struct phy_device *phydev, u16 reg);
 
+static inline int bcm_phy_write_exp_sel(struct phy_device *phydev,
+					u16 reg, u16 val)
+{
+	return bcm_phy_write_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER, val);
+}
+
 int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val);
 int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum);
 
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 29b1c88b55cc..01d2ff2f6241 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -65,10 +65,10 @@ struct bcm7xxx_phy_priv {
 static void r_rc_cal_reset(struct phy_device *phydev)
 {
 	/* Reset R_CAL/RC_CAL Engine */
-	bcm_phy_write_exp(phydev, 0x00b0, 0x0010);
+	bcm_phy_write_exp_sel(phydev, 0x00b0, 0x0010);
 
 	/* Disable Reset R_AL/RC_CAL Engine */
-	bcm_phy_write_exp(phydev, 0x00b0, 0x0000);
+	bcm_phy_write_exp_sel(phydev, 0x00b0, 0x0000);
 }
 
 static int bcm7xxx_28nm_b0_afe_config_init(struct phy_device *phydev)
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 3bb6b66dc7bf..f9c25912eb98 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -720,6 +720,15 @@ static struct phy_driver broadcom_drivers[] = {
 	.get_strings	= bcm_phy_get_strings,
 	.get_stats	= bcm53xx_phy_get_stats,
 	.probe		= bcm53xx_phy_probe,
+}, {
+	.phy_id         = PHY_ID_BCM89610,
+	.phy_id_mask    = 0xfffffff0,
+	.name           = "Broadcom BCM89610",
+	.features       = PHY_GBIT_FEATURES,
+	.flags          = PHY_HAS_INTERRUPT,
+	.config_init    = bcm54xx_config_init,
+	.ack_interrupt  = bcm_phy_ack_intr,
+	.config_intr    = bcm_phy_config_intr,
 } };
 
 module_phy_driver(broadcom_drivers);
@@ -741,6 +750,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
 	{ PHY_ID_BCMAC131, 0xfffffff0 },
 	{ PHY_ID_BCM5241, 0xfffffff0 },
 	{ PHY_ID_BCM5395, 0xfffffff0 },
+	{ PHY_ID_BCM89610, 0xfffffff0 },
 	{ }
 };
 
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index c22e8e383247..25e2a099b71c 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1393,6 +1393,15 @@ static int m88e1318_set_wol(struct phy_device *phydev,
 		if (err < 0)
 			goto error;
 
+		/* If WOL event happened once, the LED[2] interrupt pin
+		 * will not be cleared unless we reading the interrupt status
+		 * register. If interrupts are in use, the normal interrupt
+		 * handling will clear the WOL event. Clear the WOL event
+		 * before enabling it if !phy_interrupt_is_valid()
+		 */
+		if (!phy_interrupt_is_valid(phydev))
+			phy_read(phydev, MII_M1011_IEVENT);
+
 		/* Enable the WOL interrupt */
 		err = __phy_modify(phydev, MII_88E1318S_PHY_CSIER, 0,
 				   MII_88E1318S_PHY_CSIER_WOL_EIE);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index f41b224a9cdb..ab195f0916d6 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -573,9 +573,40 @@ static int ksz9031_config_init(struct phy_device *phydev)
 		ksz9031_of_load_skew_values(phydev, of_node,
 				MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4,
 				tx_data_skews, 4);
+
+		/* Silicon Errata Sheet (DS80000691D or DS80000692D):
+		 * When the device links in the 1000BASE-T slave mode only,
+		 * the optional 125MHz reference output clock (CLK125_NDO)
+		 * has wide duty cycle variation.
+		 *
+		 * The optional CLK125_NDO clock does not meet the RGMII
+		 * 45/55 percent (min/max) duty cycle requirement and therefore
+		 * cannot be used directly by the MAC side for clocking
+		 * applications that have setup/hold time requirements on
+		 * rising and falling clock edges.
+		 *
+		 * Workaround:
+		 * Force the phy to be the master to receive a stable clock
+		 * which meets the duty cycle requirement.
+		 */
+		if (of_property_read_bool(of_node, "micrel,force-master")) {
+			result = phy_read(phydev, MII_CTRL1000);
+			if (result < 0)
+				goto err_force_master;
+
+			/* enable master mode, config & prefer master */
+			result |= CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER;
+			result = phy_write(phydev, MII_CTRL1000, result);
+			if (result < 0)
+				goto err_force_master;
+		}
 	}
 
 	return ksz9031_center_flp_timing(phydev);
+
+err_force_master:
+	phydev_err(phydev, "failed to force the phy to master mode\n");
+	return result;
 }
 
 #define KSZ8873MLL_GLOBAL_CONTROL_4	0x06
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 0f293ef28935..a97ac8c12c4c 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -20,6 +20,7 @@
 #include <linux/ethtool.h>
 #include <linux/phy.h>
 #include <linux/microchipphy.h>
+#include <linux/delay.h>
 
 #define DRIVER_AUTHOR	"WOOJUNG HUH <woojung.huh@microchip.com>"
 #define DRIVER_DESC	"Microchip LAN88XX PHY driver"
@@ -30,6 +31,16 @@ struct lan88xx_priv {
 	__u32	wolopts;
 };
 
+static int lan88xx_read_page(struct phy_device *phydev)
+{
+	return __phy_read(phydev, LAN88XX_EXT_PAGE_ACCESS);
+}
+
+static int lan88xx_write_page(struct phy_device *phydev, int page)
+{
+	return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page);
+}
+
 static int lan88xx_phy_config_intr(struct phy_device *phydev)
 {
 	int rc;
@@ -66,6 +77,150 @@ static int lan88xx_suspend(struct phy_device *phydev)
 	return 0;
 }
 
+static int lan88xx_TR_reg_set(struct phy_device *phydev, u16 regaddr,
+			      u32 data)
+{
+	int val, save_page, ret = 0;
+	u16 buf;
+
+	/* Save current page */
+	save_page = phy_save_page(phydev);
+	if (save_page < 0) {
+		pr_warn("Failed to get current page\n");
+		goto err;
+	}
+
+	/* Switch to TR page */
+	lan88xx_write_page(phydev, LAN88XX_EXT_PAGE_ACCESS_TR);
+
+	ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_LOW_DATA,
+			  (data & 0xFFFF));
+	if (ret < 0) {
+		pr_warn("Failed to write TR low data\n");
+		goto err;
+	}
+
+	ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_HIGH_DATA,
+			  (data & 0x00FF0000) >> 16);
+	if (ret < 0) {
+		pr_warn("Failed to write TR high data\n");
+		goto err;
+	}
+
+	/* Config control bits [15:13] of register */
+	buf = (regaddr & ~(0x3 << 13));/* Clr [14:13] to write data in reg */
+	buf |= 0x8000; /* Set [15] to Packet transmit */
+
+	ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_CR, buf);
+	if (ret < 0) {
+		pr_warn("Failed to write data in reg\n");
+		goto err;
+	}
+
+	usleep_range(1000, 2000);/* Wait for Data to be written */
+	val = __phy_read(phydev, LAN88XX_EXT_PAGE_TR_CR);
+	if (!(val & 0x8000))
+		pr_warn("TR Register[0x%X] configuration failed\n", regaddr);
+err:
+	return phy_restore_page(phydev, save_page, ret);
+}
+
+static void lan88xx_config_TR_regs(struct phy_device *phydev)
+{
+	int err;
+
+	/* Get access to Channel 0x1, Node 0xF , Register 0x01.
+	 * Write 24-bit value 0x12B00A to register. Setting MrvlTrFix1000Kf,
+	 * MrvlTrFix1000Kp, MasterEnableTR bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x0F82, 0x12B00A);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x0F82]\n");
+
+	/* Get access to Channel b'10, Node b'1101, Register 0x06.
+	 * Write 24-bit value 0xD2C46F to register. Setting SSTrKf1000Slv,
+	 * SSTrKp1000Mas bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x168C, 0xD2C46F);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x168C]\n");
+
+	/* Get access to Channel b'10, Node b'1111, Register 0x11.
+	 * Write 24-bit value 0x620 to register. Setting rem_upd_done_thresh
+	 * bits
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x17A2, 0x620);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x17A2]\n");
+
+	/* Get access to Channel b'10, Node b'1101, Register 0x10.
+	 * Write 24-bit value 0xEEFFDD to register. Setting
+	 * eee_TrKp1Long_1000, eee_TrKp2Long_1000, eee_TrKp3Long_1000,
+	 * eee_TrKp1Short_1000,eee_TrKp2Short_1000, eee_TrKp3Short_1000 bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x16A0, 0xEEFFDD);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x16A0]\n");
+
+	/* Get access to Channel b'10, Node b'1101, Register 0x13.
+	 * Write 24-bit value 0x071448 to register. Setting
+	 * slv_lpi_tr_tmr_val1, slv_lpi_tr_tmr_val2 bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x16A6, 0x071448);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x16A6]\n");
+
+	/* Get access to Channel b'10, Node b'1101, Register 0x12.
+	 * Write 24-bit value 0x13132F to register. Setting
+	 * slv_sigdet_timer_val1, slv_sigdet_timer_val2 bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x16A4, 0x13132F);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x16A4]\n");
+
+	/* Get access to Channel b'10, Node b'1101, Register 0x14.
+	 * Write 24-bit value 0x0 to register. Setting eee_3level_delay,
+	 * eee_TrKf_freeze_delay bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x16A8, 0x0);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x16A8]\n");
+
+	/* Get access to Channel b'01, Node b'1111, Register 0x34.
+	 * Write 24-bit value 0x91B06C to register. Setting
+	 * FastMseSearchThreshLong1000, FastMseSearchThreshShort1000,
+	 * FastMseSearchUpdGain1000 bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x0FE8, 0x91B06C);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x0FE8]\n");
+
+	/* Get access to Channel b'01, Node b'1111, Register 0x3E.
+	 * Write 24-bit value 0xC0A028 to register. Setting
+	 * FastMseKp2ThreshLong1000, FastMseKp2ThreshShort1000,
+	 * FastMseKp2UpdGain1000, FastMseKp2ExitEn1000 bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x0FFC, 0xC0A028);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x0FFC]\n");
+
+	/* Get access to Channel b'01, Node b'1111, Register 0x35.
+	 * Write 24-bit value 0x041600 to register. Setting
+	 * FastMseSearchPhShNum1000, FastMseSearchClksPerPh1000,
+	 * FastMsePhChangeDelay1000 bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x0FEA, 0x041600);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x0FEA]\n");
+
+	/* Get access to Channel b'10, Node b'1101, Register 0x03.
+	 * Write 24-bit value 0x000004 to register. Setting TrFreeze bits.
+	 */
+	err = lan88xx_TR_reg_set(phydev, 0x1686, 0x000004);
+	if (err < 0)
+		pr_warn("Failed to Set Register[0x1686]\n");
+}
+
 static int lan88xx_probe(struct phy_device *phydev)
 {
 	struct device *dev = &phydev->mdio.dev;
@@ -132,6 +287,25 @@ static void lan88xx_set_mdix(struct phy_device *phydev)
 	phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, LAN88XX_EXT_PAGE_SPACE_0);
 }
 
+static int lan88xx_config_init(struct phy_device *phydev)
+{
+	int val;
+
+	genphy_config_init(phydev);
+	/*Zerodetect delay enable */
+	val = phy_read_mmd(phydev, MDIO_MMD_PCS,
+			   PHY_ARDENNES_MMD_DEV_3_PHY_CFG);
+	val |= PHY_ARDENNES_MMD_DEV_3_PHY_CFG_ZD_DLY_EN_;
+
+	phy_write_mmd(phydev, MDIO_MMD_PCS, PHY_ARDENNES_MMD_DEV_3_PHY_CFG,
+		      val);
+
+	/* Config DSP registers */
+	lan88xx_config_TR_regs(phydev);
+
+	return 0;
+}
+
 static int lan88xx_config_aneg(struct phy_device *phydev)
 {
 	lan88xx_set_mdix(phydev);
@@ -151,7 +325,7 @@ static struct phy_driver microchip_phy_driver[] = {
 	.probe		= lan88xx_probe,
 	.remove		= lan88xx_remove,
 
-	.config_init	= genphy_config_init,
+	.config_init	= lan88xx_config_init,
 	.config_aneg	= lan88xx_config_aneg,
 
 	.ack_interrupt	= lan88xx_phy_ack_interrupt,
@@ -160,6 +334,8 @@ static struct phy_driver microchip_phy_driver[] = {
 	.suspend	= lan88xx_suspend,
 	.resume		= genphy_resume,
 	.set_wol	= lan88xx_set_wol,
+	.read_page	= lan88xx_read_page,
+	.write_page	= lan88xx_write_page,
 } };
 
 module_phy_driver(microchip_phy_driver);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ac23322a32e1..9e4ba8e80a18 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -535,8 +535,17 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id,
 
 	/* Grab the bits from PHYIR1, and put them in the upper half */
 	phy_reg = mdiobus_read(bus, addr, MII_PHYSID1);
-	if (phy_reg < 0)
+	if (phy_reg < 0) {
+		/* if there is no device, return without an error so scanning
+		 * the bus works properly
+		 */
+		if (phy_reg == -EIO || phy_reg == -ENODEV) {
+			*phy_id = 0xffffffff;
+			return 0;
+		}
+
 		return -EIO;
+	}
 
 	*phy_id = (phy_reg & 0xffff) << 16;
 
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 0381da78d228..fd6c23f69c2f 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -125,7 +125,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 	if (id->base.br_nominal) {
 		if (id->base.br_nominal != 255) {
 			br_nom = id->base.br_nominal * 100;
-			br_min = br_nom + id->base.br_nominal * id->ext.br_min;
+			br_min = br_nom - id->base.br_nominal * id->ext.br_min;
 			br_max = br_nom + id->base.br_nominal * id->ext.br_max;
 		} else if (id->ext.br_max) {
 			br_nom = 250 * id->ext.br_max;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index dc7c7ec43202..02ad03a2fab7 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -605,30 +605,13 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	if (cmd == PPPIOCDETACH) {
 		/*
-		 * We have to be careful here... if the file descriptor
-		 * has been dup'd, we could have another process in the
-		 * middle of a poll using the same file *, so we had
-		 * better not free the interface data structures -
-		 * instead we fail the ioctl.  Even in this case, we
-		 * shut down the interface if we are the owner of it.
-		 * Actually, we should get rid of PPPIOCDETACH, userland
-		 * (i.e. pppd) could achieve the same effect by closing
-		 * this fd and reopening /dev/ppp.
+		 * PPPIOCDETACH is no longer supported as it was heavily broken,
+		 * and is only known to have been used by pppd older than
+		 * ppp-2.4.2 (released November 2003).
 		 */
+		pr_warn_once("%s (%d) used obsolete PPPIOCDETACH ioctl\n",
+			     current->comm, current->pid);
 		err = -EINVAL;
-		if (pf->kind == INTERFACE) {
-			ppp = PF_TO_PPP(pf);
-			rtnl_lock();
-			if (file == ppp->owner)
-				unregister_netdevice(ppp->dev);
-			rtnl_unlock();
-		}
-		if (atomic_long_read(&file->f_count) < 2) {
-			ppp_release(NULL, file);
-			err = 0;
-		} else
-			pr_warn("PPPIOCDETACH file->f_count=%ld\n",
-				atomic_long_read(&file->f_count));
 		goto out;
 	}
 
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 1483bc7b01e1..de51e8f70f44 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -620,6 +620,10 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 	lock_sock(sk);
 
 	error = -EINVAL;
+
+	if (sockaddr_len != sizeof(struct sockaddr_pppox))
+		goto end;
+
 	if (sp->sa_protocol != PX_PROTO_OE)
 		goto end;
 
@@ -1092,21 +1096,6 @@ static const struct seq_operations pppoe_seq_ops = {
 	.stop		= pppoe_seq_stop,
 	.show		= pppoe_seq_show,
 };
-
-static int pppoe_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &pppoe_seq_ops,
-			sizeof(struct seq_net_private));
-}
-
-static const struct file_operations pppoe_seq_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pppoe_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 #endif /* CONFIG_PROC_FS */
 
 static const struct proto_ops pppoe_ops = {
@@ -1118,7 +1107,7 @@ static const struct proto_ops pppoe_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pppoe_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
@@ -1142,7 +1131,8 @@ static __net_init int pppoe_init_net(struct net *net)
 
 	rwlock_init(&pn->hash_lock);
 
-	pde = proc_create("pppoe", 0444, net->proc_net, &pppoe_seq_fops);
+	pde = proc_create_net("pppoe", 0444, net->proc_net,
+			&pppoe_seq_ops, sizeof(struct seq_net_private));
 #ifdef CONFIG_PROC_FS
 	if (!pde)
 		return -ENOMEM;
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index c4267ecefd85..157b67c1bf8e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -624,7 +624,6 @@ static const struct proto_ops pptp_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept     = sock_no_accept,
 	.getname    = pptp_getname,
-	.poll       = sock_no_poll,
 	.listen     = sock_no_listen,
 	.shutdown   = sock_no_shutdown,
 	.setsockopt = sock_no_setsockopt,
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index a6c6ce19eeee..ddb6bf85a59c 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -261,6 +261,17 @@ static void __team_option_inst_mark_removed_port(struct team *team,
 	}
 }
 
+static bool __team_option_inst_tmp_find(const struct list_head *opts,
+					const struct team_option_inst *needle)
+{
+	struct team_option_inst *opt_inst;
+
+	list_for_each_entry(opt_inst, opts, tmp_list)
+		if (opt_inst == needle)
+			return true;
+	return false;
+}
+
 static int __team_options_register(struct team *team,
 				   const struct team_option *option,
 				   size_t option_count)
@@ -1061,14 +1072,11 @@ static void team_port_leave(struct team *team, struct team_port *port)
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int __team_port_enable_netpoll(struct team_port *port)
 {
 	struct netpoll *np;
 	int err;
 
-	if (!team->dev->npinfo)
-		return 0;
-
 	np = kzalloc(sizeof(*np), GFP_KERNEL);
 	if (!np)
 		return -ENOMEM;
@@ -1082,6 +1090,14 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port)
 	return err;
 }
 
+static int team_port_enable_netpoll(struct team_port *port)
+{
+	if (!port->team->dev->npinfo)
+		return 0;
+
+	return __team_port_enable_netpoll(port);
+}
+
 static void team_port_disable_netpoll(struct team_port *port)
 {
 	struct netpoll *np = port->np;
@@ -1096,7 +1112,7 @@ static void team_port_disable_netpoll(struct team_port *port)
 	kfree(np);
 }
 #else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team_port *port)
 {
 	return 0;
 }
@@ -1210,7 +1226,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_vids_add;
 	}
 
-	err = team_port_enable_netpoll(team, port);
+	err = team_port_enable_netpoll(port);
 	if (err) {
 		netdev_err(dev, "Failed to enable netpoll on device %s\n",
 			   portname);
@@ -1907,7 +1923,7 @@ static int team_netpoll_setup(struct net_device *dev,
 
 	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list) {
-		err = team_port_enable_netpoll(team, port);
+		err = __team_port_enable_netpoll(port);
 		if (err) {
 			__team_netpoll_cleanup(team);
 			break;
@@ -2568,6 +2584,14 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 			if (err)
 				goto team_put;
 			opt_inst->changed = true;
+
+			/* dumb/evil user-space can send us duplicate opt,
+			 * keep only the last one
+			 */
+			if (__team_option_inst_tmp_find(&opt_inst_list,
+							opt_inst))
+				continue;
+
 			list_add(&opt_inst->tmp_list, &opt_inst_list);
 		}
 		if (!opt_found) {
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 28583aa0c17d..23e9eb66197f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -681,15 +681,6 @@ static void tun_queue_purge(struct tun_file *tfile)
 	skb_queue_purge(&tfile->sk.sk_error_queue);
 }
 
-static void tun_cleanup_tx_ring(struct tun_file *tfile)
-{
-	if (tfile->tx_ring.queue) {
-		ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
-		xdp_rxq_info_unreg(&tfile->xdp_rxq);
-		memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring));
-	}
-}
-
 static void __tun_detach(struct tun_file *tfile, bool clean)
 {
 	struct tun_file *ntfile;
@@ -736,7 +727,9 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
 		}
-		tun_cleanup_tx_ring(tfile);
+		if (tun)
+			xdp_rxq_info_unreg(&tfile->xdp_rxq);
+		ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
 		sock_put(&tfile->sk);
 	}
 }
@@ -783,14 +776,14 @@ static void tun_detach_all(struct net_device *dev)
 		tun_napi_del(tun, tfile);
 		/* Drop read queue */
 		tun_queue_purge(tfile);
+		xdp_rxq_info_unreg(&tfile->xdp_rxq);
 		sock_put(&tfile->sk);
-		tun_cleanup_tx_ring(tfile);
 	}
 	list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
 		tun_enable_queue(tfile);
 		tun_queue_purge(tfile);
+		xdp_rxq_info_unreg(&tfile->xdp_rxq);
 		sock_put(&tfile->sk);
-		tun_cleanup_tx_ring(tfile);
 	}
 	BUG_ON(tun->numdisabled != 0);
 
@@ -834,7 +827,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	}
 
 	if (!tfile->detached &&
-	    ptr_ring_init(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL)) {
+	    ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len,
+			    GFP_KERNEL, tun_ptr_free)) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -1102,12 +1096,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 
 	len = run_ebpf_filter(tun, skb, len);
-
-	/* Trim extra bytes since we may insert vlan proto & TCI
-	 * in tun_put_user().
-	 */
-	len -= skb_vlan_tag_present(skb) ? sizeof(struct veth) : 0;
-	if (len <= 0 || pskb_trim(skb, len))
+	if (len == 0 || pskb_trim(skb, len))
 		goto drop;
 
 	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
@@ -1434,6 +1423,13 @@ static void tun_net_init(struct net_device *dev)
 	dev->max_mtu = MAX_MTU - dev->hard_header_len;
 }
 
+static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile)
+{
+	struct sock *sk = tfile->socket.sk;
+
+	return (tun->dev->flags & IFF_UP) && sock_writeable(sk);
+}
+
 /* Character device part */
 
 /* Poll */
@@ -1456,10 +1452,14 @@ static __poll_t tun_chr_poll(struct file *file, poll_table *wait)
 	if (!ptr_ring_empty(&tfile->tx_ring))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
-	if (tun->dev->flags & IFF_UP &&
-	    (sock_writeable(sk) ||
-	     (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
-	      sock_writeable(sk))))
+	/* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to
+	 * guarantee EPOLLOUT to be raised by either here or
+	 * tun_sock_write_space(). Then process could get notification
+	 * after it writes to a down device and meets -EIO.
+	 */
+	if (tun_sock_writeable(tun, tfile) ||
+	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	     tun_sock_writeable(tun, tfile)))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 
 	if (tun->dev->reg_state != NETREG_REGISTERED)
@@ -1650,7 +1650,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	else
 		*skb_xdp = 0;
 
-	preempt_disable();
+	local_bh_disable();
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(tun->xdp_prog);
 	if (xdp_prog && !*skb_xdp) {
@@ -1675,7 +1675,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			if (err)
 				goto err_redirect;
 			rcu_read_unlock();
-			preempt_enable();
+			local_bh_enable();
 			return NULL;
 		case XDP_TX:
 			get_page(alloc_frag->page);
@@ -1684,7 +1684,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 				goto err_redirect;
 			tun_xdp_flush(tun->dev);
 			rcu_read_unlock();
-			preempt_enable();
+			local_bh_enable();
 			return NULL;
 		case XDP_PASS:
 			delta = orig_data - xdp.data;
@@ -1703,7 +1703,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	skb = build_skb(buf, buflen);
 	if (!skb) {
 		rcu_read_unlock();
-		preempt_enable();
+		local_bh_enable();
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1713,7 +1713,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	alloc_frag->offset += buflen;
 
 	rcu_read_unlock();
-	preempt_enable();
+	local_bh_enable();
 
 	return skb;
 
@@ -1721,7 +1721,7 @@ err_redirect:
 	put_page(alloc_frag->page);
 err_xdp:
 	rcu_read_unlock();
-	preempt_enable();
+	local_bh_enable();
 	this_cpu_inc(tun->pcpu_stats->rx_dropped);
 	return NULL;
 }
@@ -1917,16 +1917,19 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		struct bpf_prog *xdp_prog;
 		int ret;
 
+		local_bh_disable();
 		rcu_read_lock();
 		xdp_prog = rcu_dereference(tun->xdp_prog);
 		if (xdp_prog) {
 			ret = do_xdp_generic(xdp_prog, skb);
 			if (ret != XDP_PASS) {
 				rcu_read_unlock();
+				local_bh_enable();
 				return total_len;
 			}
 		}
 		rcu_read_unlock();
+		local_bh_enable();
 	}
 
 	rcu_read_lock();
@@ -3224,6 +3227,11 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 					    &tun_proto, 0);
 	if (!tfile)
 		return -ENOMEM;
+	if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) {
+		sk_free(&tfile->sk);
+		return -ENOMEM;
+	}
+
 	RCU_INIT_POINTER(tfile->tun, NULL);
 	tfile->flags = 0;
 	tfile->ifindex = 0;
@@ -3244,8 +3252,6 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 
 	sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
 
-	memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring));
-
 	return 0;
 }
 
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 7220cd620717..0362acd5cdca 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -609,7 +609,7 @@ static const struct driver_info cdc_mbim_info_ndp_to_end = {
  */
 static const struct driver_info cdc_mbim_info_avoid_altsetting_toggle = {
 	.description = "CDC MBIM",
-	.flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN,
+	.flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN | FLAG_SEND_ZLP,
 	.bind = cdc_mbim_bind,
 	.unbind = cdc_mbim_unbind,
 	.manage_power = cdc_mbim_manage_power,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index ca066b785e9f..094680871687 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1098,15 +1098,18 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x05c6, 0x9080, 8)},
 	{QMI_FIXED_INTF(0x05c6, 0x9083, 3)},
 	{QMI_FIXED_INTF(0x05c6, 0x9084, 4)},
+	{QMI_FIXED_INTF(0x05c6, 0x90b2, 3)},    /* ublox R410M */
 	{QMI_FIXED_INTF(0x05c6, 0x920d, 0)},
 	{QMI_FIXED_INTF(0x05c6, 0x920d, 5)},
 	{QMI_QUIRK_SET_DTR(0x05c6, 0x9625, 4)},	/* YUGA CLM920-NC5 */
 	{QMI_FIXED_INTF(0x0846, 0x68a2, 8)},
+	{QMI_FIXED_INTF(0x0846, 0x68d3, 8)},	/* Netgear Aircard 779S */
 	{QMI_FIXED_INTF(0x12d1, 0x140c, 1)},	/* Huawei E173 */
 	{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)},	/* Huawei E1820 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 3)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 4)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 5)},	/* Wistron NeWeb D18Q1 */
+	{QMI_FIXED_INTF(0x1435, 0xd191, 4)},	/* Wistron NeWeb D19Q1 */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
 	{QMI_FIXED_INTF(0x16d8, 0x6007, 0)},	/* CMOTech CHE-628S */
 	{QMI_FIXED_INTF(0x16d8, 0x6008, 0)},	/* CMOTech CMU-301 */
@@ -1342,6 +1345,18 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 		id->driver_info = (unsigned long)&qmi_wwan_info;
 	}
 
+	/* There are devices where the same interface number can be
+	 * configured as different functions. We should only bind to
+	 * vendor specific functions when matching on interface number
+	 */
+	if (id->match_flags & USB_DEVICE_ID_MATCH_INT_NUMBER &&
+	    desc->bInterfaceClass != USB_CLASS_VENDOR_SPEC) {
+		dev_dbg(&intf->dev,
+			"Rejecting interface number match for class %02x\n",
+			desc->bInterfaceClass);
+		return -ENODEV;
+	}
+
 	/* Quectel EC20 quirk where we've QMI on interface 4 instead of 0 */
 	if (quectel_ec20_detected(intf) && desc->bInterfaceNumber == 0) {
 		dev_dbg(&intf->dev, "Quectel EC20 quirk, skipping interface 0\n");
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7b187ec7411e..032e1ac10a30 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -147,6 +147,17 @@ struct receive_queue {
 	struct xdp_rxq_info xdp_rxq;
 };
 
+/* Control VQ buffers: protected by the rtnl lock */
+struct control_buf {
+	struct virtio_net_ctrl_hdr hdr;
+	virtio_net_ctrl_ack status;
+	struct virtio_net_ctrl_mq mq;
+	u8 promisc;
+	u8 allmulti;
+	__virtio16 vid;
+	__virtio64 offloads;
+};
+
 struct virtnet_info {
 	struct virtio_device *vdev;
 	struct virtqueue *cvq;
@@ -192,14 +203,7 @@ struct virtnet_info {
 	struct hlist_node node;
 	struct hlist_node node_dead;
 
-	/* Control VQ buffers: protected by the rtnl lock */
-	struct virtio_net_ctrl_hdr ctrl_hdr;
-	virtio_net_ctrl_ack ctrl_status;
-	struct virtio_net_ctrl_mq ctrl_mq;
-	u8 ctrl_promisc;
-	u8 ctrl_allmulti;
-	u16 ctrl_vid;
-	u64 ctrl_offloads;
+	struct control_buf *ctrl;
 
 	/* Ethtool settings */
 	u8 duplex;
@@ -703,6 +707,13 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		void *data;
 		u32 act;
 
+		/* Transient failure which in theory could occur if
+		 * in-flight packets from before XDP was enabled reach
+		 * the receive path after XDP is loaded.
+		 */
+		if (unlikely(hdr->hdr.gso_type))
+			goto err_xdp;
+
 		/* This happens when rx buffer size is underestimated
 		 * or headroom is not enough because of the buffer
 		 * was refilled before XDP is set. This should only
@@ -723,14 +734,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			xdp_page = page;
 		}
 
-		/* Transient failure which in theory could occur if
-		 * in-flight packets from before XDP was enabled reach
-		 * the receive path after XDP is loaded. In practice I
-		 * was not able to create this condition.
-		 */
-		if (unlikely(hdr->hdr.gso_type))
-			goto err_xdp;
-
 		/* Allow consuming headroom but reserve enough space to push
 		 * the descriptor on if we get an XDP_TX return code.
 		 */
@@ -771,7 +774,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			}
 			*xdp_xmit = true;
 			if (unlikely(xdp_page != page))
-				goto err_xdp;
+				put_page(page);
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
@@ -783,7 +786,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			}
 			*xdp_xmit = true;
 			if (unlikely(xdp_page != page))
-				goto err_xdp;
+				put_page(page);
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
@@ -871,7 +874,7 @@ err_xdp:
 	rcu_read_unlock();
 err_skb:
 	put_page(page);
-	while (--num_buf) {
+	while (num_buf-- > 1) {
 		buf = virtqueue_get_buf(rq->vq, &len);
 		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers missing\n",
@@ -1269,7 +1272,9 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 {
 	struct receive_queue *rq =
 		container_of(napi, struct receive_queue, napi);
-	unsigned int received;
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	struct send_queue *sq;
+	unsigned int received, qp;
 	bool xdp_xmit = false;
 
 	virtnet_poll_cleantx(rq);
@@ -1280,8 +1285,13 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	if (received < budget)
 		virtqueue_napi_complete(napi, rq->vq, received);
 
-	if (xdp_xmit)
+	if (xdp_xmit) {
+		qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
+		     smp_processor_id();
+		sq = &vi->sq[qp];
+		virtqueue_kick(sq->vq);
 		xdp_do_flush_map();
+	}
 
 	return received;
 }
@@ -1454,25 +1464,25 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 	/* Caller should know better */
 	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
 
-	vi->ctrl_status = ~0;
-	vi->ctrl_hdr.class = class;
-	vi->ctrl_hdr.cmd = cmd;
+	vi->ctrl->status = ~0;
+	vi->ctrl->hdr.class = class;
+	vi->ctrl->hdr.cmd = cmd;
 	/* Add header */
-	sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
+	sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr));
 	sgs[out_num++] = &hdr;
 
 	if (out)
 		sgs[out_num++] = out;
 
 	/* Add return status. */
-	sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
+	sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status));
 	sgs[out_num] = &stat;
 
 	BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
 	virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
 
 	if (unlikely(!virtqueue_kick(vi->cvq)))
-		return vi->ctrl_status == VIRTIO_NET_OK;
+		return vi->ctrl->status == VIRTIO_NET_OK;
 
 	/* Spin for a response, the kick causes an ioport write, trapping
 	 * into the hypervisor, so the request should be handled immediately.
@@ -1481,7 +1491,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 	       !virtqueue_is_broken(vi->cvq))
 		cpu_relax();
 
-	return vi->ctrl_status == VIRTIO_NET_OK;
+	return vi->ctrl->status == VIRTIO_NET_OK;
 }
 
 static int virtnet_set_mac_address(struct net_device *dev, void *p)
@@ -1593,8 +1603,8 @@ static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
 		return 0;
 
-	vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
-	sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq));
+	vi->ctrl->mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
+	sg_init_one(&sg, &vi->ctrl->mq, sizeof(vi->ctrl->mq));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
 				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) {
@@ -1653,22 +1663,22 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
 		return;
 
-	vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
-	vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+	vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0);
+	vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
 
-	sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
+	sg_init_one(sg, &vi->ctrl->promisc, sizeof(vi->ctrl->promisc));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_PROMISC, sg))
 		dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
-			 vi->ctrl_promisc ? "en" : "dis");
+			 vi->ctrl->promisc ? "en" : "dis");
 
-	sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
+	sg_init_one(sg, &vi->ctrl->allmulti, sizeof(vi->ctrl->allmulti));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
 		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
-			 vi->ctrl_allmulti ? "en" : "dis");
+			 vi->ctrl->allmulti ? "en" : "dis");
 
 	uc_count = netdev_uc_count(dev);
 	mc_count = netdev_mc_count(dev);
@@ -1714,8 +1724,8 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl_vid = vid;
-	sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+	vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
+	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
 				  VIRTIO_NET_CTRL_VLAN_ADD, &sg))
@@ -1729,8 +1739,8 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl_vid = vid;
-	sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+	vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
+	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
 				  VIRTIO_NET_CTRL_VLAN_DEL, &sg))
@@ -2126,9 +2136,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads)
 {
 	struct scatterlist sg;
-	vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads);
+	vi->ctrl->offloads = cpu_to_virtio64(vi->vdev, offloads);
 
-	sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads));
+	sg_init_one(&sg, &vi->ctrl->offloads, sizeof(vi->ctrl->offloads));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS,
 				  VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) {
@@ -2351,6 +2361,7 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 
 	kfree(vi->rq);
 	kfree(vi->sq);
+	kfree(vi->ctrl);
 }
 
 static void _free_receive_bufs(struct virtnet_info *vi)
@@ -2543,6 +2554,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 {
 	int i;
 
+	vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL);
+	if (!vi->ctrl)
+		goto err_ctrl;
 	vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
 	if (!vi->sq)
 		goto err_sq;
@@ -2571,6 +2585,8 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 err_rq:
 	kfree(vi->sq);
 err_sq:
+	kfree(vi->ctrl);
+err_ctrl:
 	return -ENOMEM;
 }
 
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index e04937f44f33..27a9bb8c9611 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -369,6 +369,11 @@ vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq,
 
 	gdesc = tq->comp_ring.base + tq->comp_ring.next2proc;
 	while (VMXNET3_TCD_GET_GEN(&gdesc->tcd) == tq->comp_ring.gen) {
+		/* Prevent any &gdesc->tcd field from being (speculatively)
+		 * read before (&gdesc->tcd)->gen is read.
+		 */
+		dma_rmb();
+
 		completed += vmxnet3_unmap_pkt(VMXNET3_TCD_GET_TXIDX(
 					       &gdesc->tcd), tq, adapter->pdev,
 					       adapter);
@@ -1103,6 +1108,11 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 		gdesc->txd.tci = skb_vlan_tag_get(skb);
 	}
 
+	/* Ensure that the write to (&gdesc->txd)->gen will be observed after
+	 * all other writes to &gdesc->txd.
+	 */
+	dma_wmb();
+
 	/* finally flips the GEN bit of the SOP desc. */
 	gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
 						  VMXNET3_TXD_GEN);
@@ -1218,6 +1228,7 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
 	union {
 		void *ptr;
 		struct ethhdr *eth;
+		struct vlan_ethhdr *veth;
 		struct iphdr *ipv4;
 		struct ipv6hdr *ipv6;
 		struct tcphdr *tcp;
@@ -1228,16 +1239,24 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
 	if (unlikely(sizeof(struct iphdr) + sizeof(struct tcphdr) > maplen))
 		return 0;
 
+	if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
+	    skb->protocol == cpu_to_be16(ETH_P_8021AD))
+		hlen = sizeof(struct vlan_ethhdr);
+	else
+		hlen = sizeof(struct ethhdr);
+
 	hdr.eth = eth_hdr(skb);
 	if (gdesc->rcd.v4) {
-		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP));
-		hdr.ptr += sizeof(struct ethhdr);
+		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP) &&
+		       hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IP));
+		hdr.ptr += hlen;
 		BUG_ON(hdr.ipv4->protocol != IPPROTO_TCP);
 		hlen = hdr.ipv4->ihl << 2;
 		hdr.ptr += hdr.ipv4->ihl << 2;
 	} else if (gdesc->rcd.v6) {
-		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6));
-		hdr.ptr += sizeof(struct ethhdr);
+		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6) &&
+		       hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IPV6));
+		hdr.ptr += hlen;
 		/* Use an estimated value, since we also need to handle
 		 * TSO case.
 		 */
@@ -1289,6 +1308,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			 */
 			break;
 		}
+
+		/* Prevent any rcd field from being (speculatively) read before
+		 * rcd->gen is read.
+		 */
+		dma_rmb();
+
 		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 &&
 		       rcd->rqID != rq->dataRingQid);
 		idx = rcd->rxdIdx;
@@ -1519,6 +1544,12 @@ rcd_done:
 		ring->next2comp = idx;
 		num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring);
 		ring = rq->rx_ring + ring_idx;
+
+		/* Ensure that the writes to rxd->gen bits will be observed
+		 * after all other writes to rxd objects.
+		 */
+		dma_wmb();
+
 		while (num_to_alloc) {
 			vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd,
 					  &rxCmdDesc);
@@ -2679,7 +2710,7 @@ vmxnet3_set_mac_addr(struct net_device *netdev, void *p)
 /* ==================== initialization and cleanup routines ============ */
 
 static int
-vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
+vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter)
 {
 	int err;
 	unsigned long mmio_start, mmio_len;
@@ -2691,30 +2722,12 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
 		return err;
 	}
 
-	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
-		if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
-			dev_err(&pdev->dev,
-				"pci_set_consistent_dma_mask failed\n");
-			err = -EIO;
-			goto err_set_mask;
-		}
-		*dma64 = true;
-	} else {
-		if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
-			dev_err(&pdev->dev,
-				"pci_set_dma_mask failed\n");
-			err = -EIO;
-			goto err_set_mask;
-		}
-		*dma64 = false;
-	}
-
 	err = pci_request_selected_regions(pdev, (1 << 2) - 1,
 					   vmxnet3_driver_name);
 	if (err) {
 		dev_err(&pdev->dev,
 			"Failed to request region for adapter: error %d\n", err);
-		goto err_set_mask;
+		goto err_enable_device;
 	}
 
 	pci_set_master(pdev);
@@ -2742,7 +2755,7 @@ err_bar1:
 	iounmap(adapter->hw_addr0);
 err_ioremap:
 	pci_release_selected_regions(pdev, (1 << 2) - 1);
-err_set_mask:
+err_enable_device:
 	pci_disable_device(pdev);
 	return err;
 }
@@ -3245,7 +3258,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 #endif
 	};
 	int err;
-	bool dma64 = false; /* stupid gcc */
+	bool dma64;
 	u32 ver;
 	struct net_device *netdev;
 	struct vmxnet3_adapter *adapter;
@@ -3291,6 +3304,24 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
 	adapter->rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
 
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
+		if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
+			dev_err(&pdev->dev,
+				"pci_set_consistent_dma_mask failed\n");
+			err = -EIO;
+			goto err_set_mask;
+		}
+		dma64 = true;
+	} else {
+		if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
+			dev_err(&pdev->dev,
+				"pci_set_dma_mask failed\n");
+			err = -EIO;
+			goto err_set_mask;
+		}
+		dma64 = false;
+	}
+
 	spin_lock_init(&adapter->cmd_lock);
 	adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
 					     sizeof(struct vmxnet3_adapter),
@@ -3298,7 +3329,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
 		dev_err(&pdev->dev, "Failed to map dma\n");
 		err = -EFAULT;
-		goto err_dma_map;
+		goto err_set_mask;
 	}
 	adapter->shared = dma_alloc_coherent(
 				&adapter->pdev->dev,
@@ -3349,7 +3380,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	}
 #endif /* VMXNET3_RSS */
 
-	err = vmxnet3_alloc_pci_resources(adapter, &dma64);
+	err = vmxnet3_alloc_pci_resources(adapter);
 	if (err < 0)
 		goto err_alloc_pci;
 
@@ -3495,7 +3526,7 @@ err_alloc_queue_desc:
 err_alloc_shared:
 	dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
 			 sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
-err_dma_map:
+err_set_mask:
 	free_netdev(netdev);
 	return err;
 }
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 59ec34052a65..a2c554f8a61b 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,12 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.13.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.16.0-k"
 
-/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01040d00
+/* Each byte of this 32-bit integer encodes a version number in
+ * VMXNET3_DRIVER_VERSION_STRING.
+ */
+#define VMXNET3_DRIVER_VERSION_NUM      0x01041000
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 8a3020dbd4cf..936907227b9e 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -653,7 +653,7 @@ static const struct firmware *ath10k_fetch_fw_file(struct ath10k *ar,
 		dir = ".";
 
 	snprintf(filename, sizeof(filename), "%s/%s", dir, file);
-	ret = request_firmware(&fw, filename, ar->dev);
+	ret = firmware_request_nowarn(&fw, filename, ar->dev);
 	ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot fw request '%s': %d\n",
 		   filename, ret);
 
diff --git a/drivers/net/wireless/ath/ath10k/testmode.c b/drivers/net/wireless/ath/ath10k/testmode.c
index 568810b41657..c24ee616833c 100644
--- a/drivers/net/wireless/ath/ath10k/testmode.c
+++ b/drivers/net/wireless/ath/ath10k/testmode.c
@@ -157,7 +157,7 @@ static int ath10k_tm_fetch_utf_firmware_api_1(struct ath10k *ar,
 		 ar->hw_params.fw.dir, ATH10K_FW_UTF_FILE);
 
 	/* load utf firmware image */
-	ret = request_firmware_direct(&fw_file->firmware, filename, ar->dev);
+	ret = firmware_request_nowarn(&fw_file->firmware, filename, ar->dev);
 	ath10k_dbg(ar, ATH10K_DBG_TESTMODE, "testmode fw request '%s': %d\n",
 		   filename, ret);
 
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index d122386c382b..b01dc34d55af 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -1482,18 +1482,6 @@ static int atmel_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int atmel_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, atmel_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations atmel_proc_fops = {
-	.open		= atmel_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static const struct net_device_ops atmel_netdev_ops = {
 	.ndo_open 		= atmel_open,
 	.ndo_stop		= atmel_close,
@@ -1614,7 +1602,8 @@ struct net_device *init_atmel_card(unsigned short irq, unsigned long port,
 
 	netif_carrier_off(dev);
 
-	if (!proc_create_data("driver/atmel", 0, NULL, &atmel_proc_fops, priv))
+	if (!proc_create_single_data("driver/atmel", 0, NULL, atmel_proc_show,
+			priv))
 		printk(KERN_WARNING "atmel: unable to create /proc entry.\n");
 
 	printk(KERN_INFO "%s: Atmel at76c50x. Version %d.%d. MAC %pM\n",
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index 9277f4c2bfeb..94e177d7c9b5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -459,7 +459,7 @@ static void brcmf_fw_free_request(struct brcmf_fw_request *req)
 	kfree(req);
 }
 
-static void brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
+static int brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
 {
 	struct brcmf_fw *fwctx = ctx;
 	struct brcmf_fw_item *cur;
@@ -498,13 +498,10 @@ static void brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
 	brcmf_dbg(TRACE, "nvram %p len %d\n", nvram, nvram_length);
 	cur->nv_data.data = nvram;
 	cur->nv_data.len = nvram_length;
-	return;
+	return 0;
 
 fail:
-	brcmf_dbg(TRACE, "failed: dev=%s\n", dev_name(fwctx->dev));
-	fwctx->done(fwctx->dev, -ENOENT, NULL);
-	brcmf_fw_free_request(fwctx->req);
-	kfree(fwctx);
+	return -ENOENT;
 }
 
 static int brcmf_fw_request_next_item(struct brcmf_fw *fwctx, bool async)
@@ -553,20 +550,27 @@ static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
 	brcmf_dbg(TRACE, "enter: firmware %s %sfound\n", cur->path,
 		  fw ? "" : "not ");
 
-	if (fw) {
-		if (cur->type == BRCMF_FW_TYPE_BINARY)
-			cur->binary = fw;
-		else if (cur->type == BRCMF_FW_TYPE_NVRAM)
-			brcmf_fw_request_nvram_done(fw, fwctx);
-		else
-			release_firmware(fw);
-	} else if (cur->type == BRCMF_FW_TYPE_NVRAM) {
-		brcmf_fw_request_nvram_done(NULL, fwctx);
-	} else if (!(cur->flags & BRCMF_FW_REQF_OPTIONAL)) {
+	if (!fw)
 		ret = -ENOENT;
+
+	switch (cur->type) {
+	case BRCMF_FW_TYPE_NVRAM:
+		ret = brcmf_fw_request_nvram_done(fw, fwctx);
+		break;
+	case BRCMF_FW_TYPE_BINARY:
+		cur->binary = fw;
+		break;
+	default:
+		/* something fishy here so bail out early */
+		brcmf_err("unknown fw type: %d\n", cur->type);
+		release_firmware(fw);
+		ret = -EINVAL;
 		goto fail;
 	}
 
+	if (ret < 0 && !(cur->flags & BRCMF_FW_REQF_OPTIONAL))
+		goto fail;
+
 	do {
 		if (++fwctx->curpos == fwctx->req->n_items) {
 			ret = 0;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
index 7af3a0f51b77..a17c4a79b8d4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,7 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018        Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -749,13 +750,9 @@ struct iwl_scan_req_umac {
 } __packed;
 
 #define IWL_SCAN_REQ_UMAC_SIZE_V8 sizeof(struct iwl_scan_req_umac)
-#define IWL_SCAN_REQ_UMAC_SIZE_V7 (sizeof(struct iwl_scan_req_umac) - \
-					 4 * sizeof(u8))
-#define IWL_SCAN_REQ_UMAC_SIZE_V6 (sizeof(struct iwl_scan_req_umac) - \
-				   2 * sizeof(u8) - sizeof(__le16))
-#define IWL_SCAN_REQ_UMAC_SIZE_V1 (sizeof(struct iwl_scan_req_umac) - \
-				   2 * sizeof(__le32) - 2 * sizeof(u8) - \
-				   sizeof(__le16))
+#define IWL_SCAN_REQ_UMAC_SIZE_V7 48
+#define IWL_SCAN_REQ_UMAC_SIZE_V6 44
+#define IWL_SCAN_REQ_UMAC_SIZE_V1 36
 
 /**
  * struct iwl_umac_scan_abort
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 8928613e033e..ca0174680af9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -76,6 +76,7 @@
 #include "iwl-io.h"
 #include "iwl-csr.h"
 #include "fw/acpi.h"
+#include "fw/api/nvm-reg.h"
 
 /* NVM offsets (in words) definitions */
 enum nvm_offsets {
@@ -146,8 +147,8 @@ static const u8 iwl_ext_nvm_channels[] = {
 	149, 153, 157, 161, 165, 169, 173, 177, 181
 };
 
-#define IWL_NUM_CHANNELS		ARRAY_SIZE(iwl_nvm_channels)
-#define IWL_NUM_CHANNELS_EXT	ARRAY_SIZE(iwl_ext_nvm_channels)
+#define IWL_NVM_NUM_CHANNELS		ARRAY_SIZE(iwl_nvm_channels)
+#define IWL_NVM_NUM_CHANNELS_EXT	ARRAY_SIZE(iwl_ext_nvm_channels)
 #define NUM_2GHZ_CHANNELS		14
 #define NUM_2GHZ_CHANNELS_EXT	14
 #define FIRST_2GHZ_HT_MINUS		5
@@ -301,11 +302,11 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 	const u8 *nvm_chan;
 
 	if (cfg->nvm_type != IWL_NVM_EXT) {
-		num_of_ch = IWL_NUM_CHANNELS;
+		num_of_ch = IWL_NVM_NUM_CHANNELS;
 		nvm_chan = &iwl_nvm_channels[0];
 		num_2ghz_channels = NUM_2GHZ_CHANNELS;
 	} else {
-		num_of_ch = IWL_NUM_CHANNELS_EXT;
+		num_of_ch = IWL_NVM_NUM_CHANNELS_EXT;
 		nvm_chan = &iwl_ext_nvm_channels[0];
 		num_2ghz_channels = NUM_2GHZ_CHANNELS_EXT;
 	}
@@ -720,12 +721,12 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	if (cfg->nvm_type != IWL_NVM_EXT)
 		data = kzalloc(sizeof(*data) +
 			       sizeof(struct ieee80211_channel) *
-			       IWL_NUM_CHANNELS,
+			       IWL_NVM_NUM_CHANNELS,
 			       GFP_KERNEL);
 	else
 		data = kzalloc(sizeof(*data) +
 			       sizeof(struct ieee80211_channel) *
-			       IWL_NUM_CHANNELS_EXT,
+			       IWL_NVM_NUM_CHANNELS_EXT,
 			       GFP_KERNEL);
 	if (!data)
 		return NULL;
@@ -842,24 +843,34 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u8 *nvm_chan,
 	return flags;
 }
 
+struct regdb_ptrs {
+	struct ieee80211_wmm_rule *rule;
+	u32 token;
+};
+
 struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
-		       int num_of_ch, __le32 *channels, u16 fw_mcc)
+		       int num_of_ch, __le32 *channels, u16 fw_mcc,
+		       u16 geo_info)
 {
 	int ch_idx;
 	u16 ch_flags;
 	u32 reg_rule_flags, prev_reg_rule_flags = 0;
 	const u8 *nvm_chan = cfg->nvm_type == IWL_NVM_EXT ?
 			     iwl_ext_nvm_channels : iwl_nvm_channels;
-	struct ieee80211_regdomain *regd;
-	int size_of_regd;
+	struct ieee80211_regdomain *regd, *copy_rd;
+	int size_of_regd, regd_to_copy, wmms_to_copy;
+	int size_of_wmms = 0;
 	struct ieee80211_reg_rule *rule;
+	struct ieee80211_wmm_rule *wmm_rule, *d_wmm, *s_wmm;
+	struct regdb_ptrs *regdb_ptrs;
 	enum nl80211_band band;
 	int center_freq, prev_center_freq = 0;
-	int valid_rules = 0;
+	int valid_rules = 0, n_wmms = 0;
+	int i;
 	bool new_rule;
 	int max_num_ch = cfg->nvm_type == IWL_NVM_EXT ?
-			 IWL_NUM_CHANNELS_EXT : IWL_NUM_CHANNELS;
+			 IWL_NVM_NUM_CHANNELS_EXT : IWL_NVM_NUM_CHANNELS;
 
 	if (WARN_ON_ONCE(num_of_ch > NL80211_MAX_SUPP_REG_RULES))
 		return ERR_PTR(-EINVAL);
@@ -875,10 +886,26 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		sizeof(struct ieee80211_regdomain) +
 		num_of_ch * sizeof(struct ieee80211_reg_rule);
 
-	regd = kzalloc(size_of_regd, GFP_KERNEL);
+	if (geo_info & GEO_WMM_ETSI_5GHZ_INFO)
+		size_of_wmms =
+			num_of_ch * sizeof(struct ieee80211_wmm_rule);
+
+	regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL);
 	if (!regd)
 		return ERR_PTR(-ENOMEM);
 
+	regdb_ptrs = kcalloc(num_of_ch, sizeof(*regdb_ptrs), GFP_KERNEL);
+	if (!regdb_ptrs) {
+		copy_rd = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	/* set alpha2 from FW. */
+	regd->alpha2[0] = fw_mcc >> 8;
+	regd->alpha2[1] = fw_mcc & 0xff;
+
+	wmm_rule = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd);
+
 	for (ch_idx = 0; ch_idx < num_of_ch; ch_idx++) {
 		ch_flags = (u16)__le32_to_cpup(channels + ch_idx);
 		band = (ch_idx < NUM_2GHZ_CHANNELS) ?
@@ -927,14 +954,66 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 
 		iwl_nvm_print_channel_flags(dev, IWL_DL_LAR,
 					    nvm_chan[ch_idx], ch_flags);
+
+		if (!(geo_info & GEO_WMM_ETSI_5GHZ_INFO) ||
+		    band == NL80211_BAND_2GHZ)
+			continue;
+
+		if (!reg_query_regdb_wmm(regd->alpha2, center_freq,
+					 &regdb_ptrs[n_wmms].token, wmm_rule)) {
+			/* Add only new rules */
+			for (i = 0; i < n_wmms; i++) {
+				if (regdb_ptrs[i].token ==
+				    regdb_ptrs[n_wmms].token) {
+					rule->wmm_rule = regdb_ptrs[i].rule;
+					break;
+				}
+			}
+			if (i == n_wmms) {
+				rule->wmm_rule = wmm_rule;
+				regdb_ptrs[n_wmms++].rule = wmm_rule;
+				wmm_rule++;
+			}
+		}
 	}
 
 	regd->n_reg_rules = valid_rules;
+	regd->n_wmm_rules = n_wmms;
 
-	/* set alpha2 from FW. */
-	regd->alpha2[0] = fw_mcc >> 8;
-	regd->alpha2[1] = fw_mcc & 0xff;
+	/*
+	 * Narrow down regdom for unused regulatory rules to prevent hole
+	 * between reg rules to wmm rules.
+	 */
+	regd_to_copy = sizeof(struct ieee80211_regdomain) +
+		valid_rules * sizeof(struct ieee80211_reg_rule);
+
+	wmms_to_copy = sizeof(struct ieee80211_wmm_rule) * n_wmms;
+
+	copy_rd = kzalloc(regd_to_copy + wmms_to_copy, GFP_KERNEL);
+	if (!copy_rd) {
+		copy_rd = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	memcpy(copy_rd, regd, regd_to_copy);
+	memcpy((u8 *)copy_rd + regd_to_copy, (u8 *)regd + size_of_regd,
+	       wmms_to_copy);
+
+	d_wmm = (struct ieee80211_wmm_rule *)((u8 *)copy_rd + regd_to_copy);
+	s_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd);
+
+	for (i = 0; i < regd->n_reg_rules; i++) {
+		if (!regd->reg_rules[i].wmm_rule)
+			continue;
+
+		copy_rd->reg_rules[i].wmm_rule = d_wmm +
+			(regd->reg_rules[i].wmm_rule - s_wmm) /
+			sizeof(struct ieee80211_wmm_rule);
+	}
 
-	return regd;
+out:
+	kfree(regdb_ptrs);
+	kfree(regd);
+	return copy_rd;
 }
 IWL_EXPORT_SYMBOL(iwl_parse_nvm_mcc_info);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index 306736c7a042..3071a23b7606 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -101,12 +101,14 @@ void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
  *
  * This function parses the regulatory channel data received as a
  * MCC_UPDATE_CMD command. It returns a newly allocation regulatory domain,
- * to be fed into the regulatory core. An ERR_PTR is returned on error.
+ * to be fed into the regulatory core. In case the geo_info is set handle
+ * accordingly. An ERR_PTR is returned on error.
  * If not given to the regulatory core, the user is responsible for freeing
  * the regdomain returned here with kfree.
  */
 struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
-		       int num_of_ch, __le32 *channels, u16 fw_mcc);
+		       int num_of_ch, __le32 *channels, u16 fw_mcc,
+		       u16 geo_info);
 
 #endif /* __iwl_nvm_parse_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 51b30424575b..90f8c89ea59c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -311,7 +311,8 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
 	regd = iwl_parse_nvm_mcc_info(mvm->trans->dev, mvm->cfg,
 				      __le32_to_cpu(resp->n_channels),
 				      resp->channels,
-				      __le16_to_cpu(resp->mcc));
+				      __le16_to_cpu(resp->mcc),
+				      __le16_to_cpu(resp->geo_info));
 	/* Store the return source id */
 	src_id = resp->source_id;
 	kfree(resp);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index f8a0234d332c..5517ea4c2aa0 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1590,14 +1590,13 @@ static void iwl_pcie_set_interrupt_capa(struct pci_dev *pdev,
 					struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	int max_irqs, num_irqs, i, ret, nr_online_cpus;
+	int max_irqs, num_irqs, i, ret;
 	u16 pci_cmd;
 
 	if (!trans->cfg->mq_rx_supported)
 		goto enable_msi;
 
-	nr_online_cpus = num_online_cpus();
-	max_irqs = min_t(u32, nr_online_cpus + 2, IWL_MAX_RX_HW_QUEUES);
+	max_irqs = min_t(u32, num_online_cpus() + 2, IWL_MAX_RX_HW_QUEUES);
 	for (i = 0; i < max_irqs; i++)
 		trans_pcie->msix_entries[i].entry = i;
 
@@ -1623,16 +1622,17 @@ static void iwl_pcie_set_interrupt_capa(struct pci_dev *pdev,
 	 * Two interrupts less: non rx causes shared with FBQ and RSS.
 	 * More than two interrupts: we will use fewer RSS queues.
 	 */
-	if (num_irqs <= nr_online_cpus) {
+	if (num_irqs <= max_irqs - 2) {
 		trans_pcie->trans->num_rx_queues = num_irqs + 1;
 		trans_pcie->shared_vec_mask = IWL_SHARED_IRQ_NON_RX |
 			IWL_SHARED_IRQ_FIRST_RSS;
-	} else if (num_irqs == nr_online_cpus + 1) {
+	} else if (num_irqs == max_irqs - 1) {
 		trans_pcie->trans->num_rx_queues = num_irqs;
 		trans_pcie->shared_vec_mask = IWL_SHARED_IRQ_NON_RX;
 	} else {
 		trans_pcie->trans->num_rx_queues = num_irqs - 1;
 	}
+	WARN_ON(trans_pcie->trans->num_rx_queues > IWL_MAX_RX_HW_QUEUES);
 
 	trans_pcie->alloc_vecs = num_irqs;
 	trans_pcie->msix_enabled = true;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.c b/drivers/net/wireless/intersil/hostap/hostap_ap.c
index b4dfe1893d18..d1884b8913e7 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_ap.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_ap.c
@@ -69,7 +69,7 @@ static void prism2_send_mgmt(struct net_device *dev,
 #ifndef PRISM2_NO_PROCFS_DEBUG
 static int ap_debug_proc_show(struct seq_file *m, void *v)
 {
-	struct ap_data *ap = m->private;
+	struct ap_data *ap = PDE_DATA(file_inode(m->file));
 
 	seq_printf(m, "BridgedUnicastFrames=%u\n", ap->bridged_unicast);
 	seq_printf(m, "BridgedMulticastFrames=%u\n", ap->bridged_multicast);
@@ -81,18 +81,6 @@ static int ap_debug_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "tx_drop_nonassoc=%u\n", ap->tx_drop_nonassoc);
 	return 0;
 }
-
-static int ap_debug_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ap_debug_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ap_debug_proc_fops = {
-	.open		= ap_debug_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif /* PRISM2_NO_PROCFS_DEBUG */
 
 
@@ -333,7 +321,7 @@ void hostap_deauth_all_stas(struct net_device *dev, struct ap_data *ap,
 
 static int ap_control_proc_show(struct seq_file *m, void *v)
 {
-	struct ap_data *ap = m->private;
+	struct ap_data *ap = PDE_DATA(file_inode(m->file));
 	char *policy_txt;
 	struct mac_entry *entry;
 
@@ -365,20 +353,20 @@ static int ap_control_proc_show(struct seq_file *m, void *v)
 
 static void *ap_control_proc_start(struct seq_file *m, loff_t *_pos)
 {
-	struct ap_data *ap = m->private;
+	struct ap_data *ap = PDE_DATA(file_inode(m->file));
 	spin_lock_bh(&ap->mac_restrictions.lock);
 	return seq_list_start_head(&ap->mac_restrictions.mac_list, *_pos);
 }
 
 static void *ap_control_proc_next(struct seq_file *m, void *v, loff_t *_pos)
 {
-	struct ap_data *ap = m->private;
+	struct ap_data *ap = PDE_DATA(file_inode(m->file));
 	return seq_list_next(v, &ap->mac_restrictions.mac_list, _pos);
 }
 
 static void ap_control_proc_stop(struct seq_file *m, void *v)
 {
-	struct ap_data *ap = m->private;
+	struct ap_data *ap = PDE_DATA(file_inode(m->file));
 	spin_unlock_bh(&ap->mac_restrictions.lock);
 }
 
@@ -389,24 +377,6 @@ static const struct seq_operations ap_control_proc_seqops = {
 	.show	= ap_control_proc_show,
 };
 
-static int ap_control_proc_open(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &ap_control_proc_seqops);
-	if (ret == 0) {
-		struct seq_file *m = file->private_data;
-		m->private = PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static const struct file_operations ap_control_proc_fops = {
-	.open		= ap_control_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-
 int ap_control_add_mac(struct mac_restrictions *mac_restrictions, u8 *mac)
 {
 	struct mac_entry *entry;
@@ -585,20 +555,20 @@ static int prism2_ap_proc_show(struct seq_file *m, void *v)
 
 static void *prism2_ap_proc_start(struct seq_file *m, loff_t *_pos)
 {
-	struct ap_data *ap = m->private;
+	struct ap_data *ap = PDE_DATA(file_inode(m->file));
 	spin_lock_bh(&ap->sta_table_lock);
 	return seq_list_start_head(&ap->sta_list, *_pos);
 }
 
 static void *prism2_ap_proc_next(struct seq_file *m, void *v, loff_t *_pos)
 {
-	struct ap_data *ap = m->private;
+	struct ap_data *ap = PDE_DATA(file_inode(m->file));
 	return seq_list_next(v, &ap->sta_list, _pos);
 }
 
 static void prism2_ap_proc_stop(struct seq_file *m, void *v)
 {
-	struct ap_data *ap = m->private;
+	struct ap_data *ap = PDE_DATA(file_inode(m->file));
 	spin_unlock_bh(&ap->sta_table_lock);
 }
 
@@ -608,23 +578,6 @@ static const struct seq_operations prism2_ap_proc_seqops = {
 	.stop	= prism2_ap_proc_stop,
 	.show	= prism2_ap_proc_show,
 };
-
-static int prism2_ap_proc_open(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &prism2_ap_proc_seqops);
-	if (ret == 0) {
-		struct seq_file *m = file->private_data;
-		m->private = PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static const struct file_operations prism2_ap_proc_fops = {
-	.open		= prism2_ap_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
 
 
@@ -896,12 +849,13 @@ void hostap_init_ap_proc(local_info_t *local)
 		return;
 
 #ifndef PRISM2_NO_PROCFS_DEBUG
-	proc_create_data("ap_debug", 0, ap->proc, &ap_debug_proc_fops, ap);
+	proc_create_single_data("ap_debug", 0, ap->proc, ap_debug_proc_show, ap);
 #endif /* PRISM2_NO_PROCFS_DEBUG */
 
 #ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
-	proc_create_data("ap_control", 0, ap->proc, &ap_control_proc_fops, ap);
-	proc_create_data("ap", 0, ap->proc, &prism2_ap_proc_fops, ap);
+	proc_create_seq_data("ap_control", 0, ap->proc, &ap_control_proc_seqops,
+			ap);
+	proc_create_seq_data("ap", 0, ap->proc, &prism2_ap_proc_seqops, ap);
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
 
 }
@@ -1106,18 +1060,6 @@ static int prism2_sta_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int prism2_sta_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, prism2_sta_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_sta_proc_fops = {
-	.open		= prism2_sta_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static void handle_add_proc_queue(struct work_struct *work)
 {
 	struct ap_data *ap = container_of(work, struct ap_data,
@@ -1138,9 +1080,9 @@ static void handle_add_proc_queue(struct work_struct *work)
 
 		if (sta) {
 			sprintf(name, "%pM", sta->addr);
-			sta->proc = proc_create_data(
+			sta->proc = proc_create_single_data(
 				name, 0, ap->proc,
-				&prism2_sta_proc_fops, sta);
+				prism2_sta_proc_show, sta);
 
 			atomic_dec(&sta->users);
 		}
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index 5c4a17a18968..2720aa39f530 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -2951,19 +2951,6 @@ static int prism2_registers_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int prism2_registers_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, prism2_registers_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_registers_proc_fops = {
-	.open		= prism2_registers_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 #endif /* PRISM2_NO_PROCFS_DEBUG */
 
 
@@ -3279,8 +3266,8 @@ static int hostap_hw_ready(struct net_device *dev)
 		}
 		hostap_init_proc(local);
 #ifndef PRISM2_NO_PROCFS_DEBUG
-		proc_create_data("registers", 0, local->proc,
-				 &prism2_registers_proc_fops, local);
+		proc_create_single_data("registers", 0, local->proc,
+				 prism2_registers_proc_show, local);
 #endif /* PRISM2_NO_PROCFS_DEBUG */
 		hostap_init_ap_proc(local);
 		return 0;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c
index d234231bf532..5b33ccab9188 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_proc.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_proc.c
@@ -43,18 +43,6 @@ static int prism2_debug_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int prism2_debug_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, prism2_debug_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_debug_proc_fops = {
-	.open		= prism2_debug_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif /* PRISM2_NO_PROCFS_DEBUG */
 
 
@@ -95,19 +83,6 @@ static int prism2_stats_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int prism2_stats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, prism2_stats_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_stats_proc_fops = {
-	.open		= prism2_stats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-
 static int prism2_wds_proc_show(struct seq_file *m, void *v)
 {
 	struct list_head *ptr = v;
@@ -122,20 +97,20 @@ static int prism2_wds_proc_show(struct seq_file *m, void *v)
 
 static void *prism2_wds_proc_start(struct seq_file *m, loff_t *_pos)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	read_lock_bh(&local->iface_lock);
 	return seq_list_start(&local->hostap_interfaces, *_pos);
 }
 
 static void *prism2_wds_proc_next(struct seq_file *m, void *v, loff_t *_pos)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	return seq_list_next(v, &local->hostap_interfaces, _pos);
 }
 
 static void prism2_wds_proc_stop(struct seq_file *m, void *v)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	read_unlock_bh(&local->iface_lock);
 }
 
@@ -146,27 +121,9 @@ static const struct seq_operations prism2_wds_proc_seqops = {
 	.show	= prism2_wds_proc_show,
 };
 
-static int prism2_wds_proc_open(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &prism2_wds_proc_seqops);
-	if (ret == 0) {
-		struct seq_file *m = file->private_data;
-		m->private = PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static const struct file_operations prism2_wds_proc_fops = {
-	.open		= prism2_wds_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-
 static int prism2_bss_list_proc_show(struct seq_file *m, void *v)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	struct list_head *ptr = v;
 	struct hostap_bss_info *bss;
 
@@ -193,20 +150,20 @@ static int prism2_bss_list_proc_show(struct seq_file *m, void *v)
 
 static void *prism2_bss_list_proc_start(struct seq_file *m, loff_t *_pos)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	spin_lock_bh(&local->lock);
 	return seq_list_start_head(&local->bss_list, *_pos);
 }
 
 static void *prism2_bss_list_proc_next(struct seq_file *m, void *v, loff_t *_pos)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	return seq_list_next(v, &local->bss_list, _pos);
 }
 
 static void prism2_bss_list_proc_stop(struct seq_file *m, void *v)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	spin_unlock_bh(&local->lock);
 }
 
@@ -217,24 +174,6 @@ static const struct seq_operations prism2_bss_list_proc_seqops = {
 	.show	= prism2_bss_list_proc_show,
 };
 
-static int prism2_bss_list_proc_open(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &prism2_bss_list_proc_seqops);
-	if (ret == 0) {
-		struct seq_file *m = file->private_data;
-		m->private = PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static const struct file_operations prism2_bss_list_proc_fops = {
-	.open		= prism2_bss_list_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-
 static int prism2_crypt_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -252,19 +191,6 @@ static int prism2_crypt_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int prism2_crypt_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, prism2_crypt_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_crypt_proc_fops = {
-	.open		= prism2_crypt_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-
 static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf,
 				    size_t count, loff_t *_pos)
 {
@@ -342,7 +268,7 @@ static int prism2_io_debug_proc_read(char *page, char **start, off_t off,
 #ifndef PRISM2_NO_STATION_MODES
 static int prism2_scan_results_proc_show(struct seq_file *m, void *v)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	unsigned long entry;
 	int i, len;
 	struct hfa384x_hostscan_result *scanres;
@@ -392,7 +318,7 @@ static int prism2_scan_results_proc_show(struct seq_file *m, void *v)
 
 static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	spin_lock_bh(&local->lock);
 
 	/* We have a header (pos 0) + N results to show (pos 1...N) */
@@ -403,7 +329,7 @@ static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos)
 
 static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t *_pos)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 
 	++*_pos;
 	if (*_pos > local->last_scan_results_count)
@@ -413,7 +339,7 @@ static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t *
 
 static void prism2_scan_results_proc_stop(struct seq_file *m, void *v)
 {
-	local_info_t *local = m->private;
+	local_info_t *local = PDE_DATA(file_inode(m->file));
 	spin_unlock_bh(&local->lock);
 }
 
@@ -423,25 +349,6 @@ static const struct seq_operations prism2_scan_results_proc_seqops = {
 	.stop	= prism2_scan_results_proc_stop,
 	.show	= prism2_scan_results_proc_show,
 };
-
-static int prism2_scan_results_proc_open(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &prism2_scan_results_proc_seqops);
-	if (ret == 0) {
-		struct seq_file *m = file->private_data;
-		m->private = PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static const struct file_operations prism2_scan_results_proc_fops = {
-	.open		= prism2_scan_results_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-
 #endif /* PRISM2_NO_STATION_MODES */
 
 
@@ -463,29 +370,29 @@ void hostap_init_proc(local_info_t *local)
 	}
 
 #ifndef PRISM2_NO_PROCFS_DEBUG
-	proc_create_data("debug", 0, local->proc,
-			 &prism2_debug_proc_fops, local);
+	proc_create_single_data("debug", 0, local->proc,
+			prism2_debug_proc_show, local);
 #endif /* PRISM2_NO_PROCFS_DEBUG */
-	proc_create_data("stats", 0, local->proc,
-			 &prism2_stats_proc_fops, local);
-	proc_create_data("wds", 0, local->proc,
-			 &prism2_wds_proc_fops, local);
+	proc_create_single_data("stats", 0, local->proc, prism2_stats_proc_show,
+			local);
+	proc_create_seq_data("wds", 0, local->proc,
+			&prism2_wds_proc_seqops, local);
 	proc_create_data("pda", 0, local->proc,
 			 &prism2_pda_proc_fops, local);
 	proc_create_data("aux_dump", 0, local->proc,
 			 local->func->read_aux_fops ?: &prism2_aux_dump_proc_fops,
 			 local);
-	proc_create_data("bss_list", 0, local->proc,
-			 &prism2_bss_list_proc_fops, local);
-	proc_create_data("crypt", 0, local->proc,
-			 &prism2_crypt_proc_fops, local);
+	proc_create_seq_data("bss_list", 0, local->proc,
+			&prism2_bss_list_proc_seqops, local);
+	proc_create_single_data("crypt", 0, local->proc, prism2_crypt_proc_show,
+		local);
 #ifdef PRISM2_IO_DEBUG
-	proc_create_data("io_debug", 0, local->proc,
-			 &prism2_io_debug_proc_fops, local);
+	proc_create_single_data("io_debug", 0, local->proc,
+			prism2_debug_proc_show, local);
 #endif /* PRISM2_IO_DEBUG */
 #ifndef PRISM2_NO_STATION_MODES
-	proc_create_data("scan_results", 0, local->proc,
-			 &prism2_scan_results_proc_fops, local);
+	proc_create_seq_data("scan_results", 0, local->proc,
+			&prism2_scan_results_proc_seqops, local);
 #endif /* PRISM2_NO_STATION_MODES */
 }
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 96d26cfae90b..920c23e542a5 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3236,6 +3236,7 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 			GENL_SET_ERR_MSG(info,"MAC is no valid source addr");
 			NL_SET_BAD_ATTR(info->extack,
 					info->attrs[HWSIM_ATTR_PERM_ADDR]);
+			kfree(hwname);
 			return -EINVAL;
 		}
 
@@ -3339,7 +3340,7 @@ out_err:
 static int hwsim_dump_radio_nl(struct sk_buff *skb,
 			       struct netlink_callback *cb)
 {
-	int last_idx = cb->args[0];
+	int last_idx = cb->args[0] - 1;
 	struct mac80211_hwsim_data *data = NULL;
 	int res = 0;
 	void *hdr;
@@ -3367,7 +3368,7 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb,
 		last_idx = data->idx;
 	}
 
-	cb->args[0] = last_idx;
+	cb->args[0] = last_idx + 1;
 
 	/* list changed, but no new element sent, set interrupted flag */
 	if (skb->len == 0 && cb->prev_seq && cb->seq != cb->prev_seq) {
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
index a6884e73d2ab..7ddee980048b 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
@@ -372,16 +372,15 @@ static void rt2x00queue_create_tx_descriptor_ht(struct rt2x00_dev *rt2x00dev,
 
 	/*
 	 * Determine IFS values
-	 * - Use TXOP_BACKOFF for probe and management frames except beacons
+	 * - Use TXOP_BACKOFF for management frames except beacons
 	 * - Use TXOP_SIFS for fragment bursts
 	 * - Use TXOP_HTTXOP for everything else
 	 *
 	 * Note: rt2800 devices won't use CTS protection (if used)
 	 * for frames not transmitted with TXOP_HTTXOP
 	 */
-	if ((ieee80211_is_mgmt(hdr->frame_control) &&
-	     !ieee80211_is_beacon(hdr->frame_control)) ||
-	    (tx_info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE))
+	if (ieee80211_is_mgmt(hdr->frame_control) &&
+	    !ieee80211_is_beacon(hdr->frame_control))
 		txdesc->u.ht.txop = TXOP_BACKOFF;
 	else if (!(tx_info->flags & IEEE80211_TX_CTL_FIRST_FRAGMENT))
 		txdesc->u.ht.txop = TXOP_SIFS;
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 7f9b16b97ea3..a7e0a17aa7e8 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -2663,19 +2663,6 @@ static int ray_cs_proc_show(struct seq_file *m, void *v)
 	}
 	return 0;
 }
-
-static int ray_cs_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ray_cs_proc_show, NULL);
-}
-
-static const struct file_operations ray_cs_proc_fops = {
-	.owner = THIS_MODULE,
-	.open = ray_cs_proc_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
 #endif
 /*===========================================================================*/
 static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type)
@@ -2814,7 +2801,7 @@ static int __init init_ray_cs(void)
 #ifdef CONFIG_PROC_FS
 	proc_mkdir("driver/ray_cs", NULL);
 
-	proc_create("driver/ray_cs/ray_cs", 0, NULL, &ray_cs_proc_fops);
+	proc_create_single("driver/ray_cs/ray_cs", 0, NULL, ray_cs_proc_show);
 	proc_create("driver/ray_cs/essid", 0200, NULL, &ray_cs_essid_proc_fops);
 	proc_create_data("driver/ray_cs/net_type", 0200, NULL, &int_proc_fops,
 			 &net_type);
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
index 8b6b07a936f5..b026e80940a4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
@@ -158,16 +158,6 @@ static u8 halbtc_get_wifi_central_chnl(struct btc_coexist *btcoexist)
 
 static u8 rtl_get_hwpg_single_ant_path(struct rtl_priv *rtlpriv)
 {
-	struct rtl_mod_params *mod_params = rtlpriv->cfg->mod_params;
-
-	/* override ant_num / ant_path */
-	if (mod_params->ant_sel) {
-		rtlpriv->btcoexist.btc_info.ant_num =
-			(mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1);
-
-		rtlpriv->btcoexist.btc_info.single_ant_path =
-			(mod_params->ant_sel == 1 ? 0 : 1);
-	}
 	return rtlpriv->btcoexist.btc_info.single_ant_path;
 }
 
@@ -178,7 +168,6 @@ static u8 rtl_get_hwpg_bt_type(struct rtl_priv *rtlpriv)
 
 static u8 rtl_get_hwpg_ant_num(struct rtl_priv *rtlpriv)
 {
-	struct rtl_mod_params *mod_params = rtlpriv->cfg->mod_params;
 	u8 num;
 
 	if (rtlpriv->btcoexist.btc_info.ant_num == ANT_X2)
@@ -186,10 +175,6 @@ static u8 rtl_get_hwpg_ant_num(struct rtl_priv *rtlpriv)
 	else
 		num = 1;
 
-	/* override ant_num / ant_path */
-	if (mod_params->ant_sel)
-		num = (mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1) + 1;
-
 	return num;
 }
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
index e7bbbc95cdb1..b4f3f91b590e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
@@ -848,6 +848,9 @@ static bool _rtl8723be_init_mac(struct ieee80211_hw *hw)
 		return false;
 	}
 
+	if (rtlpriv->cfg->ops->get_btc_status())
+		rtlpriv->btcoexist.btc_ops->btc_power_on_setting(rtlpriv);
+
 	bytetmp = rtl_read_byte(rtlpriv, REG_MULTI_FUNC_CTRL);
 	rtl_write_byte(rtlpriv, REG_MULTI_FUNC_CTRL, bytetmp | BIT(3));
 
@@ -2696,21 +2699,21 @@ void rtl8723be_read_bt_coexist_info_from_hwpg(struct ieee80211_hw *hw,
 		rtlpriv->btcoexist.btc_info.bt_type = BT_RTL8723B;
 		rtlpriv->btcoexist.btc_info.ant_num = (value & 0x1);
 		rtlpriv->btcoexist.btc_info.single_ant_path =
-			 (value & 0x40);	/*0xc3[6]*/
+			 (value & 0x40 ? ANT_AUX : ANT_MAIN);	/*0xc3[6]*/
 	} else {
 		rtlpriv->btcoexist.btc_info.btcoexist = 0;
 		rtlpriv->btcoexist.btc_info.bt_type = BT_RTL8723B;
 		rtlpriv->btcoexist.btc_info.ant_num = ANT_X2;
-		rtlpriv->btcoexist.btc_info.single_ant_path = 0;
+		rtlpriv->btcoexist.btc_info.single_ant_path = ANT_MAIN;
 	}
 
 	/* override ant_num / ant_path */
 	if (mod_params->ant_sel) {
 		rtlpriv->btcoexist.btc_info.ant_num =
-			(mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1);
+			(mod_params->ant_sel == 1 ? ANT_X1 : ANT_X2);
 
 		rtlpriv->btcoexist.btc_info.single_ant_path =
-			(mod_params->ant_sel == 1 ? 0 : 1);
+			(mod_params->ant_sel == 1 ? ANT_AUX : ANT_MAIN);
 	}
 }
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index d27e33960e77..ce1754054a07 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2823,6 +2823,11 @@ enum bt_ant_num {
 	ANT_X1 = 1,
 };
 
+enum bt_ant_path {
+	ANT_MAIN = 0,
+	ANT_AUX = 1,
+};
+
 enum bt_co_type {
 	BT_2WIRE = 0,
 	BT_ISSC_3WIRE = 1,
diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index e153e8b64bb8..d5553c47014f 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -62,6 +62,9 @@ struct pn533_usb_phy {
 	struct urb *out_urb;
 	struct urb *in_urb;
 
+	struct urb *ack_urb;
+	u8 *ack_buffer;
+
 	struct pn533 *priv;
 };
 
@@ -150,13 +153,16 @@ static int pn533_usb_send_ack(struct pn533 *dev, gfp_t flags)
 	struct pn533_usb_phy *phy = dev->phy;
 	static const u8 ack[6] = {0x00, 0x00, 0xff, 0x00, 0xff, 0x00};
 	/* spec 7.1.1.3:  Preamble, SoPC (2), ACK Code (2), Postamble */
-	int rc;
 
-	phy->out_urb->transfer_buffer = (u8 *)ack;
-	phy->out_urb->transfer_buffer_length = sizeof(ack);
-	rc = usb_submit_urb(phy->out_urb, flags);
+	if (!phy->ack_buffer) {
+		phy->ack_buffer = kmemdup(ack, sizeof(ack), flags);
+		if (!phy->ack_buffer)
+			return -ENOMEM;
+	}
 
-	return rc;
+	phy->ack_urb->transfer_buffer = phy->ack_buffer;
+	phy->ack_urb->transfer_buffer_length = sizeof(ack);
+	return usb_submit_urb(phy->ack_urb, flags);
 }
 
 static int pn533_usb_send_frame(struct pn533 *dev,
@@ -375,26 +381,31 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy)
 	/* Power on th reader (CCID cmd) */
 	u8 cmd[10] = {PN533_ACR122_PC_TO_RDR_ICCPOWERON,
 		      0, 0, 0, 0, 0, 0, 3, 0, 0};
+	char *buffer;
+	int transferred;
 	int rc;
 	void *cntx;
 	struct pn533_acr122_poweron_rdr_arg arg;
 
 	dev_dbg(&phy->udev->dev, "%s\n", __func__);
 
+	buffer = kmemdup(cmd, sizeof(cmd), GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
 	init_completion(&arg.done);
 	cntx = phy->in_urb->context;  /* backup context */
 
 	phy->in_urb->complete = pn533_acr122_poweron_rdr_resp;
 	phy->in_urb->context = &arg;
 
-	phy->out_urb->transfer_buffer = cmd;
-	phy->out_urb->transfer_buffer_length = sizeof(cmd);
-
 	print_hex_dump_debug("ACR122 TX: ", DUMP_PREFIX_NONE, 16, 1,
 		       cmd, sizeof(cmd), false);
 
-	rc = usb_submit_urb(phy->out_urb, GFP_KERNEL);
-	if (rc) {
+	rc = usb_bulk_msg(phy->udev, phy->out_urb->pipe, buffer, sizeof(cmd),
+			  &transferred, 0);
+	kfree(buffer);
+	if (rc || (transferred != sizeof(cmd))) {
 		nfc_err(&phy->udev->dev,
 			"Reader power on cmd error %d\n", rc);
 		return rc;
@@ -490,8 +501,9 @@ static int pn533_usb_probe(struct usb_interface *interface,
 
 	phy->in_urb = usb_alloc_urb(0, GFP_KERNEL);
 	phy->out_urb = usb_alloc_urb(0, GFP_KERNEL);
+	phy->ack_urb = usb_alloc_urb(0, GFP_KERNEL);
 
-	if (!phy->in_urb || !phy->out_urb)
+	if (!phy->in_urb || !phy->out_urb || !phy->ack_urb)
 		goto error;
 
 	usb_fill_bulk_urb(phy->in_urb, phy->udev,
@@ -501,7 +513,9 @@ static int pn533_usb_probe(struct usb_interface *interface,
 	usb_fill_bulk_urb(phy->out_urb, phy->udev,
 			  usb_sndbulkpipe(phy->udev, out_endpoint),
 			  NULL, 0, pn533_send_complete, phy);
-
+	usb_fill_bulk_urb(phy->ack_urb, phy->udev,
+			  usb_sndbulkpipe(phy->udev, out_endpoint),
+			  NULL, 0, pn533_send_complete, phy);
 
 	switch (id->driver_info) {
 	case PN533_DEVICE_STD:
@@ -554,6 +568,7 @@ static int pn533_usb_probe(struct usb_interface *interface,
 error:
 	usb_free_urb(phy->in_urb);
 	usb_free_urb(phy->out_urb);
+	usb_free_urb(phy->ack_urb);
 	usb_put_dev(phy->udev);
 	kfree(in_buf);
 
@@ -573,10 +588,13 @@ static void pn533_usb_disconnect(struct usb_interface *interface)
 
 	usb_kill_urb(phy->in_urb);
 	usb_kill_urb(phy->out_urb);
+	usb_kill_urb(phy->ack_urb);
 
 	kfree(phy->in_urb->transfer_buffer);
 	usb_free_urb(phy->in_urb);
 	usb_free_urb(phy->out_urb);
+	usb_free_urb(phy->ack_urb);
+	kfree(phy->ack_buffer);
 
 	nfc_info(&interface->dev, "NXP PN533 NFC device disconnected\n");
 }
diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c
index d306c348c857..a59b6c4bb5b8 100644
--- a/drivers/nubus/bus.c
+++ b/drivers/nubus/bus.c
@@ -63,20 +63,15 @@ static struct device nubus_parent = {
 	.init_name	= "nubus",
 };
 
-int __init nubus_bus_register(void)
+static int __init nubus_bus_register(void)
 {
-	int err;
-
-	err = device_register(&nubus_parent);
-	if (err)
-		return err;
-
-	err = bus_register(&nubus_bus_type);
-	if (!err)
-		return 0;
+	return bus_register(&nubus_bus_type);
+}
+postcore_initcall(nubus_bus_register);
 
-	device_unregister(&nubus_parent);
-	return err;
+int __init nubus_parent_device_register(void)
+{
+	return device_register(&nubus_parent);
 }
 
 static void nubus_device_release(struct device *dev)
diff --git a/drivers/nubus/nubus.c b/drivers/nubus/nubus.c
index 4621ff98138c..bb0d63a44f41 100644
--- a/drivers/nubus/nubus.c
+++ b/drivers/nubus/nubus.c
@@ -875,7 +875,7 @@ static int __init nubus_init(void)
 		return 0;
 
 	nubus_proc_init();
-	err = nubus_bus_register();
+	err = nubus_parent_device_register();
 	if (err)
 		return err;
 	nubus_scan_bus();
diff --git a/drivers/nubus/proc.c b/drivers/nubus/proc.c
index c2e5a7e6bd3e..88e1f9a0faaf 100644
--- a/drivers/nubus/proc.c
+++ b/drivers/nubus/proc.c
@@ -45,18 +45,6 @@ nubus_devices_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int nubus_devices_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, nubus_devices_proc_show, NULL);
-}
-
-static const struct file_operations nubus_devices_proc_fops = {
-	.open		= nubus_devices_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static struct proc_dir_entry *proc_bus_nubus_dir;
 
 /*
@@ -149,18 +137,6 @@ static int nubus_proc_rsrc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int nubus_proc_rsrc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, nubus_proc_rsrc_show, inode);
-}
-
-static const struct file_operations nubus_proc_rsrc_fops = {
-	.open		= nubus_proc_rsrc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir,
 			     const struct nubus_dirent *ent,
 			     unsigned int size)
@@ -176,8 +152,8 @@ void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir,
 		pde_data = nubus_proc_alloc_pde_data(nubus_dirptr(ent), size);
 	else
 		pde_data = NULL;
-	proc_create_data(name, S_IFREG | 0444, procdir,
-			 &nubus_proc_rsrc_fops, pde_data);
+	proc_create_single_data(name, S_IFREG | 0444, procdir,
+			nubus_proc_rsrc_show, pde_data);
 }
 
 void nubus_proc_add_rsrc(struct proc_dir_entry *procdir,
@@ -190,32 +166,21 @@ void nubus_proc_add_rsrc(struct proc_dir_entry *procdir,
 		return;
 
 	snprintf(name, sizeof(name), "%x", ent->type);
-	proc_create_data(name, S_IFREG | 0444, procdir,
-			 &nubus_proc_rsrc_fops,
-			 nubus_proc_alloc_pde_data(data, 0));
+	proc_create_single_data(name, S_IFREG | 0444, procdir,
+			nubus_proc_rsrc_show,
+			nubus_proc_alloc_pde_data(data, 0));
 }
 
 /*
  * /proc/nubus stuff
  */
 
-static int nubus_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, nubus_proc_show, NULL);
-}
-
-static const struct file_operations nubus_proc_fops = {
-	.open		= nubus_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 void __init nubus_proc_init(void)
 {
-	proc_create("nubus", 0, NULL, &nubus_proc_fops);
+	proc_create_single("nubus", 0, NULL, nubus_proc_show);
 	proc_bus_nubus_dir = proc_mkdir("bus/nubus", NULL);
 	if (!proc_bus_nubus_dir)
 		return;
-	proc_create("devices", 0, proc_bus_nubus_dir, &nubus_devices_proc_fops);
+	proc_create_single("devices", 0, proc_bus_nubus_dir,
+			nubus_devices_proc_show);
 }
diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index 85997184e047..9d36473dc2a2 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -103,8 +103,7 @@ config NVDIMM_DAX
 	  Select Y if unsure
 
 config OF_PMEM
-	# FIXME: make tristate once OF_NUMA dependency removed
-	bool "Device-tree support for persistent memory regions"
+	tristate "Device-tree support for persistent memory regions"
 	depends on OF
 	default LIBNVDIMM
 	help
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 30852270484f..2e96b34bc936 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -276,7 +276,8 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	if (rw == READ) {
 		if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align)))
 			return -EIO;
-		return memcpy_mcsafe(buf, nsio->addr + offset, size);
+		if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
+			return -EIO;
 	}
 
 	if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index e00d45522b80..8d348b22ba45 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -88,9 +88,9 @@ int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd)
 int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
 {
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
+	int rc = validate_dimm(ndd), cmd_rc = 0;
 	struct nd_cmd_get_config_data_hdr *cmd;
 	struct nvdimm_bus_descriptor *nd_desc;
-	int rc = validate_dimm(ndd);
 	u32 max_cmd_size, config_size;
 	size_t offset;
 
@@ -124,9 +124,11 @@ int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
 		cmd->in_offset = offset;
 		rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
 				ND_CMD_GET_CONFIG_DATA, cmd,
-				cmd->in_length + sizeof(*cmd), NULL);
-		if (rc || cmd->status) {
-			rc = -ENXIO;
+				cmd->in_length + sizeof(*cmd), &cmd_rc);
+		if (rc < 0)
+			break;
+		if (cmd_rc < 0) {
+			rc = cmd_rc;
 			break;
 		}
 		memcpy(ndd->data + offset, cmd->out_buf, cmd->in_length);
@@ -140,9 +142,9 @@ int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
 int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 		void *buf, size_t len)
 {
-	int rc = validate_dimm(ndd);
 	size_t max_cmd_size, buf_offset;
 	struct nd_cmd_set_config_hdr *cmd;
+	int rc = validate_dimm(ndd), cmd_rc = 0;
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
 	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
 
@@ -164,7 +166,6 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 	for (buf_offset = 0; len; len -= cmd->in_length,
 			buf_offset += cmd->in_length) {
 		size_t cmd_size;
-		u32 *status;
 
 		cmd->in_offset = offset + buf_offset;
 		cmd->in_length = min(max_cmd_size, len);
@@ -172,12 +173,13 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 
 		/* status is output in the last 4-bytes of the command buffer */
 		cmd_size = sizeof(*cmd) + cmd->in_length + sizeof(u32);
-		status = ((void *) cmd) + cmd_size - sizeof(u32);
 
 		rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
-				ND_CMD_SET_CONFIG_DATA, cmd, cmd_size, NULL);
-		if (rc || *status) {
-			rc = rc ? rc : -ENXIO;
+				ND_CMD_SET_CONFIG_DATA, cmd, cmd_size, &cmd_rc);
+		if (rc < 0)
+			break;
+		if (cmd_rc < 0) {
+			rc = cmd_rc;
 			break;
 		}
 	}
diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c
index 85013bad35de..0a701837dfc0 100644
--- a/drivers/nvdimm/of_pmem.c
+++ b/drivers/nvdimm/of_pmem.c
@@ -67,7 +67,7 @@ static int of_pmem_region_probe(struct platform_device *pdev)
 		 */
 		memset(&ndr_desc, 0, sizeof(ndr_desc));
 		ndr_desc.attr_groups = region_attr_groups;
-		ndr_desc.numa_node = of_node_to_nid(np);
+		ndr_desc.numa_node = dev_to_node(&pdev->dev);
 		ndr_desc.res = &pdev->resource[i];
 		ndr_desc.of_node = np;
 		set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 9d714926ecf5..e023d6aa22b5 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -101,15 +101,15 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 		void *pmem_addr, unsigned int len)
 {
 	unsigned int chunk;
-	int rc;
+	unsigned long rem;
 	void *mem;
 
 	while (len) {
 		mem = kmap_atomic(page);
 		chunk = min_t(unsigned int, len, PAGE_SIZE);
-		rc = memcpy_mcsafe(mem + off, pmem_addr, chunk);
+		rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
 		kunmap_atomic(mem);
-		if (rc)
+		if (rem)
 			return BLK_STS_IOERR;
 		len -= chunk;
 		off = 0;
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index b979cf3bce65..88a8b5916624 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -27,7 +27,7 @@ config NVME_FABRICS
 
 config NVME_RDMA
 	tristate "NVM Express over Fabrics RDMA host driver"
-	depends on INFINIBAND && BLOCK
+	depends on INFINIBAND && INFINIBAND_ADDR_TRANS && BLOCK
 	select NVME_CORE
 	select NVME_FABRICS
 	select SG_POOL
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9df4f71e58ca..c8b30067b6ae 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -99,6 +99,16 @@ static struct class *nvme_subsys_class;
 
 static void nvme_ns_remove(struct nvme_ns *ns);
 static int nvme_revalidate_disk(struct gendisk *disk);
+static void nvme_put_subsystem(struct nvme_subsystem *subsys);
+
+static void nvme_queue_scan(struct nvme_ctrl *ctrl)
+{
+	/*
+	 * Only new queue scan work when admin and IO queues are both alive
+	 */
+	if (ctrl->state == NVME_CTRL_LIVE)
+		queue_work(nvme_wq, &ctrl->scan_work);
+}
 
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 {
@@ -117,7 +127,8 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 	ret = nvme_reset_ctrl(ctrl);
 	if (!ret) {
 		flush_work(&ctrl->reset_work);
-		if (ctrl->state != NVME_CTRL_LIVE)
+		if (ctrl->state != NVME_CTRL_LIVE &&
+		    ctrl->state != NVME_CTRL_ADMIN_ONLY)
 			ret = -ENETRESET;
 	}
 
@@ -242,9 +253,6 @@ EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
 void nvme_cancel_request(struct request *req, void *data, bool reserved)
 {
-	if (!blk_mq_request_started(req))
-		return;
-
 	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
 				"Cancelling I/O %d", req->tag);
 
@@ -349,7 +357,8 @@ static void nvme_free_ns_head(struct kref *ref)
 	nvme_mpath_remove_disk(head);
 	ida_simple_remove(&head->subsys->ns_ida, head->instance);
 	list_del_init(&head->entry);
-	cleanup_srcu_struct(&head->srcu);
+	cleanup_srcu_struct_quiesced(&head->srcu);
+	nvme_put_subsystem(head->subsys);
 	kfree(head);
 }
 
@@ -764,6 +773,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 				ret = PTR_ERR(meta);
 				goto out_unmap;
 			}
+			req->cmd_flags |= REQ_INTEGRITY;
 		}
 	}
 
@@ -1029,6 +1039,21 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 }
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
+#define NVME_AEN_SUPPORTED \
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT)
+
+static void nvme_enable_aen(struct nvme_ctrl *ctrl)
+{
+	u32 result;
+	int status;
+
+	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
+			ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+	if (status)
+		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
+			 ctrl->oaes & NVME_AEN_SUPPORTED);
+}
+
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 {
 	struct nvme_user_io io;
@@ -1347,13 +1372,19 @@ static void nvme_set_chunk_size(struct nvme_ns *ns)
 	blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
 }
 
-static void nvme_config_discard(struct nvme_ctrl *ctrl,
-		unsigned stream_alignment, struct request_queue *queue)
+static void nvme_config_discard(struct nvme_ns *ns)
 {
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	struct request_queue *queue = ns->queue;
 	u32 size = queue_logical_block_size(queue);
 
-	if (stream_alignment)
-		size *= stream_alignment;
+	if (!(ctrl->oncs & NVME_CTRL_ONCS_DSM)) {
+		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue);
+		return;
+	}
+
+	if (ctrl->nr_streams && ns->sws && ns->sgs)
+		size *= ns->sws * ns->sgs;
 
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
@@ -1361,9 +1392,12 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl,
 	queue->limits.discard_alignment = 0;
 	queue->limits.discard_granularity = size;
 
+	/* If discard is already enabled, don't reset queue limits */
+	if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
+		return;
+
 	blk_queue_max_discard_sectors(queue, UINT_MAX);
 	blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, queue);
 
 	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
@@ -1407,10 +1441,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
 {
 	sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9);
 	unsigned short bs = 1 << ns->lba_shift;
-	unsigned stream_alignment = 0;
-
-	if (ns->ctrl->nr_streams && ns->sws && ns->sgs)
-		stream_alignment = ns->sws * ns->sgs;
 
 	blk_mq_freeze_queue(disk->queue);
 	blk_integrity_unregister(disk);
@@ -1424,10 +1454,9 @@ static void nvme_update_disk_info(struct gendisk *disk,
 		nvme_init_integrity(disk, ns->ms, ns->pi_type);
 	if (ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk))
 		capacity = 0;
-	set_capacity(disk, capacity);
 
-	if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
-		nvme_config_discard(ns->ctrl, stream_alignment, disk->queue);
+	set_capacity(disk, capacity);
+	nvme_config_discard(ns);
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
@@ -1443,8 +1472,8 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 	ns->noiob = le16_to_cpu(id->noiob);
-	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
 	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
 	/* the PI implementation requires metadata equal t10 pi tuple size */
 	if (ns->ms == sizeof(struct t10_pi_tuple))
 		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
@@ -1573,7 +1602,7 @@ static int nvme_pr_reserve(struct block_device *bdev, u64 key,
 static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
 		enum pr_type type, bool abort)
 {
-	u32 cdw10 = nvme_pr_type(type) << 8 | abort ? 2 : 1;
+	u32 cdw10 = nvme_pr_type(type) << 8 | (abort ? 2 : 1);
 	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
 }
 
@@ -1585,7 +1614,7 @@ static int nvme_pr_clear(struct block_device *bdev, u64 key)
 
 static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 {
-	u32 cdw10 = nvme_pr_type(type) << 8 | key ? 1 << 3 : 0;
+	u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 1 << 3 : 0);
 	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
 }
 
@@ -2179,7 +2208,8 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		 * Verify that the subsystem actually supports multiple
 		 * controllers, else bail out.
 		 */
-		if (nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
+		if (!ctrl->opts->discovery_nqn &&
+		    nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
 			dev_err(ctrl->device,
 				"ignoring ctrl due to duplicate subnqn (%s).\n",
 				found->subnqn);
@@ -2310,7 +2340,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
 		ret = nvme_get_effects_log(ctrl);
 		if (ret < 0)
-			return ret;
+			goto out_free;
 	}
 
 	if (!ctrl->identified) {
@@ -2341,6 +2371,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 
 	ctrl->oacs = le16_to_cpu(id->oacs);
 	ctrl->oncs = le16_to_cpup(&id->oncs);
+	ctrl->oaes = le32_to_cpu(id->oaes);
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
 	ctrl->cntlid = le16_to_cpup(&id->cntlid);
@@ -2860,6 +2891,9 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 		goto out_cleanup_srcu;
 
 	list_add_tail(&head->entry, &ctrl->subsys->nsheads);
+
+	kref_get(&ctrl->subsys->ref);
+
 	return head;
 out_cleanup_srcu:
 	cleanup_srcu_struct(&head->srcu);
@@ -2997,31 +3031,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	if (nvme_init_ns_head(ns, nsid, id))
 		goto out_free_id;
 	nvme_setup_streams_ns(ctrl, ns);
-	
-#ifdef CONFIG_NVME_MULTIPATH
-	/*
-	 * If multipathing is enabled we need to always use the subsystem
-	 * instance number for numbering our devices to avoid conflicts
-	 * between subsystems that have multiple controllers and thus use
-	 * the multipath-aware subsystem node and those that have a single
-	 * controller and use the controller node directly.
-	 */
-	if (ns->head->disk) {
-		sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
-				ctrl->cntlid, ns->head->instance);
-		flags = GENHD_FL_HIDDEN;
-	} else {
-		sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
-				ns->head->instance);
-	}
-#else
-	/*
-	 * But without the multipath code enabled, multiple controller per
-	 * subsystems are visible as devices and thus we cannot use the
-	 * subsystem instance.
-	 */
-	sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
-#endif
+	nvme_set_disk_name(disk_name, ns, ctrl, &flags);
 
 	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
 		if (nvme_nvm_register(ns, disk_name, node)) {
@@ -3187,6 +3197,42 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
 	nvme_remove_invalid_namespaces(ctrl, nn);
 }
 
+static bool nvme_scan_changed_ns_log(struct nvme_ctrl *ctrl)
+{
+	size_t log_size = NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32);
+	__le32 *log;
+	int error, i;
+	bool ret = false;
+
+	log = kzalloc(log_size, GFP_KERNEL);
+	if (!log)
+		return false;
+
+	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
+	if (error) {
+		dev_warn(ctrl->device,
+			"reading changed ns log failed: %d\n", error);
+		goto out_free_log;
+	}
+
+	if (log[0] == cpu_to_le32(0xffffffff))
+		goto out_free_log;
+
+	for (i = 0; i < NVME_MAX_CHANGED_NAMESPACES; i++) {
+		u32 nsid = le32_to_cpu(log[i]);
+
+		if (nsid == 0)
+			break;
+		dev_info(ctrl->device, "rescanning namespace %d.\n", nsid);
+		nvme_validate_ns(ctrl, nsid);
+	}
+	ret = true;
+
+out_free_log:
+	kfree(log);
+	return ret;
+}
+
 static void nvme_scan_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl =
@@ -3199,6 +3245,12 @@ static void nvme_scan_work(struct work_struct *work)
 
 	WARN_ON_ONCE(!ctrl->tagset);
 
+	if (test_and_clear_bit(EVENT_NS_CHANGED, &ctrl->events)) {
+		if (nvme_scan_changed_ns_log(ctrl))
+			goto out_sort_namespaces;
+		dev_info(ctrl->device, "rescanning namespaces.\n");
+	}
+
 	if (nvme_identify_ctrl(ctrl, &id))
 		return;
 
@@ -3206,25 +3258,16 @@ static void nvme_scan_work(struct work_struct *work)
 	if (ctrl->vs >= NVME_VS(1, 1, 0) &&
 	    !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
 		if (!nvme_scan_ns_list(ctrl, nn))
-			goto done;
+			goto out_free_id;
 	}
 	nvme_scan_ns_sequential(ctrl, nn);
- done:
+out_free_id:
+	kfree(id);
+out_sort_namespaces:
 	down_write(&ctrl->namespaces_rwsem);
 	list_sort(NULL, &ctrl->namespaces, ns_cmp);
 	up_write(&ctrl->namespaces_rwsem);
-	kfree(id);
-}
-
-void nvme_queue_scan(struct nvme_ctrl *ctrl)
-{
-	/*
-	 * Only new queue scan work when admin and IO queues are both alive
-	 */
-	if (ctrl->state == NVME_CTRL_LIVE)
-		queue_work(nvme_wq, &ctrl->scan_work);
 }
-EXPORT_SYMBOL_GPL(nvme_queue_scan);
 
 /*
  * This function iterates the namespace list unlocked to allow recovery from
@@ -3339,8 +3382,23 @@ static void nvme_fw_act_work(struct work_struct *work)
 	nvme_get_fw_slot_info(ctrl);
 }
 
+static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
+{
+	switch ((result & 0xff00) >> 8) {
+	case NVME_AER_NOTICE_NS_CHANGED:
+		set_bit(EVENT_NS_CHANGED, &ctrl->events);
+		nvme_queue_scan(ctrl);
+		break;
+	case NVME_AER_NOTICE_FW_ACT_STARTING:
+		queue_work(nvme_wq, &ctrl->fw_act_work);
+		break;
+	default:
+		dev_warn(ctrl->device, "async event result %08x\n", result);
+	}
+}
+
 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
-		union nvme_result *res)
+		volatile union nvme_result *res)
 {
 	u32 result = le32_to_cpu(res->u32);
 
@@ -3348,6 +3406,9 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		return;
 
 	switch (result & 0x7) {
+	case NVME_AER_NOTICE:
+		nvme_handle_aen_notice(ctrl, result);
+		break;
 	case NVME_AER_ERROR:
 	case NVME_AER_SMART:
 	case NVME_AER_CSS:
@@ -3357,18 +3418,6 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 	default:
 		break;
 	}
-
-	switch (result & 0xff07) {
-	case NVME_AER_NOTICE_NS_CHANGED:
-		dev_info(ctrl->device, "rescanning\n");
-		nvme_queue_scan(ctrl);
-		break;
-	case NVME_AER_NOTICE_FW_ACT_STARTING:
-		queue_work(nvme_wq, &ctrl->fw_act_work);
-		break;
-	default:
-		dev_warn(ctrl->device, "async event result %08x\n", result);
-	}
 	queue_work(nvme_wq, &ctrl->async_event_work);
 }
 EXPORT_SYMBOL_GPL(nvme_complete_async_event);
@@ -3391,6 +3440,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 
 	if (ctrl->queue_count > 1) {
 		nvme_queue_scan(ctrl);
+		nvme_enable_aen(ctrl);
 		queue_work(nvme_wq, &ctrl->async_event_work);
 		nvme_start_queues(ctrl);
 	}
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 124c458806df..5f5f7067c41d 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -57,7 +57,7 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn)
 		goto out_unlock;
 
 	kref_init(&host->ref);
-	memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
+	strlcpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
 
 	list_add_tail(&host->list, &nvmf_hosts);
 out_unlock:
@@ -545,71 +545,54 @@ blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		return BLK_STS_OK;
 
 	switch (ctrl->state) {
-	case NVME_CTRL_DELETING:
-		goto reject_io;
-
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_CONNECTING:
+	case NVME_CTRL_DELETING:
+		/*
+		 * This is the case of starting a new or deleting an association
+		 * but connectivity was lost before it was fully created or torn
+		 * down. We need to error the commands used to initialize the
+		 * controller so the reconnect can go into a retry attempt.  The
+		 * commands should all be marked REQ_FAILFAST_DRIVER, which will
+		 * hit the reject path below. Anything else will be queued while
+		 * the state settles.
+		 */
 		if (!is_connected)
-			/*
-			 * This is the case of starting a new
-			 * association but connectivity was lost
-			 * before it was fully created. We need to
-			 * error the commands used to initialize the
-			 * controller so the reconnect can go into a
-			 * retry attempt. The commands should all be
-			 * marked REQ_FAILFAST_DRIVER, which will hit
-			 * the reject path below. Anything else will
-			 * be queued while the state settles.
-			 */
-			goto reject_or_queue_io;
-
-		if ((queue_live &&
-		     !(nvme_req(rq)->flags & NVME_REQ_USERCMD)) ||
-		    (!queue_live && blk_rq_is_passthrough(rq) &&
-		     cmd->common.opcode == nvme_fabrics_command &&
-		     cmd->fabrics.fctype == nvme_fabrics_type_connect))
-			/*
-			 * If queue is live, allow only commands that
-			 * are internally generated pass through. These
-			 * are commands on the admin queue to initialize
-			 * the controller. This will reject any ioctl
-			 * admin cmds received while initializing.
-			 *
-			 * If the queue is not live, allow only a
-			 * connect command. This will reject any ioctl
-			 * admin cmd as well as initialization commands
-			 * if the controller reverted the queue to non-live.
-			 */
+			break;
+
+		/*
+		 * If queue is live, allow only commands that are internally
+		 * generated pass through.  These are commands on the admin
+		 * queue to initialize the controller. This will reject any
+		 * ioctl admin cmds received while initializing.
+		 */
+		if (queue_live && !(nvme_req(rq)->flags & NVME_REQ_USERCMD))
 			return BLK_STS_OK;
 
 		/*
-		 * fall-thru to the reject_or_queue_io clause
+		 * If the queue is not live, allow only a connect command.  This
+		 * will reject any ioctl admin cmd as well as initialization
+		 * commands if the controller reverted the queue to non-live.
 		 */
+		if (!queue_live && blk_rq_is_passthrough(rq) &&
+		     cmd->common.opcode == nvme_fabrics_command &&
+		     cmd->fabrics.fctype == nvme_fabrics_type_connect)
+			return BLK_STS_OK;
 		break;
-
-	/* these cases fall-thru
-	 * case NVME_CTRL_LIVE:
-	 * case NVME_CTRL_RESETTING:
-	 */
 	default:
 		break;
 	}
 
-reject_or_queue_io:
 	/*
-	 * Any other new io is something we're not in a state to send
-	 * to the device. Default action is to busy it and retry it
-	 * after the controller state is recovered. However, anything
-	 * marked for failfast or nvme multipath is immediately failed.
-	 * Note: commands used to initialize the controller will be
-	 *  marked for failfast.
+	 * Any other new io is something we're not in a state to send to the
+	 * device.  Default action is to busy it and retry it after the
+	 * controller state is recovered. However, anything marked for failfast
+	 * or nvme multipath is immediately failed.  Note: commands used to
+	 * initialize the controller will be marked for failfast.
 	 * Note: nvme cli/ioctl commands are marked for failfast.
 	 */
 	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
-
-reject_io:
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
 	return BLK_STS_IOERR;
 }
@@ -668,6 +651,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -ENOMEM;
 				goto out;
 			}
+			kfree(opts->transport);
 			opts->transport = p;
 			break;
 		case NVMF_OPT_NQN:
@@ -676,6 +660,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -ENOMEM;
 				goto out;
 			}
+			kfree(opts->subsysnqn);
 			opts->subsysnqn = p;
 			nqnlen = strlen(opts->subsysnqn);
 			if (nqnlen >= NVMF_NQN_SIZE) {
@@ -687,10 +672,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			opts->discovery_nqn =
 				!(strcmp(opts->subsysnqn,
 					 NVME_DISC_SUBSYS_NAME));
-			if (opts->discovery_nqn) {
-				opts->kato = 0;
-				opts->nr_io_queues = 0;
-			}
 			break;
 		case NVMF_OPT_TRADDR:
 			p = match_strdup(args);
@@ -698,6 +679,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -ENOMEM;
 				goto out;
 			}
+			kfree(opts->traddr);
 			opts->traddr = p;
 			break;
 		case NVMF_OPT_TRSVCID:
@@ -706,6 +688,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -ENOMEM;
 				goto out;
 			}
+			kfree(opts->trsvcid);
 			opts->trsvcid = p;
 			break;
 		case NVMF_OPT_QUEUE_SIZE:
@@ -792,6 +775,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -EINVAL;
 				goto out;
 			}
+			nvmf_host_put(opts->host);
 			opts->host = nvmf_host_add(p);
 			kfree(p);
 			if (!opts->host) {
@@ -817,6 +801,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -ENOMEM;
 				goto out;
 			}
+			kfree(opts->host_traddr);
 			opts->host_traddr = p;
 			break;
 		case NVMF_OPT_HOST_ID:
@@ -845,6 +830,11 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 		}
 	}
 
+	if (opts->discovery_nqn) {
+		opts->kato = 0;
+		opts->nr_io_queues = 0;
+		opts->duplicate_connect = true;
+	}
 	if (ctrl_loss_tmo < 0)
 		opts->max_reconnects = -1;
 	else
@@ -977,16 +967,6 @@ nvmf_create_ctrl(struct device *dev, const char *buf, size_t count)
 		goto out_module_put;
 	}
 
-	if (strcmp(ctrl->subsys->subnqn, opts->subsysnqn)) {
-		dev_warn(ctrl->device,
-			"controller returned incorrect NQN: \"%s\".\n",
-			ctrl->subsys->subnqn);
-		module_put(ops->module);
-		up_read(&nvmf_transports_rwsem);
-		nvme_delete_ctrl_sync(ctrl);
-		return ERR_PTR(-EINVAL);
-	}
-
 	module_put(ops->module);
 	up_read(&nvmf_transports_rwsem);
 	return ctrl;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index ef46c915b7b5..0cf0460a5c92 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -139,7 +139,9 @@ static inline bool
 nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
 			struct nvmf_ctrl_options *opts)
 {
-	if (strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
+	if (ctrl->state == NVME_CTRL_DELETING ||
+	    ctrl->state == NVME_CTRL_DEAD ||
+	    strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
 	    strcmp(opts->host->nqn, ctrl->opts->host->nqn) ||
 	    memcmp(&opts->host->id, &ctrl->opts->host->id, sizeof(uuid_t)))
 		return false;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 6cb26bcf6ec0..0bad65803271 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1686,16 +1686,6 @@ done:
 		goto check_error;
 	}
 
-	/*
-	 * Force failures of commands if we're killing the controller
-	 * or have an error on a command used to create an new association
-	 */
-	if (status &&
-	    (blk_queue_dying(rq->q) ||
-	     ctrl->ctrl.state == NVME_CTRL_NEW ||
-	     ctrl->ctrl.state == NVME_CTRL_CONNECTING))
-		status |= cpu_to_le16(NVME_SC_DNR << 1);
-
 	__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
 	nvme_end_request(rq, status, result);
 
@@ -2403,9 +2393,6 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
 
-	if (!blk_mq_request_started(req))
-		return;
-
 	__nvme_fc_abort_op(ctrl, op);
 }
 
@@ -3284,6 +3271,8 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
 	}
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
+	pr_warn("%s: %s - %s combination not found\n",
+		__func__, opts->traddr, opts->host_traddr);
 	return ERR_PTR(-ENOENT);
 }
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 956e0b8e9c4d..d7b664ae5923 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -15,10 +15,32 @@
 #include "nvme.h"
 
 static bool multipath = true;
-module_param(multipath, bool, 0644);
+module_param(multipath, bool, 0444);
 MODULE_PARM_DESC(multipath,
 	"turn on native support for multiple controllers per subsystem");
 
+/*
+ * If multipathing is enabled we need to always use the subsystem instance
+ * number for numbering our devices to avoid conflicts between subsystems that
+ * have multiple controllers and thus use the multipath-aware subsystem node
+ * and those that have a single controller and use the controller node
+ * directly.
+ */
+void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+			struct nvme_ctrl *ctrl, int *flags)
+{
+	if (!multipath) {
+		sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
+	} else if (ns->head->disk) {
+		sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
+				ctrl->cntlid, ns->head->instance);
+		*flags = GENHD_FL_HIDDEN;
+	} else {
+		sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
+				ns->head->instance);
+	}
+}
+
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 061fecfd44f5..de24fe77c80b 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -22,6 +22,7 @@
 #include <linux/lightnvm.h>
 #include <linux/sed-opal.h>
 #include <linux/fault-inject.h>
+#include <linux/rcupdate.h>
 
 extern unsigned int nvme_io_timeout;
 #define NVME_IO_TIMEOUT	(nvme_io_timeout * HZ)
@@ -84,6 +85,11 @@ enum nvme_quirks {
 	 * Supports the LighNVM command set if indicated in vs[1].
 	 */
 	NVME_QUIRK_LIGHTNVM			= (1 << 6),
+
+	/*
+	 * Set MEDIUM priority on SQ creation
+	 */
+	NVME_QUIRK_MEDIUM_PRIO_SQ		= (1 << 7),
 };
 
 /*
@@ -175,6 +181,7 @@ struct nvme_ctrl {
 	u16 kas;
 	u8 npss;
 	u8 apsta;
+	u32 oaes;
 	u32 aen_result;
 	unsigned int shutdown_timeout;
 	unsigned int kato;
@@ -187,6 +194,8 @@ struct nvme_ctrl {
 	struct delayed_work ka_work;
 	struct nvme_command ka_cmd;
 	struct work_struct fw_act_work;
+#define EVENT_NS_CHANGED		(1 << 0)
+	unsigned long events;
 
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
@@ -393,14 +402,13 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl);
 void nvme_put_ctrl(struct nvme_ctrl *ctrl);
 int nvme_init_identify(struct nvme_ctrl *ctrl);
 
-void nvme_queue_scan(struct nvme_ctrl *ctrl);
 void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
 
 int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 		bool send);
 
 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
-		union nvme_result *res);
+		volatile union nvme_result *res);
 
 void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
@@ -436,6 +444,8 @@ extern const struct attribute_group nvme_ns_id_attr_group;
 extern const struct block_device_operations nvme_ns_head_ops;
 
 #ifdef CONFIG_NVME_MULTIPATH
+void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+			struct nvme_ctrl *ctrl, int *flags);
 void nvme_failover_req(struct request *req);
 bool nvme_req_needs_failover(struct request *req, blk_status_t error);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
@@ -447,7 +457,7 @@ static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
 	struct nvme_ns_head *head = ns->head;
 
-	if (head && ns == srcu_dereference(head->current_path, &head->srcu))
+	if (head && ns == rcu_access_pointer(head->current_path))
 		rcu_assign_pointer(head->current_path, NULL);
 }
 struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
@@ -461,6 +471,16 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 }
 
 #else
+/*
+ * Without the multipath code enabled, multiple controller per subsystems are
+ * visible as devices and thus we cannot use the subsystem instance.
+ */
+static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+				      struct nvme_ctrl *ctrl, int *flags)
+{
+	sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
+}
+
 static inline void nvme_failover_req(struct request *req)
 {
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index fbc71fac6f1e..e526437bacbf 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/aer.h>
+#include <linux/async.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-mq-pci.h>
@@ -68,7 +69,6 @@ MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
 struct nvme_dev;
 struct nvme_queue;
 
-static void nvme_process_cq(struct nvme_queue *nvmeq);
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
 
 /*
@@ -147,9 +147,10 @@ static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
 struct nvme_queue {
 	struct device *q_dmadev;
 	struct nvme_dev *dev;
-	spinlock_t q_lock;
+	spinlock_t sq_lock;
 	struct nvme_command *sq_cmds;
 	struct nvme_command __iomem *sq_cmds_io;
+	spinlock_t cq_lock ____cacheline_aligned_in_smp;
 	volatile struct nvme_completion *cqes;
 	struct blk_mq_tags **tags;
 	dma_addr_t sq_dma_addr;
@@ -159,9 +160,9 @@ struct nvme_queue {
 	s16 cq_vector;
 	u16 sq_tail;
 	u16 cq_head;
+	u16 last_cq_head;
 	u16 qid;
 	u8 cq_phase;
-	u8 cqe_seen;
 	u32 *dbbuf_sq_db;
 	u32 *dbbuf_cq_db;
 	u32 *dbbuf_sq_ei;
@@ -420,28 +421,25 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 }
 
 /**
- * __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
+ * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
  * @nvmeq: The queue to use
  * @cmd: The command to send
- *
- * Safe to use from interrupt context
  */
-static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
-						struct nvme_command *cmd)
+static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
 {
-	u16 tail = nvmeq->sq_tail;
-
+	spin_lock(&nvmeq->sq_lock);
 	if (nvmeq->sq_cmds_io)
-		memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd, sizeof(*cmd));
+		memcpy_toio(&nvmeq->sq_cmds_io[nvmeq->sq_tail], cmd,
+				sizeof(*cmd));
 	else
-		memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+		memcpy(&nvmeq->sq_cmds[nvmeq->sq_tail], cmd, sizeof(*cmd));
 
-	if (++tail == nvmeq->q_depth)
-		tail = 0;
-	if (nvme_dbbuf_update_and_check_event(tail, nvmeq->dbbuf_sq_db,
-					      nvmeq->dbbuf_sq_ei))
-		writel(tail, nvmeq->q_db);
-	nvmeq->sq_tail = tail;
+	if (++nvmeq->sq_tail == nvmeq->q_depth)
+		nvmeq->sq_tail = 0;
+	if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
+			nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
+		writel(nvmeq->sq_tail, nvmeq->q_db);
+	spin_unlock(&nvmeq->sq_lock);
 }
 
 static void **nvme_pci_iod_list(struct request *req)
@@ -872,6 +870,13 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_command cmnd;
 	blk_status_t ret;
 
+	/*
+	 * We should not need to do this, but we're still using this to
+	 * ensure we can drain requests on a dying queue.
+	 */
+	if (unlikely(nvmeq->cq_vector < 0))
+		return BLK_STS_IOERR;
+
 	ret = nvme_setup_cmd(ns, req, &cmnd);
 	if (ret)
 		return ret;
@@ -887,16 +892,7 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	}
 
 	blk_mq_start_request(req);
-
-	spin_lock_irq(&nvmeq->q_lock);
-	if (unlikely(nvmeq->cq_vector < 0)) {
-		ret = BLK_STS_IOERR;
-		spin_unlock_irq(&nvmeq->q_lock);
-		goto out_cleanup_iod;
-	}
-	__nvme_submit_cmd(nvmeq, &cmnd);
-	nvme_process_cq(nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
+	nvme_submit_cmd(nvmeq, &cmnd);
 	return BLK_STS_OK;
 out_cleanup_iod:
 	nvme_free_iod(dev, req);
@@ -914,10 +910,10 @@ static void nvme_pci_complete_rq(struct request *req)
 }
 
 /* We read the CQE phase first to check if the rest of the entry is valid */
-static inline bool nvme_cqe_valid(struct nvme_queue *nvmeq, u16 head,
-		u16 phase)
+static inline bool nvme_cqe_pending(struct nvme_queue *nvmeq)
 {
-	return (le16_to_cpu(nvmeq->cqes[head].status) & 1) == phase;
+	return (le16_to_cpu(nvmeq->cqes[nvmeq->cq_head].status) & 1) ==
+			nvmeq->cq_phase;
 }
 
 static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
@@ -931,9 +927,9 @@ static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
 	}
 }
 
-static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
-		struct nvme_completion *cqe)
+static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 {
+	volatile struct nvme_completion *cqe = &nvmeq->cqes[idx];
 	struct request *req;
 
 	if (unlikely(cqe->command_id >= nvmeq->q_depth)) {
@@ -956,83 +952,87 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
 		return;
 	}
 
-	nvmeq->cqe_seen = 1;
 	req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id);
 	nvme_end_request(req, cqe->status, cqe->result);
 }
 
-static inline bool nvme_read_cqe(struct nvme_queue *nvmeq,
-		struct nvme_completion *cqe)
+static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end)
 {
-	if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) {
-		*cqe = nvmeq->cqes[nvmeq->cq_head];
+	while (start != end) {
+		nvme_handle_cqe(nvmeq, start);
+		if (++start == nvmeq->q_depth)
+			start = 0;
+	}
+}
 
-		if (++nvmeq->cq_head == nvmeq->q_depth) {
-			nvmeq->cq_head = 0;
-			nvmeq->cq_phase = !nvmeq->cq_phase;
-		}
-		return true;
+static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
+{
+	if (++nvmeq->cq_head == nvmeq->q_depth) {
+		nvmeq->cq_head = 0;
+		nvmeq->cq_phase = !nvmeq->cq_phase;
 	}
-	return false;
 }
 
-static void nvme_process_cq(struct nvme_queue *nvmeq)
+static inline bool nvme_process_cq(struct nvme_queue *nvmeq, u16 *start,
+		u16 *end, int tag)
 {
-	struct nvme_completion cqe;
-	int consumed = 0;
+	bool found = false;
 
-	while (nvme_read_cqe(nvmeq, &cqe)) {
-		nvme_handle_cqe(nvmeq, &cqe);
-		consumed++;
+	*start = nvmeq->cq_head;
+	while (!found && nvme_cqe_pending(nvmeq)) {
+		if (nvmeq->cqes[nvmeq->cq_head].command_id == tag)
+			found = true;
+		nvme_update_cq_head(nvmeq);
 	}
+	*end = nvmeq->cq_head;
 
-	if (consumed)
+	if (*start != *end)
 		nvme_ring_cq_doorbell(nvmeq);
+	return found;
 }
 
 static irqreturn_t nvme_irq(int irq, void *data)
 {
-	irqreturn_t result;
 	struct nvme_queue *nvmeq = data;
-	spin_lock(&nvmeq->q_lock);
-	nvme_process_cq(nvmeq);
-	result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
-	nvmeq->cqe_seen = 0;
-	spin_unlock(&nvmeq->q_lock);
-	return result;
+	irqreturn_t ret = IRQ_NONE;
+	u16 start, end;
+
+	spin_lock(&nvmeq->cq_lock);
+	if (nvmeq->cq_head != nvmeq->last_cq_head)
+		ret = IRQ_HANDLED;
+	nvme_process_cq(nvmeq, &start, &end, -1);
+	nvmeq->last_cq_head = nvmeq->cq_head;
+	spin_unlock(&nvmeq->cq_lock);
+
+	if (start != end) {
+		nvme_complete_cqes(nvmeq, start, end);
+		return IRQ_HANDLED;
+	}
+
+	return ret;
 }
 
 static irqreturn_t nvme_irq_check(int irq, void *data)
 {
 	struct nvme_queue *nvmeq = data;
-	if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase))
+	if (nvme_cqe_pending(nvmeq))
 		return IRQ_WAKE_THREAD;
 	return IRQ_NONE;
 }
 
 static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag)
 {
-	struct nvme_completion cqe;
-	int found = 0, consumed = 0;
+	u16 start, end;
+	bool found;
 
-	if (!nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase))
+	if (!nvme_cqe_pending(nvmeq))
 		return 0;
 
-	spin_lock_irq(&nvmeq->q_lock);
-	while (nvme_read_cqe(nvmeq, &cqe)) {
-		nvme_handle_cqe(nvmeq, &cqe);
-		consumed++;
-
-		if (tag == cqe.command_id) {
-			found = 1;
-			break;
-		}
-       }
-
-	if (consumed)
-		nvme_ring_cq_doorbell(nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->cq_lock);
+	found = nvme_process_cq(nvmeq, &start, &end, tag);
+	spin_unlock_irq(&nvmeq->cq_lock);
 
+	nvme_complete_cqes(nvmeq, start, end);
 	return found;
 }
 
@@ -1052,10 +1052,7 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = nvme_admin_async_event;
 	c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
-
-	spin_lock_irq(&nvmeq->q_lock);
-	__nvme_submit_cmd(nvmeq, &c);
-	spin_unlock_irq(&nvmeq->q_lock);
+	nvme_submit_cmd(nvmeq, &c);
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
@@ -1070,7 +1067,7 @@ static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
 }
 
 static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
-						struct nvme_queue *nvmeq)
+		struct nvme_queue *nvmeq, s16 vector)
 {
 	struct nvme_command c;
 	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
@@ -1085,7 +1082,7 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 	c.create_cq.cqid = cpu_to_le16(qid);
 	c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
 	c.create_cq.cq_flags = cpu_to_le16(flags);
-	c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
+	c.create_cq.irq_vector = cpu_to_le16(vector);
 
 	return nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0);
 }
@@ -1093,10 +1090,19 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
 						struct nvme_queue *nvmeq)
 {
+	struct nvme_ctrl *ctrl = &dev->ctrl;
 	struct nvme_command c;
 	int flags = NVME_QUEUE_PHYS_CONTIG;
 
 	/*
+	 * Some drives have a bug that auto-enables WRRU if MEDIUM isn't
+	 * set. Since URGENT priority is zeroes, it makes all queues
+	 * URGENT.
+	 */
+	if (ctrl->quirks & NVME_QUIRK_MEDIUM_PRIO_SQ)
+		flags |= NVME_SQ_PRIO_MEDIUM;
+
+	/*
 	 * Note: we (ab)use the fact that the prp fields survive if no data
 	 * is attached to the request.
 	 */
@@ -1199,7 +1205,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		nvme_warn_reset(dev, csts);
 		nvme_dev_disable(dev, false);
 		nvme_reset_ctrl(&dev->ctrl);
-		return BLK_EH_HANDLED;
+		return BLK_EH_DONE;
 	}
 
 	/*
@@ -1209,24 +1215,24 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, completion polled\n",
 			 req->tag, nvmeq->qid);
-		return BLK_EH_HANDLED;
+		return BLK_EH_DONE;
 	}
 
 	/*
 	 * Shutdown immediately if controller times out while starting. The
 	 * reset work will see the pci device disabled when it gets the forced
 	 * cancellation error. All outstanding requests are completed on
-	 * shutdown, so we return BLK_EH_HANDLED.
+	 * shutdown, so we return BLK_EH_DONE.
 	 */
 	switch (dev->ctrl.state) {
 	case NVME_CTRL_CONNECTING:
 	case NVME_CTRL_RESETTING:
-		dev_warn(dev->ctrl.device,
+		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_dev_disable(dev, false);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
-		return BLK_EH_HANDLED;
+		return BLK_EH_DONE;
 	default:
 		break;
 	}
@@ -1243,12 +1249,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		nvme_dev_disable(dev, false);
 		nvme_reset_ctrl(&dev->ctrl);
 
-		/*
-		 * Mark the request as handled, since the inline shutdown
-		 * forces all outstanding requests to complete.
-		 */
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
-		return BLK_EH_HANDLED;
+		return BLK_EH_DONE;
 	}
 
 	if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
@@ -1312,15 +1314,21 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 {
 	int vector;
 
-	spin_lock_irq(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->cq_lock);
 	if (nvmeq->cq_vector == -1) {
-		spin_unlock_irq(&nvmeq->q_lock);
+		spin_unlock_irq(&nvmeq->cq_lock);
 		return 1;
 	}
 	vector = nvmeq->cq_vector;
 	nvmeq->dev->online_queues--;
 	nvmeq->cq_vector = -1;
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_unlock_irq(&nvmeq->cq_lock);
+
+	/*
+	 * Ensure that nvme_queue_rq() sees it ->cq_vector == -1 without
+	 * having to grab the lock.
+	 */
+	mb();
 
 	if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
 		blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q);
@@ -1333,15 +1341,18 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
 {
 	struct nvme_queue *nvmeq = &dev->queues[0];
+	u16 start, end;
 
 	if (shutdown)
 		nvme_shutdown_ctrl(&dev->ctrl);
 	else
 		nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);
 
-	spin_lock_irq(&nvmeq->q_lock);
-	nvme_process_cq(nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->cq_lock);
+	nvme_process_cq(nvmeq, &start, &end, -1);
+	spin_unlock_irq(&nvmeq->cq_lock);
+
+	nvme_complete_cqes(nvmeq, start, end);
 }
 
 static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
@@ -1399,7 +1410,8 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
 
 	nvmeq->q_dmadev = dev->dev;
 	nvmeq->dev = dev;
-	spin_lock_init(&nvmeq->q_lock);
+	spin_lock_init(&nvmeq->sq_lock);
+	spin_lock_init(&nvmeq->cq_lock);
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
@@ -1435,7 +1447,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 {
 	struct nvme_dev *dev = nvmeq->dev;
 
-	spin_lock_irq(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->cq_lock);
 	nvmeq->sq_tail = 0;
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
@@ -1443,13 +1455,14 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
 	nvme_dbbuf_init(dev, nvmeq, qid);
 	dev->online_queues++;
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_unlock_irq(&nvmeq->cq_lock);
 }
 
 static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 {
 	struct nvme_dev *dev = nvmeq->dev;
 	int result;
+	s16 vector;
 
 	if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
 		unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
@@ -1462,15 +1475,21 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	 * A queue's vector matches the queue identifier unless the controller
 	 * has only one vector available.
 	 */
-	nvmeq->cq_vector = dev->num_vecs == 1 ? 0 : qid;
-	result = adapter_alloc_cq(dev, qid, nvmeq);
+	vector = dev->num_vecs == 1 ? 0 : qid;
+	result = adapter_alloc_cq(dev, qid, nvmeq, vector);
 	if (result < 0)
-		goto release_vector;
+		goto out;
 
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
 		goto release_cq;
 
+	/*
+	 * Set cq_vector after alloc cq/sq, otherwise nvme_suspend_queue will
+	 * invoke free_irq for it and cause a 'Trying to free already-free IRQ
+	 * xxx' warning if the create CQ/SQ command times out.
+	 */
+	nvmeq->cq_vector = vector;
 	nvme_init_queue(nvmeq, qid);
 	result = queue_request_irq(nvmeq);
 	if (result < 0)
@@ -1478,13 +1497,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 
 	return result;
 
- release_sq:
+release_sq:
+	nvmeq->cq_vector = -1;
 	dev->online_queues--;
 	adapter_delete_sq(dev, qid);
- release_cq:
+release_cq:
 	adapter_delete_cq(dev, qid);
- release_vector:
-	nvmeq->cq_vector = -1;
+out:
 	return result;
 }
 
@@ -1988,19 +2007,22 @@ static void nvme_del_queue_end(struct request *req, blk_status_t error)
 static void nvme_del_cq_end(struct request *req, blk_status_t error)
 {
 	struct nvme_queue *nvmeq = req->end_io_data;
+	u16 start, end;
 
 	if (!error) {
 		unsigned long flags;
 
 		/*
-		 * We might be called with the AQ q_lock held
-		 * and the I/O queue q_lock should always
+		 * We might be called with the AQ cq_lock held
+		 * and the I/O queue cq_lock should always
 		 * nest inside the AQ one.
 		 */
-		spin_lock_irqsave_nested(&nvmeq->q_lock, flags,
+		spin_lock_irqsave_nested(&nvmeq->cq_lock, flags,
 					SINGLE_DEPTH_NESTING);
-		nvme_process_cq(nvmeq);
-		spin_unlock_irqrestore(&nvmeq->q_lock, flags);
+		nvme_process_cq(nvmeq, &start, &end, -1);
+		spin_unlock_irqrestore(&nvmeq->cq_lock, flags);
+
+		nvme_complete_cqes(nvmeq, start, end);
 	}
 
 	nvme_del_queue_end(req, error);
@@ -2488,6 +2510,15 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 	return 0;
 }
 
+static void nvme_async_probe(void *data, async_cookie_t cookie)
+{
+	struct nvme_dev *dev = data;
+
+	nvme_reset_ctrl_sync(&dev->ctrl);
+	flush_work(&dev->ctrl.scan_work);
+	nvme_put_ctrl(&dev->ctrl);
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int node, result = -ENOMEM;
@@ -2532,7 +2563,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
-	nvme_reset_ctrl(&dev->ctrl);
+	nvme_get_ctrl(&dev->ctrl);
+	async_schedule(nvme_async_probe, dev);
 
 	return 0;
 
@@ -2676,6 +2708,9 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
 static void nvme_error_resume(struct pci_dev *pdev)
 {
+	struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+	flush_work(&dev->ctrl.reset_work);
 	pci_cleanup_aer_uncorrect_error_status(pdev);
 }
 
@@ -2701,9 +2736,12 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
-		.driver_data = NVME_QUIRK_NO_DEEPEST_PS },
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_MEDIUM_PRIO_SQ },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
+	{ PCI_DEVICE(0x1bb1, 0x0100),   /* Seagate Nytro Flash Storage */
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x1c58, 0x0023),	/* WDC SN200 adapter */
@@ -2718,6 +2756,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x1d1d, 0x2807),	/* CNEX WL */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
+	{ PCI_DEVICE(0x1d1d, 0x2601),	/* CNEX Granby */
+		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 1eb4438a8763..7b3f08410430 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -778,7 +778,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (error) {
 		dev_err(ctrl->ctrl.device,
 			"prop_get NVME_REG_CAP failed\n");
-		goto out_cleanup_queue;
+		goto out_stop_queue;
 	}
 
 	ctrl->ctrl.sqsize =
@@ -786,23 +786,25 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 
 	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
 	if (error)
-		goto out_cleanup_queue;
+		goto out_stop_queue;
 
 	ctrl->ctrl.max_hw_sectors =
 		(ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
 
 	error = nvme_init_identify(&ctrl->ctrl);
 	if (error)
-		goto out_cleanup_queue;
+		goto out_stop_queue;
 
 	error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
 			&ctrl->async_event_sqe, sizeof(struct nvme_command),
 			DMA_TO_DEVICE);
 	if (error)
-		goto out_cleanup_queue;
+		goto out_stop_queue;
 
 	return 0;
 
+out_stop_queue:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 out_cleanup_queue:
 	if (new)
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
@@ -1598,7 +1600,7 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	/* fail with DNR on cmd timeout */
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
 
-	return BLK_EH_HANDLED;
+	return BLK_EH_DONE;
 }
 
 static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index ea91fccd1bc0..01390f0e1671 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -148,8 +148,8 @@ TRACE_EVENT(nvme_complete_rq,
 		    __entry->flags = nvme_req(req)->flags;
 		    __entry->status = nvme_req(req)->status;
 	    ),
-	    TP_printk("cmdid=%u, qid=%d, res=%llu, retries=%u, flags=0x%x, status=%u",
-		      __entry->cid, __entry->qid, __entry->result,
+	    TP_printk("qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+		      __entry->qid, __entry->cid, __entry->result,
 		      __entry->retries, __entry->flags, __entry->status)
 
 );
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index 5f4f8b16685f..3c7b61ddb0d1 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -27,7 +27,7 @@ config NVME_TARGET_LOOP
 
 config NVME_TARGET_RDMA
 	tristate "NVMe over Fabrics RDMA target support"
-	depends on INFINIBAND
+	depends on INFINIBAND && INFINIBAND_ADDR_TRANS
 	depends on NVME_TARGET
 	select SGL_ALLOC
 	help
diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile
index 488250189c99..8118c93391c6 100644
--- a/drivers/nvme/target/Makefile
+++ b/drivers/nvme/target/Makefile
@@ -6,8 +6,8 @@ obj-$(CONFIG_NVME_TARGET_RDMA)		+= nvmet-rdma.o
 obj-$(CONFIG_NVME_TARGET_FC)		+= nvmet-fc.o
 obj-$(CONFIG_NVME_TARGET_FCLOOP)	+= nvme-fcloop.o
 
-nvmet-y		+= core.o configfs.o admin-cmd.o io-cmd.o fabrics-cmd.o \
-			discovery.o
+nvmet-y		+= core.o configfs.o admin-cmd.o fabrics-cmd.o \
+			discovery.o io-cmd-file.o io-cmd-bdev.o
 nvme-loop-y	+= loop.o
 nvmet-rdma-y	+= rdma.o
 nvmet-fc-y	+= fc.o
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 5e0e9fcc0d4d..ead8fbe6922e 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -32,6 +32,11 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 	return len;
 }
 
+static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
+{
+	nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
+}
+
 static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 		struct nvme_smart_log *slog)
 {
@@ -45,6 +50,10 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 		return NVME_SC_INVALID_NS;
 	}
 
+	/* we don't have the right data for file backed ns */
+	if (!ns->bdev)
+		goto out;
+
 	host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
 	data_units_read = part_stat_read(ns->bdev->bd_part, sectors[READ]);
 	host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]);
@@ -54,6 +63,7 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 	put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
 	put_unaligned_le64(host_writes, &slog->host_writes[0]);
 	put_unaligned_le64(data_units_written, &slog->data_units_written[0]);
+out:
 	nvmet_put_namespace(ns);
 
 	return NVME_SC_SUCCESS;
@@ -71,6 +81,9 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+		/* we don't have the right data for file backed ns */
+		if (!ns->bdev)
+			continue;
 		host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]);
 		data_units_read +=
 			part_stat_read(ns->bdev->bd_part, sectors[READ]);
@@ -89,74 +102,50 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 	return NVME_SC_SUCCESS;
 }
 
-static u16 nvmet_get_smart_log(struct nvmet_req *req,
-		struct nvme_smart_log *slog)
+static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 {
-	u16 status;
+	struct nvme_smart_log *log;
+	u16 status = NVME_SC_INTERNAL;
+
+	if (req->data_len != sizeof(*log))
+		goto out;
+
+	log = kzalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		goto out;
 
-	WARN_ON(req == NULL || slog == NULL);
 	if (req->cmd->get_log_page.nsid == cpu_to_le32(NVME_NSID_ALL))
-		status = nvmet_get_smart_log_all(req, slog);
+		status = nvmet_get_smart_log_all(req, log);
 	else
-		status = nvmet_get_smart_log_nsid(req, slog);
-	return status;
+		status = nvmet_get_smart_log_nsid(req, log);
+	if (status)
+		goto out;
+
+	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+out:
+	nvmet_req_complete(req, status);
 }
 
-static void nvmet_execute_get_log_page(struct nvmet_req *req)
+static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 {
-	struct nvme_smart_log *smart_log;
-	size_t data_len = nvmet_get_log_page_len(req->cmd);
-	void *buf;
-	u16 status = 0;
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	u16 status = NVME_SC_INTERNAL;
+	size_t len;
 
-	buf = kzalloc(data_len, GFP_KERNEL);
-	if (!buf) {
-		status = NVME_SC_INTERNAL;
+	if (req->data_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32))
 		goto out;
-	}
 
-	switch (req->cmd->get_log_page.lid) {
-	case NVME_LOG_ERROR:
-		/*
-		 * We currently never set the More bit in the status field,
-		 * so all error log entries are invalid and can be zeroed out.
-		 * This is called a minum viable implementation (TM) of this
-		 * mandatory log page.
-		 */
-		break;
-	case NVME_LOG_SMART:
-		/*
-		 * XXX: fill out actual smart log
-		 *
-		 * We might have a hard time coming up with useful values for
-		 * many of the fields, and even when we have useful data
-		 * available (e.g. units or commands read/written) those aren't
-		 * persistent over power loss.
-		 */
-		if (data_len != sizeof(*smart_log)) {
-			status = NVME_SC_INTERNAL;
-			goto err;
-		}
-		smart_log = buf;
-		status = nvmet_get_smart_log(req, smart_log);
-		if (status)
-			goto err;
-		break;
-	case NVME_LOG_FW_SLOT:
-		/*
-		 * We only support a single firmware slot which always is
-		 * active, so we can zero out the whole firmware slot log and
-		 * still claim to fully implement this mandatory log page.
-		 */
-		break;
-	default:
-		BUG();
-	}
-
-	status = nvmet_copy_to_sgl(req, 0, buf, data_len);
-
-err:
-	kfree(buf);
+	mutex_lock(&ctrl->lock);
+	if (ctrl->nr_changed_ns == U32_MAX)
+		len = sizeof(__le32);
+	else
+		len = ctrl->nr_changed_ns * sizeof(__le32);
+	status = nvmet_copy_to_sgl(req, 0, ctrl->changed_ns_list, len);
+	if (!status)
+		status = nvmet_zero_sgl(req, len, req->data_len - len);
+	ctrl->nr_changed_ns = 0;
+	clear_bit(NVME_AEN_CFG_NS_ATTR, &ctrl->aen_masked);
+	mutex_unlock(&ctrl->lock);
 out:
 	nvmet_req_complete(req, status);
 }
@@ -201,7 +190,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->ver = cpu_to_le32(ctrl->subsys->ver);
 
 	/* XXX: figure out what to do about RTD3R/RTD3 */
-	id->oaes = cpu_to_le32(1 << 8);
+	id->oaes = cpu_to_le32(NVMET_AEN_CFG_OPTIONAL);
 	id->ctratt = cpu_to_le32(1 << 0);
 
 	id->oacs = 0;
@@ -447,6 +436,16 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 		req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
 		nvmet_set_result(req, req->sq->ctrl->kato);
 		break;
+	case NVME_FEAT_ASYNC_EVENT:
+		val32 = le32_to_cpu(req->cmd->common.cdw10[1]);
+		if (val32 & ~NVMET_AEN_CFG_ALL) {
+			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+			break;
+		}
+
+		WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
+		nvmet_set_result(req, val32);
+		break;
 	case NVME_FEAT_HOST_ID:
 		status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 		break;
@@ -485,9 +484,10 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		break;
 	case NVME_FEAT_WRITE_ATOMIC:
 		break;
+#endif
 	case NVME_FEAT_ASYNC_EVENT:
+		nvmet_set_result(req, READ_ONCE(req->sq->ctrl->aen_enabled));
 		break;
-#endif
 	case NVME_FEAT_VOLATILE_WC:
 		nvmet_set_result(req, 1);
 		break;
@@ -548,8 +548,6 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 	struct nvme_command *cmd = req->cmd;
 	u16 ret;
 
-	req->ns = NULL;
-
 	ret = nvmet_check_ctrl_status(req, cmd);
 	if (unlikely(ret))
 		return ret;
@@ -560,9 +558,28 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 
 		switch (cmd->get_log_page.lid) {
 		case NVME_LOG_ERROR:
+			/*
+			 * We currently never set the More bit in the status
+			 * field, so all error log entries are invalid and can
+			 * be zeroed out.  This is called a minum viable
+			 * implementation (TM) of this mandatory log page.
+			 */
+			req->execute = nvmet_execute_get_log_page_noop;
+			return 0;
 		case NVME_LOG_SMART:
+			req->execute = nvmet_execute_get_log_page_smart;
+			return 0;
 		case NVME_LOG_FW_SLOT:
-			req->execute = nvmet_execute_get_log_page;
+			/*
+			 * We only support a single firmware slot which always
+			 * is active, so we can zero out the whole firmware slot
+			 * log and still claim to fully implement this mandatory
+			 * log page.
+			 */
+			req->execute = nvmet_execute_get_log_page_noop;
+			return 0;
+		case NVME_LOG_CHANGED_NS:
+			req->execute = nvmet_execute_get_log_changed_ns;
 			return 0;
 		}
 		break;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index e95424f172fd..a03da764ecae 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -57,6 +57,13 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
 	return 0;
 }
 
+u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
+{
+	if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len)
+		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	return 0;
+}
+
 static unsigned int nvmet_max_nsid(struct nvmet_subsys *subsys)
 {
 	struct nvmet_ns *ns;
@@ -137,6 +144,51 @@ static void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 	schedule_work(&ctrl->async_event_work);
 }
 
+static bool nvmet_aen_disabled(struct nvmet_ctrl *ctrl, u32 aen)
+{
+	if (!(READ_ONCE(ctrl->aen_enabled) & aen))
+		return true;
+	return test_and_set_bit(aen, &ctrl->aen_masked);
+}
+
+static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
+{
+	u32 i;
+
+	mutex_lock(&ctrl->lock);
+	if (ctrl->nr_changed_ns > NVME_MAX_CHANGED_NAMESPACES)
+		goto out_unlock;
+
+	for (i = 0; i < ctrl->nr_changed_ns; i++) {
+		if (ctrl->changed_ns_list[i] == nsid)
+			goto out_unlock;
+	}
+
+	if (ctrl->nr_changed_ns == NVME_MAX_CHANGED_NAMESPACES) {
+		ctrl->changed_ns_list[0] = cpu_to_le32(0xffffffff);
+		ctrl->nr_changed_ns = U32_MAX;
+		goto out_unlock;
+	}
+
+	ctrl->changed_ns_list[ctrl->nr_changed_ns++] = nsid;
+out_unlock:
+	mutex_unlock(&ctrl->lock);
+}
+
+static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
+{
+	struct nvmet_ctrl *ctrl;
+
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
+		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_NS_ATTR))
+			continue;
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+				NVME_AER_NOTICE_NS_CHANGED,
+				NVME_LOG_CHANGED_NS);
+	}
+}
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
 {
 	int ret = 0;
@@ -271,33 +323,31 @@ void nvmet_put_namespace(struct nvmet_ns *ns)
 	percpu_ref_put(&ns->ref);
 }
 
+static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
+{
+	nvmet_bdev_ns_disable(ns);
+	nvmet_file_ns_disable(ns);
+}
+
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	struct nvmet_ctrl *ctrl;
 	int ret = 0;
 
 	mutex_lock(&subsys->lock);
 	if (ns->enabled)
 		goto out_unlock;
 
-	ns->bdev = blkdev_get_by_path(ns->device_path, FMODE_READ | FMODE_WRITE,
-			NULL);
-	if (IS_ERR(ns->bdev)) {
-		pr_err("failed to open block device %s: (%ld)\n",
-		       ns->device_path, PTR_ERR(ns->bdev));
-		ret = PTR_ERR(ns->bdev);
-		ns->bdev = NULL;
+	ret = nvmet_bdev_ns_enable(ns);
+	if (ret)
+		ret = nvmet_file_ns_enable(ns);
+	if (ret)
 		goto out_unlock;
-	}
-
-	ns->size = i_size_read(ns->bdev->bd_inode);
-	ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
 
 	ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace,
 				0, GFP_KERNEL);
 	if (ret)
-		goto out_blkdev_put;
+		goto out_dev_put;
 
 	if (ns->nsid > subsys->max_nsid)
 		subsys->max_nsid = ns->nsid;
@@ -320,24 +370,20 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
 	}
 
-	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
-
+	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
 	ret = 0;
 out_unlock:
 	mutex_unlock(&subsys->lock);
 	return ret;
-out_blkdev_put:
-	blkdev_put(ns->bdev, FMODE_WRITE|FMODE_READ);
-	ns->bdev = NULL;
+out_dev_put:
+	nvmet_ns_dev_disable(ns);
 	goto out_unlock;
 }
 
 void nvmet_ns_disable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	struct nvmet_ctrl *ctrl;
 
 	mutex_lock(&subsys->lock);
 	if (!ns->enabled)
@@ -363,11 +409,8 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
-	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
-
-	if (ns->bdev)
-		blkdev_put(ns->bdev, FMODE_WRITE|FMODE_READ);
+	nvmet_ns_changed(subsys, ns->nsid);
+	nvmet_ns_dev_disable(ns);
 out_unlock:
 	mutex_unlock(&subsys->lock);
 }
@@ -499,6 +542,25 @@ int nvmet_sq_init(struct nvmet_sq *sq)
 }
 EXPORT_SYMBOL_GPL(nvmet_sq_init);
 
+static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
+{
+	struct nvme_command *cmd = req->cmd;
+	u16 ret;
+
+	ret = nvmet_check_ctrl_status(req, cmd);
+	if (unlikely(ret))
+		return ret;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
+	if (unlikely(!req->ns))
+		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+
+	if (req->ns->file)
+		return nvmet_file_parse_io_cmd(req);
+	else
+		return nvmet_bdev_parse_io_cmd(req);
+}
+
 bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 		struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops)
 {
@@ -710,15 +772,14 @@ out:
 u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd)
 {
 	if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
-		pr_err("got io cmd %d while CC.EN == 0 on qid = %d\n",
+		pr_err("got cmd %d while CC.EN == 0 on qid = %d\n",
 		       cmd->common.opcode, req->sq->qid);
 		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 	}
 
 	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
-		pr_err("got io cmd %d while CSTS.RDY == 0 on qid = %d\n",
+		pr_err("got cmd %d while CSTS.RDY == 0 on qid = %d\n",
 		       cmd->common.opcode, req->sq->qid);
-		req->ns = NULL;
 		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 	}
 	return 0;
@@ -809,12 +870,18 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	kref_init(&ctrl->ref);
 	ctrl->subsys = subsys;
+	WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
+
+	ctrl->changed_ns_list = kmalloc_array(NVME_MAX_CHANGED_NAMESPACES,
+			sizeof(__le32), GFP_KERNEL);
+	if (!ctrl->changed_ns_list)
+		goto out_free_ctrl;
 
 	ctrl->cqs = kcalloc(subsys->max_qid + 1,
 			sizeof(struct nvmet_cq *),
 			GFP_KERNEL);
 	if (!ctrl->cqs)
-		goto out_free_ctrl;
+		goto out_free_changed_ns_list;
 
 	ctrl->sqs = kcalloc(subsys->max_qid + 1,
 			sizeof(struct nvmet_sq *),
@@ -872,6 +939,8 @@ out_free_sqs:
 	kfree(ctrl->sqs);
 out_free_cqs:
 	kfree(ctrl->cqs);
+out_free_changed_ns_list:
+	kfree(ctrl->changed_ns_list);
 out_free_ctrl:
 	kfree(ctrl);
 out_put_subsystem:
@@ -898,6 +967,7 @@ static void nvmet_ctrl_free(struct kref *ref)
 
 	kfree(ctrl->sqs);
 	kfree(ctrl->cqs);
+	kfree(ctrl->changed_ns_list);
 	kfree(ctrl);
 
 	nvmet_subsys_put(subsys);
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 231e04e0a496..08656b849bd6 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -187,8 +187,6 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
 
-	req->ns = NULL;
-
 	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
 		pr_err("got cmd %d while not ready\n",
 		       cmd->common.opcode);
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 19e9e42ae943..d84ae004cb85 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -77,8 +77,6 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
 
-	req->ns = NULL;
-
 	switch (cmd->fabrics.fctype) {
 	case nvme_fabrics_type_property_set:
 		req->data_len = 0;
@@ -242,8 +240,6 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
 
-	req->ns = NULL;
-
 	if (cmd->common.opcode != nvme_fabrics_command) {
 		pr_err("invalid command 0x%x on unconnected queue.\n",
 			cmd->fabrics.opcode);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 33ee8d3145f8..408279cb6f2c 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -31,7 +31,7 @@
 /* *************************** Data Structures/Defines ****************** */
 
 
-#define NVMET_LS_CTX_COUNT		4
+#define NVMET_LS_CTX_COUNT		256
 
 /* for this implementation, assume small single frame rqst/rsp */
 #define NVME_FC_MAX_LS_BUFFER_SIZE		2048
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd-bdev.c
index cd2344179673..e0b0f7df70c2 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -16,6 +16,34 @@
 #include <linux/module.h>
 #include "nvmet.h"
 
+int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
+{
+	int ret;
+
+	ns->bdev = blkdev_get_by_path(ns->device_path,
+			FMODE_READ | FMODE_WRITE, NULL);
+	if (IS_ERR(ns->bdev)) {
+		ret = PTR_ERR(ns->bdev);
+		if (ret != -ENOTBLK) {
+			pr_err("failed to open block device %s: (%ld)\n",
+					ns->device_path, PTR_ERR(ns->bdev));
+		}
+		ns->bdev = NULL;
+		return ret;
+	}
+	ns->size = i_size_read(ns->bdev->bd_inode);
+	ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
+	return 0;
+}
+
+void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
+{
+	if (ns->bdev) {
+		blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ);
+		ns->bdev = NULL;
+	}
+}
+
 static void nvmet_bio_done(struct bio *bio)
 {
 	struct nvmet_req *req = bio->bi_private;
@@ -23,20 +51,14 @@ static void nvmet_bio_done(struct bio *bio)
 	nvmet_req_complete(req,
 		bio->bi_status ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
 
-	if (bio != &req->inline_bio)
+	if (bio != &req->b.inline_bio)
 		bio_put(bio);
 }
 
-static inline u32 nvmet_rw_len(struct nvmet_req *req)
-{
-	return ((u32)le16_to_cpu(req->cmd->rw.length) + 1) <<
-			req->ns->blksize_shift;
-}
-
-static void nvmet_execute_rw(struct nvmet_req *req)
+static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 {
 	int sg_cnt = req->sg_cnt;
-	struct bio *bio = &req->inline_bio;
+	struct bio *bio = &req->b.inline_bio;
 	struct scatterlist *sg;
 	sector_t sector;
 	blk_qc_t cookie;
@@ -89,9 +111,9 @@ static void nvmet_execute_rw(struct nvmet_req *req)
 	blk_poll(bdev_get_queue(req->ns->bdev), cookie);
 }
 
-static void nvmet_execute_flush(struct nvmet_req *req)
+static void nvmet_bdev_execute_flush(struct nvmet_req *req)
 {
-	struct bio *bio = &req->inline_bio;
+	struct bio *bio = &req->b.inline_bio;
 
 	bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
 	bio_set_dev(bio, req->ns->bdev);
@@ -102,7 +124,7 @@ static void nvmet_execute_flush(struct nvmet_req *req)
 	submit_bio(bio);
 }
 
-static u16 nvmet_discard_range(struct nvmet_ns *ns,
+static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns,
 		struct nvme_dsm_range *range, struct bio **bio)
 {
 	int ret;
@@ -116,7 +138,7 @@ static u16 nvmet_discard_range(struct nvmet_ns *ns,
 	return 0;
 }
 
-static void nvmet_execute_discard(struct nvmet_req *req)
+static void nvmet_bdev_execute_discard(struct nvmet_req *req)
 {
 	struct nvme_dsm_range range;
 	struct bio *bio = NULL;
@@ -129,7 +151,7 @@ static void nvmet_execute_discard(struct nvmet_req *req)
 		if (status)
 			break;
 
-		status = nvmet_discard_range(req->ns, &range, &bio);
+		status = nvmet_bdev_discard_range(req->ns, &range, &bio);
 		if (status)
 			break;
 	}
@@ -148,11 +170,11 @@ static void nvmet_execute_discard(struct nvmet_req *req)
 	}
 }
 
-static void nvmet_execute_dsm(struct nvmet_req *req)
+static void nvmet_bdev_execute_dsm(struct nvmet_req *req)
 {
 	switch (le32_to_cpu(req->cmd->dsm.attributes)) {
 	case NVME_DSMGMT_AD:
-		nvmet_execute_discard(req);
+		nvmet_bdev_execute_discard(req);
 		return;
 	case NVME_DSMGMT_IDR:
 	case NVME_DSMGMT_IDW:
@@ -163,7 +185,7 @@ static void nvmet_execute_dsm(struct nvmet_req *req)
 	}
 }
 
-static void nvmet_execute_write_zeroes(struct nvmet_req *req)
+static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
 {
 	struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes;
 	struct bio *bio = NULL;
@@ -189,38 +211,27 @@ static void nvmet_execute_write_zeroes(struct nvmet_req *req)
 	}
 }
 
-u16 nvmet_parse_io_cmd(struct nvmet_req *req)
+u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
-	u16 ret;
-
-	ret = nvmet_check_ctrl_status(req, cmd);
-	if (unlikely(ret)) {
-		req->ns = NULL;
-		return ret;
-	}
-
-	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
-	if (unlikely(!req->ns))
-		return NVME_SC_INVALID_NS | NVME_SC_DNR;
 
 	switch (cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
-		req->execute = nvmet_execute_rw;
+		req->execute = nvmet_bdev_execute_rw;
 		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
-		req->execute = nvmet_execute_flush;
+		req->execute = nvmet_bdev_execute_flush;
 		req->data_len = 0;
 		return 0;
 	case nvme_cmd_dsm:
-		req->execute = nvmet_execute_dsm;
+		req->execute = nvmet_bdev_execute_dsm;
 		req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
 			sizeof(struct nvme_dsm_range);
 		return 0;
 	case nvme_cmd_write_zeroes:
-		req->execute = nvmet_execute_write_zeroes;
+		req->execute = nvmet_bdev_execute_write_zeroes;
 		return 0;
 	default:
 		pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
new file mode 100644
index 000000000000..8c42b3a8c420
--- /dev/null
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMe Over Fabrics Target File I/O commands implementation.
+ * Copyright (c) 2017-2018 Western Digital Corporation or its
+ * affiliates.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/uio.h>
+#include <linux/falloc.h>
+#include <linux/file.h>
+#include "nvmet.h"
+
+#define NVMET_MAX_MPOOL_BVEC		16
+#define NVMET_MIN_MPOOL_OBJ		16
+
+void nvmet_file_ns_disable(struct nvmet_ns *ns)
+{
+	if (ns->file) {
+		mempool_destroy(ns->bvec_pool);
+		ns->bvec_pool = NULL;
+		kmem_cache_destroy(ns->bvec_cache);
+		ns->bvec_cache = NULL;
+		fput(ns->file);
+		ns->file = NULL;
+	}
+}
+
+int nvmet_file_ns_enable(struct nvmet_ns *ns)
+{
+	int ret;
+	struct kstat stat;
+
+	ns->file = filp_open(ns->device_path,
+			O_RDWR | O_LARGEFILE | O_DIRECT, 0);
+	if (IS_ERR(ns->file)) {
+		pr_err("failed to open file %s: (%ld)\n",
+				ns->device_path, PTR_ERR(ns->file));
+		return PTR_ERR(ns->file);
+	}
+
+	ret = vfs_getattr(&ns->file->f_path,
+			&stat, STATX_SIZE, AT_STATX_FORCE_SYNC);
+	if (ret)
+		goto err;
+
+	ns->size = stat.size;
+	ns->blksize_shift = file_inode(ns->file)->i_blkbits;
+
+	ns->bvec_cache = kmem_cache_create("nvmet-bvec",
+			NVMET_MAX_MPOOL_BVEC * sizeof(struct bio_vec),
+			0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!ns->bvec_cache) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ns->bvec_pool = mempool_create(NVMET_MIN_MPOOL_OBJ, mempool_alloc_slab,
+			mempool_free_slab, ns->bvec_cache);
+
+	if (!ns->bvec_pool) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	return ret;
+err:
+	ns->size = 0;
+	ns->blksize_shift = 0;
+	nvmet_file_ns_disable(ns);
+	return ret;
+}
+
+static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter)
+{
+	bv->bv_page = sg_page_iter_page(iter);
+	bv->bv_offset = iter->sg->offset;
+	bv->bv_len = PAGE_SIZE - iter->sg->offset;
+}
+
+static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
+		unsigned long nr_segs, size_t count)
+{
+	struct kiocb *iocb = &req->f.iocb;
+	ssize_t (*call_iter)(struct kiocb *iocb, struct iov_iter *iter);
+	struct iov_iter iter;
+	int ki_flags = 0, rw;
+	ssize_t ret;
+
+	if (req->cmd->rw.opcode == nvme_cmd_write) {
+		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
+			ki_flags = IOCB_DSYNC;
+		call_iter = req->ns->file->f_op->write_iter;
+		rw = WRITE;
+	} else {
+		call_iter = req->ns->file->f_op->read_iter;
+		rw = READ;
+	}
+
+	iov_iter_bvec(&iter, ITER_BVEC | rw, req->f.bvec, nr_segs, count);
+
+	iocb->ki_pos = pos;
+	iocb->ki_filp = req->ns->file;
+	iocb->ki_flags = IOCB_DIRECT | ki_flags;
+
+	ret = call_iter(iocb, &iter);
+
+	if (ret != -EIOCBQUEUED && iocb->ki_complete)
+		iocb->ki_complete(iocb, ret, 0);
+
+	return ret;
+}
+
+static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
+{
+	struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb);
+
+	if (req->f.bvec != req->inline_bvec) {
+		if (likely(req->f.mpool_alloc == false))
+			kfree(req->f.bvec);
+		else
+			mempool_free(req->f.bvec, req->ns->bvec_pool);
+	}
+
+	nvmet_req_complete(req, ret != req->data_len ?
+			NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+}
+
+static void nvmet_file_execute_rw(struct nvmet_req *req)
+{
+	ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
+	struct sg_page_iter sg_pg_iter;
+	unsigned long bv_cnt = 0;
+	bool is_sync = false;
+	size_t len = 0, total_len = 0;
+	ssize_t ret = 0;
+	loff_t pos;
+
+	if (!req->sg_cnt || !nr_bvec) {
+		nvmet_req_complete(req, 0);
+		return;
+	}
+
+	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
+		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
+				GFP_KERNEL);
+	else
+		req->f.bvec = req->inline_bvec;
+
+	req->f.mpool_alloc = false;
+	if (unlikely(!req->f.bvec)) {
+		/* fallback under memory pressure */
+		req->f.bvec = mempool_alloc(req->ns->bvec_pool, GFP_KERNEL);
+		req->f.mpool_alloc = true;
+		if (nr_bvec > NVMET_MAX_MPOOL_BVEC)
+			is_sync = true;
+	}
+
+	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
+
+	memset(&req->f.iocb, 0, sizeof(struct kiocb));
+	for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
+		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
+		len += req->f.bvec[bv_cnt].bv_len;
+		total_len += req->f.bvec[bv_cnt].bv_len;
+		bv_cnt++;
+
+		WARN_ON_ONCE((nr_bvec - 1) < 0);
+
+		if (unlikely(is_sync) &&
+		    (nr_bvec - 1 == 0 || bv_cnt == NVMET_MAX_MPOOL_BVEC)) {
+			ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len);
+			if (ret < 0)
+				goto out;
+			pos += len;
+			bv_cnt = 0;
+			len = 0;
+		}
+		nr_bvec--;
+	}
+
+	if (WARN_ON_ONCE(total_len != req->data_len))
+		ret = -EIO;
+out:
+	if (unlikely(is_sync || ret)) {
+		nvmet_file_io_done(&req->f.iocb, ret < 0 ? ret : total_len, 0);
+		return;
+	}
+	req->f.iocb.ki_complete = nvmet_file_io_done;
+	nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
+}
+
+static void nvmet_file_flush_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+	int ret;
+
+	ret = vfs_fsync(req->ns->file, 1);
+
+	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+}
+
+static void nvmet_file_execute_flush(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_flush_work);
+	schedule_work(&req->f.work);
+}
+
+static void nvmet_file_execute_discard(struct nvmet_req *req)
+{
+	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
+	struct nvme_dsm_range range;
+	loff_t offset;
+	loff_t len;
+	int i, ret;
+
+	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
+		if (nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+					sizeof(range)))
+			break;
+		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
+		len = le32_to_cpu(range.nlb) << req->ns->blksize_shift;
+		ret = vfs_fallocate(req->ns->file, mode, offset, len);
+		if (ret)
+			break;
+	}
+
+	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+}
+
+static void nvmet_file_dsm_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+
+	switch (le32_to_cpu(req->cmd->dsm.attributes)) {
+	case NVME_DSMGMT_AD:
+		nvmet_file_execute_discard(req);
+		return;
+	case NVME_DSMGMT_IDR:
+	case NVME_DSMGMT_IDW:
+	default:
+		/* Not supported yet */
+		nvmet_req_complete(req, 0);
+		return;
+	}
+}
+
+static void nvmet_file_execute_dsm(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_dsm_work);
+	schedule_work(&req->f.work);
+}
+
+static void nvmet_file_write_zeroes_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+	struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes;
+	int mode = FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE;
+	loff_t offset;
+	loff_t len;
+	int ret;
+
+	offset = le64_to_cpu(write_zeroes->slba) << req->ns->blksize_shift;
+	len = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
+			req->ns->blksize_shift);
+
+	ret = vfs_fallocate(req->ns->file, mode, offset, len);
+	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+}
+
+static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work);
+	schedule_work(&req->f.work);
+}
+
+u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
+{
+	struct nvme_command *cmd = req->cmd;
+
+	switch (cmd->common.opcode) {
+	case nvme_cmd_read:
+	case nvme_cmd_write:
+		req->execute = nvmet_file_execute_rw;
+		req->data_len = nvmet_rw_len(req);
+		return 0;
+	case nvme_cmd_flush:
+		req->execute = nvmet_file_execute_flush;
+		req->data_len = 0;
+		return 0;
+	case nvme_cmd_dsm:
+		req->execute = nvmet_file_execute_dsm;
+		req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
+			sizeof(struct nvme_dsm_range);
+		return 0;
+	case nvme_cmd_write_zeroes:
+		req->execute = nvmet_file_execute_write_zeroes;
+		req->data_len = 0;
+		return 0;
+	default:
+		pr_err("unhandled cmd for file ns %d on qid %d\n",
+				cmd->common.opcode, req->sq->qid);
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+}
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 31fdfba556a8..1304ec3a7ede 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -45,6 +45,7 @@ struct nvme_loop_ctrl {
 	struct nvme_ctrl	ctrl;
 
 	struct nvmet_ctrl	*target_ctrl;
+	struct nvmet_port	*port;
 };
 
 static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
@@ -63,7 +64,8 @@ struct nvme_loop_queue {
 	unsigned long		flags;
 };
 
-static struct nvmet_port *nvmet_loop_port;
+static LIST_HEAD(nvme_loop_ports);
+static DEFINE_MUTEX(nvme_loop_ports_mutex);
 
 static LIST_HEAD(nvme_loop_ctrl_list);
 static DEFINE_MUTEX(nvme_loop_ctrl_mutex);
@@ -146,7 +148,7 @@ nvme_loop_timeout(struct request *rq, bool reserved)
 	/* fail with DNR on admin cmd timeout */
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
 
-	return BLK_EH_HANDLED;
+	return BLK_EH_DONE;
 }
 
 static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -169,12 +171,12 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(req);
 	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
-	iod->req.port = nvmet_loop_port;
+	iod->req.port = queue->ctrl->port;
 	if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
 			&queue->nvme_sq, &nvme_loop_ops))
 		return BLK_STS_OK;
 
-	if (blk_rq_payload_bytes(req)) {
+	if (blk_rq_nr_phys_segments(req)) {
 		iod->sg_table.sgl = iod->first_sgl;
 		if (sg_alloc_table_chained(&iod->sg_table,
 				blk_rq_nr_phys_segments(req),
@@ -469,6 +471,12 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_loop_shutdown_ctrl(ctrl);
 
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
+		/* state change failure should never happen */
+		WARN_ON_ONCE(1);
+		return;
+	}
+
 	ret = nvme_loop_configure_admin_queue(ctrl);
 	if (ret)
 		goto out_disable;
@@ -511,6 +519,7 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 	.free_ctrl		= nvme_loop_free_ctrl,
 	.submit_async_event	= nvme_loop_submit_async_event,
 	.delete_ctrl		= nvme_loop_delete_ctrl_host,
+	.get_address		= nvmf_get_address,
 };
 
 static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -559,6 +568,23 @@ out_destroy_queues:
 	return ret;
 }
 
+static struct nvmet_port *nvme_loop_find_port(struct nvme_ctrl *ctrl)
+{
+	struct nvmet_port *p, *found = NULL;
+
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_for_each_entry(p, &nvme_loop_ports, entry) {
+		/* if no transport address is specified use the first port */
+		if ((ctrl->opts->mask & NVMF_OPT_TRADDR) &&
+		    strcmp(ctrl->opts->traddr, p->disc_addr.traddr))
+			continue;
+		found = p;
+		break;
+	}
+	mutex_unlock(&nvme_loop_ports_mutex);
+	return found;
+}
+
 static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 		struct nvmf_ctrl_options *opts)
 {
@@ -583,6 +609,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 
 	ctrl->ctrl.sqsize = opts->queue_size - 1;
 	ctrl->ctrl.kato = opts->kato;
+	ctrl->port = nvme_loop_find_port(&ctrl->ctrl);
 
 	ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues),
 			GFP_KERNEL);
@@ -640,27 +667,17 @@ out_put_ctrl:
 
 static int nvme_loop_add_port(struct nvmet_port *port)
 {
-	/*
-	 * XXX: disalow adding more than one port so
-	 * there is no connection rejections when a
-	 * a subsystem is assigned to a port for which
-	 * loop doesn't have a pointer.
-	 * This scenario would be possible if we allowed
-	 * more than one port to be added and a subsystem
-	 * was assigned to a port other than nvmet_loop_port.
-	 */
-
-	if (nvmet_loop_port)
-		return -EPERM;
-
-	nvmet_loop_port = port;
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_add_tail(&port->entry, &nvme_loop_ports);
+	mutex_unlock(&nvme_loop_ports_mutex);
 	return 0;
 }
 
 static void nvme_loop_remove_port(struct nvmet_port *port)
 {
-	if (port == nvmet_loop_port)
-		nvmet_loop_port = NULL;
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_del_init(&port->entry);
+	mutex_unlock(&nvme_loop_ports_mutex);
 }
 
 static const struct nvmet_fabrics_ops nvme_loop_ops = {
@@ -676,6 +693,7 @@ static struct nvmf_transport_ops nvme_loop_transport = {
 	.name		= "loop",
 	.module		= THIS_MODULE,
 	.create_ctrl	= nvme_loop_create_ctrl,
+	.allowed_opts	= NVMF_OPT_TRADDR,
 };
 
 static int __init nvme_loop_init_module(void)
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 15fd84ab21f8..480dfe10fad9 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -30,6 +30,21 @@
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
 
+
+/*
+ * Supported optional AENs:
+ */
+#define NVMET_AEN_CFG_OPTIONAL \
+	NVME_AEN_CFG_NS_ATTR
+
+/*
+ * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
+ */
+#define NVMET_AEN_CFG_ALL \
+	(NVME_SMART_CRIT_SPARE | NVME_SMART_CRIT_TEMPERATURE | \
+	 NVME_SMART_CRIT_RELIABILITY | NVME_SMART_CRIT_MEDIA | \
+	 NVME_SMART_CRIT_VOLATILE_MEMORY | NVMET_AEN_CFG_OPTIONAL)
+
 /* Helper Macros when NVMe error is NVME_SC_CONNECT_INVALID_PARAM
  * The 16 bit shift is to set IATTR bit to 1, which means offending
  * offset starts in the data section of connect()
@@ -43,6 +58,7 @@ struct nvmet_ns {
 	struct list_head	dev_link;
 	struct percpu_ref	ref;
 	struct block_device	*bdev;
+	struct file		*file;
 	u32			nsid;
 	u32			blksize_shift;
 	loff_t			size;
@@ -57,6 +73,8 @@ struct nvmet_ns {
 	struct config_group	group;
 
 	struct completion	disable_done;
+	mempool_t		*bvec_pool;
+	struct kmem_cache	*bvec_cache;
 };
 
 static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
@@ -82,7 +100,7 @@ struct nvmet_sq {
 /**
  * struct nvmet_port -	Common structure to keep port
  *				information for the target.
- * @entry:		List head for holding a list of these elements.
+ * @entry:		Entry into referrals or transport list.
  * @disc_addr:		Address information is stored in a format defined
  *				for a discovery log page entry.
  * @group:		ConfigFS group for this element's folder.
@@ -120,6 +138,8 @@ struct nvmet_ctrl {
 	u16			cntlid;
 	u32			kato;
 
+	u32			aen_enabled;
+	unsigned long		aen_masked;
 	struct nvmet_req	*async_event_cmds[NVMET_ASYNC_EVENTS];
 	unsigned int		nr_async_event_cmds;
 	struct list_head	async_events;
@@ -132,6 +152,9 @@ struct nvmet_ctrl {
 
 	const struct nvmet_fabrics_ops *ops;
 
+	__le32			*changed_ns_list;
+	u32			nr_changed_ns;
+
 	char			subsysnqn[NVMF_NQN_FIELD_LEN];
 	char			hostnqn[NVMF_NQN_FIELD_LEN];
 };
@@ -222,8 +245,18 @@ struct nvmet_req {
 	struct nvmet_cq		*cq;
 	struct nvmet_ns		*ns;
 	struct scatterlist	*sg;
-	struct bio		inline_bio;
 	struct bio_vec		inline_bvec[NVMET_MAX_INLINE_BIOVEC];
+	union {
+		struct {
+			struct bio      inline_bio;
+		} b;
+		struct {
+			bool			mpool_alloc;
+			struct kiocb            iocb;
+			struct bio_vec          *bvec;
+			struct work_struct      work;
+		} f;
+	};
 	int			sg_cnt;
 	/* data length as parsed from the command: */
 	size_t			data_len;
@@ -263,7 +296,8 @@ struct nvmet_async_event {
 };
 
 u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
-u16 nvmet_parse_io_cmd(struct nvmet_req *req);
+u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req);
+u16 nvmet_file_parse_io_cmd(struct nvmet_req *req);
 u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
 u16 nvmet_parse_discovery_cmd(struct nvmet_req *req);
 u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
@@ -316,6 +350,7 @@ u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
 		size_t len);
 u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf,
 		size_t len);
+u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len);
 
 u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 
@@ -338,4 +373,14 @@ extern struct rw_semaphore nvmet_config_sem;
 bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
 		const char *hostnqn);
 
+int nvmet_bdev_ns_enable(struct nvmet_ns *ns);
+int nvmet_file_ns_enable(struct nvmet_ns *ns);
+void nvmet_bdev_ns_disable(struct nvmet_ns *ns);
+void nvmet_file_ns_disable(struct nvmet_ns *ns);
+
+static inline u32 nvmet_rw_len(struct nvmet_req *req)
+{
+	return ((u32)le16_to_cpu(req->cmd->rw.length) + 1) <<
+			req->ns->blksize_shift;
+}
 #endif /* _NVMET_H */
diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig
index 1090924efdb1..54a3c298247b 100644
--- a/drivers/nvmem/Kconfig
+++ b/drivers/nvmem/Kconfig
@@ -175,4 +175,10 @@ config NVMEM_SNVS_LPGPR
 	  This driver can also be built as a module. If so, the module
 	  will be called nvmem-snvs-lpgpr.
 
+config RAVE_SP_EEPROM
+	tristate "Rave SP EEPROM Support"
+	depends on RAVE_SP_CORE
+	help
+	  Say y here to enable Rave SP EEPROM support.
+
 endif
diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile
index e54dcfa6565a..27e96a8efd1c 100644
--- a/drivers/nvmem/Makefile
+++ b/drivers/nvmem/Makefile
@@ -37,3 +37,6 @@ obj-$(CONFIG_MESON_MX_EFUSE)	+= nvmem_meson_mx_efuse.o
 nvmem_meson_mx_efuse-y		:= meson-mx-efuse.o
 obj-$(CONFIG_NVMEM_SNVS_LPGPR)	+= nvmem_snvs_lpgpr.o
 nvmem_snvs_lpgpr-y		:= snvs_lpgpr.o
+obj-$(CONFIG_RAVE_SP_EEPROM)	+= nvmem-rave-sp-eeprom.o
+nvmem-rave-sp-eeprom-y		:= rave-sp-eeprom.o
+
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index b05aa8e81303..b5b0cdc21d01 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -353,18 +353,27 @@ static int nvmem_cell_info_to_nvmem_cell(struct nvmem_device *nvmem,
 	return 0;
 }
 
-static int nvmem_add_cells(struct nvmem_device *nvmem,
-			   const struct nvmem_config *cfg)
+/**
+ * nvmem_add_cells() - Add cell information to an nvmem device
+ *
+ * @nvmem: nvmem device to add cells to.
+ * @info: nvmem cell info to add to the device
+ * @ncells: number of cells in info
+ *
+ * Return: 0 or negative error code on failure.
+ */
+int nvmem_add_cells(struct nvmem_device *nvmem,
+		    const struct nvmem_cell_info *info,
+		    int ncells)
 {
 	struct nvmem_cell **cells;
-	const struct nvmem_cell_info *info = cfg->cells;
 	int i, rval;
 
-	cells = kcalloc(cfg->ncells, sizeof(*cells), GFP_KERNEL);
+	cells = kcalloc(ncells, sizeof(*cells), GFP_KERNEL);
 	if (!cells)
 		return -ENOMEM;
 
-	for (i = 0; i < cfg->ncells; i++) {
+	for (i = 0; i < ncells; i++) {
 		cells[i] = kzalloc(sizeof(**cells), GFP_KERNEL);
 		if (!cells[i]) {
 			rval = -ENOMEM;
@@ -380,7 +389,7 @@ static int nvmem_add_cells(struct nvmem_device *nvmem,
 		nvmem_cell_add(cells[i]);
 	}
 
-	nvmem->ncells = cfg->ncells;
+	nvmem->ncells = ncells;
 	/* remove tmp array */
 	kfree(cells);
 
@@ -393,6 +402,7 @@ err:
 
 	return rval;
 }
+EXPORT_SYMBOL_GPL(nvmem_add_cells);
 
 /*
  * nvmem_setup_compat() - Create an additional binary entry in
@@ -509,7 +519,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	}
 
 	if (config->cells)
-		nvmem_add_cells(nvmem, config);
+		nvmem_add_cells(nvmem, config->cells, config->ncells);
 
 	return nvmem;
 
@@ -559,6 +569,7 @@ static void devm_nvmem_release(struct device *dev, void *res)
  * nvmem_config.
  * Also creates an binary entry in /sys/bus/nvmem/devices/dev-name/nvmem
  *
+ * @dev: Device that uses the nvmem device.
  * @config: nvmem device configuration with which nvmem device is created.
  *
  * Return: Will be an ERR_PTR() on error or a valid pointer to nvmem_device
@@ -597,6 +608,7 @@ static int devm_nvmem_match(struct device *dev, void *res, void *data)
  * devm_nvmem_unregister() - Unregister previously registered managed nvmem
  * device.
  *
+ * @dev: Device that uses the nvmem device.
  * @nvmem: Pointer to previously registered nvmem device.
  *
  * Return: Will be an negative on error or a zero on success.
@@ -1107,6 +1119,8 @@ static void *nvmem_cell_prepare_write_buffer(struct nvmem_cell *cell,
 
 		/* setup the first byte with lsb bits from nvmem */
 		rc = nvmem_reg_read(nvmem, cell->offset, &v, 1);
+		if (rc)
+			goto err;
 		*b++ |= GENMASK(bit_offset - 1, 0) & v;
 
 		/* setup rest of the byte if any */
@@ -1125,11 +1139,16 @@ static void *nvmem_cell_prepare_write_buffer(struct nvmem_cell *cell,
 		/* setup the last byte with msb bits from nvmem */
 		rc = nvmem_reg_read(nvmem,
 				    cell->offset + cell->bytes - 1, &v, 1);
+		if (rc)
+			goto err;
 		*p |= GENMASK(7, (nbits + bit_offset) % BITS_PER_BYTE) & v;
 
 	}
 
 	return buf;
+err:
+	kfree(buf);
+	return ERR_PTR(rc);
 }
 
 /**
diff --git a/drivers/nvmem/meson-efuse.c b/drivers/nvmem/meson-efuse.c
index 71823d1403c5..d769840d1e18 100644
--- a/drivers/nvmem/meson-efuse.c
+++ b/drivers/nvmem/meson-efuse.c
@@ -24,23 +24,16 @@
 static int meson_efuse_read(void *context, unsigned int offset,
 			    void *val, size_t bytes)
 {
-	u8 *buf = val;
-	int ret;
-
-	ret = meson_sm_call_read(buf, bytes, SM_EFUSE_READ, offset,
-				 bytes, 0, 0, 0);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return meson_sm_call_read((u8 *)val, bytes, SM_EFUSE_READ, offset,
+				  bytes, 0, 0, 0);
 }
 
-static struct nvmem_config econfig = {
-	.name = "meson-efuse",
-	.stride = 1,
-	.word_size = 1,
-	.read_only = true,
-};
+static int meson_efuse_write(void *context, unsigned int offset,
+			     void *val, size_t bytes)
+{
+	return meson_sm_call_write((u8 *)val, bytes, SM_EFUSE_WRITE, offset,
+				   bytes, 0, 0, 0);
+}
 
 static const struct of_device_id meson_efuse_match[] = {
 	{ .compatible = "amlogic,meson-gxbb-efuse", },
@@ -50,17 +43,27 @@ MODULE_DEVICE_TABLE(of, meson_efuse_match);
 
 static int meson_efuse_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct nvmem_device *nvmem;
+	struct nvmem_config *econfig;
 	unsigned int size;
 
 	if (meson_sm_call(SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0)
 		return -EINVAL;
 
-	econfig.dev = &pdev->dev;
-	econfig.reg_read = meson_efuse_read;
-	econfig.size = size;
+	econfig = devm_kzalloc(dev, sizeof(*econfig), GFP_KERNEL);
+	if (!econfig)
+		return -ENOMEM;
+
+	econfig->dev = dev;
+	econfig->name = dev_name(dev);
+	econfig->stride = 1;
+	econfig->word_size = 1;
+	econfig->reg_read = meson_efuse_read;
+	econfig->reg_write = meson_efuse_write;
+	econfig->size = size;
 
-	nvmem = devm_nvmem_register(&pdev->dev, &econfig);
+	nvmem = devm_nvmem_register(&pdev->dev, econfig);
 
 	return PTR_ERR_OR_ZERO(nvmem);
 }
diff --git a/drivers/nvmem/rave-sp-eeprom.c b/drivers/nvmem/rave-sp-eeprom.c
new file mode 100644
index 000000000000..50aeea6ec6cc
--- /dev/null
+++ b/drivers/nvmem/rave-sp-eeprom.c
@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * EEPROM driver for RAVE SP
+ *
+ * Copyright (C) 2018 Zodiac Inflight Innovations
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/mfd/rave-sp.h>
+#include <linux/module.h>
+#include <linux/nvmem-provider.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/sizes.h>
+
+/**
+ * enum rave_sp_eeprom_access_type - Supported types of EEPROM access
+ *
+ * @RAVE_SP_EEPROM_WRITE:	EEPROM write
+ * @RAVE_SP_EEPROM_READ:	EEPROM read
+ */
+enum rave_sp_eeprom_access_type {
+	RAVE_SP_EEPROM_WRITE = 0,
+	RAVE_SP_EEPROM_READ  = 1,
+};
+
+/**
+ * enum rave_sp_eeprom_header_size - EEPROM command header sizes
+ *
+ * @RAVE_SP_EEPROM_HEADER_SMALL: EEPROM header size for "small" devices (< 8K)
+ * @RAVE_SP_EEPROM_HEADER_BIG:	 EEPROM header size for "big" devices (> 8K)
+ */
+enum rave_sp_eeprom_header_size {
+	RAVE_SP_EEPROM_HEADER_SMALL = 4U,
+	RAVE_SP_EEPROM_HEADER_BIG   = 5U,
+};
+
+#define	RAVE_SP_EEPROM_PAGE_SIZE	32U
+
+/**
+ * struct rave_sp_eeprom_page - RAVE SP EEPROM page
+ *
+ * @type:	Access type (see enum rave_sp_eeprom_access_type)
+ * @success:	Success flag (Success = 1, Failure = 0)
+ * @data:	Read data
+
+ * Note this structure corresponds to RSP_*_EEPROM payload from RAVE
+ * SP ICD
+ */
+struct rave_sp_eeprom_page {
+	u8  type;
+	u8  success;
+	u8  data[RAVE_SP_EEPROM_PAGE_SIZE];
+} __packed;
+
+/**
+ * struct rave_sp_eeprom - RAVE SP EEPROM device
+ *
+ * @sp:			Pointer to parent RAVE SP device
+ * @mutex:		Lock protecting access to EEPROM
+ * @address:		EEPROM device address
+ * @header_size:	Size of EEPROM command header for this device
+ * @dev:		Pointer to corresponding struct device used for logging
+ */
+struct rave_sp_eeprom {
+	struct rave_sp *sp;
+	struct mutex mutex;
+	u8 address;
+	unsigned int header_size;
+	struct device *dev;
+};
+
+/**
+ * rave_sp_eeprom_io - Low-level part of EEPROM page access
+ *
+ * @eeprom:	EEPROM device to write to
+ * @type:	EEPROM access type (read or write)
+ * @idx:	number of the EEPROM page
+ * @page:	Data to write or buffer to store result (via page->data)
+ *
+ * This function does all of the low-level work required to perform a
+ * EEPROM access. This includes formatting correct command payload,
+ * sending it and checking received results.
+ *
+ * Returns zero in case of success or negative error code in
+ * case of failure.
+ */
+static int rave_sp_eeprom_io(struct rave_sp_eeprom *eeprom,
+			     enum rave_sp_eeprom_access_type type,
+			     u16 idx,
+			     struct rave_sp_eeprom_page *page)
+{
+	const bool is_write = type == RAVE_SP_EEPROM_WRITE;
+	const unsigned int data_size = is_write ? sizeof(page->data) : 0;
+	const unsigned int cmd_size = eeprom->header_size + data_size;
+	const unsigned int rsp_size =
+		is_write ? sizeof(*page) - sizeof(page->data) : sizeof(*page);
+	unsigned int offset = 0;
+	u8 cmd[cmd_size];
+	int ret;
+
+	cmd[offset++] = eeprom->address;
+	cmd[offset++] = 0;
+	cmd[offset++] = type;
+	cmd[offset++] = idx;
+
+	/*
+	 * If there's still room in this command's header it means we
+	 * are talkin to EEPROM that uses 16-bit page numbers and we
+	 * have to specify index's MSB in payload as well.
+	 */
+	if (offset < eeprom->header_size)
+		cmd[offset++] = idx >> 8;
+	/*
+	 * Copy our data to write to command buffer first. In case of
+	 * a read data_size should be zero and memcpy would become a
+	 * no-op
+	 */
+	memcpy(&cmd[offset], page->data, data_size);
+
+	ret = rave_sp_exec(eeprom->sp, cmd, cmd_size, page, rsp_size);
+	if (ret)
+		return ret;
+
+	if (page->type != type)
+		return -EPROTO;
+
+	if (!page->success)
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * rave_sp_eeprom_page_access - Access single EEPROM page
+ *
+ * @eeprom:	EEPROM device to access
+ * @type:	Access type to perform (read or write)
+ * @offset:	Offset within EEPROM to access
+ * @data:	Data buffer
+ * @data_len:	Size of the data buffer
+ *
+ * This function performs a generic access to a single page or a
+ * portion thereof. Requested access MUST NOT cross the EEPROM page
+ * boundary.
+ *
+ * Returns zero in case of success or negative error code in
+ * case of failure.
+ */
+static int
+rave_sp_eeprom_page_access(struct rave_sp_eeprom *eeprom,
+			   enum rave_sp_eeprom_access_type type,
+			   unsigned int offset, u8 *data,
+			   size_t data_len)
+{
+	const unsigned int page_offset = offset % RAVE_SP_EEPROM_PAGE_SIZE;
+	const unsigned int page_nr     = offset / RAVE_SP_EEPROM_PAGE_SIZE;
+	struct rave_sp_eeprom_page page;
+	int ret;
+
+	/*
+	 * This function will not work if data access we've been asked
+	 * to do is crossing EEPROM page boundary. Normally this
+	 * should never happen and getting here would indicate a bug
+	 * in the code.
+	 */
+	if (WARN_ON(data_len > sizeof(page.data) - page_offset))
+		return -EINVAL;
+
+	if (type == RAVE_SP_EEPROM_WRITE) {
+		/*
+		 * If doing a partial write we need to do a read first
+		 * to fill the rest of the page with correct data.
+		 */
+		if (data_len < RAVE_SP_EEPROM_PAGE_SIZE) {
+			ret = rave_sp_eeprom_io(eeprom, RAVE_SP_EEPROM_READ,
+						page_nr, &page);
+			if (ret)
+				return ret;
+		}
+
+		memcpy(&page.data[page_offset], data, data_len);
+	}
+
+	ret = rave_sp_eeprom_io(eeprom, type, page_nr, &page);
+	if (ret)
+		return ret;
+
+	/*
+	 * Since we receive the result of the read via 'page.data'
+	 * buffer we need to copy that to 'data'
+	 */
+	if (type == RAVE_SP_EEPROM_READ)
+		memcpy(data, &page.data[page_offset], data_len);
+
+	return 0;
+}
+
+/**
+ * rave_sp_eeprom_access - Access EEPROM data
+ *
+ * @eeprom:	EEPROM device to access
+ * @type:	Access type to perform (read or write)
+ * @offset:	Offset within EEPROM to access
+ * @data:	Data buffer
+ * @data_len:	Size of the data buffer
+ *
+ * This function performs a generic access (either read or write) at
+ * arbitrary offset (not necessary page aligned) of arbitrary length
+ * (is not constrained by EEPROM page size).
+ *
+ * Returns zero in case of success or negative error code in case of
+ * failure.
+ */
+static int rave_sp_eeprom_access(struct rave_sp_eeprom *eeprom,
+				 enum rave_sp_eeprom_access_type type,
+				 unsigned int offset, u8 *data,
+				 unsigned int data_len)
+{
+	unsigned int residue;
+	unsigned int chunk;
+	unsigned int head;
+	int ret;
+
+	mutex_lock(&eeprom->mutex);
+
+	head    = offset % RAVE_SP_EEPROM_PAGE_SIZE;
+	residue = data_len;
+
+	do {
+		/*
+		 * First iteration, if we are doing an access that is
+		 * not 32-byte aligned, we need to access only data up
+		 * to a page boundary to avoid corssing it in
+		 * rave_sp_eeprom_page_access()
+		 */
+		if (unlikely(head)) {
+			chunk = RAVE_SP_EEPROM_PAGE_SIZE - head;
+			/*
+			 * This can only happen once per
+			 * rave_sp_eeprom_access() call, so we set
+			 * head to zero to process all the other
+			 * iterations normally.
+			 */
+			head  = 0;
+		} else {
+			chunk = RAVE_SP_EEPROM_PAGE_SIZE;
+		}
+
+		/*
+		 * We should never read more that 'residue' bytes
+		 */
+		chunk = min(chunk, residue);
+		ret = rave_sp_eeprom_page_access(eeprom, type, offset,
+						 data, chunk);
+		if (ret)
+			goto out;
+
+		residue -= chunk;
+		offset  += chunk;
+		data    += chunk;
+	} while (residue);
+out:
+	mutex_unlock(&eeprom->mutex);
+	return ret;
+}
+
+static int rave_sp_eeprom_reg_read(void *eeprom, unsigned int offset,
+				   void *val, size_t bytes)
+{
+	return rave_sp_eeprom_access(eeprom, RAVE_SP_EEPROM_READ,
+				     offset, val, bytes);
+}
+
+static int rave_sp_eeprom_reg_write(void *eeprom, unsigned int offset,
+				    void *val, size_t bytes)
+{
+	return rave_sp_eeprom_access(eeprom, RAVE_SP_EEPROM_WRITE,
+				     offset, val, bytes);
+}
+
+static int rave_sp_eeprom_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rave_sp *sp = dev_get_drvdata(dev->parent);
+	struct device_node *np = dev->of_node;
+	struct nvmem_config config = { 0 };
+	struct rave_sp_eeprom *eeprom;
+	struct nvmem_device *nvmem;
+	u32 reg[2], size;
+
+	if (of_property_read_u32_array(np, "reg", reg, ARRAY_SIZE(reg))) {
+		dev_err(dev, "Failed to parse \"reg\" property\n");
+		return -EINVAL;
+	}
+
+	size = reg[1];
+	/*
+	 * Per ICD, we have no more than 2 bytes to specify EEPROM
+	 * page.
+	 */
+	if (size > U16_MAX * RAVE_SP_EEPROM_PAGE_SIZE) {
+		dev_err(dev, "Specified size is too big\n");
+		return -EINVAL;
+	}
+
+	eeprom = devm_kzalloc(dev, sizeof(*eeprom), GFP_KERNEL);
+	if (!eeprom)
+		return -ENOMEM;
+
+	eeprom->address = reg[0];
+	eeprom->sp      = sp;
+	eeprom->dev     = dev;
+
+	if (size > SZ_8K)
+		eeprom->header_size = RAVE_SP_EEPROM_HEADER_BIG;
+	else
+		eeprom->header_size = RAVE_SP_EEPROM_HEADER_SMALL;
+
+	mutex_init(&eeprom->mutex);
+
+	config.id		= -1;
+	of_property_read_string(np, "zii,eeprom-name", &config.name);
+	config.priv		= eeprom;
+	config.dev		= dev;
+	config.size		= size;
+	config.reg_read		= rave_sp_eeprom_reg_read;
+	config.reg_write	= rave_sp_eeprom_reg_write;
+	config.word_size	= 1;
+	config.stride		= 1;
+
+	nvmem = devm_nvmem_register(dev, &config);
+
+	return PTR_ERR_OR_ZERO(nvmem);
+}
+
+static const struct of_device_id rave_sp_eeprom_of_match[] = {
+	{ .compatible = "zii,rave-sp-eeprom" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, rave_sp_eeprom_of_match);
+
+static struct platform_driver rave_sp_eeprom_driver = {
+	.probe = rave_sp_eeprom_probe,
+	.driver	= {
+		.name = KBUILD_MODNAME,
+		.of_match_table = rave_sp_eeprom_of_match,
+	},
+};
+module_platform_driver(rave_sp_eeprom_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Andrey Vostrikov <andrey.vostrikov@cogentembedded.com>");
+MODULE_AUTHOR("Nikita Yushchenko <nikita.yoush@cogentembedded.com>");
+MODULE_AUTHOR("Andrey Smirnov <andrew.smirnov@gmail.com>");
+MODULE_DESCRIPTION("RAVE SP EEPROM driver");
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 064c818105bd..33d85511d790 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -76,6 +76,8 @@ int of_device_add(struct platform_device *ofdev)
  * of_dma_configure - Setup DMA configuration
  * @dev:	Device to apply DMA configuration
  * @np:		Pointer to OF node having DMA configuration
+ * @force_dma:  Whether device is to be set up by of_dma_configure() even if
+ *		DMA capability is not explicitly described by firmware.
  *
  * Try to get devices's DMA configuration from DT and update it
  * accordingly.
@@ -84,7 +86,7 @@ int of_device_add(struct platform_device *ofdev)
  * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events
  * to fix up DMA configuration.
  */
-int of_dma_configure(struct device *dev, struct device_node *np)
+int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 {
 	u64 dma_addr, paddr, size = 0;
 	int ret;
@@ -100,7 +102,7 @@ int of_dma_configure(struct device *dev, struct device_node *np)
 		 * DMA configuration regardless of whether "dma-ranges" is
 		 * correctly specified or not.
 		 */
-		if (!dev->bus->force_dma)
+		if (!force_dma)
 			return ret == -ENODEV ? 0 : ret;
 
 		dma_addr = offset = 0;
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 84aa9d676375..6da20b9688f7 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -942,7 +942,7 @@ int __init early_init_dt_scan_chosen_stdout(void)
 	int offset;
 	const char *p, *q, *options = NULL;
 	int l;
-	const struct earlycon_id *match;
+	const struct earlycon_id **p_match;
 	const void *fdt = initial_boot_params;
 
 	offset = fdt_path_offset(fdt, "/chosen");
@@ -969,7 +969,10 @@ int __init early_init_dt_scan_chosen_stdout(void)
 		return 0;
 	}
 
-	for (match = __earlycon_table; match < __earlycon_table_end; match++) {
+	for (p_match = __earlycon_table; p_match < __earlycon_table_end;
+	     p_match++) {
+		const struct earlycon_id *match = *p_match;
+
 		if (!match->compatible[0])
 			continue;
 
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 9a4f4246231d..895c83e0c7b6 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -353,7 +353,7 @@ int of_reserved_mem_device_init_by_idx(struct device *dev,
 		/* ensure that dma_ops is set for virtual devices
 		 * using reserved memory
 		 */
-		of_dma_configure(dev, np);
+		of_dma_configure(dev, np, true);
 
 		dev_info(dev, "assigned reserved memory node %s\n", rmem->name);
 	} else {
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index b35fe88f1851..7baa53e5b1d7 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -102,12 +102,28 @@ static DEFINE_IDR(ovcs_idr);
 
 static BLOCKING_NOTIFIER_HEAD(overlay_notify_chain);
 
+/**
+ * of_overlay_notifier_register() - Register notifier for overlay operations
+ * @nb:		Notifier block to register
+ *
+ * Register for notification on overlay operations on device tree nodes. The
+ * reported actions definied by @of_reconfig_change. The notifier callback
+ * furthermore receives a pointer to the affected device tree node.
+ *
+ * Note that a notifier callback is not supposed to store pointers to a device
+ * tree node or its content beyond @OF_OVERLAY_POST_REMOVE corresponding to the
+ * respective node it received.
+ */
 int of_overlay_notifier_register(struct notifier_block *nb)
 {
 	return blocking_notifier_chain_register(&overlay_notify_chain, nb);
 }
 EXPORT_SYMBOL_GPL(of_overlay_notifier_register);
 
+/**
+ * of_overlay_notifier_register() - Unregister notifier for overlay operations
+ * @nb:		Notifier block to unregister
+ */
 int of_overlay_notifier_unregister(struct notifier_block *nb)
 {
 	return blocking_notifier_chain_unregister(&overlay_notify_chain, nb);
@@ -671,17 +687,13 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs)
 		of_node_put(ovcs->fragments[i].overlay);
 	}
 	kfree(ovcs->fragments);
-
 	/*
-	 * TODO
-	 *
-	 * would like to: kfree(ovcs->overlay_tree);
-	 * but can not since drivers may have pointers into this data
-	 *
-	 * would like to: kfree(ovcs->fdt);
-	 * but can not since drivers may have pointers into this data
+	 * There should be no live pointers into ovcs->overlay_tree and
+	 * ovcs->fdt due to the policy that overlay notifiers are not allowed
+	 * to retain pointers into the overlay devicetree.
 	 */
-
+	kfree(ovcs->overlay_tree);
+	kfree(ovcs->fdt);
 	kfree(ovcs);
 }
 
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 92fa94a6dcc1..ab2f3fead6b1 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -33,8 +33,6 @@ LIST_HEAD(opp_tables);
 /* Lock to allow exclusive modification to the device and opp lists */
 DEFINE_MUTEX(opp_table_lock);
 
-static void dev_pm_opp_get(struct dev_pm_opp *opp);
-
 static struct opp_device *_find_opp_dev(const struct device *dev,
 					struct opp_table *opp_table)
 {
@@ -281,6 +279,23 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 
+int _get_opp_count(struct opp_table *opp_table)
+{
+	struct dev_pm_opp *opp;
+	int count = 0;
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(opp, &opp_table->opp_list, node) {
+		if (opp->available)
+			count++;
+	}
+
+	mutex_unlock(&opp_table->lock);
+
+	return count;
+}
+
 /**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table
  * @dev:	device for which we do this operation
@@ -291,25 +306,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
 	struct opp_table *opp_table;
-	struct dev_pm_opp *temp_opp;
-	int count = 0;
+	int count;
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		count = PTR_ERR(opp_table);
 		dev_dbg(dev, "%s: OPP table not found (%d)\n",
 			__func__, count);
-		return count;
-	}
-
-	mutex_lock(&opp_table->lock);
-
-	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
-		if (temp_opp->available)
-			count++;
+		return 0;
 	}
 
-	mutex_unlock(&opp_table->lock);
+	count = _get_opp_count(opp_table);
 	dev_pm_opp_put_opp_table(opp_table);
 
 	return count;
@@ -892,7 +899,7 @@ static void _opp_kref_release(struct kref *kref)
 	dev_pm_opp_put_opp_table(opp_table);
 }
 
-static void dev_pm_opp_get(struct dev_pm_opp *opp)
+void dev_pm_opp_get(struct dev_pm_opp *opp)
 {
 	kref_get(&opp->kref);
 }
@@ -985,22 +992,11 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	return true;
 }
 
-/*
- * Returns:
- * 0: On success. And appropriate error message for duplicate OPPs.
- * -EBUSY: For OPP with same freq/volt and is available. The callers of
- *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
- *  sure we don't print error messages unnecessarily if different parts of
- *  kernel try to initialize the OPP table.
- * -EEXIST: For OPP with same freq but different volt or is unavailable. This
- *  should be considered an error by the callers of _opp_add().
- */
-int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
-	     struct opp_table *opp_table)
+static int _opp_is_duplicate(struct device *dev, struct dev_pm_opp *new_opp,
+			     struct opp_table *opp_table,
+			     struct list_head **head)
 {
 	struct dev_pm_opp *opp;
-	struct list_head *head;
-	int ret;
 
 	/*
 	 * Insert new OPP in order of increasing frequency and discard if
@@ -1010,17 +1006,14 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	 * loop, don't replace it with head otherwise it will become an infinite
 	 * loop.
 	 */
-	mutex_lock(&opp_table->lock);
-	head = &opp_table->opp_list;
-
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (new_opp->rate > opp->rate) {
-			head = &opp->node;
+			*head = &opp->node;
 			continue;
 		}
 
 		if (new_opp->rate < opp->rate)
-			break;
+			return 0;
 
 		/* Duplicate OPPs */
 		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
@@ -1029,15 +1022,39 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 			 new_opp->supplies[0].u_volt, new_opp->available);
 
 		/* Should we compare voltages for all regulators here ? */
-		ret = opp->available &&
-		      new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
-
-		mutex_unlock(&opp_table->lock);
-		return ret;
+		return opp->available &&
+		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
 	}
 
-	if (opp_table->get_pstate)
-		new_opp->pstate = opp_table->get_pstate(dev, new_opp->rate);
+	return 0;
+}
+
+/*
+ * Returns:
+ * 0: On success. And appropriate error message for duplicate OPPs.
+ * -EBUSY: For OPP with same freq/volt and is available. The callers of
+ *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
+ *  sure we don't print error messages unnecessarily if different parts of
+ *  kernel try to initialize the OPP table.
+ * -EEXIST: For OPP with same freq but different volt or is unavailable. This
+ *  should be considered an error by the callers of _opp_add().
+ */
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+	     struct opp_table *opp_table, bool rate_not_available)
+{
+	struct list_head *head;
+	int ret;
+
+	mutex_lock(&opp_table->lock);
+	head = &opp_table->opp_list;
+
+	if (likely(!rate_not_available)) {
+		ret = _opp_is_duplicate(dev, new_opp, opp_table, &head);
+		if (ret) {
+			mutex_unlock(&opp_table->lock);
+			return ret;
+		}
+	}
 
 	list_add(&new_opp->node, head);
 	mutex_unlock(&opp_table->lock);
@@ -1104,7 +1121,7 @@ int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
-	ret = _opp_add(dev, new_opp, opp_table);
+	ret = _opp_add(dev, new_opp, opp_table, false);
 	if (ret) {
 		/* Don't return error for duplicate OPPs */
 		if (ret == -EBUSY)
@@ -1140,7 +1157,6 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
 			const u32 *versions, unsigned int count)
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	opp_table = dev_pm_opp_get_opp_table(dev);
 	if (!opp_table)
@@ -1149,29 +1165,20 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	/* Do we already have a version hierarchy associated with opp_table? */
-	if (opp_table->supported_hw) {
-		dev_err(dev, "%s: Already have supported hardware list\n",
-			__func__);
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the property ? */
+	if (opp_table->supported_hw)
+		return opp_table;
 
 	opp_table->supported_hw = kmemdup(versions, count * sizeof(*versions),
 					GFP_KERNEL);
 	if (!opp_table->supported_hw) {
-		ret = -ENOMEM;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	opp_table->supported_hw_count = count;
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
 
@@ -1188,12 +1195,6 @@ void dev_pm_opp_put_supported_hw(struct opp_table *opp_table)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	if (!opp_table->supported_hw) {
-		pr_err("%s: Doesn't have supported hardware list\n",
-		       __func__);
-		return;
-	}
-
 	kfree(opp_table->supported_hw);
 	opp_table->supported_hw = NULL;
 	opp_table->supported_hw_count = 0;
@@ -1215,7 +1216,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
 struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	opp_table = dev_pm_opp_get_opp_table(dev);
 	if (!opp_table)
@@ -1224,26 +1224,17 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	/* Do we already have a prop-name associated with opp_table? */
-	if (opp_table->prop_name) {
-		dev_err(dev, "%s: Already have prop-name %s\n", __func__,
-			opp_table->prop_name);
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the property ? */
+	if (opp_table->prop_name)
+		return opp_table;
 
 	opp_table->prop_name = kstrdup(name, GFP_KERNEL);
 	if (!opp_table->prop_name) {
-		ret = -ENOMEM;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
 
@@ -1260,11 +1251,6 @@ void dev_pm_opp_put_prop_name(struct opp_table *opp_table)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	if (!opp_table->prop_name) {
-		pr_err("%s: Doesn't have a prop-name\n", __func__);
-		return;
-	}
-
 	kfree(opp_table->prop_name);
 	opp_table->prop_name = NULL;
 
@@ -1334,11 +1320,9 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 		goto err;
 	}
 
-	/* Already have regulators set */
-	if (opp_table->regulators) {
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the regulators ? */
+	if (opp_table->regulators)
+		return opp_table;
 
 	opp_table->regulators = kmalloc_array(count,
 					      sizeof(*opp_table->regulators),
@@ -1392,10 +1376,8 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 {
 	int i;
 
-	if (!opp_table->regulators) {
-		pr_err("%s: Doesn't have regulators set\n", __func__);
-		return;
-	}
+	if (!opp_table->regulators)
+		goto put_opp_table;
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1409,6 +1391,7 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
 
+put_opp_table:
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
@@ -1494,7 +1477,6 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 			int (*set_opp)(struct dev_pm_set_opp_data *data))
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	if (!set_opp)
 		return ERR_PTR(-EINVAL);
@@ -1505,24 +1487,15 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	/* Already have custom set_opp helper */
-	if (WARN_ON(opp_table->set_opp)) {
-		ret = -EBUSY;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-EBUSY);
 	}
 
-	opp_table->set_opp = set_opp;
+	/* Another CPU that shares the OPP table has set the helper ? */
+	if (!opp_table->set_opp)
+		opp_table->set_opp = set_opp;
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
 
@@ -1535,97 +1508,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
  */
 void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table)
 {
-	if (!opp_table->set_opp) {
-		pr_err("%s: Doesn't have custom set_opp helper set\n",
-		       __func__);
-		return;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	opp_table->set_opp = NULL;
-
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_set_opp_helper);
 
 /**
- * dev_pm_opp_register_get_pstate_helper() - Register get_pstate() helper.
- * @dev: Device for which the helper is getting registered.
- * @get_pstate: Helper.
- *
- * TODO: Remove this callback after the same information is available via Device
- * Tree.
- *
- * This allows a platform to initialize the performance states of individual
- * OPPs for its devices, until we get similar information directly from DT.
- *
- * This must be called before the OPPs are initialized for the device.
- */
-struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev,
-		int (*get_pstate)(struct device *dev, unsigned long rate))
-{
-	struct opp_table *opp_table;
-	int ret;
-
-	if (!get_pstate)
-		return ERR_PTR(-EINVAL);
-
-	opp_table = dev_pm_opp_get_opp_table(dev);
-	if (!opp_table)
-		return ERR_PTR(-ENOMEM);
-
-	/* This should be called before OPPs are initialized */
-	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	/* Already have genpd_performance_state set */
-	if (WARN_ON(opp_table->genpd_performance_state)) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	opp_table->genpd_performance_state = true;
-	opp_table->get_pstate = get_pstate;
-
-	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_register_get_pstate_helper);
-
-/**
- * dev_pm_opp_unregister_get_pstate_helper() - Releases resources blocked for
- *					   get_pstate() helper
- * @opp_table: OPP table returned from dev_pm_opp_register_get_pstate_helper().
- *
- * Release resources blocked for platform specific get_pstate() helper.
- */
-void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table)
-{
-	if (!opp_table->genpd_performance_state) {
-		pr_err("%s: Doesn't have performance states set\n",
-		       __func__);
-		return;
-	}
-
-	/* Make sure there are no concurrent readers while updating opp_table */
-	WARN_ON(!list_empty(&opp_table->opp_list));
-
-	opp_table->genpd_performance_state = false;
-	opp_table->get_pstate = NULL;
-
-	dev_pm_opp_put_opp_table(opp_table);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_get_pstate_helper);
-
-/**
  * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c
index b03c03576a62..e6828e5f81b0 100644
--- a/drivers/opp/debugfs.c
+++ b/drivers/opp/debugfs.c
@@ -77,10 +77,21 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 {
 	struct dentry *pdentry = opp_table->dentry;
 	struct dentry *d;
+	unsigned long id;
 	char name[25];	/* 20 chars for 64 bit value + 5 (opp:\0) */
 
-	/* Rate is unique to each OPP, use it to give opp-name */
-	snprintf(name, sizeof(name), "opp:%lu", opp->rate);
+	/*
+	 * Get directory name for OPP.
+	 *
+	 * - Normally rate is unique to each OPP, use it to get unique opp-name.
+	 * - For some devices rate isn't available, use index instead.
+	 */
+	if (likely(opp->rate))
+		id = opp->rate;
+	else
+		id = _get_opp_count(opp_table);
+
+	snprintf(name, sizeof(name), "opp:%lu", id);
 
 	/* Create per-opp directory */
 	d = debugfs_create_dir(name, pdentry);
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index cb716aa2f44b..7af0ddec936b 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/device.h>
 #include <linux/of_device.h>
+#include <linux/pm_domain.h>
 #include <linux/slab.h>
 #include <linux/export.h>
 
@@ -250,20 +251,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
 /* Returns opp descriptor node for a device node, caller must
  * do of_node_put() */
-static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np)
+static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np,
+						     int index)
 {
-	/*
-	 * There should be only ONE phandle present in "operating-points-v2"
-	 * property.
-	 */
-
-	return of_parse_phandle(np, "operating-points-v2", 0);
+	/* "operating-points-v2" can be an array for power domain providers */
+	return of_parse_phandle(np, "operating-points-v2", index);
 }
 
 /* Returns opp descriptor node for a device, caller must do of_node_put() */
 struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
 {
-	return _opp_of_get_opp_desc_node(dev->of_node);
+	return _opp_of_get_opp_desc_node(dev->of_node, 0);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
 
@@ -289,9 +287,10 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 			      struct device_node *np)
 {
 	struct dev_pm_opp *new_opp;
-	u64 rate;
+	u64 rate = 0;
 	u32 val;
 	int ret;
+	bool rate_not_available = false;
 
 	new_opp = _opp_allocate(opp_table);
 	if (!new_opp)
@@ -299,8 +298,21 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 
 	ret = of_property_read_u64(np, "opp-hz", &rate);
 	if (ret < 0) {
-		dev_err(dev, "%s: opp-hz not found\n", __func__);
-		goto free_opp;
+		/* "opp-hz" is optional for devices like power domains. */
+		if (!of_find_property(dev->of_node, "#power-domain-cells",
+				      NULL)) {
+			dev_err(dev, "%s: opp-hz not found\n", __func__);
+			goto free_opp;
+		}
+
+		rate_not_available = true;
+	} else {
+		/*
+		 * Rate is defined as an unsigned long in clk API, and so
+		 * casting explicitly to its type. Must be fixed once rate is 64
+		 * bit guaranteed in clk API.
+		 */
+		new_opp->rate = (unsigned long)rate;
 	}
 
 	/* Check if the OPP supports hardware's hierarchy of versions or not */
@@ -309,12 +321,6 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 		goto free_opp;
 	}
 
-	/*
-	 * Rate is defined as an unsigned long in clk API, and so casting
-	 * explicitly to its type. Must be fixed once rate is 64 bit
-	 * guaranteed in clk API.
-	 */
-	new_opp->rate = (unsigned long)rate;
 	new_opp->turbo = of_property_read_bool(np, "turbo-mode");
 
 	new_opp->np = np;
@@ -324,11 +330,13 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 	if (!of_property_read_u32(np, "clock-latency-ns", &val))
 		new_opp->clock_latency_ns = val;
 
+	new_opp->pstate = of_genpd_opp_to_performance_state(dev, np);
+
 	ret = opp_parse_supplies(new_opp, dev, opp_table);
 	if (ret)
 		goto free_opp;
 
-	ret = _opp_add(dev, new_opp, opp_table);
+	ret = _opp_add(dev, new_opp, opp_table, rate_not_available);
 	if (ret) {
 		/* Don't return error for duplicate OPPs */
 		if (ret == -EBUSY)
@@ -374,7 +382,8 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 {
 	struct device_node *np;
 	struct opp_table *opp_table;
-	int ret = 0, count = 0;
+	int ret = 0, count = 0, pstate_count = 0;
+	struct dev_pm_opp *opp;
 
 	opp_table = _managed_opp(opp_np);
 	if (opp_table) {
@@ -408,6 +417,20 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 		goto put_opp_table;
 	}
 
+	list_for_each_entry(opp, &opp_table->opp_list, node)
+		pstate_count += !!opp->pstate;
+
+	/* Either all or none of the nodes shall have performance state set */
+	if (pstate_count && pstate_count != count) {
+		dev_err(dev, "Not all nodes have performance state set (%d: %d)\n",
+			count, pstate_count);
+		ret = -ENOENT;
+		goto put_opp_table;
+	}
+
+	if (pstate_count)
+		opp_table->genpd_performance_state = true;
+
 	opp_table->np = opp_np;
 	if (of_property_read_bool(opp_np, "opp-shared"))
 		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
@@ -509,6 +532,54 @@ int dev_pm_opp_of_add_table(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
 
+/**
+ * dev_pm_opp_of_add_table_indexed() - Initialize indexed opp table from device tree
+ * @dev:	device pointer used to lookup OPP table.
+ * @index:	Index number.
+ *
+ * Register the initial OPP table with the OPP library for given device only
+ * using the "operating-points-v2" property.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ * -EINVAL	when invalid entries are found in opp-v2 table
+ */
+int dev_pm_opp_of_add_table_indexed(struct device *dev, int index)
+{
+	struct device_node *opp_np;
+	int ret, count;
+
+again:
+	opp_np = _opp_of_get_opp_desc_node(dev->of_node, index);
+	if (!opp_np) {
+		/*
+		 * If only one phandle is present, then the same OPP table
+		 * applies for all index requests.
+		 */
+		count = of_count_phandle_with_args(dev->of_node,
+						   "operating-points-v2", NULL);
+		if (count == 1 && index) {
+			index = 0;
+			goto again;
+		}
+
+		return -ENODEV;
+	}
+
+	ret = _of_add_opp_table_v2(dev, opp_np);
+	of_node_put(opp_np);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_indexed);
+
 /* CPU device specific helpers */
 
 /**
@@ -613,7 +684,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 		}
 
 		/* Get OPP descriptor node */
-		tmp_np = _opp_of_get_opp_desc_node(cpu_np);
+		tmp_np = _opp_of_get_opp_desc_node(cpu_np, 0);
 		of_node_put(cpu_np);
 		if (!tmp_np) {
 			pr_err("%pOF: Couldn't find opp node\n", cpu_np);
@@ -633,3 +704,76 @@ put_cpu_node:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_sharing_cpus);
+
+/**
+ * of_dev_pm_opp_find_required_opp() - Search for required OPP.
+ * @dev: The device whose OPP node is referenced by the 'np' DT node.
+ * @np: Node that contains the "required-opps" property.
+ *
+ * Returns the OPP of the device 'dev', whose phandle is present in the "np"
+ * node. Although the "required-opps" property supports having multiple
+ * phandles, this helper routine only parses the very first phandle in the list.
+ *
+ * Return: Matching opp, else returns ERR_PTR in case of error and should be
+ * handled using IS_ERR.
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev,
+						   struct device_node *np)
+{
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+	struct device_node *required_np;
+	struct opp_table *opp_table;
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
+
+	required_np = of_parse_phandle(np, "required-opps", 0);
+	if (unlikely(!required_np)) {
+		dev_err(dev, "Unable to parse required-opps\n");
+		goto put_opp_table;
+	}
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->np == required_np) {
+			opp = temp_opp;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
+			break;
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+
+	of_node_put(required_np);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(of_dev_pm_opp_find_required_opp);
+
+/**
+ * dev_pm_opp_get_of_node() - Gets the DT node corresponding to an opp
+ * @opp:	opp for which DT node has to be returned for
+ *
+ * Return: DT node corresponding to the opp, else 0 on success.
+ *
+ * The caller needs to put the node with of_node_put() after using it.
+ */
+struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp)
+{
+	if (IS_ERR_OR_NULL(opp)) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return NULL;
+	}
+
+	return of_node_get(opp->np);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 4d00061648a3..7c540fd063b2 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -140,7 +140,6 @@ enum opp_table_access {
  * @genpd_performance_state: Device's power domain support performance state.
  * @set_opp: Platform specific set_opp callback
  * @set_opp_data: Data to be passed to set_opp callback
- * @get_pstate: Platform specific get_pstate callback
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -178,7 +177,6 @@ struct opp_table {
 
 	int (*set_opp)(struct dev_pm_set_opp_data *data);
 	struct dev_pm_set_opp_data *set_opp_data;
-	int (*get_pstate)(struct device *dev, unsigned long rate);
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -187,14 +185,16 @@ struct opp_table {
 };
 
 /* Routines internal to opp core */
+void dev_pm_opp_get(struct dev_pm_opp *opp);
 void _get_opp_table_kref(struct opp_table *opp_table);
+int _get_opp_count(struct opp_table *opp_table);
 struct opp_table *_find_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
 void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all);
 void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
 struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table);
 void _opp_free(struct dev_pm_opp *opp);
-int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table, bool rate_not_available);
 int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
 struct opp_table *_add_opp_table(struct device *dev);
diff --git a/drivers/parisc/Kconfig b/drivers/parisc/Kconfig
index 3a102a84d637..5a48b5606110 100644
--- a/drivers/parisc/Kconfig
+++ b/drivers/parisc/Kconfig
@@ -103,11 +103,6 @@ config IOMMU_SBA
 	depends on PCI_LBA
 	default PCI_LBA
 
-config IOMMU_HELPER
-	bool
-	depends on IOMMU_SBA || IOMMU_CCIO
-	default y
-
 source "drivers/pcmcia/Kconfig"
 
 endmenu
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index acba1f56af3e..614823617b8b 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -1108,19 +1108,6 @@ static int ccio_proc_info(struct seq_file *m, void *p)
 	return 0;
 }
 
-static int ccio_proc_info_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, &ccio_proc_info, NULL);
-}
-
-static const struct file_operations ccio_proc_info_fops = {
-	.owner = THIS_MODULE,
-	.open = ccio_proc_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 static int ccio_proc_bitmap_info(struct seq_file *m, void *p)
 {
 	struct ioc *ioc = ioc_list;
@@ -1135,19 +1122,6 @@ static int ccio_proc_bitmap_info(struct seq_file *m, void *p)
 
 	return 0;
 }
-
-static int ccio_proc_bitmap_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, &ccio_proc_bitmap_info, NULL);
-}
-
-static const struct file_operations ccio_proc_bitmap_fops = {
-	.owner = THIS_MODULE,
-	.open = ccio_proc_bitmap_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
 #endif /* CONFIG_PROC_FS */
 
 /**
@@ -1195,7 +1169,7 @@ void * ccio_get_iommu(const struct parisc_device *dev)
  * to/from certain pages.  To avoid this happening, we mark these pages
  * as `used', and ensure that nothing will try to allocate from them.
  */
-void ccio_cujo20_fixup(struct parisc_device *cujo, u32 iovp)
+void __init ccio_cujo20_fixup(struct parisc_device *cujo, u32 iovp)
 {
 	unsigned int idx;
 	struct parisc_device *dev = parisc_parent(cujo);
@@ -1263,7 +1237,7 @@ static struct parisc_driver ccio_driver __refdata = {
  * I/O Page Directory, the resource map, and initalizing the
  * U2/Uturn chip into virtual mode.
  */
-static void
+static void __init
 ccio_ioc_init(struct ioc *ioc)
 {
 	int i;
@@ -1589,15 +1563,13 @@ static int __init ccio_probe(struct parisc_device *dev)
 
 #ifdef CONFIG_PROC_FS
 	if (ioc_count == 0) {
-		proc_create(MODULE_NAME, 0, proc_runway_root,
-			    &ccio_proc_info_fops);
-		proc_create(MODULE_NAME"-bitmap", 0, proc_runway_root,
-			    &ccio_proc_bitmap_fops);
+		proc_create_single(MODULE_NAME, 0, proc_runway_root,
+				ccio_proc_info);
+		proc_create_single(MODULE_NAME"-bitmap", 0, proc_runway_root,
+				ccio_proc_bitmap_info);
 	}
 #endif
 	ioc_count++;
-
-	parisc_has_iommu();
 	return 0;
 }
 
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 0a9c762a70fa..11de0eccf968 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -1864,20 +1864,6 @@ static int sba_proc_info(struct seq_file *m, void *p)
 }
 
 static int
-sba_proc_open(struct inode *i, struct file *f)
-{
-	return single_open(f, &sba_proc_info, NULL);
-}
-
-static const struct file_operations sba_proc_fops = {
-	.owner = THIS_MODULE,
-	.open = sba_proc_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static int
 sba_proc_bitmap_info(struct seq_file *m, void *p)
 {
 	struct sba_device *sba_dev = sba_list;
@@ -1889,20 +1875,6 @@ sba_proc_bitmap_info(struct seq_file *m, void *p)
 
 	return 0;
 }
-
-static int
-sba_proc_bitmap_open(struct inode *i, struct file *f)
-{
-	return single_open(f, &sba_proc_bitmap_info, NULL);
-}
-
-static const struct file_operations sba_proc_bitmap_fops = {
-	.owner = THIS_MODULE,
-	.open = sba_proc_bitmap_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
 #endif /* CONFIG_PROC_FS */
 
 static const struct parisc_device_id sba_tbl[] __initconst = {
@@ -2014,11 +1986,9 @@ static int __init sba_driver_callback(struct parisc_device *dev)
 		break;
 	}
 
-	proc_create("sba_iommu", 0, root, &sba_proc_fops);
-	proc_create("sba_iommu-bitmap", 0, root, &sba_proc_bitmap_fops);
+	proc_create_single("sba_iommu", 0, root, sba_proc_info);
+	proc_create_single("sba_iommu-bitmap", 0, root, sba_proc_bitmap_info);
 #endif
-
-	parisc_has_iommu();
 	return 0;
 }
 
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34b56a8f8480..29a487f31dae 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -5,10 +5,6 @@
 
 source "drivers/pci/pcie/Kconfig"
 
-config PCI_BUS_ADDR_T_64BIT
-	def_bool y if (ARCH_DMA_ADDR_T_64BIT || 64BIT)
-	depends on PCI
-
 config PCI_MSI
 	bool "Message Signaled Interrupts (MSI and MSI-X)"
 	depends on PCI
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index bc2ded4c451f..35b7fc87eac5 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -120,7 +120,7 @@ int devm_request_pci_bus_resources(struct device *dev,
 EXPORT_SYMBOL_GPL(devm_request_pci_bus_resources);
 
 static struct pci_bus_region pci_32_bit = {0, 0xffffffffULL};
-#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 static struct pci_bus_region pci_64_bit = {0,
 				(pci_bus_addr_t) 0xffffffffffffffffULL};
 static struct pci_bus_region pci_high = {(pci_bus_addr_t) 0x100000000ULL,
@@ -230,7 +230,7 @@ int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
 					  resource_size_t),
 		void *alignf_data)
 {
-#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 	int rc;
 
 	if (res->flags & IORESOURCE_MEM_64) {
diff --git a/drivers/pci/dwc/pcie-kirin.c b/drivers/pci/dwc/pcie-kirin.c
index a6b88c7f6e3e..d2970a009eb5 100644
--- a/drivers/pci/dwc/pcie-kirin.c
+++ b/drivers/pci/dwc/pcie-kirin.c
@@ -486,7 +486,7 @@ static int kirin_pcie_probe(struct platform_device *pdev)
 		return ret;
 
 	kirin_pcie->gpio_id_reset = of_get_named_gpio(dev->of_node,
-						      "reset-gpio", 0);
+						      "reset-gpios", 0);
 	if (kirin_pcie->gpio_id_reset < 0)
 		return -ENODEV;
 
diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c
index b04d37b3c5de..9abf549631b4 100644
--- a/drivers/pci/host/pci-aardvark.c
+++ b/drivers/pci/host/pci-aardvark.c
@@ -29,6 +29,7 @@
 #define     PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT	5
 #define     PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE		(0 << 11)
 #define     PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT	12
+#define     PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ		0x2
 #define PCIE_CORE_LINK_CTRL_STAT_REG				0xd0
 #define     PCIE_CORE_LINK_L0S_ENTRY				BIT(0)
 #define     PCIE_CORE_LINK_TRAINING				BIT(5)
@@ -100,7 +101,8 @@
 #define PCIE_ISR1_MASK_REG			(CONTROL_BASE_ADDR + 0x4C)
 #define     PCIE_ISR1_POWER_STATE_CHANGE	BIT(4)
 #define     PCIE_ISR1_FLUSH			BIT(5)
-#define     PCIE_ISR1_ALL_MASK			GENMASK(5, 4)
+#define     PCIE_ISR1_INTX_ASSERT(val)		BIT(8 + (val))
+#define     PCIE_ISR1_ALL_MASK			GENMASK(11, 4)
 #define PCIE_MSI_ADDR_LOW_REG			(CONTROL_BASE_ADDR + 0x50)
 #define PCIE_MSI_ADDR_HIGH_REG			(CONTROL_BASE_ADDR + 0x54)
 #define PCIE_MSI_STATUS_REG			(CONTROL_BASE_ADDR + 0x58)
@@ -172,8 +174,6 @@
 #define PCIE_CONFIG_WR_TYPE0			0xa
 #define PCIE_CONFIG_WR_TYPE1			0xb
 
-/* PCI_BDF shifts 8bit, so we need extra 4bit shift */
-#define PCIE_BDF(dev)				(dev << 4)
 #define PCIE_CONF_BUS(bus)			(((bus) & 0xff) << 20)
 #define PCIE_CONF_DEV(dev)			(((dev) & 0x1f) << 15)
 #define PCIE_CONF_FUNC(fun)			(((fun) & 0x7)	<< 12)
@@ -296,7 +296,8 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE |
 		(7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) |
 		PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE |
-		PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT;
+		(PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ <<
+		 PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT);
 	advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG);
 
 	/* Program PCIe Control 2 to disable strict ordering */
@@ -437,7 +438,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	u32 reg;
 	int ret;
 
-	if (PCI_SLOT(devfn) != 0) {
+	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) {
 		*val = 0xffffffff;
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	}
@@ -456,7 +457,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	advk_writel(pcie, reg, PIO_CTRL);
 
 	/* Program the address registers */
-	reg = PCIE_BDF(devfn) | PCIE_CONF_REG(where);
+	reg = PCIE_CONF_ADDR(bus->number, devfn, where);
 	advk_writel(pcie, reg, PIO_ADDR_LS);
 	advk_writel(pcie, 0, PIO_ADDR_MS);
 
@@ -491,7 +492,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	int offset;
 	int ret;
 
-	if (PCI_SLOT(devfn) != 0)
+	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	if (where % size)
@@ -609,9 +610,9 @@ static void advk_pcie_irq_mask(struct irq_data *d)
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	u32 mask;
 
-	mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
-	mask |= PCIE_ISR0_INTX_ASSERT(hwirq);
-	advk_writel(pcie, mask, PCIE_ISR0_MASK_REG);
+	mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+	mask |= PCIE_ISR1_INTX_ASSERT(hwirq);
+	advk_writel(pcie, mask, PCIE_ISR1_MASK_REG);
 }
 
 static void advk_pcie_irq_unmask(struct irq_data *d)
@@ -620,9 +621,9 @@ static void advk_pcie_irq_unmask(struct irq_data *d)
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	u32 mask;
 
-	mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
-	mask &= ~PCIE_ISR0_INTX_ASSERT(hwirq);
-	advk_writel(pcie, mask, PCIE_ISR0_MASK_REG);
+	mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+	mask &= ~PCIE_ISR1_INTX_ASSERT(hwirq);
+	advk_writel(pcie, mask, PCIE_ISR1_MASK_REG);
 }
 
 static int advk_pcie_irq_map(struct irq_domain *h,
@@ -765,29 +766,35 @@ static void advk_pcie_handle_msi(struct advk_pcie *pcie)
 
 static void advk_pcie_handle_int(struct advk_pcie *pcie)
 {
-	u32 val, mask, status;
+	u32 isr0_val, isr0_mask, isr0_status;
+	u32 isr1_val, isr1_mask, isr1_status;
 	int i, virq;
 
-	val = advk_readl(pcie, PCIE_ISR0_REG);
-	mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
-	status = val & ((~mask) & PCIE_ISR0_ALL_MASK);
+	isr0_val = advk_readl(pcie, PCIE_ISR0_REG);
+	isr0_mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+	isr0_status = isr0_val & ((~isr0_mask) & PCIE_ISR0_ALL_MASK);
+
+	isr1_val = advk_readl(pcie, PCIE_ISR1_REG);
+	isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+	isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK);
 
-	if (!status) {
-		advk_writel(pcie, val, PCIE_ISR0_REG);
+	if (!isr0_status && !isr1_status) {
+		advk_writel(pcie, isr0_val, PCIE_ISR0_REG);
+		advk_writel(pcie, isr1_val, PCIE_ISR1_REG);
 		return;
 	}
 
 	/* Process MSI interrupts */
-	if (status & PCIE_ISR0_MSI_INT_PENDING)
+	if (isr0_status & PCIE_ISR0_MSI_INT_PENDING)
 		advk_pcie_handle_msi(pcie);
 
 	/* Process legacy interrupts */
 	for (i = 0; i < PCI_NUM_INTX; i++) {
-		if (!(status & PCIE_ISR0_INTX_ASSERT(i)))
+		if (!(isr1_status & PCIE_ISR1_INTX_ASSERT(i)))
 			continue;
 
-		advk_writel(pcie, PCIE_ISR0_INTX_ASSERT(i),
-			    PCIE_ISR0_REG);
+		advk_writel(pcie, PCIE_ISR1_INTX_ASSERT(i),
+			    PCIE_ISR1_REG);
 
 		virq = irq_find_mapping(pcie->irq_domain, i);
 		generic_handle_irq(virq);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 30250631efe7..f45b74fcc059 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1434,6 +1434,9 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 {
 	struct irq_domain *domain;
 
+	if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE))
+		info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
+
 	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
 		pci_msi_domain_update_dom_ops(info);
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 6ace47099fc5..18ba62c76480 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -16,6 +16,8 @@
 #include <linux/pm_runtime.h>
 #include <linux/suspend.h>
 #include <linux/kexec.h>
+#include <linux/of_device.h>
+#include <linux/acpi.h>
 #include "pci.h"
 #include "pcie/portdrv.h"
 
@@ -753,10 +755,11 @@ static int pci_pm_suspend(struct device *dev)
 	 * better to resume the device from runtime suspend here.
 	 */
 	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
-	    !pci_dev_keep_suspended(pci_dev))
+	    !pci_dev_keep_suspended(pci_dev)) {
 		pm_runtime_resume(dev);
+		pci_dev->state_saved = false;
+	}
 
-	pci_dev->state_saved = false;
 	if (pm->suspend) {
 		pci_power_t prev = pci_dev->current_state;
 		int error;
@@ -958,10 +961,11 @@ static int pci_pm_freeze(struct device *dev)
 	 * devices should not be touched during freeze/thaw transitions,
 	 * however.
 	 */
-	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
+	if (!dev_pm_smart_suspend_and_suspended(dev)) {
 		pm_runtime_resume(dev);
+		pci_dev->state_saved = false;
+	}
 
-	pci_dev->state_saved = false;
 	if (pm->freeze) {
 		int error;
 
@@ -1576,6 +1580,35 @@ static int pci_bus_num_vf(struct device *dev)
 	return pci_num_vf(to_pci_dev(dev));
 }
 
+/**
+ * pci_dma_configure - Setup DMA configuration
+ * @dev: ptr to dev structure
+ *
+ * Function to update PCI devices's DMA configuration using the same
+ * info from the OF node or ACPI node of host bridge's parent (if any).
+ */
+static int pci_dma_configure(struct device *dev)
+{
+	struct device *bridge;
+	int ret = 0;
+
+	bridge = pci_get_host_bridge_device(to_pci_dev(dev));
+
+	if (IS_ENABLED(CONFIG_OF) && bridge->parent &&
+	    bridge->parent->of_node) {
+		ret = of_dma_configure(dev, bridge->parent->of_node, true);
+	} else if (has_acpi_companion(bridge)) {
+		struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
+		enum dev_dma_attr attr = acpi_get_dma_attr(adev);
+
+		if (attr != DEV_DMA_NOT_SUPPORTED)
+			ret = acpi_dma_configure(dev, attr);
+	}
+
+	pci_put_host_bridge_device(bridge);
+	return ret;
+}
+
 struct bus_type pci_bus_type = {
 	.name		= "pci",
 	.match		= pci_bus_match,
@@ -1588,7 +1621,7 @@ struct bus_type pci_bus_type = {
 	.drv_groups	= pci_drv_groups,
 	.pm		= PCI_PM_OPS_PTR,
 	.num_vf		= pci_bus_num_vf,
-	.force_dma	= true,
+	.dma_configure	= pci_dma_configure,
 };
 EXPORT_SYMBOL(pci_bus_type);
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e597655a5643..e90cf5c32e14 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1910,7 +1910,7 @@ void pci_pme_active(struct pci_dev *dev, bool enable)
 EXPORT_SYMBOL(pci_pme_active);
 
 /**
- * pci_enable_wake - enable PCI device as wakeup event source
+ * __pci_enable_wake - enable PCI device as wakeup event source
  * @dev: PCI device affected
  * @state: PCI state from which device will issue wakeup events
  * @enable: True to enable event generation; false to disable
@@ -1928,7 +1928,7 @@ EXPORT_SYMBOL(pci_pme_active);
  * Error code depending on the platform is returned if both the platform and
  * the native mechanism fail to enable the generation of wake-up events
  */
-int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
+static int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
 {
 	int ret = 0;
 
@@ -1969,6 +1969,23 @@ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
 
 	return ret;
 }
+
+/**
+ * pci_enable_wake - change wakeup settings for a PCI device
+ * @pci_dev: Target device
+ * @state: PCI state from which device will issue wakeup events
+ * @enable: Whether or not to enable event generation
+ *
+ * If @enable is set, check device_may_wakeup() for the device before calling
+ * __pci_enable_wake() for it.
+ */
+int pci_enable_wake(struct pci_dev *pci_dev, pci_power_t state, bool enable)
+{
+	if (enable && !device_may_wakeup(&pci_dev->dev))
+		return -EINVAL;
+
+	return __pci_enable_wake(pci_dev, state, enable);
+}
 EXPORT_SYMBOL(pci_enable_wake);
 
 /**
@@ -1981,9 +1998,9 @@ EXPORT_SYMBOL(pci_enable_wake);
  * should not be called twice in a row to enable wake-up due to PCI PM vs ACPI
  * ordering constraints.
  *
- * This function only returns error code if the device is not capable of
- * generating PME# from both D3_hot and D3_cold, and the platform is unable to
- * enable wake-up power for it.
+ * This function only returns error code if the device is not allowed to wake
+ * up the system from sleep or it is not capable of generating PME# from both
+ * D3_hot and D3_cold and the platform is unable to enable wake-up power for it.
  */
 int pci_wake_from_d3(struct pci_dev *dev, bool enable)
 {
@@ -2008,8 +2025,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
 
 	if (platform_pci_power_manageable(dev)) {
 		/*
-		 * Call the platform to choose the target state of the device
-		 * and enable wake-up from this state if supported.
+		 * Call the platform to find the target state for the device.
 		 */
 		pci_power_t state = platform_pci_choose_state(dev);
 
@@ -2042,8 +2058,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
 	if (wakeup) {
 		/*
 		 * Find the deepest state from which the device can generate
-		 * wake-up events, make it the target state and enable device
-		 * to generate PME#.
+		 * PME#.
 		 */
 		if (dev->pme_support) {
 			while (target_state
@@ -2114,7 +2129,7 @@ int pci_finish_runtime_suspend(struct pci_dev *dev)
 
 	dev->runtime_d3cold = target_state == PCI_D3cold;
 
-	pci_enable_wake(dev, target_state, pci_dev_run_wake(dev));
+	__pci_enable_wake(dev, target_state, pci_dev_run_wake(dev));
 
 	error = pci_set_power_state(dev, target_state);
 
@@ -2138,16 +2153,16 @@ bool pci_dev_run_wake(struct pci_dev *dev)
 {
 	struct pci_bus *bus = dev->bus;
 
-	if (device_can_wakeup(&dev->dev))
-		return true;
-
 	if (!dev->pme_support)
 		return false;
 
 	/* PME-capable in principle, but not from the target power state */
-	if (!pci_pme_capable(dev, pci_target_state(dev, false)))
+	if (!pci_pme_capable(dev, pci_target_state(dev, true)))
 		return false;
 
+	if (device_can_wakeup(&dev->dev))
+		return true;
+
 	while (bus->parent) {
 		struct pci_dev *bridge = bus->self;
 
@@ -5273,11 +5288,11 @@ void pcie_print_link_status(struct pci_dev *dev)
 	bw_avail = pcie_bandwidth_available(dev, &limiting_dev, &speed, &width);
 
 	if (bw_avail >= bw_cap)
-		pci_info(dev, "%u.%03u Gb/s available bandwidth (%s x%d link)\n",
+		pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n",
 			 bw_cap / 1000, bw_cap % 1000,
 			 PCIE_SPEED2STR(speed_cap), width_cap);
 	else
-		pci_info(dev, "%u.%03u Gb/s available bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
+		pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
 			 bw_avail / 1000, bw_avail % 1000,
 			 PCIE_SPEED2STR(speed), width,
 			 limiting_dev ? pci_name(limiting_dev) : "<unknown>",
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 1ee8927a0635..7ac035af39f0 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -435,25 +435,12 @@ int pci_proc_detach_bus(struct pci_bus *bus)
 	return 0;
 }
 
-static int proc_bus_pci_dev_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &proc_bus_pci_devices_op);
-}
-
-static const struct file_operations proc_bus_pci_dev_operations = {
-	.owner		= THIS_MODULE,
-	.open		= proc_bus_pci_dev_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int __init pci_proc_init(void)
 {
 	struct pci_dev *dev = NULL;
 	proc_bus_pci_dir = proc_mkdir("bus/pci", NULL);
-	proc_create("devices", 0, proc_bus_pci_dir,
-		    &proc_bus_pci_dev_operations);
+	proc_create_seq("devices", 0, proc_bus_pci_dir,
+		    &proc_bus_pci_devices_op);
 	proc_initialized = 1;
 	for_each_pci_dev(dev)
 		pci_proc_attach_device(dev);
diff --git a/drivers/phy/mediatek/Kconfig b/drivers/phy/mediatek/Kconfig
index 88ab4e25e34f..8857d00b3c65 100644
--- a/drivers/phy/mediatek/Kconfig
+++ b/drivers/phy/mediatek/Kconfig
@@ -12,3 +12,12 @@ config PHY_MTK_TPHY
 	  different banks layout, the T-PHY with shared banks between
 	  multi-ports is first version, otherwise is second veriosn,
 	  so you can easily distinguish them by banks layout.
+
+config PHY_MTK_XSPHY
+    tristate "MediaTek XS-PHY Driver"
+    depends on ARCH_MEDIATEK && OF
+    select GENERIC_PHY
+    help
+	  Enable this to support the SuperSpeedPlus XS-PHY transceiver for
+	  USB3.1 GEN2 controllers on MediaTek chips. The driver supports
+	  multiple USB2.0, USB3.1 GEN2 ports.
diff --git a/drivers/phy/mediatek/Makefile b/drivers/phy/mediatek/Makefile
index 763a92eefa00..e5074b607d3d 100644
--- a/drivers/phy/mediatek/Makefile
+++ b/drivers/phy/mediatek/Makefile
@@ -3,3 +3,4 @@
 #
 
 obj-$(CONFIG_PHY_MTK_TPHY)		+= phy-mtk-tphy.o
+obj-$(CONFIG_PHY_MTK_XSPHY)		+= phy-mtk-xsphy.o
diff --git a/drivers/phy/mediatek/phy-mtk-xsphy.c b/drivers/phy/mediatek/phy-mtk-xsphy.c
new file mode 100644
index 000000000000..020cd0227397
--- /dev/null
+++ b/drivers/phy/mediatek/phy-mtk-xsphy.c
@@ -0,0 +1,600 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * MediaTek USB3.1 gen2 xsphy Driver
+ *
+ * Copyright (c) 2018 MediaTek Inc.
+ * Author: Chunfeng Yun <chunfeng.yun@mediatek.com>
+ *
+ */
+
+#include <dt-bindings/phy/phy.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+
+/* u2 phy banks */
+#define SSUSB_SIFSLV_MISC		0x000
+#define SSUSB_SIFSLV_U2FREQ		0x100
+#define SSUSB_SIFSLV_U2PHY_COM	0x300
+
+/* u3 phy shared banks */
+#define SSPXTP_SIFSLV_DIG_GLB		0x000
+#define SSPXTP_SIFSLV_PHYA_GLB		0x100
+
+/* u3 phy banks */
+#define SSPXTP_SIFSLV_DIG_LN_TOP	0x000
+#define SSPXTP_SIFSLV_DIG_LN_TX0	0x100
+#define SSPXTP_SIFSLV_DIG_LN_RX0	0x200
+#define SSPXTP_SIFSLV_DIG_LN_DAIF	0x300
+#define SSPXTP_SIFSLV_PHYA_LN		0x400
+
+#define XSP_U2FREQ_FMCR0	((SSUSB_SIFSLV_U2FREQ) + 0x00)
+#define P2F_RG_FREQDET_EN	BIT(24)
+#define P2F_RG_CYCLECNT		GENMASK(23, 0)
+#define P2F_RG_CYCLECNT_VAL(x)	((P2F_RG_CYCLECNT) & (x))
+
+#define XSP_U2FREQ_MMONR0  ((SSUSB_SIFSLV_U2FREQ) + 0x0c)
+
+#define XSP_U2FREQ_FMMONR1	((SSUSB_SIFSLV_U2FREQ) + 0x10)
+#define P2F_RG_FRCK_EN		BIT(8)
+#define P2F_USB_FM_VALID	BIT(0)
+
+#define XSP_USBPHYACR0	((SSUSB_SIFSLV_U2PHY_COM) + 0x00)
+#define P2A0_RG_INTR_EN	BIT(5)
+
+#define XSP_USBPHYACR1		((SSUSB_SIFSLV_U2PHY_COM) + 0x04)
+#define P2A1_RG_INTR_CAL		GENMASK(23, 19)
+#define P2A1_RG_INTR_CAL_VAL(x)	((0x1f & (x)) << 19)
+#define P2A1_RG_VRT_SEL			GENMASK(14, 12)
+#define P2A1_RG_VRT_SEL_VAL(x)	((0x7 & (x)) << 12)
+#define P2A1_RG_TERM_SEL		GENMASK(10, 8)
+#define P2A1_RG_TERM_SEL_VAL(x)	((0x7 & (x)) << 8)
+
+#define XSP_USBPHYACR5		((SSUSB_SIFSLV_U2PHY_COM) + 0x014)
+#define P2A5_RG_HSTX_SRCAL_EN	BIT(15)
+#define P2A5_RG_HSTX_SRCTRL		GENMASK(14, 12)
+#define P2A5_RG_HSTX_SRCTRL_VAL(x)	((0x7 & (x)) << 12)
+
+#define XSP_USBPHYACR6		((SSUSB_SIFSLV_U2PHY_COM) + 0x018)
+#define P2A6_RG_BC11_SW_EN	BIT(23)
+#define P2A6_RG_OTG_VBUSCMP_EN	BIT(20)
+
+#define XSP_U2PHYDTM1		((SSUSB_SIFSLV_U2PHY_COM) + 0x06C)
+#define P2D_FORCE_IDDIG		BIT(9)
+#define P2D_RG_VBUSVALID	BIT(5)
+#define P2D_RG_SESSEND		BIT(4)
+#define P2D_RG_AVALID		BIT(2)
+#define P2D_RG_IDDIG		BIT(1)
+
+#define SSPXTP_PHYA_GLB_00		((SSPXTP_SIFSLV_PHYA_GLB) + 0x00)
+#define RG_XTP_GLB_BIAS_INTR_CTRL		GENMASK(21, 16)
+#define RG_XTP_GLB_BIAS_INTR_CTRL_VAL(x)	((0x3f & (x)) << 16)
+
+#define SSPXTP_PHYA_LN_04	((SSPXTP_SIFSLV_PHYA_LN) + 0x04)
+#define RG_XTP_LN0_TX_IMPSEL		GENMASK(4, 0)
+#define RG_XTP_LN0_TX_IMPSEL_VAL(x)	(0x1f & (x))
+
+#define SSPXTP_PHYA_LN_14	((SSPXTP_SIFSLV_PHYA_LN) + 0x014)
+#define RG_XTP_LN0_RX_IMPSEL		GENMASK(4, 0)
+#define RG_XTP_LN0_RX_IMPSEL_VAL(x)	(0x1f & (x))
+
+#define XSP_REF_CLK		26	/* MHZ */
+#define XSP_SLEW_RATE_COEF	17
+#define XSP_SR_COEF_DIVISOR	1000
+#define XSP_FM_DET_CYCLE_CNT	1024
+
+struct xsphy_instance {
+	struct phy *phy;
+	void __iomem *port_base;
+	struct clk *ref_clk;	/* reference clock of anolog phy */
+	u32 index;
+	u32 type;
+	/* only for HQA test */
+	int efuse_intr;
+	int efuse_tx_imp;
+	int efuse_rx_imp;
+	/* u2 eye diagram */
+	int eye_src;
+	int eye_vrt;
+	int eye_term;
+};
+
+struct mtk_xsphy {
+	struct device *dev;
+	void __iomem *glb_base;	/* only shared u3 sif */
+	struct xsphy_instance **phys;
+	int nphys;
+	int src_ref_clk; /* MHZ, reference clock for slew rate calibrate */
+	int src_coef;    /* coefficient for slew rate calibrate */
+};
+
+static void u2_phy_slew_rate_calibrate(struct mtk_xsphy *xsphy,
+					struct xsphy_instance *inst)
+{
+	void __iomem *pbase = inst->port_base;
+	int calib_val;
+	int fm_out;
+	u32 tmp;
+
+	/* use force value */
+	if (inst->eye_src)
+		return;
+
+	/* enable USB ring oscillator */
+	tmp = readl(pbase + XSP_USBPHYACR5);
+	tmp |= P2A5_RG_HSTX_SRCAL_EN;
+	writel(tmp, pbase + XSP_USBPHYACR5);
+	udelay(1);	/* wait clock stable */
+
+	/* enable free run clock */
+	tmp = readl(pbase + XSP_U2FREQ_FMMONR1);
+	tmp |= P2F_RG_FRCK_EN;
+	writel(tmp, pbase + XSP_U2FREQ_FMMONR1);
+
+	/* set cycle count as 1024 */
+	tmp = readl(pbase + XSP_U2FREQ_FMCR0);
+	tmp &= ~(P2F_RG_CYCLECNT);
+	tmp |= P2F_RG_CYCLECNT_VAL(XSP_FM_DET_CYCLE_CNT);
+	writel(tmp, pbase + XSP_U2FREQ_FMCR0);
+
+	/* enable frequency meter */
+	tmp = readl(pbase + XSP_U2FREQ_FMCR0);
+	tmp |= P2F_RG_FREQDET_EN;
+	writel(tmp, pbase + XSP_U2FREQ_FMCR0);
+
+	/* ignore return value */
+	readl_poll_timeout(pbase + XSP_U2FREQ_FMMONR1, tmp,
+			   (tmp & P2F_USB_FM_VALID), 10, 200);
+
+	fm_out = readl(pbase + XSP_U2FREQ_MMONR0);
+
+	/* disable frequency meter */
+	tmp = readl(pbase + XSP_U2FREQ_FMCR0);
+	tmp &= ~P2F_RG_FREQDET_EN;
+	writel(tmp, pbase + XSP_U2FREQ_FMCR0);
+
+	/* disable free run clock */
+	tmp = readl(pbase + XSP_U2FREQ_FMMONR1);
+	tmp &= ~P2F_RG_FRCK_EN;
+	writel(tmp, pbase + XSP_U2FREQ_FMMONR1);
+
+	if (fm_out) {
+		/* (1024 / FM_OUT) x reference clock frequency x coefficient */
+		tmp = xsphy->src_ref_clk * xsphy->src_coef;
+		tmp = (tmp * XSP_FM_DET_CYCLE_CNT) / fm_out;
+		calib_val = DIV_ROUND_CLOSEST(tmp, XSP_SR_COEF_DIVISOR);
+	} else {
+		/* if FM detection fail, set default value */
+		calib_val = 3;
+	}
+	dev_dbg(xsphy->dev, "phy.%d, fm_out:%d, calib:%d (clk:%d, coef:%d)\n",
+		inst->index, fm_out, calib_val,
+		xsphy->src_ref_clk, xsphy->src_coef);
+
+	/* set HS slew rate */
+	tmp = readl(pbase + XSP_USBPHYACR5);
+	tmp &= ~P2A5_RG_HSTX_SRCTRL;
+	tmp |= P2A5_RG_HSTX_SRCTRL_VAL(calib_val);
+	writel(tmp, pbase + XSP_USBPHYACR5);
+
+	/* disable USB ring oscillator */
+	tmp = readl(pbase + XSP_USBPHYACR5);
+	tmp &= ~P2A5_RG_HSTX_SRCAL_EN;
+	writel(tmp, pbase + XSP_USBPHYACR5);
+}
+
+static void u2_phy_instance_init(struct mtk_xsphy *xsphy,
+				 struct xsphy_instance *inst)
+{
+	void __iomem *pbase = inst->port_base;
+	u32 tmp;
+
+	/* DP/DM BC1.1 path Disable */
+	tmp = readl(pbase + XSP_USBPHYACR6);
+	tmp &= ~P2A6_RG_BC11_SW_EN;
+	writel(tmp, pbase + XSP_USBPHYACR6);
+
+	tmp = readl(pbase + XSP_USBPHYACR0);
+	tmp |= P2A0_RG_INTR_EN;
+	writel(tmp, pbase + XSP_USBPHYACR0);
+}
+
+static void u2_phy_instance_power_on(struct mtk_xsphy *xsphy,
+				     struct xsphy_instance *inst)
+{
+	void __iomem *pbase = inst->port_base;
+	u32 index = inst->index;
+	u32 tmp;
+
+	tmp = readl(pbase + XSP_USBPHYACR6);
+	tmp |= P2A6_RG_OTG_VBUSCMP_EN;
+	writel(tmp, pbase + XSP_USBPHYACR6);
+
+	tmp = readl(pbase + XSP_U2PHYDTM1);
+	tmp |= P2D_RG_VBUSVALID | P2D_RG_AVALID;
+	tmp &= ~P2D_RG_SESSEND;
+	writel(tmp, pbase + XSP_U2PHYDTM1);
+
+	dev_dbg(xsphy->dev, "%s(%d)\n", __func__, index);
+}
+
+static void u2_phy_instance_power_off(struct mtk_xsphy *xsphy,
+				      struct xsphy_instance *inst)
+{
+	void __iomem *pbase = inst->port_base;
+	u32 index = inst->index;
+	u32 tmp;
+
+	tmp = readl(pbase + XSP_USBPHYACR6);
+	tmp &= ~P2A6_RG_OTG_VBUSCMP_EN;
+	writel(tmp, pbase + XSP_USBPHYACR6);
+
+	tmp = readl(pbase + XSP_U2PHYDTM1);
+	tmp &= ~(P2D_RG_VBUSVALID | P2D_RG_AVALID);
+	tmp |= P2D_RG_SESSEND;
+	writel(tmp, pbase + XSP_U2PHYDTM1);
+
+	dev_dbg(xsphy->dev, "%s(%d)\n", __func__, index);
+}
+
+static void u2_phy_instance_set_mode(struct mtk_xsphy *xsphy,
+				     struct xsphy_instance *inst,
+				     enum phy_mode mode)
+{
+	u32 tmp;
+
+	tmp = readl(inst->port_base + XSP_U2PHYDTM1);
+	switch (mode) {
+	case PHY_MODE_USB_DEVICE:
+		tmp |= P2D_FORCE_IDDIG | P2D_RG_IDDIG;
+		break;
+	case PHY_MODE_USB_HOST:
+		tmp |= P2D_FORCE_IDDIG;
+		tmp &= ~P2D_RG_IDDIG;
+		break;
+	case PHY_MODE_USB_OTG:
+		tmp &= ~(P2D_FORCE_IDDIG | P2D_RG_IDDIG);
+		break;
+	default:
+		return;
+	}
+	writel(tmp, inst->port_base + XSP_U2PHYDTM1);
+}
+
+static void phy_parse_property(struct mtk_xsphy *xsphy,
+				struct xsphy_instance *inst)
+{
+	struct device *dev = &inst->phy->dev;
+
+	switch (inst->type) {
+	case PHY_TYPE_USB2:
+		device_property_read_u32(dev, "mediatek,efuse-intr",
+					 &inst->efuse_intr);
+		device_property_read_u32(dev, "mediatek,eye-src",
+					 &inst->eye_src);
+		device_property_read_u32(dev, "mediatek,eye-vrt",
+					 &inst->eye_vrt);
+		device_property_read_u32(dev, "mediatek,eye-term",
+					 &inst->eye_term);
+		dev_dbg(dev, "intr:%d, src:%d, vrt:%d, term:%d\n",
+			inst->efuse_intr, inst->eye_src,
+			inst->eye_vrt, inst->eye_term);
+		break;
+	case PHY_TYPE_USB3:
+		device_property_read_u32(dev, "mediatek,efuse-intr",
+					 &inst->efuse_intr);
+		device_property_read_u32(dev, "mediatek,efuse-tx-imp",
+					 &inst->efuse_tx_imp);
+		device_property_read_u32(dev, "mediatek,efuse-rx-imp",
+					 &inst->efuse_rx_imp);
+		dev_dbg(dev, "intr:%d, tx-imp:%d, rx-imp:%d\n",
+			inst->efuse_intr, inst->efuse_tx_imp,
+			inst->efuse_rx_imp);
+		break;
+	default:
+		dev_err(xsphy->dev, "incompatible phy type\n");
+		return;
+	}
+}
+
+static void u2_phy_props_set(struct mtk_xsphy *xsphy,
+			     struct xsphy_instance *inst)
+{
+	void __iomem *pbase = inst->port_base;
+	u32 tmp;
+
+	if (inst->efuse_intr) {
+		tmp = readl(pbase + XSP_USBPHYACR1);
+		tmp &= ~P2A1_RG_INTR_CAL;
+		tmp |= P2A1_RG_INTR_CAL_VAL(inst->efuse_intr);
+		writel(tmp, pbase + XSP_USBPHYACR1);
+	}
+
+	if (inst->eye_src) {
+		tmp = readl(pbase + XSP_USBPHYACR5);
+		tmp &= ~P2A5_RG_HSTX_SRCTRL;
+		tmp |= P2A5_RG_HSTX_SRCTRL_VAL(inst->eye_src);
+		writel(tmp, pbase + XSP_USBPHYACR5);
+	}
+
+	if (inst->eye_vrt) {
+		tmp = readl(pbase + XSP_USBPHYACR1);
+		tmp &= ~P2A1_RG_VRT_SEL;
+		tmp |= P2A1_RG_VRT_SEL_VAL(inst->eye_vrt);
+		writel(tmp, pbase + XSP_USBPHYACR1);
+	}
+
+	if (inst->eye_term) {
+		tmp = readl(pbase + XSP_USBPHYACR1);
+		tmp &= ~P2A1_RG_TERM_SEL;
+		tmp |= P2A1_RG_TERM_SEL_VAL(inst->eye_term);
+		writel(tmp, pbase + XSP_USBPHYACR1);
+	}
+}
+
+static void u3_phy_props_set(struct mtk_xsphy *xsphy,
+			     struct xsphy_instance *inst)
+{
+	void __iomem *pbase = inst->port_base;
+	u32 tmp;
+
+	if (inst->efuse_intr) {
+		tmp = readl(xsphy->glb_base + SSPXTP_PHYA_GLB_00);
+		tmp &= ~RG_XTP_GLB_BIAS_INTR_CTRL;
+		tmp |= RG_XTP_GLB_BIAS_INTR_CTRL_VAL(inst->efuse_intr);
+		writel(tmp, xsphy->glb_base + SSPXTP_PHYA_GLB_00);
+	}
+
+	if (inst->efuse_tx_imp) {
+		tmp = readl(pbase + SSPXTP_PHYA_LN_04);
+		tmp &= ~RG_XTP_LN0_TX_IMPSEL;
+		tmp |= RG_XTP_LN0_TX_IMPSEL_VAL(inst->efuse_tx_imp);
+		writel(tmp, pbase + SSPXTP_PHYA_LN_04);
+	}
+
+	if (inst->efuse_rx_imp) {
+		tmp = readl(pbase + SSPXTP_PHYA_LN_14);
+		tmp &= ~RG_XTP_LN0_RX_IMPSEL;
+		tmp |= RG_XTP_LN0_RX_IMPSEL_VAL(inst->efuse_rx_imp);
+		writel(tmp, pbase + SSPXTP_PHYA_LN_14);
+	}
+}
+
+static int mtk_phy_init(struct phy *phy)
+{
+	struct xsphy_instance *inst = phy_get_drvdata(phy);
+	struct mtk_xsphy *xsphy = dev_get_drvdata(phy->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(inst->ref_clk);
+	if (ret) {
+		dev_err(xsphy->dev, "failed to enable ref_clk\n");
+		return ret;
+	}
+
+	switch (inst->type) {
+	case PHY_TYPE_USB2:
+		u2_phy_instance_init(xsphy, inst);
+		u2_phy_props_set(xsphy, inst);
+		break;
+	case PHY_TYPE_USB3:
+		u3_phy_props_set(xsphy, inst);
+		break;
+	default:
+		dev_err(xsphy->dev, "incompatible phy type\n");
+		clk_disable_unprepare(inst->ref_clk);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int mtk_phy_power_on(struct phy *phy)
+{
+	struct xsphy_instance *inst = phy_get_drvdata(phy);
+	struct mtk_xsphy *xsphy = dev_get_drvdata(phy->dev.parent);
+
+	if (inst->type == PHY_TYPE_USB2) {
+		u2_phy_instance_power_on(xsphy, inst);
+		u2_phy_slew_rate_calibrate(xsphy, inst);
+	}
+
+	return 0;
+}
+
+static int mtk_phy_power_off(struct phy *phy)
+{
+	struct xsphy_instance *inst = phy_get_drvdata(phy);
+	struct mtk_xsphy *xsphy = dev_get_drvdata(phy->dev.parent);
+
+	if (inst->type == PHY_TYPE_USB2)
+		u2_phy_instance_power_off(xsphy, inst);
+
+	return 0;
+}
+
+static int mtk_phy_exit(struct phy *phy)
+{
+	struct xsphy_instance *inst = phy_get_drvdata(phy);
+
+	clk_disable_unprepare(inst->ref_clk);
+	return 0;
+}
+
+static int mtk_phy_set_mode(struct phy *phy, enum phy_mode mode)
+{
+	struct xsphy_instance *inst = phy_get_drvdata(phy);
+	struct mtk_xsphy *xsphy = dev_get_drvdata(phy->dev.parent);
+
+	if (inst->type == PHY_TYPE_USB2)
+		u2_phy_instance_set_mode(xsphy, inst, mode);
+
+	return 0;
+}
+
+static struct phy *mtk_phy_xlate(struct device *dev,
+				 struct of_phandle_args *args)
+{
+	struct mtk_xsphy *xsphy = dev_get_drvdata(dev);
+	struct xsphy_instance *inst = NULL;
+	struct device_node *phy_np = args->np;
+	int index;
+
+	if (args->args_count != 1) {
+		dev_err(dev, "invalid number of cells in 'phy' property\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	for (index = 0; index < xsphy->nphys; index++)
+		if (phy_np == xsphy->phys[index]->phy->dev.of_node) {
+			inst = xsphy->phys[index];
+			break;
+		}
+
+	if (!inst) {
+		dev_err(dev, "failed to find appropriate phy\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	inst->type = args->args[0];
+	if (!(inst->type == PHY_TYPE_USB2 ||
+	      inst->type == PHY_TYPE_USB3)) {
+		dev_err(dev, "unsupported phy type: %d\n", inst->type);
+		return ERR_PTR(-EINVAL);
+	}
+
+	phy_parse_property(xsphy, inst);
+
+	return inst->phy;
+}
+
+static const struct phy_ops mtk_xsphy_ops = {
+	.init		= mtk_phy_init,
+	.exit		= mtk_phy_exit,
+	.power_on	= mtk_phy_power_on,
+	.power_off	= mtk_phy_power_off,
+	.set_mode	= mtk_phy_set_mode,
+	.owner		= THIS_MODULE,
+};
+
+static const struct of_device_id mtk_xsphy_id_table[] = {
+	{ .compatible = "mediatek,xsphy", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, mtk_xsphy_id_table);
+
+static int mtk_xsphy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct device_node *child_np;
+	struct phy_provider *provider;
+	struct resource *glb_res;
+	struct mtk_xsphy *xsphy;
+	struct resource res;
+	int port, retval;
+
+	xsphy = devm_kzalloc(dev, sizeof(*xsphy), GFP_KERNEL);
+	if (!xsphy)
+		return -ENOMEM;
+
+	xsphy->nphys = of_get_child_count(np);
+	xsphy->phys = devm_kcalloc(dev, xsphy->nphys,
+				       sizeof(*xsphy->phys), GFP_KERNEL);
+	if (!xsphy->phys)
+		return -ENOMEM;
+
+	xsphy->dev = dev;
+	platform_set_drvdata(pdev, xsphy);
+
+	glb_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	/* optional, may not exist if no u3 phys */
+	if (glb_res) {
+		/* get banks shared by multiple u3 phys */
+		xsphy->glb_base = devm_ioremap_resource(dev, glb_res);
+		if (IS_ERR(xsphy->glb_base)) {
+			dev_err(dev, "failed to remap glb regs\n");
+			return PTR_ERR(xsphy->glb_base);
+		}
+	}
+
+	xsphy->src_ref_clk = XSP_REF_CLK;
+	xsphy->src_coef = XSP_SLEW_RATE_COEF;
+	/* update parameters of slew rate calibrate if exist */
+	device_property_read_u32(dev, "mediatek,src-ref-clk-mhz",
+				 &xsphy->src_ref_clk);
+	device_property_read_u32(dev, "mediatek,src-coef", &xsphy->src_coef);
+
+	port = 0;
+	for_each_child_of_node(np, child_np) {
+		struct xsphy_instance *inst;
+		struct phy *phy;
+
+		inst = devm_kzalloc(dev, sizeof(*inst), GFP_KERNEL);
+		if (!inst) {
+			retval = -ENOMEM;
+			goto put_child;
+		}
+
+		xsphy->phys[port] = inst;
+
+		phy = devm_phy_create(dev, child_np, &mtk_xsphy_ops);
+		if (IS_ERR(phy)) {
+			dev_err(dev, "failed to create phy\n");
+			retval = PTR_ERR(phy);
+			goto put_child;
+		}
+
+		retval = of_address_to_resource(child_np, 0, &res);
+		if (retval) {
+			dev_err(dev, "failed to get address resource(id-%d)\n",
+				port);
+			goto put_child;
+		}
+
+		inst->port_base = devm_ioremap_resource(&phy->dev, &res);
+		if (IS_ERR(inst->port_base)) {
+			dev_err(dev, "failed to remap phy regs\n");
+			retval = PTR_ERR(inst->port_base);
+			goto put_child;
+		}
+
+		inst->phy = phy;
+		inst->index = port;
+		phy_set_drvdata(phy, inst);
+		port++;
+
+		inst->ref_clk = devm_clk_get(&phy->dev, "ref");
+		if (IS_ERR(inst->ref_clk)) {
+			dev_err(dev, "failed to get ref_clk(id-%d)\n", port);
+			retval = PTR_ERR(inst->ref_clk);
+			goto put_child;
+		}
+	}
+
+	provider = devm_of_phy_provider_register(dev, mtk_phy_xlate);
+	return PTR_ERR_OR_ZERO(provider);
+
+put_child:
+	of_node_put(child_np);
+	return retval;
+}
+
+static struct platform_driver mtk_xsphy_driver = {
+	.probe		= mtk_xsphy_probe,
+	.driver		= {
+		.name	= "mtk-xsphy",
+		.of_match_table = mtk_xsphy_id_table,
+	},
+};
+
+module_platform_driver(mtk_xsphy_driver);
+
+MODULE_AUTHOR("Chunfeng Yun <chunfeng.yun@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek USB XS-PHY driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c
index 5439dd90d0dd..23705e1a0023 100644
--- a/drivers/phy/motorola/phy-mapphone-mdm6600.c
+++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c
@@ -19,6 +19,8 @@
 
 #define PHY_MDM6600_PHY_DELAY_MS	4000	/* PHY enable 2.2s to 3.5s */
 #define PHY_MDM6600_ENABLED_DELAY_MS	8000	/* 8s more total for MDM6600 */
+#define MDM6600_MODEM_IDLE_DELAY_MS	1000	/* modem after USB suspend */
+#define MDM6600_MODEM_WAKE_DELAY_MS	200	/* modem response after idle */
 
 enum phy_mdm6600_ctrl_lines {
 	PHY_MDM6600_ENABLE,			/* USB PHY enable */
@@ -93,9 +95,11 @@ struct phy_mdm6600 {
 	struct gpio_descs *cmd_gpios;
 	struct delayed_work bootup_work;
 	struct delayed_work status_work;
+	struct delayed_work modem_wake_work;
 	struct completion ack;
 	bool enabled;				/* mdm6600 phy enabled */
 	bool running;				/* mdm6600 boot done */
+	bool awake;				/* mdm6600 respnds on n_gsm */
 	int status;
 };
 
@@ -446,6 +450,62 @@ static void phy_mdm6600_deferred_power_on(struct work_struct *work)
 		dev_err(ddata->dev, "Device not functional\n");
 }
 
+/*
+ * USB suspend puts mdm6600 into low power mode. For any n_gsm using apps,
+ * we need to keep the modem awake by kicking it's mode0 GPIO. This will
+ * keep the modem awake for about 1.2 seconds. When no n_gsm apps are using
+ * the modem, runtime PM auto mode can be enabled so modem can enter low
+ * power mode.
+ */
+static void phy_mdm6600_wake_modem(struct phy_mdm6600 *ddata)
+{
+	struct gpio_desc *mode_gpio0;
+
+	mode_gpio0 = ddata->mode_gpios->desc[PHY_MDM6600_MODE0];
+	gpiod_set_value_cansleep(mode_gpio0, 1);
+	usleep_range(5, 15);
+	gpiod_set_value_cansleep(mode_gpio0, 0);
+	if (ddata->awake)
+		usleep_range(5, 15);
+	else
+		msleep(MDM6600_MODEM_WAKE_DELAY_MS);
+}
+
+static void phy_mdm6600_modem_wake(struct work_struct *work)
+{
+	struct phy_mdm6600 *ddata;
+
+	ddata = container_of(work, struct phy_mdm6600, modem_wake_work.work);
+	phy_mdm6600_wake_modem(ddata);
+	schedule_delayed_work(&ddata->modem_wake_work,
+			      msecs_to_jiffies(MDM6600_MODEM_IDLE_DELAY_MS));
+}
+
+static int __maybe_unused phy_mdm6600_runtime_suspend(struct device *dev)
+{
+	struct phy_mdm6600 *ddata = dev_get_drvdata(dev);
+
+	cancel_delayed_work_sync(&ddata->modem_wake_work);
+	ddata->awake = false;
+
+	return 0;
+}
+
+static int __maybe_unused phy_mdm6600_runtime_resume(struct device *dev)
+{
+	struct phy_mdm6600 *ddata = dev_get_drvdata(dev);
+
+	phy_mdm6600_modem_wake(&ddata->modem_wake_work.work);
+	ddata->awake = true;
+
+	return 0;
+}
+
+static const struct dev_pm_ops phy_mdm6600_pm_ops = {
+	SET_RUNTIME_PM_OPS(phy_mdm6600_runtime_suspend,
+			   phy_mdm6600_runtime_resume, NULL)
+};
+
 static const struct of_device_id phy_mdm6600_id_table[] = {
 	{ .compatible = "motorola,mapphone-mdm6600", },
 	{},
@@ -464,6 +524,7 @@ static int phy_mdm6600_probe(struct platform_device *pdev)
 	INIT_DELAYED_WORK(&ddata->bootup_work,
 			  phy_mdm6600_deferred_power_on);
 	INIT_DELAYED_WORK(&ddata->status_work, phy_mdm6600_status);
+	INIT_DELAYED_WORK(&ddata->modem_wake_work, phy_mdm6600_modem_wake);
 	init_completion(&ddata->ack);
 
 	ddata->dev = &pdev->dev;
@@ -500,6 +561,24 @@ static int phy_mdm6600_probe(struct platform_device *pdev)
 	 */
 	msleep(PHY_MDM6600_PHY_DELAY_MS + 500);
 
+	/*
+	 * Enable PM runtime only after PHY has been powered up properly.
+	 * It is currently only needed after USB suspends mdm6600 and n_gsm
+	 * needs to access the device. We don't want to do this earlier as
+	 * gpio mode0 pin doubles as mdm6600 wake-up gpio.
+	 */
+	pm_runtime_use_autosuspend(ddata->dev);
+	pm_runtime_set_autosuspend_delay(ddata->dev,
+					 MDM6600_MODEM_IDLE_DELAY_MS);
+	pm_runtime_enable(ddata->dev);
+	error = pm_runtime_get_sync(ddata->dev);
+	if (error < 0) {
+		dev_warn(ddata->dev, "failed to wake modem: %i\n", error);
+		pm_runtime_put_noidle(ddata->dev);
+	}
+	pm_runtime_mark_last_busy(ddata->dev);
+	pm_runtime_put_autosuspend(ddata->dev);
+
 	return 0;
 
 cleanup:
@@ -512,6 +591,10 @@ static int phy_mdm6600_remove(struct platform_device *pdev)
 	struct phy_mdm6600 *ddata = platform_get_drvdata(pdev);
 	struct gpio_desc *reset_gpio = ddata->ctrl_gpios[PHY_MDM6600_RESET];
 
+	pm_runtime_dont_use_autosuspend(ddata->dev);
+	pm_runtime_put_sync(ddata->dev);
+	pm_runtime_disable(ddata->dev);
+
 	if (!ddata->running)
 		wait_for_completion_timeout(&ddata->ack,
 			msecs_to_jiffies(PHY_MDM6600_ENABLED_DELAY_MS));
@@ -519,6 +602,7 @@ static int phy_mdm6600_remove(struct platform_device *pdev)
 	gpiod_set_value_cansleep(reset_gpio, 1);
 	phy_mdm6600_device_power_off(ddata);
 
+	cancel_delayed_work_sync(&ddata->modem_wake_work);
 	cancel_delayed_work_sync(&ddata->bootup_work);
 	cancel_delayed_work_sync(&ddata->status_work);
 
@@ -530,6 +614,7 @@ static struct platform_driver phy_mdm6600_driver = {
 	.remove = phy_mdm6600_remove,
 	.driver = {
 		.name = "phy-mapphone-mdm6600",
+		.pm = &phy_mdm6600_pm_ops,
 		.of_match_table = of_match_ptr(phy_mdm6600_id_table),
 	},
 };
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 09ac8afb97ac..35fd38c5a4a1 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -153,6 +153,9 @@ int phy_pm_runtime_get(struct phy *phy)
 {
 	int ret;
 
+	if (!phy)
+		return 0;
+
 	if (!pm_runtime_enabled(&phy->dev))
 		return -ENOTSUPP;
 
@@ -168,6 +171,9 @@ int phy_pm_runtime_get_sync(struct phy *phy)
 {
 	int ret;
 
+	if (!phy)
+		return 0;
+
 	if (!pm_runtime_enabled(&phy->dev))
 		return -ENOTSUPP;
 
@@ -181,6 +187,9 @@ EXPORT_SYMBOL_GPL(phy_pm_runtime_get_sync);
 
 int phy_pm_runtime_put(struct phy *phy)
 {
+	if (!phy)
+		return 0;
+
 	if (!pm_runtime_enabled(&phy->dev))
 		return -ENOTSUPP;
 
@@ -190,6 +199,9 @@ EXPORT_SYMBOL_GPL(phy_pm_runtime_put);
 
 int phy_pm_runtime_put_sync(struct phy *phy)
 {
+	if (!phy)
+		return 0;
+
 	if (!pm_runtime_enabled(&phy->dev))
 		return -ENOTSUPP;
 
@@ -199,6 +211,9 @@ EXPORT_SYMBOL_GPL(phy_pm_runtime_put_sync);
 
 void phy_pm_runtime_allow(struct phy *phy)
 {
+	if (!phy)
+		return;
+
 	if (!pm_runtime_enabled(&phy->dev))
 		return;
 
@@ -208,6 +223,9 @@ EXPORT_SYMBOL_GPL(phy_pm_runtime_allow);
 
 void phy_pm_runtime_forbid(struct phy *phy)
 {
+	if (!phy)
+		return;
+
 	if (!pm_runtime_enabled(&phy->dev))
 		return;
 
diff --git a/drivers/phy/qualcomm/Kconfig b/drivers/phy/qualcomm/Kconfig
index 7bfa64baf837..632a0e73ee10 100644
--- a/drivers/phy/qualcomm/Kconfig
+++ b/drivers/phy/qualcomm/Kconfig
@@ -1,6 +1,15 @@
 #
-# Phy drivers for Qualcomm platforms
+# Phy drivers for Qualcomm and Atheros platforms
 #
+config PHY_ATH79_USB
+	tristate "Atheros AR71XX/9XXX USB PHY driver"
+	depends on OF && (ATH79 || COMPILE_TEST)
+	default y if USB_EHCI_HCD_PLATFORM || USB_OHCI_HCD_PLATFORM
+	select RESET_CONTROLLER
+	select GENERIC_PHY
+	help
+	  Enable this to support the USB PHY on Atheros AR71XX/9XXX SoCs.
+
 config PHY_QCOM_APQ8064_SATA
 	tristate "Qualcomm APQ8064 SATA SerDes/PHY driver"
 	depends on ARCH_QCOM
diff --git a/drivers/phy/qualcomm/Makefile b/drivers/phy/qualcomm/Makefile
index 9abb7899762a..deb831f453ae 100644
--- a/drivers/phy/qualcomm/Makefile
+++ b/drivers/phy/qualcomm/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_PHY_ATH79_USB)		+= phy-ath79-usb.o
 obj-$(CONFIG_PHY_QCOM_APQ8064_SATA)	+= phy-qcom-apq8064-sata.o
 obj-$(CONFIG_PHY_QCOM_IPQ806X_SATA)	+= phy-qcom-ipq806x-sata.o
 obj-$(CONFIG_PHY_QCOM_QMP)		+= phy-qcom-qmp.o
diff --git a/drivers/phy/qualcomm/phy-ath79-usb.c b/drivers/phy/qualcomm/phy-ath79-usb.c
new file mode 100644
index 000000000000..6fd6e07ab345
--- /dev/null
+++ b/drivers/phy/qualcomm/phy-ath79-usb.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Atheros AR71XX/9XXX USB PHY driver
+ *
+ * Copyright (C) 2015-2018 Alban Bedel <albeu@free.fr>
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/phy/phy.h>
+#include <linux/reset.h>
+
+struct ath79_usb_phy {
+	struct reset_control *reset;
+	/* The suspend override logic is inverted, hence the no prefix
+	 * to make the code a bit easier to understand.
+	 */
+	struct reset_control *no_suspend_override;
+};
+
+static int ath79_usb_phy_power_on(struct phy *phy)
+{
+	struct ath79_usb_phy *priv = phy_get_drvdata(phy);
+	int err = 0;
+
+	if (priv->no_suspend_override) {
+		err = reset_control_assert(priv->no_suspend_override);
+		if (err)
+			return err;
+	}
+
+	err = reset_control_deassert(priv->reset);
+	if (err && priv->no_suspend_override)
+		reset_control_assert(priv->no_suspend_override);
+
+	return err;
+}
+
+static int ath79_usb_phy_power_off(struct phy *phy)
+{
+	struct ath79_usb_phy *priv = phy_get_drvdata(phy);
+	int err = 0;
+
+	err = reset_control_assert(priv->reset);
+	if (err)
+		return err;
+
+	if (priv->no_suspend_override) {
+		err = reset_control_deassert(priv->no_suspend_override);
+		if (err)
+			reset_control_deassert(priv->reset);
+	}
+
+	return err;
+}
+
+static const struct phy_ops ath79_usb_phy_ops = {
+	.power_on	= ath79_usb_phy_power_on,
+	.power_off	= ath79_usb_phy_power_off,
+	.owner		= THIS_MODULE,
+};
+
+static int ath79_usb_phy_probe(struct platform_device *pdev)
+{
+	struct ath79_usb_phy *priv;
+	struct phy *phy;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->reset = devm_reset_control_get(&pdev->dev, "usb-phy");
+	if (IS_ERR(priv->reset))
+		return PTR_ERR(priv->reset);
+
+	priv->no_suspend_override = devm_reset_control_get_optional(
+		&pdev->dev, "usb-suspend-override");
+	if (IS_ERR(priv->no_suspend_override))
+		return PTR_ERR(priv->no_suspend_override);
+
+	phy = devm_phy_create(&pdev->dev, NULL, &ath79_usb_phy_ops);
+	if (IS_ERR(phy))
+		return PTR_ERR(phy);
+
+	phy_set_drvdata(phy, priv);
+
+	return PTR_ERR_OR_ZERO(devm_of_phy_provider_register(
+				&pdev->dev, of_phy_simple_xlate));
+}
+
+static const struct of_device_id ath79_usb_phy_of_match[] = {
+	{ .compatible = "qca,ar7100-usb-phy" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, ath79_usb_phy_of_match);
+
+static struct platform_driver ath79_usb_phy_driver = {
+	.probe	= ath79_usb_phy_probe,
+	.driver = {
+		.of_match_table	= ath79_usb_phy_of_match,
+		.name		= "ath79-usb-phy",
+	}
+};
+module_platform_driver(ath79_usb_phy_driver);
+
+MODULE_DESCRIPTION("ATH79 USB PHY driver");
+MODULE_AUTHOR("Alban Bedel <albeu@free.fr>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c
index 6470c5d61d1c..4c470104a0d6 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.c
@@ -490,6 +490,118 @@ static const struct qmp_phy_init_tbl qmp_v3_usb3_pcs_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13),
 };
 
+static const struct qmp_phy_init_tbl qmp_v3_usb3_uniphy_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_IVCO, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYSCLK_EN_SEL, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_CLK_SELECT, 0x30),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYS_CLK_CTRL, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_RESETSM_CNTRL2, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_CMN_CONFIG, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SVS_MODE_CLK_SEL, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_HSCLK_SEL, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_DEC_START_MODE0, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START1_MODE0, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START2_MODE0, 0xea),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START3_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_CP_CTRL_MODE0, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_INTEGLOOP_GAIN1_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_INTEGLOOP_GAIN0_MODE0, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE2_MODE0, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE1_MODE0, 0xc9),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_CORECLK_DIV_MODE0, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP3_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP2_MODE0, 0x34),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP1_MODE0, 0x15),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP_EN, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_CORE_CLK_EN, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP_CFG, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE_MAP, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYSCLK_BUF_ENABLE, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_PER1, 0x31),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_PER2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_ADJ_PER1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_ADJ_PER2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_STEP_SIZE1, 0x85),
+	QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_STEP_SIZE2, 0x07),
+};
+
+static const struct qmp_phy_init_tbl qmp_v3_usb3_uniphy_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V3_TX_HIGHZ_DRVR_EN, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_V3_TX_RCV_DETECT_LVL_2, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V3_TX_LANE_MODE_1, 0xc6),
+	QMP_PHY_INIT_CFG(QSERDES_V3_TX_RES_CODE_LANE_OFFSET_RX, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V3_TX_RES_CODE_LANE_OFFSET_TX, 0x06),
+};
+
+static const struct qmp_phy_init_tbl qmp_v3_usb3_uniphy_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_VGA_CAL_CNTRL2, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_MODE_00, 0x50),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4e),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL4, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x77),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_OFFSET_ADAPTOR_CNTRL2, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_CNTRL, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_DEGLITCH_CNTRL, 0x1c),
+	QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x75),
+};
+
+static const struct qmp_phy_init_tbl qmp_v3_usb3_uniphy_pcs_tbl[] = {
+	/* FLL settings */
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL2, 0x83),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_L, 0x09),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_H_TOL, 0xa2),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_MAN_CODE, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL1, 0x02),
+
+	/* Lock Det settings */
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG1, 0xd1),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG2, 0x1f),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG3, 0x47),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_POWER_STATE_CONFIG2, 0x1b),
+
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RX_SIGDET_LVL, 0xba),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V0, 0x9f),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V1, 0x9f),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V2, 0xb5),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V3, 0x4c),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V4, 0x64),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_LS, 0x6a),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V0, 0x15),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V0, 0x0d),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V1, 0x15),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V1, 0x0d),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V2, 0x15),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V2, 0x0d),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V3, 0x15),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V3, 0x1d),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V4, 0x15),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V4, 0x0d),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_LS, 0x15),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_LS, 0x0d),
+
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RATE_SLEW_CNTRL, 0x02),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_TSYNC_RSYNC_TIME, 0x44),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x04),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_L, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_H, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_WAIT_TIME, 0x75),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_LFPS_TX_ECSTART_EQTLOCK, 0x86),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13),
+
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_REFGEN_REQ_CONFIG1, 0x21),
+	QMP_PHY_INIT_CFG(QPHY_V3_PCS_REFGEN_REQ_CONFIG2, 0x60),
+};
+
+
 /* struct qmp_phy_cfg - per-PHY initialization config */
 struct qmp_phy_cfg {
 	/* phy-type - PCIE/UFS/USB */
@@ -766,6 +878,7 @@ static const struct qmp_phy_cfg qmp_v3_usb3phy_cfg = {
 	.pwrdn_ctrl		= SW_PWRDN,
 	.mask_pcs_ready		= PHYSTATUS,
 
+	.has_pwrdn_delay	= true,
 	.pwrdn_delay_min	= POWER_DOWN_DELAY_US_MIN,
 	.pwrdn_delay_max	= POWER_DOWN_DELAY_US_MAX,
 
@@ -774,6 +887,35 @@ static const struct qmp_phy_cfg qmp_v3_usb3phy_cfg = {
 	.rx_b_lane_offset	= 0x400,
 };
 
+static const struct qmp_phy_cfg qmp_v3_usb3_uniphy_cfg = {
+	.type			= PHY_TYPE_USB3,
+	.nlanes			= 1,
+
+	.serdes_tbl		= qmp_v3_usb3_uniphy_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(qmp_v3_usb3_uniphy_serdes_tbl),
+	.tx_tbl			= qmp_v3_usb3_uniphy_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(qmp_v3_usb3_uniphy_tx_tbl),
+	.rx_tbl			= qmp_v3_usb3_uniphy_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(qmp_v3_usb3_uniphy_rx_tbl),
+	.pcs_tbl		= qmp_v3_usb3_uniphy_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(qmp_v3_usb3_uniphy_pcs_tbl),
+	.clk_list		= qmp_v3_phy_clk_l,
+	.num_clks		= ARRAY_SIZE(qmp_v3_phy_clk_l),
+	.reset_list		= msm8996_usb3phy_reset_l,
+	.num_resets		= ARRAY_SIZE(msm8996_usb3phy_reset_l),
+	.vreg_list		= msm8996_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(msm8996_phy_vreg_l),
+	.regs			= qmp_v3_usb3phy_regs_layout,
+
+	.start_ctrl		= SERDES_START | PCS_START,
+	.pwrdn_ctrl		= SW_PWRDN,
+	.mask_pcs_ready		= PHYSTATUS,
+
+	.has_pwrdn_delay	= true,
+	.pwrdn_delay_min	= POWER_DOWN_DELAY_US_MIN,
+	.pwrdn_delay_max	= POWER_DOWN_DELAY_US_MAX,
+};
+
 static void qcom_qmp_phy_configure(void __iomem *base,
 				   const unsigned int *regs,
 				   const struct qmp_phy_init_tbl tbl[],
@@ -793,19 +935,6 @@ static void qcom_qmp_phy_configure(void __iomem *base,
 	}
 }
 
-static int qcom_qmp_phy_poweron(struct phy *phy)
-{
-	struct qmp_phy *qphy = phy_get_drvdata(phy);
-	struct qcom_qmp *qmp = qphy->qmp;
-	int ret;
-
-	ret = clk_prepare_enable(qphy->pipe_clk);
-	if (ret)
-		dev_err(qmp->dev, "pipe_clk enable failed, err=%d\n", ret);
-
-	return ret;
-}
-
 static int qcom_qmp_phy_com_init(struct qcom_qmp *qmp)
 {
 	const struct qmp_phy_cfg *cfg = qmp->cfg;
@@ -974,6 +1103,12 @@ static int qcom_qmp_phy_init(struct phy *phy)
 		}
 	}
 
+	ret = clk_prepare_enable(qphy->pipe_clk);
+	if (ret) {
+		dev_err(qmp->dev, "pipe_clk enable failed err=%d\n", ret);
+		goto err_clk_enable;
+	}
+
 	/* Tx, Rx, and PCS configurations */
 	qcom_qmp_phy_configure(tx, cfg->regs, cfg->tx_tbl, cfg->tx_tbl_num);
 	/* Configuration for other LANE for USB-DP combo PHY */
@@ -1019,6 +1154,8 @@ static int qcom_qmp_phy_init(struct phy *phy)
 	return ret;
 
 err_pcs_ready:
+	clk_disable_unprepare(qphy->pipe_clk);
+err_clk_enable:
 	if (cfg->has_lane_rst)
 		reset_control_assert(qphy->lane_rst);
 err_lane_rst:
@@ -1283,7 +1420,6 @@ static int phy_pipe_clk_register(struct qcom_qmp *qmp, struct device_node *np)
 static const struct phy_ops qcom_qmp_phy_gen_ops = {
 	.init		= qcom_qmp_phy_init,
 	.exit		= qcom_qmp_phy_exit,
-	.power_on	= qcom_qmp_phy_poweron,
 	.set_mode	= qcom_qmp_phy_set_mode,
 	.owner		= THIS_MODULE,
 };
@@ -1381,8 +1517,11 @@ static const struct of_device_id qcom_qmp_phy_of_match_table[] = {
 		.compatible = "qcom,ipq8074-qmp-pcie-phy",
 		.data = &ipq8074_pciephy_cfg,
 	}, {
-		.compatible = "qcom,qmp-v3-usb3-phy",
+		.compatible = "qcom,sdm845-qmp-usb3-phy",
 		.data = &qmp_v3_usb3phy_cfg,
+	}, {
+		.compatible = "qcom,sdm845-qmp-usb3-uni-phy",
+		.data = &qmp_v3_usb3_uniphy_cfg,
 	},
 	{ },
 };
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index d1c6905d0439..5d78d43ba9fc 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -214,6 +214,8 @@
 #define QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN		0x030
 #define QSERDES_V3_RX_UCDR_SO_SATURATION_AND_ENABLE	0x034
 #define QSERDES_V3_RX_RX_TERM_BW			0x07c
+#define QSERDES_V3_RX_VGA_CAL_CNTRL1			0x0bc
+#define QSERDES_V3_RX_VGA_CAL_CNTRL2			0x0c0
 #define QSERDES_V3_RX_RX_EQ_GAIN2_LSB			0x0c8
 #define QSERDES_V3_RX_RX_EQ_GAIN2_MSB			0x0cc
 #define QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2		0x0d4
@@ -227,6 +229,7 @@
 #define QSERDES_V3_RX_SIGDET_DEGLITCH_CNTRL		0x10c
 #define QSERDES_V3_RX_RX_BAND				0x110
 #define QSERDES_V3_RX_RX_INTERFACE_MODE			0x11c
+#define QSERDES_V3_RX_RX_MODE_00			0x164
 
 /* Only for QMP V3 PHY - PCS registers */
 #define QPHY_V3_PCS_POWER_DOWN_CONTROL			0x004
@@ -273,6 +276,8 @@
 #define QPHY_V3_PCS_FLL_CNT_VAL_H_TOL			0x0d0
 #define QPHY_V3_PCS_FLL_MAN_CODE			0x0d4
 #define QPHY_V3_PCS_RX_SIGDET_LVL			0x1d8
+#define QPHY_V3_PCS_REFGEN_REQ_CONFIG1			0x20c
+#define QPHY_V3_PCS_REFGEN_REQ_CONFIG2			0x210
 
 /* Only for QMP V3 PHY - PCS_MISC registers */
 #define QPHY_V3_PCS_MISC_CLAMP_ENABLE			0x0c
diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c
index 94afeac1a19e..e70e425f26f5 100644
--- a/drivers/phy/qualcomm/phy-qcom-qusb2.c
+++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c
@@ -20,6 +20,8 @@
 #include <linux/reset.h>
 #include <linux/slab.h>
 
+#include <dt-bindings/phy/phy-qcom-qusb2.h>
+
 #define QUSB2PHY_PLL_TEST		0x04
 #define CLK_REF_SEL			BIT(7)
 
@@ -60,6 +62,17 @@
 #define CORE_RESET				BIT(5)
 #define CORE_RESET_MUX				BIT(6)
 
+/* QUSB2PHY_IMP_CTRL1 register bits */
+#define IMP_RES_OFFSET_MASK			GENMASK(5, 0)
+#define IMP_RES_OFFSET_SHIFT			0x0
+
+/* QUSB2PHY_PORT_TUNE1 register bits */
+#define HSTX_TRIM_MASK				GENMASK(7, 4)
+#define HSTX_TRIM_SHIFT				0x4
+#define PREEMPH_WIDTH_HALF_BIT			BIT(2)
+#define PREEMPHASIS_EN_MASK			GENMASK(1, 0)
+#define PREEMPHASIS_EN_SHIFT			0x0
+
 #define QUSB2PHY_PLL_ANALOG_CONTROLS_TWO	0x04
 #define QUSB2PHY_PLL_CLOCK_INVERTERS		0x18c
 #define QUSB2PHY_PLL_CMODE			0x2c
@@ -139,7 +152,7 @@ static const struct qusb2_phy_init_tbl msm8996_init_tbl[] = {
 	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_PWR_CTRL, 0x00),
 };
 
-static const unsigned int qusb2_v2_regs_layout[] = {
+static const unsigned int sdm845_regs_layout[] = {
 	[QUSB2PHY_PLL_CORE_INPUT_OVERRIDE] = 0xa8,
 	[QUSB2PHY_PLL_STATUS]		= 0x1a0,
 	[QUSB2PHY_PORT_TUNE1]		= 0x240,
@@ -153,7 +166,7 @@ static const unsigned int qusb2_v2_regs_layout[] = {
 	[QUSB2PHY_INTR_CTRL]		= 0x230,
 };
 
-static const struct qusb2_phy_init_tbl qusb2_v2_init_tbl[] = {
+static const struct qusb2_phy_init_tbl sdm845_init_tbl[] = {
 	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_ANALOG_CONTROLS_TWO, 0x03),
 	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_CLOCK_INVERTERS, 0x7c),
 	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_CMODE, 0x80),
@@ -208,10 +221,10 @@ static const struct qusb2_phy_cfg msm8996_phy_cfg = {
 	.autoresume_en	 = BIT(3),
 };
 
-static const struct qusb2_phy_cfg qusb2_v2_phy_cfg = {
-	.tbl		= qusb2_v2_init_tbl,
-	.tbl_num	= ARRAY_SIZE(qusb2_v2_init_tbl),
-	.regs		= qusb2_v2_regs_layout,
+static const struct qusb2_phy_cfg sdm845_phy_cfg = {
+	.tbl		= sdm845_init_tbl,
+	.tbl_num	= ARRAY_SIZE(sdm845_init_tbl),
+	.regs		= sdm845_regs_layout,
 
 	.disable_ctrl	= (PWR_CTRL1_VREF_SUPPLY_TRIM | PWR_CTRL1_CLAMP_N_EN |
 			   POWER_DOWN),
@@ -241,6 +254,15 @@ static const char * const qusb2_phy_vreg_names[] = {
  * @tcsr: TCSR syscon register map
  * @cell: nvmem cell containing phy tuning value
  *
+ * @override_imp_res_offset: PHY should use different rescode offset
+ * @imp_res_offset_value: rescode offset to be updated in IMP_CTRL1 register
+ * @override_hstx_trim: PHY should use different HSTX o/p current value
+ * @hstx_trim_value: HSTX_TRIM value to be updated in TUNE1 register
+ * @override_preemphasis: PHY should use different pre-amphasis amplitude
+ * @preemphasis_level: Amplitude Pre-Emphasis to be updated in TUNE1 register
+ * @override_preemphasis_width: PHY should use different pre-emphasis duration
+ * @preemphasis_width: half/full-width Pre-Emphasis updated via TUNE1
+ *
  * @cfg: phy config data
  * @has_se_clk_scheme: indicate if PHY has single-ended ref clock scheme
  * @phy_initialized: indicate if PHY has been initialized
@@ -259,12 +281,35 @@ struct qusb2_phy {
 	struct regmap *tcsr;
 	struct nvmem_cell *cell;
 
+	bool override_imp_res_offset;
+	u8 imp_res_offset_value;
+	bool override_hstx_trim;
+	u8 hstx_trim_value;
+	bool override_preemphasis;
+	u8 preemphasis_level;
+	bool override_preemphasis_width;
+	u8 preemphasis_width;
+
 	const struct qusb2_phy_cfg *cfg;
 	bool has_se_clk_scheme;
 	bool phy_initialized;
 	enum phy_mode mode;
 };
 
+static inline void qusb2_write_mask(void __iomem *base, u32 offset,
+				    u32 val, u32 mask)
+{
+	u32 reg;
+
+	reg = readl(base + offset);
+	reg &= ~mask;
+	reg |= val & mask;
+	writel(reg, base + offset);
+
+	/* Ensure above write is completed */
+	readl(base + offset);
+}
+
 static inline void qusb2_setbits(void __iomem *base, u32 offset, u32 val)
 {
 	u32 reg;
@@ -305,6 +350,42 @@ void qcom_qusb2_phy_configure(void __iomem *base,
 }
 
 /*
+ * Update board specific PHY tuning override values if specified from
+ * device tree.
+ */
+static void qusb2_phy_override_phy_params(struct qusb2_phy *qphy)
+{
+	const struct qusb2_phy_cfg *cfg = qphy->cfg;
+
+	if (qphy->override_imp_res_offset)
+		qusb2_write_mask(qphy->base, QUSB2PHY_IMP_CTRL1,
+			     qphy->imp_res_offset_value << IMP_RES_OFFSET_SHIFT,
+			     IMP_RES_OFFSET_MASK);
+
+	if (qphy->override_hstx_trim)
+		qusb2_write_mask(qphy->base, cfg->regs[QUSB2PHY_PORT_TUNE1],
+				 qphy->hstx_trim_value << HSTX_TRIM_SHIFT,
+				 HSTX_TRIM_MASK);
+
+	if (qphy->override_preemphasis)
+		qusb2_write_mask(qphy->base, cfg->regs[QUSB2PHY_PORT_TUNE1],
+				qphy->preemphasis_level << PREEMPHASIS_EN_SHIFT,
+				PREEMPHASIS_EN_MASK);
+
+	if (qphy->override_preemphasis_width) {
+		if (qphy->preemphasis_width ==
+		    QUSB2_V2_PREEMPHASIS_WIDTH_HALF_BIT)
+			qusb2_setbits(qphy->base,
+				      cfg->regs[QUSB2PHY_PORT_TUNE1],
+				      PREEMPH_WIDTH_HALF_BIT);
+		else
+			qusb2_clrbits(qphy->base,
+				      cfg->regs[QUSB2PHY_PORT_TUNE1],
+				      PREEMPH_WIDTH_HALF_BIT);
+	}
+}
+
+/*
  * Fetches HS Tx tuning value from nvmem and sets the
  * QUSB2PHY_PORT_TUNE1/2 register.
  * For error case, skip setting the value and use the default value.
@@ -315,6 +396,10 @@ static void qusb2_phy_set_tune2_param(struct qusb2_phy *qphy)
 	const struct qusb2_phy_cfg *cfg = qphy->cfg;
 	u8 *val;
 
+	/* efuse register is optional */
+	if (!qphy->cell)
+		return;
+
 	/*
 	 * Read efuse register having TUNE2/1 parameter's high nibble.
 	 * If efuse register shows value as 0x0, or if we fail to find
@@ -521,6 +606,9 @@ static int qusb2_phy_init(struct phy *phy)
 	qcom_qusb2_phy_configure(qphy->base, cfg->regs, cfg->tbl,
 				 cfg->tbl_num);
 
+	/* Override board specific PHY tuning values */
+	qusb2_phy_override_phy_params(qphy);
+
 	/* Set efuse value for tuning the PHY */
 	qusb2_phy_set_tune2_param(qphy);
 
@@ -643,8 +731,8 @@ static const struct of_device_id qusb2_phy_of_match_table[] = {
 		.compatible	= "qcom,msm8996-qusb2-phy",
 		.data		= &msm8996_phy_cfg,
 	}, {
-		.compatible	= "qcom,qusb2-v2-phy",
-		.data		= &qusb2_v2_phy_cfg,
+		.compatible	= "qcom,sdm845-qusb2-phy",
+		.data		= &sdm845_phy_cfg,
 	},
 	{ },
 };
@@ -664,6 +752,7 @@ static int qusb2_phy_probe(struct platform_device *pdev)
 	struct resource *res;
 	int ret, i;
 	int num;
+	u32 value;
 
 	qphy = devm_kzalloc(dev, sizeof(*qphy), GFP_KERNEL);
 	if (!qphy)
@@ -732,6 +821,31 @@ static int qusb2_phy_probe(struct platform_device *pdev)
 		qphy->cell = NULL;
 		dev_dbg(dev, "failed to lookup tune2 hstx trim value\n");
 	}
+
+	if (!of_property_read_u32(dev->of_node, "qcom,imp-res-offset-value",
+				  &value)) {
+		qphy->imp_res_offset_value = (u8)value;
+		qphy->override_imp_res_offset = true;
+	}
+
+	if (!of_property_read_u32(dev->of_node, "qcom,hstx-trim-value",
+				  &value)) {
+		qphy->hstx_trim_value = (u8)value;
+		qphy->override_hstx_trim = true;
+	}
+
+	if (!of_property_read_u32(dev->of_node, "qcom,preemphasis-level",
+				     &value)) {
+		qphy->preemphasis_level = (u8)value;
+		qphy->override_preemphasis = true;
+	}
+
+	if (!of_property_read_u32(dev->of_node, "qcom,preemphasis-width",
+				     &value)) {
+		qphy->preemphasis_width = (u8)value;
+		qphy->override_preemphasis_width = true;
+	}
+
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 	/*
diff --git a/drivers/phy/samsung/phy-exynos-mipi-video.c b/drivers/phy/samsung/phy-exynos-mipi-video.c
index c198886f80a3..00d89599c67d 100644
--- a/drivers/phy/samsung/phy-exynos-mipi-video.c
+++ b/drivers/phy/samsung/phy-exynos-mipi-video.c
@@ -231,33 +231,27 @@ struct exynos_mipi_video_phy {
 static int __set_phy_state(const struct exynos_mipi_phy_desc *data,
 			   struct exynos_mipi_video_phy *state, unsigned int on)
 {
-	u32 val;
+	struct regmap *enable_map = state->regmaps[data->enable_map];
+	struct regmap *resetn_map = state->regmaps[data->resetn_map];
 
 	spin_lock(&state->slock);
 
 	/* disable in PMU sysreg */
 	if (!on && data->coupled_phy_id >= 0 &&
-	    state->phys[data->coupled_phy_id].phy->power_count == 0) {
-		regmap_read(state->regmaps[data->enable_map], data->enable_reg,
-			    &val);
-		val &= ~data->enable_val;
-		regmap_write(state->regmaps[data->enable_map], data->enable_reg,
-			     val);
-	}
-
+	    state->phys[data->coupled_phy_id].phy->power_count == 0)
+		regmap_update_bits(enable_map, data->enable_reg,
+				   data->enable_val, 0);
 	/* PHY reset */
-	regmap_read(state->regmaps[data->resetn_map], data->resetn_reg, &val);
-	val = on ? (val | data->resetn_val) : (val & ~data->resetn_val);
-	regmap_write(state->regmaps[data->resetn_map], data->resetn_reg, val);
-
+	if (on)
+		regmap_update_bits(resetn_map, data->resetn_reg,
+				   data->resetn_val, data->resetn_val);
+	else
+		regmap_update_bits(resetn_map, data->resetn_reg,
+				   data->resetn_val, 0);
 	/* enable in PMU sysreg */
-	if (on) {
-		regmap_read(state->regmaps[data->enable_map], data->enable_reg,
-			    &val);
-		val |= data->enable_val;
-		regmap_write(state->regmaps[data->enable_map], data->enable_reg,
-			     val);
-	}
+	if (on)
+		regmap_update_bits(enable_map, data->enable_reg,
+				   data->enable_val, data->enable_val);
 
 	spin_unlock(&state->slock);
 
diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c
index bc4e78a19c91..1255cd1d9a60 100644
--- a/drivers/phy/st/phy-stm32-usbphyc.c
+++ b/drivers/phy/st/phy-stm32-usbphyc.c
@@ -71,7 +71,6 @@ struct stm32_usbphyc {
 	struct stm32_usbphyc_phy **phys;
 	int nphys;
 	int switch_setup;
-	bool pll_enabled;
 };
 
 static inline void stm32_usbphyc_set_bits(void __iomem *reg, u32 bits)
@@ -84,7 +83,8 @@ static inline void stm32_usbphyc_clr_bits(void __iomem *reg, u32 bits)
 	writel_relaxed(readl_relaxed(reg) & ~bits, reg);
 }
 
-static void stm32_usbphyc_get_pll_params(u32 clk_rate, struct pll_params *pll_params)
+static void stm32_usbphyc_get_pll_params(u32 clk_rate,
+					 struct pll_params *pll_params)
 {
 	unsigned long long fvco, ndiv, frac;
 
@@ -271,7 +271,6 @@ static struct phy *stm32_usbphyc_of_xlate(struct device *dev,
 	struct stm32_usbphyc *usbphyc = dev_get_drvdata(dev);
 	struct stm32_usbphyc_phy *usbphyc_phy = NULL;
 	struct device_node *phynode = args->np;
-
 	int port = 0;
 
 	for (port = 0; port < usbphyc->nphys; port++) {
@@ -367,8 +366,8 @@ static int stm32_usbphyc_probe(struct platform_device *pdev)
 		if (IS_ERR(phy)) {
 			ret = PTR_ERR(phy);
 			if (ret != -EPROBE_DEFER)
-				dev_err(dev,
-					"failed to create phy%d: %d\n", i, ret);
+				dev_err(dev, "failed to create phy%d: %d\n",
+					port, ret);
 			goto put_child;
 		}
 
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 11aa5902a9ac..de1b4ebe4de2 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -102,19 +102,6 @@ tegra_xusb_pad_find_phy_node(struct tegra_xusb_pad *pad, unsigned int index)
 	return np;
 }
 
-static int
-tegra_xusb_lane_lookup_function(struct tegra_xusb_lane *lane,
-				    const char *function)
-{
-	unsigned int i;
-
-	for (i = 0; i < lane->soc->num_funcs; i++)
-		if (strcmp(function, lane->soc->funcs[i]) == 0)
-			return i;
-
-	return -EINVAL;
-}
-
 int tegra_xusb_lane_parse_dt(struct tegra_xusb_lane *lane,
 			     struct device_node *np)
 {
@@ -126,7 +113,7 @@ int tegra_xusb_lane_parse_dt(struct tegra_xusb_lane *lane,
 	if (err < 0)
 		return err;
 
-	err = tegra_xusb_lane_lookup_function(lane, function);
+	err = match_string(lane->soc->funcs, lane->soc->num_funcs, function);
 	if (err < 0) {
 		dev_err(dev, "invalid function \"%s\" for lane \"%s\"\n",
 			function, np->name);
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index b1ae1618fefe..fee9225ca559 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1622,22 +1622,30 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 
 	if (!need_valid_mask) {
 		irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0,
-						chip->ngpio, NUMA_NO_NODE);
+						community->npins, NUMA_NO_NODE);
 		if (irq_base < 0) {
 			dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n");
 			return irq_base;
 		}
-	} else {
-		irq_base = 0;
 	}
 
-	ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, irq_base,
+	ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0,
 				   handle_bad_irq, IRQ_TYPE_NONE);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to add IRQ chip\n");
 		return ret;
 	}
 
+	if (!need_valid_mask) {
+		for (i = 0; i < community->ngpio_ranges; i++) {
+			range = &community->gpio_ranges[i];
+
+			irq_domain_associate_many(chip->irq.domain, irq_base,
+						  range->base, range->npins);
+			irq_base += range->npins;
+		}
+	}
+
 	gpiochip_set_chained_irqchip(chip, &chv_gpio_irqchip, irq,
 				     chv_gpio_irq_handler);
 	return 0;
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index 8870a4100164..fee3435a6f15 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -36,6 +36,27 @@
 		.npins = ((e) - (s) + 1),		\
 	}
 
+#define SPTH_GPP(r, s, e, g)				\
+	{						\
+		.reg_num = (r),				\
+		.base = (s),				\
+		.size = ((e) - (s) + 1),		\
+		.gpio_base = (g),			\
+	}
+
+#define SPTH_COMMUNITY(b, s, e, g)			\
+	{						\
+		.barno = (b),				\
+		.padown_offset = SPT_PAD_OWN,		\
+		.padcfglock_offset = SPT_PADCFGLOCK,	\
+		.hostown_offset = SPT_HOSTSW_OWN,	\
+		.ie_offset = SPT_GPI_IE,		\
+		.pin_base = (s),			\
+		.npins = ((e) - (s) + 1),		\
+		.gpps = (g),				\
+		.ngpps = ARRAY_SIZE(g),			\
+	}
+
 /* Sunrisepoint-LP */
 static const struct pinctrl_pin_desc sptlp_pins[] = {
 	/* GPP_A */
@@ -531,10 +552,28 @@ static const struct intel_function spth_functions[] = {
 	FUNCTION("i2c2", spth_i2c2_groups),
 };
 
+static const struct intel_padgroup spth_community0_gpps[] = {
+	SPTH_GPP(0, 0, 23, 0),		/* GPP_A */
+	SPTH_GPP(1, 24, 47, 24),	/* GPP_B */
+};
+
+static const struct intel_padgroup spth_community1_gpps[] = {
+	SPTH_GPP(0, 48, 71, 48),	/* GPP_C */
+	SPTH_GPP(1, 72, 95, 72),	/* GPP_D */
+	SPTH_GPP(2, 96, 108, 96),	/* GPP_E */
+	SPTH_GPP(3, 109, 132, 120),	/* GPP_F */
+	SPTH_GPP(4, 133, 156, 144),	/* GPP_G */
+	SPTH_GPP(5, 157, 180, 168),	/* GPP_H */
+};
+
+static const struct intel_padgroup spth_community3_gpps[] = {
+	SPTH_GPP(0, 181, 191, 192),	/* GPP_I */
+};
+
 static const struct intel_community spth_communities[] = {
-	SPT_COMMUNITY(0, 0, 47),
-	SPT_COMMUNITY(1, 48, 180),
-	SPT_COMMUNITY(2, 181, 191),
+	SPTH_COMMUNITY(0, 0, 47, spth_community0_gpps),
+	SPTH_COMMUNITY(1, 48, 180, spth_community1_gpps),
+	SPTH_COMMUNITY(2, 181, 191, spth_community3_gpps),
 };
 
 static const struct intel_pinctrl_soc_data spth_soc_data = {
diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c
index 4b91ff74779b..99a6ceac8e53 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-axg.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c
@@ -898,7 +898,7 @@ static struct meson_bank meson_axg_periphs_banks[] = {
 
 static struct meson_bank meson_axg_aobus_banks[] = {
 	/*   name    first      last      irq	pullen  pull    dir     out     in  */
-	BANK("AO",   GPIOAO_0,  GPIOAO_9, 0, 13, 0,  16,  0, 0,  0,  0,  0, 16,  1,  0),
+	BANK("AO",   GPIOAO_0,  GPIOAO_13, 0, 13, 0,  16,  0, 0,  0,  0,  0, 16,  1,  0),
 };
 
 static struct meson_pmx_bank meson_axg_periphs_pmx_banks[] = {
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 6cbcff42ba47..dfed60982a8a 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -267,12 +267,13 @@ static void stm32_gpio_irq_release_resources(struct irq_data *irq_data)
 }
 
 static struct irq_chip stm32_gpio_irq_chip = {
-	.name           = "stm32gpio",
-	.irq_ack       = irq_chip_ack_parent,
-	.irq_mask       = irq_chip_mask_parent,
-	.irq_unmask     = irq_chip_unmask_parent,
-	.irq_set_type   = irq_chip_set_type_parent,
-	.irq_set_wake   = irq_chip_set_wake_parent,
+	.name		= "stm32gpio",
+	.irq_eoi	= irq_chip_eoi_parent,
+	.irq_ack	= irq_chip_ack_parent,
+	.irq_mask	= irq_chip_mask_parent,
+	.irq_unmask	= irq_chip_unmask_parent,
+	.irq_set_type	= irq_chip_set_type_parent,
+	.irq_set_wake	= irq_chip_set_wake_parent,
 	.irq_request_resources = stm32_gpio_irq_request_resources,
 	.irq_release_resources = stm32_gpio_irq_release_resources,
 };
diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig
index e728a96cabfd..cb0df9eb3e0f 100644
--- a/drivers/platform/chrome/Kconfig
+++ b/drivers/platform/chrome/Kconfig
@@ -38,6 +38,17 @@ config CHROMEOS_PSTORE
 	  If you have a supported Chromebook, choose Y or M here.
 	  The module will be called chromeos_pstore.
 
+config CHROMEOS_TBMC
+	tristate "ChromeOS Tablet Switch Controller"
+	depends on ACPI
+	depends on INPUT
+	help
+	  This option adds a driver for the tablet switch on
+	  select Chrome OS systems.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called chromeos_tbmc.
+
 config CROS_EC_CTL
         tristate
 
diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile
index ff3b369911f0..e44c37a63fa9 100644
--- a/drivers/platform/chrome/Makefile
+++ b/drivers/platform/chrome/Makefile
@@ -2,6 +2,7 @@
 
 obj-$(CONFIG_CHROMEOS_LAPTOP)		+= chromeos_laptop.o
 obj-$(CONFIG_CHROMEOS_PSTORE)		+= chromeos_pstore.o
+obj-$(CONFIG_CHROMEOS_TBMC)		+= chromeos_tbmc.o
 cros_ec_ctl-objs			:= cros_ec_sysfs.o cros_ec_lightbar.o \
 					   cros_ec_vbc.o cros_ec_debugfs.o
 obj-$(CONFIG_CROS_EC_CTL)		+= cros_ec_ctl.o
diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c
index 5c47f451e43b..24326eecd787 100644
--- a/drivers/platform/chrome/chromeos_laptop.c
+++ b/drivers/platform/chrome/chromeos_laptop.c
@@ -6,6 +6,7 @@
 
 #define pr_fmt(fmt)		KBUILD_MODNAME ": " fmt
 
+#include <linux/acpi.h>
 #include <linux/dmi.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
@@ -54,6 +55,11 @@ struct i2c_peripheral {
 	struct i2c_client *client;
 };
 
+struct acpi_peripheral {
+	char hid[ACPI_ID_LEN];
+	const struct property_entry *properties;
+};
+
 struct chromeos_laptop {
 	/*
 	 * Note that we can't mark this pointer as const because
@@ -61,6 +67,9 @@ struct chromeos_laptop {
 	 */
 	struct i2c_peripheral *i2c_peripherals;
 	unsigned int num_i2c_peripherals;
+
+	const struct acpi_peripheral *acpi_peripherals;
+	unsigned int num_acpi_peripherals;
 };
 
 static const struct chromeos_laptop *cros_laptop;
@@ -148,6 +157,38 @@ static void chromeos_laptop_check_adapter(struct i2c_adapter *adapter)
 	}
 }
 
+static bool chromeos_laptop_adjust_client(struct i2c_client *client)
+{
+	const struct acpi_peripheral *acpi_dev;
+	struct acpi_device_id acpi_ids[2] = { };
+	int i;
+	int error;
+
+	if (!has_acpi_companion(&client->dev))
+		return false;
+
+	for (i = 0; i < cros_laptop->num_acpi_peripherals; i++) {
+		acpi_dev = &cros_laptop->acpi_peripherals[i];
+
+		memcpy(acpi_ids[0].id, acpi_dev->hid, ACPI_ID_LEN);
+
+		if (acpi_match_device(acpi_ids, &client->dev)) {
+			error = device_add_properties(&client->dev,
+						      acpi_dev->properties);
+			if (error) {
+				dev_err(&client->dev,
+					"failed to add properties: %d\n",
+					error);
+				break;
+			}
+
+			return true;
+		}
+	}
+
+	return false;
+}
+
 static void chromeos_laptop_detach_i2c_client(struct i2c_client *client)
 {
 	struct i2c_peripheral *i2c_dev;
@@ -170,6 +211,8 @@ static int chromeos_laptop_i2c_notifier_call(struct notifier_block *nb,
 	case BUS_NOTIFY_ADD_DEVICE:
 		if (dev->type == &i2c_adapter_type)
 			chromeos_laptop_check_adapter(to_i2c_adapter(dev));
+		else if (dev->type == &i2c_client_type)
+			chromeos_laptop_adjust_client(to_i2c_client(dev));
 		break;
 
 	case BUS_NOTIFY_REMOVED_DEVICE:
@@ -191,6 +234,12 @@ static const struct chromeos_laptop _name __initconst = {		\
 	.num_i2c_peripherals	= ARRAY_SIZE(_name##_peripherals),	\
 }
 
+#define DECLARE_ACPI_CROS_LAPTOP(_name)					\
+static const struct chromeos_laptop _name __initconst = {		\
+	.acpi_peripherals	= _name##_peripherals,			\
+	.num_acpi_peripherals	= ARRAY_SIZE(_name##_peripherals),	\
+}
+
 static struct i2c_peripheral samsung_series_5_550_peripherals[] __initdata = {
 	/* Touchpad. */
 	{
@@ -234,16 +283,25 @@ static const int chromebook_pixel_tp_keys[] __initconst = {
 
 static const struct property_entry
 chromebook_pixel_trackpad_props[] __initconst = {
+	PROPERTY_ENTRY_STRING("compatible", "atmel,maxtouch"),
 	PROPERTY_ENTRY_U32_ARRAY("linux,gpio-keymap", chromebook_pixel_tp_keys),
 	{ }
 };
 
+static const struct property_entry
+chromebook_atmel_touchscreen_props[] __initconst = {
+	PROPERTY_ENTRY_STRING("compatible", "atmel,maxtouch"),
+	{ }
+};
+
 static struct i2c_peripheral chromebook_pixel_peripherals[] __initdata = {
 	/* Touch Screen. */
 	{
 		.board_info	= {
 			I2C_BOARD_INFO("atmel_mxt_ts",
 					ATMEL_TS_I2C_ADDR),
+			.properties	=
+				chromebook_atmel_touchscreen_props,
 			.flags		= I2C_CLIENT_WAKE,
 		},
 		.dmi_name	= "touchscreen",
@@ -354,6 +412,8 @@ static struct i2c_peripheral acer_c720_peripherals[] __initdata = {
 		.board_info	= {
 			I2C_BOARD_INFO("atmel_mxt_ts",
 					ATMEL_TS_I2C_ADDR),
+			.properties	=
+				chromebook_atmel_touchscreen_props,
 			.flags		= I2C_CLIENT_WAKE,
 		},
 		.dmi_name	= "touchscreen",
@@ -419,6 +479,47 @@ static struct i2c_peripheral cr48_peripherals[] __initdata = {
 };
 DECLARE_CROS_LAPTOP(cr48);
 
+static const u32 samus_touchpad_buttons[] __initconst = {
+	KEY_RESERVED,
+	KEY_RESERVED,
+	KEY_RESERVED,
+	BTN_LEFT
+};
+
+static const struct property_entry samus_trackpad_props[] __initconst = {
+	PROPERTY_ENTRY_STRING("compatible", "atmel,maxtouch"),
+	PROPERTY_ENTRY_U32_ARRAY("linux,gpio-keymap", samus_touchpad_buttons),
+	{ }
+};
+
+static struct acpi_peripheral samus_peripherals[] __initdata = {
+	/* Touchpad */
+	{
+		.hid		= "ATML0000",
+		.properties	= samus_trackpad_props,
+	},
+	/* Touchsceen */
+	{
+		.hid		= "ATML0001",
+		.properties	= chromebook_atmel_touchscreen_props,
+	},
+};
+DECLARE_ACPI_CROS_LAPTOP(samus);
+
+static struct acpi_peripheral generic_atmel_peripherals[] __initdata = {
+	/* Touchpad */
+	{
+		.hid		= "ATML0000",
+		.properties	= chromebook_pixel_trackpad_props,
+	},
+	/* Touchsceen */
+	{
+		.hid		= "ATML0001",
+		.properties	= chromebook_atmel_touchscreen_props,
+	},
+};
+DECLARE_ACPI_CROS_LAPTOP(generic_atmel);
+
 static const struct dmi_system_id chromeos_laptop_dmi_table[] __initconst = {
 	{
 		.ident = "Samsung Series 5 550",
@@ -502,17 +603,72 @@ static const struct dmi_system_id chromeos_laptop_dmi_table[] __initconst = {
 		},
 		.driver_data = (void *)&cr48,
 	},
+	/* Devices with peripherals incompletely described in ACPI */
+	{
+		.ident = "Chromebook Pro",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Caroline"),
+		},
+		.driver_data = (void *)&samus,
+	},
+	{
+		.ident = "Google Pixel 2 (2015)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Samus"),
+		},
+		.driver_data = (void *)&samus,
+	},
+	{
+		.ident = "Samsung Chromebook 3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Celes"),
+		},
+		.driver_data = (void *)&samus,
+	},
+	{
+		/*
+		 * Other Chromebooks with Atmel touch controllers:
+		 * - Winky (touchpad)
+		 * - Clapper, Expresso, Rambi, Glimmer (touchscreen)
+		 */
+		.ident = "Other Chromebook",
+		.matches = {
+			/*
+			 * This will match all Google devices, not only devices
+			 * with Atmel, but we will validate that the device
+			 * actually has matching peripherals.
+			 */
+			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+		},
+		.driver_data = (void *)&generic_atmel,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(dmi, chromeos_laptop_dmi_table);
 
-static int __init chromeos_laptop_scan_adapter(struct device *dev, void *data)
+static int __init chromeos_laptop_scan_peripherals(struct device *dev, void *data)
 {
-	struct i2c_adapter *adapter;
+	int error;
 
-	adapter = i2c_verify_adapter(dev);
-	if (adapter)
-		chromeos_laptop_check_adapter(adapter);
+	if (dev->type == &i2c_adapter_type) {
+		chromeos_laptop_check_adapter(to_i2c_adapter(dev));
+	} else if (dev->type == &i2c_client_type) {
+		if (chromeos_laptop_adjust_client(to_i2c_client(dev))) {
+			/*
+			 * Now that we have needed properties re-trigger
+			 * driver probe in case driver was initialized
+			 * earlier and probe failed.
+			 */
+			error = device_attach(dev);
+			if (error < 0)
+				dev_warn(dev,
+					 "%s: device_attach() failed: %d\n",
+					 __func__, error);
+		}
+	}
 
 	return 0;
 }
@@ -556,27 +712,24 @@ static int __init chromeos_laptop_setup_irq(struct i2c_peripheral *i2c_dev)
 	return 0;
 }
 
-static struct chromeos_laptop * __init
-chromeos_laptop_prepare(const struct chromeos_laptop *src)
+static int __init
+chromeos_laptop_prepare_i2c_peripherals(struct chromeos_laptop *cros_laptop,
+					const struct chromeos_laptop *src)
 {
-	struct chromeos_laptop *cros_laptop;
 	struct i2c_peripheral *i2c_dev;
 	struct i2c_board_info *info;
-	int error;
 	int i;
+	int error;
 
-	cros_laptop = kzalloc(sizeof(*cros_laptop), GFP_KERNEL);
-	if (!cros_laptop)
-		return ERR_PTR(-ENOMEM);
+	if (!src->num_i2c_peripherals)
+		return 0;
 
 	cros_laptop->i2c_peripherals = kmemdup(src->i2c_peripherals,
 					       src->num_i2c_peripherals *
 						sizeof(*src->i2c_peripherals),
 					       GFP_KERNEL);
-	if (!cros_laptop->i2c_peripherals) {
-		error = -ENOMEM;
-		goto err_free_cros_laptop;
-	}
+	if (!cros_laptop->i2c_peripherals)
+		return -ENOMEM;
 
 	cros_laptop->num_i2c_peripherals = src->num_i2c_peripherals;
 
@@ -586,7 +739,7 @@ chromeos_laptop_prepare(const struct chromeos_laptop *src)
 
 		error = chromeos_laptop_setup_irq(i2c_dev);
 		if (error)
-			goto err_destroy_cros_peripherals;
+			goto err_out;
 
 		/* We need to deep-copy properties */
 		if (info->properties) {
@@ -594,14 +747,14 @@ chromeos_laptop_prepare(const struct chromeos_laptop *src)
 				property_entries_dup(info->properties);
 			if (IS_ERR(info->properties)) {
 				error = PTR_ERR(info->properties);
-				goto err_destroy_cros_peripherals;
+				goto err_out;
 			}
 		}
 	}
 
-	return cros_laptop;
+	return 0;
 
-err_destroy_cros_peripherals:
+err_out:
 	while (--i >= 0) {
 		i2c_dev = &cros_laptop->i2c_peripherals[i];
 		info = &i2c_dev->board_info;
@@ -609,13 +762,74 @@ err_destroy_cros_peripherals:
 			property_entries_free(info->properties);
 	}
 	kfree(cros_laptop->i2c_peripherals);
-err_free_cros_laptop:
-	kfree(cros_laptop);
-	return ERR_PTR(error);
+	return error;
+}
+
+static int __init
+chromeos_laptop_prepare_acpi_peripherals(struct chromeos_laptop *cros_laptop,
+					const struct chromeos_laptop *src)
+{
+	struct acpi_peripheral *acpi_peripherals;
+	struct acpi_peripheral *acpi_dev;
+	const struct acpi_peripheral *src_dev;
+	int n_peripherals = 0;
+	int i;
+	int error;
+
+	for (i = 0; i < src->num_acpi_peripherals; i++) {
+		if (acpi_dev_present(src->acpi_peripherals[i].hid, NULL, -1))
+			n_peripherals++;
+	}
+
+	if (!n_peripherals)
+		return 0;
+
+	acpi_peripherals = kcalloc(n_peripherals,
+				   sizeof(*src->acpi_peripherals),
+				   GFP_KERNEL);
+	if (!acpi_peripherals)
+		return -ENOMEM;
+
+	acpi_dev = acpi_peripherals;
+	for (i = 0; i < src->num_acpi_peripherals; i++) {
+		src_dev = &src->acpi_peripherals[i];
+		if (!acpi_dev_present(src_dev->hid, NULL, -1))
+			continue;
+
+		*acpi_dev = *src_dev;
+
+		/* We need to deep-copy properties */
+		if (src_dev->properties) {
+			acpi_dev->properties =
+				property_entries_dup(src_dev->properties);
+			if (IS_ERR(acpi_dev->properties)) {
+				error = PTR_ERR(acpi_dev->properties);
+				goto err_out;
+			}
+		}
+
+		acpi_dev++;
+	}
+
+	cros_laptop->acpi_peripherals = acpi_peripherals;
+	cros_laptop->num_acpi_peripherals = n_peripherals;
+
+	return 0;
+
+err_out:
+	while (--i >= 0) {
+		acpi_dev = &acpi_peripherals[i];
+		if (acpi_dev->properties)
+			property_entries_free(acpi_dev->properties);
+	}
+
+	kfree(acpi_peripherals);
+	return error;
 }
 
 static void chromeos_laptop_destroy(const struct chromeos_laptop *cros_laptop)
 {
+	const struct acpi_peripheral *acpi_dev;
 	struct i2c_peripheral *i2c_dev;
 	struct i2c_board_info *info;
 	int i;
@@ -631,10 +845,41 @@ static void chromeos_laptop_destroy(const struct chromeos_laptop *cros_laptop)
 			property_entries_free(info->properties);
 	}
 
+	for (i = 0; i < cros_laptop->num_acpi_peripherals; i++) {
+		acpi_dev = &cros_laptop->acpi_peripherals[i];
+
+		if (acpi_dev->properties)
+			property_entries_free(acpi_dev->properties);
+	}
+
 	kfree(cros_laptop->i2c_peripherals);
+	kfree(cros_laptop->acpi_peripherals);
 	kfree(cros_laptop);
 }
 
+static struct chromeos_laptop * __init
+chromeos_laptop_prepare(const struct chromeos_laptop *src)
+{
+	struct chromeos_laptop *cros_laptop;
+	int error;
+
+	cros_laptop = kzalloc(sizeof(*cros_laptop), GFP_KERNEL);
+	if (!cros_laptop)
+		return ERR_PTR(-ENOMEM);
+
+	error = chromeos_laptop_prepare_i2c_peripherals(cros_laptop, src);
+	if (!error)
+		error = chromeos_laptop_prepare_acpi_peripherals(cros_laptop,
+								 src);
+
+	if (error) {
+		chromeos_laptop_destroy(cros_laptop);
+		return ERR_PTR(error);
+	}
+
+	return cros_laptop;
+}
+
 static int __init chromeos_laptop_init(void)
 {
 	const struct dmi_system_id *dmi_id;
@@ -652,21 +897,33 @@ static int __init chromeos_laptop_init(void)
 	if (IS_ERR(cros_laptop))
 		return PTR_ERR(cros_laptop);
 
+	if (!cros_laptop->num_i2c_peripherals &&
+	    !cros_laptop->num_acpi_peripherals) {
+		pr_debug("no relevant devices detected\n");
+		error = -ENODEV;
+		goto err_destroy_cros_laptop;
+	}
+
 	error = bus_register_notifier(&i2c_bus_type,
 				      &chromeos_laptop_i2c_notifier);
 	if (error) {
-		pr_err("failed to register i2c bus notifier: %d\n", error);
-		chromeos_laptop_destroy(cros_laptop);
-		return error;
+		pr_err("failed to register i2c bus notifier: %d\n",
+		       error);
+		goto err_destroy_cros_laptop;
 	}
 
 	/*
-	 * Scan adapters that have been registered before we installed
-	 * the notifier to make sure we do not miss any devices.
+	 * Scan adapters that have been registered and clients that have
+	 * been created before we installed the notifier to make sure
+	 * we do not miss any devices.
 	 */
-	i2c_for_each_dev(NULL, chromeos_laptop_scan_adapter);
+	i2c_for_each_dev(NULL, chromeos_laptop_scan_peripherals);
 
 	return 0;
+
+err_destroy_cros_laptop:
+	chromeos_laptop_destroy(cros_laptop);
+	return error;
 }
 
 static void __exit chromeos_laptop_exit(void)
diff --git a/drivers/platform/chrome/chromeos_tbmc.c b/drivers/platform/chrome/chromeos_tbmc.c
new file mode 100644
index 000000000000..b935df6a9694
--- /dev/null
+++ b/drivers/platform/chrome/chromeos_tbmc.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Driver to detect Tablet Mode for ChromeOS convertible.
+//
+// Copyright (C) 2017 Google, Inc.
+// Author: Gwendal Grignou <gwendal@chromium.org>
+
+#include <linux/acpi.h>
+#include <linux/input.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+
+#define DRV_NAME "chromeos_tbmc"
+#define ACPI_DRV_NAME "GOOG0006"
+
+static int chromeos_tbmc_query_switch(struct acpi_device *adev,
+				     struct input_dev *idev)
+{
+	unsigned long long state;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(adev->handle, "TBMC", NULL, &state);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	/* input layer checks if event is redundant */
+	input_report_switch(idev, SW_TABLET_MODE, state);
+	input_sync(idev);
+
+	return 0;
+}
+
+static __maybe_unused int chromeos_tbmc_resume(struct device *dev)
+{
+	struct acpi_device *adev = to_acpi_device(dev);
+
+	return chromeos_tbmc_query_switch(adev, adev->driver_data);
+}
+
+static void chromeos_tbmc_notify(struct acpi_device *adev, u32 event)
+{
+	switch (event) {
+	case 0x80:
+		chromeos_tbmc_query_switch(adev, adev->driver_data);
+		break;
+	default:
+		dev_err(&adev->dev, "Unexpected event: 0x%08X\n", event);
+	}
+}
+
+static int chromeos_tbmc_open(struct input_dev *idev)
+{
+	struct acpi_device *adev = input_get_drvdata(idev);
+
+	return chromeos_tbmc_query_switch(adev, idev);
+}
+
+static int chromeos_tbmc_add(struct acpi_device *adev)
+{
+	struct input_dev *idev;
+	struct device *dev = &adev->dev;
+	int ret;
+
+	idev = devm_input_allocate_device(dev);
+	if (!idev)
+		return -ENOMEM;
+
+	idev->name = "Tablet Mode Switch";
+	idev->phys = acpi_device_hid(adev);
+
+	idev->id.bustype = BUS_HOST;
+	idev->id.version = 1;
+	idev->id.product = 0;
+	idev->open = chromeos_tbmc_open;
+
+	input_set_drvdata(idev, adev);
+	adev->driver_data = idev;
+
+	input_set_capability(idev, EV_SW, SW_TABLET_MODE);
+	ret = input_register_device(idev);
+	if (ret) {
+		dev_err(dev, "cannot register input device\n");
+		return ret;
+	}
+	return 0;
+}
+
+static const struct acpi_device_id chromeos_tbmc_acpi_device_ids[] = {
+	{ ACPI_DRV_NAME, 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, chromeos_tbmc_acpi_device_ids);
+
+static const SIMPLE_DEV_PM_OPS(chromeos_tbmc_pm_ops, NULL,
+		chromeos_tbmc_resume);
+
+static struct acpi_driver chromeos_tbmc_driver = {
+	.name = DRV_NAME,
+	.class = DRV_NAME,
+	.ids = chromeos_tbmc_acpi_device_ids,
+	.ops = {
+		.add = chromeos_tbmc_add,
+		.notify = chromeos_tbmc_notify,
+	},
+	.drv.pm = &chromeos_tbmc_pm_ops,
+};
+
+module_acpi_driver(chromeos_tbmc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("ChromeOS ACPI tablet switch driver");
diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c
index 6ea79d495aa2..68193bb53383 100644
--- a/drivers/platform/chrome/cros_ec_lightbar.c
+++ b/drivers/platform/chrome/cros_ec_lightbar.c
@@ -170,8 +170,7 @@ static ssize_t version_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	uint32_t version = 0, flags = 0;
-	struct cros_ec_dev *ec = container_of(dev,
-					      struct cros_ec_dev, class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 	int ret;
 
 	ret = lb_throttle();
@@ -193,8 +192,7 @@ static ssize_t brightness_store(struct device *dev,
 	struct cros_ec_command *msg;
 	int ret;
 	unsigned int val;
-	struct cros_ec_dev *ec = container_of(dev,
-					      struct cros_ec_dev, class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 
 	if (kstrtouint(buf, 0, &val))
 		return -EINVAL;
@@ -238,8 +236,7 @@ static ssize_t led_rgb_store(struct device *dev, struct device_attribute *attr,
 {
 	struct ec_params_lightbar *param;
 	struct cros_ec_command *msg;
-	struct cros_ec_dev *ec = container_of(dev,
-					      struct cros_ec_dev, class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 	unsigned int val[4];
 	int ret, i = 0, j = 0, ok = 0;
 
@@ -311,8 +308,7 @@ static ssize_t sequence_show(struct device *dev,
 	struct ec_response_lightbar *resp;
 	struct cros_ec_command *msg;
 	int ret;
-	struct cros_ec_dev *ec = container_of(dev,
-					      struct cros_ec_dev, class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 
 	msg = alloc_lightbar_cmd_msg(ec);
 	if (!msg)
@@ -439,8 +435,7 @@ static ssize_t sequence_store(struct device *dev, struct device_attribute *attr,
 	struct cros_ec_command *msg;
 	unsigned int num;
 	int ret, len;
-	struct cros_ec_dev *ec = container_of(dev,
-					      struct cros_ec_dev, class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 
 	for (len = 0; len < count; len++)
 		if (!isalnum(buf[len]))
@@ -488,8 +483,7 @@ static ssize_t program_store(struct device *dev, struct device_attribute *attr,
 	int extra_bytes, max_size, ret;
 	struct ec_params_lightbar *param;
 	struct cros_ec_command *msg;
-	struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
-					      class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 
 	/*
 	 * We might need to reject the program for size reasons. The EC
@@ -599,8 +593,7 @@ static umode_t cros_ec_lightbar_attrs_are_visible(struct kobject *kobj,
 						  struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
-	struct cros_ec_dev *ec = container_of(dev,
-					      struct cros_ec_dev, class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 	struct platform_device *pdev = to_platform_device(ec->dev);
 	struct cros_ec_platform *pdata = pdev->dev.platform_data;
 	int is_cros_ec;
diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
index 3682e1539251..31c8b8c49e45 100644
--- a/drivers/platform/chrome/cros_ec_lpc.c
+++ b/drivers/platform/chrome/cros_ec_lpc.c
@@ -435,7 +435,13 @@ static int __init cros_ec_lpc_init(void)
 	int ret;
 	acpi_status status;
 
-	if (!dmi_check_system(cros_ec_lpc_dmi_table)) {
+	status = acpi_get_devices(ACPI_DRV_NAME, cros_ec_lpc_parse_device,
+				  &cros_ec_lpc_acpi_device_found, NULL);
+	if (ACPI_FAILURE(status))
+		pr_warn(DRV_NAME ": Looking for %s failed\n", ACPI_DRV_NAME);
+
+	if (!cros_ec_lpc_acpi_device_found &&
+	    !dmi_check_system(cros_ec_lpc_dmi_table)) {
 		pr_err(DRV_NAME ": unsupported system.\n");
 		return -ENODEV;
 	}
@@ -450,11 +456,6 @@ static int __init cros_ec_lpc_init(void)
 		return ret;
 	}
 
-	status = acpi_get_devices(ACPI_DRV_NAME, cros_ec_lpc_parse_device,
-				  &cros_ec_lpc_acpi_device_found, NULL);
-	if (ACPI_FAILURE(status))
-		pr_warn(DRV_NAME ": Looking for %s failed\n", ACPI_DRV_NAME);
-
 	if (!cros_ec_lpc_acpi_device_found) {
 		/* Register the device, and it'll get hooked up automatically */
 		ret = platform_device_register(&cros_ec_lpc_device);
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index e7bbdf947bbc..8350ca2311c7 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -91,6 +91,8 @@ static int send_command(struct cros_ec_device *ec_dev,
 			usleep_range(10000, 11000);
 
 			ret = (*xfer_fxn)(ec_dev, status_msg);
+			if (ret == -EAGAIN)
+				continue;
 			if (ret < 0)
 				break;
 
diff --git a/drivers/platform/chrome/cros_ec_sysfs.c b/drivers/platform/chrome/cros_ec_sysfs.c
index 5a6db3fe213a..f34a50121064 100644
--- a/drivers/platform/chrome/cros_ec_sysfs.c
+++ b/drivers/platform/chrome/cros_ec_sysfs.c
@@ -34,8 +34,6 @@
 #include <linux/types.h>
 #include <linux/uaccess.h>
 
-#define to_cros_ec_dev(dev)  container_of(dev, struct cros_ec_dev, class_dev)
-
 /* Accessor functions */
 
 static ssize_t reboot_show(struct device *dev,
diff --git a/drivers/platform/chrome/cros_ec_vbc.c b/drivers/platform/chrome/cros_ec_vbc.c
index 6d38e6b08334..5356f26bc022 100644
--- a/drivers/platform/chrome/cros_ec_vbc.c
+++ b/drivers/platform/chrome/cros_ec_vbc.c
@@ -29,8 +29,7 @@ static ssize_t vboot_context_read(struct file *filp, struct kobject *kobj,
 				  loff_t pos, size_t count)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
-	struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
-					      class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 	struct cros_ec_device *ecdev = ec->ec_dev;
 	struct ec_params_vbnvcontext *params;
 	struct cros_ec_command *msg;
@@ -70,8 +69,7 @@ static ssize_t vboot_context_write(struct file *filp, struct kobject *kobj,
 				   loff_t pos, size_t count)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
-	struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
-					      class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 	struct cros_ec_device *ecdev = ec->ec_dev;
 	struct ec_params_vbnvcontext *params;
 	struct cros_ec_command *msg;
@@ -111,8 +109,7 @@ static umode_t cros_ec_vbc_is_visible(struct kobject *kobj,
 				      struct bin_attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
-	struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
-					      class_dev);
+	struct cros_ec_dev *ec = to_cros_ec_dev(dev);
 	struct device_node *np = ec->ec_dev->dev->of_node;
 
 	if (IS_ENABLED(CONFIG_OF) && np) {
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 39d06dd1f63a..f27cb186437d 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -154,7 +154,7 @@ config DELL_LAPTOP
 	depends on ACPI_VIDEO || ACPI_VIDEO = n
 	depends on RFKILL || RFKILL = n
 	depends on SERIO_I8042
-	select DELL_SMBIOS
+	depends on DELL_SMBIOS
 	select POWER_SUPPLY
 	select LEDS_CLASS
 	select NEW_LEDS
@@ -168,8 +168,8 @@ config DELL_WMI
 	depends on DMI
 	depends on INPUT
 	depends on ACPI_VIDEO || ACPI_VIDEO = n
+	depends on DELL_SMBIOS
 	select DELL_WMI_DESCRIPTOR
-	select DELL_SMBIOS
 	select INPUT_SPARSEKMAP
 	---help---
 	  Say Y here if you want to support WMI-based hotkeys on Dell laptops.
@@ -866,6 +866,7 @@ config ACPI_CMPC
 config INTEL_CHT_INT33FE
 	tristate "Intel Cherry Trail ACPI INT33FE Driver"
 	depends on X86 && ACPI && I2C && REGULATOR
+	depends on CHARGER_BQ24190=y || (CHARGER_BQ24190=m && m)
 	---help---
 	  This driver add support for the INT33FE ACPI device found on
 	  some Intel Cherry Trail devices.
@@ -877,8 +878,7 @@ config INTEL_CHT_INT33FE
 	  i2c drivers for these chips can bind to the them.
 
 	  If you enable this driver it is advised to also select
-	  CONFIG_TYPEC_FUSB302=m, CONFIG_CHARGER_BQ24190=m and
-	  CONFIG_BATTERY_MAX17042=m.
+	  CONFIG_TYPEC_FUSB302=m and CONFIG_BATTERY_MAX17042=m.
 
 config INTEL_INT0002_VGPIO
 	tristate "Intel ACPI INT0002 Virtual GPIO driver"
diff --git a/drivers/platform/x86/asus-wireless.c b/drivers/platform/x86/asus-wireless.c
index d4aeac3477f5..f086469ea740 100644
--- a/drivers/platform/x86/asus-wireless.c
+++ b/drivers/platform/x86/asus-wireless.c
@@ -178,8 +178,10 @@ static int asus_wireless_remove(struct acpi_device *adev)
 {
 	struct asus_wireless_data *data = acpi_driver_data(adev);
 
-	if (data->wq)
+	if (data->wq) {
+		devm_led_classdev_unregister(&adev->dev, &data->led);
 		destroy_workqueue(data->wq);
+	}
 	return 0;
 }
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index a32c5c00e0e7..ffffb9909ae1 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -163,6 +163,16 @@ MODULE_LICENSE("GPL");
 
 static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
 
+static bool ashs_present(void)
+{
+	int i = 0;
+	while (ashs_ids[i]) {
+		if (acpi_dev_found(ashs_ids[i++]))
+			return true;
+	}
+	return false;
+}
+
 struct bios_args {
 	u32 arg0;
 	u32 arg1;
@@ -1025,6 +1035,9 @@ static int asus_new_rfkill(struct asus_wmi *asus,
 
 static void asus_wmi_rfkill_exit(struct asus_wmi *asus)
 {
+	if (asus->driver->wlan_ctrl_by_user && ashs_present())
+		return;
+
 	asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P5");
 	asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P6");
 	asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P7");
@@ -2121,16 +2134,6 @@ static int asus_wmi_fan_init(struct asus_wmi *asus)
 	return 0;
 }
 
-static bool ashs_present(void)
-{
-	int i = 0;
-	while (ashs_ids[i]) {
-		if (acpi_dev_found(ashs_ids[i++]))
-			return true;
-	}
-	return false;
-}
-
 /*
  * WMI Driver
  */
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index e8d058c5ef21..eef76bfa5d73 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -1689,19 +1689,6 @@ static int version_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int version_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, version_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations version_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= version_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /*
  * Proc and module init
  */
@@ -1722,8 +1709,8 @@ static void create_toshiba_proc_entries(struct toshiba_acpi_dev *dev)
 	if (dev->hotkey_dev)
 		proc_create_data("keys", S_IRUGO | S_IWUSR, toshiba_proc_dir,
 				 &keys_proc_fops, dev);
-	proc_create_data("version", S_IRUGO, toshiba_proc_dir,
-			 &version_proc_fops, dev);
+	proc_create_single_data("version", S_IRUGO, toshiba_proc_dir,
+			version_proc_show, dev);
 }
 
 static void remove_toshiba_proc_entries(struct toshiba_acpi_dev *dev)
diff --git a/drivers/pnp/pnpbios/proc.c b/drivers/pnp/pnpbios/proc.c
index 7d4aca7948dd..fe1c8f5d9af0 100644
--- a/drivers/pnp/pnpbios/proc.c
+++ b/drivers/pnp/pnpbios/proc.c
@@ -47,19 +47,6 @@ static int pnpconfig_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int pnpconfig_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pnpconfig_proc_show, NULL);
-}
-
-static const struct file_operations pnpconfig_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pnpconfig_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int escd_info_proc_show(struct seq_file *m, void *v)
 {
 	struct escd_info_struc escd;
@@ -74,19 +61,6 @@ static int escd_info_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int escd_info_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, escd_info_proc_show, NULL);
-}
-
-static const struct file_operations escd_info_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= escd_info_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 #define MAX_SANE_ESCD_SIZE (32*1024)
 static int escd_proc_show(struct seq_file *m, void *v)
 {
@@ -129,19 +103,6 @@ static int escd_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int escd_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, escd_proc_show, NULL);
-}
-
-static const struct file_operations escd_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= escd_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int pnp_legacyres_proc_show(struct seq_file *m, void *v)
 {
 	void *buf;
@@ -159,19 +120,6 @@ static int pnp_legacyres_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int pnp_legacyres_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pnp_legacyres_proc_show, NULL);
-}
-
-static const struct file_operations pnp_legacyres_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pnp_legacyres_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int pnp_devices_proc_show(struct seq_file *m, void *v)
 {
 	struct pnp_bios_node *node;
@@ -202,19 +150,6 @@ static int pnp_devices_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int pnp_devices_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pnp_devices_proc_show, NULL);
-}
-
-static const struct file_operations pnp_devices_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pnp_devices_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int pnpbios_proc_show(struct seq_file *m, void *v)
 {
 	void *data = m->private;
@@ -318,12 +253,13 @@ int __init pnpbios_proc_init(void)
 	proc_pnp_boot = proc_mkdir("boot", proc_pnp);
 	if (!proc_pnp_boot)
 		return -EIO;
-	proc_create("devices", 0, proc_pnp, &pnp_devices_proc_fops);
-	proc_create("configuration_info", 0, proc_pnp, &pnpconfig_proc_fops);
-	proc_create("escd_info", 0, proc_pnp, &escd_info_proc_fops);
-	proc_create("escd", S_IRUSR, proc_pnp, &escd_proc_fops);
-	proc_create("legacy_device_resources", 0, proc_pnp, &pnp_legacyres_proc_fops);
-
+	proc_create_single("devices", 0, proc_pnp, pnp_devices_proc_show);
+	proc_create_single("configuration_info", 0, proc_pnp,
+			pnpconfig_proc_show);
+	proc_create_single("escd_info", 0, proc_pnp, escd_info_proc_show);
+	proc_create_single("escd", S_IRUSR, proc_pnp, escd_proc_show);
+	proc_create_single("legacy_device_resources", 0, proc_pnp,
+			pnp_legacyres_proc_show);
 	return 0;
 }
 
diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c
index ed2b109ae8fc..d6a5e6bf5f12 100644
--- a/drivers/power/avs/rockchip-io-domain.c
+++ b/drivers/power/avs/rockchip-io-domain.c
@@ -39,6 +39,10 @@
 #define MAX_VOLTAGE_1_8		1980000
 #define MAX_VOLTAGE_3_3		3600000
 
+#define PX30_IO_VSEL			0x180
+#define PX30_IO_VSEL_VCCIO6_SRC		BIT(0)
+#define PX30_IO_VSEL_VCCIO6_SUPPLY_NUM	1
+
 #define RK3288_SOC_CON2			0x24c
 #define RK3288_SOC_CON2_FLASH0		BIT(7)
 #define RK3288_SOC_FLASH_SUPPLY_NUM	2
@@ -151,6 +155,25 @@ static int rockchip_iodomain_notify(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+static void px30_iodomain_init(struct rockchip_iodomain *iod)
+{
+	int ret;
+	u32 val;
+
+	/* if no VCCIO0 supply we should leave things alone */
+	if (!iod->supplies[PX30_IO_VSEL_VCCIO6_SUPPLY_NUM].reg)
+		return;
+
+	/*
+	 * set vccio0 iodomain to also use this framework
+	 * instead of a special gpio.
+	 */
+	val = PX30_IO_VSEL_VCCIO6_SRC | (PX30_IO_VSEL_VCCIO6_SRC << 16);
+	ret = regmap_write(iod->grf, PX30_IO_VSEL, val);
+	if (ret < 0)
+		dev_warn(iod->dev, "couldn't update vccio0 ctrl\n");
+}
+
 static void rk3288_iodomain_init(struct rockchip_iodomain *iod)
 {
 	int ret;
@@ -227,6 +250,43 @@ static void rk3399_pmu_iodomain_init(struct rockchip_iodomain *iod)
 		dev_warn(iod->dev, "couldn't update pmu io iodomain ctrl\n");
 }
 
+static const struct rockchip_iodomain_soc_data soc_data_px30 = {
+	.grf_offset = 0x180,
+	.supply_names = {
+		NULL,
+		"vccio6",
+		"vccio1",
+		"vccio2",
+		"vccio3",
+		"vccio4",
+		"vccio5",
+		"vccio-oscgpi",
+	},
+	.init = px30_iodomain_init,
+};
+
+static const struct rockchip_iodomain_soc_data soc_data_px30_pmu = {
+	.grf_offset = 0x100,
+	.supply_names = {
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		"pmuio1",
+		"pmuio2",
+	},
+};
+
 /*
  * On the rk3188 the io-domains are handled by a shared register with the
  * lower 8 bits being still being continuing drive-strength settings.
@@ -381,6 +441,14 @@ static const struct rockchip_iodomain_soc_data soc_data_rv1108_pmu = {
 
 static const struct of_device_id rockchip_iodomain_match[] = {
 	{
+		.compatible = "rockchip,px30-io-voltage-domain",
+		.data = (void *)&soc_data_px30
+	},
+	{
+		.compatible = "rockchip,px30-pmu-io-voltage-domain",
+		.data = (void *)&soc_data_px30_pmu
+	},
+	{
 		.compatible = "rockchip,rk3188-io-voltage-domain",
 		.data = &soc_data_rk3188
 	},
diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index feac7b066e6c..f57ab0a27301 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -19,6 +19,7 @@
 #include <linux/err.h>
 #include <linux/of.h>
 #include <linux/power_supply.h>
+#include <linux/property.h>
 #include <linux/thermal.h>
 #include "power_supply.h"
 
@@ -843,12 +844,21 @@ __power_supply_register(struct device *parent,
 {
 	struct device *dev;
 	struct power_supply *psy;
-	int rc;
+	int i, rc;
 
 	if (!parent)
 		pr_warn("%s: Expected proper parent device for '%s'\n",
 			__func__, desc->name);
 
+	if (!desc || !desc->name || !desc->properties || !desc->num_properties)
+		return ERR_PTR(-EINVAL);
+
+	for (i = 0; i < desc->num_properties; ++i) {
+		if ((desc->properties[i] == POWER_SUPPLY_PROP_USB_TYPE) &&
+		    (!desc->usb_types || !desc->num_usb_types))
+			return ERR_PTR(-EINVAL);
+	}
+
 	psy = kzalloc(sizeof(*psy), GFP_KERNEL);
 	if (!psy)
 		return ERR_PTR(-ENOMEM);
@@ -865,7 +875,8 @@ __power_supply_register(struct device *parent,
 	psy->desc = desc;
 	if (cfg) {
 		psy->drv_data = cfg->drv_data;
-		psy->of_node = cfg->of_node;
+		psy->of_node =
+			cfg->fwnode ? to_of_node(cfg->fwnode) : cfg->of_node;
 		psy->supplied_to = cfg->supplied_to;
 		psy->num_supplicants = cfg->num_supplicants;
 	}
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index 5204f115970f..1350068c401a 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -46,6 +46,11 @@ static const char * const power_supply_type_text[] = {
 	"USB_PD", "USB_PD_DRP", "BrickID"
 };
 
+static const char * const power_supply_usb_type_text[] = {
+	"Unknown", "SDP", "DCP", "CDP", "ACA", "C",
+	"PD", "PD_DRP", "PD_PPS", "BrickID"
+};
+
 static const char * const power_supply_status_text[] = {
 	"Unknown", "Charging", "Discharging", "Not charging", "Full"
 };
@@ -73,6 +78,41 @@ static const char * const power_supply_scope_text[] = {
 	"Unknown", "System", "Device"
 };
 
+static ssize_t power_supply_show_usb_type(struct device *dev,
+					  enum power_supply_usb_type *usb_types,
+					  ssize_t num_usb_types,
+					  union power_supply_propval *value,
+					  char *buf)
+{
+	enum power_supply_usb_type usb_type;
+	ssize_t count = 0;
+	bool match = false;
+	int i;
+
+	for (i = 0; i < num_usb_types; ++i) {
+		usb_type = usb_types[i];
+
+		if (value->intval == usb_type) {
+			count += sprintf(buf + count, "[%s] ",
+					 power_supply_usb_type_text[usb_type]);
+			match = true;
+		} else {
+			count += sprintf(buf + count, "%s ",
+					 power_supply_usb_type_text[usb_type]);
+		}
+	}
+
+	if (!match) {
+		dev_warn(dev, "driver reporting unsupported connected type\n");
+		return -EINVAL;
+	}
+
+	if (count)
+		buf[count - 1] = '\n';
+
+	return count;
+}
+
 static ssize_t power_supply_show_property(struct device *dev,
 					  struct device_attribute *attr,
 					  char *buf) {
@@ -115,6 +155,10 @@ static ssize_t power_supply_show_property(struct device *dev,
 	else if (off == POWER_SUPPLY_PROP_TYPE)
 		return sprintf(buf, "%s\n",
 			       power_supply_type_text[value.intval]);
+	else if (off == POWER_SUPPLY_PROP_USB_TYPE)
+		return power_supply_show_usb_type(dev, psy->desc->usb_types,
+						  psy->desc->num_usb_types,
+						  &value, buf);
 	else if (off == POWER_SUPPLY_PROP_SCOPE)
 		return sprintf(buf, "%s\n",
 			       power_supply_scope_text[value.intval]);
@@ -241,6 +285,7 @@ static struct device_attribute power_supply_attrs[] = {
 	POWER_SUPPLY_ATTR(time_to_full_now),
 	POWER_SUPPLY_ATTR(time_to_full_avg),
 	POWER_SUPPLY_ATTR(type),
+	POWER_SUPPLY_ATTR(usb_type),
 	POWER_SUPPLY_ATTR(scope),
 	POWER_SUPPLY_ATTR(precharge_current),
 	POWER_SUPPLY_ATTR(charge_term_current),
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 9d27016c899e..0434ab7b6497 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -740,10 +740,7 @@ static int do_dma_request(struct mport_dma_req *req,
 	tx->callback = dma_xfer_callback;
 	tx->callback_param = req;
 
-	req->dmach = chan;
-	req->sync = sync;
 	req->status = DMA_IN_PROGRESS;
-	init_completion(&req->req_comp);
 	kref_get(&req->refcount);
 
 	cookie = dmaengine_submit(tx);
@@ -831,13 +828,20 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
 	if (!req)
 		return -ENOMEM;
 
-	kref_init(&req->refcount);
-
 	ret = get_dma_channel(priv);
 	if (ret) {
 		kfree(req);
 		return ret;
 	}
+	chan = priv->dmach;
+
+	kref_init(&req->refcount);
+	init_completion(&req->req_comp);
+	req->dir = dir;
+	req->filp = filp;
+	req->priv = priv;
+	req->dmach = chan;
+	req->sync = sync;
 
 	/*
 	 * If parameter loc_addr != NULL, we are transferring data from/to
@@ -925,11 +929,6 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
 				xfer->offset, xfer->length);
 	}
 
-	req->dir = dir;
-	req->filp = filp;
-	req->priv = priv;
-	chan = priv->dmach;
-
 	nents = dma_map_sg(chan->device->dev,
 			   req->sgt.sgl, req->sgt.nents, dir);
 	if (nents == 0) {
diff --git a/drivers/remoteproc/qcom_q6v5_pil.c b/drivers/remoteproc/qcom_q6v5_pil.c
index 8e70a627e0bb..cbbafdcaaecb 100644
--- a/drivers/remoteproc/qcom_q6v5_pil.c
+++ b/drivers/remoteproc/qcom_q6v5_pil.c
@@ -1083,6 +1083,7 @@ static int q6v5_alloc_memory_region(struct q6v5 *qproc)
 		dev_err(qproc->dev, "unable to resolve mba region\n");
 		return ret;
 	}
+	of_node_put(node);
 
 	qproc->mba_phys = r.start;
 	qproc->mba_size = resource_size(&r);
@@ -1100,6 +1101,7 @@ static int q6v5_alloc_memory_region(struct q6v5 *qproc)
 		dev_err(qproc->dev, "unable to resolve mpss region\n");
 		return ret;
 	}
+	of_node_put(node);
 
 	qproc->mpss_phys = qproc->mpss_reloc = r.start;
 	qproc->mpss_size = resource_size(&r);
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 6d9c5832ce47..a9609d971f7f 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1163,7 +1163,7 @@ int rproc_trigger_recovery(struct rproc *rproc)
 	if (ret)
 		return ret;
 
-	ret = rproc_stop(rproc, false);
+	ret = rproc_stop(rproc, true);
 	if (ret)
 		goto unlock_mutex;
 
@@ -1316,7 +1316,7 @@ void rproc_shutdown(struct rproc *rproc)
 	if (!atomic_dec_and_test(&rproc->power))
 		goto out;
 
-	ret = rproc_stop(rproc, true);
+	ret = rproc_stop(rproc, false);
 	if (ret) {
 		atomic_inc(&rproc->power);
 		goto out;
diff --git a/drivers/reset/reset-uniphier.c b/drivers/reset/reset-uniphier.c
index 360e06b20c53..ac18f2f27881 100644
--- a/drivers/reset/reset-uniphier.c
+++ b/drivers/reset/reset-uniphier.c
@@ -110,7 +110,7 @@ static const struct uniphier_reset_data uniphier_ld20_sys_reset_data[] = {
 	UNIPHIER_RESETX(4, 0x200c, 2),		/* eMMC */
 	UNIPHIER_RESETX(6, 0x200c, 6),		/* Ether */
 	UNIPHIER_RESETX(8, 0x200c, 8),		/* STDMAC (HSC) */
-	UNIPHIER_RESETX(12, 0x200c, 5),		/* GIO (PCIe, USB3) */
+	UNIPHIER_RESETX(14, 0x200c, 5),		/* USB30 */
 	UNIPHIER_RESETX(16, 0x200c, 12),	/* USB30-PHY0 */
 	UNIPHIER_RESETX(17, 0x200c, 13),	/* USB30-PHY1 */
 	UNIPHIER_RESETX(18, 0x200c, 14),	/* USB30-PHY2 */
@@ -127,8 +127,8 @@ static const struct uniphier_reset_data uniphier_pxs3_sys_reset_data[] = {
 	UNIPHIER_RESETX(6, 0x200c, 9),		/* Ether0 */
 	UNIPHIER_RESETX(7, 0x200c, 10),		/* Ether1 */
 	UNIPHIER_RESETX(8, 0x200c, 12),		/* STDMAC */
-	UNIPHIER_RESETX(12, 0x200c, 4),		/* USB30 link (GIO0) */
-	UNIPHIER_RESETX(13, 0x200c, 5),		/* USB31 link (GIO1) */
+	UNIPHIER_RESETX(12, 0x200c, 4),		/* USB30 link */
+	UNIPHIER_RESETX(13, 0x200c, 5),		/* USB31 link */
 	UNIPHIER_RESETX(16, 0x200c, 16),	/* USB30-PHY0 */
 	UNIPHIER_RESETX(17, 0x200c, 18),	/* USB30-PHY1 */
 	UNIPHIER_RESETX(18, 0x200c, 20),	/* USB30-PHY2 */
diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c
index 64b6de9763ee..1efdf9ff8679 100644
--- a/drivers/rpmsg/rpmsg_char.c
+++ b/drivers/rpmsg/rpmsg_char.c
@@ -581,4 +581,6 @@ static void rpmsg_chrdev_exit(void)
 	unregister_chrdev_region(rpmsg_major, RPMSG_DEV_MAX);
 }
 module_exit(rpmsg_chrdev_exit);
+
+MODULE_ALIAS("rpmsg:rpmsg_chrdev");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c
index 304e891e35fc..60f2250fd96b 100644
--- a/drivers/rtc/rtc-opal.c
+++ b/drivers/rtc/rtc-opal.c
@@ -57,7 +57,7 @@ static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms)
 
 static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
 {
-	long rc = OPAL_BUSY;
+	s64 rc = OPAL_BUSY;
 	int retries = 10;
 	u32 y_m_d;
 	u64 h_m_s_ms;
@@ -66,13 +66,17 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
+		if (rc == OPAL_BUSY_EVENT) {
+			msleep(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
-		else if (retries-- && (rc == OPAL_HARDWARE
-				       || rc == OPAL_INTERNAL_ERROR))
-			msleep(10);
-		else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
-			break;
+		} else if (rc == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
+		} else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+			if (retries--) {
+				msleep(10); /* Wait 10ms before retry */
+				rc = OPAL_BUSY; /* go around again */
+			}
+		}
 	}
 
 	if (rc != OPAL_SUCCESS)
@@ -87,21 +91,26 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
 
 static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm)
 {
-	long rc = OPAL_BUSY;
+	s64 rc = OPAL_BUSY;
 	int retries = 10;
 	u32 y_m_d = 0;
 	u64 h_m_s_ms = 0;
 
 	tm_to_opal(tm, &y_m_d, &h_m_s_ms);
+
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_write(y_m_d, h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
+		if (rc == OPAL_BUSY_EVENT) {
+			msleep(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
-		else if (retries-- && (rc == OPAL_HARDWARE
-				       || rc == OPAL_INTERNAL_ERROR))
-			msleep(10);
-		else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
-			break;
+		} else if (rc == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
+		} else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+			if (retries--) {
+				msleep(10); /* Wait 10ms before retry */
+				rc = OPAL_BUSY; /* go around again */
+			}
+		}
 	}
 
 	return rc == OPAL_SUCCESS ? 0 : -EIO;
diff --git a/drivers/rtc/rtc-proc.c b/drivers/rtc/rtc-proc.c
index 31e7e23cc5be..a9dd9218fae2 100644
--- a/drivers/rtc/rtc-proc.c
+++ b/drivers/rtc/rtc-proc.c
@@ -107,40 +107,11 @@ static int rtc_proc_show(struct seq_file *seq, void *offset)
 	return 0;
 }
 
-static int rtc_proc_open(struct inode *inode, struct file *file)
-{
-	int ret;
-	struct rtc_device *rtc = PDE_DATA(inode);
-
-	if (!try_module_get(rtc->owner))
-		return -ENODEV;
-
-	ret = single_open(file, rtc_proc_show, rtc);
-	if (ret)
-		module_put(rtc->owner);
-	return ret;
-}
-
-static int rtc_proc_release(struct inode *inode, struct file *file)
-{
-	int res = single_release(inode, file);
-	struct rtc_device *rtc = PDE_DATA(inode);
-
-	module_put(rtc->owner);
-	return res;
-}
-
-static const struct file_operations rtc_proc_fops = {
-	.open		= rtc_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= rtc_proc_release,
-};
-
 void rtc_proc_add_device(struct rtc_device *rtc)
 {
 	if (is_rtc_hctosys(rtc))
-		proc_create_data("driver/rtc", 0, NULL, &rtc_proc_fops, rtc);
+		proc_create_single_data("driver/rtc", 0, NULL, rtc_proc_show,
+				rtc);
 }
 
 void rtc_proc_del_device(struct rtc_device *rtc)
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 04143c08bd6e..73cce3ecb97f 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2569,14 +2569,11 @@ EXPORT_SYMBOL(dasd_sleep_on_immediatly);
  * Cancellation of a request is an asynchronous operation! The calling
  * function has to wait until the request is properly returned via callback.
  */
-int dasd_cancel_req(struct dasd_ccw_req *cqr)
+static int __dasd_cancel_req(struct dasd_ccw_req *cqr)
 {
 	struct dasd_device *device = cqr->startdev;
-	unsigned long flags;
-	int rc;
+	int rc = 0;
 
-	rc = 0;
-	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
 	switch (cqr->status) {
 	case DASD_CQR_QUEUED:
 		/* request was not started - just set to cleared */
@@ -2596,11 +2593,21 @@ int dasd_cancel_req(struct dasd_ccw_req *cqr)
 	default: /* already finished or clear pending - do nothing */
 		break;
 	}
-	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
 	dasd_schedule_device_bh(device);
 	return rc;
 }
-EXPORT_SYMBOL(dasd_cancel_req);
+
+int dasd_cancel_req(struct dasd_ccw_req *cqr)
+{
+	struct dasd_device *device = cqr->startdev;
+	unsigned long flags;
+	int rc;
+
+	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+	rc = __dasd_cancel_req(cqr);
+	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
+	return rc;
+}
 
 /*
  * SECTION: Operations of the dasd_block layer.
@@ -3034,7 +3041,8 @@ static blk_status_t do_dasd_request(struct blk_mq_hw_ctx *hctx,
 	cqr->callback_data = req;
 	cqr->status = DASD_CQR_FILLED;
 	cqr->dq = dq;
-	req->completion_data = cqr;
+	*((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req)) = cqr;
+
 	blk_mq_start_request(req);
 	spin_lock(&block->queue_lock);
 	list_add_tail(&cqr->blocklist, &block->ccw_queue);
@@ -3053,19 +3061,20 @@ out:
  *
  * Return values:
  * BLK_EH_RESET_TIMER if the request should be left running
- * BLK_EH_NOT_HANDLED if the request is handled or terminated
+ * BLK_EH_DONE if the request is handled or terminated
  *		      by the driver.
  */
 enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
 {
-	struct dasd_ccw_req *cqr = req->completion_data;
 	struct dasd_block *block = req->q->queuedata;
 	struct dasd_device *device;
+	struct dasd_ccw_req *cqr;
 	unsigned long flags;
 	int rc = 0;
 
+	cqr = *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req));
 	if (!cqr)
-		return BLK_EH_NOT_HANDLED;
+		return BLK_EH_DONE;
 
 	spin_lock_irqsave(&cqr->dq->lock, flags);
 	device = cqr->startdev ? cqr->startdev : block->base;
@@ -3082,12 +3091,10 @@ enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
 	cqr->retries = -1;
 	cqr->intrc = -ETIMEDOUT;
 	if (cqr->status >= DASD_CQR_QUEUED) {
-		spin_unlock(get_ccwdev_lock(device->cdev));
-		rc = dasd_cancel_req(cqr);
+		rc = __dasd_cancel_req(cqr);
 	} else if (cqr->status == DASD_CQR_FILLED ||
 		   cqr->status == DASD_CQR_NEED_ERP) {
 		cqr->status = DASD_CQR_TERMINATED;
-		spin_unlock(get_ccwdev_lock(device->cdev));
 	} else if (cqr->status == DASD_CQR_IN_ERP) {
 		struct dasd_ccw_req *searchcqr, *nextcqr, *tmpcqr;
 
@@ -3102,9 +3109,7 @@ enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
 			searchcqr->retries = -1;
 			searchcqr->intrc = -ETIMEDOUT;
 			if (searchcqr->status >= DASD_CQR_QUEUED) {
-				spin_unlock(get_ccwdev_lock(device->cdev));
-				rc = dasd_cancel_req(searchcqr);
-				spin_lock(get_ccwdev_lock(device->cdev));
+				rc = __dasd_cancel_req(searchcqr);
 			} else if ((searchcqr->status == DASD_CQR_FILLED) ||
 				   (searchcqr->status == DASD_CQR_NEED_ERP)) {
 				searchcqr->status = DASD_CQR_TERMINATED;
@@ -3118,13 +3123,13 @@ enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
 			}
 			break;
 		}
-		spin_unlock(get_ccwdev_lock(device->cdev));
 	}
+	spin_unlock(get_ccwdev_lock(device->cdev));
 	dasd_schedule_block_bh(block);
 	spin_unlock(&block->queue_lock);
 	spin_unlock_irqrestore(&cqr->dq->lock, flags);
 
-	return rc ? BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED;
+	return rc ? BLK_EH_RESET_TIMER : BLK_EH_DONE;
 }
 
 static int dasd_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
@@ -3169,6 +3174,7 @@ static int dasd_alloc_queue(struct dasd_block *block)
 	int rc;
 
 	block->tag_set.ops = &dasd_mq_ops;
+	block->tag_set.cmd_size = sizeof(struct dasd_ccw_req *);
 	block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES;
 	block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV;
 	block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index 62f5f04d8f61..5e963fe0e38d 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -592,13 +592,22 @@ static int _schedule_lcu_update(struct alias_lcu *lcu,
 int dasd_alias_add_device(struct dasd_device *device)
 {
 	struct dasd_eckd_private *private = device->private;
-	struct alias_lcu *lcu;
+	__u8 uaddr = private->uid.real_unit_addr;
+	struct alias_lcu *lcu = private->lcu;
 	unsigned long flags;
 	int rc;
 
-	lcu = private->lcu;
 	rc = 0;
 	spin_lock_irqsave(&lcu->lock, flags);
+	/*
+	 * Check if device and lcu type differ. If so, the uac data may be
+	 * outdated and needs to be updated.
+	 */
+	if (private->uid.type !=  lcu->uac->unit[uaddr].ua_type) {
+		lcu->flags |= UPDATE_PENDING;
+		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
+			      "uid type mismatch - trigger rescan");
+	}
 	if (!(lcu->flags & UPDATE_PENDING)) {
 		rc = _add_device_to_lcu(lcu, device, device);
 		if (rc)
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index f035c2f25d35..131f1989f6f3 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -27,7 +27,6 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/vtoc.h>
-#include <asm/diag.h>
 
 #include "dasd_int.h"
 #include "dasd_diag.h"
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 7bdc6aaa0ba3..2016e0ed5865 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -18,7 +18,6 @@
 #include <linux/fs.h>
 #include <linux/blkpg.h>
 #include <linux/slab.h>
-#include <asm/compat.h>
 #include <asm/ccwdev.h>
 #include <asm/schid.h>
 #include <asm/cmb.h>
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index c33788a829c3..5cb80c645489 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -131,19 +131,6 @@ static const struct seq_operations dasd_devices_seq_ops = {
 	.show		= dasd_devices_show,
 };
 
-static int dasd_devices_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &dasd_devices_seq_ops);
-}
-
-static const struct file_operations dasd_devices_file_ops = {
-	.owner		= THIS_MODULE,
-	.open		= dasd_devices_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 #ifdef CONFIG_DASD_PROFILE
 static int dasd_stats_all_block_on(void)
 {
@@ -352,10 +339,10 @@ dasd_proc_init(void)
 	dasd_proc_root_entry = proc_mkdir("dasd", NULL);
 	if (!dasd_proc_root_entry)
 		goto out_nodasd;
-	dasd_devices_entry = proc_create("devices",
+	dasd_devices_entry = proc_create_seq("devices",
 					 S_IFREG | S_IRUGO | S_IWUSR,
 					 dasd_proc_root_entry,
-					 &dasd_devices_file_ops);
+					 &dasd_devices_seq_ops);
 	if (!dasd_devices_entry)
 		goto out_nodevices;
 	dasd_statistics_entry = proc_create("statistics",
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index d049e2d74484..0a4c13e1e76e 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -54,3 +54,6 @@ obj-$(CONFIG_CRASH_DUMP) += sclp_sdias.o zcore.o
 
 hmcdrv-objs := hmcdrv_mod.o hmcdrv_dev.o hmcdrv_ftp.o hmcdrv_cache.o diag_ftp.o sclp_ftp.o
 obj-$(CONFIG_HMC_DRV) += hmcdrv.o
+
+chkbss := sclp_early_core.o
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index 61822480a2a0..16a4e8528bbc 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -19,7 +19,6 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#include <asm/compat.h>
 #include <asm/ccwdev.h>
 #include <asm/cio.h>
 #include <asm/ebcdic.h>
diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c
index a78cea0c3a09..248b5db3eaa8 100644
--- a/drivers/s390/char/sclp_ctl.c
+++ b/drivers/s390/char/sclp_ctl.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/ioctl.h>
 #include <linux/fs.h>
-#include <asm/compat.h>
 #include <asm/sclp_ctl.h>
 #include <asm/sclp.h>
 
diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c
index 5f8d9ea69ebd..eceba3858cef 100644
--- a/drivers/s390/char/sclp_early_core.c
+++ b/drivers/s390/char/sclp_early_core.c
@@ -18,7 +18,7 @@ int sclp_init_state __section(.data) = sclp_init_state_uninitialized;
  * Used to keep track of the size of the event masks. Qemu until version 2.11
  * only supports 4 and needs a workaround.
  */
-bool sclp_mask_compat_mode;
+bool sclp_mask_compat_mode __section(.data);
 
 void sclp_early_wait_irq(void)
 {
diff --git a/drivers/s390/char/tape_proc.c b/drivers/s390/char/tape_proc.c
index faae30476f4b..32a14ee31c6b 100644
--- a/drivers/s390/char/tape_proc.c
+++ b/drivers/s390/char/tape_proc.c
@@ -105,29 +105,14 @@ static const struct seq_operations tape_proc_seq = {
 	.show		= tape_proc_show,
 };
 
-static int tape_proc_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &tape_proc_seq);
-}
-
-static const struct file_operations tape_proc_ops =
-{
-	.owner		= THIS_MODULE,
-	.open		= tape_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 /*
  * Initialize procfs stuff on startup
  */
 void
 tape_proc_init(void)
 {
-	tape_proc_devices =
-		proc_create("tapedevices", S_IFREG | S_IRUGO | S_IWUSR, NULL,
-			    &tape_proc_ops);
+	tape_proc_devices = proc_create_seq("tapedevices",
+			S_IFREG | S_IRUGO | S_IWUSR, NULL,  &tape_proc_seq);
 	if (tape_proc_devices == NULL) {
 		return;
 	}
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 17e411c57576..948ce82a7725 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -23,7 +23,6 @@
 #include <linux/mutex.h>
 #include <linux/cma.h>
 #include <linux/mm.h>
-#include <asm/compat.h>
 #include <asm/cpcmd.h>
 #include <asm/debug.h>
 #include <asm/vmcp.h>
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index 5535312602af..db9c854088bc 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -561,6 +561,12 @@ static struct bus_type ccwgroup_bus_type = {
 	.pm = &ccwgroup_pm_ops,
 };
 
+bool dev_is_ccwgroup(struct device *dev)
+{
+	return dev->bus == &ccwgroup_bus_type;
+}
+EXPORT_SYMBOL(dev_is_ccwgroup);
+
 /**
  * ccwgroup_driver_register() - register a ccw group driver
  * @cdriver: driver to be registered
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 6652a49a49b1..9029804dcd22 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -452,6 +452,7 @@ static void chsc_process_sei_link_incident(struct chsc_sei_nt0_area *sei_area)
 
 static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area)
 {
+	struct channel_path *chp;
 	struct chp_link link;
 	struct chp_id chpid;
 	int status;
@@ -464,10 +465,17 @@ static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area)
 	chpid.id = sei_area->rsid;
 	/* allocate a new channel path structure, if needed */
 	status = chp_get_status(chpid);
-	if (status < 0)
-		chp_new(chpid);
-	else if (!status)
+	if (!status)
 		return;
+
+	if (status < 0) {
+		chp_new(chpid);
+	} else {
+		chp = chpid_to_chp(chpid);
+		mutex_lock(&chp->lock);
+		chp_update_desc(chp);
+		mutex_unlock(&chp->lock);
+	}
 	memset(&link, 0, sizeof(struct chp_link));
 	link.chpid = chpid;
 	if ((sei_area->vf & 0xc0) != 0) {
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 0015729d917d..8d9f36625ba5 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -16,7 +16,6 @@
 #include <linux/miscdevice.h>
 #include <linux/kernel_stat.h>
 
-#include <asm/compat.h>
 #include <asm/cio.h>
 #include <asm/chsc.h>
 #include <asm/isc.h>
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index aecfebb74157..4435ae0b3027 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -473,6 +473,36 @@ struct channel_path_desc_fmt0 *ccw_device_get_chp_desc(struct ccw_device *cdev,
 }
 
 /**
+ * ccw_device_get_util_str() - return newly allocated utility strings
+ * @cdev: device to obtain the utility strings for
+ * @chp_idx: index of the channel path
+ *
+ * On success return a newly allocated copy of the utility strings
+ * associated with the given channel path. Return %NULL on error.
+ */
+u8 *ccw_device_get_util_str(struct ccw_device *cdev, int chp_idx)
+{
+	struct subchannel *sch = to_subchannel(cdev->dev.parent);
+	struct channel_path *chp;
+	struct chp_id chpid;
+	u8 *util_str;
+
+	chp_id_init(&chpid);
+	chpid.id = sch->schib.pmcw.chpid[chp_idx];
+	chp = chpid_to_chp(chpid);
+
+	util_str = kmalloc(sizeof(chp->desc_fmt3.util_str), GFP_KERNEL);
+	if (!util_str)
+		return NULL;
+
+	mutex_lock(&chp->lock);
+	memcpy(util_str, chp->desc_fmt3.util_str, sizeof(chp->desc_fmt3.util_str));
+	mutex_unlock(&chp->lock);
+
+	return util_str;
+}
+
+/**
  * ccw_device_get_id() - obtain a ccw device id
  * @cdev: device to obtain the id for
  * @dev_id: where to fill in the values
@@ -682,3 +712,4 @@ EXPORT_SYMBOL(ccw_device_start_key);
 EXPORT_SYMBOL(ccw_device_get_ciw);
 EXPORT_SYMBOL(ccw_device_get_path_mask);
 EXPORT_SYMBOL_GPL(ccw_device_get_chp_desc);
+EXPORT_SYMBOL_GPL(ccw_device_get_util_str);
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index 439991d71b14..4c14ce428e92 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -141,7 +141,7 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues)
 	int i;
 
 	for (i = 0; i < nr_queues; i++) {
-		q = kmem_cache_alloc(qdio_q_cache, GFP_KERNEL);
+		q = kmem_cache_zalloc(qdio_q_cache, GFP_KERNEL);
 		if (!q)
 			return -ENOMEM;
 
@@ -456,7 +456,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
 {
 	struct ciw *ciw;
 	struct qdio_irq *irq_ptr = init_data->cdev->private->qdio_data;
-	int rc;
 
 	memset(&irq_ptr->qib, 0, sizeof(irq_ptr->qib));
 	memset(&irq_ptr->siga_flag, 0, sizeof(irq_ptr->siga_flag));
@@ -493,16 +492,14 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
 	ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_EQUEUE);
 	if (!ciw) {
 		DBF_ERROR("%4x NO EQ", irq_ptr->schid.sch_no);
-		rc = -EINVAL;
-		goto out_err;
+		return -EINVAL;
 	}
 	irq_ptr->equeue = *ciw;
 
 	ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_AQUEUE);
 	if (!ciw) {
 		DBF_ERROR("%4x NO AQ", irq_ptr->schid.sch_no);
-		rc = -EINVAL;
-		goto out_err;
+		return -EINVAL;
 	}
 	irq_ptr->aqueue = *ciw;
 
@@ -512,9 +509,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
 	init_data->cdev->handler = qdio_int_handler;
 	spin_unlock_irq(get_ccwdev_lock(irq_ptr->cdev));
 	return 0;
-out_err:
-	qdio_release_memory(irq_ptr);
-	return rc;
 }
 
 void qdio_print_subchannel_info(struct qdio_irq *irq_ptr,
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 2c7550797ec2..dce92b2a895d 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -715,6 +715,10 @@ void cp_free(struct channel_program *cp)
  * and stores the result to ccwchain list. @cp must have been
  * initialized by a previous call with cp_init(). Otherwise, undefined
  * behavior occurs.
+ * For each chain composing the channel program:
+ * - On entry ch_len holds the count of CCWs to be translated.
+ * - On exit ch_len is adjusted to the count of successfully translated CCWs.
+ * This allows cp_free to find in ch_len the count of CCWs to free in a chain.
  *
  * The S/390 CCW Translation APIS (prefixed by 'cp_') are introduced
  * as helpers to do ccw chain translation inside the kernel. Basically
@@ -749,11 +753,18 @@ int cp_prefetch(struct channel_program *cp)
 		for (idx = 0; idx < len; idx++) {
 			ret = ccwchain_fetch_one(chain, idx, cp);
 			if (ret)
-				return ret;
+				goto out_err;
 		}
 	}
 
 	return 0;
+out_err:
+	/* Only cleanup the chain elements that were actually translated. */
+	chain->ch_len = idx;
+	list_for_each_entry_continue(chain, &cp->ccwchain_list, next) {
+		chain->ch_len = 0;
+	}
+	return ret;
 }
 
 /**
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index ff6963ad6e39..3c800642134e 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -20,12 +20,12 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	int ccode;
 	__u8 lpm;
 	unsigned long flags;
+	int ret;
 
 	sch = private->sch;
 
 	spin_lock_irqsave(sch->lock, flags);
 	private->state = VFIO_CCW_STATE_BUSY;
-	spin_unlock_irqrestore(sch->lock, flags);
 
 	orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
 
@@ -38,10 +38,12 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 		 * Initialize device status information
 		 */
 		sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
-		return 0;
+		ret = 0;
+		break;
 	case 1:		/* Status pending */
 	case 2:		/* Busy */
-		return -EBUSY;
+		ret = -EBUSY;
+		break;
 	case 3:		/* Device/path not operational */
 	{
 		lpm = orb->cmd.lpm;
@@ -51,13 +53,16 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 			sch->lpm = 0;
 
 		if (cio_update_schib(sch))
-			return -ENODEV;
-
-		return sch->lpm ? -EACCES : -ENODEV;
+			ret = -ENODEV;
+		else
+			ret = sch->lpm ? -EACCES : -ENODEV;
+		break;
 	}
 	default:
-		return ccode;
+		ret = ccode;
 	}
+	spin_unlock_irqrestore(sch->lock, flags);
+	return ret;
 }
 
 static void fsm_notoper(struct vfio_ccw_private *private,
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 02184cf35834..6a273c5ebca5 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -198,11 +198,18 @@ struct ap_message {
  */
 static inline void ap_init_message(struct ap_message *ap_msg)
 {
-	ap_msg->psmid = 0;
-	ap_msg->length = 0;
-	ap_msg->rc = 0;
-	ap_msg->special = 0;
-	ap_msg->receive = NULL;
+	memset(ap_msg, 0, sizeof(*ap_msg));
+}
+
+/**
+ * ap_release_message() - Release ap_message.
+ * Releases all memory used internal within the ap_message struct
+ * Currently this is the message and private field.
+ */
+static inline void ap_release_message(struct ap_message *ap_msg)
+{
+	kzfree(ap_msg->message);
+	kzfree(ap_msg->private);
 }
 
 #define for_each_ap_card(_ac) \
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 5efd84862ccb..febcdb5135bf 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -371,6 +371,7 @@ long zcrypt_send_cprb(struct ica_xcRB *xcRB)
 
 	trace_s390_zcrypt_req(xcRB, TB_ZSECSENDCPRB);
 
+	ap_init_message(&ap_msg);
 	rc = get_cprb_fc(xcRB, &ap_msg, &func_code, &domain);
 	if (rc)
 		goto out;
@@ -425,6 +426,7 @@ long zcrypt_send_cprb(struct ica_xcRB *xcRB)
 	spin_unlock(&zcrypt_list_lock);
 
 out:
+	ap_release_message(&ap_msg);
 	trace_s390_zcrypt_rep(xcRB, func_code, rc,
 			      AP_QID_CARD(qid), AP_QID_QUEUE(qid));
 	return rc;
@@ -468,6 +470,8 @@ static long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
 
 	trace_s390_zcrypt_req(xcrb, TP_ZSENDEP11CPRB);
 
+	ap_init_message(&ap_msg);
+
 	target_num = (unsigned short) xcrb->targets_num;
 
 	/* empty list indicates autoselect (all available targets) */
@@ -485,7 +489,7 @@ static long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
 		if (copy_from_user(targets, uptr,
 				   target_num * sizeof(*targets))) {
 			rc = -EFAULT;
-			goto out;
+			goto out_free;
 		}
 	}
 
@@ -542,6 +546,7 @@ static long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
 out_free:
 	kfree(targets);
 out:
+	ap_release_message(&ap_msg);
 	trace_s390_zcrypt_rep(xcrb, func_code, rc,
 			      AP_QID_CARD(qid), AP_QID_QUEUE(qid));
 	return rc;
@@ -559,6 +564,7 @@ static long zcrypt_rng(char *buffer)
 
 	trace_s390_zcrypt_req(buffer, TP_HWRNGCPRB);
 
+	ap_init_message(&ap_msg);
 	rc = get_rng_fc(&ap_msg, &func_code, &domain);
 	if (rc)
 		goto out;
@@ -589,8 +595,10 @@ static long zcrypt_rng(char *buffer)
 	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
 	spin_unlock(&zcrypt_list_lock);
 
-	if (!pref_zq)
-		return -ENODEV;
+	if (!pref_zq) {
+		rc = -ENODEV;
+		goto out;
+	}
 
 	qid = pref_zq->queue->qid;
 	rc = pref_zq->ops->rng(pref_zq, buffer, &ap_msg);
@@ -600,6 +608,7 @@ static long zcrypt_rng(char *buffer)
 	spin_unlock(&zcrypt_list_lock);
 
 out:
+	ap_release_message(&ap_msg);
 	trace_s390_zcrypt_rep(buffer, func_code, rc,
 			      AP_QID_CARD(qid), AP_QID_QUEUE(qid));
 	return rc;
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index f54bef4a928e..97d4bacbc442 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -1084,6 +1084,13 @@ out_free:
 	return rc;
 }
 
+/**
+ * Fetch function code from cprb.
+ * Extracting the fc requires to copy the cprb from userspace.
+ * So this function allocates memory and needs an ap_msg prepared
+ * by the caller with ap_init_message(). Also the caller has to
+ * make sure ap_release_message() is always called even on failure.
+ */
 unsigned int get_cprb_fc(struct ica_xcRB *xcRB,
 				struct ap_message *ap_msg,
 				unsigned int *func_code, unsigned short **dom)
@@ -1091,9 +1098,7 @@ unsigned int get_cprb_fc(struct ica_xcRB *xcRB,
 	struct response_type resp_type = {
 		.type = PCIXCC_RESPONSE_TYPE_XCRB,
 	};
-	int rc;
 
-	ap_init_message(ap_msg);
 	ap_msg->message = kmalloc(MSGTYPE06_MAX_MSG_SIZE, GFP_KERNEL);
 	if (!ap_msg->message)
 		return -ENOMEM;
@@ -1101,17 +1106,10 @@ unsigned int get_cprb_fc(struct ica_xcRB *xcRB,
 	ap_msg->psmid = (((unsigned long long) current->pid) << 32) +
 				atomic_inc_return(&zcrypt_step);
 	ap_msg->private = kmalloc(sizeof(resp_type), GFP_KERNEL);
-	if (!ap_msg->private) {
-		kzfree(ap_msg->message);
+	if (!ap_msg->private)
 		return -ENOMEM;
-	}
 	memcpy(ap_msg->private, &resp_type, sizeof(resp_type));
-	rc = XCRB_msg_to_type6CPRB_msgX(ap_msg, xcRB, func_code, dom);
-	if (rc) {
-		kzfree(ap_msg->message);
-		kzfree(ap_msg->private);
-	}
-	return rc;
+	return XCRB_msg_to_type6CPRB_msgX(ap_msg, xcRB, func_code, dom);
 }
 
 /**
@@ -1139,11 +1137,16 @@ static long zcrypt_msgtype6_send_cprb(struct zcrypt_queue *zq,
 		/* Signal pending. */
 		ap_cancel_message(zq->queue, ap_msg);
 
-	kzfree(ap_msg->message);
-	kzfree(ap_msg->private);
 	return rc;
 }
 
+/**
+ * Fetch function code from ep11 cprb.
+ * Extracting the fc requires to copy the ep11 cprb from userspace.
+ * So this function allocates memory and needs an ap_msg prepared
+ * by the caller with ap_init_message(). Also the caller has to
+ * make sure ap_release_message() is always called even on failure.
+ */
 unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb,
 				    struct ap_message *ap_msg,
 				    unsigned int *func_code)
@@ -1151,9 +1154,7 @@ unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb,
 	struct response_type resp_type = {
 		.type = PCIXCC_RESPONSE_TYPE_EP11,
 	};
-	int rc;
 
-	ap_init_message(ap_msg);
 	ap_msg->message = kmalloc(MSGTYPE06_MAX_MSG_SIZE, GFP_KERNEL);
 	if (!ap_msg->message)
 		return -ENOMEM;
@@ -1161,17 +1162,10 @@ unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb,
 	ap_msg->psmid = (((unsigned long long) current->pid) << 32) +
 				atomic_inc_return(&zcrypt_step);
 	ap_msg->private = kmalloc(sizeof(resp_type), GFP_KERNEL);
-	if (!ap_msg->private) {
-		kzfree(ap_msg->message);
+	if (!ap_msg->private)
 		return -ENOMEM;
-	}
 	memcpy(ap_msg->private, &resp_type, sizeof(resp_type));
-	rc = xcrb_msg_to_type6_ep11cprb_msgx(ap_msg, xcrb, func_code);
-	if (rc) {
-		kzfree(ap_msg->message);
-		kzfree(ap_msg->private);
-	}
-	return rc;
+	return xcrb_msg_to_type6_ep11cprb_msgx(ap_msg, xcrb, func_code);
 }
 
 /**
@@ -1246,8 +1240,6 @@ static long zcrypt_msgtype6_send_ep11_cprb(struct zcrypt_queue *zq,
 		/* Signal pending. */
 		ap_cancel_message(zq->queue, ap_msg);
 
-	kzfree(ap_msg->message);
-	kzfree(ap_msg->private);
 	return rc;
 }
 
@@ -1258,7 +1250,6 @@ unsigned int get_rng_fc(struct ap_message *ap_msg, int *func_code,
 		.type = PCIXCC_RESPONSE_TYPE_XCRB,
 	};
 
-	ap_init_message(ap_msg);
 	ap_msg->message = kmalloc(MSGTYPE06_MAX_MSG_SIZE, GFP_KERNEL);
 	if (!ap_msg->message)
 		return -ENOMEM;
@@ -1266,10 +1257,8 @@ unsigned int get_rng_fc(struct ap_message *ap_msg, int *func_code,
 	ap_msg->psmid = (((unsigned long long) current->pid) << 32) +
 				atomic_inc_return(&zcrypt_step);
 	ap_msg->private = kmalloc(sizeof(resp_type), GFP_KERNEL);
-	if (!ap_msg->private) {
-		kzfree(ap_msg->message);
+	if (!ap_msg->private)
 		return -ENOMEM;
-	}
 	memcpy(ap_msg->private, &resp_type, sizeof(resp_type));
 
 	rng_type6CPRB_msgX(ap_msg, ZCRYPT_RNG_BUFFER_SIZE, domain);
@@ -1313,8 +1302,6 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq,
 		/* Signal pending. */
 		ap_cancel_message(zq->queue, ap_msg);
 
-	kzfree(ap_msg->message);
-	kzfree(ap_msg->private);
 	return rc;
 }
 
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 4326715dc13e..78b98b3e7efa 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -557,7 +557,6 @@ enum qeth_prot_versions {
 enum qeth_cmd_buffer_state {
 	BUF_STATE_FREE,
 	BUF_STATE_LOCKED,
-	BUF_STATE_PROCESSED,
 };
 
 enum qeth_cq {
@@ -601,7 +600,6 @@ struct qeth_channel {
 	struct qeth_cmd_buffer iob[QETH_CMD_BUFFER_NO];
 	atomic_t irq_pending;
 	int io_buf_no;
-	int buf_no;
 };
 
 /**
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 04fefa5bb08d..f5a0d894d9ad 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -10,6 +10,7 @@
 #define KMSG_COMPONENT "qeth"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/string.h>
@@ -32,7 +33,6 @@
 #include <asm/chpid.h>
 #include <asm/io.h>
 #include <asm/sysinfo.h>
-#include <asm/compat.h>
 #include <asm/diag.h>
 #include <asm/cio.h>
 #include <asm/ccwdev.h>
@@ -706,7 +706,6 @@ void qeth_clear_ipacmd_list(struct qeth_card *card)
 		qeth_put_reply(reply);
 	}
 	spin_unlock_irqrestore(&card->lock, flags);
-	atomic_set(&card->write.irq_pending, 0);
 }
 EXPORT_SYMBOL_GPL(qeth_clear_ipacmd_list);
 
@@ -818,7 +817,6 @@ void qeth_clear_cmd_buffers(struct qeth_channel *channel)
 
 	for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++)
 		qeth_release_buffer(channel, &channel->iob[cnt]);
-	channel->buf_no = 0;
 	channel->io_buf_no = 0;
 }
 EXPORT_SYMBOL_GPL(qeth_clear_cmd_buffers);
@@ -924,7 +922,6 @@ static int qeth_setup_channel(struct qeth_channel *channel)
 			kfree(channel->iob[cnt].data);
 		return -ENOMEM;
 	}
-	channel->buf_no = 0;
 	channel->io_buf_no = 0;
 	atomic_set(&channel->irq_pending, 0);
 	spin_lock_init(&channel->iob_lock);
@@ -1100,16 +1097,9 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 {
 	int rc;
 	int cstat, dstat;
-	struct qeth_cmd_buffer *buffer;
+	struct qeth_cmd_buffer *iob = NULL;
 	struct qeth_channel *channel;
 	struct qeth_card *card;
-	struct qeth_cmd_buffer *iob;
-	__u8 index;
-
-	if (__qeth_check_irb_error(cdev, intparm, irb))
-		return;
-	cstat = irb->scsw.cmd.cstat;
-	dstat = irb->scsw.cmd.dstat;
 
 	card = CARD_FROM_CDEV(cdev);
 	if (!card)
@@ -1127,6 +1117,19 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		channel = &card->data;
 		QETH_CARD_TEXT(card, 5, "data");
 	}
+
+	if (qeth_intparm_is_iob(intparm))
+		iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
+
+	if (__qeth_check_irb_error(cdev, intparm, irb)) {
+		/* IO was terminated, free its resources. */
+		if (iob)
+			qeth_release_buffer(iob->channel, iob);
+		atomic_set(&channel->irq_pending, 0);
+		wake_up(&card->wait_q);
+		return;
+	}
+
 	atomic_set(&channel->irq_pending, 0);
 
 	if (irb->scsw.cmd.fctl & (SCSW_FCTL_CLEAR_FUNC))
@@ -1150,6 +1153,10 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		/* we don't have to handle this further */
 		intparm = 0;
 	}
+
+	cstat = irb->scsw.cmd.cstat;
+	dstat = irb->scsw.cmd.dstat;
+
 	if ((dstat & DEV_STAT_UNIT_EXCEP) ||
 	    (dstat & DEV_STAT_UNIT_CHECK) ||
 	    (cstat)) {
@@ -1182,25 +1189,15 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		channel->state = CH_STATE_RCD_DONE;
 		goto out;
 	}
-	if (intparm) {
-		buffer = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
-		buffer->state = BUF_STATE_PROCESSED;
-	}
 	if (channel == &card->data)
 		return;
 	if (channel == &card->read &&
 	    channel->state == CH_STATE_UP)
 		__qeth_issue_next_read(card);
 
-	iob = channel->iob;
-	index = channel->buf_no;
-	while (iob[index].state == BUF_STATE_PROCESSED) {
-		if (iob[index].callback != NULL)
-			iob[index].callback(channel, iob + index);
+	if (iob && iob->callback)
+		iob->callback(iob->channel, iob);
 
-		index = (index + 1) % QETH_CMD_BUFFER_NO;
-	}
-	channel->buf_no = index;
 out:
 	wake_up(&card->wait_q);
 	return;
@@ -1870,8 +1867,8 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel,
 		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
 	QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start(channel->ccwdev,
-			      &channel->ccw, (addr_t) iob, 0, 0);
+	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+				      (addr_t) iob, 0, 0, QETH_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 
 	if (rc) {
@@ -1888,7 +1885,6 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel,
 	if (channel->state != CH_STATE_UP) {
 		rc = -ETIME;
 		QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc);
-		qeth_clear_cmd_buffers(channel);
 	} else
 		rc = 0;
 	return rc;
@@ -1942,8 +1938,8 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
 	QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start(channel->ccwdev,
-			      &channel->ccw, (addr_t) iob, 0, 0);
+	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+				      (addr_t) iob, 0, 0, QETH_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 
 	if (rc) {
@@ -1964,7 +1960,6 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 		QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n",
 			dev_name(&channel->ccwdev->dev));
 		QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME);
-		qeth_clear_cmd_buffers(channel);
 		return -ETIME;
 	}
 	return qeth_idx_activate_get_answer(channel, idx_reply_cb);
@@ -2166,8 +2161,8 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
-	rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
-			      (addr_t) iob, 0, 0);
+	rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+				      (addr_t) iob, 0, 0, event_timeout);
 	spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: "
@@ -2199,8 +2194,6 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 		}
 	}
 
-	if (reply->rc == -EIO)
-		goto error;
 	rc = reply->rc;
 	qeth_put_reply(reply);
 	return rc;
@@ -2211,10 +2204,6 @@ time_err:
 	list_del_init(&reply->list);
 	spin_unlock_irqrestore(&reply->card->lock, flags);
 	atomic_inc(&reply->received);
-error:
-	atomic_set(&card->write.irq_pending, 0);
-	qeth_release_buffer(iob->channel, iob);
-	card->write.buf_no = (card->write.buf_no + 1) % QETH_CMD_BUFFER_NO;
 	rc = reply->rc;
 	qeth_put_reply(reply);
 	return rc;
@@ -3033,28 +3022,23 @@ static int qeth_send_startlan(struct qeth_card *card)
 	return rc;
 }
 
-static int qeth_default_setadapterparms_cb(struct qeth_card *card,
-		struct qeth_reply *reply, unsigned long data)
+static int qeth_setadpparms_inspect_rc(struct qeth_ipa_cmd *cmd)
 {
-	struct qeth_ipa_cmd *cmd;
-
-	QETH_CARD_TEXT(card, 4, "defadpcb");
-
-	cmd = (struct qeth_ipa_cmd *) data;
-	if (cmd->hdr.return_code == 0)
+	if (!cmd->hdr.return_code)
 		cmd->hdr.return_code =
 			cmd->data.setadapterparms.hdr.return_code;
-	return 0;
+	return cmd->hdr.return_code;
 }
 
 static int qeth_query_setadapterparms_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 
 	QETH_CARD_TEXT(card, 3, "quyadpcb");
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
-	cmd = (struct qeth_ipa_cmd *) data;
 	if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) {
 		card->info.link_type =
 		      cmd->data.setadapterparms.data.query_cmds_supp.lan_type;
@@ -3062,7 +3046,7 @@ static int qeth_query_setadapterparms_cb(struct qeth_card *card,
 	}
 	card->options.adp.supported_funcs =
 		cmd->data.setadapterparms.data.query_cmds_supp.supported_cmds;
-	return qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
+	return 0;
 }
 
 static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card,
@@ -3154,22 +3138,20 @@ EXPORT_SYMBOL_GPL(qeth_query_ipassists);
 static int qeth_query_switch_attributes_cb(struct qeth_card *card,
 				struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
-	struct qeth_switch_info *sw_info;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 	struct qeth_query_switch_attributes *attrs;
+	struct qeth_switch_info *sw_info;
 
 	QETH_CARD_TEXT(card, 2, "qswiatcb");
-	cmd = (struct qeth_ipa_cmd *) data;
-	sw_info = (struct qeth_switch_info *)reply->param;
-	if (cmd->data.setadapterparms.hdr.return_code == 0) {
-		attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
-		sw_info->capabilities = attrs->capabilities;
-		sw_info->settings = attrs->settings;
-		QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
-							sw_info->settings);
-	}
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
+	sw_info = (struct qeth_switch_info *)reply->param;
+	attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
+	sw_info->capabilities = attrs->capabilities;
+	sw_info->settings = attrs->settings;
+	QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
+			sw_info->settings);
 	return 0;
 }
 
@@ -4207,16 +4189,13 @@ EXPORT_SYMBOL_GPL(qeth_do_send_packet);
 static int qeth_setadp_promisc_mode_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 	struct qeth_ipacmd_setadpparms *setparms;
 
 	QETH_CARD_TEXT(card, 4, "prmadpcb");
 
-	cmd = (struct qeth_ipa_cmd *) data;
 	setparms = &(cmd->data.setadapterparms);
-
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
-	if (cmd->hdr.return_code) {
+	if (qeth_setadpparms_inspect_rc(cmd)) {
 		QETH_CARD_TEXT_(card, 4, "prmrc%x", cmd->hdr.return_code);
 		setparms->data.mode = SET_PROMISC_MODE_OFF;
 	}
@@ -4286,18 +4265,18 @@ EXPORT_SYMBOL_GPL(qeth_get_stats);
 static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 
 	QETH_CARD_TEXT(card, 4, "chgmaccb");
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
-	cmd = (struct qeth_ipa_cmd *) data;
 	if (!card->options.layer2 ||
 	    !(card->info.mac_bits & QETH_LAYER2_MAC_READ)) {
 		ether_addr_copy(card->dev->dev_addr,
 				cmd->data.setadapterparms.data.change_addr.addr);
 		card->info.mac_bits |= QETH_LAYER2_MAC_READ;
 	}
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
 	return 0;
 }
 
@@ -4328,13 +4307,15 @@ EXPORT_SYMBOL_GPL(qeth_setadpparms_change_macaddr);
 static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 	struct qeth_set_access_ctrl *access_ctrl_req;
 	int fallback = *(int *)reply->param;
 
 	QETH_CARD_TEXT(card, 4, "setaccb");
+	if (cmd->hdr.return_code)
+		return 0;
+	qeth_setadpparms_inspect_rc(cmd);
 
-	cmd = (struct qeth_ipa_cmd *) data;
 	access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
 	QETH_DBF_TEXT_(SETUP, 2, "setaccb");
 	QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name);
@@ -4407,7 +4388,6 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
 			card->options.isolation = card->options.prev_isolation;
 		break;
 	}
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
 	return 0;
 }
 
@@ -4695,14 +4675,15 @@ out:
 static int qeth_setadpparms_query_oat_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
 	struct qeth_qoat_priv *priv;
 	char *resdata;
 	int resdatalen;
 
 	QETH_CARD_TEXT(card, 3, "qoatcb");
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
-	cmd = (struct qeth_ipa_cmd *)data;
 	priv = (struct qeth_qoat_priv *)reply->param;
 	resdatalen = cmd->data.setadapterparms.hdr.cmdlength;
 	resdata = (char *)data + 28;
@@ -4796,21 +4777,18 @@ out:
 static int qeth_query_card_info_cb(struct qeth_card *card,
 				   struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct carrier_info *carrier_info = (struct carrier_info *)reply->param;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
 	struct qeth_query_card_info *card_info;
-	struct carrier_info *carrier_info;
 
 	QETH_CARD_TEXT(card, 2, "qcrdincb");
-	carrier_info = (struct carrier_info *)reply->param;
-	cmd = (struct qeth_ipa_cmd *)data;
-	card_info = &cmd->data.setadapterparms.data.card_info;
-	if (cmd->data.setadapterparms.hdr.return_code == 0) {
-		carrier_info->card_type = card_info->card_type;
-		carrier_info->port_mode = card_info->port_mode;
-		carrier_info->port_speed = card_info->port_speed;
-	}
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+	card_info = &cmd->data.setadapterparms.data.card_info;
+	carrier_info->card_type = card_info->card_type;
+	carrier_info->port_mode = card_info->port_mode;
+	carrier_info->port_speed = card_info->port_speed;
 	return 0;
 }
 
@@ -4857,7 +4835,7 @@ int qeth_vm_request_mac(struct qeth_card *card)
 		goto out;
 	}
 
-	ccw_device_get_id(CARD_DDEV(card), &id);
+	ccw_device_get_id(CARD_RDEV(card), &id);
 	request->resp_buf_len = sizeof(*response);
 	request->resp_version = DIAG26C_VERSION2;
 	request->op_code = DIAG26C_GET_MAC;
@@ -6563,10 +6541,14 @@ static int __init qeth_core_init(void)
 	mutex_init(&qeth_mod_mutex);
 
 	qeth_wq = create_singlethread_workqueue("qeth_wq");
+	if (!qeth_wq) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
 
 	rc = qeth_register_dbf_views();
 	if (rc)
-		goto out_err;
+		goto dbf_err;
 	qeth_core_root_dev = root_device_register("qeth");
 	rc = PTR_ERR_OR_ZERO(qeth_core_root_dev);
 	if (rc)
@@ -6603,6 +6585,8 @@ slab_err:
 	root_device_unregister(qeth_core_root_dev);
 register_err:
 	qeth_unregister_dbf_views();
+dbf_err:
+	destroy_workqueue(qeth_wq);
 out_err:
 	pr_err("Initializing the qeth device driver failed\n");
 	return rc;
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index 619f897b4bb0..f4d1ec0b8f5a 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -35,6 +35,18 @@ extern unsigned char IPA_PDU_HEADER[];
 #define QETH_HALT_CHANNEL_PARM	-11
 #define QETH_RCD_PARM -12
 
+static inline bool qeth_intparm_is_iob(unsigned long intparm)
+{
+	switch (intparm) {
+	case QETH_CLEAR_CHANNEL_PARM:
+	case QETH_HALT_CHANNEL_PARM:
+	case QETH_RCD_PARM:
+	case 0:
+		return false;
+	}
+	return true;
+}
+
 /*****************************************************************************/
 /* IP Assist related definitions                                             */
 /*****************************************************************************/
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 50a313806dde..b8079f2a65b3 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -21,7 +21,6 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <linux/hashtable.h>
-#include <linux/string.h>
 #include <asm/setup.h>
 #include "qeth_core.h"
 #include "qeth_l2.h"
@@ -122,13 +121,10 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
 	QETH_CARD_TEXT(card, 2, "L2Setmac");
 	rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETVMAC);
 	if (rc == 0) {
-		card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
-		ether_addr_copy(card->dev->dev_addr, mac);
 		dev_info(&card->gdev->dev,
-			"MAC address %pM successfully registered on device %s\n",
-			card->dev->dev_addr, card->dev->name);
+			 "MAC address %pM successfully registered on device %s\n",
+			 mac, card->dev->name);
 	} else {
-		card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
 		switch (rc) {
 		case -EEXIST:
 			dev_warn(&card->gdev->dev,
@@ -143,19 +139,6 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
 	return rc;
 }
 
-static int qeth_l2_send_delmac(struct qeth_card *card, __u8 *mac)
-{
-	int rc;
-
-	QETH_CARD_TEXT(card, 2, "L2Delmac");
-	if (!(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
-		return 0;
-	rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_DELVMAC);
-	if (rc == 0)
-		card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
-	return rc;
-}
-
 static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
 {
 	enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
@@ -520,6 +503,7 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p)
 {
 	struct sockaddr *addr = p;
 	struct qeth_card *card = dev->ml_priv;
+	u8 old_addr[ETH_ALEN];
 	int rc = 0;
 
 	QETH_CARD_TEXT(card, 3, "setmac");
@@ -531,14 +515,35 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p)
 		return -EOPNOTSUPP;
 	}
 	QETH_CARD_HEX(card, 3, addr->sa_data, ETH_ALEN);
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
 	if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
 		QETH_CARD_TEXT(card, 3, "setmcREC");
 		return -ERESTARTSYS;
 	}
-	rc = qeth_l2_send_delmac(card, &card->dev->dev_addr[0]);
-	if (!rc || (rc == -ENOENT))
-		rc = qeth_l2_send_setmac(card, addr->sa_data);
-	return rc ? -EINVAL : 0;
+
+	if (!qeth_card_hw_is_reachable(card)) {
+		ether_addr_copy(dev->dev_addr, addr->sa_data);
+		return 0;
+	}
+
+	/* don't register the same address twice */
+	if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
+	    (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
+		return 0;
+
+	/* add the new address, switch over, drop the old */
+	rc = qeth_l2_send_setmac(card, addr->sa_data);
+	if (rc)
+		return rc;
+	ether_addr_copy(old_addr, dev->dev_addr);
+	ether_addr_copy(dev->dev_addr, addr->sa_data);
+
+	if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
+		qeth_l2_remove_mac(card, old_addr);
+	card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
+	return 0;
 }
 
 static void qeth_promisc_to_bridge(struct qeth_card *card)
@@ -1068,8 +1073,9 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		goto out_remove;
 	}
 
-	if (card->info.type != QETH_CARD_TYPE_OSN)
-		qeth_l2_send_setmac(card, &card->dev->dev_addr[0]);
+	if (card->info.type != QETH_CARD_TYPE_OSN &&
+	    !qeth_l2_send_setmac(card, card->dev->dev_addr))
+		card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
 
 	if (qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP)) {
 		if (card->info.hwtrap &&
@@ -1339,8 +1345,8 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len,
 	qeth_prepare_control_data(card, len, iob);
 	QETH_CARD_TEXT(card, 6, "osnoirqp");
 	spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
-	rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
-			      (addr_t) iob, 0, 0);
+	rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+				      (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: "
diff --git a/drivers/s390/net/smsgiucv.c b/drivers/s390/net/smsgiucv.c
index 3b0c8b8a7634..066b5c3aaae6 100644
--- a/drivers/s390/net/smsgiucv.c
+++ b/drivers/s390/net/smsgiucv.c
@@ -176,7 +176,7 @@ static struct device_driver smsg_driver = {
 
 static void __exit smsg_exit(void)
 {
-	cpcmd("SET SMSG IUCV", NULL, 0, NULL);
+	cpcmd("SET SMSG OFF", NULL, 0, NULL);
 	device_unregister(smsg_dev);
 	iucv_unregister(&smsg_handler, 1);
 	driver_unregister(&smsg_driver);
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index a8b831000b2d..18c4f933e8b9 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -4,7 +4,7 @@
  *
  * Debug traces for zfcp.
  *
- * Copyright IBM Corp. 2002, 2017
+ * Copyright IBM Corp. 2002, 2018
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -308,6 +308,27 @@ void zfcp_dbf_rec_trig(char *tag, struct zfcp_adapter *adapter,
 	spin_unlock_irqrestore(&dbf->rec_lock, flags);
 }
 
+/**
+ * zfcp_dbf_rec_trig_lock - trace event related to triggered recovery with lock
+ * @tag: identifier for event
+ * @adapter: adapter on which the erp_action should run
+ * @port: remote port involved in the erp_action
+ * @sdev: scsi device involved in the erp_action
+ * @want: wanted erp_action
+ * @need: required erp_action
+ *
+ * The adapter->erp_lock must not be held.
+ */
+void zfcp_dbf_rec_trig_lock(char *tag, struct zfcp_adapter *adapter,
+			    struct zfcp_port *port, struct scsi_device *sdev,
+			    u8 want, u8 need)
+{
+	unsigned long flags;
+
+	read_lock_irqsave(&adapter->erp_lock, flags);
+	zfcp_dbf_rec_trig(tag, adapter, port, sdev, want, need);
+	read_unlock_irqrestore(&adapter->erp_lock, flags);
+}
 
 /**
  * zfcp_dbf_rec_run_lvl - trace event related to running recovery
diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h
index bf8ea4df2bb8..e5eed8aac0ce 100644
--- a/drivers/s390/scsi/zfcp_ext.h
+++ b/drivers/s390/scsi/zfcp_ext.h
@@ -4,7 +4,7 @@
  *
  * External function declarations.
  *
- * Copyright IBM Corp. 2002, 2016
+ * Copyright IBM Corp. 2002, 2018
  */
 
 #ifndef ZFCP_EXT_H
@@ -35,6 +35,9 @@ extern int zfcp_dbf_adapter_register(struct zfcp_adapter *);
 extern void zfcp_dbf_adapter_unregister(struct zfcp_adapter *);
 extern void zfcp_dbf_rec_trig(char *, struct zfcp_adapter *,
 			      struct zfcp_port *, struct scsi_device *, u8, u8);
+extern void zfcp_dbf_rec_trig_lock(char *tag, struct zfcp_adapter *adapter,
+				   struct zfcp_port *port,
+				   struct scsi_device *sdev, u8 want, u8 need);
 extern void zfcp_dbf_rec_run(char *, struct zfcp_erp_action *);
 extern void zfcp_dbf_rec_run_lvl(int level, char *tag,
 				 struct zfcp_erp_action *erp);
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 4d2ba5682493..22f9562f415c 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -4,7 +4,7 @@
  *
  * Interface to Linux SCSI midlayer.
  *
- * Copyright IBM Corp. 2002, 2017
+ * Copyright IBM Corp. 2002, 2018
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -618,9 +618,9 @@ static void zfcp_scsi_rport_register(struct zfcp_port *port)
 	ids.port_id = port->d_id;
 	ids.roles = FC_RPORT_ROLE_FCP_TARGET;
 
-	zfcp_dbf_rec_trig("scpaddy", port->adapter, port, NULL,
-			  ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD,
-			  ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD);
+	zfcp_dbf_rec_trig_lock("scpaddy", port->adapter, port, NULL,
+			       ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD,
+			       ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD);
 	rport = fc_remote_port_add(port->adapter->scsi_host, 0, &ids);
 	if (!rport) {
 		dev_err(&port->adapter->ccw_device->dev,
@@ -642,9 +642,9 @@ static void zfcp_scsi_rport_block(struct zfcp_port *port)
 	struct fc_rport *rport = port->rport;
 
 	if (rport) {
-		zfcp_dbf_rec_trig("scpdely", port->adapter, port, NULL,
-				  ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL,
-				  ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL);
+		zfcp_dbf_rec_trig_lock("scpdely", port->adapter, port, NULL,
+				       ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL,
+				       ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL);
 		fc_remote_port_delete(rport);
 		port->rport = NULL;
 	}
diff --git a/drivers/sbus/char/Kconfig b/drivers/sbus/char/Kconfig
index bf3c5f735614..89edd13fd572 100644
--- a/drivers/sbus/char/Kconfig
+++ b/drivers/sbus/char/Kconfig
@@ -28,13 +28,6 @@ config TADPOLE_TS102_UCTRL
 	  events, and can also notice the attachment/detachment of external
 	  monitors and mice.
 
-config SUN_JSFLASH
-	tristate "JavaStation OS Flash SIMM"
-	depends on SPARC32
-	help
-	  If you say Y here, you will be able to boot from your JavaStation's
-	  Flash memory.
-
 config BBC_I2C
 	tristate "UltraSPARC-III bootbus i2c controller driver"
 	depends on PCI && SPARC64
diff --git a/drivers/sbus/char/Makefile b/drivers/sbus/char/Makefile
index 8c48ed96683f..44347c918f6b 100644
--- a/drivers/sbus/char/Makefile
+++ b/drivers/sbus/char/Makefile
@@ -15,6 +15,5 @@ obj-$(CONFIG_DISPLAY7SEG)		+= display7seg.o
 obj-$(CONFIG_OBP_FLASH)			+= flash.o
 obj-$(CONFIG_SUN_OPENPROMIO)		+= openprom.o
 obj-$(CONFIG_TADPOLE_TS102_UCTRL)	+= uctrl.o
-obj-$(CONFIG_SUN_JSFLASH)		+= jsflash.o
 obj-$(CONFIG_BBC_I2C)			+= bbc.o
 obj-$(CONFIG_ORACLE_DAX) 		+= oradax.o
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
deleted file mode 100644
index 14f377ac1280..000000000000
--- a/drivers/sbus/char/jsflash.c
+++ /dev/null
@@ -1,658 +0,0 @@
-/*
- * drivers/sbus/char/jsflash.c
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds	(drivers/char/mem.c)
- *  Copyright (C) 1997  Eddie C. Dost		(drivers/sbus/char/flash.c)
- *  Copyright (C) 1997-2000 Pavel Machek <pavel@ucw.cz>   (drivers/block/nbd.c)
- *  Copyright (C) 1999-2000 Pete Zaitcev
- *
- * This driver is used to program OS into a Flash SIMM on
- * Krups and Espresso platforms.
- *
- * TODO: do not allow erase/programming if file systems are mounted.
- * TODO: Erase/program both banks of a 8MB SIMM.
- *
- * It is anticipated that programming an OS Flash will be a routine
- * procedure. In the same time it is exceedingly dangerous because
- * a user can program its OBP flash with OS image and effectively
- * kill the machine.
- *
- * This driver uses an interface different from Eddie's flash.c
- * as a silly safeguard.
- *
- * XXX The flash.c manipulates page caching characteristics in a certain
- * dubious way; also it assumes that remap_pfn_range() can remap
- * PCI bus locations, which may be false. ioremap() must be used
- * instead. We should discuss this.
- */
-
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/miscdevice.h>
-#include <linux/fcntl.h>
-#include <linux/poll.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <linux/genhd.h>
-#include <linux/blkdev.h>
-#include <linux/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/io.h>
-#include <asm/pcic.h>
-#include <asm/oplib.h>
-
-#include <asm/jsflash.h>		/* ioctl arguments. <linux/> ?? */
-#define JSFIDSZ		(sizeof(struct jsflash_ident_arg))
-#define JSFPRGSZ	(sizeof(struct jsflash_program_arg))
-
-/*
- * Our device numbers have no business in system headers.
- * The only thing a user knows is the device name /dev/jsflash.
- *
- * Block devices are laid out like this:
- *   minor+0	- Bootstrap, for 8MB SIMM 0x20400000[0x800000]
- *   minor+1	- Filesystem to mount, normally 0x20400400[0x7ffc00]
- *   minor+2	- Whole flash area for any case... 0x20000000[0x01000000]
- * Total 3 minors per flash device.
- *
- * It is easier to have static size vectors, so we define
- * a total minor range JSF_MAX, which must cover all minors.
- */
-/* character device */
-#define JSF_MINOR	178	/* 178 is registered with hpa */
-/* block device */
-#define JSF_MAX		 3	/* 3 minors wasted total so far. */
-#define JSF_NPART	 3	/* 3 minors per flash device */
-#define JSF_PART_BITS	 2	/* 2 bits of minors to cover JSF_NPART */
-#define JSF_PART_MASK	 0x3	/* 2 bits mask */
-
-static DEFINE_MUTEX(jsf_mutex);
-
-/*
- * Access functions.
- * We could ioremap(), but it's easier this way.
- */
-static unsigned int jsf_inl(unsigned long addr)
-{
-	unsigned long retval;
-
-	__asm__ __volatile__("lda [%1] %2, %0\n\t" :
-				"=r" (retval) :
-				"r" (addr), "i" (ASI_M_BYPASS));
-        return retval;
-}
-
-static void jsf_outl(unsigned long addr, __u32 data)
-{
-
-	__asm__ __volatile__("sta %0, [%1] %2\n\t" : :
-				"r" (data), "r" (addr), "i" (ASI_M_BYPASS) :
-				"memory");
-}
-
-/*
- * soft carrier
- */
-
-struct jsfd_part {
-	unsigned long dbase;
-	unsigned long dsize;
-};
-
-struct jsflash {
-	unsigned long base;
-	unsigned long size;
-	unsigned long busy;		/* In use? */
-	struct jsflash_ident_arg id;
-	/* int mbase; */		/* Minor base, typically zero */
-	struct jsfd_part dv[JSF_NPART];
-};
-
-/*
- * We do not map normal memory or obio as a safety precaution.
- * But offsets are real, for ease of userland programming.
- */
-#define JSF_BASE_TOP	0x30000000
-#define JSF_BASE_ALL	0x20000000
-
-#define JSF_BASE_JK	0x20400000
-
-/*
- */
-static struct gendisk *jsfd_disk[JSF_MAX];
-
-/*
- * Let's pretend we may have several of these...
- */
-static struct jsflash jsf0;
-
-/*
- * Wait for AMD to finish its embedded algorithm.
- * We use the Toggle bit DQ6 (0x40) because it does not
- * depend on the data value as /DATA bit DQ7 does.
- *
- * XXX Do we need any timeout here? So far it never hanged, beware broken hw.
- */
-static void jsf_wait(unsigned long p) {
-	unsigned int x1, x2;
-
-	for (;;) {
-		x1 = jsf_inl(p);
-		x2 = jsf_inl(p);
-		if ((x1 & 0x40404040) == (x2 & 0x40404040)) return;
-	}
-}
-
-/*
- * Programming will only work if Flash is clean,
- * we leave it to the programmer application.
- *
- * AMD must be programmed one byte at a time;
- * thus, Simple Tech SIMM must be written 4 bytes at a time.
- *
- * Write waits for the chip to become ready after the write
- * was finished. This is done so that application would read
- * consistent data after the write is done.
- */
-static void jsf_write4(unsigned long fa, u32 data) {
-
-	jsf_outl(fa, 0xAAAAAAAA);		/* Unlock 1 Write 1 */
-	jsf_outl(fa, 0x55555555);		/* Unlock 1 Write 2 */
-	jsf_outl(fa, 0xA0A0A0A0);		/* Byte Program */
-	jsf_outl(fa, data);
-
-	jsf_wait(fa);
-}
-
-/*
- */
-static void jsfd_read(char *buf, unsigned long p, size_t togo) {
-	union byte4 {
-		char s[4];
-		unsigned int n;
-	} b;
-
-	while (togo >= 4) {
-		togo -= 4;
-		b.n = jsf_inl(p);
-		memcpy(buf, b.s, 4);
-		p += 4;
-		buf += 4;
-	}
-}
-
-static int jsfd_queue;
-
-static struct request *jsfd_next_request(void)
-{
-	struct request_queue *q;
-	struct request *rq;
-	int old_pos = jsfd_queue;
-
-	do {
-		q = jsfd_disk[jsfd_queue]->queue;
-		if (++jsfd_queue == JSF_MAX)
-			jsfd_queue = 0;
-		if (q) {
-			rq = blk_fetch_request(q);
-			if (rq)
-				return rq;
-		}
-	} while (jsfd_queue != old_pos);
-
-	return NULL;
-}
-
-static void jsfd_request(void)
-{
-	struct request *req;
-
-	req = jsfd_next_request();
-	while (req) {
-		struct jsfd_part *jdp = req->rq_disk->private_data;
-		unsigned long offset = blk_rq_pos(req) << 9;
-		size_t len = blk_rq_cur_bytes(req);
-		blk_status_t err = BLK_STS_IOERR;
-
-		if ((offset + len) > jdp->dsize)
-			goto end;
-
-		if (rq_data_dir(req) != READ) {
-			printk(KERN_ERR "jsfd: write\n");
-			goto end;
-		}
-
-		if ((jdp->dbase & 0xff000000) != 0x20000000) {
-			printk(KERN_ERR "jsfd: bad base %x\n", (int)jdp->dbase);
-			goto end;
-		}
-
-		jsfd_read(bio_data(req->bio), jdp->dbase + offset, len);
-		err = BLK_STS_OK;
-	end:
-		if (!__blk_end_request_cur(req, err))
-			req = jsfd_next_request();
-	}
-}
-
-static void jsfd_do_request(struct request_queue *q)
-{
-	jsfd_request();
-}
-
-/*
- * The memory devices use the full 32/64 bits of the offset, and so we cannot
- * check against negative addresses: they are ok. The return value is weird,
- * though, in that case (0).
- *
- * also note that seeking relative to the "end of file" isn't supported:
- * it has no meaning, so it returns -EINVAL.
- */
-static loff_t jsf_lseek(struct file * file, loff_t offset, int orig)
-{
-	loff_t ret;
-
-	mutex_lock(&jsf_mutex);
-	switch (orig) {
-		case 0:
-			file->f_pos = offset;
-			ret = file->f_pos;
-			break;
-		case 1:
-			file->f_pos += offset;
-			ret = file->f_pos;
-			break;
-		default:
-			ret = -EINVAL;
-	}
-	mutex_unlock(&jsf_mutex);
-	return ret;
-}
-
-/*
- * OS SIMM Cannot be read in other size but a 32bits word.
- */
-static ssize_t jsf_read(struct file * file, char __user * buf, 
-    size_t togo, loff_t *ppos)
-{
-	unsigned long p = *ppos;
-	char __user *tmp = buf;
-
-	union byte4 {
-		char s[4];
-		unsigned int n;
-	} b;
-
-	if (p < JSF_BASE_ALL || p >= JSF_BASE_TOP) {
-		return 0;
-	}
-
-	if ((p + togo) < p	/* wrap */
-	   || (p + togo) >= JSF_BASE_TOP) {
-		togo = JSF_BASE_TOP - p;
-	}
-
-	if (p < JSF_BASE_ALL && togo != 0) {
-#if 0 /* __bzero XXX */
-		size_t x = JSF_BASE_ALL - p;
-		if (x > togo) x = togo;
-		clear_user(tmp, x);
-		tmp += x;
-		p += x;
-		togo -= x;
-#else
-		/*
-		 * Implementation of clear_user() calls __bzero
-		 * without regard to modversions,
-		 * so we cannot build a module.
-		 */
-		return 0;
-#endif
-	}
-
-	while (togo >= 4) {
-		togo -= 4;
-		b.n = jsf_inl(p);
-		if (copy_to_user(tmp, b.s, 4))
-			return -EFAULT;
-		tmp += 4;
-		p += 4;
-	}
-
-	/*
-	 * XXX Small togo may remain if 1 byte is ordered.
-	 * It would be nice if we did a word size read and unpacked it.
-	 */
-
-	*ppos = p;
-	return tmp-buf;
-}
-
-static ssize_t jsf_write(struct file * file, const char __user * buf,
-    size_t count, loff_t *ppos)
-{
-	return -ENOSPC;
-}
-
-/*
- */
-static int jsf_ioctl_erase(unsigned long arg)
-{
-	unsigned long p;
-
-	/* p = jsf0.base;	hits wrong bank */
-	p = 0x20400000;
-
-	jsf_outl(p, 0xAAAAAAAA);		/* Unlock 1 Write 1 */
-	jsf_outl(p, 0x55555555);		/* Unlock 1 Write 2 */
-	jsf_outl(p, 0x80808080);		/* Erase setup */
-	jsf_outl(p, 0xAAAAAAAA);		/* Unlock 2 Write 1 */
-	jsf_outl(p, 0x55555555);		/* Unlock 2 Write 2 */
-	jsf_outl(p, 0x10101010);		/* Chip erase */
-
-#if 0
-	/*
-	 * This code is ok, except that counter based timeout
-	 * has no place in this world. Let's just drop timeouts...
-	 */
-	{
-		int i;
-		__u32 x;
-		for (i = 0; i < 1000000; i++) {
-			x = jsf_inl(p);
-			if ((x & 0x80808080) == 0x80808080) break;
-		}
-		if ((x & 0x80808080) != 0x80808080) {
-			printk("jsf0: erase timeout with 0x%08x\n", x);
-		} else {
-			printk("jsf0: erase done with 0x%08x\n", x);
-		}
-	}
-#else
-	jsf_wait(p);
-#endif
-
-	return 0;
-}
-
-/*
- * Program a block of flash.
- * Very simple because we can do it byte by byte anyway.
- */
-static int jsf_ioctl_program(void __user *arg)
-{
-	struct jsflash_program_arg abuf;
-	char __user *uptr;
-	unsigned long p;
-	unsigned int togo;
-	union {
-		unsigned int n;
-		char s[4];
-	} b;
-
-	if (copy_from_user(&abuf, arg, JSFPRGSZ))
-		return -EFAULT; 
-	p = abuf.off;
-	togo = abuf.size;
-	if ((togo & 3) || (p & 3)) return -EINVAL;
-
-	uptr = (char __user *) (unsigned long) abuf.data;
-	while (togo != 0) {
-		togo -= 4;
-		if (copy_from_user(&b.s[0], uptr, 4))
-			return -EFAULT;
-		jsf_write4(p, b.n);
-		p += 4;
-		uptr += 4;
-	}
-
-	return 0;
-}
-
-static long jsf_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
-	mutex_lock(&jsf_mutex);
-	int error = -ENOTTY;
-	void __user *argp = (void __user *)arg;
-
-	if (!capable(CAP_SYS_ADMIN)) {
-		mutex_unlock(&jsf_mutex);
-		return -EPERM;
-	}
-	switch (cmd) {
-	case JSFLASH_IDENT:
-		if (copy_to_user(argp, &jsf0.id, JSFIDSZ)) {
-			mutex_unlock(&jsf_mutex);
-			return -EFAULT;
-		}
-		break;
-	case JSFLASH_ERASE:
-		error = jsf_ioctl_erase(arg);
-		break;
-	case JSFLASH_PROGRAM:
-		error = jsf_ioctl_program(argp);
-		break;
-	}
-
-	mutex_unlock(&jsf_mutex);
-	return error;
-}
-
-static int jsf_mmap(struct file * file, struct vm_area_struct * vma)
-{
-	return -ENXIO;
-}
-
-static int jsf_open(struct inode * inode, struct file * filp)
-{
-	mutex_lock(&jsf_mutex);
-	if (jsf0.base == 0) {
-		mutex_unlock(&jsf_mutex);
-		return -ENXIO;
-	}
-	if (test_and_set_bit(0, (void *)&jsf0.busy) != 0) {
-		mutex_unlock(&jsf_mutex);
-		return -EBUSY;
-	}
-
-	mutex_unlock(&jsf_mutex);
-	return 0;	/* XXX What security? */
-}
-
-static int jsf_release(struct inode *inode, struct file *file)
-{
-	jsf0.busy = 0;
-	return 0;
-}
-
-static const struct file_operations jsf_fops = {
-	.owner =	THIS_MODULE,
-	.llseek =	jsf_lseek,
-	.read =		jsf_read,
-	.write =	jsf_write,
-	.unlocked_ioctl =	jsf_ioctl,
-	.mmap =		jsf_mmap,
-	.open =		jsf_open,
-	.release =	jsf_release,
-};
-
-static struct miscdevice jsf_dev = { JSF_MINOR, "jsflash", &jsf_fops };
-
-static const struct block_device_operations jsfd_fops = {
-	.owner =	THIS_MODULE,
-};
-
-static int jsflash_init(void)
-{
-	int rc;
-	struct jsflash *jsf;
-	phandle node;
-	char banner[128];
-	struct linux_prom_registers reg0;
-
-	node = prom_getchild(prom_root_node);
-	node = prom_searchsiblings(node, "flash-memory");
-	if (node != 0 && (s32)node != -1) {
-		if (prom_getproperty(node, "reg",
-		    (char *)&reg0, sizeof(reg0)) == -1) {
-			printk("jsflash: no \"reg\" property\n");
-			return -ENXIO;
-		}
-		if (reg0.which_io != 0) {
-			printk("jsflash: bus number nonzero: 0x%x:%x\n",
-			    reg0.which_io, reg0.phys_addr);
-			return -ENXIO;
-		}
-		/*
-		 * Flash may be somewhere else, for instance on Ebus.
-		 * So, don't do the following check for IIep flash space.
-		 */
-#if 0
-		if ((reg0.phys_addr >> 24) != 0x20) {
-			printk("jsflash: suspicious address: 0x%x:%x\n",
-			    reg0.which_io, reg0.phys_addr);
-			return -ENXIO;
-		}
-#endif
-		if ((int)reg0.reg_size <= 0) {
-			printk("jsflash: bad size 0x%x\n", (int)reg0.reg_size);
-			return -ENXIO;
-		}
-	} else {
-		/* XXX Remove this code once PROLL ID12 got widespread */
-		printk("jsflash: no /flash-memory node, use PROLL >= 12\n");
-		prom_getproperty(prom_root_node, "banner-name", banner, 128);
-		if (strcmp (banner, "JavaStation-NC") != 0 &&
-		    strcmp (banner, "JavaStation-E") != 0) {
-			return -ENXIO;
-		}
-		reg0.which_io = 0;
-		reg0.phys_addr = 0x20400000;
-		reg0.reg_size  = 0x00800000;
-	}
-
-	/* Let us be really paranoid for modifications to probing code. */
-	if (sparc_cpu_model != sun4m) {
-		/* We must be on sun4m because we use MMU Bypass ASI. */
-		return -ENXIO;
-	}
-
-	if (jsf0.base == 0) {
-		jsf = &jsf0;
-
-		jsf->base = reg0.phys_addr;
-		jsf->size = reg0.reg_size;
-
-		/* XXX Redo the userland interface. */
-		jsf->id.off = JSF_BASE_ALL;
-		jsf->id.size = 0x01000000;	/* 16M - all segments */
-		strcpy(jsf->id.name, "Krups_all");
-
-		jsf->dv[0].dbase = jsf->base;
-		jsf->dv[0].dsize = jsf->size;
-		jsf->dv[1].dbase = jsf->base + 1024;
-		jsf->dv[1].dsize = jsf->size - 1024;
-		jsf->dv[2].dbase = JSF_BASE_ALL;
-		jsf->dv[2].dsize = 0x01000000;
-
-		printk("Espresso Flash @0x%lx [%d MB]\n", jsf->base,
-		    (int) (jsf->size / (1024*1024)));
-	}
-
-	if ((rc = misc_register(&jsf_dev)) != 0) {
-		printk(KERN_ERR "jsf: unable to get misc minor %d\n",
-		    JSF_MINOR);
-		jsf0.base = 0;
-		return rc;
-	}
-
-	return 0;
-}
-
-static int jsfd_init(void)
-{
-	static DEFINE_SPINLOCK(lock);
-	struct jsflash *jsf;
-	struct jsfd_part *jdp;
-	int err;
-	int i;
-
-	if (jsf0.base == 0)
-		return -ENXIO;
-
-	err = -ENOMEM;
-	for (i = 0; i < JSF_MAX; i++) {
-		struct gendisk *disk = alloc_disk(1);
-		if (!disk)
-			goto out;
-		disk->queue = blk_init_queue(jsfd_do_request, &lock);
-		if (!disk->queue) {
-			put_disk(disk);
-			goto out;
-		}
-		blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
-		jsfd_disk[i] = disk;
-	}
-
-	if (register_blkdev(JSFD_MAJOR, "jsfd")) {
-		err = -EIO;
-		goto out;
-	}
-
-	for (i = 0; i < JSF_MAX; i++) {
-		struct gendisk *disk = jsfd_disk[i];
-		if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
-		jsf = &jsf0;	/* actually, &jsfv[i >> JSF_PART_BITS] */
-		jdp = &jsf->dv[i&JSF_PART_MASK];
-
-		disk->major = JSFD_MAJOR;
-		disk->first_minor = i;
-		sprintf(disk->disk_name, "jsfd%d", i);
-		disk->fops = &jsfd_fops;
-		set_capacity(disk, jdp->dsize >> 9);
-		disk->private_data = jdp;
-		add_disk(disk);
-		set_disk_ro(disk, 1);
-	}
-	return 0;
-out:
-	while (i--)
-		put_disk(jsfd_disk[i]);
-	return err;
-}
-
-MODULE_LICENSE("GPL");
-
-static int __init jsflash_init_module(void) {
-	int rc;
-
-	if ((rc = jsflash_init()) == 0) {
-		jsfd_init();
-		return 0;
-	}
-	return rc;
-}
-
-static void __exit jsflash_cleanup_module(void)
-{
-	int i;
-
-	for (i = 0; i < JSF_MAX; i++) {
-		if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
-		del_gendisk(jsfd_disk[i]);
-		blk_cleanup_queue(jsfd_disk[i]->queue);
-		put_disk(jsfd_disk[i]);
-	}
-	if (jsf0.busy)
-		printk("jsf0: cleaning busy unit\n");
-	jsf0.base = 0;
-	jsf0.busy = 0;
-
-	misc_deregister(&jsf_dev);
-	unregister_blkdev(JSFD_MAJOR, "jsfd");
-}
-
-module_init(jsflash_init_module);
-module_exit(jsflash_cleanup_module);
diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c
index c44d7c7ffc92..1754f55e2fac 100644
--- a/drivers/sbus/char/oradax.c
+++ b/drivers/sbus/char/oradax.c
@@ -3,7 +3,7 @@
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
+ * the Free Software Foundation, either version 2 of the License, or
  * (at your option) any later version.
  *
  * This program is distributed in the hope that it will be useful,
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index e29f9b8fd66d..56c940394729 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -182,7 +182,7 @@ zalon7xx-objs	:= zalon.o ncr53c8xx.o
 NCR_Q720_mod-objs	:= NCR_Q720.o ncr53c8xx.o
 
 # Files generated that shall be removed upon make clean
-clean-files :=	53c700_d.h 53c700_u.h
+clean-files :=	53c700_d.h 53c700_u.h scsi_devinfo_tbl.c
 
 $(obj)/53c700.o $(MODVERDIR)/$(obj)/53c700.ver: $(obj)/53c700_d.h
 
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 0156c9623c35..d62ddd63f4fe 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -724,6 +724,8 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
 	int wait;
 	unsigned long flags = 0;
 	unsigned long mflags = 0;
+	struct aac_hba_cmd_req *hbacmd = (struct aac_hba_cmd_req *)
+			fibptr->hw_fib_va;
 
 	fibptr->flags = (FIB_CONTEXT_FLAG | FIB_CONTEXT_FLAG_NATIVE_HBA);
 	if (callback) {
@@ -734,11 +736,9 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
 		wait = 1;
 
 
-	if (command == HBA_IU_TYPE_SCSI_CMD_REQ) {
-		struct aac_hba_cmd_req *hbacmd =
-			(struct aac_hba_cmd_req *)fibptr->hw_fib_va;
+	hbacmd->iu_type = command;
 
-		hbacmd->iu_type = command;
+	if (command == HBA_IU_TYPE_SCSI_CMD_REQ) {
 		/* bit1 of request_id must be 0 */
 		hbacmd->request_id =
 			cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1);
diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c
index abddde11982b..98597b59c12a 100644
--- a/drivers/scsi/fnic/fnic_trace.c
+++ b/drivers/scsi/fnic/fnic_trace.c
@@ -296,7 +296,7 @@ int fnic_get_stats_data(struct stats_debug_info *debug,
 		  "Number of Abort FW Timeouts: %lld\n"
 		  "Number of Abort IO NOT Found: %lld\n"
 
-		  "Abord issued times: \n"
+		  "Abort issued times: \n"
 		  "            < 6 sec : %lld\n"
 		  "     6 sec - 20 sec : %lld\n"
 		  "    20 sec - 30 sec : %lld\n"
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index c35f05c4c6bb..85604795d8ee 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -3882,7 +3882,7 @@ static enum blk_eh_timer_return gdth_timed_out(struct scsi_cmnd *scp)
 	struct gdth_cmndinfo *cmndinfo = gdth_cmnd_priv(scp);
 	u8 b, t;
 	unsigned long flags;
-	enum blk_eh_timer_return retval = BLK_EH_NOT_HANDLED;
+	enum blk_eh_timer_return retval = BLK_EH_DONE;
 
 	TRACE(("%s() cmd 0x%x\n", scp->cmnd[0], __func__));
 	b = scp->device->channel;
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index edb7be786c65..9e8de1462593 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -291,7 +291,7 @@ sci_mpc_agent_validate_phy_configuration(struct isci_host *ihost,
 		 * Note: We have not moved the current phy_index so we will actually
 		 *       compare the startting phy with itself.
 		 *       This is expected and required to add the phy to the port. */
-		while (phy_index < SCI_MAX_PHYS) {
+		for (; phy_index < SCI_MAX_PHYS; phy_index++) {
 			if ((phy_mask & (1 << phy_index)) == 0)
 				continue;
 			sci_phy_get_sas_address(&ihost->phys[phy_index],
@@ -311,7 +311,6 @@ sci_mpc_agent_validate_phy_configuration(struct isci_host *ihost,
 					      &ihost->phys[phy_index]);
 
 			assigned_phy_mask |= (1 << phy_index);
-			phy_index++;
 		}
 
 	}
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 15a2fef51e38..71bdc0b52cf9 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1963,7 +1963,7 @@ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn)
 
 enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 {
-	enum blk_eh_timer_return rc = BLK_EH_NOT_HANDLED;
+	enum blk_eh_timer_return rc = BLK_EH_DONE;
 	struct iscsi_task *task = NULL, *running_task;
 	struct iscsi_cls_session *cls_session;
 	struct iscsi_session *session;
@@ -1982,7 +1982,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 		 * Raced with completion. Blk layer has taken ownership
 		 * so let timeout code complete it now.
 		 */
-		rc = BLK_EH_HANDLED;
+		rc = BLK_EH_DONE;
 		goto done;
 	}
 
@@ -1997,7 +1997,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 		if (unlikely(system_state != SYSTEM_RUNNING)) {
 			sc->result = DID_NO_CONNECT << 16;
 			ISCSI_DBG_EH(session, "sc on shutdown, handled\n");
-			rc = BLK_EH_HANDLED;
+			rc = BLK_EH_DONE;
 			goto done;
 		}
 		/*
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 7195cff51d4c..91f5e2c68dbc 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -2731,53 +2731,6 @@ proc_show_rdrv_40(struct seq_file *m, void *v)
 	return proc_show_rdrv(m, m->private, 30, 39);
 }
 
-
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int mega_proc_open(struct inode *inode, struct file *file)
-{
-	adapter_t *adapter = proc_get_parent_data(inode);
-	int (*show)(struct seq_file *, void *) = PDE_DATA(inode);
-
-	return single_open(file, show, adapter);
-}
-
-static const struct file_operations mega_proc_fops = {
-	.open		= mega_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-/*
- * Table of proc files we need to create.
- */
-struct mega_proc_file {
-	const char *name;
-	unsigned short ptr_offset;
-	int (*show) (struct seq_file *m, void *v);
-};
-
-static const struct mega_proc_file mega_proc_files[] = {
-	{ "config",	      offsetof(adapter_t, proc_read), proc_show_config },
-	{ "stat",	      offsetof(adapter_t, proc_stat), proc_show_stat },
-	{ "mailbox",	      offsetof(adapter_t, proc_mbox), proc_show_mbox },
-#if MEGA_HAVE_ENH_PROC
-	{ "rebuild-rate",     offsetof(adapter_t, proc_rr), proc_show_rebuild_rate },
-	{ "battery-status",   offsetof(adapter_t, proc_battery), proc_show_battery },
-	{ "diskdrives-ch0",   offsetof(adapter_t, proc_pdrvstat[0]), proc_show_pdrv_ch0 },
-	{ "diskdrives-ch1",   offsetof(adapter_t, proc_pdrvstat[1]), proc_show_pdrv_ch1 },
-	{ "diskdrives-ch2",   offsetof(adapter_t, proc_pdrvstat[2]), proc_show_pdrv_ch2 },
-	{ "diskdrives-ch3",   offsetof(adapter_t, proc_pdrvstat[3]), proc_show_pdrv_ch3 },
-	{ "raiddrives-0-9",   offsetof(adapter_t, proc_rdrvstat[0]), proc_show_rdrv_10 },
-	{ "raiddrives-10-19", offsetof(adapter_t, proc_rdrvstat[1]), proc_show_rdrv_20 },
-	{ "raiddrives-20-29", offsetof(adapter_t, proc_rdrvstat[2]), proc_show_rdrv_30 },
-	{ "raiddrives-30-39", offsetof(adapter_t, proc_rdrvstat[3]), proc_show_rdrv_40 },
-#endif
-	{ NULL }
-};
-
 /**
  * mega_create_proc_entry()
  * @index - index in soft state array
@@ -2788,31 +2741,45 @@ static const struct mega_proc_file mega_proc_files[] = {
 static void
 mega_create_proc_entry(int index, struct proc_dir_entry *parent)
 {
-	const struct mega_proc_file *f;
-	adapter_t	*adapter = hba_soft_state[index];
-	struct proc_dir_entry	*dir, *de, **ppde;
-	u8		string[16];
+	adapter_t *adapter = hba_soft_state[index];
+	struct proc_dir_entry *dir;
+	u8 string[16];
 
 	sprintf(string, "hba%d", adapter->host->host_no);
-
-	dir = adapter->controller_proc_dir_entry =
-		proc_mkdir_data(string, 0, parent, adapter);
-	if(!dir) {
+	dir = proc_mkdir_data(string, 0, parent, adapter);
+	if (!dir) {
 		dev_warn(&adapter->dev->dev, "proc_mkdir failed\n");
 		return;
 	}
 
-	for (f = mega_proc_files; f->name; f++) {
-		de = proc_create_data(f->name, S_IRUSR, dir, &mega_proc_fops,
-				      f->show);
-		if (!de) {
-			dev_warn(&adapter->dev->dev, "proc_create failed\n");
-			return;
-		}
-
-		ppde = (void *)adapter + f->ptr_offset;
-		*ppde = de;
-	}
+	proc_create_single_data("config", S_IRUSR, dir,
+			proc_show_config, adapter);
+	proc_create_single_data("stat", S_IRUSR, dir,
+			proc_show_stat, adapter);
+	proc_create_single_data("mailbox", S_IRUSR, dir,
+			proc_show_mbox, adapter);
+#if MEGA_HAVE_ENH_PROC
+	proc_create_single_data("rebuild-rate", S_IRUSR, dir,
+			proc_show_rebuild_rate, adapter);
+	proc_create_single_data("battery-status", S_IRUSR, dir,
+			proc_show_battery, adapter);
+	proc_create_single_data("diskdrives-ch0", S_IRUSR, dir,
+			proc_show_pdrv_ch0, adapter);
+	proc_create_single_data("diskdrives-ch1", S_IRUSR, dir,
+			proc_show_pdrv_ch1, adapter);
+	proc_create_single_data("diskdrives-ch2", S_IRUSR, dir,
+			proc_show_pdrv_ch2, adapter);
+	proc_create_single_data("diskdrives-ch3", S_IRUSR, dir,
+			proc_show_pdrv_ch3, adapter);
+	proc_create_single_data("raiddrives-0-9", S_IRUSR, dir,
+			proc_show_rdrv_10, adapter);
+	proc_create_single_data("raiddrives-10-19", S_IRUSR, dir,
+			proc_show_rdrv_20, adapter);
+	proc_create_single_data("raiddrives-20-29", S_IRUSR, dir,
+			proc_show_rdrv_30, adapter);
+	proc_create_single_data("raiddrives-30-39", S_IRUSR, dir,
+			proc_show_rdrv_40, adapter);
+#endif
 }
 
 #else
@@ -4580,6 +4547,7 @@ megaraid_remove_one(struct pci_dev *pdev)
 {
 	struct Scsi_Host *host = pci_get_drvdata(pdev);
 	adapter_t *adapter = (adapter_t *)host->hostdata;
+	char buf[12] = { 0 };
 
 	scsi_remove_host(host);
 
@@ -4594,44 +4562,8 @@ megaraid_remove_one(struct pci_dev *pdev)
 
 	mega_free_sgl(adapter);
 
-#ifdef CONFIG_PROC_FS
-	if (adapter->controller_proc_dir_entry) {
-		remove_proc_entry("stat", adapter->controller_proc_dir_entry);
-		remove_proc_entry("config",
-				adapter->controller_proc_dir_entry);
-		remove_proc_entry("mailbox",
-				adapter->controller_proc_dir_entry);
-#if MEGA_HAVE_ENH_PROC
-		remove_proc_entry("rebuild-rate",
-				adapter->controller_proc_dir_entry);
-		remove_proc_entry("battery-status",
-				adapter->controller_proc_dir_entry);
-
-		remove_proc_entry("diskdrives-ch0",
-				adapter->controller_proc_dir_entry);
-		remove_proc_entry("diskdrives-ch1",
-				adapter->controller_proc_dir_entry);
-		remove_proc_entry("diskdrives-ch2",
-				adapter->controller_proc_dir_entry);
-		remove_proc_entry("diskdrives-ch3",
-				adapter->controller_proc_dir_entry);
-
-		remove_proc_entry("raiddrives-0-9",
-				adapter->controller_proc_dir_entry);
-		remove_proc_entry("raiddrives-10-19",
-				adapter->controller_proc_dir_entry);
-		remove_proc_entry("raiddrives-20-29",
-				adapter->controller_proc_dir_entry);
-		remove_proc_entry("raiddrives-30-39",
-				adapter->controller_proc_dir_entry);
-#endif
-		{
-			char	buf[12] = { 0 };
-			sprintf(buf, "hba%d", adapter->host->host_no);
-			remove_proc_entry(buf, mega_proc_dir_entry);
-		}
-	}
-#endif
+	sprintf(buf, "hba%d", adapter->host->host_no);
+	remove_proc_subtree(buf, mega_proc_dir_entry);
 
 	pci_free_consistent(adapter->dev, MEGA_BUFFER_SIZE,
 			adapter->mega_buffer, adapter->buf_dma_handle);
diff --git a/drivers/scsi/megaraid.h b/drivers/scsi/megaraid.h
index 21eba2fd465a..18e85d9267ff 100644
--- a/drivers/scsi/megaraid.h
+++ b/drivers/scsi/megaraid.h
@@ -814,18 +814,6 @@ typedef struct {
 
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*controller_proc_dir_entry;
-	struct proc_dir_entry	*proc_read;
-	struct proc_dir_entry	*proc_stat;
-	struct proc_dir_entry	*proc_mbox;
-
-#if MEGA_HAVE_ENH_PROC
-	struct proc_dir_entry	*proc_rr;
-	struct proc_dir_entry	*proc_battery;
-#define MAX_PROC_CHANNELS	4
-	struct proc_dir_entry	*proc_pdrvstat[MAX_PROC_CHANNELS];
-	struct proc_dir_entry	*proc_rdrvstat[MAX_PROC_CHANNELS];
-#endif
-
 #endif
 
 	int	has_64bit_addr;		/* are we using 64-bit addressing */
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index b89c6e6c0589..ce656c466ca9 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2772,7 +2772,7 @@ blk_eh_timer_return megasas_reset_timer(struct scsi_cmnd *scmd)
 
 	if (time_after(jiffies, scmd->jiffies_at_alloc +
 				(scmd_timeout * 2) * HZ)) {
-		return BLK_EH_NOT_HANDLED;
+		return BLK_EH_DONE;
 	}
 
 	instance = (struct megasas_instance *)scmd->device->host->hostdata;
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index ce97cde3b41c..f4d988dd1e9d 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -1124,12 +1124,12 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		goto fail_fw_init;
 	}
 
-	ret = 0;
+	return 0;
 
 fail_fw_init:
 	dev_err(&instance->pdev->dev,
-		"Init cmd return status %s for SCSI host %d\n",
-		ret ? "FAILED" : "SUCCESS", instance->host->host_no);
+		"Init cmd return status FAILED for SCSI host %d\n",
+		instance->host->host_no);
 
 	return ret;
 }
diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c
index fe97401ad192..afd27165cd93 100644
--- a/drivers/scsi/mvumi.c
+++ b/drivers/scsi/mvumi.c
@@ -2155,7 +2155,7 @@ static enum blk_eh_timer_return mvumi_timed_out(struct scsi_cmnd *scmd)
 	mvumi_return_cmd(mhba, cmd);
 	spin_unlock_irqrestore(mhba->shost->host_lock, flags);
 
-	return BLK_EH_NOT_HANDLED;
+	return BLK_EH_DONE;
 }
 
 static int
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index e18877177f1b..5a33e1ad9881 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -99,7 +99,7 @@ static int _osd_get_print_system_info(struct osd_dev *od,
 	int nelem = ARRAY_SIZE(get_attrs), a = 0;
 	int ret;
 
-	or = osd_start_request(od, GFP_KERNEL);
+	or = osd_start_request(od);
 	if (!or)
 		return -ENOMEM;
 
@@ -409,16 +409,15 @@ static void _osd_request_free(struct osd_request *or)
 	kfree(or);
 }
 
-struct osd_request *osd_start_request(struct osd_dev *dev, gfp_t gfp)
+struct osd_request *osd_start_request(struct osd_dev *dev)
 {
 	struct osd_request *or;
 
-	or = _osd_request_alloc(gfp);
+	or = _osd_request_alloc(GFP_KERNEL);
 	if (!or)
 		return NULL;
 
 	or->osd_dev = dev;
-	or->alloc_flags = gfp;
 	or->timeout = dev->def_timeout;
 	or->retries = OSD_REQ_RETRIES;
 
@@ -546,7 +545,7 @@ static int _osd_realloc_seg(struct osd_request *or,
 	if (seg->alloc_size >= max_bytes)
 		return 0;
 
-	buff = krealloc(seg->buff, max_bytes, or->alloc_flags);
+	buff = krealloc(seg->buff, max_bytes, GFP_KERNEL);
 	if (!buff) {
 		OSD_ERR("Failed to Realloc %d-bytes was-%d\n", max_bytes,
 			seg->alloc_size);
@@ -728,7 +727,7 @@ static int _osd_req_list_objects(struct osd_request *or,
 		_osd_req_encode_olist(or, list);
 
 	WARN_ON(or->in.bio);
-	bio = bio_map_kern(q, list, len, or->alloc_flags);
+	bio = bio_map_kern(q, list, len, GFP_KERNEL);
 	if (IS_ERR(bio)) {
 		OSD_ERR("!!! Failed to allocate list_objects BIO\n");
 		return PTR_ERR(bio);
@@ -1190,14 +1189,14 @@ static int _req_append_segment(struct osd_request *or,
 			pad_buff = io->pad_buff;
 
 		ret = blk_rq_map_kern(io->req->q, io->req, pad_buff, padding,
-				       or->alloc_flags);
+				       GFP_KERNEL);
 		if (ret)
 			return ret;
 		io->total_bytes += padding;
 	}
 
 	ret = blk_rq_map_kern(io->req->q, io->req, seg->buff, seg->total_bytes,
-			       or->alloc_flags);
+			       GFP_KERNEL);
 	if (ret)
 		return ret;
 
@@ -1564,14 +1563,14 @@ static int _osd_req_finalize_data_integrity(struct osd_request *or,
  * osd_finalize_request and helpers
  */
 static struct request *_make_request(struct request_queue *q, bool has_write,
-			      struct _osd_io_info *oii, gfp_t flags)
+			      struct _osd_io_info *oii)
 {
 	struct request *req;
 	struct bio *bio = oii->bio;
 	int ret;
 
 	req = blk_get_request(q, has_write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
-			flags);
+			0);
 	if (IS_ERR(req))
 		return req;
 
@@ -1589,13 +1588,12 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
 static int _init_blk_request(struct osd_request *or,
 	bool has_in, bool has_out)
 {
-	gfp_t flags = or->alloc_flags;
 	struct scsi_device *scsi_device = or->osd_dev->scsi_device;
 	struct request_queue *q = scsi_device->request_queue;
 	struct request *req;
 	int ret;
 
-	req = _make_request(q, has_out, has_out ? &or->out : &or->in, flags);
+	req = _make_request(q, has_out, has_out ? &or->out : &or->in);
 	if (IS_ERR(req)) {
 		ret = PTR_ERR(req);
 		goto out;
@@ -1611,7 +1609,7 @@ static int _init_blk_request(struct osd_request *or,
 		or->out.req = req;
 		if (has_in) {
 			/* allocate bidi request */
-			req = _make_request(q, false, &or->in, flags);
+			req = _make_request(q, false, &or->in);
 			if (IS_ERR(req)) {
 				OSD_DEBUG("blk_get_request for bidi failed\n");
 				ret = PTR_ERR(req);
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 20ec1c01dbd5..2bbe797f8c3d 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -368,7 +368,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
 	int write = (data_direction == DMA_TO_DEVICE);
 
 	req = blk_get_request(SRpnt->stp->device->request_queue,
-			write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
+			write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(req))
 		return DRIVER_ERROR << 24;
 
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 94c14ce94da2..0e13349dce57 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -1848,7 +1848,7 @@ static enum blk_eh_timer_return qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc)
 	struct iscsi_cls_session *session;
 	struct iscsi_session *sess;
 	unsigned long flags;
-	enum blk_eh_timer_return ret = BLK_EH_NOT_HANDLED;
+	enum blk_eh_timer_return ret = BLK_EH_DONE;
 
 	session = starget_to_session(scsi_target(sc->device));
 	sess = session->dd_data;
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 9ef5e3b810f6..656c98e116a9 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -234,11 +234,13 @@ static const char *sdebug_version_date = "20180128";
 #define F_INV_OP		0x200
 #define F_FAKE_RW		0x400
 #define F_M_ACCESS		0x800	/* media access */
-#define F_LONG_DELAY		0x1000
+#define F_SSU_DELAY		0x1000
+#define F_SYNC_DELAY		0x2000
 
 #define FF_RESPOND (F_RL_WLUN_OK | F_SKIP_UA | F_DELAY_OVERR)
 #define FF_MEDIA_IO (F_M_ACCESS | F_FAKE_RW)
 #define FF_SA (F_SA_HIGH | F_SA_LOW)
+#define F_LONG_DELAY		(F_SSU_DELAY | F_SYNC_DELAY)
 
 #define SDEBUG_MAX_PARTS 4
 
@@ -510,7 +512,7 @@ static const struct opcode_info_t release_iarr[] = {
 };
 
 static const struct opcode_info_t sync_cache_iarr[] = {
-	{0, 0x91, 0, F_LONG_DELAY | F_M_ACCESS, resp_sync_cache, NULL,
+	{0, 0x91, 0, F_SYNC_DELAY | F_M_ACCESS, resp_sync_cache, NULL,
 	    {16,  0x6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
 	     0xff, 0xff, 0xff, 0xff, 0x3f, 0xc7} },	/* SYNC_CACHE (16) */
 };
@@ -553,7 +555,7 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = {
 	    resp_write_dt0, write_iarr,			/* WRITE(16) */
 		{16,  0xfa, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
 		 0xff, 0xff, 0xff, 0xff, 0xff, 0xc7} },
-	{0, 0x1b, 0, F_LONG_DELAY, resp_start_stop, NULL,/* START STOP UNIT */
+	{0, 0x1b, 0, F_SSU_DELAY, resp_start_stop, NULL,/* START STOP UNIT */
 	    {6,  0x1, 0, 0xf, 0xf7, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
 	{ARRAY_SIZE(sa_in_16_iarr), 0x9e, 0x10, F_SA_LOW | F_D_IN,
 	    resp_readcap16, sa_in_16_iarr, /* SA_IN(16), READ CAPACITY(16) */
@@ -606,7 +608,7 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = {
 	    resp_write_same_10, write_same_iarr,	/* WRITE SAME(10) */
 		{10,  0xff, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, 0,
 		 0, 0, 0, 0, 0} },
-	{ARRAY_SIZE(sync_cache_iarr), 0x35, 0, F_LONG_DELAY | F_M_ACCESS,
+	{ARRAY_SIZE(sync_cache_iarr), 0x35, 0, F_SYNC_DELAY | F_M_ACCESS,
 	    resp_sync_cache, sync_cache_iarr,
 	    {10,  0x7, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, 0, 0,
 	     0, 0, 0, 0} },			/* SYNC_CACHE (10) */
@@ -667,6 +669,7 @@ static bool sdebug_strict = DEF_STRICT;
 static bool sdebug_any_injecting_opt;
 static bool sdebug_verbose;
 static bool have_dif_prot;
+static bool write_since_sync;
 static bool sdebug_statistics = DEF_STATISTICS;
 
 static unsigned int sdebug_store_sectors;
@@ -1607,6 +1610,7 @@ static int resp_start_stop(struct scsi_cmnd *scp,
 {
 	unsigned char *cmd = scp->cmnd;
 	int power_cond, stop;
+	bool changing;
 
 	power_cond = (cmd[4] & 0xf0) >> 4;
 	if (power_cond) {
@@ -1614,8 +1618,12 @@ static int resp_start_stop(struct scsi_cmnd *scp,
 		return check_condition_result;
 	}
 	stop = !(cmd[4] & 1);
+	changing = atomic_read(&devip->stopped) == !stop;
 	atomic_xchg(&devip->stopped, stop);
-	return (cmd[1] & 0x1) ? SDEG_RES_IMMED_MASK : 0; /* check IMMED bit */
+	if (!changing || cmd[1] & 0x1)  /* state unchanged or IMMED set */
+		return SDEG_RES_IMMED_MASK;
+	else
+		return 0;
 }
 
 static sector_t get_sdebug_capacity(void)
@@ -2473,6 +2481,7 @@ static int do_device_access(struct scsi_cmnd *scmd, u32 sg_skip, u64 lba,
 	if (do_write) {
 		sdb = scsi_out(scmd);
 		dir = DMA_TO_DEVICE;
+		write_since_sync = true;
 	} else {
 		sdb = scsi_in(scmd);
 		dir = DMA_FROM_DEVICE;
@@ -3583,6 +3592,7 @@ static int resp_get_lba_status(struct scsi_cmnd *scp,
 static int resp_sync_cache(struct scsi_cmnd *scp,
 			   struct sdebug_dev_info *devip)
 {
+	int res = 0;
 	u64 lba;
 	u32 num_blocks;
 	u8 *cmd = scp->cmnd;
@@ -3598,7 +3608,11 @@ static int resp_sync_cache(struct scsi_cmnd *scp,
 		mk_sense_buffer(scp, ILLEGAL_REQUEST, LBA_OUT_OF_RANGE, 0);
 		return check_condition_result;
 	}
-	return (cmd[1] & 0x2) ? SDEG_RES_IMMED_MASK : 0; /* check IMMED bit */
+	if (!write_since_sync || cmd[1] & 0x2)
+		res = SDEG_RES_IMMED_MASK;
+	else		/* delay if write_since_sync and IMMED clear */
+		write_since_sync = false;
+	return res;
 }
 
 #define RL_BUCKET_ELEMS 8
@@ -5777,13 +5791,14 @@ fini:
 		return schedule_resp(scp, devip, errsts, pfp, 0, 0);
 	else if ((sdebug_jdelay || sdebug_ndelay) && (flags & F_LONG_DELAY)) {
 		/*
-		 * If any delay is active, want F_LONG_DELAY to be at least 1
+		 * If any delay is active, for F_SSU_DELAY want at least 1
 		 * second and if sdebug_jdelay>0 want a long delay of that
-		 * many seconds.
+		 * many seconds; for F_SYNC_DELAY want 1/20 of that.
 		 */
 		int jdelay = (sdebug_jdelay < 2) ? 1 : sdebug_jdelay;
+		int denom = (flags & F_SYNC_DELAY) ? 20 : 1;
 
-		jdelay = mult_frac(USER_HZ * jdelay, HZ, USER_HZ);
+		jdelay = mult_frac(USER_HZ * jdelay, HZ, denom * USER_HZ);
 		return schedule_resp(scp, devip, errsts, pfp, jdelay, 0);
 	} else
 		return schedule_resp(scp, devip, errsts, pfp, sdebug_jdelay,
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 946039117bf4..9c02ba2e7ef3 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -282,7 +282,7 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd)
 enum blk_eh_timer_return scsi_times_out(struct request *req)
 {
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
-	enum blk_eh_timer_return rtn = BLK_EH_NOT_HANDLED;
+	enum blk_eh_timer_return rtn = BLK_EH_DONE;
 	struct Scsi_Host *host = scmd->device->host;
 
 	trace_scsi_dispatch_cmd_timeout(scmd);
@@ -294,7 +294,7 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
 	if (host->hostt->eh_timed_out)
 		rtn = host->hostt->eh_timed_out(scmd);
 
-	if (rtn == BLK_EH_NOT_HANDLED) {
+	if (rtn == BLK_EH_DONE) {
 		if (scsi_abort_command(scmd) != SUCCESS) {
 			set_host_byte(scmd, DID_TIME_OUT);
 			scsi_eh_scmd_add(scmd);
@@ -1933,11 +1933,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 	struct request *req;
 	struct scsi_request *rq;
 
-	/*
-	 * blk_get_request with GFP_KERNEL (__GFP_RECLAIM) sleeps until a
-	 * request becomes available
-	 */
-	req = blk_get_request(sdev->request_queue, REQ_OP_SCSI_IN, GFP_KERNEL);
+	req = blk_get_request(sdev->request_queue, REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(req))
 		return;
 	rq = scsi_req(req);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index e9b4f279d29c..fb38aeff9dbd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -265,7 +265,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	struct scsi_request *rq;
 	int ret = DRIVER_ERROR << 24;
 
-	req = blk_get_request_flags(sdev->request_queue,
+	req = blk_get_request(sdev->request_queue,
 			data_direction == DMA_TO_DEVICE ?
 			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, BLK_MQ_REQ_PREEMPT);
 	if (IS_ERR(req))
@@ -273,7 +273,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	rq = scsi_req(req);
 
 	if (bufflen &&	blk_rq_map_kern(sdev->request_queue, req,
-					buffer, bufflen, __GFP_RECLAIM))
+					buffer, bufflen, GFP_NOIO))
 		goto out;
 
 	rq->cmd_len = COMMAND_SIZE(cmd[0]);
@@ -2149,27 +2149,6 @@ static int scsi_map_queues(struct blk_mq_tag_set *set)
 	return blk_mq_map_queues(set);
 }
 
-static u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost)
-{
-	struct device *host_dev;
-	u64 bounce_limit = 0xffffffff;
-
-	if (shost->unchecked_isa_dma)
-		return BLK_BOUNCE_ISA;
-	/*
-	 * Platforms with virtual-DMA translation
-	 * hardware have no practical limit.
-	 */
-	if (!PCI_DMA_BUS_IS_PHYS)
-		return BLK_BOUNCE_ANY;
-
-	host_dev = scsi_get_device(shost);
-	if (host_dev && host_dev->dma_mask)
-		bounce_limit = (u64)dma_max_pfn(host_dev) << PAGE_SHIFT;
-
-	return bounce_limit;
-}
-
 void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 {
 	struct device *dev = shost->dma_dev;
@@ -2189,7 +2168,8 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 	}
 
 	blk_queue_max_hw_sectors(q, shost->max_sectors);
-	blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost));
+	if (shost->unchecked_isa_dma)
+		blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
 	blk_queue_segment_boundary(q, shost->dma_boundary);
 	dma_set_seg_boundary(dev, shost->dma_boundary);
 
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index be3be0f9cb2d..1da3d71e9f61 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -2087,7 +2087,7 @@ fc_eh_timed_out(struct scsi_cmnd *scmd)
 	if (rport->port_state == FC_PORTSTATE_BLOCKED)
 		return BLK_EH_RESET_TIMER;
 
-	return BLK_EH_NOT_HANDLED;
+	return BLK_EH_DONE;
 }
 EXPORT_SYMBOL(fc_eh_timed_out);
 
@@ -3591,10 +3591,9 @@ fc_bsg_job_timeout(struct request *req)
 	}
 
 	/* the blk_end_sync_io() doesn't check the error */
-	if (!inflight)
-		return BLK_EH_NOT_HANDLED;
-	else
-		return BLK_EH_HANDLED;
+	if (inflight)
+		blk_mq_complete_request(req);
+	return BLK_EH_DONE;
 }
 
 /**
@@ -3781,8 +3780,7 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
 	snprintf(bsg_name, sizeof(bsg_name),
 		 "fc_host%d", shost->host_no);
 
-	q = bsg_setup_queue(dev, bsg_name, fc_bsg_dispatch, i->f->dd_bsg_size,
-			NULL);
+	q = bsg_setup_queue(dev, bsg_name, fc_bsg_dispatch, i->f->dd_bsg_size);
 	if (IS_ERR(q)) {
 		dev_err(dev,
 			"fc_host%d: bsg interface failed to initialize - setup queue\n",
@@ -3827,8 +3825,8 @@ fc_bsg_rportadd(struct Scsi_Host *shost, struct fc_rport *rport)
 	if (!i->f->bsg_request)
 		return -ENOTSUPP;
 
-	q = bsg_setup_queue(dev, NULL, fc_bsg_dispatch, i->f->dd_bsg_size,
-			NULL);
+	q = bsg_setup_queue(dev, dev_name(dev), fc_bsg_dispatch,
+			i->f->dd_bsg_size);
 	if (IS_ERR(q)) {
 		dev_err(dev, "failed to setup bsg queue\n");
 		return PTR_ERR(q);
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index f4b52b44b966..6fd2fe210fc3 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1542,7 +1542,7 @@ iscsi_bsg_host_add(struct Scsi_Host *shost, struct iscsi_cls_host *ihost)
 		return -ENOTSUPP;
 
 	snprintf(bsg_name, sizeof(bsg_name), "iscsi_host%d", shost->host_no);
-	q = bsg_setup_queue(dev, bsg_name, iscsi_bsg_host_dispatch, 0, NULL);
+	q = bsg_setup_queue(dev, bsg_name, iscsi_bsg_host_dispatch, 0);
 	if (IS_ERR(q)) {
 		shost_printk(KERN_ERR, shost, "bsg interface failed to "
 			     "initialize - no request queue\n");
@@ -2322,6 +2322,12 @@ iscsi_multicast_skb(struct sk_buff *skb, uint32_t group, gfp_t gfp)
 	return nlmsg_multicast(nls, skb, 0, group, gfp);
 }
 
+static int
+iscsi_unicast_skb(struct sk_buff *skb, u32 portid)
+{
+	return nlmsg_unicast(nls, skb, portid);
+}
+
 int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
 		   char *data, uint32_t data_size)
 {
@@ -2524,14 +2530,11 @@ void iscsi_ping_comp_event(uint32_t host_no, struct iscsi_transport *transport,
 EXPORT_SYMBOL_GPL(iscsi_ping_comp_event);
 
 static int
-iscsi_if_send_reply(uint32_t group, int seq, int type, int done, int multi,
-		    void *payload, int size)
+iscsi_if_send_reply(u32 portid, int type, void *payload, int size)
 {
 	struct sk_buff	*skb;
 	struct nlmsghdr	*nlh;
 	int len = nlmsg_total_size(size);
-	int flags = multi ? NLM_F_MULTI : 0;
-	int t = done ? NLMSG_DONE : type;
 
 	skb = alloc_skb(len, GFP_ATOMIC);
 	if (!skb) {
@@ -2539,10 +2542,9 @@ iscsi_if_send_reply(uint32_t group, int seq, int type, int done, int multi,
 		return -ENOMEM;
 	}
 
-	nlh = __nlmsg_put(skb, 0, 0, t, (len - sizeof(*nlh)), 0);
-	nlh->nlmsg_flags = flags;
+	nlh = __nlmsg_put(skb, 0, 0, type, (len - sizeof(*nlh)), 0);
 	memcpy(nlmsg_data(nlh), payload, size);
-	return iscsi_multicast_skb(skb, group, GFP_ATOMIC);
+	return iscsi_unicast_skb(skb, portid);
 }
 
 static int
@@ -3470,6 +3472,7 @@ static int
 iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
 {
 	int err = 0;
+	u32 portid;
 	struct iscsi_uevent *ev = nlmsg_data(nlh);
 	struct iscsi_transport *transport = NULL;
 	struct iscsi_internal *priv;
@@ -3490,10 +3493,12 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
 	if (!try_module_get(transport->owner))
 		return -EINVAL;
 
+	portid = NETLINK_CB(skb).portid;
+
 	switch (nlh->nlmsg_type) {
 	case ISCSI_UEVENT_CREATE_SESSION:
 		err = iscsi_if_create_session(priv, ep, ev,
-					      NETLINK_CB(skb).portid,
+					      portid,
 					      ev->u.c_session.initial_cmdsn,
 					      ev->u.c_session.cmds_max,
 					      ev->u.c_session.queue_depth);
@@ -3506,7 +3511,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
 		}
 
 		err = iscsi_if_create_session(priv, ep, ev,
-					NETLINK_CB(skb).portid,
+					portid,
 					ev->u.c_bound_session.initial_cmdsn,
 					ev->u.c_bound_session.cmds_max,
 					ev->u.c_bound_session.queue_depth);
@@ -3664,6 +3669,8 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
 static void
 iscsi_if_rx(struct sk_buff *skb)
 {
+	u32 portid = NETLINK_CB(skb).portid;
+
 	mutex_lock(&rx_queue_mutex);
 	while (skb->len >= NLMSG_HDRLEN) {
 		int err;
@@ -3699,8 +3706,8 @@ iscsi_if_rx(struct sk_buff *skb)
 				break;
 			if (ev->type == ISCSI_UEVENT_GET_CHAP && !err)
 				break;
-			err = iscsi_if_send_reply(group, nlh->nlmsg_seq,
-				nlh->nlmsg_type, 0, 0, ev, sizeof(*ev));
+			err = iscsi_if_send_reply(portid, nlh->nlmsg_type,
+						  ev, sizeof(*ev));
 		} while (err < 0 && err != -ECONNREFUSED && err != -ESRCH);
 		skb_pull(skb, rlen);
 	}
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 08acbabfae07..e2953b416746 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -187,16 +187,6 @@ static int sas_smp_dispatch(struct bsg_job *job)
 	return 0;
 }
 
-static void sas_host_release(struct device *dev)
-{
-	struct Scsi_Host *shost = dev_to_shost(dev);
-	struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
-	struct request_queue *q = sas_host->q;
-
-	if (q)
-		blk_cleanup_queue(q);
-}
-
 static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 {
 	struct request_queue *q;
@@ -208,7 +198,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 
 	if (rphy) {
 		q = bsg_setup_queue(&rphy->dev, dev_name(&rphy->dev),
-				sas_smp_dispatch, 0, NULL);
+				sas_smp_dispatch, 0);
 		if (IS_ERR(q))
 			return PTR_ERR(q);
 		rphy->q = q;
@@ -217,7 +207,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 
 		snprintf(name, sizeof(name), "sas_host%d", shost->host_no);
 		q = bsg_setup_queue(&shost->shost_gendev, name,
-				sas_smp_dispatch, 0, sas_host_release);
+				sas_smp_dispatch, 0);
 		if (IS_ERR(q))
 			return PTR_ERR(q);
 		to_sas_host_attrs(shost)->q = q;
@@ -260,8 +250,11 @@ static int sas_host_remove(struct transport_container *tc, struct device *dev,
 	struct Scsi_Host *shost = dev_to_shost(dev);
 	struct request_queue *q = to_sas_host_attrs(shost)->q;
 
-	if (q)
+	if (q) {
 		bsg_unregister_queue(q);
+		blk_cleanup_queue(q);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index 36f6190931bc..4e46fdb2d7c9 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -51,6 +51,8 @@ struct srp_internal {
 	struct transport_container rport_attr_cont;
 };
 
+static int scsi_is_srp_rport(const struct device *dev);
+
 #define to_srp_internal(tmpl) container_of(tmpl, struct srp_internal, t)
 
 #define	dev_to_rport(d)	container_of(d, struct srp_rport, dev)
@@ -60,9 +62,24 @@ static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r)
 	return dev_to_shost(r->dev.parent);
 }
 
+static int find_child_rport(struct device *dev, void *data)
+{
+	struct device **child = data;
+
+	if (scsi_is_srp_rport(dev)) {
+		WARN_ON_ONCE(*child);
+		*child = dev;
+	}
+	return 0;
+}
+
 static inline struct srp_rport *shost_to_rport(struct Scsi_Host *shost)
 {
-	return transport_class_to_srp_rport(&shost->shost_gendev);
+	struct device *child = NULL;
+
+	WARN_ON_ONCE(device_for_each_child(&shost->shost_gendev, &child,
+					   find_child_rport) < 0);
+	return child ? dev_to_rport(child) : NULL;
 }
 
 /**
@@ -587,7 +604,7 @@ EXPORT_SYMBOL(srp_reconnect_rport);
  *
  * If a timeout occurs while an rport is in the blocked state, ask the SCSI
  * EH to continue waiting (BLK_EH_RESET_TIMER). Otherwise let the SCSI core
- * handle the timeout (BLK_EH_NOT_HANDLED).
+ * handle the timeout (BLK_EH_DONE).
  *
  * Note: This function is called from soft-IRQ context and with the request
  * queue lock held.
@@ -600,9 +617,10 @@ enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
 	struct srp_rport *rport = shost_to_rport(shost);
 
 	pr_debug("timeout for sdev %s\n", dev_name(&sdev->sdev_gendev));
-	return rport->fast_io_fail_tmo < 0 && rport->dev_loss_tmo < 0 &&
+	return rport && rport->fast_io_fail_tmo < 0 &&
+		rport->dev_loss_tmo < 0 &&
 		i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ?
-		BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED;
+		BLK_EH_RESET_TIMER : BLK_EH_DONE;
 }
 EXPORT_SYMBOL(srp_timed_out);
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index a6201e696ab9..9421d9877730 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2121,6 +2121,8 @@ sd_spinup_disk(struct scsi_disk *sdkp)
 				break;	/* standby */
 			if (sshdr.asc == 4 && sshdr.ascq == 0xc)
 				break;	/* unavailable */
+			if (sshdr.asc == 4 && sshdr.ascq == 0x1b)
+				break;	/* sanitize in progress */
 			/*
 			 * Issue command to spin up drive when not ready
 			 */
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 41df75eea57b..210407cd2341 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -400,8 +400,10 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
  *
  * Check that all zones of the device are equal. The last zone can however
  * be smaller. The zone size must also be a power of two number of LBAs.
+ *
+ * Returns the zone size in bytes upon success or an error code upon failure.
  */
-static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
+static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 {
 	u64 zone_blocks = 0;
 	sector_t block = 0;
@@ -412,8 +414,6 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 	int ret;
 	u8 same;
 
-	sdkp->zone_blocks = 0;
-
 	/* Get a buffer */
 	buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
 	if (!buf)
@@ -445,16 +445,17 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 
 		/* Parse zone descriptors */
 		while (rec < buf + buf_len) {
-			zone_blocks = get_unaligned_be64(&rec[8]);
-			if (sdkp->zone_blocks == 0) {
-				sdkp->zone_blocks = zone_blocks;
-			} else if (zone_blocks != sdkp->zone_blocks &&
-				   (block + zone_blocks < sdkp->capacity
-				    || zone_blocks > sdkp->zone_blocks)) {
-				zone_blocks = 0;
+			u64 this_zone_blocks = get_unaligned_be64(&rec[8]);
+
+			if (zone_blocks == 0) {
+				zone_blocks = this_zone_blocks;
+			} else if (this_zone_blocks != zone_blocks &&
+				   (block + this_zone_blocks < sdkp->capacity
+				    || this_zone_blocks > zone_blocks)) {
+				this_zone_blocks = 0;
 				goto out;
 			}
-			block += zone_blocks;
+			block += this_zone_blocks;
 			rec += 64;
 		}
 
@@ -467,8 +468,6 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 
 	} while (block < sdkp->capacity);
 
-	zone_blocks = sdkp->zone_blocks;
-
 out:
 	if (!zone_blocks) {
 		if (sdkp->first_scan)
@@ -488,8 +487,7 @@ out:
 				  "Zone size too large\n");
 		ret = -ENODEV;
 	} else {
-		sdkp->zone_blocks = zone_blocks;
-		sdkp->zone_shift = ilog2(zone_blocks);
+		ret = zone_blocks;
 	}
 
 out_free:
@@ -500,15 +498,14 @@ out_free:
 
 /**
  * sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone).
- * @sdkp: The disk of the bitmap
+ * @nr_zones: Number of zones to allocate space for.
+ * @numa_node: NUMA node to allocate the memory from.
  */
-static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
+static inline unsigned long *
+sd_zbc_alloc_zone_bitmap(u32 nr_zones, int numa_node)
 {
-	struct request_queue *q = sdkp->disk->queue;
-
-	return kzalloc_node(BITS_TO_LONGS(sdkp->nr_zones)
-			    * sizeof(unsigned long),
-			    GFP_KERNEL, q->node);
+	return kzalloc_node(BITS_TO_LONGS(nr_zones) * sizeof(unsigned long),
+			    GFP_KERNEL, numa_node);
 }
 
 /**
@@ -516,6 +513,7 @@ static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
  * @sdkp: disk used
  * @buf: report reply buffer
  * @buflen: length of @buf
+ * @zone_shift: logarithm base 2 of the number of blocks in a zone
  * @seq_zones_bitmap: bitmap of sequential zones to set
  *
  * Parse reported zone descriptors in @buf to identify sequential zones and
@@ -525,7 +523,7 @@ static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
  * Return the LBA after the last zone reported.
  */
 static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
-				     unsigned int buflen,
+				     unsigned int buflen, u32 zone_shift,
 				     unsigned long *seq_zones_bitmap)
 {
 	sector_t lba, next_lba = sdkp->capacity;
@@ -544,7 +542,7 @@ static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
 		if (type != ZBC_ZONE_TYPE_CONV &&
 		    cond != ZBC_ZONE_COND_READONLY &&
 		    cond != ZBC_ZONE_COND_OFFLINE)
-			set_bit(lba >> sdkp->zone_shift, seq_zones_bitmap);
+			set_bit(lba >> zone_shift, seq_zones_bitmap);
 		next_lba = lba + get_unaligned_be64(&rec[8]);
 		rec += 64;
 	}
@@ -553,12 +551,16 @@ static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
 }
 
 /**
- * sd_zbc_setup_seq_zones_bitmap - Initialize the disk seq zone bitmap.
+ * sd_zbc_setup_seq_zones_bitmap - Initialize a seq zone bitmap.
  * @sdkp: target disk
+ * @zone_shift: logarithm base 2 of the number of blocks in a zone
+ * @nr_zones: number of zones to set up a seq zone bitmap for
  *
  * Allocate a zone bitmap and initialize it by identifying sequential zones.
  */
-static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
+static unsigned long *
+sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift,
+			      u32 nr_zones)
 {
 	struct request_queue *q = sdkp->disk->queue;
 	unsigned long *seq_zones_bitmap;
@@ -566,9 +568,9 @@ static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
 	unsigned char *buf;
 	int ret = -ENOMEM;
 
-	seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(sdkp);
+	seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(nr_zones, q->node);
 	if (!seq_zones_bitmap)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
 	if (!buf)
@@ -579,7 +581,7 @@ static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
 		if (ret)
 			goto out;
 		lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
-					   seq_zones_bitmap);
+					   zone_shift, seq_zones_bitmap);
 	}
 
 	if (lba != sdkp->capacity) {
@@ -591,12 +593,9 @@ out:
 	kfree(buf);
 	if (ret) {
 		kfree(seq_zones_bitmap);
-		return ret;
+		return ERR_PTR(ret);
 	}
-
-	q->seq_zones_bitmap = seq_zones_bitmap;
-
-	return 0;
+	return seq_zones_bitmap;
 }
 
 static void sd_zbc_cleanup(struct scsi_disk *sdkp)
@@ -612,44 +611,64 @@ static void sd_zbc_cleanup(struct scsi_disk *sdkp)
 	q->nr_zones = 0;
 }
 
-static int sd_zbc_setup(struct scsi_disk *sdkp)
+static int sd_zbc_setup(struct scsi_disk *sdkp, u32 zone_blocks)
 {
 	struct request_queue *q = sdkp->disk->queue;
+	u32 zone_shift = ilog2(zone_blocks);
+	u32 nr_zones;
 	int ret;
 
-	/* READ16/WRITE16 is mandatory for ZBC disks */
-	sdkp->device->use_16_for_rw = 1;
-	sdkp->device->use_10_for_rw = 0;
-
 	/* chunk_sectors indicates the zone size */
-	blk_queue_chunk_sectors(sdkp->disk->queue,
-			logical_to_sectors(sdkp->device, sdkp->zone_blocks));
-	sdkp->nr_zones =
-		round_up(sdkp->capacity, sdkp->zone_blocks) >> sdkp->zone_shift;
+	blk_queue_chunk_sectors(q,
+			logical_to_sectors(sdkp->device, zone_blocks));
+	nr_zones = round_up(sdkp->capacity, zone_blocks) >> zone_shift;
 
 	/*
 	 * Initialize the device request queue information if the number
 	 * of zones changed.
 	 */
-	if (sdkp->nr_zones != q->nr_zones) {
-
-		sd_zbc_cleanup(sdkp);
-
-		q->nr_zones = sdkp->nr_zones;
-		if (sdkp->nr_zones) {
-			q->seq_zones_wlock = sd_zbc_alloc_zone_bitmap(sdkp);
-			if (!q->seq_zones_wlock) {
+	if (nr_zones != sdkp->nr_zones || nr_zones != q->nr_zones) {
+		unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
+		size_t zone_bitmap_size;
+
+		if (nr_zones) {
+			seq_zones_wlock = sd_zbc_alloc_zone_bitmap(nr_zones,
+								   q->node);
+			if (!seq_zones_wlock) {
 				ret = -ENOMEM;
 				goto err;
 			}
 
-			ret = sd_zbc_setup_seq_zones_bitmap(sdkp);
-			if (ret) {
-				sd_zbc_cleanup(sdkp);
+			seq_zones_bitmap = sd_zbc_setup_seq_zones_bitmap(sdkp,
+							zone_shift, nr_zones);
+			if (IS_ERR(seq_zones_bitmap)) {
+				ret = PTR_ERR(seq_zones_bitmap);
+				kfree(seq_zones_wlock);
 				goto err;
 			}
 		}
-
+		zone_bitmap_size = BITS_TO_LONGS(nr_zones) *
+			sizeof(unsigned long);
+		blk_mq_freeze_queue(q);
+		if (q->nr_zones != nr_zones) {
+			/* READ16/WRITE16 is mandatory for ZBC disks */
+			sdkp->device->use_16_for_rw = 1;
+			sdkp->device->use_10_for_rw = 0;
+
+			sdkp->zone_blocks = zone_blocks;
+			sdkp->zone_shift = zone_shift;
+			sdkp->nr_zones = nr_zones;
+			q->nr_zones = nr_zones;
+			swap(q->seq_zones_wlock, seq_zones_wlock);
+			swap(q->seq_zones_bitmap, seq_zones_bitmap);
+		} else if (memcmp(q->seq_zones_bitmap, seq_zones_bitmap,
+				  zone_bitmap_size) != 0) {
+			memcpy(q->seq_zones_bitmap, seq_zones_bitmap,
+			       zone_bitmap_size);
+		}
+		blk_mq_unfreeze_queue(q);
+		kfree(seq_zones_wlock);
+		kfree(seq_zones_bitmap);
 	}
 
 	return 0;
@@ -661,6 +680,7 @@ err:
 
 int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 {
+	int64_t zone_blocks;
 	int ret;
 
 	if (!sd_is_zoned(sdkp))
@@ -697,12 +717,16 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	 * Check zone size: only devices with a constant zone size (except
 	 * an eventual last runt zone) that is a power of 2 are supported.
 	 */
-	ret = sd_zbc_check_zone_size(sdkp);
-	if (ret)
+	zone_blocks = sd_zbc_check_zone_size(sdkp);
+	ret = -EFBIG;
+	if (zone_blocks != (u32)zone_blocks)
+		goto err;
+	ret = zone_blocks;
+	if (ret < 0)
 		goto err;
 
 	/* The drive satisfies the kernel restrictions: set it up */
-	ret = sd_zbc_setup(sdkp);
+	ret = sd_zbc_setup(sdkp, zone_blocks);
 	if (ret)
 		goto err;
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index c198b96368dd..6fc58e2c99d3 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -66,7 +66,6 @@ static int sg_version_num = 30536;	/* 2 digits for each component */
 static char *sg_version_date = "20140603";
 
 static int sg_proc_init(void);
-static void sg_proc_cleanup(void);
 #endif
 
 #define SG_ALLOW_DIO_DEF 0
@@ -1661,7 +1660,7 @@ static void __exit
 exit_sg(void)
 {
 #ifdef CONFIG_SCSI_PROC_FS
-	sg_proc_cleanup();
+	remove_proc_subtree("scsi/sg", NULL);
 #endif				/* CONFIG_SCSI_PROC_FS */
 	scsi_unregister_interface(&sg_interface);
 	class_destroy(sg_sysfs_class);
@@ -1715,7 +1714,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 	 * does not sleep except under memory pressure.
 	 */
 	rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ?
-			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(rq)) {
 		kfree(long_cmdp);
 		return PTR_ERR(rq);
@@ -1894,7 +1893,7 @@ retry:
 		num = (rem_sz > scatter_elem_sz_prev) ?
 			scatter_elem_sz_prev : rem_sz;
 
-		schp->pages[k] = alloc_pages(gfp_mask, order);
+		schp->pages[k] = alloc_pages(gfp_mask | __GFP_ZERO, order);
 		if (!schp->pages[k])
 			goto out;
 
@@ -2274,11 +2273,6 @@ sg_get_dev(int dev)
 }
 
 #ifdef CONFIG_SCSI_PROC_FS
-
-static struct proc_dir_entry *sg_proc_sgp = NULL;
-
-static char sg_proc_sg_dirname[] = "scsi/sg";
-
 static int sg_proc_seq_show_int(struct seq_file *s, void *v);
 
 static int sg_proc_single_open_adio(struct inode *inode, struct file *file);
@@ -2306,37 +2300,11 @@ static const struct file_operations dressz_fops = {
 };
 
 static int sg_proc_seq_show_version(struct seq_file *s, void *v);
-static int sg_proc_single_open_version(struct inode *inode, struct file *file);
-static const struct file_operations version_fops = {
-	.owner = THIS_MODULE,
-	.open = sg_proc_single_open_version,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v);
-static int sg_proc_single_open_devhdr(struct inode *inode, struct file *file);
-static const struct file_operations devhdr_fops = {
-	.owner = THIS_MODULE,
-	.open = sg_proc_single_open_devhdr,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 static int sg_proc_seq_show_dev(struct seq_file *s, void *v);
-static int sg_proc_open_dev(struct inode *inode, struct file *file);
 static void * dev_seq_start(struct seq_file *s, loff_t *pos);
 static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos);
 static void dev_seq_stop(struct seq_file *s, void *v);
-static const struct file_operations dev_fops = {
-	.owner = THIS_MODULE,
-	.open = sg_proc_open_dev,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
 static const struct seq_operations dev_seq_ops = {
 	.start = dev_seq_start,
 	.next  = dev_seq_next,
@@ -2345,14 +2313,6 @@ static const struct seq_operations dev_seq_ops = {
 };
 
 static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v);
-static int sg_proc_open_devstrs(struct inode *inode, struct file *file);
-static const struct file_operations devstrs_fops = {
-	.owner = THIS_MODULE,
-	.open = sg_proc_open_devstrs,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
 static const struct seq_operations devstrs_seq_ops = {
 	.start = dev_seq_start,
 	.next  = dev_seq_next,
@@ -2361,14 +2321,6 @@ static const struct seq_operations devstrs_seq_ops = {
 };
 
 static int sg_proc_seq_show_debug(struct seq_file *s, void *v);
-static int sg_proc_open_debug(struct inode *inode, struct file *file);
-static const struct file_operations debug_fops = {
-	.owner = THIS_MODULE,
-	.open = sg_proc_open_debug,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
 static const struct seq_operations debug_seq_ops = {
 	.start = dev_seq_start,
 	.next  = dev_seq_next,
@@ -2376,50 +2328,23 @@ static const struct seq_operations debug_seq_ops = {
 	.show  = sg_proc_seq_show_debug,
 };
 
-
-struct sg_proc_leaf {
-	const char * name;
-	const struct file_operations * fops;
-};
-
-static const struct sg_proc_leaf sg_proc_leaf_arr[] = {
-	{"allow_dio", &adio_fops},
-	{"debug", &debug_fops},
-	{"def_reserved_size", &dressz_fops},
-	{"device_hdr", &devhdr_fops},
-	{"devices", &dev_fops},
-	{"device_strs", &devstrs_fops},
-	{"version", &version_fops}
-};
-
 static int
 sg_proc_init(void)
 {
-	int num_leaves = ARRAY_SIZE(sg_proc_leaf_arr);
-	int k;
+	struct proc_dir_entry *p;
 
-	sg_proc_sgp = proc_mkdir(sg_proc_sg_dirname, NULL);
-	if (!sg_proc_sgp)
+	p = proc_mkdir("scsi/sg", NULL);
+	if (!p)
 		return 1;
-	for (k = 0; k < num_leaves; ++k) {
-		const struct sg_proc_leaf *leaf = &sg_proc_leaf_arr[k];
-		umode_t mask = leaf->fops->write ? S_IRUGO | S_IWUSR : S_IRUGO;
-		proc_create(leaf->name, mask, sg_proc_sgp, leaf->fops);
-	}
-	return 0;
-}
 
-static void
-sg_proc_cleanup(void)
-{
-	int k;
-	int num_leaves = ARRAY_SIZE(sg_proc_leaf_arr);
-
-	if (!sg_proc_sgp)
-		return;
-	for (k = 0; k < num_leaves; ++k)
-		remove_proc_entry(sg_proc_leaf_arr[k].name, sg_proc_sgp);
-	remove_proc_entry(sg_proc_sg_dirname, NULL);
+	proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_fops);
+	proc_create_seq("debug", S_IRUGO, p, &debug_seq_ops);
+	proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_fops);
+	proc_create_single("device_hdr", S_IRUGO, p, sg_proc_seq_show_devhdr);
+	proc_create_seq("devices", S_IRUGO, p, &dev_seq_ops);
+	proc_create_seq("device_strs", S_IRUGO, p, &devstrs_seq_ops);
+	proc_create_single("version", S_IRUGO, p, sg_proc_seq_show_version);
+	return 0;
 }
 
 
@@ -2482,22 +2407,12 @@ static int sg_proc_seq_show_version(struct seq_file *s, void *v)
 	return 0;
 }
 
-static int sg_proc_single_open_version(struct inode *inode, struct file *file)
-{
-	return single_open(file, sg_proc_seq_show_version, NULL);
-}
-
 static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v)
 {
 	seq_puts(s, "host\tchan\tid\tlun\ttype\topens\tqdepth\tbusy\tonline\n");
 	return 0;
 }
 
-static int sg_proc_single_open_devhdr(struct inode *inode, struct file *file)
-{
-	return single_open(file, sg_proc_seq_show_devhdr, NULL);
-}
-
 struct sg_proc_deviter {
 	loff_t	index;
 	size_t	max;
@@ -2531,11 +2446,6 @@ static void dev_seq_stop(struct seq_file *s, void *v)
 	kfree(s->private);
 }
 
-static int sg_proc_open_dev(struct inode *inode, struct file *file)
-{
-        return seq_open(file, &dev_seq_ops);
-}
-
 static int sg_proc_seq_show_dev(struct seq_file *s, void *v)
 {
 	struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
@@ -2562,11 +2472,6 @@ static int sg_proc_seq_show_dev(struct seq_file *s, void *v)
 	return 0;
 }
 
-static int sg_proc_open_devstrs(struct inode *inode, struct file *file)
-{
-        return seq_open(file, &devstrs_seq_ops);
-}
-
 static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v)
 {
 	struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
@@ -2650,11 +2555,6 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
 	}
 }
 
-static int sg_proc_open_debug(struct inode *inode, struct file *file)
-{
-        return seq_open(file, &debug_seq_ops);
-}
-
 static int sg_proc_seq_show_debug(struct seq_file *s, void *v)
 {
 	struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 2a21f2d48592..35fab1e18adc 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -188,9 +188,13 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	struct scsi_device *SDev;
 	struct scsi_sense_hdr sshdr;
 	int result, err = 0, retries = 0;
+	unsigned char sense_buffer[SCSI_SENSE_BUFFERSIZE], *senseptr = NULL;
 
 	SDev = cd->device;
 
+	if (cgc->sense)
+		senseptr = sense_buffer;
+
       retry:
 	if (!scsi_block_when_processing_errors(SDev)) {
 		err = -ENODEV;
@@ -198,10 +202,12 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	}
 
 	result = scsi_execute(SDev, cgc->cmd, cgc->data_direction,
-			      cgc->buffer, cgc->buflen,
-			      (unsigned char *)cgc->sense, &sshdr,
+			      cgc->buffer, cgc->buflen, senseptr, &sshdr,
 			      cgc->timeout, IOCTL_RETRIES, 0, 0, NULL);
 
+	if (cgc->sense)
+		memcpy(cgc->sense, sense_buffer, sizeof(*cgc->sense));
+
 	/* Minimal error checking.  Ignore cases we know about, and report the rest. */
 	if (driver_byte(result) != 0) {
 		switch (sshdr.sense_key) {
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 6c399480783d..a427ce9497be 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -545,7 +545,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 
 	req = blk_get_request(SRpnt->stp->device->request_queue,
 			data_direction == DMA_TO_DEVICE ?
-			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(req))
 		return DRIVER_ERROR << 24;
 	rq = scsi_req(req);
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 8c51d628b52e..a2ec0bc9e9fa 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1722,11 +1722,14 @@ static int storvsc_probe(struct hv_device *device,
 		max_targets = STORVSC_MAX_TARGETS;
 		max_channels = STORVSC_MAX_CHANNELS;
 		/*
-		 * On Windows8 and above, we support sub-channels for storage.
+		 * On Windows8 and above, we support sub-channels for storage
+		 * on SCSI and FC controllers.
 		 * The number of sub-channels offerred is based on the number of
 		 * VCPUs in the guest.
 		 */
-		max_sub_channels = (num_cpus / storvsc_vcpus_per_sub_channel);
+		if (!dev_is_ide)
+			max_sub_channels =
+				(num_cpus - 1) / storvsc_vcpus_per_sub_channel;
 	}
 
 	scsi_driver.can_queue = (max_outstanding_req_per_channel *
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index c5b1bf1cadcb..d0a1674915a1 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -276,6 +276,35 @@ static inline void ufshcd_remove_non_printable(char *val)
 		*val = ' ';
 }
 
+static void ufshcd_add_cmd_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+		const char *str)
+{
+	struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr;
+
+	trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->sc.cdb);
+}
+
+static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+		const char *str)
+{
+	struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr;
+
+	trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->qr);
+}
+
+static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+		const char *str)
+{
+	struct utp_task_req_desc *descp;
+	struct utp_upiu_task_req *task_req;
+	int off = (int)tag - hba->nutrs;
+
+	descp = &hba->utmrdl_base_addr[off];
+	task_req = (struct utp_upiu_task_req *)descp->task_req_upiu;
+	trace_ufshcd_upiu(dev_name(hba->dev), str, &task_req->header,
+			&task_req->input_param1);
+}
+
 static void ufshcd_add_command_trace(struct ufs_hba *hba,
 		unsigned int tag, const char *str)
 {
@@ -285,6 +314,9 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba,
 	struct ufshcd_lrb *lrbp;
 	int transfer_len = -1;
 
+	/* trace UPIU also */
+	ufshcd_add_cmd_upiu_trace(hba, tag, str);
+
 	if (!trace_ufshcd_command_enabled())
 		return;
 
@@ -2550,6 +2582,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 
 	hba->dev_cmd.complete = &wait;
 
+	ufshcd_add_query_upiu_trace(hba, tag, "query_send");
 	/* Make sure descriptors are ready before ringing the doorbell */
 	wmb();
 	spin_lock_irqsave(hba->host->host_lock, flags);
@@ -2559,6 +2592,9 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 
 	err = ufshcd_wait_for_dev_cmd(hba, lrbp, timeout);
 
+	ufshcd_add_query_upiu_trace(hba, tag,
+			err ? "query_complete_err" : "query_complete");
+
 out_put_tag:
 	ufshcd_put_dev_cmd_tag(hba, tag);
 	wake_up(&hba->dev_cmd.tag_wq);
@@ -5443,11 +5479,14 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
 
 	spin_unlock_irqrestore(host->host_lock, flags);
 
+	ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_send");
+
 	/* wait until the task management command is completed */
 	err = wait_event_timeout(hba->tm_wq,
 			test_bit(free_slot, &hba->tm_condition),
 			msecs_to_jiffies(TM_CMD_TIMEOUT));
 	if (!err) {
+		ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete_err");
 		dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
 				__func__, tm_function);
 		if (ufshcd_clear_tm_cmd(hba, free_slot))
@@ -5456,6 +5495,7 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
 		err = -ETIMEDOUT;
 	} else {
 		err = ufshcd_task_req_compl(hba, free_slot, tm_response);
+		ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete");
 	}
 
 	clear_bit(free_slot, &hba->tm_condition);
@@ -6457,12 +6497,12 @@ static enum blk_eh_timer_return ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
 	bool found = false;
 
 	if (!scmd || !scmd->device || !scmd->device->host)
-		return BLK_EH_NOT_HANDLED;
+		return BLK_EH_DONE;
 
 	host = scmd->device->host;
 	hba = shost_priv(host);
 	if (!hba)
-		return BLK_EH_NOT_HANDLED;
+		return BLK_EH_DONE;
 
 	spin_lock_irqsave(host->host_lock, flags);
 
@@ -6480,7 +6520,7 @@ static enum blk_eh_timer_return ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
 	 * SCSI command was not actually dispatched to UFS driver, otherwise
 	 * let SCSI layer handle the error as usual.
 	 */
-	return found ? BLK_EH_NOT_HANDLED : BLK_EH_RESET_TIMER;
+	return found ? BLK_EH_DONE : BLK_EH_RESET_TIMER;
 }
 
 static const struct attribute_group *ufshcd_driver_groups[] = {
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index c374e3b5c678..777e5f1e52d1 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -609,7 +609,7 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter,
 			break;
 
 		case BTSTAT_ABORTQUEUE:
-			cmd->result = (DID_ABORT << 16);
+			cmd->result = (DID_BUS_BUSY << 16);
 			break;
 
 		case BTSTAT_SCSIPARITY:
diff --git a/drivers/slimbus/messaging.c b/drivers/slimbus/messaging.c
index 884419c37e84..457ea1f8db30 100644
--- a/drivers/slimbus/messaging.c
+++ b/drivers/slimbus/messaging.c
@@ -183,7 +183,7 @@ static u16 slim_slicesize(int code)
 		0, 1, 2, 3, 3, 4, 4, 5, 5, 5, 5, 6, 6, 6, 6, 7
 	};
 
-	clamp(code, 1, (int)ARRAY_SIZE(sizetocode));
+	code = clamp(code, 1, (int)ARRAY_SIZE(sizetocode));
 
 	return sizetocode[code - 1];
 }
diff --git a/drivers/slimbus/qcom-ctrl.c b/drivers/slimbus/qcom-ctrl.c
index ffb46f915334..bb36a8fbc9b1 100644
--- a/drivers/slimbus/qcom-ctrl.c
+++ b/drivers/slimbus/qcom-ctrl.c
@@ -439,13 +439,12 @@ static int slim_get_current_rxbuf(struct qcom_slim_ctrl *ctrl, void *buf)
 static void qcom_slim_rxwq(struct work_struct *work)
 {
 	u8 buf[SLIM_MSGQ_BUF_LEN];
-	u8 mc, mt, len;
+	u8 mc, mt;
 	int ret;
 	struct qcom_slim_ctrl *ctrl = container_of(work, struct qcom_slim_ctrl,
 						 wd);
 
 	while ((slim_get_current_rxbuf(ctrl, buf)) != -ENODATA) {
-		len = SLIM_HEADER_GET_RL(buf[0]);
 		mt = SLIM_HEADER_GET_MT(buf[0]);
 		mc = SLIM_HEADER_GET_MC(buf[1]);
 		if (mt == SLIM_MSG_MT_CORE &&
diff --git a/drivers/soc/bcm/raspberrypi-power.c b/drivers/soc/bcm/raspberrypi-power.c
index fe96a8b956fb..f7ed1187518b 100644
--- a/drivers/soc/bcm/raspberrypi-power.c
+++ b/drivers/soc/bcm/raspberrypi-power.c
@@ -45,7 +45,7 @@ struct rpi_power_domains {
 struct rpi_power_domain_packet {
 	u32 domain;
 	u32 on;
-} __packet;
+};
 
 /*
  * Asks the firmware to enable or disable power on a specific power
diff --git a/drivers/soc/lantiq/gphy.c b/drivers/soc/lantiq/gphy.c
index 8d8659463b3e..feeb17cebc25 100644
--- a/drivers/soc/lantiq/gphy.c
+++ b/drivers/soc/lantiq/gphy.c
@@ -30,7 +30,6 @@ struct xway_gphy_priv {
 	struct clk *gphy_clk_gate;
 	struct reset_control *gphy_reset;
 	struct reset_control *gphy_reset2;
-	struct notifier_block gphy_reboot_nb;
 	void __iomem *membase;
 	char *fw_name;
 };
@@ -64,24 +63,6 @@ static const struct of_device_id xway_gphy_match[] = {
 };
 MODULE_DEVICE_TABLE(of, xway_gphy_match);
 
-static struct xway_gphy_priv *to_xway_gphy_priv(struct notifier_block *nb)
-{
-	return container_of(nb, struct xway_gphy_priv, gphy_reboot_nb);
-}
-
-static int xway_gphy_reboot_notify(struct notifier_block *reboot_nb,
-				   unsigned long code, void *unused)
-{
-	struct xway_gphy_priv *priv = to_xway_gphy_priv(reboot_nb);
-
-	if (priv) {
-		reset_control_assert(priv->gphy_reset);
-		reset_control_assert(priv->gphy_reset2);
-	}
-
-	return NOTIFY_DONE;
-}
-
 static int xway_gphy_load(struct device *dev, struct xway_gphy_priv *priv,
 			  dma_addr_t *dev_addr)
 {
@@ -205,14 +186,6 @@ static int xway_gphy_probe(struct platform_device *pdev)
 	reset_control_deassert(priv->gphy_reset);
 	reset_control_deassert(priv->gphy_reset2);
 
-	/* assert the gphy reset because it can hang after a reboot: */
-	priv->gphy_reboot_nb.notifier_call = xway_gphy_reboot_notify;
-	priv->gphy_reboot_nb.priority = -1;
-
-	ret = register_reboot_notifier(&priv->gphy_reboot_nb);
-	if (ret)
-		dev_warn(dev, "Failed to register reboot notifier\n");
-
 	platform_set_drvdata(pdev, priv);
 
 	return ret;
@@ -220,21 +193,12 @@ static int xway_gphy_probe(struct platform_device *pdev)
 
 static int xway_gphy_remove(struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
 	struct xway_gphy_priv *priv = platform_get_drvdata(pdev);
-	int ret;
-
-	reset_control_assert(priv->gphy_reset);
-	reset_control_assert(priv->gphy_reset2);
 
 	iowrite32be(0, priv->membase);
 
 	clk_disable_unprepare(priv->gphy_clk_gate);
 
-	ret = unregister_reboot_notifier(&priv->gphy_reboot_nb);
-	if (ret)
-		dev_warn(dev, "Failed to unregister reboot notifier\n");
-
 	return 0;
 }
 
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 5c4535b545cc..d053f2634c67 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -108,4 +108,13 @@ config QCOM_WCNSS_CTRL
 	  Client driver for the WCNSS_CTRL SMD channel, used to download nv
 	  firmware to a newly booted WCNSS chip.
 
+config QCOM_APR
+	tristate "Qualcomm APR Bus (Asynchronous Packet Router)"
+	depends on ARCH_QCOM
+	depends on RPMSG
+	help
+          Enable APR IPC protocol support between
+          application processor and QDSP6. APR is
+          used by audio driver to configure QDSP6
+          ASM, ADM and AFE modules.
 endmenu
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index dcebf2814e6d..39de5dee55d9 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
 obj-$(CONFIG_QCOM_SMP2P)	+= smp2p.o
 obj-$(CONFIG_QCOM_SMSM)	+= smsm.o
 obj-$(CONFIG_QCOM_WCNSS_CTRL) += wcnss_ctrl.o
+obj-$(CONFIG_QCOM_APR) += apr.o
diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c
new file mode 100644
index 000000000000..57af8a537332
--- /dev/null
+++ b/drivers/soc/qcom/apr.c
@@ -0,0 +1,378 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/of_device.h>
+#include <linux/soc/qcom/apr.h>
+#include <linux/rpmsg.h>
+#include <linux/of.h>
+
+struct apr {
+	struct rpmsg_endpoint *ch;
+	struct device *dev;
+	spinlock_t svcs_lock;
+	struct idr svcs_idr;
+	int dest_domain_id;
+};
+
+/**
+ * apr_send_pkt() - Send a apr message from apr device
+ *
+ * @adev: Pointer to previously registered apr device.
+ * @pkt: Pointer to apr packet to send
+ *
+ * Return: Will be an negative on packet size on success.
+ */
+int apr_send_pkt(struct apr_device *adev, struct apr_pkt *pkt)
+{
+	struct apr *apr = dev_get_drvdata(adev->dev.parent);
+	struct apr_hdr *hdr;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&adev->lock, flags);
+
+	hdr = &pkt->hdr;
+	hdr->src_domain = APR_DOMAIN_APPS;
+	hdr->src_svc = adev->svc_id;
+	hdr->dest_domain = adev->domain_id;
+	hdr->dest_svc = adev->svc_id;
+
+	ret = rpmsg_trysend(apr->ch, pkt, hdr->pkt_size);
+	spin_unlock_irqrestore(&adev->lock, flags);
+
+	return ret ? ret : hdr->pkt_size;
+}
+EXPORT_SYMBOL_GPL(apr_send_pkt);
+
+static void apr_dev_release(struct device *dev)
+{
+	struct apr_device *adev = to_apr_device(dev);
+
+	kfree(adev);
+}
+
+static int apr_callback(struct rpmsg_device *rpdev, void *buf,
+				  int len, void *priv, u32 addr)
+{
+	struct apr *apr = dev_get_drvdata(&rpdev->dev);
+	uint16_t hdr_size, msg_type, ver, svc_id;
+	struct apr_device *svc = NULL;
+	struct apr_driver *adrv = NULL;
+	struct apr_resp_pkt resp;
+	struct apr_hdr *hdr;
+	unsigned long flags;
+
+	if (len <= APR_HDR_SIZE) {
+		dev_err(apr->dev, "APR: Improper apr pkt received:%p %d\n",
+			buf, len);
+		return -EINVAL;
+	}
+
+	hdr = buf;
+	ver = APR_HDR_FIELD_VER(hdr->hdr_field);
+	if (ver > APR_PKT_VER + 1)
+		return -EINVAL;
+
+	hdr_size = APR_HDR_FIELD_SIZE_BYTES(hdr->hdr_field);
+	if (hdr_size < APR_HDR_SIZE) {
+		dev_err(apr->dev, "APR: Wrong hdr size:%d\n", hdr_size);
+		return -EINVAL;
+	}
+
+	if (hdr->pkt_size < APR_HDR_SIZE || hdr->pkt_size != len) {
+		dev_err(apr->dev, "APR: Wrong paket size\n");
+		return -EINVAL;
+	}
+
+	msg_type = APR_HDR_FIELD_MT(hdr->hdr_field);
+	if (msg_type >= APR_MSG_TYPE_MAX) {
+		dev_err(apr->dev, "APR: Wrong message type: %d\n", msg_type);
+		return -EINVAL;
+	}
+
+	if (hdr->src_domain >= APR_DOMAIN_MAX ||
+			hdr->dest_domain >= APR_DOMAIN_MAX ||
+			hdr->src_svc >= APR_SVC_MAX ||
+			hdr->dest_svc >= APR_SVC_MAX) {
+		dev_err(apr->dev, "APR: Wrong APR header\n");
+		return -EINVAL;
+	}
+
+	svc_id = hdr->dest_svc;
+	spin_lock_irqsave(&apr->svcs_lock, flags);
+	svc = idr_find(&apr->svcs_idr, svc_id);
+	if (svc && svc->dev.driver)
+		adrv = to_apr_driver(svc->dev.driver);
+	spin_unlock_irqrestore(&apr->svcs_lock, flags);
+
+	if (!adrv) {
+		dev_err(apr->dev, "APR: service is not registered\n");
+		return -EINVAL;
+	}
+
+	resp.hdr = *hdr;
+	resp.payload_size = hdr->pkt_size - hdr_size;
+
+	/*
+	 * NOTE: hdr_size is not same as APR_HDR_SIZE as remote can include
+	 * optional headers in to apr_hdr which should be ignored
+	 */
+	if (resp.payload_size > 0)
+		resp.payload = buf + hdr_size;
+
+	adrv->callback(svc, &resp);
+
+	return 0;
+}
+
+static int apr_device_match(struct device *dev, struct device_driver *drv)
+{
+	struct apr_device *adev = to_apr_device(dev);
+	struct apr_driver *adrv = to_apr_driver(drv);
+	const struct apr_device_id *id = adrv->id_table;
+
+	/* Attempt an OF style match first */
+	if (of_driver_match_device(dev, drv))
+		return 1;
+
+	if (!id)
+		return 0;
+
+	while (id->domain_id != 0 || id->svc_id != 0) {
+		if (id->domain_id == adev->domain_id &&
+		    id->svc_id == adev->svc_id)
+			return 1;
+		id++;
+	}
+
+	return 0;
+}
+
+static int apr_device_probe(struct device *dev)
+{
+	struct apr_device *adev = to_apr_device(dev);
+	struct apr_driver *adrv = to_apr_driver(dev->driver);
+
+	return adrv->probe(adev);
+}
+
+static int apr_device_remove(struct device *dev)
+{
+	struct apr_device *adev = to_apr_device(dev);
+	struct apr_driver *adrv;
+	struct apr *apr = dev_get_drvdata(adev->dev.parent);
+
+	if (dev->driver) {
+		adrv = to_apr_driver(dev->driver);
+		if (adrv->remove)
+			adrv->remove(adev);
+		spin_lock(&apr->svcs_lock);
+		idr_remove(&apr->svcs_idr, adev->svc_id);
+		spin_unlock(&apr->svcs_lock);
+	}
+
+	return 0;
+}
+
+static int apr_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct apr_device *adev = to_apr_device(dev);
+	int ret;
+
+	ret = of_device_uevent_modalias(dev, env);
+	if (ret != -ENODEV)
+		return ret;
+
+	return add_uevent_var(env, "MODALIAS=apr:%s", adev->name);
+}
+
+struct bus_type aprbus = {
+	.name		= "aprbus",
+	.match		= apr_device_match,
+	.probe		= apr_device_probe,
+	.uevent		= apr_uevent,
+	.remove		= apr_device_remove,
+};
+EXPORT_SYMBOL_GPL(aprbus);
+
+static int apr_add_device(struct device *dev, struct device_node *np,
+			  const struct apr_device_id *id)
+{
+	struct apr *apr = dev_get_drvdata(dev);
+	struct apr_device *adev = NULL;
+	int ret;
+
+	adev = kzalloc(sizeof(*adev), GFP_KERNEL);
+	if (!adev)
+		return -ENOMEM;
+
+	spin_lock_init(&adev->lock);
+
+	adev->svc_id = id->svc_id;
+	adev->domain_id = id->domain_id;
+	adev->version = id->svc_version;
+	if (np)
+		strncpy(adev->name, np->name, APR_NAME_SIZE);
+	else
+		strncpy(adev->name, id->name, APR_NAME_SIZE);
+
+	dev_set_name(&adev->dev, "aprsvc:%s:%x:%x", adev->name,
+		     id->domain_id, id->svc_id);
+
+	adev->dev.bus = &aprbus;
+	adev->dev.parent = dev;
+	adev->dev.of_node = np;
+	adev->dev.release = apr_dev_release;
+	adev->dev.driver = NULL;
+
+	spin_lock(&apr->svcs_lock);
+	idr_alloc(&apr->svcs_idr, adev, id->svc_id,
+		  id->svc_id + 1, GFP_ATOMIC);
+	spin_unlock(&apr->svcs_lock);
+
+	dev_info(dev, "Adding APR dev: %s\n", dev_name(&adev->dev));
+
+	ret = device_register(&adev->dev);
+	if (ret) {
+		dev_err(dev, "device_register failed: %d\n", ret);
+		put_device(&adev->dev);
+	}
+
+	return ret;
+}
+
+static void of_register_apr_devices(struct device *dev)
+{
+	struct apr *apr = dev_get_drvdata(dev);
+	struct device_node *node;
+
+	for_each_child_of_node(dev->of_node, node) {
+		struct apr_device_id id = { {0} };
+
+		if (of_property_read_u32(node, "reg", &id.svc_id))
+			continue;
+
+		id.domain_id = apr->dest_domain_id;
+
+		if (apr_add_device(dev, node, &id))
+			dev_err(dev, "Failed to add apr %d svc\n", id.svc_id);
+	}
+}
+
+static int apr_probe(struct rpmsg_device *rpdev)
+{
+	struct device *dev = &rpdev->dev;
+	struct apr *apr;
+	int ret;
+
+	apr = devm_kzalloc(dev, sizeof(*apr), GFP_KERNEL);
+	if (!apr)
+		return -ENOMEM;
+
+	ret = of_property_read_u32(dev->of_node, "reg", &apr->dest_domain_id);
+	if (ret) {
+		dev_err(dev, "APR Domain ID not specified in DT\n");
+		return ret;
+	}
+
+	dev_set_drvdata(dev, apr);
+	apr->ch = rpdev->ept;
+	apr->dev = dev;
+	spin_lock_init(&apr->svcs_lock);
+	idr_init(&apr->svcs_idr);
+	of_register_apr_devices(dev);
+
+	return 0;
+}
+
+static int apr_remove_device(struct device *dev, void *null)
+{
+	struct apr_device *adev = to_apr_device(dev);
+
+	device_unregister(&adev->dev);
+
+	return 0;
+}
+
+static void apr_remove(struct rpmsg_device *rpdev)
+{
+	device_for_each_child(&rpdev->dev, NULL, apr_remove_device);
+}
+
+/*
+ * __apr_driver_register() - Client driver registration with aprbus
+ *
+ * @drv:Client driver to be associated with client-device.
+ * @owner: owning module/driver
+ *
+ * This API will register the client driver with the aprbus
+ * It is called from the driver's module-init function.
+ */
+int __apr_driver_register(struct apr_driver *drv, struct module *owner)
+{
+	drv->driver.bus = &aprbus;
+	drv->driver.owner = owner;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(__apr_driver_register);
+
+/*
+ * apr_driver_unregister() - Undo effect of apr_driver_register
+ *
+ * @drv: Client driver to be unregistered
+ */
+void apr_driver_unregister(struct apr_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(apr_driver_unregister);
+
+static const struct of_device_id apr_of_match[] = {
+	{ .compatible = "qcom,apr"},
+	{ .compatible = "qcom,apr-v2"},
+	{}
+};
+MODULE_DEVICE_TABLE(of, apr_of_match);
+
+static struct rpmsg_driver apr_driver = {
+	.probe = apr_probe,
+	.remove = apr_remove,
+	.callback = apr_callback,
+	.drv = {
+		.name = "qcom,apr",
+		.of_match_table = apr_of_match,
+	},
+};
+
+static int __init apr_init(void)
+{
+	int ret;
+
+	ret = bus_register(&aprbus);
+	if (!ret)
+		ret = register_rpmsg_driver(&apr_driver);
+	else
+		bus_unregister(&aprbus);
+
+	return ret;
+}
+
+static void __exit apr_exit(void)
+{
+	bus_unregister(&aprbus);
+	unregister_rpmsg_driver(&apr_driver);
+}
+
+subsys_initcall(apr_init);
+module_exit(apr_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Qualcomm APR Bus");
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index d9fcdb592b39..3e3d12ce4587 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -559,22 +559,28 @@ EXPORT_SYMBOL(tegra_powergate_remove_clamping);
 int tegra_powergate_sequence_power_up(unsigned int id, struct clk *clk,
 				      struct reset_control *rst)
 {
-	struct tegra_powergate pg;
+	struct tegra_powergate *pg;
 	int err;
 
 	if (!tegra_powergate_is_available(id))
 		return -EINVAL;
 
-	pg.id = id;
-	pg.clks = &clk;
-	pg.num_clks = 1;
-	pg.reset = rst;
-	pg.pmc = pmc;
+	pg = kzalloc(sizeof(*pg), GFP_KERNEL);
+	if (!pg)
+		return -ENOMEM;
 
-	err = tegra_powergate_power_up(&pg, false);
+	pg->id = id;
+	pg->clks = &clk;
+	pg->num_clks = 1;
+	pg->reset = rst;
+	pg->pmc = pmc;
+
+	err = tegra_powergate_power_up(pg, false);
 	if (err)
 		pr_err("failed to turn on partition %d: %d\n", id, err);
 
+	kfree(pg);
+
 	return err;
 }
 EXPORT_SYMBOL(tegra_powergate_sequence_power_up);
diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig
index b46084b4b1f8..19c8efb9a5ee 100644
--- a/drivers/soundwire/Kconfig
+++ b/drivers/soundwire/Kconfig
@@ -27,7 +27,7 @@ config SOUNDWIRE_INTEL
 	tristate "Intel SoundWire Master driver"
 	select SOUNDWIRE_CADENCE
 	select SOUNDWIRE_BUS
-	depends on X86 && ACPI
+	depends on X86 && ACPI && SND_SOC
 	---help---
 	  SoundWire Intel Master driver.
 	  If you have an Intel platform which has a SoundWire Master then
diff --git a/drivers/soundwire/Makefile b/drivers/soundwire/Makefile
index e1a74c5692aa..5817beaca0e1 100644
--- a/drivers/soundwire/Makefile
+++ b/drivers/soundwire/Makefile
@@ -3,7 +3,7 @@
 #
 
 #Bus Objs
-soundwire-bus-objs := bus_type.o bus.o slave.o mipi_disco.o
+soundwire-bus-objs := bus_type.o bus.o slave.o mipi_disco.o stream.o
 obj-$(CONFIG_SOUNDWIRE_BUS) += soundwire-bus.o
 
 #Cadence Objs
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index d6dc8e7a8614..dcc0ff9f0c22 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -17,6 +17,7 @@
  */
 int sdw_add_bus_master(struct sdw_bus *bus)
 {
+	struct sdw_master_prop *prop = NULL;
 	int ret;
 
 	if (!bus->dev) {
@@ -32,6 +33,7 @@ int sdw_add_bus_master(struct sdw_bus *bus)
 	mutex_init(&bus->msg_lock);
 	mutex_init(&bus->bus_lock);
 	INIT_LIST_HEAD(&bus->slaves);
+	INIT_LIST_HEAD(&bus->m_rt_list);
 
 	if (bus->ops->read_prop) {
 		ret = bus->ops->read_prop(bus);
@@ -77,6 +79,21 @@ int sdw_add_bus_master(struct sdw_bus *bus)
 		return ret;
 	}
 
+	/*
+	 * Initialize clock values based on Master properties. The max
+	 * frequency is read from max_freq property. Current assumption
+	 * is that the bus will start at highest clock frequency when
+	 * powered on.
+	 *
+	 * Default active bank will be 0 as out of reset the Slaves have
+	 * to start with bank 0 (Table 40 of Spec)
+	 */
+	prop = &bus->prop;
+	bus->params.max_dr_freq = prop->max_freq * SDW_DOUBLE_RATE_FACTOR;
+	bus->params.curr_dr_freq = bus->params.max_dr_freq;
+	bus->params.curr_bank = SDW_BANK0;
+	bus->params.next_bank = SDW_BANK1;
+
 	return 0;
 }
 EXPORT_SYMBOL(sdw_add_bus_master);
@@ -576,6 +593,32 @@ static void sdw_modify_slave_status(struct sdw_slave *slave,
 	mutex_unlock(&slave->bus->bus_lock);
 }
 
+int sdw_configure_dpn_intr(struct sdw_slave *slave,
+			int port, bool enable, int mask)
+{
+	u32 addr;
+	int ret;
+	u8 val = 0;
+
+	addr = SDW_DPN_INTMASK(port);
+
+	/* Set/Clear port ready interrupt mask */
+	if (enable) {
+		val |= mask;
+		val |= SDW_DPN_INT_PORT_READY;
+	} else {
+		val &= ~(mask);
+		val &= ~SDW_DPN_INT_PORT_READY;
+	}
+
+	ret = sdw_update(slave, addr, (mask | SDW_DPN_INT_PORT_READY), val);
+	if (ret < 0)
+		dev_err(slave->bus->dev,
+				"SDW_DPN_INTMASK write failed:%d", val);
+
+	return ret;
+}
+
 static int sdw_initialize_slave(struct sdw_slave *slave)
 {
 	struct sdw_slave_prop *prop = &slave->prop;
diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h
index 345c34d697e9..3b15c4e25a3a 100644
--- a/drivers/soundwire/bus.h
+++ b/drivers/soundwire/bus.h
@@ -45,6 +45,78 @@ struct sdw_msg {
 	bool page;
 };
 
+#define SDW_DOUBLE_RATE_FACTOR		2
+
+extern int rows[SDW_FRAME_ROWS];
+extern int cols[SDW_FRAME_COLS];
+
+/**
+ * sdw_port_runtime: Runtime port parameters for Master or Slave
+ *
+ * @num: Port number. For audio streams, valid port number ranges from
+ * [1,14]
+ * @ch_mask: Channel mask
+ * @transport_params: Transport parameters
+ * @port_params: Port parameters
+ * @port_node: List node for Master or Slave port_list
+ *
+ * SoundWire spec has no mention of ports for Master interface but the
+ * concept is logically extended.
+ */
+struct sdw_port_runtime {
+	int num;
+	int ch_mask;
+	struct sdw_transport_params transport_params;
+	struct sdw_port_params port_params;
+	struct list_head port_node;
+};
+
+/**
+ * sdw_slave_runtime: Runtime Stream parameters for Slave
+ *
+ * @slave: Slave handle
+ * @direction: Data direction for Slave
+ * @ch_count: Number of channels handled by the Slave for
+ * this stream
+ * @m_rt_node: sdw_master_runtime list node
+ * @port_list: List of Slave Ports configured for this stream
+ */
+struct sdw_slave_runtime {
+	struct sdw_slave *slave;
+	enum sdw_data_direction direction;
+	unsigned int ch_count;
+	struct list_head m_rt_node;
+	struct list_head port_list;
+};
+
+/**
+ * sdw_master_runtime: Runtime stream parameters for Master
+ *
+ * @bus: Bus handle
+ * @stream: Stream runtime handle
+ * @direction: Data direction for Master
+ * @ch_count: Number of channels handled by the Master for
+ * this stream, can be zero.
+ * @slave_rt_list: Slave runtime list
+ * @port_list: List of Master Ports configured for this stream, can be zero.
+ * @bus_node: sdw_bus m_rt_list node
+ */
+struct sdw_master_runtime {
+	struct sdw_bus *bus;
+	struct sdw_stream_runtime *stream;
+	enum sdw_data_direction direction;
+	unsigned int ch_count;
+	struct list_head slave_rt_list;
+	struct list_head port_list;
+	struct list_head bus_node;
+};
+
+struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave,
+				enum sdw_data_direction direction,
+				unsigned int port_num);
+int sdw_configure_dpn_intr(struct sdw_slave *slave, int port,
+					bool enable, int mask);
+
 int sdw_transfer(struct sdw_bus *bus, struct sdw_msg *msg);
 int sdw_transfer_defer(struct sdw_bus *bus, struct sdw_msg *msg,
 				struct sdw_defer *defer);
diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index d5f3a70c06b0..283b2832728e 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -83,17 +83,16 @@ static int sdw_drv_probe(struct device *dev)
 	 * attach to power domain but don't turn on (last arg)
 	 */
 	ret = dev_pm_domain_attach(dev, false);
-	if (ret != -EPROBE_DEFER) {
-		ret = drv->probe(slave, id);
-		if (ret) {
-			dev_err(dev, "Probe of %s failed: %d\n", drv->name, ret);
-			dev_pm_domain_detach(dev, false);
-		}
-	}
-
 	if (ret)
 		return ret;
 
+	ret = drv->probe(slave, id);
+	if (ret) {
+		dev_err(dev, "Probe of %s failed: %d\n", drv->name, ret);
+		dev_pm_domain_detach(dev, false);
+		return ret;
+	}
+
 	/* device is probed so let's read the properties now */
 	if (slave->ops && slave->ops->read_prop)
 		slave->ops->read_prop(slave);
diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c
index 3a9b1462039b..cb6a331f448a 100644
--- a/drivers/soundwire/cadence_master.c
+++ b/drivers/soundwire/cadence_master.c
@@ -13,6 +13,8 @@
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/soundwire/sdw.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
 #include "bus.h"
 #include "cadence_master.h"
 
@@ -396,7 +398,7 @@ static int cdns_prep_msg(struct sdw_cdns *cdns, struct sdw_msg *msg, int *cmd)
 	return 0;
 }
 
-static enum sdw_command_response
+enum sdw_command_response
 cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg)
 {
 	struct sdw_cdns *cdns = bus_to_cdns(bus);
@@ -422,8 +424,9 @@ cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg)
 exit:
 	return ret;
 }
+EXPORT_SYMBOL(cdns_xfer_msg);
 
-static enum sdw_command_response
+enum sdw_command_response
 cdns_xfer_msg_defer(struct sdw_bus *bus,
 		struct sdw_msg *msg, struct sdw_defer *defer)
 {
@@ -443,8 +446,9 @@ cdns_xfer_msg_defer(struct sdw_bus *bus,
 
 	return _cdns_xfer_msg(cdns, msg, cmd, 0, msg->len, true);
 }
+EXPORT_SYMBOL(cdns_xfer_msg_defer);
 
-static enum sdw_command_response
+enum sdw_command_response
 cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num)
 {
 	struct sdw_cdns *cdns = bus_to_cdns(bus);
@@ -456,6 +460,7 @@ cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num)
 
 	return cdns_program_scp_addr(cdns, &msg);
 }
+EXPORT_SYMBOL(cdns_reset_page_addr);
 
 /*
  * IRQ handling
@@ -666,6 +671,120 @@ int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns)
 }
 EXPORT_SYMBOL(sdw_cdns_enable_interrupt);
 
+static int cdns_allocate_pdi(struct sdw_cdns *cdns,
+			struct sdw_cdns_pdi **stream,
+			u32 num, u32 pdi_offset)
+{
+	struct sdw_cdns_pdi *pdi;
+	int i;
+
+	if (!num)
+		return 0;
+
+	pdi = devm_kcalloc(cdns->dev, num, sizeof(*pdi), GFP_KERNEL);
+	if (!pdi)
+		return -ENOMEM;
+
+	for (i = 0; i < num; i++) {
+		pdi[i].num = i + pdi_offset;
+		pdi[i].assigned = false;
+	}
+
+	*stream = pdi;
+	return 0;
+}
+
+/**
+ * sdw_cdns_pdi_init() - PDI initialization routine
+ *
+ * @cdns: Cadence instance
+ * @config: Stream configurations
+ */
+int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
+			struct sdw_cdns_stream_config config)
+{
+	struct sdw_cdns_streams *stream;
+	int offset, i, ret;
+
+	cdns->pcm.num_bd = config.pcm_bd;
+	cdns->pcm.num_in = config.pcm_in;
+	cdns->pcm.num_out = config.pcm_out;
+	cdns->pdm.num_bd = config.pdm_bd;
+	cdns->pdm.num_in = config.pdm_in;
+	cdns->pdm.num_out = config.pdm_out;
+
+	/* Allocate PDIs for PCMs */
+	stream = &cdns->pcm;
+
+	/* First two PDIs are reserved for bulk transfers */
+	stream->num_bd -= CDNS_PCM_PDI_OFFSET;
+	offset = CDNS_PCM_PDI_OFFSET;
+
+	ret = cdns_allocate_pdi(cdns, &stream->bd,
+				stream->num_bd, offset);
+	if (ret)
+		return ret;
+
+	offset += stream->num_bd;
+
+	ret = cdns_allocate_pdi(cdns, &stream->in,
+				stream->num_in, offset);
+	if (ret)
+		return ret;
+
+	offset += stream->num_in;
+
+	ret = cdns_allocate_pdi(cdns, &stream->out,
+				stream->num_out, offset);
+	if (ret)
+		return ret;
+
+	/* Update total number of PCM PDIs */
+	stream->num_pdi = stream->num_bd + stream->num_in + stream->num_out;
+	cdns->num_ports = stream->num_pdi;
+
+	/* Allocate PDIs for PDMs */
+	stream = &cdns->pdm;
+	offset = CDNS_PDM_PDI_OFFSET;
+	ret = cdns_allocate_pdi(cdns, &stream->bd,
+				stream->num_bd, offset);
+	if (ret)
+		return ret;
+
+	offset += stream->num_bd;
+
+	ret = cdns_allocate_pdi(cdns, &stream->in,
+				stream->num_in, offset);
+	if (ret)
+		return ret;
+
+	offset += stream->num_in;
+
+	ret = cdns_allocate_pdi(cdns, &stream->out,
+				stream->num_out, offset);
+	if (ret)
+		return ret;
+
+	/* Update total number of PDM PDIs */
+	stream->num_pdi = stream->num_bd + stream->num_in + stream->num_out;
+	cdns->num_ports += stream->num_pdi;
+
+	cdns->ports = devm_kcalloc(cdns->dev, cdns->num_ports,
+				sizeof(*cdns->ports), GFP_KERNEL);
+	if (!cdns->ports) {
+		ret = -ENOMEM;
+		return ret;
+	}
+
+	for (i = 0; i < cdns->num_ports; i++) {
+		cdns->ports[i].assigned = false;
+		cdns->ports[i].num = i + 1; /* Port 0 reserved for bulk */
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(sdw_cdns_pdi_init);
+
 /**
  * sdw_cdns_init() - Cadence initialization
  * @cdns: Cadence instance
@@ -727,13 +846,133 @@ int sdw_cdns_init(struct sdw_cdns *cdns)
 }
 EXPORT_SYMBOL(sdw_cdns_init);
 
-struct sdw_master_ops sdw_cdns_master_ops = {
-	.read_prop = sdw_master_read_prop,
-	.xfer_msg = cdns_xfer_msg,
-	.xfer_msg_defer = cdns_xfer_msg_defer,
-	.reset_page_addr = cdns_reset_page_addr,
+int cdns_bus_conf(struct sdw_bus *bus, struct sdw_bus_params *params)
+{
+	struct sdw_cdns *cdns = bus_to_cdns(bus);
+	int mcp_clkctrl_off, mcp_clkctrl;
+	int divider;
+
+	if (!params->curr_dr_freq) {
+		dev_err(cdns->dev, "NULL curr_dr_freq");
+		return -EINVAL;
+	}
+
+	divider	= (params->max_dr_freq / params->curr_dr_freq) - 1;
+
+	if (params->next_bank)
+		mcp_clkctrl_off = CDNS_MCP_CLK_CTRL1;
+	else
+		mcp_clkctrl_off = CDNS_MCP_CLK_CTRL0;
+
+	mcp_clkctrl = cdns_readl(cdns, mcp_clkctrl_off);
+	mcp_clkctrl |= divider;
+	cdns_writel(cdns, mcp_clkctrl_off, mcp_clkctrl);
+
+	return 0;
+}
+EXPORT_SYMBOL(cdns_bus_conf);
+
+static int cdns_port_params(struct sdw_bus *bus,
+		struct sdw_port_params *p_params, unsigned int bank)
+{
+	struct sdw_cdns *cdns = bus_to_cdns(bus);
+	int dpn_config = 0, dpn_config_off;
+
+	if (bank)
+		dpn_config_off = CDNS_DPN_B1_CONFIG(p_params->num);
+	else
+		dpn_config_off = CDNS_DPN_B0_CONFIG(p_params->num);
+
+	dpn_config = cdns_readl(cdns, dpn_config_off);
+
+	dpn_config |= ((p_params->bps - 1) <<
+				SDW_REG_SHIFT(CDNS_DPN_CONFIG_WL));
+	dpn_config |= (p_params->flow_mode <<
+				SDW_REG_SHIFT(CDNS_DPN_CONFIG_PORT_FLOW));
+	dpn_config |= (p_params->data_mode <<
+				SDW_REG_SHIFT(CDNS_DPN_CONFIG_PORT_DAT));
+
+	cdns_writel(cdns, dpn_config_off, dpn_config);
+
+	return 0;
+}
+
+static int cdns_transport_params(struct sdw_bus *bus,
+			struct sdw_transport_params *t_params,
+			enum sdw_reg_bank bank)
+{
+	struct sdw_cdns *cdns = bus_to_cdns(bus);
+	int dpn_offsetctrl = 0, dpn_offsetctrl_off;
+	int dpn_config = 0, dpn_config_off;
+	int dpn_hctrl = 0, dpn_hctrl_off;
+	int num = t_params->port_num;
+	int dpn_samplectrl_off;
+
+	/*
+	 * Note: Only full data port is supported on the Master side for
+	 * both PCM and PDM ports.
+	 */
+
+	if (bank) {
+		dpn_config_off = CDNS_DPN_B1_CONFIG(num);
+		dpn_samplectrl_off = CDNS_DPN_B1_SAMPLE_CTRL(num);
+		dpn_hctrl_off = CDNS_DPN_B1_HCTRL(num);
+		dpn_offsetctrl_off = CDNS_DPN_B1_OFFSET_CTRL(num);
+	} else {
+		dpn_config_off = CDNS_DPN_B0_CONFIG(num);
+		dpn_samplectrl_off = CDNS_DPN_B0_SAMPLE_CTRL(num);
+		dpn_hctrl_off = CDNS_DPN_B0_HCTRL(num);
+		dpn_offsetctrl_off = CDNS_DPN_B0_OFFSET_CTRL(num);
+	}
+
+	dpn_config = cdns_readl(cdns, dpn_config_off);
+
+	dpn_config |= (t_params->blk_grp_ctrl <<
+				SDW_REG_SHIFT(CDNS_DPN_CONFIG_BGC));
+	dpn_config |= (t_params->blk_pkg_mode <<
+				SDW_REG_SHIFT(CDNS_DPN_CONFIG_BPM));
+	cdns_writel(cdns, dpn_config_off, dpn_config);
+
+	dpn_offsetctrl |= (t_params->offset1 <<
+				SDW_REG_SHIFT(CDNS_DPN_OFFSET_CTRL_1));
+	dpn_offsetctrl |= (t_params->offset2 <<
+				SDW_REG_SHIFT(CDNS_DPN_OFFSET_CTRL_2));
+	cdns_writel(cdns, dpn_offsetctrl_off,  dpn_offsetctrl);
+
+	dpn_hctrl |= (t_params->hstart <<
+				SDW_REG_SHIFT(CDNS_DPN_HCTRL_HSTART));
+	dpn_hctrl |= (t_params->hstop << SDW_REG_SHIFT(CDNS_DPN_HCTRL_HSTOP));
+	dpn_hctrl |= (t_params->lane_ctrl <<
+				SDW_REG_SHIFT(CDNS_DPN_HCTRL_LCTRL));
+
+	cdns_writel(cdns, dpn_hctrl_off, dpn_hctrl);
+	cdns_writel(cdns, dpn_samplectrl_off, (t_params->sample_interval - 1));
+
+	return 0;
+}
+
+static int cdns_port_enable(struct sdw_bus *bus,
+		struct sdw_enable_ch *enable_ch, unsigned int bank)
+{
+	struct sdw_cdns *cdns = bus_to_cdns(bus);
+	int dpn_chnen_off, ch_mask;
+
+	if (bank)
+		dpn_chnen_off = CDNS_DPN_B1_CH_EN(enable_ch->port_num);
+	else
+		dpn_chnen_off = CDNS_DPN_B0_CH_EN(enable_ch->port_num);
+
+	ch_mask = enable_ch->ch_mask * enable_ch->enable;
+	cdns_writel(cdns, dpn_chnen_off, ch_mask);
+
+	return 0;
+}
+
+static const struct sdw_master_port_ops cdns_port_ops = {
+	.dpn_set_port_params = cdns_port_params,
+	.dpn_set_port_transport_params = cdns_transport_params,
+	.dpn_port_enable_ch = cdns_port_enable,
 };
-EXPORT_SYMBOL(sdw_cdns_master_ops);
 
 /**
  * sdw_cdns_probe() - Cadence probe routine
@@ -742,10 +981,204 @@ EXPORT_SYMBOL(sdw_cdns_master_ops);
 int sdw_cdns_probe(struct sdw_cdns *cdns)
 {
 	init_completion(&cdns->tx_complete);
+	cdns->bus.port_ops = &cdns_port_ops;
 
 	return 0;
 }
 EXPORT_SYMBOL(sdw_cdns_probe);
 
+int cdns_set_sdw_stream(struct snd_soc_dai *dai,
+		void *stream, bool pcm, int direction)
+{
+	struct sdw_cdns *cdns = snd_soc_dai_get_drvdata(dai);
+	struct sdw_cdns_dma_data *dma;
+
+	dma = kzalloc(sizeof(*dma), GFP_KERNEL);
+	if (!dma)
+		return -ENOMEM;
+
+	if (pcm)
+		dma->stream_type = SDW_STREAM_PCM;
+	else
+		dma->stream_type = SDW_STREAM_PDM;
+
+	dma->bus = &cdns->bus;
+	dma->link_id = cdns->instance;
+
+	dma->stream = stream;
+
+	if (direction == SNDRV_PCM_STREAM_PLAYBACK)
+		dai->playback_dma_data = dma;
+	else
+		dai->capture_dma_data = dma;
+
+	return 0;
+}
+EXPORT_SYMBOL(cdns_set_sdw_stream);
+
+/**
+ * cdns_find_pdi() - Find a free PDI
+ *
+ * @cdns: Cadence instance
+ * @num: Number of PDIs
+ * @pdi: PDI instances
+ *
+ * Find and return a free PDI for a given PDI array
+ */
+static struct sdw_cdns_pdi *cdns_find_pdi(struct sdw_cdns *cdns,
+		unsigned int num, struct sdw_cdns_pdi *pdi)
+{
+	int i;
+
+	for (i = 0; i < num; i++) {
+		if (pdi[i].assigned == true)
+			continue;
+		pdi[i].assigned = true;
+		return &pdi[i];
+	}
+
+	return NULL;
+}
+
+/**
+ * sdw_cdns_config_stream: Configure a stream
+ *
+ * @cdns: Cadence instance
+ * @port: Cadence data port
+ * @ch: Channel count
+ * @dir: Data direction
+ * @pdi: PDI to be used
+ */
+void sdw_cdns_config_stream(struct sdw_cdns *cdns,
+				struct sdw_cdns_port *port,
+				u32 ch, u32 dir, struct sdw_cdns_pdi *pdi)
+{
+	u32 offset, val = 0;
+
+	if (dir == SDW_DATA_DIR_RX)
+		val = CDNS_PORTCTRL_DIRN;
+
+	offset = CDNS_PORTCTRL + port->num * CDNS_PORT_OFFSET;
+	cdns_updatel(cdns, offset, CDNS_PORTCTRL_DIRN, val);
+
+	val = port->num;
+	val |= ((1 << ch) - 1) << SDW_REG_SHIFT(CDNS_PDI_CONFIG_CHANNEL);
+	cdns_writel(cdns, CDNS_PDI_CONFIG(pdi->num), val);
+}
+EXPORT_SYMBOL(sdw_cdns_config_stream);
+
+/**
+ * cdns_get_num_pdi() - Get number of PDIs required
+ *
+ * @cdns: Cadence instance
+ * @pdi: PDI to be used
+ * @num: Number of PDIs
+ * @ch_count: Channel count
+ */
+static int cdns_get_num_pdi(struct sdw_cdns *cdns,
+		struct sdw_cdns_pdi *pdi,
+		unsigned int num, u32 ch_count)
+{
+	int i, pdis = 0;
+
+	for (i = 0; i < num; i++) {
+		if (pdi[i].assigned == true)
+			continue;
+
+		if (pdi[i].ch_count < ch_count)
+			ch_count -= pdi[i].ch_count;
+		else
+			ch_count = 0;
+
+		pdis++;
+
+		if (!ch_count)
+			break;
+	}
+
+	if (ch_count)
+		return 0;
+
+	return pdis;
+}
+
+/**
+ * sdw_cdns_get_stream() - Get stream information
+ *
+ * @cdns: Cadence instance
+ * @stream: Stream to be allocated
+ * @ch: Channel count
+ * @dir: Data direction
+ */
+int sdw_cdns_get_stream(struct sdw_cdns *cdns,
+			struct sdw_cdns_streams *stream,
+			u32 ch, u32 dir)
+{
+	int pdis = 0;
+
+	if (dir == SDW_DATA_DIR_RX)
+		pdis = cdns_get_num_pdi(cdns, stream->in, stream->num_in, ch);
+	else
+		pdis = cdns_get_num_pdi(cdns, stream->out, stream->num_out, ch);
+
+	/* check if we found PDI, else find in bi-directional */
+	if (!pdis)
+		pdis = cdns_get_num_pdi(cdns, stream->bd, stream->num_bd, ch);
+
+	return pdis;
+}
+EXPORT_SYMBOL(sdw_cdns_get_stream);
+
+/**
+ * sdw_cdns_alloc_stream() - Allocate a stream
+ *
+ * @cdns: Cadence instance
+ * @stream: Stream to be allocated
+ * @port: Cadence data port
+ * @ch: Channel count
+ * @dir: Data direction
+ */
+int sdw_cdns_alloc_stream(struct sdw_cdns *cdns,
+			struct sdw_cdns_streams *stream,
+			struct sdw_cdns_port *port, u32 ch, u32 dir)
+{
+	struct sdw_cdns_pdi *pdi = NULL;
+
+	if (dir == SDW_DATA_DIR_RX)
+		pdi = cdns_find_pdi(cdns, stream->num_in, stream->in);
+	else
+		pdi = cdns_find_pdi(cdns, stream->num_out, stream->out);
+
+	/* check if we found a PDI, else find in bi-directional */
+	if (!pdi)
+		pdi = cdns_find_pdi(cdns, stream->num_bd, stream->bd);
+
+	if (!pdi)
+		return -EIO;
+
+	port->pdi = pdi;
+	pdi->l_ch_num = 0;
+	pdi->h_ch_num = ch - 1;
+	pdi->dir = dir;
+	pdi->ch_count = ch;
+
+	return 0;
+}
+EXPORT_SYMBOL(sdw_cdns_alloc_stream);
+
+void sdw_cdns_shutdown(struct snd_pcm_substream *substream,
+					struct snd_soc_dai *dai)
+{
+	struct sdw_cdns_dma_data *dma;
+
+	dma = snd_soc_dai_get_dma_data(dai, substream);
+	if (!dma)
+		return;
+
+	snd_soc_dai_set_dma_data(dai, substream, NULL);
+	kfree(dma);
+}
+EXPORT_SYMBOL(sdw_cdns_shutdown);
+
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("Cadence Soundwire Library");
diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h
index beaf6c9804eb..eb902b19c5a4 100644
--- a/drivers/soundwire/cadence_master.h
+++ b/drivers/soundwire/cadence_master.h
@@ -1,10 +1,117 @@
 // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 // Copyright(c) 2015-17 Intel Corporation.
+#include <sound/soc.h>
 
 #ifndef __SDW_CADENCE_H
 #define __SDW_CADENCE_H
 
 /**
+ * struct sdw_cdns_pdi: PDI (Physical Data Interface) instance
+ *
+ * @assigned: pdi assigned
+ * @num: pdi number
+ * @intel_alh_id: link identifier
+ * @l_ch_num: low channel for PDI
+ * @h_ch_num: high channel for PDI
+ * @ch_count: total channel count for PDI
+ * @dir: data direction
+ * @type: stream type, PDM or PCM
+ */
+struct sdw_cdns_pdi {
+	bool assigned;
+	int num;
+	int intel_alh_id;
+	int l_ch_num;
+	int h_ch_num;
+	int ch_count;
+	enum sdw_data_direction dir;
+	enum sdw_stream_type type;
+};
+
+/**
+ * struct sdw_cdns_port: Cadence port structure
+ *
+ * @num: port number
+ * @assigned: port assigned
+ * @ch: channel count
+ * @direction: data port direction
+ * @pdi: pdi for this port
+ */
+struct sdw_cdns_port {
+	unsigned int num;
+	bool assigned;
+	unsigned int ch;
+	enum sdw_data_direction direction;
+	struct sdw_cdns_pdi *pdi;
+};
+
+/**
+ * struct sdw_cdns_streams: Cadence stream data structure
+ *
+ * @num_bd: number of bidirectional streams
+ * @num_in: number of input streams
+ * @num_out: number of output streams
+ * @num_ch_bd: number of bidirectional stream channels
+ * @num_ch_bd: number of input stream channels
+ * @num_ch_bd: number of output stream channels
+ * @num_pdi: total number of PDIs
+ * @bd: bidirectional streams
+ * @in: input streams
+ * @out: output streams
+ */
+struct sdw_cdns_streams {
+	unsigned int num_bd;
+	unsigned int num_in;
+	unsigned int num_out;
+	unsigned int num_ch_bd;
+	unsigned int num_ch_in;
+	unsigned int num_ch_out;
+	unsigned int num_pdi;
+	struct sdw_cdns_pdi *bd;
+	struct sdw_cdns_pdi *in;
+	struct sdw_cdns_pdi *out;
+};
+
+/**
+ * struct sdw_cdns_stream_config: stream configuration
+ *
+ * @pcm_bd: number of bidirectional PCM streams supported
+ * @pcm_in: number of input PCM streams supported
+ * @pcm_out: number of output PCM streams supported
+ * @pdm_bd: number of bidirectional PDM streams supported
+ * @pdm_in: number of input PDM streams supported
+ * @pdm_out: number of output PDM streams supported
+ */
+struct sdw_cdns_stream_config {
+	unsigned int pcm_bd;
+	unsigned int pcm_in;
+	unsigned int pcm_out;
+	unsigned int pdm_bd;
+	unsigned int pdm_in;
+	unsigned int pdm_out;
+};
+
+/**
+ * struct sdw_cdns_dma_data: Cadence DMA data
+ *
+ * @name: SoundWire stream name
+ * @nr_ports: Number of ports
+ * @port: Ports
+ * @bus: Bus handle
+ * @stream_type: Stream type
+ * @link_id: Master link id
+ */
+struct sdw_cdns_dma_data {
+	char *name;
+	struct sdw_stream_runtime *stream;
+	int nr_ports;
+	struct sdw_cdns_port **port;
+	struct sdw_bus *bus;
+	enum sdw_stream_type stream_type;
+	int link_id;
+};
+
+/**
  * struct sdw_cdns - Cadence driver context
  * @dev: Linux device
  * @bus: Bus handle
@@ -12,6 +119,10 @@
  * @response_buf: SoundWire response buffer
  * @tx_complete: Tx completion
  * @defer: Defer pointer
+ * @ports: Data ports
+ * @num_ports: Total number of data ports
+ * @pcm: PCM streams
+ * @pdm: PDM streams
  * @registers: Cadence registers
  * @link_up: Link status
  * @msg_count: Messages sent on bus
@@ -25,6 +136,12 @@ struct sdw_cdns {
 	struct completion tx_complete;
 	struct sdw_defer *defer;
 
+	struct sdw_cdns_port *ports;
+	int num_ports;
+
+	struct sdw_cdns_streams pcm;
+	struct sdw_cdns_streams pdm;
+
 	void __iomem *registers;
 
 	bool link_up;
@@ -42,7 +159,41 @@ irqreturn_t sdw_cdns_irq(int irq, void *dev_id);
 irqreturn_t sdw_cdns_thread(int irq, void *dev_id);
 
 int sdw_cdns_init(struct sdw_cdns *cdns);
+int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
+			struct sdw_cdns_stream_config config);
 int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns);
 
+int sdw_cdns_get_stream(struct sdw_cdns *cdns,
+			struct sdw_cdns_streams *stream,
+			u32 ch, u32 dir);
+int sdw_cdns_alloc_stream(struct sdw_cdns *cdns,
+			struct sdw_cdns_streams *stream,
+			struct sdw_cdns_port *port, u32 ch, u32 dir);
+void sdw_cdns_config_stream(struct sdw_cdns *cdns, struct sdw_cdns_port *port,
+			u32 ch, u32 dir, struct sdw_cdns_pdi *pdi);
+
+void sdw_cdns_shutdown(struct snd_pcm_substream *substream,
+				struct snd_soc_dai *dai);
+int sdw_cdns_pcm_set_stream(struct snd_soc_dai *dai,
+				void *stream, int direction);
+int sdw_cdns_pdm_set_stream(struct snd_soc_dai *dai,
+				void *stream, int direction);
+
+enum sdw_command_response
+cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num);
+
+enum sdw_command_response
+cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg);
+
+enum sdw_command_response
+cdns_xfer_msg_defer(struct sdw_bus *bus,
+		struct sdw_msg *msg, struct sdw_defer *defer);
+
+enum sdw_command_response
+cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num);
+
+int cdns_bus_conf(struct sdw_bus *bus, struct sdw_bus_params *params);
 
+int cdns_set_sdw_stream(struct snd_soc_dai *dai,
+		void *stream, bool pcm, int direction);
 #endif /* __SDW_CADENCE_H */
diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index 86a7bd1fc912..0a8990e758f9 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -9,6 +9,8 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_intel.h>
@@ -85,6 +87,12 @@
 #define SDW_ALH_STRMZCFG_DMAT		GENMASK(7, 0)
 #define SDW_ALH_STRMZCFG_CHN		GENMASK(19, 16)
 
+enum intel_pdi_type {
+	INTEL_PDI_IN = 0,
+	INTEL_PDI_OUT = 1,
+	INTEL_PDI_BD = 2,
+};
+
 struct sdw_intel {
 	struct sdw_cdns cdns;
 	int instance;
@@ -234,6 +242,490 @@ static int intel_shim_init(struct sdw_intel *sdw)
 	return ret;
 }
 
+/*
+ * PDI routines
+ */
+static void intel_pdi_init(struct sdw_intel *sdw,
+			struct sdw_cdns_stream_config *config)
+{
+	void __iomem *shim = sdw->res->shim;
+	unsigned int link_id = sdw->instance;
+	int pcm_cap, pdm_cap;
+
+	/* PCM Stream Capability */
+	pcm_cap = intel_readw(shim, SDW_SHIM_PCMSCAP(link_id));
+
+	config->pcm_bd = (pcm_cap & SDW_SHIM_PCMSCAP_BSS) >>
+					SDW_REG_SHIFT(SDW_SHIM_PCMSCAP_BSS);
+	config->pcm_in = (pcm_cap & SDW_SHIM_PCMSCAP_ISS) >>
+					SDW_REG_SHIFT(SDW_SHIM_PCMSCAP_ISS);
+	config->pcm_out = (pcm_cap & SDW_SHIM_PCMSCAP_OSS) >>
+					SDW_REG_SHIFT(SDW_SHIM_PCMSCAP_OSS);
+
+	/* PDM Stream Capability */
+	pdm_cap = intel_readw(shim, SDW_SHIM_PDMSCAP(link_id));
+
+	config->pdm_bd = (pdm_cap & SDW_SHIM_PDMSCAP_BSS) >>
+					SDW_REG_SHIFT(SDW_SHIM_PDMSCAP_BSS);
+	config->pdm_in = (pdm_cap & SDW_SHIM_PDMSCAP_ISS) >>
+					SDW_REG_SHIFT(SDW_SHIM_PDMSCAP_ISS);
+	config->pdm_out = (pdm_cap & SDW_SHIM_PDMSCAP_OSS) >>
+					SDW_REG_SHIFT(SDW_SHIM_PDMSCAP_OSS);
+}
+
+static int
+intel_pdi_get_ch_cap(struct sdw_intel *sdw, unsigned int pdi_num, bool pcm)
+{
+	void __iomem *shim = sdw->res->shim;
+	unsigned int link_id = sdw->instance;
+	int count;
+
+	if (pcm) {
+		count = intel_readw(shim, SDW_SHIM_PCMSYCHC(link_id, pdi_num));
+	} else {
+		count = intel_readw(shim, SDW_SHIM_PDMSCAP(link_id));
+		count = ((count & SDW_SHIM_PDMSCAP_CPSS) >>
+					SDW_REG_SHIFT(SDW_SHIM_PDMSCAP_CPSS));
+	}
+
+	/* zero based values for channel count in register */
+	count++;
+
+	return count;
+}
+
+static int intel_pdi_get_ch_update(struct sdw_intel *sdw,
+				struct sdw_cdns_pdi *pdi,
+				unsigned int num_pdi,
+				unsigned int *num_ch, bool pcm)
+{
+	int i, ch_count = 0;
+
+	for (i = 0; i < num_pdi; i++) {
+		pdi->ch_count = intel_pdi_get_ch_cap(sdw, pdi->num, pcm);
+		ch_count += pdi->ch_count;
+		pdi++;
+	}
+
+	*num_ch = ch_count;
+	return 0;
+}
+
+static int intel_pdi_stream_ch_update(struct sdw_intel *sdw,
+				struct sdw_cdns_streams *stream, bool pcm)
+{
+	intel_pdi_get_ch_update(sdw, stream->bd, stream->num_bd,
+			&stream->num_ch_bd, pcm);
+
+	intel_pdi_get_ch_update(sdw, stream->in, stream->num_in,
+			&stream->num_ch_in, pcm);
+
+	intel_pdi_get_ch_update(sdw, stream->out, stream->num_out,
+			&stream->num_ch_out, pcm);
+
+	return 0;
+}
+
+static int intel_pdi_ch_update(struct sdw_intel *sdw)
+{
+	/* First update PCM streams followed by PDM streams */
+	intel_pdi_stream_ch_update(sdw, &sdw->cdns.pcm, true);
+	intel_pdi_stream_ch_update(sdw, &sdw->cdns.pdm, false);
+
+	return 0;
+}
+
+static void
+intel_pdi_shim_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi)
+{
+	void __iomem *shim = sdw->res->shim;
+	unsigned int link_id = sdw->instance;
+	int pdi_conf = 0;
+
+	pdi->intel_alh_id = (link_id * 16) + pdi->num + 5;
+
+	/*
+	 * Program stream parameters to stream SHIM register
+	 * This is applicable for PCM stream only.
+	 */
+	if (pdi->type != SDW_STREAM_PCM)
+		return;
+
+	if (pdi->dir == SDW_DATA_DIR_RX)
+		pdi_conf |= SDW_SHIM_PCMSYCM_DIR;
+	else
+		pdi_conf &= ~(SDW_SHIM_PCMSYCM_DIR);
+
+	pdi_conf |= (pdi->intel_alh_id <<
+			SDW_REG_SHIFT(SDW_SHIM_PCMSYCM_STREAM));
+	pdi_conf |= (pdi->l_ch_num << SDW_REG_SHIFT(SDW_SHIM_PCMSYCM_LCHN));
+	pdi_conf |= (pdi->h_ch_num << SDW_REG_SHIFT(SDW_SHIM_PCMSYCM_HCHN));
+
+	intel_writew(shim, SDW_SHIM_PCMSYCHM(link_id, pdi->num), pdi_conf);
+}
+
+static void
+intel_pdi_alh_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi)
+{
+	void __iomem *alh = sdw->res->alh;
+	unsigned int link_id = sdw->instance;
+	unsigned int conf;
+
+	pdi->intel_alh_id = (link_id * 16) + pdi->num + 5;
+
+	/* Program Stream config ALH register */
+	conf = intel_readl(alh, SDW_ALH_STRMZCFG(pdi->intel_alh_id));
+
+	conf |= (SDW_ALH_STRMZCFG_DMAT_VAL <<
+			SDW_REG_SHIFT(SDW_ALH_STRMZCFG_DMAT));
+
+	conf |= ((pdi->ch_count - 1) <<
+			SDW_REG_SHIFT(SDW_ALH_STRMZCFG_CHN));
+
+	intel_writel(alh, SDW_ALH_STRMZCFG(pdi->intel_alh_id), conf);
+}
+
+static int intel_config_stream(struct sdw_intel *sdw,
+			struct snd_pcm_substream *substream,
+			struct snd_soc_dai *dai,
+			struct snd_pcm_hw_params *hw_params, int link_id)
+{
+	if (sdw->res->ops && sdw->res->ops->config_stream)
+		return sdw->res->ops->config_stream(sdw->res->arg,
+				substream, dai, hw_params, link_id);
+
+	return -EIO;
+}
+
+/*
+ * DAI routines
+ */
+
+static struct sdw_cdns_port *intel_alloc_port(struct sdw_intel *sdw,
+				u32 ch, u32 dir, bool pcm)
+{
+	struct sdw_cdns *cdns = &sdw->cdns;
+	struct sdw_cdns_port *port = NULL;
+	int i, ret = 0;
+
+	for (i = 0; i < cdns->num_ports; i++) {
+		if (cdns->ports[i].assigned == true)
+			continue;
+
+		port = &cdns->ports[i];
+		port->assigned = true;
+		port->direction = dir;
+		port->ch = ch;
+		break;
+	}
+
+	if (!port) {
+		dev_err(cdns->dev, "Unable to find a free port\n");
+		return NULL;
+	}
+
+	if (pcm) {
+		ret = sdw_cdns_alloc_stream(cdns, &cdns->pcm, port, ch, dir);
+		if (ret)
+			goto out;
+
+		intel_pdi_shim_configure(sdw, port->pdi);
+		sdw_cdns_config_stream(cdns, port, ch, dir, port->pdi);
+
+		intel_pdi_alh_configure(sdw, port->pdi);
+
+	} else {
+		ret = sdw_cdns_alloc_stream(cdns, &cdns->pdm, port, ch, dir);
+	}
+
+out:
+	if (ret) {
+		port->assigned = false;
+		port = NULL;
+	}
+
+	return port;
+}
+
+static void intel_port_cleanup(struct sdw_cdns_dma_data *dma)
+{
+	int i;
+
+	for (i = 0; i < dma->nr_ports; i++) {
+		if (dma->port[i]) {
+			dma->port[i]->pdi->assigned = false;
+			dma->port[i]->pdi = NULL;
+			dma->port[i]->assigned = false;
+			dma->port[i] = NULL;
+		}
+	}
+}
+
+static int intel_hw_params(struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *params,
+				struct snd_soc_dai *dai)
+{
+	struct sdw_cdns *cdns = snd_soc_dai_get_drvdata(dai);
+	struct sdw_intel *sdw = cdns_to_intel(cdns);
+	struct sdw_cdns_dma_data *dma;
+	struct sdw_stream_config sconfig;
+	struct sdw_port_config *pconfig;
+	int ret, i, ch, dir;
+	bool pcm = true;
+
+	dma = snd_soc_dai_get_dma_data(dai, substream);
+	if (!dma)
+		return -EIO;
+
+	ch = params_channels(params);
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+		dir = SDW_DATA_DIR_RX;
+	else
+		dir = SDW_DATA_DIR_TX;
+
+	if (dma->stream_type == SDW_STREAM_PDM) {
+		/* TODO: Check whether PDM decimator is already in use */
+		dma->nr_ports = sdw_cdns_get_stream(cdns, &cdns->pdm, ch, dir);
+		pcm = false;
+	} else {
+		dma->nr_ports = sdw_cdns_get_stream(cdns, &cdns->pcm, ch, dir);
+	}
+
+	if (!dma->nr_ports) {
+		dev_err(dai->dev, "ports/resources not available");
+		return -EINVAL;
+	}
+
+	dma->port = kcalloc(dma->nr_ports, sizeof(*dma->port), GFP_KERNEL);
+	if (!dma->port)
+		return -ENOMEM;
+
+	for (i = 0; i < dma->nr_ports; i++) {
+		dma->port[i] = intel_alloc_port(sdw, ch, dir, pcm);
+		if (!dma->port[i]) {
+			ret = -EINVAL;
+			goto port_error;
+		}
+	}
+
+	/* Inform DSP about PDI stream number */
+	for (i = 0; i < dma->nr_ports; i++) {
+		ret = intel_config_stream(sdw, substream, dai, params,
+				dma->port[i]->pdi->intel_alh_id);
+		if (ret)
+			goto port_error;
+	}
+
+	sconfig.direction = dir;
+	sconfig.ch_count = ch;
+	sconfig.frame_rate = params_rate(params);
+	sconfig.type = dma->stream_type;
+
+	if (dma->stream_type == SDW_STREAM_PDM) {
+		sconfig.frame_rate *= 50;
+		sconfig.bps = 1;
+	} else {
+		sconfig.bps = snd_pcm_format_width(params_format(params));
+	}
+
+	/* Port configuration */
+	pconfig = kcalloc(dma->nr_ports, sizeof(*pconfig), GFP_KERNEL);
+	if (!pconfig) {
+		ret =  -ENOMEM;
+		goto port_error;
+	}
+
+	for (i = 0; i < dma->nr_ports; i++) {
+		pconfig[i].num = dma->port[i]->num;
+		pconfig[i].ch_mask = (1 << ch) - 1;
+	}
+
+	ret = sdw_stream_add_master(&cdns->bus, &sconfig,
+				pconfig, dma->nr_ports, dma->stream);
+	if (ret) {
+		dev_err(cdns->dev, "add master to stream failed:%d", ret);
+		goto stream_error;
+	}
+
+	kfree(pconfig);
+	return ret;
+
+stream_error:
+	kfree(pconfig);
+port_error:
+	intel_port_cleanup(dma);
+	kfree(dma->port);
+	return ret;
+}
+
+static int
+intel_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai)
+{
+	struct sdw_cdns *cdns = snd_soc_dai_get_drvdata(dai);
+	struct sdw_cdns_dma_data *dma;
+	int ret;
+
+	dma = snd_soc_dai_get_dma_data(dai, substream);
+	if (!dma)
+		return -EIO;
+
+	ret = sdw_stream_remove_master(&cdns->bus, dma->stream);
+	if (ret < 0)
+		dev_err(dai->dev, "remove master from stream %s failed: %d",
+							dma->stream->name, ret);
+
+	intel_port_cleanup(dma);
+	kfree(dma->port);
+	return ret;
+}
+
+static int intel_pcm_set_sdw_stream(struct snd_soc_dai *dai,
+					void *stream, int direction)
+{
+	return cdns_set_sdw_stream(dai, stream, true, direction);
+}
+
+static int intel_pdm_set_sdw_stream(struct snd_soc_dai *dai,
+					void *stream, int direction)
+{
+	return cdns_set_sdw_stream(dai, stream, false, direction);
+}
+
+static struct snd_soc_dai_ops intel_pcm_dai_ops = {
+	.hw_params = intel_hw_params,
+	.hw_free = intel_hw_free,
+	.shutdown = sdw_cdns_shutdown,
+	.set_sdw_stream = intel_pcm_set_sdw_stream,
+};
+
+static struct snd_soc_dai_ops intel_pdm_dai_ops = {
+	.hw_params = intel_hw_params,
+	.hw_free = intel_hw_free,
+	.shutdown = sdw_cdns_shutdown,
+	.set_sdw_stream = intel_pdm_set_sdw_stream,
+};
+
+static const struct snd_soc_component_driver dai_component = {
+	.name           = "soundwire",
+};
+
+static int intel_create_dai(struct sdw_cdns *cdns,
+			struct snd_soc_dai_driver *dais,
+			enum intel_pdi_type type,
+			u32 num, u32 off, u32 max_ch, bool pcm)
+{
+	int i;
+
+	if (num == 0)
+		return 0;
+
+	 /* TODO: Read supported rates/formats from hardware */
+	for (i = off; i < (off + num); i++) {
+		dais[i].name = kasprintf(GFP_KERNEL, "SDW%d Pin%d",
+					cdns->instance, i);
+		if (!dais[i].name)
+			return -ENOMEM;
+
+		if (type == INTEL_PDI_BD || type == INTEL_PDI_OUT) {
+			dais[i].playback.stream_name = kasprintf(GFP_KERNEL,
+							"SDW%d Tx%d",
+							cdns->instance, i);
+			if (!dais[i].playback.stream_name) {
+				kfree(dais[i].name);
+				return -ENOMEM;
+			}
+
+			dais[i].playback.channels_min = 1;
+			dais[i].playback.channels_max = max_ch;
+			dais[i].playback.rates = SNDRV_PCM_RATE_48000;
+			dais[i].playback.formats = SNDRV_PCM_FMTBIT_S16_LE;
+		}
+
+		if (type == INTEL_PDI_BD || type == INTEL_PDI_IN) {
+			dais[i].capture.stream_name = kasprintf(GFP_KERNEL,
+							"SDW%d Rx%d",
+							cdns->instance, i);
+			if (!dais[i].capture.stream_name) {
+				kfree(dais[i].name);
+				kfree(dais[i].playback.stream_name);
+				return -ENOMEM;
+			}
+
+			dais[i].playback.channels_min = 1;
+			dais[i].playback.channels_max = max_ch;
+			dais[i].capture.rates = SNDRV_PCM_RATE_48000;
+			dais[i].capture.formats = SNDRV_PCM_FMTBIT_S16_LE;
+		}
+
+		dais[i].id = SDW_DAI_ID_RANGE_START + i;
+
+		if (pcm)
+			dais[i].ops = &intel_pcm_dai_ops;
+		else
+			dais[i].ops = &intel_pdm_dai_ops;
+	}
+
+	return 0;
+}
+
+static int intel_register_dai(struct sdw_intel *sdw)
+{
+	struct sdw_cdns *cdns = &sdw->cdns;
+	struct sdw_cdns_streams *stream;
+	struct snd_soc_dai_driver *dais;
+	int num_dai, ret, off = 0;
+
+	/* DAIs are created based on total number of PDIs supported */
+	num_dai = cdns->pcm.num_pdi + cdns->pdm.num_pdi;
+
+	dais = devm_kcalloc(cdns->dev, num_dai, sizeof(*dais), GFP_KERNEL);
+	if (!dais)
+		return -ENOMEM;
+
+	/* Create PCM DAIs */
+	stream = &cdns->pcm;
+
+	ret = intel_create_dai(cdns, dais, INTEL_PDI_IN,
+			stream->num_in, off, stream->num_ch_in, true);
+	if (ret)
+		return ret;
+
+	off += cdns->pcm.num_in;
+	ret = intel_create_dai(cdns, dais, INTEL_PDI_OUT,
+			cdns->pcm.num_out, off, stream->num_ch_out, true);
+	if (ret)
+		return ret;
+
+	off += cdns->pcm.num_out;
+	ret = intel_create_dai(cdns, dais, INTEL_PDI_BD,
+			cdns->pcm.num_bd, off, stream->num_ch_bd, true);
+	if (ret)
+		return ret;
+
+	/* Create PDM DAIs */
+	stream = &cdns->pdm;
+	off += cdns->pcm.num_bd;
+	ret = intel_create_dai(cdns, dais, INTEL_PDI_IN,
+			cdns->pdm.num_in, off, stream->num_ch_in, false);
+	if (ret)
+		return ret;
+
+	off += cdns->pdm.num_in;
+	ret = intel_create_dai(cdns, dais, INTEL_PDI_OUT,
+			cdns->pdm.num_out, off, stream->num_ch_out, false);
+	if (ret)
+		return ret;
+
+	off += cdns->pdm.num_bd;
+	ret = intel_create_dai(cdns, dais, INTEL_PDI_BD,
+			cdns->pdm.num_bd, off, stream->num_ch_bd, false);
+	if (ret)
+		return ret;
+
+	return snd_soc_register_component(cdns->dev, &dai_component,
+				dais, num_dai);
+}
+
 static int intel_prop_read(struct sdw_bus *bus)
 {
 	/* Initialize with default handler to read all DisCo properties */
@@ -252,11 +744,20 @@ static int intel_prop_read(struct sdw_bus *bus)
 	return 0;
 }
 
+static struct sdw_master_ops sdw_intel_ops = {
+	.read_prop = sdw_master_read_prop,
+	.xfer_msg = cdns_xfer_msg,
+	.xfer_msg_defer = cdns_xfer_msg_defer,
+	.reset_page_addr = cdns_reset_page_addr,
+	.set_bus_conf = cdns_bus_conf,
+};
+
 /*
  * probe and init
  */
 static int intel_probe(struct platform_device *pdev)
 {
+	struct sdw_cdns_stream_config config;
 	struct sdw_intel *sdw;
 	int ret;
 
@@ -276,8 +777,11 @@ static int intel_probe(struct platform_device *pdev)
 	sdw_cdns_probe(&sdw->cdns);
 
 	/* Set property read ops */
-	sdw_cdns_master_ops.read_prop = intel_prop_read;
-	sdw->cdns.bus.ops = &sdw_cdns_master_ops;
+	sdw_intel_ops.read_prop = intel_prop_read;
+	sdw->cdns.bus.ops = &sdw_intel_ops;
+
+	sdw_intel_ops.read_prop = intel_prop_read;
+	sdw->cdns.bus.ops = &sdw_intel_ops;
 
 	platform_set_drvdata(pdev, sdw);
 
@@ -296,9 +800,15 @@ static int intel_probe(struct platform_device *pdev)
 		goto err_init;
 
 	ret = sdw_cdns_enable_interrupt(&sdw->cdns);
+
+	/* Read the PDI config and initialize cadence PDI */
+	intel_pdi_init(sdw, &config);
+	ret = sdw_cdns_pdi_init(&sdw->cdns, config);
 	if (ret)
 		goto err_init;
 
+	intel_pdi_ch_update(sdw);
+
 	/* Acquire IRQ */
 	ret = request_threaded_irq(sdw->res->irq, sdw_cdns_irq,
 			sdw_cdns_thread, IRQF_SHARED, KBUILD_MODNAME,
@@ -309,8 +819,18 @@ static int intel_probe(struct platform_device *pdev)
 		goto err_init;
 	}
 
+	/* Register DAIs */
+	ret = intel_register_dai(sdw);
+	if (ret) {
+		dev_err(sdw->cdns.dev, "DAI registration failed: %d", ret);
+		snd_soc_unregister_component(sdw->cdns.dev);
+		goto err_dai;
+	}
+
 	return 0;
 
+err_dai:
+	free_irq(sdw->res->irq, sdw);
 err_init:
 	sdw_delete_bus_master(&sdw->cdns.bus);
 err_master_reg:
@@ -324,6 +844,7 @@ static int intel_remove(struct platform_device *pdev)
 	sdw = platform_get_drvdata(pdev);
 
 	free_irq(sdw->res->irq, sdw);
+	snd_soc_unregister_component(sdw->cdns.dev);
 	sdw_delete_bus_master(&sdw->cdns.bus);
 
 	return 0;
diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h
index ffa30d9535a2..c1a5bac6212e 100644
--- a/drivers/soundwire/intel.h
+++ b/drivers/soundwire/intel.h
@@ -10,6 +10,8 @@
  * @shim: Audio shim pointer
  * @alh: ALH (Audio Link Hub) pointer
  * @irq: Interrupt line
+ * @ops: Shim callback ops
+ * @arg: Shim callback ops argument
  *
  * This is set as pdata for each link instance.
  */
@@ -18,6 +20,8 @@ struct sdw_intel_link_res {
 	void __iomem *shim;
 	void __iomem *alh;
 	int irq;
+	const struct sdw_intel_ops *ops;
+	void *arg;
 };
 
 #endif /* __SDW_INTEL_LOCAL_H */
diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c
index 6f2bb99526f2..d1ea6b4d0ad3 100644
--- a/drivers/soundwire/intel_init.c
+++ b/drivers/soundwire/intel_init.c
@@ -111,6 +111,9 @@ static struct sdw_intel_ctx
 		link->res.shim = res->mmio_base + SDW_SHIM_BASE;
 		link->res.alh = res->mmio_base + SDW_ALH_BASE;
 
+		link->res.ops = res->ops;
+		link->res.arg = res->arg;
+
 		memset(&pdevinfo, 0, sizeof(pdevinfo));
 
 		pdevinfo.parent = res->parent;
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
new file mode 100644
index 000000000000..8974a0fcda1b
--- /dev/null
+++ b/drivers/soundwire/stream.c
@@ -0,0 +1,1479 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+// Copyright(c) 2015-18 Intel Corporation.
+
+/*
+ *  stream.c - SoundWire Bus stream operations.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+#include <linux/soundwire/sdw_registers.h>
+#include <linux/soundwire/sdw.h>
+#include "bus.h"
+
+/*
+ * Array of supported rows and columns as per MIPI SoundWire Specification 1.1
+ *
+ * The rows are arranged as per the array index value programmed
+ * in register. The index 15 has dummy value 0 in order to fill hole.
+ */
+int rows[SDW_FRAME_ROWS] = {48, 50, 60, 64, 75, 80, 125, 147,
+			96, 100, 120, 128, 150, 160, 250, 0,
+			192, 200, 240, 256, 72, 144, 90, 180};
+
+int cols[SDW_FRAME_COLS] = {2, 4, 6, 8, 10, 12, 14, 16};
+
+static int sdw_find_col_index(int col)
+{
+	int i;
+
+	for (i = 0; i < SDW_FRAME_COLS; i++) {
+		if (cols[i] == col)
+			return i;
+	}
+
+	pr_warn("Requested column not found, selecting lowest column no: 2\n");
+	return 0;
+}
+
+static int sdw_find_row_index(int row)
+{
+	int i;
+
+	for (i = 0; i < SDW_FRAME_ROWS; i++) {
+		if (rows[i] == row)
+			return i;
+	}
+
+	pr_warn("Requested row not found, selecting lowest row no: 48\n");
+	return 0;
+}
+static int _sdw_program_slave_port_params(struct sdw_bus *bus,
+				struct sdw_slave *slave,
+				struct sdw_transport_params *t_params,
+				enum sdw_dpn_type type)
+{
+	u32 addr1, addr2, addr3, addr4;
+	int ret;
+	u16 wbuf;
+
+	if (bus->params.next_bank) {
+		addr1 = SDW_DPN_OFFSETCTRL2_B1(t_params->port_num);
+		addr2 = SDW_DPN_BLOCKCTRL3_B1(t_params->port_num);
+		addr3 = SDW_DPN_SAMPLECTRL2_B1(t_params->port_num);
+		addr4 = SDW_DPN_HCTRL_B1(t_params->port_num);
+	} else {
+		addr1 = SDW_DPN_OFFSETCTRL2_B0(t_params->port_num);
+		addr2 = SDW_DPN_BLOCKCTRL3_B0(t_params->port_num);
+		addr3 = SDW_DPN_SAMPLECTRL2_B0(t_params->port_num);
+		addr4 = SDW_DPN_HCTRL_B0(t_params->port_num);
+	}
+
+	/* Program DPN_OffsetCtrl2 registers */
+	ret = sdw_write(slave, addr1, t_params->offset2);
+	if (ret < 0) {
+		dev_err(bus->dev, "DPN_OffsetCtrl2 register write failed");
+		return ret;
+	}
+
+	/* Program DPN_BlockCtrl3 register */
+	ret = sdw_write(slave, addr2, t_params->blk_pkg_mode);
+	if (ret < 0) {
+		dev_err(bus->dev, "DPN_BlockCtrl3 register write failed");
+		return ret;
+	}
+
+	/*
+	 * Data ports are FULL, SIMPLE and REDUCED. This function handles
+	 * FULL and REDUCED only and and beyond this point only FULL is
+	 * handled, so bail out if we are not FULL data port type
+	 */
+	if (type != SDW_DPN_FULL)
+		return ret;
+
+	/* Program DPN_SampleCtrl2 register */
+	wbuf = (t_params->sample_interval - 1);
+	wbuf &= SDW_DPN_SAMPLECTRL_HIGH;
+	wbuf >>= SDW_REG_SHIFT(SDW_DPN_SAMPLECTRL_HIGH);
+
+	ret = sdw_write(slave, addr3, wbuf);
+	if (ret < 0) {
+		dev_err(bus->dev, "DPN_SampleCtrl2 register write failed");
+		return ret;
+	}
+
+	/* Program DPN_HCtrl register */
+	wbuf = t_params->hstart;
+	wbuf <<= SDW_REG_SHIFT(SDW_DPN_HCTRL_HSTART);
+	wbuf |= t_params->hstop;
+
+	ret = sdw_write(slave, addr4, wbuf);
+	if (ret < 0)
+		dev_err(bus->dev, "DPN_HCtrl register write failed");
+
+	return ret;
+}
+
+static int sdw_program_slave_port_params(struct sdw_bus *bus,
+			struct sdw_slave_runtime *s_rt,
+			struct sdw_port_runtime *p_rt)
+{
+	struct sdw_transport_params *t_params = &p_rt->transport_params;
+	struct sdw_port_params *p_params = &p_rt->port_params;
+	struct sdw_slave_prop *slave_prop = &s_rt->slave->prop;
+	u32 addr1, addr2, addr3, addr4, addr5, addr6;
+	struct sdw_dpn_prop *dpn_prop;
+	int ret;
+	u8 wbuf;
+
+	dpn_prop = sdw_get_slave_dpn_prop(s_rt->slave,
+					s_rt->direction,
+					t_params->port_num);
+	if (!dpn_prop)
+		return -EINVAL;
+
+	addr1 = SDW_DPN_PORTCTRL(t_params->port_num);
+	addr2 = SDW_DPN_BLOCKCTRL1(t_params->port_num);
+
+	if (bus->params.next_bank) {
+		addr3 = SDW_DPN_SAMPLECTRL1_B1(t_params->port_num);
+		addr4 = SDW_DPN_OFFSETCTRL1_B1(t_params->port_num);
+		addr5 = SDW_DPN_BLOCKCTRL2_B1(t_params->port_num);
+		addr6 = SDW_DPN_LANECTRL_B1(t_params->port_num);
+
+	} else {
+		addr3 = SDW_DPN_SAMPLECTRL1_B0(t_params->port_num);
+		addr4 = SDW_DPN_OFFSETCTRL1_B0(t_params->port_num);
+		addr5 = SDW_DPN_BLOCKCTRL2_B0(t_params->port_num);
+		addr6 = SDW_DPN_LANECTRL_B0(t_params->port_num);
+	}
+
+	/* Program DPN_PortCtrl register */
+	wbuf = p_params->data_mode << SDW_REG_SHIFT(SDW_DPN_PORTCTRL_DATAMODE);
+	wbuf |= p_params->flow_mode;
+
+	ret = sdw_update(s_rt->slave, addr1, 0xF, wbuf);
+	if (ret < 0) {
+		dev_err(&s_rt->slave->dev,
+			"DPN_PortCtrl register write failed for port %d",
+			t_params->port_num);
+		return ret;
+	}
+
+	/* Program DPN_BlockCtrl1 register */
+	ret = sdw_write(s_rt->slave, addr2, (p_params->bps - 1));
+	if (ret < 0) {
+		dev_err(&s_rt->slave->dev,
+			"DPN_BlockCtrl1 register write failed for port %d",
+			t_params->port_num);
+		return ret;
+	}
+
+	/* Program DPN_SampleCtrl1 register */
+	wbuf = (t_params->sample_interval - 1) & SDW_DPN_SAMPLECTRL_LOW;
+	ret = sdw_write(s_rt->slave, addr3, wbuf);
+	if (ret < 0) {
+		dev_err(&s_rt->slave->dev,
+			"DPN_SampleCtrl1 register write failed for port %d",
+			t_params->port_num);
+		return ret;
+	}
+
+	/* Program DPN_OffsetCtrl1 registers */
+	ret = sdw_write(s_rt->slave, addr4, t_params->offset1);
+	if (ret < 0) {
+		dev_err(&s_rt->slave->dev,
+			"DPN_OffsetCtrl1 register write failed for port %d",
+			t_params->port_num);
+		return ret;
+	}
+
+	/* Program DPN_BlockCtrl2 register*/
+	if (t_params->blk_grp_ctrl_valid) {
+		ret = sdw_write(s_rt->slave, addr5, t_params->blk_grp_ctrl);
+		if (ret < 0) {
+			dev_err(&s_rt->slave->dev,
+				"DPN_BlockCtrl2 reg write failed for port %d",
+				t_params->port_num);
+			return ret;
+		}
+	}
+
+	/* program DPN_LaneCtrl register */
+	if (slave_prop->lane_control_support) {
+		ret = sdw_write(s_rt->slave, addr6, t_params->lane_ctrl);
+		if (ret < 0) {
+			dev_err(&s_rt->slave->dev,
+				"DPN_LaneCtrl register write failed for port %d",
+				t_params->port_num);
+			return ret;
+		}
+	}
+
+	if (dpn_prop->type != SDW_DPN_SIMPLE) {
+		ret = _sdw_program_slave_port_params(bus, s_rt->slave,
+						t_params, dpn_prop->type);
+		if (ret < 0)
+			dev_err(&s_rt->slave->dev,
+				"Transport reg write failed for port: %d",
+				t_params->port_num);
+	}
+
+	return ret;
+}
+
+static int sdw_program_master_port_params(struct sdw_bus *bus,
+		struct sdw_port_runtime *p_rt)
+{
+	int ret;
+
+	/*
+	 * we need to set transport and port parameters for the port.
+	 * Transport parameters refers to the smaple interval, offsets and
+	 * hstart/stop etc of the data. Port parameters refers to word
+	 * length, flow mode etc of the port
+	 */
+	ret = bus->port_ops->dpn_set_port_transport_params(bus,
+					&p_rt->transport_params,
+					bus->params.next_bank);
+	if (ret < 0)
+		return ret;
+
+	return bus->port_ops->dpn_set_port_params(bus,
+				&p_rt->port_params,
+				bus->params.next_bank);
+}
+
+/**
+ * sdw_program_port_params() - Programs transport parameters of Master(s)
+ * and Slave(s)
+ *
+ * @m_rt: Master stream runtime
+ */
+static int sdw_program_port_params(struct sdw_master_runtime *m_rt)
+{
+	struct sdw_slave_runtime *s_rt = NULL;
+	struct sdw_bus *bus = m_rt->bus;
+	struct sdw_port_runtime *p_rt;
+	int ret = 0;
+
+	/* Program transport & port parameters for Slave(s) */
+	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+		list_for_each_entry(p_rt, &s_rt->port_list, port_node) {
+			ret = sdw_program_slave_port_params(bus, s_rt, p_rt);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	/* Program transport & port parameters for Master(s) */
+	list_for_each_entry(p_rt, &m_rt->port_list, port_node) {
+		ret = sdw_program_master_port_params(bus, p_rt);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * sdw_enable_disable_slave_ports: Enable/disable slave data port
+ *
+ * @bus: bus instance
+ * @s_rt: slave runtime
+ * @p_rt: port runtime
+ * @en: enable or disable operation
+ *
+ * This function only sets the enable/disable bits in the relevant bank, the
+ * actual enable/disable is done with a bank switch
+ */
+static int sdw_enable_disable_slave_ports(struct sdw_bus *bus,
+				struct sdw_slave_runtime *s_rt,
+				struct sdw_port_runtime *p_rt, bool en)
+{
+	struct sdw_transport_params *t_params = &p_rt->transport_params;
+	u32 addr;
+	int ret;
+
+	if (bus->params.next_bank)
+		addr = SDW_DPN_CHANNELEN_B1(p_rt->num);
+	else
+		addr = SDW_DPN_CHANNELEN_B0(p_rt->num);
+
+	/*
+	 * Since bus doesn't support sharing a port across two streams,
+	 * it is safe to reset this register
+	 */
+	if (en)
+		ret = sdw_update(s_rt->slave, addr, 0xFF, p_rt->ch_mask);
+	else
+		ret = sdw_update(s_rt->slave, addr, 0xFF, 0x0);
+
+	if (ret < 0)
+		dev_err(&s_rt->slave->dev,
+			"Slave chn_en reg write failed:%d port:%d",
+			ret, t_params->port_num);
+
+	return ret;
+}
+
+static int sdw_enable_disable_master_ports(struct sdw_master_runtime *m_rt,
+			struct sdw_port_runtime *p_rt, bool en)
+{
+	struct sdw_transport_params *t_params = &p_rt->transport_params;
+	struct sdw_bus *bus = m_rt->bus;
+	struct sdw_enable_ch enable_ch;
+	int ret = 0;
+
+	enable_ch.port_num = p_rt->num;
+	enable_ch.ch_mask = p_rt->ch_mask;
+	enable_ch.enable = en;
+
+	/* Perform Master port channel(s) enable/disable */
+	if (bus->port_ops->dpn_port_enable_ch) {
+		ret = bus->port_ops->dpn_port_enable_ch(bus,
+				&enable_ch, bus->params.next_bank);
+		if (ret < 0) {
+			dev_err(bus->dev,
+				"Master chn_en write failed:%d port:%d",
+				ret, t_params->port_num);
+			return ret;
+		}
+	} else {
+		dev_err(bus->dev,
+			"dpn_port_enable_ch not supported, %s failed\n",
+			en ? "enable" : "disable");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * sdw_enable_disable_ports() - Enable/disable port(s) for Master and
+ * Slave(s)
+ *
+ * @m_rt: Master stream runtime
+ * @en: mode (enable/disable)
+ */
+static int sdw_enable_disable_ports(struct sdw_master_runtime *m_rt, bool en)
+{
+	struct sdw_port_runtime *s_port, *m_port;
+	struct sdw_slave_runtime *s_rt = NULL;
+	int ret = 0;
+
+	/* Enable/Disable Slave port(s) */
+	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+		list_for_each_entry(s_port, &s_rt->port_list, port_node) {
+			ret = sdw_enable_disable_slave_ports(m_rt->bus, s_rt,
+							s_port, en);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	/* Enable/Disable Master port(s) */
+	list_for_each_entry(m_port, &m_rt->port_list, port_node) {
+		ret = sdw_enable_disable_master_ports(m_rt, m_port, en);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int sdw_do_port_prep(struct sdw_slave_runtime *s_rt,
+		struct sdw_prepare_ch prep_ch, enum sdw_port_prep_ops cmd)
+{
+	const struct sdw_slave_ops *ops = s_rt->slave->ops;
+	int ret;
+
+	if (ops->port_prep) {
+		ret = ops->port_prep(s_rt->slave, &prep_ch, cmd);
+		if (ret < 0) {
+			dev_err(&s_rt->slave->dev,
+				"Slave Port Prep cmd %d failed: %d", cmd, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus,
+			struct sdw_slave_runtime *s_rt,
+			struct sdw_port_runtime *p_rt, bool prep)
+{
+	struct completion *port_ready = NULL;
+	struct sdw_dpn_prop *dpn_prop;
+	struct sdw_prepare_ch prep_ch;
+	unsigned int time_left;
+	bool intr = false;
+	int ret = 0, val;
+	u32 addr;
+
+	prep_ch.num = p_rt->num;
+	prep_ch.ch_mask = p_rt->ch_mask;
+
+	dpn_prop = sdw_get_slave_dpn_prop(s_rt->slave,
+					s_rt->direction,
+					prep_ch.num);
+	if (!dpn_prop) {
+		dev_err(bus->dev,
+			"Slave Port:%d properties not found", prep_ch.num);
+		return -EINVAL;
+	}
+
+	prep_ch.prepare = prep;
+
+	prep_ch.bank = bus->params.next_bank;
+
+	if (dpn_prop->device_interrupts || !dpn_prop->simple_ch_prep_sm)
+		intr = true;
+
+	/*
+	 * Enable interrupt before Port prepare.
+	 * For Port de-prepare, it is assumed that port
+	 * was prepared earlier
+	 */
+	if (prep && intr) {
+		ret = sdw_configure_dpn_intr(s_rt->slave, p_rt->num, prep,
+						dpn_prop->device_interrupts);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Inform slave about the impending port prepare */
+	sdw_do_port_prep(s_rt, prep_ch, SDW_OPS_PORT_PRE_PREP);
+
+	/* Prepare Slave port implementing CP_SM */
+	if (!dpn_prop->simple_ch_prep_sm) {
+		addr = SDW_DPN_PREPARECTRL(p_rt->num);
+
+		if (prep)
+			ret = sdw_update(s_rt->slave, addr,
+					0xFF, p_rt->ch_mask);
+		else
+			ret = sdw_update(s_rt->slave, addr, 0xFF, 0x0);
+
+		if (ret < 0) {
+			dev_err(&s_rt->slave->dev,
+				"Slave prep_ctrl reg write failed");
+			return ret;
+		}
+
+		/* Wait for completion on port ready */
+		port_ready = &s_rt->slave->port_ready[prep_ch.num];
+		time_left = wait_for_completion_timeout(port_ready,
+				msecs_to_jiffies(dpn_prop->ch_prep_timeout));
+
+		val = sdw_read(s_rt->slave, SDW_DPN_PREPARESTATUS(p_rt->num));
+		val &= p_rt->ch_mask;
+		if (!time_left || val) {
+			dev_err(&s_rt->slave->dev,
+				"Chn prep failed for port:%d", prep_ch.num);
+			return -ETIMEDOUT;
+		}
+	}
+
+	/* Inform slaves about ports prepared */
+	sdw_do_port_prep(s_rt, prep_ch, SDW_OPS_PORT_POST_PREP);
+
+	/* Disable interrupt after Port de-prepare */
+	if (!prep && intr)
+		ret = sdw_configure_dpn_intr(s_rt->slave, p_rt->num, prep,
+						dpn_prop->device_interrupts);
+
+	return ret;
+}
+
+static int sdw_prep_deprep_master_ports(struct sdw_master_runtime *m_rt,
+				struct sdw_port_runtime *p_rt, bool prep)
+{
+	struct sdw_transport_params *t_params = &p_rt->transport_params;
+	struct sdw_bus *bus = m_rt->bus;
+	const struct sdw_master_port_ops *ops = bus->port_ops;
+	struct sdw_prepare_ch prep_ch;
+	int ret = 0;
+
+	prep_ch.num = p_rt->num;
+	prep_ch.ch_mask = p_rt->ch_mask;
+	prep_ch.prepare = prep; /* Prepare/De-prepare */
+	prep_ch.bank = bus->params.next_bank;
+
+	/* Pre-prepare/Pre-deprepare port(s) */
+	if (ops->dpn_port_prep) {
+		ret = ops->dpn_port_prep(bus, &prep_ch);
+		if (ret < 0) {
+			dev_err(bus->dev, "Port prepare failed for port:%d",
+					t_params->port_num);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * sdw_prep_deprep_ports() - Prepare/De-prepare port(s) for Master(s) and
+ * Slave(s)
+ *
+ * @m_rt: Master runtime handle
+ * @prep: Prepare or De-prepare
+ */
+static int sdw_prep_deprep_ports(struct sdw_master_runtime *m_rt, bool prep)
+{
+	struct sdw_slave_runtime *s_rt = NULL;
+	struct sdw_port_runtime *p_rt;
+	int ret = 0;
+
+	/* Prepare/De-prepare Slave port(s) */
+	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+		list_for_each_entry(p_rt, &s_rt->port_list, port_node) {
+			ret = sdw_prep_deprep_slave_ports(m_rt->bus, s_rt,
+							p_rt, prep);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	/* Prepare/De-prepare Master port(s) */
+	list_for_each_entry(p_rt, &m_rt->port_list, port_node) {
+		ret = sdw_prep_deprep_master_ports(m_rt, p_rt, prep);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
+}
+
+/**
+ * sdw_notify_config() - Notify bus configuration
+ *
+ * @m_rt: Master runtime handle
+ *
+ * This function notifies the Master(s) and Slave(s) of the
+ * new bus configuration.
+ */
+static int sdw_notify_config(struct sdw_master_runtime *m_rt)
+{
+	struct sdw_slave_runtime *s_rt;
+	struct sdw_bus *bus = m_rt->bus;
+	struct sdw_slave *slave;
+	int ret = 0;
+
+	if (bus->ops->set_bus_conf) {
+		ret = bus->ops->set_bus_conf(bus, &bus->params);
+		if (ret < 0)
+			return ret;
+	}
+
+	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+		slave = s_rt->slave;
+
+		if (slave->ops->bus_config) {
+			ret = slave->ops->bus_config(slave, &bus->params);
+			if (ret < 0)
+				dev_err(bus->dev, "Notify Slave: %d failed",
+								slave->dev_num);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * sdw_program_params() - Program transport and port parameters for Master(s)
+ * and Slave(s)
+ *
+ * @bus: SDW bus instance
+ */
+static int sdw_program_params(struct sdw_bus *bus)
+{
+	struct sdw_master_runtime *m_rt = NULL;
+	int ret = 0;
+
+	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+		ret = sdw_program_port_params(m_rt);
+		if (ret < 0) {
+			dev_err(bus->dev,
+				"Program transport params failed: %d", ret);
+			return ret;
+		}
+
+		ret = sdw_notify_config(m_rt);
+		if (ret < 0) {
+			dev_err(bus->dev, "Notify bus config failed: %d", ret);
+			return ret;
+		}
+
+		/* Enable port(s) on alternate bank for all active streams */
+		if (m_rt->stream->state != SDW_STREAM_ENABLED)
+			continue;
+
+		ret = sdw_enable_disable_ports(m_rt, true);
+		if (ret < 0) {
+			dev_err(bus->dev, "Enable channel failed: %d", ret);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+static int sdw_bank_switch(struct sdw_bus *bus)
+{
+	int col_index, row_index;
+	struct sdw_msg *wr_msg;
+	u8 *wbuf = NULL;
+	int ret = 0;
+	u16 addr;
+
+	wr_msg = kzalloc(sizeof(*wr_msg), GFP_KERNEL);
+	if (!wr_msg)
+		return -ENOMEM;
+
+	wbuf = kzalloc(sizeof(*wbuf), GFP_KERNEL);
+	if (!wbuf) {
+		ret = -ENOMEM;
+		goto error_1;
+	}
+
+	/* Get row and column index to program register */
+	col_index = sdw_find_col_index(bus->params.col);
+	row_index = sdw_find_row_index(bus->params.row);
+	wbuf[0] = col_index | (row_index << 3);
+
+	if (bus->params.next_bank)
+		addr = SDW_SCP_FRAMECTRL_B1;
+	else
+		addr = SDW_SCP_FRAMECTRL_B0;
+
+	sdw_fill_msg(wr_msg, NULL, addr, 1, SDW_BROADCAST_DEV_NUM,
+					SDW_MSG_FLAG_WRITE, wbuf);
+	wr_msg->ssp_sync = true;
+
+	ret = sdw_transfer(bus, wr_msg);
+	if (ret < 0) {
+		dev_err(bus->dev, "Slave frame_ctrl reg write failed");
+		goto error;
+	}
+
+	kfree(wr_msg);
+	kfree(wbuf);
+	bus->defer_msg.msg = NULL;
+	bus->params.curr_bank = !bus->params.curr_bank;
+	bus->params.next_bank = !bus->params.next_bank;
+
+	return 0;
+
+error:
+	kfree(wbuf);
+error_1:
+	kfree(wr_msg);
+	return ret;
+}
+
+static int do_bank_switch(struct sdw_stream_runtime *stream)
+{
+	struct sdw_master_runtime *m_rt = stream->m_rt;
+	const struct sdw_master_ops *ops;
+	struct sdw_bus *bus = m_rt->bus;
+	int ret = 0;
+
+	ops = bus->ops;
+
+	/* Pre-bank switch */
+	if (ops->pre_bank_switch) {
+		ret = ops->pre_bank_switch(bus);
+		if (ret < 0) {
+			dev_err(bus->dev, "Pre bank switch op failed: %d", ret);
+			return ret;
+		}
+	}
+
+	/* Bank switch */
+	ret = sdw_bank_switch(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Bank switch failed: %d", ret);
+		return ret;
+	}
+
+	/* Post-bank switch */
+	if (ops->post_bank_switch) {
+		ret = ops->post_bank_switch(bus);
+		if (ret < 0) {
+			dev_err(bus->dev,
+					"Post bank switch op failed: %d", ret);
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * sdw_release_stream() - Free the assigned stream runtime
+ *
+ * @stream: SoundWire stream runtime
+ *
+ * sdw_release_stream should be called only once per stream
+ */
+void sdw_release_stream(struct sdw_stream_runtime *stream)
+{
+	kfree(stream);
+}
+EXPORT_SYMBOL(sdw_release_stream);
+
+/**
+ * sdw_alloc_stream() - Allocate and return stream runtime
+ *
+ * @stream_name: SoundWire stream name
+ *
+ * Allocates a SoundWire stream runtime instance.
+ * sdw_alloc_stream should be called only once per stream. Typically
+ * invoked from ALSA/ASoC machine/platform driver.
+ */
+struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name)
+{
+	struct sdw_stream_runtime *stream;
+
+	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
+	if (!stream)
+		return NULL;
+
+	stream->name = stream_name;
+	stream->state = SDW_STREAM_ALLOCATED;
+
+	return stream;
+}
+EXPORT_SYMBOL(sdw_alloc_stream);
+
+/**
+ * sdw_alloc_master_rt() - Allocates and initialize Master runtime handle
+ *
+ * @bus: SDW bus instance
+ * @stream_config: Stream configuration
+ * @stream: Stream runtime handle.
+ *
+ * This function is to be called with bus_lock held.
+ */
+static struct sdw_master_runtime
+*sdw_alloc_master_rt(struct sdw_bus *bus,
+			struct sdw_stream_config *stream_config,
+			struct sdw_stream_runtime *stream)
+{
+	struct sdw_master_runtime *m_rt;
+
+	m_rt = stream->m_rt;
+
+	/*
+	 * check if Master is already allocated (as a result of Slave adding
+	 * it first), if so skip allocation and go to configure
+	 */
+	if (m_rt)
+		goto stream_config;
+
+	m_rt = kzalloc(sizeof(*m_rt), GFP_KERNEL);
+	if (!m_rt)
+		return NULL;
+
+	/* Initialization of Master runtime handle */
+	INIT_LIST_HEAD(&m_rt->port_list);
+	INIT_LIST_HEAD(&m_rt->slave_rt_list);
+	stream->m_rt = m_rt;
+
+	list_add_tail(&m_rt->bus_node, &bus->m_rt_list);
+
+stream_config:
+	m_rt->ch_count = stream_config->ch_count;
+	m_rt->bus = bus;
+	m_rt->stream = stream;
+	m_rt->direction = stream_config->direction;
+
+	return m_rt;
+}
+
+/**
+ * sdw_alloc_slave_rt() - Allocate and initialize Slave runtime handle.
+ *
+ * @slave: Slave handle
+ * @stream_config: Stream configuration
+ * @stream: Stream runtime handle
+ *
+ * This function is to be called with bus_lock held.
+ */
+static struct sdw_slave_runtime
+*sdw_alloc_slave_rt(struct sdw_slave *slave,
+			struct sdw_stream_config *stream_config,
+			struct sdw_stream_runtime *stream)
+{
+	struct sdw_slave_runtime *s_rt = NULL;
+
+	s_rt = kzalloc(sizeof(*s_rt), GFP_KERNEL);
+	if (!s_rt)
+		return NULL;
+
+	INIT_LIST_HEAD(&s_rt->port_list);
+	s_rt->ch_count = stream_config->ch_count;
+	s_rt->direction = stream_config->direction;
+	s_rt->slave = slave;
+
+	return s_rt;
+}
+
+static void sdw_master_port_release(struct sdw_bus *bus,
+			struct sdw_master_runtime *m_rt)
+{
+	struct sdw_port_runtime *p_rt, *_p_rt;
+
+	list_for_each_entry_safe(p_rt, _p_rt,
+			&m_rt->port_list, port_node) {
+		list_del(&p_rt->port_node);
+		kfree(p_rt);
+	}
+}
+
+static void sdw_slave_port_release(struct sdw_bus *bus,
+			struct sdw_slave *slave,
+			struct sdw_stream_runtime *stream)
+{
+	struct sdw_port_runtime *p_rt, *_p_rt;
+	struct sdw_master_runtime *m_rt = stream->m_rt;
+	struct sdw_slave_runtime *s_rt;
+
+	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+		if (s_rt->slave != slave)
+			continue;
+
+		list_for_each_entry_safe(p_rt, _p_rt,
+				&s_rt->port_list, port_node) {
+			list_del(&p_rt->port_node);
+			kfree(p_rt);
+		}
+	}
+}
+
+/**
+ * sdw_release_slave_stream() - Free Slave(s) runtime handle
+ *
+ * @slave: Slave handle.
+ * @stream: Stream runtime handle.
+ *
+ * This function is to be called with bus_lock held.
+ */
+static void sdw_release_slave_stream(struct sdw_slave *slave,
+			struct sdw_stream_runtime *stream)
+{
+	struct sdw_slave_runtime *s_rt, *_s_rt;
+	struct sdw_master_runtime *m_rt = stream->m_rt;
+
+	/* Retrieve Slave runtime handle */
+	list_for_each_entry_safe(s_rt, _s_rt,
+			&m_rt->slave_rt_list, m_rt_node) {
+
+		if (s_rt->slave == slave) {
+			list_del(&s_rt->m_rt_node);
+			kfree(s_rt);
+			return;
+		}
+	}
+}
+
+/**
+ * sdw_release_master_stream() - Free Master runtime handle
+ *
+ * @stream: Stream runtime handle.
+ *
+ * This function is to be called with bus_lock held
+ * It frees the Master runtime handle and associated Slave(s) runtime
+ * handle. If this is called first then sdw_release_slave_stream() will have
+ * no effect as Slave(s) runtime handle would already be freed up.
+ */
+static void sdw_release_master_stream(struct sdw_stream_runtime *stream)
+{
+	struct sdw_master_runtime *m_rt = stream->m_rt;
+	struct sdw_slave_runtime *s_rt, *_s_rt;
+
+	list_for_each_entry_safe(s_rt, _s_rt,
+			&m_rt->slave_rt_list, m_rt_node)
+		sdw_stream_remove_slave(s_rt->slave, stream);
+
+	list_del(&m_rt->bus_node);
+}
+
+/**
+ * sdw_stream_remove_master() - Remove master from sdw_stream
+ *
+ * @bus: SDW Bus instance
+ * @stream: SoundWire stream
+ *
+ * This removes and frees port_rt and master_rt from a stream
+ */
+int sdw_stream_remove_master(struct sdw_bus *bus,
+		struct sdw_stream_runtime *stream)
+{
+	mutex_lock(&bus->bus_lock);
+
+	sdw_release_master_stream(stream);
+	sdw_master_port_release(bus, stream->m_rt);
+	stream->state = SDW_STREAM_RELEASED;
+	kfree(stream->m_rt);
+	stream->m_rt = NULL;
+
+	mutex_unlock(&bus->bus_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(sdw_stream_remove_master);
+
+/**
+ * sdw_stream_remove_slave() - Remove slave from sdw_stream
+ *
+ * @slave: SDW Slave instance
+ * @stream: SoundWire stream
+ *
+ * This removes and frees port_rt and slave_rt from a stream
+ */
+int sdw_stream_remove_slave(struct sdw_slave *slave,
+		struct sdw_stream_runtime *stream)
+{
+	mutex_lock(&slave->bus->bus_lock);
+
+	sdw_slave_port_release(slave->bus, slave, stream);
+	sdw_release_slave_stream(slave, stream);
+
+	mutex_unlock(&slave->bus->bus_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(sdw_stream_remove_slave);
+
+/**
+ * sdw_config_stream() - Configure the allocated stream
+ *
+ * @dev: SDW device
+ * @stream: SoundWire stream
+ * @stream_config: Stream configuration for audio stream
+ * @is_slave: is API called from Slave or Master
+ *
+ * This function is to be called with bus_lock held.
+ */
+static int sdw_config_stream(struct device *dev,
+		struct sdw_stream_runtime *stream,
+		struct sdw_stream_config *stream_config, bool is_slave)
+{
+	/*
+	 * Update the stream rate, channel and bps based on data
+	 * source. For more than one data source (multilink),
+	 * match the rate, bps, stream type and increment number of channels.
+	 *
+	 * If rate/bps is zero, it means the values are not set, so skip
+	 * comparison and allow the value to be set and stored in stream
+	 */
+	if (stream->params.rate &&
+			stream->params.rate != stream_config->frame_rate) {
+		dev_err(dev, "rate not matching, stream:%s", stream->name);
+		return -EINVAL;
+	}
+
+	if (stream->params.bps &&
+			stream->params.bps != stream_config->bps) {
+		dev_err(dev, "bps not matching, stream:%s", stream->name);
+		return -EINVAL;
+	}
+
+	stream->type = stream_config->type;
+	stream->params.rate = stream_config->frame_rate;
+	stream->params.bps = stream_config->bps;
+
+	/* TODO: Update this check during Device-device support */
+	if (is_slave)
+		stream->params.ch_count += stream_config->ch_count;
+
+	return 0;
+}
+
+static int sdw_is_valid_port_range(struct device *dev,
+				struct sdw_port_runtime *p_rt)
+{
+	if (!SDW_VALID_PORT_RANGE(p_rt->num)) {
+		dev_err(dev,
+			"SoundWire: Invalid port number :%d", p_rt->num);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct sdw_port_runtime *sdw_port_alloc(struct device *dev,
+				struct sdw_port_config *port_config,
+				int port_index)
+{
+	struct sdw_port_runtime *p_rt;
+
+	p_rt = kzalloc(sizeof(*p_rt), GFP_KERNEL);
+	if (!p_rt)
+		return NULL;
+
+	p_rt->ch_mask = port_config[port_index].ch_mask;
+	p_rt->num = port_config[port_index].num;
+
+	return p_rt;
+}
+
+static int sdw_master_port_config(struct sdw_bus *bus,
+			struct sdw_master_runtime *m_rt,
+			struct sdw_port_config *port_config,
+			unsigned int num_ports)
+{
+	struct sdw_port_runtime *p_rt;
+	int i;
+
+	/* Iterate for number of ports to perform initialization */
+	for (i = 0; i < num_ports; i++) {
+		p_rt = sdw_port_alloc(bus->dev, port_config, i);
+		if (!p_rt)
+			return -ENOMEM;
+
+		/*
+		 * TODO: Check port capabilities for requested
+		 * configuration (audio mode support)
+		 */
+
+		list_add_tail(&p_rt->port_node, &m_rt->port_list);
+	}
+
+	return 0;
+}
+
+static int sdw_slave_port_config(struct sdw_slave *slave,
+			struct sdw_slave_runtime *s_rt,
+			struct sdw_port_config *port_config,
+			unsigned int num_config)
+{
+	struct sdw_port_runtime *p_rt;
+	int i, ret;
+
+	/* Iterate for number of ports to perform initialization */
+	for (i = 0; i < num_config; i++) {
+		p_rt = sdw_port_alloc(&slave->dev, port_config, i);
+		if (!p_rt)
+			return -ENOMEM;
+
+		/*
+		 * TODO: Check valid port range as defined by DisCo/
+		 * slave
+		 */
+		ret = sdw_is_valid_port_range(&slave->dev, p_rt);
+		if (ret < 0) {
+			kfree(p_rt);
+			return ret;
+		}
+
+		/*
+		 * TODO: Check port capabilities for requested
+		 * configuration (audio mode support)
+		 */
+
+		list_add_tail(&p_rt->port_node, &s_rt->port_list);
+	}
+
+	return 0;
+}
+
+/**
+ * sdw_stream_add_master() - Allocate and add master runtime to a stream
+ *
+ * @bus: SDW Bus instance
+ * @stream_config: Stream configuration for audio stream
+ * @port_config: Port configuration for audio stream
+ * @num_ports: Number of ports
+ * @stream: SoundWire stream
+ */
+int sdw_stream_add_master(struct sdw_bus *bus,
+		struct sdw_stream_config *stream_config,
+		struct sdw_port_config *port_config,
+		unsigned int num_ports,
+		struct sdw_stream_runtime *stream)
+{
+	struct sdw_master_runtime *m_rt = NULL;
+	int ret;
+
+	mutex_lock(&bus->bus_lock);
+
+	m_rt = sdw_alloc_master_rt(bus, stream_config, stream);
+	if (!m_rt) {
+		dev_err(bus->dev,
+				"Master runtime config failed for stream:%s",
+				stream->name);
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = sdw_config_stream(bus->dev, stream, stream_config, false);
+	if (ret)
+		goto stream_error;
+
+	ret = sdw_master_port_config(bus, m_rt, port_config, num_ports);
+	if (ret)
+		goto stream_error;
+
+	stream->state = SDW_STREAM_CONFIGURED;
+
+stream_error:
+	sdw_release_master_stream(stream);
+error:
+	mutex_unlock(&bus->bus_lock);
+	return ret;
+}
+EXPORT_SYMBOL(sdw_stream_add_master);
+
+/**
+ * sdw_stream_add_slave() - Allocate and add master/slave runtime to a stream
+ *
+ * @slave: SDW Slave instance
+ * @stream_config: Stream configuration for audio stream
+ * @stream: SoundWire stream
+ * @port_config: Port configuration for audio stream
+ * @num_ports: Number of ports
+ */
+int sdw_stream_add_slave(struct sdw_slave *slave,
+		struct sdw_stream_config *stream_config,
+		struct sdw_port_config *port_config,
+		unsigned int num_ports,
+		struct sdw_stream_runtime *stream)
+{
+	struct sdw_slave_runtime *s_rt;
+	struct sdw_master_runtime *m_rt;
+	int ret;
+
+	mutex_lock(&slave->bus->bus_lock);
+
+	/*
+	 * If this API is invoked by Slave first then m_rt is not valid.
+	 * So, allocate m_rt and add Slave to it.
+	 */
+	m_rt = sdw_alloc_master_rt(slave->bus, stream_config, stream);
+	if (!m_rt) {
+		dev_err(&slave->dev,
+				"alloc master runtime failed for stream:%s",
+				stream->name);
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	s_rt = sdw_alloc_slave_rt(slave, stream_config, stream);
+	if (!s_rt) {
+		dev_err(&slave->dev,
+				"Slave runtime config failed for stream:%s",
+				stream->name);
+		ret = -ENOMEM;
+		goto stream_error;
+	}
+
+	ret = sdw_config_stream(&slave->dev, stream, stream_config, true);
+	if (ret)
+		goto stream_error;
+
+	list_add_tail(&s_rt->m_rt_node, &m_rt->slave_rt_list);
+
+	ret = sdw_slave_port_config(slave, s_rt, port_config, num_ports);
+	if (ret)
+		goto stream_error;
+
+	stream->state = SDW_STREAM_CONFIGURED;
+	goto error;
+
+stream_error:
+	/*
+	 * we hit error so cleanup the stream, release all Slave(s) and
+	 * Master runtime
+	 */
+	sdw_release_master_stream(stream);
+error:
+	mutex_unlock(&slave->bus->bus_lock);
+	return ret;
+}
+EXPORT_SYMBOL(sdw_stream_add_slave);
+
+/**
+ * sdw_get_slave_dpn_prop() - Get Slave port capabilities
+ *
+ * @slave: Slave handle
+ * @direction: Data direction.
+ * @port_num: Port number
+ */
+struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave,
+				enum sdw_data_direction direction,
+				unsigned int port_num)
+{
+	struct sdw_dpn_prop *dpn_prop;
+	u8 num_ports;
+	int i;
+
+	if (direction == SDW_DATA_DIR_TX) {
+		num_ports = hweight32(slave->prop.source_ports);
+		dpn_prop = slave->prop.src_dpn_prop;
+	} else {
+		num_ports = hweight32(slave->prop.sink_ports);
+		dpn_prop = slave->prop.sink_dpn_prop;
+	}
+
+	for (i = 0; i < num_ports; i++) {
+		dpn_prop = &dpn_prop[i];
+
+		if (dpn_prop->num == port_num)
+			return &dpn_prop[i];
+	}
+
+	return NULL;
+}
+
+static int _sdw_prepare_stream(struct sdw_stream_runtime *stream)
+{
+	struct sdw_master_runtime *m_rt = stream->m_rt;
+	struct sdw_bus *bus = m_rt->bus;
+	struct sdw_master_prop *prop = NULL;
+	struct sdw_bus_params params;
+	int ret;
+
+	prop = &bus->prop;
+	memcpy(&params, &bus->params, sizeof(params));
+
+	/* TODO: Support Asynchronous mode */
+	if ((prop->max_freq % stream->params.rate) != 0) {
+		dev_err(bus->dev, "Async mode not supported");
+		return -EINVAL;
+	}
+
+	/* Increment cumulative bus bandwidth */
+	/* TODO: Update this during Device-Device support */
+	bus->params.bandwidth += m_rt->stream->params.rate *
+		m_rt->ch_count * m_rt->stream->params.bps;
+
+	/* Program params */
+	ret = sdw_program_params(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Program params failed: %d", ret);
+		goto restore_params;
+	}
+
+	ret = do_bank_switch(stream);
+	if (ret < 0) {
+		dev_err(bus->dev, "Bank switch failed: %d", ret);
+		goto restore_params;
+	}
+
+	/* Prepare port(s) on the new clock configuration */
+	ret = sdw_prep_deprep_ports(m_rt, true);
+	if (ret < 0) {
+		dev_err(bus->dev, "Prepare port(s) failed ret = %d",
+				ret);
+		return ret;
+	}
+
+	stream->state = SDW_STREAM_PREPARED;
+
+	return ret;
+
+restore_params:
+	memcpy(&bus->params, &params, sizeof(params));
+	return ret;
+}
+
+/**
+ * sdw_prepare_stream() - Prepare SoundWire stream
+ *
+ * @stream: Soundwire stream
+ *
+ * Documentation/soundwire/stream.txt explains this API in detail
+ */
+int sdw_prepare_stream(struct sdw_stream_runtime *stream)
+{
+	int ret = 0;
+
+	if (!stream) {
+		pr_err("SoundWire: Handle not found for stream");
+		return -EINVAL;
+	}
+
+	mutex_lock(&stream->m_rt->bus->bus_lock);
+
+	ret = _sdw_prepare_stream(stream);
+	if (ret < 0)
+		pr_err("Prepare for stream:%s failed: %d", stream->name, ret);
+
+	mutex_unlock(&stream->m_rt->bus->bus_lock);
+	return ret;
+}
+EXPORT_SYMBOL(sdw_prepare_stream);
+
+static int _sdw_enable_stream(struct sdw_stream_runtime *stream)
+{
+	struct sdw_master_runtime *m_rt = stream->m_rt;
+	struct sdw_bus *bus = m_rt->bus;
+	int ret;
+
+	/* Program params */
+	ret = sdw_program_params(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Program params failed: %d", ret);
+		return ret;
+	}
+
+	/* Enable port(s) */
+	ret = sdw_enable_disable_ports(m_rt, true);
+	if (ret < 0) {
+		dev_err(bus->dev, "Enable port(s) failed ret: %d", ret);
+		return ret;
+	}
+
+	ret = do_bank_switch(stream);
+	if (ret < 0) {
+		dev_err(bus->dev, "Bank switch failed: %d", ret);
+		return ret;
+	}
+
+	stream->state = SDW_STREAM_ENABLED;
+	return 0;
+}
+
+/**
+ * sdw_enable_stream() - Enable SoundWire stream
+ *
+ * @stream: Soundwire stream
+ *
+ * Documentation/soundwire/stream.txt explains this API in detail
+ */
+int sdw_enable_stream(struct sdw_stream_runtime *stream)
+{
+	int ret = 0;
+
+	if (!stream) {
+		pr_err("SoundWire: Handle not found for stream");
+		return -EINVAL;
+	}
+
+	mutex_lock(&stream->m_rt->bus->bus_lock);
+
+	ret = _sdw_enable_stream(stream);
+	if (ret < 0)
+		pr_err("Enable for stream:%s failed: %d", stream->name, ret);
+
+	mutex_unlock(&stream->m_rt->bus->bus_lock);
+	return ret;
+}
+EXPORT_SYMBOL(sdw_enable_stream);
+
+static int _sdw_disable_stream(struct sdw_stream_runtime *stream)
+{
+	struct sdw_master_runtime *m_rt = stream->m_rt;
+	struct sdw_bus *bus = m_rt->bus;
+	int ret;
+
+	/* Disable port(s) */
+	ret = sdw_enable_disable_ports(m_rt, false);
+	if (ret < 0) {
+		dev_err(bus->dev, "Disable port(s) failed: %d", ret);
+		return ret;
+	}
+
+	stream->state = SDW_STREAM_DISABLED;
+
+	/* Program params */
+	ret = sdw_program_params(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Program params failed: %d", ret);
+		return ret;
+	}
+
+	return do_bank_switch(stream);
+}
+
+/**
+ * sdw_disable_stream() - Disable SoundWire stream
+ *
+ * @stream: Soundwire stream
+ *
+ * Documentation/soundwire/stream.txt explains this API in detail
+ */
+int sdw_disable_stream(struct sdw_stream_runtime *stream)
+{
+	int ret = 0;
+
+	if (!stream) {
+		pr_err("SoundWire: Handle not found for stream");
+		return -EINVAL;
+	}
+
+	mutex_lock(&stream->m_rt->bus->bus_lock);
+
+	ret = _sdw_disable_stream(stream);
+	if (ret < 0)
+		pr_err("Disable for stream:%s failed: %d", stream->name, ret);
+
+	mutex_unlock(&stream->m_rt->bus->bus_lock);
+	return ret;
+}
+EXPORT_SYMBOL(sdw_disable_stream);
+
+static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream)
+{
+	struct sdw_master_runtime *m_rt = stream->m_rt;
+	struct sdw_bus *bus = m_rt->bus;
+	int ret = 0;
+
+	/* De-prepare port(s) */
+	ret = sdw_prep_deprep_ports(m_rt, false);
+	if (ret < 0) {
+		dev_err(bus->dev, "De-prepare port(s) failed: %d", ret);
+		return ret;
+	}
+
+	stream->state = SDW_STREAM_DEPREPARED;
+
+	/* TODO: Update this during Device-Device support */
+	bus->params.bandwidth -= m_rt->stream->params.rate *
+		m_rt->ch_count * m_rt->stream->params.bps;
+
+	/* Program params */
+	ret = sdw_program_params(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Program params failed: %d", ret);
+		return ret;
+	}
+
+	return do_bank_switch(stream);
+}
+
+/**
+ * sdw_deprepare_stream() - Deprepare SoundWire stream
+ *
+ * @stream: Soundwire stream
+ *
+ * Documentation/soundwire/stream.txt explains this API in detail
+ */
+int sdw_deprepare_stream(struct sdw_stream_runtime *stream)
+{
+	int ret = 0;
+
+	if (!stream) {
+		pr_err("SoundWire: Handle not found for stream");
+		return -EINVAL;
+	}
+
+	mutex_lock(&stream->m_rt->bus->bus_lock);
+
+	ret = _sdw_deprepare_stream(stream);
+	if (ret < 0)
+		pr_err("De-prepare for stream:%d failed: %d", ret, ret);
+
+	mutex_unlock(&stream->m_rt->bus->bus_lock);
+	return ret;
+}
+EXPORT_SYMBOL(sdw_deprepare_stream);
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 2d4146ce2f1b..ad5d68e1dab7 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -47,6 +47,13 @@ config SPI_MASTER
 
 if SPI_MASTER
 
+config SPI_MEM
+	bool "SPI memory extension"
+	help
+	  Enable this option if you want to enable the SPI memory extension.
+	  This extension is meant to simplify interaction with SPI memories
+	  by providing a high-level interface to send memory-like commands.
+
 comment "SPI Master Controller Drivers"
 
 config SPI_ALTERA
@@ -71,7 +78,6 @@ config SPI_ARMADA_3700
 
 config SPI_ATMEL
 	tristate "Atmel SPI Controller"
-	depends on HAS_DMA
 	depends on ARCH_AT91 || COMPILE_TEST
 	help
 	  This selects a driver for the Atmel SPI Controller, present on
@@ -115,14 +121,6 @@ config SPI_BCM2835AUX
 	  "universal SPI master", and the regular SPI controller.
 	  This driver is for the universal/auxiliary SPI controller.
 
-config SPI_BCM53XX
-	tristate "Broadcom BCM53xx SPI controller"
-	depends on ARCH_BCM_5301X
-	depends on BCMA_POSSIBLE
-	select BCMA
-	help
-          Enable support for the SPI controller on Broadcom BCM53xx ARM SoCs.
-
 config SPI_BCM63XX
 	tristate "Broadcom BCM63xx SPI controller"
 	depends on BCM63XX || COMPILE_TEST
@@ -233,7 +231,6 @@ config SPI_EFM32
 
 config SPI_EP93XX
 	tristate "Cirrus Logic EP93xx SPI controller"
-	depends on HAS_DMA
 	depends on ARCH_EP93XX || COMPILE_TEST
 	help
 	  This enables using the Cirrus EP93xx SPI controller in master
@@ -355,7 +352,6 @@ config SPI_FSL_SPI
 config SPI_FSL_DSPI
 	tristate "Freescale DSPI controller"
 	select REGMAP_MMIO
-	depends on HAS_DMA
 	depends on SOC_VF610 || SOC_LS1021A || ARCH_LAYERSCAPE || M5441x || COMPILE_TEST
 	help
 	  This enables support for the Freescale DSPI controller in master
@@ -431,7 +427,6 @@ config SPI_OMAP_UWIRE
 
 config SPI_OMAP24XX
 	tristate "McSPI driver for OMAP"
-	depends on HAS_DMA
 	depends on ARCH_OMAP2PLUS || COMPILE_TEST
 	select SG_SPLIT
 	help
@@ -440,7 +435,6 @@ config SPI_OMAP24XX
 
 config SPI_TI_QSPI
 	tristate "DRA7xxx QSPI controller support"
-	depends on HAS_DMA
 	depends on ARCH_OMAP2PLUS || COMPILE_TEST
 	help
 	  QSPI master controller for DRA7xxx used for flash devices.
@@ -469,7 +463,6 @@ config SPI_PIC32
 config SPI_PIC32_SQI
 	tristate "Microchip PIC32 Quad SPI driver"
 	depends on MACH_PIC32 || COMPILE_TEST
-	depends on HAS_DMA
 	help
 	  SPI driver for PIC32 Quad SPI controller.
 
@@ -572,7 +565,7 @@ config SPI_SC18IS602
 
 config SPI_SH_MSIOF
 	tristate "SuperH MSIOF SPI controller"
-	depends on HAVE_CLK && HAS_DMA
+	depends on HAVE_CLK
 	depends on ARCH_SHMOBILE || ARCH_RENESAS || COMPILE_TEST
 	help
 	  SPI driver for SuperH and SH Mobile MSIOF blocks.
@@ -650,7 +643,7 @@ config SPI_MXS
 config SPI_TEGRA114
 	tristate "NVIDIA Tegra114 SPI Controller"
 	depends on (ARCH_TEGRA && TEGRA20_APB_DMA) || COMPILE_TEST
-	depends on RESET_CONTROLLER && HAS_DMA
+	depends on RESET_CONTROLLER
 	help
 	  SPI driver for NVIDIA Tegra114 SPI Controller interface. This controller
 	  is different than the older SoCs SPI controller and also register interface
@@ -668,7 +661,7 @@ config SPI_TEGRA20_SFLASH
 config SPI_TEGRA20_SLINK
 	tristate "Nvidia Tegra20/Tegra30 SLINK Controller"
 	depends on (ARCH_TEGRA && TEGRA20_APB_DMA) || COMPILE_TEST
-	depends on RESET_CONTROLLER && HAS_DMA
+	depends on RESET_CONTROLLER
 	help
 	  SPI driver for Nvidia Tegra20/Tegra30 SLINK Controller interface.
 
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index b935f10eb961..cb1f4378b87c 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -8,6 +8,7 @@ ccflags-$(CONFIG_SPI_DEBUG) := -DDEBUG
 # small core, mostly translating board-specific
 # config declarations into driver model code
 obj-$(CONFIG_SPI_MASTER)		+= spi.o
+obj-$(CONFIG_SPI_MEM)			+= spi-mem.o
 obj-$(CONFIG_SPI_SPIDEV)		+= spidev.o
 obj-$(CONFIG_SPI_LOOPBACK_TEST)		+= spi-loopback-test.o
 
@@ -20,7 +21,6 @@ obj-$(CONFIG_SPI_AU1550)		+= spi-au1550.o
 obj-$(CONFIG_SPI_AXI_SPI_ENGINE)	+= spi-axi-spi-engine.o
 obj-$(CONFIG_SPI_BCM2835)		+= spi-bcm2835.o
 obj-$(CONFIG_SPI_BCM2835AUX)		+= spi-bcm2835aux.o
-obj-$(CONFIG_SPI_BCM53XX)		+= spi-bcm53xx.o
 obj-$(CONFIG_SPI_BCM63XX)		+= spi-bcm63xx.o
 obj-$(CONFIG_SPI_BCM63XX_HSSPI)		+= spi-bcm63xx-hsspi.o
 obj-$(CONFIG_SPI_BCM_QSPI)		+= spi-iproc-qspi.o spi-brcmstb-qspi.o spi-bcm-qspi.o
diff --git a/drivers/spi/internals.h b/drivers/spi/internals.h
new file mode 100644
index 000000000000..4a28a8395552
--- /dev/null
+++ b/drivers/spi/internals.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2018 Exceet Electronics GmbH
+ * Copyright (C) 2018 Bootlin
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ *
+ * Helpers needed by the spi or spi-mem logic. Should not be used outside of
+ * spi-mem.c and spi.c.
+ */
+
+#ifndef __LINUX_SPI_INTERNALS_H
+#define __LINUX_SPI_INTERNALS_H
+
+#include <linux/device.h>
+#include <linux/dma-direction.h>
+#include <linux/scatterlist.h>
+#include <linux/spi/spi.h>
+
+void spi_flush_queue(struct spi_controller *ctrl);
+
+#ifdef CONFIG_HAS_DMA
+int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
+		struct sg_table *sgt, void *buf, size_t len,
+		enum dma_data_direction dir);
+void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
+		   struct sg_table *sgt, enum dma_data_direction dir);
+#else /* !CONFIG_HAS_DMA */
+static inline int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
+			      struct sg_table *sgt, void *buf, size_t len,
+			      enum dma_data_direction dir)
+{
+	return -EINVAL;
+}
+
+static inline void spi_unmap_buf(struct spi_controller *ctlr,
+				 struct device *dev, struct sg_table *sgt,
+				 enum dma_data_direction dir)
+{
+}
+#endif /* CONFIG_HAS_DMA */
+
+#endif /* __LINUX_SPI_INTERNALS_H */
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 1596d35498c5..8612525fa4e3 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -30,6 +30,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
 #include "spi-bcm-qspi.h"
@@ -215,10 +216,10 @@ struct bcm_qspi {
 	int bspi_maj_rev;
 	int bspi_min_rev;
 	int bspi_enabled;
-	struct spi_flash_read_message *bspi_rf_msg;
-	u32 bspi_rf_msg_idx;
-	u32 bspi_rf_msg_len;
-	u32 bspi_rf_msg_status;
+	const struct spi_mem_op *bspi_rf_op;
+	u32 bspi_rf_op_idx;
+	u32 bspi_rf_op_len;
+	u32 bspi_rf_op_status;
 	struct bcm_xfer_mode xfer_mode;
 	u32 s3_strap_override_ctrl;
 	bool bspi_mode;
@@ -313,26 +314,26 @@ static inline void bcm_qspi_bspi_lr_clear(struct bcm_qspi *qspi)
 
 static void bcm_qspi_bspi_lr_data_read(struct bcm_qspi *qspi)
 {
-	u32 *buf = (u32 *)qspi->bspi_rf_msg->buf;
+	u32 *buf = (u32 *)qspi->bspi_rf_op->data.buf.in;
 	u32 data = 0;
 
-	dev_dbg(&qspi->pdev->dev, "xfer %p rx %p rxlen %d\n", qspi->bspi_rf_msg,
-		qspi->bspi_rf_msg->buf, qspi->bspi_rf_msg_len);
+	dev_dbg(&qspi->pdev->dev, "xfer %p rx %p rxlen %d\n", qspi->bspi_rf_op,
+		qspi->bspi_rf_op->data.buf.in, qspi->bspi_rf_op_len);
 	while (!bcm_qspi_bspi_lr_is_fifo_empty(qspi)) {
 		data = bcm_qspi_bspi_lr_read_fifo(qspi);
-		if (likely(qspi->bspi_rf_msg_len >= 4) &&
+		if (likely(qspi->bspi_rf_op_len >= 4) &&
 		    IS_ALIGNED((uintptr_t)buf, 4)) {
-			buf[qspi->bspi_rf_msg_idx++] = data;
-			qspi->bspi_rf_msg_len -= 4;
+			buf[qspi->bspi_rf_op_idx++] = data;
+			qspi->bspi_rf_op_len -= 4;
 		} else {
 			/* Read out remaining bytes, make sure*/
-			u8 *cbuf = (u8 *)&buf[qspi->bspi_rf_msg_idx];
+			u8 *cbuf = (u8 *)&buf[qspi->bspi_rf_op_idx];
 
 			data = cpu_to_le32(data);
-			while (qspi->bspi_rf_msg_len) {
+			while (qspi->bspi_rf_op_len) {
 				*cbuf++ = (u8)data;
 				data >>= 8;
-				qspi->bspi_rf_msg_len--;
+				qspi->bspi_rf_op_len--;
 			}
 		}
 	}
@@ -349,14 +350,12 @@ static void bcm_qspi_bspi_set_xfer_params(struct bcm_qspi *qspi, u8 cmd_byte,
 }
 
 static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi,
-				       struct spi_flash_read_message *msg,
-				       int hp)
+				       const struct spi_mem_op *op, int hp)
 {
 	int bpc = 0, bpp = 0;
-	u8 command = msg->read_opcode;
-	int width  = msg->data_nbits ? msg->data_nbits : SPI_NBITS_SINGLE;
-	int addrlen = msg->addr_width;
-	int addr_nbits = msg->addr_nbits ? msg->addr_nbits : SPI_NBITS_SINGLE;
+	u8 command = op->cmd.opcode;
+	int width  = op->cmd.buswidth ? op->cmd.buswidth : SPI_NBITS_SINGLE;
+	int addrlen = op->addr.nbytes * 8;
 	int flex_mode = 1;
 
 	dev_dbg(&qspi->pdev->dev, "set flex mode w %x addrlen %x hp %d\n",
@@ -365,7 +364,7 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi,
 	if (addrlen == BSPI_ADDRLEN_4BYTES)
 		bpp = BSPI_BPP_ADDR_SELECT_MASK;
 
-	bpp |= msg->dummy_bytes * (8/addr_nbits);
+	bpp |= (op->dummy.nbytes * 8) / op->dummy.buswidth;
 
 	switch (width) {
 	case SPI_NBITS_SINGLE:
@@ -397,11 +396,10 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi,
 }
 
 static int bcm_qspi_bspi_set_override(struct bcm_qspi *qspi,
-				      struct spi_flash_read_message *msg,
-				      int hp)
+				      const struct spi_mem_op *op, int hp)
 {
-	int width = msg->data_nbits ? msg->data_nbits : SPI_NBITS_SINGLE;
-	int addrlen = msg->addr_width;
+	int width = op->data.buswidth ? op->data.buswidth : SPI_NBITS_SINGLE;
+	int addrlen = op->addr.nbytes;
 	u32 data = bcm_qspi_read(qspi, BSPI, BSPI_STRAP_OVERRIDE_CTRL);
 
 	dev_dbg(&qspi->pdev->dev, "set override mode w %x addrlen %x hp %d\n",
@@ -437,17 +435,17 @@ static int bcm_qspi_bspi_set_override(struct bcm_qspi *qspi,
 	/* set the override mode */
 	data |=	BSPI_STRAP_OVERRIDE_CTRL_OVERRIDE;
 	bcm_qspi_write(qspi, BSPI, BSPI_STRAP_OVERRIDE_CTRL, data);
-	bcm_qspi_bspi_set_xfer_params(qspi, msg->read_opcode, 0, 0, 0);
+	bcm_qspi_bspi_set_xfer_params(qspi, op->cmd.opcode, 0, 0, 0);
 
 	return 0;
 }
 
 static int bcm_qspi_bspi_set_mode(struct bcm_qspi *qspi,
-				  struct spi_flash_read_message *msg, int hp)
+				  const struct spi_mem_op *op, int hp)
 {
 	int error = 0;
-	int width = msg->data_nbits ? msg->data_nbits : SPI_NBITS_SINGLE;
-	int addrlen = msg->addr_width;
+	int width = op->data.buswidth ? op->data.buswidth : SPI_NBITS_SINGLE;
+	int addrlen = op->addr.nbytes;
 
 	/* default mode */
 	qspi->xfer_mode.flex_mode = true;
@@ -460,12 +458,12 @@ static int bcm_qspi_bspi_set_mode(struct bcm_qspi *qspi,
 		if (val & mask || qspi->s3_strap_override_ctrl & mask) {
 			qspi->xfer_mode.flex_mode = false;
 			bcm_qspi_write(qspi, BSPI, BSPI_FLEX_MODE_ENABLE, 0);
-			error = bcm_qspi_bspi_set_override(qspi, msg, hp);
+			error = bcm_qspi_bspi_set_override(qspi, op, hp);
 		}
 	}
 
 	if (qspi->xfer_mode.flex_mode)
-		error = bcm_qspi_bspi_set_flex_mode(qspi, msg, hp);
+		error = bcm_qspi_bspi_set_flex_mode(qspi, op, hp);
 
 	if (error) {
 		dev_warn(&qspi->pdev->dev,
@@ -490,7 +488,7 @@ static int bcm_qspi_bspi_set_mode(struct bcm_qspi *qspi,
 
 static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi)
 {
-	if (!has_bspi(qspi) || (qspi->bspi_enabled))
+	if (!has_bspi(qspi))
 		return;
 
 	qspi->bspi_enabled = 1;
@@ -505,7 +503,7 @@ static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi)
 
 static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi)
 {
-	if (!has_bspi(qspi) || (!qspi->bspi_enabled))
+	if (!has_bspi(qspi))
 		return;
 
 	qspi->bspi_enabled = 0;
@@ -519,16 +517,19 @@ static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi)
 
 static void bcm_qspi_chip_select(struct bcm_qspi *qspi, int cs)
 {
-	u32 data = 0;
+	u32 rd = 0;
+	u32 wr = 0;
 
-	if (qspi->curr_cs == cs)
-		return;
 	if (qspi->base[CHIP_SELECT]) {
-		data = bcm_qspi_read(qspi, CHIP_SELECT, 0);
-		data = (data & ~0xff) | (1 << cs);
-		bcm_qspi_write(qspi, CHIP_SELECT, 0, data);
+		rd = bcm_qspi_read(qspi, CHIP_SELECT, 0);
+		wr = (rd & ~0xff) | (1 << cs);
+		if (rd == wr)
+			return;
+		bcm_qspi_write(qspi, CHIP_SELECT, 0, wr);
 		usleep_range(10, 20);
 	}
+
+	dev_dbg(&qspi->pdev->dev, "using cs:%d\n", cs);
 	qspi->curr_cs = cs;
 }
 
@@ -755,8 +756,13 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi)
 			dev_dbg(&qspi->pdev->dev, "WR %04x\n", val);
 		}
 		mspi_cdram = MSPI_CDRAM_CONT_BIT;
-		mspi_cdram |= (~(1 << spi->chip_select) &
-			       MSPI_CDRAM_PCS);
+
+		if (has_bspi(qspi))
+			mspi_cdram &= ~1;
+		else
+			mspi_cdram |= (~(1 << spi->chip_select) &
+				       MSPI_CDRAM_PCS);
+
 		mspi_cdram |= ((tp.trans->bits_per_word <= 8) ? 0 :
 				MSPI_CDRAM_BITSE_BIT);
 
@@ -794,19 +800,20 @@ done:
 	return slot;
 }
 
-static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
-				    struct spi_flash_read_message *msg)
+static int bcm_qspi_bspi_exec_mem_op(struct spi_device *spi,
+				     const struct spi_mem_op *op)
 {
 	struct bcm_qspi *qspi = spi_master_get_devdata(spi->master);
-	u32 addr = 0, len, rdlen, len_words;
+	u32 addr = 0, len, rdlen, len_words, from = 0;
 	int ret = 0;
 	unsigned long timeo = msecs_to_jiffies(100);
 	struct bcm_qspi_soc_intc *soc_intc = qspi->soc_intc;
 
 	if (bcm_qspi_bspi_ver_three(qspi))
-		if (msg->addr_width == BSPI_ADDRLEN_4BYTES)
+		if (op->addr.nbytes == BSPI_ADDRLEN_4BYTES)
 			return -EIO;
 
+	from = op->addr.val;
 	bcm_qspi_chip_select(qspi, spi->chip_select);
 	bcm_qspi_write(qspi, MSPI, MSPI_WRITE_LOCK, 0);
 
@@ -815,15 +822,15 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
 	 * the upper address byte to bspi
 	 */
 	if (bcm_qspi_bspi_ver_three(qspi) == false) {
-		addr = msg->from & 0xff000000;
+		addr = from & 0xff000000;
 		bcm_qspi_write(qspi, BSPI,
 			       BSPI_BSPI_FLASH_UPPER_ADDR_BYTE, addr);
 	}
 
 	if (!qspi->xfer_mode.flex_mode)
-		addr = msg->from;
+		addr = from;
 	else
-		addr = msg->from & 0x00ffffff;
+		addr = from & 0x00ffffff;
 
 	if (bcm_qspi_bspi_ver_three(qspi) == true)
 		addr = (addr + 0xc00000) & 0xffffff;
@@ -832,8 +839,8 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
 	 * read into the entire buffer by breaking the reads
 	 * into RAF buffer read lengths
 	 */
-	len = msg->len;
-	qspi->bspi_rf_msg_idx = 0;
+	len = op->data.nbytes;
+	qspi->bspi_rf_op_idx = 0;
 
 	do {
 		if (len > BSPI_READ_LENGTH)
@@ -844,9 +851,9 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
 		reinit_completion(&qspi->bspi_done);
 		bcm_qspi_enable_bspi(qspi);
 		len_words = (rdlen + 3) >> 2;
-		qspi->bspi_rf_msg = msg;
-		qspi->bspi_rf_msg_status = 0;
-		qspi->bspi_rf_msg_len = rdlen;
+		qspi->bspi_rf_op = op;
+		qspi->bspi_rf_op_status = 0;
+		qspi->bspi_rf_op_len = rdlen;
 		dev_dbg(&qspi->pdev->dev,
 			"bspi xfr addr 0x%x len 0x%x", addr, rdlen);
 		bcm_qspi_write(qspi, BSPI, BSPI_RAF_START_ADDR, addr);
@@ -871,7 +878,6 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
 		}
 
 		/* set msg return length */
-		msg->retlen += rdlen;
 		addr += rdlen;
 		len -= rdlen;
 	} while (len);
@@ -906,61 +912,63 @@ static int bcm_qspi_transfer_one(struct spi_master *master,
 	return 0;
 }
 
-static int bcm_qspi_mspi_flash_read(struct spi_device *spi,
-				    struct spi_flash_read_message *msg)
+static int bcm_qspi_mspi_exec_mem_op(struct spi_device *spi,
+				     const struct spi_mem_op *op)
 {
-	struct bcm_qspi *qspi = spi_master_get_devdata(spi->master);
+	struct spi_master *master = spi->master;
+	struct bcm_qspi *qspi = spi_master_get_devdata(master);
 	struct spi_transfer t[2];
-	u8 cmd[6];
-	int ret;
+	u8 cmd[6] = { };
+	int ret, i;
 
 	memset(cmd, 0, sizeof(cmd));
 	memset(t, 0, sizeof(t));
 
 	/* tx */
 	/* opcode is in cmd[0] */
-	cmd[0] = msg->read_opcode;
-	cmd[1] = msg->from >> (msg->addr_width * 8 -  8);
-	cmd[2] = msg->from >> (msg->addr_width * 8 - 16);
-	cmd[3] = msg->from >> (msg->addr_width * 8 - 24);
-	cmd[4] = msg->from >> (msg->addr_width * 8 - 32);
+	cmd[0] = op->cmd.opcode;
+	for (i = 0; i < op->addr.nbytes; i++)
+		cmd[1 + i] = op->addr.val >> (8 * (op->addr.nbytes - i - 1));
+
 	t[0].tx_buf = cmd;
-	t[0].len = msg->addr_width + msg->dummy_bytes + 1;
+	t[0].len = op->addr.nbytes + op->dummy.nbytes + 1;
 	t[0].bits_per_word = spi->bits_per_word;
-	t[0].tx_nbits = msg->opcode_nbits;
+	t[0].tx_nbits = op->cmd.buswidth;
 	/* lets mspi know that this is not last transfer */
 	qspi->trans_pos.mspi_last_trans = false;
-	ret = bcm_qspi_transfer_one(spi->master, spi, &t[0]);
+	ret = bcm_qspi_transfer_one(master, spi, &t[0]);
 
 	/* rx */
 	qspi->trans_pos.mspi_last_trans = true;
 	if (!ret) {
 		/* rx */
-		t[1].rx_buf = msg->buf;
-		t[1].len = msg->len;
-		t[1].rx_nbits =  msg->data_nbits;
+		t[1].rx_buf = op->data.buf.in;
+		t[1].len = op->data.nbytes;
+		t[1].rx_nbits =  op->data.buswidth;
 		t[1].bits_per_word = spi->bits_per_word;
-		ret = bcm_qspi_transfer_one(spi->master, spi, &t[1]);
+		ret = bcm_qspi_transfer_one(master, spi, &t[1]);
 	}
 
-	if (!ret)
-		msg->retlen = msg->len;
-
 	return ret;
 }
 
-static int bcm_qspi_flash_read(struct spi_device *spi,
-			       struct spi_flash_read_message *msg)
+static int bcm_qspi_exec_mem_op(struct spi_mem *mem,
+				const struct spi_mem_op *op)
 {
+	struct spi_device *spi = mem->spi;
 	struct bcm_qspi *qspi = spi_master_get_devdata(spi->master);
 	int ret = 0;
 	bool mspi_read = false;
-	u32 addr, len;
+	u32 addr = 0, len;
 	u_char *buf;
 
-	buf = msg->buf;
-	addr = msg->from;
-	len = msg->len;
+	if (!op->data.nbytes || !op->addr.nbytes || op->addr.nbytes > 4 ||
+	    op->data.dir != SPI_MEM_DATA_IN)
+		return -ENOTSUPP;
+
+	buf = op->data.buf.in;
+	addr = op->addr.val;
+	len = op->data.nbytes;
 
 	if (bcm_qspi_bspi_ver_three(qspi) == true) {
 		/*
@@ -982,12 +990,12 @@ static int bcm_qspi_flash_read(struct spi_device *spi,
 		mspi_read = true;
 
 	if (mspi_read)
-		return bcm_qspi_mspi_flash_read(spi, msg);
+		return bcm_qspi_mspi_exec_mem_op(spi, op);
 
-	ret = bcm_qspi_bspi_set_mode(qspi, msg, -1);
+	ret = bcm_qspi_bspi_set_mode(qspi, op, -1);
 
 	if (!ret)
-		ret = bcm_qspi_bspi_flash_read(spi, msg);
+		ret = bcm_qspi_bspi_exec_mem_op(spi, op);
 
 	return ret;
 }
@@ -1026,10 +1034,10 @@ static irqreturn_t bcm_qspi_bspi_lr_l2_isr(int irq, void *dev_id)
 	struct bcm_qspi_soc_intc *soc_intc = qspi->soc_intc;
 	u32 status = qspi_dev_id->irqp->mask;
 
-	if (qspi->bspi_enabled && qspi->bspi_rf_msg) {
+	if (qspi->bspi_enabled && qspi->bspi_rf_op) {
 		bcm_qspi_bspi_lr_data_read(qspi);
-		if (qspi->bspi_rf_msg_len == 0) {
-			qspi->bspi_rf_msg = NULL;
+		if (qspi->bspi_rf_op_len == 0) {
+			qspi->bspi_rf_op = NULL;
 			if (qspi->soc_intc) {
 				/* disable soc BSPI interrupt */
 				soc_intc->bcm_qspi_int_set(soc_intc, BSPI_DONE,
@@ -1038,7 +1046,7 @@ static irqreturn_t bcm_qspi_bspi_lr_l2_isr(int irq, void *dev_id)
 				status = INTR_BSPI_LR_SESSION_DONE_MASK;
 			}
 
-			if (qspi->bspi_rf_msg_status)
+			if (qspi->bspi_rf_op_status)
 				bcm_qspi_bspi_lr_clear(qspi);
 			else
 				bcm_qspi_bspi_flush_prefetch_buffers(qspi);
@@ -1050,7 +1058,7 @@ static irqreturn_t bcm_qspi_bspi_lr_l2_isr(int irq, void *dev_id)
 	}
 
 	status &= INTR_BSPI_LR_SESSION_DONE_MASK;
-	if (qspi->bspi_enabled && status && qspi->bspi_rf_msg_len == 0)
+	if (qspi->bspi_enabled && status && qspi->bspi_rf_op_len == 0)
 		complete(&qspi->bspi_done);
 
 	return IRQ_HANDLED;
@@ -1063,7 +1071,7 @@ static irqreturn_t bcm_qspi_bspi_lr_err_l2_isr(int irq, void *dev_id)
 	struct bcm_qspi_soc_intc *soc_intc = qspi->soc_intc;
 
 	dev_err(&qspi->pdev->dev, "BSPI INT error\n");
-	qspi->bspi_rf_msg_status = -EIO;
+	qspi->bspi_rf_op_status = -EIO;
 	if (qspi->soc_intc)
 		/* clear soc interrupt */
 		soc_intc->bcm_qspi_int_ack(soc_intc, BSPI_ERR);
@@ -1186,6 +1194,10 @@ static void bcm_qspi_hw_uninit(struct bcm_qspi *qspi)
 
 }
 
+static const struct spi_controller_mem_ops bcm_qspi_mem_ops = {
+	.exec_op = bcm_qspi_exec_mem_op,
+};
+
 static const struct of_device_id bcm_qspi_of_match[] = {
 	{ .compatible = "brcm,spi-bcm-qspi" },
 	{},
@@ -1228,7 +1240,7 @@ int bcm_qspi_probe(struct platform_device *pdev,
 	master->mode_bits = SPI_CPHA | SPI_CPOL | SPI_RX_DUAL | SPI_RX_QUAD;
 	master->setup = bcm_qspi_setup;
 	master->transfer_one = bcm_qspi_transfer_one;
-	master->spi_flash_read = bcm_qspi_flash_read;
+	master->mem_ops = &bcm_qspi_mem_ops;
 	master->cleanup = bcm_qspi_cleanup;
 	master->dev.of_node = dev->of_node;
 	master->num_chipselect = NUM_CHIPSELECT;
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 1431cb98fe40..3094d818cf06 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -184,6 +184,11 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
 	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
 	irqreturn_t ret = IRQ_NONE;
 
+	/* IRQ may be shared, so return if our interrupts are disabled */
+	if (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_CNTL1) &
+	      (BCM2835_AUX_SPI_CNTL1_TXEMPTY | BCM2835_AUX_SPI_CNTL1_IDLE)))
+		return ret;
+
 	/* check if we have data to read */
 	while (bs->rx_len &&
 	       (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) &
diff --git a/drivers/spi/spi-bcm53xx.c b/drivers/spi/spi-bcm53xx.c
deleted file mode 100644
index d02ceb7a29d1..000000000000
--- a/drivers/spi/spi-bcm53xx.c
+++ /dev/null
@@ -1,360 +0,0 @@
-/*
- * Copyright (C) 2014-2016 Rafał Miłecki <rafal@milecki.pl>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#define pr_fmt(fmt)		KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/bcma/bcma.h>
-#include <linux/spi/spi.h>
-
-#include "spi-bcm53xx.h"
-
-#define BCM53XXSPI_MAX_SPI_BAUD	13500000	/* 216 MHz? */
-#define BCM53XXSPI_FLASH_WINDOW	SZ_32M
-
-/* The longest observed required wait was 19 ms */
-#define BCM53XXSPI_SPE_TIMEOUT_MS	80
-
-struct bcm53xxspi {
-	struct bcma_device *core;
-	struct spi_master *master;
-	void __iomem *mmio_base;
-	bool bspi;				/* Boot SPI mode with memory mapping */
-};
-
-static inline u32 bcm53xxspi_read(struct bcm53xxspi *b53spi, u16 offset)
-{
-	return bcma_read32(b53spi->core, offset);
-}
-
-static inline void bcm53xxspi_write(struct bcm53xxspi *b53spi, u16 offset,
-				    u32 value)
-{
-	bcma_write32(b53spi->core, offset, value);
-}
-
-static void bcm53xxspi_disable_bspi(struct bcm53xxspi *b53spi)
-{
-	struct device *dev = &b53spi->core->dev;
-	unsigned long deadline;
-	u32 tmp;
-
-	if (!b53spi->bspi)
-		return;
-
-	tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL);
-	if (tmp & 0x1)
-		return;
-
-	deadline = jiffies + usecs_to_jiffies(200);
-	do {
-		tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_BUSY_STATUS);
-		if (!(tmp & 0x1)) {
-			bcm53xxspi_write(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL,
-					 0x1);
-			ndelay(200);
-			b53spi->bspi = false;
-			return;
-		}
-		udelay(1);
-	} while (!time_after_eq(jiffies, deadline));
-
-	dev_warn(dev, "Timeout disabling BSPI\n");
-}
-
-static void bcm53xxspi_enable_bspi(struct bcm53xxspi *b53spi)
-{
-	u32 tmp;
-
-	if (b53spi->bspi)
-		return;
-
-	tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL);
-	if (!(tmp & 0x1))
-		return;
-
-	bcm53xxspi_write(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL, 0x0);
-	b53spi->bspi = true;
-}
-
-static inline unsigned int bcm53xxspi_calc_timeout(size_t len)
-{
-	/* Do some magic calculation based on length and buad. Add 10% and 1. */
-	return (len * 9000 / BCM53XXSPI_MAX_SPI_BAUD * 110 / 100) + 1;
-}
-
-static int bcm53xxspi_wait(struct bcm53xxspi *b53spi, unsigned int timeout_ms)
-{
-	unsigned long deadline;
-	u32 tmp;
-
-	/* SPE bit has to be 0 before we read MSPI STATUS */
-	deadline = jiffies + msecs_to_jiffies(BCM53XXSPI_SPE_TIMEOUT_MS);
-	do {
-		tmp = bcm53xxspi_read(b53spi, B53SPI_MSPI_SPCR2);
-		if (!(tmp & B53SPI_MSPI_SPCR2_SPE))
-			break;
-		udelay(5);
-	} while (!time_after_eq(jiffies, deadline));
-
-	if (tmp & B53SPI_MSPI_SPCR2_SPE)
-		goto spi_timeout;
-
-	/* Check status */
-	deadline = jiffies + msecs_to_jiffies(timeout_ms);
-	do {
-		tmp = bcm53xxspi_read(b53spi, B53SPI_MSPI_MSPI_STATUS);
-		if (tmp & B53SPI_MSPI_MSPI_STATUS_SPIF) {
-			bcm53xxspi_write(b53spi, B53SPI_MSPI_MSPI_STATUS, 0);
-			return 0;
-		}
-
-		cpu_relax();
-		udelay(100);
-	} while (!time_after_eq(jiffies, deadline));
-
-spi_timeout:
-	bcm53xxspi_write(b53spi, B53SPI_MSPI_MSPI_STATUS, 0);
-
-	pr_err("Timeout waiting for SPI to be ready!\n");
-
-	return -EBUSY;
-}
-
-static void bcm53xxspi_buf_write(struct bcm53xxspi *b53spi, u8 *w_buf,
-				 size_t len, bool cont)
-{
-	u32 tmp;
-	int i;
-
-	for (i = 0; i < len; i++) {
-		/* Transmit Register File MSB */
-		bcm53xxspi_write(b53spi, B53SPI_MSPI_TXRAM + 4 * (i * 2),
-				 (unsigned int)w_buf[i]);
-	}
-
-	for (i = 0; i < len; i++) {
-		tmp = B53SPI_CDRAM_CONT | B53SPI_CDRAM_PCS_DISABLE_ALL |
-		      B53SPI_CDRAM_PCS_DSCK;
-		if (!cont && i == len - 1)
-			tmp &= ~B53SPI_CDRAM_CONT;
-		tmp &= ~0x1;
-		/* Command Register File */
-		bcm53xxspi_write(b53spi, B53SPI_MSPI_CDRAM + 4 * i, tmp);
-	}
-
-	/* Set queue pointers */
-	bcm53xxspi_write(b53spi, B53SPI_MSPI_NEWQP, 0);
-	bcm53xxspi_write(b53spi, B53SPI_MSPI_ENDQP, len - 1);
-
-	if (cont)
-		bcm53xxspi_write(b53spi, B53SPI_MSPI_WRITE_LOCK, 1);
-
-	/* Start SPI transfer */
-	tmp = bcm53xxspi_read(b53spi, B53SPI_MSPI_SPCR2);
-	tmp |= B53SPI_MSPI_SPCR2_SPE;
-	if (cont)
-		tmp |= B53SPI_MSPI_SPCR2_CONT_AFTER_CMD;
-	bcm53xxspi_write(b53spi, B53SPI_MSPI_SPCR2, tmp);
-
-	/* Wait for SPI to finish */
-	bcm53xxspi_wait(b53spi, bcm53xxspi_calc_timeout(len));
-
-	if (!cont)
-		bcm53xxspi_write(b53spi, B53SPI_MSPI_WRITE_LOCK, 0);
-}
-
-static void bcm53xxspi_buf_read(struct bcm53xxspi *b53spi, u8 *r_buf,
-				size_t len, bool cont)
-{
-	u32 tmp;
-	int i;
-
-	for (i = 0; i < len; i++) {
-		tmp = B53SPI_CDRAM_CONT | B53SPI_CDRAM_PCS_DISABLE_ALL |
-		      B53SPI_CDRAM_PCS_DSCK;
-		if (!cont && i == len - 1)
-			tmp &= ~B53SPI_CDRAM_CONT;
-		tmp &= ~0x1;
-		/* Command Register File */
-		bcm53xxspi_write(b53spi, B53SPI_MSPI_CDRAM + 4 * i, tmp);
-	}
-
-	/* Set queue pointers */
-	bcm53xxspi_write(b53spi, B53SPI_MSPI_NEWQP, 0);
-	bcm53xxspi_write(b53spi, B53SPI_MSPI_ENDQP, len - 1);
-
-	if (cont)
-		bcm53xxspi_write(b53spi, B53SPI_MSPI_WRITE_LOCK, 1);
-
-	/* Start SPI transfer */
-	tmp = bcm53xxspi_read(b53spi, B53SPI_MSPI_SPCR2);
-	tmp |= B53SPI_MSPI_SPCR2_SPE;
-	if (cont)
-		tmp |= B53SPI_MSPI_SPCR2_CONT_AFTER_CMD;
-	bcm53xxspi_write(b53spi, B53SPI_MSPI_SPCR2, tmp);
-
-	/* Wait for SPI to finish */
-	bcm53xxspi_wait(b53spi, bcm53xxspi_calc_timeout(len));
-
-	if (!cont)
-		bcm53xxspi_write(b53spi, B53SPI_MSPI_WRITE_LOCK, 0);
-
-	for (i = 0; i < len; ++i) {
-		u16 reg = B53SPI_MSPI_RXRAM + 4 * (1 + i * 2);
-
-		/* Data stored in the transmit register file LSB */
-		r_buf[i] = (u8)bcm53xxspi_read(b53spi, reg);
-	}
-}
-
-static int bcm53xxspi_transfer_one(struct spi_master *master,
-				   struct spi_device *spi,
-				   struct spi_transfer *t)
-{
-	struct bcm53xxspi *b53spi = spi_master_get_devdata(master);
-	u8 *buf;
-	size_t left;
-
-	bcm53xxspi_disable_bspi(b53spi);
-
-	if (t->tx_buf) {
-		buf = (u8 *)t->tx_buf;
-		left = t->len;
-		while (left) {
-			size_t to_write = min_t(size_t, 16, left);
-			bool cont = !spi_transfer_is_last(master, t) ||
-				    left - to_write > 0;
-
-			bcm53xxspi_buf_write(b53spi, buf, to_write, cont);
-			left -= to_write;
-			buf += to_write;
-		}
-	}
-
-	if (t->rx_buf) {
-		buf = (u8 *)t->rx_buf;
-		left = t->len;
-		while (left) {
-			size_t to_read = min_t(size_t, 16, left);
-			bool cont = !spi_transfer_is_last(master, t) ||
-				    left - to_read > 0;
-
-			bcm53xxspi_buf_read(b53spi, buf, to_read, cont);
-			left -= to_read;
-			buf += to_read;
-		}
-	}
-
-	return 0;
-}
-
-static int bcm53xxspi_flash_read(struct spi_device *spi,
-				 struct spi_flash_read_message *msg)
-{
-	struct bcm53xxspi *b53spi = spi_master_get_devdata(spi->master);
-	int ret = 0;
-
-	if (msg->from + msg->len > BCM53XXSPI_FLASH_WINDOW)
-		return -EINVAL;
-
-	bcm53xxspi_enable_bspi(b53spi);
-	memcpy_fromio(msg->buf, b53spi->mmio_base + msg->from, msg->len);
-	msg->retlen = msg->len;
-
-	return ret;
-}
-
-/**************************************************
- * BCMA
- **************************************************/
-
-static const struct bcma_device_id bcm53xxspi_bcma_tbl[] = {
-	BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_NS_QSPI, BCMA_ANY_REV, BCMA_ANY_CLASS),
-	{},
-};
-MODULE_DEVICE_TABLE(bcma, bcm53xxspi_bcma_tbl);
-
-static int bcm53xxspi_bcma_probe(struct bcma_device *core)
-{
-	struct device *dev = &core->dev;
-	struct bcm53xxspi *b53spi;
-	struct spi_master *master;
-	int err;
-
-	if (core->bus->drv_cc.core->id.rev != 42) {
-		pr_err("SPI on SoC with unsupported ChipCommon rev\n");
-		return -ENOTSUPP;
-	}
-
-	master = spi_alloc_master(dev, sizeof(*b53spi));
-	if (!master)
-		return -ENOMEM;
-
-	b53spi = spi_master_get_devdata(master);
-	b53spi->master = master;
-	b53spi->core = core;
-
-	if (core->addr_s[0])
-		b53spi->mmio_base = devm_ioremap(dev, core->addr_s[0],
-						 BCM53XXSPI_FLASH_WINDOW);
-	b53spi->bspi = true;
-	bcm53xxspi_disable_bspi(b53spi);
-
-	master->dev.of_node = dev->of_node;
-	master->transfer_one = bcm53xxspi_transfer_one;
-	if (b53spi->mmio_base)
-		master->spi_flash_read = bcm53xxspi_flash_read;
-
-	bcma_set_drvdata(core, b53spi);
-
-	err = devm_spi_register_master(dev, master);
-	if (err) {
-		spi_master_put(master);
-		bcma_set_drvdata(core, NULL);
-		return err;
-	}
-
-	return 0;
-}
-
-static struct bcma_driver bcm53xxspi_bcma_driver = {
-	.name		= KBUILD_MODNAME,
-	.id_table	= bcm53xxspi_bcma_tbl,
-	.probe		= bcm53xxspi_bcma_probe,
-};
-
-/**************************************************
- * Init & exit
- **************************************************/
-
-static int __init bcm53xxspi_module_init(void)
-{
-	int err = 0;
-
-	err = bcma_driver_register(&bcm53xxspi_bcma_driver);
-	if (err)
-		pr_err("Failed to register bcma driver: %d\n", err);
-
-	return err;
-}
-
-static void __exit bcm53xxspi_module_exit(void)
-{
-	bcma_driver_unregister(&bcm53xxspi_bcma_driver);
-}
-
-module_init(bcm53xxspi_module_init);
-module_exit(bcm53xxspi_module_exit);
-
-MODULE_DESCRIPTION("Broadcom BCM53xx SPI Controller driver");
-MODULE_AUTHOR("Rafał Miłecki <zajec5@gmail.com>");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-bcm53xx.h b/drivers/spi/spi-bcm53xx.h
deleted file mode 100644
index 03e3442086ec..000000000000
--- a/drivers/spi/spi-bcm53xx.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef SPI_BCM53XX_H
-#define SPI_BCM53XX_H
-
-#define B53SPI_BSPI_REVISION_ID			0x000
-#define B53SPI_BSPI_SCRATCH			0x004
-#define B53SPI_BSPI_MAST_N_BOOT_CTRL		0x008
-#define B53SPI_BSPI_BUSY_STATUS			0x00c
-#define B53SPI_BSPI_INTR_STATUS			0x010
-#define B53SPI_BSPI_B0_STATUS			0x014
-#define B53SPI_BSPI_B0_CTRL			0x018
-#define B53SPI_BSPI_B1_STATUS			0x01c
-#define B53SPI_BSPI_B1_CTRL			0x020
-#define B53SPI_BSPI_STRAP_OVERRIDE_CTRL		0x024
-#define B53SPI_BSPI_FLEX_MODE_ENABLE		0x028
-#define B53SPI_BSPI_BITS_PER_CYCLE		0x02c
-#define B53SPI_BSPI_BITS_PER_PHASE		0x030
-#define B53SPI_BSPI_CMD_AND_MODE_BYTE		0x034
-#define B53SPI_BSPI_BSPI_FLASH_UPPER_ADDR_BYTE	0x038
-#define B53SPI_BSPI_BSPI_XOR_VALUE		0x03c
-#define B53SPI_BSPI_BSPI_XOR_ENABLE		0x040
-#define B53SPI_BSPI_BSPI_PIO_MODE_ENABLE	0x044
-#define B53SPI_BSPI_BSPI_PIO_IODIR		0x048
-#define B53SPI_BSPI_BSPI_PIO_DATA		0x04c
-
-/* RAF */
-#define B53SPI_RAF_START_ADDR			0x100
-#define B53SPI_RAF_NUM_WORDS			0x104
-#define B53SPI_RAF_CTRL				0x108
-#define B53SPI_RAF_FULLNESS			0x10c
-#define B53SPI_RAF_WATERMARK			0x110
-#define B53SPI_RAF_STATUS			0x114
-#define B53SPI_RAF_READ_DATA			0x118
-#define B53SPI_RAF_WORD_CNT			0x11c
-#define B53SPI_RAF_CURR_ADDR			0x120
-
-/* MSPI */
-#define B53SPI_MSPI_SPCR0_LSB			0x200
-#define B53SPI_MSPI_SPCR0_MSB			0x204
-#define B53SPI_MSPI_SPCR1_LSB			0x208
-#define B53SPI_MSPI_SPCR1_MSB			0x20c
-#define B53SPI_MSPI_NEWQP			0x210
-#define B53SPI_MSPI_ENDQP			0x214
-#define B53SPI_MSPI_SPCR2			0x218
-#define  B53SPI_MSPI_SPCR2_SPE			0x00000040
-#define  B53SPI_MSPI_SPCR2_CONT_AFTER_CMD	0x00000080
-#define B53SPI_MSPI_MSPI_STATUS			0x220
-#define  B53SPI_MSPI_MSPI_STATUS_SPIF		0x00000001
-#define B53SPI_MSPI_CPTQP			0x224
-#define B53SPI_MSPI_TXRAM			0x240 /* 32 registers, up to 0x2b8 */
-#define B53SPI_MSPI_RXRAM			0x2c0 /* 32 registers, up to 0x33c */
-#define B53SPI_MSPI_CDRAM			0x340 /* 16 registers, up to 0x37c */
-#define  B53SPI_CDRAM_PCS_PCS0			0x00000001
-#define  B53SPI_CDRAM_PCS_PCS1			0x00000002
-#define  B53SPI_CDRAM_PCS_PCS2			0x00000004
-#define  B53SPI_CDRAM_PCS_PCS3			0x00000008
-#define  B53SPI_CDRAM_PCS_DISABLE_ALL		0x0000000f
-#define  B53SPI_CDRAM_PCS_DSCK			0x00000010
-#define  B53SPI_CDRAM_BITSE			0x00000040
-#define  B53SPI_CDRAM_CONT			0x00000080
-#define B53SPI_MSPI_WRITE_LOCK			0x380
-#define B53SPI_MSPI_DISABLE_FLUSH_GEN		0x384
-
-/* Interrupt */
-#define B53SPI_INTR_RAF_LR_FULLNESS_REACHED	0x3a0
-#define B53SPI_INTR_RAF_LR_TRUNCATED		0x3a4
-#define B53SPI_INTR_RAF_LR_IMPATIENT		0x3a8
-#define B53SPI_INTR_RAF_LR_SESSION_DONE		0x3ac
-#define B53SPI_INTR_RAF_LR_OVERREAD		0x3b0
-#define B53SPI_INTR_MSPI_DONE			0x3b4
-#define B53SPI_INTR_MSPI_HALT_SET_TRANSACTION_DONE	0x3b8
-
-#endif /* SPI_BCM53XX_H */
diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c
index cbcba614b253..c23849f7aa7b 100644
--- a/drivers/spi/spi-bcm63xx-hsspi.c
+++ b/drivers/spi/spi-bcm63xx-hsspi.c
@@ -352,22 +352,31 @@ static int bcm63xx_hsspi_probe(struct platform_device *pdev)
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		return ret;
+
 	rate = clk_get_rate(clk);
 	if (!rate) {
 		struct clk *pll_clk = devm_clk_get(dev, "pll");
 
-		if (IS_ERR(pll_clk))
-			return PTR_ERR(pll_clk);
+		if (IS_ERR(pll_clk)) {
+			ret = PTR_ERR(pll_clk);
+			goto out_disable_clk;
+		}
+
+		ret = clk_prepare_enable(pll_clk);
+		if (ret)
+			goto out_disable_clk;
 
 		rate = clk_get_rate(pll_clk);
-		if (!rate)
-			return -EINVAL;
+		clk_disable_unprepare(pll_clk);
+		if (!rate) {
+			ret = -EINVAL;
+			goto out_disable_clk;
+		}
 	}
 
-	ret = clk_prepare_enable(clk);
-	if (ret)
-		return ret;
-
 	master = spi_alloc_master(&pdev->dev, sizeof(*bs));
 	if (!master) {
 		ret = -ENOMEM;
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 5c9516ae4942..f3dad6fcdc35 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -313,6 +313,14 @@ static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi)
 
 	while ((trans_cnt < CDNS_SPI_FIFO_DEPTH) &&
 	       (xspi->tx_bytes > 0)) {
+
+		/* When xspi in busy condition, bytes may send failed,
+		 * then spi control did't work thoroughly, add one byte delay
+		 */
+		if (cdns_spi_read(xspi, CDNS_SPI_ISR) &
+		    CDNS_SPI_IXR_TXFULL)
+			usleep_range(10, 20);
+
 		if (xspi->txbuf)
 			cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
 		else
@@ -686,8 +694,7 @@ static int cdns_spi_remove(struct platform_device *pdev)
  */
 static int __maybe_unused cdns_spi_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_master *master = dev_get_drvdata(dev);
 
 	return spi_master_suspend(master);
 }
@@ -702,8 +709,7 @@ static int __maybe_unused cdns_spi_suspend(struct device *dev)
  */
 static int __maybe_unused cdns_spi_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_master *master = dev_get_drvdata(dev);
 	struct cdns_spi *xspi = spi_master_get_devdata(master);
 
 	cdns_spi_init_hw(xspi);
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index cb3c73007ca1..e6d5cc6ab108 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -1,19 +1,8 @@
-/*
- * Freescale i.MX7ULP LPSPI driver
- *
- * Copyright 2016 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Freescale i.MX7ULP LPSPI driver
+//
+// Copyright 2016 Freescale Semiconductor, Inc.
 
 #include <linux/clk.h>
 #include <linux/completion.h>
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 6f57592a7f95..866246f21041 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1,22 +1,6 @@
-/*
- * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- * Copyright (C) 2008 Juergen Beisert
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation
- * 51 Franklin Street, Fifth Floor
- * Boston, MA  02110-1301, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
+// Copyright (C) 2008 Juergen Beisert
 
 #include <linux/clk.h>
 #include <linux/completion.h>
@@ -1701,7 +1685,7 @@ static struct platform_driver spi_imx_driver = {
 };
 module_platform_driver(spi_imx_driver);
 
-MODULE_DESCRIPTION("SPI Master Controller driver");
+MODULE_DESCRIPTION("SPI Controller driver");
 MODULE_AUTHOR("Sascha Hauer, Pengutronix");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
new file mode 100644
index 000000000000..990770dfa5cf
--- /dev/null
+++ b/drivers/spi/spi-mem.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Exceet Electronics GmbH
+ * Copyright (C) 2018 Bootlin
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+#include <linux/dmaengine.h>
+#include <linux/pm_runtime.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+#include "internals.h"
+
+/**
+ * spi_controller_dma_map_mem_op_data() - DMA-map the buffer attached to a
+ *					  memory operation
+ * @ctlr: the SPI controller requesting this dma_map()
+ * @op: the memory operation containing the buffer to map
+ * @sgt: a pointer to a non-initialized sg_table that will be filled by this
+ *	 function
+ *
+ * Some controllers might want to do DMA on the data buffer embedded in @op.
+ * This helper prepares everything for you and provides a ready-to-use
+ * sg_table. This function is not intended to be called from spi drivers.
+ * Only SPI controller drivers should use it.
+ * Note that the caller must ensure the memory region pointed by
+ * op->data.buf.{in,out} is DMA-able before calling this function.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr,
+				       const struct spi_mem_op *op,
+				       struct sg_table *sgt)
+{
+	struct device *dmadev;
+
+	if (!op->data.nbytes)
+		return -EINVAL;
+
+	if (op->data.dir == SPI_MEM_DATA_OUT && ctlr->dma_tx)
+		dmadev = ctlr->dma_tx->device->dev;
+	else if (op->data.dir == SPI_MEM_DATA_IN && ctlr->dma_rx)
+		dmadev = ctlr->dma_rx->device->dev;
+	else
+		dmadev = ctlr->dev.parent;
+
+	if (!dmadev)
+		return -EINVAL;
+
+	return spi_map_buf(ctlr, dmadev, sgt, op->data.buf.in, op->data.nbytes,
+			   op->data.dir == SPI_MEM_DATA_IN ?
+			   DMA_FROM_DEVICE : DMA_TO_DEVICE);
+}
+EXPORT_SYMBOL_GPL(spi_controller_dma_map_mem_op_data);
+
+/**
+ * spi_controller_dma_unmap_mem_op_data() - DMA-unmap the buffer attached to a
+ *					    memory operation
+ * @ctlr: the SPI controller requesting this dma_unmap()
+ * @op: the memory operation containing the buffer to unmap
+ * @sgt: a pointer to an sg_table previously initialized by
+ *	 spi_controller_dma_map_mem_op_data()
+ *
+ * Some controllers might want to do DMA on the data buffer embedded in @op.
+ * This helper prepares things so that the CPU can access the
+ * op->data.buf.{in,out} buffer again.
+ *
+ * This function is not intended to be called from SPI drivers. Only SPI
+ * controller drivers should use it.
+ *
+ * This function should be called after the DMA operation has finished and is
+ * only valid if the previous spi_controller_dma_map_mem_op_data() call
+ * returned 0.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr,
+					  const struct spi_mem_op *op,
+					  struct sg_table *sgt)
+{
+	struct device *dmadev;
+
+	if (!op->data.nbytes)
+		return;
+
+	if (op->data.dir == SPI_MEM_DATA_OUT && ctlr->dma_tx)
+		dmadev = ctlr->dma_tx->device->dev;
+	else if (op->data.dir == SPI_MEM_DATA_IN && ctlr->dma_rx)
+		dmadev = ctlr->dma_rx->device->dev;
+	else
+		dmadev = ctlr->dev.parent;
+
+	spi_unmap_buf(ctlr, dmadev, sgt,
+		      op->data.dir == SPI_MEM_DATA_IN ?
+		      DMA_FROM_DEVICE : DMA_TO_DEVICE);
+}
+EXPORT_SYMBOL_GPL(spi_controller_dma_unmap_mem_op_data);
+
+static int spi_check_buswidth_req(struct spi_mem *mem, u8 buswidth, bool tx)
+{
+	u32 mode = mem->spi->mode;
+
+	switch (buswidth) {
+	case 1:
+		return 0;
+
+	case 2:
+		if ((tx && (mode & (SPI_TX_DUAL | SPI_TX_QUAD))) ||
+		    (!tx && (mode & (SPI_RX_DUAL | SPI_RX_QUAD))))
+			return 0;
+
+		break;
+
+	case 4:
+		if ((tx && (mode & SPI_TX_QUAD)) ||
+		    (!tx && (mode & SPI_RX_QUAD)))
+			return 0;
+
+		break;
+
+	default:
+		break;
+	}
+
+	return -ENOTSUPP;
+}
+
+static bool spi_mem_default_supports_op(struct spi_mem *mem,
+					const struct spi_mem_op *op)
+{
+	if (spi_check_buswidth_req(mem, op->cmd.buswidth, true))
+		return false;
+
+	if (op->addr.nbytes &&
+	    spi_check_buswidth_req(mem, op->addr.buswidth, true))
+		return false;
+
+	if (op->dummy.nbytes &&
+	    spi_check_buswidth_req(mem, op->dummy.buswidth, true))
+		return false;
+
+	if (op->data.nbytes &&
+	    spi_check_buswidth_req(mem, op->data.buswidth,
+				   op->data.dir == SPI_MEM_DATA_OUT))
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(spi_mem_default_supports_op);
+
+/**
+ * spi_mem_supports_op() - Check if a memory device and the controller it is
+ *			   connected to support a specific memory operation
+ * @mem: the SPI memory
+ * @op: the memory operation to check
+ *
+ * Some controllers are only supporting Single or Dual IOs, others might only
+ * support specific opcodes, or it can even be that the controller and device
+ * both support Quad IOs but the hardware prevents you from using it because
+ * only 2 IO lines are connected.
+ *
+ * This function checks whether a specific operation is supported.
+ *
+ * Return: true if @op is supported, false otherwise.
+ */
+bool spi_mem_supports_op(struct spi_mem *mem, const struct spi_mem_op *op)
+{
+	struct spi_controller *ctlr = mem->spi->controller;
+
+	if (ctlr->mem_ops && ctlr->mem_ops->supports_op)
+		return ctlr->mem_ops->supports_op(mem, op);
+
+	return spi_mem_default_supports_op(mem, op);
+}
+EXPORT_SYMBOL_GPL(spi_mem_supports_op);
+
+/**
+ * spi_mem_exec_op() - Execute a memory operation
+ * @mem: the SPI memory
+ * @op: the memory operation to execute
+ *
+ * Executes a memory operation.
+ *
+ * This function first checks that @op is supported and then tries to execute
+ * it.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
+{
+	unsigned int tmpbufsize, xferpos = 0, totalxferlen = 0;
+	struct spi_controller *ctlr = mem->spi->controller;
+	struct spi_transfer xfers[4] = { };
+	struct spi_message msg;
+	u8 *tmpbuf;
+	int ret;
+
+	if (!spi_mem_supports_op(mem, op))
+		return -ENOTSUPP;
+
+	if (ctlr->mem_ops) {
+		/*
+		 * Flush the message queue before executing our SPI memory
+		 * operation to prevent preemption of regular SPI transfers.
+		 */
+		spi_flush_queue(ctlr);
+
+		if (ctlr->auto_runtime_pm) {
+			ret = pm_runtime_get_sync(ctlr->dev.parent);
+			if (ret < 0) {
+				dev_err(&ctlr->dev,
+					"Failed to power device: %d\n",
+					ret);
+				return ret;
+			}
+		}
+
+		mutex_lock(&ctlr->bus_lock_mutex);
+		mutex_lock(&ctlr->io_mutex);
+		ret = ctlr->mem_ops->exec_op(mem, op);
+		mutex_unlock(&ctlr->io_mutex);
+		mutex_unlock(&ctlr->bus_lock_mutex);
+
+		if (ctlr->auto_runtime_pm)
+			pm_runtime_put(ctlr->dev.parent);
+
+		/*
+		 * Some controllers only optimize specific paths (typically the
+		 * read path) and expect the core to use the regular SPI
+		 * interface in other cases.
+		 */
+		if (!ret || ret != -ENOTSUPP)
+			return ret;
+	}
+
+	tmpbufsize = sizeof(op->cmd.opcode) + op->addr.nbytes +
+		     op->dummy.nbytes;
+
+	/*
+	 * Allocate a buffer to transmit the CMD, ADDR cycles with kmalloc() so
+	 * we're guaranteed that this buffer is DMA-able, as required by the
+	 * SPI layer.
+	 */
+	tmpbuf = kzalloc(tmpbufsize, GFP_KERNEL | GFP_DMA);
+	if (!tmpbuf)
+		return -ENOMEM;
+
+	spi_message_init(&msg);
+
+	tmpbuf[0] = op->cmd.opcode;
+	xfers[xferpos].tx_buf = tmpbuf;
+	xfers[xferpos].len = sizeof(op->cmd.opcode);
+	xfers[xferpos].tx_nbits = op->cmd.buswidth;
+	spi_message_add_tail(&xfers[xferpos], &msg);
+	xferpos++;
+	totalxferlen++;
+
+	if (op->addr.nbytes) {
+		int i;
+
+		for (i = 0; i < op->addr.nbytes; i++)
+			tmpbuf[i + 1] = op->addr.val >>
+					(8 * (op->addr.nbytes - i - 1));
+
+		xfers[xferpos].tx_buf = tmpbuf + 1;
+		xfers[xferpos].len = op->addr.nbytes;
+		xfers[xferpos].tx_nbits = op->addr.buswidth;
+		spi_message_add_tail(&xfers[xferpos], &msg);
+		xferpos++;
+		totalxferlen += op->addr.nbytes;
+	}
+
+	if (op->dummy.nbytes) {
+		memset(tmpbuf + op->addr.nbytes + 1, 0xff, op->dummy.nbytes);
+		xfers[xferpos].tx_buf = tmpbuf + op->addr.nbytes + 1;
+		xfers[xferpos].len = op->dummy.nbytes;
+		xfers[xferpos].tx_nbits = op->dummy.buswidth;
+		spi_message_add_tail(&xfers[xferpos], &msg);
+		xferpos++;
+		totalxferlen += op->dummy.nbytes;
+	}
+
+	if (op->data.nbytes) {
+		if (op->data.dir == SPI_MEM_DATA_IN) {
+			xfers[xferpos].rx_buf = op->data.buf.in;
+			xfers[xferpos].rx_nbits = op->data.buswidth;
+		} else {
+			xfers[xferpos].tx_buf = op->data.buf.out;
+			xfers[xferpos].tx_nbits = op->data.buswidth;
+		}
+
+		xfers[xferpos].len = op->data.nbytes;
+		spi_message_add_tail(&xfers[xferpos], &msg);
+		xferpos++;
+		totalxferlen += op->data.nbytes;
+	}
+
+	ret = spi_sync(mem->spi, &msg);
+
+	kfree(tmpbuf);
+
+	if (ret)
+		return ret;
+
+	if (msg.actual_length != totalxferlen)
+		return -EIO;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(spi_mem_exec_op);
+
+/**
+ * spi_mem_adjust_op_size() - Adjust the data size of a SPI mem operation to
+ *			      match controller limitations
+ * @mem: the SPI memory
+ * @op: the operation to adjust
+ *
+ * Some controllers have FIFO limitations and must split a data transfer
+ * operation into multiple ones, others require a specific alignment for
+ * optimized accesses. This function allows SPI mem drivers to split a single
+ * operation into multiple sub-operations when required.
+ *
+ * Return: a negative error code if the controller can't properly adjust @op,
+ *	   0 otherwise. Note that @op->data.nbytes will be updated if @op
+ *	   can't be handled in a single step.
+ */
+int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
+{
+	struct spi_controller *ctlr = mem->spi->controller;
+
+	if (ctlr->mem_ops && ctlr->mem_ops->adjust_op_size)
+		return ctlr->mem_ops->adjust_op_size(mem, op);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(spi_mem_adjust_op_size);
+
+static inline struct spi_mem_driver *to_spi_mem_drv(struct device_driver *drv)
+{
+	return container_of(drv, struct spi_mem_driver, spidrv.driver);
+}
+
+static int spi_mem_probe(struct spi_device *spi)
+{
+	struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+	struct spi_mem *mem;
+
+	mem = devm_kzalloc(&spi->dev, sizeof(*mem), GFP_KERNEL);
+	if (!mem)
+		return -ENOMEM;
+
+	mem->spi = spi;
+	spi_set_drvdata(spi, mem);
+
+	return memdrv->probe(mem);
+}
+
+static int spi_mem_remove(struct spi_device *spi)
+{
+	struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+	struct spi_mem *mem = spi_get_drvdata(spi);
+
+	if (memdrv->remove)
+		return memdrv->remove(mem);
+
+	return 0;
+}
+
+static void spi_mem_shutdown(struct spi_device *spi)
+{
+	struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+	struct spi_mem *mem = spi_get_drvdata(spi);
+
+	if (memdrv->shutdown)
+		memdrv->shutdown(mem);
+}
+
+/**
+ * spi_mem_driver_register_with_owner() - Register a SPI memory driver
+ * @memdrv: the SPI memory driver to register
+ * @owner: the owner of this driver
+ *
+ * Registers a SPI memory driver.
+ *
+ * Return: 0 in case of success, a negative error core otherwise.
+ */
+
+int spi_mem_driver_register_with_owner(struct spi_mem_driver *memdrv,
+				       struct module *owner)
+{
+	memdrv->spidrv.probe = spi_mem_probe;
+	memdrv->spidrv.remove = spi_mem_remove;
+	memdrv->spidrv.shutdown = spi_mem_shutdown;
+
+	return __spi_register_driver(owner, &memdrv->spidrv);
+}
+EXPORT_SYMBOL_GPL(spi_mem_driver_register_with_owner);
+
+/**
+ * spi_mem_driver_unregister_with_owner() - Unregister a SPI memory driver
+ * @memdrv: the SPI memory driver to unregister
+ *
+ * Unregisters a SPI memory driver.
+ */
+void spi_mem_driver_unregister(struct spi_mem_driver *memdrv)
+{
+	spi_unregister_driver(&memdrv->spidrv);
+}
+EXPORT_SYMBOL_GPL(spi_mem_driver_unregister);
diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index 5c82910e3480..7fe4488ace57 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -574,10 +574,15 @@ static int meson_spicc_probe(struct platform_device *pdev)
 		master->max_speed_hz = rate >> 2;
 
 	ret = devm_spi_register_master(&pdev->dev, master);
-	if (!ret)
-		return 0;
+	if (ret) {
+		dev_err(&pdev->dev, "spi master registration failed\n");
+		goto out_clk;
+	}
 
-	dev_err(&pdev->dev, "spi master registration failed\n");
+	return 0;
+
+out_clk:
+	clk_disable_unprepare(spicc->core);
 
 out_master:
 	spi_master_put(master);
diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c
index e8b59ce4dc3a..0e55784a3ad9 100644
--- a/drivers/spi/spi-mpc52xx.c
+++ b/drivers/spi/spi-mpc52xx.c
@@ -447,7 +447,7 @@ static int mpc52xx_spi_probe(struct platform_device *op)
 
 		for (i = 0; i < ms->gpio_cs_count; i++) {
 			gpio_cs = of_get_gpio(op->dev.of_node, i);
-			if (gpio_cs < 0) {
+			if (!gpio_is_valid(gpio_cs)) {
 				dev_err(&op->dev,
 					"could not parse the gpio field in oftree\n");
 				rc = -ENODEV;
diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c
index 3d216b950b41..6ac95a2a21ce 100644
--- a/drivers/spi/spi-mxs.c
+++ b/drivers/spi/spi-mxs.c
@@ -1,32 +1,22 @@
-/*
- * Freescale MXS SPI master driver
- *
- * Copyright 2012 DENX Software Engineering, GmbH.
- * Copyright 2012 Freescale Semiconductor, Inc.
- * Copyright 2008 Embedded Alley Solutions, Inc All Rights Reserved.
- *
- * Rework and transition to new API by:
- * Marek Vasut <marex@denx.de>
- *
- * Based on previous attempt by:
- * Fabio Estevam <fabio.estevam@freescale.com>
- *
- * Based on code from U-Boot bootloader by:
- * Marek Vasut <marex@denx.de>
- *
- * Based on spi-stmp.c, which is:
- * Author: Dmitry Pervushin <dimka@embeddedalley.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Freescale MXS SPI master driver
+//
+// Copyright 2012 DENX Software Engineering, GmbH.
+// Copyright 2012 Freescale Semiconductor, Inc.
+// Copyright 2008 Embedded Alley Solutions, Inc All Rights Reserved.
+//
+// Rework and transition to new API by:
+// Marek Vasut <marex@denx.de>
+//
+// Based on previous attempt by:
+// Fabio Estevam <fabio.estevam@freescale.com>
+//
+// Based on code from U-Boot bootloader by:
+// Marek Vasut <marex@denx.de>
+//
+// Based on spi-stmp.c, which is:
+// Author: Dmitry Pervushin <dimka@embeddedalley.com>
 
 #include <linux/kernel.h>
 #include <linux/ioport.h>
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 9bf64e6eca9b..6c628a54e946 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -255,6 +255,7 @@ static void omap2_mcspi_set_cs(struct spi_device *spi, bool enable)
 	if (spi->controller_state) {
 		int err = pm_runtime_get_sync(mcspi->dev);
 		if (err < 0) {
+			pm_runtime_put_noidle(mcspi->dev);
 			dev_err(mcspi->dev, "failed to get sync: %d\n", err);
 			return;
 		}
@@ -350,20 +351,6 @@ disable_fifo:
 	mcspi->fifo_depth = 0;
 }
 
-static void omap2_mcspi_restore_ctx(struct omap2_mcspi *mcspi)
-{
-	struct spi_master	*spi_cntrl = mcspi->master;
-	struct omap2_mcspi_regs	*ctx = &mcspi->ctx;
-	struct omap2_mcspi_cs	*cs;
-
-	/* McSPI: context restore */
-	mcspi_write_reg(spi_cntrl, OMAP2_MCSPI_MODULCTRL, ctx->modulctrl);
-	mcspi_write_reg(spi_cntrl, OMAP2_MCSPI_WAKEUPENABLE, ctx->wakeupenable);
-
-	list_for_each_entry(cs, &ctx->cs, node)
-		writel_relaxed(cs->chconf0, cs->base + OMAP2_MCSPI_CHCONF0);
-}
-
 static int mcspi_wait_for_reg_bit(void __iomem *reg, unsigned long bit)
 {
 	unsigned long timeout;
@@ -1065,8 +1052,11 @@ static int omap2_mcspi_setup(struct spi_device *spi)
 	}
 
 	ret = pm_runtime_get_sync(mcspi->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(mcspi->dev);
+
 		return ret;
+	}
 
 	ret = omap2_mcspi_setup_transfer(spi, NULL);
 	pm_runtime_mark_last_busy(mcspi->dev);
@@ -1284,8 +1274,11 @@ static int omap2_mcspi_master_setup(struct omap2_mcspi *mcspi)
 	int			ret = 0;
 
 	ret = pm_runtime_get_sync(mcspi->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(mcspi->dev);
+
 		return ret;
+	}
 
 	mcspi_write_reg(master, OMAP2_MCSPI_WAKEUPENABLE,
 			OMAP2_MCSPI_WAKEUPENABLE_WKEN);
@@ -1297,14 +1290,39 @@ static int omap2_mcspi_master_setup(struct omap2_mcspi *mcspi)
 	return 0;
 }
 
+/*
+ * When SPI wake up from off-mode, CS is in activate state. If it was in
+ * inactive state when driver was suspend, then force it to inactive state at
+ * wake up.
+ */
 static int omap_mcspi_runtime_resume(struct device *dev)
 {
-	struct omap2_mcspi	*mcspi;
-	struct spi_master	*master;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+	struct omap2_mcspi_regs *ctx = &mcspi->ctx;
+	struct omap2_mcspi_cs *cs;
 
-	master = dev_get_drvdata(dev);
-	mcspi = spi_master_get_devdata(master);
-	omap2_mcspi_restore_ctx(mcspi);
+	/* McSPI: context restore */
+	mcspi_write_reg(master, OMAP2_MCSPI_MODULCTRL, ctx->modulctrl);
+	mcspi_write_reg(master, OMAP2_MCSPI_WAKEUPENABLE, ctx->wakeupenable);
+
+	list_for_each_entry(cs, &ctx->cs, node) {
+		/*
+		 * We need to toggle CS state for OMAP take this
+		 * change in account.
+		 */
+		if ((cs->chconf0 & OMAP2_MCSPI_CHCONF_FORCE) == 0) {
+			cs->chconf0 |= OMAP2_MCSPI_CHCONF_FORCE;
+			writel_relaxed(cs->chconf0,
+				       cs->base + OMAP2_MCSPI_CHCONF0);
+			cs->chconf0 &= ~OMAP2_MCSPI_CHCONF_FORCE;
+			writel_relaxed(cs->chconf0,
+				       cs->base + OMAP2_MCSPI_CHCONF0);
+		} else {
+			writel_relaxed(cs->chconf0,
+				       cs->base + OMAP2_MCSPI_CHCONF0);
+		}
+	}
 
 	return 0;
 }
@@ -1447,50 +1465,33 @@ static int omap2_mcspi_remove(struct platform_device *pdev)
 MODULE_ALIAS("platform:omap2_mcspi");
 
 #ifdef	CONFIG_SUSPEND
-/*
- * When SPI wake up from off-mode, CS is in activate state. If it was in
- * unactive state when driver was suspend, then force it to unactive state at
- * wake up.
- */
-static int omap2_mcspi_resume(struct device *dev)
+static int omap2_mcspi_suspend_noirq(struct device *dev)
 {
-	struct spi_master	*master = dev_get_drvdata(dev);
-	struct omap2_mcspi	*mcspi = spi_master_get_devdata(master);
-	struct omap2_mcspi_regs	*ctx = &mcspi->ctx;
-	struct omap2_mcspi_cs	*cs;
-
-	pm_runtime_get_sync(mcspi->dev);
-	list_for_each_entry(cs, &ctx->cs, node) {
-		if ((cs->chconf0 & OMAP2_MCSPI_CHCONF_FORCE) == 0) {
-			/*
-			 * We need to toggle CS state for OMAP take this
-			 * change in account.
-			 */
-			cs->chconf0 |= OMAP2_MCSPI_CHCONF_FORCE;
-			writel_relaxed(cs->chconf0, cs->base + OMAP2_MCSPI_CHCONF0);
-			cs->chconf0 &= ~OMAP2_MCSPI_CHCONF_FORCE;
-			writel_relaxed(cs->chconf0, cs->base + OMAP2_MCSPI_CHCONF0);
-		}
-	}
-	pm_runtime_mark_last_busy(mcspi->dev);
-	pm_runtime_put_autosuspend(mcspi->dev);
-
-	return pinctrl_pm_select_default_state(dev);
+	return pinctrl_pm_select_sleep_state(dev);
 }
 
-static int omap2_mcspi_suspend(struct device *dev)
+static int omap2_mcspi_resume_noirq(struct device *dev)
 {
-	return pinctrl_pm_select_sleep_state(dev);
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+	int error;
+
+	error = pinctrl_pm_select_default_state(dev);
+	if (error)
+		dev_warn(mcspi->dev, "%s: failed to set pins: %i\n",
+			 __func__, error);
+
+	return 0;
 }
 
 #else
-#define omap2_mcspi_suspend	NULL
-#define	omap2_mcspi_resume	NULL
+#define omap2_mcspi_suspend_noirq	NULL
+#define omap2_mcspi_resume_noirq	NULL
 #endif
 
 static const struct dev_pm_ops omap2_mcspi_pm_ops = {
-	.resume = omap2_mcspi_resume,
-	.suspend = omap2_mcspi_suspend,
+	.suspend_noirq = omap2_mcspi_suspend_noirq,
+	.resume_noirq = omap2_mcspi_resume_noirq,
 	.runtime_resume	= omap_mcspi_runtime_resume,
 };
 
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index 3d7f66080c57..2fa7f4b43492 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -51,19 +51,15 @@ static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data,
 		if (!pxa25x_ssp_comp(drv_data))
 			pxa2xx_spi_write(drv_data, SSTO, 0);
 
-		if (!error) {
-			msg->actual_length += drv_data->len;
-			msg->state = pxa2xx_spi_next_transfer(drv_data);
-		} else {
+		if (error) {
 			/* In case we got an error we disable the SSP now */
 			pxa2xx_spi_write(drv_data, SSCR0,
 					 pxa2xx_spi_read(drv_data, SSCR0)
 					 & ~SSCR0_SSE);
-
-			msg->state = ERROR_STATE;
+			msg->status = -EIO;
 		}
 
-		tasklet_schedule(&drv_data->pump_transfers);
+		spi_finalize_current_transfer(drv_data->master);
 	}
 }
 
@@ -74,11 +70,11 @@ static void pxa2xx_spi_dma_callback(void *data)
 
 static struct dma_async_tx_descriptor *
 pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
-			   enum dma_transfer_direction dir)
+			   enum dma_transfer_direction dir,
+			   struct spi_transfer *xfer)
 {
 	struct chip_data *chip =
 		spi_get_ctldata(drv_data->master->cur_msg->spi);
-	struct spi_transfer *xfer = drv_data->cur_transfer;
 	enum dma_slave_buswidth width;
 	struct dma_slave_config cfg;
 	struct dma_chan *chan;
@@ -144,12 +140,13 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data)
 	return IRQ_NONE;
 }
 
-int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, u32 dma_burst)
+int pxa2xx_spi_dma_prepare(struct driver_data *drv_data,
+			   struct spi_transfer *xfer)
 {
 	struct dma_async_tx_descriptor *tx_desc, *rx_desc;
 	int err;
 
-	tx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_MEM_TO_DEV);
+	tx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_MEM_TO_DEV, xfer);
 	if (!tx_desc) {
 		dev_err(&drv_data->pdev->dev,
 			"failed to get DMA TX descriptor\n");
@@ -157,7 +154,7 @@ int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, u32 dma_burst)
 		goto err_tx;
 	}
 
-	rx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_DEV_TO_MEM);
+	rx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_DEV_TO_MEM, xfer);
 	if (!rx_desc) {
 		dev_err(&drv_data->pdev->dev,
 			"failed to get DMA RX descriptor\n");
@@ -187,6 +184,13 @@ void pxa2xx_spi_dma_start(struct driver_data *drv_data)
 	atomic_set(&drv_data->dma_running, 1);
 }
 
+void pxa2xx_spi_dma_stop(struct driver_data *drv_data)
+{
+	atomic_set(&drv_data->dma_running, 0);
+	dmaengine_terminate_sync(drv_data->master->dma_rx);
+	dmaengine_terminate_sync(drv_data->master->dma_tx);
+}
+
 int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
 {
 	struct pxa2xx_spi_master *pdata = drv_data->master_info;
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 82dcb88fcfba..0b2d60d30f69 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -340,9 +340,11 @@ static void lpss_ssp_setup(struct driver_data *drv_data)
 	}
 }
 
-static void lpss_ssp_select_cs(struct driver_data *drv_data,
+static void lpss_ssp_select_cs(struct spi_device *spi,
 			       const struct lpss_config *config)
 {
+	struct driver_data *drv_data =
+		spi_controller_get_devdata(spi->controller);
 	u32 value, cs;
 
 	if (!config->cs_sel_mask)
@@ -350,7 +352,7 @@ static void lpss_ssp_select_cs(struct driver_data *drv_data,
 
 	value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl);
 
-	cs = drv_data->master->cur_msg->spi->chip_select;
+	cs = spi->chip_select;
 	cs <<= config->cs_sel_shift;
 	if (cs != (value & config->cs_sel_mask)) {
 		/*
@@ -369,15 +371,17 @@ static void lpss_ssp_select_cs(struct driver_data *drv_data,
 	}
 }
 
-static void lpss_ssp_cs_control(struct driver_data *drv_data, bool enable)
+static void lpss_ssp_cs_control(struct spi_device *spi, bool enable)
 {
+	struct driver_data *drv_data =
+		spi_controller_get_devdata(spi->controller);
 	const struct lpss_config *config;
 	u32 value;
 
 	config = lpss_get_config(drv_data);
 
 	if (enable)
-		lpss_ssp_select_cs(drv_data, config);
+		lpss_ssp_select_cs(spi, config);
 
 	value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl);
 	if (enable)
@@ -387,10 +391,11 @@ static void lpss_ssp_cs_control(struct driver_data *drv_data, bool enable)
 	__lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value);
 }
 
-static void cs_assert(struct driver_data *drv_data)
+static void cs_assert(struct spi_device *spi)
 {
-	struct chip_data *chip =
-		spi_get_ctldata(drv_data->master->cur_msg->spi);
+	struct chip_data *chip = spi_get_ctldata(spi);
+	struct driver_data *drv_data =
+		spi_controller_get_devdata(spi->controller);
 
 	if (drv_data->ssp_type == CE4100_SSP) {
 		pxa2xx_spi_write(drv_data, SSSR, chip->frm);
@@ -408,13 +413,14 @@ static void cs_assert(struct driver_data *drv_data)
 	}
 
 	if (is_lpss_ssp(drv_data))
-		lpss_ssp_cs_control(drv_data, true);
+		lpss_ssp_cs_control(spi, true);
 }
 
-static void cs_deassert(struct driver_data *drv_data)
+static void cs_deassert(struct spi_device *spi)
 {
-	struct chip_data *chip =
-		spi_get_ctldata(drv_data->master->cur_msg->spi);
+	struct chip_data *chip = spi_get_ctldata(spi);
+	struct driver_data *drv_data =
+		spi_controller_get_devdata(spi->controller);
 	unsigned long timeout;
 
 	if (drv_data->ssp_type == CE4100_SSP)
@@ -437,7 +443,15 @@ static void cs_deassert(struct driver_data *drv_data)
 	}
 
 	if (is_lpss_ssp(drv_data))
-		lpss_ssp_cs_control(drv_data, false);
+		lpss_ssp_cs_control(spi, false);
+}
+
+static void pxa2xx_spi_set_cs(struct spi_device *spi, bool level)
+{
+	if (level)
+		cs_deassert(spi);
+	else
+		cs_assert(spi);
 }
 
 int pxa2xx_spi_flush(struct driver_data *drv_data)
@@ -549,70 +563,6 @@ static int u32_reader(struct driver_data *drv_data)
 	return drv_data->rx == drv_data->rx_end;
 }
 
-void *pxa2xx_spi_next_transfer(struct driver_data *drv_data)
-{
-	struct spi_message *msg = drv_data->master->cur_msg;
-	struct spi_transfer *trans = drv_data->cur_transfer;
-
-	/* Move to next transfer */
-	if (trans->transfer_list.next != &msg->transfers) {
-		drv_data->cur_transfer =
-			list_entry(trans->transfer_list.next,
-					struct spi_transfer,
-					transfer_list);
-		return RUNNING_STATE;
-	} else
-		return DONE_STATE;
-}
-
-/* caller already set message->status; dma and pio irqs are blocked */
-static void giveback(struct driver_data *drv_data)
-{
-	struct spi_transfer* last_transfer;
-	struct spi_message *msg;
-
-	msg = drv_data->master->cur_msg;
-	drv_data->cur_transfer = NULL;
-
-	last_transfer = list_last_entry(&msg->transfers, struct spi_transfer,
-					transfer_list);
-
-	/* Delay if requested before any change in chip select */
-	if (last_transfer->delay_usecs)
-		udelay(last_transfer->delay_usecs);
-
-	/* Drop chip select UNLESS cs_change is true or we are returning
-	 * a message with an error, or next message is for another chip
-	 */
-	if (!last_transfer->cs_change)
-		cs_deassert(drv_data);
-	else {
-		struct spi_message *next_msg;
-
-		/* Holding of cs was hinted, but we need to make sure
-		 * the next message is for the same chip.  Don't waste
-		 * time with the following tests unless this was hinted.
-		 *
-		 * We cannot postpone this until pump_messages, because
-		 * after calling msg->complete (below) the driver that
-		 * sent the current message could be unloaded, which
-		 * could invalidate the cs_control() callback...
-		 */
-
-		/* get a pointer to the next message, if any */
-		next_msg = spi_get_next_queued_message(drv_data->master);
-
-		/* see if the next and current messages point
-		 * to the same chip
-		 */
-		if ((next_msg && next_msg->spi != msg->spi) ||
-		    msg->state == ERROR_STATE)
-			cs_deassert(drv_data);
-	}
-
-	spi_finalize_current_message(drv_data->master);
-}
-
 static void reset_sccr1(struct driver_data *drv_data)
 {
 	struct chip_data *chip =
@@ -648,8 +598,8 @@ static void int_error_stop(struct driver_data *drv_data, const char* msg)
 
 	dev_err(&drv_data->pdev->dev, "%s\n", msg);
 
-	drv_data->master->cur_msg->state = ERROR_STATE;
-	tasklet_schedule(&drv_data->pump_transfers);
+	drv_data->master->cur_msg->status = -EIO;
+	spi_finalize_current_transfer(drv_data->master);
 }
 
 static void int_transfer_complete(struct driver_data *drv_data)
@@ -660,19 +610,7 @@ static void int_transfer_complete(struct driver_data *drv_data)
 	if (!pxa25x_ssp_comp(drv_data))
 		pxa2xx_spi_write(drv_data, SSTO, 0);
 
-	/* Update total byte transferred return count actual bytes read */
-	drv_data->master->cur_msg->actual_length += drv_data->len -
-				(drv_data->rx_end - drv_data->rx);
-
-	/* Transfer delays and chip select release are
-	 * handled in pump_transfers or giveback
-	 */
-
-	/* Move to next transfer */
-	drv_data->master->cur_msg->state = pxa2xx_spi_next_transfer(drv_data);
-
-	/* Schedule transfer tasklet */
-	tasklet_schedule(&drv_data->pump_transfers);
+	spi_finalize_current_transfer(drv_data->master);
 }
 
 static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
@@ -973,17 +911,16 @@ static bool pxa2xx_spi_can_dma(struct spi_controller *master,
 	       xfer->len >= chip->dma_burst_size;
 }
 
-static void pump_transfers(unsigned long data)
+static int pxa2xx_spi_transfer_one(struct spi_controller *master,
+				   struct spi_device *spi,
+				   struct spi_transfer *transfer)
 {
-	struct driver_data *drv_data = (struct driver_data *)data;
-	struct spi_controller *master = drv_data->master;
+	struct driver_data *drv_data = spi_controller_get_devdata(master);
 	struct spi_message *message = master->cur_msg;
 	struct chip_data *chip = spi_get_ctldata(message->spi);
 	u32 dma_thresh = chip->dma_threshold;
 	u32 dma_burst = chip->dma_burst_size;
 	u32 change_mask = pxa2xx_spi_get_ssrc1_change_mask(drv_data);
-	struct spi_transfer *transfer;
-	struct spi_transfer *previous;
 	u32 clk_div;
 	u8 bits;
 	u32 speed;
@@ -992,36 +929,6 @@ static void pump_transfers(unsigned long data)
 	int err;
 	int dma_mapped;
 
-	/* Get current state information */
-	transfer = drv_data->cur_transfer;
-
-	/* Handle for abort */
-	if (message->state == ERROR_STATE) {
-		message->status = -EIO;
-		giveback(drv_data);
-		return;
-	}
-
-	/* Handle end of message */
-	if (message->state == DONE_STATE) {
-		message->status = 0;
-		giveback(drv_data);
-		return;
-	}
-
-	/* Delay if requested at end of transfer before CS change */
-	if (message->state == RUNNING_STATE) {
-		previous = list_entry(transfer->transfer_list.prev,
-					struct spi_transfer,
-					transfer_list);
-		if (previous->delay_usecs)
-			udelay(previous->delay_usecs);
-
-		/* Drop chip select only if cs_change is requested */
-		if (previous->cs_change)
-			cs_deassert(drv_data);
-	}
-
 	/* Check if we can DMA this transfer */
 	if (transfer->len > MAX_DMA_LEN && chip->enable_dma) {
 
@@ -1029,34 +936,27 @@ static void pump_transfers(unsigned long data)
 		if (message->is_dma_mapped
 				|| transfer->rx_dma || transfer->tx_dma) {
 			dev_err(&drv_data->pdev->dev,
-				"pump_transfers: mapped transfer length of "
-				"%u is greater than %d\n",
+				"Mapped transfer length of %u is greater than %d\n",
 				transfer->len, MAX_DMA_LEN);
-			message->status = -EINVAL;
-			giveback(drv_data);
-			return;
+			return -EINVAL;
 		}
 
 		/* warn ... we force this to PIO mode */
 		dev_warn_ratelimited(&message->spi->dev,
-				     "pump_transfers: DMA disabled for transfer length %ld "
-				     "greater than %d\n",
-				     (long)drv_data->len, MAX_DMA_LEN);
+				     "DMA disabled for transfer length %ld greater than %d\n",
+				     (long)transfer->len, MAX_DMA_LEN);
 	}
 
 	/* Setup the transfer state based on the type of transfer */
 	if (pxa2xx_spi_flush(drv_data) == 0) {
-		dev_err(&drv_data->pdev->dev, "pump_transfers: flush failed\n");
-		message->status = -EIO;
-		giveback(drv_data);
-		return;
+		dev_err(&drv_data->pdev->dev, "Flush failed\n");
+		return -EIO;
 	}
 	drv_data->n_bytes = chip->n_bytes;
 	drv_data->tx = (void *)transfer->tx_buf;
 	drv_data->tx_end = drv_data->tx + transfer->len;
 	drv_data->rx = transfer->rx_buf;
 	drv_data->rx_end = drv_data->rx + transfer->len;
-	drv_data->len = transfer->len;
 	drv_data->write = drv_data->tx ? chip->write : null_writer;
 	drv_data->read = drv_data->rx ? chip->read : null_reader;
 
@@ -1095,11 +995,9 @@ static void pump_transfers(unsigned long data)
 						bits, &dma_burst,
 						&dma_thresh))
 			dev_warn_ratelimited(&message->spi->dev,
-					     "pump_transfers: DMA burst size reduced to match bits_per_word\n");
+					     "DMA burst size reduced to match bits_per_word\n");
 	}
 
-	message->state = RUNNING_STATE;
-
 	dma_mapped = master->can_dma &&
 		     master->can_dma(master, message->spi, transfer) &&
 		     master->cur_msg_mapped;
@@ -1108,12 +1006,9 @@ static void pump_transfers(unsigned long data)
 		/* Ensure we have the correct interrupt handler */
 		drv_data->transfer_handler = pxa2xx_spi_dma_transfer;
 
-		err = pxa2xx_spi_dma_prepare(drv_data, dma_burst);
-		if (err) {
-			message->status = err;
-			giveback(drv_data);
-			return;
-		}
+		err = pxa2xx_spi_dma_prepare(drv_data, transfer);
+		if (err)
+			return err;
 
 		/* Clear status and start DMA engine */
 		cr1 = chip->cr1 | dma_thresh | drv_data->dma_cr1;
@@ -1175,27 +1070,40 @@ static void pump_transfers(unsigned long data)
 			pxa2xx_spi_write(drv_data, SSTO, chip->timeout);
 	}
 
-	cs_assert(drv_data);
-
-	/* after chip select, release the data by enabling service
-	 * requests and interrupts, without changing any mode bits */
+	/*
+	 * Release the data by enabling service requests and interrupts,
+	 * without changing any mode bits
+	 */
 	pxa2xx_spi_write(drv_data, SSCR1, cr1);
+
+	return 1;
 }
 
-static int pxa2xx_spi_transfer_one_message(struct spi_controller *master,
-					   struct spi_message *msg)
+static void pxa2xx_spi_handle_err(struct spi_controller *master,
+				 struct spi_message *msg)
 {
 	struct driver_data *drv_data = spi_controller_get_devdata(master);
 
-	/* Initial message state*/
-	msg->state = START_STATE;
-	drv_data->cur_transfer = list_entry(msg->transfers.next,
-						struct spi_transfer,
-						transfer_list);
+	/* Disable the SSP */
+	pxa2xx_spi_write(drv_data, SSCR0,
+			 pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE);
+	/* Clear and disable interrupts and service requests */
+	write_SSSR_CS(drv_data, drv_data->clear_sr);
+	pxa2xx_spi_write(drv_data, SSCR1,
+			 pxa2xx_spi_read(drv_data, SSCR1)
+			 & ~(drv_data->int_cr1 | drv_data->dma_cr1));
+	if (!pxa25x_ssp_comp(drv_data))
+		pxa2xx_spi_write(drv_data, SSTO, 0);
 
-	/* Mark as busy and launch transfers */
-	tasklet_schedule(&drv_data->pump_transfers);
-	return 0;
+	/*
+	 * Stop the DMA if running. Note DMA callback handler may have unset
+	 * the dma_running already, which is fine as stopping is not needed
+	 * then but we shouldn't rely this flag for anything else than
+	 * stopping. For instance to differentiate between PIO and DMA
+	 * transfers.
+	 */
+	if (atomic_read(&drv_data->dma_running))
+		pxa2xx_spi_dma_stop(drv_data);
 }
 
 static int pxa2xx_spi_unprepare_transfer(struct spi_controller *master)
@@ -1651,7 +1559,9 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	master->dma_alignment = DMA_ALIGNMENT;
 	master->cleanup = cleanup;
 	master->setup = setup;
-	master->transfer_one_message = pxa2xx_spi_transfer_one_message;
+	master->set_cs = pxa2xx_spi_set_cs;
+	master->transfer_one = pxa2xx_spi_transfer_one;
+	master->handle_err = pxa2xx_spi_handle_err;
 	master->unprepare_transfer_hardware = pxa2xx_spi_unprepare_transfer;
 	master->fw_translate_cs = pxa2xx_spi_fw_translate_cs;
 	master->auto_runtime_pm = true;
@@ -1702,7 +1612,9 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	}
 
 	/* Enable SOC clock */
-	clk_prepare_enable(ssp->clk);
+	status = clk_prepare_enable(ssp->clk);
+	if (status)
+		goto out_error_dma_irq_alloc;
 
 	master->max_speed_hz = clk_get_rate(ssp->clk);
 
@@ -1787,9 +1699,6 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 		}
 	}
 
-	tasklet_init(&drv_data->pump_transfers, pump_transfers,
-		     (unsigned long)drv_data);
-
 	pm_runtime_set_autosuspend_delay(&pdev->dev, 50);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_set_active(&pdev->dev);
@@ -1809,6 +1718,8 @@ out_error_clock_enabled:
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	clk_disable_unprepare(ssp->clk);
+
+out_error_dma_irq_alloc:
 	pxa2xx_spi_dma_release(drv_data);
 	free_irq(ssp->irq, drv_data);
 
@@ -1882,8 +1793,11 @@ static int pxa2xx_spi_resume(struct device *dev)
 	int status;
 
 	/* Enable the SSP clock */
-	if (!pm_runtime_suspended(dev))
-		clk_prepare_enable(ssp->clk);
+	if (!pm_runtime_suspended(dev)) {
+		status = clk_prepare_enable(ssp->clk);
+		if (status)
+			return status;
+	}
 
 	/* Restore LPSS private register bits */
 	if (is_lpss_ssp(drv_data))
@@ -1912,9 +1826,10 @@ static int pxa2xx_spi_runtime_suspend(struct device *dev)
 static int pxa2xx_spi_runtime_resume(struct device *dev)
 {
 	struct driver_data *drv_data = dev_get_drvdata(dev);
+	int status;
 
-	clk_prepare_enable(drv_data->ssp->clk);
-	return 0;
+	status = clk_prepare_enable(drv_data->ssp->clk);
+	return status;
 }
 #endif
 
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index 513ec6c6e25b..513c53aaeab2 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -38,7 +38,7 @@ struct driver_data {
 
 	/* SSP register addresses */
 	void __iomem *ioaddr;
-	u32 ssdr_physical;
+	phys_addr_t ssdr_physical;
 
 	/* SSP masks*/
 	u32 dma_cr1;
@@ -46,15 +46,10 @@ struct driver_data {
 	u32 clear_sr;
 	u32 mask_sr;
 
-	/* Message Transfer pump */
-	struct tasklet_struct pump_transfers;
-
 	/* DMA engine support */
 	atomic_t dma_running;
 
-	/* Current message transfer state info */
-	struct spi_transfer *cur_transfer;
-	size_t len;
+	/* Current transfer state info */
 	void *tx;
 	void *tx_end;
 	void *rx;
@@ -104,11 +99,6 @@ static  inline void pxa2xx_spi_write(const struct driver_data *drv_data,
 	__raw_writel(val, drv_data->ioaddr + reg);
 }
 
-#define START_STATE ((void *)0)
-#define RUNNING_STATE ((void *)1)
-#define DONE_STATE ((void *)2)
-#define ERROR_STATE ((void *)-1)
-
 #define DMA_ALIGNMENT		8
 
 static inline int pxa25x_ssp_comp(struct driver_data *drv_data)
@@ -133,14 +123,15 @@ static inline void write_SSSR_CS(struct driver_data *drv_data, u32 val)
 }
 
 extern int pxa2xx_spi_flush(struct driver_data *drv_data);
-extern void *pxa2xx_spi_next_transfer(struct driver_data *drv_data);
 
 #define MAX_DMA_LEN		SZ_64K
 #define DEFAULT_DMA_CR1		(SSCR1_TSRE | SSCR1_RSRE | SSCR1_TRAIL)
 
 extern irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data);
-extern int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, u32 dma_burst);
+extern int pxa2xx_spi_dma_prepare(struct driver_data *drv_data,
+				  struct spi_transfer *xfer);
 extern void pxa2xx_spi_dma_start(struct driver_data *drv_data);
+extern void pxa2xx_spi_dma_stop(struct driver_data *drv_data);
 extern int pxa2xx_spi_dma_setup(struct driver_data *drv_data);
 extern void pxa2xx_spi_dma_release(struct driver_data *drv_data);
 extern int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index baa3a9fa2638..7b7151ec14c8 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -28,15 +28,15 @@
 
 #define S3C64XX_SPI_CH_CFG		0x00
 #define S3C64XX_SPI_CLK_CFG		0x04
-#define S3C64XX_SPI_MODE_CFG	0x08
-#define S3C64XX_SPI_SLAVE_SEL	0x0C
+#define S3C64XX_SPI_MODE_CFG		0x08
+#define S3C64XX_SPI_SLAVE_SEL		0x0C
 #define S3C64XX_SPI_INT_EN		0x10
 #define S3C64XX_SPI_STATUS		0x14
 #define S3C64XX_SPI_TX_DATA		0x18
 #define S3C64XX_SPI_RX_DATA		0x1C
-#define S3C64XX_SPI_PACKET_CNT	0x20
-#define S3C64XX_SPI_PENDING_CLR	0x24
-#define S3C64XX_SPI_SWAP_CFG	0x28
+#define S3C64XX_SPI_PACKET_CNT		0x20
+#define S3C64XX_SPI_PENDING_CLR		0x24
+#define S3C64XX_SPI_SWAP_CFG		0x28
 #define S3C64XX_SPI_FB_CLK		0x2C
 
 #define S3C64XX_SPI_CH_HS_EN		(1<<6)	/* High Speed Enable */
@@ -77,9 +77,9 @@
 #define S3C64XX_SPI_INT_TX_FIFORDY_EN		(1<<0)
 
 #define S3C64XX_SPI_ST_RX_OVERRUN_ERR		(1<<5)
-#define S3C64XX_SPI_ST_RX_UNDERRUN_ERR	(1<<4)
+#define S3C64XX_SPI_ST_RX_UNDERRUN_ERR		(1<<4)
 #define S3C64XX_SPI_ST_TX_OVERRUN_ERR		(1<<3)
-#define S3C64XX_SPI_ST_TX_UNDERRUN_ERR	(1<<2)
+#define S3C64XX_SPI_ST_TX_UNDERRUN_ERR		(1<<2)
 #define S3C64XX_SPI_ST_RX_FIFORDY		(1<<1)
 #define S3C64XX_SPI_ST_TX_FIFORDY		(1<<0)
 
@@ -100,7 +100,7 @@
 #define S3C64XX_SPI_SWAP_TX_BIT			(1<<1)
 #define S3C64XX_SPI_SWAP_TX_EN			(1<<0)
 
-#define S3C64XX_SPI_FBCLK_MSK		(3<<0)
+#define S3C64XX_SPI_FBCLK_MSK			(3<<0)
 
 #define FIFO_LVL_MASK(i) ((i)->port_conf->fifo_lvl_mask[i->port_id])
 #define S3C64XX_SPI_ST_TX_DONE(v, i) (((v) & \
@@ -156,7 +156,6 @@ struct s3c64xx_spi_port_config {
  * @ioclk: Pointer to the i/o clock between master and slave
  * @master: Pointer to the SPI Protocol master.
  * @cntrlr_info: Platform specific data for the controller this driver manages.
- * @tgl_spi: Pointer to the last CS left untoggled by the cs_change hint.
  * @lock: Controller specific lock.
  * @state: Set of FLAGS to indicate status.
  * @rx_dmach: Controller's DMA channel for Rx.
@@ -177,7 +176,6 @@ struct s3c64xx_spi_driver_data {
 	struct platform_device          *pdev;
 	struct spi_master               *master;
 	struct s3c64xx_spi_info  *cntrlr_info;
-	struct spi_device               *tgl_spi;
 	spinlock_t                      lock;
 	unsigned long                   sfr_start;
 	struct completion               xfer_completion;
@@ -190,7 +188,7 @@ struct s3c64xx_spi_driver_data {
 	unsigned int			port_id;
 };
 
-static void flush_fifo(struct s3c64xx_spi_driver_data *sdd)
+static void s3c64xx_flush_fifo(struct s3c64xx_spi_driver_data *sdd)
 {
 	void __iomem *regs = sdd->regs;
 	unsigned long loops;
@@ -350,9 +348,8 @@ static bool s3c64xx_spi_can_dma(struct spi_master *master,
 	return xfer->len > (FIFO_LVL_MASK(sdd) >> 1) + 1;
 }
 
-static void enable_datapath(struct s3c64xx_spi_driver_data *sdd,
-				struct spi_device *spi,
-				struct spi_transfer *xfer, int dma_mode)
+static void s3c64xx_enable_datapath(struct s3c64xx_spi_driver_data *sdd,
+				    struct spi_transfer *xfer, int dma_mode)
 {
 	void __iomem *regs = sdd->regs;
 	u32 modecfg, chcfg;
@@ -442,8 +439,8 @@ static u32 s3c64xx_spi_wait_for_timeout(struct s3c64xx_spi_driver_data *sdd,
 	return RX_FIFO_LVL(status, sdd);
 }
 
-static int wait_for_dma(struct s3c64xx_spi_driver_data *sdd,
-			struct spi_transfer *xfer)
+static int s3c64xx_wait_for_dma(struct s3c64xx_spi_driver_data *sdd,
+				struct spi_transfer *xfer)
 {
 	void __iomem *regs = sdd->regs;
 	unsigned long val;
@@ -485,8 +482,8 @@ static int wait_for_dma(struct s3c64xx_spi_driver_data *sdd,
 	return 0;
 }
 
-static int wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
-			struct spi_transfer *xfer)
+static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
+				struct spi_transfer *xfer)
 {
 	void __iomem *regs = sdd->regs;
 	unsigned long val;
@@ -505,6 +502,8 @@ static int wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
 		status = readl(regs + S3C64XX_SPI_STATUS);
 	} while (RX_FIFO_LVL(status, sdd) < xfer->len && --val);
 
+	if (!val)
+		return -EIO;
 
 	/* If it was only Tx */
 	if (!xfer->rx_buf) {
@@ -635,11 +634,15 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master,
 				    struct spi_transfer *xfer)
 {
 	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(master);
+	const unsigned int fifo_len = (FIFO_LVL_MASK(sdd) >> 1) + 1;
+	const void *tx_buf = NULL;
+	void *rx_buf = NULL;
+	int target_len = 0, origin_len = 0;
+	int use_dma = 0;
 	int status;
 	u32 speed;
 	u8 bpw;
 	unsigned long flags;
-	int use_dma;
 
 	reinit_completion(&sdd->xfer_completion);
 
@@ -654,48 +657,77 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master,
 		s3c64xx_spi_config(sdd);
 	}
 
-	/* Polling method for xfers not bigger than FIFO capacity */
-	use_dma = 0;
-	if (!is_polling(sdd) &&
-	    (sdd->rx_dma.ch && sdd->tx_dma.ch &&
-	     (xfer->len > ((FIFO_LVL_MASK(sdd) >> 1) + 1))))
+	if (!is_polling(sdd) && (xfer->len > fifo_len) &&
+	    sdd->rx_dma.ch && sdd->tx_dma.ch) {
 		use_dma = 1;
 
-	spin_lock_irqsave(&sdd->lock, flags);
+	} else if (is_polling(sdd) && xfer->len > fifo_len) {
+		tx_buf = xfer->tx_buf;
+		rx_buf = xfer->rx_buf;
+		origin_len = xfer->len;
 
-	/* Pending only which is to be done */
-	sdd->state &= ~RXBUSY;
-	sdd->state &= ~TXBUSY;
+		target_len = xfer->len;
+		if (xfer->len > fifo_len)
+			xfer->len = fifo_len;
+	}
 
-	enable_datapath(sdd, spi, xfer, use_dma);
+	do {
+		spin_lock_irqsave(&sdd->lock, flags);
 
-	/* Start the signals */
-	s3c64xx_spi_set_cs(spi, true);
+		/* Pending only which is to be done */
+		sdd->state &= ~RXBUSY;
+		sdd->state &= ~TXBUSY;
 
-	spin_unlock_irqrestore(&sdd->lock, flags);
+		s3c64xx_enable_datapath(sdd, xfer, use_dma);
 
-	if (use_dma)
-		status = wait_for_dma(sdd, xfer);
-	else
-		status = wait_for_pio(sdd, xfer);
-
-	if (status) {
-		dev_err(&spi->dev, "I/O Error: rx-%d tx-%d res:rx-%c tx-%c len-%d\n",
-			xfer->rx_buf ? 1 : 0, xfer->tx_buf ? 1 : 0,
-			(sdd->state & RXBUSY) ? 'f' : 'p',
-			(sdd->state & TXBUSY) ? 'f' : 'p',
-			xfer->len);
-
-		if (use_dma) {
-			if (xfer->tx_buf != NULL
-			    && (sdd->state & TXBUSY))
-				dmaengine_terminate_all(sdd->tx_dma.ch);
-			if (xfer->rx_buf != NULL
-			    && (sdd->state & RXBUSY))
-				dmaengine_terminate_all(sdd->rx_dma.ch);
+		/* Start the signals */
+		s3c64xx_spi_set_cs(spi, true);
+
+		spin_unlock_irqrestore(&sdd->lock, flags);
+
+		if (use_dma)
+			status = s3c64xx_wait_for_dma(sdd, xfer);
+		else
+			status = s3c64xx_wait_for_pio(sdd, xfer);
+
+		if (status) {
+			dev_err(&spi->dev,
+				"I/O Error: rx-%d tx-%d res:rx-%c tx-%c len-%d\n",
+				xfer->rx_buf ? 1 : 0, xfer->tx_buf ? 1 : 0,
+				(sdd->state & RXBUSY) ? 'f' : 'p',
+				(sdd->state & TXBUSY) ? 'f' : 'p',
+				xfer->len);
+
+			if (use_dma) {
+				if (xfer->tx_buf && (sdd->state & TXBUSY))
+					dmaengine_terminate_all(sdd->tx_dma.ch);
+				if (xfer->rx_buf && (sdd->state & RXBUSY))
+					dmaengine_terminate_all(sdd->rx_dma.ch);
+			}
+		} else {
+			s3c64xx_flush_fifo(sdd);
 		}
-	} else {
-		flush_fifo(sdd);
+		if (target_len > 0) {
+			target_len -= xfer->len;
+
+			if (xfer->tx_buf)
+				xfer->tx_buf += xfer->len;
+
+			if (xfer->rx_buf)
+				xfer->rx_buf += xfer->len;
+
+			if (target_len > fifo_len)
+				xfer->len = fifo_len;
+			else
+				xfer->len = target_len;
+		}
+	} while (target_len > 0);
+
+	if (origin_len) {
+		/* Restore original xfer buffers and length */
+		xfer->tx_buf = tx_buf;
+		xfer->rx_buf = rx_buf;
+		xfer->len = origin_len;
 	}
 
 	return status;
@@ -891,7 +923,7 @@ static irqreturn_t s3c64xx_spi_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void s3c64xx_spi_hwinit(struct s3c64xx_spi_driver_data *sdd, int channel)
+static void s3c64xx_spi_hwinit(struct s3c64xx_spi_driver_data *sdd)
 {
 	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	void __iomem *regs = sdd->regs;
@@ -929,7 +961,7 @@ static void s3c64xx_spi_hwinit(struct s3c64xx_spi_driver_data *sdd, int channel)
 	val |= (S3C64XX_SPI_TRAILCNT << S3C64XX_SPI_TRAILCNT_OFF);
 	writel(val, regs + S3C64XX_SPI_MODE_CFG);
 
-	flush_fifo(sdd);
+	s3c64xx_flush_fifo(sdd);
 }
 
 #ifdef CONFIG_OF
@@ -1145,7 +1177,7 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 	pm_runtime_get_sync(&pdev->dev);
 
 	/* Setup Deufult Mode */
-	s3c64xx_spi_hwinit(sdd, sdd->port_id);
+	s3c64xx_spi_hwinit(sdd);
 
 	spin_lock_init(&sdd->lock);
 	init_completion(&sdd->xfer_completion);
@@ -1260,8 +1292,6 @@ static int s3c64xx_spi_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	s3c64xx_spi_hwinit(sdd, sdd->port_id);
-
 	return spi_master_resume(master);
 }
 #endif /* CONFIG_PM_SLEEP */
@@ -1299,6 +1329,8 @@ static int s3c64xx_spi_runtime_resume(struct device *dev)
 	if (ret != 0)
 		goto err_disable_src_clk;
 
+	s3c64xx_spi_hwinit(sdd);
+
 	return 0;
 
 err_disable_src_clk:
@@ -1344,15 +1376,6 @@ static struct s3c64xx_spi_port_config exynos4_spi_port_config = {
 	.clk_from_cmu	= true,
 };
 
-static struct s3c64xx_spi_port_config exynos5440_spi_port_config = {
-	.fifo_lvl_mask	= { 0x1ff },
-	.rx_lvl_offset	= 15,
-	.tx_st_done	= 25,
-	.high_speed	= true,
-	.clk_from_cmu	= true,
-	.quirks		= S3C64XX_SPI_QUIRK_POLL,
-};
-
 static struct s3c64xx_spi_port_config exynos7_spi_port_config = {
 	.fifo_lvl_mask	= { 0x1ff, 0x7F, 0x7F, 0x7F, 0x7F, 0x1ff},
 	.rx_lvl_offset	= 15,
@@ -1396,9 +1419,6 @@ static const struct of_device_id s3c64xx_spi_dt_match[] = {
 	{ .compatible = "samsung,exynos4210-spi",
 			.data = (void *)&exynos4_spi_port_config,
 	},
-	{ .compatible = "samsung,exynos5440-spi",
-			.data = (void *)&exynos5440_spi_port_config,
-	},
 	{ .compatible = "samsung,exynos7-spi",
 			.data = (void *)&exynos7_spi_port_config,
 	},
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index ae086aab57d5..0e74cbf9929d 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -39,7 +39,7 @@ struct sh_msiof_chipdata {
 	u16 tx_fifo_size;
 	u16 rx_fifo_size;
 	u16 master_flags;
-	u16 min_div;
+	u16 min_div_pow;
 };
 
 struct sh_msiof_spi_priv {
@@ -51,7 +51,7 @@ struct sh_msiof_spi_priv {
 	struct completion done;
 	unsigned int tx_fifo_size;
 	unsigned int rx_fifo_size;
-	unsigned int min_div;
+	unsigned int min_div_pow;
 	void *tx_dma_page;
 	void *rx_dma_page;
 	dma_addr_t tx_dma_addr;
@@ -249,42 +249,46 @@ static irqreturn_t sh_msiof_spi_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static struct {
-	unsigned short div;
-	unsigned short brdv;
-} const sh_msiof_spi_div_table[] = {
-	{ 1,	SCR_BRDV_DIV_1 },
-	{ 2,	SCR_BRDV_DIV_2 },
-	{ 4,	SCR_BRDV_DIV_4 },
-	{ 8,	SCR_BRDV_DIV_8 },
-	{ 16,	SCR_BRDV_DIV_16 },
-	{ 32,	SCR_BRDV_DIV_32 },
+static const u32 sh_msiof_spi_div_array[] = {
+	SCR_BRDV_DIV_1, SCR_BRDV_DIV_2,	 SCR_BRDV_DIV_4,
+	SCR_BRDV_DIV_8,	SCR_BRDV_DIV_16, SCR_BRDV_DIV_32,
 };
 
 static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p,
 				      unsigned long parent_rate, u32 spi_hz)
 {
-	unsigned long div = 1024;
+	unsigned long div;
 	u32 brps, scr;
-	size_t k;
+	unsigned int div_pow = p->min_div_pow;
 
-	if (!WARN_ON(!spi_hz || !parent_rate))
-		div = DIV_ROUND_UP(parent_rate, spi_hz);
-
-	div = max_t(unsigned long, div, p->min_div);
+	if (!spi_hz || !parent_rate) {
+		WARN(1, "Invalid clock rate parameters %lu and %u\n",
+		     parent_rate, spi_hz);
+		return;
+	}
 
-	for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_div_table); k++) {
-		brps = DIV_ROUND_UP(div, sh_msiof_spi_div_table[k].div);
+	div = DIV_ROUND_UP(parent_rate, spi_hz);
+	if (div <= 1024) {
 		/* SCR_BRDV_DIV_1 is valid only if BRPS is x 1/1 or x 1/2 */
-		if (sh_msiof_spi_div_table[k].div == 1 && brps > 2)
-			continue;
-		if (brps <= 32) /* max of brdv is 32 */
-			break;
-	}
+		if (!div_pow && div <= 32 && div > 2)
+			div_pow = 1;
+
+		if (div_pow)
+			brps = (div + 1) >> div_pow;
+		else
+			brps = div;
 
-	k = min_t(int, k, ARRAY_SIZE(sh_msiof_spi_div_table) - 1);
+		for (; brps > 32; div_pow++)
+			brps = (brps + 1) >> 1;
+	} else {
+		/* Set transfer rate composite divisor to 2^5 * 32 = 1024 */
+		dev_err(&p->pdev->dev,
+			"Requested SPI transfer rate %d is too low\n", spi_hz);
+		div_pow = 5;
+		brps = 32;
+	}
 
-	scr = sh_msiof_spi_div_table[k].brdv | SCR_BRPS(brps);
+	scr = sh_msiof_spi_div_array[div_pow] | SCR_BRPS(brps);
 	sh_msiof_write(p, TSCR, scr);
 	if (!(p->master->flags & SPI_MASTER_MUST_TX))
 		sh_msiof_write(p, RSCR, scr);
@@ -563,14 +567,16 @@ static int sh_msiof_spi_setup(struct spi_device *spi)
 
 	/* Configure native chip select mode/polarity early */
 	clr = MDR1_SYNCMD_MASK;
-	set = MDR1_TRMD | TMDR1_PCON | MDR1_SYNCMD_SPI;
+	set = MDR1_SYNCMD_SPI;
 	if (spi->mode & SPI_CS_HIGH)
 		clr |= BIT(MDR1_SYNCAC_SHIFT);
 	else
 		set |= BIT(MDR1_SYNCAC_SHIFT);
 	pm_runtime_get_sync(&p->pdev->dev);
 	tmp = sh_msiof_read(p, TMDR1) & ~clr;
-	sh_msiof_write(p, TMDR1, tmp | set);
+	sh_msiof_write(p, TMDR1, tmp | set | MDR1_TRMD | TMDR1_PCON);
+	tmp = sh_msiof_read(p, RMDR1) & ~clr;
+	sh_msiof_write(p, RMDR1, tmp | set);
 	pm_runtime_put(&p->pdev->dev);
 	p->native_cs_high = spi->mode & SPI_CS_HIGH;
 	p->native_cs_inited = true;
@@ -1040,21 +1046,21 @@ static const struct sh_msiof_chipdata sh_data = {
 	.tx_fifo_size = 64,
 	.rx_fifo_size = 64,
 	.master_flags = 0,
-	.min_div = 1,
+	.min_div_pow = 0,
 };
 
 static const struct sh_msiof_chipdata rcar_gen2_data = {
 	.tx_fifo_size = 64,
 	.rx_fifo_size = 64,
 	.master_flags = SPI_MASTER_MUST_TX,
-	.min_div = 1,
+	.min_div_pow = 0,
 };
 
 static const struct sh_msiof_chipdata rcar_gen3_data = {
 	.tx_fifo_size = 64,
 	.rx_fifo_size = 64,
 	.master_flags = SPI_MASTER_MUST_TX,
-	.min_div = 2,
+	.min_div_pow = 1,
 };
 
 static const struct of_device_id sh_msiof_match[] = {
@@ -1318,7 +1324,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, p);
 	p->master = master;
 	p->info = info;
-	p->min_div = chipdata->min_div;
+	p->min_div_pow = chipdata->min_div_pow;
 
 	init_completion(&p->done);
 
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index ba9743fa2326..ad1e55d3d5d5 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -1129,7 +1129,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	if (!spi->clk_rate) {
 		dev_err(&pdev->dev, "clk rate = 0\n");
 		ret = -EINVAL;
-		goto err_master_put;
+		goto err_clk_disable;
 	}
 
 	spi->rst = devm_reset_control_get_exclusive(&pdev->dev, NULL);
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index c24d9b45a27c..5f19016bbf10 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -36,6 +36,7 @@
 #include <linux/sizes.h>
 
 #include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
 
 struct ti_qspi_regs {
 	u32 clkctrl;
@@ -50,6 +51,7 @@ struct ti_qspi {
 	struct spi_master	*master;
 	void __iomem            *base;
 	void __iomem            *mmap_base;
+	size_t			mmap_size;
 	struct regmap		*ctrl_base;
 	unsigned int		ctrl_reg;
 	struct clk		*fclk;
@@ -434,12 +436,10 @@ static int ti_qspi_dma_xfer(struct ti_qspi *qspi, dma_addr_t dma_dst,
 	return 0;
 }
 
-static int ti_qspi_dma_bounce_buffer(struct ti_qspi *qspi,
-				     struct spi_flash_read_message *msg)
+static int ti_qspi_dma_bounce_buffer(struct ti_qspi *qspi, loff_t offs,
+				     void *to, size_t readsize)
 {
-	size_t readsize = msg->len;
-	void *to = msg->buf;
-	dma_addr_t dma_src = qspi->mmap_phys_base + msg->from;
+	dma_addr_t dma_src = qspi->mmap_phys_base + offs;
 	int ret = 0;
 
 	/*
@@ -507,13 +507,14 @@ static void ti_qspi_disable_memory_map(struct spi_device *spi)
 	qspi->mmap_enabled = false;
 }
 
-static void ti_qspi_setup_mmap_read(struct spi_device *spi,
-				    struct spi_flash_read_message *msg)
+static void ti_qspi_setup_mmap_read(struct spi_device *spi, u8 opcode,
+				    u8 data_nbits, u8 addr_width,
+				    u8 dummy_bytes)
 {
 	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
-	u32 memval = msg->read_opcode;
+	u32 memval = opcode;
 
-	switch (msg->data_nbits) {
+	switch (data_nbits) {
 	case SPI_NBITS_QUAD:
 		memval |= QSPI_SETUP_RD_QUAD;
 		break;
@@ -524,48 +525,64 @@ static void ti_qspi_setup_mmap_read(struct spi_device *spi,
 		memval |= QSPI_SETUP_RD_NORMAL;
 		break;
 	}
-	memval |= ((msg->addr_width - 1) << QSPI_SETUP_ADDR_SHIFT |
-		   msg->dummy_bytes << QSPI_SETUP_DUMMY_SHIFT);
+	memval |= ((addr_width - 1) << QSPI_SETUP_ADDR_SHIFT |
+		   dummy_bytes << QSPI_SETUP_DUMMY_SHIFT);
 	ti_qspi_write(qspi, memval,
 		      QSPI_SPI_SETUP_REG(spi->chip_select));
 }
 
-static bool ti_qspi_spi_flash_can_dma(struct spi_device *spi,
-				      struct spi_flash_read_message *msg)
+static int ti_qspi_exec_mem_op(struct spi_mem *mem,
+			       const struct spi_mem_op *op)
 {
-	return virt_addr_valid(msg->buf);
-}
-
-static int ti_qspi_spi_flash_read(struct spi_device *spi,
-				  struct spi_flash_read_message *msg)
-{
-	struct ti_qspi *qspi = spi_master_get_devdata(spi->master);
+	struct ti_qspi *qspi = spi_master_get_devdata(mem->spi->master);
+	u32 from = 0;
 	int ret = 0;
 
+	/* Only optimize read path. */
+	if (!op->data.nbytes || op->data.dir != SPI_MEM_DATA_IN ||
+	    !op->addr.nbytes || op->addr.nbytes > 4)
+		return -ENOTSUPP;
+
+	/* Address exceeds MMIO window size, fall back to regular mode. */
+	from = op->addr.val;
+	if (from + op->data.nbytes > qspi->mmap_size)
+		return -ENOTSUPP;
+
 	mutex_lock(&qspi->list_lock);
 
 	if (!qspi->mmap_enabled)
-		ti_qspi_enable_memory_map(spi);
-	ti_qspi_setup_mmap_read(spi, msg);
+		ti_qspi_enable_memory_map(mem->spi);
+	ti_qspi_setup_mmap_read(mem->spi, op->cmd.opcode, op->data.buswidth,
+				op->addr.nbytes, op->dummy.nbytes);
 
 	if (qspi->rx_chan) {
-		if (msg->cur_msg_mapped)
-			ret = ti_qspi_dma_xfer_sg(qspi, msg->rx_sg, msg->from);
-		else
-			ret = ti_qspi_dma_bounce_buffer(qspi, msg);
-		if (ret)
-			goto err_unlock;
+		struct sg_table sgt;
+
+		if (virt_addr_valid(op->data.buf.in) &&
+		    !spi_controller_dma_map_mem_op_data(mem->spi->master, op,
+							&sgt)) {
+			ret = ti_qspi_dma_xfer_sg(qspi, sgt, from);
+			spi_controller_dma_unmap_mem_op_data(mem->spi->master,
+							     op, &sgt);
+		} else {
+			ret = ti_qspi_dma_bounce_buffer(qspi, from,
+							op->data.buf.in,
+							op->data.nbytes);
+		}
 	} else {
-		memcpy_fromio(msg->buf, qspi->mmap_base + msg->from, msg->len);
+		memcpy_fromio(op->data.buf.in, qspi->mmap_base + from,
+			      op->data.nbytes);
 	}
-	msg->retlen = msg->len;
 
-err_unlock:
 	mutex_unlock(&qspi->list_lock);
 
 	return ret;
 }
 
+static const struct spi_controller_mem_ops ti_qspi_mem_ops = {
+	.exec_op = ti_qspi_exec_mem_op,
+};
+
 static int ti_qspi_start_transfer_one(struct spi_master *master,
 		struct spi_message *m)
 {
@@ -672,7 +689,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 	master->dev.of_node = pdev->dev.of_node;
 	master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) |
 				     SPI_BPW_MASK(8);
-	master->spi_flash_read = ti_qspi_spi_flash_read;
+	master->mem_ops = &ti_qspi_mem_ops;
 
 	if (!of_property_read_u32(np, "num-cs", &num_cs))
 		master->num_chipselect = num_cs;
@@ -702,6 +719,9 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (res_mmap)
+		qspi->mmap_size = resource_size(res_mmap);
+
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		dev_err(&pdev->dev, "no irq resource?\n");
@@ -770,7 +790,6 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		dma_release_channel(qspi->rx_chan);
 		goto no_dma;
 	}
-	master->spi_flash_can_dma = ti_qspi_spi_flash_can_dma;
 	master->dma_rx = qspi->rx_chan;
 	init_completion(&qspi->transfer_complete);
 	if (res_mmap)
@@ -784,7 +803,7 @@ no_dma:
 				 "mmap failed with error %ld using PIO mode\n",
 				 PTR_ERR(qspi->mmap_base));
 			qspi->mmap_base = NULL;
-			master->spi_flash_read = NULL;
+			master->mem_ops = NULL;
 		}
 	}
 	qspi->mmap_enabled = false;
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index 18aeaceee286..cc4d31033494 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -20,6 +20,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/spi/spi.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
@@ -135,6 +136,7 @@
 #define GQSPI_DMA_UNALIGN		0x3
 #define GQSPI_DEFAULT_NUM_CS	1	/* Default number of chip selects */
 
+#define SPI_AUTOSUSPEND_TIMEOUT		3000
 enum mode_type {GQSPI_MODE_IO, GQSPI_MODE_DMA};
 
 /**
@@ -356,21 +358,9 @@ static void zynqmp_qspi_copy_read_data(struct zynqmp_qspi *xqspi,
 static int zynqmp_prepare_transfer_hardware(struct spi_master *master)
 {
 	struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
-	int ret;
-
-	ret = clk_enable(xqspi->refclk);
-	if (ret)
-		return ret;
-
-	ret = clk_enable(xqspi->pclk);
-	if (ret)
-		goto clk_err;
 
 	zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, GQSPI_EN_MASK);
 	return 0;
-clk_err:
-	clk_disable(xqspi->refclk);
-	return ret;
 }
 
 /**
@@ -387,8 +377,6 @@ static int zynqmp_unprepare_transfer_hardware(struct spi_master *master)
 	struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
 
 	zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, 0x0);
-	clk_disable(xqspi->refclk);
-	clk_disable(xqspi->pclk);
 	return 0;
 }
 
@@ -918,8 +906,7 @@ static int zynqmp_qspi_start_transfer(struct spi_master *master,
  */
 static int __maybe_unused zynqmp_qspi_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_master *master = dev_get_drvdata(dev);
 
 	spi_master_suspend(master);
 
@@ -939,8 +926,7 @@ static int __maybe_unused zynqmp_qspi_suspend(struct device *dev)
  */
 static int __maybe_unused zynqmp_qspi_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_master *master = dev_get_drvdata(dev);
 	struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
 	int ret = 0;
 
@@ -959,11 +945,67 @@ static int __maybe_unused zynqmp_qspi_resume(struct device *dev)
 
 	spi_master_resume(master);
 
+	clk_disable(xqspi->refclk);
+	clk_disable(xqspi->pclk);
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(zynqmp_qspi_dev_pm_ops, zynqmp_qspi_suspend,
-			 zynqmp_qspi_resume);
+/**
+ * zynqmp_runtime_suspend - Runtime suspend method for the SPI driver
+ * @dev:	Address of the platform_device structure
+ *
+ * This function disables the clocks
+ *
+ * Return:	Always 0
+ */
+static int __maybe_unused zynqmp_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
+
+	clk_disable(xqspi->refclk);
+	clk_disable(xqspi->pclk);
+
+	return 0;
+}
+
+/**
+ * zynqmp_runtime_resume - Runtime resume method for the SPI driver
+ * @dev:	Address of the platform_device structure
+ *
+ * This function enables the clocks
+ *
+ * Return:	0 on success and error value on error
+ */
+static int __maybe_unused zynqmp_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = clk_enable(xqspi->pclk);
+	if (ret) {
+		dev_err(dev, "Cannot enable APB clock.\n");
+		return ret;
+	}
+
+	ret = clk_enable(xqspi->refclk);
+	if (ret) {
+		dev_err(dev, "Cannot enable device clock.\n");
+		clk_disable(xqspi->pclk);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops zynqmp_qspi_dev_pm_ops = {
+	SET_RUNTIME_PM_OPS(zynqmp_runtime_suspend,
+			   zynqmp_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(zynqmp_qspi_suspend, zynqmp_qspi_resume)
+};
 
 /**
  * zynqmp_qspi_probe:	Probe method for the QSPI driver
@@ -1023,9 +1065,15 @@ static int zynqmp_qspi_probe(struct platform_device *pdev)
 		goto clk_dis_pclk;
 	}
 
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 	/* QSPI controller initializations */
 	zynqmp_qspi_init_hw(xqspi);
 
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
 	xqspi->irq = platform_get_irq(pdev, 0);
 	if (xqspi->irq <= 0) {
 		ret = -ENXIO;
@@ -1063,6 +1111,8 @@ static int zynqmp_qspi_probe(struct platform_device *pdev)
 	return 0;
 
 clk_dis_all:
+	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 	clk_disable_unprepare(xqspi->refclk);
 clk_dis_pclk:
 	clk_disable_unprepare(xqspi->pclk);
@@ -1090,6 +1140,8 @@ static int zynqmp_qspi_remove(struct platform_device *pdev)
 	zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, 0x0);
 	clk_disable_unprepare(xqspi->refclk);
 	clk_disable_unprepare(xqspi->pclk);
+	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 
 	spi_unregister_master(master);
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 7b213faa0a2b..efc624f9e490 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/mod_devicetable.h>
 #include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
 #include <linux/of_gpio.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
@@ -46,6 +47,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/spi.h>
 
+#include "internals.h"
+
 static DEFINE_IDR(spi_master_idr);
 
 static void spidev_release(struct device *dev)
@@ -356,11 +359,12 @@ static int spi_drv_probe(struct device *dev)
 	}
 
 	ret = dev_pm_domain_attach(dev, true);
-	if (ret != -EPROBE_DEFER) {
-		ret = sdrv->probe(spi);
-		if (ret)
-			dev_pm_domain_detach(dev, true);
-	}
+	if (ret)
+		return ret;
+
+	ret = sdrv->probe(spi);
+	if (ret)
+		dev_pm_domain_detach(dev, true);
 
 	return ret;
 }
@@ -740,9 +744,9 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
 }
 
 #ifdef CONFIG_HAS_DMA
-static int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
-		       struct sg_table *sgt, void *buf, size_t len,
-		       enum dma_data_direction dir)
+int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
+		struct sg_table *sgt, void *buf, size_t len,
+		enum dma_data_direction dir)
 {
 	const bool vmalloced_buf = is_vmalloc_addr(buf);
 	unsigned int max_seg_size = dma_get_max_seg_size(dev);
@@ -821,8 +825,8 @@ static int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
 	return 0;
 }
 
-static void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
-			  struct sg_table *sgt, enum dma_data_direction dir)
+void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
+		   struct sg_table *sgt, enum dma_data_direction dir)
 {
 	if (sgt->orig_nents) {
 		dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir);
@@ -907,19 +911,6 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg)
 	return 0;
 }
 #else /* !CONFIG_HAS_DMA */
-static inline int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
-			      struct sg_table *sgt, void *buf, size_t len,
-			      enum dma_data_direction dir)
-{
-	return -EINVAL;
-}
-
-static inline void spi_unmap_buf(struct spi_controller *ctlr,
-				 struct device *dev, struct sg_table *sgt,
-				 enum dma_data_direction dir)
-{
-}
-
 static inline int __spi_map_msg(struct spi_controller *ctlr,
 				struct spi_message *msg)
 {
@@ -1222,6 +1213,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread)
 	if (!was_busy && ctlr->auto_runtime_pm) {
 		ret = pm_runtime_get_sync(ctlr->dev.parent);
 		if (ret < 0) {
+			pm_runtime_put_noidle(ctlr->dev.parent);
 			dev_err(&ctlr->dev, "Failed to power device: %d\n",
 				ret);
 			mutex_unlock(&ctlr->io_mutex);
@@ -1533,6 +1525,22 @@ err_init_queue:
 	return ret;
 }
 
+/**
+ * spi_flush_queue - Send all pending messages in the queue from the callers'
+ *		     context
+ * @ctlr: controller to process queue for
+ *
+ * This should be used when one wants to ensure all pending messages have been
+ * sent before doing something. Is used by the spi-mem code to make sure SPI
+ * memory operations do not preempt regular SPI transfers that have been queued
+ * before the spi-mem operation.
+ */
+void spi_flush_queue(struct spi_controller *ctlr)
+{
+	if (ctlr->transfer == spi_queued_transfer)
+		__spi_pump_messages(ctlr, false);
+}
+
 /*-------------------------------------------------------------------------*/
 
 #if defined(CONFIG_OF)
@@ -2063,6 +2071,26 @@ static int of_spi_register_master(struct spi_controller *ctlr)
 }
 #endif
 
+static int spi_controller_check_ops(struct spi_controller *ctlr)
+{
+	/*
+	 * The controller may implement only the high-level SPI-memory like
+	 * operations if it does not support regular SPI transfers, and this is
+	 * valid use case.
+	 * If ->mem_ops is NULL, we request that at least one of the
+	 * ->transfer_xxx() method be implemented.
+	 */
+	if (ctlr->mem_ops) {
+		if (!ctlr->mem_ops->exec_op)
+			return -EINVAL;
+	} else if (!ctlr->transfer && !ctlr->transfer_one &&
+		   !ctlr->transfer_one_message) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * spi_register_controller - register SPI master or slave controller
  * @ctlr: initialized master, originally from spi_alloc_master() or
@@ -2096,6 +2124,14 @@ int spi_register_controller(struct spi_controller *ctlr)
 	if (!dev)
 		return -ENODEV;
 
+	/*
+	 * Make sure all necessary hooks are implemented before registering
+	 * the SPI controller.
+	 */
+	status = spi_controller_check_ops(ctlr);
+	if (status)
+		return status;
+
 	if (!spi_controller_is_slave(ctlr)) {
 		status = of_spi_register_master(ctlr);
 		if (status)
@@ -2161,10 +2197,14 @@ int spi_register_controller(struct spi_controller *ctlr)
 			spi_controller_is_slave(ctlr) ? "slave" : "master",
 			dev_name(&ctlr->dev));
 
-	/* If we're using a queued driver, start the queue */
-	if (ctlr->transfer)
+	/*
+	 * If we're using a queued driver, start the queue. Note that we don't
+	 * need the queueing logic if the driver is only supporting high-level
+	 * memory operations.
+	 */
+	if (ctlr->transfer) {
 		dev_info(dev, "controller is unqueued, this is deprecated\n");
-	else {
+	} else if (ctlr->transfer_one || ctlr->transfer_one_message) {
 		status = spi_controller_initialize_queue(ctlr);
 		if (status) {
 			device_del(&ctlr->dev);
@@ -2894,6 +2934,13 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message)
 {
 	struct spi_controller *ctlr = spi->controller;
 
+	/*
+	 * Some controllers do not support doing regular SPI transfers. Return
+	 * ENOTSUPP when this is the case.
+	 */
+	if (!ctlr->transfer)
+		return -ENOTSUPP;
+
 	message->spi = spi;
 
 	SPI_STATISTICS_INCREMENT_FIELD(&ctlr->statistics, spi_async);
@@ -3010,63 +3057,6 @@ int spi_async_locked(struct spi_device *spi, struct spi_message *message)
 }
 EXPORT_SYMBOL_GPL(spi_async_locked);
 
-
-int spi_flash_read(struct spi_device *spi,
-		   struct spi_flash_read_message *msg)
-
-{
-	struct spi_controller *master = spi->controller;
-	struct device *rx_dev = NULL;
-	int ret;
-
-	if ((msg->opcode_nbits == SPI_NBITS_DUAL ||
-	     msg->addr_nbits == SPI_NBITS_DUAL) &&
-	    !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD)))
-		return -EINVAL;
-	if ((msg->opcode_nbits == SPI_NBITS_QUAD ||
-	     msg->addr_nbits == SPI_NBITS_QUAD) &&
-	    !(spi->mode & SPI_TX_QUAD))
-		return -EINVAL;
-	if (msg->data_nbits == SPI_NBITS_DUAL &&
-	    !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD)))
-		return -EINVAL;
-	if (msg->data_nbits == SPI_NBITS_QUAD &&
-	    !(spi->mode &  SPI_RX_QUAD))
-		return -EINVAL;
-
-	if (master->auto_runtime_pm) {
-		ret = pm_runtime_get_sync(master->dev.parent);
-		if (ret < 0) {
-			dev_err(&master->dev, "Failed to power device: %d\n",
-				ret);
-			return ret;
-		}
-	}
-
-	mutex_lock(&master->bus_lock_mutex);
-	mutex_lock(&master->io_mutex);
-	if (master->dma_rx && master->spi_flash_can_dma(spi, msg)) {
-		rx_dev = master->dma_rx->device->dev;
-		ret = spi_map_buf(master, rx_dev, &msg->rx_sg,
-				  msg->buf, msg->len,
-				  DMA_FROM_DEVICE);
-		if (!ret)
-			msg->cur_msg_mapped = true;
-	}
-	ret = master->spi_flash_read(spi, msg);
-	if (msg->cur_msg_mapped)
-		spi_unmap_buf(master, rx_dev, &msg->rx_sg,
-			      DMA_FROM_DEVICE);
-	mutex_unlock(&master->io_mutex);
-	mutex_unlock(&master->bus_lock_mutex);
-
-	if (master->auto_runtime_pm)
-		pm_runtime_put(master->dev.parent);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(spi_flash_read);
-
 /*-------------------------------------------------------------------------*/
 
 /* Utility methods for SPI protocol drivers, layered on
diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig
index 9371651d8017..c574dd210500 100644
--- a/drivers/ssb/Kconfig
+++ b/drivers/ssb/Kconfig
@@ -117,7 +117,7 @@ config SSB_SERIAL
 
 config SSB_DRIVER_PCICORE_POSSIBLE
 	bool
-	depends on SSB_PCIHOST && SSB = y
+	depends on SSB_PCIHOST
 	default y
 
 config SSB_DRIVER_PCICORE
@@ -131,7 +131,7 @@ config SSB_DRIVER_PCICORE
 
 config SSB_PCICORE_HOSTMODE
 	bool "Hostmode support for SSB PCI core"
-	depends on SSB_DRIVER_PCICORE && SSB_DRIVER_MIPS
+	depends on SSB_DRIVER_PCICORE && SSB_DRIVER_MIPS && SSB = y
 	help
 	  PCIcore hostmode operation (external PCI bus).
 
diff --git a/drivers/staging/comedi/drivers/serial2002.c b/drivers/staging/comedi/drivers/serial2002.c
index b3f3b4a201af..5471b2212a62 100644
--- a/drivers/staging/comedi/drivers/serial2002.c
+++ b/drivers/staging/comedi/drivers/serial2002.c
@@ -113,7 +113,7 @@ static void serial2002_tty_read_poll_wait(struct file *f, int timeout)
 		long elapsed;
 		__poll_t mask;
 
-		mask = f->f_op->poll(f, &table.pt);
+		mask = vfs_poll(f, &table.pt);
 		if (mask & (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN |
 			    EPOLLHUP | EPOLLERR)) {
 			break;
@@ -136,7 +136,7 @@ static int serial2002_tty_read(struct file *f, int timeout)
 
 	result = -1;
 	if (!IS_ERR(f)) {
-		if (f->f_op->poll) {
+		if (file_can_poll(f)) {
 			serial2002_tty_read_poll_wait(f, timeout);
 
 			if (kernel_read(f, &ch, 1, &pos) == 1)
diff --git a/drivers/staging/comedi/proc.c b/drivers/staging/comedi/proc.c
index 50d38938ac6f..8bc8e42beb90 100644
--- a/drivers/staging/comedi/proc.c
+++ b/drivers/staging/comedi/proc.c
@@ -62,25 +62,9 @@ static int comedi_read(struct seq_file *m, void *v)
 	return 0;
 }
 
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int comedi_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, comedi_read, NULL);
-}
-
-static const struct file_operations comedi_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= comedi_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 void __init comedi_proc_init(void)
 {
-	if (!proc_create("comedi", 0444, NULL, &comedi_proc_fops))
+	if (!proc_create_single("comedi", 0444, NULL, comedi_read))
 		pr_warn("comedi: unable to create proc entry\n");
 }
 
diff --git a/drivers/staging/fwserial/fwserial.c b/drivers/staging/fwserial/fwserial.c
index e8bfe5520bc7..fa0dd425b454 100644
--- a/drivers/staging/fwserial/fwserial.c
+++ b/drivers/staging/fwserial/fwserial.c
@@ -1506,11 +1506,6 @@ static int fwtty_debugfs_peers_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int fwtty_proc_open(struct inode *inode, struct file *fp)
-{
-	return single_open(fp, fwtty_proc_show, NULL);
-}
-
 static int fwtty_stats_open(struct inode *inode, struct file *fp)
 {
 	return single_open(fp, fwtty_debugfs_stats_show, inode->i_private);
@@ -1537,14 +1532,6 @@ static const struct file_operations fwtty_peers_fops = {
 	.release =	single_release,
 };
 
-static const struct file_operations fwtty_proc_fops = {
-	.owner =        THIS_MODULE,
-	.open =         fwtty_proc_open,
-	.read =         seq_read,
-	.llseek =       seq_lseek,
-	.release =      single_release,
-};
-
 static const struct tty_port_operations fwtty_port_ops = {
 	.dtr_rts =		fwtty_port_dtr_rts,
 	.carrier_raised =	fwtty_port_carrier_raised,
@@ -1570,7 +1557,7 @@ static const struct tty_operations fwtty_ops = {
 	.tiocmget =		fwtty_tiocmget,
 	.tiocmset =		fwtty_tiocmset,
 	.get_icount =		fwtty_get_icount,
-	.proc_fops =		&fwtty_proc_fops,
+	.proc_show =		fwtty_proc_show,
 };
 
 static const struct tty_operations fwloop_ops = {
diff --git a/drivers/staging/ipx/af_ipx.c b/drivers/staging/ipx/af_ipx.c
index 5703dd176787..208b5c161631 100644
--- a/drivers/staging/ipx/af_ipx.c
+++ b/drivers/staging/ipx/af_ipx.c
@@ -1965,7 +1965,7 @@ static const struct proto_ops ipx_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= ipx_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.ioctl		= ipx_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ipx_compat_ioctl,
diff --git a/drivers/staging/ipx/ipx_proc.c b/drivers/staging/ipx/ipx_proc.c
index b9232e4e2ed4..360f0ad970de 100644
--- a/drivers/staging/ipx/ipx_proc.c
+++ b/drivers/staging/ipx/ipx_proc.c
@@ -244,42 +244,6 @@ static const struct seq_operations ipx_seq_socket_ops = {
 	.show   = ipx_seq_socket_show,
 };
 
-static int ipx_seq_route_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &ipx_seq_route_ops);
-}
-
-static int ipx_seq_interface_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &ipx_seq_interface_ops);
-}
-
-static int ipx_seq_socket_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &ipx_seq_socket_ops);
-}
-
-static const struct file_operations ipx_seq_interface_fops = {
-	.open           = ipx_seq_interface_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = seq_release,
-};
-
-static const struct file_operations ipx_seq_route_fops = {
-	.open           = ipx_seq_route_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = seq_release,
-};
-
-static const struct file_operations ipx_seq_socket_fops = {
-	.open           = ipx_seq_socket_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = seq_release,
-};
-
 static struct proc_dir_entry *ipx_proc_dir;
 
 int __init ipx_proc_init(void)
@@ -291,16 +255,17 @@ int __init ipx_proc_init(void)
 
 	if (!ipx_proc_dir)
 		goto out;
-	p = proc_create("interface", S_IRUGO,
-			ipx_proc_dir, &ipx_seq_interface_fops);
+	p = proc_create_seq("interface", S_IRUGO, ipx_proc_dir,
+			&ipx_seq_interface_ops);
 	if (!p)
 		goto out_interface;
 
-	p = proc_create("route", S_IRUGO, ipx_proc_dir, &ipx_seq_route_fops);
+	p = proc_create_seq("route", S_IRUGO, ipx_proc_dir, &ipx_seq_route_ops);
 	if (!p)
 		goto out_route;
 
-	p = proc_create("socket", S_IRUGO, ipx_proc_dir, &ipx_seq_socket_fops);
+	p = proc_create_seq("socket", S_IRUGO, ipx_proc_dir,
+			&ipx_seq_socket_ops);
 	if (!p)
 		goto out_socket;
 
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 16cab40156ca..aeab05f682d9 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -1799,7 +1799,7 @@ static int imx_csi_probe(struct platform_device *pdev)
 	priv->dev->of_node = pdata->of_node;
 	pinctrl = devm_pinctrl_get_select_default(priv->dev);
 	if (IS_ERR(pinctrl)) {
-		ret = PTR_ERR(priv->vdev);
+		ret = PTR_ERR(pinctrl);
 		dev_dbg(priv->dev,
 			"devm_pinctrl_get_select_default() failed: %d\n", ret);
 		if (ret != -ENODEV)
diff --git a/drivers/staging/ncpfs/dir.c b/drivers/staging/ncpfs/dir.c
index 0c57c5c5d40a..072bcb12898f 100644
--- a/drivers/staging/ncpfs/dir.c
+++ b/drivers/staging/ncpfs/dir.c
@@ -823,12 +823,11 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsig
 	struct ncp_server *server = NCP_SERVER(dir);
 	struct inode *inode = NULL;
 	struct ncp_entry_info finfo;
-	int error, res, len;
+	int res, len;
 	__u8 __name[NCP_MAXPATHLEN + 1];
 
-	error = -EIO;
 	if (!ncp_conn_valid(server))
-		goto finished;
+		return ERR_PTR(-EIO);
 
 	ncp_vdbg("server lookup for %pd2\n", dentry);
 
@@ -847,31 +846,20 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsig
 			res = ncp_obtain_info(server, dir, __name, &(finfo.i));
 	}
 	ncp_vdbg("looked for %pd2, res=%d\n", dentry, res);
-	/*
-	 * If we didn't find an entry, make a negative dentry.
-	 */
-	if (res)
-		goto add_entry;
-
-	/*
-	 * Create an inode for the entry.
-	 */
-	finfo.opened = 0;
-	finfo.ino = iunique(dir->i_sb, 2);
-	finfo.volume = finfo.i.volNumber;
-	error = -EACCES;
-	inode = ncp_iget(dir->i_sb, &finfo);
-
-	if (inode) {
-		ncp_new_dentry(dentry);
-add_entry:
-		d_add(dentry, inode);
-		error = 0;
+	if (!res) {
+		/*
+		 * Entry found; create an inode for it.
+		 */
+		finfo.opened = 0;
+		finfo.ino = iunique(dir->i_sb, 2);
+		finfo.volume = finfo.i.volNumber;
+		inode = ncp_iget(dir->i_sb, &finfo);
+		if (unlikely(!inode))
+			inode = ERR_PTR(-EACCES);
+		else
+			ncp_new_dentry(dentry);
 	}
-
-finished:
-	ncp_vdbg("result=%d\n", error);
-	return ERR_PTR(error);
+	return d_splice_alias(inode, dentry);
 }
 
 /*
diff --git a/drivers/staging/rtl8192u/r8192U_core.c b/drivers/staging/rtl8192u/r8192U_core.c
index d607c59761cf..7a0dbc0fa18e 100644
--- a/drivers/staging/rtl8192u/r8192U_core.c
+++ b/drivers/staging/rtl8192u/r8192U_core.c
@@ -646,64 +646,25 @@ static void rtl8192_proc_module_init(void)
 	rtl8192_proc = proc_mkdir(RTL819xU_MODULE_NAME, init_net.proc_net);
 }
 
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int rtl8192_proc_open(struct inode *inode, struct file *file)
-{
-	struct net_device *dev = proc_get_parent_data(inode);
-	int (*show)(struct seq_file *, void *) = PDE_DATA(inode);
-
-	return single_open(file, show, dev);
-}
-
-static const struct file_operations rtl8192_proc_fops = {
-	.open		= rtl8192_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-/*
- * Table of proc files we need to create.
- */
-struct rtl8192_proc_file {
-	char name[12];
-	int (*show)(struct seq_file *, void *);
-};
-
-static const struct rtl8192_proc_file rtl8192_proc_files[] = {
-	{ "stats-rx",	&proc_get_stats_rx },
-	{ "stats-tx",	&proc_get_stats_tx },
-	{ "stats-ap",	&proc_get_stats_ap },
-	{ "registers",	&proc_get_registers },
-	{ "" }
-};
-
 static void rtl8192_proc_init_one(struct net_device *dev)
 {
-	const struct rtl8192_proc_file *f;
 	struct proc_dir_entry *dir;
 
-	if (rtl8192_proc) {
-		dir = proc_mkdir_data(dev->name, 0, rtl8192_proc, dev);
-		if (!dir) {
-			RT_TRACE(COMP_ERR,
-				 "Unable to initialize /proc/net/rtl8192/%s\n",
-				 dev->name);
-			return;
-		}
+	if (!rtl8192_proc)
+		return;
 
-		for (f = rtl8192_proc_files; f->name[0]; f++) {
-			if (!proc_create_data(f->name, S_IFREG | S_IRUGO, dir,
-					      &rtl8192_proc_fops, f->show)) {
-				RT_TRACE(COMP_ERR,
-					 "Unable to initialize /proc/net/rtl8192/%s/%s\n",
-					 dev->name, f->name);
-				return;
-			}
-		}
-	}
+	dir = proc_mkdir_data(dev->name, 0, rtl8192_proc, dev);
+	if (!dir)
+		return;
+
+	proc_create_single("stats-rx", S_IFREG | S_IRUGO, dir,
+			proc_get_stats_rx);
+	proc_create_single("stats-tx", S_IFREG | S_IRUGO, dir,
+			proc_get_stats_tx);
+	proc_create_single("stats-ap", S_IFREG | S_IRUGO, dir,
+			proc_get_stats_ap);
+	proc_create_single("registers", S_IFREG | S_IRUGO, dir,
+			proc_get_registers);
 }
 
 static void rtl8192_proc_remove_one(struct net_device *dev)
diff --git a/drivers/staging/typec/Kconfig b/drivers/staging/typec/Kconfig
index 5359f556d203..3aa981fbc8f5 100644
--- a/drivers/staging/typec/Kconfig
+++ b/drivers/staging/typec/Kconfig
@@ -9,6 +9,14 @@ config TYPEC_TCPCI
 	help
 	  Type-C Port Controller driver for TCPCI-compliant controller.
 
+config TYPEC_RT1711H
+	tristate "Richtek RT1711H Type-C chip driver"
+	select TYPEC_TCPCI
+	help
+	  Richtek RT1711H Type-C chip driver that works with
+	  Type-C Port Controller Manager to provide USB PD and USB
+	  Type-C functionalities.
+
 endif
 
 endmenu
diff --git a/drivers/staging/typec/Makefile b/drivers/staging/typec/Makefile
index 53d649abcb53..7803d485e1b3 100644
--- a/drivers/staging/typec/Makefile
+++ b/drivers/staging/typec/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_TYPEC_TCPCI)	+= tcpci.o
+obj-$(CONFIG_TYPEC_RT1711H)	+= tcpci_rt1711h.o
diff --git a/drivers/staging/typec/tcpci.h b/drivers/staging/typec/tcpci.h
index 34c865f0dcf6..303ebde26546 100644
--- a/drivers/staging/typec/tcpci.h
+++ b/drivers/staging/typec/tcpci.h
@@ -59,6 +59,7 @@
 #define TCPC_POWER_CTRL_VCONN_ENABLE	BIT(0)
 
 #define TCPC_CC_STATUS			0x1d
+#define TCPC_CC_STATUS_TOGGLING		BIT(5)
 #define TCPC_CC_STATUS_TERM		BIT(4)
 #define TCPC_CC_STATUS_CC2_SHIFT	2
 #define TCPC_CC_STATUS_CC2_MASK		0x3
diff --git a/drivers/staging/typec/tcpci_rt1711h.c b/drivers/staging/typec/tcpci_rt1711h.c
new file mode 100644
index 000000000000..017389021b96
--- /dev/null
+++ b/drivers/staging/typec/tcpci_rt1711h.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018, Richtek Technology Corporation
+ *
+ * Richtek RT1711H Type-C Chip Driver
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/gpio/consumer.h>
+#include <linux/usb/tcpm.h>
+#include <linux/regmap.h>
+#include "tcpci.h"
+
+#define RT1711H_VID		0x29CF
+#define RT1711H_PID		0x1711
+
+#define RT1711H_RTCTRL8		0x9B
+
+/* Autoidle timeout = (tout * 2 + 1) * 6.4ms */
+#define RT1711H_RTCTRL8_SET(ck300, ship_off, auto_idle, tout) \
+			    (((ck300) << 7) | ((ship_off) << 5) | \
+			    ((auto_idle) << 3) | ((tout) & 0x07))
+
+#define RT1711H_RTCTRL11	0x9E
+
+/* I2C timeout = (tout + 1) * 12.5ms */
+#define RT1711H_RTCTRL11_SET(en, tout) \
+			     (((en) << 7) | ((tout) & 0x0F))
+
+#define RT1711H_RTCTRL13	0xA0
+#define RT1711H_RTCTRL14	0xA1
+#define RT1711H_RTCTRL15	0xA2
+#define RT1711H_RTCTRL16	0xA3
+
+struct rt1711h_chip {
+	struct tcpci_data data;
+	struct tcpci *tcpci;
+	struct device *dev;
+};
+
+static int rt1711h_read16(struct rt1711h_chip *chip, unsigned int reg, u16 *val)
+{
+	return regmap_raw_read(chip->data.regmap, reg, val, sizeof(u16));
+}
+
+static int rt1711h_write16(struct rt1711h_chip *chip, unsigned int reg, u16 val)
+{
+	return regmap_raw_write(chip->data.regmap, reg, &val, sizeof(u16));
+}
+
+static int rt1711h_read8(struct rt1711h_chip *chip, unsigned int reg, u8 *val)
+{
+	return regmap_raw_read(chip->data.regmap, reg, val, sizeof(u8));
+}
+
+static int rt1711h_write8(struct rt1711h_chip *chip, unsigned int reg, u8 val)
+{
+	return regmap_raw_write(chip->data.regmap, reg, &val, sizeof(u8));
+}
+
+static const struct regmap_config rt1711h_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = 0xFF, /* 0x80 .. 0xFF are vendor defined */
+};
+
+static struct rt1711h_chip *tdata_to_rt1711h(struct tcpci_data *tdata)
+{
+	return container_of(tdata, struct rt1711h_chip, data);
+}
+
+static int rt1711h_init(struct tcpci *tcpci, struct tcpci_data *tdata)
+{
+	int ret;
+	struct rt1711h_chip *chip = tdata_to_rt1711h(tdata);
+
+	/* CK 300K from 320K, shipping off, auto_idle enable, tout = 32ms */
+	ret = rt1711h_write8(chip, RT1711H_RTCTRL8,
+			     RT1711H_RTCTRL8_SET(0, 1, 1, 2));
+	if (ret < 0)
+		return ret;
+
+	/* I2C reset : (val + 1) * 12.5ms */
+	ret = rt1711h_write8(chip, RT1711H_RTCTRL11,
+			     RT1711H_RTCTRL11_SET(1, 0x0F));
+	if (ret < 0)
+		return ret;
+
+	/* tTCPCfilter : (26.7 * val) us */
+	ret = rt1711h_write8(chip, RT1711H_RTCTRL14, 0x0F);
+	if (ret < 0)
+		return ret;
+
+	/*  tDRP : (51.2 + 6.4 * val) ms */
+	ret = rt1711h_write8(chip, RT1711H_RTCTRL15, 0x04);
+	if (ret < 0)
+		return ret;
+
+	/* dcSRC.DRP : 33% */
+	return rt1711h_write16(chip, RT1711H_RTCTRL16, 330);
+}
+
+static int rt1711h_set_vconn(struct tcpci *tcpci, struct tcpci_data *tdata,
+			     bool enable)
+{
+	struct rt1711h_chip *chip = tdata_to_rt1711h(tdata);
+
+	return rt1711h_write8(chip, RT1711H_RTCTRL8,
+			      RT1711H_RTCTRL8_SET(0, 1, !enable, 2));
+}
+
+static int rt1711h_start_drp_toggling(struct tcpci *tcpci,
+				      struct tcpci_data *tdata,
+				      enum typec_cc_status cc)
+{
+	struct rt1711h_chip *chip = tdata_to_rt1711h(tdata);
+	int ret;
+	unsigned int reg = 0;
+
+	switch (cc) {
+	default:
+	case TYPEC_CC_RP_DEF:
+		reg |= (TCPC_ROLE_CTRL_RP_VAL_DEF <<
+			TCPC_ROLE_CTRL_RP_VAL_SHIFT);
+		break;
+	case TYPEC_CC_RP_1_5:
+		reg |= (TCPC_ROLE_CTRL_RP_VAL_1_5 <<
+			TCPC_ROLE_CTRL_RP_VAL_SHIFT);
+		break;
+	case TYPEC_CC_RP_3_0:
+		reg |= (TCPC_ROLE_CTRL_RP_VAL_3_0 <<
+			TCPC_ROLE_CTRL_RP_VAL_SHIFT);
+		break;
+	}
+
+	if (cc == TYPEC_CC_RD)
+		reg |= (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC1_SHIFT) |
+			   (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_CC2_SHIFT);
+	else
+		reg |= (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC1_SHIFT) |
+			   (TCPC_ROLE_CTRL_CC_RP << TCPC_ROLE_CTRL_CC2_SHIFT);
+
+	ret = rt1711h_write8(chip, TCPC_ROLE_CTRL, reg);
+	if (ret < 0)
+		return ret;
+	usleep_range(500, 1000);
+
+	return 0;
+}
+
+static irqreturn_t rt1711h_irq(int irq, void *dev_id)
+{
+	int ret;
+	u16 alert;
+	u8 status;
+	struct rt1711h_chip *chip = dev_id;
+
+	if (!chip->tcpci)
+		return IRQ_HANDLED;
+
+	ret = rt1711h_read16(chip, TCPC_ALERT, &alert);
+	if (ret < 0)
+		goto out;
+
+	if (alert & TCPC_ALERT_CC_STATUS) {
+		ret = rt1711h_read8(chip, TCPC_CC_STATUS, &status);
+		if (ret < 0)
+			goto out;
+		/* Clear cc change event triggered by starting toggling */
+		if (status & TCPC_CC_STATUS_TOGGLING)
+			rt1711h_write8(chip, TCPC_ALERT, TCPC_ALERT_CC_STATUS);
+	}
+
+out:
+	return tcpci_irq(chip->tcpci);
+}
+
+static int rt1711h_init_alert(struct rt1711h_chip *chip,
+			      struct i2c_client *client)
+{
+	int ret;
+
+	/* Disable chip interrupts before requesting irq */
+	ret = rt1711h_write16(chip, TCPC_ALERT_MASK, 0);
+	if (ret < 0)
+		return ret;
+
+	ret = devm_request_threaded_irq(chip->dev, client->irq, NULL,
+					rt1711h_irq,
+					IRQF_ONESHOT | IRQF_TRIGGER_LOW,
+					dev_name(chip->dev), chip);
+	if (ret < 0)
+		return ret;
+	enable_irq_wake(client->irq);
+	return 0;
+}
+
+static int rt1711h_sw_reset(struct rt1711h_chip *chip)
+{
+	int ret;
+
+	ret = rt1711h_write8(chip, RT1711H_RTCTRL13, 0x01);
+	if (ret < 0)
+		return ret;
+
+	usleep_range(1000, 2000);
+	return 0;
+}
+
+static int rt1711h_check_revision(struct i2c_client *i2c)
+{
+	int ret;
+
+	ret = i2c_smbus_read_word_data(i2c, TCPC_VENDOR_ID);
+	if (ret < 0)
+		return ret;
+	if (ret != RT1711H_VID) {
+		dev_err(&i2c->dev, "vid is not correct, 0x%04x\n", ret);
+		return -ENODEV;
+	}
+	ret = i2c_smbus_read_word_data(i2c, TCPC_PRODUCT_ID);
+	if (ret < 0)
+		return ret;
+	if (ret != RT1711H_PID) {
+		dev_err(&i2c->dev, "pid is not correct, 0x%04x\n", ret);
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static int rt1711h_probe(struct i2c_client *client,
+			 const struct i2c_device_id *i2c_id)
+{
+	int ret;
+	struct rt1711h_chip *chip;
+
+	ret = rt1711h_check_revision(client);
+	if (ret < 0) {
+		dev_err(&client->dev, "check vid/pid fail\n");
+		return ret;
+	}
+
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->data.regmap = devm_regmap_init_i2c(client,
+						 &rt1711h_regmap_config);
+	if (IS_ERR(chip->data.regmap))
+		return PTR_ERR(chip->data.regmap);
+
+	chip->dev = &client->dev;
+	i2c_set_clientdata(client, chip);
+
+	ret = rt1711h_sw_reset(chip);
+	if (ret < 0)
+		return ret;
+
+	ret = rt1711h_init_alert(chip, client);
+	if (ret < 0)
+		return ret;
+
+	chip->data.init = rt1711h_init;
+	chip->data.set_vconn = rt1711h_set_vconn;
+	chip->data.start_drp_toggling = rt1711h_start_drp_toggling;
+	chip->tcpci = tcpci_register_port(chip->dev, &chip->data);
+	if (IS_ERR_OR_NULL(chip->tcpci))
+		return PTR_ERR(chip->tcpci);
+
+	return 0;
+}
+
+static int rt1711h_remove(struct i2c_client *client)
+{
+	struct rt1711h_chip *chip = i2c_get_clientdata(client);
+
+	tcpci_unregister_port(chip->tcpci);
+	return 0;
+}
+
+static const struct i2c_device_id rt1711h_id[] = {
+	{ "rt1711h", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, rt1711h_id);
+
+#ifdef CONFIG_OF
+static const struct of_device_id rt1711h_of_match[] = {
+	{ .compatible = "richtek,rt1711h", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, rt1711h_of_match);
+#endif
+
+static struct i2c_driver rt1711h_i2c_driver = {
+	.driver = {
+		.name = "rt1711h",
+		.of_match_table = of_match_ptr(rt1711h_of_match),
+	},
+	.probe = rt1711h_probe,
+	.remove = rt1711h_remove,
+	.id_table = rt1711h_id,
+};
+module_i2c_driver(rt1711h_i2c_driver);
+
+MODULE_AUTHOR("ShuFan Lee <shufan_lee@richtek.com>");
+MODULE_DESCRIPTION("RT1711H USB Type-C Port Controller Interface Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/staging/vboxvideo/vbox_drv.c b/drivers/staging/vboxvideo/vbox_drv.c
index e18642e5027e..f6d26beffa54 100644
--- a/drivers/staging/vboxvideo/vbox_drv.c
+++ b/drivers/staging/vboxvideo/vbox_drv.c
@@ -242,7 +242,7 @@ static struct drm_driver driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 
-	.gem_free_object = vbox_gem_free_object,
+	.gem_free_object_unlocked = vbox_gem_free_object,
 	.dumb_create = vbox_dumb_create,
 	.dumb_map_offset = vbox_dumb_mmap_offset,
 	.dumb_destroy = drm_gem_dumb_destroy,
diff --git a/drivers/staging/wilc1000/host_interface.c b/drivers/staging/wilc1000/host_interface.c
index 6b5300ca44a6..885f5fcead77 100644
--- a/drivers/staging/wilc1000/host_interface.c
+++ b/drivers/staging/wilc1000/host_interface.c
@@ -1390,7 +1390,7 @@ static inline void host_int_parse_assoc_resp_info(struct wilc_vif *vif,
 	}
 
 	if (hif_drv->usr_conn_req.ies) {
-		conn_info.req_ies = kmemdup(conn_info.req_ies,
+		conn_info.req_ies = kmemdup(hif_drv->usr_conn_req.ies,
 					    hif_drv->usr_conn_req.ies_len,
 					    GFP_KERNEL);
 		if (conn_info.req_ies)
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 07c814c42648..ce1321a5cb7b 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -94,8 +94,8 @@ static int iblock_configure_device(struct se_device *dev)
 		return -EINVAL;
 	}
 
-	ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-	if (!ib_dev->ibd_bio_set) {
+	ret = bioset_init(&ib_dev->ibd_bio_set, IBLOCK_BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	if (ret) {
 		pr_err("IBLOCK: Unable to create bioset\n");
 		goto out;
 	}
@@ -141,7 +141,7 @@ static int iblock_configure_device(struct se_device *dev)
 
 	bi = bdev_get_integrity(bd);
 	if (bi) {
-		struct bio_set *bs = ib_dev->ibd_bio_set;
+		struct bio_set *bs = &ib_dev->ibd_bio_set;
 
 		if (!strcmp(bi->profile->name, "T10-DIF-TYPE3-IP") ||
 		    !strcmp(bi->profile->name, "T10-DIF-TYPE1-IP")) {
@@ -164,7 +164,7 @@ static int iblock_configure_device(struct se_device *dev)
 				goto out_blkdev_put;
 			}
 			pr_debug("IBLOCK setup BIP bs->bio_integrity_pool: %p\n",
-				 bs->bio_integrity_pool);
+				 &bs->bio_integrity_pool);
 		}
 		dev->dev_attrib.hw_pi_prot_type = dev->dev_attrib.pi_prot_type;
 	}
@@ -174,8 +174,7 @@ static int iblock_configure_device(struct se_device *dev)
 out_blkdev_put:
 	blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
 out_free_bioset:
-	bioset_free(ib_dev->ibd_bio_set);
-	ib_dev->ibd_bio_set = NULL;
+	bioset_exit(&ib_dev->ibd_bio_set);
 out:
 	return ret;
 }
@@ -199,8 +198,7 @@ static void iblock_destroy_device(struct se_device *dev)
 
 	if (ib_dev->ibd_bd != NULL)
 		blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
-	if (ib_dev->ibd_bio_set != NULL)
-		bioset_free(ib_dev->ibd_bio_set);
+	bioset_exit(&ib_dev->ibd_bio_set);
 }
 
 static unsigned long long iblock_emulate_read_cap_with_block_size(
@@ -332,7 +330,7 @@ iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num, int op,
 	if (sg_num > BIO_MAX_PAGES)
 		sg_num = BIO_MAX_PAGES;
 
-	bio = bio_alloc_bioset(GFP_NOIO, sg_num, ib_dev->ibd_bio_set);
+	bio = bio_alloc_bioset(GFP_NOIO, sg_num, &ib_dev->ibd_bio_set);
 	if (!bio) {
 		pr_err("Unable to allocate memory for bio\n");
 		return NULL;
@@ -427,8 +425,8 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct scatterlist *sg = &cmd->t_data_sg[0];
-	unsigned char *buf, zero = 0x00, *p = &zero;
-	int rc, ret;
+	unsigned char *buf, *not_zero;
+	int ret;
 
 	buf = kmap(sg_page(sg)) + sg->offset;
 	if (!buf)
@@ -437,10 +435,10 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd)
 	 * Fall back to block_execute_write_same() slow-path if
 	 * incoming WRITE_SAME payload does not contain zeros.
 	 */
-	rc = memcmp(buf, p, cmd->data_length);
+	not_zero = memchr_inv(buf, 0x00, cmd->data_length);
 	kunmap(sg_page(sg));
 
-	if (rc)
+	if (not_zero)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	ret = blkdev_issue_zeroout(bdev,
diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h
index b4aeb2584ad4..9cc3843404d4 100644
--- a/drivers/target/target_core_iblock.h
+++ b/drivers/target/target_core_iblock.h
@@ -22,7 +22,7 @@ struct iblock_dev {
 	struct se_device dev;
 	unsigned char ibd_udev_path[SE_UDEV_PATH_LEN];
 	u32	ibd_flags;
-	struct bio_set	*ibd_bio_set;
+	struct bio_set	ibd_bio_set;
 	struct block_device *ibd_bd;
 	bool ibd_readonly;
 } ____cacheline_aligned;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 0d99b242e82e..668934ea74cb 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -890,6 +890,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 			bytes = min(bytes, data_len);
 
 			if (!bio) {
+new_bio:
 				nr_vecs = min_t(int, BIO_MAX_PAGES, nr_pages);
 				nr_pages -= nr_vecs;
 				/*
@@ -931,6 +932,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 				 * be allocated with pscsi_get_bio() above.
 				 */
 				bio = NULL;
+				goto new_bio;
 			}
 
 			data_len -= bytes;
@@ -984,8 +986,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 
 	req = blk_get_request(pdv->pdv_sd->request_queue,
 			cmd->data_direction == DMA_TO_DEVICE ?
-			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
-			GFP_KERNEL);
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(req)) {
 		pr_err("PSCSI: blk_get_request() failed\n");
 		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 4ad89ea71a70..4f26bdc3d1dc 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -2121,6 +2121,8 @@ static ssize_t tcmu_qfull_time_out_store(struct config_item *item,
 
 	if (val >= 0) {
 		udev->qfull_time_out = val * MSEC_PER_SEC;
+	} else if (val == -1) {
+		udev->qfull_time_out = val;
 	} else {
 		printk(KERN_ERR "Invalid qfull timeout value %d\n", val);
 		return -EINVAL;
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index 0124a91c8d71..dd46b758852a 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -238,6 +238,17 @@ static int params_from_user(struct tee_context *ctx, struct tee_param *params,
 			if (IS_ERR(shm))
 				return PTR_ERR(shm);
 
+			/*
+			 * Ensure offset + size does not overflow offset
+			 * and does not overflow the size of the referred
+			 * shared memory object.
+			 */
+			if ((ip.a + ip.b) < ip.a ||
+			    (ip.a + ip.b) > shm->size) {
+				tee_shm_put(shm);
+				return -EINVAL;
+			}
+
 			params[n].u.memref.shm_offs = ip.a;
 			params[n].u.memref.size = ip.b;
 			params[n].u.memref.shm = shm;
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 556960a1bab3..07d3be6f0780 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -360,9 +360,10 @@ int tee_shm_get_fd(struct tee_shm *shm)
 	if (!(shm->flags & TEE_SHM_DMA_BUF))
 		return -EINVAL;
 
+	get_dma_buf(shm->dmabuf);
 	fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC);
-	if (fd >= 0)
-		get_dma_buf(shm->dmabuf);
+	if (fd < 0)
+		dma_buf_put(shm->dmabuf);
 	return fd;
 }
 
diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c
index a4d6a0e2e993..23ad4f9f2143 100644
--- a/drivers/thermal/broadcom/bcm2835_thermal.c
+++ b/drivers/thermal/broadcom/bcm2835_thermal.c
@@ -213,8 +213,8 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
 	rate = clk_get_rate(data->clk);
 	if ((rate < 1920000) || (rate > 5000000))
 		dev_warn(&pdev->dev,
-			 "Clock %pCn running at %pCr Hz is outside of the recommended range: 1.92 to 5MHz\n",
-			 data->clk, data->clk);
+			 "Clock %pCn running at %lu Hz is outside of the recommended range: 1.92 to 5MHz\n",
+			 data->clk, rate);
 
 	/* register of thermal sensor and get info from DT */
 	tz = thermal_zone_of_sensor_register(&pdev->dev, 0, data,
diff --git a/drivers/thermal/int340x_thermal/int3403_thermal.c b/drivers/thermal/int340x_thermal/int3403_thermal.c
index 8a7f24dd9315..0c19fcd56a0d 100644
--- a/drivers/thermal/int340x_thermal/int3403_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3403_thermal.c
@@ -194,6 +194,7 @@ static int int3403_cdev_add(struct int3403_priv *priv)
 		return -EFAULT;
 	}
 
+	priv->priv = obj;
 	obj->max_state = p->package.count - 1;
 	obj->cdev =
 		thermal_cooling_device_register(acpi_device_bid(priv->adev),
@@ -201,8 +202,6 @@ static int int3403_cdev_add(struct int3403_priv *priv)
 	if (IS_ERR(obj->cdev))
 		result = PTR_ERR(obj->cdev);
 
-	priv->priv = obj;
-
 	kfree(buf.pointer);
 	/* TODO: add ACPI notification support */
 
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index ed805c7c5ace..ac83f721db24 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -185,6 +185,7 @@
  * @regulator: pointer to the TMU regulator structure.
  * @reg_conf: pointer to structure to register with core thermal.
  * @ntrip: number of supported trip points.
+ * @enabled: current status of TMU device
  * @tmu_initialize: SoC specific TMU initialization method
  * @tmu_control: SoC specific TMU control method
  * @tmu_read: SoC specific TMU temperature read method
@@ -205,6 +206,7 @@ struct exynos_tmu_data {
 	struct regulator *regulator;
 	struct thermal_zone_device *tzd;
 	unsigned int ntrip;
+	bool enabled;
 
 	int (*tmu_initialize)(struct platform_device *pdev);
 	void (*tmu_control)(struct platform_device *pdev, bool on);
@@ -398,6 +400,7 @@ static void exynos_tmu_control(struct platform_device *pdev, bool on)
 	mutex_lock(&data->lock);
 	clk_enable(data->clk);
 	data->tmu_control(pdev, on);
+	data->enabled = on;
 	clk_disable(data->clk);
 	mutex_unlock(&data->lock);
 }
@@ -889,19 +892,24 @@ static void exynos7_tmu_control(struct platform_device *pdev, bool on)
 static int exynos_get_temp(void *p, int *temp)
 {
 	struct exynos_tmu_data *data = p;
+	int value, ret = 0;
 
-	if (!data || !data->tmu_read)
+	if (!data || !data->tmu_read || !data->enabled)
 		return -EINVAL;
 
 	mutex_lock(&data->lock);
 	clk_enable(data->clk);
 
-	*temp = code_to_temp(data, data->tmu_read(data)) * MCELSIUS;
+	value = data->tmu_read(data);
+	if (value < 0)
+		ret = value;
+	else
+		*temp = code_to_temp(data, value) * MCELSIUS;
 
 	clk_disable(data->clk);
 	mutex_unlock(&data->lock);
 
-	return 0;
+	return ret;
 }
 
 #ifdef CONFIG_THERMAL_EMULATION
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index 2d2ceda9aa26..500911f16498 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -1255,7 +1255,7 @@ static int icm_ar_get_boot_acl(struct tb *tb, uuid_t *uuids, size_t nuuids)
 			/* Map empty entries to null UUID */
 			uuid[0] = 0;
 			uuid[1] = 0;
-		} else {
+		} else if (uuid[0] != 0 || uuid[1] != 0) {
 			/* Upper two DWs are always one's */
 			uuid[2] = 0xffffffff;
 			uuid[3] = 0xffffffff;
diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index 32d7ce430b02..34dead614149 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -1566,19 +1566,6 @@ static int rs_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int rs_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, rs_proc_show, NULL);
-}
-
-static const struct file_operations rs_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= rs_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /*
  * ---------------------------------------------------------------------
  * rs_init() and friends
@@ -1620,7 +1607,7 @@ static const struct tty_operations serial_ops = {
 	.tiocmget = rs_tiocmget,
 	.tiocmset = rs_tiocmset,
 	.get_icount = rs_get_icount,
-	.proc_fops = &rs_proc_fops,
+	.proc_show = rs_proc_show,
 };
 
 static int amiga_carrier_raised(struct tty_port *port)
diff --git a/drivers/tty/cyclades.c b/drivers/tty/cyclades.c
index cf0bde3bb927..6d3c58051ce3 100644
--- a/drivers/tty/cyclades.c
+++ b/drivers/tty/cyclades.c
@@ -3972,19 +3972,6 @@ static int cyclades_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int cyclades_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, cyclades_proc_show, NULL);
-}
-
-static const struct file_operations cyclades_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= cyclades_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /* The serial driver boot-time initialization code!
     Hardware I/O ports are mapped to character special devices on a
     first found, first allocated manner.  That is, this code searches
@@ -4024,7 +4011,7 @@ static const struct tty_operations cy_ops = {
 	.tiocmget = cy_tiocmget,
 	.tiocmset = cy_tiocmset,
 	.get_icount = cy_get_icount,
-	.proc_fops = &cyclades_proc_fops,
+	.proc_show = cyclades_proc_show,
 };
 
 static int __init cy_init(void)
diff --git a/drivers/tty/ipwireless/network.c b/drivers/tty/ipwireless/network.c
index 695439c03147..cf20616340a1 100644
--- a/drivers/tty/ipwireless/network.c
+++ b/drivers/tty/ipwireless/network.c
@@ -416,7 +416,7 @@ void ipwireless_network_packet_received(struct ipw_network *network,
 struct ipw_network *ipwireless_network_create(struct ipw_hardware *hw)
 {
 	struct ipw_network *network =
-		kzalloc(sizeof(struct ipw_network), GFP_ATOMIC);
+		kzalloc(sizeof(struct ipw_network), GFP_KERNEL);
 
 	if (!network)
 		return NULL;
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 3b3e1f6632d7..86b7e20ffd7f 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -121,6 +121,9 @@ struct gsm_dlci {
 	struct mutex mutex;
 
 	/* Link layer */
+	int mode;
+#define DLCI_MODE_ABM		0	/* Normal Asynchronous Balanced Mode */
+#define DLCI_MODE_ADM		1	/* Asynchronous Disconnected Mode */
 	spinlock_t lock;	/* Protects the internal state */
 	struct timer_list t1;	/* Retransmit timer for SABM and UA */
 	int retries;
@@ -1364,7 +1367,13 @@ retry:
 	ctrl->data = data;
 	ctrl->len = clen;
 	gsm->pending_cmd = ctrl;
-	gsm->cretries = gsm->n2;
+
+	/* If DLCI0 is in ADM mode skip retries, it won't respond */
+	if (gsm->dlci[0]->mode == DLCI_MODE_ADM)
+		gsm->cretries = 1;
+	else
+		gsm->cretries = gsm->n2;
+
 	mod_timer(&gsm->t2_timer, jiffies + gsm->t2 * HZ / 100);
 	gsm_control_transmit(gsm, ctrl);
 	spin_unlock_irqrestore(&gsm->control_lock, flags);
@@ -1472,6 +1481,7 @@ static void gsm_dlci_t1(struct timer_list *t)
 			if (debug & 8)
 				pr_info("DLCI %d opening in ADM mode.\n",
 					dlci->addr);
+			dlci->mode = DLCI_MODE_ADM;
 			gsm_dlci_open(dlci);
 		} else {
 			gsm_dlci_close(dlci);
@@ -2665,7 +2675,7 @@ static inline void muxnet_put(struct gsm_mux_net *mux_net)
 	kref_put(&mux_net->ref, net_free);
 }
 
-static int gsm_mux_net_start_xmit(struct sk_buff *skb,
+static netdev_tx_t gsm_mux_net_start_xmit(struct sk_buff *skb,
 				      struct net_device *net)
 {
 	struct gsm_mux_net *mux_net = netdev_priv(net);
@@ -2861,11 +2871,22 @@ static int gsmtty_modem_update(struct gsm_dlci *dlci, u8 brk)
 static int gsm_carrier_raised(struct tty_port *port)
 {
 	struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port);
+	struct gsm_mux *gsm = dlci->gsm;
+
 	/* Not yet open so no carrier info */
 	if (dlci->state != DLCI_OPEN)
 		return 0;
 	if (debug & 2)
 		return 1;
+
+	/*
+	 * Basic mode with control channel in ADM mode may not respond
+	 * to CMD_MSC at all and modem_rx is empty.
+	 */
+	if (gsm->encoding == 0 && gsm->dlci[0]->mode == DLCI_MODE_ADM &&
+	    !dlci->modem_rx)
+		return 1;
+
 	return dlci->modem_rx & TIOCM_CD;
 }
 
diff --git a/drivers/tty/nozomi.c b/drivers/tty/nozomi.c
index b57b35066ebe..fed820e9ab9d 100644
--- a/drivers/tty/nozomi.c
+++ b/drivers/tty/nozomi.c
@@ -72,19 +72,19 @@ do {							\
 
 #define TMP_BUF_MAX 256
 
-#define DUMP(buf__,len__) \
-  do {  \
-    char tbuf[TMP_BUF_MAX] = {0};\
-    if (len__ > 1) {\
-	snprintf(tbuf, len__ > TMP_BUF_MAX ? TMP_BUF_MAX : len__, "%s", buf__);\
-	if (tbuf[len__-2] == '\r') {\
-		tbuf[len__-2] = 'r';\
-	} \
-	DBG1("SENDING: '%s' (%d+n)", tbuf, len__);\
-    } else {\
-	DBG1("SENDING: '%s' (%d)", tbuf, len__);\
-    } \
-} while (0)
+#define DUMP(buf__, len__)						\
+	do {								\
+		char tbuf[TMP_BUF_MAX] = {0};				\
+		if (len__ > 1) {					\
+			u32 data_len = min_t(u32, len__, TMP_BUF_MAX);	\
+			strscpy(tbuf, buf__, data_len);			\
+			if (tbuf[data_len - 2] == '\r')			\
+				tbuf[data_len - 2] = 'r';		\
+			DBG1("SENDING: '%s' (%d+n)", tbuf, len__);	\
+		} else {						\
+			DBG1("SENDING: '%s' (%d)", tbuf, len__);	\
+		}							\
+	} while (0)
 
 /*    Defines */
 #define NOZOMI_NAME		"nozomi"
@@ -102,41 +102,41 @@ do {							\
 #define RECEIVE_BUF_MAX		4
 
 
-#define R_IIR		0x0000	/* Interrupt Identity Register */
-#define R_FCR		0x0000	/* Flow Control Register */
-#define R_IER		0x0004	/* Interrupt Enable Register */
+#define R_IIR			0x0000	/* Interrupt Identity Register */
+#define R_FCR			0x0000	/* Flow Control Register */
+#define R_IER			0x0004	/* Interrupt Enable Register */
 
 #define NOZOMI_CONFIG_MAGIC	0xEFEFFEFE
 #define TOGGLE_VALID		0x0000
 
 /* Definition of interrupt tokens */
-#define MDM_DL1		0x0001
-#define MDM_UL1		0x0002
-#define MDM_DL2		0x0004
-#define MDM_UL2		0x0008
-#define DIAG_DL1	0x0010
-#define DIAG_DL2	0x0020
-#define DIAG_UL		0x0040
-#define APP1_DL		0x0080
-#define APP1_UL		0x0100
-#define APP2_DL		0x0200
-#define APP2_UL		0x0400
-#define CTRL_DL		0x0800
-#define CTRL_UL		0x1000
-#define RESET		0x8000
-
-#define MDM_DL		(MDM_DL1  | MDM_DL2)
-#define MDM_UL		(MDM_UL1  | MDM_UL2)
-#define DIAG_DL		(DIAG_DL1 | DIAG_DL2)
+#define MDM_DL1			0x0001
+#define MDM_UL1			0x0002
+#define MDM_DL2			0x0004
+#define MDM_UL2			0x0008
+#define DIAG_DL1		0x0010
+#define DIAG_DL2		0x0020
+#define DIAG_UL			0x0040
+#define APP1_DL			0x0080
+#define APP1_UL			0x0100
+#define APP2_DL			0x0200
+#define APP2_UL			0x0400
+#define CTRL_DL			0x0800
+#define CTRL_UL			0x1000
+#define RESET			0x8000
+
+#define MDM_DL			(MDM_DL1  | MDM_DL2)
+#define MDM_UL			(MDM_UL1  | MDM_UL2)
+#define DIAG_DL			(DIAG_DL1 | DIAG_DL2)
 
 /* modem signal definition */
-#define CTRL_DSR	0x0001
-#define CTRL_DCD	0x0002
-#define CTRL_RI		0x0004
-#define CTRL_CTS	0x0008
+#define CTRL_DSR		0x0001
+#define CTRL_DCD		0x0002
+#define CTRL_RI			0x0004
+#define CTRL_CTS		0x0008
 
-#define CTRL_DTR	0x0001
-#define CTRL_RTS	0x0002
+#define CTRL_DTR		0x0001
+#define CTRL_RTS		0x0002
 
 #define MAX_PORT		4
 #define NOZOMI_MAX_PORTS	5
@@ -155,7 +155,7 @@ enum card_type {
 
 /* Initialization states a card can be in */
 enum card_state {
-	NOZOMI_STATE_UKNOWN	= 0,
+	NOZOMI_STATE_UNKNOWN	= 0,
 	NOZOMI_STATE_ENABLED	= 1,	/* pci device enabled */
 	NOZOMI_STATE_ALLOCATED	= 2,	/* config setup done */
 	NOZOMI_STATE_READY	= 3,	/* flowcontrols received */
@@ -365,7 +365,7 @@ struct buffer {
 	u8 *data;
 } __attribute__ ((packed));
 
-/*    Global variables */
+/* Global variables */
 static const struct pci_device_id nozomi_pci_tbl[] = {
 	{PCI_DEVICE(0x1931, 0x000c)},	/* Nozomi HSDPA */
 	{},
@@ -1686,12 +1686,12 @@ static int ntty_tiocmget(struct tty_struct *tty)
 
 	/* Note: these could change under us but it is not clear this
 	   matters if so */
-	return	(ctrl_ul->RTS ? TIOCM_RTS : 0) |
-		(ctrl_ul->DTR ? TIOCM_DTR : 0) |
-		(ctrl_dl->DCD ? TIOCM_CAR : 0) |
-		(ctrl_dl->RI  ? TIOCM_RNG : 0) |
-		(ctrl_dl->DSR ? TIOCM_DSR : 0) |
-		(ctrl_dl->CTS ? TIOCM_CTS : 0);
+	return (ctrl_ul->RTS ? TIOCM_RTS : 0)
+		| (ctrl_ul->DTR ? TIOCM_DTR : 0)
+		| (ctrl_dl->DCD ? TIOCM_CAR : 0)
+		| (ctrl_dl->RI  ? TIOCM_RNG : 0)
+		| (ctrl_dl->DSR ? TIOCM_DSR : 0)
+		| (ctrl_dl->CTS ? TIOCM_CTS : 0);
 }
 
 /* Sets io controls parameters */
@@ -1722,10 +1722,10 @@ static int ntty_cflags_changed(struct port *port, unsigned long flags,
 	const struct async_icount cnow = port->tty_icount;
 	int ret;
 
-	ret =	((flags & TIOCM_RNG) && (cnow.rng != cprev->rng)) ||
-		((flags & TIOCM_DSR) && (cnow.dsr != cprev->dsr)) ||
-		((flags & TIOCM_CD)  && (cnow.dcd != cprev->dcd)) ||
-		((flags & TIOCM_CTS) && (cnow.cts != cprev->cts));
+	ret = ((flags & TIOCM_RNG) && (cnow.rng != cprev->rng))
+		|| ((flags & TIOCM_DSR) && (cnow.dsr != cprev->dsr))
+		|| ((flags & TIOCM_CD)  && (cnow.dcd != cprev->dcd))
+		|| ((flags & TIOCM_CTS) && (cnow.cts != cprev->cts));
 
 	*cprev = cnow;
 
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 6c7151edd715..b0e2c4847a5d 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -110,16 +110,19 @@ static void pty_unthrottle(struct tty_struct *tty)
 static int pty_write(struct tty_struct *tty, const unsigned char *buf, int c)
 {
 	struct tty_struct *to = tty->link;
+	unsigned long flags;
 
 	if (tty->stopped)
 		return 0;
 
 	if (c > 0) {
+		spin_lock_irqsave(&to->port->lock, flags);
 		/* Stuff the data into the input queue of the other end */
 		c = tty_insert_flip_string(to->port, buf, c);
 		/* And shovel */
 		if (c)
 			tty_flip_buffer_push(to->port);
+		spin_unlock_irqrestore(&to->port->lock, flags);
 	}
 	return c;
 }
diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c
index 74a408d9db24..435bec40dee6 100644
--- a/drivers/tty/serial/8250/8250_aspeed_vuart.c
+++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c
@@ -10,6 +10,8 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
 #include <linux/clk.h>
 
 #include "8250.h"
@@ -28,9 +30,18 @@ struct aspeed_vuart {
 	void __iomem		*regs;
 	struct clk		*clk;
 	int			line;
+	struct timer_list	unthrottle_timer;
+	struct uart_8250_port	*port;
 };
 
 /*
+ * If we fill the tty flip buffers, we throttle the data ready interrupt
+ * to prevent dropped characters. This timeout defines how long we wait
+ * to (conditionally, depending on buffer state) unthrottle.
+ */
+static const int unthrottle_timeout = HZ/10;
+
+/*
  * The VUART is basically two UART 'front ends' connected by their FIFO
  * (no actual serial line in between). One is on the BMC side (management
  * controller) and one is on the host CPU side.
@@ -179,6 +190,114 @@ static void aspeed_vuart_shutdown(struct uart_port *uart_port)
 	serial8250_do_shutdown(uart_port);
 }
 
+static void __aspeed_vuart_set_throttle(struct uart_8250_port *up,
+		bool throttle)
+{
+	unsigned char irqs = UART_IER_RLSI | UART_IER_RDI;
+
+	up->ier &= ~irqs;
+	if (!throttle)
+		up->ier |= irqs;
+	serial_out(up, UART_IER, up->ier);
+}
+static void aspeed_vuart_set_throttle(struct uart_port *port, bool throttle)
+{
+	struct uart_8250_port *up = up_to_u8250p(port);
+	unsigned long flags;
+
+	spin_lock_irqsave(&port->lock, flags);
+	__aspeed_vuart_set_throttle(up, throttle);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static void aspeed_vuart_throttle(struct uart_port *port)
+{
+	aspeed_vuart_set_throttle(port, true);
+}
+
+static void aspeed_vuart_unthrottle(struct uart_port *port)
+{
+	aspeed_vuart_set_throttle(port, false);
+}
+
+static void aspeed_vuart_unthrottle_exp(struct timer_list *timer)
+{
+	struct aspeed_vuart *vuart = from_timer(vuart, timer, unthrottle_timer);
+	struct uart_8250_port *up = vuart->port;
+
+	if (!tty_buffer_space_avail(&up->port.state->port)) {
+		mod_timer(&vuart->unthrottle_timer,
+			  jiffies + unthrottle_timeout);
+		return;
+	}
+
+	aspeed_vuart_unthrottle(&up->port);
+}
+
+/*
+ * Custom interrupt handler to manage finer-grained flow control. Although we
+ * have throttle/unthrottle callbacks, we've seen that the VUART device can
+ * deliver characters faster than the ldisc has a chance to check buffer space
+ * against the throttle threshold. This results in dropped characters before
+ * the throttle.
+ *
+ * We do this by checking for flip buffer space before RX. If we have no space,
+ * throttle now and schedule an unthrottle for later, once the ldisc has had
+ * a chance to drain the buffers.
+ */
+static int aspeed_vuart_handle_irq(struct uart_port *port)
+{
+	struct uart_8250_port *up = up_to_u8250p(port);
+	unsigned int iir, lsr;
+	unsigned long flags;
+	int space, count;
+
+	iir = serial_port_in(port, UART_IIR);
+
+	if (iir & UART_IIR_NO_INT)
+		return 0;
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	lsr = serial_port_in(port, UART_LSR);
+
+	if (lsr & (UART_LSR_DR | UART_LSR_BI)) {
+		space = tty_buffer_space_avail(&port->state->port);
+
+		if (!space) {
+			/* throttle and schedule an unthrottle later */
+			struct aspeed_vuart *vuart = port->private_data;
+			__aspeed_vuart_set_throttle(up, true);
+
+			if (!timer_pending(&vuart->unthrottle_timer)) {
+				vuart->port = up;
+				mod_timer(&vuart->unthrottle_timer,
+					  jiffies + unthrottle_timeout);
+			}
+
+		} else {
+			count = min(space, 256);
+
+			do {
+				serial8250_read_char(up, lsr);
+				lsr = serial_in(up, UART_LSR);
+				if (--count == 0)
+					break;
+			} while (lsr & (UART_LSR_DR | UART_LSR_BI));
+
+			tty_flip_buffer_push(&port->state->port);
+		}
+	}
+
+	serial8250_modem_status(up);
+	if (lsr & UART_LSR_THRE)
+		serial8250_tx_chars(up);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return 1;
+}
+
 static int aspeed_vuart_probe(struct platform_device *pdev)
 {
 	struct uart_8250_port port;
@@ -195,6 +314,7 @@ static int aspeed_vuart_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	vuart->dev = &pdev->dev;
+	timer_setup(&vuart->unthrottle_timer, aspeed_vuart_unthrottle_exp, 0);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	vuart->regs = devm_ioremap_resource(&pdev->dev, res);
@@ -208,6 +328,9 @@ static int aspeed_vuart_probe(struct platform_device *pdev)
 	port.port.mapsize = resource_size(res);
 	port.port.startup = aspeed_vuart_startup;
 	port.port.shutdown = aspeed_vuart_shutdown;
+	port.port.throttle = aspeed_vuart_throttle;
+	port.port.unthrottle = aspeed_vuart_unthrottle;
+	port.port.status = UPSTAT_SYNC_FIFO;
 	port.port.dev = &pdev->dev;
 
 	rc = sysfs_create_group(&vuart->dev->kobj, &aspeed_vuart_attr_group);
@@ -253,6 +376,7 @@ static int aspeed_vuart_probe(struct platform_device *pdev)
 
 	port.port.irq = irq_of_parse_and_map(np, 0);
 	port.port.irqflags = IRQF_SHARED;
+	port.port.handle_irq = aspeed_vuart_handle_irq;
 	port.port.iotype = UPIO_MEM;
 	port.port.type = PORT_16550A;
 	port.port.uartclk = clk;
@@ -292,6 +416,7 @@ static int aspeed_vuart_remove(struct platform_device *pdev)
 {
 	struct aspeed_vuart *vuart = platform_get_drvdata(pdev);
 
+	del_timer_sync(&vuart->unthrottle_timer);
 	aspeed_vuart_set_enabled(vuart, false);
 	serial8250_unregister_port(vuart->line);
 	sysfs_remove_group(&vuart->dev->kobj, &aspeed_vuart_attr_group);
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 6fcdb90f616a..aff04f1de3a5 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -121,25 +121,44 @@ static void dw8250_check_lcr(struct uart_port *p, int value)
 }
 
 /* Returns once the transmitter is empty or we run out of retries */
-static void dw8250_tx_wait_empty(struct uart_port *p, int tries)
+static void dw8250_tx_wait_empty(struct uart_port *p)
 {
+	unsigned int tries = 20000;
+	unsigned int delay_threshold = tries - 1000;
 	unsigned int lsr;
 
 	while (tries--) {
 		lsr = readb (p->membase + (UART_LSR << p->regshift));
 		if (lsr & UART_LSR_TEMT)
 			break;
-		udelay (10);
+
+		/* The device is first given a chance to empty without delay,
+		 * to avoid slowdowns at high bitrates. If after 1000 tries
+		 * the buffer has still not emptied, allow more time for low-
+		 * speed links. */
+		if (tries < delay_threshold)
+			udelay (1);
 	}
 }
 
-static void dw8250_serial_out(struct uart_port *p, int offset, int value)
+static void dw8250_serial_out38x(struct uart_port *p, int offset, int value)
 {
 	struct dw8250_data *d = p->private_data;
 
 	/* Allow the TX to drain before we reconfigure */
 	if (offset == UART_LCR)
-		dw8250_tx_wait_empty(p, 1000);
+		dw8250_tx_wait_empty(p);
+
+	writeb(value, p->membase + (offset << p->regshift));
+
+	if (offset == UART_LCR && !d->uart_16550_compatible)
+		dw8250_check_lcr(p, value);
+}
+
+
+static void dw8250_serial_out(struct uart_port *p, int offset, int value)
+{
+	struct dw8250_data *d = p->private_data;
 
 	writeb(value, p->membase + (offset << p->regshift));
 
@@ -357,6 +376,9 @@ static void dw8250_quirks(struct uart_port *p, struct dw8250_data *data)
 			p->serial_in = dw8250_serial_in32be;
 			p->serial_out = dw8250_serial_out32be;
 		}
+		if (of_device_is_compatible(np, "marvell,armada-38x-uart"))
+			p->serial_out = dw8250_serial_out38x;
+
 	} else if (acpi_dev_present("APMC0D08", NULL, -1)) {
 		p->iotype = UPIO_MEM32;
 		p->regshift = 2;
@@ -554,6 +576,10 @@ static int dw8250_probe(struct platform_device *pdev)
 	if (!data->skip_autocfg)
 		dw8250_setup_port(p);
 
+#ifdef CONFIG_PM
+	uart.capabilities |= UART_CAP_RPM;
+#endif
+
 	/* If we have a valid fifosize, try hooking up DMA */
 	if (p->fifosize) {
 		data->dma.rxconf.src_maxburst = p->fifosize / 4;
@@ -666,6 +692,7 @@ static const struct dev_pm_ops dw8250_pm_ops = {
 static const struct of_device_id dw8250_of_match[] = {
 	{ .compatible = "snps,dw-apb-uart" },
 	{ .compatible = "cavium,octeon-3860-uart" },
+	{ .compatible = "marvell,armada-38x-uart" },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, dw8250_of_match);
diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index ae6a256524d8..5cd8c36c8fcc 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -122,7 +122,7 @@ static void __init init_port(struct earlycon_device *device)
 	serial8250_early_out(port, UART_FCR, 0);	/* no fifo */
 	serial8250_early_out(port, UART_MCR, 0x3);	/* DTR + RTS */
 
-	if (port->uartclk && device->baud) {
+	if (port->uartclk) {
 		divisor = DIV_ROUND_CLOSEST(port->uartclk, 16 * device->baud);
 		c = serial8250_early_in(port, UART_LCR);
 		serial8250_early_out(port, UART_LCR, c | UART_LCR_DLAB);
diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c
index 9835b1c1cbe1..bfb37f0be22f 100644
--- a/drivers/tty/serial/8250/8250_of.c
+++ b/drivers/tty/serial/8250/8250_of.c
@@ -92,13 +92,43 @@ static int of_platform_serial_setup(struct platform_device *ofdev,
 		goto err_unprepare;
 	}
 
+	port->flags = UPF_SHARE_IRQ | UPF_BOOT_AUTOCONF | UPF_FIXED_PORT |
+				  UPF_FIXED_TYPE;
 	spin_lock_init(&port->lock);
-	port->mapbase = resource.start;
-	port->mapsize = resource_size(&resource);
 
-	/* Check for shifted address mapping */
-	if (of_property_read_u32(np, "reg-offset", &prop) == 0)
-		port->mapbase += prop;
+	if (resource_type(&resource) == IORESOURCE_IO) {
+		port->iotype = UPIO_PORT;
+		port->iobase = resource.start;
+	} else {
+		port->mapbase = resource.start;
+		port->mapsize = resource_size(&resource);
+
+		/* Check for shifted address mapping */
+		if (of_property_read_u32(np, "reg-offset", &prop) == 0)
+			port->mapbase += prop;
+
+		port->iotype = UPIO_MEM;
+		if (of_property_read_u32(np, "reg-io-width", &prop) == 0) {
+			switch (prop) {
+			case 1:
+				port->iotype = UPIO_MEM;
+				break;
+			case 2:
+				port->iotype = UPIO_MEM16;
+				break;
+			case 4:
+				port->iotype = of_device_is_big_endian(np) ?
+					       UPIO_MEM32BE : UPIO_MEM32;
+				break;
+			default:
+				dev_warn(&ofdev->dev, "unsupported reg-io-width (%d)\n",
+					 prop);
+				ret = -EINVAL;
+				goto err_dispose;
+			}
+		}
+		port->flags |= UPF_IOREMAP;
+	}
 
 	/* Check for registers offset within the devices address range */
 	if (of_property_read_u32(np, "reg-shift", &prop) == 0)
@@ -114,26 +144,6 @@ static int of_platform_serial_setup(struct platform_device *ofdev,
 		port->line = ret;
 
 	port->irq = irq_of_parse_and_map(np, 0);
-	port->iotype = UPIO_MEM;
-	if (of_property_read_u32(np, "reg-io-width", &prop) == 0) {
-		switch (prop) {
-		case 1:
-			port->iotype = UPIO_MEM;
-			break;
-		case 2:
-			port->iotype = UPIO_MEM16;
-			break;
-		case 4:
-			port->iotype = of_device_is_big_endian(np) ?
-				       UPIO_MEM32BE : UPIO_MEM32;
-			break;
-		default:
-			dev_warn(&ofdev->dev, "unsupported reg-io-width (%d)\n",
-				 prop);
-			ret = -EINVAL;
-			goto err_dispose;
-		}
-	}
 
 	info->rst = devm_reset_control_get_optional_shared(&ofdev->dev, NULL);
 	if (IS_ERR(info->rst)) {
@@ -147,8 +157,7 @@ static int of_platform_serial_setup(struct platform_device *ofdev,
 
 	port->type = type;
 	port->uartclk = clk;
-	port->flags = UPF_SHARE_IRQ | UPF_BOOT_AUTOCONF | UPF_IOREMAP
-		| UPF_FIXED_PORT | UPF_FIXED_TYPE;
+	port->irqflags |= IRQF_SHARED;
 
 	if (of_property_read_bool(np, "no-loopback-test"))
 		port->flags |= UPF_SKIP_TEST;
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 624b501fd253..1b337fee07ed 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -1110,13 +1110,14 @@ static int omap8250_no_handle_irq(struct uart_port *port)
 	return 0;
 }
 
+static const u8 omap4_habit = UART_ERRATA_CLOCK_DISABLE;
 static const u8 am3352_habit = OMAP_DMA_TX_KICK | UART_ERRATA_CLOCK_DISABLE;
 static const u8 dra742_habit = UART_ERRATA_CLOCK_DISABLE;
 
 static const struct of_device_id omap8250_dt_ids[] = {
 	{ .compatible = "ti,omap2-uart" },
 	{ .compatible = "ti,omap3-uart" },
-	{ .compatible = "ti,omap4-uart" },
+	{ .compatible = "ti,omap4-uart", .data = &omap4_habit, },
 	{ .compatible = "ti,am3352-uart", .data = &am3352_habit, },
 	{ .compatible = "ti,am4372-uart", .data = &am3352_habit, },
 	{ .compatible = "ti,dra742-uart", .data = &dra742_habit, },
@@ -1310,8 +1311,17 @@ static void omap8250_complete(struct device *dev)
 static int omap8250_suspend(struct device *dev)
 {
 	struct omap8250_priv *priv = dev_get_drvdata(dev);
+	struct uart_8250_port *up = serial8250_get_port(priv->line);
 
 	serial8250_suspend_port(priv->line);
+
+	pm_runtime_get_sync(dev);
+	if (!device_may_wakeup(dev))
+		priv->wer = 0;
+	serial_out(up, UART_OMAP_WER, priv->wer);
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
 	flush_work(&priv->qos_work);
 	return 0;
 }
@@ -1353,6 +1363,19 @@ static int omap8250_soft_reset(struct device *dev)
 	int sysc;
 	int syss;
 
+	/*
+	 * At least on omap4, unused uarts may not idle after reset without
+	 * a basic scr dma configuration even with no dma in use. The
+	 * module clkctrl status bits will be 1 instead of 3 blocking idle
+	 * for the whole clockdomain. The softreset below will clear scr,
+	 * and we restore it on resume so this is safe to do on all SoCs
+	 * needing omap8250_soft_reset() quirk. Do it in two writes as
+	 * recommended in the comment for omap8250_update_scr().
+	 */
+	serial_out(up, UART_OMAP_SCR, OMAP_UART_SCR_DMAMODE_1);
+	serial_out(up, UART_OMAP_SCR,
+		   OMAP_UART_SCR_DMAMODE_1 | OMAP_UART_SCR_DMAMODE_CTL);
+
 	sysc = serial_in(up, UART_OMAP_SYSC);
 
 	/* softreset the UART */
@@ -1403,6 +1426,8 @@ static int omap8250_runtime_suspend(struct device *dev)
 
 		/* Restore to UART mode after reset (for wakeup) */
 		omap8250_update_mdr1(up, priv);
+		/* Restore wakeup enable register */
+		serial_out(up, UART_OMAP_WER, priv->wer);
 	}
 
 	if (up->dma && up->dma->rxchan)
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 95833cbc4338..cf541aab2bd0 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -243,6 +243,7 @@ static const struct serial8250_config uart_config[] = {
 		.fifo_size	= 32,
 		.tx_loadsz	= 32,
 		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+		.rxtrig_bytes	= {1, 8, 16, 30},
 		.flags		= UART_CAP_FIFO | UART_CAP_AFE,
 	},
 	[PORT_ALTR_16550_F64] = {
@@ -250,6 +251,7 @@ static const struct serial8250_config uart_config[] = {
 		.fifo_size	= 64,
 		.tx_loadsz	= 64,
 		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+		.rxtrig_bytes	= {1, 16, 32, 62},
 		.flags		= UART_CAP_FIFO | UART_CAP_AFE,
 	},
 	[PORT_ALTR_16550_F128] = {
@@ -257,6 +259,7 @@ static const struct serial8250_config uart_config[] = {
 		.fifo_size	= 128,
 		.tx_loadsz	= 128,
 		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+		.rxtrig_bytes	= {1, 32, 64, 126},
 		.flags		= UART_CAP_FIFO | UART_CAP_AFE,
 	},
 	/*
@@ -1680,7 +1683,7 @@ static void serial8250_enable_ms(struct uart_port *port)
 	serial8250_rpm_put(up);
 }
 
-static void serial8250_read_char(struct uart_8250_port *up, unsigned char lsr)
+void serial8250_read_char(struct uart_8250_port *up, unsigned char lsr)
 {
 	struct uart_port *port = &up->port;
 	unsigned char ch;
@@ -1740,6 +1743,7 @@ static void serial8250_read_char(struct uart_8250_port *up, unsigned char lsr)
 
 	uart_insert_char(port, lsr, UART_LSR_OE, ch, flag);
 }
+EXPORT_SYMBOL_GPL(serial8250_read_char);
 
 /*
  * serial8250_rx_chars: processes according to the passed in LSR
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 0f058df0b070..df8bd0c7b97d 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -115,7 +115,6 @@ config SERIAL_SB1250_DUART_CONSOLE
 
 config SERIAL_ATMEL
 	bool "AT91 on-chip serial port support"
-	depends on HAS_DMA
 	depends on ARCH_AT91 || COMPILE_TEST
 	select SERIAL_CORE
 	select SERIAL_MCTRL_GPIO if GPIOLIB
@@ -500,7 +499,6 @@ config SERIAL_SA1100_CONSOLE
 
 config SERIAL_IMX
 	tristate "IMX serial port support"
-	depends on HAS_DMA
 	depends on ARCH_MXC || COMPILE_TEST
 	select SERIAL_CORE
 	select RATIONAL
@@ -676,6 +674,8 @@ config SERIAL_SH_SCI
 
 config SERIAL_SH_SCI_NR_UARTS
 	int "Maximum number of SCI(F) serial ports" if EXPERT
+	range 1 64 if 64BIT
+	range 1 32 if !64BIT
 	depends on SERIAL_SH_SCI
 	default "3" if H8300
 	default "10" if SUPERH
@@ -1262,7 +1262,6 @@ config SERIAL_PCH_UART_CONSOLE
 
 config SERIAL_MXS_AUART
 	tristate "MXS AUART support"
-	depends on HAS_DMA
 	depends on ARCH_MXS || MACH_ASM9260 || COMPILE_TEST
 	select SERIAL_CORE
 	select SERIAL_MCTRL_GPIO if GPIOLIB
@@ -1295,7 +1294,7 @@ config SERIAL_XILINX_PS_UART_CONSOLE
 
 config SERIAL_AR933X
 	tristate "AR933X serial port support"
-	depends on HAVE_CLK && SOC_AR933X
+	depends on HAVE_CLK && ATH79
 	select SERIAL_CORE
 	help
 	  If you have an Atheros AR933X SOC based board and want to use the
@@ -1473,7 +1472,6 @@ config SERIAL_SPRD_CONSOLE
 config SERIAL_STM32
 	tristate "STMicroelectronics STM32 serial port support"
 	select SERIAL_CORE
-	depends on HAS_DMA
 	depends on ARCH_STM32 || COMPILE_TEST
 	help
 	  This driver is for the on-chip Serial Controller on
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 4b40a5b449ee..ebd33c0232e6 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1727,10 +1727,26 @@ static int pl011_allocate_irq(struct uart_amba_port *uap)
  */
 static void pl011_enable_interrupts(struct uart_amba_port *uap)
 {
+	unsigned int i;
+
 	spin_lock_irq(&uap->port.lock);
 
 	/* Clear out any spuriously appearing RX interrupts */
 	pl011_write(UART011_RTIS | UART011_RXIS, uap, REG_ICR);
+
+	/*
+	 * RXIS is asserted only when the RX FIFO transitions from below
+	 * to above the trigger threshold.  If the RX FIFO is already
+	 * full to the threshold this can't happen and RXIS will now be
+	 * stuck off.  Drain the RX FIFO explicitly to fix this:
+	 */
+	for (i = 0; i < uap->fifosize * 2; ++i) {
+		if (pl011_read(uap, REG_FR) & UART01x_FR_RXFE)
+			break;
+
+		pl011_read(uap, REG_DR);
+	}
+
 	uap->im = UART011_RTIM;
 	if (!pl011_dma_rx_running(uap))
 		uap->im |= UART011_RXIM;
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index e287fe8f10fc..55b3eff148b1 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1757,7 +1757,6 @@ static int atmel_startup(struct uart_port *port)
 {
 	struct platform_device *pdev = to_platform_device(port->dev);
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
-	struct tty_struct *tty = port->state->port.tty;
 	int retval;
 
 	/*
@@ -1772,8 +1771,8 @@ static int atmel_startup(struct uart_port *port)
 	 * Allocate the IRQ
 	 */
 	retval = request_irq(port->irq, atmel_interrupt,
-			IRQF_SHARED | IRQF_COND_SUSPEND,
-			tty ? tty->name : "atmel_serial", port);
+			     IRQF_SHARED | IRQF_COND_SUSPEND,
+			     dev_name(&pdev->dev), port);
 	if (retval) {
 		dev_err(port->dev, "atmel_startup - Can't get irq\n");
 		return retval;
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
index a24278380fec..c14873b67803 100644
--- a/drivers/tty/serial/earlycon.c
+++ b/drivers/tty/serial/earlycon.c
@@ -169,7 +169,7 @@ static int __init register_earlycon(char *buf, const struct earlycon_id *match)
  */
 int __init setup_earlycon(char *buf)
 {
-	const struct earlycon_id *match;
+	const struct earlycon_id **p_match;
 
 	if (!buf || !buf[0])
 		return -EINVAL;
@@ -177,7 +177,9 @@ int __init setup_earlycon(char *buf)
 	if (early_con.flags & CON_ENABLED)
 		return -EALREADY;
 
-	for (match = __earlycon_table; match < __earlycon_table_end; match++) {
+	for (p_match = __earlycon_table; p_match < __earlycon_table_end;
+	     p_match++) {
+		const struct earlycon_id *match = *p_match;
 		size_t len = strlen(match->name);
 
 		if (strncmp(buf, match->name, len))
@@ -244,7 +246,6 @@ int __init of_setup_earlycon(const struct earlycon_id *match,
 		return -ENXIO;
 	}
 	port->mapbase = addr;
-	port->uartclk = BASE_BAUD * 16;
 
 	val = of_get_flat_dt_prop(node, "reg-offset", NULL);
 	if (val)
@@ -279,6 +280,10 @@ int __init of_setup_earlycon(const struct earlycon_id *match,
 	if (val)
 		early_console_dev.baud = be32_to_cpu(*val);
 
+	val = of_get_flat_dt_prop(node, "clock-frequency", NULL);
+	if (val)
+		port->uartclk = be32_to_cpu(*val);
+
 	if (options) {
 		early_console_dev.baud = simple_strtoul(options, NULL, 0);
 		strlcpy(early_console_dev.options, options,
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 91f3a1a5cb7f..4e853570ea80 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -316,7 +316,7 @@ static u32 imx_uart_readl(struct imx_port *sport, u32 offset)
 		 * differ from the value that was last written. As it only
 		 * clears after being set, reread conditionally.
 		 */
-		if (sport->ucr2 & UCR2_SRST)
+		if (!(sport->ucr2 & UCR2_SRST))
 			sport->ucr2 = readl(sport->port.membase + offset);
 		return sport->ucr2;
 		break;
@@ -1291,18 +1291,13 @@ static void imx_uart_enable_dma(struct imx_port *sport)
 
 static void imx_uart_disable_dma(struct imx_port *sport)
 {
-	u32 ucr1, ucr2;
+	u32 ucr1;
 
 	/* clear UCR1 */
 	ucr1 = imx_uart_readl(sport, UCR1);
 	ucr1 &= ~(UCR1_RXDMAEN | UCR1_TXDMAEN | UCR1_ATDMAEN);
 	imx_uart_writel(sport, ucr1, UCR1);
 
-	/* clear UCR2 */
-	ucr2 = imx_uart_readl(sport, UCR2);
-	ucr2 &= ~(UCR2_CTSC | UCR2_CTS | UCR2_ATEN);
-	imx_uart_writel(sport, ucr2, UCR2);
-
 	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
 
 	sport->dma_is_enabled = 0;
@@ -1427,13 +1422,21 @@ static void imx_uart_shutdown(struct uart_port *port)
 {
 	struct imx_port *sport = (struct imx_port *)port;
 	unsigned long flags;
-	u32 ucr1, ucr2;
+	u32 ucr1, ucr2, ucr4;
 
 	if (sport->dma_is_enabled) {
-		sport->dma_is_rxing = 0;
-		sport->dma_is_txing = 0;
 		dmaengine_terminate_sync(sport->dma_chan_tx);
+		if (sport->dma_is_txing) {
+			dma_unmap_sg(sport->port.dev, &sport->tx_sgl[0],
+				     sport->dma_tx_nents, DMA_TO_DEVICE);
+			sport->dma_is_txing = 0;
+		}
 		dmaengine_terminate_sync(sport->dma_chan_rx);
+		if (sport->dma_is_rxing) {
+			dma_unmap_sg(sport->port.dev, &sport->rx_sgl,
+				     1, DMA_FROM_DEVICE);
+			sport->dma_is_rxing = 0;
+		}
 
 		spin_lock_irqsave(&sport->port.lock, flags);
 		imx_uart_stop_tx(port);
@@ -1449,6 +1452,10 @@ static void imx_uart_shutdown(struct uart_port *port)
 	ucr2 = imx_uart_readl(sport, UCR2);
 	ucr2 &= ~(UCR2_TXEN | UCR2_ATEN);
 	imx_uart_writel(sport, ucr2, UCR2);
+
+	ucr4 = imx_uart_readl(sport, UCR4);
+	ucr4 &= ~UCR4_OREN;
+	imx_uart_writel(sport, ucr4, UCR4);
 	spin_unlock_irqrestore(&sport->port.lock, flags);
 
 	/*
@@ -1833,6 +1840,11 @@ static int imx_uart_rs485_config(struct uart_port *port,
 		rs485conf->flags &= ~SER_RS485_ENABLED;
 
 	if (rs485conf->flags & SER_RS485_ENABLED) {
+		/* Enable receiver if low-active RTS signal is requested */
+		if (sport->have_rtscts &&  !sport->have_rtsgpio &&
+		    !(rs485conf->flags & SER_RS485_RTS_ON_SEND))
+			rs485conf->flags |= SER_RS485_RX_DURING_TX;
+
 		/* disable transmitter */
 		ucr2 = imx_uart_readl(sport, UCR2);
 		if (rs485conf->flags & SER_RS485_RTS_AFTER_SEND)
@@ -2265,6 +2277,18 @@ static int imx_uart_probe(struct platform_device *pdev)
 	    (!sport->have_rtscts && !sport->have_rtsgpio))
 		dev_err(&pdev->dev, "no RTS control, disabling rs485\n");
 
+	/*
+	 * If using the i.MX UART RTS/CTS control then the RTS (CTS_B)
+	 * signal cannot be set low during transmission in case the
+	 * receiver is off (limitation of the i.MX UART IP).
+	 */
+	if (sport->port.rs485.flags & SER_RS485_ENABLED &&
+	    sport->have_rtscts && !sport->have_rtsgpio &&
+	    (!(sport->port.rs485.flags & SER_RS485_RTS_ON_SEND) &&
+	     !(sport->port.rs485.flags & SER_RS485_RX_DURING_TX)))
+		dev_err(&pdev->dev,
+			"low-active RTS not possible when receiver is off, enabling receiver\n");
+
 	imx_uart_rs485_config(&sport->port, &sport->port.rs485);
 
 	/* Disable interrupts before requesting them */
@@ -2408,8 +2432,7 @@ static void imx_uart_enable_wakeup(struct imx_port *sport, bool on)
 
 static int imx_uart_suspend_noirq(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct imx_port *sport = platform_get_drvdata(pdev);
+	struct imx_port *sport = dev_get_drvdata(dev);
 
 	imx_uart_save_context(sport);
 
@@ -2420,8 +2443,7 @@ static int imx_uart_suspend_noirq(struct device *dev)
 
 static int imx_uart_resume_noirq(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct imx_port *sport = platform_get_drvdata(pdev);
+	struct imx_port *sport = dev_get_drvdata(dev);
 	int ret;
 
 	ret = clk_enable(sport->clk_ipg);
@@ -2435,8 +2457,7 @@ static int imx_uart_resume_noirq(struct device *dev)
 
 static int imx_uart_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct imx_port *sport = platform_get_drvdata(pdev);
+	struct imx_port *sport = dev_get_drvdata(dev);
 	int ret;
 
 	uart_suspend_port(&imx_uart_uart_driver, &sport->port);
@@ -2454,8 +2475,7 @@ static int imx_uart_suspend(struct device *dev)
 
 static int imx_uart_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct imx_port *sport = platform_get_drvdata(pdev);
+	struct imx_port *sport = dev_get_drvdata(dev);
 
 	/* disable wakeup from i.MX UART */
 	imx_uart_enable_wakeup(sport, false);
@@ -2470,8 +2490,7 @@ static int imx_uart_resume(struct device *dev)
 
 static int imx_uart_freeze(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct imx_port *sport = platform_get_drvdata(pdev);
+	struct imx_port *sport = dev_get_drvdata(dev);
 
 	uart_suspend_port(&imx_uart_uart_driver, &sport->port);
 
@@ -2480,8 +2499,7 @@ static int imx_uart_freeze(struct device *dev)
 
 static int imx_uart_thaw(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct imx_port *sport = platform_get_drvdata(pdev);
+	struct imx_port *sport = dev_get_drvdata(dev);
 
 	uart_resume_port(&imx_uart_uart_driver, &sport->port);
 
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index ee96cf0d0057..736b74fd6623 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -1812,11 +1812,34 @@ static const struct of_device_id msm_match_table[] = {
 };
 MODULE_DEVICE_TABLE(of, msm_match_table);
 
+static int __maybe_unused msm_serial_suspend(struct device *dev)
+{
+	struct msm_port *port = dev_get_drvdata(dev);
+
+	uart_suspend_port(&msm_uart_driver, &port->uart);
+
+	return 0;
+}
+
+static int __maybe_unused msm_serial_resume(struct device *dev)
+{
+	struct msm_port *port = dev_get_drvdata(dev);
+
+	uart_resume_port(&msm_uart_driver, &port->uart);
+
+	return 0;
+}
+
+static const struct dev_pm_ops msm_serial_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(msm_serial_suspend, msm_serial_resume)
+};
+
 static struct platform_driver msm_platform_driver = {
 	.remove = msm_serial_remove,
 	.probe = msm_serial_probe,
 	.driver = {
 		.name = "msm_serial",
+		.pm = &msm_serial_dev_pm_ops,
 		.of_match_table = msm_match_table,
 	},
 };
diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c
index 750e5645dc85..d04b5eeea3c6 100644
--- a/drivers/tty/serial/mvebu-uart.c
+++ b/drivers/tty/serial/mvebu-uart.c
@@ -71,6 +71,8 @@
 #define UART_BRDV		0x10
 #define  BRDV_BAUD_MASK         0x3FF
 
+#define UART_OSAMP		0x14
+
 #define MVEBU_NR_UARTS		2
 
 #define MVEBU_UART_TYPE		"mvebu-uart"
@@ -108,6 +110,17 @@ struct mvebu_uart_driver_data {
 	struct uart_flags flags;
 };
 
+/* Saved registers during suspend */
+struct mvebu_uart_pm_regs {
+	unsigned int rbr;
+	unsigned int tsh;
+	unsigned int ctrl;
+	unsigned int intr;
+	unsigned int stat;
+	unsigned int brdv;
+	unsigned int osamp;
+};
+
 /* MVEBU UART driver structure */
 struct mvebu_uart {
 	struct uart_port *port;
@@ -115,6 +128,9 @@ struct mvebu_uart {
 	int irq[UART_IRQ_COUNT];
 	unsigned char __iomem *nb;
 	struct mvebu_uart_driver_data *data;
+#if defined(CONFIG_PM)
+	struct mvebu_uart_pm_regs pm_regs;
+#endif /* CONFIG_PM */
 };
 
 static struct mvebu_uart *to_mvuart(struct uart_port *port)
@@ -495,7 +511,6 @@ static void mvebu_uart_set_termios(struct uart_port *port,
 		termios->c_iflag |= old->c_iflag & ~(INPCK | IGNPAR);
 		termios->c_cflag &= CREAD | CBAUD;
 		termios->c_cflag |= old->c_cflag & ~(CREAD | CBAUD);
-		termios->c_lflag = old->c_lflag;
 	}
 
 	spin_unlock_irqrestore(&port->lock, flags);
@@ -719,6 +734,51 @@ static struct uart_driver mvebu_uart_driver = {
 #endif
 };
 
+#if defined(CONFIG_PM)
+static int mvebu_uart_suspend(struct device *dev)
+{
+	struct mvebu_uart *mvuart = dev_get_drvdata(dev);
+	struct uart_port *port = mvuart->port;
+
+	uart_suspend_port(&mvebu_uart_driver, port);
+
+	mvuart->pm_regs.rbr = readl(port->membase + UART_RBR(port));
+	mvuart->pm_regs.tsh = readl(port->membase + UART_TSH(port));
+	mvuart->pm_regs.ctrl = readl(port->membase + UART_CTRL(port));
+	mvuart->pm_regs.intr = readl(port->membase + UART_INTR(port));
+	mvuart->pm_regs.stat = readl(port->membase + UART_STAT);
+	mvuart->pm_regs.brdv = readl(port->membase + UART_BRDV);
+	mvuart->pm_regs.osamp = readl(port->membase + UART_OSAMP);
+
+	device_set_wakeup_enable(dev, true);
+
+	return 0;
+}
+
+static int mvebu_uart_resume(struct device *dev)
+{
+	struct mvebu_uart *mvuart = dev_get_drvdata(dev);
+	struct uart_port *port = mvuart->port;
+
+	writel(mvuart->pm_regs.rbr, port->membase + UART_RBR(port));
+	writel(mvuart->pm_regs.tsh, port->membase + UART_TSH(port));
+	writel(mvuart->pm_regs.ctrl, port->membase + UART_CTRL(port));
+	writel(mvuart->pm_regs.intr, port->membase + UART_INTR(port));
+	writel(mvuart->pm_regs.stat, port->membase + UART_STAT);
+	writel(mvuart->pm_regs.brdv, port->membase + UART_BRDV);
+	writel(mvuart->pm_regs.osamp, port->membase + UART_OSAMP);
+
+	uart_resume_port(&mvebu_uart_driver, port);
+
+	return 0;
+}
+
+static const struct dev_pm_ops mvebu_uart_pm_ops = {
+	.suspend        = mvebu_uart_suspend,
+	.resume         = mvebu_uart_resume,
+};
+#endif /* CONFIG_PM */
+
 static const struct of_device_id mvebu_uart_of_match[];
 
 /* Counter to keep track of each UART port id when not using CONFIG_OF */
@@ -892,6 +952,9 @@ static struct platform_driver mvebu_uart_platform_driver = {
 		.name  = "mvebu-uart",
 		.of_match_table = of_match_ptr(mvebu_uart_of_match),
 		.suppress_bind_attrs = true,
+#if defined(CONFIG_PM)
+		.pm	= &mvebu_uart_pm_ops,
+#endif /* CONFIG_PM */
 	},
 };
 
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 65ff669373d4..c62e17c85f57 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -98,14 +98,13 @@ struct qcom_geni_serial_port {
 	enum geni_se_xfer_mode xfer_mode;
 	bool setup;
 	int (*handle_rx)(struct uart_port *uport, u32 bytes, bool drop);
-	unsigned int xmit_size;
 	unsigned int baud;
 	unsigned int tx_bytes_pw;
 	unsigned int rx_bytes_pw;
 	bool brk;
 };
 
-static const struct uart_ops qcom_geni_serial_pops;
+static const struct uart_ops qcom_geni_console_pops;
 static struct uart_driver qcom_geni_console_driver;
 static int handle_rx_console(struct uart_port *uport, u32 bytes, bool drop);
 static unsigned int qcom_geni_serial_tx_empty(struct uart_port *port);
@@ -118,7 +117,14 @@ static const unsigned long root_freq[] = {7372800, 14745600, 19200000, 29491200,
 #define to_dev_port(ptr, member) \
 		container_of(ptr, struct qcom_geni_serial_port, member)
 
-static struct qcom_geni_serial_port qcom_geni_console_port;
+static struct qcom_geni_serial_port qcom_geni_console_port = {
+	.uport = {
+		.iotype = UPIO_MEM,
+		.ops = &qcom_geni_console_pops,
+		.flags = UPF_BOOT_AUTOCONF,
+		.line = 0,
+	},
+};
 
 static int qcom_geni_serial_request_port(struct uart_port *uport)
 {
@@ -189,8 +195,19 @@ static bool qcom_geni_serial_poll_bit(struct uart_port *uport,
 		timeout_us = ((fifo_bits * USEC_PER_SEC) / baud) + 500;
 	}
 
-	return !readl_poll_timeout_atomic(uport->membase + offset, reg,
-			 (bool)(reg & field) == set, 10, timeout_us);
+	/*
+	 * Use custom implementation instead of readl_poll_atomic since ktimer
+	 * is not ready at the time of early console.
+	 */
+	timeout_us = DIV_ROUND_UP(timeout_us, 10) * 10;
+	while (timeout_us) {
+		reg = readl_relaxed(uport->membase + offset);
+		if ((bool)(reg & field) == set)
+			return true;
+		udelay(10);
+		timeout_us -= 10;
+	}
+	return false;
 }
 
 static void qcom_geni_serial_setup_tx(struct uart_port *uport, u32 xmit_size)
@@ -286,6 +303,10 @@ __qcom_geni_serial_console_write(struct uart_port *uport, const char *s,
 	u32 bytes_to_send = count;
 
 	for (i = 0; i < count; i++) {
+		/*
+		 * uart_console_write() adds a carriage return for each newline.
+		 * Account for additional bytes to be written.
+		 */
 		if (s[i] == '\n')
 			bytes_to_send++;
 	}
@@ -305,7 +326,7 @@ __qcom_geni_serial_console_write(struct uart_port *uport, const char *s,
 		if (!qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS,
 						M_TX_FIFO_WATERMARK_EN, true))
 			break;
-		chars_to_write = min_t(size_t, (size_t)(count - i), avail / 2);
+		chars_to_write = min_t(size_t, count - i, avail / 2);
 		uart_console_write(uport, s + i, chars_to_write,
 						qcom_geni_serial_wr_char);
 		writel_relaxed(M_TX_FIFO_WATERMARK_EN, uport->membase +
@@ -406,20 +427,18 @@ static void qcom_geni_serial_start_tx(struct uart_port *uport)
 	u32 status;
 
 	if (port->xfer_mode == GENI_SE_FIFO) {
-		status = readl_relaxed(uport->membase + SE_GENI_STATUS);
+		/*
+		 * readl ensures reading & writing of IRQ_EN register
+		 * is not re-ordered before checking the status of the
+		 * Serial Engine.
+		 */
+		status = readl(uport->membase + SE_GENI_STATUS);
 		if (status & M_GENI_CMD_ACTIVE)
 			return;
 
 		if (!qcom_geni_serial_tx_empty(uport))
 			return;
 
-		/*
-		 * Ensure writing to IRQ_EN & watermark registers are not
-		 * re-ordered before checking the status of the Serial
-		 * Engine and TX FIFO
-		 */
-		mb();
-
 		irq_en = readl_relaxed(uport->membase +	SE_GENI_M_IRQ_EN);
 		irq_en |= M_TX_FIFO_WATERMARK_EN | M_CMD_DONE_EN;
 
@@ -442,7 +461,6 @@ static void qcom_geni_serial_stop_tx(struct uart_port *uport)
 		writel_relaxed(0, uport->membase +
 				     SE_GENI_TX_WATERMARK_REG);
 	}
-	port->xmit_size = 0;
 	writel_relaxed(irq_en, uport->membase + SE_GENI_M_IRQ_EN);
 	status = readl_relaxed(uport->membase + SE_GENI_STATUS);
 	/* Possible stop tx is called multiple times. */
@@ -572,21 +590,14 @@ static void qcom_geni_serial_handle_tx(struct uart_port *uport)
 	chunk = uart_circ_chars_pending(xmit);
 	status = readl_relaxed(uport->membase + SE_GENI_TX_FIFO_STATUS);
 	/* Both FIFO and framework buffer are drained */
-	if (chunk == port->xmit_size && !status) {
-		port->xmit_size = 0;
-		uart_circ_clear(xmit);
+	if (!chunk && !status) {
 		qcom_geni_serial_stop_tx(uport);
 		goto out_write_wakeup;
 	}
-	chunk -= port->xmit_size;
 
 	avail = (port->tx_fifo_depth - port->tx_wm) * port->tx_bytes_pw;
-	tail = (xmit->tail + port->xmit_size) & (UART_XMIT_SIZE - 1);
-	if (chunk > (UART_XMIT_SIZE - tail))
-		chunk = UART_XMIT_SIZE - tail;
-	if (chunk > avail)
-		chunk = avail;
-
+	tail = xmit->tail;
+	chunk = min3((size_t)chunk, (size_t)(UART_XMIT_SIZE - tail), avail);
 	if (!chunk)
 		goto out_write_wakeup;
 
@@ -595,24 +606,27 @@ static void qcom_geni_serial_handle_tx(struct uart_port *uport)
 	remaining = chunk;
 	for (i = 0; i < chunk; ) {
 		unsigned int tx_bytes;
-		unsigned int buf = 0;
+		u8 buf[sizeof(u32)];
 		int c;
 
-		tx_bytes = min_t(size_t, remaining, (size_t)port->tx_bytes_pw);
+		memset(buf, 0, ARRAY_SIZE(buf));
+		tx_bytes = min_t(size_t, remaining, port->tx_bytes_pw);
 		for (c = 0; c < tx_bytes ; c++)
-			buf |= (xmit->buf[tail + c] << (c * BITS_PER_BYTE));
+			buf[c] = xmit->buf[tail + c];
 
-		writel_relaxed(buf, uport->membase + SE_GENI_TX_FIFOn);
+		iowrite32_rep(uport->membase + SE_GENI_TX_FIFOn, buf, 1);
 
 		i += tx_bytes;
-		tail = (tail + tx_bytes) & (UART_XMIT_SIZE - 1);
+		tail += tx_bytes;
 		uport->icount.tx += tx_bytes;
 		remaining -= tx_bytes;
 	}
+
+	xmit->tail = tail & (UART_XMIT_SIZE - 1);
 	qcom_geni_serial_poll_tx_done(uport);
-	port->xmit_size += chunk;
 out_write_wakeup:
-	uart_write_wakeup(uport);
+	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+		uart_write_wakeup(uport);
 }
 
 static irqreturn_t qcom_geni_serial_isr(int isr, void *dev)
@@ -627,7 +641,7 @@ static irqreturn_t qcom_geni_serial_isr(int isr, void *dev)
 	struct qcom_geni_serial_port *port = to_dev_port(uport, uport);
 
 	if (uport->suspended)
-		return IRQ_HANDLED;
+		return IRQ_NONE;
 
 	spin_lock_irqsave(&uport->lock, flags);
 	m_irq_status = readl_relaxed(uport->membase + SE_GENI_M_IRQ_STATUS);
@@ -667,20 +681,16 @@ out_unlock:
 	return IRQ_HANDLED;
 }
 
-static int get_tx_fifo_size(struct qcom_geni_serial_port *port)
+static void get_tx_fifo_size(struct qcom_geni_serial_port *port)
 {
 	struct uart_port *uport;
 
-	if (!port)
-		return -ENODEV;
-
 	uport = &port->uport;
 	port->tx_fifo_depth = geni_se_get_tx_fifo_depth(&port->se);
 	port->tx_fifo_width = geni_se_get_tx_fifo_width(&port->se);
 	port->rx_fifo_depth = geni_se_get_rx_fifo_depth(&port->se);
 	uport->fifosize =
 		(port->tx_fifo_depth * port->tx_fifo_width) / BITS_PER_BYTE;
-	return 0;
 }
 
 static void set_rfr_wm(struct qcom_geni_serial_port *port)
@@ -702,7 +712,6 @@ static void qcom_geni_serial_shutdown(struct uart_port *uport)
 	/* Stop the console before stopping the current tx */
 	console_stop(uport->cons);
 
-	disable_irq(uport->irq);
 	free_irq(uport->irq, uport);
 	spin_lock_irqsave(&uport->lock, flags);
 	qcom_geni_serial_stop_tx(uport);
@@ -892,7 +901,7 @@ out_restart_rx:
 
 static unsigned int qcom_geni_serial_tx_empty(struct uart_port *uport)
 {
-	return !readl_relaxed(uport->membase + SE_GENI_TX_FIFO_STATUS);
+	return !readl(uport->membase + SE_GENI_TX_FIFO_STATUS);
 }
 
 #ifdef CONFIG_SERIAL_QCOM_GENI_CONSOLE
@@ -910,7 +919,7 @@ static int __init qcom_geni_console_setup(struct console *co, char *options)
 
 	port = get_port_from_line(co->index);
 	if (IS_ERR(port)) {
-		pr_err("Invalid line %d(%d)\n", co->index, (int)PTR_ERR(port));
+		pr_err("Invalid line %d\n", co->index);
 		return PTR_ERR(port);
 	}
 
@@ -942,6 +951,65 @@ static int __init qcom_geni_console_setup(struct console *co, char *options)
 	return uart_set_options(uport, co, baud, parity, bits, flow);
 }
 
+static void qcom_geni_serial_earlycon_write(struct console *con,
+					const char *s, unsigned int n)
+{
+	struct earlycon_device *dev = con->data;
+
+	__qcom_geni_serial_console_write(&dev->port, s, n);
+}
+
+static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev,
+								const char *opt)
+{
+	struct uart_port *uport = &dev->port;
+	u32 tx_trans_cfg;
+	u32 tx_parity_cfg = 0;	/* Disable Tx Parity */
+	u32 rx_trans_cfg = 0;
+	u32 rx_parity_cfg = 0;	/* Disable Rx Parity */
+	u32 stop_bit_len = 0;	/* Default stop bit length - 1 bit */
+	u32 bits_per_char;
+	struct geni_se se;
+
+	if (!uport->membase)
+		return -EINVAL;
+
+	memset(&se, 0, sizeof(se));
+	se.base = uport->membase;
+	if (geni_se_read_proto(&se) != GENI_SE_UART)
+		return -ENXIO;
+	/*
+	 * Ignore Flow control.
+	 * n = 8.
+	 */
+	tx_trans_cfg = UART_CTS_MASK;
+	bits_per_char = BITS_PER_BYTE;
+
+	/*
+	 * Make an unconditional cancel on the main sequencer to reset
+	 * it else we could end up in data loss scenarios.
+	 */
+	qcom_geni_serial_poll_tx_done(uport);
+	qcom_geni_serial_abort_rx(uport);
+	geni_se_config_packing(&se, BITS_PER_BYTE, 1, false, true, false);
+	geni_se_init(&se, DEF_FIFO_DEPTH_WORDS / 2, DEF_FIFO_DEPTH_WORDS - 2);
+	geni_se_select_mode(&se, GENI_SE_FIFO);
+
+	writel_relaxed(tx_trans_cfg, uport->membase + SE_UART_TX_TRANS_CFG);
+	writel_relaxed(tx_parity_cfg, uport->membase + SE_UART_TX_PARITY_CFG);
+	writel_relaxed(rx_trans_cfg, uport->membase + SE_UART_RX_TRANS_CFG);
+	writel_relaxed(rx_parity_cfg, uport->membase + SE_UART_RX_PARITY_CFG);
+	writel_relaxed(bits_per_char, uport->membase + SE_UART_TX_WORD_LEN);
+	writel_relaxed(bits_per_char, uport->membase + SE_UART_RX_WORD_LEN);
+	writel_relaxed(stop_bit_len, uport->membase + SE_UART_TX_STOP_BIT_LEN);
+
+	dev->con->write = qcom_geni_serial_earlycon_write;
+	dev->con->setup = NULL;
+	return 0;
+}
+OF_EARLYCON_DECLARE(qcom_geni, "qcom,geni-debug-uart",
+				qcom_geni_serial_earlycon_setup);
+
 static int __init console_register(struct uart_driver *drv)
 {
 	return uart_register_driver(drv);
@@ -1022,19 +1090,17 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 	struct qcom_geni_serial_port *port;
 	struct uart_port *uport;
 	struct resource *res;
+	int irq;
 
 	if (pdev->dev.of_node)
 		line = of_alias_get_id(pdev->dev.of_node, "serial");
-	else
-		line = pdev->id;
 
 	if (line < 0 || line >= GENI_UART_CONS_PORTS)
 		return -ENXIO;
 	port = get_port_from_line(line);
 	if (IS_ERR(port)) {
-		ret = PTR_ERR(port);
-		dev_err(&pdev->dev, "Invalid line %d(%d)\n", line, ret);
-		return ret;
+		dev_err(&pdev->dev, "Invalid line %d\n", line);
+		return PTR_ERR(port);
 	}
 
 	uport = &port->uport;
@@ -1061,16 +1127,16 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
 	port->rx_fifo_depth = DEF_FIFO_DEPTH_WORDS;
 	port->tx_fifo_width = DEF_FIFO_WIDTH_BITS;
 
-	uport->irq = platform_get_irq(pdev, 0);
-	if (uport->irq < 0) {
-		dev_err(&pdev->dev, "Failed to get IRQ %d\n", uport->irq);
-		return uport->irq;
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "Failed to get IRQ %d\n", irq);
+		return irq;
 	}
+	uport->irq = irq;
 
 	uport->private_data = &qcom_geni_console_driver;
 	platform_set_drvdata(pdev, port);
 	port->handle_rx = handle_rx_console;
-	port->setup = false;
 	return uart_add_one_port(&qcom_geni_console_driver, uport);
 }
 
@@ -1085,8 +1151,7 @@ static int qcom_geni_serial_remove(struct platform_device *pdev)
 
 static int __maybe_unused qcom_geni_serial_sys_suspend_noirq(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct qcom_geni_serial_port *port = platform_get_drvdata(pdev);
+	struct qcom_geni_serial_port *port = dev_get_drvdata(dev);
 	struct uart_port *uport = &port->uport;
 
 	uart_suspend_port(uport->private_data, uport);
@@ -1095,12 +1160,19 @@ static int __maybe_unused qcom_geni_serial_sys_suspend_noirq(struct device *dev)
 
 static int __maybe_unused qcom_geni_serial_sys_resume_noirq(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct qcom_geni_serial_port *port = platform_get_drvdata(pdev);
+	struct qcom_geni_serial_port *port = dev_get_drvdata(dev);
 	struct uart_port *uport = &port->uport;
 
 	if (console_suspend_enabled && uport->suspended) {
 		uart_resume_port(uport->private_data, uport);
+		/*
+		 * uart_suspend_port() invokes port shutdown which in turn
+		 * frees the irq. uart_resume_port invokes port startup which
+		 * performs request_irq. The request_irq auto-enables the IRQ.
+		 * In addition, resume_noirq implicitly enables the IRQ and
+		 * leads to an unbalanced IRQ enable warning. Disable the IRQ
+		 * before returning so that the warning is suppressed.
+		 */
 		disable_irq(uport->irq);
 	}
 	return 0;
@@ -1131,11 +1203,6 @@ static int __init qcom_geni_serial_init(void)
 {
 	int ret;
 
-	qcom_geni_console_port.uport.iotype = UPIO_MEM;
-	qcom_geni_console_port.uport.ops = &qcom_geni_console_pops;
-	qcom_geni_console_port.uport.flags = UPF_BOOT_AUTOCONF;
-	qcom_geni_console_port.uport.line = 0;
-
 	ret = console_register(&qcom_geni_console_driver);
 	if (ret)
 		return ret;
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index 3f2f8c118ce0..2f8fa184aafa 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -856,35 +856,54 @@ static void s3c24xx_serial_break_ctl(struct uart_port *port, int break_state)
 static int s3c24xx_serial_request_dma(struct s3c24xx_uart_port *p)
 {
 	struct s3c24xx_uart_dma	*dma = p->dma;
+	struct dma_slave_caps dma_caps;
+	const char *reason = NULL;
 	int ret;
 
 	/* Default slave configuration parameters */
 	dma->rx_conf.direction		= DMA_DEV_TO_MEM;
 	dma->rx_conf.src_addr_width	= DMA_SLAVE_BUSWIDTH_1_BYTE;
 	dma->rx_conf.src_addr		= p->port.mapbase + S3C2410_URXH;
-	dma->rx_conf.src_maxburst	= 16;
+	dma->rx_conf.src_maxburst	= 1;
 
 	dma->tx_conf.direction		= DMA_MEM_TO_DEV;
 	dma->tx_conf.dst_addr_width	= DMA_SLAVE_BUSWIDTH_1_BYTE;
 	dma->tx_conf.dst_addr		= p->port.mapbase + S3C2410_UTXH;
-	if (dma_get_cache_alignment() >= 16)
-		dma->tx_conf.dst_maxburst = 16;
-	else
-		dma->tx_conf.dst_maxburst = 1;
+	dma->tx_conf.dst_maxburst	= 1;
 
 	dma->rx_chan = dma_request_chan(p->port.dev, "rx");
 
-	if (IS_ERR(dma->rx_chan))
-		return PTR_ERR(dma->rx_chan);
+	if (IS_ERR(dma->rx_chan)) {
+		reason = "DMA RX channel request failed";
+		ret = PTR_ERR(dma->rx_chan);
+		goto err_warn;
+	}
+
+	ret = dma_get_slave_caps(dma->rx_chan, &dma_caps);
+	if (ret < 0 ||
+	    dma_caps.residue_granularity < DMA_RESIDUE_GRANULARITY_BURST) {
+		reason = "insufficient DMA RX engine capabilities";
+		ret = -EOPNOTSUPP;
+		goto err_release_rx;
+	}
 
 	dmaengine_slave_config(dma->rx_chan, &dma->rx_conf);
 
 	dma->tx_chan = dma_request_chan(p->port.dev, "tx");
 	if (IS_ERR(dma->tx_chan)) {
+		reason = "DMA TX channel request failed";
 		ret = PTR_ERR(dma->tx_chan);
 		goto err_release_rx;
 	}
 
+	ret = dma_get_slave_caps(dma->tx_chan, &dma_caps);
+	if (ret < 0 ||
+	    dma_caps.residue_granularity < DMA_RESIDUE_GRANULARITY_BURST) {
+		reason = "insufficient DMA TX engine capabilities";
+		ret = -EOPNOTSUPP;
+		goto err_release_tx;
+	}
+
 	dmaengine_slave_config(dma->tx_chan, &dma->tx_conf);
 
 	/* RX buffer */
@@ -899,6 +918,7 @@ static int s3c24xx_serial_request_dma(struct s3c24xx_uart_port *p)
 	dma->rx_addr = dma_map_single(p->port.dev, dma->rx_buf,
 				dma->rx_size, DMA_FROM_DEVICE);
 	if (dma_mapping_error(p->port.dev, dma->rx_addr)) {
+		reason = "DMA mapping error for RX buffer";
 		ret = -EIO;
 		goto err_free_rx;
 	}
@@ -907,6 +927,7 @@ static int s3c24xx_serial_request_dma(struct s3c24xx_uart_port *p)
 	dma->tx_addr = dma_map_single(p->port.dev, p->port.state->xmit.buf,
 				UART_XMIT_SIZE, DMA_TO_DEVICE);
 	if (dma_mapping_error(p->port.dev, dma->tx_addr)) {
+		reason = "DMA mapping error for TX buffer";
 		ret = -EIO;
 		goto err_unmap_rx;
 	}
@@ -922,6 +943,9 @@ err_release_tx:
 	dma_release_channel(dma->tx_chan);
 err_release_rx:
 	dma_release_channel(dma->rx_chan);
+err_warn:
+	if (reason)
+		dev_warn(p->port.dev, "%s, DMA will not be used\n", reason);
 	return ret;
 }
 
@@ -1040,8 +1064,6 @@ static int s3c64xx_serial_startup(struct uart_port *port)
 	if (ourport->dma) {
 		ret = s3c24xx_serial_request_dma(ourport);
 		if (ret < 0) {
-			dev_warn(port->dev,
-				 "DMA request failed, DMA will not be used\n");
 			devm_kfree(port->dev, ourport->dma);
 			ourport->dma = NULL;
 		}
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 65792a3539d0..243c96025053 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1168,7 +1168,10 @@ static int sc16is7xx_probe(struct device *dev,
 		else
 			return PTR_ERR(s->clk);
 	} else {
-		clk_prepare_enable(s->clk);
+		ret = clk_prepare_enable(s->clk);
+		if (ret)
+			return ret;
+
 		freq = clk_get_rate(s->clk);
 	}
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 0466f9f08a91..890b8832aff2 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -674,8 +674,8 @@ static void uart_send_xchar(struct tty_struct *tty, char ch)
 static void uart_throttle(struct tty_struct *tty)
 {
 	struct uart_state *state = tty->driver_data;
+	upstat_t mask = UPSTAT_SYNC_FIFO;
 	struct uart_port *port;
-	upstat_t mask = 0;
 
 	port = uart_port_ref(state);
 	if (!port)
@@ -703,8 +703,8 @@ static void uart_throttle(struct tty_struct *tty)
 static void uart_unthrottle(struct tty_struct *tty)
 {
 	struct uart_state *state = tty->driver_data;
+	upstat_t mask = UPSTAT_SYNC_FIFO;
 	struct uart_port *port;
-	upstat_t mask = 0;
 
 	port = uart_port_ref(state);
 	if (!port)
@@ -1829,19 +1829,6 @@ static int uart_proc_show(struct seq_file *m, void *v)
 		uart_line_info(m, drv, i);
 	return 0;
 }
-
-static int uart_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, uart_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations uart_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= uart_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 #if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(CONFIG_CONSOLE_POLL)
@@ -2415,7 +2402,7 @@ static const struct tty_operations uart_ops = {
 	.break_ctl	= uart_break_ctl,
 	.wait_until_sent= uart_wait_until_sent,
 #ifdef CONFIG_PROC_FS
-	.proc_fops	= &uart_proc_fops,
+	.proc_show	= uart_proc_show,
 #endif
 	.tiocmget	= uart_tiocmget,
 	.tiocmset	= uart_tiocmset,
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index fdbbff547106..c181eb37f985 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -160,6 +160,7 @@ struct sci_port {
 #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS
 
 static struct sci_port sci_ports[SCI_NPORTS];
+static unsigned long sci_ports_in_use;
 static struct uart_driver sci_uart_driver;
 
 static inline struct sci_port *
@@ -2390,6 +2391,27 @@ done:
 
 	uart_update_timeout(port, termios->c_cflag, baud);
 
+	/* byte size and parity */
+	switch (termios->c_cflag & CSIZE) {
+	case CS5:
+		bits = 7;
+		break;
+	case CS6:
+		bits = 8;
+		break;
+	case CS7:
+		bits = 9;
+		break;
+	default:
+		bits = 10;
+		break;
+	}
+
+	if (termios->c_cflag & CSTOPB)
+		bits++;
+	if (termios->c_cflag & PARENB)
+		bits++;
+
 	if (best_clk >= 0) {
 		if (port->type == PORT_SCIFA || port->type == PORT_SCIFB)
 			switch (srr + 1) {
@@ -2406,8 +2428,27 @@ done:
 		serial_port_out(port, SCSCR, scr_val | s->hscif_tot);
 		serial_port_out(port, SCSMR, smr_val);
 		serial_port_out(port, SCBRR, brr);
-		if (sci_getreg(port, HSSRR)->size)
-			serial_port_out(port, HSSRR, srr | HSCIF_SRE);
+		if (sci_getreg(port, HSSRR)->size) {
+			unsigned int hssrr = srr | HSCIF_SRE;
+			/* Calculate deviation from intended rate at the
+			 * center of the last stop bit in sampling clocks.
+			 */
+			int last_stop = bits * 2 - 1;
+			int deviation = min_err * srr * last_stop / 2 / baud;
+
+			if (abs(deviation) >= 2) {
+				/* At least two sampling clocks off at the
+				 * last stop bit; we can increase the error
+				 * margin by shifting the sampling point.
+				 */
+				int shift = min(-8, max(7, deviation / 2));
+
+				hssrr |= (shift << HSCIF_SRHP_SHIFT) &
+					 HSCIF_SRHP_MASK;
+				hssrr |= HSCIF_SRDE;
+			}
+			serial_port_out(port, HSSRR, hssrr);
+		}
 
 		/* Wait one bit interval */
 		udelay((1000000 + (baud - 1)) / baud);
@@ -2474,27 +2515,6 @@ done:
 	 * value obtained by this formula is too small. Therefore, if the value
 	 * is smaller than 20ms, use 20ms as the timeout value for DMA.
 	 */
-	/* byte size and parity */
-	switch (termios->c_cflag & CSIZE) {
-	case CS5:
-		bits = 7;
-		break;
-	case CS6:
-		bits = 8;
-		break;
-	case CS7:
-		bits = 9;
-		break;
-	default:
-		bits = 10;
-		break;
-	}
-
-	if (termios->c_cflag & CSTOPB)
-		bits++;
-	if (termios->c_cflag & PARENB)
-		bits++;
-
 	s->rx_frame = (10000 * bits) / (baud / 100);
 #ifdef CONFIG_SERIAL_SH_SCI_DMA
 	s->rx_timeout = s->buf_len_rx * 2 * s->rx_frame;
@@ -2704,8 +2724,8 @@ found:
 			dev_dbg(dev, "failed to get %s (%ld)\n", clk_names[i],
 				PTR_ERR(clk));
 		else
-			dev_dbg(dev, "clk %s is %pC rate %pCr\n", clk_names[i],
-				clk, clk);
+			dev_dbg(dev, "clk %s is %pC rate %lu\n", clk_names[i],
+				clk, clk_get_rate(clk));
 		sci_port->clks[i] = IS_ERR(clk) ? NULL : clk;
 	}
 	return 0;
@@ -2890,16 +2910,15 @@ static void serial_console_write(struct console *co, const char *s,
 	unsigned long flags;
 	int locked = 1;
 
-	local_irq_save(flags);
 #if defined(SUPPORT_SYSRQ)
 	if (port->sysrq)
 		locked = 0;
 	else
 #endif
 	if (oops_in_progress)
-		locked = spin_trylock(&port->lock);
+		locked = spin_trylock_irqsave(&port->lock, flags);
 	else
-		spin_lock(&port->lock);
+		spin_lock_irqsave(&port->lock, flags);
 
 	/* first save SCSCR then disable interrupts, keep clock source */
 	ctrl = serial_port_in(port, SCSCR);
@@ -2919,8 +2938,7 @@ static void serial_console_write(struct console *co, const char *s,
 	serial_port_out(port, SCSCR, ctrl);
 
 	if (locked)
-		spin_unlock(&port->lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&port->lock, flags);
 }
 
 static int serial_console_setup(struct console *co, char *options)
@@ -3026,6 +3044,7 @@ static int sci_remove(struct platform_device *dev)
 {
 	struct sci_port *port = platform_get_drvdata(dev);
 
+	sci_ports_in_use &= ~BIT(port->port.line);
 	uart_remove_one_port(&sci_uart_driver, &port->port);
 
 	sci_cleanup_single(port);
@@ -3107,6 +3126,8 @@ static struct plat_sci_port *sci_parse_dt(struct platform_device *pdev,
 
 	/* Get the line number from the aliases node. */
 	id = of_alias_get_id(np, "serial");
+	if (id < 0 && ~sci_ports_in_use)
+		id = ffz(sci_ports_in_use);
 	if (id < 0) {
 		dev_err(&pdev->dev, "failed to get alias id (%d)\n", id);
 		return NULL;
@@ -3141,6 +3162,9 @@ static int sci_probe_single(struct platform_device *dev,
 		dev_notice(&dev->dev, "Consider bumping CONFIG_SERIAL_SH_SCI_NR_UARTS!\n");
 		return -EINVAL;
 	}
+	BUILD_BUG_ON(SCI_NPORTS > sizeof(sci_ports_in_use) * 8);
+	if (sci_ports_in_use & BIT(index))
+		return -EBUSY;
 
 	mutex_lock(&sci_uart_registration_lock);
 	if (!sci_uart_driver.state) {
@@ -3239,6 +3263,7 @@ static int sci_probe(struct platform_device *dev)
 	sh_bios_gdb_detach();
 #endif
 
+	sci_ports_in_use |= BIT(dev_id);
 	return 0;
 }
 
diff --git a/drivers/tty/serial/sh-sci.h b/drivers/tty/serial/sh-sci.h
index a5f792fd48d9..0b9e804e61a9 100644
--- a/drivers/tty/serial/sh-sci.h
+++ b/drivers/tty/serial/sh-sci.h
@@ -130,6 +130,10 @@ enum {
 
 /* HSSRR HSCIF */
 #define HSCIF_SRE	BIT(15)	/* Sampling Rate Register Enable */
+#define HSCIF_SRDE	BIT(14) /* Sampling Point Register Enable */
+
+#define HSCIF_SRHP_SHIFT	8
+#define HSCIF_SRHP_MASK		0x0f00
 
 /* SCPCR (Serial Port Control Register), SCIFA/SCIFB only */
 #define SCPCR_RTSC	BIT(4)	/* Serial Port RTS# Pin / Output Pin */
diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c
index 5f9f01fac6dd..7971997cdead 100644
--- a/drivers/tty/serial/st-asc.c
+++ b/drivers/tty/serial/st-asc.c
@@ -842,16 +842,14 @@ static int asc_serial_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int asc_serial_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct uart_port *port = platform_get_drvdata(pdev);
+	struct uart_port *port = dev_get_drvdata(dev);
 
 	return uart_suspend_port(&asc_uart_driver, port);
 }
 
 static int asc_serial_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct uart_port *port = platform_get_drvdata(pdev);
+	struct uart_port *port = dev_get_drvdata(dev);
 
 	return uart_resume_port(&asc_uart_driver, port);
 }
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index abcb4d09a2d8..8a3e34234e98 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1097,45 +1097,6 @@ static const struct uart_ops cdns_uart_ops = {
 #endif
 };
 
-static struct uart_port cdns_uart_port[CDNS_UART_NR_PORTS];
-
-/**
- * cdns_uart_get_port - Configure the port from platform device resource info
- * @id: Port id
- *
- * Return: a pointer to a uart_port or NULL for failure
- */
-static struct uart_port *cdns_uart_get_port(int id)
-{
-	struct uart_port *port;
-
-	/* Try the given port id if failed use default method */
-	if (id < CDNS_UART_NR_PORTS && cdns_uart_port[id].mapbase != 0) {
-		/* Find the next unused port */
-		for (id = 0; id < CDNS_UART_NR_PORTS; id++)
-			if (cdns_uart_port[id].mapbase == 0)
-				break;
-	}
-
-	if (id >= CDNS_UART_NR_PORTS)
-		return NULL;
-
-	port = &cdns_uart_port[id];
-
-	/* At this point, we've got an empty uart_port struct, initialize it */
-	spin_lock_init(&port->lock);
-	port->membase	= NULL;
-	port->irq	= 0;
-	port->type	= PORT_UNKNOWN;
-	port->iotype	= UPIO_MEM32;
-	port->flags	= UPF_BOOT_AUTOCONF;
-	port->ops	= &cdns_uart_ops;
-	port->fifosize	= CDNS_UART_FIFO_SIZE;
-	port->line	= id;
-	port->dev	= NULL;
-	return port;
-}
-
 #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
 /**
  * cdns_uart_console_wait_tx - Wait for the TX to be full
@@ -1181,7 +1142,7 @@ static int __init cdns_early_console_setup(struct earlycon_device *device,
 	/* only set baud if specified on command line - otherwise
 	 * assume it has been initialized by a boot loader.
 	 */
-	if (device->baud) {
+	if (port->uartclk && device->baud) {
 		u32 cd = 0, bdiv = 0;
 		u32 mr;
 		int div8;
@@ -1206,6 +1167,10 @@ OF_EARLYCON_DECLARE(cdns, "cdns,uart-r1p8", cdns_early_console_setup);
 OF_EARLYCON_DECLARE(cdns, "cdns,uart-r1p12", cdns_early_console_setup);
 OF_EARLYCON_DECLARE(cdns, "xlnx,zynqmp-uart", cdns_early_console_setup);
 
+
+/* Static pointer to console port */
+static struct uart_port *console_port;
+
 /**
  * cdns_uart_console_write - perform write operation
  * @co: Console handle
@@ -1215,7 +1180,7 @@ OF_EARLYCON_DECLARE(cdns, "xlnx,zynqmp-uart", cdns_early_console_setup);
 static void cdns_uart_console_write(struct console *co, const char *s,
 				unsigned int count)
 {
-	struct uart_port *port = &cdns_uart_port[co->index];
+	struct uart_port *port = console_port;
 	unsigned long flags;
 	unsigned int imr, ctrl;
 	int locked = 1;
@@ -1261,15 +1226,13 @@ static void cdns_uart_console_write(struct console *co, const char *s,
  */
 static int __init cdns_uart_console_setup(struct console *co, char *options)
 {
-	struct uart_port *port = &cdns_uart_port[co->index];
+	struct uart_port *port = console_port;
+
 	int baud = 9600;
 	int bits = 8;
 	int parity = 'n';
 	int flow = 'n';
 
-	if (co->index < 0 || co->index >= CDNS_UART_NR_PORTS)
-		return -EINVAL;
-
 	if (!port->membase) {
 		pr_debug("console on " CDNS_UART_TTY_NAME "%i not present\n",
 			 co->index);
@@ -1293,20 +1256,6 @@ static struct console cdns_uart_console = {
 	.index	= -1, /* Specified on the cmdline (e.g. console=ttyPS ) */
 	.data	= &cdns_uart_uart_driver,
 };
-
-/**
- * cdns_uart_console_init - Initialization call
- *
- * Return: 0 on success, negative errno otherwise
- */
-static int __init cdns_uart_console_init(void)
-{
-	register_console(&cdns_uart_console);
-	return 0;
-}
-
-console_initcall(cdns_uart_console_init);
-
 #endif /* CONFIG_SERIAL_XILINX_PS_UART_CONSOLE */
 
 static struct uart_driver cdns_uart_uart_driver = {
@@ -1430,8 +1379,7 @@ static int cdns_uart_resume(struct device *device)
 #endif /* ! CONFIG_PM_SLEEP */
 static int __maybe_unused cdns_runtime_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct uart_port *port = platform_get_drvdata(pdev);
+	struct uart_port *port = dev_get_drvdata(dev);
 	struct cdns_uart *cdns_uart = port->private_data;
 
 	clk_disable(cdns_uart->uartclk);
@@ -1441,8 +1389,7 @@ static int __maybe_unused cdns_runtime_suspend(struct device *dev)
 
 static int __maybe_unused cdns_runtime_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct uart_port *port = platform_get_drvdata(pdev);
+	struct uart_port *port = dev_get_drvdata(dev);
 	struct cdns_uart *cdns_uart = port->private_data;
 
 	clk_enable(cdns_uart->pclk);
@@ -1487,6 +1434,9 @@ static int cdns_uart_probe(struct platform_device *pdev)
 			GFP_KERNEL);
 	if (!cdns_uart_data)
 		return -ENOMEM;
+	port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
 
 	match = of_match_node(cdns_uart_of_match, pdev->dev.of_node);
 	if (match && match->data) {
@@ -1552,15 +1502,24 @@ static int cdns_uart_probe(struct platform_device *pdev)
 	if (id < 0)
 		id = 0;
 
-	/* Initialize the port structure */
-	port = cdns_uart_get_port(id);
-
-	if (!port) {
+	if (id >= CDNS_UART_NR_PORTS) {
 		dev_err(&pdev->dev, "Cannot get uart_port structure\n");
 		rc = -ENODEV;
 		goto err_out_notif_unreg;
 	}
 
+	/* At this point, we've got an empty uart_port struct, initialize it */
+	spin_lock_init(&port->lock);
+	port->membase	= NULL;
+	port->irq	= 0;
+	port->type	= PORT_UNKNOWN;
+	port->iotype	= UPIO_MEM32;
+	port->flags	= UPF_BOOT_AUTOCONF;
+	port->ops	= &cdns_uart_ops;
+	port->fifosize	= CDNS_UART_FIFO_SIZE;
+	port->line	= id;
+	port->dev	= NULL;
+
 	/*
 	 * Register the port.
 	 * This function also registers this device with the tty layer
@@ -1579,6 +1538,17 @@ static int cdns_uart_probe(struct platform_device *pdev)
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
+#ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
+	/*
+	 * If console hasn't been found yet try to assign this port
+	 * because it is required to be assigned for console setup function.
+	 * If register_console() don't assign value, then console_port pointer
+	 * is cleanup.
+	 */
+	if (cdns_uart_uart_driver.cons->index == -1)
+		console_port = port;
+#endif
+
 	rc = uart_add_one_port(&cdns_uart_uart_driver, port);
 	if (rc) {
 		dev_err(&pdev->dev,
@@ -1586,6 +1556,12 @@ static int cdns_uart_probe(struct platform_device *pdev)
 		goto err_out_pm_disable;
 	}
 
+#ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
+	/* This is not port which is used for console that's why clean it up */
+	if (cdns_uart_uart_driver.cons->index == -1)
+		console_port = NULL;
+#endif
+
 	return 0;
 
 err_out_pm_disable:
diff --git a/drivers/tty/synclink.c b/drivers/tty/synclink.c
index 3c4ad71f261d..fbdf4d01c6a9 100644
--- a/drivers/tty/synclink.c
+++ b/drivers/tty/synclink.c
@@ -3534,19 +3534,6 @@ static int mgsl_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int mgsl_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mgsl_proc_show, NULL);
-}
-
-static const struct file_operations mgsl_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= mgsl_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /* mgsl_allocate_dma_buffers()
  * 
  * 	Allocate and format DMA buffers (ISA adapter)
@@ -4298,7 +4285,7 @@ static const struct tty_operations mgsl_ops = {
 	.tiocmget = tiocmget,
 	.tiocmset = tiocmset,
 	.get_icount = msgl_get_icount,
-	.proc_fops = &mgsl_proc_fops,
+	.proc_show = mgsl_proc_show,
 };
 
 /*
diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c
index 255c49687877..a94086597ebd 100644
--- a/drivers/tty/synclink_gt.c
+++ b/drivers/tty/synclink_gt.c
@@ -1316,19 +1316,6 @@ static int synclink_gt_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int synclink_gt_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, synclink_gt_proc_show, NULL);
-}
-
-static const struct file_operations synclink_gt_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= synclink_gt_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /*
  * return count of bytes in transmit buffer
  */
@@ -3721,7 +3708,7 @@ static const struct tty_operations ops = {
 	.tiocmget = tiocmget,
 	.tiocmset = tiocmset,
 	.get_icount = get_icount,
-	.proc_fops = &synclink_gt_proc_fops,
+	.proc_show = synclink_gt_proc_show,
 };
 
 static void slgt_cleanup(void)
diff --git a/drivers/tty/synclinkmp.c b/drivers/tty/synclinkmp.c
index 75f11ce1f0a1..1e4d5b9c981a 100644
--- a/drivers/tty/synclinkmp.c
+++ b/drivers/tty/synclinkmp.c
@@ -1421,19 +1421,6 @@ static int synclinkmp_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int synclinkmp_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, synclinkmp_proc_show, NULL);
-}
-
-static const struct file_operations synclinkmp_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= synclinkmp_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /* Return the count of bytes in transmit buffer
  */
 static int chars_in_buffer(struct tty_struct *tty)
@@ -3899,7 +3886,7 @@ static const struct tty_operations ops = {
 	.tiocmget = tiocmget,
 	.tiocmset = tiocmset,
 	.get_icount = get_icount,
-	.proc_fops = &synclinkmp_proc_fops,
+	.proc_show = synclinkmp_proc_show,
 };
 
 
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 63114ea35ec1..7c838b90a31d 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2816,7 +2816,10 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx)
 
 	kref_init(&tty->kref);
 	tty->magic = TTY_MAGIC;
-	tty_ldisc_init(tty);
+	if (tty_ldisc_init(tty)) {
+		kfree(tty);
+		return NULL;
+	}
 	tty->session = NULL;
 	tty->pgrp = NULL;
 	mutex_init(&tty->legacy_mutex);
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index d9b561d89432..d99fec44036c 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -290,7 +290,7 @@ EXPORT_SYMBOL(tty_termios_copy_hw);
  *	between the two termios structures, or a speed change is needed.
  */
 
-int tty_termios_hw_change(struct ktermios *a, struct ktermios *b)
+int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b)
 {
 	if (a->c_ispeed != b->c_ispeed || a->c_ospeed != b->c_ospeed)
 		return 1;
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 050f4d650891..fc4c97cae01e 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -176,12 +176,11 @@ static struct tty_ldisc *tty_ldisc_get(struct tty_struct *tty, int disc)
 			return ERR_CAST(ldops);
 	}
 
-	ld = kmalloc(sizeof(struct tty_ldisc), GFP_KERNEL);
-	if (ld == NULL) {
-		put_ldops(ldops);
-		return ERR_PTR(-ENOMEM);
-	}
-
+	/*
+	 * There is no way to handle allocation failure of only 16 bytes.
+	 * Let's simplify error handling and save more memory.
+	 */
+	ld = kmalloc(sizeof(struct tty_ldisc), GFP_KERNEL | __GFP_NOFAIL);
 	ld->ops = ldops;
 	ld->tty = tty;
 
@@ -230,26 +229,13 @@ static int tty_ldiscs_seq_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static const struct seq_operations tty_ldiscs_seq_ops = {
+const struct seq_operations tty_ldiscs_seq_ops = {
 	.start	= tty_ldiscs_seq_start,
 	.next	= tty_ldiscs_seq_next,
 	.stop	= tty_ldiscs_seq_stop,
 	.show	= tty_ldiscs_seq_show,
 };
 
-static int proc_tty_ldiscs_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &tty_ldiscs_seq_ops);
-}
-
-const struct file_operations tty_ldiscs_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_tty_ldiscs_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 /**
  *	tty_ldisc_ref_wait	-	wait for the tty ldisc
  *	@tty: tty device
@@ -527,19 +513,16 @@ static int tty_ldisc_failto(struct tty_struct *tty, int ld)
 static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
 {
 	/* There is an outstanding reference here so this is safe */
-	old = tty_ldisc_get(tty, old->ops->num);
-	WARN_ON(IS_ERR(old));
-	tty->ldisc = old;
-	tty_set_termios_ldisc(tty, old->ops->num);
-	if (tty_ldisc_open(tty, old) < 0) {
-		tty_ldisc_put(old);
+	if (tty_ldisc_failto(tty, old->ops->num) < 0) {
+		const char *name = tty_name(tty);
+
+		pr_warn("Falling back ldisc for %s.\n", name);
 		/* The traditional behaviour is to fall back to N_TTY, we
 		   want to avoid falling back to N_NULL unless we have no
 		   choice to avoid the risk of breaking anything */
 		if (tty_ldisc_failto(tty, N_TTY) < 0 &&
 		    tty_ldisc_failto(tty, N_NULL) < 0)
-			panic("Couldn't open N_NULL ldisc for %s.",
-			      tty_name(tty));
+			panic("Couldn't open N_NULL ldisc for %s.", name);
 	}
 }
 
@@ -824,12 +807,13 @@ EXPORT_SYMBOL_GPL(tty_ldisc_release);
  *	the tty structure is not completely set up when this call is made.
  */
 
-void tty_ldisc_init(struct tty_struct *tty)
+int tty_ldisc_init(struct tty_struct *tty)
 {
 	struct tty_ldisc *ld = tty_ldisc_get(tty, N_TTY);
 	if (IS_ERR(ld))
-		panic("n_tty: init_tty");
+		return PTR_ERR(ld);
 	tty->ldisc = ld;
+	return 0;
 }
 
 /**
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index f97251f39c26..1eb1a376a041 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1178,15 +1178,8 @@ static void csi_J(struct vc_data *vc, int vpar)
 			count = ((vc->vc_pos - vc->vc_origin) >> 1) + 1;
 			start = (unsigned short *)vc->vc_origin;
 			break;
-		case 3: /* erase scroll-back buffer (and whole display) */
-			scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char,
-				    vc->vc_screenbuf_size);
-			flush_scrollback(vc);
-			set_origin(vc);
-			if (con_is_visible(vc))
-				update_screen(vc);
-			/* fall through */
 		case 2: /* erase whole display */
+		case 3: /* (and scrollback buffer later) */
 			count = vc->vc_cols * vc->vc_rows;
 			start = (unsigned short *)vc->vc_origin;
 			break;
@@ -1194,7 +1187,12 @@ static void csi_J(struct vc_data *vc, int vpar)
 			return;
 	}
 	scr_memsetw(start, vc->vc_video_erase_char, 2 * count);
-	if (con_should_update(vc))
+	if (vpar == 3) {
+		set_origin(vc);
+		flush_scrollback(vc);
+		if (con_is_visible(vc))
+			update_screen(vc);
+	} else if (con_should_update(vc))
 		do_update_region(vc, (unsigned long) start, count);
 	vc->vc_need_wrap = 0;
 }
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index fd4848392e0d..e8f4ac9400ea 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -270,7 +270,7 @@ static int uio_dev_add_attributes(struct uio_device *idev)
 		if (!map_found) {
 			map_found = 1;
 			idev->map_dir = kobject_create_and_add("maps",
-							&idev->dev->kobj);
+							&idev->dev.kobj);
 			if (!idev->map_dir) {
 				ret = -ENOMEM;
 				goto err_map;
@@ -299,7 +299,7 @@ static int uio_dev_add_attributes(struct uio_device *idev)
 		if (!portio_found) {
 			portio_found = 1;
 			idev->portio_dir = kobject_create_and_add("portio",
-							&idev->dev->kobj);
+							&idev->dev.kobj);
 			if (!idev->portio_dir) {
 				ret = -ENOMEM;
 				goto err_portio;
@@ -342,7 +342,7 @@ err_map_kobj:
 		kobject_put(&map->kobj);
 	}
 	kobject_put(idev->map_dir);
-	dev_err(idev->dev, "error creating sysfs files (%d)\n", ret);
+	dev_err(&idev->dev, "error creating sysfs files (%d)\n", ret);
 	return ret;
 }
 
@@ -379,7 +379,7 @@ static int uio_get_minor(struct uio_device *idev)
 		idev->minor = retval;
 		retval = 0;
 	} else if (retval == -ENOSPC) {
-		dev_err(idev->dev, "too many uio devices\n");
+		dev_err(&idev->dev, "too many uio devices\n");
 		retval = -EINVAL;
 	}
 	mutex_unlock(&minor_lock);
@@ -433,6 +433,7 @@ static int uio_open(struct inode *inode, struct file *filep)
 	struct uio_device *idev;
 	struct uio_listener *listener;
 	int ret = 0;
+	unsigned long flags;
 
 	mutex_lock(&minor_lock);
 	idev = idr_find(&uio_idr, iminor(inode));
@@ -442,9 +443,11 @@ static int uio_open(struct inode *inode, struct file *filep)
 		goto out;
 	}
 
+	get_device(&idev->dev);
+
 	if (!try_module_get(idev->owner)) {
 		ret = -ENODEV;
-		goto out;
+		goto err_module_get;
 	}
 
 	listener = kmalloc(sizeof(*listener), GFP_KERNEL);
@@ -457,11 +460,13 @@ static int uio_open(struct inode *inode, struct file *filep)
 	listener->event_count = atomic_read(&idev->event);
 	filep->private_data = listener;
 
-	if (idev->info->open) {
+	spin_lock_irqsave(&idev->info_lock, flags);
+	if (idev->info && idev->info->open)
 		ret = idev->info->open(idev->info, inode);
-		if (ret)
-			goto err_infoopen;
-	}
+	spin_unlock_irqrestore(&idev->info_lock, flags);
+	if (ret)
+		goto err_infoopen;
+
 	return 0;
 
 err_infoopen:
@@ -470,6 +475,9 @@ err_infoopen:
 err_alloc_listener:
 	module_put(idev->owner);
 
+err_module_get:
+	put_device(&idev->dev);
+
 out:
 	return ret;
 }
@@ -487,12 +495,16 @@ static int uio_release(struct inode *inode, struct file *filep)
 	int ret = 0;
 	struct uio_listener *listener = filep->private_data;
 	struct uio_device *idev = listener->dev;
+	unsigned long flags;
 
-	if (idev->info->release)
+	spin_lock_irqsave(&idev->info_lock, flags);
+	if (idev->info && idev->info->release)
 		ret = idev->info->release(idev->info, inode);
+	spin_unlock_irqrestore(&idev->info_lock, flags);
 
 	module_put(idev->owner);
 	kfree(listener);
+	put_device(&idev->dev);
 	return ret;
 }
 
@@ -500,9 +512,16 @@ static __poll_t uio_poll(struct file *filep, poll_table *wait)
 {
 	struct uio_listener *listener = filep->private_data;
 	struct uio_device *idev = listener->dev;
+	__poll_t ret = 0;
+	unsigned long flags;
 
-	if (!idev->info->irq)
-		return -EIO;
+	spin_lock_irqsave(&idev->info_lock, flags);
+	if (!idev->info || !idev->info->irq)
+		ret = -EIO;
+	spin_unlock_irqrestore(&idev->info_lock, flags);
+
+	if (ret)
+		return ret;
 
 	poll_wait(filep, &idev->wait, wait);
 	if (listener->event_count != atomic_read(&idev->event))
@@ -516,11 +535,17 @@ static ssize_t uio_read(struct file *filep, char __user *buf,
 	struct uio_listener *listener = filep->private_data;
 	struct uio_device *idev = listener->dev;
 	DECLARE_WAITQUEUE(wait, current);
-	ssize_t retval;
+	ssize_t retval = 0;
 	s32 event_count;
+	unsigned long flags;
 
-	if (!idev->info->irq)
-		return -EIO;
+	spin_lock_irqsave(&idev->info_lock, flags);
+	if (!idev->info || !idev->info->irq)
+		retval = -EIO;
+	spin_unlock_irqrestore(&idev->info_lock, flags);
+
+	if (retval)
+		return retval;
 
 	if (count != sizeof(s32))
 		return -EINVAL;
@@ -567,21 +592,33 @@ static ssize_t uio_write(struct file *filep, const char __user *buf,
 	struct uio_device *idev = listener->dev;
 	ssize_t retval;
 	s32 irq_on;
+	unsigned long flags;
 
-	if (!idev->info->irq)
-		return -EIO;
+	spin_lock_irqsave(&idev->info_lock, flags);
+	if (!idev->info || !idev->info->irq) {
+		retval = -EIO;
+		goto out;
+	}
 
-	if (count != sizeof(s32))
-		return -EINVAL;
+	if (count != sizeof(s32)) {
+		retval = -EINVAL;
+		goto out;
+	}
 
-	if (!idev->info->irqcontrol)
-		return -ENOSYS;
+	if (!idev->info->irqcontrol) {
+		retval = -ENOSYS;
+		goto out;
+	}
 
-	if (copy_from_user(&irq_on, buf, count))
-		return -EFAULT;
+	if (copy_from_user(&irq_on, buf, count)) {
+		retval = -EFAULT;
+		goto out;
+	}
 
 	retval = idev->info->irqcontrol(idev->info, irq_on);
 
+out:
+	spin_unlock_irqrestore(&idev->info_lock, flags);
 	return retval ? retval : sizeof(s32);
 }
 
@@ -597,7 +634,7 @@ static int uio_find_mem_index(struct vm_area_struct *vma)
 	return -1;
 }
 
-static int uio_vma_fault(struct vm_fault *vmf)
+static vm_fault_t uio_vma_fault(struct vm_fault *vmf)
 {
 	struct uio_device *idev = vmf->vma->vm_private_data;
 	struct page *page;
@@ -794,6 +831,13 @@ static void release_uio_class(void)
 	uio_major_cleanup();
 }
 
+static void uio_device_release(struct device *dev)
+{
+	struct uio_device *idev = dev_get_drvdata(dev);
+
+	kfree(idev);
+}
+
 /**
  * uio_register_device - register a new userspace IO device
  * @owner:	module that creates the new device
@@ -814,13 +858,14 @@ int __uio_register_device(struct module *owner,
 
 	info->uio_dev = NULL;
 
-	idev = devm_kzalloc(parent, sizeof(*idev), GFP_KERNEL);
+	idev = kzalloc(sizeof(*idev), GFP_KERNEL);
 	if (!idev) {
 		return -ENOMEM;
 	}
 
 	idev->owner = owner;
 	idev->info = info;
+	spin_lock_init(&idev->info_lock);
 	init_waitqueue_head(&idev->wait);
 	atomic_set(&idev->event, 0);
 
@@ -828,14 +873,19 @@ int __uio_register_device(struct module *owner,
 	if (ret)
 		return ret;
 
-	idev->dev = device_create(&uio_class, parent,
-				  MKDEV(uio_major, idev->minor), idev,
-				  "uio%d", idev->minor);
-	if (IS_ERR(idev->dev)) {
-		printk(KERN_ERR "UIO: device register failed\n");
-		ret = PTR_ERR(idev->dev);
+	idev->dev.devt = MKDEV(uio_major, idev->minor);
+	idev->dev.class = &uio_class;
+	idev->dev.parent = parent;
+	idev->dev.release = uio_device_release;
+	dev_set_drvdata(&idev->dev, idev);
+
+	ret = dev_set_name(&idev->dev, "uio%d", idev->minor);
+	if (ret)
+		goto err_device_create;
+
+	ret = device_register(&idev->dev);
+	if (ret)
 		goto err_device_create;
-	}
 
 	ret = uio_dev_add_attributes(idev);
 	if (ret)
@@ -863,7 +913,7 @@ int __uio_register_device(struct module *owner,
 err_request_irq:
 	uio_dev_del_attributes(idev);
 err_uio_dev_add_attributes:
-	device_destroy(&uio_class, MKDEV(uio_major, idev->minor));
+	device_unregister(&idev->dev);
 err_device_create:
 	uio_free_minor(idev);
 	return ret;
@@ -878,6 +928,7 @@ EXPORT_SYMBOL_GPL(__uio_register_device);
 void uio_unregister_device(struct uio_info *info)
 {
 	struct uio_device *idev;
+	unsigned long flags;
 
 	if (!info || !info->uio_dev)
 		return;
@@ -891,7 +942,11 @@ void uio_unregister_device(struct uio_info *info)
 	if (info->irq && info->irq != UIO_IRQ_CUSTOM)
 		free_irq(info->irq, idev);
 
-	device_destroy(&uio_class, MKDEV(uio_major, idev->minor));
+	spin_lock_irqsave(&idev->info_lock, flags);
+	idev->info = NULL;
+	spin_unlock_irqrestore(&idev->info_lock, flags);
+
+	device_unregister(&idev->dev);
 
 	return;
 }
diff --git a/drivers/uio/uio_fsl_elbc_gpcm.c b/drivers/uio/uio_fsl_elbc_gpcm.c
index b46323d9dc18..b55191335d90 100644
--- a/drivers/uio/uio_fsl_elbc_gpcm.c
+++ b/drivers/uio/uio_fsl_elbc_gpcm.c
@@ -475,7 +475,6 @@ MODULE_DEVICE_TABLE(of, uio_fsl_elbc_gpcm_match);
 static struct platform_driver uio_fsl_elbc_gpcm_driver = {
 	.driver = {
 		.name = "fsl,elbc-gpcm-uio",
-		.owner = THIS_MODULE,
 		.of_match_table = uio_fsl_elbc_gpcm_match,
 	},
 	.probe = uio_fsl_elbc_gpcm_probe,
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index f695a7e8c314..c690d100adcd 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -19,7 +19,7 @@
  * # echo -n "ed963694-e847-4b2a-85af-bc9cfc11d6f3" \
  *    > /sys/bus/vmbus/drivers/uio_hv_generic/bind
  */
-
+#define DEBUG 1
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/device.h>
@@ -94,10 +94,11 @@ hv_uio_irqcontrol(struct uio_info *info, s32 irq_state)
  */
 static void hv_uio_channel_cb(void *context)
 {
-	struct hv_uio_private_data *pdata = context;
-	struct hv_device *dev = pdata->device;
+	struct vmbus_channel *chan = context;
+	struct hv_device *hv_dev = chan->device_obj;
+	struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
 
-	dev->channel->inbound.ring_buffer->interrupt_mask = 1;
+	chan->inbound.ring_buffer->interrupt_mask = 1;
 	virt_mb();
 
 	uio_event_notify(&pdata->info);
@@ -121,78 +122,46 @@ static void hv_uio_rescind(struct vmbus_channel *channel)
 	uio_event_notify(&pdata->info);
 }
 
-/*
- * Handle fault when looking for sub channel ring buffer
- * Subchannel ring buffer is same as resource 0 which is main ring buffer
- * This is derived from uio_vma_fault
+/* Sysfs API to allow mmap of the ring buffers
+ * The ring buffer is allocated as contiguous memory by vmbus_open
  */
-static int hv_uio_vma_fault(struct vm_fault *vmf)
-{
-	struct vm_area_struct *vma = vmf->vma;
-	void *ring_buffer = vma->vm_private_data;
-	struct page *page;
-	void *addr;
-
-	addr = ring_buffer + (vmf->pgoff << PAGE_SHIFT);
-	page = virt_to_page(addr);
-	get_page(page);
-	vmf->page = page;
-	return 0;
-}
-
-static const struct vm_operations_struct hv_uio_vm_ops = {
-	.fault = hv_uio_vma_fault,
-};
-
-/* Sysfs API to allow mmap of the ring buffers */
 static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
 			    struct bin_attribute *attr,
 			    struct vm_area_struct *vma)
 {
 	struct vmbus_channel *channel
 		= container_of(kobj, struct vmbus_channel, kobj);
-	unsigned long requested_pages, actual_pages;
-
-	if (vma->vm_end < vma->vm_start)
-		return -EINVAL;
-
-	/* only allow 0 for now */
-	if (vma->vm_pgoff > 0)
-		return -EINVAL;
+	struct hv_device *dev = channel->primary_channel->device_obj;
+	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 
-	requested_pages = vma_pages(vma);
-	actual_pages = 2 * HV_RING_SIZE;
-	if (requested_pages > actual_pages)
-		return -EINVAL;
+	dev_dbg(&dev->device, "mmap channel %u pages %#lx at %#lx\n",
+		q_idx, vma_pages(vma), vma->vm_pgoff);
 
-	vma->vm_private_data = channel->ringbuffer_pages;
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
-	vma->vm_ops = &hv_uio_vm_ops;
-	return 0;
+	return vm_iomap_memory(vma, virt_to_phys(channel->ringbuffer_pages),
+			       channel->ringbuffer_pagecount << PAGE_SHIFT);
 }
 
-static struct bin_attribute ring_buffer_bin_attr __ro_after_init = {
+static const struct bin_attribute ring_buffer_bin_attr = {
 	.attr = {
 		.name = "ring",
 		.mode = 0600,
-		/* size is set at init time */
 	},
+	.size = 2 * HV_RING_SIZE * PAGE_SIZE,
 	.mmap = hv_uio_ring_mmap,
 };
 
-/* Callback from VMBUS subystem when new channel created. */
+/* Callback from VMBUS subsystem when new channel created. */
 static void
 hv_uio_new_channel(struct vmbus_channel *new_sc)
 {
 	struct hv_device *hv_dev = new_sc->primary_channel->device_obj;
 	struct device *device = &hv_dev->device;
-	struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
 	const size_t ring_bytes = HV_RING_SIZE * PAGE_SIZE;
 	int ret;
 
 	/* Create host communication ring */
 	ret = vmbus_open(new_sc, ring_bytes, ring_bytes, NULL, 0,
-			 hv_uio_channel_cb, pdata);
+			 hv_uio_channel_cb, new_sc);
 	if (ret) {
 		dev_err(device, "vmbus_open subchannel failed: %d\n", ret);
 		return;
@@ -234,7 +203,7 @@ hv_uio_probe(struct hv_device *dev,
 
 	ret = vmbus_open(dev->channel, HV_RING_SIZE * PAGE_SIZE,
 			 HV_RING_SIZE * PAGE_SIZE, NULL, 0,
-			 hv_uio_channel_cb, pdata);
+			 hv_uio_channel_cb, dev->channel);
 	if (ret)
 		goto fail;
 
@@ -326,6 +295,11 @@ hv_uio_probe(struct hv_device *dev,
 	vmbus_set_chn_rescind_callback(dev->channel, hv_uio_rescind);
 	vmbus_set_sc_create_callback(dev->channel, hv_uio_new_channel);
 
+	ret = sysfs_create_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr);
+	if (ret)
+		dev_notice(&dev->device,
+			   "sysfs create ring bin file failed; %d\n", ret);
+
 	hv_set_drvdata(dev, pdata);
 
 	return 0;
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index 75f7fb151f71..987fc5ba6321 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -207,5 +207,6 @@ config USB_ULPI_BUS
 
 config USB_ROLE_SWITCH
 	tristate
+	select USB_COMMON
 
 endif # USB_SUPPORT
diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index 98b7cb3d0064..0bf244d50544 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -450,7 +450,7 @@ void hw_phymode_configure(struct ci_hdrc *ci);
 
 void ci_platform_configure(struct ci_hdrc *ci);
 
-int dbg_create_files(struct ci_hdrc *ci);
+void dbg_create_files(struct ci_hdrc *ci);
 
 void dbg_remove_files(struct ci_hdrc *ci);
 #endif	/* __DRIVERS_USB_CHIPIDEA_CI_H */
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index e431c5aafe35..19f5f5f2a48a 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -291,7 +291,8 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 
 	pdata.usb_phy = data->phy;
 
-	if (of_device_is_compatible(np, "fsl,imx53-usb") && pdata.usb_phy &&
+	if ((of_device_is_compatible(np, "fsl,imx53-usb") ||
+	     of_device_is_compatible(np, "fsl,imx51-usb")) && pdata.usb_phy &&
 	    of_usb_get_phy_mode(np) == USBPHY_INTERFACE_MODE_ULPI) {
 		pdata.flags |= CI_HDRC_OVERRIDE_PHY_CONTROL;
 		data->override_phy_control = true;
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 33ae87fa3ff3..85fc6db48e44 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -1062,9 +1062,7 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 		ci_hdrc_otg_fsm_start(ci);
 
 	device_set_wakeup_capable(&pdev->dev, true);
-	ret = dbg_create_files(ci);
-	if (ret)
-		goto stop;
+	dbg_create_files(ci);
 
 	ret = sysfs_create_group(&dev->kobj, &ci_attr_group);
 	if (ret)
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index ce648cb3ed94..fcc91a338875 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -340,54 +340,28 @@ DEFINE_SHOW_ATTRIBUTE(ci_registers);
  *
  * This function returns an error code
  */
-int dbg_create_files(struct ci_hdrc *ci)
+void dbg_create_files(struct ci_hdrc *ci)
 {
-	struct dentry *dent;
-
 	ci->debugfs = debugfs_create_dir(dev_name(ci->dev), NULL);
-	if (!ci->debugfs)
-		return -ENOMEM;
-
-	dent = debugfs_create_file("device", S_IRUGO, ci->debugfs, ci,
-				   &ci_device_fops);
-	if (!dent)
-		goto err;
-
-	dent = debugfs_create_file("port_test", S_IRUGO | S_IWUSR, ci->debugfs,
-				   ci, &ci_port_test_fops);
-	if (!dent)
-		goto err;
-
-	dent = debugfs_create_file("qheads", S_IRUGO, ci->debugfs, ci,
-				   &ci_qheads_fops);
-	if (!dent)
-		goto err;
 
-	dent = debugfs_create_file("requests", S_IRUGO, ci->debugfs, ci,
-				   &ci_requests_fops);
-	if (!dent)
-		goto err;
+	debugfs_create_file("device", S_IRUGO, ci->debugfs, ci,
+			    &ci_device_fops);
+	debugfs_create_file("port_test", S_IRUGO | S_IWUSR, ci->debugfs, ci,
+			    &ci_port_test_fops);
+	debugfs_create_file("qheads", S_IRUGO, ci->debugfs, ci,
+			    &ci_qheads_fops);
+	debugfs_create_file("requests", S_IRUGO, ci->debugfs, ci,
+			    &ci_requests_fops);
 
 	if (ci_otg_is_fsm_mode(ci)) {
-		dent = debugfs_create_file("otg", S_IRUGO, ci->debugfs, ci,
-					&ci_otg_fops);
-		if (!dent)
-			goto err;
+		debugfs_create_file("otg", S_IRUGO, ci->debugfs, ci,
+				    &ci_otg_fops);
 	}
 
-	dent = debugfs_create_file("role", S_IRUGO | S_IWUSR, ci->debugfs, ci,
-				   &ci_role_fops);
-	if (!dent)
-		goto err;
-
-	dent = debugfs_create_file("registers", S_IRUGO, ci->debugfs, ci,
-				&ci_registers_fops);
-
-	if (dent)
-		return 0;
-err:
-	debugfs_remove_recursive(ci->debugfs);
-	return -ENOMEM;
+	debugfs_create_file("role", S_IRUGO | S_IWUSR, ci->debugfs, ci,
+			    &ci_role_fops);
+	debugfs_create_file("registers", S_IRUGO, ci->debugfs, ci,
+			    &ci_registers_fops);
 }
 
 /**
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index bdb1de0c0cef..529295a17579 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -21,7 +21,6 @@
 #include <linux/usb/tmc.h>
 
 
-#define RIGOL			1
 #define USBTMC_HEADER_SIZE	12
 #define USBTMC_MINOR_BASE	176
 
@@ -93,8 +92,6 @@ struct usbtmc_device_data {
 	/* coalesced usb488_caps from usbtmc_dev_capabilities */
 	__u8 usb488_caps;
 
-	u8 rigol_quirk;
-
 	/* attributes from the USB TMC spec for this device */
 	u8 TermChar;
 	bool TermCharEnabled;
@@ -110,17 +107,6 @@ struct usbtmc_device_data {
 };
 #define to_usbtmc_data(d) container_of(d, struct usbtmc_device_data, kref)
 
-struct usbtmc_ID_rigol_quirk {
-	__u16 idVendor;
-	__u16 idProduct;
-};
-
-static const struct usbtmc_ID_rigol_quirk usbtmc_id_quirk[] = {
-	{ 0x1ab1, 0x0588 },
-	{ 0x1ab1, 0x04b0 },
-	{ 0, 0 }
-};
-
 /* Forward declarations */
 static struct usb_driver usbtmc_driver;
 
@@ -603,16 +589,14 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 		goto exit;
 	}
 
-	if (data->rigol_quirk) {
-		dev_dbg(dev, "usb_bulk_msg_in: count(%zu)\n", count);
+	dev_dbg(dev, "usb_bulk_msg_in: count(%zu)\n", count);
 
-		retval = send_request_dev_dep_msg_in(data, count);
+	retval = send_request_dev_dep_msg_in(data, count);
 
-		if (retval < 0) {
-			if (data->auto_abort)
-				usbtmc_ioctl_abort_bulk_out(data);
-			goto exit;
-		}
+	if (retval < 0) {
+		if (data->auto_abort)
+			usbtmc_ioctl_abort_bulk_out(data);
+		goto exit;
 	}
 
 	/* Loop until we have fetched everything we requested */
@@ -621,23 +605,6 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 	done = 0;
 
 	while (remaining > 0) {
-		if (!data->rigol_quirk) {
-			dev_dbg(dev, "usb_bulk_msg_in: remaining(%zu), count(%zu)\n", remaining, count);
-
-			if (remaining > USBTMC_SIZE_IOBUFFER - USBTMC_HEADER_SIZE - 3)
-				this_part = USBTMC_SIZE_IOBUFFER - USBTMC_HEADER_SIZE - 3;
-			else
-				this_part = remaining;
-
-			retval = send_request_dev_dep_msg_in(data, this_part);
-			if (retval < 0) {
-			dev_err(dev, "usb_bulk_msg returned %d\n", retval);
-				if (data->auto_abort)
-					usbtmc_ioctl_abort_bulk_out(data);
-				goto exit;
-			}
-		}
-
 		/* Send bulk URB */
 		retval = usb_bulk_msg(data->usb_dev,
 				      usb_rcvbulkpipe(data->usb_dev,
@@ -658,7 +625,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 		}
 
 		/* Parse header in first packet */
-		if ((done == 0) || !data->rigol_quirk) {
+		if (done == 0) {
 			/* Sanity checks for the header */
 			if (actual < USBTMC_HEADER_SIZE) {
 				dev_err(dev, "Device sent too small first packet: %u < %u\n", actual, USBTMC_HEADER_SIZE);
@@ -698,20 +665,11 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 			actual -= USBTMC_HEADER_SIZE;
 
 			/* Check if the message is smaller than requested */
-			if (data->rigol_quirk) {
-				if (remaining > n_characters)
-					remaining = n_characters;
-				/* Remove padding if it exists */
-				if (actual > remaining)
-					actual = remaining;
-			}
-			else {
-				if (this_part > n_characters)
-					this_part = n_characters;
-				/* Remove padding if it exists */
-				if (actual > this_part)
-					actual = this_part;
-			}
+			if (remaining > n_characters)
+				remaining = n_characters;
+			/* Remove padding if it exists */
+			if (actual > remaining)
+				actual = remaining;
 
 			dev_dbg(dev, "Bulk-IN header: N_characters(%u), bTransAttr(%u)\n", n_characters, buffer[8]);
 
@@ -1365,7 +1323,6 @@ static int usbtmc_probe(struct usb_interface *intf,
 	struct usbtmc_device_data *data;
 	struct usb_host_interface *iface_desc;
 	struct usb_endpoint_descriptor *bulk_in, *bulk_out, *int_in;
-	int n;
 	int retcode;
 
 	dev_dbg(&intf->dev, "%s called\n", __func__);
@@ -1385,20 +1342,6 @@ static int usbtmc_probe(struct usb_interface *intf,
 	atomic_set(&data->srq_asserted, 0);
 	data->zombie = 0;
 
-	/* Determine if it is a Rigol or not */
-	data->rigol_quirk = 0;
-	dev_dbg(&intf->dev, "Trying to find if device Vendor 0x%04X Product 0x%04X has the RIGOL quirk\n",
-		le16_to_cpu(data->usb_dev->descriptor.idVendor),
-		le16_to_cpu(data->usb_dev->descriptor.idProduct));
-	for(n = 0; usbtmc_id_quirk[n].idVendor > 0; n++) {
-		if ((usbtmc_id_quirk[n].idVendor == le16_to_cpu(data->usb_dev->descriptor.idVendor)) &&
-		    (usbtmc_id_quirk[n].idProduct == le16_to_cpu(data->usb_dev->descriptor.idProduct))) {
-			dev_dbg(&intf->dev, "Setting this device as having the RIGOL quirk\n");
-			data->rigol_quirk = 1;
-			break;
-		}
-	}
-
 	/* Initialize USBTMC bTag and other fields */
 	data->bTag	= 1;
 	data->TermCharEnabled = 0;
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index c821b4b9647e..7b5cb28ffb35 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -191,7 +191,9 @@ static const unsigned short full_speed_maxpacket_maxes[4] = {
 static const unsigned short high_speed_maxpacket_maxes[4] = {
 	[USB_ENDPOINT_XFER_CONTROL] = 64,
 	[USB_ENDPOINT_XFER_ISOC] = 1024,
-	[USB_ENDPOINT_XFER_BULK] = 512,
+
+	/* Bulk should be 512, but some devices use 1024: we will warn below */
+	[USB_ENDPOINT_XFER_BULK] = 1024,
 	[USB_ENDPOINT_XFER_INT] = 1024,
 };
 static const unsigned short super_speed_maxpacket_maxes[4] = {
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 9792cedfc351..e76e95f62f76 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1922,4 +1922,5 @@ struct bus_type usb_bus_type = {
 	.name =		"usb",
 	.match =	usb_device_match,
 	.uevent =	usb_uevent,
+	.need_parent_lock =	true,
 };
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 777036ae6367..1c21955fe7c0 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -33,7 +33,6 @@
 #include <linux/phy/phy.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
-#include <linux/usb/phy.h>
 #include <linux/usb/otg.h>
 
 #include "usb.h"
@@ -568,6 +567,7 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb)
 		switch (wValue & 0xff00) {
 		case USB_DT_DEVICE << 8:
 			switch (hcd->speed) {
+			case HCD_USB32:
 			case HCD_USB31:
 				bufp = usb31_rh_dev_descriptor;
 				break;
@@ -592,6 +592,7 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb)
 			break;
 		case USB_DT_CONFIG << 8:
 			switch (hcd->speed) {
+			case HCD_USB32:
 			case HCD_USB31:
 			case HCD_USB3:
 				bufp = ss_rh_config_descriptor;
@@ -2262,7 +2263,8 @@ int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg)
 		hcd->state = HC_STATE_SUSPENDED;
 
 		if (!PMSG_IS_AUTO(msg))
-			usb_phy_roothub_power_off(hcd->phy_roothub);
+			usb_phy_roothub_suspend(hcd->self.sysdev,
+						hcd->phy_roothub);
 
 		/* Did we race with a root-hub wakeup event? */
 		if (rhdev->do_remote_wakeup) {
@@ -2302,7 +2304,8 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
 	}
 
 	if (!PMSG_IS_AUTO(msg)) {
-		status = usb_phy_roothub_power_on(hcd->phy_roothub);
+		status = usb_phy_roothub_resume(hcd->self.sysdev,
+						hcd->phy_roothub);
 		if (status)
 			return status;
 	}
@@ -2344,7 +2347,7 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
 		}
 	} else {
 		hcd->state = old_state;
-		usb_phy_roothub_power_off(hcd->phy_roothub);
+		usb_phy_roothub_suspend(hcd->self.sysdev, hcd->phy_roothub);
 		dev_dbg(&rhdev->dev, "bus %s fail, err %d\n",
 				"resume", status);
 		if (status != -ESHUTDOWN)
@@ -2377,6 +2380,7 @@ void usb_hcd_resume_root_hub (struct usb_hcd *hcd)
 
 	spin_lock_irqsave (&hcd_root_hub_lock, flags);
 	if (hcd->rh_registered) {
+		pm_wakeup_event(&hcd->self.root_hub->dev, 0);
 		set_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags);
 		queue_work(pm_wq, &hcd->wakeup_work);
 	}
@@ -2739,30 +2743,14 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	int retval;
 	struct usb_device *rhdev;
 
-	if (IS_ENABLED(CONFIG_USB_PHY) && !hcd->skip_phy_initialization) {
-		struct usb_phy *phy = usb_get_phy_dev(hcd->self.sysdev, 0);
-
-		if (IS_ERR(phy)) {
-			retval = PTR_ERR(phy);
-			if (retval == -EPROBE_DEFER)
-				return retval;
-		} else {
-			retval = usb_phy_init(phy);
-			if (retval) {
-				usb_put_phy(phy);
-				return retval;
-			}
-			hcd->usb_phy = phy;
-			hcd->remove_phy = 1;
-		}
-	}
-
 	if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) {
-		hcd->phy_roothub = usb_phy_roothub_init(hcd->self.sysdev);
-		if (IS_ERR(hcd->phy_roothub)) {
-			retval = PTR_ERR(hcd->phy_roothub);
-			goto err_phy_roothub_init;
-		}
+		hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev);
+		if (IS_ERR(hcd->phy_roothub))
+			return PTR_ERR(hcd->phy_roothub);
+
+		retval = usb_phy_roothub_init(hcd->phy_roothub);
+		if (retval)
+			return retval;
 
 		retval = usb_phy_roothub_power_on(hcd->phy_roothub);
 		if (retval)
@@ -2812,6 +2800,9 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	hcd->self.root_hub = rhdev;
 	mutex_unlock(&usb_port_peer_mutex);
 
+	rhdev->rx_lanes = 1;
+	rhdev->tx_lanes = 1;
+
 	switch (hcd->speed) {
 	case HCD_USB11:
 		rhdev->speed = USB_SPEED_FULL;
@@ -2825,6 +2816,10 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	case HCD_USB3:
 		rhdev->speed = USB_SPEED_SUPER;
 		break;
+	case HCD_USB32:
+		rhdev->rx_lanes = 2;
+		rhdev->tx_lanes = 2;
+		/* fall through */
 	case HCD_USB31:
 		rhdev->speed = USB_SPEED_SUPER_PLUS;
 		break;
@@ -2936,12 +2931,7 @@ err_create_buf:
 	usb_phy_roothub_power_off(hcd->phy_roothub);
 err_usb_phy_roothub_power_on:
 	usb_phy_roothub_exit(hcd->phy_roothub);
-err_phy_roothub_init:
-	if (hcd->remove_phy && hcd->usb_phy) {
-		usb_phy_shutdown(hcd->usb_phy);
-		usb_put_phy(hcd->usb_phy);
-		hcd->usb_phy = NULL;
-	}
+
 	return retval;
 }
 EXPORT_SYMBOL_GPL(usb_add_hcd);
@@ -3017,12 +3007,6 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	usb_phy_roothub_power_off(hcd->phy_roothub);
 	usb_phy_roothub_exit(hcd->phy_roothub);
 
-	if (hcd->remove_phy && hcd->usb_phy) {
-		usb_phy_shutdown(hcd->usb_phy);
-		usb_put_phy(hcd->usb_phy);
-		hcd->usb_phy = NULL;
-	}
-
 	usb_put_invalidate_rhdev(hcd);
 	hcd->flags = 0;
 }
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index f6ea16e9f6bb..26c2438d2889 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -653,12 +653,17 @@ void usb_wakeup_notification(struct usb_device *hdev,
 		unsigned int portnum)
 {
 	struct usb_hub *hub;
+	struct usb_port *port_dev;
 
 	if (!hdev)
 		return;
 
 	hub = usb_hub_to_struct_hub(hdev);
 	if (hub) {
+		port_dev = hub->ports[portnum - 1];
+		if (port_dev && port_dev->child)
+			pm_wakeup_event(&port_dev->child->dev, 0);
+
 		set_bit(portnum, hub->wakeup_bits);
 		kick_hub_wq(hub);
 	}
@@ -2631,7 +2636,7 @@ static unsigned hub_is_wusb(struct usb_hub *hub)
 #define SET_ADDRESS_TRIES	2
 #define GET_DESCRIPTOR_TRIES	2
 #define SET_CONFIG_TRIES	(2 * (use_both_schemes + 1))
-#define USE_NEW_SCHEME(i)	((i) / 2 == (int)old_scheme_first)
+#define USE_NEW_SCHEME(i, scheme)	((i) / 2 == (int)scheme)
 
 #define HUB_ROOT_RESET_TIME	60	/* times are in msec */
 #define HUB_SHORT_RESET_TIME	10
@@ -2646,12 +2651,16 @@ static unsigned hub_is_wusb(struct usb_hub *hub)
  * enumeration failures, so disable this enumeration scheme for USB3
  * devices.
  */
-static bool use_new_scheme(struct usb_device *udev, int retry)
+static bool use_new_scheme(struct usb_device *udev, int retry,
+			   struct usb_port *port_dev)
 {
+	int old_scheme_first_port =
+		port_dev->quirks & USB_PORT_QUIRK_OLD_SCHEME;
+
 	if (udev->speed >= USB_SPEED_SUPER)
 		return false;
 
-	return USE_NEW_SCHEME(retry);
+	return USE_NEW_SCHEME(retry, old_scheme_first_port || old_scheme_first);
 }
 
 /* Is a USB 3.0 port in the Inactive or Compliance Mode state?
@@ -2746,6 +2755,14 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1,
 	if (!udev)
 		return 0;
 
+	if (hub_is_superspeedplus(hub->hdev)) {
+		/* extended portstatus Rx and Tx lane count are zero based */
+		udev->rx_lanes = USB_EXT_PORT_RX_LANES(ext_portstatus) + 1;
+		udev->tx_lanes = USB_EXT_PORT_TX_LANES(ext_portstatus) + 1;
+	} else {
+		udev->rx_lanes = 1;
+		udev->tx_lanes = 1;
+	}
 	if (hub_is_wusb(hub))
 		udev->speed = USB_SPEED_WIRELESS;
 	else if (hub_is_superspeedplus(hub->hdev) &&
@@ -2862,7 +2879,11 @@ static int hub_port_reset(struct usb_hub *hub, int port1,
 done:
 	if (status == 0) {
 		/* TRSTRCY = 10 ms; plus some extra */
-		msleep(10 + 40);
+		if (port_dev->quirks & USB_PORT_QUIRK_FAST_ENUM)
+			usleep_range(10000, 12000);
+		else
+			msleep(10 + 40);
+
 		if (udev) {
 			struct usb_hcd *hcd = bus_to_hcd(udev->bus);
 
@@ -3371,6 +3392,10 @@ static int wait_for_connected(struct usb_device *udev,
 	while (delay_ms < 2000) {
 		if (status || *portstatus & USB_PORT_STAT_CONNECTION)
 			break;
+		if (!port_is_power_on(hub, *portstatus)) {
+			status = -ENODEV;
+			break;
+		}
 		msleep(20);
 		delay_ms += 20;
 		status = hub_port_status(hub, *port1, portstatus, portchange);
@@ -3434,8 +3459,11 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 
 	/* Skip the initial Clear-Suspend step for a remote wakeup */
 	status = hub_port_status(hub, port1, &portstatus, &portchange);
-	if (status == 0 && !port_is_suspended(hub, portstatus))
+	if (status == 0 && !port_is_suspended(hub, portstatus)) {
+		if (portchange & USB_PORT_STAT_C_SUSPEND)
+			pm_wakeup_event(&udev->dev, 0);
 		goto SuspendCleared;
+	}
 
 	/* see 7.1.7.7; affects power usage, but not budgeting */
 	if (hub_is_superspeed(hub->hdev))
@@ -4372,6 +4400,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 {
 	struct usb_device	*hdev = hub->hdev;
 	struct usb_hcd		*hcd = bus_to_hcd(hdev->bus);
+	struct usb_port		*port_dev = hub->ports[port1 - 1];
 	int			retries, operations, retval, i;
 	unsigned		delay = HUB_SHORT_RESET_TIME;
 	enum usb_device_speed	oldspeed = udev->speed;
@@ -4493,7 +4522,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	for (retries = 0; retries < GET_DESCRIPTOR_TRIES; (++retries, msleep(100))) {
 		bool did_new_scheme = false;
 
-		if (use_new_scheme(udev, retry_counter)) {
+		if (use_new_scheme(udev, retry_counter, port_dev)) {
 			struct usb_device_descriptor *buf;
 			int r = 0;
 
@@ -4543,7 +4572,9 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 				 * reset. But only on the first attempt,
 				 * lest we get into a time out/reset loop
 				 */
-				if (r == 0  || (r == -ETIMEDOUT && retries == 0))
+				if (r == 0 || (r == -ETIMEDOUT &&
+						retries == 0 &&
+						udev->speed > USB_SPEED_FULL))
 					break;
 			}
 			udev->descriptor.bMaxPacketSize0 =
@@ -4590,9 +4621,12 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 			if (udev->speed >= USB_SPEED_SUPER) {
 				devnum = udev->devnum;
 				dev_info(&udev->dev,
-						"%s SuperSpeed%s USB device number %d using %s\n",
+						"%s SuperSpeed%s%s USB device number %d using %s\n",
 						(udev->config) ? "reset" : "new",
-					 (udev->speed == USB_SPEED_SUPER_PLUS) ? "Plus" : "",
+					 (udev->speed == USB_SPEED_SUPER_PLUS) ?
+							"Plus Gen 2" : " Gen 1",
+					 (udev->rx_lanes == 2 && udev->tx_lanes == 2) ?
+							"x2" : "",
 					 devnum, driver_name);
 			}
 
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index 4dc769ee9c74..4accfb63f7dc 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -98,6 +98,7 @@ struct usb_port {
 	struct mutex status_lock;
 	u32 over_current_count;
 	u8 portnum;
+	u32 quirks;
 	unsigned int is_superspeed:1;
 	unsigned int usb3_lpm_u1_permit:1;
 	unsigned int usb3_lpm_u2_permit:1;
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 0c11d40a12bc..7b137003c2be 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -940,7 +940,7 @@ int usb_set_isoch_delay(struct usb_device *dev)
 	return usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 			USB_REQ_SET_ISOCH_DELAY,
 			USB_DIR_OUT | USB_TYPE_STANDARD | USB_RECIP_DEVICE,
-			cpu_to_le16(dev->hub_delay), 0, NULL, 0,
+			dev->hub_delay, 0, NULL, 0,
 			USB_CTRL_SET_TIMEOUT);
 }
 
diff --git a/drivers/usb/core/phy.c b/drivers/usb/core/phy.c
index 09b7c43c0ea4..9879767452a2 100644
--- a/drivers/usb/core/phy.c
+++ b/drivers/usb/core/phy.c
@@ -19,19 +19,6 @@ struct usb_phy_roothub {
 	struct list_head	list;
 };
 
-static struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev)
-{
-	struct usb_phy_roothub *roothub_entry;
-
-	roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL);
-	if (!roothub_entry)
-		return ERR_PTR(-ENOMEM);
-
-	INIT_LIST_HEAD(&roothub_entry->list);
-
-	return roothub_entry;
-}
-
 static int usb_phy_roothub_add_phy(struct device *dev, int index,
 				   struct list_head *list)
 {
@@ -45,9 +32,11 @@ static int usb_phy_roothub_add_phy(struct device *dev, int index,
 			return PTR_ERR(phy);
 	}
 
-	roothub_entry = usb_phy_roothub_alloc(dev);
-	if (IS_ERR(roothub_entry))
-		return PTR_ERR(roothub_entry);
+	roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL);
+	if (!roothub_entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&roothub_entry->list);
 
 	roothub_entry->phy = phy;
 
@@ -56,28 +45,44 @@ static int usb_phy_roothub_add_phy(struct device *dev, int index,
 	return 0;
 }
 
-struct usb_phy_roothub *usb_phy_roothub_init(struct device *dev)
+struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev)
 {
 	struct usb_phy_roothub *phy_roothub;
-	struct usb_phy_roothub *roothub_entry;
-	struct list_head *head;
 	int i, num_phys, err;
 
+	if (!IS_ENABLED(CONFIG_GENERIC_PHY))
+		return NULL;
+
 	num_phys = of_count_phandle_with_args(dev->of_node, "phys",
 					      "#phy-cells");
 	if (num_phys <= 0)
 		return NULL;
 
-	phy_roothub = usb_phy_roothub_alloc(dev);
-	if (IS_ERR(phy_roothub))
-		return phy_roothub;
+	phy_roothub = devm_kzalloc(dev, sizeof(*phy_roothub), GFP_KERNEL);
+	if (!phy_roothub)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&phy_roothub->list);
 
 	for (i = 0; i < num_phys; i++) {
 		err = usb_phy_roothub_add_phy(dev, i, &phy_roothub->list);
 		if (err)
-			goto err_out;
+			return ERR_PTR(err);
 	}
 
+	return phy_roothub;
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_alloc);
+
+int usb_phy_roothub_init(struct usb_phy_roothub *phy_roothub)
+{
+	struct usb_phy_roothub *roothub_entry;
+	struct list_head *head;
+	int err;
+
+	if (!phy_roothub)
+		return 0;
+
 	head = &phy_roothub->list;
 
 	list_for_each_entry(roothub_entry, head, list) {
@@ -86,14 +91,13 @@ struct usb_phy_roothub *usb_phy_roothub_init(struct device *dev)
 			goto err_exit_phys;
 	}
 
-	return phy_roothub;
+	return 0;
 
 err_exit_phys:
 	list_for_each_entry_continue_reverse(roothub_entry, head, list)
 		phy_exit(roothub_entry->phy);
 
-err_out:
-	return ERR_PTR(err);
+	return err;
 }
 EXPORT_SYMBOL_GPL(usb_phy_roothub_init);
 
@@ -111,7 +115,7 @@ int usb_phy_roothub_exit(struct usb_phy_roothub *phy_roothub)
 	list_for_each_entry(roothub_entry, head, list) {
 		err = phy_exit(roothub_entry->phy);
 		if (err)
-			ret = ret;
+			ret = err;
 	}
 
 	return ret;
@@ -156,3 +160,38 @@ void usb_phy_roothub_power_off(struct usb_phy_roothub *phy_roothub)
 		phy_power_off(roothub_entry->phy);
 }
 EXPORT_SYMBOL_GPL(usb_phy_roothub_power_off);
+
+int usb_phy_roothub_suspend(struct device *controller_dev,
+			    struct usb_phy_roothub *phy_roothub)
+{
+	usb_phy_roothub_power_off(phy_roothub);
+
+	/* keep the PHYs initialized so the device can wake up the system */
+	if (device_may_wakeup(controller_dev))
+		return 0;
+
+	return usb_phy_roothub_exit(phy_roothub);
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_suspend);
+
+int usb_phy_roothub_resume(struct device *controller_dev,
+			   struct usb_phy_roothub *phy_roothub)
+{
+	int err;
+
+	/* if the device can't wake up the system _exit was called */
+	if (!device_may_wakeup(controller_dev)) {
+		err = usb_phy_roothub_init(phy_roothub);
+		if (err)
+			return err;
+	}
+
+	err = usb_phy_roothub_power_on(phy_roothub);
+
+	/* undo _init if _power_on failed */
+	if (err && !device_may_wakeup(controller_dev))
+		usb_phy_roothub_exit(phy_roothub);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_resume);
diff --git a/drivers/usb/core/phy.h b/drivers/usb/core/phy.h
index 6fde59bfbff8..88a3c037e9df 100644
--- a/drivers/usb/core/phy.h
+++ b/drivers/usb/core/phy.h
@@ -1,7 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * USB roothub wrapper
+ *
+ * Copyright (C) 2018 Martin Blumenstingl <martin.blumenstingl@googlemail.com>
+ */
+
+#ifndef __USB_CORE_PHY_H_
+#define __USB_CORE_PHY_H_
+
+struct device;
 struct usb_phy_roothub;
 
-struct usb_phy_roothub *usb_phy_roothub_init(struct device *dev);
+struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev);
+
+int usb_phy_roothub_init(struct usb_phy_roothub *phy_roothub);
 int usb_phy_roothub_exit(struct usb_phy_roothub *phy_roothub);
 
 int usb_phy_roothub_power_on(struct usb_phy_roothub *phy_roothub);
 void usb_phy_roothub_power_off(struct usb_phy_roothub *phy_roothub);
+
+int usb_phy_roothub_suspend(struct device *controller_dev,
+			    struct usb_phy_roothub *phy_roothub);
+int usb_phy_roothub_resume(struct device *controller_dev,
+			   struct usb_phy_roothub *phy_roothub);
+
+#endif /* __USB_CORE_PHY_H_ */
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index 6979bde87d31..4a2143195395 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -50,6 +50,28 @@ static ssize_t over_current_count_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(over_current_count);
 
+static ssize_t quirks_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	struct usb_port *port_dev = to_usb_port(dev);
+
+	return sprintf(buf, "%08x\n", port_dev->quirks);
+}
+
+static ssize_t quirks_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct usb_port *port_dev = to_usb_port(dev);
+	u32 value;
+
+	if (kstrtou32(buf, 16, &value))
+		return -EINVAL;
+
+	port_dev->quirks = value;
+	return count;
+}
+static DEVICE_ATTR_RW(quirks);
+
 static ssize_t usb3_lpm_permit_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
@@ -118,6 +140,7 @@ static DEVICE_ATTR_RW(usb3_lpm_permit);
 
 static struct attribute *port_dev_attrs[] = {
 	&dev_attr_connect_type.attr,
+	&dev_attr_quirks.attr,
 	&dev_attr_over_current_count.attr,
 	NULL,
 };
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 920f48a49a87..c55def2f1320 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -186,6 +186,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x03f0, 0x0701), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
 
+	/* HP v222w 16GB Mini USB Drive */
+	{ USB_DEVICE(0x03f0, 0x3f40), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index 27bb34043053..ea18284dfa9a 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -175,6 +175,26 @@ static ssize_t speed_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(speed);
 
+static ssize_t rx_lanes_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct usb_device *udev;
+
+	udev = to_usb_device(dev);
+	return sprintf(buf, "%d\n", udev->rx_lanes);
+}
+static DEVICE_ATTR_RO(rx_lanes);
+
+static ssize_t tx_lanes_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct usb_device *udev;
+
+	udev = to_usb_device(dev);
+	return sprintf(buf, "%d\n", udev->tx_lanes);
+}
+static DEVICE_ATTR_RO(tx_lanes);
+
 static ssize_t busnum_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
@@ -790,6 +810,8 @@ static struct attribute *dev_attrs[] = {
 	&dev_attr_bNumConfigurations.attr,
 	&dev_attr_bMaxPacketSize0.attr,
 	&dev_attr_speed.attr,
+	&dev_attr_rx_lanes.attr,
+	&dev_attr_tx_lanes.attr,
 	&dev_attr_busnum.attr,
 	&dev_attr_devnum.attr,
 	&dev_attr_devpath.attr,
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 0adb6345ff2e..623be3174fb3 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -1167,30 +1167,16 @@ static struct notifier_block usb_bus_nb = {
 struct dentry *usb_debug_root;
 EXPORT_SYMBOL_GPL(usb_debug_root);
 
-static struct dentry *usb_debug_devices;
-
-static int usb_debugfs_init(void)
+static void usb_debugfs_init(void)
 {
 	usb_debug_root = debugfs_create_dir("usb", NULL);
-	if (!usb_debug_root)
-		return -ENOENT;
-
-	usb_debug_devices = debugfs_create_file("devices", 0444,
-						usb_debug_root, NULL,
-						&usbfs_devices_fops);
-	if (!usb_debug_devices) {
-		debugfs_remove(usb_debug_root);
-		usb_debug_root = NULL;
-		return -ENOENT;
-	}
-
-	return 0;
+	debugfs_create_file("devices", 0444, usb_debug_root, NULL,
+			    &usbfs_devices_fops);
 }
 
 static void usb_debugfs_cleanup(void)
 {
-	debugfs_remove(usb_debug_devices);
-	debugfs_remove(usb_debug_root);
+	debugfs_remove_recursive(usb_debug_root);
 }
 
 /*
@@ -1205,9 +1191,7 @@ static int __init usb_init(void)
 	}
 	usb_init_pool_max();
 
-	retval = usb_debugfs_init();
-	if (retval)
-		goto out;
+	usb_debugfs_init();
 
 	usb_acpi_register();
 	retval = bus_register(&usb_bus_type);
diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c
index 18a0a1771289..1c36a6a9dd63 100644
--- a/drivers/usb/dwc2/core.c
+++ b/drivers/usb/dwc2/core.c
@@ -419,6 +419,8 @@ static void dwc2_wait_for_mode(struct dwc2_hsotg *hsotg,
 /**
  * dwc2_iddig_filter_enabled() - Returns true if the IDDIG debounce
  * filter is enabled.
+ *
+ * @hsotg: Programming view of DWC_otg controller
  */
 static bool dwc2_iddig_filter_enabled(struct dwc2_hsotg *hsotg)
 {
@@ -564,6 +566,9 @@ int dwc2_core_reset(struct dwc2_hsotg *hsotg, bool skip_wait)
  * If a force is done, it requires a IDDIG debounce filter delay if
  * the filter is configured and enabled. We poll the current mode of
  * the controller to account for this delay.
+ *
+ * @hsotg: Programming view of DWC_otg controller
+ * @host: Host mode flag
  */
 void dwc2_force_mode(struct dwc2_hsotg *hsotg, bool host)
 {
@@ -610,6 +615,8 @@ void dwc2_force_mode(struct dwc2_hsotg *hsotg, bool host)
  * or not because the value of the connector ID status is affected by
  * the force mode. We only need to call this once during probe if
  * dr_mode == OTG.
+ *
+ * @hsotg: Programming view of DWC_otg controller
  */
 static void dwc2_clear_force_mode(struct dwc2_hsotg *hsotg)
 {
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index d83be5651f87..4a56ac772a3c 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -164,12 +164,11 @@ struct dwc2_hsotg_req;
  *       and has yet to be completed (maybe due to data move, or simply
  *       awaiting an ack from the core all the data has been completed).
  * @debugfs: File entry for debugfs file for this endpoint.
- * @lock: State lock to protect contents of endpoint.
  * @dir_in: Set to true if this endpoint is of the IN direction, which
  *          means that it is sending data to the Host.
  * @index: The index for the endpoint registers.
  * @mc: Multi Count - number of transactions per microframe
- * @interval - Interval for periodic endpoints, in frames or microframes.
+ * @interval: Interval for periodic endpoints, in frames or microframes.
  * @name: The name array passed to the USB core.
  * @halted: Set if the endpoint has been halted.
  * @periodic: Set if this is a periodic ep, such as Interrupt
@@ -178,10 +177,11 @@ struct dwc2_hsotg_req;
  * @desc_list_dma: The DMA address of descriptor chain currently in use.
  * @desc_list: Pointer to descriptor DMA chain head currently in use.
  * @desc_count: Count of entries within the DMA descriptor chain of EP.
- * @isoc_chain_num: Number of ISOC chain currently in use - either 0 or 1.
  * @next_desc: index of next free descriptor in the ISOC chain under SW control.
+ * @compl_desc: index of next descriptor to be completed by xFerComplete
  * @total_data: The total number of data bytes done.
  * @fifo_size: The size of the FIFO (for periodic IN endpoints)
+ * @fifo_index: For Dedicated FIFO operation, only FIFO0 can be used for EP0.
  * @fifo_load: The amount of data loaded into the FIFO (periodic IN)
  * @last_load: The offset of data for the last start of request.
  * @size_loaded: The last loaded size for DxEPTSIZE for periodic IN
@@ -231,8 +231,8 @@ struct dwc2_hsotg_ep {
 	struct dwc2_dma_desc	*desc_list;
 	u8			desc_count;
 
-	unsigned char		isoc_chain_num;
 	unsigned int		next_desc;
+	unsigned int		compl_desc;
 
 	char                    name[10];
 };
@@ -380,6 +380,12 @@ enum dwc2_ep0_state {
  *                      is FS.
  *                       0 - No (default)
  *                       1 - Yes
+ * @ipg_isoc_en:        Indicates the IPG supports is enabled or disabled.
+ *                       0 - Disable (default)
+ *                       1 - Enable
+ * @acg_enable:		For enabling Active Clock Gating in the controller
+ *                       0 - No
+ *                       1 - Yes
  * @ulpi_fs_ls:         Make ULPI phy operate in FS/LS mode only
  *                       0 - No (default)
  *                       1 - Yes
@@ -511,6 +517,7 @@ struct dwc2_core_params {
 	bool hird_threshold_en;
 	u8 hird_threshold;
 	bool activate_stm_fs_transceiver;
+	bool ipg_isoc_en;
 	u16 max_packet_count;
 	u32 max_transfer_size;
 	u32 ahbcfg;
@@ -548,7 +555,7 @@ struct dwc2_core_params {
  *
  * The values that are not in dwc2_core_params are documented below.
  *
- * @op_mode             Mode of Operation
+ * @op_mode:             Mode of Operation
  *                       0 - HNP- and SRP-Capable OTG (Host & Device)
  *                       1 - SRP-Capable OTG (Host & Device)
  *                       2 - Non-HNP and Non-SRP Capable OTG (Host & Device)
@@ -556,43 +563,102 @@ struct dwc2_core_params {
  *                       4 - Non-OTG Device
  *                       5 - SRP-Capable Host
  *                       6 - Non-OTG Host
- * @arch                Architecture
+ * @arch:                Architecture
  *                       0 - Slave only
  *                       1 - External DMA
  *                       2 - Internal DMA
- * @power_optimized     Are power optimizations enabled?
- * @num_dev_ep          Number of device endpoints available
- * @num_dev_in_eps      Number of device IN endpoints available
- * @num_dev_perio_in_ep Number of device periodic IN endpoints
- *                      available
- * @dev_token_q_depth   Device Mode IN Token Sequence Learning Queue
+ * @ipg_isoc_en:        This feature indicates that the controller supports
+ *                      the worst-case scenario of Rx followed by Rx
+ *                      Interpacket Gap (IPG) (32 bitTimes) as per the utmi
+ *                      specification for any token following ISOC OUT token.
+ *                       0 - Don't support
+ *                       1 - Support
+ * @power_optimized:    Are power optimizations enabled?
+ * @num_dev_ep:         Number of device endpoints available
+ * @num_dev_in_eps:     Number of device IN endpoints available
+ * @num_dev_perio_in_ep: Number of device periodic IN endpoints
+ *                       available
+ * @dev_token_q_depth:  Device Mode IN Token Sequence Learning Queue
  *                      Depth
  *                       0 to 30
- * @host_perio_tx_q_depth
+ * @host_perio_tx_q_depth:
  *                      Host Mode Periodic Request Queue Depth
  *                       2, 4 or 8
- * @nperio_tx_q_depth
+ * @nperio_tx_q_depth:
  *                      Non-Periodic Request Queue Depth
  *                       2, 4 or 8
- * @hs_phy_type         High-speed PHY interface type
+ * @hs_phy_type:         High-speed PHY interface type
  *                       0 - High-speed interface not supported
  *                       1 - UTMI+
  *                       2 - ULPI
  *                       3 - UTMI+ and ULPI
- * @fs_phy_type         Full-speed PHY interface type
+ * @fs_phy_type:         Full-speed PHY interface type
  *                       0 - Full speed interface not supported
  *                       1 - Dedicated full speed interface
  *                       2 - FS pins shared with UTMI+ pins
  *                       3 - FS pins shared with ULPI pins
  * @total_fifo_size:    Total internal RAM for FIFOs (bytes)
- * @hibernation		Is hibernation enabled?
- * @utmi_phy_data_width UTMI+ PHY data width
+ * @hibernation:	Is hibernation enabled?
+ * @utmi_phy_data_width: UTMI+ PHY data width
  *                       0 - 8 bits
  *                       1 - 16 bits
  *                       2 - 8 or 16 bits
  * @snpsid:             Value from SNPSID register
  * @dev_ep_dirs:        Direction of device endpoints (GHWCFG1)
- * @g_tx_fifo_size[]	Power-on values of TxFIFO sizes
+ * @g_tx_fifo_size:	Power-on values of TxFIFO sizes
+ * @dma_desc_enable:    When DMA mode is enabled, specifies whether to use
+ *                      address DMA mode or descriptor DMA mode for accessing
+ *                      the data FIFOs. The driver will automatically detect the
+ *                      value for this if none is specified.
+ *                       0 - Address DMA
+ *                       1 - Descriptor DMA (default, if available)
+ * @enable_dynamic_fifo: 0 - Use coreConsultant-specified FIFO size parameters
+ *                       1 - Allow dynamic FIFO sizing (default, if available)
+ * @en_multiple_tx_fifo: Specifies whether dedicated per-endpoint transmit FIFOs
+ *                      are enabled for non-periodic IN endpoints in device
+ *                      mode.
+ * @host_nperio_tx_fifo_size: Number of 4-byte words in the non-periodic Tx FIFO
+ *                      in host mode when dynamic FIFO sizing is enabled
+ *                       16 to 32768
+ *                      Actual maximum value is autodetected and also
+ *                      the default.
+ * @host_perio_tx_fifo_size: Number of 4-byte words in the periodic Tx FIFO in
+ *                      host mode when dynamic FIFO sizing is enabled
+ *                       16 to 32768
+ *                      Actual maximum value is autodetected and also
+ *                      the default.
+ * @max_transfer_size:  The maximum transfer size supported, in bytes
+ *                       2047 to 65,535
+ *                      Actual maximum value is autodetected and also
+ *                      the default.
+ * @max_packet_count:   The maximum number of packets in a transfer
+ *                       15 to 511
+ *                      Actual maximum value is autodetected and also
+ *                      the default.
+ * @host_channels:      The number of host channel registers to use
+ *                       1 to 16
+ *                      Actual maximum value is autodetected and also
+ *                      the default.
+ * @dev_nperio_tx_fifo_size: Number of 4-byte words in the non-periodic Tx FIFO
+ *			     in device mode when dynamic FIFO sizing is enabled
+ *			     16 to 32768
+ *			     Actual maximum value is autodetected and also
+ *			     the default.
+ * @i2c_enable:         Specifies whether to use the I2Cinterface for a full
+ *                      speed PHY. This parameter is only applicable if phy_type
+ *                      is FS.
+ *                       0 - No (default)
+ *                       1 - Yes
+ * @acg_enable:		For enabling Active Clock Gating in the controller
+ *                       0 - Disable
+ *                       1 - Enable
+ * @lpm_mode:		For enabling Link Power Management in the controller
+ *                       0 - Disable
+ *                       1 - Enable
+ * @rx_fifo_size:	Number of 4-byte words in the  Rx FIFO when dynamic
+ *			FIFO sizing is enabled 16 to 32768
+ *			Actual maximum value is autodetected and also
+ *			the default.
  */
 struct dwc2_hw_params {
 	unsigned op_mode:3;
@@ -622,6 +688,7 @@ struct dwc2_hw_params {
 	unsigned hibernation:1;
 	unsigned utmi_phy_data_width:2;
 	unsigned lpm_mode:1;
+	unsigned ipg_isoc_en:1;
 	u32 snpsid;
 	u32 dev_ep_dirs;
 	u32 g_tx_fifo_size[MAX_EPS_CHANNELS];
@@ -642,7 +709,11 @@ struct dwc2_hw_params {
  * @gi2cctl:		Backup of GI2CCTL register
  * @glpmcfg:		Backup of GLPMCFG register
  * @gdfifocfg:		Backup of GDFIFOCFG register
+ * @pcgcctl:		Backup of PCGCCTL register
+ * @pcgcctl1:		Backup of PCGCCTL1 register
+ * @dtxfsiz:		Backup of DTXFSIZ registers for each endpoint
  * @gpwrdn:		Backup of GPWRDN register
+ * @valid:		True if registers values backuped.
  */
 struct dwc2_gregs_backup {
 	u32 gotgctl;
@@ -675,6 +746,7 @@ struct dwc2_gregs_backup {
  * @doeptsiz:		Backup of DOEPTSIZ register
  * @doepdma:		Backup of DOEPDMA register
  * @dtxfsiz:		Backup of DTXFSIZ registers for each endpoint
+ * @valid:      True if registers values backuped.
  */
 struct dwc2_dregs_backup {
 	u32 dcfg;
@@ -698,9 +770,10 @@ struct dwc2_dregs_backup {
  * @hcfg:		Backup of HCFG register
  * @haintmsk:		Backup of HAINTMSK register
  * @hcintmsk:		Backup of HCINTMSK register
- * @hptr0:		Backup of HPTR0 register
+ * @hprt0:		Backup of HPTR0 register
  * @hfir:		Backup of HFIR register
  * @hptxfsiz:		Backup of HPTXFSIZ register
+ * @valid:      True if registers values backuped.
  */
 struct dwc2_hregs_backup {
 	u32 hcfg;
@@ -800,7 +873,7 @@ struct dwc2_hregs_backup {
  * @regs:		Pointer to controller regs
  * @hw_params:          Parameters that were autodetected from the
  *                      hardware registers
- * @core_params:	Parameters that define how the core should be configured
+ * @params:	Parameters that define how the core should be configured
  * @op_state:           The operational State, during transitions (a_host=>
  *                      a_peripheral and b_device=>b_host) this may not match
  *                      the core, but allows the software to determine
@@ -809,10 +882,13 @@ struct dwc2_hregs_backup {
  *                      - USB_DR_MODE_PERIPHERAL
  *                      - USB_DR_MODE_HOST
  *                      - USB_DR_MODE_OTG
- * @hcd_enabled		Host mode sub-driver initialization indicator.
- * @gadget_enabled	Peripheral mode sub-driver initialization indicator.
- * @ll_hw_enabled	Status of low-level hardware resources.
+ * @hcd_enabled:	Host mode sub-driver initialization indicator.
+ * @gadget_enabled:	Peripheral mode sub-driver initialization indicator.
+ * @ll_hw_enabled:	Status of low-level hardware resources.
  * @hibernated:		True if core is hibernated
+ * @frame_number:       Frame number read from the core. For both device
+ *			and host modes. The value ranges are from 0
+ *			to HFNUM_MAX_FRNUM.
  * @phy:                The otg phy transceiver structure for phy control.
  * @uphy:               The otg phy transceiver structure for old USB phy
  *                      control.
@@ -832,13 +908,25 @@ struct dwc2_hregs_backup {
  *                      interrupt
  * @wkp_timer:          Timer object for handling Wakeup Detected interrupt
  * @lx_state:           Lx state of connected device
- * @gregs_backup: Backup of global registers during suspend
- * @dregs_backup: Backup of device registers during suspend
- * @hregs_backup: Backup of host registers during suspend
+ * @gr_backup: Backup of global registers during suspend
+ * @dr_backup: Backup of device registers during suspend
+ * @hr_backup: Backup of host registers during suspend
  *
  * These are for host mode:
  *
  * @flags:              Flags for handling root port state changes
+ * @flags.d32:          Contain all root port flags
+ * @flags.b:            Separate root port flags from each other
+ * @flags.b.port_connect_status_change: True if root port connect status
+ *                      changed
+ * @flags.b.port_connect_status: True if device connected to root port
+ * @flags.b.port_reset_change: True if root port reset status changed
+ * @flags.b.port_enable_change: True if root port enable status changed
+ * @flags.b.port_suspend_change: True if root port suspend status changed
+ * @flags.b.port_over_current_change: True if root port over current state
+ *                       changed.
+ * @flags.b.port_l1_change: True if root port l1 status changed
+ * @flags.b.reserved:   Reserved bits of root port register
  * @non_periodic_sched_inactive: Inactive QHs in the non-periodic schedule.
  *                      Transfers associated with these QHs are not currently
  *                      assigned to a host channel.
@@ -847,6 +935,9 @@ struct dwc2_hregs_backup {
  *                      assigned to a host channel.
  * @non_periodic_qh_ptr: Pointer to next QH to process in the active
  *                      non-periodic schedule
+ * @non_periodic_sched_waiting: Waiting QHs in the non-periodic schedule.
+ *                      Transfers associated with these QHs are not currently
+ *                      assigned to a host channel.
  * @periodic_sched_inactive: Inactive QHs in the periodic schedule. This is a
  *                      list of QHs for periodic transfers that are _not_
  *                      scheduled for the next frame. Each QH in the list has an
@@ -886,8 +977,6 @@ struct dwc2_hregs_backup {
  * @hs_periodic_bitmap: Bitmap used by the microframe scheduler any time the
  *                      host is in high speed mode; low speed schedules are
  *                      stored elsewhere since we need one per TT.
- * @frame_number:       Frame number read from the core at SOF. The value ranges
- *                      from 0 to HFNUM_MAX_FRNUM.
  * @periodic_qh_count:  Count of periodic QHs, if using several eps. Used for
  *                      SOF enable/disable.
  * @free_hc_list:       Free host channels in the controller. This is a list of
@@ -898,8 +987,8 @@ struct dwc2_hregs_backup {
  *                      host channel is available for non-periodic transactions.
  * @non_periodic_channels: Number of host channels assigned to non-periodic
  *                      transfers
- * @available_host_channels Number of host channels available for the microframe
- *                      scheduler to use
+ * @available_host_channels: Number of host channels available for the
+ *			     microframe scheduler to use
  * @hc_ptr_array:       Array of pointers to the host channel descriptors.
  *                      Allows accessing a host channel descriptor given the
  *                      host channel number. This is useful in interrupt
@@ -922,9 +1011,6 @@ struct dwc2_hregs_backup {
  * @dedicated_fifos:    Set if the hardware has dedicated IN-EP fifos.
  * @num_of_eps:         Number of available EPs (excluding EP0)
  * @debug_root:         Root directrory for debugfs.
- * @debug_file:         Main status file for debugfs.
- * @debug_testmode:     Testmode status file for debugfs.
- * @debug_fifo:         FIFO status file for debugfs.
  * @ep0_reply:          Request used for ep0 reply.
  * @ep0_buff:           Buffer for EP0 reply data, if needed.
  * @ctrl_buff:          Buffer for EP0 control requests.
@@ -939,7 +1025,37 @@ struct dwc2_hregs_backup {
  * @ctrl_in_desc:	EP0 IN data phase desc chain pointer
  * @ctrl_out_desc_dma:	EP0 OUT data phase desc chain DMA address
  * @ctrl_out_desc:	EP0 OUT data phase desc chain pointer
- * @eps:                The endpoints being supplied to the gadget framework
+ * @irq:		Interrupt request line number
+ * @clk:		Pointer to otg clock
+ * @reset:		Pointer to dwc2 reset controller
+ * @reset_ecc:          Pointer to dwc2 optional reset controller in Stratix10.
+ * @regset:		A pointer to a struct debugfs_regset32, which contains
+ *			a pointer to an array of register definitions, the
+ *			array size and the base address where the register bank
+ *			is to be found.
+ * @bus_suspended:	True if bus is suspended
+ * @last_frame_num:	Number of last frame. Range from 0 to  32768
+ * @frame_num_array:    Used only  if CONFIG_USB_DWC2_TRACK_MISSED_SOFS is
+ *			defined, for missed SOFs tracking. Array holds that
+ *			frame numbers, which not equal to last_frame_num +1
+ * @last_frame_num_array:   Used only  if CONFIG_USB_DWC2_TRACK_MISSED_SOFS is
+ *			    defined, for missed SOFs tracking.
+ *			    If current_frame_number != last_frame_num+1
+ *			    then last_frame_num added to this array
+ * @frame_num_idx:	Actual size of frame_num_array and last_frame_num_array
+ * @dumped_frame_num_array:	1 - if missed SOFs frame numbers dumbed
+ *				0 - if missed SOFs frame numbers not dumbed
+ * @fifo_mem:			Total internal RAM for FIFOs (bytes)
+ * @fifo_map:		Each bit intend for concrete fifo. If that bit is set,
+ *			then that fifo is used
+ * @gadget:		Represents a usb slave device
+ * @connected:		Used in slave mode. True if device connected with host
+ * @eps_in:		The IN endpoints being supplied to the gadget framework
+ * @eps_out:		The OUT endpoints being supplied to the gadget framework
+ * @new_connection:	Used in host mode. True if there are new connected
+ *			device
+ * @enabled:		Indicates the enabling state of controller
+ *
  */
 struct dwc2_hsotg {
 	struct device *dev;
@@ -954,6 +1070,7 @@ struct dwc2_hsotg {
 	unsigned int gadget_enabled:1;
 	unsigned int ll_hw_enabled:1;
 	unsigned int hibernated:1;
+	u16 frame_number;
 
 	struct phy *phy;
 	struct usb_phy *uphy;
@@ -985,6 +1102,7 @@ struct dwc2_hsotg {
 
 	/* DWC OTG HW Release versions */
 #define DWC2_CORE_REV_2_71a	0x4f54271a
+#define DWC2_CORE_REV_2_72a     0x4f54272a
 #define DWC2_CORE_REV_2_80a	0x4f54280a
 #define DWC2_CORE_REV_2_90a	0x4f54290a
 #define DWC2_CORE_REV_2_91a	0x4f54291a
@@ -992,6 +1110,7 @@ struct dwc2_hsotg {
 #define DWC2_CORE_REV_2_94a	0x4f54294a
 #define DWC2_CORE_REV_3_00a	0x4f54300a
 #define DWC2_CORE_REV_3_10a	0x4f54310a
+#define DWC2_CORE_REV_4_00a	0x4f54400a
 #define DWC2_FS_IOT_REV_1_00a	0x5531100a
 #define DWC2_HS_IOT_REV_1_00a	0x5532100a
 
@@ -1027,7 +1146,6 @@ struct dwc2_hsotg {
 	u16 periodic_usecs;
 	unsigned long hs_periodic_bitmap[
 		DIV_ROUND_UP(DWC2_HS_SCHEDULE_US, BITS_PER_LONG)];
-	u16 frame_number;
 	u16 periodic_qh_count;
 	bool bus_suspended;
 	bool new_connection;
diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c
index 2982a155734d..cc90b58b6b3c 100644
--- a/drivers/usb/dwc2/core_intr.c
+++ b/drivers/usb/dwc2/core_intr.c
@@ -778,6 +778,14 @@ irqreturn_t dwc2_handle_common_intr(int irq, void *dev)
 		goto out;
 	}
 
+	/* Reading current frame number value in device or host modes. */
+	if (dwc2_is_device_mode(hsotg))
+		hsotg->frame_number = (dwc2_readl(hsotg->regs + DSTS)
+				       & DSTS_SOFFN_MASK) >> DSTS_SOFFN_SHIFT;
+	else
+		hsotg->frame_number = (dwc2_readl(hsotg->regs + HFNUM)
+				       & HFNUM_FRNUM_MASK) >> HFNUM_FRNUM_SHIFT;
+
 	gintsts = dwc2_read_common_intr(hsotg);
 	if (gintsts & ~GINTSTS_PRTINT)
 		retval = IRQ_HANDLED;
diff --git a/drivers/usb/dwc2/debug.h b/drivers/usb/dwc2/debug.h
index 6f23219c13cb..a8c565b6bc34 100644
--- a/drivers/usb/dwc2/debug.h
+++ b/drivers/usb/dwc2/debug.h
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * debug.h - Designware USB2 DRD controller debug header
  *
  * Copyright (C) 2015 Intel Corporation
diff --git a/drivers/usb/dwc2/debugfs.c b/drivers/usb/dwc2/debugfs.c
index 58c691f882a8..d0bdb7997557 100644
--- a/drivers/usb/dwc2/debugfs.c
+++ b/drivers/usb/dwc2/debugfs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * debugfs.c - Designware USB2 DRD controller debugfs
  *
  * Copyright (C) 2015 Intel Corporation
@@ -16,12 +16,13 @@
 
 #if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \
 	IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE)
+
 /**
- * testmode_write - debugfs: change usb test mode
- * @seq: The seq file to write to.
- * @v: Unused parameter.
- *
- * This debugfs entry modify the current usb test mode.
+ * testmode_write() - change usb test mode state.
+ * @file: The  file to write to.
+ * @ubuf: The buffer where user wrote.
+ * @count: The ubuf size.
+ * @ppos: Unused parameter.
  */
 static ssize_t testmode_write(struct file *file, const char __user *ubuf, size_t
 		count, loff_t *ppos)
@@ -55,9 +56,9 @@ static ssize_t testmode_write(struct file *file, const char __user *ubuf, size_t
 }
 
 /**
- * testmode_show - debugfs: show usb test mode state
- * @seq: The seq file to write to.
- * @v: Unused parameter.
+ * testmode_show() - debugfs: show usb test mode state
+ * @s: The seq file to write to.
+ * @unused: Unused parameter.
  *
  * This debugfs entry shows which usb test mode is currently enabled.
  */
@@ -293,52 +294,30 @@ DEFINE_SHOW_ATTRIBUTE(ep);
 static void dwc2_hsotg_create_debug(struct dwc2_hsotg *hsotg)
 {
 	struct dentry *root;
-	struct dentry *file;
 	unsigned int epidx;
 
 	root = hsotg->debug_root;
 
 	/* create general state file */
-
-	file = debugfs_create_file("state", 0444, root, hsotg, &state_fops);
-	if (IS_ERR(file))
-		dev_err(hsotg->dev, "%s: failed to create state\n", __func__);
-
-	file = debugfs_create_file("testmode", 0644, root, hsotg,
-				   &testmode_fops);
-	if (IS_ERR(file))
-		dev_err(hsotg->dev, "%s: failed to create testmode\n",
-			__func__);
-
-	file = debugfs_create_file("fifo", 0444, root, hsotg, &fifo_fops);
-	if (IS_ERR(file))
-		dev_err(hsotg->dev, "%s: failed to create fifo\n", __func__);
+	debugfs_create_file("state", 0444, root, hsotg, &state_fops);
+	debugfs_create_file("testmode", 0644, root, hsotg, &testmode_fops);
+	debugfs_create_file("fifo", 0444, root, hsotg, &fifo_fops);
 
 	/* Create one file for each out endpoint */
 	for (epidx = 0; epidx < hsotg->num_of_eps; epidx++) {
 		struct dwc2_hsotg_ep *ep;
 
 		ep = hsotg->eps_out[epidx];
-		if (ep) {
-			file = debugfs_create_file(ep->name, 0444,
-						   root, ep, &ep_fops);
-			if (IS_ERR(file))
-				dev_err(hsotg->dev, "failed to create %s debug file\n",
-					ep->name);
-		}
+		if (ep)
+			debugfs_create_file(ep->name, 0444, root, ep, &ep_fops);
 	}
 	/* Create one file for each in endpoint. EP0 is handled with out eps */
 	for (epidx = 1; epidx < hsotg->num_of_eps; epidx++) {
 		struct dwc2_hsotg_ep *ep;
 
 		ep = hsotg->eps_in[epidx];
-		if (ep) {
-			file = debugfs_create_file(ep->name, 0444,
-						   root, ep, &ep_fops);
-			if (IS_ERR(file))
-				dev_err(hsotg->dev, "failed to create %s debug file\n",
-					ep->name);
-		}
+		if (ep)
+			debugfs_create_file(ep->name, 0444, root, ep, &ep_fops);
 	}
 }
 #else
@@ -368,7 +347,7 @@ static const struct debugfs_reg32 dwc2_regs[] = {
 	dump_register(GINTSTS),
 	dump_register(GINTMSK),
 	dump_register(GRXSTSR),
-	dump_register(GRXSTSP),
+	/* Omit GRXSTSP */
 	dump_register(GRXFSIZ),
 	dump_register(GNPTXFSIZ),
 	dump_register(GNPTXSTS),
@@ -710,6 +689,7 @@ static int params_show(struct seq_file *seq, void *v)
 	print_param(seq, p, phy_ulpi_ddr);
 	print_param(seq, p, phy_ulpi_ext_vbus);
 	print_param(seq, p, i2c_enable);
+	print_param(seq, p, ipg_isoc_en);
 	print_param(seq, p, ulpi_fs_ls);
 	print_param(seq, p, host_support_fs_ls_low_power);
 	print_param(seq, p, host_ls_low_power_phy_clk);
@@ -790,32 +770,14 @@ DEFINE_SHOW_ATTRIBUTE(dr_mode);
 int dwc2_debugfs_init(struct dwc2_hsotg *hsotg)
 {
 	int			ret;
-	struct dentry		*file;
+	struct dentry		*root;
 
-	hsotg->debug_root = debugfs_create_dir(dev_name(hsotg->dev), NULL);
-	if (!hsotg->debug_root) {
-		ret = -ENOMEM;
-		goto err0;
-	}
+	root = debugfs_create_dir(dev_name(hsotg->dev), NULL);
+	hsotg->debug_root = root;
 
-	file = debugfs_create_file("params", 0444,
-				   hsotg->debug_root,
-				   hsotg, &params_fops);
-	if (IS_ERR(file))
-		dev_err(hsotg->dev, "%s: failed to create params\n", __func__);
-
-	file = debugfs_create_file("hw_params", 0444,
-				   hsotg->debug_root,
-				   hsotg, &hw_params_fops);
-	if (IS_ERR(file))
-		dev_err(hsotg->dev, "%s: failed to create hw_params\n",
-			__func__);
-
-	file = debugfs_create_file("dr_mode", 0444,
-				   hsotg->debug_root,
-				   hsotg, &dr_mode_fops);
-	if (IS_ERR(file))
-		dev_err(hsotg->dev, "%s: failed to create dr_mode\n", __func__);
+	debugfs_create_file("params", 0444, root, hsotg, &params_fops);
+	debugfs_create_file("hw_params", 0444, root, hsotg, &hw_params_fops);
+	debugfs_create_file("dr_mode", 0444, root, hsotg, &dr_mode_fops);
 
 	/* Add gadget debugfs nodes */
 	dwc2_hsotg_create_debug(hsotg);
@@ -824,24 +786,18 @@ int dwc2_debugfs_init(struct dwc2_hsotg *hsotg)
 								GFP_KERNEL);
 	if (!hsotg->regset) {
 		ret = -ENOMEM;
-		goto err1;
+		goto err;
 	}
 
 	hsotg->regset->regs = dwc2_regs;
 	hsotg->regset->nregs = ARRAY_SIZE(dwc2_regs);
 	hsotg->regset->base = hsotg->regs;
 
-	file = debugfs_create_regset32("regdump", 0444, hsotg->debug_root,
-				       hsotg->regset);
-	if (!file) {
-		ret = -ENOMEM;
-		goto err1;
-	}
+	debugfs_create_regset32("regdump", 0444, root, hsotg->regset);
 
 	return 0;
-err1:
+err:
 	debugfs_remove_recursive(hsotg->debug_root);
-err0:
 	return ret;
 }
 
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 6c32bf26e48e..f0d9ccf1d665 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
@@ -107,7 +107,6 @@ static inline bool using_desc_dma(struct dwc2_hsotg *hsotg)
 /**
  * dwc2_gadget_incr_frame_num - Increments the targeted frame number.
  * @hs_ep: The endpoint
- * @increment: The value to increment by
  *
  * This function will also check if the frame number overruns DSTS_SOFFN_LIMIT.
  * If an overrun occurs it will wrap the value and set the frame_overrun flag.
@@ -190,6 +189,8 @@ static void dwc2_hsotg_ctrl_epint(struct dwc2_hsotg *hsotg,
 
 /**
  * dwc2_hsotg_tx_fifo_count - return count of TX FIFOs in device mode
+ *
+ * @hsotg: Programming view of the DWC_otg controller
  */
 int dwc2_hsotg_tx_fifo_count(struct dwc2_hsotg *hsotg)
 {
@@ -204,6 +205,8 @@ int dwc2_hsotg_tx_fifo_count(struct dwc2_hsotg *hsotg)
 /**
  * dwc2_hsotg_tx_fifo_total_depth - return total FIFO depth available for
  * device mode TX FIFOs
+ *
+ * @hsotg: Programming view of the DWC_otg controller
  */
 int dwc2_hsotg_tx_fifo_total_depth(struct dwc2_hsotg *hsotg)
 {
@@ -227,6 +230,8 @@ int dwc2_hsotg_tx_fifo_total_depth(struct dwc2_hsotg *hsotg)
 /**
  * dwc2_hsotg_tx_fifo_average_depth - returns average depth of device mode
  * TX FIFOs
+ *
+ * @hsotg: Programming view of the DWC_otg controller
  */
 int dwc2_hsotg_tx_fifo_average_depth(struct dwc2_hsotg *hsotg)
 {
@@ -327,6 +332,7 @@ static void dwc2_hsotg_init_fifo(struct dwc2_hsotg *hsotg)
 }
 
 /**
+ * dwc2_hsotg_ep_alloc_request - allocate USB rerequest structure
  * @ep: USB endpoint to allocate request for.
  * @flags: Allocation flags
  *
@@ -793,9 +799,7 @@ static void dwc2_gadget_config_nonisoc_xfer_ddma(struct dwc2_hsotg_ep *hs_ep,
  * @dma_buff: usb requests dma buffer.
  * @len: usb request transfer length.
  *
- * Finds out index of first free entry either in the bottom or up half of
- * descriptor chain depend on which is under SW control and not processed
- * by HW. Then fills that descriptor with the data of the arrived usb request,
+ * Fills next free descriptor with the data of the arrived usb request,
  * frame info, sets Last and IOC bits increments next_desc. If filled
  * descriptor is not the first one, removes L bit from the previous descriptor
  * status.
@@ -810,34 +814,17 @@ static int dwc2_gadget_fill_isoc_desc(struct dwc2_hsotg_ep *hs_ep,
 	u32 mask = 0;
 
 	maxsize = dwc2_gadget_get_desc_params(hs_ep, &mask);
-	if (len > maxsize) {
-		dev_err(hsotg->dev, "wrong len %d\n", len);
-		return -EINVAL;
-	}
-
-	/*
-	 * If SW has already filled half of chain, then return and wait for
-	 * the other chain to be processed by HW.
-	 */
-	if (hs_ep->next_desc == MAX_DMA_DESC_NUM_GENERIC / 2)
-		return -EBUSY;
-
-	/* Increment frame number by interval for IN */
-	if (hs_ep->dir_in)
-		dwc2_gadget_incr_frame_num(hs_ep);
 
-	index = (MAX_DMA_DESC_NUM_GENERIC / 2) * hs_ep->isoc_chain_num +
-		 hs_ep->next_desc;
+	index = hs_ep->next_desc;
+	desc = &hs_ep->desc_list[index];
 
-	/* Sanity check of calculated index */
-	if ((hs_ep->isoc_chain_num && index > MAX_DMA_DESC_NUM_GENERIC) ||
-	    (!hs_ep->isoc_chain_num && index > MAX_DMA_DESC_NUM_GENERIC / 2)) {
-		dev_err(hsotg->dev, "wrong index %d for iso chain\n", index);
-		return -EINVAL;
+	/* Check if descriptor chain full */
+	if ((desc->status >> DEV_DMA_BUFF_STS_SHIFT) ==
+	    DEV_DMA_BUFF_STS_HREADY) {
+		dev_dbg(hsotg->dev, "%s: desc chain full\n", __func__);
+		return 1;
 	}
 
-	desc = &hs_ep->desc_list[index];
-
 	/* Clear L bit of previous desc if more than one entries in the chain */
 	if (hs_ep->next_desc)
 		hs_ep->desc_list[index - 1].status &= ~DEV_DMA_L;
@@ -865,8 +852,14 @@ static int dwc2_gadget_fill_isoc_desc(struct dwc2_hsotg_ep *hs_ep,
 	desc->status &= ~DEV_DMA_BUFF_STS_MASK;
 	desc->status |= (DEV_DMA_BUFF_STS_HREADY << DEV_DMA_BUFF_STS_SHIFT);
 
+	/* Increment frame number by interval for IN */
+	if (hs_ep->dir_in)
+		dwc2_gadget_incr_frame_num(hs_ep);
+
 	/* Update index of last configured entry in the chain */
 	hs_ep->next_desc++;
+	if (hs_ep->next_desc >= MAX_DMA_DESC_NUM_GENERIC)
+		hs_ep->next_desc = 0;
 
 	return 0;
 }
@@ -875,11 +868,8 @@ static int dwc2_gadget_fill_isoc_desc(struct dwc2_hsotg_ep *hs_ep,
  * dwc2_gadget_start_isoc_ddma - start isochronous transfer in DDMA
  * @hs_ep: The isochronous endpoint.
  *
- * Prepare first descriptor chain for isochronous endpoints. Afterwards
+ * Prepare descriptor chain for isochronous endpoints. Afterwards
  * write DMA address to HW and enable the endpoint.
- *
- * Switch between descriptor chains via isoc_chain_num to give SW opportunity
- * to prepare second descriptor chain while first one is being processed by HW.
  */
 static void dwc2_gadget_start_isoc_ddma(struct dwc2_hsotg_ep *hs_ep)
 {
@@ -887,24 +877,34 @@ static void dwc2_gadget_start_isoc_ddma(struct dwc2_hsotg_ep *hs_ep)
 	struct dwc2_hsotg_req *hs_req, *treq;
 	int index = hs_ep->index;
 	int ret;
+	int i;
 	u32 dma_reg;
 	u32 depctl;
 	u32 ctrl;
+	struct dwc2_dma_desc *desc;
 
 	if (list_empty(&hs_ep->queue)) {
 		dev_dbg(hsotg->dev, "%s: No requests in queue\n", __func__);
 		return;
 	}
 
+	/* Initialize descriptor chain by Host Busy status */
+	for (i = 0; i < MAX_DMA_DESC_NUM_GENERIC; i++) {
+		desc = &hs_ep->desc_list[i];
+		desc->status = 0;
+		desc->status |= (DEV_DMA_BUFF_STS_HBUSY
+				    << DEV_DMA_BUFF_STS_SHIFT);
+	}
+
+	hs_ep->next_desc = 0;
 	list_for_each_entry_safe(hs_req, treq, &hs_ep->queue, queue) {
 		ret = dwc2_gadget_fill_isoc_desc(hs_ep, hs_req->req.dma,
 						 hs_req->req.length);
-		if (ret) {
-			dev_dbg(hsotg->dev, "%s: desc chain full\n", __func__);
+		if (ret)
 			break;
-		}
 	}
 
+	hs_ep->compl_desc = 0;
 	depctl = hs_ep->dir_in ? DIEPCTL(index) : DOEPCTL(index);
 	dma_reg = hs_ep->dir_in ? DIEPDMA(index) : DOEPDMA(index);
 
@@ -914,10 +914,6 @@ static void dwc2_gadget_start_isoc_ddma(struct dwc2_hsotg_ep *hs_ep)
 	ctrl = dwc2_readl(hsotg->regs + depctl);
 	ctrl |= DXEPCTL_EPENA | DXEPCTL_CNAK;
 	dwc2_writel(ctrl, hsotg->regs + depctl);
-
-	/* Switch ISOC descriptor chain number being processed by SW*/
-	hs_ep->isoc_chain_num = (hs_ep->isoc_chain_num ^ 1) & 0x1;
-	hs_ep->next_desc = 0;
 }
 
 /**
@@ -1235,7 +1231,7 @@ static bool dwc2_gadget_target_frame_elapsed(struct dwc2_hsotg_ep *hs_ep)
 {
 	struct dwc2_hsotg *hsotg = hs_ep->parent;
 	u32 target_frame = hs_ep->target_frame;
-	u32 current_frame = dwc2_hsotg_read_frameno(hsotg);
+	u32 current_frame = hsotg->frame_number;
 	bool frame_overrun = hs_ep->frame_overrun;
 
 	if (!frame_overrun && current_frame >= target_frame)
@@ -1291,6 +1287,9 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req,
 	struct dwc2_hsotg *hs = hs_ep->parent;
 	bool first;
 	int ret;
+	u32 maxsize = 0;
+	u32 mask = 0;
+
 
 	dev_dbg(hs->dev, "%s: req %p: %d@%p, noi=%d, zero=%d, snok=%d\n",
 		ep->name, req, req->length, req->buf, req->no_interrupt,
@@ -1308,6 +1307,24 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req,
 	req->actual = 0;
 	req->status = -EINPROGRESS;
 
+	/* In DDMA mode for ISOC's don't queue request if length greater
+	 * than descriptor limits.
+	 */
+	if (using_desc_dma(hs) && hs_ep->isochronous) {
+		maxsize = dwc2_gadget_get_desc_params(hs_ep, &mask);
+		if (hs_ep->dir_in && req->length > maxsize) {
+			dev_err(hs->dev, "wrong length %d (maxsize=%d)\n",
+				req->length, maxsize);
+			return -EINVAL;
+		}
+
+		if (!hs_ep->dir_in && req->length > hs_ep->ep.maxpacket) {
+			dev_err(hs->dev, "ISOC OUT: wrong length %d (mps=%d)\n",
+				req->length, hs_ep->ep.maxpacket);
+			return -EINVAL;
+		}
+	}
+
 	ret = dwc2_hsotg_handle_unaligned_buf_start(hs, hs_ep, hs_req);
 	if (ret)
 		return ret;
@@ -1330,17 +1347,15 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req,
 
 	/*
 	 * Handle DDMA isochronous transfers separately - just add new entry
-	 * to the half of descriptor chain that is not processed by HW.
+	 * to the descriptor chain.
 	 * Transfer will be started once SW gets either one of NAK or
 	 * OutTknEpDis interrupts.
 	 */
-	if (using_desc_dma(hs) && hs_ep->isochronous &&
-	    hs_ep->target_frame != TARGET_FRAME_INITIAL) {
-		ret = dwc2_gadget_fill_isoc_desc(hs_ep, hs_req->req.dma,
-						 hs_req->req.length);
-		if (ret)
-			dev_dbg(hs->dev, "%s: ISO desc chain full\n", __func__);
-
+	if (using_desc_dma(hs) && hs_ep->isochronous) {
+		if (hs_ep->target_frame != TARGET_FRAME_INITIAL) {
+			dwc2_gadget_fill_isoc_desc(hs_ep, hs_req->req.dma,
+						   hs_req->req.length);
+		}
 		return 0;
 	}
 
@@ -1350,8 +1365,15 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req,
 			return 0;
 		}
 
-		while (dwc2_gadget_target_frame_elapsed(hs_ep))
+		/* Update current frame number value. */
+		hs->frame_number = dwc2_hsotg_read_frameno(hs);
+		while (dwc2_gadget_target_frame_elapsed(hs_ep)) {
 			dwc2_gadget_incr_frame_num(hs_ep);
+			/* Update current frame number value once more as it
+			 * changes here.
+			 */
+			hs->frame_number = dwc2_hsotg_read_frameno(hs);
+		}
 
 		if (hs_ep->target_frame != TARGET_FRAME_INITIAL)
 			dwc2_hsotg_start_req(hs, hs_ep, hs_req, false);
@@ -2011,108 +2033,75 @@ static void dwc2_hsotg_complete_request(struct dwc2_hsotg *hsotg,
  * @hs_ep: The endpoint the request was on.
  *
  * Get first request from the ep queue, determine descriptor on which complete
- * happened. SW based on isoc_chain_num discovers which half of the descriptor
- * chain is currently in use by HW, adjusts dma_address and calculates index
- * of completed descriptor based on the value of DEPDMA register. Update actual
- * length of request, giveback to gadget.
+ * happened. SW discovers which descriptor currently in use by HW, adjusts
+ * dma_address and calculates index of completed descriptor based on the value
+ * of DEPDMA register. Update actual length of request, giveback to gadget.
  */
 static void dwc2_gadget_complete_isoc_request_ddma(struct dwc2_hsotg_ep *hs_ep)
 {
 	struct dwc2_hsotg *hsotg = hs_ep->parent;
 	struct dwc2_hsotg_req *hs_req;
 	struct usb_request *ureq;
-	int index;
-	dma_addr_t dma_addr;
-	u32 dma_reg;
-	u32 depdma;
 	u32 desc_sts;
 	u32 mask;
 
-	hs_req = get_ep_head(hs_ep);
-	if (!hs_req) {
-		dev_warn(hsotg->dev, "%s: ISOC EP queue empty\n", __func__);
-		return;
-	}
-	ureq = &hs_req->req;
-
-	dma_addr = hs_ep->desc_list_dma;
-
-	/*
-	 * If lower half of  descriptor chain is currently use by SW,
-	 * that means higher half is being processed by HW, so shift
-	 * DMA address to higher half of descriptor chain.
-	 */
-	if (!hs_ep->isoc_chain_num)
-		dma_addr += sizeof(struct dwc2_dma_desc) *
-			    (MAX_DMA_DESC_NUM_GENERIC / 2);
-
-	dma_reg = hs_ep->dir_in ? DIEPDMA(hs_ep->index) : DOEPDMA(hs_ep->index);
-	depdma = dwc2_readl(hsotg->regs + dma_reg);
+	desc_sts = hs_ep->desc_list[hs_ep->compl_desc].status;
 
-	index = (depdma - dma_addr) / sizeof(struct dwc2_dma_desc) - 1;
-	desc_sts = hs_ep->desc_list[index].status;
+	/* Process only descriptors with buffer status set to DMA done */
+	while ((desc_sts & DEV_DMA_BUFF_STS_MASK) >>
+		DEV_DMA_BUFF_STS_SHIFT == DEV_DMA_BUFF_STS_DMADONE) {
 
-	mask = hs_ep->dir_in ? DEV_DMA_ISOC_TX_NBYTES_MASK :
-	       DEV_DMA_ISOC_RX_NBYTES_MASK;
-	ureq->actual = ureq->length -
-		       ((desc_sts & mask) >> DEV_DMA_ISOC_NBYTES_SHIFT);
+		hs_req = get_ep_head(hs_ep);
+		if (!hs_req) {
+			dev_warn(hsotg->dev, "%s: ISOC EP queue empty\n", __func__);
+			return;
+		}
+		ureq = &hs_req->req;
+
+		/* Check completion status */
+		if ((desc_sts & DEV_DMA_STS_MASK) >> DEV_DMA_STS_SHIFT ==
+			DEV_DMA_STS_SUCC) {
+			mask = hs_ep->dir_in ? DEV_DMA_ISOC_TX_NBYTES_MASK :
+				DEV_DMA_ISOC_RX_NBYTES_MASK;
+			ureq->actual = ureq->length - ((desc_sts & mask) >>
+				DEV_DMA_ISOC_NBYTES_SHIFT);
+
+			/* Adjust actual len for ISOC Out if len is
+			 * not align of 4
+			 */
+			if (!hs_ep->dir_in && ureq->length & 0x3)
+				ureq->actual += 4 - (ureq->length & 0x3);
+		}
 
-	/* Adjust actual length for ISOC Out if length is not align of 4 */
-	if (!hs_ep->dir_in && ureq->length & 0x3)
-		ureq->actual += 4 - (ureq->length & 0x3);
+		dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, 0);
 
-	dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, 0);
+		hs_ep->compl_desc++;
+		if (hs_ep->compl_desc > (MAX_DMA_DESC_NUM_GENERIC - 1))
+			hs_ep->compl_desc = 0;
+		desc_sts = hs_ep->desc_list[hs_ep->compl_desc].status;
+	}
 }
 
 /*
- * dwc2_gadget_start_next_isoc_ddma - start next isoc request, if any.
- * @hs_ep: The isochronous endpoint to be re-enabled.
+ * dwc2_gadget_handle_isoc_bna - handle BNA interrupt for ISOC.
+ * @hs_ep: The isochronous endpoint.
  *
- * If ep has been disabled due to last descriptor servicing (IN endpoint) or
- * BNA (OUT endpoint) check the status of other half of descriptor chain that
- * was under SW control till HW was busy and restart the endpoint if needed.
+ * If EP ISOC OUT then need to flush RX FIFO to remove source of BNA
+ * interrupt. Reset target frame and next_desc to allow to start
+ * ISOC's on NAK interrupt for IN direction or on OUTTKNEPDIS
+ * interrupt for OUT direction.
  */
-static void dwc2_gadget_start_next_isoc_ddma(struct dwc2_hsotg_ep *hs_ep)
+static void dwc2_gadget_handle_isoc_bna(struct dwc2_hsotg_ep *hs_ep)
 {
 	struct dwc2_hsotg *hsotg = hs_ep->parent;
-	u32 depctl;
-	u32 dma_reg;
-	u32 ctrl;
-	u32 dma_addr = hs_ep->desc_list_dma;
-	unsigned char index = hs_ep->index;
-
-	dma_reg = hs_ep->dir_in ? DIEPDMA(index) : DOEPDMA(index);
-	depctl = hs_ep->dir_in ? DIEPCTL(index) : DOEPCTL(index);
 
-	ctrl = dwc2_readl(hsotg->regs + depctl);
+	if (!hs_ep->dir_in)
+		dwc2_flush_rx_fifo(hsotg);
+	dwc2_hsotg_complete_request(hsotg, hs_ep, get_ep_head(hs_ep), 0);
 
-	/*
-	 * EP was disabled if HW has processed last descriptor or BNA was set.
-	 * So restart ep if SW has prepared new descriptor chain in ep_queue
-	 * routine while HW was busy.
-	 */
-	if (!(ctrl & DXEPCTL_EPENA)) {
-		if (!hs_ep->next_desc) {
-			dev_dbg(hsotg->dev, "%s: No more ISOC requests\n",
-				__func__);
-			return;
-		}
-
-		dma_addr += sizeof(struct dwc2_dma_desc) *
-			    (MAX_DMA_DESC_NUM_GENERIC / 2) *
-			    hs_ep->isoc_chain_num;
-		dwc2_writel(dma_addr, hsotg->regs + dma_reg);
-
-		ctrl |= DXEPCTL_EPENA | DXEPCTL_CNAK;
-		dwc2_writel(ctrl, hsotg->regs + depctl);
-
-		/* Switch ISOC descriptor chain number being processed by SW*/
-		hs_ep->isoc_chain_num = (hs_ep->isoc_chain_num ^ 1) & 0x1;
-		hs_ep->next_desc = 0;
-
-		dev_dbg(hsotg->dev, "%s: Restarted isochronous endpoint\n",
-			__func__);
-	}
+	hs_ep->target_frame = TARGET_FRAME_INITIAL;
+	hs_ep->next_desc = 0;
+	hs_ep->compl_desc = 0;
 }
 
 /**
@@ -2441,6 +2430,7 @@ static u32 dwc2_hsotg_ep0_mps(unsigned int mps)
  * @ep: The index number of the endpoint
  * @mps: The maximum packet size in bytes
  * @mc: The multicount value
+ * @dir_in: True if direction is in.
  *
  * Configure the maximum packet size for the given endpoint, updating
  * the hardware control registers to reflect this.
@@ -2731,6 +2721,8 @@ static void dwc2_gadget_handle_ep_disabled(struct dwc2_hsotg_ep *hs_ep)
 			dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req,
 						    -ENODATA);
 		dwc2_gadget_incr_frame_num(hs_ep);
+		/* Update current frame number value. */
+		hsotg->frame_number = dwc2_hsotg_read_frameno(hsotg);
 	} while (dwc2_gadget_target_frame_elapsed(hs_ep));
 
 	dwc2_gadget_start_next_request(hs_ep);
@@ -2738,7 +2730,7 @@ static void dwc2_gadget_handle_ep_disabled(struct dwc2_hsotg_ep *hs_ep)
 
 /**
  * dwc2_gadget_handle_out_token_ep_disabled - handle DXEPINT_OUTTKNEPDIS
- * @hs_ep: The endpoint on which interrupt is asserted.
+ * @ep: The endpoint on which interrupt is asserted.
  *
  * This is starting point for ISOC-OUT transfer, synchronization done with
  * first out token received from host while corresponding EP is disabled.
@@ -2763,7 +2755,7 @@ static void dwc2_gadget_handle_out_token_ep_disabled(struct dwc2_hsotg_ep *ep)
 	 */
 	tmp = dwc2_hsotg_read_frameno(hsotg);
 
-	dwc2_hsotg_complete_request(hsotg, ep, get_ep_head(ep), -ENODATA);
+	dwc2_hsotg_complete_request(hsotg, ep, get_ep_head(ep), 0);
 
 	if (using_desc_dma(hsotg)) {
 		if (ep->target_frame == TARGET_FRAME_INITIAL) {
@@ -2816,18 +2808,25 @@ static void dwc2_gadget_handle_nak(struct dwc2_hsotg_ep *hs_ep)
 {
 	struct dwc2_hsotg *hsotg = hs_ep->parent;
 	int dir_in = hs_ep->dir_in;
+	u32 tmp;
 
 	if (!dir_in || !hs_ep->isochronous)
 		return;
 
 	if (hs_ep->target_frame == TARGET_FRAME_INITIAL) {
-		hs_ep->target_frame = dwc2_hsotg_read_frameno(hsotg);
 
+		tmp = dwc2_hsotg_read_frameno(hsotg);
 		if (using_desc_dma(hsotg)) {
+			dwc2_hsotg_complete_request(hsotg, hs_ep,
+						    get_ep_head(hs_ep), 0);
+
+			hs_ep->target_frame = tmp;
+			dwc2_gadget_incr_frame_num(hs_ep);
 			dwc2_gadget_start_isoc_ddma(hs_ep);
 			return;
 		}
 
+		hs_ep->target_frame = tmp;
 		if (hs_ep->interval > 1) {
 			u32 ctrl = dwc2_readl(hsotg->regs +
 					      DIEPCTL(hs_ep->index));
@@ -2843,7 +2842,8 @@ static void dwc2_gadget_handle_nak(struct dwc2_hsotg_ep *hs_ep)
 					    get_ep_head(hs_ep), 0);
 	}
 
-	dwc2_gadget_incr_frame_num(hs_ep);
+	if (!using_desc_dma(hsotg))
+		dwc2_gadget_incr_frame_num(hs_ep);
 }
 
 /**
@@ -2901,9 +2901,9 @@ static void dwc2_hsotg_epint(struct dwc2_hsotg *hsotg, unsigned int idx,
 
 		/* In DDMA handle isochronous requests separately */
 		if (using_desc_dma(hsotg) && hs_ep->isochronous) {
-			dwc2_gadget_complete_isoc_request_ddma(hs_ep);
-			/* Try to start next isoc request */
-			dwc2_gadget_start_next_isoc_ddma(hs_ep);
+			/* XferCompl set along with BNA */
+			if (!(ints & DXEPINT_BNAINTR))
+				dwc2_gadget_complete_isoc_request_ddma(hs_ep);
 		} else if (dir_in) {
 			/*
 			 * We get OutDone from the FIFO, so we only
@@ -2978,15 +2978,8 @@ static void dwc2_hsotg_epint(struct dwc2_hsotg *hsotg, unsigned int idx,
 
 	if (ints & DXEPINT_BNAINTR) {
 		dev_dbg(hsotg->dev, "%s: BNA interrupt\n", __func__);
-
-		/*
-		 * Try to start next isoc request, if any.
-		 * Sometimes the endpoint remains enabled after BNA interrupt
-		 * assertion, which is not expected, hence we can enter here
-		 * couple of times.
-		 */
 		if (hs_ep->isochronous)
-			dwc2_gadget_start_next_isoc_ddma(hs_ep);
+			dwc2_gadget_handle_isoc_bna(hs_ep);
 	}
 
 	if (dir_in && !hs_ep->isochronous) {
@@ -3197,6 +3190,7 @@ static void dwc2_hsotg_irq_fifoempty(struct dwc2_hsotg *hsotg, bool periodic)
 /**
  * dwc2_hsotg_core_init - issue softreset to the core
  * @hsotg: The device state
+ * @is_usb_reset: Usb resetting flag
  *
  * Issue a soft reset to the core, and await the core finishing it.
  */
@@ -3259,6 +3253,9 @@ void dwc2_hsotg_core_init_disconnected(struct dwc2_hsotg *hsotg,
 		dcfg |= DCFG_DEVSPD_HS;
 	}
 
+	if (hsotg->params.ipg_isoc_en)
+		dcfg |= DCFG_IPG_ISOC_SUPPORDED;
+
 	dwc2_writel(dcfg,  hsotg->regs + DCFG);
 
 	/* Clear any pending OTG interrupts */
@@ -3320,8 +3317,10 @@ void dwc2_hsotg_core_init_disconnected(struct dwc2_hsotg *hsotg,
 		hsotg->regs + DOEPMSK);
 
 	/* Enable BNA interrupt for DDMA */
-	if (using_desc_dma(hsotg))
+	if (using_desc_dma(hsotg)) {
 		dwc2_set_bit(hsotg->regs + DOEPMSK, DOEPMSK_BNAMSK);
+		dwc2_set_bit(hsotg->regs + DIEPMSK, DIEPMSK_BNAININTRMSK);
+	}
 
 	dwc2_writel(0, hsotg->regs + DAINTMSK);
 
@@ -3427,7 +3426,7 @@ static void dwc2_gadget_handle_incomplete_isoc_in(struct dwc2_hsotg *hsotg)
 
 	daintmsk = dwc2_readl(hsotg->regs + DAINTMSK);
 
-	for (idx = 1; idx <= hsotg->num_of_eps; idx++) {
+	for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 		hs_ep = hsotg->eps_in[idx];
 		/* Proceed only unmasked ISOC EPs */
 		if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
@@ -3473,7 +3472,7 @@ static void dwc2_gadget_handle_incomplete_isoc_out(struct dwc2_hsotg *hsotg)
 	daintmsk = dwc2_readl(hsotg->regs + DAINTMSK);
 	daintmsk >>= DAINT_OUTEP_SHIFT;
 
-	for (idx = 1; idx <= hsotg->num_of_eps; idx++) {
+	for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 		hs_ep = hsotg->eps_out[idx];
 		/* Proceed only unmasked ISOC EPs */
 		if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
@@ -3647,7 +3646,7 @@ irq_retry:
 		dwc2_writel(gintmsk, hsotg->regs + GINTMSK);
 
 		dev_dbg(hsotg->dev, "GOUTNakEff triggered\n");
-		for (idx = 1; idx <= hsotg->num_of_eps; idx++) {
+		for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 			hs_ep = hsotg->eps_out[idx];
 			/* Proceed only unmasked ISOC EPs */
 			if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
@@ -3789,6 +3788,7 @@ static int dwc2_hsotg_ep_enable(struct usb_ep *ep,
 	unsigned int dir_in;
 	unsigned int i, val, size;
 	int ret = 0;
+	unsigned char ep_type;
 
 	dev_dbg(hsotg->dev,
 		"%s: ep %s: a 0x%02x, attr 0x%02x, mps 0x%04x, intr %d\n",
@@ -3807,9 +3807,26 @@ static int dwc2_hsotg_ep_enable(struct usb_ep *ep,
 		return -EINVAL;
 	}
 
+	ep_type = desc->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK;
 	mps = usb_endpoint_maxp(desc);
 	mc = usb_endpoint_maxp_mult(desc);
 
+	/* ISOC IN in DDMA supported bInterval up to 10 */
+	if (using_desc_dma(hsotg) && ep_type == USB_ENDPOINT_XFER_ISOC &&
+	    dir_in && desc->bInterval > 10) {
+		dev_err(hsotg->dev,
+			"%s: ISOC IN, DDMA: bInterval>10 not supported!\n", __func__);
+		return -EINVAL;
+	}
+
+	/* High bandwidth ISOC OUT in DDMA not supported */
+	if (using_desc_dma(hsotg) && ep_type == USB_ENDPOINT_XFER_ISOC &&
+	    !dir_in && mc > 1) {
+		dev_err(hsotg->dev,
+			"%s: ISOC OUT, DDMA: HB not supported!\n", __func__);
+		return -EINVAL;
+	}
+
 	/* note, we handle this here instead of dwc2_hsotg_set_ep_maxpacket */
 
 	epctrl_reg = dir_in ? DIEPCTL(index) : DOEPCTL(index);
@@ -3850,15 +3867,15 @@ static int dwc2_hsotg_ep_enable(struct usb_ep *ep,
 	hs_ep->halted = 0;
 	hs_ep->interval = desc->bInterval;
 
-	switch (desc->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) {
+	switch (ep_type) {
 	case USB_ENDPOINT_XFER_ISOC:
 		epctrl |= DXEPCTL_EPTYPE_ISO;
 		epctrl |= DXEPCTL_SETEVENFR;
 		hs_ep->isochronous = 1;
 		hs_ep->interval = 1 << (desc->bInterval - 1);
 		hs_ep->target_frame = TARGET_FRAME_INITIAL;
-		hs_ep->isoc_chain_num = 0;
 		hs_ep->next_desc = 0;
+		hs_ep->compl_desc = 0;
 		if (dir_in) {
 			hs_ep->periodic = 1;
 			mask = dwc2_readl(hsotg->regs + DIEPMSK);
@@ -3928,6 +3945,27 @@ static int dwc2_hsotg_ep_enable(struct usb_ep *ep,
 	if (index && !hs_ep->isochronous)
 		epctrl |= DXEPCTL_SETD0PID;
 
+	/* WA for Full speed ISOC IN in DDMA mode.
+	 * By Clear NAK status of EP, core will send ZLP
+	 * to IN token and assert NAK interrupt relying
+	 * on TxFIFO status only
+	 */
+
+	if (hsotg->gadget.speed == USB_SPEED_FULL &&
+	    hs_ep->isochronous && dir_in) {
+		/* The WA applies only to core versions from 2.72a
+		 * to 4.00a (including both). Also for FS_IOT_1.00a
+		 * and HS_IOT_1.00a.
+		 */
+		u32 gsnpsid = dwc2_readl(hsotg->regs + GSNPSID);
+
+		if ((gsnpsid >= DWC2_CORE_REV_2_72a &&
+		     gsnpsid <= DWC2_CORE_REV_4_00a) ||
+		     gsnpsid == DWC2_FS_IOT_REV_1_00a ||
+		     gsnpsid == DWC2_HS_IOT_REV_1_00a)
+			epctrl |= DXEPCTL_CNAK;
+	}
+
 	dev_dbg(hsotg->dev, "%s: write DxEPCTL=0x%08x\n",
 		__func__, epctrl);
 
@@ -4280,7 +4318,6 @@ err:
 /**
  * dwc2_hsotg_udc_stop - stop the udc
  * @gadget: The usb gadget state
- * @driver: The usb gadget driver
  *
  * Stop udc hw block and stay tunned for future transmissions
  */
@@ -4432,6 +4469,7 @@ static const struct usb_gadget_ops dwc2_hsotg_gadget_ops = {
  * @hsotg: The device state.
  * @hs_ep: The endpoint to be initialised.
  * @epnum: The endpoint number
+ * @dir_in: True if direction is in.
  *
  * Initialise the given endpoint (as part of the probe and device state
  * creation) to give to the gadget driver. Setup the endpoint name, any
@@ -4505,7 +4543,7 @@ static void dwc2_hsotg_initep(struct dwc2_hsotg *hsotg,
 
 /**
  * dwc2_hsotg_hw_cfg - read HW configuration registers
- * @param: The device state
+ * @hsotg: Programming view of the DWC_otg controller
  *
  * Read the USB core HW configuration registers
  */
@@ -4561,7 +4599,8 @@ static int dwc2_hsotg_hw_cfg(struct dwc2_hsotg *hsotg)
 
 /**
  * dwc2_hsotg_dump - dump state of the udc
- * @param: The device state
+ * @hsotg: Programming view of the DWC_otg controller
+ *
  */
 static void dwc2_hsotg_dump(struct dwc2_hsotg *hsotg)
 {
@@ -4612,7 +4651,8 @@ static void dwc2_hsotg_dump(struct dwc2_hsotg *hsotg)
 
 /**
  * dwc2_gadget_init - init function for gadget
- * @dwc2: The data structure for the DWC2 driver.
+ * @hsotg: Programming view of the DWC_otg controller
+ *
  */
 int dwc2_gadget_init(struct dwc2_hsotg *hsotg)
 {
@@ -4709,7 +4749,8 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg)
 
 /**
  * dwc2_hsotg_remove - remove function for hsotg driver
- * @pdev: The platform information for the driver
+ * @hsotg: Programming view of the DWC_otg controller
+ *
  */
 int dwc2_hsotg_remove(struct dwc2_hsotg *hsotg)
 {
@@ -4990,7 +5031,7 @@ int dwc2_gadget_enter_hibernation(struct dwc2_hsotg *hsotg)
  *
  * @hsotg: Programming view of the DWC_otg controller
  * @rem_wakeup: indicates whether resume is initiated by Device or Host.
- * @param reset: indicates whether resume is initiated by Reset.
+ * @reset: indicates whether resume is initiated by Reset.
  *
  * Return non-zero if failed to exit from hibernation.
  */
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index 190f95964000..1faefea16cec 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -358,9 +358,14 @@ static void dwc2_gusbcfg_init(struct dwc2_hsotg *hsotg)
 
 static int dwc2_vbus_supply_init(struct dwc2_hsotg *hsotg)
 {
+	int ret;
+
 	hsotg->vbus_supply = devm_regulator_get_optional(hsotg->dev, "vbus");
-	if (IS_ERR(hsotg->vbus_supply))
-		return 0;
+	if (IS_ERR(hsotg->vbus_supply)) {
+		ret = PTR_ERR(hsotg->vbus_supply);
+		hsotg->vbus_supply = NULL;
+		return ret == -ENODEV ? 0 : ret;
+	}
 
 	return regulator_enable(hsotg->vbus_supply);
 }
@@ -592,7 +597,7 @@ u32 dwc2_calc_frame_interval(struct dwc2_hsotg *hsotg)
  * dwc2_read_packet() - Reads a packet from the Rx FIFO into the destination
  * buffer
  *
- * @core_if: Programming view of DWC_otg controller
+ * @hsotg: Programming view of DWC_otg controller
  * @dest:    Destination buffer for the packet
  * @bytes:   Number of bytes to copy to the destination
  */
@@ -4082,7 +4087,6 @@ static struct dwc2_hsotg *dwc2_hcd_to_hsotg(struct usb_hcd *hcd)
  * then the refcount for the structure will go to 0 and we'll free it.
  *
  * @hsotg:     The HCD state structure for the DWC OTG controller.
- * @qh:        The QH structure.
  * @context:   The priv pointer from a struct dwc2_hcd_urb.
  * @mem_flags: Flags for allocating memory.
  * @ttport:    We'll return this device's port number here.  That's used to
@@ -4342,9 +4346,7 @@ static int _dwc2_hcd_start(struct usb_hcd *hcd)
 
 	spin_unlock_irqrestore(&hsotg->lock, flags);
 
-	dwc2_vbus_supply_init(hsotg);
-
-	return 0;
+	return dwc2_vbus_supply_init(hsotg);
 }
 
 /*
diff --git a/drivers/usb/dwc2/hcd.h b/drivers/usb/dwc2/hcd.h
index 96a9da5fb202..7db1ee7e7a77 100644
--- a/drivers/usb/dwc2/hcd.h
+++ b/drivers/usb/dwc2/hcd.h
@@ -80,7 +80,7 @@ struct dwc2_qh;
  * @xfer_count:         Number of bytes transferred so far
  * @start_pkt_count:    Packet count at start of transfer
  * @xfer_started:       True if the transfer has been started
- * @ping:               True if a PING request should be issued on this channel
+ * @do_ping:            True if a PING request should be issued on this channel
  * @error_state:        True if the error count for this transaction is non-zero
  * @halt_on_queue:      True if this channel should be halted the next time a
  *                      request is queued for the channel. This is necessary in
@@ -102,7 +102,7 @@ struct dwc2_qh;
  * @schinfo:            Scheduling micro-frame bitmap
  * @ntd:                Number of transfer descriptors for the transfer
  * @halt_status:        Reason for halting the host channel
- * @hcint               Contents of the HCINT register when the interrupt came
+ * @hcint:               Contents of the HCINT register when the interrupt came
  * @qh:                 QH for the transfer being processed by this channel
  * @hc_list_entry:      For linking to list of host channels
  * @desc_list_addr:     Current QH's descriptor list DMA address
@@ -237,7 +237,7 @@ struct dwc2_tt {
 /**
  * struct dwc2_hs_transfer_time - Info about a transfer on the high speed bus.
  *
- * @start_schedule_usecs:  The start time on the main bus schedule.  Note that
+ * @start_schedule_us:  The start time on the main bus schedule.  Note that
  *                         the main bus schedule is tightly packed and this
  *			   time should be interpreted as tightly packed (so
  *			   uFrame 0 starts at 0 us, uFrame 1 starts at 100 us
@@ -301,7 +301,6 @@ struct dwc2_hs_transfer_time {
  *                           "struct dwc2_tt".  Not used if this device is high
  *                           speed.  Note that this is in "schedule slice" which
  *                           is tightly packed.
- * @ls_duration_us:     Duration on the low speed bus schedule.
  * @ntd:                Actual number of transfer descriptors in a list
  * @qtd_list:           List of QTDs for this QH
  * @channel:            Host channel currently processing transfers for this QH
@@ -315,7 +314,7 @@ struct dwc2_hs_transfer_time {
  *                      descriptor
  * @unreserve_timer:    Timer for releasing periodic reservation.
  * @wait_timer:         Timer used to wait before re-queuing.
- * @dwc2_tt:            Pointer to our tt info (or NULL if no tt).
+ * @dwc_tt:            Pointer to our tt info (or NULL if no tt).
  * @ttport:             Port number within our tt.
  * @tt_buffer_dirty     True if clear_tt_buffer_complete is pending
  * @unreserve_pending:  True if we planned to unreserve but haven't yet.
@@ -325,6 +324,7 @@ struct dwc2_hs_transfer_time {
  *                      periodic transfers and is ignored for periodic ones.
  * @wait_timer_cancel:  Set to true to cancel the wait_timer.
  *
+ * @tt_buffer_dirty:	True if EP's TT buffer is not clean.
  * A Queue Head (QH) holds the static characteristics of an endpoint and
  * maintains a list of transfers (QTDs) for that endpoint. A QH structure may
  * be entered in either the non-periodic or periodic schedule.
@@ -400,6 +400,10 @@ struct dwc2_qh {
  * @urb:                URB for this transfer
  * @qh:                 Queue head for this QTD
  * @qtd_list_entry:     For linking to the QH's list of QTDs
+ * @isoc_td_first:	Index of first activated isochronous transfer
+ *			descriptor in Descriptor DMA mode
+ * @isoc_td_last:	Index of last activated isochronous transfer
+ *			descriptor in Descriptor DMA mode
  *
  * A Queue Transfer Descriptor (QTD) holds the state of a bulk, control,
  * interrupt, or isochronous transfer. A single QTD is created for each URB
diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c
index 28c8898b3b66..74f11c823f79 100644
--- a/drivers/usb/dwc2/hcd_ddma.c
+++ b/drivers/usb/dwc2/hcd_ddma.c
@@ -332,6 +332,7 @@ static void dwc2_release_channel_ddma(struct dwc2_hsotg *hsotg,
  *
  * @hsotg: The HCD state structure for the DWC OTG controller
  * @qh:    The QH to init
+ * @mem_flags: Indicates the type of memory allocation
  *
  * Return: 0 if successful, negative error code otherwise
  *
diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c
index a5dfd9d8bd9a..fbea5e3fb947 100644
--- a/drivers/usb/dwc2/hcd_intr.c
+++ b/drivers/usb/dwc2/hcd_intr.c
@@ -478,6 +478,12 @@ static u32 dwc2_get_actual_xfer_length(struct dwc2_hsotg *hsotg,
  * of the URB based on the number of bytes transferred via the host channel.
  * Sets the URB status if the data transfer is finished.
  *
+ * @hsotg: Programming view of the DWC_otg controller
+ * @chan: Programming view of host channel
+ * @chnum: Channel number
+ * @urb: Processing URB
+ * @qtd: Queue transfer descriptor
+ *
  * Return: 1 if the data transfer specified by the URB is completely finished,
  * 0 otherwise
  */
@@ -566,6 +572,12 @@ void dwc2_hcd_save_data_toggle(struct dwc2_hsotg *hsotg,
  * halt_status. Completes the Isochronous URB if all the URB frames have been
  * completed.
  *
+ * @hsotg: Programming view of the DWC_otg controller
+ * @chan: Programming view of host channel
+ * @chnum: Channel number
+ * @halt_status: Reason for halting a host channel
+ * @qtd: Queue transfer descriptor
+ *
  * Return: DWC2_HC_XFER_COMPLETE if there are more frames remaining to be
  * transferred in the URB. Otherwise return DWC2_HC_XFER_URB_COMPLETE.
  */
diff --git a/drivers/usb/dwc2/hcd_queue.c b/drivers/usb/dwc2/hcd_queue.c
index e34ad5e65350..d7c3d6c776d8 100644
--- a/drivers/usb/dwc2/hcd_queue.c
+++ b/drivers/usb/dwc2/hcd_queue.c
@@ -679,6 +679,7 @@ static int dwc2_hs_pmap_schedule(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh,
  *
  * @hsotg:       The HCD state structure for the DWC OTG controller.
  * @qh:          QH for the periodic transfer.
+ * @index:       Transfer index
  */
 static void dwc2_hs_pmap_unschedule(struct dwc2_hsotg *hsotg,
 				    struct dwc2_qh *qh, int index)
@@ -1276,7 +1277,7 @@ static void dwc2_do_unreserve(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh)
  * release the reservation.  This worker is called after the appropriate
  * delay.
  *
- * @work: Pointer to a qh unreserve_work.
+ * @t: Address to a qh unreserve_work.
  */
 static void dwc2_unreserve_timer_fn(struct timer_list *t)
 {
@@ -1631,7 +1632,7 @@ static void dwc2_qh_init(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh,
  * @hsotg:        The HCD state structure for the DWC OTG controller
  * @urb:          Holds the information about the device/endpoint needed
  *                to initialize the QH
- * @atomic_alloc: Flag to do atomic allocation if needed
+ * @mem_flags:   Flags for allocating memory.
  *
  * Return: Pointer to the newly allocated QH, or NULL on error
  */
diff --git a/drivers/usb/dwc2/hw.h b/drivers/usb/dwc2/hw.h
index 38391e48351f..0ca8e7bc7aaf 100644
--- a/drivers/usb/dwc2/hw.h
+++ b/drivers/usb/dwc2/hw.h
@@ -311,6 +311,7 @@
 #define GHWCFG4_UTMI_PHY_DATA_WIDTH_MASK	(0x3 << 14)
 #define GHWCFG4_UTMI_PHY_DATA_WIDTH_SHIFT	14
 #define GHWCFG4_ACG_SUPPORTED			BIT(12)
+#define GHWCFG4_IPG_ISOC_SUPPORTED		BIT(11)
 #define GHWCFG4_UTMI_PHY_DATA_WIDTH_8		0
 #define GHWCFG4_UTMI_PHY_DATA_WIDTH_16		1
 #define GHWCFG4_UTMI_PHY_DATA_WIDTH_8_OR_16	2
@@ -424,6 +425,7 @@
 #define DCFG_EPMISCNT_SHIFT		18
 #define DCFG_EPMISCNT_LIMIT		0x1f
 #define DCFG_EPMISCNT(_x)		((_x) << 18)
+#define DCFG_IPG_ISOC_SUPPORDED		BIT(17)
 #define DCFG_PERFRINT_MASK		(0x3 << 11)
 #define DCFG_PERFRINT_SHIFT		11
 #define DCFG_PERFRINT_LIMIT		0x3
diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c
index f03e41879224..af075d4da895 100644
--- a/drivers/usb/dwc2/params.c
+++ b/drivers/usb/dwc2/params.c
@@ -70,6 +70,7 @@ static void dwc2_set_his_params(struct dwc2_hsotg *hsotg)
 		GAHBCFG_HBSTLEN_SHIFT;
 	p->uframe_sched = false;
 	p->change_speed_quirk = true;
+	p->power_down = false;
 }
 
 static void dwc2_set_rk_params(struct dwc2_hsotg *hsotg)
@@ -269,6 +270,9 @@ static void dwc2_set_param_power_down(struct dwc2_hsotg *hsotg)
 /**
  * dwc2_set_default_params() - Set all core parameters to their
  * auto-detected default values.
+ *
+ * @hsotg: Programming view of the DWC_otg controller
+ *
  */
 static void dwc2_set_default_params(struct dwc2_hsotg *hsotg)
 {
@@ -298,6 +302,7 @@ static void dwc2_set_default_params(struct dwc2_hsotg *hsotg)
 	p->besl = true;
 	p->hird_threshold_en = true;
 	p->hird_threshold = 4;
+	p->ipg_isoc_en = false;
 	p->max_packet_count = hw->max_packet_count;
 	p->max_transfer_size = hw->max_transfer_size;
 	p->ahbcfg = GAHBCFG_HBSTLEN_INCR << GAHBCFG_HBSTLEN_SHIFT;
@@ -338,6 +343,8 @@ static void dwc2_set_default_params(struct dwc2_hsotg *hsotg)
 /**
  * dwc2_get_device_properties() - Read in device properties.
  *
+ * @hsotg: Programming view of the DWC_otg controller
+ *
  * Read in the device properties and adjust core parameters if needed.
  */
 static void dwc2_get_device_properties(struct dwc2_hsotg *hsotg)
@@ -549,7 +556,7 @@ static void dwc2_check_param_tx_fifo_sizes(struct dwc2_hsotg *hsotg)
 }
 
 #define CHECK_RANGE(_param, _min, _max, _def) do {			\
-		if ((hsotg->params._param) < (_min) ||			\
+		if ((int)(hsotg->params._param) < (_min) ||		\
 		    (hsotg->params._param) > (_max)) {			\
 			dev_warn(hsotg->dev, "%s: Invalid parameter %s=%d\n", \
 				 __func__, #_param, hsotg->params._param); \
@@ -579,6 +586,7 @@ static void dwc2_check_params(struct dwc2_hsotg *hsotg)
 	CHECK_BOOL(enable_dynamic_fifo, hw->enable_dynamic_fifo);
 	CHECK_BOOL(en_multiple_tx_fifo, hw->en_multiple_tx_fifo);
 	CHECK_BOOL(i2c_enable, hw->i2c_enable);
+	CHECK_BOOL(ipg_isoc_en, hw->ipg_isoc_en);
 	CHECK_BOOL(acg_enable, hw->acg_enable);
 	CHECK_BOOL(reload_ctl, (hsotg->hw_params.snpsid > DWC2_CORE_REV_2_92a));
 	CHECK_BOOL(lpm, (hsotg->hw_params.snpsid >= DWC2_CORE_REV_2_80a));
@@ -688,6 +696,9 @@ static void dwc2_get_dev_hwparams(struct dwc2_hsotg *hsotg)
 /**
  * During device initialization, read various hardware configuration
  * registers and interpret the contents.
+ *
+ * @hsotg: Programming view of the DWC_otg controller
+ *
  */
 int dwc2_get_hwparams(struct dwc2_hsotg *hsotg)
 {
@@ -772,6 +783,7 @@ int dwc2_get_hwparams(struct dwc2_hsotg *hsotg)
 	hw->utmi_phy_data_width = (hwcfg4 & GHWCFG4_UTMI_PHY_DATA_WIDTH_MASK) >>
 				  GHWCFG4_UTMI_PHY_DATA_WIDTH_SHIFT;
 	hw->acg_enable = !!(hwcfg4 & GHWCFG4_ACG_SUPPORTED);
+	hw->ipg_isoc_en = !!(hwcfg4 & GHWCFG4_IPG_ISOC_SUPPORTED);
 
 	/* fifo sizes */
 	hw->rx_fifo_size = (grxfsiz & GRXFSIZ_DEPTH_MASK) >>
diff --git a/drivers/usb/dwc2/pci.c b/drivers/usb/dwc2/pci.c
index 7f21747007f1..d257c541e51b 100644
--- a/drivers/usb/dwc2/pci.c
+++ b/drivers/usb/dwc2/pci.c
@@ -77,6 +77,12 @@ static int dwc2_pci_quirks(struct pci_dev *pdev, struct platform_device *dwc2)
 	return 0;
 }
 
+/**
+ * dwc2_pci_probe() - Provides the cleanup entry points for the DWC_otg PCI
+ * driver
+ *
+ * @pci: The programming view of DWC_otg PCI
+ */
 static void dwc2_pci_remove(struct pci_dev *pci)
 {
 	struct dwc2_pci_glue *glue = pci_get_drvdata(pci);
@@ -141,8 +147,10 @@ static int dwc2_pci_probe(struct pci_dev *pci,
 		goto err;
 
 	glue = devm_kzalloc(dev, sizeof(*glue), GFP_KERNEL);
-	if (!glue)
+	if (!glue) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	ret = platform_device_add(dwc2);
 	if (ret) {
diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig
index ab8c0e0d3b60..451012ea1294 100644
--- a/drivers/usb/dwc3/Kconfig
+++ b/drivers/usb/dwc3/Kconfig
@@ -106,4 +106,16 @@ config USB_DWC3_ST
 	  inside (i.e. STiH407).
 	  Say 'Y' or 'M' if you have one such device.
 
+config USB_DWC3_QCOM
+	tristate "Qualcomm Platform"
+	depends on ARCH_QCOM || COMPILE_TEST
+	depends on OF
+	default USB_DWC3
+	help
+	  Some Qualcomm SoCs use DesignWare Core IP for USB2/3
+	  functionality.
+	  This driver also handles Qscratch wrapper which is needed
+	  for peripheral mode support.
+	  Say 'Y' or 'M' if you have one such device.
+
 endif
diff --git a/drivers/usb/dwc3/Makefile b/drivers/usb/dwc3/Makefile
index 025bc68094fc..5c07d8f925e0 100644
--- a/drivers/usb/dwc3/Makefile
+++ b/drivers/usb/dwc3/Makefile
@@ -48,3 +48,4 @@ obj-$(CONFIG_USB_DWC3_PCI)		+= dwc3-pci.o
 obj-$(CONFIG_USB_DWC3_KEYSTONE)		+= dwc3-keystone.o
 obj-$(CONFIG_USB_DWC3_OF_SIMPLE)	+= dwc3-of-simple.o
 obj-$(CONFIG_USB_DWC3_ST)		+= dwc3-st.o
+obj-$(CONFIG_USB_DWC3_QCOM)		+= dwc3-qcom.o
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index a15648d25e30..ea91310113b9 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -8,6 +8,7 @@
  *	    Sebastian Andrzej Siewior <bigeasy@linutronix.de>
  */
 
+#include <linux/clk.h>
 #include <linux/version.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -24,6 +25,7 @@
 #include <linux/of.h>
 #include <linux/acpi.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/reset.h>
 
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
@@ -266,6 +268,12 @@ done:
 	return 0;
 }
 
+static const struct clk_bulk_data dwc3_core_clks[] = {
+	{ .id = "ref" },
+	{ .id = "bus_early" },
+	{ .id = "suspend" },
+};
+
 /*
  * dwc3_frame_length_adjustment - Adjusts frame length if required
  * @dwc3: Pointer to our controller context structure
@@ -667,6 +675,9 @@ static void dwc3_core_exit(struct dwc3 *dwc)
 	usb_phy_set_suspend(dwc->usb3_phy, 1);
 	phy_power_off(dwc->usb2_generic_phy);
 	phy_power_off(dwc->usb3_generic_phy);
+	clk_bulk_disable(dwc->num_clks, dwc->clks);
+	clk_bulk_unprepare(dwc->num_clks, dwc->clks);
+	reset_control_assert(dwc->reset);
 }
 
 static bool dwc3_core_is_valid(struct dwc3 *dwc)
@@ -1245,7 +1256,7 @@ static void dwc3_check_params(struct dwc3 *dwc)
 static int dwc3_probe(struct platform_device *pdev)
 {
 	struct device		*dev = &pdev->dev;
-	struct resource		*res;
+	struct resource		*res, dwc_res;
 	struct dwc3		*dwc;
 
 	int			ret;
@@ -1256,6 +1267,12 @@ static int dwc3_probe(struct platform_device *pdev)
 	if (!dwc)
 		return -ENOMEM;
 
+	dwc->clks = devm_kmemdup(dev, dwc3_core_clks, sizeof(dwc3_core_clks),
+				 GFP_KERNEL);
+	if (!dwc->clks)
+		return -ENOMEM;
+
+	dwc->num_clks = ARRAY_SIZE(dwc3_core_clks);
 	dwc->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1270,23 +1287,48 @@ static int dwc3_probe(struct platform_device *pdev)
 	dwc->xhci_resources[0].flags = res->flags;
 	dwc->xhci_resources[0].name = res->name;
 
-	res->start += DWC3_GLOBALS_REGS_START;
-
 	/*
 	 * Request memory region but exclude xHCI regs,
 	 * since it will be requested by the xhci-plat driver.
 	 */
-	regs = devm_ioremap_resource(dev, res);
-	if (IS_ERR(regs)) {
-		ret = PTR_ERR(regs);
-		goto err0;
-	}
+	dwc_res = *res;
+	dwc_res.start += DWC3_GLOBALS_REGS_START;
+
+	regs = devm_ioremap_resource(dev, &dwc_res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	dwc->regs	= regs;
-	dwc->regs_size	= resource_size(res);
+	dwc->regs_size	= resource_size(&dwc_res);
 
 	dwc3_get_properties(dwc);
 
+	dwc->reset = devm_reset_control_get_optional_shared(dev, NULL);
+	if (IS_ERR(dwc->reset))
+		return PTR_ERR(dwc->reset);
+
+	ret = clk_bulk_get(dev, dwc->num_clks, dwc->clks);
+	if (ret == -EPROBE_DEFER)
+		return ret;
+	/*
+	 * Clocks are optional, but new DT platforms should support all clocks
+	 * as required by the DT-binding.
+	 */
+	if (ret)
+		dwc->num_clks = 0;
+
+	ret = reset_control_deassert(dwc->reset);
+	if (ret)
+		goto put_clks;
+
+	ret = clk_bulk_prepare(dwc->num_clks, dwc->clks);
+	if (ret)
+		goto assert_reset;
+
+	ret = clk_bulk_enable(dwc->num_clks, dwc->clks);
+	if (ret)
+		goto unprepare_clks;
+
 	platform_set_drvdata(pdev, dwc);
 	dwc3_cache_hwparams(dwc);
 
@@ -1350,13 +1392,13 @@ err1:
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
-err0:
-	/*
-	 * restore res->start back to its original value so that, in case the
-	 * probe is deferred, we don't end up getting error in request the
-	 * memory region the next time probe is called.
-	 */
-	res->start -= DWC3_GLOBALS_REGS_START;
+	clk_bulk_disable(dwc->num_clks, dwc->clks);
+unprepare_clks:
+	clk_bulk_unprepare(dwc->num_clks, dwc->clks);
+assert_reset:
+	reset_control_assert(dwc->reset);
+put_clks:
+	clk_bulk_put(dwc->num_clks, dwc->clks);
 
 	return ret;
 }
@@ -1364,15 +1406,8 @@ err0:
 static int dwc3_remove(struct platform_device *pdev)
 {
 	struct dwc3	*dwc = platform_get_drvdata(pdev);
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
 	pm_runtime_get_sync(&pdev->dev);
-	/*
-	 * restore res->start back to its original value so that, in case the
-	 * probe is deferred, we don't end up getting error in request the
-	 * memory region the next time probe is called.
-	 */
-	res->start -= DWC3_GLOBALS_REGS_START;
 
 	dwc3_debugfs_exit(dwc);
 	dwc3_core_exit_mode(dwc);
@@ -1386,14 +1421,48 @@ static int dwc3_remove(struct platform_device *pdev)
 
 	dwc3_free_event_buffers(dwc);
 	dwc3_free_scratch_buffers(dwc);
+	clk_bulk_put(dwc->num_clks, dwc->clks);
 
 	return 0;
 }
 
 #ifdef CONFIG_PM
+static int dwc3_core_init_for_resume(struct dwc3 *dwc)
+{
+	int ret;
+
+	ret = reset_control_deassert(dwc->reset);
+	if (ret)
+		return ret;
+
+	ret = clk_bulk_prepare(dwc->num_clks, dwc->clks);
+	if (ret)
+		goto assert_reset;
+
+	ret = clk_bulk_enable(dwc->num_clks, dwc->clks);
+	if (ret)
+		goto unprepare_clks;
+
+	ret = dwc3_core_init(dwc);
+	if (ret)
+		goto disable_clks;
+
+	return 0;
+
+disable_clks:
+	clk_bulk_disable(dwc->num_clks, dwc->clks);
+unprepare_clks:
+	clk_bulk_unprepare(dwc->num_clks, dwc->clks);
+assert_reset:
+	reset_control_assert(dwc->reset);
+
+	return ret;
+}
+
 static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 {
 	unsigned long	flags;
+	u32 reg;
 
 	switch (dwc->current_dr_role) {
 	case DWC3_GCTL_PRTCAP_DEVICE:
@@ -1403,9 +1472,25 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 		dwc3_core_exit(dwc);
 		break;
 	case DWC3_GCTL_PRTCAP_HOST:
-		/* do nothing during host runtime_suspend */
-		if (!PMSG_IS_AUTO(msg))
+		if (!PMSG_IS_AUTO(msg)) {
 			dwc3_core_exit(dwc);
+			break;
+		}
+
+		/* Let controller to suspend HSPHY before PHY driver suspends */
+		if (dwc->dis_u2_susphy_quirk ||
+		    dwc->dis_enblslpm_quirk) {
+			reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
+			reg |=  DWC3_GUSB2PHYCFG_ENBLSLPM |
+				DWC3_GUSB2PHYCFG_SUSPHY;
+			dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
+
+			/* Give some time for USB2 PHY to suspend */
+			usleep_range(5000, 6000);
+		}
+
+		phy_pm_runtime_put_sync(dwc->usb2_generic_phy);
+		phy_pm_runtime_put_sync(dwc->usb3_generic_phy);
 		break;
 	case DWC3_GCTL_PRTCAP_OTG:
 		/* do nothing during runtime_suspend */
@@ -1433,10 +1518,11 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 {
 	unsigned long	flags;
 	int		ret;
+	u32		reg;
 
 	switch (dwc->current_dr_role) {
 	case DWC3_GCTL_PRTCAP_DEVICE:
-		ret = dwc3_core_init(dwc);
+		ret = dwc3_core_init_for_resume(dwc);
 		if (ret)
 			return ret;
 
@@ -1446,13 +1532,25 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 		spin_unlock_irqrestore(&dwc->lock, flags);
 		break;
 	case DWC3_GCTL_PRTCAP_HOST:
-		/* nothing to do on host runtime_resume */
 		if (!PMSG_IS_AUTO(msg)) {
-			ret = dwc3_core_init(dwc);
+			ret = dwc3_core_init_for_resume(dwc);
 			if (ret)
 				return ret;
 			dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST);
+			break;
 		}
+		/* Restore GUSB2PHYCFG bits that were modified in suspend */
+		reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
+		if (dwc->dis_u2_susphy_quirk)
+			reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
+
+		if (dwc->dis_enblslpm_quirk)
+			reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM;
+
+		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
+
+		phy_pm_runtime_get_sync(dwc->usb2_generic_phy);
+		phy_pm_runtime_get_sync(dwc->usb3_generic_phy);
 		break;
 	case DWC3_GCTL_PRTCAP_OTG:
 		/* nothing to do on runtime_resume */
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 4f3b43809917..285ce0ef3b91 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -639,8 +639,6 @@ struct dwc3_event_buffer {
  * @resource_index: Resource transfer index
  * @frame_number: set to the frame number we want this transfer to start (ISOC)
  * @interval: the interval on which the ISOC transfer is started
- * @allocated_requests: number of requests allocated
- * @queued_requests: number of requests queued for transfer
  * @name: a human readable name e.g. ep1out-bulk
  * @direction: true for TX, false for RX
  * @stream_capable: true when streams are enabled
@@ -664,11 +662,9 @@ struct dwc3_ep {
 #define DWC3_EP_ENABLED		BIT(0)
 #define DWC3_EP_STALL		BIT(1)
 #define DWC3_EP_WEDGE		BIT(2)
-#define DWC3_EP_BUSY		BIT(4)
+#define DWC3_EP_TRANSFER_STARTED BIT(3)
 #define DWC3_EP_PENDING_REQUEST	BIT(5)
-#define DWC3_EP_MISSED_ISOC	BIT(6)
 #define DWC3_EP_END_TRANSFER_PENDING	BIT(7)
-#define DWC3_EP_TRANSFER_STARTED BIT(8)
 
 	/* This last one is specific to EP0 */
 #define DWC3_EP0_DIR_IN		BIT(31)
@@ -688,8 +684,6 @@ struct dwc3_ep {
 	u8			number;
 	u8			type;
 	u8			resource_index;
-	u32			allocated_requests;
-	u32			queued_requests;
 	u32			frame_number;
 	u32			interval;
 
@@ -832,7 +826,9 @@ struct dwc3_hwparams {
  * @list: a list_head used for request queueing
  * @dep: struct dwc3_ep owning this request
  * @sg: pointer to first incomplete sg
+ * @start_sg: pointer to the sg which should be queued next
  * @num_pending_sgs: counter to pending sgs
+ * @num_queued_sgs: counter to the number of sgs which already got queued
  * @remaining: amount of data remaining
  * @epnum: endpoint number to which this request refers
  * @trb: pointer to struct dwc3_trb
@@ -848,8 +844,10 @@ struct dwc3_request {
 	struct list_head	list;
 	struct dwc3_ep		*dep;
 	struct scatterlist	*sg;
+	struct scatterlist	*start_sg;
 
 	unsigned		num_pending_sgs;
+	unsigned int		num_queued_sgs;
 	unsigned		remaining;
 	u8			epnum;
 	struct dwc3_trb		*trb;
@@ -891,6 +889,9 @@ struct dwc3_scratchpad_array {
  * @eps: endpoint array
  * @gadget: device side representation of the peripheral controller
  * @gadget_driver: pointer to the gadget driver
+ * @clks: array of clocks
+ * @num_clks: number of clocks
+ * @reset: reset control
  * @regs: base address for our registers
  * @regs_size: address space size
  * @fladj: frame length adjustment
@@ -1013,6 +1014,11 @@ struct dwc3 {
 	struct usb_gadget	gadget;
 	struct usb_gadget_driver *gadget_driver;
 
+	struct clk_bulk_data	*clks;
+	int			num_clks;
+
+	struct reset_control	*reset;
+
 	struct usb_phy		*usb2_phy;
 	struct usb_phy		*usb3_phy;
 
@@ -1197,11 +1203,12 @@ struct dwc3_event_depevt {
 /* Within XferNotReady */
 #define DEPEVT_STATUS_TRANSFER_ACTIVE	BIT(3)
 
-/* Within XferComplete */
+/* Within XferComplete or XferInProgress */
 #define DEPEVT_STATUS_BUSERR	BIT(0)
 #define DEPEVT_STATUS_SHORT	BIT(1)
 #define DEPEVT_STATUS_IOC	BIT(2)
-#define DEPEVT_STATUS_LST	BIT(3)
+#define DEPEVT_STATUS_LST	BIT(3) /* XferComplete */
+#define DEPEVT_STATUS_MISSED_ISOC BIT(3) /* XferInProgress */
 
 /* Stream event only */
 #define DEPEVT_STREAMEVT_FOUND		1
diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h
index bfb90c52d8fc..c66d216dcc30 100644
--- a/drivers/usb/dwc3/debug.h
+++ b/drivers/usb/dwc3/debug.h
@@ -475,21 +475,37 @@ dwc3_ep_event_string(char *str, const struct dwc3_event_depevt *event,
 	if (ret < 0)
 		return "UNKNOWN";
 
+	status = event->status;
+
 	switch (event->endpoint_event) {
 	case DWC3_DEPEVT_XFERCOMPLETE:
-		strcat(str, "Transfer Complete");
+		len = strlen(str);
+		sprintf(str + len, "Transfer Complete (%c%c%c)",
+				status & DEPEVT_STATUS_SHORT ? 'S' : 's',
+				status & DEPEVT_STATUS_IOC ? 'I' : 'i',
+				status & DEPEVT_STATUS_LST ? 'L' : 'l');
+
 		len = strlen(str);
 
 		if (epnum <= 1)
 			sprintf(str + len, " [%s]", dwc3_ep0_state_string(ep0state));
 		break;
 	case DWC3_DEPEVT_XFERINPROGRESS:
-		strcat(str, "Transfer In-Progress");
+		len = strlen(str);
+
+		sprintf(str + len, "Transfer In Progress [%d] (%c%c%c)",
+				event->parameters,
+				status & DEPEVT_STATUS_SHORT ? 'S' : 's',
+				status & DEPEVT_STATUS_IOC ? 'I' : 'i',
+				status & DEPEVT_STATUS_LST ? 'M' : 'm');
 		break;
 	case DWC3_DEPEVT_XFERNOTREADY:
-		strcat(str, "Transfer Not Ready");
-		status = event->status & DEPEVT_STATUS_TRANSFER_ACTIVE;
-		strcat(str, status ? " (Active)" : " (Not Active)");
+		len = strlen(str);
+
+		sprintf(str + len, "Transfer Not Ready [%d]%s",
+				event->parameters,
+				status & DEPEVT_STATUS_TRANSFER_ACTIVE ?
+				" (Active)" : " (Not Active)");
 
 		/* Control Endpoints */
 		if (epnum <= 1) {
diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c
index 2f07be1e1f31..df8e73ec3342 100644
--- a/drivers/usb/dwc3/debugfs.c
+++ b/drivers/usb/dwc3/debugfs.c
@@ -716,9 +716,6 @@ static void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep,
 	struct dentry		*dir;
 
 	dir = debugfs_create_dir(dep->name, parent);
-	if (IS_ERR_OR_NULL(dir))
-		return;
-
 	dwc3_debugfs_create_endpoint_files(dep, dir);
 }
 
@@ -740,49 +737,31 @@ static void dwc3_debugfs_create_endpoint_dirs(struct dwc3 *dwc,
 void dwc3_debugfs_init(struct dwc3 *dwc)
 {
 	struct dentry		*root;
-	struct dentry           *file;
-
-	root = debugfs_create_dir(dev_name(dwc->dev), NULL);
-	if (IS_ERR_OR_NULL(root)) {
-		if (!root)
-			dev_err(dwc->dev, "Can't create debugfs root\n");
-		return;
-	}
-	dwc->root = root;
 
 	dwc->regset = kzalloc(sizeof(*dwc->regset), GFP_KERNEL);
-	if (!dwc->regset) {
-		debugfs_remove_recursive(root);
+	if (!dwc->regset)
 		return;
-	}
 
 	dwc->regset->regs = dwc3_regs;
 	dwc->regset->nregs = ARRAY_SIZE(dwc3_regs);
 	dwc->regset->base = dwc->regs - DWC3_GLOBALS_REGS_START;
 
-	file = debugfs_create_regset32("regdump", S_IRUGO, root, dwc->regset);
-	if (!file)
-		dev_dbg(dwc->dev, "Can't create debugfs regdump\n");
+	root = debugfs_create_dir(dev_name(dwc->dev), NULL);
+	dwc->root = root;
+
+	debugfs_create_regset32("regdump", S_IRUGO, root, dwc->regset);
 
 	if (IS_ENABLED(CONFIG_USB_DWC3_DUAL_ROLE)) {
-		file = debugfs_create_file("mode", S_IRUGO | S_IWUSR, root,
-				dwc, &dwc3_mode_fops);
-		if (!file)
-			dev_dbg(dwc->dev, "Can't create debugfs mode\n");
+		debugfs_create_file("mode", S_IRUGO | S_IWUSR, root, dwc,
+				    &dwc3_mode_fops);
 	}
 
 	if (IS_ENABLED(CONFIG_USB_DWC3_DUAL_ROLE) ||
 			IS_ENABLED(CONFIG_USB_DWC3_GADGET)) {
-		file = debugfs_create_file("testmode", S_IRUGO | S_IWUSR, root,
-				dwc, &dwc3_testmode_fops);
-		if (!file)
-			dev_dbg(dwc->dev, "Can't create debugfs testmode\n");
-
-		file = debugfs_create_file("link_state", S_IRUGO | S_IWUSR,
-				root, dwc, &dwc3_link_state_fops);
-		if (!file)
-			dev_dbg(dwc->dev, "Can't create debugfs link_state\n");
-
+		debugfs_create_file("testmode", S_IRUGO | S_IWUSR, root, dwc,
+				    &dwc3_testmode_fops);
+		debugfs_create_file("link_state", S_IRUGO | S_IWUSR, root, dwc,
+				    &dwc3_link_state_fops);
 		dwc3_debugfs_create_endpoint_dirs(dwc, root);
 	}
 }
diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index 1d8c557e97e0..218371f985ca 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/extcon.h>
+#include <linux/of_graph.h>
 #include <linux/platform_device.h>
 
 #include "debug.h"
@@ -439,17 +440,38 @@ static int dwc3_drd_notifier(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+static struct extcon_dev *dwc3_get_extcon(struct dwc3 *dwc)
+{
+	struct device *dev = dwc->dev;
+	struct device_node *np_phy, *np_conn;
+	struct extcon_dev *edev;
+
+	if (of_property_read_bool(dev->of_node, "extcon"))
+		return extcon_get_edev_by_phandle(dwc->dev, 0);
+
+	np_phy = of_parse_phandle(dev->of_node, "phys", 0);
+	np_conn = of_graph_get_remote_node(np_phy, -1, -1);
+
+	if (np_conn)
+		edev = extcon_find_edev_by_node(np_conn);
+	else
+		edev = NULL;
+
+	of_node_put(np_conn);
+	of_node_put(np_phy);
+
+	return edev;
+}
+
 int dwc3_drd_init(struct dwc3 *dwc)
 {
 	int ret, irq;
 
-	if (dwc->dev->of_node &&
-	    of_property_read_bool(dwc->dev->of_node, "extcon")) {
-		dwc->edev = extcon_get_edev_by_phandle(dwc->dev, 0);
-
-		if (IS_ERR(dwc->edev))
-			return PTR_ERR(dwc->edev);
+	dwc->edev = dwc3_get_extcon(dwc);
+	if (IS_ERR(dwc->edev))
+		return PTR_ERR(dwc->edev);
 
+	if (dwc->edev) {
 		dwc->edev_nb.notifier_call = dwc3_drd_notifier;
 		ret = extcon_register_notifier(dwc->edev, EXTCON_USB_HOST,
 					       &dwc->edev_nb);
diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c
index cb2ee96fd3e8..6b3ccd542bd7 100644
--- a/drivers/usb/dwc3/dwc3-of-simple.c
+++ b/drivers/usb/dwc3/dwc3-of-simple.c
@@ -208,13 +208,13 @@ static const struct dev_pm_ops dwc3_of_simple_dev_pm_ops = {
 };
 
 static const struct of_device_id of_dwc3_simple_match[] = {
-	{ .compatible = "qcom,dwc3" },
 	{ .compatible = "rockchip,rk3399-dwc3" },
 	{ .compatible = "xlnx,zynqmp-dwc3" },
 	{ .compatible = "cavium,octeon-7130-usb-uctl" },
 	{ .compatible = "sprd,sc9860-dwc3" },
 	{ .compatible = "amlogic,meson-axg-dwc3" },
 	{ .compatible = "amlogic,meson-gxl-dwc3" },
+	{ .compatible = "allwinner,sun50i-h6-dwc3" },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, of_dwc3_simple_match);
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
new file mode 100644
index 000000000000..b0e67ab2f98c
--- /dev/null
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -0,0 +1,619 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ *
+ * Inspired by dwc3-of-simple.c
+ */
+
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/extcon.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/phy/phy.h>
+#include <linux/usb/of.h>
+#include <linux/reset.h>
+#include <linux/iopoll.h>
+
+#include "core.h"
+
+/* USB QSCRATCH Hardware registers */
+#define QSCRATCH_HS_PHY_CTRL			0x10
+#define UTMI_OTG_VBUS_VALID			BIT(20)
+#define SW_SESSVLD_SEL				BIT(28)
+
+#define QSCRATCH_SS_PHY_CTRL			0x30
+#define LANE0_PWR_PRESENT			BIT(24)
+
+#define QSCRATCH_GENERAL_CFG			0x08
+#define PIPE_UTMI_CLK_SEL			BIT(0)
+#define PIPE3_PHYSTATUS_SW			BIT(3)
+#define PIPE_UTMI_CLK_DIS			BIT(8)
+
+#define PWR_EVNT_IRQ_STAT_REG			0x58
+#define PWR_EVNT_LPM_IN_L2_MASK			BIT(4)
+#define PWR_EVNT_LPM_OUT_L2_MASK		BIT(5)
+
+struct dwc3_qcom {
+	struct device		*dev;
+	void __iomem		*qscratch_base;
+	struct platform_device	*dwc3;
+	struct clk		**clks;
+	int			num_clocks;
+	struct reset_control	*resets;
+
+	int			hs_phy_irq;
+	int			dp_hs_phy_irq;
+	int			dm_hs_phy_irq;
+	int			ss_phy_irq;
+
+	struct extcon_dev	*edev;
+	struct extcon_dev	*host_edev;
+	struct notifier_block	vbus_nb;
+	struct notifier_block	host_nb;
+
+	enum usb_dr_mode	mode;
+	bool			is_suspended;
+	bool			pm_suspended;
+};
+
+static inline void dwc3_qcom_setbits(void __iomem *base, u32 offset, u32 val)
+{
+	u32 reg;
+
+	reg = readl(base + offset);
+	reg |= val;
+	writel(reg, base + offset);
+
+	/* ensure that above write is through */
+	readl(base + offset);
+}
+
+static inline void dwc3_qcom_clrbits(void __iomem *base, u32 offset, u32 val)
+{
+	u32 reg;
+
+	reg = readl(base + offset);
+	reg &= ~val;
+	writel(reg, base + offset);
+
+	/* ensure that above write is through */
+	readl(base + offset);
+}
+
+static void dwc3_qcom_vbus_overrride_enable(struct dwc3_qcom *qcom, bool enable)
+{
+	if (enable) {
+		dwc3_qcom_setbits(qcom->qscratch_base, QSCRATCH_SS_PHY_CTRL,
+				  LANE0_PWR_PRESENT);
+		dwc3_qcom_setbits(qcom->qscratch_base, QSCRATCH_HS_PHY_CTRL,
+				  UTMI_OTG_VBUS_VALID | SW_SESSVLD_SEL);
+	} else {
+		dwc3_qcom_clrbits(qcom->qscratch_base, QSCRATCH_SS_PHY_CTRL,
+				  LANE0_PWR_PRESENT);
+		dwc3_qcom_clrbits(qcom->qscratch_base, QSCRATCH_HS_PHY_CTRL,
+				  UTMI_OTG_VBUS_VALID | SW_SESSVLD_SEL);
+	}
+}
+
+static int dwc3_qcom_vbus_notifier(struct notifier_block *nb,
+				   unsigned long event, void *ptr)
+{
+	struct dwc3_qcom *qcom = container_of(nb, struct dwc3_qcom, vbus_nb);
+
+	/* enable vbus override for device mode */
+	dwc3_qcom_vbus_overrride_enable(qcom, event);
+	qcom->mode = event ? USB_DR_MODE_PERIPHERAL : USB_DR_MODE_HOST;
+
+	return NOTIFY_DONE;
+}
+
+static int dwc3_qcom_host_notifier(struct notifier_block *nb,
+				   unsigned long event, void *ptr)
+{
+	struct dwc3_qcom *qcom = container_of(nb, struct dwc3_qcom, host_nb);
+
+	/* disable vbus override in host mode */
+	dwc3_qcom_vbus_overrride_enable(qcom, !event);
+	qcom->mode = event ? USB_DR_MODE_HOST : USB_DR_MODE_PERIPHERAL;
+
+	return NOTIFY_DONE;
+}
+
+static int dwc3_qcom_register_extcon(struct dwc3_qcom *qcom)
+{
+	struct device		*dev = qcom->dev;
+	struct extcon_dev	*host_edev;
+	int			ret;
+
+	if (!of_property_read_bool(dev->of_node, "extcon"))
+		return 0;
+
+	qcom->edev = extcon_get_edev_by_phandle(dev, 0);
+	if (IS_ERR(qcom->edev))
+		return PTR_ERR(qcom->edev);
+
+	qcom->vbus_nb.notifier_call = dwc3_qcom_vbus_notifier;
+
+	qcom->host_edev = extcon_get_edev_by_phandle(dev, 1);
+	if (IS_ERR(qcom->host_edev))
+		qcom->host_edev = NULL;
+
+	ret = devm_extcon_register_notifier(dev, qcom->edev, EXTCON_USB,
+					    &qcom->vbus_nb);
+	if (ret < 0) {
+		dev_err(dev, "VBUS notifier register failed\n");
+		return ret;
+	}
+
+	if (qcom->host_edev)
+		host_edev = qcom->host_edev;
+	else
+		host_edev = qcom->edev;
+
+	qcom->host_nb.notifier_call = dwc3_qcom_host_notifier;
+	ret = devm_extcon_register_notifier(dev, host_edev, EXTCON_USB_HOST,
+					    &qcom->host_nb);
+	if (ret < 0) {
+		dev_err(dev, "Host notifier register failed\n");
+		return ret;
+	}
+
+	/* Update initial VBUS override based on extcon state */
+	if (extcon_get_state(qcom->edev, EXTCON_USB) ||
+	    !extcon_get_state(host_edev, EXTCON_USB_HOST))
+		dwc3_qcom_vbus_notifier(&qcom->vbus_nb, true, qcom->edev);
+	else
+		dwc3_qcom_vbus_notifier(&qcom->vbus_nb, false, qcom->edev);
+
+	return 0;
+}
+
+static void dwc3_qcom_disable_interrupts(struct dwc3_qcom *qcom)
+{
+	if (qcom->hs_phy_irq) {
+		disable_irq_wake(qcom->hs_phy_irq);
+		disable_irq_nosync(qcom->hs_phy_irq);
+	}
+
+	if (qcom->dp_hs_phy_irq) {
+		disable_irq_wake(qcom->dp_hs_phy_irq);
+		disable_irq_nosync(qcom->dp_hs_phy_irq);
+	}
+
+	if (qcom->dm_hs_phy_irq) {
+		disable_irq_wake(qcom->dm_hs_phy_irq);
+		disable_irq_nosync(qcom->dm_hs_phy_irq);
+	}
+
+	if (qcom->ss_phy_irq) {
+		disable_irq_wake(qcom->ss_phy_irq);
+		disable_irq_nosync(qcom->ss_phy_irq);
+	}
+}
+
+static void dwc3_qcom_enable_interrupts(struct dwc3_qcom *qcom)
+{
+	if (qcom->hs_phy_irq) {
+		enable_irq(qcom->hs_phy_irq);
+		enable_irq_wake(qcom->hs_phy_irq);
+	}
+
+	if (qcom->dp_hs_phy_irq) {
+		enable_irq(qcom->dp_hs_phy_irq);
+		enable_irq_wake(qcom->dp_hs_phy_irq);
+	}
+
+	if (qcom->dm_hs_phy_irq) {
+		enable_irq(qcom->dm_hs_phy_irq);
+		enable_irq_wake(qcom->dm_hs_phy_irq);
+	}
+
+	if (qcom->ss_phy_irq) {
+		enable_irq(qcom->ss_phy_irq);
+		enable_irq_wake(qcom->ss_phy_irq);
+	}
+}
+
+static int dwc3_qcom_suspend(struct dwc3_qcom *qcom)
+{
+	u32 val;
+	int i;
+
+	if (qcom->is_suspended)
+		return 0;
+
+	val = readl(qcom->qscratch_base + PWR_EVNT_IRQ_STAT_REG);
+	if (!(val & PWR_EVNT_LPM_IN_L2_MASK))
+		dev_err(qcom->dev, "HS-PHY not in L2\n");
+
+	for (i = qcom->num_clocks - 1; i >= 0; i--)
+		clk_disable_unprepare(qcom->clks[i]);
+
+	qcom->is_suspended = true;
+	dwc3_qcom_enable_interrupts(qcom);
+
+	return 0;
+}
+
+static int dwc3_qcom_resume(struct dwc3_qcom *qcom)
+{
+	int ret;
+	int i;
+
+	if (!qcom->is_suspended)
+		return 0;
+
+	dwc3_qcom_disable_interrupts(qcom);
+
+	for (i = 0; i < qcom->num_clocks; i++) {
+		ret = clk_prepare_enable(qcom->clks[i]);
+		if (ret < 0) {
+			while (--i >= 0)
+				clk_disable_unprepare(qcom->clks[i]);
+			return ret;
+		}
+	}
+
+	/* Clear existing events from PHY related to L2 in/out */
+	dwc3_qcom_setbits(qcom->qscratch_base, PWR_EVNT_IRQ_STAT_REG,
+			  PWR_EVNT_LPM_IN_L2_MASK | PWR_EVNT_LPM_OUT_L2_MASK);
+
+	qcom->is_suspended = false;
+
+	return 0;
+}
+
+static irqreturn_t qcom_dwc3_resume_irq(int irq, void *data)
+{
+	struct dwc3_qcom *qcom = data;
+	struct dwc3	*dwc = platform_get_drvdata(qcom->dwc3);
+
+	/* If pm_suspended then let pm_resume take care of resuming h/w */
+	if (qcom->pm_suspended)
+		return IRQ_HANDLED;
+
+	if (dwc->xhci)
+		pm_runtime_resume(&dwc->xhci->dev);
+
+	return IRQ_HANDLED;
+}
+
+static void dwc3_qcom_select_utmi_clk(struct dwc3_qcom *qcom)
+{
+	/* Configure dwc3 to use UTMI clock as PIPE clock not present */
+	dwc3_qcom_setbits(qcom->qscratch_base, QSCRATCH_GENERAL_CFG,
+			  PIPE_UTMI_CLK_DIS);
+
+	usleep_range(100, 1000);
+
+	dwc3_qcom_setbits(qcom->qscratch_base, QSCRATCH_GENERAL_CFG,
+			  PIPE_UTMI_CLK_SEL | PIPE3_PHYSTATUS_SW);
+
+	usleep_range(100, 1000);
+
+	dwc3_qcom_clrbits(qcom->qscratch_base, QSCRATCH_GENERAL_CFG,
+			  PIPE_UTMI_CLK_DIS);
+}
+
+static int dwc3_qcom_setup_irq(struct platform_device *pdev)
+{
+	struct dwc3_qcom *qcom = platform_get_drvdata(pdev);
+	int irq, ret;
+
+	irq = platform_get_irq_byname(pdev, "hs_phy_irq");
+	if (irq > 0) {
+		/* Keep wakeup interrupts disabled until suspend */
+		irq_set_status_flags(irq, IRQ_NOAUTOEN);
+		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
+					qcom_dwc3_resume_irq,
+					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					"qcom_dwc3 HS", qcom);
+		if (ret) {
+			dev_err(qcom->dev, "hs_phy_irq failed: %d\n", ret);
+			return ret;
+		}
+		qcom->hs_phy_irq = irq;
+	}
+
+	irq = platform_get_irq_byname(pdev, "dp_hs_phy_irq");
+	if (irq > 0) {
+		irq_set_status_flags(irq, IRQ_NOAUTOEN);
+		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
+					qcom_dwc3_resume_irq,
+					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					"qcom_dwc3 DP_HS", qcom);
+		if (ret) {
+			dev_err(qcom->dev, "dp_hs_phy_irq failed: %d\n", ret);
+			return ret;
+		}
+		qcom->dp_hs_phy_irq = irq;
+	}
+
+	irq = platform_get_irq_byname(pdev, "dm_hs_phy_irq");
+	if (irq > 0) {
+		irq_set_status_flags(irq, IRQ_NOAUTOEN);
+		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
+					qcom_dwc3_resume_irq,
+					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					"qcom_dwc3 DM_HS", qcom);
+		if (ret) {
+			dev_err(qcom->dev, "dm_hs_phy_irq failed: %d\n", ret);
+			return ret;
+		}
+		qcom->dm_hs_phy_irq = irq;
+	}
+
+	irq = platform_get_irq_byname(pdev, "ss_phy_irq");
+	if (irq > 0) {
+		irq_set_status_flags(irq, IRQ_NOAUTOEN);
+		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
+					qcom_dwc3_resume_irq,
+					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					"qcom_dwc3 SS", qcom);
+		if (ret) {
+			dev_err(qcom->dev, "ss_phy_irq failed: %d\n", ret);
+			return ret;
+		}
+		qcom->ss_phy_irq = irq;
+	}
+
+	return 0;
+}
+
+static int dwc3_qcom_clk_init(struct dwc3_qcom *qcom, int count)
+{
+	struct device		*dev = qcom->dev;
+	struct device_node	*np = dev->of_node;
+	int			i;
+
+	qcom->num_clocks = count;
+
+	if (!count)
+		return 0;
+
+	qcom->clks = devm_kcalloc(dev, qcom->num_clocks,
+				  sizeof(struct clk *), GFP_KERNEL);
+	if (!qcom->clks)
+		return -ENOMEM;
+
+	for (i = 0; i < qcom->num_clocks; i++) {
+		struct clk	*clk;
+		int		ret;
+
+		clk = of_clk_get(np, i);
+		if (IS_ERR(clk)) {
+			while (--i >= 0)
+				clk_put(qcom->clks[i]);
+			return PTR_ERR(clk);
+		}
+
+		ret = clk_prepare_enable(clk);
+		if (ret < 0) {
+			while (--i >= 0) {
+				clk_disable_unprepare(qcom->clks[i]);
+				clk_put(qcom->clks[i]);
+			}
+			clk_put(clk);
+
+			return ret;
+		}
+
+		qcom->clks[i] = clk;
+	}
+
+	return 0;
+}
+
+static int dwc3_qcom_probe(struct platform_device *pdev)
+{
+	struct device_node	*np = pdev->dev.of_node, *dwc3_np;
+	struct device		*dev = &pdev->dev;
+	struct dwc3_qcom	*qcom;
+	struct resource		*res;
+	int			ret, i;
+	bool			ignore_pipe_clk;
+
+	qcom = devm_kzalloc(&pdev->dev, sizeof(*qcom), GFP_KERNEL);
+	if (!qcom)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, qcom);
+	qcom->dev = &pdev->dev;
+
+	qcom->resets = devm_reset_control_array_get_optional_exclusive(dev);
+	if (IS_ERR(qcom->resets)) {
+		ret = PTR_ERR(qcom->resets);
+		dev_err(&pdev->dev, "failed to get resets, err=%d\n", ret);
+		return ret;
+	}
+
+	ret = reset_control_assert(qcom->resets);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to assert resets, err=%d\n", ret);
+		return ret;
+	}
+
+	usleep_range(10, 1000);
+
+	ret = reset_control_deassert(qcom->resets);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to deassert resets, err=%d\n", ret);
+		goto reset_assert;
+	}
+
+	ret = dwc3_qcom_clk_init(qcom, of_count_phandle_with_args(np,
+						"clocks", "#clock-cells"));
+	if (ret) {
+		dev_err(dev, "failed to get clocks\n");
+		goto reset_assert;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	qcom->qscratch_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(qcom->qscratch_base)) {
+		dev_err(dev, "failed to map qscratch, err=%d\n", ret);
+		ret = PTR_ERR(qcom->qscratch_base);
+		goto clk_disable;
+	}
+
+	ret = dwc3_qcom_setup_irq(pdev);
+	if (ret)
+		goto clk_disable;
+
+	dwc3_np = of_get_child_by_name(np, "dwc3");
+	if (!dwc3_np) {
+		dev_err(dev, "failed to find dwc3 core child\n");
+		ret = -ENODEV;
+		goto clk_disable;
+	}
+
+	/*
+	 * Disable pipe_clk requirement if specified. Used when dwc3
+	 * operates without SSPHY and only HS/FS/LS modes are supported.
+	 */
+	ignore_pipe_clk = device_property_read_bool(dev,
+				"qcom,select-utmi-as-pipe-clk");
+	if (ignore_pipe_clk)
+		dwc3_qcom_select_utmi_clk(qcom);
+
+	ret = of_platform_populate(np, NULL, NULL, dev);
+	if (ret) {
+		dev_err(dev, "failed to register dwc3 core - %d\n", ret);
+		goto clk_disable;
+	}
+
+	qcom->dwc3 = of_find_device_by_node(dwc3_np);
+	if (!qcom->dwc3) {
+		dev_err(&pdev->dev, "failed to get dwc3 platform device\n");
+		goto depopulate;
+	}
+
+	qcom->mode = usb_get_dr_mode(&qcom->dwc3->dev);
+
+	/* enable vbus override for device mode */
+	if (qcom->mode == USB_DR_MODE_PERIPHERAL)
+		dwc3_qcom_vbus_overrride_enable(qcom, true);
+
+	/* register extcon to override sw_vbus on Vbus change later */
+	ret = dwc3_qcom_register_extcon(qcom);
+	if (ret)
+		goto depopulate;
+
+	device_init_wakeup(&pdev->dev, 1);
+	qcom->is_suspended = false;
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+	pm_runtime_forbid(dev);
+
+	return 0;
+
+depopulate:
+	of_platform_depopulate(&pdev->dev);
+clk_disable:
+	for (i = qcom->num_clocks - 1; i >= 0; i--) {
+		clk_disable_unprepare(qcom->clks[i]);
+		clk_put(qcom->clks[i]);
+	}
+reset_assert:
+	reset_control_assert(qcom->resets);
+
+	return ret;
+}
+
+static int dwc3_qcom_remove(struct platform_device *pdev)
+{
+	struct dwc3_qcom *qcom = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+	int i;
+
+	of_platform_depopulate(dev);
+
+	for (i = qcom->num_clocks - 1; i >= 0; i--) {
+		clk_disable_unprepare(qcom->clks[i]);
+		clk_put(qcom->clks[i]);
+	}
+	qcom->num_clocks = 0;
+
+	reset_control_assert(qcom->resets);
+
+	pm_runtime_allow(dev);
+	pm_runtime_disable(dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int dwc3_qcom_pm_suspend(struct device *dev)
+{
+	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
+	int ret = 0;
+
+	ret = dwc3_qcom_suspend(qcom);
+	if (!ret)
+		qcom->pm_suspended = true;
+
+	return ret;
+}
+
+static int dwc3_qcom_pm_resume(struct device *dev)
+{
+	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
+	int ret;
+
+	ret = dwc3_qcom_resume(qcom);
+	if (!ret)
+		qcom->pm_suspended = false;
+
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_PM
+static int dwc3_qcom_runtime_suspend(struct device *dev)
+{
+	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
+
+	return dwc3_qcom_suspend(qcom);
+}
+
+static int dwc3_qcom_runtime_resume(struct device *dev)
+{
+	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
+
+	return dwc3_qcom_resume(qcom);
+}
+#endif
+
+static const struct dev_pm_ops dwc3_qcom_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(dwc3_qcom_pm_suspend, dwc3_qcom_pm_resume)
+	SET_RUNTIME_PM_OPS(dwc3_qcom_runtime_suspend, dwc3_qcom_runtime_resume,
+			   NULL)
+};
+
+static const struct of_device_id dwc3_qcom_of_match[] = {
+	{ .compatible = "qcom,dwc3" },
+	{ .compatible = "qcom,msm8996-dwc3" },
+	{ .compatible = "qcom,sdm845-dwc3" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, dwc3_qcom_of_match);
+
+static struct platform_driver dwc3_qcom_driver = {
+	.probe		= dwc3_qcom_probe,
+	.remove		= dwc3_qcom_remove,
+	.driver		= {
+		.name	= "dwc3-qcom",
+		.pm	= &dwc3_qcom_dev_pm_ops,
+		.of_match_table	= dwc3_qcom_of_match,
+	},
+};
+
+module_platform_driver(dwc3_qcom_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("DesignWare DWC3 QCOM Glue Driver");
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 5a991bca8ed7..c77ff50a88a2 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -66,7 +66,7 @@ static int dwc3_ep0_start_trans(struct dwc3_ep *dep)
 	struct dwc3			*dwc;
 	int				ret;
 
-	if (dep->flags & DWC3_EP_BUSY)
+	if (dep->flags & DWC3_EP_TRANSFER_STARTED)
 		return 0;
 
 	dwc = dep->dwc;
@@ -79,8 +79,6 @@ static int dwc3_ep0_start_trans(struct dwc3_ep *dep)
 	if (ret < 0)
 		return ret;
 
-	dep->flags |= DWC3_EP_BUSY;
-	dep->resource_index = dwc3_gadget_ep_get_transfer_index(dep);
 	dwc->ep0_next_event = DWC3_EP0_COMPLETE;
 
 	return 0;
@@ -913,7 +911,7 @@ static void dwc3_ep0_xfer_complete(struct dwc3 *dwc,
 {
 	struct dwc3_ep		*dep = dwc->eps[event->endpoint_number];
 
-	dep->flags &= ~DWC3_EP_BUSY;
+	dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
 	dep->resource_index = 0;
 	dwc->setup_packet_pending = false;
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 8796a5ee9bb9..69bf137aab37 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -27,6 +27,9 @@
 #include "gadget.h"
 #include "io.h"
 
+#define DWC3_ALIGN_FRAME(d)	(((d)->frame_number + (d)->interval) \
+					& ~((d)->interval - 1))
+
 /**
  * dwc3_gadget_set_test_mode - enables usb2 test modes
  * @dwc: pointer to our context structure
@@ -166,7 +169,7 @@ static void dwc3_ep_inc_deq(struct dwc3_ep *dep)
 	dwc3_ep_inc_trb(&dep->trb_dequeue);
 }
 
-void dwc3_gadget_del_and_unmap_request(struct dwc3_ep *dep,
+static void dwc3_gadget_del_and_unmap_request(struct dwc3_ep *dep,
 		struct dwc3_request *req, int status)
 {
 	struct dwc3			*dwc = dep->dwc;
@@ -375,6 +378,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned cmd,
 		switch (DWC3_DEPCMD_CMD(cmd)) {
 		case DWC3_DEPCMD_STARTTRANSFER:
 			dep->flags |= DWC3_EP_TRANSFER_STARTED;
+			dwc3_gadget_ep_get_transfer_index(dep);
 			break;
 		case DWC3_DEPCMD_ENDTRANSFER:
 			dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
@@ -455,7 +459,17 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep)
 	dep->trb_pool_dma = 0;
 }
 
-static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep);
+static int dwc3_gadget_set_xfer_resource(struct dwc3_ep *dep)
+{
+	struct dwc3_gadget_ep_cmd_params params;
+
+	memset(&params, 0x00, sizeof(params));
+
+	params.param0 = DWC3_DEPXFERCFG_NUM_XFER_RES(1);
+
+	return dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_SETTRANSFRESOURCE,
+			&params);
+}
 
 /**
  * dwc3_gadget_start_config - configure ep resources
@@ -491,9 +505,10 @@ static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep);
  * triggered only when called for EP0-out, which always happens first, and which
  * should only happen in one of the above conditions.
  */
-static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep)
+static int dwc3_gadget_start_config(struct dwc3_ep *dep)
 {
 	struct dwc3_gadget_ep_cmd_params params;
+	struct dwc3		*dwc;
 	u32			cmd;
 	int			i;
 	int			ret;
@@ -503,6 +518,7 @@ static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep)
 
 	memset(&params, 0x00, sizeof(params));
 	cmd = DWC3_DEPCMD_DEPSTARTCFG;
+	dwc = dep->dwc;
 
 	ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params);
 	if (ret)
@@ -514,7 +530,7 @@ static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep)
 		if (!dep)
 			continue;
 
-		ret = dwc3_gadget_set_xfer_resource(dwc, dep);
+		ret = dwc3_gadget_set_xfer_resource(dep);
 		if (ret)
 			return ret;
 	}
@@ -522,16 +538,12 @@ static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep)
 	return 0;
 }
 
-static int dwc3_gadget_set_ep_config(struct dwc3 *dwc, struct dwc3_ep *dep,
-		bool modify, bool restore)
+static int dwc3_gadget_set_ep_config(struct dwc3_ep *dep, unsigned int action)
 {
 	const struct usb_ss_ep_comp_descriptor *comp_desc;
 	const struct usb_endpoint_descriptor *desc;
 	struct dwc3_gadget_ep_cmd_params params;
-
-	if (dev_WARN_ONCE(dwc->dev, modify && restore,
-					"Can't modify and restore\n"))
-		return -EINVAL;
+	struct dwc3 *dwc = dep->dwc;
 
 	comp_desc = dep->endpoint.comp_desc;
 	desc = dep->endpoint.desc;
@@ -547,14 +559,9 @@ static int dwc3_gadget_set_ep_config(struct dwc3 *dwc, struct dwc3_ep *dep,
 		params.param0 |= DWC3_DEPCFG_BURST_SIZE(burst - 1);
 	}
 
-	if (modify) {
-		params.param0 |= DWC3_DEPCFG_ACTION_MODIFY;
-	} else if (restore) {
-		params.param0 |= DWC3_DEPCFG_ACTION_RESTORE;
+	params.param0 |= action;
+	if (action == DWC3_DEPCFG_ACTION_RESTORE)
 		params.param2 |= dep->saved_state;
-	} else {
-		params.param0 |= DWC3_DEPCFG_ACTION_INIT;
-	}
 
 	if (usb_endpoint_xfer_control(desc))
 		params.param1 = DWC3_DEPCFG_XFER_COMPLETE_EN;
@@ -594,29 +601,15 @@ static int dwc3_gadget_set_ep_config(struct dwc3 *dwc, struct dwc3_ep *dep,
 	return dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_SETEPCONFIG, &params);
 }
 
-static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep)
-{
-	struct dwc3_gadget_ep_cmd_params params;
-
-	memset(&params, 0x00, sizeof(params));
-
-	params.param0 = DWC3_DEPXFERCFG_NUM_XFER_RES(1);
-
-	return dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_SETTRANSFRESOURCE,
-			&params);
-}
-
 /**
  * __dwc3_gadget_ep_enable - initializes a hw endpoint
  * @dep: endpoint to be initialized
- * @modify: if true, modify existing endpoint configuration
- * @restore: if true, restore endpoint configuration from scratch buffer
+ * @action: one of INIT, MODIFY or RESTORE
  *
  * Caller should take care of locking. Execute all necessary commands to
  * initialize a HW endpoint so it can be used by a gadget driver.
  */
-static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
-		bool modify, bool restore)
+static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, unsigned int action)
 {
 	const struct usb_endpoint_descriptor *desc = dep->endpoint.desc;
 	struct dwc3		*dwc = dep->dwc;
@@ -625,12 +618,12 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 	int			ret;
 
 	if (!(dep->flags & DWC3_EP_ENABLED)) {
-		ret = dwc3_gadget_start_config(dwc, dep);
+		ret = dwc3_gadget_start_config(dep);
 		if (ret)
 			return ret;
 	}
 
-	ret = dwc3_gadget_set_ep_config(dwc, dep, modify, restore);
+	ret = dwc3_gadget_set_ep_config(dep, action);
 	if (ret)
 		return ret;
 
@@ -671,7 +664,8 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 	 * Issue StartTransfer here with no-op TRB so we can always rely on No
 	 * Response Update Transfer command.
 	 */
-	if (usb_endpoint_xfer_bulk(desc)) {
+	if (usb_endpoint_xfer_bulk(desc) ||
+			usb_endpoint_xfer_int(desc)) {
 		struct dwc3_gadget_ep_cmd_params params;
 		struct dwc3_trb	*trb;
 		dma_addr_t trb_dma;
@@ -689,26 +683,20 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 		ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params);
 		if (ret < 0)
 			return ret;
-
-		dep->flags |= DWC3_EP_BUSY;
-
-		dep->resource_index = dwc3_gadget_ep_get_transfer_index(dep);
-		WARN_ON_ONCE(!dep->resource_index);
 	}
 
-
 out:
 	trace_dwc3_gadget_ep_enable(dep);
 
 	return 0;
 }
 
-static void dwc3_stop_active_transfer(struct dwc3 *dwc, u32 epnum, bool force);
+static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force);
 static void dwc3_remove_requests(struct dwc3 *dwc, struct dwc3_ep *dep)
 {
 	struct dwc3_request		*req;
 
-	dwc3_stop_active_transfer(dwc, dep->number, true);
+	dwc3_stop_active_transfer(dep, true);
 
 	/* - giveback all requests to gadget driver */
 	while (!list_empty(&dep->started_list)) {
@@ -806,7 +794,7 @@ static int dwc3_gadget_ep_enable(struct usb_ep *ep,
 		return 0;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	ret = __dwc3_gadget_ep_enable(dep, false, false);
+	ret = __dwc3_gadget_ep_enable(dep, DWC3_DEPCFG_ACTION_INIT);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return ret;
@@ -840,7 +828,7 @@ static int dwc3_gadget_ep_disable(struct usb_ep *ep)
 }
 
 static struct usb_request *dwc3_gadget_ep_alloc_request(struct usb_ep *ep,
-	gfp_t gfp_flags)
+		gfp_t gfp_flags)
 {
 	struct dwc3_request		*req;
 	struct dwc3_ep			*dep = to_dwc3_ep(ep);
@@ -849,11 +837,10 @@ static struct usb_request *dwc3_gadget_ep_alloc_request(struct usb_ep *ep,
 	if (!req)
 		return NULL;
 
+	req->direction	= dep->direction;
 	req->epnum	= dep->number;
 	req->dep	= dep;
 
-	dep->allocated_requests++;
-
 	trace_dwc3_alloc_request(req);
 
 	return &req->request;
@@ -863,14 +850,58 @@ static void dwc3_gadget_ep_free_request(struct usb_ep *ep,
 		struct usb_request *request)
 {
 	struct dwc3_request		*req = to_dwc3_request(request);
-	struct dwc3_ep			*dep = to_dwc3_ep(ep);
 
-	dep->allocated_requests--;
 	trace_dwc3_free_request(req);
 	kfree(req);
 }
 
-static u32 dwc3_calc_trbs_left(struct dwc3_ep *dep);
+/**
+ * dwc3_ep_prev_trb - returns the previous TRB in the ring
+ * @dep: The endpoint with the TRB ring
+ * @index: The index of the current TRB in the ring
+ *
+ * Returns the TRB prior to the one pointed to by the index. If the
+ * index is 0, we will wrap backwards, skip the link TRB, and return
+ * the one just before that.
+ */
+static struct dwc3_trb *dwc3_ep_prev_trb(struct dwc3_ep *dep, u8 index)
+{
+	u8 tmp = index;
+
+	if (!tmp)
+		tmp = DWC3_TRB_NUM - 1;
+
+	return &dep->trb_pool[tmp - 1];
+}
+
+static u32 dwc3_calc_trbs_left(struct dwc3_ep *dep)
+{
+	struct dwc3_trb		*tmp;
+	u8			trbs_left;
+
+	/*
+	 * If enqueue & dequeue are equal than it is either full or empty.
+	 *
+	 * One way to know for sure is if the TRB right before us has HWO bit
+	 * set or not. If it has, then we're definitely full and can't fit any
+	 * more transfers in our ring.
+	 */
+	if (dep->trb_enqueue == dep->trb_dequeue) {
+		tmp = dwc3_ep_prev_trb(dep, dep->trb_enqueue);
+		if (tmp->ctrl & DWC3_TRB_CTRL_HWO)
+			return 0;
+
+		return DWC3_TRB_NUM - 1;
+	}
+
+	trbs_left = dep->trb_dequeue - dep->trb_enqueue;
+	trbs_left &= (DWC3_TRB_NUM - 1);
+
+	if (dep->trb_dequeue < dep->trb_enqueue)
+		trbs_left--;
+
+	return trbs_left;
+}
 
 static void __dwc3_prepare_one_trb(struct dwc3_ep *dep, struct dwc3_trb *trb,
 		dma_addr_t dma, unsigned length, unsigned chain, unsigned node,
@@ -985,11 +1016,19 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
 		struct dwc3_request *req, unsigned chain, unsigned node)
 {
 	struct dwc3_trb		*trb;
-	unsigned		length = req->request.length;
+	unsigned int		length;
+	dma_addr_t		dma;
 	unsigned		stream_id = req->request.stream_id;
 	unsigned		short_not_ok = req->request.short_not_ok;
 	unsigned		no_interrupt = req->request.no_interrupt;
-	dma_addr_t		dma = req->request.dma;
+
+	if (req->request.num_sgs > 0) {
+		length = sg_dma_len(req->start_sg);
+		dma = sg_dma_address(req->start_sg);
+	} else {
+		length = req->request.length;
+		dma = req->request.dma;
+	}
 
 	trb = &dep->trb_pool[dep->trb_enqueue];
 
@@ -997,69 +1036,23 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
 		dwc3_gadget_move_started_request(req);
 		req->trb = trb;
 		req->trb_dma = dwc3_trb_dma_offset(dep, trb);
-		dep->queued_requests++;
 	}
 
 	__dwc3_prepare_one_trb(dep, trb, dma, length, chain, node,
 			stream_id, short_not_ok, no_interrupt);
 }
 
-/**
- * dwc3_ep_prev_trb - returns the previous TRB in the ring
- * @dep: The endpoint with the TRB ring
- * @index: The index of the current TRB in the ring
- *
- * Returns the TRB prior to the one pointed to by the index. If the
- * index is 0, we will wrap backwards, skip the link TRB, and return
- * the one just before that.
- */
-static struct dwc3_trb *dwc3_ep_prev_trb(struct dwc3_ep *dep, u8 index)
-{
-	u8 tmp = index;
-
-	if (!tmp)
-		tmp = DWC3_TRB_NUM - 1;
-
-	return &dep->trb_pool[tmp - 1];
-}
-
-static u32 dwc3_calc_trbs_left(struct dwc3_ep *dep)
-{
-	struct dwc3_trb		*tmp;
-	u8			trbs_left;
-
-	/*
-	 * If enqueue & dequeue are equal than it is either full or empty.
-	 *
-	 * One way to know for sure is if the TRB right before us has HWO bit
-	 * set or not. If it has, then we're definitely full and can't fit any
-	 * more transfers in our ring.
-	 */
-	if (dep->trb_enqueue == dep->trb_dequeue) {
-		tmp = dwc3_ep_prev_trb(dep, dep->trb_enqueue);
-		if (tmp->ctrl & DWC3_TRB_CTRL_HWO)
-			return 0;
-
-		return DWC3_TRB_NUM - 1;
-	}
-
-	trbs_left = dep->trb_dequeue - dep->trb_enqueue;
-	trbs_left &= (DWC3_TRB_NUM - 1);
-
-	if (dep->trb_dequeue < dep->trb_enqueue)
-		trbs_left--;
-
-	return trbs_left;
-}
-
 static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep,
 		struct dwc3_request *req)
 {
-	struct scatterlist *sg = req->sg;
+	struct scatterlist *sg = req->start_sg;
 	struct scatterlist *s;
 	int		i;
 
-	for_each_sg(sg, s, req->num_pending_sgs, i) {
+	unsigned int remaining = req->request.num_mapped_sgs
+		- req->num_queued_sgs;
+
+	for_each_sg(sg, s, remaining, i) {
 		unsigned int length = req->request.length;
 		unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc);
 		unsigned int rem = length % maxp;
@@ -1088,6 +1081,18 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep,
 			dwc3_prepare_one_trb(dep, req, chain, i);
 		}
 
+		/*
+		 * There can be a situation where all sgs in sglist are not
+		 * queued because of insufficient trb number. To handle this
+		 * case, update start_sg to next sg to be queued, so that
+		 * we have free trbs we can continue queuing from where we
+		 * previously stopped
+		 */
+		if (chain)
+			req->start_sg = sg_next(s);
+
+		req->num_queued_sgs++;
+
 		if (!dwc3_calc_trbs_left(dep))
 			break;
 	}
@@ -1178,6 +1183,8 @@ static void dwc3_prepare_trbs(struct dwc3_ep *dep)
 			return;
 
 		req->sg			= req->request.sg;
+		req->start_sg		= req->sg;
+		req->num_queued_sgs	= 0;
 		req->num_pending_sgs	= req->request.num_mapped_sgs;
 
 		if (req->num_pending_sgs > 0)
@@ -1201,7 +1208,7 @@ static int __dwc3_gadget_kick_transfer(struct dwc3_ep *dep)
 	if (!dwc3_calc_trbs_left(dep))
 		return 0;
 
-	starting = !(dep->flags & DWC3_EP_BUSY);
+	starting = !(dep->flags & DWC3_EP_TRANSFER_STARTED);
 
 	dwc3_prepare_trbs(dep);
 	req = next_request(&dep->started_list);
@@ -1233,18 +1240,10 @@ static int __dwc3_gadget_kick_transfer(struct dwc3_ep *dep)
 		 */
 		if (req->trb)
 			memset(req->trb, 0, sizeof(struct dwc3_trb));
-		dep->queued_requests--;
 		dwc3_gadget_del_and_unmap_request(dep, req, ret);
 		return ret;
 	}
 
-	dep->flags |= DWC3_EP_BUSY;
-
-	if (starting) {
-		dep->resource_index = dwc3_gadget_ep_get_transfer_index(dep);
-		WARN_ON_ONCE(!dep->resource_index);
-	}
-
 	return 0;
 }
 
@@ -1256,35 +1255,19 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc)
 	return DWC3_DSTS_SOFFN(reg);
 }
 
-static void __dwc3_gadget_start_isoc(struct dwc3 *dwc,
-		struct dwc3_ep *dep, u32 cur_uf)
+static void __dwc3_gadget_start_isoc(struct dwc3_ep *dep)
 {
 	if (list_empty(&dep->pending_list)) {
-		dev_info(dwc->dev, "%s: ran out of requests\n",
+		dev_info(dep->dwc->dev, "%s: ran out of requests\n",
 				dep->name);
 		dep->flags |= DWC3_EP_PENDING_REQUEST;
 		return;
 	}
 
-	/*
-	 * Schedule the first trb for one interval in the future or at
-	 * least 4 microframes.
-	 */
-	dep->frame_number = cur_uf + max_t(u32, 4, dep->interval);
+	dep->frame_number = DWC3_ALIGN_FRAME(dep);
 	__dwc3_gadget_kick_transfer(dep);
 }
 
-static void dwc3_gadget_start_isoc(struct dwc3 *dwc,
-		struct dwc3_ep *dep, const struct dwc3_event_depevt *event)
-{
-	u32 cur_uf, mask;
-
-	mask = ~(dep->interval - 1);
-	cur_uf = event->parameters & mask;
-
-	__dwc3_gadget_start_isoc(dwc, dep, cur_uf);
-}
-
 static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
 {
 	struct dwc3		*dwc = dep->dwc;
@@ -1303,8 +1286,6 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
 
 	req->request.actual	= 0;
 	req->request.status	= -EINPROGRESS;
-	req->direction		= dep->direction;
-	req->epnum		= dep->number;
 
 	trace_dwc3_ep_queue(req);
 
@@ -1319,28 +1300,18 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
 	 * errors which will force us issue EndTransfer command.
 	 */
 	if (usb_endpoint_xfer_isoc(dep->endpoint.desc)) {
-		if ((dep->flags & DWC3_EP_PENDING_REQUEST)) {
-			if (dep->flags & DWC3_EP_TRANSFER_STARTED) {
-				dwc3_stop_active_transfer(dwc, dep->number, true);
-				dep->flags = DWC3_EP_ENABLED;
-			} else {
-				u32 cur_uf;
+		if (!(dep->flags & DWC3_EP_PENDING_REQUEST) &&
+				!(dep->flags & DWC3_EP_TRANSFER_STARTED))
+			return 0;
 
-				cur_uf = __dwc3_gadget_get_frame(dwc);
-				__dwc3_gadget_start_isoc(dwc, dep, cur_uf);
-				dep->flags &= ~DWC3_EP_PENDING_REQUEST;
+		if ((dep->flags & DWC3_EP_PENDING_REQUEST)) {
+			if (!(dep->flags & DWC3_EP_TRANSFER_STARTED)) {
+				__dwc3_gadget_start_isoc(dep);
+				return 0;
 			}
-			return 0;
 		}
-
-		if ((dep->flags & DWC3_EP_BUSY) &&
-		    !(dep->flags & DWC3_EP_MISSED_ISOC))
-			goto out;
-
-		return 0;
 	}
 
-out:
 	return __dwc3_gadget_kick_transfer(dep);
 }
 
@@ -1390,7 +1361,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 		}
 		if (r == req) {
 			/* wait until it is processed */
-			dwc3_stop_active_transfer(dwc, dep->number, true);
+			dwc3_stop_active_transfer(dep, true);
 
 			/*
 			 * If request was already started, this means we had to
@@ -1424,7 +1395,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 					dwc->lock);
 
 			if (!r->trb)
-				goto out1;
+				goto out0;
 
 			if (r->num_pending_sgs) {
 				struct dwc3_trb *trb;
@@ -1463,7 +1434,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 
 out1:
 	/* giveback the request */
-	dep->queued_requests--;
+
 	dwc3_gadget_giveback(dep, req, -ECONNRESET);
 
 out0:
@@ -1878,14 +1849,14 @@ static int __dwc3_gadget_start(struct dwc3 *dwc)
 	dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512);
 
 	dep = dwc->eps[0];
-	ret = __dwc3_gadget_ep_enable(dep, false, false);
+	ret = __dwc3_gadget_ep_enable(dep, DWC3_DEPCFG_ACTION_INIT);
 	if (ret) {
 		dev_err(dwc->dev, "failed to enable %s\n", dep->name);
 		goto err0;
 	}
 
 	dep = dwc->eps[1];
-	ret = __dwc3_gadget_ep_enable(dep, false, false);
+	ret = __dwc3_gadget_ep_enable(dep, DWC3_DEPCFG_ACTION_INIT);
 	if (ret) {
 		dev_err(dwc->dev, "failed to enable %s\n", dep->name);
 		goto err1;
@@ -2082,113 +2053,142 @@ static const struct usb_gadget_ops dwc3_gadget_ops = {
 
 /* -------------------------------------------------------------------------- */
 
-static int dwc3_gadget_init_endpoints(struct dwc3 *dwc, u8 total)
+static int dwc3_gadget_init_control_endpoint(struct dwc3_ep *dep)
 {
-	struct dwc3_ep			*dep;
-	u8				epnum;
+	struct dwc3 *dwc = dep->dwc;
 
-	INIT_LIST_HEAD(&dwc->gadget.ep_list);
+	usb_ep_set_maxpacket_limit(&dep->endpoint, 512);
+	dep->endpoint.maxburst = 1;
+	dep->endpoint.ops = &dwc3_gadget_ep0_ops;
+	if (!dep->direction)
+		dwc->gadget.ep0 = &dep->endpoint;
 
-	for (epnum = 0; epnum < total; epnum++) {
-		bool			direction = epnum & 1;
-		u8			num = epnum >> 1;
+	dep->endpoint.caps.type_control = true;
 
-		dep = kzalloc(sizeof(*dep), GFP_KERNEL);
-		if (!dep)
-			return -ENOMEM;
+	return 0;
+}
 
-		dep->dwc = dwc;
-		dep->number = epnum;
-		dep->direction = direction;
-		dep->regs = dwc->regs + DWC3_DEP_BASE(epnum);
-		dwc->eps[epnum] = dep;
+static int dwc3_gadget_init_in_endpoint(struct dwc3_ep *dep)
+{
+	struct dwc3 *dwc = dep->dwc;
+	int mdwidth;
+	int kbytes;
+	int size;
 
-		snprintf(dep->name, sizeof(dep->name), "ep%u%s", num,
-				direction ? "in" : "out");
+	mdwidth = DWC3_MDWIDTH(dwc->hwparams.hwparams0);
+	/* MDWIDTH is represented in bits, we need it in bytes */
+	mdwidth /= 8;
 
-		dep->endpoint.name = dep->name;
+	size = dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(dep->number >> 1));
+	if (dwc3_is_usb31(dwc))
+		size = DWC31_GTXFIFOSIZ_TXFDEF(size);
+	else
+		size = DWC3_GTXFIFOSIZ_TXFDEF(size);
 
-		if (!(dep->number > 1)) {
-			dep->endpoint.desc = &dwc3_gadget_ep0_desc;
-			dep->endpoint.comp_desc = NULL;
-		}
+	/* FIFO Depth is in MDWDITH bytes. Multiply */
+	size *= mdwidth;
 
-		spin_lock_init(&dep->lock);
-
-		if (num == 0) {
-			usb_ep_set_maxpacket_limit(&dep->endpoint, 512);
-			dep->endpoint.maxburst = 1;
-			dep->endpoint.ops = &dwc3_gadget_ep0_ops;
-			if (!direction)
-				dwc->gadget.ep0 = &dep->endpoint;
-		} else if (direction) {
-			int mdwidth;
-			int kbytes;
-			int size;
-			int ret;
-
-			mdwidth = DWC3_MDWIDTH(dwc->hwparams.hwparams0);
-			/* MDWIDTH is represented in bits, we need it in bytes */
-			mdwidth /= 8;
-
-			size = dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(num));
-			if (dwc3_is_usb31(dwc))
-				size = DWC31_GTXFIFOSIZ_TXFDEF(size);
-			else
-				size = DWC3_GTXFIFOSIZ_TXFDEF(size);
+	kbytes = size / 1024;
+	if (kbytes == 0)
+		kbytes = 1;
 
-			/* FIFO Depth is in MDWDITH bytes. Multiply */
-			size *= mdwidth;
+	/*
+	 * FIFO sizes account an extra MDWIDTH * (kbytes + 1) bytes for
+	 * internal overhead. We don't really know how these are used,
+	 * but documentation say it exists.
+	 */
+	size -= mdwidth * (kbytes + 1);
+	size /= kbytes;
 
-			kbytes = size / 1024;
-			if (kbytes == 0)
-				kbytes = 1;
+	usb_ep_set_maxpacket_limit(&dep->endpoint, size);
 
-			/*
-			 * FIFO sizes account an extra MDWIDTH * (kbytes + 1) bytes for
-			 * internal overhead. We don't really know how these are used,
-			 * but documentation say it exists.
-			 */
-			size -= mdwidth * (kbytes + 1);
-			size /= kbytes;
+	dep->endpoint.max_streams = 15;
+	dep->endpoint.ops = &dwc3_gadget_ep_ops;
+	list_add_tail(&dep->endpoint.ep_list,
+			&dwc->gadget.ep_list);
+	dep->endpoint.caps.type_iso = true;
+	dep->endpoint.caps.type_bulk = true;
+	dep->endpoint.caps.type_int = true;
 
-			usb_ep_set_maxpacket_limit(&dep->endpoint, size);
+	return dwc3_alloc_trb_pool(dep);
+}
 
-			dep->endpoint.max_streams = 15;
-			dep->endpoint.ops = &dwc3_gadget_ep_ops;
-			list_add_tail(&dep->endpoint.ep_list,
-					&dwc->gadget.ep_list);
+static int dwc3_gadget_init_out_endpoint(struct dwc3_ep *dep)
+{
+	struct dwc3 *dwc = dep->dwc;
 
-			ret = dwc3_alloc_trb_pool(dep);
-			if (ret)
-				return ret;
-		} else {
-			int		ret;
+	usb_ep_set_maxpacket_limit(&dep->endpoint, 1024);
+	dep->endpoint.max_streams = 15;
+	dep->endpoint.ops = &dwc3_gadget_ep_ops;
+	list_add_tail(&dep->endpoint.ep_list,
+			&dwc->gadget.ep_list);
+	dep->endpoint.caps.type_iso = true;
+	dep->endpoint.caps.type_bulk = true;
+	dep->endpoint.caps.type_int = true;
 
-			usb_ep_set_maxpacket_limit(&dep->endpoint, 1024);
-			dep->endpoint.max_streams = 15;
-			dep->endpoint.ops = &dwc3_gadget_ep_ops;
-			list_add_tail(&dep->endpoint.ep_list,
-					&dwc->gadget.ep_list);
+	return dwc3_alloc_trb_pool(dep);
+}
 
-			ret = dwc3_alloc_trb_pool(dep);
-			if (ret)
-				return ret;
-		}
+static int dwc3_gadget_init_endpoint(struct dwc3 *dwc, u8 epnum)
+{
+	struct dwc3_ep			*dep;
+	bool				direction = epnum & 1;
+	int				ret;
+	u8				num = epnum >> 1;
 
-		if (num == 0) {
-			dep->endpoint.caps.type_control = true;
-		} else {
-			dep->endpoint.caps.type_iso = true;
-			dep->endpoint.caps.type_bulk = true;
-			dep->endpoint.caps.type_int = true;
-		}
+	dep = kzalloc(sizeof(*dep), GFP_KERNEL);
+	if (!dep)
+		return -ENOMEM;
 
-		dep->endpoint.caps.dir_in = direction;
-		dep->endpoint.caps.dir_out = !direction;
+	dep->dwc = dwc;
+	dep->number = epnum;
+	dep->direction = direction;
+	dep->regs = dwc->regs + DWC3_DEP_BASE(epnum);
+	dwc->eps[epnum] = dep;
 
-		INIT_LIST_HEAD(&dep->pending_list);
-		INIT_LIST_HEAD(&dep->started_list);
+	snprintf(dep->name, sizeof(dep->name), "ep%u%s", num,
+			direction ? "in" : "out");
+
+	dep->endpoint.name = dep->name;
+
+	if (!(dep->number > 1)) {
+		dep->endpoint.desc = &dwc3_gadget_ep0_desc;
+		dep->endpoint.comp_desc = NULL;
+	}
+
+	spin_lock_init(&dep->lock);
+
+	if (num == 0)
+		ret = dwc3_gadget_init_control_endpoint(dep);
+	else if (direction)
+		ret = dwc3_gadget_init_in_endpoint(dep);
+	else
+		ret = dwc3_gadget_init_out_endpoint(dep);
+
+	if (ret)
+		return ret;
+
+	dep->endpoint.caps.dir_in = direction;
+	dep->endpoint.caps.dir_out = !direction;
+
+	INIT_LIST_HEAD(&dep->pending_list);
+	INIT_LIST_HEAD(&dep->started_list);
+
+	return 0;
+}
+
+static int dwc3_gadget_init_endpoints(struct dwc3 *dwc, u8 total)
+{
+	u8				epnum;
+
+	INIT_LIST_HEAD(&dwc->gadget.ep_list);
+
+	for (epnum = 0; epnum < total; epnum++) {
+		int			ret;
+
+		ret = dwc3_gadget_init_endpoint(dwc, epnum);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -2223,20 +2223,14 @@ static void dwc3_gadget_free_endpoints(struct dwc3 *dwc)
 
 /* -------------------------------------------------------------------------- */
 
-static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
+static int dwc3_gadget_ep_reclaim_completed_trb(struct dwc3_ep *dep,
 		struct dwc3_request *req, struct dwc3_trb *trb,
-		const struct dwc3_event_depevt *event, int status,
-		int chain)
+		const struct dwc3_event_depevt *event, int status, int chain)
 {
 	unsigned int		count;
-	unsigned int		s_pkt = 0;
-	unsigned int		trb_status;
 
 	dwc3_ep_inc_deq(dep);
 
-	if (req->trb == trb)
-		dep->queued_requests--;
-
 	trace_dwc3_complete_trb(dep, trb);
 
 	/*
@@ -2268,159 +2262,140 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
 	if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN)
 		return 1;
 
-	if (dep->direction) {
-		if (count) {
-			trb_status = DWC3_TRB_SIZE_TRBSTS(trb->size);
-			if (trb_status == DWC3_TRBSTS_MISSED_ISOC) {
-				/*
-				 * If missed isoc occurred and there is
-				 * no request queued then issue END
-				 * TRANSFER, so that core generates
-				 * next xfernotready and we will issue
-				 * a fresh START TRANSFER.
-				 * If there are still queued request
-				 * then wait, do not issue either END
-				 * or UPDATE TRANSFER, just attach next
-				 * request in pending_list during
-				 * giveback.If any future queued request
-				 * is successfully transferred then we
-				 * will issue UPDATE TRANSFER for all
-				 * request in the pending_list.
-				 */
-				dep->flags |= DWC3_EP_MISSED_ISOC;
-			} else {
-				dev_err(dwc->dev, "incomplete IN transfer %s\n",
-						dep->name);
-				status = -ECONNRESET;
-			}
-		} else {
-			dep->flags &= ~DWC3_EP_MISSED_ISOC;
-		}
-	} else {
-		if (count && (event->status & DEPEVT_STATUS_SHORT))
-			s_pkt = 1;
-	}
-
-	if (s_pkt && !chain)
+	if (event->status & DEPEVT_STATUS_SHORT && !chain)
 		return 1;
 
-	if ((event->status & DEPEVT_STATUS_IOC) &&
-			(trb->ctrl & DWC3_TRB_CTRL_IOC))
+	if (event->status & DEPEVT_STATUS_IOC)
 		return 1;
 
 	return 0;
 }
 
-static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep,
-		const struct dwc3_event_depevt *event, int status)
+static int dwc3_gadget_ep_reclaim_trb_sg(struct dwc3_ep *dep,
+		struct dwc3_request *req, const struct dwc3_event_depevt *event,
+		int status)
 {
-	struct dwc3_request	*req, *n;
-	struct dwc3_trb		*trb;
-	bool			ioc = false;
-	int			ret = 0;
+	struct dwc3_trb *trb = &dep->trb_pool[dep->trb_dequeue];
+	struct scatterlist *sg = req->sg;
+	struct scatterlist *s;
+	unsigned int pending = req->num_pending_sgs;
+	unsigned int i;
+	int ret = 0;
 
-	list_for_each_entry_safe(req, n, &dep->started_list, list) {
-		unsigned length;
-		int chain;
+	for_each_sg(sg, s, pending, i) {
+		trb = &dep->trb_pool[dep->trb_dequeue];
 
-		length = req->request.length;
-		chain = req->num_pending_sgs > 0;
-		if (chain) {
-			struct scatterlist *sg = req->sg;
-			struct scatterlist *s;
-			unsigned int pending = req->num_pending_sgs;
-			unsigned int i;
-
-			for_each_sg(sg, s, pending, i) {
-				trb = &dep->trb_pool[dep->trb_dequeue];
-
-				if (trb->ctrl & DWC3_TRB_CTRL_HWO)
-					break;
-
-				req->sg = sg_next(s);
-				req->num_pending_sgs--;
-
-				ret = __dwc3_cleanup_done_trbs(dwc, dep, req, trb,
-						event, status, chain);
-				if (ret)
-					break;
-			}
-		} else {
-			trb = &dep->trb_pool[dep->trb_dequeue];
-			ret = __dwc3_cleanup_done_trbs(dwc, dep, req, trb,
-					event, status, chain);
-		}
+		if (trb->ctrl & DWC3_TRB_CTRL_HWO)
+			break;
 
-		if (req->unaligned || req->zero) {
-			trb = &dep->trb_pool[dep->trb_dequeue];
-			ret = __dwc3_cleanup_done_trbs(dwc, dep, req, trb,
-					event, status, false);
-			req->unaligned = false;
-			req->zero = false;
-		}
+		req->sg = sg_next(s);
+		req->num_pending_sgs--;
 
-		req->request.actual = length - req->remaining;
+		ret = dwc3_gadget_ep_reclaim_completed_trb(dep, req,
+				trb, event, status, true);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
 
-		if ((req->request.actual < length) && req->num_pending_sgs)
-			return __dwc3_gadget_kick_transfer(dep);
+static int dwc3_gadget_ep_reclaim_trb_linear(struct dwc3_ep *dep,
+		struct dwc3_request *req, const struct dwc3_event_depevt *event,
+		int status)
+{
+	struct dwc3_trb *trb = &dep->trb_pool[dep->trb_dequeue];
 
-		dwc3_gadget_giveback(dep, req, status);
+	return dwc3_gadget_ep_reclaim_completed_trb(dep, req, trb,
+			event, status, false);
+}
 
-		if (ret) {
-			if ((event->status & DEPEVT_STATUS_IOC) &&
-			    (trb->ctrl & DWC3_TRB_CTRL_IOC))
-				ioc = true;
-			break;
-		}
+static bool dwc3_gadget_ep_request_completed(struct dwc3_request *req)
+{
+	return req->request.actual == req->request.length;
+}
+
+static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep,
+		const struct dwc3_event_depevt *event,
+		struct dwc3_request *req, int status)
+{
+	int ret;
+
+	if (req->num_pending_sgs)
+		ret = dwc3_gadget_ep_reclaim_trb_sg(dep, req, event,
+				status);
+	else
+		ret = dwc3_gadget_ep_reclaim_trb_linear(dep, req, event,
+				status);
+
+	if (req->unaligned || req->zero) {
+		ret = dwc3_gadget_ep_reclaim_trb_linear(dep, req, event,
+				status);
+		req->unaligned = false;
+		req->zero = false;
 	}
 
-	/*
-	 * Our endpoint might get disabled by another thread during
-	 * dwc3_gadget_giveback(). If that happens, we're just gonna return 1
-	 * early on so DWC3_EP_BUSY flag gets cleared
-	 */
-	if (!dep->endpoint.desc)
-		return 1;
+	req->request.actual = req->request.length - req->remaining;
 
-	if (usb_endpoint_xfer_isoc(dep->endpoint.desc) &&
-			list_empty(&dep->started_list)) {
-		if (list_empty(&dep->pending_list)) {
-			/*
-			 * If there is no entry in request list then do
-			 * not issue END TRANSFER now. Just set PENDING
-			 * flag, so that END TRANSFER is issued when an
-			 * entry is added into request list.
-			 */
-			dep->flags = DWC3_EP_PENDING_REQUEST;
-		} else {
-			dwc3_stop_active_transfer(dwc, dep->number, true);
-			dep->flags = DWC3_EP_ENABLED;
-		}
-		return 1;
+	if (!dwc3_gadget_ep_request_completed(req) &&
+			req->num_pending_sgs) {
+		__dwc3_gadget_kick_transfer(dep);
+		goto out;
 	}
 
-	if (usb_endpoint_xfer_isoc(dep->endpoint.desc) && ioc)
-		return 0;
+	dwc3_gadget_giveback(dep, req, status);
+
+out:
+	return ret;
+}
+
+static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep,
+		const struct dwc3_event_depevt *event, int status)
+{
+	struct dwc3_request	*req;
+	struct dwc3_request	*tmp;
+
+	list_for_each_entry_safe(req, tmp, &dep->started_list, list) {
+		int ret;
+
+		ret = dwc3_gadget_ep_cleanup_completed_request(dep, event,
+				req, status);
+		if (ret)
+			break;
+	}
+}
 
-	return 1;
+static void dwc3_gadget_endpoint_frame_from_event(struct dwc3_ep *dep,
+		const struct dwc3_event_depevt *event)
+{
+	dep->frame_number = event->parameters;
 }
 
-static void dwc3_endpoint_transfer_complete(struct dwc3 *dwc,
-		struct dwc3_ep *dep, const struct dwc3_event_depevt *event)
+static void dwc3_gadget_endpoint_transfer_in_progress(struct dwc3_ep *dep,
+		const struct dwc3_event_depevt *event)
 {
+	struct dwc3		*dwc = dep->dwc;
 	unsigned		status = 0;
-	int			clean_busy;
-	u32			is_xfer_complete;
+	bool			stop = false;
 
-	is_xfer_complete = (event->endpoint_event == DWC3_DEPEVT_XFERCOMPLETE);
+	dwc3_gadget_endpoint_frame_from_event(dep, event);
 
 	if (event->status & DEPEVT_STATUS_BUSERR)
 		status = -ECONNRESET;
 
-	clean_busy = dwc3_cleanup_done_reqs(dwc, dep, event, status);
-	if (clean_busy && (!dep->endpoint.desc || is_xfer_complete ||
-				usb_endpoint_xfer_isoc(dep->endpoint.desc)))
-		dep->flags &= ~DWC3_EP_BUSY;
+	if (event->status & DEPEVT_STATUS_MISSED_ISOC) {
+		status = -EXDEV;
+
+		if (list_empty(&dep->started_list))
+			stop = true;
+	}
+
+	dwc3_gadget_ep_cleanup_completed_requests(dep, event, status);
+
+	if (stop) {
+		dwc3_stop_active_transfer(dep, true);
+		dep->flags = DWC3_EP_ENABLED;
+	}
 
 	/*
 	 * WORKAROUND: This is the 2nd half of U1/U2 -> U0 workaround.
@@ -2446,17 +2421,13 @@ static void dwc3_endpoint_transfer_complete(struct dwc3 *dwc,
 
 		dwc->u1u2 = 0;
 	}
+}
 
-	/*
-	 * Our endpoint might get disabled by another thread during
-	 * dwc3_gadget_giveback(). If that happens, we're just gonna return 1
-	 * early on so DWC3_EP_BUSY flag gets cleared
-	 */
-	if (!dep->endpoint.desc)
-		return;
-
-	if (!usb_endpoint_xfer_isoc(dep->endpoint.desc))
-		__dwc3_gadget_kick_transfer(dep);
+static void dwc3_gadget_endpoint_transfer_not_ready(struct dwc3_ep *dep,
+		const struct dwc3_event_depevt *event)
+{
+	dwc3_gadget_endpoint_frame_from_event(dep, event);
+	__dwc3_gadget_start_isoc(dep);
 }
 
 static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
@@ -2483,32 +2454,11 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
 	}
 
 	switch (event->endpoint_event) {
-	case DWC3_DEPEVT_XFERCOMPLETE:
-		dep->resource_index = 0;
-
-		if (usb_endpoint_xfer_isoc(dep->endpoint.desc)) {
-			dev_err(dwc->dev, "XferComplete for Isochronous endpoint\n");
-			return;
-		}
-
-		dwc3_endpoint_transfer_complete(dwc, dep, event);
-		break;
 	case DWC3_DEPEVT_XFERINPROGRESS:
-		dwc3_endpoint_transfer_complete(dwc, dep, event);
+		dwc3_gadget_endpoint_transfer_in_progress(dep, event);
 		break;
 	case DWC3_DEPEVT_XFERNOTREADY:
-		if (usb_endpoint_xfer_isoc(dep->endpoint.desc))
-			dwc3_gadget_start_isoc(dwc, dep, event);
-		else
-			__dwc3_gadget_kick_transfer(dep);
-
-		break;
-	case DWC3_DEPEVT_STREAMEVT:
-		if (!usb_endpoint_xfer_bulk(dep->endpoint.desc)) {
-			dev_err(dwc->dev, "Stream event for non-Bulk %s\n",
-					dep->name);
-			return;
-		}
+		dwc3_gadget_endpoint_transfer_not_ready(dep, event);
 		break;
 	case DWC3_DEPEVT_EPCMDCMPLT:
 		cmd = DEPEVT_PARAMETER_CMD(event->parameters);
@@ -2518,6 +2468,8 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
 			wake_up(&dep->wait_end_transfer);
 		}
 		break;
+	case DWC3_DEPEVT_STREAMEVT:
+	case DWC3_DEPEVT_XFERCOMPLETE:
 	case DWC3_DEPEVT_RXTXFIFOEVT:
 		break;
 	}
@@ -2562,15 +2514,13 @@ static void dwc3_reset_gadget(struct dwc3 *dwc)
 	}
 }
 
-static void dwc3_stop_active_transfer(struct dwc3 *dwc, u32 epnum, bool force)
+static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force)
 {
-	struct dwc3_ep *dep;
+	struct dwc3 *dwc = dep->dwc;
 	struct dwc3_gadget_ep_cmd_params params;
 	u32 cmd;
 	int ret;
 
-	dep = dwc->eps[epnum];
-
 	if ((dep->flags & DWC3_EP_END_TRANSFER_PENDING) ||
 	    !dep->resource_index)
 		return;
@@ -2614,7 +2564,6 @@ static void dwc3_stop_active_transfer(struct dwc3 *dwc, u32 epnum, bool force)
 	ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params);
 	WARN_ON_ONCE(ret);
 	dep->resource_index = 0;
-	dep->flags &= ~DWC3_EP_BUSY;
 
 	if (dwc3_is_usb31(dwc) || dwc->revision < DWC3_REVISION_310A) {
 		dep->flags |= DWC3_EP_END_TRANSFER_PENDING;
@@ -2816,14 +2765,14 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc)
 	}
 
 	dep = dwc->eps[0];
-	ret = __dwc3_gadget_ep_enable(dep, true, false);
+	ret = __dwc3_gadget_ep_enable(dep, DWC3_DEPCFG_ACTION_MODIFY);
 	if (ret) {
 		dev_err(dwc->dev, "failed to enable %s\n", dep->name);
 		return;
 	}
 
 	dep = dwc->eps[1];
-	ret = __dwc3_gadget_ep_enable(dep, true, false);
+	ret = __dwc3_gadget_ep_enable(dep, DWC3_DEPCFG_ACTION_MODIFY);
 	if (ret) {
 		dev_err(dwc->dev, "failed to enable %s\n", dep->name);
 		return;
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 578aa856f986..db610c56f1d6 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -98,13 +98,12 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol);
  * Caller should take care of locking. Returns the transfer resource
  * index for a given endpoint.
  */
-static inline u32 dwc3_gadget_ep_get_transfer_index(struct dwc3_ep *dep)
+static inline void dwc3_gadget_ep_get_transfer_index(struct dwc3_ep *dep)
 {
 	u32			res_id;
 
 	res_id = dwc3_readl(dep->regs, DWC3_DEPCMD);
-
-	return DWC3_DEPCMD_GET_RSC_IDX(res_id);
+	dep->resource_index = DWC3_DEPCMD_GET_RSC_IDX(res_id);
 }
 
 #endif /* __DRIVERS_USB_DWC3_GADGET_H */
diff --git a/drivers/usb/dwc3/trace.h b/drivers/usb/dwc3/trace.h
index babaee981aa7..f22714cce070 100644
--- a/drivers/usb/dwc3/trace.h
+++ b/drivers/usb/dwc3/trace.h
@@ -230,17 +230,14 @@ DECLARE_EVENT_CLASS(dwc3_log_trb,
 	TP_fast_assign(
 		__assign_str(name, dep->name);
 		__entry->trb = trb;
-		__entry->allocated = dep->allocated_requests;
-		__entry->queued = dep->queued_requests;
 		__entry->bpl = trb->bpl;
 		__entry->bph = trb->bph;
 		__entry->size = trb->size;
 		__entry->ctrl = trb->ctrl;
 		__entry->type = usb_endpoint_type(dep->endpoint.desc);
 	),
-	TP_printk("%s: %d/%d trb %p buf %08x%08x size %s%d ctrl %08x (%c%c%c%c:%c%c:%s)",
-		__get_str(name), __entry->queued, __entry->allocated,
-		__entry->trb, __entry->bph, __entry->bpl,
+	TP_printk("%s: trb %p buf %08x%08x size %s%d ctrl %08x (%c%c%c%c:%c%c:%s)",
+		__get_str(name), __entry->trb, __entry->bph, __entry->bpl,
 		({char *s;
 		int pcm = ((__entry->size >> 24) & 3) + 1;
 		switch (__entry->type) {
@@ -306,7 +303,7 @@ DECLARE_EVENT_CLASS(dwc3_log_ep,
 		__entry->trb_enqueue = dep->trb_enqueue;
 		__entry->trb_dequeue = dep->trb_dequeue;
 	),
-	TP_printk("%s: mps %d/%d streams %d burst %d ring %d/%d flags %c:%c%c%c%c%c:%c:%c",
+	TP_printk("%s: mps %d/%d streams %d burst %d ring %d/%d flags %c:%c%c%c%c:%c:%c",
 		__get_str(name), __entry->maxpacket,
 		__entry->maxpacket_limit, __entry->max_streams,
 		__entry->maxburst, __entry->trb_enqueue,
@@ -314,9 +311,8 @@ DECLARE_EVENT_CLASS(dwc3_log_ep,
 		__entry->flags & DWC3_EP_ENABLED ? 'E' : 'e',
 		__entry->flags & DWC3_EP_STALL ? 'S' : 's',
 		__entry->flags & DWC3_EP_WEDGE ? 'W' : 'w',
-		__entry->flags & DWC3_EP_BUSY ? 'B' : 'b',
+		__entry->flags & DWC3_EP_TRANSFER_STARTED ? 'B' : 'b',
 		__entry->flags & DWC3_EP_PENDING_REQUEST ? 'P' : 'p',
-		__entry->flags & DWC3_EP_MISSED_ISOC ? 'M' : 'm',
 		__entry->flags & DWC3_EP_END_TRANSFER_PENDING ? 'E' : 'e',
 		__entry->direction ? '<' : '>'
 	)
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 63a7cb87514a..f242c2bcea81 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1601,7 +1601,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 				cdev->gadget->ep0->maxpacket;
 			if (gadget_is_superspeed(gadget)) {
 				if (gadget->speed >= USB_SPEED_SUPER) {
-					cdev->desc.bcdUSB = cpu_to_le16(0x0310);
+					cdev->desc.bcdUSB = cpu_to_le16(0x0320);
 					cdev->desc.bMaxPacketSize0 = 9;
 				} else {
 					cdev->desc.bcdUSB = cpu_to_le16(0x0210);
diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c
index b104ed0c1ab5..6ce044008cf6 100644
--- a/drivers/usb/gadget/function/f_ecm.c
+++ b/drivers/usb/gadget/function/f_ecm.c
@@ -705,6 +705,8 @@ ecm_bind(struct usb_configuration *c, struct usb_function *f)
 		ecm_opts->bound = true;
 	}
 
+	ecm_string_defs[1].s = ecm->ethaddr;
+
 	us = usb_gstrings_attach(cdev, ecm_strings,
 				 ARRAY_SIZE(ecm_string_defs));
 	if (IS_ERR(us))
@@ -928,7 +930,6 @@ static struct usb_function *ecm_alloc(struct usb_function_instance *fi)
 		mutex_unlock(&opts->lock);
 		return ERR_PTR(-EINVAL);
 	}
-	ecm_string_defs[1].s = ecm->ethaddr;
 
 	ecm->port.ioport = netdev_priv(opts->net);
 	mutex_unlock(&opts->lock);
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 0294e4f18873..199d25700050 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1266,6 +1266,14 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code,
 	return ret;
 }
 
+#ifdef CONFIG_COMPAT
+static long ffs_epfile_compat_ioctl(struct file *file, unsigned code,
+		unsigned long value)
+{
+	return ffs_epfile_ioctl(file, code, value);
+}
+#endif
+
 static const struct file_operations ffs_epfile_operations = {
 	.llseek =	no_llseek,
 
@@ -1274,6 +1282,9 @@ static const struct file_operations ffs_epfile_operations = {
 	.read_iter =	ffs_epfile_read_iter,
 	.release =	ffs_epfile_release,
 	.unlocked_ioctl =	ffs_epfile_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = ffs_epfile_compat_ioctl,
+#endif
 };
 
 
diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index e8f35db42394..f80699747ee0 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -109,6 +109,7 @@ static inline struct f_midi *func_to_midi(struct usb_function *f)
 
 static void f_midi_transmit(struct f_midi *midi);
 static void f_midi_rmidi_free(struct snd_rawmidi *rmidi);
+static void f_midi_free_inst(struct usb_function_instance *f);
 
 DECLARE_UAC_AC_HEADER_DESCRIPTOR(1);
 DECLARE_USB_MIDI_OUT_JACK_DESCRIPTOR(1);
@@ -1102,7 +1103,7 @@ static ssize_t f_midi_opts_##name##_store(struct config_item *item,	\
 	u32 num;							\
 									\
 	mutex_lock(&opts->lock);					\
-	if (opts->refcnt) {						\
+	if (opts->refcnt > 1) {						\
 		ret = -EBUSY;						\
 		goto end;						\
 	}								\
@@ -1157,7 +1158,7 @@ static ssize_t f_midi_opts_id_store(struct config_item *item,
 	char *c;
 
 	mutex_lock(&opts->lock);
-	if (opts->refcnt) {
+	if (opts->refcnt > 1) {
 		ret = -EBUSY;
 		goto end;
 	}
@@ -1198,13 +1199,21 @@ static const struct config_item_type midi_func_type = {
 static void f_midi_free_inst(struct usb_function_instance *f)
 {
 	struct f_midi_opts *opts;
+	bool free = false;
 
 	opts = container_of(f, struct f_midi_opts, func_inst);
 
-	if (opts->id_allocated)
-		kfree(opts->id);
+	mutex_lock(&opts->lock);
+	if (!--opts->refcnt) {
+		free = true;
+	}
+	mutex_unlock(&opts->lock);
 
-	kfree(opts);
+	if (free) {
+		if (opts->id_allocated)
+			kfree(opts->id);
+		kfree(opts);
+	}
 }
 
 static struct usb_function_instance *f_midi_alloc_inst(void)
@@ -1223,6 +1232,7 @@ static struct usb_function_instance *f_midi_alloc_inst(void)
 	opts->qlen = 32;
 	opts->in_ports = 1;
 	opts->out_ports = 1;
+	opts->refcnt = 1;
 
 	config_group_init_type_name(&opts->func_inst.group, "",
 				    &midi_func_type);
@@ -1234,6 +1244,7 @@ static void f_midi_free(struct usb_function *f)
 {
 	struct f_midi *midi;
 	struct f_midi_opts *opts;
+	bool free = false;
 
 	midi = func_to_midi(f);
 	opts = container_of(f->fi, struct f_midi_opts, func_inst);
@@ -1242,9 +1253,12 @@ static void f_midi_free(struct usb_function *f)
 		kfree(midi->id);
 		kfifo_free(&midi->in_req_fifo);
 		kfree(midi);
-		--opts->refcnt;
+		free = true;
 	}
 	mutex_unlock(&opts->lock);
+
+	if (free)
+		f_midi_free_inst(&opts->func_inst);
 }
 
 static void f_midi_rmidi_free(struct snd_rawmidi *rmidi)
diff --git a/drivers/usb/gadget/function/f_phonet.c b/drivers/usb/gadget/function/f_phonet.c
index 7889bcc0509a..8b72b192c747 100644
--- a/drivers/usb/gadget/function/f_phonet.c
+++ b/drivers/usb/gadget/function/f_phonet.c
@@ -221,7 +221,7 @@ static void pn_tx_complete(struct usb_ep *ep, struct usb_request *req)
 	netif_wake_queue(dev);
 }
 
-static int pn_net_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t pn_net_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct phonet_port *port = netdev_priv(dev);
 	struct f_phonet *fp;
diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c
index d359efe06c76..9c7ed2539ff7 100644
--- a/drivers/usb/gadget/function/f_printer.c
+++ b/drivers/usb/gadget/function/f_printer.c
@@ -631,19 +631,19 @@ printer_write(struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 			return -EAGAIN;
 		}
 
+		list_add(&req->list, &dev->tx_reqs_active);
+
 		/* here, we unlock, and only unlock, to avoid deadlock. */
 		spin_unlock(&dev->lock);
 		value = usb_ep_queue(dev->in_ep, req, GFP_ATOMIC);
 		spin_lock(&dev->lock);
 		if (value) {
+			list_del(&req->list);
 			list_add(&req->list, &dev->tx_reqs);
 			spin_unlock_irqrestore(&dev->lock, flags);
 			mutex_unlock(&dev->lock_printer_io);
 			return -EAGAIN;
 		}
-
-		list_add(&req->list, &dev->tx_reqs_active);
-
 	}
 
 	spin_unlock_irqrestore(&dev->lock, flags);
diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c
index 51dd3e90b06c..04c142c13075 100644
--- a/drivers/usb/gadget/function/rndis.c
+++ b/drivers/usb/gadget/function/rndis.c
@@ -851,6 +851,9 @@ int rndis_msg_parser(struct rndis_params *params, u8 *buf)
 		 */
 		pr_warn("%s: unknown RNDIS message 0x%08X len %d\n",
 			__func__, MsgType, MsgLength);
+		/* Garbled message can be huge, so limit what we display */
+		if (MsgLength > 16)
+			MsgLength = 16;
 		print_hex_dump_bytes(__func__, DUMP_PREFIX_OFFSET,
 				     buf, MsgLength);
 		break;
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 6fcda62f55ea..1000d864929c 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -844,6 +844,10 @@ struct net_device *gether_setup_name_default(const char *netname)
 	net->ethtool_ops = &ops;
 	SET_NETDEV_DEVTYPE(net, &gadget_type);
 
+	/* MTU range: 14 - 15412 */
+	net->min_mtu = ETH_HLEN;
+	net->max_mtu = GETHER_MAX_ETH_FRAME_LEN;
+
 	return net;
 }
 EXPORT_SYMBOL_GPL(gether_setup_name_default);
diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig
index 0875d38476ee..1df4dedffe86 100644
--- a/drivers/usb/gadget/udc/Kconfig
+++ b/drivers/usb/gadget/udc/Kconfig
@@ -179,7 +179,7 @@ config USB_R8A66597
 
 config USB_RENESAS_USBHS_UDC
 	tristate 'Renesas USBHS controller'
-	depends on USB_RENESAS_USBHS && HAS_DMA
+	depends on USB_RENESAS_USBHS
 	help
 	   Renesas USBHS is a discrete USB host and peripheral controller chip
 	   that supports both full and high speed USB 2.0 data transfers.
@@ -192,7 +192,7 @@ config USB_RENESAS_USBHS_UDC
 config USB_RENESAS_USB3
 	tristate 'Renesas USB3.0 Peripheral controller'
 	depends on ARCH_RENESAS || COMPILE_TEST
-	depends on EXTCON && HAS_DMA
+	depends on EXTCON
 	help
 	   Renesas USB3.0 Peripheral controller is a USB peripheral controller
 	   that supports super, high, and full speed USB 3.0 data transfers.
@@ -438,6 +438,8 @@ config USB_GADGET_XILINX
 	  dynamically linked module called "udc-xilinx" and force all
 	  gadget drivers to also be dynamically linked.
 
+source "drivers/usb/gadget/udc/aspeed-vhub/Kconfig"
+
 #
 # LAST -- dummy/emulated controller
 #
diff --git a/drivers/usb/gadget/udc/Makefile b/drivers/usb/gadget/udc/Makefile
index ce865b129fd6..897f648f3cf1 100644
--- a/drivers/usb/gadget/udc/Makefile
+++ b/drivers/usb/gadget/udc/Makefile
@@ -39,4 +39,5 @@ obj-$(CONFIG_USB_MV_U3D)	+= mv_u3d_core.o
 obj-$(CONFIG_USB_GR_UDC)	+= gr_udc.o
 obj-$(CONFIG_USB_GADGET_XILINX)	+= udc-xilinx.o
 obj-$(CONFIG_USB_SNP_UDC_PLAT) += snps_udc_plat.o
+obj-$(CONFIG_USB_ASPEED_VHUB)	+= aspeed-vhub/
 obj-$(CONFIG_USB_BDC_UDC)	+= bdc/
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/Kconfig b/drivers/usb/gadget/udc/aspeed-vhub/Kconfig
new file mode 100644
index 000000000000..f0cdf89b8503
--- /dev/null
+++ b/drivers/usb/gadget/udc/aspeed-vhub/Kconfig
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0+
+config USB_ASPEED_VHUB
+	tristate "Aspeed vHub UDC driver"
+	depends on ARCH_ASPEED || COMPILE_TEST
+	help
+	  USB peripheral controller for the Aspeed AST2500 family
+	  SoCs supporting the "vHub" functionality and USB2.0
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/Makefile b/drivers/usb/gadget/udc/aspeed-vhub/Makefile
new file mode 100644
index 000000000000..9f3add605f8e
--- /dev/null
+++ b/drivers/usb/gadget/udc/aspeed-vhub/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0+
+obj-$(CONFIG_USB_ASPEED_VHUB)	+= aspeed-vhub.o
+aspeed-vhub-y	:= core.o ep0.o epn.o dev.o hub.o
+
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/core.c b/drivers/usb/gadget/udc/aspeed-vhub/core.c
new file mode 100644
index 000000000000..db3628be38c0
--- /dev/null
+++ b/drivers/usb/gadget/udc/aspeed-vhub/core.c
@@ -0,0 +1,425 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * aspeed-vhub -- Driver for Aspeed SoC "vHub" USB gadget
+ *
+ * core.c - Top level support
+ *
+ * Copyright 2017 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/proc_fs.h>
+#include <linux/prefetch.h>
+#include <linux/clk.h>
+#include <linux/usb/gadget.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/regmap.h>
+#include <linux/dma-mapping.h>
+
+#include "vhub.h"
+
+void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
+		   int status)
+{
+	bool internal = req->internal;
+
+	EPVDBG(ep, "completing request @%p, status %d\n", req, status);
+
+	list_del_init(&req->queue);
+
+	if (req->req.status == -EINPROGRESS)
+		req->req.status = status;
+
+	if (req->req.dma) {
+		if (!WARN_ON(!ep->dev))
+			usb_gadget_unmap_request(&ep->dev->gadget,
+						 &req->req, ep->epn.is_in);
+		req->req.dma = 0;
+	}
+
+	/*
+	 * If this isn't an internal EP0 request, call the core
+	 * to call the gadget completion.
+	 */
+	if (!internal) {
+		spin_unlock(&ep->vhub->lock);
+		usb_gadget_giveback_request(&ep->ep, &req->req);
+		spin_lock(&ep->vhub->lock);
+	}
+}
+
+void ast_vhub_nuke(struct ast_vhub_ep *ep, int status)
+{
+	struct ast_vhub_req *req;
+
+	EPDBG(ep, "Nuking\n");
+
+	/* Beware, lock will be dropped & req-acquired by done() */
+	while (!list_empty(&ep->queue)) {
+		req = list_first_entry(&ep->queue, struct ast_vhub_req, queue);
+		ast_vhub_done(ep, req, status);
+	}
+}
+
+struct usb_request *ast_vhub_alloc_request(struct usb_ep *u_ep,
+					   gfp_t gfp_flags)
+{
+	struct ast_vhub_req *req;
+
+	req = kzalloc(sizeof(*req), gfp_flags);
+	if (!req)
+		return NULL;
+	return &req->req;
+}
+
+void ast_vhub_free_request(struct usb_ep *u_ep, struct usb_request *u_req)
+{
+	struct ast_vhub_req *req = to_ast_req(u_req);
+
+	kfree(req);
+}
+
+static irqreturn_t ast_vhub_irq(int irq, void *data)
+{
+	struct ast_vhub *vhub = data;
+	irqreturn_t iret = IRQ_NONE;
+	u32 istat;
+
+	/* Stale interrupt while tearing down */
+	if (!vhub->ep0_bufs)
+		return IRQ_NONE;
+
+	spin_lock(&vhub->lock);
+
+	/* Read and ACK interrupts */
+	istat = readl(vhub->regs + AST_VHUB_ISR);
+	if (!istat)
+		goto bail;
+	writel(istat, vhub->regs + AST_VHUB_ISR);
+	iret = IRQ_HANDLED;
+
+	UDCVDBG(vhub, "irq status=%08x, ep_acks=%08x ep_nacks=%08x\n",
+	       istat,
+	       readl(vhub->regs + AST_VHUB_EP_ACK_ISR),
+	       readl(vhub->regs + AST_VHUB_EP_NACK_ISR));
+
+	/* Handle generic EPs first */
+	if (istat & VHUB_IRQ_EP_POOL_ACK_STALL) {
+		u32 i, ep_acks = readl(vhub->regs + AST_VHUB_EP_ACK_ISR);
+		writel(ep_acks, vhub->regs + AST_VHUB_EP_ACK_ISR);
+
+		for (i = 0; ep_acks && i < AST_VHUB_NUM_GEN_EPs; i++) {
+			u32 mask = VHUB_EP_IRQ(i);
+			if (ep_acks & mask) {
+				ast_vhub_epn_ack_irq(&vhub->epns[i]);
+				ep_acks &= ~mask;
+			}
+		}
+	}
+
+	/* Handle device interrupts */
+	if (istat & (VHUB_IRQ_DEVICE1 |
+		     VHUB_IRQ_DEVICE2 |
+		     VHUB_IRQ_DEVICE3 |
+		     VHUB_IRQ_DEVICE4 |
+		     VHUB_IRQ_DEVICE5)) {
+		if (istat & VHUB_IRQ_DEVICE1)
+			ast_vhub_dev_irq(&vhub->ports[0].dev);
+		if (istat & VHUB_IRQ_DEVICE2)
+			ast_vhub_dev_irq(&vhub->ports[1].dev);
+		if (istat & VHUB_IRQ_DEVICE3)
+			ast_vhub_dev_irq(&vhub->ports[2].dev);
+		if (istat & VHUB_IRQ_DEVICE4)
+			ast_vhub_dev_irq(&vhub->ports[3].dev);
+		if (istat & VHUB_IRQ_DEVICE5)
+			ast_vhub_dev_irq(&vhub->ports[4].dev);
+	}
+
+	/* Handle top-level vHub EP0 interrupts */
+	if (istat & (VHUB_IRQ_HUB_EP0_OUT_ACK_STALL |
+		     VHUB_IRQ_HUB_EP0_IN_ACK_STALL |
+		     VHUB_IRQ_HUB_EP0_SETUP)) {
+		if (istat & VHUB_IRQ_HUB_EP0_IN_ACK_STALL)
+			ast_vhub_ep0_handle_ack(&vhub->ep0, true);
+		if (istat & VHUB_IRQ_HUB_EP0_OUT_ACK_STALL)
+			ast_vhub_ep0_handle_ack(&vhub->ep0, false);
+		if (istat & VHUB_IRQ_HUB_EP0_SETUP)
+			ast_vhub_ep0_handle_setup(&vhub->ep0);
+	}
+
+	/* Various top level bus events */
+	if (istat & (VHUB_IRQ_BUS_RESUME |
+		     VHUB_IRQ_BUS_SUSPEND |
+		     VHUB_IRQ_BUS_RESET)) {
+		if (istat & VHUB_IRQ_BUS_RESUME)
+			ast_vhub_hub_resume(vhub);
+		if (istat & VHUB_IRQ_BUS_SUSPEND)
+			ast_vhub_hub_suspend(vhub);
+		if (istat & VHUB_IRQ_BUS_RESET)
+			ast_vhub_hub_reset(vhub);
+	}
+
+ bail:
+	spin_unlock(&vhub->lock);
+	return iret;
+}
+
+void ast_vhub_init_hw(struct ast_vhub *vhub)
+{
+	u32 ctrl;
+
+	UDCDBG(vhub,"(Re)Starting HW ...\n");
+
+	/* Enable PHY */
+	ctrl = VHUB_CTRL_PHY_CLK |
+		VHUB_CTRL_PHY_RESET_DIS;
+
+       /*
+	* We do *NOT* set the VHUB_CTRL_CLK_STOP_SUSPEND bit
+	* to stop the logic clock during suspend because
+	* it causes the registers to become inaccessible and
+	* we haven't yet figured out a good wayt to bring the
+	* controller back into life to issue a wakeup.
+	*/
+
+	/*
+	 * Set some ISO & split control bits according to Aspeed
+	 * recommendation
+	 *
+	 * VHUB_CTRL_ISO_RSP_CTRL: When set tells the HW to respond
+	 * with 0 bytes data packet to ISO IN endpoints when no data
+	 * is available.
+	 *
+	 * VHUB_CTRL_SPLIT_IN: This makes a SOF complete a split IN
+	 * transaction.
+	 */
+	ctrl |= VHUB_CTRL_ISO_RSP_CTRL | VHUB_CTRL_SPLIT_IN;
+	writel(ctrl, vhub->regs + AST_VHUB_CTRL);
+	udelay(1);
+
+	/* Set descriptor ring size */
+	if (AST_VHUB_DESCS_COUNT == 256) {
+		ctrl |= VHUB_CTRL_LONG_DESC;
+		writel(ctrl, vhub->regs + AST_VHUB_CTRL);
+	} else {
+		BUILD_BUG_ON(AST_VHUB_DESCS_COUNT != 32);
+	}
+
+	/* Reset all devices */
+	writel(VHUB_SW_RESET_ALL, vhub->regs + AST_VHUB_SW_RESET);
+	udelay(1);
+	writel(0, vhub->regs + AST_VHUB_SW_RESET);
+
+	/* Disable and cleanup EP ACK/NACK interrupts */
+	writel(0, vhub->regs + AST_VHUB_EP_ACK_IER);
+	writel(0, vhub->regs + AST_VHUB_EP_NACK_IER);
+	writel(VHUB_EP_IRQ_ALL, vhub->regs + AST_VHUB_EP_ACK_ISR);
+	writel(VHUB_EP_IRQ_ALL, vhub->regs + AST_VHUB_EP_NACK_ISR);
+
+	/* Default settings for EP0, enable HW hub EP1 */
+	writel(0, vhub->regs + AST_VHUB_EP0_CTRL);
+	writel(VHUB_EP1_CTRL_RESET_TOGGLE |
+	       VHUB_EP1_CTRL_ENABLE,
+	       vhub->regs + AST_VHUB_EP1_CTRL);
+	writel(0, vhub->regs + AST_VHUB_EP1_STS_CHG);
+
+	/* Configure EP0 DMA buffer */
+	writel(vhub->ep0.buf_dma, vhub->regs + AST_VHUB_EP0_DATA);
+
+	/* Clear address */
+	writel(0, vhub->regs + AST_VHUB_CONF);
+
+	/* Pullup hub (activate on host) */
+	if (vhub->force_usb1)
+		ctrl |= VHUB_CTRL_FULL_SPEED_ONLY;
+
+	ctrl |= VHUB_CTRL_UPSTREAM_CONNECT;
+	writel(ctrl, vhub->regs + AST_VHUB_CTRL);
+
+	/* Enable some interrupts */
+	writel(VHUB_IRQ_HUB_EP0_IN_ACK_STALL |
+	       VHUB_IRQ_HUB_EP0_OUT_ACK_STALL |
+	       VHUB_IRQ_HUB_EP0_SETUP |
+	       VHUB_IRQ_EP_POOL_ACK_STALL |
+	       VHUB_IRQ_BUS_RESUME |
+	       VHUB_IRQ_BUS_SUSPEND |
+	       VHUB_IRQ_BUS_RESET,
+	       vhub->regs + AST_VHUB_IER);
+}
+
+static int ast_vhub_remove(struct platform_device *pdev)
+{
+	struct ast_vhub *vhub = platform_get_drvdata(pdev);
+	unsigned long flags;
+	int i;
+
+	if (!vhub || !vhub->regs)
+		return 0;
+
+	/* Remove devices */
+	for (i = 0; i < AST_VHUB_NUM_PORTS; i++)
+		ast_vhub_del_dev(&vhub->ports[i].dev);
+
+	spin_lock_irqsave(&vhub->lock, flags);
+
+	/* Mask & ack all interrupts  */
+	writel(0, vhub->regs + AST_VHUB_IER);
+	writel(VHUB_IRQ_ACK_ALL, vhub->regs + AST_VHUB_ISR);
+
+	/* Pull device, leave PHY enabled */
+	writel(VHUB_CTRL_PHY_CLK |
+	       VHUB_CTRL_PHY_RESET_DIS,
+	       vhub->regs + AST_VHUB_CTRL);
+
+	if (vhub->clk)
+		clk_disable_unprepare(vhub->clk);
+
+	spin_unlock_irqrestore(&vhub->lock, flags);
+
+	if (vhub->ep0_bufs)
+		dma_free_coherent(&pdev->dev,
+				  AST_VHUB_EP0_MAX_PACKET *
+				  (AST_VHUB_NUM_PORTS + 1),
+				  vhub->ep0_bufs,
+				  vhub->ep0_bufs_dma);
+	vhub->ep0_bufs = NULL;
+
+	return 0;
+}
+
+static int ast_vhub_probe(struct platform_device *pdev)
+{
+	enum usb_device_speed max_speed;
+	struct ast_vhub *vhub;
+	struct resource *res;
+	int i, rc = 0;
+
+	vhub = devm_kzalloc(&pdev->dev, sizeof(*vhub), GFP_KERNEL);
+	if (!vhub)
+		return -ENOMEM;
+
+	spin_lock_init(&vhub->lock);
+	vhub->pdev = pdev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	vhub->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(vhub->regs)) {
+		dev_err(&pdev->dev, "Failed to map resources\n");
+		return PTR_ERR(vhub->regs);
+	}
+	UDCDBG(vhub, "vHub@%pR mapped @%p\n", res, vhub->regs);
+
+	platform_set_drvdata(pdev, vhub);
+
+	vhub->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(vhub->clk)) {
+		rc = PTR_ERR(vhub->clk);
+		goto err;
+	}
+	rc = clk_prepare_enable(vhub->clk);
+	if (rc) {
+		dev_err(&pdev->dev, "Error couldn't enable clock (%d)\n", rc);
+		goto err;
+	}
+
+	/* Check if we need to limit the HW to USB1 */
+	max_speed = usb_get_maximum_speed(&pdev->dev);
+	if (max_speed != USB_SPEED_UNKNOWN && max_speed < USB_SPEED_HIGH)
+		vhub->force_usb1 = true;
+
+	/* Mask & ack all interrupts before installing the handler */
+	writel(0, vhub->regs + AST_VHUB_IER);
+	writel(VHUB_IRQ_ACK_ALL, vhub->regs + AST_VHUB_ISR);
+
+	/* Find interrupt and install handler */
+	vhub->irq = platform_get_irq(pdev, 0);
+	if (vhub->irq < 0) {
+		dev_err(&pdev->dev, "Failed to get interrupt\n");
+		rc = vhub->irq;
+		goto err;
+	}
+	rc = devm_request_irq(&pdev->dev, vhub->irq, ast_vhub_irq, 0,
+			      KBUILD_MODNAME, vhub);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to request interrupt\n");
+		goto err;
+	}
+
+	/*
+	 * Allocate DMA buffers for all EP0s in one chunk,
+	 * one per port and one for the vHub itself
+	 */
+	vhub->ep0_bufs = dma_alloc_coherent(&pdev->dev,
+					    AST_VHUB_EP0_MAX_PACKET *
+					    (AST_VHUB_NUM_PORTS + 1),
+					    &vhub->ep0_bufs_dma, GFP_KERNEL);
+	if (!vhub->ep0_bufs) {
+		dev_err(&pdev->dev, "Failed to allocate EP0 DMA buffers\n");
+		rc = -ENOMEM;
+		goto err;
+	}
+	UDCVDBG(vhub, "EP0 DMA buffers @%p (DMA 0x%08x)\n",
+		vhub->ep0_bufs, (u32)vhub->ep0_bufs_dma);
+
+	/* Init vHub EP0 */
+	ast_vhub_init_ep0(vhub, &vhub->ep0, NULL);
+
+	/* Init devices */
+	for (i = 0; i < AST_VHUB_NUM_PORTS && rc == 0; i++)
+		rc = ast_vhub_init_dev(vhub, i);
+	if (rc)
+		goto err;
+
+	/* Init hub emulation */
+	ast_vhub_init_hub(vhub);
+
+	/* Initialize HW */
+	ast_vhub_init_hw(vhub);
+
+	dev_info(&pdev->dev, "Initialized virtual hub in USB%d mode\n",
+		 vhub->force_usb1 ? 1 : 2);
+
+	return 0;
+ err:
+	ast_vhub_remove(pdev);
+	return rc;
+}
+
+static const struct of_device_id ast_vhub_dt_ids[] = {
+	{
+		.compatible = "aspeed,ast2400-usb-vhub",
+	},
+	{
+		.compatible = "aspeed,ast2500-usb-vhub",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ast_vhub_dt_ids);
+
+static struct platform_driver ast_vhub_driver = {
+	.probe		= ast_vhub_probe,
+	.remove		= ast_vhub_remove,
+	.driver		= {
+		.name	= KBUILD_MODNAME,
+		.of_match_table	= ast_vhub_dt_ids,
+	},
+};
+module_platform_driver(ast_vhub_driver);
+
+MODULE_DESCRIPTION("Aspeed vHub udc driver");
+MODULE_AUTHOR("Benjamin Herrenschmidt <benh@kernel.crashing.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/dev.c b/drivers/usb/gadget/udc/aspeed-vhub/dev.c
new file mode 100644
index 000000000000..f0233912bace
--- /dev/null
+++ b/drivers/usb/gadget/udc/aspeed-vhub/dev.c
@@ -0,0 +1,589 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * aspeed-vhub -- Driver for Aspeed SoC "vHub" USB gadget
+ *
+ * dev.c - Individual device/gadget management (ie, a port = a gadget)
+ *
+ * Copyright 2017 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/proc_fs.h>
+#include <linux/prefetch.h>
+#include <linux/clk.h>
+#include <linux/usb/gadget.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/regmap.h>
+#include <linux/dma-mapping.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+
+#include "vhub.h"
+
+void ast_vhub_dev_irq(struct ast_vhub_dev *d)
+{
+	u32 istat = readl(d->regs + AST_VHUB_DEV_ISR);
+
+	writel(istat, d->regs + AST_VHUB_DEV_ISR);
+
+	if (istat & VHUV_DEV_IRQ_EP0_IN_ACK_STALL)
+		ast_vhub_ep0_handle_ack(&d->ep0, true);
+	if (istat & VHUV_DEV_IRQ_EP0_OUT_ACK_STALL)
+		ast_vhub_ep0_handle_ack(&d->ep0, false);
+	if (istat & VHUV_DEV_IRQ_EP0_SETUP)
+		ast_vhub_ep0_handle_setup(&d->ep0);
+}
+
+static void ast_vhub_dev_enable(struct ast_vhub_dev *d)
+{
+	u32 reg, hmsk;
+
+	if (d->enabled)
+		return;
+
+	/* Enable device and its EP0 interrupts */
+	reg = VHUB_DEV_EN_ENABLE_PORT |
+		VHUB_DEV_EN_EP0_IN_ACK_IRQEN |
+		VHUB_DEV_EN_EP0_OUT_ACK_IRQEN |
+		VHUB_DEV_EN_EP0_SETUP_IRQEN;
+	if (d->gadget.speed == USB_SPEED_HIGH)
+		reg |= VHUB_DEV_EN_SPEED_SEL_HIGH;
+	writel(reg, d->regs + AST_VHUB_DEV_EN_CTRL);
+
+	/* Enable device interrupt in the hub as well */
+	hmsk = VHUB_IRQ_DEVICE1 << d->index;
+	reg = readl(d->vhub->regs + AST_VHUB_IER);
+	reg |= hmsk;
+	writel(reg, d->vhub->regs + AST_VHUB_IER);
+
+	/* Set EP0 DMA buffer address */
+	writel(d->ep0.buf_dma, d->regs + AST_VHUB_DEV_EP0_DATA);
+
+	d->enabled = true;
+}
+
+static void ast_vhub_dev_disable(struct ast_vhub_dev *d)
+{
+	u32 reg, hmsk;
+
+	if (!d->enabled)
+		return;
+
+	/* Disable device interrupt in the hub */
+	hmsk = VHUB_IRQ_DEVICE1 << d->index;
+	reg = readl(d->vhub->regs + AST_VHUB_IER);
+	reg &= ~hmsk;
+	writel(reg, d->vhub->regs + AST_VHUB_IER);
+
+	/* Then disable device */
+	writel(0, d->regs + AST_VHUB_DEV_EN_CTRL);
+	d->gadget.speed = USB_SPEED_UNKNOWN;
+	d->enabled = false;
+	d->suspended = false;
+}
+
+static int ast_vhub_dev_feature(struct ast_vhub_dev *d,
+				u16 wIndex, u16 wValue,
+				bool is_set)
+{
+	DDBG(d, "%s_FEATURE(dev val=%02x)\n",
+	     is_set ? "SET" : "CLEAR", wValue);
+
+	if (wValue != USB_DEVICE_REMOTE_WAKEUP)
+		return std_req_driver;
+
+	d->wakeup_en = is_set;
+
+	return std_req_complete;
+}
+
+static int ast_vhub_ep_feature(struct ast_vhub_dev *d,
+			       u16 wIndex, u16 wValue, bool is_set)
+{
+	struct ast_vhub_ep *ep;
+	int ep_num;
+
+	ep_num = wIndex & USB_ENDPOINT_NUMBER_MASK;
+	DDBG(d, "%s_FEATURE(ep%d val=%02x)\n",
+	     is_set ? "SET" : "CLEAR", ep_num, wValue);
+	if (ep_num == 0)
+		return std_req_complete;
+	if (ep_num >= AST_VHUB_NUM_GEN_EPs || !d->epns[ep_num - 1])
+		return std_req_stall;
+	if (wValue != USB_ENDPOINT_HALT)
+		return std_req_driver;
+
+	ep = d->epns[ep_num - 1];
+	if (WARN_ON(!ep))
+		return std_req_stall;
+
+	if (!ep->epn.enabled || !ep->ep.desc || ep->epn.is_iso ||
+	    ep->epn.is_in != !!(wIndex & USB_DIR_IN))
+		return std_req_stall;
+
+	DDBG(d, "%s stall on EP %d\n",
+	     is_set ? "setting" : "clearing", ep_num);
+	ep->epn.stalled = is_set;
+	ast_vhub_update_epn_stall(ep);
+
+	return std_req_complete;
+}
+
+static int ast_vhub_dev_status(struct ast_vhub_dev *d,
+			       u16 wIndex, u16 wValue)
+{
+	u8 st0;
+
+	DDBG(d, "GET_STATUS(dev)\n");
+
+	st0 = d->gadget.is_selfpowered << USB_DEVICE_SELF_POWERED;
+	if (d->wakeup_en)
+		st0 |= 1 << USB_DEVICE_REMOTE_WAKEUP;
+
+	return ast_vhub_simple_reply(&d->ep0, st0, 0);
+}
+
+static int ast_vhub_ep_status(struct ast_vhub_dev *d,
+			      u16 wIndex, u16 wValue)
+{
+	int ep_num = wIndex & USB_ENDPOINT_NUMBER_MASK;
+	struct ast_vhub_ep *ep;
+	u8 st0 = 0;
+
+	DDBG(d, "GET_STATUS(ep%d)\n", ep_num);
+
+	if (ep_num >= AST_VHUB_NUM_GEN_EPs)
+		return std_req_stall;
+	if (ep_num != 0) {
+		ep = d->epns[ep_num - 1];
+		if (!ep)
+			return std_req_stall;
+		if (!ep->epn.enabled || !ep->ep.desc || ep->epn.is_iso ||
+		    ep->epn.is_in != !!(wIndex & USB_DIR_IN))
+			return std_req_stall;
+		if (ep->epn.stalled)
+			st0 |= 1 << USB_ENDPOINT_HALT;
+	}
+
+	return ast_vhub_simple_reply(&d->ep0, st0, 0);
+}
+
+static void ast_vhub_dev_set_address(struct ast_vhub_dev *d, u8 addr)
+{
+	u32 reg;
+
+	DDBG(d, "SET_ADDRESS: Got address %x\n", addr);
+
+	reg = readl(d->regs + AST_VHUB_DEV_EN_CTRL);
+	reg &= ~VHUB_DEV_EN_ADDR_MASK;
+	reg |= VHUB_DEV_EN_SET_ADDR(addr);
+	writel(reg, d->regs + AST_VHUB_DEV_EN_CTRL);
+}
+
+int ast_vhub_std_dev_request(struct ast_vhub_ep *ep,
+			     struct usb_ctrlrequest *crq)
+{
+	struct ast_vhub_dev *d = ep->dev;
+	u16 wValue, wIndex;
+
+	/* No driver, we shouldn't be enabled ... */
+	if (!d->driver || !d->enabled || d->suspended) {
+		EPDBG(ep,
+		      "Device is wrong state driver=%p enabled=%d"
+		      " suspended=%d\n",
+		      d->driver, d->enabled, d->suspended);
+		return std_req_stall;
+	}
+
+	/* First packet, grab speed */
+	if (d->gadget.speed == USB_SPEED_UNKNOWN) {
+		d->gadget.speed = ep->vhub->speed;
+		if (d->gadget.speed > d->driver->max_speed)
+			d->gadget.speed = d->driver->max_speed;
+		DDBG(d, "fist packet, captured speed %d\n",
+		     d->gadget.speed);
+	}
+
+	wValue = le16_to_cpu(crq->wValue);
+	wIndex = le16_to_cpu(crq->wIndex);
+
+	switch ((crq->bRequestType << 8) | crq->bRequest) {
+		/* SET_ADDRESS */
+	case DeviceOutRequest | USB_REQ_SET_ADDRESS:
+		ast_vhub_dev_set_address(d, wValue);
+		return std_req_complete;
+
+		/* GET_STATUS */
+	case DeviceRequest | USB_REQ_GET_STATUS:
+		return ast_vhub_dev_status(d, wIndex, wValue);
+	case InterfaceRequest | USB_REQ_GET_STATUS:
+		return ast_vhub_simple_reply(ep, 0, 0);
+	case EndpointRequest | USB_REQ_GET_STATUS:
+		return ast_vhub_ep_status(d, wIndex, wValue);
+
+		/* SET/CLEAR_FEATURE */
+	case DeviceOutRequest | USB_REQ_SET_FEATURE:
+		return ast_vhub_dev_feature(d, wIndex, wValue, true);
+	case DeviceOutRequest | USB_REQ_CLEAR_FEATURE:
+		return ast_vhub_dev_feature(d, wIndex, wValue, false);
+	case EndpointOutRequest | USB_REQ_SET_FEATURE:
+		return ast_vhub_ep_feature(d, wIndex, wValue, true);
+	case EndpointOutRequest | USB_REQ_CLEAR_FEATURE:
+		return ast_vhub_ep_feature(d, wIndex, wValue, false);
+	}
+	return std_req_driver;
+}
+
+static int ast_vhub_udc_wakeup(struct usb_gadget* gadget)
+{
+	struct ast_vhub_dev *d = to_ast_dev(gadget);
+	unsigned long flags;
+	int rc = -EINVAL;
+
+	spin_lock_irqsave(&d->vhub->lock, flags);
+	if (!d->wakeup_en)
+		goto err;
+
+	DDBG(d, "Device initiated wakeup\n");
+
+	/* Wakeup the host */
+	ast_vhub_hub_wake_all(d->vhub);
+	rc = 0;
+ err:
+	spin_unlock_irqrestore(&d->vhub->lock, flags);
+	return rc;
+}
+
+static int ast_vhub_udc_get_frame(struct usb_gadget* gadget)
+{
+	struct ast_vhub_dev *d = to_ast_dev(gadget);
+
+	return (readl(d->vhub->regs + AST_VHUB_USBSTS) >> 16) & 0x7ff;
+}
+
+static void ast_vhub_dev_nuke(struct ast_vhub_dev *d)
+{
+	unsigned int i;
+
+	for (i = 0; i < AST_VHUB_NUM_GEN_EPs; i++) {
+		if (!d->epns[i])
+			continue;
+		ast_vhub_nuke(d->epns[i], -ESHUTDOWN);
+	}
+}
+
+static int ast_vhub_udc_pullup(struct usb_gadget* gadget, int on)
+{
+	struct ast_vhub_dev *d = to_ast_dev(gadget);
+	unsigned long flags;
+
+	spin_lock_irqsave(&d->vhub->lock, flags);
+
+	DDBG(d, "pullup(%d)\n", on);
+
+	/* Mark disconnected in the hub */
+	ast_vhub_device_connect(d->vhub, d->index, on);
+
+	/*
+	 * If enabled, nuke all requests if any (there shouldn't be)
+	 * and disable the port. This will clear the address too.
+	 */
+	if (d->enabled) {
+		ast_vhub_dev_nuke(d);
+		ast_vhub_dev_disable(d);
+	}
+
+	spin_unlock_irqrestore(&d->vhub->lock, flags);
+
+	return 0;
+}
+
+static int ast_vhub_udc_start(struct usb_gadget *gadget,
+			      struct usb_gadget_driver *driver)
+{
+	struct ast_vhub_dev *d = to_ast_dev(gadget);
+	unsigned long flags;
+
+	spin_lock_irqsave(&d->vhub->lock, flags);
+
+	DDBG(d, "start\n");
+
+	/* We don't do much more until the hub enables us */
+	d->driver = driver;
+	d->gadget.is_selfpowered = 1;
+
+	spin_unlock_irqrestore(&d->vhub->lock, flags);
+
+	return 0;
+}
+
+static struct usb_ep *ast_vhub_udc_match_ep(struct usb_gadget *gadget,
+					    struct usb_endpoint_descriptor *desc,
+					    struct usb_ss_ep_comp_descriptor *ss)
+{
+	struct ast_vhub_dev *d = to_ast_dev(gadget);
+	struct ast_vhub_ep *ep;
+	struct usb_ep *u_ep;
+	unsigned int max, addr, i;
+
+	DDBG(d, "Match EP type %d\n", usb_endpoint_type(desc));
+
+	/*
+	 * First we need to look for an existing unclaimed EP as another
+	 * configuration may have already associated a bunch of EPs with
+	 * this gadget. This duplicates the code in usb_ep_autoconfig_ss()
+	 * unfortunately.
+	 */
+	list_for_each_entry(u_ep, &gadget->ep_list, ep_list) {
+		if (usb_gadget_ep_match_desc(gadget, u_ep, desc, ss)) {
+			DDBG(d, " -> using existing EP%d\n",
+			     to_ast_ep(u_ep)->d_idx);
+			return u_ep;
+		}
+	}
+
+	/*
+	 * We didn't find one, we need to grab one from the pool.
+	 *
+	 * First let's do some sanity checking
+	 */
+	switch(usb_endpoint_type(desc)) {
+	case USB_ENDPOINT_XFER_CONTROL:
+		/* Only EP0 can be a control endpoint */
+		return NULL;
+	case USB_ENDPOINT_XFER_ISOC:
+		/* ISO:	 limit 1023 bytes full speed, 1024 high/super speed */
+		if (gadget_is_dualspeed(gadget))
+			max = 1024;
+		else
+			max = 1023;
+		break;
+	case USB_ENDPOINT_XFER_BULK:
+		if (gadget_is_dualspeed(gadget))
+			max = 512;
+		else
+			max = 64;
+		break;
+	case USB_ENDPOINT_XFER_INT:
+		if (gadget_is_dualspeed(gadget))
+			max = 1024;
+		else
+			max = 64;
+		break;
+	}
+	if (usb_endpoint_maxp(desc) > max)
+		return NULL;
+
+	/*
+	 * Find a free EP address for that device. We can't
+	 * let the generic code assign these as it would
+	 * create overlapping numbers for IN and OUT which
+	 * we don't support, so also create a suitable name
+	 * that will allow the generic code to use our
+	 * assigned address.
+	 */
+	for (i = 0; i < AST_VHUB_NUM_GEN_EPs; i++)
+		if (d->epns[i] == NULL)
+			break;
+	if (i >= AST_VHUB_NUM_GEN_EPs)
+		return NULL;
+	addr = i + 1;
+
+	/*
+	 * Now grab an EP from the shared pool and associate
+	 * it with our device
+	 */
+	ep = ast_vhub_alloc_epn(d, addr);
+	if (!ep)
+		return NULL;
+	DDBG(d, "Allocated epn#%d for port EP%d\n",
+	     ep->epn.g_idx, addr);
+
+	return &ep->ep;
+}
+
+static int ast_vhub_udc_stop(struct usb_gadget *gadget)
+{
+	struct ast_vhub_dev *d = to_ast_dev(gadget);
+	unsigned long flags;
+
+	spin_lock_irqsave(&d->vhub->lock, flags);
+
+	DDBG(d, "stop\n");
+
+	d->driver = NULL;
+	d->gadget.speed = USB_SPEED_UNKNOWN;
+
+	ast_vhub_dev_nuke(d);
+
+	if (d->enabled)
+		ast_vhub_dev_disable(d);
+
+	spin_unlock_irqrestore(&d->vhub->lock, flags);
+
+	return 0;
+}
+
+static struct usb_gadget_ops ast_vhub_udc_ops = {
+	.get_frame	= ast_vhub_udc_get_frame,
+	.wakeup		= ast_vhub_udc_wakeup,
+	.pullup		= ast_vhub_udc_pullup,
+	.udc_start	= ast_vhub_udc_start,
+	.udc_stop	= ast_vhub_udc_stop,
+	.match_ep	= ast_vhub_udc_match_ep,
+};
+
+void ast_vhub_dev_suspend(struct ast_vhub_dev *d)
+{
+	d->suspended = true;
+	if (d->driver) {
+		spin_unlock(&d->vhub->lock);
+		d->driver->suspend(&d->gadget);
+		spin_lock(&d->vhub->lock);
+	}
+}
+
+void ast_vhub_dev_resume(struct ast_vhub_dev *d)
+{
+	d->suspended = false;
+	if (d->driver) {
+		spin_unlock(&d->vhub->lock);
+		d->driver->resume(&d->gadget);
+		spin_lock(&d->vhub->lock);
+	}
+}
+
+void ast_vhub_dev_reset(struct ast_vhub_dev *d)
+{
+	/*
+	 * If speed is not set, we enable the port. If it is,
+	 * send reset to the gadget and reset "speed".
+	 *
+	 * Speed is an indication that we have got the first
+	 * setup packet to the device.
+	 */
+	if (d->gadget.speed == USB_SPEED_UNKNOWN && !d->enabled) {
+		DDBG(d, "Reset at unknown speed of disabled device, enabling...\n");
+		ast_vhub_dev_enable(d);
+		d->suspended = false;
+	}
+	if (d->gadget.speed != USB_SPEED_UNKNOWN && d->driver) {
+		unsigned int i;
+
+		DDBG(d, "Reset at known speed of bound device, resetting...\n");
+		spin_unlock(&d->vhub->lock);
+		d->driver->reset(&d->gadget);
+		spin_lock(&d->vhub->lock);
+
+		/*
+		 * Disable/re-enable HW, this will clear the address
+		 * and speed setting.
+		 */
+		ast_vhub_dev_disable(d);
+		ast_vhub_dev_enable(d);
+
+		/* Clear stall on all EPs */
+		for (i = 0; i < AST_VHUB_NUM_GEN_EPs; i++) {
+			struct ast_vhub_ep *ep = d->epns[i];
+
+			if (ep && ep->epn.stalled) {
+				ep->epn.stalled = false;
+				ast_vhub_update_epn_stall(ep);
+			}
+		}
+
+		/* Additional cleanups */
+		d->wakeup_en = false;
+		d->suspended = false;
+	}
+}
+
+void ast_vhub_del_dev(struct ast_vhub_dev *d)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&d->vhub->lock, flags);
+	if (!d->registered) {
+		spin_unlock_irqrestore(&d->vhub->lock, flags);
+		return;
+	}
+	d->registered = false;
+	spin_unlock_irqrestore(&d->vhub->lock, flags);
+
+	usb_del_gadget_udc(&d->gadget);
+	device_unregister(d->port_dev);
+}
+
+static void ast_vhub_dev_release(struct device *dev)
+{
+	kfree(dev);
+}
+
+int ast_vhub_init_dev(struct ast_vhub *vhub, unsigned int idx)
+{
+	struct ast_vhub_dev *d = &vhub->ports[idx].dev;
+	struct device *parent = &vhub->pdev->dev;
+	int rc;
+
+	d->vhub = vhub;
+	d->index = idx;
+	d->name = devm_kasprintf(parent, GFP_KERNEL, "port%d", idx+1);
+	d->regs = vhub->regs + 0x100 + 0x10 * idx;
+
+	ast_vhub_init_ep0(vhub, &d->ep0, d);
+
+	/*
+	 * The UDC core really needs us to have separate and uniquely
+	 * named "parent" devices for each port so we create a sub device
+	 * here for that purpose
+	 */
+	d->port_dev = kzalloc(sizeof(struct device), GFP_KERNEL);
+	if (!d->port_dev)
+		return -ENOMEM;
+	device_initialize(d->port_dev);
+	d->port_dev->release = ast_vhub_dev_release;
+	d->port_dev->parent = parent;
+	dev_set_name(d->port_dev, "%s:p%d", dev_name(parent), idx + 1);
+	rc = device_add(d->port_dev);
+	if (rc)
+		goto fail_add;
+
+	/* Populate gadget */
+	INIT_LIST_HEAD(&d->gadget.ep_list);
+	d->gadget.ops = &ast_vhub_udc_ops;
+	d->gadget.ep0 = &d->ep0.ep;
+	d->gadget.name = KBUILD_MODNAME;
+	if (vhub->force_usb1)
+		d->gadget.max_speed = USB_SPEED_FULL;
+	else
+		d->gadget.max_speed = USB_SPEED_HIGH;
+	d->gadget.speed = USB_SPEED_UNKNOWN;
+	d->gadget.dev.of_node = vhub->pdev->dev.of_node;
+
+	rc = usb_add_gadget_udc(d->port_dev, &d->gadget);
+	if (rc != 0)
+		goto fail_udc;
+	d->registered = true;
+
+	return 0;
+ fail_udc:
+	device_del(d->port_dev);
+ fail_add:
+	put_device(d->port_dev);
+
+	return rc;
+}
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
new file mode 100644
index 000000000000..20ffb03ff6ac
--- /dev/null
+++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * aspeed-vhub -- Driver for Aspeed SoC "vHub" USB gadget
+ *
+ * ep0.c - Endpoint 0 handling
+ *
+ * Copyright 2017 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/proc_fs.h>
+#include <linux/prefetch.h>
+#include <linux/clk.h>
+#include <linux/usb/gadget.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/regmap.h>
+#include <linux/dma-mapping.h>
+
+#include "vhub.h"
+
+int ast_vhub_reply(struct ast_vhub_ep *ep, char *ptr, int len)
+{
+	struct usb_request *req = &ep->ep0.req.req;
+	int rc;
+
+	if (WARN_ON(ep->d_idx != 0))
+		return std_req_stall;
+	if (WARN_ON(!ep->ep0.dir_in))
+		return std_req_stall;
+	if (WARN_ON(len > AST_VHUB_EP0_MAX_PACKET))
+		return std_req_stall;
+	if (WARN_ON(req->status == -EINPROGRESS))
+		return std_req_stall;
+
+	req->buf = ptr;
+	req->length = len;
+	req->complete = NULL;
+	req->zero = true;
+
+	/*
+	 * Call internal queue directly after dropping the lock. This is
+	 * safe to do as the reply is always the last thing done when
+	 * processing a SETUP packet, usually as a tail call
+	 */
+	spin_unlock(&ep->vhub->lock);
+	if (ep->ep.ops->queue(&ep->ep, req, GFP_ATOMIC))
+		rc = std_req_stall;
+	else
+		rc = std_req_data;
+	spin_lock(&ep->vhub->lock);
+	return rc;
+}
+
+int __ast_vhub_simple_reply(struct ast_vhub_ep *ep, int len, ...)
+{
+	u8 *buffer = ep->buf;
+	unsigned int i;
+	va_list args;
+
+	va_start(args, len);
+
+	/* Copy data directly into EP buffer */
+	for (i = 0; i < len; i++)
+		buffer[i] = va_arg(args, int);
+	va_end(args);
+
+	/* req->buf NULL means data is already there */
+	return ast_vhub_reply(ep, NULL, len);
+}
+
+void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep)
+{
+	struct usb_ctrlrequest crq;
+	enum std_req_rc std_req_rc;
+	int rc = -ENODEV;
+
+	if (WARN_ON(ep->d_idx != 0))
+		return;
+
+	/*
+	 * Grab the setup packet from the chip and byteswap
+	 * interesting fields
+	 */
+	memcpy_fromio(&crq, ep->ep0.setup, sizeof(crq));
+
+	EPDBG(ep, "SETUP packet %02x/%02x/%04x/%04x/%04x [%s] st=%d\n",
+	      crq.bRequestType, crq.bRequest,
+	       le16_to_cpu(crq.wValue),
+	       le16_to_cpu(crq.wIndex),
+	       le16_to_cpu(crq.wLength),
+	       (crq.bRequestType & USB_DIR_IN) ? "in" : "out",
+	       ep->ep0.state);
+
+	/* Check our state, cancel pending requests if needed */
+	if (ep->ep0.state != ep0_state_token) {
+		EPDBG(ep, "wrong state\n");
+		ast_vhub_nuke(ep, 0);
+		goto stall;
+	}
+
+	/* Calculate next state for EP0 */
+	ep->ep0.state = ep0_state_data;
+	ep->ep0.dir_in = !!(crq.bRequestType & USB_DIR_IN);
+
+	/* If this is the vHub, we handle requests differently */
+	std_req_rc = std_req_driver;
+	if (ep->dev == NULL) {
+		if ((crq.bRequestType & USB_TYPE_MASK) == USB_TYPE_STANDARD)
+			std_req_rc = ast_vhub_std_hub_request(ep, &crq);
+		else if ((crq.bRequestType & USB_TYPE_MASK) == USB_TYPE_CLASS)
+			std_req_rc = ast_vhub_class_hub_request(ep, &crq);
+		else
+			std_req_rc = std_req_stall;
+	} else if ((crq.bRequestType & USB_TYPE_MASK) == USB_TYPE_STANDARD)
+		std_req_rc = ast_vhub_std_dev_request(ep, &crq);
+
+	/* Act upon result */
+	switch(std_req_rc) {
+	case std_req_complete:
+		goto complete;
+	case std_req_stall:
+		goto stall;
+	case std_req_driver:
+		break;
+	case std_req_data:
+		return;
+	}
+
+	/* Pass request up to the gadget driver */
+	if (WARN_ON(!ep->dev))
+		goto stall;
+	if (ep->dev->driver) {
+		EPDBG(ep, "forwarding to gadget...\n");
+		spin_unlock(&ep->vhub->lock);
+		rc = ep->dev->driver->setup(&ep->dev->gadget, &crq);
+		spin_lock(&ep->vhub->lock);
+		EPDBG(ep, "driver returned %d\n", rc);
+	} else {
+		EPDBG(ep, "no gadget for request !\n");
+	}
+	if (rc >= 0)
+		return;
+
+ stall:
+	EPDBG(ep, "stalling\n");
+	writel(VHUB_EP0_CTRL_STALL, ep->ep0.ctlstat);
+	ep->ep0.state = ep0_state_status;
+	ep->ep0.dir_in = false;
+	return;
+
+ complete:
+	EPVDBG(ep, "sending [in] status with no data\n");
+	writel(VHUB_EP0_TX_BUFF_RDY, ep->ep0.ctlstat);
+	ep->ep0.state = ep0_state_status;
+	ep->ep0.dir_in = false;
+}
+
+
+static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep,
+				 struct ast_vhub_req *req)
+{
+	unsigned int chunk;
+	u32 reg;
+
+	/* If this is a 0-length request, it's the gadget trying to
+	 * send a status on our behalf. We take it from here.
+	 */
+	if (req->req.length == 0)
+		req->last_desc = 1;
+
+	/* Are we done ? Complete request, otherwise wait for next interrupt */
+	if (req->last_desc >= 0) {
+		EPVDBG(ep, "complete send %d/%d\n",
+		       req->req.actual, req->req.length);
+		ep->ep0.state = ep0_state_status;
+		writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat);
+		ast_vhub_done(ep, req, 0);
+		return;
+	}
+
+	/*
+	 * Next chunk cropped to max packet size. Also check if this
+	 * is the last packet
+	 */
+	chunk = req->req.length - req->req.actual;
+	if (chunk > ep->ep.maxpacket)
+		chunk = ep->ep.maxpacket;
+	else if ((chunk < ep->ep.maxpacket) || !req->req.zero)
+		req->last_desc = 1;
+
+	EPVDBG(ep, "send chunk=%d last=%d, req->act=%d mp=%d\n",
+	       chunk, req->last_desc, req->req.actual, ep->ep.maxpacket);
+
+	/*
+	 * Copy data if any (internal requests already have data
+	 * in the EP buffer)
+	 */
+	if (chunk && req->req.buf)
+		memcpy(ep->buf, req->req.buf + req->req.actual, chunk);
+
+	/* Remember chunk size and trigger send */
+	reg = VHUB_EP0_SET_TX_LEN(chunk);
+	writel(reg, ep->ep0.ctlstat);
+	writel(reg | VHUB_EP0_TX_BUFF_RDY, ep->ep0.ctlstat);
+	req->req.actual += chunk;
+}
+
+static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep)
+{
+	EPVDBG(ep, "rx prime\n");
+
+	/* Prime endpoint for receiving data */
+	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL);
+}
+
+static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
+				    unsigned int len)
+{
+	unsigned int remain;
+	int rc = 0;
+
+	/* We are receiving... grab request */
+	remain = req->req.length - req->req.actual;
+
+	EPVDBG(ep, "receive got=%d remain=%d\n", len, remain);
+
+	/* Are we getting more than asked ? */
+	if (len > remain) {
+		EPDBG(ep, "receiving too much (ovf: %d) !\n",
+		      len - remain);
+		len = remain;
+		rc = -EOVERFLOW;
+	}
+	if (len && req->req.buf)
+		memcpy(req->req.buf + req->req.actual, ep->buf, len);
+	req->req.actual += len;
+
+	/* Done ? */
+	if (len < ep->ep.maxpacket || len == remain) {
+		ep->ep0.state = ep0_state_status;
+		writel(VHUB_EP0_TX_BUFF_RDY, ep->ep0.ctlstat);
+		ast_vhub_done(ep, req, rc);
+	} else
+		ast_vhub_ep0_rx_prime(ep);
+}
+
+void ast_vhub_ep0_handle_ack(struct ast_vhub_ep *ep, bool in_ack)
+{
+	struct ast_vhub_req *req;
+	struct ast_vhub *vhub = ep->vhub;
+	struct device *dev = &vhub->pdev->dev;
+	bool stall = false;
+	u32 stat;
+
+	/* Read EP0 status */
+	stat = readl(ep->ep0.ctlstat);
+
+	/* Grab current request if any */
+	req = list_first_entry_or_null(&ep->queue, struct ast_vhub_req, queue);
+
+	EPVDBG(ep, "ACK status=%08x,state=%d is_in=%d in_ack=%d req=%p\n",
+		stat, ep->ep0.state, ep->ep0.dir_in, in_ack, req);
+
+	switch(ep->ep0.state) {
+	case ep0_state_token:
+		/* There should be no request queued in that state... */
+		if (req) {
+			dev_warn(dev, "request present while in TOKEN state\n");
+			ast_vhub_nuke(ep, -EINVAL);
+		}
+		dev_warn(dev, "ack while in TOKEN state\n");
+		stall = true;
+		break;
+	case ep0_state_data:
+		/* Check the state bits corresponding to our direction */
+		if ((ep->ep0.dir_in && (stat & VHUB_EP0_TX_BUFF_RDY)) ||
+		    (!ep->ep0.dir_in && (stat & VHUB_EP0_RX_BUFF_RDY)) ||
+		    (ep->ep0.dir_in != in_ack)) {
+			dev_warn(dev, "irq state mismatch");
+			stall = true;
+			break;
+		}
+		/*
+		 * We are in data phase and there's no request, something is
+		 * wrong, stall
+		 */
+		if (!req) {
+			dev_warn(dev, "data phase, no request\n");
+			stall = true;
+			break;
+		}
+
+		/* We have a request, handle data transfers */
+		if (ep->ep0.dir_in)
+			ast_vhub_ep0_do_send(ep, req);
+		else
+			ast_vhub_ep0_do_receive(ep, req, VHUB_EP0_RX_LEN(stat));
+		return;
+	case ep0_state_status:
+		/* Nuke stale requests */
+		if (req) {
+			dev_warn(dev, "request present while in STATUS state\n");
+			ast_vhub_nuke(ep, -EINVAL);
+		}
+
+		/*
+		 * If the status phase completes with the wrong ack, stall
+		 * the endpoint just in case, to abort whatever the host
+		 * was doing.
+		 */
+		if (ep->ep0.dir_in == in_ack) {
+			dev_warn(dev, "status direction mismatch\n");
+			stall = true;
+		}
+	}
+
+	/* Reset to token state */
+	ep->ep0.state = ep0_state_token;
+	if (stall)
+		writel(VHUB_EP0_CTRL_STALL, ep->ep0.ctlstat);
+}
+
+static int ast_vhub_ep0_queue(struct usb_ep* u_ep, struct usb_request *u_req,
+			      gfp_t gfp_flags)
+{
+	struct ast_vhub_req *req = to_ast_req(u_req);
+	struct ast_vhub_ep *ep = to_ast_ep(u_ep);
+	struct ast_vhub *vhub = ep->vhub;
+	struct device *dev = &vhub->pdev->dev;
+	unsigned long flags;
+
+	/* Paranoid cheks */
+	if (!u_req || (!u_req->complete && !req->internal)) {
+		dev_warn(dev, "Bogus EP0 request ! u_req=%p\n", u_req);
+		if (u_req) {
+			dev_warn(dev, "complete=%p internal=%d\n",
+				 u_req->complete, req->internal);
+		}
+		return -EINVAL;
+	}
+
+	/* Not endpoint 0 ? */
+	if (WARN_ON(ep->d_idx != 0))
+		return -EINVAL;
+
+	/* Disabled device */
+	if (ep->dev && (!ep->dev->enabled || ep->dev->suspended))
+		return -ESHUTDOWN;
+
+	/* Data, no buffer and not internal ? */
+	if (u_req->length && !u_req->buf && !req->internal) {
+		dev_warn(dev, "Request with no buffer !\n");
+		return -EINVAL;
+	}
+
+	EPVDBG(ep, "enqueue req @%p\n", req);
+	EPVDBG(ep, "  l=%d zero=%d noshort=%d is_in=%d\n",
+	       u_req->length, u_req->zero,
+	       u_req->short_not_ok, ep->ep0.dir_in);
+
+	/* Initialize request progress fields */
+	u_req->status = -EINPROGRESS;
+	u_req->actual = 0;
+	req->last_desc = -1;
+	req->active = false;
+
+	spin_lock_irqsave(&vhub->lock, flags);
+
+	/* EP0 can only support a single request at a time */
+	if (!list_empty(&ep->queue) || ep->ep0.state == ep0_state_token) {
+		dev_warn(dev, "EP0: Request in wrong state\n");
+		spin_unlock_irqrestore(&vhub->lock, flags);
+		return -EBUSY;
+	}
+
+	/* Add request to list and kick processing if empty */
+	list_add_tail(&req->queue, &ep->queue);
+
+	if (ep->ep0.dir_in) {
+		/* IN request, send data */
+		ast_vhub_ep0_do_send(ep, req);
+	} else if (u_req->length == 0) {
+		/* 0-len request, send completion as rx */
+		EPVDBG(ep, "0-length rx completion\n");
+		ep->ep0.state = ep0_state_status;
+		writel(VHUB_EP0_TX_BUFF_RDY, ep->ep0.ctlstat);
+		ast_vhub_done(ep, req, 0);
+	} else {
+		/* OUT request, start receiver */
+		ast_vhub_ep0_rx_prime(ep);
+	}
+
+	spin_unlock_irqrestore(&vhub->lock, flags);
+
+	return 0;
+}
+
+static int ast_vhub_ep0_dequeue(struct usb_ep* u_ep, struct usb_request *u_req)
+{
+	struct ast_vhub_ep *ep = to_ast_ep(u_ep);
+	struct ast_vhub *vhub = ep->vhub;
+	struct ast_vhub_req *req;
+	unsigned long flags;
+	int rc = -EINVAL;
+
+	spin_lock_irqsave(&vhub->lock, flags);
+
+	/* Only one request can be in the queue */
+	req = list_first_entry_or_null(&ep->queue, struct ast_vhub_req, queue);
+
+	/* Is it ours ? */
+	if (req && u_req == &req->req) {
+		EPVDBG(ep, "dequeue req @%p\n", req);
+
+		/*
+		 * We don't have to deal with "active" as all
+		 * DMAs go to the EP buffers, not the request.
+		 */
+		ast_vhub_done(ep, req, -ECONNRESET);
+
+		/* We do stall the EP to clean things up in HW */
+		writel(VHUB_EP0_CTRL_STALL, ep->ep0.ctlstat);
+		ep->ep0.state = ep0_state_status;
+		ep->ep0.dir_in = false;
+		rc = 0;
+	}
+	spin_unlock_irqrestore(&vhub->lock, flags);
+	return rc;
+}
+
+
+static const struct usb_ep_ops ast_vhub_ep0_ops = {
+	.queue		= ast_vhub_ep0_queue,
+	.dequeue	= ast_vhub_ep0_dequeue,
+	.alloc_request	= ast_vhub_alloc_request,
+	.free_request	= ast_vhub_free_request,
+};
+
+void ast_vhub_init_ep0(struct ast_vhub *vhub, struct ast_vhub_ep *ep,
+		       struct ast_vhub_dev *dev)
+{
+	memset(ep, 0, sizeof(*ep));
+
+	INIT_LIST_HEAD(&ep->ep.ep_list);
+	INIT_LIST_HEAD(&ep->queue);
+	ep->ep.ops = &ast_vhub_ep0_ops;
+	ep->ep.name = "ep0";
+	ep->ep.caps.type_control = true;
+	usb_ep_set_maxpacket_limit(&ep->ep, AST_VHUB_EP0_MAX_PACKET);
+	ep->d_idx = 0;
+	ep->dev = dev;
+	ep->vhub = vhub;
+	ep->ep0.state = ep0_state_token;
+	INIT_LIST_HEAD(&ep->ep0.req.queue);
+	ep->ep0.req.internal = true;
+
+	/* Small difference between vHub and devices */
+	if (dev) {
+		ep->ep0.ctlstat = dev->regs + AST_VHUB_DEV_EP0_CTRL;
+		ep->ep0.setup = vhub->regs +
+			AST_VHUB_SETUP0 + 8 * (dev->index + 1);
+		ep->buf = vhub->ep0_bufs +
+			AST_VHUB_EP0_MAX_PACKET * (dev->index + 1);
+		ep->buf_dma = vhub->ep0_bufs_dma +
+			AST_VHUB_EP0_MAX_PACKET * (dev->index + 1);
+	} else {
+		ep->ep0.ctlstat = vhub->regs + AST_VHUB_EP0_CTRL;
+		ep->ep0.setup = vhub->regs + AST_VHUB_SETUP0;
+		ep->buf = vhub->ep0_bufs;
+		ep->buf_dma = vhub->ep0_bufs_dma;
+	}
+}
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c
new file mode 100644
index 000000000000..80c9feac5147
--- /dev/null
+++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c
@@ -0,0 +1,843 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * aspeed-vhub -- Driver for Aspeed SoC "vHub" USB gadget
+ *
+ * epn.c - Generic endpoints management
+ *
+ * Copyright 2017 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/proc_fs.h>
+#include <linux/prefetch.h>
+#include <linux/clk.h>
+#include <linux/usb/gadget.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/regmap.h>
+#include <linux/dma-mapping.h>
+
+#include "vhub.h"
+
+#define EXTRA_CHECKS
+
+#ifdef EXTRA_CHECKS
+#define CHECK(ep, expr, fmt...)					\
+	do {							\
+		if (!(expr)) EPDBG(ep, "CHECK:" fmt);		\
+	} while(0)
+#else
+#define CHECK(ep, expr, fmt...)	do { } while(0)
+#endif
+
+static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req)
+{
+	unsigned int act = req->req.actual;
+	unsigned int len = req->req.length;
+	unsigned int chunk;
+
+	/* There should be no DMA ongoing */
+	WARN_ON(req->active);
+
+	/* Calculate next chunk size */
+	chunk = len - act;
+	if (chunk > ep->ep.maxpacket)
+		chunk = ep->ep.maxpacket;
+	else if ((chunk < ep->ep.maxpacket) || !req->req.zero)
+		req->last_desc = 1;
+
+	EPVDBG(ep, "kick req %p act=%d/%d chunk=%d last=%d\n",
+	       req, act, len, chunk, req->last_desc);
+
+	/* If DMA unavailable, using staging EP buffer */
+	if (!req->req.dma) {
+
+		/* For IN transfers, copy data over first */
+		if (ep->epn.is_in)
+			memcpy(ep->buf, req->req.buf + act, chunk);
+		writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
+	} else
+		writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
+
+	/* Start DMA */
+	req->active = true;
+	writel(VHUB_EP_DMA_SET_TX_SIZE(chunk),
+	       ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+	writel(VHUB_EP_DMA_SET_TX_SIZE(chunk) | VHUB_EP_DMA_SINGLE_KICK,
+	       ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+}
+
+static void ast_vhub_epn_handle_ack(struct ast_vhub_ep *ep)
+{
+	struct ast_vhub_req *req;
+	unsigned int len;
+	u32 stat;
+
+	/* Read EP status */
+	stat = readl(ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+
+	/* Grab current request if any */
+	req = list_first_entry_or_null(&ep->queue, struct ast_vhub_req, queue);
+
+	EPVDBG(ep, "ACK status=%08x is_in=%d, req=%p (active=%d)\n",
+	       stat, ep->epn.is_in, req, req ? req->active : 0);
+
+	/* In absence of a request, bail out, must have been dequeued */
+	if (!req)
+		return;
+
+	/*
+	 * Request not active, move on to processing queue, active request
+	 * was probably dequeued
+	 */
+	if (!req->active)
+		goto next_chunk;
+
+	/* Check if HW has moved on */
+	if (VHUB_EP_DMA_RPTR(stat) != 0) {
+		EPDBG(ep, "DMA read pointer not 0 !\n");
+		return;
+	}
+
+	/* No current DMA ongoing */
+	req->active = false;
+
+	/* Grab lenght out of HW */
+	len = VHUB_EP_DMA_TX_SIZE(stat);
+
+	/* If not using DMA, copy data out if needed */
+	if (!req->req.dma && !ep->epn.is_in && len)
+		memcpy(req->req.buf + req->req.actual, ep->buf, len);
+
+	/* Adjust size */
+	req->req.actual += len;
+
+	/* Check for short packet */
+	if (len < ep->ep.maxpacket)
+		req->last_desc = 1;
+
+	/* That's it ? complete the request and pick a new one */
+	if (req->last_desc >= 0) {
+		ast_vhub_done(ep, req, 0);
+		req = list_first_entry_or_null(&ep->queue, struct ast_vhub_req,
+					       queue);
+
+		/*
+		 * Due to lock dropping inside "done" the next request could
+		 * already be active, so check for that and bail if needed.
+		 */
+		if (!req || req->active)
+			return;
+	}
+
+ next_chunk:
+	ast_vhub_epn_kick(ep, req);
+}
+
+static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep)
+{
+	/*
+	 * d_next == d_last means descriptor list empty to HW,
+	 * thus we can only have AST_VHUB_DESCS_COUNT-1 descriptors
+	 * in the list
+	 */
+	return (ep->epn.d_last + AST_VHUB_DESCS_COUNT - ep->epn.d_next - 1) &
+		(AST_VHUB_DESCS_COUNT - 1);
+}
+
+static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
+				   struct ast_vhub_req *req)
+{
+	unsigned int act = req->act_count;
+	unsigned int len = req->req.length;
+	unsigned int chunk;
+
+	/* Mark request active if not already */
+	req->active = true;
+
+	/* If the request was already completely written, do nothing */
+	if (req->last_desc >= 0)
+		return;
+
+	EPVDBG(ep, "kick act=%d/%d chunk_max=%d free_descs=%d\n",
+	       act, len, ep->epn.chunk_max, ast_vhub_count_free_descs(ep));
+
+	/* While we can create descriptors */
+	while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) {
+		struct ast_vhub_desc *desc;
+		unsigned int d_num;
+
+		/* Grab next free descriptor */
+		d_num = ep->epn.d_next;
+		desc = &ep->epn.descs[d_num];
+		ep->epn.d_next = (d_num + 1) & (AST_VHUB_DESCS_COUNT - 1);
+
+		/* Calculate next chunk size */
+		chunk = len - act;
+		if (chunk <= ep->epn.chunk_max) {
+			/*
+			 * Is this the last packet ? Because of having up to 8
+			 * packets in a descriptor we can't just compare "chunk"
+			 * with ep.maxpacket. We have to see if it's a multiple
+			 * of it to know if we have to send a zero packet.
+			 * Sadly that involves a modulo which is a bit expensive
+			 * but probably still better than not doing it.
+			 */
+			if (!chunk || !req->req.zero || (chunk % ep->ep.maxpacket) != 0)
+				req->last_desc = d_num;
+		} else {
+			chunk = ep->epn.chunk_max;
+		}
+
+		EPVDBG(ep, " chunk: act=%d/%d chunk=%d last=%d desc=%d free=%d\n",
+		       act, len, chunk, req->last_desc, d_num,
+		       ast_vhub_count_free_descs(ep));
+
+		/* Populate descriptor */
+		desc->w0 = cpu_to_le32(req->req.dma + act);
+
+		/* Interrupt if end of request or no more descriptors */
+
+		/*
+		 * TODO: Be smarter about it, if we don't have enough
+		 * descriptors request an interrupt before queue empty
+		 * or so in order to be able to populate more before
+		 * the HW runs out. This isn't a problem at the moment
+		 * as we use 256 descriptors and only put at most one
+		 * request in the ring.
+		 */
+		desc->w1 = cpu_to_le32(VHUB_DSC1_IN_SET_LEN(chunk));
+		if (req->last_desc >= 0 || !ast_vhub_count_free_descs(ep))
+			desc->w1 |= cpu_to_le32(VHUB_DSC1_IN_INTERRUPT);
+
+		/* Account packet */
+		req->act_count = act = act + chunk;
+	}
+
+	/* Tell HW about new descriptors */
+	writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next),
+	       ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+
+	EPVDBG(ep, "HW kicked, d_next=%d dstat=%08x\n",
+	       ep->epn.d_next, readl(ep->epn.regs + AST_VHUB_EP_DESC_STATUS));
+}
+
+static void ast_vhub_epn_handle_ack_desc(struct ast_vhub_ep *ep)
+{
+	struct ast_vhub_req *req;
+	unsigned int len, d_last;
+	u32 stat, stat1;
+
+	/* Read EP status, workaround HW race */
+	do {
+		stat = readl(ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+		stat1 = readl(ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+	} while(stat != stat1);
+
+	/* Extract RPTR */
+	d_last = VHUB_EP_DMA_RPTR(stat);
+
+	/* Grab current request if any */
+	req = list_first_entry_or_null(&ep->queue, struct ast_vhub_req, queue);
+
+	EPVDBG(ep, "ACK status=%08x is_in=%d ep->d_last=%d..%d\n",
+	       stat, ep->epn.is_in, ep->epn.d_last, d_last);
+
+	/* Check all completed descriptors */
+	while (ep->epn.d_last != d_last) {
+		struct ast_vhub_desc *desc;
+		unsigned int d_num;
+		bool is_last_desc;
+
+		/* Grab next completed descriptor */
+		d_num = ep->epn.d_last;
+		desc = &ep->epn.descs[d_num];
+		ep->epn.d_last = (d_num + 1) & (AST_VHUB_DESCS_COUNT - 1);
+
+		/* Grab len out of descriptor */
+		len = VHUB_DSC1_IN_LEN(le32_to_cpu(desc->w1));
+
+		EPVDBG(ep, " desc %d len=%d req=%p (act=%d)\n",
+		       d_num, len, req, req ? req->active : 0);
+
+		/* If no active request pending, move on */
+		if (!req || !req->active)
+			continue;
+
+		/* Adjust size */
+		req->req.actual += len;
+
+		/* Is that the last chunk ? */
+		is_last_desc = req->last_desc == d_num;
+		CHECK(ep, is_last_desc == (len < ep->ep.maxpacket ||
+					   (req->req.actual >= req->req.length &&
+					    !req->req.zero)),
+		      "Last packet discrepancy: last_desc=%d len=%d r.act=%d "
+		      "r.len=%d r.zero=%d mp=%d\n",
+		      is_last_desc, len, req->req.actual, req->req.length,
+		      req->req.zero, ep->ep.maxpacket);
+
+		if (is_last_desc) {
+			/*
+			 * Because we can only have one request at a time
+			 * in our descriptor list in this implementation,
+			 * d_last and ep->d_last should now be equal
+			 */
+			CHECK(ep, d_last == ep->epn.d_last,
+			      "DMA read ptr mismatch %d vs %d\n",
+			      d_last, ep->epn.d_last);
+
+			/* Note: done will drop and re-acquire the lock */
+			ast_vhub_done(ep, req, 0);
+			req = list_first_entry_or_null(&ep->queue,
+						       struct ast_vhub_req,
+						       queue);
+			break;
+		}
+	}
+
+	/* More work ? */
+	if (req)
+		ast_vhub_epn_kick_desc(ep, req);
+}
+
+void ast_vhub_epn_ack_irq(struct ast_vhub_ep *ep)
+{
+	if (ep->epn.desc_mode)
+		ast_vhub_epn_handle_ack_desc(ep);
+	else
+		ast_vhub_epn_handle_ack(ep);
+}
+
+static int ast_vhub_epn_queue(struct usb_ep* u_ep, struct usb_request *u_req,
+			      gfp_t gfp_flags)
+{
+	struct ast_vhub_req *req = to_ast_req(u_req);
+	struct ast_vhub_ep *ep = to_ast_ep(u_ep);
+	struct ast_vhub *vhub = ep->vhub;
+	unsigned long flags;
+	bool empty;
+	int rc;
+
+	/* Paranoid checks */
+	if (!u_req || !u_req->complete || !u_req->buf) {
+		dev_warn(&vhub->pdev->dev, "Bogus EPn request ! u_req=%p\n", u_req);
+		if (u_req) {
+			dev_warn(&vhub->pdev->dev, "complete=%p internal=%d\n",
+				 u_req->complete, req->internal);
+		}
+		return -EINVAL;
+	}
+
+	/* Endpoint enabled ? */
+	if (!ep->epn.enabled || !u_ep->desc || !ep->dev || !ep->d_idx ||
+	    !ep->dev->enabled || ep->dev->suspended) {
+		EPDBG(ep,"Enqueing request on wrong or disabled EP\n");
+		return -ESHUTDOWN;
+	}
+
+	/* Map request for DMA if possible. For now, the rule for DMA is
+	 * that:
+	 *
+	 *  * For single stage mode (no descriptors):
+	 *
+	 *   - The buffer is aligned to a 8 bytes boundary (HW requirement)
+	 *   - For a OUT endpoint, the request size is a multiple of the EP
+	 *     packet size (otherwise the controller will DMA past the end
+	 *     of the buffer if the host is sending a too long packet).
+	 *
+	 *  * For descriptor mode (tx only for now), always.
+	 *
+	 * We could relax the latter by making the decision to use the bounce
+	 * buffer based on the size of a given *segment* of the request rather
+	 * than the whole request.
+	 */
+	if (ep->epn.desc_mode ||
+	    ((((unsigned long)u_req->buf & 7) == 0) &&
+	     (ep->epn.is_in || !(u_req->length & (u_ep->maxpacket - 1))))) {
+		rc = usb_gadget_map_request(&ep->dev->gadget, u_req,
+					    ep->epn.is_in);
+		if (rc) {
+			dev_warn(&vhub->pdev->dev,
+				 "Request mapping failure %d\n", rc);
+			return rc;
+		}
+	} else
+		u_req->dma = 0;
+
+	EPVDBG(ep, "enqueue req @%p\n", req);
+	EPVDBG(ep, " l=%d dma=0x%x zero=%d noshort=%d noirq=%d is_in=%d\n",
+	       u_req->length, (u32)u_req->dma, u_req->zero,
+	       u_req->short_not_ok, u_req->no_interrupt,
+	       ep->epn.is_in);
+
+	/* Initialize request progress fields */
+	u_req->status = -EINPROGRESS;
+	u_req->actual = 0;
+	req->act_count = 0;
+	req->active = false;
+	req->last_desc = -1;
+	spin_lock_irqsave(&vhub->lock, flags);
+	empty = list_empty(&ep->queue);
+
+	/* Add request to list and kick processing if empty */
+	list_add_tail(&req->queue, &ep->queue);
+	if (empty) {
+		if (ep->epn.desc_mode)
+			ast_vhub_epn_kick_desc(ep, req);
+		else
+			ast_vhub_epn_kick(ep, req);
+	}
+	spin_unlock_irqrestore(&vhub->lock, flags);
+
+	return 0;
+}
+
+static void ast_vhub_stop_active_req(struct ast_vhub_ep *ep,
+				     bool restart_ep)
+{
+	u32 state, reg, loops;
+
+	/* Stop DMA activity */
+	writel(0, ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+
+	/* Wait for it to complete */
+	for (loops = 0; loops < 1000; loops++) {
+		state = readl(ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+		state = VHUB_EP_DMA_PROC_STATUS(state);
+		if (state == EP_DMA_PROC_RX_IDLE ||
+		    state == EP_DMA_PROC_TX_IDLE)
+			break;
+		udelay(1);
+	}
+	if (loops >= 1000)
+		dev_warn(&ep->vhub->pdev->dev, "Timeout waiting for DMA\n");
+
+	/* If we don't have to restart the endpoint, that's it */
+	if (!restart_ep)
+		return;
+
+	/* Restart the endpoint */
+	if (ep->epn.desc_mode) {
+		/*
+		 * Take out descriptors by resetting the DMA read
+		 * pointer to be equal to the CPU write pointer.
+		 *
+		 * Note: If we ever support creating descriptors for
+		 * requests that aren't the head of the queue, we
+		 * may have to do something more complex here,
+		 * especially if the request being taken out is
+		 * not the current head descriptors.
+		 */
+		reg = VHUB_EP_DMA_SET_RPTR(ep->epn.d_next) |
+			VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next);
+		writel(reg, ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+
+		/* Then turn it back on */
+		writel(ep->epn.dma_conf,
+		       ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+	} else {
+		/* Single mode: just turn it back on */
+		writel(ep->epn.dma_conf,
+		       ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+	}
+}
+
+static int ast_vhub_epn_dequeue(struct usb_ep* u_ep, struct usb_request *u_req)
+{
+	struct ast_vhub_ep *ep = to_ast_ep(u_ep);
+	struct ast_vhub *vhub = ep->vhub;
+	struct ast_vhub_req *req;
+	unsigned long flags;
+	int rc = -EINVAL;
+
+	spin_lock_irqsave(&vhub->lock, flags);
+
+	/* Make sure it's actually queued on this endpoint */
+	list_for_each_entry (req, &ep->queue, queue) {
+		if (&req->req == u_req)
+			break;
+	}
+
+	if (&req->req == u_req) {
+		EPVDBG(ep, "dequeue req @%p active=%d\n",
+		       req, req->active);
+		if (req->active)
+			ast_vhub_stop_active_req(ep, true);
+		ast_vhub_done(ep, req, -ECONNRESET);
+		rc = 0;
+	}
+
+	spin_unlock_irqrestore(&vhub->lock, flags);
+	return rc;
+}
+
+void ast_vhub_update_epn_stall(struct ast_vhub_ep *ep)
+{
+	u32 reg;
+
+	if (WARN_ON(ep->d_idx == 0))
+		return;
+	reg = readl(ep->epn.regs + AST_VHUB_EP_CONFIG);
+	if (ep->epn.stalled || ep->epn.wedged)
+		reg |= VHUB_EP_CFG_STALL_CTRL;
+	else
+		reg &= ~VHUB_EP_CFG_STALL_CTRL;
+	writel(reg, ep->epn.regs + AST_VHUB_EP_CONFIG);
+
+	if (!ep->epn.stalled && !ep->epn.wedged)
+		writel(VHUB_EP_TOGGLE_SET_EPNUM(ep->epn.g_idx),
+		       ep->vhub->regs + AST_VHUB_EP_TOGGLE);
+}
+
+static int ast_vhub_set_halt_and_wedge(struct usb_ep* u_ep, bool halt,
+				      bool wedge)
+{
+	struct ast_vhub_ep *ep = to_ast_ep(u_ep);
+	struct ast_vhub *vhub = ep->vhub;
+	unsigned long flags;
+
+	EPDBG(ep, "Set halt (%d) & wedge (%d)\n", halt, wedge);
+
+	if (!u_ep || !u_ep->desc)
+		return -EINVAL;
+	if (ep->d_idx == 0)
+		return 0;
+	if (ep->epn.is_iso)
+		return -EOPNOTSUPP;
+
+	spin_lock_irqsave(&vhub->lock, flags);
+
+	/* Fail with still-busy IN endpoints */
+	if (halt && ep->epn.is_in && !list_empty(&ep->queue)) {
+		spin_unlock_irqrestore(&vhub->lock, flags);
+		return -EAGAIN;
+	}
+	ep->epn.stalled = halt;
+	ep->epn.wedged = wedge;
+	ast_vhub_update_epn_stall(ep);
+
+	spin_unlock_irqrestore(&vhub->lock, flags);
+
+	return 0;
+}
+
+static int ast_vhub_epn_set_halt(struct usb_ep *u_ep, int value)
+{
+	return ast_vhub_set_halt_and_wedge(u_ep, value != 0, false);
+}
+
+static int ast_vhub_epn_set_wedge(struct usb_ep *u_ep)
+{
+	return ast_vhub_set_halt_and_wedge(u_ep, true, true);
+}
+
+static int ast_vhub_epn_disable(struct usb_ep* u_ep)
+{
+	struct ast_vhub_ep *ep = to_ast_ep(u_ep);
+	struct ast_vhub *vhub = ep->vhub;
+	unsigned long flags;
+	u32 imask, ep_ier;
+
+	EPDBG(ep, "Disabling !\n");
+
+	spin_lock_irqsave(&vhub->lock, flags);
+
+	ep->epn.enabled = false;
+
+	/* Stop active DMA if any */
+	ast_vhub_stop_active_req(ep, false);
+
+	/* Disable endpoint */
+	writel(0, ep->epn.regs + AST_VHUB_EP_CONFIG);
+
+	/* Disable ACK interrupt */
+	imask = VHUB_EP_IRQ(ep->epn.g_idx);
+	ep_ier = readl(vhub->regs + AST_VHUB_EP_ACK_IER);
+	ep_ier &= ~imask;
+	writel(ep_ier, vhub->regs + AST_VHUB_EP_ACK_IER);
+	writel(imask, vhub->regs + AST_VHUB_EP_ACK_ISR);
+
+	/* Nuke all pending requests */
+	ast_vhub_nuke(ep, -ESHUTDOWN);
+
+	/* No more descriptor associated with request */
+	ep->ep.desc = NULL;
+
+	spin_unlock_irqrestore(&vhub->lock, flags);
+
+	return 0;
+}
+
+static int ast_vhub_epn_enable(struct usb_ep* u_ep,
+			       const struct usb_endpoint_descriptor *desc)
+{
+	static const char *ep_type_string[] __maybe_unused = { "ctrl",
+							       "isoc",
+							       "bulk",
+							       "intr" };
+	struct ast_vhub_ep *ep = to_ast_ep(u_ep);
+	struct ast_vhub_dev *dev;
+	struct ast_vhub *vhub;
+	u16 maxpacket, type;
+	unsigned long flags;
+	u32 ep_conf, ep_ier, imask;
+
+	/* Check arguments */
+	if (!u_ep || !desc)
+		return -EINVAL;
+
+	maxpacket = usb_endpoint_maxp(desc);
+	if (!ep->d_idx || !ep->dev ||
+	    desc->bDescriptorType != USB_DT_ENDPOINT ||
+	    maxpacket == 0 || maxpacket > ep->ep.maxpacket) {
+		EPDBG(ep, "Invalid EP enable,d_idx=%d,dev=%p,type=%d,mp=%d/%d\n",
+		      ep->d_idx, ep->dev, desc->bDescriptorType,
+		      maxpacket, ep->ep.maxpacket);
+		return -EINVAL;
+	}
+	if (ep->d_idx != usb_endpoint_num(desc)) {
+		EPDBG(ep, "EP number mismatch !\n");
+		return -EINVAL;
+	}
+
+	if (ep->epn.enabled) {
+		EPDBG(ep, "Already enabled\n");
+		return -EBUSY;
+	}
+	dev = ep->dev;
+	vhub = ep->vhub;
+
+	/* Check device state */
+	if (!dev->driver) {
+		EPDBG(ep, "Bogus device state: driver=%p speed=%d\n",
+		       dev->driver, dev->gadget.speed);
+		return -ESHUTDOWN;
+	}
+
+	/* Grab some info from the descriptor */
+	ep->epn.is_in = usb_endpoint_dir_in(desc);
+	ep->ep.maxpacket = maxpacket;
+	type = usb_endpoint_type(desc);
+	ep->epn.d_next = ep->epn.d_last = 0;
+	ep->epn.is_iso = false;
+	ep->epn.stalled = false;
+	ep->epn.wedged = false;
+
+	EPDBG(ep, "Enabling [%s] %s num %d maxpacket=%d\n",
+	      ep->epn.is_in ? "in" : "out", ep_type_string[type],
+	      usb_endpoint_num(desc), maxpacket);
+
+	/* Can we use DMA descriptor mode ? */
+	ep->epn.desc_mode = ep->epn.descs && ep->epn.is_in;
+	if (ep->epn.desc_mode)
+		memset(ep->epn.descs, 0, 8 * AST_VHUB_DESCS_COUNT);
+
+	/*
+	 * Large send function can send up to 8 packets from
+	 * one descriptor with a limit of 4095 bytes.
+	 */
+	ep->epn.chunk_max = ep->ep.maxpacket;
+	if (ep->epn.is_in) {
+		ep->epn.chunk_max <<= 3;
+		while (ep->epn.chunk_max > 4095)
+			ep->epn.chunk_max -= ep->ep.maxpacket;
+	}
+
+	switch(type) {
+	case USB_ENDPOINT_XFER_CONTROL:
+		EPDBG(ep, "Only one control endpoint\n");
+		return -EINVAL;
+	case USB_ENDPOINT_XFER_INT:
+		ep_conf = VHUB_EP_CFG_SET_TYPE(EP_TYPE_INT);
+		break;
+	case USB_ENDPOINT_XFER_BULK:
+		ep_conf = VHUB_EP_CFG_SET_TYPE(EP_TYPE_BULK);
+		break;
+	case USB_ENDPOINT_XFER_ISOC:
+		ep_conf = VHUB_EP_CFG_SET_TYPE(EP_TYPE_ISO);
+		ep->epn.is_iso = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Encode the rest of the EP config register */
+	if (maxpacket < 1024)
+		ep_conf |= VHUB_EP_CFG_SET_MAX_PKT(maxpacket);
+	if (!ep->epn.is_in)
+		ep_conf |= VHUB_EP_CFG_DIR_OUT;
+	ep_conf |= VHUB_EP_CFG_SET_EP_NUM(usb_endpoint_num(desc));
+	ep_conf |= VHUB_EP_CFG_ENABLE;
+	ep_conf |= VHUB_EP_CFG_SET_DEV(dev->index + 1);
+	EPVDBG(ep, "config=%08x\n", ep_conf);
+
+	spin_lock_irqsave(&vhub->lock, flags);
+
+	/* Disable HW and reset DMA */
+	writel(0, ep->epn.regs + AST_VHUB_EP_CONFIG);
+	writel(VHUB_EP_DMA_CTRL_RESET,
+	       ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+
+	/* Configure and enable */
+	writel(ep_conf, ep->epn.regs + AST_VHUB_EP_CONFIG);
+
+	if (ep->epn.desc_mode) {
+		/* Clear DMA status, including the DMA read ptr */
+		writel(0, ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+
+		/* Set descriptor base */
+		writel(ep->epn.descs_dma,
+		       ep->epn.regs + AST_VHUB_EP_DESC_BASE);
+
+		/* Set base DMA config value */
+		ep->epn.dma_conf = VHUB_EP_DMA_DESC_MODE;
+		if (ep->epn.is_in)
+			ep->epn.dma_conf |= VHUB_EP_DMA_IN_LONG_MODE;
+
+		/* First reset and disable all operations */
+		writel(ep->epn.dma_conf | VHUB_EP_DMA_CTRL_RESET,
+		       ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+
+		/* Enable descriptor mode */
+		writel(ep->epn.dma_conf,
+		       ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+	} else {
+		/* Set base DMA config value */
+		ep->epn.dma_conf = VHUB_EP_DMA_SINGLE_STAGE;
+
+		/* Reset and switch to single stage mode */
+		writel(ep->epn.dma_conf | VHUB_EP_DMA_CTRL_RESET,
+		       ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+		writel(ep->epn.dma_conf,
+		       ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT);
+		writel(0, ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
+	}
+
+	/* Cleanup data toggle just in case */
+	writel(VHUB_EP_TOGGLE_SET_EPNUM(ep->epn.g_idx),
+	       vhub->regs + AST_VHUB_EP_TOGGLE);
+
+	/* Cleanup and enable ACK interrupt */
+	imask = VHUB_EP_IRQ(ep->epn.g_idx);
+	writel(imask, vhub->regs + AST_VHUB_EP_ACK_ISR);
+	ep_ier = readl(vhub->regs + AST_VHUB_EP_ACK_IER);
+	ep_ier |= imask;
+	writel(ep_ier, vhub->regs + AST_VHUB_EP_ACK_IER);
+
+	/* Woot, we are online ! */
+	ep->epn.enabled = true;
+
+	spin_unlock_irqrestore(&vhub->lock, flags);
+
+	return 0;
+}
+
+static void ast_vhub_epn_dispose(struct usb_ep *u_ep)
+{
+	struct ast_vhub_ep *ep = to_ast_ep(u_ep);
+
+	if (WARN_ON(!ep->dev || !ep->d_idx))
+		return;
+
+	EPDBG(ep, "Releasing endpoint\n");
+
+	/* Take it out of the EP list */
+	list_del_init(&ep->ep.ep_list);
+
+	/* Mark the address free in the device */
+	ep->dev->epns[ep->d_idx - 1] = NULL;
+
+	/* Free name & DMA buffers */
+	kfree(ep->ep.name);
+	ep->ep.name = NULL;
+	dma_free_coherent(&ep->vhub->pdev->dev,
+			  AST_VHUB_EPn_MAX_PACKET +
+			  8 * AST_VHUB_DESCS_COUNT,
+			  ep->buf, ep->buf_dma);
+	ep->buf = NULL;
+	ep->epn.descs = NULL;
+
+	/* Mark free */
+	ep->dev = NULL;
+}
+
+static const struct usb_ep_ops ast_vhub_epn_ops = {
+	.enable		= ast_vhub_epn_enable,
+	.disable	= ast_vhub_epn_disable,
+	.dispose	= ast_vhub_epn_dispose,
+	.queue		= ast_vhub_epn_queue,
+	.dequeue	= ast_vhub_epn_dequeue,
+	.set_halt	= ast_vhub_epn_set_halt,
+	.set_wedge	= ast_vhub_epn_set_wedge,
+	.alloc_request	= ast_vhub_alloc_request,
+	.free_request	= ast_vhub_free_request,
+};
+
+struct ast_vhub_ep *ast_vhub_alloc_epn(struct ast_vhub_dev *d, u8 addr)
+{
+	struct ast_vhub *vhub = d->vhub;
+	struct ast_vhub_ep *ep;
+	unsigned long flags;
+	int i;
+
+	/* Find a free one (no device) */
+	spin_lock_irqsave(&vhub->lock, flags);
+	for (i = 0; i < AST_VHUB_NUM_GEN_EPs; i++)
+		if (vhub->epns[i].dev == NULL)
+			break;
+	if (i >= AST_VHUB_NUM_GEN_EPs) {
+		spin_unlock_irqrestore(&vhub->lock, flags);
+		return NULL;
+	}
+
+	/* Set it up */
+	ep = &vhub->epns[i];
+	ep->dev = d;
+	spin_unlock_irqrestore(&vhub->lock, flags);
+
+	DDBG(d, "Allocating gen EP %d for addr %d\n", i, addr);
+	INIT_LIST_HEAD(&ep->queue);
+	ep->d_idx = addr;
+	ep->vhub = vhub;
+	ep->ep.ops = &ast_vhub_epn_ops;
+	ep->ep.name = kasprintf(GFP_KERNEL, "ep%d", addr);
+	d->epns[addr-1] = ep;
+	ep->epn.g_idx = i;
+	ep->epn.regs = vhub->regs + 0x200 + (i * 0x10);
+
+	ep->buf = dma_alloc_coherent(&vhub->pdev->dev,
+				     AST_VHUB_EPn_MAX_PACKET +
+				     8 * AST_VHUB_DESCS_COUNT,
+				     &ep->buf_dma, GFP_KERNEL);
+	if (!ep->buf) {
+		kfree(ep->ep.name);
+		ep->ep.name = NULL;
+		return NULL;
+	}
+	ep->epn.descs = ep->buf + AST_VHUB_EPn_MAX_PACKET;
+	ep->epn.descs_dma = ep->buf_dma + AST_VHUB_EPn_MAX_PACKET;
+
+	usb_ep_set_maxpacket_limit(&ep->ep, AST_VHUB_EPn_MAX_PACKET);
+	list_add_tail(&ep->ep.ep_list, &d->gadget.ep_list);
+	ep->ep.caps.type_iso = true;
+	ep->ep.caps.type_bulk = true;
+	ep->ep.caps.type_int = true;
+	ep->ep.caps.dir_in = true;
+	ep->ep.caps.dir_out = true;
+
+	return ep;
+}
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/hub.c b/drivers/usb/gadget/udc/aspeed-vhub/hub.c
new file mode 100644
index 000000000000..35ba0e55a2e9
--- /dev/null
+++ b/drivers/usb/gadget/udc/aspeed-vhub/hub.c
@@ -0,0 +1,829 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * aspeed-vhub -- Driver for Aspeed SoC "vHub" USB gadget
+ *
+ * hub.c - virtual hub handling
+ *
+ * Copyright 2017 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/proc_fs.h>
+#include <linux/prefetch.h>
+#include <linux/clk.h>
+#include <linux/usb/gadget.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/regmap.h>
+#include <linux/dma-mapping.h>
+#include <linux/bcd.h>
+#include <linux/version.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+
+#include "vhub.h"
+
+/* usb 2.0 hub device descriptor
+ *
+ * A few things we may want to improve here:
+ *
+ *    - We may need to indicate TT support
+ *    - We may need a device qualifier descriptor
+ *	as devices can pretend to be usb1 or 2
+ *    - Make vid/did overridable
+ *    - make it look like usb1 if usb1 mode forced
+ */
+#define KERNEL_REL	bin2bcd(((LINUX_VERSION_CODE >> 16) & 0x0ff))
+#define KERNEL_VER	bin2bcd(((LINUX_VERSION_CODE >> 8) & 0x0ff))
+
+enum {
+	AST_VHUB_STR_MANUF = 3,
+	AST_VHUB_STR_PRODUCT = 2,
+	AST_VHUB_STR_SERIAL = 1,
+};
+
+static const struct usb_device_descriptor ast_vhub_dev_desc = {
+	.bLength		= USB_DT_DEVICE_SIZE,
+	.bDescriptorType	= USB_DT_DEVICE,
+	.bcdUSB			= cpu_to_le16(0x0200),
+	.bDeviceClass		= USB_CLASS_HUB,
+	.bDeviceSubClass	= 0,
+	.bDeviceProtocol	= 1,
+	.bMaxPacketSize0	= 64,
+	.idVendor		= cpu_to_le16(0x1d6b),
+	.idProduct		= cpu_to_le16(0x0107),
+	.bcdDevice		= cpu_to_le16(0x0100),
+	.iManufacturer		= AST_VHUB_STR_MANUF,
+	.iProduct		= AST_VHUB_STR_PRODUCT,
+	.iSerialNumber		= AST_VHUB_STR_SERIAL,
+	.bNumConfigurations	= 1,
+};
+
+/* Patches to the above when forcing USB1 mode */
+static void ast_vhub_patch_dev_desc_usb1(struct usb_device_descriptor *desc)
+{
+	desc->bcdUSB = cpu_to_le16(0x0100);
+	desc->bDeviceProtocol = 0;
+}
+
+/*
+ * Configuration descriptor: same comments as above
+ * regarding handling USB1 mode.
+ */
+
+/*
+ * We don't use sizeof() as Linux definition of
+ * struct usb_endpoint_descriptor contains 2
+ * extra bytes
+ */
+#define AST_VHUB_CONF_DESC_SIZE	(USB_DT_CONFIG_SIZE + \
+				 USB_DT_INTERFACE_SIZE + \
+				 USB_DT_ENDPOINT_SIZE)
+
+static const struct ast_vhub_full_cdesc {
+	struct usb_config_descriptor	cfg;
+	struct usb_interface_descriptor intf;
+	struct usb_endpoint_descriptor	ep;
+} __attribute__ ((packed)) ast_vhub_conf_desc = {
+	.cfg = {
+		.bLength		= USB_DT_CONFIG_SIZE,
+		.bDescriptorType	= USB_DT_CONFIG,
+		.wTotalLength		= cpu_to_le16(AST_VHUB_CONF_DESC_SIZE),
+		.bNumInterfaces		= 1,
+		.bConfigurationValue	= 1,
+		.iConfiguration		= 0,
+		.bmAttributes		= USB_CONFIG_ATT_ONE |
+					  USB_CONFIG_ATT_SELFPOWER |
+					  USB_CONFIG_ATT_WAKEUP,
+		.bMaxPower		= 0,
+	},
+	.intf = {
+		.bLength		= USB_DT_INTERFACE_SIZE,
+		.bDescriptorType	= USB_DT_INTERFACE,
+		.bInterfaceNumber	= 0,
+		.bAlternateSetting	= 0,
+		.bNumEndpoints		= 1,
+		.bInterfaceClass	= USB_CLASS_HUB,
+		.bInterfaceSubClass	= 0,
+		.bInterfaceProtocol	= 0,
+		.iInterface		= 0,
+	},
+	.ep = {
+		.bLength		= USB_DT_ENDPOINT_SIZE,
+		.bDescriptorType	= USB_DT_ENDPOINT,
+		.bEndpointAddress	= 0x81,
+		.bmAttributes		= USB_ENDPOINT_XFER_INT,
+		.wMaxPacketSize		= cpu_to_le16(1),
+		.bInterval		= 0x0c,
+	},
+};
+
+#define AST_VHUB_HUB_DESC_SIZE	(USB_DT_HUB_NONVAR_SIZE + 2)
+
+static const struct usb_hub_descriptor ast_vhub_hub_desc = {
+	.bDescLength			= AST_VHUB_HUB_DESC_SIZE,
+	.bDescriptorType		= USB_DT_HUB,
+	.bNbrPorts			= AST_VHUB_NUM_PORTS,
+	.wHubCharacteristics		= cpu_to_le16(HUB_CHAR_NO_LPSM),
+	.bPwrOn2PwrGood			= 10,
+	.bHubContrCurrent		= 0,
+	.u.hs.DeviceRemovable[0]	= 0,
+	.u.hs.DeviceRemovable[1]	= 0xff,
+};
+
+/*
+ * These strings converted to UTF-16 must be smaller than
+ * our EP0 buffer.
+ */
+static const struct usb_string ast_vhub_str_array[] = {
+	{
+		.id = AST_VHUB_STR_SERIAL,
+		.s = "00000000"
+	},
+	{
+		.id = AST_VHUB_STR_PRODUCT,
+		.s = "USB Virtual Hub"
+	},
+	{
+		.id = AST_VHUB_STR_MANUF,
+		.s = "Aspeed"
+	},
+	{ }
+};
+
+static const struct usb_gadget_strings ast_vhub_strings = {
+	.language = 0x0409,
+	.strings = (struct usb_string *)ast_vhub_str_array
+};
+
+static int ast_vhub_hub_dev_status(struct ast_vhub_ep *ep,
+				   u16 wIndex, u16 wValue)
+{
+	u8 st0;
+
+	EPDBG(ep, "GET_STATUS(dev)\n");
+
+	/*
+	 * Mark it as self-powered, I doubt the BMC is powered off
+	 * the USB bus ...
+	 */
+	st0 = 1 << USB_DEVICE_SELF_POWERED;
+
+	/*
+	 * Need to double check how remote wakeup actually works
+	 * on that chip and what triggers it.
+	 */
+	if (ep->vhub->wakeup_en)
+		st0 |= 1 << USB_DEVICE_REMOTE_WAKEUP;
+
+	return ast_vhub_simple_reply(ep, st0, 0);
+}
+
+static int ast_vhub_hub_ep_status(struct ast_vhub_ep *ep,
+				  u16 wIndex, u16 wValue)
+{
+	int ep_num;
+	u8 st0 = 0;
+
+	ep_num = wIndex & USB_ENDPOINT_NUMBER_MASK;
+	EPDBG(ep, "GET_STATUS(ep%d)\n", ep_num);
+
+	/* On the hub we have only EP 0 and 1 */
+	if (ep_num == 1) {
+		if (ep->vhub->ep1_stalled)
+			st0 |= 1 << USB_ENDPOINT_HALT;
+	} else if (ep_num != 0)
+		return std_req_stall;
+
+	return ast_vhub_simple_reply(ep, st0, 0);
+}
+
+static int ast_vhub_hub_dev_feature(struct ast_vhub_ep *ep,
+				    u16 wIndex, u16 wValue,
+				    bool is_set)
+{
+	EPDBG(ep, "%s_FEATURE(dev val=%02x)\n",
+	      is_set ? "SET" : "CLEAR", wValue);
+
+	if (wValue != USB_DEVICE_REMOTE_WAKEUP)
+		return std_req_stall;
+
+	ep->vhub->wakeup_en = is_set;
+	EPDBG(ep, "Hub remote wakeup %s\n",
+	      is_set ? "enabled" : "disabled");
+
+	return std_req_complete;
+}
+
+static int ast_vhub_hub_ep_feature(struct ast_vhub_ep *ep,
+				   u16 wIndex, u16 wValue,
+				   bool is_set)
+{
+	int ep_num;
+	u32 reg;
+
+	ep_num = wIndex & USB_ENDPOINT_NUMBER_MASK;
+	EPDBG(ep, "%s_FEATURE(ep%d val=%02x)\n",
+	      is_set ? "SET" : "CLEAR", ep_num, wValue);
+
+	if (ep_num > 1)
+		return std_req_stall;
+	if (wValue != USB_ENDPOINT_HALT)
+		return std_req_stall;
+	if (ep_num == 0)
+		return std_req_complete;
+
+	EPDBG(ep, "%s stall on EP 1\n",
+	      is_set ? "setting" : "clearing");
+
+	ep->vhub->ep1_stalled = is_set;
+	reg = readl(ep->vhub->regs + AST_VHUB_EP1_CTRL);
+	if (is_set) {
+		reg |= VHUB_EP1_CTRL_STALL;
+	} else {
+		reg &= ~VHUB_EP1_CTRL_STALL;
+		reg |= VHUB_EP1_CTRL_RESET_TOGGLE;
+	}
+	writel(reg, ep->vhub->regs + AST_VHUB_EP1_CTRL);
+
+	return std_req_complete;
+}
+
+static int ast_vhub_rep_desc(struct ast_vhub_ep *ep,
+			     u8 desc_type, u16 len)
+{
+	size_t dsize;
+
+	EPDBG(ep, "GET_DESCRIPTOR(type:%d)\n", desc_type);
+
+	/*
+	 * Copy first to EP buffer and send from there, so
+	 * we can do some in-place patching if needed. We know
+	 * the EP buffer is big enough but ensure that doesn't
+	 * change. We do that now rather than later after we
+	 * have checked sizes etc... to avoid a gcc bug where
+	 * it thinks len is constant and barfs about read
+	 * overflows in memcpy.
+	 */
+	switch(desc_type) {
+	case USB_DT_DEVICE:
+		dsize = USB_DT_DEVICE_SIZE;
+		memcpy(ep->buf, &ast_vhub_dev_desc, dsize);
+		BUILD_BUG_ON(dsize > sizeof(ast_vhub_dev_desc));
+		BUILD_BUG_ON(USB_DT_DEVICE_SIZE >= AST_VHUB_EP0_MAX_PACKET);
+		break;
+	case USB_DT_CONFIG:
+		dsize = AST_VHUB_CONF_DESC_SIZE;
+		memcpy(ep->buf, &ast_vhub_conf_desc, dsize);
+		BUILD_BUG_ON(dsize > sizeof(ast_vhub_conf_desc));
+		BUILD_BUG_ON(AST_VHUB_CONF_DESC_SIZE >= AST_VHUB_EP0_MAX_PACKET);
+		break;
+	case USB_DT_HUB:
+		dsize = AST_VHUB_HUB_DESC_SIZE;
+		memcpy(ep->buf, &ast_vhub_hub_desc, dsize);
+		BUILD_BUG_ON(dsize > sizeof(ast_vhub_hub_desc));
+	BUILD_BUG_ON(AST_VHUB_HUB_DESC_SIZE >= AST_VHUB_EP0_MAX_PACKET);
+		break;
+	default:
+		return std_req_stall;
+	}
+
+	/* Crop requested length */
+	if (len > dsize)
+		len = dsize;
+
+	/* Patch it if forcing USB1 */
+	if (desc_type == USB_DT_DEVICE && ep->vhub->force_usb1)
+		ast_vhub_patch_dev_desc_usb1(ep->buf);
+
+	/* Shoot it from the EP buffer */
+	return ast_vhub_reply(ep, NULL, len);
+}
+
+static int ast_vhub_rep_string(struct ast_vhub_ep *ep,
+			       u8 string_id, u16 lang_id,
+			       u16 len)
+{
+	int rc = usb_gadget_get_string (&ast_vhub_strings, string_id, ep->buf);
+
+	/*
+	 * This should never happen unless we put too big strings in
+	 * the array above
+	 */
+	BUG_ON(rc >= AST_VHUB_EP0_MAX_PACKET);
+
+	if (rc < 0)
+		return std_req_stall;
+
+	/* Shoot it from the EP buffer */
+	return ast_vhub_reply(ep, NULL, min_t(u16, rc, len));
+}
+
+enum std_req_rc ast_vhub_std_hub_request(struct ast_vhub_ep *ep,
+					 struct usb_ctrlrequest *crq)
+{
+	struct ast_vhub *vhub = ep->vhub;
+	u16 wValue, wIndex, wLength;
+
+	wValue = le16_to_cpu(crq->wValue);
+	wIndex = le16_to_cpu(crq->wIndex);
+	wLength = le16_to_cpu(crq->wLength);
+
+	/* First packet, grab speed */
+	if (vhub->speed == USB_SPEED_UNKNOWN) {
+		u32 ustat = readl(vhub->regs + AST_VHUB_USBSTS);
+		if (ustat & VHUB_USBSTS_HISPEED)
+			vhub->speed = USB_SPEED_HIGH;
+		else
+			vhub->speed = USB_SPEED_FULL;
+		UDCDBG(vhub, "USB status=%08x speed=%s\n", ustat,
+		       vhub->speed == USB_SPEED_HIGH ? "high" : "full");
+	}
+
+	switch ((crq->bRequestType << 8) | crq->bRequest) {
+		/* SET_ADDRESS */
+	case DeviceOutRequest | USB_REQ_SET_ADDRESS:
+		EPDBG(ep, "SET_ADDRESS: Got address %x\n", wValue);
+		writel(wValue, vhub->regs + AST_VHUB_CONF);
+		return std_req_complete;
+
+		/* GET_STATUS */
+	case DeviceRequest | USB_REQ_GET_STATUS:
+		return ast_vhub_hub_dev_status(ep, wIndex, wValue);
+	case InterfaceRequest | USB_REQ_GET_STATUS:
+		return ast_vhub_simple_reply(ep, 0, 0);
+	case EndpointRequest | USB_REQ_GET_STATUS:
+		return ast_vhub_hub_ep_status(ep, wIndex, wValue);
+
+		/* SET/CLEAR_FEATURE */
+	case DeviceOutRequest | USB_REQ_SET_FEATURE:
+		return ast_vhub_hub_dev_feature(ep, wIndex, wValue, true);
+	case DeviceOutRequest | USB_REQ_CLEAR_FEATURE:
+		return ast_vhub_hub_dev_feature(ep, wIndex, wValue, false);
+	case EndpointOutRequest | USB_REQ_SET_FEATURE:
+		return ast_vhub_hub_ep_feature(ep, wIndex, wValue, true);
+	case EndpointOutRequest | USB_REQ_CLEAR_FEATURE:
+		return ast_vhub_hub_ep_feature(ep, wIndex, wValue, false);
+
+		/* GET/SET_CONFIGURATION */
+	case DeviceRequest | USB_REQ_GET_CONFIGURATION:
+		return ast_vhub_simple_reply(ep, 1);
+	case DeviceOutRequest | USB_REQ_SET_CONFIGURATION:
+		if (wValue != 1)
+			return std_req_stall;
+		return std_req_complete;
+
+		/* GET_DESCRIPTOR */
+	case DeviceRequest | USB_REQ_GET_DESCRIPTOR:
+		switch (wValue >> 8) {
+		case USB_DT_DEVICE:
+		case USB_DT_CONFIG:
+			return ast_vhub_rep_desc(ep, wValue >> 8,
+						 wLength);
+		case USB_DT_STRING:
+			return ast_vhub_rep_string(ep, wValue & 0xff,
+						   wIndex, wLength);
+		}
+		return std_req_stall;
+
+		/* GET/SET_INTERFACE */
+	case DeviceRequest | USB_REQ_GET_INTERFACE:
+		return ast_vhub_simple_reply(ep, 0);
+	case DeviceOutRequest | USB_REQ_SET_INTERFACE:
+		if (wValue != 0 || wIndex != 0)
+			return std_req_stall;
+		return std_req_complete;
+	}
+	return std_req_stall;
+}
+
+static void ast_vhub_update_hub_ep1(struct ast_vhub *vhub,
+				    unsigned int port)
+{
+	/* Update HW EP1 response */
+	u32 reg = readl(vhub->regs + AST_VHUB_EP1_STS_CHG);
+	u32 pmask = (1 << (port + 1));
+	if (vhub->ports[port].change)
+		reg |= pmask;
+	else
+		reg &= ~pmask;
+	writel(reg, vhub->regs + AST_VHUB_EP1_STS_CHG);
+}
+
+static void ast_vhub_change_port_stat(struct ast_vhub *vhub,
+				      unsigned int port,
+				      u16 clr_flags,
+				      u16 set_flags,
+				      bool set_c)
+{
+	struct ast_vhub_port *p = &vhub->ports[port];
+	u16 prev;
+
+	/* Update port status */
+	prev = p->status;
+	p->status = (prev & ~clr_flags) | set_flags;
+	DDBG(&p->dev, "port %d status %04x -> %04x (C=%d)\n",
+	     port + 1, prev, p->status, set_c);
+
+	/* Update change bits if needed */
+	if (set_c) {
+		u16 chg = p->status ^ prev;
+
+		/* Only these are relevant for change */
+		chg &= USB_PORT_STAT_C_CONNECTION |
+		       USB_PORT_STAT_C_ENABLE |
+		       USB_PORT_STAT_C_SUSPEND |
+		       USB_PORT_STAT_C_OVERCURRENT |
+		       USB_PORT_STAT_C_RESET |
+		       USB_PORT_STAT_C_L1;
+		p->change |= chg;
+
+		ast_vhub_update_hub_ep1(vhub, port);
+	}
+}
+
+static void ast_vhub_send_host_wakeup(struct ast_vhub *vhub)
+{
+	u32 reg = readl(vhub->regs + AST_VHUB_CTRL);
+	UDCDBG(vhub, "Waking up host !\n");
+	reg |= VHUB_CTRL_MANUAL_REMOTE_WAKEUP;
+	writel(reg, vhub->regs + AST_VHUB_CTRL);
+}
+
+void ast_vhub_device_connect(struct ast_vhub *vhub,
+			     unsigned int port, bool on)
+{
+	if (on)
+		ast_vhub_change_port_stat(vhub, port, 0,
+					  USB_PORT_STAT_CONNECTION, true);
+	else
+		ast_vhub_change_port_stat(vhub, port,
+					  USB_PORT_STAT_CONNECTION |
+					  USB_PORT_STAT_ENABLE,
+					  0, true);
+
+	/*
+	 * If the hub is set to wakup the host on connection events
+	 * then send a wakeup.
+	 */
+	if (vhub->wakeup_en)
+		ast_vhub_send_host_wakeup(vhub);
+}
+
+static void ast_vhub_wake_work(struct work_struct *work)
+{
+	struct ast_vhub *vhub = container_of(work,
+					     struct ast_vhub,
+					     wake_work);
+	unsigned long flags;
+	unsigned int i;
+
+	/*
+	 * Wake all sleeping ports. If a port is suspended by
+	 * the host suspend (without explicit state suspend),
+	 * we let the normal host wake path deal with it later.
+	 */
+	spin_lock_irqsave(&vhub->lock, flags);
+	for (i = 0; i < AST_VHUB_NUM_PORTS; i++) {
+		struct ast_vhub_port *p = &vhub->ports[i];
+
+		if (!(p->status & USB_PORT_STAT_SUSPEND))
+			continue;
+		ast_vhub_change_port_stat(vhub, i,
+					  USB_PORT_STAT_SUSPEND,
+					  0, true);
+		ast_vhub_dev_resume(&p->dev);
+	}
+	ast_vhub_send_host_wakeup(vhub);
+	spin_unlock_irqrestore(&vhub->lock, flags);
+}
+
+void ast_vhub_hub_wake_all(struct ast_vhub *vhub)
+{
+	/*
+	 * A device is trying to wake the world, because this
+	 * can recurse into the device, we break the call chain
+	 * using a work queue
+	 */
+	schedule_work(&vhub->wake_work);
+}
+
+static void ast_vhub_port_reset(struct ast_vhub *vhub, u8 port)
+{
+	struct ast_vhub_port *p = &vhub->ports[port];
+	u16 set, clr, speed;
+
+	/* First mark disabled */
+	ast_vhub_change_port_stat(vhub, port,
+				  USB_PORT_STAT_ENABLE |
+				  USB_PORT_STAT_SUSPEND,
+				  USB_PORT_STAT_RESET,
+				  false);
+
+	if (!p->dev.driver)
+		return;
+
+	/*
+	 * This will either "start" the port or reset the
+	 * device if already started...
+	 */
+	ast_vhub_dev_reset(&p->dev);
+
+	/* Grab the right speed */
+	speed = p->dev.driver->max_speed;
+	if (speed == USB_SPEED_UNKNOWN || speed > vhub->speed)
+		speed = vhub->speed;
+
+	switch (speed) {
+	case USB_SPEED_LOW:
+		set = USB_PORT_STAT_LOW_SPEED;
+		clr = USB_PORT_STAT_HIGH_SPEED;
+		break;
+	case USB_SPEED_FULL:
+		set = 0;
+		clr = USB_PORT_STAT_LOW_SPEED |
+			USB_PORT_STAT_HIGH_SPEED;
+		break;
+	case USB_SPEED_HIGH:
+		set = USB_PORT_STAT_HIGH_SPEED;
+		clr = USB_PORT_STAT_LOW_SPEED;
+		break;
+	default:
+		UDCDBG(vhub, "Unsupported speed %d when"
+		       " connecting device\n",
+		       speed);
+		return;
+	}
+	clr |= USB_PORT_STAT_RESET;
+	set |= USB_PORT_STAT_ENABLE;
+
+	/* This should ideally be delayed ... */
+	ast_vhub_change_port_stat(vhub, port, clr, set, true);
+}
+
+static enum std_req_rc ast_vhub_set_port_feature(struct ast_vhub_ep *ep,
+						 u8 port, u16 feat)
+{
+	struct ast_vhub *vhub = ep->vhub;
+	struct ast_vhub_port *p;
+
+	if (port == 0 || port > AST_VHUB_NUM_PORTS)
+		return std_req_stall;
+	port--;
+	p = &vhub->ports[port];
+
+	switch(feat) {
+	case USB_PORT_FEAT_SUSPEND:
+		if (!(p->status & USB_PORT_STAT_ENABLE))
+			return std_req_complete;
+		ast_vhub_change_port_stat(vhub, port,
+					  0, USB_PORT_STAT_SUSPEND,
+					  false);
+		ast_vhub_dev_suspend(&p->dev);
+		return std_req_complete;
+	case USB_PORT_FEAT_RESET:
+		EPDBG(ep, "Port reset !\n");
+		ast_vhub_port_reset(vhub, port);
+		return std_req_complete;
+	case USB_PORT_FEAT_POWER:
+		/*
+		 * On Power-on, we mark the connected flag changed,
+		 * if there's a connected device, some hosts will
+		 * otherwise fail to detect it.
+		 */
+		if (p->status & USB_PORT_STAT_CONNECTION) {
+			p->change |= USB_PORT_STAT_C_CONNECTION;
+			ast_vhub_update_hub_ep1(vhub, port);
+		}
+		return std_req_complete;
+	case USB_PORT_FEAT_TEST:
+	case USB_PORT_FEAT_INDICATOR:
+		/* We don't do anything with these */
+		return std_req_complete;
+	}
+	return std_req_stall;
+}
+
+static enum std_req_rc ast_vhub_clr_port_feature(struct ast_vhub_ep *ep,
+						 u8 port, u16 feat)
+{
+	struct ast_vhub *vhub = ep->vhub;
+	struct ast_vhub_port *p;
+
+	if (port == 0 || port > AST_VHUB_NUM_PORTS)
+		return std_req_stall;
+	port--;
+	p = &vhub->ports[port];
+
+	switch(feat) {
+	case USB_PORT_FEAT_ENABLE:
+		ast_vhub_change_port_stat(vhub, port,
+					  USB_PORT_STAT_ENABLE |
+					  USB_PORT_STAT_SUSPEND, 0,
+					  false);
+		ast_vhub_dev_suspend(&p->dev);
+		return std_req_complete;
+	case USB_PORT_FEAT_SUSPEND:
+		if (!(p->status & USB_PORT_STAT_SUSPEND))
+			return std_req_complete;
+		ast_vhub_change_port_stat(vhub, port,
+					  USB_PORT_STAT_SUSPEND, 0,
+					  false);
+		ast_vhub_dev_resume(&p->dev);
+		return std_req_complete;
+	case USB_PORT_FEAT_POWER:
+		/* We don't do power control */
+		return std_req_complete;
+	case USB_PORT_FEAT_INDICATOR:
+		/* We don't have indicators */
+		return std_req_complete;
+	case USB_PORT_FEAT_C_CONNECTION:
+	case USB_PORT_FEAT_C_ENABLE:
+	case USB_PORT_FEAT_C_SUSPEND:
+	case USB_PORT_FEAT_C_OVER_CURRENT:
+	case USB_PORT_FEAT_C_RESET:
+		/* Clear state-change feature */
+		p->change &= ~(1u << (feat - 16));
+		ast_vhub_update_hub_ep1(vhub, port);
+		return std_req_complete;
+	}
+	return std_req_stall;
+}
+
+static enum std_req_rc ast_vhub_get_port_stat(struct ast_vhub_ep *ep,
+					      u8 port)
+{
+	struct ast_vhub *vhub = ep->vhub;
+	u16 stat, chg;
+
+	if (port == 0 || port > AST_VHUB_NUM_PORTS)
+		return std_req_stall;
+	port--;
+
+	stat = vhub->ports[port].status;
+	chg = vhub->ports[port].change;
+
+	/* We always have power */
+	stat |= USB_PORT_STAT_POWER;
+
+	EPDBG(ep, " port status=%04x change=%04x\n", stat, chg);
+
+	return ast_vhub_simple_reply(ep,
+				     stat & 0xff,
+				     stat >> 8,
+				     chg & 0xff,
+				     chg >> 8);
+}
+
+enum std_req_rc ast_vhub_class_hub_request(struct ast_vhub_ep *ep,
+					   struct usb_ctrlrequest *crq)
+{
+	u16 wValue, wIndex, wLength;
+
+	wValue = le16_to_cpu(crq->wValue);
+	wIndex = le16_to_cpu(crq->wIndex);
+	wLength = le16_to_cpu(crq->wLength);
+
+	switch ((crq->bRequestType << 8) | crq->bRequest) {
+	case GetHubStatus:
+		EPDBG(ep, "GetHubStatus\n");
+		return ast_vhub_simple_reply(ep, 0, 0, 0, 0);
+	case GetPortStatus:
+		EPDBG(ep, "GetPortStatus(%d)\n", wIndex & 0xff);
+		return ast_vhub_get_port_stat(ep, wIndex & 0xf);
+	case GetHubDescriptor:
+		if (wValue != (USB_DT_HUB << 8))
+			return std_req_stall;
+		EPDBG(ep, "GetHubDescriptor(%d)\n", wIndex & 0xff);
+		return ast_vhub_rep_desc(ep, USB_DT_HUB, wLength);
+	case SetHubFeature:
+	case ClearHubFeature:
+		EPDBG(ep, "Get/SetHubFeature(%d)\n", wValue);
+		/* No feature, just complete the requests */
+		if (wValue == C_HUB_LOCAL_POWER ||
+		    wValue == C_HUB_OVER_CURRENT)
+			return std_req_complete;
+		return std_req_stall;
+	case SetPortFeature:
+		EPDBG(ep, "SetPortFeature(%d,%d)\n", wIndex & 0xf, wValue);
+		return ast_vhub_set_port_feature(ep, wIndex & 0xf, wValue);
+	case ClearPortFeature:
+		EPDBG(ep, "ClearPortFeature(%d,%d)\n", wIndex & 0xf, wValue);
+		return ast_vhub_clr_port_feature(ep, wIndex & 0xf, wValue);
+	default:
+		EPDBG(ep, "Unknown class request\n");
+	}
+	return std_req_stall;
+}
+
+void ast_vhub_hub_suspend(struct ast_vhub *vhub)
+{
+	unsigned int i;
+
+	UDCDBG(vhub, "USB bus suspend\n");
+
+	if (vhub->suspended)
+		return;
+
+	vhub->suspended = true;
+
+	/*
+	 * Forward to unsuspended ports without changing
+	 * their connection status.
+	 */
+	for (i = 0; i < AST_VHUB_NUM_PORTS; i++) {
+		struct ast_vhub_port *p = &vhub->ports[i];
+
+		if (!(p->status & USB_PORT_STAT_SUSPEND))
+			ast_vhub_dev_suspend(&p->dev);
+	}
+}
+
+void ast_vhub_hub_resume(struct ast_vhub *vhub)
+{
+	unsigned int i;
+
+	UDCDBG(vhub, "USB bus resume\n");
+
+	if (!vhub->suspended)
+		return;
+
+	vhub->suspended = false;
+
+	/*
+	 * Forward to unsuspended ports without changing
+	 * their connection status.
+	 */
+	for (i = 0; i < AST_VHUB_NUM_PORTS; i++) {
+		struct ast_vhub_port *p = &vhub->ports[i];
+
+		if (!(p->status & USB_PORT_STAT_SUSPEND))
+			ast_vhub_dev_resume(&p->dev);
+	}
+}
+
+void ast_vhub_hub_reset(struct ast_vhub *vhub)
+{
+	unsigned int i;
+
+	UDCDBG(vhub, "USB bus reset\n");
+
+	/*
+	 * Is the speed known ? If not we don't care, we aren't
+	 * initialized yet and ports haven't been enabled.
+	 */
+	if (vhub->speed == USB_SPEED_UNKNOWN)
+		return;
+
+	/* We aren't suspended anymore obviously */
+	vhub->suspended = false;
+
+	/* No speed set */
+	vhub->speed = USB_SPEED_UNKNOWN;
+
+	/* Wakeup not enabled anymore */
+	vhub->wakeup_en = false;
+
+	/*
+	 * Clear all port status, disable gadgets and "suspend"
+	 * them. They will be woken up by a port reset.
+	 */
+	for (i = 0; i < AST_VHUB_NUM_PORTS; i++) {
+		struct ast_vhub_port *p = &vhub->ports[i];
+
+		/* Only keep the connected flag */
+		p->status &= USB_PORT_STAT_CONNECTION;
+		p->change = 0;
+
+		/* Suspend the gadget if any */
+		ast_vhub_dev_suspend(&p->dev);
+	}
+
+	/* Cleanup HW */
+	writel(0, vhub->regs + AST_VHUB_CONF);
+	writel(0, vhub->regs + AST_VHUB_EP0_CTRL);
+	writel(VHUB_EP1_CTRL_RESET_TOGGLE |
+	       VHUB_EP1_CTRL_ENABLE,
+	       vhub->regs + AST_VHUB_EP1_CTRL);
+	writel(0, vhub->regs + AST_VHUB_EP1_STS_CHG);
+}
+
+void ast_vhub_init_hub(struct ast_vhub *vhub)
+{
+	vhub->speed = USB_SPEED_UNKNOWN;
+	INIT_WORK(&vhub->wake_work, ast_vhub_wake_work);
+}
+
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
new file mode 100644
index 000000000000..2b040257bc1f
--- /dev/null
+++ b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
@@ -0,0 +1,514 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef __ASPEED_VHUB_H
+#define __ASPEED_VHUB_H
+
+/*****************************
+ *                           *
+ * VHUB register definitions *
+ *                           *
+ *****************************/
+
+#define	AST_VHUB_CTRL		0x00	/* Root Function Control & Status Register */
+#define	AST_VHUB_CONF		0x04	/* Root Configuration Setting Register */
+#define	AST_VHUB_IER		0x08	/* Interrupt Ctrl Register */
+#define	AST_VHUB_ISR		0x0C	/* Interrupt Status Register */
+#define	AST_VHUB_EP_ACK_IER	0x10	/* Programmable Endpoint Pool ACK Interrupt Enable Register */
+#define	AST_VHUB_EP_NACK_IER	0x14	/* Programmable Endpoint Pool NACK Interrupt Enable Register  */
+#define AST_VHUB_EP_ACK_ISR	0x18	/* Programmable Endpoint Pool ACK Interrupt Status Register  */
+#define AST_VHUB_EP_NACK_ISR	0x1C	/* Programmable Endpoint Pool NACK Interrupt Status Register  */
+#define AST_VHUB_SW_RESET	0x20	/* Device Controller Soft Reset Enable Register */
+#define AST_VHUB_USBSTS		0x24	/* USB Status Register */
+#define AST_VHUB_EP_TOGGLE	0x28	/* Programmable Endpoint Pool Data Toggle Value Set */
+#define AST_VHUB_ISO_FAIL_ACC	0x2C	/* Isochronous Transaction Fail Accumulator */
+#define AST_VHUB_EP0_CTRL	0x30	/* Endpoint 0 Contrl/Status Register */
+#define AST_VHUB_EP0_DATA	0x34	/* Base Address of Endpoint 0 In/OUT Data Buffer Register */
+#define AST_VHUB_EP1_CTRL	0x38	/* Endpoint 1 Contrl/Status Register */
+#define AST_VHUB_EP1_STS_CHG	0x3C	/* Endpoint 1 Status Change Bitmap Data */
+#define AST_VHUB_SETUP0		0x80	/* Root Device Setup Data Buffer0 */
+#define AST_VHUB_SETUP1		0x84	/* Root Device Setup Data Buffer1 */
+
+/* Main control reg */
+#define VHUB_CTRL_PHY_CLK			(1 << 31)
+#define VHUB_CTRL_PHY_LOOP_TEST			(1 << 25)
+#define VHUB_CTRL_DN_PWN			(1 << 24)
+#define VHUB_CTRL_DP_PWN			(1 << 23)
+#define VHUB_CTRL_LONG_DESC			(1 << 18)
+#define VHUB_CTRL_ISO_RSP_CTRL			(1 << 17)
+#define VHUB_CTRL_SPLIT_IN			(1 << 16)
+#define VHUB_CTRL_LOOP_T_RESULT			(1 << 15)
+#define VHUB_CTRL_LOOP_T_STS			(1 << 14)
+#define VHUB_CTRL_PHY_BIST_RESULT		(1 << 13)
+#define VHUB_CTRL_PHY_BIST_CTRL			(1 << 12)
+#define VHUB_CTRL_PHY_RESET_DIS			(1 << 11)
+#define VHUB_CTRL_SET_TEST_MODE(x)		((x) << 8)
+#define VHUB_CTRL_MANUAL_REMOTE_WAKEUP		(1 << 4)
+#define VHUB_CTRL_AUTO_REMOTE_WAKEUP		(1 << 3)
+#define VHUB_CTRL_CLK_STOP_SUSPEND		(1 << 2)
+#define VHUB_CTRL_FULL_SPEED_ONLY		(1 << 1)
+#define VHUB_CTRL_UPSTREAM_CONNECT		(1 << 0)
+
+/* IER & ISR */
+#define VHUB_IRQ_USB_CMD_DEADLOCK		(1 << 18)
+#define VHUB_IRQ_EP_POOL_NAK			(1 << 17)
+#define VHUB_IRQ_EP_POOL_ACK_STALL		(1 << 16)
+#define VHUB_IRQ_DEVICE5			(1 << 13)
+#define VHUB_IRQ_DEVICE4			(1 << 12)
+#define VHUB_IRQ_DEVICE3			(1 << 11)
+#define VHUB_IRQ_DEVICE2			(1 << 10)
+#define VHUB_IRQ_DEVICE1			(1 << 9)
+#define VHUB_IRQ_BUS_RESUME			(1 << 8)
+#define VHUB_IRQ_BUS_SUSPEND 			(1 << 7)
+#define VHUB_IRQ_BUS_RESET 			(1 << 6)
+#define VHUB_IRQ_HUB_EP1_IN_DATA_ACK		(1 << 5)
+#define VHUB_IRQ_HUB_EP0_IN_DATA_NAK		(1 << 4)
+#define VHUB_IRQ_HUB_EP0_IN_ACK_STALL		(1 << 3)
+#define VHUB_IRQ_HUB_EP0_OUT_NAK		(1 << 2)
+#define VHUB_IRQ_HUB_EP0_OUT_ACK_STALL		(1 << 1)
+#define VHUB_IRQ_HUB_EP0_SETUP			(1 << 0)
+#define VHUB_IRQ_ACK_ALL			0x1ff
+
+/* SW reset reg */
+#define VHUB_SW_RESET_EP_POOL			(1 << 9)
+#define VHUB_SW_RESET_DMA_CONTROLLER		(1 << 8)
+#define VHUB_SW_RESET_DEVICE5			(1 << 5)
+#define VHUB_SW_RESET_DEVICE4			(1 << 4)
+#define VHUB_SW_RESET_DEVICE3			(1 << 3)
+#define VHUB_SW_RESET_DEVICE2			(1 << 2)
+#define VHUB_SW_RESET_DEVICE1			(1 << 1)
+#define VHUB_SW_RESET_ROOT_HUB			(1 << 0)
+#define VHUB_SW_RESET_ALL			(VHUB_SW_RESET_EP_POOL | \
+						 VHUB_SW_RESET_DMA_CONTROLLER | \
+						 VHUB_SW_RESET_DEVICE5 | \
+						 VHUB_SW_RESET_DEVICE4 | \
+						 VHUB_SW_RESET_DEVICE3 | \
+						 VHUB_SW_RESET_DEVICE2 | \
+						 VHUB_SW_RESET_DEVICE1 | \
+						 VHUB_SW_RESET_ROOT_HUB)
+/* EP ACK/NACK IRQ masks */
+#define VHUB_EP_IRQ(n)				(1 << (n))
+#define VHUB_EP_IRQ_ALL				0x7fff	/* 15 EPs */
+
+/* USB status reg */
+#define VHUB_USBSTS_HISPEED			(1 << 27)
+
+/* EP toggle */
+#define VHUB_EP_TOGGLE_VALUE			(1 << 8)
+#define VHUB_EP_TOGGLE_SET_EPNUM(x)		((x) & 0x1f)
+
+/* HUB EP0 control */
+#define VHUB_EP0_CTRL_STALL			(1 << 0)
+#define VHUB_EP0_TX_BUFF_RDY			(1 << 1)
+#define VHUB_EP0_RX_BUFF_RDY			(1 << 2)
+#define VHUB_EP0_RX_LEN(x)			(((x) >> 16) & 0x7f)
+#define VHUB_EP0_SET_TX_LEN(x)			(((x) & 0x7f) << 8)
+
+/* HUB EP1 control */
+#define VHUB_EP1_CTRL_RESET_TOGGLE		(1 << 2)
+#define VHUB_EP1_CTRL_STALL			(1 << 1)
+#define VHUB_EP1_CTRL_ENABLE			(1 << 0)
+
+/***********************************
+ *                                 *
+ * per-device register definitions *
+ *                                 *
+ ***********************************/
+#define AST_VHUB_DEV_EN_CTRL		0x00
+#define AST_VHUB_DEV_ISR		0x04
+#define AST_VHUB_DEV_EP0_CTRL		0x08
+#define AST_VHUB_DEV_EP0_DATA		0x0c
+
+/* Device enable control */
+#define VHUB_DEV_EN_SET_ADDR(x)			((x) << 8)
+#define VHUB_DEV_EN_ADDR_MASK			((0xff) << 8)
+#define VHUB_DEV_EN_EP0_NAK_IRQEN		(1 << 6)
+#define VHUB_DEV_EN_EP0_IN_ACK_IRQEN		(1 << 5)
+#define VHUB_DEV_EN_EP0_OUT_NAK_IRQEN		(1 << 4)
+#define VHUB_DEV_EN_EP0_OUT_ACK_IRQEN		(1 << 3)
+#define VHUB_DEV_EN_EP0_SETUP_IRQEN		(1 << 2)
+#define VHUB_DEV_EN_SPEED_SEL_HIGH		(1 << 1)
+#define VHUB_DEV_EN_ENABLE_PORT			(1 << 0)
+
+/* Interrupt status */
+#define VHUV_DEV_IRQ_EP0_IN_DATA_NACK		(1 << 4)
+#define VHUV_DEV_IRQ_EP0_IN_ACK_STALL		(1 << 3)
+#define VHUV_DEV_IRQ_EP0_OUT_DATA_NACK		(1 << 2)
+#define VHUV_DEV_IRQ_EP0_OUT_ACK_STALL		(1 << 1)
+#define VHUV_DEV_IRQ_EP0_SETUP			(1 << 0)
+
+/* Control bits.
+ *
+ * Note: The driver relies on the bulk of those bits
+ *       matching corresponding vHub EP0 control bits
+ */
+#define VHUB_DEV_EP0_CTRL_STALL			VHUB_EP0_CTRL_STALL
+#define VHUB_DEV_EP0_TX_BUFF_RDY		VHUB_EP0_TX_BUFF_RDY
+#define VHUB_DEV_EP0_RX_BUFF_RDY		VHUB_EP0_RX_BUFF_RDY
+#define VHUB_DEV_EP0_RX_LEN(x)			VHUB_EP0_RX_LEN(x)
+#define VHUB_DEV_EP0_SET_TX_LEN(x)		VHUB_EP0_SET_TX_LEN(x)
+
+/*************************************
+ *                                   *
+ * per-endpoint register definitions *
+ *                                   *
+ *************************************/
+
+#define AST_VHUB_EP_CONFIG		0x00
+#define AST_VHUB_EP_DMA_CTLSTAT		0x04
+#define AST_VHUB_EP_DESC_BASE		0x08
+#define AST_VHUB_EP_DESC_STATUS		0x0C
+
+/* EP config reg */
+#define VHUB_EP_CFG_SET_MAX_PKT(x)	(((x) & 0x3ff) << 16)
+#define VHUB_EP_CFG_AUTO_DATA_DISABLE	(1 << 13)
+#define VHUB_EP_CFG_STALL_CTRL		(1 << 12)
+#define VHUB_EP_CFG_SET_EP_NUM(x)	(((x) & 0xf) << 8)
+#define VHUB_EP_CFG_SET_TYPE(x)		((x) << 5)
+#define   EP_TYPE_OFF			0
+#define   EP_TYPE_BULK			1
+#define   EP_TYPE_INT			2
+#define   EP_TYPE_ISO			3
+#define VHUB_EP_CFG_DIR_OUT		(1 << 4)
+#define VHUB_EP_CFG_SET_DEV(x)		((x) << 1)
+#define VHUB_EP_CFG_ENABLE		(1 << 0)
+
+/* EP DMA control */
+#define VHUB_EP_DMA_PROC_STATUS(x)	(((x) >> 4) & 0xf)
+#define   EP_DMA_PROC_RX_IDLE		0
+#define   EP_DMA_PROC_TX_IDLE		8
+#define VHUB_EP_DMA_IN_LONG_MODE	(1 << 3)
+#define VHUB_EP_DMA_OUT_CONTIG_MODE	(1 << 3)
+#define VHUB_EP_DMA_CTRL_RESET		(1 << 2)
+#define VHUB_EP_DMA_SINGLE_STAGE	(1 << 1)
+#define VHUB_EP_DMA_DESC_MODE		(1 << 0)
+
+/* EP DMA status */
+#define VHUB_EP_DMA_SET_TX_SIZE(x)	((x) << 16)
+#define VHUB_EP_DMA_TX_SIZE(x)		(((x) >> 16) & 0x7ff)
+#define VHUB_EP_DMA_RPTR(x)		(((x) >> 8) & 0xff)
+#define VHUB_EP_DMA_SET_RPTR(x)		(((x) & 0xff) << 8)
+#define VHUB_EP_DMA_SET_CPU_WPTR(x)	(x)
+#define VHUB_EP_DMA_SINGLE_KICK		(1 << 0) /* WPTR = 1 for single mode */
+
+/*******************************
+ *                             *
+ * DMA descriptors definitions *
+ *                             *
+ *******************************/
+
+/* Desc W1 IN */
+#define VHUB_DSC1_IN_INTERRUPT		(1 << 31)
+#define VHUB_DSC1_IN_SPID_DATA0		(0 << 14)
+#define VHUB_DSC1_IN_SPID_DATA2		(1 << 14)
+#define VHUB_DSC1_IN_SPID_DATA1		(2 << 14)
+#define VHUB_DSC1_IN_SPID_MDATA		(3 << 14)
+#define VHUB_DSC1_IN_SET_LEN(x)		((x) & 0xfff)
+#define VHUB_DSC1_IN_LEN(x)		((x) & 0xfff)
+
+/****************************************
+ *                                      *
+ * Data structures and misc definitions *
+ *                                      *
+ ****************************************/
+
+#define AST_VHUB_NUM_GEN_EPs	15	/* Generic non-0 EPs */
+#define AST_VHUB_NUM_PORTS	5	/* vHub ports */
+#define AST_VHUB_EP0_MAX_PACKET	64	/* EP0's max packet size */
+#define AST_VHUB_EPn_MAX_PACKET	1024	/* Generic EPs max packet size */
+#define AST_VHUB_DESCS_COUNT	256	/* Use 256 descriptor mode (valid
+					 * values are 256 and 32)
+					 */
+
+struct ast_vhub;
+struct ast_vhub_dev;
+
+/*
+ * DMA descriptor (generic EPs only, currently only used
+ * for IN endpoints
+ */
+struct ast_vhub_desc {
+	__le32	w0;
+	__le32	w1;
+};
+
+/* A transfer request, either core-originated or internal */
+struct ast_vhub_req {
+	struct usb_request	req;
+	struct list_head	queue;
+
+	/* Actual count written to descriptors (desc mode only) */
+	unsigned int		act_count;
+
+	/*
+	 * Desc number of the final packet or -1. For non-desc
+	 * mode (or ep0), any >= 0 value means "last packet"
+	 */
+	int			last_desc;
+
+	/* Request active (pending DMAs) */
+	bool			active  : 1;
+
+	/* Internal request (don't call back core) */
+	bool			internal : 1;
+};
+#define to_ast_req(__ureq) container_of(__ureq, struct ast_vhub_req, req)
+
+/* Current state of an EP0 */
+enum ep0_state {
+	ep0_state_token,
+	ep0_state_data,
+	ep0_state_status,
+};
+
+/*
+ * An endpoint, either generic, ep0, actual gadget EP
+ * or internal use vhub EP0. vhub EP1 doesn't have an
+ * associated structure as it's mostly HW managed.
+ */
+struct ast_vhub_ep {
+	struct usb_ep		ep;
+
+	/* Request queue */
+	struct list_head	queue;
+
+	/* EP index in the device, 0 means this is an EP0 */
+	unsigned int		d_idx;
+
+	/* Dev pointer or NULL for vHub EP0 */
+	struct ast_vhub_dev	*dev;
+
+	/* vHub itself */
+	struct ast_vhub		*vhub;
+
+	/*
+	 * DMA buffer for EP0, fallback DMA buffer for misaligned
+	 * OUT transfers for generic EPs
+	 */
+	void			*buf;
+	dma_addr_t		buf_dma;
+
+	/* The rest depends on the EP type */
+	union {
+		/* EP0 (either device or vhub) */
+		struct {
+			/*
+			 * EP0 registers are "similar" for
+			 * vHub and devices but located in
+			 * different places.
+			 */
+			void __iomem		*ctlstat;
+			void __iomem		*setup;
+
+			/* Current state & direction */
+			enum ep0_state		state;
+			bool			dir_in;
+
+			/* Internal use request */
+			struct ast_vhub_req	req;
+		} ep0;
+
+		/* Generic endpoint (aka EPn) */
+		struct {
+			/* Registers */
+			void __iomem   		*regs;
+
+			/* Index in global pool (0..14) */
+			unsigned int		g_idx;
+
+			/* DMA Descriptors */
+			struct ast_vhub_desc	*descs;
+			dma_addr_t		descs_dma;
+			unsigned int		d_next;
+			unsigned int		d_last;
+			unsigned int		dma_conf;
+
+			/* Max chunk size for IN EPs */
+			unsigned int		chunk_max;
+
+			/* State flags */
+			bool			is_in :  1;
+			bool			is_iso : 1;
+			bool			stalled : 1;
+			bool			wedged : 1;
+			bool			enabled : 1;
+			bool			desc_mode : 1;
+		} epn;
+	};
+};
+#define to_ast_ep(__uep) container_of(__uep, struct ast_vhub_ep, ep)
+
+/* A device attached to a vHub port */
+struct ast_vhub_dev {
+	struct ast_vhub			*vhub;
+	void __iomem			*regs;
+
+	/* Device index (0...4) and name string */
+	unsigned int			index;
+	const char			*name;
+
+	/* sysfs enclosure for the gadget gunk */
+	struct device			*port_dev;
+
+	/* Link to gadget core */
+	struct usb_gadget		gadget;
+	struct usb_gadget_driver	*driver;
+	bool				registered : 1;
+	bool				wakeup_en : 1;
+	bool				suspended : 1;
+	bool				enabled : 1;
+
+	/* Endpoint structures */
+	struct ast_vhub_ep		ep0;
+	struct ast_vhub_ep		*epns[AST_VHUB_NUM_GEN_EPs];
+
+};
+#define to_ast_dev(__g) container_of(__g, struct ast_vhub_dev, gadget)
+
+/* Per vhub port stateinfo structure */
+struct ast_vhub_port {
+	/* Port status & status change registers */
+	u16			status;
+	u16			change;
+
+	/* Associated device slot */
+	struct ast_vhub_dev	dev;
+};
+
+/* Global vhub structure */
+struct ast_vhub {
+	struct platform_device		*pdev;
+	void __iomem			*regs;
+	int				irq;
+	spinlock_t			lock;
+	struct work_struct		wake_work;
+	struct clk			*clk;
+
+	/* EP0 DMA buffers allocated in one chunk */
+	void				*ep0_bufs;
+	dma_addr_t			ep0_bufs_dma;
+
+	/* EP0 of the vhub itself */
+	struct ast_vhub_ep		ep0;
+
+	/* State of vhub ep1 */
+	bool				ep1_stalled : 1;
+
+	/* Per-port info */
+	struct ast_vhub_port		ports[AST_VHUB_NUM_PORTS];
+
+	/* Generic EP data structures */
+	struct ast_vhub_ep		epns[AST_VHUB_NUM_GEN_EPs];
+
+	/* Upstream bus is suspended ? */
+	bool				suspended : 1;
+
+	/* Hub itself can signal remote wakeup */
+	bool				wakeup_en : 1;
+
+	/* Force full speed only */
+	bool				force_usb1 : 1;
+
+	/* Upstream bus speed captured at bus reset */
+	unsigned int			speed;
+};
+
+/* Standard request handlers result codes */
+enum std_req_rc {
+	std_req_stall = -1,	/* Stall requested */
+	std_req_complete = 0,	/* Request completed with no data */
+	std_req_data = 1,	/* Request completed with data */
+	std_req_driver = 2,	/* Pass to driver pls */
+};
+
+#ifdef CONFIG_USB_GADGET_VERBOSE
+#define UDCVDBG(u, fmt...)	dev_dbg(&(u)->pdev->dev, fmt)
+
+#define EPVDBG(ep, fmt, ...)	do {			\
+	dev_dbg(&(ep)->vhub->pdev->dev,			\
+		"%s:EP%d " fmt,				\
+		(ep)->dev ? (ep)->dev->name : "hub",	\
+		(ep)->d_idx, ##__VA_ARGS__);		\
+	} while(0)
+
+#define DVDBG(d, fmt, ...)	do {			\
+	dev_dbg(&(d)->vhub->pdev->dev,			\
+		"%s " fmt, (d)->name,			\
+		##__VA_ARGS__);				\
+	} while(0)
+
+#else
+#define UDCVDBG(u, fmt...)	do { } while(0)
+#define EPVDBG(ep, fmt, ...)	do { } while(0)
+#define DVDBG(d, fmt, ...)	do { } while(0)
+#endif
+
+#ifdef CONFIG_USB_GADGET_DEBUG
+#define UDCDBG(u, fmt...)	dev_dbg(&(u)->pdev->dev, fmt)
+
+#define EPDBG(ep, fmt, ...)	do {			\
+	dev_dbg(&(ep)->vhub->pdev->dev,			\
+		"%s:EP%d " fmt,				\
+		(ep)->dev ? (ep)->dev->name : "hub",	\
+		(ep)->d_idx, ##__VA_ARGS__);		\
+	} while(0)
+
+#define DDBG(d, fmt, ...)	do {			\
+	dev_dbg(&(d)->vhub->pdev->dev,			\
+		"%s " fmt, (d)->name,			\
+		##__VA_ARGS__);				\
+	} while(0)
+#else
+#define UDCDBG(u, fmt...)	do { } while(0)
+#define EPDBG(ep, fmt, ...)	do { } while(0)
+#define DDBG(d, fmt, ...)	do { } while(0)
+#endif
+
+/* core.c */
+void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
+		   int status);
+void ast_vhub_nuke(struct ast_vhub_ep *ep, int status);
+struct usb_request *ast_vhub_alloc_request(struct usb_ep *u_ep,
+					   gfp_t gfp_flags);
+void ast_vhub_free_request(struct usb_ep *u_ep, struct usb_request *u_req);
+void ast_vhub_init_hw(struct ast_vhub *vhub);
+
+/* ep0.c */
+void ast_vhub_ep0_handle_ack(struct ast_vhub_ep *ep, bool in_ack);
+void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep);
+void ast_vhub_init_ep0(struct ast_vhub *vhub, struct ast_vhub_ep *ep,
+		       struct ast_vhub_dev *dev);
+int ast_vhub_reply(struct ast_vhub_ep *ep, char *ptr, int len);
+int __ast_vhub_simple_reply(struct ast_vhub_ep *ep, int len, ...);
+#define ast_vhub_simple_reply(udc, ...)					       \
+	__ast_vhub_simple_reply((udc),					       \
+			       sizeof((u8[]) { __VA_ARGS__ })/sizeof(u8),      \
+			       __VA_ARGS__)
+
+/* hub.c */
+void ast_vhub_init_hub(struct ast_vhub *vhub);
+enum std_req_rc ast_vhub_std_hub_request(struct ast_vhub_ep *ep,
+					 struct usb_ctrlrequest *crq);
+enum std_req_rc ast_vhub_class_hub_request(struct ast_vhub_ep *ep,
+					   struct usb_ctrlrequest *crq);
+void ast_vhub_device_connect(struct ast_vhub *vhub, unsigned int port,
+			     bool on);
+void ast_vhub_hub_suspend(struct ast_vhub *vhub);
+void ast_vhub_hub_resume(struct ast_vhub *vhub);
+void ast_vhub_hub_reset(struct ast_vhub *vhub);
+void ast_vhub_hub_wake_all(struct ast_vhub *vhub);
+
+/* dev.c */
+int ast_vhub_init_dev(struct ast_vhub *vhub, unsigned int idx);
+void ast_vhub_del_dev(struct ast_vhub_dev *d);
+void ast_vhub_dev_irq(struct ast_vhub_dev *d);
+int ast_vhub_std_dev_request(struct ast_vhub_ep *ep,
+			     struct usb_ctrlrequest *crq);
+
+/* epn.c */
+void ast_vhub_epn_ack_irq(struct ast_vhub_ep *ep);
+void ast_vhub_update_epn_stall(struct ast_vhub_ep *ep);
+struct ast_vhub_ep *ast_vhub_alloc_epn(struct ast_vhub_dev *d, u8 addr);
+void ast_vhub_dev_suspend(struct ast_vhub_dev *d);
+void ast_vhub_dev_resume(struct ast_vhub_dev *d);
+void ast_vhub_dev_reset(struct ast_vhub_dev *d);
+
+#endif /* __ASPEED_VHUB_H */
diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c
index ad743a8493be..03959dc86cfd 100644
--- a/drivers/usb/gadget/udc/at91_udc.c
+++ b/drivers/usb/gadget/udc/at91_udc.c
@@ -234,22 +234,10 @@ static int proc_udc_show(struct seq_file *s, void *unused)
 	return 0;
 }
 
-static int proc_udc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_udc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_ops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_udc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static void create_debug_file(struct at91_udc *udc)
 {
-	udc->pde = proc_create_data(debug_filename, 0, NULL, &proc_ops, udc);
+	udc->pde = proc_create_single_data(debug_filename, 0, NULL,
+			proc_udc_show, udc);
 }
 
 static void remove_debug_file(struct at91_udc *udc)
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 27c16399c7e8..a4d99bf50f2f 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -20,7 +20,6 @@
 #include <linux/ctype.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
-#include <linux/usb/atmel_usba_udc.h>
 #include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/irq.h>
@@ -207,94 +206,45 @@ static void usba_ep_init_debugfs(struct usba_udc *udc,
 	struct dentry *ep_root;
 
 	ep_root = debugfs_create_dir(ep->ep.name, udc->debugfs_root);
-	if (!ep_root)
-		goto err_root;
 	ep->debugfs_dir = ep_root;
 
-	ep->debugfs_queue = debugfs_create_file("queue", 0400, ep_root,
-						ep, &queue_dbg_fops);
-	if (!ep->debugfs_queue)
-		goto err_queue;
-
-	if (ep->can_dma) {
-		ep->debugfs_dma_status
-			= debugfs_create_u32("dma_status", 0400, ep_root,
-					&ep->last_dma_status);
-		if (!ep->debugfs_dma_status)
-			goto err_dma_status;
-	}
-	if (ep_is_control(ep)) {
-		ep->debugfs_state
-			= debugfs_create_u32("state", 0400, ep_root,
-					&ep->state);
-		if (!ep->debugfs_state)
-			goto err_state;
-	}
-
-	return;
-
-err_state:
+	debugfs_create_file("queue", 0400, ep_root, ep, &queue_dbg_fops);
 	if (ep->can_dma)
-		debugfs_remove(ep->debugfs_dma_status);
-err_dma_status:
-	debugfs_remove(ep->debugfs_queue);
-err_queue:
-	debugfs_remove(ep_root);
-err_root:
-	dev_err(&ep->udc->pdev->dev,
-		"failed to create debugfs directory for %s\n", ep->ep.name);
+		debugfs_create_u32("dma_status", 0400, ep_root,
+				   &ep->last_dma_status);
+	if (ep_is_control(ep))
+		debugfs_create_u32("state", 0400, ep_root, &ep->state);
 }
 
 static void usba_ep_cleanup_debugfs(struct usba_ep *ep)
 {
-	debugfs_remove(ep->debugfs_queue);
-	debugfs_remove(ep->debugfs_dma_status);
-	debugfs_remove(ep->debugfs_state);
-	debugfs_remove(ep->debugfs_dir);
-	ep->debugfs_dma_status = NULL;
-	ep->debugfs_dir = NULL;
+	debugfs_remove_recursive(ep->debugfs_dir);
 }
 
 static void usba_init_debugfs(struct usba_udc *udc)
 {
-	struct dentry *root, *regs;
+	struct dentry *root;
 	struct resource *regs_resource;
 
 	root = debugfs_create_dir(udc->gadget.name, NULL);
-	if (IS_ERR(root) || !root)
-		goto err_root;
 	udc->debugfs_root = root;
 
 	regs_resource = platform_get_resource(udc->pdev, IORESOURCE_MEM,
 				CTRL_IOMEM_ID);
 
 	if (regs_resource) {
-		regs = debugfs_create_file_size("regs", 0400, root, udc,
-						&regs_dbg_fops,
-						resource_size(regs_resource));
-		if (!regs)
-			goto err_regs;
-		udc->debugfs_regs = regs;
+		debugfs_create_file_size("regs", 0400, root, udc,
+					 &regs_dbg_fops,
+					 resource_size(regs_resource));
 	}
 
 	usba_ep_init_debugfs(udc, to_usba_ep(udc->gadget.ep0));
-
-	return;
-
-err_regs:
-	debugfs_remove(root);
-err_root:
-	udc->debugfs_root = NULL;
-	dev_err(&udc->pdev->dev, "debugfs is not available\n");
 }
 
 static void usba_cleanup_debugfs(struct usba_udc *udc)
 {
 	usba_ep_cleanup_debugfs(to_usba_ep(udc->gadget.ep0));
-	debugfs_remove(udc->debugfs_regs);
-	debugfs_remove(udc->debugfs_root);
-	udc->debugfs_regs = NULL;
-	udc->debugfs_root = NULL;
+	debugfs_remove_recursive(udc->debugfs_root);
 }
 #else
 static inline void usba_ep_init_debugfs(struct usba_udc *udc,
@@ -417,7 +367,7 @@ static inline void usba_int_enb_set(struct usba_udc *udc, u32 val)
 static int vbus_is_present(struct usba_udc *udc)
 {
 	if (udc->vbus_pin)
-		return gpiod_get_value(udc->vbus_pin) ^ udc->vbus_pin_inverted;
+		return gpiod_get_value(udc->vbus_pin);
 
 	/* No Vbus detection: Assume always present */
 	return 1;
@@ -2076,7 +2026,6 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
 
 	udc->vbus_pin = devm_gpiod_get_optional(&pdev->dev, "atmel,vbus",
 						GPIOD_IN);
-	udc->vbus_pin_inverted = gpiod_is_active_low(udc->vbus_pin);
 
 	if (fifo_mode == 0) {
 		pp = NULL;
@@ -2279,15 +2228,15 @@ static int usba_udc_probe(struct platform_device *pdev)
 	if (udc->vbus_pin) {
 		irq_set_status_flags(gpiod_to_irq(udc->vbus_pin), IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(&pdev->dev,
-					gpiod_to_irq(udc->vbus_pin), NULL,
-					usba_vbus_irq_thread, USBA_VBUS_IRQFLAGS,
-					"atmel_usba_udc", udc);
-			if (ret) {
-				udc->vbus_pin = NULL;
-				dev_warn(&udc->pdev->dev,
-					 "failed to request vbus irq; "
-					 "assuming always on\n");
-			}
+				gpiod_to_irq(udc->vbus_pin), NULL,
+				usba_vbus_irq_thread, USBA_VBUS_IRQFLAGS,
+				"atmel_usba_udc", udc);
+		if (ret) {
+			udc->vbus_pin = NULL;
+			dev_warn(&udc->pdev->dev,
+				 "failed to request vbus irq; "
+				 "assuming always on\n");
+		}
 	}
 
 	ret = usb_add_gadget_udc(&pdev->dev, &udc->gadget);
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.h b/drivers/usb/gadget/udc/atmel_usba_udc.h
index 969ce8f3c3e2..030bf797cd25 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.h
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.h
@@ -287,9 +287,6 @@ struct usba_ep {
 #ifdef CONFIG_USB_GADGET_DEBUG_FS
 	u32					last_dma_status;
 	struct dentry				*debugfs_dir;
-	struct dentry				*debugfs_queue;
-	struct dentry				*debugfs_dma_status;
-	struct dentry				*debugfs_state;
 #endif
 };
 
@@ -326,7 +323,6 @@ struct usba_udc {
 	const struct usba_udc_errata *errata;
 	int irq;
 	struct gpio_desc *vbus_pin;
-	int vbus_pin_inverted;
 	int num_ep;
 	int configured_ep;
 	struct usba_fifo_cfg *fifo_cfg;
@@ -345,7 +341,6 @@ struct usba_udc {
 
 #ifdef CONFIG_USB_GADGET_DEBUG_FS
 	struct dentry *debugfs_root;
-	struct dentry *debugfs_regs;
 #endif
 
 	struct regmap *pmc;
diff --git a/drivers/usb/gadget/udc/bcm63xx_udc.c b/drivers/usb/gadget/udc/bcm63xx_udc.c
index 3a8df8601074..c1fcc77403ea 100644
--- a/drivers/usb/gadget/udc/bcm63xx_udc.c
+++ b/drivers/usb/gadget/udc/bcm63xx_udc.c
@@ -288,8 +288,6 @@ struct bcm63xx_req {
  * @ep0_reply: Pending reply from gadget driver.
  * @ep0_request: Outstanding ep0 request.
  * @debugfs_root: debugfs directory: /sys/kernel/debug/<DRV_MODULE_NAME>.
- * @debugfs_usbd: debugfs file "usbd" for controller state.
- * @debugfs_iudma: debugfs file "usbd" for IUDMA state.
  */
 struct bcm63xx_udc {
 	spinlock_t			lock;
@@ -330,8 +328,6 @@ struct bcm63xx_udc {
 	struct usb_request		*ep0_request;
 
 	struct dentry			*debugfs_root;
-	struct dentry			*debugfs_usbd;
-	struct dentry			*debugfs_iudma;
 };
 
 static const struct usb_ep_ops bcm63xx_udc_ep_ops;
@@ -2247,34 +2243,16 @@ DEFINE_SHOW_ATTRIBUTE(bcm63xx_iudma_dbg);
  */
 static void bcm63xx_udc_init_debugfs(struct bcm63xx_udc *udc)
 {
-	struct dentry *root, *usbd, *iudma;
+	struct dentry *root;
 
 	if (!IS_ENABLED(CONFIG_USB_GADGET_DEBUG_FS))
 		return;
 
 	root = debugfs_create_dir(udc->gadget.name, NULL);
-	if (IS_ERR(root) || !root)
-		goto err_root;
-
-	usbd = debugfs_create_file("usbd", 0400, root, udc,
-			&bcm63xx_usbd_dbg_fops);
-	if (!usbd)
-		goto err_usbd;
-	iudma = debugfs_create_file("iudma", 0400, root, udc,
-			&bcm63xx_iudma_dbg_fops);
-	if (!iudma)
-		goto err_iudma;
-
 	udc->debugfs_root = root;
-	udc->debugfs_usbd = usbd;
-	udc->debugfs_iudma = iudma;
-	return;
-err_iudma:
-	debugfs_remove(usbd);
-err_usbd:
-	debugfs_remove(root);
-err_root:
-	dev_err(udc->dev, "debugfs is not available\n");
+
+	debugfs_create_file("usbd", 0400, root, udc, &bcm63xx_usbd_dbg_fops);
+	debugfs_create_file("iudma", 0400, root, udc, &bcm63xx_iudma_dbg_fops);
 }
 
 /**
@@ -2285,12 +2263,7 @@ err_root:
  */
 static void bcm63xx_udc_cleanup_debugfs(struct bcm63xx_udc *udc)
 {
-	debugfs_remove(udc->debugfs_iudma);
-	debugfs_remove(udc->debugfs_usbd);
-	debugfs_remove(udc->debugfs_root);
-	udc->debugfs_iudma = NULL;
-	udc->debugfs_usbd = NULL;
-	udc->debugfs_root = NULL;
+	debugfs_remove_recursive(udc->debugfs_root);
 }
 
 /***********************************************************************
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 842814bc0e4f..cab5e4f09924 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -244,6 +244,12 @@ EXPORT_SYMBOL_GPL(usb_ep_free_request);
  * Returns zero, or a negative error code.  Endpoints that are not enabled
  * report errors; errors will also be
  * reported when the usb peripheral is disconnected.
+ *
+ * If and only if @req is successfully queued (the return value is zero),
+ * @req->complete() will be called exactly once, when the Gadget core and
+ * UDC are finished with the request.  When the completion function is called,
+ * control of the request is returned to the device driver which submitted it.
+ * The completion handler may then immediately free or reuse @req.
  */
 int usb_ep_queue(struct usb_ep *ep,
 			       struct usb_request *req, gfp_t gfp_flags)
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index 56b517a38865..9a3f7db26a5e 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -253,6 +253,7 @@ static int dr_controller_setup(struct fsl_udc *udc)
 		portctrl |= PORTSCX_PTW_16BIT;
 		/* fall through */
 	case FSL_USB2_PHY_UTMI:
+	case FSL_USB2_PHY_UTMI_DUAL:
 		if (udc->pdata->have_sysif_regs) {
 			if (udc->pdata->controller_ver) {
 				/* controller version 1.6 or above */
@@ -2207,22 +2208,8 @@ static int fsl_proc_read(struct seq_file *m, void *v)
 	return 0;
 }
 
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int fsl_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, fsl_proc_read, NULL);
-}
-
-static const struct file_operations fsl_proc_fops = {
-	.open		= fsl_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-#define create_proc_file()	proc_create(proc_filename, 0, NULL, &fsl_proc_fops)
+#define create_proc_file() \
+	proc_create_single(proc_filename, 0, NULL, fsl_proc_read)
 #define remove_proc_file()	remove_proc_entry(proc_filename, NULL)
 
 #else				/* !CONFIG_USB_GADGET_DEBUG_FILES */
diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c
index 4504d0b202db..c3721225b61e 100644
--- a/drivers/usb/gadget/udc/goku_udc.c
+++ b/drivers/usb/gadget/udc/goku_udc.c
@@ -1241,22 +1241,6 @@ done:
 	local_irq_restore(flags);
 	return 0;
 }
-
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int udc_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, udc_proc_read, PDE_DATA(file_inode(file)));
-}
-
-static const struct file_operations udc_proc_fops = {
-	.open		= udc_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 #endif	/* CONFIG_USB_GADGET_DEBUG_FILES */
 
 /*-------------------------------------------------------------------------*/
@@ -1826,7 +1810,7 @@ static int goku_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 
 #ifdef CONFIG_USB_GADGET_DEBUG_FILES
-	proc_create_data(proc_node_name, 0, NULL, &udc_proc_fops, dev);
+	proc_create_single_data(proc_node_name, 0, NULL, udc_proc_read, dev);
 #endif
 
 	retval = usb_add_gadget_udc_release(&pdev->dev, &dev->gadget,
diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index ca83c15d8ea4..729e60e49564 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -209,15 +209,12 @@ static void gr_dfs_create(struct gr_udc *dev)
 	const char *name = "gr_udc_state";
 
 	dev->dfs_root = debugfs_create_dir(dev_name(dev->dev), NULL);
-	dev->dfs_state = debugfs_create_file(name, 0444, dev->dfs_root, dev,
-					     &gr_dfs_fops);
+	debugfs_create_file(name, 0444, dev->dfs_root, dev, &gr_dfs_fops);
 }
 
 static void gr_dfs_delete(struct gr_udc *dev)
 {
-	/* Handles NULL and ERR pointers internally */
-	debugfs_remove(dev->dfs_state);
-	debugfs_remove(dev->dfs_root);
+	debugfs_remove_recursive(dev->dfs_root);
 }
 
 #else /* !CONFIG_USB_GADGET_DEBUG_FS */
diff --git a/drivers/usb/gadget/udc/gr_udc.h b/drivers/usb/gadget/udc/gr_udc.h
index 3e913268c8c5..417ad2aa2cc7 100644
--- a/drivers/usb/gadget/udc/gr_udc.h
+++ b/drivers/usb/gadget/udc/gr_udc.h
@@ -217,7 +217,6 @@ struct gr_udc {
 	spinlock_t lock; /* General lock, a.k.a. "dev->lock" in comments */
 
 	struct dentry *dfs_root;
-	struct dentry *dfs_state;
 };
 
 #define to_gr_udc(gadget)	(container_of((gadget), struct gr_udc, gadget))
diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c
index dc35a54bad90..3a16431da321 100644
--- a/drivers/usb/gadget/udc/omap_udc.c
+++ b/drivers/usb/gadget/udc/omap_udc.c
@@ -2432,22 +2432,9 @@ static int proc_udc_show(struct seq_file *s, void *_)
 	return 0;
 }
 
-static int proc_udc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_udc_show, NULL);
-}
-
-static const struct file_operations proc_ops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_udc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static void create_proc_file(void)
 {
-	proc_create(proc_filename, 0, NULL, &proc_ops);
+	proc_create_single(proc_filename, 0, NULL, proc_udc_show);
 }
 
 static void remove_proc_file(void)
diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c
index a58242e901df..014233252299 100644
--- a/drivers/usb/gadget/udc/pxa27x_udc.c
+++ b/drivers/usb/gadget/udc/pxa27x_udc.c
@@ -205,50 +205,19 @@ DEFINE_SHOW_ATTRIBUTE(eps_dbg);
 
 static void pxa_init_debugfs(struct pxa_udc *udc)
 {
-	struct dentry *root, *state, *queues, *eps;
+	struct dentry *root;
 
 	root = debugfs_create_dir(udc->gadget.name, NULL);
-	if (IS_ERR(root) || !root)
-		goto err_root;
-
-	state = debugfs_create_file("udcstate", 0400, root, udc,
-			&state_dbg_fops);
-	if (!state)
-		goto err_state;
-	queues = debugfs_create_file("queues", 0400, root, udc,
-			&queues_dbg_fops);
-	if (!queues)
-		goto err_queues;
-	eps = debugfs_create_file("epstate", 0400, root, udc,
-			&eps_dbg_fops);
-	if (!eps)
-		goto err_eps;
-
 	udc->debugfs_root = root;
-	udc->debugfs_state = state;
-	udc->debugfs_queues = queues;
-	udc->debugfs_eps = eps;
-	return;
-err_eps:
-	debugfs_remove(eps);
-err_queues:
-	debugfs_remove(queues);
-err_state:
-	debugfs_remove(root);
-err_root:
-	dev_err(udc->dev, "debugfs is not available\n");
+
+	debugfs_create_file("udcstate", 0400, root, udc, &state_dbg_fops);
+	debugfs_create_file("queues", 0400, root, udc, &queues_dbg_fops);
+	debugfs_create_file("epstate", 0400, root, udc, &eps_dbg_fops);
 }
 
 static void pxa_cleanup_debugfs(struct pxa_udc *udc)
 {
-	debugfs_remove(udc->debugfs_eps);
-	debugfs_remove(udc->debugfs_queues);
-	debugfs_remove(udc->debugfs_state);
-	debugfs_remove(udc->debugfs_root);
-	udc->debugfs_eps = NULL;
-	udc->debugfs_queues = NULL;
-	udc->debugfs_state = NULL;
-	udc->debugfs_root = NULL;
+	debugfs_remove_recursive(udc->debugfs_root);
 }
 
 #else
diff --git a/drivers/usb/gadget/udc/pxa27x_udc.h b/drivers/usb/gadget/udc/pxa27x_udc.h
index 1128d39a4255..13b2977399ab 100644
--- a/drivers/usb/gadget/udc/pxa27x_udc.h
+++ b/drivers/usb/gadget/udc/pxa27x_udc.h
@@ -476,9 +476,6 @@ struct pxa_udc {
 #endif
 #ifdef CONFIG_USB_GADGET_DEBUG_FS
 	struct dentry				*debugfs_root;
-	struct dentry				*debugfs_state;
-	struct dentry				*debugfs_queues;
-	struct dentry				*debugfs_eps;
 #endif
 };
 #define to_pxa(g)	(container_of((g), struct pxa_udc, gadget))
diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c
index 409cde4e6a51..977ea1a02cf9 100644
--- a/drivers/usb/gadget/udc/renesas_usb3.c
+++ b/drivers/usb/gadget/udc/renesas_usb3.c
@@ -333,6 +333,7 @@ struct renesas_usb3 {
 	struct extcon_dev *extcon;
 	struct work_struct extcon_work;
 	struct phy *phy;
+	struct dentry *dentry;
 
 	struct renesas_usb3_ep *usb3_ep;
 	int num_usb3_eps;
@@ -622,6 +623,13 @@ static void usb3_disconnect(struct renesas_usb3 *usb3)
 	usb3_usb2_pullup(usb3, 0);
 	usb3_clear_bit(usb3, USB30_CON_B3_CONNECT, USB3_USB30_CON);
 	usb3_reset_epc(usb3);
+	usb3_disable_irq_1(usb3, USB_INT_1_B2_RSUM | USB_INT_1_B3_PLLWKUP |
+			   USB_INT_1_B3_LUPSUCS | USB_INT_1_B3_DISABLE |
+			   USB_INT_1_SPEED | USB_INT_1_B3_WRMRST |
+			   USB_INT_1_B3_HOTRST | USB_INT_1_B2_SPND |
+			   USB_INT_1_B2_L1SPND | USB_INT_1_B2_USBRST);
+	usb3_clear_bit(usb3, USB_COM_CON_SPD_MODE, USB3_USB_COM_CON);
+	usb3_init_epc_registers(usb3);
 
 	if (usb3->driver)
 		usb3->driver->disconnect(&usb3->gadget);
@@ -2383,18 +2391,10 @@ static const struct file_operations renesas_usb3_b_device_fops = {
 static void renesas_usb3_debugfs_init(struct renesas_usb3 *usb3,
 				      struct device *dev)
 {
-	struct dentry *root, *file;
-
-	root = debugfs_create_dir(dev_name(dev), NULL);
-	if (IS_ERR_OR_NULL(root)) {
-		dev_info(dev, "%s: Can't create the root\n", __func__);
-		return;
-	}
+	usb3->dentry = debugfs_create_dir(dev_name(dev), NULL);
 
-	file = debugfs_create_file("b_device", 0644, root, usb3,
-				   &renesas_usb3_b_device_fops);
-	if (!file)
-		dev_info(dev, "%s: Can't create debugfs mode\n", __func__);
+	debugfs_create_file("b_device", 0644, usb3->dentry, usb3,
+			    &renesas_usb3_b_device_fops);
 }
 
 /*------- platform_driver ------------------------------------------------*/
@@ -2402,14 +2402,13 @@ static int renesas_usb3_remove(struct platform_device *pdev)
 {
 	struct renesas_usb3 *usb3 = platform_get_drvdata(pdev);
 
+	debugfs_remove_recursive(usb3->dentry);
 	device_remove_file(&pdev->dev, &dev_attr_role);
 
 	usb_del_gadget_udc(&usb3->gadget);
 	renesas_usb3_dma_free_prd(usb3, &pdev->dev);
 
 	__renesas_usb3_ep_free_request(usb3->ep0_req);
-	if (usb3->phy)
-		phy_put(usb3->phy);
 	pm_runtime_disable(&pdev->dev);
 
 	return 0;
@@ -2628,6 +2627,17 @@ static int renesas_usb3_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_alloc_prd;
 
+	/*
+	 * This is optional. So, if this driver cannot get a phy,
+	 * this driver will not handle a phy anymore.
+	 */
+	usb3->phy = devm_phy_optional_get(&pdev->dev, "usb");
+	if (IS_ERR(usb3->phy)) {
+		ret = PTR_ERR(usb3->phy);
+		goto err_add_udc;
+	}
+
+	pm_runtime_enable(&pdev->dev);
 	ret = usb_add_gadget_udc(&pdev->dev, &usb3->gadget);
 	if (ret < 0)
 		goto err_add_udc;
@@ -2636,20 +2646,11 @@ static int renesas_usb3_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_dev_create;
 
-	/*
-	 * This is an optional. So, if this driver cannot get a phy,
-	 * this driver will not handle a phy anymore.
-	 */
-	usb3->phy = devm_phy_get(&pdev->dev, "usb");
-	if (IS_ERR(usb3->phy))
-		usb3->phy = NULL;
-
 	usb3->workaround_for_vbus = priv->workaround_for_vbus;
 
 	renesas_usb3_debugfs_init(usb3, &pdev->dev);
 
 	dev_info(&pdev->dev, "probed%s\n", usb3->phy ? " with phy" : "");
-	pm_runtime_enable(usb3_to_dev(usb3));
 
 	return 0;
 
diff --git a/drivers/usb/gadget/udc/s3c2410_udc.c b/drivers/usb/gadget/udc/s3c2410_udc.c
index f154f49e98c8..8bf5ad7a59ad 100644
--- a/drivers/usb/gadget/udc/s3c2410_udc.c
+++ b/drivers/usb/gadget/udc/s3c2410_udc.c
@@ -1871,13 +1871,9 @@ static int s3c2410_udc_probe(struct platform_device *pdev)
 	if (retval)
 		goto err_add_udc;
 
-	if (s3c2410_udc_debugfs_root) {
-		udc->regs_info = debugfs_create_file("registers", S_IRUGO,
-				s3c2410_udc_debugfs_root,
-				udc, &s3c2410_udc_debugfs_fops);
-		if (!udc->regs_info)
-			dev_warn(dev, "debugfs file creation failed\n");
-	}
+	udc->regs_info = debugfs_create_file("registers", S_IRUGO,
+					     s3c2410_udc_debugfs_root, udc,
+					     &s3c2410_udc_debugfs_fops);
 
 	dev_dbg(dev, "probe ok\n");
 
@@ -1994,11 +1990,6 @@ static int __init udc_init(void)
 	dprintk(DEBUG_NORMAL, "%s\n", gadget_name);
 
 	s3c2410_udc_debugfs_root = debugfs_create_dir(gadget_name, NULL);
-	if (IS_ERR(s3c2410_udc_debugfs_root)) {
-		pr_err("%s: debugfs dir creation failed %ld\n",
-			gadget_name, PTR_ERR(s3c2410_udc_debugfs_root));
-		s3c2410_udc_debugfs_root = NULL;
-	}
 
 	retval = platform_driver_register(&udc_driver_24x0);
 	if (retval)
@@ -2014,7 +2005,7 @@ err:
 static void __exit udc_exit(void)
 {
 	platform_driver_unregister(&udc_driver_24x0);
-	debugfs_remove(s3c2410_udc_debugfs_root);
+	debugfs_remove_recursive(s3c2410_udc_debugfs_root);
 }
 
 module_init(udc_init);
diff --git a/drivers/usb/gadget/usbstring.c b/drivers/usb/gadget/usbstring.c
index 566ab261e8b7..7c24d1ce1088 100644
--- a/drivers/usb/gadget/usbstring.c
+++ b/drivers/usb/gadget/usbstring.c
@@ -33,7 +33,7 @@
  * characters (which are also widely used in C strings).
  */
 int
-usb_gadget_get_string (struct usb_gadget_strings *table, int id, u8 *buf)
+usb_gadget_get_string (const struct usb_gadget_strings *table, int id, u8 *buf)
 {
 	struct usb_string	*s;
 	int			len;
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index 5d958da8e1bc..6e64d3a64dbb 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -52,6 +52,13 @@ config USB_XHCI_PLATFORM
 
 	  If unsure, say N.
 
+config USB_XHCI_HISTB
+	tristate "xHCI support for HiSilicon STB SoCs"
+	depends on USB_XHCI_PLATFORM && (ARCH_HISI || COMPILE_TEST)
+	help
+	  Say 'Y' to enable the support for the xHCI host controller
+	  found in HiSilicon STB SoCs.
+
 config USB_XHCI_MTK
 	tristate "xHCI support for MediaTek SoCs"
 	select MFD_SYSCON
@@ -234,9 +241,7 @@ config USB_EHCI_TEGRA
        tristate "NVIDIA Tegra HCD support"
        depends on ARCH_TEGRA
        select USB_EHCI_ROOT_HUB_TT
-       select USB_PHY
-	select USB_ULPI
-	select USB_ULPI_VIEWPORT
+       select USB_TEGRA_PHY
        help
          This driver enables support for the internal USB Host Controllers
          found in NVIDIA Tegra SoCs. The controllers are EHCI compliant.
diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile
index 8a8cffe0b445..9b669c9f9a48 100644
--- a/drivers/usb/host/Makefile
+++ b/drivers/usb/host/Makefile
@@ -74,6 +74,7 @@ obj-$(CONFIG_USB_FHCI_HCD)	+= fhci.o
 obj-$(CONFIG_USB_XHCI_HCD)	+= xhci-hcd.o
 obj-$(CONFIG_USB_XHCI_PCI)	+= xhci-pci.o
 obj-$(CONFIG_USB_XHCI_PLATFORM) += xhci-plat-hcd.o
+obj-$(CONFIG_USB_XHCI_HISTB)	+= xhci-histb.o
 obj-$(CONFIG_USB_XHCI_MTK)	+= xhci-mtk.o
 obj-$(CONFIG_USB_XHCI_TEGRA)	+= xhci-tegra.o
 obj-$(CONFIG_USB_SL811_HCD)	+= sl811-hcd.o
diff --git a/drivers/usb/host/ehci-dbg.c b/drivers/usb/host/ehci-dbg.c
index 3ed75aaa09d9..7619cfb06883 100644
--- a/drivers/usb/host/ehci-dbg.c
+++ b/drivers/usb/host/ehci-dbg.c
@@ -1028,29 +1028,15 @@ static inline void create_debug_files(struct ehci_hcd *ehci)
 	struct usb_bus *bus = &ehci_to_hcd(ehci)->self;
 
 	ehci->debug_dir = debugfs_create_dir(bus->bus_name, ehci_debug_root);
-	if (!ehci->debug_dir)
-		return;
 
-	if (!debugfs_create_file("async", S_IRUGO, ehci->debug_dir, bus,
-						&debug_async_fops))
-		goto file_error;
-
-	if (!debugfs_create_file("bandwidth", S_IRUGO, ehci->debug_dir, bus,
-						&debug_bandwidth_fops))
-		goto file_error;
-
-	if (!debugfs_create_file("periodic", S_IRUGO, ehci->debug_dir, bus,
-						&debug_periodic_fops))
-		goto file_error;
-
-	if (!debugfs_create_file("registers", S_IRUGO, ehci->debug_dir, bus,
-						    &debug_registers_fops))
-		goto file_error;
-
-	return;
-
-file_error:
-	debugfs_remove_recursive(ehci->debug_dir);
+	debugfs_create_file("async", S_IRUGO, ehci->debug_dir, bus,
+			    &debug_async_fops);
+	debugfs_create_file("bandwidth", S_IRUGO, ehci->debug_dir, bus,
+			    &debug_bandwidth_fops);
+	debugfs_create_file("periodic", S_IRUGO, ehci->debug_dir, bus,
+			    &debug_periodic_fops);
+	debugfs_create_file("registers", S_IRUGO, ehci->debug_dir, bus,
+			    &debug_registers_fops);
 }
 
 static inline void remove_debug_files(struct ehci_hcd *ehci)
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index d927adf3afcd..89c47ae5c7d3 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -1311,10 +1311,6 @@ static int __init ehci_hcd_init(void)
 
 #ifdef CONFIG_DYNAMIC_DEBUG
 	ehci_debug_root = debugfs_create_dir("ehci", usb_debug_root);
-	if (!ehci_debug_root) {
-		retval = -ENOENT;
-		goto err_debug;
-	}
 #endif
 
 #ifdef PLATFORM_DRIVER
@@ -1361,7 +1357,6 @@ clean0:
 #ifdef CONFIG_DYNAMIC_DEBUG
 	debugfs_remove(ehci_debug_root);
 	ehci_debug_root = NULL;
-err_debug:
 #endif
 	clear_bit(USB_EHCI_LOADED, &usb_hcds_loaded);
 	return retval;
diff --git a/drivers/usb/host/ehci-mem.c b/drivers/usb/host/ehci-mem.c
index 4c6c08b675b5..21307d862af6 100644
--- a/drivers/usb/host/ehci-mem.c
+++ b/drivers/usb/host/ehci-mem.c
@@ -73,9 +73,10 @@ static struct ehci_qh *ehci_qh_alloc (struct ehci_hcd *ehci, gfp_t flags)
 	if (!qh)
 		goto done;
 	qh->hw = (struct ehci_qh_hw *)
-		dma_pool_zalloc(ehci->qh_pool, flags, &dma);
+		dma_pool_alloc(ehci->qh_pool, flags, &dma);
 	if (!qh->hw)
 		goto fail;
+	memset(qh->hw, 0, sizeof *qh->hw);
 	qh->qh_dma = dma;
 	// INIT_LIST_HEAD (&qh->qh_list);
 	INIT_LIST_HEAD (&qh->qtd_list);
diff --git a/drivers/usb/host/ehci-omap.c b/drivers/usb/host/ehci-omap.c
index 8d8bafc70c1f..7e4c13346a1e 100644
--- a/drivers/usb/host/ehci-omap.c
+++ b/drivers/usb/host/ehci-omap.c
@@ -157,10 +157,7 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev)
 		struct usb_phy *phy;
 
 		/* get the PHY device */
-		if (dev->of_node)
-			phy = devm_usb_get_phy_by_phandle(dev, "phys", i);
-		else
-			phy = devm_usb_get_phy_dev(dev, i);
+		phy = devm_usb_get_phy_by_phandle(dev, "phys", i);
 		if (IS_ERR(phy)) {
 			/* Don't bail out if PHY is not absolutely necessary */
 			if (pdata->port_mode[i] != OMAP_EHCI_PORT_MODE_PHY)
diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c
index 28e2a338b481..e56db44708bc 100644
--- a/drivers/usb/host/ehci-sched.c
+++ b/drivers/usb/host/ehci-sched.c
@@ -1287,7 +1287,7 @@ itd_urb_transaction(
 		} else {
  alloc_itd:
 			spin_unlock_irqrestore(&ehci->lock, flags);
-			itd = dma_pool_zalloc(ehci->itd_pool, mem_flags,
+			itd = dma_pool_alloc(ehci->itd_pool, mem_flags,
 					&itd_dma);
 			spin_lock_irqsave(&ehci->lock, flags);
 			if (!itd) {
@@ -1297,6 +1297,7 @@ itd_urb_transaction(
 			}
 		}
 
+		memset(itd, 0, sizeof(*itd));
 		itd->itd_dma = itd_dma;
 		itd->frame = NO_FRAME;
 		list_add(&itd->itd_list, &sched->td_list);
@@ -2080,7 +2081,7 @@ sitd_urb_transaction(
 		} else {
  alloc_sitd:
 			spin_unlock_irqrestore(&ehci->lock, flags);
-			sitd = dma_pool_zalloc(ehci->sitd_pool, mem_flags,
+			sitd = dma_pool_alloc(ehci->sitd_pool, mem_flags,
 					&sitd_dma);
 			spin_lock_irqsave(&ehci->lock, flags);
 			if (!sitd) {
@@ -2090,6 +2091,7 @@ sitd_urb_transaction(
 			}
 		}
 
+		memset(sitd, 0, sizeof(*sitd));
 		sitd->sitd_dma = sitd_dma;
 		sitd->frame = NO_FRAME;
 		list_add(&sitd->sitd_list, &iso_sched->td_list);
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index a6f4389f7e88..4d2cdec4cb78 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -36,7 +36,6 @@
 #define DRV_NAME "tegra-ehci"
 
 static struct hc_driver __read_mostly tegra_ehci_hc_driver;
-static bool usb1_reset_attempted;
 
 struct tegra_ehci_soc_config {
 	bool has_hostpc;
@@ -51,67 +50,54 @@ struct tegra_ehci_hcd {
 	enum tegra_usb_phy_port_speed port_speed;
 };
 
-/*
- * The 1st USB controller contains some UTMI pad registers that are global for
- * all the controllers on the chip. Those registers are also cleared when
- * reset is asserted to the 1st controller. This means that the 1st controller
- * can only be reset when no other controlled has finished probing. So we'll
- * reset the 1st controller before doing any other setup on any of the
- * controllers, and then never again.
- *
- * Since this is a PHY issue, the Tegra PHY driver should probably be doing
- * the resetting of the USB controllers. But to keep compatibility with old
- * device trees that don't have reset phandles in the PHYs, do it here.
- * Those old DTs will be vulnerable to total USB breakage if the 1st EHCI
- * device isn't the first one to finish probing, so warn them.
- */
 static int tegra_reset_usb_controller(struct platform_device *pdev)
 {
 	struct device_node *phy_np;
 	struct usb_hcd *hcd = platform_get_drvdata(pdev);
 	struct tegra_ehci_hcd *tegra =
 		(struct tegra_ehci_hcd *)hcd_to_ehci(hcd)->priv;
-	bool has_utmi_pad_registers = false;
+	struct reset_control *rst;
+	int err;
 
 	phy_np = of_parse_phandle(pdev->dev.of_node, "nvidia,phy", 0);
 	if (!phy_np)
 		return -ENOENT;
 
-	if (of_property_read_bool(phy_np, "nvidia,has-utmi-pad-registers"))
-		has_utmi_pad_registers = true;
+	/*
+	 * The 1st USB controller contains some UTMI pad registers that are
+	 * global for all the controllers on the chip. Those registers are
+	 * also cleared when reset is asserted to the 1st controller.
+	 */
+	rst = of_reset_control_get_shared(phy_np, "utmi-pads");
+	if (IS_ERR(rst)) {
+		dev_warn(&pdev->dev,
+			 "can't get utmi-pads reset from the PHY\n");
+		dev_warn(&pdev->dev,
+			 "continuing, but please update your DT\n");
+	} else {
+		/*
+		 * PHY driver performs UTMI-pads reset in a case of
+		 * non-legacy DT.
+		 */
+		reset_control_put(rst);
+	}
 
-	if (!usb1_reset_attempted) {
-		struct reset_control *usb1_reset;
+	of_node_put(phy_np);
 
-		if (!has_utmi_pad_registers)
-			usb1_reset = of_reset_control_get(phy_np, "utmi-pads");
-		else
-			usb1_reset = tegra->rst;
-
-		if (IS_ERR(usb1_reset)) {
-			dev_warn(&pdev->dev,
-				 "can't get utmi-pads reset from the PHY\n");
-			dev_warn(&pdev->dev,
-				 "continuing, but please update your DT\n");
-		} else {
-			reset_control_assert(usb1_reset);
-			udelay(1);
-			reset_control_deassert(usb1_reset);
-
-			if (!has_utmi_pad_registers)
-				reset_control_put(usb1_reset);
-		}
+	/* reset control is shared, hence initialize it first */
+	err = reset_control_deassert(tegra->rst);
+	if (err)
+		return err;
 
-		usb1_reset_attempted = true;
-	}
+	err = reset_control_assert(tegra->rst);
+	if (err)
+		return err;
 
-	if (!has_utmi_pad_registers) {
-		reset_control_assert(tegra->rst);
-		udelay(1);
-		reset_control_deassert(tegra->rst);
-	}
+	udelay(1);
 
-	of_node_put(phy_np);
+	err = reset_control_deassert(tegra->rst);
+	if (err)
+		return err;
 
 	return 0;
 }
@@ -440,7 +426,7 @@ static int tegra_ehci_probe(struct platform_device *pdev)
 		goto cleanup_hcd_create;
 	}
 
-	tegra->rst = devm_reset_control_get(&pdev->dev, "usb");
+	tegra->rst = devm_reset_control_get_shared(&pdev->dev, "usb");
 	if (IS_ERR(tegra->rst)) {
 		dev_err(&pdev->dev, "Can't get ehci reset\n");
 		err = PTR_ERR(tegra->rst);
@@ -452,8 +438,10 @@ static int tegra_ehci_probe(struct platform_device *pdev)
 		goto cleanup_hcd_create;
 
 	err = tegra_reset_usb_controller(pdev);
-	if (err)
+	if (err) {
+		dev_err(&pdev->dev, "Failed to reset controller\n");
 		goto cleanup_clk_en;
+	}
 
 	u_phy = devm_usb_get_phy_by_phandle(&pdev->dev, "nvidia,phy", 0);
 	if (IS_ERR(u_phy)) {
@@ -538,6 +526,9 @@ static int tegra_ehci_remove(struct platform_device *pdev)
 	usb_phy_shutdown(hcd->usb_phy);
 	usb_remove_hcd(hcd);
 
+	reset_control_assert(tegra->rst);
+	udelay(1);
+
 	clk_disable_unprepare(tegra->clk);
 
 	usb_put_hcd(hcd);
diff --git a/drivers/usb/host/fhci-dbg.c b/drivers/usb/host/fhci-dbg.c
index ebf9bb219f75..100048b3bd17 100644
--- a/drivers/usb/host/fhci-dbg.c
+++ b/drivers/usb/host/fhci-dbg.c
@@ -83,27 +83,14 @@ void fhci_dfs_create(struct fhci_hcd *fhci)
 	struct device *dev = fhci_to_hcd(fhci)->self.controller;
 
 	fhci->dfs_root = debugfs_create_dir(dev_name(dev), usb_debug_root);
-	if (!fhci->dfs_root) {
-		WARN_ON(1);
-		return;
-	}
-
-	fhci->dfs_regs = debugfs_create_file("regs", S_IFREG | S_IRUGO,
-		fhci->dfs_root, fhci, &fhci_dfs_regs_fops);
 
-	fhci->dfs_irq_stat = debugfs_create_file("irq_stat",
-		S_IFREG | S_IRUGO, fhci->dfs_root, fhci,
-		&fhci_dfs_irq_stat_fops);
-
-	WARN_ON(!fhci->dfs_regs || !fhci->dfs_irq_stat);
+	debugfs_create_file("regs", S_IFREG | S_IRUGO, fhci->dfs_root, fhci,
+			    &fhci_dfs_regs_fops);
+	debugfs_create_file("irq_stat", S_IFREG | S_IRUGO, fhci->dfs_root, fhci,
+			    &fhci_dfs_irq_stat_fops);
 }
 
 void fhci_dfs_destroy(struct fhci_hcd *fhci)
 {
-	if (!fhci->dfs_root)
-		return;
-
-	debugfs_remove(fhci->dfs_irq_stat);
-	debugfs_remove(fhci->dfs_regs);
-	debugfs_remove(fhci->dfs_root);
+	debugfs_remove_recursive(fhci->dfs_root);
 }
diff --git a/drivers/usb/host/fhci.h b/drivers/usb/host/fhci.h
index e7ec41d62410..2ce5031d866d 100644
--- a/drivers/usb/host/fhci.h
+++ b/drivers/usb/host/fhci.h
@@ -262,8 +262,6 @@ struct fhci_hcd {
 #ifdef CONFIG_FHCI_DEBUG
 	int usb_irq_stat[13];
 	struct dentry *dfs_root;
-	struct dentry *dfs_regs;
-	struct dentry *dfs_irq_stat;
 #endif
 };
 
diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c
index d8abf401918a..e64eb47770c8 100644
--- a/drivers/usb/host/fotg210-hcd.c
+++ b/drivers/usb/host/fotg210-hcd.c
@@ -844,28 +844,16 @@ static int debug_registers_open(struct inode *inode, struct file *file)
 static inline void create_debug_files(struct fotg210_hcd *fotg210)
 {
 	struct usb_bus *bus = &fotg210_to_hcd(fotg210)->self;
+	struct dentry *root;
 
-	fotg210->debug_dir = debugfs_create_dir(bus->bus_name,
-			fotg210_debug_root);
-	if (!fotg210->debug_dir)
-		return;
-
-	if (!debugfs_create_file("async", S_IRUGO, fotg210->debug_dir, bus,
-			&debug_async_fops))
-		goto file_error;
-
-	if (!debugfs_create_file("periodic", S_IRUGO, fotg210->debug_dir, bus,
-			&debug_periodic_fops))
-		goto file_error;
+	root = debugfs_create_dir(bus->bus_name, fotg210_debug_root);
+	fotg210->debug_dir = root;
 
-	if (!debugfs_create_file("registers", S_IRUGO, fotg210->debug_dir, bus,
-			&debug_registers_fops))
-		goto file_error;
-
-	return;
-
-file_error:
-	debugfs_remove_recursive(fotg210->debug_dir);
+	debugfs_create_file("async", S_IRUGO, root, bus, &debug_async_fops);
+	debugfs_create_file("periodic", S_IRUGO, root, bus,
+			    &debug_periodic_fops);
+	debugfs_create_file("registers", S_IRUGO, root, bus,
+			    &debug_registers_fops);
 }
 
 static inline void remove_debug_files(struct fotg210_hcd *fotg210)
@@ -5686,10 +5674,6 @@ static int __init fotg210_hcd_init(void)
 			sizeof(struct fotg210_itd));
 
 	fotg210_debug_root = debugfs_create_dir("fotg210", usb_debug_root);
-	if (!fotg210_debug_root) {
-		retval = -ENOENT;
-		goto err_debug;
-	}
 
 	retval = platform_driver_register(&fotg210_hcd_driver);
 	if (retval < 0)
@@ -5699,7 +5683,7 @@ static int __init fotg210_hcd_init(void)
 clean:
 	debugfs_remove(fotg210_debug_root);
 	fotg210_debug_root = NULL;
-err_debug:
+
 	clear_bit(USB_EHCI_LOADED, &usb_hcds_loaded);
 	return retval;
 }
diff --git a/drivers/usb/host/imx21-dbg.c b/drivers/usb/host/imx21-dbg.c
index a213ed6f07b5..7fcf1d9dd7f3 100644
--- a/drivers/usb/host/imx21-dbg.c
+++ b/drivers/usb/host/imx21-dbg.c
@@ -417,46 +417,22 @@ DEFINE_SHOW_ATTRIBUTE(debug_isoc);
 
 static void create_debug_files(struct imx21 *imx21)
 {
-	imx21->debug_root = debugfs_create_dir(dev_name(imx21->dev), NULL);
-	if (!imx21->debug_root)
-		goto failed_create_rootdir;
+	struct dentry *root;
 
-	if (!debugfs_create_file("status", S_IRUGO,
-			imx21->debug_root, imx21, &debug_status_fops))
-		goto failed_create;
+	root = debugfs_create_dir(dev_name(imx21->dev), NULL);
+	imx21->debug_root = root;
 
-	if (!debugfs_create_file("dmem", S_IRUGO,
-			imx21->debug_root, imx21, &debug_dmem_fops))
-		goto failed_create;
-
-	if (!debugfs_create_file("etd", S_IRUGO,
-			imx21->debug_root, imx21, &debug_etd_fops))
-		goto failed_create;
-
-	if (!debugfs_create_file("statistics", S_IRUGO,
-			imx21->debug_root, imx21, &debug_statistics_fops))
-		goto failed_create;
-
-	if (!debugfs_create_file("isoc", S_IRUGO,
-			imx21->debug_root, imx21, &debug_isoc_fops))
-		goto failed_create;
-
-	return;
-
-failed_create:
-	debugfs_remove_recursive(imx21->debug_root);
-
-failed_create_rootdir:
-	imx21->debug_root = NULL;
+	debugfs_create_file("status", S_IRUGO, root, imx21, &debug_status_fops);
+	debugfs_create_file("dmem", S_IRUGO, root, imx21, &debug_dmem_fops);
+	debugfs_create_file("etd", S_IRUGO, root, imx21, &debug_etd_fops);
+	debugfs_create_file("statistics", S_IRUGO, root, imx21,
+			    &debug_statistics_fops);
+	debugfs_create_file("isoc", S_IRUGO, root, imx21, &debug_isoc_fops);
 }
 
-
 static void remove_debug_files(struct imx21 *imx21)
 {
-	if (imx21->debug_root) {
-		debugfs_remove_recursive(imx21->debug_root);
-		imx21->debug_root = NULL;
-	}
+	debugfs_remove_recursive(imx21->debug_root);
 }
 
 #endif
diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index 4602ed801f0a..74da136d322a 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -1198,14 +1198,11 @@ static int isp116x_debug_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(isp116x_debug);
 
-static int create_debug_file(struct isp116x *isp116x)
+static void create_debug_file(struct isp116x *isp116x)
 {
 	isp116x->dentry = debugfs_create_file(hcd_name,
 					      S_IRUGO, NULL, isp116x,
 					      &isp116x_debug_fops);
-	if (!isp116x->dentry)
-		return -ENOMEM;
-	return 0;
 }
 
 static void remove_debug_file(struct isp116x *isp116x)
@@ -1215,8 +1212,8 @@ static void remove_debug_file(struct isp116x *isp116x)
 
 #else
 
-#define	create_debug_file(d)	0
-#define	remove_debug_file(d)	do{}while(0)
+static inline void create_debug_file(struct isp116x *isp116x) { }
+static inline void remove_debug_file(struct isp116x *isp116x) { }
 
 #endif				/* CONFIG_DEBUG_FS */
 
@@ -1643,16 +1640,10 @@ static int isp116x_probe(struct platform_device *pdev)
 
 	device_wakeup_enable(hcd->self.controller);
 
-	ret = create_debug_file(isp116x);
-	if (ret) {
-		ERR("Couldn't create debugfs entry\n");
-		goto err7;
-	}
+	create_debug_file(isp116x);
 
 	return 0;
 
-      err7:
-	usb_remove_hcd(hcd);
       err6:
 	usb_put_hcd(hcd);
       err5:
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 5ad9e9bdc8ee..e98673954020 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -212,7 +212,7 @@ static int usb_hcd_at91_probe(const struct hc_driver *driver,
 
 	ohci_at91->sfr_regmap = at91_dt_syscon_sfr();
 	if (!ohci_at91->sfr_regmap)
-		dev_warn(dev, "failed to find sfr node\n");
+		dev_dbg(dev, "failed to find sfr node\n");
 
 	board = hcd->self.controller->platform_data;
 	ohci = hcd_to_ohci(hcd);
diff --git a/drivers/usb/host/ohci-dbg.c b/drivers/usb/host/ohci-dbg.c
index ac7d4ac34b02..d3ee1f52aaab 100644
--- a/drivers/usb/host/ohci-dbg.c
+++ b/drivers/usb/host/ohci-dbg.c
@@ -762,50 +762,23 @@ static int debug_registers_open(struct inode *inode, struct file *file)
 static inline void create_debug_files (struct ohci_hcd *ohci)
 {
 	struct usb_bus *bus = &ohci_to_hcd(ohci)->self;
+	struct dentry *root;
 
-	ohci->debug_dir = debugfs_create_dir(bus->bus_name, ohci_debug_root);
-	if (!ohci->debug_dir)
-		goto dir_error;
+	root = debugfs_create_dir(bus->bus_name, ohci_debug_root);
+	ohci->debug_dir = root;
 
-	ohci->debug_async = debugfs_create_file("async", S_IRUGO,
-						ohci->debug_dir, ohci,
-						&debug_async_fops);
-	if (!ohci->debug_async)
-		goto async_error;
-
-	ohci->debug_periodic = debugfs_create_file("periodic", S_IRUGO,
-						   ohci->debug_dir, ohci,
-						   &debug_periodic_fops);
-	if (!ohci->debug_periodic)
-		goto periodic_error;
-
-	ohci->debug_registers = debugfs_create_file("registers", S_IRUGO,
-						    ohci->debug_dir, ohci,
-						    &debug_registers_fops);
-	if (!ohci->debug_registers)
-		goto registers_error;
+	debugfs_create_file("async", S_IRUGO, root, ohci, &debug_async_fops);
+	debugfs_create_file("periodic", S_IRUGO, root, ohci,
+			    &debug_periodic_fops);
+	debugfs_create_file("registers", S_IRUGO, root, ohci,
+			    &debug_registers_fops);
 
 	ohci_dbg (ohci, "created debug files\n");
-	return;
-
-registers_error:
-	debugfs_remove(ohci->debug_periodic);
-periodic_error:
-	debugfs_remove(ohci->debug_async);
-async_error:
-	debugfs_remove(ohci->debug_dir);
-dir_error:
-	ohci->debug_periodic = NULL;
-	ohci->debug_async = NULL;
-	ohci->debug_dir = NULL;
 }
 
 static inline void remove_debug_files (struct ohci_hcd *ohci)
 {
-	debugfs_remove(ohci->debug_registers);
-	debugfs_remove(ohci->debug_periodic);
-	debugfs_remove(ohci->debug_async);
-	debugfs_remove(ohci->debug_dir);
+	debugfs_remove_recursive(ohci->debug_dir);
 }
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 4806e0f9e8d4..210181fd98d2 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -1258,10 +1258,6 @@ static int __init ohci_hcd_mod_init(void)
 	set_bit(USB_OHCI_LOADED, &usb_hcds_loaded);
 
 	ohci_debug_root = debugfs_create_dir("ohci", usb_debug_root);
-	if (!ohci_debug_root) {
-		retval = -ENOENT;
-		goto error_debug;
-	}
 
 #ifdef PS3_SYSTEM_BUS_DRIVER
 	retval = ps3_ohci_driver_register(&PS3_SYSTEM_BUS_DRIVER);
@@ -1318,7 +1314,6 @@ static int __init ohci_hcd_mod_init(void)
 #endif
 	debugfs_remove(ohci_debug_root);
 	ohci_debug_root = NULL;
- error_debug:
 
 	clear_bit(USB_OHCI_LOADED, &usb_hcds_loaded);
 	return retval;
diff --git a/drivers/usb/host/ohci.h b/drivers/usb/host/ohci.h
index 508a803139dd..ef4813bfc5bf 100644
--- a/drivers/usb/host/ohci.h
+++ b/drivers/usb/host/ohci.h
@@ -431,9 +431,6 @@ struct ohci_hcd {
 	struct work_struct	nec_work;	/* Worker for NEC quirk */
 
 	struct dentry		*debug_dir;
-	struct dentry		*debug_async;
-	struct dentry		*debug_periodic;
-	struct dentry		*debug_registers;
 
 	/* platform-specific data -- must come last */
 	unsigned long           priv[0] __aligned(sizeof(s64));
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 67ad4bb6919a..3625a5c1a41b 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -1268,23 +1268,3 @@ static void quirk_usb_early_handoff(struct pci_dev *pdev)
 }
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID,
 			PCI_CLASS_SERIAL_USB, 8, quirk_usb_early_handoff);
-
-bool usb_xhci_needs_pci_reset(struct pci_dev *pdev)
-{
-	/*
-	 * Our dear uPD72020{1,2} friend only partially resets when
-	 * asked to via the XHCI interface, and may end up doing DMA
-	 * at the wrong addresses, as it keeps the top 32bit of some
-	 * addresses from its previous programming under obscure
-	 * circumstances.
-	 * Give it a good wack at probe time. Unfortunately, this
-	 * needs to happen before we've had a chance to discover any
-	 * quirk, or the system will be in a rather bad state.
-	 */
-	if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
-	    (pdev->device == 0x0014 || pdev->device == 0x0015))
-		return true;
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(usb_xhci_needs_pci_reset);
diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h
index 4ca0d9b7e463..63c633077d9e 100644
--- a/drivers/usb/host/pci-quirks.h
+++ b/drivers/usb/host/pci-quirks.h
@@ -16,7 +16,6 @@ void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev);
 void usb_enable_intel_xhci_ports(struct pci_dev *xhci_pdev);
 void usb_disable_xhci_ports(struct pci_dev *xhci_pdev);
 void sb800_prefetch(struct device *dev, int on);
-bool usb_xhci_needs_pci_reset(struct pci_dev *pdev);
 bool usb_amd_pt_check_port(struct device *device, int port);
 #else
 struct pci_dev;
diff --git a/drivers/usb/host/uhci-hcd.c b/drivers/usb/host/uhci-hcd.c
index f9c3947577fc..6218bfe54f52 100644
--- a/drivers/usb/host/uhci-hcd.c
+++ b/drivers/usb/host/uhci-hcd.c
@@ -590,14 +590,10 @@ static int uhci_start(struct usb_hcd *hcd)
 	init_waitqueue_head(&uhci->waitqh);
 
 #ifdef UHCI_DEBUG_OPS
-	dentry = debugfs_create_file(hcd->self.bus_name,
-			S_IFREG|S_IRUGO|S_IWUSR, uhci_debugfs_root,
-			uhci, &uhci_debug_operations);
-	if (!dentry) {
-		dev_err(uhci_dev(uhci), "couldn't create uhci debugfs entry\n");
-		return -ENOMEM;
-	}
-	uhci->dentry = dentry;
+	uhci->dentry = debugfs_create_file(hcd->self.bus_name,
+					   S_IFREG|S_IRUGO|S_IWUSR,
+					   uhci_debugfs_root, uhci,
+					   &uhci_debug_operations);
 #endif
 
 	uhci->frame = dma_zalloc_coherent(uhci_dev(uhci),
@@ -882,8 +878,6 @@ static int __init uhci_hcd_init(void)
 	if (!errbuf)
 		goto errbuf_failed;
 	uhci_debugfs_root = debugfs_create_dir("uhci", usb_debug_root);
-	if (!uhci_debugfs_root)
-		goto debug_failed;
 #endif
 
 	uhci_up_cachep = kmem_cache_create("uhci_urb_priv",
@@ -918,7 +912,6 @@ up_failed:
 #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
 	debugfs_remove(uhci_debugfs_root);
 
-debug_failed:
 	kfree(errbuf);
 
 errbuf_failed:
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index c359bae7b754..1fbfd89d0a0f 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /**
  * xhci-dbgcap.c - xHCI debug capability support
  *
diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h
index e66ea0748ba3..ce0c6072bd48 100644
--- a/drivers/usb/host/xhci-dbgcap.h
+++ b/drivers/usb/host/xhci-dbgcap.h
@@ -1,4 +1,4 @@
-
+/* SPDX-License-Identifier: GPL-2.0 */
 /**
  * xhci-dbgcap.h - xHCI debug capability support
  *
diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c
index 48779c44c361..aff79ff5aba4 100644
--- a/drivers/usb/host/xhci-dbgtty.c
+++ b/drivers/usb/host/xhci-dbgtty.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /**
  * xhci-dbgtty.c - tty glue for xHCI debug capability
  *
@@ -320,9 +321,11 @@ int xhci_dbc_tty_register_driver(struct xhci_hcd *xhci)
 
 void xhci_dbc_tty_unregister_driver(void)
 {
-	tty_unregister_driver(dbc_tty_driver);
-	put_tty_driver(dbc_tty_driver);
-	dbc_tty_driver = NULL;
+	if (dbc_tty_driver) {
+		tty_unregister_driver(dbc_tty_driver);
+		put_tty_driver(dbc_tty_driver);
+		dbc_tty_driver = NULL;
+	}
 }
 
 static void dbc_rx_push(unsigned long _port)
diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 5851052d4668..cadc01336bf8 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/uaccess.h>
 
 #include "xhci.h"
 #include "xhci-debugfs.h"
@@ -333,6 +334,67 @@ static const struct file_operations xhci_context_fops = {
 	.release		= single_release,
 };
 
+
+
+static int xhci_portsc_show(struct seq_file *s, void *unused)
+{
+	struct xhci_port	*port = s->private;
+	u32			portsc;
+
+	portsc = readl(port->addr);
+	seq_printf(s, "%s\n", xhci_decode_portsc(portsc));
+
+	return 0;
+}
+
+static int xhci_port_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, xhci_portsc_show, inode->i_private);
+}
+
+static ssize_t xhci_port_write(struct file *file,  const char __user *ubuf,
+			       size_t count, loff_t *ppos)
+{
+	struct seq_file         *s = file->private_data;
+	struct xhci_port	*port = s->private;
+	struct xhci_hcd		*xhci = hcd_to_xhci(port->rhub->hcd);
+	char                    buf[32];
+	u32			portsc;
+	unsigned long		flags;
+
+	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
+		return -EFAULT;
+
+	if (!strncmp(buf, "compliance", 10)) {
+		/* If CTC is clear, compliance is enabled by default */
+		if (!HCC2_CTC(xhci->hcc_params2))
+			return count;
+		spin_lock_irqsave(&xhci->lock, flags);
+		/* compliance mode can only be enabled on ports in RxDetect */
+		portsc = readl(port->addr);
+		if ((portsc & PORT_PLS_MASK) != XDEV_RXDETECT) {
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			return -EPERM;
+		}
+		portsc = xhci_port_state_to_neutral(portsc);
+		portsc &= ~PORT_PLS_MASK;
+		portsc |= PORT_LINK_STROBE | XDEV_COMP_MODE;
+		writel(portsc, port->addr);
+		spin_unlock_irqrestore(&xhci->lock, flags);
+	} else {
+		return -EINVAL;
+	}
+	return count;
+}
+
+static const struct file_operations port_fops = {
+	.open			= xhci_port_open,
+	.write                  = xhci_port_write,
+	.read			= seq_read,
+	.llseek			= seq_lseek,
+	.release		= single_release,
+};
+
 static void xhci_debugfs_create_files(struct xhci_hcd *xhci,
 				      struct xhci_file_map *files,
 				      size_t nentries, void *data,
@@ -449,6 +511,27 @@ void xhci_debugfs_remove_slot(struct xhci_hcd *xhci, int slot_id)
 	dev->debugfs_private = NULL;
 }
 
+static void xhci_debugfs_create_ports(struct xhci_hcd *xhci,
+				      struct dentry *parent)
+{
+	unsigned int		num_ports;
+	char			port_name[8];
+	struct xhci_port	*port;
+	struct dentry		*dir;
+
+	num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
+
+	parent = debugfs_create_dir("ports", parent);
+
+	while (num_ports--) {
+		scnprintf(port_name, sizeof(port_name), "port%02d",
+			  num_ports + 1);
+		dir = debugfs_create_dir(port_name, parent);
+		port = &xhci->hw_ports[num_ports];
+		debugfs_create_file("portsc", 0644, dir, port, &port_fops);
+	}
+}
+
 void xhci_debugfs_init(struct xhci_hcd *xhci)
 {
 	struct device		*dev = xhci_to_hcd(xhci)->self.controller;
@@ -497,6 +580,8 @@ void xhci_debugfs_init(struct xhci_hcd *xhci)
 				     xhci->debugfs_root);
 
 	xhci->debugfs_slots = debugfs_create_dir("devices", xhci->debugfs_root);
+
+	xhci_debugfs_create_ports(xhci, xhci->debugfs_root);
 }
 
 void xhci_debugfs_exit(struct xhci_hcd *xhci)
diff --git a/drivers/usb/host/xhci-histb.c b/drivers/usb/host/xhci-histb.c
new file mode 100644
index 000000000000..27f00160332e
--- /dev/null
+++ b/drivers/usb/host/xhci-histb.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * xHCI host controller driver for HiSilicon STB SoCs
+ *
+ * Copyright (C) 2017-2018 HiSilicon Co., Ltd. http://www.hisilicon.com
+ *
+ * Authors: Jianguo Sun <sunjianguo1@huawei.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+
+#include "xhci.h"
+
+#define GTXTHRCFG		0xc108
+#define GRXTHRCFG		0xc10c
+#define REG_GUSB2PHYCFG0	0xc200
+#define BIT_UTMI_8_16		BIT(3)
+#define BIT_UTMI_ULPI		BIT(4)
+#define BIT_FREECLK_EXIST	BIT(30)
+
+#define REG_GUSB3PIPECTL0	0xc2c0
+#define USB3_DEEMPHASIS_MASK	GENMASK(2, 1)
+#define USB3_DEEMPHASIS0	BIT(1)
+#define USB3_TX_MARGIN1		BIT(4)
+
+struct xhci_hcd_histb {
+	struct device		*dev;
+	struct usb_hcd		*hcd;
+	void __iomem		*ctrl;
+	struct clk		*bus_clk;
+	struct clk		*utmi_clk;
+	struct clk		*pipe_clk;
+	struct clk		*suspend_clk;
+	struct reset_control	*soft_reset;
+};
+
+static inline struct xhci_hcd_histb *hcd_to_histb(struct usb_hcd *hcd)
+{
+	return dev_get_drvdata(hcd->self.controller);
+}
+
+static int xhci_histb_config(struct xhci_hcd_histb *histb)
+{
+	struct device_node *np = histb->dev->of_node;
+	u32 regval;
+
+	if (of_property_match_string(np, "phys-names", "inno") >= 0) {
+		/* USB2 PHY chose ulpi 8bit interface */
+		regval = readl(histb->ctrl + REG_GUSB2PHYCFG0);
+		regval &= ~BIT_UTMI_ULPI;
+		regval &= ~(BIT_UTMI_8_16);
+		regval &= ~BIT_FREECLK_EXIST;
+		writel(regval, histb->ctrl + REG_GUSB2PHYCFG0);
+	}
+
+	if (of_property_match_string(np, "phys-names", "combo") >= 0) {
+		/*
+		 * write 0x010c0012 to GUSB3PIPECTL0
+		 * GUSB3PIPECTL0[5:3] = 010 : Tx Margin = 900mV ,
+		 * decrease TX voltage
+		 * GUSB3PIPECTL0[2:1] = 01 : Tx Deemphasis = -3.5dB,
+		 * refer to xHCI spec
+		 */
+		regval = readl(histb->ctrl + REG_GUSB3PIPECTL0);
+		regval &= ~USB3_DEEMPHASIS_MASK;
+		regval |= USB3_DEEMPHASIS0;
+		regval |= USB3_TX_MARGIN1;
+		writel(regval, histb->ctrl + REG_GUSB3PIPECTL0);
+	}
+
+	writel(0x23100000, histb->ctrl + GTXTHRCFG);
+	writel(0x23100000, histb->ctrl + GRXTHRCFG);
+
+	return 0;
+}
+
+static int xhci_histb_clks_get(struct xhci_hcd_histb *histb)
+{
+	struct device *dev = histb->dev;
+
+	histb->bus_clk = devm_clk_get(dev, "bus");
+	if (IS_ERR(histb->bus_clk)) {
+		dev_err(dev, "fail to get bus clk\n");
+		return PTR_ERR(histb->bus_clk);
+	}
+
+	histb->utmi_clk = devm_clk_get(dev, "utmi");
+	if (IS_ERR(histb->utmi_clk)) {
+		dev_err(dev, "fail to get utmi clk\n");
+		return PTR_ERR(histb->utmi_clk);
+	}
+
+	histb->pipe_clk = devm_clk_get(dev, "pipe");
+	if (IS_ERR(histb->pipe_clk)) {
+		dev_err(dev, "fail to get pipe clk\n");
+		return PTR_ERR(histb->pipe_clk);
+	}
+
+	histb->suspend_clk = devm_clk_get(dev, "suspend");
+	if (IS_ERR(histb->suspend_clk)) {
+		dev_err(dev, "fail to get suspend clk\n");
+		return PTR_ERR(histb->suspend_clk);
+	}
+
+	return 0;
+}
+
+static int xhci_histb_host_enable(struct xhci_hcd_histb *histb)
+{
+	int ret;
+
+	ret = clk_prepare_enable(histb->bus_clk);
+	if (ret) {
+		dev_err(histb->dev, "failed to enable bus clk\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(histb->utmi_clk);
+	if (ret) {
+		dev_err(histb->dev, "failed to enable utmi clk\n");
+		goto err_utmi_clk;
+	}
+
+	ret = clk_prepare_enable(histb->pipe_clk);
+	if (ret) {
+		dev_err(histb->dev, "failed to enable pipe clk\n");
+		goto err_pipe_clk;
+	}
+
+	ret = clk_prepare_enable(histb->suspend_clk);
+	if (ret) {
+		dev_err(histb->dev, "failed to enable suspend clk\n");
+		goto err_suspend_clk;
+	}
+
+	reset_control_deassert(histb->soft_reset);
+
+	return 0;
+
+err_suspend_clk:
+	clk_disable_unprepare(histb->pipe_clk);
+err_pipe_clk:
+	clk_disable_unprepare(histb->utmi_clk);
+err_utmi_clk:
+	clk_disable_unprepare(histb->bus_clk);
+
+	return ret;
+}
+
+static void xhci_histb_host_disable(struct xhci_hcd_histb *histb)
+{
+	reset_control_assert(histb->soft_reset);
+
+	clk_disable_unprepare(histb->suspend_clk);
+	clk_disable_unprepare(histb->pipe_clk);
+	clk_disable_unprepare(histb->utmi_clk);
+	clk_disable_unprepare(histb->bus_clk);
+}
+
+static void xhci_histb_quirks(struct device *dev, struct xhci_hcd *xhci)
+{
+	/*
+	 * As of now platform drivers don't provide MSI support so we ensure
+	 * here that the generic code does not try to make a pci_dev from our
+	 * dev struct in order to setup MSI
+	 */
+	xhci->quirks |= XHCI_PLAT;
+}
+
+/* called during probe() after chip reset completes */
+static int xhci_histb_setup(struct usb_hcd *hcd)
+{
+	struct xhci_hcd_histb *histb = hcd_to_histb(hcd);
+	int ret;
+
+	if (usb_hcd_is_primary_hcd(hcd)) {
+		ret = xhci_histb_config(histb);
+		if (ret)
+			return ret;
+	}
+
+	return xhci_gen_setup(hcd, xhci_histb_quirks);
+}
+
+static const struct xhci_driver_overrides xhci_histb_overrides __initconst = {
+	.reset = xhci_histb_setup,
+};
+
+static struct hc_driver __read_mostly xhci_histb_hc_driver;
+static int xhci_histb_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct xhci_hcd_histb *histb;
+	const struct hc_driver *driver;
+	struct usb_hcd *hcd;
+	struct xhci_hcd *xhci;
+	struct resource *res;
+	int irq;
+	int ret = -ENODEV;
+
+	if (usb_disabled())
+		return -ENODEV;
+
+	driver = &xhci_histb_hc_driver;
+	histb = devm_kzalloc(dev, sizeof(*histb), GFP_KERNEL);
+	if (!histb)
+		return -ENOMEM;
+
+	histb->dev = dev;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	histb->ctrl = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(histb->ctrl))
+		return PTR_ERR(histb->ctrl);
+
+	ret = xhci_histb_clks_get(histb);
+	if (ret)
+		return ret;
+
+	histb->soft_reset = devm_reset_control_get(dev, "soft");
+	if (IS_ERR(histb->soft_reset)) {
+		dev_err(dev, "failed to get soft reset\n");
+		return PTR_ERR(histb->soft_reset);
+	}
+
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
+	device_enable_async_suspend(dev);
+
+	/* Initialize dma_mask and coherent_dma_mask to 32-bits */
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	hcd = usb_create_hcd(driver, dev, dev_name(dev));
+	if (!hcd) {
+		ret = -ENOMEM;
+		goto disable_pm;
+	}
+
+	hcd->regs = histb->ctrl;
+	hcd->rsrc_start = res->start;
+	hcd->rsrc_len = resource_size(res);
+
+	histb->hcd = hcd;
+	dev_set_drvdata(hcd->self.controller, histb);
+
+	ret = xhci_histb_host_enable(histb);
+	if (ret)
+		goto put_hcd;
+
+	xhci = hcd_to_xhci(hcd);
+
+	device_wakeup_enable(hcd->self.controller);
+
+	xhci->main_hcd = hcd;
+	xhci->shared_hcd = usb_create_shared_hcd(driver, dev, dev_name(dev),
+						 hcd);
+	if (!xhci->shared_hcd) {
+		ret = -ENOMEM;
+		goto disable_host;
+	}
+
+	if (device_property_read_bool(dev, "usb2-lpm-disable"))
+		xhci->quirks |= XHCI_HW_LPM_DISABLE;
+
+	if (device_property_read_bool(dev, "usb3-lpm-capable"))
+		xhci->quirks |= XHCI_LPM_SUPPORT;
+
+	/* imod_interval is the interrupt moderation value in nanoseconds. */
+	xhci->imod_interval = 40000;
+	device_property_read_u32(dev, "imod-interval-ns",
+				 &xhci->imod_interval);
+
+	ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
+	if (ret)
+		goto put_usb3_hcd;
+
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+		xhci->shared_hcd->can_do_streams = 1;
+
+	ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
+	if (ret)
+		goto dealloc_usb2_hcd;
+
+	device_enable_async_suspend(dev);
+	pm_runtime_put_noidle(dev);
+
+	/*
+	 * Prevent runtime pm from being on as default, users should enable
+	 * runtime pm using power/control in sysfs.
+	 */
+	pm_runtime_forbid(dev);
+
+	return 0;
+
+dealloc_usb2_hcd:
+	usb_remove_hcd(hcd);
+put_usb3_hcd:
+	usb_put_hcd(xhci->shared_hcd);
+disable_host:
+	xhci_histb_host_disable(histb);
+put_hcd:
+	usb_put_hcd(hcd);
+disable_pm:
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+
+	return ret;
+}
+
+static int xhci_histb_remove(struct platform_device *dev)
+{
+	struct xhci_hcd_histb *histb = platform_get_drvdata(dev);
+	struct usb_hcd *hcd = histb->hcd;
+	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
+
+	xhci->xhc_state |= XHCI_STATE_REMOVING;
+
+	usb_remove_hcd(xhci->shared_hcd);
+	device_wakeup_disable(&dev->dev);
+
+	usb_remove_hcd(hcd);
+	usb_put_hcd(xhci->shared_hcd);
+
+	xhci_histb_host_disable(histb);
+	usb_put_hcd(hcd);
+	pm_runtime_put_sync(&dev->dev);
+	pm_runtime_disable(&dev->dev);
+
+	return 0;
+}
+
+static int __maybe_unused xhci_histb_suspend(struct device *dev)
+{
+	struct xhci_hcd_histb *histb = dev_get_drvdata(dev);
+	struct usb_hcd *hcd = histb->hcd;
+	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
+	int ret;
+
+	ret = xhci_suspend(xhci, device_may_wakeup(dev));
+
+	if (!device_may_wakeup(dev))
+		xhci_histb_host_disable(histb);
+
+	return ret;
+}
+
+static int __maybe_unused xhci_histb_resume(struct device *dev)
+{
+	struct xhci_hcd_histb *histb = dev_get_drvdata(dev);
+	struct usb_hcd *hcd = histb->hcd;
+	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+
+	if (!device_may_wakeup(dev))
+		xhci_histb_host_enable(histb);
+
+	return xhci_resume(xhci, 0);
+}
+
+static const struct dev_pm_ops xhci_histb_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(xhci_histb_suspend, xhci_histb_resume)
+};
+#define DEV_PM_OPS (IS_ENABLED(CONFIG_PM) ? &xhci_histb_pm_ops : NULL)
+
+#ifdef CONFIG_OF
+static const struct of_device_id histb_xhci_of_match[] = {
+	{ .compatible = "hisilicon,hi3798cv200-xhci"},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, histb_xhci_of_match);
+#endif
+
+static struct platform_driver histb_xhci_driver = {
+	.probe	= xhci_histb_probe,
+	.remove	= xhci_histb_remove,
+	.driver	= {
+		.name = "xhci-histb",
+		.pm = DEV_PM_OPS,
+		.of_match_table = of_match_ptr(histb_xhci_of_match),
+	},
+};
+MODULE_ALIAS("platform:xhci-histb");
+
+static int __init xhci_histb_init(void)
+{
+	xhci_init_driver(&xhci_histb_hc_driver, &xhci_histb_overrides);
+	return platform_driver_register(&histb_xhci_driver);
+}
+module_init(xhci_histb_init);
+
+static void __exit xhci_histb_exit(void)
+{
+	platform_driver_unregister(&histb_xhci_driver);
+}
+module_exit(xhci_histb_exit);
+
+MODULE_DESCRIPTION("HiSilicon STB xHCI Host Controller Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 72ebbc908e19..a4b95d019f84 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -189,9 +189,10 @@ static void xhci_usb2_hub_descriptor(struct usb_hcd *hcd, struct xhci_hcd *xhci,
 	__u8 port_removable[(USB_MAXCHILDREN + 1 + 7) / 8];
 	u32 portsc;
 	unsigned int i;
+	struct xhci_hub *rhub;
 
-	ports = xhci->num_usb2_ports;
-
+	rhub = &xhci->usb2_rhub;
+	ports = rhub->num_ports;
 	xhci_common_hub_descriptor(xhci, desc, ports);
 	desc->bDescriptorType = USB_DT_HUB;
 	temp = 1 + (ports / 8);
@@ -202,7 +203,7 @@ static void xhci_usb2_hub_descriptor(struct usb_hcd *hcd, struct xhci_hcd *xhci,
 	 */
 	memset(port_removable, 0, sizeof(port_removable));
 	for (i = 0; i < ports; i++) {
-		portsc = readl(xhci->usb2_ports[i]);
+		portsc = readl(rhub->ports[i]->addr);
 		/* If a device is removable, PORTSC reports a 0, same as in the
 		 * hub descriptor DeviceRemovable bits.
 		 */
@@ -241,8 +242,10 @@ static void xhci_usb3_hub_descriptor(struct usb_hcd *hcd, struct xhci_hcd *xhci,
 	u16 port_removable;
 	u32 portsc;
 	unsigned int i;
+	struct xhci_hub *rhub;
 
-	ports = xhci->num_usb3_ports;
+	rhub = &xhci->usb3_rhub;
+	ports = rhub->num_ports;
 	xhci_common_hub_descriptor(xhci, desc, ports);
 	desc->bDescriptorType = USB_DT_SS_HUB;
 	desc->bDescLength = USB_DT_SS_HUB_SIZE;
@@ -256,7 +259,7 @@ static void xhci_usb3_hub_descriptor(struct usb_hcd *hcd, struct xhci_hcd *xhci,
 	port_removable = 0;
 	/* bit 0 is reserved, bit 1 is for port 1, etc. */
 	for (i = 0; i < ports; i++) {
-		portsc = readl(xhci->usb3_ports[i]);
+		portsc = readl(rhub->ports[i]->addr);
 		if (portsc & PORT_DEV_REMOVE)
 			port_removable |= 1 << (i + 1);
 	}
@@ -354,7 +357,7 @@ int xhci_find_slot_id_by_port(struct usb_hcd *hcd, struct xhci_hcd *xhci,
 
 	slot_id = 0;
 	for (i = 0; i < MAX_HC_SLOTS; i++) {
-		if (!xhci->devs[i])
+		if (!xhci->devs[i] || !xhci->devs[i]->udev)
 			continue;
 		speed = xhci->devs[i]->udev->speed;
 		if (((speed >= USB_SPEED_SUPER) == (hcd->speed >= HCD_USB3))
@@ -538,28 +541,13 @@ static void xhci_clear_port_change_bit(struct xhci_hcd *xhci, u16 wValue,
 			port_change_bit, wIndex, port_status);
 }
 
-static int xhci_get_ports(struct usb_hcd *hcd, __le32 __iomem ***port_array)
+struct xhci_hub *xhci_get_rhub(struct usb_hcd *hcd)
 {
-	int max_ports;
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 
-	if (hcd->speed >= HCD_USB3) {
-		max_ports = xhci->num_usb3_ports;
-		*port_array = xhci->usb3_ports;
-	} else {
-		max_ports = xhci->num_usb2_ports;
-		*port_array = xhci->usb2_ports;
-	}
-
-	return max_ports;
-}
-
-static __le32 __iomem *xhci_get_port_io_addr(struct usb_hcd *hcd, int index)
-{
-	__le32 __iomem **port_array;
-
-	xhci_get_ports(hcd, &port_array);
-	return port_array[index];
+	if (hcd->speed >= HCD_USB3)
+		return &xhci->usb3_rhub;
+	return &xhci->usb2_rhub;
 }
 
 /*
@@ -570,21 +558,23 @@ static __le32 __iomem *xhci_get_port_io_addr(struct usb_hcd *hcd, int index)
 static void xhci_set_port_power(struct xhci_hcd *xhci, struct usb_hcd *hcd,
 				u16 index, bool on, unsigned long *flags)
 {
-	__le32 __iomem *addr;
+	struct xhci_hub *rhub;
+	struct xhci_port *port;
 	u32 temp;
 
-	addr = xhci_get_port_io_addr(hcd, index);
-	temp = readl(addr);
+	rhub = xhci_get_rhub(hcd);
+	port = rhub->ports[index];
+	temp = readl(port->addr);
 	temp = xhci_port_state_to_neutral(temp);
 	if (on) {
 		/* Power on */
-		writel(temp | PORT_POWER, addr);
-		temp = readl(addr);
+		writel(temp | PORT_POWER, port->addr);
+		temp = readl(port->addr);
 		xhci_dbg(xhci, "set port power, actual port %d status  = 0x%x\n",
 						index, temp);
 	} else {
 		/* Power off */
-		writel(temp & ~PORT_POWER, addr);
+		writel(temp & ~PORT_POWER, port->addr);
 	}
 
 	spin_unlock_irqrestore(&xhci->lock, *flags);
@@ -600,13 +590,13 @@ static void xhci_port_set_test_mode(struct xhci_hcd *xhci,
 	u16 test_mode, u16 wIndex)
 {
 	u32 temp;
-	__le32 __iomem *addr;
+	struct xhci_port *port;
 
-	/* xhci only supports test mode for usb2 ports, i.e. xhci->main_hcd */
-	addr = xhci_get_port_io_addr(xhci->main_hcd, wIndex);
-	temp = readl(addr + PORTPMSC);
+	/* xhci only supports test mode for usb2 ports */
+	port = xhci->usb2_rhub.ports[wIndex];
+	temp = readl(port->addr + PORTPMSC);
 	temp |= test_mode << PORT_TEST_MODE_SHIFT;
-	writel(temp, addr + PORTPMSC);
+	writel(temp, port->addr + PORTPMSC);
 	xhci->test_mode = test_mode;
 	if (test_mode == TEST_FORCE_EN)
 		xhci_start(xhci);
@@ -633,10 +623,10 @@ static int xhci_enter_test_mode(struct xhci_hcd *xhci,
 	/* Put all ports to the Disable state by clear PP */
 	xhci_dbg(xhci, "Disable all port (PP = 0)\n");
 	/* Power off USB3 ports*/
-	for (i = 0; i < xhci->num_usb3_ports; i++)
+	for (i = 0; i < xhci->usb3_rhub.num_ports; i++)
 		xhci_set_port_power(xhci, xhci->shared_hcd, i, false, flags);
 	/* Power off USB2 ports*/
-	for (i = 0; i < xhci->num_usb2_ports; i++)
+	for (i = 0; i < xhci->usb2_rhub.num_ports; i++)
 		xhci_set_port_power(xhci, xhci->main_hcd, i, false, flags);
 	/* Stop the controller */
 	xhci_dbg(xhci, "Stop controller\n");
@@ -672,24 +662,24 @@ static int xhci_exit_test_mode(struct xhci_hcd *xhci)
 	return xhci_reset(xhci);
 }
 
-void xhci_set_link_state(struct xhci_hcd *xhci, __le32 __iomem **port_array,
-				int port_id, u32 link_state)
+void xhci_set_link_state(struct xhci_hcd *xhci, struct xhci_port *port,
+			 u32 link_state)
 {
 	u32 temp;
 
-	temp = readl(port_array[port_id]);
+	temp = readl(port->addr);
 	temp = xhci_port_state_to_neutral(temp);
 	temp &= ~PORT_PLS_MASK;
 	temp |= PORT_LINK_STROBE | link_state;
-	writel(temp, port_array[port_id]);
+	writel(temp, port->addr);
 }
 
 static void xhci_set_remote_wake_mask(struct xhci_hcd *xhci,
-		__le32 __iomem **port_array, int port_id, u16 wake_mask)
+				      struct xhci_port *port, u16 wake_mask)
 {
 	u32 temp;
 
-	temp = readl(port_array[port_id]);
+	temp = readl(port->addr);
 	temp = xhci_port_state_to_neutral(temp);
 
 	if (wake_mask & USB_PORT_FEAT_REMOTE_WAKE_CONNECT)
@@ -707,20 +697,20 @@ static void xhci_set_remote_wake_mask(struct xhci_hcd *xhci,
 	else
 		temp &= ~PORT_WKOC_E;
 
-	writel(temp, port_array[port_id]);
+	writel(temp, port->addr);
 }
 
 /* Test and clear port RWC bit */
-void xhci_test_and_clear_bit(struct xhci_hcd *xhci, __le32 __iomem **port_array,
-				int port_id, u32 port_bit)
+void xhci_test_and_clear_bit(struct xhci_hcd *xhci, struct xhci_port *port,
+			     u32 port_bit)
 {
 	u32 temp;
 
-	temp = readl(port_array[port_id]);
+	temp = readl(port->addr);
 	if (temp & port_bit) {
 		temp = xhci_port_state_to_neutral(temp);
 		temp |= port_bit;
-		writel(temp, port_array[port_id]);
+		writel(temp, port->addr);
 	}
 }
 
@@ -794,7 +784,7 @@ static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci,
 static void xhci_del_comp_mod_timer(struct xhci_hcd *xhci, u32 status,
 				    u16 wIndex)
 {
-	u32 all_ports_seen_u0 = ((1 << xhci->num_usb3_ports)-1);
+	u32 all_ports_seen_u0 = ((1 << xhci->usb3_rhub.num_ports) - 1);
 	bool port_in_u0 = ((status & PORT_PLS_MASK) == XDEV_U0);
 
 	if (!(xhci->quirks & XHCI_COMP_MODE_QUIRK))
@@ -840,8 +830,7 @@ static u32 xhci_get_ext_port_status(u32 raw_port_status, u32 port_li)
  */
 static u32 xhci_get_port_status(struct usb_hcd *hcd,
 		struct xhci_bus_state *bus_state,
-		__le32 __iomem **port_array,
-		u16 wIndex, u32 raw_port_status,
+	u16 wIndex, u32 raw_port_status,
 		unsigned long flags)
 	__releases(&xhci->lock)
 	__acquires(&xhci->lock)
@@ -849,6 +838,11 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 	u32 status = 0;
 	int slot_id;
+	struct xhci_hub *rhub;
+	struct xhci_port *port;
+
+	rhub = xhci_get_rhub(hcd);
+	port = rhub->ports[wIndex];
 
 	/* wPortChange bits */
 	if (raw_port_status & PORT_CSC)
@@ -919,10 +913,8 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 
 			set_bit(wIndex, &bus_state->rexit_ports);
 
-			xhci_test_and_clear_bit(xhci, port_array, wIndex,
-						PORT_PLC);
-			xhci_set_link_state(xhci, port_array, wIndex,
-					XDEV_U0);
+			xhci_test_and_clear_bit(xhci, port, PORT_PLC);
+			xhci_set_link_state(xhci, port, XDEV_U0);
 
 			spin_unlock_irqrestore(&xhci->lock, flags);
 			time_left = wait_for_completion_timeout(
@@ -940,7 +932,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 				}
 				xhci_ring_device(xhci, slot_id);
 			} else {
-				int port_status = readl(port_array[wIndex]);
+				int port_status = readl(port->addr);
 				xhci_warn(xhci, "Port resume took longer than %i msec, port status = 0x%x\n",
 						XHCI_MAX_REXIT_TIMEOUT,
 						port_status);
@@ -1024,15 +1016,18 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 	unsigned long flags;
 	u32 temp, status;
 	int retval = 0;
-	__le32 __iomem **port_array;
 	int slot_id;
 	struct xhci_bus_state *bus_state;
 	u16 link_state = 0;
 	u16 wake_mask = 0;
 	u16 timeout = 0;
 	u16 test_mode = 0;
+	struct xhci_hub *rhub;
+	struct xhci_port **ports;
 
-	max_ports = xhci_get_ports(hcd, &port_array);
+	rhub = xhci_get_rhub(hcd);
+	ports = rhub->ports;
+	max_ports = rhub->num_ports;
 	bus_state = &xhci->bus_state[hcd_index(hcd)];
 
 	spin_lock_irqsave(&xhci->lock, flags);
@@ -1070,15 +1065,15 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		if (!wIndex || wIndex > max_ports)
 			goto error;
 		wIndex--;
-		temp = readl(port_array[wIndex]);
+		temp = readl(ports[wIndex]->addr);
 		if (temp == ~(u32)0) {
 			xhci_hc_died(xhci);
 			retval = -ENODEV;
 			break;
 		}
 		trace_xhci_get_port_status(wIndex, temp);
-		status = xhci_get_port_status(hcd, bus_state, port_array,
-				wIndex, temp, flags);
+		status = xhci_get_port_status(hcd, bus_state, wIndex, temp,
+					      flags);
 		if (status == 0xffffffff)
 			goto error;
 
@@ -1096,7 +1091,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 				retval = -EINVAL;
 				break;
 			}
-			port_li = readl(port_array[wIndex] + PORTLI);
+			port_li = readl(ports[wIndex]->addr + PORTLI);
 			status = xhci_get_ext_port_status(temp, port_li);
 			put_unaligned_le32(cpu_to_le32(status), &buf[4]);
 		}
@@ -1114,7 +1109,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		if (!wIndex || wIndex > max_ports)
 			goto error;
 		wIndex--;
-		temp = readl(port_array[wIndex]);
+		temp = readl(ports[wIndex]->addr);
 		if (temp == ~(u32)0) {
 			xhci_hc_died(xhci);
 			retval = -ENODEV;
@@ -1124,10 +1119,10 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		/* FIXME: What new port features do we need to support? */
 		switch (wValue) {
 		case USB_PORT_FEAT_SUSPEND:
-			temp = readl(port_array[wIndex]);
+			temp = readl(ports[wIndex]->addr);
 			if ((temp & PORT_PLS_MASK) != XDEV_U0) {
 				/* Resume the port to U0 first */
-				xhci_set_link_state(xhci, port_array, wIndex,
+				xhci_set_link_state(xhci, ports[wIndex],
 							XDEV_U0);
 				spin_unlock_irqrestore(&xhci->lock, flags);
 				msleep(10);
@@ -1137,7 +1132,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			 * a port unless the port reports that it is in the
 			 * enabled (PED = ‘1’,PLS < ‘3’) state.
 			 */
-			temp = readl(port_array[wIndex]);
+			temp = readl(ports[wIndex]->addr);
 			if ((temp & PORT_PE) == 0 || (temp & PORT_RESET)
 				|| (temp & PORT_PLS_MASK) >= XDEV_U3) {
 				xhci_warn(xhci, "USB core suspending device not in U0/U1/U2.\n");
@@ -1155,18 +1150,17 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			xhci_stop_device(xhci, slot_id, 1);
 			spin_lock_irqsave(&xhci->lock, flags);
 
-			xhci_set_link_state(xhci, port_array, wIndex, XDEV_U3);
+			xhci_set_link_state(xhci, ports[wIndex], XDEV_U3);
 
 			spin_unlock_irqrestore(&xhci->lock, flags);
 			msleep(10); /* wait device to enter */
 			spin_lock_irqsave(&xhci->lock, flags);
 
-			temp = readl(port_array[wIndex]);
+			temp = readl(ports[wIndex]->addr);
 			bus_state->suspended_ports |= 1 << wIndex;
 			break;
 		case USB_PORT_FEAT_LINK_STATE:
-			temp = readl(port_array[wIndex]);
-
+			temp = readl(ports[wIndex]->addr);
 			/* Disable port */
 			if (link_state == USB_SS_PORT_LS_SS_DISABLED) {
 				xhci_dbg(xhci, "Disable port %d\n", wIndex);
@@ -1178,17 +1172,17 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 				temp |= PORT_CSC | PORT_PEC | PORT_WRC |
 					PORT_OCC | PORT_RC | PORT_PLC |
 					PORT_CEC;
-				writel(temp | PORT_PE, port_array[wIndex]);
-				temp = readl(port_array[wIndex]);
+				writel(temp | PORT_PE, ports[wIndex]->addr);
+				temp = readl(ports[wIndex]->addr);
 				break;
 			}
 
 			/* Put link in RxDetect (enable port) */
 			if (link_state == USB_SS_PORT_LS_RX_DETECT) {
 				xhci_dbg(xhci, "Enable port %d\n", wIndex);
-				xhci_set_link_state(xhci, port_array, wIndex,
-						link_state);
-				temp = readl(port_array[wIndex]);
+				xhci_set_link_state(xhci, ports[wIndex],
+							link_state);
+				temp = readl(ports[wIndex]->addr);
 				break;
 			}
 
@@ -1219,9 +1213,10 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 
 				xhci_dbg(xhci, "Enable compliance mode transition for port %d\n",
 						wIndex);
-				xhci_set_link_state(xhci, port_array, wIndex,
+				xhci_set_link_state(xhci, ports[wIndex],
 						link_state);
-				temp = readl(port_array[wIndex]);
+
+				temp = readl(ports[wIndex]->addr);
 				break;
 			}
 			/* Port must be enabled */
@@ -1248,14 +1243,13 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 				}
 			}
 
-			xhci_set_link_state(xhci, port_array, wIndex,
-						link_state);
+			xhci_set_link_state(xhci, ports[wIndex], link_state);
 
 			spin_unlock_irqrestore(&xhci->lock, flags);
 			msleep(20); /* wait device to enter */
 			spin_lock_irqsave(&xhci->lock, flags);
 
-			temp = readl(port_array[wIndex]);
+			temp = readl(ports[wIndex]->addr);
 			if (link_state == USB_SS_PORT_LS_U3)
 				bus_state->suspended_ports |= 1 << wIndex;
 			break;
@@ -1270,40 +1264,39 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			break;
 		case USB_PORT_FEAT_RESET:
 			temp = (temp | PORT_RESET);
-			writel(temp, port_array[wIndex]);
+			writel(temp, ports[wIndex]->addr);
 
-			temp = readl(port_array[wIndex]);
+			temp = readl(ports[wIndex]->addr);
 			xhci_dbg(xhci, "set port reset, actual port %d status  = 0x%x\n", wIndex, temp);
 			break;
 		case USB_PORT_FEAT_REMOTE_WAKE_MASK:
-			xhci_set_remote_wake_mask(xhci, port_array,
-					wIndex, wake_mask);
-			temp = readl(port_array[wIndex]);
+			xhci_set_remote_wake_mask(xhci, ports[wIndex],
+						  wake_mask);
+			temp = readl(ports[wIndex]->addr);
 			xhci_dbg(xhci, "set port remote wake mask, "
 					"actual port %d status  = 0x%x\n",
 					wIndex, temp);
 			break;
 		case USB_PORT_FEAT_BH_PORT_RESET:
 			temp |= PORT_WR;
-			writel(temp, port_array[wIndex]);
-
-			temp = readl(port_array[wIndex]);
+			writel(temp, ports[wIndex]->addr);
+			temp = readl(ports[wIndex]->addr);
 			break;
 		case USB_PORT_FEAT_U1_TIMEOUT:
 			if (hcd->speed < HCD_USB3)
 				goto error;
-			temp = readl(port_array[wIndex] + PORTPMSC);
+			temp = readl(ports[wIndex]->addr + PORTPMSC);
 			temp &= ~PORT_U1_TIMEOUT_MASK;
 			temp |= PORT_U1_TIMEOUT(timeout);
-			writel(temp, port_array[wIndex] + PORTPMSC);
+			writel(temp, ports[wIndex]->addr + PORTPMSC);
 			break;
 		case USB_PORT_FEAT_U2_TIMEOUT:
 			if (hcd->speed < HCD_USB3)
 				goto error;
-			temp = readl(port_array[wIndex] + PORTPMSC);
+			temp = readl(ports[wIndex]->addr + PORTPMSC);
 			temp &= ~PORT_U2_TIMEOUT_MASK;
 			temp |= PORT_U2_TIMEOUT(timeout);
-			writel(temp, port_array[wIndex] + PORTPMSC);
+			writel(temp, ports[wIndex]->addr + PORTPMSC);
 			break;
 		case USB_PORT_FEAT_TEST:
 			/* 4.19.6 Port Test Modes (USB2 Test Mode) */
@@ -1318,13 +1311,13 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			goto error;
 		}
 		/* unblock any posted writes */
-		temp = readl(port_array[wIndex]);
+		temp = readl(ports[wIndex]->addr);
 		break;
 	case ClearPortFeature:
 		if (!wIndex || wIndex > max_ports)
 			goto error;
 		wIndex--;
-		temp = readl(port_array[wIndex]);
+		temp = readl(ports[wIndex]->addr);
 		if (temp == ~(u32)0) {
 			xhci_hc_died(xhci);
 			retval = -ENODEV;
@@ -1334,7 +1327,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		temp = xhci_port_state_to_neutral(temp);
 		switch (wValue) {
 		case USB_PORT_FEAT_SUSPEND:
-			temp = readl(port_array[wIndex]);
+			temp = readl(ports[wIndex]->addr);
 			xhci_dbg(xhci, "clear USB_PORT_FEAT_SUSPEND\n");
 			xhci_dbg(xhci, "PORTSC %04x\n", temp);
 			if (temp & PORT_RESET)
@@ -1344,12 +1337,12 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 					goto error;
 
 				set_bit(wIndex, &bus_state->resuming_ports);
-				xhci_set_link_state(xhci, port_array, wIndex,
-							XDEV_RESUME);
+				xhci_set_link_state(xhci, ports[wIndex],
+						    XDEV_RESUME);
 				spin_unlock_irqrestore(&xhci->lock, flags);
 				msleep(USB_RESUME_TIMEOUT);
 				spin_lock_irqsave(&xhci->lock, flags);
-				xhci_set_link_state(xhci, port_array, wIndex,
+				xhci_set_link_state(xhci, ports[wIndex],
 							XDEV_U0);
 				clear_bit(wIndex, &bus_state->resuming_ports);
 			}
@@ -1374,11 +1367,11 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		case USB_PORT_FEAT_C_PORT_LINK_STATE:
 		case USB_PORT_FEAT_C_PORT_CONFIG_ERROR:
 			xhci_clear_port_change_bit(xhci, wValue, wIndex,
-					port_array[wIndex], temp);
+					ports[wIndex]->addr, temp);
 			break;
 		case USB_PORT_FEAT_ENABLE:
 			xhci_disable_port(hcd, xhci, wIndex,
-					port_array[wIndex], temp);
+					ports[wIndex]->addr, temp);
 			break;
 		case USB_PORT_FEAT_POWER:
 			xhci_set_port_power(xhci, hcd, wIndex, false, &flags);
@@ -1415,11 +1408,14 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 	int i, retval;
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	int max_ports;
-	__le32 __iomem **port_array;
 	struct xhci_bus_state *bus_state;
 	bool reset_change = false;
+	struct xhci_hub *rhub;
+	struct xhci_port **ports;
 
-	max_ports = xhci_get_ports(hcd, &port_array);
+	rhub = xhci_get_rhub(hcd);
+	ports = rhub->ports;
+	max_ports = rhub->num_ports;
 	bus_state = &xhci->bus_state[hcd_index(hcd)];
 
 	/* Initial status is no changes */
@@ -1437,7 +1433,7 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 	spin_lock_irqsave(&xhci->lock, flags);
 	/* For each port, did anything change?  If so, set that bit in buf. */
 	for (i = 0; i < max_ports; i++) {
-		temp = readl(port_array[i]);
+		temp = readl(ports[i]->addr);
 		if (temp == ~(u32)0) {
 			xhci_hc_died(xhci);
 			retval = -ENODEV;
@@ -1469,11 +1465,14 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	int max_ports, port_index;
-	__le32 __iomem **port_array;
 	struct xhci_bus_state *bus_state;
 	unsigned long flags;
+	struct xhci_hub *rhub;
+	struct xhci_port **ports;
 
-	max_ports = xhci_get_ports(hcd, &port_array);
+	rhub = xhci_get_rhub(hcd);
+	ports = rhub->ports;
+	max_ports = rhub->num_ports;
 	bus_state = &xhci->bus_state[hcd_index(hcd)];
 
 	spin_lock_irqsave(&xhci->lock, flags);
@@ -1494,7 +1493,7 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 		u32 t1, t2;
 		int slot_id;
 
-		t1 = readl(port_array[port_index]);
+		t1 = readl(ports[port_index]->addr);
 		t2 = xhci_port_state_to_neutral(t1);
 
 		if ((t1 & PORT_PE) && !(t1 & PORT_PLS_MASK)) {
@@ -1534,7 +1533,7 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 
 		t1 = xhci_port_state_to_neutral(t1);
 		if (t1 != t2)
-			writel(t2, port_array[port_index]);
+			writel(t2, ports[port_index]->addr);
 	}
 	hcd->state = HC_STATE_SUSPENDED;
 	bus_state->next_statechange = jiffies + msecs_to_jiffies(10);
@@ -1547,12 +1546,11 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
  * warm reset a USB3 device stuck in polling or compliance mode after resume.
  * See Intel 100/c230 series PCH specification update Doc #332692-006 Errata #8
  */
-static bool xhci_port_missing_cas_quirk(int port_index,
-					     __le32 __iomem **port_array)
+static bool xhci_port_missing_cas_quirk(struct xhci_port *port)
 {
 	u32 portsc;
 
-	portsc = readl(port_array[port_index]);
+	portsc = readl(port->addr);
 
 	/* if any of these are set we are not stuck */
 	if (portsc & (PORT_CONNECT | PORT_CAS))
@@ -1565,9 +1563,9 @@ static bool xhci_port_missing_cas_quirk(int port_index,
 	/* clear wakeup/change bits, and do a warm port reset */
 	portsc &= ~(PORT_RWC_BITS | PORT_CEC | PORT_WAKE_BITS);
 	portsc |= PORT_WR;
-	writel(portsc, port_array[port_index]);
+	writel(portsc, port->addr);
 	/* flush write */
-	readl(port_array[port_index]);
+	readl(port->addr);
 	return true;
 }
 
@@ -1575,15 +1573,18 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	struct xhci_bus_state *bus_state;
-	__le32 __iomem **port_array;
 	unsigned long flags;
 	int max_ports, port_index;
 	int slot_id;
 	int sret;
 	u32 next_state;
 	u32 temp, portsc;
+	struct xhci_hub *rhub;
+	struct xhci_port **ports;
 
-	max_ports = xhci_get_ports(hcd, &port_array);
+	rhub = xhci_get_rhub(hcd);
+	ports = rhub->ports;
+	max_ports = rhub->num_ports;
 	bus_state = &xhci->bus_state[hcd_index(hcd)];
 
 	if (time_before(jiffies, bus_state->next_statechange))
@@ -1608,12 +1609,12 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 
 	port_index = max_ports;
 	while (port_index--) {
-		portsc = readl(port_array[port_index]);
+		portsc = readl(ports[port_index]->addr);
 
 		/* warm reset CAS limited ports stuck in polling/compliance */
 		if ((xhci->quirks & XHCI_MISSING_CAS) &&
 		    (hcd->speed >= HCD_USB3) &&
-		    xhci_port_missing_cas_quirk(port_index, port_array)) {
+		    xhci_port_missing_cas_quirk(ports[port_index])) {
 			xhci_dbg(xhci, "reset stuck port %d\n", port_index);
 			clear_bit(port_index, &bus_state->bus_suspended);
 			continue;
@@ -1637,7 +1638,7 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 			}
 		/* disable wake for all ports, write new link state if needed */
 		portsc &= ~(PORT_RWC_BITS | PORT_CEC | PORT_WAKE_BITS);
-		writel(portsc, port_array[port_index]);
+		writel(portsc, ports[port_index]->addr);
 	}
 
 	/* USB2 specific resume signaling delay and U0 link state transition */
@@ -1650,23 +1651,22 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 		for_each_set_bit(port_index, &bus_state->bus_suspended,
 				 BITS_PER_LONG) {
 			/* Clear PLC to poll it later for U0 transition */
-			xhci_test_and_clear_bit(xhci, port_array, port_index,
+			xhci_test_and_clear_bit(xhci, ports[port_index],
 						PORT_PLC);
-			xhci_set_link_state(xhci, port_array, port_index,
-					    XDEV_U0);
+			xhci_set_link_state(xhci, ports[port_index], XDEV_U0);
 		}
 	}
 
 	/* poll for U0 link state complete, both USB2 and USB3 */
 	for_each_set_bit(port_index, &bus_state->bus_suspended, BITS_PER_LONG) {
-		sret = xhci_handshake(port_array[port_index], PORT_PLC,
+		sret = xhci_handshake(ports[port_index]->addr, PORT_PLC,
 				      PORT_PLC, 10 * 1000);
 		if (sret) {
 			xhci_warn(xhci, "port %d resume PLC timeout\n",
 				  port_index);
 			continue;
 		}
-		xhci_test_and_clear_bit(xhci, port_array, port_index, PORT_PLC);
+		xhci_test_and_clear_bit(xhci, ports[port_index], PORT_PLC);
 		slot_id = xhci_find_slot_id_by_port(hcd, xhci, port_index + 1);
 		if (slot_id)
 			xhci_ring_device(xhci, slot_id);
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index e5ace8995b3b..4fe74711938e 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -33,8 +33,9 @@ static struct xhci_segment *xhci_segment_alloc(struct xhci_hcd *xhci,
 	struct xhci_segment *seg;
 	dma_addr_t	dma;
 	int		i;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 
-	seg = kzalloc(sizeof *seg, flags);
+	seg = kzalloc_node(sizeof(*seg), flags, dev_to_node(dev));
 	if (!seg)
 		return NULL;
 
@@ -45,7 +46,8 @@ static struct xhci_segment *xhci_segment_alloc(struct xhci_hcd *xhci,
 	}
 
 	if (max_packet) {
-		seg->bounce_buf = kzalloc(max_packet, flags);
+		seg->bounce_buf = kzalloc_node(max_packet, flags,
+					dev_to_node(dev));
 		if (!seg->bounce_buf) {
 			dma_pool_free(xhci->segment_pool, seg->trbs, dma);
 			kfree(seg);
@@ -363,8 +365,9 @@ struct xhci_ring *xhci_ring_alloc(struct xhci_hcd *xhci,
 {
 	struct xhci_ring	*ring;
 	int ret;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 
-	ring = kzalloc(sizeof *(ring), flags);
+	ring = kzalloc_node(sizeof(*ring), flags, dev_to_node(dev));
 	if (!ring)
 		return NULL;
 
@@ -458,11 +461,12 @@ struct xhci_container_ctx *xhci_alloc_container_ctx(struct xhci_hcd *xhci,
 						    int type, gfp_t flags)
 {
 	struct xhci_container_ctx *ctx;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 
 	if ((type != XHCI_CTX_TYPE_DEVICE) && (type != XHCI_CTX_TYPE_INPUT))
 		return NULL;
 
-	ctx = kzalloc(sizeof(*ctx), flags);
+	ctx = kzalloc_node(sizeof(*ctx), flags, dev_to_node(dev));
 	if (!ctx)
 		return NULL;
 
@@ -615,6 +619,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 	struct xhci_ring *cur_ring;
 	u64 addr;
 	int ret;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 
 	xhci_dbg(xhci, "Allocating %u streams and %u "
 			"stream context array entries.\n",
@@ -625,7 +630,8 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 	}
 	xhci->cmd_ring_reserved_trbs++;
 
-	stream_info = kzalloc(sizeof(struct xhci_stream_info), mem_flags);
+	stream_info = kzalloc_node(sizeof(*stream_info), mem_flags,
+			dev_to_node(dev));
 	if (!stream_info)
 		goto cleanup_trbs;
 
@@ -633,9 +639,9 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
 	stream_info->num_stream_ctxs = num_stream_ctxs;
 
 	/* Initialize the array of virtual pointers to stream rings. */
-	stream_info->stream_rings = kzalloc(
-			sizeof(struct xhci_ring *)*num_streams,
-			mem_flags);
+	stream_info->stream_rings = kcalloc_node(
+			num_streams, sizeof(struct xhci_ring *), mem_flags,
+			dev_to_node(dev));
 	if (!stream_info->stream_rings)
 		goto cleanup_info;
 
@@ -831,6 +837,7 @@ int xhci_alloc_tt_info(struct xhci_hcd *xhci,
 	struct xhci_tt_bw_info		*tt_info;
 	unsigned int			num_ports;
 	int				i, j;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 
 	if (!tt->multi)
 		num_ports = 1;
@@ -840,7 +847,8 @@ int xhci_alloc_tt_info(struct xhci_hcd *xhci,
 	for (i = 0; i < num_ports; i++, tt_info++) {
 		struct xhci_interval_bw_table *bw_table;
 
-		tt_info = kzalloc(sizeof(*tt_info), mem_flags);
+		tt_info = kzalloc_node(sizeof(*tt_info), mem_flags,
+				dev_to_node(dev));
 		if (!tt_info)
 			goto free_tts;
 		INIT_LIST_HEAD(&tt_info->tt_list);
@@ -1054,8 +1062,7 @@ void xhci_copy_ep0_dequeue_into_input_ctx(struct xhci_hcd *xhci,
 
 /*
  * The xHCI roothub may have ports of differing speeds in any order in the port
- * status registers.  xhci->port_array provides an array of the port speed for
- * each offset into the port status registers.
+ * status registers.
  *
  * The xHCI hardware wants to know the roothub port number that the USB device
  * is attached to (or the roothub port its ancestor hub is attached to).  All we
@@ -1642,7 +1649,8 @@ static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags)
 	if (!num_sp)
 		return 0;
 
-	xhci->scratchpad = kzalloc(sizeof(*xhci->scratchpad), flags);
+	xhci->scratchpad = kzalloc_node(sizeof(*xhci->scratchpad), flags,
+				dev_to_node(dev));
 	if (!xhci->scratchpad)
 		goto fail_sp;
 
@@ -1652,7 +1660,8 @@ static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags)
 	if (!xhci->scratchpad->sp_array)
 		goto fail_sp2;
 
-	xhci->scratchpad->sp_buffers = kzalloc(sizeof(void *) * num_sp, flags);
+	xhci->scratchpad->sp_buffers = kcalloc_node(num_sp, sizeof(void *),
+					flags, dev_to_node(dev));
 	if (!xhci->scratchpad->sp_buffers)
 		goto fail_sp3;
 
@@ -1720,14 +1729,16 @@ struct xhci_command *xhci_alloc_command(struct xhci_hcd *xhci,
 		bool allocate_completion, gfp_t mem_flags)
 {
 	struct xhci_command *command;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 
-	command = kzalloc(sizeof(*command), mem_flags);
+	command = kzalloc_node(sizeof(*command), mem_flags, dev_to_node(dev));
 	if (!command)
 		return NULL;
 
 	if (allocate_completion) {
 		command->completion =
-			kzalloc(sizeof(struct completion), mem_flags);
+			kzalloc_node(sizeof(struct completion), mem_flags,
+				dev_to_node(dev));
 		if (!command->completion) {
 			kfree(command);
 			return NULL;
@@ -1890,18 +1901,18 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 
 no_bw:
 	xhci->cmd_ring_reserved_trbs = 0;
-	xhci->num_usb2_ports = 0;
-	xhci->num_usb3_ports = 0;
+	xhci->usb2_rhub.num_ports = 0;
+	xhci->usb3_rhub.num_ports = 0;
 	xhci->num_active_eps = 0;
-	kfree(xhci->usb2_ports);
-	kfree(xhci->usb3_ports);
-	kfree(xhci->port_array);
+	kfree(xhci->usb2_rhub.ports);
+	kfree(xhci->usb3_rhub.ports);
+	kfree(xhci->hw_ports);
 	kfree(xhci->rh_bw);
 	kfree(xhci->ext_caps);
 
-	xhci->usb2_ports = NULL;
-	xhci->usb3_ports = NULL;
-	xhci->port_array = NULL;
+	xhci->usb2_rhub.ports = NULL;
+	xhci->usb3_rhub.ports = NULL;
+	xhci->hw_ports = NULL;
 	xhci->rh_bw = NULL;
 	xhci->ext_caps = NULL;
 
@@ -2100,6 +2111,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
 	int i;
 	u8 major_revision, minor_revision;
 	struct xhci_hub *rhub;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 
 	temp = readl(addr);
 	major_revision = XHCI_EXT_PORT_MAJOR(temp);
@@ -2136,8 +2148,8 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
 
 	rhub->psi_count = XHCI_EXT_PORT_PSIC(temp);
 	if (rhub->psi_count) {
-		rhub->psi = kcalloc(rhub->psi_count, sizeof(*rhub->psi),
-				    GFP_KERNEL);
+		rhub->psi = kcalloc_node(rhub->psi_count, sizeof(*rhub->psi),
+				    GFP_KERNEL, dev_to_node(dev));
 		if (!rhub->psi)
 			rhub->psi_count = 0;
 
@@ -2186,36 +2198,53 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
 
 	port_offset--;
 	for (i = port_offset; i < (port_offset + port_count); i++) {
+		struct xhci_port *hw_port = &xhci->hw_ports[i];
 		/* Duplicate entry.  Ignore the port if the revisions differ. */
-		if (xhci->port_array[i] != 0) {
+		if (hw_port->rhub) {
 			xhci_warn(xhci, "Duplicate port entry, Ext Cap %p,"
 					" port %u\n", addr, i);
 			xhci_warn(xhci, "Port was marked as USB %u, "
 					"duplicated as USB %u\n",
-					xhci->port_array[i], major_revision);
+					hw_port->rhub->maj_rev, major_revision);
 			/* Only adjust the roothub port counts if we haven't
 			 * found a similar duplicate.
 			 */
-			if (xhci->port_array[i] != major_revision &&
-				xhci->port_array[i] != DUPLICATE_ENTRY) {
-				if (xhci->port_array[i] == 0x03)
-					xhci->num_usb3_ports--;
-				else
-					xhci->num_usb2_ports--;
-				xhci->port_array[i] = DUPLICATE_ENTRY;
+			if (hw_port->rhub != rhub &&
+				 hw_port->hcd_portnum != DUPLICATE_ENTRY) {
+				hw_port->rhub->num_ports--;
+				hw_port->hcd_portnum = DUPLICATE_ENTRY;
 			}
-			/* FIXME: Should we disable the port? */
 			continue;
 		}
-		xhci->port_array[i] = major_revision;
-		if (major_revision == 0x03)
-			xhci->num_usb3_ports++;
-		else
-			xhci->num_usb2_ports++;
+		hw_port->rhub = rhub;
+		rhub->num_ports++;
 	}
 	/* FIXME: Should we disable ports not in the Extended Capabilities? */
 }
 
+static void xhci_create_rhub_port_array(struct xhci_hcd *xhci,
+					struct xhci_hub *rhub, gfp_t flags)
+{
+	int port_index = 0;
+	int i;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
+
+	if (!rhub->num_ports)
+		return;
+	rhub->ports = kcalloc_node(rhub->num_ports, sizeof(rhub->ports), flags,
+			dev_to_node(dev));
+	for (i = 0; i < HCS_MAX_PORTS(xhci->hcs_params1); i++) {
+		if (xhci->hw_ports[i].rhub != rhub ||
+		    xhci->hw_ports[i].hcd_portnum == DUPLICATE_ENTRY)
+			continue;
+		xhci->hw_ports[i].hcd_portnum = port_index;
+		rhub->ports[port_index] = &xhci->hw_ports[i];
+		port_index++;
+		if (port_index == rhub->num_ports)
+			break;
+	}
+}
+
 /*
  * Scan the Extended Capabilities for the "Supported Protocol Capabilities" that
  * specify what speeds each port is supposed to be.  We can't count on the port
@@ -2228,16 +2257,25 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
 	void __iomem *base;
 	u32 offset;
 	unsigned int num_ports;
-	int i, j, port_index;
+	int i, j;
 	int cap_count = 0;
 	u32 cap_start;
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
 
 	num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
-	xhci->port_array = kzalloc(sizeof(*xhci->port_array)*num_ports, flags);
-	if (!xhci->port_array)
+	xhci->hw_ports = kcalloc_node(num_ports, sizeof(*xhci->hw_ports),
+				flags, dev_to_node(dev));
+	if (!xhci->hw_ports)
 		return -ENOMEM;
 
-	xhci->rh_bw = kzalloc(sizeof(*xhci->rh_bw)*num_ports, flags);
+	for (i = 0; i < num_ports; i++) {
+		xhci->hw_ports[i].addr = &xhci->op_regs->port_status_base +
+			NUM_PORT_REGS * i;
+		xhci->hw_ports[i].hw_portnum = i;
+	}
+
+	xhci->rh_bw = kzalloc_node(sizeof(*xhci->rh_bw)*num_ports, flags,
+			dev_to_node(dev));
 	if (!xhci->rh_bw)
 		return -ENOMEM;
 	for (i = 0; i < num_ports; i++) {
@@ -2264,7 +2302,8 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
 						      XHCI_EXT_CAPS_PROTOCOL);
 	}
 
-	xhci->ext_caps = kzalloc(sizeof(*xhci->ext_caps) * cap_count, flags);
+	xhci->ext_caps = kcalloc_node(cap_count, sizeof(*xhci->ext_caps),
+				flags, dev_to_node(dev));
 	if (!xhci->ext_caps)
 		return -ENOMEM;
 
@@ -2272,86 +2311,44 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
 
 	while (offset) {
 		xhci_add_in_port(xhci, num_ports, base + offset, cap_count);
-		if (xhci->num_usb2_ports + xhci->num_usb3_ports == num_ports)
+		if (xhci->usb2_rhub.num_ports + xhci->usb3_rhub.num_ports ==
+		    num_ports)
 			break;
 		offset = xhci_find_next_ext_cap(base, offset,
 						XHCI_EXT_CAPS_PROTOCOL);
 	}
-
-	if (xhci->num_usb2_ports == 0 && xhci->num_usb3_ports == 0) {
+	if (xhci->usb2_rhub.num_ports == 0 && xhci->usb3_rhub.num_ports == 0) {
 		xhci_warn(xhci, "No ports on the roothubs?\n");
 		return -ENODEV;
 	}
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-			"Found %u USB 2.0 ports and %u USB 3.0 ports.",
-			xhci->num_usb2_ports, xhci->num_usb3_ports);
+		       "Found %u USB 2.0 ports and %u USB 3.0 ports.",
+		       xhci->usb2_rhub.num_ports, xhci->usb3_rhub.num_ports);
 
 	/* Place limits on the number of roothub ports so that the hub
 	 * descriptors aren't longer than the USB core will allocate.
 	 */
-	if (xhci->num_usb3_ports > USB_SS_MAXPORTS) {
+	if (xhci->usb3_rhub.num_ports > USB_SS_MAXPORTS) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 				"Limiting USB 3.0 roothub ports to %u.",
 				USB_SS_MAXPORTS);
-		xhci->num_usb3_ports = USB_SS_MAXPORTS;
+		xhci->usb3_rhub.num_ports = USB_SS_MAXPORTS;
 	}
-	if (xhci->num_usb2_ports > USB_MAXCHILDREN) {
+	if (xhci->usb2_rhub.num_ports > USB_MAXCHILDREN) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 				"Limiting USB 2.0 roothub ports to %u.",
 				USB_MAXCHILDREN);
-		xhci->num_usb2_ports = USB_MAXCHILDREN;
+		xhci->usb2_rhub.num_ports = USB_MAXCHILDREN;
 	}
 
 	/*
 	 * Note we could have all USB 3.0 ports, or all USB 2.0 ports.
 	 * Not sure how the USB core will handle a hub with no ports...
 	 */
-	if (xhci->num_usb2_ports) {
-		xhci->usb2_ports = kmalloc(sizeof(*xhci->usb2_ports)*
-				xhci->num_usb2_ports, flags);
-		if (!xhci->usb2_ports)
-			return -ENOMEM;
-
-		port_index = 0;
-		for (i = 0; i < num_ports; i++) {
-			if (xhci->port_array[i] == 0x03 ||
-					xhci->port_array[i] == 0 ||
-					xhci->port_array[i] == DUPLICATE_ENTRY)
-				continue;
 
-			xhci->usb2_ports[port_index] =
-				&xhci->op_regs->port_status_base +
-				NUM_PORT_REGS*i;
-			xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-					"USB 2.0 port at index %u, "
-					"addr = %p", i,
-					xhci->usb2_ports[port_index]);
-			port_index++;
-			if (port_index == xhci->num_usb2_ports)
-				break;
-		}
-	}
-	if (xhci->num_usb3_ports) {
-		xhci->usb3_ports = kmalloc(sizeof(*xhci->usb3_ports)*
-				xhci->num_usb3_ports, flags);
-		if (!xhci->usb3_ports)
-			return -ENOMEM;
+	xhci_create_rhub_port_array(xhci, &xhci->usb2_rhub, flags);
+	xhci_create_rhub_port_array(xhci, &xhci->usb3_rhub, flags);
 
-		port_index = 0;
-		for (i = 0; i < num_ports; i++)
-			if (xhci->port_array[i] == 0x03) {
-				xhci->usb3_ports[port_index] =
-					&xhci->op_regs->port_status_base +
-					NUM_PORT_REGS*i;
-				xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-						"USB 3.0 port at index %u, "
-						"addr = %p", i,
-						xhci->usb3_ports[port_index]);
-				port_index++;
-				if (port_index == xhci->num_usb3_ports)
-					break;
-			}
-	}
 	return 0;
 }
 
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index eea7360a18fc..fa33d6e5b1cb 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -58,7 +58,7 @@ static int get_bw_index(struct xhci_hcd *xhci, struct usb_device *udev,
 			bw_index = (virt_dev->real_port - 1) * 2 + 1;
 	} else {
 		/* add one more for each SS port */
-		bw_index = virt_dev->real_port + xhci->num_usb3_ports - 1;
+		bw_index = virt_dev->real_port + xhci->usb3_rhub.num_ports - 1;
 	}
 
 	return bw_index;
@@ -284,7 +284,7 @@ int xhci_mtk_sch_init(struct xhci_hcd_mtk *mtk)
 	int i;
 
 	/* ss IN and OUT are separated */
-	num_usb_bus = xhci->num_usb3_ports * 2 + xhci->num_usb2_ports;
+	num_usb_bus = xhci->usb3_rhub.num_ports * 2 + xhci->usb2_rhub.num_ports;
 
 	sch_array = kcalloc(num_usb_bus, sizeof(*sch_array), GFP_KERNEL);
 	if (sch_array == NULL)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index f17b7eab66cf..6372edf339d9 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -126,7 +126,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
 		xhci->quirks |= XHCI_AMD_PLL_FIX;
 
-	if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x43bb)
+	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+		(pdev->device == 0x15e0 ||
+		 pdev->device == 0x15e1 ||
+		 pdev->device == 0x43bb))
 		xhci->quirks |= XHCI_SUSPEND_DELAY;
 
 	if (pdev->vendor == PCI_VENDOR_ID_AMD)
@@ -193,11 +196,15 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
-			pdev->device == 0x0014)
+	    pdev->device == 0x0014) {
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+		xhci->quirks |= XHCI_ZERO_64B_REGS;
+	}
 	if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
-			pdev->device == 0x0015)
+	    pdev->device == 0x0015) {
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
+		xhci->quirks |= XHCI_ZERO_64B_REGS;
+	}
 	if (pdev->vendor == PCI_VENDOR_ID_VIA)
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
 
@@ -281,13 +288,6 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	driver = (struct hc_driver *)id->driver_data;
 
-	/* For some HW implementation, a XHCI reset is just not enough... */
-	if (usb_xhci_needs_pci_reset(dev)) {
-		dev_info(&dev->dev, "Resetting\n");
-		if (pci_reset_function_locked(dev))
-			dev_warn(&dev->dev, "Reset failed");
-	}
-
 	/* Prevent runtime suspending between USB-2 and USB-3 initialization */
 	pm_runtime_get_noresume(&dev->dev);
 
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index df327dcc2bac..c1b22fc64e38 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -157,6 +157,7 @@ static int xhci_plat_probe(struct platform_device *pdev)
 	struct resource         *res;
 	struct usb_hcd		*hcd;
 	struct clk              *clk;
+	struct clk              *reg_clk;
 	int			ret;
 	int			irq;
 
@@ -226,17 +227,27 @@ static int xhci_plat_probe(struct platform_device *pdev)
 	hcd->rsrc_len = resource_size(res);
 
 	/*
-	 * Not all platforms have a clk so it is not an error if the
-	 * clock does not exists.
+	 * Not all platforms have clks so it is not an error if the
+	 * clock do not exist.
 	 */
+	reg_clk = devm_clk_get(&pdev->dev, "reg");
+	if (!IS_ERR(reg_clk)) {
+		ret = clk_prepare_enable(reg_clk);
+		if (ret)
+			goto put_hcd;
+	} else if (PTR_ERR(reg_clk) == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		goto put_hcd;
+	}
+
 	clk = devm_clk_get(&pdev->dev, NULL);
 	if (!IS_ERR(clk)) {
 		ret = clk_prepare_enable(clk);
 		if (ret)
-			goto put_hcd;
+			goto disable_reg_clk;
 	} else if (PTR_ERR(clk) == -EPROBE_DEFER) {
 		ret = -EPROBE_DEFER;
-		goto put_hcd;
+		goto disable_reg_clk;
 	}
 
 	xhci = hcd_to_xhci(hcd);
@@ -252,6 +263,7 @@ static int xhci_plat_probe(struct platform_device *pdev)
 	device_wakeup_enable(hcd->self.controller);
 
 	xhci->clk = clk;
+	xhci->reg_clk = reg_clk;
 	xhci->main_hcd = hcd;
 	xhci->shared_hcd = __usb_create_hcd(driver, sysdev, &pdev->dev,
 			dev_name(&pdev->dev), hcd);
@@ -320,8 +332,10 @@ put_usb3_hcd:
 	usb_put_hcd(xhci->shared_hcd);
 
 disable_clk:
-	if (!IS_ERR(clk))
-		clk_disable_unprepare(clk);
+	clk_disable_unprepare(clk);
+
+disable_reg_clk:
+	clk_disable_unprepare(reg_clk);
 
 put_hcd:
 	usb_put_hcd(hcd);
@@ -338,6 +352,7 @@ static int xhci_plat_remove(struct platform_device *dev)
 	struct usb_hcd	*hcd = platform_get_drvdata(dev);
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	struct clk *clk = xhci->clk;
+	struct clk *reg_clk = xhci->reg_clk;
 
 	xhci->xhc_state |= XHCI_STATE_REMOVING;
 
@@ -347,8 +362,8 @@ static int xhci_plat_remove(struct platform_device *dev)
 	usb_remove_hcd(hcd);
 	usb_put_hcd(xhci->shared_hcd);
 
-	if (!IS_ERR(clk))
-		clk_disable_unprepare(clk);
+	clk_disable_unprepare(clk);
+	clk_disable_unprepare(reg_clk);
 	usb_put_hcd(hcd);
 
 	pm_runtime_set_suspended(&dev->dev);
@@ -420,7 +435,6 @@ MODULE_DEVICE_TABLE(acpi, usb_xhci_acpi_match);
 static struct platform_driver usb_xhci_driver = {
 	.probe	= xhci_plat_probe,
 	.remove	= xhci_plat_remove,
-	.shutdown	= usb_hcd_platform_shutdown,
 	.driver	= {
 		.name = "xhci-hcd",
 		.pm = &xhci_plat_pm_ops,
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 91a1a824673d..f0a99aa0ac58 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1497,44 +1497,6 @@ static void handle_vendor_event(struct xhci_hcd *xhci,
 		handle_cmd_completion(xhci, &event->event_cmd);
 }
 
-/* @port_id: the one-based port ID from the hardware (indexed from array of all
- * port registers -- USB 3.0 and USB 2.0).
- *
- * Returns a zero-based port number, which is suitable for indexing into each of
- * the split roothubs' port arrays and bus state arrays.
- * Add one to it in order to call xhci_find_slot_id_by_port.
- */
-static unsigned int find_faked_portnum_from_hw_portnum(struct usb_hcd *hcd,
-		struct xhci_hcd *xhci, u32 port_id)
-{
-	unsigned int i;
-	unsigned int num_similar_speed_ports = 0;
-
-	/* port_id from the hardware is 1-based, but port_array[], usb3_ports[],
-	 * and usb2_ports are 0-based indexes.  Count the number of similar
-	 * speed ports, up to 1 port before this port.
-	 */
-	for (i = 0; i < (port_id - 1); i++) {
-		u8 port_speed = xhci->port_array[i];
-
-		/*
-		 * Skip ports that don't have known speeds, or have duplicate
-		 * Extended Capabilities port speed entries.
-		 */
-		if (port_speed == 0 || port_speed == DUPLICATE_ENTRY)
-			continue;
-
-		/*
-		 * USB 3.0 ports are always under a USB 3.0 hub.  USB 2.0 and
-		 * 1.1 ports are under the USB 2.0 hub.  If the port speed
-		 * matches the device speed, it's a similar speed port.
-		 */
-		if ((port_speed == 0x03) == (hcd->speed >= HCD_USB3))
-			num_similar_speed_ports++;
-	}
-	return num_similar_speed_ports;
-}
-
 static void handle_device_notification(struct xhci_hcd *xhci,
 		union xhci_trb *event)
 {
@@ -1563,11 +1525,10 @@ static void handle_port_status(struct xhci_hcd *xhci,
 	u32 portsc, cmd_reg;
 	int max_ports;
 	int slot_id;
-	unsigned int faked_port_index;
-	u8 major_revision;
+	unsigned int hcd_portnum;
 	struct xhci_bus_state *bus_state;
-	__le32 __iomem **port_array;
 	bool bogus_port_status = false;
+	struct xhci_port *port;
 
 	/* Port status change events always have a successful completion code */
 	if (GET_COMP_CODE(le32_to_cpu(event->generic.field[2])) != COMP_SUCCESS)
@@ -1584,49 +1545,19 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		return;
 	}
 
-	/* Figure out which usb_hcd this port is attached to:
-	 * is it a USB 3.0 port or a USB 2.0/1.1 port?
-	 */
-	major_revision = xhci->port_array[port_id - 1];
-
-	/* Find the right roothub. */
-	hcd = xhci_to_hcd(xhci);
-	if ((major_revision == 0x03) != (hcd->speed >= HCD_USB3))
-		hcd = xhci->shared_hcd;
-
-	if (major_revision == 0) {
-		xhci_warn(xhci, "Event for port %u not in "
-				"Extended Capabilities, ignoring.\n",
-				port_id);
-		bogus_port_status = true;
-		goto cleanup;
-	}
-	if (major_revision == DUPLICATE_ENTRY) {
-		xhci_warn(xhci, "Event for port %u duplicated in"
-				"Extended Capabilities, ignoring.\n",
-				port_id);
+	port = &xhci->hw_ports[port_id - 1];
+	if (!port || !port->rhub || port->hcd_portnum == DUPLICATE_ENTRY) {
+		xhci_warn(xhci, "Event for invalid port %u\n", port_id);
 		bogus_port_status = true;
 		goto cleanup;
 	}
 
-	/*
-	 * Hardware port IDs reported by a Port Status Change Event include USB
-	 * 3.0 and USB 2.0 ports.  We want to check if the port has reported a
-	 * resume event, but we first need to translate the hardware port ID
-	 * into the index into the ports on the correct split roothub, and the
-	 * correct bus_state structure.
-	 */
+	hcd = port->rhub->hcd;
 	bus_state = &xhci->bus_state[hcd_index(hcd)];
-	if (hcd->speed >= HCD_USB3)
-		port_array = xhci->usb3_ports;
-	else
-		port_array = xhci->usb2_ports;
-	/* Find the faked port hub number */
-	faked_port_index = find_faked_portnum_from_hw_portnum(hcd, xhci,
-			port_id);
-	portsc = readl(port_array[faked_port_index]);
+	hcd_portnum = port->hcd_portnum;
+	portsc = readl(port->addr);
 
-	trace_xhci_handle_port_status(faked_port_index, portsc);
+	trace_xhci_handle_port_status(hcd_portnum, portsc);
 
 	if (hcd->state == HC_STATE_SUSPENDED) {
 		xhci_dbg(xhci, "resume root hub\n");
@@ -1634,7 +1565,7 @@ static void handle_port_status(struct xhci_hcd *xhci,
 	}
 
 	if (hcd->speed >= HCD_USB3 && (portsc & PORT_PLS_MASK) == XDEV_INACTIVE)
-		bus_state->port_remote_wakeup &= ~(1 << faked_port_index);
+		bus_state->port_remote_wakeup &= ~(1 << hcd_portnum);
 
 	if ((portsc & PORT_PLC) && (portsc & PORT_PLS_MASK) == XDEV_RESUME) {
 		xhci_dbg(xhci, "port resume event for port %d\n", port_id);
@@ -1651,29 +1582,26 @@ static void handle_port_status(struct xhci_hcd *xhci,
 			 * so we can tell the difference between the end of
 			 * device and host initiated resume.
 			 */
-			bus_state->port_remote_wakeup |= 1 << faked_port_index;
-			xhci_test_and_clear_bit(xhci, port_array,
-					faked_port_index, PORT_PLC);
-			xhci_set_link_state(xhci, port_array, faked_port_index,
-						XDEV_U0);
+			bus_state->port_remote_wakeup |= 1 << hcd_portnum;
+			xhci_test_and_clear_bit(xhci, port, PORT_PLC);
+			xhci_set_link_state(xhci, port, XDEV_U0);
 			/* Need to wait until the next link state change
 			 * indicates the device is actually in U0.
 			 */
 			bogus_port_status = true;
 			goto cleanup;
-		} else if (!test_bit(faked_port_index,
-				     &bus_state->resuming_ports)) {
+		} else if (!test_bit(hcd_portnum, &bus_state->resuming_ports)) {
 			xhci_dbg(xhci, "resume HS port %d\n", port_id);
-			bus_state->resume_done[faked_port_index] = jiffies +
+			bus_state->resume_done[hcd_portnum] = jiffies +
 				msecs_to_jiffies(USB_RESUME_TIMEOUT);
-			set_bit(faked_port_index, &bus_state->resuming_ports);
+			set_bit(hcd_portnum, &bus_state->resuming_ports);
 			/* Do the rest in GetPortStatus after resume time delay.
 			 * Avoid polling roothub status before that so that a
 			 * usb device auto-resume latency around ~40ms.
 			 */
 			set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
 			mod_timer(&hcd->rh_timer,
-				  bus_state->resume_done[faked_port_index]);
+				  bus_state->resume_done[hcd_portnum]);
 			bogus_port_status = true;
 		}
 	}
@@ -1688,17 +1616,14 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		 * so the roothub behavior is consistent with external
 		 * USB 3.0 hub behavior.
 		 */
-		slot_id = xhci_find_slot_id_by_port(hcd, xhci,
-				faked_port_index + 1);
+		slot_id = xhci_find_slot_id_by_port(hcd, xhci, hcd_portnum + 1);
 		if (slot_id && xhci->devs[slot_id])
 			xhci_ring_device(xhci, slot_id);
-		if (bus_state->port_remote_wakeup & (1 << faked_port_index)) {
-			bus_state->port_remote_wakeup &=
-				~(1 << faked_port_index);
-			xhci_test_and_clear_bit(xhci, port_array,
-					faked_port_index, PORT_PLC);
+		if (bus_state->port_remote_wakeup & (1 << hcd_portnum)) {
+			bus_state->port_remote_wakeup &= ~(1 << hcd_portnum);
+			xhci_test_and_clear_bit(xhci, port, PORT_PLC);
 			usb_wakeup_notification(hcd->self.root_hub,
-					faked_port_index + 1);
+					hcd_portnum + 1);
 			bogus_port_status = true;
 			goto cleanup;
 		}
@@ -1710,16 +1635,15 @@ static void handle_port_status(struct xhci_hcd *xhci,
 	 * out of the RExit state.
 	 */
 	if (!DEV_SUPERSPEED_ANY(portsc) &&
-			test_and_clear_bit(faked_port_index,
+			test_and_clear_bit(hcd_portnum,
 				&bus_state->rexit_ports)) {
-		complete(&bus_state->rexit_done[faked_port_index]);
+		complete(&bus_state->rexit_done[hcd_portnum]);
 		bogus_port_status = true;
 		goto cleanup;
 	}
 
 	if (hcd->speed < HCD_USB3)
-		xhci_test_and_clear_bit(xhci, port_array, faked_port_index,
-					PORT_PLC);
+		xhci_test_and_clear_bit(xhci, port, PORT_PLC);
 
 cleanup:
 	/* Update event ring dequeue pointer before dropping the lock */
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index 2c076ea80522..a8c1d073cba0 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -18,9 +18,11 @@
 #include <linux/phy/tegra/xusb.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
+#include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 #include <linux/slab.h>
+#include <soc/tegra/pmc.h>
 
 #include "xhci.h"
 
@@ -761,6 +763,49 @@ static void tegra_xusb_phy_disable(struct tegra_xusb *tegra)
 	}
 }
 
+static int tegra_xusb_runtime_suspend(struct device *dev)
+{
+	struct tegra_xusb *tegra = dev_get_drvdata(dev);
+
+	tegra_xusb_phy_disable(tegra);
+	regulator_bulk_disable(tegra->soc->num_supplies, tegra->supplies);
+	tegra_xusb_clk_disable(tegra);
+
+	return 0;
+}
+
+static int tegra_xusb_runtime_resume(struct device *dev)
+{
+	struct tegra_xusb *tegra = dev_get_drvdata(dev);
+	int err;
+
+	err = tegra_xusb_clk_enable(tegra);
+	if (err) {
+		dev_err(dev, "failed to enable clocks: %d\n", err);
+		return err;
+	}
+
+	err = regulator_bulk_enable(tegra->soc->num_supplies, tegra->supplies);
+	if (err) {
+		dev_err(dev, "failed to enable regulators: %d\n", err);
+		goto disable_clk;
+	}
+
+	err = tegra_xusb_phy_enable(tegra);
+	if (err < 0) {
+		dev_err(dev, "failed to enable PHYs: %d\n", err);
+		goto disable_regulator;
+	}
+
+	return 0;
+
+disable_regulator:
+	regulator_bulk_disable(tegra->soc->num_supplies, tegra->supplies);
+disable_clk:
+	tegra_xusb_clk_disable(tegra);
+	return err;
+}
+
 static int tegra_xusb_load_firmware(struct tegra_xusb *tegra)
 {
 	unsigned int code_tag_blocks, code_size_blocks, code_blocks;
@@ -930,20 +975,6 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 	if (IS_ERR(tegra->padctl))
 		return PTR_ERR(tegra->padctl);
 
-	tegra->host_rst = devm_reset_control_get(&pdev->dev, "xusb_host");
-	if (IS_ERR(tegra->host_rst)) {
-		err = PTR_ERR(tegra->host_rst);
-		dev_err(&pdev->dev, "failed to get xusb_host reset: %d\n", err);
-		goto put_padctl;
-	}
-
-	tegra->ss_rst = devm_reset_control_get(&pdev->dev, "xusb_ss");
-	if (IS_ERR(tegra->ss_rst)) {
-		err = PTR_ERR(tegra->ss_rst);
-		dev_err(&pdev->dev, "failed to get xusb_ss reset: %d\n", err);
-		goto put_padctl;
-	}
-
 	tegra->host_clk = devm_clk_get(&pdev->dev, "xusb_host");
 	if (IS_ERR(tegra->host_clk)) {
 		err = PTR_ERR(tegra->host_clk);
@@ -1007,11 +1038,48 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 		goto put_padctl;
 	}
 
+	if (!pdev->dev.pm_domain) {
+		tegra->host_rst = devm_reset_control_get(&pdev->dev,
+							 "xusb_host");
+		if (IS_ERR(tegra->host_rst)) {
+			err = PTR_ERR(tegra->host_rst);
+			dev_err(&pdev->dev,
+				"failed to get xusb_host reset: %d\n", err);
+			goto put_padctl;
+		}
+
+		tegra->ss_rst = devm_reset_control_get(&pdev->dev, "xusb_ss");
+		if (IS_ERR(tegra->ss_rst)) {
+			err = PTR_ERR(tegra->ss_rst);
+			dev_err(&pdev->dev, "failed to get xusb_ss reset: %d\n",
+				err);
+			goto put_padctl;
+		}
+
+		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_XUSBA,
+							tegra->ss_clk,
+							tegra->ss_rst);
+		if (err) {
+			dev_err(&pdev->dev,
+				"failed to enable XUSBA domain: %d\n", err);
+			goto put_padctl;
+		}
+
+		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_XUSBC,
+							tegra->host_clk,
+							tegra->host_rst);
+		if (err) {
+			dev_err(&pdev->dev,
+				"failed to enable XUSBC domain: %d\n", err);
+			goto disable_xusba;
+		}
+	}
+
 	tegra->supplies = devm_kcalloc(&pdev->dev, tegra->soc->num_supplies,
 				       sizeof(*tegra->supplies), GFP_KERNEL);
 	if (!tegra->supplies) {
 		err = -ENOMEM;
-		goto put_padctl;
+		goto disable_xusbc;
 	}
 
 	for (i = 0; i < tegra->soc->num_supplies; i++)
@@ -1021,7 +1089,7 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 				      tegra->supplies);
 	if (err) {
 		dev_err(&pdev->dev, "failed to get regulators: %d\n", err);
-		goto put_padctl;
+		goto disable_xusbc;
 	}
 
 	for (i = 0; i < tegra->soc->num_types; i++)
@@ -1031,7 +1099,7 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 				   sizeof(*tegra->phys), GFP_KERNEL);
 	if (!tegra->phys) {
 		err = -ENOMEM;
-		goto put_padctl;
+		goto disable_xusbc;
 	}
 
 	for (i = 0, k = 0; i < tegra->soc->num_types; i++) {
@@ -1047,29 +1115,35 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 					"failed to get PHY %s: %ld\n", prop,
 					PTR_ERR(phy));
 				err = PTR_ERR(phy);
-				goto put_padctl;
+				goto disable_xusbc;
 			}
 
 			tegra->phys[k++] = phy;
 		}
 	}
 
-	err = tegra_xusb_clk_enable(tegra);
-	if (err) {
-		dev_err(&pdev->dev, "failed to enable clocks: %d\n", err);
-		goto put_padctl;
+	tegra->hcd = usb_create_hcd(&tegra_xhci_hc_driver, &pdev->dev,
+				    dev_name(&pdev->dev));
+	if (!tegra->hcd) {
+		err = -ENOMEM;
+		goto disable_xusbc;
 	}
 
-	err = regulator_bulk_enable(tegra->soc->num_supplies, tegra->supplies);
-	if (err) {
-		dev_err(&pdev->dev, "failed to enable regulators: %d\n", err);
-		goto disable_clk;
-	}
+	/*
+	 * This must happen after usb_create_hcd(), because usb_create_hcd()
+	 * will overwrite the drvdata of the device with the hcd it creates.
+	 */
+	platform_set_drvdata(pdev, tegra);
+
+	pm_runtime_enable(&pdev->dev);
+	if (pm_runtime_enabled(&pdev->dev))
+		err = pm_runtime_get_sync(&pdev->dev);
+	else
+		err = tegra_xusb_runtime_resume(&pdev->dev);
 
-	err = tegra_xusb_phy_enable(tegra);
 	if (err < 0) {
-		dev_err(&pdev->dev, "failed to enable PHYs: %d\n", err);
-		goto disable_regulator;
+		dev_err(&pdev->dev, "failed to enable device: %d\n", err);
+		goto disable_rpm;
 	}
 
 	tegra_xusb_ipfs_config(tegra, regs);
@@ -1077,22 +1151,9 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 	err = tegra_xusb_load_firmware(tegra);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to load firmware: %d\n", err);
-		goto disable_phy;
-	}
-
-	tegra->hcd = usb_create_hcd(&tegra_xhci_hc_driver, &pdev->dev,
-				    dev_name(&pdev->dev));
-	if (!tegra->hcd) {
-		err = -ENOMEM;
-		goto disable_phy;
+		goto put_rpm;
 	}
 
-	/*
-	 * This must happen after usb_create_hcd(), because usb_create_hcd()
-	 * will overwrite the drvdata of the device with the hcd it creates.
-	 */
-	platform_set_drvdata(pdev, tegra);
-
 	tegra->hcd->regs = tegra->regs;
 	tegra->hcd->rsrc_start = regs->start;
 	tegra->hcd->rsrc_len = resource_size(regs);
@@ -1100,7 +1161,7 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 	err = usb_add_hcd(tegra->hcd, tegra->xhci_irq, IRQF_SHARED);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to add USB HCD: %d\n", err);
-		goto put_usb2;
+		goto put_rpm;
 	}
 
 	device_wakeup_enable(tegra->hcd->self.controller);
@@ -1155,14 +1216,18 @@ put_usb3:
 	usb_put_hcd(xhci->shared_hcd);
 remove_usb2:
 	usb_remove_hcd(tegra->hcd);
-put_usb2:
+put_rpm:
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		tegra_xusb_runtime_suspend(&pdev->dev);
+disable_rpm:
+	pm_runtime_disable(&pdev->dev);
 	usb_put_hcd(tegra->hcd);
-disable_phy:
-	tegra_xusb_phy_disable(tegra);
-disable_regulator:
-	regulator_bulk_disable(tegra->soc->num_supplies, tegra->supplies);
-disable_clk:
-	tegra_xusb_clk_disable(tegra);
+disable_xusbc:
+	if (!&pdev->dev.pm_domain)
+		tegra_powergate_power_off(TEGRA_POWERGATE_XUSBC);
+disable_xusba:
+	if (!&pdev->dev.pm_domain)
+		tegra_powergate_power_off(TEGRA_POWERGATE_XUSBA);
 put_padctl:
 	tegra_xusb_padctl_put(tegra->padctl);
 	return err;
@@ -1181,9 +1246,8 @@ static int tegra_xusb_remove(struct platform_device *pdev)
 	dma_free_coherent(&pdev->dev, tegra->fw.size, tegra->fw.virt,
 			  tegra->fw.phys);
 
-	tegra_xusb_phy_disable(tegra);
-	regulator_bulk_disable(tegra->soc->num_supplies, tegra->supplies);
-	tegra_xusb_clk_disable(tegra);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 
 	tegra_xusb_padctl_put(tegra->padctl);
 
@@ -1211,6 +1275,8 @@ static int tegra_xusb_resume(struct device *dev)
 #endif
 
 static const struct dev_pm_ops tegra_xusb_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_xusb_runtime_suspend,
+			   tegra_xusb_runtime_resume, NULL)
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_xusb_suspend, tegra_xusb_resume)
 };
 
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 9b27798ecce5..8c8da2d657fa 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -33,8 +33,8 @@ static int link_quirk;
 module_param(link_quirk, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(link_quirk, "Don't clear the chain bit on a link TRB");
 
-static unsigned int quirks;
-module_param(quirks, uint, S_IRUGO);
+static unsigned long long quirks;
+module_param(quirks, ullong, S_IRUGO);
 MODULE_PARM_DESC(quirks, "Bit flags for quirks to be enabled as default");
 
 /* TODO: copied from ehci-hcd.c - can this be refactored? */
@@ -209,6 +209,68 @@ int xhci_reset(struct xhci_hcd *xhci)
 	return ret;
 }
 
+static void xhci_zero_64b_regs(struct xhci_hcd *xhci)
+{
+	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
+	int err, i;
+	u64 val;
+
+	/*
+	 * Some Renesas controllers get into a weird state if they are
+	 * reset while programmed with 64bit addresses (they will preserve
+	 * the top half of the address in internal, non visible
+	 * registers). You end up with half the address coming from the
+	 * kernel, and the other half coming from the firmware. Also,
+	 * changing the programming leads to extra accesses even if the
+	 * controller is supposed to be halted. The controller ends up with
+	 * a fatal fault, and is then ripe for being properly reset.
+	 *
+	 * Special care is taken to only apply this if the device is behind
+	 * an iommu. Doing anything when there is no iommu is definitely
+	 * unsafe...
+	 */
+	if (!(xhci->quirks & XHCI_ZERO_64B_REGS) || !dev->iommu_group)
+		return;
+
+	xhci_info(xhci, "Zeroing 64bit base registers, expecting fault\n");
+
+	/* Clear HSEIE so that faults do not get signaled */
+	val = readl(&xhci->op_regs->command);
+	val &= ~CMD_HSEIE;
+	writel(val, &xhci->op_regs->command);
+
+	/* Clear HSE (aka FATAL) */
+	val = readl(&xhci->op_regs->status);
+	val |= STS_FATAL;
+	writel(val, &xhci->op_regs->status);
+
+	/* Now zero the registers, and brace for impact */
+	val = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr);
+	if (upper_32_bits(val))
+		xhci_write_64(xhci, 0, &xhci->op_regs->dcbaa_ptr);
+	val = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
+	if (upper_32_bits(val))
+		xhci_write_64(xhci, 0, &xhci->op_regs->cmd_ring);
+
+	for (i = 0; i < HCS_MAX_INTRS(xhci->hcs_params1); i++) {
+		struct xhci_intr_reg __iomem *ir;
+
+		ir = &xhci->run_regs->ir_set[i];
+		val = xhci_read_64(xhci, &ir->erst_base);
+		if (upper_32_bits(val))
+			xhci_write_64(xhci, 0, &ir->erst_base);
+		val= xhci_read_64(xhci, &ir->erst_dequeue);
+		if (upper_32_bits(val))
+			xhci_write_64(xhci, 0, &ir->erst_dequeue);
+	}
+
+	/* Wait for the fault to appear. It will be cleared on reset */
+	err = xhci_handshake(&xhci->op_regs->status,
+			     STS_FATAL, STS_FATAL,
+			     XHCI_MAX_HALT_USEC);
+	if (!err)
+		xhci_info(xhci, "Fault detected\n");
+}
 
 #ifdef CONFIG_USB_PCI
 /*
@@ -400,13 +462,15 @@ static void compliance_mode_recovery(struct timer_list *t)
 {
 	struct xhci_hcd *xhci;
 	struct usb_hcd *hcd;
+	struct xhci_hub *rhub;
 	u32 temp;
 	int i;
 
 	xhci = from_timer(xhci, t, comp_mode_recovery_timer);
+	rhub = &xhci->usb3_rhub;
 
-	for (i = 0; i < xhci->num_usb3_ports; i++) {
-		temp = readl(xhci->usb3_ports[i]);
+	for (i = 0; i < rhub->num_ports; i++) {
+		temp = readl(rhub->ports[i]->addr);
 		if ((temp & PORT_PLS_MASK) == USB_SS_PORT_LS_COMP_MOD) {
 			/*
 			 * Compliance Mode Detected. Letting USB Core
@@ -426,7 +490,7 @@ static void compliance_mode_recovery(struct timer_list *t)
 		}
 	}
 
-	if (xhci->port_status_u0 != ((1 << xhci->num_usb3_ports)-1))
+	if (xhci->port_status_u0 != ((1 << rhub->num_ports) - 1))
 		mod_timer(&xhci->comp_mode_recovery_timer,
 			jiffies + msecs_to_jiffies(COMP_MODE_RCVRY_MSECS));
 }
@@ -483,7 +547,7 @@ static bool xhci_compliance_mode_recovery_timer_quirk_check(void)
 
 static int xhci_all_ports_seen_u0(struct xhci_hcd *xhci)
 {
-	return (xhci->port_status_u0 == ((1 << xhci->num_usb3_ports)-1));
+	return (xhci->port_status_u0 == ((1 << xhci->usb3_rhub.num_ports) - 1));
 }
 
 
@@ -812,33 +876,33 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci)
 
 static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
 {
+	struct xhci_port **ports;
 	int port_index;
-	__le32 __iomem **port_array;
 	unsigned long flags;
 	u32 t1, t2;
 
 	spin_lock_irqsave(&xhci->lock, flags);
 
 	/* disable usb3 ports Wake bits */
-	port_index = xhci->num_usb3_ports;
-	port_array = xhci->usb3_ports;
+	port_index = xhci->usb3_rhub.num_ports;
+	ports = xhci->usb3_rhub.ports;
 	while (port_index--) {
-		t1 = readl(port_array[port_index]);
+		t1 = readl(ports[port_index]->addr);
 		t1 = xhci_port_state_to_neutral(t1);
 		t2 = t1 & ~PORT_WAKE_BITS;
 		if (t1 != t2)
-			writel(t2, port_array[port_index]);
+			writel(t2, ports[port_index]->addr);
 	}
 
 	/* disable usb2 ports Wake bits */
-	port_index = xhci->num_usb2_ports;
-	port_array = xhci->usb2_ports;
+	port_index = xhci->usb2_rhub.num_ports;
+	ports = xhci->usb2_rhub.ports;
 	while (port_index--) {
-		t1 = readl(port_array[port_index]);
+		t1 = readl(ports[port_index]->addr);
 		t1 = xhci_port_state_to_neutral(t1);
 		t2 = t1 & ~PORT_WAKE_BITS;
 		if (t1 != t2)
-			writel(t2, port_array[port_index]);
+			writel(t2, ports[port_index]->addr);
 	}
 
 	spin_unlock_irqrestore(&xhci->lock, flags);
@@ -1004,6 +1068,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 
 		xhci_dbg(xhci, "Stop HCD\n");
 		xhci_halt(xhci);
+		xhci_zero_64b_regs(xhci);
 		xhci_reset(xhci);
 		spin_unlock_irq(&xhci->lock);
 		xhci_cleanup_msix(xhci);
@@ -3621,6 +3686,7 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
 		del_timer_sync(&virt_dev->eps[i].stop_cmd_timer);
 	}
 	xhci_debugfs_remove_slot(xhci, udev->slot_id);
+	virt_dev->udev = NULL;
 	ret = xhci_disable_slot(xhci, udev->slot_id);
 	if (ret)
 		xhci_free_virt_device(xhci, udev->slot_id);
@@ -3975,18 +4041,10 @@ static int xhci_enable_device(struct usb_hcd *hcd, struct usb_device *udev)
  */
 int xhci_find_raw_port_number(struct usb_hcd *hcd, int port1)
 {
-	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	__le32 __iomem *base_addr = &xhci->op_regs->port_status_base;
-	__le32 __iomem *addr;
-	int raw_port;
+	struct xhci_hub *rhub;
 
-	if (hcd->speed < HCD_USB3)
-		addr = xhci->usb2_ports[port1 - 1];
-	else
-		addr = xhci->usb3_ports[port1 - 1];
-
-	raw_port = (addr - base_addr)/NUM_PORT_REGS + 1;
-	return raw_port;
+	rhub = xhci_get_rhub(hcd);
+	return rhub->ports[port1 - 1]->hw_portnum + 1;
 }
 
 /*
@@ -4119,7 +4177,7 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
 			struct usb_device *udev, int enable)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
-	__le32 __iomem	**port_array;
+	struct xhci_port **ports;
 	__le32 __iomem	*pm_addr, *hlpm_addr;
 	u32		pm_val, hlpm_val, field;
 	unsigned int	port_num;
@@ -4140,11 +4198,11 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
 
 	spin_lock_irqsave(&xhci->lock, flags);
 
-	port_array = xhci->usb2_ports;
+	ports = xhci->usb2_rhub.ports;
 	port_num = udev->portnum - 1;
-	pm_addr = port_array[port_num] + PORTPMSC;
+	pm_addr = ports[port_num]->addr + PORTPMSC;
 	pm_val = readl(pm_addr);
-	hlpm_addr = port_array[port_num] + PORTHLPMC;
+	hlpm_addr = ports[port_num]->addr + PORTHLPMC;
 	field = le32_to_cpu(udev->bos->ext_cap->bmAttributes);
 
 	xhci_dbg(xhci, "%s port %d USB2 hardware LPM\n",
@@ -4857,6 +4915,7 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks)
 
 	if (usb_hcd_is_primary_hcd(hcd)) {
 		xhci->main_hcd = hcd;
+		xhci->usb2_rhub.hcd = hcd;
 		/* Mark the first roothub as being USB 2.0.
 		 * The xHCI driver will register the USB 3.0 roothub.
 		 */
@@ -4882,6 +4941,7 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks)
 			  minor_rev,
 			  minor_rev ? "Enhanced" : "");
 
+		xhci->usb3_rhub.hcd = hcd;
 		/* xHCI private pointer was set in xhci_pci_probe for the second
 		 * registered roothub.
 		 */
@@ -4920,6 +4980,8 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks)
 	if (retval)
 		return retval;
 
+	xhci_zero_64b_regs(xhci);
+
 	xhci_dbg(xhci, "Resetting HCD\n");
 	/* Reset the internal HC memory state and registers. */
 	retval = xhci_reset(xhci);
@@ -4962,7 +5024,7 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks)
 		return retval;
 	xhci_dbg(xhci, "Called HCD init\n");
 
-	xhci_info(xhci, "hcc params 0x%08x hci version 0x%x quirks 0x%08x\n",
+	xhci_info(xhci, "hcc params 0x%08x hci version 0x%x quirks 0x%016llx\n",
 		  xhci->hcc_params, xhci->hci_version, xhci->quirks);
 
 	return 0;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 05c909b04f14..939e2f86b595 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1683,13 +1683,23 @@ static inline unsigned int hcd_index(struct usb_hcd *hcd)
 	else
 		return 1;
 }
+struct xhci_port {
+	__le32 __iomem		*addr;
+	int			hw_portnum;
+	int			hcd_portnum;
+	struct xhci_hub		*rhub;
+};
 
 struct xhci_hub {
-	u8	maj_rev;
-	u8	min_rev;
-	u32	*psi;		/* array of protocol speed ID entries */
-	u8	psi_count;
-	u8	psi_uid_count;
+	struct xhci_port	**ports;
+	unsigned int		num_ports;
+	struct usb_hcd		*hcd;
+	/* supported prococol extended capabiliy values */
+	u8			maj_rev;
+	u8			min_rev;
+	u32			*psi;	/* array of protocol speed ID entries */
+	u8			psi_count;
+	u8			psi_uid_count;
 };
 
 /* There is one xhci_hcd structure per controller */
@@ -1729,8 +1739,9 @@ struct xhci_hcd {
 	int		page_shift;
 	/* msi-x vectors */
 	int		msix_count;
-	/* optional clock */
+	/* optional clocks */
 	struct clk		*clk;
+	struct clk		*reg_clk;
 	/* data structures */
 	struct xhci_device_context_array *dcbaa;
 	struct xhci_ring	*cmd_ring;
@@ -1786,12 +1797,12 @@ struct xhci_hcd {
 #define XHCI_STATE_DYING	(1 << 0)
 #define XHCI_STATE_HALTED	(1 << 1)
 #define XHCI_STATE_REMOVING	(1 << 2)
-	unsigned int		quirks;
-#define	XHCI_LINK_TRB_QUIRK	(1 << 0)
-#define XHCI_RESET_EP_QUIRK	(1 << 1)
-#define XHCI_NEC_HOST		(1 << 2)
-#define XHCI_AMD_PLL_FIX	(1 << 3)
-#define XHCI_SPURIOUS_SUCCESS	(1 << 4)
+	unsigned long long	quirks;
+#define	XHCI_LINK_TRB_QUIRK	BIT_ULL(0)
+#define XHCI_RESET_EP_QUIRK	BIT_ULL(1)
+#define XHCI_NEC_HOST		BIT_ULL(2)
+#define XHCI_AMD_PLL_FIX	BIT_ULL(3)
+#define XHCI_SPURIOUS_SUCCESS	BIT_ULL(4)
 /*
  * Certain Intel host controllers have a limit to the number of endpoint
  * contexts they can handle.  Ideally, they would signal that they can't handle
@@ -1801,50 +1812,44 @@ struct xhci_hcd {
  * commands, reset device commands, disable slot commands, and address device
  * commands.
  */
-#define XHCI_EP_LIMIT_QUIRK	(1 << 5)
-#define XHCI_BROKEN_MSI		(1 << 6)
-#define XHCI_RESET_ON_RESUME	(1 << 7)
-#define	XHCI_SW_BW_CHECKING	(1 << 8)
-#define XHCI_AMD_0x96_HOST	(1 << 9)
-#define XHCI_TRUST_TX_LENGTH	(1 << 10)
-#define XHCI_LPM_SUPPORT	(1 << 11)
-#define XHCI_INTEL_HOST		(1 << 12)
-#define XHCI_SPURIOUS_REBOOT	(1 << 13)
-#define XHCI_COMP_MODE_QUIRK	(1 << 14)
-#define XHCI_AVOID_BEI		(1 << 15)
-#define XHCI_PLAT		(1 << 16)
-#define XHCI_SLOW_SUSPEND	(1 << 17)
-#define XHCI_SPURIOUS_WAKEUP	(1 << 18)
+#define XHCI_EP_LIMIT_QUIRK	BIT_ULL(5)
+#define XHCI_BROKEN_MSI		BIT_ULL(6)
+#define XHCI_RESET_ON_RESUME	BIT_ULL(7)
+#define	XHCI_SW_BW_CHECKING	BIT_ULL(8)
+#define XHCI_AMD_0x96_HOST	BIT_ULL(9)
+#define XHCI_TRUST_TX_LENGTH	BIT_ULL(10)
+#define XHCI_LPM_SUPPORT	BIT_ULL(11)
+#define XHCI_INTEL_HOST		BIT_ULL(12)
+#define XHCI_SPURIOUS_REBOOT	BIT_ULL(13)
+#define XHCI_COMP_MODE_QUIRK	BIT_ULL(14)
+#define XHCI_AVOID_BEI		BIT_ULL(15)
+#define XHCI_PLAT		BIT_ULL(16)
+#define XHCI_SLOW_SUSPEND	BIT_ULL(17)
+#define XHCI_SPURIOUS_WAKEUP	BIT_ULL(18)
 /* For controllers with a broken beyond repair streams implementation */
-#define XHCI_BROKEN_STREAMS	(1 << 19)
-#define XHCI_PME_STUCK_QUIRK	(1 << 20)
-#define XHCI_MTK_HOST		(1 << 21)
-#define XHCI_SSIC_PORT_UNUSED	(1 << 22)
-#define XHCI_NO_64BIT_SUPPORT	(1 << 23)
-#define XHCI_MISSING_CAS	(1 << 24)
+#define XHCI_BROKEN_STREAMS	BIT_ULL(19)
+#define XHCI_PME_STUCK_QUIRK	BIT_ULL(20)
+#define XHCI_MTK_HOST		BIT_ULL(21)
+#define XHCI_SSIC_PORT_UNUSED	BIT_ULL(22)
+#define XHCI_NO_64BIT_SUPPORT	BIT_ULL(23)
+#define XHCI_MISSING_CAS	BIT_ULL(24)
 /* For controller with a broken Port Disable implementation */
-#define XHCI_BROKEN_PORT_PED	(1 << 25)
-#define XHCI_LIMIT_ENDPOINT_INTERVAL_7	(1 << 26)
-#define XHCI_U2_DISABLE_WAKE	(1 << 27)
-#define XHCI_ASMEDIA_MODIFY_FLOWCONTROL	(1 << 28)
-#define XHCI_HW_LPM_DISABLE	(1 << 29)
-#define XHCI_SUSPEND_DELAY	(1 << 30)
-#define XHCI_INTEL_USB_ROLE_SW	(1 << 31)
+#define XHCI_BROKEN_PORT_PED	BIT_ULL(25)
+#define XHCI_LIMIT_ENDPOINT_INTERVAL_7	BIT_ULL(26)
+#define XHCI_U2_DISABLE_WAKE	BIT_ULL(27)
+#define XHCI_ASMEDIA_MODIFY_FLOWCONTROL	BIT_ULL(28)
+#define XHCI_HW_LPM_DISABLE	BIT_ULL(29)
+#define XHCI_SUSPEND_DELAY	BIT_ULL(30)
+#define XHCI_INTEL_USB_ROLE_SW	BIT_ULL(31)
+#define XHCI_ZERO_64B_REGS	BIT_ULL(32)
 
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;
 	/* There are two roothubs to keep track of bus suspend info for */
 	struct xhci_bus_state   bus_state[2];
-	/* Is each xHCI roothub port a USB 3.0, USB 2.0, or USB 1.1 port? */
-	u8			*port_array;
-	/* Array of pointers to USB 3.0 PORTSC registers */
-	__le32 __iomem		**usb3_ports;
-	unsigned int		num_usb3_ports;
-	/* Array of pointers to USB 2.0 PORTSC registers */
-	__le32 __iomem		**usb2_ports;
+	struct xhci_port	*hw_ports;
 	struct xhci_hub		usb2_rhub;
 	struct xhci_hub		usb3_rhub;
-	unsigned int		num_usb2_ports;
 	/* support xHCI 0.96 spec USB2 software LPM */
 	unsigned		sw_lpm_support:1;
 	/* support xHCI 1.0 spec USB2 hardware LPM */
@@ -2090,14 +2095,16 @@ void inc_deq(struct xhci_hcd *xhci, struct xhci_ring *ring);
 unsigned int count_trbs(u64 addr, u64 len);
 
 /* xHCI roothub code */
-void xhci_set_link_state(struct xhci_hcd *xhci, __le32 __iomem **port_array,
-				int port_id, u32 link_state);
-void xhci_test_and_clear_bit(struct xhci_hcd *xhci, __le32 __iomem **port_array,
-				int port_id, u32 port_bit);
+void xhci_set_link_state(struct xhci_hcd *xhci, struct xhci_port *port,
+				u32 link_state);
+void xhci_test_and_clear_bit(struct xhci_hcd *xhci, struct xhci_port *port,
+				u32 port_bit);
 int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex,
 		char *buf, u16 wLength);
 int xhci_hub_status_data(struct usb_hcd *hcd, char *buf);
 int xhci_find_raw_port_number(struct usb_hcd *hcd, int port1);
+struct xhci_hub *xhci_get_rhub(struct usb_hcd *hcd);
+
 void xhci_hc_died(struct xhci_hcd *xhci);
 
 #ifdef CONFIG_PM
diff --git a/drivers/usb/isp1760/isp1760-core.c b/drivers/usb/isp1760/isp1760-core.c
index 05d22589b5cc..55b94fd10331 100644
--- a/drivers/usb/isp1760/isp1760-core.c
+++ b/drivers/usb/isp1760/isp1760-core.c
@@ -31,7 +31,7 @@ static void isp1760_init_core(struct isp1760_device *isp)
 	/* Low-level chip reset */
 	if (isp->rst_gpio) {
 		gpiod_set_value_cansleep(isp->rst_gpio, 1);
-		mdelay(50);
+		msleep(50);
 		gpiod_set_value_cansleep(isp->rst_gpio, 0);
 	}
 
diff --git a/drivers/usb/isp1760/isp1760-hcd.c b/drivers/usb/isp1760/isp1760-hcd.c
index 42672d6ec525..1045521be293 100644
--- a/drivers/usb/isp1760/isp1760-hcd.c
+++ b/drivers/usb/isp1760/isp1760-hcd.c
@@ -2093,7 +2093,7 @@ static void isp1760_stop(struct usb_hcd *hcd)
 
 	isp1760_hub_control(hcd, ClearPortFeature, USB_PORT_FEAT_POWER,	1,
 			NULL, 0);
-	mdelay(20);
+	msleep(20);
 
 	spin_lock_irq(&priv->lock);
 	ehci_reset(hcd);
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index 3e65bdc2615c..f92c5df26320 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -2107,7 +2107,7 @@ static void sisusb_get_ramconfig(struct sisusb_usb_data *sisusb)
 		bw = busSDR[(tmp8 & 0x03)];
 		break;
 	case 2:
-		ramtypetext1 = "asymmeric";
+		ramtypetext1 = "asymmetric";
 		sisusb->vramsize += sisusb->vramsize/2;
 		bw = busDDRA[(tmp8 & 0x03)];
 		break;
diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c
index 2761fad66b95..34e866ad4a81 100644
--- a/drivers/usb/mon/mon_bin.c
+++ b/drivers/usb/mon/mon_bin.c
@@ -1227,7 +1227,7 @@ static void mon_bin_vma_close(struct vm_area_struct *vma)
 /*
  * Map ring pages to user space.
  */
-static int mon_bin_vma_fault(struct vm_fault *vmf)
+static vm_fault_t mon_bin_vma_fault(struct vm_fault *vmf)
 {
 	struct mon_reader_bin *rp = vmf->vma->vm_private_data;
 	unsigned long offset, chunk_idx;
diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c
index 984f7e12a6a5..bc5ecd5ff565 100644
--- a/drivers/usb/mon/mon_text.c
+++ b/drivers/usb/mon/mon_text.c
@@ -700,7 +700,6 @@ static const struct file_operations mon_fops_text_u = {
 
 int mon_text_add(struct mon_bus *mbus, const struct usb_bus *ubus)
 {
-	struct dentry *d;
 	enum { NAMESZ = 10 };
 	char name[NAMESZ];
 	int busnum = ubus? ubus->busnum: 0;
@@ -713,42 +712,32 @@ int mon_text_add(struct mon_bus *mbus, const struct usb_bus *ubus)
 		rc = snprintf(name, NAMESZ, "%dt", busnum);
 		if (rc <= 0 || rc >= NAMESZ)
 			goto err_print_t;
-		d = debugfs_create_file(name, 0600, mon_dir, mbus,
+		mbus->dent_t = debugfs_create_file(name, 0600, mon_dir, mbus,
 							     &mon_fops_text_t);
-		if (d == NULL)
-			goto err_create_t;
-		mbus->dent_t = d;
 	}
 
 	rc = snprintf(name, NAMESZ, "%du", busnum);
 	if (rc <= 0 || rc >= NAMESZ)
 		goto err_print_u;
-	d = debugfs_create_file(name, 0600, mon_dir, mbus, &mon_fops_text_u);
-	if (d == NULL)
-		goto err_create_u;
-	mbus->dent_u = d;
+	mbus->dent_u = debugfs_create_file(name, 0600, mon_dir, mbus,
+					   &mon_fops_text_u);
 
 	rc = snprintf(name, NAMESZ, "%ds", busnum);
 	if (rc <= 0 || rc >= NAMESZ)
 		goto err_print_s;
-	d = debugfs_create_file(name, 0600, mon_dir, mbus, &mon_fops_stat);
-	if (d == NULL)
-		goto err_create_s;
-	mbus->dent_s = d;
+	mbus->dent_s = debugfs_create_file(name, 0600, mon_dir, mbus,
+					   &mon_fops_stat);
 
 	return 1;
 
-err_create_s:
 err_print_s:
 	debugfs_remove(mbus->dent_u);
 	mbus->dent_u = NULL;
-err_create_u:
 err_print_u:
 	if (ubus != NULL) {
 		debugfs_remove(mbus->dent_t);
 		mbus->dent_t = NULL;
 	}
-err_create_t:
 err_print_t:
 	return 0;
 }
@@ -756,8 +745,7 @@ err_print_t:
 void mon_text_del(struct mon_bus *mbus)
 {
 	debugfs_remove(mbus->dent_u);
-	if (mbus->dent_t != NULL)
-		debugfs_remove(mbus->dent_t);
+	debugfs_remove(mbus->dent_t);
 	debugfs_remove(mbus->dent_s);
 }
 
@@ -775,18 +763,7 @@ static void mon_text_ctor(void *mem)
 
 int __init mon_text_init(void)
 {
-	struct dentry *mondir;
-
-	mondir = debugfs_create_dir("usbmon", usb_debug_root);
-	if (IS_ERR(mondir)) {
-		/* debugfs not available, but we can use usbmon without it */
-		return 0;
-	}
-	if (mondir == NULL) {
-		printk(KERN_NOTICE TAG ": unable to create usbmon directory\n");
-		return -ENOMEM;
-	}
-	mon_dir = mondir;
+	mon_dir = debugfs_create_dir("usbmon", usb_debug_root);
 	return 0;
 }
 
diff --git a/drivers/usb/mtu3/Kconfig b/drivers/usb/mtu3/Kconfig
index 25cd61947bee..40bbf1f53337 100644
--- a/drivers/usb/mtu3/Kconfig
+++ b/drivers/usb/mtu3/Kconfig
@@ -2,7 +2,7 @@
 
 config USB_MTU3
 	tristate "MediaTek USB3 Dual Role controller"
-	depends on EXTCON && (USB || USB_GADGET) && HAS_DMA
+	depends on USB || USB_GADGET
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	select USB_XHCI_MTK if USB_SUPPORT && USB_XHCI_HCD
 	help
@@ -40,6 +40,7 @@ config USB_MTU3_GADGET
 config USB_MTU3_DUAL_ROLE
 	bool "Dual Role mode"
 	depends on ((USB=y || USB=USB_MTU3) && (USB_GADGET=y || USB_GADGET=USB_MTU3))
+	depends on (EXTCON=y || EXTCON=USB_MTU3)
 	help
 	  This is the default mode of working of MTU3 controller where
 	  both host and gadget features are enabled.
diff --git a/drivers/usb/mtu3/mtu3.h b/drivers/usb/mtu3/mtu3.h
index 2cd00a24afd9..87823ac0d120 100644
--- a/drivers/usb/mtu3/mtu3.h
+++ b/drivers/usb/mtu3/mtu3.h
@@ -196,10 +196,12 @@ struct mtu3_gpd_ring {
 * @vbus: vbus 5V used by host mode
 * @edev: external connector used to detect vbus and iddig changes
 * @vbus_nb: notifier for vbus detection
-* @vbus_nb: notifier for iddig(idpin) detection
-* @extcon_reg_dwork: delay work for extcon notifier register, waiting for
-*		xHCI driver initialization, it's necessary for system bootup
-*		as device.
+* @vbus_work : work of vbus detection notifier, used to avoid sleep in
+*		notifier callback which is atomic context
+* @vbus_event : event of vbus detecion notifier
+* @id_nb : notifier for iddig(idpin) detection
+* @id_work : work of iddig detection notifier
+* @id_event : event of iddig detecion notifier
 * @is_u3_drd: whether port0 supports usb3.0 dual-role device or not
 * @manual_drd_enabled: it's true when supports dual-role device by debugfs
 *		to switch host/device modes depending on user input.
@@ -208,8 +210,11 @@ struct otg_switch_mtk {
 	struct regulator *vbus;
 	struct extcon_dev *edev;
 	struct notifier_block vbus_nb;
+	struct work_struct vbus_work;
+	unsigned long vbus_event;
 	struct notifier_block id_nb;
-	struct delayed_work extcon_reg_dwork;
+	struct work_struct id_work;
+	unsigned long id_event;
 	bool is_u3_drd;
 	bool manual_drd_enabled;
 };
diff --git a/drivers/usb/mtu3/mtu3_core.c b/drivers/usb/mtu3/mtu3_core.c
index b1b99a8f6a7a..eecfd0671362 100644
--- a/drivers/usb/mtu3/mtu3_core.c
+++ b/drivers/usb/mtu3/mtu3_core.c
@@ -176,7 +176,7 @@ static void mtu3_intr_enable(struct mtu3 *mtu)
 	mtu3_writel(mbase, U3D_LV1IESR, value);
 
 	/* Enable U2 common USB interrupts */
-	value = SUSPEND_INTR | RESUME_INTR | RESET_INTR;
+	value = SUSPEND_INTR | RESUME_INTR | RESET_INTR | LPM_RESUME_INTR;
 	mtu3_writel(mbase, U3D_COMMON_USB_INTR_ENABLE, value);
 
 	if (mtu->is_u3_ip) {
@@ -195,6 +195,16 @@ static void mtu3_intr_enable(struct mtu3 *mtu)
 	mtu3_writel(mbase, U3D_DEV_LINK_INTR_ENABLE, SSUSB_DEV_SPEED_CHG_INTR);
 }
 
+/* reset: u2 - data toggle, u3 - SeqN, flow control status etc */
+static void mtu3_ep_reset(struct mtu3_ep *mep)
+{
+	struct mtu3 *mtu = mep->mtu;
+	u32 rst_bit = EP_RST(mep->is_in, mep->epnum);
+
+	mtu3_setbits(mtu->mac_base, U3D_EP_RST, rst_bit);
+	mtu3_clrbits(mtu->mac_base, U3D_EP_RST, rst_bit);
+}
+
 /* set/clear the stall and toggle bits for non-ep0 */
 void mtu3_ep_stall_set(struct mtu3_ep *mep, bool set)
 {
@@ -220,8 +230,7 @@ void mtu3_ep_stall_set(struct mtu3_ep *mep, bool set)
 	}
 
 	if (!set) {
-		mtu3_setbits(mbase, U3D_EP_RST, EP_RST(mep->is_in, epnum));
-		mtu3_clrbits(mbase, U3D_EP_RST, EP_RST(mep->is_in, epnum));
+		mtu3_ep_reset(mep);
 		mep->flags &= ~MTU3_EP_STALL;
 	} else {
 		mep->flags |= MTU3_EP_STALL;
@@ -400,6 +409,7 @@ void mtu3_deconfig_ep(struct mtu3 *mtu, struct mtu3_ep *mep)
 		mtu3_setbits(mbase, U3D_QIECR0, QMU_RX_DONE_INT(epnum));
 	}
 
+	mtu3_ep_reset(mep);
 	ep_fifo_free(mep);
 
 	dev_dbg(mtu->dev, "%s: %s\n", __func__, mep->name);
@@ -658,8 +668,10 @@ static irqreturn_t mtu3_u3_ltssm_isr(struct mtu3 *mtu)
 	if (ltssm & (HOT_RST_INTR | WARM_RST_INTR))
 		mtu3_gadget_reset(mtu);
 
-	if (ltssm & VBUS_FALL_INTR)
+	if (ltssm & VBUS_FALL_INTR) {
 		mtu3_ss_func_set(mtu, false);
+		mtu3_gadget_reset(mtu);
+	}
 
 	if (ltssm & VBUS_RISE_INTR)
 		mtu3_ss_func_set(mtu, true);
@@ -692,6 +704,12 @@ static irqreturn_t mtu3_u2_common_isr(struct mtu3 *mtu)
 	if (u2comm & RESET_INTR)
 		mtu3_gadget_reset(mtu);
 
+	if (u2comm & LPM_RESUME_INTR) {
+		if (!(mtu3_readl(mbase, U3D_POWER_MANAGEMENT) & LPM_HRWE))
+			mtu3_setbits(mbase, U3D_USB20_MISC_CONTROL,
+				     LPM_U3_ACK_EN);
+	}
+
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/usb/mtu3/mtu3_dr.c b/drivers/usb/mtu3/mtu3_dr.c
index db7562d99b95..ac60e9c8564e 100644
--- a/drivers/usb/mtu3/mtu3_dr.c
+++ b/drivers/usb/mtu3/mtu3_dr.c
@@ -174,16 +174,40 @@ static void ssusb_set_mailbox(struct otg_switch_mtk *otg_sx,
 	}
 }
 
-static int ssusb_id_notifier(struct notifier_block *nb,
-	unsigned long event, void *ptr)
+static void ssusb_id_work(struct work_struct *work)
 {
 	struct otg_switch_mtk *otg_sx =
-		container_of(nb, struct otg_switch_mtk, id_nb);
+		container_of(work, struct otg_switch_mtk, id_work);
 
-	if (event)
+	if (otg_sx->id_event)
 		ssusb_set_mailbox(otg_sx, MTU3_ID_GROUND);
 	else
 		ssusb_set_mailbox(otg_sx, MTU3_ID_FLOAT);
+}
+
+static void ssusb_vbus_work(struct work_struct *work)
+{
+	struct otg_switch_mtk *otg_sx =
+		container_of(work, struct otg_switch_mtk, vbus_work);
+
+	if (otg_sx->vbus_event)
+		ssusb_set_mailbox(otg_sx, MTU3_VBUS_VALID);
+	else
+		ssusb_set_mailbox(otg_sx, MTU3_VBUS_OFF);
+}
+
+/*
+ * @ssusb_id_notifier is called in atomic context, but @ssusb_set_mailbox
+ * may sleep, so use work queue here
+ */
+static int ssusb_id_notifier(struct notifier_block *nb,
+	unsigned long event, void *ptr)
+{
+	struct otg_switch_mtk *otg_sx =
+		container_of(nb, struct otg_switch_mtk, id_nb);
+
+	otg_sx->id_event = event;
+	schedule_work(&otg_sx->id_work);
 
 	return NOTIFY_DONE;
 }
@@ -194,10 +218,8 @@ static int ssusb_vbus_notifier(struct notifier_block *nb,
 	struct otg_switch_mtk *otg_sx =
 		container_of(nb, struct otg_switch_mtk, vbus_nb);
 
-	if (event)
-		ssusb_set_mailbox(otg_sx, MTU3_VBUS_VALID);
-	else
-		ssusb_set_mailbox(otg_sx, MTU3_VBUS_OFF);
+	otg_sx->vbus_event = event;
+	schedule_work(&otg_sx->vbus_work);
 
 	return NOTIFY_DONE;
 }
@@ -238,15 +260,6 @@ static int ssusb_extcon_register(struct otg_switch_mtk *otg_sx)
 	return 0;
 }
 
-static void extcon_register_dwork(struct work_struct *work)
-{
-	struct delayed_work *dwork = to_delayed_work(work);
-	struct otg_switch_mtk *otg_sx =
-	    container_of(dwork, struct otg_switch_mtk, extcon_reg_dwork);
-
-	ssusb_extcon_register(otg_sx);
-}
-
 /*
  * We provide an interface via debugfs to switch between host and device modes
  * depending on user input.
@@ -365,10 +378,6 @@ static void ssusb_debugfs_init(struct ssusb_mtk *ssusb)
 	struct dentry *root;
 
 	root = debugfs_create_dir(dev_name(ssusb->dev), usb_debug_root);
-	if (!root) {
-		dev_err(ssusb->dev, "create debugfs root failed\n");
-		return;
-	}
 	ssusb->dbgfs_root = root;
 
 	debugfs_create_file("mode", 0644, root, ssusb, &ssusb_mode_fops);
@@ -407,18 +416,13 @@ int ssusb_otg_switch_init(struct ssusb_mtk *ssusb)
 {
 	struct otg_switch_mtk *otg_sx = &ssusb->otg_switch;
 
-	if (otg_sx->manual_drd_enabled) {
+	INIT_WORK(&otg_sx->id_work, ssusb_id_work);
+	INIT_WORK(&otg_sx->vbus_work, ssusb_vbus_work);
+
+	if (otg_sx->manual_drd_enabled)
 		ssusb_debugfs_init(ssusb);
-	} else {
-		INIT_DELAYED_WORK(&otg_sx->extcon_reg_dwork,
-				  extcon_register_dwork);
-
-		/*
-		 * It is enough to delay 1s for waiting for
-		 * host initialization
-		 */
-		schedule_delayed_work(&otg_sx->extcon_reg_dwork, HZ);
-	}
+	else
+		ssusb_extcon_register(otg_sx);
 
 	return 0;
 }
@@ -429,6 +433,7 @@ void ssusb_otg_switch_exit(struct ssusb_mtk *ssusb)
 
 	if (otg_sx->manual_drd_enabled)
 		ssusb_debugfs_exit(ssusb);
-	else
-		cancel_delayed_work(&otg_sx->extcon_reg_dwork);
+
+	cancel_work_sync(&otg_sx->id_work);
+	cancel_work_sync(&otg_sx->vbus_work);
 }
diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c
index f05f10f5c171..5c60a8c5a0b5 100644
--- a/drivers/usb/mtu3/mtu3_gadget.c
+++ b/drivers/usb/mtu3/mtu3_gadget.c
@@ -660,14 +660,10 @@ int mtu3_gadget_setup(struct mtu3 *mtu)
 	mtu3_gadget_init_eps(mtu);
 
 	ret = usb_add_gadget_udc(mtu->dev, &mtu->g);
-	if (ret) {
+	if (ret)
 		dev_err(mtu->dev, "failed to register udc\n");
-		return ret;
-	}
 
-	usb_gadget_set_state(&mtu->g, USB_STATE_NOTATTACHED);
-
-	return 0;
+	return ret;
 }
 
 void mtu3_gadget_cleanup(struct mtu3 *mtu)
@@ -723,4 +719,5 @@ void mtu3_gadget_reset(struct mtu3 *mtu)
 	mtu->u1_enable = 0;
 	mtu->u2_enable = 0;
 	mtu->delayed_status = false;
+	mtu->test_mode = false;
 }
diff --git a/drivers/usb/mtu3/mtu3_gadget_ep0.c b/drivers/usb/mtu3/mtu3_gadget_ep0.c
index ebdcf7a38c29..25216e79cd6e 100644
--- a/drivers/usb/mtu3/mtu3_gadget_ep0.c
+++ b/drivers/usb/mtu3/mtu3_gadget_ep0.c
@@ -7,6 +7,7 @@
  * Author:  Chunfeng.Yun <chunfeng.yun@mediatek.com>
  */
 
+#include <linux/iopoll.h>
 #include <linux/usb/composite.h>
 
 #include "mtu3.h"
@@ -263,6 +264,7 @@ static int handle_test_mode(struct mtu3 *mtu, struct usb_ctrlrequest *setup)
 {
 	void __iomem *mbase = mtu->mac_base;
 	int handled = 1;
+	u32 value;
 
 	switch (le16_to_cpu(setup->wIndex) >> 8) {
 	case TEST_J:
@@ -292,6 +294,14 @@ static int handle_test_mode(struct mtu3 *mtu, struct usb_ctrlrequest *setup)
 	if (mtu->test_mode_nr == TEST_PACKET_MODE)
 		ep0_load_test_packet(mtu);
 
+	/* send status before entering test mode. */
+	value = mtu3_readl(mbase, U3D_EP0CSR) & EP0_W1C_BITS;
+	mtu3_writel(mbase, U3D_EP0CSR, value | EP0_SETUPPKTRDY | EP0_DATAEND);
+
+	/* wait for ACK status sent by host */
+	readl_poll_timeout_atomic(mbase + U3D_EP0CSR, value,
+			!(value & EP0_DATAEND), 100, 5000);
+
 	mtu3_writel(mbase, U3D_USB2_TEST_MODE, mtu->test_mode_nr);
 
 	mtu->ep0_state = MU3D_EP0_STATE_SETUP;
@@ -546,7 +556,7 @@ static void ep0_tx_state(struct mtu3 *mtu)
 	struct usb_request *req;
 	u32 csr;
 	u8 *src;
-	u8 count;
+	u32 count;
 	u32 maxp;
 
 	dev_dbg(mtu->dev, "%s\n", __func__);
diff --git a/drivers/usb/mtu3/mtu3_plat.c b/drivers/usb/mtu3/mtu3_plat.c
index 628d5ce356ca..46551f6d16fd 100644
--- a/drivers/usb/mtu3/mtu3_plat.c
+++ b/drivers/usb/mtu3/mtu3_plat.c
@@ -447,8 +447,7 @@ static int mtu3_remove(struct platform_device *pdev)
  */
 static int __maybe_unused mtu3_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct ssusb_mtk *ssusb = platform_get_drvdata(pdev);
+	struct ssusb_mtk *ssusb = dev_get_drvdata(dev);
 
 	dev_dbg(dev, "%s\n", __func__);
 
@@ -466,8 +465,7 @@ static int __maybe_unused mtu3_suspend(struct device *dev)
 
 static int __maybe_unused mtu3_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct ssusb_mtk *ssusb = platform_get_drvdata(pdev);
+	struct ssusb_mtk *ssusb = dev_get_drvdata(dev);
 	int ret;
 
 	dev_dbg(dev, "%s\n", __func__);
diff --git a/drivers/usb/musb/am35x.c b/drivers/usb/musb/am35x.c
index 0ad664efda6b..660641ab1545 100644
--- a/drivers/usb/musb/am35x.c
+++ b/drivers/usb/musb/am35x.c
@@ -201,7 +201,6 @@ static irqreturn_t am35x_musb_interrupt(int irq, void *hci)
 	struct device *dev = musb->controller;
 	struct musb_hdrc_platform_data *plat = dev_get_platdata(dev);
 	struct omap_musb_board_data *data = plat->board_data;
-	struct usb_otg *otg = musb->xceiv->otg;
 	unsigned long flags;
 	irqreturn_t ret = IRQ_NONE;
 	u32 epintr, usbintr;
@@ -264,14 +263,12 @@ static irqreturn_t am35x_musb_interrupt(int irq, void *hci)
 			WARNING("VBUS error workaround (delay coming)\n");
 		} else if (drvvbus) {
 			MUSB_HST_MODE(musb);
-			otg->default_a = 1;
 			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			portstate(musb->port1_status |= USB_PORT_STAT_POWER);
 			del_timer(&musb->dev_timer);
 		} else {
 			musb->is_active = 0;
 			MUSB_DEV_MODE(musb);
-			otg->default_a = 0;
 			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			portstate(musb->port1_status &= ~USB_PORT_STAT_POWER);
 		}
diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c
index b8295ce7c4fe..1c023c0091c4 100644
--- a/drivers/usb/musb/da8xx.c
+++ b/drivers/usb/musb/da8xx.c
@@ -223,7 +223,6 @@ static irqreturn_t da8xx_musb_interrupt(int irq, void *hci)
 {
 	struct musb		*musb = hci;
 	void __iomem		*reg_base = musb->ctrl_base;
-	struct usb_otg		*otg = musb->xceiv->otg;
 	unsigned long		flags;
 	irqreturn_t		ret = IRQ_NONE;
 	u32			status;
@@ -280,7 +279,6 @@ static irqreturn_t da8xx_musb_interrupt(int irq, void *hci)
 			WARNING("VBUS error workaround (delay coming)\n");
 		} else if (drvvbus) {
 			MUSB_HST_MODE(musb);
-			otg->default_a = 1;
 			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			portstate(musb->port1_status |= USB_PORT_STAT_POWER);
 			del_timer(&musb->dev_timer);
@@ -295,7 +293,6 @@ static irqreturn_t da8xx_musb_interrupt(int irq, void *hci)
 			 */
 			musb->is_active = 0;
 			MUSB_DEV_MODE(musb);
-			otg->default_a = 0;
 			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			portstate(musb->port1_status &= ~USB_PORT_STAT_POWER);
 		}
diff --git a/drivers/usb/musb/davinci.c b/drivers/usb/musb/davinci.c
index 2ad39dcd2f4c..fb6bbd254ab7 100644
--- a/drivers/usb/musb/davinci.c
+++ b/drivers/usb/musb/davinci.c
@@ -311,14 +311,12 @@ static irqreturn_t davinci_musb_interrupt(int irq, void *__hci)
 			WARNING("VBUS error workaround (delay coming)\n");
 		} else if (drvvbus) {
 			MUSB_HST_MODE(musb);
-			otg->default_a = 1;
 			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			portstate(musb->port1_status |= USB_PORT_STAT_POWER);
 			del_timer(&musb->dev_timer);
 		} else {
 			musb->is_active = 0;
 			MUSB_DEV_MODE(musb);
-			otg->default_a = 0;
 			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			portstate(musb->port1_status &= ~USB_PORT_STAT_POWER);
 		}
@@ -425,6 +423,9 @@ unregister:
 
 static int davinci_musb_exit(struct musb *musb)
 {
+	int	maxdelay = 30;
+	u8	devctl, warn = 0;
+
 	del_timer_sync(&musb->dev_timer);
 
 	/* force VBUS off */
@@ -438,31 +439,27 @@ static int davinci_musb_exit(struct musb *musb)
 
 	davinci_musb_source_power(musb, 0 /*off*/, 1);
 
-	/* delay, to avoid problems with module reload */
-	if (musb->xceiv->otg->default_a) {
-		int	maxdelay = 30;
-		u8	devctl, warn = 0;
+	/*
+	 * delay, to avoid problems with module reload.
+	 * if there's no peripheral connected, this can take a
+	 * long time to fall, especially on EVM with huge C133.
+	 */
+	do {
+		devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
+		if (!(devctl & MUSB_DEVCTL_VBUS))
+			break;
+		if ((devctl & MUSB_DEVCTL_VBUS) != warn) {
+			warn = devctl & MUSB_DEVCTL_VBUS;
+			dev_dbg(musb->controller, "VBUS %d\n",
+				warn >> MUSB_DEVCTL_VBUS_SHIFT);
+		}
+		msleep(1000);
+		maxdelay--;
+	} while (maxdelay > 0);
 
-		/* if there's no peripheral connected, this can take a
-		 * long time to fall, especially on EVM with huge C133.
-		 */
-		do {
-			devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
-			if (!(devctl & MUSB_DEVCTL_VBUS))
-				break;
-			if ((devctl & MUSB_DEVCTL_VBUS) != warn) {
-				warn = devctl & MUSB_DEVCTL_VBUS;
-				dev_dbg(musb->controller, "VBUS %d\n",
-					warn >> MUSB_DEVCTL_VBUS_SHIFT);
-			}
-			msleep(1000);
-			maxdelay--;
-		} while (maxdelay > 0);
-
-		/* in OTG mode, another host might be connected */
-		if (devctl & MUSB_DEVCTL_VBUS)
-			dev_dbg(musb->controller, "VBUS off timeout (devctl %02x)\n", devctl);
-	}
+	/* in OTG mode, another host might be connected */
+	if (devctl & MUSB_DEVCTL_VBUS)
+		dev_dbg(musb->controller, "VBUS off timeout (devctl %02x)\n", devctl);
 
 	phy_off();
 
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index fb5e4523dc28..b7d56272f9d1 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -274,20 +274,6 @@ static void musb_default_writew(void __iomem *addr, unsigned offset, u16 data)
 	__raw_writew(data, addr + offset);
 }
 
-static u32 musb_default_readl(const void __iomem *addr, unsigned offset)
-{
-	u32 data = __raw_readl(addr + offset);
-
-	trace_musb_readl(__builtin_return_address(0), addr, offset, data);
-	return data;
-}
-
-static void musb_default_writel(void __iomem *addr, unsigned offset, u32 data)
-{
-	trace_musb_writel(__builtin_return_address(0), addr, offset, data);
-	__raw_writel(data, addr + offset);
-}
-
 /*
  * Load an endpoint's FIFO
  */
@@ -390,10 +376,20 @@ EXPORT_SYMBOL_GPL(musb_readw);
 void (*musb_writew)(void __iomem *addr, unsigned offset, u16 data);
 EXPORT_SYMBOL_GPL(musb_writew);
 
-u32 (*musb_readl)(const void __iomem *addr, unsigned offset);
+u32 musb_readl(const void __iomem *addr, unsigned offset)
+{
+	u32 data = __raw_readl(addr + offset);
+
+	trace_musb_readl(__builtin_return_address(0), addr, offset, data);
+	return data;
+}
 EXPORT_SYMBOL_GPL(musb_readl);
 
-void (*musb_writel)(void __iomem *addr, unsigned offset, u32 data);
+void musb_writel(void __iomem *addr, unsigned offset, u32 data)
+{
+	trace_musb_writel(__builtin_return_address(0), addr, offset, data);
+	__raw_writel(data, addr + offset);
+}
 EXPORT_SYMBOL_GPL(musb_writel);
 
 #ifndef CONFIG_MUSB_PIO_ONLY
@@ -527,6 +523,383 @@ void musb_hnp_stop(struct musb *musb)
 
 static void musb_recover_from_babble(struct musb *musb);
 
+static void musb_handle_intr_resume(struct musb *musb, u8 devctl)
+{
+	musb_dbg(musb, "RESUME (%s)",
+			usb_otg_state_string(musb->xceiv->otg->state));
+
+	if (devctl & MUSB_DEVCTL_HM) {
+		switch (musb->xceiv->otg->state) {
+		case OTG_STATE_A_SUSPEND:
+			/* remote wakeup? */
+			musb->port1_status |=
+					(USB_PORT_STAT_C_SUSPEND << 16)
+					| MUSB_PORT_STAT_RESUME;
+			musb->rh_timer = jiffies
+				+ msecs_to_jiffies(USB_RESUME_TIMEOUT);
+			musb->xceiv->otg->state = OTG_STATE_A_HOST;
+			musb->is_active = 1;
+			musb_host_resume_root_hub(musb);
+			schedule_delayed_work(&musb->finish_resume_work,
+				msecs_to_jiffies(USB_RESUME_TIMEOUT));
+			break;
+		case OTG_STATE_B_WAIT_ACON:
+			musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
+			musb->is_active = 1;
+			MUSB_DEV_MODE(musb);
+			break;
+		default:
+			WARNING("bogus %s RESUME (%s)\n",
+				"host",
+				usb_otg_state_string(musb->xceiv->otg->state));
+		}
+	} else {
+		switch (musb->xceiv->otg->state) {
+		case OTG_STATE_A_SUSPEND:
+			/* possibly DISCONNECT is upcoming */
+			musb->xceiv->otg->state = OTG_STATE_A_HOST;
+			musb_host_resume_root_hub(musb);
+			break;
+		case OTG_STATE_B_WAIT_ACON:
+		case OTG_STATE_B_PERIPHERAL:
+			/* disconnect while suspended?  we may
+			 * not get a disconnect irq...
+			 */
+			if ((devctl & MUSB_DEVCTL_VBUS)
+					!= (3 << MUSB_DEVCTL_VBUS_SHIFT)
+					) {
+				musb->int_usb |= MUSB_INTR_DISCONNECT;
+				musb->int_usb &= ~MUSB_INTR_SUSPEND;
+				break;
+			}
+			musb_g_resume(musb);
+			break;
+		case OTG_STATE_B_IDLE:
+			musb->int_usb &= ~MUSB_INTR_SUSPEND;
+			break;
+		default:
+			WARNING("bogus %s RESUME (%s)\n",
+				"peripheral",
+				usb_otg_state_string(musb->xceiv->otg->state));
+		}
+	}
+}
+
+/* return IRQ_HANDLED to tell the caller to return immediately */
+static irqreturn_t musb_handle_intr_sessreq(struct musb *musb, u8 devctl)
+{
+	void __iomem *mbase = musb->mregs;
+
+	if ((devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS
+			&& (devctl & MUSB_DEVCTL_BDEVICE)) {
+		musb_dbg(musb, "SessReq while on B state");
+		return IRQ_HANDLED;
+	}
+
+	musb_dbg(musb, "SESSION_REQUEST (%s)",
+		usb_otg_state_string(musb->xceiv->otg->state));
+
+	/* IRQ arrives from ID pin sense or (later, if VBUS power
+	 * is removed) SRP.  responses are time critical:
+	 *  - turn on VBUS (with silicon-specific mechanism)
+	 *  - go through A_WAIT_VRISE
+	 *  - ... to A_WAIT_BCON.
+	 * a_wait_vrise_tmout triggers VBUS_ERROR transitions
+	 */
+	musb_writeb(mbase, MUSB_DEVCTL, MUSB_DEVCTL_SESSION);
+	musb->ep0_stage = MUSB_EP0_START;
+	musb->xceiv->otg->state = OTG_STATE_A_IDLE;
+	MUSB_HST_MODE(musb);
+	musb_platform_set_vbus(musb, 1);
+
+	return IRQ_NONE;
+}
+
+static void musb_handle_intr_vbuserr(struct musb *musb, u8 devctl)
+{
+	int	ignore = 0;
+
+	/* During connection as an A-Device, we may see a short
+	 * current spikes causing voltage drop, because of cable
+	 * and peripheral capacitance combined with vbus draw.
+	 * (So: less common with truly self-powered devices, where
+	 * vbus doesn't act like a power supply.)
+	 *
+	 * Such spikes are short; usually less than ~500 usec, max
+	 * of ~2 msec.  That is, they're not sustained overcurrent
+	 * errors, though they're reported using VBUSERROR irqs.
+	 *
+	 * Workarounds:  (a) hardware: use self powered devices.
+	 * (b) software:  ignore non-repeated VBUS errors.
+	 *
+	 * REVISIT:  do delays from lots of DEBUG_KERNEL checks
+	 * make trouble here, keeping VBUS < 4.4V ?
+	 */
+	switch (musb->xceiv->otg->state) {
+	case OTG_STATE_A_HOST:
+		/* recovery is dicey once we've gotten past the
+		 * initial stages of enumeration, but if VBUS
+		 * stayed ok at the other end of the link, and
+		 * another reset is due (at least for high speed,
+		 * to redo the chirp etc), it might work OK...
+		 */
+	case OTG_STATE_A_WAIT_BCON:
+	case OTG_STATE_A_WAIT_VRISE:
+		if (musb->vbuserr_retry) {
+			void __iomem *mbase = musb->mregs;
+
+			musb->vbuserr_retry--;
+			ignore = 1;
+			devctl |= MUSB_DEVCTL_SESSION;
+			musb_writeb(mbase, MUSB_DEVCTL, devctl);
+		} else {
+			musb->port1_status |=
+				  USB_PORT_STAT_OVERCURRENT
+				| (USB_PORT_STAT_C_OVERCURRENT << 16);
+		}
+		break;
+	default:
+		break;
+	}
+
+	dev_printk(ignore ? KERN_DEBUG : KERN_ERR, musb->controller,
+			"VBUS_ERROR in %s (%02x, %s), retry #%d, port1 %08x\n",
+			usb_otg_state_string(musb->xceiv->otg->state),
+			devctl,
+			({ char *s;
+			switch (devctl & MUSB_DEVCTL_VBUS) {
+			case 0 << MUSB_DEVCTL_VBUS_SHIFT:
+				s = "<SessEnd"; break;
+			case 1 << MUSB_DEVCTL_VBUS_SHIFT:
+				s = "<AValid"; break;
+			case 2 << MUSB_DEVCTL_VBUS_SHIFT:
+				s = "<VBusValid"; break;
+			/* case 3 << MUSB_DEVCTL_VBUS_SHIFT: */
+			default:
+				s = "VALID"; break;
+			} s; }),
+			VBUSERR_RETRY_COUNT - musb->vbuserr_retry,
+			musb->port1_status);
+
+	/* go through A_WAIT_VFALL then start a new session */
+	if (!ignore)
+		musb_platform_set_vbus(musb, 0);
+}
+
+static void musb_handle_intr_suspend(struct musb *musb, u8 devctl)
+{
+	musb_dbg(musb, "SUSPEND (%s) devctl %02x",
+		usb_otg_state_string(musb->xceiv->otg->state), devctl);
+
+	switch (musb->xceiv->otg->state) {
+	case OTG_STATE_A_PERIPHERAL:
+		/* We also come here if the cable is removed, since
+		 * this silicon doesn't report ID-no-longer-grounded.
+		 *
+		 * We depend on T(a_wait_bcon) to shut us down, and
+		 * hope users don't do anything dicey during this
+		 * undesired detour through A_WAIT_BCON.
+		 */
+		musb_hnp_stop(musb);
+		musb_host_resume_root_hub(musb);
+		musb_root_disconnect(musb);
+		musb_platform_try_idle(musb, jiffies
+				+ msecs_to_jiffies(musb->a_wait_bcon
+					? : OTG_TIME_A_WAIT_BCON));
+
+		break;
+	case OTG_STATE_B_IDLE:
+		if (!musb->is_active)
+			break;
+		/* fall through */
+	case OTG_STATE_B_PERIPHERAL:
+		musb_g_suspend(musb);
+		musb->is_active = musb->g.b_hnp_enable;
+		if (musb->is_active) {
+			musb->xceiv->otg->state = OTG_STATE_B_WAIT_ACON;
+			musb_dbg(musb, "HNP: Setting timer for b_ase0_brst");
+			mod_timer(&musb->otg_timer, jiffies
+				+ msecs_to_jiffies(
+						OTG_TIME_B_ASE0_BRST));
+		}
+		break;
+	case OTG_STATE_A_WAIT_BCON:
+		if (musb->a_wait_bcon != 0)
+			musb_platform_try_idle(musb, jiffies
+				+ msecs_to_jiffies(musb->a_wait_bcon));
+		break;
+	case OTG_STATE_A_HOST:
+		musb->xceiv->otg->state = OTG_STATE_A_SUSPEND;
+		musb->is_active = musb->hcd->self.b_hnp_enable;
+		break;
+	case OTG_STATE_B_HOST:
+		/* Transition to B_PERIPHERAL, see 6.8.2.6 p 44 */
+		musb_dbg(musb, "REVISIT: SUSPEND as B_HOST");
+		break;
+	default:
+		/* "should not happen" */
+		musb->is_active = 0;
+		break;
+	}
+}
+
+static void musb_handle_intr_connect(struct musb *musb, u8 devctl, u8 int_usb)
+{
+	struct usb_hcd *hcd = musb->hcd;
+
+	musb->is_active = 1;
+	musb->ep0_stage = MUSB_EP0_START;
+
+	musb->intrtxe = musb->epmask;
+	musb_writew(musb->mregs, MUSB_INTRTXE, musb->intrtxe);
+	musb->intrrxe = musb->epmask & 0xfffe;
+	musb_writew(musb->mregs, MUSB_INTRRXE, musb->intrrxe);
+	musb_writeb(musb->mregs, MUSB_INTRUSBE, 0xf7);
+	musb->port1_status &= ~(USB_PORT_STAT_LOW_SPEED
+				|USB_PORT_STAT_HIGH_SPEED
+				|USB_PORT_STAT_ENABLE
+				);
+	musb->port1_status |= USB_PORT_STAT_CONNECTION
+				|(USB_PORT_STAT_C_CONNECTION << 16);
+
+	/* high vs full speed is just a guess until after reset */
+	if (devctl & MUSB_DEVCTL_LSDEV)
+		musb->port1_status |= USB_PORT_STAT_LOW_SPEED;
+
+	/* indicate new connection to OTG machine */
+	switch (musb->xceiv->otg->state) {
+	case OTG_STATE_B_PERIPHERAL:
+		if (int_usb & MUSB_INTR_SUSPEND) {
+			musb_dbg(musb, "HNP: SUSPEND+CONNECT, now b_host");
+			int_usb &= ~MUSB_INTR_SUSPEND;
+			goto b_host;
+		} else
+			musb_dbg(musb, "CONNECT as b_peripheral???");
+		break;
+	case OTG_STATE_B_WAIT_ACON:
+		musb_dbg(musb, "HNP: CONNECT, now b_host");
+b_host:
+		musb->xceiv->otg->state = OTG_STATE_B_HOST;
+		if (musb->hcd)
+			musb->hcd->self.is_b_host = 1;
+		del_timer(&musb->otg_timer);
+		break;
+	default:
+		if ((devctl & MUSB_DEVCTL_VBUS)
+				== (3 << MUSB_DEVCTL_VBUS_SHIFT)) {
+			musb->xceiv->otg->state = OTG_STATE_A_HOST;
+			if (hcd)
+				hcd->self.is_b_host = 0;
+		}
+		break;
+	}
+
+	musb_host_poke_root_hub(musb);
+
+	musb_dbg(musb, "CONNECT (%s) devctl %02x",
+			usb_otg_state_string(musb->xceiv->otg->state), devctl);
+}
+
+static void musb_handle_intr_disconnect(struct musb *musb, u8 devctl)
+{
+	musb_dbg(musb, "DISCONNECT (%s) as %s, devctl %02x",
+			usb_otg_state_string(musb->xceiv->otg->state),
+			MUSB_MODE(musb), devctl);
+
+	switch (musb->xceiv->otg->state) {
+	case OTG_STATE_A_HOST:
+	case OTG_STATE_A_SUSPEND:
+		musb_host_resume_root_hub(musb);
+		musb_root_disconnect(musb);
+		if (musb->a_wait_bcon != 0)
+			musb_platform_try_idle(musb, jiffies
+				+ msecs_to_jiffies(musb->a_wait_bcon));
+		break;
+	case OTG_STATE_B_HOST:
+		/* REVISIT this behaves for "real disconnect"
+		 * cases; make sure the other transitions from
+		 * from B_HOST act right too.  The B_HOST code
+		 * in hnp_stop() is currently not used...
+		 */
+		musb_root_disconnect(musb);
+		if (musb->hcd)
+			musb->hcd->self.is_b_host = 0;
+		musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
+		MUSB_DEV_MODE(musb);
+		musb_g_disconnect(musb);
+		break;
+	case OTG_STATE_A_PERIPHERAL:
+		musb_hnp_stop(musb);
+		musb_root_disconnect(musb);
+		/* FALLTHROUGH */
+	case OTG_STATE_B_WAIT_ACON:
+		/* FALLTHROUGH */
+	case OTG_STATE_B_PERIPHERAL:
+	case OTG_STATE_B_IDLE:
+		musb_g_disconnect(musb);
+		break;
+	default:
+		WARNING("unhandled DISCONNECT transition (%s)\n",
+			usb_otg_state_string(musb->xceiv->otg->state));
+		break;
+	}
+}
+
+/*
+ * mentor saves a bit: bus reset and babble share the same irq.
+ * only host sees babble; only peripheral sees bus reset.
+ */
+static void musb_handle_intr_reset(struct musb *musb)
+{
+	if (is_host_active(musb)) {
+		/*
+		 * When BABBLE happens what we can depends on which
+		 * platform MUSB is running, because some platforms
+		 * implemented proprietary means for 'recovering' from
+		 * Babble conditions. One such platform is AM335x. In
+		 * most cases, however, the only thing we can do is
+		 * drop the session.
+		 */
+		dev_err(musb->controller, "Babble\n");
+		musb_recover_from_babble(musb);
+	} else {
+		musb_dbg(musb, "BUS RESET as %s",
+			usb_otg_state_string(musb->xceiv->otg->state));
+		switch (musb->xceiv->otg->state) {
+		case OTG_STATE_A_SUSPEND:
+			musb_g_reset(musb);
+			/* FALLTHROUGH */
+		case OTG_STATE_A_WAIT_BCON:	/* OPT TD.4.7-900ms */
+			/* never use invalid T(a_wait_bcon) */
+			musb_dbg(musb, "HNP: in %s, %d msec timeout",
+				usb_otg_state_string(musb->xceiv->otg->state),
+				TA_WAIT_BCON(musb));
+			mod_timer(&musb->otg_timer, jiffies
+				+ msecs_to_jiffies(TA_WAIT_BCON(musb)));
+			break;
+		case OTG_STATE_A_PERIPHERAL:
+			del_timer(&musb->otg_timer);
+			musb_g_reset(musb);
+			break;
+		case OTG_STATE_B_WAIT_ACON:
+			musb_dbg(musb, "HNP: RESET (%s), to b_peripheral",
+				usb_otg_state_string(musb->xceiv->otg->state));
+			musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
+			musb_g_reset(musb);
+			break;
+		case OTG_STATE_B_IDLE:
+			musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
+			/* FALLTHROUGH */
+		case OTG_STATE_B_PERIPHERAL:
+			musb_g_reset(musb);
+			break;
+		default:
+			musb_dbg(musb, "Unhandled BUS RESET as %s",
+				usb_otg_state_string(musb->xceiv->otg->state));
+		}
+	}
+}
+
 /*
  * Interrupt Service Routine to record USB "global" interrupts.
  * Since these do not happen often and signify things of
@@ -551,379 +924,40 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 	 * spurious RESUME irqs happen too, paired with SUSPEND.
 	 */
 	if (int_usb & MUSB_INTR_RESUME) {
+		musb_handle_intr_resume(musb, devctl);
 		handled = IRQ_HANDLED;
-		musb_dbg(musb, "RESUME (%s)",
-				usb_otg_state_string(musb->xceiv->otg->state));
-
-		if (devctl & MUSB_DEVCTL_HM) {
-			switch (musb->xceiv->otg->state) {
-			case OTG_STATE_A_SUSPEND:
-				/* remote wakeup? */
-				musb->port1_status |=
-						(USB_PORT_STAT_C_SUSPEND << 16)
-						| MUSB_PORT_STAT_RESUME;
-				musb->rh_timer = jiffies
-					+ msecs_to_jiffies(USB_RESUME_TIMEOUT);
-				musb->xceiv->otg->state = OTG_STATE_A_HOST;
-				musb->is_active = 1;
-				musb_host_resume_root_hub(musb);
-				schedule_delayed_work(&musb->finish_resume_work,
-					msecs_to_jiffies(USB_RESUME_TIMEOUT));
-				break;
-			case OTG_STATE_B_WAIT_ACON:
-				musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
-				musb->is_active = 1;
-				MUSB_DEV_MODE(musb);
-				break;
-			default:
-				WARNING("bogus %s RESUME (%s)\n",
-					"host",
-					usb_otg_state_string(musb->xceiv->otg->state));
-			}
-		} else {
-			switch (musb->xceiv->otg->state) {
-			case OTG_STATE_A_SUSPEND:
-				/* possibly DISCONNECT is upcoming */
-				musb->xceiv->otg->state = OTG_STATE_A_HOST;
-				musb_host_resume_root_hub(musb);
-				break;
-			case OTG_STATE_B_WAIT_ACON:
-			case OTG_STATE_B_PERIPHERAL:
-				/* disconnect while suspended?  we may
-				 * not get a disconnect irq...
-				 */
-				if ((devctl & MUSB_DEVCTL_VBUS)
-						!= (3 << MUSB_DEVCTL_VBUS_SHIFT)
-						) {
-					musb->int_usb |= MUSB_INTR_DISCONNECT;
-					musb->int_usb &= ~MUSB_INTR_SUSPEND;
-					break;
-				}
-				musb_g_resume(musb);
-				break;
-			case OTG_STATE_B_IDLE:
-				musb->int_usb &= ~MUSB_INTR_SUSPEND;
-				break;
-			default:
-				WARNING("bogus %s RESUME (%s)\n",
-					"peripheral",
-					usb_otg_state_string(musb->xceiv->otg->state));
-			}
-		}
 	}
 
 	/* see manual for the order of the tests */
 	if (int_usb & MUSB_INTR_SESSREQ) {
-		void __iomem *mbase = musb->mregs;
-
-		if ((devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS
-				&& (devctl & MUSB_DEVCTL_BDEVICE)) {
-			musb_dbg(musb, "SessReq while on B state");
+		if (musb_handle_intr_sessreq(musb, devctl))
 			return IRQ_HANDLED;
-		}
-
-		musb_dbg(musb, "SESSION_REQUEST (%s)",
-			usb_otg_state_string(musb->xceiv->otg->state));
-
-		/* IRQ arrives from ID pin sense or (later, if VBUS power
-		 * is removed) SRP.  responses are time critical:
-		 *  - turn on VBUS (with silicon-specific mechanism)
-		 *  - go through A_WAIT_VRISE
-		 *  - ... to A_WAIT_BCON.
-		 * a_wait_vrise_tmout triggers VBUS_ERROR transitions
-		 */
-		musb_writeb(mbase, MUSB_DEVCTL, MUSB_DEVCTL_SESSION);
-		musb->ep0_stage = MUSB_EP0_START;
-		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
-		MUSB_HST_MODE(musb);
-		musb_platform_set_vbus(musb, 1);
-
 		handled = IRQ_HANDLED;
 	}
 
 	if (int_usb & MUSB_INTR_VBUSERROR) {
-		int	ignore = 0;
-
-		/* During connection as an A-Device, we may see a short
-		 * current spikes causing voltage drop, because of cable
-		 * and peripheral capacitance combined with vbus draw.
-		 * (So: less common with truly self-powered devices, where
-		 * vbus doesn't act like a power supply.)
-		 *
-		 * Such spikes are short; usually less than ~500 usec, max
-		 * of ~2 msec.  That is, they're not sustained overcurrent
-		 * errors, though they're reported using VBUSERROR irqs.
-		 *
-		 * Workarounds:  (a) hardware: use self powered devices.
-		 * (b) software:  ignore non-repeated VBUS errors.
-		 *
-		 * REVISIT:  do delays from lots of DEBUG_KERNEL checks
-		 * make trouble here, keeping VBUS < 4.4V ?
-		 */
-		switch (musb->xceiv->otg->state) {
-		case OTG_STATE_A_HOST:
-			/* recovery is dicey once we've gotten past the
-			 * initial stages of enumeration, but if VBUS
-			 * stayed ok at the other end of the link, and
-			 * another reset is due (at least for high speed,
-			 * to redo the chirp etc), it might work OK...
-			 */
-		case OTG_STATE_A_WAIT_BCON:
-		case OTG_STATE_A_WAIT_VRISE:
-			if (musb->vbuserr_retry) {
-				void __iomem *mbase = musb->mregs;
-
-				musb->vbuserr_retry--;
-				ignore = 1;
-				devctl |= MUSB_DEVCTL_SESSION;
-				musb_writeb(mbase, MUSB_DEVCTL, devctl);
-			} else {
-				musb->port1_status |=
-					  USB_PORT_STAT_OVERCURRENT
-					| (USB_PORT_STAT_C_OVERCURRENT << 16);
-			}
-			break;
-		default:
-			break;
-		}
-
-		dev_printk(ignore ? KERN_DEBUG : KERN_ERR, musb->controller,
-				"VBUS_ERROR in %s (%02x, %s), retry #%d, port1 %08x\n",
-				usb_otg_state_string(musb->xceiv->otg->state),
-				devctl,
-				({ char *s;
-				switch (devctl & MUSB_DEVCTL_VBUS) {
-				case 0 << MUSB_DEVCTL_VBUS_SHIFT:
-					s = "<SessEnd"; break;
-				case 1 << MUSB_DEVCTL_VBUS_SHIFT:
-					s = "<AValid"; break;
-				case 2 << MUSB_DEVCTL_VBUS_SHIFT:
-					s = "<VBusValid"; break;
-				/* case 3 << MUSB_DEVCTL_VBUS_SHIFT: */
-				default:
-					s = "VALID"; break;
-				} s; }),
-				VBUSERR_RETRY_COUNT - musb->vbuserr_retry,
-				musb->port1_status);
-
-		/* go through A_WAIT_VFALL then start a new session */
-		if (!ignore)
-			musb_platform_set_vbus(musb, 0);
+		musb_handle_intr_vbuserr(musb, devctl);
 		handled = IRQ_HANDLED;
 	}
 
 	if (int_usb & MUSB_INTR_SUSPEND) {
-		musb_dbg(musb, "SUSPEND (%s) devctl %02x",
-			usb_otg_state_string(musb->xceiv->otg->state), devctl);
+		musb_handle_intr_suspend(musb, devctl);
 		handled = IRQ_HANDLED;
-
-		switch (musb->xceiv->otg->state) {
-		case OTG_STATE_A_PERIPHERAL:
-			/* We also come here if the cable is removed, since
-			 * this silicon doesn't report ID-no-longer-grounded.
-			 *
-			 * We depend on T(a_wait_bcon) to shut us down, and
-			 * hope users don't do anything dicey during this
-			 * undesired detour through A_WAIT_BCON.
-			 */
-			musb_hnp_stop(musb);
-			musb_host_resume_root_hub(musb);
-			musb_root_disconnect(musb);
-			musb_platform_try_idle(musb, jiffies
-					+ msecs_to_jiffies(musb->a_wait_bcon
-						? : OTG_TIME_A_WAIT_BCON));
-
-			break;
-		case OTG_STATE_B_IDLE:
-			if (!musb->is_active)
-				break;
-			/* fall through */
-		case OTG_STATE_B_PERIPHERAL:
-			musb_g_suspend(musb);
-			musb->is_active = musb->g.b_hnp_enable;
-			if (musb->is_active) {
-				musb->xceiv->otg->state = OTG_STATE_B_WAIT_ACON;
-				musb_dbg(musb, "HNP: Setting timer for b_ase0_brst");
-				mod_timer(&musb->otg_timer, jiffies
-					+ msecs_to_jiffies(
-							OTG_TIME_B_ASE0_BRST));
-			}
-			break;
-		case OTG_STATE_A_WAIT_BCON:
-			if (musb->a_wait_bcon != 0)
-				musb_platform_try_idle(musb, jiffies
-					+ msecs_to_jiffies(musb->a_wait_bcon));
-			break;
-		case OTG_STATE_A_HOST:
-			musb->xceiv->otg->state = OTG_STATE_A_SUSPEND;
-			musb->is_active = musb->hcd->self.b_hnp_enable;
-			break;
-		case OTG_STATE_B_HOST:
-			/* Transition to B_PERIPHERAL, see 6.8.2.6 p 44 */
-			musb_dbg(musb, "REVISIT: SUSPEND as B_HOST");
-			break;
-		default:
-			/* "should not happen" */
-			musb->is_active = 0;
-			break;
-		}
 	}
 
 	if (int_usb & MUSB_INTR_CONNECT) {
-		struct usb_hcd *hcd = musb->hcd;
-
+		musb_handle_intr_connect(musb, devctl, int_usb);
 		handled = IRQ_HANDLED;
-		musb->is_active = 1;
-
-		musb->ep0_stage = MUSB_EP0_START;
-
-		musb->intrtxe = musb->epmask;
-		musb_writew(musb->mregs, MUSB_INTRTXE, musb->intrtxe);
-		musb->intrrxe = musb->epmask & 0xfffe;
-		musb_writew(musb->mregs, MUSB_INTRRXE, musb->intrrxe);
-		musb_writeb(musb->mregs, MUSB_INTRUSBE, 0xf7);
-		musb->port1_status &= ~(USB_PORT_STAT_LOW_SPEED
-					|USB_PORT_STAT_HIGH_SPEED
-					|USB_PORT_STAT_ENABLE
-					);
-		musb->port1_status |= USB_PORT_STAT_CONNECTION
-					|(USB_PORT_STAT_C_CONNECTION << 16);
-
-		/* high vs full speed is just a guess until after reset */
-		if (devctl & MUSB_DEVCTL_LSDEV)
-			musb->port1_status |= USB_PORT_STAT_LOW_SPEED;
-
-		/* indicate new connection to OTG machine */
-		switch (musb->xceiv->otg->state) {
-		case OTG_STATE_B_PERIPHERAL:
-			if (int_usb & MUSB_INTR_SUSPEND) {
-				musb_dbg(musb, "HNP: SUSPEND+CONNECT, now b_host");
-				int_usb &= ~MUSB_INTR_SUSPEND;
-				goto b_host;
-			} else
-				musb_dbg(musb, "CONNECT as b_peripheral???");
-			break;
-		case OTG_STATE_B_WAIT_ACON:
-			musb_dbg(musb, "HNP: CONNECT, now b_host");
-b_host:
-			musb->xceiv->otg->state = OTG_STATE_B_HOST;
-			if (musb->hcd)
-				musb->hcd->self.is_b_host = 1;
-			del_timer(&musb->otg_timer);
-			break;
-		default:
-			if ((devctl & MUSB_DEVCTL_VBUS)
-					== (3 << MUSB_DEVCTL_VBUS_SHIFT)) {
-				musb->xceiv->otg->state = OTG_STATE_A_HOST;
-				if (hcd)
-					hcd->self.is_b_host = 0;
-			}
-			break;
-		}
-
-		musb_host_poke_root_hub(musb);
-
-		musb_dbg(musb, "CONNECT (%s) devctl %02x",
-				usb_otg_state_string(musb->xceiv->otg->state), devctl);
 	}
 
 	if (int_usb & MUSB_INTR_DISCONNECT) {
-		musb_dbg(musb, "DISCONNECT (%s) as %s, devctl %02x",
-				usb_otg_state_string(musb->xceiv->otg->state),
-				MUSB_MODE(musb), devctl);
+		musb_handle_intr_disconnect(musb, devctl);
 		handled = IRQ_HANDLED;
-
-		switch (musb->xceiv->otg->state) {
-		case OTG_STATE_A_HOST:
-		case OTG_STATE_A_SUSPEND:
-			musb_host_resume_root_hub(musb);
-			musb_root_disconnect(musb);
-			if (musb->a_wait_bcon != 0)
-				musb_platform_try_idle(musb, jiffies
-					+ msecs_to_jiffies(musb->a_wait_bcon));
-			break;
-		case OTG_STATE_B_HOST:
-			/* REVISIT this behaves for "real disconnect"
-			 * cases; make sure the other transitions from
-			 * from B_HOST act right too.  The B_HOST code
-			 * in hnp_stop() is currently not used...
-			 */
-			musb_root_disconnect(musb);
-			if (musb->hcd)
-				musb->hcd->self.is_b_host = 0;
-			musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
-			MUSB_DEV_MODE(musb);
-			musb_g_disconnect(musb);
-			break;
-		case OTG_STATE_A_PERIPHERAL:
-			musb_hnp_stop(musb);
-			musb_root_disconnect(musb);
-			/* FALLTHROUGH */
-		case OTG_STATE_B_WAIT_ACON:
-			/* FALLTHROUGH */
-		case OTG_STATE_B_PERIPHERAL:
-		case OTG_STATE_B_IDLE:
-			musb_g_disconnect(musb);
-			break;
-		default:
-			WARNING("unhandled DISCONNECT transition (%s)\n",
-				usb_otg_state_string(musb->xceiv->otg->state));
-			break;
-		}
 	}
 
-	/* mentor saves a bit: bus reset and babble share the same irq.
-	 * only host sees babble; only peripheral sees bus reset.
-	 */
 	if (int_usb & MUSB_INTR_RESET) {
+		musb_handle_intr_reset(musb);
 		handled = IRQ_HANDLED;
-		if (is_host_active(musb)) {
-			/*
-			 * When BABBLE happens what we can depends on which
-			 * platform MUSB is running, because some platforms
-			 * implemented proprietary means for 'recovering' from
-			 * Babble conditions. One such platform is AM335x. In
-			 * most cases, however, the only thing we can do is
-			 * drop the session.
-			 */
-			dev_err(musb->controller, "Babble\n");
-			musb_recover_from_babble(musb);
-		} else {
-			musb_dbg(musb, "BUS RESET as %s",
-				usb_otg_state_string(musb->xceiv->otg->state));
-			switch (musb->xceiv->otg->state) {
-			case OTG_STATE_A_SUSPEND:
-				musb_g_reset(musb);
-				/* FALLTHROUGH */
-			case OTG_STATE_A_WAIT_BCON:	/* OPT TD.4.7-900ms */
-				/* never use invalid T(a_wait_bcon) */
-				musb_dbg(musb, "HNP: in %s, %d msec timeout",
-					usb_otg_state_string(musb->xceiv->otg->state),
-					TA_WAIT_BCON(musb));
-				mod_timer(&musb->otg_timer, jiffies
-					+ msecs_to_jiffies(TA_WAIT_BCON(musb)));
-				break;
-			case OTG_STATE_A_PERIPHERAL:
-				del_timer(&musb->otg_timer);
-				musb_g_reset(musb);
-				break;
-			case OTG_STATE_B_WAIT_ACON:
-				musb_dbg(musb, "HNP: RESET (%s), to b_peripheral",
-					usb_otg_state_string(musb->xceiv->otg->state));
-				musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
-				musb_g_reset(musb);
-				break;
-			case OTG_STATE_B_IDLE:
-				musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
-				/* FALLTHROUGH */
-			case OTG_STATE_B_PERIPHERAL:
-				musb_g_reset(musb);
-				break;
-			default:
-				musb_dbg(musb, "Unhandled BUS RESET as %s",
-					usb_otg_state_string(musb->xceiv->otg->state));
-			}
-		}
 	}
 
 #if 0
@@ -1042,7 +1076,7 @@ void musb_start(struct musb *musb)
 	 * (b) vbus present/connect IRQ, peripheral mode;
 	 * (c) peripheral initiates, using SRP
 	 */
-	if (musb->port_mode != MUSB_PORT_MODE_HOST &&
+	if (musb->port_mode != MUSB_HOST &&
 			musb->xceiv->otg->state != OTG_STATE_A_WAIT_BCON &&
 			(devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS) {
 		musb->is_active = 1;
@@ -1244,25 +1278,25 @@ fifo_setup(struct musb *musb, struct musb_hw_ep  *hw_ep,
 	/* REVISIT error check:  be sure ep0 can both rx and tx ... */
 	switch (cfg->style) {
 	case FIFO_TX:
-		musb_write_txfifosz(mbase, c_size);
-		musb_write_txfifoadd(mbase, c_off);
+		musb_writeb(mbase, MUSB_TXFIFOSZ, c_size);
+		musb_writew(mbase, MUSB_TXFIFOADD, c_off);
 		hw_ep->tx_double_buffered = !!(c_size & MUSB_FIFOSZ_DPB);
 		hw_ep->max_packet_sz_tx = maxpacket;
 		break;
 	case FIFO_RX:
-		musb_write_rxfifosz(mbase, c_size);
-		musb_write_rxfifoadd(mbase, c_off);
+		musb_writeb(mbase, MUSB_RXFIFOSZ, c_size);
+		musb_writew(mbase, MUSB_RXFIFOADD, c_off);
 		hw_ep->rx_double_buffered = !!(c_size & MUSB_FIFOSZ_DPB);
 		hw_ep->max_packet_sz_rx = maxpacket;
 		break;
 	case FIFO_RXTX:
-		musb_write_txfifosz(mbase, c_size);
-		musb_write_txfifoadd(mbase, c_off);
+		musb_writeb(mbase, MUSB_TXFIFOSZ, c_size);
+		musb_writew(mbase, MUSB_TXFIFOADD, c_off);
 		hw_ep->rx_double_buffered = !!(c_size & MUSB_FIFOSZ_DPB);
 		hw_ep->max_packet_sz_rx = maxpacket;
 
-		musb_write_rxfifosz(mbase, c_size);
-		musb_write_rxfifoadd(mbase, c_off);
+		musb_writeb(mbase, MUSB_RXFIFOSZ, c_size);
+		musb_writew(mbase, MUSB_RXFIFOADD, c_off);
 		hw_ep->tx_double_buffered = hw_ep->rx_double_buffered;
 		hw_ep->max_packet_sz_tx = maxpacket;
 
@@ -1470,7 +1504,7 @@ static int musb_core_init(u16 musb_type, struct musb *musb)
 	}
 
 	/* log release info */
-	musb->hwvers = musb_read_hwvers(mbase);
+	musb->hwvers = musb_readw(mbase, MUSB_HWVERS);
 	pr_debug("%s: %sHDRC RTL version %d.%d%s\n",
 		 musb_driver_name, type, MUSB_HWVERS_MAJOR(musb->hwvers),
 		 MUSB_HWVERS_MINOR(musb->hwvers),
@@ -1497,7 +1531,7 @@ static int musb_core_init(u16 musb_type, struct musb *musb)
 
 		hw_ep->fifo = musb->io.fifo_offset(i) + mbase;
 #if IS_ENABLED(CONFIG_USB_MUSB_TUSB6010)
-		if (musb->io.quirks & MUSB_IN_TUSB) {
+		if (musb->ops->quirks & MUSB_IN_TUSB) {
 			hw_ep->fifo_async = musb->async + 0x400 +
 				musb->io.fifo_offset(i);
 			hw_ep->fifo_sync = musb->sync + 0x400 +
@@ -2158,8 +2192,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 	musb_writeb = musb_default_writeb;
 	musb_readw = musb_default_readw;
 	musb_writew = musb_default_writew;
-	musb_readl = musb_default_readl;
-	musb_writel = musb_default_writel;
 
 	/* The musb_platform_init() call:
 	 *   - adjusts musb->mregs
@@ -2182,11 +2214,9 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 		goto fail2;
 	}
 
-	if (musb->ops->quirks)
-		musb->io.quirks = musb->ops->quirks;
 
 	/* Most devices use indexed offset or flat offset */
-	if (musb->io.quirks & MUSB_INDEXED_EP) {
+	if (musb->ops->quirks & MUSB_INDEXED_EP) {
 		musb->io.ep_offset = musb_indexed_ep_offset;
 		musb->io.ep_select = musb_indexed_ep_select;
 	} else {
@@ -2194,7 +2224,7 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 		musb->io.ep_select = musb_flat_ep_select;
 	}
 
-	if (musb->io.quirks & MUSB_G_NO_SKB_RESERVE)
+	if (musb->ops->quirks & MUSB_G_NO_SKB_RESERVE)
 		musb->g.quirk_avoids_skb_reserve = 1;
 
 	/* At least tusb6010 has its own offsets */
@@ -2226,10 +2256,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 		musb_readw = musb->ops->readw;
 	if (musb->ops->writew)
 		musb_writew = musb->ops->writew;
-	if (musb->ops->readl)
-		musb_readl = musb->ops->readl;
-	if (musb->ops->writel)
-		musb_writel = musb->ops->writel;
 
 #ifndef CONFIG_MUSB_PIO_ONLY
 	if (!musb->ops->dma_init || !musb->ops->dma_exit) {
@@ -2321,33 +2347,28 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 
 	/* program PHY to use external vBus if required */
 	if (plat->extvbus) {
-		u8 busctl = musb_read_ulpi_buscontrol(musb->mregs);
+		u8 busctl = musb_readb(musb->mregs, MUSB_ULPI_BUSCONTROL);
 		busctl |= MUSB_ULPI_USE_EXTVBUS;
-		musb_write_ulpi_buscontrol(musb->mregs, busctl);
+		musb_writeb(musb->mregs, MUSB_ULPI_BUSCONTROL, busctl);
 	}
 
-	if (musb->xceiv->otg->default_a) {
-		MUSB_HST_MODE(musb);
-		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
-	} else {
-		MUSB_DEV_MODE(musb);
-		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
-	}
+	MUSB_DEV_MODE(musb);
+	musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 
 	switch (musb->port_mode) {
-	case MUSB_PORT_MODE_HOST:
+	case MUSB_HOST:
 		status = musb_host_setup(musb, plat->power);
 		if (status < 0)
 			goto fail3;
 		status = musb_platform_set_mode(musb, MUSB_HOST);
 		break;
-	case MUSB_PORT_MODE_GADGET:
+	case MUSB_PERIPHERAL:
 		status = musb_gadget_setup(musb);
 		if (status < 0)
 			goto fail3;
 		status = musb_platform_set_mode(musb, MUSB_PERIPHERAL);
 		break;
-	case MUSB_PORT_MODE_DUAL_ROLE:
+	case MUSB_OTG:
 		status = musb_host_setup(musb, plat->power);
 		if (status < 0)
 			goto fail3;
@@ -2366,9 +2387,7 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 	if (status < 0)
 		goto fail3;
 
-	status = musb_init_debugfs(musb);
-	if (status < 0)
-		goto fail4;
+	musb_init_debugfs(musb);
 
 	status = sysfs_create_group(&musb->controller->kobj, &musb_attr_group);
 	if (status)
@@ -2383,7 +2402,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 fail5:
 	musb_exit_debugfs(musb);
 
-fail4:
 	musb_gadget_cleanup(musb);
 	musb_host_cleanup(musb);
 
@@ -2492,7 +2510,7 @@ static void musb_save_context(struct musb *musb)
 
 	musb->context.frame = musb_readw(musb_base, MUSB_FRAME);
 	musb->context.testmode = musb_readb(musb_base, MUSB_TESTMODE);
-	musb->context.busctl = musb_read_ulpi_buscontrol(musb->mregs);
+	musb->context.busctl = musb_readb(musb_base, MUSB_ULPI_BUSCONTROL);
 	musb->context.power = musb_readb(musb_base, MUSB_POWER);
 	musb->context.intrusbe = musb_readb(musb_base, MUSB_INTRUSBE);
 	musb->context.index = musb_readb(musb_base, MUSB_INDEX);
@@ -2521,13 +2539,13 @@ static void musb_save_context(struct musb *musb)
 
 		if (musb->dyn_fifo) {
 			musb->context.index_regs[i].txfifoadd =
-					musb_read_txfifoadd(musb_base);
+					musb_readw(musb_base, MUSB_TXFIFOADD);
 			musb->context.index_regs[i].rxfifoadd =
-					musb_read_rxfifoadd(musb_base);
+					musb_readw(musb_base, MUSB_RXFIFOADD);
 			musb->context.index_regs[i].txfifosz =
-					musb_read_txfifosz(musb_base);
+					musb_readb(musb_base, MUSB_TXFIFOSZ);
 			musb->context.index_regs[i].rxfifosz =
-					musb_read_rxfifosz(musb_base);
+					musb_readb(musb_base, MUSB_RXFIFOSZ);
 		}
 
 		musb->context.index_regs[i].txtype =
@@ -2564,7 +2582,7 @@ static void musb_restore_context(struct musb *musb)
 
 	musb_writew(musb_base, MUSB_FRAME, musb->context.frame);
 	musb_writeb(musb_base, MUSB_TESTMODE, musb->context.testmode);
-	musb_write_ulpi_buscontrol(musb->mregs, musb->context.busctl);
+	musb_writeb(musb_base, MUSB_ULPI_BUSCONTROL, musb->context.busctl);
 
 	/* Don't affect SUSPENDM/RESUME bits in POWER reg */
 	power = musb_readb(musb_base, MUSB_POWER);
@@ -2601,13 +2619,13 @@ static void musb_restore_context(struct musb *musb)
 			musb->context.index_regs[i].rxcsr);
 
 		if (musb->dyn_fifo) {
-			musb_write_txfifosz(musb_base,
+			musb_writeb(musb_base, MUSB_TXFIFOSZ,
 				musb->context.index_regs[i].txfifosz);
-			musb_write_rxfifosz(musb_base,
+			musb_writeb(musb_base, MUSB_RXFIFOSZ,
 				musb->context.index_regs[i].rxfifosz);
-			musb_write_txfifoadd(musb_base,
+			musb_writew(musb_base, MUSB_TXFIFOADD,
 				musb->context.index_regs[i].txfifoadd);
-			musb_write_rxfifoadd(musb_base,
+			musb_writew(musb_base, MUSB_RXFIFOADD,
 				musb->context.index_regs[i].rxfifoadd);
 		}
 
@@ -2657,7 +2675,7 @@ static int musb_suspend(struct device *dev)
 		;
 	musb->flush_irq_work = false;
 
-	if (!(musb->io.quirks & MUSB_PRESERVE_SESSION))
+	if (!(musb->ops->quirks & MUSB_PRESERVE_SESSION))
 		musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
 
 	WARN_ON(!list_empty(&musb->pending_list));
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index 8a74cb2907f8..04203b7126d5 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -53,12 +53,6 @@ struct musb_ep;
 #define is_peripheral_active(m)		(!(m)->is_host)
 #define is_host_active(m)		((m)->is_host)
 
-enum {
-	MUSB_PORT_MODE_HOST	= 1,
-	MUSB_PORT_MODE_GADGET,
-	MUSB_PORT_MODE_DUAL_ROLE,
-};
-
 /****************************** CONSTANTS ********************************/
 
 #ifndef MUSB_C_NUM_EPS
@@ -127,8 +121,6 @@ struct musb_io;
  * @writeb:	write 8 bits
  * @readw:	read 16 bits
  * @writew:	write 16 bits
- * @readl:	read 32 bits
- * @writel:	write 32 bits
  * @read_fifo:	reads the fifo
  * @write_fifo:	writes to fifo
  * @dma_init:	platform specific dma init function
@@ -140,7 +132,6 @@ struct musb_io;
  * @recover:	platform-specific babble recovery
  * @vbus_status: returns vbus status if possible
  * @set_vbus:	forces vbus status
- * @adjust_channel_params: pre check for standard dma channel_program func
  * @pre_root_reset_end: called before the root usb port reset flag gets cleared
  * @post_root_reset_end: called after the root usb port reset flag gets cleared
  * @phy_callback: optional callback function for the phy to call
@@ -174,8 +165,6 @@ struct musb_platform_ops {
 	void	(*writeb)(void __iomem *addr, unsigned offset, u8 data);
 	u16	(*readw)(const void __iomem *addr, unsigned offset);
 	void	(*writew)(void __iomem *addr, unsigned offset, u16 data);
-	u32	(*readl)(const void __iomem *addr, unsigned offset);
-	void	(*writel)(void __iomem *addr, unsigned offset, u32 data);
 	void	(*read_fifo)(struct musb_hw_ep *hw_ep, u16 len, u8 *buf);
 	void	(*write_fifo)(struct musb_hw_ep *hw_ep, u16 len, const u8 *buf);
 	struct dma_controller *
@@ -188,9 +177,6 @@ struct musb_platform_ops {
 	int	(*vbus_status)(struct musb *musb);
 	void	(*set_vbus)(struct musb *musb, int on);
 
-	int	(*adjust_channel_params)(struct dma_channel *channel,
-				u16 packet_sz, u8 *mode,
-				dma_addr_t *dma_addr, u32 *len);
 	void	(*pre_root_reset_end)(struct musb *musb);
 	void	(*post_root_reset_end)(struct musb *musb);
 	int	(*phy_callback)(enum musb_vbus_id_status status);
@@ -359,7 +345,7 @@ struct musb {
 
 	u8			min_power;	/* vbus for periph, in mA/2 */
 
-	int			port_mode;	/* MUSB_PORT_MODE_* */
+	enum musb_mode		port_mode;
 	bool			session;
 	unsigned long		quirk_retries;
 	bool			is_host;
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index d0dd4f470bbe..7fbb8a307145 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -614,7 +614,7 @@ static int cppi41_dma_channel_abort(struct dma_channel *channel)
 	}
 
 	/* DA8xx Advisory 2.3.27: wait 250 ms before to start the teardown */
-	if (musb->io.quirks & MUSB_DA8XX)
+	if (musb->ops->quirks & MUSB_DA8XX)
 		mdelay(250);
 
 	tdbit = 1 << cppi41_channel->port_num;
@@ -773,7 +773,7 @@ cppi41_dma_controller_create(struct musb *musb, void __iomem *base)
 	controller->controller.is_compatible = cppi41_is_compatible;
 	controller->controller.musb = musb;
 
-	if (musb->io.quirks & MUSB_DA8XX) {
+	if (musb->ops->quirks & MUSB_DA8XX) {
 		controller->tdown_reg = DA8XX_USB_TEARDOWN;
 		controller->autoreq_reg = DA8XX_USB_AUTOREQ;
 		controller->set_dma_mode = da8xx_set_dma_mode;
diff --git a/drivers/usb/musb/musb_debug.h b/drivers/usb/musb/musb_debug.h
index 5e0f079dde21..c444a80fe1da 100644
--- a/drivers/usb/musb/musb_debug.h
+++ b/drivers/usb/musb/musb_debug.h
@@ -20,12 +20,11 @@
 void musb_dbg(struct musb *musb, const char *fmt, ...);
 
 #ifdef CONFIG_DEBUG_FS
-int musb_init_debugfs(struct musb *musb);
+void musb_init_debugfs(struct musb *musb);
 void musb_exit_debugfs(struct musb *musb);
 #else
-static inline int musb_init_debugfs(struct musb *musb)
+static inline void musb_init_debugfs(struct musb *musb)
 {
-	return 0;
 }
 static inline void musb_exit_debugfs(struct musb *musb)
 {
diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c
index e2050cac3eae..f42858e2b54c 100644
--- a/drivers/usb/musb/musb_debugfs.c
+++ b/drivers/usb/musb/musb_debugfs.c
@@ -321,48 +321,18 @@ static const struct file_operations musb_softconnect_fops = {
 	.release		= single_release,
 };
 
-int musb_init_debugfs(struct musb *musb)
+void musb_init_debugfs(struct musb *musb)
 {
-	struct dentry		*root;
-	struct dentry		*file;
-	int			ret;
+	struct dentry *root;
 
 	root = debugfs_create_dir(dev_name(musb->controller), NULL);
-	if (!root) {
-		ret = -ENOMEM;
-		goto err0;
-	}
-
-	file = debugfs_create_file("regdump", S_IRUGO, root, musb,
-			&musb_regdump_fops);
-	if (!file) {
-		ret = -ENOMEM;
-		goto err1;
-	}
-
-	file = debugfs_create_file("testmode", S_IRUGO | S_IWUSR,
-			root, musb, &musb_test_mode_fops);
-	if (!file) {
-		ret = -ENOMEM;
-		goto err1;
-	}
-
-	file = debugfs_create_file("softconnect", S_IRUGO | S_IWUSR,
-			root, musb, &musb_softconnect_fops);
-	if (!file) {
-		ret = -ENOMEM;
-		goto err1;
-	}
-
 	musb->debugfs_root = root;
 
-	return 0;
-
-err1:
-	debugfs_remove_recursive(root);
-
-err0:
-	return ret;
+	debugfs_create_file("regdump", S_IRUGO, root, musb, &musb_regdump_fops);
+	debugfs_create_file("testmode", S_IRUGO | S_IWUSR, root, musb,
+			    &musb_test_mode_fops);
+	debugfs_create_file("softconnect", S_IRUGO | S_IWUSR, root, musb,
+			    &musb_softconnect_fops);
 }
 
 void /* __init_or_exit */ musb_exit_debugfs(struct musb *musb)
diff --git a/drivers/usb/musb/musb_dma.h b/drivers/usb/musb/musb_dma.h
index 0fc8cd0c2a5c..8f60271c0a9d 100644
--- a/drivers/usb/musb/musb_dma.h
+++ b/drivers/usb/musb/musb_dma.h
@@ -44,31 +44,31 @@ struct musb_hw_ep;
 #endif
 
 #ifdef CONFIG_USB_UX500_DMA
-#define musb_dma_ux500(musb)		(musb->io.quirks & MUSB_DMA_UX500)
+#define musb_dma_ux500(musb)		(musb->ops->quirks & MUSB_DMA_UX500)
 #else
 #define musb_dma_ux500(musb)		0
 #endif
 
 #ifdef CONFIG_USB_TI_CPPI41_DMA
-#define musb_dma_cppi41(musb)		(musb->io.quirks & MUSB_DMA_CPPI41)
+#define musb_dma_cppi41(musb)		(musb->ops->quirks & MUSB_DMA_CPPI41)
 #else
 #define musb_dma_cppi41(musb)		0
 #endif
 
 #ifdef CONFIG_USB_TI_CPPI_DMA
-#define musb_dma_cppi(musb)		(musb->io.quirks & MUSB_DMA_CPPI)
+#define musb_dma_cppi(musb)		(musb->ops->quirks & MUSB_DMA_CPPI)
 #else
 #define musb_dma_cppi(musb)		0
 #endif
 
 #ifdef CONFIG_USB_TUSB_OMAP_DMA
-#define tusb_dma_omap(musb)		(musb->io.quirks & MUSB_DMA_TUSB_OMAP)
+#define tusb_dma_omap(musb)		(musb->ops->quirks & MUSB_DMA_TUSB_OMAP)
 #else
 #define tusb_dma_omap(musb)		0
 #endif
 
 #ifdef CONFIG_USB_INVENTRA_DMA
-#define musb_dma_inventra(musb)		(musb->io.quirks & MUSB_DMA_INVENTRA)
+#define musb_dma_inventra(musb)		(musb->ops->quirks & MUSB_DMA_INVENTRA)
 #else
 #define musb_dma_inventra(musb)		0
 #endif
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 05a679d5e3a2..fb871eabcc10 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -183,7 +183,7 @@ static void dsps_musb_enable(struct musb *musb)
 	musb_writel(reg_base, wrp->coreintr_set, coremask);
 	/* start polling for ID change in dual-role idle mode */
 	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE &&
-			musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
+			musb->port_mode == MUSB_OTG)
 		dsps_mod_timer(glue, -1);
 }
 
@@ -231,7 +231,7 @@ static int dsps_check_status(struct musb *musb, void *unused)
 		break;
 	case OTG_STATE_A_WAIT_BCON:
 		/* keep VBUS on for host-only mode */
-		if (musb->port_mode == MUSB_PORT_MODE_HOST) {
+		if (musb->port_mode == MUSB_HOST) {
 			dsps_mod_timer_optional(glue);
 			break;
 		}
@@ -360,13 +360,11 @@ static irqreturn_t dsps_interrupt(int irq, void *hci)
 			WARNING("VBUS error workaround (delay coming)\n");
 		} else if (drvvbus) {
 			MUSB_HST_MODE(musb);
-			musb->xceiv->otg->default_a = 1;
 			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			dsps_mod_timer_optional(glue);
 		} else {
 			musb->is_active = 0;
 			MUSB_DEV_MODE(musb);
-			musb->xceiv->otg->default_a = 0;
 			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		}
 
@@ -401,24 +399,17 @@ out:
 static int dsps_musb_dbg_init(struct musb *musb, struct dsps_glue *glue)
 {
 	struct dentry *root;
-	struct dentry *file;
 	char buf[128];
 
 	sprintf(buf, "%s.dsps", dev_name(musb->controller));
 	root = debugfs_create_dir(buf, NULL);
-	if (!root)
-		return -ENOMEM;
 	glue->dbgfs_root = root;
 
 	glue->regset.regs = dsps_musb_regs;
 	glue->regset.nregs = ARRAY_SIZE(dsps_musb_regs);
 	glue->regset.base = musb->ctrl_base;
 
-	file = debugfs_create_regset32("regdump", S_IRUGO, root, &glue->regset);
-	if (!file) {
-		debugfs_remove_recursive(root);
-		return -ENOMEM;
-	}
+	debugfs_create_regset32("regdump", S_IRUGO, root, &glue->regset);
 	return 0;
 }
 
@@ -451,7 +442,6 @@ static int dsps_musb_init(struct musb *musb)
 	if (!rev)
 		return -ENODEV;
 
-	usb_phy_init(musb->xceiv);
 	if (IS_ERR(musb->phy))  {
 		musb->phy = NULL;
 	} else {
@@ -501,7 +491,6 @@ static int dsps_musb_exit(struct musb *musb)
 	struct dsps_glue *glue = dev_get_drvdata(dev->parent);
 
 	del_timer_sync(&musb->dev_timer);
-	usb_phy_shutdown(musb->xceiv);
 	phy_power_off(musb->phy);
 	phy_exit(musb->phy);
 	debugfs_remove_recursive(glue->dbgfs_root);
@@ -731,25 +720,6 @@ static int get_int_prop(struct device_node *dn, const char *s)
 	return val;
 }
 
-static int get_musb_port_mode(struct device *dev)
-{
-	enum usb_dr_mode mode;
-
-	mode = usb_get_dr_mode(dev);
-	switch (mode) {
-	case USB_DR_MODE_HOST:
-		return MUSB_PORT_MODE_HOST;
-
-	case USB_DR_MODE_PERIPHERAL:
-		return MUSB_PORT_MODE_GADGET;
-
-	case USB_DR_MODE_UNKNOWN:
-	case USB_DR_MODE_OTG:
-	default:
-		return MUSB_PORT_MODE_DUAL_ROLE;
-	}
-}
-
 static int dsps_create_musb_pdev(struct dsps_glue *glue,
 		struct platform_device *parent)
 {
@@ -788,6 +758,7 @@ static int dsps_create_musb_pdev(struct dsps_glue *glue,
 	musb->dev.parent		= dev;
 	musb->dev.dma_mask		= &musb_dmamask;
 	musb->dev.coherent_dma_mask	= musb_dmamask;
+	device_set_of_node_from_dev(&musb->dev, &parent->dev);
 
 	glue->musb = musb;
 
@@ -809,7 +780,7 @@ static int dsps_create_musb_pdev(struct dsps_glue *glue,
 	config->num_eps = get_int_prop(dn, "mentor,num-eps");
 	config->ram_bits = get_int_prop(dn, "mentor,ram-bits");
 	config->host_port_deassert_reset_at_resume = 1;
-	pdata.mode = get_musb_port_mode(dev);
+	pdata.mode = musb_get_mode(dev);
 	/* DT keeps this entry in mA, musb expects it as per USB spec */
 	pdata.power = get_int_prop(dn, "mentor,power") / 2;
 
@@ -1049,7 +1020,7 @@ static int dsps_resume(struct device *dev)
 	musb_writel(mbase, wrp->tx_mode, glue->context.tx_mode);
 	musb_writel(mbase, wrp->rx_mode, glue->context.rx_mode);
 	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE &&
-	    musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
+	    musb->port_mode == MUSB_OTG)
 		dsps_mod_timer(glue, -1);
 
 	pm_runtime_put(dev);
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index e564695c6c8d..eae8b1b1b45b 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -417,7 +417,6 @@ void musb_g_tx(struct musb *musb, u8 epnum)
 	req = next_request(musb_ep);
 	request = &req->request;
 
-	trace_musb_req_tx(req);
 	csr = musb_readw(epio, MUSB_TXCSR);
 	musb_dbg(musb, "<== %s, txcsr %04x", musb_ep->end_point.name, csr);
 
@@ -456,6 +455,8 @@ void musb_g_tx(struct musb *musb, u8 epnum)
 		u8	is_dma = 0;
 		bool	short_packet = false;
 
+		trace_musb_req_tx(req);
+
 		if (dma && (csr & MUSB_TXCSR_DMAENAB)) {
 			is_dma = 1;
 			csr |= MUSB_TXCSR_P_WZC_BITS;
@@ -1793,16 +1794,12 @@ int musb_gadget_setup(struct musb *musb)
 	musb->g.speed = USB_SPEED_UNKNOWN;
 
 	MUSB_DEV_MODE(musb);
-	musb->xceiv->otg->default_a = 0;
 	musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 
 	/* this "gadget" abstracts/virtualizes the controller */
 	musb->g.name = musb_driver_name;
-#if IS_ENABLED(CONFIG_USB_MUSB_DUAL_ROLE)
-	musb->g.is_otg = 1;
-#elif IS_ENABLED(CONFIG_USB_MUSB_GADGET)
+	/* don't support otg protocols */
 	musb->g.is_otg = 0;
-#endif
 	INIT_DELAYED_WORK(&musb->gadget_work, musb_gadget_work);
 	musb_g_init_endpoints(musb);
 
@@ -1822,7 +1819,7 @@ err:
 
 void musb_gadget_cleanup(struct musb *musb)
 {
-	if (musb->port_mode == MUSB_PORT_MODE_HOST)
+	if (musb->port_mode == MUSB_HOST)
 		return;
 
 	cancel_delayed_work_sync(&musb->gadget_work);
diff --git a/drivers/usb/musb/musb_gadget.h b/drivers/usb/musb/musb_gadget.h
index 9c34aca06db6..d02663660813 100644
--- a/drivers/usb/musb/musb_gadget.h
+++ b/drivers/usb/musb/musb_gadget.h
@@ -60,10 +60,7 @@ struct musb_request {
 	enum buffer_map_state map_state;
 };
 
-static inline struct musb_request *to_musb_request(struct usb_request *req)
-{
-	return req ? container_of(req, struct musb_request, request) : NULL;
-}
+#define to_musb_request(r)	container_of((r), struct musb_request, request)
 
 extern struct usb_request *
 musb_alloc_request(struct usb_ep *ep, gfp_t gfp_flags);
@@ -99,10 +96,7 @@ struct musb_ep {
 	u8				hb_mult;
 };
 
-static inline struct musb_ep *to_musb_ep(struct usb_ep *ep)
-{
-	return ep ? container_of(ep, struct musb_ep, end_point) : NULL;
-}
+#define to_musb_ep(ep)	container_of((ep), struct musb_ep, end_point)
 
 static inline struct musb_request *next_request(struct musb_ep *ep)
 {
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 3a8451a15f7f..8000c7c02f79 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -990,7 +990,9 @@ static void musb_bulk_nak_timeout(struct musb *musb, struct musb_hw_ep *ep,
 			/* set tx_reinit and schedule the next qh */
 			ep->tx_reinit = 1;
 		}
-		musb_start_urb(musb, is_in, next_qh);
+
+		if (next_qh)
+			musb_start_urb(musb, is_in, next_qh);
 	}
 }
 
@@ -2522,8 +2524,11 @@ static int musb_bus_suspend(struct usb_hcd *hcd)
 {
 	struct musb	*musb = hcd_to_musb(hcd);
 	u8		devctl;
+	int		ret;
 
-	musb_port_suspend(musb, true);
+	ret = musb_port_suspend(musb, true);
+	if (ret)
+		return ret;
 
 	if (!is_host_active(musb))
 		return 0;
@@ -2730,7 +2735,7 @@ int musb_host_alloc(struct musb *musb)
 
 void musb_host_cleanup(struct musb *musb)
 {
-	if (musb->port_mode == MUSB_PORT_MODE_GADGET)
+	if (musb->port_mode == MUSB_PERIPHERAL)
 		return;
 	usb_remove_hcd(musb->hcd);
 }
@@ -2745,15 +2750,16 @@ int musb_host_setup(struct musb *musb, int power_budget)
 	int ret;
 	struct usb_hcd *hcd = musb->hcd;
 
-	if (musb->port_mode == MUSB_PORT_MODE_HOST) {
+	if (musb->port_mode == MUSB_HOST) {
 		MUSB_HST_MODE(musb);
-		musb->xceiv->otg->default_a = 1;
 		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 	}
 	otg_set_host(musb->xceiv->otg, &hcd->self);
-	hcd->self.otg_port = 1;
+	/* don't support otg protocols */
+	hcd->self.otg_port = 0;
 	musb->xceiv->otg->host = &hcd->self;
 	hcd->power_budget = 2 * (power_budget ? : 250);
+	hcd->skip_phy_initialization = 1;
 
 	ret = usb_add_hcd(hcd, 0, 0);
 	if (ret < 0)
diff --git a/drivers/usb/musb/musb_host.h b/drivers/usb/musb/musb_host.h
index 72392bbcd0a4..2999845632ce 100644
--- a/drivers/usb/musb/musb_host.h
+++ b/drivers/usb/musb/musb_host.h
@@ -67,7 +67,7 @@ extern void musb_host_rx(struct musb *, u8);
 extern void musb_root_disconnect(struct musb *musb);
 extern void musb_host_resume_root_hub(struct musb *musb);
 extern void musb_host_poke_root_hub(struct musb *musb);
-extern void musb_port_suspend(struct musb *musb, bool do_suspend);
+extern int musb_port_suspend(struct musb *musb, bool do_suspend);
 extern void musb_port_reset(struct musb *musb, bool do_reset);
 extern void musb_host_finish_resume(struct work_struct *work);
 #else
@@ -99,7 +99,10 @@ static inline void musb_root_disconnect(struct musb *musb)	{}
 static inline void musb_host_resume_root_hub(struct musb *musb)	{}
 static inline void musb_host_poll_rh_status(struct musb *musb)	{}
 static inline void musb_host_poke_root_hub(struct musb *musb)	{}
-static inline void musb_port_suspend(struct musb *musb, bool do_suspend) {}
+static inline int musb_port_suspend(struct musb *musb, bool do_suspend)
+{
+	return 0;
+}
 static inline void musb_port_reset(struct musb *musb, bool do_reset) {}
 static inline void musb_host_finish_resume(struct work_struct *work) {}
 #endif
diff --git a/drivers/usb/musb/musb_io.h b/drivers/usb/musb/musb_io.h
index b7025b2e6e00..8058a58092cf 100644
--- a/drivers/usb/musb/musb_io.h
+++ b/drivers/usb/musb/musb_io.h
@@ -16,7 +16,6 @@
 
 /**
  * struct musb_io - IO functions for MUSB
- * @quirks:	platform specific flags
  * @ep_offset:	platform specific function to get end point offset
  * @ep_select:	platform specific function to select end point
  * @fifo_offset: platform specific function to get fifo offset
@@ -25,7 +24,6 @@
  * @busctl_offset: platform specific function to get busctl offset
  */
 struct musb_io {
-	u32	quirks;
 	u32	(*ep_offset)(u8 epnum, u16 offset);
 	void	(*ep_select)(void __iomem *mbase, u8 epnum);
 	u32	(*fifo_offset)(u8 epnum);
@@ -39,7 +37,7 @@ extern u8 (*musb_readb)(const void __iomem *addr, unsigned offset);
 extern void (*musb_writeb)(void __iomem *addr, unsigned offset, u8 data);
 extern u16 (*musb_readw)(const void __iomem *addr, unsigned offset);
 extern void (*musb_writew)(void __iomem *addr, unsigned offset, u16 data);
-extern u32 (*musb_readl)(const void __iomem *addr, unsigned offset);
-extern void (*musb_writel)(void __iomem *addr, unsigned offset, u32 data);
+extern u32 musb_readl(const void __iomem *addr, unsigned offset);
+extern void musb_writel(void __iomem *addr, unsigned offset, u32 data);
 
 #endif
diff --git a/drivers/usb/musb/musb_regs.h b/drivers/usb/musb/musb_regs.h
index 88466622c89f..5cd7264fc2cb 100644
--- a/drivers/usb/musb/musb_regs.h
+++ b/drivers/usb/musb/musb_regs.h
@@ -273,67 +273,12 @@
 #define MUSB_RXHUBADDR		0x06
 #define MUSB_RXHUBPORT		0x07
 
-static inline void musb_write_txfifosz(void __iomem *mbase, u8 c_size)
-{
-	musb_writeb(mbase, MUSB_TXFIFOSZ, c_size);
-}
-
-static inline void musb_write_txfifoadd(void __iomem *mbase, u16 c_off)
-{
-	musb_writew(mbase, MUSB_TXFIFOADD, c_off);
-}
-
-static inline void musb_write_rxfifosz(void __iomem *mbase, u8 c_size)
-{
-	musb_writeb(mbase, MUSB_RXFIFOSZ, c_size);
-}
-
-static inline void  musb_write_rxfifoadd(void __iomem *mbase, u16 c_off)
-{
-	musb_writew(mbase, MUSB_RXFIFOADD, c_off);
-}
-
-static inline void musb_write_ulpi_buscontrol(void __iomem *mbase, u8 val)
-{
-	musb_writeb(mbase, MUSB_ULPI_BUSCONTROL, val);
-}
-
-static inline u8 musb_read_txfifosz(void __iomem *mbase)
-{
-	return musb_readb(mbase, MUSB_TXFIFOSZ);
-}
-
-static inline u16 musb_read_txfifoadd(void __iomem *mbase)
-{
-	return musb_readw(mbase, MUSB_TXFIFOADD);
-}
-
-static inline u8 musb_read_rxfifosz(void __iomem *mbase)
-{
-	return musb_readb(mbase, MUSB_RXFIFOSZ);
-}
-
-static inline u16  musb_read_rxfifoadd(void __iomem *mbase)
-{
-	return musb_readw(mbase, MUSB_RXFIFOADD);
-}
-
-static inline u8 musb_read_ulpi_buscontrol(void __iomem *mbase)
-{
-	return musb_readb(mbase, MUSB_ULPI_BUSCONTROL);
-}
-
 static inline u8 musb_read_configdata(void __iomem *mbase)
 {
 	musb_writeb(mbase, MUSB_INDEX, 0);
 	return musb_readb(mbase, 0x10 + MUSB_CONFIGDATA);
 }
 
-static inline u16 musb_read_hwvers(void __iomem *mbase)
-{
-	return musb_readw(mbase, MUSB_HWVERS);
-}
-
 static inline void musb_write_rxfunaddr(struct musb *musb, u8 epnum,
 		u8 qh_addr_reg)
 {
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index 5165d2b07ade..a84ec27c4c12 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -48,14 +48,14 @@ void musb_host_finish_resume(struct work_struct *work)
 	spin_unlock_irqrestore(&musb->lock, flags);
 }
 
-void musb_port_suspend(struct musb *musb, bool do_suspend)
+int musb_port_suspend(struct musb *musb, bool do_suspend)
 {
 	struct usb_otg	*otg = musb->xceiv->otg;
 	u8		power;
 	void __iomem	*mbase = musb->mregs;
 
 	if (!is_host_active(musb))
-		return;
+		return 0;
 
 	/* NOTE:  this doesn't necessarily put PHY into low power mode,
 	 * turning off its clock; that's a function of PHY integration and
@@ -66,16 +66,20 @@ void musb_port_suspend(struct musb *musb, bool do_suspend)
 	if (do_suspend) {
 		int retries = 10000;
 
-		power &= ~MUSB_POWER_RESUME;
-		power |= MUSB_POWER_SUSPENDM;
-		musb_writeb(mbase, MUSB_POWER, power);
+		if (power & MUSB_POWER_RESUME)
+			return -EBUSY;
 
-		/* Needed for OPT A tests */
-		power = musb_readb(mbase, MUSB_POWER);
-		while (power & MUSB_POWER_SUSPENDM) {
+		if (!(power & MUSB_POWER_SUSPENDM)) {
+			power |= MUSB_POWER_SUSPENDM;
+			musb_writeb(mbase, MUSB_POWER, power);
+
+			/* Needed for OPT A tests */
 			power = musb_readb(mbase, MUSB_POWER);
-			if (retries-- < 1)
-				break;
+			while (power & MUSB_POWER_SUSPENDM) {
+				power = musb_readb(mbase, MUSB_POWER);
+				if (retries-- < 1)
+					break;
+			}
 		}
 
 		musb_dbg(musb, "Root port suspended, power %02x", power);
@@ -111,6 +115,7 @@ void musb_port_suspend(struct musb *musb, bool do_suspend)
 		schedule_delayed_work(&musb->finish_resume_work,
 				      msecs_to_jiffies(USB_RESUME_TIMEOUT));
 	}
+	return 0;
 }
 
 void musb_port_reset(struct musb *musb, bool do_reset)
@@ -249,7 +254,7 @@ static int musb_has_gadget(struct musb *musb)
 #ifdef CONFIG_USB_MUSB_HOST
 	return 1;
 #else
-	return musb->port_mode == MUSB_PORT_MODE_HOST;
+	return musb->port_mode == MUSB_HOST;
 #endif
 }
 
diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c
index 4389fc3422bd..a688f7f87829 100644
--- a/drivers/usb/musb/musbhsdma.c
+++ b/drivers/usb/musb/musbhsdma.c
@@ -10,7 +10,71 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include "musb_core.h"
-#include "musbhsdma.h"
+
+#define MUSB_HSDMA_BASE		0x200
+#define MUSB_HSDMA_INTR		(MUSB_HSDMA_BASE + 0)
+#define MUSB_HSDMA_CONTROL		0x4
+#define MUSB_HSDMA_ADDRESS		0x8
+#define MUSB_HSDMA_COUNT		0xc
+
+#define MUSB_HSDMA_CHANNEL_OFFSET(_bchannel, _offset)		\
+		(MUSB_HSDMA_BASE + (_bchannel << 4) + _offset)
+
+#define musb_read_hsdma_addr(mbase, bchannel)	\
+	musb_readl(mbase,	\
+		   MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_ADDRESS))
+
+#define musb_write_hsdma_addr(mbase, bchannel, addr) \
+	musb_writel(mbase, \
+		    MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_ADDRESS), \
+		    addr)
+
+#define musb_read_hsdma_count(mbase, bchannel)	\
+	musb_readl(mbase,	\
+		   MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT))
+
+#define musb_write_hsdma_count(mbase, bchannel, len) \
+	musb_writel(mbase, \
+		    MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT), \
+		    len)
+/* control register (16-bit): */
+#define MUSB_HSDMA_ENABLE_SHIFT		0
+#define MUSB_HSDMA_TRANSMIT_SHIFT	1
+#define MUSB_HSDMA_MODE1_SHIFT		2
+#define MUSB_HSDMA_IRQENABLE_SHIFT	3
+#define MUSB_HSDMA_ENDPOINT_SHIFT	4
+#define MUSB_HSDMA_BUSERROR_SHIFT	8
+#define MUSB_HSDMA_BURSTMODE_SHIFT	9
+#define MUSB_HSDMA_BURSTMODE		(3 << MUSB_HSDMA_BURSTMODE_SHIFT)
+#define MUSB_HSDMA_BURSTMODE_UNSPEC	0
+#define MUSB_HSDMA_BURSTMODE_INCR4	1
+#define MUSB_HSDMA_BURSTMODE_INCR8	2
+#define MUSB_HSDMA_BURSTMODE_INCR16	3
+
+#define MUSB_HSDMA_CHANNELS		8
+
+struct musb_dma_controller;
+
+struct musb_dma_channel {
+	struct dma_channel		channel;
+	struct musb_dma_controller	*controller;
+	u32				start_addr;
+	u32				len;
+	u16				max_packet_sz;
+	u8				idx;
+	u8				epnum;
+	u8				transmit;
+};
+
+struct musb_dma_controller {
+	struct dma_controller		controller;
+	struct musb_dma_channel		channel[MUSB_HSDMA_CHANNELS];
+	void				*private_data;
+	void __iomem			*base;
+	u8				channel_count;
+	u8				used_channels;
+	int				irq;
+};
 
 static void dma_channel_release(struct dma_channel *channel);
 
@@ -135,14 +199,6 @@ static int dma_channel_program(struct dma_channel *channel,
 	BUG_ON(channel->status == MUSB_DMA_STATUS_UNKNOWN ||
 		channel->status == MUSB_DMA_STATUS_BUSY);
 
-	/* Let targets check/tweak the arguments */
-	if (musb->ops->adjust_channel_params) {
-		int ret = musb->ops->adjust_channel_params(channel,
-			packet_sz, &mode, &dma_addr, &len);
-		if (ret)
-			return ret;
-	}
-
 	/*
 	 * The DMA engine in RTL1.8 and above cannot handle
 	 * DMA addresses that are not aligned to a 4 byte boundary.
diff --git a/drivers/usb/musb/musbhsdma.h b/drivers/usb/musb/musbhsdma.h
deleted file mode 100644
index 93665135aff1..000000000000
--- a/drivers/usb/musb/musbhsdma.h
+++ /dev/null
@@ -1,72 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * MUSB OTG driver - support for Mentor's DMA controller
- *
- * Copyright 2005 Mentor Graphics Corporation
- * Copyright (C) 2005-2007 by Texas Instruments
- */
-
-#define MUSB_HSDMA_BASE		0x200
-#define MUSB_HSDMA_INTR		(MUSB_HSDMA_BASE + 0)
-#define MUSB_HSDMA_CONTROL		0x4
-#define MUSB_HSDMA_ADDRESS		0x8
-#define MUSB_HSDMA_COUNT		0xc
-
-#define MUSB_HSDMA_CHANNEL_OFFSET(_bchannel, _offset)		\
-		(MUSB_HSDMA_BASE + (_bchannel << 4) + _offset)
-
-#define musb_read_hsdma_addr(mbase, bchannel)	\
-	musb_readl(mbase,	\
-		   MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_ADDRESS))
-
-#define musb_write_hsdma_addr(mbase, bchannel, addr) \
-	musb_writel(mbase, \
-		    MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_ADDRESS), \
-		    addr)
-
-#define musb_read_hsdma_count(mbase, bchannel)	\
-	musb_readl(mbase,	\
-		   MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT))
-
-#define musb_write_hsdma_count(mbase, bchannel, len) \
-	musb_writel(mbase, \
-		    MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT), \
-		    len)
-/* control register (16-bit): */
-#define MUSB_HSDMA_ENABLE_SHIFT		0
-#define MUSB_HSDMA_TRANSMIT_SHIFT	1
-#define MUSB_HSDMA_MODE1_SHIFT		2
-#define MUSB_HSDMA_IRQENABLE_SHIFT	3
-#define MUSB_HSDMA_ENDPOINT_SHIFT	4
-#define MUSB_HSDMA_BUSERROR_SHIFT	8
-#define MUSB_HSDMA_BURSTMODE_SHIFT	9
-#define MUSB_HSDMA_BURSTMODE		(3 << MUSB_HSDMA_BURSTMODE_SHIFT)
-#define MUSB_HSDMA_BURSTMODE_UNSPEC	0
-#define MUSB_HSDMA_BURSTMODE_INCR4	1
-#define MUSB_HSDMA_BURSTMODE_INCR8	2
-#define MUSB_HSDMA_BURSTMODE_INCR16	3
-
-#define MUSB_HSDMA_CHANNELS		8
-
-struct musb_dma_controller;
-
-struct musb_dma_channel {
-	struct dma_channel		channel;
-	struct musb_dma_controller	*controller;
-	u32				start_addr;
-	u32				len;
-	u16				max_packet_sz;
-	u8				idx;
-	u8				epnum;
-	u8				transmit;
-};
-
-struct musb_dma_controller {
-	struct dma_controller		controller;
-	struct musb_dma_channel		channel[MUSB_HSDMA_CHANNELS];
-	void				*private_data;
-	void __iomem			*base;
-	u8				channel_count;
-	u8				used_channels;
-	int				irq;
-};
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 5d705930ef47..b1dd81fb5f55 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -77,7 +77,6 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
 			otg_set_vbus(otg, 1);
 		} else {
 			musb->is_active = 1;
-			otg->default_a = 1;
 			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			devctl |= MUSB_DEVCTL_SESSION;
 			MUSB_HST_MODE(musb);
@@ -89,7 +88,6 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
 		 * jumping right to B_IDLE...
 		 */
 
-		otg->default_a = 0;
 		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		devctl &= ~MUSB_DEVCTL_SESSION;
 
@@ -148,14 +146,12 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 	struct musb_hdrc_platform_data *pdata =
 		dev_get_platdata(musb->controller);
 	struct omap_musb_board_data *data = pdata->board_data;
-	struct usb_otg *otg = musb->xceiv->otg;
 
 	pm_runtime_get_sync(musb->controller);
 	switch (glue->status) {
 	case MUSB_ID_GROUND:
 		dev_dbg(musb->controller, "ID GND\n");
 
-		otg->default_a = true;
 		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 		musb->xceiv->last_event = USB_EVENT_ID;
 		if (musb->gadget_driver) {
@@ -168,7 +164,6 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 	case MUSB_VBUS_VALID:
 		dev_dbg(musb->controller, "VBUS Connect\n");
 
-		otg->default_a = false;
 		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		musb->xceiv->last_event = USB_EVENT_VBUS;
 		omap_control_usb_set_mode(glue->control_otghs, USB_MODE_DEVICE);
@@ -239,21 +234,15 @@ static int omap2430_musb_init(struct musb *musb)
 	 * up through ULPI.  TWL4030-family PMICs include one,
 	 * which needs a driver, drivers aren't always needed.
 	 */
-	if (dev->parent->of_node) {
-		musb->phy = devm_phy_get(dev->parent, "usb2-phy");
-
-		/* We can't totally remove musb->xceiv as of now because
-		 * musb core uses xceiv.state and xceiv.otg. Once we have
-		 * a separate state machine to handle otg, these can be moved
-		 * out of xceiv and then we can start using the generic PHY
-		 * framework
-		 */
-		musb->xceiv = devm_usb_get_phy_by_phandle(dev->parent,
-		    "usb-phy", 0);
-	} else {
-		musb->xceiv = devm_usb_get_phy_dev(dev, 0);
-		musb->phy = devm_phy_get(dev, "usb");
-	}
+	musb->phy = devm_phy_get(dev->parent, "usb2-phy");
+
+	/* We can't totally remove musb->xceiv as of now because
+	 * musb core uses xceiv.state and xceiv.otg. Once we have
+	 * a separate state machine to handle otg, these can be moved
+	 * out of xceiv and then we can start using the generic PHY
+	 * framework
+	 */
+	musb->xceiv = devm_usb_get_phy_by_phandle(dev->parent, "usb-phy", 0);
 
 	if (IS_ERR(musb->xceiv)) {
 		status = PTR_ERR(musb->xceiv);
@@ -391,8 +380,13 @@ static int omap2430_probe(struct platform_device *pdev)
 	struct omap2430_glue		*glue;
 	struct device_node		*np = pdev->dev.of_node;
 	struct musb_hdrc_config		*config;
+	struct device_node		*control_node;
+	struct platform_device		*control_pdev;
 	int				ret = -ENOMEM, val;
 
+	if (!np)
+		return -ENODEV;
+
 	glue = devm_kzalloc(&pdev->dev, sizeof(*glue), GFP_KERNEL);
 	if (!glue)
 		goto err0;
@@ -412,47 +406,43 @@ static int omap2430_probe(struct platform_device *pdev)
 	glue->status			= MUSB_UNKNOWN;
 	glue->control_otghs = ERR_PTR(-ENODEV);
 
-	if (np) {
-		struct device_node *control_node;
-		struct platform_device *control_pdev;
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		goto err2;
 
-		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata)
-			goto err2;
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto err2;
 
-		data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
-		if (!data)
-			goto err2;
+	config = devm_kzalloc(&pdev->dev, sizeof(*config), GFP_KERNEL);
+	if (!config)
+		goto err2;
 
-		config = devm_kzalloc(&pdev->dev, sizeof(*config), GFP_KERNEL);
-		if (!config)
+	of_property_read_u32(np, "mode", (u32 *)&pdata->mode);
+	of_property_read_u32(np, "interface-type",
+			(u32 *)&data->interface_type);
+	of_property_read_u32(np, "num-eps", (u32 *)&config->num_eps);
+	of_property_read_u32(np, "ram-bits", (u32 *)&config->ram_bits);
+	of_property_read_u32(np, "power", (u32 *)&pdata->power);
+
+	ret = of_property_read_u32(np, "multipoint", &val);
+	if (!ret && val)
+		config->multipoint = true;
+
+	pdata->board_data	= data;
+	pdata->config		= config;
+
+	control_node = of_parse_phandle(np, "ctrl-module", 0);
+	if (control_node) {
+		control_pdev = of_find_device_by_node(control_node);
+		if (!control_pdev) {
+			dev_err(&pdev->dev, "Failed to get control device\n");
+			ret = -EINVAL;
 			goto err2;
-
-		of_property_read_u32(np, "mode", (u32 *)&pdata->mode);
-		of_property_read_u32(np, "interface-type",
-						(u32 *)&data->interface_type);
-		of_property_read_u32(np, "num-eps", (u32 *)&config->num_eps);
-		of_property_read_u32(np, "ram-bits", (u32 *)&config->ram_bits);
-		of_property_read_u32(np, "power", (u32 *)&pdata->power);
-
-		ret = of_property_read_u32(np, "multipoint", &val);
-		if (!ret && val)
-			config->multipoint = true;
-
-		pdata->board_data	= data;
-		pdata->config		= config;
-
-		control_node = of_parse_phandle(np, "ctrl-module", 0);
-		if (control_node) {
-			control_pdev = of_find_device_by_node(control_node);
-			if (!control_pdev) {
-				dev_err(&pdev->dev, "Failed to get control device\n");
-				ret = -EINVAL;
-				goto err2;
-			}
-			glue->control_otghs = &control_pdev->dev;
 		}
+		glue->control_otghs = &control_pdev->dev;
 	}
+
 	pdata->platform_ops		= &omap2430_ops;
 
 	platform_set_drvdata(pdev, glue);
diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c
index 2d201219ecff..832a41f9ee7d 100644
--- a/drivers/usb/musb/sunxi.c
+++ b/drivers/usb/musb/sunxi.c
@@ -105,13 +105,11 @@ static void sunxi_musb_work(struct work_struct *work)
 		devctl = readb(musb->mregs + SUNXI_MUSB_DEVCTL);
 		if (test_bit(SUNXI_MUSB_FL_HOSTMODE, &glue->flags)) {
 			set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
-			musb->xceiv->otg->default_a = 1;
 			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			MUSB_HST_MODE(musb);
 			devctl |= MUSB_DEVCTL_SESSION;
 		} else {
 			clear_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
-			musb->xceiv->otg->default_a = 0;
 			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			MUSB_DEV_MODE(musb);
 			devctl &= ~MUSB_DEVCTL_SESSION;
@@ -347,7 +345,7 @@ static int sunxi_musb_set_mode(struct musb *musb, u8 mode)
 	if (glue->phy_mode == new_mode)
 		return 0;
 
-	if (musb->port_mode != MUSB_PORT_MODE_DUAL_ROLE) {
+	if (musb->port_mode != MUSB_OTG) {
 		dev_err(musb->controller->parent,
 			"Error changing modes is only supported in dual role mode\n");
 		return -EINVAL;
@@ -651,10 +649,8 @@ static const struct musb_hdrc_config sunxi_musb_hdrc_config = {
 	.fifo_cfg_size  = ARRAY_SIZE(sunxi_musb_mode_cfg),
 	.multipoint	= true,
 	.dyn_fifo	= true,
-	.soft_con       = true,
 	.num_eps	= SUNXI_MUSB_MAX_EP_NUM,
 	.ram_bits	= SUNXI_MUSB_RAM_BITS,
-	.dma		= 0,
 };
 
 static struct musb_hdrc_config sunxi_musb_hdrc_config_h3 = {
@@ -662,10 +658,8 @@ static struct musb_hdrc_config sunxi_musb_hdrc_config_h3 = {
 	.fifo_cfg_size  = ARRAY_SIZE(sunxi_musb_mode_cfg_h3),
 	.multipoint	= true,
 	.dyn_fifo	= true,
-	.soft_con       = true,
 	.num_eps	= SUNXI_MUSB_MAX_EP_NUM_H3,
 	.ram_bits	= SUNXI_MUSB_RAM_BITS,
-	.dma		= 0,
 };
 
 
@@ -690,19 +684,19 @@ static int sunxi_musb_probe(struct platform_device *pdev)
 	switch (usb_get_dr_mode(&pdev->dev)) {
 #if defined CONFIG_USB_MUSB_DUAL_ROLE || defined CONFIG_USB_MUSB_HOST
 	case USB_DR_MODE_HOST:
-		pdata.mode = MUSB_PORT_MODE_HOST;
+		pdata.mode = MUSB_HOST;
 		glue->phy_mode = PHY_MODE_USB_HOST;
 		break;
 #endif
 #if defined CONFIG_USB_MUSB_DUAL_ROLE || defined CONFIG_USB_MUSB_GADGET
 	case USB_DR_MODE_PERIPHERAL:
-		pdata.mode = MUSB_PORT_MODE_GADGET;
+		pdata.mode = MUSB_PERIPHERAL;
 		glue->phy_mode = PHY_MODE_USB_DEVICE;
 		break;
 #endif
 #ifdef CONFIG_USB_MUSB_DUAL_ROLE
 	case USB_DR_MODE_OTG:
-		pdata.mode = MUSB_PORT_MODE_DUAL_ROLE;
+		pdata.mode = MUSB_OTG;
 		glue->phy_mode = PHY_MODE_USB_OTG;
 		break;
 #endif
diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c
index 27b4a77a9e23..73538d1d0524 100644
--- a/drivers/usb/musb/ux500.c
+++ b/drivers/usb/musb/ux500.c
@@ -62,7 +62,6 @@ static void ux500_musb_set_vbus(struct musb *musb, int is_on)
 
 		} else {
 			musb->is_active = 1;
-			musb->xceiv->otg->default_a = 1;
 			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			devctl |= MUSB_DEVCTL_SESSION;
 			MUSB_HST_MODE(musb);
@@ -73,7 +72,6 @@ static void ux500_musb_set_vbus(struct musb *musb, int is_on)
 		/* NOTE: we're skipping A_WAIT_VFALL -> A_IDLE and jumping
 		 * right to B_IDLE...
 		 */
-		musb->xceiv->otg->default_a = 0;
 		devctl &= ~MUSB_DEVCTL_SESSION;
 		MUSB_DEV_MODE(musb);
 	}
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 0f8ab981d572..d7312eed6088 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -159,6 +159,16 @@ config USB_MXS_PHY
 
 	  MXS Phy is used by some of the i.MX SoCs, for example imx23/28/6x.
 
+config USB_TEGRA_PHY
+	tristate "NVIDIA Tegra USB PHY Driver"
+	depends on ARCH_TEGRA
+	select USB_COMMON
+	select USB_PHY
+	select USB_ULPI
+	help
+	  This driver provides PHY support for the USB controllers found
+	  on NVIDIA Tegra SoC's.
+
 config USB_ULPI
 	bool "Generic ULPI Transceiver Driver"
 	depends on ARM || ARM64
diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile
index 25e579fb92b8..df1d99010079 100644
--- a/drivers/usb/phy/Makefile
+++ b/drivers/usb/phy/Makefile
@@ -16,7 +16,7 @@ obj-$(CONFIG_AM335X_CONTROL_USB)	+= phy-am335x-control.o
 obj-$(CONFIG_AM335X_PHY_USB)		+= phy-am335x.o
 obj-$(CONFIG_OMAP_OTG)			+= phy-omap-otg.o
 obj-$(CONFIG_TWL6030_USB)		+= phy-twl6030-usb.o
-obj-$(CONFIG_USB_EHCI_TEGRA)		+= phy-tegra-usb.o
+obj-$(CONFIG_USB_TEGRA_PHY)		+= phy-tegra-usb.o
 obj-$(CONFIG_USB_GPIO_VBUS)		+= phy-gpio-vbus-usb.o
 obj-$(CONFIG_USB_ISP1301)		+= phy-isp1301.o
 obj-$(CONFIG_USB_MV_OTG)		+= phy-mv-usb.o
diff --git a/drivers/usb/phy/phy-am335x.c b/drivers/usb/phy/phy-am335x.c
index b36fa8b953d0..27bdb7222527 100644
--- a/drivers/usb/phy/phy-am335x.c
+++ b/drivers/usb/phy/phy-am335x.c
@@ -96,8 +96,7 @@ static int am335x_phy_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int am335x_phy_suspend(struct device *dev)
 {
-	struct platform_device	*pdev = to_platform_device(dev);
-	struct am335x_phy *am_phy = platform_get_drvdata(pdev);
+	struct am335x_phy *am_phy = dev_get_drvdata(dev);
 
 	/*
 	 * Enable phy wakeup only if dev->power.can_wakeup is true.
@@ -117,8 +116,7 @@ static int am335x_phy_suspend(struct device *dev)
 
 static int am335x_phy_resume(struct device *dev)
 {
-	struct platform_device	*pdev = to_platform_device(dev);
-	struct am335x_phy	*am_phy = platform_get_drvdata(pdev);
+	struct am335x_phy	*am_phy = dev_get_drvdata(dev);
 
 	phy_ctrl_power(am_phy->phy_ctrl, am_phy->id, am_phy->dr_mode, true);
 
diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c
index 0e8d23e51732..ea7ef1dc0b42 100644
--- a/drivers/usb/phy/phy-tegra-usb.c
+++ b/drivers/usb/phy/phy-tegra-usb.c
@@ -236,13 +236,83 @@ static void set_phcd(struct tegra_usb_phy *phy, bool enable)
 
 static int utmip_pad_open(struct tegra_usb_phy *phy)
 {
+	int ret;
+
 	phy->pad_clk = devm_clk_get(phy->u_phy.dev, "utmi-pads");
 	if (IS_ERR(phy->pad_clk)) {
-		pr_err("%s: can't get utmip pad clock\n", __func__);
-		return PTR_ERR(phy->pad_clk);
+		ret = PTR_ERR(phy->pad_clk);
+		dev_err(phy->u_phy.dev,
+			"Failed to get UTMIP pad clock: %d\n", ret);
+		return ret;
 	}
 
-	return 0;
+	phy->pad_rst = devm_reset_control_get_optional_shared(
+						phy->u_phy.dev, "utmi-pads");
+	if (IS_ERR(phy->pad_rst)) {
+		ret = PTR_ERR(phy->pad_rst);
+		dev_err(phy->u_phy.dev,
+			"Failed to get UTMI-pads reset: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(phy->pad_clk);
+	if (ret) {
+		dev_err(phy->u_phy.dev,
+			"Failed to enable UTMI-pads clock: %d\n", ret);
+		return ret;
+	}
+
+	spin_lock(&utmip_pad_lock);
+
+	ret = reset_control_deassert(phy->pad_rst);
+	if (ret) {
+		dev_err(phy->u_phy.dev,
+			"Failed to initialize UTMI-pads reset: %d\n", ret);
+		goto unlock;
+	}
+
+	ret = reset_control_assert(phy->pad_rst);
+	if (ret) {
+		dev_err(phy->u_phy.dev,
+			"Failed to assert UTMI-pads reset: %d\n", ret);
+		goto unlock;
+	}
+
+	udelay(1);
+
+	ret = reset_control_deassert(phy->pad_rst);
+	if (ret)
+		dev_err(phy->u_phy.dev,
+			"Failed to deassert UTMI-pads reset: %d\n", ret);
+unlock:
+	spin_unlock(&utmip_pad_lock);
+
+	clk_disable_unprepare(phy->pad_clk);
+
+	return ret;
+}
+
+static int utmip_pad_close(struct tegra_usb_phy *phy)
+{
+	int ret;
+
+	ret = clk_prepare_enable(phy->pad_clk);
+	if (ret) {
+		dev_err(phy->u_phy.dev,
+			"Failed to enable UTMI-pads clock: %d\n", ret);
+		return ret;
+	}
+
+	ret = reset_control_assert(phy->pad_rst);
+	if (ret)
+		dev_err(phy->u_phy.dev,
+			"Failed to assert UTMI-pads reset: %d\n", ret);
+
+	udelay(1);
+
+	clk_disable_unprepare(phy->pad_clk);
+
+	return ret;
 }
 
 static void utmip_pad_power_on(struct tegra_usb_phy *phy)
@@ -282,7 +352,7 @@ static int utmip_pad_power_off(struct tegra_usb_phy *phy)
 	void __iomem *base = phy->pad_regs;
 
 	if (!utmip_pad_count) {
-		pr_err("%s: utmip pad already powered off\n", __func__);
+		dev_err(phy->u_phy.dev, "UTMIP pad already powered off\n");
 		return -EINVAL;
 	}
 
@@ -338,7 +408,8 @@ static void utmi_phy_clk_disable(struct tegra_usb_phy *phy)
 		set_phcd(phy, true);
 
 	if (utmi_wait_register(base + USB_SUSP_CTRL, USB_PHY_CLK_VALID, 0) < 0)
-		pr_err("%s: timeout waiting for phy to stabilize\n", __func__);
+		dev_err(phy->u_phy.dev,
+			"Timeout waiting for PHY to stabilize on disable\n");
 }
 
 static void utmi_phy_clk_enable(struct tegra_usb_phy *phy)
@@ -370,7 +441,8 @@ static void utmi_phy_clk_enable(struct tegra_usb_phy *phy)
 
 	if (utmi_wait_register(base + USB_SUSP_CTRL, USB_PHY_CLK_VALID,
 						     USB_PHY_CLK_VALID))
-		pr_err("%s: timeout waiting for phy to stabilize\n", __func__);
+		dev_err(phy->u_phy.dev,
+			"Timeout waiting for PHY to stabilize on enable\n");
 }
 
 static int utmi_phy_power_on(struct tegra_usb_phy *phy)
@@ -617,15 +689,15 @@ static int ulpi_phy_power_on(struct tegra_usb_phy *phy)
 
 	ret = gpio_direction_output(phy->reset_gpio, 0);
 	if (ret < 0) {
-		dev_err(phy->u_phy.dev, "gpio %d not set to 0\n",
-			phy->reset_gpio);
+		dev_err(phy->u_phy.dev, "GPIO %d not set to 0: %d\n",
+			phy->reset_gpio, ret);
 		return ret;
 	}
 	msleep(5);
 	ret = gpio_direction_output(phy->reset_gpio, 1);
 	if (ret < 0) {
-		dev_err(phy->u_phy.dev, "gpio %d not set to 1\n",
-			phy->reset_gpio);
+		dev_err(phy->u_phy.dev, "GPIO %d not set to 1: %d\n",
+			phy->reset_gpio, ret);
 		return ret;
 	}
 
@@ -661,13 +733,13 @@ static int ulpi_phy_power_on(struct tegra_usb_phy *phy)
 	/* Fix VbusInvalid due to floating VBUS */
 	ret = usb_phy_io_write(phy->ulpi, 0x40, 0x08);
 	if (ret) {
-		pr_err("%s: ulpi write failed\n", __func__);
+		dev_err(phy->u_phy.dev, "ULPI write failed: %d\n", ret);
 		return ret;
 	}
 
 	ret = usb_phy_io_write(phy->ulpi, 0x80, 0x0B);
 	if (ret) {
-		pr_err("%s: ulpi write failed\n", __func__);
+		dev_err(phy->u_phy.dev, "ULPI write failed: %d\n", ret);
 		return ret;
 	}
 
@@ -694,6 +766,9 @@ static void tegra_usb_phy_close(struct tegra_usb_phy *phy)
 	if (!IS_ERR(phy->vbus))
 		regulator_disable(phy->vbus);
 
+	if (!phy->is_ulpi_phy)
+		utmip_pad_close(phy);
+
 	clk_disable_unprepare(phy->pll_u);
 }
 
@@ -728,28 +803,30 @@ static int ulpi_open(struct tegra_usb_phy *phy)
 
 	phy->clk = devm_clk_get(phy->u_phy.dev, "ulpi-link");
 	if (IS_ERR(phy->clk)) {
-		pr_err("%s: can't get ulpi clock\n", __func__);
-		return PTR_ERR(phy->clk);
+		err = PTR_ERR(phy->clk);
+		dev_err(phy->u_phy.dev, "Failed to get ULPI clock: %d\n", err);
+		return err;
 	}
 
 	err = devm_gpio_request(phy->u_phy.dev, phy->reset_gpio,
 		"ulpi_phy_reset_b");
 	if (err < 0) {
-		dev_err(phy->u_phy.dev, "request failed for gpio: %d\n",
-		       phy->reset_gpio);
+		dev_err(phy->u_phy.dev, "Request failed for GPIO %d: %d\n",
+			phy->reset_gpio, err);
 		return err;
 	}
 
 	err = gpio_direction_output(phy->reset_gpio, 0);
 	if (err < 0) {
-		dev_err(phy->u_phy.dev, "gpio %d direction not set to output\n",
-		       phy->reset_gpio);
+		dev_err(phy->u_phy.dev,
+			"GPIO %d direction not set to output: %d\n",
+			phy->reset_gpio, err);
 		return err;
 	}
 
 	phy->ulpi = otg_ulpi_create(&ulpi_viewport_access_ops, 0);
 	if (!phy->ulpi) {
-		dev_err(phy->u_phy.dev, "otg_ulpi_create returned NULL\n");
+		dev_err(phy->u_phy.dev, "Failed to create ULPI OTG\n");
 		err = -ENOMEM;
 		return err;
 	}
@@ -766,8 +843,10 @@ static int tegra_usb_phy_init(struct tegra_usb_phy *phy)
 
 	phy->pll_u = devm_clk_get(phy->u_phy.dev, "pll_u");
 	if (IS_ERR(phy->pll_u)) {
-		pr_err("Can't get pll_u clock\n");
-		return PTR_ERR(phy->pll_u);
+		err = PTR_ERR(phy->pll_u);
+		dev_err(phy->u_phy.dev,
+			"Failed to get pll_u clock: %d\n", err);
+		return err;
 	}
 
 	err = clk_prepare_enable(phy->pll_u);
@@ -782,7 +861,8 @@ static int tegra_usb_phy_init(struct tegra_usb_phy *phy)
 		}
 	}
 	if (!phy->freq) {
-		pr_err("invalid pll_u parent rate %ld\n", parent_rate);
+		dev_err(phy->u_phy.dev, "Invalid pll_u parent rate %ld\n",
+			parent_rate);
 		err = -EINVAL;
 		goto fail;
 	}
@@ -791,7 +871,7 @@ static int tegra_usb_phy_init(struct tegra_usb_phy *phy)
 		err = regulator_enable(phy->vbus);
 		if (err) {
 			dev_err(phy->u_phy.dev,
-				"failed to enable usb vbus regulator: %d\n",
+				"Failed to enable USB VBUS regulator: %d\n",
 				err);
 			goto fail;
 		}
@@ -855,7 +935,8 @@ static int read_utmi_param(struct platform_device *pdev, const char *param,
 	int err = of_property_read_u32(pdev->dev.of_node, param, &value);
 	*dest = (u8)value;
 	if (err < 0)
-		dev_err(&pdev->dev, "Failed to read USB UTMI parameter %s: %d\n",
+		dev_err(&pdev->dev,
+			"Failed to read USB UTMI parameter %s: %d\n",
 			param, err);
 	return err;
 }
@@ -871,14 +952,14 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy,
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	if (!res) {
-		dev_err(&pdev->dev, "Failed to get UTMI Pad regs\n");
+		dev_err(&pdev->dev, "Failed to get UTMI pad regs\n");
 		return  -ENXIO;
 	}
 
 	tegra_phy->pad_regs = devm_ioremap(&pdev->dev, res->start,
 		resource_size(res));
 	if (!tegra_phy->pad_regs) {
-		dev_err(&pdev->dev, "Failed to remap UTMI Pad regs\n");
+		dev_err(&pdev->dev, "Failed to remap UTMI pad regs\n");
 		return -ENOMEM;
 	}
 
@@ -1020,15 +1101,16 @@ static int tegra_usb_phy_probe(struct platform_device *pdev)
 		tegra_phy->reset_gpio =
 			of_get_named_gpio(np, "nvidia,phy-reset-gpio", 0);
 		if (!gpio_is_valid(tegra_phy->reset_gpio)) {
-			dev_err(&pdev->dev, "invalid gpio: %d\n",
-				tegra_phy->reset_gpio);
+			dev_err(&pdev->dev,
+				"Invalid GPIO: %d\n", tegra_phy->reset_gpio);
 			return tegra_phy->reset_gpio;
 		}
 		tegra_phy->config = NULL;
 		break;
 
 	default:
-		dev_err(&pdev->dev, "phy_type is invalid or unsupported\n");
+		dev_err(&pdev->dev, "phy_type %u is invalid or unsupported\n",
+			phy_type);
 		return -EINVAL;
 	}
 
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index bceb2c9988dd..0277f62739a2 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -27,7 +27,6 @@
 #define DEFAULT_ACA_CUR_MAX	5000
 
 static LIST_HEAD(phy_list);
-static LIST_HEAD(phy_bind_list);
 static DEFINE_SPINLOCK(phy_lock);
 
 struct phy_devm {
@@ -50,24 +49,6 @@ static struct usb_phy *__usb_find_phy(struct list_head *list,
 	return ERR_PTR(-ENODEV);
 }
 
-static struct usb_phy *__usb_find_phy_dev(struct device *dev,
-	struct list_head *list, u8 index)
-{
-	struct usb_phy_bind *phy_bind = NULL;
-
-	list_for_each_entry(phy_bind, list, list) {
-		if (!(strcmp(phy_bind->dev_name, dev_name(dev))) &&
-				phy_bind->index == index) {
-			if (phy_bind->phy)
-				return phy_bind->phy;
-			else
-				return ERR_PTR(-EPROBE_DEFER);
-		}
-	}
-
-	return ERR_PTR(-ENODEV);
-}
-
 static struct usb_phy *__of_usb_find_phy(struct device_node *node)
 {
 	struct usb_phy  *phy;
@@ -585,72 +566,6 @@ struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev,
 EXPORT_SYMBOL_GPL(devm_usb_get_phy_by_phandle);
 
 /**
- * usb_get_phy_dev - find the USB PHY
- * @dev - device that requests this phy
- * @index - the index of the phy
- *
- * Returns the phy driver, after getting a refcount to it; or
- * -ENODEV if there is no such phy.  The caller is responsible for
- * calling usb_put_phy() to release that count.
- *
- * For use by USB host and peripheral drivers.
- */
-struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index)
-{
-	struct usb_phy	*phy = NULL;
-	unsigned long	flags;
-
-	spin_lock_irqsave(&phy_lock, flags);
-
-	phy = __usb_find_phy_dev(dev, &phy_bind_list, index);
-	if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) {
-		dev_dbg(dev, "unable to find transceiver\n");
-		if (!IS_ERR(phy))
-			phy = ERR_PTR(-ENODEV);
-
-		goto err0;
-	}
-
-	get_device(phy->dev);
-
-err0:
-	spin_unlock_irqrestore(&phy_lock, flags);
-
-	return phy;
-}
-EXPORT_SYMBOL_GPL(usb_get_phy_dev);
-
-/**
- * devm_usb_get_phy_dev - find the USB PHY using device ptr and index
- * @dev - device that requests this phy
- * @index - the index of the phy
- *
- * Gets the phy using usb_get_phy_dev(), and associates a device with it using
- * devres. On driver detach, release function is invoked on the devres data,
- * then, devres data is freed.
- *
- * For use by USB host and peripheral drivers.
- */
-struct usb_phy *devm_usb_get_phy_dev(struct device *dev, u8 index)
-{
-	struct usb_phy **ptr, *phy;
-
-	ptr = devres_alloc(devm_usb_phy_release, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr)
-		return NULL;
-
-	phy = usb_get_phy_dev(dev, index);
-	if (!IS_ERR(phy)) {
-		*ptr = phy;
-		devres_add(dev, ptr);
-	} else
-		devres_free(ptr);
-
-	return phy;
-}
-EXPORT_SYMBOL_GPL(devm_usb_get_phy_dev);
-
-/**
  * devm_usb_put_phy - release the USB PHY
  * @dev - device that wants to release this phy
  * @phy - the phy returned by devm_usb_get_phy()
@@ -745,7 +660,6 @@ EXPORT_SYMBOL_GPL(usb_add_phy);
  */
 int usb_add_phy_dev(struct usb_phy *x)
 {
-	struct usb_phy_bind *phy_bind;
 	unsigned long flags;
 	int ret;
 
@@ -762,13 +676,9 @@ int usb_add_phy_dev(struct usb_phy *x)
 	ATOMIC_INIT_NOTIFIER_HEAD(&x->notifier);
 
 	spin_lock_irqsave(&phy_lock, flags);
-	list_for_each_entry(phy_bind, &phy_bind_list, list)
-		if (!(strcmp(phy_bind->phy_dev_name, dev_name(x->dev))))
-			phy_bind->phy = x;
-
 	list_add_tail(&x->head, &phy_list);
-
 	spin_unlock_irqrestore(&phy_lock, flags);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(usb_add_phy_dev);
@@ -782,54 +692,15 @@ EXPORT_SYMBOL_GPL(usb_add_phy_dev);
 void usb_remove_phy(struct usb_phy *x)
 {
 	unsigned long	flags;
-	struct usb_phy_bind *phy_bind;
 
 	spin_lock_irqsave(&phy_lock, flags);
-	if (x) {
-		list_for_each_entry(phy_bind, &phy_bind_list, list)
-			if (phy_bind->phy == x)
-				phy_bind->phy = NULL;
+	if (x)
 		list_del(&x->head);
-	}
 	spin_unlock_irqrestore(&phy_lock, flags);
 }
 EXPORT_SYMBOL_GPL(usb_remove_phy);
 
 /**
- * usb_bind_phy - bind the phy and the controller that uses the phy
- * @dev_name: the device name of the device that will bind to the phy
- * @index: index to specify the port number
- * @phy_dev_name: the device name of the phy
- *
- * Fills the phy_bind structure with the dev_name and phy_dev_name. This will
- * be used when the phy driver registers the phy and when the controller
- * requests this phy.
- *
- * To be used by platform specific initialization code.
- */
-int usb_bind_phy(const char *dev_name, u8 index,
-				const char *phy_dev_name)
-{
-	struct usb_phy_bind *phy_bind;
-	unsigned long flags;
-
-	phy_bind = kzalloc(sizeof(*phy_bind), GFP_KERNEL);
-	if (!phy_bind)
-		return -ENOMEM;
-
-	phy_bind->dev_name = dev_name;
-	phy_bind->phy_dev_name = phy_dev_name;
-	phy_bind->index = index;
-
-	spin_lock_irqsave(&phy_lock, flags);
-	list_add_tail(&phy_bind->list, &phy_bind_list);
-	spin_unlock_irqrestore(&phy_lock, flags);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(usb_bind_phy);
-
-/**
  * usb_phy_set_event - set event to phy event
  * @x: the phy returned by usb_get_phy();
  *
diff --git a/drivers/usb/renesas_usbhs/common.h b/drivers/usb/renesas_usbhs/common.h
index f619afeae2b8..6137f7942c05 100644
--- a/drivers/usb/renesas_usbhs/common.h
+++ b/drivers/usb/renesas_usbhs/common.h
@@ -276,7 +276,6 @@ struct usbhs_priv {
 	 */
 	struct usbhs_fifo_info fifo_info;
 
-	struct usb_phy *usb_phy;
 	struct phy *phy;
 };
 
diff --git a/drivers/usb/renesas_usbhs/rcar2.c b/drivers/usb/renesas_usbhs/rcar2.c
index 85a0e0933917..0027092b1118 100644
--- a/drivers/usb/renesas_usbhs/rcar2.c
+++ b/drivers/usb/renesas_usbhs/rcar2.c
@@ -8,7 +8,6 @@
 #include <linux/gpio.h>
 #include <linux/of_gpio.h>
 #include <linux/phy/phy.h>
-#include <linux/usb/phy.h>
 #include "common.h"
 #include "rcar2.h"
 
@@ -26,16 +25,6 @@ static int usbhs_rcar2_hardware_init(struct platform_device *pdev)
 		return 0;
 	}
 
-	if (IS_ENABLED(CONFIG_USB_PHY)) {
-		struct usb_phy *usb_phy = usb_get_phy_dev(&pdev->dev, 0);
-
-		if (IS_ERR(usb_phy))
-			return PTR_ERR(usb_phy);
-
-		priv->usb_phy = usb_phy;
-		return 0;
-	}
-
 	return -ENXIO;
 }
 
@@ -48,11 +37,6 @@ static int usbhs_rcar2_hardware_exit(struct platform_device *pdev)
 		priv->phy = NULL;
 	}
 
-	if (priv->usb_phy) {
-		usb_put_phy(priv->usb_phy);
-		priv->usb_phy = NULL;
-	}
-
 	return 0;
 }
 
@@ -75,19 +59,6 @@ static int usbhs_rcar2_power_ctrl(struct platform_device *pdev,
 		}
 	}
 
-	if (priv->usb_phy) {
-		if (enable) {
-			retval = usb_phy_init(priv->usb_phy);
-
-			if (!retval)
-				retval = usb_phy_set_suspend(priv->usb_phy, 0);
-		} else {
-			usb_phy_set_suspend(priv->usb_phy, 1);
-			usb_phy_shutdown(priv->usb_phy);
-			retval = 0;
-		}
-	}
-
 	return retval;
 }
 
diff --git a/drivers/usb/roles/intel-xhci-usb-role-switch.c b/drivers/usb/roles/intel-xhci-usb-role-switch.c
index de72eedb762e..1fb3dd0f1dfa 100644
--- a/drivers/usb/roles/intel-xhci-usb-role-switch.c
+++ b/drivers/usb/roles/intel-xhci-usb-role-switch.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/usb/role.h>
 
 /* register definition */
@@ -38,20 +39,6 @@ struct intel_xhci_usb_data {
 	void __iomem *base;
 };
 
-struct intel_xhci_acpi_match {
-	const char *hid;
-	int hrv;
-};
-
-/*
- * ACPI IDs for PMICs which do not support separate data and power role
- * detection (USB ACA detection for micro USB OTG), we allow userspace to
- * change the role manually on these.
- */
-static const struct intel_xhci_acpi_match allow_userspace_ctrl_ids[] = {
-	{ "INT33F4",  3 }, /* X-Powers AXP288 PMIC */
-};
-
 static int intel_xhci_usb_set_role(struct device *dev, enum usb_role role)
 {
 	struct intel_xhci_usb_data *data = dev_get_drvdata(dev);
@@ -70,6 +57,8 @@ static int intel_xhci_usb_set_role(struct device *dev, enum usb_role role)
 		return -EIO;
 	}
 
+	pm_runtime_get_sync(dev);
+
 	/* Set idpin value as requested */
 	val = readl(data->base + DUAL_ROLE_CFG0);
 	switch (role) {
@@ -98,13 +87,17 @@ static int intel_xhci_usb_set_role(struct device *dev, enum usb_role role)
 	/* Polling on CFG1 register to confirm mode switch.*/
 	do {
 		val = readl(data->base + DUAL_ROLE_CFG1);
-		if (!!(val & HOST_MODE) == (role == USB_ROLE_HOST))
+		if (!!(val & HOST_MODE) == (role == USB_ROLE_HOST)) {
+			pm_runtime_put(dev);
 			return 0;
+		}
 
 		/* Interval for polling is set to about 5 - 10 ms */
 		usleep_range(5000, 10000);
 	} while (time_before(jiffies, timeout));
 
+	pm_runtime_put(dev);
+
 	dev_warn(dev, "Timeout waiting for role-switch\n");
 	return -ETIMEDOUT;
 }
@@ -115,7 +108,9 @@ static enum usb_role intel_xhci_usb_get_role(struct device *dev)
 	enum usb_role role;
 	u32 val;
 
+	pm_runtime_get_sync(dev);
 	val = readl(data->base + DUAL_ROLE_CFG0);
+	pm_runtime_put(dev);
 
 	if (!(val & SW_IDPIN))
 		role = USB_ROLE_HOST;
@@ -127,9 +122,10 @@ static enum usb_role intel_xhci_usb_get_role(struct device *dev)
 	return role;
 }
 
-static struct usb_role_switch_desc sw_desc = {
+static const struct usb_role_switch_desc sw_desc = {
 	.set = intel_xhci_usb_set_role,
 	.get = intel_xhci_usb_get_role,
+	.allow_userspace_control = true,
 };
 
 static int intel_xhci_usb_probe(struct platform_device *pdev)
@@ -137,28 +133,27 @@ static int intel_xhci_usb_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct intel_xhci_usb_data *data;
 	struct resource *res;
-	int i;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
 	data->base = devm_ioremap_nocache(dev, res->start, resource_size(res));
 	if (!data->base)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(allow_userspace_ctrl_ids); i++)
-		if (acpi_dev_present(allow_userspace_ctrl_ids[i].hid, "1",
-				     allow_userspace_ctrl_ids[i].hrv))
-			sw_desc.allow_userspace_control = true;
-
 	platform_set_drvdata(pdev, data);
 
 	data->role_sw = usb_role_switch_register(dev, &sw_desc);
 	if (IS_ERR(data->role_sw))
 		return PTR_ERR(data->role_sw);
 
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	return 0;
 }
 
diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig
index a646820f5a78..533f127c30ad 100644
--- a/drivers/usb/serial/Kconfig
+++ b/drivers/usb/serial/Kconfig
@@ -62,6 +62,7 @@ config USB_SERIAL_SIMPLE
 		- Fundamental Software dongle.
 		- Google USB serial devices
 		- HP4x calculators
+		- Libtransistor USB console
 		- a number of Motorola phones
 		- Motorola Tetra devices
 		- Novatel Wireless GPS receivers
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 9e265eb92611..eb0195cf37dd 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -60,7 +60,8 @@ static int usb_serial_device_probe(struct device *dev)
 	}
 
 	minor = port->minor;
-	tty_dev = tty_register_device(usb_serial_tty_driver, minor, dev);
+	tty_dev = tty_port_register_device(&port->port, usb_serial_tty_driver,
+					   minor, dev);
 	if (IS_ERR(tty_dev)) {
 		retval = PTR_ERR(tty_dev);
 		goto err_port_remove;
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index de1e759dd512..eb6c26cbe579 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -214,6 +214,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x3195, 0xF190) }, /* Link Instruments MSO-19 */
 	{ USB_DEVICE(0x3195, 0xF280) }, /* Link Instruments MSO-28 */
 	{ USB_DEVICE(0x3195, 0xF281) }, /* Link Instruments MSO-28 */
+	{ USB_DEVICE(0x3923, 0x7A0B) }, /* National Instruments USB Serial Console */
 	{ USB_DEVICE(0x413C, 0x9500) }, /* DW700 GPS USB interface */
 	{ } /* Terminating Entry */
 };
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 87202ad5a50d..b5cef322826f 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -54,15 +54,14 @@ struct ftdi_private {
 	int custom_divisor;	/* custom_divisor kludge, this is for
 				   baud_base (different from what goes to the
 				   chip!) */
-	__u16 last_set_data_urb_value ;
-				/* the last data state set - needed for doing
-				 * a break
-				 */
+	u16 last_set_data_value; /* the last data state set - needed for doing
+				  * a break
+				  */
 	int flags;		/* some ASYNC_xxxx flags are supported */
 	unsigned long last_dtr_rts;	/* saved modem control outputs */
 	char prev_status;        /* Used for TIOCMIWAIT */
 	char transmit_empty;	/* If transmitter is empty or not */
-	__u16 interface;	/* FT2232C, FT2232H or FT4232H port interface
+	u16 interface;		/* FT2232C, FT2232H or FT4232H port interface
 				   (0 for FT232/245) */
 
 	speed_t force_baud;	/* if non-zero, force the baud rate to
@@ -1063,10 +1062,10 @@ static int ftdi_get_modem_status(struct usb_serial_port *port,
 
 static unsigned short int ftdi_232am_baud_base_to_divisor(int baud, int base);
 static unsigned short int ftdi_232am_baud_to_divisor(int baud);
-static __u32 ftdi_232bm_baud_base_to_divisor(int baud, int base);
-static __u32 ftdi_232bm_baud_to_divisor(int baud);
-static __u32 ftdi_2232h_baud_base_to_divisor(int baud, int base);
-static __u32 ftdi_2232h_baud_to_divisor(int baud);
+static u32 ftdi_232bm_baud_base_to_divisor(int baud, int base);
+static u32 ftdi_232bm_baud_to_divisor(int baud);
+static u32 ftdi_2232h_baud_base_to_divisor(int baud, int base);
+static u32 ftdi_2232h_baud_to_divisor(int baud);
 
 static struct usb_serial_driver ftdi_sio_device = {
 	.driver = {
@@ -1136,14 +1135,14 @@ static unsigned short int ftdi_232am_baud_to_divisor(int baud)
 	 return ftdi_232am_baud_base_to_divisor(baud, 48000000);
 }
 
-static __u32 ftdi_232bm_baud_base_to_divisor(int baud, int base)
+static u32 ftdi_232bm_baud_base_to_divisor(int baud, int base)
 {
 	static const unsigned char divfrac[8] = { 0, 3, 2, 4, 1, 5, 6, 7 };
-	__u32 divisor;
+	u32 divisor;
 	/* divisor shifted 3 bits to the left */
 	int divisor3 = base / 2 / baud;
 	divisor = divisor3 >> 3;
-	divisor |= (__u32)divfrac[divisor3 & 0x7] << 14;
+	divisor |= (u32)divfrac[divisor3 & 0x7] << 14;
 	/* Deal with special cases for highest baud rates. */
 	if (divisor == 1)
 		divisor = 0;
@@ -1152,22 +1151,22 @@ static __u32 ftdi_232bm_baud_base_to_divisor(int baud, int base)
 	return divisor;
 }
 
-static __u32 ftdi_232bm_baud_to_divisor(int baud)
+static u32 ftdi_232bm_baud_to_divisor(int baud)
 {
 	 return ftdi_232bm_baud_base_to_divisor(baud, 48000000);
 }
 
-static __u32 ftdi_2232h_baud_base_to_divisor(int baud, int base)
+static u32 ftdi_2232h_baud_base_to_divisor(int baud, int base)
 {
 	static const unsigned char divfrac[8] = { 0, 3, 2, 4, 1, 5, 6, 7 };
-	__u32 divisor;
+	u32 divisor;
 	int divisor3;
 
 	/* hi-speed baud rate is 10-bit sampling instead of 16-bit */
 	divisor3 = base * 8 / (baud * 10);
 
 	divisor = divisor3 >> 3;
-	divisor |= (__u32)divfrac[divisor3 & 0x7] << 14;
+	divisor |= (u32)divfrac[divisor3 & 0x7] << 14;
 	/* Deal with special cases for highest baud rates. */
 	if (divisor == 1)
 		divisor = 0;
@@ -1182,7 +1181,7 @@ static __u32 ftdi_2232h_baud_base_to_divisor(int baud, int base)
 	return divisor;
 }
 
-static __u32 ftdi_2232h_baud_to_divisor(int baud)
+static u32 ftdi_2232h_baud_to_divisor(int baud)
 {
 	 return ftdi_2232h_baud_base_to_divisor(baud, 120000000);
 }
@@ -1195,7 +1194,7 @@ static int update_mctrl(struct usb_serial_port *port, unsigned int set,
 {
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
 	struct device *dev = &port->dev;
-	unsigned urb_value;
+	unsigned value;
 	int rv;
 
 	if (((set | clear) & (TIOCM_DTR | TIOCM_RTS)) == 0) {
@@ -1204,20 +1203,20 @@ static int update_mctrl(struct usb_serial_port *port, unsigned int set,
 	}
 
 	clear &= ~set;	/* 'set' takes precedence over 'clear' */
-	urb_value = 0;
+	value = 0;
 	if (clear & TIOCM_DTR)
-		urb_value |= FTDI_SIO_SET_DTR_LOW;
+		value |= FTDI_SIO_SET_DTR_LOW;
 	if (clear & TIOCM_RTS)
-		urb_value |= FTDI_SIO_SET_RTS_LOW;
+		value |= FTDI_SIO_SET_RTS_LOW;
 	if (set & TIOCM_DTR)
-		urb_value |= FTDI_SIO_SET_DTR_HIGH;
+		value |= FTDI_SIO_SET_DTR_HIGH;
 	if (set & TIOCM_RTS)
-		urb_value |= FTDI_SIO_SET_RTS_HIGH;
+		value |= FTDI_SIO_SET_RTS_HIGH;
 	rv = usb_control_msg(port->serial->dev,
 			       usb_sndctrlpipe(port->serial->dev, 0),
 			       FTDI_SIO_SET_MODEM_CTRL_REQUEST,
 			       FTDI_SIO_SET_MODEM_CTRL_REQUEST_TYPE,
-			       urb_value, priv->interface,
+			       value, priv->interface,
 			       NULL, 0, WDR_TIMEOUT);
 	if (rv < 0) {
 		dev_dbg(dev, "%s Error from MODEM_CTRL urb: DTR %s, RTS %s\n",
@@ -1236,12 +1235,12 @@ static int update_mctrl(struct usb_serial_port *port, unsigned int set,
 }
 
 
-static __u32 get_ftdi_divisor(struct tty_struct *tty,
+static u32 get_ftdi_divisor(struct tty_struct *tty,
 						struct usb_serial_port *port)
 {
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
 	struct device *dev = &port->dev;
-	__u32 div_value = 0;
+	u32 div_value = 0;
 	int div_okay = 1;
 	int baud;
 
@@ -1299,7 +1298,7 @@ static __u32 get_ftdi_divisor(struct tty_struct *tty,
 	case FT232RL: /* FT232RL chip */
 	case FTX:     /* FT-X series */
 		if (baud <= 3000000) {
-			__u16 product_id = le16_to_cpu(
+			u16 product_id = le16_to_cpu(
 				port->serial->dev->descriptor.idProduct);
 			if (((product_id == FTDI_NDI_HUC_PID)		||
 			     (product_id == FTDI_NDI_SPECTRA_SCU_PID)	||
@@ -1346,26 +1345,26 @@ static __u32 get_ftdi_divisor(struct tty_struct *tty,
 static int change_speed(struct tty_struct *tty, struct usb_serial_port *port)
 {
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
-	__u16 urb_value;
-	__u16 urb_index;
-	__u32 urb_index_value;
+	u16 value;
+	u16 index;
+	u32 index_value;
 	int rv;
 
-	urb_index_value = get_ftdi_divisor(tty, port);
-	urb_value = (__u16)urb_index_value;
-	urb_index = (__u16)(urb_index_value >> 16);
+	index_value = get_ftdi_divisor(tty, port);
+	value = (u16)index_value;
+	index = (u16)(index_value >> 16);
 	if ((priv->chip_type == FT2232C) || (priv->chip_type == FT2232H) ||
 		(priv->chip_type == FT4232H) || (priv->chip_type == FT232H)) {
 		/* Probably the BM type needs the MSB of the encoded fractional
 		 * divider also moved like for the chips above. Any infos? */
-		urb_index = (__u16)((urb_index << 8) | priv->interface);
+		index = (u16)((index << 8) | priv->interface);
 	}
 
 	rv = usb_control_msg(port->serial->dev,
 			    usb_sndctrlpipe(port->serial->dev, 0),
 			    FTDI_SIO_SET_BAUDRATE_REQUEST,
 			    FTDI_SIO_SET_BAUDRATE_REQUEST_TYPE,
-			    urb_value, urb_index,
+			    value, index,
 			    NULL, 0, WDR_SHORT_TIMEOUT);
 	return rv;
 }
@@ -1898,7 +1897,8 @@ static int ftdi_8u2232c_probe(struct usb_serial *serial)
 		return ftdi_jtag_probe(serial);
 
 	if (udev->product &&
-		(!strcmp(udev->product, "BeagleBone/XDS100V2") ||
+		(!strcmp(udev->product, "Arrow USB Blaster") ||
+		 !strcmp(udev->product, "BeagleBone/XDS100V2") ||
 		 !strcmp(udev->product, "SNAP Connect E10")))
 		return ftdi_jtag_probe(serial);
 
@@ -2139,29 +2139,29 @@ static void ftdi_break_ctl(struct tty_struct *tty, int break_state)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
-	__u16 urb_value;
+	u16 value;
 
 	/* break_state = -1 to turn on break, and 0 to turn off break */
 	/* see drivers/char/tty_io.c to see it used */
-	/* last_set_data_urb_value NEVER has the break bit set in it */
+	/* last_set_data_value NEVER has the break bit set in it */
 
 	if (break_state)
-		urb_value = priv->last_set_data_urb_value | FTDI_SIO_SET_BREAK;
+		value = priv->last_set_data_value | FTDI_SIO_SET_BREAK;
 	else
-		urb_value = priv->last_set_data_urb_value;
+		value = priv->last_set_data_value;
 
 	if (usb_control_msg(port->serial->dev,
 			usb_sndctrlpipe(port->serial->dev, 0),
 			FTDI_SIO_SET_DATA_REQUEST,
 			FTDI_SIO_SET_DATA_REQUEST_TYPE,
-			urb_value , priv->interface,
+			value , priv->interface,
 			NULL, 0, WDR_TIMEOUT) < 0) {
 		dev_err(&port->dev, "%s FAILED to enable/disable break state (state was %d)\n",
 			__func__, break_state);
 	}
 
 	dev_dbg(&port->dev, "%s break state is %d - urb is %d\n", __func__,
-		break_state, urb_value);
+		break_state, value);
 
 }
 
@@ -2191,12 +2191,8 @@ static void ftdi_set_termios(struct tty_struct *tty,
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
 	struct ktermios *termios = &tty->termios;
 	unsigned int cflag = termios->c_cflag;
-	__u16 urb_value; /* will hold the new flags */
-
-	/* Added for xon/xoff support */
-	unsigned int iflag = termios->c_iflag;
-	unsigned char vstop;
-	unsigned char vstart;
+	u16 value, index;
+	int ret;
 
 	/* Force baud rate if this device requires it, unless it is set to
 	   B0. */
@@ -2257,44 +2253,44 @@ static void ftdi_set_termios(struct tty_struct *tty,
 no_skip:
 	/* Set number of data bits, parity, stop bits */
 
-	urb_value = 0;
-	urb_value |= (cflag & CSTOPB ? FTDI_SIO_SET_DATA_STOP_BITS_2 :
-		      FTDI_SIO_SET_DATA_STOP_BITS_1);
+	value = 0;
+	value |= (cflag & CSTOPB ? FTDI_SIO_SET_DATA_STOP_BITS_2 :
+			FTDI_SIO_SET_DATA_STOP_BITS_1);
 	if (cflag & PARENB) {
 		if (cflag & CMSPAR)
-			urb_value |= cflag & PARODD ?
-				     FTDI_SIO_SET_DATA_PARITY_MARK :
-				     FTDI_SIO_SET_DATA_PARITY_SPACE;
+			value |= cflag & PARODD ?
+					FTDI_SIO_SET_DATA_PARITY_MARK :
+					FTDI_SIO_SET_DATA_PARITY_SPACE;
 		else
-			urb_value |= cflag & PARODD ?
-				     FTDI_SIO_SET_DATA_PARITY_ODD :
-				     FTDI_SIO_SET_DATA_PARITY_EVEN;
+			value |= cflag & PARODD ?
+					FTDI_SIO_SET_DATA_PARITY_ODD :
+					FTDI_SIO_SET_DATA_PARITY_EVEN;
 	} else {
-		urb_value |= FTDI_SIO_SET_DATA_PARITY_NONE;
+		value |= FTDI_SIO_SET_DATA_PARITY_NONE;
 	}
 	switch (cflag & CSIZE) {
 	case CS5:
 		dev_dbg(ddev, "Setting CS5 quirk\n");
 		break;
 	case CS7:
-		urb_value |= 7;
+		value |= 7;
 		dev_dbg(ddev, "Setting CS7\n");
 		break;
 	default:
 	case CS8:
-		urb_value |= 8;
+		value |= 8;
 		dev_dbg(ddev, "Setting CS8\n");
 		break;
 	}
 
 	/* This is needed by the break command since it uses the same command
 	   - but is or'ed with this value  */
-	priv->last_set_data_urb_value = urb_value;
+	priv->last_set_data_value = value;
 
 	if (usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 			    FTDI_SIO_SET_DATA_REQUEST,
 			    FTDI_SIO_SET_DATA_REQUEST_TYPE,
-			    urb_value , priv->interface,
+			    value , priv->interface,
 			    NULL, 0, WDR_SHORT_TIMEOUT) < 0) {
 		dev_err(ddev, "%s FAILED to set databits/stopbits/parity\n",
 			__func__);
@@ -2325,65 +2321,30 @@ no_data_parity_stop_changes:
 			set_mctrl(port, TIOCM_DTR | TIOCM_RTS);
 	}
 
-	/* Set flow control */
-	/* Note device also supports DTR/CD (ugh) and Xon/Xoff in hardware */
 no_c_cflag_changes:
-	if (cflag & CRTSCTS) {
-		dev_dbg(ddev, "%s Setting to CRTSCTS flow control\n", __func__);
-		if (usb_control_msg(dev,
-				    usb_sndctrlpipe(dev, 0),
-				    FTDI_SIO_SET_FLOW_CTRL_REQUEST,
-				    FTDI_SIO_SET_FLOW_CTRL_REQUEST_TYPE,
-				    0 , (FTDI_SIO_RTS_CTS_HS | priv->interface),
-				    NULL, 0, WDR_TIMEOUT) < 0) {
-			dev_err(ddev, "urb failed to set to rts/cts flow control\n");
-		}
+	/* Set hardware-assisted flow control */
+	value = 0;
+
+	if (C_CRTSCTS(tty)) {
+		dev_dbg(&port->dev, "enabling rts/cts flow control\n");
+		index = FTDI_SIO_RTS_CTS_HS;
+	} else if (I_IXON(tty)) {
+		dev_dbg(&port->dev, "enabling xon/xoff flow control\n");
+		index = FTDI_SIO_XON_XOFF_HS;
+		value = STOP_CHAR(tty) << 8 | START_CHAR(tty);
 	} else {
-		/*
-		 * Xon/Xoff code
-		 *
-		 * Check the IXOFF status in the iflag component of the
-		 * termios structure. If IXOFF is not set, the pre-xon/xoff
-		 * code is executed.
-		 */
-		if (iflag & IXOFF) {
-			dev_dbg(ddev, "%s  request to enable xonxoff iflag=%04x\n",
-				__func__, iflag);
-			/* Try to enable the XON/XOFF on the ftdi_sio
-			 * Set the vstart and vstop -- could have been done up
-			 * above where a lot of other dereferencing is done but
-			 * that would be very inefficient as vstart and vstop
-			 * are not always needed.
-			 */
-			vstart = termios->c_cc[VSTART];
-			vstop = termios->c_cc[VSTOP];
-			urb_value = (vstop << 8) | (vstart);
-
-			if (usb_control_msg(dev,
-					    usb_sndctrlpipe(dev, 0),
-					    FTDI_SIO_SET_FLOW_CTRL_REQUEST,
-					    FTDI_SIO_SET_FLOW_CTRL_REQUEST_TYPE,
-					    urb_value , (FTDI_SIO_XON_XOFF_HS
-							 | priv->interface),
-					    NULL, 0, WDR_TIMEOUT) < 0) {
-				dev_err(&port->dev, "urb failed to set to "
-					"xon/xoff flow control\n");
-			}
-		} else {
-			/* else clause to only run if cflag ! CRTSCTS and iflag
-			 * ! XOFF. CHECKME Assuming XON/XOFF handled by tty
-			 * stack - not by device */
-			dev_dbg(ddev, "%s Turning off hardware flow control\n", __func__);
-			if (usb_control_msg(dev,
-					    usb_sndctrlpipe(dev, 0),
-					    FTDI_SIO_SET_FLOW_CTRL_REQUEST,
-					    FTDI_SIO_SET_FLOW_CTRL_REQUEST_TYPE,
-					    0, priv->interface,
-					    NULL, 0, WDR_TIMEOUT) < 0) {
-				dev_err(ddev, "urb failed to clear flow control\n");
-			}
-		}
+		dev_dbg(&port->dev, "disabling flow control\n");
+		index = FTDI_SIO_DISABLE_FLOW_CTRL;
 	}
+
+	index |= priv->interface;
+
+	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
+			FTDI_SIO_SET_FLOW_CTRL_REQUEST,
+			FTDI_SIO_SET_FLOW_CTRL_REQUEST_TYPE,
+			value, index, NULL, 0, WDR_TIMEOUT);
+	if (ret < 0)
+		dev_err(&port->dev, "failed to set flow control: %d\n", ret);
 }
 
 /*
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index c3f252283ab9..664e61f16b6a 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -233,6 +233,8 @@ static void option_instat_callback(struct urb *urb);
 /* These Quectel products use Qualcomm's vendor ID */
 #define QUECTEL_PRODUCT_UC20			0x9003
 #define QUECTEL_PRODUCT_UC15			0x9090
+/* These u-blox products use Qualcomm's vendor ID */
+#define UBLOX_PRODUCT_R410M			0x90b2
 /* These Yuga products use Qualcomm's vendor ID */
 #define YUGA_PRODUCT_CLM920_NC5			0x9625
 
@@ -1065,6 +1067,9 @@ static const struct usb_device_id option_ids[] = {
 	/* Yuga products use Qualcomm vendor ID */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5),
 	  .driver_info = RSVD(1) | RSVD(4) },
+	/* u-blox products using Qualcomm vendor ID */
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M),
+	  .driver_info = RSVD(1) | RSVD(3) },
 	/* Quectel products using Quectel vendor ID */
 	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
 	  .driver_info = RSVD(4) },
@@ -1911,7 +1916,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d01, 0xff) },			/* D-Link DWM-156 (variant) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d02, 0xff) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d03, 0xff) },
-	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d04, 0xff) },			/* D-Link DWM-158 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d04, 0xff),			/* D-Link DWM-158 */
+	 .driver_info = RSVD(4) | RSVD(5) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d0e, 0xff) },			/* D-Link DWM-157 C1 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e19, 0xff),			/* D-Link DWM-221 B1 */
 	  .driver_info = RSVD(4) },
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 46dd09da2434..5d1a1931967e 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -533,6 +533,17 @@ static int pl2303_set_line_request(struct usb_serial_port *port,
 	return 0;
 }
 
+static bool pl2303_termios_change(const struct ktermios *a, const struct ktermios *b)
+{
+	bool ixon_change;
+
+	ixon_change = ((a->c_iflag ^ b->c_iflag) & (IXON | IXANY)) ||
+			a->c_cc[VSTART] != b->c_cc[VSTART] ||
+			a->c_cc[VSTOP] != b->c_cc[VSTOP];
+
+	return tty_termios_hw_change(a, b) || ixon_change;
+}
+
 static void pl2303_set_termios(struct tty_struct *tty,
 		struct usb_serial_port *port, struct ktermios *old_termios)
 {
@@ -544,7 +555,7 @@ static void pl2303_set_termios(struct tty_struct *tty,
 	int ret;
 	u8 control;
 
-	if (old_termios && !tty_termios_hw_change(&tty->termios, old_termios))
+	if (old_termios && !pl2303_termios_change(&tty->termios, old_termios))
 		return;
 
 	buf = kzalloc(7, GFP_KERNEL);
@@ -662,6 +673,9 @@ static void pl2303_set_termios(struct tty_struct *tty,
 			pl2303_vendor_write(serial, 0x0, 0x41);
 		else
 			pl2303_vendor_write(serial, 0x0, 0x61);
+	} else if (I_IXON(tty) && !I_IXANY(tty) && START_CHAR(tty) == 0x11 &&
+			STOP_CHAR(tty) == 0x13) {
+		pl2303_vendor_write(serial, 0x0, 0xc0);
 	} else {
 		pl2303_vendor_write(serial, 0x0, 0x0);
 	}
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index 4ef79e29cb26..40864c2bd9dc 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -63,6 +63,11 @@ DEVICE(flashloader, FLASHLOADER_IDS);
 					0x01) }
 DEVICE(google, GOOGLE_IDS);
 
+/* Libtransistor USB console */
+#define LIBTRANSISTOR_IDS()			\
+	{ USB_DEVICE(0x1209, 0x8b00) }
+DEVICE(libtransistor, LIBTRANSISTOR_IDS);
+
 /* ViVOpay USB Serial Driver */
 #define VIVOPAY_IDS()			\
 	{ USB_DEVICE(0x1d5f, 0x1004) }	/* ViVOpay 8800 */
@@ -110,6 +115,7 @@ static struct usb_serial_driver * const serial_drivers[] = {
 	&funsoft_device,
 	&flashloader_device,
 	&google_device,
+	&libtransistor_device,
 	&vivopay_device,
 	&moto_modem_device,
 	&motorola_tetra_device,
@@ -126,6 +132,7 @@ static const struct usb_device_id id_table[] = {
 	FUNSOFT_IDS(),
 	FLASHLOADER_IDS(),
 	GOOGLE_IDS(),
+	LIBTRANSISTOR_IDS(),
 	VIVOPAY_IDS(),
 	MOTO_IDS(),
 	MOTOROLA_TETRA_IDS(),
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 790e0cbe3da9..f7aaa7f079e1 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -192,7 +192,7 @@ static int serial_install(struct tty_driver *driver, struct tty_struct *tty)
 	if (retval)
 		goto error_get_interface;
 
-	retval = tty_port_install(&port->port, driver, tty);
+	retval = tty_standard_install(driver, tty);
 	if (retval)
 		goto error_init_termios;
 
@@ -476,19 +476,6 @@ static int serial_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int serial_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, serial_proc_show, NULL);
-}
-
-static const struct file_operations serial_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= serial_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int serial_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
@@ -1192,7 +1179,7 @@ static const struct tty_operations serial_ops = {
 	.get_icount =		serial_get_icount,
 	.cleanup =		serial_cleanup,
 	.install =		serial_install,
-	.proc_fops =		&serial_proc_fops,
+	.proc_show =		serial_proc_show,
 };
 
 
diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c
index f5373ed2cd45..8ddbecc25d89 100644
--- a/drivers/usb/serial/visor.c
+++ b/drivers/usb/serial/visor.c
@@ -335,47 +335,48 @@ static int palm_os_3_probe(struct usb_serial *serial,
 		goto exit;
 	}
 
-	if (retval == sizeof(*connection_info)) {
-			connection_info = (struct visor_connection_info *)
-							transfer_buffer;
-
-		num_ports = le16_to_cpu(connection_info->num_ports);
-		for (i = 0; i < num_ports; ++i) {
-			switch (
-			   connection_info->connections[i].port_function_id) {
-			case VISOR_FUNCTION_GENERIC:
-				string = "Generic";
-				break;
-			case VISOR_FUNCTION_DEBUGGER:
-				string = "Debugger";
-				break;
-			case VISOR_FUNCTION_HOTSYNC:
-				string = "HotSync";
-				break;
-			case VISOR_FUNCTION_CONSOLE:
-				string = "Console";
-				break;
-			case VISOR_FUNCTION_REMOTE_FILE_SYS:
-				string = "Remote File System";
-				break;
-			default:
-				string = "unknown";
-				break;
-			}
-			dev_info(dev, "%s: port %d, is for %s use\n",
-				serial->type->description,
-				connection_info->connections[i].port, string);
-		}
+	if (retval != sizeof(*connection_info)) {
+		dev_err(dev, "Invalid connection information received from device\n");
+		retval = -ENODEV;
+		goto exit;
 	}
-	/*
-	* Handle devices that report invalid stuff here.
-	*/
+
+	connection_info = (struct visor_connection_info *)transfer_buffer;
+
+	num_ports = le16_to_cpu(connection_info->num_ports);
+
+	/* Handle devices that report invalid stuff here. */
 	if (num_ports == 0 || num_ports > 2) {
 		dev_warn(dev, "%s: No valid connect info available\n",
 			serial->type->description);
 		num_ports = 2;
 	}
 
+	for (i = 0; i < num_ports; ++i) {
+		switch (connection_info->connections[i].port_function_id) {
+		case VISOR_FUNCTION_GENERIC:
+			string = "Generic";
+			break;
+		case VISOR_FUNCTION_DEBUGGER:
+			string = "Debugger";
+			break;
+		case VISOR_FUNCTION_HOTSYNC:
+			string = "HotSync";
+			break;
+		case VISOR_FUNCTION_CONSOLE:
+			string = "Console";
+			break;
+		case VISOR_FUNCTION_REMOTE_FILE_SYS:
+			string = "Remote File System";
+			break;
+		default:
+			string = "unknown";
+			break;
+		}
+		dev_info(dev, "%s: port %d, is for %s use\n",
+			serial->type->description,
+			connection_info->connections[i].port, string);
+	}
 	dev_info(dev, "%s: Number of ports: %d\n", serial->type->description,
 		num_ports);
 
diff --git a/drivers/usb/storage/freecom.c b/drivers/usb/storage/freecom.c
index ec4d92c92762..4f542df37a44 100644
--- a/drivers/usb/storage/freecom.c
+++ b/drivers/usb/storage/freecom.c
@@ -464,7 +464,7 @@ static int init_freecom(struct us_data *us)
 	usb_stor_dbg(us, "result from activate reset is %d\n", result);
 
 	/* wait 250ms */
-	mdelay(250);
+	msleep(250);
 
 	/* clear reset */
 	result = usb_stor_control_msg(us, us->send_ctrl_pipe,
@@ -472,7 +472,7 @@ static int init_freecom(struct us_data *us)
 	usb_stor_dbg(us, "result from clear reset is %d\n", result);
 
 	/* wait 3 seconds */
-	mdelay(3 * 1000);
+	msleep(3 * 1000);
 
 	return USB_STOR_TRANSPORT_GOOD;
 }
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 6034c39b67d1..9e9de5452860 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -836,6 +836,12 @@ static int uas_slave_configure(struct scsi_device *sdev)
 	if (devinfo->flags & US_FL_BROKEN_FUA)
 		sdev->broken_fua = 1;
 
+	/* UAS also needs to support FL_ALWAYS_SYNC */
+	if (devinfo->flags & US_FL_ALWAYS_SYNC) {
+		sdev->skip_ms_page_3f = 1;
+		sdev->skip_ms_page_8 = 1;
+		sdev->wce_default_on = 1;
+	}
 	scsi_change_queue_depth(sdev, devinfo->qdepth - 2);
 	return 0;
 }
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 747d3a9596d9..22fcfccf453a 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2321,6 +2321,15 @@ UNUSUAL_DEV(  0x4146, 0xba01, 0x0100, 0x0100,
 		"Micro Mini 1GB",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NOT_LOCKABLE ),
 
+/* "G-DRIVE" external HDD hangs on write without these.
+ * Patch submitted by Alexander Kappner <agk@godking.net>
+ */
+UNUSUAL_DEV(0x4971, 0x8024, 0x0000, 0x9999,
+		"SimpleTech",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_ALWAYS_SYNC),
+
 /*
  * Nick Bowler <nbowler@elliptictech.com>
  * SCSI stack spams (otherwise harmless) error messages.
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 38434d88954a..d0bdebd87ce3 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -107,3 +107,12 @@ UNUSUAL_DEV(0x4971, 0x8017, 0x0000, 0x9999,
 		"External HDD",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_OPCODES),
+
+/* "G-DRIVE" external HDD hangs on write without these.
+ * Patch submitted by Alexander Kappner <agk@godking.net>
+ */
+UNUSUAL_DEV(0x4971, 0x8024, 0x0000, 0x9999,
+		"SimpleTech",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_ALWAYS_SYNC),
diff --git a/drivers/usb/typec/Kconfig b/drivers/usb/typec/Kconfig
index 030f88cb0c3f..2c8eab11a493 100644
--- a/drivers/usb/typec/Kconfig
+++ b/drivers/usb/typec/Kconfig
@@ -49,6 +49,7 @@ config TYPEC_TCPM
 	tristate "USB Type-C Port Controller Manager"
 	depends on USB
 	select USB_ROLE_SWITCH
+	select POWER_SUPPLY
 	help
 	  The Type-C Port Controller Manager provides a USB PD and USB Type-C
 	  state machine for use with Type-C Port Controllers.
diff --git a/drivers/usb/typec/fusb302/Kconfig b/drivers/usb/typec/fusb302/Kconfig
index 48a4f2fcee03..fce099ff39fe 100644
--- a/drivers/usb/typec/fusb302/Kconfig
+++ b/drivers/usb/typec/fusb302/Kconfig
@@ -1,6 +1,6 @@
 config TYPEC_FUSB302
 	tristate "Fairchild FUSB302 Type-C chip driver"
-	depends on I2C && POWER_SUPPLY
+	depends on I2C
 	help
 	  The Fairchild FUSB302 Type-C chip driver that works with
 	  Type-C Port Controller Manager to provide USB PD and USB
diff --git a/drivers/usb/typec/fusb302/fusb302.c b/drivers/usb/typec/fusb302/fusb302.c
index 703617129067..1e68da10bf17 100644
--- a/drivers/usb/typec/fusb302/fusb302.c
+++ b/drivers/usb/typec/fusb302/fusb302.c
@@ -18,7 +18,6 @@
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/pinctrl/consumer.h>
-#include <linux/power_supply.h>
 #include <linux/proc_fs.h>
 #include <linux/regulator/consumer.h>
 #include <linux/sched/clock.h>
@@ -99,11 +98,6 @@ struct fusb302_chip {
 	/* lock for sharing chip states */
 	struct mutex lock;
 
-	/* psy + psy status */
-	struct power_supply *psy;
-	u32 current_limit;
-	u32 supply_voltage;
-
 	/* chip status */
 	enum toggling_mode toggling_mode;
 	enum src_current_status src_current_status;
@@ -120,6 +114,7 @@ struct fusb302_chip {
 	enum typec_cc_polarity cc_polarity;
 	enum typec_cc_status cc1;
 	enum typec_cc_status cc2;
+	u32 snk_pdo[PDO_MAX_OBJECTS];
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -220,32 +215,28 @@ DEFINE_SHOW_ATTRIBUTE(fusb302_debug);
 
 static struct dentry *rootdir;
 
-static int fusb302_debugfs_init(struct fusb302_chip *chip)
+static void fusb302_debugfs_init(struct fusb302_chip *chip)
 {
 	mutex_init(&chip->logbuffer_lock);
-	if (!rootdir) {
+	if (!rootdir)
 		rootdir = debugfs_create_dir("fusb302", NULL);
-		if (!rootdir)
-			return -ENOMEM;
-	}
 
 	chip->dentry = debugfs_create_file(dev_name(chip->dev),
 					   S_IFREG | 0444, rootdir,
 					   chip, &fusb302_debug_fops);
-
-	return 0;
 }
 
 static void fusb302_debugfs_exit(struct fusb302_chip *chip)
 {
 	debugfs_remove(chip->dentry);
+	debugfs_remove(rootdir);
 }
 
 #else
 
 static void fusb302_log(const struct fusb302_chip *chip,
 			const char *fmt, ...) { }
-static int fusb302_debugfs_init(const struct fusb302_chip *chip) { return 0; }
+static void fusb302_debugfs_init(const struct fusb302_chip *chip) { }
 static void fusb302_debugfs_exit(const struct fusb302_chip *chip) { }
 
 #endif
@@ -861,13 +852,11 @@ static int tcpm_set_vbus(struct tcpc_dev *dev, bool on, bool charge)
 		chip->vbus_on = on;
 		fusb302_log(chip, "vbus := %s", on ? "On" : "Off");
 	}
-	if (chip->charge_on == charge) {
+	if (chip->charge_on == charge)
 		fusb302_log(chip, "charge is already %s",
 			    charge ? "On" : "Off");
-	} else {
+	else
 		chip->charge_on = charge;
-		power_supply_changed(chip->psy);
-	}
 
 done:
 	mutex_unlock(&chip->lock);
@@ -883,11 +872,6 @@ static int tcpm_set_current_limit(struct tcpc_dev *dev, u32 max_ma, u32 mv)
 	fusb302_log(chip, "current limit: %d ma, %d mv (not implemented)",
 		    max_ma, mv);
 
-	chip->supply_voltage = mv;
-	chip->current_limit = max_ma;
-
-	power_supply_changed(chip->psy);
-
 	return 0;
 }
 
@@ -1212,11 +1196,6 @@ static const u32 snk_pdo[] = {
 static const struct tcpc_config fusb302_tcpc_config = {
 	.src_pdo = src_pdo,
 	.nr_src_pdo = ARRAY_SIZE(src_pdo),
-	.snk_pdo = snk_pdo,
-	.nr_snk_pdo = ARRAY_SIZE(snk_pdo),
-	.max_snk_mv = 5000,
-	.max_snk_ma = 3000,
-	.max_snk_mw = 15000,
 	.operating_snk_mw = 2500,
 	.type = TYPEC_PORT_DRP,
 	.data = TYPEC_PORT_DRD,
@@ -1686,43 +1665,6 @@ done:
 	return IRQ_HANDLED;
 }
 
-static int fusb302_psy_get_property(struct power_supply *psy,
-				    enum power_supply_property psp,
-				    union power_supply_propval *val)
-{
-	struct fusb302_chip *chip = power_supply_get_drvdata(psy);
-
-	switch (psp) {
-	case POWER_SUPPLY_PROP_ONLINE:
-		val->intval = chip->charge_on;
-		break;
-	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
-		val->intval = chip->supply_voltage * 1000; /* mV -> µV */
-		break;
-	case POWER_SUPPLY_PROP_CURRENT_MAX:
-		val->intval = chip->current_limit * 1000; /* mA -> µA */
-		break;
-	default:
-		return -ENODATA;
-	}
-
-	return 0;
-}
-
-static enum power_supply_property fusb302_psy_properties[] = {
-	POWER_SUPPLY_PROP_ONLINE,
-	POWER_SUPPLY_PROP_VOLTAGE_NOW,
-	POWER_SUPPLY_PROP_CURRENT_MAX,
-};
-
-static const struct power_supply_desc fusb302_psy_desc = {
-	.name		= "fusb302-typec-source",
-	.type		= POWER_SUPPLY_TYPE_USB_TYPE_C,
-	.properties	= fusb302_psy_properties,
-	.num_properties	= ARRAY_SIZE(fusb302_psy_properties),
-	.get_property	= fusb302_psy_get_property,
-};
-
 static int init_gpio(struct fusb302_chip *chip)
 {
 	struct device_node *node;
@@ -1756,13 +1698,35 @@ static int init_gpio(struct fusb302_chip *chip)
 	return 0;
 }
 
+static int fusb302_composite_snk_pdo_array(struct fusb302_chip *chip)
+{
+	struct device *dev = chip->dev;
+	u32 max_uv, max_ua;
+
+	chip->snk_pdo[0] = PDO_FIXED(5000, 400, PDO_FIXED_FLAGS);
+
+	/*
+	 * As max_snk_ma/mv/mw is not needed for tcpc_config,
+	 * those settings should be passed in via sink PDO, so
+	 * "fcs, max-sink-*" properties will be deprecated, to
+	 * perserve compatibility with existing users of them,
+	 * we read those properties to convert them to be a var
+	 * PDO.
+	 */
+	if (device_property_read_u32(dev, "fcs,max-sink-microvolt", &max_uv) ||
+		device_property_read_u32(dev, "fcs,max-sink-microamp", &max_ua))
+		return 1;
+
+	chip->snk_pdo[1] = PDO_VAR(5000, max_uv / 1000, max_ua / 1000);
+	return 2;
+}
+
 static int fusb302_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
 	struct fusb302_chip *chip;
 	struct i2c_adapter *adapter;
 	struct device *dev = &client->dev;
-	struct power_supply_config cfg = {};
 	const char *name;
 	int ret = 0;
 	u32 v;
@@ -1784,18 +1748,13 @@ static int fusb302_probe(struct i2c_client *client,
 	chip->tcpc_dev.config = &chip->tcpc_config;
 	mutex_init(&chip->lock);
 
-	if (!device_property_read_u32(dev, "fcs,max-sink-microvolt", &v))
-		chip->tcpc_config.max_snk_mv = v / 1000;
-
-	if (!device_property_read_u32(dev, "fcs,max-sink-microamp", &v))
-		chip->tcpc_config.max_snk_ma = v / 1000;
-
-	if (!device_property_read_u32(dev, "fcs,max-sink-microwatt", &v))
-		chip->tcpc_config.max_snk_mw = v / 1000;
-
 	if (!device_property_read_u32(dev, "fcs,operating-sink-microwatt", &v))
 		chip->tcpc_config.operating_snk_mw = v / 1000;
 
+	/* Composite sink PDO */
+	chip->tcpc_config.nr_snk_pdo = fusb302_composite_snk_pdo_array(chip);
+	chip->tcpc_config.snk_pdo = chip->snk_pdo;
+
 	/*
 	 * Devicetree platforms should get extcon via phandle (not yet
 	 * supported). On ACPI platforms, we get the name from a device prop.
@@ -1809,17 +1768,7 @@ static int fusb302_probe(struct i2c_client *client,
 			return -EPROBE_DEFER;
 	}
 
-	cfg.drv_data = chip;
-	chip->psy = devm_power_supply_register(dev, &fusb302_psy_desc, &cfg);
-	if (IS_ERR(chip->psy)) {
-		ret = PTR_ERR(chip->psy);
-		dev_err(chip->dev, "Error registering power-supply: %d\n", ret);
-		return ret;
-	}
-
-	ret = fusb302_debugfs_init(chip);
-	if (ret < 0)
-		return ret;
+	fusb302_debugfs_init(chip);
 
 	chip->wq = create_singlethread_workqueue(dev_name(chip->dev));
 	if (!chip->wq) {
diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c
index f89093bd7185..9d8330e9c431 100644
--- a/drivers/usb/typec/mux.c
+++ b/drivers/usb/typec/mux.c
@@ -178,7 +178,7 @@ EXPORT_SYMBOL_GPL(typec_mux_register);
 
 /**
  * typec_mux_unregister - Unregister Multiplexer Switch
- * @sw: USB Type-C Connector Multiplexer/DeMultiplexer
+ * @mux: USB Type-C Connector Multiplexer/DeMultiplexer
  *
  * Unregister mux that was registered with typec_mux_register().
  */
diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c
index 677d12138dbd..8a201dd53d36 100644
--- a/drivers/usb/typec/tcpm.c
+++ b/drivers/usb/typec/tcpm.c
@@ -12,13 +12,17 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/power_supply.h>
 #include <linux/proc_fs.h>
+#include <linux/property.h>
 #include <linux/sched/clock.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/usb/pd.h>
+#include <linux/usb/pd_ado.h>
 #include <linux/usb/pd_bdo.h>
+#include <linux/usb/pd_ext_sdb.h>
 #include <linux/usb/pd_vdo.h>
 #include <linux/usb/role.h>
 #include <linux/usb/tcpm.h>
@@ -48,6 +52,7 @@
 	S(SNK_DISCOVERY_DEBOUNCE_DONE),		\
 	S(SNK_WAIT_CAPABILITIES),		\
 	S(SNK_NEGOTIATE_CAPABILITIES),		\
+	S(SNK_NEGOTIATE_PPS_CAPABILITIES),	\
 	S(SNK_TRANSITION_SINK),			\
 	S(SNK_TRANSITION_SINK_VBUS),		\
 	S(SNK_READY),				\
@@ -112,6 +117,11 @@
 	S(SNK_TRYWAIT_VBUS),			\
 	S(BIST_RX),				\
 						\
+	S(GET_STATUS_SEND),			\
+	S(GET_STATUS_SEND_TIMEOUT),		\
+	S(GET_PPS_STATUS_SEND),			\
+	S(GET_PPS_STATUS_SEND_TIMEOUT),		\
+						\
 	S(ERROR_RECOVERY),			\
 	S(PORT_RESET),				\
 	S(PORT_RESET_WAIT_OFF)
@@ -142,6 +152,7 @@ enum pd_msg_request {
 	PD_MSG_NONE = 0,
 	PD_MSG_CTRL_REJECT,
 	PD_MSG_CTRL_WAIT,
+	PD_MSG_CTRL_NOT_SUPP,
 	PD_MSG_DATA_SINK_CAP,
 	PD_MSG_DATA_SOURCE_CAP,
 };
@@ -167,6 +178,16 @@ struct pd_mode_data {
 	struct typec_altmode_desc altmode_desc[SVID_DISCOVERY_MAX];
 };
 
+struct pd_pps_data {
+	u32 min_volt;
+	u32 max_volt;
+	u32 max_curr;
+	u32 out_volt;
+	u32 op_curr;
+	bool supported;
+	bool active;
+};
+
 struct tcpm_port {
 	struct device *dev;
 
@@ -235,6 +256,7 @@ struct tcpm_port {
 	struct completion swap_complete;
 	int swap_status;
 
+	unsigned int negotiated_rev;
 	unsigned int message_id;
 	unsigned int caps_count;
 	unsigned int hard_reset_count;
@@ -257,15 +279,18 @@ struct tcpm_port {
 	u32 snk_vdo[VDO_MAX_OBJECTS];
 	unsigned int nr_snk_vdo;
 
-	unsigned int max_snk_mv;
-	unsigned int max_snk_ma;
-	unsigned int max_snk_mw;
 	unsigned int operating_snk_mw;
+	bool update_sink_caps;
 
 	/* Requested current / voltage */
 	u32 current_limit;
 	u32 supply_voltage;
 
+	/* Used to export TA voltage and current */
+	struct power_supply *psy;
+	struct power_supply_desc psy_desc;
+	enum power_supply_usb_type usb_type;
+
 	u32 bist_request;
 
 	/* PD state for Vendor Defined Messages */
@@ -277,8 +302,13 @@ struct tcpm_port {
 	/* VDO to retry if UFP responder replied busy */
 	u32 vdo_retry;
 
-	/* Alternate mode data */
+	/* PPS */
+	struct pd_pps_data pps_data;
+	struct completion pps_complete;
+	bool pps_pending;
+	int pps_status;
 
+	/* Alternate mode data */
 	struct pd_mode_data mode_data;
 	struct typec_altmode *partner_altmode[SVID_DISCOVERY_MAX];
 	struct typec_altmode *port_altmode[SVID_DISCOVERY_MAX];
@@ -496,6 +526,16 @@ static void tcpm_log_source_caps(struct tcpm_port *port)
 				  pdo_max_voltage(pdo),
 				  pdo_max_power(pdo));
 			break;
+		case PDO_TYPE_APDO:
+			if (pdo_apdo_type(pdo) == APDO_TYPE_PPS)
+				scnprintf(msg, sizeof(msg),
+					  "%u-%u mV, %u mA",
+					  pdo_pps_apdo_min_voltage(pdo),
+					  pdo_pps_apdo_max_voltage(pdo),
+					  pdo_pps_apdo_max_current(pdo));
+			else
+				strcpy(msg, "undefined APDO");
+			break;
 		default:
 			strcpy(msg, "undefined");
 			break;
@@ -526,21 +566,16 @@ DEFINE_SHOW_ATTRIBUTE(tcpm_debug);
 
 static struct dentry *rootdir;
 
-static int tcpm_debugfs_init(struct tcpm_port *port)
+static void tcpm_debugfs_init(struct tcpm_port *port)
 {
 	mutex_init(&port->logbuffer_lock);
 	/* /sys/kernel/debug/tcpm/usbcX */
-	if (!rootdir) {
+	if (!rootdir)
 		rootdir = debugfs_create_dir("tcpm", NULL);
-		if (!rootdir)
-			return -ENOMEM;
-	}
 
 	port->dentry = debugfs_create_file(dev_name(port->dev),
 					   S_IFREG | 0444, rootdir,
 					   port, &tcpm_debug_fops);
-
-	return 0;
 }
 
 static void tcpm_debugfs_exit(struct tcpm_port *port)
@@ -555,7 +590,7 @@ static void tcpm_log(const struct tcpm_port *port, const char *fmt, ...) { }
 __printf(2, 3)
 static void tcpm_log_force(struct tcpm_port *port, const char *fmt, ...) { }
 static void tcpm_log_source_caps(struct tcpm_port *port) { }
-static int tcpm_debugfs_init(const struct tcpm_port *port) { return 0; }
+static void tcpm_debugfs_init(const struct tcpm_port *port) { }
 static void tcpm_debugfs_exit(const struct tcpm_port *port) { }
 
 #endif
@@ -793,11 +828,13 @@ static int tcpm_pd_send_source_caps(struct tcpm_port *port)
 		msg.header = PD_HEADER_LE(PD_CTRL_REJECT,
 					  port->pwr_role,
 					  port->data_role,
+					  port->negotiated_rev,
 					  port->message_id, 0);
 	} else {
 		msg.header = PD_HEADER_LE(PD_DATA_SOURCE_CAP,
 					  port->pwr_role,
 					  port->data_role,
+					  port->negotiated_rev,
 					  port->message_id,
 					  port->nr_src_pdo);
 	}
@@ -818,11 +855,13 @@ static int tcpm_pd_send_sink_caps(struct tcpm_port *port)
 		msg.header = PD_HEADER_LE(PD_CTRL_REJECT,
 					  port->pwr_role,
 					  port->data_role,
+					  port->negotiated_rev,
 					  port->message_id, 0);
 	} else {
 		msg.header = PD_HEADER_LE(PD_DATA_SINK_CAP,
 					  port->pwr_role,
 					  port->data_role,
+					  port->negotiated_rev,
 					  port->message_id,
 					  port->nr_snk_pdo);
 	}
@@ -1189,6 +1228,7 @@ static void vdm_run_state_machine(struct tcpm_port *port)
 		msg.header = PD_HEADER_LE(PD_DATA_VENDOR_DEF,
 					  port->pwr_role,
 					  port->data_role,
+					  port->negotiated_rev,
 					  port->message_id, port->vdo_count);
 		for (i = 0; i < port->vdo_count; i++)
 			msg.payload[i] = cpu_to_le32(port->vdo_data[i]);
@@ -1260,6 +1300,8 @@ enum pdo_err {
 	PDO_ERR_FIXED_NOT_SORTED,
 	PDO_ERR_VARIABLE_BATT_NOT_SORTED,
 	PDO_ERR_DUPE_PDO,
+	PDO_ERR_PPS_APDO_NOT_SORTED,
+	PDO_ERR_DUPE_PPS_APDO,
 };
 
 static const char * const pdo_err_msg[] = {
@@ -1275,6 +1317,10 @@ static const char * const pdo_err_msg[] = {
 	" err: Variable/Battery supply pdos should be in increasing order of their minimum voltage",
 	[PDO_ERR_DUPE_PDO] =
 	" err: Variable/Batt supply pdos cannot have same min/max voltage",
+	[PDO_ERR_PPS_APDO_NOT_SORTED] =
+	" err: Programmable power supply apdos should be in increasing order of their maximum voltage",
+	[PDO_ERR_DUPE_PPS_APDO] =
+	" err: Programmable power supply apdos cannot have same min/max voltage and max current",
 };
 
 static enum pdo_err tcpm_caps_err(struct tcpm_port *port, const u32 *pdo,
@@ -1324,6 +1370,26 @@ static enum pdo_err tcpm_caps_err(struct tcpm_port *port, const u32 *pdo,
 					  pdo_min_voltage(pdo[i - 1])))
 					return PDO_ERR_DUPE_PDO;
 				break;
+			/*
+			 * The Programmable Power Supply APDOs, if present,
+			 * shall be sent in Maximum Voltage order;
+			 * lowest to highest.
+			 */
+			case PDO_TYPE_APDO:
+				if (pdo_apdo_type(pdo[i]) != APDO_TYPE_PPS)
+					break;
+
+				if (pdo_pps_apdo_max_current(pdo[i]) <
+				    pdo_pps_apdo_max_current(pdo[i - 1]))
+					return PDO_ERR_PPS_APDO_NOT_SORTED;
+				else if (pdo_pps_apdo_min_voltage(pdo[i]) ==
+					  pdo_pps_apdo_min_voltage(pdo[i - 1]) &&
+					 pdo_pps_apdo_max_voltage(pdo[i]) ==
+					  pdo_pps_apdo_max_voltage(pdo[i - 1]) &&
+					 pdo_pps_apdo_max_current(pdo[i]) ==
+					  pdo_pps_apdo_max_current(pdo[i - 1]))
+					return PDO_ERR_DUPE_PPS_APDO;
+				break;
 			default:
 				tcpm_log_force(port, " Unknown pdo type");
 			}
@@ -1349,11 +1415,48 @@ static int tcpm_validate_caps(struct tcpm_port *port, const u32 *pdo,
 /*
  * PD (data, control) command handling functions
  */
+static inline enum tcpm_state ready_state(struct tcpm_port *port)
+{
+	if (port->pwr_role == TYPEC_SOURCE)
+		return SRC_READY;
+	else
+		return SNK_READY;
+}
+
+static int tcpm_pd_send_control(struct tcpm_port *port,
+				enum pd_ctrl_msg_type type);
+
+static void tcpm_handle_alert(struct tcpm_port *port, const __le32 *payload,
+			      int cnt)
+{
+	u32 p0 = le32_to_cpu(payload[0]);
+	unsigned int type = usb_pd_ado_type(p0);
+
+	if (!type) {
+		tcpm_log(port, "Alert message received with no type");
+		return;
+	}
+
+	/* Just handling non-battery alerts for now */
+	if (!(type & USB_PD_ADO_TYPE_BATT_STATUS_CHANGE)) {
+		switch (port->state) {
+		case SRC_READY:
+		case SNK_READY:
+			tcpm_set_state(port, GET_STATUS_SEND, 0);
+			break;
+		default:
+			tcpm_queue_message(port, PD_MSG_CTRL_WAIT);
+			break;
+		}
+	}
+}
+
 static void tcpm_pd_data_request(struct tcpm_port *port,
 				 const struct pd_message *msg)
 {
 	enum pd_data_msg_type type = pd_header_type_le(msg->header);
 	unsigned int cnt = pd_header_cnt_le(msg->header);
+	unsigned int rev = pd_header_rev_le(msg->header);
 	unsigned int i;
 
 	switch (type) {
@@ -1372,6 +1475,17 @@ static void tcpm_pd_data_request(struct tcpm_port *port,
 				   port->nr_source_caps);
 
 		/*
+		 * Adjust revision in subsequent message headers, as required,
+		 * to comply with 6.2.1.1.5 of the USB PD 3.0 spec. We don't
+		 * support Rev 1.0 so just do nothing in that scenario.
+		 */
+		if (rev == PD_REV10)
+			break;
+
+		if (rev < PD_MAX_REV)
+			port->negotiated_rev = rev;
+
+		/*
 		 * This message may be received even if VBUS is not
 		 * present. This is quite unexpected; see USB PD
 		 * specification, sections 8.3.3.6.3.1 and 8.3.3.6.3.2.
@@ -1392,6 +1506,20 @@ static void tcpm_pd_data_request(struct tcpm_port *port,
 			tcpm_queue_message(port, PD_MSG_CTRL_REJECT);
 			break;
 		}
+
+		/*
+		 * Adjust revision in subsequent message headers, as required,
+		 * to comply with 6.2.1.1.5 of the USB PD 3.0 spec. We don't
+		 * support Rev 1.0 so just reject in that scenario.
+		 */
+		if (rev == PD_REV10) {
+			tcpm_queue_message(port, PD_MSG_CTRL_REJECT);
+			break;
+		}
+
+		if (rev < PD_MAX_REV)
+			port->negotiated_rev = rev;
+
 		port->sink_request = le32_to_cpu(msg->payload[0]);
 		tcpm_set_state(port, SRC_NEGOTIATE_CAPABILITIES, 0);
 		break;
@@ -1410,12 +1538,29 @@ static void tcpm_pd_data_request(struct tcpm_port *port,
 			tcpm_set_state(port, BIST_RX, 0);
 		}
 		break;
+	case PD_DATA_ALERT:
+		tcpm_handle_alert(port, msg->payload, cnt);
+		break;
+	case PD_DATA_BATT_STATUS:
+	case PD_DATA_GET_COUNTRY_INFO:
+		/* Currently unsupported */
+		tcpm_queue_message(port, PD_MSG_CTRL_NOT_SUPP);
+		break;
 	default:
 		tcpm_log(port, "Unhandled data message type %#x", type);
 		break;
 	}
 }
 
+static void tcpm_pps_complete(struct tcpm_port *port, int result)
+{
+	if (port->pps_pending) {
+		port->pps_status = result;
+		port->pps_pending = false;
+		complete(&port->pps_complete);
+	}
+}
+
 static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 				 const struct pd_message *msg)
 {
@@ -1483,6 +1628,7 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 		break;
 	case PD_CTRL_REJECT:
 	case PD_CTRL_WAIT:
+	case PD_CTRL_NOT_SUPP:
 		switch (port->state) {
 		case SNK_NEGOTIATE_CAPABILITIES:
 			/* USB PD specification, Figure 8-43 */
@@ -1492,6 +1638,14 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 				next_state = SNK_WAIT_CAPABILITIES;
 			tcpm_set_state(port, next_state, 0);
 			break;
+		case SNK_NEGOTIATE_PPS_CAPABILITIES:
+			/* Revert data back from any requested PPS updates */
+			port->pps_data.out_volt = port->supply_voltage;
+			port->pps_data.op_curr = port->current_limit;
+			port->pps_status = (type == PD_CTRL_WAIT ?
+					    -EAGAIN : -EOPNOTSUPP);
+			tcpm_set_state(port, SNK_READY, 0);
+			break;
 		case DR_SWAP_SEND:
 			port->swap_status = (type == PD_CTRL_WAIT ?
 					     -EAGAIN : -EOPNOTSUPP);
@@ -1514,6 +1668,13 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 	case PD_CTRL_ACCEPT:
 		switch (port->state) {
 		case SNK_NEGOTIATE_CAPABILITIES:
+			port->pps_data.active = false;
+			tcpm_set_state(port, SNK_TRANSITION_SINK, 0);
+			break;
+		case SNK_NEGOTIATE_PPS_CAPABILITIES:
+			port->pps_data.active = true;
+			port->supply_voltage = port->pps_data.out_volt;
+			port->current_limit = port->pps_data.op_curr;
 			tcpm_set_state(port, SNK_TRANSITION_SINK, 0);
 			break;
 		case SOFT_RESET_SEND:
@@ -1587,12 +1748,75 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 			break;
 		}
 		break;
+	case PD_CTRL_GET_SOURCE_CAP_EXT:
+	case PD_CTRL_GET_STATUS:
+	case PD_CTRL_FR_SWAP:
+	case PD_CTRL_GET_PPS_STATUS:
+	case PD_CTRL_GET_COUNTRY_CODES:
+		/* Currently not supported */
+		tcpm_queue_message(port, PD_MSG_CTRL_NOT_SUPP);
+		break;
 	default:
 		tcpm_log(port, "Unhandled ctrl message type %#x", type);
 		break;
 	}
 }
 
+static void tcpm_pd_ext_msg_request(struct tcpm_port *port,
+				    const struct pd_message *msg)
+{
+	enum pd_ext_msg_type type = pd_header_type_le(msg->header);
+	unsigned int data_size = pd_ext_header_data_size_le(msg->ext_msg.header);
+
+	if (!(msg->ext_msg.header & PD_EXT_HDR_CHUNKED)) {
+		tcpm_log(port, "Unchunked extended messages unsupported");
+		return;
+	}
+
+	if (data_size > PD_EXT_MAX_CHUNK_DATA) {
+		tcpm_log(port, "Chunk handling not yet supported");
+		return;
+	}
+
+	switch (type) {
+	case PD_EXT_STATUS:
+		/*
+		 * If PPS related events raised then get PPS status to clear
+		 * (see USB PD 3.0 Spec, 6.5.2.4)
+		 */
+		if (msg->ext_msg.data[USB_PD_EXT_SDB_EVENT_FLAGS] &
+		    USB_PD_EXT_SDB_PPS_EVENTS)
+			tcpm_set_state(port, GET_PPS_STATUS_SEND, 0);
+		else
+			tcpm_set_state(port, ready_state(port), 0);
+		break;
+	case PD_EXT_PPS_STATUS:
+		/*
+		 * For now the PPS status message is used to clear events
+		 * and nothing more.
+		 */
+		tcpm_set_state(port, ready_state(port), 0);
+		break;
+	case PD_EXT_SOURCE_CAP_EXT:
+	case PD_EXT_GET_BATT_CAP:
+	case PD_EXT_GET_BATT_STATUS:
+	case PD_EXT_BATT_CAP:
+	case PD_EXT_GET_MANUFACTURER_INFO:
+	case PD_EXT_MANUFACTURER_INFO:
+	case PD_EXT_SECURITY_REQUEST:
+	case PD_EXT_SECURITY_RESPONSE:
+	case PD_EXT_FW_UPDATE_REQUEST:
+	case PD_EXT_FW_UPDATE_RESPONSE:
+	case PD_EXT_COUNTRY_INFO:
+	case PD_EXT_COUNTRY_CODES:
+		tcpm_queue_message(port, PD_MSG_CTRL_NOT_SUPP);
+		break;
+	default:
+		tcpm_log(port, "Unhandled extended message type %#x", type);
+		break;
+	}
+}
+
 static void tcpm_pd_rx_handler(struct work_struct *work)
 {
 	struct pd_rx_event *event = container_of(work,
@@ -1633,7 +1857,9 @@ static void tcpm_pd_rx_handler(struct work_struct *work)
 				 "Data role mismatch, initiating error recovery");
 			tcpm_set_state(port, ERROR_RECOVERY, 0);
 		} else {
-			if (cnt)
+			if (msg->header & PD_HEADER_EXT_HDR)
+				tcpm_pd_ext_msg_request(port, msg);
+			else if (cnt)
 				tcpm_pd_data_request(port, msg);
 			else
 				tcpm_pd_ctrl_request(port, msg);
@@ -1668,6 +1894,7 @@ static int tcpm_pd_send_control(struct tcpm_port *port,
 	memset(&msg, 0, sizeof(msg));
 	msg.header = PD_HEADER_LE(type, port->pwr_role,
 				  port->data_role,
+				  port->negotiated_rev,
 				  port->message_id, 0);
 
 	return tcpm_pd_transmit(port, TCPC_TX_SOP, &msg);
@@ -1693,6 +1920,9 @@ static bool tcpm_send_queued_message(struct tcpm_port *port)
 		case PD_MSG_CTRL_REJECT:
 			tcpm_pd_send_control(port, PD_CTRL_REJECT);
 			break;
+		case PD_MSG_CTRL_NOT_SUPP:
+			tcpm_pd_send_control(port, PD_CTRL_NOT_SUPP);
+			break;
 		case PD_MSG_DATA_SINK_CAP:
 			tcpm_pd_send_sink_caps(port);
 			break;
@@ -1772,84 +2002,254 @@ static int tcpm_pd_check_request(struct tcpm_port *port)
 	return 0;
 }
 
-static int tcpm_pd_select_pdo(struct tcpm_port *port)
+#define min_power(x, y) min(pdo_max_power(x), pdo_max_power(y))
+#define min_current(x, y) min(pdo_max_current(x), pdo_max_current(y))
+
+static int tcpm_pd_select_pdo(struct tcpm_port *port, int *sink_pdo,
+			      int *src_pdo)
 {
-	unsigned int i, max_mw = 0, max_mv = 0;
+	unsigned int i, j, max_src_mv = 0, min_src_mv = 0, max_mw = 0,
+		     max_mv = 0, src_mw = 0, src_ma = 0, max_snk_mv = 0,
+		     min_snk_mv = 0;
 	int ret = -EINVAL;
 
+	port->pps_data.supported = false;
+	port->usb_type = POWER_SUPPLY_USB_TYPE_PD;
+
 	/*
-	 * Select the source PDO providing the most power while staying within
-	 * the board's voltage limits. Prefer PDO providing exp
+	 * Select the source PDO providing the most power which has a
+	 * matchig sink cap.
 	 */
 	for (i = 0; i < port->nr_source_caps; i++) {
 		u32 pdo = port->source_caps[i];
 		enum pd_pdo_type type = pdo_type(pdo);
-		unsigned int mv, ma, mw;
 
-		if (type == PDO_TYPE_FIXED)
-			mv = pdo_fixed_voltage(pdo);
-		else
-			mv = pdo_min_voltage(pdo);
+		switch (type) {
+		case PDO_TYPE_FIXED:
+			max_src_mv = pdo_fixed_voltage(pdo);
+			min_src_mv = max_src_mv;
+			break;
+		case PDO_TYPE_BATT:
+		case PDO_TYPE_VAR:
+			max_src_mv = pdo_max_voltage(pdo);
+			min_src_mv = pdo_min_voltage(pdo);
+			break;
+		case PDO_TYPE_APDO:
+			if (pdo_apdo_type(pdo) == APDO_TYPE_PPS) {
+				port->pps_data.supported = true;
+				port->usb_type =
+					POWER_SUPPLY_USB_TYPE_PD_PPS;
+			}
+			continue;
+		default:
+			tcpm_log(port, "Invalid source PDO type, ignoring");
+			continue;
+		}
 
-		if (type == PDO_TYPE_BATT) {
-			mw = pdo_max_power(pdo);
-		} else {
-			ma = min(pdo_max_current(pdo),
-				 port->max_snk_ma);
-			mw = ma * mv / 1000;
+		switch (type) {
+		case PDO_TYPE_FIXED:
+		case PDO_TYPE_VAR:
+			src_ma = pdo_max_current(pdo);
+			src_mw = src_ma * min_src_mv / 1000;
+			break;
+		case PDO_TYPE_BATT:
+			src_mw = pdo_max_power(pdo);
+			break;
+		case PDO_TYPE_APDO:
+			continue;
+		default:
+			tcpm_log(port, "Invalid source PDO type, ignoring");
+			continue;
 		}
 
-		/* Perfer higher voltages if available */
-		if ((mw > max_mw || (mw == max_mw && mv > max_mv)) &&
-		    mv <= port->max_snk_mv) {
-			ret = i;
-			max_mw = mw;
-			max_mv = mv;
+		for (j = 0; j < port->nr_snk_pdo; j++) {
+			pdo = port->snk_pdo[j];
+
+			switch (pdo_type(pdo)) {
+			case PDO_TYPE_FIXED:
+				max_snk_mv = pdo_fixed_voltage(pdo);
+				min_snk_mv = max_snk_mv;
+				break;
+			case PDO_TYPE_BATT:
+			case PDO_TYPE_VAR:
+				max_snk_mv = pdo_max_voltage(pdo);
+				min_snk_mv = pdo_min_voltage(pdo);
+				break;
+			case PDO_TYPE_APDO:
+				continue;
+			default:
+				tcpm_log(port, "Invalid sink PDO type, ignoring");
+				continue;
+			}
+
+			if (max_src_mv <= max_snk_mv &&
+				min_src_mv >= min_snk_mv) {
+				/* Prefer higher voltages if available */
+				if ((src_mw == max_mw && min_src_mv > max_mv) ||
+							src_mw > max_mw) {
+					*src_pdo = i;
+					*sink_pdo = j;
+					max_mw = src_mw;
+					max_mv = min_src_mv;
+					ret = 0;
+				}
+			}
 		}
 	}
 
 	return ret;
 }
 
+#define min_pps_apdo_current(x, y)	\
+	min(pdo_pps_apdo_max_current(x), pdo_pps_apdo_max_current(y))
+
+static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port)
+{
+	unsigned int i, j, max_mw = 0, max_mv = 0;
+	unsigned int min_src_mv, max_src_mv, src_ma, src_mw;
+	unsigned int min_snk_mv, max_snk_mv, snk_ma;
+	u32 pdo;
+	unsigned int src_pdo = 0, snk_pdo = 0;
+
+	/*
+	 * Select the source PPS APDO providing the most power while staying
+	 * within the board's limits. We skip the first PDO as this is always
+	 * 5V 3A.
+	 */
+	for (i = 1; i < port->nr_source_caps; ++i) {
+		pdo = port->source_caps[i];
+
+		switch (pdo_type(pdo)) {
+		case PDO_TYPE_APDO:
+			if (pdo_apdo_type(pdo) != APDO_TYPE_PPS) {
+				tcpm_log(port, "Not PPS APDO (source), ignoring");
+				continue;
+			}
+
+			min_src_mv = pdo_pps_apdo_min_voltage(pdo);
+			max_src_mv = pdo_pps_apdo_max_voltage(pdo);
+			src_ma = pdo_pps_apdo_max_current(pdo);
+			src_mw = (src_ma * max_src_mv) / 1000;
+
+			/*
+			 * Now search through the sink PDOs to find a matching
+			 * PPS APDO. Again skip the first sink PDO as this will
+			 * always be 5V 3A.
+			 */
+			for (j = i; j < port->nr_snk_pdo; j++) {
+				pdo = port->snk_pdo[j];
+
+				switch (pdo_type(pdo)) {
+				case PDO_TYPE_APDO:
+					if (pdo_apdo_type(pdo) != APDO_TYPE_PPS) {
+						tcpm_log(port,
+							 "Not PPS APDO (sink), ignoring");
+						continue;
+					}
+
+					min_snk_mv =
+						pdo_pps_apdo_min_voltage(pdo);
+					max_snk_mv =
+						pdo_pps_apdo_max_voltage(pdo);
+					snk_ma =
+						pdo_pps_apdo_max_current(pdo);
+					break;
+				default:
+					tcpm_log(port,
+						 "Not APDO type (sink), ignoring");
+					continue;
+				}
+
+				if (max_src_mv <= max_snk_mv &&
+				    min_src_mv >= min_snk_mv) {
+					/* Prefer higher voltages if available */
+					if ((src_mw == max_mw &&
+					     min_src_mv > max_mv) ||
+					    src_mw > max_mw) {
+						src_pdo = i;
+						snk_pdo = j;
+						max_mw = src_mw;
+						max_mv = max_src_mv;
+					}
+				}
+			}
+
+			break;
+		default:
+			tcpm_log(port, "Not APDO type (source), ignoring");
+			continue;
+		}
+	}
+
+	if (src_pdo) {
+		pdo = port->source_caps[src_pdo];
+
+		port->pps_data.min_volt = pdo_pps_apdo_min_voltage(pdo);
+		port->pps_data.max_volt = pdo_pps_apdo_max_voltage(pdo);
+		port->pps_data.max_curr =
+			min_pps_apdo_current(pdo, port->snk_pdo[snk_pdo]);
+		port->pps_data.out_volt =
+			min(pdo_pps_apdo_max_voltage(pdo), port->pps_data.out_volt);
+		port->pps_data.op_curr =
+			min(port->pps_data.max_curr, port->pps_data.op_curr);
+	}
+
+	return src_pdo;
+}
+
 static int tcpm_pd_build_request(struct tcpm_port *port, u32 *rdo)
 {
 	unsigned int mv, ma, mw, flags;
 	unsigned int max_ma, max_mw;
 	enum pd_pdo_type type;
-	int index;
-	u32 pdo;
+	u32 pdo, matching_snk_pdo;
+	int src_pdo_index = 0;
+	int snk_pdo_index = 0;
+	int ret;
 
-	index = tcpm_pd_select_pdo(port);
-	if (index < 0)
-		return -EINVAL;
-	pdo = port->source_caps[index];
+	ret = tcpm_pd_select_pdo(port, &snk_pdo_index, &src_pdo_index);
+	if (ret < 0)
+		return ret;
+
+	pdo = port->source_caps[src_pdo_index];
+	matching_snk_pdo = port->snk_pdo[snk_pdo_index];
 	type = pdo_type(pdo);
 
-	if (type == PDO_TYPE_FIXED)
+	switch (type) {
+	case PDO_TYPE_FIXED:
 		mv = pdo_fixed_voltage(pdo);
-	else
+		break;
+	case PDO_TYPE_BATT:
+	case PDO_TYPE_VAR:
 		mv = pdo_min_voltage(pdo);
+		break;
+	default:
+		tcpm_log(port, "Invalid PDO selected!");
+		return -EINVAL;
+	}
 
-	/* Select maximum available current within the board's power limit */
+	/* Select maximum available current within the sink pdo's limit */
 	if (type == PDO_TYPE_BATT) {
-		mw = pdo_max_power(pdo);
-		ma = 1000 * min(mw, port->max_snk_mw) / mv;
+		mw = min_power(pdo, matching_snk_pdo);
+		ma = 1000 * mw / mv;
 	} else {
-		ma = min(pdo_max_current(pdo),
-			 1000 * port->max_snk_mw / mv);
+		ma = min_current(pdo, matching_snk_pdo);
+		mw = ma * mv / 1000;
 	}
-	ma = min(ma, port->max_snk_ma);
 
 	flags = RDO_USB_COMM | RDO_NO_SUSPEND;
 
 	/* Set mismatch bit if offered power is less than operating power */
-	mw = ma * mv / 1000;
 	max_ma = ma;
 	max_mw = mw;
 	if (mw < port->operating_snk_mw) {
 		flags |= RDO_CAP_MISMATCH;
-		max_mw = port->operating_snk_mw;
-		max_ma = max_mw * 1000 / mv;
+		if (type == PDO_TYPE_BATT &&
+		    (pdo_max_power(matching_snk_pdo) > pdo_max_power(pdo)))
+			max_mw = pdo_max_power(matching_snk_pdo);
+		else if (pdo_max_current(matching_snk_pdo) >
+			 pdo_max_current(pdo))
+			max_ma = pdo_max_current(matching_snk_pdo);
 	}
 
 	tcpm_log(port, "cc=%d cc1=%d cc2=%d vbus=%d vconn=%s polarity=%d",
@@ -1858,16 +2258,16 @@ static int tcpm_pd_build_request(struct tcpm_port *port, u32 *rdo)
 		 port->polarity);
 
 	if (type == PDO_TYPE_BATT) {
-		*rdo = RDO_BATT(index + 1, mw, max_mw, flags);
+		*rdo = RDO_BATT(src_pdo_index + 1, mw, max_mw, flags);
 
 		tcpm_log(port, "Requesting PDO %d: %u mV, %u mW%s",
-			 index, mv, mw,
+			 src_pdo_index, mv, mw,
 			 flags & RDO_CAP_MISMATCH ? " [mismatch]" : "");
 	} else {
-		*rdo = RDO_FIXED(index + 1, ma, max_ma, flags);
+		*rdo = RDO_FIXED(src_pdo_index + 1, ma, max_ma, flags);
 
 		tcpm_log(port, "Requesting PDO %d: %u mV, %u mA%s",
-			 index, mv, ma,
+			 src_pdo_index, mv, ma,
 			 flags & RDO_CAP_MISMATCH ? " [mismatch]" : "");
 	}
 
@@ -1891,6 +2291,105 @@ static int tcpm_pd_send_request(struct tcpm_port *port)
 	msg.header = PD_HEADER_LE(PD_DATA_REQUEST,
 				  port->pwr_role,
 				  port->data_role,
+				  port->negotiated_rev,
+				  port->message_id, 1);
+	msg.payload[0] = cpu_to_le32(rdo);
+
+	return tcpm_pd_transmit(port, TCPC_TX_SOP, &msg);
+}
+
+static int tcpm_pd_build_pps_request(struct tcpm_port *port, u32 *rdo)
+{
+	unsigned int out_mv, op_ma, op_mw, min_mv, max_mv, max_ma, flags;
+	enum pd_pdo_type type;
+	unsigned int src_pdo_index;
+	u32 pdo;
+
+	src_pdo_index = tcpm_pd_select_pps_apdo(port);
+	if (!src_pdo_index)
+		return -EOPNOTSUPP;
+
+	pdo = port->source_caps[src_pdo_index];
+	type = pdo_type(pdo);
+
+	switch (type) {
+	case PDO_TYPE_APDO:
+		if (pdo_apdo_type(pdo) != APDO_TYPE_PPS) {
+			tcpm_log(port, "Invalid APDO selected!");
+			return -EINVAL;
+		}
+		min_mv = port->pps_data.min_volt;
+		max_mv = port->pps_data.max_volt;
+		max_ma = port->pps_data.max_curr;
+		out_mv = port->pps_data.out_volt;
+		op_ma = port->pps_data.op_curr;
+		break;
+	default:
+		tcpm_log(port, "Invalid PDO selected!");
+		return -EINVAL;
+	}
+
+	flags = RDO_USB_COMM | RDO_NO_SUSPEND;
+
+	op_mw = (op_ma * out_mv) / 1000;
+	if (op_mw < port->operating_snk_mw) {
+		/*
+		 * Try raising current to meet power needs. If that's not enough
+		 * then try upping the voltage. If that's still not enough
+		 * then we've obviously chosen a PPS APDO which really isn't
+		 * suitable so abandon ship.
+		 */
+		op_ma = (port->operating_snk_mw * 1000) / out_mv;
+		if ((port->operating_snk_mw * 1000) % out_mv)
+			++op_ma;
+		op_ma += RDO_PROG_CURR_MA_STEP - (op_ma % RDO_PROG_CURR_MA_STEP);
+
+		if (op_ma > max_ma) {
+			op_ma = max_ma;
+			out_mv = (port->operating_snk_mw * 1000) / op_ma;
+			if ((port->operating_snk_mw * 1000) % op_ma)
+				++out_mv;
+			out_mv += RDO_PROG_VOLT_MV_STEP -
+				  (out_mv % RDO_PROG_VOLT_MV_STEP);
+
+			if (out_mv > max_mv) {
+				tcpm_log(port, "Invalid PPS APDO selected!");
+				return -EINVAL;
+			}
+		}
+	}
+
+	tcpm_log(port, "cc=%d cc1=%d cc2=%d vbus=%d vconn=%s polarity=%d",
+		 port->cc_req, port->cc1, port->cc2, port->vbus_source,
+		 port->vconn_role == TYPEC_SOURCE ? "source" : "sink",
+		 port->polarity);
+
+	*rdo = RDO_PROG(src_pdo_index + 1, out_mv, op_ma, flags);
+
+	tcpm_log(port, "Requesting APDO %d: %u mV, %u mA",
+		 src_pdo_index, out_mv, op_ma);
+
+	port->pps_data.op_curr = op_ma;
+	port->pps_data.out_volt = out_mv;
+
+	return 0;
+}
+
+static int tcpm_pd_send_pps_request(struct tcpm_port *port)
+{
+	struct pd_message msg;
+	int ret;
+	u32 rdo;
+
+	ret = tcpm_pd_build_pps_request(port, &rdo);
+	if (ret < 0)
+		return ret;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.header = PD_HEADER_LE(PD_DATA_REQUEST,
+				  port->pwr_role,
+				  port->data_role,
+				  port->negotiated_rev,
 				  port->message_id, 1);
 	msg.payload[0] = cpu_to_le32(rdo);
 
@@ -2077,6 +2576,7 @@ static void tcpm_reset_port(struct tcpm_port *port)
 	tcpm_typec_disconnect(port);
 	port->attached = false;
 	port->pd_capable = false;
+	port->pps_data.supported = false;
 
 	/*
 	 * First Rx ID should be 0; set this to a sentinel of -1 so that
@@ -2094,6 +2594,11 @@ static void tcpm_reset_port(struct tcpm_port *port)
 	tcpm_set_attached_state(port, false);
 	port->try_src_count = 0;
 	port->try_snk_count = 0;
+	port->supply_voltage = 0;
+	port->current_limit = 0;
+	port->usb_type = POWER_SUPPLY_USB_TYPE_C;
+
+	power_supply_changed(port->psy);
 }
 
 static void tcpm_detach(struct tcpm_port *port)
@@ -2181,14 +2686,6 @@ static inline enum tcpm_state hard_reset_state(struct tcpm_port *port)
 	return SNK_UNATTACHED;
 }
 
-static inline enum tcpm_state ready_state(struct tcpm_port *port)
-{
-	if (port->pwr_role == TYPEC_SOURCE)
-		return SRC_READY;
-	else
-		return SNK_READY;
-}
-
 static inline enum tcpm_state unattached_state(struct tcpm_port *port)
 {
 	if (port->port_type == TYPEC_PORT_DRP) {
@@ -2338,6 +2835,7 @@ static void run_state_machine(struct tcpm_port *port)
 		typec_set_pwr_opmode(port->typec_port, opmode);
 		port->pwr_opmode = TYPEC_PWR_MODE_USB;
 		port->caps_count = 0;
+		port->negotiated_rev = PD_MAX_REV;
 		port->message_id = 0;
 		port->rx_msgid = -1;
 		port->explicit_contract = false;
@@ -2398,6 +2896,7 @@ static void run_state_machine(struct tcpm_port *port)
 
 		tcpm_swap_complete(port, 0);
 		tcpm_typec_connect(port);
+
 		tcpm_check_send_discover(port);
 		/*
 		 * 6.3.5
@@ -2421,6 +2920,7 @@ static void run_state_machine(struct tcpm_port *port)
 	case SNK_UNATTACHED:
 		if (!port->non_pd_role_swap)
 			tcpm_swap_complete(port, -ENOTCONN);
+		tcpm_pps_complete(port, -ENOTCONN);
 		tcpm_snk_detach(port);
 		if (tcpm_start_drp_toggling(port)) {
 			tcpm_set_state(port, DRP_TOGGLING, 0);
@@ -2510,6 +3010,7 @@ static void run_state_machine(struct tcpm_port *port)
 					      port->cc2 : port->cc1);
 		typec_set_pwr_opmode(port->typec_port, opmode);
 		port->pwr_opmode = TYPEC_PWR_MODE_USB;
+		port->negotiated_rev = PD_MAX_REV;
 		port->message_id = 0;
 		port->rx_msgid = -1;
 		port->explicit_contract = false;
@@ -2580,6 +3081,24 @@ static void run_state_machine(struct tcpm_port *port)
 					    PD_T_SENDER_RESPONSE);
 		}
 		break;
+	case SNK_NEGOTIATE_PPS_CAPABILITIES:
+		ret = tcpm_pd_send_pps_request(port);
+		if (ret < 0) {
+			port->pps_status = ret;
+			/*
+			 * If this was called due to updates to sink
+			 * capabilities, and pps is no longer valid, we should
+			 * safely fall back to a standard PDO.
+			 */
+			if (port->update_sink_caps)
+				tcpm_set_state(port, SNK_NEGOTIATE_CAPABILITIES, 0);
+			else
+				tcpm_set_state(port, SNK_READY, 0);
+		} else {
+			tcpm_set_state_cond(port, hard_reset_state(port),
+					    PD_T_SENDER_RESPONSE);
+		}
+		break;
 	case SNK_TRANSITION_SINK:
 	case SNK_TRANSITION_SINK_VBUS:
 		tcpm_set_state(port, hard_reset_state(port),
@@ -2587,6 +3106,7 @@ static void run_state_machine(struct tcpm_port *port)
 		break;
 	case SNK_READY:
 		port->try_snk_count = 0;
+		port->update_sink_caps = false;
 		if (port->explicit_contract) {
 			typec_set_pwr_opmode(port->typec_port,
 					     TYPEC_PWR_MODE_PD);
@@ -2596,6 +3116,10 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_swap_complete(port, 0);
 		tcpm_typec_connect(port);
 		tcpm_check_send_discover(port);
+		tcpm_pps_complete(port, port->pps_status);
+
+		power_supply_changed(port->psy);
+
 		break;
 
 	/* Accessory states */
@@ -2642,6 +3166,7 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_state(port, SRC_UNATTACHED, PD_T_PS_SOURCE_ON);
 		break;
 	case SNK_HARD_RESET_SINK_OFF:
+		memset(&port->pps_data, 0, sizeof(port->pps_data));
 		tcpm_set_vconn(port, false);
 		tcpm_set_charge(port, false);
 		tcpm_set_roles(port, false, TYPEC_SINK, TYPEC_DEVICE);
@@ -2860,8 +3385,25 @@ static void run_state_machine(struct tcpm_port *port)
 		/* Always switch to unattached state */
 		tcpm_set_state(port, unattached_state(port), 0);
 		break;
+	case GET_STATUS_SEND:
+		tcpm_pd_send_control(port, PD_CTRL_GET_STATUS);
+		tcpm_set_state(port, GET_STATUS_SEND_TIMEOUT,
+			       PD_T_SENDER_RESPONSE);
+		break;
+	case GET_STATUS_SEND_TIMEOUT:
+		tcpm_set_state(port, ready_state(port), 0);
+		break;
+	case GET_PPS_STATUS_SEND:
+		tcpm_pd_send_control(port, PD_CTRL_GET_PPS_STATUS);
+		tcpm_set_state(port, GET_PPS_STATUS_SEND_TIMEOUT,
+			       PD_T_SENDER_RESPONSE);
+		break;
+	case GET_PPS_STATUS_SEND_TIMEOUT:
+		tcpm_set_state(port, ready_state(port), 0);
+		break;
 	case ERROR_RECOVERY:
 		tcpm_swap_complete(port, -EPROTO);
+		tcpm_pps_complete(port, -EPROTO);
 		tcpm_set_state(port, PORT_RESET, 0);
 		break;
 	case PORT_RESET:
@@ -3444,6 +3986,162 @@ static int tcpm_try_role(const struct typec_capability *cap, int role)
 	return ret;
 }
 
+static int tcpm_pps_set_op_curr(struct tcpm_port *port, u16 op_curr)
+{
+	unsigned int target_mw;
+	int ret;
+
+	mutex_lock(&port->swap_lock);
+	mutex_lock(&port->lock);
+
+	if (!port->pps_data.active) {
+		ret = -EOPNOTSUPP;
+		goto port_unlock;
+	}
+
+	if (port->state != SNK_READY) {
+		ret = -EAGAIN;
+		goto port_unlock;
+	}
+
+	if (op_curr > port->pps_data.max_curr) {
+		ret = -EINVAL;
+		goto port_unlock;
+	}
+
+	target_mw = (op_curr * port->pps_data.out_volt) / 1000;
+	if (target_mw < port->operating_snk_mw) {
+		ret = -EINVAL;
+		goto port_unlock;
+	}
+
+	reinit_completion(&port->pps_complete);
+	port->pps_data.op_curr = op_curr;
+	port->pps_status = 0;
+	port->pps_pending = true;
+	tcpm_set_state(port, SNK_NEGOTIATE_PPS_CAPABILITIES, 0);
+	mutex_unlock(&port->lock);
+
+	if (!wait_for_completion_timeout(&port->pps_complete,
+				msecs_to_jiffies(PD_PPS_CTRL_TIMEOUT)))
+		ret = -ETIMEDOUT;
+	else
+		ret = port->pps_status;
+
+	goto swap_unlock;
+
+port_unlock:
+	mutex_unlock(&port->lock);
+swap_unlock:
+	mutex_unlock(&port->swap_lock);
+
+	return ret;
+}
+
+static int tcpm_pps_set_out_volt(struct tcpm_port *port, u16 out_volt)
+{
+	unsigned int target_mw;
+	int ret;
+
+	mutex_lock(&port->swap_lock);
+	mutex_lock(&port->lock);
+
+	if (!port->pps_data.active) {
+		ret = -EOPNOTSUPP;
+		goto port_unlock;
+	}
+
+	if (port->state != SNK_READY) {
+		ret = -EAGAIN;
+		goto port_unlock;
+	}
+
+	if (out_volt < port->pps_data.min_volt ||
+	    out_volt > port->pps_data.max_volt) {
+		ret = -EINVAL;
+		goto port_unlock;
+	}
+
+	target_mw = (port->pps_data.op_curr * out_volt) / 1000;
+	if (target_mw < port->operating_snk_mw) {
+		ret = -EINVAL;
+		goto port_unlock;
+	}
+
+	reinit_completion(&port->pps_complete);
+	port->pps_data.out_volt = out_volt;
+	port->pps_status = 0;
+	port->pps_pending = true;
+	tcpm_set_state(port, SNK_NEGOTIATE_PPS_CAPABILITIES, 0);
+	mutex_unlock(&port->lock);
+
+	if (!wait_for_completion_timeout(&port->pps_complete,
+				msecs_to_jiffies(PD_PPS_CTRL_TIMEOUT)))
+		ret = -ETIMEDOUT;
+	else
+		ret = port->pps_status;
+
+	goto swap_unlock;
+
+port_unlock:
+	mutex_unlock(&port->lock);
+swap_unlock:
+	mutex_unlock(&port->swap_lock);
+
+	return ret;
+}
+
+static int tcpm_pps_activate(struct tcpm_port *port, bool activate)
+{
+	int ret = 0;
+
+	mutex_lock(&port->swap_lock);
+	mutex_lock(&port->lock);
+
+	if (!port->pps_data.supported) {
+		ret = -EOPNOTSUPP;
+		goto port_unlock;
+	}
+
+	/* Trying to deactivate PPS when already deactivated so just bail */
+	if (!port->pps_data.active && !activate)
+		goto port_unlock;
+
+	if (port->state != SNK_READY) {
+		ret = -EAGAIN;
+		goto port_unlock;
+	}
+
+	reinit_completion(&port->pps_complete);
+	port->pps_status = 0;
+	port->pps_pending = true;
+
+	/* Trigger PPS request or move back to standard PDO contract */
+	if (activate) {
+		port->pps_data.out_volt = port->supply_voltage;
+		port->pps_data.op_curr = port->current_limit;
+		tcpm_set_state(port, SNK_NEGOTIATE_PPS_CAPABILITIES, 0);
+	} else {
+		tcpm_set_state(port, SNK_NEGOTIATE_CAPABILITIES, 0);
+	}
+	mutex_unlock(&port->lock);
+
+	if (!wait_for_completion_timeout(&port->pps_complete,
+				msecs_to_jiffies(PD_PPS_CTRL_TIMEOUT)))
+		ret = -ETIMEDOUT;
+	else
+		ret = port->pps_status;
+
+	goto swap_unlock;
+
+port_unlock:
+	mutex_unlock(&port->lock);
+swap_unlock:
+	mutex_unlock(&port->swap_lock);
+
+	return ret;
+}
+
 static void tcpm_init(struct tcpm_port *port)
 {
 	enum typec_cc_status cc1, cc2;
@@ -3569,9 +4267,6 @@ EXPORT_SYMBOL_GPL(tcpm_update_source_capabilities);
 
 int tcpm_update_sink_capabilities(struct tcpm_port *port, const u32 *pdo,
 				  unsigned int nr_pdo,
-				  unsigned int max_snk_mv,
-				  unsigned int max_snk_ma,
-				  unsigned int max_snk_mw,
 				  unsigned int operating_snk_mw)
 {
 	if (tcpm_validate_caps(port, pdo, nr_pdo))
@@ -3579,17 +4274,19 @@ int tcpm_update_sink_capabilities(struct tcpm_port *port, const u32 *pdo,
 
 	mutex_lock(&port->lock);
 	port->nr_snk_pdo = tcpm_copy_pdos(port->snk_pdo, pdo, nr_pdo);
-	port->max_snk_mv = max_snk_mv;
-	port->max_snk_ma = max_snk_ma;
-	port->max_snk_mw = max_snk_mw;
 	port->operating_snk_mw = operating_snk_mw;
+	port->update_sink_caps = true;
 
 	switch (port->state) {
 	case SNK_NEGOTIATE_CAPABILITIES:
+	case SNK_NEGOTIATE_PPS_CAPABILITIES:
 	case SNK_READY:
 	case SNK_TRANSITION_SINK:
 	case SNK_TRANSITION_SINK_VBUS:
-		tcpm_set_state(port, SNK_NEGOTIATE_CAPABILITIES, 0);
+		if (port->pps_data.active)
+			tcpm_set_state(port, SNK_NEGOTIATE_PPS_CAPABILITIES, 0);
+		else
+			tcpm_set_state(port, SNK_NEGOTIATE_CAPABILITIES, 0);
 		break;
 	default:
 		break;
@@ -3599,6 +4296,231 @@ int tcpm_update_sink_capabilities(struct tcpm_port *port, const u32 *pdo,
 }
 EXPORT_SYMBOL_GPL(tcpm_update_sink_capabilities);
 
+/* Power Supply access to expose source power information */
+enum tcpm_psy_online_states {
+	TCPM_PSY_OFFLINE = 0,
+	TCPM_PSY_FIXED_ONLINE,
+	TCPM_PSY_PROG_ONLINE,
+};
+
+static enum power_supply_property tcpm_psy_props[] = {
+	POWER_SUPPLY_PROP_USB_TYPE,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN,
+	POWER_SUPPLY_PROP_VOLTAGE_MAX,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_MAX,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+};
+
+static int tcpm_psy_get_online(struct tcpm_port *port,
+			       union power_supply_propval *val)
+{
+	if (port->vbus_charge) {
+		if (port->pps_data.active)
+			val->intval = TCPM_PSY_PROG_ONLINE;
+		else
+			val->intval = TCPM_PSY_FIXED_ONLINE;
+	} else {
+		val->intval = TCPM_PSY_OFFLINE;
+	}
+
+	return 0;
+}
+
+static int tcpm_psy_get_voltage_min(struct tcpm_port *port,
+				    union power_supply_propval *val)
+{
+	if (port->pps_data.active)
+		val->intval = port->pps_data.min_volt * 1000;
+	else
+		val->intval = port->supply_voltage * 1000;
+
+	return 0;
+}
+
+static int tcpm_psy_get_voltage_max(struct tcpm_port *port,
+				    union power_supply_propval *val)
+{
+	if (port->pps_data.active)
+		val->intval = port->pps_data.max_volt * 1000;
+	else
+		val->intval = port->supply_voltage * 1000;
+
+	return 0;
+}
+
+static int tcpm_psy_get_voltage_now(struct tcpm_port *port,
+				    union power_supply_propval *val)
+{
+	val->intval = port->supply_voltage * 1000;
+
+	return 0;
+}
+
+static int tcpm_psy_get_current_max(struct tcpm_port *port,
+				    union power_supply_propval *val)
+{
+	if (port->pps_data.active)
+		val->intval = port->pps_data.max_curr * 1000;
+	else
+		val->intval = port->current_limit * 1000;
+
+	return 0;
+}
+
+static int tcpm_psy_get_current_now(struct tcpm_port *port,
+				    union power_supply_propval *val)
+{
+	val->intval = port->current_limit * 1000;
+
+	return 0;
+}
+
+static int tcpm_psy_get_prop(struct power_supply *psy,
+			     enum power_supply_property psp,
+			     union power_supply_propval *val)
+{
+	struct tcpm_port *port = power_supply_get_drvdata(psy);
+	int ret = 0;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_USB_TYPE:
+		val->intval = port->usb_type;
+		break;
+	case POWER_SUPPLY_PROP_ONLINE:
+		ret = tcpm_psy_get_online(port, val);
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN:
+		ret = tcpm_psy_get_voltage_min(port, val);
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_MAX:
+		ret = tcpm_psy_get_voltage_max(port, val);
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		ret = tcpm_psy_get_voltage_now(port, val);
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_MAX:
+		ret = tcpm_psy_get_current_max(port, val);
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		ret = tcpm_psy_get_current_now(port, val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int tcpm_psy_set_online(struct tcpm_port *port,
+			       const union power_supply_propval *val)
+{
+	int ret;
+
+	switch (val->intval) {
+	case TCPM_PSY_FIXED_ONLINE:
+		ret = tcpm_pps_activate(port, false);
+		break;
+	case TCPM_PSY_PROG_ONLINE:
+		ret = tcpm_pps_activate(port, true);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int tcpm_psy_set_prop(struct power_supply *psy,
+			     enum power_supply_property psp,
+			     const union power_supply_propval *val)
+{
+	struct tcpm_port *port = power_supply_get_drvdata(psy);
+	int ret;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_ONLINE:
+		ret = tcpm_psy_set_online(port, val);
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		if (val->intval < port->pps_data.min_volt * 1000 ||
+		    val->intval > port->pps_data.max_volt * 1000)
+			ret = -EINVAL;
+		else
+			ret = tcpm_pps_set_out_volt(port, val->intval / 1000);
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		if (val->intval > port->pps_data.max_curr * 1000)
+			ret = -EINVAL;
+		else
+			ret = tcpm_pps_set_op_curr(port, val->intval / 1000);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int tcpm_psy_prop_writeable(struct power_supply *psy,
+				   enum power_supply_property psp)
+{
+	switch (psp) {
+	case POWER_SUPPLY_PROP_ONLINE:
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static enum power_supply_usb_type tcpm_psy_usb_types[] = {
+	POWER_SUPPLY_USB_TYPE_C,
+	POWER_SUPPLY_USB_TYPE_PD,
+	POWER_SUPPLY_USB_TYPE_PD_PPS,
+};
+
+static const char *tcpm_psy_name_prefix = "tcpm-source-psy-";
+
+static int devm_tcpm_psy_register(struct tcpm_port *port)
+{
+	struct power_supply_config psy_cfg = {};
+	const char *port_dev_name = dev_name(port->dev);
+	size_t psy_name_len = strlen(tcpm_psy_name_prefix) +
+				     strlen(port_dev_name) + 1;
+	char *psy_name;
+
+	psy_cfg.drv_data = port;
+	psy_cfg.fwnode = dev_fwnode(port->dev);
+	psy_name = devm_kzalloc(port->dev, psy_name_len, GFP_KERNEL);
+	if (!psy_name)
+		return -ENOMEM;
+
+	snprintf(psy_name, psy_name_len, "%s%s", tcpm_psy_name_prefix,
+		 port_dev_name);
+	port->psy_desc.name = psy_name;
+	port->psy_desc.type = POWER_SUPPLY_TYPE_USB,
+	port->psy_desc.usb_types = tcpm_psy_usb_types;
+	port->psy_desc.num_usb_types = ARRAY_SIZE(tcpm_psy_usb_types);
+	port->psy_desc.properties = tcpm_psy_props,
+	port->psy_desc.num_properties = ARRAY_SIZE(tcpm_psy_props),
+	port->psy_desc.get_property = tcpm_psy_get_prop,
+	port->psy_desc.set_property = tcpm_psy_set_prop,
+	port->psy_desc.property_is_writeable = tcpm_psy_prop_writeable,
+
+	port->usb_type = POWER_SUPPLY_USB_TYPE_C;
+
+	port->psy = devm_power_supply_register(port->dev, &port->psy_desc,
+					       &psy_cfg);
+
+	return PTR_ERR_OR_ZERO(port->psy);
+}
+
 struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 {
 	struct tcpm_port *port;
@@ -3631,6 +4553,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 
 	init_completion(&port->tx_complete);
 	init_completion(&port->swap_complete);
+	init_completion(&port->pps_complete);
 	tcpm_debugfs_init(port);
 
 	if (tcpm_validate_caps(port, tcpc->config->src_pdo,
@@ -3647,9 +4570,6 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	port->nr_snk_vdo = tcpm_copy_vdos(port->snk_vdo, tcpc->config->snk_vdo,
 					  tcpc->config->nr_snk_vdo);
 
-	port->max_snk_mv = tcpc->config->max_snk_mv;
-	port->max_snk_ma = tcpc->config->max_snk_ma;
-	port->max_snk_mw = tcpc->config->max_snk_mw;
 	port->operating_snk_mw = tcpc->config->operating_snk_mw;
 	if (!tcpc->config->try_role_hw)
 		port->try_role = tcpc->config->default_role;
@@ -3660,7 +4580,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	port->typec_caps.type = tcpc->config->type;
 	port->typec_caps.data = tcpc->config->data;
 	port->typec_caps.revision = 0x0120;	/* Type-C spec release 1.2 */
-	port->typec_caps.pd_revision = 0x0200;	/* USB-PD spec release 2.0 */
+	port->typec_caps.pd_revision = 0x0300;	/* USB-PD spec release 3.0 */
 	port->typec_caps.dr_set = tcpm_dr_set;
 	port->typec_caps.pr_set = tcpm_pr_set;
 	port->typec_caps.vconn_set = tcpm_vconn_set;
@@ -3676,6 +4596,10 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 		goto out_destroy_wq;
 	}
 
+	err = devm_tcpm_psy_register(port);
+	if (err)
+		goto out_destroy_wq;
+
 	port->typec_port = typec_register_port(port->dev, &port->typec_caps);
 	if (IS_ERR(port->typec_port)) {
 		err = PTR_ERR(port->typec_port);
@@ -3725,6 +4649,7 @@ void tcpm_unregister_port(struct tcpm_port *port)
 	for (i = 0; i < ARRAY_SIZE(port->port_altmode); i++)
 		typec_unregister_altmode(port->port_altmode[i]);
 	typec_unregister_port(port->typec_port);
+	usb_role_switch_put(port->role_sw);
 	tcpm_debugfs_exit(port);
 	destroy_workqueue(port->wq);
 }
diff --git a/drivers/usb/typec/tps6598x.c b/drivers/usb/typec/tps6598x.c
index 8b8406867c02..4b4c8d271b27 100644
--- a/drivers/usb/typec/tps6598x.c
+++ b/drivers/usb/typec/tps6598x.c
@@ -73,6 +73,7 @@ struct tps6598x {
 	struct device *dev;
 	struct regmap *regmap;
 	struct mutex lock; /* device lock */
+	u8 i2c_protocol:1;
 
 	struct typec_port *port;
 	struct typec_partner *partner;
@@ -80,19 +81,39 @@ struct tps6598x {
 	struct typec_capability typec_cap;
 };
 
+static int
+tps6598x_block_read(struct tps6598x *tps, u8 reg, void *val, size_t len)
+{
+	u8 data[len + 1];
+	int ret;
+
+	if (!tps->i2c_protocol)
+		return regmap_raw_read(tps->regmap, reg, val, len);
+
+	ret = regmap_raw_read(tps->regmap, reg, data, sizeof(data));
+	if (ret)
+		return ret;
+
+	if (data[0] < len)
+		return -EIO;
+
+	memcpy(val, &data[1], len);
+	return 0;
+}
+
 static inline int tps6598x_read16(struct tps6598x *tps, u8 reg, u16 *val)
 {
-	return regmap_raw_read(tps->regmap, reg, val, sizeof(u16));
+	return tps6598x_block_read(tps, reg, val, sizeof(u16));
 }
 
 static inline int tps6598x_read32(struct tps6598x *tps, u8 reg, u32 *val)
 {
-	return regmap_raw_read(tps->regmap, reg, val, sizeof(u32));
+	return tps6598x_block_read(tps, reg, val, sizeof(u32));
 }
 
 static inline int tps6598x_read64(struct tps6598x *tps, u8 reg, u64 *val)
 {
-	return regmap_raw_read(tps->regmap, reg, val, sizeof(u64));
+	return tps6598x_block_read(tps, reg, val, sizeof(u64));
 }
 
 static inline int tps6598x_write16(struct tps6598x *tps, u8 reg, u16 val)
@@ -121,8 +142,8 @@ static int tps6598x_read_partner_identity(struct tps6598x *tps)
 	struct tps6598x_rx_identity_reg id;
 	int ret;
 
-	ret = regmap_raw_read(tps->regmap, TPS_REG_RX_IDENTITY_SOP,
-			      &id, sizeof(id));
+	ret = tps6598x_block_read(tps, TPS_REG_RX_IDENTITY_SOP,
+				  &id, sizeof(id));
 	if (ret)
 		return ret;
 
@@ -224,13 +245,13 @@ static int tps6598x_exec_cmd(struct tps6598x *tps, const char *cmd,
 	} while (val);
 
 	if (out_len) {
-		ret = regmap_raw_read(tps->regmap, TPS_REG_DATA1,
-				      out_data, out_len);
+		ret = tps6598x_block_read(tps, TPS_REG_DATA1,
+					  out_data, out_len);
 		if (ret)
 			return ret;
 		val = out_data[0];
 	} else {
-		ret = regmap_read(tps->regmap, TPS_REG_DATA1, &val);
+		ret = tps6598x_block_read(tps, TPS_REG_DATA1, &val, sizeof(u8));
 		if (ret)
 			return ret;
 	}
@@ -385,6 +406,16 @@ static int tps6598x_probe(struct i2c_client *client)
 	if (!vid)
 		return -ENODEV;
 
+	/*
+	 * Checking can the adapter handle SMBus protocol. If it can not, the
+	 * driver needs to take care of block reads separately.
+	 *
+	 * FIXME: Testing with I2C_FUNC_I2C. regmap-i2c uses I2C protocol
+	 * unconditionally if the adapter has I2C_FUNC_I2C set.
+	 */
+	if (i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		tps->i2c_protocol = true;
+
 	ret = tps6598x_read32(tps, TPS_REG_STATUS, &status);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/usb/typec/typec_wcove.c b/drivers/usb/typec/typec_wcove.c
index 19cca7f1b2c5..423208e19383 100644
--- a/drivers/usb/typec/typec_wcove.c
+++ b/drivers/usb/typec/typec_wcove.c
@@ -202,6 +202,10 @@ static int wcove_init(struct tcpc_dev *tcpc)
 	struct wcove_typec *wcove = tcpc_to_wcove(tcpc);
 	int ret;
 
+	ret = regmap_write(wcove->regmap, USBC_CONTROL1, 0);
+	if (ret)
+		return ret;
+
 	/* Unmask everything */
 	ret = regmap_write(wcove->regmap, USBC_IRQMASK1, 0);
 	if (ret)
@@ -285,8 +289,30 @@ static int wcove_get_cc(struct tcpc_dev *tcpc, enum typec_cc_status *cc1,
 
 static int wcove_set_cc(struct tcpc_dev *tcpc, enum typec_cc_status cc)
 {
-	/* XXX: Relying on the HW FSM to configure things correctly for now */
-	return 0;
+	struct wcove_typec *wcove = tcpc_to_wcove(tcpc);
+	unsigned int ctrl;
+
+	switch (cc) {
+	case TYPEC_CC_RD:
+		ctrl = USBC_CONTROL1_MODE_SNK;
+		break;
+	case TYPEC_CC_RP_DEF:
+		ctrl = USBC_CONTROL1_CURSRC_UA_80 | USBC_CONTROL1_MODE_SRC;
+		break;
+	case TYPEC_CC_RP_1_5:
+		ctrl = USBC_CONTROL1_CURSRC_UA_180 | USBC_CONTROL1_MODE_SRC;
+		break;
+	case TYPEC_CC_RP_3_0:
+		ctrl = USBC_CONTROL1_CURSRC_UA_330 | USBC_CONTROL1_MODE_SRC;
+		break;
+	case TYPEC_CC_OPEN:
+		ctrl = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return regmap_write(wcove->regmap, USBC_CONTROL1, ctrl);
 }
 
 static int wcove_set_polarity(struct tcpc_dev *tcpc, enum typec_cc_polarity pol)
@@ -558,6 +584,7 @@ static const u32 src_pdo[] = {
 static const u32 snk_pdo[] = {
 	PDO_FIXED(5000, 500, PDO_FIXED_DUAL_ROLE | PDO_FIXED_DATA_SWAP |
 		  PDO_FIXED_USB_COMM),
+	PDO_VAR(5000, 12000, 3000),
 };
 
 static struct tcpc_config wcove_typec_config = {
@@ -566,9 +593,6 @@ static struct tcpc_config wcove_typec_config = {
 	.snk_pdo = snk_pdo,
 	.nr_snk_pdo = ARRAY_SIZE(snk_pdo),
 
-	.max_snk_mv = 12000,
-	.max_snk_ma = 3000,
-	.max_snk_mw = 36000,
 	.operating_snk_mw = 15000,
 
 	.type = TYPEC_PORT_DRP,
diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile
index b57891c1fd31..7afbea512207 100644
--- a/drivers/usb/typec/ucsi/Makefile
+++ b/drivers/usb/typec/ucsi/Makefile
@@ -5,6 +5,6 @@ obj-$(CONFIG_TYPEC_UCSI)	+= typec_ucsi.o
 
 typec_ucsi-y			:= ucsi.o
 
-typec_ucsi-$(CONFIG_FTRACE)	+= trace.o
+typec_ucsi-$(CONFIG_TRACING)	+= trace.o
 
 obj-$(CONFIG_UCSI_ACPI)		+= ucsi_acpi.o
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index bf0977fbd100..bd5cca5632b3 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -28,7 +28,7 @@
  * difficult to estimate the time it takes for the system to process the command
  * before it is actually passed to the PPM.
  */
-#define UCSI_TIMEOUT_MS		1000
+#define UCSI_TIMEOUT_MS		5000
 
 /*
  * UCSI_SWAP_TIMEOUT_MS - Timeout for role swap requests
diff --git a/drivers/usb/usbip/stub.h b/drivers/usb/usbip/stub.h
index 14a72357800a..35618ceb2791 100644
--- a/drivers/usb/usbip/stub.h
+++ b/drivers/usb/usbip/stub.h
@@ -73,6 +73,7 @@ struct bus_id_priv {
 	struct stub_device *sdev;
 	struct usb_device *udev;
 	char shutdown_busid;
+	spinlock_t busid_lock;
 };
 
 /* stub_priv is allocated from stub_priv_cache */
@@ -83,6 +84,7 @@ extern struct usb_device_driver stub_driver;
 
 /* stub_main.c */
 struct bus_id_priv *get_busid_priv(const char *busid);
+void put_busid_priv(struct bus_id_priv *bid);
 int del_match_busid(char *busid);
 void stub_device_cleanup_urbs(struct stub_device *sdev);
 
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index dd8ef36ab10e..c0d6ff1baa72 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -300,9 +300,9 @@ static int stub_probe(struct usb_device *udev)
 	struct stub_device *sdev = NULL;
 	const char *udev_busid = dev_name(&udev->dev);
 	struct bus_id_priv *busid_priv;
-	int rc;
+	int rc = 0;
 
-	dev_dbg(&udev->dev, "Enter\n");
+	dev_dbg(&udev->dev, "Enter probe\n");
 
 	/* check we should claim or not by busid_table */
 	busid_priv = get_busid_priv(udev_busid);
@@ -317,13 +317,15 @@ static int stub_probe(struct usb_device *udev)
 		 * other matched drivers by the driver core.
 		 * See driver_probe_device() in driver/base/dd.c
 		 */
-		return -ENODEV;
+		rc = -ENODEV;
+		goto call_put_busid_priv;
 	}
 
 	if (udev->descriptor.bDeviceClass == USB_CLASS_HUB) {
 		dev_dbg(&udev->dev, "%s is a usb hub device... skip!\n",
 			 udev_busid);
-		return -ENODEV;
+		rc = -ENODEV;
+		goto call_put_busid_priv;
 	}
 
 	if (!strcmp(udev->bus->bus_name, "vhci_hcd")) {
@@ -331,13 +333,16 @@ static int stub_probe(struct usb_device *udev)
 			"%s is attached on vhci_hcd... skip!\n",
 			udev_busid);
 
-		return -ENODEV;
+		rc = -ENODEV;
+		goto call_put_busid_priv;
 	}
 
 	/* ok, this is my device */
 	sdev = stub_device_alloc(udev);
-	if (!sdev)
-		return -ENOMEM;
+	if (!sdev) {
+		rc = -ENOMEM;
+		goto call_put_busid_priv;
+	}
 
 	dev_info(&udev->dev,
 		"usbip-host: register new device (bus %u dev %u)\n",
@@ -369,7 +374,9 @@ static int stub_probe(struct usb_device *udev)
 	}
 	busid_priv->status = STUB_BUSID_ALLOC;
 
-	return 0;
+	rc = 0;
+	goto call_put_busid_priv;
+
 err_files:
 	usb_hub_release_port(udev->parent, udev->portnum,
 			     (struct usb_dev_state *) udev);
@@ -379,6 +386,9 @@ err_port:
 
 	busid_priv->sdev = NULL;
 	stub_device_free(sdev);
+
+call_put_busid_priv:
+	put_busid_priv(busid_priv);
 	return rc;
 }
 
@@ -404,7 +414,7 @@ static void stub_disconnect(struct usb_device *udev)
 	struct bus_id_priv *busid_priv;
 	int rc;
 
-	dev_dbg(&udev->dev, "Enter\n");
+	dev_dbg(&udev->dev, "Enter disconnect\n");
 
 	busid_priv = get_busid_priv(udev_busid);
 	if (!busid_priv) {
@@ -417,7 +427,7 @@ static void stub_disconnect(struct usb_device *udev)
 	/* get stub_device */
 	if (!sdev) {
 		dev_err(&udev->dev, "could not get device");
-		return;
+		goto call_put_busid_priv;
 	}
 
 	dev_set_drvdata(&udev->dev, NULL);
@@ -432,12 +442,12 @@ static void stub_disconnect(struct usb_device *udev)
 				  (struct usb_dev_state *) udev);
 	if (rc) {
 		dev_dbg(&udev->dev, "unable to release port\n");
-		return;
+		goto call_put_busid_priv;
 	}
 
 	/* If usb reset is called from event handler */
 	if (usbip_in_eh(current))
-		return;
+		goto call_put_busid_priv;
 
 	/* shutdown the current connection */
 	shutdown_busid(busid_priv);
@@ -448,12 +458,11 @@ static void stub_disconnect(struct usb_device *udev)
 	busid_priv->sdev = NULL;
 	stub_device_free(sdev);
 
-	if (busid_priv->status == STUB_BUSID_ALLOC) {
+	if (busid_priv->status == STUB_BUSID_ALLOC)
 		busid_priv->status = STUB_BUSID_ADDED;
-	} else {
-		busid_priv->status = STUB_BUSID_OTHER;
-		del_match_busid((char *)udev_busid);
-	}
+
+call_put_busid_priv:
+	put_busid_priv(busid_priv);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index c31c8402a0c5..bf8a5feb0ee9 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -14,6 +14,7 @@
 #define DRIVER_DESC "USB/IP Host Driver"
 
 struct kmem_cache *stub_priv_cache;
+
 /*
  * busid_tables defines matching busids that usbip can grab. A user can change
  * dynamically what device is locally used and what device is exported to a
@@ -25,6 +26,8 @@ static spinlock_t busid_table_lock;
 
 static void init_busid_table(void)
 {
+	int i;
+
 	/*
 	 * This also sets the bus_table[i].status to
 	 * STUB_BUSID_OTHER, which is 0.
@@ -32,6 +35,9 @@ static void init_busid_table(void)
 	memset(busid_table, 0, sizeof(busid_table));
 
 	spin_lock_init(&busid_table_lock);
+
+	for (i = 0; i < MAX_BUSID; i++)
+		spin_lock_init(&busid_table[i].busid_lock);
 }
 
 /*
@@ -43,15 +49,20 @@ static int get_busid_idx(const char *busid)
 	int i;
 	int idx = -1;
 
-	for (i = 0; i < MAX_BUSID; i++)
+	for (i = 0; i < MAX_BUSID; i++) {
+		spin_lock(&busid_table[i].busid_lock);
 		if (busid_table[i].name[0])
 			if (!strncmp(busid_table[i].name, busid, BUSID_SIZE)) {
 				idx = i;
+				spin_unlock(&busid_table[i].busid_lock);
 				break;
 			}
+		spin_unlock(&busid_table[i].busid_lock);
+	}
 	return idx;
 }
 
+/* Returns holding busid_lock. Should call put_busid_priv() to unlock */
 struct bus_id_priv *get_busid_priv(const char *busid)
 {
 	int idx;
@@ -59,13 +70,22 @@ struct bus_id_priv *get_busid_priv(const char *busid)
 
 	spin_lock(&busid_table_lock);
 	idx = get_busid_idx(busid);
-	if (idx >= 0)
+	if (idx >= 0) {
 		bid = &(busid_table[idx]);
+		/* get busid_lock before returning */
+		spin_lock(&bid->busid_lock);
+	}
 	spin_unlock(&busid_table_lock);
 
 	return bid;
 }
 
+void put_busid_priv(struct bus_id_priv *bid)
+{
+	if (bid)
+		spin_unlock(&bid->busid_lock);
+}
+
 static int add_match_busid(char *busid)
 {
 	int i;
@@ -78,15 +98,19 @@ static int add_match_busid(char *busid)
 		goto out;
 	}
 
-	for (i = 0; i < MAX_BUSID; i++)
+	for (i = 0; i < MAX_BUSID; i++) {
+		spin_lock(&busid_table[i].busid_lock);
 		if (!busid_table[i].name[0]) {
 			strlcpy(busid_table[i].name, busid, BUSID_SIZE);
 			if ((busid_table[i].status != STUB_BUSID_ALLOC) &&
 			    (busid_table[i].status != STUB_BUSID_REMOV))
 				busid_table[i].status = STUB_BUSID_ADDED;
 			ret = 0;
+			spin_unlock(&busid_table[i].busid_lock);
 			break;
 		}
+		spin_unlock(&busid_table[i].busid_lock);
+	}
 
 out:
 	spin_unlock(&busid_table_lock);
@@ -107,6 +131,8 @@ int del_match_busid(char *busid)
 	/* found */
 	ret = 0;
 
+	spin_lock(&busid_table[idx].busid_lock);
+
 	if (busid_table[idx].status == STUB_BUSID_OTHER)
 		memset(busid_table[idx].name, 0, BUSID_SIZE);
 
@@ -114,6 +140,7 @@ int del_match_busid(char *busid)
 	    (busid_table[idx].status != STUB_BUSID_ADDED))
 		busid_table[idx].status = STUB_BUSID_REMOV;
 
+	spin_unlock(&busid_table[idx].busid_lock);
 out:
 	spin_unlock(&busid_table_lock);
 
@@ -126,9 +153,12 @@ static ssize_t match_busid_show(struct device_driver *drv, char *buf)
 	char *out = buf;
 
 	spin_lock(&busid_table_lock);
-	for (i = 0; i < MAX_BUSID; i++)
+	for (i = 0; i < MAX_BUSID; i++) {
+		spin_lock(&busid_table[i].busid_lock);
 		if (busid_table[i].name[0])
 			out += sprintf(out, "%s ", busid_table[i].name);
+		spin_unlock(&busid_table[i].busid_lock);
+	}
 	spin_unlock(&busid_table_lock);
 	out += sprintf(out, "\n");
 
@@ -169,6 +199,51 @@ static ssize_t match_busid_store(struct device_driver *dev, const char *buf,
 }
 static DRIVER_ATTR_RW(match_busid);
 
+static int do_rebind(char *busid, struct bus_id_priv *busid_priv)
+{
+	int ret;
+
+	/* device_attach() callers should hold parent lock for USB */
+	if (busid_priv->udev->dev.parent)
+		device_lock(busid_priv->udev->dev.parent);
+	ret = device_attach(&busid_priv->udev->dev);
+	if (busid_priv->udev->dev.parent)
+		device_unlock(busid_priv->udev->dev.parent);
+	if (ret < 0) {
+		dev_err(&busid_priv->udev->dev, "rebind failed\n");
+		return ret;
+	}
+	return 0;
+}
+
+static void stub_device_rebind(void)
+{
+#if IS_MODULE(CONFIG_USBIP_HOST)
+	struct bus_id_priv *busid_priv;
+	int i;
+
+	/* update status to STUB_BUSID_OTHER so probe ignores the device */
+	spin_lock(&busid_table_lock);
+	for (i = 0; i < MAX_BUSID; i++) {
+		if (busid_table[i].name[0] &&
+		    busid_table[i].shutdown_busid) {
+			busid_priv = &(busid_table[i]);
+			busid_priv->status = STUB_BUSID_OTHER;
+		}
+	}
+	spin_unlock(&busid_table_lock);
+
+	/* now run rebind - no need to hold locks. driver files are removed */
+	for (i = 0; i < MAX_BUSID; i++) {
+		if (busid_table[i].name[0] &&
+		    busid_table[i].shutdown_busid) {
+			busid_priv = &(busid_table[i]);
+			do_rebind(busid_table[i].name, busid_priv);
+		}
+	}
+#endif
+}
+
 static ssize_t rebind_store(struct device_driver *dev, const char *buf,
 				 size_t count)
 {
@@ -186,11 +261,17 @@ static ssize_t rebind_store(struct device_driver *dev, const char *buf,
 	if (!bid)
 		return -ENODEV;
 
-	ret = device_attach(&bid->udev->dev);
-	if (ret < 0) {
-		dev_err(&bid->udev->dev, "rebind failed\n");
+	/* mark the device for deletion so probe ignores it during rescan */
+	bid->status = STUB_BUSID_OTHER;
+	/* release the busid lock */
+	put_busid_priv(bid);
+
+	ret = do_rebind((char *) buf, bid);
+	if (ret < 0)
 		return ret;
-	}
+
+	/* delete device from busid_table */
+	del_match_busid((char *) buf);
 
 	return count;
 }
@@ -312,6 +393,9 @@ static void __exit usbip_host_exit(void)
 	 */
 	usb_deregister_device_driver(&stub_driver);
 
+	/* initiate scan to attach devices */
+	stub_device_rebind();
+
 	kmem_cache_destroy(stub_priv_cache);
 }
 
diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
index 473fb8a87289..bf8afe9b5883 100644
--- a/drivers/usb/usbip/usbip_common.h
+++ b/drivers/usb/usbip/usbip_common.h
@@ -243,7 +243,7 @@ enum usbip_side {
 #define	VUDC_EVENT_ERROR_USB	(USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
 #define	VUDC_EVENT_ERROR_MALLOC	(USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
 
-#define	VDEV_EVENT_REMOVED	(USBIP_EH_SHUTDOWN | USBIP_EH_BYE)
+#define	VDEV_EVENT_REMOVED (USBIP_EH_SHUTDOWN | USBIP_EH_RESET | USBIP_EH_BYE)
 #define	VDEV_EVENT_DOWN		(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
 #define	VDEV_EVENT_ERROR_TCP	(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
 #define	VDEV_EVENT_ERROR_MALLOC	(USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
diff --git a/drivers/usb/usbip/usbip_event.c b/drivers/usb/usbip/usbip_event.c
index 5b4c0864ad92..5d88917c9631 100644
--- a/drivers/usb/usbip/usbip_event.c
+++ b/drivers/usb/usbip/usbip_event.c
@@ -91,10 +91,6 @@ static void event_handler(struct work_struct *work)
 			unset_event(ud, USBIP_EH_UNUSABLE);
 		}
 
-		/* Stop the error handler. */
-		if (ud->event & USBIP_EH_BYE)
-			usbip_dbg_eh("removed %p\n", ud);
-
 		wake_up(&ud->eh_waitq);
 	}
 }
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 20e3d4609583..d11f3f8dad40 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -354,6 +354,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		usbip_dbg_vhci_rh(" ClearHubFeature\n");
 		break;
 	case ClearPortFeature:
+		if (rhport < 0)
+			goto error;
 		switch (wValue) {
 		case USB_PORT_FEAT_SUSPEND:
 			if (hcd->speed == HCD_USB3) {
@@ -511,11 +513,16 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 				goto error;
 			}
 
+			if (rhport < 0)
+				goto error;
+
 			vhci_hcd->port_status[rhport] |= USB_PORT_STAT_SUSPEND;
 			break;
 		case USB_PORT_FEAT_POWER:
 			usbip_dbg_vhci_rh(
 				" SetPortFeature: USB_PORT_FEAT_POWER\n");
+			if (rhport < 0)
+				goto error;
 			if (hcd->speed == HCD_USB3)
 				vhci_hcd->port_status[rhport] |= USB_SS_PORT_STAT_POWER;
 			else
@@ -524,6 +531,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		case USB_PORT_FEAT_BH_PORT_RESET:
 			usbip_dbg_vhci_rh(
 				" SetPortFeature: USB_PORT_FEAT_BH_PORT_RESET\n");
+			if (rhport < 0)
+				goto error;
 			/* Applicable only for USB3.0 hub */
 			if (hcd->speed != HCD_USB3) {
 				pr_err("USB_PORT_FEAT_BH_PORT_RESET req not "
@@ -534,6 +543,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		case USB_PORT_FEAT_RESET:
 			usbip_dbg_vhci_rh(
 				" SetPortFeature: USB_PORT_FEAT_RESET\n");
+			if (rhport < 0)
+				goto error;
 			/* if it's already enabled, disable */
 			if (hcd->speed == HCD_USB3) {
 				vhci_hcd->port_status[rhport] = 0;
@@ -554,6 +565,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		default:
 			usbip_dbg_vhci_rh(" SetPortFeature: default %d\n",
 					  wValue);
+			if (rhport < 0)
+				goto error;
 			if (hcd->speed == HCD_USB3) {
 				if ((vhci_hcd->port_status[rhport] &
 				     USB_SS_PORT_STAT_POWER) != 0) {
diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c
index 48808388ec33..be37aec250c2 100644
--- a/drivers/usb/usbip/vhci_sysfs.c
+++ b/drivers/usb/usbip/vhci_sysfs.c
@@ -10,6 +10,9 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
 #include "usbip_common.h"
 #include "vhci.h"
 
@@ -205,16 +208,20 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport)
 	return 0;
 }
 
-static int valid_port(__u32 pdev_nr, __u32 rhport)
+static int valid_port(__u32 *pdev_nr, __u32 *rhport)
 {
-	if (pdev_nr >= vhci_num_controllers) {
-		pr_err("pdev %u\n", pdev_nr);
+	if (*pdev_nr >= vhci_num_controllers) {
+		pr_err("pdev %u\n", *pdev_nr);
 		return 0;
 	}
-	if (rhport >= VHCI_HC_PORTS) {
-		pr_err("rhport %u\n", rhport);
+	*pdev_nr = array_index_nospec(*pdev_nr, vhci_num_controllers);
+
+	if (*rhport >= VHCI_HC_PORTS) {
+		pr_err("rhport %u\n", *rhport);
 		return 0;
 	}
+	*rhport = array_index_nospec(*rhport, VHCI_HC_PORTS);
+
 	return 1;
 }
 
@@ -232,7 +239,7 @@ static ssize_t detach_store(struct device *dev, struct device_attribute *attr,
 	pdev_nr = port_to_pdev_nr(port);
 	rhport = port_to_rhport(port);
 
-	if (!valid_port(pdev_nr, rhport))
+	if (!valid_port(&pdev_nr, &rhport))
 		return -EINVAL;
 
 	hcd = platform_get_drvdata(vhcis[pdev_nr].pdev);
@@ -258,7 +265,8 @@ static ssize_t detach_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_WO(detach);
 
-static int valid_args(__u32 pdev_nr, __u32 rhport, enum usb_device_speed speed)
+static int valid_args(__u32 *pdev_nr, __u32 *rhport,
+		      enum usb_device_speed speed)
 {
 	if (!valid_port(pdev_nr, rhport)) {
 		return 0;
@@ -322,7 +330,7 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr,
 			     sockfd, devid, speed);
 
 	/* check received parameters */
-	if (!valid_args(pdev_nr, rhport, speed))
+	if (!valid_args(&pdev_nr, &rhport, speed))
 		return -EINVAL;
 
 	hcd = platform_get_drvdata(vhcis[pdev_nr].pdev);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5c212bf29640..3c082451ab1a 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -404,6 +404,7 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 {
 	unsigned long pfn = 0;
 	long ret, pinned = 0, lock_acct = 0;
+	bool rsvd;
 	dma_addr_t iova = vaddr - dma->vaddr + dma->iova;
 
 	/* This code path is only user initiated */
@@ -414,23 +415,14 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 	if (ret)
 		return ret;
 
-	if (is_invalid_reserved_pfn(*pfn_base)) {
-		struct vm_area_struct *vma;
-
-		down_read(&current->mm->mmap_sem);
-		vma = find_vma_intersection(current->mm, vaddr, vaddr + 1);
-		pinned = min_t(long, npage, vma_pages(vma));
-		up_read(&current->mm->mmap_sem);
-		return pinned;
-	}
-
 	pinned++;
+	rsvd = is_invalid_reserved_pfn(*pfn_base);
 
 	/*
 	 * Reserved pages aren't counted against the user, externally pinned
 	 * pages are already counted against the user.
 	 */
-	if (!vfio_find_vpfn(dma, iova)) {
+	if (!rsvd && !vfio_find_vpfn(dma, iova)) {
 		if (!lock_cap && current->mm->locked_vm + 1 > limit) {
 			put_pfn(*pfn_base, dma->prot);
 			pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
@@ -450,12 +442,13 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 		if (ret)
 			break;
 
-		if (pfn != *pfn_base + pinned) {
+		if (pfn != *pfn_base + pinned ||
+		    rsvd != is_invalid_reserved_pfn(pfn)) {
 			put_pfn(pfn, dma->prot);
 			break;
 		}
 
-		if (!vfio_find_vpfn(dma, iova)) {
+		if (!rsvd && !vfio_find_vpfn(dma, iova)) {
 			if (!lock_cap &&
 			    current->mm->locked_vm + lock_acct + 1 > limit) {
 				put_pfn(pfn, dma->prot);
@@ -473,8 +466,10 @@ out:
 
 unpin_out:
 	if (ret) {
-		for (pfn = *pfn_base ; pinned ; pfn++, pinned--)
-			put_pfn(pfn, dma->prot);
+		if (!rsvd) {
+			for (pfn = *pfn_base ; pinned ; pfn++, pinned--)
+				put_pfn(pfn, dma->prot);
+		}
 
 		return ret;
 	}
diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
index 085700f1be10..2a1be859ee71 100644
--- a/drivers/vfio/virqfd.c
+++ b/drivers/vfio/virqfd.c
@@ -166,7 +166,7 @@ int vfio_virqfd_enable(void *opaque,
 	init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
 	init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
 
-	events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
+	events = vfs_poll(irqfd.file, &virqfd->pt);
 
 	/*
 	 * Check if there was an event already pending on the eventfd
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 986058a57917..eeaf6739215f 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -105,7 +105,9 @@ struct vhost_net_virtqueue {
 	/* vhost zerocopy support fields below: */
 	/* last used idx for outstanding DMA zerocopy buffers */
 	int upend_idx;
-	/* first used idx for DMA done zerocopy buffers */
+	/* For TX, first used idx for DMA done zerocopy buffers
+	 * For RX, number of batched heads
+	 */
 	int done_idx;
 	/* an array of userspace buffers info */
 	struct ubuf_info *ubuf_info;
@@ -626,6 +628,18 @@ static int sk_has_rx_data(struct sock *sk)
 	return skb_queue_empty(&sk->sk_receive_queue);
 }
 
+static void vhost_rx_signal_used(struct vhost_net_virtqueue *nvq)
+{
+	struct vhost_virtqueue *vq = &nvq->vq;
+	struct vhost_dev *dev = vq->dev;
+
+	if (!nvq->done_idx)
+		return;
+
+	vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
+	nvq->done_idx = 0;
+}
+
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 {
 	struct vhost_net_virtqueue *rvq = &net->vqs[VHOST_NET_VQ_RX];
@@ -635,6 +649,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 	int len = peek_head_len(rvq, sk);
 
 	if (!len && vq->busyloop_timeout) {
+		/* Flush batched heads first */
+		vhost_rx_signal_used(rvq);
 		/* Both tx vq and rx socket were polled here */
 		mutex_lock_nested(&vq->mutex, 1);
 		vhost_disable_notify(&net->dev, vq);
@@ -762,7 +778,7 @@ static void handle_rx(struct vhost_net *net)
 	};
 	size_t total_len = 0;
 	int err, mergeable;
-	s16 headcount, nheads = 0;
+	s16 headcount;
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
 	struct socket *sock;
@@ -790,8 +806,8 @@ static void handle_rx(struct vhost_net *net)
 	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
-		headcount = get_rx_bufs(vq, vq->heads + nheads, vhost_len,
-					&in, vq_log, &log,
+		headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
+					vhost_len, &in, vq_log, &log,
 					likely(mergeable) ? UIO_MAXIOV : 1);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
@@ -862,12 +878,9 @@ static void handle_rx(struct vhost_net *net)
 			vhost_discard_vq_desc(vq, headcount);
 			goto out;
 		}
-		nheads += headcount;
-		if (nheads > VHOST_RX_BATCH) {
-			vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
-						    nheads);
-			nheads = 0;
-		}
+		nvq->done_idx += headcount;
+		if (nvq->done_idx > VHOST_RX_BATCH)
+			vhost_rx_signal_used(nvq);
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
 		total_len += vhost_len;
@@ -878,9 +891,7 @@ static void handle_rx(struct vhost_net *net)
 	}
 	vhost_net_enable_vq(net, vq);
 out:
-	if (nheads)
-		vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
-					    nheads);
+	vhost_rx_signal_used(nvq);
 	mutex_unlock(&vq->mutex);
 }
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index f3bd8e941224..895eaa25807c 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -208,7 +208,7 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file)
 	if (poll->wqh)
 		return 0;
 
-	mask = file->f_op->poll(file, &poll->table);
+	mask = vfs_poll(file, &poll->table);
 	if (mask)
 		vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask));
 	if (mask & EPOLLERR) {
@@ -981,6 +981,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 {
 	int ret = 0;
 
+	mutex_lock(&dev->mutex);
 	vhost_dev_lock_vqs(dev);
 	switch (msg->type) {
 	case VHOST_IOTLB_UPDATE:
@@ -1016,6 +1017,8 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 	}
 
 	vhost_dev_unlock_vqs(dev);
+	mutex_unlock(&dev->mutex);
+
 	return ret;
 }
 ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index f741ba8df01b..924d0730ffe2 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -713,19 +713,6 @@ static const struct seq_operations proc_fb_seq_ops = {
 	.show	= fb_seq_show,
 };
 
-static int proc_fb_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &proc_fb_seq_ops);
-}
-
-static const struct file_operations fb_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_fb_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 /*
  * We hold a reference to the fb_info in file->private_data,
  * but if the current registered fb has changed, we don't
@@ -1877,7 +1864,7 @@ fbmem_init(void)
 {
 	int ret;
 
-	if (!proc_create("fb", 0, NULL, &fb_proc_fops))
+	if (!proc_create_seq("fb", 0, NULL, &proc_fb_seq_ops))
 		return -ENOMEM;
 
 	ret = register_chrdev(FB_MAJOR, "fb", &fb_fops);
diff --git a/drivers/video/fbdev/via/viafbdev.c b/drivers/video/fbdev/via/viafbdev.c
index badee04ef496..9b45125988fb 100644
--- a/drivers/video/fbdev/via/viafbdev.c
+++ b/drivers/video/fbdev/via/viafbdev.c
@@ -1475,19 +1475,6 @@ static int viafb_sup_odev_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int viafb_sup_odev_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, viafb_sup_odev_proc_show, NULL);
-}
-
-static const struct file_operations viafb_sup_odev_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= viafb_sup_odev_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static ssize_t odev_update(const char __user *buffer, size_t count, u32 *odev)
 {
 	char buf[64], *ptr = buf;
@@ -1616,8 +1603,8 @@ static void viafb_init_proc(struct viafb_shared *shared)
 				&viafb_vt1636_proc_fops);
 #endif /* CONFIG_FB_VIA_DIRECT_PROCFS */
 
-		proc_create("supported_output_devices", 0, viafb_entry,
-			&viafb_sup_odev_proc_fops);
+		proc_create_single("supported_output_devices", 0, viafb_entry,
+			viafb_sup_odev_proc_show);
 		iga1_entry = proc_mkdir("iga1", viafb_entry);
 		shared->iga1_proc_entry = iga1_entry;
 		proc_create("output_devices", 0, iga1_entry,
diff --git a/drivers/video/hdmi.c b/drivers/video/hdmi.c
index 111a0ab6280a..38716eb50408 100644
--- a/drivers/video/hdmi.c
+++ b/drivers/video/hdmi.c
@@ -93,6 +93,9 @@ ssize_t hdmi_avi_infoframe_pack(struct hdmi_avi_infoframe *frame, void *buffer,
 	if (size < length)
 		return -ENOSPC;
 
+	if (frame->picture_aspect > HDMI_PICTURE_ASPECT_16_9)
+		return -EINVAL;
+
 	memset(buffer, 0, size);
 
 	ptr[0] = frame->type;
diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c
index 190dbf8cfcb5..2f3856a95856 100644
--- a/drivers/virt/vboxguest/vboxguest_core.c
+++ b/drivers/virt/vboxguest/vboxguest_core.c
@@ -114,7 +114,7 @@ static void vbg_guest_mappings_init(struct vbg_dev *gdev)
 	}
 
 out:
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 	kfree(pages);
 }
 
@@ -144,7 +144,7 @@ static void vbg_guest_mappings_exit(struct vbg_dev *gdev)
 
 	rc = vbg_req_perform(gdev, req);
 
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 
 	if (rc < 0) {
 		vbg_err("%s error: %d\n", __func__, rc);
@@ -214,8 +214,8 @@ static int vbg_report_guest_info(struct vbg_dev *gdev)
 	ret = vbg_status_code_to_errno(rc);
 
 out_free:
-	kfree(req2);
-	kfree(req1);
+	vbg_req_free(req2, sizeof(*req2));
+	vbg_req_free(req1, sizeof(*req1));
 	return ret;
 }
 
@@ -245,7 +245,7 @@ static int vbg_report_driver_status(struct vbg_dev *gdev, bool active)
 	if (rc == VERR_NOT_IMPLEMENTED)	/* Compatibility with older hosts. */
 		rc = VINF_SUCCESS;
 
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 
 	return vbg_status_code_to_errno(rc);
 }
@@ -431,7 +431,7 @@ static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled)
 	rc = vbg_req_perform(gdev, req);
 	do_div(req->interval_ns, 1000000); /* ns -> ms */
 	gdev->heartbeat_interval_ms = req->interval_ns;
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 
 	return vbg_status_code_to_errno(rc);
 }
@@ -454,12 +454,6 @@ static int vbg_heartbeat_init(struct vbg_dev *gdev)
 	if (ret < 0)
 		return ret;
 
-	/*
-	 * Preallocate the request to use it from the timer callback because:
-	 *    1) on Windows vbg_req_alloc must be called at IRQL <= APC_LEVEL
-	 *       and the timer callback runs at DISPATCH_LEVEL;
-	 *    2) avoid repeated allocations.
-	 */
 	gdev->guest_heartbeat_req = vbg_req_alloc(
 					sizeof(*gdev->guest_heartbeat_req),
 					VMMDEVREQ_GUEST_HEARTBEAT);
@@ -481,8 +475,8 @@ static void vbg_heartbeat_exit(struct vbg_dev *gdev)
 {
 	del_timer_sync(&gdev->heartbeat_timer);
 	vbg_heartbeat_host_config(gdev, false);
-	kfree(gdev->guest_heartbeat_req);
-
+	vbg_req_free(gdev->guest_heartbeat_req,
+		     sizeof(*gdev->guest_heartbeat_req));
 }
 
 /**
@@ -543,7 +537,7 @@ static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
 	if (rc < 0)
 		vbg_err("%s error, rc: %d\n", __func__, rc);
 
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 	return vbg_status_code_to_errno(rc);
 }
 
@@ -617,7 +611,7 @@ static int vbg_set_session_event_filter(struct vbg_dev *gdev,
 
 out:
 	mutex_unlock(&gdev->session_mutex);
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 
 	return ret;
 }
@@ -642,7 +636,7 @@ static int vbg_reset_host_capabilities(struct vbg_dev *gdev)
 	if (rc < 0)
 		vbg_err("%s error, rc: %d\n", __func__, rc);
 
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 	return vbg_status_code_to_errno(rc);
 }
 
@@ -712,7 +706,7 @@ static int vbg_set_session_capabilities(struct vbg_dev *gdev,
 
 out:
 	mutex_unlock(&gdev->session_mutex);
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 
 	return ret;
 }
@@ -733,8 +727,10 @@ static int vbg_query_host_version(struct vbg_dev *gdev)
 
 	rc = vbg_req_perform(gdev, req);
 	ret = vbg_status_code_to_errno(rc);
-	if (ret)
+	if (ret) {
+		vbg_err("%s error: %d\n", __func__, rc);
 		goto out;
+	}
 
 	snprintf(gdev->host_version, sizeof(gdev->host_version), "%u.%u.%ur%u",
 		 req->major, req->minor, req->build, req->revision);
@@ -749,7 +745,7 @@ static int vbg_query_host_version(struct vbg_dev *gdev)
 	}
 
 out:
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 	return ret;
 }
 
@@ -847,11 +843,16 @@ int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events)
 	return 0;
 
 err_free_reqs:
-	kfree(gdev->mouse_status_req);
-	kfree(gdev->ack_events_req);
-	kfree(gdev->cancel_req);
-	kfree(gdev->mem_balloon.change_req);
-	kfree(gdev->mem_balloon.get_req);
+	vbg_req_free(gdev->mouse_status_req,
+		     sizeof(*gdev->mouse_status_req));
+	vbg_req_free(gdev->ack_events_req,
+		     sizeof(*gdev->ack_events_req));
+	vbg_req_free(gdev->cancel_req,
+		     sizeof(*gdev->cancel_req));
+	vbg_req_free(gdev->mem_balloon.change_req,
+		     sizeof(*gdev->mem_balloon.change_req));
+	vbg_req_free(gdev->mem_balloon.get_req,
+		     sizeof(*gdev->mem_balloon.get_req));
 	return ret;
 }
 
@@ -872,11 +873,16 @@ void vbg_core_exit(struct vbg_dev *gdev)
 	vbg_reset_host_capabilities(gdev);
 	vbg_core_set_mouse_status(gdev, 0);
 
-	kfree(gdev->mouse_status_req);
-	kfree(gdev->ack_events_req);
-	kfree(gdev->cancel_req);
-	kfree(gdev->mem_balloon.change_req);
-	kfree(gdev->mem_balloon.get_req);
+	vbg_req_free(gdev->mouse_status_req,
+		     sizeof(*gdev->mouse_status_req));
+	vbg_req_free(gdev->ack_events_req,
+		     sizeof(*gdev->ack_events_req));
+	vbg_req_free(gdev->cancel_req,
+		     sizeof(*gdev->cancel_req));
+	vbg_req_free(gdev->mem_balloon.change_req,
+		     sizeof(*gdev->mem_balloon.change_req));
+	vbg_req_free(gdev->mem_balloon.get_req,
+		     sizeof(*gdev->mem_balloon.get_req));
 }
 
 /**
@@ -1415,7 +1421,7 @@ static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev,
 	req->flags = dump->u.in.flags;
 	dump->hdr.rc = vbg_req_perform(gdev, req);
 
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 	return 0;
 }
 
@@ -1513,7 +1519,7 @@ int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features)
 	if (rc < 0)
 		vbg_err("%s error, rc: %d\n", __func__, rc);
 
-	kfree(req);
+	vbg_req_free(req, sizeof(*req));
 	return vbg_status_code_to_errno(rc);
 }
 
diff --git a/drivers/virt/vboxguest/vboxguest_core.h b/drivers/virt/vboxguest/vboxguest_core.h
index 6c784bf4fa6d..7ad9ec45bfa9 100644
--- a/drivers/virt/vboxguest/vboxguest_core.h
+++ b/drivers/virt/vboxguest/vboxguest_core.h
@@ -171,4 +171,13 @@ irqreturn_t vbg_core_isr(int irq, void *dev_id);
 
 void vbg_linux_mouse_event(struct vbg_dev *gdev);
 
+/* Private (non exported) functions form vboxguest_utils.c */
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type);
+void vbg_req_free(void *req, size_t len);
+int vbg_req_perform(struct vbg_dev *gdev, void *req);
+int vbg_hgcm_call32(
+	struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
+	struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
+	int *vbox_status);
+
 #endif
diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c
index 82e280d38cc2..6e2a9619192d 100644
--- a/drivers/virt/vboxguest/vboxguest_linux.c
+++ b/drivers/virt/vboxguest/vboxguest_linux.c
@@ -87,6 +87,7 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
 	struct vbg_session *session = filp->private_data;
 	size_t returned_size, size;
 	struct vbg_ioctl_hdr hdr;
+	bool is_vmmdev_req;
 	int ret = 0;
 	void *buf;
 
@@ -106,12 +107,23 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
 	if (size > SZ_16M)
 		return -E2BIG;
 
-	/* __GFP_DMA32 because IOCTL_VMMDEV_REQUEST passes this to the host */
-	buf = kmalloc(size, GFP_KERNEL | __GFP_DMA32);
+	/*
+	 * IOCTL_VMMDEV_REQUEST needs the buffer to be below 4G to avoid
+	 * the need for a bounce-buffer and another copy later on.
+	 */
+	is_vmmdev_req = (req & ~IOCSIZE_MASK) == VBG_IOCTL_VMMDEV_REQUEST(0) ||
+			 req == VBG_IOCTL_VMMDEV_REQUEST_BIG;
+
+	if (is_vmmdev_req)
+		buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT);
+	else
+		buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	if (copy_from_user(buf, (void *)arg, hdr.size_in)) {
+	*((struct vbg_ioctl_hdr *)buf) = hdr;
+	if (copy_from_user(buf + sizeof(hdr), (void *)arg + sizeof(hdr),
+			   hdr.size_in - sizeof(hdr))) {
 		ret = -EFAULT;
 		goto out;
 	}
@@ -132,7 +144,10 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
 		ret = -EFAULT;
 
 out:
-	kfree(buf);
+	if (is_vmmdev_req)
+		vbg_req_free(buf, size);
+	else
+		kfree(buf);
 
 	return ret;
 }
diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c
index 0f0dab8023cf..bf4474214b4d 100644
--- a/drivers/virt/vboxguest/vboxguest_utils.c
+++ b/drivers/virt/vboxguest/vboxguest_utils.c
@@ -65,8 +65,9 @@ VBG_LOG(vbg_debug, pr_debug);
 void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type)
 {
 	struct vmmdev_request_header *req;
+	int order = get_order(PAGE_ALIGN(len));
 
-	req = kmalloc(len, GFP_KERNEL | __GFP_DMA32);
+	req = (void *)__get_free_pages(GFP_KERNEL | GFP_DMA32, order);
 	if (!req)
 		return NULL;
 
@@ -82,6 +83,14 @@ void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type)
 	return req;
 }
 
+void vbg_req_free(void *req, size_t len)
+{
+	if (!req)
+		return;
+
+	free_pages((unsigned long)req, get_order(PAGE_ALIGN(len)));
+}
+
 /* Note this function returns a VBox status code, not a negative errno!! */
 int vbg_req_perform(struct vbg_dev *gdev, void *req)
 {
@@ -137,7 +146,7 @@ int vbg_hgcm_connect(struct vbg_dev *gdev,
 		rc = hgcm_connect->header.result;
 	}
 
-	kfree(hgcm_connect);
+	vbg_req_free(hgcm_connect, sizeof(*hgcm_connect));
 
 	*vbox_status = rc;
 	return 0;
@@ -166,7 +175,7 @@ int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 client_id, int *vbox_status)
 	if (rc >= 0)
 		rc = hgcm_disconnect->header.result;
 
-	kfree(hgcm_disconnect);
+	vbg_req_free(hgcm_disconnect, sizeof(*hgcm_disconnect));
 
 	*vbox_status = rc;
 	return 0;
@@ -623,7 +632,7 @@ int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
 	}
 
 	if (!leak_it)
-		kfree(call);
+		vbg_req_free(call, size);
 
 free_bounce_bufs:
 	if (bounce_bufs) {
diff --git a/drivers/w1/masters/mxc_w1.c b/drivers/w1/masters/mxc_w1.c
index 74f2e6e6202a..8851d441e5fd 100644
--- a/drivers/w1/masters/mxc_w1.c
+++ b/drivers/w1/masters/mxc_w1.c
@@ -112,6 +112,10 @@ static int mxc_w1_probe(struct platform_device *pdev)
 	if (IS_ERR(mdev->clk))
 		return PTR_ERR(mdev->clk);
 
+	err = clk_prepare_enable(mdev->clk);
+	if (err)
+		return err;
+
 	clkrate = clk_get_rate(mdev->clk);
 	if (clkrate < 10000000)
 		dev_warn(&pdev->dev,
@@ -125,12 +129,10 @@ static int mxc_w1_probe(struct platform_device *pdev)
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mdev->regs = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(mdev->regs))
-		return PTR_ERR(mdev->regs);
-
-	err = clk_prepare_enable(mdev->clk);
-	if (err)
-		return err;
+	if (IS_ERR(mdev->regs)) {
+		err = PTR_ERR(mdev->regs);
+		goto out_disable_clk;
+	}
 
 	/* Software reset 1-Wire module */
 	writeb(MXC_W1_RESET_RST, mdev->regs + MXC_W1_RESET);
@@ -146,8 +148,12 @@ static int mxc_w1_probe(struct platform_device *pdev)
 
 	err = w1_add_master_device(&mdev->bus_master);
 	if (err)
-		clk_disable_unprepare(mdev->clk);
+		goto out_disable_clk;
 
+	return 0;
+
+out_disable_clk:
+	clk_disable_unprepare(mdev->clk);
 	return err;
 }
 
diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index 80a778b02f28..caef0e0fd817 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -751,7 +751,7 @@ int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn)
 
 	/* slave modules need to be loaded in a context with unlocked mutex */
 	mutex_unlock(&dev->mutex);
-	request_module("w1-family-0x%02x", rn->family);
+	request_module("w1-family-0x%02X", rn->family);
 	mutex_lock(&dev->mutex);
 
 	spin_lock(&w1_flock);
diff --git a/drivers/w1/w1_io.c b/drivers/w1/w1_io.c
index 075d120e7b88..0364d3329c52 100644
--- a/drivers/w1/w1_io.c
+++ b/drivers/w1/w1_io.c
@@ -194,6 +194,7 @@ static u8 w1_read_bit(struct w1_master *dev)
  *  bit 0 = id_bit
  *  bit 1 = comp_bit
  *  bit 2 = dir_taken
+ *
  * If both bits 0 & 1 are set, the search should be restarted.
  *
  * Return:        bit fields - see above
diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c
index a5b8eb21201f..1abe4d021fd2 100644
--- a/drivers/watchdog/aspeed_wdt.c
+++ b/drivers/watchdog/aspeed_wdt.c
@@ -55,6 +55,8 @@ MODULE_DEVICE_TABLE(of, aspeed_wdt_of_table);
 #define   WDT_CTRL_WDT_INTR		BIT(2)
 #define   WDT_CTRL_RESET_SYSTEM		BIT(1)
 #define   WDT_CTRL_ENABLE		BIT(0)
+#define WDT_TIMEOUT_STATUS	0x10
+#define   WDT_TIMEOUT_STATUS_BOOT_SECONDARY	BIT(1)
 
 /*
  * WDT_RESET_WIDTH controls the characteristics of the external pulse (if
@@ -192,6 +194,7 @@ static int aspeed_wdt_probe(struct platform_device *pdev)
 	struct device_node *np;
 	const char *reset_type;
 	u32 duration;
+	u32 status;
 	int ret;
 
 	wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
@@ -307,6 +310,10 @@ static int aspeed_wdt_probe(struct platform_device *pdev)
 		writel(duration - 1, wdt->base + WDT_RESET_WIDTH);
 	}
 
+	status = readl(wdt->base + WDT_TIMEOUT_STATUS);
+	if (status & WDT_TIMEOUT_STATUS_BOOT_SECONDARY)
+		wdt->wdd.bootstatus = WDIOF_CARDRESET;
+
 	ret = devm_watchdog_register_device(&pdev->dev, &wdt->wdd);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register\n");
diff --git a/drivers/watchdog/renesas_wdt.c b/drivers/watchdog/renesas_wdt.c
index 6b8c6ddfe30b..514db5cc1595 100644
--- a/drivers/watchdog/renesas_wdt.c
+++ b/drivers/watchdog/renesas_wdt.c
@@ -121,7 +121,8 @@ static int rwdt_restart(struct watchdog_device *wdev, unsigned long action,
 }
 
 static const struct watchdog_info rwdt_ident = {
-	.options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT,
+	.options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT |
+		WDIOF_CARDRESET,
 	.identity = "Renesas WDT Watchdog",
 };
 
@@ -197,9 +198,10 @@ static int rwdt_probe(struct platform_device *pdev)
 		return PTR_ERR(clk);
 
 	pm_runtime_enable(&pdev->dev);
-
 	pm_runtime_get_sync(&pdev->dev);
 	priv->clk_rate = clk_get_rate(clk);
+	priv->wdev.bootstatus = (readb_relaxed(priv->base + RWTCSRA) &
+				RWTCSRA_WOVF) ? WDIOF_CARDRESET : 0;
 	pm_runtime_put(&pdev->dev);
 
 	if (!priv->clk_rate) {
diff --git a/drivers/watchdog/sch311x_wdt.c b/drivers/watchdog/sch311x_wdt.c
index 43d0cbb7ba0b..814cdf539b0f 100644
--- a/drivers/watchdog/sch311x_wdt.c
+++ b/drivers/watchdog/sch311x_wdt.c
@@ -299,7 +299,7 @@ static long sch311x_wdt_ioctl(struct file *file, unsigned int cmd,
 		if (sch311x_wdt_set_heartbeat(new_timeout))
 			return -EINVAL;
 		sch311x_wdt_keepalive();
-		/* Fall */
+		/* Fall through */
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 	default:
diff --git a/drivers/watchdog/w83977f_wdt.c b/drivers/watchdog/w83977f_wdt.c
index 20e2bba10400..672b61a7f9a3 100644
--- a/drivers/watchdog/w83977f_wdt.c
+++ b/drivers/watchdog/w83977f_wdt.c
@@ -427,7 +427,7 @@ static long wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			return -EINVAL;
 
 		wdt_keepalive();
-		/* Fall */
+		/* Fall through */
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, uarg.i);
diff --git a/drivers/watchdog/wafer5823wdt.c b/drivers/watchdog/wafer5823wdt.c
index db0da7ea4fd8..93c5b610e264 100644
--- a/drivers/watchdog/wafer5823wdt.c
+++ b/drivers/watchdog/wafer5823wdt.c
@@ -178,7 +178,7 @@ static long wafwdt_ioctl(struct file *file, unsigned int cmd,
 		timeout = new_timeout;
 		wafwdt_stop();
 		wafwdt_start();
-		/* Fall */
+		/* Fall through */
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index e1c60899fdbc..a6f9ba85dc4b 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -351,7 +351,7 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	 * physical address */
 	phys = xen_bus_to_phys(dev_addr);
 
-	if (((dev_addr + size - 1 > dma_mask)) ||
+	if (((dev_addr + size - 1 <= dma_mask)) ||
 	    range_straddles_page_boundary(phys, size))
 		xen_destroy_contiguous_region(phys, order);
 
diff --git a/drivers/xen/xen-pciback/conf_space_quirks.c b/drivers/xen/xen-pciback/conf_space_quirks.c
index 89d9744ece61..ed593d1042a6 100644
--- a/drivers/xen/xen-pciback/conf_space_quirks.c
+++ b/drivers/xen/xen-pciback/conf_space_quirks.c
@@ -95,7 +95,7 @@ int xen_pcibk_config_quirks_init(struct pci_dev *dev)
 	struct xen_pcibk_config_quirk *quirk;
 	int ret = 0;
 
-	quirk = kzalloc(sizeof(*quirk), GFP_ATOMIC);
+	quirk = kzalloc(sizeof(*quirk), GFP_KERNEL);
 	if (!quirk) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 9e480fdebe1f..59661db144e5 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -71,7 +71,7 @@ static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev)
 
 	dev_dbg(&dev->dev, "pcistub_device_alloc\n");
 
-	psdev = kzalloc(sizeof(*psdev), GFP_ATOMIC);
+	psdev = kzalloc(sizeof(*psdev), GFP_KERNEL);
 	if (!psdev)
 		return NULL;
 
@@ -364,7 +364,7 @@ static int pcistub_init_device(struct pci_dev *dev)
 	 * here and then to call kfree(pci_get_drvdata(psdev->dev)).
 	 */
 	dev_data = kzalloc(sizeof(*dev_data) +  strlen(DRV_NAME "[]")
-				+ strlen(pci_name(dev)) + 1, GFP_ATOMIC);
+				+ strlen(pci_name(dev)) + 1, GFP_KERNEL);
 	if (!dev_data) {
 		err = -ENOMEM;
 		goto out;
@@ -577,7 +577,7 @@ static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		}
 
 		if (!match) {
-			pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_ATOMIC);
+			pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_KERNEL);
 			if (!pci_dev_id) {
 				err = -ENOMEM;
 				goto out;
@@ -1149,7 +1149,7 @@ static int pcistub_reg_add(int domain, int bus, int slot, int func,
 	}
 	dev = psdev->dev;
 
-	field = kzalloc(sizeof(*field), GFP_ATOMIC);
+	field = kzalloc(sizeof(*field), GFP_KERNEL);
 	if (!field) {
 		err = -ENOMEM;
 		goto out;
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 0d6d9264d6a9..c3e201025ef0 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -403,7 +403,7 @@ static int xenbus_command_reply(struct xenbus_file_priv *u,
 {
 	struct {
 		struct xsd_sockmsg hdr;
-		const char body[16];
+		char body[16];
 	} msg;
 	int rc;
 
@@ -412,6 +412,7 @@ static int xenbus_command_reply(struct xenbus_file_priv *u,
 	msg.hdr.len = strlen(reply) + 1;
 	if (msg.hdr.len > sizeof(msg.body))
 		return -E2BIG;
+	memcpy(&msg.body, reply, msg.hdr.len);
 
 	mutex_lock(&u->reply_mutex);
 	rc = queue_reply(&u->read_buffers, &msg, sizeof(msg.hdr) + msg.hdr.len);
diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c
index df05a26ab8d8..2e4ca4dc0960 100644
--- a/drivers/zorro/proc.c
+++ b/drivers/zorro/proc.c
@@ -96,19 +96,6 @@ static const struct seq_operations zorro_devices_seq_ops = {
 	.show  = zorro_seq_show,
 };
 
-static int zorro_devices_proc_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &zorro_devices_seq_ops);
-}
-
-static const struct file_operations zorro_devices_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= zorro_devices_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static struct proc_dir_entry *proc_bus_zorro_dir;
 
 static int __init zorro_proc_attach_device(unsigned int slot)
@@ -132,8 +119,8 @@ static int __init zorro_proc_init(void)
 
 	if (MACH_IS_AMIGA && AMIGAHW_PRESENT(ZORRO)) {
 		proc_bus_zorro_dir = proc_mkdir("bus/zorro", NULL);
-		proc_create("devices", 0, proc_bus_zorro_dir,
-			    &zorro_devices_proc_fops);
+		proc_create_seq("devices", 0, proc_bus_zorro_dir,
+			    &zorro_devices_seq_ops);
 		for (slot = 0; slot < zorro_num_autocon; slot++)
 			zorro_proc_attach_device(slot);
 	}
diff --git a/drivers/zorro/zorro.c b/drivers/zorro/zorro.c
index 47728477297e..67fa900572a9 100644
--- a/drivers/zorro/zorro.c
+++ b/drivers/zorro/zorro.c
@@ -101,6 +101,7 @@ static void __init mark_region(unsigned long start, unsigned long end,
 	end = end > Z2RAM_END ? Z2RAM_SIZE : end-Z2RAM_START;
 	while (start < end) {
 		u32 chunk = start>>Z2RAM_CHUNKSHIFT;
+
 		if (flag)
 			set_bit(chunk, zorro_unused_z2ram);
 		else
@@ -117,6 +118,7 @@ static struct resource __init *zorro_find_parent_resource(
 
 	for (i = 0; i < bridge->num_resources; i++) {
 		struct resource *r = &bridge->resource[i];
+
 		if (zorro_resource_start(z) >= r->start &&
 		    zorro_resource_end(z) <= r->end)
 			return r;
@@ -168,6 +170,7 @@ static int __init amiga_zorro_probe(struct platform_device *pdev)
 		if (z->id == ZORRO_PROD_GVP_EPC_BASE) {
 			/* GVP quirk */
 			unsigned long magic = zi->boardaddr + 0x8000;
+
 			z->id |= *(u16 *)ZTWO_VADDR(magic) & GVP_PRODMASK;
 		}
 		z->slotaddr = zi->slotaddr;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 9ee534159cc6..42e102e2e74a 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -823,28 +823,21 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(dfid))
 		return ERR_CAST(dfid);
 
-	name = dentry->d_name.name;
-	fid = p9_client_walk(dfid, 1, &name, 1);
-	if (IS_ERR(fid)) {
-		if (fid == ERR_PTR(-ENOENT)) {
-			d_add(dentry, NULL);
-			return NULL;
-		}
-		return ERR_CAST(fid);
-	}
 	/*
 	 * Make sure we don't use a wrong inode due to parallel
 	 * unlink. For cached mode create calls request for new
 	 * inode. But with cache disabled, lookup should do this.
 	 */
-	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+	name = dentry->d_name.name;
+	fid = p9_client_walk(dfid, 1, &name, 1);
+	if (fid == ERR_PTR(-ENOENT))
+		inode = NULL;
+	else if (IS_ERR(fid))
+		inode = ERR_CAST(fid);
+	else if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
 	else
 		inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
-	if (IS_ERR(inode)) {
-		p9_client_clunk(fid);
-		return ERR_CAST(inode);
-	}
 	/*
 	 * If we had a rename on the server and a parallel lookup
 	 * for the new name, then make sure we instantiate with
@@ -853,12 +846,14 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	 * k/b.
 	 */
 	res = d_splice_alias(inode, dentry);
-	if (!res)
-		v9fs_fid_add(dentry, fid);
-	else if (!IS_ERR(res))
-		v9fs_fid_add(res, fid);
-	else
-		p9_client_clunk(fid);
+	if (!IS_ERR(fid)) {
+		if (!res)
+			v9fs_fid_add(dentry, fid);
+		else if (!IS_ERR(res))
+			v9fs_fid_add(res, fid);
+		else
+			p9_client_clunk(fid);
+	}
 	return res;
 }
 
diff --git a/fs/Kconfig b/fs/Kconfig
index bc821a86d965..ac4ac908f001 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -196,7 +196,7 @@ config HUGETLBFS
 	help
 	  hugetlbfs is a filesystem backing for HugeTLB pages, based on
 	  ramfs. For architectures that support it, say Y here and read
-	  <file:Documentation/vm/hugetlbpage.txt> for details.
+	  <file:Documentation/admin-guide/mm/hugetlbpage.rst> for details.
 
 	  If unsure, say N.
 
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 29444c83da48..e18eff854e1a 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -146,20 +146,6 @@ adfs_dir_lookup_byname(struct inode *inode, const struct qstr *name, struct obje
 
 	obj->parent_id = inode->i_ino;
 
-	/*
-	 * '.' is handled by reserved_lookup() in fs/namei.c
-	 */
-	if (name->len == 2 && name->name[0] == '.' && name->name[1] == '.') {
-		/*
-		 * Currently unable to fill in the rest of 'obj',
-		 * but this is better than nothing.  We need to
-		 * ascend one level to find it's parent.
-		 */
-		obj->name_len = 0;
-		obj->file_id  = obj->parent_id;
-		goto free_out;
-	}
-
 	read_lock(&adfs_dir_lock);
 
 	ret = ops->setpos(&dir, 0);
@@ -266,17 +252,17 @@ adfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 
 	error = adfs_dir_lookup_byname(dir, &dentry->d_name, &obj);
 	if (error == 0) {
-		error = -EACCES;
 		/*
 		 * This only returns NULL if get_empty_inode
 		 * fails.
 		 */
 		inode = adfs_iget(dir->i_sb, &obj);
-		if (inode)
-			error = 0;
+		if (!inode)
+			inode = ERR_PTR(-EACCES);
+	} else if (error != -ENOENT) {
+		inode = ERR_PTR(error);
 	}
-	d_add(dentry, inode);
-	return ERR_PTR(error);
+	return d_splice_alias(inode, dentry);
 }
 
 /*
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index d8aa0ae3d037..41c5749f4db7 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -201,14 +201,16 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 	struct super_block *sb = dir->i_sb;
 	struct buffer_head *bh;
 	struct inode *inode = NULL;
+	struct dentry *res;
 
 	pr_debug("%s(\"%pd\")\n", __func__, dentry);
 
 	affs_lock_dir(dir);
 	bh = affs_find_entry(dir, dentry);
-	affs_unlock_dir(dir);
-	if (IS_ERR(bh))
+	if (IS_ERR(bh)) {
+		affs_unlock_dir(dir);
 		return ERR_CAST(bh);
+	}
 	if (bh) {
 		u32 ino = bh->b_blocknr;
 
@@ -222,11 +224,12 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 		}
 		affs_brelse(bh);
 		inode = affs_iget(sb, ino);
-		if (IS_ERR(inode))
-			return ERR_CAST(inode);
 	}
-	d_add(dentry, inode);
-	return NULL;
+	res = d_splice_alias(inode, dentry);
+	if (!IS_ERR_OR_NULL(res))
+		res->d_fsdata = dentry->d_fsdata;
+	affs_unlock_dir(dir);
+	return res;
 }
 
 int
diff --git a/fs/affs/super.c b/fs/affs/super.c
index e602619aed9d..d1ad11a8a4a5 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -241,6 +241,7 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
 			affs_set_opt(*mount_opts, SF_NO_TRUNCATE);
 			break;
 		case Opt_prefix:
+			kfree(*prefix);
 			*prefix = match_strdup(&args[0]);
 			if (!*prefix)
 				return 0;
diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index 3bedfed608a2..7587fb665ff1 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -121,7 +121,7 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
 	p = text;
 	do {
 		struct sockaddr_rxrpc *srx = &alist->addrs[alist->nr_addrs];
-		char tdelim = delim;
+		const char *q, *stop;
 
 		if (*p == delim) {
 			p++;
@@ -130,28 +130,33 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
 
 		if (*p == '[') {
 			p++;
-			tdelim = ']';
+			q = memchr(p, ']', end - p);
+		} else {
+			for (q = p; q < end; q++)
+				if (*q == '+' || *q == delim)
+					break;
 		}
 
-		if (in4_pton(p, end - p,
+		if (in4_pton(p, q - p,
 			     (u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3],
-			     tdelim, &p)) {
+			     -1, &stop)) {
 			srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
 			srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
 			srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
-		} else if (in6_pton(p, end - p,
+		} else if (in6_pton(p, q - p,
 				    srx->transport.sin6.sin6_addr.s6_addr,
-				    tdelim, &p)) {
+				    -1, &stop)) {
 			/* Nothing to do */
 		} else {
 			goto bad_address;
 		}
 
-		if (tdelim == ']') {
-			if (p == end || *p != ']')
-				goto bad_address;
+		if (stop != q)
+			goto bad_address;
+
+		p = q;
+		if (q < end && *q == ']')
 			p++;
-		}
 
 		if (p < end) {
 			if (*p == '+') {
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index abd9a84f4e88..571437dcb252 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -23,36 +23,55 @@
 /*
  * Set up an interest-in-callbacks record for a volume on a server and
  * register it with the server.
- * - Called with volume->server_sem held.
+ * - Called with vnode->io_lock held.
  */
 int afs_register_server_cb_interest(struct afs_vnode *vnode,
-				    struct afs_server_entry *entry)
+				    struct afs_server_list *slist,
+				    unsigned int index)
 {
-	struct afs_cb_interest *cbi = entry->cb_interest, *vcbi, *new, *x;
+	struct afs_server_entry *entry = &slist->servers[index];
+	struct afs_cb_interest *cbi, *vcbi, *new, *old;
 	struct afs_server *server = entry->server;
 
 again:
+	if (vnode->cb_interest &&
+	    likely(vnode->cb_interest == entry->cb_interest))
+		return 0;
+
+	read_lock(&slist->lock);
+	cbi = afs_get_cb_interest(entry->cb_interest);
+	read_unlock(&slist->lock);
+
 	vcbi = vnode->cb_interest;
 	if (vcbi) {
-		if (vcbi == cbi)
+		if (vcbi == cbi) {
+			afs_put_cb_interest(afs_v2net(vnode), cbi);
 			return 0;
+		}
 
+		/* Use a new interest in the server list for the same server
+		 * rather than an old one that's still attached to a vnode.
+		 */
 		if (cbi && vcbi->server == cbi->server) {
 			write_seqlock(&vnode->cb_lock);
-			vnode->cb_interest = afs_get_cb_interest(cbi);
+			old = vnode->cb_interest;
+			vnode->cb_interest = cbi;
 			write_sequnlock(&vnode->cb_lock);
-			afs_put_cb_interest(afs_v2net(vnode), cbi);
+			afs_put_cb_interest(afs_v2net(vnode), old);
 			return 0;
 		}
 
+		/* Re-use the one attached to the vnode. */
 		if (!cbi && vcbi->server == server) {
-			afs_get_cb_interest(vcbi);
-			x = cmpxchg(&entry->cb_interest, cbi, vcbi);
-			if (x != cbi) {
-				cbi = x;
-				afs_put_cb_interest(afs_v2net(vnode), vcbi);
+			write_lock(&slist->lock);
+			if (entry->cb_interest) {
+				write_unlock(&slist->lock);
+				afs_put_cb_interest(afs_v2net(vnode), cbi);
 				goto again;
 			}
+
+			entry->cb_interest = cbi;
+			write_unlock(&slist->lock);
 			return 0;
 		}
 	}
@@ -72,13 +91,16 @@ again:
 		list_add_tail(&new->cb_link, &server->cb_interests);
 		write_unlock(&server->cb_break_lock);
 
-		x = cmpxchg(&entry->cb_interest, cbi, new);
-		if (x == cbi) {
+		write_lock(&slist->lock);
+		if (!entry->cb_interest) {
+			entry->cb_interest = afs_get_cb_interest(new);
 			cbi = new;
+			new = NULL;
 		} else {
-			cbi = x;
-			afs_put_cb_interest(afs_v2net(vnode), new);
+			cbi = afs_get_cb_interest(entry->cb_interest);
 		}
+		write_unlock(&slist->lock);
+		afs_put_cb_interest(afs_v2net(vnode), new);
 	}
 
 	ASSERT(cbi);
@@ -88,11 +110,14 @@ again:
 	 */
 	write_seqlock(&vnode->cb_lock);
 
-	vnode->cb_interest = afs_get_cb_interest(cbi);
+	old = vnode->cb_interest;
+	vnode->cb_interest = cbi;
 	vnode->cb_s_break = cbi->server->cb_s_break;
+	vnode->cb_v_break = vnode->volume->cb_v_break;
 	clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
 
 	write_sequnlock(&vnode->cb_lock);
+	afs_put_cb_interest(afs_v2net(vnode), old);
 	return 0;
 }
 
@@ -171,13 +196,24 @@ static void afs_break_one_callback(struct afs_server *server,
 		if (cbi->vid != fid->vid)
 			continue;
 
-		data.volume = NULL;
-		data.fid = *fid;
-		inode = ilookup5_nowait(cbi->sb, fid->vnode, afs_iget5_test, &data);
-		if (inode) {
-			vnode = AFS_FS_I(inode);
-			afs_break_callback(vnode);
-			iput(inode);
+		if (fid->vnode == 0 && fid->unique == 0) {
+			/* The callback break applies to an entire volume. */
+			struct afs_super_info *as = AFS_FS_S(cbi->sb);
+			struct afs_volume *volume = as->volume;
+
+			write_lock(&volume->cb_break_lock);
+			volume->cb_v_break++;
+			write_unlock(&volume->cb_break_lock);
+		} else {
+			data.volume = NULL;
+			data.fid = *fid;
+			inode = ilookup5_nowait(cbi->sb, fid->vnode,
+						afs_iget5_test, &data);
+			if (inode) {
+				vnode = AFS_FS_I(inode);
+				afs_break_callback(vnode);
+				iput(inode);
+			}
 		}
 	}
 
@@ -195,6 +231,8 @@ void afs_break_callbacks(struct afs_server *server, size_t count,
 	ASSERT(server != NULL);
 	ASSERTCMP(count, <=, AFSCBMAX);
 
+	/* TODO: Sort the callback break list by volume ID */
+
 	for (; count > 0; callbacks++, count--) {
 		_debug("- Fid { vl=%08x n=%u u=%u }  CB { v=%u x=%u t=%u }",
 		       callbacks->fid.vid,
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 357de908df3a..c332c95a6940 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -133,21 +133,10 @@ bool afs_cm_incoming_call(struct afs_call *call)
 }
 
 /*
- * clean up a cache manager call
+ * Clean up a cache manager call.
  */
 static void afs_cm_destructor(struct afs_call *call)
 {
-	_enter("");
-
-	/* Break the callbacks here so that we do it after the final ACK is
-	 * received.  The step number here must match the final number in
-	 * afs_deliver_cb_callback().
-	 */
-	if (call->unmarshall == 5) {
-		ASSERT(call->cm_server && call->count && call->request);
-		afs_break_callbacks(call->cm_server, call->count, call->request);
-	}
-
 	kfree(call->buffer);
 	call->buffer = NULL;
 }
@@ -161,14 +150,14 @@ static void SRXAFSCB_CallBack(struct work_struct *work)
 
 	_enter("");
 
-	/* be sure to send the reply *before* attempting to spam the AFS server
-	 * with FSFetchStatus requests on the vnodes with broken callbacks lest
-	 * the AFS server get into a vicious cycle of trying to break further
-	 * callbacks because it hadn't received completion of the CBCallBack op
-	 * yet */
-	afs_send_empty_reply(call);
+	/* We need to break the callbacks before sending the reply as the
+	 * server holds up change visibility till it receives our reply so as
+	 * to maintain cache coherency.
+	 */
+	if (call->cm_server)
+		afs_break_callbacks(call->cm_server, call->count, call->request);
 
-	afs_break_callbacks(call->cm_server, call->count, call->request);
+	afs_send_empty_reply(call);
 	afs_put_call(call);
 	_leave("");
 }
@@ -180,7 +169,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 {
 	struct afs_callback_break *cb;
 	struct sockaddr_rxrpc srx;
-	struct afs_server *server;
 	__be32 *bp;
 	int ret, loop;
 
@@ -267,15 +255,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 
 		call->offset = 0;
 		call->unmarshall++;
-
-		/* Record that the message was unmarshalled successfully so
-		 * that the call destructor can know do the callback breaking
-		 * work, even if the final ACK isn't received.
-		 *
-		 * If the step number changes, then afs_cm_destructor() must be
-		 * updated also.
-		 */
-		call->unmarshall++;
 	case 5:
 		break;
 	}
@@ -286,10 +265,9 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 	/* we'll need the file server record as that tells us which set of
 	 * vnodes to operate upon */
 	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
-	server = afs_find_server(call->net, &srx);
-	if (!server)
-		return -ENOTCONN;
-	call->cm_server = server;
+	call->cm_server = afs_find_server(call->net, &srx);
+	if (!call->cm_server)
+		trace_afs_cm_no_server(call, &srx);
 
 	return afs_queue_call_work(call);
 }
@@ -303,7 +281,8 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
 
 	_enter("{%p}", call->cm_server);
 
-	afs_init_callback_state(call->cm_server);
+	if (call->cm_server)
+		afs_init_callback_state(call->cm_server);
 	afs_send_empty_reply(call);
 	afs_put_call(call);
 	_leave("");
@@ -315,7 +294,6 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
 static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
 {
 	struct sockaddr_rxrpc srx;
-	struct afs_server *server;
 	int ret;
 
 	_enter("");
@@ -328,10 +306,9 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
 
 	/* we'll need the file server record as that tells us which set of
 	 * vnodes to operate upon */
-	server = afs_find_server(call->net, &srx);
-	if (!server)
-		return -ENOTCONN;
-	call->cm_server = server;
+	call->cm_server = afs_find_server(call->net, &srx);
+	if (!call->cm_server)
+		trace_afs_cm_no_server(call, &srx);
 
 	return afs_queue_call_work(call);
 }
@@ -341,8 +318,6 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
  */
 static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 {
-	struct sockaddr_rxrpc srx;
-	struct afs_server *server;
 	struct afs_uuid *r;
 	unsigned loop;
 	__be32 *b;
@@ -398,11 +373,11 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 
 	/* we'll need the file server record as that tells us which set of
 	 * vnodes to operate upon */
-	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
-	server = afs_find_server(call->net, &srx);
-	if (!server)
-		return -ENOTCONN;
-	call->cm_server = server;
+	rcu_read_lock();
+	call->cm_server = afs_find_server_by_uuid(call->net, call->request);
+	rcu_read_unlock();
+	if (!call->cm_server)
+		trace_afs_cm_no_server_u(call, call->request);
 
 	return afs_queue_call_work(call);
 }
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 5889f70d4d27..7d623008157f 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -180,6 +180,7 @@ static int afs_dir_open(struct inode *inode, struct file *file)
  * get reclaimed during the iteration.
  */
 static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
+	__acquires(&dvnode->validate_lock)
 {
 	struct afs_read *req;
 	loff_t i_size;
@@ -261,18 +262,21 @@ retry:
 	/* If we're going to reload, we need to lock all the pages to prevent
 	 * races.
 	 */
-	if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
-		ret = -ERESTARTSYS;
-		for (i = 0; i < req->nr_pages; i++)
-			if (lock_page_killable(req->pages[i]) < 0)
-				goto error_unlock;
+	ret = -ERESTARTSYS;
+	if (down_read_killable(&dvnode->validate_lock) < 0)
+		goto error;
 
-		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
-			goto success;
+	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+		goto success;
+
+	up_read(&dvnode->validate_lock);
+	if (down_write_killable(&dvnode->validate_lock) < 0)
+		goto error;
 
+	if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
 		ret = afs_fetch_data(dvnode, key, req);
 		if (ret < 0)
-			goto error_unlock_all;
+			goto error_unlock;
 
 		task_io_account_read(PAGE_SIZE * req->nr_pages);
 
@@ -284,33 +288,26 @@ retry:
 		for (i = 0; i < req->nr_pages; i++)
 			if (!afs_dir_check_page(dvnode, req->pages[i],
 						req->actual_len))
-				goto error_unlock_all;
+				goto error_unlock;
 
 		// TODO: Trim excess pages
 
 		set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags);
 	}
 
+	downgrade_write(&dvnode->validate_lock);
 success:
-	i = req->nr_pages;
-	while (i > 0)
-		unlock_page(req->pages[--i]);
 	return req;
 
-error_unlock_all:
-	i = req->nr_pages;
 error_unlock:
-	while (i > 0)
-		unlock_page(req->pages[--i]);
+	up_write(&dvnode->validate_lock);
 error:
 	afs_put_read(req);
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
 
 content_has_grown:
-	i = req->nr_pages;
-	while (i > 0)
-		unlock_page(req->pages[--i]);
+	up_write(&dvnode->validate_lock);
 	afs_put_read(req);
 	goto retry;
 }
@@ -473,6 +470,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
 	}
 
 out:
+	up_read(&dvnode->validate_lock);
 	afs_put_read(req);
 	_leave(" = %d", ret);
 	return ret;
@@ -1143,7 +1141,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
 			afs_fs_create(&fc, dentry->d_name.name, mode, data_version,
 				      &newfid, &newstatus, &newcb);
 		}
@@ -1213,7 +1211,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
 			afs_fs_remove(&fc, dentry->d_name.name, true,
 				      data_version);
 		}
@@ -1316,7 +1314,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
 			afs_fs_remove(&fc, dentry->d_name.name, false,
 				      data_version);
 		}
@@ -1373,7 +1371,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
 			afs_fs_create(&fc, dentry->d_name.name, mode, data_version,
 				      &newfid, &newstatus, &newcb);
 		}
@@ -1443,8 +1441,8 @@ static int afs_link(struct dentry *from, struct inode *dir,
 		}
 
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
-			fc.cb_break_2 = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
+			fc.cb_break_2 = afs_calc_vnode_cb_break(vnode);
 			afs_fs_link(&fc, vnode, dentry->d_name.name, data_version);
 		}
 
@@ -1512,7 +1510,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
 			afs_fs_symlink(&fc, dentry->d_name.name,
 				       content, data_version,
 				       &newfid, &newstatus);
@@ -1588,8 +1586,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			}
 		}
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = orig_dvnode->cb_break + orig_dvnode->cb_s_break;
-			fc.cb_break_2 = new_dvnode->cb_break + new_dvnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode);
+			fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode);
 			afs_fs_rename(&fc, old_dentry->d_name.name,
 				      new_dvnode, new_dentry->d_name.name,
 				      orig_data_version, new_data_version);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index c24c08016dd9..7d4f26198573 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -238,7 +238,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, vnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(vnode);
 			afs_fs_fetch_data(&fc, desc);
 		}
 
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 7a0e017070ec..dc62d15a964b 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -86,7 +86,7 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key,
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, vnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(vnode);
 			afs_fs_set_lock(&fc, type);
 		}
 
@@ -117,7 +117,7 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key)
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, vnode, key)) {
 		while (afs_select_current_fileserver(&fc)) {
-			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(vnode);
 			afs_fs_extend_lock(&fc);
 		}
 
@@ -148,7 +148,7 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key)
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, vnode, key)) {
 		while (afs_select_current_fileserver(&fc)) {
-			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(vnode);
 			afs_fs_release_lock(&fc);
 		}
 
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index efacdb7c1dee..b273e1d60478 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -134,6 +134,7 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
 				     struct afs_read *read_req)
 {
 	const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp;
+	bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus);
 	u64 data_version, size;
 	u32 type, abort_code;
 	u8 flags = 0;
@@ -142,13 +143,32 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
 	if (vnode)
 		write_seqlock(&vnode->cb_lock);
 
+	abort_code = ntohl(xdr->abort_code);
+
 	if (xdr->if_version != htonl(AFS_FSTATUS_VERSION)) {
+		if (xdr->if_version == htonl(0) &&
+		    abort_code != 0 &&
+		    inline_error) {
+			/* The OpenAFS fileserver has a bug in FS.InlineBulkStatus
+			 * whereby it doesn't set the interface version in the error
+			 * case.
+			 */
+			status->abort_code = abort_code;
+			ret = 0;
+			goto out;
+		}
+
 		pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version));
 		goto bad;
 	}
 
+	if (abort_code != 0 && inline_error) {
+		status->abort_code = abort_code;
+		ret = 0;
+		goto out;
+	}
+
 	type = ntohl(xdr->type);
-	abort_code = ntohl(xdr->abort_code);
 	switch (type) {
 	case AFS_FTYPE_FILE:
 	case AFS_FTYPE_DIR:
@@ -165,13 +185,6 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
 		}
 		status->type = type;
 		break;
-	case AFS_FTYPE_INVALID:
-		if (abort_code != 0) {
-			status->abort_code = abort_code;
-			ret = 0;
-			goto out;
-		}
-		/* Fall through */
 	default:
 		goto bad;
 	}
@@ -248,7 +261,7 @@ static void xdr_decode_AFSCallBack(struct afs_call *call,
 
 	write_seqlock(&vnode->cb_lock);
 
-	if (call->cb_break == (vnode->cb_break + cbi->server->cb_s_break)) {
+	if (call->cb_break == afs_cb_break_sum(vnode, cbi)) {
 		vnode->cb_version	= ntohl(*bp++);
 		cb_expiry		= ntohl(*bp++);
 		vnode->cb_type		= ntohl(*bp++);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 06194cfe9724..479b7fdda124 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -108,7 +108,7 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode)
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, vnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(vnode);
 			afs_fs_fetch_file_status(&fc, NULL, new_inode);
 		}
 
@@ -393,15 +393,18 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 	read_seqlock_excl(&vnode->cb_lock);
 
 	if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
-		if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break) {
+		if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break ||
+		    vnode->cb_v_break != vnode->volume->cb_v_break) {
 			vnode->cb_s_break = vnode->cb_interest->server->cb_s_break;
+			vnode->cb_v_break = vnode->volume->cb_v_break;
+			valid = false;
 		} else if (vnode->status.type == AFS_FTYPE_DIR &&
 			   test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) &&
 			   vnode->cb_expires_at - 10 > now) {
-				valid = true;
+			valid = true;
 		} else if (!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) &&
 			   vnode->cb_expires_at - 10 > now) {
-				valid = true;
+			valid = true;
 		}
 	} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
 		valid = true;
@@ -415,7 +418,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 	if (valid)
 		goto valid;
 
-	mutex_lock(&vnode->validate_lock);
+	down_write(&vnode->validate_lock);
 
 	/* if the promise has expired, we need to check the server again to get
 	 * a new promise - note that if the (parent) directory's metadata was
@@ -444,13 +447,13 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 	 * different */
 	if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
 		afs_zap_data(vnode);
-	mutex_unlock(&vnode->validate_lock);
+	up_write(&vnode->validate_lock);
 valid:
 	_leave(" = 0");
 	return 0;
 
 error_unlock:
-	mutex_unlock(&vnode->validate_lock);
+	up_write(&vnode->validate_lock);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -574,7 +577,7 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, vnode, key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(vnode);
 			afs_fs_setattr(&fc, attr);
 		}
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index f8086ec95e24..e3f8a46663db 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -396,6 +396,7 @@ struct afs_server {
 #define AFS_SERVER_FL_PROBED	5		/* The fileserver has been probed */
 #define AFS_SERVER_FL_PROBING	6		/* Fileserver is being probed */
 #define AFS_SERVER_FL_NO_IBULK	7		/* Fileserver doesn't support FS.InlineBulkStatus */
+#define AFS_SERVER_FL_MAY_HAVE_CB 8		/* May have callbacks on this fileserver */
 	atomic_t		usage;
 	u32			addr_version;	/* Address list version */
 
@@ -433,6 +434,7 @@ struct afs_server_list {
 	unsigned short		index;		/* Server currently in use */
 	unsigned short		vnovol_mask;	/* Servers to be skipped due to VNOVOL */
 	unsigned int		seq;		/* Set to ->servers_seq when installed */
+	rwlock_t		lock;
 	struct afs_server_entry	servers[];
 };
 
@@ -459,6 +461,9 @@ struct afs_volume {
 	rwlock_t		servers_lock;	/* Lock for ->servers */
 	unsigned int		servers_seq;	/* Incremented each time ->servers changes */
 
+	unsigned		cb_v_break;	/* Break-everything counter. */
+	rwlock_t		cb_break_lock;
+
 	afs_voltype_t		type;		/* type of volume */
 	short			error;
 	char			type_force;	/* force volume type (suppress R/O -> R/W) */
@@ -494,7 +499,7 @@ struct afs_vnode {
 #endif
 	struct afs_permits __rcu *permit_cache;	/* cache of permits so far obtained */
 	struct mutex		io_lock;	/* Lock for serialising I/O on this mutex */
-	struct mutex		validate_lock;	/* lock for validating this vnode */
+	struct rw_semaphore	validate_lock;	/* lock for validating this vnode */
 	spinlock_t		wb_lock;	/* lock for wb_keys */
 	spinlock_t		lock;		/* waitqueue/flags lock */
 	unsigned long		flags;
@@ -519,6 +524,7 @@ struct afs_vnode {
 	/* outstanding callback notification on this file */
 	struct afs_cb_interest	*cb_interest;	/* Server on which this resides */
 	unsigned int		cb_s_break;	/* Mass break counter on ->server */
+	unsigned int		cb_v_break;	/* Mass break counter on ->volume */
 	unsigned int		cb_break;	/* Break counter on vnode */
 	seqlock_t		cb_lock;	/* Lock for ->cb_interest, ->status, ->cb_*break */
 
@@ -648,16 +654,29 @@ extern void afs_init_callback_state(struct afs_server *);
 extern void afs_break_callback(struct afs_vnode *);
 extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*);
 
-extern int afs_register_server_cb_interest(struct afs_vnode *, struct afs_server_entry *);
+extern int afs_register_server_cb_interest(struct afs_vnode *,
+					   struct afs_server_list *, unsigned int);
 extern void afs_put_cb_interest(struct afs_net *, struct afs_cb_interest *);
 extern void afs_clear_callback_interests(struct afs_net *, struct afs_server_list *);
 
 static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest *cbi)
 {
-	refcount_inc(&cbi->usage);
+	if (cbi)
+		refcount_inc(&cbi->usage);
 	return cbi;
 }
 
+static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
+{
+	return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break;
+}
+
+static inline unsigned int afs_cb_break_sum(struct afs_vnode *vnode,
+					    struct afs_cb_interest *cbi)
+{
+	return vnode->cb_break + cbi->server->cb_s_break + vnode->volume->cb_v_break;
+}
+
 /*
  * cell.c
  */
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 839a22280606..3aad32762989 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -62,7 +62,6 @@ static const struct file_operations afs_proc_rootcell_fops = {
 	.llseek		= no_llseek,
 };
 
-static int afs_proc_cell_volumes_open(struct inode *inode, struct file *file);
 static void *afs_proc_cell_volumes_start(struct seq_file *p, loff_t *pos);
 static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v,
 					loff_t *pos);
@@ -76,15 +75,6 @@ static const struct seq_operations afs_proc_cell_volumes_ops = {
 	.show	= afs_proc_cell_volumes_show,
 };
 
-static const struct file_operations afs_proc_cell_volumes_fops = {
-	.open		= afs_proc_cell_volumes_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static int afs_proc_cell_vlservers_open(struct inode *inode,
-					struct file *file);
 static void *afs_proc_cell_vlservers_start(struct seq_file *p, loff_t *pos);
 static void *afs_proc_cell_vlservers_next(struct seq_file *p, void *v,
 					  loff_t *pos);
@@ -98,14 +88,6 @@ static const struct seq_operations afs_proc_cell_vlservers_ops = {
 	.show	= afs_proc_cell_vlservers_show,
 };
 
-static const struct file_operations afs_proc_cell_vlservers_fops = {
-	.open		= afs_proc_cell_vlservers_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static int afs_proc_servers_open(struct inode *inode, struct file *file);
 static void *afs_proc_servers_start(struct seq_file *p, loff_t *pos);
 static void *afs_proc_servers_next(struct seq_file *p, void *v,
 					loff_t *pos);
@@ -119,13 +101,6 @@ static const struct seq_operations afs_proc_servers_ops = {
 	.show	= afs_proc_servers_show,
 };
 
-static const struct file_operations afs_proc_servers_fops = {
-	.open		= afs_proc_servers_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int afs_proc_sysname_open(struct inode *inode, struct file *file);
 static int afs_proc_sysname_release(struct inode *inode, struct file *file);
 static void *afs_proc_sysname_start(struct seq_file *p, loff_t *pos);
@@ -152,7 +127,7 @@ static const struct file_operations afs_proc_sysname_fops = {
 	.write		= afs_proc_sysname_write,
 };
 
-static const struct file_operations afs_proc_stats_fops;
+static int afs_proc_stats_show(struct seq_file *m, void *v);
 
 /*
  * initialise the /proc/fs/afs/ directory
@@ -167,8 +142,8 @@ int afs_proc_init(struct afs_net *net)
 
 	if (!proc_create("cells", 0644, net->proc_afs, &afs_proc_cells_fops) ||
 	    !proc_create("rootcell", 0644, net->proc_afs, &afs_proc_rootcell_fops) ||
-	    !proc_create("servers", 0644, net->proc_afs, &afs_proc_servers_fops) ||
-	    !proc_create("stats", 0644, net->proc_afs, &afs_proc_stats_fops) ||
+	    !proc_create_seq("servers", 0644, net->proc_afs, &afs_proc_servers_ops) ||
+	    !proc_create_single("stats", 0644, net->proc_afs, afs_proc_stats_show) ||
 	    !proc_create("sysname", 0644, net->proc_afs, &afs_proc_sysname_fops))
 		goto error_tree;
 
@@ -196,16 +171,7 @@ void afs_proc_cleanup(struct afs_net *net)
  */
 static int afs_proc_cells_open(struct inode *inode, struct file *file)
 {
-	struct seq_file *m;
-	int ret;
-
-	ret = seq_open(file, &afs_proc_cells_ops);
-	if (ret < 0)
-		return ret;
-
-	m = file->private_data;
-	m->private = PDE_DATA(inode);
-	return 0;
+	return seq_open(file, &afs_proc_cells_ops);
 }
 
 /*
@@ -430,10 +396,11 @@ int afs_proc_cell_setup(struct afs_net *net, struct afs_cell *cell)
 	if (!dir)
 		goto error_dir;
 
-	if (!proc_create_data("vlservers", 0, dir,
-			      &afs_proc_cell_vlservers_fops, cell) ||
-	    !proc_create_data("volumes", 0, dir,
-			      &afs_proc_cell_volumes_fops, cell))
+	if (!proc_create_seq_data("vlservers", 0, dir,
+			&afs_proc_cell_vlservers_ops, cell))
+		goto error_tree;
+	if (!proc_create_seq_data("volumes", 0, dir, &afs_proc_cell_volumes_ops,
+			cell))
 		goto error_tree;
 
 	_leave(" = 0");
@@ -459,36 +426,13 @@ void afs_proc_cell_remove(struct afs_net *net, struct afs_cell *cell)
 }
 
 /*
- * open "/proc/fs/afs/<cell>/volumes" which provides a summary of extant cells
- */
-static int afs_proc_cell_volumes_open(struct inode *inode, struct file *file)
-{
-	struct afs_cell *cell;
-	struct seq_file *m;
-	int ret;
-
-	cell = PDE_DATA(inode);
-	if (!cell)
-		return -ENOENT;
-
-	ret = seq_open(file, &afs_proc_cell_volumes_ops);
-	if (ret < 0)
-		return ret;
-
-	m = file->private_data;
-	m->private = cell;
-
-	return 0;
-}
-
-/*
  * set up the iterator to start reading from the cells list and return the
  * first item
  */
 static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos)
 	__acquires(cell->proc_lock)
 {
-	struct afs_cell *cell = m->private;
+	struct afs_cell *cell = PDE_DATA(file_inode(m->file));
 
 	_enter("cell=%p pos=%Ld", cell, *_pos);
 
@@ -502,7 +446,7 @@ static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos)
 static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v,
 					loff_t *_pos)
 {
-	struct afs_cell *cell = p->private;
+	struct afs_cell *cell = PDE_DATA(file_inode(p->file));
 
 	_enter("cell=%p pos=%Ld", cell, *_pos);
 	return seq_list_next(v, &cell->proc_volumes, _pos);
@@ -514,7 +458,7 @@ static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v,
 static void afs_proc_cell_volumes_stop(struct seq_file *p, void *v)
 	__releases(cell->proc_lock)
 {
-	struct afs_cell *cell = p->private;
+	struct afs_cell *cell = PDE_DATA(file_inode(p->file));
 
 	read_unlock(&cell->proc_lock);
 }
@@ -530,7 +474,7 @@ static const char afs_vol_types[3][3] = {
  */
 static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
 {
-	struct afs_cell *cell = m->private;
+	struct afs_cell *cell = PDE_DATA(file_inode(m->file));
 	struct afs_volume *vol = list_entry(v, struct afs_volume, proc_link);
 
 	/* Display header on line 1 */
@@ -547,30 +491,6 @@ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
 }
 
 /*
- * open "/proc/fs/afs/<cell>/vlservers" which provides a list of volume
- * location server
- */
-static int afs_proc_cell_vlservers_open(struct inode *inode, struct file *file)
-{
-	struct afs_cell *cell;
-	struct seq_file *m;
-	int ret;
-
-	cell = PDE_DATA(inode);
-	if (!cell)
-		return -ENOENT;
-
-	ret = seq_open(file, &afs_proc_cell_vlservers_ops);
-	if (ret<0)
-		return ret;
-
-	m = file->private_data;
-	m->private = cell;
-
-	return 0;
-}
-
-/*
  * set up the iterator to start reading from the cells list and return the
  * first item
  */
@@ -578,7 +498,7 @@ static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos)
 	__acquires(rcu)
 {
 	struct afs_addr_list *alist;
-	struct afs_cell *cell = m->private;
+	struct afs_cell *cell = PDE_DATA(file_inode(m->file));
 	loff_t pos = *_pos;
 
 	rcu_read_lock();
@@ -603,7 +523,7 @@ static void *afs_proc_cell_vlservers_next(struct seq_file *p, void *v,
 					  loff_t *_pos)
 {
 	struct afs_addr_list *alist;
-	struct afs_cell *cell = p->private;
+	struct afs_cell *cell = PDE_DATA(file_inode(p->file));
 	loff_t pos;
 
 	alist = rcu_dereference(cell->vl_addrs);
@@ -644,15 +564,6 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
 }
 
 /*
- * open "/proc/fs/afs/servers" which provides a summary of active
- * servers
- */
-static int afs_proc_servers_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &afs_proc_servers_ops);
-}
-
-/*
  * Set up the iterator to start reading from the server list and return the
  * first item.
  */
@@ -931,18 +842,3 @@ static int afs_proc_stats_show(struct seq_file *m, void *v)
 		   atomic_long_read(&net->n_store_bytes));
 	return 0;
 }
-
-/*
- * Open "/proc/fs/afs/stats" to allow reading of the stat counters.
- */
-static int afs_proc_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, afs_proc_stats_show, NULL);
-}
-
-static const struct file_operations afs_proc_stats_fops = {
-	.open		= afs_proc_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release        = single_release,
-};
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index ac0feac9d746..e065bc0768e6 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -179,7 +179,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			 */
 			if (fc->flags & AFS_FS_CURSOR_VNOVOL) {
 				fc->ac.error = -EREMOTEIO;
-				goto failed;
+				goto next_server;
 			}
 
 			write_lock(&vnode->volume->servers_lock);
@@ -201,7 +201,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			 */
 			if (vnode->volume->servers == fc->server_list) {
 				fc->ac.error = -EREMOTEIO;
-				goto failed;
+				goto next_server;
 			}
 
 			/* Try again */
@@ -350,8 +350,8 @@ use_server:
 	 * break request before we've finished decoding the reply and
 	 * installing the vnode.
 	 */
-	fc->ac.error = afs_register_server_cb_interest(
-		vnode, &fc->server_list->servers[fc->index]);
+	fc->ac.error = afs_register_server_cb_interest(vnode, fc->server_list,
+						       fc->index);
 	if (fc->ac.error < 0)
 		goto failed;
 
@@ -369,8 +369,16 @@ use_server:
 	if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) {
 		fc->ac.alist = afs_get_addrlist(alist);
 
-		if (!afs_probe_fileserver(fc))
-			goto failed;
+		if (!afs_probe_fileserver(fc)) {
+			switch (fc->ac.error) {
+			case -ENOMEM:
+			case -ERESTARTSYS:
+			case -EINTR:
+				goto failed;
+			default:
+				goto next_server;
+			}
+		}
 	}
 
 	if (!fc->ac.alist)
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 5c6263972ec9..08735948f15d 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -41,6 +41,7 @@ int afs_open_socket(struct afs_net *net)
 {
 	struct sockaddr_rxrpc srx;
 	struct socket *socket;
+	unsigned int min_level;
 	int ret;
 
 	_enter("");
@@ -60,6 +61,12 @@ int afs_open_socket(struct afs_net *net)
 	srx.transport.sin6.sin6_family	= AF_INET6;
 	srx.transport.sin6.sin6_port	= htons(AFS_CM_PORT);
 
+	min_level = RXRPC_SECURITY_ENCRYPT;
+	ret = kernel_setsockopt(socket, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL,
+				(void *)&min_level, sizeof(min_level));
+	if (ret < 0)
+		goto error_2;
+
 	ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx));
 	if (ret == -EADDRINUSE) {
 		srx.transport.sin6.sin6_port = 0;
@@ -482,8 +489,12 @@ static void afs_deliver_to_call(struct afs_call *call)
 		state = READ_ONCE(call->state);
 		switch (ret) {
 		case 0:
-			if (state == AFS_CALL_CL_PROC_REPLY)
+			if (state == AFS_CALL_CL_PROC_REPLY) {
+				if (call->cbi)
+					set_bit(AFS_SERVER_FL_MAY_HAVE_CB,
+						&call->cbi->server->flags);
 				goto call_complete;
+			}
 			ASSERTCMP(state, >, AFS_CALL_CL_PROC_REPLY);
 			goto done;
 		case -EINPROGRESS:
@@ -493,11 +504,6 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -ECONNABORTED:
 			ASSERTCMP(state, ==, AFS_CALL_COMPLETE);
 			goto done;
-		case -ENOTCONN:
-			abort_code = RX_CALL_DEAD;
-			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
-						abort_code, ret, "KNC");
-			goto local_abort;
 		case -ENOTSUPP:
 			abort_code = RXGEN_OPCODE;
 			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
diff --git a/fs/afs/security.c b/fs/afs/security.c
index cea2fff313dc..81dfedb7879f 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -147,8 +147,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
 					break;
 				}
 
-				if (cb_break != (vnode->cb_break +
-						 vnode->cb_interest->server->cb_s_break)) {
+				if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) {
 					changed = true;
 					break;
 				}
@@ -178,7 +177,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
 		}
 	}
 
-	if (cb_break != (vnode->cb_break + vnode->cb_interest->server->cb_s_break))
+	if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest))
 		goto someone_else_changed_it;
 
 	/* We need a ref on any permits list we want to copy as we'll have to
@@ -257,7 +256,7 @@ found:
 
 	spin_lock(&vnode->lock);
 	zap = rcu_access_pointer(vnode->permit_cache);
-	if (cb_break == (vnode->cb_break + vnode->cb_interest->server->cb_s_break) &&
+	if (cb_break == afs_cb_break_sum(vnode, vnode->cb_interest) &&
 	    zap == permits)
 		rcu_assign_pointer(vnode->permit_cache, replacement);
 	else
@@ -373,18 +372,14 @@ int afs_permission(struct inode *inode, int mask)
 	       mask, access, S_ISDIR(inode->i_mode) ? "dir" : "file");
 
 	if (S_ISDIR(inode->i_mode)) {
-		if (mask & MAY_EXEC) {
+		if (mask & (MAY_EXEC | MAY_READ | MAY_CHDIR)) {
 			if (!(access & AFS_ACE_LOOKUP))
 				goto permission_denied;
-		} else if (mask & MAY_READ) {
-			if (!(access & AFS_ACE_LOOKUP))
-				goto permission_denied;
-		} else if (mask & MAY_WRITE) {
+		}
+		if (mask & MAY_WRITE) {
 			if (!(access & (AFS_ACE_DELETE | /* rmdir, unlink, rename from */
 					AFS_ACE_INSERT))) /* create, mkdir, symlink, rename to */
 				goto permission_denied;
-		} else {
-			BUG();
 		}
 	} else {
 		if (!(access & AFS_ACE_LOOKUP))
diff --git a/fs/afs/server.c b/fs/afs/server.c
index e23be63998a8..3af4625e2f8c 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -67,12 +67,6 @@ struct afs_server *afs_find_server(struct afs_net *net,
 							      sizeof(struct in6_addr));
 					if (diff == 0)
 						goto found;
-					if (diff < 0) {
-						// TODO: Sort the list
-						//if (i == alist->nr_ipv4)
-						//	goto not_found;
-						break;
-					}
 				}
 			}
 		} else {
@@ -87,17 +81,10 @@ struct afs_server *afs_find_server(struct afs_net *net,
 							(u32 __force)b->sin6_addr.s6_addr32[3]);
 					if (diff == 0)
 						goto found;
-					if (diff < 0) {
-						// TODO: Sort the list
-						//if (i == 0)
-						//	goto not_found;
-						break;
-					}
 				}
 			}
 		}
 
-	//not_found:
 		server = NULL;
 	found:
 		if (server && !atomic_inc_not_zero(&server->usage))
@@ -395,14 +382,16 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server)
 	struct afs_addr_list *alist = rcu_access_pointer(server->addresses);
 	struct afs_addr_cursor ac = {
 		.alist	= alist,
-		.addr	= &alist->addrs[0],
 		.start	= alist->index,
-		.index	= alist->index,
+		.index	= 0,
+		.addr	= &alist->addrs[alist->index],
 		.error	= 0,
 	};
 	_enter("%p", server);
 
-	afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+	if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags))
+		afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+
 	call_rcu(&server->rcu, afs_server_rcu);
 	afs_dec_servers_outstanding(net);
 }
@@ -428,8 +417,15 @@ static void afs_gc_servers(struct afs_net *net, struct afs_server *gc_list)
 		}
 		write_sequnlock(&net->fs_lock);
 
-		if (deleted)
+		if (deleted) {
+			write_seqlock(&net->fs_addr_lock);
+			if (!hlist_unhashed(&server->addr4_link))
+				hlist_del_rcu(&server->addr4_link);
+			if (!hlist_unhashed(&server->addr6_link))
+				hlist_del_rcu(&server->addr6_link);
+			write_sequnlock(&net->fs_addr_lock);
 			afs_destroy_server(net, server);
+		}
 	}
 }
 
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index 0f8dc4c8f07c..8a5760aa5832 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -49,6 +49,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
 		goto error;
 
 	refcount_set(&slist->usage, 1);
+	rwlock_init(&slist->lock);
 
 	/* Make sure a records exists for each server in the list. */
 	for (i = 0; i < vldb->nr_servers; i++) {
@@ -64,9 +65,11 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
 			goto error_2;
 		}
 
-		/* Insertion-sort by server pointer */
+		/* Insertion-sort by UUID */
 		for (j = 0; j < slist->nr_servers; j++)
-			if (slist->servers[j].server >= server)
+			if (memcmp(&slist->servers[j].server->uuid,
+				   &server->uuid,
+				   sizeof(server->uuid)) >= 0)
 				break;
 		if (j < slist->nr_servers) {
 			if (slist->servers[j].server == server) {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 65081ec3c36e..9e5d7966621c 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -590,7 +590,7 @@ static void afs_i_init_once(void *_vnode)
 	memset(vnode, 0, sizeof(*vnode));
 	inode_init_once(&vnode->vfs_inode);
 	mutex_init(&vnode->io_lock);
-	mutex_init(&vnode->validate_lock);
+	init_rwsem(&vnode->validate_lock);
 	spin_lock_init(&vnode->wb_lock);
 	spin_lock_init(&vnode->lock);
 	INIT_LIST_HEAD(&vnode->wb_keys);
@@ -688,7 +688,7 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	if (afs_begin_vnode_operation(&fc, vnode, key)) {
 		fc.flags |= AFS_FS_CURSOR_NO_VSLEEP;
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(vnode);
 			afs_fs_get_volume_status(&fc, &vs);
 		}
 
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 1ed7e2fd2f35..c3b740813fc7 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -23,7 +23,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	struct afs_uvldbentry__xdr *uvldb;
 	struct afs_vldb_entry *entry;
 	bool new_only = false;
-	u32 tmp, nr_servers;
+	u32 tmp, nr_servers, vlflags;
 	int i, ret;
 
 	_enter("");
@@ -55,6 +55,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 			new_only = true;
 	}
 
+	vlflags = ntohl(uvldb->flags);
 	for (i = 0; i < nr_servers; i++) {
 		struct afs_uuid__xdr *xdr;
 		struct afs_uuid *uuid;
@@ -64,12 +65,13 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 		if (tmp & AFS_VLSF_DONTUSE ||
 		    (new_only && !(tmp & AFS_VLSF_NEWREPSITE)))
 			continue;
-		if (tmp & AFS_VLSF_RWVOL)
+		if (tmp & AFS_VLSF_RWVOL) {
 			entry->fs_mask[i] |= AFS_VOL_VTM_RW;
+			if (vlflags & AFS_VLF_BACKEXISTS)
+				entry->fs_mask[i] |= AFS_VOL_VTM_BAK;
+		}
 		if (tmp & AFS_VLSF_ROVOL)
 			entry->fs_mask[i] |= AFS_VOL_VTM_RO;
-		if (tmp & AFS_VLSF_BACKVOL)
-			entry->fs_mask[i] |= AFS_VOL_VTM_BAK;
 		if (!entry->fs_mask[i])
 			continue;
 
@@ -89,15 +91,14 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	for (i = 0; i < AFS_MAXTYPES; i++)
 		entry->vid[i] = ntohl(uvldb->volumeId[i]);
 
-	tmp = ntohl(uvldb->flags);
-	if (tmp & AFS_VLF_RWEXISTS)
+	if (vlflags & AFS_VLF_RWEXISTS)
 		__set_bit(AFS_VLDB_HAS_RW, &entry->flags);
-	if (tmp & AFS_VLF_ROEXISTS)
+	if (vlflags & AFS_VLF_ROEXISTS)
 		__set_bit(AFS_VLDB_HAS_RO, &entry->flags);
-	if (tmp & AFS_VLF_BACKEXISTS)
+	if (vlflags & AFS_VLF_BACKEXISTS)
 		__set_bit(AFS_VLDB_HAS_BAK, &entry->flags);
 
-	if (!(tmp & (AFS_VLF_RWEXISTS | AFS_VLF_ROEXISTS | AFS_VLF_BACKEXISTS))) {
+	if (!(vlflags & (AFS_VLF_RWEXISTS | AFS_VLF_ROEXISTS | AFS_VLF_BACKEXISTS))) {
 		entry->error = -ENOMEDIUM;
 		__set_bit(AFS_VLDB_QUERY_ERROR, &entry->flags);
 	}
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c164698dc304..8b39e6ebb40b 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -351,7 +351,7 @@ found_key:
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, vnode, wbk->key)) {
 		while (afs_select_fileserver(&fc)) {
-			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+			fc.cb_break = afs_calc_vnode_cb_break(vnode);
 			afs_fs_store_data(&fc, mapping, first, last, offset, to);
 		}
 
diff --git a/fs/aio.c b/fs/aio.c
index 88d7927ffbc6..b850e92ee0d5 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -5,6 +5,7 @@
  *	Implements an efficient asynchronous io interface.
  *
  *	Copyright 2000, 2001, 2002 Red Hat, Inc.  All Rights Reserved.
+ *	Copyright 2018 Christoph Hellwig.
  *
  *	See ../COPYING for licensing terms.
  */
@@ -46,6 +47,8 @@
 
 #include "internal.h"
 
+#define KIOCB_KEY		0
+
 #define AIO_RING_MAGIC			0xa10a10a1
 #define AIO_RING_COMPAT_FEATURES	1
 #define AIO_RING_INCOMPAT_FEATURES	0
@@ -156,21 +159,29 @@ struct kioctx {
 	unsigned		id;
 };
 
-/*
- * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
- * cancelled or completed (this makes a certain amount of sense because
- * successful cancellation - io_cancel() - does deliver the completion to
- * userspace).
- *
- * And since most things don't implement kiocb cancellation and we'd really like
- * kiocb completion to be lockless when possible, we use ki_cancel to
- * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
- * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
- */
-#define KIOCB_CANCELLED		((void *) (~0ULL))
+struct fsync_iocb {
+	struct work_struct	work;
+	struct file		*file;
+	bool			datasync;
+};
+
+struct poll_iocb {
+	struct file		*file;
+	__poll_t		events;
+	struct wait_queue_head	*head;
+
+	union {
+		struct wait_queue_entry	wait;
+		struct work_struct	work;
+	};
+};
 
 struct aio_kiocb {
-	struct kiocb		common;
+	union {
+		struct kiocb		rw;
+		struct fsync_iocb	fsync;
+		struct poll_iocb	poll;
+	};
 
 	struct kioctx		*ki_ctx;
 	kiocb_cancel_fn		*ki_cancel;
@@ -264,9 +275,6 @@ static int __init aio_setup(void)
 
 	kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
-
-	pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));
-
 	return 0;
 }
 __initcall(aio_setup);
@@ -552,42 +560,20 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 
 void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 {
-	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common);
+	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
 	struct kioctx *ctx = req->ki_ctx;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ctx->ctx_lock, flags);
-
-	if (!req->ki_list.next)
-		list_add(&req->ki_list, &ctx->active_reqs);
+	if (WARN_ON_ONCE(!list_empty(&req->ki_list)))
+		return;
 
+	spin_lock_irqsave(&ctx->ctx_lock, flags);
+	list_add_tail(&req->ki_list, &ctx->active_reqs);
 	req->ki_cancel = cancel;
-
 	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
 }
 EXPORT_SYMBOL(kiocb_set_cancel_fn);
 
-static int kiocb_cancel(struct aio_kiocb *kiocb)
-{
-	kiocb_cancel_fn *old, *cancel;
-
-	/*
-	 * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
-	 * actually has a cancel function, hence the cmpxchg()
-	 */
-
-	cancel = READ_ONCE(kiocb->ki_cancel);
-	do {
-		if (!cancel || cancel == KIOCB_CANCELLED)
-			return -EINVAL;
-
-		old = cancel;
-		cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
-	} while (cancel != old);
-
-	return cancel(&kiocb->common);
-}
-
 /*
  * free_ioctx() should be RCU delayed to synchronize against the RCU
  * protected lookup_ioctx() and also needs process context to call
@@ -634,9 +620,8 @@ static void free_ioctx_users(struct percpu_ref *ref)
 	while (!list_empty(&ctx->active_reqs)) {
 		req = list_first_entry(&ctx->active_reqs,
 				       struct aio_kiocb, ki_list);
-
+		req->ki_cancel(&req->rw);
 		list_del_init(&req->ki_list);
-		kiocb_cancel(req);
 	}
 
 	spin_unlock_irq(&ctx->ctx_lock);
@@ -1042,7 +1027,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 		goto out_put;
 
 	percpu_ref_get(&ctx->reqs);
-
+	INIT_LIST_HEAD(&req->ki_list);
 	req->ki_ctx = ctx;
 	return req;
 out_put:
@@ -1050,15 +1035,6 @@ out_put:
 	return NULL;
 }
 
-static void kiocb_free(struct aio_kiocb *req)
-{
-	if (req->common.ki_filp)
-		fput(req->common.ki_filp);
-	if (req->ki_eventfd != NULL)
-		eventfd_ctx_put(req->ki_eventfd);
-	kmem_cache_free(kiocb_cachep, req);
-}
-
 static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 {
 	struct aio_ring __user *ring  = (void __user *)ctx_id;
@@ -1078,8 +1054,8 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 
 	ctx = rcu_dereference(table->table[id]);
 	if (ctx && ctx->user_id == ctx_id) {
-		percpu_ref_get(&ctx->users);
-		ret = ctx;
+		if (percpu_ref_tryget_live(&ctx->users))
+			ret = ctx;
 	}
 out:
 	rcu_read_unlock();
@@ -1089,44 +1065,14 @@ out:
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
-static void aio_complete(struct kiocb *kiocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 {
-	struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, common);
 	struct kioctx	*ctx = iocb->ki_ctx;
 	struct aio_ring	*ring;
 	struct io_event	*ev_page, *event;
 	unsigned tail, pos, head;
 	unsigned long	flags;
 
-	if (kiocb->ki_flags & IOCB_WRITE) {
-		struct file *file = kiocb->ki_filp;
-
-		/*
-		 * Tell lockdep we inherited freeze protection from submission
-		 * thread.
-		 */
-		if (S_ISREG(file_inode(file)->i_mode))
-			__sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
-		file_end_write(file);
-	}
-
-	/*
-	 * Special case handling for sync iocbs:
-	 *  - events go directly into the iocb for fast handling
-	 *  - the sync task with the iocb in its stack holds the single iocb
-	 *    ref, no other paths have a way to get another ref
-	 *  - the sync task helpfully left a reference to itself in the iocb
-	 */
-	BUG_ON(is_sync_kiocb(kiocb));
-
-	if (iocb->ki_list.next) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&ctx->ctx_lock, flags);
-		list_del(&iocb->ki_list);
-		spin_unlock_irqrestore(&ctx->ctx_lock, flags);
-	}
-
 	/*
 	 * Add a completion event to the ring buffer. Must be done holding
 	 * ctx->completion_lock to prevent other code from messing with the tail
@@ -1180,11 +1126,12 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 	 * eventfd. The eventfd_signal() function is safe to be called
 	 * from IRQ context.
 	 */
-	if (iocb->ki_eventfd != NULL)
+	if (iocb->ki_eventfd) {
 		eventfd_signal(iocb->ki_eventfd, 1);
+		eventfd_ctx_put(iocb->ki_eventfd);
+	}
 
-	/* everything turned out well, dispose of the aiocb. */
-	kiocb_free(iocb);
+	kmem_cache_free(kiocb_cachep, iocb);
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -1250,14 +1197,13 @@ static long aio_read_events_ring(struct kioctx *ctx,
 		if (head == tail)
 			break;
 
-		avail = min(avail, nr - ret);
-		avail = min_t(long, avail, AIO_EVENTS_PER_PAGE -
-			    ((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE));
-
 		pos = head + AIO_EVENTS_OFFSET;
 		page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE];
 		pos %= AIO_EVENTS_PER_PAGE;
 
+		avail = min(avail, nr - ret);
+		avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos);
+
 		ev = kmap(page);
 		copy_ret = copy_to_user(event + ret, ev + pos,
 					sizeof(*ev) * avail);
@@ -1328,10 +1274,6 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
 		wait_event_interruptible_hrtimeout(ctx->wait,
 				aio_read_events(ctx, min_nr, nr, event, &ret),
 				until);
-
-	if (!ret && signal_pending(current))
-		ret = -EINTR;
-
 	return ret;
 }
 
@@ -1447,6 +1389,58 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	return -EINVAL;
 }
 
+static void aio_remove_iocb(struct aio_kiocb *iocb)
+{
+	struct kioctx *ctx = iocb->ki_ctx;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->ctx_lock, flags);
+	list_del(&iocb->ki_list);
+	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+}
+
+static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+	struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw);
+
+	if (!list_empty_careful(&iocb->ki_list))
+		aio_remove_iocb(iocb);
+
+	if (kiocb->ki_flags & IOCB_WRITE) {
+		struct inode *inode = file_inode(kiocb->ki_filp);
+
+		/*
+		 * Tell lockdep we inherited freeze protection from submission
+		 * thread.
+		 */
+		if (S_ISREG(inode->i_mode))
+			__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+		file_end_write(kiocb->ki_filp);
+	}
+
+	fput(kiocb->ki_filp);
+	aio_complete(iocb, res, res2);
+}
+
+static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
+{
+	int ret;
+
+	req->ki_filp = fget(iocb->aio_fildes);
+	if (unlikely(!req->ki_filp))
+		return -EBADF;
+	req->ki_complete = aio_complete_rw;
+	req->ki_pos = iocb->aio_offset;
+	req->ki_flags = iocb_flags(req->ki_filp);
+	if (iocb->aio_flags & IOCB_FLAG_RESFD)
+		req->ki_flags |= IOCB_EVENTFD;
+	req->ki_hint = file_write_hint(req->ki_filp);
+	ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
+	if (unlikely(ret))
+		fput(req->ki_filp);
+	return ret;
+}
+
 static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
 		bool vectored, bool compat, struct iov_iter *iter)
 {
@@ -1466,11 +1460,11 @@ static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
 	return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
 }
 
-static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
+static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
 {
 	switch (ret) {
 	case -EIOCBQUEUED:
-		return ret;
+		break;
 	case -ERESTARTSYS:
 	case -ERESTARTNOINTR:
 	case -ERESTARTNOHAND:
@@ -1482,85 +1476,270 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
 		ret = -EINTR;
 		/*FALLTHRU*/
 	default:
-		aio_complete(req, ret, 0);
-		return 0;
+		aio_complete_rw(req, ret, 0);
 	}
 }
 
 static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
 		bool compat)
 {
-	struct file *file = req->ki_filp;
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
+	struct file *file;
 	ssize_t ret;
 
+	ret = aio_prep_rw(req, iocb);
+	if (ret)
+		return ret;
+	file = req->ki_filp;
+
+	ret = -EBADF;
 	if (unlikely(!(file->f_mode & FMODE_READ)))
-		return -EBADF;
+		goto out_fput;
+	ret = -EINVAL;
 	if (unlikely(!file->f_op->read_iter))
-		return -EINVAL;
+		goto out_fput;
 
 	ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
 	if (ret)
-		return ret;
+		goto out_fput;
 	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret)
-		ret = aio_ret(req, call_read_iter(file, req, &iter));
+		aio_rw_done(req, call_read_iter(file, req, &iter));
 	kfree(iovec);
+out_fput:
+	if (unlikely(ret))
+		fput(file);
 	return ret;
 }
 
 static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 		bool compat)
 {
-	struct file *file = req->ki_filp;
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
+	struct file *file;
 	ssize_t ret;
 
+	ret = aio_prep_rw(req, iocb);
+	if (ret)
+		return ret;
+	file = req->ki_filp;
+
+	ret = -EBADF;
 	if (unlikely(!(file->f_mode & FMODE_WRITE)))
-		return -EBADF;
+		goto out_fput;
+	ret = -EINVAL;
 	if (unlikely(!file->f_op->write_iter))
-		return -EINVAL;
+		goto out_fput;
 
 	ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
 	if (ret)
-		return ret;
+		goto out_fput;
 	ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret) {
-		req->ki_flags |= IOCB_WRITE;
-		file_start_write(file);
-		ret = aio_ret(req, call_write_iter(file, req, &iter));
 		/*
-		 * We release freeze protection in aio_complete().  Fool lockdep
-		 * by telling it the lock got released so that it doesn't
-		 * complain about held lock when we return to userspace.
+		 * Open-code file_start_write here to grab freeze protection,
+		 * which will be released by another thread in
+		 * aio_complete_rw().  Fool lockdep by telling it the lock got
+		 * released so that it doesn't complain about the held lock when
+		 * we return to userspace.
 		 */
-		if (S_ISREG(file_inode(file)->i_mode))
+		if (S_ISREG(file_inode(file)->i_mode)) {
+			__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
 			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		}
+		req->ki_flags |= IOCB_WRITE;
+		aio_rw_done(req, call_write_iter(file, req, &iter));
 	}
 	kfree(iovec);
+out_fput:
+	if (unlikely(ret))
+		fput(file);
 	return ret;
 }
 
+static void aio_fsync_work(struct work_struct *work)
+{
+	struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
+	int ret;
+
+	ret = vfs_fsync(req->file, req->datasync);
+	fput(req->file);
+	aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+}
+
+static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
+{
+	if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
+			iocb->aio_rw_flags))
+		return -EINVAL;
+	req->file = fget(iocb->aio_fildes);
+	if (unlikely(!req->file))
+		return -EBADF;
+	if (unlikely(!req->file->f_op->fsync)) {
+		fput(req->file);
+		return -EINVAL;
+	}
+
+	req->datasync = datasync;
+	INIT_WORK(&req->work, aio_fsync_work);
+	schedule_work(&req->work);
+	return 0;
+}
+
+/* need to use list_del_init so we can check if item was present */
+static inline bool __aio_poll_remove(struct poll_iocb *req)
+{
+	if (list_empty(&req->wait.entry))
+		return false;
+	list_del_init(&req->wait.entry);
+	return true;
+}
+
+static inline void __aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
+{
+	fput(iocb->poll.file);
+	aio_complete(iocb, mangle_poll(mask), 0);
+}
+
+static void aio_poll_work(struct work_struct *work)
+{
+	struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, poll.work);
+
+	if (!list_empty_careful(&iocb->ki_list))
+		aio_remove_iocb(iocb);
+	__aio_poll_complete(iocb, iocb->poll.events);
+}
+
+static int aio_poll_cancel(struct kiocb *iocb)
+{
+	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
+	struct poll_iocb *req = &aiocb->poll;
+	struct wait_queue_head *head = req->head;
+	bool found = false;
+
+	spin_lock(&head->lock);
+	found = __aio_poll_remove(req);
+	spin_unlock(&head->lock);
+
+	if (found) {
+		req->events = 0;
+		INIT_WORK(&req->work, aio_poll_work);
+		schedule_work(&req->work);
+	}
+	return 0;
+}
+
+static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+		void *key)
+{
+	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+	struct file *file = req->file;
+	__poll_t mask = key_to_poll(key);
+
+	assert_spin_locked(&req->head->lock);
+
+	/* for instances that support it check for an event match first: */
+	if (mask && !(mask & req->events))
+		return 0;
+
+	mask = file->f_op->poll_mask(file, req->events);
+	if (!mask)
+		return 0;
+
+	__aio_poll_remove(req);
+
+	/*
+	 * Try completing without a context switch if we can acquire ctx_lock
+	 * without spinning.  Otherwise we need to defer to a workqueue to
+	 * avoid a deadlock due to the lock order.
+	 */
+	if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+		list_del_init(&iocb->ki_list);
+		spin_unlock(&iocb->ki_ctx->ctx_lock);
+
+		__aio_poll_complete(iocb, mask);
+	} else {
+		req->events = mask;
+		INIT_WORK(&req->work, aio_poll_work);
+		schedule_work(&req->work);
+	}
+
+	return 1;
+}
+
+static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+{
+	struct kioctx *ctx = aiocb->ki_ctx;
+	struct poll_iocb *req = &aiocb->poll;
+	__poll_t mask;
+
+	/* reject any unknown events outside the normal event mask. */
+	if ((u16)iocb->aio_buf != iocb->aio_buf)
+		return -EINVAL;
+	/* reject fields that are not defined for poll */
+	if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
+		return -EINVAL;
+
+	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
+	req->file = fget(iocb->aio_fildes);
+	if (unlikely(!req->file))
+		return -EBADF;
+	if (!file_has_poll_mask(req->file))
+		goto out_fail;
+
+	req->head = req->file->f_op->get_poll_head(req->file, req->events);
+	if (!req->head)
+		goto out_fail;
+	if (IS_ERR(req->head)) {
+		mask = EPOLLERR;
+		goto done;
+	}
+
+	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
+	aiocb->ki_cancel = aio_poll_cancel;
+
+	spin_lock_irq(&ctx->ctx_lock);
+	spin_lock(&req->head->lock);
+	mask = req->file->f_op->poll_mask(req->file, req->events);
+	if (!mask) {
+		__add_wait_queue(req->head, &req->wait);
+		list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+	}
+	spin_unlock(&req->head->lock);
+	spin_unlock_irq(&ctx->ctx_lock);
+done:
+	if (mask)
+		__aio_poll_complete(aiocb, mask);
+	return 0;
+out_fail:
+	fput(req->file);
+	return -EINVAL; /* same as no support for IOCB_CMD_POLL */
+}
+
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
-			 struct iocb *iocb, bool compat)
+			 bool compat)
 {
 	struct aio_kiocb *req;
-	struct file *file;
+	struct iocb iocb;
 	ssize_t ret;
 
+	if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
+		return -EFAULT;
+
 	/* enforce forwards compatibility on users */
-	if (unlikely(iocb->aio_reserved2)) {
+	if (unlikely(iocb.aio_reserved2)) {
 		pr_debug("EINVAL: reserve field set\n");
 		return -EINVAL;
 	}
 
 	/* prevent overflows */
 	if (unlikely(
-	    (iocb->aio_buf != (unsigned long)iocb->aio_buf) ||
-	    (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) ||
-	    ((ssize_t)iocb->aio_nbytes < 0)
+	    (iocb.aio_buf != (unsigned long)iocb.aio_buf) ||
+	    (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) ||
+	    ((ssize_t)iocb.aio_nbytes < 0)
 	   )) {
 		pr_debug("EINVAL: overflow check\n");
 		return -EINVAL;
@@ -1570,37 +1749,19 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	if (unlikely(!req))
 		return -EAGAIN;
 
-	req->common.ki_filp = file = fget(iocb->aio_fildes);
-	if (unlikely(!req->common.ki_filp)) {
-		ret = -EBADF;
-		goto out_put_req;
-	}
-	req->common.ki_pos = iocb->aio_offset;
-	req->common.ki_complete = aio_complete;
-	req->common.ki_flags = iocb_flags(req->common.ki_filp);
-	req->common.ki_hint = file_write_hint(file);
-
-	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
+	if (iocb.aio_flags & IOCB_FLAG_RESFD) {
 		/*
 		 * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
 		 * instance of the file* now. The file descriptor must be
 		 * an eventfd() fd, and will be signaled for each completed
 		 * event using the eventfd_signal() function.
 		 */
-		req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
+		req->ki_eventfd = eventfd_ctx_fdget((int) iocb.aio_resfd);
 		if (IS_ERR(req->ki_eventfd)) {
 			ret = PTR_ERR(req->ki_eventfd);
 			req->ki_eventfd = NULL;
 			goto out_put_req;
 		}
-
-		req->common.ki_flags |= IOCB_EVENTFD;
-	}
-
-	ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags);
-	if (unlikely(ret)) {
-		pr_debug("EINVAL: aio_rw_flags\n");
-		goto out_put_req;
 	}
 
 	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
@@ -1610,41 +1771,67 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	}
 
 	req->ki_user_iocb = user_iocb;
-	req->ki_user_data = iocb->aio_data;
+	req->ki_user_data = iocb.aio_data;
 
-	get_file(file);
-	switch (iocb->aio_lio_opcode) {
+	switch (iocb.aio_lio_opcode) {
 	case IOCB_CMD_PREAD:
-		ret = aio_read(&req->common, iocb, false, compat);
+		ret = aio_read(&req->rw, &iocb, false, compat);
 		break;
 	case IOCB_CMD_PWRITE:
-		ret = aio_write(&req->common, iocb, false, compat);
+		ret = aio_write(&req->rw, &iocb, false, compat);
 		break;
 	case IOCB_CMD_PREADV:
-		ret = aio_read(&req->common, iocb, true, compat);
+		ret = aio_read(&req->rw, &iocb, true, compat);
 		break;
 	case IOCB_CMD_PWRITEV:
-		ret = aio_write(&req->common, iocb, true, compat);
+		ret = aio_write(&req->rw, &iocb, true, compat);
+		break;
+	case IOCB_CMD_FSYNC:
+		ret = aio_fsync(&req->fsync, &iocb, false);
+		break;
+	case IOCB_CMD_FDSYNC:
+		ret = aio_fsync(&req->fsync, &iocb, true);
+		break;
+	case IOCB_CMD_POLL:
+		ret = aio_poll(req, &iocb);
 		break;
 	default:
-		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
+		pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
 		ret = -EINVAL;
 		break;
 	}
-	fput(file);
 
-	if (ret && ret != -EIOCBQUEUED)
+	/*
+	 * If ret is 0, we'd either done aio_complete() ourselves or have
+	 * arranged for that to be done asynchronously.  Anything non-zero
+	 * means that we need to destroy req ourselves.
+	 */
+	if (ret)
 		goto out_put_req;
 	return 0;
 out_put_req:
 	put_reqs_available(ctx, 1);
 	percpu_ref_put(&ctx->reqs);
-	kiocb_free(req);
+	if (req->ki_eventfd)
+		eventfd_ctx_put(req->ki_eventfd);
+	kmem_cache_free(kiocb_cachep, req);
 	return ret;
 }
 
-static long do_io_submit(aio_context_t ctx_id, long nr,
-			  struct iocb __user *__user *iocbpp, bool compat)
+/* sys_io_submit:
+ *	Queue the nr iocbs pointed to by iocbpp for processing.  Returns
+ *	the number of iocbs queued.  May return -EINVAL if the aio_context
+ *	specified by ctx_id is invalid, if nr is < 0, if the iocb at
+ *	*iocbpp[0] is not properly initialized, if the operation specified
+ *	is invalid for the file descriptor in the iocb.  May fail with
+ *	-EFAULT if any of the data structures point to invalid data.  May
+ *	fail with -EBADF if the file descriptor specified in the first
+ *	iocb is invalid.  May fail with -EAGAIN if insufficient resources
+ *	are available to queue any iocbs.  Will return 0 if nr is 0.  Will
+ *	fail with -ENOSYS if not implemented.
+ */
+SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
+		struct iocb __user * __user *, iocbpp)
 {
 	struct kioctx *ctx;
 	long ret = 0;
@@ -1654,39 +1841,25 @@ static long do_io_submit(aio_context_t ctx_id, long nr,
 	if (unlikely(nr < 0))
 		return -EINVAL;
 
-	if (unlikely(nr > LONG_MAX/sizeof(*iocbpp)))
-		nr = LONG_MAX/sizeof(*iocbpp);
-
-	if (unlikely(!access_ok(VERIFY_READ, iocbpp, (nr*sizeof(*iocbpp)))))
-		return -EFAULT;
-
 	ctx = lookup_ioctx(ctx_id);
 	if (unlikely(!ctx)) {
 		pr_debug("EINVAL: invalid context id\n");
 		return -EINVAL;
 	}
 
-	blk_start_plug(&plug);
+	if (nr > ctx->nr_events)
+		nr = ctx->nr_events;
 
-	/*
-	 * AKPM: should this return a partial result if some of the IOs were
-	 * successfully submitted?
-	 */
-	for (i=0; i<nr; i++) {
+	blk_start_plug(&plug);
+	for (i = 0; i < nr; i++) {
 		struct iocb __user *user_iocb;
-		struct iocb tmp;
 
-		if (unlikely(__get_user(user_iocb, iocbpp + i))) {
+		if (unlikely(get_user(user_iocb, iocbpp + i))) {
 			ret = -EFAULT;
 			break;
 		}
 
-		if (unlikely(copy_from_user(&tmp, user_iocb, sizeof(tmp)))) {
-			ret = -EFAULT;
-			break;
-		}
-
-		ret = io_submit_one(ctx, user_iocb, &tmp, compat);
+		ret = io_submit_one(ctx, user_iocb, false);
 		if (ret)
 			break;
 	}
@@ -1696,59 +1869,44 @@ static long do_io_submit(aio_context_t ctx_id, long nr,
 	return i ? i : ret;
 }
 
-/* sys_io_submit:
- *	Queue the nr iocbs pointed to by iocbpp for processing.  Returns
- *	the number of iocbs queued.  May return -EINVAL if the aio_context
- *	specified by ctx_id is invalid, if nr is < 0, if the iocb at
- *	*iocbpp[0] is not properly initialized, if the operation specified
- *	is invalid for the file descriptor in the iocb.  May fail with
- *	-EFAULT if any of the data structures point to invalid data.  May
- *	fail with -EBADF if the file descriptor specified in the first
- *	iocb is invalid.  May fail with -EAGAIN if insufficient resources
- *	are available to queue any iocbs.  Will return 0 if nr is 0.  Will
- *	fail with -ENOSYS if not implemented.
- */
-SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
-		struct iocb __user * __user *, iocbpp)
-{
-	return do_io_submit(ctx_id, nr, iocbpp, 0);
-}
-
 #ifdef CONFIG_COMPAT
-static inline long
-copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
+COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
+		       int, nr, compat_uptr_t __user *, iocbpp)
 {
-	compat_uptr_t uptr;
-	int i;
+	struct kioctx *ctx;
+	long ret = 0;
+	int i = 0;
+	struct blk_plug plug;
 
-	for (i = 0; i < nr; ++i) {
-		if (get_user(uptr, ptr32 + i))
-			return -EFAULT;
-		if (put_user(compat_ptr(uptr), ptr64 + i))
-			return -EFAULT;
+	if (unlikely(nr < 0))
+		return -EINVAL;
+
+	ctx = lookup_ioctx(ctx_id);
+	if (unlikely(!ctx)) {
+		pr_debug("EINVAL: invalid context id\n");
+		return -EINVAL;
 	}
-	return 0;
-}
 
-#define MAX_AIO_SUBMITS 	(PAGE_SIZE/sizeof(struct iocb *))
+	if (nr > ctx->nr_events)
+		nr = ctx->nr_events;
 
-COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
-		       int, nr, u32 __user *, iocb)
-{
-	struct iocb __user * __user *iocb64;
-	long ret;
+	blk_start_plug(&plug);
+	for (i = 0; i < nr; i++) {
+		compat_uptr_t user_iocb;
 
-	if (unlikely(nr < 0))
-		return -EINVAL;
+		if (unlikely(get_user(user_iocb, iocbpp + i))) {
+			ret = -EFAULT;
+			break;
+		}
 
-	if (nr > MAX_AIO_SUBMITS)
-		nr = MAX_AIO_SUBMITS;
+		ret = io_submit_one(ctx, compat_ptr(user_iocb), true);
+		if (ret)
+			break;
+	}
+	blk_finish_plug(&plug);
 
-	iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64));
-	ret = copy_iocb(nr, iocb, iocb64);
-	if (!ret)
-		ret = do_io_submit(ctx_id, nr, iocb64, 1);
-	return ret;
+	percpu_ref_put(&ctx->users);
+	return i ? i : ret;
 }
 #endif
 
@@ -1756,15 +1914,12 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
  *	Finds a given iocb for cancellation.
  */
 static struct aio_kiocb *
-lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, u32 key)
+lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb)
 {
 	struct aio_kiocb *kiocb;
 
 	assert_spin_locked(&ctx->ctx_lock);
 
-	if (key != KIOCB_KEY)
-		return NULL;
-
 	/* TODO: use a hash or array, this sucks. */
 	list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
 		if (kiocb->ki_user_iocb == iocb)
@@ -1788,25 +1943,24 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 {
 	struct kioctx *ctx;
 	struct aio_kiocb *kiocb;
+	int ret = -EINVAL;
 	u32 key;
-	int ret;
 
-	ret = get_user(key, &iocb->aio_key);
-	if (unlikely(ret))
+	if (unlikely(get_user(key, &iocb->aio_key)))
 		return -EFAULT;
+	if (unlikely(key != KIOCB_KEY))
+		return -EINVAL;
 
 	ctx = lookup_ioctx(ctx_id);
 	if (unlikely(!ctx))
 		return -EINVAL;
 
 	spin_lock_irq(&ctx->ctx_lock);
-
-	kiocb = lookup_kiocb(ctx, iocb, key);
-	if (kiocb)
-		ret = kiocb_cancel(kiocb);
-	else
-		ret = -EINVAL;
-
+	kiocb = lookup_kiocb(ctx, iocb);
+	if (kiocb) {
+		ret = kiocb->ki_cancel(&kiocb->rw);
+		list_del_init(&kiocb->ki_list);
+	}
 	spin_unlock_irq(&ctx->ctx_lock);
 
 	if (!ret) {
@@ -1861,13 +2015,60 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
 		struct timespec __user *, timeout)
 {
 	struct timespec64	ts;
+	int			ret;
+
+	if (timeout && unlikely(get_timespec64(&ts, timeout)))
+		return -EFAULT;
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	if (!ret && signal_pending(current))
+		ret = -EINTR;
+	return ret;
+}
+
+SYSCALL_DEFINE6(io_pgetevents,
+		aio_context_t, ctx_id,
+		long, min_nr,
+		long, nr,
+		struct io_event __user *, events,
+		struct timespec __user *, timeout,
+		const struct __aio_sigset __user *, usig)
+{
+	struct __aio_sigset	ksig = { NULL, };
+	sigset_t		ksigmask, sigsaved;
+	struct timespec64	ts;
+	int ret;
+
+	if (timeout && unlikely(get_timespec64(&ts, timeout)))
+		return -EFAULT;
+
+	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+		return -EFAULT;
 
-	if (timeout) {
-		if (unlikely(get_timespec64(&ts, timeout)))
+	if (ksig.sigmask) {
+		if (ksig.sigsetsize != sizeof(sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ksigmask, ksig.sigmask, sizeof(ksigmask)))
 			return -EFAULT;
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	if (signal_pending(current)) {
+		if (ksig.sigmask) {
+			current->saved_sigmask = sigsaved;
+			set_restore_sigmask();
+		}
+
+		if (!ret)
+			ret = -ERESTARTNOHAND;
+	} else {
+		if (ksig.sigmask)
+			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 	}
 
-	return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT
@@ -1878,13 +2079,64 @@ COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
 		       struct compat_timespec __user *, timeout)
 {
 	struct timespec64 t;
+	int ret;
+
+	if (timeout && compat_get_timespec64(&t, timeout))
+		return -EFAULT;
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	if (!ret && signal_pending(current))
+		ret = -EINTR;
+	return ret;
+}
+
+
+struct __compat_aio_sigset {
+	compat_sigset_t __user	*sigmask;
+	compat_size_t		sigsetsize;
+};
+
+COMPAT_SYSCALL_DEFINE6(io_pgetevents,
+		compat_aio_context_t, ctx_id,
+		compat_long_t, min_nr,
+		compat_long_t, nr,
+		struct io_event __user *, events,
+		struct compat_timespec __user *, timeout,
+		const struct __compat_aio_sigset __user *, usig)
+{
+	struct __compat_aio_sigset ksig = { NULL, };
+	sigset_t ksigmask, sigsaved;
+	struct timespec64 t;
+	int ret;
+
+	if (timeout && compat_get_timespec64(&t, timeout))
+		return -EFAULT;
+
+	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+		return -EFAULT;
 
-	if (timeout) {
-		if (compat_get_timespec64(&t, timeout))
+	if (ksig.sigmask) {
+		if (ksig.sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (get_compat_sigset(&ksigmask, ksig.sigmask))
 			return -EFAULT;
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
 
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	if (signal_pending(current)) {
+		if (ksig.sigmask) {
+			current->saved_sigmask = sigsaved;
+			set_restore_sigmask();
+		}
+		if (!ret)
+			ret = -ERESTARTNOHAND;
+	} else {
+		if (ksig.sigmask)
+			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 	}
 
-	return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	return ret;
 }
 #endif
diff --git a/fs/attr.c b/fs/attr.c
index 12ffdb6fb63c..d0b4d34878fb 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -18,6 +18,32 @@
 #include <linux/evm.h>
 #include <linux/ima.h>
 
+static bool chown_ok(const struct inode *inode, kuid_t uid)
+{
+	if (uid_eq(current_fsuid(), inode->i_uid) &&
+	    uid_eq(uid, inode->i_uid))
+		return true;
+	if (capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+		return true;
+	if (uid_eq(inode->i_uid, INVALID_UID) &&
+	    ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
+		return true;
+	return false;
+}
+
+static bool chgrp_ok(const struct inode *inode, kgid_t gid)
+{
+	if (uid_eq(current_fsuid(), inode->i_uid) &&
+	    (in_group_p(gid) || gid_eq(gid, inode->i_gid)))
+		return true;
+	if (capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+		return true;
+	if (gid_eq(inode->i_gid, INVALID_GID) &&
+	    ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
+		return true;
+	return false;
+}
+
 /**
  * setattr_prepare - check if attribute changes to a dentry are allowed
  * @dentry:	dentry to check
@@ -52,17 +78,11 @@ int setattr_prepare(struct dentry *dentry, struct iattr *attr)
 		goto kill_priv;
 
 	/* Make sure a caller can chown. */
-	if ((ia_valid & ATTR_UID) &&
-	    (!uid_eq(current_fsuid(), inode->i_uid) ||
-	     !uid_eq(attr->ia_uid, inode->i_uid)) &&
-	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+	if ((ia_valid & ATTR_UID) && !chown_ok(inode, attr->ia_uid))
 		return -EPERM;
 
 	/* Make sure caller can chgrp. */
-	if ((ia_valid & ATTR_GID) &&
-	    (!uid_eq(current_fsuid(), inode->i_uid) ||
-	    (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
-	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+	if ((ia_valid & ATTR_GID) && !chgrp_ok(inode, attr->ia_gid))
 		return -EPERM;
 
 	/* Make sure a caller can chmod. */
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 82e8f6edfb48..b12e37f27530 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -749,7 +749,7 @@ static int autofs4_dir_mkdir(struct inode *dir,
 
 	autofs4_del_active(dentry);
 
-	inode = autofs4_get_inode(dir->i_sb, S_IFDIR | 0555);
+	inode = autofs4_get_inode(dir->i_sb, S_IFDIR | mode);
 	if (!inode)
 		return -ENOMEM;
 	d_add(dentry, inode);
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index af2832aaeec5..4700b4534439 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -198,23 +198,16 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 
 	if (ret == BEFS_BT_NOT_FOUND) {
 		befs_debug(sb, "<--- %s %pd not found", __func__, dentry);
-		d_add(dentry, NULL);
-		return ERR_PTR(-ENOENT);
-
+		inode = NULL;
 	} else if (ret != BEFS_OK || offset == 0) {
 		befs_error(sb, "<--- %s Error", __func__);
-		return ERR_PTR(-ENODATA);
+		inode = ERR_PTR(-ENODATA);
+	} else {
+		inode = befs_iget(dir->i_sb, (ino_t) offset);
 	}
-
-	inode = befs_iget(dir->i_sb, (ino_t) offset);
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
-
-	d_add(dentry, inode);
-
 	befs_debug(sb, "<--- %s", __func__);
 
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 static int
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index ee832ca5f734..f32f21c3bbc7 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -21,10 +21,9 @@
 #define dprintf(x...)
 #endif
 
-static int bfs_add_entry(struct inode *dir, const unsigned char *name,
-						int namelen, int ino);
+static int bfs_add_entry(struct inode *dir, const struct qstr *child, int ino);
 static struct buffer_head *bfs_find_entry(struct inode *dir,
-				const unsigned char *name, int namelen,
+				const struct qstr *child,
 				struct bfs_dirent **res_dir);
 
 static int bfs_readdir(struct file *f, struct dir_context *ctx)
@@ -111,8 +110,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
         mark_inode_dirty(inode);
 	bfs_dump_imap("create", s);
 
-	err = bfs_add_entry(dir, dentry->d_name.name, dentry->d_name.len,
-							inode->i_ino);
+	err = bfs_add_entry(dir, &dentry->d_name, inode->i_ino);
 	if (err) {
 		inode_dec_link_count(inode);
 		mutex_unlock(&info->bfs_lock);
@@ -136,19 +134,14 @@ static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_PTR(-ENAMETOOLONG);
 
 	mutex_lock(&info->bfs_lock);
-	bh = bfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len, &de);
+	bh = bfs_find_entry(dir, &dentry->d_name, &de);
 	if (bh) {
 		unsigned long ino = (unsigned long)le16_to_cpu(de->ino);
 		brelse(bh);
 		inode = bfs_iget(dir->i_sb, ino);
-		if (IS_ERR(inode)) {
-			mutex_unlock(&info->bfs_lock);
-			return ERR_CAST(inode);
-		}
 	}
 	mutex_unlock(&info->bfs_lock);
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 static int bfs_link(struct dentry *old, struct inode *dir,
@@ -159,8 +152,7 @@ static int bfs_link(struct dentry *old, struct inode *dir,
 	int err;
 
 	mutex_lock(&info->bfs_lock);
-	err = bfs_add_entry(dir, new->d_name.name, new->d_name.len,
-							inode->i_ino);
+	err = bfs_add_entry(dir, &new->d_name, inode->i_ino);
 	if (err) {
 		mutex_unlock(&info->bfs_lock);
 		return err;
@@ -183,7 +175,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct bfs_sb_info *info = BFS_SB(inode->i_sb);
 
 	mutex_lock(&info->bfs_lock);
-	bh = bfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len, &de);
+	bh = bfs_find_entry(dir, &dentry->d_name, &de);
 	if (!bh || (le16_to_cpu(de->ino) != inode->i_ino))
 		goto out_brelse;
 
@@ -228,27 +220,21 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	info = BFS_SB(old_inode->i_sb);
 
 	mutex_lock(&info->bfs_lock);
-	old_bh = bfs_find_entry(old_dir, 
-				old_dentry->d_name.name, 
-				old_dentry->d_name.len, &old_de);
+	old_bh = bfs_find_entry(old_dir, &old_dentry->d_name, &old_de);
 
 	if (!old_bh || (le16_to_cpu(old_de->ino) != old_inode->i_ino))
 		goto end_rename;
 
 	error = -EPERM;
 	new_inode = d_inode(new_dentry);
-	new_bh = bfs_find_entry(new_dir, 
-				new_dentry->d_name.name, 
-				new_dentry->d_name.len, &new_de);
+	new_bh = bfs_find_entry(new_dir, &new_dentry->d_name, &new_de);
 
 	if (new_bh && !new_inode) {
 		brelse(new_bh);
 		new_bh = NULL;
 	}
 	if (!new_bh) {
-		error = bfs_add_entry(new_dir, 
-					new_dentry->d_name.name,
-					new_dentry->d_name.len,
+		error = bfs_add_entry(new_dir, &new_dentry->d_name,
 					old_inode->i_ino);
 		if (error)
 			goto end_rename;
@@ -278,9 +264,10 @@ const struct inode_operations bfs_dir_inops = {
 	.rename			= bfs_rename,
 };
 
-static int bfs_add_entry(struct inode *dir, const unsigned char *name,
-							int namelen, int ino)
+static int bfs_add_entry(struct inode *dir, const struct qstr *child, int ino)
 {
+	const unsigned char *name = child->name;
+	int namelen = child->len;
 	struct buffer_head *bh;
 	struct bfs_dirent *de;
 	int block, sblock, eblock, off, pos;
@@ -332,12 +319,14 @@ static inline int bfs_namecmp(int len, const unsigned char *name,
 }
 
 static struct buffer_head *bfs_find_entry(struct inode *dir,
-			const unsigned char *name, int namelen,
+			const struct qstr *child,
 			struct bfs_dirent **res_dir)
 {
 	unsigned long block = 0, offset = 0;
 	struct buffer_head *bh = NULL;
 	struct bfs_dirent *de;
+	const unsigned char *name = child->name;
+	int namelen = child->len;
 
 	*res_dir = NULL;
 	if (namelen > BFS_NAMELEN)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 41e04183e4ce..4ad6f669fe34 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -377,10 +377,10 @@ static unsigned long elf_map(struct file *filep, unsigned long addr,
 	} else
 		map_addr = vm_mmap(filep, addr, size, prot, type, off);
 
-	if ((type & MAP_FIXED_NOREPLACE) && BAD_ADDR(map_addr))
-		pr_info("%d (%s): Uhuuh, elf segment at %p requested but the memory is mapped already\n",
-				task_pid_nr(current), current->comm,
-				(void *)addr);
+	if ((type & MAP_FIXED_NOREPLACE) &&
+	    PTR_ERR((void *)map_addr) == -EEXIST)
+		pr_info("%d (%s): Uhuuh, elf segment at %px requested but the memory is mapped already\n",
+			task_pid_nr(current), current->comm, (void *)addr);
 
 	return(map_addr);
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7ec920e27065..bef6934b6189 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -272,7 +272,7 @@ struct blkdev_dio {
 	struct bio		bio;
 };
 
-static struct bio_set *blkdev_dio_pool __read_mostly;
+static struct bio_set blkdev_dio_pool;
 
 static void blkdev_bio_end_io(struct bio *bio)
 {
@@ -334,7 +334,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	    (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
-	bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, blkdev_dio_pool);
+	bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
 	bio_get(bio); /* extra ref for the completion handler */
 
 	dio = container_of(bio, struct blkdev_dio, bio);
@@ -432,10 +432,7 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 static __init int blkdev_init(void)
 {
-	blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
-	if (!blkdev_dio_pool)
-		return -ENOMEM;
-	return 0;
+	return bioset_init(&blkdev_dio_pool, 4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
 }
 module_init(blkdev_init);
 
@@ -1322,27 +1319,30 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
  * check_disk_size_change - checks for disk size change and adjusts bdev size.
  * @disk: struct gendisk to check
  * @bdev: struct bdev to adjust.
+ * @verbose: if %true log a message about a size change if there is any
  *
  * This routine checks to see if the bdev size does not match the disk size
  * and adjusts it if it differs. When shrinking the bdev size, its all caches
  * are freed.
  */
-void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
+void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
+		bool verbose)
 {
 	loff_t disk_size, bdev_size;
 
 	disk_size = (loff_t)get_capacity(disk) << 9;
 	bdev_size = i_size_read(bdev->bd_inode);
 	if (disk_size != bdev_size) {
-		printk(KERN_INFO
-		       "%s: detected capacity change from %lld to %lld\n",
-		       disk->disk_name, bdev_size, disk_size);
+		if (verbose) {
+			printk(KERN_INFO
+			       "%s: detected capacity change from %lld to %lld\n",
+			       disk->disk_name, bdev_size, disk_size);
+		}
 		i_size_write(bdev->bd_inode, disk_size);
 		if (bdev_size > disk_size)
 			flush_disk(bdev, false);
 	}
 }
-EXPORT_SYMBOL(check_disk_size_change);
 
 /**
  * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
@@ -1364,7 +1364,7 @@ int revalidate_disk(struct gendisk *disk)
 		return ret;
 
 	mutex_lock(&bdev->bd_mutex);
-	check_disk_size_change(disk, bdev);
+	check_disk_size_change(disk, bdev, ret == 0);
 	bdev->bd_invalidated = 0;
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 234bae55b85d..7e075343daa5 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -19,17 +19,17 @@
  * ordered operations list so that we make sure to flush out any
  * new data the application may have written before commit.
  */
-#define BTRFS_INODE_ORDERED_DATA_CLOSE		0
-#define BTRFS_INODE_ORPHAN_META_RESERVED	1
-#define BTRFS_INODE_DUMMY			2
-#define BTRFS_INODE_IN_DEFRAG			3
-#define BTRFS_INODE_HAS_ORPHAN_ITEM		4
-#define BTRFS_INODE_HAS_ASYNC_EXTENT		5
-#define BTRFS_INODE_NEEDS_FULL_SYNC		6
-#define BTRFS_INODE_COPY_EVERYTHING		7
-#define BTRFS_INODE_IN_DELALLOC_LIST		8
-#define BTRFS_INODE_READDIO_NEED_LOCK		9
-#define BTRFS_INODE_HAS_PROPS		        10
+enum {
+	BTRFS_INODE_ORDERED_DATA_CLOSE = 0,
+	BTRFS_INODE_DUMMY,
+	BTRFS_INODE_IN_DEFRAG,
+	BTRFS_INODE_HAS_ASYNC_EXTENT,
+	BTRFS_INODE_NEEDS_FULL_SYNC,
+	BTRFS_INODE_COPY_EVERYTHING,
+	BTRFS_INODE_IN_DELALLOC_LIST,
+	BTRFS_INODE_READDIO_NEED_LOCK,
+	BTRFS_INODE_HAS_PROPS,
+};
 
 /* in memory btrfs inode */
 struct btrfs_inode {
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1061575a7d25..d3e447b45bf7 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -990,12 +990,7 @@ static void __free_workspace(int type, struct list_head *workspace,
 		btrfs_compress_op[idx]->free_workspace(workspace);
 	atomic_dec(total_ws);
 wake:
-	/*
-	 * Make sure counter is updated before we wake up waiters.
-	 */
-	smp_mb();
-	if (waitqueue_active(ws_wait))
-		wake_up(ws_wait);
+	cond_wake_up(ws_wait);
 }
 
 static void free_workspace(int type, struct list_head *ws)
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index cc605f7b23fb..ddda9b80bf20 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -6,6 +6,8 @@
 #ifndef BTRFS_COMPRESSION_H
 #define BTRFS_COMPRESSION_H
 
+#include <linux/sizes.h>
+
 /*
  * We want to make sure that amount of RAM required to uncompress an extent is
  * reasonable, so we limit the total size in ram of a compressed extent to
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 3fd44835b386..4bc326df472e 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2330,7 +2330,7 @@ static noinline void unlock_up(struct btrfs_path *path, int level,
 			no_skips = 1;
 
 		t = path->nodes[i];
-		if (i >= lowest_unlock && i > skip_level && path->locks[i]) {
+		if (i >= lowest_unlock && i > skip_level) {
 			btrfs_tree_unlock_rw(t, path->locks[i]);
 			path->locks[i] = 0;
 			if (write_lock_level &&
@@ -2432,14 +2432,11 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 	btrfs_unlock_up_safe(p, level + 1);
 	btrfs_set_path_blocking(p);
 
-	free_extent_buffer(tmp);
 	if (p->reada != READA_NONE)
 		reada_for_search(fs_info, p, level, slot, key->objectid);
 
-	btrfs_release_path(p);
-
 	ret = -EAGAIN;
-	tmp = read_tree_block(fs_info, blocknr, 0, parent_level - 1,
+	tmp = read_tree_block(fs_info, blocknr, gen, parent_level - 1,
 			      &first_key);
 	if (!IS_ERR(tmp)) {
 		/*
@@ -2448,12 +2445,14 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 		 * and give up so that our caller doesn't loop forever
 		 * on our EAGAINs.
 		 */
-		if (!btrfs_buffer_uptodate(tmp, 0, 0))
+		if (!extent_buffer_uptodate(tmp))
 			ret = -EIO;
 		free_extent_buffer(tmp);
 	} else {
 		ret = PTR_ERR(tmp);
 	}
+
+	btrfs_release_path(p);
 	return ret;
 }
 
@@ -2599,6 +2598,78 @@ int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
 	return 0;
 }
 
+static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
+							struct btrfs_path *p,
+							int write_lock_level)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct extent_buffer *b;
+	int root_lock;
+	int level = 0;
+
+	/* We try very hard to do read locks on the root */
+	root_lock = BTRFS_READ_LOCK;
+
+	if (p->search_commit_root) {
+		/* The commit roots are read only so we always do read locks */
+		if (p->need_commit_sem)
+			down_read(&fs_info->commit_root_sem);
+		b = root->commit_root;
+		extent_buffer_get(b);
+		level = btrfs_header_level(b);
+		if (p->need_commit_sem)
+			up_read(&fs_info->commit_root_sem);
+		/*
+		 * Ensure that all callers have set skip_locking when
+		 * p->search_commit_root = 1.
+		 */
+		ASSERT(p->skip_locking == 1);
+
+		goto out;
+	}
+
+	if (p->skip_locking) {
+		b = btrfs_root_node(root);
+		level = btrfs_header_level(b);
+		goto out;
+	}
+
+	/*
+	 * If the level is set to maximum, we can skip trying to get the read
+	 * lock.
+	 */
+	if (write_lock_level < BTRFS_MAX_LEVEL) {
+		/*
+		 * We don't know the level of the root node until we actually
+		 * have it read locked
+		 */
+		b = btrfs_read_lock_root_node(root);
+		level = btrfs_header_level(b);
+		if (level > write_lock_level)
+			goto out;
+
+		/* Whoops, must trade for write lock */
+		btrfs_tree_read_unlock(b);
+		free_extent_buffer(b);
+	}
+
+	b = btrfs_lock_root_node(root);
+	root_lock = BTRFS_WRITE_LOCK;
+
+	/* The level might have changed, check again */
+	level = btrfs_header_level(b);
+
+out:
+	p->nodes[level] = b;
+	if (!p->skip_locking)
+		p->locks[level] = root_lock;
+	/*
+	 * Callers are responsible for dropping b's references.
+	 */
+	return b;
+}
+
+
 /*
  * btrfs_search_slot - look for a key in a tree and perform necessary
  * modifications to preserve tree invariants.
@@ -2635,7 +2706,6 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	int err;
 	int level;
 	int lowest_unlock = 1;
-	int root_lock;
 	/* everything at write_lock_level or lower must be write locked */
 	int write_lock_level = 0;
 	u8 lowest_level = 0;
@@ -2673,50 +2743,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 again:
 	prev_cmp = -1;
-	/*
-	 * we try very hard to do read locks on the root
-	 */
-	root_lock = BTRFS_READ_LOCK;
-	level = 0;
-	if (p->search_commit_root) {
-		/*
-		 * the commit roots are read only
-		 * so we always do read locks
-		 */
-		if (p->need_commit_sem)
-			down_read(&fs_info->commit_root_sem);
-		b = root->commit_root;
-		extent_buffer_get(b);
-		level = btrfs_header_level(b);
-		if (p->need_commit_sem)
-			up_read(&fs_info->commit_root_sem);
-		if (!p->skip_locking)
-			btrfs_tree_read_lock(b);
-	} else {
-		if (p->skip_locking) {
-			b = btrfs_root_node(root);
-			level = btrfs_header_level(b);
-		} else {
-			/* we don't know the level of the root node
-			 * until we actually have it read locked
-			 */
-			b = btrfs_read_lock_root_node(root);
-			level = btrfs_header_level(b);
-			if (level <= write_lock_level) {
-				/* whoops, must trade for write lock */
-				btrfs_tree_read_unlock(b);
-				free_extent_buffer(b);
-				b = btrfs_lock_root_node(root);
-				root_lock = BTRFS_WRITE_LOCK;
-
-				/* the level might have changed, check again */
-				level = btrfs_header_level(b);
-			}
-		}
-	}
-	p->nodes[level] = b;
-	if (!p->skip_locking)
-		p->locks[level] = root_lock;
+	b = btrfs_search_slot_get_root(root, p, write_lock_level);
 
 	while (b) {
 		level = btrfs_header_level(b);
@@ -5414,12 +5441,24 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 	down_read(&fs_info->commit_root_sem);
 	left_level = btrfs_header_level(left_root->commit_root);
 	left_root_level = left_level;
-	left_path->nodes[left_level] = left_root->commit_root;
+	left_path->nodes[left_level] =
+			btrfs_clone_extent_buffer(left_root->commit_root);
+	if (!left_path->nodes[left_level]) {
+		up_read(&fs_info->commit_root_sem);
+		ret = -ENOMEM;
+		goto out;
+	}
 	extent_buffer_get(left_path->nodes[left_level]);
 
 	right_level = btrfs_header_level(right_root->commit_root);
 	right_root_level = right_level;
-	right_path->nodes[right_level] = right_root->commit_root;
+	right_path->nodes[right_level] =
+			btrfs_clone_extent_buffer(right_root->commit_root);
+	if (!right_path->nodes[right_level]) {
+		up_read(&fs_info->commit_root_sem);
+		ret = -ENOMEM;
+		goto out;
+	}
 	extent_buffer_get(right_path->nodes[right_level]);
 	up_read(&fs_info->commit_root_sem);
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5474ef14d6e6..f4bf7874c24a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -459,6 +459,25 @@ struct btrfs_block_rsv {
 	unsigned short full;
 	unsigned short type;
 	unsigned short failfast;
+
+	/*
+	 * Qgroup equivalent for @size @reserved
+	 *
+	 * Unlike normal @size/@reserved for inode rsv, qgroup doesn't care
+	 * about things like csum size nor how many tree blocks it will need to
+	 * reserve.
+	 *
+	 * Qgroup cares more about net change of the extent usage.
+	 *
+	 * So for one newly inserted file extent, in worst case it will cause
+	 * leaf split and level increase, nodesize for each file extent is
+	 * already too much.
+	 *
+	 * In short, qgroup_size/reserved is the upper limit of possible needed
+	 * qgroup metadata reservation.
+	 */
+	u64 qgroup_rsv_size;
+	u64 qgroup_rsv_reserved;
 };
 
 /*
@@ -714,6 +733,18 @@ struct btrfs_delayed_root;
  */
 #define BTRFS_FS_EXCL_OP			16
 
+/*
+ * To info transaction_kthread we need an immediate commit so it doesn't
+ * need to wait for commit_interval
+ */
+#define BTRFS_FS_NEED_ASYNC_COMMIT		17
+
+/*
+ * Indicate that balance has been set up from the ioctl and is in the main
+ * phase. The fs_info::balance_ctl is initialized.
+ */
+#define BTRFS_FS_BALANCE_RUNNING		18
+
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
 	u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
@@ -813,7 +844,6 @@ struct btrfs_fs_info {
 	struct mutex transaction_kthread_mutex;
 	struct mutex cleaner_mutex;
 	struct mutex chunk_mutex;
-	struct mutex volume_mutex;
 
 	/*
 	 * this is taken to make sure we don't set block groups ro after
@@ -979,7 +1009,6 @@ struct btrfs_fs_info {
 	/* restriper state */
 	spinlock_t balance_lock;
 	struct mutex balance_mutex;
-	atomic_t balance_running;
 	atomic_t balance_pause_req;
 	atomic_t balance_cancel_req;
 	struct btrfs_balance_control *balance_ctl;
@@ -1194,9 +1223,6 @@ struct btrfs_root {
 	spinlock_t log_extents_lock[2];
 	struct list_head logged_list[2];
 
-	spinlock_t orphan_lock;
-	atomic_t orphan_inodes;
-	struct btrfs_block_rsv *orphan_block_rsv;
 	int orphan_cleanup_state;
 
 	spinlock_t inode_lock;
@@ -2739,13 +2765,9 @@ void btrfs_delalloc_release_space(struct inode *inode,
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
-int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
-				  struct btrfs_inode *inode);
-void btrfs_orphan_release_metadata(struct btrfs_inode *inode);
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
-				     int nitems,
-				     u64 *qgroup_reserved, bool use_global_rsv);
+				     int nitems, bool use_global_rsv);
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
 void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
@@ -2803,7 +2825,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
 void check_system_chunk(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info, const u64 type);
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
-		       struct btrfs_fs_info *info, u64 start, u64 end);
+		       u64 start, u64 end);
 
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
@@ -3017,11 +3039,9 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root);
 
 /* uuid-tree.c */
-int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 			u64 subid);
-int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 			u64 subid);
 int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
 			    int (*check_func)(struct btrfs_fs_info *, u8 *, u8,
@@ -3138,18 +3158,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     struct extent_map *em);
 
 /* inode.c */
-struct btrfs_delalloc_work {
-	struct inode *inode;
-	int delay_iput;
-	struct completion completion;
-	struct list_head list;
-	struct btrfs_work work;
-};
-
-struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
-						    int delay_iput);
-void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work);
-
 struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start,
 		u64 len, int create);
@@ -3157,6 +3165,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes);
 
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+				struct btrfs_inode *inode);
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
 int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
@@ -3166,10 +3176,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index);
-int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root,
-			struct inode *dir, u64 objectid,
-			const char *name, int name_len);
+int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry);
 int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 			int front);
 int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
@@ -3177,9 +3184,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct inode *inode, u64 new_size,
 			       u32 min_type);
 
-int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
-			       int nr);
+int btrfs_start_delalloc_inodes(struct btrfs_root *root);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr);
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 			      unsigned int extra_bits,
 			      struct extent_state **cached_state, int dedupe);
@@ -3213,10 +3219,7 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
 int btrfs_orphan_add(struct btrfs_trans_handle *trans,
 		struct btrfs_inode *inode);
 int btrfs_orphan_cleanup(struct btrfs_root *root);
-void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root);
 int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
-void btrfs_invalidate_inodes(struct btrfs_root *root);
 void btrfs_add_delayed_iput(struct inode *inode);
 void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
 int btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -3235,14 +3238,14 @@ void btrfs_test_inode_set_ops(struct inode *inode);
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int btrfs_ioctl_get_supported_features(void __user *arg);
-void btrfs_update_iflags(struct inode *inode);
+void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
 int btrfs_is_empty_uuid(u8 *uuid);
 int btrfs_defrag_file(struct inode *inode, struct file *file,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_pages);
 void btrfs_get_block_group_info(struct list_head *groups_list,
 				struct btrfs_ioctl_space_info *space);
-void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
 			       struct btrfs_ioctl_balance_args *bargs);
 ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 			   struct file *dst_file, u64 dst_loff);
@@ -3740,4 +3743,26 @@ static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
+static inline void cond_wake_up(struct wait_queue_head *wq)
+{
+	/*
+	 * This implies a full smp_mb barrier, see comments for
+	 * waitqueue_active why.
+	 */
+	if (wq_has_sleeper(wq))
+		wake_up(wq);
+}
+
+static inline void cond_wake_up_nomb(struct wait_queue_head *wq)
+{
+	/*
+	 * Special case for conditional wakeup where the barrier required for
+	 * waitqueue_active is implied by some of the preceding code. Eg. one
+	 * of such atomic operations (atomic_dec_and_return, ...), or a
+	 * unlock/lock sequence, etc.
+	 */
+	if (waitqueue_active(wq))
+		wake_up(wq);
+}
+
 #endif
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 06ec8ab6d9ba..fe6caa7e698b 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -460,13 +460,10 @@ static void finish_one_item(struct btrfs_delayed_root *delayed_root)
 {
 	int seq = atomic_inc_return(&delayed_root->items_seq);
 
-	/*
-	 * atomic_dec_return implies a barrier for waitqueue_active
-	 */
+	/* atomic_dec_return implies a barrier */
 	if ((atomic_dec_return(&delayed_root->items) <
-	    BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0) &&
-	    waitqueue_active(&delayed_root->wait))
-		wake_up(&delayed_root->wait);
+	    BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0))
+		cond_wake_up_nomb(&delayed_root->wait);
 }
 
 static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
@@ -556,6 +553,12 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
 	dst_rsv = &fs_info->delayed_block_rsv;
 
 	num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
+
+	/*
+	 * Here we migrate space rsv from transaction rsv, since have already
+	 * reserved space when starting a transaction.  So no need to reserve
+	 * qgroup space here.
+	 */
 	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 	if (!ret) {
 		trace_btrfs_space_reservation(fs_info, "delayed_item",
@@ -577,7 +580,10 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_root *root,
 		return;
 
 	rsv = &fs_info->delayed_block_rsv;
-	btrfs_qgroup_convert_reserved_meta(root, item->bytes_reserved);
+	/*
+	 * Check btrfs_delayed_item_reserve_metadata() to see why we don't need
+	 * to release/reserve qgroup space.
+	 */
 	trace_btrfs_space_reservation(fs_info, "delayed_item",
 				      item->key.objectid, item->bytes_reserved,
 				      0);
@@ -602,9 +608,6 @@ static int btrfs_delayed_inode_reserve_metadata(
 
 	num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
 
-	ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
-	if (ret < 0)
-		return ret;
 	/*
 	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
 	 * which doesn't reserve space for speed.  This is a problem since we
@@ -616,6 +619,10 @@ static int btrfs_delayed_inode_reserve_metadata(
 	 */
 	if (!src_rsv || (!trans->bytes_reserved &&
 			 src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) {
+		ret = btrfs_qgroup_reserve_meta_prealloc(root,
+				fs_info->nodesize, true);
+		if (ret < 0)
+			return ret;
 		ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes,
 					  BTRFS_RESERVE_NO_FLUSH);
 		/*
@@ -634,6 +641,8 @@ static int btrfs_delayed_inode_reserve_metadata(
 						      "delayed_inode",
 						      btrfs_ino(inode),
 						      num_bytes, 1);
+		} else {
+			btrfs_qgroup_free_meta_prealloc(root, fs_info->nodesize);
 		}
 		return ret;
 	}
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 9e98295de7ce..03dec673d12a 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -286,10 +286,10 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
 }
 
 void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info,
 			      struct btrfs_delayed_ref_root *delayed_refs,
 			      struct btrfs_delayed_ref_head *head)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_ref_node *ref;
 	struct rb_node *node;
 	u64 seq = 0;
@@ -323,9 +323,7 @@ again:
 	}
 }
 
-int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
-			    struct btrfs_delayed_ref_root *delayed_refs,
-			    u64 seq)
+int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
 {
 	struct seq_list *elem;
 	int ret = 0;
@@ -336,10 +334,9 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
 					struct seq_list, list);
 		if (seq >= elem->seq) {
 			btrfs_debug(fs_info,
-				"holding back delayed_ref %#x.%x, lowest is %#x.%x (%p)",
+				"holding back delayed_ref %#x.%x, lowest is %#x.%x",
 				(u32)(seq >> 32), (u32)seq,
-				(u32)(elem->seq >> 32), (u32)elem->seq,
-				delayed_refs);
+				(u32)(elem->seq >> 32), (u32)elem->seq);
 			ret = 1;
 		}
 	}
@@ -529,31 +526,20 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
 	spin_unlock(&existing->lock);
 }
 
-/*
- * helper function to actually insert a head node into the rbtree.
- * this does all the dirty work in terms of maintaining the correct
- * overall modification count.
- */
-static noinline struct btrfs_delayed_ref_head *
-add_delayed_ref_head(struct btrfs_fs_info *fs_info,
-		     struct btrfs_trans_handle *trans,
-		     struct btrfs_delayed_ref_head *head_ref,
-		     struct btrfs_qgroup_extent_record *qrecord,
-		     u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved,
-		     int action, int is_data, int *qrecord_inserted_ret,
-		     int *old_ref_mod, int *new_ref_mod)
+static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
+				  struct btrfs_qgroup_extent_record *qrecord,
+				  u64 bytenr, u64 num_bytes, u64 ref_root,
+				  u64 reserved, int action, bool is_data,
+				  bool is_system)
 {
-	struct btrfs_delayed_ref_head *existing;
-	struct btrfs_delayed_ref_root *delayed_refs;
 	int count_mod = 1;
 	int must_insert_reserved = 0;
-	int qrecord_inserted = 0;
 
 	/* If reserved is provided, it must be a data extent. */
 	BUG_ON(!is_data && reserved);
 
 	/*
-	 * the head node stores the sum of all the mods, so dropping a ref
+	 * The head node stores the sum of all the mods, so dropping a ref
 	 * should drop the sum in the head node by one.
 	 */
 	if (action == BTRFS_UPDATE_DELAYED_HEAD)
@@ -562,12 +548,11 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		count_mod = -1;
 
 	/*
-	 * BTRFS_ADD_DELAYED_EXTENT means that we need to update
-	 * the reserved accounting when the extent is finally added, or
-	 * if a later modification deletes the delayed ref without ever
-	 * inserting the extent into the extent allocation tree.
-	 * ref->must_insert_reserved is the flag used to record
-	 * that accounting mods are required.
+	 * BTRFS_ADD_DELAYED_EXTENT means that we need to update the reserved
+	 * accounting when the extent is finally added, or if a later
+	 * modification deletes the delayed ref without ever inserting the
+	 * extent into the extent allocation tree.  ref->must_insert_reserved
+	 * is the flag used to record that accounting mods are required.
 	 *
 	 * Once we record must_insert_reserved, switch the action to
 	 * BTRFS_ADD_DELAYED_REF because other special casing is not required.
@@ -577,14 +562,13 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	else
 		must_insert_reserved = 0;
 
-	delayed_refs = &trans->transaction->delayed_refs;
-
 	refcount_set(&head_ref->refs, 1);
 	head_ref->bytenr = bytenr;
 	head_ref->num_bytes = num_bytes;
 	head_ref->ref_mod = count_mod;
 	head_ref->must_insert_reserved = must_insert_reserved;
 	head_ref->is_data = is_data;
+	head_ref->is_system = is_system;
 	head_ref->ref_tree = RB_ROOT;
 	INIT_LIST_HEAD(&head_ref->ref_add_list);
 	RB_CLEAR_NODE(&head_ref->href_node);
@@ -595,7 +579,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	spin_lock_init(&head_ref->lock);
 	mutex_init(&head_ref->mutex);
 
-	/* Record qgroup extent info if provided */
 	if (qrecord) {
 		if (ref_root && reserved) {
 			head_ref->qgroup_ref_root = ref_root;
@@ -605,20 +588,44 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		qrecord->bytenr = bytenr;
 		qrecord->num_bytes = num_bytes;
 		qrecord->old_roots = NULL;
+	}
+}
 
-		if(btrfs_qgroup_trace_extent_nolock(fs_info,
+/*
+ * helper function to actually insert a head node into the rbtree.
+ * this does all the dirty work in terms of maintaining the correct
+ * overall modification count.
+ */
+static noinline struct btrfs_delayed_ref_head *
+add_delayed_ref_head(struct btrfs_trans_handle *trans,
+		     struct btrfs_delayed_ref_head *head_ref,
+		     struct btrfs_qgroup_extent_record *qrecord,
+		     int action, int *qrecord_inserted_ret,
+		     int *old_ref_mod, int *new_ref_mod)
+{
+	struct btrfs_delayed_ref_head *existing;
+	struct btrfs_delayed_ref_root *delayed_refs;
+	int qrecord_inserted = 0;
+
+	delayed_refs = &trans->transaction->delayed_refs;
+
+	/* Record qgroup extent info if provided */
+	if (qrecord) {
+		if (btrfs_qgroup_trace_extent_nolock(trans->fs_info,
 					delayed_refs, qrecord))
 			kfree(qrecord);
 		else
 			qrecord_inserted = 1;
 	}
 
-	trace_add_delayed_ref_head(fs_info, head_ref, action);
+	trace_add_delayed_ref_head(trans->fs_info, head_ref, action);
 
 	existing = htree_insert(&delayed_refs->href_root,
 				&head_ref->href_node);
 	if (existing) {
-		WARN_ON(ref_root && reserved && existing->qgroup_ref_root
+		WARN_ON(qrecord && head_ref->qgroup_ref_root
+			&& head_ref->qgroup_reserved
+			&& existing->qgroup_ref_root
 			&& existing->qgroup_reserved);
 		update_existing_head_ref(delayed_refs, existing, head_ref,
 					 old_ref_mod);
@@ -631,8 +638,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	} else {
 		if (old_ref_mod)
 			*old_ref_mod = 0;
-		if (is_data && count_mod < 0)
-			delayed_refs->pending_csums += num_bytes;
+		if (head_ref->is_data && head_ref->ref_mod < 0)
+			delayed_refs->pending_csums += head_ref->num_bytes;
 		delayed_refs->num_heads++;
 		delayed_refs->num_heads_ready++;
 		atomic_inc(&delayed_refs->num_entries);
@@ -642,90 +649,48 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		*qrecord_inserted_ret = qrecord_inserted;
 	if (new_ref_mod)
 		*new_ref_mod = head_ref->total_ref_mod;
-	return head_ref;
-}
 
-/*
- * helper to insert a delayed tree ref into the rbtree.
- */
-static noinline void
-add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
-		     struct btrfs_trans_handle *trans,
-		     struct btrfs_delayed_ref_head *head_ref,
-		     struct btrfs_delayed_ref_node *ref, u64 bytenr,
-		     u64 num_bytes, u64 parent, u64 ref_root, int level,
-		     int action)
-{
-	struct btrfs_delayed_tree_ref *full_ref;
-	struct btrfs_delayed_ref_root *delayed_refs;
-	u64 seq = 0;
-	int ret;
-
-	if (action == BTRFS_ADD_DELAYED_EXTENT)
-		action = BTRFS_ADD_DELAYED_REF;
-
-	if (is_fstree(ref_root))
-		seq = atomic64_read(&fs_info->tree_mod_seq);
-	delayed_refs = &trans->transaction->delayed_refs;
-
-	/* first set the basic ref node struct up */
-	refcount_set(&ref->refs, 1);
-	ref->bytenr = bytenr;
-	ref->num_bytes = num_bytes;
-	ref->ref_mod = 1;
-	ref->action = action;
-	ref->is_head = 0;
-	ref->in_tree = 1;
-	ref->seq = seq;
-	RB_CLEAR_NODE(&ref->ref_node);
-	INIT_LIST_HEAD(&ref->add_list);
-
-	full_ref = btrfs_delayed_node_to_tree_ref(ref);
-	full_ref->parent = parent;
-	full_ref->root = ref_root;
-	if (parent)
-		ref->type = BTRFS_SHARED_BLOCK_REF_KEY;
-	else
-		ref->type = BTRFS_TREE_BLOCK_REF_KEY;
-	full_ref->level = level;
-
-	trace_add_delayed_tree_ref(fs_info, ref, full_ref, action);
-
-	ret = insert_delayed_ref(trans, delayed_refs, head_ref, ref);
-
-	/*
-	 * XXX: memory should be freed at the same level allocated.
-	 * But bad practice is anywhere... Follow it now. Need cleanup.
-	 */
-	if (ret > 0)
-		kmem_cache_free(btrfs_delayed_tree_ref_cachep, full_ref);
+	return head_ref;
 }
 
 /*
- * helper to insert a delayed data ref into the rbtree.
+ * init_delayed_ref_common - Initialize the structure which represents a
+ *			     modification to a an extent.
+ *
+ * @fs_info:    Internal to the mounted filesystem mount structure.
+ *
+ * @ref:	The structure which is going to be initialized.
+ *
+ * @bytenr:	The logical address of the extent for which a modification is
+ *		going to be recorded.
+ *
+ * @num_bytes:  Size of the extent whose modification is being recorded.
+ *
+ * @ref_root:	The id of the root where this modification has originated, this
+ *		can be either one of the well-known metadata trees or the
+ *		subvolume id which references this extent.
+ *
+ * @action:	Can be one of BTRFS_ADD_DELAYED_REF/BTRFS_DROP_DELAYED_REF or
+ *		BTRFS_ADD_DELAYED_EXTENT
+ *
+ * @ref_type:	Holds the type of the extent which is being recorded, can be
+ *		one of BTRFS_SHARED_BLOCK_REF_KEY/BTRFS_TREE_BLOCK_REF_KEY
+ *		when recording a metadata extent or BTRFS_SHARED_DATA_REF_KEY/
+ *		BTRFS_EXTENT_DATA_REF_KEY when recording data extent
  */
-static noinline void
-add_delayed_data_ref(struct btrfs_fs_info *fs_info,
-		     struct btrfs_trans_handle *trans,
-		     struct btrfs_delayed_ref_head *head_ref,
-		     struct btrfs_delayed_ref_node *ref, u64 bytenr,
-		     u64 num_bytes, u64 parent, u64 ref_root, u64 owner,
-		     u64 offset, int action)
+static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
+				    struct btrfs_delayed_ref_node *ref,
+				    u64 bytenr, u64 num_bytes, u64 ref_root,
+				    int action, u8 ref_type)
 {
-	struct btrfs_delayed_data_ref *full_ref;
-	struct btrfs_delayed_ref_root *delayed_refs;
 	u64 seq = 0;
-	int ret;
 
 	if (action == BTRFS_ADD_DELAYED_EXTENT)
 		action = BTRFS_ADD_DELAYED_REF;
 
-	delayed_refs = &trans->transaction->delayed_refs;
-
 	if (is_fstree(ref_root))
 		seq = atomic64_read(&fs_info->tree_mod_seq);
 
-	/* first set the basic ref node struct up */
 	refcount_set(&ref->refs, 1);
 	ref->bytenr = bytenr;
 	ref->num_bytes = num_bytes;
@@ -734,25 +699,9 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 	ref->seq = seq;
+	ref->type = ref_type;
 	RB_CLEAR_NODE(&ref->ref_node);
 	INIT_LIST_HEAD(&ref->add_list);
-
-	full_ref = btrfs_delayed_node_to_data_ref(ref);
-	full_ref->parent = parent;
-	full_ref->root = ref_root;
-	if (parent)
-		ref->type = BTRFS_SHARED_DATA_REF_KEY;
-	else
-		ref->type = BTRFS_EXTENT_DATA_REF_KEY;
-
-	full_ref->objectid = owner;
-	full_ref->offset = offset;
-
-	trace_add_delayed_data_ref(fs_info, ref, full_ref, action);
-
-	ret = insert_delayed_ref(trans, delayed_refs, head_ref, ref);
-	if (ret > 0)
-		kmem_cache_free(btrfs_delayed_data_ref_cachep, full_ref);
 }
 
 /*
@@ -772,12 +721,25 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
 	int qrecord_inserted;
+	bool is_system = (ref_root == BTRFS_CHUNK_TREE_OBJECTID);
+	int ret;
+	u8 ref_type;
 
 	BUG_ON(extent_op && extent_op->is_data);
 	ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
 	if (!ref)
 		return -ENOMEM;
 
+	if (parent)
+		ref_type = BTRFS_SHARED_BLOCK_REF_KEY;
+	else
+		ref_type = BTRFS_TREE_BLOCK_REF_KEY;
+	init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
+				ref_root, action, ref_type);
+	ref->root = ref_root;
+	ref->parent = parent;
+	ref->level = level;
+
 	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
 	if (!head_ref)
 		goto free_ref;
@@ -789,6 +751,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 			goto free_head_ref;
 	}
 
+	init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
+			      ref_root, 0, action, false, is_system);
 	head_ref->extent_op = extent_op;
 
 	delayed_refs = &trans->transaction->delayed_refs;
@@ -798,15 +762,19 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	 * insert both the head node and the new ref without dropping
 	 * the spin lock
 	 */
-	head_ref = add_delayed_ref_head(fs_info, trans, head_ref, record,
-					bytenr, num_bytes, 0, 0, action, 0,
-					&qrecord_inserted, old_ref_mod,
-					new_ref_mod);
+	head_ref = add_delayed_ref_head(trans, head_ref, record,
+					action, &qrecord_inserted,
+					old_ref_mod, new_ref_mod);
 
-	add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
-			     num_bytes, parent, ref_root, level, action);
+	ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);
 
+	trace_add_delayed_tree_ref(fs_info, &ref->node, ref,
+				   action == BTRFS_ADD_DELAYED_EXTENT ?
+				   BTRFS_ADD_DELAYED_REF : action);
+	if (ret > 0)
+		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+
 	if (qrecord_inserted)
 		btrfs_qgroup_trace_extent_post(fs_info, record);
 
@@ -835,11 +803,25 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
 	int qrecord_inserted;
+	int ret;
+	u8 ref_type;
 
 	ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
 	if (!ref)
 		return -ENOMEM;
 
+	if (parent)
+	        ref_type = BTRFS_SHARED_DATA_REF_KEY;
+	else
+	        ref_type = BTRFS_EXTENT_DATA_REF_KEY;
+	init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
+				ref_root, action, ref_type);
+	ref->root = ref_root;
+	ref->parent = parent;
+	ref->objectid = owner;
+	ref->offset = offset;
+
+
 	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
 	if (!head_ref) {
 		kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
@@ -857,6 +839,8 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 		}
 	}
 
+	init_delayed_ref_head(head_ref, record, bytenr, num_bytes, ref_root,
+			      reserved, action, true, false);
 	head_ref->extent_op = NULL;
 
 	delayed_refs = &trans->transaction->delayed_refs;
@@ -866,16 +850,20 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	 * insert both the head node and the new ref without dropping
 	 * the spin lock
 	 */
-	head_ref = add_delayed_ref_head(fs_info, trans, head_ref, record,
-					bytenr, num_bytes, ref_root, reserved,
-					action, 1, &qrecord_inserted,
+	head_ref = add_delayed_ref_head(trans, head_ref, record,
+					action, &qrecord_inserted,
 					old_ref_mod, new_ref_mod);
 
-	add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
-				   num_bytes, parent, ref_root, owner, offset,
-				   action);
+	ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);
 
+	trace_add_delayed_data_ref(trans->fs_info, &ref->node, ref,
+				   action == BTRFS_ADD_DELAYED_EXTENT ?
+				   BTRFS_ADD_DELAYED_REF : action);
+	if (ret > 0)
+		kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
+
+
 	if (qrecord_inserted)
 		return btrfs_qgroup_trace_extent_post(fs_info, record);
 	return 0;
@@ -893,14 +881,16 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
 	if (!head_ref)
 		return -ENOMEM;
 
+	init_delayed_ref_head(head_ref, NULL, bytenr, num_bytes, 0, 0,
+			      BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data,
+			      false);
 	head_ref->extent_op = extent_op;
 
 	delayed_refs = &trans->transaction->delayed_refs;
 	spin_lock(&delayed_refs->lock);
 
-	add_delayed_ref_head(fs_info, trans, head_ref, NULL, bytenr,
-			     num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD,
-			     extent_op->is_data, NULL, NULL, NULL);
+	add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD,
+			     NULL, NULL, NULL);
 
 	spin_unlock(&delayed_refs->lock);
 	return 0;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 741869dbc316..ea1aecb6a50d 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -127,6 +127,7 @@ struct btrfs_delayed_ref_head {
 	 */
 	unsigned int must_insert_reserved:1;
 	unsigned int is_data:1;
+	unsigned int is_system:1;
 	unsigned int processing:1;
 };
 
@@ -250,7 +251,6 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
 				u64 bytenr, u64 num_bytes,
 				struct btrfs_delayed_extent_op *extent_op);
 void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info,
 			      struct btrfs_delayed_ref_root *delayed_refs,
 			      struct btrfs_delayed_ref_head *head);
 
@@ -268,9 +268,7 @@ static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head)
 struct btrfs_delayed_ref_head *
 btrfs_select_ref_head(struct btrfs_trans_handle *trans);
 
-int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
-			    struct btrfs_delayed_ref_root *delayed_refs,
-			    u64 seq);
+int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq);
 
 /*
  * helper functions to cast a node into its container
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f82be266ba4b..e2ba0419297a 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -33,8 +33,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 						struct btrfs_device *srcdev,
 						struct btrfs_device *tgtdev);
 static int btrfs_dev_replace_kthread(void *data);
-static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info);
-
 
 int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
 {
@@ -179,6 +177,105 @@ out:
 }
 
 /*
+ * Initialize a new device for device replace target from a given source dev
+ * and path.
+ *
+ * Return 0 and new device in @device_out, otherwise return < 0
+ */
+static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
+				  const char *device_path,
+				  struct btrfs_device *srcdev,
+				  struct btrfs_device **device_out)
+{
+	struct btrfs_device *device;
+	struct block_device *bdev;
+	struct list_head *devices;
+	struct rcu_string *name;
+	u64 devid = BTRFS_DEV_REPLACE_DEVID;
+	int ret = 0;
+
+	*device_out = NULL;
+	if (fs_info->fs_devices->seeding) {
+		btrfs_err(fs_info, "the filesystem is a seed filesystem!");
+		return -EINVAL;
+	}
+
+	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
+				  fs_info->bdev_holder);
+	if (IS_ERR(bdev)) {
+		btrfs_err(fs_info, "target device %s is invalid!", device_path);
+		return PTR_ERR(bdev);
+	}
+
+	filemap_write_and_wait(bdev->bd_inode->i_mapping);
+
+	devices = &fs_info->fs_devices->devices;
+	list_for_each_entry(device, devices, dev_list) {
+		if (device->bdev == bdev) {
+			btrfs_err(fs_info,
+				  "target device is in the filesystem!");
+			ret = -EEXIST;
+			goto error;
+		}
+	}
+
+
+	if (i_size_read(bdev->bd_inode) <
+	    btrfs_device_get_total_bytes(srcdev)) {
+		btrfs_err(fs_info,
+			  "target device is smaller than source device!");
+		ret = -EINVAL;
+		goto error;
+	}
+
+
+	device = btrfs_alloc_device(NULL, &devid, NULL);
+	if (IS_ERR(device)) {
+		ret = PTR_ERR(device);
+		goto error;
+	}
+
+	name = rcu_string_strdup(device_path, GFP_KERNEL);
+	if (!name) {
+		btrfs_free_device(device);
+		ret = -ENOMEM;
+		goto error;
+	}
+	rcu_assign_pointer(device->name, name);
+
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
+	device->generation = 0;
+	device->io_width = fs_info->sectorsize;
+	device->io_align = fs_info->sectorsize;
+	device->sector_size = fs_info->sectorsize;
+	device->total_bytes = btrfs_device_get_total_bytes(srcdev);
+	device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev);
+	device->bytes_used = btrfs_device_get_bytes_used(srcdev);
+	device->commit_total_bytes = srcdev->commit_total_bytes;
+	device->commit_bytes_used = device->bytes_used;
+	device->fs_info = fs_info;
+	device->bdev = bdev;
+	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
+	set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
+	device->mode = FMODE_EXCL;
+	device->dev_stats_valid = 1;
+	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
+	device->fs_devices = fs_info->fs_devices;
+	list_add(&device->dev_list, &fs_info->fs_devices->devices);
+	fs_info->fs_devices->num_devices++;
+	fs_info->fs_devices->open_devices++;
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+
+	*device_out = device;
+	return 0;
+
+error:
+	blkdev_put(bdev, FMODE_EXCL);
+	return ret;
+}
+
+/*
  * called from commit_transaction. Writes changed device replace state to
  * disk.
  */
@@ -317,18 +414,13 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	struct btrfs_device *tgt_device = NULL;
 	struct btrfs_device *src_device = NULL;
 
-	/* the disk copy procedure reuses the scrub code */
-	mutex_lock(&fs_info->volume_mutex);
 	ret = btrfs_find_device_by_devspec(fs_info, srcdevid,
 					    srcdev_name, &src_device);
-	if (ret) {
-		mutex_unlock(&fs_info->volume_mutex);
+	if (ret)
 		return ret;
-	}
 
 	ret = btrfs_init_dev_replace_tgtdev(fs_info, tgtdev_name,
 					    src_device, &tgt_device);
-	mutex_unlock(&fs_info->volume_mutex);
 	if (ret)
 		return ret;
 
@@ -360,7 +452,6 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	dev_replace->cont_reading_from_srcdev_mode = read_src;
 	WARN_ON(!src_device);
 	dev_replace->srcdev = src_device;
-	WARN_ON(!tgt_device);
 	dev_replace->tgtdev = tgt_device;
 
 	btrfs_info_in_rcu(fs_info,
@@ -503,7 +594,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 * flush all outstanding I/O and inode extent mappings before the
 	 * copy operation is declared as being finished
 	 */
-	ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
+	ret = btrfs_start_delalloc_roots(fs_info, -1);
 	if (ret) {
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
@@ -518,7 +609,6 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	ret = btrfs_commit_transaction(trans);
 	WARN_ON(ret);
 
-	mutex_lock(&uuid_mutex);
 	/* keep away write_all_supers() during the finishing procedure */
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	mutex_lock(&fs_info->chunk_mutex);
@@ -545,7 +635,6 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		btrfs_dev_replace_write_unlock(dev_replace);
 		mutex_unlock(&fs_info->chunk_mutex);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		mutex_unlock(&uuid_mutex);
 		btrfs_rm_dev_replace_blocked(fs_info);
 		if (tgt_device)
 			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
@@ -596,7 +685,6 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 */
 	mutex_unlock(&fs_info->chunk_mutex);
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-	mutex_unlock(&uuid_mutex);
 
 	/* replace the sysfs entry */
 	btrfs_sysfs_rm_device_link(fs_info->fs_devices, src_device);
@@ -800,7 +888,17 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
 	}
 	btrfs_dev_replace_write_unlock(dev_replace);
 
-	WARN_ON(test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
+	/*
+	 * This could collide with a paused balance, but the exclusive op logic
+	 * should never allow both to start and pause. We don't want to allow
+	 * dev-replace to start anyway.
+	 */
+	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
+		btrfs_info(fs_info,
+		"cannot resume dev-replace, other exclusive operation running");
+		return 0;
+	}
+
 	task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl");
 	return PTR_ERR_OR_ZERO(task);
 }
@@ -810,6 +908,7 @@ static int btrfs_dev_replace_kthread(void *data)
 	struct btrfs_fs_info *fs_info = data;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	u64 progress;
+	int ret;
 
 	progress = btrfs_dev_replace_progress(fs_info);
 	progress = div_u64(progress, 10);
@@ -820,23 +919,14 @@ static int btrfs_dev_replace_kthread(void *data)
 		btrfs_dev_name(dev_replace->tgtdev),
 		(unsigned int)progress);
 
-	btrfs_dev_replace_continue_on_mount(fs_info);
-	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
-
-	return 0;
-}
-
-static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
-	int ret;
-
 	ret = btrfs_scrub_dev(fs_info, dev_replace->srcdev->devid,
 			      dev_replace->committed_cursor_left,
 			      btrfs_device_get_total_bytes(dev_replace->srcdev),
 			      &dev_replace->scrub_progress, 0, 1);
 	ret = btrfs_dev_replace_finishing(fs_info, ret);
 	WARN_ON(ret);
+
+	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 	return 0;
 }
 
@@ -916,9 +1006,9 @@ void btrfs_dev_replace_clear_lock_blocking(
 	ASSERT(atomic_read(&dev_replace->read_locks) > 0);
 	ASSERT(atomic_read(&dev_replace->blocking_readers) > 0);
 	read_lock(&dev_replace->lock);
-	if (atomic_dec_and_test(&dev_replace->blocking_readers) &&
-	    waitqueue_active(&dev_replace->read_lock_wq))
-		wake_up(&dev_replace->read_lock_wq);
+	/* Barrier implied by atomic_dec_and_test */
+	if (atomic_dec_and_test(&dev_replace->blocking_readers))
+		cond_wake_up_nomb(&dev_replace->read_lock_wq);
 }
 
 void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
@@ -929,9 +1019,7 @@ void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
 void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount)
 {
 	percpu_counter_sub(&fs_info->bio_counter, amount);
-
-	if (waitqueue_active(&fs_info->replace_wait))
-		wake_up(&fs_info->replace_wait);
+	cond_wake_up_nomb(&fs_info->replace_wait);
 }
 
 void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4ac8b1d21baf..205092dc9390 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -55,7 +55,6 @@
 static const struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
-static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info);
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_fs_info *fs_info);
@@ -416,7 +415,7 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
 
 static int verify_level_key(struct btrfs_fs_info *fs_info,
 			    struct extent_buffer *eb, int level,
-			    struct btrfs_key *first_key)
+			    struct btrfs_key *first_key, u64 parent_transid)
 {
 	int found_level;
 	struct btrfs_key found_key;
@@ -454,10 +453,11 @@ static int verify_level_key(struct btrfs_fs_info *fs_info,
 	if (ret) {
 		WARN_ON(1);
 		btrfs_err(fs_info,
-"tree first key mismatch detected, bytenr=%llu key expected=(%llu, %u, %llu) has=(%llu, %u, %llu)",
-			  eb->start, first_key->objectid, first_key->type,
-			  first_key->offset, found_key.objectid,
-			  found_key.type, found_key.offset);
+"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)",
+			  eb->start, parent_transid, first_key->objectid,
+			  first_key->type, first_key->offset,
+			  found_key.objectid, found_key.type,
+			  found_key.offset);
 	}
 #endif
 	return ret;
@@ -493,7 +493,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
 						   parent_transid, 0))
 				ret = -EIO;
 			else if (verify_level_key(fs_info, eb, level,
-						  first_key))
+						  first_key, parent_transid))
 				ret = -EUCLEAN;
 			else
 				break;
@@ -1185,7 +1185,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->inode_tree = RB_ROOT;
 	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
 	root->block_rsv = NULL;
-	root->orphan_block_rsv = NULL;
 
 	INIT_LIST_HEAD(&root->dirty_list);
 	INIT_LIST_HEAD(&root->root_list);
@@ -1195,7 +1194,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	INIT_LIST_HEAD(&root->ordered_root);
 	INIT_LIST_HEAD(&root->logged_list[0]);
 	INIT_LIST_HEAD(&root->logged_list[1]);
-	spin_lock_init(&root->orphan_lock);
 	spin_lock_init(&root->inode_lock);
 	spin_lock_init(&root->delalloc_lock);
 	spin_lock_init(&root->ordered_extent_lock);
@@ -1216,7 +1214,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	atomic_set(&root->log_commit[1], 0);
 	atomic_set(&root->log_writers, 0);
 	atomic_set(&root->log_batch, 0);
-	atomic_set(&root->orphan_inodes, 0);
 	refcount_set(&root->refs, 1);
 	atomic_set(&root->will_be_snapshotted, 0);
 	root->log_transid = 0;
@@ -1824,6 +1821,7 @@ static int transaction_kthread(void *arg)
 
 		now = get_seconds();
 		if (cur->state < TRANS_STATE_BLOCKED &&
+		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
 		     now - cur->start_time < fs_info->commit_interval)) {
 			spin_unlock(&fs_info->trans_lock);
@@ -2163,7 +2161,6 @@ static void btrfs_init_balance(struct btrfs_fs_info *fs_info)
 {
 	spin_lock_init(&fs_info->balance_lock);
 	mutex_init(&fs_info->balance_mutex);
-	atomic_set(&fs_info->balance_running, 0);
 	atomic_set(&fs_info->balance_pause_req, 0);
 	atomic_set(&fs_info->balance_cancel_req, 0);
 	fs_info->balance_ctl = NULL;
@@ -2441,6 +2438,211 @@ out:
 	return ret;
 }
 
+/*
+ * Real super block validation
+ * NOTE: super csum type and incompat features will not be checked here.
+ *
+ * @sb:		super block to check
+ * @mirror_num:	the super block number to check its bytenr:
+ * 		0	the primary (1st) sb
+ * 		1, 2	2nd and 3rd backup copy
+ * 	       -1	skip bytenr check
+ */
+static int validate_super(struct btrfs_fs_info *fs_info,
+			    struct btrfs_super_block *sb, int mirror_num)
+{
+	u64 nodesize = btrfs_super_nodesize(sb);
+	u64 sectorsize = btrfs_super_sectorsize(sb);
+	int ret = 0;
+
+	if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
+		btrfs_err(fs_info, "no valid FS found");
+		ret = -EINVAL;
+	}
+	if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) {
+		btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu",
+				btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
+		ret = -EINVAL;
+	}
+	if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
+		btrfs_err(fs_info, "tree_root level too big: %d >= %d",
+				btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+	if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
+		btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
+				btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+	if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
+		btrfs_err(fs_info, "log_root level too big: %d >= %d",
+				btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+
+	/*
+	 * Check sectorsize and nodesize first, other check will need it.
+	 * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
+	 */
+	if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
+	    sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+		btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
+		ret = -EINVAL;
+	}
+	/* Only PAGE SIZE is supported yet */
+	if (sectorsize != PAGE_SIZE) {
+		btrfs_err(fs_info,
+			"sectorsize %llu not supported yet, only support %lu",
+			sectorsize, PAGE_SIZE);
+		ret = -EINVAL;
+	}
+	if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
+	    nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+		btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
+		ret = -EINVAL;
+	}
+	if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
+		btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
+			  le32_to_cpu(sb->__unused_leafsize), nodesize);
+		ret = -EINVAL;
+	}
+
+	/* Root alignment check */
+	if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
+		btrfs_warn(fs_info, "tree_root block unaligned: %llu",
+			   btrfs_super_root(sb));
+		ret = -EINVAL;
+	}
+	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
+		btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
+			   btrfs_super_chunk_root(sb));
+		ret = -EINVAL;
+	}
+	if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
+		btrfs_warn(fs_info, "log_root block unaligned: %llu",
+			   btrfs_super_log_root(sb));
+		ret = -EINVAL;
+	}
+
+	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) {
+		btrfs_err(fs_info,
+			   "dev_item UUID does not match fsid: %pU != %pU",
+			   fs_info->fsid, sb->dev_item.fsid);
+		ret = -EINVAL;
+	}
+
+	/*
+	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
+	 * done later
+	 */
+	if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+		btrfs_err(fs_info, "bytes_used is too small %llu",
+			  btrfs_super_bytes_used(sb));
+		ret = -EINVAL;
+	}
+	if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+		btrfs_err(fs_info, "invalid stripesize %u",
+			  btrfs_super_stripesize(sb));
+		ret = -EINVAL;
+	}
+	if (btrfs_super_num_devices(sb) > (1UL << 31))
+		btrfs_warn(fs_info, "suspicious number of devices: %llu",
+			   btrfs_super_num_devices(sb));
+	if (btrfs_super_num_devices(sb) == 0) {
+		btrfs_err(fs_info, "number of devices is 0");
+		ret = -EINVAL;
+	}
+
+	if (mirror_num >= 0 &&
+	    btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) {
+		btrfs_err(fs_info, "super offset mismatch %llu != %u",
+			  btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
+		ret = -EINVAL;
+	}
+
+	/*
+	 * Obvious sys_chunk_array corruptions, it must hold at least one key
+	 * and one chunk
+	 */
+	if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
+		btrfs_err(fs_info, "system chunk array too big %u > %u",
+			  btrfs_super_sys_array_size(sb),
+			  BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
+		ret = -EINVAL;
+	}
+	if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
+			+ sizeof(struct btrfs_chunk)) {
+		btrfs_err(fs_info, "system chunk array too small %u < %zu",
+			  btrfs_super_sys_array_size(sb),
+			  sizeof(struct btrfs_disk_key)
+			  + sizeof(struct btrfs_chunk));
+		ret = -EINVAL;
+	}
+
+	/*
+	 * The generation is a global counter, we'll trust it more than the others
+	 * but it's still possible that it's the one that's wrong.
+	 */
+	if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
+		btrfs_warn(fs_info,
+			"suspicious: generation < chunk_root_generation: %llu < %llu",
+			btrfs_super_generation(sb),
+			btrfs_super_chunk_root_generation(sb));
+	if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
+	    && btrfs_super_cache_generation(sb) != (u64)-1)
+		btrfs_warn(fs_info,
+			"suspicious: generation < cache_generation: %llu < %llu",
+			btrfs_super_generation(sb),
+			btrfs_super_cache_generation(sb));
+
+	return ret;
+}
+
+/*
+ * Validation of super block at mount time.
+ * Some checks already done early at mount time, like csum type and incompat
+ * flags will be skipped.
+ */
+static int btrfs_validate_mount_super(struct btrfs_fs_info *fs_info)
+{
+	return validate_super(fs_info, fs_info->super_copy, 0);
+}
+
+/*
+ * Validation of super block at write time.
+ * Some checks like bytenr check will be skipped as their values will be
+ * overwritten soon.
+ * Extra checks like csum type and incompat flags will be done here.
+ */
+static int btrfs_validate_write_super(struct btrfs_fs_info *fs_info,
+				      struct btrfs_super_block *sb)
+{
+	int ret;
+
+	ret = validate_super(fs_info, sb, -1);
+	if (ret < 0)
+		goto out;
+	if (btrfs_super_csum_type(sb) != BTRFS_CSUM_TYPE_CRC32) {
+		ret = -EUCLEAN;
+		btrfs_err(fs_info, "invalid csum type, has %u want %u",
+			  btrfs_super_csum_type(sb), BTRFS_CSUM_TYPE_CRC32);
+		goto out;
+	}
+	if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
+		ret = -EUCLEAN;
+		btrfs_err(fs_info,
+		"invalid incompat flags, has 0x%llx valid mask 0x%llx",
+			  btrfs_super_incompat_flags(sb),
+			  (unsigned long long)BTRFS_FEATURE_INCOMPAT_SUPP);
+		goto out;
+	}
+out:
+	if (ret < 0)
+		btrfs_err(fs_info,
+		"super block corruption detected before writing it to disk");
+	return ret;
+}
+
 int open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options)
@@ -2600,7 +2802,6 @@ int open_ctree(struct super_block *sb,
 	mutex_init(&fs_info->chunk_mutex);
 	mutex_init(&fs_info->transaction_kthread_mutex);
 	mutex_init(&fs_info->cleaner_mutex);
-	mutex_init(&fs_info->volume_mutex);
 	mutex_init(&fs_info->ro_block_group_mutex);
 	init_rwsem(&fs_info->commit_root_sem);
 	init_rwsem(&fs_info->cleanup_work_sem);
@@ -2667,7 +2868,7 @@ int open_ctree(struct super_block *sb,
 
 	memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE);
 
-	ret = btrfs_check_super_valid(fs_info);
+	ret = btrfs_validate_mount_super(fs_info);
 	if (ret) {
 		btrfs_err(fs_info, "superblock contains fatal errors");
 		err = -EINVAL;
@@ -3522,7 +3723,7 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags)
 	for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) {
 		if (raid_type == BTRFS_RAID_SINGLE)
 			continue;
-		if (!(flags & btrfs_raid_group[raid_type]))
+		if (!(flags & btrfs_raid_array[raid_type].bg_flag))
 			continue;
 		min_tolerated = min(min_tolerated,
 				    btrfs_raid_array[raid_type].
@@ -3602,6 +3803,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 		flags = btrfs_super_flags(sb);
 		btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN);
 
+		ret = btrfs_validate_write_super(fs_info, sb);
+		if (ret < 0) {
+			mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+			btrfs_handle_fs_error(fs_info, -EUCLEAN,
+				"unexpected superblock corruption detected");
+			return -EUCLEAN;
+		}
+
 		ret = write_dev_supers(dev, sb, max_mirrors);
 		if (ret)
 			total_errors++;
@@ -3673,8 +3882,6 @@ static void free_fs_root(struct btrfs_root *root)
 {
 	iput(root->ino_cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
-	btrfs_free_block_rsv(root->fs_info, root->orphan_block_rsv);
-	root->orphan_block_rsv = NULL;
 	if (root->anon_dev)
 		free_anon_bdev(root->anon_dev);
 	if (root->subv_writers)
@@ -3765,7 +3972,6 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info)
 
 void close_ctree(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_root *root = fs_info->tree_root;
 	int ret;
 
 	set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
@@ -3817,6 +4023,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
 
 	btrfs_free_qgroup_config(fs_info);
+	ASSERT(list_empty(&fs_info->delalloc_roots));
 
 	if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
 		btrfs_info(fs_info, "at unmount delalloc count %lld",
@@ -3860,9 +4067,6 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	btrfs_free_stripe_hash_table(fs_info);
 	btrfs_free_ref_cache(fs_info);
 
-	__btrfs_free_block_rsv(root->orphan_block_rsv);
-	root->orphan_block_rsv = NULL;
-
 	while (!list_empty(&fs_info->pinned_chunks)) {
 		struct extent_map *em;
 
@@ -3973,166 +4177,17 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level,
 					      level, first_key);
 }
 
-static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_super_block *sb = fs_info->super_copy;
-	u64 nodesize = btrfs_super_nodesize(sb);
-	u64 sectorsize = btrfs_super_sectorsize(sb);
-	int ret = 0;
-
-	if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
-		btrfs_err(fs_info, "no valid FS found");
-		ret = -EINVAL;
-	}
-	if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) {
-		btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu",
-				btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
-		ret = -EINVAL;
-	}
-	if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
-		btrfs_err(fs_info, "tree_root level too big: %d >= %d",
-				btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
-		ret = -EINVAL;
-	}
-	if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
-		btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
-				btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
-		ret = -EINVAL;
-	}
-	if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
-		btrfs_err(fs_info, "log_root level too big: %d >= %d",
-				btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
-		ret = -EINVAL;
-	}
-
-	/*
-	 * Check sectorsize and nodesize first, other check will need it.
-	 * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
-	 */
-	if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
-	    sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
-		btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
-		ret = -EINVAL;
-	}
-	/* Only PAGE SIZE is supported yet */
-	if (sectorsize != PAGE_SIZE) {
-		btrfs_err(fs_info,
-			"sectorsize %llu not supported yet, only support %lu",
-			sectorsize, PAGE_SIZE);
-		ret = -EINVAL;
-	}
-	if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
-	    nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
-		btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
-		ret = -EINVAL;
-	}
-	if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
-		btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
-			  le32_to_cpu(sb->__unused_leafsize), nodesize);
-		ret = -EINVAL;
-	}
-
-	/* Root alignment check */
-	if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
-		btrfs_warn(fs_info, "tree_root block unaligned: %llu",
-			   btrfs_super_root(sb));
-		ret = -EINVAL;
-	}
-	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
-		btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
-			   btrfs_super_chunk_root(sb));
-		ret = -EINVAL;
-	}
-	if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
-		btrfs_warn(fs_info, "log_root block unaligned: %llu",
-			   btrfs_super_log_root(sb));
-		ret = -EINVAL;
-	}
-
-	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) {
-		btrfs_err(fs_info,
-			   "dev_item UUID does not match fsid: %pU != %pU",
-			   fs_info->fsid, sb->dev_item.fsid);
-		ret = -EINVAL;
-	}
-
-	/*
-	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
-	 * done later
-	 */
-	if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
-		btrfs_err(fs_info, "bytes_used is too small %llu",
-			  btrfs_super_bytes_used(sb));
-		ret = -EINVAL;
-	}
-	if (!is_power_of_2(btrfs_super_stripesize(sb))) {
-		btrfs_err(fs_info, "invalid stripesize %u",
-			  btrfs_super_stripesize(sb));
-		ret = -EINVAL;
-	}
-	if (btrfs_super_num_devices(sb) > (1UL << 31))
-		btrfs_warn(fs_info, "suspicious number of devices: %llu",
-			   btrfs_super_num_devices(sb));
-	if (btrfs_super_num_devices(sb) == 0) {
-		btrfs_err(fs_info, "number of devices is 0");
-		ret = -EINVAL;
-	}
-
-	if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) {
-		btrfs_err(fs_info, "super offset mismatch %llu != %u",
-			  btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
-		ret = -EINVAL;
-	}
-
-	/*
-	 * Obvious sys_chunk_array corruptions, it must hold at least one key
-	 * and one chunk
-	 */
-	if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
-		btrfs_err(fs_info, "system chunk array too big %u > %u",
-			  btrfs_super_sys_array_size(sb),
-			  BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
-		ret = -EINVAL;
-	}
-	if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
-			+ sizeof(struct btrfs_chunk)) {
-		btrfs_err(fs_info, "system chunk array too small %u < %zu",
-			  btrfs_super_sys_array_size(sb),
-			  sizeof(struct btrfs_disk_key)
-			  + sizeof(struct btrfs_chunk));
-		ret = -EINVAL;
-	}
-
-	/*
-	 * The generation is a global counter, we'll trust it more than the others
-	 * but it's still possible that it's the one that's wrong.
-	 */
-	if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
-		btrfs_warn(fs_info,
-			"suspicious: generation < chunk_root_generation: %llu < %llu",
-			btrfs_super_generation(sb),
-			btrfs_super_chunk_root_generation(sb));
-	if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
-	    && btrfs_super_cache_generation(sb) != (u64)-1)
-		btrfs_warn(fs_info,
-			"suspicious: generation < cache_generation: %llu < %llu",
-			btrfs_super_generation(sb),
-			btrfs_super_cache_generation(sb));
-
-	return ret;
-}
-
 static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
 {
+	/* cleanup FS via transaction */
+	btrfs_cleanup_transaction(fs_info);
+
 	mutex_lock(&fs_info->cleaner_mutex);
 	btrfs_run_delayed_iputs(fs_info);
 	mutex_unlock(&fs_info->cleaner_mutex);
 
 	down_write(&fs_info->cleanup_work_sem);
 	up_write(&fs_info->cleanup_work_sem);
-
-	/* cleanup FS via transaction */
-	btrfs_cleanup_transaction(fs_info);
 }
 
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
@@ -4257,19 +4312,23 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
 	list_splice_init(&root->delalloc_inodes, &splice);
 
 	while (!list_empty(&splice)) {
+		struct inode *inode = NULL;
 		btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
 					       delalloc_inodes);
-
-		list_del_init(&btrfs_inode->delalloc_inodes);
-		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-			  &btrfs_inode->runtime_flags);
+		__btrfs_del_delalloc_inode(root, btrfs_inode);
 		spin_unlock(&root->delalloc_lock);
 
-		btrfs_invalidate_inodes(btrfs_inode->root);
-
+		/*
+		 * Make sure we get a live inode and that it'll not disappear
+		 * meanwhile.
+		 */
+		inode = igrab(&btrfs_inode->vfs_inode);
+		if (inode) {
+			invalidate_inode_pages2(inode->i_mapping);
+			iput(inode);
+		}
 		spin_lock(&root->delalloc_lock);
 	}
-
 	spin_unlock(&root->delalloc_lock);
 }
 
@@ -4285,7 +4344,6 @@ static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info)
 	while (!list_empty(&splice)) {
 		root = list_first_entry(&splice, struct btrfs_root,
 					 delalloc_root);
-		list_del_init(&root->delalloc_root);
 		root = btrfs_grab_fs_root(root);
 		BUG_ON(!root);
 		spin_unlock(&fs_info->delalloc_root_lock);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 75cfb80d2551..3d9fe58c0080 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -66,10 +66,8 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 				      u64 flags, u64 owner, u64 offset,
 				      struct btrfs_key *ins, int ref_mod);
 static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
-				     struct btrfs_fs_info *fs_info,
-				     u64 parent, u64 root_objectid,
-				     u64 flags, struct btrfs_disk_key *key,
-				     int level, struct btrfs_key *ins);
+				     struct btrfs_delayed_ref_node *node,
+				     struct btrfs_delayed_extent_op *extent_op);
 static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 			  struct btrfs_fs_info *fs_info, u64 flags,
 			  int force);
@@ -256,7 +254,7 @@ static int exclude_super_stripes(struct btrfs_fs_info *fs_info,
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
 		bytenr = btrfs_sb_offset(i);
 		ret = btrfs_rmap_block(fs_info, cache->key.objectid,
-				       bytenr, 0, &logical, &nr, &stripe_len);
+				       bytenr, &logical, &nr, &stripe_len);
 		if (ret)
 			return ret;
 
@@ -343,8 +341,9 @@ static void fragment_free_space(struct btrfs_block_group_cache *block_group)
  * since their free space will be released as soon as the transaction commits.
  */
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
-		       struct btrfs_fs_info *info, u64 start, u64 end)
+		       u64 start, u64 end)
 {
+	struct btrfs_fs_info *info = block_group->fs_info;
 	u64 extent_start, extent_end, size, total_added = 0;
 	int ret;
 
@@ -489,8 +488,7 @@ next:
 
 		if (key.type == BTRFS_EXTENT_ITEM_KEY ||
 		    key.type == BTRFS_METADATA_ITEM_KEY) {
-			total_found += add_new_free_space(block_group,
-							  fs_info, last,
+			total_found += add_new_free_space(block_group, last,
 							  key.objectid);
 			if (key.type == BTRFS_METADATA_ITEM_KEY)
 				last = key.objectid +
@@ -508,7 +506,7 @@ next:
 	}
 	ret = 0;
 
-	total_found += add_new_free_space(block_group, fs_info, last,
+	total_found += add_new_free_space(block_group, last,
 					  block_group->key.objectid +
 					  block_group->key.offset);
 	caching_ctl->progress = (u64)-1;
@@ -744,12 +742,12 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
 }
 
 static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes,
-			     u64 owner, u64 root_objectid)
+			     bool metadata, u64 root_objectid)
 {
 	struct btrfs_space_info *space_info;
 	u64 flags;
 
-	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+	if (metadata) {
 		if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID)
 			flags = BTRFS_BLOCK_GROUP_SYSTEM;
 		else
@@ -2200,8 +2198,11 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 						 &old_ref_mod, &new_ref_mod);
 	}
 
-	if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0)
-		add_pinned_bytes(fs_info, -num_bytes, owner, root_objectid);
+	if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) {
+		bool metadata = owner < BTRFS_FIRST_FREE_OBJECTID;
+
+		add_pinned_bytes(fs_info, -num_bytes, metadata, root_objectid);
+	}
 
 	return ret;
 }
@@ -2428,10 +2429,8 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 {
 	int ret = 0;
 	struct btrfs_delayed_tree_ref *ref;
-	struct btrfs_key ins;
 	u64 parent = 0;
 	u64 ref_root = 0;
-	bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
 
 	ref = btrfs_delayed_node_to_tree_ref(node);
 	trace_run_delayed_tree_ref(fs_info, node, ref, node->action);
@@ -2440,15 +2439,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		parent = ref->parent;
 	ref_root = ref->root;
 
-	ins.objectid = node->bytenr;
-	if (skinny_metadata) {
-		ins.offset = ref->level;
-		ins.type = BTRFS_METADATA_ITEM_KEY;
-	} else {
-		ins.offset = node->num_bytes;
-		ins.type = BTRFS_EXTENT_ITEM_KEY;
-	}
-
 	if (node->ref_mod != 1) {
 		btrfs_err(fs_info,
 	"btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
@@ -2458,11 +2448,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	}
 	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
 		BUG_ON(!extent_op || !extent_op->update_flags);
-		ret = alloc_reserved_tree_block(trans, fs_info,
-						parent, ref_root,
-						extent_op->flags_to_set,
-						&extent_op->key,
-						ref->level, &ins);
+		ret = alloc_reserved_tree_block(trans, node, extent_op);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
 		ret = __btrfs_inc_extent_ref(trans, fs_info, node,
 					     parent, ref_root,
@@ -2594,20 +2580,26 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 	delayed_refs->num_heads--;
 	rb_erase(&head->href_node, &delayed_refs->href_root);
 	RB_CLEAR_NODE(&head->href_node);
-	spin_unlock(&delayed_refs->lock);
 	spin_unlock(&head->lock);
+	spin_unlock(&delayed_refs->lock);
 	atomic_dec(&delayed_refs->num_entries);
 
 	trace_run_delayed_ref_head(fs_info, head, 0);
 
 	if (head->total_ref_mod < 0) {
-		struct btrfs_block_group_cache *cache;
+		struct btrfs_space_info *space_info;
+		u64 flags;
 
-		cache = btrfs_lookup_block_group(fs_info, head->bytenr);
-		ASSERT(cache);
-		percpu_counter_add(&cache->space_info->total_bytes_pinned,
+		if (head->is_data)
+			flags = BTRFS_BLOCK_GROUP_DATA;
+		else if (head->is_system)
+			flags = BTRFS_BLOCK_GROUP_SYSTEM;
+		else
+			flags = BTRFS_BLOCK_GROUP_METADATA;
+		space_info = __find_space_info(fs_info, flags);
+		ASSERT(space_info);
+		percpu_counter_add(&space_info->total_bytes_pinned,
 				   -head->num_bytes);
-		btrfs_put_block_group(cache);
 
 		if (head->is_data) {
 			spin_lock(&delayed_refs->lock);
@@ -2694,17 +2686,12 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		 * insert_inline_extent_backref()).
 		 */
 		spin_lock(&locked_ref->lock);
-		btrfs_merge_delayed_refs(trans, fs_info, delayed_refs,
-					 locked_ref);
+		btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref);
 
-		/*
-		 * locked_ref is the head node, so we have to go one
-		 * node back for any delayed ref updates
-		 */
 		ref = select_delayed_ref(locked_ref);
 
 		if (ref && ref->seq &&
-		    btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
+		    btrfs_check_delayed_seq(fs_info, ref->seq)) {
 			spin_unlock(&locked_ref->lock);
 			unselect_delayed_ref_head(delayed_refs, locked_ref);
 			locked_ref = NULL;
@@ -3136,7 +3123,11 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 	struct rb_node *node;
 	int ret = 0;
 
+	spin_lock(&root->fs_info->trans_lock);
 	cur_trans = root->fs_info->running_transaction;
+	if (cur_trans)
+		refcount_inc(&cur_trans->use_count);
+	spin_unlock(&root->fs_info->trans_lock);
 	if (!cur_trans)
 		return 0;
 
@@ -3145,6 +3136,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 	head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
 	if (!head) {
 		spin_unlock(&delayed_refs->lock);
+		btrfs_put_transaction(cur_trans);
 		return 0;
 	}
 
@@ -3161,6 +3153,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 		mutex_lock(&head->mutex);
 		mutex_unlock(&head->mutex);
 		btrfs_put_delayed_ref_head(head);
+		btrfs_put_transaction(cur_trans);
 		return -EAGAIN;
 	}
 	spin_unlock(&delayed_refs->lock);
@@ -3193,6 +3186,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 	}
 	spin_unlock(&head->lock);
 	mutex_unlock(&head->mutex);
+	btrfs_put_transaction(cur_trans);
 	return ret;
 }
 
@@ -3278,7 +3272,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
 
 	path = btrfs_alloc_path();
 	if (!path)
-		return -ENOENT;
+		return -ENOMEM;
 
 	do {
 		ret = check_committed_ref(root, path, objectid,
@@ -4013,8 +4007,7 @@ static const char *alloc_name(u64 flags)
 	};
 }
 
-static int create_space_info(struct btrfs_fs_info *info, u64 flags,
-			     struct btrfs_space_info **new)
+static int create_space_info(struct btrfs_fs_info *info, u64 flags)
 {
 
 	struct btrfs_space_info *space_info;
@@ -4052,7 +4045,6 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags,
 		return ret;
 	}
 
-	*new = space_info;
 	list_add_rcu(&space_info->list, &info->space_info);
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
 		info->data_sinfo = space_info;
@@ -4109,7 +4101,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
  * returns target flags in extended format or 0 if restripe for this
  * chunk_type is not in progress
  *
- * should be called with either volume_mutex or balance_lock held
+ * should be called with balance_lock held
  */
 static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
 {
@@ -4165,7 +4157,7 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags)
 	/* First, mask out the RAID levels which aren't possible */
 	for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) {
 		if (num_devices >= btrfs_raid_array[raid_type].devs_min)
-			allowed |= btrfs_raid_group[raid_type];
+			allowed |= btrfs_raid_array[raid_type].bg_flag;
 	}
 	allowed &= flags;
 
@@ -4328,7 +4320,7 @@ commit_trans:
 			need_commit--;
 
 			if (need_commit > 0) {
-				btrfs_start_delalloc_roots(fs_info, 0, -1);
+				btrfs_start_delalloc_roots(fs_info, -1);
 				btrfs_wait_ordered_roots(fs_info, U64_MAX, 0,
 							 (u64)-1);
 			}
@@ -4665,12 +4657,14 @@ again:
 	trans->allocating_chunk = false;
 
 	spin_lock(&space_info->lock);
-	if (ret < 0 && ret != -ENOSPC)
-		goto out;
-	if (ret)
-		space_info->full = 1;
-	else
+	if (ret < 0) {
+		if (ret == -ENOSPC)
+			space_info->full = 1;
+		else
+			goto out;
+	} else {
 		ret = 1;
+	}
 
 	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
 out:
@@ -4779,7 +4773,7 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info,
 		 * the filesystem is readonly(all dirty pages are written to
 		 * the disk).
 		 */
-		btrfs_start_delalloc_roots(fs_info, 0, nr_items);
+		btrfs_start_delalloc_roots(fs_info, nr_items);
 		if (!current->journal_info)
 			btrfs_wait_ordered_roots(fs_info, nr_items, 0, (u64)-1);
 	}
@@ -5559,14 +5553,18 @@ again:
 
 static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 				    struct btrfs_block_rsv *block_rsv,
-				    struct btrfs_block_rsv *dest, u64 num_bytes)
+				    struct btrfs_block_rsv *dest, u64 num_bytes,
+				    u64 *qgroup_to_release_ret)
 {
 	struct btrfs_space_info *space_info = block_rsv->space_info;
+	u64 qgroup_to_release = 0;
 	u64 ret;
 
 	spin_lock(&block_rsv->lock);
-	if (num_bytes == (u64)-1)
+	if (num_bytes == (u64)-1) {
 		num_bytes = block_rsv->size;
+		qgroup_to_release = block_rsv->qgroup_rsv_size;
+	}
 	block_rsv->size -= num_bytes;
 	if (block_rsv->reserved >= block_rsv->size) {
 		num_bytes = block_rsv->reserved - block_rsv->size;
@@ -5575,6 +5573,13 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 	} else {
 		num_bytes = 0;
 	}
+	if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
+		qgroup_to_release = block_rsv->qgroup_rsv_reserved -
+				    block_rsv->qgroup_rsv_size;
+		block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size;
+	} else {
+		qgroup_to_release = 0;
+	}
 	spin_unlock(&block_rsv->lock);
 
 	ret = num_bytes;
@@ -5597,6 +5602,8 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 			space_info_add_old_bytes(fs_info, space_info,
 						 num_bytes);
 	}
+	if (qgroup_to_release_ret)
+		*qgroup_to_release_ret = qgroup_to_release;
 	return ret;
 }
 
@@ -5738,17 +5745,21 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
 	struct btrfs_root *root = inode->root;
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
 	u64 num_bytes = 0;
+	u64 qgroup_num_bytes = 0;
 	int ret = -ENOSPC;
 
 	spin_lock(&block_rsv->lock);
 	if (block_rsv->reserved < block_rsv->size)
 		num_bytes = block_rsv->size - block_rsv->reserved;
+	if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
+		qgroup_num_bytes = block_rsv->qgroup_rsv_size -
+				   block_rsv->qgroup_rsv_reserved;
 	spin_unlock(&block_rsv->lock);
 
 	if (num_bytes == 0)
 		return 0;
 
-	ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
+	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, true);
 	if (ret)
 		return ret;
 	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
@@ -5756,7 +5767,13 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
 		block_rsv_add_bytes(block_rsv, num_bytes, 0);
 		trace_btrfs_space_reservation(root->fs_info, "delalloc",
 					      btrfs_ino(inode), num_bytes, 1);
-	}
+
+		/* Don't forget to increase qgroup_rsv_reserved */
+		spin_lock(&block_rsv->lock);
+		block_rsv->qgroup_rsv_reserved += qgroup_num_bytes;
+		spin_unlock(&block_rsv->lock);
+	} else
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
 	return ret;
 }
 
@@ -5777,20 +5794,23 @@ static void btrfs_inode_rsv_release(struct btrfs_inode *inode, bool qgroup_free)
 	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
 	u64 released = 0;
+	u64 qgroup_to_release = 0;
 
 	/*
 	 * Since we statically set the block_rsv->size we just want to say we
 	 * are releasing 0 bytes, and then we'll just get the reservation over
 	 * the size free'd.
 	 */
-	released = block_rsv_release_bytes(fs_info, block_rsv, global_rsv, 0);
+	released = block_rsv_release_bytes(fs_info, block_rsv, global_rsv, 0,
+					   &qgroup_to_release);
 	if (released > 0)
 		trace_btrfs_space_reservation(fs_info, "delalloc",
 					      btrfs_ino(inode), released, 0);
 	if (qgroup_free)
-		btrfs_qgroup_free_meta_prealloc(inode->root, released);
+		btrfs_qgroup_free_meta_prealloc(inode->root, qgroup_to_release);
 	else
-		btrfs_qgroup_convert_reserved_meta(inode->root, released);
+		btrfs_qgroup_convert_reserved_meta(inode->root,
+						   qgroup_to_release);
 }
 
 void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
@@ -5802,7 +5822,7 @@ void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
 	if (global_rsv == block_rsv ||
 	    block_rsv->space_info != global_rsv->space_info)
 		global_rsv = NULL;
-	block_rsv_release_bytes(fs_info, block_rsv, global_rsv, num_bytes);
+	block_rsv_release_bytes(fs_info, block_rsv, global_rsv, num_bytes, NULL);
 }
 
 static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
@@ -5882,7 +5902,7 @@ static void init_global_block_rsv(struct btrfs_fs_info *fs_info)
 static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
 {
 	block_rsv_release_bytes(fs_info, &fs_info->global_block_rsv, NULL,
-				(u64)-1);
+				(u64)-1, NULL);
 	WARN_ON(fs_info->trans_block_rsv.size > 0);
 	WARN_ON(fs_info->trans_block_rsv.reserved > 0);
 	WARN_ON(fs_info->chunk_block_rsv.size > 0);
@@ -5906,48 +5926,10 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
 	WARN_ON_ONCE(!list_empty(&trans->new_bgs));
 
 	block_rsv_release_bytes(fs_info, &fs_info->chunk_block_rsv, NULL,
-				trans->chunk_bytes_reserved);
+				trans->chunk_bytes_reserved, NULL);
 	trans->chunk_bytes_reserved = 0;
 }
 
-/* Can only return 0 or -ENOSPC */
-int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
-				  struct btrfs_inode *inode)
-{
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
-	struct btrfs_root *root = inode->root;
-	/*
-	 * We always use trans->block_rsv here as we will have reserved space
-	 * for our orphan when starting the transaction, using get_block_rsv()
-	 * here will sometimes make us choose the wrong block rsv as we could be
-	 * doing a reloc inode for a non refcounted root.
-	 */
-	struct btrfs_block_rsv *src_rsv = trans->block_rsv;
-	struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv;
-
-	/*
-	 * We need to hold space in order to delete our orphan item once we've
-	 * added it, so this takes the reservation so we can release it later
-	 * when we are truly done with the orphan item.
-	 */
-	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
-
-	trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode),
-			num_bytes, 1);
-	return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
-}
-
-void btrfs_orphan_release_metadata(struct btrfs_inode *inode)
-{
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
-	struct btrfs_root *root = inode->root;
-	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
-
-	trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode),
-			num_bytes, 0);
-	btrfs_block_rsv_release(fs_info, root->orphan_block_rsv, num_bytes);
-}
-
 /*
  * btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation
  * root: the root of the parent directory
@@ -5965,7 +5947,6 @@ void btrfs_orphan_release_metadata(struct btrfs_inode *inode)
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
 				     int items,
-				     u64 *qgroup_reserved,
 				     bool use_global_rsv)
 {
 	u64 num_bytes;
@@ -5983,8 +5964,6 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 		num_bytes = 0;
 	}
 
-	*qgroup_reserved = num_bytes;
-
 	num_bytes = btrfs_calc_trans_metadata_size(fs_info, items);
 	rsv->space_info = __find_space_info(fs_info,
 					    BTRFS_BLOCK_GROUP_METADATA);
@@ -5994,8 +5973,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 	if (ret == -ENOSPC && use_global_rsv)
 		ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, 1);
 
-	if (ret && *qgroup_reserved)
-		btrfs_qgroup_free_meta_prealloc(root, *qgroup_reserved);
+	if (ret && num_bytes)
+		btrfs_qgroup_free_meta_prealloc(root, num_bytes);
 
 	return ret;
 }
@@ -6011,6 +5990,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
 	u64 reserve_size = 0;
+	u64 qgroup_rsv_size = 0;
 	u64 csum_leaves;
 	unsigned outstanding_extents;
 
@@ -6023,9 +6003,17 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 						 inode->csum_bytes);
 	reserve_size += btrfs_calc_trans_metadata_size(fs_info,
 						       csum_leaves);
+	/*
+	 * For qgroup rsv, the calculation is very simple:
+	 * account one nodesize for each outstanding extent
+	 *
+	 * This is overestimating in most cases.
+	 */
+	qgroup_rsv_size = outstanding_extents * fs_info->nodesize;
 
 	spin_lock(&block_rsv->lock);
 	block_rsv->size = reserve_size;
+	block_rsv->qgroup_rsv_size = qgroup_rsv_size;
 	spin_unlock(&block_rsv->lock);
 }
 
@@ -6306,6 +6294,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			spin_lock(&info->unused_bgs_lock);
 			if (list_empty(&cache->bg_list)) {
 				btrfs_get_block_group(cache);
+				trace_btrfs_add_unused_block_group(cache);
 				list_add_tail(&cache->bg_list,
 					      &info->unused_bgs);
 			}
@@ -6463,6 +6452,7 @@ int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info,
 	struct btrfs_key key;
 	int found_type;
 	int i;
+	int ret = 0;
 
 	if (!btrfs_fs_incompat(fs_info, MIXED_GROUPS))
 		return 0;
@@ -6479,10 +6469,12 @@ int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info,
 			continue;
 		key.objectid = btrfs_file_extent_disk_bytenr(eb, item);
 		key.offset = btrfs_file_extent_disk_num_bytes(eb, item);
-		__exclude_logged_extent(fs_info, key.objectid, key.offset);
+		ret = __exclude_logged_extent(fs_info, key.objectid, key.offset);
+		if (ret)
+			break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static void
@@ -7074,7 +7066,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			}
 		}
 
-		ret = add_to_free_space_tree(trans, info, bytenr, num_bytes);
+		ret = add_to_free_space_tree(trans, bytenr, num_bytes);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
 			goto out;
@@ -7218,7 +7210,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 	}
 out:
 	if (pin)
-		add_pinned_bytes(fs_info, buf->len, btrfs_header_level(buf),
+		add_pinned_bytes(fs_info, buf->len, true,
 				 root->root_key.objectid);
 
 	if (last_ref) {
@@ -7272,8 +7264,11 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 						 &old_ref_mod, &new_ref_mod);
 	}
 
-	if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0)
-		add_pinned_bytes(fs_info, num_bytes, owner, root_objectid);
+	if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) {
+		bool metadata = owner < BTRFS_FIRST_FREE_OBJECTID;
+
+		add_pinned_bytes(fs_info, num_bytes, metadata, root_objectid);
+	}
 
 	return ret;
 }
@@ -7325,24 +7320,6 @@ wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
 	return ret;
 }
 
-static const char *btrfs_raid_type_names[BTRFS_NR_RAID_TYPES] = {
-	[BTRFS_RAID_RAID10]	= "raid10",
-	[BTRFS_RAID_RAID1]	= "raid1",
-	[BTRFS_RAID_DUP]	= "dup",
-	[BTRFS_RAID_RAID0]	= "raid0",
-	[BTRFS_RAID_SINGLE]	= "single",
-	[BTRFS_RAID_RAID5]	= "raid5",
-	[BTRFS_RAID_RAID6]	= "raid6",
-};
-
-static const char *get_raid_name(enum btrfs_raid_types type)
-{
-	if (type >= BTRFS_NR_RAID_TYPES)
-		return NULL;
-
-	return btrfs_raid_type_names[type];
-}
-
 enum btrfs_loop_type {
 	LOOP_CACHING_NOWAIT = 0,
 	LOOP_CACHING_WAIT = 1,
@@ -7614,7 +7591,7 @@ have_block_group:
 			if (offset) {
 				/* we have a block, we're done */
 				spin_unlock(&last_ptr->refill_lock);
-				trace_btrfs_reserve_extent_cluster(fs_info,
+				trace_btrfs_reserve_extent_cluster(
 						used_block_group,
 						search_start, num_bytes);
 				if (used_block_group != block_group) {
@@ -7687,7 +7664,7 @@ refill_cluster:
 				if (offset) {
 					/* we found one, proceed */
 					spin_unlock(&last_ptr->refill_lock);
-					trace_btrfs_reserve_extent_cluster(fs_info,
+					trace_btrfs_reserve_extent_cluster(
 						block_group, search_start,
 						num_bytes);
 					goto checks;
@@ -7787,8 +7764,7 @@ checks:
 		ins->objectid = search_start;
 		ins->offset = num_bytes;
 
-		trace_btrfs_reserve_extent(fs_info, block_group,
-					   search_start, num_bytes);
+		trace_btrfs_reserve_extent(block_group, search_start, num_bytes);
 		btrfs_release_block_group(block_group, delalloc);
 		break;
 loop:
@@ -8136,8 +8112,7 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(path->nodes[0]);
 	btrfs_free_path(path);
 
-	ret = remove_from_free_space_tree(trans, fs_info, ins->objectid,
-					  ins->offset);
+	ret = remove_from_free_space_tree(trans, ins->objectid, ins->offset);
 	if (ret)
 		return ret;
 
@@ -8152,37 +8127,52 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 }
 
 static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
-				     struct btrfs_fs_info *fs_info,
-				     u64 parent, u64 root_objectid,
-				     u64 flags, struct btrfs_disk_key *key,
-				     int level, struct btrfs_key *ins)
+				     struct btrfs_delayed_ref_node *node,
+				     struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_extent_item *extent_item;
+	struct btrfs_key extent_key;
 	struct btrfs_tree_block_info *block_info;
 	struct btrfs_extent_inline_ref *iref;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
+	struct btrfs_delayed_tree_ref *ref;
 	u32 size = sizeof(*extent_item) + sizeof(*iref);
-	u64 num_bytes = ins->offset;
+	u64 num_bytes;
+	u64 flags = extent_op->flags_to_set;
 	bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
 
-	if (!skinny_metadata)
+	ref = btrfs_delayed_node_to_tree_ref(node);
+
+	extent_key.objectid = node->bytenr;
+	if (skinny_metadata) {
+		extent_key.offset = ref->level;
+		extent_key.type = BTRFS_METADATA_ITEM_KEY;
+		num_bytes = fs_info->nodesize;
+	} else {
+		extent_key.offset = node->num_bytes;
+		extent_key.type = BTRFS_EXTENT_ITEM_KEY;
 		size += sizeof(*block_info);
+		num_bytes = node->num_bytes;
+	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		btrfs_free_and_pin_reserved_extent(fs_info, ins->objectid,
+		btrfs_free_and_pin_reserved_extent(fs_info,
+						   extent_key.objectid,
 						   fs_info->nodesize);
 		return -ENOMEM;
 	}
 
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
-				      ins, size);
+				      &extent_key, size);
 	if (ret) {
 		btrfs_free_path(path);
-		btrfs_free_and_pin_reserved_extent(fs_info, ins->objectid,
+		btrfs_free_and_pin_reserved_extent(fs_info,
+						   extent_key.objectid,
 						   fs_info->nodesize);
 		return ret;
 	}
@@ -8197,42 +8187,41 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 
 	if (skinny_metadata) {
 		iref = (struct btrfs_extent_inline_ref *)(extent_item + 1);
-		num_bytes = fs_info->nodesize;
 	} else {
 		block_info = (struct btrfs_tree_block_info *)(extent_item + 1);
-		btrfs_set_tree_block_key(leaf, block_info, key);
-		btrfs_set_tree_block_level(leaf, block_info, level);
+		btrfs_set_tree_block_key(leaf, block_info, &extent_op->key);
+		btrfs_set_tree_block_level(leaf, block_info, ref->level);
 		iref = (struct btrfs_extent_inline_ref *)(block_info + 1);
 	}
 
-	if (parent > 0) {
+	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) {
 		BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
 		btrfs_set_extent_inline_ref_type(leaf, iref,
 						 BTRFS_SHARED_BLOCK_REF_KEY);
-		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, ref->parent);
 	} else {
 		btrfs_set_extent_inline_ref_type(leaf, iref,
 						 BTRFS_TREE_BLOCK_REF_KEY);
-		btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, ref->root);
 	}
 
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_free_path(path);
 
-	ret = remove_from_free_space_tree(trans, fs_info, ins->objectid,
+	ret = remove_from_free_space_tree(trans, extent_key.objectid,
 					  num_bytes);
 	if (ret)
 		return ret;
 
-	ret = update_block_group(trans, fs_info, ins->objectid,
+	ret = update_block_group(trans, fs_info, extent_key.objectid,
 				 fs_info->nodesize, 1);
 	if (ret) { /* -ENOENT, logic error */
 		btrfs_err(fs_info, "update block group failed for %llu %llu",
-			ins->objectid, ins->offset);
+			extent_key.objectid, extent_key.offset);
 		BUG();
 	}
 
-	trace_btrfs_reserved_extent_alloc(fs_info, ins->objectid,
+	trace_btrfs_reserved_extent_alloc(fs_info, extent_key.objectid,
 					  fs_info->nodesize);
 	return ret;
 }
@@ -8403,7 +8392,7 @@ static void unuse_block_rsv(struct btrfs_fs_info *fs_info,
 			    struct btrfs_block_rsv *block_rsv, u32 blocksize)
 {
 	block_rsv_add_bytes(block_rsv, blocksize, 0);
-	block_rsv_release_bytes(fs_info, block_rsv, NULL, 0);
+	block_rsv_release_bytes(fs_info, block_rsv, NULL, 0, NULL);
 }
 
 /*
@@ -10125,8 +10114,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
-			add_new_free_space(cache, info,
-					   found_key.objectid,
+			add_new_free_space(cache, found_key.objectid,
 					   found_key.objectid +
 					   found_key.offset);
 			free_excluded_extents(info, cache);
@@ -10156,6 +10144,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 			/* Should always be true but just in case. */
 			if (list_empty(&cache->bg_list)) {
 				btrfs_get_block_group(cache);
+				trace_btrfs_add_unused_block_group(cache);
 				list_add_tail(&cache->bg_list,
 					      &info->unused_bgs);
 			}
@@ -10221,7 +10210,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 					       key.offset);
 		if (ret)
 			btrfs_abort_transaction(trans, ret);
-		add_block_group_free_space(trans, fs_info, block_group);
+		add_block_group_free_space(trans, block_group);
 		/* already aborted the transaction if it failed. */
 next:
 		list_del_init(&block_group->bg_list);
@@ -10262,7 +10251,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	add_new_free_space(cache, fs_info, chunk_offset, chunk_offset + size);
+	add_new_free_space(cache, chunk_offset, chunk_offset + size);
 
 	free_excluded_extents(fs_info, cache);
 
@@ -10343,6 +10332,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	BUG_ON(!block_group);
 	BUG_ON(!block_group->ro);
 
+	trace_btrfs_remove_block_group(block_group);
 	/*
 	 * Free the reserved super bytes from this block group before
 	 * remove it.
@@ -10600,7 +10590,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	mutex_unlock(&fs_info->chunk_mutex);
 
-	ret = remove_block_group_free_space(trans, fs_info, block_group);
+	ret = remove_block_group_free_space(trans, block_group);
 	if (ret)
 		goto out;
 
@@ -10707,6 +10697,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			 * the ro check in case balance is currently acting on
 			 * this block group.
 			 */
+			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
 			up_write(&space_info->groups_sem);
 			goto next;
@@ -10829,7 +10820,6 @@ next:
 
 int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_space_info *space_info;
 	struct btrfs_super_block *disk_super;
 	u64 features;
 	u64 flags;
@@ -10845,21 +10835,21 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
 		mixed = 1;
 
 	flags = BTRFS_BLOCK_GROUP_SYSTEM;
-	ret = create_space_info(fs_info, flags, &space_info);
+	ret = create_space_info(fs_info, flags);
 	if (ret)
 		goto out;
 
 	if (mixed) {
 		flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA;
-		ret = create_space_info(fs_info, flags, &space_info);
+		ret = create_space_info(fs_info, flags);
 	} else {
 		flags = BTRFS_BLOCK_GROUP_METADATA;
-		ret = create_space_info(fs_info, flags, &space_info);
+		ret = create_space_info(fs_info, flags);
 		if (ret)
 			goto out;
 
 		flags = BTRFS_BLOCK_GROUP_DATA;
-		ret = create_space_info(fs_info, flags, &space_info);
+		ret = create_space_info(fs_info, flags);
 	}
 out:
 	return ret;
@@ -11044,12 +11034,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 void btrfs_end_write_no_snapshotting(struct btrfs_root *root)
 {
 	percpu_counter_dec(&root->subv_writers->counter);
-	/*
-	 * Make sure counter is updated before we wake up waiters.
-	 */
-	smp_mb();
-	if (waitqueue_active(&root->subv_writers->wait))
-		wake_up(&root->subv_writers->wait);
+	cond_wake_up(&root->subv_writers->wait);
 }
 
 int btrfs_start_write_no_snapshotting(struct btrfs_root *root)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e99b329002cf..51fc015c7d2c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -26,7 +26,7 @@
 
 static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;
-static struct bio_set *btrfs_bioset;
+static struct bio_set btrfs_bioset;
 
 static inline bool extent_state_in_tree(const struct extent_state *state)
 {
@@ -162,20 +162,18 @@ int __init extent_io_init(void)
 	if (!extent_buffer_cache)
 		goto free_state_cache;
 
-	btrfs_bioset = bioset_create(BIO_POOL_SIZE,
-				     offsetof(struct btrfs_io_bio, bio),
-				     BIOSET_NEED_BVECS);
-	if (!btrfs_bioset)
+	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
+			offsetof(struct btrfs_io_bio, bio),
+			BIOSET_NEED_BVECS))
 		goto free_buffer_cache;
 
-	if (bioset_integrity_create(btrfs_bioset, BIO_POOL_SIZE))
+	if (bioset_integrity_create(&btrfs_bioset, BIO_POOL_SIZE))
 		goto free_bioset;
 
 	return 0;
 
 free_bioset:
-	bioset_free(btrfs_bioset);
-	btrfs_bioset = NULL;
+	bioset_exit(&btrfs_bioset);
 
 free_buffer_cache:
 	kmem_cache_destroy(extent_buffer_cache);
@@ -198,8 +196,7 @@ void __cold extent_io_exit(void)
 	rcu_barrier();
 	kmem_cache_destroy(extent_state_cache);
 	kmem_cache_destroy(extent_buffer_cache);
-	if (btrfs_bioset)
-		bioset_free(btrfs_bioset);
+	bioset_exit(&btrfs_bioset);
 }
 
 void extent_io_tree_init(struct extent_io_tree *tree,
@@ -2679,7 +2676,7 @@ struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte)
 {
 	struct bio *bio;
 
-	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, btrfs_bioset);
+	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &btrfs_bioset);
 	bio_set_dev(bio, bdev);
 	bio->bi_iter.bi_sector = first_byte >> 9;
 	btrfs_io_bio_init(btrfs_io_bio(bio));
@@ -2692,7 +2689,7 @@ struct bio *btrfs_bio_clone(struct bio *bio)
 	struct bio *new;
 
 	/* Bio allocation backed by a bioset does not fail */
-	new = bio_clone_fast(bio, GFP_NOFS, btrfs_bioset);
+	new = bio_clone_fast(bio, GFP_NOFS, &btrfs_bioset);
 	btrfs_bio = btrfs_io_bio(new);
 	btrfs_io_bio_init(btrfs_bio);
 	btrfs_bio->iter = bio->bi_iter;
@@ -2704,7 +2701,7 @@ struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs)
 	struct bio *bio;
 
 	/* Bio allocation backed by a bioset does not fail */
-	bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, btrfs_bioset);
+	bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, &btrfs_bioset);
 	btrfs_io_bio_init(btrfs_io_bio(bio));
 	return bio;
 }
@@ -2715,7 +2712,7 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
 	struct btrfs_io_bio *btrfs_bio;
 
 	/* this will never fail when it's backed by a bioset */
-	bio = bio_clone_fast(orig, GFP_NOFS, btrfs_bioset);
+	bio = bio_clone_fast(orig, GFP_NOFS, &btrfs_bioset);
 	ASSERT(bio);
 
 	btrfs_bio = btrfs_io_bio(bio);
@@ -4109,14 +4106,13 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 	return ret;
 }
 
-int extent_writepages(struct extent_io_tree *tree,
-		      struct address_space *mapping,
+int extent_writepages(struct address_space *mapping,
 		      struct writeback_control *wbc)
 {
 	int ret = 0;
 	struct extent_page_data epd = {
 		.bio = NULL,
-		.tree = tree,
+		.tree = &BTRFS_I(mapping->host)->io_tree,
 		.extent_locked = 0,
 		.sync_io = wbc->sync_mode == WB_SYNC_ALL,
 	};
@@ -4126,9 +4122,8 @@ int extent_writepages(struct extent_io_tree *tree,
 	return ret;
 }
 
-int extent_readpages(struct extent_io_tree *tree,
-		     struct address_space *mapping,
-		     struct list_head *pages, unsigned nr_pages)
+int extent_readpages(struct address_space *mapping, struct list_head *pages,
+		     unsigned nr_pages)
 {
 	struct bio *bio = NULL;
 	unsigned page_idx;
@@ -4136,6 +4131,7 @@ int extent_readpages(struct extent_io_tree *tree,
 	struct page *pagepool[16];
 	struct page *page;
 	struct extent_map *em_cached = NULL;
+	struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
 	int nr = 0;
 	u64 prev_em_start = (u64)-1;
 
@@ -4202,8 +4198,7 @@ int extent_invalidatepage(struct extent_io_tree *tree,
  * are locked or under IO and drops the related state bits if it is safe
  * to drop the page.
  */
-static int try_release_extent_state(struct extent_map_tree *map,
-				    struct extent_io_tree *tree,
+static int try_release_extent_state(struct extent_io_tree *tree,
 				    struct page *page, gfp_t mask)
 {
 	u64 start = page_offset(page);
@@ -4238,13 +4233,13 @@ static int try_release_extent_state(struct extent_map_tree *map,
  * in the range corresponding to the page, both state records and extent
  * map records are removed
  */
-int try_release_extent_mapping(struct extent_map_tree *map,
-			       struct extent_io_tree *tree, struct page *page,
-			       gfp_t mask)
+int try_release_extent_mapping(struct page *page, gfp_t mask)
 {
 	struct extent_map *em;
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
+	struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree;
+	struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree;
 
 	if (gfpflags_allow_blocking(mask) &&
 	    page->mapping->host->i_size > SZ_16M) {
@@ -4278,7 +4273,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 			free_extent_map(em);
 		}
 	}
-	return try_release_extent_state(map, tree, page, mask);
+	return try_release_extent_state(tree, page, mask);
 }
 
 /*
@@ -5620,46 +5615,6 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
 	}
 }
 
-void le_bitmap_set(u8 *map, unsigned int start, int len)
-{
-	u8 *p = map + BIT_BYTE(start);
-	const unsigned int size = start + len;
-	int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE);
-	u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start);
-
-	while (len - bits_to_set >= 0) {
-		*p |= mask_to_set;
-		len -= bits_to_set;
-		bits_to_set = BITS_PER_BYTE;
-		mask_to_set = ~0;
-		p++;
-	}
-	if (len) {
-		mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
-		*p |= mask_to_set;
-	}
-}
-
-void le_bitmap_clear(u8 *map, unsigned int start, int len)
-{
-	u8 *p = map + BIT_BYTE(start);
-	const unsigned int size = start + len;
-	int bits_to_clear = BITS_PER_BYTE - (start % BITS_PER_BYTE);
-	u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(start);
-
-	while (len - bits_to_clear >= 0) {
-		*p &= ~mask_to_clear;
-		len -= bits_to_clear;
-		bits_to_clear = BITS_PER_BYTE;
-		mask_to_clear = ~0;
-		p++;
-	}
-	if (len) {
-		mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
-		*p &= ~mask_to_clear;
-	}
-}
-
 /*
  * eb_bitmap_offset() - calculate the page and offset of the byte containing the
  * given bit number
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index a53009694b16..0bfd4aeb822d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -79,14 +79,6 @@
 #define BITMAP_LAST_BYTE_MASK(nbits) \
 	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
 
-static inline int le_test_bit(int nr, const u8 *addr)
-{
-	return 1U & (addr[BIT_BYTE(nr)] >> (nr & (BITS_PER_BYTE-1)));
-}
-
-void le_bitmap_set(u8 *map, unsigned int start, int len);
-void le_bitmap_clear(u8 *map, unsigned int start, int len);
-
 struct extent_state;
 struct btrfs_root;
 struct btrfs_inode;
@@ -278,9 +270,7 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
 					  int create);
 
 void extent_io_tree_init(struct extent_io_tree *tree, void *private_data);
-int try_release_extent_mapping(struct extent_map_tree *map,
-			       struct extent_io_tree *tree, struct page *page,
-			       gfp_t mask);
+int try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 		     struct extent_state **cached);
@@ -421,14 +411,12 @@ int extent_invalidatepage(struct extent_io_tree *tree,
 int extent_write_full_page(struct page *page, struct writeback_control *wbc);
 int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 			      int mode);
-int extent_writepages(struct extent_io_tree *tree,
-		      struct address_space *mapping,
+int extent_writepages(struct address_space *mapping,
 		      struct writeback_control *wbc);
 int btree_write_cache_pages(struct address_space *mapping,
 			    struct writeback_control *wbc);
-int extent_readpages(struct extent_io_tree *tree,
-		     struct address_space *mapping,
-		     struct list_head *pages, unsigned nr_pages);
+int extent_readpages(struct address_space *mapping, struct list_head *pages,
+		     unsigned nr_pages);
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len);
 void set_page_extent_mapped(struct page *page);
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 1b8a078f92eb..6648d55e5339 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -518,6 +518,7 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
 
 /**
  * btrfs_add_extent_mapping - add extent mapping into em_tree
+ * @fs_info - used for tracepoint
  * @em_tree - the extent tree into which we want to insert the extent mapping
  * @em_in   - extent we are inserting
  * @start   - start of the logical range btrfs_get_extent() is requesting
@@ -535,7 +536,8 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
  * Return 0 on success, otherwise -EEXIST.
  *
  */
-int btrfs_add_extent_mapping(struct extent_map_tree *em_tree,
+int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
+			     struct extent_map_tree *em_tree,
 			     struct extent_map **em_in, u64 start, u64 len)
 {
 	int ret;
@@ -553,7 +555,7 @@ int btrfs_add_extent_mapping(struct extent_map_tree *em_tree,
 
 		existing = search_extent_mapping(em_tree, start, len);
 
-		trace_btrfs_handle_em_exist(existing, em, start, len);
+		trace_btrfs_handle_em_exist(fs_info, existing, em, start, len);
 
 		/*
 		 * existing will always be non-NULL, since there must be
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 5fcb80a6ce37..25d985e7532a 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -92,7 +92,8 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, u64 gen
 void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em);
 struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len);
-int btrfs_add_extent_mapping(struct extent_map_tree *em_tree,
+int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
+			     struct extent_map_tree *em_tree,
 			     struct extent_map **em_in, u64 start, u64 len);
 
 #endif
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0167a9c97c9c..f660ba1e5e58 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1748,7 +1748,7 @@ again:
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 					     lockstart, lockend, &cached_state);
 		btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes,
-					       (ret != 0));
+					       true);
 		if (ret) {
 			btrfs_drop_pages(pages, num_pages);
 			break;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index e5b569bebc73..d5f80cb300be 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -253,10 +253,8 @@ int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
 	truncate_pagecache(inode, 0);
 
 	/*
-	 * We don't need an orphan item because truncating the free space cache
-	 * will never be split across transactions.
-	 * We don't need to check for -EAGAIN because we're a free space
-	 * cache inode
+	 * We skip the throttling logic for free space cache inodes, so we don't
+	 * need to check for -EAGAIN.
 	 */
 	ret = btrfs_truncate_inode_items(trans, root, inode,
 					 0, BTRFS_EXTENT_DATA_KEY);
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 32a0f6cb5594..b5950aacd697 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -12,7 +12,6 @@
 #include "transaction.h"
 
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
-					struct btrfs_fs_info *fs_info,
 					struct btrfs_block_group_cache *block_group,
 					struct btrfs_path *path);
 
@@ -45,11 +44,10 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
 }
 
 static int add_new_free_space_info(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   struct btrfs_block_group_cache *block_group,
 				   struct btrfs_path *path)
 {
-	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_root *root = trans->fs_info->free_space_root;
 	struct btrfs_free_space_info *info;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
@@ -138,10 +136,11 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
 	return DIV_ROUND_UP((u32)div_u64(size, sectorsize), BITS_PER_BYTE);
 }
 
-static u8 *alloc_bitmap(u32 bitmap_size)
+static unsigned long *alloc_bitmap(u32 bitmap_size)
 {
-	u8 *ret;
+	unsigned long *ret;
 	unsigned int nofs_flag;
+	u32 bitmap_rounded_size = round_up(bitmap_size, sizeof(unsigned long));
 
 	/*
 	 * GFP_NOFS doesn't work with kvmalloc(), but we really can't recurse
@@ -152,21 +151,42 @@ static u8 *alloc_bitmap(u32 bitmap_size)
 	 * know that recursion is unsafe.
 	 */
 	nofs_flag = memalloc_nofs_save();
-	ret = kvzalloc(bitmap_size, GFP_KERNEL);
+	ret = kvzalloc(bitmap_rounded_size, GFP_KERNEL);
 	memalloc_nofs_restore(nofs_flag);
 	return ret;
 }
 
+static void le_bitmap_set(unsigned long *map, unsigned int start, int len)
+{
+	u8 *p = ((u8 *)map) + BIT_BYTE(start);
+	const unsigned int size = start + len;
+	int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE);
+	u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start);
+
+	while (len - bits_to_set >= 0) {
+		*p |= mask_to_set;
+		len -= bits_to_set;
+		bits_to_set = BITS_PER_BYTE;
+		mask_to_set = ~0;
+		p++;
+	}
+	if (len) {
+		mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
+		*p |= mask_to_set;
+	}
+}
+
 int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_block_group_cache *block_group,
 				  struct btrfs_path *path)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->free_space_root;
 	struct btrfs_free_space_info *info;
 	struct btrfs_key key, found_key;
 	struct extent_buffer *leaf;
-	u8 *bitmap, *bitmap_cursor;
+	unsigned long *bitmap;
+	char *bitmap_cursor;
 	u64 start, end;
 	u64 bitmap_range, i;
 	u32 bitmap_size, flags, expected_extent_count;
@@ -255,7 +275,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	bitmap_cursor = bitmap;
+	bitmap_cursor = (char *)bitmap;
 	bitmap_range = fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
 	i = start;
 	while (i < end) {
@@ -296,21 +316,18 @@ out:
 }
 
 int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_block_group_cache *block_group,
 				  struct btrfs_path *path)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->free_space_root;
 	struct btrfs_free_space_info *info;
 	struct btrfs_key key, found_key;
 	struct extent_buffer *leaf;
-	u8 *bitmap;
+	unsigned long *bitmap;
 	u64 start, end;
-	/* Initialize to silence GCC. */
-	u64 extent_start = 0;
-	u64 offset;
 	u32 bitmap_size, flags, expected_extent_count;
-	int prev_bit = 0, bit, bitnr;
+	unsigned long nrbits, start_bit, end_bit;
 	u32 extent_count = 0;
 	int done = 0, nr;
 	int ret;
@@ -348,7 +365,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 				break;
 			} else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
 				unsigned long ptr;
-				u8 *bitmap_cursor;
+				char *bitmap_cursor;
 				u32 bitmap_pos, data_size;
 
 				ASSERT(found_key.objectid >= start);
@@ -358,7 +375,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 				bitmap_pos = div_u64(found_key.objectid - start,
 						     fs_info->sectorsize *
 						     BITS_PER_BYTE);
-				bitmap_cursor = bitmap + bitmap_pos;
+				bitmap_cursor = ((char *)bitmap) + bitmap_pos;
 				data_size = free_space_bitmap_size(found_key.offset,
 								   fs_info->sectorsize);
 
@@ -392,32 +409,16 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
-	offset = start;
-	bitnr = 0;
-	while (offset < end) {
-		bit = !!le_test_bit(bitnr, bitmap);
-		if (prev_bit == 0 && bit == 1) {
-			extent_start = offset;
-		} else if (prev_bit == 1 && bit == 0) {
-			key.objectid = extent_start;
-			key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
-			key.offset = offset - extent_start;
-
-			ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
-			if (ret)
-				goto out;
-			btrfs_release_path(path);
+	nrbits = div_u64(block_group->key.offset, block_group->fs_info->sectorsize);
+	start_bit = find_next_bit_le(bitmap, nrbits, 0);
 
-			extent_count++;
-		}
-		prev_bit = bit;
-		offset += fs_info->sectorsize;
-		bitnr++;
-	}
-	if (prev_bit == 1) {
-		key.objectid = extent_start;
+	while (start_bit < nrbits) {
+		end_bit = find_next_zero_bit_le(bitmap, nrbits, start_bit);
+		ASSERT(start_bit < end_bit);
+
+		key.objectid = start + start_bit * block_group->fs_info->sectorsize;
 		key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
-		key.offset = end - extent_start;
+		key.offset = (end_bit - start_bit) * block_group->fs_info->sectorsize;
 
 		ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
 		if (ret)
@@ -425,6 +426,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 		btrfs_release_path(path);
 
 		extent_count++;
+
+		start_bit = find_next_bit_le(bitmap, nrbits, end_bit);
 	}
 
 	if (extent_count != expected_extent_count) {
@@ -446,7 +449,6 @@ out:
 }
 
 static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
-					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_block_group_cache *block_group,
 					  struct btrfs_path *path,
 					  int new_extents)
@@ -459,7 +461,8 @@ static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
 	if (new_extents == 0)
 		return 0;
 
-	info = search_free_space_info(trans, fs_info, block_group, path, 1);
+	info = search_free_space_info(trans, trans->fs_info, block_group, path,
+				      1);
 	if (IS_ERR(info)) {
 		ret = PTR_ERR(info);
 		goto out;
@@ -474,12 +477,10 @@ static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
 
 	if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) &&
 	    extent_count > block_group->bitmap_high_thresh) {
-		ret = convert_free_space_to_bitmaps(trans, fs_info, block_group,
-						    path);
+		ret = convert_free_space_to_bitmaps(trans, block_group, path);
 	} else if ((flags & BTRFS_FREE_SPACE_USING_BITMAPS) &&
 		   extent_count < block_group->bitmap_low_thresh) {
-		ret = convert_free_space_to_extents(trans, fs_info, block_group,
-						    path);
+		ret = convert_free_space_to_extents(trans, block_group, path);
 	}
 
 out:
@@ -576,12 +577,11 @@ static int free_space_next_bitmap(struct btrfs_trans_handle *trans,
  * the bitmap.
  */
 static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
-				    struct btrfs_fs_info *fs_info,
 				    struct btrfs_block_group_cache *block_group,
 				    struct btrfs_path *path,
 				    u64 start, u64 size, int remove)
 {
-	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_root *root = block_group->fs_info->free_space_root;
 	struct btrfs_key key;
 	u64 end = start + size;
 	u64 cur_start, cur_size;
@@ -682,7 +682,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
 	}
 
 	btrfs_release_path(path);
-	ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+	ret = update_free_space_extent_count(trans, block_group, path,
 					     new_extents);
 
 out:
@@ -690,12 +690,11 @@ out:
 }
 
 static int remove_free_space_extent(struct btrfs_trans_handle *trans,
-				    struct btrfs_fs_info *fs_info,
 				    struct btrfs_block_group_cache *block_group,
 				    struct btrfs_path *path,
 				    u64 start, u64 size)
 {
-	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_root *root = trans->fs_info->free_space_root;
 	struct btrfs_key key;
 	u64 found_start, found_end;
 	u64 end = start + size;
@@ -769,7 +768,7 @@ static int remove_free_space_extent(struct btrfs_trans_handle *trans,
 	}
 
 	btrfs_release_path(path);
-	ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+	ret = update_free_space_extent_count(trans, block_group, path,
 					     new_extents);
 
 out:
@@ -777,7 +776,6 @@ out:
 }
 
 int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_block_group_cache *block_group,
 				  struct btrfs_path *path, u64 start, u64 size)
 {
@@ -786,36 +784,35 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 	int ret;
 
 	if (block_group->needs_free_space) {
-		ret = __add_block_group_free_space(trans, fs_info, block_group,
-						   path);
+		ret = __add_block_group_free_space(trans, block_group, path);
 		if (ret)
 			return ret;
 	}
 
-	info = search_free_space_info(NULL, fs_info, block_group, path, 0);
+	info = search_free_space_info(NULL, trans->fs_info, block_group, path,
+				      0);
 	if (IS_ERR(info))
 		return PTR_ERR(info);
 	flags = btrfs_free_space_flags(path->nodes[0], info);
 	btrfs_release_path(path);
 
 	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
-		return modify_free_space_bitmap(trans, fs_info, block_group,
-						path, start, size, 1);
+		return modify_free_space_bitmap(trans, block_group, path,
+						start, size, 1);
 	} else {
-		return remove_free_space_extent(trans, fs_info, block_group,
-						path, start, size);
+		return remove_free_space_extent(trans, block_group, path,
+						start, size);
 	}
 }
 
 int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				u64 start, u64 size)
 {
 	struct btrfs_block_group_cache *block_group;
 	struct btrfs_path *path;
 	int ret;
 
-	if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+	if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
 		return 0;
 
 	path = btrfs_alloc_path();
@@ -824,7 +821,7 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	block_group = btrfs_lookup_block_group(fs_info, start);
+	block_group = btrfs_lookup_block_group(trans->fs_info, start);
 	if (!block_group) {
 		ASSERT(0);
 		ret = -ENOENT;
@@ -832,8 +829,8 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 	}
 
 	mutex_lock(&block_group->free_space_lock);
-	ret = __remove_from_free_space_tree(trans, fs_info, block_group, path,
-					    start, size);
+	ret = __remove_from_free_space_tree(trans, block_group, path, start,
+					    size);
 	mutex_unlock(&block_group->free_space_lock);
 
 	btrfs_put_block_group(block_group);
@@ -845,12 +842,11 @@ out:
 }
 
 static int add_free_space_extent(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_block_group_cache *block_group,
 				 struct btrfs_path *path,
 				 u64 start, u64 size)
 {
-	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_root *root = trans->fs_info->free_space_root;
 	struct btrfs_key key, new_key;
 	u64 found_start, found_end;
 	u64 end = start + size;
@@ -965,7 +961,7 @@ insert:
 		goto out;
 
 	btrfs_release_path(path);
-	ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+	ret = update_free_space_extent_count(trans, block_group, path,
 					     new_extents);
 
 out:
@@ -973,17 +969,16 @@ out:
 }
 
 int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_group_cache *block_group,
 			     struct btrfs_path *path, u64 start, u64 size)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_free_space_info *info;
 	u32 flags;
 	int ret;
 
 	if (block_group->needs_free_space) {
-		ret = __add_block_group_free_space(trans, fs_info, block_group,
-						   path);
+		ret = __add_block_group_free_space(trans, block_group, path);
 		if (ret)
 			return ret;
 	}
@@ -995,23 +990,22 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
 	btrfs_release_path(path);
 
 	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
-		return modify_free_space_bitmap(trans, fs_info, block_group,
-						path, start, size, 0);
+		return modify_free_space_bitmap(trans, block_group, path,
+						start, size, 0);
 	} else {
-		return add_free_space_extent(trans, fs_info, block_group, path,
-					     start, size);
+		return add_free_space_extent(trans, block_group, path, start,
+					     size);
 	}
 }
 
 int add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info,
 			   u64 start, u64 size)
 {
 	struct btrfs_block_group_cache *block_group;
 	struct btrfs_path *path;
 	int ret;
 
-	if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+	if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
 		return 0;
 
 	path = btrfs_alloc_path();
@@ -1020,7 +1014,7 @@ int add_to_free_space_tree(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	block_group = btrfs_lookup_block_group(fs_info, start);
+	block_group = btrfs_lookup_block_group(trans->fs_info, start);
 	if (!block_group) {
 		ASSERT(0);
 		ret = -ENOENT;
@@ -1028,8 +1022,7 @@ int add_to_free_space_tree(struct btrfs_trans_handle *trans,
 	}
 
 	mutex_lock(&block_group->free_space_lock);
-	ret = __add_to_free_space_tree(trans, fs_info, block_group, path, start,
-				       size);
+	ret = __add_to_free_space_tree(trans, block_group, path, start, size);
 	mutex_unlock(&block_group->free_space_lock);
 
 	btrfs_put_block_group(block_group);
@@ -1046,10 +1039,9 @@ out:
  * through the normal add/remove hooks.
  */
 static int populate_free_space_tree(struct btrfs_trans_handle *trans,
-				    struct btrfs_fs_info *fs_info,
 				    struct btrfs_block_group_cache *block_group)
 {
-	struct btrfs_root *extent_root = fs_info->extent_root;
+	struct btrfs_root *extent_root = trans->fs_info->extent_root;
 	struct btrfs_path *path, *path2;
 	struct btrfs_key key;
 	u64 start, end;
@@ -1066,7 +1058,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	ret = add_new_free_space_info(trans, fs_info, block_group, path2);
+	ret = add_new_free_space_info(trans, block_group, path2);
 	if (ret)
 		goto out;
 
@@ -1099,7 +1091,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 				break;
 
 			if (start < key.objectid) {
-				ret = __add_to_free_space_tree(trans, fs_info,
+				ret = __add_to_free_space_tree(trans,
 							       block_group,
 							       path2, start,
 							       key.objectid -
@@ -1109,7 +1101,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 			}
 			start = key.objectid;
 			if (key.type == BTRFS_METADATA_ITEM_KEY)
-				start += fs_info->nodesize;
+				start += trans->fs_info->nodesize;
 			else
 				start += key.offset;
 		} else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
@@ -1124,8 +1116,8 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 			break;
 	}
 	if (start < end) {
-		ret = __add_to_free_space_tree(trans, fs_info, block_group,
-					       path2, start, end - start);
+		ret = __add_to_free_space_tree(trans, block_group, path2,
+					       start, end - start);
 		if (ret)
 			goto out_locked;
 	}
@@ -1165,7 +1157,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 	while (node) {
 		block_group = rb_entry(node, struct btrfs_block_group_cache,
 				       cache_node);
-		ret = populate_free_space_tree(trans, fs_info, block_group);
+		ret = populate_free_space_tree(trans, block_group);
 		if (ret)
 			goto abort;
 		node = rb_next(node);
@@ -1269,7 +1261,6 @@ abort:
 }
 
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
-					struct btrfs_fs_info *fs_info,
 					struct btrfs_block_group_cache *block_group,
 					struct btrfs_path *path)
 {
@@ -1277,19 +1268,19 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
 
 	block_group->needs_free_space = 0;
 
-	ret = add_new_free_space_info(trans, fs_info, block_group, path);
+	ret = add_new_free_space_info(trans, block_group, path);
 	if (ret)
 		return ret;
 
-	return __add_to_free_space_tree(trans, fs_info, block_group, path,
+	return __add_to_free_space_tree(trans, block_group, path,
 					block_group->key.objectid,
 					block_group->key.offset);
 }
 
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
 			       struct btrfs_block_group_cache *block_group)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_path *path = NULL;
 	int ret = 0;
 
@@ -1306,7 +1297,7 @@ int add_block_group_free_space(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	ret = __add_block_group_free_space(trans, fs_info, block_group, path);
+	ret = __add_block_group_free_space(trans, block_group, path);
 
 out:
 	btrfs_free_path(path);
@@ -1317,10 +1308,9 @@ out:
 }
 
 int remove_block_group_free_space(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_block_group_cache *block_group)
 {
-	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_root *root = trans->fs_info->free_space_root;
 	struct btrfs_path *path;
 	struct btrfs_key key, found_key;
 	struct extent_buffer *leaf;
@@ -1328,7 +1318,7 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans,
 	int done = 0, nr;
 	int ret;
 
-	if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+	if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
 		return 0;
 
 	if (block_group->needs_free_space) {
@@ -1439,7 +1429,6 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 				extent_start = offset;
 			} else if (prev_bit == 1 && bit == 0) {
 				total_found += add_new_free_space(block_group,
-								  fs_info,
 								  extent_start,
 								  offset);
 				if (total_found > CACHING_CTL_WAKE_UP) {
@@ -1453,8 +1442,8 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 		}
 	}
 	if (prev_bit == 1) {
-		total_found += add_new_free_space(block_group, fs_info,
-						  extent_start, end);
+		total_found += add_new_free_space(block_group, extent_start,
+						  end);
 		extent_count++;
 	}
 
@@ -1511,8 +1500,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 
 		caching_ctl->progress = key.objectid;
 
-		total_found += add_new_free_space(block_group, fs_info,
-						  key.objectid,
+		total_found += add_new_free_space(block_group, key.objectid,
 						  key.objectid + key.offset);
 		if (total_found > CACHING_CTL_WAKE_UP) {
 			total_found = 0;
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
index 874b4feecad2..3133651d7d70 100644
--- a/fs/btrfs/free-space-tree.h
+++ b/fs/btrfs/free-space-tree.h
@@ -19,16 +19,12 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
 int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
 int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
 			       struct btrfs_block_group_cache *block_group);
 int remove_block_group_free_space(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_block_group_cache *block_group);
 int add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info,
 			   u64 start, u64 size);
 int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				u64 start, u64 size);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
@@ -38,19 +34,15 @@ search_free_space_info(struct btrfs_trans_handle *trans,
 		       struct btrfs_block_group_cache *block_group,
 		       struct btrfs_path *path, int cow);
 int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_group_cache *block_group,
 			     struct btrfs_path *path, u64 start, u64 size);
 int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_block_group_cache *block_group,
 				  struct btrfs_path *path, u64 start, u64 size);
 int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_block_group_cache *block_group,
 				  struct btrfs_path *path);
 int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_block_group_cache *block_group,
 				  struct btrfs_path *path);
 int free_space_test_bit(struct btrfs_block_group_cache *block_group,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e064c49c9a9a..89b208201783 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -31,6 +31,7 @@
 #include <linux/uio.h>
 #include <linux/magic.h>
 #include <linux/iversion.h>
+#include <asm/unaligned.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -1017,8 +1018,10 @@ static noinline int cow_file_range(struct inode *inode,
 				  ram_size, /* ram_bytes */
 				  BTRFS_COMPRESS_NONE, /* compress_type */
 				  BTRFS_ORDERED_REGULAR /* type */);
-		if (IS_ERR(em))
+		if (IS_ERR(em)) {
+			ret = PTR_ERR(em);
 			goto out_reserve;
+		}
 		free_extent_map(em);
 
 		ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
@@ -1155,13 +1158,10 @@ static noinline void async_cow_submit(struct btrfs_work *work)
 	nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >>
 		PAGE_SHIFT;
 
-	/*
-	 * atomic_sub_return implies a barrier for waitqueue_active
-	 */
+	/* atomic_sub_return implies a barrier */
 	if (atomic_sub_return(nr_pages, &fs_info->async_delalloc_pages) <
-	    5 * SZ_1M &&
-	    waitqueue_active(&fs_info->async_submit_wait))
-		wake_up(&fs_info->async_submit_wait);
+	    5 * SZ_1M)
+		cond_wake_up_nomb(&fs_info->async_submit_wait);
 
 	if (async_cow->inode)
 		submit_compressed_extents(async_cow->inode, async_cow);
@@ -1372,6 +1372,13 @@ next_slot:
 			    btrfs_file_extent_encryption(leaf, fi) ||
 			    btrfs_file_extent_other_encoding(leaf, fi))
 				goto out_check;
+			/*
+			 * Do the same check as in btrfs_cross_ref_exist but
+			 * without the unnecessary search.
+			 */
+			if (btrfs_file_extent_generation(leaf, fi) <=
+			    btrfs_root_last_snapshot(&root->root_item))
+				goto out_check;
 			if (extent_type == BTRFS_FILE_EXTENT_REG && !force)
 				goto out_check;
 			if (btrfs_extent_readonly(fs_info, disk_bytenr))
@@ -1741,24 +1748,32 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
 	spin_unlock(&root->delalloc_lock);
 }
 
-static void btrfs_del_delalloc_inode(struct btrfs_root *root,
-				     struct btrfs_inode *inode)
+
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+				struct btrfs_inode *inode)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 
-	spin_lock(&root->delalloc_lock);
 	if (!list_empty(&inode->delalloc_inodes)) {
 		list_del_init(&inode->delalloc_inodes);
 		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
 			  &inode->runtime_flags);
 		root->nr_delalloc_inodes--;
 		if (!root->nr_delalloc_inodes) {
+			ASSERT(list_empty(&root->delalloc_inodes));
 			spin_lock(&fs_info->delalloc_root_lock);
 			BUG_ON(list_empty(&root->delalloc_root));
 			list_del_init(&root->delalloc_root);
 			spin_unlock(&fs_info->delalloc_root_lock);
 		}
 	}
+}
+
+static void btrfs_del_delalloc_inode(struct btrfs_root *root,
+				     struct btrfs_inode *inode)
+{
+	spin_lock(&root->delalloc_lock);
+	__btrfs_del_delalloc_inode(root, inode);
 	spin_unlock(&root->delalloc_lock);
 }
 
@@ -3150,6 +3165,9 @@ out:
 	/* once for the tree */
 	btrfs_put_ordered_extent(ordered_extent);
 
+	/* Try to release some metadata so we don't get an OOM but don't wait */
+	btrfs_btree_balance_dirty_nodelay(fs_info);
+
 	return ret;
 }
 
@@ -3292,177 +3310,31 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
 }
 
 /*
- * This is called in transaction commit time. If there are no orphan
- * files in the subvolume, it removes orphan item and frees block_rsv
- * structure.
- */
-void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_block_rsv *block_rsv;
-	int ret;
-
-	if (atomic_read(&root->orphan_inodes) ||
-	    root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE)
-		return;
-
-	spin_lock(&root->orphan_lock);
-	if (atomic_read(&root->orphan_inodes)) {
-		spin_unlock(&root->orphan_lock);
-		return;
-	}
-
-	if (root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE) {
-		spin_unlock(&root->orphan_lock);
-		return;
-	}
-
-	block_rsv = root->orphan_block_rsv;
-	root->orphan_block_rsv = NULL;
-	spin_unlock(&root->orphan_lock);
-
-	if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state) &&
-	    btrfs_root_refs(&root->root_item) > 0) {
-		ret = btrfs_del_orphan_item(trans, fs_info->tree_root,
-					    root->root_key.objectid);
-		if (ret)
-			btrfs_abort_transaction(trans, ret);
-		else
-			clear_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
-				  &root->state);
-	}
-
-	if (block_rsv) {
-		WARN_ON(block_rsv->size > 0);
-		btrfs_free_block_rsv(fs_info, block_rsv);
-	}
-}
-
-/*
- * This creates an orphan entry for the given inode in case something goes
- * wrong in the middle of an unlink/truncate.
- *
- * NOTE: caller of this function should reserve 5 units of metadata for
- *	 this function.
+ * This creates an orphan entry for the given inode in case something goes wrong
+ * in the middle of an unlink.
  */
 int btrfs_orphan_add(struct btrfs_trans_handle *trans,
-		struct btrfs_inode *inode)
+		     struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
-	struct btrfs_root *root = inode->root;
-	struct btrfs_block_rsv *block_rsv = NULL;
-	int reserve = 0;
-	bool insert = false;
 	int ret;
 
-	if (!root->orphan_block_rsv) {
-		block_rsv = btrfs_alloc_block_rsv(fs_info,
-						  BTRFS_BLOCK_RSV_TEMP);
-		if (!block_rsv)
-			return -ENOMEM;
-	}
-
-	if (!test_and_set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-			      &inode->runtime_flags))
-		insert = true;
-
-	if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-			      &inode->runtime_flags))
-		reserve = 1;
-
-	spin_lock(&root->orphan_lock);
-	/* If someone has created ->orphan_block_rsv, be happy to use it. */
-	if (!root->orphan_block_rsv) {
-		root->orphan_block_rsv = block_rsv;
-	} else if (block_rsv) {
-		btrfs_free_block_rsv(fs_info, block_rsv);
-		block_rsv = NULL;
-	}
-
-	if (insert)
-		atomic_inc(&root->orphan_inodes);
-	spin_unlock(&root->orphan_lock);
-
-	/* grab metadata reservation from transaction handle */
-	if (reserve) {
-		ret = btrfs_orphan_reserve_metadata(trans, inode);
-		ASSERT(!ret);
-		if (ret) {
-			/*
-			 * dec doesn't need spin_lock as ->orphan_block_rsv
-			 * would be released only if ->orphan_inodes is
-			 * zero.
-			 */
-			atomic_dec(&root->orphan_inodes);
-			clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-				  &inode->runtime_flags);
-			if (insert)
-				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-					  &inode->runtime_flags);
-			return ret;
-		}
-	}
-
-	/* insert an orphan item to track this unlinked/truncated file */
-	if (insert) {
-		ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
-		if (ret) {
-			if (reserve) {
-				clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-					  &inode->runtime_flags);
-				btrfs_orphan_release_metadata(inode);
-			}
-			/*
-			 * btrfs_orphan_commit_root may race with us and set
-			 * ->orphan_block_rsv to zero, in order to avoid that,
-			 * decrease ->orphan_inodes after everything is done.
-			 */
-			atomic_dec(&root->orphan_inodes);
-			if (ret != -EEXIST) {
-				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-					  &inode->runtime_flags);
-				btrfs_abort_transaction(trans, ret);
-				return ret;
-			}
-		}
-		ret = 0;
+	ret = btrfs_insert_orphan_item(trans, inode->root, btrfs_ino(inode));
+	if (ret && ret != -EEXIST) {
+		btrfs_abort_transaction(trans, ret);
+		return ret;
 	}
 
 	return 0;
 }
 
 /*
- * We have done the truncate/delete so we can go ahead and remove the orphan
- * item for this particular inode.
+ * We have done the delete so we can go ahead and remove the orphan item for
+ * this particular inode.
  */
 static int btrfs_orphan_del(struct btrfs_trans_handle *trans,
 			    struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = inode->root;
-	int delete_item = 0;
-	int ret = 0;
-
-	if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-			       &inode->runtime_flags))
-		delete_item = 1;
-
-	if (delete_item && trans)
-		ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode));
-
-	if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-			       &inode->runtime_flags))
-		btrfs_orphan_release_metadata(inode);
-
-	/*
-	 * btrfs_orphan_commit_root may race with us and set ->orphan_block_rsv
-	 * to zero, in order to avoid that, decrease ->orphan_inodes after
-	 * everything is done.
-	 */
-	if (delete_item)
-		atomic_dec(&root->orphan_inodes);
-
-	return ret;
+	return btrfs_del_orphan_item(trans, inode->root, btrfs_ino(inode));
 }
 
 /*
@@ -3478,7 +3350,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 	struct btrfs_trans_handle *trans;
 	struct inode *inode;
 	u64 last_objectid = 0;
-	int ret = 0, nr_unlink = 0, nr_truncate = 0;
+	int ret = 0, nr_unlink = 0;
 
 	if (cmpxchg(&root->orphan_cleanup_state, 0, ORPHAN_CLEANUP_STARTED))
 		return 0;
@@ -3578,12 +3450,31 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 				key.offset = found_key.objectid - 1;
 				continue;
 			}
+
 		}
+
 		/*
-		 * Inode is already gone but the orphan item is still there,
-		 * kill the orphan item.
+		 * If we have an inode with links, there are a couple of
+		 * possibilities. Old kernels (before v3.12) used to create an
+		 * orphan item for truncate indicating that there were possibly
+		 * extent items past i_size that needed to be deleted. In v3.12,
+		 * truncate was changed to update i_size in sync with the extent
+		 * items, but the (useless) orphan item was still created. Since
+		 * v4.18, we don't create the orphan item for truncate at all.
+		 *
+		 * So, this item could mean that we need to do a truncate, but
+		 * only if this filesystem was last used on a pre-v3.12 kernel
+		 * and was not cleanly unmounted. The odds of that are quite
+		 * slim, and it's a pain to do the truncate now, so just delete
+		 * the orphan item.
+		 *
+		 * It's also possible that this orphan item was supposed to be
+		 * deleted but wasn't. The inode number may have been reused,
+		 * but either way, we can delete the orphan item.
 		 */
-		if (ret == -ENOENT) {
+		if (ret == -ENOENT || inode->i_nlink) {
+			if (!ret)
+				iput(inode);
 			trans = btrfs_start_transaction(root, 1);
 			if (IS_ERR(trans)) {
 				ret = PTR_ERR(trans);
@@ -3599,42 +3490,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 			continue;
 		}
 
-		/*
-		 * add this inode to the orphan list so btrfs_orphan_del does
-		 * the proper thing when we hit it
-		 */
-		set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-			&BTRFS_I(inode)->runtime_flags);
-		atomic_inc(&root->orphan_inodes);
-
-		/* if we have links, this was a truncate, lets do that */
-		if (inode->i_nlink) {
-			if (WARN_ON(!S_ISREG(inode->i_mode))) {
-				iput(inode);
-				continue;
-			}
-			nr_truncate++;
-
-			/* 1 for the orphan item deletion. */
-			trans = btrfs_start_transaction(root, 1);
-			if (IS_ERR(trans)) {
-				iput(inode);
-				ret = PTR_ERR(trans);
-				goto out;
-			}
-			ret = btrfs_orphan_add(trans, BTRFS_I(inode));
-			btrfs_end_transaction(trans);
-			if (ret) {
-				iput(inode);
-				goto out;
-			}
-
-			ret = btrfs_truncate(inode, false);
-			if (ret)
-				btrfs_orphan_del(NULL, BTRFS_I(inode));
-		} else {
-			nr_unlink++;
-		}
+		nr_unlink++;
 
 		/* this will do delete_inode and everything for us */
 		iput(inode);
@@ -3646,12 +3502,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 
 	root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE;
 
-	if (root->orphan_block_rsv)
-		btrfs_block_rsv_release(fs_info, root->orphan_block_rsv,
-					(u64)-1);
-
-	if (root->orphan_block_rsv ||
-	    test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
+	if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
 		trans = btrfs_join_transaction(root);
 		if (!IS_ERR(trans))
 			btrfs_end_transaction(trans);
@@ -3659,8 +3510,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 
 	if (nr_unlink)
 		btrfs_debug(fs_info, "unlinked %d orphans", nr_unlink);
-	if (nr_truncate)
-		btrfs_debug(fs_info, "truncated %d orphans", nr_truncate);
 
 out:
 	if (ret)
@@ -3923,7 +3772,7 @@ cache_acl:
 		break;
 	}
 
-	btrfs_update_iflags(inode);
+	btrfs_sync_inode_flags_to_i_flags(inode);
 	return 0;
 
 make_bad:
@@ -4237,7 +4086,7 @@ out:
 	return ret;
 }
 
-int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
+static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct inode *dir, u64 objectid,
 			const char *name, int name_len)
@@ -4318,6 +4167,262 @@ out:
 	return ret;
 }
 
+/*
+ * Helper to check if the subvolume references other subvolumes or if it's
+ * default.
+ */
+static noinline int may_destroy_subvol(struct btrfs_root *root)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_path *path;
+	struct btrfs_dir_item *di;
+	struct btrfs_key key;
+	u64 dir_id;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	/* Make sure this root isn't set as the default subvol */
+	dir_id = btrfs_super_root_dir(fs_info->super_copy);
+	di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path,
+				   dir_id, "default", 7, 0);
+	if (di && !IS_ERR(di)) {
+		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
+		if (key.objectid == root->root_key.objectid) {
+			ret = -EPERM;
+			btrfs_err(fs_info,
+				  "deleting default subvolume %llu is not allowed",
+				  key.objectid);
+			goto out;
+		}
+		btrfs_release_path(path);
+	}
+
+	key.objectid = root->root_key.objectid;
+	key.type = BTRFS_ROOT_REF_KEY;
+	key.offset = (u64)-1;
+
+	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	BUG_ON(ret == 0);
+
+	ret = 0;
+	if (path->slots[0] > 0) {
+		path->slots[0]--;
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		if (key.objectid == root->root_key.objectid &&
+		    key.type == BTRFS_ROOT_REF_KEY)
+			ret = -ENOTEMPTY;
+	}
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+/* Delete all dentries for inodes belonging to the root */
+static void btrfs_prune_dentries(struct btrfs_root *root)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct rb_node *node;
+	struct rb_node *prev;
+	struct btrfs_inode *entry;
+	struct inode *inode;
+	u64 objectid = 0;
+
+	if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
+		WARN_ON(btrfs_root_refs(&root->root_item) != 0);
+
+	spin_lock(&root->inode_lock);
+again:
+	node = root->inode_tree.rb_node;
+	prev = NULL;
+	while (node) {
+		prev = node;
+		entry = rb_entry(node, struct btrfs_inode, rb_node);
+
+		if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+			node = node->rb_left;
+		else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+			node = node->rb_right;
+		else
+			break;
+	}
+	if (!node) {
+		while (prev) {
+			entry = rb_entry(prev, struct btrfs_inode, rb_node);
+			if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) {
+				node = prev;
+				break;
+			}
+			prev = rb_next(prev);
+		}
+	}
+	while (node) {
+		entry = rb_entry(node, struct btrfs_inode, rb_node);
+		objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1;
+		inode = igrab(&entry->vfs_inode);
+		if (inode) {
+			spin_unlock(&root->inode_lock);
+			if (atomic_read(&inode->i_count) > 1)
+				d_prune_aliases(inode);
+			/*
+			 * btrfs_drop_inode will have it removed from the inode
+			 * cache when its usage count hits zero.
+			 */
+			iput(inode);
+			cond_resched();
+			spin_lock(&root->inode_lock);
+			goto again;
+		}
+
+		if (cond_resched_lock(&root->inode_lock))
+			goto again;
+
+		node = rb_next(node);
+	}
+	spin_unlock(&root->inode_lock);
+}
+
+int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
+	struct btrfs_root *root = BTRFS_I(dir)->root;
+	struct inode *inode = d_inode(dentry);
+	struct btrfs_root *dest = BTRFS_I(inode)->root;
+	struct btrfs_trans_handle *trans;
+	struct btrfs_block_rsv block_rsv;
+	u64 root_flags;
+	int ret;
+	int err;
+
+	/*
+	 * Don't allow to delete a subvolume with send in progress. This is
+	 * inside the inode lock so the error handling that has to drop the bit
+	 * again is not run concurrently.
+	 */
+	spin_lock(&dest->root_item_lock);
+	root_flags = btrfs_root_flags(&dest->root_item);
+	if (dest->send_in_progress == 0) {
+		btrfs_set_root_flags(&dest->root_item,
+				root_flags | BTRFS_ROOT_SUBVOL_DEAD);
+		spin_unlock(&dest->root_item_lock);
+	} else {
+		spin_unlock(&dest->root_item_lock);
+		btrfs_warn(fs_info,
+			   "attempt to delete subvolume %llu during send",
+			   dest->root_key.objectid);
+		return -EPERM;
+	}
+
+	down_write(&fs_info->subvol_sem);
+
+	err = may_destroy_subvol(dest);
+	if (err)
+		goto out_up_write;
+
+	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
+	/*
+	 * One for dir inode,
+	 * two for dir entries,
+	 * two for root ref/backref.
+	 */
+	err = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
+	if (err)
+		goto out_up_write;
+
+	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto out_release;
+	}
+	trans->block_rsv = &block_rsv;
+	trans->bytes_reserved = block_rsv.size;
+
+	btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
+
+	ret = btrfs_unlink_subvol(trans, root, dir,
+				dest->root_key.objectid,
+				dentry->d_name.name,
+				dentry->d_name.len);
+	if (ret) {
+		err = ret;
+		btrfs_abort_transaction(trans, ret);
+		goto out_end_trans;
+	}
+
+	btrfs_record_root_in_trans(trans, dest);
+
+	memset(&dest->root_item.drop_progress, 0,
+		sizeof(dest->root_item.drop_progress));
+	dest->root_item.drop_level = 0;
+	btrfs_set_root_refs(&dest->root_item, 0);
+
+	if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
+		ret = btrfs_insert_orphan_item(trans,
+					fs_info->tree_root,
+					dest->root_key.objectid);
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			err = ret;
+			goto out_end_trans;
+		}
+	}
+
+	ret = btrfs_uuid_tree_remove(trans, dest->root_item.uuid,
+				  BTRFS_UUID_KEY_SUBVOL,
+				  dest->root_key.objectid);
+	if (ret && ret != -ENOENT) {
+		btrfs_abort_transaction(trans, ret);
+		err = ret;
+		goto out_end_trans;
+	}
+	if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
+		ret = btrfs_uuid_tree_remove(trans,
+					  dest->root_item.received_uuid,
+					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
+					  dest->root_key.objectid);
+		if (ret && ret != -ENOENT) {
+			btrfs_abort_transaction(trans, ret);
+			err = ret;
+			goto out_end_trans;
+		}
+	}
+
+out_end_trans:
+	trans->block_rsv = NULL;
+	trans->bytes_reserved = 0;
+	ret = btrfs_end_transaction(trans);
+	if (ret && !err)
+		err = ret;
+	inode->i_flags |= S_DEAD;
+out_release:
+	btrfs_subvolume_release_metadata(fs_info, &block_rsv);
+out_up_write:
+	up_write(&fs_info->subvol_sem);
+	if (err) {
+		spin_lock(&dest->root_item_lock);
+		root_flags = btrfs_root_flags(&dest->root_item);
+		btrfs_set_root_flags(&dest->root_item,
+				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
+		spin_unlock(&dest->root_item_lock);
+	} else {
+		d_invalidate(dentry);
+		btrfs_prune_dentries(dest);
+		ASSERT(dest->send_in_progress == 0);
+
+		/* the last ref */
+		if (dest->ino_cache_inode) {
+			iput(dest->ino_cache_inode);
+			dest->ino_cache_inode = NULL;
+		}
+	}
+
+	return err;
+}
+
 static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
@@ -4329,7 +4434,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
 		return -ENOTEMPTY;
 	if (btrfs_ino(BTRFS_I(inode)) == BTRFS_FIRST_FREE_OBJECTID)
-		return -EPERM;
+		return btrfs_delete_subvolume(dir, dentry);
 
 	trans = __unlink_start_trans(dir);
 	if (IS_ERR(trans))
@@ -4441,7 +4546,6 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	int pending_del_slot = 0;
 	int extent_type = -1;
 	int ret;
-	int err = 0;
 	u64 ino = btrfs_ino(BTRFS_I(inode));
 	u64 bytes_deleted = 0;
 	bool be_nice = false;
@@ -4493,22 +4597,19 @@ search_again:
 	 * up a huge file in a single leaf.  Most of the time that
 	 * bytes_deleted is > 0, it will be huge by the time we get here
 	 */
-	if (be_nice && bytes_deleted > SZ_32M) {
-		if (btrfs_should_end_transaction(trans)) {
-			err = -EAGAIN;
-			goto error;
-		}
+	if (be_nice && bytes_deleted > SZ_32M &&
+	    btrfs_should_end_transaction(trans)) {
+		ret = -EAGAIN;
+		goto out;
 	}
 
-
 	path->leave_spinning = 1;
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-	if (ret < 0) {
-		err = ret;
+	if (ret < 0)
 		goto out;
-	}
 
 	if (ret > 0) {
+		ret = 0;
 		/* there are no items in the tree for us to truncate, we're
 		 * done
 		 */
@@ -4619,7 +4720,7 @@ search_again:
 				 * We have to bail so the last_size is set to
 				 * just before this extent.
 				 */
-				err = NEED_TRUNCATE_BLOCK;
+				ret = NEED_TRUNCATE_BLOCK;
 				break;
 			}
 
@@ -4658,7 +4759,10 @@ delete:
 						extent_num_bytes, 0,
 						btrfs_header_owner(leaf),
 						ino, extent_offset);
-			BUG_ON(ret);
+			if (ret) {
+				btrfs_abort_transaction(trans, ret);
+				break;
+			}
 			if (btrfs_should_throttle_delayed_refs(trans, fs_info))
 				btrfs_async_run_delayed_refs(fs_info,
 					trans->delayed_ref_updates * 2,
@@ -4686,7 +4790,7 @@ delete:
 						pending_del_nr);
 				if (ret) {
 					btrfs_abort_transaction(trans, ret);
-					goto error;
+					break;
 				}
 				pending_del_nr = 0;
 			}
@@ -4697,8 +4801,8 @@ delete:
 					trans->delayed_ref_updates = 0;
 					ret = btrfs_run_delayed_refs(trans,
 								   updates * 2);
-					if (ret && !err)
-						err = ret;
+					if (ret)
+						break;
 				}
 			}
 			/*
@@ -4706,8 +4810,8 @@ delete:
 			 * and let the transaction restart
 			 */
 			if (should_end) {
-				err = -EAGAIN;
-				goto error;
+				ret = -EAGAIN;
+				break;
 			}
 			goto search_again;
 		} else {
@@ -4715,32 +4819,37 @@ delete:
 		}
 	}
 out:
-	if (pending_del_nr) {
-		ret = btrfs_del_items(trans, root, path, pending_del_slot,
+	if (ret >= 0 && pending_del_nr) {
+		int err;
+
+		err = btrfs_del_items(trans, root, path, pending_del_slot,
 				      pending_del_nr);
-		if (ret)
-			btrfs_abort_transaction(trans, ret);
+		if (err) {
+			btrfs_abort_transaction(trans, err);
+			ret = err;
+		}
 	}
-error:
 	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
 		ASSERT(last_size >= new_size);
-		if (!err && last_size > new_size)
+		if (!ret && last_size > new_size)
 			last_size = new_size;
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
 	}
 
 	btrfs_free_path(path);
 
-	if (be_nice && bytes_deleted > SZ_32M) {
+	if (be_nice && bytes_deleted > SZ_32M && (ret >= 0 || ret == -EAGAIN)) {
 		unsigned long updates = trans->delayed_ref_updates;
+		int err;
+
 		if (updates) {
 			trans->delayed_ref_updates = 0;
-			ret = btrfs_run_delayed_refs(trans, updates * 2);
-			if (ret && !err)
-				err = ret;
+			err = btrfs_run_delayed_refs(trans, updates * 2);
+			if (err)
+				ret = err;
 		}
 	}
-	return err;
+	return ret;
 }
 
 /*
@@ -5082,30 +5191,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 			set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
 				&BTRFS_I(inode)->runtime_flags);
 
-		/*
-		 * 1 for the orphan item we're going to add
-		 * 1 for the orphan item deletion.
-		 */
-		trans = btrfs_start_transaction(root, 2);
-		if (IS_ERR(trans))
-			return PTR_ERR(trans);
-
-		/*
-		 * We need to do this in case we fail at _any_ point during the
-		 * actual truncate.  Once we do the truncate_setsize we could
-		 * invalidate pages which forces any outstanding ordered io to
-		 * be instantly completed which will give us extents that need
-		 * to be truncated.  If we fail to get an orphan inode down we
-		 * could have left over extents that were never meant to live,
-		 * so we need to guarantee from this point on that everything
-		 * will be consistent.
-		 */
-		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
-		btrfs_end_transaction(trans);
-		if (ret)
-			return ret;
-
-		/* we don't support swapfiles, so vmtruncate shouldn't fail */
 		truncate_setsize(inode, newsize);
 
 		/* Disable nonlocked read DIO to avoid the end less truncate */
@@ -5117,29 +5202,16 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		if (ret && inode->i_nlink) {
 			int err;
 
-			/* To get a stable disk_i_size */
-			err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
-			if (err) {
-				btrfs_orphan_del(NULL, BTRFS_I(inode));
-				return err;
-			}
-
 			/*
-			 * failed to truncate, disk_i_size is only adjusted down
-			 * as we remove extents, so it should represent the true
-			 * size of the inode, so reset the in memory size and
-			 * delete our orphan entry.
+			 * Truncate failed, so fix up the in-memory size. We
+			 * adjusted disk_i_size down as we removed extents, so
+			 * wait for disk_i_size to be stable and then update the
+			 * in-memory size to match.
 			 */
-			trans = btrfs_join_transaction(root);
-			if (IS_ERR(trans)) {
-				btrfs_orphan_del(NULL, BTRFS_I(inode));
-				return ret;
-			}
-			i_size_write(inode, BTRFS_I(inode)->disk_i_size);
-			err = btrfs_orphan_del(trans, BTRFS_I(inode));
+			err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
 			if (err)
-				btrfs_abort_transaction(trans, err);
-			btrfs_end_transaction(trans);
+				return err;
+			i_size_write(inode, BTRFS_I(inode)->disk_i_size);
 		}
 	}
 
@@ -5269,13 +5341,52 @@ static void evict_inode_truncate_pages(struct inode *inode)
 	spin_unlock(&io_tree->lock);
 }
 
+static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root,
+							struct btrfs_block_rsv *rsv,
+							u64 min_size)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
+	int failures = 0;
+
+	for (;;) {
+		struct btrfs_trans_handle *trans;
+		int ret;
+
+		ret = btrfs_block_rsv_refill(root, rsv, min_size,
+					     BTRFS_RESERVE_FLUSH_LIMIT);
+
+		if (ret && ++failures > 2) {
+			btrfs_warn(fs_info,
+				   "could not allocate space for a delete; will truncate on mount");
+			return ERR_PTR(-ENOSPC);
+		}
+
+		trans = btrfs_join_transaction(root);
+		if (IS_ERR(trans) || !ret)
+			return trans;
+
+		/*
+		 * Try to steal from the global reserve if there is space for
+		 * it.
+		 */
+		if (!btrfs_check_space_for_delayed_refs(trans, fs_info) &&
+		    !btrfs_block_rsv_migrate(global_rsv, rsv, min_size, 0))
+			return trans;
+
+		/* If not, commit and try again. */
+		ret = btrfs_commit_transaction(trans);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+}
+
 void btrfs_evict_inode(struct inode *inode)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_block_rsv *rsv, *global_rsv;
-	int steal_from_global = 0;
+	struct btrfs_block_rsv *rsv;
 	u64 min_size;
 	int ret;
 
@@ -5296,21 +5407,16 @@ void btrfs_evict_inode(struct inode *inode)
 	     btrfs_is_free_space_inode(BTRFS_I(inode))))
 		goto no_delete;
 
-	if (is_bad_inode(inode)) {
-		btrfs_orphan_del(NULL, BTRFS_I(inode));
+	if (is_bad_inode(inode))
 		goto no_delete;
-	}
 	/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
 	if (!special_file(inode->i_mode))
 		btrfs_wait_ordered_range(inode, 0, (u64)-1);
 
 	btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1);
 
-	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
-		BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-				 &BTRFS_I(inode)->runtime_flags));
+	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
 		goto no_delete;
-	}
 
 	if (inode->i_nlink > 0) {
 		BUG_ON(btrfs_root_refs(&root->root_item) != 0 &&
@@ -5319,130 +5425,63 @@ void btrfs_evict_inode(struct inode *inode)
 	}
 
 	ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode));
-	if (ret) {
-		btrfs_orphan_del(NULL, BTRFS_I(inode));
+	if (ret)
 		goto no_delete;
-	}
 
 	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
-	if (!rsv) {
-		btrfs_orphan_del(NULL, BTRFS_I(inode));
+	if (!rsv)
 		goto no_delete;
-	}
 	rsv->size = min_size;
 	rsv->failfast = 1;
-	global_rsv = &fs_info->global_block_rsv;
 
 	btrfs_i_size_write(BTRFS_I(inode), 0);
 
-	/*
-	 * This is a bit simpler than btrfs_truncate since we've already
-	 * reserved our space for our orphan item in the unlink, so we just
-	 * need to reserve some slack space in case we add bytes and update
-	 * inode item when doing the truncate.
-	 */
 	while (1) {
-		ret = btrfs_block_rsv_refill(root, rsv, min_size,
-					     BTRFS_RESERVE_FLUSH_LIMIT);
-
-		/*
-		 * Try and steal from the global reserve since we will
-		 * likely not use this space anyway, we want to try as
-		 * hard as possible to get this to work.
-		 */
-		if (ret)
-			steal_from_global++;
-		else
-			steal_from_global = 0;
-		ret = 0;
-
-		/*
-		 * steal_from_global == 0: we reserved stuff, hooray!
-		 * steal_from_global == 1: we didn't reserve stuff, boo!
-		 * steal_from_global == 2: we've committed, still not a lot of
-		 * room but maybe we'll have room in the global reserve this
-		 * time.
-		 * steal_from_global == 3: abandon all hope!
-		 */
-		if (steal_from_global > 2) {
-			btrfs_warn(fs_info,
-				   "Could not get space for a delete, will truncate on mount %d",
-				   ret);
-			btrfs_orphan_del(NULL, BTRFS_I(inode));
-			btrfs_free_block_rsv(fs_info, rsv);
-			goto no_delete;
-		}
-
-		trans = btrfs_join_transaction(root);
-		if (IS_ERR(trans)) {
-			btrfs_orphan_del(NULL, BTRFS_I(inode));
-			btrfs_free_block_rsv(fs_info, rsv);
-			goto no_delete;
-		}
-
-		/*
-		 * We can't just steal from the global reserve, we need to make
-		 * sure there is room to do it, if not we need to commit and try
-		 * again.
-		 */
-		if (steal_from_global) {
-			if (!btrfs_check_space_for_delayed_refs(trans, fs_info))
-				ret = btrfs_block_rsv_migrate(global_rsv, rsv,
-							      min_size, 0);
-			else
-				ret = -ENOSPC;
-		}
-
-		/*
-		 * Couldn't steal from the global reserve, we have too much
-		 * pending stuff built up, commit the transaction and try it
-		 * again.
-		 */
-		if (ret) {
-			ret = btrfs_commit_transaction(trans);
-			if (ret) {
-				btrfs_orphan_del(NULL, BTRFS_I(inode));
-				btrfs_free_block_rsv(fs_info, rsv);
-				goto no_delete;
-			}
-			continue;
-		} else {
-			steal_from_global = 0;
-		}
+		trans = evict_refill_and_join(root, rsv, min_size);
+		if (IS_ERR(trans))
+			goto free_rsv;
 
 		trans->block_rsv = rsv;
 
 		ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0);
-		if (ret != -ENOSPC && ret != -EAGAIN)
-			break;
-
 		trans->block_rsv = &fs_info->trans_block_rsv;
 		btrfs_end_transaction(trans);
-		trans = NULL;
 		btrfs_btree_balance_dirty(fs_info);
+		if (ret && ret != -ENOSPC && ret != -EAGAIN)
+			goto free_rsv;
+		else if (!ret)
+			break;
 	}
 
-	btrfs_free_block_rsv(fs_info, rsv);
-
 	/*
-	 * Errors here aren't a big deal, it just means we leave orphan items
-	 * in the tree.  They will be cleaned up on the next mount.
+	 * Errors here aren't a big deal, it just means we leave orphan items in
+	 * the tree. They will be cleaned up on the next mount. If the inode
+	 * number gets reused, cleanup deletes the orphan item without doing
+	 * anything, and unlink reuses the existing orphan item.
+	 *
+	 * If it turns out that we are dropping too many of these, we might want
+	 * to add a mechanism for retrying these after a commit.
 	 */
-	if (ret == 0) {
-		trans->block_rsv = root->orphan_block_rsv;
+	trans = evict_refill_and_join(root, rsv, min_size);
+	if (!IS_ERR(trans)) {
+		trans->block_rsv = rsv;
 		btrfs_orphan_del(trans, BTRFS_I(inode));
-	} else {
-		btrfs_orphan_del(NULL, BTRFS_I(inode));
+		trans->block_rsv = &fs_info->trans_block_rsv;
+		btrfs_end_transaction(trans);
 	}
 
-	trans->block_rsv = &fs_info->trans_block_rsv;
 	if (!(root == fs_info->tree_root ||
 	      root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID))
 		btrfs_return_ino(root, btrfs_ino(BTRFS_I(inode)));
 
-	btrfs_end_transaction(trans);
-	btrfs_btree_balance_dirty(fs_info);
+free_rsv:
+	btrfs_free_block_rsv(fs_info, rsv);
 no_delete:
+	/*
+	 * If we didn't successfully delete, the orphan item will still be in
+	 * the tree and we'll retry on the next mount. Again, we might also want
+	 * to retry these periodically in the future.
+	 */
 	btrfs_remove_delayed_node(BTRFS_I(inode));
 	clear_inode(inode);
 }
@@ -5618,69 +5657,6 @@ static void inode_tree_del(struct inode *inode)
 	}
 }
 
-void btrfs_invalidate_inodes(struct btrfs_root *root)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct rb_node *node;
-	struct rb_node *prev;
-	struct btrfs_inode *entry;
-	struct inode *inode;
-	u64 objectid = 0;
-
-	if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
-		WARN_ON(btrfs_root_refs(&root->root_item) != 0);
-
-	spin_lock(&root->inode_lock);
-again:
-	node = root->inode_tree.rb_node;
-	prev = NULL;
-	while (node) {
-		prev = node;
-		entry = rb_entry(node, struct btrfs_inode, rb_node);
-
-		if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
-			node = node->rb_left;
-		else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
-			node = node->rb_right;
-		else
-			break;
-	}
-	if (!node) {
-		while (prev) {
-			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) {
-				node = prev;
-				break;
-			}
-			prev = rb_next(prev);
-		}
-	}
-	while (node) {
-		entry = rb_entry(node, struct btrfs_inode, rb_node);
-		objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1;
-		inode = igrab(&entry->vfs_inode);
-		if (inode) {
-			spin_unlock(&root->inode_lock);
-			if (atomic_read(&inode->i_count) > 1)
-				d_prune_aliases(inode);
-			/*
-			 * btrfs_drop_inode will have it removed from
-			 * the inode cache when its usage count
-			 * hits zero.
-			 */
-			iput(inode);
-			cond_resched();
-			spin_lock(&root->inode_lock);
-			goto again;
-		}
-
-		if (cond_resched_lock(&root->inode_lock))
-			goto again;
-
-		node = rb_next(node);
-	}
-	spin_unlock(&root->inode_lock);
-}
 
 static int btrfs_init_locked_inode(struct inode *inode, void *p)
 {
@@ -5842,11 +5818,6 @@ static int btrfs_dentry_delete(const struct dentry *dentry)
 	return 0;
 }
 
-static void btrfs_dentry_release(struct dentry *dentry)
-{
-	kfree(dentry->d_fsdata);
-}
-
 static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
 				   unsigned int flags)
 {
@@ -5905,11 +5876,13 @@ static int btrfs_filldir(void *addr, int entries, struct dir_context *ctx)
 		struct dir_entry *entry = addr;
 		char *name = (char *)(entry + 1);
 
-		ctx->pos = entry->offset;
-		if (!dir_emit(ctx, name, entry->name_len, entry->ino,
-			      entry->type))
+		ctx->pos = get_unaligned(&entry->offset);
+		if (!dir_emit(ctx, name, get_unaligned(&entry->name_len),
+					 get_unaligned(&entry->ino),
+					 get_unaligned(&entry->type)))
 			return 1;
-		addr += sizeof(struct dir_entry) + entry->name_len;
+		addr += sizeof(struct dir_entry) +
+			get_unaligned(&entry->name_len);
 		ctx->pos++;
 	}
 	return 0;
@@ -5999,14 +5972,15 @@ again:
 		}
 
 		entry = addr;
-		entry->name_len = name_len;
+		put_unaligned(name_len, &entry->name_len);
 		name_ptr = (char *)(entry + 1);
 		read_extent_buffer(leaf, name_ptr, (unsigned long)(di + 1),
 				   name_len);
-		entry->type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
+		put_unaligned(btrfs_filetype_table[btrfs_dir_type(leaf, di)],
+				&entry->type);
 		btrfs_dir_item_key_to_cpu(leaf, di, &location);
-		entry->ino = location.objectid;
-		entry->offset = found_key.offset;
+		put_unaligned(location.objectid, &entry->ino);
+		put_unaligned(found_key.offset, &entry->offset);
 		entries++;
 		addr += sizeof(struct dir_entry) + name_len;
 		total_len += sizeof(struct dir_entry) + name_len;
@@ -6259,7 +6233,7 @@ static void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
 			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
 	}
 
-	btrfs_update_iflags(inode);
+	btrfs_sync_inode_flags_to_i_flags(inode);
 }
 
 static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
@@ -6575,8 +6549,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 		goto out_unlock_inode;
 	} else {
 		btrfs_update_inode(trans, root, inode);
-		unlock_new_inode(inode);
-		d_instantiate(dentry, inode);
+		d_instantiate_new(dentry, inode);
 	}
 
 out_unlock:
@@ -6652,8 +6625,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 		goto out_unlock_inode;
 
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
@@ -6696,8 +6668,9 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	 * 2 items for inode and inode ref
 	 * 2 items for dir items
 	 * 1 item for parent inode
+	 * 1 item for orphan item deletion if O_TMPFILE
 	 */
-	trans = btrfs_start_transaction(root, 5);
+	trans = btrfs_start_transaction(root, inode->i_nlink ? 5 : 6);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
 		trans = NULL;
@@ -6798,12 +6771,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (err)
 		goto out_fail_inode;
 
-	d_instantiate(dentry, inode);
-	/*
-	 * mkdir is special.  We're unlocking after we call d_instantiate
-	 * to avoid a race with nfsd calling d_instantiate.
-	 */
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 	drop_on_err = 0;
 
 out_fail:
@@ -7079,7 +7047,7 @@ insert:
 
 	err = 0;
 	write_lock(&em_tree->lock);
-	err = btrfs_add_extent_mapping(em_tree, &em, start, len);
+	err = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
 	write_unlock(&em_tree->lock);
 out:
 
@@ -7364,6 +7332,14 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	    btrfs_file_extent_other_encoding(leaf, fi))
 		goto out;
 
+	/*
+	 * Do the same check as in btrfs_cross_ref_exist but without the
+	 * unnecessary search.
+	 */
+	if (btrfs_file_extent_generation(leaf, fi) <=
+	    btrfs_root_last_snapshot(&root->root_item))
+		goto out;
+
 	backref_offset = btrfs_file_extent_offset(leaf, fi);
 
 	if (orig_start) {
@@ -7564,6 +7540,125 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 	return em;
 }
 
+
+static int btrfs_get_blocks_direct_read(struct extent_map *em,
+					struct buffer_head *bh_result,
+					struct inode *inode,
+					u64 start, u64 len)
+{
+	if (em->block_start == EXTENT_MAP_HOLE ||
+			test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		return -ENOENT;
+
+	len = min(len, em->len - (start - em->start));
+
+	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
+		inode->i_blkbits;
+	bh_result->b_size = len;
+	bh_result->b_bdev = em->bdev;
+	set_buffer_mapped(bh_result);
+
+	return 0;
+}
+
+static int btrfs_get_blocks_direct_write(struct extent_map **map,
+					 struct buffer_head *bh_result,
+					 struct inode *inode,
+					 struct btrfs_dio_data *dio_data,
+					 u64 start, u64 len)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct extent_map *em = *map;
+	int ret = 0;
+
+	/*
+	 * We don't allocate a new extent in the following cases
+	 *
+	 * 1) The inode is marked as NODATACOW. In this case we'll just use the
+	 * existing extent.
+	 * 2) The extent is marked as PREALLOC. We're good to go here and can
+	 * just use the extent.
+	 *
+	 */
+	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
+	     em->block_start != EXTENT_MAP_HOLE)) {
+		int type;
+		u64 block_start, orig_start, orig_block_len, ram_bytes;
+
+		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+			type = BTRFS_ORDERED_PREALLOC;
+		else
+			type = BTRFS_ORDERED_NOCOW;
+		len = min(len, em->len - (start - em->start));
+		block_start = em->block_start + (start - em->start);
+
+		if (can_nocow_extent(inode, start, &len, &orig_start,
+				     &orig_block_len, &ram_bytes) == 1 &&
+		    btrfs_inc_nocow_writers(fs_info, block_start)) {
+			struct extent_map *em2;
+
+			em2 = btrfs_create_dio_extent(inode, start, len,
+						      orig_start, block_start,
+						      len, orig_block_len,
+						      ram_bytes, type);
+			btrfs_dec_nocow_writers(fs_info, block_start);
+			if (type == BTRFS_ORDERED_PREALLOC) {
+				free_extent_map(em);
+				*map = em = em2;
+			}
+
+			if (em2 && IS_ERR(em2)) {
+				ret = PTR_ERR(em2);
+				goto out;
+			}
+			/*
+			 * For inode marked NODATACOW or extent marked PREALLOC,
+			 * use the existing or preallocated extent, so does not
+			 * need to adjust btrfs_space_info's bytes_may_use.
+			 */
+			btrfs_free_reserved_data_space_noquota(inode, start,
+							       len);
+			goto skip_cow;
+		}
+	}
+
+	/* this will cow the extent */
+	len = bh_result->b_size;
+	free_extent_map(em);
+	*map = em = btrfs_new_extent_direct(inode, start, len);
+	if (IS_ERR(em)) {
+		ret = PTR_ERR(em);
+		goto out;
+	}
+
+	len = min(len, em->len - (start - em->start));
+
+skip_cow:
+	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
+		inode->i_blkbits;
+	bh_result->b_size = len;
+	bh_result->b_bdev = em->bdev;
+	set_buffer_mapped(bh_result);
+
+	if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		set_buffer_new(bh_result);
+
+	/*
+	 * Need to update the i_size under the extent lock so buffered
+	 * readers will get the updated i_size when we unlock.
+	 */
+	if (!dio_data->overwrite && start + len > i_size_read(inode))
+		i_size_write(inode, start + len);
+
+	WARN_ON(dio_data->reserve < len);
+	dio_data->reserve -= len;
+	dio_data->unsubmitted_oe_range_end = start + len;
+	current->journal_info = dio_data;
+out:
+	return ret;
+}
+
 static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
 {
@@ -7632,116 +7727,36 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		goto unlock_err;
 	}
 
-	/* Just a good old fashioned hole, return */
-	if (!create && (em->block_start == EXTENT_MAP_HOLE ||
-			test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
-		free_extent_map(em);
-		goto unlock_err;
-	}
-
-	/*
-	 * We don't allocate a new extent in the following cases
-	 *
-	 * 1) The inode is marked as NODATACOW.  In this case we'll just use the
-	 * existing extent.
-	 * 2) The extent is marked as PREALLOC.  We're good to go here and can
-	 * just use the extent.
-	 *
-	 */
-	if (!create) {
-		len = min(len, em->len - (start - em->start));
-		lockstart = start + len;
-		goto unlock;
-	}
-
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
-	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
-	     em->block_start != EXTENT_MAP_HOLE)) {
-		int type;
-		u64 block_start, orig_start, orig_block_len, ram_bytes;
-
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
-			type = BTRFS_ORDERED_PREALLOC;
-		else
-			type = BTRFS_ORDERED_NOCOW;
-		len = min(len, em->len - (start - em->start));
-		block_start = em->block_start + (start - em->start);
-
-		if (can_nocow_extent(inode, start, &len, &orig_start,
-				     &orig_block_len, &ram_bytes) == 1 &&
-		    btrfs_inc_nocow_writers(fs_info, block_start)) {
-			struct extent_map *em2;
-
-			em2 = btrfs_create_dio_extent(inode, start, len,
-						      orig_start, block_start,
-						      len, orig_block_len,
-						      ram_bytes, type);
-			btrfs_dec_nocow_writers(fs_info, block_start);
-			if (type == BTRFS_ORDERED_PREALLOC) {
-				free_extent_map(em);
-				em = em2;
-			}
-			if (em2 && IS_ERR(em2)) {
-				ret = PTR_ERR(em2);
-				goto unlock_err;
-			}
-			/*
-			 * For inode marked NODATACOW or extent marked PREALLOC,
-			 * use the existing or preallocated extent, so does not
-			 * need to adjust btrfs_space_info's bytes_may_use.
-			 */
-			btrfs_free_reserved_data_space_noquota(inode,
-					start, len);
-			goto unlock;
-		}
-	}
-
-	/*
-	 * this will cow the extent, reset the len in case we changed
-	 * it above
-	 */
-	len = bh_result->b_size;
-	free_extent_map(em);
-	em = btrfs_new_extent_direct(inode, start, len);
-	if (IS_ERR(em)) {
-		ret = PTR_ERR(em);
-		goto unlock_err;
-	}
-	len = min(len, em->len - (start - em->start));
-unlock:
-	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
-		inode->i_blkbits;
-	bh_result->b_size = len;
-	bh_result->b_bdev = em->bdev;
-	set_buffer_mapped(bh_result);
 	if (create) {
-		if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
-			set_buffer_new(bh_result);
+		ret = btrfs_get_blocks_direct_write(&em, bh_result, inode,
+						    dio_data, start, len);
+		if (ret < 0)
+			goto unlock_err;
 
+		/* clear and unlock the entire range */
+		clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
+				 unlock_bits, 1, 0, &cached_state);
+	} else {
+		ret = btrfs_get_blocks_direct_read(em, bh_result, inode,
+						   start, len);
+		/* Can be negative only if we read from a hole */
+		if (ret < 0) {
+			ret = 0;
+			free_extent_map(em);
+			goto unlock_err;
+		}
 		/*
-		 * Need to update the i_size under the extent lock so buffered
-		 * readers will get the updated i_size when we unlock.
+		 * We need to unlock only the end area that we aren't using.
+		 * The rest is going to be unlocked by the endio routine.
 		 */
-		if (!dio_data->overwrite && start + len > i_size_read(inode))
-			i_size_write(inode, start + len);
-
-		WARN_ON(dio_data->reserve < len);
-		dio_data->reserve -= len;
-		dio_data->unsubmitted_oe_range_end = start + len;
-		current->journal_info = dio_data;
-	}
-
-	/*
-	 * In the case of write we need to clear and unlock the entire range,
-	 * in the case of read we need to unlock only the end area that we
-	 * aren't using if there is any left over space.
-	 */
-	if (lockstart < lockend) {
-		clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
-				 lockend, unlock_bits, 1, 0,
-				 &cached_state);
-	} else {
-		free_extent_state(cached_state);
+		lockstart = start + bh_result->b_size;
+		if (lockstart < lockend) {
+			clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
+					 lockend, unlock_bits, 1, 0,
+					 &cached_state);
+		} else {
+			free_extent_state(cached_state);
+		}
 	}
 
 	free_extent_map(em);
@@ -8127,7 +8142,6 @@ static void __endio_write_update_ordered(struct inode *inode,
 	u64 ordered_offset = offset;
 	u64 ordered_bytes = bytes;
 	u64 last_offset;
-	int ret;
 
 	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		wq = fs_info->endio_freespace_worker;
@@ -8137,32 +8151,31 @@ static void __endio_write_update_ordered(struct inode *inode,
 		func = btrfs_endio_write_helper;
 	}
 
-again:
-	last_offset = ordered_offset;
-	ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
-						   &ordered_offset,
-						   ordered_bytes,
-						   uptodate);
-	if (!ret)
-		goto out_test;
-
-	btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL);
-	btrfs_queue_work(wq, &ordered->work);
-out_test:
-	/*
-	 * If btrfs_dec_test_ordered_pending does not find any ordered extent
-	 * in the range, we can exit.
-	 */
-	if (ordered_offset == last_offset)
-		return;
-	/*
-	 * our bio might span multiple ordered extents.  If we haven't
-	 * completed the accounting for the whole dio, go back and try again
-	 */
-	if (ordered_offset < offset + bytes) {
-		ordered_bytes = offset + bytes - ordered_offset;
-		ordered = NULL;
-		goto again;
+	while (ordered_offset < offset + bytes) {
+		last_offset = ordered_offset;
+		if (btrfs_dec_test_first_ordered_pending(inode, &ordered,
+							   &ordered_offset,
+							   ordered_bytes,
+							   uptodate)) {
+			btrfs_init_work(&ordered->work, func,
+					finish_ordered_fn,
+					NULL, NULL);
+			btrfs_queue_work(wq, &ordered->work);
+		}
+		/*
+		 * If btrfs_dec_test_ordered_pending does not find any ordered
+		 * extent in the range, we can exit.
+		 */
+		if (ordered_offset == last_offset)
+			return;
+		/*
+		 * Our bio might span multiple ordered extents. In this case
+		 * we keep goin until we have accounted the whole dio.
+		 */
+		if (ordered_offset < offset + bytes) {
+			ordered_bytes = offset + bytes - ordered_offset;
+			ordered = NULL;
+		}
 	}
 }
 
@@ -8701,29 +8714,19 @@ static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
 static int btrfs_writepages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
-	struct extent_io_tree *tree;
-
-	tree = &BTRFS_I(mapping->host)->io_tree;
-	return extent_writepages(tree, mapping, wbc);
+	return extent_writepages(mapping, wbc);
 }
 
 static int
 btrfs_readpages(struct file *file, struct address_space *mapping,
 		struct list_head *pages, unsigned nr_pages)
 {
-	struct extent_io_tree *tree;
-	tree = &BTRFS_I(mapping->host)->io_tree;
-	return extent_readpages(tree, mapping, pages, nr_pages);
+	return extent_readpages(mapping, pages, nr_pages);
 }
+
 static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
 {
-	struct extent_io_tree *tree;
-	struct extent_map_tree *map;
-	int ret;
-
-	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	map = &BTRFS_I(page->mapping->host)->extent_tree;
-	ret = try_release_extent_mapping(map, tree, page, gfp_flags);
+	int ret = try_release_extent_mapping(page, gfp_flags);
 	if (ret == 1) {
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
@@ -8864,8 +8867,8 @@ again:
  *
  * We are not allowed to take the i_mutex here so we have to play games to
  * protect against truncate races as the page could now be beyond EOF.  Because
- * vmtruncate() writes the inode size before removing pages, once we have the
- * page lock we can determine safely if the page is beyond EOF. If it is not
+ * truncate_setsize() writes the inode size before removing pages, once we have
+ * the page lock we can determine safely if the page is beyond EOF. If it is not
  * beyond EOF, then the page is guaranteed safe against truncation until we
  * unlock the page.
  */
@@ -9027,8 +9030,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_block_rsv *rsv;
-	int ret = 0;
-	int err = 0;
+	int ret;
 	struct btrfs_trans_handle *trans;
 	u64 mask = fs_info->sectorsize - 1;
 	u64 min_size = btrfs_calc_trunc_metadata_size(fs_info, 1);
@@ -9041,39 +9043,31 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
 	}
 
 	/*
-	 * Yes ladies and gentlemen, this is indeed ugly.  The fact is we have
-	 * 3 things going on here
-	 *
-	 * 1) We need to reserve space for our orphan item and the space to
-	 * delete our orphan item.  Lord knows we don't want to have a dangling
-	 * orphan item because we didn't reserve space to remove it.
+	 * Yes ladies and gentlemen, this is indeed ugly.  We have a couple of
+	 * things going on here:
 	 *
-	 * 2) We need to reserve space to update our inode.
+	 * 1) We need to reserve space to update our inode.
 	 *
-	 * 3) We need to have something to cache all the space that is going to
+	 * 2) We need to have something to cache all the space that is going to
 	 * be free'd up by the truncate operation, but also have some slack
 	 * space reserved in case it uses space during the truncate (thank you
 	 * very much snapshotting).
 	 *
-	 * And we need these to all be separate.  The fact is we can use a lot of
+	 * And we need these to be separate.  The fact is we can use a lot of
 	 * space doing the truncate, and we have no earthly idea how much space
 	 * we will use, so we need the truncate reservation to be separate so it
-	 * doesn't end up using space reserved for updating the inode or
-	 * removing the orphan item.  We also need to be able to stop the
-	 * transaction and start a new one, which means we need to be able to
-	 * update the inode several times, and we have no idea of knowing how
-	 * many times that will be, so we can't just reserve 1 item for the
-	 * entirety of the operation, so that has to be done separately as well.
-	 * Then there is the orphan item, which does indeed need to be held on
-	 * to for the whole operation, and we need nobody to touch this reserved
-	 * space except the orphan code.
+	 * doesn't end up using space reserved for updating the inode.  We also
+	 * need to be able to stop the transaction and start a new one, which
+	 * means we need to be able to update the inode several times, and we
+	 * have no idea of knowing how many times that will be, so we can't just
+	 * reserve 1 item for the entirety of the operation, so that has to be
+	 * done separately as well.
 	 *
 	 * So that leaves us with
 	 *
-	 * 1) root->orphan_block_rsv - for the orphan deletion.
-	 * 2) rsv - for the truncate reservation, which we will steal from the
+	 * 1) rsv - for the truncate reservation, which we will steal from the
 	 * transaction reservation.
-	 * 3) fs_info->trans_block_rsv - this will have 1 items worth left for
+	 * 2) fs_info->trans_block_rsv - this will have 1 items worth left for
 	 * updating the inode.
 	 */
 	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
@@ -9088,7 +9082,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
 	 */
 	trans = btrfs_start_transaction(root, 2);
 	if (IS_ERR(trans)) {
-		err = PTR_ERR(trans);
+		ret = PTR_ERR(trans);
 		goto out;
 	}
 
@@ -9112,23 +9106,19 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
 						 inode->i_size,
 						 BTRFS_EXTENT_DATA_KEY);
 		trans->block_rsv = &fs_info->trans_block_rsv;
-		if (ret != -ENOSPC && ret != -EAGAIN) {
-			err = ret;
+		if (ret != -ENOSPC && ret != -EAGAIN)
 			break;
-		}
 
 		ret = btrfs_update_inode(trans, root, inode);
-		if (ret) {
-			err = ret;
+		if (ret)
 			break;
-		}
 
 		btrfs_end_transaction(trans);
 		btrfs_btree_balance_dirty(fs_info);
 
 		trans = btrfs_start_transaction(root, 2);
 		if (IS_ERR(trans)) {
-			ret = err = PTR_ERR(trans);
+			ret = PTR_ERR(trans);
 			trans = NULL;
 			break;
 		}
@@ -9161,29 +9151,23 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
 		btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
 	}
 
-	if (ret == 0 && inode->i_nlink > 0) {
-		trans->block_rsv = root->orphan_block_rsv;
-		ret = btrfs_orphan_del(trans, BTRFS_I(inode));
-		if (ret)
-			err = ret;
-	}
-
 	if (trans) {
+		int ret2;
+
 		trans->block_rsv = &fs_info->trans_block_rsv;
-		ret = btrfs_update_inode(trans, root, inode);
-		if (ret && !err)
-			err = ret;
+		ret2 = btrfs_update_inode(trans, root, inode);
+		if (ret2 && !ret)
+			ret = ret2;
 
-		ret = btrfs_end_transaction(trans);
+		ret2 = btrfs_end_transaction(trans);
+		if (ret2 && !ret)
+			ret = ret2;
 		btrfs_btree_balance_dirty(fs_info);
 	}
 out:
 	btrfs_free_block_rsv(fs_info, rsv);
 
-	if (ret && !err)
-		err = ret;
-
-	return err;
+	return ret;
 }
 
 /*
@@ -9319,13 +9303,6 @@ void btrfs_destroy_inode(struct inode *inode)
 	if (!root)
 		goto free;
 
-	if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-		     &BTRFS_I(inode)->runtime_flags)) {
-		btrfs_info(fs_info, "inode %llu still on the orphan list",
-			   btrfs_ino(BTRFS_I(inode)));
-		atomic_dec(&root->orphan_inodes);
-	}
-
 	while (1) {
 		ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1);
 		if (!ordered)
@@ -9959,6 +9936,13 @@ static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry,
 	return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
+struct btrfs_delalloc_work {
+	struct inode *inode;
+	struct completion completion;
+	struct list_head list;
+	struct btrfs_work work;
+};
+
 static void btrfs_run_delalloc_work(struct btrfs_work *work)
 {
 	struct btrfs_delalloc_work *delalloc_work;
@@ -9972,15 +9956,11 @@ static void btrfs_run_delalloc_work(struct btrfs_work *work)
 				&BTRFS_I(inode)->runtime_flags))
 		filemap_flush(inode->i_mapping);
 
-	if (delalloc_work->delay_iput)
-		btrfs_add_delayed_iput(inode);
-	else
-		iput(inode);
+	iput(inode);
 	complete(&delalloc_work->completion);
 }
 
-struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
-						    int delay_iput)
+static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode)
 {
 	struct btrfs_delalloc_work *work;
 
@@ -9991,7 +9971,6 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 	init_completion(&work->completion);
 	INIT_LIST_HEAD(&work->list);
 	work->inode = inode;
-	work->delay_iput = delay_iput;
 	WARN_ON_ONCE(!inode);
 	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
 			btrfs_run_delalloc_work, NULL, NULL);
@@ -9999,18 +9978,11 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 	return work;
 }
 
-void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
-{
-	wait_for_completion(&work->completion);
-	kfree(work);
-}
-
 /*
  * some fairly slow code that needs optimization. This walks the list
  * of all the inodes with pending delalloc and forces them to disk.
  */
-static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
-				   int nr)
+static int start_delalloc_inodes(struct btrfs_root *root, int nr)
 {
 	struct btrfs_inode *binode;
 	struct inode *inode;
@@ -10038,12 +10010,9 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
 		}
 		spin_unlock(&root->delalloc_lock);
 
-		work = btrfs_alloc_delalloc_work(inode, delay_iput);
+		work = btrfs_alloc_delalloc_work(inode);
 		if (!work) {
-			if (delay_iput)
-				btrfs_add_delayed_iput(inode);
-			else
-				iput(inode);
+			iput(inode);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -10061,10 +10030,11 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
 out:
 	list_for_each_entry_safe(work, next, &works, list) {
 		list_del_init(&work->list);
-		btrfs_wait_and_free_delalloc_work(work);
+		wait_for_completion(&work->completion);
+		kfree(work);
 	}
 
-	if (!list_empty_careful(&splice)) {
+	if (!list_empty(&splice)) {
 		spin_lock(&root->delalloc_lock);
 		list_splice_tail(&splice, &root->delalloc_inodes);
 		spin_unlock(&root->delalloc_lock);
@@ -10073,7 +10043,7 @@ out:
 	return ret;
 }
 
-int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
+int btrfs_start_delalloc_inodes(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
@@ -10081,14 +10051,13 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
 		return -EROFS;
 
-	ret = __start_delalloc_inodes(root, delay_iput, -1);
+	ret = start_delalloc_inodes(root, -1);
 	if (ret > 0)
 		ret = 0;
 	return ret;
 }
 
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
-			       int nr)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
@@ -10111,7 +10080,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
 			       &fs_info->delalloc_roots);
 		spin_unlock(&fs_info->delalloc_root_lock);
 
-		ret = __start_delalloc_inodes(root, delay_iput, nr);
+		ret = start_delalloc_inodes(root, nr);
 		btrfs_put_fs_root(root);
 		if (ret < 0)
 			goto out;
@@ -10126,7 +10095,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
 
 	ret = 0;
 out:
-	if (!list_empty_careful(&splice)) {
+	if (!list_empty(&splice)) {
 		spin_lock(&fs_info->delalloc_root_lock);
 		list_splice_tail(&splice, &fs_info->delalloc_roots);
 		spin_unlock(&fs_info->delalloc_root_lock);
@@ -10246,8 +10215,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		goto out_unlock_inode;
 	}
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
@@ -10665,5 +10633,4 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
 
 const struct dentry_operations btrfs_dentry_operations = {
 	.d_delete	= btrfs_dentry_delete,
-	.d_release	= btrfs_dentry_release,
 };
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 632e26d6f7ce..d29992f7dc63 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -93,20 +93,22 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 		       int no_time_update);
 
 /* Mask out flags that are inappropriate for the given type of inode. */
-static unsigned int btrfs_mask_flags(umode_t mode, unsigned int flags)
+static unsigned int btrfs_mask_fsflags_for_type(struct inode *inode,
+		unsigned int flags)
 {
-	if (S_ISDIR(mode))
+	if (S_ISDIR(inode->i_mode))
 		return flags;
-	else if (S_ISREG(mode))
+	else if (S_ISREG(inode->i_mode))
 		return flags & ~FS_DIRSYNC_FL;
 	else
 		return flags & (FS_NODUMP_FL | FS_NOATIME_FL);
 }
 
 /*
- * Export inode flags to the format expected by the FS_IOC_GETFLAGS ioctl.
+ * Export internal inode flags to the format expected by the FS_IOC_GETFLAGS
+ * ioctl.
  */
-static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
+static unsigned int btrfs_inode_flags_to_fsflags(unsigned int flags)
 {
 	unsigned int iflags = 0;
 
@@ -136,20 +138,20 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
 /*
  * Update inode->i_flags based on the btrfs internal flags.
  */
-void btrfs_update_iflags(struct inode *inode)
+void btrfs_sync_inode_flags_to_i_flags(struct inode *inode)
 {
-	struct btrfs_inode *ip = BTRFS_I(inode);
+	struct btrfs_inode *binode = BTRFS_I(inode);
 	unsigned int new_fl = 0;
 
-	if (ip->flags & BTRFS_INODE_SYNC)
+	if (binode->flags & BTRFS_INODE_SYNC)
 		new_fl |= S_SYNC;
-	if (ip->flags & BTRFS_INODE_IMMUTABLE)
+	if (binode->flags & BTRFS_INODE_IMMUTABLE)
 		new_fl |= S_IMMUTABLE;
-	if (ip->flags & BTRFS_INODE_APPEND)
+	if (binode->flags & BTRFS_INODE_APPEND)
 		new_fl |= S_APPEND;
-	if (ip->flags & BTRFS_INODE_NOATIME)
+	if (binode->flags & BTRFS_INODE_NOATIME)
 		new_fl |= S_NOATIME;
-	if (ip->flags & BTRFS_INODE_DIRSYNC)
+	if (binode->flags & BTRFS_INODE_DIRSYNC)
 		new_fl |= S_DIRSYNC;
 
 	set_mask_bits(&inode->i_flags,
@@ -159,15 +161,16 @@ void btrfs_update_iflags(struct inode *inode)
 
 static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
 {
-	struct btrfs_inode *ip = BTRFS_I(file_inode(file));
-	unsigned int flags = btrfs_flags_to_ioctl(ip->flags);
+	struct btrfs_inode *binode = BTRFS_I(file_inode(file));
+	unsigned int flags = btrfs_inode_flags_to_fsflags(binode->flags);
 
 	if (copy_to_user(arg, &flags, sizeof(flags)))
 		return -EFAULT;
 	return 0;
 }
 
-static int check_flags(unsigned int flags)
+/* Check if @flags are a supported and valid set of FS_*_FL flags */
+static int check_fsflags(unsigned int flags)
 {
 	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
 		      FS_NOATIME_FL | FS_NODUMP_FL | \
@@ -186,13 +189,13 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_inode *ip = BTRFS_I(inode);
-	struct btrfs_root *root = ip->root;
+	struct btrfs_inode *binode = BTRFS_I(inode);
+	struct btrfs_root *root = binode->root;
 	struct btrfs_trans_handle *trans;
-	unsigned int flags, oldflags;
+	unsigned int fsflags, old_fsflags;
 	int ret;
-	u64 ip_oldflags;
-	unsigned int i_oldflags;
+	u64 old_flags;
+	unsigned int old_i_flags;
 	umode_t mode;
 
 	if (!inode_owner_or_capable(inode))
@@ -201,10 +204,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	if (btrfs_root_readonly(root))
 		return -EROFS;
 
-	if (copy_from_user(&flags, arg, sizeof(flags)))
+	if (copy_from_user(&fsflags, arg, sizeof(fsflags)))
 		return -EFAULT;
 
-	ret = check_flags(flags);
+	ret = check_fsflags(fsflags);
 	if (ret)
 		return ret;
 
@@ -214,44 +217,44 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 
 	inode_lock(inode);
 
-	ip_oldflags = ip->flags;
-	i_oldflags = inode->i_flags;
+	old_flags = binode->flags;
+	old_i_flags = inode->i_flags;
 	mode = inode->i_mode;
 
-	flags = btrfs_mask_flags(inode->i_mode, flags);
-	oldflags = btrfs_flags_to_ioctl(ip->flags);
-	if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
+	fsflags = btrfs_mask_fsflags_for_type(inode, fsflags);
+	old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags);
+	if ((fsflags ^ old_fsflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
 		if (!capable(CAP_LINUX_IMMUTABLE)) {
 			ret = -EPERM;
 			goto out_unlock;
 		}
 	}
 
-	if (flags & FS_SYNC_FL)
-		ip->flags |= BTRFS_INODE_SYNC;
+	if (fsflags & FS_SYNC_FL)
+		binode->flags |= BTRFS_INODE_SYNC;
 	else
-		ip->flags &= ~BTRFS_INODE_SYNC;
-	if (flags & FS_IMMUTABLE_FL)
-		ip->flags |= BTRFS_INODE_IMMUTABLE;
+		binode->flags &= ~BTRFS_INODE_SYNC;
+	if (fsflags & FS_IMMUTABLE_FL)
+		binode->flags |= BTRFS_INODE_IMMUTABLE;
 	else
-		ip->flags &= ~BTRFS_INODE_IMMUTABLE;
-	if (flags & FS_APPEND_FL)
-		ip->flags |= BTRFS_INODE_APPEND;
+		binode->flags &= ~BTRFS_INODE_IMMUTABLE;
+	if (fsflags & FS_APPEND_FL)
+		binode->flags |= BTRFS_INODE_APPEND;
 	else
-		ip->flags &= ~BTRFS_INODE_APPEND;
-	if (flags & FS_NODUMP_FL)
-		ip->flags |= BTRFS_INODE_NODUMP;
+		binode->flags &= ~BTRFS_INODE_APPEND;
+	if (fsflags & FS_NODUMP_FL)
+		binode->flags |= BTRFS_INODE_NODUMP;
 	else
-		ip->flags &= ~BTRFS_INODE_NODUMP;
-	if (flags & FS_NOATIME_FL)
-		ip->flags |= BTRFS_INODE_NOATIME;
+		binode->flags &= ~BTRFS_INODE_NODUMP;
+	if (fsflags & FS_NOATIME_FL)
+		binode->flags |= BTRFS_INODE_NOATIME;
 	else
-		ip->flags &= ~BTRFS_INODE_NOATIME;
-	if (flags & FS_DIRSYNC_FL)
-		ip->flags |= BTRFS_INODE_DIRSYNC;
+		binode->flags &= ~BTRFS_INODE_NOATIME;
+	if (fsflags & FS_DIRSYNC_FL)
+		binode->flags |= BTRFS_INODE_DIRSYNC;
 	else
-		ip->flags &= ~BTRFS_INODE_DIRSYNC;
-	if (flags & FS_NOCOW_FL) {
+		binode->flags &= ~BTRFS_INODE_DIRSYNC;
+	if (fsflags & FS_NOCOW_FL) {
 		if (S_ISREG(mode)) {
 			/*
 			 * It's safe to turn csums off here, no extents exist.
@@ -259,10 +262,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 			 * status of the file and will not set it.
 			 */
 			if (inode->i_size == 0)
-				ip->flags |= BTRFS_INODE_NODATACOW
-					   | BTRFS_INODE_NODATASUM;
+				binode->flags |= BTRFS_INODE_NODATACOW
+					      | BTRFS_INODE_NODATASUM;
 		} else {
-			ip->flags |= BTRFS_INODE_NODATACOW;
+			binode->flags |= BTRFS_INODE_NODATACOW;
 		}
 	} else {
 		/*
@@ -270,10 +273,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		 */
 		if (S_ISREG(mode)) {
 			if (inode->i_size == 0)
-				ip->flags &= ~(BTRFS_INODE_NODATACOW
+				binode->flags &= ~(BTRFS_INODE_NODATACOW
 				             | BTRFS_INODE_NODATASUM);
 		} else {
-			ip->flags &= ~BTRFS_INODE_NODATACOW;
+			binode->flags &= ~BTRFS_INODE_NODATACOW;
 		}
 	}
 
@@ -282,18 +285,18 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	 * flag may be changed automatically if compression code won't make
 	 * things smaller.
 	 */
-	if (flags & FS_NOCOMP_FL) {
-		ip->flags &= ~BTRFS_INODE_COMPRESS;
-		ip->flags |= BTRFS_INODE_NOCOMPRESS;
+	if (fsflags & FS_NOCOMP_FL) {
+		binode->flags &= ~BTRFS_INODE_COMPRESS;
+		binode->flags |= BTRFS_INODE_NOCOMPRESS;
 
 		ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
 		if (ret && ret != -ENODATA)
 			goto out_drop;
-	} else if (flags & FS_COMPR_FL) {
+	} else if (fsflags & FS_COMPR_FL) {
 		const char *comp;
 
-		ip->flags |= BTRFS_INODE_COMPRESS;
-		ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
+		binode->flags |= BTRFS_INODE_COMPRESS;
+		binode->flags &= ~BTRFS_INODE_NOCOMPRESS;
 
 		comp = btrfs_compress_type2str(fs_info->compress_type);
 		if (!comp || comp[0] == 0)
@@ -308,7 +311,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
 		if (ret && ret != -ENODATA)
 			goto out_drop;
-		ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
+		binode->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
 	}
 
 	trans = btrfs_start_transaction(root, 1);
@@ -317,7 +320,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		goto out_drop;
 	}
 
-	btrfs_update_iflags(inode);
+	btrfs_sync_inode_flags_to_i_flags(inode);
 	inode_inc_iversion(inode);
 	inode->i_ctime = current_time(inode);
 	ret = btrfs_update_inode(trans, root, inode);
@@ -325,8 +328,8 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	btrfs_end_transaction(trans);
  out_drop:
 	if (ret) {
-		ip->flags = ip_oldflags;
-		inode->i_flags = i_oldflags;
+		binode->flags = old_flags;
+		inode->i_flags = old_i_flags;
 	}
 
  out_unlock:
@@ -335,6 +338,148 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	return ret;
 }
 
+/*
+ * Translate btrfs internal inode flags to xflags as expected by the
+ * FS_IOC_FSGETXATT ioctl. Filter only the supported ones, unknown flags are
+ * silently dropped.
+ */
+static unsigned int btrfs_inode_flags_to_xflags(unsigned int flags)
+{
+	unsigned int xflags = 0;
+
+	if (flags & BTRFS_INODE_APPEND)
+		xflags |= FS_XFLAG_APPEND;
+	if (flags & BTRFS_INODE_IMMUTABLE)
+		xflags |= FS_XFLAG_IMMUTABLE;
+	if (flags & BTRFS_INODE_NOATIME)
+		xflags |= FS_XFLAG_NOATIME;
+	if (flags & BTRFS_INODE_NODUMP)
+		xflags |= FS_XFLAG_NODUMP;
+	if (flags & BTRFS_INODE_SYNC)
+		xflags |= FS_XFLAG_SYNC;
+
+	return xflags;
+}
+
+/* Check if @flags are a supported and valid set of FS_XFLAGS_* flags */
+static int check_xflags(unsigned int flags)
+{
+	if (flags & ~(FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE | FS_XFLAG_NOATIME |
+		      FS_XFLAG_NODUMP | FS_XFLAG_SYNC))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+/*
+ * Set the xflags from the internal inode flags. The remaining items of fsxattr
+ * are zeroed.
+ */
+static int btrfs_ioctl_fsgetxattr(struct file *file, void __user *arg)
+{
+	struct btrfs_inode *binode = BTRFS_I(file_inode(file));
+	struct fsxattr fa;
+
+	memset(&fa, 0, sizeof(fa));
+	fa.fsx_xflags = btrfs_inode_flags_to_xflags(binode->flags);
+
+	if (copy_to_user(arg, &fa, sizeof(fa)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg)
+{
+	struct inode *inode = file_inode(file);
+	struct btrfs_inode *binode = BTRFS_I(inode);
+	struct btrfs_root *root = binode->root;
+	struct btrfs_trans_handle *trans;
+	struct fsxattr fa;
+	unsigned old_flags;
+	unsigned old_i_flags;
+	int ret = 0;
+
+	if (!inode_owner_or_capable(inode))
+		return -EPERM;
+
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
+	memset(&fa, 0, sizeof(fa));
+	if (copy_from_user(&fa, arg, sizeof(fa)))
+		return -EFAULT;
+
+	ret = check_xflags(fa.fsx_xflags);
+	if (ret)
+		return ret;
+
+	if (fa.fsx_extsize != 0 || fa.fsx_projid != 0 || fa.fsx_cowextsize != 0)
+		return -EOPNOTSUPP;
+
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
+	inode_lock(inode);
+
+	old_flags = binode->flags;
+	old_i_flags = inode->i_flags;
+
+	/* We need the capabilities to change append-only or immutable inode */
+	if (((old_flags & (BTRFS_INODE_APPEND | BTRFS_INODE_IMMUTABLE)) ||
+	     (fa.fsx_xflags & (FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE))) &&
+	    !capable(CAP_LINUX_IMMUTABLE)) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+
+	if (fa.fsx_xflags & FS_XFLAG_SYNC)
+		binode->flags |= BTRFS_INODE_SYNC;
+	else
+		binode->flags &= ~BTRFS_INODE_SYNC;
+	if (fa.fsx_xflags & FS_XFLAG_IMMUTABLE)
+		binode->flags |= BTRFS_INODE_IMMUTABLE;
+	else
+		binode->flags &= ~BTRFS_INODE_IMMUTABLE;
+	if (fa.fsx_xflags & FS_XFLAG_APPEND)
+		binode->flags |= BTRFS_INODE_APPEND;
+	else
+		binode->flags &= ~BTRFS_INODE_APPEND;
+	if (fa.fsx_xflags & FS_XFLAG_NODUMP)
+		binode->flags |= BTRFS_INODE_NODUMP;
+	else
+		binode->flags &= ~BTRFS_INODE_NODUMP;
+	if (fa.fsx_xflags & FS_XFLAG_NOATIME)
+		binode->flags |= BTRFS_INODE_NOATIME;
+	else
+		binode->flags &= ~BTRFS_INODE_NOATIME;
+
+	/* 1 item for the inode */
+	trans = btrfs_start_transaction(root, 1);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out_unlock;
+	}
+
+	btrfs_sync_inode_flags_to_i_flags(inode);
+	inode_inc_iversion(inode);
+	inode->i_ctime = current_time(inode);
+	ret = btrfs_update_inode(trans, root, inode);
+
+	btrfs_end_transaction(trans);
+
+out_unlock:
+	if (ret) {
+		binode->flags = old_flags;
+		inode->i_flags = old_i_flags;
+	}
+
+	inode_unlock(inode);
+	mnt_drop_write_file(file);
+
+	return ret;
+}
+
 static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
 {
 	struct inode *inode = file_inode(file);
@@ -424,7 +569,6 @@ static noinline int create_subvol(struct inode *dir,
 	u64 objectid;
 	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
 	u64 index = 0;
-	u64 qgroup_reserved;
 	uuid_le new_uuid;
 
 	root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
@@ -449,8 +593,7 @@ static noinline int create_subvol(struct inode *dir,
 	 * The same as the snapshot creation, please see the comment
 	 * of create_snapshot().
 	 */
-	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
-					       8, &qgroup_reserved, false);
+	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 8, false);
 	if (ret)
 		goto fail_free;
 
@@ -573,7 +716,7 @@ static noinline int create_subvol(struct inode *dir,
 				 btrfs_ino(BTRFS_I(dir)), index, name, namelen);
 	BUG_ON(ret);
 
-	ret = btrfs_uuid_tree_add(trans, fs_info, root_item->uuid,
+	ret = btrfs_uuid_tree_add(trans, root_item->uuid,
 				  BTRFS_UUID_KEY_SUBVOL, objectid);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
@@ -640,7 +783,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	wait_event(root->subv_writers->wait,
 		   percpu_counter_sum(&root->subv_writers->counter) == 0);
 
-	ret = btrfs_start_delalloc_inodes(root, 0);
+	ret = btrfs_start_delalloc_inodes(root);
 	if (ret)
 		goto dec_and_free;
 
@@ -658,7 +801,6 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	 */
 	ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
 					&pending_snapshot->block_rsv, 8,
-					&pending_snapshot->qgroup_reserved,
 					false);
 	if (ret)
 		goto dec_and_free;
@@ -1457,7 +1599,6 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 	}
 
-	mutex_lock(&fs_info->volume_mutex);
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args)) {
 		ret = PTR_ERR(vol_args);
@@ -1565,7 +1706,6 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 out_free:
 	kfree(vol_args);
 out:
-	mutex_unlock(&fs_info->volume_mutex);
 	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 	mnt_drop_write_file(file);
 	return ret;
@@ -1832,60 +1972,6 @@ out:
 	return ret;
 }
 
-/*
- * helper to check if the subvolume references other subvolumes
- */
-static noinline int may_destroy_subvol(struct btrfs_root *root)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_path *path;
-	struct btrfs_dir_item *di;
-	struct btrfs_key key;
-	u64 dir_id;
-	int ret;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-
-	/* Make sure this root isn't set as the default subvol */
-	dir_id = btrfs_super_root_dir(fs_info->super_copy);
-	di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path,
-				   dir_id, "default", 7, 0);
-	if (di && !IS_ERR(di)) {
-		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
-		if (key.objectid == root->root_key.objectid) {
-			ret = -EPERM;
-			btrfs_err(fs_info,
-				  "deleting default subvolume %llu is not allowed",
-				  key.objectid);
-			goto out;
-		}
-		btrfs_release_path(path);
-	}
-
-	key.objectid = root->root_key.objectid;
-	key.type = BTRFS_ROOT_REF_KEY;
-	key.offset = (u64)-1;
-
-	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
-	if (ret < 0)
-		goto out;
-	BUG_ON(ret == 0);
-
-	ret = 0;
-	if (path->slots[0] > 0) {
-		path->slots[0]--;
-		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-		if (key.objectid == root->root_key.objectid &&
-		    key.type == BTRFS_ROOT_REF_KEY)
-			ret = -ENOTEMPTY;
-	}
-out:
-	btrfs_free_path(path);
-	return ret;
-}
-
 static noinline int key_in_sk(struct btrfs_key *key,
 			      struct btrfs_ioctl_search_key *sk)
 {
@@ -2066,7 +2152,7 @@ static noinline int search_ioctl(struct inode *inode,
 		root = btrfs_read_fs_root_no_name(info, &key);
 		if (IS_ERR(root)) {
 			btrfs_free_path(path);
-			return -ENOENT;
+			return PTR_ERR(root);
 		}
 	}
 
@@ -2200,8 +2286,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info,
 	key.offset = (u64)-1;
 	root = btrfs_read_fs_root_no_name(info, &key);
 	if (IS_ERR(root)) {
-		btrfs_err(info, "could not find root %llu", tree_id);
-		ret = -ENOENT;
+		ret = PTR_ERR(root);
 		goto out;
 	}
 
@@ -2256,6 +2341,165 @@ out:
 	return ret;
 }
 
+static int btrfs_search_path_in_tree_user(struct inode *inode,
+				struct btrfs_ioctl_ino_lookup_user_args *args)
+{
+	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+	struct super_block *sb = inode->i_sb;
+	struct btrfs_key upper_limit = BTRFS_I(inode)->location;
+	u64 treeid = BTRFS_I(inode)->root->root_key.objectid;
+	u64 dirid = args->dirid;
+	unsigned long item_off;
+	unsigned long item_len;
+	struct btrfs_inode_ref *iref;
+	struct btrfs_root_ref *rref;
+	struct btrfs_root *root;
+	struct btrfs_path *path;
+	struct btrfs_key key, key2;
+	struct extent_buffer *leaf;
+	struct inode *temp_inode;
+	char *ptr;
+	int slot;
+	int len;
+	int total_len = 0;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	/*
+	 * If the bottom subvolume does not exist directly under upper_limit,
+	 * construct the path in from the bottom up.
+	 */
+	if (dirid != upper_limit.objectid) {
+		ptr = &args->path[BTRFS_INO_LOOKUP_USER_PATH_MAX - 1];
+
+		key.objectid = treeid;
+		key.type = BTRFS_ROOT_ITEM_KEY;
+		key.offset = (u64)-1;
+		root = btrfs_read_fs_root_no_name(fs_info, &key);
+		if (IS_ERR(root)) {
+			ret = PTR_ERR(root);
+			goto out;
+		}
+
+		key.objectid = dirid;
+		key.type = BTRFS_INODE_REF_KEY;
+		key.offset = (u64)-1;
+		while (1) {
+			ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+			if (ret < 0) {
+				goto out;
+			} else if (ret > 0) {
+				ret = btrfs_previous_item(root, path, dirid,
+							  BTRFS_INODE_REF_KEY);
+				if (ret < 0) {
+					goto out;
+				} else if (ret > 0) {
+					ret = -ENOENT;
+					goto out;
+				}
+			}
+
+			leaf = path->nodes[0];
+			slot = path->slots[0];
+			btrfs_item_key_to_cpu(leaf, &key, slot);
+
+			iref = btrfs_item_ptr(leaf, slot, struct btrfs_inode_ref);
+			len = btrfs_inode_ref_name_len(leaf, iref);
+			ptr -= len + 1;
+			total_len += len + 1;
+			if (ptr < args->path) {
+				ret = -ENAMETOOLONG;
+				goto out;
+			}
+
+			*(ptr + len) = '/';
+			read_extent_buffer(leaf, ptr,
+					(unsigned long)(iref + 1), len);
+
+			/* Check the read+exec permission of this directory */
+			ret = btrfs_previous_item(root, path, dirid,
+						  BTRFS_INODE_ITEM_KEY);
+			if (ret < 0) {
+				goto out;
+			} else if (ret > 0) {
+				ret = -ENOENT;
+				goto out;
+			}
+
+			leaf = path->nodes[0];
+			slot = path->slots[0];
+			btrfs_item_key_to_cpu(leaf, &key2, slot);
+			if (key2.objectid != dirid) {
+				ret = -ENOENT;
+				goto out;
+			}
+
+			temp_inode = btrfs_iget(sb, &key2, root, NULL);
+			ret = inode_permission(temp_inode, MAY_READ | MAY_EXEC);
+			iput(temp_inode);
+			if (ret) {
+				ret = -EACCES;
+				goto out;
+			}
+
+			if (key.offset == upper_limit.objectid)
+				break;
+			if (key.objectid == BTRFS_FIRST_FREE_OBJECTID) {
+				ret = -EACCES;
+				goto out;
+			}
+
+			btrfs_release_path(path);
+			key.objectid = key.offset;
+			key.offset = (u64)-1;
+			dirid = key.objectid;
+		}
+
+		memmove(args->path, ptr, total_len);
+		args->path[total_len] = '\0';
+		btrfs_release_path(path);
+	}
+
+	/* Get the bottom subvolume's name from ROOT_REF */
+	root = fs_info->tree_root;
+	key.objectid = treeid;
+	key.type = BTRFS_ROOT_REF_KEY;
+	key.offset = args->treeid;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0) {
+		goto out;
+	} else if (ret > 0) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	leaf = path->nodes[0];
+	slot = path->slots[0];
+	btrfs_item_key_to_cpu(leaf, &key, slot);
+
+	item_off = btrfs_item_ptr_offset(leaf, slot);
+	item_len = btrfs_item_size_nr(leaf, slot);
+	/* Check if dirid in ROOT_REF corresponds to passed dirid */
+	rref = btrfs_item_ptr(leaf, slot, struct btrfs_root_ref);
+	if (args->dirid != btrfs_root_ref_dirid(leaf, rref)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Copy subvolume's name */
+	item_off += sizeof(struct btrfs_root_ref);
+	item_len -= sizeof(struct btrfs_root_ref);
+	read_extent_buffer(leaf, args->name, item_off, item_len);
+	args->name[item_len] = 0;
+
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 static noinline int btrfs_ioctl_ino_lookup(struct file *file,
 					   void __user *argp)
 {
@@ -2298,6 +2542,265 @@ out:
 	return ret;
 }
 
+/*
+ * Version of ino_lookup ioctl (unprivileged)
+ *
+ * The main differences from ino_lookup ioctl are:
+ *
+ *   1. Read + Exec permission will be checked using inode_permission() during
+ *      path construction. -EACCES will be returned in case of failure.
+ *   2. Path construction will be stopped at the inode number which corresponds
+ *      to the fd with which this ioctl is called. If constructed path does not
+ *      exist under fd's inode, -EACCES will be returned.
+ *   3. The name of bottom subvolume is also searched and filled.
+ */
+static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp)
+{
+	struct btrfs_ioctl_ino_lookup_user_args *args;
+	struct inode *inode;
+	int ret;
+
+	args = memdup_user(argp, sizeof(*args));
+	if (IS_ERR(args))
+		return PTR_ERR(args);
+
+	inode = file_inode(file);
+
+	if (args->dirid == BTRFS_FIRST_FREE_OBJECTID &&
+	    BTRFS_I(inode)->location.objectid != BTRFS_FIRST_FREE_OBJECTID) {
+		/*
+		 * The subvolume does not exist under fd with which this is
+		 * called
+		 */
+		kfree(args);
+		return -EACCES;
+	}
+
+	ret = btrfs_search_path_in_tree_user(inode, args);
+
+	if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
+		ret = -EFAULT;
+
+	kfree(args);
+	return ret;
+}
+
+/* Get the subvolume information in BTRFS_ROOT_ITEM and BTRFS_ROOT_BACKREF */
+static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp)
+{
+	struct btrfs_ioctl_get_subvol_info_args *subvol_info;
+	struct btrfs_fs_info *fs_info;
+	struct btrfs_root *root;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_root_item *root_item;
+	struct btrfs_root_ref *rref;
+	struct extent_buffer *leaf;
+	unsigned long item_off;
+	unsigned long item_len;
+	struct inode *inode;
+	int slot;
+	int ret = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	subvol_info = kzalloc(sizeof(*subvol_info), GFP_KERNEL);
+	if (!subvol_info) {
+		btrfs_free_path(path);
+		return -ENOMEM;
+	}
+
+	inode = file_inode(file);
+	fs_info = BTRFS_I(inode)->root->fs_info;
+
+	/* Get root_item of inode's subvolume */
+	key.objectid = BTRFS_I(inode)->root->root_key.objectid;
+	key.type = BTRFS_ROOT_ITEM_KEY;
+	key.offset = (u64)-1;
+	root = btrfs_read_fs_root_no_name(fs_info, &key);
+	if (IS_ERR(root)) {
+		ret = PTR_ERR(root);
+		goto out;
+	}
+	root_item = &root->root_item;
+
+	subvol_info->treeid = key.objectid;
+
+	subvol_info->generation = btrfs_root_generation(root_item);
+	subvol_info->flags = btrfs_root_flags(root_item);
+
+	memcpy(subvol_info->uuid, root_item->uuid, BTRFS_UUID_SIZE);
+	memcpy(subvol_info->parent_uuid, root_item->parent_uuid,
+						    BTRFS_UUID_SIZE);
+	memcpy(subvol_info->received_uuid, root_item->received_uuid,
+						    BTRFS_UUID_SIZE);
+
+	subvol_info->ctransid = btrfs_root_ctransid(root_item);
+	subvol_info->ctime.sec = btrfs_stack_timespec_sec(&root_item->ctime);
+	subvol_info->ctime.nsec = btrfs_stack_timespec_nsec(&root_item->ctime);
+
+	subvol_info->otransid = btrfs_root_otransid(root_item);
+	subvol_info->otime.sec = btrfs_stack_timespec_sec(&root_item->otime);
+	subvol_info->otime.nsec = btrfs_stack_timespec_nsec(&root_item->otime);
+
+	subvol_info->stransid = btrfs_root_stransid(root_item);
+	subvol_info->stime.sec = btrfs_stack_timespec_sec(&root_item->stime);
+	subvol_info->stime.nsec = btrfs_stack_timespec_nsec(&root_item->stime);
+
+	subvol_info->rtransid = btrfs_root_rtransid(root_item);
+	subvol_info->rtime.sec = btrfs_stack_timespec_sec(&root_item->rtime);
+	subvol_info->rtime.nsec = btrfs_stack_timespec_nsec(&root_item->rtime);
+
+	if (key.objectid != BTRFS_FS_TREE_OBJECTID) {
+		/* Search root tree for ROOT_BACKREF of this subvolume */
+		root = fs_info->tree_root;
+
+		key.type = BTRFS_ROOT_BACKREF_KEY;
+		key.offset = 0;
+		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+		if (ret < 0) {
+			goto out;
+		} else if (path->slots[0] >=
+			   btrfs_header_nritems(path->nodes[0])) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0) {
+				goto out;
+			} else if (ret > 0) {
+				ret = -EUCLEAN;
+				goto out;
+			}
+		}
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid == subvol_info->treeid &&
+		    key.type == BTRFS_ROOT_BACKREF_KEY) {
+			subvol_info->parent_id = key.offset;
+
+			rref = btrfs_item_ptr(leaf, slot, struct btrfs_root_ref);
+			subvol_info->dirid = btrfs_root_ref_dirid(leaf, rref);
+
+			item_off = btrfs_item_ptr_offset(leaf, slot)
+					+ sizeof(struct btrfs_root_ref);
+			item_len = btrfs_item_size_nr(leaf, slot)
+					- sizeof(struct btrfs_root_ref);
+			read_extent_buffer(leaf, subvol_info->name,
+					   item_off, item_len);
+		} else {
+			ret = -ENOENT;
+			goto out;
+		}
+	}
+
+	if (copy_to_user(argp, subvol_info, sizeof(*subvol_info)))
+		ret = -EFAULT;
+
+out:
+	btrfs_free_path(path);
+	kzfree(subvol_info);
+	return ret;
+}
+
+/*
+ * Return ROOT_REF information of the subvolume containing this inode
+ * except the subvolume name.
+ */
+static int btrfs_ioctl_get_subvol_rootref(struct file *file, void __user *argp)
+{
+	struct btrfs_ioctl_get_subvol_rootref_args *rootrefs;
+	struct btrfs_root_ref *rref;
+	struct btrfs_root *root;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct extent_buffer *leaf;
+	struct inode *inode;
+	u64 objectid;
+	int slot;
+	int ret;
+	u8 found;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	rootrefs = memdup_user(argp, sizeof(*rootrefs));
+	if (IS_ERR(rootrefs)) {
+		btrfs_free_path(path);
+		return PTR_ERR(rootrefs);
+	}
+
+	inode = file_inode(file);
+	root = BTRFS_I(inode)->root->fs_info->tree_root;
+	objectid = BTRFS_I(inode)->root->root_key.objectid;
+
+	key.objectid = objectid;
+	key.type = BTRFS_ROOT_REF_KEY;
+	key.offset = rootrefs->min_treeid;
+	found = 0;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0) {
+		goto out;
+	} else if (path->slots[0] >=
+		   btrfs_header_nritems(path->nodes[0])) {
+		ret = btrfs_next_leaf(root, path);
+		if (ret < 0) {
+			goto out;
+		} else if (ret > 0) {
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+	while (1) {
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid != objectid || key.type != BTRFS_ROOT_REF_KEY) {
+			ret = 0;
+			goto out;
+		}
+
+		if (found == BTRFS_MAX_ROOTREF_BUFFER_NUM) {
+			ret = -EOVERFLOW;
+			goto out;
+		}
+
+		rref = btrfs_item_ptr(leaf, slot, struct btrfs_root_ref);
+		rootrefs->rootref[found].treeid = key.offset;
+		rootrefs->rootref[found].dirid =
+				  btrfs_root_ref_dirid(leaf, rref);
+		found++;
+
+		ret = btrfs_next_item(root, path);
+		if (ret < 0) {
+			goto out;
+		} else if (ret > 0) {
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+
+out:
+	if (!ret || ret == -EOVERFLOW) {
+		rootrefs->num_items = found;
+		/* update min_treeid for next search */
+		if (found)
+			rootrefs->min_treeid =
+				rootrefs->rootref[found - 1].treeid + 1;
+		if (copy_to_user(argp, rootrefs, sizeof(*rootrefs)))
+			ret = -EFAULT;
+	}
+
+	kfree(rootrefs);
+	btrfs_free_path(path);
+
+	return ret;
+}
+
 static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 					     void __user *arg)
 {
@@ -2309,12 +2812,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_root *dest = NULL;
 	struct btrfs_ioctl_vol_args *vol_args;
-	struct btrfs_trans_handle *trans;
-	struct btrfs_block_rsv block_rsv;
-	u64 root_flags;
-	u64 qgroup_reserved;
 	int namelen;
-	int ret;
 	int err = 0;
 
 	if (!S_ISDIR(dir->i_mode))
@@ -2398,133 +2896,11 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	}
 
 	inode_lock(inode);
-
-	/*
-	 * Don't allow to delete a subvolume with send in progress. This is
-	 * inside the i_mutex so the error handling that has to drop the bit
-	 * again is not run concurrently.
-	 */
-	spin_lock(&dest->root_item_lock);
-	root_flags = btrfs_root_flags(&dest->root_item);
-	if (dest->send_in_progress == 0) {
-		btrfs_set_root_flags(&dest->root_item,
-				root_flags | BTRFS_ROOT_SUBVOL_DEAD);
-		spin_unlock(&dest->root_item_lock);
-	} else {
-		spin_unlock(&dest->root_item_lock);
-		btrfs_warn(fs_info,
-			   "Attempt to delete subvolume %llu during send",
-			   dest->root_key.objectid);
-		err = -EPERM;
-		goto out_unlock_inode;
-	}
-
-	down_write(&fs_info->subvol_sem);
-
-	err = may_destroy_subvol(dest);
-	if (err)
-		goto out_up_write;
-
-	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
-	/*
-	 * One for dir inode, two for dir entries, two for root
-	 * ref/backref.
-	 */
-	err = btrfs_subvolume_reserve_metadata(root, &block_rsv,
-					       5, &qgroup_reserved, true);
-	if (err)
-		goto out_up_write;
-
-	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans)) {
-		err = PTR_ERR(trans);
-		goto out_release;
-	}
-	trans->block_rsv = &block_rsv;
-	trans->bytes_reserved = block_rsv.size;
-
-	btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
-
-	ret = btrfs_unlink_subvol(trans, root, dir,
-				dest->root_key.objectid,
-				dentry->d_name.name,
-				dentry->d_name.len);
-	if (ret) {
-		err = ret;
-		btrfs_abort_transaction(trans, ret);
-		goto out_end_trans;
-	}
-
-	btrfs_record_root_in_trans(trans, dest);
-
-	memset(&dest->root_item.drop_progress, 0,
-		sizeof(dest->root_item.drop_progress));
-	dest->root_item.drop_level = 0;
-	btrfs_set_root_refs(&dest->root_item, 0);
-
-	if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
-		ret = btrfs_insert_orphan_item(trans,
-					fs_info->tree_root,
-					dest->root_key.objectid);
-		if (ret) {
-			btrfs_abort_transaction(trans, ret);
-			err = ret;
-			goto out_end_trans;
-		}
-	}
-
-	ret = btrfs_uuid_tree_rem(trans, fs_info, dest->root_item.uuid,
-				  BTRFS_UUID_KEY_SUBVOL,
-				  dest->root_key.objectid);
-	if (ret && ret != -ENOENT) {
-		btrfs_abort_transaction(trans, ret);
-		err = ret;
-		goto out_end_trans;
-	}
-	if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
-		ret = btrfs_uuid_tree_rem(trans, fs_info,
-					  dest->root_item.received_uuid,
-					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
-					  dest->root_key.objectid);
-		if (ret && ret != -ENOENT) {
-			btrfs_abort_transaction(trans, ret);
-			err = ret;
-			goto out_end_trans;
-		}
-	}
-
-out_end_trans:
-	trans->block_rsv = NULL;
-	trans->bytes_reserved = 0;
-	ret = btrfs_end_transaction(trans);
-	if (ret && !err)
-		err = ret;
-	inode->i_flags |= S_DEAD;
-out_release:
-	btrfs_subvolume_release_metadata(fs_info, &block_rsv);
-out_up_write:
-	up_write(&fs_info->subvol_sem);
-	if (err) {
-		spin_lock(&dest->root_item_lock);
-		root_flags = btrfs_root_flags(&dest->root_item);
-		btrfs_set_root_flags(&dest->root_item,
-				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
-		spin_unlock(&dest->root_item_lock);
-	}
-out_unlock_inode:
+	err = btrfs_delete_subvolume(dir, dentry);
 	inode_unlock(inode);
-	if (!err) {
-		d_invalidate(dentry);
-		btrfs_invalidate_inodes(dest);
+	if (!err)
 		d_delete(dentry);
-		ASSERT(dest->send_in_progress == 0);
 
-		/* the last ref */
-		if (dest->ino_cache_inode) {
-			iput(dest->ino_cache_inode);
-			dest->ino_cache_inode = NULL;
-		}
-	}
 out_dput:
 	dput(dentry);
 out_unlock_dir:
@@ -2613,7 +2989,6 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
 	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
 		return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 
-	mutex_lock(&fs_info->volume_mutex);
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args)) {
 		ret = PTR_ERR(vol_args);
@@ -2628,7 +3003,6 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
 
 	kfree(vol_args);
 out:
-	mutex_unlock(&fs_info->volume_mutex);
 	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 	return ret;
 }
@@ -2654,8 +3028,10 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	}
 
 	/* Check for compatibility reject unknown flags */
-	if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
-		return -EOPNOTSUPP;
+	if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
 
 	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
 		ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
@@ -2954,8 +3330,6 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 			put_page(pg);
 		}
 	}
-	kfree(cmp->src_pages);
-	kfree(cmp->dst_pages);
 }
 
 static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
@@ -2964,40 +3338,14 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
 {
 	int ret;
 	int num_pages = PAGE_ALIGN(len) >> PAGE_SHIFT;
-	struct page **src_pgarr, **dst_pgarr;
 
-	/*
-	 * We must gather up all the pages before we initiate our
-	 * extent locking. We use an array for the page pointers. Size
-	 * of the array is bounded by len, which is in turn bounded by
-	 * BTRFS_MAX_DEDUPE_LEN.
-	 */
-	src_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
-	dst_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
-	if (!src_pgarr || !dst_pgarr) {
-		kfree(src_pgarr);
-		kfree(dst_pgarr);
-		return -ENOMEM;
-	}
 	cmp->num_pages = num_pages;
-	cmp->src_pages = src_pgarr;
-	cmp->dst_pages = dst_pgarr;
-
-	/*
-	 * If deduping ranges in the same inode, locking rules make it mandatory
-	 * to always lock pages in ascending order to avoid deadlocks with
-	 * concurrent tasks (such as starting writeback/delalloc).
-	 */
-	if (src == dst && dst_loff < loff) {
-		swap(src_pgarr, dst_pgarr);
-		swap(loff, dst_loff);
-	}
 
-	ret = gather_extent_pages(src, src_pgarr, cmp->num_pages, loff);
+	ret = gather_extent_pages(src, cmp->src_pages, num_pages, loff);
 	if (ret)
 		goto out;
 
-	ret = gather_extent_pages(dst, dst_pgarr, cmp->num_pages, dst_loff);
+	ret = gather_extent_pages(dst, cmp->dst_pages, num_pages, dst_loff);
 
 out:
 	if (ret)
@@ -3067,31 +3415,23 @@ static int extent_same_check_offsets(struct inode *inode, u64 off, u64 *plen,
 	return 0;
 }
 
-static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
-			     struct inode *dst, u64 dst_loff)
+static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
+				   struct inode *dst, u64 dst_loff,
+				   struct cmp_pages *cmp)
 {
 	int ret;
 	u64 len = olen;
-	struct cmp_pages cmp;
 	bool same_inode = (src == dst);
 	u64 same_lock_start = 0;
 	u64 same_lock_len = 0;
 
-	if (len == 0)
-		return 0;
-
-	if (same_inode)
-		inode_lock(src);
-	else
-		btrfs_double_inode_lock(src, dst);
-
 	ret = extent_same_check_offsets(src, loff, &len, olen);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	if (same_inode) {
 		/*
@@ -3108,32 +3448,21 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		 * allow an unaligned length so long as it ends at
 		 * i_size.
 		 */
-		if (len != olen) {
-			ret = -EINVAL;
-			goto out_unlock;
-		}
+		if (len != olen)
+			return -EINVAL;
 
 		/* Check for overlapping ranges */
-		if (dst_loff + len > loff && dst_loff < loff + len) {
-			ret = -EINVAL;
-			goto out_unlock;
-		}
+		if (dst_loff + len > loff && dst_loff < loff + len)
+			return -EINVAL;
 
 		same_lock_start = min_t(u64, loff, dst_loff);
 		same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start;
 	}
 
-	/* don't make the dst file partly checksummed */
-	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
-	    (BTRFS_I(dst)->flags & BTRFS_INODE_NODATASUM)) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
 again:
-	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
+	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, cmp);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	if (same_inode)
 		ret = lock_extent_range(src, same_lock_start, same_lock_len,
@@ -3154,7 +3483,7 @@ again:
 		 * Ranges in the io trees already unlocked. Now unlock all
 		 * pages before waiting for all IO to complete.
 		 */
-		btrfs_cmp_data_free(&cmp);
+		btrfs_cmp_data_free(cmp);
 		if (same_inode) {
 			btrfs_wait_ordered_range(src, same_lock_start,
 						 same_lock_len);
@@ -3167,12 +3496,12 @@ again:
 	ASSERT(ret == 0);
 	if (WARN_ON(ret)) {
 		/* ranges in the io trees already unlocked */
-		btrfs_cmp_data_free(&cmp);
+		btrfs_cmp_data_free(cmp);
 		return ret;
 	}
 
 	/* pass original length for comparison so we stay within i_size */
-	ret = btrfs_cmp_data(olen, &cmp);
+	ret = btrfs_cmp_data(olen, cmp);
 	if (ret == 0)
 		ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
 
@@ -3182,18 +3511,91 @@ again:
 	else
 		btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
 
-	btrfs_cmp_data_free(&cmp);
+	btrfs_cmp_data_free(cmp);
+
+	return ret;
+}
+
+#define BTRFS_MAX_DEDUPE_LEN	SZ_16M
+
+static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
+			     struct inode *dst, u64 dst_loff)
+{
+	int ret;
+	struct cmp_pages cmp;
+	int num_pages = PAGE_ALIGN(BTRFS_MAX_DEDUPE_LEN) >> PAGE_SHIFT;
+	bool same_inode = (src == dst);
+	u64 i, tail_len, chunk_count;
+
+	if (olen == 0)
+		return 0;
+
+	if (same_inode)
+		inode_lock(src);
+	else
+		btrfs_double_inode_lock(src, dst);
+
+	/* don't make the dst file partly checksummed */
+	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+	    (BTRFS_I(dst)->flags & BTRFS_INODE_NODATASUM)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	tail_len = olen % BTRFS_MAX_DEDUPE_LEN;
+	chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN);
+	if (chunk_count == 0)
+		num_pages = PAGE_ALIGN(tail_len) >> PAGE_SHIFT;
+
+	/*
+	 * If deduping ranges in the same inode, locking rules make it
+	 * mandatory to always lock pages in ascending order to avoid deadlocks
+	 * with concurrent tasks (such as starting writeback/delalloc).
+	 */
+	if (same_inode && dst_loff < loff)
+		swap(loff, dst_loff);
+
+	/*
+	 * We must gather up all the pages before we initiate our extent
+	 * locking. We use an array for the page pointers. Size of the array is
+	 * bounded by len, which is in turn bounded by BTRFS_MAX_DEDUPE_LEN.
+	 */
+	cmp.src_pages = kvmalloc_array(num_pages, sizeof(struct page *),
+				       GFP_KERNEL | __GFP_ZERO);
+	cmp.dst_pages = kvmalloc_array(num_pages, sizeof(struct page *),
+				       GFP_KERNEL | __GFP_ZERO);
+	if (!cmp.src_pages || !cmp.dst_pages) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	for (i = 0; i < chunk_count; i++) {
+		ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
+					      dst, dst_loff, &cmp);
+		if (ret)
+			goto out_unlock;
+
+		loff += BTRFS_MAX_DEDUPE_LEN;
+		dst_loff += BTRFS_MAX_DEDUPE_LEN;
+	}
+
+	if (tail_len > 0)
+		ret = btrfs_extent_same_range(src, loff, tail_len, dst,
+					      dst_loff, &cmp);
+
 out_unlock:
 	if (same_inode)
 		inode_unlock(src);
 	else
 		btrfs_double_inode_unlock(src, dst);
 
+out_free:
+	kvfree(cmp.src_pages);
+	kvfree(cmp.dst_pages);
+
 	return ret;
 }
 
-#define BTRFS_MAX_DEDUPE_LEN	SZ_16M
-
 ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 				struct file *dst_file, u64 dst_loff)
 {
@@ -3202,9 +3604,6 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 	u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
 	ssize_t res;
 
-	if (olen > BTRFS_MAX_DEDUPE_LEN)
-		olen = BTRFS_MAX_DEDUPE_LEN;
-
 	if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
 		/*
 		 * Btrfs does not support blocksize < page_size. As a
@@ -3826,11 +4225,6 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	    src->i_sb != inode->i_sb)
 		return -EXDEV;
 
-	/* don't make the dst file partly checksummed */
-	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
-	    (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
-		return -EINVAL;
-
 	if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
 		return -EISDIR;
 
@@ -3840,6 +4234,13 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 		inode_lock(src);
 	}
 
+	/* don't make the dst file partly checksummed */
+	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+	    (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	/* determine range to clone */
 	ret = -EINVAL;
 	if (off + len > src->i_size || off + len < off)
@@ -4007,8 +4408,8 @@ out:
 	return ret;
 }
 
-void btrfs_get_block_group_info(struct list_head *groups_list,
-				struct btrfs_ioctl_space_info *space)
+static void get_block_group_info(struct list_head *groups_list,
+				 struct btrfs_ioctl_space_info *space)
 {
 	struct btrfs_block_group_cache *block_group;
 
@@ -4124,8 +4525,8 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info,
 		down_read(&info->groups_sem);
 		for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
 			if (!list_empty(&info->block_groups[c])) {
-				btrfs_get_block_group_info(
-					&info->block_groups[c], &space);
+				get_block_group_info(&info->block_groups[c],
+						     &space);
 				memcpy(dest, &space, sizeof(space));
 				dest++;
 				space_args.total_spaces++;
@@ -4490,14 +4891,14 @@ out_loi:
 	return ret;
 }
 
-void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
 			       struct btrfs_ioctl_balance_args *bargs)
 {
 	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
 
 	bargs->flags = bctl->flags;
 
-	if (atomic_read(&fs_info->balance_running))
+	if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags))
 		bargs->state |= BTRFS_BALANCE_STATE_RUNNING;
 	if (atomic_read(&fs_info->balance_pause_req))
 		bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ;
@@ -4508,13 +4909,9 @@ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
 	memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta));
 	memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys));
 
-	if (lock) {
-		spin_lock(&fs_info->balance_lock);
-		memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
-		spin_unlock(&fs_info->balance_lock);
-	} else {
-		memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
-	}
+	spin_lock(&fs_info->balance_lock);
+	memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+	spin_unlock(&fs_info->balance_lock);
 }
 
 static long btrfs_ioctl_balance(struct file *file, void __user *arg)
@@ -4535,7 +4932,6 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 
 again:
 	if (!test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
-		mutex_lock(&fs_info->volume_mutex);
 		mutex_lock(&fs_info->balance_mutex);
 		need_unlock = true;
 		goto locked;
@@ -4550,21 +4946,22 @@ again:
 	mutex_lock(&fs_info->balance_mutex);
 	if (fs_info->balance_ctl) {
 		/* this is either (2) or (3) */
-		if (!atomic_read(&fs_info->balance_running)) {
+		if (!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
 			mutex_unlock(&fs_info->balance_mutex);
-			if (!mutex_trylock(&fs_info->volume_mutex))
-				goto again;
+			/*
+			 * Lock released to allow other waiters to continue,
+			 * we'll reexamine the status again.
+			 */
 			mutex_lock(&fs_info->balance_mutex);
 
 			if (fs_info->balance_ctl &&
-			    !atomic_read(&fs_info->balance_running)) {
+			    !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
 				/* this is (3) */
 				need_unlock = false;
 				goto locked;
 			}
 
 			mutex_unlock(&fs_info->balance_mutex);
-			mutex_unlock(&fs_info->volume_mutex);
 			goto again;
 		} else {
 			/* this is (2) */
@@ -4617,7 +5014,6 @@ locked:
 		goto out_bargs;
 	}
 
-	bctl->fs_info = fs_info;
 	if (arg) {
 		memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
 		memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
@@ -4636,14 +5032,14 @@ locked:
 
 do_balance:
 	/*
-	 * Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP
-	 * goes to to btrfs_balance.  bctl is freed in __cancel_balance,
-	 * or, if restriper was paused all the way until unmount, in
-	 * free_fs_info.  The flag is cleared in __cancel_balance.
+	 * Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP goes to
+	 * btrfs_balance.  bctl is freed in reset_balance_state, or, if
+	 * restriper was paused all the way until unmount, in free_fs_info.
+	 * The flag should be cleared after reset_balance_state.
 	 */
 	need_unlock = false;
 
-	ret = btrfs_balance(bctl, bargs);
+	ret = btrfs_balance(fs_info, bctl, bargs);
 	bctl = NULL;
 
 	if (arg) {
@@ -4657,7 +5053,6 @@ out_bargs:
 	kfree(bargs);
 out_unlock:
 	mutex_unlock(&fs_info->balance_mutex);
-	mutex_unlock(&fs_info->volume_mutex);
 	if (need_unlock)
 		clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 out:
@@ -4701,7 +5096,7 @@ static long btrfs_ioctl_balance_progress(struct btrfs_fs_info *fs_info,
 		goto out;
 	}
 
-	update_ioctl_balance_args(fs_info, 1, bargs);
+	btrfs_update_ioctl_balance_args(fs_info, bargs);
 
 	if (copy_to_user(arg, bargs, sizeof(*bargs)))
 		ret = -EFAULT;
@@ -5038,8 +5433,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 				       BTRFS_UUID_SIZE);
 	if (received_uuid_changed &&
 	    !btrfs_is_empty_uuid(root_item->received_uuid)) {
-		ret = btrfs_uuid_tree_rem(trans, fs_info,
-					  root_item->received_uuid,
+		ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 					  root->root_key.objectid);
 		if (ret && ret != -ENOENT) {
@@ -5063,7 +5457,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 		goto out;
 	}
 	if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) {
-		ret = btrfs_uuid_tree_add(trans, fs_info, sa->uuid,
+		ret = btrfs_uuid_tree_add(trans, sa->uuid,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 					  root->root_key.objectid);
 		if (ret < 0 && ret != -EEXIST) {
@@ -5497,7 +5891,7 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_SYNC: {
 		int ret;
 
-		ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
+		ret = btrfs_start_delalloc_roots(fs_info, -1);
 		if (ret)
 			return ret;
 		ret = btrfs_sync_fs(inode->i_sb, 1);
@@ -5565,6 +5959,16 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_get_features(file, argp);
 	case BTRFS_IOC_SET_FEATURES:
 		return btrfs_ioctl_set_features(file, argp);
+	case FS_IOC_FSGETXATTR:
+		return btrfs_ioctl_fsgetxattr(file, argp);
+	case FS_IOC_FSSETXATTR:
+		return btrfs_ioctl_fssetxattr(file, argp);
+	case BTRFS_IOC_GET_SUBVOL_INFO:
+		return btrfs_ioctl_get_subvol_info(file, argp);
+	case BTRFS_IOC_GET_SUBVOL_ROOTREF:
+		return btrfs_ioctl_get_subvol_rootref(file, argp);
+	case BTRFS_IOC_INO_LOOKUP_USER:
+		return btrfs_ioctl_ino_lookup_user(file, argp);
 	}
 
 	return -ENOTTY;
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index e4faefac9d16..1da768e5ef75 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -66,22 +66,16 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
 		write_lock(&eb->lock);
 		WARN_ON(atomic_read(&eb->spinning_writers));
 		atomic_inc(&eb->spinning_writers);
-		/*
-		 * atomic_dec_and_test implies a barrier for waitqueue_active
-		 */
-		if (atomic_dec_and_test(&eb->blocking_writers) &&
-		    waitqueue_active(&eb->write_lock_wq))
-			wake_up(&eb->write_lock_wq);
+		/* atomic_dec_and_test implies a barrier */
+		if (atomic_dec_and_test(&eb->blocking_writers))
+			cond_wake_up_nomb(&eb->write_lock_wq);
 	} else if (rw == BTRFS_READ_LOCK_BLOCKING) {
 		BUG_ON(atomic_read(&eb->blocking_readers) == 0);
 		read_lock(&eb->lock);
 		atomic_inc(&eb->spinning_readers);
-		/*
-		 * atomic_dec_and_test implies a barrier for waitqueue_active
-		 */
-		if (atomic_dec_and_test(&eb->blocking_readers) &&
-		    waitqueue_active(&eb->read_lock_wq))
-			wake_up(&eb->read_lock_wq);
+		/* atomic_dec_and_test implies a barrier */
+		if (atomic_dec_and_test(&eb->blocking_readers))
+			cond_wake_up_nomb(&eb->read_lock_wq);
 	}
 }
 
@@ -221,12 +215,9 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
 	}
 	btrfs_assert_tree_read_locked(eb);
 	WARN_ON(atomic_read(&eb->blocking_readers) == 0);
-	/*
-	 * atomic_dec_and_test implies a barrier for waitqueue_active
-	 */
-	if (atomic_dec_and_test(&eb->blocking_readers) &&
-	    waitqueue_active(&eb->read_lock_wq))
-		wake_up(&eb->read_lock_wq);
+	/* atomic_dec_and_test implies a barrier */
+	if (atomic_dec_and_test(&eb->blocking_readers))
+		cond_wake_up_nomb(&eb->read_lock_wq);
 	atomic_dec(&eb->read_locks);
 }
 
@@ -275,12 +266,9 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
 	if (blockers) {
 		WARN_ON(atomic_read(&eb->spinning_writers));
 		atomic_dec(&eb->blocking_writers);
-		/*
-		 * Make sure counter is updated before we wake up waiters.
-		 */
+		/* Use the lighter barrier after atomic */
 		smp_mb__after_atomic();
-		if (waitqueue_active(&eb->write_lock_wq))
-			wake_up(&eb->write_lock_wq);
+		cond_wake_up_nomb(&eb->write_lock_wq);
 	} else {
 		WARN_ON(atomic_read(&eb->spinning_writers) != 1);
 		atomic_dec(&eb->spinning_writers);
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 0667ea07f766..b6a4cc178bee 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -17,6 +17,43 @@
 
 #define LZO_LEN	4
 
+/*
+ * Btrfs LZO compression format
+ *
+ * Regular and inlined LZO compressed data extents consist of:
+ *
+ * 1.  Header
+ *     Fixed size. LZO_LEN (4) bytes long, LE32.
+ *     Records the total size (including the header) of compressed data.
+ *
+ * 2.  Segment(s)
+ *     Variable size. Each segment includes one segment header, followd by data
+ *     payload.
+ *     One regular LZO compressed extent can have one or more segments.
+ *     For inlined LZO compressed extent, only one segment is allowed.
+ *     One segment represents at most one page of uncompressed data.
+ *
+ * 2.1 Segment header
+ *     Fixed size. LZO_LEN (4) bytes long, LE32.
+ *     Records the total size of the segment (not including the header).
+ *     Segment header never crosses page boundary, thus it's possible to
+ *     have at most 3 padding zeros at the end of the page.
+ *
+ * 2.2 Data Payload
+ *     Variable size. Size up limit should be lzo1x_worst_compress(PAGE_SIZE)
+ *     which is 4419 for a 4KiB page.
+ *
+ * Example:
+ * Page 1:
+ *          0     0x2   0x4   0x6   0x8   0xa   0xc   0xe     0x10
+ * 0x0000   |  Header   | SegHdr 01 | Data payload 01 ...     |
+ * ...
+ * 0x0ff0   | SegHdr  N | Data payload  N     ...          |00|
+ *                                                          ^^ padding zeros
+ * Page 2:
+ * 0x1000   | SegHdr N+1| Data payload N+1 ...                |
+ */
+
 struct workspace {
 	void *mem;
 	void *buf;	/* where decompressed data goes */
@@ -258,6 +295,7 @@ static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 	unsigned long working_bytes;
 	size_t in_len;
 	size_t out_len;
+	const size_t max_segment_len = lzo1x_worst_compress(PAGE_SIZE);
 	unsigned long in_offset;
 	unsigned long in_page_bytes_left;
 	unsigned long tot_in;
@@ -271,10 +309,22 @@ static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 
 	data_in = kmap(pages_in[0]);
 	tot_len = read_compress_length(data_in);
+	/*
+	 * Compressed data header check.
+	 *
+	 * The real compressed size can't exceed the maximum extent length, and
+	 * all pages should be used (whole unused page with just the segment
+	 * header is not possible).  If this happens it means the compressed
+	 * extent is corrupted.
+	 */
+	if (tot_len > min_t(size_t, BTRFS_MAX_COMPRESSED, srclen) ||
+	    tot_len < srclen - PAGE_SIZE) {
+		ret = -EUCLEAN;
+		goto done;
+	}
 
 	tot_in = LZO_LEN;
 	in_offset = LZO_LEN;
-	tot_len = min_t(size_t, srclen, tot_len);
 	in_page_bytes_left = PAGE_SIZE - LZO_LEN;
 
 	tot_out = 0;
@@ -285,6 +335,17 @@ static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 		in_offset += LZO_LEN;
 		tot_in += LZO_LEN;
 
+		/*
+		 * Segment header check.
+		 *
+		 * The segment length must not exceed the maximum LZO
+		 * compression size, nor the total compressed size.
+		 */
+		if (in_len > max_segment_len || tot_in + in_len > tot_len) {
+			ret = -EUCLEAN;
+			goto done;
+		}
+
 		tot_in += in_len;
 		working_bytes = in_len;
 		may_late_unmap = need_unmap = false;
@@ -335,7 +396,7 @@ cont:
 			}
 		}
 
-		out_len = lzo1x_worst_compress(PAGE_SIZE);
+		out_len = max_segment_len;
 		ret = lzo1x_decompress_safe(buf, in_len, workspace->buf,
 					    &out_len);
 		if (need_unmap)
@@ -369,15 +430,24 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	size_t in_len;
 	size_t out_len;
+	size_t max_segment_len = lzo1x_worst_compress(PAGE_SIZE);
 	int ret = 0;
 	char *kaddr;
 	unsigned long bytes;
 
-	BUG_ON(srclen < LZO_LEN);
+	if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
+		return -EUCLEAN;
 
+	in_len = read_compress_length(data_in);
+	if (in_len != srclen)
+		return -EUCLEAN;
 	data_in += LZO_LEN;
 
 	in_len = read_compress_length(data_in);
+	if (in_len != srclen - LZO_LEN * 2) {
+		ret = -EUCLEAN;
+		goto out;
+	}
 	data_in += LZO_LEN;
 
 	out_len = PAGE_SIZE;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 6db8bb2f2c28..2e1a1694a33d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -343,11 +343,8 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
 
 	if (entry->bytes_left == 0) {
 		ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
-		/*
-		 * Implicit memory barrier after test_and_set_bit
-		 */
-		if (waitqueue_active(&entry->wait))
-			wake_up(&entry->wait);
+		/* test_and_set_bit implies a barrier */
+		cond_wake_up_nomb(&entry->wait);
 	} else {
 		ret = 1;
 	}
@@ -410,11 +407,8 @@ have_entry:
 
 	if (entry->bytes_left == 0) {
 		ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
-		/*
-		 * Implicit memory barrier after test_and_set_bit
-		 */
-		if (waitqueue_active(&entry->wait))
-			wake_up(&entry->wait);
+		/* test_and_set_bit implies a barrier */
+		cond_wake_up_nomb(&entry->wait);
 	} else {
 		ret = 1;
 	}
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 124276bba8cf..a4e11cf04671 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -166,6 +166,25 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
 	}
 }
 
+/*
+ * Helper to output refs and locking status of extent buffer.  Useful to debug
+ * race condition related problems.
+ */
+static void print_eb_refs_lock(struct extent_buffer *eb)
+{
+#ifdef CONFIG_BTRFS_DEBUG
+	btrfs_info(eb->fs_info,
+"refs %u lock (w:%d r:%d bw:%d br:%d sw:%d sr:%d) lock_owner %u current %u",
+		   atomic_read(&eb->refs), atomic_read(&eb->write_locks),
+		   atomic_read(&eb->read_locks),
+		   atomic_read(&eb->blocking_writers),
+		   atomic_read(&eb->blocking_readers),
+		   atomic_read(&eb->spinning_writers),
+		   atomic_read(&eb->spinning_readers),
+		   eb->lock_owner, current->pid);
+#endif
+}
+
 void btrfs_print_leaf(struct extent_buffer *l)
 {
 	struct btrfs_fs_info *fs_info;
@@ -189,9 +208,11 @@ void btrfs_print_leaf(struct extent_buffer *l)
 	fs_info = l->fs_info;
 	nr = btrfs_header_nritems(l);
 
-	btrfs_info(fs_info, "leaf %llu total ptrs %d free space %d",
-		   btrfs_header_bytenr(l), nr,
-		   btrfs_leaf_free_space(fs_info, l));
+	btrfs_info(fs_info,
+		   "leaf %llu gen %llu total ptrs %d free space %d owner %llu",
+		   btrfs_header_bytenr(l), btrfs_header_generation(l), nr,
+		   btrfs_leaf_free_space(fs_info, l), btrfs_header_owner(l));
+	print_eb_refs_lock(l);
 	for (i = 0 ; i < nr ; i++) {
 		item = btrfs_item_nr(i);
 		btrfs_item_key_to_cpu(l, &key, i);
@@ -325,7 +346,7 @@ void btrfs_print_leaf(struct extent_buffer *l)
 	}
 }
 
-void btrfs_print_tree(struct extent_buffer *c)
+void btrfs_print_tree(struct extent_buffer *c, bool follow)
 {
 	struct btrfs_fs_info *fs_info;
 	int i; u32 nr;
@@ -342,15 +363,20 @@ void btrfs_print_tree(struct extent_buffer *c)
 		return;
 	}
 	btrfs_info(fs_info,
-		   "node %llu level %d total ptrs %d free spc %u",
-		   btrfs_header_bytenr(c), level, nr,
-		   (u32)BTRFS_NODEPTRS_PER_BLOCK(fs_info) - nr);
+		   "node %llu level %d gen %llu total ptrs %d free spc %u owner %llu",
+		   btrfs_header_bytenr(c), level, btrfs_header_generation(c),
+		   nr, (u32)BTRFS_NODEPTRS_PER_BLOCK(fs_info) - nr,
+		   btrfs_header_owner(c));
+	print_eb_refs_lock(c);
 	for (i = 0; i < nr; i++) {
 		btrfs_node_key_to_cpu(c, &key, i);
-		pr_info("\tkey %d (%llu %u %llu) block %llu\n",
+		pr_info("\tkey %d (%llu %u %llu) block %llu gen %llu\n",
 		       i, key.objectid, key.type, key.offset,
-		       btrfs_node_blockptr(c, i));
+		       btrfs_node_blockptr(c, i),
+		       btrfs_node_ptr_generation(c, i));
 	}
+	if (!follow)
+		return;
 	for (i = 0; i < nr; i++) {
 		struct btrfs_key first_key;
 		struct extent_buffer *next;
@@ -372,7 +398,7 @@ void btrfs_print_tree(struct extent_buffer *c)
 		if (btrfs_header_level(next) !=
 		       level - 1)
 			BUG();
-		btrfs_print_tree(next);
+		btrfs_print_tree(next, follow);
 		free_extent_buffer(next);
 	}
 }
diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h
index 4a98481688f4..e6bb38fd75ad 100644
--- a/fs/btrfs/print-tree.h
+++ b/fs/btrfs/print-tree.h
@@ -7,6 +7,6 @@
 #define BTRFS_PRINT_TREE_H
 
 void btrfs_print_leaf(struct extent_buffer *l);
-void btrfs_print_tree(struct extent_buffer *c);
+void btrfs_print_tree(struct extent_buffer *c, bool follow);
 
 #endif
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 53a8c95828e3..dc6140013ae8 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -380,6 +380,7 @@ static int prop_compression_apply(struct inode *inode,
 				  const char *value,
 				  size_t len)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	int type;
 
 	if (len == 0) {
@@ -390,14 +391,17 @@ static int prop_compression_apply(struct inode *inode,
 		return 0;
 	}
 
-	if (!strncmp("lzo", value, 3))
+	if (!strncmp("lzo", value, 3)) {
 		type = BTRFS_COMPRESS_LZO;
-	else if (!strncmp("zlib", value, 4))
+		btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+	} else if (!strncmp("zlib", value, 4)) {
 		type = BTRFS_COMPRESS_ZLIB;
-	else if (!strncmp("zstd", value, len))
+	} else if (!strncmp("zstd", value, len)) {
 		type = BTRFS_COMPRESS_ZSTD;
-	else
+		btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
+	} else {
 		return -EINVAL;
+	}
 
 	BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
 	BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 09c7e4fd550f..1874a6d2e6f5 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include <linux/btrfs.h>
+#include <linux/sizes.h>
 
 #include "ctree.h"
 #include "transaction.h"
@@ -1881,8 +1882,8 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
 		cur_old_count = btrfs_qgroup_get_old_refcnt(qg, seq);
 		cur_new_count = btrfs_qgroup_get_new_refcnt(qg, seq);
 
-		trace_qgroup_update_counters(fs_info, qg->qgroupid,
-					     cur_old_count, cur_new_count);
+		trace_qgroup_update_counters(fs_info, qg, cur_old_count,
+					     cur_new_count);
 
 		/* Rfer update part */
 		if (cur_old_count == 0 && cur_new_count > 0) {
@@ -2013,8 +2014,8 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
 
 	BUG_ON(!fs_info->quota_root);
 
-	trace_btrfs_qgroup_account_extent(fs_info, bytenr, num_bytes,
-					  nr_old_roots, nr_new_roots);
+	trace_btrfs_qgroup_account_extent(fs_info, trans->transid, bytenr,
+					num_bytes, nr_old_roots, nr_new_roots);
 
 	qgroups = ulist_alloc(GFP_NOFS);
 	if (!qgroups) {
@@ -2375,8 +2376,21 @@ out:
 	return ret;
 }
 
-static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
+/*
+ * Two limits to commit transaction in advance.
+ *
+ * For RATIO, it will be 1/RATIO of the remaining limit
+ * (excluding data and prealloc meta) as threshold.
+ * For SIZE, it will be in byte unit as threshold.
+ */
+#define QGROUP_PERTRANS_RATIO		32
+#define QGROUP_PERTRANS_SIZE		SZ_32M
+static bool qgroup_check_limits(struct btrfs_fs_info *fs_info,
+				const struct btrfs_qgroup *qg, u64 num_bytes)
 {
+	u64 limit;
+	u64 threshold;
+
 	if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
 	    qgroup_rsv_total(qg) + (s64)qg->rfer + num_bytes > qg->max_rfer)
 		return false;
@@ -2385,6 +2399,31 @@ static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
 	    qgroup_rsv_total(qg) + (s64)qg->excl + num_bytes > qg->max_excl)
 		return false;
 
+	/*
+	 * Even if we passed the check, it's better to check if reservation
+	 * for meta_pertrans is pushing us near limit.
+	 * If there is too much pertrans reservation or it's near the limit,
+	 * let's try commit transaction to free some, using transaction_kthread
+	 */
+	if ((qg->lim_flags & (BTRFS_QGROUP_LIMIT_MAX_RFER |
+			      BTRFS_QGROUP_LIMIT_MAX_EXCL))) {
+		if (qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL)
+			limit = qg->max_excl;
+		else
+			limit = qg->max_rfer;
+		threshold = (limit - qg->rsv.values[BTRFS_QGROUP_RSV_DATA] -
+			    qg->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC]) /
+			    QGROUP_PERTRANS_RATIO;
+		threshold = min_t(u64, threshold, QGROUP_PERTRANS_SIZE);
+
+		/*
+		 * Use transaction_kthread to commit transaction, so we no
+		 * longer need to bother nested transaction nor lock context.
+		 */
+		if (qg->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > threshold)
+			btrfs_commit_transaction_locksafe(fs_info);
+	}
+
 	return true;
 }
 
@@ -2434,7 +2473,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce,
 
 		qg = unode_aux_to_qgroup(unode);
 
-		if (enforce && !qgroup_check_limits(qg, num_bytes)) {
+		if (enforce && !qgroup_check_limits(fs_info, qg, num_bytes)) {
 			ret = -EDQUOT;
 			goto out;
 		}
@@ -2541,6 +2580,21 @@ out:
 }
 
 /*
+ * Check if the leaf is the last leaf. Which means all node pointers
+ * are at their last position.
+ */
+static bool is_last_leaf(struct btrfs_path *path)
+{
+	int i;
+
+	for (i = 1; i < BTRFS_MAX_LEVEL && path->nodes[i]; i++) {
+		if (path->slots[i] != btrfs_header_nritems(path->nodes[i]) - 1)
+			return false;
+	}
+	return true;
+}
+
+/*
  * returns < 0 on error, 0 when more leafs are to be scanned.
  * returns 1 when done.
  */
@@ -2551,8 +2605,8 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	struct btrfs_key found;
 	struct extent_buffer *scratch_leaf = NULL;
 	struct ulist *roots = NULL;
-	struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem);
 	u64 num_bytes;
+	bool done;
 	int slot;
 	int ret;
 
@@ -2581,12 +2635,12 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 		mutex_unlock(&fs_info->qgroup_rescan_lock);
 		return ret;
 	}
+	done = is_last_leaf(path);
 
 	btrfs_item_key_to_cpu(path->nodes[0], &found,
 			      btrfs_header_nritems(path->nodes[0]) - 1);
 	fs_info->qgroup_rescan_progress.objectid = found.objectid + 1;
 
-	btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem);
 	scratch_leaf = btrfs_clone_extent_buffer(path->nodes[0]);
 	if (!scratch_leaf) {
 		ret = -ENOMEM;
@@ -2625,8 +2679,9 @@ out:
 		btrfs_tree_read_unlock_blocking(scratch_leaf);
 		free_extent_buffer(scratch_leaf);
 	}
-	btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem);
 
+	if (done && !ret)
+		ret = 1;
 	return ret;
 }
 
@@ -2642,6 +2697,12 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	path = btrfs_alloc_path();
 	if (!path)
 		goto out;
+	/*
+	 * Rescan should only search for commit root, and any later difference
+	 * should be recorded by qgroup
+	 */
+	path->search_commit_root = 1;
+	path->skip_locking = 1;
 
 	err = 0;
 	while (!err && !btrfs_fs_closing(fs_info)) {
@@ -2721,26 +2782,36 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 {
 	int ret = 0;
 
-	if (!init_flags &&
-	    (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) ||
-	     !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))) {
-		ret = -EINVAL;
-		goto err;
+	if (!init_flags) {
+		/* we're resuming qgroup rescan at mount time */
+		if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN))
+			btrfs_warn(fs_info,
+			"qgroup rescan init failed, qgroup is not enabled");
+		else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
+			btrfs_warn(fs_info,
+			"qgroup rescan init failed, qgroup rescan is not queued");
+		return -EINVAL;
 	}
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	spin_lock(&fs_info->qgroup_lock);
 
 	if (init_flags) {
-		if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
+		if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
+			btrfs_warn(fs_info,
+				   "qgroup rescan is already in progress");
 			ret = -EINPROGRESS;
-		else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
+		} else if (!(fs_info->qgroup_flags &
+			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
+			btrfs_warn(fs_info,
+			"qgroup rescan init failed, qgroup is not enabled");
 			ret = -EINVAL;
+		}
 
 		if (ret) {
 			spin_unlock(&fs_info->qgroup_lock);
 			mutex_unlock(&fs_info->qgroup_rescan_lock);
-			goto err;
+			return ret;
 		}
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN;
 	}
@@ -2759,13 +2830,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
 			btrfs_qgroup_rescan_helper,
 			btrfs_qgroup_rescan_worker, NULL, NULL);
-
-	if (ret) {
-err:
-		btrfs_info(fs_info, "qgroup_rescan_init failed with %d", ret);
-		return ret;
-	}
-
 	return 0;
 }
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 9abd950e7f78..5e4ad134b9ad 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -163,6 +163,12 @@ struct btrfs_raid_bio {
 	 * bitmap to record which horizontal stripe has data
 	 */
 	unsigned long *dbitmap;
+
+	/* allocated with real_stripes-many pointers for finish_*() calls */
+	void **finish_pointers;
+
+	/* allocated with stripe_npages-many bits for finish_*() calls */
+	unsigned long *finish_pbitmap;
 };
 
 static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
@@ -981,9 +987,14 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 	int stripe_npages = DIV_ROUND_UP(stripe_len, PAGE_SIZE);
 	void *p;
 
-	rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 +
-		       DIV_ROUND_UP(stripe_npages, BITS_PER_LONG) *
-		       sizeof(long), GFP_NOFS);
+	rbio = kzalloc(sizeof(*rbio) +
+		       sizeof(*rbio->stripe_pages) * num_pages +
+		       sizeof(*rbio->bio_pages) * num_pages +
+		       sizeof(*rbio->finish_pointers) * real_stripes +
+		       sizeof(*rbio->dbitmap) * BITS_TO_LONGS(stripe_npages) +
+		       sizeof(*rbio->finish_pbitmap) *
+				BITS_TO_LONGS(stripe_npages),
+		       GFP_NOFS);
 	if (!rbio)
 		return ERR_PTR(-ENOMEM);
 
@@ -1005,13 +1016,20 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 	atomic_set(&rbio->stripes_pending, 0);
 
 	/*
-	 * the stripe_pages and bio_pages array point to the extra
+	 * the stripe_pages, bio_pages, etc arrays point to the extra
 	 * memory we allocated past the end of the rbio
 	 */
 	p = rbio + 1;
-	rbio->stripe_pages = p;
-	rbio->bio_pages = p + sizeof(struct page *) * num_pages;
-	rbio->dbitmap = p + sizeof(struct page *) * num_pages * 2;
+#define CONSUME_ALLOC(ptr, count)	do {				\
+		ptr = p;						\
+		p = (unsigned char *)p + sizeof(*(ptr)) * (count);	\
+	} while (0)
+	CONSUME_ALLOC(rbio->stripe_pages, num_pages);
+	CONSUME_ALLOC(rbio->bio_pages, num_pages);
+	CONSUME_ALLOC(rbio->finish_pointers, real_stripes);
+	CONSUME_ALLOC(rbio->dbitmap, BITS_TO_LONGS(stripe_npages));
+	CONSUME_ALLOC(rbio->finish_pbitmap, BITS_TO_LONGS(stripe_npages));
+#undef  CONSUME_ALLOC
 
 	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID5)
 		nr_data = real_stripes - 1;
@@ -1180,7 +1198,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 {
 	struct btrfs_bio *bbio = rbio->bbio;
-	void *pointers[rbio->real_stripes];
+	void **pointers = rbio->finish_pointers;
 	int nr_data = rbio->nr_data;
 	int stripe;
 	int pagenr;
@@ -2350,8 +2368,8 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 					 int need_check)
 {
 	struct btrfs_bio *bbio = rbio->bbio;
-	void *pointers[rbio->real_stripes];
-	DECLARE_BITMAP(pbitmap, rbio->stripe_npages);
+	void **pointers = rbio->finish_pointers;
+	unsigned long *pbitmap = rbio->finish_pbitmap;
 	int nr_data = rbio->nr_data;
 	int stripe;
 	int pagenr;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 00b7d3231821..879b76fa881a 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1841,7 +1841,7 @@ again:
 		old_bytenr = btrfs_node_blockptr(parent, slot);
 		blocksize = fs_info->nodesize;
 		old_ptr_gen = btrfs_node_ptr_generation(parent, slot);
-		btrfs_node_key_to_cpu(parent, &key, slot);
+		btrfs_node_key_to_cpu(parent, &first_key, slot);
 
 		if (level <= max_level) {
 			eb = path->nodes[level];
@@ -4299,7 +4299,7 @@ out:
 	return inode;
 }
 
-static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
+static struct reloc_control *alloc_reloc_control(void)
 {
 	struct reloc_control *rc;
 
@@ -4344,7 +4344,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
 		DESCRIBE_FLAG(RAID5,    "raid5");
 		DESCRIBE_FLAG(RAID6,    "raid6");
 		if (flags)
-			snprintf(buf, buf - bp + sizeof(buf), "|0x%llx", flags);
+			snprintf(bp, buf - bp + sizeof(buf), "|0x%llx", flags);
 #undef DESCRIBE_FLAG
 	}
 
@@ -4366,7 +4366,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	int rw = 0;
 	int err = 0;
 
-	rc = alloc_reloc_control(fs_info);
+	rc = alloc_reloc_control();
 	if (!rc)
 		return -ENOMEM;
 
@@ -4562,7 +4562,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 	if (list_empty(&reloc_roots))
 		goto out;
 
-	rc = alloc_reloc_control(fs_info);
+	rc = alloc_reloc_control();
 	if (!rc) {
 		err = -ENOMEM;
 		goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 52b39a0924e9..a59005862010 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3984,6 +3984,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			spin_lock(&fs_info->unused_bgs_lock);
 			if (list_empty(&cache->bg_list)) {
 				btrfs_get_block_group(cache);
+				trace_btrfs_add_unused_block_group(cache);
 				list_add_tail(&cache->bg_list,
 					      &fs_info->unused_bgs);
 			}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 221e5cdb060b..c47f62b19226 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -235,6 +235,7 @@ struct orphan_dir_info {
 	struct rb_node node;
 	u64 ino;
 	u64 gen;
+	u64 last_dir_index_offset;
 };
 
 struct name_cache_entry {
@@ -2844,12 +2845,6 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
 	struct rb_node *parent = NULL;
 	struct orphan_dir_info *entry, *odi;
 
-	odi = kmalloc(sizeof(*odi), GFP_KERNEL);
-	if (!odi)
-		return ERR_PTR(-ENOMEM);
-	odi->ino = dir_ino;
-	odi->gen = 0;
-
 	while (*p) {
 		parent = *p;
 		entry = rb_entry(parent, struct orphan_dir_info, node);
@@ -2858,11 +2853,17 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
 		} else if (dir_ino > entry->ino) {
 			p = &(*p)->rb_right;
 		} else {
-			kfree(odi);
 			return entry;
 		}
 	}
 
+	odi = kmalloc(sizeof(*odi), GFP_KERNEL);
+	if (!odi)
+		return ERR_PTR(-ENOMEM);
+	odi->ino = dir_ino;
+	odi->gen = 0;
+	odi->last_dir_index_offset = 0;
+
 	rb_link_node(&odi->node, parent, p);
 	rb_insert_color(&odi->node, &sctx->orphan_dirs);
 	return odi;
@@ -2917,6 +2918,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	struct btrfs_key found_key;
 	struct btrfs_key loc;
 	struct btrfs_dir_item *di;
+	struct orphan_dir_info *odi = NULL;
 
 	/*
 	 * Don't try to rmdir the top/root subvolume dir.
@@ -2931,6 +2933,11 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	key.objectid = dir;
 	key.type = BTRFS_DIR_INDEX_KEY;
 	key.offset = 0;
+
+	odi = get_orphan_dir_info(sctx, dir);
+	if (odi)
+		key.offset = odi->last_dir_index_offset;
+
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
@@ -2958,30 +2965,33 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 
 		dm = get_waiting_dir_move(sctx, loc.objectid);
 		if (dm) {
-			struct orphan_dir_info *odi;
-
 			odi = add_orphan_dir_info(sctx, dir);
 			if (IS_ERR(odi)) {
 				ret = PTR_ERR(odi);
 				goto out;
 			}
 			odi->gen = dir_gen;
+			odi->last_dir_index_offset = found_key.offset;
 			dm->rmdir_ino = dir;
 			ret = 0;
 			goto out;
 		}
 
 		if (loc.objectid > send_progress) {
-			struct orphan_dir_info *odi;
-
-			odi = get_orphan_dir_info(sctx, dir);
-			free_orphan_dir_info(sctx, odi);
+			odi = add_orphan_dir_info(sctx, dir);
+			if (IS_ERR(odi)) {
+				ret = PTR_ERR(odi);
+				goto out;
+			}
+			odi->gen = dir_gen;
+			odi->last_dir_index_offset = found_key.offset;
 			ret = 0;
 			goto out;
 		}
 
 		path->slots[0]++;
 	}
+	free_orphan_dir_info(sctx, odi);
 
 	ret = 1;
 
@@ -3259,13 +3269,16 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 
 	if (rmdir_ino) {
 		struct orphan_dir_info *odi;
+		u64 gen;
 
 		odi = get_orphan_dir_info(sctx, rmdir_ino);
 		if (!odi) {
 			/* already deleted */
 			goto finish;
 		}
-		ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino);
+		gen = odi->gen;
+
+		ret = can_rmdir(sctx, rmdir_ino, gen, sctx->cur_ino);
 		if (ret < 0)
 			goto out;
 		if (!ret)
@@ -3276,13 +3289,12 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 			ret = -ENOMEM;
 			goto out;
 		}
-		ret = get_cur_path(sctx, rmdir_ino, odi->gen, name);
+		ret = get_cur_path(sctx, rmdir_ino, gen, name);
 		if (ret < 0)
 			goto out;
 		ret = send_rmdir(sctx, name);
 		if (ret < 0)
 			goto out;
-		free_orphan_dir_info(sctx, odi);
 	}
 
 finish:
@@ -5236,6 +5248,10 @@ static int send_write_or_clone(struct send_ctx *sctx,
 		len = btrfs_file_extent_num_bytes(path->nodes[0], ei);
 	}
 
+	if (offset >= sctx->cur_inode_size) {
+		ret = 0;
+		goto out;
+	}
 	if (offset + len > sctx->cur_inode_size)
 		len = sctx->cur_inode_size - offset;
 	if (len == 0) {
@@ -6450,7 +6466,7 @@ static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
 	 */
 	if (root->send_in_progress < 0)
 		btrfs_err(root->fs_info,
-			  "send_in_progres unbalanced %d root %llu",
+			  "send_in_progress unbalanced %d root %llu",
 			  root->send_in_progress, root->root_key.objectid);
 	spin_unlock(&root->root_item_lock);
 }
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0628092b0b1b..81107ad49f3a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -323,6 +323,7 @@ enum {
 	Opt_ssd, Opt_nossd,
 	Opt_ssd_spread, Opt_nossd_spread,
 	Opt_subvol,
+	Opt_subvol_empty,
 	Opt_subvolid,
 	Opt_thread_pool,
 	Opt_treelog, Opt_notreelog,
@@ -388,6 +389,7 @@ static const match_table_t tokens = {
 	{Opt_ssd_spread, "ssd_spread"},
 	{Opt_nossd_spread, "nossd_spread"},
 	{Opt_subvol, "subvol=%s"},
+	{Opt_subvol_empty, "subvol="},
 	{Opt_subvolid, "subvolid=%s"},
 	{Opt_thread_pool, "thread_pool=%u"},
 	{Opt_treelog, "treelog"},
@@ -461,6 +463,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			btrfs_set_opt(info->mount_opt, DEGRADED);
 			break;
 		case Opt_subvol:
+		case Opt_subvol_empty:
 		case Opt_subvolid:
 		case Opt_subvolrootid:
 		case Opt_device:
@@ -1782,10 +1785,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	}
 
 	ret = btrfs_parse_options(fs_info, data, *flags);
-	if (ret) {
-		ret = -EINVAL;
+	if (ret)
 		goto restore;
-	}
 
 	btrfs_remount_begin(fs_info, old_opts, *flags);
 	btrfs_resize_thread_pool(fs_info,
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4848a4318fb5..4a4e960c7c66 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -210,12 +210,42 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	NULL
 };
 
+/*
+ * Features which depend on feature bits and may differ between each fs.
+ *
+ * /sys/fs/btrfs/features lists all available features of this kernel while
+ * /sys/fs/btrfs/UUID/features shows features of the fs which are enabled or
+ * can be changed online.
+ */
 static const struct attribute_group btrfs_feature_attr_group = {
 	.name = "features",
 	.is_visible = btrfs_feature_visible,
 	.attrs = btrfs_supported_feature_attrs,
 };
 
+static ssize_t rmdir_subvol_show(struct kobject *kobj,
+				 struct kobj_attribute *ka, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0\n");
+}
+BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show);
+
+static struct attribute *btrfs_supported_static_feature_attrs[] = {
+	BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
+	NULL
+};
+
+/*
+ * Features which only depend on kernel version.
+ *
+ * These are listed in /sys/fs/btrfs/features along with
+ * btrfs_feature_attr_group
+ */
+static const struct attribute_group btrfs_static_feature_attr_group = {
+	.name = "features",
+	.attrs = btrfs_supported_static_feature_attrs,
+};
+
 static ssize_t btrfs_show_u64(u64 *value_ptr, spinlock_t *lock, char *buf)
 {
 	u64 val;
@@ -514,10 +544,11 @@ static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj)
 }
 
 #define NUM_FEATURE_BITS 64
-static char btrfs_unknown_feature_names[3][NUM_FEATURE_BITS][13];
-static struct btrfs_feature_attr btrfs_feature_attrs[3][NUM_FEATURE_BITS];
+#define BTRFS_FEATURE_NAME_MAX 13
+static char btrfs_unknown_feature_names[FEAT_MAX][NUM_FEATURE_BITS][BTRFS_FEATURE_NAME_MAX];
+static struct btrfs_feature_attr btrfs_feature_attrs[FEAT_MAX][NUM_FEATURE_BITS];
 
-static const u64 supported_feature_masks[3] = {
+static const u64 supported_feature_masks[FEAT_MAX] = {
 	[FEAT_COMPAT]    = BTRFS_FEATURE_COMPAT_SUPP,
 	[FEAT_COMPAT_RO] = BTRFS_FEATURE_COMPAT_RO_SUPP,
 	[FEAT_INCOMPAT]  = BTRFS_FEATURE_INCOMPAT_SUPP,
@@ -589,7 +620,7 @@ void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs)
 		return;
 	}
 
-	list_for_each_entry(fs_devs, fs_uuids, list) {
+	list_for_each_entry(fs_devs, fs_uuids, fs_list) {
 		__btrfs_sysfs_remove_fsid(fs_devs);
 	}
 }
@@ -609,7 +640,7 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info)
 	btrfs_sysfs_rm_device_link(fs_info->fs_devices, NULL);
 }
 
-const char * const btrfs_feature_set_names[3] = {
+const char * const btrfs_feature_set_names[FEAT_MAX] = {
 	[FEAT_COMPAT]	 = "compat",
 	[FEAT_COMPAT_RO] = "compat_ro",
 	[FEAT_INCOMPAT]	 = "incompat",
@@ -673,7 +704,7 @@ static void init_feature_attrs(void)
 			if (fa->kobj_attr.attr.name)
 				continue;
 
-			snprintf(name, 13, "%s:%u",
+			snprintf(name, BTRFS_FEATURE_NAME_MAX, "%s:%u",
 				 btrfs_feature_set_names[set], i);
 
 			fa->kobj_attr.attr.name = name;
@@ -900,8 +931,15 @@ int __init btrfs_init_sysfs(void)
 	ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
 	if (ret)
 		goto out2;
+	ret = sysfs_merge_group(&btrfs_kset->kobj,
+				&btrfs_static_feature_attr_group);
+	if (ret)
+		goto out_remove_group;
 
 	return 0;
+
+out_remove_group:
+	sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
 out2:
 	debugfs_remove_recursive(btrfs_debugfs_root_dentry);
 out1:
@@ -912,6 +950,8 @@ out1:
 
 void __cold btrfs_exit_sysfs(void)
 {
+	sysfs_unmerge_group(&btrfs_kset->kobj,
+			    &btrfs_static_feature_attr_group);
 	sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
 	kset_unregister(btrfs_kset);
 	debugfs_remove_recursive(btrfs_debugfs_root_dentry);
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index b567560d9aa9..c6ee600aff89 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -9,7 +9,7 @@
 extern u64 btrfs_debugfs_test;
 
 enum btrfs_feature_set {
-	FEAT_COMPAT,
+	FEAT_COMPAT = 0,
 	FEAT_COMPAT_RO,
 	FEAT_INCOMPAT,
 	FEAT_MAX
@@ -77,7 +77,7 @@ attr_to_btrfs_feature_attr(struct attribute *attr)
 }
 
 char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags);
-extern const char * const btrfs_feature_set_names[3];
+extern const char * const btrfs_feature_set_names[FEAT_MAX];
 extern struct kobj_type space_info_ktype;
 extern struct kobj_type btrfs_raid_ktype;
 int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 30ed438da2a9..db72b3b6209e 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -219,11 +219,13 @@ void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache)
 	kfree(cache);
 }
 
-void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans)
+void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans,
+			    struct btrfs_fs_info *fs_info)
 {
 	memset(trans, 0, sizeof(*trans));
 	trans->transid = 1;
 	trans->type = __TRANS_DUMMY;
+	trans->fs_info = fs_info;
 }
 
 int btrfs_run_sanity_tests(void)
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index a5a0b9500d3e..70ff9f9d86a1 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -9,7 +9,8 @@
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 int btrfs_run_sanity_tests(void);
 
-#define test_msg(fmt, ...) pr_info("BTRFS: selftest: " fmt, ##__VA_ARGS__)
+#define test_msg(fmt, ...) pr_info("BTRFS: selftest: " fmt "\n", ##__VA_ARGS__)
+#define test_err(fmt, ...) pr_err("BTRFS: selftest: " fmt "\n", ##__VA_ARGS__)
 
 struct btrfs_root;
 struct btrfs_trans_handle;
@@ -28,7 +29,8 @@ void btrfs_free_dummy_root(struct btrfs_root *root);
 struct btrfs_block_group_cache *
 btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long length);
 void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
-void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans);
+void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans,
+			    struct btrfs_fs_info *fs_info);
 #else
 static inline int btrfs_run_sanity_tests(void)
 {
diff --git a/fs/btrfs/tests/extent-buffer-tests.c b/fs/btrfs/tests/extent-buffer-tests.c
index 31e8a9ec228c..7d72eab6d32c 100644
--- a/fs/btrfs/tests/extent-buffer-tests.c
+++ b/fs/btrfs/tests/extent-buffer-tests.c
@@ -26,31 +26,31 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	u32 value_len = strlen(value);
 	int ret = 0;
 
-	test_msg("Running btrfs_split_item tests\n");
+	test_msg("running btrfs_split_item tests");
 
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
-		test_msg("Could not allocate fs_info\n");
+		test_err("could not allocate fs_info");
 		return -ENOMEM;
 	}
 
 	root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(root)) {
-		test_msg("Could not allocate root\n");
+		test_err("could not allocate root");
 		ret = PTR_ERR(root);
 		goto out;
 	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		test_msg("Could not allocate path\n");
+		test_err("could not allocate path");
 		ret = -ENOMEM;
 		goto out;
 	}
 
 	path->nodes[0] = eb = alloc_dummy_extent_buffer(fs_info, nodesize);
 	if (!eb) {
-		test_msg("Could not allocate dummy buffer\n");
+		test_err("could not allocate dummy buffer");
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -75,7 +75,7 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	 */
 	ret = btrfs_split_item(NULL, root, path, &key, 17);
 	if (ret) {
-		test_msg("Split item failed %d\n", ret);
+		test_err("split item failed %d", ret);
 		goto out;
 	}
 
@@ -86,14 +86,14 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	btrfs_item_key_to_cpu(eb, &key, 0);
 	if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
 	    key.offset != 0) {
-		test_msg("Invalid key at slot 0\n");
+		test_err("invalid key at slot 0");
 		ret = -EINVAL;
 		goto out;
 	}
 
 	item = btrfs_item_nr(0);
 	if (btrfs_item_size(eb, item) != strlen(split1)) {
-		test_msg("Invalid len in the first split\n");
+		test_err("invalid len in the first split");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -101,8 +101,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 0),
 			   strlen(split1));
 	if (memcmp(buf, split1, strlen(split1))) {
-		test_msg("Data in the buffer doesn't match what it should "
-			 "in the first split have='%.*s' want '%s'\n",
+		test_err(
+"data in the buffer doesn't match what it should in the first split have='%.*s' want '%s'",
 			 (int)strlen(split1), buf, split1);
 		ret = -EINVAL;
 		goto out;
@@ -111,14 +111,14 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	btrfs_item_key_to_cpu(eb, &key, 1);
 	if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
 	    key.offset != 3) {
-		test_msg("Invalid key at slot 1\n");
+		test_err("invalid key at slot 1");
 		ret = -EINVAL;
 		goto out;
 	}
 
 	item = btrfs_item_nr(1);
 	if (btrfs_item_size(eb, item) != strlen(split2)) {
-		test_msg("Invalid len in the second split\n");
+		test_err("invalid len in the second split");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -126,8 +126,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 1),
 			   strlen(split2));
 	if (memcmp(buf, split2, strlen(split2))) {
-		test_msg("Data in the buffer doesn't match what it should "
-			 "in the second split\n");
+		test_err(
+	"data in the buffer doesn't match what it should in the second split");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -136,21 +136,21 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	/* Do it again so we test memmoving the other items in the leaf */
 	ret = btrfs_split_item(NULL, root, path, &key, 4);
 	if (ret) {
-		test_msg("Second split item failed %d\n", ret);
+		test_err("second split item failed %d", ret);
 		goto out;
 	}
 
 	btrfs_item_key_to_cpu(eb, &key, 0);
 	if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
 	    key.offset != 0) {
-		test_msg("Invalid key at slot 0\n");
+		test_err("invalid key at slot 0");
 		ret = -EINVAL;
 		goto out;
 	}
 
 	item = btrfs_item_nr(0);
 	if (btrfs_item_size(eb, item) != strlen(split3)) {
-		test_msg("Invalid len in the first split\n");
+		test_err("invalid len in the first split");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -158,8 +158,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 0),
 			   strlen(split3));
 	if (memcmp(buf, split3, strlen(split3))) {
-		test_msg("Data in the buffer doesn't match what it should "
-			 "in the third split");
+		test_err(
+	"data in the buffer doesn't match what it should in the third split");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -167,14 +167,14 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	btrfs_item_key_to_cpu(eb, &key, 1);
 	if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
 	    key.offset != 1) {
-		test_msg("Invalid key at slot 1\n");
+		test_err("invalid key at slot 1");
 		ret = -EINVAL;
 		goto out;
 	}
 
 	item = btrfs_item_nr(1);
 	if (btrfs_item_size(eb, item) != strlen(split4)) {
-		test_msg("Invalid len in the second split\n");
+		test_err("invalid len in the second split");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -182,8 +182,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 1),
 			   strlen(split4));
 	if (memcmp(buf, split4, strlen(split4))) {
-		test_msg("Data in the buffer doesn't match what it should "
-			 "in the fourth split\n");
+		test_err(
+	"data in the buffer doesn't match what it should in the fourth split");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -191,14 +191,14 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	btrfs_item_key_to_cpu(eb, &key, 2);
 	if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
 	    key.offset != 3) {
-		test_msg("Invalid key at slot 2\n");
+		test_err("invalid key at slot 2");
 		ret = -EINVAL;
 		goto out;
 	}
 
 	item = btrfs_item_nr(2);
 	if (btrfs_item_size(eb, item) != strlen(split2)) {
-		test_msg("Invalid len in the second split\n");
+		test_err("invalid len in the second split");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -206,8 +206,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 	read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 2),
 			   strlen(split2));
 	if (memcmp(buf, split2, strlen(split2))) {
-		test_msg("Data in the buffer doesn't match what it should "
-			 "in the last chunk\n");
+		test_err(
+	"data in the buffer doesn't match what it should in the last chunk");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -220,6 +220,6 @@ out:
 
 int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize)
 {
-	test_msg("Running extent buffer operation tests\n");
+	test_msg("running extent buffer operation tests");
 	return test_btrfs_split_item(sectorsize, nodesize);
 }
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 76aa5a678a96..d9269a531a4d 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -46,7 +46,9 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
 		cond_resched();
 		loops++;
 		if (loops > 100000) {
-			printk(KERN_ERR "stuck in a loop, start %Lu, end %Lu, nr_pages %lu, ret %d\n", start, end, nr_pages, ret);
+			printk(KERN_ERR
+		"stuck in a loop, start %llu, end %llu, nr_pages %lu, ret %d\n",
+				start, end, nr_pages, ret);
 			break;
 		}
 	}
@@ -66,11 +68,11 @@ static int test_find_delalloc(u32 sectorsize)
 	u64 found;
 	int ret = -EINVAL;
 
-	test_msg("Running find delalloc tests\n");
+	test_msg("running find delalloc tests");
 
 	inode = btrfs_new_test_inode();
 	if (!inode) {
-		test_msg("Failed to allocate test inode\n");
+		test_err("failed to allocate test inode");
 		return -ENOMEM;
 	}
 
@@ -84,7 +86,7 @@ static int test_find_delalloc(u32 sectorsize)
 	for (index = 0; index < (total_dirty >> PAGE_SHIFT); index++) {
 		page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
 		if (!page) {
-			test_msg("Failed to allocate test page\n");
+			test_err("failed to allocate test page");
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -107,11 +109,11 @@ static int test_find_delalloc(u32 sectorsize)
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
 					 &end, max_bytes);
 	if (!found) {
-		test_msg("Should have found at least one delalloc\n");
+		test_err("should have found at least one delalloc");
 		goto out_bits;
 	}
 	if (start != 0 || end != (sectorsize - 1)) {
-		test_msg("Expected start 0 end %u, got start %llu end %llu\n",
+		test_err("expected start 0 end %u, got start %llu end %llu",
 			sectorsize - 1, start, end);
 		goto out_bits;
 	}
@@ -129,7 +131,7 @@ static int test_find_delalloc(u32 sectorsize)
 	locked_page = find_lock_page(inode->i_mapping,
 				     test_start >> PAGE_SHIFT);
 	if (!locked_page) {
-		test_msg("Couldn't find the locked page\n");
+		test_err("couldn't find the locked page");
 		goto out_bits;
 	}
 	set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, 0, NULL);
@@ -138,17 +140,17 @@ static int test_find_delalloc(u32 sectorsize)
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
 					 &end, max_bytes);
 	if (!found) {
-		test_msg("Couldn't find delalloc in our range\n");
+		test_err("couldn't find delalloc in our range");
 		goto out_bits;
 	}
 	if (start != test_start || end != max_bytes - 1) {
-		test_msg("Expected start %Lu end %Lu, got start %Lu, end "
-			 "%Lu\n", test_start, max_bytes - 1, start, end);
+		test_err("expected start %llu end %llu, got start %llu, end %llu",
+				test_start, max_bytes - 1, start, end);
 		goto out_bits;
 	}
 	if (process_page_range(inode, start, end,
 			       PROCESS_TEST_LOCKED | PROCESS_UNLOCK)) {
-		test_msg("There were unlocked pages in the range\n");
+		test_err("there were unlocked pages in the range");
 		goto out_bits;
 	}
 	unlock_extent(&tmp, start, end);
@@ -164,7 +166,7 @@ static int test_find_delalloc(u32 sectorsize)
 	locked_page = find_lock_page(inode->i_mapping, test_start >>
 				     PAGE_SHIFT);
 	if (!locked_page) {
-		test_msg("Couldn't find the locked page\n");
+		test_err("couldn't find the locked page");
 		goto out_bits;
 	}
 	start = test_start;
@@ -172,11 +174,11 @@ static int test_find_delalloc(u32 sectorsize)
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
 					 &end, max_bytes);
 	if (found) {
-		test_msg("Found range when we shouldn't have\n");
+		test_err("found range when we shouldn't have");
 		goto out_bits;
 	}
 	if (end != (u64)-1) {
-		test_msg("Did not return the proper end offset\n");
+		test_err("did not return the proper end offset");
 		goto out_bits;
 	}
 
@@ -193,17 +195,17 @@ static int test_find_delalloc(u32 sectorsize)
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
 					 &end, max_bytes);
 	if (!found) {
-		test_msg("Didn't find our range\n");
+		test_err("didn't find our range");
 		goto out_bits;
 	}
 	if (start != test_start || end != total_dirty - 1) {
-		test_msg("Expected start %Lu end %Lu, got start %Lu end %Lu\n",
+		test_err("expected start %llu end %llu, got start %llu end %llu",
 			 test_start, total_dirty - 1, start, end);
 		goto out_bits;
 	}
 	if (process_page_range(inode, start, end,
 			       PROCESS_TEST_LOCKED | PROCESS_UNLOCK)) {
-		test_msg("Pages in range were not all locked\n");
+		test_err("pages in range were not all locked");
 		goto out_bits;
 	}
 	unlock_extent(&tmp, start, end);
@@ -215,7 +217,7 @@ static int test_find_delalloc(u32 sectorsize)
 	page = find_get_page(inode->i_mapping,
 			     (max_bytes + SZ_1M) >> PAGE_SHIFT);
 	if (!page) {
-		test_msg("Couldn't find our page\n");
+		test_err("couldn't find our page");
 		goto out_bits;
 	}
 	ClearPageDirty(page);
@@ -234,18 +236,17 @@ static int test_find_delalloc(u32 sectorsize)
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
 					 &end, max_bytes);
 	if (!found) {
-		test_msg("Didn't find our range\n");
+		test_err("didn't find our range");
 		goto out_bits;
 	}
 	if (start != test_start && end != test_start + PAGE_SIZE - 1) {
-		test_msg("Expected start %Lu end %Lu, got start %Lu end %Lu\n",
-			 test_start, test_start + PAGE_SIZE - 1, start,
-			 end);
+		test_err("expected start %llu end %llu, got start %llu end %llu",
+			 test_start, test_start + PAGE_SIZE - 1, start, end);
 		goto out_bits;
 	}
 	if (process_page_range(inode, start, end, PROCESS_TEST_LOCKED |
 			       PROCESS_UNLOCK)) {
-		test_msg("Pages in range were not all locked\n");
+		test_err("pages in range were not all locked");
 		goto out_bits;
 	}
 	ret = 0;
@@ -271,14 +272,14 @@ static int check_eb_bitmap(unsigned long *bitmap, struct extent_buffer *eb,
 		bit = !!test_bit(i, bitmap);
 		bit1 = !!extent_buffer_test_bit(eb, 0, i);
 		if (bit1 != bit) {
-			test_msg("Bits do not match\n");
+			test_err("bits do not match");
 			return -EINVAL;
 		}
 
 		bit1 = !!extent_buffer_test_bit(eb, i / BITS_PER_BYTE,
 						i % BITS_PER_BYTE);
 		if (bit1 != bit) {
-			test_msg("Offset bits do not match\n");
+			test_err("offset bits do not match");
 			return -EINVAL;
 		}
 	}
@@ -295,7 +296,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 	memset(bitmap, 0, len);
 	memzero_extent_buffer(eb, 0, len);
 	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
-		test_msg("Bitmap was not zeroed\n");
+		test_err("bitmap was not zeroed");
 		return -EINVAL;
 	}
 
@@ -303,7 +304,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 	extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
 	ret = check_eb_bitmap(bitmap, eb, len);
 	if (ret) {
-		test_msg("Setting all bits failed\n");
+		test_err("setting all bits failed");
 		return ret;
 	}
 
@@ -311,7 +312,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 	extent_buffer_bitmap_clear(eb, 0, 0, len * BITS_PER_BYTE);
 	ret = check_eb_bitmap(bitmap, eb, len);
 	if (ret) {
-		test_msg("Clearing all bits failed\n");
+		test_err("clearing all bits failed");
 		return ret;
 	}
 
@@ -324,7 +325,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 					sizeof(long) * BITS_PER_BYTE);
 		ret = check_eb_bitmap(bitmap, eb, len);
 		if (ret) {
-			test_msg("Setting straddling pages failed\n");
+			test_err("setting straddling pages failed");
 			return ret;
 		}
 
@@ -337,7 +338,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 					sizeof(long) * BITS_PER_BYTE);
 		ret = check_eb_bitmap(bitmap, eb, len);
 		if (ret) {
-			test_msg("Clearing straddling pages failed\n");
+			test_err("clearing straddling pages failed");
 			return ret;
 		}
 	}
@@ -361,7 +362,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 
 	ret = check_eb_bitmap(bitmap, eb, len);
 	if (ret) {
-		test_msg("Random bit pattern failed\n");
+		test_err("random bit pattern failed");
 		return ret;
 	}
 
@@ -376,7 +377,7 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
 	struct extent_buffer *eb;
 	int ret;
 
-	test_msg("Running extent buffer bitmap tests\n");
+	test_msg("running extent buffer bitmap tests");
 
 	/*
 	 * In ppc64, sectorsize can be 64K, thus 4 * 64K will be larger than
@@ -389,13 +390,13 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
 
 	bitmap = kmalloc(len, GFP_KERNEL);
 	if (!bitmap) {
-		test_msg("Couldn't allocate test bitmap\n");
+		test_err("couldn't allocate test bitmap");
 		return -ENOMEM;
 	}
 
 	eb = __alloc_dummy_extent_buffer(fs_info, 0, len);
 	if (!eb) {
-		test_msg("Couldn't allocate test extent buffer\n");
+		test_err("couldn't allocate test extent buffer");
 		kfree(bitmap);
 		return -ENOMEM;
 	}
@@ -408,7 +409,7 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
 	free_extent_buffer(eb);
 	eb = __alloc_dummy_extent_buffer(NULL, nodesize / 2, len);
 	if (!eb) {
-		test_msg("Couldn't allocate test extent buffer\n");
+		test_err("couldn't allocate test extent buffer");
 		kfree(bitmap);
 		return -ENOMEM;
 	}
@@ -424,7 +425,7 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 {
 	int ret;
 
-	test_msg("Running extent I/O tests\n");
+	test_msg("running extent I/O tests");
 
 	ret = test_find_delalloc(sectorsize);
 	if (ret)
@@ -432,6 +433,6 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 
 	ret = test_eb_bitmaps(sectorsize, nodesize);
 out:
-	test_msg("Extent I/O tests finished\n");
+	test_msg("extent I/O tests finished");
 	return ret;
 }
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index 79e0a5f4d9c9..385a5316e4bf 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -19,8 +19,8 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree)
 
 #ifdef CONFIG_BTRFS_DEBUG
 		if (refcount_read(&em->refs) != 1) {
-			test_msg(
-"em leak: em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx) refs %d\n",
+			test_err(
+"em leak: em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx) refs %d",
 				 em->start, em->len, em->block_start,
 				 em->block_len, refcount_read(&em->refs));
 
@@ -47,7 +47,8 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree)
  *                                    ->add_extent_mapping(0, 16K)
  *                                    -> #handle -EEXIST
  */
-static void test_case_1(struct extent_map_tree *em_tree)
+static void test_case_1(struct btrfs_fs_info *fs_info,
+		struct extent_map_tree *em_tree)
 {
 	struct extent_map *em;
 	u64 start = 0;
@@ -90,14 +91,14 @@ static void test_case_1(struct extent_map_tree *em_tree)
 	em->len = len;
 	em->block_start = start;
 	em->block_len = len;
-	ret = btrfs_add_extent_mapping(em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	if (ret)
-		test_msg("case1 [%llu %llu]: ret %d\n", start, start + len, ret);
+		test_err("case1 [%llu %llu]: ret %d", start, start + len, ret);
 	if (em &&
 	    (em->start != 0 || extent_map_end(em) != SZ_16K ||
 	     em->block_start != 0 || em->block_len != SZ_16K))
-		test_msg(
-"case1 [%llu %llu]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu\n",
+		test_err(
+"case1 [%llu %llu]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu",
 			 start, start + len, ret, em->start, em->len,
 			 em->block_start, em->block_len);
 	free_extent_map(em);
@@ -112,7 +113,8 @@ out:
  * Reading the inline ending up with EEXIST, ie. read an inline
  * extent and discard page cache and read it again.
  */
-static void test_case_2(struct extent_map_tree *em_tree)
+static void test_case_2(struct btrfs_fs_info *fs_info,
+		struct extent_map_tree *em_tree)
 {
 	struct extent_map *em;
 	int ret;
@@ -153,14 +155,14 @@ static void test_case_2(struct extent_map_tree *em_tree)
 	em->len = SZ_1K;
 	em->block_start = EXTENT_MAP_INLINE;
 	em->block_len = (u64)-1;
-	ret = btrfs_add_extent_mapping(em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	if (ret)
-		test_msg("case2 [0 1K]: ret %d\n", ret);
+		test_err("case2 [0 1K]: ret %d", ret);
 	if (em &&
 	    (em->start != 0 || extent_map_end(em) != SZ_1K ||
 	     em->block_start != EXTENT_MAP_INLINE || em->block_len != (u64)-1))
-		test_msg(
-"case2 [0 1K]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu\n",
+		test_err(
+"case2 [0 1K]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu",
 			 ret, em->start, em->len, em->block_start,
 			 em->block_len);
 	free_extent_map(em);
@@ -169,7 +171,8 @@ out:
 	free_extent_map_tree(em_tree);
 }
 
-static void __test_case_3(struct extent_map_tree *em_tree, u64 start)
+static void __test_case_3(struct btrfs_fs_info *fs_info,
+		struct extent_map_tree *em_tree, u64 start)
 {
 	struct extent_map *em;
 	u64 len = SZ_4K;
@@ -198,9 +201,9 @@ static void __test_case_3(struct extent_map_tree *em_tree, u64 start)
 	em->len = SZ_16K;
 	em->block_start = 0;
 	em->block_len = SZ_16K;
-	ret = btrfs_add_extent_mapping(em_tree, &em, start, len);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
 	if (ret)
-		test_msg("case3 [0x%llx 0x%llx): ret %d\n",
+		test_err("case3 [0x%llx 0x%llx): ret %d",
 			 start, start + len, ret);
 	/*
 	 * Since bytes within em are contiguous, em->block_start is identical to
@@ -209,8 +212,8 @@ static void __test_case_3(struct extent_map_tree *em_tree, u64 start)
 	if (em &&
 	    (start < em->start || start + len > extent_map_end(em) ||
 	     em->start != em->block_start || em->len != em->block_len))
-		test_msg(
-"case3 [0x%llx 0x%llx): ret %d em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)\n",
+		test_err(
+"case3 [0x%llx 0x%llx): ret %d em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)",
 			 start, start + len, ret, em->start, em->len,
 			 em->block_start, em->block_len);
 	free_extent_map(em);
@@ -235,14 +238,16 @@ out:
  *   -> add_extent_mapping()
  *                            -> add_extent_mapping()
  */
-static void test_case_3(struct extent_map_tree *em_tree)
+static void test_case_3(struct btrfs_fs_info *fs_info,
+		struct extent_map_tree *em_tree)
 {
-	__test_case_3(em_tree, 0);
-	__test_case_3(em_tree, SZ_8K);
-	__test_case_3(em_tree, (12 * 1024ULL));
+	__test_case_3(fs_info, em_tree, 0);
+	__test_case_3(fs_info, em_tree, SZ_8K);
+	__test_case_3(fs_info, em_tree, (12 * 1024ULL));
 }
 
-static void __test_case_4(struct extent_map_tree *em_tree, u64 start)
+static void __test_case_4(struct btrfs_fs_info *fs_info,
+		struct extent_map_tree *em_tree, u64 start)
 {
 	struct extent_map *em;
 	u64 len = SZ_4K;
@@ -283,14 +288,14 @@ static void __test_case_4(struct extent_map_tree *em_tree, u64 start)
 	em->len = SZ_32K;
 	em->block_start = 0;
 	em->block_len = SZ_32K;
-	ret = btrfs_add_extent_mapping(em_tree, &em, start, len);
+	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
 	if (ret)
-		test_msg("case4 [0x%llx 0x%llx): ret %d\n",
+		test_err("case4 [0x%llx 0x%llx): ret %d",
 			 start, len, ret);
 	if (em &&
 	    (start < em->start || start + len > extent_map_end(em)))
-		test_msg(
-"case4 [0x%llx 0x%llx): ret %d, added wrong em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)\n",
+		test_err(
+"case4 [0x%llx 0x%llx): ret %d, added wrong em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)",
 			 start, len, ret, em->start, em->len, em->block_start,
 			 em->block_len);
 	free_extent_map(em);
@@ -324,30 +329,45 @@ out:
  *                                             # handle -EEXIST when adding
  *                                             # [0, 32K)
  */
-static void test_case_4(struct extent_map_tree *em_tree)
+static void test_case_4(struct btrfs_fs_info *fs_info,
+		struct extent_map_tree *em_tree)
 {
-	__test_case_4(em_tree, 0);
-	__test_case_4(em_tree, SZ_4K);
+	__test_case_4(fs_info, em_tree, 0);
+	__test_case_4(fs_info, em_tree, SZ_4K);
 }
 
 int btrfs_test_extent_map(void)
 {
+	struct btrfs_fs_info *fs_info = NULL;
 	struct extent_map_tree *em_tree;
 
-	test_msg("Running extent_map tests\n");
+	test_msg("running extent_map tests");
+
+	/*
+	 * Note: the fs_info is not set up completely, we only need
+	 * fs_info::fsid for the tracepoint.
+	 */
+	fs_info = btrfs_alloc_dummy_fs_info(PAGE_SIZE, PAGE_SIZE);
+	if (!fs_info) {
+		test_msg("Couldn't allocate dummy fs info");
+		return -ENOMEM;
+	}
 
 	em_tree = kzalloc(sizeof(*em_tree), GFP_KERNEL);
 	if (!em_tree)
 		/* Skip the test on error. */
-		return 0;
+		goto out;
 
 	extent_map_tree_init(em_tree);
 
-	test_case_1(em_tree);
-	test_case_2(em_tree);
-	test_case_3(em_tree);
-	test_case_4(em_tree);
+	test_case_1(fs_info, em_tree);
+	test_case_2(fs_info, em_tree);
+	test_case_3(fs_info, em_tree);
+	test_case_4(fs_info, em_tree);
 
 	kfree(em_tree);
+out:
+	btrfs_free_dummy_fs_info(fs_info);
+
 	return 0;
 }
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index d3c9f8a59ba5..5c2f77e9439b 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -20,63 +20,63 @@ static int test_extents(struct btrfs_block_group_cache *cache)
 {
 	int ret = 0;
 
-	test_msg("Running extent only tests\n");
+	test_msg("running extent only tests");
 
 	/* First just make sure we can remove an entire entry */
 	ret = btrfs_add_free_space(cache, 0, SZ_4M);
 	if (ret) {
-		test_msg("Error adding initial extents %d\n", ret);
+		test_err("error adding initial extents %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, 0, SZ_4M);
 	if (ret) {
-		test_msg("Error removing extent %d\n", ret);
+		test_err("error removing extent %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, 0, SZ_4M)) {
-		test_msg("Full remove left some lingering space\n");
+		test_err("full remove left some lingering space");
 		return -1;
 	}
 
 	/* Ok edge and middle cases now */
 	ret = btrfs_add_free_space(cache, 0, SZ_4M);
 	if (ret) {
-		test_msg("Error adding half extent %d\n", ret);
+		test_err("error adding half extent %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, 3 * SZ_1M, SZ_1M);
 	if (ret) {
-		test_msg("Error removing tail end %d\n", ret);
+		test_err("error removing tail end %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, 0, SZ_1M);
 	if (ret) {
-		test_msg("Error removing front end %d\n", ret);
+		test_err("error removing front end %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, SZ_2M, 4096);
 	if (ret) {
-		test_msg("Error removing middle piece %d\n", ret);
+		test_err("error removing middle piece %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, 0, SZ_1M)) {
-		test_msg("Still have space at the front\n");
+		test_err("still have space at the front");
 		return -1;
 	}
 
 	if (test_check_exists(cache, SZ_2M, 4096)) {
-		test_msg("Still have space in the middle\n");
+		test_err("still have space in the middle");
 		return -1;
 	}
 
 	if (test_check_exists(cache, 3 * SZ_1M, SZ_1M)) {
-		test_msg("Still have space at the end\n");
+		test_err("still have space at the end");
 		return -1;
 	}
 
@@ -92,34 +92,34 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache,
 	u64 next_bitmap_offset;
 	int ret;
 
-	test_msg("Running bitmap only tests\n");
+	test_msg("running bitmap only tests");
 
 	ret = test_add_free_space_entry(cache, 0, SZ_4M, 1);
 	if (ret) {
-		test_msg("Couldn't create a bitmap entry %d\n", ret);
+		test_err("couldn't create a bitmap entry %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, 0, SZ_4M);
 	if (ret) {
-		test_msg("Error removing bitmap full range %d\n", ret);
+		test_err("error removing bitmap full range %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, 0, SZ_4M)) {
-		test_msg("Left some space in bitmap\n");
+		test_err("left some space in bitmap");
 		return -1;
 	}
 
 	ret = test_add_free_space_entry(cache, 0, SZ_4M, 1);
 	if (ret) {
-		test_msg("Couldn't add to our bitmap entry %d\n", ret);
+		test_err("couldn't add to our bitmap entry %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, SZ_1M, SZ_2M);
 	if (ret) {
-		test_msg("Couldn't remove middle chunk %d\n", ret);
+		test_err("couldn't remove middle chunk %d", ret);
 		return ret;
 	}
 
@@ -133,19 +133,19 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache,
 	ret = test_add_free_space_entry(cache, next_bitmap_offset - SZ_2M,
 					SZ_4M, 1);
 	if (ret) {
-		test_msg("Couldn't add space that straddles two bitmaps %d\n",
+		test_err("couldn't add space that straddles two bitmaps %d",
 				ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, next_bitmap_offset - SZ_1M, SZ_2M);
 	if (ret) {
-		test_msg("Couldn't remove overlapping space %d\n", ret);
+		test_err("couldn't remove overlapping space %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, next_bitmap_offset - SZ_1M, SZ_2M)) {
-		test_msg("Left some space when removing overlapping\n");
+		test_err("left some space when removing overlapping");
 		return -1;
 	}
 
@@ -161,7 +161,7 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
 	u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
 	int ret;
 
-	test_msg("Running bitmap and extent tests\n");
+	test_msg("running bitmap and extent tests");
 
 	/*
 	 * First let's do something simple, an extent at the same offset as the
@@ -170,42 +170,42 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
 	 */
 	ret = test_add_free_space_entry(cache, SZ_4M, SZ_1M, 1);
 	if (ret) {
-		test_msg("Couldn't create bitmap entry %d\n", ret);
+		test_err("couldn't create bitmap entry %d", ret);
 		return ret;
 	}
 
 	ret = test_add_free_space_entry(cache, 0, SZ_1M, 0);
 	if (ret) {
-		test_msg("Couldn't add extent entry %d\n", ret);
+		test_err("couldn't add extent entry %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, 0, SZ_1M);
 	if (ret) {
-		test_msg("Couldn't remove extent entry %d\n", ret);
+		test_err("couldn't remove extent entry %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, 0, SZ_1M)) {
-		test_msg("Left remnants after our remove\n");
+		test_err("left remnants after our remove");
 		return -1;
 	}
 
 	/* Now to add back the extent entry and remove from the bitmap */
 	ret = test_add_free_space_entry(cache, 0, SZ_1M, 0);
 	if (ret) {
-		test_msg("Couldn't re-add extent entry %d\n", ret);
+		test_err("couldn't re-add extent entry %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, SZ_4M, SZ_1M);
 	if (ret) {
-		test_msg("Couldn't remove from bitmap %d\n", ret);
+		test_err("couldn't remove from bitmap %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, SZ_4M, SZ_1M)) {
-		test_msg("Left remnants in the bitmap\n");
+		test_err("left remnants in the bitmap");
 		return -1;
 	}
 
@@ -215,18 +215,18 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
 	 */
 	ret = test_add_free_space_entry(cache, SZ_1M, SZ_4M, 1);
 	if (ret) {
-		test_msg("Couldn't add to a bitmap %d\n", ret);
+		test_err("couldn't add to a bitmap %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, SZ_512K, 3 * SZ_1M);
 	if (ret) {
-		test_msg("Couldn't remove overlapping space %d\n", ret);
+		test_err("couldn't remove overlapping space %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, SZ_512K, 3 * SZ_1M)) {
-		test_msg("Left over pieces after removing overlapping\n");
+		test_err("left over pieces after removing overlapping");
 		return -1;
 	}
 
@@ -235,24 +235,24 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
 	/* Now with the extent entry offset into the bitmap */
 	ret = test_add_free_space_entry(cache, SZ_4M, SZ_4M, 1);
 	if (ret) {
-		test_msg("Couldn't add space to the bitmap %d\n", ret);
+		test_err("couldn't add space to the bitmap %d", ret);
 		return ret;
 	}
 
 	ret = test_add_free_space_entry(cache, SZ_2M, SZ_2M, 0);
 	if (ret) {
-		test_msg("Couldn't add extent to the cache %d\n", ret);
+		test_err("couldn't add extent to the cache %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, 3 * SZ_1M, SZ_4M);
 	if (ret) {
-		test_msg("Problem removing overlapping space %d\n", ret);
+		test_err("problem removing overlapping space %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, 3 * SZ_1M, SZ_4M)) {
-		test_msg("Left something behind when removing space");
+		test_err("left something behind when removing space");
 		return -1;
 	}
 
@@ -269,25 +269,25 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
 	__btrfs_remove_free_space_cache(cache->free_space_ctl);
 	ret = test_add_free_space_entry(cache, bitmap_offset + SZ_4M, SZ_4M, 1);
 	if (ret) {
-		test_msg("Couldn't add bitmap %d\n", ret);
+		test_err("couldn't add bitmap %d", ret);
 		return ret;
 	}
 
 	ret = test_add_free_space_entry(cache, bitmap_offset - SZ_1M,
 					5 * SZ_1M, 0);
 	if (ret) {
-		test_msg("Couldn't add extent entry %d\n", ret);
+		test_err("couldn't add extent entry %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, bitmap_offset + SZ_1M, 5 * SZ_1M);
 	if (ret) {
-		test_msg("Failed to free our space %d\n", ret);
+		test_err("failed to free our space %d", ret);
 		return ret;
 	}
 
 	if (test_check_exists(cache, bitmap_offset + SZ_1M, 5 * SZ_1M)) {
-		test_msg("Left stuff over\n");
+		test_err("left stuff over");
 		return -1;
 	}
 
@@ -301,19 +301,19 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
 	 */
 	ret = test_add_free_space_entry(cache, SZ_1M, SZ_2M, 1);
 	if (ret) {
-		test_msg("Couldn't add bitmap entry %d\n", ret);
+		test_err("couldn't add bitmap entry %d", ret);
 		return ret;
 	}
 
 	ret = test_add_free_space_entry(cache, 3 * SZ_1M, SZ_1M, 0);
 	if (ret) {
-		test_msg("Couldn't add extent entry %d\n", ret);
+		test_err("couldn't add extent entry %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_remove_free_space(cache, SZ_1M, 3 * SZ_1M);
 	if (ret) {
-		test_msg("Error removing bitmap and extent overlapping %d\n", ret);
+		test_err("error removing bitmap and extent overlapping %d", ret);
 		return ret;
 	}
 
@@ -335,12 +335,14 @@ check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
 			      const int num_bitmaps)
 {
 	if (cache->free_space_ctl->free_extents != num_extents) {
-		test_msg("Incorrect # of extent entries in the cache: %d, expected %d\n",
+		test_err(
+		"incorrect # of extent entries in the cache: %d, expected %d",
 			 cache->free_space_ctl->free_extents, num_extents);
 		return -EINVAL;
 	}
 	if (cache->free_space_ctl->total_bitmaps != num_bitmaps) {
-		test_msg("Incorrect # of extent entries in the cache: %d, expected %d\n",
+		test_err(
+		"incorrect # of extent entries in the cache: %d, expected %d",
 			 cache->free_space_ctl->total_bitmaps, num_bitmaps);
 		return -EINVAL;
 	}
@@ -358,7 +360,7 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
 	 * allocate.
 	 */
 	if (cache->free_space_ctl->free_space != 0) {
-		test_msg("Cache free space is not 0\n");
+		test_err("cache free space is not 0");
 		return -EINVAL;
 	}
 
@@ -366,7 +368,7 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
 	offset = btrfs_find_space_for_alloc(cache, 0, 4096, 0,
 					    &max_extent_size);
 	if (offset != 0) {
-		test_msg("Space allocation did not fail, returned offset: %llu",
+		test_err("space allocation did not fail, returned offset: %llu",
 			 offset);
 		return -EINVAL;
 	}
@@ -402,7 +404,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	};
 	const struct btrfs_free_space_op *orig_free_space_ops;
 
-	test_msg("Running space stealing from bitmap to extent\n");
+	test_msg("running space stealing from bitmap to extent");
 
 	/*
 	 * For this test, we want to ensure we end up with an extent entry
@@ -430,7 +432,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = test_add_free_space_entry(cache, SZ_128M - SZ_256K, SZ_128K, 0);
 	if (ret) {
-		test_msg("Couldn't add extent entry %d\n", ret);
+		test_err("couldn't add extent entry %d", ret);
 		return ret;
 	}
 
@@ -438,7 +440,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	ret = test_add_free_space_entry(cache, SZ_128M + SZ_512K,
 					SZ_128M - SZ_512K, 1);
 	if (ret) {
-		test_msg("Couldn't add bitmap entry %d\n", ret);
+		test_err("couldn't add bitmap entry %d", ret);
 		return ret;
 	}
 
@@ -457,17 +459,17 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 				      SZ_128M + 768 * SZ_1K,
 				      SZ_128M - 768 * SZ_1K);
 	if (ret) {
-		test_msg("Failed to free part of bitmap space %d\n", ret);
+		test_err("failed to free part of bitmap space %d", ret);
 		return ret;
 	}
 
 	/* Confirm that only those 2 ranges are marked as free. */
 	if (!test_check_exists(cache, SZ_128M - SZ_256K, SZ_128K)) {
-		test_msg("Free space range missing\n");
+		test_err("free space range missing");
 		return -ENOENT;
 	}
 	if (!test_check_exists(cache, SZ_128M + SZ_512K, SZ_256K)) {
-		test_msg("Free space range missing\n");
+		test_err("free space range missing");
 		return -ENOENT;
 	}
 
@@ -477,7 +479,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	if (test_check_exists(cache, SZ_128M + 768 * SZ_1K,
 			      SZ_128M - 768 * SZ_1K)) {
-		test_msg("Bitmap region not removed from space cache\n");
+		test_err("bitmap region not removed from space cache");
 		return -EINVAL;
 	}
 
@@ -486,7 +488,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 * covered by the bitmap, isn't marked as free.
 	 */
 	if (test_check_exists(cache, SZ_128M + SZ_256K, SZ_256K)) {
-		test_msg("Invalid bitmap region marked as free\n");
+		test_err("invalid bitmap region marked as free");
 		return -EINVAL;
 	}
 
@@ -495,7 +497,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 * by the bitmap too, isn't marked as free either.
 	 */
 	if (test_check_exists(cache, SZ_128M, SZ_256K)) {
-		test_msg("Invalid bitmap region marked as free\n");
+		test_err("invalid bitmap region marked as free");
 		return -EINVAL;
 	}
 
@@ -506,12 +508,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = btrfs_add_free_space(cache, SZ_128M, SZ_512K);
 	if (ret) {
-		test_msg("Error adding free space: %d\n", ret);
+		test_err("error adding free space: %d", ret);
 		return ret;
 	}
 	/* Confirm the region is marked as free. */
 	if (!test_check_exists(cache, SZ_128M, SZ_512K)) {
-		test_msg("Bitmap region not marked as free\n");
+		test_err("bitmap region not marked as free");
 		return -ENOENT;
 	}
 
@@ -531,7 +533,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, sectorsize);
 	if (ret) {
-		test_msg("Error adding free space: %d\n", ret);
+		test_err("error adding free space: %d", ret);
 		return ret;
 	}
 
@@ -550,12 +552,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = btrfs_add_free_space(cache, SZ_128M - SZ_128K, SZ_128K);
 	if (ret) {
-		test_msg("Error adding free space: %d\n", ret);
+		test_err("error adding free space: %d", ret);
 		return ret;
 	}
 	/* Confirm the region is marked as free. */
 	if (!test_check_exists(cache, SZ_128M - SZ_128K, SZ_128K)) {
-		test_msg("Extent region not marked as free\n");
+		test_err("extent region not marked as free");
 		return -ENOENT;
 	}
 
@@ -583,12 +585,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 * allocate the whole free space at once.
 	 */
 	if (!test_check_exists(cache, SZ_128M - SZ_256K, SZ_1M)) {
-		test_msg("Expected region not marked as free\n");
+		test_err("expected region not marked as free");
 		return -ENOENT;
 	}
 
 	if (cache->free_space_ctl->free_space != (SZ_1M + sectorsize)) {
-		test_msg("Cache free space is not 1Mb + %u\n", sectorsize);
+		test_err("cache free space is not 1Mb + %u", sectorsize);
 		return -EINVAL;
 	}
 
@@ -596,7 +598,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 					    0, SZ_1M, 0,
 					    &max_extent_size);
 	if (offset != (SZ_128M - SZ_256K)) {
-		test_msg("Failed to allocate 1Mb from space cache, returned offset is: %llu\n",
+		test_err(
+	"failed to allocate 1Mb from space cache, returned offset is: %llu",
 			 offset);
 		return -EINVAL;
 	}
@@ -610,7 +613,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 		return ret;
 
 	if (cache->free_space_ctl->free_space != sectorsize) {
-		test_msg("Cache free space is not %u\n", sectorsize);
+		test_err("cache free space is not %u", sectorsize);
 		return -EINVAL;
 	}
 
@@ -618,7 +621,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 					    0, sectorsize, 0,
 					    &max_extent_size);
 	if (offset != (SZ_128M + SZ_16M)) {
-		test_msg("Failed to allocate %u, returned offset : %llu\n",
+		test_err("failed to allocate %u, returned offset : %llu",
 			 sectorsize, offset);
 		return -EINVAL;
 	}
@@ -640,14 +643,14 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = test_add_free_space_entry(cache, SZ_128M + SZ_128K, SZ_128K, 0);
 	if (ret) {
-		test_msg("Couldn't add extent entry %d\n", ret);
+		test_err("couldn't add extent entry %d", ret);
 		return ret;
 	}
 
 	/* Bitmap entry covering free space range [0, 128Mb - 512Kb[ */
 	ret = test_add_free_space_entry(cache, 0, SZ_128M - SZ_512K, 1);
 	if (ret) {
-		test_msg("Couldn't add bitmap entry %d\n", ret);
+		test_err("couldn't add bitmap entry %d", ret);
 		return ret;
 	}
 
@@ -664,17 +667,17 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = btrfs_remove_free_space(cache, 0, SZ_128M - 768 * SZ_1K);
 	if (ret) {
-		test_msg("Failed to free part of bitmap space %d\n", ret);
+		test_err("failed to free part of bitmap space %d", ret);
 		return ret;
 	}
 
 	/* Confirm that only those 2 ranges are marked as free. */
 	if (!test_check_exists(cache, SZ_128M + SZ_128K, SZ_128K)) {
-		test_msg("Free space range missing\n");
+		test_err("free space range missing");
 		return -ENOENT;
 	}
 	if (!test_check_exists(cache, SZ_128M - 768 * SZ_1K, SZ_256K)) {
-		test_msg("Free space range missing\n");
+		test_err("free space range missing");
 		return -ENOENT;
 	}
 
@@ -683,7 +686,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 * as free anymore.
 	 */
 	if (test_check_exists(cache, 0, SZ_128M - 768 * SZ_1K)) {
-		test_msg("Bitmap region not removed from space cache\n");
+		test_err("bitmap region not removed from space cache");
 		return -EINVAL;
 	}
 
@@ -692,7 +695,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 * covered by the bitmap, isn't marked as free.
 	 */
 	if (test_check_exists(cache, SZ_128M - SZ_512K, SZ_512K)) {
-		test_msg("Invalid bitmap region marked as free\n");
+		test_err("invalid bitmap region marked as free");
 		return -EINVAL;
 	}
 
@@ -703,12 +706,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = btrfs_add_free_space(cache, SZ_128M - SZ_512K, SZ_512K);
 	if (ret) {
-		test_msg("Error adding free space: %d\n", ret);
+		test_err("error adding free space: %d", ret);
 		return ret;
 	}
 	/* Confirm the region is marked as free. */
 	if (!test_check_exists(cache, SZ_128M - SZ_512K, SZ_512K)) {
-		test_msg("Bitmap region not marked as free\n");
+		test_err("bitmap region not marked as free");
 		return -ENOENT;
 	}
 
@@ -728,7 +731,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = btrfs_add_free_space(cache, SZ_32M, 2 * sectorsize);
 	if (ret) {
-		test_msg("Error adding free space: %d\n", ret);
+		test_err("error adding free space: %d", ret);
 		return ret;
 	}
 
@@ -739,12 +742,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 */
 	ret = btrfs_add_free_space(cache, SZ_128M, SZ_128K);
 	if (ret) {
-		test_msg("Error adding free space: %d\n", ret);
+		test_err("error adding free space: %d", ret);
 		return ret;
 	}
 	/* Confirm the region is marked as free. */
 	if (!test_check_exists(cache, SZ_128M, SZ_128K)) {
-		test_msg("Extent region not marked as free\n");
+		test_err("extent region not marked as free");
 		return -ENOENT;
 	}
 
@@ -772,19 +775,20 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 	 * allocate the whole free space at once.
 	 */
 	if (!test_check_exists(cache, SZ_128M - 768 * SZ_1K, SZ_1M)) {
-		test_msg("Expected region not marked as free\n");
+		test_err("expected region not marked as free");
 		return -ENOENT;
 	}
 
 	if (cache->free_space_ctl->free_space != (SZ_1M + 2 * sectorsize)) {
-		test_msg("Cache free space is not 1Mb + %u\n", 2 * sectorsize);
+		test_err("cache free space is not 1Mb + %u", 2 * sectorsize);
 		return -EINVAL;
 	}
 
 	offset = btrfs_find_space_for_alloc(cache, 0, SZ_1M, 0,
 					    &max_extent_size);
 	if (offset != (SZ_128M - 768 * SZ_1K)) {
-		test_msg("Failed to allocate 1Mb from space cache, returned offset is: %llu\n",
+		test_err(
+	"failed to allocate 1Mb from space cache, returned offset is: %llu",
 			 offset);
 		return -EINVAL;
 	}
@@ -798,7 +802,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 		return ret;
 
 	if (cache->free_space_ctl->free_space != 2 * sectorsize) {
-		test_msg("Cache free space is not %u\n", 2 * sectorsize);
+		test_err("cache free space is not %u", 2 * sectorsize);
 		return -EINVAL;
 	}
 
@@ -806,9 +810,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 					    0, 2 * sectorsize, 0,
 					    &max_extent_size);
 	if (offset != SZ_32M) {
-		test_msg("Failed to allocate %u, offset: %llu\n",
-			 2 * sectorsize,
-			 offset);
+		test_err("failed to allocate %u, offset: %llu",
+			 2 * sectorsize, offset);
 		return -EINVAL;
 	}
 
@@ -829,7 +832,7 @@ int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
 	struct btrfs_root *root = NULL;
 	int ret = -ENOMEM;
 
-	test_msg("Running btrfs free space cache tests\n");
+	test_msg("running btrfs free space cache tests");
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info)
 		return -ENOMEM;
@@ -843,7 +846,7 @@ int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
 	cache = btrfs_alloc_dummy_block_group(fs_info,
 				      BITS_PER_BITMAP * sectorsize + PAGE_SIZE);
 	if (!cache) {
-		test_msg("Couldn't run the tests\n");
+		test_err("couldn't run the tests");
 		btrfs_free_dummy_fs_info(fs_info);
 		return 0;
 	}
@@ -871,6 +874,6 @@ out:
 	btrfs_free_dummy_block_group(cache);
 	btrfs_free_dummy_root(root);
 	btrfs_free_dummy_fs_info(fs_info);
-	test_msg("Free space cache tests finished\n");
+	test_msg("free space cache tests finished");
 	return ret;
 }
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index e1f9666c4974..89346da890cf 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -32,7 +32,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 
 	info = search_free_space_info(trans, fs_info, cache, path, 0);
 	if (IS_ERR(info)) {
-		test_msg("Could not find free space info\n");
+		test_err("could not find free space info");
 		ret = PTR_ERR(info);
 		goto out;
 	}
@@ -40,7 +40,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 	extent_count = btrfs_free_space_extent_count(path->nodes[0], info);
 
 	if (extent_count != num_extents) {
-		test_msg("Extent count is wrong\n");
+		test_err("extent count is wrong");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -99,7 +99,7 @@ out:
 	btrfs_release_path(path);
 	return ret;
 invalid:
-	test_msg("Free space tree is invalid\n");
+	test_err("free space tree is invalid");
 	ret = -EINVAL;
 	goto out;
 }
@@ -117,7 +117,7 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
 
 	info = search_free_space_info(trans, fs_info, cache, path, 0);
 	if (IS_ERR(info)) {
-		test_msg("Could not find free space info\n");
+		test_err("could not find free space info");
 		btrfs_release_path(path);
 		return PTR_ERR(info);
 	}
@@ -131,15 +131,15 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
 
 	/* Flip it to the other format and check that for good measure. */
 	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
-		ret = convert_free_space_to_extents(trans, fs_info, cache, path);
+		ret = convert_free_space_to_extents(trans, cache, path);
 		if (ret) {
-			test_msg("Could not convert to extents\n");
+			test_err("could not convert to extents");
 			return ret;
 		}
 	} else {
-		ret = convert_free_space_to_bitmaps(trans, fs_info, cache, path);
+		ret = convert_free_space_to_bitmaps(trans, cache, path);
 		if (ret) {
-			test_msg("Could not convert to bitmaps\n");
+			test_err("could not convert to bitmaps");
 			return ret;
 		}
 	}
@@ -170,11 +170,11 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
 	const struct free_space_extent extents[] = {};
 	int ret;
 
-	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+	ret = __remove_from_free_space_tree(trans, cache, path,
 					    cache->key.objectid,
 					    cache->key.offset);
 	if (ret) {
-		test_msg("Could not remove free space\n");
+		test_err("could not remove free space");
 		return ret;
 	}
 
@@ -194,10 +194,10 @@ static int test_remove_beginning(struct btrfs_trans_handle *trans,
 	};
 	int ret;
 
-	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+	ret = __remove_from_free_space_tree(trans, cache, path,
 					    cache->key.objectid, alignment);
 	if (ret) {
-		test_msg("Could not remove free space\n");
+		test_err("could not remove free space");
 		return ret;
 	}
 
@@ -217,12 +217,12 @@ static int test_remove_end(struct btrfs_trans_handle *trans,
 	};
 	int ret;
 
-	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+	ret = __remove_from_free_space_tree(trans, cache, path,
 					    cache->key.objectid +
 					    cache->key.offset - alignment,
 					    alignment);
 	if (ret) {
-		test_msg("Could not remove free space\n");
+		test_err("could not remove free space");
 		return ret;
 	}
 
@@ -243,11 +243,11 @@ static int test_remove_middle(struct btrfs_trans_handle *trans,
 	};
 	int ret;
 
-	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+	ret = __remove_from_free_space_tree(trans, cache, path,
 					    cache->key.objectid + alignment,
 					    alignment);
 	if (ret) {
-		test_msg("Could not remove free space\n");
+		test_err("could not remove free space");
 		return ret;
 	}
 
@@ -266,26 +266,26 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
 	};
 	int ret;
 
-	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+	ret = __remove_from_free_space_tree(trans, cache, path,
 					    cache->key.objectid,
 					    cache->key.offset);
 	if (ret) {
-		test_msg("Could not remove free space\n");
+		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
-				       cache->key.objectid, alignment);
+	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+	ret = __add_to_free_space_tree(trans, cache, path,
 				       cache->key.objectid + alignment,
 				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
@@ -304,27 +304,27 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
 	};
 	int ret;
 
-	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+	ret = __remove_from_free_space_tree(trans, cache, path,
 					    cache->key.objectid,
 					    cache->key.offset);
 	if (ret) {
-		test_msg("Could not remove free space\n");
+		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+	ret = __add_to_free_space_tree(trans, cache, path,
 				       cache->key.objectid + 2 * alignment,
 				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+	ret = __add_to_free_space_tree(trans, cache, path,
 				       cache->key.objectid + alignment,
 				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
@@ -343,34 +343,34 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
 	};
 	int ret;
 
-	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+	ret = __remove_from_free_space_tree(trans, cache, path,
 					    cache->key.objectid,
 					    cache->key.offset);
 	if (ret) {
-		test_msg("Could not remove free space\n");
+		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
-				       cache->key.objectid, alignment);
+	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+	ret = __add_to_free_space_tree(trans, cache, path,
 				       cache->key.objectid + 2 * alignment,
 				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+	ret = __add_to_free_space_tree(trans, cache, path,
 				       cache->key.objectid + alignment,
 				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
@@ -391,34 +391,34 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
 	};
 	int ret;
 
-	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+	ret = __remove_from_free_space_tree(trans, cache, path,
 					    cache->key.objectid,
 					    cache->key.offset);
 	if (ret) {
-		test_msg("Could not remove free space\n");
+		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
-				       cache->key.objectid, alignment);
+	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+	ret = __add_to_free_space_tree(trans, cache, path,
 				       cache->key.objectid + 4 * alignment,
 				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+	ret = __add_to_free_space_tree(trans, cache, path,
 				       cache->key.objectid + 2 * alignment,
 				       alignment);
 	if (ret) {
-		test_msg("Could not add free space\n");
+		test_err("could not add free space");
 		return ret;
 	}
 
@@ -444,14 +444,14 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
 
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
-		test_msg("Couldn't allocate dummy fs info\n");
+		test_err("couldn't allocate dummy fs info");
 		ret = -ENOMEM;
 		goto out;
 	}
 
 	root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(root)) {
-		test_msg("Couldn't allocate dummy root\n");
+		test_err("couldn't allocate dummy root");
 		ret = PTR_ERR(root);
 		goto out;
 	}
@@ -463,7 +463,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
 
 	root->node = alloc_test_extent_buffer(root->fs_info, nodesize);
 	if (!root->node) {
-		test_msg("Couldn't allocate dummy buffer\n");
+		test_err("couldn't allocate dummy buffer");
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -473,7 +473,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
 
 	cache = btrfs_alloc_dummy_block_group(fs_info, 8 * alignment);
 	if (!cache) {
-		test_msg("Couldn't allocate dummy block group cache\n");
+		test_err("couldn't allocate dummy block group cache");
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -482,26 +482,25 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
 	cache->needs_free_space = 1;
 	cache->fs_info = root->fs_info;
 
-	btrfs_init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans, root->fs_info);
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		test_msg("Couldn't allocate path\n");
+		test_err("couldn't allocate path");
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	ret = add_block_group_free_space(&trans, root->fs_info, cache);
+	ret = add_block_group_free_space(&trans, cache);
 	if (ret) {
-		test_msg("Could not add block group free space\n");
+		test_err("could not add block group free space");
 		goto out;
 	}
 
 	if (bitmaps) {
-		ret = convert_free_space_to_bitmaps(&trans, root->fs_info,
-						    cache, path);
+		ret = convert_free_space_to_bitmaps(&trans, cache, path);
 		if (ret) {
-			test_msg("Could not convert block group to bitmaps\n");
+			test_err("could not convert block group to bitmaps");
 			goto out;
 		}
 	}
@@ -510,14 +509,14 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
 	if (ret)
 		goto out;
 
-	ret = remove_block_group_free_space(&trans, root->fs_info, cache);
+	ret = remove_block_group_free_space(&trans, cache);
 	if (ret) {
-		test_msg("Could not remove block group free space\n");
+		test_err("could not remove block group free space");
 		goto out;
 	}
 
 	if (btrfs_header_nritems(root->node) != 0) {
-		test_msg("Free space tree has leftover items\n");
+		test_err("free space tree has leftover items");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -539,14 +538,16 @@ static int run_test_both_formats(test_func_t test_func, u32 sectorsize,
 
 	ret = run_test(test_func, 0, sectorsize, nodesize, alignment);
 	if (ret) {
-		test_msg("%pf failed with extents, sectorsize=%u, nodesize=%u, alignment=%u\n",
+		test_err(
+	"%pf failed with extents, sectorsize=%u, nodesize=%u, alignment=%u",
 			 test_func, sectorsize, nodesize, alignment);
 		test_ret = ret;
 	}
 
 	ret = run_test(test_func, 1, sectorsize, nodesize, alignment);
 	if (ret) {
-		test_msg("%pf failed with bitmaps, sectorsize=%u, nodesize=%u, alignment=%u\n",
+		test_err(
+	"%pf failed with bitmaps, sectorsize=%u, nodesize=%u, alignment=%u",
 			 test_func, sectorsize, nodesize, alignment);
 		test_ret = ret;
 	}
@@ -577,7 +578,7 @@ int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
 	 */
 	bitmap_alignment = BTRFS_FREE_SPACE_BITMAP_BITS * PAGE_SIZE;
 
-	test_msg("Running free space tree tests\n");
+	test_msg("running free space tree tests");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		int ret;
 
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index e0ba799536b4..64043f028820 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -228,7 +228,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	inode = btrfs_new_test_inode();
 	if (!inode) {
-		test_msg("Couldn't allocate inode\n");
+		test_err("couldn't allocate inode");
 		return ret;
 	}
 
@@ -238,19 +238,19 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
-		test_msg("Couldn't allocate dummy fs info\n");
+		test_err("couldn't allocate dummy fs info");
 		goto out;
 	}
 
 	root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(root)) {
-		test_msg("Couldn't allocate root\n");
+		test_err("couldn't allocate root");
 		goto out;
 	}
 
 	root->node = alloc_dummy_extent_buffer(fs_info, nodesize);
 	if (!root->node) {
-		test_msg("Couldn't allocate dummy buffer\n");
+		test_err("couldn't allocate dummy buffer");
 		goto out;
 	}
 
@@ -268,11 +268,11 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, sectorsize, 0);
 	if (IS_ERR(em)) {
 		em = NULL;
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != EXTENT_MAP_HOLE) {
-		test_msg("Expected a hole, got %llu\n", em->block_start);
+		test_err("expected a hole, got %llu", em->block_start);
 		goto out;
 	}
 	free_extent_map(em);
@@ -287,20 +287,21 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, (u64)-1, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != EXTENT_MAP_HOLE) {
-		test_msg("Expected a hole, got %llu\n", em->block_start);
+		test_err("expected a hole, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != 0 || em->len != 5) {
-		test_msg("Unexpected extent wanted start 0 len 5, got start "
-			 "%llu len %llu\n", em->start, em->len);
+		test_err(
+		"unexpected extent wanted start 0 len 5, got start %llu len %llu",
+			em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -308,21 +309,22 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != EXTENT_MAP_INLINE) {
-		test_msg("Expected an inline, got %llu\n", em->block_start);
+		test_err("expected an inline, got %llu", em->block_start);
 		goto out;
 	}
 
 	if (em->start != offset || em->len != (sectorsize - 5)) {
-		test_msg("Unexpected extent wanted start %llu len 1, got start "
-			 "%llu len %llu\n", offset, em->start, em->len);
+		test_err(
+	"unexpected extent wanted start %llu len 1, got start %llu len %llu",
+			offset, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	/*
@@ -335,20 +337,21 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != EXTENT_MAP_HOLE) {
-		test_msg("Expected a hole, got %llu\n", em->block_start);
+		test_err("expected a hole, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != 4) {
-		test_msg("Unexpected extent wanted start %llu len 4, got start "
-			 "%llu len %llu\n", offset, em->start, em->len);
+		test_err(
+	"unexpected extent wanted start %llu len 4, got start %llu len %llu",
+			offset, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -357,24 +360,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	/* Regular extent */
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize - 1) {
-		test_msg("Unexpected extent wanted start %llu len 4095, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+		test_err(
+	"unexpected extent wanted start %llu len 4095, got start %llu len %llu",
+			offset, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+		test_err("wrong orig offset, want %llu, have %llu", em->start,
 			 em->orig_start);
 		goto out;
 	}
@@ -384,25 +388,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	/* The next 3 are split extents */
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+		"unexpected extent start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+		test_err("wrong orig offset, want %llu, have %llu", em->start,
 			 em->orig_start);
 		goto out;
 	}
@@ -413,21 +417,21 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != EXTENT_MAP_HOLE) {
-		test_msg("Expected a hole, got %llu\n", em->block_start);
+		test_err("expected a hole, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -435,31 +439,31 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != 2 * sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	if (em->orig_start != orig_start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n",
+		test_err("wrong orig offset, want %llu, have %llu",
 			 orig_start, em->orig_start);
 		goto out;
 	}
 	disk_bytenr += (em->start - orig_start);
 	if (em->block_start != disk_bytenr) {
-		test_msg("Wrong block start, want %llu, have %llu\n",
+		test_err("wrong block start, want %llu, have %llu",
 			 disk_bytenr, em->block_start);
 		goto out;
 	}
@@ -469,26 +473,26 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	/* Prealloc extent */
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_msg("Unexpected flags set, want %lu have %lu\n",
+		test_err("unexpected flags set, want %lu have %lu",
 			 prealloc_only, em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+		test_err("wrong orig offset, want %llu, have %llu", em->start,
 			 em->orig_start);
 		goto out;
 	}
@@ -498,26 +502,26 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	/* The next 3 are a half written prealloc extent */
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_msg("Unexpected flags set, want %lu have %lu\n",
+		test_err("unexpected flags set, want %lu have %lu",
 			 prealloc_only, em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+		test_err("wrong orig offset, want %llu, have %llu", em->start,
 			 em->orig_start);
 		goto out;
 	}
@@ -528,30 +532,30 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_HOLE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	if (em->orig_start != orig_start) {
-		test_msg("Unexpected orig offset, wanted %llu, have %llu\n",
+		test_err("unexpected orig offset, wanted %llu, have %llu",
 			 orig_start, em->orig_start);
 		goto out;
 	}
 	if (em->block_start != (disk_bytenr + (em->start - em->orig_start))) {
-		test_msg("Unexpected block start, wanted %llu, have %llu\n",
+		test_err("unexpected block start, wanted %llu, have %llu",
 			 disk_bytenr + (em->start - em->orig_start),
 			 em->block_start);
 		goto out;
@@ -561,31 +565,31 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != 2 * sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_msg("Unexpected flags set, want %lu have %lu\n",
+		test_err("unexpected flags set, want %lu have %lu",
 			 prealloc_only, em->flags);
 		goto out;
 	}
 	if (em->orig_start != orig_start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", orig_start,
+		test_err("wrong orig offset, want %llu, have %llu", orig_start,
 			 em->orig_start);
 		goto out;
 	}
 	if (em->block_start != (disk_bytenr + (em->start - em->orig_start))) {
-		test_msg("Unexpected block start, wanted %llu, have %llu\n",
+		test_err("unexpected block start, wanted %llu, have %llu",
 			 disk_bytenr + (em->start - em->orig_start),
 			 em->block_start);
 		goto out;
@@ -596,31 +600,31 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	/* Now for the compressed extent */
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != 2 * sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u,"
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_msg("Unexpected flags set, want %lu have %lu\n",
+		test_err("unexpected flags set, want %lu have %lu",
 			 compressed_only, em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n",
+		test_err("wrong orig offset, want %llu, have %llu",
 			 em->start, em->orig_start);
 		goto out;
 	}
 	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
-		test_msg("Unexpected compress type, wanted %d, got %d\n",
+		test_err("unexpected compress type, wanted %d, got %d",
 			 BTRFS_COMPRESS_ZLIB, em->compress_type);
 		goto out;
 	}
@@ -630,31 +634,31 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	/* Split compressed extent */
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u,"
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_msg("Unexpected flags set, want %lu have %lu\n",
+		test_err("unexpected flags set, want %lu have %lu",
 			 compressed_only, em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n",
+		test_err("wrong orig offset, want %llu, have %llu",
 			 em->start, em->orig_start);
 		goto out;
 	}
 	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
-		test_msg("Unexpected compress type, wanted %d, got %d\n",
+		test_err("unexpected compress type, wanted %d, got %d",
 			 BTRFS_COMPRESS_ZLIB, em->compress_type);
 		goto out;
 	}
@@ -665,25 +669,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+		test_err("wrong orig offset, want %llu, have %llu", em->start,
 			 em->orig_start);
 		goto out;
 	}
@@ -692,32 +696,32 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != disk_bytenr) {
-		test_msg("Block start does not match, want %llu got %llu\n",
+		test_err("block start does not match, want %llu got %llu",
 			 disk_bytenr, em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != 2 * sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_msg("Unexpected flags set, want %lu have %lu\n",
+		test_err("unexpected flags set, want %lu have %lu",
 			 compressed_only, em->flags);
 		goto out;
 	}
 	if (em->orig_start != orig_start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n",
+		test_err("wrong orig offset, want %llu, have %llu",
 			 em->start, orig_start);
 		goto out;
 	}
 	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
-		test_msg("Unexpected compress type, wanted %d, got %d\n",
+		test_err("unexpected compress type, wanted %d, got %d",
 			 BTRFS_COMPRESS_ZLIB, em->compress_type);
 		goto out;
 	}
@@ -728,25 +732,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset + 6,
 			sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+		test_err("wrong orig offset, want %llu, have %llu", em->start,
 			 em->orig_start);
 		goto out;
 	}
@@ -755,11 +759,11 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, SZ_4M, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != EXTENT_MAP_HOLE) {
-		test_msg("Expected a hole extent, got %llu\n", em->block_start);
+		test_err("expected a hole extent, got %llu", em->block_start);
 		goto out;
 	}
 	/*
@@ -768,18 +772,18 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	 * test.
 	 */
 	if (em->start != offset || em->len != 3 * sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, 3 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
-		test_msg("Unexpected flags set, want %lu have %lu\n",
+		test_err("unexpected flags set, want %lu have %lu",
 			 vacancy_only, em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+		test_err("wrong orig offset, want %llu, have %llu", em->start,
 			 em->orig_start);
 		goto out;
 	}
@@ -788,25 +792,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != offset || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %llu len %u,"
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %llu len %u, got start %llu len %llu",
 			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+		test_err("unexpected flags set, want 0 have %lu", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
-		test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+		test_err("wrong orig offset, want %llu, have %llu", em->start,
 			 em->orig_start);
 		goto out;
 	}
@@ -830,7 +834,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 
 	inode = btrfs_new_test_inode();
 	if (!inode) {
-		test_msg("Couldn't allocate inode\n");
+		test_err("couldn't allocate inode");
 		return ret;
 	}
 
@@ -840,19 +844,19 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
-		test_msg("Couldn't allocate dummy fs info\n");
+		test_err("couldn't allocate dummy fs info");
 		goto out;
 	}
 
 	root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(root)) {
-		test_msg("Couldn't allocate root\n");
+		test_err("couldn't allocate root");
 		goto out;
 	}
 
 	root->node = alloc_dummy_extent_buffer(fs_info, nodesize);
 	if (!root->node) {
-		test_msg("Couldn't allocate dummy buffer\n");
+		test_err("couldn't allocate dummy buffer");
 		goto out;
 	}
 
@@ -871,21 +875,21 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, 2 * sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != EXTENT_MAP_HOLE) {
-		test_msg("Expected a hole, got %llu\n", em->block_start);
+		test_err("expected a hole, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != 0 || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start 0 len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start 0 len %u, got start %llu len %llu",
 			sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
-		test_msg("Wrong flags, wanted %lu, have %lu\n", vacancy_only,
+		test_err("wrong flags, wanted %lu, have %lu", vacancy_only,
 			 em->flags);
 		goto out;
 	}
@@ -894,21 +898,21 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize,
 			2 * sectorsize, 0);
 	if (IS_ERR(em)) {
-		test_msg("Got an error when we shouldn't have\n");
+		test_err("got an error when we shouldn't have");
 		goto out;
 	}
 	if (em->block_start != sectorsize) {
-		test_msg("Expected a real extent, got %llu\n", em->block_start);
+		test_err("expected a real extent, got %llu", em->block_start);
 		goto out;
 	}
 	if (em->start != sectorsize || em->len != sectorsize) {
-		test_msg("Unexpected extent wanted start %u len %u, "
-			"got start %llu len %llu\n",
+		test_err(
+	"unexpected extent wanted start %u len %u, got start %llu len %llu",
 			sectorsize, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_msg("Unexpected flags set, wanted 0 got %lu\n",
+		test_err("unexpected flags set, wanted 0 got %lu",
 			 em->flags);
 		goto out;
 	}
@@ -931,19 +935,19 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 
 	inode = btrfs_new_test_inode();
 	if (!inode) {
-		test_msg("Couldn't allocate inode\n");
+		test_err("couldn't allocate inode");
 		return ret;
 	}
 
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
-		test_msg("Couldn't allocate dummy fs info\n");
+		test_err("couldn't allocate dummy fs info");
 		goto out;
 	}
 
 	root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(root)) {
-		test_msg("Couldn't allocate root\n");
+		test_err("couldn't allocate root");
 		goto out;
 	}
 
@@ -954,12 +958,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 	ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, 0,
 					NULL, 0);
 	if (ret) {
-		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		test_err("btrfs_set_extent_delalloc returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents != 1) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 1, got %u\n",
+		test_err("miscount, wanted 1, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -969,12 +973,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 					BTRFS_MAX_EXTENT_SIZE + sectorsize - 1,
 					0, NULL, 0);
 	if (ret) {
-		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		test_err("btrfs_set_extent_delalloc returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents != 2) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 2, got %u\n",
+		test_err("miscount, wanted 2, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -986,12 +990,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 			       EXTENT_DELALLOC | EXTENT_DIRTY |
 			       EXTENT_UPTODATE, 0, 0, NULL);
 	if (ret) {
-		test_msg("clear_extent_bit returned %d\n", ret);
+		test_err("clear_extent_bit returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents != 2) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 2, got %u\n",
+		test_err("miscount, wanted 2, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -1002,12 +1006,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 					+ sectorsize - 1,
 					0, NULL, 0);
 	if (ret) {
-		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		test_err("btrfs_set_extent_delalloc returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents != 2) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 2, got %u\n",
+		test_err("miscount, wanted 2, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -1020,12 +1024,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 			(BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1,
 			0, NULL, 0);
 	if (ret) {
-		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		test_err("btrfs_set_extent_delalloc returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents != 4) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 4, got %u\n",
+		test_err("miscount, wanted 4, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -1037,12 +1041,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 			BTRFS_MAX_EXTENT_SIZE + sectorsize,
 			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0);
 	if (ret) {
-		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		test_err("btrfs_set_extent_delalloc returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents != 3) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 3, got %u\n",
+		test_err("miscount, wanted 3, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -1054,12 +1058,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
 			       EXTENT_UPTODATE, 0, 0, NULL);
 	if (ret) {
-		test_msg("clear_extent_bit returned %d\n", ret);
+		test_err("clear_extent_bit returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents != 4) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 4, got %u\n",
+		test_err("miscount, wanted 4, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -1072,12 +1076,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 			BTRFS_MAX_EXTENT_SIZE + sectorsize,
 			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0);
 	if (ret) {
-		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		test_err("btrfs_set_extent_delalloc returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents != 3) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 3, got %u\n",
+		test_err("miscount, wanted 3, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -1087,12 +1091,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
 			       EXTENT_UPTODATE, 0, 0, NULL);
 	if (ret) {
-		test_msg("clear_extent_bit returned %d\n", ret);
+		test_err("clear_extent_bit returned %d", ret);
 		goto out;
 	}
 	if (BTRFS_I(inode)->outstanding_extents) {
 		ret = -EINVAL;
-		test_msg("Miscount, wanted 0, got %u\n",
+		test_err("miscount, wanted 0, got %u",
 			 BTRFS_I(inode)->outstanding_extents);
 		goto out;
 	}
@@ -1115,14 +1119,14 @@ int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
 	set_bit(EXTENT_FLAG_COMPRESSED, &compressed_only);
 	set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only);
 
-	test_msg("Running btrfs_get_extent tests\n");
+	test_msg("running btrfs_get_extent tests");
 	ret = test_btrfs_get_extent(sectorsize, nodesize);
 	if (ret)
 		return ret;
-	test_msg("Running hole first btrfs_get_extent test\n");
+	test_msg("running hole first btrfs_get_extent test");
 	ret = test_hole_first(sectorsize, nodesize);
 	if (ret)
 		return ret;
-	test_msg("Running outstanding_extents tests\n");
+	test_msg("running outstanding_extents tests");
 	return test_extent_accounting(sectorsize, nodesize);
 }
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index 39b95783f736..ace94db09d29 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -24,7 +24,7 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
 	u32 size = sizeof(*item) + sizeof(*iref) + sizeof(*block_info);
 	int ret;
 
-	btrfs_init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans, NULL);
 
 	ins.objectid = bytenr;
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
@@ -32,14 +32,14 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		test_msg("Couldn't allocate path\n");
+		test_err("couldn't allocate path");
 		return -ENOMEM;
 	}
 
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(&trans, root, path, &ins, size);
 	if (ret) {
-		test_msg("Couldn't insert ref %d\n", ret);
+		test_err("couldn't insert ref %d", ret);
 		btrfs_free_path(path);
 		return ret;
 	}
@@ -74,7 +74,7 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
 	u64 refs;
 	int ret;
 
-	btrfs_init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans, NULL);
 
 	key.objectid = bytenr;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -82,14 +82,14 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		test_msg("Couldn't allocate path\n");
+		test_err("couldn't allocate path");
 		return -ENOMEM;
 	}
 
 	path->leave_spinning = 1;
 	ret = btrfs_search_slot(&trans, root, &key, path, 0, 1);
 	if (ret) {
-		test_msg("Couldn't find extent ref\n");
+		test_err("couldn't find extent ref");
 		btrfs_free_path(path);
 		return ret;
 	}
@@ -111,7 +111,7 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
 
 	ret = btrfs_insert_empty_item(&trans, root, path, &key, 0);
 	if (ret)
-		test_msg("Failed to insert backref\n");
+		test_err("failed to insert backref");
 	btrfs_free_path(path);
 	return ret;
 }
@@ -124,7 +124,7 @@ static int remove_extent_item(struct btrfs_root *root, u64 bytenr,
 	struct btrfs_path *path;
 	int ret;
 
-	btrfs_init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans, NULL);
 
 	key.objectid = bytenr;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -132,14 +132,14 @@ static int remove_extent_item(struct btrfs_root *root, u64 bytenr,
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		test_msg("Couldn't allocate path\n");
+		test_err("couldn't allocate path");
 		return -ENOMEM;
 	}
 	path->leave_spinning = 1;
 
 	ret = btrfs_search_slot(&trans, root, &key, path, -1, 1);
 	if (ret) {
-		test_msg("Didn't find our key %d\n", ret);
+		test_err("didn't find our key %d", ret);
 		btrfs_free_path(path);
 		return ret;
 	}
@@ -158,7 +158,7 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
 	u64 refs;
 	int ret;
 
-	btrfs_init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans, NULL);
 
 	key.objectid = bytenr;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -166,14 +166,14 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		test_msg("Couldn't allocate path\n");
+		test_err("couldn't allocate path");
 		return -ENOMEM;
 	}
 
 	path->leave_spinning = 1;
 	ret = btrfs_search_slot(&trans, root, &key, path, 0, 1);
 	if (ret) {
-		test_msg("Couldn't find extent ref\n");
+		test_err("couldn't find extent ref");
 		btrfs_free_path(path);
 		return ret;
 	}
@@ -195,7 +195,7 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
 
 	ret = btrfs_search_slot(&trans, root, &key, path, -1, 1);
 	if (ret) {
-		test_msg("Couldn't find backref %d\n", ret);
+		test_err("couldn't find backref %d", ret);
 		btrfs_free_path(path);
 		return ret;
 	}
@@ -213,12 +213,12 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 	struct ulist *new_roots = NULL;
 	int ret;
 
-	btrfs_init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans, fs_info);
 
-	test_msg("Qgroup basic add\n");
+	test_msg("qgroup basic add");
 	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FS_TREE_OBJECTID);
 	if (ret) {
-		test_msg("Couldn't create a qgroup %d\n", ret);
+		test_err("couldn't create a qgroup %d", ret);
 		return ret;
 	}
 
@@ -231,7 +231,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 			false);
 	if (ret) {
 		ulist_free(old_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
@@ -245,20 +245,20 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
 					  nodesize, old_roots, new_roots);
 	if (ret) {
-		test_msg("Couldn't account space for a qgroup %d\n", ret);
+		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
 	}
 
 	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
 				nodesize, nodesize)) {
-		test_msg("Qgroup counts didn't match expected values\n");
+		test_err("qgroup counts didn't match expected values");
 		return -EINVAL;
 	}
 	old_roots = NULL;
@@ -268,7 +268,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 			false);
 	if (ret) {
 		ulist_free(old_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
@@ -281,19 +281,19 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
 					  nodesize, old_roots, new_roots);
 	if (ret) {
-		test_msg("Couldn't account space for a qgroup %d\n", ret);
+		test_err("couldn't account space for a qgroup %d", ret);
 		return -EINVAL;
 	}
 
 	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, 0, 0)) {
-		test_msg("Qgroup counts didn't match expected values\n");
+		test_err("qgroup counts didn't match expected values");
 		return -EINVAL;
 	}
 
@@ -314,9 +314,9 @@ static int test_multiple_refs(struct btrfs_root *root,
 	struct ulist *new_roots = NULL;
 	int ret;
 
-	btrfs_init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans, fs_info);
 
-	test_msg("Qgroup multiple refs test\n");
+	test_msg("qgroup multiple refs test");
 
 	/*
 	 * We have BTRFS_FS_TREE_OBJECTID created already from the
@@ -324,7 +324,7 @@ static int test_multiple_refs(struct btrfs_root *root,
 	 */
 	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FIRST_FREE_OBJECTID);
 	if (ret) {
-		test_msg("Couldn't create a qgroup %d\n", ret);
+		test_err("couldn't create a qgroup %d", ret);
 		return ret;
 	}
 
@@ -332,7 +332,7 @@ static int test_multiple_refs(struct btrfs_root *root,
 			false);
 	if (ret) {
 		ulist_free(old_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
@@ -346,20 +346,20 @@ static int test_multiple_refs(struct btrfs_root *root,
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
 					  nodesize, old_roots, new_roots);
 	if (ret) {
-		test_msg("Couldn't account space for a qgroup %d\n", ret);
+		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
 	}
 
 	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
 				       nodesize, nodesize)) {
-		test_msg("Qgroup counts didn't match expected values\n");
+		test_err("qgroup counts didn't match expected values");
 		return -EINVAL;
 	}
 
@@ -367,7 +367,7 @@ static int test_multiple_refs(struct btrfs_root *root,
 			false);
 	if (ret) {
 		ulist_free(old_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
@@ -381,26 +381,26 @@ static int test_multiple_refs(struct btrfs_root *root,
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
 					  nodesize, old_roots, new_roots);
 	if (ret) {
-		test_msg("Couldn't account space for a qgroup %d\n", ret);
+		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
 	}
 
 	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
 					nodesize, 0)) {
-		test_msg("Qgroup counts didn't match expected values\n");
+		test_err("qgroup counts didn't match expected values");
 		return -EINVAL;
 	}
 
 	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
 					nodesize, 0)) {
-		test_msg("Qgroup counts didn't match expected values\n");
+		test_err("qgroup counts didn't match expected values");
 		return -EINVAL;
 	}
 
@@ -408,7 +408,7 @@ static int test_multiple_refs(struct btrfs_root *root,
 			false);
 	if (ret) {
 		ulist_free(old_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
@@ -422,26 +422,26 @@ static int test_multiple_refs(struct btrfs_root *root,
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
-		test_msg("Couldn't find old roots: %d\n", ret);
+		test_err("couldn't find old roots: %d", ret);
 		return ret;
 	}
 
 	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
 					  nodesize, old_roots, new_roots);
 	if (ret) {
-		test_msg("Couldn't account space for a qgroup %d\n", ret);
+		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
 	}
 
 	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
 					0, 0)) {
-		test_msg("Qgroup counts didn't match expected values\n");
+		test_err("qgroup counts didn't match expected values");
 		return -EINVAL;
 	}
 
 	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
 					nodesize, nodesize)) {
-		test_msg("Qgroup counts didn't match expected values\n");
+		test_err("qgroup counts didn't match expected values");
 		return -EINVAL;
 	}
 
@@ -457,13 +457,13 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
-		test_msg("Couldn't allocate dummy fs info\n");
+		test_err("couldn't allocate dummy fs info");
 		return -ENOMEM;
 	}
 
 	root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(root)) {
-		test_msg("Couldn't allocate root\n");
+		test_err("couldn't allocate root");
 		ret = PTR_ERR(root);
 		goto out;
 	}
@@ -485,7 +485,7 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 	 */
 	root->node = alloc_test_extent_buffer(root->fs_info, nodesize);
 	if (!root->node) {
-		test_msg("Couldn't allocate dummy buffer\n");
+		test_err("couldn't allocate dummy buffer");
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -495,7 +495,7 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 
 	tmp_root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(tmp_root)) {
-		test_msg("Couldn't allocate a fs root\n");
+		test_err("couldn't allocate a fs root");
 		ret = PTR_ERR(tmp_root);
 		goto out;
 	}
@@ -504,13 +504,13 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 	root->fs_info->fs_root = tmp_root;
 	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
 	if (ret) {
-		test_msg("Couldn't insert fs root %d\n", ret);
+		test_err("couldn't insert fs root %d", ret);
 		goto out;
 	}
 
 	tmp_root = btrfs_alloc_dummy_root(fs_info);
 	if (IS_ERR(tmp_root)) {
-		test_msg("Couldn't allocate a fs root\n");
+		test_err("couldn't allocate a fs root");
 		ret = PTR_ERR(tmp_root);
 		goto out;
 	}
@@ -518,11 +518,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 	tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
 	if (ret) {
-		test_msg("Couldn't insert fs root %d\n", ret);
+		test_err("couldn't insert fs root %d", ret);
 		goto out;
 	}
 
-	test_msg("Running qgroup tests\n");
+	test_msg("running qgroup tests");
 	ret = test_no_shared_qgroup(root, sectorsize, nodesize);
 	if (ret)
 		goto out;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 63fdcab64b01..4485eae41e88 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -877,12 +877,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	atomic_dec(&cur_trans->num_writers);
 	extwriter_counter_dec(cur_trans, trans->type);
 
-	/*
-	 * Make sure counter is updated before we wake up waiters.
-	 */
-	smp_mb();
-	if (waitqueue_active(&cur_trans->writer_wait))
-		wake_up(&cur_trans->writer_wait);
+	cond_wake_up(&cur_trans->writer_wait);
 	btrfs_put_transaction(cur_trans);
 
 	if (current->journal_info == trans)
@@ -1250,7 +1245,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
 
 			btrfs_free_log(trans, root);
 			btrfs_update_reloc_root(trans, root);
-			btrfs_orphan_commit_root(trans, root);
 
 			btrfs_save_ino_cache(root, trans);
 
@@ -1640,15 +1634,14 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
-	ret = btrfs_uuid_tree_add(trans, fs_info, new_uuid.b,
-				  BTRFS_UUID_KEY_SUBVOL, objectid);
+	ret = btrfs_uuid_tree_add(trans, new_uuid.b, BTRFS_UUID_KEY_SUBVOL,
+				  objectid);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 	if (!btrfs_is_empty_uuid(new_root_item->received_uuid)) {
-		ret = btrfs_uuid_tree_add(trans, fs_info,
-					  new_root_item->received_uuid,
+		ret = btrfs_uuid_tree_add(trans, new_root_item->received_uuid,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 					  objectid);
 		if (ret && ret != -EEXIST) {
@@ -2267,6 +2260,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	 */
 	cur_trans->state = TRANS_STATE_COMPLETED;
 	wake_up(&cur_trans->commit_wait);
+	clear_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
 
 	spin_lock(&fs_info->trans_lock);
 	list_del_init(&cur_trans->list);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index c88fccd80bc5..94439482a0ec 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -139,7 +139,6 @@ struct btrfs_pending_snapshot {
 	struct btrfs_path *path;
 	/* block reservation for the operation */
 	struct btrfs_block_rsv block_rsv;
-	u64 qgroup_reserved;
 	/* extra metadata reservation for relocation */
 	int error;
 	bool readonly;
@@ -199,6 +198,20 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root);
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans);
 int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 				   int wait_for_unblock);
+
+/*
+ * Try to commit transaction asynchronously, so this is safe to call
+ * even holding a spinlock.
+ *
+ * It's done by informing transaction_kthread to commit transaction without
+ * waiting for commit interval.
+ */
+static inline void btrfs_commit_transaction_locksafe(
+		struct btrfs_fs_info *fs_info)
+{
+	set_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
+	wake_up_process(fs_info->transaction_kthread);
+}
 int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans);
 int btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
 void btrfs_throttle(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 43758e30aa7a..f8220ec02036 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -222,11 +222,8 @@ int btrfs_pin_log_trans(struct btrfs_root *root)
 void btrfs_end_log_trans(struct btrfs_root *root)
 {
 	if (atomic_dec_and_test(&root->log_writers)) {
-		/*
-		 * Implicit memory barrier after atomic_dec_and_test
-		 */
-		if (waitqueue_active(&root->log_writer_wait))
-			wake_up(&root->log_writer_wait);
+		/* atomic_dec_and_test implies a barrier */
+		cond_wake_up_nomb(&root->log_writer_wait);
 	}
 }
 
@@ -2988,11 +2985,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&log_root_tree->log_mutex);
 	if (atomic_dec_and_test(&log_root_tree->log_writers)) {
-		/*
-		 * Implicit memory barrier after atomic_dec_and_test
-		 */
-		if (waitqueue_active(&log_root_tree->log_writer_wait))
-			wake_up(&log_root_tree->log_writer_wait);
+		/* atomic_dec_and_test implies a barrier */
+		cond_wake_up_nomb(&log_root_tree->log_writer_wait);
 	}
 
 	if (ret) {
@@ -3116,10 +3110,11 @@ out_wake_log_root:
 	mutex_unlock(&log_root_tree->log_mutex);
 
 	/*
-	 * The barrier before waitqueue_active is implied by mutex_unlock
+	 * The barrier before waitqueue_active (in cond_wake_up) is needed so
+	 * all the updates above are seen by the woken threads. It might not be
+	 * necessary, but proving that seems to be hard.
 	 */
-	if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
-		wake_up(&log_root_tree->log_commit_wait[index2]);
+	cond_wake_up(&log_root_tree->log_commit_wait[index2]);
 out:
 	mutex_lock(&root->log_mutex);
 	btrfs_remove_all_log_ctxs(root, index1, ret);
@@ -3128,10 +3123,11 @@ out:
 	mutex_unlock(&root->log_mutex);
 
 	/*
-	 * The barrier before waitqueue_active is implied by mutex_unlock
+	 * The barrier before waitqueue_active (in cond_wake_up) is needed so
+	 * all the updates above are seen by the woken threads. It might not be
+	 * necessary, but proving that seems to be hard.
 	 */
-	if (waitqueue_active(&root->log_commit_wait[index1]))
-		wake_up(&root->log_commit_wait[index1]);
+	cond_wake_up(&root->log_commit_wait[index1]);
 	return ret;
 }
 
@@ -4320,6 +4316,110 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * Log all prealloc extents beyond the inode's i_size to make sure we do not
+ * lose them after doing a fast fsync and replaying the log. We scan the
+ * subvolume's root instead of iterating the inode's extent map tree because
+ * otherwise we can log incorrect extent items based on extent map conversion.
+ * That can happen due to the fact that extent maps are merged when they
+ * are not in the extent map tree's list of modified extents.
+ */
+static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
+				      struct btrfs_inode *inode,
+				      struct btrfs_path *path)
+{
+	struct btrfs_root *root = inode->root;
+	struct btrfs_key key;
+	const u64 i_size = i_size_read(&inode->vfs_inode);
+	const u64 ino = btrfs_ino(inode);
+	struct btrfs_path *dst_path = NULL;
+	u64 last_extent = (u64)-1;
+	int ins_nr = 0;
+	int start_slot;
+	int ret;
+
+	if (!(inode->flags & BTRFS_INODE_PREALLOC))
+		return 0;
+
+	key.objectid = ino;
+	key.type = BTRFS_EXTENT_DATA_KEY;
+	key.offset = i_size;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	while (true) {
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+
+		if (slot >= btrfs_header_nritems(leaf)) {
+			if (ins_nr > 0) {
+				ret = copy_items(trans, inode, dst_path, path,
+						 &last_extent, start_slot,
+						 ins_nr, 1, 0);
+				if (ret < 0)
+					goto out;
+				ins_nr = 0;
+			}
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto out;
+			if (ret > 0) {
+				ret = 0;
+				break;
+			}
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid > ino)
+			break;
+		if (WARN_ON_ONCE(key.objectid < ino) ||
+		    key.type < BTRFS_EXTENT_DATA_KEY ||
+		    key.offset < i_size) {
+			path->slots[0]++;
+			continue;
+		}
+		if (last_extent == (u64)-1) {
+			last_extent = key.offset;
+			/*
+			 * Avoid logging extent items logged in past fsync calls
+			 * and leading to duplicate keys in the log tree.
+			 */
+			do {
+				ret = btrfs_truncate_inode_items(trans,
+							 root->log_root,
+							 &inode->vfs_inode,
+							 i_size,
+							 BTRFS_EXTENT_DATA_KEY);
+			} while (ret == -EAGAIN);
+			if (ret)
+				goto out;
+		}
+		if (ins_nr == 0)
+			start_slot = slot;
+		ins_nr++;
+		path->slots[0]++;
+		if (!dst_path) {
+			dst_path = btrfs_alloc_path();
+			if (!dst_path) {
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+	}
+	if (ins_nr > 0) {
+		ret = copy_items(trans, inode, dst_path, path, &last_extent,
+				 start_slot, ins_nr, 1, 0);
+		if (ret > 0)
+			ret = 0;
+	}
+out:
+	btrfs_release_path(path);
+	btrfs_free_path(dst_path);
+	return ret;
+}
+
 static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     struct btrfs_inode *inode,
@@ -4362,6 +4462,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 		if (em->generation <= test_gen)
 			continue;
 
+		/* We log prealloc extents beyond eof later. */
+		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) &&
+		    em->start >= i_size_read(&inode->vfs_inode))
+			continue;
+
 		if (em->start < logged_start)
 			logged_start = em->start;
 		if ((em->start + em->len - 1) > logged_end)
@@ -4374,31 +4479,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 		num++;
 	}
 
-	/*
-	 * Add all prealloc extents beyond the inode's i_size to make sure we
-	 * don't lose them after doing a fast fsync and replaying the log.
-	 */
-	if (inode->flags & BTRFS_INODE_PREALLOC) {
-		struct rb_node *node;
-
-		for (node = rb_last(&tree->map); node; node = rb_prev(node)) {
-			em = rb_entry(node, struct extent_map, rb_node);
-			if (em->start < i_size_read(&inode->vfs_inode))
-				break;
-			if (!list_empty(&em->list))
-				continue;
-			/* Same as above loop. */
-			if (++num > 32768) {
-				list_del_init(&tree->modified_extents);
-				ret = -EFBIG;
-				goto process;
-			}
-			refcount_inc(&em->refs);
-			set_bit(EXTENT_FLAG_LOGGING, &em->flags);
-			list_add_tail(&em->list, &extents);
-		}
-	}
-
 	list_sort(NULL, &extents, extent_cmp);
 	btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
 	/*
@@ -4443,6 +4523,9 @@ process:
 	up_write(&inode->dio_sem);
 
 	btrfs_release_path(path);
+	if (!ret)
+		ret = btrfs_log_prealloc_extents(trans, inode, path);
+
 	return ret;
 }
 
@@ -4827,6 +4910,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	u64 logged_isize = 0;
 	bool need_log_inode_item = true;
+	bool xattrs_logged = false;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -5128,6 +5212,7 @@ next_key:
 	err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
 	if (err)
 		goto out_unlock;
+	xattrs_logged = true;
 	if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
 		btrfs_release_path(path);
 		btrfs_release_path(dst_path);
@@ -5140,6 +5225,11 @@ log_extents:
 	btrfs_release_path(dst_path);
 	if (need_log_inode_item) {
 		err = log_inode_item(trans, log, dst_path, inode);
+		if (!err && !xattrs_logged) {
+			err = btrfs_log_all_xattrs(trans, root, inode, path,
+						   dst_path);
+			btrfs_release_path(path);
+		}
 		if (err)
 			goto out_unlock;
 	}
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index 1ba7ca2a4200..3b2ae342e649 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -79,10 +79,10 @@ out:
 	return ret;
 }
 
-int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 			u64 subid_cpu)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *uuid_root = fs_info->uuid_root;
 	int ret;
 	struct btrfs_path *path = NULL;
@@ -144,10 +144,10 @@ out:
 	return ret;
 }
 
-int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 			u64 subid)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *uuid_root = fs_info->uuid_root;
 	int ret;
 	struct btrfs_path *path = NULL;
@@ -239,7 +239,7 @@ static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type,
 		goto out;
 	}
 
-	ret = btrfs_uuid_tree_rem(trans, uuid_root->fs_info, uuid, type, subid);
+	ret = btrfs_uuid_tree_remove(trans, uuid, type, subid);
 	btrfs_end_transaction(trans);
 
 out:
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 292266f6ab9c..e034ad9e23b4 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -40,6 +40,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.tolerated_failures = 1,
 		.devs_increment	= 2,
 		.ncopies	= 2,
+		.raid_name	= "raid10",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID10,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
 	},
 	[BTRFS_RAID_RAID1] = {
 		.sub_stripes	= 1,
@@ -49,6 +52,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.tolerated_failures = 1,
 		.devs_increment	= 2,
 		.ncopies	= 2,
+		.raid_name	= "raid1",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
 	},
 	[BTRFS_RAID_DUP] = {
 		.sub_stripes	= 1,
@@ -58,6 +64,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.tolerated_failures = 0,
 		.devs_increment	= 1,
 		.ncopies	= 2,
+		.raid_name	= "dup",
+		.bg_flag	= BTRFS_BLOCK_GROUP_DUP,
+		.mindev_error	= 0,
 	},
 	[BTRFS_RAID_RAID0] = {
 		.sub_stripes	= 1,
@@ -67,6 +76,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.tolerated_failures = 0,
 		.devs_increment	= 1,
 		.ncopies	= 1,
+		.raid_name	= "raid0",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID0,
+		.mindev_error	= 0,
 	},
 	[BTRFS_RAID_SINGLE] = {
 		.sub_stripes	= 1,
@@ -76,6 +88,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.tolerated_failures = 0,
 		.devs_increment	= 1,
 		.ncopies	= 1,
+		.raid_name	= "single",
+		.bg_flag	= 0,
+		.mindev_error	= 0,
 	},
 	[BTRFS_RAID_RAID5] = {
 		.sub_stripes	= 1,
@@ -85,6 +100,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.tolerated_failures = 1,
 		.devs_increment	= 1,
 		.ncopies	= 2,
+		.raid_name	= "raid5",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID5,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
 	},
 	[BTRFS_RAID_RAID6] = {
 		.sub_stripes	= 1,
@@ -94,33 +112,19 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.tolerated_failures = 2,
 		.devs_increment	= 1,
 		.ncopies	= 3,
+		.raid_name	= "raid6",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID6,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
 	},
 };
 
-const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
-	[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
-	[BTRFS_RAID_RAID1]  = BTRFS_BLOCK_GROUP_RAID1,
-	[BTRFS_RAID_DUP]    = BTRFS_BLOCK_GROUP_DUP,
-	[BTRFS_RAID_RAID0]  = BTRFS_BLOCK_GROUP_RAID0,
-	[BTRFS_RAID_SINGLE] = 0,
-	[BTRFS_RAID_RAID5]  = BTRFS_BLOCK_GROUP_RAID5,
-	[BTRFS_RAID_RAID6]  = BTRFS_BLOCK_GROUP_RAID6,
-};
+const char *get_raid_name(enum btrfs_raid_types type)
+{
+	if (type >= BTRFS_NR_RAID_TYPES)
+		return NULL;
 
-/*
- * Table to convert BTRFS_RAID_* to the error code if minimum number of devices
- * condition is not met. Zero means there's no corresponding
- * BTRFS_ERROR_DEV_*_NOT_MET value.
- */
-const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = {
-	[BTRFS_RAID_RAID10] = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
-	[BTRFS_RAID_RAID1]  = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
-	[BTRFS_RAID_DUP]    = 0,
-	[BTRFS_RAID_RAID0]  = 0,
-	[BTRFS_RAID_SINGLE] = 0,
-	[BTRFS_RAID_RAID5]  = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
-	[BTRFS_RAID_RAID6]  = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
-};
+	return btrfs_raid_array[type].raid_name;
+}
 
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_fs_info *fs_info);
@@ -167,12 +171,6 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
  * may be used to exclude some operations from running concurrently without any
  * modifications to the list (see write_all_supers)
  *
- * volume_mutex
- * ------------
- * coarse lock owned by a mounted filesystem; used to exclude some operations
- * that cannot run in parallel and affect the higher-level properties of the
- * filesystem like: device add/deleting/resize/replace, or balance
- *
  * balance_mutex
  * -------------
  * protects balance structures (status, state) and context accessed from
@@ -197,6 +195,41 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
  *     device_list_mutex
  *       chunk_mutex
  *     balance_mutex
+ *
+ *
+ * Exclusive operations, BTRFS_FS_EXCL_OP
+ * ======================================
+ *
+ * Maintains the exclusivity of the following operations that apply to the
+ * whole filesystem and cannot run in parallel.
+ *
+ * - Balance (*)
+ * - Device add
+ * - Device remove
+ * - Device replace (*)
+ * - Resize
+ *
+ * The device operations (as above) can be in one of the following states:
+ *
+ * - Running state
+ * - Paused state
+ * - Completed state
+ *
+ * Only device operations marked with (*) can go into the Paused state for the
+ * following reasons:
+ *
+ * - ioctl (only Balance can be Paused through ioctl)
+ * - filesystem remounted as read-only
+ * - filesystem unmounted and mounted as read-only
+ * - system power-cycle and filesystem mounted as read-only
+ * - filesystem or device errors leading to forced read-only
+ *
+ * BTRFS_FS_EXCL_OP flag is set and cleared using atomic operations.
+ * During the course of Paused state, the BTRFS_FS_EXCL_OP remains set.
+ * A device operation in Paused or Running state can be canceled or resumed
+ * either by ioctl (Balance only) or when remounted as read-write.
+ * BTRFS_FS_EXCL_OP flag is cleared when the device operation is canceled or
+ * completed.
  */
 
 DEFINE_MUTEX(uuid_mutex);
@@ -227,14 +260,14 @@ static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid)
 	INIT_LIST_HEAD(&fs_devs->devices);
 	INIT_LIST_HEAD(&fs_devs->resized_devices);
 	INIT_LIST_HEAD(&fs_devs->alloc_list);
-	INIT_LIST_HEAD(&fs_devs->list);
+	INIT_LIST_HEAD(&fs_devs->fs_list);
 	if (fsid)
 		memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE);
 
 	return fs_devs;
 }
 
-static void free_device(struct btrfs_device *device)
+void btrfs_free_device(struct btrfs_device *device)
 {
 	rcu_string_free(device->name);
 	bio_put(device->flush_bio);
@@ -249,7 +282,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
 		device = list_entry(fs_devices->devices.next,
 				    struct btrfs_device, dev_list);
 		list_del(&device->dev_list);
-		free_device(device);
+		btrfs_free_device(device);
 	}
 	kfree(fs_devices);
 }
@@ -273,8 +306,8 @@ void __exit btrfs_cleanup_fs_uuids(void)
 
 	while (!list_empty(&fs_uuids)) {
 		fs_devices = list_entry(fs_uuids.next,
-					struct btrfs_fs_devices, list);
-		list_del(&fs_devices->list);
+					struct btrfs_fs_devices, fs_list);
+		list_del(&fs_devices->fs_list);
 		free_fs_devices(fs_devices);
 	}
 }
@@ -282,7 +315,7 @@ void __exit btrfs_cleanup_fs_uuids(void)
 /*
  * Returns a pointer to a new btrfs_device on success; ERR_PTR() on error.
  * Returned struct is not linked onto any lists and must be destroyed using
- * free_device.
+ * btrfs_free_device.
  */
 static struct btrfs_device *__alloc_device(void)
 {
@@ -327,10 +360,9 @@ static struct btrfs_device *__alloc_device(void)
 static struct btrfs_device *find_device(struct btrfs_fs_devices *fs_devices,
 		u64 devid, const u8 *uuid)
 {
-	struct list_head *head = &fs_devices->devices;
 	struct btrfs_device *dev;
 
-	list_for_each_entry(dev, head, dev_list) {
+	list_for_each_entry(dev, &fs_devices->devices, dev_list) {
 		if (dev->devid == devid &&
 		    (!uuid || !memcmp(dev->uuid, uuid, BTRFS_UUID_SIZE))) {
 			return dev;
@@ -343,7 +375,7 @@ static noinline struct btrfs_fs_devices *find_fsid(u8 *fsid)
 {
 	struct btrfs_fs_devices *fs_devices;
 
-	list_for_each_entry(fs_devices, &fs_uuids, list) {
+	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
 		if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0)
 			return fs_devices;
 	}
@@ -607,7 +639,7 @@ static void btrfs_free_stale_devices(const char *path,
 	struct btrfs_fs_devices *fs_devs, *tmp_fs_devs;
 	struct btrfs_device *dev, *tmp_dev;
 
-	list_for_each_entry_safe(fs_devs, tmp_fs_devs, &fs_uuids, list) {
+	list_for_each_entry_safe(fs_devs, tmp_fs_devs, &fs_uuids, fs_list) {
 
 		if (fs_devs->opened)
 			continue;
@@ -632,13 +664,13 @@ static void btrfs_free_stale_devices(const char *path,
 			/* delete the stale device */
 			if (fs_devs->num_devices == 1) {
 				btrfs_sysfs_remove_fsid(fs_devs);
-				list_del(&fs_devs->list);
+				list_del(&fs_devs->fs_list);
 				free_fs_devices(fs_devs);
 				break;
 			} else {
 				fs_devs->num_devices--;
 				list_del(&dev->dev_list);
-				free_device(dev);
+				btrfs_free_device(dev);
 			}
 		}
 	}
@@ -732,7 +764,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		if (IS_ERR(fs_devices))
 			return ERR_CAST(fs_devices);
 
-		list_add(&fs_devices->list, &fs_uuids);
+		list_add(&fs_devices->fs_list, &fs_uuids);
 
 		device = NULL;
 	} else {
@@ -753,7 +785,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 		name = rcu_string_strdup(path, GFP_NOFS);
 		if (!name) {
-			free_device(device);
+			btrfs_free_device(device);
 			return ERR_PTR(-ENOMEM);
 		}
 		rcu_assign_pointer(device->name, name);
@@ -866,7 +898,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 			name = rcu_string_strdup(orig_dev->name->str,
 					GFP_KERNEL);
 			if (!name) {
-				free_device(device);
+				btrfs_free_device(device);
 				goto error;
 			}
 			rcu_assign_pointer(device->name, name);
@@ -938,7 +970,7 @@ again:
 		}
 		list_del_init(&device->dev_list);
 		fs_devices->num_devices--;
-		free_device(device);
+		btrfs_free_device(device);
 	}
 
 	if (fs_devices->seed) {
@@ -956,7 +988,7 @@ static void free_device_rcu(struct rcu_head *head)
 	struct btrfs_device *device;
 
 	device = container_of(head, struct btrfs_device, rcu);
-	free_device(device);
+	btrfs_free_device(device);
 }
 
 static void btrfs_close_bdev(struct btrfs_device *device)
@@ -1005,7 +1037,7 @@ static void btrfs_prepare_close_one_device(struct btrfs_device *device)
 	new_device->fs_devices = device->fs_devices;
 }
 
-static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
+static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device, *tmp;
 	struct list_head pending_put;
@@ -1050,7 +1082,7 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 	int ret;
 
 	mutex_lock(&uuid_mutex);
-	ret = __btrfs_close_devices(fs_devices);
+	ret = close_fs_devices(fs_devices);
 	if (!fs_devices->opened) {
 		seed_devices = fs_devices->seed;
 		fs_devices->seed = NULL;
@@ -1060,23 +1092,22 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 	while (seed_devices) {
 		fs_devices = seed_devices;
 		seed_devices = fs_devices->seed;
-		__btrfs_close_devices(fs_devices);
+		close_fs_devices(fs_devices);
 		free_fs_devices(fs_devices);
 	}
 	return ret;
 }
 
-static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
+static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
 				fmode_t flags, void *holder)
 {
-	struct list_head *head = &fs_devices->devices;
 	struct btrfs_device *device;
 	struct btrfs_device *latest_dev = NULL;
 	int ret = 0;
 
 	flags |= FMODE_EXCL;
 
-	list_for_each_entry(device, head, dev_list) {
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
 		/* Just open everything we can; ignore failures here */
 		if (btrfs_open_one_device(fs_devices, device, flags, holder))
 			continue;
@@ -1115,15 +1146,16 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 {
 	int ret;
 
-	mutex_lock(&uuid_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	if (fs_devices->opened) {
 		fs_devices->opened++;
 		ret = 0;
 	} else {
 		list_sort(NULL, &fs_devices->devices, devid_cmp);
-		ret = __btrfs_open_devices(fs_devices, flags, holder);
+		ret = open_fs_devices(fs_devices, flags, holder);
 	}
-	mutex_unlock(&uuid_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
+
 	return ret;
 }
 
@@ -1201,31 +1233,29 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	 */
 	bytenr = btrfs_sb_offset(0);
 	flags |= FMODE_EXCL;
-	mutex_lock(&uuid_mutex);
 
 	bdev = blkdev_get_by_path(path, flags, holder);
-	if (IS_ERR(bdev)) {
-		ret = PTR_ERR(bdev);
-		goto error;
-	}
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 
 	if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super)) {
 		ret = -EINVAL;
 		goto error_bdev_put;
 	}
 
+	mutex_lock(&uuid_mutex);
 	device = device_list_add(path, disk_super);
 	if (IS_ERR(device))
 		ret = PTR_ERR(device);
 	else
 		*fs_devices_ret = device->fs_devices;
+	mutex_unlock(&uuid_mutex);
 
 	btrfs_release_disk_super(page);
 
 error_bdev_put:
 	blkdev_put(bdev, flags);
-error:
-	mutex_unlock(&uuid_mutex);
+
 	return ret;
 }
 
@@ -1857,11 +1887,11 @@ static int btrfs_check_raid_min_devices(struct btrfs_fs_info *fs_info,
 	} while (read_seqretry(&fs_info->profiles_lock, seq));
 
 	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
-		if (!(all_avail & btrfs_raid_group[i]))
+		if (!(all_avail & btrfs_raid_array[i].bg_flag))
 			continue;
 
 		if (num_devices < btrfs_raid_array[i].devs_min) {
-			int ret = btrfs_raid_mindev_error[i];
+			int ret = btrfs_raid_array[i].mindev_error;
 
 			if (ret)
 				return ret;
@@ -1917,13 +1947,13 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *cur_devices;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	u64 num_devices;
 	int ret = 0;
 
-	mutex_lock(&fs_info->volume_mutex);
 	mutex_lock(&uuid_mutex);
 
-	num_devices = fs_info->fs_devices->num_devices;
+	num_devices = fs_devices->num_devices;
 	btrfs_dev_replace_read_lock(&fs_info->dev_replace);
 	if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
 		WARN_ON(num_devices < 1);
@@ -1986,27 +2016,32 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 	 * (super_copy) should hold the device list mutex.
 	 */
 
+	/*
+	 * In normal cases the cur_devices == fs_devices. But in case
+	 * of deleting a seed device, the cur_devices should point to
+	 * its own fs_devices listed under the fs_devices->seed.
+	 */
 	cur_devices = device->fs_devices;
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	list_del_rcu(&device->dev_list);
 
-	device->fs_devices->num_devices--;
-	device->fs_devices->total_devices--;
+	cur_devices->num_devices--;
+	cur_devices->total_devices--;
 
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
-		device->fs_devices->missing_devices--;
+		cur_devices->missing_devices--;
 
 	btrfs_assign_next_active_device(fs_info, device, NULL);
 
 	if (device->bdev) {
-		device->fs_devices->open_devices--;
+		cur_devices->open_devices--;
 		/* remove sysfs entry */
-		btrfs_sysfs_rm_device_link(fs_info->fs_devices, device);
+		btrfs_sysfs_rm_device_link(fs_devices, device);
 	}
 
 	num_devices = btrfs_super_num_devices(fs_info->super_copy) - 1;
 	btrfs_set_super_num_devices(fs_info->super_copy, num_devices);
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	/*
 	 * at this point, the device is zero sized and detached from
@@ -2020,8 +2055,6 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 	call_rcu(&device->rcu, free_device_rcu);
 
 	if (cur_devices->open_devices == 0) {
-		struct btrfs_fs_devices *fs_devices;
-		fs_devices = fs_info->fs_devices;
 		while (fs_devices) {
 			if (fs_devices->seed == cur_devices) {
 				fs_devices->seed = cur_devices->seed;
@@ -2030,20 +2063,19 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 			fs_devices = fs_devices->seed;
 		}
 		cur_devices->seed = NULL;
-		__btrfs_close_devices(cur_devices);
+		close_fs_devices(cur_devices);
 		free_fs_devices(cur_devices);
 	}
 
 out:
 	mutex_unlock(&uuid_mutex);
-	mutex_unlock(&fs_info->volume_mutex);
 	return ret;
 
 error_undo:
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		mutex_lock(&fs_info->chunk_mutex);
 		list_add(&device->dev_alloc_list,
-			 &fs_info->fs_devices->alloc_list);
+			 &fs_devices->alloc_list);
 		device->fs_devices->rw_devices++;
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
@@ -2112,7 +2144,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 			tmp_fs_devices = tmp_fs_devices->seed;
 		}
 		fs_devices->seed = NULL;
-		__btrfs_close_devices(fs_devices);
+		close_fs_devices(fs_devices);
 		free_fs_devices(fs_devices);
 	}
 }
@@ -2120,23 +2152,23 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *tgtdev)
 {
-	mutex_lock(&uuid_mutex);
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+
 	WARN_ON(!tgtdev);
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 
-	btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
+	btrfs_sysfs_rm_device_link(fs_devices, tgtdev);
 
 	if (tgtdev->bdev)
-		fs_info->fs_devices->open_devices--;
+		fs_devices->open_devices--;
 
-	fs_info->fs_devices->num_devices--;
+	fs_devices->num_devices--;
 
 	btrfs_assign_next_active_device(fs_info, tgtdev, NULL);
 
 	list_del_rcu(&tgtdev->dev_list);
 
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-	mutex_unlock(&uuid_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	/*
 	 * The update_dev_time() with in btrfs_scratch_superblocks()
@@ -2188,10 +2220,6 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
 		struct btrfs_device *tmp;
 
 		devices = &fs_info->fs_devices->devices;
-		/*
-		 * It is safe to read the devices since the volume_mutex
-		 * is held by the caller.
-		 */
 		list_for_each_entry(tmp, devices, dev_list) {
 			if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA,
 					&tmp->dev_state) && !tmp->bdev) {
@@ -2259,7 +2287,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 		return PTR_ERR(old_devices);
 	}
 
-	list_add(&old_devices->list, &fs_uuids);
+	list_add(&old_devices->fs_list, &fs_uuids);
 
 	memcpy(seed_devices, fs_devices, sizeof(*seed_devices));
 	seed_devices->opened = 1;
@@ -2570,7 +2598,7 @@ error_trans:
 	if (trans)
 		btrfs_end_transaction(trans);
 error_free_device:
-	free_device(device);
+	btrfs_free_device(device);
 error:
 	blkdev_put(bdev, FMODE_EXCL);
 	if (seeding_dev && !unlocked) {
@@ -2580,99 +2608,6 @@ error:
 	return ret;
 }
 
-int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				  const char *device_path,
-				  struct btrfs_device *srcdev,
-				  struct btrfs_device **device_out)
-{
-	struct btrfs_device *device;
-	struct block_device *bdev;
-	struct list_head *devices;
-	struct rcu_string *name;
-	u64 devid = BTRFS_DEV_REPLACE_DEVID;
-	int ret = 0;
-
-	*device_out = NULL;
-	if (fs_info->fs_devices->seeding) {
-		btrfs_err(fs_info, "the filesystem is a seed filesystem!");
-		return -EINVAL;
-	}
-
-	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
-				  fs_info->bdev_holder);
-	if (IS_ERR(bdev)) {
-		btrfs_err(fs_info, "target device %s is invalid!", device_path);
-		return PTR_ERR(bdev);
-	}
-
-	filemap_write_and_wait(bdev->bd_inode->i_mapping);
-
-	devices = &fs_info->fs_devices->devices;
-	list_for_each_entry(device, devices, dev_list) {
-		if (device->bdev == bdev) {
-			btrfs_err(fs_info,
-				  "target device is in the filesystem!");
-			ret = -EEXIST;
-			goto error;
-		}
-	}
-
-
-	if (i_size_read(bdev->bd_inode) <
-	    btrfs_device_get_total_bytes(srcdev)) {
-		btrfs_err(fs_info,
-			  "target device is smaller than source device!");
-		ret = -EINVAL;
-		goto error;
-	}
-
-
-	device = btrfs_alloc_device(NULL, &devid, NULL);
-	if (IS_ERR(device)) {
-		ret = PTR_ERR(device);
-		goto error;
-	}
-
-	name = rcu_string_strdup(device_path, GFP_KERNEL);
-	if (!name) {
-		free_device(device);
-		ret = -ENOMEM;
-		goto error;
-	}
-	rcu_assign_pointer(device->name, name);
-
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
-	device->generation = 0;
-	device->io_width = fs_info->sectorsize;
-	device->io_align = fs_info->sectorsize;
-	device->sector_size = fs_info->sectorsize;
-	device->total_bytes = btrfs_device_get_total_bytes(srcdev);
-	device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev);
-	device->bytes_used = btrfs_device_get_bytes_used(srcdev);
-	device->commit_total_bytes = srcdev->commit_total_bytes;
-	device->commit_bytes_used = device->bytes_used;
-	device->fs_info = fs_info;
-	device->bdev = bdev;
-	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
-	set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
-	device->mode = FMODE_EXCL;
-	device->dev_stats_valid = 1;
-	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
-	device->fs_devices = fs_info->fs_devices;
-	list_add(&device->dev_list, &fs_info->fs_devices->devices);
-	fs_info->fs_devices->num_devices++;
-	fs_info->fs_devices->open_devices++;
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-
-	*device_out = device;
-	return ret;
-
-error:
-	blkdev_put(bdev, FMODE_EXCL);
-	return ret;
-}
-
 static noinline int btrfs_update_device(struct btrfs_trans_handle *trans,
 					struct btrfs_device *device)
 {
@@ -3273,24 +3208,12 @@ static void update_balance_args(struct btrfs_balance_control *bctl)
 }
 
 /*
- * Should be called with both balance and volume mutexes held to
- * serialize other volume operations (add_dev/rm_dev/resize) with
- * restriper.  Same goes for unset_balance_control.
+ * Clear the balance status in fs_info and delete the balance item from disk.
  */
-static void set_balance_control(struct btrfs_balance_control *bctl)
-{
-	struct btrfs_fs_info *fs_info = bctl->fs_info;
-
-	BUG_ON(fs_info->balance_ctl);
-
-	spin_lock(&fs_info->balance_lock);
-	fs_info->balance_ctl = bctl;
-	spin_unlock(&fs_info->balance_lock);
-}
-
-static void unset_balance_control(struct btrfs_fs_info *fs_info)
+static void reset_balance_state(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+	int ret;
 
 	BUG_ON(!fs_info->balance_ctl);
 
@@ -3299,6 +3222,9 @@ static void unset_balance_control(struct btrfs_fs_info *fs_info)
 	spin_unlock(&fs_info->balance_lock);
 
 	kfree(bctl);
+	ret = del_balance_item(fs_info);
+	if (ret)
+		btrfs_handle_fs_error(fs_info, ret, NULL);
 }
 
 /*
@@ -3835,18 +3761,6 @@ static inline int balance_need_close(struct btrfs_fs_info *fs_info)
 		 atomic_read(&fs_info->balance_cancel_req) == 0);
 }
 
-static void __cancel_balance(struct btrfs_fs_info *fs_info)
-{
-	int ret;
-
-	unset_balance_control(fs_info);
-	ret = del_balance_item(fs_info);
-	if (ret)
-		btrfs_handle_fs_error(fs_info, ret, NULL);
-
-	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
-}
-
 /* Non-zero return value signifies invalidity */
 static inline int validate_convert_profile(struct btrfs_balance_args *bctl_arg,
 		u64 allowed)
@@ -3857,12 +3771,12 @@ static inline int validate_convert_profile(struct btrfs_balance_args *bctl_arg,
 }
 
 /*
- * Should be called with both balance and volume mutexes held
+ * Should be called with balance mutexe held
  */
-int btrfs_balance(struct btrfs_balance_control *bctl,
+int btrfs_balance(struct btrfs_fs_info *fs_info,
+		  struct btrfs_balance_control *bctl,
 		  struct btrfs_ioctl_balance_args *bargs)
 {
-	struct btrfs_fs_info *fs_info = bctl->fs_info;
 	u64 meta_target, data_target;
 	u64 allowed;
 	int mixed = 0;
@@ -3891,7 +3805,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		    !(bctl->flags & BTRFS_BALANCE_METADATA) ||
 		    memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) {
 			btrfs_err(fs_info,
-				  "with mixed groups data and metadata balance options must be the same");
+	  "balance: mixed groups data and metadata options must be the same");
 			ret = -EINVAL;
 			goto out;
 		}
@@ -3913,23 +3827,29 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		allowed |= (BTRFS_BLOCK_GROUP_RAID10 |
 			    BTRFS_BLOCK_GROUP_RAID6);
 	if (validate_convert_profile(&bctl->data, allowed)) {
+		int index = btrfs_bg_flags_to_raid_index(bctl->data.target);
+
 		btrfs_err(fs_info,
-			  "unable to start balance with target data profile %llu",
-			  bctl->data.target);
+			  "balance: invalid convert data profile %s",
+			  get_raid_name(index));
 		ret = -EINVAL;
 		goto out;
 	}
 	if (validate_convert_profile(&bctl->meta, allowed)) {
+		int index = btrfs_bg_flags_to_raid_index(bctl->meta.target);
+
 		btrfs_err(fs_info,
-			  "unable to start balance with target metadata profile %llu",
-			  bctl->meta.target);
+			  "balance: invalid convert metadata profile %s",
+			  get_raid_name(index));
 		ret = -EINVAL;
 		goto out;
 	}
 	if (validate_convert_profile(&bctl->sys, allowed)) {
+		int index = btrfs_bg_flags_to_raid_index(bctl->sys.target);
+
 		btrfs_err(fs_info,
-			  "unable to start balance with target system profile %llu",
-			  bctl->sys.target);
+			  "balance: invalid convert system profile %s",
+			  get_raid_name(index));
 		ret = -EINVAL;
 		goto out;
 	}
@@ -3950,10 +3870,10 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		     !(bctl->meta.target & allowed))) {
 			if (bctl->flags & BTRFS_BALANCE_FORCE) {
 				btrfs_info(fs_info,
-					   "force reducing metadata integrity");
+				"balance: force reducing metadata integrity");
 			} else {
 				btrfs_err(fs_info,
-					  "balance will reduce metadata integrity, use force if you want this");
+	"balance: reduces metadata integrity, use --force if you want this");
 				ret = -EINVAL;
 				goto out;
 			}
@@ -3967,9 +3887,12 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		bctl->data.target : fs_info->avail_data_alloc_bits;
 	if (btrfs_get_num_tolerated_disk_barrier_failures(meta_target) <
 		btrfs_get_num_tolerated_disk_barrier_failures(data_target)) {
+		int meta_index = btrfs_bg_flags_to_raid_index(meta_target);
+		int data_index = btrfs_bg_flags_to_raid_index(data_target);
+
 		btrfs_warn(fs_info,
-			   "metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
-			   meta_target, data_target);
+	"balance: metadata profile %s has lower redundancy than data profile %s",
+			   get_raid_name(meta_index), get_raid_name(data_index));
 	}
 
 	ret = insert_balance_item(fs_info, bctl);
@@ -3978,7 +3901,10 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 
 	if (!(bctl->flags & BTRFS_BALANCE_RESUME)) {
 		BUG_ON(ret == -EEXIST);
-		set_balance_control(bctl);
+		BUG_ON(fs_info->balance_ctl);
+		spin_lock(&fs_info->balance_lock);
+		fs_info->balance_ctl = bctl;
+		spin_unlock(&fs_info->balance_lock);
 	} else {
 		BUG_ON(ret != -EEXIST);
 		spin_lock(&fs_info->balance_lock);
@@ -3986,22 +3912,24 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		spin_unlock(&fs_info->balance_lock);
 	}
 
-	atomic_inc(&fs_info->balance_running);
+	ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
+	set_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags);
 	mutex_unlock(&fs_info->balance_mutex);
 
 	ret = __btrfs_balance(fs_info);
 
 	mutex_lock(&fs_info->balance_mutex);
-	atomic_dec(&fs_info->balance_running);
+	clear_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags);
 
 	if (bargs) {
 		memset(bargs, 0, sizeof(*bargs));
-		update_ioctl_balance_args(fs_info, 0, bargs);
+		btrfs_update_ioctl_balance_args(fs_info, bargs);
 	}
 
 	if ((ret && ret != -ECANCELED && ret != -ENOSPC) ||
 	    balance_need_close(fs_info)) {
-		__cancel_balance(fs_info);
+		reset_balance_state(fs_info);
+		clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 	}
 
 	wake_up(&fs_info->balance_wait_q);
@@ -4009,11 +3937,11 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 	return ret;
 out:
 	if (bctl->flags & BTRFS_BALANCE_RESUME)
-		__cancel_balance(fs_info);
-	else {
+		reset_balance_state(fs_info);
+	else
 		kfree(bctl);
-		clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
-	}
+	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+
 	return ret;
 }
 
@@ -4022,16 +3950,12 @@ static int balance_kthread(void *data)
 	struct btrfs_fs_info *fs_info = data;
 	int ret = 0;
 
-	mutex_lock(&fs_info->volume_mutex);
 	mutex_lock(&fs_info->balance_mutex);
-
 	if (fs_info->balance_ctl) {
-		btrfs_info(fs_info, "continuing balance");
-		ret = btrfs_balance(fs_info->balance_ctl, NULL);
+		btrfs_info(fs_info, "balance: resuming");
+		ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL);
 	}
-
 	mutex_unlock(&fs_info->balance_mutex);
-	mutex_unlock(&fs_info->volume_mutex);
 
 	return ret;
 }
@@ -4040,18 +3964,27 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
 {
 	struct task_struct *tsk;
 
-	spin_lock(&fs_info->balance_lock);
+	mutex_lock(&fs_info->balance_mutex);
 	if (!fs_info->balance_ctl) {
-		spin_unlock(&fs_info->balance_lock);
+		mutex_unlock(&fs_info->balance_mutex);
 		return 0;
 	}
-	spin_unlock(&fs_info->balance_lock);
+	mutex_unlock(&fs_info->balance_mutex);
 
 	if (btrfs_test_opt(fs_info, SKIP_BALANCE)) {
-		btrfs_info(fs_info, "force skipping balance");
+		btrfs_info(fs_info, "balance: resume skipped");
 		return 0;
 	}
 
+	/*
+	 * A ro->rw remount sequence should continue with the paused balance
+	 * regardless of who pauses it, system or the user as of now, so set
+	 * the resume flag.
+	 */
+	spin_lock(&fs_info->balance_lock);
+	fs_info->balance_ctl->flags |= BTRFS_BALANCE_RESUME;
+	spin_unlock(&fs_info->balance_lock);
+
 	tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
 	return PTR_ERR_OR_ZERO(tsk);
 }
@@ -4091,7 +4024,6 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item);
 
-	bctl->fs_info = fs_info;
 	bctl->flags = btrfs_balance_flags(leaf, item);
 	bctl->flags |= BTRFS_BALANCE_RESUME;
 
@@ -4102,15 +4034,26 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
 	btrfs_balance_sys(leaf, item, &disk_bargs);
 	btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
 
-	WARN_ON(test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
+	/*
+	 * This should never happen, as the paused balance state is recovered
+	 * during mount without any chance of other exclusive ops to collide.
+	 *
+	 * This gives the exclusive op status to balance and keeps in paused
+	 * state until user intervention (cancel or umount). If the ownership
+	 * cannot be assigned, show a message but do not fail. The balance
+	 * is in a paused state and must have fs_info::balance_ctl properly
+	 * set up.
+	 */
+	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
+		btrfs_warn(fs_info,
+	"balance: cannot set exclusive op status, resume manually");
 
-	mutex_lock(&fs_info->volume_mutex);
 	mutex_lock(&fs_info->balance_mutex);
-
-	set_balance_control(bctl);
-
+	BUG_ON(fs_info->balance_ctl);
+	spin_lock(&fs_info->balance_lock);
+	fs_info->balance_ctl = bctl;
+	spin_unlock(&fs_info->balance_lock);
 	mutex_unlock(&fs_info->balance_mutex);
-	mutex_unlock(&fs_info->volume_mutex);
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -4126,16 +4069,16 @@ int btrfs_pause_balance(struct btrfs_fs_info *fs_info)
 		return -ENOTCONN;
 	}
 
-	if (atomic_read(&fs_info->balance_running)) {
+	if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
 		atomic_inc(&fs_info->balance_pause_req);
 		mutex_unlock(&fs_info->balance_mutex);
 
 		wait_event(fs_info->balance_wait_q,
-			   atomic_read(&fs_info->balance_running) == 0);
+			   !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
 
 		mutex_lock(&fs_info->balance_mutex);
 		/* we are good with balance_ctl ripped off from under us */
-		BUG_ON(atomic_read(&fs_info->balance_running));
+		BUG_ON(test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
 		atomic_dec(&fs_info->balance_pause_req);
 	} else {
 		ret = -ENOTCONN;
@@ -4147,38 +4090,49 @@ int btrfs_pause_balance(struct btrfs_fs_info *fs_info)
 
 int btrfs_cancel_balance(struct btrfs_fs_info *fs_info)
 {
-	if (sb_rdonly(fs_info->sb))
-		return -EROFS;
-
 	mutex_lock(&fs_info->balance_mutex);
 	if (!fs_info->balance_ctl) {
 		mutex_unlock(&fs_info->balance_mutex);
 		return -ENOTCONN;
 	}
 
+	/*
+	 * A paused balance with the item stored on disk can be resumed at
+	 * mount time if the mount is read-write. Otherwise it's still paused
+	 * and we must not allow cancelling as it deletes the item.
+	 */
+	if (sb_rdonly(fs_info->sb)) {
+		mutex_unlock(&fs_info->balance_mutex);
+		return -EROFS;
+	}
+
 	atomic_inc(&fs_info->balance_cancel_req);
 	/*
 	 * if we are running just wait and return, balance item is
 	 * deleted in btrfs_balance in this case
 	 */
-	if (atomic_read(&fs_info->balance_running)) {
+	if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
 		mutex_unlock(&fs_info->balance_mutex);
 		wait_event(fs_info->balance_wait_q,
-			   atomic_read(&fs_info->balance_running) == 0);
+			   !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
 		mutex_lock(&fs_info->balance_mutex);
 	} else {
-		/* __cancel_balance needs volume_mutex */
 		mutex_unlock(&fs_info->balance_mutex);
-		mutex_lock(&fs_info->volume_mutex);
+		/*
+		 * Lock released to allow other waiters to continue, we'll
+		 * reexamine the status again.
+		 */
 		mutex_lock(&fs_info->balance_mutex);
 
-		if (fs_info->balance_ctl)
-			__cancel_balance(fs_info);
-
-		mutex_unlock(&fs_info->volume_mutex);
+		if (fs_info->balance_ctl) {
+			reset_balance_state(fs_info);
+			clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+			btrfs_info(fs_info, "balance: canceled");
+		}
 	}
 
-	BUG_ON(fs_info->balance_ctl || atomic_read(&fs_info->balance_running));
+	BUG_ON(fs_info->balance_ctl ||
+		test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
 	atomic_dec(&fs_info->balance_cancel_req);
 	mutex_unlock(&fs_info->balance_mutex);
 	return 0;
@@ -4255,8 +4209,7 @@ static int btrfs_uuid_scan_kthread(void *data)
 		}
 update_tree:
 		if (!btrfs_is_empty_uuid(root_item.uuid)) {
-			ret = btrfs_uuid_tree_add(trans, fs_info,
-						  root_item.uuid,
+			ret = btrfs_uuid_tree_add(trans, root_item.uuid,
 						  BTRFS_UUID_KEY_SUBVOL,
 						  key.objectid);
 			if (ret < 0) {
@@ -4267,7 +4220,7 @@ update_tree:
 		}
 
 		if (!btrfs_is_empty_uuid(root_item.received_uuid)) {
-			ret = btrfs_uuid_tree_add(trans, fs_info,
+			ret = btrfs_uuid_tree_add(trans,
 						  root_item.received_uuid,
 						 BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 						  key.objectid);
@@ -4473,7 +4426,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = READA_FORWARD;
+	path->reada = READA_BACK;
 
 	mutex_lock(&fs_info->chunk_mutex);
 
@@ -6034,9 +5987,8 @@ int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	return __btrfs_map_block(fs_info, op, logical, length, bbio_ret, 0, 1);
 }
 
-int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
-		     u64 chunk_start, u64 physical, u64 devid,
-		     u64 **logical, int *naddrs, int *stripe_len)
+int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
+		     u64 physical, u64 **logical, int *naddrs, int *stripe_len)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
@@ -6068,8 +6020,6 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
 	BUG_ON(!buf); /* -ENOMEM */
 
 	for (i = 0; i < map->num_stripes; i++) {
-		if (devid && map->stripes[i].dev->devid != devid)
-			continue;
 		if (map->stripes[i].physical > physical ||
 		    map->stripes[i].physical + length <= physical)
 			continue;
@@ -6401,7 +6351,7 @@ static struct btrfs_device *add_missing_dev(struct btrfs_fs_devices *fs_devices,
  *
  * Return: a pointer to a new &struct btrfs_device on success; ERR_PTR()
  * on error.  Returned struct is not linked onto any lists and must be
- * destroyed with free_device.
+ * destroyed with btrfs_free_device.
  */
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u64 *devid,
@@ -6424,7 +6374,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 
 		ret = find_next_devid(fs_info, &tmp);
 		if (ret) {
-			free_device(dev);
+			btrfs_free_device(dev);
 			return ERR_PTR(ret);
 		}
 	}
@@ -6675,8 +6625,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(fs_devices))
 		return fs_devices;
 
-	ret = __btrfs_open_devices(fs_devices, FMODE_READ,
-				   fs_info->bdev_holder);
+	ret = open_fs_devices(fs_devices, FMODE_READ, fs_info->bdev_holder);
 	if (ret) {
 		free_fs_devices(fs_devices);
 		fs_devices = ERR_PTR(ret);
@@ -6684,7 +6633,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 	}
 
 	if (!fs_devices->seeding) {
-		__btrfs_close_devices(fs_devices);
+		close_fs_devices(fs_devices);
 		free_fs_devices(fs_devices);
 		fs_devices = ERR_PTR(-EINVAL);
 		goto out;
@@ -6993,6 +6942,10 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	if (!path)
 		return -ENOMEM;
 
+	/*
+	 * uuid_mutex is needed only if we are mounting a sprout FS
+	 * otherwise we don't need it.
+	 */
 	mutex_lock(&uuid_mutex);
 	mutex_lock(&fs_info->chunk_mutex);
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 79096884654f..5139ec8daf4c 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -208,6 +208,7 @@ BTRFS_DEVICE_GETSET_FUNCS(bytes_used);
 
 struct btrfs_fs_devices {
 	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
+	struct list_head fs_list;
 
 	u64 num_devices;
 	u64 open_devices;
@@ -229,7 +230,6 @@ struct btrfs_fs_devices {
 	struct list_head resized_devices;
 	/* devices not currently being allocated */
 	struct list_head alloc_list;
-	struct list_head list;
 
 	struct btrfs_fs_devices *seed;
 	int seeding;
@@ -329,11 +329,12 @@ struct btrfs_raid_attr {
 	int tolerated_failures; /* max tolerated fail devs */
 	int devs_increment;	/* ndevs has to be a multiple of this */
 	int ncopies;		/* how many copies to data has */
+	int mindev_error;	/* error code if min devs requisite is unmet */
+	const char raid_name[8]; /* name of the raid */
+	u64 bg_flag;		/* block group flag of the raid */
 };
 
 extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
-extern const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES];
-extern const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES];
 
 struct map_lookup {
 	u64 type;
@@ -351,8 +352,6 @@ struct map_lookup {
 struct btrfs_balance_args;
 struct btrfs_balance_progress;
 struct btrfs_balance_control {
-	struct btrfs_fs_info *fs_info;
-
 	struct btrfs_balance_args data;
 	struct btrfs_balance_args meta;
 	struct btrfs_balance_args sys;
@@ -393,9 +392,8 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
 		     struct btrfs_bio **bbio_ret);
-int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
-		     u64 chunk_start, u64 physical, u64 devid,
-		     u64 **logical, int *naddrs, int *stripe_len);
+int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
+		     u64 physical, u64 **logical, int *naddrs, int *stripe_len);
 int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
 int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
@@ -421,6 +419,7 @@ int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid,
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u64 *devid,
 					const u8 *uuid);
+void btrfs_free_device(struct btrfs_device *device);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    const char *device_path, u64 devid);
 void __exit btrfs_cleanup_fs_uuids(void);
@@ -431,11 +430,8 @@ struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
 				       u8 *uuid, u8 *fsid);
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
 int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
-int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				  const char *device_path,
-				  struct btrfs_device *srcdev,
-				  struct btrfs_device **device_out);
-int btrfs_balance(struct btrfs_balance_control *bctl,
+int btrfs_balance(struct btrfs_fs_info *fs_info,
+		  struct btrfs_balance_control *bctl,
 		  struct btrfs_ioctl_balance_args *bargs);
 int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info);
 int btrfs_recover_balance(struct btrfs_fs_info *fs_info);
@@ -553,6 +549,8 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
 	return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */
 }
 
+const char *get_raid_name(enum btrfs_raid_types type);
+
 void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info);
 void btrfs_update_commit_device_bytes_used(struct btrfs_transaction *trans);
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 249b83fafe48..cabc045f483d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3427,120 +3427,6 @@ int bh_submit_read(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(bh_submit_read);
 
-/*
- * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
- *
- * Returns the offset within the file on success, and -ENOENT otherwise.
- */
-static loff_t
-page_seek_hole_data(struct page *page, loff_t lastoff, int whence)
-{
-	loff_t offset = page_offset(page);
-	struct buffer_head *bh, *head;
-	bool seek_data = whence == SEEK_DATA;
-
-	if (lastoff < offset)
-		lastoff = offset;
-
-	bh = head = page_buffers(page);
-	do {
-		offset += bh->b_size;
-		if (lastoff >= offset)
-			continue;
-
-		/*
-		 * Unwritten extents that have data in the page cache covering
-		 * them can be identified by the BH_Unwritten state flag.
-		 * Pages with multiple buffers might have a mix of holes, data
-		 * and unwritten extents - any buffer with valid data in it
-		 * should have BH_Uptodate flag set on it.
-		 */
-
-		if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data)
-			return lastoff;
-
-		lastoff = offset;
-	} while ((bh = bh->b_this_page) != head);
-	return -ENOENT;
-}
-
-/*
- * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
- *
- * Within unwritten extents, the page cache determines which parts are holes
- * and which are data: unwritten and uptodate buffer heads count as data;
- * everything else counts as a hole.
- *
- * Returns the resulting offset on successs, and -ENOENT otherwise.
- */
-loff_t
-page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
-			  int whence)
-{
-	pgoff_t index = offset >> PAGE_SHIFT;
-	pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
-	loff_t lastoff = offset;
-	struct pagevec pvec;
-
-	if (length <= 0)
-		return -ENOENT;
-
-	pagevec_init(&pvec);
-
-	do {
-		unsigned nr_pages, i;
-
-		nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
-						end - 1);
-		if (nr_pages == 0)
-			break;
-
-		for (i = 0; i < nr_pages; i++) {
-			struct page *page = pvec.pages[i];
-
-			/*
-			 * At this point, the page may be truncated or
-			 * invalidated (changing page->mapping to NULL), or
-			 * even swizzled back from swapper_space to tmpfs file
-			 * mapping.  However, page->index will not change
-			 * because we have a reference on the page.
-                         *
-			 * If current page offset is beyond where we've ended,
-			 * we've found a hole.
-                         */
-			if (whence == SEEK_HOLE &&
-			    lastoff < page_offset(page))
-				goto check_range;
-
-			lock_page(page);
-			if (likely(page->mapping == inode->i_mapping) &&
-			    page_has_buffers(page)) {
-				lastoff = page_seek_hole_data(page, lastoff, whence);
-				if (lastoff >= 0) {
-					unlock_page(page);
-					goto check_range;
-				}
-			}
-			unlock_page(page);
-			lastoff = page_offset(page) + PAGE_SIZE;
-		}
-		pagevec_release(&pvec);
-	} while (index < end);
-
-	/* When no page at lastoff and we are not done, we found a hole. */
-	if (whence != SEEK_HOLE)
-		goto not_found;
-
-check_range:
-	if (lastoff < offset + length)
-		goto out;
-not_found:
-	lastoff = -ENOENT;
-out:
-	pagevec_release(&pvec);
-	return lastoff;
-}
-
 void __init buffer_init(void)
 {
 	unsigned long nrpages;
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 0daa1e3fe0df..ab0bbe93b398 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -572,6 +572,11 @@ lookup_again:
 			if (ret < 0)
 				goto create_error;
 
+			if (unlikely(d_unhashed(next))) {
+				dput(next);
+				inode_unlock(d_inode(dir));
+				goto lookup_again;
+			}
 			ASSERT(d_backing_inode(next));
 
 			_debug("mkdir -> %p{%p{ino=%lu}}",
@@ -764,6 +769,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 	/* search the current directory for the element name */
 	inode_lock(d_inode(dir));
 
+retry:
 	start = jiffies;
 	subdir = lookup_one_len(dirname, dir, strlen(dirname));
 	cachefiles_hist(cachefiles_lookup_histogram, start);
@@ -793,6 +799,10 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 		if (ret < 0)
 			goto mkdir_error;
 
+		if (unlikely(d_unhashed(subdir))) {
+			dput(subdir);
+			goto retry;
+		}
 		ASSERT(d_backing_inode(subdir));
 
 		_debug("mkdir -> %p{%p{ino=%lu}}",
diff --git a/fs/cachefiles/proc.c b/fs/cachefiles/proc.c
index 125b90f6c796..0ce1aa56b67f 100644
--- a/fs/cachefiles/proc.c
+++ b/fs/cachefiles/proc.c
@@ -85,21 +85,6 @@ static const struct seq_operations cachefiles_histogram_ops = {
 };
 
 /*
- * open "/proc/fs/cachefiles/XXX" which provide statistics summaries
- */
-static int cachefiles_histogram_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &cachefiles_histogram_ops);
-}
-
-static const struct file_operations cachefiles_histogram_fops = {
-	.open		= cachefiles_histogram_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-/*
  * initialise the /proc/fs/cachefiles/ directory
  */
 int __init cachefiles_proc_init(void)
@@ -109,8 +94,8 @@ int __init cachefiles_proc_init(void)
 	if (!proc_mkdir("fs/cachefiles", NULL))
 		goto error_dir;
 
-	if (!proc_create("fs/cachefiles/histogram", S_IFREG | 0444, NULL,
-			 &cachefiles_histogram_fops))
+	if (!proc_create_seq("fs/cachefiles/histogram", S_IFREG | 0444, NULL,
+			 &cachefiles_histogram_ops))
 		goto error_histogram;
 
 	_leave(" = 0");
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index f85040d73e3d..cf0e45b10121 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -70,69 +70,104 @@ static __le32 ceph_flags_sys2wire(u32 flags)
  */
 
 /*
- * Calculate the length sum of direct io vectors that can
- * be combined into one page vector.
+ * How many pages to get in one call to iov_iter_get_pages().  This
+ * determines the size of the on-stack array used as a buffer.
  */
-static size_t dio_get_pagev_size(const struct iov_iter *it)
+#define ITER_GET_BVECS_PAGES	64
+
+static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize,
+				struct bio_vec *bvecs)
 {
-    const struct iovec *iov = it->iov;
-    const struct iovec *iovend = iov + it->nr_segs;
-    size_t size;
-
-    size = iov->iov_len - it->iov_offset;
-    /*
-     * An iov can be page vectored when both the current tail
-     * and the next base are page aligned.
-     */
-    while (PAGE_ALIGNED((iov->iov_base + iov->iov_len)) &&
-           (++iov < iovend && PAGE_ALIGNED((iov->iov_base)))) {
-        size += iov->iov_len;
-    }
-    dout("dio_get_pagevlen len = %zu\n", size);
-    return size;
+	size_t size = 0;
+	int bvec_idx = 0;
+
+	if (maxsize > iov_iter_count(iter))
+		maxsize = iov_iter_count(iter);
+
+	while (size < maxsize) {
+		struct page *pages[ITER_GET_BVECS_PAGES];
+		ssize_t bytes;
+		size_t start;
+		int idx = 0;
+
+		bytes = iov_iter_get_pages(iter, pages, maxsize - size,
+					   ITER_GET_BVECS_PAGES, &start);
+		if (bytes < 0)
+			return size ?: bytes;
+
+		iov_iter_advance(iter, bytes);
+		size += bytes;
+
+		for ( ; bytes; idx++, bvec_idx++) {
+			struct bio_vec bv = {
+				.bv_page = pages[idx],
+				.bv_len = min_t(int, bytes, PAGE_SIZE - start),
+				.bv_offset = start,
+			};
+
+			bvecs[bvec_idx] = bv;
+			bytes -= bv.bv_len;
+			start = 0;
+		}
+	}
+
+	return size;
 }
 
 /*
- * Allocate a page vector based on (@it, @nbytes).
- * The return value is the tuple describing a page vector,
- * that is (@pages, @page_align, @num_pages).
+ * iov_iter_get_pages() only considers one iov_iter segment, no matter
+ * what maxsize or maxpages are given.  For ITER_BVEC that is a single
+ * page.
+ *
+ * Attempt to get up to @maxsize bytes worth of pages from @iter.
+ * Return the number of bytes in the created bio_vec array, or an error.
  */
-static struct page **
-dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes,
-		    size_t *page_align, int *num_pages)
+static ssize_t iter_get_bvecs_alloc(struct iov_iter *iter, size_t maxsize,
+				    struct bio_vec **bvecs, int *num_bvecs)
 {
-	struct iov_iter tmp_it = *it;
-	size_t align;
-	struct page **pages;
-	int ret = 0, idx, npages;
+	struct bio_vec *bv;
+	size_t orig_count = iov_iter_count(iter);
+	ssize_t bytes;
+	int npages;
 
-	align = (unsigned long)(it->iov->iov_base + it->iov_offset) &
-		(PAGE_SIZE - 1);
-	npages = calc_pages_for(align, nbytes);
-	pages = kvmalloc(sizeof(*pages) * npages, GFP_KERNEL);
-	if (!pages)
-		return ERR_PTR(-ENOMEM);
+	iov_iter_truncate(iter, maxsize);
+	npages = iov_iter_npages(iter, INT_MAX);
+	iov_iter_reexpand(iter, orig_count);
 
-	for (idx = 0; idx < npages; ) {
-		size_t start;
-		ret = iov_iter_get_pages(&tmp_it, pages + idx, nbytes,
-					 npages - idx, &start);
-		if (ret < 0)
-			goto fail;
+	/*
+	 * __iter_get_bvecs() may populate only part of the array -- zero it
+	 * out.
+	 */
+	bv = kvmalloc_array(npages, sizeof(*bv), GFP_KERNEL | __GFP_ZERO);
+	if (!bv)
+		return -ENOMEM;
 
-		iov_iter_advance(&tmp_it, ret);
-		nbytes -= ret;
-		idx += (ret + start + PAGE_SIZE - 1) / PAGE_SIZE;
+	bytes = __iter_get_bvecs(iter, maxsize, bv);
+	if (bytes < 0) {
+		/*
+		 * No pages were pinned -- just free the array.
+		 */
+		kvfree(bv);
+		return bytes;
 	}
 
-	BUG_ON(nbytes != 0);
-	*num_pages = npages;
-	*page_align = align;
-	dout("dio_get_pages_alloc: got %d pages align %zu\n", npages, align);
-	return pages;
-fail:
-	ceph_put_page_vector(pages, idx, false);
-	return ERR_PTR(ret);
+	*bvecs = bv;
+	*num_bvecs = npages;
+	return bytes;
+}
+
+static void put_bvecs(struct bio_vec *bvecs, int num_bvecs, bool should_dirty)
+{
+	int i;
+
+	for (i = 0; i < num_bvecs; i++) {
+		if (bvecs[i].bv_page) {
+			if (should_dirty)
+				set_page_dirty_lock(bvecs[i].bv_page);
+			put_page(bvecs[i].bv_page);
+		}
+	}
+	kvfree(bvecs);
 }
 
 /*
@@ -746,11 +781,12 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 	struct inode *inode = req->r_inode;
 	struct ceph_aio_request *aio_req = req->r_priv;
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
-	int num_pages = calc_pages_for((u64)osd_data->alignment,
-				       osd_data->length);
 
-	dout("ceph_aio_complete_req %p rc %d bytes %llu\n",
-	     inode, rc, osd_data->length);
+	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
+	BUG_ON(!osd_data->num_bvecs);
+
+	dout("ceph_aio_complete_req %p rc %d bytes %u\n",
+	     inode, rc, osd_data->bvec_pos.iter.bi_size);
 
 	if (rc == -EOLDSNAPC) {
 		struct ceph_aio_work *aio_work;
@@ -768,9 +804,10 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 	} else if (!aio_req->write) {
 		if (rc == -ENOENT)
 			rc = 0;
-		if (rc >= 0 && osd_data->length > rc) {
-			int zoff = osd_data->alignment + rc;
-			int zlen = osd_data->length - rc;
+		if (rc >= 0 && osd_data->bvec_pos.iter.bi_size > rc) {
+			struct iov_iter i;
+			int zlen = osd_data->bvec_pos.iter.bi_size - rc;
+
 			/*
 			 * If read is satisfied by single OSD request,
 			 * it can pass EOF. Otherwise read is within
@@ -785,13 +822,16 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 				aio_req->total_len = rc + zlen;
 			}
 
-			if (zlen > 0)
-				ceph_zero_page_vector_range(zoff, zlen,
-							    osd_data->pages);
+			iov_iter_bvec(&i, ITER_BVEC, osd_data->bvec_pos.bvecs,
+				      osd_data->num_bvecs,
+				      osd_data->bvec_pos.iter.bi_size);
+			iov_iter_advance(&i, rc);
+			iov_iter_zero(zlen, &i);
 		}
 	}
 
-	ceph_put_page_vector(osd_data->pages, num_pages, aio_req->should_dirty);
+	put_bvecs(osd_data->bvec_pos.bvecs, osd_data->num_bvecs,
+		  aio_req->should_dirty);
 	ceph_osdc_put_request(req);
 
 	if (rc < 0)
@@ -879,7 +919,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_vino vino;
 	struct ceph_osd_request *req;
-	struct page **pages;
+	struct bio_vec *bvecs;
 	struct ceph_aio_request *aio_req = NULL;
 	int num_pages = 0;
 	int flags;
@@ -914,10 +954,14 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	while (iov_iter_count(iter) > 0) {
-		u64 size = dio_get_pagev_size(iter);
-		size_t start = 0;
+		u64 size = iov_iter_count(iter);
 		ssize_t len;
 
+		if (write)
+			size = min_t(u64, size, fsc->mount_options->wsize);
+		else
+			size = min_t(u64, size, fsc->mount_options->rsize);
+
 		vino = ceph_vino(inode);
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 					    vino, pos, &size, 0,
@@ -933,18 +977,14 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 			break;
 		}
 
-		if (write)
-			size = min_t(u64, size, fsc->mount_options->wsize);
-		else
-			size = min_t(u64, size, fsc->mount_options->rsize);
-
-		len = size;
-		pages = dio_get_pages_alloc(iter, len, &start, &num_pages);
-		if (IS_ERR(pages)) {
+		len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages);
+		if (len < 0) {
 			ceph_osdc_put_request(req);
-			ret = PTR_ERR(pages);
+			ret = len;
 			break;
 		}
+		if (len != size)
+			osd_req_op_extent_update(req, 0, len);
 
 		/*
 		 * To simplify error handling, allow AIO when IO within i_size
@@ -977,8 +1017,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 			req->r_mtime = mtime;
 		}
 
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len, start,
-						 false, false);
+		osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
 
 		if (aio_req) {
 			aio_req->total_len += len;
@@ -991,7 +1030,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 			list_add_tail(&req->r_unsafe_item, &aio_req->osd_reqs);
 
 			pos += len;
-			iov_iter_advance(iter, len);
 			continue;
 		}
 
@@ -1004,25 +1042,26 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 			if (ret == -ENOENT)
 				ret = 0;
 			if (ret >= 0 && ret < len && pos + ret < size) {
+				struct iov_iter i;
 				int zlen = min_t(size_t, len - ret,
 						 size - pos - ret);
-				ceph_zero_page_vector_range(start + ret, zlen,
-							    pages);
+
+				iov_iter_bvec(&i, ITER_BVEC, bvecs, num_pages,
+					      len);
+				iov_iter_advance(&i, ret);
+				iov_iter_zero(zlen, &i);
 				ret += zlen;
 			}
 			if (ret >= 0)
 				len = ret;
 		}
 
-		ceph_put_page_vector(pages, num_pages, should_dirty);
-
+		put_bvecs(bvecs, num_pages, should_dirty);
 		ceph_osdc_put_request(req);
 		if (ret < 0)
 			break;
 
 		pos += len;
-		iov_iter_advance(iter, len);
-
 		if (!write && pos >= size)
 			break;
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8bf60250309e..ae056927080d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -669,13 +669,15 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 		      CEPH_CAP_FILE_BUFFER|
 		      CEPH_CAP_AUTH_EXCL|
 		      CEPH_CAP_XATTR_EXCL)) {
-		if (timespec_compare(ctime, &inode->i_ctime) > 0) {
+		if (ci->i_version == 0 ||
+		    timespec_compare(ctime, &inode->i_ctime) > 0) {
 			dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
 			     inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
 			     ctime->tv_sec, ctime->tv_nsec);
 			inode->i_ctime = *ctime;
 		}
-		if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
+		if (ci->i_version == 0 ||
+		    ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
 			/* the MDS did a utimes() */
 			dout("mtime %ld.%09ld -> %ld.%09ld "
 			     "tw %d -> %d\n",
@@ -795,7 +797,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	new_issued = ~issued & le32_to_cpu(info->cap.caps);
 
 	/* update inode */
-	ci->i_version = le64_to_cpu(info->version);
 	inode->i_rdev = le32_to_cpu(info->rdev);
 	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
 
@@ -868,6 +869,9 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 		xattr_blob = NULL;
 	}
 
+	/* finally update i_version */
+	ci->i_version = le64_to_cpu(info->version);
+
 	inode->i_mapping->a_ops = &ceph_aops;
 
 	switch (inode->i_mode & S_IFMT) {
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 7e72348639e4..315f7e63e7cc 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -228,7 +228,15 @@ static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
 
 static bool ceph_vxattrcb_quota_exists(struct ceph_inode_info *ci)
 {
-	return (ci->i_max_files || ci->i_max_bytes);
+	bool ret = false;
+	spin_lock(&ci->i_ceph_lock);
+	if ((ci->i_max_files || ci->i_max_bytes) &&
+	    ci->i_vino.snap == CEPH_NOSNAP &&
+	    ci->i_snap_realm &&
+	    ci->i_snap_realm->ino == ci->i_vino.ino)
+		ret = true;
+	spin_unlock(&ci->i_ceph_lock);
+	return ret;
 }
 
 static size_t ceph_vxattrcb_quota(struct ceph_inode_info *ci, char *val,
@@ -1008,14 +1016,19 @@ int __ceph_setxattr(struct inode *inode, const char *name,
 	char *newval = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
 	int required_blob_size;
+	bool check_realm = false;
 	bool lock_snap_rwsem = false;
 
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
 
 	vxattr = ceph_match_vxattr(inode, name);
-	if (vxattr && vxattr->readonly)
-		return -EOPNOTSUPP;
+	if (vxattr) {
+		if (vxattr->readonly)
+			return -EOPNOTSUPP;
+		if (value && !strncmp(vxattr->name, "ceph.quota", 10))
+			check_realm = true;
+	}
 
 	/* pass any unhandled ceph.* xattrs through to the MDS */
 	if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
@@ -1109,6 +1122,15 @@ do_sync_unlocked:
 		err = -EBUSY;
 	} else {
 		err = ceph_sync_setxattr(inode, name, value, size, flags);
+		if (err >= 0 && check_realm) {
+			/* check if snaprealm was created for quota inode */
+			spin_lock(&ci->i_ceph_lock);
+			if ((ci->i_max_files || ci->i_max_bytes) &&
+			    !(ci->i_snap_realm &&
+			      ci->i_snap_realm->ino == ci->i_vino.ino))
+				err = -EOPNOTSUPP;
+			spin_unlock(&ci->i_ceph_lock);
+		}
 	}
 out:
 	ceph_free_cap_flush(prealloc_cf);
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 741749a98614..5f132d59dfc2 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -197,7 +197,7 @@ config CIFS_SMB311
 
 config CIFS_SMB_DIRECT
 	bool "SMB Direct support (Experimental)"
-	depends on CIFS=m && INFINIBAND || CIFS=y && INFINIBAND=y
+	depends on CIFS=m && INFINIBAND && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND=y && INFINIBAND_ADDR_TRANS=y
 	help
 	  Enables SMB Direct experimental support for SMB 3.0, 3.02 and 3.1.1.
 	  SMB Direct allows transferring SMB packets over RDMA. If unsure,
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 7e4a1e2f0696..85817991ee68 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -1,11 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
 #
-# Makefile for Linux CIFS VFS client 
+# Makefile for Linux CIFS/SMB2/SMB3 VFS client
 #
+ccflags-y += -I$(src)		# needed for trace events
 obj-$(CONFIG_CIFS) += cifs.o
 
-cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
-	  link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \
+cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \
+	  inode.o link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \
 	  cifs_unicode.o nterr.o cifsencrypt.o \
 	  readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o \
 	  smb2ops.o smb2maperror.o smb2transport.o \
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 9d69ea433330..116146022aa1 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -42,7 +42,7 @@ cifs_dump_mem(char *label, void *data, int length)
 		       data, length, true);
 }
 
-void cifs_dump_detail(void *buf)
+void cifs_dump_detail(void *buf, struct TCP_Server_Info *server)
 {
 #ifdef CONFIG_CIFS_DEBUG2
 	struct smb_hdr *smb = (struct smb_hdr *)buf;
@@ -50,7 +50,8 @@ void cifs_dump_detail(void *buf)
 	cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d\n",
 		 smb->Command, smb->Status.CifsError,
 		 smb->Flags, smb->Flags2, smb->Mid, smb->Pid);
-	cifs_dbg(VFS, "smb buf %p len %u\n", smb, smbCalcSize(smb));
+	cifs_dbg(VFS, "smb buf %p len %u\n", smb,
+		 server->ops->calc_smb_size(smb, server));
 #endif /* CONFIG_CIFS_DEBUG2 */
 }
 
@@ -83,7 +84,7 @@ void cifs_dump_mids(struct TCP_Server_Info *server)
 		cifs_dbg(VFS, "IsMult: %d IsEnd: %d\n",
 			 mid_entry->multiRsp, mid_entry->multiEnd);
 		if (mid_entry->resp_buf) {
-			cifs_dump_detail(mid_entry->resp_buf);
+			cifs_dump_detail(mid_entry->resp_buf, server);
 			cifs_dump_mem("existing buf: ",
 				mid_entry->resp_buf, 62);
 		}
@@ -113,6 +114,8 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon)
 		seq_printf(m, " type: %d ", dev_type);
 	if (tcon->seal)
 		seq_printf(m, " Encrypted");
+	if (tcon->nocase)
+		seq_printf(m, " nocase");
 	if (tcon->unix_ext)
 		seq_printf(m, " POSIX Extensions");
 	if (tcon->ses->server->ops->dump_share_caps)
@@ -237,6 +240,10 @@ skip_rdma:
 			server->credits,  server->dialect);
 		if (server->sign)
 			seq_printf(m, " signed");
+#ifdef CONFIG_CIFS_SMB311
+		if (server->posix_ext_supported)
+			seq_printf(m, " posix");
+#endif /* 3.1.1 */
 		i++;
 		list_for_each(tmp2, &server->smb_ses_list) {
 			ses = list_entry(tmp2, struct cifs_ses,
@@ -314,18 +321,6 @@ skip_rdma:
 	return 0;
 }
 
-static int cifs_debug_data_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, cifs_debug_data_proc_show, NULL);
-}
-
-static const struct file_operations cifs_debug_data_proc_fops = {
-	.open		= cifs_debug_data_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 #ifdef CONFIG_CIFS_STATS
 static ssize_t cifs_stats_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
@@ -497,35 +492,36 @@ cifs_proc_init(void)
 	if (proc_fs_cifs == NULL)
 		return;
 
-	proc_create("DebugData", 0, proc_fs_cifs, &cifs_debug_data_proc_fops);
+	proc_create_single("DebugData", 0, proc_fs_cifs,
+			cifs_debug_data_proc_show);
 
 #ifdef CONFIG_CIFS_STATS
-	proc_create("Stats", 0, proc_fs_cifs, &cifs_stats_proc_fops);
+	proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops);
 #endif /* STATS */
-	proc_create("cifsFYI", 0, proc_fs_cifs, &cifsFYI_proc_fops);
-	proc_create("traceSMB", 0, proc_fs_cifs, &traceSMB_proc_fops);
-	proc_create("LinuxExtensionsEnabled", 0, proc_fs_cifs,
+	proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops);
+	proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops);
+	proc_create("LinuxExtensionsEnabled", 0644, proc_fs_cifs,
 		    &cifs_linux_ext_proc_fops);
-	proc_create("SecurityFlags", 0, proc_fs_cifs,
+	proc_create("SecurityFlags", 0644, proc_fs_cifs,
 		    &cifs_security_flags_proc_fops);
-	proc_create("LookupCacheEnabled", 0, proc_fs_cifs,
+	proc_create("LookupCacheEnabled", 0644, proc_fs_cifs,
 		    &cifs_lookup_cache_proc_fops);
 #ifdef CONFIG_CIFS_SMB_DIRECT
-	proc_create("rdma_readwrite_threshold", 0, proc_fs_cifs,
+	proc_create("rdma_readwrite_threshold", 0644, proc_fs_cifs,
 		&cifs_rdma_readwrite_threshold_proc_fops);
-	proc_create("smbd_max_frmr_depth", 0, proc_fs_cifs,
+	proc_create("smbd_max_frmr_depth", 0644, proc_fs_cifs,
 		&cifs_smbd_max_frmr_depth_proc_fops);
-	proc_create("smbd_keep_alive_interval", 0, proc_fs_cifs,
+	proc_create("smbd_keep_alive_interval", 0644, proc_fs_cifs,
 		&cifs_smbd_keep_alive_interval_proc_fops);
-	proc_create("smbd_max_receive_size", 0, proc_fs_cifs,
+	proc_create("smbd_max_receive_size", 0644, proc_fs_cifs,
 		&cifs_smbd_max_receive_size_proc_fops);
-	proc_create("smbd_max_fragmented_recv_size", 0, proc_fs_cifs,
+	proc_create("smbd_max_fragmented_recv_size", 0644, proc_fs_cifs,
 		&cifs_smbd_max_fragmented_recv_size_proc_fops);
-	proc_create("smbd_max_send_size", 0, proc_fs_cifs,
+	proc_create("smbd_max_send_size", 0644, proc_fs_cifs,
 		&cifs_smbd_max_send_size_proc_fops);
-	proc_create("smbd_send_credit_target", 0, proc_fs_cifs,
+	proc_create("smbd_send_credit_target", 0644, proc_fs_cifs,
 		&cifs_smbd_send_credit_target_proc_fops);
-	proc_create("smbd_receive_credit_max", 0, proc_fs_cifs,
+	proc_create("smbd_receive_credit_max", 0644, proc_fs_cifs,
 		&cifs_smbd_receive_credit_max_proc_fops);
 #endif
 }
@@ -583,6 +579,8 @@ static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
 		cifsFYI = bv;
 	else if ((c[0] > '1') && (c[0] <= '9'))
 		cifsFYI = (int) (c[0] - '0'); /* see cifs_debug.h for meanings */
+	else
+		return -EINVAL;
 
 	return count;
 }
diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index fe5567655662..f4f3f0853c6e 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -23,7 +23,7 @@
 #define _H_CIFS_DEBUG
 
 void cifs_dump_mem(char *label, void *data, int length);
-void cifs_dump_detail(void *);
+void cifs_dump_detail(void *buf, struct TCP_Server_Info *ptcp_info);
 void cifs_dump_mids(struct TCP_Server_Info *);
 extern bool traceSMB;		/* flag which enables the function below */
 void dump_smb(void *, int);
@@ -54,7 +54,7 @@ do {								\
 		pr_debug_ ## ratefunc("%s: "			\
 				fmt, __FILE__, ##__VA_ARGS__);	\
 	} else if ((type) & VFS) {				\
-		pr_err_ ## ratefunc("CuIFS VFS: "		\
+		pr_err_ ## ratefunc("CIFS VFS: "		\
 				 fmt, ##__VA_ARGS__);		\
 	} else if ((type) & NOISY && (NOISY != 0)) {		\
 		pr_debug_ ## ratefunc(fmt, ##__VA_ARGS__);	\
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index 350fa55a1bf7..9731d0d891e7 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -50,6 +50,7 @@
 					      * root mountable
 					      */
 #define CIFS_MOUNT_UID_FROM_ACL 0x2000000 /* try to get UID via special SID */
+#define CIFS_MOUNT_NO_HANDLE_CACHE 0x4000000 /* disable caching dir handles */
 
 struct cifs_sb_info {
 	struct rb_root tlink_tree;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index f715609b13f3..eb7b6573f322 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -58,13 +58,15 @@ bool traceSMB;
 bool enable_oplocks = true;
 bool linuxExtEnabled = true;
 bool lookupCacheEnabled = true;
+bool disable_legacy_dialects; /* false by default */
 unsigned int global_secflags = CIFSSEC_DEF;
 /* unsigned int ntlmv2_support = 0; */
 unsigned int sign_CIFS_PDUs = 1;
 static const struct super_operations cifs_super_ops;
 unsigned int CIFSMaxBufSize = CIFS_MAX_MSGSIZE;
 module_param(CIFSMaxBufSize, uint, 0444);
-MODULE_PARM_DESC(CIFSMaxBufSize, "Network buffer size (not including header). "
+MODULE_PARM_DESC(CIFSMaxBufSize, "Network buffer size (not including header) "
+				 "for CIFS requests. "
 				 "Default: 16384 Range: 8192 to 130048");
 unsigned int cifs_min_rcv = CIFS_MIN_RCV_POOL;
 module_param(cifs_min_rcv, uint, 0444);
@@ -76,11 +78,21 @@ MODULE_PARM_DESC(cifs_min_small, "Small network buffers in pool. Default: 30 "
 				 "Range: 2 to 256");
 unsigned int cifs_max_pending = CIFS_MAX_REQ;
 module_param(cifs_max_pending, uint, 0444);
-MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server. "
+MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server for "
+				   "CIFS/SMB1 dialect (N/A for SMB3) "
 				   "Default: 32767 Range: 2 to 32767.");
 module_param(enable_oplocks, bool, 0644);
 MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1");
 
+module_param(disable_legacy_dialects, bool, 0644);
+MODULE_PARM_DESC(disable_legacy_dialects, "To improve security it may be "
+				  "helpful to restrict the ability to "
+				  "override the default dialects (SMB2.1, "
+				  "SMB3 and SMB3.02) on mount with old "
+				  "dialects (CIFS/SMB1 and SMB2) since "
+				  "vers=1.0 (CIFS/SMB1) and vers=2.0 are weaker"
+				  " and less secure. Default: n/N/0");
+
 extern mempool_t *cifs_sm_req_poolp;
 extern mempool_t *cifs_req_poolp;
 extern mempool_t *cifs_mid_poolp;
@@ -469,10 +481,20 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",persistenthandles");
 	else if (tcon->use_resilient)
 		seq_puts(s, ",resilienthandles");
+
+#ifdef CONFIG_CIFS_SMB311
+	if (tcon->posix_extensions)
+		seq_puts(s, ",posix");
+	else if (tcon->unix_ext)
+		seq_puts(s, ",unix");
+	else
+		seq_puts(s, ",nounix");
+#else
 	if (tcon->unix_ext)
 		seq_puts(s, ",unix");
 	else
 		seq_puts(s, ",nounix");
+#endif /* SMB311 */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
 		seq_puts(s, ",posixpaths");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
@@ -495,6 +517,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",sfu");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
 		seq_puts(s, ",nobrl");
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_HANDLE_CACHE)
+		seq_puts(s, ",nohandlecache");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
 		seq_puts(s, ",cifsacl");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
@@ -897,6 +921,17 @@ struct file_system_type cifs_fs_type = {
 	/*  .fs_flags */
 };
 MODULE_ALIAS_FS("cifs");
+
+static struct file_system_type smb3_fs_type = {
+	.owner = THIS_MODULE,
+	.name = "smb3",
+	.mount = cifs_do_mount,
+	.kill_sb = cifs_kill_sb,
+	/*  .fs_flags */
+};
+MODULE_ALIAS_FS("smb3");
+MODULE_ALIAS("smb3");
+
 const struct inode_operations cifs_dir_inode_ops = {
 	.create = cifs_create,
 	.atomic_open = cifs_atomic_open,
@@ -1047,6 +1082,18 @@ out:
 	return rc;
 }
 
+/*
+ * Directory operations under CIFS/SMB2/SMB3 are synchronous, so fsync()
+ * is a dummy operation.
+ */
+static int cifs_dir_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	cifs_dbg(FYI, "Sync directory - name: %pD datasync: 0x%x\n",
+		 file, datasync);
+
+	return 0;
+}
+
 static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
 				struct file *dst_file, loff_t destoff,
 				size_t len, unsigned int flags)
@@ -1181,6 +1228,7 @@ const struct file_operations cifs_dir_ops = {
 	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.llseek = generic_file_llseek,
+	.fsync = cifs_dir_fsync,
 };
 
 static void
@@ -1422,6 +1470,12 @@ init_cifs(void)
 	if (rc)
 		goto out_init_cifs_idmap;
 
+	rc = register_filesystem(&smb3_fs_type);
+	if (rc) {
+		unregister_filesystem(&cifs_fs_type);
+		goto out_init_cifs_idmap;
+	}
+
 	return 0;
 
 out_init_cifs_idmap:
@@ -1452,8 +1506,9 @@ out_clean_proc:
 static void __exit
 exit_cifs(void)
 {
-	cifs_dbg(NOISY, "exit_cifs\n");
+	cifs_dbg(NOISY, "exit_smb3\n");
 	unregister_filesystem(&cifs_fs_type);
+	unregister_filesystem(&smb3_fs_type);
 	cifs_dfs_release_automount_timer();
 #ifdef CONFIG_CIFS_ACL
 	exit_cifs_idmap();
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 013ba2aed8d9..5f0231803431 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -149,5 +149,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "2.11"
+#define CIFS_VERSION   "2.12"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index cb950a5fa078..08d1cdd96701 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -176,6 +176,7 @@ struct smb_rqst {
 	struct kvec	*rq_iov;	/* array of kvecs */
 	unsigned int	rq_nvec;	/* number of kvecs in array */
 	struct page	**rq_pages;	/* pointer to array of page ptrs */
+	unsigned int	rq_offset;	/* the offset to the 1st page */
 	unsigned int	rq_npages;	/* number pages in array */
 	unsigned int	rq_pagesz;	/* page size to use */
 	unsigned int	rq_tailsz;	/* length of last page */
@@ -244,7 +245,7 @@ struct smb_version_operations {
 	int (*map_error)(char *, bool);
 	/* find mid corresponding to the response message */
 	struct mid_q_entry * (*find_mid)(struct TCP_Server_Info *, char *);
-	void (*dump_detail)(void *);
+	void (*dump_detail)(void *buf, struct TCP_Server_Info *ptcp_info);
 	void (*clear_stats)(struct cifs_tcon *);
 	void (*print_stats)(struct seq_file *m, struct cifs_tcon *);
 	void (*dump_share_caps)(struct seq_file *, struct cifs_tcon *);
@@ -372,7 +373,7 @@ struct smb_version_operations {
 	int (*close_dir)(const unsigned int, struct cifs_tcon *,
 			 struct cifs_fid *);
 	/* calculate a size of SMB message */
-	unsigned int (*calc_smb_size)(void *);
+	unsigned int (*calc_smb_size)(void *buf, struct TCP_Server_Info *ptcpi);
 	/* check for STATUS_PENDING and process it in a positive case */
 	bool (*is_status_pending)(char *, struct TCP_Server_Info *, int);
 	/* check for STATUS_NETWORK_SESSION_EXPIRED */
@@ -417,7 +418,7 @@ struct smb_version_operations {
 	/* create lease context buffer for CREATE request */
 	char * (*create_lease_buf)(u8 *, u8);
 	/* parse lease context buffer and return oplock/epoch info */
-	__u8 (*parse_lease_buf)(void *, unsigned int *);
+	__u8 (*parse_lease_buf)(void *buf, unsigned int *epoch, char *lkey);
 	ssize_t (*copychunk_range)(const unsigned int,
 			struct cifsFileInfo *src_file,
 			struct cifsFileInfo *target_file,
@@ -457,7 +458,7 @@ struct smb_version_operations {
 				 struct mid_q_entry **);
 	enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
 			    enum securityEnum);
-
+	int (*next_header)(char *);
 };
 
 struct smb_version_values {
@@ -521,10 +522,12 @@ struct smb_vol {
 	bool sfu_remap:1;  /* remap seven reserved chars ala SFU */
 	bool posix_paths:1; /* unset to not ask for posix pathnames. */
 	bool no_linux_ext:1;
+	bool linux_ext:1;
 	bool sfu_emul:1;
 	bool nullauth:1;   /* attempt to authenticate with null user */
 	bool nocase:1;     /* request case insensitive filenames */
 	bool nobrl:1;      /* disable sending byte range locks to srv */
+	bool nohandlecache:1; /* disable caching dir handles if srvr probs */
 	bool mand_lock:1;  /* send mandatory not posix byte range lock reqs */
 	bool seal:1;       /* request transport encryption on share */
 	bool nodfs:1;      /* Do not request DFS, even if available */
@@ -630,7 +633,7 @@ struct TCP_Server_Info {
 	bool oplocks:1; /* enable oplocks */
 	unsigned int maxReq;	/* Clients should submit no more */
 	/* than maxReq distinct unanswered SMBs to the server when using  */
-	/* multiplexed reads or writes */
+	/* multiplexed reads or writes (for SMB1/CIFS only, not SMB2/SMB3) */
 	unsigned int maxBuf;	/* maxBuf specifies the maximum */
 	/* message size the server can send or receive for non-raw SMBs */
 	/* maxBuf is returned by SMB NegotiateProtocol so maxBuf is only 0 */
@@ -681,6 +684,7 @@ struct TCP_Server_Info {
 	__le16	cipher_type;
 	 /* save initital negprot hash */
 	__u8	preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
+	bool	posix_ext_supported;
 #endif /* 3.1.1 */
 	struct delayed_work reconnect; /* reconnect workqueue job */
 	struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
@@ -953,9 +957,13 @@ struct cifs_tcon {
 	bool print:1; /* set if connection to printer share */
 	bool retry:1;
 	bool nocase:1;
+	bool nohandlecache:1; /* if strange server resource prob can turn off */
 	bool seal:1;      /* transport encryption for this mounted share */
 	bool unix_ext:1;  /* if false disable Linux extensions to CIFS protocol
 				for this mount even if server would support */
+#ifdef CONFIG_CIFS_SMB311
+	bool posix_extensions; /* if true SMB3.11 posix extensions enabled */
+#endif /* CIFS_311 */
 	bool local_lease:1; /* check leases (only) on local system not remote */
 	bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */
 	bool broken_sparse_sup; /* if server or share does not support sparse */
@@ -979,6 +987,9 @@ struct cifs_tcon {
 	struct fscache_cookie *fscache;	/* cookie for share */
 #endif
 	struct list_head pending_opens;	/* list of incomplete opens */
+	bool valid_root_fid:1;	/* Do we have a useable root fid */
+	struct mutex prfid_mutex; /* prevents reopen race after dead ses*/
+	struct cifs_fid *prfid;	/* handle to the directory at top of share */
 	/* BB add field for back pointer to sb struct(s)? */
 };
 
@@ -1071,6 +1082,7 @@ struct cifs_open_parms {
 	int create_options;
 	const char *path;
 	struct cifs_fid *fid;
+	umode_t mode;
 	bool reconnect:1;
 };
 
@@ -1169,10 +1181,11 @@ struct cifs_readdata {
 	struct smbd_mr			*mr;
 #endif
 	unsigned int			pagesz;
+	unsigned int			page_offset;
 	unsigned int			tailsz;
 	unsigned int			credits;
 	unsigned int			nr_pages;
-	struct page			*pages[];
+	struct page			**pages;
 };
 
 struct cifs_writedata;
@@ -1194,10 +1207,11 @@ struct cifs_writedata {
 	struct smbd_mr			*mr;
 #endif
 	unsigned int			pagesz;
+	unsigned int			page_offset;
 	unsigned int			tailsz;
 	unsigned int			credits;
 	unsigned int			nr_pages;
-	struct page			*pages[];
+	struct page			**pages;
 };
 
 /*
@@ -1692,16 +1706,17 @@ GLOBAL_EXTERN atomic_t smBufAllocCount;
 GLOBAL_EXTERN atomic_t midCount;
 
 /* Misc globals */
-GLOBAL_EXTERN bool enable_oplocks; /* enable or disable oplocks */
-GLOBAL_EXTERN bool lookupCacheEnabled;
-GLOBAL_EXTERN unsigned int global_secflags;	/* if on, session setup sent
+extern bool enable_oplocks; /* enable or disable oplocks */
+extern bool lookupCacheEnabled;
+extern unsigned int global_secflags;	/* if on, session setup sent
 				with more secure ntlmssp2 challenge/resp */
-GLOBAL_EXTERN unsigned int sign_CIFS_PDUs;  /* enable smb packet signing */
-GLOBAL_EXTERN bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
-GLOBAL_EXTERN unsigned int CIFSMaxBufSize;  /* max size not including hdr */
-GLOBAL_EXTERN unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
-GLOBAL_EXTERN unsigned int cifs_min_small;  /* min size of small buf pool */
-GLOBAL_EXTERN unsigned int cifs_max_pending; /* MAX requests at once to server*/
+extern unsigned int sign_CIFS_PDUs;  /* enable smb packet signing */
+extern bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
+extern unsigned int CIFSMaxBufSize;  /* max size not including hdr */
+extern unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
+extern unsigned int cifs_min_small;  /* min size of small buf pool */
+extern unsigned int cifs_max_pending; /* MAX requests at once to server*/
+extern bool disable_legacy_dialects;  /* forbid vers=1.0 and vers=2.0 mounts */
 
 #ifdef CONFIG_CIFS_ACL
 GLOBAL_EXTERN struct rb_root uidtree;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 365a414a75e9..7933c5f9c076 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -21,6 +21,7 @@
 #ifndef _CIFSPROTO_H
 #define _CIFSPROTO_H
 #include <linux/nls.h>
+#include "trace.h"
 
 struct statfs;
 struct smb_vol;
@@ -47,6 +48,7 @@ extern void _free_xid(unsigned int);
 	cifs_dbg(FYI, "CIFS VFS: in %s as Xid: %u with uid: %d\n",	\
 		 __func__, __xid,					\
 		 from_kuid(&init_user_ns, current_fsuid()));		\
+	trace_smb3_enter(__xid, __func__);			\
 	__xid;							\
 })
 
@@ -54,7 +56,11 @@ extern void _free_xid(unsigned int);
 do {								\
 	_free_xid(curr_xid);					\
 	cifs_dbg(FYI, "CIFS VFS: leaving %s (xid = %u) rc = %d\n",	\
-		 __func__, curr_xid, (int)rc);				\
+		 __func__, curr_xid, (int)rc);			\
+	if (rc)							\
+		trace_smb3_exit_err(curr_xid, __func__, (int)rc);	\
+	else							\
+		trace_smb3_exit_done(curr_xid, __func__);	\
 } while (0)
 extern int init_cifs_idmap(void);
 extern void exit_cifs_idmap(void);
@@ -124,7 +130,7 @@ extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
 			    unsigned int bytes_written);
 extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, bool);
 extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
-extern unsigned int smbCalcSize(void *buf);
+extern unsigned int smbCalcSize(void *buf, struct TCP_Server_Info *server);
 extern int decode_negTokenInit(unsigned char *security_blob, int length,
 			struct TCP_Server_Info *server);
 extern int cifs_convert_address(struct sockaddr *dst, const char *src, int len);
@@ -197,7 +203,9 @@ extern void dequeue_mid(struct mid_q_entry *mid, bool malformed);
 extern int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 			         unsigned int to_read);
 extern int cifs_read_page_from_socket(struct TCP_Server_Info *server,
-				      struct page *page, unsigned int to_read);
+					struct page *page,
+					unsigned int page_offset,
+					unsigned int to_read);
 extern int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 			       struct cifs_sb_info *cifs_sb);
 extern int cifs_match_super(struct super_block *, void *);
@@ -525,6 +533,8 @@ int cifs_async_writev(struct cifs_writedata *wdata,
 void cifs_writev_complete(struct work_struct *work);
 struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages,
 						work_func_t complete);
+struct cifs_writedata *cifs_writedata_direct_alloc(struct page **pages,
+						work_func_t complete);
 void cifs_writedata_release(struct kref *refcount);
 int cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 			  struct cifs_sb_info *cifs_sb,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 6d3e40d7029c..5aca336642c0 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -106,6 +106,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
 		open_file->oplock_break_cancelled = true;
 	}
 	spin_unlock(&tcon->open_file_lock);
+
+	mutex_lock(&tcon->prfid_mutex);
+	tcon->valid_root_fid = false;
+	memset(tcon->prfid, 0, sizeof(struct cifs_fid));
+	mutex_unlock(&tcon->prfid_mutex);
+
 	/*
 	 * BB Add call to invalidate_inodes(sb) for all superblocks mounted
 	 * to this tcon.
@@ -455,6 +461,9 @@ cifs_enable_signing(struct TCP_Server_Info *server, bool mnt_sign_required)
 		server->sign = true;
 	}
 
+	if (cifs_rdma_enabled(server) && server->sign)
+		cifs_dbg(VFS, "Signing is enabled, and RDMA read/write will be disabled");
+
 	return 0;
 }
 
@@ -1943,6 +1952,7 @@ cifs_writedata_release(struct kref *refcount)
 	if (wdata->cfile)
 		cifsFileInfo_put(wdata->cfile);
 
+	kvfree(wdata->pages);
 	kfree(wdata);
 }
 
@@ -2066,12 +2076,22 @@ cifs_writev_complete(struct work_struct *work)
 struct cifs_writedata *
 cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete)
 {
+	struct page **pages =
+		kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+	if (pages)
+		return cifs_writedata_direct_alloc(pages, complete);
+
+	return NULL;
+}
+
+struct cifs_writedata *
+cifs_writedata_direct_alloc(struct page **pages, work_func_t complete)
+{
 	struct cifs_writedata *wdata;
 
-	/* writedata + number of page pointers */
-	wdata = kzalloc(sizeof(*wdata) +
-			sizeof(struct page *) * nr_pages, GFP_NOFS);
+	wdata = kzalloc(sizeof(*wdata), GFP_NOFS);
 	if (wdata != NULL) {
+		wdata->pages = pages;
 		kref_init(&wdata->refcount);
 		INIT_LIST_HEAD(&wdata->list);
 		init_completion(&wdata->done);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index e8830f076a7f..e5a2fe7f0dd4 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -61,6 +61,7 @@
 #define RFC1001_PORT 139
 
 extern mempool_t *cifs_req_poolp;
+extern bool disable_legacy_dialects;
 
 /* FIXME: should these be tunable? */
 #define TLINK_ERROR_EXPIRE	(1 * HZ)
@@ -76,9 +77,10 @@ enum {
 	Opt_mapposix, Opt_nomapposix,
 	Opt_mapchars, Opt_nomapchars, Opt_sfu,
 	Opt_nosfu, Opt_nodfs, Opt_posixpaths,
-	Opt_noposixpaths, Opt_nounix,
+	Opt_noposixpaths, Opt_nounix, Opt_unix,
 	Opt_nocase,
 	Opt_brl, Opt_nobrl,
+	Opt_handlecache, Opt_nohandlecache,
 	Opt_forcemandatorylock, Opt_setuidfromacl, Opt_setuids,
 	Opt_nosetuids, Opt_dynperm, Opt_nodynperm,
 	Opt_nohard, Opt_nosoft,
@@ -144,10 +146,16 @@ static const match_table_t cifs_mount_option_tokens = {
 	{ Opt_noposixpaths, "noposixpaths" },
 	{ Opt_nounix, "nounix" },
 	{ Opt_nounix, "nolinux" },
+	{ Opt_nounix, "noposix" },
+	{ Opt_unix, "unix" },
+	{ Opt_unix, "linux" },
+	{ Opt_unix, "posix" },
 	{ Opt_nocase, "nocase" },
 	{ Opt_nocase, "ignorecase" },
 	{ Opt_brl, "brl" },
 	{ Opt_nobrl, "nobrl" },
+	{ Opt_handlecache, "handlecache" },
+	{ Opt_nohandlecache, "nohandlecache" },
 	{ Opt_nobrl, "nolock" },
 	{ Opt_forcemandatorylock, "forcemandatorylock" },
 	{ Opt_forcemandatorylock, "forcemand" },
@@ -591,10 +599,11 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 
 int
 cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page,
-		      unsigned int to_read)
+	unsigned int page_offset, unsigned int to_read)
 {
 	struct msghdr smb_msg;
-	struct bio_vec bv = {.bv_page = page, .bv_len = to_read};
+	struct bio_vec bv = {
+		.bv_page = page, .bv_len = to_read, .bv_offset = page_offset};
 	iov_iter_bvec(&smb_msg.msg_iter, READ | ITER_BVEC, &bv, 1, to_read);
 	return cifs_readv_from_socket(server, &smb_msg);
 }
@@ -848,6 +857,7 @@ cifs_demultiplex_thread(void *p)
 	int length;
 	struct TCP_Server_Info *server = p;
 	unsigned int pdu_length;
+	unsigned int next_offset;
 	char *buf = NULL;
 	struct task_struct *task_to_wake = NULL;
 	struct mid_q_entry *mid_entry;
@@ -874,24 +884,29 @@ cifs_demultiplex_thread(void *p)
 		length = cifs_read_from_socket(server, buf, pdu_length);
 		if (length < 0)
 			continue;
-		server->total_read = length;
+
+		if (server->vals->header_preamble_size == 0)
+			server->total_read = 0;
+		else
+			server->total_read = length;
 
 		/*
 		 * The right amount was read from socket - 4 bytes,
 		 * so we can now interpret the length field.
 		 */
 		pdu_length = get_rfc1002_length(buf);
-		server->pdu_size = pdu_length;
 
 		cifs_dbg(FYI, "RFC1002 header 0x%x\n", pdu_length);
 		if (!is_smb_response(server, buf[0]))
 			continue;
+next_pdu:
+		server->pdu_size = pdu_length;
 
 		/* make sure we have enough to get to the MID */
-		if (pdu_length < HEADER_SIZE(server) - 1 -
+		if (server->pdu_size < HEADER_SIZE(server) - 1 -
 		    server->vals->header_preamble_size) {
 			cifs_dbg(VFS, "SMB response too short (%u bytes)\n",
-				 pdu_length);
+				 server->pdu_size);
 			cifs_reconnect(server);
 			wake_up(&server->response_q);
 			continue;
@@ -906,6 +921,12 @@ cifs_demultiplex_thread(void *p)
 			continue;
 		server->total_read += length;
 
+		if (server->ops->next_header) {
+			next_offset = server->ops->next_header(buf);
+			if (next_offset)
+				server->pdu_size = next_offset;
+		}
+
 		if (server->ops->is_transform_hdr &&
 		    server->ops->receive_transform &&
 		    server->ops->is_transform_hdr(buf)) {
@@ -948,10 +969,18 @@ cifs_demultiplex_thread(void *p)
 				      HEADER_SIZE(server));
 #ifdef CONFIG_CIFS_DEBUG2
 			if (server->ops->dump_detail)
-				server->ops->dump_detail(buf);
+				server->ops->dump_detail(buf, server);
 			cifs_dump_mids(server);
 #endif /* CIFS_DEBUG2 */
-
+		}
+		if (pdu_length > server->pdu_size) {
+			if (!allocate_buffers(server))
+				continue;
+			pdu_length -= server->pdu_size;
+			server->total_read = 0;
+			server->large_buf = false;
+			buf = server->smallbuf;
+			goto next_pdu;
 		}
 	} /* end while !EXITING */
 
@@ -1143,10 +1172,18 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol)
 
 	switch (match_token(value, cifs_smb_version_tokens, args)) {
 	case Smb_1:
+		if (disable_legacy_dialects) {
+			cifs_dbg(VFS, "mount with legacy dialect disabled\n");
+			return 1;
+		}
 		vol->ops = &smb1_operations;
 		vol->vals = &smb1_values;
 		break;
 	case Smb_20:
+		if (disable_legacy_dialects) {
+			cifs_dbg(VFS, "mount with legacy dialect disabled\n");
+			return 1;
+		}
 		vol->ops = &smb20_operations;
 		vol->vals = &smb20_values;
 		break;
@@ -1426,8 +1463,17 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			vol->posix_paths = 0;
 			break;
 		case Opt_nounix:
+			if (vol->linux_ext)
+				cifs_dbg(VFS,
+					"conflicting unix mount options\n");
 			vol->no_linux_ext = 1;
 			break;
+		case Opt_unix:
+			if (vol->no_linux_ext)
+				cifs_dbg(VFS,
+					"conflicting unix mount options\n");
+			vol->linux_ext = 1;
+			break;
 		case Opt_nocase:
 			vol->nocase = 1;
 			break;
@@ -1445,6 +1491,12 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 				(S_IALLUGO & ~(S_ISUID | S_IXGRP)))
 				vol->file_mode = S_IALLUGO;
 			break;
+		case Opt_nohandlecache:
+			vol->nohandlecache = 1;
+			break;
+		case Opt_handlecache:
+			vol->nohandlecache = 0;
+			break;
 		case Opt_forcemandatorylock:
 			vol->mand_lock = 1;
 			break;
@@ -1977,14 +2029,6 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 		goto cifs_parse_mount_err;
 	}
 
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	if (vol->rdma && vol->sign) {
-		cifs_dbg(VFS, "Currently SMB direct doesn't support signing."
-			" This is being fixed\n");
-		goto cifs_parse_mount_err;
-	}
-#endif
-
 #ifndef CONFIG_KEYS
 	/* Muliuser mounts require CONFIG_KEYS support */
 	if (vol->multiuser) {
@@ -2959,6 +3003,29 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		}
 	}
 
+	if (volume_info->seal) {
+		if (ses->server->vals->protocol_id == 0) {
+			cifs_dbg(VFS,
+				 "SMB3 or later required for encryption\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+		} else if (tcon->ses->server->capabilities &
+					SMB2_GLOBAL_CAP_ENCRYPTION)
+			tcon->seal = true;
+		else {
+			cifs_dbg(VFS, "Encryption is not supported on share\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+		}
+	}
+
+#ifdef CONFIG_CIFS_SMB311
+	if ((volume_info->linux_ext) && (ses->server->posix_ext_supported)) {
+		if (ses->server->vals->protocol_id == SMB311_PROT_ID)
+			tcon->posix_extensions = true;
+	}
+#endif /* 311 */
+
 	/*
 	 * BB Do we need to wrap session_mutex around this TCon call and Unix
 	 * SetFS as we do on SessSetup and reconnect?
@@ -3007,22 +3074,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		tcon->use_resilient = true;
 	}
 
-	if (volume_info->seal) {
-		if (ses->server->vals->protocol_id == 0) {
-			cifs_dbg(VFS,
-				 "SMB3 or later required for encryption\n");
-			rc = -EOPNOTSUPP;
-			goto out_fail;
-		} else if (tcon->ses->server->capabilities &
-					SMB2_GLOBAL_CAP_ENCRYPTION)
-			tcon->seal = true;
-		else {
-			cifs_dbg(VFS, "Encryption is not supported on share\n");
-			rc = -EOPNOTSUPP;
-			goto out_fail;
-		}
-	}
-
 	/*
 	 * We can have only one retry value for a connection to a share so for
 	 * resources mounted more than once to the same server share the last
@@ -3030,6 +3081,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	 */
 	tcon->retry = volume_info->retry;
 	tcon->nocase = volume_info->nocase;
+	tcon->nohandlecache = volume_info->nohandlecache;
 	tcon->local_lease = volume_info->local_lease;
 	INIT_LIST_HEAD(&tcon->pending_opens);
 
@@ -3588,6 +3640,8 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UNX_EMUL;
 	if (pvolume_info->nobrl)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_BRL;
+	if (pvolume_info->nohandlecache)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_HANDLE_CACHE;
 	if (pvolume_info->nostrictsync)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOSSYNC;
 	if (pvolume_info->mand_lock)
@@ -3930,6 +3984,12 @@ try_mount_again:
 		goto remote_path_check;
 	}
 
+#ifdef CONFIG_CIFS_SMB311
+	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
+	if (tcon->posix_extensions)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
+#endif /* SMB3.11 */
+
 	/* tell server which Unix caps we support */
 	if (cap_unix(tcon->ses)) {
 		/* reset of caps checks mount to see if unix extensions
@@ -4361,6 +4421,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 	vol_info->UNC = master_tcon->treeName;
 	vol_info->retry = master_tcon->retry;
 	vol_info->nocase = master_tcon->nocase;
+	vol_info->nohandlecache = master_tcon->nohandlecache;
 	vol_info->local_lease = master_tcon->local_lease;
 	vol_info->no_linux_ext = !master_tcon->unix_ext;
 	vol_info->sectype = master_tcon->ses->sectype;
@@ -4390,8 +4451,14 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 		goto out;
 	}
 
+#ifdef CONFIG_CIFS_SMB311
+	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
+	if (tcon->posix_extensions)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
+#endif /* SMB3.11 */
 	if (cap_unix(ses))
 		reset_cifs_unix_caps(0, tcon, NULL, vol_info);
+
 out:
 	kfree(vol_info->username);
 	kzfree(vol_info->password);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 81ba6e0d88d8..ddae52bd1993 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -369,7 +369,7 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
 	oparms.path = full_path;
 	oparms.fid = fid;
 	oparms.reconnect = false;
-
+	oparms.mode = mode;
 	rc = server->ops->open(xid, &oparms, oplock, buf);
 	if (rc) {
 		cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc);
@@ -684,6 +684,9 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
 		goto mknod_out;
 	}
 
+	if (!S_ISCHR(mode) && !S_ISBLK(mode))
+		goto mknod_out;
+
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
 		goto mknod_out;
 
@@ -692,10 +695,8 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
 
 	buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
 	if (buf == NULL) {
-		kfree(full_path);
 		rc = -ENOMEM;
-		free_xid(xid);
-		return rc;
+		goto mknod_out;
 	}
 
 	if (backup_cred(cifs_sb))
@@ -742,7 +743,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
 		pdev->minor = cpu_to_le64(MINOR(device_number));
 		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
 							&bytes_written, iov, 1);
-	} /* else if (S_ISFIFO) */
+	}
 	tcon->ses->server->ops->close(xid, tcon, &fid);
 	d_drop(direntry);
 
@@ -779,21 +780,25 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink)) {
 		free_xid(xid);
-		return (struct dentry *)tlink;
+		return ERR_CAST(tlink);
 	}
 	pTcon = tlink_tcon(tlink);
 
 	rc = check_name(direntry, pTcon);
-	if (rc)
-		goto lookup_out;
+	if (unlikely(rc)) {
+		cifs_put_tlink(tlink);
+		free_xid(xid);
+		return ERR_PTR(rc);
+	}
 
 	/* can not grab the rename sem here since it would
 	deadlock in the cases (beginning of sys_rename itself)
 	in which we already have the sb rename sem */
 	full_path = build_path_from_dentry(direntry);
 	if (full_path == NULL) {
-		rc = -ENOMEM;
-		goto lookup_out;
+		cifs_put_tlink(tlink);
+		free_xid(xid);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	if (d_really_is_positive(direntry)) {
@@ -812,29 +817,25 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 				parent_dir_inode->i_sb, xid, NULL);
 	}
 
-	if ((rc == 0) && (newInode != NULL)) {
-		d_add(direntry, newInode);
+	if (rc == 0) {
 		/* since paths are not looked up by component - the parent
 		   directories are presumed to be good here */
 		renew_parental_timestamps(direntry);
-
 	} else if (rc == -ENOENT) {
-		rc = 0;
 		cifs_set_time(direntry, jiffies);
-		d_add(direntry, NULL);
-	/*	if it was once a directory (but how can we tell?) we could do
-		shrink_dcache_parent(direntry); */
-	} else if (rc != -EACCES) {
-		cifs_dbg(FYI, "Unexpected lookup error %d\n", rc);
-		/* We special case check for Access Denied - since that
-		is a common return code */
+		newInode = NULL;
+	} else {
+		if (rc != -EACCES) {
+			cifs_dbg(FYI, "Unexpected lookup error %d\n", rc);
+			/* We special case check for Access Denied - since that
+			is a common return code */
+		}
+		newInode = ERR_PTR(rc);
 	}
-
-lookup_out:
 	kfree(full_path);
 	cifs_put_tlink(tlink);
 	free_xid(xid);
-	return ERR_PTR(rc);
+	return d_splice_alias(newInode, direntry);
 }
 
 static int
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 4bcd4e838b47..87eece6fbd48 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2880,13 +2880,13 @@ out:
 }
 
 static struct cifs_readdata *
-cifs_readdata_alloc(unsigned int nr_pages, work_func_t complete)
+cifs_readdata_direct_alloc(struct page **pages, work_func_t complete)
 {
 	struct cifs_readdata *rdata;
 
-	rdata = kzalloc(sizeof(*rdata) + (sizeof(struct page *) * nr_pages),
-			GFP_KERNEL);
+	rdata = kzalloc(sizeof(*rdata), GFP_KERNEL);
 	if (rdata != NULL) {
+		rdata->pages = pages;
 		kref_init(&rdata->refcount);
 		INIT_LIST_HEAD(&rdata->list);
 		init_completion(&rdata->done);
@@ -2896,6 +2896,22 @@ cifs_readdata_alloc(unsigned int nr_pages, work_func_t complete)
 	return rdata;
 }
 
+static struct cifs_readdata *
+cifs_readdata_alloc(unsigned int nr_pages, work_func_t complete)
+{
+	struct page **pages =
+		kzalloc(sizeof(struct page *) * nr_pages, GFP_KERNEL);
+	struct cifs_readdata *ret = NULL;
+
+	if (pages) {
+		ret = cifs_readdata_direct_alloc(pages, complete);
+		if (!ret)
+			kfree(pages);
+	}
+
+	return ret;
+}
+
 void
 cifs_readdata_release(struct kref *refcount)
 {
@@ -2910,6 +2926,7 @@ cifs_readdata_release(struct kref *refcount)
 	if (rdata->cfile)
 		cifsFileInfo_put(rdata->cfile);
 
+	kvfree(rdata->pages);
 	kfree(rdata);
 }
 
@@ -3009,12 +3026,20 @@ uncached_fill_pages(struct TCP_Server_Info *server,
 	int result = 0;
 	unsigned int i;
 	unsigned int nr_pages = rdata->nr_pages;
+	unsigned int page_offset = rdata->page_offset;
 
 	rdata->got_bytes = 0;
 	rdata->tailsz = PAGE_SIZE;
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page = rdata->pages[i];
 		size_t n;
+		unsigned int segment_size = rdata->pagesz;
+
+		if (i == 0)
+			segment_size -= page_offset;
+		else
+			page_offset = 0;
+
 
 		if (len <= 0) {
 			/* no need to hold page hostage */
@@ -3023,24 +3048,25 @@ uncached_fill_pages(struct TCP_Server_Info *server,
 			put_page(page);
 			continue;
 		}
+
 		n = len;
-		if (len >= PAGE_SIZE) {
+		if (len >= segment_size)
 			/* enough data to fill the page */
-			n = PAGE_SIZE;
-			len -= n;
-		} else {
-			zero_user(page, len, PAGE_SIZE - len);
+			n = segment_size;
+		else
 			rdata->tailsz = len;
-			len = 0;
-		}
+		len -= n;
+
 		if (iter)
-			result = copy_page_from_iter(page, 0, n, iter);
+			result = copy_page_from_iter(
+					page, page_offset, n, iter);
 #ifdef CONFIG_CIFS_SMB_DIRECT
 		else if (rdata->mr)
 			result = n;
 #endif
 		else
-			result = cifs_read_page_from_socket(server, page, n);
+			result = cifs_read_page_from_socket(
+					server, page, page_offset, n);
 		if (result < 0)
 			break;
 
@@ -3113,6 +3139,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		rdata->bytes = cur_len;
 		rdata->pid = pid;
 		rdata->pagesz = PAGE_SIZE;
+		rdata->tailsz = PAGE_SIZE;
 		rdata->read_into_pages = cifs_uncached_read_into_pages;
 		rdata->copy_into_pages = cifs_uncached_copy_into_pages;
 		rdata->credits = credits;
@@ -3462,7 +3489,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
  * If the page is mmap'ed into a process' page tables, then we need to make
  * sure that it doesn't change while being written back.
  */
-static int
+static vm_fault_t
 cifs_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
@@ -3557,6 +3584,7 @@ readpages_fill_pages(struct TCP_Server_Info *server,
 	u64 eof;
 	pgoff_t eof_index;
 	unsigned int nr_pages = rdata->nr_pages;
+	unsigned int page_offset = rdata->page_offset;
 
 	/* determine the eof that the server (probably) has */
 	eof = CIFS_I(rdata->mapping->host)->server_eof;
@@ -3567,13 +3595,21 @@ readpages_fill_pages(struct TCP_Server_Info *server,
 	rdata->tailsz = PAGE_SIZE;
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page = rdata->pages[i];
-		size_t n = PAGE_SIZE;
+		unsigned int to_read = rdata->pagesz;
+		size_t n;
+
+		if (i == 0)
+			to_read -= page_offset;
+		else
+			page_offset = 0;
+
+		n = to_read;
 
-		if (len >= PAGE_SIZE) {
-			len -= PAGE_SIZE;
+		if (len >= to_read) {
+			len -= to_read;
 		} else if (len > 0) {
 			/* enough for partial page, fill and zero the rest */
-			zero_user(page, len, PAGE_SIZE - len);
+			zero_user(page, len + page_offset, to_read - len);
 			n = rdata->tailsz = len;
 			len = 0;
 		} else if (page->index > eof_index) {
@@ -3605,13 +3641,15 @@ readpages_fill_pages(struct TCP_Server_Info *server,
 		}
 
 		if (iter)
-			result = copy_page_from_iter(page, 0, n, iter);
+			result = copy_page_from_iter(
+					page, page_offset, n, iter);
 #ifdef CONFIG_CIFS_SMB_DIRECT
 		else if (rdata->mr)
 			result = n;
 #endif
 		else
-			result = cifs_read_page_from_socket(server, page, n);
+			result = cifs_read_page_from_socket(
+					server, page, page_offset, n);
 		if (result < 0)
 			break;
 
@@ -3790,6 +3828,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		rdata->bytes = bytes;
 		rdata->pid = pid;
 		rdata->pagesz = PAGE_SIZE;
+		rdata->tailsz = PAGE_SIZE;
 		rdata->read_into_pages = cifs_readpages_read_into_pages;
 		rdata->copy_into_pages = cifs_readpages_copy_into_pages;
 		rdata->credits = credits;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 3c371f7f5963..745fd7fe8d0e 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -746,7 +746,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 	cifs_dbg(FYI, "Getting info on %s\n", full_path);
 
 	if ((data == NULL) && (*inode != NULL)) {
-		if (CIFS_CACHE_READ(CIFS_I(*inode))) {
+		if (CIFS_CACHE_READ(CIFS_I(*inode)) &&
+		    CIFS_I(*inode)->time != 0) {
 			cifs_dbg(FYI, "No need to revalidate cached inode sizes\n");
 			goto cgii_exit;
 		}
@@ -1857,15 +1858,15 @@ cifs_inode_needs_reval(struct inode *inode)
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 
+	if (cifs_i->time == 0)
+		return true;
+
 	if (CIFS_CACHE_READ(cifs_i))
 		return false;
 
 	if (!lookupCacheEnabled)
 		return true;
 
-	if (cifs_i->time == 0)
-		return true;
-
 	if (!cifs_sb->actimeo)
 		return true;
 
@@ -2104,10 +2105,14 @@ static int cifs_truncate_page(struct address_space *mapping, loff_t from)
 
 static void cifs_setsize(struct inode *inode, loff_t offset)
 {
+	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
+
 	spin_lock(&inode->i_lock);
 	i_size_write(inode, offset);
 	spin_unlock(&inode->i_lock);
 
+	/* Cached inode must be refreshed on truncate */
+	cifs_i->time = 0;
 	truncate_pagecache(inode, offset);
 }
 
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 460084a8eac5..aba3fc3058da 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -117,6 +117,8 @@ tconInfoAlloc(void)
 		INIT_LIST_HEAD(&ret_buf->openFileList);
 		INIT_LIST_HEAD(&ret_buf->tcon_list);
 		spin_lock_init(&ret_buf->open_file_lock);
+		mutex_init(&ret_buf->prfid_mutex);
+		ret_buf->prfid = kzalloc(sizeof(struct cifs_fid), GFP_KERNEL);
 #ifdef CONFIG_CIFS_STATS
 		spin_lock_init(&ret_buf->stat_lock);
 #endif
@@ -134,6 +136,7 @@ tconInfoFree(struct cifs_tcon *buf_to_free)
 	atomic_dec(&tconInfoAllocCount);
 	kfree(buf_to_free->nativeFileSystem);
 	kzfree(buf_to_free->password);
+	kfree(buf_to_free->prfid);
 	kfree(buf_to_free);
 }
 
@@ -145,7 +148,7 @@ cifs_buf_get(void)
 	 * SMB2 header is bigger than CIFS one - no problems to clean some
 	 * more bytes for CIFS.
 	 */
-	size_t buf_size = sizeof(struct smb2_hdr);
+	size_t buf_size = sizeof(struct smb2_sync_hdr);
 
 	/*
 	 * We could use negotiated size instead of max_msgsize -
@@ -339,7 +342,7 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server)
 	/* otherwise, there is enough to get to the BCC */
 	if (check_smb_hdr(smb))
 		return -EIO;
-	clc_len = smbCalcSize(smb);
+	clc_len = smbCalcSize(smb, server);
 
 	if (4 + rfclen != total_read) {
 		cifs_dbg(VFS, "Length read does not match RFC1001 length %d\n",
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index cc88f4f0325e..d7ad0dfe4e68 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -903,7 +903,7 @@ map_smb_to_linux_error(char *buf, bool logErr)
  * portion, the number of word parameters and the data portion of the message
  */
 unsigned int
-smbCalcSize(void *buf)
+smbCalcSize(void *buf, struct TCP_Server_Info *server)
 {
 	struct smb_hdr *ptr = (struct smb_hdr *)buf;
 	return (sizeof(struct smb_hdr) + (2 * ptr->WordCount) +
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index a27fc8791551..eeab81c9452f 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -650,7 +650,8 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
 		char *cur_ent;
 		char *end_of_smb = cfile->srch_inf.ntwrk_buf_start +
 			server->ops->calc_smb_size(
-					cfile->srch_inf.ntwrk_buf_start);
+					cfile->srch_inf.ntwrk_buf_start,
+					server);
 
 		cur_ent = cfile->srch_inf.srch_entries_start;
 		first_entry_in_buffer = cfile->srch_inf.index_of_last_entry
@@ -831,7 +832,8 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
 	cifs_dbg(FYI, "loop through %d times filling dir for net buf %p\n",
 		 num_to_fill, cifsFile->srch_inf.ntwrk_buf_start);
 	max_len = tcon->ses->server->ops->calc_smb_size(
-			cifsFile->srch_inf.ntwrk_buf_start);
+			cifsFile->srch_inf.ntwrk_buf_start,
+			tcon->ses->server);
 	end_of_smb = cifsFile->srch_inf.ntwrk_buf_start + max_len;
 
 	tmp_buf = kmalloc(UNICODE_NAME_MAX, GFP_KERNEL);
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 401a5d856636..0ffa18094335 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -61,9 +61,4 @@
 /* Maximum buffer size value we can send with 1 credit */
 #define SMB2_MAX_BUFFER_SIZE 65536
 
-static inline struct smb2_sync_hdr *get_sync_hdr(void *buf)
-{
-	return &(((struct smb2_hdr *)buf)->sync_hdr);
-}
-
 #endif	/* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 1238cd3552f9..a6e786e39248 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -44,26 +44,38 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
 		   __u32 create_options, void *data, int command)
 {
 	int rc, tmprc = 0;
-	__le16 *utf16_path;
+	__le16 *utf16_path = NULL;
 	__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
+	bool use_cached_root_handle = false;
 
-	utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
-	if (!utf16_path)
-		return -ENOMEM;
+	if ((strcmp(full_path, "") == 0) && (create_options == 0) &&
+	    (desired_access == FILE_READ_ATTRIBUTES) &&
+	    (create_disposition == FILE_OPEN) &&
+	    (tcon->nohandlecache == false)) {
+		rc = open_shroot(xid, tcon, &fid);
+		if (rc == 0)
+			use_cached_root_handle = true;
+	}
+
+	if (use_cached_root_handle == false) {
+		utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
+		if (!utf16_path)
+			return -ENOMEM;
 
-	oparms.tcon = tcon;
-	oparms.desired_access = desired_access;
-	oparms.disposition = create_disposition;
-	oparms.create_options = create_options;
-	oparms.fid = &fid;
-	oparms.reconnect = false;
+		oparms.tcon = tcon;
+		oparms.desired_access = desired_access;
+		oparms.disposition = create_disposition;
+		oparms.create_options = create_options;
+		oparms.fid = &fid;
+		oparms.reconnect = false;
 
-	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
-	if (rc) {
-		kfree(utf16_path);
-		return rc;
+		rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
+		if (rc) {
+			kfree(utf16_path);
+			return rc;
+		}
 	}
 
 	switch (command) {
@@ -107,7 +119,8 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
 		break;
 	}
 
-	rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	if (use_cached_root_handle == false)
+		rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	if (tmprc)
 		rc = tmprc;
 	kfree(utf16_path);
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 3bfc9c990724..20a2d304c603 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -27,6 +27,7 @@
 #include "smb2proto.h"
 #include "smb2status.h"
 #include "smb2glob.h"
+#include "trace.h"
 
 struct status_to_posix_error {
 	__le32 smb2_status;
@@ -2450,13 +2451,16 @@ smb2_print_status(__le32 status)
 int
 map_smb2_to_linux_error(char *buf, bool log_err)
 {
-	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
 	unsigned int i;
 	int rc = -EIO;
 	__le32 smb2err = shdr->Status;
 
-	if (smb2err == 0)
+	if (smb2err == 0) {
+		trace_smb3_cmd_done(shdr->TreeId, shdr->SessionId,
+			le16_to_cpu(shdr->Command), le64_to_cpu(shdr->MessageId));
 		return 0;
+	}
 
 	/* mask facility */
 	if (log_err && (smb2err != STATUS_MORE_PROCESSING_REQUIRED) &&
@@ -2478,5 +2482,8 @@ map_smb2_to_linux_error(char *buf, bool log_err)
 	cifs_dbg(FYI, "Mapping SMB2 status code 0x%08x to POSIX err %d\n",
 		 __le32_to_cpu(smb2err), rc);
 
+	trace_smb3_cmd_err(shdr->TreeId, shdr->SessionId,
+			le16_to_cpu(shdr->Command),
+			le64_to_cpu(shdr->MessageId), le32_to_cpu(smb2err), rc);
 	return rc;
 }
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 68ea8491c160..cb5728e3d87d 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -94,8 +94,8 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 };
 
 #ifdef CONFIG_CIFS_SMB311
-static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, __u32 non_ctxlen,
-				size_t hdr_preamble_size)
+static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
+			      __u32 non_ctxlen)
 {
 	__u16 neg_count;
 	__u32 nc_offset, size_of_pad_before_neg_ctxts;
@@ -109,12 +109,11 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, __u32 non_ctxlen,
 
 	/* Make sure that negotiate contexts start after gss security blob */
 	nc_offset = le32_to_cpu(pneg_rsp->NegotiateContextOffset);
-	if (nc_offset < non_ctxlen - hdr_preamble_size /* RFC1001 len */) {
+	if (nc_offset < non_ctxlen) {
 		printk_once(KERN_WARNING "invalid negotiate context offset\n");
 		return 0;
 	}
-	size_of_pad_before_neg_ctxts = nc_offset -
-					(non_ctxlen - hdr_preamble_size);
+	size_of_pad_before_neg_ctxts = nc_offset - non_ctxlen;
 
 	/* Verify that at least minimal negotiate contexts fit within frame */
 	if (len < nc_offset + (neg_count * sizeof(struct smb2_neg_context))) {
@@ -131,25 +130,20 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, __u32 non_ctxlen,
 #endif /* CIFS_SMB311 */
 
 int
-smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
+smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
 {
-	struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
-	struct smb2_hdr *hdr = &pdu->hdr;
-	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+	struct smb2_sync_pdu *pdu = (struct smb2_sync_pdu *)shdr;
 	__u64 mid;
-	__u32 len = get_rfc1002_length(buf);
 	__u32 clc_len;  /* calculated length */
 	int command;
-
-	/* BB disable following printk later */
-	cifs_dbg(FYI, "%s length: 0x%x, smb_buf_length: 0x%x\n",
-		 __func__, length, len);
+	int pdu_size = sizeof(struct smb2_sync_pdu);
+	int hdr_size = sizeof(struct smb2_sync_hdr);
 
 	/*
 	 * Add function to do table lookup of StructureSize by command
 	 * ie Validate the wct via smb2_struct_sizes table above
 	 */
-
 	if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
 		struct smb2_transform_hdr *thdr =
 			(struct smb2_transform_hdr *)buf;
@@ -173,8 +167,8 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 	}
 
 	mid = le64_to_cpu(shdr->MessageId);
-	if (length < sizeof(struct smb2_pdu)) {
-		if ((length >= sizeof(struct smb2_hdr))
+	if (len < pdu_size) {
+		if ((len >= hdr_size)
 		    && (shdr->Status != 0)) {
 			pdu->StructureSize2 = 0;
 			/*
@@ -187,8 +181,7 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 		}
 		return 1;
 	}
-	if (len > CIFSMaxBufSize + MAX_SMB2_HDR_SIZE -
-	    srvr->vals->header_preamble_size) {
+	if (len > CIFSMaxBufSize + MAX_SMB2_HDR_SIZE) {
 		cifs_dbg(VFS, "SMB length greater than maximum, mid=%llu\n",
 			 mid);
 		return 1;
@@ -227,44 +220,38 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 		}
 	}
 
-	if (srvr->vals->header_preamble_size + len != length) {
-		cifs_dbg(VFS, "Total length %u RFC1002 length %zu mismatch mid %llu\n",
-			 length, srvr->vals->header_preamble_size + len, mid);
-		return 1;
-	}
-
-	clc_len = smb2_calc_size(hdr);
+	clc_len = smb2_calc_size(buf, srvr);
 
 #ifdef CONFIG_CIFS_SMB311
 	if (shdr->Command == SMB2_NEGOTIATE)
-		clc_len += get_neg_ctxt_len(hdr, len, clc_len,
-					srvr->vals->header_preamble_size);
+		clc_len += get_neg_ctxt_len(shdr, len, clc_len);
 #endif /* SMB311 */
-	if (srvr->vals->header_preamble_size + len != clc_len) {
-		cifs_dbg(FYI, "Calculated size %u length %zu mismatch mid %llu\n",
-			 clc_len, srvr->vals->header_preamble_size + len, mid);
+	if (len != clc_len) {
+		cifs_dbg(FYI, "Calculated size %u length %u mismatch mid %llu\n",
+			 clc_len, len, mid);
 		/* create failed on symlink */
 		if (command == SMB2_CREATE_HE &&
 		    shdr->Status == STATUS_STOPPED_ON_SYMLINK)
 			return 0;
 		/* Windows 7 server returns 24 bytes more */
-		if (clc_len + 24 - srvr->vals->header_preamble_size == len && command == SMB2_OPLOCK_BREAK_HE)
+		if (clc_len + 24 == len && command == SMB2_OPLOCK_BREAK_HE)
 			return 0;
 		/* server can return one byte more due to implied bcc[0] */
-		if (clc_len == srvr->vals->header_preamble_size + len + 1)
+		if (clc_len == len + 1)
 			return 0;
 
 		/*
 		 * MacOS server pads after SMB2.1 write response with 3 bytes
 		 * of junk. Other servers match RFC1001 len to actual
 		 * SMB2/SMB3 frame length (header + smb2 response specific data)
+		 * Some windows servers do too when compounding is used.
 		 * Log the server error (once), but allow it and continue
 		 * since the frame is parseable.
 		 */
-		if (clc_len < srvr->vals->header_preamble_size /* RFC1001 header size */ + len) {
+		if (clc_len < len) {
 			printk_once(KERN_WARNING
-				"SMB2 server sent bad RFC1001 len %d not %zu\n",
-				len, clc_len - srvr->vals->header_preamble_size);
+				"SMB2 server sent bad RFC1001 len %d not %d\n",
+				len, clc_len);
 			return 0;
 		}
 
@@ -305,15 +292,14 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = {
  * area and the offset to it (from the beginning of the smb are also returned.
  */
 char *
-smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
+smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr)
 {
-	struct smb2_sync_hdr *shdr = get_sync_hdr(hdr);
 	*off = 0;
 	*len = 0;
 
 	/* error responses do not have data area */
 	if (shdr->Status && shdr->Status != STATUS_MORE_PROCESSING_REQUIRED &&
-	    (((struct smb2_err_rsp *)hdr)->StructureSize) ==
+	    (((struct smb2_err_rsp *)shdr)->StructureSize) ==
 						SMB2_ERROR_STRUCTURE_SIZE2)
 		return NULL;
 
@@ -325,42 +311,44 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 	switch (shdr->Command) {
 	case SMB2_NEGOTIATE:
 		*off = le16_to_cpu(
-		    ((struct smb2_negotiate_rsp *)hdr)->SecurityBufferOffset);
+		  ((struct smb2_negotiate_rsp *)shdr)->SecurityBufferOffset);
 		*len = le16_to_cpu(
-		    ((struct smb2_negotiate_rsp *)hdr)->SecurityBufferLength);
+		  ((struct smb2_negotiate_rsp *)shdr)->SecurityBufferLength);
 		break;
 	case SMB2_SESSION_SETUP:
 		*off = le16_to_cpu(
-		    ((struct smb2_sess_setup_rsp *)hdr)->SecurityBufferOffset);
+		  ((struct smb2_sess_setup_rsp *)shdr)->SecurityBufferOffset);
 		*len = le16_to_cpu(
-		    ((struct smb2_sess_setup_rsp *)hdr)->SecurityBufferLength);
+		  ((struct smb2_sess_setup_rsp *)shdr)->SecurityBufferLength);
 		break;
 	case SMB2_CREATE:
 		*off = le32_to_cpu(
-		    ((struct smb2_create_rsp *)hdr)->CreateContextsOffset);
+		    ((struct smb2_create_rsp *)shdr)->CreateContextsOffset);
 		*len = le32_to_cpu(
-		    ((struct smb2_create_rsp *)hdr)->CreateContextsLength);
+		    ((struct smb2_create_rsp *)shdr)->CreateContextsLength);
 		break;
 	case SMB2_QUERY_INFO:
 		*off = le16_to_cpu(
-		    ((struct smb2_query_info_rsp *)hdr)->OutputBufferOffset);
+		    ((struct smb2_query_info_rsp *)shdr)->OutputBufferOffset);
 		*len = le32_to_cpu(
-		    ((struct smb2_query_info_rsp *)hdr)->OutputBufferLength);
+		    ((struct smb2_query_info_rsp *)shdr)->OutputBufferLength);
 		break;
 	case SMB2_READ:
-		*off = ((struct smb2_read_rsp *)hdr)->DataOffset;
-		*len = le32_to_cpu(((struct smb2_read_rsp *)hdr)->DataLength);
+		/* TODO: is this a bug ? */
+		*off = ((struct smb2_read_rsp *)shdr)->DataOffset;
+		*len = le32_to_cpu(((struct smb2_read_rsp *)shdr)->DataLength);
 		break;
 	case SMB2_QUERY_DIRECTORY:
 		*off = le16_to_cpu(
-		  ((struct smb2_query_directory_rsp *)hdr)->OutputBufferOffset);
+		  ((struct smb2_query_directory_rsp *)shdr)->OutputBufferOffset);
 		*len = le32_to_cpu(
-		  ((struct smb2_query_directory_rsp *)hdr)->OutputBufferLength);
+		  ((struct smb2_query_directory_rsp *)shdr)->OutputBufferLength);
 		break;
 	case SMB2_IOCTL:
 		*off = le32_to_cpu(
-		  ((struct smb2_ioctl_rsp *)hdr)->OutputOffset);
-		*len = le32_to_cpu(((struct smb2_ioctl_rsp *)hdr)->OutputCount);
+		  ((struct smb2_ioctl_rsp *)shdr)->OutputOffset);
+		*len = le32_to_cpu(
+		  ((struct smb2_ioctl_rsp *)shdr)->OutputCount);
 		break;
 	case SMB2_CHANGE_NOTIFY:
 	default:
@@ -403,15 +391,14 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
  * portion, the number of word parameters and the data portion of the message.
  */
 unsigned int
-smb2_calc_size(void *buf)
+smb2_calc_size(void *buf, struct TCP_Server_Info *srvr)
 {
-	struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
-	struct smb2_hdr *hdr = &pdu->hdr;
-	struct smb2_sync_hdr *shdr = get_sync_hdr(hdr);
+	struct smb2_sync_pdu *pdu = (struct smb2_sync_pdu *)buf;
+	struct smb2_sync_hdr *shdr = &pdu->sync_hdr;
 	int offset; /* the offset from the beginning of SMB to data area */
 	int data_length; /* the length of the variable length data area */
 	/* Structure Size has already been checked to make sure it is 64 */
-	int len = 4 + le16_to_cpu(shdr->StructureSize);
+	int len = le16_to_cpu(shdr->StructureSize);
 
 	/*
 	 * StructureSize2, ie length of fixed parameter area has already
@@ -422,7 +409,7 @@ smb2_calc_size(void *buf)
 	if (has_smb2_data_area[le16_to_cpu(shdr->Command)] == false)
 		goto calc_size_exit;
 
-	smb2_get_data_area_len(&offset, &data_length, hdr);
+	smb2_get_data_area_len(&offset, &data_length, shdr);
 	cifs_dbg(FYI, "SMB2 data length %d offset %d\n", data_length, offset);
 
 	if (data_length > 0) {
@@ -430,15 +417,14 @@ smb2_calc_size(void *buf)
 		 * Check to make sure that data area begins after fixed area,
 		 * Note that last byte of the fixed area is part of data area
 		 * for some commands, typically those with odd StructureSize,
-		 * so we must add one to the calculation (and 4 to account for
-		 * the size of the RFC1001 hdr.
+		 * so we must add one to the calculation.
 		 */
-		if (offset + 4 + 1 < len) {
+		if (offset + 1 < len) {
 			cifs_dbg(VFS, "data area offset %d overlaps SMB2 header %d\n",
-				 offset + 4 + 1, len);
+				 offset + 1, len);
 			data_length = 0;
 		} else {
-			len = 4 + offset + data_length;
+			len = offset + data_length;
 		}
 	}
 calc_size_exit:
@@ -465,8 +451,14 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 	/* Windows doesn't allow paths beginning with \ */
 	if (from[0] == '\\')
 		start_of_path = from + 1;
+#ifdef CONFIG_CIFS_SMB311
+	/* SMB311 POSIX extensions paths do not include leading slash */
+	else if (cifs_sb_master_tcon(cifs_sb)->posix_extensions)
+		start_of_path = from + 1;
+#endif /* 311 */
 	else
 		start_of_path = from;
+
 	to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
 				   cifs_sb->local_nls, map_type);
 	return to;
@@ -621,7 +613,7 @@ smb2_is_valid_lease_break(char *buffer)
 bool
 smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 {
-	struct smb2_oplock_break_rsp *rsp = (struct smb2_oplock_break_rsp *)buffer;
+	struct smb2_oplock_break *rsp = (struct smb2_oplock_break *)buffer;
 	struct list_head *tmp, *tmp1, *tmp2;
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
@@ -630,7 +622,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 
 	cifs_dbg(FYI, "Checking for oplock break\n");
 
-	if (rsp->hdr.sync_hdr.Command != SMB2_OPLOCK_BREAK)
+	if (rsp->sync_hdr.Command != SMB2_OPLOCK_BREAK)
 		return false;
 
 	if (rsp->StructureSize !=
@@ -721,7 +713,7 @@ smb2_cancelled_close_fid(struct work_struct *work)
 int
 smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
 {
-	struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer);
+	struct smb2_sync_hdr *sync_hdr = (struct smb2_sync_hdr *)buffer;
 	struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
 	struct cifs_tcon *tcon;
 	struct close_cancelled_open *cancelled;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index b4ae932ea134..950d0ab2cc61 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -123,7 +123,7 @@ smb2_get_credits_field(struct TCP_Server_Info *server, const int optype)
 static unsigned int
 smb2_get_credits(struct mid_q_entry *mid)
 {
-	struct smb2_sync_hdr *shdr = get_sync_hdr(mid->resp_buf);
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)mid->resp_buf;
 
 	return le16_to_cpu(shdr->CreditRequest);
 }
@@ -190,7 +190,7 @@ static struct mid_q_entry *
 smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 {
 	struct mid_q_entry *mid;
-	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
 	__u64 wire_mid = le64_to_cpu(shdr->MessageId);
 
 	if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
@@ -212,15 +212,16 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 }
 
 static void
-smb2_dump_detail(void *buf)
+smb2_dump_detail(void *buf, struct TCP_Server_Info *server)
 {
 #ifdef CONFIG_CIFS_DEBUG2
-	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
 
 	cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n",
 		 shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId,
 		 shdr->ProcessId);
-	cifs_dbg(VFS, "smb buf %p len %u\n", buf, smb2_calc_size(buf));
+	cifs_dbg(VFS, "smb buf %p len %u\n", buf,
+		 server->ops->calc_smb_size(buf, server));
 #endif
 }
 
@@ -252,9 +253,14 @@ smb2_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
 	wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
 	wsize = min_t(unsigned int, wsize, server->max_write);
 #ifdef CONFIG_CIFS_SMB_DIRECT
-	if (server->rdma)
-		wsize = min_t(unsigned int,
+	if (server->rdma) {
+		if (server->sign)
+			wsize = min_t(unsigned int,
+				wsize, server->smbd_conn->max_fragmented_send_size);
+		else
+			wsize = min_t(unsigned int,
 				wsize, server->smbd_conn->max_readwrite_size);
+	}
 #endif
 	if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
 		wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
@@ -272,9 +278,14 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
 	rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
 	rsize = min_t(unsigned int, rsize, server->max_read);
 #ifdef CONFIG_CIFS_SMB_DIRECT
-	if (server->rdma)
-		rsize = min_t(unsigned int,
+	if (server->rdma) {
+		if (server->sign)
+			rsize = min_t(unsigned int,
+				rsize, server->smbd_conn->max_fragmented_recv_size);
+		else
+			rsize = min_t(unsigned int,
 				rsize, server->smbd_conn->max_readwrite_size);
+	}
 #endif
 
 	if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
@@ -312,6 +323,40 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 }
 #endif /* STATS2 */
 
+/*
+ * Open the directory at the root of a share
+ */
+int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
+{
+	struct cifs_open_parms oparams;
+	int rc;
+	__le16 srch_path = 0; /* Null - since an open of top of share */
+	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+
+	mutex_lock(&tcon->prfid_mutex);
+	if (tcon->valid_root_fid) {
+		cifs_dbg(FYI, "found a cached root file handle\n");
+		memcpy(pfid, tcon->prfid, sizeof(struct cifs_fid));
+		mutex_unlock(&tcon->prfid_mutex);
+		return 0;
+	}
+
+	oparams.tcon = tcon;
+	oparams.create_options = 0;
+	oparams.desired_access = FILE_READ_ATTRIBUTES;
+	oparams.disposition = FILE_OPEN;
+	oparams.fid = pfid;
+	oparams.reconnect = false;
+
+	rc = SMB2_open(xid, &oparams, &srch_path, &oplock, NULL, NULL);
+	if (rc == 0) {
+		memcpy(tcon->prfid, pfid, sizeof(struct cifs_fid));
+		tcon->valid_root_fid = true;
+	}
+	mutex_unlock(&tcon->prfid_mutex);
+	return rc;
+}
+
 static void
 smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
 {
@@ -320,6 +365,7 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
 	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
+	bool no_cached_open = tcon->nohandlecache;
 
 	oparms.tcon = tcon;
 	oparms.desired_access = FILE_READ_ATTRIBUTES;
@@ -328,7 +374,11 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
 	oparms.fid = &fid;
 	oparms.reconnect = false;
 
-	rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL);
+	if (no_cached_open)
+		rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL);
+	else
+		rc = open_shroot(xid, tcon, &fid);
+
 	if (rc)
 		return;
 
@@ -342,7 +392,8 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
 			FS_DEVICE_INFORMATION);
 	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
 			FS_SECTOR_SIZE_INFORMATION); /* SMB3 specific */
-	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	if (no_cached_open)
+		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	return;
 }
 
@@ -384,6 +435,9 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
 
+	if ((*full_path == 0) && tcon->valid_root_fid)
+		return 0;
+
 	utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
 	if (!utf16_path)
 		return -ENOMEM;
@@ -579,9 +633,15 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
 
 	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 
+	/*
+	 * If ea_name is NULL (listxattr) and there are no EAs, return 0 as it's
+	 * not an error. Otherwise, the specified ea_name was not found.
+	 */
 	if (!rc)
 		rc = move_smb2_ea_to_cifs(ea_data, buf_size, smb2_data,
 					  SMB2_MAX_EA_BUF, ea_name);
+	else if (!ea_name && rc == -ENODATA)
+		rc = 0;
 
 	kfree(smb2_data);
 	return rc;
@@ -688,9 +748,11 @@ smb2_dump_share_caps(struct seq_file *m, struct cifs_tcon *tcon)
 		seq_puts(m, " TRIM-support,");
 
 	seq_printf(m, "\tShare Flags: 0x%x", tcon->share_flags);
+	seq_printf(m, "\n\ttid: 0x%x", tcon->tid);
 	if (tcon->perf_sector_size)
 		seq_printf(m, "\tOptimal sector size: 0x%x",
 			   tcon->perf_sector_size);
+	seq_printf(m, "\tMaximal Access: 0x%x", tcon->maximal_access);
 }
 
 static void
@@ -1241,7 +1303,7 @@ smb2_close_dir(const unsigned int xid, struct cifs_tcon *tcon,
 static bool
 smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length)
 {
-	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
 
 	if (shdr->Status != STATUS_PENDING)
 		return false;
@@ -1259,12 +1321,13 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length)
 static bool
 smb2_is_session_expired(char *buf)
 {
-	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
 
-	if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED)
+	if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED &&
+	    shdr->Status != STATUS_USER_SESSION_DELETED)
 		return false;
 
-	cifs_dbg(FYI, "Session expired\n");
+	cifs_dbg(FYI, "Session expired or deleted\n");
 	return true;
 }
 
@@ -1452,14 +1515,12 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
 	struct kvec err_iov = {NULL, 0};
-	struct smb2_err_rsp *err_buf = NULL;
+	struct smb2_err_rsp *err_buf;
 	struct smb2_symlink_err_rsp *symlink;
 	unsigned int sub_len;
 	unsigned int sub_offset;
 	unsigned int print_len;
 	unsigned int print_offset;
-	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = ses->server;
 
 	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
 
@@ -1476,14 +1537,14 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov);
 
-	if (!rc || !err_buf) {
+	if (!rc || !err_iov.iov_base) {
 		kfree(utf16_path);
 		return -ENOENT;
 	}
 
 	err_buf = err_iov.iov_base;
 	if (le32_to_cpu(err_buf->ByteCount) < sizeof(struct smb2_symlink_err_rsp) ||
-	    err_iov.iov_len + server->vals->header_preamble_size < SMB2_SYMLINK_STRUCT_SIZE) {
+	    err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE) {
 		kfree(utf16_path);
 		return -ENOENT;
 	}
@@ -1496,14 +1557,13 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 	print_len = le16_to_cpu(symlink->PrintNameLength);
 	print_offset = le16_to_cpu(symlink->PrintNameOffset);
 
-	if (err_iov.iov_len + server->vals->header_preamble_size <
-			SMB2_SYMLINK_STRUCT_SIZE + sub_offset + sub_len) {
+	if (err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE + sub_offset + sub_len) {
 		kfree(utf16_path);
 		return -ENOENT;
 	}
 
-	if (err_iov.iov_len + server->vals->header_preamble_size <
-			SMB2_SYMLINK_STRUCT_SIZE + print_offset + print_len) {
+	if (err_iov.iov_len <
+	    SMB2_SYMLINK_STRUCT_SIZE + print_offset + print_len) {
 		kfree(utf16_path);
 		return -ENOENT;
 	}
@@ -1577,8 +1637,11 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb,
 		oparms.create_options = 0;
 
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
-	if (!utf16_path)
-		return ERR_PTR(-ENOMEM);
+	if (!utf16_path) {
+		rc = -ENOMEM;
+		free_xid(xid);
+		return ERR_PTR(rc);
+	}
 
 	oparms.tcon = tcon;
 	oparms.desired_access = READ_CONTROL;
@@ -1636,8 +1699,11 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
 		access_flags = WRITE_DAC;
 
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
-	if (!utf16_path)
-		return -ENOMEM;
+	if (!utf16_path) {
+		rc = -ENOMEM;
+		free_xid(xid);
+		return rc;
+	}
 
 	oparms.tcon = tcon;
 	oparms.desired_access = access_flags;
@@ -1697,15 +1763,21 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 
 	/* if file not oplocked can't be sure whether asking to extend size */
 	if (!CIFS_CACHE_READ(cifsi))
-		if (keep_size == false)
-			return -EOPNOTSUPP;
+		if (keep_size == false) {
+			rc = -EOPNOTSUPP;
+			free_xid(xid);
+			return rc;
+		}
 
 	/*
 	 * Must check if file sparse since fallocate -z (zero range) assumes
 	 * non-sparse allocation
 	 */
-	if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE))
-		return -EOPNOTSUPP;
+	if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)) {
+		rc = -EOPNOTSUPP;
+		free_xid(xid);
+		return rc;
+	}
 
 	/*
 	 * need to make sure we are not asked to extend the file since the SMB3
@@ -1714,8 +1786,11 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	 * which for a non sparse file would zero the newly extended range
 	 */
 	if (keep_size == false)
-		if (i_size_read(inode) < offset + len)
-			return -EOPNOTSUPP;
+		if (i_size_read(inode) < offset + len) {
+			rc = -EOPNOTSUPP;
+			free_xid(xid);
+			return rc;
+		}
 
 	cifs_dbg(FYI, "offset %lld len %lld", offset, len);
 
@@ -1748,8 +1823,11 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 
 	/* Need to make file sparse, if not already, before freeing range. */
 	/* Consider adding equivalent for compressed since it could also work */
-	if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse))
-		return -EOPNOTSUPP;
+	if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) {
+		rc = -EOPNOTSUPP;
+		free_xid(xid);
+		return rc;
+	}
 
 	cifs_dbg(FYI, "offset %lld len %lld", offset, len);
 
@@ -1780,8 +1858,10 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 
 	/* if file not oplocked can't be sure whether asking to extend size */
 	if (!CIFS_CACHE_READ(cifsi))
-		if (keep_size == false)
-			return -EOPNOTSUPP;
+		if (keep_size == false) {
+			free_xid(xid);
+			return rc;
+		}
 
 	/*
 	 * Files are non-sparse by default so falloc may be a no-op
@@ -1790,14 +1870,16 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 	 */
 	if ((cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) == 0) {
 		if (keep_size == true)
-			return 0;
+			rc = 0;
 		/* check if extending file */
 		else if (i_size_read(inode) >= off + len)
 			/* not extending file and already not sparse */
-			return 0;
+			rc = 0;
 		/* BB: in future add else clause to extend file */
 		else
-			return -EOPNOTSUPP;
+			rc = -EOPNOTSUPP;
+		free_xid(xid);
+		return rc;
 	}
 
 	if ((keep_size == true) || (i_size_read(inode) >= off + len)) {
@@ -1809,8 +1891,11 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 		 * ie potentially making a few extra pages at the beginning
 		 * or end of the file non-sparse via set_sparse is harmless.
 		 */
-		if ((off > 8192) || (off + len + 8192 < i_size_read(inode)))
-			return -EOPNOTSUPP;
+		if ((off > 8192) || (off + len + 8192 < i_size_read(inode))) {
+			rc = -EOPNOTSUPP;
+			free_xid(xid);
+			return rc;
+		}
 
 		rc = smb2_set_sparse(xid, tcon, cfile, inode, false);
 	}
@@ -2019,7 +2104,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock)
 }
 
 static __u8
-smb2_parse_lease_buf(void *buf, unsigned int *epoch)
+smb2_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
 {
 	struct create_lease *lc = (struct create_lease *)buf;
 
@@ -2030,13 +2115,16 @@ smb2_parse_lease_buf(void *buf, unsigned int *epoch)
 }
 
 static __u8
-smb3_parse_lease_buf(void *buf, unsigned int *epoch)
+smb3_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
 {
 	struct create_lease_v2 *lc = (struct create_lease_v2 *)buf;
 
 	*epoch = le16_to_cpu(lc->lcontext.Epoch);
 	if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS)
 		return SMB2_OPLOCK_LEVEL_NOCHANGE;
+	if (lease_key)
+		memcpy(lease_key, &lc->lcontext.LeaseKeyLow,
+		       SMB2_LEASE_KEY_SIZE);
 	return le32_to_cpu(lc->lcontext.LeaseState);
 }
 
@@ -2054,12 +2142,11 @@ smb2_dir_needs_close(struct cifsFileInfo *cfile)
 }
 
 static void
-fill_transform_hdr(struct TCP_Server_Info *server,
-		   struct smb2_transform_hdr *tr_hdr, struct smb_rqst *old_rq)
+fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, unsigned int orig_len,
+		   struct smb_rqst *old_rq)
 {
 	struct smb2_sync_hdr *shdr =
 			(struct smb2_sync_hdr *)old_rq->rq_iov[1].iov_base;
-	unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base);
 
 	memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr));
 	tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM;
@@ -2067,8 +2154,6 @@ fill_transform_hdr(struct TCP_Server_Info *server,
 	tr_hdr->Flags = cpu_to_le16(0x01);
 	get_random_bytes(&tr_hdr->Nonce, SMB3_AES128CMM_NONCE);
 	memcpy(&tr_hdr->SessionId, &shdr->SessionId, 8);
-	inc_rfc1001_len(tr_hdr, sizeof(struct smb2_transform_hdr) - server->vals->header_preamble_size);
-	inc_rfc1001_len(tr_hdr, orig_len);
 }
 
 /* We can not use the normal sg_set_buf() as we will sometimes pass a
@@ -2080,11 +2165,16 @@ static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf,
 	sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
 }
 
+/* Assumes:
+ * rqst->rq_iov[0]  is rfc1002 length
+ * rqst->rq_iov[1]  is tranform header
+ * rqst->rq_iov[2+] data to be encrypted/decrypted
+ */
 static struct scatterlist *
 init_sg(struct smb_rqst *rqst, u8 *sign)
 {
-	unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1;
-	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
+	unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages;
+	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
 	struct scatterlist *sg;
 	unsigned int i;
 	unsigned int j;
@@ -2094,10 +2184,10 @@ init_sg(struct smb_rqst *rqst, u8 *sign)
 		return NULL;
 
 	sg_init_table(sg, sg_len);
-	smb2_sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 24, assoc_data_len);
-	for (i = 1; i < rqst->rq_nvec; i++)
-		smb2_sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base,
-						rqst->rq_iov[i].iov_len);
+	smb2_sg_set_buf(&sg[0], rqst->rq_iov[1].iov_base + 20, assoc_data_len);
+	for (i = 1; i < rqst->rq_nvec - 1; i++)
+		smb2_sg_set_buf(&sg[i], rqst->rq_iov[i+1].iov_base,
+						rqst->rq_iov[i+1].iov_len);
 	for (j = 0; i < sg_len - 1; i++, j++) {
 		unsigned int len = (j < rqst->rq_npages - 1) ? rqst->rq_pagesz
 							: rqst->rq_tailsz;
@@ -2129,9 +2219,10 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
 }
 /*
  * Encrypt or decrypt @rqst message. @rqst has the following format:
- * iov[0] - transform header (associate data),
- * iov[1-N] and pages - data to encrypt.
- * On success return encrypted data in iov[1-N] and pages, leave iov[0]
+ * iov[0] - rfc1002 length
+ * iov[1] - transform header (associate data),
+ * iov[2-N] and pages - data to encrypt.
+ * On success return encrypted data in iov[2-N] and pages, leave iov[0-1]
  * untouched.
  */
 static int
@@ -2139,7 +2230,7 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 {
 	struct smb2_transform_hdr *tr_hdr =
 			(struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
-	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20 - server->vals->header_preamble_size;
+	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
 	int rc = 0;
 	struct scatterlist *sg;
 	u8 sign[SMB2_SIGNATURE_SIZE] = {};
@@ -2226,6 +2317,10 @@ free_req:
 	return rc;
 }
 
+/*
+ * This is called from smb_send_rqst. At this point we have the rfc1002
+ * header as the first element in the vector.
+ */
 static int
 smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
 		       struct smb_rqst *old_rq)
@@ -2234,6 +2329,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
 	struct page **pages;
 	struct smb2_transform_hdr *tr_hdr;
 	unsigned int npages = old_rq->rq_npages;
+	unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base);
 	int i;
 	int rc = -ENOMEM;
 
@@ -2252,24 +2348,34 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
 			goto err_free_pages;
 	}
 
-	iov = kmalloc_array(old_rq->rq_nvec, sizeof(struct kvec), GFP_KERNEL);
+	/* Make space for one extra iov to hold the transform header */
+	iov = kmalloc_array(old_rq->rq_nvec + 1, sizeof(struct kvec),
+			    GFP_KERNEL);
 	if (!iov)
 		goto err_free_pages;
 
 	/* copy all iovs from the old except the 1st one (rfc1002 length) */
-	memcpy(&iov[1], &old_rq->rq_iov[1],
+	memcpy(&iov[2], &old_rq->rq_iov[1],
 				sizeof(struct kvec) * (old_rq->rq_nvec - 1));
+	/* copy the rfc1002 iov */
+	iov[0].iov_base = old_rq->rq_iov[0].iov_base;
+	iov[0].iov_len  = old_rq->rq_iov[0].iov_len;
+
 	new_rq->rq_iov = iov;
-	new_rq->rq_nvec = old_rq->rq_nvec;
+	new_rq->rq_nvec = old_rq->rq_nvec + 1;
 
 	tr_hdr = kmalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL);
 	if (!tr_hdr)
 		goto err_free_iov;
 
-	/* fill the 1st iov with a transform header */
-	fill_transform_hdr(server, tr_hdr, old_rq);
-	new_rq->rq_iov[0].iov_base = tr_hdr;
-	new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+	/* fill the 2nd iov with a transform header */
+	fill_transform_hdr(tr_hdr, orig_len, old_rq);
+	new_rq->rq_iov[1].iov_base = tr_hdr;
+	new_rq->rq_iov[1].iov_len = sizeof(struct smb2_transform_hdr);
+
+	/* Update rfc1002 header */
+	inc_rfc1001_len(new_rq->rq_iov[0].iov_base,
+			sizeof(struct smb2_transform_hdr));
 
 	/* copy pages form the old */
 	for (i = 0; i < npages; i++) {
@@ -2309,7 +2415,7 @@ smb3_free_transform_rq(struct smb_rqst *rqst)
 		put_page(rqst->rq_pages[i]);
 	kfree(rqst->rq_pages);
 	/* free transform header */
-	kfree(rqst->rq_iov[0].iov_base);
+	kfree(rqst->rq_iov[1].iov_base);
 	kfree(rqst->rq_iov);
 }
 
@@ -2326,18 +2432,19 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
 		 unsigned int buf_data_size, struct page **pages,
 		 unsigned int npages, unsigned int page_data_size)
 {
-	struct kvec iov[2];
+	struct kvec iov[3];
 	struct smb_rqst rqst = {NULL};
-	struct smb2_hdr *hdr;
 	int rc;
 
-	iov[0].iov_base = buf;
-	iov[0].iov_len = sizeof(struct smb2_transform_hdr);
-	iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr);
-	iov[1].iov_len = buf_data_size;
+	iov[0].iov_base = NULL;
+	iov[0].iov_len = 0;
+	iov[1].iov_base = buf;
+	iov[1].iov_len = sizeof(struct smb2_transform_hdr);
+	iov[2].iov_base = buf + sizeof(struct smb2_transform_hdr);
+	iov[2].iov_len = buf_data_size;
 
 	rqst.rq_iov = iov;
-	rqst.rq_nvec = 2;
+	rqst.rq_nvec = 3;
 	rqst.rq_pages = pages;
 	rqst.rq_npages = npages;
 	rqst.rq_pagesz = PAGE_SIZE;
@@ -2349,10 +2456,9 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
 	if (rc)
 		return rc;
 
-	memmove(buf + server->vals->header_preamble_size, iov[1].iov_base, buf_data_size);
-	hdr = (struct smb2_hdr *)buf;
-	hdr->smb2_buf_length = cpu_to_be32(buf_data_size + page_data_size);
-	server->total_read = buf_data_size + page_data_size + server->vals->header_preamble_size;
+	memmove(buf, iov[2].iov_base, buf_data_size);
+
+	server->total_read = buf_data_size + page_data_size;
 
 	return rc;
 }
@@ -2377,7 +2483,7 @@ read_data_into_pages(struct TCP_Server_Info *server, struct page **pages,
 			zero_user(page, len, PAGE_SIZE - len);
 			len = 0;
 		}
-		length = cifs_read_page_from_socket(server, page, n);
+		length = cifs_read_page_from_socket(server, page, 0, n);
 		if (length < 0)
 			return length;
 		server->total_read += length;
@@ -2425,7 +2531,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 	unsigned int cur_page_idx;
 	unsigned int pad_len;
 	struct cifs_readdata *rdata = mid->callback_data;
-	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
 	struct bio_vec *bvec = NULL;
 	struct iov_iter iter;
 	struct kvec iov;
@@ -2456,7 +2562,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 		return 0;
 	}
 
-	data_offset = server->ops->read_data_offset(buf) + server->vals->header_preamble_size;
+	data_offset = server->ops->read_data_offset(buf);
 #ifdef CONFIG_CIFS_SMB_DIRECT
 	use_rdma_mr = rdata->mr;
 #endif
@@ -2552,12 +2658,11 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid)
 	unsigned int npages;
 	struct page **pages;
 	unsigned int len;
-	unsigned int buflen = server->pdu_size + server->vals->header_preamble_size;
+	unsigned int buflen = server->pdu_size;
 	int rc;
 	int i = 0;
 
-	len = min_t(unsigned int, buflen, server->vals->read_rsp_size -
-		server->vals->header_preamble_size +
+	len = min_t(unsigned int, buflen, server->vals->read_rsp_size +
 		sizeof(struct smb2_transform_hdr)) - HEADER_SIZE(server) + 1;
 
 	rc = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1, len);
@@ -2565,8 +2670,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid)
 		return rc;
 	server->total_read += rc;
 
-	len = le32_to_cpu(tr_hdr->OriginalMessageSize) +
-		server->vals->header_preamble_size -
+	len = le32_to_cpu(tr_hdr->OriginalMessageSize) -
 		server->vals->read_rsp_size;
 	npages = DIV_ROUND_UP(len, PAGE_SIZE);
 
@@ -2593,8 +2697,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid)
 	if (rc)
 		goto free_pages;
 
-	rc = decrypt_raw_data(server, buf, server->vals->read_rsp_size -
-			      server->vals->header_preamble_size,
+	rc = decrypt_raw_data(server, buf, server->vals->read_rsp_size,
 			      pages, npages, len);
 	if (rc)
 		goto free_pages;
@@ -2631,7 +2734,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 	struct mid_q_entry *mid_entry;
 
 	/* switch to large buffer if too big for a small one */
-	if (pdu_length + server->vals->header_preamble_size > MAX_CIFS_SMALL_BUFFER_SIZE) {
+	if (pdu_length > MAX_CIFS_SMALL_BUFFER_SIZE) {
 		server->large_buf = true;
 		memcpy(server->bigbuf, buf, server->total_read);
 		buf = server->bigbuf;
@@ -2639,13 +2742,12 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 
 	/* now read the rest */
 	length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1,
-				pdu_length - HEADER_SIZE(server) + 1 +
-				server->vals->header_preamble_size);
+				pdu_length - HEADER_SIZE(server) + 1);
 	if (length < 0)
 		return length;
 	server->total_read += length;
 
-	buf_size = pdu_length + server->vals->header_preamble_size - sizeof(struct smb2_transform_hdr);
+	buf_size = pdu_length - sizeof(struct smb2_transform_hdr);
 	length = decrypt_raw_data(server, buf, buf_size, NULL, 0, 0);
 	if (length)
 		return length;
@@ -2674,7 +2776,7 @@ smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
 	struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf;
 	unsigned int orig_len = le32_to_cpu(tr_hdr->OriginalMessageSize);
 
-	if (pdu_length + server->vals->header_preamble_size < sizeof(struct smb2_transform_hdr) +
+	if (pdu_length < sizeof(struct smb2_transform_hdr) +
 						sizeof(struct smb2_sync_hdr)) {
 		cifs_dbg(VFS, "Transform message is too small (%u)\n",
 			 pdu_length);
@@ -2683,14 +2785,14 @@ smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
 		return -ECONNABORTED;
 	}
 
-	if (pdu_length + server->vals->header_preamble_size < orig_len + sizeof(struct smb2_transform_hdr)) {
+	if (pdu_length < orig_len + sizeof(struct smb2_transform_hdr)) {
 		cifs_dbg(VFS, "Transform message is broken\n");
 		cifs_reconnect(server);
 		wake_up(&server->response_q);
 		return -ECONNABORTED;
 	}
 
-	if (pdu_length + server->vals->header_preamble_size > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
+	if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
 		return receive_encrypted_read(server, mid);
 
 	return receive_encrypted_standard(server, mid);
@@ -2701,11 +2803,23 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
 	char *buf = server->large_buf ? server->bigbuf : server->smallbuf;
 
-	return handle_read_data(server, mid, buf, server->pdu_size +
-				server->vals->header_preamble_size,
+	return handle_read_data(server, mid, buf, server->pdu_size,
 				NULL, 0, 0);
 }
 
+static int
+smb2_next_header(char *buf)
+{
+	struct smb2_sync_hdr *hdr = (struct smb2_sync_hdr *)buf;
+	struct smb2_transform_hdr *t_hdr = (struct smb2_transform_hdr *)buf;
+
+	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM)
+		return sizeof(struct smb2_transform_hdr) +
+		  le32_to_cpu(t_hdr->OriginalMessageSize);
+
+	return le32_to_cpu(hdr->NextCommand);
+}
+
 struct smb_version_operations smb20_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,
@@ -2797,6 +2911,7 @@ struct smb_version_operations smb20_operations = {
 	.get_acl_by_fid = get_smb2_acl_by_fid,
 	.set_acl = set_smb2_acl,
 #endif /* CIFS_ACL */
+	.next_header = smb2_next_header,
 };
 
 struct smb_version_operations smb21_operations = {
@@ -2891,6 +3006,7 @@ struct smb_version_operations smb21_operations = {
 	.get_acl_by_fid = get_smb2_acl_by_fid,
 	.set_acl = set_smb2_acl,
 #endif /* CIFS_ACL */
+	.next_header = smb2_next_header,
 };
 
 struct smb_version_operations smb30_operations = {
@@ -2995,6 +3111,7 @@ struct smb_version_operations smb30_operations = {
 	.get_acl_by_fid = get_smb2_acl_by_fid,
 	.set_acl = set_smb2_acl,
 #endif /* CIFS_ACL */
+	.next_header = smb2_next_header,
 };
 
 #ifdef CONFIG_CIFS_SMB311
@@ -3095,6 +3212,7 @@ struct smb_version_operations smb311_operations = {
 	.query_all_EAs = smb2_query_eas,
 	.set_EA = smb2_set_ea,
 #endif /* CIFS_XATTR */
+	.next_header = smb2_next_header,
 };
 #endif /* CIFS_SMB311 */
 
@@ -3106,8 +3224,8 @@ struct smb_version_values smb20_values = {
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
 	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
-	.header_size = sizeof(struct smb2_hdr),
-	.header_preamble_size = 4,
+	.header_size = sizeof(struct smb2_sync_hdr),
+	.header_preamble_size = 0,
 	.max_header_size = MAX_SMB2_HDR_SIZE,
 	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
 	.lock_cmd = SMB2_LOCK,
@@ -3127,8 +3245,8 @@ struct smb_version_values smb21_values = {
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
 	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
-	.header_size = sizeof(struct smb2_hdr),
-	.header_preamble_size = 4,
+	.header_size = sizeof(struct smb2_sync_hdr),
+	.header_preamble_size = 0,
 	.max_header_size = MAX_SMB2_HDR_SIZE,
 	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
 	.lock_cmd = SMB2_LOCK,
@@ -3148,8 +3266,8 @@ struct smb_version_values smb3any_values = {
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
 	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
-	.header_size = sizeof(struct smb2_hdr),
-	.header_preamble_size = 4,
+	.header_size = sizeof(struct smb2_sync_hdr),
+	.header_preamble_size = 0,
 	.max_header_size = MAX_SMB2_HDR_SIZE,
 	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
 	.lock_cmd = SMB2_LOCK,
@@ -3169,8 +3287,8 @@ struct smb_version_values smbdefault_values = {
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
 	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
-	.header_size = sizeof(struct smb2_hdr),
-	.header_preamble_size = 4,
+	.header_size = sizeof(struct smb2_sync_hdr),
+	.header_preamble_size = 0,
 	.max_header_size = MAX_SMB2_HDR_SIZE,
 	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
 	.lock_cmd = SMB2_LOCK,
@@ -3190,8 +3308,8 @@ struct smb_version_values smb30_values = {
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
 	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
-	.header_size = sizeof(struct smb2_hdr),
-	.header_preamble_size = 4,
+	.header_size = sizeof(struct smb2_sync_hdr),
+	.header_preamble_size = 0,
 	.max_header_size = MAX_SMB2_HDR_SIZE,
 	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
 	.lock_cmd = SMB2_LOCK,
@@ -3211,8 +3329,8 @@ struct smb_version_values smb302_values = {
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
 	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
-	.header_size = sizeof(struct smb2_hdr),
-	.header_preamble_size = 4,
+	.header_size = sizeof(struct smb2_sync_hdr),
+	.header_preamble_size = 0,
 	.max_header_size = MAX_SMB2_HDR_SIZE,
 	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
 	.lock_cmd = SMB2_LOCK,
@@ -3233,8 +3351,8 @@ struct smb_version_values smb311_values = {
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
 	.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
-	.header_size = sizeof(struct smb2_hdr),
-	.header_preamble_size = 4,
+	.header_size = sizeof(struct smb2_sync_hdr),
+	.header_preamble_size = 0,
 	.max_header_size = MAX_SMB2_HDR_SIZE,
 	.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
 	.lock_cmd = SMB2_LOCK,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 0f044c4a2dc9..281fbc1dc720 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -49,6 +49,7 @@
 #include "cifspdu.h"
 #include "cifs_spnego.h"
 #include "smbdirect.h"
+#include "trace.h"
 
 /*
  *  The following table defines the expected "StructureSize" of SMB2 requests
@@ -79,7 +80,7 @@ static const int smb2_req_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 	/* SMB2_OPLOCK_BREAK */ 24 /* BB this is 36 for LEASE_BREAK variant */
 };
 
-static int encryption_required(const struct cifs_tcon *tcon)
+static int smb3_encryption_required(const struct cifs_tcon *tcon)
 {
 	if (!tcon)
 		return 0;
@@ -145,7 +146,7 @@ smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd,
 		shdr->Flags |= SMB2_FLAGS_DFS_OPERATIONS; */
 
 	if (tcon->ses && tcon->ses->server && tcon->ses->server->sign &&
-	    !encryption_required(tcon))
+	    !smb3_encryption_required(tcon))
 		shdr->Flags |= SMB2_FLAGS_SIGNED;
 out:
 	return;
@@ -367,6 +368,7 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 
 #define SMB2_PREAUTH_INTEGRITY_CAPABILITIES	cpu_to_le16(1)
 #define SMB2_ENCRYPTION_CAPABILITIES		cpu_to_le16(2)
+#define SMB2_POSIX_EXTENSIONS_AVAILABLE		cpu_to_le16(0x100)
 
 static void
 build_preauth_ctxt(struct smb2_preauth_neg_context *pneg_ctxt)
@@ -383,10 +385,17 @@ static void
 build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt)
 {
 	pneg_ctxt->ContextType = SMB2_ENCRYPTION_CAPABILITIES;
-	pneg_ctxt->DataLength = cpu_to_le16(6);
-	pneg_ctxt->CipherCount = cpu_to_le16(2);
-	pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_GCM;
-	pneg_ctxt->Ciphers[1] = SMB2_ENCRYPTION_AES128_CCM;
+	pneg_ctxt->DataLength = cpu_to_le16(4); /* Cipher Count + le16 cipher */
+	pneg_ctxt->CipherCount = cpu_to_le16(1);
+/* pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_GCM;*/ /* not supported yet */
+	pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_CCM;
+}
+
+static void
+build_posix_ctxt(struct smb2_posix_neg_context *pneg_ctxt)
+{
+	pneg_ctxt->ContextType = SMB2_POSIX_EXTENSIONS_AVAILABLE;
+	pneg_ctxt->DataLength = cpu_to_le16(POSIX_CTXT_DATA_LEN);
 }
 
 static void
@@ -394,17 +403,24 @@ assemble_neg_contexts(struct smb2_negotiate_req *req,
 		      unsigned int *total_len)
 {
 	char *pneg_ctxt = (char *)req + OFFSET_OF_NEG_CONTEXT;
+	unsigned int ctxt_len;
 
+	*total_len += 2; /* Add 2 due to round to 8 byte boundary for 1st ctxt */
 	build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt);
-	/* Add 2 to size to round to 8 byte boundary */
+	ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_preauth_neg_context), 8) * 8;
+	*total_len += ctxt_len;
+	pneg_ctxt += ctxt_len;
 
-	pneg_ctxt += 2 + sizeof(struct smb2_preauth_neg_context);
 	build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt);
-	req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
-	req->NegotiateContextCount = cpu_to_le16(2);
+	ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_encryption_neg_context), 8) * 8;
+	*total_len += ctxt_len;
+	pneg_ctxt += ctxt_len;
+
+	build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt);
+	*total_len += sizeof(struct smb2_posix_neg_context);
 
-	*total_len += 4 + sizeof(struct smb2_preauth_neg_context)
-		+ sizeof(struct smb2_encryption_neg_context);
+	req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
+	req->NegotiateContextCount = cpu_to_le16(3);
 }
 
 static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt)
@@ -444,16 +460,17 @@ static int decode_encrypt_ctx(struct TCP_Server_Info *server,
 		return -EINVAL;
 	}
 	server->cipher_type = ctxt->Ciphers[0];
+	server->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
 	return 0;
 }
 
 static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp,
-				     struct TCP_Server_Info *server)
+				     struct TCP_Server_Info *server,
+				     unsigned int len_of_smb)
 {
 	struct smb2_neg_context *pctx;
 	unsigned int offset = le32_to_cpu(rsp->NegotiateContextOffset);
 	unsigned int ctxt_cnt = le16_to_cpu(rsp->NegotiateContextCount);
-	unsigned int len_of_smb = be32_to_cpu(rsp->hdr.smb2_buf_length);
 	unsigned int len_of_ctxts, i;
 	int rc = 0;
 
@@ -474,8 +491,7 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp,
 		if (len_of_ctxts < sizeof(struct smb2_neg_context))
 			break;
 
-		pctx = (struct smb2_neg_context *)(offset +
-			server->vals->header_preamble_size + (char *)rsp);
+		pctx = (struct smb2_neg_context *)(offset + (char *)rsp);
 		clen = le16_to_cpu(pctx->DataLength);
 		if (clen > len_of_ctxts)
 			break;
@@ -486,6 +502,8 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp,
 		else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES)
 			rc = decode_encrypt_ctx(server,
 				(struct smb2_encryption_neg_context *)pctx);
+		else if (pctx->ContextType == SMB2_POSIX_EXTENSIONS_AVAILABLE)
+			server->posix_ext_supported = true;
 		else
 			cifs_dbg(VFS, "unknown negcontext of type %d ignored\n",
 				le16_to_cpu(pctx->ContextType));
@@ -500,6 +518,64 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp,
 	return rc;
 }
 
+static struct create_posix *
+create_posix_buf(umode_t mode)
+{
+	struct create_posix *buf;
+
+	buf = kzalloc(sizeof(struct create_posix),
+			GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	buf->ccontext.DataOffset =
+		cpu_to_le16(offsetof(struct create_posix, Mode));
+	buf->ccontext.DataLength = cpu_to_le32(4);
+	buf->ccontext.NameOffset =
+		cpu_to_le16(offsetof(struct create_posix, Name));
+	buf->ccontext.NameLength = cpu_to_le16(16);
+
+	/* SMB2_CREATE_TAG_POSIX is "0x93AD25509CB411E7B42383DE968BCD7C" */
+	buf->Name[0] = 0x93;
+	buf->Name[1] = 0xAD;
+	buf->Name[2] = 0x25;
+	buf->Name[3] = 0x50;
+	buf->Name[4] = 0x9C;
+	buf->Name[5] = 0xB4;
+	buf->Name[6] = 0x11;
+	buf->Name[7] = 0xE7;
+	buf->Name[8] = 0xB4;
+	buf->Name[9] = 0x23;
+	buf->Name[10] = 0x83;
+	buf->Name[11] = 0xDE;
+	buf->Name[12] = 0x96;
+	buf->Name[13] = 0x8B;
+	buf->Name[14] = 0xCD;
+	buf->Name[15] = 0x7C;
+	buf->Mode = cpu_to_le32(mode);
+	cifs_dbg(FYI, "mode on posix create 0%o", mode);
+	return buf;
+}
+
+static int
+add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode)
+{
+	struct smb2_create_req *req = iov[0].iov_base;
+	unsigned int num = *num_iovec;
+
+	iov[num].iov_base = create_posix_buf(mode);
+	if (iov[num].iov_base == NULL)
+		return -ENOMEM;
+	iov[num].iov_len = sizeof(struct create_posix);
+	if (!req->CreateContextsOffset)
+		req->CreateContextsOffset = cpu_to_le32(
+				sizeof(struct smb2_create_req) +
+				iov[num - 1].iov_len);
+	le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_posix));
+	*num_iovec = num + 1;
+	return 0;
+}
+
 #else
 static void assemble_neg_contexts(struct smb2_negotiate_req *req,
 				  unsigned int *total_len)
@@ -690,7 +766,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	server->capabilities |= SMB2_NT_FIND | SMB2_LARGE_FILES;
 
 	security_blob = smb2_get_data_area_len(&blob_offset, &blob_length,
-					       &rsp->hdr);
+					       (struct smb2_sync_hdr *)rsp);
 	/*
 	 * See MS-SMB2 section 2.2.4: if no blob, client picks default which
 	 * for us will be
@@ -717,7 +793,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 #ifdef CONFIG_CIFS_SMB311
 	if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
 		if (rsp->NegotiateContextCount)
-			rc = smb311_decode_neg_context(rsp, server);
+			rc = smb311_decode_neg_context(rsp, server,
+						       rsp_iov.iov_len);
 		else
 			cifs_dbg(VFS, "Missing expected negotiate contexts\n");
 	}
@@ -729,19 +806,14 @@ neg_exit:
 
 int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 {
-	int rc = 0;
-	struct validate_negotiate_info_req vneg_inbuf;
+	int rc;
+	struct validate_negotiate_info_req *pneg_inbuf;
 	struct validate_negotiate_info_rsp *pneg_rsp = NULL;
 	u32 rsplen;
 	u32 inbuflen; /* max of 4 dialects */
 
 	cifs_dbg(FYI, "validate negotiate\n");
 
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	if (tcon->ses->server->rdma)
-		return 0;
-#endif
-
 	/* In SMB3.11 preauth integrity supersedes validate negotiate */
 	if (tcon->ses->server->dialect == SMB311_PROT_ID)
 		return 0;
@@ -764,63 +836,69 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 	if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
 		cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n");
 
-	vneg_inbuf.Capabilities =
+	pneg_inbuf = kmalloc(sizeof(*pneg_inbuf), GFP_NOFS);
+	if (!pneg_inbuf)
+		return -ENOMEM;
+
+	pneg_inbuf->Capabilities =
 			cpu_to_le32(tcon->ses->server->vals->req_capabilities);
-	memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,
+	memcpy(pneg_inbuf->Guid, tcon->ses->server->client_guid,
 					SMB2_CLIENT_GUID_SIZE);
 
 	if (tcon->ses->sign)
-		vneg_inbuf.SecurityMode =
+		pneg_inbuf->SecurityMode =
 			cpu_to_le16(SMB2_NEGOTIATE_SIGNING_REQUIRED);
 	else if (global_secflags & CIFSSEC_MAY_SIGN)
-		vneg_inbuf.SecurityMode =
+		pneg_inbuf->SecurityMode =
 			cpu_to_le16(SMB2_NEGOTIATE_SIGNING_ENABLED);
 	else
-		vneg_inbuf.SecurityMode = 0;
+		pneg_inbuf->SecurityMode = 0;
 
 
 	if (strcmp(tcon->ses->server->vals->version_string,
 		SMB3ANY_VERSION_STRING) == 0) {
-		vneg_inbuf.Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
-		vneg_inbuf.Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
-		vneg_inbuf.DialectCount = cpu_to_le16(2);
+		pneg_inbuf->Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
+		pneg_inbuf->Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
+		pneg_inbuf->DialectCount = cpu_to_le16(2);
 		/* structure is big enough for 3 dialects, sending only 2 */
-		inbuflen = sizeof(struct validate_negotiate_info_req) - 2;
+		inbuflen = sizeof(*pneg_inbuf) -
+				sizeof(pneg_inbuf->Dialects[0]);
 	} else if (strcmp(tcon->ses->server->vals->version_string,
 		SMBDEFAULT_VERSION_STRING) == 0) {
-		vneg_inbuf.Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
-		vneg_inbuf.Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
-		vneg_inbuf.Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
-		vneg_inbuf.DialectCount = cpu_to_le16(3);
+		pneg_inbuf->Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
+		pneg_inbuf->Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
+		pneg_inbuf->Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
+		pneg_inbuf->DialectCount = cpu_to_le16(3);
 		/* structure is big enough for 3 dialects */
-		inbuflen = sizeof(struct validate_negotiate_info_req);
+		inbuflen = sizeof(*pneg_inbuf);
 	} else {
 		/* otherwise specific dialect was requested */
-		vneg_inbuf.Dialects[0] =
+		pneg_inbuf->Dialects[0] =
 			cpu_to_le16(tcon->ses->server->vals->protocol_id);
-		vneg_inbuf.DialectCount = cpu_to_le16(1);
+		pneg_inbuf->DialectCount = cpu_to_le16(1);
 		/* structure is big enough for 3 dialects, sending only 1 */
-		inbuflen = sizeof(struct validate_negotiate_info_req) - 4;
+		inbuflen = sizeof(*pneg_inbuf) -
+				sizeof(pneg_inbuf->Dialects[0]) * 2;
 	}
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 		FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
-		(char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req),
-		(char **)&pneg_rsp, &rsplen);
+		(char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen);
 
 	if (rc != 0) {
 		cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc);
-		return -EIO;
+		rc = -EIO;
+		goto out_free_inbuf;
 	}
 
-	if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
+	rc = -EIO;
+	if (rsplen != sizeof(*pneg_rsp)) {
 		cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n",
 			 rsplen);
 
 		/* relax check since Mac returns max bufsize allowed on ioctl */
-		if ((rsplen > CIFSMaxBufSize)
-		     || (rsplen < sizeof(struct validate_negotiate_info_rsp)))
-			goto err_rsp_free;
+		if (rsplen > CIFSMaxBufSize || rsplen < sizeof(*pneg_rsp))
+			goto out_free_rsp;
 	}
 
 	/* check validate negotiate info response matches what we got earlier */
@@ -837,15 +915,17 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 		goto vneg_out;
 
 	/* validate negotiate successful */
+	rc = 0;
 	cifs_dbg(FYI, "validate negotiate info successful\n");
-	kfree(pneg_rsp);
-	return 0;
+	goto out_free_rsp;
 
 vneg_out:
 	cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n");
-err_rsp_free:
+out_free_rsp:
 	kfree(pneg_rsp);
-	return -EIO;
+out_free_inbuf:
+	kfree(pneg_inbuf);
+	return rc;
 }
 
 enum securityEnum
@@ -1050,7 +1130,7 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
 		goto out_put_spnego_key;
 
 	rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
-	ses->Suid = rsp->hdr.sync_hdr.SessionId;
+	ses->Suid = rsp->sync_hdr.SessionId;
 
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
 
@@ -1126,13 +1206,13 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
 
 	/* If true, rc here is expected and not an error */
 	if (sess_data->buf0_type != CIFS_NO_BUFFER &&
-		rsp->hdr.sync_hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
+		rsp->sync_hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
 		rc = 0;
 
 	if (rc)
 		goto out;
 
-	if (offsetof(struct smb2_sess_setup_rsp, Buffer) - ses->server->vals->header_preamble_size !=
+	if (offsetof(struct smb2_sess_setup_rsp, Buffer) !=
 			le16_to_cpu(rsp->SecurityBufferOffset)) {
 		cifs_dbg(VFS, "Invalid security buffer offset %d\n",
 			le16_to_cpu(rsp->SecurityBufferOffset));
@@ -1147,7 +1227,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
 	cifs_dbg(FYI, "rawntlmssp session setup challenge phase\n");
 
 
-	ses->Suid = rsp->hdr.sync_hdr.SessionId;
+	ses->Suid = rsp->sync_hdr.SessionId;
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
 
 out:
@@ -1205,7 +1285,7 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
 
 	rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
 
-	ses->Suid = rsp->hdr.sync_hdr.SessionId;
+	ses->Suid = rsp->sync_hdr.SessionId;
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
 
 	rc = SMB2_sess_establish_session(sess_data);
@@ -1272,6 +1352,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	sess_data->ses = ses;
 	sess_data->buf0_type = CIFS_NO_BUFFER;
 	sess_data->nls_cp = (struct nls_table *) nls_cp;
+	sess_data->previous_session = ses->Suid;
 
 #ifdef CONFIG_CIFS_SMB311
 	/*
@@ -1399,7 +1480,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 		return rc;
 	}
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	iov[0].iov_base = (char *)req;
@@ -1415,7 +1496,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 
 	/* 3.11 tcon req must be signed if not encrypted. See MS-SMB2 3.2.4.1.1 */
 	if ((ses->server->dialect == SMB311_PROT_ID) &&
-	    !encryption_required(tcon))
+	    !smb3_encryption_required(tcon))
 		req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
 
 	rc = smb2_send_recv(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
@@ -1453,7 +1534,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess);
 	tcon->tidStatus = CifsGood;
 	tcon->need_reconnect = false;
-	tcon->tid = rsp->hdr.sync_hdr.TreeId;
+	tcon->tid = rsp->sync_hdr.TreeId;
 	strlcpy(tcon->treeName, tree, sizeof(tcon->treeName));
 
 	if ((rsp->Capabilities & SMB2_SHARE_CAP_DFS) &&
@@ -1473,7 +1554,7 @@ tcon_exit:
 	return rc;
 
 tcon_error_exit:
-	if (rsp && rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
+	if (rsp && rsp->sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
 	}
 	goto tcon_exit;
@@ -1504,7 +1585,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	flags |= CIFS_NO_RESP;
@@ -1571,7 +1652,7 @@ create_reconnect_durable_buf(struct cifs_fid *fid)
 
 static __u8
 parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
-		  unsigned int *epoch)
+		  unsigned int *epoch, char *lease_key)
 {
 	char *data_offset;
 	struct create_context *cc;
@@ -1579,14 +1660,15 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
 	unsigned int remaining;
 	char *name;
 
-	data_offset = (char *)rsp + server->vals->header_preamble_size + le32_to_cpu(rsp->CreateContextsOffset);
+	data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset);
 	remaining = le32_to_cpu(rsp->CreateContextsLength);
 	cc = (struct create_context *)data_offset;
 	while (remaining >= sizeof(struct create_context)) {
 		name = le16_to_cpu(cc->NameOffset) + (char *)cc;
 		if (le16_to_cpu(cc->NameLength) == 4 &&
 		    strncmp(name, "RqLs", 4) == 0)
-			return server->ops->parse_lease_buf(cc, epoch);
+			return server->ops->parse_lease_buf(cc, epoch,
+							    lease_key);
 
 		next = le32_to_cpu(cc->Next);
 		if (!next)
@@ -1814,7 +1896,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	struct TCP_Server_Info *server;
 	struct cifs_tcon *tcon = oparms->tcon;
 	struct cifs_ses *ses = tcon->ses;
-	struct kvec iov[4];
+	struct kvec iov[5]; /* make sure at least one for each open context */
 	struct kvec rsp_iov = {NULL, 0};
 	int resp_buftype;
 	int uni_path_len;
@@ -1823,7 +1905,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	int rc = 0;
 	unsigned int n_iov = 2;
 	__u32 file_attributes = 0;
-	char *dhc_buf = NULL, *lc_buf = NULL;
+	char *dhc_buf = NULL, *lc_buf = NULL, *pc_buf = NULL;
 	int flags = 0;
 	unsigned int total_len;
 
@@ -1839,7 +1921,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	if (oparms->create_options & CREATE_OPTION_READONLY)
@@ -1940,6 +2022,27 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		dhc_buf = iov[n_iov-1].iov_base;
 	}
 
+#ifdef CONFIG_CIFS_SMB311
+	if (tcon->posix_extensions) {
+		if (n_iov > 2) {
+			struct create_context *ccontext =
+			    (struct create_context *)iov[n_iov-1].iov_base;
+			ccontext->Next =
+				cpu_to_le32(iov[n_iov-1].iov_len);
+		}
+
+		rc = add_posix_context(iov, &n_iov, oparms->mode);
+		if (rc) {
+			cifs_small_buf_release(req);
+			kfree(copy_path);
+			kfree(lc_buf);
+			kfree(dhc_buf);
+			return rc;
+		}
+		pc_buf = iov[n_iov-1].iov_base;
+	}
+#endif /* SMB311 */
+
 	rc = smb2_send_recv(xid, ses, iov, n_iov, &resp_buftype, flags,
 			    &rsp_iov);
 	cifs_small_buf_release(req);
@@ -1952,8 +2055,13 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 			resp_buftype = CIFS_NO_BUFFER;
 			rsp = NULL;
 		}
+		trace_smb3_open_err(xid, tcon->tid, ses->Suid,
+				    oparms->create_options, oparms->desired_access, rc);
 		goto creat_exit;
-	}
+	} else
+		trace_smb3_open_done(xid, rsp->PersistentFileId, tcon->tid,
+				     ses->Suid, oparms->create_options,
+				     oparms->desired_access);
 
 	oparms->fid->persistent_fid = rsp->PersistentFileId;
 	oparms->fid->volatile_fid = rsp->VolatileFileId;
@@ -1968,13 +2076,15 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	}
 
 	if (rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE)
-		*oplock = parse_lease_state(server, rsp, &oparms->fid->epoch);
+		*oplock = parse_lease_state(server, rsp, &oparms->fid->epoch,
+					    oparms->fid->lease_key);
 	else
 		*oplock = rsp->OplockLevel;
 creat_exit:
 	kfree(copy_path);
 	kfree(lc_buf);
 	kfree(dhc_buf);
+	kfree(pc_buf);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
@@ -1990,7 +2100,6 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 {
 	struct smb2_ioctl_req *req;
 	struct smb2_ioctl_rsp *rsp;
-	struct smb2_sync_hdr *shdr;
 	struct cifs_ses *ses;
 	struct kvec iov[2];
 	struct kvec rsp_iov;
@@ -2021,7 +2130,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->CtlCode = cpu_to_le32(opcode);
@@ -2084,6 +2193,10 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	cifs_small_buf_release(req);
 	rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base;
 
+	if (rc != 0)
+		trace_smb3_fsctl_err(xid, persistent_fid, tcon->tid,
+				ses->Suid, 0, opcode, rc);
+
 	if ((rc != 0) && (rc != -EINVAL)) {
 		cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
 		goto ioctl_exit;
@@ -2111,7 +2224,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		goto ioctl_exit;
 	}
 
-	if (get_rfc1002_length(rsp) < le32_to_cpu(rsp->OutputOffset) + *plen) {
+	if (rsp_iov.iov_len < le32_to_cpu(rsp->OutputOffset) + *plen) {
 		cifs_dbg(VFS, "Malformed ioctl resp: len %d offset %d\n", *plen,
 			le32_to_cpu(rsp->OutputOffset));
 		*plen = 0;
@@ -2125,8 +2238,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		goto ioctl_exit;
 	}
 
-	shdr = get_sync_hdr(rsp);
-	memcpy(*out_data, (char *)shdr + le32_to_cpu(rsp->OutputOffset), *plen);
+	memcpy(*out_data, (char *)rsp + le32_to_cpu(rsp->OutputOffset), *plen);
 ioctl_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -2158,8 +2270,8 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 }
 
 int
-SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
-	   u64 persistent_fid, u64 volatile_fid)
+SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
+		 u64 persistent_fid, u64 volatile_fid, int flags)
 {
 	struct smb2_close_req *req;
 	struct smb2_close_rsp *rsp;
@@ -2168,7 +2280,6 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	struct kvec rsp_iov;
 	int resp_buftype;
 	int rc = 0;
-	int flags = 0;
 	unsigned int total_len;
 
 	cifs_dbg(FYI, "Close\n");
@@ -2180,7 +2291,7 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->PersistentFileId = persistent_fid;
@@ -2195,6 +2306,8 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 
 	if (rc != 0) {
 		cifs_stats_fail_inc(tcon, SMB2_CLOSE_HE);
+		trace_smb3_close_err(xid, persistent_fid, tcon->tid, ses->Suid,
+				     rc);
 		goto close_exit;
 	}
 
@@ -2205,14 +2318,20 @@ close_exit:
 	return rc;
 }
 
+int
+SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
+	   u64 persistent_fid, u64 volatile_fid)
+{
+	return SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
+}
+
 static int
-validate_iov(struct TCP_Server_Info *server,
-	     unsigned int offset, unsigned int buffer_length,
+validate_iov(unsigned int offset, unsigned int buffer_length,
 	     struct kvec *iov, unsigned int min_buf_size)
 {
 	unsigned int smb_len = iov->iov_len;
-	char *end_of_smb = smb_len + server->vals->header_preamble_size + (char *)iov->iov_base;
-	char *begin_of_buf = server->vals->header_preamble_size + offset + (char *)iov->iov_base;
+	char *end_of_smb = smb_len + (char *)iov->iov_base;
+	char *begin_of_buf = offset + (char *)iov->iov_base;
 	char *end_of_buf = begin_of_buf + buffer_length;
 
 
@@ -2242,18 +2361,17 @@ validate_iov(struct TCP_Server_Info *server,
  * Caller must free buffer.
  */
 static int
-validate_and_copy_iov(struct TCP_Server_Info *server,
-		      unsigned int offset, unsigned int buffer_length,
+validate_and_copy_iov(unsigned int offset, unsigned int buffer_length,
 		      struct kvec *iov, unsigned int minbufsize,
 		      char *data)
 {
-	char *begin_of_buf = server->vals->header_preamble_size + offset + (char *)(iov->iov_base);
+	char *begin_of_buf = offset + (char *)iov->iov_base;
 	int rc;
 
 	if (!data)
 		return -EINVAL;
 
-	rc = validate_iov(server, offset, buffer_length, iov, minbufsize);
+	rc = validate_iov(offset, buffer_length, iov, minbufsize);
 	if (rc)
 		return rc;
 
@@ -2288,7 +2406,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->InfoType = info_type;
@@ -2314,6 +2432,8 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
+		trace_smb3_query_info_err(xid, persistent_fid, tcon->tid,
+				ses->Suid, info_class, (__u32)info_type, rc);
 		goto qinf_exit;
 	}
 
@@ -2331,8 +2451,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 		}
 	}
 
-	rc = validate_and_copy_iov(ses->server,
-				   le16_to_cpu(rsp->OutputBufferOffset),
+	rc = validate_and_copy_iov(le16_to_cpu(rsp->OutputBufferOffset),
 				   le32_to_cpu(rsp->OutputBufferLength),
 				   &rsp_iov, min_len, *data);
 
@@ -2403,7 +2522,7 @@ smb2_echo_callback(struct mid_q_entry *mid)
 	unsigned int credits_received = 1;
 
 	if (mid->mid_state == MID_RESPONSE_RECEIVED)
-		credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
+		credits_received = le16_to_cpu(rsp->sync_hdr.CreditRequest);
 
 	DeleteMidQEntry(mid);
 	add_credits(server, credits_received, CIFS_ECHO_OP);
@@ -2532,7 +2651,7 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->PersistentFileId = persistent_fid;
@@ -2544,8 +2663,11 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
 	cifs_small_buf_release(req);
 
-	if (rc != 0)
+	if (rc != 0) {
 		cifs_stats_fail_inc(tcon, SMB2_FLUSH_HE);
+		trace_smb3_flush_err(xid, persistent_fid, tcon->tid, ses->Suid,
+				     rc);
+	}
 
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	return rc;
@@ -2590,7 +2712,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
 	 * If we want to do a RDMA write, fill in and append
 	 * smbd_buffer_descriptor_v1 to the end of read request
 	 */
-	if (server->rdma && rdata &&
+	if (server->rdma && rdata && !server->sign &&
 		rdata->bytes >= server->smbd_conn->rdma_readwrite_threshold) {
 
 		struct smbd_buffer_descriptor_v1 *v1;
@@ -2654,11 +2776,12 @@ smb2_readv_callback(struct mid_q_entry *mid)
 	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct smb2_sync_hdr *shdr =
-				(struct smb2_sync_hdr *)rdata->iov[1].iov_base;
+				(struct smb2_sync_hdr *)rdata->iov[0].iov_base;
 	unsigned int credits_received = 1;
 	struct smb_rqst rqst = { .rq_iov = rdata->iov,
 				 .rq_nvec = 2,
 				 .rq_pages = rdata->pages,
+				 .rq_offset = rdata->page_offset,
 				 .rq_npages = rdata->nr_pages,
 				 .rq_pagesz = rdata->pagesz,
 				 .rq_tailsz = rdata->tailsz };
@@ -2756,7 +2879,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
 		return rc;
 	}
 
-	if (encryption_required(io_parms.tcon))
+	if (smb3_encryption_required(io_parms.tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req_len = cpu_to_be32(total_len);
@@ -2787,7 +2910,13 @@ smb2_async_readv(struct cifs_readdata *rdata)
 	if (rc) {
 		kref_put(&rdata->refcount, cifs_readdata_release);
 		cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
-	}
+		trace_smb3_read_err(rc, 0 /* xid */, io_parms.persistent_fid,
+				   io_parms.tcon->tid, io_parms.tcon->ses->Suid,
+				   io_parms.offset, io_parms.length);
+	} else
+		trace_smb3_read_done(0 /* xid */, io_parms.persistent_fid,
+				   io_parms.tcon->tid, io_parms.tcon->ses->Suid,
+				   io_parms.offset, io_parms.length);
 
 	cifs_small_buf_release(buf);
 	return rc;
@@ -2800,7 +2929,6 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 	int resp_buftype, rc = -EACCES;
 	struct smb2_read_plain_req *req = NULL;
 	struct smb2_read_rsp *rsp = NULL;
-	struct smb2_sync_hdr *shdr;
 	struct kvec iov[1];
 	struct kvec rsp_iov;
 	unsigned int total_len;
@@ -2812,7 +2940,7 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 	if (rc)
 		return rc;
 
-	if (encryption_required(io_parms->tcon))
+	if (smb3_encryption_required(io_parms->tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	iov[0].iov_base = (char *)req;
@@ -2828,9 +2956,15 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 			cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE);
 			cifs_dbg(VFS, "Send error in read = %d\n", rc);
 		}
+		trace_smb3_read_err(rc, xid, req->PersistentFileId,
+				    io_parms->tcon->tid, ses->Suid,
+				    io_parms->offset, io_parms->length);
 		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 		return rc == -ENODATA ? 0 : rc;
-	}
+	} else
+		trace_smb3_read_done(xid, req->PersistentFileId,
+				    io_parms->tcon->tid, ses->Suid,
+				    io_parms->offset, io_parms->length);
 
 	*nbytes = le32_to_cpu(rsp->DataLength);
 	if ((*nbytes > CIFS_MAX_MSGSIZE) ||
@@ -2841,10 +2975,8 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 		*nbytes = 0;
 	}
 
-	shdr = get_sync_hdr(rsp);
-
 	if (*buf) {
-		memcpy(*buf, (char *)shdr + rsp->DataOffset, *nbytes);
+		memcpy(*buf, (char *)rsp + rsp->DataOffset, *nbytes);
 		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	} else if (resp_buftype != CIFS_NO_BUFFER) {
 		*buf = rsp_iov.iov_base;
@@ -2871,7 +3003,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
-		credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
+		credits_received = le16_to_cpu(rsp->sync_hdr.CreditRequest);
 		wdata->result = smb2_check_receive(mid, tcon->ses->server, 0);
 		if (wdata->result != 0)
 			break;
@@ -2948,7 +3080,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 		goto async_writev_out;
 	}
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	shdr = (struct smb2_sync_hdr *)req;
@@ -2968,7 +3100,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	 * If we want to do a server RDMA read, fill in and append
 	 * smbd_buffer_descriptor_v1 to the end of write request
 	 */
-	if (server->rdma && wdata->bytes >=
+	if (server->rdma && !server->sign && wdata->bytes >=
 		server->smbd_conn->rdma_readwrite_threshold) {
 
 		struct smbd_buffer_descriptor_v1 *v1;
@@ -3009,6 +3141,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 2;
 	rqst.rq_pages = wdata->pages;
+	rqst.rq_offset = wdata->page_offset;
 	rqst.rq_npages = wdata->nr_pages;
 	rqst.rq_pagesz = wdata->pagesz;
 	rqst.rq_tailsz = wdata->tailsz;
@@ -3046,9 +3179,15 @@ smb2_async_writev(struct cifs_writedata *wdata,
 			     wdata, flags);
 
 	if (rc) {
+		trace_smb3_write_err(0 /* no xid */, req->PersistentFileId,
+				     tcon->tid, tcon->ses->Suid, wdata->offset,
+				     wdata->bytes, rc);
 		kref_put(&wdata->refcount, release);
 		cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
-	}
+	} else
+		trace_smb3_write_done(0 /* no xid */, req->PersistentFileId,
+				     tcon->tid, tcon->ses->Suid, wdata->offset,
+				     wdata->bytes);
 
 async_writev_out:
 	cifs_small_buf_release(req);
@@ -3086,7 +3225,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	if (io_parms->tcon->ses->server == NULL)
 		return -ECONNABORTED;
 
-	if (encryption_required(io_parms->tcon))
+	if (smb3_encryption_required(io_parms->tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->sync_hdr.ProcessId = cpu_to_le32(io_parms->pid);
@@ -3112,10 +3251,19 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
+		trace_smb3_write_err(xid, req->PersistentFileId,
+				     io_parms->tcon->tid,
+				     io_parms->tcon->ses->Suid,
+				     io_parms->offset, io_parms->length, rc);
 		cifs_stats_fail_inc(io_parms->tcon, SMB2_WRITE_HE);
 		cifs_dbg(VFS, "Send error in write = %d\n", rc);
-	} else
+	} else {
 		*nbytes = le32_to_cpu(rsp->DataLength);
+		trace_smb3_write_done(xid, req->PersistentFileId,
+				     io_parms->tcon->tid,
+				     io_parms->tcon->ses->Suid,
+				     io_parms->offset, *nbytes);
+	}
 
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -3196,7 +3344,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	switch (srch_inf->info_level) {
@@ -3247,7 +3395,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 
 	if (rc) {
 		if (rc == -ENODATA &&
-		    rsp->hdr.sync_hdr.Status == STATUS_NO_MORE_FILES) {
+		    rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) {
 			srch_inf->endOfSearch = true;
 			rc = 0;
 		}
@@ -3255,8 +3403,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 		goto qdir_exit;
 	}
 
-	rc = validate_iov(server,
-			  le16_to_cpu(rsp->OutputBufferOffset),
+	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
 			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
 			  info_buf_size);
 	if (rc)
@@ -3271,10 +3418,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 			cifs_buf_release(srch_inf->ntwrk_buf_start);
 	}
 	srch_inf->ntwrk_buf_start = (char *)rsp;
-	srch_inf->srch_entries_start = srch_inf->last_entry = 4 /* rfclen */ +
-		(char *)&rsp->hdr + le16_to_cpu(rsp->OutputBufferOffset);
-	/* 4 for rfc1002 length field */
-	end_of_smb = get_rfc1002_length(rsp) + 4 + (char *)&rsp->hdr;
+	srch_inf->srch_entries_start = srch_inf->last_entry =
+		(char *)rsp + le16_to_cpu(rsp->OutputBufferOffset);
+	end_of_smb = rsp_iov.iov_len + (char *)rsp;
 	srch_inf->entries_in_buffer =
 			num_entries(srch_inf->srch_entries_start, end_of_smb,
 				    &srch_inf->last_entry, info_buf_size);
@@ -3329,7 +3475,7 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 		return rc;
 	}
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->sync_hdr.ProcessId = cpu_to_le32(pid);
@@ -3362,8 +3508,11 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 	cifs_small_buf_release(req);
 	rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base;
 
-	if (rc != 0)
+	if (rc != 0) {
 		cifs_stats_fail_inc(tcon, SMB2_SET_INFO_HE);
+		trace_smb3_set_info_err(xid, persistent_fid, tcon->tid,
+				ses->Suid, info_class, (__u32)info_type, rc);
+	}
 
 	free_rsp_buf(resp_buftype, rsp);
 	kfree(iov);
@@ -3510,7 +3659,7 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 		  __u8 oplock_level)
 {
 	int rc;
-	struct smb2_oplock_break_req *req = NULL;
+	struct smb2_oplock_break *req = NULL;
 	struct cifs_ses *ses = tcon->ses;
 	int flags = CIFS_OBREAK_OP;
 	unsigned int total_len;
@@ -3524,7 +3673,7 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->VolatileFid = volatile_fid;
@@ -3589,7 +3738,7 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
 	req->InputBufferOffset =
 			cpu_to_le16(sizeof(struct smb2_query_info_req) - 1);
 	req->OutputBufferLength = cpu_to_le32(
-		outbuf_len + sizeof(struct smb2_query_info_rsp) - 1 - server->vals->header_preamble_size);
+		outbuf_len + sizeof(struct smb2_query_info_rsp) - 1);
 
 	iov->iov_base = (char *)req;
 	iov->iov_len = total_len;
@@ -3606,7 +3755,6 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = ses->server;
 	struct smb2_fs_full_size_info *info = NULL;
 	int flags = 0;
 
@@ -3616,7 +3764,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
@@ -3627,10 +3775,9 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	}
 	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
-	info = (struct smb2_fs_full_size_info *)(server->vals->header_preamble_size +
-		le16_to_cpu(rsp->OutputBufferOffset) + (char *)&rsp->hdr);
-	rc = validate_iov(server,
-			  le16_to_cpu(rsp->OutputBufferOffset),
+	info = (struct smb2_fs_full_size_info *)(
+		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
+	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
 			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
 			  sizeof(struct smb2_fs_full_size_info));
 	if (!rc)
@@ -3651,7 +3798,6 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	int resp_buftype, max_len, min_len;
 	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server = ses->server;
 	unsigned int rsp_len, offset;
 	int flags = 0;
 
@@ -3674,7 +3820,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
@@ -3687,20 +3833,20 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rsp_len = le32_to_cpu(rsp->OutputBufferLength);
 	offset = le16_to_cpu(rsp->OutputBufferOffset);
-	rc = validate_iov(server, offset, rsp_len, &rsp_iov, min_len);
+	rc = validate_iov(offset, rsp_len, &rsp_iov, min_len);
 	if (rc)
 		goto qfsattr_exit;
 
 	if (level == FS_ATTRIBUTE_INFORMATION)
-		memcpy(&tcon->fsAttrInfo, server->vals->header_preamble_size + offset
-			+ (char *)&rsp->hdr, min_t(unsigned int,
+		memcpy(&tcon->fsAttrInfo, offset
+			+ (char *)rsp, min_t(unsigned int,
 			rsp_len, max_len));
 	else if (level == FS_DEVICE_INFORMATION)
-		memcpy(&tcon->fsDevInfo, server->vals->header_preamble_size + offset
-			+ (char *)&rsp->hdr, sizeof(FILE_SYSTEM_DEVICE_INFO));
+		memcpy(&tcon->fsDevInfo, offset
+			+ (char *)rsp, sizeof(FILE_SYSTEM_DEVICE_INFO));
 	else if (level == FS_SECTOR_SIZE_INFORMATION) {
 		struct smb3_fs_ss_info *ss_info = (struct smb3_fs_ss_info *)
-			(server->vals->header_preamble_size + offset + (char *)&rsp->hdr);
+			(offset + (char *)rsp);
 		tcon->ss_flags = le32_to_cpu(ss_info->Flags);
 		tcon->perf_sector_size =
 			le32_to_cpu(ss_info->PhysicalBytesPerSectorForPerf);
@@ -3731,7 +3877,7 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->sync_hdr.ProcessId = cpu_to_le32(pid);
@@ -3754,6 +3900,8 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc) {
 		cifs_dbg(FYI, "Send error in smb2_lockv = %d\n", rc);
 		cifs_stats_fail_inc(tcon, SMB2_LOCK_HE);
+		trace_smb3_lock_err(xid, persist_fid, tcon->tid,
+				    tcon->ses->Suid, rc);
 	}
 
 	return rc;
@@ -3795,7 +3943,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	if (encryption_required(tcon))
+	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
 	req->sync_hdr.CreditRequest = cpu_to_le16(1);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 6093e5142b2b..a345560001ce 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -122,25 +122,10 @@ struct smb2_sync_pdu {
 	__le16 StructureSize2; /* size of wct area (varies, request specific) */
 } __packed;
 
-struct smb2_hdr {
-	__be32 smb2_buf_length;	/* big endian on wire */
-				/* length is only two or three bytes - with */
-				/* one or two byte type preceding it that MBZ */
-	struct smb2_sync_hdr sync_hdr;
-} __packed;
-
-struct smb2_pdu {
-	struct smb2_hdr hdr;
-	__le16 StructureSize2; /* size of wct area (varies, request specific) */
-} __packed;
-
 #define SMB3_AES128CMM_NONCE 11
 #define SMB3_AES128GCM_NONCE 12
 
 struct smb2_transform_hdr {
-	__be32 smb2_buf_length;	/* big endian on wire */
-				/* length is only two or three bytes - with
-				 one or two byte type preceding it that MBZ */
 	__le32 ProtocolId;	/* 0xFD 'S' 'M' 'B' */
 	__u8   Signature[16];
 	__u8   Nonce[16];
@@ -171,7 +156,7 @@ struct smb2_transform_hdr {
 #define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
 
 struct smb2_err_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;
 	__le16 Reserved; /* MBZ */
 	__le32 ByteCount;  /* even if zero, at least one byte follows */
@@ -297,11 +282,19 @@ struct smb2_encryption_neg_context {
 	__le16	DataLength;
 	__le32	Reserved;
 	__le16	CipherCount; /* AES-128-GCM and AES-128-CCM */
-	__le16	Ciphers[2]; /* Ciphers[0] since only one used now */
+	__le16	Ciphers[1]; /* Ciphers[0] since only one used now */
+} __packed;
+
+#define POSIX_CTXT_DATA_LEN	8
+struct smb2_posix_neg_context {
+	__le16	ContextType; /* 0x100 */
+	__le16	DataLength;
+	__le32	Reserved;
+	__le64	Reserved1; /* In case needed for future (eg version or caps) */
 } __packed;
 
 struct smb2_negotiate_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;	/* Must be 65 */
 	__le16 SecurityMode;
 	__le16 DialectRevision;
@@ -341,7 +334,7 @@ struct smb2_sess_setup_req {
 #define SMB2_SESSION_FLAG_IS_NULL	0x0002
 #define SMB2_SESSION_FLAG_ENCRYPT_DATA	0x0004
 struct smb2_sess_setup_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 9 */
 	__le16 SessionFlags;
 	__le16 SecurityBufferOffset;
@@ -356,7 +349,7 @@ struct smb2_logoff_req {
 } __packed;
 
 struct smb2_logoff_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;	/* Must be 4 */
 	__le16 Reserved;
 } __packed;
@@ -452,7 +445,7 @@ struct smb2_tree_connect_req_extension {
 } __packed;
 
 struct smb2_tree_connect_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;	/* Must be 16 */
 	__u8   ShareType;  /* see below */
 	__u8   Reserved;
@@ -503,7 +496,7 @@ struct smb2_tree_disconnect_req {
 } __packed;
 
 struct smb2_tree_disconnect_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;	/* Must be 4 */
 	__le16 Reserved;
 } __packed;
@@ -615,7 +608,9 @@ struct smb2_tree_disconnect_rsp {
 #define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2	"DH2Q"
 #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2	"DH2C"
 #define SMB2_CREATE_APP_INSTANCE_ID	0x45BCA66AEFA7F74A9008FA462E144D74
-#define SVHDX_OPEN_DEVICE_CONTEXT	0x83CE6F1AD851E0986E34401CC9BCFCE9
+#define SVHDX_OPEN_DEVICE_CONTEX	0x9CCBCF9E04C1E643980E158DA1F6EC83
+#define SMB2_CREATE_TAG_POSIX		0x93AD25509CB411E7B42383DE968BCD7C
+
 
 struct smb2_create_req {
 	struct smb2_sync_hdr sync_hdr;
@@ -638,7 +633,7 @@ struct smb2_create_req {
 } __packed;
 
 struct smb2_create_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;	/* Must be 89 */
 	__u8   OplockLevel;
 	__u8   Reserved;
@@ -727,6 +722,13 @@ struct create_durable {
 	} Data;
 } __packed;
 
+struct create_posix {
+	struct create_context ccontext;
+	__u8	Name[16];
+	__le32  Mode;
+	__u32	Reserved;
+} __packed;
+
 /* See MS-SMB2 2.2.13.2.11 */
 /* Flags */
 #define SMB2_DHANDLE_FLAG_PERSISTENT	0x00000002
@@ -894,7 +896,7 @@ struct smb2_ioctl_req {
 } __packed;
 
 struct smb2_ioctl_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;	/* Must be 57 */
 	__u16 Reserved;
 	__le32 CtlCode;
@@ -921,7 +923,7 @@ struct smb2_close_req {
 } __packed;
 
 struct smb2_close_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* 60 */
 	__le16 Flags;
 	__le32 Reserved;
@@ -944,7 +946,7 @@ struct smb2_flush_req {
 } __packed;
 
 struct smb2_flush_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;
 	__le16 Reserved;
 } __packed;
@@ -976,7 +978,7 @@ struct smb2_read_plain_req {
 } __packed;
 
 struct smb2_read_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 17 */
 	__u8   DataOffset;
 	__u8   Reserved;
@@ -1007,7 +1009,7 @@ struct smb2_write_req {
 } __packed;
 
 struct smb2_write_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 17 */
 	__u8   DataOffset;
 	__u8   Reserved;
@@ -1041,7 +1043,7 @@ struct smb2_lock_req {
 } __packed;
 
 struct smb2_lock_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 4 */
 	__le16 Reserved;
 } __packed;
@@ -1053,7 +1055,7 @@ struct smb2_echo_req {
 } __packed;
 
 struct smb2_echo_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize;	/* Must be 4 */
 	__u16  Reserved;
 } __packed;
@@ -1079,7 +1081,7 @@ struct smb2_query_directory_req {
 } __packed;
 
 struct smb2_query_directory_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 9 */
 	__le16 OutputBufferOffset;
 	__le32 OutputBufferLength;
@@ -1128,7 +1130,7 @@ struct smb2_query_info_req {
 } __packed;
 
 struct smb2_query_info_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 9 */
 	__le16 OutputBufferOffset;
 	__le32 OutputBufferLength;
@@ -1150,12 +1152,11 @@ struct smb2_set_info_req {
 } __packed;
 
 struct smb2_set_info_rsp {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 2 */
 } __packed;
 
-/* oplock break without an rfc1002 header */
-struct smb2_oplock_break_req {
+struct smb2_oplock_break {
 	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 24 */
 	__u8   OplockLevel;
@@ -1165,21 +1166,10 @@ struct smb2_oplock_break_req {
 	__u64  VolatileFid;
 } __packed;
 
-/* oplock break with an rfc1002 header */
-struct smb2_oplock_break_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 24 */
-	__u8   OplockLevel;
-	__u8   Reserved;
-	__le32 Reserved2;
-	__u64  PersistentFid;
-	__u64  VolatileFid;
-} __packed;
-
 #define SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED cpu_to_le32(0x01)
 
 struct smb2_lease_break {
-	struct smb2_hdr hdr;
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 44 */
 	__le16 Reserved;
 	__le32 Flags;
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 8ba24a95db71..908555b1c6b5 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -36,8 +36,9 @@ struct smb_rqst;
 extern int map_smb2_to_linux_error(char *buf, bool log_err);
 extern int smb2_check_message(char *buf, unsigned int length,
 			      struct TCP_Server_Info *server);
-extern unsigned int smb2_calc_size(void *buf);
-extern char *smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr);
+extern unsigned int smb2_calc_size(void *buf, struct TCP_Server_Info *server);
+extern char *smb2_get_data_area_len(int *off, int *len,
+				    struct smb2_sync_hdr *shdr);
 extern __le16 *cifs_convert_path_to_utf16(const char *from,
 					  struct cifs_sb_info *cifs_sb);
 
@@ -65,6 +66,8 @@ extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
 extern int smb3_handle_read_data(struct TCP_Server_Info *server,
 				 struct mid_q_entry *mid);
 
+extern int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
+			struct cifs_fid *pfid);
 extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
 				   struct smb2_file_all_info *src);
 extern int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
@@ -129,6 +132,8 @@ extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
 		     char **out_data, u32 *plen /* returned data len */);
 extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
+extern int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
+			    u64 persistent_fid, u64 volatile_fid, int flags);
 extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 8806f3f76c1d..2c671123a6bf 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -480,7 +480,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	unsigned int rc;
 	char server_response_sig[16];
 	struct smb2_sync_hdr *shdr =
-			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
+			(struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
 
 	if ((shdr->Command == SMB2_NEGOTIATE) ||
 	    (shdr->Command == SMB2_SESSION_SETUP) ||
@@ -605,14 +605,12 @@ smb2_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 		   bool log_error)
 {
 	unsigned int len = mid->resp_buf_size;
-	struct kvec iov[2];
+	struct kvec iov[1];
 	struct smb_rqst rqst = { .rq_iov = iov,
-				 .rq_nvec = 2 };
+				 .rq_nvec = 1 };
 
 	iov[0].iov_base = (char *)mid->resp_buf;
-	iov[0].iov_len = 4;
-	iov[1].iov_base = (char *)mid->resp_buf + 4;
-	iov[1].iov_len = len;
+	iov[0].iov_len = len;
 
 	dump_smb(mid->resp_buf, min_t(u32, 80, len));
 	/* convert the length into a more usable form */
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index 5008af546dd1..c62f7c95683c 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -1028,7 +1028,7 @@ static int smbd_post_send(struct smbd_connection *info,
 	for (i = 0; i < request->num_sge; i++) {
 		log_rdma_send(INFO,
 			"rdma_request sge[%d] addr=%llu length=%u\n",
-			i, request->sge[0].addr, request->sge[0].length);
+			i, request->sge[i].addr, request->sge[i].length);
 		ib_dma_sync_single_for_device(
 			info->id->device,
 			request->sge[i].addr,
@@ -2086,7 +2086,7 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
 	int start, i, j;
 	int max_iov_size =
 		info->max_send_size - sizeof(struct smbd_data_transfer);
-	struct kvec iov[SMBDIRECT_MAX_SGE];
+	struct kvec *iov;
 	int rc;
 
 	info->smbd_send_pending++;
@@ -2096,32 +2096,20 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
 	}
 
 	/*
-	 * This usually means a configuration error
-	 * We use RDMA read/write for packet size > rdma_readwrite_threshold
-	 * as long as it's properly configured we should never get into this
-	 * situation
-	 */
-	if (rqst->rq_nvec + rqst->rq_npages > SMBDIRECT_MAX_SGE) {
-		log_write(ERR, "maximum send segment %x exceeding %x\n",
-			 rqst->rq_nvec + rqst->rq_npages, SMBDIRECT_MAX_SGE);
-		rc = -EINVAL;
-		goto done;
-	}
-
-	/*
-	 * Remove the RFC1002 length defined in MS-SMB2 section 2.1
-	 * It is used only for TCP transport
+	 * Skip the RFC1002 length defined in MS-SMB2 section 2.1
+	 * It is used only for TCP transport in the iov[0]
 	 * In future we may want to add a transport layer under protocol
 	 * layer so this will only be issued to TCP transport
 	 */
-	iov[0].iov_base = (char *)rqst->rq_iov[0].iov_base + 4;
-	iov[0].iov_len = rqst->rq_iov[0].iov_len - 4;
-	buflen += iov[0].iov_len;
+
+	if (rqst->rq_iov[0].iov_len != 4) {
+		log_write(ERR, "expected the pdu length in 1st iov, but got %zu\n", rqst->rq_iov[0].iov_len);
+		return -EINVAL;
+	}
+	iov = &rqst->rq_iov[1];
 
 	/* total up iov array first */
-	for (i = 1; i < rqst->rq_nvec; i++) {
-		iov[i].iov_base = rqst->rq_iov[i].iov_base;
-		iov[i].iov_len = rqst->rq_iov[i].iov_len;
+	for (i = 0; i < rqst->rq_nvec-1; i++) {
 		buflen += iov[i].iov_len;
 	}
 
@@ -2139,6 +2127,10 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
 		goto done;
 	}
 
+	cifs_dbg(FYI, "Sending smb (RDMA): smb_len=%u\n", buflen);
+	for (i = 0; i < rqst->rq_nvec-1; i++)
+		dump_smb(iov[i].iov_base, iov[i].iov_len);
+
 	remaining_data_length = buflen;
 
 	log_write(INFO, "rqst->rq_nvec=%d rqst->rq_npages=%d rq_pagesz=%d "
@@ -2194,12 +2186,14 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
 						goto done;
 				}
 				i++;
+				if (i == rqst->rq_nvec-1)
+					break;
 			}
 			start = i;
 			buflen = 0;
 		} else {
 			i++;
-			if (i == rqst->rq_nvec) {
+			if (i == rqst->rq_nvec-1) {
 				/* send out all remaining vecs */
 				remaining_data_length -= buflen;
 				log_write(INFO,
diff --git a/fs/cifs/trace.c b/fs/cifs/trace.c
new file mode 100644
index 000000000000..bd4a546feec1
--- /dev/null
+++ b/fs/cifs/trace.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *   Copyright (C) 2018, Microsoft Corporation.
+ *
+ *   Author(s): Steve French <stfrench@microsoft.com>
+ *
+ *   This program is free software;  you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
+ *   the GNU General Public License for more details.
+ */
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
new file mode 100644
index 000000000000..61e74d455d90
--- /dev/null
+++ b/fs/cifs/trace.h
@@ -0,0 +1,429 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *   Copyright (C) 2018, Microsoft Corporation.
+ *
+ *   Author(s): Steve French <stfrench@microsoft.com>
+ *
+ *   This program is free software;  you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
+ *   the GNU General Public License for more details.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cifs
+
+#if !defined(_CIFS_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _CIFS_TRACE_H
+
+#include <linux/tracepoint.h>
+
+/* For logging errors in read or write */
+DECLARE_EVENT_CLASS(smb3_rw_err_class,
+	TP_PROTO(unsigned int xid,
+		__u64	fid,
+		__u32	tid,
+		__u64	sesid,
+		__u64	offset,
+		__u32	len,
+		int	rc),
+	TP_ARGS(xid, fid, tid, sesid, offset, len, rc),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u64, fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u64, offset)
+		__field(__u32, len)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->fid = fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->offset = offset;
+		__entry->len = len;
+		__entry->rc = rc;
+	),
+	TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d",
+		__entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+		__entry->offset, __entry->len, __entry->rc)
+)
+
+#define DEFINE_SMB3_RW_ERR_EVENT(name)          \
+DEFINE_EVENT(smb3_rw_err_class, smb3_##name,    \
+	TP_PROTO(unsigned int xid,		\
+		__u64	fid,			\
+		__u32	tid,			\
+		__u64	sesid,			\
+		__u64	offset,			\
+		__u32	len,			\
+		int	rc),			\
+	TP_ARGS(xid, fid, tid, sesid, offset, len, rc))
+
+DEFINE_SMB3_RW_ERR_EVENT(write_err);
+DEFINE_SMB3_RW_ERR_EVENT(read_err);
+
+
+/* For logging successful read or write */
+DECLARE_EVENT_CLASS(smb3_rw_done_class,
+	TP_PROTO(unsigned int xid,
+		__u64	fid,
+		__u32	tid,
+		__u64	sesid,
+		__u64	offset,
+		__u32	len),
+	TP_ARGS(xid, fid, tid, sesid, offset, len),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u64, fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u64, offset)
+		__field(__u32, len)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->fid = fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->offset = offset;
+		__entry->len = len;
+	),
+	TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x",
+		__entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+		__entry->offset, __entry->len)
+)
+
+#define DEFINE_SMB3_RW_DONE_EVENT(name)         \
+DEFINE_EVENT(smb3_rw_done_class, smb3_##name,   \
+	TP_PROTO(unsigned int xid,		\
+		__u64	fid,			\
+		__u32	tid,			\
+		__u64	sesid,			\
+		__u64	offset,			\
+		__u32	len),			\
+	TP_ARGS(xid, fid, tid, sesid, offset, len))
+
+DEFINE_SMB3_RW_DONE_EVENT(write_done);
+DEFINE_SMB3_RW_DONE_EVENT(read_done);
+
+/*
+ * For handle based calls other than read and write, and get/set info
+ */
+DECLARE_EVENT_CLASS(smb3_fd_err_class,
+	TP_PROTO(unsigned int xid,
+		__u64	fid,
+		__u32	tid,
+		__u64	sesid,
+		int	rc),
+	TP_ARGS(xid, fid, tid, sesid, rc),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u64, fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->fid = fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->rc = rc;
+	),
+	TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx rc=%d",
+		__entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+		__entry->rc)
+)
+
+#define DEFINE_SMB3_FD_ERR_EVENT(name)          \
+DEFINE_EVENT(smb3_fd_err_class, smb3_##name,    \
+	TP_PROTO(unsigned int xid,		\
+		__u64	fid,			\
+		__u32	tid,			\
+		__u64	sesid,			\
+		int	rc),			\
+	TP_ARGS(xid, fid, tid, sesid, rc))
+
+DEFINE_SMB3_FD_ERR_EVENT(flush_err);
+DEFINE_SMB3_FD_ERR_EVENT(lock_err);
+DEFINE_SMB3_FD_ERR_EVENT(close_err);
+
+/*
+ * For handle based query/set info calls
+ */
+DECLARE_EVENT_CLASS(smb3_inf_err_class,
+	TP_PROTO(unsigned int xid,
+		__u64	fid,
+		__u32	tid,
+		__u64	sesid,
+		__u8	infclass,
+		__u32	type,
+		int	rc),
+	TP_ARGS(xid, fid, tid, sesid, infclass, type, rc),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u64, fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u8, infclass)
+		__field(__u32, type)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->fid = fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->infclass = infclass;
+		__entry->type = type;
+		__entry->rc = rc;
+	),
+	TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx class=%u type=0x%x rc=%d",
+		__entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+		__entry->infclass, __entry->type, __entry->rc)
+)
+
+#define DEFINE_SMB3_INF_ERR_EVENT(name)          \
+DEFINE_EVENT(smb3_inf_err_class, smb3_##name,    \
+	TP_PROTO(unsigned int xid,		\
+		__u64	fid,			\
+		__u32	tid,			\
+		__u64	sesid,			\
+		__u8	infclass,		\
+		__u32	type,			\
+		int	rc),			\
+	TP_ARGS(xid, fid, tid, sesid, infclass, type, rc))
+
+DEFINE_SMB3_INF_ERR_EVENT(query_info_err);
+DEFINE_SMB3_INF_ERR_EVENT(set_info_err);
+DEFINE_SMB3_INF_ERR_EVENT(fsctl_err);
+
+/*
+ * For logging SMB3 Status code and Command for responses which return errors
+ */
+DECLARE_EVENT_CLASS(smb3_cmd_err_class,
+	TP_PROTO(__u32	tid,
+		__u64	sesid,
+		__u16	cmd,
+		__u64	mid,
+		__u32	status,
+		int	rc),
+	TP_ARGS(tid, sesid, cmd, mid, status, rc),
+	TP_STRUCT__entry(
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u16, cmd)
+		__field(__u64, mid)
+		__field(__u32, status)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->cmd = cmd;
+		__entry->mid = mid;
+		__entry->status = status;
+		__entry->rc = rc;
+	),
+	TP_printk("\tsid=0x%llx tid=0x%x cmd=%u mid=%llu status=0x%x rc=%d",
+		__entry->sesid, __entry->tid, __entry->cmd, __entry->mid,
+		__entry->status, __entry->rc)
+)
+
+#define DEFINE_SMB3_CMD_ERR_EVENT(name)          \
+DEFINE_EVENT(smb3_cmd_err_class, smb3_##name,    \
+	TP_PROTO(__u32	tid,			\
+		__u64	sesid,			\
+		__u16	cmd,			\
+		__u64	mid,			\
+		__u32	status,			\
+		int	rc),			\
+	TP_ARGS(tid, sesid, cmd, mid, status, rc))
+
+DEFINE_SMB3_CMD_ERR_EVENT(cmd_err);
+
+DECLARE_EVENT_CLASS(smb3_cmd_done_class,
+	TP_PROTO(__u32	tid,
+		__u64	sesid,
+		__u16	cmd,
+		__u64	mid),
+	TP_ARGS(tid, sesid, cmd, mid),
+	TP_STRUCT__entry(
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u16, cmd)
+		__field(__u64, mid)
+	),
+	TP_fast_assign(
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->cmd = cmd;
+		__entry->mid = mid;
+	),
+	TP_printk("\tsid=0x%llx tid=0x%x cmd=%u mid=%llu",
+		__entry->sesid, __entry->tid,
+		__entry->cmd, __entry->mid)
+)
+
+#define DEFINE_SMB3_CMD_DONE_EVENT(name)          \
+DEFINE_EVENT(smb3_cmd_done_class, smb3_##name,    \
+	TP_PROTO(__u32	tid,			\
+		__u64	sesid,			\
+		__u16	cmd,			\
+		__u64	mid),			\
+	TP_ARGS(tid, sesid, cmd, mid))
+
+DEFINE_SMB3_CMD_DONE_EVENT(cmd_done);
+
+DECLARE_EVENT_CLASS(smb3_exit_err_class,
+	TP_PROTO(unsigned int xid,
+		const char *func_name,
+		int	rc),
+	TP_ARGS(xid, func_name, rc),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(const char *, func_name)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->func_name = func_name;
+		__entry->rc = rc;
+	),
+	TP_printk("\t%s: xid=%u rc=%d",
+		__entry->func_name, __entry->xid, __entry->rc)
+)
+
+#define DEFINE_SMB3_EXIT_ERR_EVENT(name)          \
+DEFINE_EVENT(smb3_exit_err_class, smb3_##name,    \
+	TP_PROTO(unsigned int xid,		\
+		const char *func_name,		\
+		int	rc),			\
+	TP_ARGS(xid, func_name, rc))
+
+DEFINE_SMB3_EXIT_ERR_EVENT(exit_err);
+
+DECLARE_EVENT_CLASS(smb3_enter_exit_class,
+	TP_PROTO(unsigned int xid,
+		const char *func_name),
+	TP_ARGS(xid, func_name),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(const char *, func_name)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->func_name = func_name;
+	),
+	TP_printk("\t%s: xid=%u",
+		__entry->func_name, __entry->xid)
+)
+
+#define DEFINE_SMB3_ENTER_EXIT_EVENT(name)        \
+DEFINE_EVENT(smb3_enter_exit_class, smb3_##name,  \
+	TP_PROTO(unsigned int xid,		\
+		const char *func_name),		\
+	TP_ARGS(xid, func_name))
+
+DEFINE_SMB3_ENTER_EXIT_EVENT(enter);
+DEFINE_SMB3_ENTER_EXIT_EVENT(exit_done);
+
+/*
+ * For smb2/smb3 open call
+ */
+DECLARE_EVENT_CLASS(smb3_open_err_class,
+	TP_PROTO(unsigned int xid,
+		__u32	tid,
+		__u64	sesid,
+		int	create_options,
+		int	desired_access,
+		int	rc),
+	TP_ARGS(xid, tid, sesid, create_options, desired_access, rc),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(int,   create_options)
+		__field(int, desired_access)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->create_options = create_options;
+		__entry->desired_access = desired_access;
+		__entry->rc = rc;
+	),
+	TP_printk("xid=%u sid=0x%llx tid=0x%x cr_opts=0x%x des_access=0x%x rc=%d",
+		__entry->xid, __entry->sesid, __entry->tid,
+		__entry->create_options, __entry->desired_access, __entry->rc)
+)
+
+#define DEFINE_SMB3_OPEN_ERR_EVENT(name)          \
+DEFINE_EVENT(smb3_open_err_class, smb3_##name,    \
+	TP_PROTO(unsigned int xid,		\
+		__u32	tid,			\
+		__u64	sesid,			\
+		int	create_options,		\
+		int	desired_access,		\
+		int	rc),			\
+	TP_ARGS(xid, tid, sesid, create_options, desired_access, rc))
+
+DEFINE_SMB3_OPEN_ERR_EVENT(open_err);
+
+
+DECLARE_EVENT_CLASS(smb3_open_done_class,
+	TP_PROTO(unsigned int xid,
+		__u64	fid,
+		__u32	tid,
+		__u64	sesid,
+		int	create_options,
+		int	desired_access),
+	TP_ARGS(xid, fid, tid, sesid, create_options, desired_access),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u64, fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(int, create_options)
+		__field(int, desired_access)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->fid = fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->create_options = create_options;
+		__entry->desired_access = desired_access;
+	),
+	TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx cr_opts=0x%x des_access=0x%x",
+		__entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+		__entry->create_options, __entry->desired_access)
+)
+
+#define DEFINE_SMB3_OPEN_DONE_EVENT(name)        \
+DEFINE_EVENT(smb3_open_done_class, smb3_##name,  \
+	TP_PROTO(unsigned int xid,		\
+		__u64	fid,			\
+		__u32	tid,			\
+		__u64	sesid,			\
+		int	create_options,		\
+		int	desired_access),	\
+	TP_ARGS(xid, fid, tid, sesid, create_options, desired_access))
+
+DEFINE_SMB3_OPEN_DONE_EVENT(open_done);
+
+#endif /* _CIFS_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 8f6f25918229..e7254e386b79 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -753,7 +753,7 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 		goto out;
 
 #ifdef CONFIG_CIFS_SMB311
-	if (ses->status == CifsNew)
+	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
 		smb311_update_preauth_hash(ses, rqst->rq_iov+1,
 					   rqst->rq_nvec-1);
 #endif
@@ -798,10 +798,10 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 		*resp_buf_type = CIFS_SMALL_BUFFER;
 
 #ifdef CONFIG_CIFS_SMB311
-	if (ses->status == CifsNew) {
+	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
 		struct kvec iov = {
-			.iov_base = buf + 4,
-			.iov_len = get_rfc1002_length(buf)
+			.iov_base = buf,
+			.iov_len = midQ->resp_buf_size
 		};
 		smb311_update_preauth_hash(ses, &iov, 1);
 	}
@@ -834,8 +834,11 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	if (n_vec + 1 > CIFS_MAX_IOV_SIZE) {
 		new_iov = kmalloc(sizeof(struct kvec) * (n_vec + 1),
 				  GFP_KERNEL);
-		if (!new_iov)
+		if (!new_iov) {
+			/* otherwise cifs_send_recv below sets resp_buf_type */
+			*resp_buf_type = CIFS_NO_BUFFER;
 			return -ENOMEM;
+		}
 	} else
 		new_iov = s_iov;
 
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 017b0ab19bc4..c4fb9ad7c808 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -492,7 +492,7 @@ static void cramfs_kill_sb(struct super_block *sb)
 {
 	struct cramfs_sb_info *sbi = CRAMFS_SB(sb);
 
-	if (IS_ENABLED(CCONFIG_CRAMFS_MTD) && sb->s_mtd) {
+	if (IS_ENABLED(CONFIG_CRAMFS_MTD) && sb->s_mtd) {
 		if (sbi && sbi->mtd_point_size)
 			mtd_unpoint(sb->s_mtd, 0, sbi->mtd_point_size);
 		kill_mtd_super(sb);
@@ -808,10 +808,7 @@ static struct dentry *cramfs_lookup(struct inode *dir, struct dentry *dentry, un
 	}
 out:
 	mutex_unlock(&read_mutex);
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 static int cramfs_readpage(struct file *file, struct page *page)
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index ce654526c0fb..243a269e6c5f 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -156,12 +156,8 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
 	}
 
 	req = skcipher_request_alloc(tfm, gfp_flags);
-	if (!req) {
-		printk_ratelimited(KERN_ERR
-				"%s: crypto_request_alloc() failed\n",
-				__func__);
+	if (!req)
 		return -ENOMEM;
-	}
 
 	skcipher_request_set_callback(
 		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
@@ -178,9 +174,10 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
 		res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
 	skcipher_request_free(req);
 	if (res) {
-		printk_ratelimited(KERN_ERR
-			"%s: crypto_skcipher_encrypt() returned %d\n",
-			__func__, res);
+		fscrypt_err(inode->i_sb,
+			    "%scryption failed for inode %lu, block %llu: %d",
+			    (rw == FS_DECRYPT ? "de" : "en"),
+			    inode->i_ino, lblk_num, res);
 		return res;
 	}
 	return 0;
@@ -326,7 +323,6 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 		return 0;
 	}
 
-	/* this should eventually be an flag in d_flags */
 	spin_lock(&dentry->d_lock);
 	cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
 	spin_unlock(&dentry->d_lock);
@@ -353,7 +349,6 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 const struct dentry_operations fscrypt_d_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
 };
-EXPORT_SYMBOL(fscrypt_d_ops);
 
 void fscrypt_restore_control_page(struct page *page)
 {
@@ -422,13 +417,43 @@ fail:
 	return res;
 }
 
+void fscrypt_msg(struct super_block *sb, const char *level,
+		 const char *fmt, ...)
+{
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+	struct va_format vaf;
+	va_list args;
+
+	if (!__ratelimit(&rs))
+		return;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	if (sb)
+		printk("%sfscrypt (%s): %pV\n", level, sb->s_id, &vaf);
+	else
+		printk("%sfscrypt: %pV\n", level, &vaf);
+	va_end(args);
+}
+
 /**
  * fscrypt_init() - Set up for fs encryption.
  */
 static int __init fscrypt_init(void)
 {
+	/*
+	 * Use an unbound workqueue to allow bios to be decrypted in parallel
+	 * even when they happen to complete on the same CPU.  This sacrifices
+	 * locality, but it's worthwhile since decryption is CPU-intensive.
+	 *
+	 * Also use a high-priority workqueue to prioritize decryption work,
+	 * which blocks reads from completing, over regular application tasks.
+	 */
 	fscrypt_read_workqueue = alloc_workqueue("fscrypt_read_queue",
-							WQ_HIGHPRI, 0);
+						 WQ_UNBOUND | WQ_HIGHPRI,
+						 num_online_cpus());
 	if (!fscrypt_read_workqueue)
 		goto fail;
 
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index e33f3d3c5ade..d7a0f682ca12 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -59,11 +59,8 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname,
 
 	/* Set up the encryption request */
 	req = skcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		printk_ratelimited(KERN_ERR
-			"%s: skcipher_request_alloc() failed\n", __func__);
+	if (!req)
 		return -ENOMEM;
-	}
 	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			crypto_req_done, &wait);
@@ -74,8 +71,9 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname,
 	res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
 	skcipher_request_free(req);
 	if (res < 0) {
-		printk_ratelimited(KERN_ERR
-				"%s: Error (error code %d)\n", __func__, res);
+		fscrypt_err(inode->i_sb,
+			    "Filename encryption failed for inode %lu: %d",
+			    inode->i_ino, res);
 		return res;
 	}
 
@@ -96,23 +94,14 @@ static int fname_decrypt(struct inode *inode,
 	struct skcipher_request *req = NULL;
 	DECLARE_CRYPTO_WAIT(wait);
 	struct scatterlist src_sg, dst_sg;
-	struct fscrypt_info *ci = inode->i_crypt_info;
-	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = inode->i_crypt_info->ci_ctfm;
 	int res = 0;
 	char iv[FS_CRYPTO_BLOCK_SIZE];
-	unsigned lim;
-
-	lim = inode->i_sb->s_cop->max_namelen(inode);
-	if (iname->len <= 0 || iname->len > lim)
-		return -EIO;
 
 	/* Allocate request */
 	req = skcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		printk_ratelimited(KERN_ERR
-			"%s: crypto_request_alloc() failed\n",  __func__);
+	if (!req)
 		return -ENOMEM;
-	}
 	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		crypto_req_done, &wait);
@@ -127,8 +116,9 @@ static int fname_decrypt(struct inode *inode,
 	res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait);
 	skcipher_request_free(req);
 	if (res < 0) {
-		printk_ratelimited(KERN_ERR
-				"%s: Error (error code %d)\n", __func__, res);
+		fscrypt_err(inode->i_sb,
+			    "Filename decryption failed for inode %lu: %d",
+			    inode->i_ino, res);
 		return res;
 	}
 
@@ -341,12 +331,12 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		return 0;
 	}
 	ret = fscrypt_get_encryption_info(dir);
-	if (ret && ret != -EOPNOTSUPP)
+	if (ret)
 		return ret;
 
 	if (dir->i_crypt_info) {
 		if (!fscrypt_fname_encrypted_size(dir, iname->len,
-						  dir->i_sb->s_cop->max_namelen(dir),
+						  dir->i_sb->s_cop->max_namelen,
 						  &fname->crypto_buf.len))
 			return -ENAMETOOLONG;
 		fname->crypto_buf.name = kmalloc(fname->crypto_buf.len,
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index ad6722bae8b7..37562394c5de 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -18,15 +18,7 @@
 
 /* Encryption parameters */
 #define FS_IV_SIZE			16
-#define FS_AES_128_ECB_KEY_SIZE		16
-#define FS_AES_128_CBC_KEY_SIZE		16
-#define FS_AES_128_CTS_KEY_SIZE		16
-#define FS_AES_256_GCM_KEY_SIZE		32
-#define FS_AES_256_CBC_KEY_SIZE		32
-#define FS_AES_256_CTS_KEY_SIZE		32
-#define FS_AES_256_XTS_KEY_SIZE		64
-
-#define FS_KEY_DERIVATION_NONCE_SIZE		16
+#define FS_KEY_DERIVATION_NONCE_SIZE	16
 
 /**
  * Encryption context for inode
@@ -91,6 +83,10 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode,
 	    filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS)
 		return true;
 
+	if (contents_mode == FS_ENCRYPTION_MODE_SPECK128_256_XTS &&
+	    filenames_mode == FS_ENCRYPTION_MODE_SPECK128_256_CTS)
+		return true;
+
 	return false;
 }
 
@@ -106,6 +102,15 @@ extern int fscrypt_do_page_crypto(const struct inode *inode,
 				  gfp_t gfp_flags);
 extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
 					      gfp_t gfp_flags);
+extern const struct dentry_operations fscrypt_d_ops;
+
+extern void __printf(3, 4) __cold
+fscrypt_msg(struct super_block *sb, const char *level, const char *fmt, ...);
+
+#define fscrypt_warn(sb, fmt, ...)		\
+	fscrypt_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__)
+#define fscrypt_err(sb, fmt, ...)		\
+	fscrypt_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__)
 
 /* fname.c */
 extern int fname_encrypt(struct inode *inode, const struct qstr *iname,
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index bec06490fb13..926e5df20ec3 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -39,8 +39,9 @@ int fscrypt_file_open(struct inode *inode, struct file *filp)
 	dir = dget_parent(file_dentry(filp));
 	if (IS_ENCRYPTED(d_inode(dir)) &&
 	    !fscrypt_has_permitted_context(d_inode(dir), inode)) {
-		pr_warn_ratelimited("fscrypt: inconsistent encryption contexts: %lu/%lu",
-				    d_inode(dir)->i_ino, inode->i_ino);
+		fscrypt_warn(inode->i_sb,
+			     "inconsistent encryption contexts: %lu/%lu",
+			     d_inode(dir)->i_ino, inode->i_ino);
 		err = -EPERM;
 	}
 	dput(dir);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 05f5ee1f0705..e997ca51192f 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -19,17 +19,16 @@
 
 static struct crypto_shash *essiv_hash_tfm;
 
-/**
- * derive_key_aes() - Derive a key using AES-128-ECB
- * @deriving_key: Encryption key used for derivation.
- * @source_key:   Source key to which to apply derivation.
- * @derived_raw_key:  Derived raw key.
+/*
+ * Key derivation function.  This generates the derived key by encrypting the
+ * master key with AES-128-ECB using the inode's nonce as the AES key.
  *
- * Return: Zero on success; non-zero otherwise.
+ * The master key must be at least as long as the derived key.  If the master
+ * key is longer, then only the first 'derived_keysize' bytes are used.
  */
-static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
-				const struct fscrypt_key *source_key,
-				u8 derived_raw_key[FS_MAX_KEY_SIZE])
+static int derive_key_aes(const u8 *master_key,
+			  const struct fscrypt_context *ctx,
+			  u8 *derived_key, unsigned int derived_keysize)
 {
 	int res = 0;
 	struct skcipher_request *req = NULL;
@@ -51,14 +50,13 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
 	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			crypto_req_done, &wait);
-	res = crypto_skcipher_setkey(tfm, deriving_key,
-					FS_AES_128_ECB_KEY_SIZE);
+	res = crypto_skcipher_setkey(tfm, ctx->nonce, sizeof(ctx->nonce));
 	if (res < 0)
 		goto out;
 
-	sg_init_one(&src_sg, source_key->raw, source_key->size);
-	sg_init_one(&dst_sg, derived_raw_key, source_key->size);
-	skcipher_request_set_crypt(req, &src_sg, &dst_sg, source_key->size,
+	sg_init_one(&src_sg, master_key, derived_keysize);
+	sg_init_one(&dst_sg, derived_key, derived_keysize);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, derived_keysize,
 				   NULL);
 	res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
 out:
@@ -67,101 +65,147 @@ out:
 	return res;
 }
 
-static int validate_user_key(struct fscrypt_info *crypt_info,
-			struct fscrypt_context *ctx, u8 *raw_key,
-			const char *prefix, int min_keysize)
+/*
+ * Search the current task's subscribed keyrings for a "logon" key with
+ * description prefix:descriptor, and if found acquire a read lock on it and
+ * return a pointer to its validated payload in *payload_ret.
+ */
+static struct key *
+find_and_lock_process_key(const char *prefix,
+			  const u8 descriptor[FS_KEY_DESCRIPTOR_SIZE],
+			  unsigned int min_keysize,
+			  const struct fscrypt_key **payload_ret)
 {
 	char *description;
-	struct key *keyring_key;
-	struct fscrypt_key *master_key;
+	struct key *key;
 	const struct user_key_payload *ukp;
-	int res;
+	const struct fscrypt_key *payload;
 
 	description = kasprintf(GFP_NOFS, "%s%*phN", prefix,
-				FS_KEY_DESCRIPTOR_SIZE,
-				ctx->master_key_descriptor);
+				FS_KEY_DESCRIPTOR_SIZE, descriptor);
 	if (!description)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	keyring_key = request_key(&key_type_logon, description, NULL);
+	key = request_key(&key_type_logon, description, NULL);
 	kfree(description);
-	if (IS_ERR(keyring_key))
-		return PTR_ERR(keyring_key);
-	down_read(&keyring_key->sem);
-
-	if (keyring_key->type != &key_type_logon) {
-		printk_once(KERN_WARNING
-				"%s: key type must be logon\n", __func__);
-		res = -ENOKEY;
-		goto out;
-	}
-	ukp = user_key_payload_locked(keyring_key);
-	if (!ukp) {
-		/* key was revoked before we acquired its semaphore */
-		res = -EKEYREVOKED;
-		goto out;
+	if (IS_ERR(key))
+		return key;
+
+	down_read(&key->sem);
+	ukp = user_key_payload_locked(key);
+
+	if (!ukp) /* was the key revoked before we acquired its semaphore? */
+		goto invalid;
+
+	payload = (const struct fscrypt_key *)ukp->data;
+
+	if (ukp->datalen != sizeof(struct fscrypt_key) ||
+	    payload->size < 1 || payload->size > FS_MAX_KEY_SIZE) {
+		fscrypt_warn(NULL,
+			     "key with description '%s' has invalid payload",
+			     key->description);
+		goto invalid;
 	}
-	if (ukp->datalen != sizeof(struct fscrypt_key)) {
-		res = -EINVAL;
-		goto out;
+
+	if (payload->size < min_keysize) {
+		fscrypt_warn(NULL,
+			     "key with description '%s' is too short (got %u bytes, need %u+ bytes)",
+			     key->description, payload->size, min_keysize);
+		goto invalid;
 	}
-	master_key = (struct fscrypt_key *)ukp->data;
-	BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
-
-	if (master_key->size < min_keysize || master_key->size > FS_MAX_KEY_SIZE
-	    || master_key->size % AES_BLOCK_SIZE != 0) {
-		printk_once(KERN_WARNING
-				"%s: key size incorrect: %d\n",
-				__func__, master_key->size);
-		res = -ENOKEY;
-		goto out;
+
+	*payload_ret = payload;
+	return key;
+
+invalid:
+	up_read(&key->sem);
+	key_put(key);
+	return ERR_PTR(-ENOKEY);
+}
+
+/* Find the master key, then derive the inode's actual encryption key */
+static int find_and_derive_key(const struct inode *inode,
+			       const struct fscrypt_context *ctx,
+			       u8 *derived_key, unsigned int derived_keysize)
+{
+	struct key *key;
+	const struct fscrypt_key *payload;
+	int err;
+
+	key = find_and_lock_process_key(FS_KEY_DESC_PREFIX,
+					ctx->master_key_descriptor,
+					derived_keysize, &payload);
+	if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) {
+		key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix,
+						ctx->master_key_descriptor,
+						derived_keysize, &payload);
 	}
-	res = derive_key_aes(ctx->nonce, master_key, raw_key);
-out:
-	up_read(&keyring_key->sem);
-	key_put(keyring_key);
-	return res;
+	if (IS_ERR(key))
+		return PTR_ERR(key);
+	err = derive_key_aes(payload->raw, ctx, derived_key, derived_keysize);
+	up_read(&key->sem);
+	key_put(key);
+	return err;
 }
 
-static const struct {
+static struct fscrypt_mode {
+	const char *friendly_name;
 	const char *cipher_str;
 	int keysize;
+	bool logged_impl_name;
 } available_modes[] = {
-	[FS_ENCRYPTION_MODE_AES_256_XTS] = { "xts(aes)",
-					     FS_AES_256_XTS_KEY_SIZE },
-	[FS_ENCRYPTION_MODE_AES_256_CTS] = { "cts(cbc(aes))",
-					     FS_AES_256_CTS_KEY_SIZE },
-	[FS_ENCRYPTION_MODE_AES_128_CBC] = { "cbc(aes)",
-					     FS_AES_128_CBC_KEY_SIZE },
-	[FS_ENCRYPTION_MODE_AES_128_CTS] = { "cts(cbc(aes))",
-					     FS_AES_128_CTS_KEY_SIZE },
+	[FS_ENCRYPTION_MODE_AES_256_XTS] = {
+		.friendly_name = "AES-256-XTS",
+		.cipher_str = "xts(aes)",
+		.keysize = 64,
+	},
+	[FS_ENCRYPTION_MODE_AES_256_CTS] = {
+		.friendly_name = "AES-256-CTS-CBC",
+		.cipher_str = "cts(cbc(aes))",
+		.keysize = 32,
+	},
+	[FS_ENCRYPTION_MODE_AES_128_CBC] = {
+		.friendly_name = "AES-128-CBC",
+		.cipher_str = "cbc(aes)",
+		.keysize = 16,
+	},
+	[FS_ENCRYPTION_MODE_AES_128_CTS] = {
+		.friendly_name = "AES-128-CTS-CBC",
+		.cipher_str = "cts(cbc(aes))",
+		.keysize = 16,
+	},
+	[FS_ENCRYPTION_MODE_SPECK128_256_XTS] = {
+		.friendly_name = "Speck128/256-XTS",
+		.cipher_str = "xts(speck128)",
+		.keysize = 64,
+	},
+	[FS_ENCRYPTION_MODE_SPECK128_256_CTS] = {
+		.friendly_name = "Speck128/256-CTS-CBC",
+		.cipher_str = "cts(cbc(speck128))",
+		.keysize = 32,
+	},
 };
 
-static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode,
-				 const char **cipher_str_ret, int *keysize_ret)
+static struct fscrypt_mode *
+select_encryption_mode(const struct fscrypt_info *ci, const struct inode *inode)
 {
-	u32 mode;
-
 	if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) {
-		pr_warn_ratelimited("fscrypt: inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)\n",
-				    inode->i_ino,
-				    ci->ci_data_mode, ci->ci_filename_mode);
-		return -EINVAL;
+		fscrypt_warn(inode->i_sb,
+			     "inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)",
+			     inode->i_ino, ci->ci_data_mode,
+			     ci->ci_filename_mode);
+		return ERR_PTR(-EINVAL);
 	}
 
-	if (S_ISREG(inode->i_mode)) {
-		mode = ci->ci_data_mode;
-	} else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
-		mode = ci->ci_filename_mode;
-	} else {
-		WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
-			  inode->i_ino, (inode->i_mode & S_IFMT));
-		return -EINVAL;
-	}
+	if (S_ISREG(inode->i_mode))
+		return &available_modes[ci->ci_data_mode];
+
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		return &available_modes[ci->ci_filename_mode];
 
-	*cipher_str_ret = available_modes[mode].cipher_str;
-	*keysize_ret = available_modes[mode].keysize;
-	return 0;
+	WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
+		  inode->i_ino, (inode->i_mode & S_IFMT));
+	return ERR_PTR(-EINVAL);
 }
 
 static void put_crypt_info(struct fscrypt_info *ci)
@@ -184,8 +228,9 @@ static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt)
 
 		tfm = crypto_alloc_shash("sha256", 0, 0);
 		if (IS_ERR(tfm)) {
-			pr_warn_ratelimited("fscrypt: error allocating SHA-256 transform: %ld\n",
-					    PTR_ERR(tfm));
+			fscrypt_warn(NULL,
+				     "error allocating SHA-256 transform: %ld",
+				     PTR_ERR(tfm));
 			return PTR_ERR(tfm);
 		}
 		prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm);
@@ -245,8 +290,7 @@ int fscrypt_get_encryption_info(struct inode *inode)
 	struct fscrypt_info *crypt_info;
 	struct fscrypt_context ctx;
 	struct crypto_skcipher *ctfm;
-	const char *cipher_str;
-	int keysize;
+	struct fscrypt_mode *mode;
 	u8 *raw_key = NULL;
 	int res;
 
@@ -290,57 +334,59 @@ int fscrypt_get_encryption_info(struct inode *inode)
 	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
 				sizeof(crypt_info->ci_master_key));
 
-	res = determine_cipher_type(crypt_info, inode, &cipher_str, &keysize);
-	if (res)
+	mode = select_encryption_mode(crypt_info, inode);
+	if (IS_ERR(mode)) {
+		res = PTR_ERR(mode);
 		goto out;
+	}
 
 	/*
 	 * This cannot be a stack buffer because it is passed to the scatterlist
 	 * crypto API as part of key derivation.
 	 */
 	res = -ENOMEM;
-	raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS);
+	raw_key = kmalloc(mode->keysize, GFP_NOFS);
 	if (!raw_key)
 		goto out;
 
-	res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX,
-				keysize);
-	if (res && inode->i_sb->s_cop->key_prefix) {
-		int res2 = validate_user_key(crypt_info, &ctx, raw_key,
-					     inode->i_sb->s_cop->key_prefix,
-					     keysize);
-		if (res2) {
-			if (res2 == -ENOKEY)
-				res = -ENOKEY;
-			goto out;
-		}
-	} else if (res) {
+	res = find_and_derive_key(inode, &ctx, raw_key, mode->keysize);
+	if (res)
 		goto out;
-	}
-	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
-	if (!ctfm || IS_ERR(ctfm)) {
-		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
-		pr_debug("%s: error %d (inode %lu) allocating crypto tfm\n",
-			 __func__, res, inode->i_ino);
+
+	ctfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0);
+	if (IS_ERR(ctfm)) {
+		res = PTR_ERR(ctfm);
+		fscrypt_warn(inode->i_sb,
+			     "error allocating '%s' transform for inode %lu: %d",
+			     mode->cipher_str, inode->i_ino, res);
 		goto out;
 	}
+	if (unlikely(!mode->logged_impl_name)) {
+		/*
+		 * fscrypt performance can vary greatly depending on which
+		 * crypto algorithm implementation is used.  Help people debug
+		 * performance problems by logging the ->cra_driver_name the
+		 * first time a mode is used.  Note that multiple threads can
+		 * race here, but it doesn't really matter.
+		 */
+		mode->logged_impl_name = true;
+		pr_info("fscrypt: %s using implementation \"%s\"\n",
+			mode->friendly_name,
+			crypto_skcipher_alg(ctfm)->base.cra_driver_name);
+	}
 	crypt_info->ci_ctfm = ctfm;
-	crypto_skcipher_clear_flags(ctfm, ~0);
 	crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	/*
-	 * if the provided key is longer than keysize, we use the first
-	 * keysize bytes of the derived key only
-	 */
-	res = crypto_skcipher_setkey(ctfm, raw_key, keysize);
+	res = crypto_skcipher_setkey(ctfm, raw_key, mode->keysize);
 	if (res)
 		goto out;
 
 	if (S_ISREG(inode->i_mode) &&
 	    crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) {
-		res = init_essiv_generator(crypt_info, raw_key, keysize);
+		res = init_essiv_generator(crypt_info, raw_key, mode->keysize);
 		if (res) {
-			pr_debug("%s: error %d (inode %lu) allocating essiv tfm\n",
-				 __func__, res, inode->i_ino);
+			fscrypt_warn(inode->i_sb,
+				     "error initializing ESSIV generator for inode %lu: %d",
+				     inode->i_ino, res);
 			goto out;
 		}
 	}
diff --git a/fs/dax.c b/fs/dax.c
index aaec72ded1b6..aa86d9f971a4 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -677,7 +677,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
 		 * downgrading page table protection not changing it to point
 		 * to a new page.
 		 *
-		 * See Documentation/vm/mmu_notifier.txt
+		 * See Documentation/vm/mmu_notifier.rst
 		 */
 		if (pmdp) {
 #ifdef CONFIG_FS_DAX_PMD
diff --git a/fs/dcache.c b/fs/dcache.c
index 86d2de63461e..0e8e5de3c48a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -580,6 +580,7 @@ static void __dentry_kill(struct dentry *dentry)
 	spin_unlock(&dentry->d_lock);
 	if (likely(can_free))
 		dentry_free(dentry);
+	cond_resched();
 }
 
 static struct dentry *__lock_parent(struct dentry *dentry)
@@ -827,30 +828,24 @@ static inline bool fast_dput(struct dentry *dentry)
  */
 void dput(struct dentry *dentry)
 {
-	if (unlikely(!dentry))
-		return;
+	while (dentry) {
+		might_sleep();
 
-repeat:
-	might_sleep();
+		rcu_read_lock();
+		if (likely(fast_dput(dentry))) {
+			rcu_read_unlock();
+			return;
+		}
 
-	rcu_read_lock();
-	if (likely(fast_dput(dentry))) {
+		/* Slow case: now with the dentry lock held */
 		rcu_read_unlock();
-		return;
-	}
-
-	/* Slow case: now with the dentry lock held */
-	rcu_read_unlock();
 
-	if (likely(retain_dentry(dentry))) {
-		spin_unlock(&dentry->d_lock);
-		return;
-	}
+		if (likely(retain_dentry(dentry))) {
+			spin_unlock(&dentry->d_lock);
+			return;
+		}
 
-	dentry = dentry_kill(dentry);
-	if (dentry) {
-		cond_resched();
-		goto repeat;
+		dentry = dentry_kill(dentry);
 	}
 }
 EXPORT_SYMBOL(dput);
@@ -907,6 +902,35 @@ repeat:
 }
 EXPORT_SYMBOL(dget_parent);
 
+static struct dentry * __d_find_any_alias(struct inode *inode)
+{
+	struct dentry *alias;
+
+	if (hlist_empty(&inode->i_dentry))
+		return NULL;
+	alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
+	__dget(alias);
+	return alias;
+}
+
+/**
+ * d_find_any_alias - find any alias for a given inode
+ * @inode: inode to find an alias for
+ *
+ * If any aliases exist for the given inode, take and return a
+ * reference for one of them.  If no aliases exist, return %NULL.
+ */
+struct dentry *d_find_any_alias(struct inode *inode)
+{
+	struct dentry *de;
+
+	spin_lock(&inode->i_lock);
+	de = __d_find_any_alias(inode);
+	spin_unlock(&inode->i_lock);
+	return de;
+}
+EXPORT_SYMBOL(d_find_any_alias);
+
 /**
  * d_find_alias - grab a hashed alias of inode
  * @inode: inode in question
@@ -923,34 +947,19 @@ EXPORT_SYMBOL(dget_parent);
  */
 static struct dentry *__d_find_alias(struct inode *inode)
 {
-	struct dentry *alias, *discon_alias;
+	struct dentry *alias;
+
+	if (S_ISDIR(inode->i_mode))
+		return __d_find_any_alias(inode);
 
-again:
-	discon_alias = NULL;
 	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		spin_lock(&alias->d_lock);
- 		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
-			if (IS_ROOT(alias) &&
-			    (alias->d_flags & DCACHE_DISCONNECTED)) {
-				discon_alias = alias;
-			} else {
-				__dget_dlock(alias);
-				spin_unlock(&alias->d_lock);
-				return alias;
-			}
-		}
-		spin_unlock(&alias->d_lock);
-	}
-	if (discon_alias) {
-		alias = discon_alias;
-		spin_lock(&alias->d_lock);
-		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
+ 		if (!d_unhashed(alias)) {
 			__dget_dlock(alias);
 			spin_unlock(&alias->d_lock);
 			return alias;
 		}
 		spin_unlock(&alias->d_lock);
-		goto again;
 	}
 	return NULL;
 }
@@ -1052,8 +1061,6 @@ static void shrink_dentry_list(struct list_head *list)
 	while (!list_empty(list)) {
 		struct dentry *dentry, *parent;
 
-		cond_resched();
-
 		dentry = list_entry(list->prev, struct dentry, d_lru);
 		spin_lock(&dentry->d_lock);
 		rcu_read_lock();
@@ -1230,13 +1237,11 @@ enum d_walk_ret {
  * @parent:	start of walk
  * @data:	data passed to @enter() and @finish()
  * @enter:	callback when first entering the dentry
- * @finish:	callback when successfully finished the walk
  *
- * The @enter() and @finish() callbacks are called with d_lock held.
+ * The @enter() callbacks are called with d_lock held.
  */
 static void d_walk(struct dentry *parent, void *data,
-		   enum d_walk_ret (*enter)(void *, struct dentry *),
-		   void (*finish)(void *))
+		   enum d_walk_ret (*enter)(void *, struct dentry *))
 {
 	struct dentry *this_parent;
 	struct list_head *next;
@@ -1325,8 +1330,6 @@ ascend:
 	if (need_seqretry(&rename_lock, seq))
 		goto rename_retry;
 	rcu_read_unlock();
-	if (finish)
-		finish(data);
 
 out_unlock:
 	spin_unlock(&this_parent->d_lock);
@@ -1375,7 +1378,7 @@ int path_has_submounts(const struct path *parent)
 	struct check_mount data = { .mnt = parent->mnt, .mounted = 0 };
 
 	read_seqlock_excl(&mount_lock);
-	d_walk(parent->dentry, &data, path_check_mount, NULL);
+	d_walk(parent->dentry, &data, path_check_mount);
 	read_sequnlock_excl(&mount_lock);
 
 	return data.mounted;
@@ -1483,11 +1486,16 @@ void shrink_dcache_parent(struct dentry *parent)
 		data.start = parent;
 		data.found = 0;
 
-		d_walk(parent, &data, select_collect, NULL);
+		d_walk(parent, &data, select_collect);
+
+		if (!list_empty(&data.dispose)) {
+			shrink_dentry_list(&data.dispose);
+			continue;
+		}
+
+		cond_resched();
 		if (!data.found)
 			break;
-
-		shrink_dentry_list(&data.dispose);
 	}
 }
 EXPORT_SYMBOL(shrink_dcache_parent);
@@ -1518,7 +1526,7 @@ static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
 static void do_one_tree(struct dentry *dentry)
 {
 	shrink_dcache_parent(dentry);
-	d_walk(dentry, dentry, umount_check, NULL);
+	d_walk(dentry, dentry, umount_check);
 	d_drop(dentry);
 	dput(dentry);
 }
@@ -1542,78 +1550,48 @@ void shrink_dcache_for_umount(struct super_block *sb)
 	}
 }
 
-struct detach_data {
-	struct select_data select;
-	struct dentry *mountpoint;
-};
-static enum d_walk_ret detach_and_collect(void *_data, struct dentry *dentry)
+static enum d_walk_ret find_submount(void *_data, struct dentry *dentry)
 {
-	struct detach_data *data = _data;
-
+	struct dentry **victim = _data;
 	if (d_mountpoint(dentry)) {
 		__dget_dlock(dentry);
-		data->mountpoint = dentry;
+		*victim = dentry;
 		return D_WALK_QUIT;
 	}
-
-	return select_collect(&data->select, dentry);
-}
-
-static void check_and_drop(void *_data)
-{
-	struct detach_data *data = _data;
-
-	if (!data->mountpoint && list_empty(&data->select.dispose))
-		__d_drop(data->select.start);
+	return D_WALK_CONTINUE;
 }
 
 /**
  * d_invalidate - detach submounts, prune dcache, and drop
  * @dentry: dentry to invalidate (aka detach, prune and drop)
- *
- * no dcache lock.
- *
- * The final d_drop is done as an atomic operation relative to
- * rename_lock ensuring there are no races with d_set_mounted.  This
- * ensures there are no unhashed dentries on the path to a mountpoint.
  */
 void d_invalidate(struct dentry *dentry)
 {
-	/*
-	 * If it's already been dropped, return OK.
-	 */
+	bool had_submounts = false;
 	spin_lock(&dentry->d_lock);
 	if (d_unhashed(dentry)) {
 		spin_unlock(&dentry->d_lock);
 		return;
 	}
+	__d_drop(dentry);
 	spin_unlock(&dentry->d_lock);
 
 	/* Negative dentries can be dropped without further checks */
-	if (!dentry->d_inode) {
-		d_drop(dentry);
+	if (!dentry->d_inode)
 		return;
-	}
 
+	shrink_dcache_parent(dentry);
 	for (;;) {
-		struct detach_data data;
-
-		data.mountpoint = NULL;
-		INIT_LIST_HEAD(&data.select.dispose);
-		data.select.start = dentry;
-		data.select.found = 0;
-
-		d_walk(dentry, &data, detach_and_collect, check_and_drop);
-
-		if (!list_empty(&data.select.dispose))
-			shrink_dentry_list(&data.select.dispose);
-		else if (!data.mountpoint)
+		struct dentry *victim = NULL;
+		d_walk(dentry, &victim, find_submount);
+		if (!victim) {
+			if (had_submounts)
+				shrink_dcache_parent(dentry);
 			return;
-
-		if (data.mountpoint) {
-			detach_mounts(data.mountpoint);
-			dput(data.mountpoint);
 		}
+		had_submounts = true;
+		detach_mounts(victim);
+		dput(victim);
 	}
 }
 EXPORT_SYMBOL(d_invalidate);
@@ -1899,6 +1877,28 @@ void d_instantiate(struct dentry *entry, struct inode * inode)
 }
 EXPORT_SYMBOL(d_instantiate);
 
+/*
+ * This should be equivalent to d_instantiate() + unlock_new_inode(),
+ * with lockdep-related part of unlock_new_inode() done before
+ * anything else.  Use that instead of open-coding d_instantiate()/
+ * unlock_new_inode() combinations.
+ */
+void d_instantiate_new(struct dentry *entry, struct inode *inode)
+{
+	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
+	BUG_ON(!inode);
+	lockdep_annotate_inode_mutex_key(inode);
+	security_d_instantiate(entry, inode);
+	spin_lock(&inode->i_lock);
+	__d_instantiate(entry, inode);
+	WARN_ON(!(inode->i_state & I_NEW));
+	inode->i_state &= ~I_NEW;
+	smp_mb();
+	wake_up_bit(&inode->i_state, __I_NEW);
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(d_instantiate_new);
+
 /**
  * d_instantiate_no_diralias - instantiate a non-aliased dentry
  * @entry: dentry to complete
@@ -1941,35 +1941,6 @@ struct dentry *d_make_root(struct inode *root_inode)
 }
 EXPORT_SYMBOL(d_make_root);
 
-static struct dentry * __d_find_any_alias(struct inode *inode)
-{
-	struct dentry *alias;
-
-	if (hlist_empty(&inode->i_dentry))
-		return NULL;
-	alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
-	__dget(alias);
-	return alias;
-}
-
-/**
- * d_find_any_alias - find any alias for a given inode
- * @inode: inode to find an alias for
- *
- * If any aliases exist for the given inode, take and return a
- * reference for one of them.  If no aliases exist, return %NULL.
- */
-struct dentry *d_find_any_alias(struct inode *inode)
-{
-	struct dentry *de;
-
-	spin_lock(&inode->i_lock);
-	de = __d_find_any_alias(inode);
-	spin_unlock(&inode->i_lock);
-	return de;
-}
-EXPORT_SYMBOL(d_find_any_alias);
-
 static struct dentry *__d_instantiate_anon(struct dentry *dentry,
 					   struct inode *inode,
 					   bool disconnected)
@@ -3112,7 +3083,7 @@ static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
 
 void d_genocide(struct dentry *parent)
 {
-	d_walk(parent, parent, d_genocide_kill, NULL);
+	d_walk(parent, parent, d_genocide_kill);
 }
 
 EXPORT_SYMBOL(d_genocide);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 1f99678ff5d3..4fce1da7db23 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -796,19 +796,13 @@ EXPORT_SYMBOL_GPL(debugfs_read_file_bool);
 ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
 				size_t count, loff_t *ppos)
 {
-	char buf[32];
-	size_t buf_size;
 	bool bv;
 	int r;
 	bool *val = file->private_data;
 	struct dentry *dentry = F_DENTRY(file);
 
-	buf_size = min(count, (sizeof(buf)-1));
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
-	if (strtobool(buf, &bv) == 0) {
+	r = kstrtobool_from_user(user_buf, count, &bv);
+	if (!r) {
 		r = debugfs_file_get(dentry);
 		if (unlikely(r))
 			return r;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 13b01351dd1c..a913b12fc7f8 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -512,7 +512,9 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
 	if (unlikely(!inode))
 		return failed_creating(dentry);
 
-	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	if (!parent)
+		parent = debugfs_mount->mnt_root;
+	inode->i_mode = S_IFDIR | ((d_inode(parent)->i_mode & 0770));
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 874607bb6e02..093fb54cd316 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -432,8 +432,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 	struct bio *bio;
 
 	/*
-	 * bio_alloc() is guaranteed to return a bio when called with
-	 * __GFP_RECLAIM and we request a valid number of vectors.
+	 * bio_alloc() is guaranteed to return a bio when allowed to sleep and
+	 * we request a valid number of vectors.
 	 */
 	bio = bio_alloc(GFP_KERNEL, nr_vecs);
 
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 5243989a60cc..a5e4a221435c 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1037,6 +1037,7 @@ static void sctp_connect_to_sock(struct connection *con)
 	int result;
 	int addr_len;
 	struct socket *sock;
+	struct timeval tv = { .tv_sec = 5, .tv_usec = 0 };
 
 	if (con->nodeid == 0) {
 		log_print("attempt to connect sock 0 foiled");
@@ -1080,11 +1081,22 @@ static void sctp_connect_to_sock(struct connection *con)
 	log_print("connecting to %d", con->nodeid);
 
 	/* Turn off Nagle's algorithm */
-	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
+	kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one,
 			  sizeof(one));
 
+	/*
+	 * Make sock->ops->connect() function return in specified time,
+	 * since O_NONBLOCK argument in connect() function does not work here,
+	 * then, we should restore the default value of this attribute.
+	 */
+	kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv,
+			  sizeof(tv));
 	result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len,
-				   O_NONBLOCK);
+				   0);
+	memset(&tv, 0, sizeof(tv));
+	kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv,
+			  sizeof(tv));
+
 	if (result == -EINPROGRESS)
 		result = 0;
 	if (result == 0)
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 846ca150d52e..4dd842f72846 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1997,6 +1997,16 @@ out:
 	return rc;
 }
 
+static bool is_dot_dotdot(const char *name, size_t name_size)
+{
+	if (name_size == 1 && name[0] == '.')
+		return true;
+	else if (name_size == 2 && name[0] == '.' && name[1] == '.')
+		return true;
+
+	return false;
+}
+
 /**
  * ecryptfs_decode_and_decrypt_filename - converts the encoded cipher text name to decoded plaintext
  * @plaintext_name: The plaintext name
@@ -2021,13 +2031,21 @@ int ecryptfs_decode_and_decrypt_filename(char **plaintext_name,
 	size_t packet_size;
 	int rc = 0;
 
-	if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
-	    && !(mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
-	    && (name_size > ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE)
-	    && (strncmp(name, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX,
-			ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE) == 0)) {
-		const char *orig_name = name;
-		size_t orig_name_size = name_size;
+	if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) &&
+	    !(mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)) {
+		if (is_dot_dotdot(name, name_size)) {
+			rc = ecryptfs_copy_filename(plaintext_name,
+						    plaintext_name_size,
+						    name, name_size);
+			goto out;
+		}
+
+		if (name_size <= ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE ||
+		    strncmp(name, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX,
+			    ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE)) {
+			rc = -EINVAL;
+			goto out;
+		}
 
 		name += ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE;
 		name_size -= ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE;
@@ -2047,12 +2065,9 @@ int ecryptfs_decode_and_decrypt_filename(char **plaintext_name,
 						  decoded_name,
 						  decoded_name_size);
 		if (rc) {
-			printk(KERN_INFO "%s: Could not parse tag 70 packet "
-			       "from filename; copying through filename "
-			       "as-is\n", __func__);
-			rc = ecryptfs_copy_filename(plaintext_name,
-						    plaintext_name_size,
-						    orig_name, orig_name_size);
+			ecryptfs_printk(KERN_DEBUG,
+					"%s: Could not parse tag 70 packet from filename\n",
+					__func__);
 			goto out_free;
 		}
 	} else {
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index c74ed3ca3372..b76a9853325e 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -82,17 +82,28 @@ ecryptfs_filldir(struct dir_context *ctx, const char *lower_name,
 						  buf->sb, lower_name,
 						  lower_namelen);
 	if (rc) {
-		printk(KERN_ERR "%s: Error attempting to decode and decrypt "
-		       "filename [%s]; rc = [%d]\n", __func__, lower_name,
-		       rc);
-		goto out;
+		if (rc != -EINVAL) {
+			ecryptfs_printk(KERN_DEBUG,
+					"%s: Error attempting to decode and decrypt filename [%s]; rc = [%d]\n",
+					__func__, lower_name, rc);
+			return rc;
+		}
+
+		/* Mask -EINVAL errors as these are most likely due a plaintext
+		 * filename present in the lower filesystem despite filename
+		 * encryption being enabled. One unavoidable example would be
+		 * the "lost+found" dentry in the root directory of an Ext4
+		 * filesystem.
+		 */
+		return 0;
 	}
+
 	buf->caller->pos = buf->ctx.pos;
 	rc = !dir_emit(buf->caller, name, name_size, ino, d_type);
 	kfree(name);
 	if (!rc)
 		buf->entries_written++;
-out:
+
 	return rc;
 }
 
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 847904aa63a9..49121e5a8de2 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -283,8 +283,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
 		iget_failed(ecryptfs_inode);
 		goto out;
 	}
-	unlock_new_inode(ecryptfs_inode);
-	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+	d_instantiate_new(ecryptfs_dentry, ecryptfs_inode);
 out:
 	return rc;
 }
@@ -395,8 +394,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 
 	mount_crypt_stat = &ecryptfs_superblock_to_private(
 				ecryptfs_dentry->d_sb)->mount_crypt_stat;
-	if (mount_crypt_stat
-	    && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) {
+	if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
 		rc = ecryptfs_encrypt_and_encode_filename(
 			&encrypted_and_encoded_name, &len,
 			mount_crypt_stat, name, len);
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index c89a58cfc991..e74fe84d0886 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1880,7 +1880,7 @@ find_next_matching_auth_tok:
 		candidate_auth_tok = &auth_tok_list_item->auth_tok;
 		if (unlikely(ecryptfs_verbosity > 0)) {
 			ecryptfs_printk(KERN_DEBUG,
-					"Considering cadidate auth tok:\n");
+					"Considering candidate auth tok:\n");
 			ecryptfs_dump_auth_tok(candidate_auth_tok);
 		}
 		rc = ecryptfs_get_auth_tok_sig(&candidate_auth_tok_sig,
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 08d3bd602f73..61c9514da5e9 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -101,14 +101,20 @@ static int eventfd_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static __poll_t eventfd_poll(struct file *file, poll_table *wait)
+static struct wait_queue_head *
+eventfd_get_poll_head(struct file *file, __poll_t events)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+
+	return &ctx->wqh;
+}
+
+static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
 {
 	struct eventfd_ctx *ctx = file->private_data;
 	__poll_t events = 0;
 	u64 count;
 
-	poll_wait(file, &ctx->wqh, wait);
-
 	/*
 	 * All writes to ctx->count occur within ctx->wqh.lock.  This read
 	 * can be done outside ctx->wqh.lock because we know that poll_wait
@@ -305,7 +311,8 @@ static const struct file_operations eventfd_fops = {
 	.show_fdinfo	= eventfd_show_fdinfo,
 #endif
 	.release	= eventfd_release,
-	.poll		= eventfd_poll,
+	.get_poll_head	= eventfd_get_poll_head,
+	.poll_mask	= eventfd_poll_mask,
 	.read		= eventfd_read,
 	.write		= eventfd_write,
 	.llseek		= noop_llseek,
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 602ca4285b2e..67db22fe99c5 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -884,8 +884,7 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
 
 	pt->_key = epi->event.events;
 	if (!is_file_epoll(epi->ffd.file))
-		return epi->ffd.file->f_op->poll(epi->ffd.file, pt) &
-		       epi->event.events;
+		return vfs_poll(epi->ffd.file, pt) & epi->event.events;
 
 	ep = epi->ffd.file->private_data;
 	poll_wait(epi->ffd.file, &ep->poll_wait, pt);
@@ -2025,7 +2024,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 
 	/* The target file descriptor must support poll */
 	error = -EPERM;
-	if (!tf.file->f_op->poll)
+	if (!file_can_poll(tf.file))
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 3c6a9c156b7a..ddbf87246898 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -790,7 +790,7 @@ int ore_create(struct ore_io_state *ios)
 	for (i = 0; i < ios->oc->numdevs; i++) {
 		struct osd_request *or;
 
-		or = osd_start_request(_ios_od(ios, i), GFP_KERNEL);
+		or = osd_start_request(_ios_od(ios, i));
 		if (unlikely(!or)) {
 			ORE_ERR("%s: osd_start_request failed\n", __func__);
 			ret = -ENOMEM;
@@ -815,7 +815,7 @@ int ore_remove(struct ore_io_state *ios)
 	for (i = 0; i < ios->oc->numdevs; i++) {
 		struct osd_request *or;
 
-		or = osd_start_request(_ios_od(ios, i), GFP_KERNEL);
+		or = osd_start_request(_ios_od(ios, i));
 		if (unlikely(!or)) {
 			ORE_ERR("%s: osd_start_request failed\n", __func__);
 			ret = -ENOMEM;
@@ -847,7 +847,7 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
 		struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
 		struct osd_request *or;
 
-		or = osd_start_request(_ios_od(ios, dev), GFP_KERNEL);
+		or = osd_start_request(_ios_od(ios, dev));
 		if (unlikely(!or)) {
 			ORE_ERR("%s: osd_start_request failed\n", __func__);
 			ret = -ENOMEM;
@@ -966,7 +966,7 @@ int _ore_read_mirror(struct ore_io_state *ios, unsigned cur_comp)
 		return 0; /* Just an empty slot */
 
 	first_dev = per_dev->dev + first_dev % ios->layout->mirrors_p1;
-	or = osd_start_request(_ios_od(ios, first_dev), GFP_KERNEL);
+	or = osd_start_request(_ios_od(ios, first_dev));
 	if (unlikely(!or)) {
 		ORE_ERR("%s: osd_start_request failed\n", __func__);
 		return -ENOMEM;
@@ -1060,7 +1060,7 @@ static int _truncate_mirrors(struct ore_io_state *ios, unsigned cur_comp,
 		struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
 		struct osd_request *or;
 
-		or = osd_start_request(_ios_od(ios, cur_comp), GFP_KERNEL);
+		or = osd_start_request(_ios_od(ios, cur_comp));
 		if (unlikely(!or)) {
 			ORE_ERR("%s: osd_start_request failed\n", __func__);
 			return -ENOMEM;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 179cd5c2f52a..719a3152da80 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -229,7 +229,7 @@ void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], const struct osd_obj_id *obj)
 static int exofs_read_kern(struct osd_dev *od, u8 *cred, struct osd_obj_id *obj,
 		    u64 offset, void *p, unsigned length)
 {
-	struct osd_request *or = osd_start_request(od, GFP_KERNEL);
+	struct osd_request *or = osd_start_request(od);
 /*	struct osd_sense_info osi = {.key = 0};*/
 	int ret;
 
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 09640220fda8..047c327a6b23 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -88,11 +88,11 @@ out_unlock:
  * The default page_lock and i_size verification done by non-DAX fault paths
  * is sufficient because ext2 doesn't support hole punching.
  */
-static int ext2_dax_fault(struct vm_fault *vmf)
+static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct ext2_inode_info *ei = EXT2_I(inode);
-	int ret;
+	vm_fault_t ret;
 
 	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 1e01fabef130..71635909df3b 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1264,21 +1264,11 @@ do_indirects:
 
 static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
 {
-	/*
-	 * XXX: it seems like a bug here that we don't allow
-	 * IS_APPEND inode to have blocks-past-i_size trimmed off.
-	 * review and fix this.
-	 *
-	 * Also would be nice to be able to handle IO errors and such,
-	 * but that's probably too much to ask.
-	 */
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 	    S_ISLNK(inode->i_mode)))
 		return;
 	if (ext2_inode_is_fast_symlink(inode))
 		return;
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-		return;
 
 	dax_sem_down_write(EXT2_I(inode));
 	__ext2_truncate_blocks(inode, offset);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 55f7caadb093..152453a91877 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -41,8 +41,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 {
 	int err = ext2_add_link(dentry, inode);
 	if (!err) {
-		unlock_new_inode(inode);
-		d_instantiate(dentry, inode);
+		d_instantiate_new(dentry, inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
@@ -255,8 +254,7 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 	if (err)
 		goto out_fail;
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 out:
 	return err;
 
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index de1694512f1f..c09289a42dc5 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -961,8 +961,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
 	if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
-		err = bdev_dax_supported(sb, blocksize);
-		if (err) {
+		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
 			ext2_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			sbi->s_mount_opt &= ~EXT2_MOUNT_DAX;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index a33d8fb1bf2a..b00481c475cb 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -185,25 +185,15 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t start, tmp;
 	int flex_bg = 0;
-	struct ext4_group_info *grp;
 
 	J_ASSERT_BH(bh, buffer_locked(bh));
 
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		grp = ext4_get_group_info(sb, block_group);
-		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
-			percpu_counter_sub(&sbi->s_freeclusters_counter,
-					   grp->bb_free);
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
-		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
-			int count;
-			count = ext4_free_inodes_count(sb, gdp);
-			percpu_counter_sub(&sbi->s_freeinodes_counter,
-					   count);
-		}
-		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT |
+					EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 		return -EFSBADCRC;
 	}
 	memset(bh->b_data, 0, sb->s_blocksize);
@@ -321,6 +311,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_grpblk_t offset;
 	ext4_grpblk_t next_zero_bit;
+	ext4_grpblk_t max_bit = EXT4_CLUSTERS_PER_GROUP(sb);
 	ext4_fsblk_t blk;
 	ext4_fsblk_t group_first_block;
 
@@ -338,7 +329,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 	/* check whether block bitmap block number is set */
 	blk = ext4_block_bitmap(sb, desc);
 	offset = blk - group_first_block;
-	if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
+	if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
 	    !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
 		/* bad block bitmap */
 		return blk;
@@ -346,7 +337,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 	/* check whether the inode bitmap block number is set */
 	blk = ext4_inode_bitmap(sb, desc);
 	offset = blk - group_first_block;
-	if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
+	if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
 	    !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
 		/* bad block bitmap */
 		return blk;
@@ -354,8 +345,8 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 	/* check whether the inode table block number is set */
 	blk = ext4_inode_table(sb, desc);
 	offset = blk - group_first_block;
-	if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
-	    EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= sb->s_blocksize)
+	if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
+	    EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= max_bit)
 		return blk;
 	next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
 			EXT4_B2C(sbi, offset + sbi->s_itb_per_group),
@@ -374,7 +365,6 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 {
 	ext4_fsblk_t	blk;
 	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (buffer_verified(bh))
 		return 0;
@@ -386,10 +376,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 			desc, bh))) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
-		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
-			percpu_counter_sub(&sbi->s_freeclusters_counter,
-					   grp->bb_free);
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		return -EFSBADCRC;
 	}
 	blk = ext4_valid_block_bitmap(sb, desc, block_group, bh);
@@ -397,10 +385,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
 			   block_group, blk);
-		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
-			percpu_counter_sub(&sbi->s_freeclusters_counter,
-					   grp->bb_free);
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		return -EFSCORRUPTED;
 	}
 	set_buffer_verified(bh);
@@ -435,6 +421,8 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	    (bitmap_blk >= ext4_blocks_count(sbi->s_es))) {
 		ext4_error(sb, "Invalid block bitmap block %llu in "
 			   "block_group %u", bitmap_blk, block_group);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		return ERR_PTR(-EFSCORRUPTED);
 	}
 	bh = sb_getblk(sb, bitmap_blk);
@@ -513,6 +501,8 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
 		ext4_error(sb, "Cannot read block bitmap - "
 			   "block_group = %u, block_bitmap = %llu",
 			   block_group, (unsigned long long) bh->b_blocknr);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		return -EIO;
 	}
 	clear_buffer_new(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a42e71203e53..df95412915ea 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2390,7 +2390,7 @@ extern int ext4_init_inode_table(struct super_block *sb,
 extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 
 /* mballoc.c */
-extern const struct file_operations ext4_seq_mb_groups_fops;
+extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern long ext4_mb_stats;
 extern long ext4_mb_max_to_scan;
 extern int ext4_mb_init(struct super_block *);
@@ -2530,6 +2530,9 @@ extern int ext4_alloc_flex_bg_array(struct super_block *sb,
 				    ext4_group_t ngroup);
 extern const char *ext4_decode_error(struct super_block *sb, int errno,
 				     char nbuf[16]);
+extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
+					     ext4_group_t block_group,
+					     unsigned int flags);
 
 extern __printf(4, 5)
 void __ext4_error(struct super_block *, const char *, unsigned int,
@@ -2857,6 +2860,10 @@ struct ext4_group_info {
 #define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
 #define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT	2
 #define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT	3
+#define EXT4_GROUP_INFO_BBITMAP_CORRUPT		\
+	(1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT)
+#define EXT4_GROUP_INFO_IBITMAP_CORRUPT		\
+	(1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT)
 
 #define EXT4_MB_GRP_NEED_INIT(grp)	\
 	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0a7315961bac..c969275ce3ee 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5329,8 +5329,9 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	stop = le32_to_cpu(extent->ee_block);
 
        /*
-	 * In case of left shift, Don't start shifting extents until we make
-	 * sure the hole is big enough to accommodate the shift.
+	* For left shifts, make sure the hole on the left is big enough to
+	* accommodate the shift.  For right shifts, make sure the last extent
+	* won't be shifted beyond EXT_MAX_BLOCKS.
 	*/
 	if (SHIFT == SHIFT_LEFT) {
 		path = ext4_find_extent(inode, start - 1, &path,
@@ -5350,9 +5351,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 
 		if ((start == ex_start && shift > ex_start) ||
 		    (shift > start - ex_end)) {
-			ext4_ext_drop_refs(path);
-			kfree(path);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
+		}
+	} else {
+		if (shift > EXT_MAX_BLOCKS -
+		    (stop + ext4_ext_get_actual_len(extent))) {
+			ret = -EINVAL;
+			goto out;
 		}
 	}
 
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 763ef185dd17..c4e6fb15101b 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -162,8 +162,7 @@ int __init ext4_init_es(void)
 
 void ext4_exit_es(void)
 {
-	if (ext4_es_cachep)
-		kmem_cache_destroy(ext4_es_cachep);
+	kmem_cache_destroy(ext4_es_cachep);
 }
 
 void ext4_es_init_tree(struct ext4_es_tree *tree)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index fb6f023622fe..7f8023340eb8 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -277,10 +277,11 @@ out:
 }
 
 #ifdef CONFIG_FS_DAX
-static int ext4_dax_huge_fault(struct vm_fault *vmf,
+static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size)
 {
-	int result, error = 0;
+	int error = 0;
+	vm_fault_t result;
 	int retries = 0;
 	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -335,7 +336,7 @@ retry:
 	return result;
 }
 
-static int ext4_dax_fault(struct vm_fault *vmf)
+static vm_fault_t ext4_dax_fault(struct vm_fault *vmf)
 {
 	return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
 }
@@ -380,50 +381,64 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-static int ext4_file_open(struct inode * inode, struct file * filp)
+static int ext4_sample_last_mounted(struct super_block *sb,
+				    struct vfsmount *mnt)
 {
-	struct super_block *sb = inode->i_sb;
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct vfsmount *mnt = filp->f_path.mnt;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct path path;
 	char buf[64], *cp;
+	handle_t *handle;
+	int err;
+
+	if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
+		return 0;
+
+	if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
+		return 0;
+
+	sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+	/*
+	 * Sample where the filesystem has been mounted and
+	 * store it in the superblock for sysadmin convenience
+	 * when trying to sort through large numbers of block
+	 * devices or filesystem images.
+	 */
+	memset(buf, 0, sizeof(buf));
+	path.mnt = mnt;
+	path.dentry = mnt->mnt_root;
+	cp = d_path(&path, buf, sizeof(buf));
+	err = 0;
+	if (IS_ERR(cp))
+		goto out;
+
+	handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
+	err = PTR_ERR(handle);
+	if (IS_ERR(handle))
+		goto out;
+	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+	if (err)
+		goto out_journal;
+	strlcpy(sbi->s_es->s_last_mounted, cp,
+		sizeof(sbi->s_es->s_last_mounted));
+	ext4_handle_dirty_super(handle, sb);
+out_journal:
+	ext4_journal_stop(handle);
+out:
+	sb_end_intwrite(sb);
+	return err;
+}
+
+static int ext4_file_open(struct inode * inode, struct file * filp)
+{
 	int ret;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
-		     !sb_rdonly(sb))) {
-		sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
-		/*
-		 * Sample where the filesystem has been mounted and
-		 * store it in the superblock for sysadmin convenience
-		 * when trying to sort through large numbers of block
-		 * devices or filesystem images.
-		 */
-		memset(buf, 0, sizeof(buf));
-		path.mnt = mnt;
-		path.dentry = mnt->mnt_root;
-		cp = d_path(&path, buf, sizeof(buf));
-		if (!IS_ERR(cp)) {
-			handle_t *handle;
-			int err;
-
-			handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
-			if (IS_ERR(handle))
-				return PTR_ERR(handle);
-			BUFFER_TRACE(sbi->s_sbh, "get_write_access");
-			err = ext4_journal_get_write_access(handle, sbi->s_sbh);
-			if (err) {
-				ext4_journal_stop(handle);
-				return err;
-			}
-			strlcpy(sbi->s_es->s_last_mounted, cp,
-				sizeof(sbi->s_es->s_last_mounted));
-			ext4_handle_dirty_super(handle, sb);
-			ext4_journal_stop(handle);
-		}
-	}
+	ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt);
+	if (ret)
+		return ret;
 
 	ret = fscrypt_file_open(inode, filp);
 	if (ret)
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index e871c4bf18e9..4b99e2db95b8 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -402,8 +402,8 @@ static void ext4_getfsmap_free_fixed_metadata(struct list_head *meta_list)
 }
 
 /* Find all the fixed metadata in the filesystem. */
-int ext4_getfsmap_find_fixed_metadata(struct super_block *sb,
-				      struct list_head *meta_list)
+static int ext4_getfsmap_find_fixed_metadata(struct super_block *sb,
+					     struct list_head *meta_list)
 {
 	struct ext4_group_desc *gdp;
 	ext4_group_t agno;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index df92e3ec9913..4d6e007f3569 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -83,7 +83,6 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 {
 	ext4_fsblk_t	blk;
 	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (buffer_verified(bh))
 		return 0;
@@ -97,14 +96,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
 			   "inode_bitmap = %llu", block_group, blk);
-		grp = ext4_get_group_info(sb, block_group);
-		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
-			int count;
-			count = ext4_free_inodes_count(sb, desc);
-			percpu_counter_sub(&sbi->s_freeinodes_counter,
-					   count);
-		}
-		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+					EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 		return -EFSBADCRC;
 	}
 	set_buffer_verified(bh);
@@ -136,6 +129,8 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	    (bitmap_blk >= ext4_blocks_count(sbi->s_es))) {
 		ext4_error(sb, "Invalid inode bitmap blk %llu in "
 			   "block_group %u", bitmap_blk, block_group);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+					EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 		return ERR_PTR(-EFSCORRUPTED);
 	}
 	bh = sb_getblk(sb, bitmap_blk);
@@ -143,7 +138,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		ext4_error(sb, "Cannot read inode bitmap - "
 			    "block_group = %u, inode_bitmap = %llu",
 			    block_group, bitmap_blk);
-		return ERR_PTR(-EIO);
+		return ERR_PTR(-ENOMEM);
 	}
 	if (bitmap_uptodate(bh))
 		goto verify;
@@ -190,6 +185,8 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		ext4_error(sb, "Cannot read inode bitmap - "
 			   "block_group = %u, inode_bitmap = %llu",
 			   block_group, bitmap_blk);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+				EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 		return ERR_PTR(-EIO);
 	}
 
@@ -337,13 +334,8 @@ out:
 			fatal = err;
 	} else {
 		ext4_error(sb, "bit already cleared for inode %lu", ino);
-		if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
-			int count;
-			count = ext4_free_inodes_count(sb, gdp);
-			percpu_counter_sub(&sbi->s_freeinodes_counter,
-					   count);
-		}
-		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+					EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 	}
 
 error_return:
@@ -914,6 +906,8 @@ repeat_in_this_group:
 		if (group == 0 && (ino + 1) < EXT4_FIRST_INO(sb)) {
 			ext4_error(sb, "reserved inode found cleared - "
 				   "inode=%lu", ino + 1);
+			ext4_mark_group_bitmap_corrupted(sb, group,
+					EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 			goto next_group;
 		}
 
@@ -1105,6 +1099,8 @@ got:
 		err = -EIO;
 		ext4_error(sb, "failed to insert inode %lu: doubly allocated?",
 			   inode->i_ino);
+		ext4_mark_group_bitmap_corrupted(sb, group,
+					EXT4_GROUP_INFO_IBITMAP_CORRUPT);
 		goto out;
 	}
 	inode->i_generation = prandom_u32();
@@ -1206,11 +1202,8 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
 	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
-	if (IS_ERR(bitmap_bh)) {
-		ext4_error(sb, "inode bitmap error %ld for orphan %lu",
-			   ino, PTR_ERR(bitmap_bh));
+	if (IS_ERR(bitmap_bh))
 		return (struct inode *) bitmap_bh;
-	}
 
 	/* Having the inode bit set should be a 100% indicator that this
 	 * is a valid orphan (no e2fsck run on fs).  Orphans also include
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index c32802c956d5..bf7fa1507e81 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -561,10 +561,16 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 		unsigned epb = inode->i_sb->s_blocksize / sizeof(u32);
 		int i;
 
-		/* Count number blocks in a subtree under 'partial' */
-		count = 1;
-		for (i = 0; partial + i != chain + depth - 1; i++)
-			count *= epb;
+		/*
+		 * Count number blocks in a subtree under 'partial'. At each
+		 * level we count number of complete empty subtrees beyond
+		 * current offset and then descend into the subtree only
+		 * partially beyond current offset.
+		 */
+		count = 0;
+		for (i = partial - chain + 1; i < depth; i++)
+			count = count * epb + (epb - offsets[i] - 1);
+		count++;
 		/* Fill in size of a hole we found */
 		map->m_pblk = 0;
 		map->m_len = min_t(unsigned int, map->m_len, count);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 70cf4c7b268a..285ed1588730 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -144,6 +144,12 @@ int ext4_find_inline_data_nolock(struct inode *inode)
 		goto out;
 
 	if (!is.s.not_found) {
+		if (is.s.here->e_value_inum) {
+			EXT4_ERROR_INODE(inode, "inline data xattr refers "
+					 "to an external xattr inode");
+			error = -EFSCORRUPTED;
+			goto out;
+		}
 		EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
 					(void *)ext4_raw_inode(&is.iloc));
 		EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
@@ -1835,8 +1841,8 @@ int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap)
 	iomap->offset = 0;
 	iomap->length = min_t(loff_t, ext4_get_inline_size(inode),
 			      i_size_read(inode));
-	iomap->type = 0;
-	iomap->flags = IOMAP_F_DATA_INLINE;
+	iomap->type = IOMAP_INLINE;
+	iomap->flags = 0;
 
 out:
 	up_read(&EXT4_I(inode)->xattr_sem);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1e50c5efae67..2ea07efbe016 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4298,28 +4298,28 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 		EXT4_BLOCK_SIZE_BITS(sb);
 	stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
 
-	/* If there are no blocks to remove, return now */
-	if (first_block >= stop_block)
-		goto out_stop;
+	/* If there are blocks to remove, do it */
+	if (stop_block > first_block) {
 
-	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
+		down_write(&EXT4_I(inode)->i_data_sem);
+		ext4_discard_preallocations(inode);
 
-	ret = ext4_es_remove_extent(inode, first_block,
-				    stop_block - first_block);
-	if (ret) {
-		up_write(&EXT4_I(inode)->i_data_sem);
-		goto out_stop;
-	}
+		ret = ext4_es_remove_extent(inode, first_block,
+					    stop_block - first_block);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_data_sem);
+			goto out_stop;
+		}
 
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		ret = ext4_ext_remove_space(inode, first_block,
-					    stop_block - 1);
-	else
-		ret = ext4_ind_remove_space(handle, inode, first_block,
-					    stop_block);
+		if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+			ret = ext4_ext_remove_space(inode, first_block,
+						    stop_block - 1);
+		else
+			ret = ext4_ind_remove_space(handle, inode, first_block,
+						    stop_block);
 
-	up_write(&EXT4_I(inode)->i_data_sem);
+		up_write(&EXT4_I(inode)->i_data_sem);
+	}
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
@@ -4701,19 +4701,21 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
 	}
 }
 
-static inline void ext4_iget_extra_inode(struct inode *inode,
+static inline int ext4_iget_extra_inode(struct inode *inode,
 					 struct ext4_inode *raw_inode,
 					 struct ext4_inode_info *ei)
 {
 	__le32 *magic = (void *)raw_inode +
 			EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
+
 	if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <=
 	    EXT4_INODE_SIZE(inode->i_sb) &&
 	    *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
 		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
-		ext4_find_inline_data_nolock(inode);
+		return ext4_find_inline_data_nolock(inode);
 	} else
 		EXT4_I(inode)->i_inline_off = 0;
+	return 0;
 }
 
 int ext4_get_projid(struct inode *inode, kprojid_t *projid)
@@ -4724,6 +4726,26 @@ int ext4_get_projid(struct inode *inode, kprojid_t *projid)
 	return 0;
 }
 
+/*
+ * ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of
+ * refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag
+ * set.
+ */
+static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val)
+{
+	if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+		inode_set_iversion_raw(inode, val);
+	else
+		inode_set_iversion_queried(inode, val);
+}
+static inline u64 ext4_inode_peek_iversion(const struct inode *inode)
+{
+	if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+		return inode_peek_iversion_raw(inode);
+	else
+		return inode_peek_iversion(inode);
+}
+
 struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 {
 	struct ext4_iloc iloc;
@@ -4893,7 +4915,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 			ei->i_extra_isize = sizeof(struct ext4_inode) -
 					    EXT4_GOOD_OLD_INODE_SIZE;
 		} else {
-			ext4_iget_extra_inode(inode, raw_inode, ei);
+			ret = ext4_iget_extra_inode(inode, raw_inode, ei);
+			if (ret)
+				goto bad_inode;
 		}
 	}
 
@@ -4910,7 +4934,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 				ivers |=
 		    (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
 		}
-		inode_set_iversion_queried(inode, ivers);
+		ext4_inode_set_iversion_queried(inode, ivers);
 	}
 
 	ret = 0;
@@ -4945,6 +4969,13 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		inode->i_op = &ext4_dir_inode_operations;
 		inode->i_fop = &ext4_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
+		/* VFS does not allow setting these so must be corruption */
+		if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+			EXT4_ERROR_INODE(inode,
+			  "immutable or append flags not allowed on symlinks");
+			ret = -EFSCORRUPTED;
+			goto bad_inode;
+		}
 		if (ext4_encrypted_inode(inode)) {
 			inode->i_op = &ext4_encrypted_symlink_inode_operations;
 			ext4_set_aops(inode);
@@ -5196,7 +5227,7 @@ static int ext4_do_update_inode(handle_t *handle,
 	}
 
 	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
-		u64 ivers = inode_peek_iversion(inode);
+		u64 ivers = ext4_inode_peek_iversion(inode);
 
 		raw_inode->i_disk_version = cpu_to_le32(ivers);
 		if (ei->i_extra_isize) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 769a62708b1c..6eae2b91aafa 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -470,6 +470,8 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
 					      "freeing block already freed "
 					      "(bit %u)",
 					      first + i);
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		}
 		mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
 	}
@@ -747,10 +749,8 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 		 * corrupt and update bb_free using bitmap value
 		 */
 		grp->bb_free = free;
-		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
-			percpu_counter_sub(&sbi->s_freeclusters_counter,
-					   grp->bb_free);
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		ext4_mark_group_bitmap_corrupted(sb, group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 	}
 	mb_set_largest_free_order(sb, grp);
 
@@ -1454,12 +1454,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 				      "freeing already freed block "
 				      "(bit %u); block bitmap corrupt.",
 				      block);
-		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))
-			percpu_counter_sub(&sbi->s_freeclusters_counter,
-					   e4b->bd_info->bb_free);
-		/* Mark the block group as corrupt. */
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
-			&e4b->bd_info->bb_state);
+		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		mb_regenerate_buddy(e4b);
 		goto done;
 	}
@@ -1956,6 +1952,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 					"%d free clusters as per "
 					"group info. But bitmap says 0",
 					free);
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 
@@ -1966,6 +1964,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 					"%d free clusters as per "
 					"group info. But got %d blocks",
 					free, ex.fe_len);
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			/*
 			 * The number of free blocks differs. This mostly
 			 * indicate that the bitmap is corrupt. So exit
@@ -2254,7 +2254,7 @@ out:
 
 static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
 {
-	struct super_block *sb = seq->private;
+	struct super_block *sb = PDE_DATA(file_inode(seq->file));
 	ext4_group_t group;
 
 	if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
@@ -2265,7 +2265,7 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
 
 static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct super_block *sb = seq->private;
+	struct super_block *sb = PDE_DATA(file_inode(seq->file));
 	ext4_group_t group;
 
 	++*pos;
@@ -2277,7 +2277,7 @@ static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
 
 static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 {
-	struct super_block *sb = seq->private;
+	struct super_block *sb = PDE_DATA(file_inode(seq->file));
 	ext4_group_t group = (ext4_group_t) ((unsigned long) v);
 	int i;
 	int err, buddy_loaded = 0;
@@ -2330,34 +2330,13 @@ static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v)
 {
 }
 
-static const struct seq_operations ext4_mb_seq_groups_ops = {
+const struct seq_operations ext4_mb_seq_groups_ops = {
 	.start  = ext4_mb_seq_groups_start,
 	.next   = ext4_mb_seq_groups_next,
 	.stop   = ext4_mb_seq_groups_stop,
 	.show   = ext4_mb_seq_groups_show,
 };
 
-static int ext4_mb_seq_groups_open(struct inode *inode, struct file *file)
-{
-	struct super_block *sb = PDE_DATA(inode);
-	int rc;
-
-	rc = seq_open(file, &ext4_mb_seq_groups_ops);
-	if (rc == 0) {
-		struct seq_file *m = file->private_data;
-		m->private = sb;
-	}
-	return rc;
-
-}
-
-const struct file_operations ext4_seq_mb_groups_fops = {
-	.open		= ext4_mb_seq_groups_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static struct kmem_cache *get_groupinfo_cache(int blocksize_bits)
 {
 	int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
@@ -2537,8 +2516,7 @@ static void ext4_groupinfo_destroy_slabs(void)
 	int i;
 
 	for (i = 0; i < NR_GRPINFO_CACHES; i++) {
-		if (ext4_groupinfo_caches[i])
-			kmem_cache_destroy(ext4_groupinfo_caches[i]);
+		kmem_cache_destroy(ext4_groupinfo_caches[i]);
 		ext4_groupinfo_caches[i] = NULL;
 	}
 }
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b1f21e3a0763..4a09063ce1d2 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2411,8 +2411,7 @@ static int ext4_add_nondir(handle_t *handle,
 	int err = ext4_add_entry(handle, dentry, inode);
 	if (!err) {
 		ext4_mark_inode_dirty(handle, inode);
-		unlock_new_inode(inode);
-		d_instantiate(dentry, inode);
+		d_instantiate_new(dentry, inode);
 		return 0;
 	}
 	drop_nlink(inode);
@@ -2651,8 +2650,7 @@ out_clear_inode:
 	err = ext4_mark_inode_dirty(handle, dir);
 	if (err)
 		goto out_clear_inode;
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index b6bec270a8e4..d792b7689d92 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1933,7 +1933,7 @@ retry:
 		return 0;
 
 	n_group = ext4_get_group_number(sb, n_blocks_count - 1);
-	if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
+	if (n_group >= (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
 		ext4_warning(sb, "resize would cause inodes_count overflow");
 		return -EINVAL;
 	}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 185f7e61f4cf..00fe75a71c4b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -763,6 +763,36 @@ __acquires(bitlock)
 	return;
 }
 
+void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
+				     ext4_group_t group,
+				     unsigned int flags)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+
+	if ((flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) &&
+	    !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) {
+		percpu_counter_sub(&sbi->s_freeclusters_counter,
+					grp->bb_free);
+		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+			&grp->bb_state);
+	}
+
+	if ((flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) &&
+	    !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+		if (gdp) {
+			int count;
+
+			count = ext4_free_inodes_count(sb, gdp);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
+		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
+			&grp->bb_state);
+	}
+}
+
 void ext4_update_dynamic_rev(struct super_block *sb)
 {
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
@@ -1237,19 +1267,13 @@ static bool ext4_dummy_context(struct inode *inode)
 	return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
 }
 
-static unsigned ext4_max_namelen(struct inode *inode)
-{
-	return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
-		EXT4_NAME_LEN;
-}
-
 static const struct fscrypt_operations ext4_cryptops = {
 	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
 	.set_context		= ext4_set_context,
 	.dummy_context		= ext4_dummy_context,
 	.empty_dir		= ext4_empty_dir,
-	.max_namelen		= ext4_max_namelen,
+	.max_namelen		= EXT4_NAME_LEN,
 };
 #endif
 
@@ -2116,12 +2140,12 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 			    int read_only)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	int res = 0;
+	int err = 0;
 
 	if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
 		ext4_msg(sb, KERN_ERR, "revision level too high, "
 			 "forcing read-only mode");
-		res = SB_RDONLY;
+		err = -EROFS;
 	}
 	if (read_only)
 		goto done;
@@ -2154,7 +2178,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	if (sbi->s_journal)
 		ext4_set_feature_journal_needs_recovery(sb);
 
-	ext4_commit_super(sb, 1);
+	err = ext4_commit_super(sb, 1);
 done:
 	if (test_opt(sb, DEBUG))
 		printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
@@ -2166,7 +2190,7 @@ done:
 			sbi->s_mount_opt, sbi->s_mount_opt2);
 
 	cleancache_init_fs(sb);
-	return res;
+	return err;
 }
 
 int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
@@ -3732,8 +3756,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 					" that may contain inline data");
 			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;
 		}
-		err = bdev_dax_supported(sb, blocksize);
-		if (err) {
+		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
 			ext4_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;
@@ -4224,8 +4247,12 @@ no_journal:
 		goto failed_mount4;
 	}
 
-	if (ext4_setup_super(sb, es, sb_rdonly(sb)))
+	ret = ext4_setup_super(sb, es, sb_rdonly(sb));
+	if (ret == -EROFS) {
 		sb->s_flags |= SB_RDONLY;
+		ret = 0;
+	} else if (ret)
+		goto failed_mount4a;
 
 	/* determine the minimum size of new large inodes, if present */
 	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
@@ -4760,11 +4787,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 		unlock_buffer(sbh);
 		error = __sync_dirty_buffer(sbh,
 			REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
-		if (error)
-			return error;
-
-		error = buffer_write_io_error(sbh);
-		if (error) {
+		if (buffer_write_io_error(sbh)) {
 			ext4_msg(sb, KERN_ERR, "I/O error while writing "
 			       "superblock");
 			clear_buffer_write_io_error(sbh);
@@ -5165,8 +5188,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			if (sbi->s_journal)
 				ext4_clear_journal_err(sb, es);
 			sbi->s_mount_state = le16_to_cpu(es->s_state);
-			if (!ext4_setup_super(sb, es, 0))
-				sb->s_flags &= ~SB_RDONLY;
+
+			err = ext4_setup_super(sb, es, 0);
+			if (err)
+				goto restore_opts;
+
+			sb->s_flags &= ~SB_RDONLY;
 			if (ext4_has_feature_mmp(sb))
 				if (ext4_multi_mount_protect(sb,
 						le64_to_cpu(es->s_mmp_block))) {
@@ -5190,8 +5217,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	}
 
 	ext4_setup_system_zone(sb);
-	if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY))
-		ext4_commit_super(sb, 1);
+	if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
+		err = ext4_commit_super(sb, 1);
+		if (err)
+			goto restore_opts;
+	}
 
 #ifdef CONFIG_QUOTA
 	/* Release old quota file names */
@@ -5252,7 +5282,8 @@ static int ext4_statfs_project(struct super_block *sb,
 		 dquot->dq_dqb.dqb_bsoftlimit :
 		 dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
 	if (limit && buf->f_blocks > limit) {
-		curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+		curblock = (dquot->dq_dqb.dqb_curspace +
+			    dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
 		buf->f_blocks = limit;
 		buf->f_bfree = buf->f_bavail =
 			(buf->f_blocks > curblock) ?
@@ -5886,5 +5917,6 @@ static void __exit ext4_exit_fs(void)
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
 MODULE_DESCRIPTION("Fourth Extended Filesystem");
 MODULE_LICENSE("GPL");
+MODULE_SOFTDEP("pre: crc32c");
 module_init(ext4_init_fs)
 module_exit(ext4_exit_fs)
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 9ebd26c957c2..f34da0bb8f17 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -346,39 +346,9 @@ static struct kobject *ext4_root;
 
 static struct kobject *ext4_feat;
 
-#define PROC_FILE_SHOW_DEFN(name) \
-static int name##_open(struct inode *inode, struct file *file) \
-{ \
-	return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \
-} \
-\
-static const struct file_operations ext4_seq_##name##_fops = { \
-	.open		= name##_open, \
-	.read		= seq_read, \
-	.llseek		= seq_lseek, \
-	.release	= single_release, \
-}
-
-#define PROC_FILE_LIST(name) \
-	{ __stringify(name), &ext4_seq_##name##_fops }
-
-PROC_FILE_SHOW_DEFN(es_shrinker_info);
-PROC_FILE_SHOW_DEFN(options);
-
-static const struct ext4_proc_files {
-	const char *name;
-	const struct file_operations *fops;
-} proc_files[] = {
-	PROC_FILE_LIST(options),
-	PROC_FILE_LIST(es_shrinker_info),
-	PROC_FILE_LIST(mb_groups),
-	{ NULL, NULL },
-};
-
 int ext4_register_sysfs(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	const struct ext4_proc_files *p;
 	int err;
 
 	init_completion(&sbi->s_kobj_unregister);
@@ -392,11 +362,14 @@ int ext4_register_sysfs(struct super_block *sb)
 
 	if (ext4_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
-
 	if (sbi->s_proc) {
-		for (p = proc_files; p->name; p++)
-			proc_create_data(p->name, S_IRUGO, sbi->s_proc,
-					 p->fops, sb);
+		proc_create_single_data("options", S_IRUGO, sbi->s_proc,
+				ext4_seq_options_show, sb);
+		proc_create_single_data("es_shrinker_info", S_IRUGO,
+				sbi->s_proc, ext4_seq_es_shrinker_info_show,
+				sb);
+		proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc,
+				&ext4_mb_seq_groups_ops, sb);
 	}
 	return 0;
 }
@@ -404,13 +377,9 @@ int ext4_register_sysfs(struct super_block *sb)
 void ext4_unregister_sysfs(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	const struct ext4_proc_files *p;
 
-	if (sbi->s_proc) {
-		for (p = proc_files; p->name; p++)
-			remove_proc_entry(p->name, sbi->s_proc);
-		remove_proc_entry(sb->s_id, ext4_proc_root);
-	}
+	if (sbi->s_proc)
+		remove_proc_subtree(sb->s_id, ext4_proc_root);
 	kobject_del(&sbi->s_kobj);
 }
 
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 499cb4b1fbd2..fc4ced59c565 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1688,7 +1688,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 
 	/* No failures allowed past this point. */
 
-	if (!s->not_found && here->e_value_offs) {
+	if (!s->not_found && here->e_value_size && here->e_value_offs) {
 		/* Remove the old value. */
 		void *first_val = s->base + min_offs;
 		size_t offs = le16_to_cpu(here->e_value_offs);
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 629001b28632..197a9d8a15ef 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -43,7 +43,7 @@ ext4_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 		err = ext4_xattr_set_handle(handle, inode,
 					    EXT4_XATTR_INDEX_SECURITY,
 					    xattr->name, xattr->value,
-					    xattr->value_len, 0);
+					    xattr->value_len, XATTR_CREATE);
 		if (err < 0)
 			break;
 	}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index d5098efe577c..75e37fd720b2 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -294,8 +294,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	alloc_nid_done(sbi, ino);
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
@@ -597,8 +596,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	err = page_symlink(inode, disk_link.name, disk_link.len);
 
 err_out:
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 
 	/*
 	 * Let's flush symlink data in order to avoid broken symlink as much as
@@ -661,8 +659,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	alloc_nid_done(sbi, inode->i_ino);
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
@@ -713,8 +710,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 
 	alloc_nid_done(sbi, inode->i_ino);
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 42d564c5ccd0..970ae27f401c 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1930,19 +1930,13 @@ static bool f2fs_dummy_context(struct inode *inode)
 	return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode));
 }
 
-static unsigned f2fs_max_namelen(struct inode *inode)
-{
-	return S_ISLNK(inode->i_mode) ?
-			inode->i_sb->s_blocksize : F2FS_NAME_LEN;
-}
-
 static const struct fscrypt_operations f2fs_cryptops = {
 	.key_prefix	= "f2fs:",
 	.get_context	= f2fs_get_context,
 	.set_context	= f2fs_set_context,
 	.dummy_context	= f2fs_dummy_context,
 	.empty_dir	= f2fs_empty_dir,
-	.max_namelen	= f2fs_max_namelen,
+	.max_namelen	= F2FS_NAME_LEN,
 };
 #endif
 
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index f33a56d6e6dd..4b47ca6296a7 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -572,23 +572,6 @@ static int iostat_info_seq_show(struct seq_file *seq, void *offset)
 	return 0;
 }
 
-#define F2FS_PROC_FILE_DEF(_name)					\
-static int _name##_open_fs(struct inode *inode, struct file *file)	\
-{									\
-	return single_open(file, _name##_seq_show, PDE_DATA(inode));	\
-}									\
-									\
-static const struct file_operations f2fs_seq_##_name##_fops = {		\
-	.open = _name##_open_fs,					\
-	.read = seq_read,						\
-	.llseek = seq_lseek,						\
-	.release = single_release,					\
-};
-
-F2FS_PROC_FILE_DEF(segment_info);
-F2FS_PROC_FILE_DEF(segment_bits);
-F2FS_PROC_FILE_DEF(iostat_info);
-
 int __init f2fs_init_sysfs(void)
 {
 	int ret;
@@ -632,12 +615,12 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
 		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
 
 	if (sbi->s_proc) {
-		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
-				 &f2fs_seq_segment_info_fops, sb);
-		proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
-				 &f2fs_seq_segment_bits_fops, sb);
-		proc_create_data("iostat_info", S_IRUGO, sbi->s_proc,
-				&f2fs_seq_iostat_info_fops, sb);
+		proc_create_single_data("segment_info", S_IRUGO, sbi->s_proc,
+				segment_info_seq_show, sb);
+		proc_create_single_data("segment_bits", S_IRUGO, sbi->s_proc,
+				segment_bits_seq_show, sb);
+		proc_create_single_data("iostat_info", S_IRUGO, sbi->s_proc,
+				iostat_info_seq_show, sb);
 	}
 	return 0;
 }
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 582ca731a6c9..484ce674e0cd 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -314,10 +314,6 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
 	int err;
 
 	mutex_lock(&MSDOS_SB(sb)->s_lock);
-	/*
-	 * Check whether the directory is not in use, then check
-	 * whether it is empty.
-	 */
 	err = fat_dir_empty(inode);
 	if (err)
 		goto out;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 2649759c478a..4f4362d5a04c 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -697,15 +697,6 @@ static int vfat_find(struct inode *dir, const struct qstr *qname,
 	return fat_search_long(dir, qname->name, len, sinfo);
 }
 
-/*
- * (nfsd's) anonymous disconnected dentry?
- * NOTE: !IS_ROOT() is not anonymous (I.e. d_splice_alias() did the job).
- */
-static int vfat_d_anon_disconn(struct dentry *dentry)
-{
-	return IS_ROOT(dentry) && (dentry->d_flags & DCACHE_DISCONNECTED);
-}
-
 static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 				  unsigned int flags)
 {
@@ -738,8 +729,7 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 	 * Checking "alias->d_parent == dentry->d_parent" to make sure
 	 * FS is not corrupted (especially double linked dir).
 	 */
-	if (alias && alias->d_parent == dentry->d_parent &&
-	    !vfat_d_anon_disconn(alias)) {
+	if (alias && alias->d_parent == dentry->d_parent) {
 		/*
 		 * This inode has non anonymous-DCACHE_DISCONNECTED
 		 * dentry. This means, the user did ->lookup() by an
@@ -747,7 +737,6 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 		 *
 		 * Switch to new one for reason of locality if possible.
 		 */
-		BUG_ON(d_unhashed(alias));
 		if (!S_ISDIR(inode->i_mode))
 			d_move(alias, dentry);
 		iput(inode);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index d737ff082472..c42169459298 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -871,9 +871,9 @@ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
 		if (fa->fa_file != filp)
 			continue;
 
-		spin_lock_irq(&fa->fa_lock);
+		write_lock_irq(&fa->fa_lock);
 		fa->fa_file = NULL;
-		spin_unlock_irq(&fa->fa_lock);
+		write_unlock_irq(&fa->fa_lock);
 
 		*fp = fa->fa_next;
 		call_rcu(&fa->fa_rcu, fasync_free_rcu);
@@ -918,13 +918,13 @@ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasy
 		if (fa->fa_file != filp)
 			continue;
 
-		spin_lock_irq(&fa->fa_lock);
+		write_lock_irq(&fa->fa_lock);
 		fa->fa_fd = fd;
-		spin_unlock_irq(&fa->fa_lock);
+		write_unlock_irq(&fa->fa_lock);
 		goto out;
 	}
 
-	spin_lock_init(&new->fa_lock);
+	rwlock_init(&new->fa_lock);
 	new->magic = FASYNC_MAGIC;
 	new->fa_file = filp;
 	new->fa_fd = fd;
@@ -987,14 +987,13 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
 {
 	while (fa) {
 		struct fown_struct *fown;
-		unsigned long flags;
 
 		if (fa->magic != FASYNC_MAGIC) {
 			printk(KERN_ERR "kill_fasync: bad magic number in "
 			       "fasync_struct!\n");
 			return;
 		}
-		spin_lock_irqsave(&fa->fa_lock, flags);
+		read_lock(&fa->fa_lock);
 		if (fa->fa_file) {
 			fown = &fa->fa_file->f_owner;
 			/* Don't send SIGURG to processes which have not set a
@@ -1003,7 +1002,7 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
 			if (!(sig == SIGURG && fown->signum == 0))
 				send_sigio(fown, fa->fa_fd, band);
 		}
-		spin_unlock_irqrestore(&fa->fa_lock, flags);
+		read_unlock(&fa->fa_lock);
 		fa = rcu_dereference(fa->fa_next);
 	}
 }
diff --git a/fs/filesystems.c b/fs/filesystems.c
index f2728a4a03a1..b03f57b1105b 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -238,21 +238,9 @@ static int filesystems_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int filesystems_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, filesystems_proc_show, NULL);
-}
-
-static const struct file_operations filesystems_proc_fops = {
-	.open		= filesystems_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_filesystems_init(void)
 {
-	proc_create("filesystems", 0, NULL, &filesystems_proc_fops);
+	proc_create_single("filesystems", 0, NULL, filesystems_proc_show);
 	return 0;
 }
 module_init(proc_filesystems_init);
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index ce4785fd81c6..a51425634f65 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -193,13 +193,9 @@ vxfs_lookup(struct inode *dip, struct dentry *dp, unsigned int flags)
 		return ERR_PTR(-ENAMETOOLONG);
 				 
 	ino = vxfs_inode_by_name(dip, dp);
-	if (ino) {
+	if (ino)
 		ip = vxfs_iget(dip->i_sb, ino);
-		if (IS_ERR(ip))
-			return ERR_CAST(ip);
-	}
-	d_add(dp, ip);
-	return NULL;
+	return d_splice_alias(ip, dp);
 }
 
 /**
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 4b12ba70a895..471d863958bc 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -745,11 +745,12 @@ int inode_congested(struct inode *inode, int cong_bits)
 	 */
 	if (inode && inode_to_wb_is_valid(inode)) {
 		struct bdi_writeback *wb;
-		bool locked, congested;
+		struct wb_lock_cookie lock_cookie = {};
+		bool congested;
 
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &lock_cookie);
 		congested = wb_congested(wb, cong_bits);
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &lock_cookie);
 		return congested;
 	}
 
@@ -1960,7 +1961,7 @@ void wb_workfn(struct work_struct *work)
 	}
 
 	if (!list_empty(&wb->work_list))
-		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+		wb_wakeup(wb);
 	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
 		wb_wakeup_delayed(wb);
 
diff --git a/fs/fscache/histogram.c b/fs/fscache/histogram.c
index 15a3d042247e..9a13e9e15b69 100644
--- a/fs/fscache/histogram.c
+++ b/fs/fscache/histogram.c
@@ -83,24 +83,9 @@ static void fscache_histogram_stop(struct seq_file *m, void *v)
 {
 }
 
-static const struct seq_operations fscache_histogram_ops = {
+const struct seq_operations fscache_histogram_ops = {
 	.start		= fscache_histogram_start,
 	.stop		= fscache_histogram_stop,
 	.next		= fscache_histogram_next,
 	.show		= fscache_histogram_show,
 };
-
-/*
- * open "/proc/fs/fscache/histogram" to provide latency data
- */
-static int fscache_histogram_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &fscache_histogram_ops);
-}
-
-const struct file_operations fscache_histogram_fops = {
-	.open		= fscache_histogram_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 500650f938fe..f83328a7f048 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -31,6 +31,7 @@
 #include <linux/fscache-cache.h>
 #include <trace/events/fscache.h>
 #include <linux/sched.h>
+#include <linux/seq_file.h>
 
 #define FSCACHE_MIN_THREADS	4
 #define FSCACHE_MAX_THREADS	32
@@ -84,7 +85,7 @@ static inline void fscache_hist(atomic_t histogram[], unsigned long start_jif)
 	atomic_inc(&histogram[jif]);
 }
 
-extern const struct file_operations fscache_histogram_fops;
+extern const struct seq_operations fscache_histogram_ops;
 
 #else
 #define fscache_hist(hist, start_jif) do {} while (0)
@@ -294,7 +295,7 @@ static inline void fscache_stat_d(atomic_t *stat)
 
 #define __fscache_stat(stat) (stat)
 
-extern const struct file_operations fscache_stats_fops;
+int fscache_stats_show(struct seq_file *m, void *v);
 #else
 
 #define __fscache_stat(stat) (NULL)
diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c
index 1d9e4951a597..49a8c90414bc 100644
--- a/fs/fscache/proc.c
+++ b/fs/fscache/proc.c
@@ -26,14 +26,14 @@ int __init fscache_proc_init(void)
 		goto error_dir;
 
 #ifdef CONFIG_FSCACHE_STATS
-	if (!proc_create("fs/fscache/stats", S_IFREG | 0444, NULL,
-			 &fscache_stats_fops))
+	if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL,
+			fscache_stats_show))
 		goto error_stats;
 #endif
 
 #ifdef CONFIG_FSCACHE_HISTOGRAM
-	if (!proc_create("fs/fscache/histogram", S_IFREG | 0444, NULL,
-			 &fscache_histogram_fops))
+	if (!proc_create_seq("fs/fscache/histogram", S_IFREG | 0444, NULL,
+			 &fscache_histogram_ops))
 		goto error_histogram;
 #endif
 
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index fcc8c2f2690e..00564a1dfd76 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -138,7 +138,7 @@ atomic_t fscache_n_cache_culled_objects;
 /*
  * display the general statistics
  */
-static int fscache_stats_show(struct seq_file *m, void *v)
+int fscache_stats_show(struct seq_file *m, void *v)
 {
 	seq_puts(m, "FS-Cache statistics\n");
 
@@ -284,18 +284,3 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_cache_culled_objects));
 	return 0;
 }
-
-/*
- * open "/proc/fs/fscache/stats" allowing provision of a statistical summary
- */
-static int fscache_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, fscache_stats_show, NULL);
-}
-
-const struct file_operations fscache_stats_fops = {
-	.open		= fscache_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release        = single_release,
-};
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index f58716567972..35f5ee23566d 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -54,8 +54,7 @@ static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
 			continue;
 		if (start >= to)
 			break;
-		if (gfs2_is_jdata(ip))
-			set_buffer_uptodate(bh);
+		set_buffer_uptodate(bh);
 		gfs2_trans_add_data(ip->i_gl, bh);
 	}
 }
@@ -747,18 +746,21 @@ out:
 	put_page(page);
 
 	gfs2_trans_end(sdp);
-	if (pos + len > ip->i_inode.i_size)
-		gfs2_trim_blocks(&ip->i_inode);
-	goto out_trans_fail;
+	if (alloc_required) {
+		gfs2_inplace_release(ip);
+		if (pos + len > ip->i_inode.i_size)
+			gfs2_trim_blocks(&ip->i_inode);
+	}
+	goto out_qunlock;
 
 out_endtrans:
 	gfs2_trans_end(sdp);
 out_trans_fail:
-	if (alloc_required) {
+	if (alloc_required)
 		gfs2_inplace_release(ip);
 out_qunlock:
+	if (alloc_required)
 		gfs2_quota_unlock(ip);
-	}
 out_unlock:
 	if (&ip->i_inode == sdp->sd_rindex) {
 		gfs2_glock_dq(&m_ip->i_gh);
@@ -814,7 +816,6 @@ out:
  * @inode: The inode
  * @dibh: The buffer_head containing the on-disk inode
  * @pos: The file position
- * @len: The length of the write
  * @copied: How much was actually copied by the VFS
  * @page: The page
  *
@@ -824,17 +825,15 @@ out:
  * Returns: errno
  */
 static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
-				  loff_t pos, unsigned len, unsigned copied,
+				  loff_t pos, unsigned copied,
 				  struct page *page)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 	u64 to = pos + copied;
 	void *kaddr;
 	unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
 
-	BUG_ON(pos + len > gfs2_max_stuffed_size(ip));
+	BUG_ON(pos + copied > gfs2_max_stuffed_size(ip));
 
 	kaddr = kmap_atomic(page);
 	memcpy(buf + pos, kaddr + pos, copied);
@@ -850,20 +849,6 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 			i_size_write(inode, to);
 		mark_inode_dirty(inode);
 	}
-
-	if (inode == sdp->sd_rindex) {
-		adjust_fs_space(inode);
-		sdp->sd_rindex_uptodate = 0;
-	}
-
-	brelse(dibh);
-	gfs2_trans_end(sdp);
-	if (inode == sdp->sd_rindex) {
-		gfs2_glock_dq(&m_ip->i_gh);
-		gfs2_holder_uninit(&m_ip->i_gh);
-	}
-	gfs2_glock_dq(&ip->i_gh);
-	gfs2_holder_uninit(&ip->i_gh);
 	return copied;
 }
 
@@ -877,9 +862,8 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
  * @page: The page that has been written
  * @fsdata: The fsdata (unused in GFS2)
  *
- * The main write_end function for GFS2. We have a separate one for
- * stuffed files as they are slightly different, otherwise we just
- * put our locking around the VFS provided functions.
+ * The main write_end function for GFS2. We just put our locking around the VFS
+ * provided functions.
  *
  * Returns: errno
  */
@@ -900,32 +884,39 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
 
 	ret = gfs2_meta_inode_buffer(ip, &dibh);
-	if (unlikely(ret)) {
-		unlock_page(page);
-		put_page(page);
-		goto failed;
-	}
+	if (unlikely(ret))
+		goto out;
 
-	if (gfs2_is_stuffed(ip))
-		return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
+	if (gfs2_is_stuffed(ip)) {
+		ret = gfs2_stuffed_write_end(inode, dibh, pos, copied, page);
+		page = NULL;
+		goto out2;
+	}
 
-	if (!gfs2_is_writeback(ip))
+	if (gfs2_is_jdata(ip))
 		gfs2_page_add_databufs(ip, page, pos & ~PAGE_MASK, len);
+	else
+		gfs2_ordered_add_inode(ip);
 
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	page = NULL;
 	if (tr->tr_num_buf_new)
 		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 	else
 		gfs2_trans_add_meta(ip->i_gl, dibh);
 
-
+out2:
 	if (inode == sdp->sd_rindex) {
 		adjust_fs_space(inode);
 		sdp->sd_rindex_uptodate = 0;
 	}
 
 	brelse(dibh);
-failed:
+out:
+	if (page) {
+		unlock_page(page);
+		put_page(page);
+	}
 	gfs2_trans_end(sdp);
 	gfs2_inplace_release(ip);
 	if (ip->i_qadata && ip->i_qadata->qa_qd_num)
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 278ed0869c3c..ed6699705c13 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -89,10 +89,12 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 		map_bh(bh, inode->i_sb, block);
 
 	set_buffer_uptodate(bh);
-	if (!gfs2_is_jdata(ip))
-		mark_buffer_dirty(bh);
-	if (!gfs2_is_writeback(ip))
+	if (gfs2_is_jdata(ip))
 		gfs2_trans_add_data(ip->i_gl, bh);
+	else {
+		mark_buffer_dirty(bh);
+		gfs2_ordered_add_inode(ip);
+	}
 
 	if (release) {
 		unlock_page(page);
@@ -176,8 +178,8 @@ out:
 /**
  * find_metapath - Find path through the metadata tree
  * @sdp: The superblock
- * @mp: The metapath to return the result in
  * @block: The disk block to look up
+ * @mp: The metapath to return the result in
  * @height: The pre-calculated height of the metadata tree
  *
  *   This routine returns a struct metapath structure that defines a path
@@ -188,8 +190,7 @@ out:
  *   filesystem with a blocksize of 4096.
  *
  *   find_metapath() would return a struct metapath structure set to:
- *   mp_offset = 101342453, mp_height = 3, mp_list[0] = 0, mp_list[1] = 48,
- *   and mp_list[2] = 165.
+ *   mp_fheight = 3, mp_list[0] = 0, mp_list[1] = 48, and mp_list[2] = 165.
  *
  *   That means that in order to get to the block containing the byte at
  *   offset 101342453, we would load the indirect block pointed to by pointer
@@ -279,6 +280,21 @@ static inline __be64 *metapointer(unsigned int height, const struct metapath *mp
 	return p + mp->mp_list[height];
 }
 
+static inline const __be64 *metaend(unsigned int height, const struct metapath *mp)
+{
+	const struct buffer_head *bh = mp->mp_bh[height];
+	return (const __be64 *)(bh->b_data + bh->b_size);
+}
+
+static void clone_metapath(struct metapath *clone, struct metapath *mp)
+{
+	unsigned int hgt;
+
+	*clone = *mp;
+	for (hgt = 0; hgt < mp->mp_aheight; hgt++)
+		get_bh(clone->mp_bh[hgt]);
+}
+
 static void gfs2_metapath_ra(struct gfs2_glock *gl, __be64 *start, __be64 *end)
 {
 	const __be64 *t;
@@ -420,20 +436,140 @@ static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __b
 	return (ptr - first);
 }
 
-static inline void bmap_lock(struct gfs2_inode *ip, int create)
+typedef const __be64 *(*gfs2_metadata_walker)(
+		struct metapath *mp,
+		const __be64 *start, const __be64 *end,
+		u64 factor, void *data);
+
+#define WALK_STOP ((__be64 *)0)
+#define WALK_NEXT ((__be64 *)1)
+
+static int gfs2_walk_metadata(struct inode *inode, sector_t lblock,
+		u64 len, struct metapath *mp, gfs2_metadata_walker walker,
+		void *data)
 {
-	if (create)
-		down_write(&ip->i_rw_mutex);
-	else
-		down_read(&ip->i_rw_mutex);
+	struct metapath clone;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	const __be64 *start, *end, *ptr;
+	u64 factor = 1;
+	unsigned int hgt;
+	int ret = 0;
+
+	for (hgt = ip->i_height - 1; hgt >= mp->mp_aheight; hgt--)
+		factor *= sdp->sd_inptrs;
+
+	for (;;) {
+		u64 step;
+
+		/* Walk indirect block. */
+		start = metapointer(hgt, mp);
+		end = metaend(hgt, mp);
+
+		step = (end - start) * factor;
+		if (step > len)
+			end = start + DIV_ROUND_UP_ULL(len, factor);
+
+		ptr = walker(mp, start, end, factor, data);
+		if (ptr == WALK_STOP)
+			break;
+		if (step >= len)
+			break;
+		len -= step;
+		if (ptr != WALK_NEXT) {
+			BUG_ON(!*ptr);
+			mp->mp_list[hgt] += ptr - start;
+			goto fill_up_metapath;
+		}
+
+lower_metapath:
+		/* Decrease height of metapath. */
+		if (mp != &clone) {
+			clone_metapath(&clone, mp);
+			mp = &clone;
+		}
+		brelse(mp->mp_bh[hgt]);
+		mp->mp_bh[hgt] = NULL;
+		if (!hgt)
+			break;
+		hgt--;
+		factor *= sdp->sd_inptrs;
+
+		/* Advance in metadata tree. */
+		(mp->mp_list[hgt])++;
+		start = metapointer(hgt, mp);
+		end = metaend(hgt, mp);
+		if (start >= end) {
+			mp->mp_list[hgt] = 0;
+			if (!hgt)
+				break;
+			goto lower_metapath;
+		}
+
+fill_up_metapath:
+		/* Increase height of metapath. */
+		if (mp != &clone) {
+			clone_metapath(&clone, mp);
+			mp = &clone;
+		}
+		ret = fillup_metapath(ip, mp, ip->i_height - 1);
+		if (ret < 0)
+			break;
+		hgt += ret;
+		for (; ret; ret--)
+			do_div(factor, sdp->sd_inptrs);
+		mp->mp_aheight = hgt + 1;
+	}
+	if (mp == &clone)
+		release_metapath(mp);
+	return ret;
 }
 
-static inline void bmap_unlock(struct gfs2_inode *ip, int create)
+struct gfs2_hole_walker_args {
+	u64 blocks;
+};
+
+static const __be64 *gfs2_hole_walker(struct metapath *mp,
+		const __be64 *start, const __be64 *end,
+		u64 factor, void *data)
 {
-	if (create)
-		up_write(&ip->i_rw_mutex);
-	else
-		up_read(&ip->i_rw_mutex);
+	struct gfs2_hole_walker_args *args = data;
+	const __be64 *ptr;
+
+	for (ptr = start; ptr < end; ptr++) {
+		if (*ptr) {
+			args->blocks += (ptr - start) * factor;
+			if (mp->mp_aheight == mp->mp_fheight)
+				return WALK_STOP;
+			return ptr;  /* increase height */
+		}
+	}
+	args->blocks += (end - start) * factor;
+	return WALK_NEXT;
+}
+
+/**
+ * gfs2_hole_size - figure out the size of a hole
+ * @inode: The inode
+ * @lblock: The logical starting block number
+ * @len: How far to look (in blocks)
+ * @mp: The metapath at lblock
+ * @iomap: The iomap to store the hole size in
+ *
+ * This function modifies @mp.
+ *
+ * Returns: errno on error
+ */
+static int gfs2_hole_size(struct inode *inode, sector_t lblock, u64 len,
+			  struct metapath *mp, struct iomap *iomap)
+{
+	struct gfs2_hole_walker_args args = { };
+	int ret = 0;
+
+	ret = gfs2_walk_metadata(inode, lblock, len, mp, gfs2_hole_walker, &args);
+	if (!ret)
+		iomap->length = args.blocks << inode->i_blkbits;
+	return ret;
 }
 
 static inline __be64 *gfs2_indirect_init(struct metapath *mp,
@@ -462,15 +598,11 @@ enum alloc_state {
 };
 
 /**
- * gfs2_bmap_alloc - Build a metadata tree of the requested height
+ * gfs2_iomap_alloc - Build a metadata tree of the requested height
  * @inode: The GFS2 inode
- * @lblock: The logical starting block of the extent
- * @bh_map: This is used to return the mapping details
- * @zero_new: True if newly allocated blocks should be zeroed
+ * @iomap: The iomap structure
+ * @flags: iomap flags
  * @mp: The metapath, with proper height information calculated
- * @maxlen: The max number of data blocks to alloc
- * @dblock: Pointer to return the resulting new block
- * @dblks: Pointer to return the number of blocks allocated
  *
  * In this routine we may have to alloc:
  *   i) Indirect blocks to grow the metadata tree height
@@ -483,6 +615,13 @@ enum alloc_state {
  * blocks are available, there will only be one request per bmap call)
  * and uses the state machine to initialise the blocks in order.
  *
+ * Right now, this function will allocate at most one indirect block
+ * worth of data -- with a default block size of 4K, that's slightly
+ * less than 2M.  If this limitation is ever removed to allow huge
+ * allocations, we would probably still want to limit the iomap size we
+ * return to avoid stalling other tasks during huge writes; the next
+ * iomap iteration would then find the blocks already allocated.
+ *
  * Returns: errno on error
  */
 
@@ -497,6 +636,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 	unsigned dblks = 0;
 	unsigned ptrs_per_blk;
 	const unsigned end_of_metadata = mp->mp_fheight - 1;
+	int ret;
 	enum alloc_state state;
 	__be64 *ptr;
 	__be64 zero_bn = 0;
@@ -507,6 +647,8 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 
 	gfs2_trans_add_meta(ip->i_gl, dibh);
 
+	down_write(&ip->i_rw_mutex);
+
 	if (mp->mp_fheight == mp->mp_aheight) {
 		struct buffer_head *bh;
 		int eob;
@@ -542,11 +684,10 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 	blks = dblks + iblks;
 	i = mp->mp_aheight;
 	do {
-		int error;
 		n = blks - alloced;
-		error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
-		if (error)
-			return error;
+		ret = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
+		if (ret)
+			goto out;
 		alloced += n;
 		if (state != ALLOC_DATA || gfs2_is_jdata(ip))
 			gfs2_trans_add_unrevoke(sdp, bn, n);
@@ -602,7 +743,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 			dblks = n;
 			ptr = metapointer(end_of_metadata, mp);
 			iomap->addr = bn << inode->i_blkbits;
-			iomap->flags |= IOMAP_F_NEW;
+			iomap->flags |= IOMAP_F_MERGED | IOMAP_F_NEW;
 			while (n-- > 0)
 				*ptr++ = cpu_to_be64(bn++);
 			break;
@@ -612,64 +753,10 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 	iomap->length = (u64)dblks << inode->i_blkbits;
 	ip->i_height = mp->mp_fheight;
 	gfs2_add_inode_blocks(&ip->i_inode, alloced);
-	gfs2_dinode_out(ip, mp->mp_bh[0]->b_data);
-	return 0;
-}
-
-/**
- * hole_size - figure out the size of a hole
- * @inode: The inode
- * @lblock: The logical starting block number
- * @mp: The metapath
- *
- * Returns: The hole size in bytes
- *
- */
-static u64 hole_size(struct inode *inode, sector_t lblock, struct metapath *mp)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct metapath mp_eof;
-	u64 factor = 1;
-	int hgt;
-	u64 holesz = 0;
-	const __be64 *first, *end, *ptr;
-	const struct buffer_head *bh;
-	u64 lblock_stop = (i_size_read(inode) - 1) >> inode->i_blkbits;
-	int zeroptrs;
-	bool done = false;
-
-	/* Get another metapath, to the very last byte */
-	find_metapath(sdp, lblock_stop, &mp_eof, ip->i_height);
-	for (hgt = ip->i_height - 1; hgt >= 0 && !done; hgt--) {
-		bh = mp->mp_bh[hgt];
-		if (bh) {
-			zeroptrs = 0;
-			first = metapointer(hgt, mp);
-			end = (const __be64 *)(bh->b_data + bh->b_size);
-
-			for (ptr = first; ptr < end; ptr++) {
-				if (*ptr) {
-					done = true;
-					break;
-				} else {
-					zeroptrs++;
-				}
-			}
-		} else {
-			zeroptrs = sdp->sd_inptrs;
-		}
-		if (factor * zeroptrs >= lblock_stop - lblock + 1) {
-			holesz = lblock_stop - lblock + 1;
-			break;
-		}
-		holesz += factor * zeroptrs;
-
-		factor *= sdp->sd_inptrs;
-		if (hgt && (mp->mp_list[hgt - 1] < mp_eof.mp_list[hgt - 1]))
-			(mp->mp_list[hgt - 1])++;
-	}
-	return holesz << inode->i_blkbits;
+	gfs2_dinode_out(ip, dibh->b_data);
+out:
+	up_write(&ip->i_rw_mutex);
+	return ret;
 }
 
 static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
@@ -680,126 +767,136 @@ static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
 		      sizeof(struct gfs2_dinode);
 	iomap->offset = 0;
 	iomap->length = i_size_read(inode);
-	iomap->type = IOMAP_MAPPED;
-	iomap->flags = IOMAP_F_DATA_INLINE;
+	iomap->type = IOMAP_INLINE;
 }
 
+#define IOMAP_F_GFS2_BOUNDARY IOMAP_F_PRIVATE
+
 /**
- * gfs2_iomap_begin - Map blocks from an inode to disk blocks
+ * gfs2_iomap_get - Map blocks from an inode to disk blocks
  * @inode: The inode
  * @pos: Starting position in bytes
  * @length: Length to map, in bytes
  * @flags: iomap flags
  * @iomap: The iomap structure
+ * @mp: The metapath
  *
  * Returns: errno
  */
-int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
-		     unsigned flags, struct iomap *iomap)
+static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
+			  unsigned flags, struct iomap *iomap,
+			  struct metapath *mp)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct metapath mp = { .mp_aheight = 1, };
-	unsigned int factor = sdp->sd_sb.sb_bsize;
-	const u64 *arr = sdp->sd_heightsize;
 	__be64 *ptr;
 	sector_t lblock;
-	sector_t lend;
-	int ret = 0;
+	sector_t lblock_stop;
+	int ret;
 	int eob;
-	unsigned int len;
+	u64 len;
 	struct buffer_head *bh;
 	u8 height;
 
-	trace_gfs2_iomap_start(ip, pos, length, flags);
-	if (!length) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!length)
+		return -EINVAL;
 
 	if (gfs2_is_stuffed(ip)) {
 		if (flags & IOMAP_REPORT) {
+			if (pos >= i_size_read(inode))
+				return -ENOENT;
 			gfs2_stuffed_iomap(inode, iomap);
-			if (pos >= iomap->length)
-				ret = -ENOENT;
-			goto out;
+			return 0;
 		}
 		BUG_ON(!(flags & IOMAP_WRITE));
 	}
-
 	lblock = pos >> inode->i_blkbits;
-	lend = (pos + length + sdp->sd_sb.sb_bsize - 1) >> inode->i_blkbits;
-
 	iomap->offset = lblock << inode->i_blkbits;
-	iomap->addr = IOMAP_NULL_ADDR;
-	iomap->type = IOMAP_HOLE;
-	iomap->length = (u64)(lend - lblock) << inode->i_blkbits;
-	iomap->flags = IOMAP_F_MERGED;
-	bmap_lock(ip, flags & IOMAP_WRITE);
+	lblock_stop = (pos + length - 1) >> inode->i_blkbits;
+	len = lblock_stop - lblock + 1;
 
-	/*
-	 * Directory data blocks have a struct gfs2_meta_header header, so the
-	 * remaining size is smaller than the filesystem block size.  Logical
-	 * block numbers for directories are in units of this remaining size!
-	 */
-	if (gfs2_is_dir(ip)) {
-		factor = sdp->sd_jbsize;
-		arr = sdp->sd_jheightsize;
-	}
+	down_read(&ip->i_rw_mutex);
 
-	ret = gfs2_meta_inode_buffer(ip, &mp.mp_bh[0]);
+	ret = gfs2_meta_inode_buffer(ip, &mp->mp_bh[0]);
 	if (ret)
-		goto out_release;
+		goto unlock;
 
 	height = ip->i_height;
-	while ((lblock + 1) * factor > arr[height])
+	while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height])
 		height++;
-	find_metapath(sdp, lblock, &mp, height);
+	find_metapath(sdp, lblock, mp, height);
 	if (height > ip->i_height || gfs2_is_stuffed(ip))
 		goto do_alloc;
 
-	ret = lookup_metapath(ip, &mp);
+	ret = lookup_metapath(ip, mp);
 	if (ret)
-		goto out_release;
+		goto unlock;
 
-	if (mp.mp_aheight != ip->i_height)
+	if (mp->mp_aheight != ip->i_height)
 		goto do_alloc;
 
-	ptr = metapointer(ip->i_height - 1, &mp);
+	ptr = metapointer(ip->i_height - 1, mp);
 	if (*ptr == 0)
 		goto do_alloc;
 
-	iomap->type = IOMAP_MAPPED;
-	iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits;
+	bh = mp->mp_bh[ip->i_height - 1];
+	len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, len, &eob);
 
-	bh = mp.mp_bh[ip->i_height - 1];
-	len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, lend - lblock, &eob);
+	iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits;
+	iomap->length = len << inode->i_blkbits;
+	iomap->type = IOMAP_MAPPED;
+	iomap->flags = IOMAP_F_MERGED;
 	if (eob)
-		iomap->flags |= IOMAP_F_BOUNDARY;
-	iomap->length = (u64)len << inode->i_blkbits;
+		iomap->flags |= IOMAP_F_GFS2_BOUNDARY;
 
-out_release:
-	release_metapath(&mp);
-	bmap_unlock(ip, flags & IOMAP_WRITE);
 out:
-	trace_gfs2_iomap_end(ip, iomap, ret);
+	iomap->bdev = inode->i_sb->s_bdev;
+unlock:
+	up_read(&ip->i_rw_mutex);
 	return ret;
 
 do_alloc:
-	if (flags & IOMAP_WRITE) {
-		ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
-	} else if (flags & IOMAP_REPORT) {
+	iomap->addr = IOMAP_NULL_ADDR;
+	iomap->length = len << inode->i_blkbits;
+	iomap->type = IOMAP_HOLE;
+	iomap->flags = 0;
+	if (flags & IOMAP_REPORT) {
 		loff_t size = i_size_read(inode);
 		if (pos >= size)
 			ret = -ENOENT;
-		else if (height <= ip->i_height)
-			iomap->length = hole_size(inode, lblock, &mp);
+		else if (height == ip->i_height)
+			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 		else
 			iomap->length = size - pos;
 	}
-	goto out_release;
+	goto out;
+}
+
+static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
+			    unsigned flags, struct iomap *iomap)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct metapath mp = { .mp_aheight = 1, };
+	int ret;
+
+	trace_gfs2_iomap_start(ip, pos, length, flags);
+	if (flags & IOMAP_WRITE) {
+		ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
+		if (!ret && iomap->type == IOMAP_HOLE)
+			ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
+		release_metapath(&mp);
+	} else {
+		ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
+		release_metapath(&mp);
+	}
+	trace_gfs2_iomap_end(ip, iomap, ret);
+	return ret;
 }
 
+const struct iomap_ops gfs2_iomap_ops = {
+	.iomap_begin = gfs2_iomap_begin,
+};
+
 /**
  * gfs2_block_map - Map one or more blocks of an inode to a disk block
  * @inode: The inode
@@ -825,34 +922,43 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
 		   struct buffer_head *bh_map, int create)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
-	struct iomap iomap;
-	int ret, flags = 0;
+	loff_t pos = (loff_t)lblock << inode->i_blkbits;
+	loff_t length = bh_map->b_size;
+	struct metapath mp = { .mp_aheight = 1, };
+	struct iomap iomap = { };
+	int ret;
 
 	clear_buffer_mapped(bh_map);
 	clear_buffer_new(bh_map);
 	clear_buffer_boundary(bh_map);
 	trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
 
-	if (create)
-		flags |= IOMAP_WRITE;
-	ret = gfs2_iomap_begin(inode, (loff_t)lblock << inode->i_blkbits,
-			       bh_map->b_size, flags, &iomap);
-	if (ret) {
-		if (!create && ret == -ENOENT) {
-			/* Return unmapped buffer beyond the end of file.  */
+	if (create) {
+		ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, &iomap, &mp);
+		if (!ret && iomap.type == IOMAP_HOLE)
+			ret = gfs2_iomap_alloc(inode, &iomap, IOMAP_WRITE, &mp);
+		release_metapath(&mp);
+	} else {
+		ret = gfs2_iomap_get(inode, pos, length, 0, &iomap, &mp);
+		release_metapath(&mp);
+
+		/* Return unmapped buffer beyond the end of file. */
+		if (ret == -ENOENT) {
 			ret = 0;
+			goto out;
 		}
-		goto out;
 	}
+	if (ret)
+		goto out;
 
 	if (iomap.length > bh_map->b_size) {
 		iomap.length = bh_map->b_size;
-		iomap.flags &= ~IOMAP_F_BOUNDARY;
+		iomap.flags &= ~IOMAP_F_GFS2_BOUNDARY;
 	}
 	if (iomap.addr != IOMAP_NULL_ADDR)
 		map_bh(bh_map, inode->i_sb, iomap.addr >> inode->i_blkbits);
 	bh_map->b_size = iomap.length;
-	if (iomap.flags & IOMAP_F_BOUNDARY)
+	if (iomap.flags & IOMAP_F_GFS2_BOUNDARY)
 		set_buffer_boundary(bh_map);
 	if (iomap.flags & IOMAP_F_NEW)
 		set_buffer_new(bh_map);
@@ -945,8 +1051,10 @@ static int gfs2_block_zero_range(struct inode *inode, loff_t from,
 		err = 0;
 	}
 
-	if (!gfs2_is_writeback(ip))
+	if (gfs2_is_jdata(ip))
 		gfs2_trans_add_data(ip->i_gl, bh);
+	else
+		gfs2_ordered_add_inode(ip);
 
 	zero_user(page, offset, length);
 	mark_buffer_dirty(bh);
@@ -1056,6 +1164,19 @@ out:
 	return error;
 }
 
+int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length,
+			 struct iomap *iomap)
+{
+	struct metapath mp = { .mp_aheight = 1, };
+	int ret;
+
+	ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, iomap, &mp);
+	if (!ret && iomap->type == IOMAP_HOLE)
+		ret = gfs2_iomap_alloc(inode, iomap, IOMAP_WRITE, &mp);
+	release_metapath(&mp);
+	return ret;
+}
+
 /**
  * sweep_bh_for_rgrps - find an rgrp in a meta buffer and free blocks therein
  * @ip: inode
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index c3402fe00653..6b18fb323f0a 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -46,11 +46,13 @@ static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip,
 	}
 }
 
+extern const struct iomap_ops gfs2_iomap_ops;
+
 extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
 extern int gfs2_block_map(struct inode *inode, sector_t lblock,
 			  struct buffer_head *bh, int create);
-extern int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
-			    unsigned flags, struct iomap *iomap);
+extern int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length,
+				struct iomap *iomap);
 extern int gfs2_extent_map(struct inode *inode, u64 lblock, int *new,
 			   u64 *dblock, unsigned *extlen);
 extern int gfs2_setattr_size(struct inode *inode, u64 size);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4b71f021a9e2..7137db7b0119 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -733,7 +733,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	loff_t end = offset + len;
 	struct buffer_head *dibh;
-	struct iomap iomap;
+	struct iomap iomap = { };
 	int error;
 
 	error = gfs2_meta_inode_buffer(ip, &dibh);
@@ -749,8 +749,8 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 	}
 
 	while (offset < end) {
-		error = gfs2_iomap_begin(inode, offset, end - offset,
-					 IOMAP_WRITE, &iomap);
+		error = gfs2_iomap_get_alloc(inode, offset, end - offset,
+					     &iomap);
 		if (error)
 			goto out;
 		offset = iomap.offset + iomap.length;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 1b6b1e3f5caf..d2ad817e089f 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -116,6 +116,7 @@ static inline struct gfs2_bitmap *rbm_bi(const struct gfs2_rbm *rbm)
 
 static inline u64 gfs2_rbm_to_block(const struct gfs2_rbm *rbm)
 {
+	BUG_ON(rbm->offset >= rbm->rgd->rd_data);
 	return rbm->rgd->rd_data0 + (rbm_bi(rbm)->bi_start * GFS2_NBBY) +
 		rbm->offset;
 }
@@ -696,8 +697,6 @@ struct gfs2_sbd {
 	u32 sd_max_dirres;	/* Max blocks needed to add a directory entry */
 	u32 sd_max_height;	/* Max height of a file's metadata tree */
 	u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1];
-	u32 sd_max_jheight; /* Max height of journaled file's meta tree */
-	u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1];
 	u32 sd_max_dents_per_leaf; /* Max number of dirents in a leaf block */
 
 	struct gfs2_args sd_args;	/* Mount arguments */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 8700eb815638..feda55f67050 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -2006,10 +2006,6 @@ static int gfs2_getattr(const struct path *path, struct kstat *stat,
 	return 0;
 }
 
-const struct iomap_ops gfs2_iomap_ops = {
-	.iomap_begin = gfs2_iomap_begin,
-};
-
 static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		       u64 start, u64 len)
 {
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 1862e310a067..20241436126d 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/writeback.h>
 #include "incore.h"
+#include "inode.h"
 
 /**
  * gfs2_log_lock - acquire the right to mess with the log manager
@@ -50,8 +51,12 @@ static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
 
 static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_sbd *sdp;
 
+	if (!gfs2_is_ordered(ip))
+		return;
+
+	sdp = GFS2_SB(&ip->i_inode);
 	if (!test_bit(GIF_ORDERED, &ip->i_flags)) {
 		spin_lock(&sdp->sd_ordered_lock);
 		if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags))
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 3ba3f167641c..c2469833b4fb 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -335,25 +335,6 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
 	sdp->sd_heightsize[x] = ~0;
 	gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
 
-	sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
-				 sizeof(struct gfs2_dinode);
-	sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
-	for (x = 2;; x++) {
-		u64 space, d;
-		u32 m;
-
-		space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
-		d = space;
-		m = do_div(d, sdp->sd_inptrs);
-
-		if (d != sdp->sd_jheightsize[x - 1] || m)
-			break;
-		sdp->sd_jheightsize[x] = space;
-	}
-	sdp->sd_max_jheight = x;
-	sdp->sd_jheightsize[x] = ~0;
-	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
-
 	sdp->sd_max_dents_per_leaf = (sdp->sd_sb.sb_bsize -
 				      sizeof(struct gfs2_leaf)) /
 				     GFS2_MIN_DIRENT_SIZE;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 7a98abd340ee..e8585dfd209f 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -735,7 +735,10 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
 			if (!buffer_uptodate(bh))
 				goto unlock_out;
 		}
-		gfs2_trans_add_data(ip->i_gl, bh);
+		if (gfs2_is_jdata(ip))
+			gfs2_trans_add_data(ip->i_gl, bh);
+		else
+			gfs2_ordered_add_inode(ip);
 
 		/* If we need to write to the next block as well */
 		if (to_write > (bsize - boff)) {
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 8b683917a27e..6bc5cfe710d1 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -372,8 +372,8 @@ static u32 gfs2_free_extlen(const struct gfs2_rbm *rrbm, u32 len)
 		start = bi->bi_bh->b_data;
 		if (bi->bi_clone)
 			start = bi->bi_clone;
-		end = start + bi->bi_bh->b_size;
 		start += bi->bi_offset;
+		end = start + bi->bi_len;
 		BUG_ON(rbm.offset & 3);
 		start += (rbm.offset / GFS2_NBBY);
 		bytes = min_t(u32, len / GFS2_NBBY, (end - start));
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index c75cacaa349b..064c9a0ef046 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -143,32 +143,21 @@ static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
  * @gl: The inode glock associated with the buffer
  * @bh: The buffer to add
  *
- * This is used in two distinct cases:
- * i) In ordered write mode
- *    We put the data buffer on a list so that we can ensure that it's
- *    synced to disk at the right time
- * ii) In journaled data mode
- *    We need to journal the data block in the same way as metadata in
- *    the functions above. The difference is that here we have a tag
- *    which is two __be64's being the block number (as per meta data)
- *    and a flag which says whether the data block needs escaping or
- *    not. This means we need a new log entry for each 251 or so data
- *    blocks, which isn't an enormous overhead but twice as much as
- *    for normal metadata blocks.
+ * This is used in journaled data mode.
+ * We need to journal the data block in the same way as metadata in
+ * the functions above. The difference is that here we have a tag
+ * which is two __be64's being the block number (as per meta data)
+ * and a flag which says whether the data block needs escaping or
+ * not. This means we need a new log entry for each 251 or so data
+ * blocks, which isn't an enormous overhead but twice as much as
+ * for normal metadata blocks.
  */
 void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 {
 	struct gfs2_trans *tr = current->journal_info;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct address_space *mapping = bh->b_page->mapping;
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
 	struct gfs2_bufdata *bd;
 
-	if (!gfs2_is_jdata(ip)) {
-		gfs2_ordered_add_inode(ip);
-		return;
-	}
-
 	lock_buffer(bh);
 	if (buffer_pinned(bh)) {
 		set_bit(TR_TOUCHED, &tr->tr_flags);
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 75b254280ff6..3bf2ae0e467c 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -31,21 +31,15 @@ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry,
 	hfs_cat_build_key(dir->i_sb, fd.search_key, dir->i_ino, &dentry->d_name);
 	res = hfs_brec_read(&fd, &rec, sizeof(rec));
 	if (res) {
-		hfs_find_exit(&fd);
-		if (res == -ENOENT) {
-			/* No such entry */
-			inode = NULL;
-			goto done;
-		}
-		return ERR_PTR(res);
+		if (res != -ENOENT)
+			inode = ERR_PTR(res);
+	} else {
+		inode = hfs_iget(dir->i_sb, &fd.search_key->cat, &rec);
+		if (!inode)
+			inode = ERR_PTR(-EACCES);
 	}
-	inode = hfs_iget(dir->i_sb, &fd.search_key->cat, &rec);
 	hfs_find_exit(&fd);
-	if (!inode)
-		return ERR_PTR(-EACCES);
-done:
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 /*
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 2538b49cc349..b3309b83371a 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -543,9 +543,9 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
 	igrab(dir);
 	hlist_add_fake(&inode->i_hash);
 	mark_inode_dirty(inode);
+	dont_mount(dentry);
 out:
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 void hfs_evict_inode(struct inode *inode)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 15e06fb552da..b5254378f011 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -122,8 +122,7 @@ again:
 	if (S_ISREG(inode->i_mode))
 		HFSPLUS_I(inode)->linkid = linkid;
 out:
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 fail:
 	hfs_find_exit(&fd);
 	return ERR_PTR(err);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 513c357c734b..a6c0f54c48c3 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -588,6 +588,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	return 0;
 
 out_put_hidden_dir:
+	cancel_delayed_work_sync(&sbi->sync_work);
 	iput(sbi->hidden_dir);
 out_put_root:
 	dput(sb->s_root);
diff --git a/fs/inode.c b/fs/inode.c
index 13ceb98c3bd3..3b55391072f3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -178,6 +178,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	mapping->a_ops = &empty_aops;
 	mapping->host = inode;
 	mapping->flags = 0;
+	mapping->wb_err = 0;
 	atomic_set(&mapping->i_mmap_writable, 0);
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
 	mapping->private_data = NULL;
diff --git a/fs/internal.h b/fs/internal.h
index e08972db0303..980d005b21b4 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -125,6 +125,7 @@ int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 
+extern int open_check_o_direct(struct file *f);
 extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file *filp_clone_open(struct file *);
 
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 4823431d1c9d..b445b13fc59b 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -549,7 +549,7 @@ static int ioctl_fsfreeze(struct file *filp)
 {
 	struct super_block *sb = file_inode(filp)->i_sb;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/* If filesystem doesn't support freeze feature, return. */
@@ -566,7 +566,7 @@ static int ioctl_fsthaw(struct file *filp)
 {
 	struct super_block *sb = file_inode(filp)->i_sb;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/* Thaw */
diff --git a/fs/iomap.c b/fs/iomap.c
index afd163586aa0..206539d369a8 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
+#include <linux/pagevec.h>
 #include <linux/file.h>
 #include <linux/uio.h>
 #include <linux/backing-dev.h>
@@ -27,6 +28,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/dax.h>
 #include <linux/sched/signal.h>
+#include <linux/swap.h>
 
 #include "internal.h"
 
@@ -95,6 +97,12 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
 	return written ? written : ret;
 }
 
+static sector_t
+iomap_sector(struct iomap *iomap, loff_t pos)
+{
+	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
+}
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
@@ -352,11 +360,8 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
 		struct iomap *iomap)
 {
-	sector_t sector = (iomap->addr +
-			   (pos & PAGE_MASK) - iomap->offset) >> 9;
-
-	return __dax_zero_page_range(iomap->bdev, iomap->dax_dev, sector,
-			offset, bytes);
+	return __dax_zero_page_range(iomap->bdev, iomap->dax_dev,
+			iomap_sector(iomap, pos & PAGE_MASK), offset, bytes);
 }
 
 static loff_t
@@ -501,10 +506,13 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
 	case IOMAP_DELALLOC:
 		flags |= FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN;
 		break;
+	case IOMAP_MAPPED:
+		break;
 	case IOMAP_UNWRITTEN:
 		flags |= FIEMAP_EXTENT_UNWRITTEN;
 		break;
-	case IOMAP_MAPPED:
+	case IOMAP_INLINE:
+		flags |= FIEMAP_EXTENT_DATA_INLINE;
 		break;
 	}
 
@@ -512,8 +520,6 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
 		flags |= FIEMAP_EXTENT_MERGED;
 	if (iomap->flags & IOMAP_F_SHARED)
 		flags |= FIEMAP_EXTENT_SHARED;
-	if (iomap->flags & IOMAP_F_DATA_INLINE)
-		flags |= FIEMAP_EXTENT_DATA_INLINE;
 
 	return fiemap_fill_next_extent(fi, iomap->offset,
 			iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0,
@@ -587,6 +593,113 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 }
 EXPORT_SYMBOL_GPL(iomap_fiemap);
 
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
+ * Returns true if found and updates @lastoff to the offset in file.
+ */
+static bool
+page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff,
+		int whence)
+{
+	const struct address_space_operations *ops = inode->i_mapping->a_ops;
+	unsigned int bsize = i_blocksize(inode), off;
+	bool seek_data = whence == SEEK_DATA;
+	loff_t poff = page_offset(page);
+
+	if (WARN_ON_ONCE(*lastoff >= poff + PAGE_SIZE))
+		return false;
+
+	if (*lastoff < poff) {
+		/*
+		 * Last offset smaller than the start of the page means we found
+		 * a hole:
+		 */
+		if (whence == SEEK_HOLE)
+			return true;
+		*lastoff = poff;
+	}
+
+	/*
+	 * Just check the page unless we can and should check block ranges:
+	 */
+	if (bsize == PAGE_SIZE || !ops->is_partially_uptodate)
+		return PageUptodate(page) == seek_data;
+
+	lock_page(page);
+	if (unlikely(page->mapping != inode->i_mapping))
+		goto out_unlock_not_found;
+
+	for (off = 0; off < PAGE_SIZE; off += bsize) {
+		if ((*lastoff & ~PAGE_MASK) >= off + bsize)
+			continue;
+		if (ops->is_partially_uptodate(page, off, bsize) == seek_data) {
+			unlock_page(page);
+			return true;
+		}
+		*lastoff = poff + off + bsize;
+	}
+
+out_unlock_not_found:
+	unlock_page(page);
+	return false;
+}
+
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
+ *
+ * Within unwritten extents, the page cache determines which parts are holes
+ * and which are data: uptodate buffer heads count as data; everything else
+ * counts as a hole.
+ *
+ * Returns the resulting offset on successs, and -ENOENT otherwise.
+ */
+static loff_t
+page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
+		int whence)
+{
+	pgoff_t index = offset >> PAGE_SHIFT;
+	pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
+	loff_t lastoff = offset;
+	struct pagevec pvec;
+
+	if (length <= 0)
+		return -ENOENT;
+
+	pagevec_init(&pvec);
+
+	do {
+		unsigned nr_pages, i;
+
+		nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
+						end - 1);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			if (page_seek_hole_data(inode, page, &lastoff, whence))
+				goto check_range;
+			lastoff = page_offset(page) + PAGE_SIZE;
+		}
+		pagevec_release(&pvec);
+	} while (index < end);
+
+	/* When no page at lastoff and we are not done, we found a hole. */
+	if (whence != SEEK_HOLE)
+		goto not_found;
+
+check_range:
+	if (lastoff < offset + length)
+		goto out;
+not_found:
+	lastoff = -ENOENT;
+out:
+	pagevec_release(&pvec);
+	return lastoff;
+}
+
+
 static loff_t
 iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
 		      void *data, struct iomap *iomap)
@@ -685,6 +798,8 @@ EXPORT_SYMBOL_GPL(iomap_seek_data);
  * Private flags for iomap_dio, must not overlap with the public ones in
  * iomap.h:
  */
+#define IOMAP_DIO_WRITE_FUA	(1 << 28)
+#define IOMAP_DIO_NEED_SYNC	(1 << 29)
 #define IOMAP_DIO_WRITE		(1 << 30)
 #define IOMAP_DIO_DIRTY		(1 << 31)
 
@@ -759,6 +874,13 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 			dio_warn_stale_pagecache(iocb->ki_filp);
 	}
 
+	/*
+	 * If this is a DSYNC write, make sure we push it to stable storage now
+	 * that we've written data.
+	 */
+	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
+		ret = generic_write_sync(iocb, ret);
+
 	inode_dio_end(file_inode(iocb->ki_filp));
 	kfree(dio);
 
@@ -769,13 +891,8 @@ static void iomap_dio_complete_work(struct work_struct *work)
 {
 	struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work);
 	struct kiocb *iocb = dio->iocb;
-	bool is_write = (dio->flags & IOMAP_DIO_WRITE);
-	ssize_t ret;
 
-	ret = iomap_dio_complete(dio);
-	if (is_write && ret > 0)
-		ret = generic_write_sync(iocb, ret);
-	iocb->ki_complete(iocb, ret, 0);
+	iocb->ki_complete(iocb, iomap_dio_complete(dio), 0);
 }
 
 /*
@@ -833,14 +950,12 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 
 	bio = bio_alloc(GFP_KERNEL, 1);
 	bio_set_dev(bio, iomap->bdev);
-	bio->bi_iter.bi_sector =
-		(iomap->addr + pos - iomap->offset) >> 9;
+	bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
 	get_page(page);
-	if (bio_add_page(bio, page, len, 0) != len)
-		BUG();
+	__bio_add_page(bio, page, len, 0);
 	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
 
 	atomic_inc(&dio->ref);
@@ -858,6 +973,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct iov_iter iter;
 	struct bio *bio;
 	bool need_zeroout = false;
+	bool use_fua = false;
 	int nr_pages, ret;
 	size_t copied = 0;
 
@@ -881,8 +997,20 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	case IOMAP_MAPPED:
 		if (iomap->flags & IOMAP_F_SHARED)
 			dio->flags |= IOMAP_DIO_COW;
-		if (iomap->flags & IOMAP_F_NEW)
+		if (iomap->flags & IOMAP_F_NEW) {
 			need_zeroout = true;
+		} else {
+			/*
+			 * Use a FUA write if we need datasync semantics, this
+			 * is a pure data IO that doesn't require any metadata
+			 * updates and the underlying device supports FUA. This
+			 * allows us to avoid cache flushes on IO completion.
+			 */
+			if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
+			    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
+			    blk_queue_fua(bdev_get_queue(iomap->bdev)))
+				use_fua = true;
+		}
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -916,8 +1044,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 		bio_set_dev(bio, iomap->bdev);
-		bio->bi_iter.bi_sector =
-			(iomap->addr + pos - iomap->offset) >> 9;
+		bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
 		bio->bi_write_hint = dio->iocb->ki_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
@@ -930,10 +1057,14 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 
 		n = bio->bi_iter.bi_size;
 		if (dio->flags & IOMAP_DIO_WRITE) {
-			bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
+			bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+			if (use_fua)
+				bio->bi_opf |= REQ_FUA;
+			else
+				dio->flags &= ~IOMAP_DIO_WRITE_FUA;
 			task_io_account_write(n);
 		} else {
-			bio_set_op_attrs(bio, REQ_OP_READ, 0);
+			bio->bi_opf = REQ_OP_READ;
 			if (dio->flags & IOMAP_DIO_DIRTY)
 				bio_set_pages_dirty(bio);
 		}
@@ -961,6 +1092,15 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	return copied;
 }
 
+/*
+ * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO
+ * is being issued as AIO or not.  This allows us to optimise pure data writes
+ * to use REQ_FUA rather than requiring generic_write_sync() to issue a
+ * REQ_FLUSH post write. This is slightly tricky because a single request here
+ * can be mapped into multiple disjoint IOs and only a subset of the IOs issued
+ * may be pure data writes. In that case, we still need to do a full data sync
+ * completion.
+ */
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, iomap_dio_end_io_t end_io)
@@ -1005,8 +1145,21 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		if (iter->type == ITER_IOVEC)
 			dio->flags |= IOMAP_DIO_DIRTY;
 	} else {
-		dio->flags |= IOMAP_DIO_WRITE;
 		flags |= IOMAP_WRITE;
+		dio->flags |= IOMAP_DIO_WRITE;
+
+		/* for data sync or sync, we need sync completion processing */
+		if (iocb->ki_flags & IOCB_DSYNC)
+			dio->flags |= IOMAP_DIO_NEED_SYNC;
+
+		/*
+		 * For datasync only writes, we optimistically try using FUA for
+		 * this IO.  Any non-FUA write that occurs will clear this flag,
+		 * hence we know before completion whether a cache flush is
+		 * necessary.
+		 */
+		if ((iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) == IOCB_DSYNC)
+			dio->flags |= IOMAP_DIO_WRITE_FUA;
 	}
 
 	if (iocb->ki_flags & IOCB_NOWAIT) {
@@ -1062,6 +1215,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (ret < 0)
 		iomap_dio_set_error(dio, ret);
 
+	/*
+	 * If all the writes we issued were FUA, we don't need to flush the
+	 * cache on IO completion. Clear the sync flag for this case.
+	 */
+	if (dio->flags & IOMAP_DIO_WRITE_FUA)
+		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
+
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!is_sync_kiocb(iocb))
 			return -EIOCBQUEUED;
@@ -1089,3 +1249,203 @@ out_free_dio:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
+
+/* Swapfile activation */
+
+#ifdef CONFIG_SWAP
+struct iomap_swapfile_info {
+	struct iomap iomap;		/* accumulated iomap */
+	struct swap_info_struct *sis;
+	uint64_t lowest_ppage;		/* lowest physical addr seen (pages) */
+	uint64_t highest_ppage;		/* highest physical addr seen (pages) */
+	unsigned long nr_pages;		/* number of pages collected */
+	int nr_extents;			/* extent count */
+};
+
+/*
+ * Collect physical extents for this swap file.  Physical extents reported to
+ * the swap code must be trimmed to align to a page boundary.  The logical
+ * offset within the file is irrelevant since the swapfile code maps logical
+ * page numbers of the swap device to the physical page-aligned extents.
+ */
+static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi)
+{
+	struct iomap *iomap = &isi->iomap;
+	unsigned long nr_pages;
+	uint64_t first_ppage;
+	uint64_t first_ppage_reported;
+	uint64_t next_ppage;
+	int error;
+
+	/*
+	 * Round the start up and the end down so that the physical
+	 * extent aligns to a page boundary.
+	 */
+	first_ppage = ALIGN(iomap->addr, PAGE_SIZE) >> PAGE_SHIFT;
+	next_ppage = ALIGN_DOWN(iomap->addr + iomap->length, PAGE_SIZE) >>
+			PAGE_SHIFT;
+
+	/* Skip too-short physical extents. */
+	if (first_ppage >= next_ppage)
+		return 0;
+	nr_pages = next_ppage - first_ppage;
+
+	/*
+	 * Calculate how much swap space we're adding; the first page contains
+	 * the swap header and doesn't count.  The mm still wants that first
+	 * page fed to add_swap_extent, however.
+	 */
+	first_ppage_reported = first_ppage;
+	if (iomap->offset == 0)
+		first_ppage_reported++;
+	if (isi->lowest_ppage > first_ppage_reported)
+		isi->lowest_ppage = first_ppage_reported;
+	if (isi->highest_ppage < (next_ppage - 1))
+		isi->highest_ppage = next_ppage - 1;
+
+	/* Add extent, set up for the next call. */
+	error = add_swap_extent(isi->sis, isi->nr_pages, nr_pages, first_ppage);
+	if (error < 0)
+		return error;
+	isi->nr_extents += error;
+	isi->nr_pages += nr_pages;
+	return 0;
+}
+
+/*
+ * Accumulate iomaps for this swap file.  We have to accumulate iomaps because
+ * swap only cares about contiguous page-aligned physical extents and makes no
+ * distinction between written and unwritten extents.
+ */
+static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos,
+		loff_t count, void *data, struct iomap *iomap)
+{
+	struct iomap_swapfile_info *isi = data;
+	int error;
+
+	switch (iomap->type) {
+	case IOMAP_MAPPED:
+	case IOMAP_UNWRITTEN:
+		/* Only real or unwritten extents. */
+		break;
+	case IOMAP_INLINE:
+		/* No inline data. */
+		pr_err("swapon: file is inline\n");
+		return -EINVAL;
+	default:
+		pr_err("swapon: file has unallocated extents\n");
+		return -EINVAL;
+	}
+
+	/* No uncommitted metadata or shared blocks. */
+	if (iomap->flags & IOMAP_F_DIRTY) {
+		pr_err("swapon: file is not committed\n");
+		return -EINVAL;
+	}
+	if (iomap->flags & IOMAP_F_SHARED) {
+		pr_err("swapon: file has shared extents\n");
+		return -EINVAL;
+	}
+
+	/* Only one bdev per swap file. */
+	if (iomap->bdev != isi->sis->bdev) {
+		pr_err("swapon: file is on multiple devices\n");
+		return -EINVAL;
+	}
+
+	if (isi->iomap.length == 0) {
+		/* No accumulated extent, so just store it. */
+		memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
+	} else if (isi->iomap.addr + isi->iomap.length == iomap->addr) {
+		/* Append this to the accumulated extent. */
+		isi->iomap.length += iomap->length;
+	} else {
+		/* Otherwise, add the retained iomap and store this one. */
+		error = iomap_swapfile_add_extent(isi);
+		if (error)
+			return error;
+		memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
+	}
+	return count;
+}
+
+/*
+ * Iterate a swap file's iomaps to construct physical extents that can be
+ * passed to the swapfile subsystem.
+ */
+int iomap_swapfile_activate(struct swap_info_struct *sis,
+		struct file *swap_file, sector_t *pagespan,
+		const struct iomap_ops *ops)
+{
+	struct iomap_swapfile_info isi = {
+		.sis = sis,
+		.lowest_ppage = (sector_t)-1ULL,
+	};
+	struct address_space *mapping = swap_file->f_mapping;
+	struct inode *inode = mapping->host;
+	loff_t pos = 0;
+	loff_t len = ALIGN_DOWN(i_size_read(inode), PAGE_SIZE);
+	loff_t ret;
+
+	ret = filemap_write_and_wait(inode->i_mapping);
+	if (ret)
+		return ret;
+
+	while (len > 0) {
+		ret = iomap_apply(inode, pos, len, IOMAP_REPORT,
+				ops, &isi, iomap_swapfile_activate_actor);
+		if (ret <= 0)
+			return ret;
+
+		pos += ret;
+		len -= ret;
+	}
+
+	if (isi.iomap.length) {
+		ret = iomap_swapfile_add_extent(&isi);
+		if (ret)
+			return ret;
+	}
+
+	*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
+	sis->max = isi.nr_pages;
+	sis->pages = isi.nr_pages - 1;
+	sis->highest_bit = isi.nr_pages - 1;
+	return isi.nr_extents;
+}
+EXPORT_SYMBOL_GPL(iomap_swapfile_activate);
+#endif /* CONFIG_SWAP */
+
+static loff_t
+iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	sector_t *bno = data, addr;
+
+	if (iomap->type == IOMAP_MAPPED) {
+		addr = (pos - iomap->offset + iomap->addr) >> inode->i_blkbits;
+		if (addr > INT_MAX)
+			WARN(1, "would truncate bmap result\n");
+		else
+			*bno = addr;
+	}
+	return 0;
+}
+
+/* legacy ->bmap interface.  0 is the error return (!) */
+sector_t
+iomap_bmap(struct address_space *mapping, sector_t bno,
+		const struct iomap_ops *ops)
+{
+	struct inode *inode = mapping->host;
+	loff_t pos = bno >> inode->i_blkbits;
+	unsigned blocksize = i_blocksize(inode);
+
+	if (filemap_write_and_wait(mapping))
+		return 0;
+
+	bno = 0;
+	iomap_apply(inode, pos, blocksize, 0, ops, &bno, iomap_bmap_actor);
+	return bno;
+}
+EXPORT_SYMBOL_GPL(iomap_bmap);
diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index 9bb2fe35799d..10205ececc27 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/bio.h>
 
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/zlib.h>
 
@@ -59,7 +60,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
 				>> bufshift;
 	int haveblocks;
 	blkcnt_t blocknum;
-	struct buffer_head *bhs[needblocks + 1];
+	struct buffer_head **bhs;
 	int curbh, curpage;
 
 	if (block_size > deflateBound(1UL << zisofs_block_shift)) {
@@ -80,7 +81,11 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
 
 	/* Because zlib is not thread-safe, do all the I/O at the top. */
 	blocknum = block_start >> bufshift;
-	memset(bhs, 0, (needblocks + 1) * sizeof(struct buffer_head *));
+	bhs = kcalloc(needblocks + 1, sizeof(*bhs), GFP_KERNEL);
+	if (!bhs) {
+		*errp = -ENOMEM;
+		return 0;
+	}
 	haveblocks = isofs_get_blocks(inode, blocknum, bhs, needblocks);
 	ll_rw_block(REQ_OP_READ, 0, haveblocks, bhs);
 
@@ -190,6 +195,7 @@ z_eio:
 b_eio:
 	for (i = 0; i < haveblocks; i++)
 		brelse(bhs[i]);
+	kfree(bhs);
 	return stream.total_out;
 }
 
@@ -305,7 +311,7 @@ static int zisofs_readpage(struct file *file, struct page *page)
 	unsigned int zisofs_pages_per_cblock =
 		PAGE_SHIFT <= zisofs_block_shift ?
 		(1 << (zisofs_block_shift - PAGE_SHIFT)) : 0;
-	struct page *pages[max_t(unsigned, zisofs_pages_per_cblock, 1)];
+	struct page **pages;
 	pgoff_t index = page->index, end_index;
 
 	end_index = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -330,6 +336,12 @@ static int zisofs_readpage(struct file *file, struct page *page)
 		full_page = 0;
 		pcount = 1;
 	}
+	pages = kcalloc(max_t(unsigned int, zisofs_pages_per_cblock, 1),
+					sizeof(*pages), GFP_KERNEL);
+	if (!pages) {
+		unlock_page(page);
+		return -ENOMEM;
+	}
 	pages[full_page] = page;
 
 	for (i = 0; i < pcount; i++, index++) {
@@ -357,6 +369,7 @@ static int zisofs_readpage(struct file *file, struct page *page)
 	}			
 
 	/* At this point, err contains 0 or -EIO depending on the "critical" page */
+	kfree(pages);
 	return err;
 }
 
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index bc258a4402f6..ec3fba7d492f 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -394,7 +394,10 @@ static int parse_options(char *options, struct iso9660_options *popt)
 			break;
 #ifdef CONFIG_JOLIET
 		case Opt_iocharset:
+			kfree(popt->iocharset);
 			popt->iocharset = match_strdup(&args[0]);
+			if (!popt->iocharset)
+				return 0;
 			break;
 #endif
 		case Opt_map_a:
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index dfb057900e79..8ef6b6daaa7a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -114,7 +114,7 @@ void __jbd2_debug(int level, const char *file, const char *func,
 	va_start(args, fmt);
 	vaf.fmt = fmt;
 	vaf.va = &args;
-	printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf);
+	printk(KERN_DEBUG "%s: (%s, %u): %pV", file, func, line, &vaf);
 	va_end(args);
 }
 EXPORT_SYMBOL(__jbd2_debug);
@@ -2302,8 +2302,7 @@ static void jbd2_journal_destroy_slabs(void)
 	int i;
 
 	for (i = 0; i < JBD2_MAX_SLABS; i++) {
-		if (jbd2_slab[i])
-			kmem_cache_destroy(jbd2_slab[i]);
+		kmem_cache_destroy(jbd2_slab[i]);
 		jbd2_slab[i] = NULL;
 	}
 }
@@ -2404,10 +2403,8 @@ static int jbd2_journal_init_journal_head_cache(void)
 
 static void jbd2_journal_destroy_journal_head_cache(void)
 {
-	if (jbd2_journal_head_cache) {
-		kmem_cache_destroy(jbd2_journal_head_cache);
-		jbd2_journal_head_cache = NULL;
-	}
+	kmem_cache_destroy(jbd2_journal_head_cache);
+	jbd2_journal_head_cache = NULL;
 }
 
 /*
@@ -2665,11 +2662,10 @@ static int __init jbd2_journal_init_handle_cache(void)
 
 static void jbd2_journal_destroy_handle_cache(void)
 {
-	if (jbd2_handle_cache)
-		kmem_cache_destroy(jbd2_handle_cache);
-	if (jbd2_inode_cache)
-		kmem_cache_destroy(jbd2_inode_cache);
-
+	kmem_cache_destroy(jbd2_handle_cache);
+	jbd2_handle_cache = NULL;
+	kmem_cache_destroy(jbd2_inode_cache);
+	jbd2_inode_cache = NULL;
 }
 
 /*
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 696ef15ec942..240779e4689c 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -180,14 +180,10 @@ static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal,
 
 void jbd2_journal_destroy_revoke_caches(void)
 {
-	if (jbd2_revoke_record_cache) {
-		kmem_cache_destroy(jbd2_revoke_record_cache);
-		jbd2_revoke_record_cache = NULL;
-	}
-	if (jbd2_revoke_table_cache) {
-		kmem_cache_destroy(jbd2_revoke_table_cache);
-		jbd2_revoke_table_cache = NULL;
-	}
+	kmem_cache_destroy(jbd2_revoke_record_cache);
+	jbd2_revoke_record_cache = NULL;
+	kmem_cache_destroy(jbd2_revoke_table_cache);
+	jbd2_revoke_table_cache = NULL;
 }
 
 int __init jbd2_journal_init_revoke_caches(void)
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index ac311037d7a5..51dd68e67b0f 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -49,10 +49,8 @@ int __init jbd2_journal_init_transaction_cache(void)
 
 void jbd2_journal_destroy_transaction_cache(void)
 {
-	if (transaction_cache) {
-		kmem_cache_destroy(transaction_cache);
-		transaction_cache = NULL;
-	}
+	kmem_cache_destroy(transaction_cache);
+	transaction_cache = NULL;
 }
 
 void jbd2_journal_free_transaction(transaction_t *transaction)
@@ -532,6 +530,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type,
 	 */
 	ret = start_this_handle(journal, handle, GFP_NOFS);
 	if (ret < 0) {
+		handle->h_journal = journal;
 		jbd2_journal_free_reserved(handle);
 		return ret;
 	}
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 0a754f38462e..e5a6deb38e1e 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -209,8 +209,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
 		  __func__, inode->i_ino, inode->i_mode, inode->i_nlink,
 		  f->inocache->pino_nlink, inode->i_mapping->nrpages);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
  fail:
@@ -430,8 +429,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 	mutex_unlock(&dir_f->sem);
 	jffs2_complete_reservation(c);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
  fail:
@@ -575,8 +573,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	mutex_unlock(&dir_f->sem);
 	jffs2_complete_reservation(c);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
  fail:
@@ -747,8 +744,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	mutex_unlock(&dir_f->sem);
 	jffs2_complete_reservation(c);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
  fail:
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index f60dee7faf03..87bdf0f4cba1 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -342,7 +342,7 @@ static void jffs2_put_super (struct super_block *sb)
 static void jffs2_kill_sb(struct super_block *sb)
 {
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
-	if (!sb_rdonly(sb))
+	if (c && !sb_rdonly(sb))
 		jffs2_stop_garbage_collect_thread(c);
 	kill_mtd_super(sb);
 	kfree(c);
diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c
index a70907606025..35a5b2a81ae0 100644
--- a/fs/jfs/jfs_debug.c
+++ b/fs/jfs/jfs_debug.c
@@ -29,7 +29,6 @@
 
 #ifdef PROC_FS_JFS /* see jfs_debug.h */
 
-static struct proc_dir_entry *base;
 #ifdef CONFIG_JFS_DEBUG
 static int jfs_loglevel_proc_show(struct seq_file *m, void *v)
 {
@@ -66,43 +65,29 @@ static const struct file_operations jfs_loglevel_proc_fops = {
 };
 #endif
 
-static struct {
-	const char	*name;
-	const struct file_operations *proc_fops;
-} Entries[] = {
-#ifdef CONFIG_JFS_STATISTICS
-	{ "lmstats",	&jfs_lmstats_proc_fops, },
-	{ "txstats",	&jfs_txstats_proc_fops, },
-	{ "xtstat",	&jfs_xtstat_proc_fops, },
-	{ "mpstat",	&jfs_mpstat_proc_fops, },
-#endif
-#ifdef CONFIG_JFS_DEBUG
-	{ "TxAnchor",	&jfs_txanchor_proc_fops, },
-	{ "loglevel",	&jfs_loglevel_proc_fops }
-#endif
-};
-#define NPROCENT	ARRAY_SIZE(Entries)
-
 void jfs_proc_init(void)
 {
-	int i;
+	struct proc_dir_entry *base;
 
-	if (!(base = proc_mkdir("fs/jfs", NULL)))
+	base = proc_mkdir("fs/jfs", NULL);
+	if (!base)
 		return;
 
-	for (i = 0; i < NPROCENT; i++)
-		proc_create(Entries[i].name, 0, base, Entries[i].proc_fops);
+#ifdef CONFIG_JFS_STATISTICS
+	proc_create_single("lmstats", 0, base, jfs_lmstats_proc_show);
+	proc_create_single("txstats", 0, base, jfs_txstats_proc_show);
+	proc_create_single("xtstat", 0, base, jfs_xtstat_proc_show);
+	proc_create_single("mpstat", 0, base, jfs_mpstat_proc_show);
+#endif
+#ifdef CONFIG_JFS_DEBUG
+	proc_create_single("TxAnchor", 0, base, jfs_txanchor_proc_show);
+	proc_create("loglevel", 0, base, &jfs_loglevel_proc_fops);
+#endif
 }
 
 void jfs_proc_clean(void)
 {
-	int i;
-
-	if (base) {
-		for (i = 0; i < NPROCENT; i++)
-			remove_proc_entry(Entries[i].name, base);
-		remove_proc_entry("fs/jfs", NULL);
-	}
+	remove_proc_subtree("fs/jfs", NULL);
 }
 
 #endif /* PROC_FS_JFS */
diff --git a/fs/jfs/jfs_debug.h b/fs/jfs/jfs_debug.h
index eafd1300a00b..0d9e35da8462 100644
--- a/fs/jfs/jfs_debug.h
+++ b/fs/jfs/jfs_debug.h
@@ -62,7 +62,7 @@ extern void jfs_proc_clean(void);
 
 extern int jfsloglevel;
 
-extern const struct file_operations jfs_txanchor_proc_fops;
+int jfs_txanchor_proc_show(struct seq_file *m, void *v);
 
 /* information message: e.g., configuration, major event */
 #define jfs_info(fmt, arg...) do {			\
@@ -105,10 +105,10 @@ extern const struct file_operations jfs_txanchor_proc_fops;
  *	----------
  */
 #ifdef	CONFIG_JFS_STATISTICS
-extern const struct file_operations jfs_lmstats_proc_fops;
-extern const struct file_operations jfs_txstats_proc_fops;
-extern const struct file_operations jfs_mpstat_proc_fops;
-extern const struct file_operations jfs_xtstat_proc_fops;
+int jfs_lmstats_proc_show(struct seq_file *m, void *v);
+int jfs_txstats_proc_show(struct seq_file *m, void *v);
+int jfs_mpstat_proc_show(struct seq_file *m, void *v);
+int jfs_xtstat_proc_show(struct seq_file *m, void *v);
 
 #define	INCREMENT(x)		((x)++)
 #define	DECREMENT(x)		((x)--)
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 0e5d412c0b01..6b68df395892 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -2493,7 +2493,7 @@ exit:
 }
 
 #ifdef CONFIG_JFS_STATISTICS
-static int jfs_lmstats_proc_show(struct seq_file *m, void *v)
+int jfs_lmstats_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m,
 		       "JFS Logmgr stats\n"
@@ -2510,16 +2510,4 @@ static int jfs_lmstats_proc_show(struct seq_file *m, void *v)
 		       lmStat.partial_page);
 	return 0;
 }
-
-static int jfs_lmstats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, jfs_lmstats_proc_show, NULL);
-}
-
-const struct file_operations jfs_lmstats_proc_fops = {
-	.open		= jfs_lmstats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif /* CONFIG_JFS_STATISTICS */
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 1a3b0cc22ad3..fa2c6824c7f2 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -815,7 +815,7 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len)
 }
 
 #ifdef CONFIG_JFS_STATISTICS
-static int jfs_mpstat_proc_show(struct seq_file *m, void *v)
+int jfs_mpstat_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m,
 		       "JFS Metapage statistics\n"
@@ -828,16 +828,4 @@ static int jfs_mpstat_proc_show(struct seq_file *m, void *v)
 		       mpStat.lockwait);
 	return 0;
 }
-
-static int jfs_mpstat_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, jfs_mpstat_proc_show, NULL);
-}
-
-const struct file_operations jfs_mpstat_proc_fops = {
-	.open		= jfs_mpstat_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index 4d973524c887..a5663cb621d8 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -2998,7 +2998,7 @@ int jfs_sync(void *arg)
 }
 
 #if defined(CONFIG_PROC_FS) && defined(CONFIG_JFS_DEBUG)
-static int jfs_txanchor_proc_show(struct seq_file *m, void *v)
+int jfs_txanchor_proc_show(struct seq_file *m, void *v)
 {
 	char *freewait;
 	char *freelockwait;
@@ -3032,22 +3032,10 @@ static int jfs_txanchor_proc_show(struct seq_file *m, void *v)
 		       list_empty(&TxAnchor.unlock_queue) ? "" : "not ");
 	return 0;
 }
-
-static int jfs_txanchor_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, jfs_txanchor_proc_show, NULL);
-}
-
-const struct file_operations jfs_txanchor_proc_fops = {
-	.open		= jfs_txanchor_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 #if defined(CONFIG_PROC_FS) && defined(CONFIG_JFS_STATISTICS)
-static int jfs_txstats_proc_show(struct seq_file *m, void *v)
+int jfs_txstats_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m,
 		       "JFS TxStats\n"
@@ -3072,16 +3060,4 @@ static int jfs_txstats_proc_show(struct seq_file *m, void *v)
 		       TxStat.txLockAlloc_freelock);
 	return 0;
 }
-
-static int jfs_txstats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, jfs_txstats_proc_show, NULL);
-}
-
-const struct file_operations jfs_txstats_proc_fops = {
-	.open		= jfs_txstats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c
index 5cde6d2fcfca..2c200b5256a6 100644
--- a/fs/jfs/jfs_xtree.c
+++ b/fs/jfs/jfs_xtree.c
@@ -3874,7 +3874,7 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size)
 }
 
 #ifdef CONFIG_JFS_STATISTICS
-static int jfs_xtstat_proc_show(struct seq_file *m, void *v)
+int jfs_xtstat_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m,
 		       "JFS Xtree statistics\n"
@@ -3887,16 +3887,4 @@ static int jfs_xtstat_proc_show(struct seq_file *m, void *v)
 		       xtStat.split);
 	return 0;
 }
-
-static int jfs_xtstat_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, jfs_xtstat_proc_show, NULL);
-}
-
-const struct file_operations jfs_xtstat_proc_fops = {
-	.open		= jfs_xtstat_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index b41596d71858..56c3fcbfe80e 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -178,8 +178,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
 		unlock_new_inode(ip);
 		iput(ip);
 	} else {
-		unlock_new_inode(ip);
-		d_instantiate(dentry, ip);
+		d_instantiate_new(dentry, ip);
 	}
 
       out2:
@@ -313,8 +312,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
 		unlock_new_inode(ip);
 		iput(ip);
 	} else {
-		unlock_new_inode(ip);
-		d_instantiate(dentry, ip);
+		d_instantiate_new(dentry, ip);
 	}
 
       out2:
@@ -1059,8 +1057,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 		unlock_new_inode(ip);
 		iput(ip);
 	} else {
-		unlock_new_inode(ip);
-		d_instantiate(dentry, ip);
+		d_instantiate_new(dentry, ip);
 	}
 
       out2:
@@ -1447,8 +1444,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
 		unlock_new_inode(ip);
 		iput(ip);
 	} else {
-		unlock_new_inode(ip);
-		d_instantiate(dentry, ip);
+		d_instantiate_new(dentry, ip);
 	}
 
       out1:
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index fd5ce883072e..2015d8c45e4a 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -348,11 +348,11 @@ static void kernfs_vma_open(struct vm_area_struct *vma)
 	kernfs_put_active(of->kn);
 }
 
-static int kernfs_vma_fault(struct vm_fault *vmf)
+static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf)
 {
 	struct file *file = vmf->vma->vm_file;
 	struct kernfs_open_file *of = kernfs_of(file);
-	int ret;
+	vm_fault_t ret;
 
 	if (!of->vm_ops)
 		return VM_FAULT_SIGBUS;
@@ -368,11 +368,11 @@ static int kernfs_vma_fault(struct vm_fault *vmf)
 	return ret;
 }
 
-static int kernfs_vma_page_mkwrite(struct vm_fault *vmf)
+static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf)
 {
 	struct file *file = vmf->vma->vm_file;
 	struct kernfs_open_file *of = kernfs_of(file);
-	int ret;
+	vm_fault_t ret;
 
 	if (!of->vm_ops)
 		return VM_FAULT_SIGBUS;
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 26dd9a50f383..ff2716f9322e 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -316,6 +316,7 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
 
 	info->root = root;
 	info->ns = ns;
+	INIT_LIST_HEAD(&info->node);
 
 	sb = sget_userns(fs_type, kernfs_test_super, kernfs_set_super, flags,
 			 &init_user_ns, info);
diff --git a/fs/locks.c b/fs/locks.c
index 62bbe8b31f26..05e211be8684 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2788,22 +2788,10 @@ static const struct seq_operations locks_seq_operations = {
 	.show	= locks_show,
 };
 
-static int locks_open(struct inode *inode, struct file *filp)
-{
-	return seq_open_private(filp, &locks_seq_operations,
-					sizeof(struct locks_iterator));
-}
-
-static const struct file_operations proc_locks_operations = {
-	.open		= locks_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
-
 static int __init proc_locks_init(void)
 {
-	proc_create("locks", 0, NULL, &proc_locks_operations);
+	proc_create_seq_private("locks", 0, NULL, &locks_seq_operations,
+			sizeof(struct locks_iterator), NULL);
 	return 0;
 }
 fs_initcall(proc_locks_init);
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index ccf0f00030bf..1a6084d2b02e 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -28,13 +28,9 @@ static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, un
 		return ERR_PTR(-ENAMETOOLONG);
 
 	ino = minix_inode_by_name(dentry);
-	if (ino) {
+	if (ino)
 		inode = minix_iget(dir->i_sb, ino);
-		if (IS_ERR(inode))
-			return ERR_CAST(inode);
-	}
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 static int minix_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev)
diff --git a/fs/namei.c b/fs/namei.c
index 186bd2464fd5..6df1f61855d6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -984,13 +984,15 @@ static bool safe_hardlink_source(struct inode *inode)
  */
 static int may_linkat(struct path *link)
 {
-	struct inode *inode;
+	struct inode *inode = link->dentry->d_inode;
+
+	/* Inode writeback is not safe when the uid or gid are invalid. */
+	if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+		return -EOVERFLOW;
 
 	if (!sysctl_protected_hardlinks)
 		return 0;
 
-	inode = link->dentry->d_inode;
-
 	/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
 	 * otherwise, it must be a safe source.
 	 */
@@ -1438,10 +1440,8 @@ static int path_parent_directory(struct path *path)
 static int follow_dotdot(struct nameidata *nd)
 {
 	while(1) {
-		if (nd->path.dentry == nd->root.dentry &&
-		    nd->path.mnt == nd->root.mnt) {
+		if (path_equal(&nd->path, &nd->root))
 			break;
-		}
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
 			int ret = path_parent_directory(&nd->path);
 			if (ret)
@@ -2749,6 +2749,11 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 	BUG_ON(!inode);
 
 	BUG_ON(victim->d_parent->d_inode != dir);
+
+	/* Inode writeback is not safe when the uid or gid are invalid. */
+	if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+		return -EOVERFLOW;
+
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
 	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
@@ -3367,7 +3372,9 @@ finish_open_created:
 		goto out;
 	*opened |= FILE_OPENED;
 opened:
-	error = ima_file_check(file, op->acc_mode, *opened);
+	error = open_check_o_direct(file);
+	if (!error)
+		error = ima_file_check(file, op->acc_mode, *opened);
 	if (!error && will_truncate)
 		error = handle_truncate(file);
 out:
@@ -3447,6 +3454,9 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	error = finish_open(file, child, NULL, opened);
 	if (error)
 		goto out2;
+	error = open_check_o_direct(file);
+	if (error)
+		fput(file);
 out2:
 	mnt_drop_write(path.mnt);
 out:
@@ -3672,7 +3682,8 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
 	if (error)
 		return error;
 
-	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
+	if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
+	    !ns_capable(dentry->d_sb->s_user_ns, CAP_MKNOD))
 		return -EPERM;
 
 	if (!dir->i_op->mknod)
@@ -3847,11 +3858,11 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (error)
 		goto out;
 
-	shrink_dcache_parent(dentry);
 	error = dir->i_op->rmdir(dir, dentry);
 	if (error)
 		goto out;
 
+	shrink_dcache_parent(dentry);
 	dentry->d_inode->i_flags |= S_DEAD;
 	dont_mount(dentry);
 	detach_mounts(dentry);
@@ -4434,8 +4445,6 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		    old_dir->i_nlink >= max_links)
 			goto out;
 	}
-	if (is_dir && !(flags & RENAME_EXCHANGE) && target)
-		shrink_dcache_parent(new_dentry);
 	if (!is_dir) {
 		error = try_break_deleg(source, delegated_inode);
 		if (error)
@@ -4452,8 +4461,10 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		goto out;
 
 	if (!(flags & RENAME_EXCHANGE) && target) {
-		if (is_dir)
+		if (is_dir) {
+			shrink_dcache_parent(new_dentry);
 			target->i_flags |= S_DEAD;
+		}
 		dont_mount(new_dentry);
 		detach_mounts(new_dentry);
 	}
diff --git a/fs/namespace.c b/fs/namespace.c
index e398f32d7541..8ddd14806799 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1089,7 +1089,8 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 			goto out_free;
 	}
 
-	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
+	mnt->mnt.mnt_flags = old->mnt.mnt_flags;
+	mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
 	/* Don't allow unprivileged users to change mount flags */
 	if (flag & CL_UNPRIVILEGED) {
 		mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
@@ -1589,7 +1590,7 @@ static int do_umount(struct mount *mnt, int flags)
 		 * Special case for "unmounting" root ...
 		 * we just try to remount it readonly.
 		 */
-		if (!capable(CAP_SYS_ADMIN))
+		if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
 			return -EPERM;
 		down_write(&sb->s_umount);
 		if (!sb_rdonly(sb))
@@ -2332,7 +2333,7 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags,
 	down_write(&sb->s_umount);
 	if (ms_flags & MS_BIND)
 		err = change_mount_flags(path->mnt, ms_flags);
-	else if (!capable(CAP_SYS_ADMIN))
+	else if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
 		err = -EPERM;
 	else
 		err = do_remount_sb(sb, sb_flags, data, 0);
@@ -2814,7 +2815,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 		mnt_flags |= MNT_NODIRATIME;
 	if (flags & MS_STRICTATIME)
 		mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
-	if (flags & SB_RDONLY)
+	if (flags & MS_RDONLY)
 		mnt_flags |= MNT_READONLY;
 
 	/* The default atime for remount is preservation */
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index b9129e2befea..bbc91d7ca1bd 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1067,7 +1067,6 @@ void nfs_clients_init(struct net *net)
 }
 
 #ifdef CONFIG_PROC_FS
-static int nfs_server_list_open(struct inode *inode, struct file *file);
 static void *nfs_server_list_start(struct seq_file *p, loff_t *pos);
 static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos);
 static void nfs_server_list_stop(struct seq_file *p, void *v);
@@ -1080,14 +1079,6 @@ static const struct seq_operations nfs_server_list_ops = {
 	.show	= nfs_server_list_show,
 };
 
-static const struct file_operations nfs_server_list_fops = {
-	.open		= nfs_server_list_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
-static int nfs_volume_list_open(struct inode *inode, struct file *file);
 static void *nfs_volume_list_start(struct seq_file *p, loff_t *pos);
 static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos);
 static void nfs_volume_list_stop(struct seq_file *p, void *v);
@@ -1100,23 +1091,6 @@ static const struct seq_operations nfs_volume_list_ops = {
 	.show	= nfs_volume_list_show,
 };
 
-static const struct file_operations nfs_volume_list_fops = {
-	.open		= nfs_volume_list_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
-/*
- * open "/proc/fs/nfsfs/servers" which provides a summary of servers with which
- * we're dealing
- */
-static int nfs_server_list_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &nfs_server_list_ops,
-			   sizeof(struct seq_net_private));
-}
-
 /*
  * set up the iterator to start reading from the server list and return the first item
  */
@@ -1185,15 +1159,6 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
 }
 
 /*
- * open "/proc/fs/nfsfs/volumes" which provides a summary of extant volumes
- */
-static int nfs_volume_list_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &nfs_volume_list_ops,
-			   sizeof(struct seq_net_private));
-}
-
-/*
  * set up the iterator to start reading from the volume list and return the first item
  */
 static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
@@ -1278,14 +1243,14 @@ int nfs_fs_proc_net_init(struct net *net)
 		goto error_0;
 
 	/* a file of servers with which we're dealing */
-	p = proc_create("servers", S_IFREG|S_IRUGO,
-			nn->proc_nfsfs, &nfs_server_list_fops);
+	p = proc_create_net("servers", S_IFREG|S_IRUGO, nn->proc_nfsfs,
+			&nfs_server_list_ops, sizeof(struct seq_net_private));
 	if (!p)
 		goto error_1;
 
 	/* a file of volumes that we have mounted */
-	p = proc_create("volumes", S_IFREG|S_IRUGO,
-			nn->proc_nfsfs, &nfs_volume_list_fops);
+	p = proc_create_net("volumes", S_IFREG|S_IRUGO, nn->proc_nfsfs,
+			&nfs_volume_list_ops, sizeof(struct seq_net_private));
 	if (!p)
 		goto error_1;
 	return 0;
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 70b8bf781fce..a43dfedd69ec 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -227,7 +227,7 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
 	if (!buf)
 		return -ENOMEM;
 
-	rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
+	rq = blk_get_request(q, REQ_OP_SCSI_IN, 0);
 	if (IS_ERR(rq)) {
 		error = -ENOMEM;
 		goto out_free_buf;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 2410b093a2e6..b0555d7d8200 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1201,6 +1201,28 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		break;
 	case S_IFDIR:
 		host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
+		if (!host_err && unlikely(d_unhashed(dchild))) {
+			struct dentry *d;
+			d = lookup_one_len(dchild->d_name.name,
+					   dchild->d_parent,
+					   dchild->d_name.len);
+			if (IS_ERR(d)) {
+				host_err = PTR_ERR(d);
+				break;
+			}
+			if (unlikely(d_is_negative(d))) {
+				dput(d);
+				err = nfserr_serverfault;
+				goto out;
+			}
+			dput(resfhp->fh_dentry);
+			resfhp->fh_dentry = dget(d);
+			err = fh_update(resfhp);
+			dput(dchild);
+			dchild = d;
+			if (err)
+				goto out;
+		}
 		break;
 	case S_IFCHR:
 	case S_IFBLK:
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1a2894aa0194..dd52d3f82e8d 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -46,8 +46,7 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
 	int err = nilfs_add_link(dentry, inode);
 
 	if (!err) {
-		d_instantiate(dentry, inode);
-		unlock_new_inode(inode);
+		d_instantiate_new(dentry, inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
@@ -243,8 +242,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto out_fail;
 
 	nilfs_mark_inode_dirty(inode);
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 out:
 	if (!err)
 		err = nilfs_transaction_commit(dir->i_sb);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index d51e1bb781cf..d94e8031fe5f 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -92,7 +92,7 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 				       u32 event_mask,
 				       const void *data, int data_type)
 {
-	__u32 marks_mask, marks_ignored_mask;
+	__u32 marks_mask = 0, marks_ignored_mask = 0;
 	const struct path *path = data;
 
 	pr_debug("%s: inode_mark=%p vfsmnt_mark=%p mask=%x data=%p"
@@ -108,24 +108,20 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 	    !d_can_lookup(path->dentry))
 		return false;
 
-	if (inode_mark && vfsmnt_mark) {
-		marks_mask = (vfsmnt_mark->mask | inode_mark->mask);
-		marks_ignored_mask = (vfsmnt_mark->ignored_mask | inode_mark->ignored_mask);
-	} else if (inode_mark) {
-		/*
-		 * if the event is for a child and this inode doesn't care about
-		 * events on the child, don't send it!
-		 */
-		if ((event_mask & FS_EVENT_ON_CHILD) &&
-		    !(inode_mark->mask & FS_EVENT_ON_CHILD))
-			return false;
-		marks_mask = inode_mark->mask;
-		marks_ignored_mask = inode_mark->ignored_mask;
-	} else if (vfsmnt_mark) {
-		marks_mask = vfsmnt_mark->mask;
-		marks_ignored_mask = vfsmnt_mark->ignored_mask;
-	} else {
-		BUG();
+	/*
+	 * if the event is for a child and this inode doesn't care about
+	 * events on the child, don't send it!
+	 */
+	if (inode_mark &&
+	    (!(event_mask & FS_EVENT_ON_CHILD) ||
+	     (inode_mark->mask & FS_EVENT_ON_CHILD))) {
+		marks_mask |= inode_mark->mask;
+		marks_ignored_mask |= inode_mark->ignored_mask;
+	}
+
+	if (vfsmnt_mark) {
+		marks_mask |= vfsmnt_mark->mask;
+		marks_ignored_mask |= vfsmnt_mark->ignored_mask;
 	}
 
 	if (d_is_dir(path->dentry) &&
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 219b269c737e..613ec7e5a465 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -192,8 +192,9 @@ static int send_to_group(struct inode *to_tell,
 			 struct fsnotify_iter_info *iter_info)
 {
 	struct fsnotify_group *group = NULL;
-	__u32 inode_test_mask = 0;
-	__u32 vfsmount_test_mask = 0;
+	__u32 test_mask = (mask & ~FS_EVENT_ON_CHILD);
+	__u32 marks_mask = 0;
+	__u32 marks_ignored_mask = 0;
 
 	if (unlikely(!inode_mark && !vfsmount_mark)) {
 		BUG();
@@ -213,29 +214,25 @@ static int send_to_group(struct inode *to_tell,
 	/* does the inode mark tell us to do something? */
 	if (inode_mark) {
 		group = inode_mark->group;
-		inode_test_mask = (mask & ~FS_EVENT_ON_CHILD);
-		inode_test_mask &= inode_mark->mask;
-		inode_test_mask &= ~inode_mark->ignored_mask;
+		marks_mask |= inode_mark->mask;
+		marks_ignored_mask |= inode_mark->ignored_mask;
 	}
 
 	/* does the vfsmount_mark tell us to do something? */
 	if (vfsmount_mark) {
-		vfsmount_test_mask = (mask & ~FS_EVENT_ON_CHILD);
 		group = vfsmount_mark->group;
-		vfsmount_test_mask &= vfsmount_mark->mask;
-		vfsmount_test_mask &= ~vfsmount_mark->ignored_mask;
-		if (inode_mark)
-			vfsmount_test_mask &= ~inode_mark->ignored_mask;
+		marks_mask |= vfsmount_mark->mask;
+		marks_ignored_mask |= vfsmount_mark->ignored_mask;
 	}
 
 	pr_debug("%s: group=%p to_tell=%p mask=%x inode_mark=%p"
-		 " inode_test_mask=%x vfsmount_mark=%p vfsmount_test_mask=%x"
+		 " vfsmount_mark=%p marks_mask=%x marks_ignored_mask=%x"
 		 " data=%p data_is=%d cookie=%d\n",
-		 __func__, group, to_tell, mask, inode_mark,
-		 inode_test_mask, vfsmount_mark, vfsmount_test_mask, data,
+		 __func__, group, to_tell, mask, inode_mark, vfsmount_mark,
+		 marks_mask, marks_ignored_mask, data,
 		 data_is, cookie);
 
-	if (!inode_test_mask && !vfsmount_test_mask)
+	if (!(test_mask & marks_mask & ~marks_ignored_mask))
 		return 0;
 
 	return group->ops->handle_event(group, to_tell, inode_mark,
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 91a8889abf9b..ea8c551bcd7e 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -570,16 +570,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 		     current_page, vec_len, vec_start);
 
 		len = bio_add_page(bio, page, vec_len, vec_start);
-		if (len != vec_len) {
-			mlog(ML_ERROR, "Adding page[%d] to bio failed, "
-			     "page %p, len %d, vec_len %u, vec_start %u, "
-			     "bi_sector %llu\n", current_page, page, len,
-			     vec_len, vec_start,
-			     (unsigned long long)bio->bi_iter.bi_sector);
-			bio_put(bio);
-			bio = ERR_PTR(-EIO);
-			return bio;
-		}
+		if (len != vec_len) break;
 
 		cs += vec_len / (PAGE_SIZE/spp);
 		vec_start = 0;
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 01c6b3894406..7869622af22a 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4250,10 +4250,11 @@ out:
 static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 			 struct dentry *new_dentry, bool preserve)
 {
-	int error;
+	int error, had_lock;
 	struct inode *inode = d_inode(old_dentry);
 	struct buffer_head *old_bh = NULL;
 	struct inode *new_orphan_inode = NULL;
+	struct ocfs2_lock_holder oh;
 
 	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)))
 		return -EOPNOTSUPP;
@@ -4295,6 +4296,14 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 		goto out;
 	}
 
+	had_lock = ocfs2_inode_lock_tracker(new_orphan_inode, NULL, 1,
+					    &oh);
+	if (had_lock < 0) {
+		error = had_lock;
+		mlog_errno(error);
+		goto out;
+	}
+
 	/* If the security isn't preserved, we need to re-initialize them. */
 	if (!preserve) {
 		error = ocfs2_init_security_and_acl(dir, new_orphan_inode,
@@ -4302,14 +4311,15 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 		if (error)
 			mlog_errno(error);
 	}
-out:
 	if (!error) {
 		error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode,
 						       new_dentry);
 		if (error)
 			mlog_errno(error);
 	}
+	ocfs2_inode_unlock_tracker(new_orphan_inode, 1, &oh, had_lock);
 
+out:
 	if (new_orphan_inode) {
 		/*
 		 * We need to open_unlock the inode no matter whether we
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index b7146526afff..4bee3a72b9f3 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -305,11 +305,10 @@ static struct dentry *omfs_lookup(struct inode *dir, struct dentry *dentry,
 		ino_t ino = be64_to_cpu(oi->i_head.h_self);
 		brelse(bh);
 		inode = omfs_iget(dir->i_sb, ino);
-		if (IS_ERR(inode))
-			return ERR_CAST(inode);
+	} else if (bh != ERR_PTR(-ENOENT)) {
+		inode = ERR_CAST(bh);
 	}
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 /* sanity check block's self pointer */
diff --git a/fs/open.c b/fs/open.c
index c5ee7cd60424..d0e955b558ad 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -724,6 +724,16 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 	return ksys_fchown(fd, user, group);
 }
 
+int open_check_o_direct(struct file *f)
+{
+	/* NB: we're sure to have correct a_ops only after f_op->open */
+	if (f->f_flags & O_DIRECT) {
+		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
+			return -EINVAL;
+	}
+	return 0;
+}
+
 static int do_dentry_open(struct file *f,
 			  struct inode *inode,
 			  int (*open)(struct inode *, struct file *),
@@ -745,7 +755,7 @@ static int do_dentry_open(struct file *f,
 	if (unlikely(f->f_flags & O_PATH)) {
 		f->f_mode = FMODE_PATH;
 		f->f_op = &empty_fops;
-		goto done;
+		return 0;
 	}
 
 	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
@@ -798,12 +808,7 @@ static int do_dentry_open(struct file *f,
 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
-done:
-	/* NB: we're sure to have correct a_ops only after f_op->open */
-	error = -EINVAL;
-	if ((f->f_flags & O_DIRECT) &&
-	    (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO))
-	    	goto out_fput;
+
 	return 0;
 
 cleanup_all:
@@ -818,9 +823,6 @@ cleanup_file:
 	f->f_path.dentry = NULL;
 	f->f_inode = NULL;
 	return error;
-out_fput:
-    	fput(f);
-	return error;
 }
 
 /**
@@ -918,14 +920,20 @@ struct file *dentry_open(const struct path *path, int flags,
 	BUG_ON(!path->mnt);
 
 	f = get_empty_filp();
-	if (IS_ERR(f))
-		return f;
-
-	f->f_flags = flags;
-	error = vfs_open(path, f, cred);
-	if (error) {
-		put_filp(f);
-		return ERR_PTR(error);
+	if (!IS_ERR(f)) {
+		f->f_flags = flags;
+		error = vfs_open(path, f, cred);
+		if (!error) {
+			/* from now on we need fput() to dispose of f */
+			error = open_check_o_direct(f);
+			if (error) {
+				fput(f);
+				f = ERR_PTR(error);
+			}
+		} else { 
+			put_filp(f);
+			f = ERR_PTR(error);
+		}
 	}
 	return f;
 }
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 2200662a9bf1..607092f367ad 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -256,8 +256,7 @@ found:
 		break;
 	}
 
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 static int openpromfs_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index 6e3134e6d98a..365cd73d9109 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -75,8 +75,7 @@ static int orangefs_create(struct inode *dir,
 		     get_khandle_from_ino(inode),
 		     dentry);
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 	ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
@@ -111,7 +110,6 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
 	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
 	struct orangefs_kernel_op_s *new_op;
 	struct inode *inode;
-	struct dentry *res;
 	int ret = -EINVAL;
 
 	/*
@@ -159,65 +157,18 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
 		     new_op->downcall.resp.lookup.refn.fs_id,
 		     ret);
 
-	if (ret < 0) {
-		if (ret == -ENOENT) {
-			/*
-			 * if no inode was found, add a negative dentry to
-			 * dcache anyway; if we don't, we don't hold expected
-			 * lookup semantics and we most noticeably break
-			 * during directory renames.
-			 *
-			 * however, if the operation failed or exited, do not
-			 * add the dentry (e.g. in the case that a touch is
-			 * issued on a file that already exists that was
-			 * interrupted during this lookup -- no need to add
-			 * another negative dentry for an existing file)
-			 */
-
-			gossip_debug(GOSSIP_NAME_DEBUG,
-				     "orangefs_lookup: Adding *negative* dentry "
-				     "%p for %pd\n",
-				     dentry,
-				     dentry);
-
-			d_add(dentry, NULL);
-			res = NULL;
-			goto out;
-		}
-
+	if (ret >= 0) {
+		orangefs_set_timeout(dentry);
+		inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
+	} else if (ret == -ENOENT) {
+		inode = NULL;
+	} else {
 		/* must be a non-recoverable error */
-		res = ERR_PTR(ret);
-		goto out;
-	}
-
-	orangefs_set_timeout(dentry);
-
-	inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
-	if (IS_ERR(inode)) {
-		gossip_debug(GOSSIP_NAME_DEBUG,
-			"error %ld from iget\n", PTR_ERR(inode));
-		res = ERR_CAST(inode);
-		goto out;
+		inode = ERR_PTR(ret);
 	}
 
-	gossip_debug(GOSSIP_NAME_DEBUG,
-		     "%s:%s:%d "
-		     "Found good inode [%lu] with count [%d]\n",
-		     __FILE__,
-		     __func__,
-		     __LINE__,
-		     inode->i_ino,
-		     (int)atomic_read(&inode->i_count));
-
-	/* update dentry/inode pair into dcache */
-	res = d_splice_alias(inode, dentry);
-
-	gossip_debug(GOSSIP_NAME_DEBUG,
-		     "Lookup success (inode ct = %d)\n",
-		     (int)atomic_read(&inode->i_count));
-out:
 	op_release(new_op);
-	return res;
+	return d_splice_alias(inode, dentry);
 }
 
 /* return 0 on success; non-zero otherwise */
@@ -332,8 +283,7 @@ static int orangefs_symlink(struct inode *dir,
 		     "Assigned symlink inode new number of %pU\n",
 		     get_khandle_from_ino(inode));
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 	ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
@@ -402,8 +352,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 		     "Assigned dir inode new number of %pU\n",
 		     get_khandle_from_ino(inode));
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 	ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index 3ae5fdba0225..10796d3fe27d 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -579,6 +579,11 @@ void orangefs_kill_sb(struct super_block *sb)
 	/* provided sb cleanup */
 	kill_anon_super(sb);
 
+	if (!ORANGEFS_SB(sb)) {
+		mutex_lock(&orangefs_request_mutex);
+		mutex_unlock(&orangefs_request_mutex);
+		return;
+	}
 	/*
 	 * issue the unmount to userspace to tell it to remove the
 	 * dynamic mount info it has for this superblock
diff --git a/fs/pipe.c b/fs/pipe.c
index 39d6f431da83..bb0840e234f3 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -509,19 +509,22 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 }
 
-/* No kernel lock held - fine */
-static __poll_t
-pipe_poll(struct file *filp, poll_table *wait)
+static struct wait_queue_head *
+pipe_get_poll_head(struct file *filp, __poll_t events)
 {
-	__poll_t mask;
 	struct pipe_inode_info *pipe = filp->private_data;
-	int nrbufs;
 
-	poll_wait(filp, &pipe->wait, wait);
+	return &pipe->wait;
+}
+
+/* No kernel lock held - fine */
+static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+{
+	struct pipe_inode_info *pipe = filp->private_data;
+	int nrbufs = pipe->nrbufs;
+	__poll_t mask = 0;
 
 	/* Reading only -- no need for acquiring the semaphore.  */
-	nrbufs = pipe->nrbufs;
-	mask = 0;
 	if (filp->f_mode & FMODE_READ) {
 		mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
 		if (!pipe->writers && filp->f_version != pipe->w_counter)
@@ -1020,7 +1023,8 @@ const struct file_operations pipefifo_fops = {
 	.llseek		= no_llseek,
 	.read_iter	= pipe_read,
 	.write_iter	= pipe_write,
-	.poll		= pipe_poll,
+	.get_poll_head	= pipe_get_poll_head,
+	.poll_mask	= pipe_poll_mask,
 	.unlocked_ioctl	= pipe_ioctl,
 	.release	= pipe_release,
 	.fasync		= pipe_fasync,
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ae2c807fd719..004077f1a7bf 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -85,6 +85,7 @@
 #include <linux/delayacct.h>
 #include <linux/seq_file.h>
 #include <linux/pid_namespace.h>
+#include <linux/prctl.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
 #include <linux/string_helpers.h>
@@ -95,22 +96,29 @@
 #include <asm/processor.h>
 #include "internal.h"
 
-static inline void task_name(struct seq_file *m, struct task_struct *p)
+void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape)
 {
 	char *buf;
 	size_t size;
-	char tcomm[sizeof(p->comm)];
+	char tcomm[64];
 	int ret;
 
-	get_task_comm(tcomm, p);
-
-	seq_puts(m, "Name:\t");
+	if (p->flags & PF_WQ_WORKER)
+		wq_worker_comm(tcomm, sizeof(tcomm), p);
+	else
+		__get_task_comm(tcomm, sizeof(tcomm), p);
 
 	size = seq_get_buf(m, &buf);
-	ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
-	seq_commit(m, ret < size ? ret : -1);
+	if (escape) {
+		ret = string_escape_str(tcomm, buf, size,
+					ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+		if (ret >= size)
+			ret = -1;
+	} else {
+		ret = strscpy(buf, tcomm, size);
+	}
 
-	seq_putc(m, '\n');
+	seq_commit(m, ret);
 }
 
 /*
@@ -335,6 +343,30 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
 #ifdef CONFIG_SECCOMP
 	seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode);
 #endif
+	seq_printf(m, "\nSpeculation_Store_Bypass:\t");
+	switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
+	case -EINVAL:
+		seq_printf(m, "unknown");
+		break;
+	case PR_SPEC_NOT_AFFECTED:
+		seq_printf(m, "not vulnerable");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE:
+		seq_printf(m, "thread force mitigated");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
+		seq_printf(m, "thread mitigated");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_ENABLE:
+		seq_printf(m, "thread vulnerable");
+		break;
+	case PR_SPEC_DISABLE:
+		seq_printf(m, "globally mitigated");
+		break;
+	default:
+		seq_printf(m, "vulnerable");
+		break;
+	}
 	seq_putc(m, '\n');
 }
 
@@ -365,7 +397,10 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 {
 	struct mm_struct *mm = get_task_mm(task);
 
-	task_name(m, task);
+	seq_puts(m, "Name:\t");
+	proc_task_name(m, task, true);
+	seq_putc(m, '\n');
+
 	task_state(m, ns, pid, task);
 
 	if (mm) {
@@ -400,7 +435,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	u64 cutime, cstime, utime, stime;
 	u64 cgtime, gtime;
 	unsigned long rsslim = 0;
-	char tcomm[sizeof(task->comm)];
 	unsigned long flags;
 
 	state = *get_task_state(task);
@@ -427,8 +461,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		}
 	}
 
-	get_task_comm(tcomm, task);
-
 	sigemptyset(&sigign);
 	sigemptyset(&sigcatch);
 	cutime = cstime = utime = stime = 0;
@@ -495,7 +527,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns));
 	seq_puts(m, " (");
-	seq_puts(m, tcomm);
+	proc_task_name(m, task, false);
 	seq_puts(m, ") ");
 	seq_putc(m, state);
 	seq_put_decimal_ll(m, " ", ppid);
@@ -677,25 +709,22 @@ out:
 
 static int children_seq_show(struct seq_file *seq, void *v)
 {
-	struct inode *inode = seq->private;
-	pid_t pid;
-
-	pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
-	seq_printf(seq, "%d ", pid);
+	struct inode *inode = file_inode(seq->file);
 
+	seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode)));
 	return 0;
 }
 
 static void *children_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	return get_children_pid(seq->private, NULL, *pos);
+	return get_children_pid(file_inode(seq->file), NULL, *pos);
 }
 
 static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct pid *pid;
 
-	pid = get_children_pid(seq->private, v, *pos + 1);
+	pid = get_children_pid(file_inode(seq->file), v, *pos + 1);
 	put_pid(v);
 
 	++*pos;
@@ -716,17 +745,7 @@ static const struct seq_operations children_seq_ops = {
 
 static int children_seq_open(struct inode *inode, struct file *file)
 {
-	struct seq_file *m;
-	int ret;
-
-	ret = seq_open(file, &children_seq_ops);
-	if (ret)
-		return ret;
-
-	m = file->private_data;
-	m->private = inode;
-
-	return ret;
+	return seq_open(file, &children_seq_ops);
 }
 
 const struct file_operations proc_tid_children_operations = {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index eafa39a3a88c..af128b374143 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -261,7 +261,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 	 * Inherently racy -- command line shares address space
 	 * with code and data.
 	 */
-	rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+	rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON);
 	if (rv <= 0)
 		goto out_free_page;
 
@@ -279,7 +279,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 			int nr_read;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -325,7 +325,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 				bool final;
 
 				_count = min3(count, len, PAGE_SIZE);
-				nr_read = access_remote_vm(mm, p, page, _count, 0);
+				nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
 				if (nr_read < 0)
 					rv = nr_read;
 				if (nr_read <= 0)
@@ -698,7 +698,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
 
 static int proc_pid_permission(struct inode *inode, int mask)
 {
-	struct pid_namespace *pid = inode->i_sb->s_fs_info;
+	struct pid_namespace *pid = proc_pid_ns(inode);
 	struct task_struct *task;
 	bool has_perms;
 
@@ -733,13 +733,11 @@ static const struct inode_operations proc_def_inode_operations = {
 static int proc_single_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = m->private;
-	struct pid_namespace *ns;
-	struct pid *pid;
+	struct pid_namespace *ns = proc_pid_ns(inode);
+	struct pid *pid = proc_pid(inode);
 	struct task_struct *task;
 	int ret;
 
-	ns = inode->i_sb->s_fs_info;
-	pid = proc_pid(inode);
 	task = get_pid_task(pid, PIDTYPE_PID);
 	if (!task)
 		return -ESRCH;
@@ -946,7 +944,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 		max_len = min_t(size_t, PAGE_SIZE, count);
 		this_len = min(max_len, this_len);
 
-		retval = access_remote_vm(mm, (env_start + src), page, this_len, 0);
+		retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);
 
 		if (retval <= 0) {
 			ret = retval;
@@ -1410,7 +1408,7 @@ static const struct file_operations proc_fail_nth_operations = {
 static int sched_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = m->private;
-	struct pid_namespace *ns = inode->i_sb->s_fs_info;
+	struct pid_namespace *ns = proc_pid_ns(inode);
 	struct task_struct *p;
 
 	p = get_proc_task(inode);
@@ -1565,9 +1563,8 @@ static int comm_show(struct seq_file *m, void *v)
 	if (!p)
 		return -ESRCH;
 
-	task_lock(p);
-	seq_printf(m, "%s\n", p->comm);
-	task_unlock(p);
+	proc_task_name(m, p, false);
+	seq_putc(m, '\n');
 
 	put_task_struct(p);
 
@@ -1693,6 +1690,12 @@ void task_dump_owner(struct task_struct *task, umode_t mode,
 	kuid_t uid;
 	kgid_t gid;
 
+	if (unlikely(task->flags & PF_KTHREAD)) {
+		*ruid = GLOBAL_ROOT_UID;
+		*rgid = GLOBAL_ROOT_GID;
+		return;
+	}
+
 	/* Default to the tasks effective ownership */
 	rcu_read_lock();
 	cred = __task_cred(task);
@@ -1776,8 +1779,8 @@ int pid_getattr(const struct path *path, struct kstat *stat,
 		u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
+	struct pid_namespace *pid = proc_pid_ns(inode);
 	struct task_struct *task;
-	struct pid_namespace *pid = path->dentry->d_sb->s_fs_info;
 
 	generic_fillattr(inode, stat);
 
@@ -1803,15 +1806,22 @@ int pid_getattr(const struct path *path, struct kstat *stat,
 /* dentry stuff */
 
 /*
- *	Exceptional case: normally we are not allowed to unhash a busy
- * directory. In this case, however, we can do it - no aliasing problems
- * due to the way we treat inodes.
- *
+ * Set <pid>/... inode ownership (can change due to setuid(), etc.)
+ */
+void pid_update_inode(struct task_struct *task, struct inode *inode)
+{
+	task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid);
+
+	inode->i_mode &= ~(S_ISUID | S_ISGID);
+	security_task_to_inode(task, inode);
+}
+
+/*
  * Rewrite the inode's ownerships here because the owning task may have
  * performed a setuid(), etc.
  *
  */
-int pid_revalidate(struct dentry *dentry, unsigned int flags)
+static int pid_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	struct task_struct *task;
@@ -1823,10 +1833,7 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
 	task = get_proc_task(inode);
 
 	if (task) {
-		task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid);
-
-		inode->i_mode &= ~(S_ISUID | S_ISGID);
-		security_task_to_inode(task, inode);
+		pid_update_inode(task, inode);
 		put_task_struct(task);
 		return 1;
 	}
@@ -1874,8 +1881,8 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
 	struct dentry *child, *dir = file->f_path.dentry;
 	struct qstr qname = QSTR_INIT(name, len);
 	struct inode *inode;
-	unsigned type;
-	ino_t ino;
+	unsigned type = DT_UNKNOWN;
+	ino_t ino = 1;
 
 	child = d_hash_and_lookup(dir, &qname);
 	if (!child) {
@@ -1884,22 +1891,23 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
 		if (IS_ERR(child))
 			goto end_instantiate;
 		if (d_in_lookup(child)) {
-			int err = instantiate(d_inode(dir), child, task, ptr);
+			struct dentry *res;
+			res = instantiate(child, task, ptr);
 			d_lookup_done(child);
-			if (err < 0) {
-				dput(child);
+			if (IS_ERR(res))
 				goto end_instantiate;
+			if (unlikely(res)) {
+				dput(child);
+				child = res;
 			}
 		}
 	}
 	inode = d_inode(child);
 	ino = inode->i_ino;
 	type = inode->i_mode >> 12;
+end_instantiate:
 	dput(child);
 	return dir_emit(ctx, name, len, ino, type);
-
-end_instantiate:
-	return dir_emit(ctx, name, len, 1, DT_UNKNOWN);
 }
 
 /*
@@ -2061,19 +2069,19 @@ static const struct inode_operations proc_map_files_link_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static int
-proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
+static struct dentry *
+proc_map_files_instantiate(struct dentry *dentry,
 			   struct task_struct *task, const void *ptr)
 {
 	fmode_t mode = (fmode_t)(unsigned long)ptr;
 	struct proc_inode *ei;
 	struct inode *inode;
 
-	inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK |
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK |
 				    ((mode & FMODE_READ ) ? S_IRUSR : 0) |
 				    ((mode & FMODE_WRITE) ? S_IWUSR : 0));
 	if (!inode)
-		return -ENOENT;
+		return ERR_PTR(-ENOENT);
 
 	ei = PROC_I(inode);
 	ei->op.proc_get_link = map_files_get_link;
@@ -2082,9 +2090,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 	inode->i_size = 64;
 
 	d_set_d_op(dentry, &tid_map_files_dentry_operations);
-	d_add(dentry, inode);
-
-	return 0;
+	return d_splice_alias(inode, dentry);
 }
 
 static struct dentry *proc_map_files_lookup(struct inode *dir,
@@ -2093,19 +2099,19 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 	unsigned long vm_start, vm_end;
 	struct vm_area_struct *vma;
 	struct task_struct *task;
-	int result;
+	struct dentry *result;
 	struct mm_struct *mm;
 
-	result = -ENOENT;
+	result = ERR_PTR(-ENOENT);
 	task = get_proc_task(dir);
 	if (!task)
 		goto out;
 
-	result = -EACCES;
+	result = ERR_PTR(-EACCES);
 	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
-	result = -ENOENT;
+	result = ERR_PTR(-ENOENT);
 	if (dname_to_vma_addr(dentry, &vm_start, &vm_end))
 		goto out_put_task;
 
@@ -2119,7 +2125,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 		goto out_no_vma;
 
 	if (vma->vm_file)
-		result = proc_map_files_instantiate(dir, dentry, task,
+		result = proc_map_files_instantiate(dentry, task,
 				(void *)(unsigned long)vma->vm_file->f_mode);
 
 out_no_vma:
@@ -2128,7 +2134,7 @@ out_no_vma:
 out_put_task:
 	put_task_struct(task);
 out:
-	return ERR_PTR(result);
+	return result;
 }
 
 static const struct inode_operations proc_map_files_inode_operations = {
@@ -2331,7 +2337,7 @@ static int proc_timers_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 
 	tp->pid = proc_pid(inode);
-	tp->ns = inode->i_sb->s_fs_info;
+	tp->ns = proc_pid_ns(inode);
 	return 0;
 }
 
@@ -2429,16 +2435,16 @@ static const struct file_operations proc_pid_set_timerslack_ns_operations = {
 	.release	= single_release,
 };
 
-static int proc_pident_instantiate(struct inode *dir,
-	struct dentry *dentry, struct task_struct *task, const void *ptr)
+static struct dentry *proc_pident_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
 {
 	const struct pid_entry *p = ptr;
 	struct inode *inode;
 	struct proc_inode *ei;
 
-	inode = proc_pid_make_inode(dir->i_sb, task, p->mode);
+	inode = proc_pid_make_inode(dentry->d_sb, task, p->mode);
 	if (!inode)
-		goto out;
+		return ERR_PTR(-ENOENT);
 
 	ei = PROC_I(inode);
 	if (S_ISDIR(inode->i_mode))
@@ -2448,13 +2454,9 @@ static int proc_pident_instantiate(struct inode *dir,
 	if (p->fop)
 		inode->i_fop = p->fop;
 	ei->op = p->op;
+	pid_update_inode(task, inode);
 	d_set_d_op(dentry, &pid_dentry_operations);
-	d_add(dentry, inode);
-	/* Close the race of the process dying before we return the dentry */
-	if (pid_revalidate(dentry, 0))
-		return 0;
-out:
-	return -ENOENT;
+	return d_splice_alias(inode, dentry);
 }
 
 static struct dentry *proc_pident_lookup(struct inode *dir, 
@@ -2462,11 +2464,9 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 					 const struct pid_entry *ents,
 					 unsigned int nents)
 {
-	int error;
 	struct task_struct *task = get_proc_task(dir);
 	const struct pid_entry *p, *last;
-
-	error = -ENOENT;
+	struct dentry *res = ERR_PTR(-ENOENT);
 
 	if (!task)
 		goto out_no_task;
@@ -2485,11 +2485,11 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 	if (p >= last)
 		goto out;
 
-	error = proc_pident_instantiate(dir, dentry, task, p);
+	res = proc_pident_instantiate(dentry, task, p);
 out:
 	put_task_struct(task);
 out_no_task:
-	return ERR_PTR(error);
+	return res;
 }
 
 static int proc_pident_readdir(struct file *file, struct dir_context *ctx,
@@ -3132,38 +3132,32 @@ void proc_flush_task(struct task_struct *task)
 	}
 }
 
-static int proc_pid_instantiate(struct inode *dir,
-				   struct dentry * dentry,
+static struct dentry *proc_pid_instantiate(struct dentry * dentry,
 				   struct task_struct *task, const void *ptr)
 {
 	struct inode *inode;
 
-	inode = proc_pid_make_inode(dir->i_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
 	if (!inode)
-		goto out;
+		return ERR_PTR(-ENOENT);
 
 	inode->i_op = &proc_tgid_base_inode_operations;
 	inode->i_fop = &proc_tgid_base_operations;
 	inode->i_flags|=S_IMMUTABLE;
 
 	set_nlink(inode, nlink_tgid);
+	pid_update_inode(task, inode);
 
 	d_set_d_op(dentry, &pid_dentry_operations);
-
-	d_add(dentry, inode);
-	/* Close the race of the process dying before we return the dentry */
-	if (pid_revalidate(dentry, 0))
-		return 0;
-out:
-	return -ENOENT;
+	return d_splice_alias(inode, dentry);
 }
 
 struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
-	int result = -ENOENT;
 	struct task_struct *task;
 	unsigned tgid;
 	struct pid_namespace *ns;
+	struct dentry *result = ERR_PTR(-ENOENT);
 
 	tgid = name_to_int(&dentry->d_name);
 	if (tgid == ~0U)
@@ -3178,10 +3172,10 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsign
 	if (!task)
 		goto out;
 
-	result = proc_pid_instantiate(dir, dentry, task, NULL);
+	result = proc_pid_instantiate(dentry, task, NULL);
 	put_task_struct(task);
 out:
-	return ERR_PTR(result);
+	return result;
 }
 
 /*
@@ -3233,7 +3227,7 @@ retry:
 int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct tgid_iter iter;
-	struct pid_namespace *ns = file_inode(file)->i_sb->s_fs_info;
+	struct pid_namespace *ns = proc_pid_ns(file_inode(file));
 	loff_t pos = ctx->pos;
 
 	if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
@@ -3429,37 +3423,32 @@ static const struct inode_operations proc_tid_base_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static int proc_task_instantiate(struct inode *dir,
-	struct dentry *dentry, struct task_struct *task, const void *ptr)
+static struct dentry *proc_task_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
 {
 	struct inode *inode;
-	inode = proc_pid_make_inode(dir->i_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
-
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
 	if (!inode)
-		goto out;
+		return ERR_PTR(-ENOENT);
+
 	inode->i_op = &proc_tid_base_inode_operations;
 	inode->i_fop = &proc_tid_base_operations;
-	inode->i_flags|=S_IMMUTABLE;
+	inode->i_flags |= S_IMMUTABLE;
 
 	set_nlink(inode, nlink_tid);
+	pid_update_inode(task, inode);
 
 	d_set_d_op(dentry, &pid_dentry_operations);
-
-	d_add(dentry, inode);
-	/* Close the race of the process dying before we return the dentry */
-	if (pid_revalidate(dentry, 0))
-		return 0;
-out:
-	return -ENOENT;
+	return d_splice_alias(inode, dentry);
 }
 
 static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
-	int result = -ENOENT;
 	struct task_struct *task;
 	struct task_struct *leader = get_proc_task(dir);
 	unsigned tid;
 	struct pid_namespace *ns;
+	struct dentry *result = ERR_PTR(-ENOENT);
 
 	if (!leader)
 		goto out_no_task;
@@ -3479,13 +3468,13 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
 	if (!same_thread_group(leader, task))
 		goto out_drop_task;
 
-	result = proc_task_instantiate(dir, dentry, task, NULL);
+	result = proc_task_instantiate(dentry, task, NULL);
 out_drop_task:
 	put_task_struct(task);
 out:
 	put_task_struct(leader);
 out_no_task:
-	return ERR_PTR(result);
+	return result;
 }
 
 /*
@@ -3582,7 +3571,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
 	/* f_version caches the tgid value that the last readdir call couldn't
 	 * return. lseek aka telldir automagically resets f_version to 0.
 	 */
-	ns = inode->i_sb->s_fs_info;
+	ns = proc_pid_ns(inode);
 	tid = (int)file->f_version;
 	file->f_version = 0;
 	for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);
diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c
index 8233e7af9389..fa762c5fbcb2 100644
--- a/fs/proc/cmdline.c
+++ b/fs/proc/cmdline.c
@@ -11,21 +11,9 @@ static int cmdline_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int cmdline_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, cmdline_proc_show, NULL);
-}
-
-static const struct file_operations cmdline_proc_fops = {
-	.open		= cmdline_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_cmdline_init(void)
 {
-	proc_create("cmdline", 0, NULL, &cmdline_proc_fops);
+	proc_create_single("cmdline", 0, NULL, cmdline_proc_show);
 	return 0;
 }
 fs_initcall(proc_cmdline_init);
diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c
index a8ac48aebd59..954caf0b7fee 100644
--- a/fs/proc/consoles.c
+++ b/fs/proc/consoles.c
@@ -91,21 +91,9 @@ static const struct seq_operations consoles_op = {
 	.show	= show_console_dev
 };
 
-static int consoles_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &consoles_op);
-}
-
-static const struct file_operations proc_consoles_operations = {
-	.open		= consoles_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int __init proc_consoles_init(void)
 {
-	proc_create("consoles", 0, NULL, &proc_consoles_operations);
+	proc_create_seq("consoles", 0, NULL, &consoles_op);
 	return 0;
 }
 fs_initcall(proc_consoles_init);
diff --git a/fs/proc/devices.c b/fs/proc/devices.c
index 2c7f22b14489..37d38697eaf8 100644
--- a/fs/proc/devices.c
+++ b/fs/proc/devices.c
@@ -51,21 +51,9 @@ static const struct seq_operations devinfo_ops = {
 	.show  = devinfo_show
 };
 
-static int devinfo_open(struct inode *inode, struct file *filp)
-{
-	return seq_open(filp, &devinfo_ops);
-}
-
-static const struct file_operations proc_devinfo_operations = {
-	.open		= devinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int __init proc_devices_init(void)
 {
-	proc_create("devices", 0, NULL, &proc_devinfo_operations);
+	proc_create_seq("devices", 0, NULL, &devinfo_ops);
 	return 0;
 }
 fs_initcall(proc_devices_init);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 6b80cd1e419a..05b9893e9a22 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -81,9 +81,41 @@ static const struct file_operations proc_fdinfo_file_operations = {
 	.release	= single_release,
 };
 
+static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
+{
+	struct files_struct *files = get_files_struct(task);
+	struct file *file;
+
+	if (!files)
+		return false;
+
+	rcu_read_lock();
+	file = fcheck_files(files, fd);
+	if (file)
+		*mode = file->f_mode;
+	rcu_read_unlock();
+	put_files_struct(files);
+	return !!file;
+}
+
+static void tid_fd_update_inode(struct task_struct *task, struct inode *inode,
+				fmode_t f_mode)
+{
+	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
+
+	if (S_ISLNK(inode->i_mode)) {
+		unsigned i_mode = S_IFLNK;
+		if (f_mode & FMODE_READ)
+			i_mode |= S_IRUSR | S_IXUSR;
+		if (f_mode & FMODE_WRITE)
+			i_mode |= S_IWUSR | S_IXUSR;
+		inode->i_mode = i_mode;
+	}
+	security_task_to_inode(task, inode);
+}
+
 static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	struct files_struct *files;
 	struct task_struct *task;
 	struct inode *inode;
 	unsigned int fd;
@@ -96,35 +128,11 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
 	fd = proc_fd(inode);
 
 	if (task) {
-		files = get_files_struct(task);
-		if (files) {
-			struct file *file;
-
-			rcu_read_lock();
-			file = fcheck_files(files, fd);
-			if (file) {
-				unsigned f_mode = file->f_mode;
-
-				rcu_read_unlock();
-				put_files_struct(files);
-
-				task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
-
-				if (S_ISLNK(inode->i_mode)) {
-					unsigned i_mode = S_IFLNK;
-					if (f_mode & FMODE_READ)
-						i_mode |= S_IRUSR | S_IXUSR;
-					if (f_mode & FMODE_WRITE)
-						i_mode |= S_IWUSR | S_IXUSR;
-					inode->i_mode = i_mode;
-				}
-
-				security_task_to_inode(task, inode);
-				put_task_struct(task);
-				return 1;
-			}
-			rcu_read_unlock();
-			put_files_struct(files);
+		fmode_t f_mode;
+		if (tid_fd_mode(task, fd, &f_mode)) {
+			tid_fd_update_inode(task, inode, f_mode);
+			put_task_struct(task);
+			return 1;
 		}
 		put_task_struct(task);
 	}
@@ -166,34 +174,33 @@ static int proc_fd_link(struct dentry *dentry, struct path *path)
 	return ret;
 }
 
-static int
-proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
-		    struct task_struct *task, const void *ptr)
+struct fd_data {
+	fmode_t mode;
+	unsigned fd;
+};
+
+static struct dentry *proc_fd_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
 {
-	unsigned fd = (unsigned long)ptr;
+	const struct fd_data *data = ptr;
 	struct proc_inode *ei;
 	struct inode *inode;
 
-	inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK);
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK);
 	if (!inode)
-		goto out;
+		return ERR_PTR(-ENOENT);
 
 	ei = PROC_I(inode);
-	ei->fd = fd;
+	ei->fd = data->fd;
 
 	inode->i_op = &proc_pid_link_inode_operations;
 	inode->i_size = 64;
 
 	ei->op.proc_get_link = proc_fd_link;
+	tid_fd_update_inode(task, inode, data->mode);
 
 	d_set_d_op(dentry, &tid_fd_dentry_operations);
-	d_add(dentry, inode);
-
-	/* Close the race of the process dying before we return the dentry */
-	if (tid_fd_revalidate(dentry, 0))
-		return 0;
- out:
-	return -ENOENT;
+	return d_splice_alias(inode, dentry);
 }
 
 static struct dentry *proc_lookupfd_common(struct inode *dir,
@@ -201,19 +208,21 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
 					   instantiate_t instantiate)
 {
 	struct task_struct *task = get_proc_task(dir);
-	int result = -ENOENT;
-	unsigned fd = name_to_int(&dentry->d_name);
+	struct fd_data data = {.fd = name_to_int(&dentry->d_name)};
+	struct dentry *result = ERR_PTR(-ENOENT);
 
 	if (!task)
 		goto out_no_task;
-	if (fd == ~0U)
+	if (data.fd == ~0U)
+		goto out;
+	if (!tid_fd_mode(task, data.fd, &data.mode))
 		goto out;
 
-	result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
+	result = instantiate(dentry, task, &data);
 out:
 	put_task_struct(task);
 out_no_task:
-	return ERR_PTR(result);
+	return result;
 }
 
 static int proc_readfd_common(struct file *file, struct dir_context *ctx,
@@ -236,17 +245,22 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 	for (fd = ctx->pos - 2;
 	     fd < files_fdtable(files)->max_fds;
 	     fd++, ctx->pos++) {
+		struct file *f;
+		struct fd_data data;
 		char name[10 + 1];
 		int len;
 
-		if (!fcheck_files(files, fd))
+		f = fcheck_files(files, fd);
+		if (!f)
 			continue;
+		data.mode = f->f_mode;
 		rcu_read_unlock();
+		data.fd = fd;
 
 		len = snprintf(name, sizeof(name), "%u", fd);
 		if (!proc_fill_cache(file, ctx,
 				     name, len, instantiate, p,
-				     (void *)(unsigned long)fd))
+				     &data))
 			goto out_fd_loop;
 		cond_resched();
 		rcu_read_lock();
@@ -304,31 +318,25 @@ const struct inode_operations proc_fd_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static int
-proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
-			struct task_struct *task, const void *ptr)
+static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
 {
-	unsigned fd = (unsigned long)ptr;
+	const struct fd_data *data = ptr;
 	struct proc_inode *ei;
 	struct inode *inode;
 
-	inode = proc_pid_make_inode(dir->i_sb, task, S_IFREG | S_IRUSR);
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUSR);
 	if (!inode)
-		goto out;
+		return ERR_PTR(-ENOENT);
 
 	ei = PROC_I(inode);
-	ei->fd = fd;
+	ei->fd = data->fd;
 
 	inode->i_fop = &proc_fdinfo_file_operations;
+	tid_fd_update_inode(task, inode, 0);
 
 	d_set_d_op(dentry, &tid_fd_dentry_operations);
-	d_add(dentry, inode);
-
-	/* Close the race of the process dying before we return the dentry */
-	if (tid_fd_revalidate(dentry, 0))
-		return 0;
- out:
-	return -ENOENT;
+	return d_splice_alias(inode, dentry);
 }
 
 static struct dentry *
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 2078e70e1595..7b4d9714f248 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -25,6 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/uaccess.h>
+#include <linux/seq_file.h>
 
 #include "internal.h"
 
@@ -256,8 +257,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
 		if (!inode)
 			return ERR_PTR(-ENOMEM);
 		d_set_d_op(dentry, &proc_misc_dentry_ops);
-		d_add(dentry, inode);
-		return NULL;
+		return d_splice_alias(inode, dentry);
 	}
 	read_unlock(&proc_subdir_lock);
 	return ERR_PTR(-ENOENT);
@@ -346,13 +346,12 @@ static const struct inode_operations proc_dir_inode_operations = {
 	.setattr	= proc_notify_change,
 };
 
-static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
+/* returns the registered entry, or frees dp and returns NULL on failure */
+struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
+		struct proc_dir_entry *dp)
 {
-	int ret;
-
-	ret = proc_alloc_inum(&dp->low_ino);
-	if (ret)
-		return ret;
+	if (proc_alloc_inum(&dp->low_ino))
+		goto out_free_entry;
 
 	write_lock(&proc_subdir_lock);
 	dp->parent = dir;
@@ -360,12 +359,16 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
 		WARN(1, "proc_dir_entry '%s/%s' already registered\n",
 		     dir->name, dp->name);
 		write_unlock(&proc_subdir_lock);
-		proc_free_inum(dp->low_ino);
-		return -EEXIST;
+		goto out_free_inum;
 	}
 	write_unlock(&proc_subdir_lock);
 
-	return 0;
+	return dp;
+out_free_inum:
+	proc_free_inum(dp->low_ino);
+out_free_entry:
+	pde_free(dp);
+	return NULL;
 }
 
 static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
@@ -443,10 +446,7 @@ struct proc_dir_entry *proc_symlink(const char *name,
 		if (ent->data) {
 			strcpy((char*)ent->data,dest);
 			ent->proc_iops = &proc_link_inode_operations;
-			if (proc_register(parent, ent) < 0) {
-				pde_free(ent);
-				ent = NULL;
-			}
+			ent = proc_register(parent, ent);
 		} else {
 			pde_free(ent);
 			ent = NULL;
@@ -470,11 +470,9 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
 		ent->proc_fops = &proc_dir_operations;
 		ent->proc_iops = &proc_dir_inode_operations;
 		parent->nlink++;
-		if (proc_register(parent, ent) < 0) {
-			pde_free(ent);
+		ent = proc_register(parent, ent);
+		if (!ent)
 			parent->nlink--;
-			ent = NULL;
-		}
 	}
 	return ent;
 }
@@ -505,47 +503,47 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
 		ent->proc_fops = NULL;
 		ent->proc_iops = NULL;
 		parent->nlink++;
-		if (proc_register(parent, ent) < 0) {
-			pde_free(ent);
+		ent = proc_register(parent, ent);
+		if (!ent)
 			parent->nlink--;
-			ent = NULL;
-		}
 	}
 	return ent;
 }
 EXPORT_SYMBOL(proc_create_mount_point);
 
-struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
-					struct proc_dir_entry *parent,
-					const struct file_operations *proc_fops,
-					void *data)
+struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
+		struct proc_dir_entry **parent, void *data)
 {
-	struct proc_dir_entry *pde;
+	struct proc_dir_entry *p;
+
 	if ((mode & S_IFMT) == 0)
 		mode |= S_IFREG;
-
-	if (!S_ISREG(mode)) {
-		WARN_ON(1);	/* use proc_mkdir() */
+	if ((mode & S_IALLUGO) == 0)
+		mode |= S_IRUGO;
+	if (WARN_ON_ONCE(!S_ISREG(mode)))
 		return NULL;
+
+	p = __proc_create(parent, name, mode, 1);
+	if (p) {
+		p->proc_iops = &proc_file_inode_operations;
+		p->data = data;
 	}
+	return p;
+}
+
+struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		const struct file_operations *proc_fops, void *data)
+{
+	struct proc_dir_entry *p;
 
 	BUG_ON(proc_fops == NULL);
 
-	if ((mode & S_IALLUGO) == 0)
-		mode |= S_IRUGO;
-	pde = __proc_create(&parent, name, mode, 1);
-	if (!pde)
-		goto out;
-	pde->proc_fops = proc_fops;
-	pde->data = data;
-	pde->proc_iops = &proc_file_inode_operations;
-	if (proc_register(parent, pde) < 0)
-		goto out_free;
-	return pde;
-out_free:
-	pde_free(pde);
-out:
-	return NULL;
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	p->proc_fops = proc_fops;
+	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_data);
  
@@ -557,6 +555,67 @@ struct proc_dir_entry *proc_create(const char *name, umode_t mode,
 }
 EXPORT_SYMBOL(proc_create);
 
+static int proc_seq_open(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+
+	if (de->state_size)
+		return seq_open_private(file, de->seq_ops, de->state_size);
+	return seq_open(file, de->seq_ops);
+}
+
+static const struct file_operations proc_seq_fops = {
+	.open		= proc_seq_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, const struct seq_operations *ops,
+		unsigned int state_size, void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	p->proc_fops = &proc_seq_fops;
+	p->seq_ops = ops;
+	p->state_size = state_size;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL(proc_create_seq_private);
+
+static int proc_single_open(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+
+	return single_open(file, de->single_show, de->data);
+}
+
+static const struct file_operations proc_single_fops = {
+	.open		= proc_single_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		int (*show)(struct seq_file *, void *), void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	p->proc_fops = &proc_single_fops;
+	p->single_show = show;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL(proc_create_single_data);
+
 void proc_set_size(struct proc_dir_entry *de, loff_t size)
 {
 	de->size = size;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 0f1692e63cb6..93eb1906c28d 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -44,7 +44,12 @@ struct proc_dir_entry {
 	struct completion *pde_unload_completion;
 	const struct inode_operations *proc_iops;
 	const struct file_operations *proc_fops;
+	union {
+		const struct seq_operations *seq_ops;
+		int (*single_show)(struct seq_file *, void *);
+	};
 	void *data;
+	unsigned int state_size;
 	unsigned int low_ino;
 	nlink_t nlink;
 	kuid_t uid;
@@ -57,9 +62,9 @@ struct proc_dir_entry {
 	umode_t mode;
 	u8 namelen;
 #ifdef CONFIG_64BIT
-#define SIZEOF_PDE_INLINE_NAME	(192-139)
+#define SIZEOF_PDE_INLINE_NAME	(192-155)
 #else
-#define SIZEOF_PDE_INLINE_NAME	(128-87)
+#define SIZEOF_PDE_INLINE_NAME	(128-95)
 #endif
 	char inline_name[SIZEOF_PDE_INLINE_NAME];
 } __randomize_layout;
@@ -131,6 +136,8 @@ unsigned name_to_int(const struct qstr *qstr);
  */
 extern const struct file_operations proc_tid_children_operations;
 
+extern void proc_task_name(struct seq_file *m, struct task_struct *p,
+			   bool escape);
 extern int proc_tid_stat(struct seq_file *, struct pid_namespace *,
 			 struct pid *, struct task_struct *);
 extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *,
@@ -147,14 +154,14 @@ extern const struct dentry_operations pid_dentry_operations;
 extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int proc_setattr(struct dentry *, struct iattr *);
 extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
-extern int pid_revalidate(struct dentry *, unsigned int);
+extern void pid_update_inode(struct task_struct *, struct inode *);
 extern int pid_delete_dentry(const struct dentry *);
 extern int proc_pid_readdir(struct file *, struct dir_context *);
 extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int);
 extern loff_t mem_lseek(struct file *, loff_t, int);
 
 /* Lookups */
-typedef int instantiate_t(struct inode *, struct dentry *,
+typedef struct dentry *instantiate_t(struct dentry *,
 				     struct task_struct *, const void *);
 extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int,
 			   instantiate_t, struct task_struct *, const void *);
@@ -162,6 +169,10 @@ extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, i
 /*
  * generic.c
  */
+struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
+		struct proc_dir_entry **parent, void *data);
+struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
+		struct proc_dir_entry *dp);
 extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
 struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *);
 extern int proc_readdir(struct file *, struct dir_context *);
diff --git a/fs/proc/interrupts.c b/fs/proc/interrupts.c
index 6a6bee9c603c..cb0edc7cbf09 100644
--- a/fs/proc/interrupts.c
+++ b/fs/proc/interrupts.c
@@ -34,21 +34,9 @@ static const struct seq_operations int_seq_ops = {
 	.show  = show_interrupts
 };
 
-static int interrupts_open(struct inode *inode, struct file *filp)
-{
-	return seq_open(filp, &int_seq_ops);
-}
-
-static const struct file_operations proc_interrupts_operations = {
-	.open		= interrupts_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int __init proc_interrupts_init(void)
 {
-	proc_create("interrupts", 0, NULL, &proc_interrupts_operations);
+	proc_create_seq("interrupts", 0, NULL, &int_seq_ops);
 	return 0;
 }
 fs_initcall(proc_interrupts_init);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index d1e82761de81..e64ecb9f2720 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -209,25 +209,34 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
 {
 	struct list_head *head = (struct list_head *)arg;
 	struct kcore_list *ent;
+	struct page *p;
+
+	if (!pfn_valid(pfn))
+		return 1;
+
+	p = pfn_to_page(pfn);
+	if (!memmap_valid_within(pfn, p, page_zone(p)))
+		return 1;
 
 	ent = kmalloc(sizeof(*ent), GFP_KERNEL);
 	if (!ent)
 		return -ENOMEM;
-	ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT));
+	ent->addr = (unsigned long)page_to_virt(p);
 	ent->size = nr_pages << PAGE_SHIFT;
 
-	/* Sanity check: Can happen in 32bit arch...maybe */
-	if (ent->addr < (unsigned long) __va(0))
+	if (!virt_addr_valid(ent->addr))
 		goto free_out;
 
 	/* cut not-mapped area. ....from ppc-32 code. */
 	if (ULONG_MAX - ent->addr < ent->size)
 		ent->size = ULONG_MAX - ent->addr;
 
-	/* cut when vmalloc() area is higher than direct-map area */
-	if (VMALLOC_START > (unsigned long)__va(0)) {
-		if (ent->addr > VMALLOC_START)
-			goto free_out;
+	/*
+	 * We've already checked virt_addr_valid so we know this address
+	 * is a valid pointer, therefore we can check against it to determine
+	 * if we need to trim
+	 */
+	if (VMALLOC_START > ent->addr) {
 		if (VMALLOC_START - ent->addr < ent->size)
 			ent->size = VMALLOC_START - ent->addr;
 	}
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index a000d7547479..d06694757201 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -24,25 +24,13 @@ static int loadavg_proc_show(struct seq_file *m, void *v)
 		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
 		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
 		nr_running(), nr_threads,
-		idr_get_cursor(&task_active_pid_ns(current)->idr));
+		idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
 	return 0;
 }
 
-static int loadavg_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, loadavg_proc_show, NULL);
-}
-
-static const struct file_operations loadavg_proc_fops = {
-	.open		= loadavg_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_loadavg_init(void)
 {
-	proc_create("loadavg", 0, NULL, &loadavg_proc_fops);
+	proc_create_single("loadavg", 0, NULL, loadavg_proc_show);
 	return 0;
 }
 fs_initcall(proc_loadavg_init);
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 65a72ab57471..2fb04846ed11 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -149,21 +149,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int meminfo_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, meminfo_proc_show, NULL);
-}
-
-static const struct file_operations meminfo_proc_fops = {
-	.open		= meminfo_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_meminfo_init(void)
 {
-	proc_create("meminfo", 0, NULL, &meminfo_proc_fops);
+	proc_create_single("meminfo", 0, NULL, meminfo_proc_show);
 	return 0;
 }
 fs_initcall(proc_meminfo_init);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 59b17e509f46..dd2b35f78b09 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -87,28 +87,24 @@ static const struct inode_operations proc_ns_link_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static int proc_ns_instantiate(struct inode *dir,
-	struct dentry *dentry, struct task_struct *task, const void *ptr)
+static struct dentry *proc_ns_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
 {
 	const struct proc_ns_operations *ns_ops = ptr;
 	struct inode *inode;
 	struct proc_inode *ei;
 
-	inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK | S_IRWXUGO);
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO);
 	if (!inode)
-		goto out;
+		return ERR_PTR(-ENOENT);
 
 	ei = PROC_I(inode);
 	inode->i_op = &proc_ns_link_inode_operations;
 	ei->ns_ops = ns_ops;
+	pid_update_inode(task, inode);
 
 	d_set_d_op(dentry, &pid_dentry_operations);
-	d_add(dentry, inode);
-	/* Close the race of the process dying before we return the dentry */
-	if (pid_revalidate(dentry, 0))
-		return 0;
-out:
-	return -ENOENT;
+	return d_splice_alias(inode, dentry);
 }
 
 static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
@@ -147,12 +143,10 @@ const struct file_operations proc_ns_dir_operations = {
 static struct dentry *proc_ns_dir_lookup(struct inode *dir,
 				struct dentry *dentry, unsigned int flags)
 {
-	int error;
 	struct task_struct *task = get_proc_task(dir);
 	const struct proc_ns_operations **entry, **last;
 	unsigned int len = dentry->d_name.len;
-
-	error = -ENOENT;
+	struct dentry *res = ERR_PTR(-ENOENT);
 
 	if (!task)
 		goto out_no_task;
@@ -167,11 +161,11 @@ static struct dentry *proc_ns_dir_lookup(struct inode *dir,
 	if (entry == last)
 		goto out;
 
-	error = proc_ns_instantiate(dir, dentry, task, *entry);
+	res = proc_ns_instantiate(dentry, task, *entry);
 out:
 	put_task_struct(task);
 out_no_task:
-	return ERR_PTR(error);
+	return res;
 }
 
 const struct inode_operations proc_ns_dir_inode_operations = {
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 75634379f82e..3b63be64e436 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -113,21 +113,9 @@ static const struct seq_operations proc_nommu_region_list_seqop = {
 	.show	= nommu_region_list_show
 };
 
-static int proc_nommu_region_list_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &proc_nommu_region_list_seqop);
-}
-
-static const struct file_operations proc_nommu_region_list_operations = {
-	.open    = proc_nommu_region_list_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-};
-
 static int __init proc_nommu_init(void)
 {
-	proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations);
+	proc_create_seq("maps", S_IRUGO, NULL, &proc_nommu_region_list_seqop);
 	return 0;
 }
 
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 1763f370489d..7d94fa005b0d 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -38,20 +38,20 @@ static struct net *get_proc_net(const struct inode *inode)
 	return maybe_get_net(PDE_NET(PDE(inode)));
 }
 
-int seq_open_net(struct inode *ino, struct file *f,
-		 const struct seq_operations *ops, int size)
+static int seq_open_net(struct inode *inode, struct file *file)
 {
-	struct net *net;
+	unsigned int state_size = PDE(inode)->state_size;
 	struct seq_net_private *p;
+	struct net *net;
 
-	BUG_ON(size < sizeof(*p));
+	WARN_ON_ONCE(state_size < sizeof(*p));
 
-	net = get_proc_net(ino);
-	if (net == NULL)
+	net = get_proc_net(inode);
+	if (!net)
 		return -ENXIO;
 
-	p = __seq_open_private(f, ops, size);
-	if (p == NULL) {
+	p = __seq_open_private(file, PDE(inode)->seq_ops, state_size);
+	if (!p) {
 		put_net(net);
 		return -ENOMEM;
 	}
@@ -60,51 +60,83 @@ int seq_open_net(struct inode *ino, struct file *f,
 #endif
 	return 0;
 }
-EXPORT_SYMBOL_GPL(seq_open_net);
 
-int single_open_net(struct inode *inode, struct file *file,
-		int (*show)(struct seq_file *, void *))
+static int seq_release_net(struct inode *ino, struct file *f)
 {
-	int err;
-	struct net *net;
-
-	err = -ENXIO;
-	net = get_proc_net(inode);
-	if (net == NULL)
-		goto err_net;
-
-	err = single_open(file, show, net);
-	if (err < 0)
-		goto err_open;
+	struct seq_file *seq = f->private_data;
 
+	put_net(seq_file_net(seq));
+	seq_release_private(ino, f);
 	return 0;
+}
 
-err_open:
-	put_net(net);
-err_net:
-	return err;
+static const struct file_operations proc_net_seq_fops = {
+	.open		= seq_open_net,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_net,
+};
+
+struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, const struct seq_operations *ops,
+		unsigned int state_size, void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	p->proc_fops = &proc_net_seq_fops;
+	p->seq_ops = ops;
+	p->state_size = state_size;
+	return proc_register(parent, p);
 }
-EXPORT_SYMBOL_GPL(single_open_net);
+EXPORT_SYMBOL_GPL(proc_create_net_data);
 
-int seq_release_net(struct inode *ino, struct file *f)
+static int single_open_net(struct inode *inode, struct file *file)
 {
-	struct seq_file *seq;
+	struct proc_dir_entry *de = PDE(inode);
+	struct net *net;
+	int err;
 
-	seq = f->private_data;
+	net = get_proc_net(inode);
+	if (!net)
+		return -ENXIO;
 
-	put_net(seq_file_net(seq));
-	seq_release_private(ino, f);
-	return 0;
+	err = single_open(file, de->single_show, net);
+	if (err)
+		put_net(net);
+	return err;
 }
-EXPORT_SYMBOL_GPL(seq_release_net);
 
-int single_release_net(struct inode *ino, struct file *f)
+static int single_release_net(struct inode *ino, struct file *f)
 {
 	struct seq_file *seq = f->private_data;
 	put_net(seq->private);
 	return single_release(ino, f);
 }
-EXPORT_SYMBOL_GPL(single_release_net);
+
+static const struct file_operations proc_net_single_fops = {
+	.open		= single_open_net,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release_net,
+};
+
+struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		int (*show)(struct seq_file *, void *), void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	p->proc_fops = &proc_net_single_fops;
+	p->single_show = show;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_single);
 
 static struct net *get_proc_task_net(struct inode *dir)
 {
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 8989936f2995..4d765e5e91ed 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -554,9 +554,8 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
 	if (!inode)
 		goto out;
 
-	err = NULL;
 	d_set_d_op(dentry, &proc_sys_dentry_operations);
-	d_add(dentry, inode);
+	err = d_splice_alias(inode, dentry);
 
 out:
 	if (h)
@@ -684,6 +683,7 @@ static bool proc_sys_fill_cache(struct file *file,
 		if (IS_ERR(child))
 			return false;
 		if (d_in_lookup(child)) {
+			struct dentry *res;
 			inode = proc_sys_make_inode(dir->d_sb, head, table);
 			if (!inode) {
 				d_lookup_done(child);
@@ -691,7 +691,16 @@ static bool proc_sys_fill_cache(struct file *file,
 				return false;
 			}
 			d_set_d_op(child, &proc_sys_dentry_operations);
-			d_add(child, inode);
+			res = d_splice_alias(inode, child);
+			d_lookup_done(child);
+			if (unlikely(res)) {
+				if (IS_ERR(res)) {
+					dput(child);
+					return false;
+				}
+				dput(child);
+				child = res;
+			}
 		}
 	}
 	inode = d_inode(child);
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index d0cf1c50bb6c..c69ff191e5d8 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -126,18 +126,6 @@ static const struct seq_operations tty_drivers_op = {
 	.show	= show_tty_driver
 };
 
-static int tty_drivers_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &tty_drivers_op);
-}
-
-static const struct file_operations proc_tty_drivers_operations = {
-	.open		= tty_drivers_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 /*
  * This function is called by tty_register_driver() to handle
  * registering the driver's /proc handler into /proc/tty/driver/<foo>
@@ -147,11 +135,11 @@ void proc_tty_register_driver(struct tty_driver *driver)
 	struct proc_dir_entry *ent;
 		
 	if (!driver->driver_name || driver->proc_entry ||
-	    !driver->ops->proc_fops)
+	    !driver->ops->proc_show)
 		return;
 
-	ent = proc_create_data(driver->driver_name, 0, proc_tty_driver,
-			       driver->ops->proc_fops, driver);
+	ent = proc_create_single_data(driver->driver_name, 0, proc_tty_driver,
+			       driver->ops->proc_show, driver);
 	driver->proc_entry = ent;
 }
 
@@ -186,6 +174,6 @@ void __init proc_tty_init(void)
 	 * entry.
 	 */
 	proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL);
-	proc_create("tty/ldiscs", 0, NULL, &tty_ldiscs_proc_fops);
-	proc_create("tty/drivers", 0, NULL, &proc_tty_drivers_operations);
+	proc_create_seq("tty/ldiscs", 0, NULL, &tty_ldiscs_seq_ops);
+	proc_create_seq("tty/drivers", 0, NULL, &tty_drivers_op);
 }
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 4d7d061696b3..127265e5c55f 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -12,7 +12,7 @@ static const char *proc_self_get_link(struct dentry *dentry,
 				      struct inode *inode,
 				      struct delayed_call *done)
 {
-	struct pid_namespace *ns = inode->i_sb->s_fs_info;
+	struct pid_namespace *ns = proc_pid_ns(inode);
 	pid_t tgid = task_tgid_nr_ns(current, ns);
 	char *name;
 
@@ -36,7 +36,7 @@ static unsigned self_inum __ro_after_init;
 int proc_setup_self(struct super_block *s)
 {
 	struct inode *root_inode = d_inode(s->s_root);
-	struct pid_namespace *ns = s->s_fs_info;
+	struct pid_namespace *ns = proc_pid_ns(root_inode);
 	struct dentry *self;
 	
 	inode_lock(root_inode);
diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c
index 24072cc06e65..12901dcf57e2 100644
--- a/fs/proc/softirqs.c
+++ b/fs/proc/softirqs.c
@@ -25,21 +25,9 @@ static int show_softirqs(struct seq_file *p, void *v)
 	return 0;
 }
 
-static int softirqs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, show_softirqs, NULL);
-}
-
-static const struct file_operations proc_softirqs_operations = {
-	.open		= softirqs_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_softirqs_init(void)
 {
-	proc_create("softirqs", 0, NULL, &proc_softirqs_operations);
+	proc_create_single("softirqs", 0, NULL, show_softirqs);
 	return 0;
 }
 fs_initcall(proc_softirqs_init);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 65ae54659833..a20c6e495bb2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -937,7 +937,7 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	/*
 	 * The soft-dirty tracker uses #PF-s to catch writes
 	 * to pages, so write-protect the pte as well. See the
-	 * Documentation/vm/soft-dirty.txt for full description
+	 * Documentation/admin-guide/mm/soft-dirty.rst for full description
 	 * of how soft-dirty works.
 	 */
 	pte_t ptent = *pte;
@@ -1310,9 +1310,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 		else if (is_swap_pmd(pmd)) {
 			swp_entry_t entry = pmd_to_swp_entry(pmd);
+			unsigned long offset = swp_offset(entry);
 
+			offset += (addr & ~PMD_MASK) >> PAGE_SHIFT;
 			frame = swp_type(entry) |
-				(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+				(offset << MAX_SWAPFILES_SHIFT);
 			flags |= PM_SWAP;
 			if (pmd_swp_soft_dirty(pmd))
 				flags |= PM_SOFT_DIRTY;
@@ -1332,6 +1334,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 				break;
 			if (pm->show_pfn && (flags & PM_PRESENT))
 				frame++;
+			else if (flags & PM_SWAP)
+				frame += (1 << MAX_SWAPFILES_SHIFT);
 		}
 		spin_unlock(ptl);
 		return err;
@@ -1417,7 +1421,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
  * Bits 0-54  page frame number (PFN) if present
  * Bits 0-4   swap type if swapped
  * Bits 5-54  swap offset if swapped
- * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
+ * Bit  55    pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst)
  * Bit  56    page exclusively mapped
  * Bits 57-60 zero
  * Bit  61    page is file-page or shared-anon
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index 9d2efaca499f..b905010ca9eb 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -12,7 +12,7 @@ static const char *proc_thread_self_get_link(struct dentry *dentry,
 					     struct inode *inode,
 					     struct delayed_call *done)
 {
-	struct pid_namespace *ns = inode->i_sb->s_fs_info;
+	struct pid_namespace *ns = proc_pid_ns(inode);
 	pid_t tgid = task_tgid_nr_ns(current, ns);
 	pid_t pid = task_pid_nr_ns(current, ns);
 	char *name;
@@ -36,7 +36,7 @@ static unsigned thread_self_inum __ro_after_init;
 int proc_setup_thread_self(struct super_block *s)
 {
 	struct inode *root_inode = d_inode(s->s_root);
-	struct pid_namespace *ns = s->s_fs_info;
+	struct pid_namespace *ns = proc_pid_ns(root_inode);
 	struct dentry *thread_self;
 
 	inode_lock(root_inode);
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 95a708d83721..3bd12f955867 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -30,21 +30,9 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int uptime_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, uptime_proc_show, NULL);
-}
-
-static const struct file_operations uptime_proc_fops = {
-	.open		= uptime_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_uptime_init(void)
 {
-	proc_create("uptime", 0, NULL, &uptime_proc_fops);
+	proc_create_single("uptime", 0, NULL, uptime_proc_show);
 	return 0;
 }
 fs_initcall(proc_uptime_init);
diff --git a/fs/proc/version.c b/fs/proc/version.c
index 94901e8e700d..b449f186577f 100644
--- a/fs/proc/version.c
+++ b/fs/proc/version.c
@@ -15,21 +15,9 @@ static int version_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int version_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, version_proc_show, NULL);
-}
-
-static const struct file_operations version_proc_fops = {
-	.open		= version_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_version_init(void)
 {
-	proc_create("version", 0, NULL, &version_proc_fops);
+	proc_create_single("version", 0, NULL, version_proc_show);
 	return 0;
 }
 fs_initcall(proc_version_init);
diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c
index eca27878079d..8d72221735d7 100644
--- a/fs/qnx4/namei.c
+++ b/fs/qnx4/namei.c
@@ -114,13 +114,9 @@ struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned i
 	brelse(bh);
 
 	foundinode = qnx4_iget(dir->i_sb, ino);
-	if (IS_ERR(foundinode)) {
+	if (IS_ERR(foundinode))
 		QNX4DEBUG((KERN_ERR "qnx4: lookup->iget -> error %ld\n",
 			   PTR_ERR(foundinode)));
-		return ERR_CAST(foundinode);
-	}
 out:
-	d_add(dentry, foundinode);
-
-	return NULL;
+	return d_splice_alias(foundinode, dentry);
 }
diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c
index 72c2770830be..e2e98e653b8d 100644
--- a/fs/qnx6/namei.c
+++ b/fs/qnx6/namei.c
@@ -29,15 +29,11 @@ struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
 	if (ino) {
 		foundinode = qnx6_iget(dir->i_sb, ino);
 		qnx6_put_page(page);
-		if (IS_ERR(foundinode)) {
+		if (IS_ERR(foundinode))
 			pr_debug("lookup->iget ->  error %ld\n",
 				 PTR_ERR(foundinode));
-			return ERR_CAST(foundinode);
-		}
 	} else {
 		pr_debug("%s(): not found %s\n", __func__, name);
-		return NULL;
 	}
-	d_add(dentry, foundinode);
-	return NULL;
+	return d_splice_alias(foundinode, dentry);
 }
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 020c597ef9b6..d88231e3b2be 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2966,7 +2966,7 @@ static int __init dquot_init(void)
 			NULL);
 
 	order = 0;
-	dquot_hash = (struct hlist_head *)__get_free_pages(GFP_ATOMIC, order);
+	dquot_hash = (struct hlist_head *)__get_free_pages(GFP_KERNEL, order);
 	if (!dquot_hash)
 		panic("Cannot create dquot hash table");
 
diff --git a/fs/read_write.c b/fs/read_write.c
index c4eabbfc90df..e83bd9744b5d 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -2023,7 +2023,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 		ret = mnt_want_write_file(dst_file);
 		if (ret) {
 			info->status = ret;
-			goto next_loop;
+			goto next_fdput;
 		}
 
 		dst_off = info->dest_offset;
@@ -2058,9 +2058,9 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 
 next_file:
 		mnt_drop_write_file(dst_file);
-next_loop:
+next_fdput:
 		fdput(dst_fd);
-
+next_loop:
 		if (fatal_signal_pending(current))
 			goto out;
 	}
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index bd39a998843d..5089dac02660 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -687,8 +687,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod
 	reiserfs_update_inode_transaction(inode);
 	reiserfs_update_inode_transaction(dir);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	retval = journal_end(&th);
 
 out_failed:
@@ -771,8 +770,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
 		goto out_failed;
 	}
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	retval = journal_end(&th);
 
 out_failed:
@@ -871,8 +869,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 	/* the above add_entry did not update dir's stat data */
 	reiserfs_update_sd(&th, dir);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	retval = journal_end(&th);
 out_failed:
 	reiserfs_write_unlock(dir->i_sb);
@@ -1187,8 +1184,7 @@ static int reiserfs_symlink(struct inode *parent_dir,
 		goto out_failed;
 	}
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	retval = journal_end(&th);
 out_failed:
 	reiserfs_write_unlock(parent_dir->i_sb);
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index fe999157dd97..e39b3910d24d 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -389,27 +389,13 @@ static int show_journal(struct seq_file *m, void *unused)
 	return 0;
 }
 
-static int r_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, PDE_DATA(inode), 
-				proc_get_parent_data(inode));
-}
-
-static const struct file_operations r_file_operations = {
-	.open = r_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 static struct proc_dir_entry *proc_info_root = NULL;
 static const char proc_info_root_name[] = "fs/reiserfs";
 
 static void add_file(struct super_block *sb, char *name,
 		     int (*func) (struct seq_file *, void *))
 {
-	proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
-			 &r_file_operations, func);
+	proc_create_single_data(name, 0, REISERFS_SB(sb)->procdir, func, sb);
 }
 
 int reiserfs_proc_info_init(struct super_block *sb)
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 8f06fd1f3d69..6ccb51993a76 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -213,7 +213,7 @@ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
 				   unsigned int flags)
 {
 	unsigned long offset, maxoff;
-	struct inode *inode;
+	struct inode *inode = NULL;
 	struct romfs_inode ri;
 	const char *name;		/* got from dentry */
 	int len, ret;
@@ -233,7 +233,7 @@ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
 
 	for (;;) {
 		if (!offset || offset >= maxoff)
-			goto out0;
+			break;
 
 		ret = romfs_dev_read(dir->i_sb, offset, &ri, sizeof(ri));
 		if (ret < 0)
@@ -244,37 +244,19 @@ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
 				       len);
 		if (ret < 0)
 			goto error;
-		if (ret == 1)
+		if (ret == 1) {
+			/* Hard link handling */
+			if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD)
+				offset = be32_to_cpu(ri.spec) & ROMFH_MASK;
+			inode = romfs_iget(dir->i_sb, offset);
 			break;
+		}
 
 		/* next entry */
 		offset = be32_to_cpu(ri.next) & ROMFH_MASK;
 	}
 
-	/* Hard link handling */
-	if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD)
-		offset = be32_to_cpu(ri.spec) & ROMFH_MASK;
-
-	inode = romfs_iget(dir->i_sb, offset);
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		goto error;
-	}
-	goto outi;
-
-	/*
-	 * it's a bit funky, _lookup needs to return an error code
-	 * (negative) or a NULL, both as a dentry.  ENOENT should not
-	 * be returned, instead we need to create a negative dentry by
-	 * d_add(dentry, NULL); and return 0 as no error.
-	 * (Although as I see, it only matters on writable file
-	 * systems).
-	 */
-out0:
-	inode = NULL;
-outi:
-	d_add(dentry, inode);
-	ret = 0;
+	return d_splice_alias(inode, dentry);
 error:
 	return ERR_PTR(ret);
 }
diff --git a/fs/select.c b/fs/select.c
index ba879c51288f..bc3cc0f98896 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -34,6 +34,29 @@
 
 #include <linux/uaccess.h>
 
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
+{
+	if (file->f_op->poll) {
+		return file->f_op->poll(file, pt);
+	} else if (file_has_poll_mask(file)) {
+		unsigned int events = poll_requested_events(pt);
+		struct wait_queue_head *head;
+
+		if (pt && pt->_qproc) {
+			head = file->f_op->get_poll_head(file, events);
+			if (!head)
+				return DEFAULT_POLLMASK;
+			if (IS_ERR(head))
+				return EPOLLERR;
+			pt->_qproc(file, head, pt);
+		}
+
+		return file->f_op->poll_mask(file, events);
+	} else {
+		return DEFAULT_POLLMASK;
+	}
+}
+EXPORT_SYMBOL_GPL(vfs_poll);
 
 /*
  * Estimate expected accuracy in ns from a timeval.
@@ -233,7 +256,7 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
 	add_wait_queue(wait_address, &entry->wait);
 }
 
-int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
+static int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 			  ktime_t *expires, unsigned long slack)
 {
 	int rc = -EINTR;
@@ -258,7 +281,6 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 
 	return rc;
 }
-EXPORT_SYMBOL(poll_schedule_timeout);
 
 /**
  * poll_select_set_timeout - helper function to setup the timeout value
@@ -503,14 +525,10 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 					continue;
 				f = fdget(i);
 				if (f.file) {
-					const struct file_operations *f_op;
-					f_op = f.file->f_op;
-					mask = DEFAULT_POLLMASK;
-					if (f_op->poll) {
-						wait_key_set(wait, in, out,
-							     bit, busy_flag);
-						mask = (*f_op->poll)(f.file, wait);
-					}
+					wait_key_set(wait, in, out, bit,
+						     busy_flag);
+					mask = vfs_poll(f.file, wait);
+
 					fdput(f);
 					if ((mask & POLLIN_SET) && (in & bit)) {
 						res_in |= bit;
@@ -813,34 +831,29 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
 				     bool *can_busy_poll,
 				     __poll_t busy_flag)
 {
-	__poll_t mask;
-	int fd;
-
-	mask = 0;
-	fd = pollfd->fd;
-	if (fd >= 0) {
-		struct fd f = fdget(fd);
-		mask = EPOLLNVAL;
-		if (f.file) {
-			/* userland u16 ->events contains POLL... bitmap */
-			__poll_t filter = demangle_poll(pollfd->events) |
-						EPOLLERR | EPOLLHUP;
-			mask = DEFAULT_POLLMASK;
-			if (f.file->f_op->poll) {
-				pwait->_key = filter;
-				pwait->_key |= busy_flag;
-				mask = f.file->f_op->poll(f.file, pwait);
-				if (mask & busy_flag)
-					*can_busy_poll = true;
-			}
-			/* Mask out unneeded events. */
-			mask &= filter;
-			fdput(f);
-		}
-	}
+	int fd = pollfd->fd;
+	__poll_t mask = 0, filter;
+	struct fd f;
+
+	if (fd < 0)
+		goto out;
+	mask = EPOLLNVAL;
+	f = fdget(fd);
+	if (!f.file)
+		goto out;
+
+	/* userland u16 ->events contains POLL... bitmap */
+	filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP;
+	pwait->_key = filter | busy_flag;
+	mask = vfs_poll(f.file, pwait);
+	if (mask & busy_flag)
+		*can_busy_poll = true;
+	mask &= filter;		/* Mask out unneeded events. */
+	fdput(f);
+
+out:
 	/* ... and so does ->revents */
 	pollfd->revents = mangle_poll(mask);
-
 	return mask;
 }
 
diff --git a/fs/seq_file.c b/fs/seq_file.c
index c6c27f1f9c98..4cc090b50cc5 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -709,11 +709,6 @@ void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter,
 	if (m->count + width >= m->size)
 		goto overflow;
 
-	if (num < 10) {
-		m->buf[m->count++] = num + '0';
-		return;
-	}
-
 	len = num_to_str(m->buf + m->count, m->size - m->count, num, width);
 	if (!len)
 		goto overflow;
diff --git a/fs/signalfd.c b/fs/signalfd.c
index d2187a813376..cbb42f77a2bd 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -81,83 +81,86 @@ static __poll_t signalfd_poll(struct file *file, poll_table *wait)
 static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 			     siginfo_t const *kinfo)
 {
-	long err;
+	struct signalfd_siginfo new;
 
 	BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128);
 
 	/*
 	 * Unused members should be zero ...
 	 */
-	err = __clear_user(uinfo, sizeof(*uinfo));
+	memset(&new, 0, sizeof(new));
 
 	/*
 	 * If you change siginfo_t structure, please be sure
 	 * this code is fixed accordingly.
 	 */
-	err |= __put_user(kinfo->si_signo, &uinfo->ssi_signo);
-	err |= __put_user(kinfo->si_errno, &uinfo->ssi_errno);
-	err |= __put_user(kinfo->si_code, &uinfo->ssi_code);
+	new.ssi_signo = kinfo->si_signo;
+	new.ssi_errno = kinfo->si_errno;
+	new.ssi_code  = kinfo->si_code;
 	switch (siginfo_layout(kinfo->si_signo, kinfo->si_code)) {
 	case SIL_KILL:
-		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
-		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
+		new.ssi_pid = kinfo->si_pid;
+		new.ssi_uid = kinfo->si_uid;
 		break;
 	case SIL_TIMER:
-		 err |= __put_user(kinfo->si_tid, &uinfo->ssi_tid);
-		 err |= __put_user(kinfo->si_overrun, &uinfo->ssi_overrun);
-		 err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
-		 err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
+		new.ssi_tid = kinfo->si_tid;
+		new.ssi_overrun = kinfo->si_overrun;
+		new.ssi_ptr = (long) kinfo->si_ptr;
+		new.ssi_int = kinfo->si_int;
 		break;
 	case SIL_POLL:
-		err |= __put_user(kinfo->si_band, &uinfo->ssi_band);
-		err |= __put_user(kinfo->si_fd, &uinfo->ssi_fd);
+		new.ssi_band = kinfo->si_band;
+		new.ssi_fd   = kinfo->si_fd;
 		break;
-	case SIL_FAULT:
-		err |= __put_user((long) kinfo->si_addr, &uinfo->ssi_addr);
-#ifdef __ARCH_SI_TRAPNO
-		err |= __put_user(kinfo->si_trapno, &uinfo->ssi_trapno);
-#endif
-#ifdef BUS_MCEERR_AO
+	case SIL_FAULT_BNDERR:
+	case SIL_FAULT_PKUERR:
 		/*
-		 * Other callers might not initialize the si_lsb field,
-		 * so check explicitly for the right codes here.
+		 * Fall through to the SIL_FAULT case.  Both SIL_FAULT_BNDERR
+		 * and SIL_FAULT_PKUERR are only generated by faults that
+		 * deliver them synchronously to userspace.  In case someone
+		 * injects one of these signals and signalfd catches it treat
+		 * it as SIL_FAULT.
 		 */
-		if (kinfo->si_signo == SIGBUS &&
-		     kinfo->si_code == BUS_MCEERR_AO)
-			err |= __put_user((short) kinfo->si_addr_lsb,
-					  &uinfo->ssi_addr_lsb);
+	case SIL_FAULT:
+		new.ssi_addr = (long) kinfo->si_addr;
+#ifdef __ARCH_SI_TRAPNO
+		new.ssi_trapno = kinfo->si_trapno;
 #endif
-#ifdef BUS_MCEERR_AR
-		/*
-		 * Other callers might not initialize the si_lsb field,
-		 * so check explicitly for the right codes here.
-		 */
-		if (kinfo->si_signo == SIGBUS &&
-		    kinfo->si_code == BUS_MCEERR_AR)
-			err |= __put_user((short) kinfo->si_addr_lsb,
-					  &uinfo->ssi_addr_lsb);
+		break;
+	case SIL_FAULT_MCEERR:
+		new.ssi_addr = (long) kinfo->si_addr;
+#ifdef __ARCH_SI_TRAPNO
+		new.ssi_trapno = kinfo->si_trapno;
 #endif
+		new.ssi_addr_lsb = (short) kinfo->si_addr_lsb;
 		break;
 	case SIL_CHLD:
-		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
-		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
-		err |= __put_user(kinfo->si_status, &uinfo->ssi_status);
-		err |= __put_user(kinfo->si_utime, &uinfo->ssi_utime);
-		err |= __put_user(kinfo->si_stime, &uinfo->ssi_stime);
+		new.ssi_pid    = kinfo->si_pid;
+		new.ssi_uid    = kinfo->si_uid;
+		new.ssi_status = kinfo->si_status;
+		new.ssi_utime  = kinfo->si_utime;
+		new.ssi_stime  = kinfo->si_stime;
 		break;
 	case SIL_RT:
-	default:
 		/*
 		 * This case catches also the signals queued by sigqueue().
 		 */
-		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
-		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
-		err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
-		err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
+		new.ssi_pid = kinfo->si_pid;
+		new.ssi_uid = kinfo->si_uid;
+		new.ssi_ptr = (long) kinfo->si_ptr;
+		new.ssi_int = kinfo->si_int;
+		break;
+	case SIL_SYS:
+		new.ssi_call_addr = (long) kinfo->si_call_addr;
+		new.ssi_syscall   = kinfo->si_syscall;
+		new.ssi_arch      = kinfo->si_arch;
 		break;
 	}
 
-	return err ? -EFAULT: sizeof(*uinfo);
+	if (copy_to_user(uinfo, &new, sizeof(struct signalfd_siginfo)))
+		return -EFAULT;
+
+	return sizeof(*uinfo);
 }
 
 static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, siginfo_t *info,
diff --git a/fs/super.c b/fs/super.c
index 5fa9a8d8d865..50728d9c1a05 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -121,13 +121,23 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	sb = container_of(shrink, struct super_block, s_shrink);
 
 	/*
-	 * Don't call trylock_super as it is a potential
-	 * scalability bottleneck. The counts could get updated
-	 * between super_cache_count and super_cache_scan anyway.
-	 * Call to super_cache_count with shrinker_rwsem held
-	 * ensures the safety of call to list_lru_shrink_count() and
-	 * s_op->nr_cached_objects().
+	 * We don't call trylock_super() here as it is a scalability bottleneck,
+	 * so we're exposed to partial setup state. The shrinker rwsem does not
+	 * protect filesystem operations backing list_lru_shrink_count() or
+	 * s_op->nr_cached_objects(). Counts can change between
+	 * super_cache_count and super_cache_scan, so we really don't need locks
+	 * here.
+	 *
+	 * However, if we are currently mounting the superblock, the underlying
+	 * filesystem might be in a state of partial construction and hence it
+	 * is dangerous to access it.  trylock_super() uses a SB_BORN check to
+	 * avoid this situation, so do the same here. The memory barrier is
+	 * matched with the one in mount_fs() as we don't hold locks here.
 	 */
+	if (!(sb->s_flags & SB_BORN))
+		return 0;
+	smp_rmb();
+
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		total_objects = sb->s_op->nr_cached_objects(sb, sc);
 
@@ -167,6 +177,7 @@ static void destroy_unused_super(struct super_block *s)
 	security_sb_free(s);
 	put_user_ns(s->s_user_ns);
 	kfree(s->s_subtype);
+	free_prealloced_shrinker(&s->s_shrink);
 	/* no delays needed */
 	destroy_super_work(&s->destroy_work);
 }
@@ -252,6 +263,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	s->s_shrink.count_objects = super_cache_count;
 	s->s_shrink.batch = 1024;
 	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
+	if (prealloc_shrinker(&s->s_shrink))
+		goto fail;
 	return s;
 
 fail:
@@ -518,11 +531,7 @@ retry:
 	hlist_add_head(&s->s_instances, &type->fs_supers);
 	spin_unlock(&sb_lock);
 	get_filesystem(type);
-	err = register_shrinker(&s->s_shrink);
-	if (err) {
-		deactivate_locked_super(s);
-		s = ERR_PTR(err);
-	}
+	register_shrinker_prepared(&s->s_shrink);
 	return s;
 }
 
@@ -938,7 +947,7 @@ void emergency_remount(void)
 static void do_thaw_all_callback(struct super_block *sb)
 {
 	down_write(&sb->s_umount);
-	if (sb->s_root && sb->s_flags & MS_BORN) {
+	if (sb->s_root && sb->s_flags & SB_BORN) {
 		emergency_thaw_bdev(sb);
 		thaw_super_locked(sb);
 	} else {
@@ -1273,6 +1282,14 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
 	sb = root->d_sb;
 	BUG_ON(!sb);
 	WARN_ON(!sb->s_bdi);
+
+	/*
+	 * Write barrier is for super_cache_count(). We place it before setting
+	 * SB_BORN as the data dependency between the two functions is the
+	 * superblock structure contents that we just set up, not the SB_BORN
+	 * flag.
+	 */
+	smp_wmb();
 	sb->s_flags |= SB_BORN;
 
 	error = security_sb_kern_mount(sb, flags, secdata);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index b428d317ae92..92682fcc41f6 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -25,7 +25,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 {
 	struct dentry *root;
 	void *ns;
-	bool new_sb;
+	bool new_sb = false;
 
 	if (!(flags & SB_KERNMOUNT)) {
 		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
@@ -35,9 +35,9 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
 	root = kernfs_mount_ns(fs_type, flags, sysfs_root,
 				SYSFS_MAGIC, &new_sb, ns);
-	if (IS_ERR(root) || !new_sb)
+	if (!new_sb)
 		kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
-	else if (new_sb)
+	else if (!IS_ERR(root))
 		root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE;
 
 	return root;
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index 250b0755b908..4d5d20491ffd 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -51,14 +51,9 @@ static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, un
 	if (dentry->d_name.len > SYSV_NAMELEN)
 		return ERR_PTR(-ENAMETOOLONG);
 	ino = sysv_inode_by_name(dentry);
-
-	if (ino) {
+	if (ino)
 		inode = sysv_iget(dir->i_sb, ino);
-		if (IS_ERR(inode))
-			return ERR_CAST(inode);
-	}
-	d_add(dentry, inode);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 static int sysv_mknod(struct inode * dir, struct dentry * dentry, umode_t mode, dev_t rdev)
diff --git a/fs/timerfd.c b/fs/timerfd.c
index cdad49da3ff7..d84a2bee4f82 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -226,21 +226,20 @@ static int timerfd_release(struct inode *inode, struct file *file)
 	kfree_rcu(ctx, rcu);
 	return 0;
 }
-
-static __poll_t timerfd_poll(struct file *file, poll_table *wait)
+	
+static struct wait_queue_head *timerfd_get_poll_head(struct file *file,
+		__poll_t eventmask)
 {
 	struct timerfd_ctx *ctx = file->private_data;
-	__poll_t events = 0;
-	unsigned long flags;
 
-	poll_wait(file, &ctx->wqh, wait);
+	return &ctx->wqh;
+}
 
-	spin_lock_irqsave(&ctx->wqh.lock, flags);
-	if (ctx->ticks)
-		events |= EPOLLIN;
-	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+static __poll_t timerfd_poll_mask(struct file *file, __poll_t eventmask)
+{
+	struct timerfd_ctx *ctx = file->private_data;
 
-	return events;
+	return ctx->ticks ? EPOLLIN : 0;
 }
 
 static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
@@ -364,7 +363,8 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 
 static const struct file_operations timerfd_fops = {
 	.release	= timerfd_release,
-	.poll		= timerfd_poll,
+	.get_poll_head	= timerfd_get_poll_head,
+	.poll_mask	= timerfd_poll_mask,
 	.read		= timerfd_read,
 	.llseek		= noop_llseek,
 	.show_fdinfo	= timerfd_show,
diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c
index 616a688f5d8f..55c508fe8131 100644
--- a/fs/ubifs/crypto.c
+++ b/fs/ubifs/crypto.c
@@ -24,14 +24,6 @@ static bool ubifs_crypt_empty_dir(struct inode *inode)
 	return ubifs_check_dir_empty(inode) == 0;
 }
 
-static unsigned int ubifs_crypt_max_namelen(struct inode *inode)
-{
-	if (S_ISLNK(inode->i_mode))
-		return UBIFS_MAX_INO_DATA;
-	else
-		return UBIFS_MAX_NLEN;
-}
-
 int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn,
 		  unsigned int in_len, unsigned int *out_len, int block)
 {
@@ -89,5 +81,5 @@ const struct fscrypt_operations ubifs_crypt_operations = {
 	.get_context		= ubifs_crypt_get_context,
 	.set_context		= ubifs_crypt_set_context,
 	.empty_dir		= ubifs_crypt_empty_dir,
-	.max_namelen		= ubifs_crypt_max_namelen,
+	.max_namelen		= UBIFS_MAX_NLEN,
 };
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 9d7fb88e172e..4e267cc21c77 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -214,7 +214,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 	int err;
 	union ubifs_key key;
 	struct inode *inode = NULL;
-	struct ubifs_dent_node *dent;
+	struct ubifs_dent_node *dent = NULL;
 	struct ubifs_info *c = dir->i_sb->s_fs_info;
 	struct fscrypt_name nm;
 
@@ -229,14 +229,14 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_PTR(err);
 
 	if (fname_len(&nm) > UBIFS_MAX_NLEN) {
-		err = -ENAMETOOLONG;
-		goto out_fname;
+		inode = ERR_PTR(-ENAMETOOLONG);
+		goto done;
 	}
 
 	dent = kmalloc(UBIFS_MAX_DENT_NODE_SZ, GFP_NOFS);
 	if (!dent) {
-		err = -ENOMEM;
-		goto out_fname;
+		inode = ERR_PTR(-ENOMEM);
+		goto done;
 	}
 
 	if (nm.hash) {
@@ -250,16 +250,16 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 	}
 
 	if (err) {
-		if (err == -ENOENT) {
+		if (err == -ENOENT)
 			dbg_gen("not found");
-			goto done;
-		}
-		goto out_dent;
+		else
+			inode = ERR_PTR(err);
+		goto done;
 	}
 
 	if (dbg_check_name(c, dent, &nm)) {
-		err = -EINVAL;
-		goto out_dent;
+		inode = ERR_PTR(-EINVAL);
+		goto done;
 	}
 
 	inode = ubifs_iget(dir->i_sb, le64_to_cpu(dent->inum));
@@ -272,7 +272,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 		ubifs_err(c, "dead directory entry '%pd', error %d",
 			  dentry, err);
 		ubifs_ro_mode(c, err);
-		goto out_dent;
+		goto done;
 	}
 
 	if (ubifs_crypt_is_encrypted(dir) &&
@@ -280,27 +280,14 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 	    !fscrypt_has_permitted_context(dir, inode)) {
 		ubifs_warn(c, "Inconsistent encryption contexts: %lu/%lu",
 			   dir->i_ino, inode->i_ino);
-		err = -EPERM;
-		goto out_inode;
+		iput(inode);
+		inode = ERR_PTR(-EPERM);
 	}
 
 done:
 	kfree(dent);
 	fscrypt_free_filename(&nm);
-	/*
-	 * Note, d_splice_alias() would be required instead if we supported
-	 * NFS.
-	 */
-	d_add(dentry, inode);
-	return NULL;
-
-out_inode:
-	iput(inode);
-out_dent:
-	kfree(dent);
-out_fname:
-	fscrypt_free_filename(&nm);
-	return ERR_PTR(err);
+	return d_splice_alias(inode, dentry);
 }
 
 static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 0458dd47e105..c586026508db 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -622,8 +622,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
 	if (fibh.sbh != fibh.ebh)
 		brelse(fibh.ebh);
 	brelse(fibh.sbh);
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 
 	return 0;
 }
@@ -733,8 +732,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inc_nlink(dir);
 	dir->i_ctime = dir->i_mtime = current_time(dir);
 	mark_inode_dirty(dir);
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	if (fibh.sbh != fibh.ebh)
 		brelse(fibh.ebh);
 	brelse(fibh.sbh);
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index f897e55f2cd0..16a8ad21b77e 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -28,6 +28,9 @@
 
 #include "udf_sb.h"
 
+#define SURROGATE_MASK 0xfffff800
+#define SURROGATE_PAIR 0x0000d800
+
 static int udf_uni2char_utf8(wchar_t uni,
 			     unsigned char *out,
 			     int boundlen)
@@ -37,6 +40,9 @@ static int udf_uni2char_utf8(wchar_t uni,
 	if (boundlen <= 0)
 		return -ENAMETOOLONG;
 
+	if ((uni & SURROGATE_MASK) == SURROGATE_PAIR)
+		return -EINVAL;
+
 	if (uni < 0x80) {
 		out[u_len++] = (unsigned char)uni;
 	} else if (uni < 0x800) {
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 32545cd00ceb..d5f43ba76c59 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -39,8 +39,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
 {
 	int err = ufs_add_link(dentry, inode);
 	if (!err) {
-		unlock_new_inode(inode);
-		d_instantiate(dentry, inode);
+		d_instantiate_new(dentry, inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
@@ -193,8 +192,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 	if (err)
 		goto out_fail;
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
 out_fail:
diff --git a/fs/xattr.c b/fs/xattr.c
index 61cd28ba25f3..f9cb1db187b7 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -229,7 +229,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(vfs_setxattr);
 
-ssize_t
+static ssize_t
 xattr_getsecurity(struct inode *inode, const char *name, void *value,
 			size_t size)
 {
@@ -254,7 +254,6 @@ out:
 out_noalloc:
 	return len;
 }
-EXPORT_SYMBOL_GPL(xattr_getsecurity);
 
 /*
  * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr
@@ -354,7 +353,6 @@ vfs_listxattr(struct dentry *dentry, char *list, size_t size)
 	if (error)
 		return error;
 	if (inode->i_op->listxattr && (inode->i_opflags & IOP_XATTR)) {
-		error = -EOPNOTSUPP;
 		error = inode->i_op->listxattr(dentry, list, size);
 	} else {
 		error = security_inode_listsecurity(inode, list, size);
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 46bcf0e649f5..457ac9f97377 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -85,6 +85,24 @@ config XFS_ONLINE_SCRUB
 
 	  If unsure, say N.
 
+config XFS_ONLINE_REPAIR
+	bool "XFS online metadata repair support"
+	default n
+	depends on XFS_FS && XFS_ONLINE_SCRUB
+	help
+	  If you say Y here you will be able to repair metadata on a
+	  mounted XFS filesystem.  This feature is intended to reduce
+	  filesystem downtime by fixing minor problems before they cause the
+	  filesystem to go down.  However, it requires that the filesystem be
+	  formatted with secondary metadata, such as reverse mappings and inode
+	  parent pointers.
+
+	  This feature is considered EXPERIMENTAL.  Use with caution!
+
+	  See the xfs_scrub man page in section 8 for additional information.
+
+	  If unsure, say N.
+
 config XFS_WARN
 	bool "XFS Verbose Warnings"
 	depends on XFS_FS && !XFS_DEBUG
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7ceb41a9786a..e8d67a443bd7 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -28,6 +28,7 @@ xfs-y				+= xfs_trace.o
 
 # build the libxfs code first
 xfs-y				+= $(addprefix libxfs/, \
+				   xfs_ag.o \
 				   xfs_alloc.o \
 				   xfs_alloc_btree.o \
 				   xfs_attr.o \
@@ -163,4 +164,12 @@ xfs-y				+= $(addprefix scrub/, \
 
 xfs-$(CONFIG_XFS_RT)		+= scrub/rtbitmap.o
 xfs-$(CONFIG_XFS_QUOTA)		+= scrub/quota.o
+
+# online repair
+ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
+xfs-y				+= $(addprefix scrub/, \
+				   agheader_repair.o \
+				   repair.o \
+				   )
+endif
 endif
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
new file mode 100644
index 000000000000..9345802c99f7
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -0,0 +1,464 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2018 Red Hat, Inc.
+ * All rights reserved.
+ */
+
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+
+static struct xfs_buf *
+xfs_get_aghdr_buf(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	int			flags,
+	const struct xfs_buf_ops *ops)
+{
+	struct xfs_buf		*bp;
+
+	bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
+	if (!bp)
+		return NULL;
+
+	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+	bp->b_bn = blkno;
+	bp->b_maps[0].bm_bn = blkno;
+	bp->b_ops = ops;
+
+	return bp;
+}
+
+/*
+ * Generic btree root block init function
+ */
+static void
+xfs_btroot_init(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct aghdr_init_data	*id)
+{
+	xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno, 0);
+}
+
+/*
+ * Alloc btree root block init functions
+ */
+static void
+xfs_bnoroot_init(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct aghdr_init_data	*id)
+{
+	struct xfs_alloc_rec	*arec;
+
+	xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno, 0);
+	arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
+	arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
+	arec->ar_blockcount = cpu_to_be32(id->agsize -
+					  be32_to_cpu(arec->ar_startblock));
+}
+
+static void
+xfs_cntroot_init(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct aghdr_init_data	*id)
+{
+	struct xfs_alloc_rec	*arec;
+
+	xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno, 0);
+	arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
+	arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
+	arec->ar_blockcount = cpu_to_be32(id->agsize -
+					  be32_to_cpu(arec->ar_startblock));
+}
+
+/*
+ * Reverse map root block init
+ */
+static void
+xfs_rmaproot_init(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct aghdr_init_data	*id)
+{
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_rmap_rec	*rrec;
+
+	xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno, 0);
+
+	/*
+	 * mark the AG header regions as static metadata The BNO
+	 * btree block is the first block after the headers, so
+	 * it's location defines the size of region the static
+	 * metadata consumes.
+	 *
+	 * Note: unlike mkfs, we never have to account for log
+	 * space when growing the data regions
+	 */
+	rrec = XFS_RMAP_REC_ADDR(block, 1);
+	rrec->rm_startblock = 0;
+	rrec->rm_blockcount = cpu_to_be32(XFS_BNO_BLOCK(mp));
+	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_FS);
+	rrec->rm_offset = 0;
+
+	/* account freespace btree root blocks */
+	rrec = XFS_RMAP_REC_ADDR(block, 2);
+	rrec->rm_startblock = cpu_to_be32(XFS_BNO_BLOCK(mp));
+	rrec->rm_blockcount = cpu_to_be32(2);
+	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
+	rrec->rm_offset = 0;
+
+	/* account inode btree root blocks */
+	rrec = XFS_RMAP_REC_ADDR(block, 3);
+	rrec->rm_startblock = cpu_to_be32(XFS_IBT_BLOCK(mp));
+	rrec->rm_blockcount = cpu_to_be32(XFS_RMAP_BLOCK(mp) -
+					  XFS_IBT_BLOCK(mp));
+	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_INOBT);
+	rrec->rm_offset = 0;
+
+	/* account for rmap btree root */
+	rrec = XFS_RMAP_REC_ADDR(block, 4);
+	rrec->rm_startblock = cpu_to_be32(XFS_RMAP_BLOCK(mp));
+	rrec->rm_blockcount = cpu_to_be32(1);
+	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
+	rrec->rm_offset = 0;
+
+	/* account for refc btree root */
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		rrec = XFS_RMAP_REC_ADDR(block, 5);
+		rrec->rm_startblock = cpu_to_be32(xfs_refc_block(mp));
+		rrec->rm_blockcount = cpu_to_be32(1);
+		rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC);
+		rrec->rm_offset = 0;
+		be16_add_cpu(&block->bb_numrecs, 1);
+	}
+}
+
+/*
+ * Initialise new secondary superblocks with the pre-grow geometry, but mark
+ * them as "in progress" so we know they haven't yet been activated. This will
+ * get cleared when the update with the new geometry information is done after
+ * changes to the primary are committed. This isn't strictly necessary, but we
+ * get it for free with the delayed buffer write lists and it means we can tell
+ * if a grow operation didn't complete properly after the fact.
+ */
+static void
+xfs_sbblock_init(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct aghdr_init_data	*id)
+{
+	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);
+
+	xfs_sb_to_disk(dsb, &mp->m_sb);
+	dsb->sb_inprogress = 1;
+}
+
+static void
+xfs_agfblock_init(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct aghdr_init_data	*id)
+{
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(bp);
+	xfs_extlen_t		tmpsize;
+
+	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
+	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
+	agf->agf_seqno = cpu_to_be32(id->agno);
+	agf->agf_length = cpu_to_be32(id->agsize);
+	agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
+	agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
+	agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
+	agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
+	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
+		agf->agf_roots[XFS_BTNUM_RMAPi] =
+					cpu_to_be32(XFS_RMAP_BLOCK(mp));
+		agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
+		agf->agf_rmap_blocks = cpu_to_be32(1);
+	}
+
+	agf->agf_flfirst = cpu_to_be32(1);
+	agf->agf_fllast = 0;
+	agf->agf_flcount = 0;
+	tmpsize = id->agsize - mp->m_ag_prealloc_blocks;
+	agf->agf_freeblks = cpu_to_be32(tmpsize);
+	agf->agf_longest = cpu_to_be32(tmpsize);
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		agf->agf_refcount_root = cpu_to_be32(
+				xfs_refc_block(mp));
+		agf->agf_refcount_level = cpu_to_be32(1);
+		agf->agf_refcount_blocks = cpu_to_be32(1);
+	}
+}
+
+static void
+xfs_agflblock_init(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct aghdr_init_data	*id)
+{
+	struct xfs_agfl		*agfl = XFS_BUF_TO_AGFL(bp);
+	__be32			*agfl_bno;
+	int			bucket;
+
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
+		agfl->agfl_seqno = cpu_to_be32(id->agno);
+		uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
+	}
+
+	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
+	for (bucket = 0; bucket < xfs_agfl_size(mp); bucket++)
+		agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
+}
+
+static void
+xfs_agiblock_init(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct aghdr_init_data	*id)
+{
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(bp);
+	int			bucket;
+
+	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
+	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
+	agi->agi_seqno = cpu_to_be32(id->agno);
+	agi->agi_length = cpu_to_be32(id->agsize);
+	agi->agi_count = 0;
+	agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp));
+	agi->agi_level = cpu_to_be32(1);
+	agi->agi_freecount = 0;
+	agi->agi_newino = cpu_to_be32(NULLAGINO);
+	agi->agi_dirino = cpu_to_be32(NULLAGINO);
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
+	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+		agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
+		agi->agi_free_level = cpu_to_be32(1);
+	}
+	for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
+		agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
+}
+
+typedef void (*aghdr_init_work_f)(struct xfs_mount *mp, struct xfs_buf *bp,
+				  struct aghdr_init_data *id);
+static int
+xfs_ag_init_hdr(
+	struct xfs_mount	*mp,
+	struct aghdr_init_data	*id,
+	aghdr_init_work_f	work,
+	const struct xfs_buf_ops *ops)
+
+{
+	struct xfs_buf		*bp;
+
+	bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, 0, ops);
+	if (!bp)
+		return -ENOMEM;
+
+	(*work)(mp, bp, id);
+
+	xfs_buf_delwri_queue(bp, &id->buffer_list);
+	xfs_buf_relse(bp);
+	return 0;
+}
+
+struct xfs_aghdr_grow_data {
+	xfs_daddr_t		daddr;
+	size_t			numblks;
+	const struct xfs_buf_ops *ops;
+	aghdr_init_work_f	work;
+	xfs_btnum_t		type;
+	bool			need_init;
+};
+
+/*
+ * Prepare new AG headers to be written to disk. We use uncached buffers here,
+ * as it is assumed these new AG headers are currently beyond the currently
+ * valid filesystem address space. Using cached buffers would trip over EOFS
+ * corruption detection alogrithms in the buffer cache lookup routines.
+ *
+ * This is a non-transactional function, but the prepared buffers are added to a
+ * delayed write buffer list supplied by the caller so they can submit them to
+ * disk and wait on them as required.
+ */
+int
+xfs_ag_init_headers(
+	struct xfs_mount	*mp,
+	struct aghdr_init_data	*id)
+
+{
+	struct xfs_aghdr_grow_data aghdr_data[] = {
+	{ /* SB */
+		.daddr = XFS_AG_DADDR(mp, id->agno, XFS_SB_DADDR),
+		.numblks = XFS_FSS_TO_BB(mp, 1),
+		.ops = &xfs_sb_buf_ops,
+		.work = &xfs_sbblock_init,
+		.need_init = true
+	},
+	{ /* AGF */
+		.daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGF_DADDR(mp)),
+		.numblks = XFS_FSS_TO_BB(mp, 1),
+		.ops = &xfs_agf_buf_ops,
+		.work = &xfs_agfblock_init,
+		.need_init = true
+	},
+	{ /* AGFL */
+		.daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGFL_DADDR(mp)),
+		.numblks = XFS_FSS_TO_BB(mp, 1),
+		.ops = &xfs_agfl_buf_ops,
+		.work = &xfs_agflblock_init,
+		.need_init = true
+	},
+	{ /* AGI */
+		.daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGI_DADDR(mp)),
+		.numblks = XFS_FSS_TO_BB(mp, 1),
+		.ops = &xfs_agi_buf_ops,
+		.work = &xfs_agiblock_init,
+		.need_init = true
+	},
+	{ /* BNO root block */
+		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_BNO_BLOCK(mp)),
+		.numblks = BTOBB(mp->m_sb.sb_blocksize),
+		.ops = &xfs_allocbt_buf_ops,
+		.work = &xfs_bnoroot_init,
+		.need_init = true
+	},
+	{ /* CNT root block */
+		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
+		.numblks = BTOBB(mp->m_sb.sb_blocksize),
+		.ops = &xfs_allocbt_buf_ops,
+		.work = &xfs_cntroot_init,
+		.need_init = true
+	},
+	{ /* INO root block */
+		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_IBT_BLOCK(mp)),
+		.numblks = BTOBB(mp->m_sb.sb_blocksize),
+		.ops = &xfs_inobt_buf_ops,
+		.work = &xfs_btroot_init,
+		.type = XFS_BTNUM_INO,
+		.need_init = true
+	},
+	{ /* FINO root block */
+		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_FIBT_BLOCK(mp)),
+		.numblks = BTOBB(mp->m_sb.sb_blocksize),
+		.ops = &xfs_inobt_buf_ops,
+		.work = &xfs_btroot_init,
+		.type = XFS_BTNUM_FINO,
+		.need_init =  xfs_sb_version_hasfinobt(&mp->m_sb)
+	},
+	{ /* RMAP root block */
+		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_RMAP_BLOCK(mp)),
+		.numblks = BTOBB(mp->m_sb.sb_blocksize),
+		.ops = &xfs_rmapbt_buf_ops,
+		.work = &xfs_rmaproot_init,
+		.need_init = xfs_sb_version_hasrmapbt(&mp->m_sb)
+	},
+	{ /* REFC root block */
+		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, xfs_refc_block(mp)),
+		.numblks = BTOBB(mp->m_sb.sb_blocksize),
+		.ops = &xfs_refcountbt_buf_ops,
+		.work = &xfs_btroot_init,
+		.type = XFS_BTNUM_REFC,
+		.need_init = xfs_sb_version_hasreflink(&mp->m_sb)
+	},
+	{ /* NULL terminating block */
+		.daddr = XFS_BUF_DADDR_NULL,
+	}
+	};
+	struct  xfs_aghdr_grow_data *dp;
+	int			error = 0;
+
+	/* Account for AG free space in new AG */
+	id->nfree += id->agsize - mp->m_ag_prealloc_blocks;
+	for (dp = &aghdr_data[0]; dp->daddr != XFS_BUF_DADDR_NULL; dp++) {
+		if (!dp->need_init)
+			continue;
+
+		id->daddr = dp->daddr;
+		id->numblks = dp->numblks;
+		id->type = dp->type;
+		error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops);
+		if (error)
+			break;
+	}
+	return error;
+}
+
+/*
+ * Extent the AG indicated by the @id by the length passed in
+ */
+int
+xfs_ag_extend_space(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct aghdr_init_data	*id,
+	xfs_extlen_t		len)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_buf		*bp;
+	struct xfs_agi		*agi;
+	struct xfs_agf		*agf;
+	int			error;
+
+	/*
+	 * Change the agi length.
+	 */
+	error = xfs_ialloc_read_agi(mp, tp, id->agno, &bp);
+	if (error)
+		return error;
+
+	agi = XFS_BUF_TO_AGI(bp);
+	be32_add_cpu(&agi->agi_length, len);
+	ASSERT(id->agno == mp->m_sb.sb_agcount - 1 ||
+	       be32_to_cpu(agi->agi_length) == mp->m_sb.sb_agblocks);
+	xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH);
+
+	/*
+	 * Change agf length.
+	 */
+	error = xfs_alloc_read_agf(mp, tp, id->agno, 0, &bp);
+	if (error)
+		return error;
+
+	agf = XFS_BUF_TO_AGF(bp);
+	be32_add_cpu(&agf->agf_length, len);
+	ASSERT(agf->agf_length == agi->agi_length);
+	xfs_alloc_log_agf(tp, bp, XFS_AGF_LENGTH);
+
+	/*
+	 * Free the new space.
+	 *
+	 * XFS_RMAP_OWN_NULL is used here to tell the rmap btree that
+	 * this doesn't actually exist in the rmap btree.
+	 */
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL);
+	error = xfs_rmap_free(tp, bp, id->agno,
+				be32_to_cpu(agf->agf_length) - len,
+				len, &oinfo);
+	if (error)
+		return error;
+
+	return  xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, id->agno,
+					be32_to_cpu(agf->agf_length) - len),
+				len, &oinfo, XFS_AG_RESV_NONE);
+}
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
new file mode 100644
index 000000000000..412702e23f61
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018 Red Hat, Inc.
+ * All rights reserved.
+ */
+
+#ifndef __LIBXFS_AG_H
+#define __LIBXFS_AG_H 1
+
+struct xfs_mount;
+struct xfs_trans;
+
+struct aghdr_init_data {
+	/* per ag data */
+	xfs_agblock_t		agno;		/* ag to init */
+	xfs_extlen_t		agsize;		/* new AG size */
+	struct list_head	buffer_list;	/* buffer writeback list */
+	xfs_rfsblock_t		nfree;		/* cumulative new free space */
+
+	/* per header data */
+	xfs_daddr_t		daddr;		/* header location */
+	size_t			numblks;	/* size of header */
+	xfs_btnum_t		type;		/* type of btree root block */
+};
+
+int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
+int xfs_ag_extend_space(struct xfs_mount *mp, struct xfs_trans *tp,
+			struct aghdr_init_data *id, xfs_extlen_t len);
+
+#endif /* __LIBXFS_AG_H */
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 4bcc095fe44a..dc9dd3805d97 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -39,6 +39,9 @@
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
 #include "xfs_ag_resv.h"
+#include "xfs_bmap.h"
+
+extern kmem_zone_t	*xfs_bmap_free_item_zone;
 
 struct workqueue_struct *xfs_alloc_wq;
 
@@ -2060,6 +2063,30 @@ xfs_alloc_space_available(
 	return true;
 }
 
+int
+xfs_free_agfl_block(
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		agbno,
+	struct xfs_buf		*agbp,
+	struct xfs_owner_info	*oinfo)
+{
+	int			error;
+	struct xfs_buf		*bp;
+
+	error = xfs_free_ag_extent(tp, agbp, agno, agbno, 1, oinfo,
+				   XFS_AG_RESV_AGFL);
+	if (error)
+		return error;
+
+	bp = xfs_btree_get_bufs(tp->t_mountp, tp, agno, agbno, 0);
+	if (!bp)
+		return -EFSCORRUPTED;
+	xfs_trans_binval(tp, bp);
+
+	return 0;
+}
+
 /*
  * Check the agfl fields of the agf for inconsistency or corruption. The purpose
  * is to detect an agfl header padding mismatch between current and early v5
@@ -2148,6 +2175,40 @@ xfs_agfl_reset(
 }
 
 /*
+ * Defer an AGFL block free. This is effectively equivalent to
+ * xfs_bmap_add_free() with some special handling particular to AGFL blocks.
+ *
+ * Deferring AGFL frees helps prevent log reservation overruns due to too many
+ * allocation operations in a transaction. AGFL frees are prone to this problem
+ * because for one they are always freed one at a time. Further, an immediate
+ * AGFL block free can cause a btree join and require another block free before
+ * the real allocation can proceed. Deferring the free disconnects freeing up
+ * the AGFL slot from freeing the block.
+ */
+STATIC void
+xfs_defer_agfl_block(
+	struct xfs_mount		*mp,
+	struct xfs_defer_ops		*dfops,
+	xfs_agnumber_t			agno,
+	xfs_fsblock_t			agbno,
+	struct xfs_owner_info		*oinfo)
+{
+	struct xfs_extent_free_item	*new;		/* new element */
+
+	ASSERT(xfs_bmap_free_item_zone != NULL);
+	ASSERT(oinfo != NULL);
+
+	new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
+	new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
+	new->xefi_blockcount = 1;
+	new->xefi_oinfo = *oinfo;
+
+	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
+
+	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
+}
+
+/*
  * Decide whether to use this allocation group for this allocation.
  * If so, fix up the btree freelist's size.
  */
@@ -2247,21 +2308,20 @@ xfs_alloc_fix_freelist(
 	else
 		xfs_rmap_ag_owner(&targs.oinfo, XFS_RMAP_OWN_AG);
 	while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) {
-		struct xfs_buf	*bp;
-
 		error = xfs_alloc_get_freelist(tp, agbp, &bno, 0);
 		if (error)
 			goto out_agbp_relse;
-		error = xfs_free_ag_extent(tp, agbp, args->agno, bno, 1,
-					   &targs.oinfo, XFS_AG_RESV_AGFL);
-		if (error)
-			goto out_agbp_relse;
-		bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0);
-		if (!bp) {
-			error = -EFSCORRUPTED;
-			goto out_agbp_relse;
+
+		/* defer agfl frees if dfops is provided */
+		if (tp->t_agfl_dfops) {
+			xfs_defer_agfl_block(mp, tp->t_agfl_dfops, args->agno,
+					     bno, &targs.oinfo);
+		} else {
+			error = xfs_free_agfl_block(tp, args->agno, bno, agbp,
+						    &targs.oinfo);
+			if (error)
+				goto out_agbp_relse;
 		}
-		xfs_trans_binval(tp, bp);
 	}
 
 	targs.tp = tp;
@@ -2949,18 +3009,20 @@ out:
  * after fixing up the freelist.
  */
 int				/* error */
-xfs_free_extent(
+__xfs_free_extent(
 	struct xfs_trans	*tp,	/* transaction pointer */
 	xfs_fsblock_t		bno,	/* starting block number of extent */
 	xfs_extlen_t		len,	/* length of extent */
 	struct xfs_owner_info	*oinfo,	/* extent owner */
-	enum xfs_ag_resv_type	type)	/* block reservation type */
+	enum xfs_ag_resv_type	type,	/* block reservation type */
+	bool			skip_discard)
 {
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*agbp;
 	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, bno);
 	xfs_agblock_t		agbno = XFS_FSB_TO_AGBNO(mp, bno);
 	int			error;
+	unsigned int		busy_flags = 0;
 
 	ASSERT(len != 0);
 	ASSERT(type != XFS_AG_RESV_AGFL);
@@ -2984,7 +3046,9 @@ xfs_free_extent(
 	if (error)
 		goto err;
 
-	xfs_extent_busy_insert(tp, agno, agbno, len, 0);
+	if (skip_discard)
+		busy_flags |= XFS_EXTENT_BUSY_SKIP_DISCARD;
+	xfs_extent_busy_insert(tp, agno, agbno, len, busy_flags);
 	return 0;
 
 err:
@@ -3116,3 +3180,40 @@ xfs_alloc_has_record(
 
 	return xfs_btree_has_record(cur, &low, &high, exists);
 }
+
+/*
+ * Walk all the blocks in the AGFL.  The @walk_fn can return any negative
+ * error code or XFS_BTREE_QUERY_RANGE_ABORT.
+ */
+int
+xfs_agfl_walk(
+	struct xfs_mount	*mp,
+	struct xfs_agf		*agf,
+	struct xfs_buf		*agflbp,
+	xfs_agfl_walk_fn	walk_fn,
+	void			*priv)
+{
+	__be32			*agfl_bno;
+	unsigned int		i;
+	int			error;
+
+	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agflbp);
+	i = be32_to_cpu(agf->agf_flfirst);
+
+	/* Nothing to walk in an empty AGFL. */
+	if (agf->agf_flcount == cpu_to_be32(0))
+		return 0;
+
+	/* Otherwise, walk from first to last, wrapping as needed. */
+	for (;;) {
+		error = walk_fn(mp, be32_to_cpu(agfl_bno[i]), priv);
+		if (error)
+			return error;
+		if (i == be32_to_cpu(agf->agf_fllast))
+			break;
+		if (++i == xfs_agfl_size(mp))
+			i = 0;
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index cbf789ea5a4e..0747adcd57d6 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -191,12 +191,24 @@ xfs_alloc_vextent(
  * Free an extent.
  */
 int				/* error */
-xfs_free_extent(
+__xfs_free_extent(
 	struct xfs_trans	*tp,	/* transaction pointer */
 	xfs_fsblock_t		bno,	/* starting block number of extent */
 	xfs_extlen_t		len,	/* length of extent */
 	struct xfs_owner_info	*oinfo,	/* extent owner */
-	enum xfs_ag_resv_type	type);	/* block reservation type */
+	enum xfs_ag_resv_type	type,	/* block reservation type */
+	bool			skip_discard);
+
+static inline int
+xfs_free_extent(
+	struct xfs_trans	*tp,
+	xfs_fsblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type	type)
+{
+	return __xfs_free_extent(tp, bno, len, oinfo, type, false);
+}
 
 int				/* error */
 xfs_alloc_lookup_le(
@@ -223,6 +235,8 @@ int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
 int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, struct xfs_buf **bpp);
+int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t,
+			struct xfs_buf *, struct xfs_owner_info *);
 int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
 int xfs_free_extent_fix_freelist(struct xfs_trans *tp, xfs_agnumber_t agno,
 		struct xfs_buf **agbp);
@@ -248,4 +262,9 @@ bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno);
 int xfs_alloc_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, bool *exist);
 
+typedef int (*xfs_agfl_walk_fn)(struct xfs_mount *mp, xfs_agblock_t bno,
+		void *priv);
+int xfs_agfl_walk(struct xfs_mount *mp, struct xfs_agf *agf,
+		struct xfs_buf *agflbp, xfs_agfl_walk_fn walk_fn, void *priv);
+
 #endif	/* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index b451649ba176..18aec7a0e599 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -547,3 +547,12 @@ xfs_allocbt_maxrecs(
 		return blocklen / sizeof(xfs_alloc_rec_t);
 	return blocklen / (sizeof(xfs_alloc_key_t) + sizeof(xfs_alloc_ptr_t));
 }
+
+/* Calculate the freespace btree size for some records. */
+xfs_extlen_t
+xfs_allocbt_calc_size(
+	struct xfs_mount	*mp,
+	unsigned long long	len)
+{
+	return xfs_btree_calc_size(mp->m_alloc_mnr, len);
+}
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.h b/fs/xfs/libxfs/xfs_alloc_btree.h
index 45e189e7e81c..2fd54728871c 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.h
+++ b/fs/xfs/libxfs/xfs_alloc_btree.h
@@ -61,5 +61,7 @@ extern struct xfs_btree_cur *xfs_allocbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_buf *,
 		xfs_agnumber_t, xfs_btnum_t);
 extern int xfs_allocbt_maxrecs(struct xfs_mount *, int, int);
+extern xfs_extlen_t xfs_allocbt_calc_size(struct xfs_mount *mp,
+		unsigned long long len);
 
 #endif	/* __XFS_ALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index ce4a34a2751d..c3d02a66d39d 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -236,7 +236,7 @@ xfs_attr_set(
 	args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	args.total = xfs_attr_calc_size(&args, &local);
 
-	error = xfs_qm_dqattach(dp, 0);
+	error = xfs_qm_dqattach(dp);
 	if (error)
 		return error;
 
@@ -427,7 +427,7 @@ xfs_attr_remove(
 	 */
 	args.op_flags = XFS_DA_OP_OKNOENT;
 
-	error = xfs_qm_dqattach(dp, 0);
+	error = xfs_qm_dqattach(dp);
 	if (error)
 		return error;
 
@@ -511,7 +511,14 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
 		if (args->flags & ATTR_CREATE)
 			return retval;
 		retval = xfs_attr_shortform_remove(args);
-		ASSERT(retval == 0);
+		if (retval)
+			return retval;
+		/*
+		 * Since we have removed the old attr, clear ATTR_REPLACE so
+		 * that the leaf format add routine won't trip over the attr
+		 * not being around.
+		 */
+		args->flags &= ~ATTR_REPLACE;
 	}
 
 	if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 21be186067a2..83a6d3c7f872 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -620,7 +620,7 @@ xfs_attr_rmtval_remove(
 		/*
 		 * If the "remote" value is in the cache, remove it.
 		 */
-		bp = xfs_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
+		bp = xfs_buf_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
 		if (bp) {
 			xfs_buf_stale(bp);
 			xfs_buf_relse(bp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 6a7c2f03ea11..7b0e2b551e23 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -246,7 +246,7 @@ xfs_bmap_get_bp(
 	struct xfs_btree_cur	*cur,
 	xfs_fsblock_t		bno)
 {
-	struct xfs_log_item_desc *lidp;
+	struct xfs_log_item	*lip;
 	int			i;
 
 	if (!cur)
@@ -260,9 +260,9 @@ xfs_bmap_get_bp(
 	}
 
 	/* Chase down all the log items to see if the bp is there */
-	list_for_each_entry(lidp, &cur->bc_tp->t_items, lid_trans) {
-		struct xfs_buf_log_item	*bip;
-		bip = (struct xfs_buf_log_item *)lidp->lid_item;
+	list_for_each_entry(lip, &cur->bc_tp->t_items, li_trans) {
+		struct xfs_buf_log_item	*bip = (struct xfs_buf_log_item *)lip;
+
 		if (bip->bli_item.li_type == XFS_LI_BUF &&
 		    XFS_BUF_ADDR(bip->bli_buf) == bno)
 			return bip->bli_buf;
@@ -312,8 +312,9 @@ xfs_check_block(
 				xfs_warn(mp, "%s: thispa(%d) == pp(%d) %Ld",
 					__func__, j, i,
 					(unsigned long long)be64_to_cpu(*thispa));
-				panic("%s: ptrs are equal in node\n",
+				xfs_err(mp, "%s: ptrs are equal in node\n",
 					__func__);
+				xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 			}
 		}
 	}
@@ -483,7 +484,8 @@ error0:
 error_norelse:
 	xfs_warn(mp, "%s: BAD after btree leaves for %d extents",
 		__func__, i);
-	panic("%s: CORRUPTED BTREE OR SOMETHING", __func__);
+	xfs_err(mp, "%s: CORRUPTED BTREE OR SOMETHING", __func__);
+	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 	return;
 }
 
@@ -542,12 +544,13 @@ xfs_bmap_validate_ret(
  * The list is maintained sorted (by block number).
  */
 void
-xfs_bmap_add_free(
+__xfs_bmap_add_free(
 	struct xfs_mount		*mp,
 	struct xfs_defer_ops		*dfops,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
-	struct xfs_owner_info		*oinfo)
+	struct xfs_owner_info		*oinfo,
+	bool				skip_discard)
 {
 	struct xfs_extent_free_item	*new;		/* new element */
 #ifdef DEBUG
@@ -574,6 +577,7 @@ xfs_bmap_add_free(
 		new->xefi_oinfo = *oinfo;
 	else
 		xfs_rmap_skip_owner_update(&new->xefi_oinfo);
+	new->xefi_skip_discard = skip_discard;
 	trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0,
 			XFS_FSB_TO_AGBNO(mp, bno), len);
 	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
@@ -725,12 +729,16 @@ xfs_bmap_extents_to_btree(
 	*logflagsp = 0;
 	if ((error = xfs_alloc_vextent(&args))) {
 		xfs_iroot_realloc(ip, -1, whichfork);
+		ASSERT(ifp->if_broot == NULL);
+		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
 		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
 		return error;
 	}
 
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		xfs_iroot_realloc(ip, -1, whichfork);
+		ASSERT(ifp->if_broot == NULL);
+		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
 		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
 		return -ENOSPC;
 	}
@@ -1997,10 +2005,13 @@ xfs_bmap_add_extent_delay_real(
 		ASSERT(0);
 	}
 
-	/* add reverse mapping */
-	error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip, whichfork, new);
-	if (error)
-		goto done;
+	/* add reverse mapping unless caller opted out */
+	if (!(bma->flags & XFS_BMAPI_NORMAP)) {
+		error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip,
+				whichfork, new);
+		if (error)
+			goto done;
+	}
 
 	/* convert to a btree if necessary */
 	if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
@@ -2664,7 +2675,8 @@ xfs_bmap_add_extent_hole_real(
 	struct xfs_bmbt_irec	*new,
 	xfs_fsblock_t		*first,
 	struct xfs_defer_ops	*dfops,
-	int			*logflagsp)
+	int			*logflagsp,
+	int			flags)
 {
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -2841,10 +2853,12 @@ xfs_bmap_add_extent_hole_real(
 		break;
 	}
 
-	/* add reverse mapping */
-	error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new);
-	if (error)
-		goto done;
+	/* add reverse mapping unless caller opted out */
+	if (!(flags & XFS_BMAPI_NORMAP)) {
+		error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new);
+		if (error)
+			goto done;
+	}
 
 	/* convert to a btree if necessary */
 	if (xfs_bmap_needs_btree(ip, whichfork)) {
@@ -4119,7 +4133,8 @@ xfs_bmapi_allocate(
 	else
 		error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
 				whichfork, &bma->icur, &bma->cur, &bma->got,
-				bma->firstblock, bma->dfops, &bma->logflags);
+				bma->firstblock, bma->dfops, &bma->logflags,
+				bma->flags);
 
 	bma->logflags |= tmp_logflags;
 	if (error)
@@ -4505,30 +4520,37 @@ error0:
 	return error;
 }
 
-static int
+int
 xfs_bmapi_remap(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		bno,
 	xfs_filblks_t		len,
 	xfs_fsblock_t		startblock,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_defer_ops	*dfops,
+	int			flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	struct xfs_ifork	*ifp;
 	struct xfs_btree_cur	*cur = NULL;
 	xfs_fsblock_t		firstblock = NULLFSBLOCK;
 	struct xfs_bmbt_irec	got;
 	struct xfs_iext_cursor	icur;
+	int			whichfork = xfs_bmapi_whichfork(flags);
 	int			logflags = 0, error;
 
+	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT(len > 0);
 	ASSERT(len <= (xfs_filblks_t)MAXEXTLEN);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC |
+			   XFS_BMAPI_NORMAP)));
+	ASSERT((flags & (XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC)) !=
+			(XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC));
 
 	if (unlikely(XFS_TEST_ERROR(
-	    (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
-	     XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
+	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
+	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
 	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmapi_remap", XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
@@ -4538,7 +4560,7 @@ xfs_bmapi_remap(
 		return -EIO;
 
 	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+		error = xfs_iread_extents(tp, ip, whichfork);
 		if (error)
 			return error;
 	}
@@ -4553,7 +4575,7 @@ xfs_bmapi_remap(
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	if (ifp->if_flags & XFS_IFBROOT) {
-		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
+		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = firstblock;
 		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
@@ -4562,18 +4584,21 @@ xfs_bmapi_remap(
 	got.br_startoff = bno;
 	got.br_startblock = startblock;
 	got.br_blockcount = len;
-	got.br_state = XFS_EXT_NORM;
+	if (flags & XFS_BMAPI_PREALLOC)
+		got.br_state = XFS_EXT_UNWRITTEN;
+	else
+		got.br_state = XFS_EXT_NORM;
 
-	error = xfs_bmap_add_extent_hole_real(tp, ip, XFS_DATA_FORK, &icur,
-			&cur, &got, &firstblock, dfops, &logflags);
+	error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur,
+			&cur, &got, &firstblock, dfops, &logflags, flags);
 	if (error)
 		goto error0;
 
-	if (xfs_bmap_wants_extents(ip, XFS_DATA_FORK)) {
+	if (xfs_bmap_wants_extents(ip, whichfork)) {
 		int		tmp_logflags = 0;
 
 		error = xfs_bmap_btree_to_extents(tp, ip, cur,
-			&tmp_logflags, XFS_DATA_FORK);
+			&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 	}
 
@@ -5100,9 +5125,12 @@ xfs_bmap_del_extent_real(
 			error = xfs_refcount_decrease_extent(mp, dfops, del);
 			if (error)
 				goto done;
-		} else
-			xfs_bmap_add_free(mp, dfops, del->br_startblock,
-					del->br_blockcount, NULL);
+		} else {
+			__xfs_bmap_add_free(mp, dfops, del->br_startblock,
+					del->br_blockcount, NULL,
+					(bflags & XFS_BMAPI_NODISCARD) ||
+					del->br_state == XFS_EXT_UNWRITTEN);
+		}
 	}
 
 	/*
@@ -6144,7 +6172,7 @@ xfs_bmap_finish_one(
 	switch (type) {
 	case XFS_BMAP_MAP:
 		error = xfs_bmapi_remap(tp, ip, startoff, *blockcount,
-				startblock, dfops);
+				startblock, dfops, 0);
 		*blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 2b766b37096d..2c233f9f1a26 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -68,6 +68,7 @@ struct xfs_extent_free_item
 	xfs_extlen_t		xefi_blockcount;/* number of blocks in extent */
 	struct list_head	xefi_list;
 	struct xfs_owner_info	xefi_oinfo;	/* extent owner */
+	bool			xefi_skip_discard;
 };
 
 #define	XFS_BMAP_MAX_NMAP	4
@@ -116,6 +117,12 @@ struct xfs_extent_free_item
 /* Only convert unwritten extents, don't allocate new blocks */
 #define XFS_BMAPI_CONVERT_ONLY	0x800
 
+/* Skip online discard of freed extents */
+#define XFS_BMAPI_NODISCARD	0x1000
+
+/* Do not update the rmap btree.  Used for reconstructing bmbt from rmapbt. */
+#define XFS_BMAPI_NORMAP	0x2000
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
@@ -128,7 +135,9 @@ struct xfs_extent_free_item
 	{ XFS_BMAPI_REMAP,	"REMAP" }, \
 	{ XFS_BMAPI_COWFORK,	"COWFORK" }, \
 	{ XFS_BMAPI_DELALLOC,	"DELALLOC" }, \
-	{ XFS_BMAPI_CONVERT_ONLY, "CONVERT_ONLY" }
+	{ XFS_BMAPI_CONVERT_ONLY, "CONVERT_ONLY" }, \
+	{ XFS_BMAPI_NODISCARD,	"NODISCARD" }, \
+	{ XFS_BMAPI_NORMAP,	"NORMAP" }
 
 
 static inline int xfs_bmapi_aflag(int w)
@@ -192,9 +201,9 @@ void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 void	xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
-void	xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
+void	__xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 			  xfs_fsblock_t bno, xfs_filblks_t len,
-			  struct xfs_owner_info *oinfo);
+			  struct xfs_owner_info *oinfo, bool skip_discard);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
@@ -240,6 +249,17 @@ int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur,
 		int eof);
 
+static inline void
+xfs_bmap_add_free(
+	struct xfs_mount		*mp,
+	struct xfs_defer_ops		*dfops,
+	xfs_fsblock_t			bno,
+	xfs_filblks_t			len,
+	struct xfs_owner_info		*oinfo)
+{
+	__xfs_bmap_add_free(mp, dfops, bno, len, oinfo, false);
+}
+
 enum xfs_bmap_intent_type {
 	XFS_BMAP_MAP = 1,
 	XFS_BMAP_UNMAP,
@@ -277,4 +297,8 @@ static inline int xfs_bmap_fork_to_state(int whichfork)
 xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *irec);
 
+int	xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
+		xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
+		struct xfs_defer_ops *dfops, int flags);
+
 #endif	/* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index d89d06bea6e3..ac9d4aeedb09 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -660,3 +660,12 @@ xfs_bmbt_change_owner(
 	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
 	return error;
 }
+
+/* Calculate the bmap btree size for some records. */
+unsigned long long
+xfs_bmbt_calc_size(
+	struct xfs_mount	*mp,
+	unsigned long long	len)
+{
+	return xfs_btree_calc_size(mp->m_bmap_dmnr, len);
+}
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index e4505746ccaa..fb3cd2d9e0f8 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -118,4 +118,7 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
 
+extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
+		unsigned long long len);
+
 #endif	/* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index ac7d66427e42..c825c8182b30 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4836,14 +4836,14 @@ xfs_btree_query_all(
  * Calculate the number of blocks needed to store a given number of records
  * in a short-format (per-AG metadata) btree.
  */
-xfs_extlen_t
+unsigned long long
 xfs_btree_calc_size(
 	uint			*limits,
 	unsigned long long	len)
 {
 	int			level;
 	int			maxrecs;
-	xfs_extlen_t		rval;
+	unsigned long long	rval;
 
 	maxrecs = limits[0];
 	for (level = 0, rval = 0; len > 1; level++) {
@@ -4919,3 +4919,24 @@ xfs_btree_has_record(
 	*exists = false;
 	return error;
 }
+
+/* Are there more records in this btree? */
+bool
+xfs_btree_has_more_records(
+	struct xfs_btree_cur	*cur)
+{
+	struct xfs_btree_block	*block;
+	struct xfs_buf		*bp;
+
+	block = xfs_btree_get_block(cur, 0, &bp);
+
+	/* There are still records in this block. */
+	if (cur->bc_ptrs[0] < xfs_btree_get_numrecs(block))
+		return true;
+
+	/* There are more record blocks. */
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		return block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK);
+	else
+		return block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK);
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 9227159a751e..d7911efee6dc 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -482,7 +482,7 @@ xfs_failaddr_t xfs_btree_lblock_verify(struct xfs_buf *bp,
 		unsigned int max_recs);
 
 uint xfs_btree_compute_maxlevels(uint *limits, unsigned long len);
-xfs_extlen_t xfs_btree_calc_size(uint *limits, unsigned long long len);
+unsigned long long xfs_btree_calc_size(uint *limits, unsigned long long len);
 
 /* return codes */
 #define XFS_BTREE_QUERY_RANGE_CONTINUE	0	/* keep iterating */
@@ -528,5 +528,6 @@ union xfs_btree_key *xfs_btree_high_key_from_key(struct xfs_btree_cur *cur,
 		union xfs_btree_key *key);
 int xfs_btree_has_record(struct xfs_btree_cur *cur, union xfs_btree_irec *low,
 		union xfs_btree_irec *high, bool *exists);
+bool xfs_btree_has_more_records(struct xfs_btree_cur *cur);
 
 #endif	/* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 087fea02c389..3daf175e2535 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -220,7 +220,7 @@ xfs_defer_trans_abort(
 {
 	struct xfs_defer_pending	*dfp;
 
-	trace_xfs_defer_trans_abort(tp->t_mountp, dop);
+	trace_xfs_defer_trans_abort(tp->t_mountp, dop, _RET_IP_);
 
 	/* Abort intent items that don't have a done item. */
 	list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
@@ -253,7 +253,7 @@ xfs_defer_trans_roll(
 	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++)
 		xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]);
 
-	trace_xfs_defer_trans_roll((*tp)->t_mountp, dop);
+	trace_xfs_defer_trans_roll((*tp)->t_mountp, dop, _RET_IP_);
 
 	/* Roll the transaction. */
 	error = xfs_trans_roll(tp);
@@ -352,10 +352,21 @@ xfs_defer_finish(
 	void				*state;
 	int				error = 0;
 	void				(*cleanup_fn)(struct xfs_trans *, void *, int);
+	struct xfs_defer_ops		*orig_dop;
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
-	trace_xfs_defer_finish((*tp)->t_mountp, dop);
+	trace_xfs_defer_finish((*tp)->t_mountp, dop, _RET_IP_);
+
+	/*
+	 * Attach dfops to the transaction during deferred ops processing. This
+	 * explicitly causes calls into the allocator to defer AGFL block frees.
+	 * Note that this code can go away once all dfops users attach to the
+	 * associated tp.
+	 */
+	ASSERT(!(*tp)->t_agfl_dfops || ((*tp)->t_agfl_dfops == dop));
+	orig_dop = (*tp)->t_agfl_dfops;
+	(*tp)->t_agfl_dfops = dop;
 
 	/* Until we run out of pending work to finish... */
 	while (xfs_defer_has_unfinished_work(dop)) {
@@ -428,10 +439,11 @@ xfs_defer_finish(
 	}
 
 out:
+	(*tp)->t_agfl_dfops = orig_dop;
 	if (error)
 		trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
 	else
-		trace_xfs_defer_finish_done((*tp)->t_mountp, dop);
+		trace_xfs_defer_finish_done((*tp)->t_mountp, dop, _RET_IP_);
 	return error;
 }
 
@@ -447,7 +459,7 @@ xfs_defer_cancel(
 	struct list_head		*pwi;
 	struct list_head		*n;
 
-	trace_xfs_defer_cancel(NULL, dop);
+	trace_xfs_defer_cancel(NULL, dop, _RET_IP_);
 
 	/*
 	 * Free the pending items.  Caller should already have arranged
@@ -532,5 +544,5 @@ xfs_defer_init(
 	*fbp = NULLFSBLOCK;
 	INIT_LIST_HEAD(&dop->dop_intake);
 	INIT_LIST_HEAD(&dop->dop_pending);
-	trace_xfs_defer_init(NULL, dop);
+	trace_xfs_defer_init(NULL, dop, _RET_IP_);
 }
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 045beacdd37d..e70725ba1f5f 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -55,6 +55,7 @@ enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_REFCOUNT,
 	XFS_DEFER_OPS_TYPE_RMAP,
 	XFS_DEFER_OPS_TYPE_FREE,
+	XFS_DEFER_OPS_TYPE_AGFL_FREE,
 	XFS_DEFER_OPS_TYPE_MAX,
 };
 
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 8b7a6c3cb599..cce520becee4 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -41,14 +41,18 @@ xfs_calc_dquots_per_chunk(
 
 /*
  * Do some primitive error checking on ondisk dquot data structures.
+ *
+ * The xfs_dqblk structure /contains/ the xfs_disk_dquot structure;
+ * we verify them separately because at some points we have only the
+ * smaller xfs_disk_dquot structure available.
  */
+
 xfs_failaddr_t
 xfs_dquot_verify(
 	struct xfs_mount *mp,
 	xfs_disk_dquot_t *ddq,
 	xfs_dqid_t	 id,
-	uint		 type,	  /* used only when IO_dorepair is true */
-	uint		 flags)
+	uint		 type)	  /* used only during quotacheck */
 {
 	/*
 	 * We can encounter an uninitialized dquot buffer for 2 reasons:
@@ -70,6 +74,8 @@ xfs_dquot_verify(
 	if (ddq->d_version != XFS_DQUOT_VERSION)
 		return __this_address;
 
+	if (type && ddq->d_flags != type)
+		return __this_address;
 	if (ddq->d_flags != XFS_DQ_USER &&
 	    ddq->d_flags != XFS_DQ_PROJ &&
 	    ddq->d_flags != XFS_DQ_GROUP)
@@ -99,33 +105,44 @@ xfs_dquot_verify(
 	return NULL;
 }
 
+xfs_failaddr_t
+xfs_dqblk_verify(
+	struct xfs_mount	*mp,
+	struct xfs_dqblk	*dqb,
+	xfs_dqid_t	 	id,
+	uint		 	type)	/* used only during quotacheck */
+{
+	if (xfs_sb_version_hascrc(&mp->m_sb) &&
+	    !uuid_equal(&dqb->dd_uuid, &mp->m_sb.sb_meta_uuid))
+		return __this_address;
+
+	return xfs_dquot_verify(mp, &dqb->dd_diskdq, id, type);
+}
+
 /*
  * Do some primitive error checking on ondisk dquot data structures.
  */
 int
-xfs_dquot_repair(
+xfs_dqblk_repair(
 	struct xfs_mount	*mp,
-	struct xfs_disk_dquot	*ddq,
+	struct xfs_dqblk	*dqb,
 	xfs_dqid_t		id,
 	uint			type)
 {
-	struct xfs_dqblk	*d = (struct xfs_dqblk *)ddq;
-
-
 	/*
 	 * Typically, a repair is only requested by quotacheck.
 	 */
 	ASSERT(id != -1);
-	memset(d, 0, sizeof(xfs_dqblk_t));
+	memset(dqb, 0, sizeof(xfs_dqblk_t));
 
-	d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
-	d->dd_diskdq.d_version = XFS_DQUOT_VERSION;
-	d->dd_diskdq.d_flags = type;
-	d->dd_diskdq.d_id = cpu_to_be32(id);
+	dqb->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
+	dqb->dd_diskdq.d_version = XFS_DQUOT_VERSION;
+	dqb->dd_diskdq.d_flags = type;
+	dqb->dd_diskdq.d_id = cpu_to_be32(id);
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
-		uuid_copy(&d->dd_uuid, &mp->m_sb.sb_meta_uuid);
-		xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk),
+		uuid_copy(&dqb->dd_uuid, &mp->m_sb.sb_meta_uuid);
+		xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
 				 XFS_DQUOT_CRC_OFF);
 	}
 
@@ -135,7 +152,8 @@ xfs_dquot_repair(
 STATIC bool
 xfs_dquot_buf_verify_crc(
 	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	bool			readahead)
 {
 	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
 	int			ndquots;
@@ -156,10 +174,12 @@ xfs_dquot_buf_verify_crc(
 
 	for (i = 0; i < ndquots; i++, d++) {
 		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
-				 XFS_DQUOT_CRC_OFF))
-			return false;
-		if (!uuid_equal(&d->dd_uuid, &mp->m_sb.sb_meta_uuid))
+				 XFS_DQUOT_CRC_OFF)) {
+			if (!readahead)
+				xfs_buf_verifier_error(bp, -EFSBADCRC, __func__,
+					d, sizeof(*d), __this_address);
 			return false;
+		}
 	}
 	return true;
 }
@@ -167,9 +187,10 @@ xfs_dquot_buf_verify_crc(
 STATIC xfs_failaddr_t
 xfs_dquot_buf_verify(
 	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	bool			readahead)
 {
-	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
+	struct xfs_dqblk	*dqb = bp->b_addr;
 	xfs_failaddr_t		fa;
 	xfs_dqid_t		id = 0;
 	int			ndquots;
@@ -195,14 +216,19 @@ xfs_dquot_buf_verify(
 	for (i = 0; i < ndquots; i++) {
 		struct xfs_disk_dquot	*ddq;
 
-		ddq = &d[i].dd_diskdq;
+		ddq = &dqb[i].dd_diskdq;
 
 		if (i == 0)
 			id = be32_to_cpu(ddq->d_id);
 
-		fa = xfs_dquot_verify(mp, ddq, id + i, 0, 0);
-		if (fa)
+		fa = xfs_dqblk_verify(mp, &dqb[i], id + i, 0);
+		if (fa) {
+			if (!readahead)
+				xfs_buf_verifier_error(bp, -EFSCORRUPTED,
+					__func__, &dqb[i],
+					sizeof(struct xfs_dqblk), fa);
 			return fa;
+		}
 	}
 
 	return NULL;
@@ -214,7 +240,7 @@ xfs_dquot_buf_verify_struct(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 
-	return xfs_dquot_buf_verify(mp, bp);
+	return xfs_dquot_buf_verify(mp, bp, false);
 }
 
 static void
@@ -222,15 +248,10 @@ xfs_dquot_buf_read_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
-	xfs_failaddr_t		fa;
 
-	if (!xfs_dquot_buf_verify_crc(mp, bp))
-		xfs_verifier_error(bp, -EFSBADCRC, __this_address);
-	else {
-		fa = xfs_dquot_buf_verify(mp, bp);
-		if (fa)
-			xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
-	}
+	if (!xfs_dquot_buf_verify_crc(mp, bp, false))
+		return;
+	xfs_dquot_buf_verify(mp, bp, false);
 }
 
 /*
@@ -245,8 +266,8 @@ xfs_dquot_buf_readahead_verify(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 
-	if (!xfs_dquot_buf_verify_crc(mp, bp) ||
-	    xfs_dquot_buf_verify(mp, bp) != NULL) {
+	if (!xfs_dquot_buf_verify_crc(mp, bp, true) ||
+	    xfs_dquot_buf_verify(mp, bp, true) != NULL) {
 		xfs_buf_ioerror(bp, -EIO);
 		bp->b_flags &= ~XBF_DONE;
 	}
@@ -262,11 +283,8 @@ xfs_dquot_buf_write_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
-	xfs_failaddr_t		fa;
 
-	fa = xfs_dquot_buf_verify(mp, bp);
-	if (fa)
-		xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
+	xfs_dquot_buf_verify(mp, bp, false);
 }
 
 const struct xfs_buf_ops xfs_dquot_buf_ops = {
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index bc1789d95152..d47b91625945 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -65,7 +65,8 @@
 #define XFS_ERRTAG_LOG_BAD_CRC				29
 #define XFS_ERRTAG_LOG_ITEM_PIN				30
 #define XFS_ERRTAG_BUF_LRU_REF				31
-#define XFS_ERRTAG_MAX					32
+#define XFS_ERRTAG_FORCE_SCRUB_REPAIR			32
+#define XFS_ERRTAG_MAX					33
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -102,5 +103,6 @@
 #define XFS_RANDOM_LOG_BAD_CRC				1
 #define XFS_RANDOM_LOG_ITEM_PIN				1
 #define XFS_RANDOM_BUF_LRU_REF				2
+#define XFS_RANDOM_FORCE_SCRUB_REPAIR			1
 
 #endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 42956d8d95ed..c1cb29a5f4f6 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -98,6 +98,9 @@ struct xfs_ifork;
 	 XFS_SB_VERSION2_PROJID32BIT	| \
 	 XFS_SB_VERSION2_FTYPE)
 
+/* Maximum size of the xfs filesystem label, no terminating NULL */
+#define XFSLABEL_MAX			12
+
 /*
  * Superblock - in core version.  Must match the ondisk version below.
  * Must be padded to 64 bit alignment.
@@ -122,7 +125,7 @@ typedef struct xfs_sb {
 	uint16_t	sb_sectsize;	/* volume sector size, bytes */
 	uint16_t	sb_inodesize;	/* inode size, bytes */
 	uint16_t	sb_inopblock;	/* inodes per block */
-	char		sb_fname[12];	/* file system name */
+	char		sb_fname[XFSLABEL_MAX]; /* file system name */
 	uint8_t		sb_blocklog;	/* log2 of sb_blocksize */
 	uint8_t		sb_sectlog;	/* log2 of sb_sectsize */
 	uint8_t		sb_inodelog;	/* log2 of sb_inodesize */
@@ -213,7 +216,7 @@ typedef struct xfs_dsb {
 	__be16		sb_sectsize;	/* volume sector size, bytes */
 	__be16		sb_inodesize;	/* inode size, bytes */
 	__be16		sb_inopblock;	/* inodes per block */
-	char		sb_fname[12];	/* file system name */
+	char		sb_fname[XFSLABEL_MAX]; /* file system name */
 	__u8		sb_blocklog;	/* log2 of sb_blocksize */
 	__u8		sb_sectlog;	/* log2 of sb_sectsize */
 	__u8		sb_inodelog;	/* log2 of sb_inodesize */
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index faf1a4edd618..dddc75e4f1f6 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -542,13 +542,20 @@ struct xfs_scrub_metadata {
 /* o: Metadata object looked funny but isn't corrupt. */
 #define XFS_SCRUB_OFLAG_WARNING		(1 << 6)
 
+/*
+ * o: IFLAG_REPAIR was set but metadata object did not need fixing or
+ *    optimization and has therefore not been altered.
+ */
+#define XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED (1 << 7)
+
 #define XFS_SCRUB_FLAGS_IN	(XFS_SCRUB_IFLAG_REPAIR)
 #define XFS_SCRUB_FLAGS_OUT	(XFS_SCRUB_OFLAG_CORRUPT | \
 				 XFS_SCRUB_OFLAG_PREEN | \
 				 XFS_SCRUB_OFLAG_XFAIL | \
 				 XFS_SCRUB_OFLAG_XCORRUPT | \
 				 XFS_SCRUB_OFLAG_INCOMPLETE | \
-				 XFS_SCRUB_OFLAG_WARNING)
+				 XFS_SCRUB_OFLAG_WARNING | \
+				 XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED)
 #define XFS_SCRUB_FLAGS_ALL	(XFS_SCRUB_FLAGS_IN | XFS_SCRUB_FLAGS_OUT)
 
 /*
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index de627fa19168..4ca4ff7a757d 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -148,7 +148,7 @@ xfs_inobt_get_rec(
 /*
  * Insert a single inobt record. Cursor must already point to desired location.
  */
-STATIC int
+int
 xfs_inobt_insert_rec(
 	struct xfs_btree_cur	*cur,
 	uint16_t		holemask,
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index c5402bb4ce0c..77fffced8bac 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -176,6 +176,9 @@ int xfs_ialloc_has_inode_record(struct xfs_btree_cur *cur, xfs_agino_t low,
 		xfs_agino_t high, bool *exists);
 int xfs_ialloc_count_inodes(struct xfs_btree_cur *cur, xfs_agino_t *count,
 		xfs_agino_t *freecount);
+int xfs_inobt_insert_rec(struct xfs_btree_cur *cur, uint16_t holemask,
+		uint8_t count, int32_t freecount, xfs_inofree_t free,
+		int *stat);
 
 int xfs_ialloc_cluster_alignment(struct xfs_mount *mp);
 void xfs_ialloc_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 367e9a0726e6..b04c55512159 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -296,7 +296,7 @@ xfs_inobt_verify(
 	case cpu_to_be32(XFS_FIBT_MAGIC):
 		break;
 	default:
-		return NULL;
+		return __this_address;
 	}
 
 	/* level verification */
@@ -608,3 +608,12 @@ xfs_finobt_calc_reserves(
 	*used += tree_len;
 	return 0;
 }
+
+/* Calculate the inobt btree size for some records. */
+xfs_extlen_t
+xfs_iallocbt_calc_size(
+	struct xfs_mount	*mp,
+	unsigned long long	len)
+{
+	return xfs_btree_calc_size(mp->m_inobt_mnr, len);
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index aa81e2e63f3f..4acdd5458d59 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -74,5 +74,7 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
 
 int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
 		xfs_extlen_t *ask, xfs_extlen_t *used);
+extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp,
+		unsigned long long len);
 
 #endif	/* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index ef68b1de006a..1201107eabc6 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -466,6 +466,8 @@ xfs_dinode_verify(
 				return __this_address;
 			if (di_size > XFS_DFORK_DSIZE(dip, mp))
 				return __this_address;
+			if (dip->di_nextents)
+				return __this_address;
 			/* fall through */
 		case XFS_DINODE_FMT_EXTENTS:
 		case XFS_DINODE_FMT_BTREE:
@@ -484,12 +486,31 @@ xfs_dinode_verify(
 	if (XFS_DFORK_Q(dip)) {
 		switch (dip->di_aformat) {
 		case XFS_DINODE_FMT_LOCAL:
+			if (dip->di_anextents)
+				return __this_address;
+		/* fall through */
 		case XFS_DINODE_FMT_EXTENTS:
 		case XFS_DINODE_FMT_BTREE:
 			break;
 		default:
 			return __this_address;
 		}
+	} else {
+		/*
+		 * If there is no fork offset, this may be a freshly-made inode
+		 * in a new disk cluster, in which case di_aformat is zeroed.
+		 * Otherwise, such an inode must be in EXTENTS format; this goes
+		 * for freed inodes as well.
+		 */
+		switch (dip->di_aformat) {
+		case 0:
+		case XFS_DINODE_FMT_EXTENTS:
+			break;
+		default:
+			return __this_address;
+		}
+		if (dip->di_anextents)
+			return __this_address;
 	}
 
 	/* only version 3 or greater inodes are extensively verified here */
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index bb1b13a9b5f4..d4af2804b178 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -107,14 +107,12 @@ typedef uint16_t	xfs_qwarncnt_t;
  * to a single function. None of these XFS_QMOPT_* flags are meant to have
  * persistent values (ie. their values can and will change between versions)
  */
-#define XFS_QMOPT_DQALLOC	0x0000002 /* alloc dquot ondisk if needed */
 #define XFS_QMOPT_UQUOTA	0x0000004 /* user dquot requested */
 #define XFS_QMOPT_PQUOTA	0x0000008 /* project dquot requested */
 #define XFS_QMOPT_FORCE_RES	0x0000010 /* ignore quota limits */
 #define XFS_QMOPT_SBVERSION	0x0000040 /* change superblock version num */
 #define XFS_QMOPT_GQUOTA	0x0002000 /* group dquot requested */
 #define XFS_QMOPT_ENOSPC	0x0004000 /* enospc instead of edquot (prj) */
-#define XFS_QMOPT_DQNEXT	0x0008000 /* return next dquot >= this ID */
 
 /*
  * flags to xfs_trans_mod_dquot to indicate which field needs to be
@@ -152,10 +150,11 @@ typedef uint16_t	xfs_qwarncnt_t;
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
 extern xfs_failaddr_t xfs_dquot_verify(struct xfs_mount *mp,
-		struct xfs_disk_dquot *ddq, xfs_dqid_t id, uint type,
-		uint flags);
+		struct xfs_disk_dquot *ddq, xfs_dqid_t id, uint type);
+extern xfs_failaddr_t xfs_dqblk_verify(struct xfs_mount *mp,
+		struct xfs_dqblk *dqb, xfs_dqid_t id, uint type);
 extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
-extern int xfs_dquot_repair(struct xfs_mount *mp, struct xfs_disk_dquot *ddq,
+extern int xfs_dqblk_repair(struct xfs_mount *mp, struct xfs_dqblk *dqb,
 		xfs_dqid_t id, uint type);
 
 #endif	/* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 560e28473024..418d53295893 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -88,8 +88,25 @@ xfs_refcount_lookup_ge(
 	return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
 }
 
+/*
+ * Look up the first record equal to [bno, len] in the btree
+ * given by cur.
+ */
+int
+xfs_refcount_lookup_eq(
+	struct xfs_btree_cur	*cur,
+	xfs_agblock_t		bno,
+	int			*stat)
+{
+	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_private.a.agno, bno,
+			XFS_LOOKUP_LE);
+	cur->bc_rec.rc.rc_startblock = bno;
+	cur->bc_rec.rc.rc_blockcount = 0;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
+}
+
 /* Convert on-disk record to in-core format. */
-static inline void
+void
 xfs_refcount_btrec_to_irec(
 	union xfs_btree_rec		*rec,
 	struct xfs_refcount_irec	*irec)
@@ -149,7 +166,7 @@ xfs_refcount_update(
  * by [bno, len, refcount].
  * This either works (return 0) or gets an EFSCORRUPTED error.
  */
-STATIC int
+int
 xfs_refcount_insert(
 	struct xfs_btree_cur		*cur,
 	struct xfs_refcount_irec	*irec,
@@ -162,7 +179,10 @@ xfs_refcount_insert(
 	cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount;
 	cur->bc_rec.rc.rc_refcount = irec->rc_refcount;
 	error = xfs_btree_insert(cur, i);
+	if (error)
+		goto out_error;
 	XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, *i == 1, out_error);
+
 out_error:
 	if (error)
 		trace_xfs_refcount_insert_error(cur->bc_mp,
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 2a731ac68fe4..a92ad9078bc1 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -24,6 +24,8 @@ extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur,
 		xfs_agblock_t bno, int *stat);
 extern int xfs_refcount_lookup_ge(struct xfs_btree_cur *cur,
 		xfs_agblock_t bno, int *stat);
+extern int xfs_refcount_lookup_eq(struct xfs_btree_cur *cur,
+		xfs_agblock_t bno, int *stat);
 extern int xfs_refcount_get_rec(struct xfs_btree_cur *cur,
 		struct xfs_refcount_irec *irec, int *stat);
 
@@ -85,5 +87,10 @@ static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
 
 extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
 		xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
+union xfs_btree_rec;
+extern void xfs_refcount_btrec_to_irec(union xfs_btree_rec *rec,
+		struct xfs_refcount_irec *irec);
+extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
+		struct xfs_refcount_irec *irec, int *stat);
 
 #endif	/* __XFS_REFCOUNT_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index fba8d2718017..c0644f1be8a8 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -1374,6 +1374,8 @@ xfs_rmap_convert_shared(
 	 */
 	error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags,
 			&PREV, &i);
+	if (error)
+		goto done;
 	XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
 
 	ASSERT(PREV.rm_offset <= offset);
@@ -2030,6 +2032,34 @@ out_error:
 	return error;
 }
 
+/* Insert a raw rmap into the rmapbt. */
+int
+xfs_rmap_map_raw(
+	struct xfs_btree_cur	*cur,
+	struct xfs_rmap_irec	*rmap)
+{
+	struct xfs_owner_info	oinfo;
+
+	oinfo.oi_owner = rmap->rm_owner;
+	oinfo.oi_offset = rmap->rm_offset;
+	oinfo.oi_flags = 0;
+	if (rmap->rm_flags & XFS_RMAP_ATTR_FORK)
+		oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
+	if (rmap->rm_flags & XFS_RMAP_BMBT_BLOCK)
+		oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
+
+	if (rmap->rm_flags || XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+		return xfs_rmap_map(cur, rmap->rm_startblock,
+				rmap->rm_blockcount,
+				rmap->rm_flags & XFS_RMAP_UNWRITTEN,
+				&oinfo);
+
+	return xfs_rmap_map_shared(cur, rmap->rm_startblock,
+			rmap->rm_blockcount,
+			rmap->rm_flags & XFS_RMAP_UNWRITTEN,
+			&oinfo);
+}
+
 struct xfs_rmap_query_range_info {
 	xfs_rmap_query_range_fn	fn;
 	void				*priv;
@@ -2453,3 +2483,56 @@ xfs_rmap_record_exists(
 		     irec.rm_startblock + irec.rm_blockcount >= bno + len);
 	return 0;
 }
+
+struct xfs_rmap_key_state {
+	uint64_t			owner;
+	uint64_t			offset;
+	unsigned int			flags;
+	bool				has_rmap;
+};
+
+/* For each rmap given, figure out if it doesn't match the key we want. */
+STATIC int
+xfs_rmap_has_other_keys_helper(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*priv)
+{
+	struct xfs_rmap_key_state	*rks = priv;
+
+	if (rks->owner == rec->rm_owner && rks->offset == rec->rm_offset &&
+	    ((rks->flags & rec->rm_flags) & XFS_RMAP_KEY_FLAGS) == rks->flags)
+		return 0;
+	rks->has_rmap = true;
+	return XFS_BTREE_QUERY_RANGE_ABORT;
+}
+
+/*
+ * Given an extent and some owner info, can we find records overlapping
+ * the extent whose owner info does not match the given owner?
+ */
+int
+xfs_rmap_has_other_keys(
+	struct xfs_btree_cur		*cur,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	struct xfs_owner_info		*oinfo,
+	bool				*has_rmap)
+{
+	struct xfs_rmap_irec		low = {0};
+	struct xfs_rmap_irec		high;
+	struct xfs_rmap_key_state	rks;
+	int				error;
+
+	xfs_owner_info_unpack(oinfo, &rks.owner, &rks.offset, &rks.flags);
+	rks.has_rmap = false;
+
+	low.rm_startblock = bno;
+	memset(&high, 0xFF, sizeof(high));
+	high.rm_startblock = bno + len - 1;
+
+	error = xfs_rmap_query_range(cur, &low, &high,
+			xfs_rmap_has_other_keys_helper, &rks);
+	*has_rmap = rks.has_rmap;
+	return error;
+}
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 380e53be98d5..43e506f67680 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -238,5 +238,9 @@ int xfs_rmap_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, struct xfs_owner_info *oinfo,
 		bool *has_rmap);
+int xfs_rmap_has_other_keys(struct xfs_btree_cur *cur, xfs_agblock_t bno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo,
+		bool *has_rmap);
+int xfs_rmap_map_raw(struct xfs_btree_cur *cur, struct xfs_rmap_irec *rmap);
 
 #endif	/* __XFS_RMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 106be2d0bb88..369eeb7a52ec 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -90,6 +90,9 @@ xfs_rtbuf_get(
 	if (error)
 		return error;
 
+	if (nmap == 0 || !xfs_bmap_is_real_extent(&map))
+		return -EFSCORRUPTED;
+
 	ASSERT(map.br_startblock != NULLFSBLOCK);
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
@@ -1033,14 +1036,17 @@ xfs_rtalloc_query_range(
 	int				is_free;
 	int				error = 0;
 
-	if (low_rec->ar_startblock > high_rec->ar_startblock)
+	if (low_rec->ar_startext > high_rec->ar_startext)
 		return -EINVAL;
-	else if (low_rec->ar_startblock == high_rec->ar_startblock)
+	if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
+	    low_rec->ar_startext == high_rec->ar_startext)
 		return 0;
+	if (high_rec->ar_startext >= mp->m_sb.sb_rextents)
+		high_rec->ar_startext = mp->m_sb.sb_rextents - 1;
 
 	/* Iterate the bitmap, looking for discrepancies. */
-	rtstart = low_rec->ar_startblock;
-	rem = high_rec->ar_startblock - rtstart;
+	rtstart = low_rec->ar_startext;
+	rem = high_rec->ar_startext - rtstart;
 	while (rem) {
 		/* Is the first block free? */
 		error = xfs_rtcheck_range(mp, tp, rtstart, 1, 1, &rtend,
@@ -1050,13 +1056,13 @@ xfs_rtalloc_query_range(
 
 		/* How long does the extent go for? */
 		error = xfs_rtfind_forw(mp, tp, rtstart,
-				high_rec->ar_startblock - 1, &rtend);
+				high_rec->ar_startext - 1, &rtend);
 		if (error)
 			break;
 
 		if (is_free) {
-			rec.ar_startblock = rtstart;
-			rec.ar_blockcount = rtend - rtstart + 1;
+			rec.ar_startext = rtstart;
+			rec.ar_extcount = rtend - rtstart + 1;
 
 			error = fn(tp, &rec, priv);
 			if (error)
@@ -1079,9 +1085,9 @@ xfs_rtalloc_query_all(
 {
 	struct xfs_rtalloc_rec		keys[2];
 
-	keys[0].ar_startblock = 0;
-	keys[1].ar_startblock = tp->t_mountp->m_sb.sb_rblocks;
-	keys[0].ar_blockcount = keys[1].ar_blockcount = 0;
+	keys[0].ar_startext = 0;
+	keys[1].ar_startext = tp->t_mountp->m_sb.sb_rextents - 1;
+	keys[0].ar_extcount = keys[1].ar_extcount = 0;
 
 	return xfs_rtalloc_query_range(tp, &keys[0], &keys[1], fn, priv);
 }
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index d9b94bd5f689..d485e14313c6 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -888,6 +888,109 @@ xfs_sync_sb(
 	return xfs_trans_commit(tp);
 }
 
+/*
+ * Update all the secondary superblocks to match the new state of the primary.
+ * Because we are completely overwriting all the existing fields in the
+ * secondary superblock buffers, there is no need to read them in from disk.
+ * Just get a new buffer, stamp it and write it.
+ *
+ * The sb buffers need to be cached here so that we serialise against other
+ * operations that access the secondary superblocks, but we don't want to keep
+ * them in memory once it is written so we mark it as a one-shot buffer.
+ */
+int
+xfs_update_secondary_sbs(
+	struct xfs_mount	*mp)
+{
+	xfs_agnumber_t		agno;
+	int			saved_error = 0;
+	int			error = 0;
+	LIST_HEAD		(buffer_list);
+
+	/* update secondary superblocks. */
+	for (agno = 1; agno < mp->m_sb.sb_agcount; agno++) {
+		struct xfs_buf		*bp;
+
+		bp = xfs_buf_get(mp->m_ddev_targp,
+				 XFS_AG_DADDR(mp, agno, XFS_SB_DADDR),
+				 XFS_FSS_TO_BB(mp, 1), 0);
+		/*
+		 * If we get an error reading or writing alternate superblocks,
+		 * continue.  xfs_repair chooses the "best" superblock based
+		 * on most matches; if we break early, we'll leave more
+		 * superblocks un-updated than updated, and xfs_repair may
+		 * pick them over the properly-updated primary.
+		 */
+		if (!bp) {
+			xfs_warn(mp,
+		"error allocating secondary superblock for ag %d",
+				agno);
+			if (!saved_error)
+				saved_error = -ENOMEM;
+			continue;
+		}
+
+		bp->b_ops = &xfs_sb_buf_ops;
+		xfs_buf_oneshot(bp);
+		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
+		xfs_buf_delwri_queue(bp, &buffer_list);
+		xfs_buf_relse(bp);
+
+		/* don't hold too many buffers at once */
+		if (agno % 16)
+			continue;
+
+		error = xfs_buf_delwri_submit(&buffer_list);
+		if (error) {
+			xfs_warn(mp,
+		"write error %d updating a secondary superblock near ag %d",
+				error, agno);
+			if (!saved_error)
+				saved_error = error;
+			continue;
+		}
+	}
+	error = xfs_buf_delwri_submit(&buffer_list);
+	if (error) {
+		xfs_warn(mp,
+		"write error %d updating a secondary superblock near ag %d",
+			error, agno);
+	}
+
+	return saved_error ? saved_error : error;
+}
+
+/*
+ * Same behavior as xfs_sync_sb, except that it is always synchronous and it
+ * also writes the superblock buffer to disk sector 0 immediately.
+ */
+int
+xfs_sync_sb_buf(
+	struct xfs_mount	*mp)
+{
+	struct xfs_trans	*tp;
+	int			error;
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
+	if (error)
+		return error;
+
+	xfs_log_sb(tp);
+	xfs_trans_bhold(tp, mp->m_sb_bp);
+	xfs_trans_set_sync(tp);
+	error = xfs_trans_commit(tp);
+	if (error)
+		goto out;
+	/*
+	 * write out the sb buffer to get the changes to disk
+	 */
+	error = xfs_bwrite(mp->m_sb_bp);
+out:
+	xfs_buf_relse(mp->m_sb_bp);
+	return error;
+}
+
 int
 xfs_fs_geometry(
 	struct xfs_sb		*sbp,
@@ -972,3 +1075,47 @@ xfs_fs_geometry(
 
 	return 0;
 }
+
+/* Read a secondary superblock. */
+int
+xfs_sb_read_secondary(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_buf		*bp;
+	int			error;
+
+	ASSERT(agno != 0 && agno != NULLAGNUMBER);
+	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+	if (error)
+		return error;
+	xfs_buf_set_ref(bp, XFS_SSB_REF);
+	*bpp = bp;
+	return 0;
+}
+
+/* Get an uninitialised secondary superblock buffer. */
+int
+xfs_sb_get_secondary(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_buf		*bp;
+
+	ASSERT(agno != 0 && agno != NULLAGNUMBER);
+	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0);
+	if (!bp)
+		return -ENOMEM;
+	bp->b_ops = &xfs_sb_buf_ops;
+	xfs_buf_oneshot(bp);
+	*bpp = bp;
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 63dcd2a1a657..244e0162c49e 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -18,6 +18,13 @@
 #ifndef __XFS_SB_H__
 #define	__XFS_SB_H__
 
+struct xfs_mount;
+struct xfs_sb;
+struct xfs_dsb;
+struct xfs_trans;
+struct xfs_fsop_geom;
+struct xfs_perag;
+
 /*
  * perag get/put wrappers for ref counting
  */
@@ -29,13 +36,22 @@ extern int	xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t);
 
 extern void	xfs_log_sb(struct xfs_trans *tp);
 extern int	xfs_sync_sb(struct xfs_mount *mp, bool wait);
+extern int	xfs_sync_sb_buf(struct xfs_mount *mp);
 extern void	xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp);
 extern void	xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from);
 extern void	xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from);
 extern void	xfs_sb_quota_from_disk(struct xfs_sb *sbp);
 
+extern int	xfs_update_secondary_sbs(struct xfs_mount *mp);
+
 #define XFS_FS_GEOM_MAX_STRUCT_VER	(4)
 extern int	xfs_fs_geometry(struct xfs_sb *sbp, struct xfs_fsop_geom *geo,
 				int struct_version);
+extern int	xfs_sb_read_secondary(struct xfs_mount *mp,
+				struct xfs_trans *tp, xfs_agnumber_t agno,
+				struct xfs_buf **bpp);
+extern int	xfs_sb_get_secondary(struct xfs_mount *mp,
+				struct xfs_trans *tp, xfs_agnumber_t agno,
+				struct xfs_buf **bpp);
 
 #endif	/* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index d0b84da0cb1e..ae99c260adb1 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -57,21 +57,6 @@ extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
 extern const struct xfs_buf_ops xfs_rtbuf_ops;
 
-/*
- * This structure is used to track log items associated with
- * a transaction.  It points to the log item and keeps some
- * flags to track the state of the log item.  It also tracks
- * the amount of space needed to log the item it describes
- * once we get to commit processing (see xfs_trans_commit()).
- */
-struct xfs_log_item_desc {
-	struct xfs_log_item	*lid_item;
-	struct list_head	lid_trans;
-	unsigned char		lid_flags;
-};
-
-#define XFS_LID_DIRTY		0x1
-
 /* log size calculation functions */
 int	xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
 int	xfs_log_calc_minimum_size(struct xfs_mount *);
@@ -127,6 +112,7 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 #define	XFS_ATTR_BTREE_REF	1
 #define	XFS_DQUOT_REF		1
 #define	XFS_REFC_BTREE_REF	1
+#define	XFS_SSB_REF		0
 
 /*
  * Flags for xfs_trans_ichgtime().
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 3c560695c546..ea18449bd732 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -30,7 +30,7 @@ typedef int64_t		xfs_fsize_t;	/* bytes in a file */
 typedef uint64_t	xfs_ufsize_t;	/* unsigned bytes in a file */
 
 typedef int32_t		xfs_suminfo_t;	/* type of bitmap summary info */
-typedef int32_t		xfs_rtword_t;	/* word type for bitmap manipulations */
+typedef uint32_t	xfs_rtword_t;	/* word type for bitmap manipulations */
 
 typedef int64_t		xfs_lsn_t;	/* log sequence number */
 typedef int32_t		xfs_tid_t;	/* transaction identifier */
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 018aabbd9394..1f71793f7db4 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -38,68 +38,6 @@
 #include "scrub/common.h"
 #include "scrub/trace.h"
 
-/*
- * Walk all the blocks in the AGFL.  The fn function can return any negative
- * error code or XFS_BTREE_QUERY_RANGE_ABORT.
- */
-int
-xfs_scrub_walk_agfl(
-	struct xfs_scrub_context	*sc,
-	int				(*fn)(struct xfs_scrub_context *,
-					      xfs_agblock_t bno, void *),
-	void				*priv)
-{
-	struct xfs_agf			*agf;
-	__be32				*agfl_bno;
-	struct xfs_mount		*mp = sc->mp;
-	unsigned int			flfirst;
-	unsigned int			fllast;
-	int				i;
-	int				error;
-
-	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, sc->sa.agfl_bp);
-	flfirst = be32_to_cpu(agf->agf_flfirst);
-	fllast = be32_to_cpu(agf->agf_fllast);
-
-	/* Nothing to walk in an empty AGFL. */
-	if (agf->agf_flcount == cpu_to_be32(0))
-		return 0;
-
-	/* first to last is a consecutive list. */
-	if (fllast >= flfirst) {
-		for (i = flfirst; i <= fllast; i++) {
-			error = fn(sc, be32_to_cpu(agfl_bno[i]), priv);
-			if (error)
-				return error;
-			if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
-				return error;
-		}
-
-		return 0;
-	}
-
-	/* first to the end */
-	for (i = flfirst; i < xfs_agfl_size(mp); i++) {
-		error = fn(sc, be32_to_cpu(agfl_bno[i]), priv);
-		if (error)
-			return error;
-		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
-			return error;
-	}
-
-	/* the start to last. */
-	for (i = 0; i <= fllast; i++) {
-		error = fn(sc, be32_to_cpu(agfl_bno[i]), priv);
-		if (error)
-			return error;
-		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
-			return error;
-	}
-
-	return 0;
-}
-
 /* Superblock */
 
 /* Cross-reference with the other btrees. */
@@ -157,9 +95,7 @@ xfs_scrub_superblock(
 	if (agno == 0)
 		return 0;
 
-	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
-		  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
-		  XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+	error = xfs_sb_read_secondary(mp, sc->tp, agno, &bp);
 	/*
 	 * The superblock verifier can return several different error codes
 	 * if it thinks the superblock doesn't look right.  For a mount these
@@ -680,6 +616,7 @@ struct xfs_scrub_agfl_info {
 	unsigned int			sz_entries;
 	unsigned int			nr_entries;
 	xfs_agblock_t			*entries;
+	struct xfs_scrub_context	*sc;
 };
 
 /* Cross-reference with the other btrees. */
@@ -701,12 +638,12 @@ xfs_scrub_agfl_block_xref(
 /* Scrub an AGFL block. */
 STATIC int
 xfs_scrub_agfl_block(
-	struct xfs_scrub_context	*sc,
+	struct xfs_mount		*mp,
 	xfs_agblock_t			agbno,
 	void				*priv)
 {
-	struct xfs_mount		*mp = sc->mp;
 	struct xfs_scrub_agfl_info	*sai = priv;
+	struct xfs_scrub_context	*sc = sai->sc;
 	xfs_agnumber_t			agno = sc->sa.agno;
 
 	if (xfs_verify_agbno(mp, agno, agbno) &&
@@ -717,6 +654,9 @@ xfs_scrub_agfl_block(
 
 	xfs_scrub_agfl_block_xref(sc, agbno, priv);
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return XFS_BTREE_QUERY_RANGE_ABORT;
+
 	return 0;
 }
 
@@ -796,8 +736,10 @@ xfs_scrub_agfl(
 		goto out;
 	}
 	memset(&sai, 0, sizeof(sai));
+	sai.sc = sc;
 	sai.sz_entries = agflcount;
-	sai.entries = kmem_zalloc(sizeof(xfs_agblock_t) * agflcount, KM_NOFS);
+	sai.entries = kmem_zalloc(sizeof(xfs_agblock_t) * agflcount,
+			KM_MAYFAIL);
 	if (!sai.entries) {
 		error = -ENOMEM;
 		goto out;
@@ -805,7 +747,12 @@ xfs_scrub_agfl(
 
 	/* Check the blocks in the AGFL. */
 	xfs_rmap_ag_owner(&sai.oinfo, XFS_RMAP_OWN_AG);
-	error = xfs_scrub_walk_agfl(sc, xfs_scrub_agfl_block, &sai);
+	error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(sc->sa.agf_bp),
+			sc->sa.agfl_bp, xfs_scrub_agfl_block, &sai);
+	if (error == XFS_BTREE_QUERY_RANGE_ABORT) {
+		error = 0;
+		goto out_free;
+	}
 	if (error)
 		goto out_free;
 
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
new file mode 100644
index 000000000000..8b91e9ebe1e7
--- /dev/null
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+
+/* Superblock */
+
+/* Repair the superblock. */
+int
+xfs_repair_superblock(
+	struct xfs_scrub_context	*sc)
+{
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_buf			*bp;
+	xfs_agnumber_t			agno;
+	int				error;
+
+	/* Don't try to repair AG 0's sb; let xfs_repair deal with it. */
+	agno = sc->sm->sm_agno;
+	if (agno == 0)
+		return -EOPNOTSUPP;
+
+	error = xfs_sb_get_secondary(mp, sc->tp, agno, &bp);
+	if (error)
+		return error;
+
+	/* Copy AG 0's superblock to this one. */
+	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+	xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
+
+	/* Write this to disk. */
+	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_SB_BUF);
+	xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
+	return error;
+}
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 517c079d3f68..941a0a55224e 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -70,7 +70,7 @@ xfs_scrub_allocbt_xref_other(
 		pcur = &sc->sa.cnt_cur;
 	else
 		pcur = &sc->sa.bno_cur;
-	if (!*pcur)
+	if (!*pcur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	error = xfs_alloc_lookup_le(*pcur, agbno, len, &has_otherrec);
@@ -172,7 +172,7 @@ xfs_scrub_xref_is_used_space(
 	bool				is_freesp;
 	int				error;
 
-	if (!sc->sa.bno_cur)
+	if (!sc->sa.bno_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	error = xfs_alloc_has_record(sc->sa.bno_cur, agbno, len, &is_freesp);
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 127575f0abfb..84b6d6b66578 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -126,8 +126,9 @@ xfs_scrub_xattr_listent(
 	if (args.valuelen != valuelen)
 		xfs_scrub_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
 					     args.blkno);
-
 fail_xref:
+	if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		context->seen_enough = 1;
 	return;
 }
 
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 639d14b51e90..eeadb33a701c 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -51,7 +51,6 @@ xfs_scrub_setup_inode_bmap(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	struct xfs_mount		*mp = sc->mp;
 	int				error;
 
 	error = xfs_scrub_get_inode(sc, ip);
@@ -75,7 +74,7 @@ xfs_scrub_setup_inode_bmap(
 	}
 
 	/* Got the inode, lock it and we're ready to go. */
-	error = xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
+	error = xfs_scrub_trans_alloc(sc, 0);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -175,7 +174,7 @@ xfs_scrub_bmap_xref_rmap(
 	unsigned long long		rmap_end;
 	uint64_t			owner;
 
-	if (!info->sc->sa.rmap_cur)
+	if (!info->sc->sa.rmap_cur || xfs_scrub_skip_xref(info->sc->sm))
 		return;
 
 	if (info->whichfork == XFS_COW_FORK)
@@ -684,7 +683,8 @@ xfs_scrub_bmap(
 	info.lastoff = 0;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	for_each_xfs_iext(ifp, &icur, &irec) {
-		if (xfs_scrub_should_terminate(sc, &error))
+		if (xfs_scrub_should_terminate(sc, &error) ||
+		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 			break;
 		if (isnullstartblock(irec.br_startblock))
 			continue;
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 54218168c8f9..2d29dceaa00e 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -442,7 +442,7 @@ xfs_scrub_btree_check_owner(
 	 */
 	if (cur->bc_btnum == XFS_BTNUM_BNO || cur->bc_btnum == XFS_BTNUM_RMAP) {
 		co = kmem_alloc(sizeof(struct check_owner),
-				KM_MAYFAIL | KM_NOFS);
+				KM_MAYFAIL);
 		if (!co)
 			return -ENOMEM;
 		co->level = level;
@@ -455,6 +455,44 @@ xfs_scrub_btree_check_owner(
 }
 
 /*
+ * Check that this btree block has at least minrecs records or is one of the
+ * special blocks that don't require that.
+ */
+STATIC void
+xfs_scrub_btree_check_minrecs(
+	struct xfs_scrub_btree	*bs,
+	int			level,
+	struct xfs_btree_block	*block)
+{
+	unsigned int		numrecs;
+	int			ok_level;
+
+	numrecs = be16_to_cpu(block->bb_numrecs);
+
+	/* More records than minrecs means the block is ok. */
+	if (numrecs >= bs->cur->bc_ops->get_minrecs(bs->cur, level))
+		return;
+
+	/*
+	 * Certain btree blocks /can/ have fewer than minrecs records.  Any
+	 * level greater than or equal to the level of the highest dedicated
+	 * btree block are allowed to violate this constraint.
+	 *
+	 * For a btree rooted in a block, the btree root can have fewer than
+	 * minrecs records.  If the btree is rooted in an inode and does not
+	 * store records in the root, the direct children of the root and the
+	 * root itself can have fewer than minrecs records.
+	 */
+	ok_level = bs->cur->bc_nlevels - 1;
+	if (bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+		ok_level--;
+	if (level >= ok_level)
+		return;
+
+	xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+}
+
+/*
  * Grab and scrub a btree block given a btree pointer.  Returns block
  * and buffer pointers (if applicable) if they're ok to use.
  */
@@ -491,6 +529,8 @@ xfs_scrub_btree_get_block(
 	if (*pbp)
 		xfs_scrub_buffer_recheck(bs->sc, *pbp);
 
+	xfs_scrub_btree_check_minrecs(bs, level, *pblock);
+
 	/*
 	 * Check the block's owner; this function absorbs error codes
 	 * for us.
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 8ed91d5c868d..41198a5f872c 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -44,11 +44,14 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_log.h"
 #include "xfs_trans_priv.h"
+#include "xfs_attr.h"
+#include "xfs_reflink.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/btree.h"
+#include "scrub/repair.h"
 
 /* Common code for the metadata scrubbers. */
 
@@ -539,6 +542,10 @@ xfs_scrub_ag_free(
 		xfs_trans_brelse(sc->tp, sa->agi_bp);
 		sa->agi_bp = NULL;
 	}
+	if (sa->pag) {
+		xfs_perag_put(sa->pag);
+		sa->pag = NULL;
+	}
 	sa->agno = NULLAGNUMBER;
 }
 
@@ -566,15 +573,53 @@ xfs_scrub_ag_init(
 	return xfs_scrub_ag_btcur_init(sc, sa);
 }
 
+/*
+ * Grab the per-ag structure if we haven't already gotten it.  Teardown of the
+ * xfs_scrub_ag will release it for us.
+ */
+void
+xfs_scrub_perag_get(
+	struct xfs_mount	*mp,
+	struct xfs_scrub_ag	*sa)
+{
+	if (!sa->pag)
+		sa->pag = xfs_perag_get(mp, sa->agno);
+}
+
 /* Per-scrubber setup functions */
 
+/*
+ * Grab an empty transaction so that we can re-grab locked buffers if
+ * one of our btrees turns out to be cyclic.
+ *
+ * If we're going to repair something, we need to ask for the largest possible
+ * log reservation so that we can handle the worst case scenario for metadata
+ * updates while rebuilding a metadata item.  We also need to reserve as many
+ * blocks in the head transaction as we think we're going to need to rebuild
+ * the metadata object.
+ */
+int
+xfs_scrub_trans_alloc(
+	struct xfs_scrub_context	*sc,
+	uint				resblks)
+{
+	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+		return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
+				resblks, 0, 0, &sc->tp);
+
+	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+}
+
 /* Set us up with a transaction and an empty context. */
 int
 xfs_scrub_setup_fs(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	return xfs_scrub_trans_alloc(sc->sm, sc->mp, &sc->tp);
+	uint				resblks;
+
+	resblks = xfs_repair_calc_ag_resblks(sc);
+	return xfs_scrub_trans_alloc(sc, resblks);
 }
 
 /* Set us up with AG headers and btree cursors. */
@@ -695,7 +740,6 @@ xfs_scrub_setup_inode_contents(
 	struct xfs_inode		*ip,
 	unsigned int			resblks)
 {
-	struct xfs_mount		*mp = sc->mp;
 	int				error;
 
 	error = xfs_scrub_get_inode(sc, ip);
@@ -705,7 +749,7 @@ xfs_scrub_setup_inode_contents(
 	/* Got the inode, lock it and we're ready to go. */
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	error = xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
+	error = xfs_scrub_trans_alloc(sc, resblks);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -727,6 +771,10 @@ xfs_scrub_should_check_xref(
 	int				*error,
 	struct xfs_btree_cur		**curpp)
 {
+	/* No point in xref if we already know we're corrupt. */
+	if (xfs_scrub_skip_xref(sc->sm))
+		return false;
+
 	if (*error == 0)
 		return true;
 
@@ -773,3 +821,80 @@ xfs_scrub_buffer_recheck(
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 	trace_xfs_scrub_block_error(sc, bp->b_bn, fa);
 }
+
+/*
+ * Scrub the attr/data forks of a metadata inode.  The metadata inode must be
+ * pointed to by sc->ip and the ILOCK must be held.
+ */
+int
+xfs_scrub_metadata_inode_forks(
+	struct xfs_scrub_context	*sc)
+{
+	__u32				smtype;
+	bool				shared;
+	int				error;
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return 0;
+
+	/* Metadata inodes don't live on the rt device. */
+	if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
+		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		return 0;
+	}
+
+	/* They should never participate in reflink. */
+	if (xfs_is_reflink_inode(sc->ip)) {
+		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		return 0;
+	}
+
+	/* They also should never have extended attributes. */
+	if (xfs_inode_hasattr(sc->ip)) {
+		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		return 0;
+	}
+
+	/* Invoke the data fork scrubber. */
+	smtype = sc->sm->sm_type;
+	sc->sm->sm_type = XFS_SCRUB_TYPE_BMBTD;
+	error = xfs_scrub_bmap_data(sc);
+	sc->sm->sm_type = smtype;
+	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+		return error;
+
+	/* Look for incorrect shared blocks. */
+	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
+		error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
+				&shared);
+		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0,
+				&error))
+			return error;
+		if (shared)
+			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+	}
+
+	return error;
+}
+
+/*
+ * Try to lock an inode in violation of the usual locking order rules.  For
+ * example, trying to get the IOLOCK while in transaction context, or just
+ * plain breaking AG-order or inode-order inode locking rules.  Either way,
+ * the only way to avoid an ABBA deadlock is to use trylock and back off if
+ * we can't.
+ */
+int
+xfs_scrub_ilock_inverted(
+	struct xfs_inode	*ip,
+	uint			lock_mode)
+{
+	int			i;
+
+	for (i = 0; i < 20; i++) {
+		if (xfs_ilock_nowait(ip, lock_mode))
+			return 0;
+		delay(1);
+	}
+	return -EDEADLOCK;
+}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index deaf60400981..76bb2d1d808c 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -38,19 +38,7 @@ xfs_scrub_should_terminate(
 	return false;
 }
 
-/*
- * Grab an empty transaction so that we can re-grab locked buffers if
- * one of our btrees turns out to be cyclic.
- */
-static inline int
-xfs_scrub_trans_alloc(
-	struct xfs_scrub_metadata	*sm,
-	struct xfs_mount		*mp,
-	struct xfs_trans		**tpp)
-{
-	return xfs_trans_alloc_empty(mp, tpp);
-}
-
+int xfs_scrub_trans_alloc(struct xfs_scrub_context *sc, uint resblks);
 bool xfs_scrub_process_error(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
 		xfs_agblock_t bno, int *error);
 bool xfs_scrub_fblock_process_error(struct xfs_scrub_context *sc, int whichfork,
@@ -135,16 +123,13 @@ xfs_scrub_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip)
 void xfs_scrub_ag_free(struct xfs_scrub_context *sc, struct xfs_scrub_ag *sa);
 int xfs_scrub_ag_init(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
 		      struct xfs_scrub_ag *sa);
+void xfs_scrub_perag_get(struct xfs_mount *mp, struct xfs_scrub_ag *sa);
 int xfs_scrub_ag_read_headers(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
 			      struct xfs_buf **agi, struct xfs_buf **agf,
 			      struct xfs_buf **agfl);
 void xfs_scrub_ag_btcur_free(struct xfs_scrub_ag *sa);
 int xfs_scrub_ag_btcur_init(struct xfs_scrub_context *sc,
 			    struct xfs_scrub_ag *sa);
-int xfs_scrub_walk_agfl(struct xfs_scrub_context *sc,
-			int (*fn)(struct xfs_scrub_context *, xfs_agblock_t bno,
-				  void *),
-			void *priv);
 int xfs_scrub_count_rmap_ownedby_ag(struct xfs_scrub_context *sc,
 				    struct xfs_btree_cur *cur,
 				    struct xfs_owner_info *oinfo,
@@ -157,4 +142,17 @@ int xfs_scrub_setup_inode_contents(struct xfs_scrub_context *sc,
 				   struct xfs_inode *ip, unsigned int resblks);
 void xfs_scrub_buffer_recheck(struct xfs_scrub_context *sc, struct xfs_buf *bp);
 
+/*
+ * Don't bother cross-referencing if we already found corruption or cross
+ * referencing discrepancies.
+ */
+static inline bool xfs_scrub_skip_xref(struct xfs_scrub_metadata *sm)
+{
+	return sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+			       XFS_SCRUB_OFLAG_XCORRUPT);
+}
+
+int xfs_scrub_metadata_inode_forks(struct xfs_scrub_context *sc);
+int xfs_scrub_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
+
 #endif	/* __XFS_SCRUB_COMMON_H__ */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 38f29806eb54..1a4309b3e786 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -172,7 +172,7 @@ xfs_scrub_dir_actor(
 	error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL);
 	if (!xfs_scrub_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset,
 			&error))
-		goto fail_xref;
+		goto out;
 	if (lookup_ino != ino) {
 		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
 		goto out;
@@ -183,8 +183,13 @@ xfs_scrub_dir_actor(
 	if (error)
 		goto out;
 out:
-	return error;
-fail_xref:
+	/*
+	 * A negative error code returned here is supposed to cause the
+	 * dir_emit caller (xfs_readdir) to abort the directory iteration
+	 * and return zero to xfs_scrub_directory.
+	 */
+	if (error == 0 && sdc->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return -EFSCORRUPTED;
 	return error;
 }
 
@@ -240,6 +245,9 @@ xfs_scrub_dir_rec(
 	}
 	xfs_scrub_buffer_recheck(ds->sc, bp);
 
+	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out_relse;
+
 	dent = (struct xfs_dir2_data_entry *)(((char *)bp->b_addr) + off);
 
 	/* Make sure we got a real directory entry. */
@@ -357,6 +365,9 @@ xfs_scrub_directory_data_bestfree(
 
 	/* XXX: Check xfs_dir3_data_hdr.pad is zero once we start setting it. */
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out_buf;
+
 	/* Do the bestfrees correspond to actual free space? */
 	bf = d_ops->data_bestfree_p(bp->b_addr);
 	smallest_bestfree = UINT_MAX;
@@ -413,14 +424,18 @@ xfs_scrub_directory_data_bestfree(
 
 		/* Spot check this free entry */
 		tag = be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup));
-		if (tag != ((char *)dup - (char *)bp->b_addr))
+		if (tag != ((char *)dup - (char *)bp->b_addr)) {
 			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			goto out_buf;
+		}
 
 		/*
 		 * Either this entry is a bestfree or it's smaller than
 		 * any of the bestfrees.
 		 */
 		xfs_scrub_directory_check_free_entry(sc, lblk, bf, dup);
+		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+			goto out_buf;
 
 		/* Move on. */
 		newlen = be16_to_cpu(dup->length);
@@ -546,6 +561,8 @@ xfs_scrub_directory_leaf1_bestfree(
 	}
 	if (leafhdr.stale != stale)
 		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
 
 	/* Check all the bestfree entries. */
 	for (i = 0; i < bestcount; i++, bestp++) {
@@ -556,9 +573,11 @@ xfs_scrub_directory_leaf1_bestfree(
 				i * args->geo->fsbcount, -1, &dbp);
 		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
-			continue;
+			break;
 		xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
 		xfs_trans_brelse(sc->tp, dbp);
+		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+			goto out;
 	}
 out:
 	return error;
@@ -607,7 +626,7 @@ xfs_scrub_directory_free_bestfree(
 				-1, &dbp);
 		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
-			continue;
+			break;
 		xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
 		xfs_trans_brelse(sc->tp, dbp);
 	}
@@ -656,7 +675,7 @@ xfs_scrub_directory_blocks(
 
 	/* Iterate all the data extents in the directory... */
 	found = xfs_iext_lookup_extent(sc->ip, ifp, lblk, &icur, &got);
-	while (found) {
+	while (found && !(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
 		/* Block directories only have a single block at offset 0. */
 		if (is_block &&
 		    (got.br_startoff > 0 ||
@@ -719,7 +738,7 @@ xfs_scrub_directory_blocks(
 	/* Scan for free blocks */
 	lblk = free_lblk;
 	found = xfs_iext_lookup_extent(sc->ip, ifp, lblk, &icur, &got);
-	while (found) {
+	while (found && !(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
 		/*
 		 * Dirs can't have blocks mapped above 2^32.
 		 * Single-block dirs shouldn't even be here.
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 106ca4bd753f..00a834d3b56d 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -387,7 +387,8 @@ xfs_scrub_iallocbt_xref_rmap_btreeblks(
 	int				error;
 
 	if (!sc->sa.ino_cur || !sc->sa.rmap_cur ||
-	    (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur))
+	    (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur) ||
+	    xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many inobt blocks as the rmap says. */
@@ -424,7 +425,7 @@ xfs_scrub_iallocbt_xref_rmap_inodes(
 	xfs_filblks_t			blocks;
 	int				error;
 
-	if (!sc->sa.rmap_cur)
+	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many inode blocks as the rmap knows about. */
@@ -496,7 +497,7 @@ xfs_scrub_xref_inode_check(
 	bool				has_inodes;
 	int				error;
 
-	if (!(*icur))
+	if (!(*icur) || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	error = xfs_ialloc_has_inodes_at_extent(*icur, agbno, len, &has_inodes);
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index df14930e4fc5..0c696f7018de 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -55,7 +55,6 @@ xfs_scrub_setup_inode(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	struct xfs_mount		*mp = sc->mp;
 	int				error;
 
 	/*
@@ -68,7 +67,7 @@ xfs_scrub_setup_inode(
 		break;
 	case -EFSCORRUPTED:
 	case -EFSBADCRC:
-		return xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
+		return xfs_scrub_trans_alloc(sc, 0);
 	default:
 		return error;
 	}
@@ -76,7 +75,7 @@ xfs_scrub_setup_inode(
 	/* Got the inode, lock it and we're ready to go. */
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	error = xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
+	error = xfs_scrub_trans_alloc(sc, 0);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -449,7 +448,7 @@ xfs_scrub_inode_xref_finobt(
 	int				has_record;
 	int				error;
 
-	if (!sc->sa.fino_cur)
+	if (!sc->sa.fino_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	agino = XFS_INO_TO_AGINO(sc->mp, ino);
@@ -492,6 +491,9 @@ xfs_scrub_inode_xref_bmap(
 	xfs_filblks_t			acount;
 	int				error;
 
+	if (xfs_scrub_skip_xref(sc->sm))
+		return;
+
 	/* Walk all the extents to check nextents/naextents/nblocks. */
 	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
 			&nextents, &count);
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 1fb88c18d455..77c6b22c6bfd 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -147,6 +147,9 @@ xfs_scrub_parent_validate(
 
 	*try_again = false;
 
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
 	/* '..' must not point to ourselves. */
 	if (sc->ip->i_ino == dnum) {
 		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
@@ -211,7 +214,9 @@ xfs_scrub_parent_validate(
 	 */
 	xfs_iunlock(sc->ip, sc->ilock_flags);
 	sc->ilock_flags = 0;
-	xfs_ilock(dp, XFS_IOLOCK_SHARED);
+	error = xfs_scrub_ilock_inverted(dp, XFS_IOLOCK_SHARED);
+	if (error)
+		goto out_rele;
 
 	/* Go looking for our dentry. */
 	error = xfs_scrub_parent_count_parent_dentries(sc, dp, &nlink);
@@ -220,8 +225,10 @@ xfs_scrub_parent_validate(
 
 	/* Drop the parent lock, relock this inode. */
 	xfs_iunlock(dp, XFS_IOLOCK_SHARED);
+	error = xfs_scrub_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL);
+	if (error)
+		goto out_rele;
 	sc->ilock_flags = XFS_IOLOCK_EXCL;
-	xfs_ilock(sc->ip, sc->ilock_flags);
 
 	/*
 	 * If we're an unlinked directory, the parent /won't/ have a link
@@ -323,5 +330,13 @@ xfs_scrub_parent(
 	if (try_again && tries == 20)
 		xfs_scrub_set_incomplete(sc);
 out:
+	/*
+	 * If we failed to lock the parent inode even after a retry, just mark
+	 * this scrub incomplete and return.
+	 */
+	if (sc->try_harder && error == -EDEADLOCK) {
+		error = 0;
+		xfs_scrub_set_incomplete(sc);
+	}
 	return error;
 }
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 6ba465e6c885..15ae4d23d6ac 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -66,25 +66,43 @@ xfs_scrub_setup_quota(
 	struct xfs_inode		*ip)
 {
 	uint				dqtype;
+	int				error;
+
+	if (!XFS_IS_QUOTA_RUNNING(sc->mp) || !XFS_IS_QUOTA_ON(sc->mp))
+		return -ENOENT;
 
 	dqtype = xfs_scrub_quota_to_dqtype(sc);
 	if (dqtype == 0)
 		return -EINVAL;
+	sc->has_quotaofflock = true;
+	mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock);
 	if (!xfs_this_quota_on(sc->mp, dqtype))
 		return -ENOENT;
+	error = xfs_scrub_setup_fs(sc, ip);
+	if (error)
+		return error;
+	sc->ip = xfs_quota_inode(sc->mp, dqtype);
+	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);
+	sc->ilock_flags = XFS_ILOCK_EXCL;
 	return 0;
 }
 
 /* Quotas. */
 
+struct xfs_scrub_quota_info {
+	struct xfs_scrub_context	*sc;
+	xfs_dqid_t			last_id;
+};
+
 /* Scrub the fields in an individual quota item. */
-STATIC void
+STATIC int
 xfs_scrub_quota_item(
-	struct xfs_scrub_context	*sc,
-	uint				dqtype,
 	struct xfs_dquot		*dq,
-	xfs_dqid_t			id)
+	uint				dqtype,
+	void				*priv)
 {
+	struct xfs_scrub_quota_info	*sqi = priv;
+	struct xfs_scrub_context	*sc = sqi->sc;
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_disk_dquot		*d = &dq->q_core;
 	struct xfs_quotainfo		*qi = mp->m_quotainfo;
@@ -99,17 +117,18 @@ xfs_scrub_quota_item(
 	unsigned long long		icount;
 	unsigned long long		rcount;
 	xfs_ino_t			fs_icount;
-
-	offset = id / qi->qi_dqperchunk;
+	xfs_dqid_t			id = be32_to_cpu(d->d_id);
 
 	/*
-	 * We fed $id and DQNEXT into the xfs_qm_dqget call, which means
-	 * that the actual dquot we got must either have the same id or
-	 * the next higher id.
+	 * Except for the root dquot, the actual dquot we got must either have
+	 * the same or higher id as we saw before.
 	 */
-	if (id > be32_to_cpu(d->d_id))
+	offset = id / qi->qi_dqperchunk;
+	if (id && id <= sqi->last_id)
 		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
+	sqi->last_id = id;
+
 	/* Did we get the dquot type we wanted? */
 	if (dqtype != (d->d_flags & XFS_DQ_ALLTYPES))
 		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
@@ -183,115 +202,85 @@ xfs_scrub_quota_item(
 		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (id != 0 && rhard != 0 && rcount > rhard)
 		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+
+	return 0;
 }
 
-/* Scrub all of a quota type's items. */
-int
-xfs_scrub_quota(
+/* Check the quota's data fork. */
+STATIC int
+xfs_scrub_quota_data_fork(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_bmbt_irec		irec = { 0 };
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip;
-	struct xfs_quotainfo		*qi = mp->m_quotainfo;
-	struct xfs_dquot		*dq;
+	struct xfs_iext_cursor		icur;
+	struct xfs_quotainfo		*qi = sc->mp->m_quotainfo;
+	struct xfs_ifork		*ifp;
 	xfs_fileoff_t			max_dqid_off;
-	xfs_fileoff_t			off = 0;
-	xfs_dqid_t			id = 0;
-	uint				dqtype;
-	int				nimaps;
 	int				error = 0;
 
-	if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp))
-		return -ENOENT;
-
-	mutex_lock(&qi->qi_quotaofflock);
-	dqtype = xfs_scrub_quota_to_dqtype(sc);
-	if (!xfs_this_quota_on(sc->mp, dqtype)) {
-		error = -ENOENT;
-		goto out_unlock_quota;
-	}
-
-	/* Attach to the quota inode and set sc->ip so that reporting works. */
-	ip = xfs_quota_inode(sc->mp, dqtype);
-	sc->ip = ip;
+	/* Invoke the fork scrubber. */
+	error = xfs_scrub_metadata_inode_forks(sc);
+	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+		return error;
 
-	/* Look for problem extents. */
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
-		goto out_unlock_inode;
-	}
+	/* Check for data fork problems that apply only to quota files. */
 	max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
-	while (1) {
+	ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
+	for_each_xfs_iext(ifp, &icur, &irec) {
 		if (xfs_scrub_should_terminate(sc, &error))
 			break;
-
-		off = irec.br_startoff + irec.br_blockcount;
-		nimaps = 1;
-		error = xfs_bmapi_read(ip, off, -1, &irec, &nimaps,
-				XFS_BMAPI_ENTIRE);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, off,
-				&error))
-			goto out_unlock_inode;
-		if (!nimaps)
-			break;
-		if (irec.br_startblock == HOLESTARTBLOCK)
-			continue;
-
-		/* Check the extent record doesn't point to crap. */
-		if (irec.br_startblock + irec.br_blockcount <=
-		    irec.br_startblock)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
-					irec.br_startoff);
-		if (!xfs_verify_fsbno(mp, irec.br_startblock) ||
-		    !xfs_verify_fsbno(mp, irec.br_startblock +
-					irec.br_blockcount - 1))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
-					irec.br_startoff);
-
 		/*
-		 * Unwritten extents or blocks mapped above the highest
+		 * delalloc extents or blocks mapped above the highest
 		 * quota id shouldn't happen.
 		 */
 		if (isnullstartblock(irec.br_startblock) ||
 		    irec.br_startoff > max_dqid_off ||
-		    irec.br_startoff + irec.br_blockcount > max_dqid_off + 1)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
+		    irec.br_startoff + irec.br_blockcount - 1 > max_dqid_off) {
+			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+					irec.br_startoff);
+			break;
+		}
 	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
-		goto out;
 
-	/* Check all the quota items. */
-	while (id < ((xfs_dqid_t)-1ULL)) {
-		if (xfs_scrub_should_terminate(sc, &error))
-			break;
+	return error;
+}
 
-		error = xfs_qm_dqget(mp, NULL, id, dqtype, XFS_QMOPT_DQNEXT,
-				&dq);
-		if (error == -ENOENT)
-			break;
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK,
-				id * qi->qi_dqperchunk, &error))
-			break;
+/* Scrub all of a quota type's items. */
+int
+xfs_scrub_quota(
+	struct xfs_scrub_context	*sc)
+{
+	struct xfs_scrub_quota_info	sqi;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_quotainfo		*qi = mp->m_quotainfo;
+	uint				dqtype;
+	int				error = 0;
 
-		xfs_scrub_quota_item(sc, dqtype, dq, id);
+	dqtype = xfs_scrub_quota_to_dqtype(sc);
 
-		id = be32_to_cpu(dq->q_core.d_id) + 1;
-		xfs_qm_dqput(dq);
-		if (!id)
-			break;
-	}
+	/* Look for problem extents. */
+	error = xfs_scrub_quota_data_fork(sc);
+	if (error)
+		goto out;
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		goto out;
+
+	/*
+	 * Check all the quota items.  Now that we've checked the quota inode
+	 * data fork we have to drop ILOCK_EXCL to use the regular dquot
+	 * functions.
+	 */
+	xfs_iunlock(sc->ip, sc->ilock_flags);
+	sc->ilock_flags = 0;
+	sqi.sc = sc;
+	sqi.last_id = 0;
+	error = xfs_qm_dqiterate(mp, dqtype, xfs_scrub_quota_item, &sqi);
+	sc->ilock_flags = XFS_ILOCK_EXCL;
+	xfs_ilock(sc->ip, sc->ilock_flags);
+	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK,
+			sqi.last_id * qi->qi_dqperchunk, &error))
+		goto out;
 
 out:
-	/* We set sc->ip earlier, so make sure we clear it now. */
-	sc->ip = NULL;
-out_unlock_quota:
-	mutex_unlock(&qi->qi_quotaofflock);
 	return error;
-
-out_unlock_inode:
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	goto out;
 }
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 400f1561cd3d..324a5f159145 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -150,7 +150,7 @@ xfs_scrub_refcountbt_rmap_check(
 		 * so we don't need insertion sort here.
 		 */
 		frag = kmem_alloc(sizeof(struct xfs_scrub_refcnt_frag),
-				KM_MAYFAIL | KM_NOFS);
+				KM_MAYFAIL);
 		if (!frag)
 			return -ENOMEM;
 		memcpy(&frag->rm, rec, sizeof(frag->rm));
@@ -310,7 +310,7 @@ xfs_scrub_refcountbt_xref_rmap(
 	struct xfs_scrub_refcnt_frag	*n;
 	int				error;
 
-	if (!sc->sa.rmap_cur)
+	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	/* Cross-reference with the rmapbt to confirm the refcount. */
@@ -404,7 +404,7 @@ xfs_scrub_refcount_xref_rmap(
 	xfs_filblks_t			blocks;
 	int				error;
 
-	if (!sc->sa.rmap_cur)
+	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many refcbt blocks as the rmap knows about. */
@@ -460,7 +460,7 @@ xfs_scrub_xref_is_cow_staging(
 	int				has_refcount;
 	int				error;
 
-	if (!sc->sa.refc_cur)
+	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	/* Find the CoW staging extent. */
@@ -504,7 +504,7 @@ xfs_scrub_xref_is_not_shared(
 	bool				shared;
 	int				error;
 
-	if (!sc->sa.refc_cur)
+	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared);
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
new file mode 100644
index 000000000000..e3e8fba1c99c
--- /dev/null
+++ b/fs/xfs/scrub/repair.c
@@ -0,0 +1,1089 @@
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
+#include "xfs_extent_busy.h"
+#include "xfs_ag_resv.h"
+#include "xfs_trans_space.h"
+#include "xfs_quota.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Attempt to repair some metadata, if the metadata is corrupt and userspace
+ * told us to fix it.  This function returns -EAGAIN to mean "re-run scrub",
+ * and will set *fixed to true if it thinks it repaired anything.
+ */
+int
+xfs_repair_attempt(
+	struct xfs_inode		*ip,
+	struct xfs_scrub_context	*sc,
+	bool				*fixed)
+{
+	int				error = 0;
+
+	trace_xfs_repair_attempt(ip, sc->sm, error);
+
+	xfs_scrub_ag_btcur_free(&sc->sa);
+
+	/* Repair whatever's broken. */
+	ASSERT(sc->ops->repair);
+	error = sc->ops->repair(sc);
+	trace_xfs_repair_done(ip, sc->sm, error);
+	switch (error) {
+	case 0:
+		/*
+		 * Repair succeeded.  Commit the fixes and perform a second
+		 * scrub so that we can tell userspace if we fixed the problem.
+		 */
+		sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+		*fixed = true;
+		return -EAGAIN;
+	case -EDEADLOCK:
+	case -EAGAIN:
+		/* Tell the caller to try again having grabbed all the locks. */
+		if (!sc->try_harder) {
+			sc->try_harder = true;
+			return -EAGAIN;
+		}
+		/*
+		 * We tried harder but still couldn't grab all the resources
+		 * we needed to fix it.  The corruption has not been fixed,
+		 * so report back to userspace.
+		 */
+		return -EFSCORRUPTED;
+	default:
+		return error;
+	}
+}
+
+/*
+ * Complain about unfixable problems in the filesystem.  We don't log
+ * corruptions when IFLAG_REPAIR wasn't set on the assumption that the driver
+ * program is xfs_scrub, which will call back with IFLAG_REPAIR set if the
+ * administrator isn't running xfs_scrub in no-repairs mode.
+ *
+ * Use this helper function because _ratelimited silently declares a static
+ * structure to track rate limiting information.
+ */
+void
+xfs_repair_failure(
+	struct xfs_mount		*mp)
+{
+	xfs_alert_ratelimited(mp,
+"Corruption not fixed during online repair.  Unmount and run xfs_repair.");
+}
+
+/*
+ * Repair probe -- userspace uses this to probe if we're willing to repair a
+ * given mountpoint.
+ */
+int
+xfs_repair_probe(
+	struct xfs_scrub_context	*sc)
+{
+	int				error = 0;
+
+	if (xfs_scrub_should_terminate(sc, &error))
+		return error;
+
+	return 0;
+}
+
+/*
+ * Roll a transaction, keeping the AG headers locked and reinitializing
+ * the btree cursors.
+ */
+int
+xfs_repair_roll_ag_trans(
+	struct xfs_scrub_context	*sc)
+{
+	int				error;
+
+	/* Keep the AG header buffers locked so we can keep going. */
+	xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
+	xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
+	xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
+
+	/* Roll the transaction. */
+	error = xfs_trans_roll(&sc->tp);
+	if (error)
+		goto out_release;
+
+	/* Join AG headers to the new transaction. */
+	xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
+	xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
+	xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
+
+	return 0;
+
+out_release:
+	/*
+	 * Rolling failed, so release the hold on the buffers.  The
+	 * buffers will be released during teardown on our way out
+	 * of the kernel.
+	 */
+	xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
+	xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
+	xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp);
+
+	return error;
+}
+
+/*
+ * Does the given AG have enough space to rebuild a btree?  Neither AG
+ * reservation can be critical, and we must have enough space (factoring
+ * in AG reservations) to construct a whole btree.
+ */
+bool
+xfs_repair_ag_has_space(
+	struct xfs_perag		*pag,
+	xfs_extlen_t			nr_blocks,
+	enum xfs_ag_resv_type		type)
+{
+	return  !xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) &&
+		!xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA) &&
+		pag->pagf_freeblks > xfs_ag_resv_needed(pag, type) + nr_blocks;
+}
+
+/*
+ * Figure out how many blocks to reserve for an AG repair.  We calculate the
+ * worst case estimate for the number of blocks we'd need to rebuild one of
+ * any type of per-AG btree.
+ */
+xfs_extlen_t
+xfs_repair_calc_ag_resblks(
+	struct xfs_scrub_context	*sc)
+{
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_scrub_metadata	*sm = sc->sm;
+	struct xfs_perag		*pag;
+	struct xfs_buf			*bp;
+	xfs_agino_t			icount = 0;
+	xfs_extlen_t			aglen = 0;
+	xfs_extlen_t			usedlen;
+	xfs_extlen_t			freelen;
+	xfs_extlen_t			bnobt_sz;
+	xfs_extlen_t			inobt_sz;
+	xfs_extlen_t			rmapbt_sz;
+	xfs_extlen_t			refcbt_sz;
+	int				error;
+
+	if (!(sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
+		return 0;
+
+	/* Use in-core counters if possible. */
+	pag = xfs_perag_get(mp, sm->sm_agno);
+	if (pag->pagi_init)
+		icount = pag->pagi_count;
+
+	/*
+	 * Otherwise try to get the actual counters from disk; if not, make
+	 * some worst case assumptions.
+	 */
+	if (icount == 0) {
+		error = xfs_ialloc_read_agi(mp, NULL, sm->sm_agno, &bp);
+		if (error) {
+			icount = mp->m_sb.sb_agblocks / mp->m_sb.sb_inopblock;
+		} else {
+			icount = pag->pagi_count;
+			xfs_buf_relse(bp);
+		}
+	}
+
+	/* Now grab the block counters from the AGF. */
+	error = xfs_alloc_read_agf(mp, NULL, sm->sm_agno, 0, &bp);
+	if (error) {
+		aglen = mp->m_sb.sb_agblocks;
+		freelen = aglen;
+		usedlen = aglen;
+	} else {
+		aglen = be32_to_cpu(XFS_BUF_TO_AGF(bp)->agf_length);
+		freelen = pag->pagf_freeblks;
+		usedlen = aglen - freelen;
+		xfs_buf_relse(bp);
+	}
+	xfs_perag_put(pag);
+
+	trace_xfs_repair_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
+			freelen, usedlen);
+
+	/*
+	 * Figure out how many blocks we'd need worst case to rebuild
+	 * each type of btree.  Note that we can only rebuild the
+	 * bnobt/cntbt or inobt/finobt as pairs.
+	 */
+	bnobt_sz = 2 * xfs_allocbt_calc_size(mp, freelen);
+	if (xfs_sb_version_hassparseinodes(&mp->m_sb))
+		inobt_sz = xfs_iallocbt_calc_size(mp, icount /
+				XFS_INODES_PER_HOLEMASK_BIT);
+	else
+		inobt_sz = xfs_iallocbt_calc_size(mp, icount /
+				XFS_INODES_PER_CHUNK);
+	if (xfs_sb_version_hasfinobt(&mp->m_sb))
+		inobt_sz *= 2;
+	if (xfs_sb_version_hasreflink(&mp->m_sb))
+		refcbt_sz = xfs_refcountbt_calc_size(mp, usedlen);
+	else
+		refcbt_sz = 0;
+	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
+		/*
+		 * Guess how many blocks we need to rebuild the rmapbt.
+		 * For non-reflink filesystems we can't have more records than
+		 * used blocks.  However, with reflink it's possible to have
+		 * more than one rmap record per AG block.  We don't know how
+		 * many rmaps there could be in the AG, so we start off with
+		 * what we hope is an generous over-estimation.
+		 */
+		if (xfs_sb_version_hasreflink(&mp->m_sb))
+			rmapbt_sz = xfs_rmapbt_calc_size(mp,
+					(unsigned long long)aglen * 2);
+		else
+			rmapbt_sz = xfs_rmapbt_calc_size(mp, usedlen);
+	} else {
+		rmapbt_sz = 0;
+	}
+
+	trace_xfs_repair_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
+			inobt_sz, rmapbt_sz, refcbt_sz);
+
+	return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
+}
+
+/* Allocate a block in an AG. */
+int
+xfs_repair_alloc_ag_block(
+	struct xfs_scrub_context	*sc,
+	struct xfs_owner_info		*oinfo,
+	xfs_fsblock_t			*fsbno,
+	enum xfs_ag_resv_type		resv)
+{
+	struct xfs_alloc_arg		args = {0};
+	xfs_agblock_t			bno;
+	int				error;
+
+	switch (resv) {
+	case XFS_AG_RESV_AGFL:
+	case XFS_AG_RESV_RMAPBT:
+		error = xfs_alloc_get_freelist(sc->tp, sc->sa.agf_bp, &bno, 1);
+		if (error)
+			return error;
+		if (bno == NULLAGBLOCK)
+			return -ENOSPC;
+		xfs_extent_busy_reuse(sc->mp, sc->sa.agno, bno,
+				1, false);
+		*fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.agno, bno);
+		if (resv == XFS_AG_RESV_RMAPBT)
+			xfs_ag_resv_rmapbt_alloc(sc->mp, sc->sa.agno);
+		return 0;
+	default:
+		break;
+	}
+
+	args.tp = sc->tp;
+	args.mp = sc->mp;
+	args.oinfo = *oinfo;
+	args.fsbno = XFS_AGB_TO_FSB(args.mp, sc->sa.agno, 0);
+	args.minlen = 1;
+	args.maxlen = 1;
+	args.prod = 1;
+	args.type = XFS_ALLOCTYPE_THIS_AG;
+	args.resv = resv;
+
+	error = xfs_alloc_vextent(&args);
+	if (error)
+		return error;
+	if (args.fsbno == NULLFSBLOCK)
+		return -ENOSPC;
+	ASSERT(args.len == 1);
+	*fsbno = args.fsbno;
+
+	return 0;
+}
+
+/* Initialize a new AG btree root block with zero entries. */
+int
+xfs_repair_init_btblock(
+	struct xfs_scrub_context	*sc,
+	xfs_fsblock_t			fsb,
+	struct xfs_buf			**bpp,
+	xfs_btnum_t			btnum,
+	const struct xfs_buf_ops	*ops)
+{
+	struct xfs_trans		*tp = sc->tp;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_buf			*bp;
+
+	trace_xfs_repair_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
+			XFS_FSB_TO_AGBNO(mp, fsb), btnum);
+
+	ASSERT(XFS_FSB_TO_AGNO(mp, fsb) == sc->sa.agno);
+	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, fsb),
+			XFS_FSB_TO_BB(mp, 1), 0);
+	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+	xfs_btree_init_block(mp, bp, btnum, 0, 0, sc->sa.agno, 0);
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_BTREE_BUF);
+	xfs_trans_log_buf(tp, bp, 0, bp->b_length);
+	bp->b_ops = ops;
+	*bpp = bp;
+
+	return 0;
+}
+
+/*
+ * Reconstructing per-AG Btrees
+ *
+ * When a space btree is corrupt, we don't bother trying to fix it.  Instead,
+ * we scan secondary space metadata to derive the records that should be in
+ * the damaged btree, initialize a fresh btree root, and insert the records.
+ * Note that for rebuilding the rmapbt we scan all the primary data to
+ * generate the new records.
+ *
+ * However, that leaves the matter of removing all the metadata describing the
+ * old broken structure.  For primary metadata we use the rmap data to collect
+ * every extent with a matching rmap owner (exlist); we then iterate all other
+ * metadata structures with the same rmap owner to collect the extents that
+ * cannot be removed (sublist).  We then subtract sublist from exlist to
+ * derive the blocks that were used by the old btree.  These blocks can be
+ * reaped.
+ *
+ * For rmapbt reconstructions we must use different tactics for extent
+ * collection.  First we iterate all primary metadata (this excludes the old
+ * rmapbt, obviously) to generate new rmap records.  The gaps in the rmap
+ * records are collected as exlist.  The bnobt records are collected as
+ * sublist.  As with the other btrees we subtract sublist from exlist, and the
+ * result (since the rmapbt lives in the free space) are the blocks from the
+ * old rmapbt.
+ */
+
+/* Collect a dead btree extent for later disposal. */
+int
+xfs_repair_collect_btree_extent(
+	struct xfs_scrub_context	*sc,
+	struct xfs_repair_extent_list	*exlist,
+	xfs_fsblock_t			fsbno,
+	xfs_extlen_t			len)
+{
+	struct xfs_repair_extent	*rex;
+
+	trace_xfs_repair_collect_btree_extent(sc->mp,
+			XFS_FSB_TO_AGNO(sc->mp, fsbno),
+			XFS_FSB_TO_AGBNO(sc->mp, fsbno), len);
+
+	rex = kmem_alloc(sizeof(struct xfs_repair_extent), KM_MAYFAIL);
+	if (!rex)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&rex->list);
+	rex->fsbno = fsbno;
+	rex->len = len;
+	list_add_tail(&rex->list, &exlist->list);
+
+	return 0;
+}
+
+/*
+ * An error happened during the rebuild so the transaction will be cancelled.
+ * The fs will shut down, and the administrator has to unmount and run repair.
+ * Therefore, free all the memory associated with the list so we can die.
+ */
+void
+xfs_repair_cancel_btree_extents(
+	struct xfs_scrub_context	*sc,
+	struct xfs_repair_extent_list	*exlist)
+{
+	struct xfs_repair_extent	*rex;
+	struct xfs_repair_extent	*n;
+
+	for_each_xfs_repair_extent_safe(rex, n, exlist) {
+		list_del(&rex->list);
+		kmem_free(rex);
+	}
+}
+
+/* Compare two btree extents. */
+static int
+xfs_repair_btree_extent_cmp(
+	void				*priv,
+	struct list_head		*a,
+	struct list_head		*b)
+{
+	struct xfs_repair_extent	*ap;
+	struct xfs_repair_extent	*bp;
+
+	ap = container_of(a, struct xfs_repair_extent, list);
+	bp = container_of(b, struct xfs_repair_extent, list);
+
+	if (ap->fsbno > bp->fsbno)
+		return 1;
+	if (ap->fsbno < bp->fsbno)
+		return -1;
+	return 0;
+}
+
+/*
+ * Remove all the blocks mentioned in @sublist from the extents in @exlist.
+ *
+ * The intent is that callers will iterate the rmapbt for all of its records
+ * for a given owner to generate @exlist; and iterate all the blocks of the
+ * metadata structures that are not being rebuilt and have the same rmapbt
+ * owner to generate @sublist.  This routine subtracts all the extents
+ * mentioned in sublist from all the extents linked in @exlist, which leaves
+ * @exlist as the list of blocks that are not accounted for, which we assume
+ * are the dead blocks of the old metadata structure.  The blocks mentioned in
+ * @exlist can be reaped.
+ */
+#define LEFT_ALIGNED	(1 << 0)
+#define RIGHT_ALIGNED	(1 << 1)
+int
+xfs_repair_subtract_extents(
+	struct xfs_scrub_context	*sc,
+	struct xfs_repair_extent_list	*exlist,
+	struct xfs_repair_extent_list	*sublist)
+{
+	struct list_head		*lp;
+	struct xfs_repair_extent	*ex;
+	struct xfs_repair_extent	*newex;
+	struct xfs_repair_extent	*subex;
+	xfs_fsblock_t			sub_fsb;
+	xfs_extlen_t			sub_len;
+	int				state;
+	int				error = 0;
+
+	if (list_empty(&exlist->list) || list_empty(&sublist->list))
+		return 0;
+	ASSERT(!list_empty(&sublist->list));
+
+	list_sort(NULL, &exlist->list, xfs_repair_btree_extent_cmp);
+	list_sort(NULL, &sublist->list, xfs_repair_btree_extent_cmp);
+
+	/*
+	 * Now that we've sorted both lists, we iterate exlist once, rolling
+	 * forward through sublist and/or exlist as necessary until we find an
+	 * overlap or reach the end of either list.  We do not reset lp to the
+	 * head of exlist nor do we reset subex to the head of sublist.  The
+	 * list traversal is similar to merge sort, but we're deleting
+	 * instead.  In this manner we avoid O(n^2) operations.
+	 */
+	subex = list_first_entry(&sublist->list, struct xfs_repair_extent,
+			list);
+	lp = exlist->list.next;
+	while (lp != &exlist->list) {
+		ex = list_entry(lp, struct xfs_repair_extent, list);
+
+		/*
+		 * Advance subex and/or ex until we find a pair that
+		 * intersect or we run out of extents.
+		 */
+		while (subex->fsbno + subex->len <= ex->fsbno) {
+			if (list_is_last(&subex->list, &sublist->list))
+				goto out;
+			subex = list_next_entry(subex, list);
+		}
+		if (subex->fsbno >= ex->fsbno + ex->len) {
+			lp = lp->next;
+			continue;
+		}
+
+		/* trim subex to fit the extent we have */
+		sub_fsb = subex->fsbno;
+		sub_len = subex->len;
+		if (subex->fsbno < ex->fsbno) {
+			sub_len -= ex->fsbno - subex->fsbno;
+			sub_fsb = ex->fsbno;
+		}
+		if (sub_len > ex->len)
+			sub_len = ex->len;
+
+		state = 0;
+		if (sub_fsb == ex->fsbno)
+			state |= LEFT_ALIGNED;
+		if (sub_fsb + sub_len == ex->fsbno + ex->len)
+			state |= RIGHT_ALIGNED;
+		switch (state) {
+		case LEFT_ALIGNED:
+			/* Coincides with only the left. */
+			ex->fsbno += sub_len;
+			ex->len -= sub_len;
+			break;
+		case RIGHT_ALIGNED:
+			/* Coincides with only the right. */
+			ex->len -= sub_len;
+			lp = lp->next;
+			break;
+		case LEFT_ALIGNED | RIGHT_ALIGNED:
+			/* Total overlap, just delete ex. */
+			lp = lp->next;
+			list_del(&ex->list);
+			kmem_free(ex);
+			break;
+		case 0:
+			/*
+			 * Deleting from the middle: add the new right extent
+			 * and then shrink the left extent.
+			 */
+			newex = kmem_alloc(sizeof(struct xfs_repair_extent),
+					KM_MAYFAIL);
+			if (!newex) {
+				error = -ENOMEM;
+				goto out;
+			}
+			INIT_LIST_HEAD(&newex->list);
+			newex->fsbno = sub_fsb + sub_len;
+			newex->len = ex->fsbno + ex->len - newex->fsbno;
+			list_add(&newex->list, &ex->list);
+			ex->len = sub_fsb - ex->fsbno;
+			lp = lp->next;
+			break;
+		default:
+			ASSERT(0);
+			break;
+		}
+	}
+
+out:
+	return error;
+}
+#undef LEFT_ALIGNED
+#undef RIGHT_ALIGNED
+
+/*
+ * Disposal of Blocks from Old per-AG Btrees
+ *
+ * Now that we've constructed a new btree to replace the damaged one, we want
+ * to dispose of the blocks that (we think) the old btree was using.
+ * Previously, we used the rmapbt to collect the extents (exlist) with the
+ * rmap owner corresponding to the tree we rebuilt, collected extents for any
+ * blocks with the same rmap owner that are owned by another data structure
+ * (sublist), and subtracted sublist from exlist.  In theory the extents
+ * remaining in exlist are the old btree's blocks.
+ *
+ * Unfortunately, it's possible that the btree was crosslinked with other
+ * blocks on disk.  The rmap data can tell us if there are multiple owners, so
+ * if the rmapbt says there is an owner of this block other than @oinfo, then
+ * the block is crosslinked.  Remove the reverse mapping and continue.
+ *
+ * If there is one rmap record, we can free the block, which removes the
+ * reverse mapping but doesn't add the block to the free space.  Our repair
+ * strategy is to hope the other metadata objects crosslinked on this block
+ * will be rebuilt (atop different blocks), thereby removing all the cross
+ * links.
+ *
+ * If there are no rmap records at all, we also free the block.  If the btree
+ * being rebuilt lives in the free space (bnobt/cntbt/rmapbt) then there isn't
+ * supposed to be a rmap record and everything is ok.  For other btrees there
+ * had to have been an rmap entry for the block to have ended up on @exlist,
+ * so if it's gone now there's something wrong and the fs will shut down.
+ *
+ * Note: If there are multiple rmap records with only the same rmap owner as
+ * the btree we're trying to rebuild and the block is indeed owned by another
+ * data structure with the same rmap owner, then the block will be in sublist
+ * and therefore doesn't need disposal.  If there are multiple rmap records
+ * with only the same rmap owner but the block is not owned by something with
+ * the same rmap owner, the block will be freed.
+ *
+ * The caller is responsible for locking the AG headers for the entire rebuild
+ * operation so that nothing else can sneak in and change the AG state while
+ * we're not looking.  We also assume that the caller already invalidated any
+ * buffers associated with @exlist.
+ */
+
+/*
+ * Invalidate buffers for per-AG btree blocks we're dumping.  This function
+ * is not intended for use with file data repairs; we have bunmapi for that.
+ */
+int
+xfs_repair_invalidate_blocks(
+	struct xfs_scrub_context	*sc,
+	struct xfs_repair_extent_list	*exlist)
+{
+	struct xfs_repair_extent	*rex;
+	struct xfs_repair_extent	*n;
+	struct xfs_buf			*bp;
+	xfs_fsblock_t			fsbno;
+	xfs_agblock_t			i;
+
+	/*
+	 * For each block in each extent, see if there's an incore buffer for
+	 * exactly that block; if so, invalidate it.  The buffer cache only
+	 * lets us look for one buffer at a time, so we have to look one block
+	 * at a time.  Avoid invalidating AG headers and post-EOFS blocks
+	 * because we never own those; and if we can't TRYLOCK the buffer we
+	 * assume it's owned by someone else.
+	 */
+	for_each_xfs_repair_extent_safe(rex, n, exlist) {
+		for (fsbno = rex->fsbno, i = rex->len; i > 0; fsbno++, i--) {
+			/* Skip AG headers and post-EOFS blocks */
+			if (!xfs_verify_fsbno(sc->mp, fsbno))
+				continue;
+			bp = xfs_buf_incore(sc->mp->m_ddev_targp,
+					XFS_FSB_TO_DADDR(sc->mp, fsbno),
+					XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
+			if (bp) {
+				xfs_trans_bjoin(sc->tp, bp);
+				xfs_trans_binval(sc->tp, bp);
+			}
+		}
+	}
+
+	return 0;
+}
+
+/* Ensure the freelist is the correct size. */
+int
+xfs_repair_fix_freelist(
+	struct xfs_scrub_context	*sc,
+	bool				can_shrink)
+{
+	struct xfs_alloc_arg		args = {0};
+
+	args.mp = sc->mp;
+	args.tp = sc->tp;
+	args.agno = sc->sa.agno;
+	args.alignment = 1;
+	args.pag = sc->sa.pag;
+
+	return xfs_alloc_fix_freelist(&args,
+			can_shrink ? 0 : XFS_ALLOC_FLAG_NOSHRINK);
+}
+
+/*
+ * Put a block back on the AGFL.
+ */
+STATIC int
+xfs_repair_put_freelist(
+	struct xfs_scrub_context	*sc,
+	xfs_agblock_t			agbno)
+{
+	struct xfs_owner_info		oinfo;
+	int				error;
+
+	/* Make sure there's space on the freelist. */
+	error = xfs_repair_fix_freelist(sc, true);
+	if (error)
+		return error;
+
+	/*
+	 * Since we're "freeing" a lost block onto the AGFL, we have to
+	 * create an rmap for the block prior to merging it or else other
+	 * parts will break.
+	 */
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
+	error = xfs_rmap_alloc(sc->tp, sc->sa.agf_bp, sc->sa.agno, agbno, 1,
+			&oinfo);
+	if (error)
+		return error;
+
+	/* Put the block on the AGFL. */
+	error = xfs_alloc_put_freelist(sc->tp, sc->sa.agf_bp, sc->sa.agfl_bp,
+			agbno, 0);
+	if (error)
+		return error;
+	xfs_extent_busy_insert(sc->tp, sc->sa.agno, agbno, 1,
+			XFS_EXTENT_BUSY_SKIP_DISCARD);
+
+	return 0;
+}
+
+/* Dispose of a single metadata block. */
+STATIC int
+xfs_repair_dispose_btree_block(
+	struct xfs_scrub_context	*sc,
+	xfs_fsblock_t			fsbno,
+	struct xfs_owner_info		*oinfo,
+	enum xfs_ag_resv_type		resv)
+{
+	struct xfs_btree_cur		*cur;
+	struct xfs_buf			*agf_bp = NULL;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
+	bool				has_other_rmap;
+	int				error;
+
+	agno = XFS_FSB_TO_AGNO(sc->mp, fsbno);
+	agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno);
+
+	/*
+	 * If we are repairing per-inode metadata, we need to read in the AGF
+	 * buffer.  Otherwise, we're repairing a per-AG structure, so reuse
+	 * the AGF buffer that the setup functions already grabbed.
+	 */
+	if (sc->ip) {
+		error = xfs_alloc_read_agf(sc->mp, sc->tp, agno, 0, &agf_bp);
+		if (error)
+			return error;
+		if (!agf_bp)
+			return -ENOMEM;
+	} else {
+		agf_bp = sc->sa.agf_bp;
+	}
+	cur = xfs_rmapbt_init_cursor(sc->mp, sc->tp, agf_bp, agno);
+
+	/* Can we find any other rmappings? */
+	error = xfs_rmap_has_other_keys(cur, agbno, 1, oinfo, &has_other_rmap);
+	if (error)
+		goto out_cur;
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+
+	/*
+	 * If there are other rmappings, this block is cross linked and must
+	 * not be freed.  Remove the reverse mapping and move on.  Otherwise,
+	 * we were the only owner of the block, so free the extent, which will
+	 * also remove the rmap.
+	 *
+	 * XXX: XFS doesn't support detecting the case where a single block
+	 * metadata structure is crosslinked with a multi-block structure
+	 * because the buffer cache doesn't detect aliasing problems, so we
+	 * can't fix 100% of crosslinking problems (yet).  The verifiers will
+	 * blow on writeout, the filesystem will shut down, and the admin gets
+	 * to run xfs_repair.
+	 */
+	if (has_other_rmap)
+		error = xfs_rmap_free(sc->tp, agf_bp, agno, agbno, 1, oinfo);
+	else if (resv == XFS_AG_RESV_AGFL)
+		error = xfs_repair_put_freelist(sc, agbno);
+	else
+		error = xfs_free_extent(sc->tp, fsbno, 1, oinfo, resv);
+	if (agf_bp != sc->sa.agf_bp)
+		xfs_trans_brelse(sc->tp, agf_bp);
+	if (error)
+		return error;
+
+	if (sc->ip)
+		return xfs_trans_roll_inode(&sc->tp, sc->ip);
+	return xfs_repair_roll_ag_trans(sc);
+
+out_cur:
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	if (agf_bp != sc->sa.agf_bp)
+		xfs_trans_brelse(sc->tp, agf_bp);
+	return error;
+}
+
+/* Dispose of btree blocks from an old per-AG btree. */
+int
+xfs_repair_reap_btree_extents(
+	struct xfs_scrub_context	*sc,
+	struct xfs_repair_extent_list	*exlist,
+	struct xfs_owner_info		*oinfo,
+	enum xfs_ag_resv_type		type)
+{
+	struct xfs_repair_extent	*rex;
+	struct xfs_repair_extent	*n;
+	int				error = 0;
+
+	ASSERT(xfs_sb_version_hasrmapbt(&sc->mp->m_sb));
+
+	/* Dispose of every block from the old btree. */
+	for_each_xfs_repair_extent_safe(rex, n, exlist) {
+		ASSERT(sc->ip != NULL ||
+		       XFS_FSB_TO_AGNO(sc->mp, rex->fsbno) == sc->sa.agno);
+
+		trace_xfs_repair_dispose_btree_extent(sc->mp,
+				XFS_FSB_TO_AGNO(sc->mp, rex->fsbno),
+				XFS_FSB_TO_AGBNO(sc->mp, rex->fsbno), rex->len);
+
+		for (; rex->len > 0; rex->len--, rex->fsbno++) {
+			error = xfs_repair_dispose_btree_block(sc, rex->fsbno,
+					oinfo, type);
+			if (error)
+				goto out;
+		}
+		list_del(&rex->list);
+		kmem_free(rex);
+	}
+
+out:
+	xfs_repair_cancel_btree_extents(sc, exlist);
+	return error;
+}
+
+/*
+ * Finding per-AG Btree Roots for AGF/AGI Reconstruction
+ *
+ * If the AGF or AGI become slightly corrupted, it may be necessary to rebuild
+ * the AG headers by using the rmap data to rummage through the AG looking for
+ * btree roots.  This is not guaranteed to work if the AG is heavily damaged
+ * or the rmap data are corrupt.
+ *
+ * Callers of xfs_repair_find_ag_btree_roots must lock the AGF and AGFL
+ * buffers if the AGF is being rebuilt; or the AGF and AGI buffers if the
+ * AGI is being rebuilt.  It must maintain these locks until it's safe for
+ * other threads to change the btrees' shapes.  The caller provides
+ * information about the btrees to look for by passing in an array of
+ * xfs_repair_find_ag_btree with the (rmap owner, buf_ops, magic) fields set.
+ * The (root, height) fields will be set on return if anything is found.  The
+ * last element of the array should have a NULL buf_ops to mark the end of the
+ * array.
+ *
+ * For every rmapbt record matching any of the rmap owners in btree_info,
+ * read each block referenced by the rmap record.  If the block is a btree
+ * block from this filesystem matching any of the magic numbers and has a
+ * level higher than what we've already seen, remember the block and the
+ * height of the tree required to have such a block.  When the call completes,
+ * we return the highest block we've found for each btree description; those
+ * should be the roots.
+ */
+
+struct xfs_repair_findroot {
+	struct xfs_scrub_context	*sc;
+	struct xfs_buf			*agfl_bp;
+	struct xfs_agf			*agf;
+	struct xfs_repair_find_ag_btree	*btree_info;
+};
+
+/* See if our block is in the AGFL. */
+STATIC int
+xfs_repair_findroot_agfl_walk(
+	struct xfs_mount		*mp,
+	xfs_agblock_t			bno,
+	void				*priv)
+{
+	xfs_agblock_t			*agbno = priv;
+
+	return (*agbno == bno) ? XFS_BTREE_QUERY_RANGE_ABORT : 0;
+}
+
+/* Does this block match the btree information passed in? */
+STATIC int
+xfs_repair_findroot_block(
+	struct xfs_repair_findroot	*ri,
+	struct xfs_repair_find_ag_btree	*fab,
+	uint64_t			owner,
+	xfs_agblock_t			agbno,
+	bool				*found_it)
+{
+	struct xfs_mount		*mp = ri->sc->mp;
+	struct xfs_buf			*bp;
+	struct xfs_btree_block		*btblock;
+	xfs_daddr_t			daddr;
+	int				error;
+
+	daddr = XFS_AGB_TO_DADDR(mp, ri->sc->sa.agno, agbno);
+
+	/*
+	 * Blocks in the AGFL have stale contents that might just happen to
+	 * have a matching magic and uuid.  We don't want to pull these blocks
+	 * in as part of a tree root, so we have to filter out the AGFL stuff
+	 * here.  If the AGFL looks insane we'll just refuse to repair.
+	 */
+	if (owner == XFS_RMAP_OWN_AG) {
+		error = xfs_agfl_walk(mp, ri->agf, ri->agfl_bp,
+				xfs_repair_findroot_agfl_walk, &agbno);
+		if (error == XFS_BTREE_QUERY_RANGE_ABORT)
+			return 0;
+		if (error)
+			return error;
+	}
+
+	error = xfs_trans_read_buf(mp, ri->sc->tp, mp->m_ddev_targp, daddr,
+			mp->m_bsize, 0, &bp, NULL);
+	if (error)
+		return error;
+
+	/*
+	 * Does this look like a block matching our fs and higher than any
+	 * other block we've found so far?  If so, reattach buffer verifiers
+	 * so the AIL won't complain if the buffer is also dirty.
+	 */
+	btblock = XFS_BUF_TO_BLOCK(bp);
+	if (be32_to_cpu(btblock->bb_magic) != fab->magic)
+		goto out;
+	if (xfs_sb_version_hascrc(&mp->m_sb) &&
+	    !uuid_equal(&btblock->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
+		goto out;
+	bp->b_ops = fab->buf_ops;
+
+	/* Ignore this block if it's lower in the tree than we've seen. */
+	if (fab->root != NULLAGBLOCK &&
+	    xfs_btree_get_level(btblock) < fab->height)
+		goto out;
+
+	/* Make sure we pass the verifiers. */
+	bp->b_ops->verify_read(bp);
+	if (bp->b_error)
+		goto out;
+	fab->root = agbno;
+	fab->height = xfs_btree_get_level(btblock) + 1;
+	*found_it = true;
+
+	trace_xfs_repair_findroot_block(mp, ri->sc->sa.agno, agbno,
+			be32_to_cpu(btblock->bb_magic), fab->height - 1);
+out:
+	xfs_trans_brelse(ri->sc->tp, bp);
+	return error;
+}
+
+/*
+ * Do any of the blocks in this rmap record match one of the btrees we're
+ * looking for?
+ */
+STATIC int
+xfs_repair_findroot_rmap(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*priv)
+{
+	struct xfs_repair_findroot	*ri = priv;
+	struct xfs_repair_find_ag_btree	*fab;
+	xfs_agblock_t			b;
+	bool				found_it;
+	int				error = 0;
+
+	/* Ignore anything that isn't AG metadata. */
+	if (!XFS_RMAP_NON_INODE_OWNER(rec->rm_owner))
+		return 0;
+
+	/* Otherwise scan each block + btree type. */
+	for (b = 0; b < rec->rm_blockcount; b++) {
+		found_it = false;
+		for (fab = ri->btree_info; fab->buf_ops; fab++) {
+			if (rec->rm_owner != fab->rmap_owner)
+				continue;
+			error = xfs_repair_findroot_block(ri, fab,
+					rec->rm_owner, rec->rm_startblock + b,
+					&found_it);
+			if (error)
+				return error;
+			if (found_it)
+				break;
+		}
+	}
+
+	return 0;
+}
+
+/* Find the roots of the per-AG btrees described in btree_info. */
+int
+xfs_repair_find_ag_btree_roots(
+	struct xfs_scrub_context	*sc,
+	struct xfs_buf			*agf_bp,
+	struct xfs_repair_find_ag_btree	*btree_info,
+	struct xfs_buf			*agfl_bp)
+{
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_repair_findroot	ri;
+	struct xfs_repair_find_ag_btree	*fab;
+	struct xfs_btree_cur		*cur;
+	int				error;
+
+	ASSERT(xfs_buf_islocked(agf_bp));
+	ASSERT(agfl_bp == NULL || xfs_buf_islocked(agfl_bp));
+
+	ri.sc = sc;
+	ri.btree_info = btree_info;
+	ri.agf = XFS_BUF_TO_AGF(agf_bp);
+	ri.agfl_bp = agfl_bp;
+	for (fab = btree_info; fab->buf_ops; fab++) {
+		ASSERT(agfl_bp || fab->rmap_owner != XFS_RMAP_OWN_AG);
+		ASSERT(XFS_RMAP_NON_INODE_OWNER(fab->rmap_owner));
+		fab->root = NULLAGBLOCK;
+		fab->height = 0;
+	}
+
+	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
+	error = xfs_rmap_query_all(cur, xfs_repair_findroot_rmap, &ri);
+	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+
+	return error;
+}
+
+/* Force a quotacheck the next time we mount. */
+void
+xfs_repair_force_quotacheck(
+	struct xfs_scrub_context	*sc,
+	uint				dqtype)
+{
+	uint				flag;
+
+	flag = xfs_quota_chkd_flag(dqtype);
+	if (!(flag & sc->mp->m_qflags))
+		return;
+
+	sc->mp->m_qflags &= ~flag;
+	spin_lock(&sc->mp->m_sb_lock);
+	sc->mp->m_sb.sb_qflags &= ~flag;
+	spin_unlock(&sc->mp->m_sb_lock);
+	xfs_log_sb(sc->tp);
+}
+
+/*
+ * Attach dquots to this inode, or schedule quotacheck to fix them.
+ *
+ * This function ensures that the appropriate dquots are attached to an inode.
+ * We cannot allow the dquot code to allocate an on-disk dquot block here
+ * because we're already in transaction context with the inode locked.  The
+ * on-disk dquot should already exist anyway.  If the quota code signals
+ * corruption or missing quota information, schedule quotacheck, which will
+ * repair corruptions in the quota metadata.
+ */
+int
+xfs_repair_ino_dqattach(
+	struct xfs_scrub_context	*sc)
+{
+	int				error;
+
+	error = xfs_qm_dqattach_locked(sc->ip, false);
+	switch (error) {
+	case -EFSBADCRC:
+	case -EFSCORRUPTED:
+	case -ENOENT:
+		xfs_err_ratelimited(sc->mp,
+"inode %llu repair encountered quota error %d, quotacheck forced.",
+				(unsigned long long)sc->ip->i_ino, error);
+		if (XFS_IS_UQUOTA_ON(sc->mp) && !sc->ip->i_udquot)
+			xfs_repair_force_quotacheck(sc, XFS_DQ_USER);
+		if (XFS_IS_GQUOTA_ON(sc->mp) && !sc->ip->i_gdquot)
+			xfs_repair_force_quotacheck(sc, XFS_DQ_GROUP);
+		if (XFS_IS_PQUOTA_ON(sc->mp) && !sc->ip->i_pdquot)
+			xfs_repair_force_quotacheck(sc, XFS_DQ_PROJ);
+		/* fall through */
+	case -ESRCH:
+		error = 0;
+		break;
+	default:
+		break;
+	}
+
+	return error;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
new file mode 100644
index 000000000000..f2b0895294db
--- /dev/null
+++ b/fs/xfs/scrub/repair.h
@@ -0,0 +1,132 @@
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#ifndef __XFS_SCRUB_REPAIR_H__
+#define __XFS_SCRUB_REPAIR_H__
+
+static inline int xfs_repair_notsupported(struct xfs_scrub_context *sc)
+{
+	return -EOPNOTSUPP;
+}
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+
+/* Repair helpers */
+
+int xfs_repair_attempt(struct xfs_inode *ip, struct xfs_scrub_context *sc,
+		bool *fixed);
+void xfs_repair_failure(struct xfs_mount *mp);
+int xfs_repair_roll_ag_trans(struct xfs_scrub_context *sc);
+bool xfs_repair_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
+		enum xfs_ag_resv_type type);
+xfs_extlen_t xfs_repair_calc_ag_resblks(struct xfs_scrub_context *sc);
+int xfs_repair_alloc_ag_block(struct xfs_scrub_context *sc,
+		struct xfs_owner_info *oinfo, xfs_fsblock_t *fsbno,
+		enum xfs_ag_resv_type resv);
+int xfs_repair_init_btblock(struct xfs_scrub_context *sc, xfs_fsblock_t fsb,
+		struct xfs_buf **bpp, xfs_btnum_t btnum,
+		const struct xfs_buf_ops *ops);
+
+struct xfs_repair_extent {
+	struct list_head		list;
+	xfs_fsblock_t			fsbno;
+	xfs_extlen_t			len;
+};
+
+struct xfs_repair_extent_list {
+	struct list_head		list;
+};
+
+static inline void
+xfs_repair_init_extent_list(
+	struct xfs_repair_extent_list	*exlist)
+{
+	INIT_LIST_HEAD(&exlist->list);
+}
+
+#define for_each_xfs_repair_extent_safe(rbe, n, exlist) \
+	list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
+int xfs_repair_collect_btree_extent(struct xfs_scrub_context *sc,
+		struct xfs_repair_extent_list *btlist, xfs_fsblock_t fsbno,
+		xfs_extlen_t len);
+void xfs_repair_cancel_btree_extents(struct xfs_scrub_context *sc,
+		struct xfs_repair_extent_list *btlist);
+int xfs_repair_subtract_extents(struct xfs_scrub_context *sc,
+		struct xfs_repair_extent_list *exlist,
+		struct xfs_repair_extent_list *sublist);
+int xfs_repair_fix_freelist(struct xfs_scrub_context *sc, bool can_shrink);
+int xfs_repair_invalidate_blocks(struct xfs_scrub_context *sc,
+		struct xfs_repair_extent_list *btlist);
+int xfs_repair_reap_btree_extents(struct xfs_scrub_context *sc,
+		struct xfs_repair_extent_list *exlist,
+		struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
+
+struct xfs_repair_find_ag_btree {
+	/* in: rmap owner of the btree we're looking for */
+	uint64_t			rmap_owner;
+
+	/* in: buffer ops */
+	const struct xfs_buf_ops	*buf_ops;
+
+	/* in: magic number of the btree */
+	uint32_t			magic;
+
+	/* out: the highest btree block found and the tree height */
+	xfs_agblock_t			root;
+	unsigned int			height;
+};
+
+int xfs_repair_find_ag_btree_roots(struct xfs_scrub_context *sc,
+		struct xfs_buf *agf_bp,
+		struct xfs_repair_find_ag_btree *btree_info,
+		struct xfs_buf *agfl_bp);
+void xfs_repair_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype);
+int xfs_repair_ino_dqattach(struct xfs_scrub_context *sc);
+
+/* Metadata repairers */
+
+int xfs_repair_probe(struct xfs_scrub_context *sc);
+int xfs_repair_superblock(struct xfs_scrub_context *sc);
+
+#else
+
+static inline int xfs_repair_attempt(
+	struct xfs_inode		*ip,
+	struct xfs_scrub_context	*sc,
+	bool				*fixed)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void xfs_repair_failure(struct xfs_mount *mp) {}
+
+static inline xfs_extlen_t
+xfs_repair_calc_ag_resblks(
+	struct xfs_scrub_context	*sc)
+{
+	ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
+	return 0;
+}
+
+#define xfs_repair_probe		xfs_repair_notsupported
+#define xfs_repair_superblock		xfs_repair_notsupported
+
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif	/* __XFS_SCRUB_REPAIR_H__ */
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 8f2a7c3ff455..b376a9a77c04 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -66,7 +66,7 @@ xfs_scrub_rmapbt_xref_refc(
 	bool				is_unwritten;
 	int				error;
 
-	if (!sc->sa.refc_cur)
+	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	non_inode = XFS_RMAP_NON_INODE_OWNER(irec->rm_owner);
@@ -207,7 +207,7 @@ xfs_scrub_xref_check_owner(
 	bool				has_rmap;
 	int				error;
 
-	if (!sc->sa.rmap_cur)
+	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	error = xfs_rmap_record_exists(sc->sa.rmap_cur, bno, len, oinfo,
@@ -250,7 +250,7 @@ xfs_scrub_xref_has_no_owner(
 	bool				has_rmap;
 	int				error;
 
-	if (!sc->sa.rmap_cur)
+	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
 		return;
 
 	error = xfs_rmap_has_record(sc->sa.rmap_cur, bno, len, &has_rmap);
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 39c41dfe08ee..40f462a11ea5 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -66,11 +66,15 @@ xfs_scrub_rtbitmap_rec(
 	void				*priv)
 {
 	struct xfs_scrub_context	*sc = priv;
+	xfs_rtblock_t			startblock;
+	xfs_rtblock_t			blockcount;
 
-	if (rec->ar_startblock + rec->ar_blockcount <= rec->ar_startblock ||
-	    !xfs_verify_rtbno(sc->mp, rec->ar_startblock) ||
-	    !xfs_verify_rtbno(sc->mp, rec->ar_startblock +
-			rec->ar_blockcount - 1))
+	startblock = rec->ar_startext * tp->t_mountp->m_sb.sb_rextsize;
+	blockcount = rec->ar_extcount * tp->t_mountp->m_sb.sb_rextsize;
+
+	if (startblock + blockcount <= startblock ||
+	    !xfs_verify_rtbno(sc->mp, startblock) ||
+	    !xfs_verify_rtbno(sc->mp, startblock + blockcount - 1))
 		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 	return 0;
 }
@@ -82,6 +86,11 @@ xfs_scrub_rtbitmap(
 {
 	int				error;
 
+	/* Invoke the fork scrubber. */
+	error = xfs_scrub_metadata_inode_forks(sc);
+	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+		return error;
+
 	error = xfs_rtalloc_query_all(sc->tp, xfs_scrub_rtbitmap_rec, sc);
 	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
@@ -95,8 +104,35 @@ int
 xfs_scrub_rtsummary(
 	struct xfs_scrub_context	*sc)
 {
+	struct xfs_inode		*rsumip = sc->mp->m_rsumip;
+	struct xfs_inode		*old_ip = sc->ip;
+	uint				old_ilock_flags = sc->ilock_flags;
+	int				error = 0;
+
+	/*
+	 * We ILOCK'd the rt bitmap ip in the setup routine, now lock the
+	 * rt summary ip in compliance with the rt inode locking rules.
+	 *
+	 * Since we switch sc->ip to rsumip we have to save the old ilock
+	 * flags so that we don't mix up the inode state that @sc tracks.
+	 */
+	sc->ip = rsumip;
+	sc->ilock_flags = XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM;
+	xfs_ilock(sc->ip, sc->ilock_flags);
+
+	/* Invoke the fork scrubber. */
+	error = xfs_scrub_metadata_inode_forks(sc);
+	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+		goto out;
+
 	/* XXX: implement this some day */
-	return -ENOENT;
+	xfs_scrub_set_incomplete(sc);
+out:
+	/* Switch back to the rtbitmap inode and lock flags. */
+	xfs_iunlock(sc->ip, sc->ilock_flags);
+	sc->ilock_flags = old_ilock_flags;
+	sc->ip = old_ip;
+	return error;
 }
 
 
@@ -107,11 +143,23 @@ xfs_scrub_xref_is_used_rt_space(
 	xfs_rtblock_t			fsbno,
 	xfs_extlen_t			len)
 {
+	xfs_rtblock_t			startext;
+	xfs_rtblock_t			endext;
+	xfs_rtblock_t			extcount;
 	bool				is_free;
 	int				error;
 
+	if (xfs_scrub_skip_xref(sc->sm))
+		return;
+
+	startext = fsbno;
+	endext = fsbno + len - 1;
+	do_div(startext, sc->mp->m_sb.sb_rextsize);
+	if (do_div(endext, sc->mp->m_sb.sb_rextsize))
+		endext++;
+	extcount = endext - startext;
 	xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-	error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, fsbno, len,
+	error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, startext, extcount,
 			&is_free);
 	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
 		goto out_unlock;
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 26c75967a072..36db098ba583 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -42,11 +42,18 @@
 #include "xfs_refcount_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_rmap_btree.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_errortag.h"
+#include "xfs_error.h"
+#include "xfs_log.h"
+#include "xfs_trans_priv.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/btree.h"
+#include "scrub/repair.h"
 
 /*
  * Online Scrub and Repair
@@ -120,6 +127,24 @@
  * XCORRUPT flag; btree query function errors are noted by setting the
  * XFAIL flag and deleting the cursor to prevent further attempts to
  * cross-reference with a defective btree.
+ *
+ * If a piece of metadata proves corrupt or suboptimal, the userspace
+ * program can ask the kernel to apply some tender loving care (TLC) to
+ * the metadata object by setting the REPAIR flag and re-calling the
+ * scrub ioctl.  "Corruption" is defined by metadata violating the
+ * on-disk specification; operations cannot continue if the violation is
+ * left untreated.  It is possible for XFS to continue if an object is
+ * "suboptimal", however performance may be degraded.  Repairs are
+ * usually performed by rebuilding the metadata entirely out of
+ * redundant metadata.  Optimizing, on the other hand, can sometimes be
+ * done without rebuilding entire structures.
+ *
+ * Generally speaking, the repair code has the following code structure:
+ * Lock -> scrub -> repair -> commit -> re-lock -> re-scrub -> unlock.
+ * The first check helps us figure out if we need to rebuild or simply
+ * optimize the structure so that the rebuild knows what to do.  The
+ * second check evaluates the completeness of the repair; that is what
+ * is reported to userspace.
  */
 
 /*
@@ -155,7 +180,10 @@ xfs_scrub_teardown(
 {
 	xfs_scrub_ag_free(sc, &sc->sa);
 	if (sc->tp) {
-		xfs_trans_cancel(sc->tp);
+		if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
+			error = xfs_trans_commit(sc->tp);
+		else
+			xfs_trans_cancel(sc->tp);
 		sc->tp = NULL;
 	}
 	if (sc->ip) {
@@ -166,6 +194,8 @@ xfs_scrub_teardown(
 			iput(VFS_I(sc->ip));
 		sc->ip = NULL;
 	}
+	if (sc->has_quotaofflock)
+		mutex_unlock(&sc->mp->m_quotainfo->qi_quotaofflock);
 	if (sc->buf) {
 		kmem_free(sc->buf);
 		sc->buf = NULL;
@@ -180,126 +210,150 @@ static const struct xfs_scrub_meta_ops meta_scrub_ops[] = {
 		.type	= ST_NONE,
 		.setup	= xfs_scrub_setup_fs,
 		.scrub	= xfs_scrub_probe,
+		.repair = xfs_repair_probe,
 	},
 	[XFS_SCRUB_TYPE_SB] = {		/* superblock */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_fs,
 		.scrub	= xfs_scrub_superblock,
+		.repair	= xfs_repair_superblock,
 	},
 	[XFS_SCRUB_TYPE_AGF] = {	/* agf */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_fs,
 		.scrub	= xfs_scrub_agf,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_AGFL]= {	/* agfl */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_fs,
 		.scrub	= xfs_scrub_agfl,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_AGI] = {	/* agi */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_fs,
 		.scrub	= xfs_scrub_agi,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BNOBT] = {	/* bnobt */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_ag_allocbt,
 		.scrub	= xfs_scrub_bnobt,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_CNTBT] = {	/* cntbt */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_ag_allocbt,
 		.scrub	= xfs_scrub_cntbt,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INOBT] = {	/* inobt */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_ag_iallocbt,
 		.scrub	= xfs_scrub_inobt,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_FINOBT] = {	/* finobt */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_ag_iallocbt,
 		.scrub	= xfs_scrub_finobt,
 		.has	= xfs_sb_version_hasfinobt,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RMAPBT] = {	/* rmapbt */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_ag_rmapbt,
 		.scrub	= xfs_scrub_rmapbt,
 		.has	= xfs_sb_version_hasrmapbt,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_REFCNTBT] = {	/* refcountbt */
 		.type	= ST_PERAG,
 		.setup	= xfs_scrub_setup_ag_refcountbt,
 		.scrub	= xfs_scrub_refcountbt,
 		.has	= xfs_sb_version_hasreflink,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INODE] = {	/* inode record */
 		.type	= ST_INODE,
 		.setup	= xfs_scrub_setup_inode,
 		.scrub	= xfs_scrub_inode,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTD] = {	/* inode data fork */
 		.type	= ST_INODE,
 		.setup	= xfs_scrub_setup_inode_bmap,
 		.scrub	= xfs_scrub_bmap_data,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTA] = {	/* inode attr fork */
 		.type	= ST_INODE,
 		.setup	= xfs_scrub_setup_inode_bmap,
 		.scrub	= xfs_scrub_bmap_attr,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTC] = {	/* inode CoW fork */
 		.type	= ST_INODE,
 		.setup	= xfs_scrub_setup_inode_bmap,
 		.scrub	= xfs_scrub_bmap_cow,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_DIR] = {	/* directory */
 		.type	= ST_INODE,
 		.setup	= xfs_scrub_setup_directory,
 		.scrub	= xfs_scrub_directory,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_XATTR] = {	/* extended attributes */
 		.type	= ST_INODE,
 		.setup	= xfs_scrub_setup_xattr,
 		.scrub	= xfs_scrub_xattr,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_SYMLINK] = {	/* symbolic link */
 		.type	= ST_INODE,
 		.setup	= xfs_scrub_setup_symlink,
 		.scrub	= xfs_scrub_symlink,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PARENT] = {	/* parent pointers */
 		.type	= ST_INODE,
 		.setup	= xfs_scrub_setup_parent,
 		.scrub	= xfs_scrub_parent,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_FS,
 		.setup	= xfs_scrub_setup_rt,
 		.scrub	= xfs_scrub_rtbitmap,
 		.has	= xfs_sb_version_hasrealtime,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_FS,
 		.setup	= xfs_scrub_setup_rt,
 		.scrub	= xfs_scrub_rtsummary,
 		.has	= xfs_sb_version_hasrealtime,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_UQUOTA] = {	/* user quota */
 		.type	= ST_FS,
 		.setup	= xfs_scrub_setup_quota,
 		.scrub	= xfs_scrub_quota,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_GQUOTA] = {	/* group quota */
 		.type	= ST_FS,
 		.setup	= xfs_scrub_setup_quota,
 		.scrub	= xfs_scrub_quota,
+		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PQUOTA] = {	/* project quota */
 		.type	= ST_FS,
 		.setup	= xfs_scrub_setup_quota,
 		.scrub	= xfs_scrub_quota,
+		.repair	= xfs_repair_notsupported,
 	},
 };
 
@@ -379,15 +433,54 @@ xfs_scrub_validate_inputs(
 	if (!xfs_sb_version_hasextflgbit(&mp->m_sb))
 		goto out;
 
-	/* We don't know how to repair anything yet. */
-	if (sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
-		goto out;
+	/*
+	 * We only want to repair read-write v5+ filesystems.  Defer the check
+	 * for ops->repair until after our scrub confirms that we need to
+	 * perform repairs so that we avoid failing due to not supporting
+	 * repairing an object that doesn't need repairs.
+	 */
+	if (sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) {
+		error = -EOPNOTSUPP;
+		if (!xfs_sb_version_hascrc(&mp->m_sb))
+			goto out;
+
+		error = -EROFS;
+		if (mp->m_flags & XFS_MOUNT_RDONLY)
+			goto out;
+	}
 
 	error = 0;
 out:
 	return error;
 }
 
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+{
+	/*
+	 * Userspace asked us to repair something, we repaired it, rescanned
+	 * it, and the rescan says it's still broken.  Scream about this in
+	 * the system logs.
+	 */
+	if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
+	    (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+				 XFS_SCRUB_OFLAG_XCORRUPT)))
+		xfs_repair_failure(sc->mp);
+}
+#else
+static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+{
+	/*
+	 * Userspace asked us to scrub something, it's broken, and we have no
+	 * way of fixing it.  Scream in the logs.
+	 */
+	if (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+				XFS_SCRUB_OFLAG_XCORRUPT))
+		xfs_alert_ratelimited(sc->mp,
+				"Corruption detected during scrub.");
+}
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
 /* Dispatch metadata scrubbing. */
 int
 xfs_scrub_metadata(
@@ -397,6 +490,7 @@ xfs_scrub_metadata(
 	struct xfs_scrub_context	sc;
 	struct xfs_mount		*mp = ip->i_mount;
 	bool				try_harder = false;
+	bool				already_fixed = false;
 	int				error = 0;
 
 	BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
@@ -446,10 +540,44 @@ retry_op:
 	} else if (error)
 		goto out_teardown;
 
-	if (sc.sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
-			       XFS_SCRUB_OFLAG_XCORRUPT))
-		xfs_alert_ratelimited(mp, "Corruption detected during scrub.");
+	if ((sc.sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) && !already_fixed) {
+		bool needs_fix;
+
+		/* Let debug users force us into the repair routines. */
+		if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
+			sc.sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+
+		needs_fix = (sc.sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+						XFS_SCRUB_OFLAG_XCORRUPT |
+						XFS_SCRUB_OFLAG_PREEN));
+		/*
+		 * If userspace asked for a repair but it wasn't necessary,
+		 * report that back to userspace.
+		 */
+		if (!needs_fix) {
+			sc.sm->sm_flags |= XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED;
+			goto out_nofix;
+		}
+
+		/*
+		 * If it's broken, userspace wants us to fix it, and we haven't
+		 * already tried to fix it, then attempt a repair.
+		 */
+		error = xfs_repair_attempt(ip, &sc, &already_fixed);
+		if (error == -EAGAIN) {
+			if (sc.try_harder)
+				try_harder = true;
+			error = xfs_scrub_teardown(&sc, ip, 0);
+			if (error) {
+				xfs_repair_failure(mp);
+				goto out;
+			}
+			goto retry_op;
+		}
+	}
 
+out_nofix:
+	xfs_scrub_postmortem(&sc);
 out_teardown:
 	error = xfs_scrub_teardown(&sc, ip, error);
 out:
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 0d92af86f67a..636424d5e2ee 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -38,6 +38,9 @@ struct xfs_scrub_meta_ops {
 	/* Examine metadata for errors. */
 	int		(*scrub)(struct xfs_scrub_context *);
 
+	/* Repair or optimize the metadata. */
+	int		(*repair)(struct xfs_scrub_context *);
+
 	/* Decide if we even have this piece of metadata. */
 	bool		(*has)(struct xfs_sb *);
 
@@ -48,6 +51,7 @@ struct xfs_scrub_meta_ops {
 /* Buffer pointers and btree cursors for an entire AG. */
 struct xfs_scrub_ag {
 	xfs_agnumber_t			agno;
+	struct xfs_perag		*pag;
 
 	/* AG btree roots */
 	struct xfs_buf			*agf_bp;
@@ -73,6 +77,7 @@ struct xfs_scrub_context {
 	void				*buf;
 	uint				ilock_flags;
 	bool				try_harder;
+	bool				has_quotaofflock;
 
 	/* State tracking for single-AG operations. */
 	struct xfs_scrub_ag		sa;
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 5d2b1c241be5..794d56bb1af8 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -69,6 +69,8 @@ DEFINE_EVENT(xfs_scrub_class, name, \
 DEFINE_SCRUB_EVENT(xfs_scrub_start);
 DEFINE_SCRUB_EVENT(xfs_scrub_done);
 DEFINE_SCRUB_EVENT(xfs_scrub_deadlock_retry);
+DEFINE_SCRUB_EVENT(xfs_repair_attempt);
+DEFINE_SCRUB_EVENT(xfs_repair_done);
 
 TRACE_EVENT(xfs_scrub_op_error,
 	TP_PROTO(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
@@ -492,6 +494,262 @@ TRACE_EVENT(xfs_scrub_xref_error,
 		  __entry->ret_ip)
 );
 
+/* repair tracepoints */
+#if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
+
+DECLARE_EVENT_CLASS(xfs_repair_extent_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 xfs_agblock_t agbno, xfs_extlen_t len),
+	TP_ARGS(mp, agno, agbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->agbno = agbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d agno %u agbno %u len %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len)
+);
+#define DEFINE_REPAIR_EXTENT_EVENT(name) \
+DEFINE_EVENT(xfs_repair_extent_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 xfs_agblock_t agbno, xfs_extlen_t len), \
+	TP_ARGS(mp, agno, agbno, len))
+DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_dispose_btree_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_collect_btree_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_agfl_insert);
+
+DECLARE_EVENT_CLASS(xfs_repair_rmap_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 xfs_agblock_t agbno, xfs_extlen_t len,
+		 uint64_t owner, uint64_t offset, unsigned int flags),
+	TP_ARGS(mp, agno, agbno, len, owner, offset, flags),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->agbno = agbno;
+		__entry->len = len;
+		__entry->owner = owner;
+		__entry->offset = offset;
+		__entry->flags = flags;
+	),
+	TP_printk("dev %d:%d agno %u agbno %u len %u owner %lld offset %llu flags 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len,
+		  __entry->owner,
+		  __entry->offset,
+		  __entry->flags)
+);
+#define DEFINE_REPAIR_RMAP_EVENT(name) \
+DEFINE_EVENT(xfs_repair_rmap_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 xfs_agblock_t agbno, xfs_extlen_t len, \
+		 uint64_t owner, uint64_t offset, unsigned int flags), \
+	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
+DEFINE_REPAIR_RMAP_EVENT(xfs_repair_alloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xfs_repair_ialloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xfs_repair_rmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xfs_repair_bmap_extent_fn);
+
+TRACE_EVENT(xfs_repair_refcount_extent_fn,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 struct xfs_refcount_irec *irec),
+	TP_ARGS(mp, agno, irec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, startblock)
+		__field(xfs_extlen_t, blockcount)
+		__field(xfs_nlink_t, refcount)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->startblock = irec->rc_startblock;
+		__entry->blockcount = irec->rc_blockcount;
+		__entry->refcount = irec->rc_refcount;
+	),
+	TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->startblock,
+		  __entry->blockcount,
+		  __entry->refcount)
+)
+
+TRACE_EVENT(xfs_repair_init_btblock,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
+		 xfs_btnum_t btnum),
+	TP_ARGS(mp, agno, agbno, btnum),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(uint32_t, btnum)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->agbno = agbno;
+		__entry->btnum = btnum;
+	),
+	TP_printk("dev %d:%d agno %u agbno %u btnum %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->btnum)
+)
+TRACE_EVENT(xfs_repair_findroot_block,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
+		 uint32_t magic, uint16_t level),
+	TP_ARGS(mp, agno, agbno, magic, level),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(uint32_t, magic)
+		__field(uint16_t, level)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->agbno = agbno;
+		__entry->magic = magic;
+		__entry->level = level;
+	),
+	TP_printk("dev %d:%d agno %u agbno %u magic 0x%x level %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->magic,
+		  __entry->level)
+)
+TRACE_EVENT(xfs_repair_calc_ag_resblks,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 xfs_agino_t icount, xfs_agblock_t aglen, xfs_agblock_t freelen,
+		 xfs_agblock_t usedlen),
+	TP_ARGS(mp, agno, icount, aglen, freelen, usedlen),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, icount)
+		__field(xfs_agblock_t, aglen)
+		__field(xfs_agblock_t, freelen)
+		__field(xfs_agblock_t, usedlen)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->icount = icount;
+		__entry->aglen = aglen;
+		__entry->freelen = freelen;
+		__entry->usedlen = usedlen;
+	),
+	TP_printk("dev %d:%d agno %d icount %u aglen %u freelen %u usedlen %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->icount,
+		  __entry->aglen,
+		  __entry->freelen,
+		  __entry->usedlen)
+)
+TRACE_EVENT(xfs_repair_calc_ag_resblks_btsize,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 xfs_agblock_t bnobt_sz, xfs_agblock_t inobt_sz,
+		 xfs_agblock_t rmapbt_sz, xfs_agblock_t refcbt_sz),
+	TP_ARGS(mp, agno, bnobt_sz, inobt_sz, rmapbt_sz, refcbt_sz),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, bnobt_sz)
+		__field(xfs_agblock_t, inobt_sz)
+		__field(xfs_agblock_t, rmapbt_sz)
+		__field(xfs_agblock_t, refcbt_sz)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->bnobt_sz = bnobt_sz;
+		__entry->inobt_sz = inobt_sz;
+		__entry->rmapbt_sz = rmapbt_sz;
+		__entry->refcbt_sz = refcbt_sz;
+	),
+	TP_printk("dev %d:%d agno %d bno %u ino %u rmap %u refcount %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->bnobt_sz,
+		  __entry->inobt_sz,
+		  __entry->rmapbt_sz,
+		  __entry->refcbt_sz)
+)
+TRACE_EVENT(xfs_repair_reset_counters,
+	TP_PROTO(struct xfs_mount *mp),
+	TP_ARGS(mp),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+	),
+	TP_printk("dev %d:%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev))
+)
+
+TRACE_EVENT(xfs_repair_ialloc_insert,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 xfs_agino_t startino, uint16_t holemask, uint8_t count,
+		 uint8_t freecount, uint64_t freemask),
+	TP_ARGS(mp, agno, startino, holemask, count, freecount, freemask),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, startino)
+		__field(uint16_t, holemask)
+		__field(uint8_t, count)
+		__field(uint8_t, freecount)
+		__field(uint64_t, freemask)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->startino = startino;
+		__entry->holemask = holemask;
+		__entry->count = count;
+		__entry->freecount = freecount;
+		__entry->freemask = freemask;
+	),
+	TP_printk("dev %d:%d agno %d startino %u holemask 0x%x count %u freecount %u freemask 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->startino,
+		  __entry->holemask,
+		  __entry->count,
+		  __entry->freecount,
+		  __entry->freemask)
+)
+
+#endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
+
 #endif /* _TRACE_XFS_SCRUB_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0ab824f574ed..ca6903726689 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -594,7 +594,7 @@ xfs_alloc_ioend(
 	struct xfs_ioend	*ioend;
 	struct bio		*bio;
 
-	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, xfs_ioend_bioset);
+	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset);
 	xfs_init_bio_from_bh(bio, bh);
 
 	ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
@@ -1378,10 +1378,9 @@ xfs_vm_bmap(
 	struct address_space	*mapping,
 	sector_t		block)
 {
-	struct inode		*inode = (struct inode *)mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_inode	*ip = XFS_I(mapping->host);
 
-	trace_xfs_vm_bmap(XFS_I(inode));
+	trace_xfs_vm_bmap(ip);
 
 	/*
 	 * The swap code (ab-)uses ->bmap to get a block mapping and then
@@ -1394,9 +1393,7 @@ xfs_vm_bmap(
 	 */
 	if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip))
 		return 0;
-
-	filemap_write_and_wait(mapping);
-	return generic_block_bmap(mapping, block, xfs_get_blocks);
+	return iomap_bmap(mapping, block, &xfs_iomap_ops);
 }
 
 STATIC int
@@ -1475,6 +1472,16 @@ xfs_vm_set_page_dirty(
 	return newly_dirty;
 }
 
+static int
+xfs_iomap_swapfile_activate(
+	struct swap_info_struct		*sis,
+	struct file			*swap_file,
+	sector_t			*span)
+{
+	sis->bdev = xfs_find_bdev_for_inode(file_inode(swap_file));
+	return iomap_swapfile_activate(sis, swap_file, span, &xfs_iomap_ops);
+}
+
 const struct address_space_operations xfs_address_space_operations = {
 	.readpage		= xfs_vm_readpage,
 	.readpages		= xfs_vm_readpages,
@@ -1488,6 +1495,7 @@ const struct address_space_operations xfs_address_space_operations = {
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
+	.swap_activate		= xfs_iomap_swapfile_activate,
 };
 
 const struct address_space_operations xfs_dax_aops = {
@@ -1495,4 +1503,5 @@ const struct address_space_operations xfs_dax_aops = {
 	.direct_IO		= noop_direct_IO,
 	.set_page_dirty		= noop_set_page_dirty,
 	.invalidatepage		= noop_invalidatepage,
+	.swap_activate		= xfs_iomap_swapfile_activate,
 };
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 69346d460dfa..694c85b03813 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -18,7 +18,7 @@
 #ifndef __XFS_AOPS_H__
 #define __XFS_AOPS_H__
 
-extern struct bio_set *xfs_ioend_bioset;
+extern struct bio_set xfs_ioend_bioset;
 
 /*
  * Types of I/O for bmap clustering and I/O completion tracking.
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 2203465e63ea..618bb71535c8 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -160,7 +160,7 @@ STATIC void
 xfs_bui_item_unlock(
 	struct xfs_log_item	*lip)
 {
-	if (lip->li_flags & XFS_LI_ABORTED)
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
 		xfs_bui_release(BUI_ITEM(lip));
 }
 
@@ -305,7 +305,7 @@ xfs_bud_item_unlock(
 {
 	struct xfs_bud_log_item	*budp = BUD_ITEM(lip);
 
-	if (lip->li_flags & XFS_LI_ABORTED) {
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
 		xfs_bui_release(budp->bud_buip);
 		kmem_zone_free(xfs_bud_zone, budp);
 	}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 8cd8c412f52d..06badcbadeb4 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -848,7 +848,7 @@ xfs_free_eofblocks(
 		/*
 		 * Attach the dquots to the inode up front.
 		 */
-		error = xfs_qm_dqattach(ip, 0);
+		error = xfs_qm_dqattach(ip);
 		if (error)
 			return error;
 
@@ -871,8 +871,8 @@ xfs_free_eofblocks(
 		 * contents of the file are flushed to disk then the files
 		 * may be full of holes (ie NULL files bug).
 		 */
-		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK,
-					      XFS_ISIZE(ip));
+		error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK,
+					XFS_ISIZE(ip), XFS_BMAPI_NODISCARD);
 		if (error) {
 			/*
 			 * If we get an error at this point we simply don't
@@ -918,7 +918,7 @@ xfs_alloc_file_space(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	error = xfs_qm_dqattach(ip, 0);
+	error = xfs_qm_dqattach(ip);
 	if (error)
 		return error;
 
@@ -1169,7 +1169,7 @@ xfs_free_file_space(
 
 	trace_xfs_free_file_space(ip);
 
-	error = xfs_qm_dqattach(ip, 0);
+	error = xfs_qm_dqattach(ip);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 55661cbdb51b..5179ab9e3d6a 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -549,17 +549,31 @@ xfs_buf_hash_destroy(
 }
 
 /*
- *	Look up, and creates if absent, a lockable buffer for
- *	a given range of an inode.  The buffer is returned
- *	locked.	No I/O is implied by this call.
+ * Look up a buffer in the buffer cache and return it referenced and locked
+ * in @found_bp.
+ *
+ * If @new_bp is supplied and we have a lookup miss, insert @new_bp into the
+ * cache.
+ *
+ * If XBF_TRYLOCK is set in @flags, only try to lock the buffer and return
+ * -EAGAIN if we fail to lock it.
+ *
+ * Return values are:
+ *	-EFSCORRUPTED if have been supplied with an invalid address
+ *	-EAGAIN on trylock failure
+ *	-ENOENT if we fail to find a match and @new_bp was NULL
+ *	0, with @found_bp:
+ *		- @new_bp if we inserted it into the cache
+ *		- the buffer we found and locked.
  */
-xfs_buf_t *
-_xfs_buf_find(
+static int
+xfs_buf_find(
 	struct xfs_buftarg	*btp,
 	struct xfs_buf_map	*map,
 	int			nmaps,
 	xfs_buf_flags_t		flags,
-	xfs_buf_t		*new_bp)
+	struct xfs_buf		*new_bp,
+	struct xfs_buf		**found_bp)
 {
 	struct xfs_perag	*pag;
 	xfs_buf_t		*bp;
@@ -567,6 +581,8 @@ _xfs_buf_find(
 	xfs_daddr_t		eofs;
 	int			i;
 
+	*found_bp = NULL;
+
 	for (i = 0; i < nmaps; i++)
 		cmap.bm_len += map[i].bm_len;
 
@@ -580,16 +596,11 @@ _xfs_buf_find(
 	 */
 	eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks);
 	if (cmap.bm_bn < 0 || cmap.bm_bn >= eofs) {
-		/*
-		 * XXX (dgc): we should really be returning -EFSCORRUPTED here,
-		 * but none of the higher level infrastructure supports
-		 * returning a specific error on buffer lookup failures.
-		 */
 		xfs_alert(btp->bt_mount,
 			  "%s: daddr 0x%llx out of range, EOFS 0x%llx",
 			  __func__, cmap.bm_bn, eofs);
 		WARN_ON(1);
-		return NULL;
+		return -EFSCORRUPTED;
 	}
 
 	pag = xfs_perag_get(btp->bt_mount,
@@ -604,19 +615,20 @@ _xfs_buf_find(
 	}
 
 	/* No match found */
-	if (new_bp) {
-		/* the buffer keeps the perag reference until it is freed */
-		new_bp->b_pag = pag;
-		rhashtable_insert_fast(&pag->pag_buf_hash,
-				       &new_bp->b_rhash_head,
-				       xfs_buf_hash_params);
-		spin_unlock(&pag->pag_buf_lock);
-	} else {
+	if (!new_bp) {
 		XFS_STATS_INC(btp->bt_mount, xb_miss_locked);
 		spin_unlock(&pag->pag_buf_lock);
 		xfs_perag_put(pag);
+		return -ENOENT;
 	}
-	return new_bp;
+
+	/* the buffer keeps the perag reference until it is freed */
+	new_bp->b_pag = pag;
+	rhashtable_insert_fast(&pag->pag_buf_hash, &new_bp->b_rhash_head,
+			       xfs_buf_hash_params);
+	spin_unlock(&pag->pag_buf_lock);
+	*found_bp = new_bp;
+	return 0;
 
 found:
 	spin_unlock(&pag->pag_buf_lock);
@@ -626,7 +638,7 @@ found:
 		if (flags & XBF_TRYLOCK) {
 			xfs_buf_rele(bp);
 			XFS_STATS_INC(btp->bt_mount, xb_busy_locked);
-			return NULL;
+			return -EAGAIN;
 		}
 		xfs_buf_lock(bp);
 		XFS_STATS_INC(btp->bt_mount, xb_get_locked_waited);
@@ -646,6 +658,24 @@ found:
 
 	trace_xfs_buf_find(bp, flags, _RET_IP_);
 	XFS_STATS_INC(btp->bt_mount, xb_get_locked);
+	*found_bp = bp;
+	return 0;
+}
+
+struct xfs_buf *
+xfs_buf_incore(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	struct xfs_buf		*bp;
+	int			error;
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+
+	error = xfs_buf_find(target, &map, 1, flags, NULL, &bp);
+	if (error)
+		return NULL;
 	return bp;
 }
 
@@ -665,9 +695,27 @@ xfs_buf_get_map(
 	struct xfs_buf		*new_bp;
 	int			error = 0;
 
-	bp = _xfs_buf_find(target, map, nmaps, flags, NULL);
-	if (likely(bp))
+	error = xfs_buf_find(target, map, nmaps, flags, NULL, &bp);
+
+	switch (error) {
+	case 0:
+		/* cache hit */
 		goto found;
+	case -EAGAIN:
+		/* cache hit, trylock failure, caller handles failure */
+		ASSERT(flags & XBF_TRYLOCK);
+		return NULL;
+	case -ENOENT:
+		/* cache miss, go for insert */
+		break;
+	case -EFSCORRUPTED:
+	default:
+		/*
+		 * None of the higher layers understand failure types
+		 * yet, so return NULL to signal a fatal lookup error.
+		 */
+		return NULL;
+	}
 
 	new_bp = _xfs_buf_alloc(target, map, nmaps, flags);
 	if (unlikely(!new_bp))
@@ -679,8 +727,8 @@ xfs_buf_get_map(
 		return NULL;
 	}
 
-	bp = _xfs_buf_find(target, map, nmaps, flags, new_bp);
-	if (!bp) {
+	error = xfs_buf_find(target, map, nmaps, flags, new_bp, &bp);
+	if (error) {
 		xfs_buf_free(new_bp);
 		return NULL;
 	}
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index edced162a674..f5f2b71c2fde 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -218,20 +218,9 @@ typedef struct xfs_buf {
 } xfs_buf_t;
 
 /* Finding and Reading Buffers */
-struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target,
-			      struct xfs_buf_map *map, int nmaps,
-			      xfs_buf_flags_t flags, struct xfs_buf *new_bp);
-
-static inline struct xfs_buf *
-xfs_incore(
-	struct xfs_buftarg	*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
-	xfs_buf_flags_t		flags)
-{
-	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
-	return _xfs_buf_find(target, &map, 1, flags, NULL);
-}
+struct xfs_buf *xfs_buf_incore(struct xfs_buftarg *target,
+			   xfs_daddr_t blkno, size_t numblks,
+			   xfs_buf_flags_t flags);
 
 struct xfs_buf *_xfs_buf_alloc(struct xfs_buftarg *target,
 			       struct xfs_buf_map *map, int nmaps,
@@ -358,6 +347,18 @@ extern void xfs_buf_terminate(void);
 
 void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref);
 
+/*
+ * If the buffer is already on the LRU, do nothing. Otherwise set the buffer
+ * up with a reference count of 0 so it will be tossed from the cache when
+ * released.
+ */
+static inline void xfs_buf_oneshot(struct xfs_buf *bp)
+{
+	if (!list_empty(&bp->b_lru) || atomic_read(&bp->b_lru_ref) > 1)
+		return;
+	atomic_set(&bp->b_lru_ref, 0);
+}
+
 static inline int xfs_buf_ispinned(struct xfs_buf *bp)
 {
 	return atomic_read(&bp->b_pin_count);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 82ad270e390e..c2311379d1c3 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -438,7 +438,7 @@ xfs_buf_item_unpin(
 			 * xfs_trans_uncommit() will try to reference the
 			 * buffer which we no longer have a hold on.
 			 */
-			if (lip->li_desc)
+			if (!list_empty(&lip->li_trans))
 				xfs_trans_del_item(lip);
 
 			/*
@@ -568,13 +568,15 @@ xfs_buf_item_unlock(
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
-	bool			aborted = !!(lip->li_flags & XFS_LI_ABORTED);
+	bool			aborted;
 	bool			hold = !!(bip->bli_flags & XFS_BLI_HOLD);
 	bool			dirty = !!(bip->bli_flags & XFS_BLI_DIRTY);
 #if defined(DEBUG) || defined(XFS_WARN)
 	bool			ordered = !!(bip->bli_flags & XFS_BLI_ORDERED);
 #endif
 
+	aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags);
+
 	/* Clear the buffer's association with this transaction. */
 	bp->b_transp = NULL;
 
@@ -743,8 +745,10 @@ xfs_buf_item_init(
 	 * nothing to do here so return.
 	 */
 	ASSERT(bp->b_target->bt_mount == mp);
-	if (bip != NULL) {
+	if (bip) {
 		ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
+		ASSERT(!bp->b_transp);
+		ASSERT(bip->bli_buf == bp);
 		return 0;
 	}
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index a7daef9e16bf..2567391489bd 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -288,49 +288,43 @@ xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp)
 }
 
 /*
- * Allocate a block and fill it with dquots.
- * This is called when the bmapi finds a hole.
+ * Ensure that the given in-core dquot has a buffer on disk backing it, and
+ * return the buffer. This is called when the bmapi finds a hole.
  */
 STATIC int
-xfs_qm_dqalloc(
-	xfs_trans_t	**tpp,
-	xfs_mount_t	*mp,
-	xfs_dquot_t	*dqp,
-	xfs_inode_t	*quotip,
-	xfs_fileoff_t	offset_fsb,
-	xfs_buf_t	**O_bpp)
+xfs_dquot_disk_alloc(
+	struct xfs_trans	**tpp,
+	struct xfs_dquot	*dqp,
+	struct xfs_buf		**bpp)
 {
-	xfs_fsblock_t	firstblock;
-	struct xfs_defer_ops dfops;
-	xfs_bmbt_irec_t map;
-	int		nmaps, error;
-	xfs_buf_t	*bp;
-	xfs_trans_t	*tp = *tpp;
-
-	ASSERT(tp != NULL);
+	struct xfs_bmbt_irec	map;
+	struct xfs_defer_ops	dfops;
+	struct xfs_mount	*mp = (*tpp)->t_mountp;
+	struct xfs_buf		*bp;
+	struct xfs_inode	*quotip = xfs_quota_inode(mp, dqp->dq_flags);
+	xfs_fsblock_t		firstblock;
+	int			nmaps = 1;
+	int			error;
 
 	trace_xfs_dqalloc(dqp);
 
-	/*
-	 * Initialize the bmap freelist prior to calling bmapi code.
-	 */
 	xfs_defer_init(&dfops, &firstblock);
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
-	/*
-	 * Return if this type of quotas is turned off while we didn't
-	 * have an inode lock
-	 */
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
+		/*
+		 * Return if this type of quotas is turned off while we didn't
+		 * have an inode lock
+		 */
 		xfs_iunlock(quotip, XFS_ILOCK_EXCL);
 		return -ESRCH;
 	}
 
-	xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
-	nmaps = 1;
-	error = xfs_bmapi_write(tp, quotip, offset_fsb,
-				XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
-				&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
-				&map, &nmaps, &dfops);
+	/* Create the block mapping. */
+	xfs_trans_ijoin(*tpp, quotip, XFS_ILOCK_EXCL);
+	error = xfs_bmapi_write(*tpp, quotip, dqp->q_fileoffset,
+			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
+			&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
+			&map, &nmaps, &dfops);
 	if (error)
 		goto error0;
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
@@ -344,10 +338,8 @@ xfs_qm_dqalloc(
 	dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
 
 	/* now we can just get the buffer (there's nothing to read yet) */
-	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
-			       dqp->q_blkno,
-			       mp->m_quotainfo->qi_dqchunklen,
-			       0);
+	bp = xfs_trans_get_buf(*tpp, mp->m_ddev_targp, dqp->q_blkno,
+			mp->m_quotainfo->qi_dqchunklen, 0);
 	if (!bp) {
 		error = -ENOMEM;
 		goto error1;
@@ -358,37 +350,45 @@ xfs_qm_dqalloc(
 	 * Make a chunk of dquots out of this buffer and log
 	 * the entire thing.
 	 */
-	xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
+	xfs_qm_init_dquot_blk(*tpp, mp, be32_to_cpu(dqp->q_core.d_id),
 			      dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
+	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
 
 	/*
-	 * xfs_defer_finish() may commit the current transaction and
-	 * start a second transaction if the freelist is not empty.
+	 * Hold the buffer and join it to the dfops so that we'll still own
+	 * the buffer when we return to the caller.  The buffer disposal on
+	 * error must be paid attention to very carefully, as it has been
+	 * broken since commit efa092f3d4c6 "[XFS] Fixes a bug in the quota
+	 * code when allocating a new dquot record" in 2005, and the later
+	 * conversion to xfs_defer_ops in commit 310a75a3c6c747 failed to keep
+	 * the buffer locked across the _defer_finish call.  We can now do
+	 * this correctly with xfs_defer_bjoin.
 	 *
-	 * Since we still want to modify this buffer, we need to
-	 * ensure that the buffer is not released on commit of
-	 * the first transaction and ensure the buffer is added to the
-	 * second transaction.
+	 * Above, we allocated a disk block for the dquot information and
+	 * used get_buf to initialize the dquot.  If the _defer_bjoin fails,
+	 * the buffer is still locked to *tpp, so we must _bhold_release and
+	 * then _trans_brelse the buffer.  If the _defer_finish fails, the old
+	 * transaction is gone but the new buffer is not joined or held to any
+	 * transaction, so we must _buf_relse it.
 	 *
-	 * If there is only one transaction then don't stop the buffer
-	 * from being released when it commits later on.
+	 * If everything succeeds, the caller of this function is returned a
+	 * buffer that is locked and held to the transaction.  The caller
+	 * is responsible for unlocking any buffer passed back, either
+	 * manually or by committing the transaction.
 	 */
-
-	xfs_trans_bhold(tp, bp);
-
+	xfs_trans_bhold(*tpp, bp);
+	error = xfs_defer_bjoin(&dfops, bp);
+	if (error) {
+		xfs_trans_bhold_release(*tpp, bp);
+		xfs_trans_brelse(*tpp, bp);
+		goto error1;
+	}
 	error = xfs_defer_finish(tpp, &dfops);
-	if (error)
+	if (error) {
+		xfs_buf_relse(bp);
 		goto error1;
-
-	/* Transaction was committed? */
-	if (*tpp != tp) {
-		tp = *tpp;
-		xfs_trans_bjoin(tp, bp);
-	} else {
-		xfs_trans_bhold_release(tp, bp);
 	}
-
-	*O_bpp = bp;
+	*bpp = bp;
 	return 0;
 
 error1:
@@ -398,32 +398,24 @@ error0:
 }
 
 /*
- * Maps a dquot to the buffer containing its on-disk version.
- * This returns a ptr to the buffer containing the on-disk dquot
- * in the bpp param, and a ptr to the on-disk dquot within that buffer
+ * Read in the in-core dquot's on-disk metadata and return the buffer.
+ * Returns ENOENT to signal a hole.
  */
 STATIC int
-xfs_qm_dqtobp(
-	xfs_trans_t		**tpp,
-	xfs_dquot_t		*dqp,
-	xfs_disk_dquot_t	**O_ddpp,
-	xfs_buf_t		**O_bpp,
-	uint			flags)
+xfs_dquot_disk_read(
+	struct xfs_mount	*mp,
+	struct xfs_dquot	*dqp,
+	struct xfs_buf		**bpp)
 {
 	struct xfs_bmbt_irec	map;
-	int			nmaps = 1, error;
 	struct xfs_buf		*bp;
-	struct xfs_inode	*quotip;
-	struct xfs_mount	*mp = dqp->q_mount;
-	xfs_dqid_t		id = be32_to_cpu(dqp->q_core.d_id);
-	struct xfs_trans	*tp = (tpp ? *tpp : NULL);
+	struct xfs_inode	*quotip = xfs_quota_inode(mp, dqp->dq_flags);
 	uint			lock_mode;
-
-	quotip = xfs_quota_inode(dqp->q_mount, dqp->dq_flags);
-	dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
+	int			nmaps = 1;
+	int			error;
 
 	lock_mode = xfs_ilock_data_map_shared(quotip);
-	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
+	if (!xfs_this_quota_on(mp, dqp->dq_flags)) {
 		/*
 		 * Return if this type of quotas is turned off while we
 		 * didn't have the quota inode lock.
@@ -436,81 +428,48 @@ xfs_qm_dqtobp(
 	 * Find the block map; no allocations yet
 	 */
 	error = xfs_bmapi_read(quotip, dqp->q_fileoffset,
-			       XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0);
-
+			XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0);
 	xfs_iunlock(quotip, lock_mode);
 	if (error)
 		return error;
 
 	ASSERT(nmaps == 1);
-	ASSERT(map.br_blockcount == 1);
+	ASSERT(map.br_blockcount >= 1);
+	ASSERT(map.br_startblock != DELAYSTARTBLOCK);
+	if (map.br_startblock == HOLESTARTBLOCK)
+		return -ENOENT;
+
+	trace_xfs_dqtobp_read(dqp);
 
 	/*
-	 * Offset of dquot in the (fixed sized) dquot chunk.
+	 * store the blkno etc so that we don't have to do the
+	 * mapping all the time
 	 */
-	dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) *
-		sizeof(xfs_dqblk_t);
-
-	ASSERT(map.br_startblock != DELAYSTARTBLOCK);
-	if (map.br_startblock == HOLESTARTBLOCK) {
-		/*
-		 * We don't allocate unless we're asked to
-		 */
-		if (!(flags & XFS_QMOPT_DQALLOC))
-			return -ENOENT;
-
-		ASSERT(tp);
-		error = xfs_qm_dqalloc(tpp, mp, dqp, quotip,
-					dqp->q_fileoffset, &bp);
-		if (error)
-			return error;
-		tp = *tpp;
-	} else {
-		trace_xfs_dqtobp_read(dqp);
+	dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
 
-		/*
-		 * store the blkno etc so that we don't have to do the
-		 * mapping all the time
-		 */
-		dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
-
-		error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-					   dqp->q_blkno,
-					   mp->m_quotainfo->qi_dqchunklen,
-					   0, &bp, &xfs_dquot_buf_ops);
-		if (error) {
-			ASSERT(bp == NULL);
-			return error;
-		}
+	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
+			mp->m_quotainfo->qi_dqchunklen, 0, &bp,
+			&xfs_dquot_buf_ops);
+	if (error) {
+		ASSERT(bp == NULL);
+		return error;
 	}
 
 	ASSERT(xfs_buf_islocked(bp));
-	*O_bpp = bp;
-	*O_ddpp = bp->b_addr + dqp->q_bufoffset;
+	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
+	*bpp = bp;
 
 	return 0;
 }
 
-
-/*
- * Read in the ondisk dquot using dqtobp() then copy it to an incore version,
- * and release the buffer immediately.
- *
- * If XFS_QMOPT_DQALLOC is set, allocate a dquot on disk if it needed.
- */
-int
-xfs_qm_dqread(
+/* Allocate and initialize everything we need for an incore dquot. */
+STATIC struct xfs_dquot *
+xfs_dquot_alloc(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type,
-	uint			flags,
-	struct xfs_dquot	**O_dqpp)
+	uint			type)
 {
 	struct xfs_dquot	*dqp;
-	struct xfs_disk_dquot	*ddqp;
-	struct xfs_buf		*bp;
-	struct xfs_trans	*tp = NULL;
-	int			error;
 
 	dqp = kmem_zone_zalloc(xfs_qm_dqzone, KM_SLEEP);
 
@@ -520,6 +479,12 @@ xfs_qm_dqread(
 	INIT_LIST_HEAD(&dqp->q_lru);
 	mutex_init(&dqp->q_qlock);
 	init_waitqueue_head(&dqp->q_pinwait);
+	dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
+	/*
+	 * Offset of dquot in the (fixed sized) dquot chunk.
+	 */
+	dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) *
+			sizeof(xfs_dqblk_t);
 
 	/*
 	 * Because we want to use a counting completion, complete
@@ -548,35 +513,22 @@ xfs_qm_dqread(
 		break;
 	}
 
-	XFS_STATS_INC(mp, xs_qm_dquot);
-
-	trace_xfs_dqread(dqp);
+	xfs_qm_dquot_logitem_init(dqp);
 
-	if (flags & XFS_QMOPT_DQALLOC) {
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc,
-				XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
-		if (error)
-			goto error0;
-	}
+	XFS_STATS_INC(mp, xs_qm_dquot);
+	return dqp;
+}
 
-	/*
-	 * get a pointer to the on-disk dquot and the buffer containing it
-	 * dqp already knows its own type (GROUP/USER).
-	 */
-	error = xfs_qm_dqtobp(&tp, dqp, &ddqp, &bp, flags);
-	if (error) {
-		/*
-		 * This can happen if quotas got turned off (ESRCH),
-		 * or if the dquot didn't exist on disk and we ask to
-		 * allocate (ENOENT).
-		 */
-		trace_xfs_dqread_fail(dqp);
-		goto error1;
-	}
+/* Copy the in-core quota fields in from the on-disk buffer. */
+STATIC void
+xfs_dquot_from_disk(
+	struct xfs_dquot	*dqp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_disk_dquot	*ddqp = bp->b_addr + dqp->q_bufoffset;
 
 	/* copy everything from disk dquot to the incore dquot */
 	memcpy(&dqp->q_core, ddqp, sizeof(xfs_disk_dquot_t));
-	xfs_qm_dquot_logitem_init(dqp);
 
 	/*
 	 * Reservation counters are defined as reservation plus current usage
@@ -588,40 +540,90 @@ xfs_qm_dqread(
 
 	/* initialize the dquot speculative prealloc thresholds */
 	xfs_dquot_set_prealloc_limits(dqp);
+}
 
-	/* Mark the buf so that this will stay incore a little longer */
-	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
+/* Allocate and initialize the dquot buffer for this in-core dquot. */
+static int
+xfs_qm_dqread_alloc(
+	struct xfs_mount	*mp,
+	struct xfs_dquot	*dqp,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_trans	*tp;
+	struct xfs_buf		*bp;
+	int			error;
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc,
+			XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
+	if (error)
+		goto err;
+
+	error = xfs_dquot_disk_alloc(&tp, dqp, &bp);
+	if (error)
+		goto err_cancel;
+
+	error = xfs_trans_commit(tp);
+	if (error) {
+		/*
+		 * Buffer was held to the transaction, so we have to unlock it
+		 * manually here because we're not passing it back.
+		 */
+		xfs_buf_relse(bp);
+		goto err;
+	}
+	*bpp = bp;
+	return 0;
+
+err_cancel:
+	xfs_trans_cancel(tp);
+err:
+	return error;
+}
+
+/*
+ * Read in the ondisk dquot using dqtobp() then copy it to an incore version,
+ * and release the buffer immediately.  If @can_alloc is true, fill any
+ * holes in the on-disk metadata.
+ */
+static int
+xfs_qm_dqread(
+	struct xfs_mount	*mp,
+	xfs_dqid_t		id,
+	uint			type,
+	bool			can_alloc,
+	struct xfs_dquot	**dqpp)
+{
+	struct xfs_dquot	*dqp;
+	struct xfs_buf		*bp;
+	int			error;
+
+	dqp = xfs_dquot_alloc(mp, id, type);
+	trace_xfs_dqread(dqp);
+
+	/* Try to read the buffer, allocating if necessary. */
+	error = xfs_dquot_disk_read(mp, dqp, &bp);
+	if (error == -ENOENT && can_alloc)
+		error = xfs_qm_dqread_alloc(mp, dqp, &bp);
+	if (error)
+		goto err;
 
 	/*
-	 * We got the buffer with a xfs_trans_read_buf() (in dqtobp())
-	 * So we need to release with xfs_trans_brelse().
-	 * The strategy here is identical to that of inodes; we lock
-	 * the dquot in xfs_qm_dqget() before making it accessible to
-	 * others. This is because dquots, like inodes, need a good level of
-	 * concurrency, and we don't want to take locks on the entire buffers
-	 * for dquot accesses.
-	 * Note also that the dquot buffer may even be dirty at this point, if
-	 * this particular dquot was repaired. We still aren't afraid to
-	 * brelse it because we have the changes incore.
+	 * At this point we should have a clean locked buffer.  Copy the data
+	 * to the incore dquot and release the buffer since the incore dquot
+	 * has its own locking protocol so we needn't tie up the buffer any
+	 * further.
 	 */
 	ASSERT(xfs_buf_islocked(bp));
-	xfs_trans_brelse(tp, bp);
+	xfs_dquot_from_disk(dqp, bp);
 
-	if (tp) {
-		error = xfs_trans_commit(tp);
-		if (error)
-			goto error0;
-	}
-
-	*O_dqpp = dqp;
+	xfs_buf_relse(bp);
+	*dqpp = dqp;
 	return error;
 
-error1:
-	if (tp)
-		xfs_trans_cancel(tp);
-error0:
+err:
+	trace_xfs_dqread_fail(dqp);
 	xfs_qm_dqdestroy(dqp);
-	*O_dqpp = NULL;
+	*dqpp = NULL;
 	return error;
 }
 
@@ -679,77 +681,230 @@ xfs_dq_get_next_id(
 }
 
 /*
- * Given the file system, inode OR id, and type (UDQUOT/GDQUOT), return a
- * a locked dquot, doing an allocation (if requested) as needed.
- * When both an inode and an id are given, the inode's id takes precedence.
- * That is, if the id changes while we don't hold the ilock inside this
- * function, the new dquot is returned, not necessarily the one requested
- * in the id argument.
+ * Look up the dquot in the in-core cache.  If found, the dquot is returned
+ * locked and ready to go.
+ */
+static struct xfs_dquot *
+xfs_qm_dqget_cache_lookup(
+	struct xfs_mount	*mp,
+	struct xfs_quotainfo	*qi,
+	struct radix_tree_root	*tree,
+	xfs_dqid_t		id)
+{
+	struct xfs_dquot	*dqp;
+
+restart:
+	mutex_lock(&qi->qi_tree_lock);
+	dqp = radix_tree_lookup(tree, id);
+	if (!dqp) {
+		mutex_unlock(&qi->qi_tree_lock);
+		XFS_STATS_INC(mp, xs_qm_dqcachemisses);
+		return NULL;
+	}
+
+	xfs_dqlock(dqp);
+	if (dqp->dq_flags & XFS_DQ_FREEING) {
+		xfs_dqunlock(dqp);
+		mutex_unlock(&qi->qi_tree_lock);
+		trace_xfs_dqget_freeing(dqp);
+		delay(1);
+		goto restart;
+	}
+
+	dqp->q_nrefs++;
+	mutex_unlock(&qi->qi_tree_lock);
+
+	trace_xfs_dqget_hit(dqp);
+	XFS_STATS_INC(mp, xs_qm_dqcachehits);
+	return dqp;
+}
+
+/*
+ * Try to insert a new dquot into the in-core cache.  If an error occurs the
+ * caller should throw away the dquot and start over.  Otherwise, the dquot
+ * is returned locked (and held by the cache) as if there had been a cache
+ * hit.
+ */
+static int
+xfs_qm_dqget_cache_insert(
+	struct xfs_mount	*mp,
+	struct xfs_quotainfo	*qi,
+	struct radix_tree_root	*tree,
+	xfs_dqid_t		id,
+	struct xfs_dquot	*dqp)
+{
+	int			error;
+
+	mutex_lock(&qi->qi_tree_lock);
+	error = radix_tree_insert(tree, id, dqp);
+	if (unlikely(error)) {
+		/* Duplicate found!  Caller must try again. */
+		WARN_ON(error != -EEXIST);
+		mutex_unlock(&qi->qi_tree_lock);
+		trace_xfs_dqget_dup(dqp);
+		return error;
+	}
+
+	/* Return a locked dquot to the caller, with a reference taken. */
+	xfs_dqlock(dqp);
+	dqp->q_nrefs = 1;
+
+	qi->qi_dquots++;
+	mutex_unlock(&qi->qi_tree_lock);
+
+	return 0;
+}
+
+/* Check our input parameters. */
+static int
+xfs_qm_dqget_checks(
+	struct xfs_mount	*mp,
+	uint			type)
+{
+	if (WARN_ON_ONCE(!XFS_IS_QUOTA_RUNNING(mp)))
+		return -ESRCH;
+
+	switch (type) {
+	case XFS_DQ_USER:
+		if (!XFS_IS_UQUOTA_ON(mp))
+			return -ESRCH;
+		return 0;
+	case XFS_DQ_GROUP:
+		if (!XFS_IS_GQUOTA_ON(mp))
+			return -ESRCH;
+		return 0;
+	case XFS_DQ_PROJ:
+		if (!XFS_IS_PQUOTA_ON(mp))
+			return -ESRCH;
+		return 0;
+	default:
+		WARN_ON_ONCE(0);
+		return -EINVAL;
+	}
+}
+
+/*
+ * Given the file system, id, and type (UDQUOT/GDQUOT), return a a locked
+ * dquot, doing an allocation (if requested) as needed.
  */
 int
 xfs_qm_dqget(
-	xfs_mount_t	*mp,
-	xfs_inode_t	*ip,	  /* locked inode (optional) */
-	xfs_dqid_t	id,	  /* uid/projid/gid depending on type */
-	uint		type,	  /* XFS_DQ_USER/XFS_DQ_PROJ/XFS_DQ_GROUP */
-	uint		flags,	  /* DQALLOC, DQSUSER, DQREPAIR, DOWARN */
-	xfs_dquot_t	**O_dqpp) /* OUT : locked incore dquot */
+	struct xfs_mount	*mp,
+	xfs_dqid_t		id,
+	uint			type,
+	bool			can_alloc,
+	struct xfs_dquot	**O_dqpp)
 {
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
-	struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
+	struct radix_tree_root	*tree = xfs_dquot_tree(qi, type);
 	struct xfs_dquot	*dqp;
 	int			error;
 
-	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
-	if ((! XFS_IS_UQUOTA_ON(mp) && type == XFS_DQ_USER) ||
-	    (! XFS_IS_PQUOTA_ON(mp) && type == XFS_DQ_PROJ) ||
-	    (! XFS_IS_GQUOTA_ON(mp) && type == XFS_DQ_GROUP)) {
-		return -ESRCH;
+	error = xfs_qm_dqget_checks(mp, type);
+	if (error)
+		return error;
+
+restart:
+	dqp = xfs_qm_dqget_cache_lookup(mp, qi, tree, id);
+	if (dqp) {
+		*O_dqpp = dqp;
+		return 0;
 	}
 
-	ASSERT(type == XFS_DQ_USER ||
-	       type == XFS_DQ_PROJ ||
-	       type == XFS_DQ_GROUP);
-	if (ip) {
-		ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-		ASSERT(xfs_inode_dquot(ip, type) == NULL);
+	error = xfs_qm_dqread(mp, id, type, can_alloc, &dqp);
+	if (error)
+		return error;
+
+	error = xfs_qm_dqget_cache_insert(mp, qi, tree, id, dqp);
+	if (error) {
+		/*
+		 * Duplicate found. Just throw away the new dquot and start
+		 * over.
+		 */
+		xfs_qm_dqdestroy(dqp);
+		XFS_STATS_INC(mp, xs_qm_dquot_dups);
+		goto restart;
 	}
 
-restart:
-	mutex_lock(&qi->qi_tree_lock);
-	dqp = radix_tree_lookup(tree, id);
-	if (dqp) {
-		xfs_dqlock(dqp);
-		if (dqp->dq_flags & XFS_DQ_FREEING) {
-			xfs_dqunlock(dqp);
-			mutex_unlock(&qi->qi_tree_lock);
-			trace_xfs_dqget_freeing(dqp);
-			delay(1);
-			goto restart;
-		}
+	trace_xfs_dqget_miss(dqp);
+	*O_dqpp = dqp;
+	return 0;
+}
 
-		/* uninit / unused quota found in radix tree, keep looking  */
-		if (flags & XFS_QMOPT_DQNEXT) {
-			if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
-				xfs_dqunlock(dqp);
-				mutex_unlock(&qi->qi_tree_lock);
-				error = xfs_dq_get_next_id(mp, type, &id);
-				if (error)
-					return error;
-				goto restart;
-			}
-		}
+/*
+ * Given a dquot id and type, read and initialize a dquot from the on-disk
+ * metadata.  This function is only for use during quota initialization so
+ * it ignores the dquot cache assuming that the dquot shrinker isn't set up.
+ * The caller is responsible for _qm_dqdestroy'ing the returned dquot.
+ */
+int
+xfs_qm_dqget_uncached(
+	struct xfs_mount	*mp,
+	xfs_dqid_t		id,
+	uint			type,
+	struct xfs_dquot	**dqpp)
+{
+	int			error;
 
-		dqp->q_nrefs++;
-		mutex_unlock(&qi->qi_tree_lock);
+	error = xfs_qm_dqget_checks(mp, type);
+	if (error)
+		return error;
+
+	return xfs_qm_dqread(mp, id, type, 0, dqpp);
+}
+
+/* Return the quota id for a given inode and type. */
+xfs_dqid_t
+xfs_qm_id_for_quotatype(
+	struct xfs_inode	*ip,
+	uint			type)
+{
+	switch (type) {
+	case XFS_DQ_USER:
+		return ip->i_d.di_uid;
+	case XFS_DQ_GROUP:
+		return ip->i_d.di_gid;
+	case XFS_DQ_PROJ:
+		return xfs_get_projid(ip);
+	}
+	ASSERT(0);
+	return 0;
+}
+
+/*
+ * Return the dquot for a given inode and type.  If @can_alloc is true, then
+ * allocate blocks if needed.  The inode's ILOCK must be held and it must not
+ * have already had an inode attached.
+ */
+int
+xfs_qm_dqget_inode(
+	struct xfs_inode	*ip,
+	uint			type,
+	bool			can_alloc,
+	struct xfs_dquot	**O_dqpp)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	struct radix_tree_root	*tree = xfs_dquot_tree(qi, type);
+	struct xfs_dquot	*dqp;
+	xfs_dqid_t		id;
+	int			error;
 
-		trace_xfs_dqget_hit(dqp);
-		XFS_STATS_INC(mp, xs_qm_dqcachehits);
+	error = xfs_qm_dqget_checks(mp, type);
+	if (error)
+		return error;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(xfs_inode_dquot(ip, type) == NULL);
+
+	id = xfs_qm_id_for_quotatype(ip, type);
+
+restart:
+	dqp = xfs_qm_dqget_cache_lookup(mp, qi, tree, id);
+	if (dqp) {
 		*O_dqpp = dqp;
 		return 0;
 	}
-	mutex_unlock(&qi->qi_tree_lock);
-	XFS_STATS_INC(mp, xs_qm_dqcachemisses);
 
 	/*
 	 * Dquot cache miss. We don't want to keep the inode lock across
@@ -758,87 +913,81 @@ restart:
 	 * lock here means dealing with a chown that can happen before
 	 * we re-acquire the lock.
 	 */
-	if (ip)
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-	error = xfs_qm_dqread(mp, id, type, flags, &dqp);
-
-	if (ip)
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-	/* If we are asked to find next active id, keep looking */
-	if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) {
-		error = xfs_dq_get_next_id(mp, type, &id);
-		if (!error)
-			goto restart;
-	}
-
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	error = xfs_qm_dqread(mp, id, type, can_alloc, &dqp);
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	if (error)
 		return error;
 
-	if (ip) {
-		/*
-		 * A dquot could be attached to this inode by now, since
-		 * we had dropped the ilock.
-		 */
-		if (xfs_this_quota_on(mp, type)) {
-			struct xfs_dquot	*dqp1;
-
-			dqp1 = xfs_inode_dquot(ip, type);
-			if (dqp1) {
-				xfs_qm_dqdestroy(dqp);
-				dqp = dqp1;
-				xfs_dqlock(dqp);
-				goto dqret;
-			}
-		} else {
-			/* inode stays locked on return */
+	/*
+	 * A dquot could be attached to this inode by now, since we had
+	 * dropped the ilock.
+	 */
+	if (xfs_this_quota_on(mp, type)) {
+		struct xfs_dquot	*dqp1;
+
+		dqp1 = xfs_inode_dquot(ip, type);
+		if (dqp1) {
 			xfs_qm_dqdestroy(dqp);
-			return -ESRCH;
+			dqp = dqp1;
+			xfs_dqlock(dqp);
+			goto dqret;
 		}
+	} else {
+		/* inode stays locked on return */
+		xfs_qm_dqdestroy(dqp);
+		return -ESRCH;
 	}
 
-	mutex_lock(&qi->qi_tree_lock);
-	error = radix_tree_insert(tree, id, dqp);
-	if (unlikely(error)) {
-		WARN_ON(error != -EEXIST);
-
+	error = xfs_qm_dqget_cache_insert(mp, qi, tree, id, dqp);
+	if (error) {
 		/*
 		 * Duplicate found. Just throw away the new dquot and start
 		 * over.
 		 */
-		mutex_unlock(&qi->qi_tree_lock);
-		trace_xfs_dqget_dup(dqp);
 		xfs_qm_dqdestroy(dqp);
 		XFS_STATS_INC(mp, xs_qm_dquot_dups);
 		goto restart;
 	}
 
-	/*
-	 * We return a locked dquot to the caller, with a reference taken
-	 */
-	xfs_dqlock(dqp);
-	dqp->q_nrefs = 1;
+dqret:
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	trace_xfs_dqget_miss(dqp);
+	*O_dqpp = dqp;
+	return 0;
+}
 
-	qi->qi_dquots++;
-	mutex_unlock(&qi->qi_tree_lock);
+/*
+ * Starting at @id and progressing upwards, look for an initialized incore
+ * dquot, lock it, and return it.
+ */
+int
+xfs_qm_dqget_next(
+	struct xfs_mount	*mp,
+	xfs_dqid_t		id,
+	uint			type,
+	struct xfs_dquot	**dqpp)
+{
+	struct xfs_dquot	*dqp;
+	int			error = 0;
 
-	/* If we are asked to find next active id, keep looking */
-	if (flags & XFS_QMOPT_DQNEXT) {
-		if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
-			xfs_qm_dqput(dqp);
-			error = xfs_dq_get_next_id(mp, type, &id);
-			if (error)
-				return error;
-			goto restart;
+	*dqpp = NULL;
+	for (; !error; error = xfs_dq_get_next_id(mp, type, &id)) {
+		error = xfs_qm_dqget(mp, id, type, false, &dqp);
+		if (error == -ENOENT)
+			continue;
+		else if (error != 0)
+			break;
+
+		if (!XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
+			*dqpp = dqp;
+			return 0;
 		}
+
+		xfs_qm_dqput(dqp);
 	}
 
- dqret:
-	ASSERT((ip == NULL) || xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	trace_xfs_dqget_miss(dqp);
-	*O_dqpp = dqp;
-	return 0;
+	return error;
 }
 
 /*
@@ -913,9 +1062,9 @@ xfs_qm_dqflush_done(
 	 * since it's cheaper, and then we recheck while
 	 * holding the lock before removing the dquot from the AIL.
 	 */
-	if ((lip->li_flags & XFS_LI_IN_AIL) &&
+	if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) &&
 	    ((lip->li_lsn == qip->qli_flush_lsn) ||
-	     (lip->li_flags & XFS_LI_FAILED))) {
+	     test_bit(XFS_LI_FAILED, &lip->li_flags))) {
 
 		/* xfs_trans_ail_delete() drops the AIL lock. */
 		spin_lock(&ailp->ail_lock);
@@ -926,8 +1075,7 @@ xfs_qm_dqflush_done(
 			 * Clear the failed state since we are about to drop the
 			 * flush lock
 			 */
-			if (lip->li_flags & XFS_LI_FAILED)
-				xfs_clear_li_failed(lip);
+			xfs_clear_li_failed(lip);
 			spin_unlock(&ailp->ail_lock);
 		}
 	}
@@ -953,6 +1101,7 @@ xfs_qm_dqflush(
 {
 	struct xfs_mount	*mp = dqp->q_mount;
 	struct xfs_buf		*bp;
+	struct xfs_dqblk	*dqb;
 	struct xfs_disk_dquot	*ddqp;
 	xfs_failaddr_t		fa;
 	int			error;
@@ -996,12 +1145,13 @@ xfs_qm_dqflush(
 	/*
 	 * Calculate the location of the dquot inside the buffer.
 	 */
-	ddqp = bp->b_addr + dqp->q_bufoffset;
+	dqb = bp->b_addr + dqp->q_bufoffset;
+	ddqp = &dqb->dd_diskdq;
 
 	/*
-	 * A simple sanity check in case we got a corrupted dquot..
+	 * A simple sanity check in case we got a corrupted dquot.
 	 */
-	fa = xfs_dquot_verify(mp, &dqp->q_core, be32_to_cpu(ddqp->d_id), 0, 0);
+	fa = xfs_dqblk_verify(mp, dqb, be32_to_cpu(ddqp->d_id), 0);
 	if (fa) {
 		xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS",
 				be32_to_cpu(ddqp->d_id), fa);
@@ -1032,8 +1182,6 @@ xfs_qm_dqflush(
 	 * of a dquot without an up-to-date CRC getting to disk.
 	 */
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
-		struct xfs_dqblk *dqb = (struct xfs_dqblk *)ddqp;
-
 		dqb->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn);
 		xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
 				 XFS_DQUOT_CRC_OFF);
@@ -1119,3 +1267,35 @@ xfs_qm_exit(void)
 	kmem_zone_destroy(xfs_qm_dqtrxzone);
 	kmem_zone_destroy(xfs_qm_dqzone);
 }
+
+/*
+ * Iterate every dquot of a particular type.  The caller must ensure that the
+ * particular quota type is active.  iter_fn can return negative error codes,
+ * or XFS_BTREE_QUERY_RANGE_ABORT to indicate that it wants to stop iterating.
+ */
+int
+xfs_qm_dqiterate(
+	struct xfs_mount	*mp,
+	uint			dqtype,
+	xfs_qm_dqiterate_fn	iter_fn,
+	void			*priv)
+{
+	struct xfs_dquot	*dq;
+	xfs_dqid_t		id = 0;
+	int			error;
+
+	do {
+		error = xfs_qm_dqget_next(mp, id, dqtype, &dq);
+		if (error == -ENOENT)
+			return 0;
+		if (error)
+			return error;
+
+		error = iter_fn(dq, dqtype, priv);
+		id = be32_to_cpu(dq->q_core.d_id);
+		xfs_qm_dqput(dq);
+		id++;
+	} while (error == 0 && id != 0);
+
+	return error;
+}
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 2f536f33cd26..bdd6bd921528 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -160,8 +160,6 @@ static inline bool xfs_dquot_lowsp(struct xfs_dquot *dqp)
 #define XFS_QM_ISPDQ(dqp)	((dqp)->dq_flags & XFS_DQ_PROJ)
 #define XFS_QM_ISGDQ(dqp)	((dqp)->dq_flags & XFS_DQ_GROUP)
 
-extern int		xfs_qm_dqread(struct xfs_mount *, xfs_dqid_t, uint,
-					uint, struct xfs_dquot	**);
 extern void		xfs_qm_dqdestroy(xfs_dquot_t *);
 extern int		xfs_qm_dqflush(struct xfs_dquot *, struct xfs_buf **);
 extern void		xfs_qm_dqunpin_wait(xfs_dquot_t *);
@@ -169,8 +167,19 @@ extern void		xfs_qm_adjust_dqtimers(xfs_mount_t *,
 					xfs_disk_dquot_t *);
 extern void		xfs_qm_adjust_dqlimits(struct xfs_mount *,
 					       struct xfs_dquot *);
-extern int		xfs_qm_dqget(xfs_mount_t *, xfs_inode_t *,
-					xfs_dqid_t, uint, uint, xfs_dquot_t **);
+extern xfs_dqid_t	xfs_qm_id_for_quotatype(struct xfs_inode *ip,
+					uint type);
+extern int		xfs_qm_dqget(struct xfs_mount *mp, xfs_dqid_t id,
+					uint type, bool can_alloc,
+					struct xfs_dquot **dqpp);
+extern int		xfs_qm_dqget_inode(struct xfs_inode *ip, uint type,
+					bool can_alloc,
+					struct xfs_dquot **dqpp);
+extern int		xfs_qm_dqget_next(struct xfs_mount *mp, xfs_dqid_t id,
+					uint type, struct xfs_dquot **dqpp);
+extern int		xfs_qm_dqget_uncached(struct xfs_mount *mp,
+					xfs_dqid_t id, uint type,
+					struct xfs_dquot **dqpp);
 extern void		xfs_qm_dqput(xfs_dquot_t *);
 
 extern void		xfs_dqlock2(struct xfs_dquot *, struct xfs_dquot *);
@@ -185,4 +194,9 @@ static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
 	return dqp;
 }
 
+typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq, uint dqtype,
+		void *priv);
+int xfs_qm_dqiterate(struct xfs_mount *mp, uint dqtype,
+		xfs_qm_dqiterate_fn iter_fn, void *priv);
+
 #endif /* __XFS_DQUOT_H__ */
diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 4b331e354da7..8eb7415474d6 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -173,7 +173,7 @@ xfs_qm_dquot_logitem_push(
 	 * The buffer containing this item failed to be written back
 	 * previously. Resubmit the buffer for IO
 	 */
-	if (lip->li_flags & XFS_LI_FAILED) {
+	if (test_bit(XFS_LI_FAILED, &lip->li_flags)) {
 		if (!xfs_buf_trylock(bp))
 			return XFS_ITEM_LOCKED;
 
@@ -209,10 +209,7 @@ xfs_qm_dquot_logitem_push(
 	spin_unlock(&lip->li_ailp->ail_lock);
 
 	error = xfs_qm_dqflush(dqp, &bp);
-	if (error) {
-		xfs_warn(dqp->q_mount, "%s: push error %d on dqp "PTR_FMT,
-			__func__, error, dqp);
-	} else {
+	if (!error) {
 		if (!xfs_buf_delwri_queue(bp, buffer_list))
 			rval = XFS_ITEM_FLUSHING;
 		xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index a63f5083f497..7975634cb8fe 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -61,6 +61,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_LOG_BAD_CRC,
 	XFS_RANDOM_LOG_ITEM_PIN,
 	XFS_RANDOM_BUF_LRU_REF,
+	XFS_RANDOM_FORCE_SCRUB_REPAIR,
 };
 
 struct xfs_errortag_attr {
@@ -167,6 +168,7 @@ XFS_ERRORTAG_ATTR_RW(drop_writes,	XFS_ERRTAG_DROP_WRITES);
 XFS_ERRORTAG_ATTR_RW(log_bad_crc,	XFS_ERRTAG_LOG_BAD_CRC);
 XFS_ERRORTAG_ATTR_RW(log_item_pin,	XFS_ERRTAG_LOG_ITEM_PIN);
 XFS_ERRORTAG_ATTR_RW(buf_lru_ref,	XFS_ERRTAG_BUF_LRU_REF);
+XFS_ERRORTAG_ATTR_RW(force_repair,	XFS_ERRTAG_FORCE_SCRUB_REPAIR);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -201,6 +203,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(log_bad_crc),
 	XFS_ERRORTAG_ATTR_LIST(log_item_pin),
 	XFS_ERRORTAG_ATTR_LIST(buf_lru_ref),
+	XFS_ERRORTAG_ATTR_LIST(force_repair),
 	NULL,
 };
 
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index b5b1e567b9f4..a889b550979a 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -168,7 +168,7 @@ STATIC void
 xfs_efi_item_unlock(
 	struct xfs_log_item	*lip)
 {
-	if (lip->li_flags & XFS_LI_ABORTED)
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
 		xfs_efi_release(EFI_ITEM(lip));
 }
 
@@ -402,7 +402,7 @@ xfs_efd_item_unlock(
 {
 	struct xfs_efd_log_item	*efdp = EFD_ITEM(lip);
 
-	if (lip->li_flags & XFS_LI_ABORTED) {
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
 		xfs_efi_release(efdp->efd_efip);
 		xfs_efd_item_free(efdp);
 	}
@@ -542,7 +542,7 @@ xfs_efi_recover(
 	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
 		extp = &efip->efi_format.efi_extents[i];
 		error = xfs_trans_free_extent(tp, efdp, extp->ext_start,
-					      extp->ext_len, &oinfo);
+					      extp->ext_len, &oinfo, false);
 		if (error)
 			goto abort_error;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 299aee4b7b0b..0e3fb8978344 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -414,6 +414,12 @@ xfs_dio_write_end_io(
 	if (size <= 0)
 		return size;
 
+	/*
+	 * Capture amount written on completion as we can't reliably account
+	 * for it on submission.
+	 */
+	XFS_STATS_ADD(ip->i_mount, xs_write_bytes, size);
+
 	if (flags & IOMAP_DIO_COW) {
 		error = xfs_reflink_end_cow(ip, offset, size);
 		if (error)
@@ -599,7 +605,16 @@ xfs_file_dax_write(
 	}
 out:
 	xfs_iunlock(ip, iolock);
-	return error ? error : ret;
+	if (error)
+		return error;
+
+	if (ret > 0) {
+		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
+
+		/* Handle various SYNC-type writes */
+		ret = generic_write_sync(iocb, ret);
+	}
+	return ret;
 }
 
 STATIC ssize_t
@@ -669,6 +684,12 @@ write_retry:
 out:
 	if (iolock)
 		xfs_iunlock(ip, iolock);
+
+	if (ret > 0) {
+		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
+		/* Handle various SYNC-type writes */
+		ret = generic_write_sync(iocb, ret);
+	}
 	return ret;
 }
 
@@ -693,8 +714,9 @@ xfs_file_write_iter(
 		return -EIO;
 
 	if (IS_DAX(inode))
-		ret = xfs_file_dax_write(iocb, from);
-	else if (iocb->ki_flags & IOCB_DIRECT) {
+		return xfs_file_dax_write(iocb, from);
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
 		/*
 		 * Allow a directio write to fall back to a buffered
 		 * write *only* in the case that we're doing a reflink
@@ -702,20 +724,11 @@ xfs_file_write_iter(
 		 * allow an operation to fall back to buffered mode.
 		 */
 		ret = xfs_file_dio_aio_write(iocb, from);
-		if (ret == -EREMCHG)
-			goto buffered;
-	} else {
-buffered:
-		ret = xfs_file_buffered_aio_write(iocb, from);
+		if (ret != -EREMCHG)
+			return ret;
 	}
 
-	if (ret > 0) {
-		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
-
-		/* Handle various SYNC-type writes */
-		ret = generic_write_sync(iocb, ret);
-	}
-	return ret;
+	return xfs_file_buffered_aio_write(iocb, from);
 }
 
 #define	XFS_FALLOC_FL_SUPPORTED						\
@@ -778,22 +791,26 @@ xfs_file_fallocate(
 		if (error)
 			goto out_unlock;
 	} else if (mode & FALLOC_FL_INSERT_RANGE) {
-		unsigned int blksize_mask = i_blocksize(inode) - 1;
+		unsigned int	blksize_mask = i_blocksize(inode) - 1;
+		loff_t		isize = i_size_read(inode);
 
-		new_size = i_size_read(inode) + len;
 		if (offset & blksize_mask || len & blksize_mask) {
 			error = -EINVAL;
 			goto out_unlock;
 		}
 
-		/* check the new inode size does not wrap through zero */
-		if (new_size > inode->i_sb->s_maxbytes) {
+		/*
+		 * New inode size must not exceed ->s_maxbytes, accounting for
+		 * possible signed overflow.
+		 */
+		if (inode->i_sb->s_maxbytes - isize < len) {
 			error = -EFBIG;
 			goto out_unlock;
 		}
+		new_size = isize + len;
 
 		/* Offset should be less than i_size */
-		if (offset >= i_size_read(inode)) {
+		if (offset >= isize) {
 			error = -EINVAL;
 			goto out_unlock;
 		}
@@ -876,8 +893,18 @@ xfs_file_dedupe_range(
 	struct file	*dst_file,
 	u64		dst_loff)
 {
+	struct inode	*srci = file_inode(src_file);
+	u64		max_dedupe;
 	int		error;
 
+	/*
+	 * Since we have to read all these pages in to compare them, cut
+	 * it off at MAX_RW_COUNT/2 rounded down to the nearest block.
+	 * That means we won't do more than MAX_RW_COUNT IO per request.
+	 */
+	max_dedupe = (MAX_RW_COUNT >> 1) & ~(i_blocksize(srci) - 1);
+	if (len > max_dedupe)
+		len = max_dedupe;
 	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
 				     len, true);
 	if (error)
@@ -993,7 +1020,7 @@ xfs_file_llseek(
  *       page_lock (MM)
  *         i_lock (XFS - extent map serialisation)
  */
-static int
+static vm_fault_t
 __xfs_filemap_fault(
 	struct vm_fault		*vmf,
 	enum page_entry_size	pe_size,
@@ -1001,7 +1028,7 @@ __xfs_filemap_fault(
 {
 	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
-	int			ret;
+	vm_fault_t		ret;
 
 	trace_xfs_filemap_fault(ip, pe_size, write_fault);
 
@@ -1030,7 +1057,7 @@ __xfs_filemap_fault(
 	return ret;
 }
 
-static int
+static vm_fault_t
 xfs_filemap_fault(
 	struct vm_fault		*vmf)
 {
@@ -1040,7 +1067,7 @@ xfs_filemap_fault(
 			(vmf->flags & FAULT_FLAG_WRITE));
 }
 
-static int
+static vm_fault_t
 xfs_filemap_huge_fault(
 	struct vm_fault		*vmf,
 	enum page_entry_size	pe_size)
@@ -1053,7 +1080,7 @@ xfs_filemap_huge_fault(
 			(vmf->flags & FAULT_FLAG_WRITE));
 }
 
-static int
+static vm_fault_t
 xfs_filemap_page_mkwrite(
 	struct vm_fault		*vmf)
 {
@@ -1065,7 +1092,7 @@ xfs_filemap_page_mkwrite(
  * on write faults. In reality, it needs to serialise against truncate and
  * prepare memory for writing so handle is as standard write fault.
  */
-static int
+static vm_fault_t
 xfs_filemap_pfn_mkwrite(
 	struct vm_fault		*vmf)
 {
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 43cfc07996a4..0299febece9c 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -465,10 +465,9 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 	struct xfs_rmap_irec		irec;
 	xfs_daddr_t			rec_daddr;
 
-	rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock);
-
-	irec.rm_startblock = rec->ar_startblock;
-	irec.rm_blockcount = rec->ar_blockcount;
+	irec.rm_startblock = rec->ar_startext * mp->m_sb.sb_rextsize;
+	rec_daddr = XFS_FSB_TO_BB(mp, irec.rm_startblock);
+	irec.rm_blockcount = rec->ar_extcount * mp->m_sb.sb_rextsize;
 	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
 	irec.rm_offset = 0;
 	irec.rm_flags = 0;
@@ -534,8 +533,11 @@ xfs_getfsmap_rtdev_rtbitmap_query(
 
 	xfs_ilock(tp->t_mountp->m_rbmip, XFS_ILOCK_SHARED);
 
-	alow.ar_startblock = info->low.rm_startblock;
-	ahigh.ar_startblock = info->high.rm_startblock;
+	alow.ar_startext = info->low.rm_startblock;
+	ahigh.ar_startext = info->high.rm_startblock;
+	do_div(alow.ar_startext, tp->t_mountp->m_sb.sb_rextsize);
+	if (do_div(ahigh.ar_startext, tp->t_mountp->m_sb.sb_rextsize))
+		ahigh.ar_startext++;
 	error = xfs_rtalloc_query_range(tp, &alow, &ahigh,
 			xfs_getfsmap_rtdev_rtbitmap_helper, info);
 	if (error)
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 523792768080..bc7ef18da243 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -24,85 +24,42 @@
 #include "xfs_sb.h"
 #include "xfs_mount.h"
 #include "xfs_defer.h"
-#include "xfs_da_format.h"
-#include "xfs_da_btree.h"
-#include "xfs_inode.h"
 #include "xfs_trans.h"
-#include "xfs_inode_item.h"
 #include "xfs_error.h"
 #include "xfs_btree.h"
-#include "xfs_alloc_btree.h"
 #include "xfs_alloc.h"
-#include "xfs_rmap_btree.h"
-#include "xfs_ialloc.h"
 #include "xfs_fsops.h"
-#include "xfs_itable.h"
 #include "xfs_trans_space.h"
 #include "xfs_rtalloc.h"
 #include "xfs_trace.h"
 #include "xfs_log.h"
-#include "xfs_filestream.h"
-#include "xfs_rmap.h"
+#include "xfs_ag.h"
 #include "xfs_ag_resv.h"
 
 /*
- * File system operations
+ * growfs operations
  */
-
-static struct xfs_buf *
-xfs_growfs_get_hdr_buf(
-	struct xfs_mount	*mp,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
-	int			flags,
-	const struct xfs_buf_ops *ops)
-{
-	struct xfs_buf		*bp;
-
-	bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
-	if (!bp)
-		return NULL;
-
-	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
-	bp->b_bn = blkno;
-	bp->b_maps[0].bm_bn = blkno;
-	bp->b_ops = ops;
-
-	return bp;
-}
-
 static int
 xfs_growfs_data_private(
 	xfs_mount_t		*mp,		/* mount point for filesystem */
 	xfs_growfs_data_t	*in)		/* growfs data input struct */
 {
-	xfs_agf_t		*agf;
-	struct xfs_agfl		*agfl;
-	xfs_agi_t		*agi;
-	xfs_agnumber_t		agno;
-	xfs_extlen_t		agsize;
-	xfs_extlen_t		tmpsize;
-	xfs_alloc_rec_t		*arec;
 	xfs_buf_t		*bp;
-	int			bucket;
-	int			dpct;
-	int			error, saved_error = 0;
+	int			error;
 	xfs_agnumber_t		nagcount;
 	xfs_agnumber_t		nagimax = 0;
 	xfs_rfsblock_t		nb, nb_mod;
 	xfs_rfsblock_t		new;
-	xfs_rfsblock_t		nfree;
 	xfs_agnumber_t		oagcount;
-	int			pct;
 	xfs_trans_t		*tp;
+	LIST_HEAD		(buffer_list);
+	struct aghdr_init_data	id = {};
 
 	nb = in->newblocks;
-	pct = in->imaxpct;
-	if (nb < mp->m_sb.sb_dblocks || pct < 0 || pct > 100)
+	if (nb < mp->m_sb.sb_dblocks)
 		return -EINVAL;
 	if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
 		return error;
-	dpct = pct - mp->m_sb.sb_imax_pct;
 	error = xfs_buf_read_uncached(mp->m_ddev_targp,
 				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
 				XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
@@ -135,376 +92,45 @@ xfs_growfs_data_private(
 		return error;
 
 	/*
-	 * Write new AG headers to disk. Non-transactional, but written
-	 * synchronously so they are completed prior to the growfs transaction
-	 * being logged.
+	 * Write new AG headers to disk. Non-transactional, but need to be
+	 * written and completed prior to the growfs transaction being logged.
+	 * To do this, we use a delayed write buffer list and wait for
+	 * submission and IO completion of the list as a whole. This allows the
+	 * IO subsystem to merge all the AG headers in a single AG into a single
+	 * IO and hide most of the latency of the IO from us.
+	 *
+	 * This also means that if we get an error whilst building the buffer
+	 * list to write, we can cancel the entire list without having written
+	 * anything.
 	 */
-	nfree = 0;
-	for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
-		__be32	*agfl_bno;
-
-		/*
-		 * AG freespace header block
-		 */
-		bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
-				XFS_FSS_TO_BB(mp, 1), 0,
-				&xfs_agf_buf_ops);
-		if (!bp) {
-			error = -ENOMEM;
-			goto error0;
-		}
-
-		agf = XFS_BUF_TO_AGF(bp);
-		agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
-		agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
-		agf->agf_seqno = cpu_to_be32(agno);
-		if (agno == nagcount - 1)
-			agsize =
-				nb -
-				(agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
+	INIT_LIST_HEAD(&id.buffer_list);
+	for (id.agno = nagcount - 1;
+	     id.agno >= oagcount;
+	     id.agno--, new -= id.agsize) {
+
+		if (id.agno == nagcount - 1)
+			id.agsize = nb -
+				(id.agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
 		else
-			agsize = mp->m_sb.sb_agblocks;
-		agf->agf_length = cpu_to_be32(agsize);
-		agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
-		agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
-		agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
-		agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
-		if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
-			agf->agf_roots[XFS_BTNUM_RMAPi] =
-						cpu_to_be32(XFS_RMAP_BLOCK(mp));
-			agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
-			agf->agf_rmap_blocks = cpu_to_be32(1);
-		}
-
-		agf->agf_flfirst = cpu_to_be32(1);
-		agf->agf_fllast = 0;
-		agf->agf_flcount = 0;
-		tmpsize = agsize - mp->m_ag_prealloc_blocks;
-		agf->agf_freeblks = cpu_to_be32(tmpsize);
-		agf->agf_longest = cpu_to_be32(tmpsize);
-		if (xfs_sb_version_hascrc(&mp->m_sb))
-			uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
-		if (xfs_sb_version_hasreflink(&mp->m_sb)) {
-			agf->agf_refcount_root = cpu_to_be32(
-					xfs_refc_block(mp));
-			agf->agf_refcount_level = cpu_to_be32(1);
-			agf->agf_refcount_blocks = cpu_to_be32(1);
-		}
-
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-		if (error)
-			goto error0;
-
-		/*
-		 * AG freelist header block
-		 */
-		bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
-				XFS_FSS_TO_BB(mp, 1), 0,
-				&xfs_agfl_buf_ops);
-		if (!bp) {
-			error = -ENOMEM;
-			goto error0;
-		}
-
-		agfl = XFS_BUF_TO_AGFL(bp);
-		if (xfs_sb_version_hascrc(&mp->m_sb)) {
-			agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
-			agfl->agfl_seqno = cpu_to_be32(agno);
-			uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
-		}
-
-		agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
-		for (bucket = 0; bucket < xfs_agfl_size(mp); bucket++)
-			agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
-
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-		if (error)
-			goto error0;
-
-		/*
-		 * AG inode header block
-		 */
-		bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
-				XFS_FSS_TO_BB(mp, 1), 0,
-				&xfs_agi_buf_ops);
-		if (!bp) {
-			error = -ENOMEM;
-			goto error0;
-		}
-
-		agi = XFS_BUF_TO_AGI(bp);
-		agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
-		agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
-		agi->agi_seqno = cpu_to_be32(agno);
-		agi->agi_length = cpu_to_be32(agsize);
-		agi->agi_count = 0;
-		agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp));
-		agi->agi_level = cpu_to_be32(1);
-		agi->agi_freecount = 0;
-		agi->agi_newino = cpu_to_be32(NULLAGINO);
-		agi->agi_dirino = cpu_to_be32(NULLAGINO);
-		if (xfs_sb_version_hascrc(&mp->m_sb))
-			uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
-		if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
-			agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
-			agi->agi_free_level = cpu_to_be32(1);
-		}
-		for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
-			agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
-
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-		if (error)
-			goto error0;
+			id.agsize = mp->m_sb.sb_agblocks;
 
-		/*
-		 * BNO btree root block
-		 */
-		bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
-				BTOBB(mp->m_sb.sb_blocksize), 0,
-				&xfs_allocbt_buf_ops);
-
-		if (!bp) {
-			error = -ENOMEM;
-			goto error0;
-		}
-
-		xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, agno, 0);
-
-		arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
-		arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
-		arec->ar_blockcount = cpu_to_be32(
-			agsize - be32_to_cpu(arec->ar_startblock));
-
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-		if (error)
-			goto error0;
-
-		/*
-		 * CNT btree root block
-		 */
-		bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
-				BTOBB(mp->m_sb.sb_blocksize), 0,
-				&xfs_allocbt_buf_ops);
-		if (!bp) {
-			error = -ENOMEM;
-			goto error0;
-		}
-
-		xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, agno, 0);
-
-		arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
-		arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
-		arec->ar_blockcount = cpu_to_be32(
-			agsize - be32_to_cpu(arec->ar_startblock));
-		nfree += be32_to_cpu(arec->ar_blockcount);
-
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-		if (error)
-			goto error0;
-
-		/* RMAP btree root block */
-		if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
-			struct xfs_rmap_rec	*rrec;
-			struct xfs_btree_block	*block;
-
-			bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AGB_TO_DADDR(mp, agno, XFS_RMAP_BLOCK(mp)),
-				BTOBB(mp->m_sb.sb_blocksize), 0,
-				&xfs_rmapbt_buf_ops);
-			if (!bp) {
-				error = -ENOMEM;
-				goto error0;
-			}
-
-			xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 0,
-						agno, 0);
-			block = XFS_BUF_TO_BLOCK(bp);
-
-
-			/*
-			 * mark the AG header regions as static metadata The BNO
-			 * btree block is the first block after the headers, so
-			 * it's location defines the size of region the static
-			 * metadata consumes.
-			 *
-			 * Note: unlike mkfs, we never have to account for log
-			 * space when growing the data regions
-			 */
-			rrec = XFS_RMAP_REC_ADDR(block, 1);
-			rrec->rm_startblock = 0;
-			rrec->rm_blockcount = cpu_to_be32(XFS_BNO_BLOCK(mp));
-			rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_FS);
-			rrec->rm_offset = 0;
-			be16_add_cpu(&block->bb_numrecs, 1);
-
-			/* account freespace btree root blocks */
-			rrec = XFS_RMAP_REC_ADDR(block, 2);
-			rrec->rm_startblock = cpu_to_be32(XFS_BNO_BLOCK(mp));
-			rrec->rm_blockcount = cpu_to_be32(2);
-			rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
-			rrec->rm_offset = 0;
-			be16_add_cpu(&block->bb_numrecs, 1);
-
-			/* account inode btree root blocks */
-			rrec = XFS_RMAP_REC_ADDR(block, 3);
-			rrec->rm_startblock = cpu_to_be32(XFS_IBT_BLOCK(mp));
-			rrec->rm_blockcount = cpu_to_be32(XFS_RMAP_BLOCK(mp) -
-							XFS_IBT_BLOCK(mp));
-			rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_INOBT);
-			rrec->rm_offset = 0;
-			be16_add_cpu(&block->bb_numrecs, 1);
-
-			/* account for rmap btree root */
-			rrec = XFS_RMAP_REC_ADDR(block, 4);
-			rrec->rm_startblock = cpu_to_be32(XFS_RMAP_BLOCK(mp));
-			rrec->rm_blockcount = cpu_to_be32(1);
-			rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
-			rrec->rm_offset = 0;
-			be16_add_cpu(&block->bb_numrecs, 1);
-
-			/* account for refc btree root */
-			if (xfs_sb_version_hasreflink(&mp->m_sb)) {
-				rrec = XFS_RMAP_REC_ADDR(block, 5);
-				rrec->rm_startblock = cpu_to_be32(
-						xfs_refc_block(mp));
-				rrec->rm_blockcount = cpu_to_be32(1);
-				rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC);
-				rrec->rm_offset = 0;
-				be16_add_cpu(&block->bb_numrecs, 1);
-			}
-
-			error = xfs_bwrite(bp);
-			xfs_buf_relse(bp);
-			if (error)
-				goto error0;
-		}
-
-		/*
-		 * INO btree root block
-		 */
-		bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
-				BTOBB(mp->m_sb.sb_blocksize), 0,
-				&xfs_inobt_buf_ops);
-		if (!bp) {
-			error = -ENOMEM;
-			goto error0;
-		}
-
-		xfs_btree_init_block(mp, bp, XFS_BTNUM_INO , 0, 0, agno, 0);
-
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-		if (error)
-			goto error0;
-
-		/*
-		 * FINO btree root block
-		 */
-		if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
-			bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AGB_TO_DADDR(mp, agno, XFS_FIBT_BLOCK(mp)),
-				BTOBB(mp->m_sb.sb_blocksize), 0,
-				&xfs_inobt_buf_ops);
-			if (!bp) {
-				error = -ENOMEM;
-				goto error0;
-			}
-
-			xfs_btree_init_block(mp, bp, XFS_BTNUM_FINO,
-						     0, 0, agno, 0);
-
-			error = xfs_bwrite(bp);
-			xfs_buf_relse(bp);
-			if (error)
-				goto error0;
-		}
-
-		/*
-		 * refcount btree root block
-		 */
-		if (xfs_sb_version_hasreflink(&mp->m_sb)) {
-			bp = xfs_growfs_get_hdr_buf(mp,
-				XFS_AGB_TO_DADDR(mp, agno, xfs_refc_block(mp)),
-				BTOBB(mp->m_sb.sb_blocksize), 0,
-				&xfs_refcountbt_buf_ops);
-			if (!bp) {
-				error = -ENOMEM;
-				goto error0;
-			}
-
-			xfs_btree_init_block(mp, bp, XFS_BTNUM_REFC,
-					     0, 0, agno, 0);
-
-			error = xfs_bwrite(bp);
-			xfs_buf_relse(bp);
-			if (error)
-				goto error0;
-		}
-	}
-	xfs_trans_agblocks_delta(tp, nfree);
-	/*
-	 * There are new blocks in the old last a.g.
-	 */
-	if (new) {
-		struct xfs_owner_info	oinfo;
-
-		/*
-		 * Change the agi length.
-		 */
-		error = xfs_ialloc_read_agi(mp, tp, agno, &bp);
-		if (error) {
-			goto error0;
-		}
-		ASSERT(bp);
-		agi = XFS_BUF_TO_AGI(bp);
-		be32_add_cpu(&agi->agi_length, new);
-		ASSERT(nagcount == oagcount ||
-		       be32_to_cpu(agi->agi_length) == mp->m_sb.sb_agblocks);
-		xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH);
-		/*
-		 * Change agf length.
-		 */
-		error = xfs_alloc_read_agf(mp, tp, agno, 0, &bp);
+		error = xfs_ag_init_headers(mp, &id);
 		if (error) {
-			goto error0;
+			xfs_buf_delwri_cancel(&id.buffer_list);
+			goto out_trans_cancel;
 		}
-		ASSERT(bp);
-		agf = XFS_BUF_TO_AGF(bp);
-		be32_add_cpu(&agf->agf_length, new);
-		ASSERT(be32_to_cpu(agf->agf_length) ==
-		       be32_to_cpu(agi->agi_length));
+	}
+	error = xfs_buf_delwri_submit(&id.buffer_list);
+	if (error)
+		goto out_trans_cancel;
 
-		xfs_alloc_log_agf(tp, bp, XFS_AGF_LENGTH);
+	xfs_trans_agblocks_delta(tp, id.nfree);
 
-		/*
-		 * Free the new space.
-		 *
-		 * XFS_RMAP_OWN_NULL is used here to tell the rmap btree that
-		 * this doesn't actually exist in the rmap btree.
-		 */
-		xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL);
-		error = xfs_rmap_free(tp, bp, agno,
-				be32_to_cpu(agf->agf_length) - new,
-				new, &oinfo);
-		if (error)
-			goto error0;
-		error = xfs_free_extent(tp,
-				XFS_AGB_TO_FSB(mp, agno,
-					be32_to_cpu(agf->agf_length) - new),
-				new, &oinfo, XFS_AG_RESV_NONE);
+	/* If there are new blocks in the old last AG, extend it. */
+	if (new) {
+		error = xfs_ag_extend_space(mp, tp, &id, new);
 		if (error)
-			goto error0;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -517,10 +143,8 @@ xfs_growfs_data_private(
 	if (nb > mp->m_sb.sb_dblocks)
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS,
 				 nb - mp->m_sb.sb_dblocks);
-	if (nfree)
-		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, nfree);
-	if (dpct)
-		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
+	if (id.nfree)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree);
 	xfs_trans_set_sync(tp);
 	error = xfs_trans_commit(tp);
 	if (error)
@@ -529,12 +153,6 @@ xfs_growfs_data_private(
 	/* New allocation groups fully initialized, so update mount struct */
 	if (nagimax)
 		mp->m_maxagi = nagimax;
-	if (mp->m_sb.sb_imax_pct) {
-		uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
-		do_div(icount, 100);
-		mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
-	} else
-		mp->m_maxicount = 0;
 	xfs_set_low_space_thresholds(mp);
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
 
@@ -545,73 +163,24 @@ xfs_growfs_data_private(
 	if (new) {
 		struct xfs_perag	*pag;
 
-		pag = xfs_perag_get(mp, agno);
+		pag = xfs_perag_get(mp, id.agno);
 		error = xfs_ag_resv_free(pag);
 		xfs_perag_put(pag);
 		if (error)
-			goto out;
+			return error;
 	}
 
-	/* Reserve AG metadata blocks. */
+	/*
+	 * Reserve AG metadata blocks. ENOSPC here does not mean there was a
+	 * growfs failure, just that there still isn't space for new user data
+	 * after the grow has been run.
+	 */
 	error = xfs_fs_reserve_ag_blocks(mp);
-	if (error && error != -ENOSPC)
-		goto out;
-
-	/* update secondary superblocks. */
-	for (agno = 1; agno < nagcount; agno++) {
+	if (error == -ENOSPC)
 		error = 0;
-		/*
-		 * new secondary superblocks need to be zeroed, not read from
-		 * disk as the contents of the new area we are growing into is
-		 * completely unknown.
-		 */
-		if (agno < oagcount) {
-			error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
-				  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
-				  XFS_FSS_TO_BB(mp, 1), 0, &bp,
-				  &xfs_sb_buf_ops);
-		} else {
-			bp = xfs_trans_get_buf(NULL, mp->m_ddev_targp,
-				  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
-				  XFS_FSS_TO_BB(mp, 1), 0);
-			if (bp) {
-				bp->b_ops = &xfs_sb_buf_ops;
-				xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
-			} else
-				error = -ENOMEM;
-		}
-
-		/*
-		 * If we get an error reading or writing alternate superblocks,
-		 * continue.  xfs_repair chooses the "best" superblock based
-		 * on most matches; if we break early, we'll leave more
-		 * superblocks un-updated than updated, and xfs_repair may
-		 * pick them over the properly-updated primary.
-		 */
-		if (error) {
-			xfs_warn(mp,
-		"error %d reading secondary superblock for ag %d",
-				error, agno);
-			saved_error = error;
-			continue;
-		}
-		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
-
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-		if (error) {
-			xfs_warn(mp,
-		"write error %d updating secondary superblock for ag %d",
-				error, agno);
-			saved_error = error;
-			continue;
-		}
-	}
-
- out:
-	return saved_error ? saved_error : error;
+	return error;
 
- error0:
+out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -638,25 +207,71 @@ xfs_growfs_log_private(
 	return -ENOSYS;
 }
 
+static int
+xfs_growfs_imaxpct(
+	struct xfs_mount	*mp,
+	__u32			imaxpct)
+{
+	struct xfs_trans	*tp;
+	int			dpct;
+	int			error;
+
+	if (imaxpct > 100)
+		return -EINVAL;
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
+			XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+	if (error)
+		return error;
+
+	dpct = imaxpct - mp->m_sb.sb_imax_pct;
+	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
+	xfs_trans_set_sync(tp);
+	return xfs_trans_commit(tp);
+}
+
 /*
  * protected versions of growfs function acquire and release locks on the mount
  * point - exported through ioctls: XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG,
  * XFS_IOC_FSGROWFSRT
  */
-
-
 int
 xfs_growfs_data(
-	xfs_mount_t		*mp,
-	xfs_growfs_data_t	*in)
+	struct xfs_mount	*mp,
+	struct xfs_growfs_data	*in)
 {
-	int error;
+	int			error = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	if (!mutex_trylock(&mp->m_growlock))
 		return -EWOULDBLOCK;
-	error = xfs_growfs_data_private(mp, in);
+
+	/* update imaxpct separately to the physical grow of the filesystem */
+	if (in->imaxpct != mp->m_sb.sb_imax_pct) {
+		error = xfs_growfs_imaxpct(mp, in->imaxpct);
+		if (error)
+			goto out_error;
+	}
+
+	if (in->newblocks != mp->m_sb.sb_dblocks) {
+		error = xfs_growfs_data_private(mp, in);
+		if (error)
+			goto out_error;
+	}
+
+	/* Post growfs calculations needed to reflect new state in operations */
+	if (mp->m_sb.sb_imax_pct) {
+		uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
+		do_div(icount, 100);
+		mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
+	} else
+		mp->m_maxicount = 0;
+
+	/* Update secondary superblocks now the physical grow has completed */
+	error = xfs_update_secondary_sbs(mp);
+
+out_error:
 	/*
 	 * Increment the generation unconditionally, the error could be from
 	 * updating the secondary superblocks, in which case the new size
diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 3e1cc3001bcb..fdde17a2333c 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -47,6 +47,7 @@ xfs_param_t xfs_params = {
 
 struct xfs_globals xfs_globals = {
 	.log_recovery_delay	=	0,	/* no delay by default */
+	.mount_delay		=	0,	/* no delay by default */
 #ifdef XFS_ASSERT_FATAL
 	.bug_on_assert		=	true,	/* assert failures BUG() */
 #else
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 9a18f69f6e96..164350d91efc 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -107,7 +107,8 @@ xfs_inode_free_callback(
 		xfs_idestroy_fork(ip, XFS_COW_FORK);
 
 	if (ip->i_itemp) {
-		ASSERT(!(ip->i_itemp->ili_item.li_flags & XFS_LI_IN_AIL));
+		ASSERT(!test_bit(XFS_LI_IN_AIL,
+				 &ip->i_itemp->ili_item.li_flags));
 		xfs_inode_item_destroy(ip);
 		ip->i_itemp = NULL;
 	}
@@ -309,6 +310,46 @@ xfs_reinit_inode(
 }
 
 /*
+ * If we are allocating a new inode, then check what was returned is
+ * actually a free, empty inode. If we are not allocating an inode,
+ * then check we didn't find a free inode.
+ *
+ * Returns:
+ *	0		if the inode free state matches the lookup context
+ *	-ENOENT		if the inode is free and we are not allocating
+ *	-EFSCORRUPTED	if there is any state mismatch at all
+ */
+static int
+xfs_iget_check_free_state(
+	struct xfs_inode	*ip,
+	int			flags)
+{
+	if (flags & XFS_IGET_CREATE) {
+		/* should be a free inode */
+		if (VFS_I(ip)->i_mode != 0) {
+			xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)",
+				ip->i_ino, VFS_I(ip)->i_mode);
+			return -EFSCORRUPTED;
+		}
+
+		if (ip->i_d.di_nblocks != 0) {
+			xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx has blocks allocated!",
+				ip->i_ino);
+			return -EFSCORRUPTED;
+		}
+		return 0;
+	}
+
+	/* should be an allocated inode */
+	if (VFS_I(ip)->i_mode == 0)
+		return -ENOENT;
+
+	return 0;
+}
+
+/*
  * Check the validity of the inode we just found it the cache
  */
 static int
@@ -357,12 +398,12 @@ xfs_iget_cache_hit(
 	}
 
 	/*
-	 * If lookup is racing with unlink return an error immediately.
+	 * Check the inode free state is valid. This also detects lookup
+	 * racing with unlinks.
 	 */
-	if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) {
-		error = -ENOENT;
+	error = xfs_iget_check_free_state(ip, flags);
+	if (error)
 		goto out_error;
-	}
 
 	/*
 	 * If IRECLAIMABLE is set, we've torn down the VFS inode already.
@@ -485,29 +526,12 @@ xfs_iget_cache_miss(
 
 
 	/*
-	 * If we are allocating a new inode, then check what was returned is
-	 * actually a free, empty inode. If we are not allocating an inode,
-	 * the check we didn't find a free inode.
+	 * Check the inode free state is valid. This also detects lookup
+	 * racing with unlinks.
 	 */
-	if (flags & XFS_IGET_CREATE) {
-		if (VFS_I(ip)->i_mode != 0) {
-			xfs_warn(mp,
-"Corruption detected! Free inode 0x%llx not marked free on disk",
-				ino);
-			error = -EFSCORRUPTED;
-			goto out_destroy;
-		}
-		if (ip->i_d.di_nblocks != 0) {
-			xfs_warn(mp,
-"Corruption detected! Free inode 0x%llx has blocks allocated!",
-				ino);
-			error = -EFSCORRUPTED;
-			goto out_destroy;
-		}
-	} else if (VFS_I(ip)->i_mode == 0) {
-		error = -ENOENT;
+	error = xfs_iget_check_free_state(ip, flags);
+	if (error)
 		goto out_destroy;
-	}
 
 	/*
 	 * Preload the radix tree so we can insert safely under the
@@ -1802,3 +1826,21 @@ xfs_inode_clear_cowblocks_tag(
 	return __xfs_inode_clear_blocks_tag(ip,
 			trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
 }
+
+/* Disable post-EOF and CoW block auto-reclamation. */
+void
+xfs_icache_disable_reclaim(
+	struct xfs_mount	*mp)
+{
+	cancel_delayed_work_sync(&mp->m_eofblocks_work);
+	cancel_delayed_work_sync(&mp->m_cowblocks_work);
+}
+
+/* Enable post-EOF and CoW block auto-reclamation. */
+void
+xfs_icache_enable_reclaim(
+	struct xfs_mount	*mp)
+{
+	xfs_queue_eofblocks(mp);
+	xfs_queue_cowblocks(mp);
+}
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index d4a77588eca1..d69a0f5a6a73 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -131,4 +131,7 @@ xfs_fs_eofblocks_from_user(
 int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp,
 				  xfs_ino_t ino, bool *inuse);
 
+void xfs_icache_disable_reclaim(struct xfs_mount *mp);
+void xfs_icache_enable_reclaim(struct xfs_mount *mp);
+
 #endif
diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c
index 865ad1373e5e..5da9599156ed 100644
--- a/fs/xfs/xfs_icreate_item.c
+++ b/fs/xfs/xfs_icreate_item.c
@@ -91,7 +91,7 @@ xfs_icreate_item_unlock(
 {
 	struct xfs_icreate_item	*icp = ICR_ITEM(lip);
 
-	if (icp->ic_item.li_flags & XFS_LI_ABORTED)
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
 		kmem_zone_free(xfs_icreate_zone, icp);
 	return;
 }
@@ -184,5 +184,5 @@ xfs_icreate_log(
 
 	xfs_trans_add_item(tp, &icp->ic_item);
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	icp->ic_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &icp->ic_item.li_flags);
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2b70c8b4cee2..05207a64dd53 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -498,7 +498,7 @@ again:
 		if (!try_lock) {
 			for (j = (i - 1); j >= 0 && !try_lock; j--) {
 				lp = (xfs_log_item_t *)ips[j]->i_itemp;
-				if (lp && (lp->li_flags & XFS_LI_IN_AIL))
+				if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags))
 					try_lock++;
 			}
 		}
@@ -598,7 +598,7 @@ xfs_lock_two_inodes(
 	 * and try again.
 	 */
 	lp = (xfs_log_item_t *)ip0->i_itemp;
-	if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
+	if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) {
 		if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) {
 			xfs_iunlock(ip0, ip0_mode);
 			if ((++attempts % 5) == 0)
@@ -791,6 +791,18 @@ xfs_ialloc(
 	ASSERT(*ialloc_context == NULL);
 
 	/*
+	 * Protect against obviously corrupt allocation btree records. Later
+	 * xfs_iget checks will catch re-allocation of other active in-memory
+	 * and on-disk inodes. If we don't catch reallocating the parent inode
+	 * here we will deadlock in xfs_iget() so we have to do these checks
+	 * first.
+	 */
+	if ((pip && ino == pip->i_ino) || !xfs_verify_dir_ino(mp, ino)) {
+		xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
+		return -EFSCORRUPTED;
+	}
+
+	/*
 	 * Get the in-core inode with the lock held exclusively.
 	 * This is because we're setting fields here we need
 	 * to prevent others from looking at until we're done.
@@ -1196,6 +1208,7 @@ xfs_create(
 	unlock_dp_on_error = true;
 
 	xfs_defer_init(&dfops, &first_block);
+	tp->t_agfl_dfops = &dfops;
 
 	/*
 	 * Reserve disk quota and the inode.
@@ -1411,11 +1424,11 @@ xfs_link(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	error = xfs_qm_dqattach(sip, 0);
+	error = xfs_qm_dqattach(sip);
 	if (error)
 		goto std_return;
 
-	error = xfs_qm_dqattach(tdp, 0);
+	error = xfs_qm_dqattach(tdp);
 	if (error)
 		goto std_return;
 
@@ -1451,6 +1464,7 @@ xfs_link(
 	}
 
 	xfs_defer_init(&dfops, &first_block);
+	tp->t_agfl_dfops = &dfops;
 
 	/*
 	 * Handle initial link state of O_TMPFILE inode
@@ -1534,11 +1548,12 @@ xfs_itruncate_clear_reflink_flags(
  * dirty on error so that transactions can be easily aborted if possible.
  */
 int
-xfs_itruncate_extents(
+xfs_itruncate_extents_flags(
 	struct xfs_trans	**tpp,
 	struct xfs_inode	*ip,
 	int			whichfork,
-	xfs_fsize_t		new_size)
+	xfs_fsize_t		new_size,
+	int			flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
@@ -1561,6 +1576,8 @@ xfs_itruncate_extents(
 
 	trace_xfs_itruncate_extents_start(ip, new_size);
 
+	flags |= xfs_bmapi_aflag(whichfork);
+
 	/*
 	 * Since it is possible for space to become allocated beyond
 	 * the end of the file (in a crash where the space is allocated
@@ -1579,12 +1596,9 @@ xfs_itruncate_extents(
 	unmap_len = last_block - first_unmap_block + 1;
 	while (!done) {
 		xfs_defer_init(&dfops, &first_block);
-		error = xfs_bunmapi(tp, ip,
-				    first_unmap_block, unmap_len,
-				    xfs_bmapi_aflag(whichfork),
-				    XFS_ITRUNC_MAX_EXTENTS,
-				    &first_block, &dfops,
-				    &done);
+		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
+				    XFS_ITRUNC_MAX_EXTENTS, &first_block,
+				    &dfops, &done);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1811,6 +1825,7 @@ xfs_inactive_ifree(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	xfs_defer_init(&dfops, &first_block);
+	tp->t_agfl_dfops = &dfops;
 	error = xfs_ifree(tp, ip, &dfops);
 	if (error) {
 		/*
@@ -1911,7 +1926,7 @@ xfs_inactive(
 	     ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
 		truncate = 1;
 
-	error = xfs_qm_dqattach(ip, 0);
+	error = xfs_qm_dqattach(ip);
 	if (error)
 		return;
 
@@ -2574,11 +2589,11 @@ xfs_remove(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	error = xfs_qm_dqattach(dp, 0);
+	error = xfs_qm_dqattach(dp);
 	if (error)
 		goto std_return;
 
-	error = xfs_qm_dqattach(ip, 0);
+	error = xfs_qm_dqattach(ip);
 	if (error)
 		goto std_return;
 
@@ -2647,6 +2662,7 @@ xfs_remove(
 		goto out_trans_cancel;
 
 	xfs_defer_init(&dfops, &first_block);
+	tp->t_agfl_dfops = &dfops;
 	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
 					&first_block, &dfops, resblks);
 	if (error) {
@@ -3014,6 +3030,7 @@ xfs_rename(
 	}
 
 	xfs_defer_init(&dfops, &first_block);
+	tp->t_agfl_dfops = &dfops;
 
 	/* RENAME_EXCHANGE is unique from here on. */
 	if (flags & RENAME_EXCHANGE)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1eebc53df7d7..00fee6824745 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -415,8 +415,8 @@ uint		xfs_ilock_attr_map_shared(struct xfs_inode *);
 uint		xfs_ip2xflags(struct xfs_inode *);
 int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
 			   struct xfs_defer_ops *);
-int		xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *,
-				      int, xfs_fsize_t);
+int		xfs_itruncate_extents_flags(struct xfs_trans **,
+				struct xfs_inode *, int, xfs_fsize_t, int);
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
 
 void		xfs_iunpin_wait(xfs_inode_t *);
@@ -433,6 +433,16 @@ int		xfs_dir_ialloc(struct xfs_trans **, struct xfs_inode *, umode_t,
 			       xfs_nlink_t, dev_t, prid_t,
 			       struct xfs_inode **);
 
+static inline int
+xfs_itruncate_extents(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	int			whichfork,
+	xfs_fsize_t		new_size)
+{
+	return xfs_itruncate_extents_flags(tpp, ip, whichfork, new_size, 0);
+}
+
 /* from xfs_file.c */
 enum xfs_prealloc_flags {
 	XFS_PREALLOC_SET	= (1 << 1),
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 34b91b789702..3e5b8574818e 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -518,7 +518,7 @@ xfs_inode_item_push(
 	 * The buffer containing this item failed to be written back
 	 * previously. Resubmit the buffer for IO.
 	 */
-	if (lip->li_flags & XFS_LI_FAILED) {
+	if (test_bit(XFS_LI_FAILED, &lip->li_flags)) {
 		if (!xfs_buf_trylock(bp))
 			return XFS_ITEM_LOCKED;
 
@@ -729,14 +729,14 @@ xfs_iflush_done(
 		 */
 		iip = INODE_ITEM(blip);
 		if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
-		    (blip->li_flags & XFS_LI_FAILED))
+		    test_bit(XFS_LI_FAILED, &blip->li_flags))
 			need_ail++;
 	}
 
 	/* make sure we capture the state of the initial inode. */
 	iip = INODE_ITEM(lip);
 	if ((iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) ||
-	    lip->li_flags & XFS_LI_FAILED)
+	    test_bit(XFS_LI_FAILED, &lip->li_flags))
 		need_ail++;
 
 	/*
@@ -803,7 +803,7 @@ xfs_iflush_abort(
 	xfs_inode_log_item_t	*iip = ip->i_itemp;
 
 	if (iip) {
-		if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
+		if (test_bit(XFS_LI_IN_AIL, &iip->ili_item.li_flags)) {
 			xfs_trans_ail_remove(&iip->ili_item,
 					     stale ? SHUTDOWN_LOG_IO_ERROR :
 						     SHUTDOWN_CORRUPT_INCORE);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 89fb1eb80aae..5dd9e22b4a4c 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1103,7 +1103,8 @@ xfs_ioctl_setattr_dax_invalidate(
 	if (fa->fsx_xflags & FS_XFLAG_DAX) {
 		if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
 			return -EINVAL;
-		if (bdev_dax_supported(sb, sb->s_blocksize) < 0)
+		if (!bdev_dax_supported(xfs_find_bdev_for_inode(VFS_I(ip)),
+				sb->s_blocksize))
 			return -EINVAL;
 	}
 
@@ -1811,6 +1812,88 @@ xfs_ioc_swapext(
 	return error;
 }
 
+static int
+xfs_ioc_getlabel(
+	struct xfs_mount	*mp,
+	char			__user *user_label)
+{
+	struct xfs_sb		*sbp = &mp->m_sb;
+	char			label[XFSLABEL_MAX + 1];
+
+	/* Paranoia */
+	BUILD_BUG_ON(sizeof(sbp->sb_fname) > FSLABEL_MAX);
+
+	spin_lock(&mp->m_sb_lock);
+	strncpy(label, sbp->sb_fname, sizeof(sbp->sb_fname));
+	spin_unlock(&mp->m_sb_lock);
+
+	/* xfs on-disk label is 12 chars, be sure we send a null to user */
+	label[XFSLABEL_MAX] = '\0';
+	if (copy_to_user(user_label, label, sizeof(sbp->sb_fname)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+xfs_ioc_setlabel(
+	struct file		*filp,
+	struct xfs_mount	*mp,
+	char			__user *newlabel)
+{
+	struct xfs_sb		*sbp = &mp->m_sb;
+	char			label[XFSLABEL_MAX + 1];
+	size_t			len;
+	int			error;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	/*
+	 * The generic ioctl allows up to FSLABEL_MAX chars, but XFS is much
+	 * smaller, at 12 bytes.  We copy one more to be sure we find the
+	 * (required) NULL character to test the incoming label length.
+	 * NB: The on disk label doesn't need to be null terminated.
+	 */
+	if (copy_from_user(label, newlabel, XFSLABEL_MAX + 1))
+		return -EFAULT;
+	len = strnlen(label, XFSLABEL_MAX + 1);
+	if (len > sizeof(sbp->sb_fname))
+		return -EINVAL;
+
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+
+	spin_lock(&mp->m_sb_lock);
+	memset(sbp->sb_fname, 0, sizeof(sbp->sb_fname));
+	strncpy(sbp->sb_fname, label, sizeof(sbp->sb_fname));
+	spin_unlock(&mp->m_sb_lock);
+
+	/*
+	 * Now we do several things to satisfy userspace.
+	 * In addition to normal logging of the primary superblock, we also
+	 * immediately write these changes to sector zero for the primary, then
+	 * update all backup supers (as xfs_db does for a label change), then
+	 * invalidate the block device page cache.  This is so that any prior
+	 * buffered reads from userspace (i.e. from blkid) are invalidated,
+	 * and userspace will see the newly-written label.
+	 */
+	error = xfs_sync_sb_buf(mp);
+	if (error)
+		goto out;
+	/*
+	 * growfs also updates backup supers so lock against that.
+	 */
+	mutex_lock(&mp->m_growlock);
+	error = xfs_update_secondary_sbs(mp);
+	mutex_unlock(&mp->m_growlock);
+
+	invalidate_bdev(mp->m_ddev_targp->bt_bdev);
+
+out:
+	mnt_drop_write_file(filp);
+	return error;
+}
+
 /*
  * Note: some of the ioctl's return positive numbers as a
  * byte count indicating success, such as readlink_by_handle.
@@ -1834,6 +1917,10 @@ xfs_file_ioctl(
 	switch (cmd) {
 	case FITRIM:
 		return xfs_ioc_trim(mp, arg);
+	case FS_IOC_GETFSLABEL:
+		return xfs_ioc_getlabel(mp, arg);
+	case FS_IOC_SETFSLABEL:
+		return xfs_ioc_setlabel(filp, mp, arg);
 	case XFS_IOC_ALLOCSP:
 	case XFS_IOC_FREESP:
 	case XFS_IOC_RESVSP:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 046469fcc1b8..c6ce6f9335b6 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -224,7 +224,7 @@ xfs_iomap_write_direct(
 	 * necessary and move on to transaction setup.
 	 */
 	xfs_iunlock(ip, lockmode);
-	error = xfs_qm_dqattach(ip, 0);
+	error = xfs_qm_dqattach(ip);
 	if (error)
 		return error;
 
@@ -576,7 +576,7 @@ xfs_file_iomap_begin_delay(
 		goto done;
 	}
 
-	error = xfs_qm_dqattach_locked(ip, 0);
+	error = xfs_qm_dqattach_locked(ip, false);
 	if (error)
 		goto out_unlock;
 
@@ -692,7 +692,7 @@ xfs_iomap_write_allocate(
 	/*
 	 * Make sure that the dquots are there.
 	 */
-	error = xfs_qm_dqattach(ip, 0);
+	error = xfs_qm_dqattach(ip);
 	if (error)
 		return error;
 
@@ -946,8 +946,11 @@ error_on_bmapi_transaction:
 	return error;
 }
 
-static inline bool imap_needs_alloc(struct inode *inode,
-		struct xfs_bmbt_irec *imap, int nimaps)
+static inline bool
+imap_needs_alloc(
+	struct inode		*inode,
+	struct xfs_bmbt_irec	*imap,
+	int			nimaps)
 {
 	return !nimaps ||
 		imap->br_startblock == HOLESTARTBLOCK ||
@@ -955,31 +958,58 @@ static inline bool imap_needs_alloc(struct inode *inode,
 		(IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN);
 }
 
-static inline bool needs_cow_for_zeroing(struct xfs_bmbt_irec *imap, int nimaps)
+static inline bool
+needs_cow_for_zeroing(
+	struct xfs_bmbt_irec	*imap,
+	int			nimaps)
 {
 	return nimaps &&
 		imap->br_startblock != HOLESTARTBLOCK &&
 		imap->br_state != XFS_EXT_UNWRITTEN;
 }
 
-static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
+static int
+xfs_ilock_for_iomap(
+	struct xfs_inode	*ip,
+	unsigned		flags,
+	unsigned		*lockmode)
 {
+	unsigned		mode = XFS_ILOCK_SHARED;
+
 	/*
 	 * COW writes may allocate delalloc space or convert unwritten COW
 	 * extents, so we need to make sure to take the lock exclusively here.
 	 */
-	if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO)))
-		return true;
+	if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) {
+		/*
+		 * FIXME: It could still overwrite on unshared extents and not
+		 * need allocation.
+		 */
+		if (flags & IOMAP_NOWAIT)
+			return -EAGAIN;
+		mode = XFS_ILOCK_EXCL;
+	}
 
 	/*
-	 * Extents not yet cached requires exclusive access, don't block.
-	 * This is an opencoded xfs_ilock_data_map_shared() to cater for the
+	 * Extents not yet cached requires exclusive access, don't block.  This
+	 * is an opencoded xfs_ilock_data_map_shared() call but with
 	 * non-blocking behaviour.
 	 */
-	if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
-	    !(ip->i_df.if_flags & XFS_IFEXTENTS))
-		return true;
-	return false;
+	if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) {
+		if (flags & IOMAP_NOWAIT)
+			return -EAGAIN;
+		mode = XFS_ILOCK_EXCL;
+	}
+
+	if (flags & IOMAP_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, mode))
+			return -EAGAIN;
+	} else {
+		xfs_ilock(ip, mode);
+	}
+
+	*lockmode = mode;
+	return 0;
 }
 
 static int
@@ -1007,19 +1037,15 @@ xfs_file_iomap_begin(
 		return xfs_file_iomap_begin_delay(inode, offset, length, iomap);
 	}
 
-	if (need_excl_ilock(ip, flags))
-		lockmode = XFS_ILOCK_EXCL;
-	else
-		lockmode = XFS_ILOCK_SHARED;
-
-	if (flags & IOMAP_NOWAIT) {
-		if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
-			return -EAGAIN;
-		if (!xfs_ilock_nowait(ip, lockmode))
-			return -EAGAIN;
-	} else {
-		xfs_ilock(ip, lockmode);
-	}
+	/*
+	 * Lock the inode in the manner required for the specified operation and
+	 * check for as many conditions that would result in blocking as
+	 * possible. This removes most of the non-blocking checks from the
+	 * mapping code below.
+	 */
+	error = xfs_ilock_for_iomap(ip, flags, &lockmode);
+	if (error)
+		return error;
 
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if (offset > mp->m_super->s_maxbytes - length)
@@ -1040,19 +1066,21 @@ xfs_file_iomap_begin(
 			goto out_unlock;
 	}
 
-	if (xfs_is_reflink_inode(ip) &&
-	    ((flags & IOMAP_WRITE) ||
-	     ((flags & IOMAP_ZERO) && needs_cow_for_zeroing(&imap, nimaps)))) {
+	/* Non-modifying mapping requested, so we are done */
+	if (!(flags & (IOMAP_WRITE | IOMAP_ZERO)))
+		goto out_found;
+
+	/*
+	 * Break shared extents if necessary. Checks for non-blocking IO have
+	 * been done up front, so we don't need to do them here.
+	 */
+	if (xfs_is_reflink_inode(ip)) {
+		/* if zeroing doesn't need COW allocation, then we are done. */
+		if ((flags & IOMAP_ZERO) &&
+		    !needs_cow_for_zeroing(&imap, nimaps))
+			goto out_found;
+
 		if (flags & IOMAP_DIRECT) {
-			/*
-			 * A reflinked inode will result in CoW alloc.
-			 * FIXME: It could still overwrite on unshared extents
-			 * and not need allocation.
-			 */
-			if (flags & IOMAP_NOWAIT) {
-				error = -EAGAIN;
-				goto out_unlock;
-			}
 			/* may drop and re-acquire the ilock */
 			error = xfs_reflink_allocate_cow(ip, &imap, &shared,
 					&lockmode);
@@ -1068,46 +1096,45 @@ xfs_file_iomap_begin(
 		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
 	}
 
-	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
-		/*
-		 * If nowait is set bail since we are going to make
-		 * allocations.
-		 */
-		if (flags & IOMAP_NOWAIT) {
-			error = -EAGAIN;
-			goto out_unlock;
-		}
-		/*
-		 * We cap the maximum length we map here to MAX_WRITEBACK_PAGES
-		 * pages to keep the chunks of work done where somewhat symmetric
-		 * with the work writeback does. This is a completely arbitrary
-		 * number pulled out of thin air as a best guess for initial
-		 * testing.
-		 *
-		 * Note that the values needs to be less than 32-bits wide until
-		 * the lower level functions are updated.
-		 */
-		length = min_t(loff_t, length, 1024 * PAGE_SIZE);
-		/*
-		 * xfs_iomap_write_direct() expects the shared lock. It
-		 * is unlocked on return.
-		 */
-		if (lockmode == XFS_ILOCK_EXCL)
-			xfs_ilock_demote(ip, lockmode);
-		error = xfs_iomap_write_direct(ip, offset, length, &imap,
-				nimaps);
-		if (error)
-			return error;
+	/* Don't need to allocate over holes when doing zeroing operations. */
+	if (flags & IOMAP_ZERO)
+		goto out_found;
 
-		iomap->flags = IOMAP_F_NEW;
-		trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
-	} else {
-		ASSERT(nimaps);
+	if (!imap_needs_alloc(inode, &imap, nimaps))
+		goto out_found;
 
-		xfs_iunlock(ip, lockmode);
-		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
+	/* If nowait is set bail since we are going to make allocations. */
+	if (flags & IOMAP_NOWAIT) {
+		error = -EAGAIN;
+		goto out_unlock;
 	}
 
+	/*
+	 * We cap the maximum length we map to a sane size  to keep the chunks
+	 * of work done where somewhat symmetric with the work writeback does.
+	 * This is a completely arbitrary number pulled out of thin air as a
+	 * best guess for initial testing.
+	 *
+	 * Note that the values needs to be less than 32-bits wide until the
+	 * lower level functions are updated.
+	 */
+	length = min_t(loff_t, length, 1024 * PAGE_SIZE);
+
+	/*
+	 * xfs_iomap_write_direct() expects the shared lock. It is unlocked on
+	 * return.
+	 */
+	if (lockmode == XFS_ILOCK_EXCL)
+		xfs_ilock_demote(ip, lockmode);
+	error = xfs_iomap_write_direct(ip, offset, length, &imap,
+			nimaps);
+	if (error)
+		return error;
+
+	iomap->flags = IOMAP_F_NEW;
+	trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
+
+out_finish:
 	if (xfs_ipincount(ip) && (ip->i_itemp->ili_fsync_fields
 				& ~XFS_ILOG_TIMESTAMP))
 		iomap->flags |= IOMAP_F_DIRTY;
@@ -1117,6 +1144,13 @@ xfs_file_iomap_begin(
 	if (shared)
 		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
+
+out_found:
+	ASSERT(nimaps);
+	xfs_iunlock(ip, lockmode);
+	trace_xfs_iomap_found(ip, offset, length, 0, &imap);
+	goto out_finish;
+
 out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index a3ed3c811dfa..b0eb49bb4918 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -260,6 +260,7 @@ xfs_vn_lookup(
 	struct dentry	*dentry,
 	unsigned int flags)
 {
+	struct inode *inode;
 	struct xfs_inode *cip;
 	struct xfs_name	name;
 	int		error;
@@ -269,14 +270,13 @@ xfs_vn_lookup(
 
 	xfs_dentry_to_name(&name, dentry);
 	error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
-	if (unlikely(error)) {
-		if (unlikely(error != -ENOENT))
-			return ERR_PTR(error);
-		d_add(dentry, NULL);
-		return NULL;
-	}
-
-	return d_splice_alias(VFS_I(cip), dentry);
+	if (likely(!error))
+		inode = VFS_I(cip);
+	else if (likely(error == -ENOENT))
+		inode = NULL;
+	else
+		inode = ERR_PTR(error);
+	return d_splice_alias(inode, dentry);
 }
 
 STATIC struct dentry *
@@ -855,7 +855,7 @@ xfs_setattr_size(
 	/*
 	 * Make sure that the dquots are attached to the inode.
 	 */
-	error = xfs_qm_dqattach(ip, 0);
+	error = xfs_qm_dqattach(ip);
 	if (error)
 		return error;
 
@@ -1195,6 +1195,30 @@ static const struct inode_operations xfs_inline_symlink_inode_operations = {
 	.update_time		= xfs_vn_update_time,
 };
 
+/* Figure out if this file actually supports DAX. */
+static bool
+xfs_inode_supports_dax(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	/* Only supported on non-reflinked files. */
+	if (!S_ISREG(VFS_I(ip)->i_mode) || xfs_is_reflink_inode(ip))
+		return false;
+
+	/* DAX mount option or DAX iflag must be set. */
+	if (!(mp->m_flags & XFS_MOUNT_DAX) &&
+	    !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
+		return false;
+
+	/* Block size must match page size */
+	if (mp->m_sb.sb_blocksize != PAGE_SIZE)
+		return false;
+
+	/* Device has to support DAX too. */
+	return xfs_find_daxdev_for_inode(VFS_I(ip)) != NULL;
+}
+
 STATIC void
 xfs_diflags_to_iflags(
 	struct inode		*inode,
@@ -1213,11 +1237,7 @@ xfs_diflags_to_iflags(
 		inode->i_flags |= S_SYNC;
 	if (flags & XFS_DIFLAG_NOATIME)
 		inode->i_flags |= S_NOATIME;
-	if (S_ISREG(inode->i_mode) &&
-	    ip->i_mount->m_sb.sb_blocksize == PAGE_SIZE &&
-	    !xfs_is_reflink_inode(ip) &&
-	    (ip->i_mount->m_flags & XFS_MOUNT_DAX ||
-	     ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
+	if (xfs_inode_supports_dax(ip))
 		inode->i_flags |= S_DAX;
 }
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 2fcd9ed5d075..c21039f27e39 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1047,6 +1047,7 @@ xfs_log_item_init(
 	INIT_LIST_HEAD(&item->li_ail);
 	INIT_LIST_HEAD(&item->li_cil);
 	INIT_LIST_HEAD(&item->li_bio_list);
+	INIT_LIST_HEAD(&item->li_trans);
 }
 
 /*
@@ -2110,10 +2111,10 @@ xlog_print_tic_res(
  */
 void
 xlog_print_trans(
-	struct xfs_trans		*tp)
+	struct xfs_trans	*tp)
 {
-	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_log_item_desc	*lidp;
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_log_item	*lip;
 
 	/* dump core transaction and ticket info */
 	xfs_warn(mp, "transaction summary:");
@@ -2124,15 +2125,14 @@ xlog_print_trans(
 	xlog_print_tic_res(mp, tp->t_ticket);
 
 	/* dump each log item */
-	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
-		struct xfs_log_item	*lip = lidp->lid_item;
+	list_for_each_entry(lip, &tp->t_items, li_trans) {
 		struct xfs_log_vec	*lv = lip->li_lv;
 		struct xfs_log_iovec	*vec;
 		int			i;
 
 		xfs_warn(mp, "log item: ");
 		xfs_warn(mp, "  type	= 0x%x", lip->li_type);
-		xfs_warn(mp, "  flags	= 0x%x", lip->li_flags);
+		xfs_warn(mp, "  flags	= 0x%lx", lip->li_flags);
 		if (!lv)
 			continue;
 		xfs_warn(mp, "  niovecs	= %d", lv->lv_niovecs);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 4668403b1741..c15687724728 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -141,10 +141,9 @@ xlog_cil_alloc_shadow_bufs(
 	struct xlog		*log,
 	struct xfs_trans	*tp)
 {
-	struct xfs_log_item_desc *lidp;
+	struct xfs_log_item	*lip;
 
-	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
-		struct xfs_log_item *lip = lidp->lid_item;
+	list_for_each_entry(lip, &tp->t_items, li_trans) {
 		struct xfs_log_vec *lv;
 		int	niovecs = 0;
 		int	nbytes = 0;
@@ -152,7 +151,7 @@ xlog_cil_alloc_shadow_bufs(
 		bool	ordered = false;
 
 		/* Skip items which aren't dirty in this transaction. */
-		if (!(lidp->lid_flags & XFS_LID_DIRTY))
+		if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
 			continue;
 
 		/* get number of vecs and size of data to be stored */
@@ -317,7 +316,7 @@ xlog_cil_insert_format_items(
 	int			*diff_len,
 	int			*diff_iovecs)
 {
-	struct xfs_log_item_desc *lidp;
+	struct xfs_log_item	*lip;
 
 
 	/* Bail out if we didn't find a log item.  */
@@ -326,15 +325,14 @@ xlog_cil_insert_format_items(
 		return;
 	}
 
-	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
-		struct xfs_log_item *lip = lidp->lid_item;
+	list_for_each_entry(lip, &tp->t_items, li_trans) {
 		struct xfs_log_vec *lv;
 		struct xfs_log_vec *old_lv = NULL;
 		struct xfs_log_vec *shadow;
 		bool	ordered = false;
 
 		/* Skip items which aren't dirty in this transaction. */
-		if (!(lidp->lid_flags & XFS_LID_DIRTY))
+		if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
 			continue;
 
 		/*
@@ -406,7 +404,7 @@ xlog_cil_insert_items(
 {
 	struct xfs_cil		*cil = log->l_cilp;
 	struct xfs_cil_ctx	*ctx = cil->xc_ctx;
-	struct xfs_log_item_desc *lidp;
+	struct xfs_log_item	*lip;
 	int			len = 0;
 	int			diff_iovecs = 0;
 	int			iclog_space;
@@ -479,11 +477,10 @@ xlog_cil_insert_items(
 	 * We do this here so we only need to take the CIL lock once during
 	 * the transaction commit.
 	 */
-	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
-		struct xfs_log_item	*lip = lidp->lid_item;
+	list_for_each_entry(lip, &tp->t_items, li_trans) {
 
 		/* Skip items which aren't dirty in this transaction. */
-		if (!(lidp->lid_flags & XFS_LID_DIRTY))
+		if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
 			continue;
 
 		/*
@@ -1013,6 +1010,7 @@ xfs_log_commit_cil(
 		*commit_lsn = xc_commit_lsn;
 
 	xfs_log_done(mp, tp->t_ticket, NULL, regrant);
+	tp->t_ticket = NULL;
 	xfs_trans_unreserve_and_mod_sb(tp);
 
 	/*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 2b2383f1895e..06a09cb948b5 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2702,7 +2702,7 @@ xlog_recover_do_reg_buffer(
 				goto next;
 			}
 			fa = xfs_dquot_verify(mp, item->ri_buf[i].i_addr,
-					       -1, 0, 0);
+					       -1, 0);
 			if (fa) {
 				xfs_alert(mp,
 	"dquot corrupt at %pS trying to replay into block 0x%llx",
@@ -3348,7 +3348,7 @@ xlog_recover_dquot_pass2(
 	 */
 	dq_f = item->ri_buf[0].i_addr;
 	ASSERT(dq_f);
-	fa = xfs_dquot_verify(mp, recddq, dq_f->qlf_id, 0, 0);
+	fa = xfs_dquot_verify(mp, recddq, dq_f->qlf_id, 0);
 	if (fa) {
 		xfs_alert(mp, "corrupt dquot ID 0x%x in log at %pS",
 				dq_f->qlf_id, fa);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index a901b86772f8..73ed8fec0328 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1072,9 +1072,7 @@ xfs_unmountfs(
 	uint64_t		resblks;
 	int			error;
 
-	cancel_delayed_work_sync(&mp->m_eofblocks_work);
-	cancel_delayed_work_sync(&mp->m_cowblocks_work);
-
+	xfs_icache_disable_reclaim(mp);
 	xfs_fs_unreserve_ag_blocks(mp);
 	xfs_qm_unmount_quotas(mp);
 	xfs_rtunmount_inodes(mp);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index ec39ae274c78..c3e014bfc848 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -161,10 +161,7 @@ xfs_qm_dqpurge(
 		 * to purge this dquot anyway, so we go ahead regardless.
 		 */
 		error = xfs_qm_dqflush(dqp, &bp);
-		if (error) {
-			xfs_warn(mp, "%s: dquot "PTR_FMT" flush failed",
-				__func__, dqp);
-		} else {
+		if (!error) {
 			error = xfs_bwrite(bp);
 			xfs_buf_relse(bp);
 		}
@@ -173,7 +170,7 @@ xfs_qm_dqpurge(
 
 	ASSERT(atomic_read(&dqp->q_pincount) == 0);
 	ASSERT(XFS_FORCED_SHUTDOWN(mp) ||
-	       !(dqp->q_logitem.qli_item.li_flags & XFS_LI_IN_AIL));
+		!test_bit(XFS_LI_IN_AIL, &dqp->q_logitem.qli_item.li_flags));
 
 	xfs_dqfunlock(dqp);
 	xfs_dqunlock(dqp);
@@ -265,7 +262,7 @@ xfs_qm_dqattach_one(
 	xfs_inode_t	*ip,
 	xfs_dqid_t	id,
 	uint		type,
-	uint		doalloc,
+	bool		doalloc,
 	xfs_dquot_t	**IO_idqpp)
 {
 	xfs_dquot_t	*dqp;
@@ -291,7 +288,7 @@ xfs_qm_dqattach_one(
 	 * exist on disk and we didn't ask it to allocate; ESRCH if quotas got
 	 * turned off suddenly.
 	 */
-	error = xfs_qm_dqget(ip->i_mount, ip, id, type, doalloc, &dqp);
+	error = xfs_qm_dqget_inode(ip, type, doalloc, &dqp);
 	if (error)
 		return error;
 
@@ -326,14 +323,14 @@ xfs_qm_need_dqattach(
 /*
  * Given a locked inode, attach dquot(s) to it, taking U/G/P-QUOTAON
  * into account.
- * If XFS_QMOPT_DQALLOC, the dquot(s) will be allocated if needed.
+ * If @doalloc is true, the dquot(s) will be allocated if needed.
  * Inode may get unlocked and relocked in here, and the caller must deal with
  * the consequences.
  */
 int
 xfs_qm_dqattach_locked(
 	xfs_inode_t	*ip,
-	uint		flags)
+	bool		doalloc)
 {
 	xfs_mount_t	*mp = ip->i_mount;
 	int		error = 0;
@@ -345,8 +342,7 @@ xfs_qm_dqattach_locked(
 
 	if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
 		error = xfs_qm_dqattach_one(ip, ip->i_d.di_uid, XFS_DQ_USER,
-						flags & XFS_QMOPT_DQALLOC,
-						&ip->i_udquot);
+				doalloc, &ip->i_udquot);
 		if (error)
 			goto done;
 		ASSERT(ip->i_udquot);
@@ -354,8 +350,7 @@ xfs_qm_dqattach_locked(
 
 	if (XFS_IS_GQUOTA_ON(mp) && !ip->i_gdquot) {
 		error = xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP,
-						flags & XFS_QMOPT_DQALLOC,
-						&ip->i_gdquot);
+				doalloc, &ip->i_gdquot);
 		if (error)
 			goto done;
 		ASSERT(ip->i_gdquot);
@@ -363,8 +358,7 @@ xfs_qm_dqattach_locked(
 
 	if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) {
 		error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ,
-						flags & XFS_QMOPT_DQALLOC,
-						&ip->i_pdquot);
+				doalloc, &ip->i_pdquot);
 		if (error)
 			goto done;
 		ASSERT(ip->i_pdquot);
@@ -381,8 +375,7 @@ done:
 
 int
 xfs_qm_dqattach(
-	struct xfs_inode	*ip,
-	uint			flags)
+	struct xfs_inode	*ip)
 {
 	int			error;
 
@@ -390,7 +383,7 @@ xfs_qm_dqattach(
 		return 0;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	error = xfs_qm_dqattach_locked(ip, flags);
+	error = xfs_qm_dqattach_locked(ip, false);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
 	return error;
@@ -479,11 +472,8 @@ xfs_qm_dquot_isolate(
 		spin_unlock(lru_lock);
 
 		error = xfs_qm_dqflush(dqp, &bp);
-		if (error) {
-			xfs_warn(dqp->q_mount, "%s: dquot "PTR_FMT" flush failed",
-				 __func__, dqp);
+		if (error)
 			goto out_unlock_dirty;
-		}
 
 		xfs_buf_delwri_queue(bp, &isol->buffers);
 		xfs_buf_relse(bp);
@@ -571,27 +561,88 @@ xfs_qm_set_defquota(
 {
 	xfs_dquot_t		*dqp;
 	struct xfs_def_quota    *defq;
+	struct xfs_disk_dquot	*ddqp;
 	int			error;
 
-	error = xfs_qm_dqread(mp, 0, type, 0, &dqp);
+	error = xfs_qm_dqget_uncached(mp, 0, type, &dqp);
+	if (error)
+		return;
 
-	if (!error) {
-		xfs_disk_dquot_t        *ddqp = &dqp->q_core;
+	ddqp = &dqp->q_core;
+	defq = xfs_get_defquota(dqp, qinf);
 
-		defq = xfs_get_defquota(dqp, qinf);
+	/*
+	 * Timers and warnings have been already set, let's just set the
+	 * default limits for this quota type
+	 */
+	defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
+	defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
+	defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
+	defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
+	defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
+	defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
+	xfs_qm_dqdestroy(dqp);
+}
 
-		/*
-		 * Timers and warnings have been already set, let's just set the
-		 * default limits for this quota type
-		 */
-		defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
-		defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
-		defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
-		defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
-		defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
-		defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
-		xfs_qm_dqdestroy(dqp);
-	}
+/* Initialize quota time limits from the root dquot. */
+static void
+xfs_qm_init_timelimits(
+	struct xfs_mount	*mp,
+	struct xfs_quotainfo	*qinf)
+{
+	struct xfs_disk_dquot	*ddqp;
+	struct xfs_dquot	*dqp;
+	uint			type;
+	int			error;
+
+	qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
+	qinf->qi_itimelimit = XFS_QM_ITIMELIMIT;
+	qinf->qi_rtbtimelimit = XFS_QM_RTBTIMELIMIT;
+	qinf->qi_bwarnlimit = XFS_QM_BWARNLIMIT;
+	qinf->qi_iwarnlimit = XFS_QM_IWARNLIMIT;
+	qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
+
+	/*
+	 * We try to get the limits from the superuser's limits fields.
+	 * This is quite hacky, but it is standard quota practice.
+	 *
+	 * Since we may not have done a quotacheck by this point, just read
+	 * the dquot without attaching it to any hashtables or lists.
+	 *
+	 * Timers and warnings are globally set by the first timer found in
+	 * user/group/proj quota types, otherwise a default value is used.
+	 * This should be split into different fields per quota type.
+	 */
+	if (XFS_IS_UQUOTA_RUNNING(mp))
+		type = XFS_DQ_USER;
+	else if (XFS_IS_GQUOTA_RUNNING(mp))
+		type = XFS_DQ_GROUP;
+	else
+		type = XFS_DQ_PROJ;
+	error = xfs_qm_dqget_uncached(mp, 0, type, &dqp);
+	if (error)
+		return;
+
+	ddqp = &dqp->q_core;
+	/*
+	 * The warnings and timers set the grace period given to
+	 * a user or group before he or she can not perform any
+	 * more writing. If it is zero, a default is used.
+	 */
+	if (ddqp->d_btimer)
+		qinf->qi_btimelimit = be32_to_cpu(ddqp->d_btimer);
+	if (ddqp->d_itimer)
+		qinf->qi_itimelimit = be32_to_cpu(ddqp->d_itimer);
+	if (ddqp->d_rtbtimer)
+		qinf->qi_rtbtimelimit = be32_to_cpu(ddqp->d_rtbtimer);
+	if (ddqp->d_bwarns)
+		qinf->qi_bwarnlimit = be16_to_cpu(ddqp->d_bwarns);
+	if (ddqp->d_iwarns)
+		qinf->qi_iwarnlimit = be16_to_cpu(ddqp->d_iwarns);
+	if (ddqp->d_rtbwarns)
+		qinf->qi_rtbwarnlimit = be16_to_cpu(ddqp->d_rtbwarns);
+
+	xfs_qm_dqdestroy(dqp);
 }
 
 /*
@@ -600,11 +651,10 @@ xfs_qm_set_defquota(
  */
 STATIC int
 xfs_qm_init_quotainfo(
-	xfs_mount_t	*mp)
+	struct xfs_mount	*mp)
 {
-	xfs_quotainfo_t *qinf;
-	int		error;
-	xfs_dquot_t	*dqp;
+	struct xfs_quotainfo	*qinf;
+	int			error;
 
 	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
 
@@ -636,52 +686,7 @@ xfs_qm_init_quotainfo(
 
 	mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
 
-	/*
-	 * We try to get the limits from the superuser's limits fields.
-	 * This is quite hacky, but it is standard quota practice.
-	 *
-	 * Since we may not have done a quotacheck by this point, just read
-	 * the dquot without attaching it to any hashtables or lists.
-	 *
-	 * Timers and warnings are globally set by the first timer found in
-	 * user/group/proj quota types, otherwise a default value is used.
-	 * This should be split into different fields per quota type.
-	 */
-	error = xfs_qm_dqread(mp, 0,
-			XFS_IS_UQUOTA_RUNNING(mp) ? XFS_DQ_USER :
-			 (XFS_IS_GQUOTA_RUNNING(mp) ? XFS_DQ_GROUP :
-			  XFS_DQ_PROJ),
-			0, &dqp);
-
-	if (!error) {
-		xfs_disk_dquot_t	*ddqp = &dqp->q_core;
-
-		/*
-		 * The warnings and timers set the grace period given to
-		 * a user or group before he or she can not perform any
-		 * more writing. If it is zero, a default is used.
-		 */
-		qinf->qi_btimelimit = ddqp->d_btimer ?
-			be32_to_cpu(ddqp->d_btimer) : XFS_QM_BTIMELIMIT;
-		qinf->qi_itimelimit = ddqp->d_itimer ?
-			be32_to_cpu(ddqp->d_itimer) : XFS_QM_ITIMELIMIT;
-		qinf->qi_rtbtimelimit = ddqp->d_rtbtimer ?
-			be32_to_cpu(ddqp->d_rtbtimer) : XFS_QM_RTBTIMELIMIT;
-		qinf->qi_bwarnlimit = ddqp->d_bwarns ?
-			be16_to_cpu(ddqp->d_bwarns) : XFS_QM_BWARNLIMIT;
-		qinf->qi_iwarnlimit = ddqp->d_iwarns ?
-			be16_to_cpu(ddqp->d_iwarns) : XFS_QM_IWARNLIMIT;
-		qinf->qi_rtbwarnlimit = ddqp->d_rtbwarns ?
-			be16_to_cpu(ddqp->d_rtbwarns) : XFS_QM_RTBWARNLIMIT;
-		xfs_qm_dqdestroy(dqp);
-	} else {
-		qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
-		qinf->qi_itimelimit = XFS_QM_ITIMELIMIT;
-		qinf->qi_rtbtimelimit = XFS_QM_RTBTIMELIMIT;
-		qinf->qi_bwarnlimit = XFS_QM_BWARNLIMIT;
-		qinf->qi_iwarnlimit = XFS_QM_IWARNLIMIT;
-		qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
-	}
+	xfs_qm_init_timelimits(mp, qinf);
 
 	if (XFS_IS_UQUOTA_RUNNING(mp))
 		xfs_qm_set_defquota(mp, XFS_DQ_USER, qinf);
@@ -865,9 +870,9 @@ xfs_qm_reset_dqcounts(
 		 * find uninitialised dquot blks. See comment in
 		 * xfs_dquot_verify.
 		 */
-		fa = xfs_dquot_verify(mp, ddq, id + j, type, 0);
+		fa = xfs_dqblk_verify(mp, &dqb[j], id + j, type);
 		if (fa)
-			xfs_dquot_repair(mp, ddq, id + j, type);
+			xfs_dqblk_repair(mp, &dqb[j], id + j, type);
 
 		/*
 		 * Reset type in case we are reusing group quota file for
@@ -893,7 +898,7 @@ xfs_qm_reset_dqcounts(
 }
 
 STATIC int
-xfs_qm_dqiter_bufs(
+xfs_qm_reset_dqcounts_all(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		firstid,
 	xfs_fsblock_t		bno,
@@ -961,11 +966,11 @@ xfs_qm_dqiter_bufs(
 }
 
 /*
- * Iterate over all allocated USR/GRP/PRJ dquots in the system, calling a
- * caller supplied function for every chunk of dquots that we find.
+ * Iterate over all allocated dquot blocks in this quota inode, zeroing all
+ * counters for every chunk of dquots that we find.
  */
 STATIC int
-xfs_qm_dqiterate(
+xfs_qm_reset_dqcounts_buf(
 	struct xfs_mount	*mp,
 	struct xfs_inode	*qip,
 	uint			flags,
@@ -1041,7 +1046,7 @@ xfs_qm_dqiterate(
 			 * Iterate thru all the blks in the extent and
 			 * reset the counters of all the dquots inside them.
 			 */
-			error = xfs_qm_dqiter_bufs(mp, firstid,
+			error = xfs_qm_reset_dqcounts_all(mp, firstid,
 						   map[i].br_startblock,
 						   map[i].br_blockcount,
 						   flags, buffer_list);
@@ -1066,16 +1071,17 @@ out:
 STATIC int
 xfs_qm_quotacheck_dqadjust(
 	struct xfs_inode	*ip,
-	xfs_dqid_t		id,
 	uint			type,
 	xfs_qcnt_t		nblks,
 	xfs_qcnt_t		rtblks)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_dquot	*dqp;
+	xfs_dqid_t		id;
 	int			error;
 
-	error = xfs_qm_dqget(mp, ip, id, type, XFS_QMOPT_DQALLOC, &dqp);
+	id = xfs_qm_id_for_quotatype(ip, type);
+	error = xfs_qm_dqget(mp, id, type, true, &dqp);
 	if (error) {
 		/*
 		 * Shouldn't be able to turn off quotas here.
@@ -1148,13 +1154,10 @@ xfs_qm_dqusage_adjust(
 	}
 
 	/*
-	 * We don't _need_ to take the ilock EXCL. However, the xfs_qm_dqget
-	 * interface expects the inode to be exclusively locked because that's
-	 * the case in all other instances. It's OK that we do this because
-	 * quotacheck is done only at mount time.
+	 * We don't _need_ to take the ilock EXCL here because quotacheck runs
+	 * at mount time and therefore nobody will be racing chown/chproj.
 	 */
-	error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, XFS_ILOCK_EXCL,
-			 &ip);
+	error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, 0, &ip);
 	if (error) {
 		*res = BULKSTAT_RV_NOTHING;
 		return error;
@@ -1189,33 +1192,31 @@ xfs_qm_dqusage_adjust(
 	 * and quotaoffs don't race. (Quotachecks happen at mount time only).
 	 */
 	if (XFS_IS_UQUOTA_ON(mp)) {
-		error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_uid,
-						   XFS_DQ_USER, nblks, rtblks);
+		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_USER, nblks,
+				rtblks);
 		if (error)
 			goto error0;
 	}
 
 	if (XFS_IS_GQUOTA_ON(mp)) {
-		error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_gid,
-						   XFS_DQ_GROUP, nblks, rtblks);
+		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_GROUP, nblks,
+				rtblks);
 		if (error)
 			goto error0;
 	}
 
 	if (XFS_IS_PQUOTA_ON(mp)) {
-		error = xfs_qm_quotacheck_dqadjust(ip, xfs_get_projid(ip),
-						   XFS_DQ_PROJ, nblks, rtblks);
+		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_PROJ, nblks,
+				rtblks);
 		if (error)
 			goto error0;
 	}
 
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	IRELE(ip);
 	*res = BULKSTAT_RV_DIDONE;
 	return 0;
 
 error0:
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	IRELE(ip);
 	*res = BULKSTAT_RV_GIVEUP;
 	return error;
@@ -1247,9 +1248,8 @@ xfs_qm_flush_one(
 	 */
 	if (!xfs_dqflock_nowait(dqp)) {
 		/* buf is pinned in-core by delwri list */
-		DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno,
-				      mp->m_quotainfo->qi_dqchunklen);
-		bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL);
+		bp = xfs_buf_incore(mp->m_ddev_targp, dqp->q_blkno,
+				mp->m_quotainfo->qi_dqchunklen, 0);
 		if (!bp) {
 			error = -EINVAL;
 			goto out_unlock;
@@ -1307,7 +1307,7 @@ xfs_qm_quotacheck(
 	 * We don't log our changes till later.
 	 */
 	if (uip) {
-		error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA,
+		error = xfs_qm_reset_dqcounts_buf(mp, uip, XFS_QMOPT_UQUOTA,
 					 &buffer_list);
 		if (error)
 			goto error_return;
@@ -1315,7 +1315,7 @@ xfs_qm_quotacheck(
 	}
 
 	if (gip) {
-		error = xfs_qm_dqiterate(mp, gip, XFS_QMOPT_GQUOTA,
+		error = xfs_qm_reset_dqcounts_buf(mp, gip, XFS_QMOPT_GQUOTA,
 					 &buffer_list);
 		if (error)
 			goto error_return;
@@ -1323,7 +1323,7 @@ xfs_qm_quotacheck(
 	}
 
 	if (pip) {
-		error = xfs_qm_dqiterate(mp, pip, XFS_QMOPT_PQUOTA,
+		error = xfs_qm_reset_dqcounts_buf(mp, pip, XFS_QMOPT_PQUOTA,
 					 &buffer_list);
 		if (error)
 			goto error_return;
@@ -1675,7 +1675,7 @@ xfs_qm_vop_dqalloc(
 	 * if necessary. The dquot(s) will not be locked.
 	 */
 	if (XFS_NOT_DQATTACHED(mp, ip)) {
-		error = xfs_qm_dqattach_locked(ip, XFS_QMOPT_DQALLOC);
+		error = xfs_qm_dqattach_locked(ip, true);
 		if (error) {
 			xfs_iunlock(ip, lockflags);
 			return error;
@@ -1694,10 +1694,7 @@ xfs_qm_vop_dqalloc(
 			 * holding ilock.
 			 */
 			xfs_iunlock(ip, lockflags);
-			error = xfs_qm_dqget(mp, NULL, uid,
-						 XFS_DQ_USER,
-						 XFS_QMOPT_DQALLOC,
-						 &uq);
+			error = xfs_qm_dqget(mp, uid, XFS_DQ_USER, true, &uq);
 			if (error) {
 				ASSERT(error != -ENOENT);
 				return error;
@@ -1720,10 +1717,7 @@ xfs_qm_vop_dqalloc(
 	if ((flags & XFS_QMOPT_GQUOTA) && XFS_IS_GQUOTA_ON(mp)) {
 		if (ip->i_d.di_gid != gid) {
 			xfs_iunlock(ip, lockflags);
-			error = xfs_qm_dqget(mp, NULL, gid,
-						 XFS_DQ_GROUP,
-						 XFS_QMOPT_DQALLOC,
-						 &gq);
+			error = xfs_qm_dqget(mp, gid, XFS_DQ_GROUP, true, &gq);
 			if (error) {
 				ASSERT(error != -ENOENT);
 				goto error_rele;
@@ -1739,10 +1733,8 @@ xfs_qm_vop_dqalloc(
 	if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) {
 		if (xfs_get_projid(ip) != prid) {
 			xfs_iunlock(ip, lockflags);
-			error = xfs_qm_dqget(mp, NULL, (xfs_dqid_t)prid,
-						 XFS_DQ_PROJ,
-						 XFS_QMOPT_DQALLOC,
-						 &pq);
+			error = xfs_qm_dqget(mp, (xfs_dqid_t)prid, XFS_DQ_PROJ,
+					true, &pq);
 			if (error) {
 				ASSERT(error != -ENOENT);
 				goto error_rele;
@@ -1933,7 +1925,7 @@ xfs_qm_vop_rename_dqattach(
 		 */
 		if (i == 0 || ip != i_tab[i-1]) {
 			if (XFS_NOT_DQATTACHED(mp, ip)) {
-				error = xfs_qm_dqattach(ip, 0);
+				error = xfs_qm_dqattach(ip);
 				if (error)
 					return error;
 			}
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 2975a822e9f0..e3129b280423 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -170,8 +170,10 @@ extern void		xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint);
 
 /* quota ops */
 extern int		xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);
-extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t *,
-					uint, struct qc_dqblk *, uint);
+extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t,
+					uint, struct qc_dqblk *);
+extern int		xfs_qm_scall_getquota_next(struct xfs_mount *,
+					xfs_dqid_t *, uint, struct qc_dqblk *);
 extern int		xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint,
 					struct qc_dqblk *);
 extern int		xfs_qm_scall_quotaon(struct xfs_mount *, uint);
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 2be6d2735ca9..36b89e2c5eb9 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -72,7 +72,7 @@ xfs_qm_statvfs(
 	xfs_mount_t		*mp = ip->i_mount;
 	xfs_dquot_t		*dqp;
 
-	if (!xfs_qm_dqget(mp, NULL, xfs_get_projid(ip), XFS_DQ_PROJ, 0, &dqp)) {
+	if (!xfs_qm_dqget(mp, xfs_get_projid(ip), XFS_DQ_PROJ, false, &dqp)) {
 		xfs_fill_statvfs_from_dquot(statp, dqp);
 		xfs_qm_dqput(dqp);
 	}
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 9cb5c381b01c..3e05d300b14e 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -425,7 +425,7 @@ xfs_qm_scall_setqlim(
 	 * a reference to the dquot, so it's safe to do this unlock/lock without
 	 * it being reclaimed in the mean time.
 	 */
-	error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp);
+	error = xfs_qm_dqget(mp, id, type, true, &dqp);
 	if (error) {
 		ASSERT(error != -ENOENT);
 		goto out_unlock;
@@ -622,39 +622,14 @@ out:
 	return error;
 }
 
-
-int
-xfs_qm_scall_getquota(
+/* Fill out the quota context. */
+static void
+xfs_qm_scall_getquota_fill_qc(
 	struct xfs_mount	*mp,
-	xfs_dqid_t		*id,
 	uint			type,
-	struct qc_dqblk		*dst,
-	uint			dqget_flags)
+	const struct xfs_dquot	*dqp,
+	struct qc_dqblk		*dst)
 {
-	struct xfs_dquot	*dqp;
-	int			error;
-
-	/*
-	 * Try to get the dquot. We don't want it allocated on disk, so
-	 * we aren't passing the XFS_QMOPT_DOALLOC flag. If it doesn't
-	 * exist, we'll get ENOENT back.
-	 */
-	error = xfs_qm_dqget(mp, NULL, *id, type, dqget_flags, &dqp);
-	if (error)
-		return error;
-
-	/*
-	 * If everything's NULL, this dquot doesn't quite exist as far as
-	 * our utility programs are concerned.
-	 */
-	if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
-		error = -ENOENT;
-		goto out_put;
-	}
-
-	/* Fill in the ID we actually read from disk */
-	*id = be32_to_cpu(dqp->q_core.d_id);
-
 	memset(dst, 0, sizeof(*dst));
 	dst->d_spc_hardlimit =
 		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
@@ -696,7 +671,7 @@ xfs_qm_scall_getquota(
 	if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) ||
 	     (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) ||
 	     (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) &&
-	    *id != 0) {
+	    dqp->q_core.d_id != 0) {
 		if ((dst->d_space > dst->d_spc_softlimit) &&
 		    (dst->d_spc_softlimit > 0)) {
 			ASSERT(dst->d_spc_timer != 0);
@@ -707,11 +682,69 @@ xfs_qm_scall_getquota(
 		}
 	}
 #endif
+}
+
+/* Return the quota information for the dquot matching id. */
+int
+xfs_qm_scall_getquota(
+	struct xfs_mount	*mp,
+	xfs_dqid_t		id,
+	uint			type,
+	struct qc_dqblk		*dst)
+{
+	struct xfs_dquot	*dqp;
+	int			error;
+
+	/*
+	 * Try to get the dquot. We don't want it allocated on disk, so don't
+	 * set doalloc. If it doesn't exist, we'll get ENOENT back.
+	 */
+	error = xfs_qm_dqget(mp, id, type, false, &dqp);
+	if (error)
+		return error;
+
+	/*
+	 * If everything's NULL, this dquot doesn't quite exist as far as
+	 * our utility programs are concerned.
+	 */
+	if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
+		error = -ENOENT;
+		goto out_put;
+	}
+
+	xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst);
+
 out_put:
 	xfs_qm_dqput(dqp);
 	return error;
 }
 
+/*
+ * Return the quota information for the first initialized dquot whose id
+ * is at least as high as id.
+ */
+int
+xfs_qm_scall_getquota_next(
+	struct xfs_mount	*mp,
+	xfs_dqid_t		*id,
+	uint			type,
+	struct qc_dqblk		*dst)
+{
+	struct xfs_dquot	*dqp;
+	int			error;
+
+	error = xfs_qm_dqget_next(mp, *id, type, &dqp);
+	if (error)
+		return error;
+
+	/* Fill in the ID we actually read from disk */
+	*id = be32_to_cpu(dqp->q_core.d_id);
+
+	xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst);
+
+	xfs_qm_dqput(dqp);
+	return error;
+}
 
 STATIC int
 xfs_dqrele_inode(
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index ce6506adab7b..3edf52b14919 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -48,6 +48,22 @@ struct xfs_trans;
 	 (XFS_IS_PQUOTA_ON(mp) && \
 		(mp->m_sb.sb_qflags & XFS_PQUOTA_CHKD) == 0))
 
+static inline uint
+xfs_quota_chkd_flag(
+	uint		dqtype)
+{
+	switch (dqtype) {
+	case XFS_DQ_USER:
+		return XFS_UQUOTA_CHKD;
+	case XFS_DQ_GROUP:
+		return XFS_GQUOTA_CHKD;
+	case XFS_DQ_PROJ:
+		return XFS_PQUOTA_CHKD;
+	default:
+		return 0;
+	}
+}
+
 /*
  * The structure kept inside the xfs_trans_t keep track of dquot changes
  * within a transaction and apply them later.
@@ -90,8 +106,8 @@ extern struct xfs_dquot *xfs_qm_vop_chown(struct xfs_trans *,
 extern int xfs_qm_vop_chown_reserve(struct xfs_trans *, struct xfs_inode *,
 		struct xfs_dquot *, struct xfs_dquot *,
 		struct xfs_dquot *, uint);
-extern int xfs_qm_dqattach(struct xfs_inode *, uint);
-extern int xfs_qm_dqattach_locked(struct xfs_inode *, uint);
+extern int xfs_qm_dqattach(struct xfs_inode *);
+extern int xfs_qm_dqattach_locked(struct xfs_inode *ip, bool doalloc);
 extern void xfs_qm_dqdetach(struct xfs_inode *);
 extern void xfs_qm_dqrele(struct xfs_dquot *);
 extern void xfs_qm_statvfs(struct xfs_inode *, struct kstatfs *);
@@ -132,7 +148,7 @@ static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp,
 #define xfs_qm_vop_rename_dqattach(it)					(0)
 #define xfs_qm_vop_chown(tp, ip, old, new)				(NULL)
 #define xfs_qm_vop_chown_reserve(tp, ip, u, g, p, fl)			(0)
-#define xfs_qm_dqattach(ip, fl)						(0)
+#define xfs_qm_dqattach(ip)						(0)
 #define xfs_qm_dqattach_locked(ip, fl)					(0)
 #define xfs_qm_dqdetach(ip)
 #define xfs_qm_dqrele(d)
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index a65108594a07..c93fc913dffb 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -239,8 +239,7 @@ xfs_fs_get_dqblk(
 		return -ESRCH;
 
 	id = from_kqid(&init_user_ns, qid);
-	return xfs_qm_scall_getquota(mp, &id,
-				      xfs_quota_type(qid.type), qdq, 0);
+	return xfs_qm_scall_getquota(mp, id, xfs_quota_type(qid.type), qdq);
 }
 
 /* Return quota info for active quota >= this qid */
@@ -260,9 +259,8 @@ xfs_fs_get_nextdqblk(
 		return -ESRCH;
 
 	id = from_kqid(&init_user_ns, *qid);
-	ret = xfs_qm_scall_getquota(mp, &id,
-				    xfs_quota_type(qid->type), qdq,
-				    XFS_QMOPT_DQNEXT);
+	ret = xfs_qm_scall_getquota_next(mp, &id, xfs_quota_type(qid->type),
+			qdq);
 	if (ret)
 		return ret;
 
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 15c9393dd7a7..e5866b714d5f 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -159,7 +159,7 @@ STATIC void
 xfs_cui_item_unlock(
 	struct xfs_log_item	*lip)
 {
-	if (lip->li_flags & XFS_LI_ABORTED)
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
 		xfs_cui_release(CUI_ITEM(lip));
 }
 
@@ -310,7 +310,7 @@ xfs_cud_item_unlock(
 {
 	struct xfs_cud_log_item	*cudp = CUD_ITEM(lip);
 
-	if (lip->li_flags & XFS_LI_ABORTED) {
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
 		xfs_cui_release(cudp->cud_cuip);
 		kmem_zone_free(xfs_cud_zone, cudp);
 	}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index cdbd342a5249..713e857d9ffa 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -305,7 +305,7 @@ xfs_reflink_reserve_cow(
 	 * Fork all the shared blocks from our write offset until the end of
 	 * the extent.
 	 */
-	error = xfs_qm_dqattach_locked(ip, 0);
+	error = xfs_qm_dqattach_locked(ip, false);
 	if (error)
 		return error;
 
@@ -431,7 +431,7 @@ retry:
 		if (error)
 			return error;
 
-		error = xfs_qm_dqattach_locked(ip, 0);
+		error = xfs_qm_dqattach_locked(ip, false);
 		if (error)
 			goto out;
 		goto retry;
@@ -552,6 +552,9 @@ xfs_reflink_trim_irec_to_next_cow(
  *
  * If cancel_real is true this function cancels all COW fork extents for the
  * inode; if cancel_real is false, real extents are not cleared.
+ *
+ * Caller must have already joined the inode to the current transaction. The
+ * inode will be joined to the transaction returned to the caller.
  */
 int
 xfs_reflink_cancel_cow_blocks(
@@ -592,7 +595,6 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			xfs_trans_ijoin(*tpp, ip, 0);
 			xfs_defer_init(&dfops, &firstfsb);
 
 			/* Free the CoW orphan record. */
@@ -1359,7 +1361,7 @@ xfs_reflink_remap_range(
 		goto out_unlock;
 
 	/* Attach dquots to dest inode before changing block map */
-	ret = xfs_qm_dqattach(dest, 0);
+	ret = xfs_qm_dqattach(dest);
 	if (ret)
 		goto out_unlock;
 
@@ -1551,7 +1553,12 @@ next:
 	return 0;
 }
 
-/* Clear the inode reflink flag if there are no shared extents. */
+/*
+ * Clear the inode reflink flag if there are no shared extents.
+ *
+ * The caller is responsible for joining the inode to the transaction passed in.
+ * The inode will be joined to the transaction that is returned to the caller.
+ */
 int
 xfs_reflink_clear_inode_flag(
 	struct xfs_inode	*ip,
@@ -1578,7 +1585,6 @@ xfs_reflink_clear_inode_flag(
 	trace_xfs_reflink_unset_inode_flag(ip);
 	ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
 	xfs_inode_clear_cowblocks_tag(ip);
-	xfs_trans_ijoin(*tpp, ip, 0);
 	xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
 
 	return error;
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 06a07846c9b3..e5b5b3e7ef82 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -158,7 +158,7 @@ STATIC void
 xfs_rui_item_unlock(
 	struct xfs_log_item	*lip)
 {
-	if (lip->li_flags & XFS_LI_ABORTED)
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
 		xfs_rui_release(RUI_ITEM(lip));
 }
 
@@ -331,7 +331,7 @@ xfs_rud_item_unlock(
 {
 	struct xfs_rud_log_item	*rudp = RUD_ITEM(lip);
 
-	if (lip->li_flags & XFS_LI_ABORTED) {
+	if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
 		xfs_rui_release(rudp->rud_ruip);
 		kmem_zone_free(xfs_rud_zone, rudp);
 	}
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index dfee3c991155..52632ab727f7 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -23,9 +23,14 @@
 struct xfs_mount;
 struct xfs_trans;
 
+/*
+ * XXX: Most of the realtime allocation functions deal in units of realtime
+ * extents, not realtime blocks.  This looks funny when paired with the type
+ * name and screams for a larger cleanup.
+ */
 struct xfs_rtalloc_rec {
-	xfs_rtblock_t		ar_startblock;
-	xfs_rtblock_t		ar_blockcount;
+	xfs_rtblock_t		ar_startext;
+	xfs_rtblock_t		ar_extcount;
 };
 
 typedef int (*xfs_rtalloc_query_range_fn)(
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index 056e12b421eb..1cc79907b377 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -113,6 +113,7 @@ void xfs_stats_clearall(struct xfsstats __percpu *stats)
 	}
 }
 
+#ifdef CONFIG_PROC_FS
 /* legacy quota interfaces */
 #ifdef CONFIG_XFS_QUOTA
 static int xqm_proc_show(struct seq_file *m, void *v)
@@ -124,18 +125,6 @@ static int xqm_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int xqm_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, xqm_proc_show, NULL);
-}
-
-static const struct file_operations xqm_proc_fops = {
-	.open		= xqm_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /* legacy quota stats interface no 2 */
 static int xqmstat_proc_show(struct seq_file *m, void *v)
 {
@@ -147,22 +136,8 @@ static int xqmstat_proc_show(struct seq_file *m, void *v)
 	seq_putc(m, '\n');
 	return 0;
 }
-
-static int xqmstat_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, xqmstat_proc_show, NULL);
-}
-
-static const struct file_operations xqmstat_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= xqmstat_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif /* CONFIG_XFS_QUOTA */
 
-#ifdef CONFIG_PROC_FS
 int
 xfs_init_procfs(void)
 {
@@ -174,11 +149,9 @@ xfs_init_procfs(void)
 		goto out;
 
 #ifdef CONFIG_XFS_QUOTA
-	if (!proc_create("fs/xfs/xqmstat", 0, NULL,
-			 &xqmstat_proc_fops))
+	if (!proc_create_single("fs/xfs/xqmstat", 0, NULL, xqmstat_proc_show))
 		goto out;
-	if (!proc_create("fs/xfs/xqm", 0, NULL,
-			 &xqm_proc_fops))
+	if (!proc_create_single("fs/xfs/xqm", 0, NULL, xqm_proc_show))
 		goto out;
 #endif
 	return 0;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d71424052917..ed67389f4948 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -63,7 +63,7 @@
 #include <linux/parser.h>
 
 static const struct super_operations xfs_super_operations;
-struct bio_set *xfs_ioend_bioset;
+struct bio_set xfs_ioend_bioset;
 
 static struct kset *xfs_kset;		/* top-level xfs sysfs dir */
 #ifdef DEBUG
@@ -1372,7 +1372,6 @@ xfs_fs_remount(
 		 */
 		xfs_restore_resvblks(mp);
 		xfs_log_work_queue(mp);
-		xfs_queue_eofblocks(mp);
 
 		/* Recover any CoW blocks that never got remapped. */
 		error = xfs_reflink_recover_cow(mp);
@@ -1382,7 +1381,7 @@ xfs_fs_remount(
 			xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 			return error;
 		}
-		xfs_queue_cowblocks(mp);
+		xfs_icache_enable_reclaim(mp);
 
 		/* Create the per-AG metadata reservation pool .*/
 		error = xfs_fs_reserve_ag_blocks(mp);
@@ -1392,8 +1391,13 @@ xfs_fs_remount(
 
 	/* rw -> ro */
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & SB_RDONLY)) {
+		/*
+		 * Cancel background eofb scanning so it cannot race with the
+		 * final log force+buftarg wait and deadlock the remount.
+		 */
+		xfs_icache_disable_reclaim(mp);
+
 		/* Get rid of any leftover CoW reservations... */
-		cancel_delayed_work_sync(&mp->m_cowblocks_work);
 		error = xfs_icache_free_cowblocks(mp, NULL);
 		if (error) {
 			xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
@@ -1416,12 +1420,6 @@ xfs_fs_remount(
 		 */
 		xfs_save_resvblks(mp);
 
-		/*
-		 * Cancel background eofb scanning so it cannot race with the
-		 * final log force+buftarg wait and deadlock the remount.
-		 */
-		cancel_delayed_work_sync(&mp->m_eofblocks_work);
-
 		xfs_quiesce_attr(mp);
 		mp->m_flags |= XFS_MOUNT_RDONLY;
 	}
@@ -1441,6 +1439,7 @@ xfs_fs_freeze(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
+	xfs_icache_disable_reclaim(mp);
 	xfs_save_resvblks(mp);
 	xfs_quiesce_attr(mp);
 	return xfs_sync_sb(mp, true);
@@ -1454,6 +1453,7 @@ xfs_fs_unfreeze(
 
 	xfs_restore_resvblks(mp);
 	xfs_log_work_queue(mp);
+	xfs_icache_enable_reclaim(mp);
 	return 0;
 }
 
@@ -1635,6 +1635,17 @@ xfs_fs_fill_super(
 #endif
 	sb->s_op = &xfs_super_operations;
 
+	/*
+	 * Delay mount work if the debug hook is set. This is debug
+	 * instrumention to coordinate simulation of xfs mount failures with
+	 * VFS superblock operations
+	 */
+	if (xfs_globals.mount_delay) {
+		xfs_notice(mp, "Delaying mount for %d seconds.",
+			xfs_globals.mount_delay);
+		msleep(xfs_globals.mount_delay * 1000);
+	}
+
 	if (silent)
 		flags |= XFS_MFSI_QUIET;
 
@@ -1690,11 +1701,17 @@ xfs_fs_fill_super(
 		sb->s_flags |= SB_I_VERSION;
 
 	if (mp->m_flags & XFS_MOUNT_DAX) {
+		bool rtdev_is_dax = false, datadev_is_dax;
+
 		xfs_warn(mp,
 		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
 
-		error = bdev_dax_supported(sb, sb->s_blocksize);
-		if (error) {
+		datadev_is_dax = bdev_dax_supported(mp->m_ddev_targp->bt_bdev,
+			sb->s_blocksize);
+		if (mp->m_rtdev_targp)
+			rtdev_is_dax = bdev_dax_supported(
+				mp->m_rtdev_targp->bt_bdev, sb->s_blocksize);
+		if (!rtdev_is_dax && !datadev_is_dax) {
 			xfs_alert(mp,
 			"DAX unsupported by block device. Turning off DAX.");
 			mp->m_flags &= ~XFS_MOUNT_DAX;
@@ -1761,6 +1778,7 @@ xfs_fs_fill_super(
  out_close_devices:
 	xfs_close_devices(mp);
  out_free_fsname:
+	sb->s_fs_info = NULL;
 	xfs_free_fsname(mp);
 	kfree(mp);
  out:
@@ -1778,6 +1796,10 @@ xfs_fs_put_super(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
+	/* if ->fill_super failed, we have no mount to tear down */
+	if (!sb->s_fs_info)
+		return;
+
 	xfs_notice(mp, "Unmounting Filesystem");
 	xfs_filestream_unmount(mp);
 	xfs_unmountfs(mp);
@@ -1787,6 +1809,8 @@ xfs_fs_put_super(
 	xfs_destroy_percpu_counters(mp);
 	xfs_destroy_mount_workqueues(mp);
 	xfs_close_devices(mp);
+
+	sb->s_fs_info = NULL;
 	xfs_free_fsname(mp);
 	kfree(mp);
 }
@@ -1806,6 +1830,9 @@ xfs_fs_nr_cached_objects(
 	struct super_block	*sb,
 	struct shrink_control	*sc)
 {
+	/* Paranoia: catch incorrect calls during mount setup or teardown */
+	if (WARN_ON_ONCE(!sb->s_fs_info))
+		return 0;
 	return xfs_reclaim_inodes_count(XFS_M(sb));
 }
 
@@ -1845,10 +1872,9 @@ MODULE_ALIAS_FS("xfs");
 STATIC int __init
 xfs_init_zones(void)
 {
-	xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE,
+	if (bioset_init(&xfs_ioend_bioset, 4 * MAX_BUF_PER_PAGE,
 			offsetof(struct xfs_ioend, io_inline_bio),
-			BIOSET_NEED_BVECS);
-	if (!xfs_ioend_bioset)
+			BIOSET_NEED_BVECS))
 		goto out;
 
 	xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
@@ -1880,11 +1906,6 @@ xfs_init_zones(void)
 	if (!xfs_trans_zone)
 		goto out_destroy_ifork_zone;
 
-	xfs_log_item_desc_zone =
-		kmem_zone_init(sizeof(struct xfs_log_item_desc),
-			       "xfs_log_item_desc");
-	if (!xfs_log_item_desc_zone)
-		goto out_destroy_trans_zone;
 
 	/*
 	 * The size of the zone allocated buf log item is the maximum
@@ -1894,7 +1915,7 @@ xfs_init_zones(void)
 	xfs_buf_item_zone = kmem_zone_init(sizeof(struct xfs_buf_log_item),
 					   "xfs_buf_item");
 	if (!xfs_buf_item_zone)
-		goto out_destroy_log_item_desc_zone;
+		goto out_destroy_trans_zone;
 
 	xfs_efd_zone = kmem_zone_init((sizeof(xfs_efd_log_item_t) +
 			((XFS_EFD_MAX_FAST_EXTENTS - 1) *
@@ -1982,8 +2003,6 @@ xfs_init_zones(void)
 	kmem_zone_destroy(xfs_efd_zone);
  out_destroy_buf_item_zone:
 	kmem_zone_destroy(xfs_buf_item_zone);
- out_destroy_log_item_desc_zone:
-	kmem_zone_destroy(xfs_log_item_desc_zone);
  out_destroy_trans_zone:
 	kmem_zone_destroy(xfs_trans_zone);
  out_destroy_ifork_zone:
@@ -1997,7 +2016,7 @@ xfs_init_zones(void)
  out_destroy_log_ticket_zone:
 	kmem_zone_destroy(xfs_log_ticket_zone);
  out_free_ioend_bioset:
-	bioset_free(xfs_ioend_bioset);
+	bioset_exit(&xfs_ioend_bioset);
  out:
 	return -ENOMEM;
 }
@@ -2022,14 +2041,13 @@ xfs_destroy_zones(void)
 	kmem_zone_destroy(xfs_efi_zone);
 	kmem_zone_destroy(xfs_efd_zone);
 	kmem_zone_destroy(xfs_buf_item_zone);
-	kmem_zone_destroy(xfs_log_item_desc_zone);
 	kmem_zone_destroy(xfs_trans_zone);
 	kmem_zone_destroy(xfs_ifork_zone);
 	kmem_zone_destroy(xfs_da_state_zone);
 	kmem_zone_destroy(xfs_btree_cur_zone);
 	kmem_zone_destroy(xfs_bmap_free_item_zone);
 	kmem_zone_destroy(xfs_log_ticket_zone);
-	bioset_free(xfs_ioend_bioset);
+	bioset_exit(&xfs_ioend_bioset);
 }
 
 STATIC int __init
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 5b66ac12913c..aed03da637d4 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -259,6 +259,7 @@ xfs_symlink(
 	 * bmapi or the directory create code.
 	 */
 	xfs_defer_init(&dfops, &first_block);
+	tp->t_agfl_dfops = &dfops;
 
 	/*
 	 * Allocate an inode for the symlink.
@@ -488,16 +489,11 @@ xfs_inactive_symlink_rmt(
 	error = xfs_defer_finish(&tp, &dfops);
 	if (error)
 		goto error_bmap_cancel;
-	/*
-	 * The first xact was committed, so add the inode to the new one.
-	 * Mark it dirty so it will be logged and moved forward in the log as
-	 * part of every commit.
-	 */
-	xfs_trans_ijoin(tp, ip, 0);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
 	/*
 	 * Commit the transaction containing extent freeing and EFDs.
 	 */
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	error = xfs_trans_commit(tp);
 	if (error) {
 		ASSERT(XFS_FORCED_SHUTDOWN(mp));
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index 82afee005140..b53a33e69932 100644
--- a/fs/xfs/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
@@ -95,6 +95,7 @@ extern xfs_param_t	xfs_params;
 
 struct xfs_globals {
 	int	log_recovery_delay;	/* log recovery delay (secs) */
+	int	mount_delay;		/* mount setup delay (secs) */
 	bool	bug_on_assert;		/* BUG() the kernel on assert failure */
 };
 extern struct xfs_globals	xfs_globals;
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 8b2ccc234f36..2d5cd2529f8e 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -165,9 +165,40 @@ log_recovery_delay_show(
 }
 XFS_SYSFS_ATTR_RW(log_recovery_delay);
 
+STATIC ssize_t
+mount_delay_store(
+	struct kobject	*kobject,
+	const char	*buf,
+	size_t		count)
+{
+	int		ret;
+	int		val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val < 0 || val > 60)
+		return -EINVAL;
+
+	xfs_globals.mount_delay = val;
+
+	return count;
+}
+
+STATIC ssize_t
+mount_delay_show(
+	struct kobject	*kobject,
+	char		*buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.mount_delay);
+}
+XFS_SYSFS_ATTR_RW(mount_delay);
+
 static struct attribute *xfs_dbg_attrs[] = {
 	ATTR_LIST(bug_on_assert),
 	ATTR_LIST(log_recovery_delay),
+	ATTR_LIST(mount_delay),
 	NULL,
 };
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 8955254b900e..9d4c4ca24fe6 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -441,8 +441,7 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class,
 		__field(unsigned, bli_recur)
 		__field(int, bli_refcount)
 		__field(unsigned, bli_flags)
-		__field(void *, li_desc)
-		__field(unsigned, li_flags)
+		__field(unsigned long, li_flags)
 	),
 	TP_fast_assign(
 		__entry->dev = bip->bli_buf->b_target->bt_dev;
@@ -455,12 +454,11 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class,
 		__entry->buf_hold = atomic_read(&bip->bli_buf->b_hold);
 		__entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count);
 		__entry->buf_lockval = bip->bli_buf->b_sema.count;
-		__entry->li_desc = bip->bli_item.li_desc;
 		__entry->li_flags = bip->bli_item.li_flags;
 	),
 	TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
 		  "lock %d flags %s recur %d refcount %d bliflags %s "
-		  "lidesc %p liflags %s",
+		  "liflags %s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long long)__entry->buf_bno,
 		  __entry->buf_len,
@@ -471,7 +469,6 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class,
 		  __entry->bli_recur,
 		  __entry->bli_refcount,
 		  __print_flags(__entry->bli_flags, "|", XFS_BLI_FLAGS),
-		  __entry->li_desc,
 		  __print_flags(__entry->li_flags, "|", XFS_LI_FLAGS))
 )
 
@@ -1018,7 +1015,7 @@ DECLARE_EVENT_CLASS(xfs_log_item_class,
 		__field(dev_t, dev)
 		__field(void *, lip)
 		__field(uint, type)
-		__field(uint, flags)
+		__field(unsigned long, flags)
 		__field(xfs_lsn_t, lsn)
 	),
 	TP_fast_assign(
@@ -1070,7 +1067,7 @@ DECLARE_EVENT_CLASS(xfs_ail_class,
 		__field(dev_t, dev)
 		__field(void *, lip)
 		__field(uint, type)
-		__field(uint, flags)
+		__field(unsigned long, flags)
 		__field(xfs_lsn_t, old_lsn)
 		__field(xfs_lsn_t, new_lsn)
 	),
@@ -1750,6 +1747,7 @@ DECLARE_EVENT_CLASS(xfs_attr_class,
 		__field(int, namelen)
 		__field(int, valuelen)
 		__field(xfs_dahash_t, hashval)
+		__field(int, flags)
 		__field(int, op_flags)
 	),
 	TP_fast_assign(
@@ -1760,10 +1758,11 @@ DECLARE_EVENT_CLASS(xfs_attr_class,
 		__entry->namelen = args->namelen;
 		__entry->valuelen = args->valuelen;
 		__entry->hashval = args->hashval;
+		__entry->flags = args->flags;
 		__entry->op_flags = args->op_flags;
 	),
 	TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d valuelen %d "
-		  "hashval 0x%x op_flags %s",
+		  "hashval 0x%x flags %s op_flags %s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->namelen,
@@ -1771,6 +1770,7 @@ DECLARE_EVENT_CLASS(xfs_attr_class,
 		  __entry->namelen,
 		  __entry->valuelen,
 		  __entry->hashval,
+		  __print_flags(__entry->flags, "|", XFS_ATTR_FLAGS),
 		  __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS))
 )
 
@@ -2243,30 +2243,35 @@ struct xfs_defer_pending;
 struct xfs_defer_ops;
 
 DECLARE_EVENT_CLASS(xfs_defer_class,
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop),
-	TP_ARGS(mp, dop),
+	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop,
+		 unsigned long caller_ip),
+	TP_ARGS(mp, dop, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(void *, dop)
 		__field(char, committed)
 		__field(char, low)
+		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
 		__entry->dev = mp ? mp->m_super->s_dev : 0;
 		__entry->dop = dop;
 		__entry->committed = dop->dop_committed;
 		__entry->low = dop->dop_low;
+		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d",
+	TP_printk("dev %d:%d ops %p committed %d low %d, caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dop,
 		  __entry->committed,
-		  __entry->low)
+		  __entry->low,
+		  (char *)__entry->caller_ip)
 )
 #define DEFINE_DEFER_EVENT(name) \
 DEFINE_EVENT(xfs_defer_class, name, \
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop), \
-	TP_ARGS(mp, dop))
+	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, \
+		 unsigned long caller_ip), \
+	TP_ARGS(mp, dop, caller_ip))
 
 DECLARE_EVENT_CLASS(xfs_defer_error_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, int error),
@@ -2433,6 +2438,8 @@ DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
 #define DEFINE_BMAP_FREE_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT
 DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_defer);
 DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_deferred);
+DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_defer);
+DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_deferred);
 
 /* rmap tracepoints */
 DECLARE_EVENT_CLASS(xfs_rmap_class,
@@ -3346,6 +3353,43 @@ TRACE_EVENT(xfs_trans_resv_calc,
 		  __entry->logflags)
 );
 
+DECLARE_EVENT_CLASS(xfs_trans_class,
+	TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip),
+	TP_ARGS(tp, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(uint32_t, tid)
+		__field(uint32_t, flags)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = tp->t_mountp->m_super->s_dev;
+		__entry->tid = 0;
+		if (tp->t_ticket)
+			__entry->tid = tp->t_ticket->t_tid;
+		__entry->flags = tp->t_flags;
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d trans %x flags 0x%x caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->tid,
+		  __entry->flags,
+		  (char *)__entry->caller_ip)
+)
+
+#define DEFINE_TRANS_EVENT(name) \
+DEFINE_EVENT(xfs_trans_class, name, \
+	TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), \
+	TP_ARGS(tp, caller_ip))
+DEFINE_TRANS_EVENT(xfs_trans_alloc);
+DEFINE_TRANS_EVENT(xfs_trans_cancel);
+DEFINE_TRANS_EVENT(xfs_trans_commit);
+DEFINE_TRANS_EVENT(xfs_trans_dup);
+DEFINE_TRANS_EVENT(xfs_trans_free);
+DEFINE_TRANS_EVENT(xfs_trans_roll);
+DEFINE_TRANS_EVENT(xfs_trans_add_item);
+DEFINE_TRANS_EVENT(xfs_trans_free_items);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index d6d8f9d129a7..fc7ba75b8b69 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -31,9 +31,9 @@
 #include "xfs_log.h"
 #include "xfs_trace.h"
 #include "xfs_error.h"
+#include "xfs_defer.h"
 
 kmem_zone_t	*xfs_trans_zone;
-kmem_zone_t	*xfs_log_item_desc_zone;
 
 #if defined(CONFIG_TRACEPOINTS)
 static void
@@ -79,6 +79,7 @@ xfs_trans_free(
 	xfs_extent_busy_sort(&tp->t_busy);
 	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
+	trace_xfs_trans_free(tp, _RET_IP_);
 	atomic_dec(&tp->t_mountp->m_active_trans);
 	if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_end_intwrite(tp->t_mountp->m_super);
@@ -94,11 +95,13 @@ xfs_trans_free(
  * blocks.  Locks and log items, however, are no inherited.  They must
  * be added to the new transaction explicitly.
  */
-STATIC xfs_trans_t *
+STATIC struct xfs_trans *
 xfs_trans_dup(
-	xfs_trans_t	*tp)
+	struct xfs_trans	*tp)
 {
-	xfs_trans_t	*ntp;
+	struct xfs_trans	*ntp;
+
+	trace_xfs_trans_dup(tp, _RET_IP_);
 
 	ntp = kmem_zone_zalloc(xfs_trans_zone, KM_SLEEP);
 
@@ -127,6 +130,7 @@ xfs_trans_dup(
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	tp->t_rtx_res = tp->t_rtx_res_used;
 	ntp->t_pflags = tp->t_pflags;
+	ntp->t_agfl_dfops = tp->t_agfl_dfops;
 
 	xfs_trans_dup_dqinfo(tp, ntp);
 
@@ -283,6 +287,8 @@ xfs_trans_alloc(
 		return error;
 	}
 
+	trace_xfs_trans_alloc(tp, _RET_IP_);
+
 	*tpp = tp;
 	return 0;
 }
@@ -727,73 +733,52 @@ out:
 	return;
 }
 
-/*
- * Add the given log item to the transaction's list of log items.
- *
- * The log item will now point to its new descriptor with its li_desc field.
- */
+/* Add the given log item to the transaction's list of log items. */
 void
 xfs_trans_add_item(
 	struct xfs_trans	*tp,
 	struct xfs_log_item	*lip)
 {
-	struct xfs_log_item_desc *lidp;
-
 	ASSERT(lip->li_mountp == tp->t_mountp);
 	ASSERT(lip->li_ailp == tp->t_mountp->m_ail);
+	ASSERT(list_empty(&lip->li_trans));
+	ASSERT(!test_bit(XFS_LI_DIRTY, &lip->li_flags));
 
-	lidp = kmem_zone_zalloc(xfs_log_item_desc_zone, KM_SLEEP | KM_NOFS);
-
-	lidp->lid_item = lip;
-	lidp->lid_flags = 0;
-	list_add_tail(&lidp->lid_trans, &tp->t_items);
-
-	lip->li_desc = lidp;
-}
-
-STATIC void
-xfs_trans_free_item_desc(
-	struct xfs_log_item_desc *lidp)
-{
-	list_del_init(&lidp->lid_trans);
-	kmem_zone_free(xfs_log_item_desc_zone, lidp);
+	list_add_tail(&lip->li_trans, &tp->t_items);
+	trace_xfs_trans_add_item(tp, _RET_IP_);
 }
 
 /*
- * Unlink and free the given descriptor.
+ * Unlink the log item from the transaction. the log item is no longer
+ * considered dirty in this transaction, as the linked transaction has
+ * finished, either by abort or commit completion.
  */
 void
 xfs_trans_del_item(
 	struct xfs_log_item	*lip)
 {
-	xfs_trans_free_item_desc(lip->li_desc);
-	lip->li_desc = NULL;
+	clear_bit(XFS_LI_DIRTY, &lip->li_flags);
+	list_del_init(&lip->li_trans);
 }
 
-/*
- * Unlock all of the items of a transaction and free all the descriptors
- * of that transaction.
- */
+/* Detach and unlock all of the items in a transaction */
 void
 xfs_trans_free_items(
 	struct xfs_trans	*tp,
 	xfs_lsn_t		commit_lsn,
 	bool			abort)
 {
-	struct xfs_log_item_desc *lidp, *next;
-
-	list_for_each_entry_safe(lidp, next, &tp->t_items, lid_trans) {
-		struct xfs_log_item	*lip = lidp->lid_item;
+	struct xfs_log_item	*lip, *next;
 
-		lip->li_desc = NULL;
+	trace_xfs_trans_free_items(tp, _RET_IP_);
 
+	list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) {
+		xfs_trans_del_item(lip);
 		if (commit_lsn != NULLCOMMITLSN)
 			lip->li_ops->iop_committing(lip, commit_lsn);
 		if (abort)
-			lip->li_flags |= XFS_LI_ABORTED;
+			set_bit(XFS_LI_ABORTED, &lip->li_flags);
 		lip->li_ops->iop_unlock(lip);
-
-		xfs_trans_free_item_desc(lidp);
 	}
 }
 
@@ -861,7 +846,7 @@ xfs_trans_committed_bulk(
 		xfs_lsn_t		item_lsn;
 
 		if (aborted)
-			lip->li_flags |= XFS_LI_ABORTED;
+			set_bit(XFS_LI_ABORTED, &lip->li_flags);
 		item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
 
 		/* item_lsn of -1 means the item needs no further processing */
@@ -936,6 +921,11 @@ __xfs_trans_commit(
 	int			error = 0;
 	int			sync = tp->t_flags & XFS_TRANS_SYNC;
 
+	ASSERT(!tp->t_agfl_dfops ||
+	       !xfs_defer_has_unfinished_work(tp->t_agfl_dfops) || regrant);
+
+	trace_xfs_trans_commit(tp, _RET_IP_);
+
 	/*
 	 * If there is nothing to be logged by the transaction,
 	 * then unlock all of the items associated with the
@@ -991,6 +981,7 @@ out_unreserve:
 		commit_lsn = xfs_log_done(mp, tp->t_ticket, NULL, regrant);
 		if (commit_lsn == -1 && !error)
 			error = -EIO;
+		tp->t_ticket = NULL;
 	}
 	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free_items(tp, NULLCOMMITLSN, !!error);
@@ -1022,6 +1013,8 @@ xfs_trans_cancel(
 	struct xfs_mount	*mp = tp->t_mountp;
 	bool			dirty = (tp->t_flags & XFS_TRANS_DIRTY);
 
+	trace_xfs_trans_cancel(tp, _RET_IP_);
+
 	/*
 	 * See if the caller is relying on us to shut down the
 	 * filesystem.  This happens in paths where we detect
@@ -1033,17 +1026,19 @@ xfs_trans_cancel(
 	}
 #ifdef DEBUG
 	if (!dirty && !XFS_FORCED_SHUTDOWN(mp)) {
-		struct xfs_log_item_desc *lidp;
+		struct xfs_log_item *lip;
 
-		list_for_each_entry(lidp, &tp->t_items, lid_trans)
-			ASSERT(!(lidp->lid_item->li_type == XFS_LI_EFD));
+		list_for_each_entry(lip, &tp->t_items, li_trans)
+			ASSERT(!(lip->li_type == XFS_LI_EFD));
 	}
 #endif
 	xfs_trans_unreserve_and_mod_sb(tp);
 	xfs_trans_unreserve_and_mod_dquots(tp);
 
-	if (tp->t_ticket)
+	if (tp->t_ticket) {
 		xfs_log_done(mp, tp->t_ticket, NULL, false);
+		tp->t_ticket = NULL;
+	}
 
 	/* mark this thread as no longer being in a transaction */
 	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
@@ -1067,6 +1062,8 @@ xfs_trans_roll(
 	struct xfs_trans_res	tres;
 	int			error;
 
+	trace_xfs_trans_roll(trans, _RET_IP_);
+
 	/*
 	 * Copy the critical parameters from one trans to the next.
 	 */
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 9d542dfe0052..29706b8b3bd4 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -27,7 +27,6 @@ struct xfs_efi_log_item;
 struct xfs_inode;
 struct xfs_item_ops;
 struct xfs_log_iovec;
-struct xfs_log_item_desc;
 struct xfs_mount;
 struct xfs_trans;
 struct xfs_trans_res;
@@ -43,12 +42,12 @@ struct xfs_bud_log_item;
 
 typedef struct xfs_log_item {
 	struct list_head		li_ail;		/* AIL pointers */
+	struct list_head		li_trans;	/* transaction list */
 	xfs_lsn_t			li_lsn;		/* last on-disk lsn */
-	struct xfs_log_item_desc	*li_desc;	/* ptr to current desc*/
 	struct xfs_mount		*li_mountp;	/* ptr to fs mount */
 	struct xfs_ail			*li_ailp;	/* ptr to AIL */
 	uint				li_type;	/* item type */
-	uint				li_flags;	/* misc flags */
+	unsigned long			li_flags;	/* misc flags */
 	struct xfs_buf			*li_buf;	/* real buffer pointer */
 	struct list_head		li_bio_list;	/* buffer item list */
 	void				(*li_cb)(struct xfs_buf *,
@@ -64,14 +63,21 @@ typedef struct xfs_log_item {
 	xfs_lsn_t			li_seq;		/* CIL commit seq */
 } xfs_log_item_t;
 
-#define	XFS_LI_IN_AIL	0x1
-#define	XFS_LI_ABORTED	0x2
-#define	XFS_LI_FAILED	0x4
+/*
+ * li_flags use the (set/test/clear)_bit atomic interfaces because updates can
+ * race with each other and we don't want to have to use the AIL lock to
+ * serialise all updates.
+ */
+#define	XFS_LI_IN_AIL	0
+#define	XFS_LI_ABORTED	1
+#define	XFS_LI_FAILED	2
+#define	XFS_LI_DIRTY	3	/* log item dirty in transaction */
 
 #define XFS_LI_FLAGS \
-	{ XFS_LI_IN_AIL,	"IN_AIL" }, \
-	{ XFS_LI_ABORTED,	"ABORTED" }, \
-	{ XFS_LI_FAILED,	"FAILED" }
+	{ (1 << XFS_LI_IN_AIL),		"IN_AIL" }, \
+	{ (1 << XFS_LI_ABORTED),	"ABORTED" }, \
+	{ (1 << XFS_LI_FAILED),		"FAILED" }, \
+	{ (1 << XFS_LI_DIRTY),		"DIRTY" }
 
 struct xfs_item_ops {
 	void (*iop_size)(xfs_log_item_t *, int *, int *);
@@ -111,6 +117,7 @@ typedef struct xfs_trans {
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
+	struct xfs_defer_ops	*t_agfl_dfops;	/* optional agfl fixup dfops */
 	unsigned int		t_flags;	/* misc flags */
 	int64_t			t_icount_delta;	/* superblock icount change */
 	int64_t			t_ifree_delta;	/* superblock ifree change */
@@ -228,7 +235,8 @@ struct xfs_efd_log_item	*xfs_trans_get_efd(struct xfs_trans *,
 				  uint);
 int		xfs_trans_free_extent(struct xfs_trans *,
 				      struct xfs_efd_log_item *, xfs_fsblock_t,
-				      xfs_extlen_t, struct xfs_owner_info *);
+				      xfs_extlen_t, struct xfs_owner_info *,
+				      bool);
 int		xfs_trans_commit(struct xfs_trans *);
 int		xfs_trans_roll(struct xfs_trans **);
 int		xfs_trans_roll_inode(struct xfs_trans **, struct xfs_inode *);
@@ -242,7 +250,6 @@ void		xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
 					struct xfs_buf *src_bp);
 
 extern kmem_zone_t	*xfs_trans_zone;
-extern kmem_zone_t	*xfs_log_item_desc_zone;
 
 /* rmap updates */
 enum xfs_rmap_intent_type;
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index d4a2445215e6..41e280ef1483 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -32,30 +32,51 @@
 #ifdef DEBUG
 /*
  * Check that the list is sorted as it should be.
+ *
+ * Called with the ail lock held, but we don't want to assert fail with it
+ * held otherwise we'll lock everything up and won't be able to debug the
+ * cause. Hence we sample and check the state under the AIL lock and return if
+ * everything is fine, otherwise we drop the lock and run the ASSERT checks.
+ * Asserts may not be fatal, so pick the lock back up and continue onwards.
  */
 STATIC void
 xfs_ail_check(
-	struct xfs_ail	*ailp,
-	xfs_log_item_t	*lip)
+	struct xfs_ail		*ailp,
+	struct xfs_log_item	*lip)
 {
-	xfs_log_item_t	*prev_lip;
+	struct xfs_log_item	*prev_lip;
+	struct xfs_log_item	*next_lip;
+	xfs_lsn_t		prev_lsn = NULLCOMMITLSN;
+	xfs_lsn_t		next_lsn = NULLCOMMITLSN;
+	xfs_lsn_t		lsn;
+	bool			in_ail;
+
 
 	if (list_empty(&ailp->ail_head))
 		return;
 
 	/*
-	 * Check the next and previous entries are valid.
+	 * Sample then check the next and previous entries are valid.
 	 */
-	ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0);
-	prev_lip = list_entry(lip->li_ail.prev, xfs_log_item_t, li_ail);
+	in_ail = test_bit(XFS_LI_IN_AIL, &lip->li_flags);
+	prev_lip = list_entry(lip->li_ail.prev, struct xfs_log_item, li_ail);
 	if (&prev_lip->li_ail != &ailp->ail_head)
-		ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0);
-
-	prev_lip = list_entry(lip->li_ail.next, xfs_log_item_t, li_ail);
-	if (&prev_lip->li_ail != &ailp->ail_head)
-		ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0);
+		prev_lsn = prev_lip->li_lsn;
+	next_lip = list_entry(lip->li_ail.next, struct xfs_log_item, li_ail);
+	if (&next_lip->li_ail != &ailp->ail_head)
+		next_lsn = next_lip->li_lsn;
+	lsn = lip->li_lsn;
 
+	if (in_ail &&
+	    (prev_lsn == NULLCOMMITLSN || XFS_LSN_CMP(prev_lsn, lsn) <= 0) &&
+	    (next_lsn == NULLCOMMITLSN || XFS_LSN_CMP(next_lsn, lsn) >= 0))
+		return;
 
+	spin_unlock(&ailp->ail_lock);
+	ASSERT(in_ail);
+	ASSERT(prev_lsn == NULLCOMMITLSN || XFS_LSN_CMP(prev_lsn, lsn) <= 0);
+	ASSERT(next_lsn == NULLCOMMITLSN || XFS_LSN_CMP(next_lsn, lsn) >= 0);
+	spin_lock(&ailp->ail_lock);
 }
 #else /* !DEBUG */
 #define	xfs_ail_check(a,l)
@@ -684,7 +705,7 @@ xfs_trans_ail_update_bulk(
 
 	for (i = 0; i < nr_items; i++) {
 		struct xfs_log_item *lip = log_items[i];
-		if (lip->li_flags & XFS_LI_IN_AIL) {
+		if (test_and_set_bit(XFS_LI_IN_AIL, &lip->li_flags)) {
 			/* check if we really need to move the item */
 			if (XFS_LSN_CMP(lsn, lip->li_lsn) <= 0)
 				continue;
@@ -694,7 +715,6 @@ xfs_trans_ail_update_bulk(
 			if (mlip == lip)
 				mlip_changed = 1;
 		} else {
-			lip->li_flags |= XFS_LI_IN_AIL;
 			trace_xfs_ail_insert(lip, 0, lsn);
 		}
 		lip->li_lsn = lsn;
@@ -725,7 +745,7 @@ xfs_ail_delete_one(
 	trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
 	xfs_ail_delete(ailp, lip);
 	xfs_clear_li_failed(lip);
-	lip->li_flags &= ~XFS_LI_IN_AIL;
+	clear_bit(XFS_LI_IN_AIL, &lip->li_flags);
 	lip->li_lsn = 0;
 
 	return mlip == lip;
@@ -761,7 +781,7 @@ xfs_trans_ail_delete(
 	struct xfs_mount	*mp = ailp->ail_mount;
 	bool			mlip_changed;
 
-	if (!(lip->li_flags & XFS_LI_IN_AIL)) {
+	if (!test_bit(XFS_LI_IN_AIL, &lip->li_flags)) {
 		spin_unlock(&ailp->ail_lock);
 		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c
index 14543d93cd4b..230a21df4b12 100644
--- a/fs/xfs/xfs_trans_bmap.c
+++ b/fs/xfs/xfs_trans_bmap.c
@@ -79,7 +79,7 @@ xfs_trans_log_finish_bmap_update(
 	 * 2.) shuts down the filesystem
 	 */
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	budp->bud_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags);
 
 	return error;
 }
@@ -158,7 +158,7 @@ xfs_bmap_update_log_item(
 	bmap = container_of(item, struct xfs_bmap_intent, bi_list);
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	buip->bui_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags);
 
 	/*
 	 * atomic_inc_return gives us the value after the increment;
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index a5d9dfc45d98..a8ddb4eed279 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -40,7 +40,7 @@ xfs_trans_buf_item_match(
 	struct xfs_buf_map	*map,
 	int			nmaps)
 {
-	struct xfs_log_item_desc *lidp;
+	struct xfs_log_item	*lip;
 	struct xfs_buf_log_item	*blip;
 	int			len = 0;
 	int			i;
@@ -48,8 +48,8 @@ xfs_trans_buf_item_match(
 	for (i = 0; i < nmaps; i++)
 		len += map[i].bm_len;
 
-	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
-		blip = (struct xfs_buf_log_item *)lidp->lid_item;
+	list_for_each_entry(lip, &tp->t_items, li_trans) {
+		blip = (struct xfs_buf_log_item *)lip;
 		if (blip->bli_item.li_type == XFS_LI_BUF &&
 		    blip->bli_buf->b_target == target &&
 		    XFS_BUF_ADDR(blip->bli_buf) == map[0].bm_bn &&
@@ -100,14 +100,10 @@ _xfs_trans_bjoin(
 	atomic_inc(&bip->bli_refcount);
 
 	/*
-	 * Get a log_item_desc to point at the new item.
+	 * Attach the item to the transaction so we can find it in
+	 * xfs_trans_get_buf() and friends.
 	 */
 	xfs_trans_add_item(tp, &bip->bli_item);
-
-	/*
-	 * Initialize b_fsprivate2 so we can find it with incore_match()
-	 * in xfs_trans_get_buf() and friends above.
-	 */
 	bp->b_transp = tp;
 
 }
@@ -391,7 +387,7 @@ xfs_trans_brelse(
 	 * If the buffer is dirty within this transaction, we can't
 	 * release it until we commit.
 	 */
-	if (bip->bli_item.li_desc->lid_flags & XFS_LID_DIRTY)
+	if (test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags))
 		return;
 
 	/*
@@ -442,7 +438,7 @@ xfs_trans_brelse(
 		ASSERT(bp->b_pincount == 0);
 ***/
 		ASSERT(atomic_read(&bip->bli_refcount) == 0);
-		ASSERT(!(bip->bli_item.li_flags & XFS_LI_IN_AIL));
+		ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
 		ASSERT(!(bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF));
 		xfs_buf_item_relse(bp);
 	}
@@ -542,7 +538,7 @@ xfs_trans_dirty_buf(
 	bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED;
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags);
 }
 
 /*
@@ -626,7 +622,7 @@ xfs_trans_binval(
 		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF));
 		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLFT_MASK));
 		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
-		ASSERT(bip->bli_item.li_desc->lid_flags & XFS_LID_DIRTY);
+		ASSERT(test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags));
 		ASSERT(tp->t_flags & XFS_TRANS_DIRTY);
 		return;
 	}
@@ -642,7 +638,7 @@ xfs_trans_binval(
 		memset(bip->bli_formats[i].blf_data_map, 0,
 		       (bip->bli_formats[i].blf_map_size * sizeof(uint)));
 	}
-	bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags);
 	tp->t_flags |= XFS_TRANS_DIRTY;
 }
 
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index c3d547211d16..c381c02cca45 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -77,7 +77,7 @@ xfs_trans_log_dquot(
 	ASSERT(XFS_DQ_IS_LOCKED(dqp));
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	dqp->q_logitem.qli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &dqp->q_logitem.qli_item.li_flags);
 }
 
 /*
@@ -879,7 +879,7 @@ xfs_trans_log_quotaoff_item(
 	xfs_qoff_logitem_t	*qlp)
 {
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	qlp->qql_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &qlp->qql_item.li_flags);
 }
 
 STATIC void
diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c
index ab438647592a..2f44a08bdf65 100644
--- a/fs/xfs/xfs_trans_extfree.c
+++ b/fs/xfs/xfs_trans_extfree.c
@@ -68,7 +68,8 @@ xfs_trans_free_extent(
 	struct xfs_efd_log_item	*efdp,
 	xfs_fsblock_t		start_block,
 	xfs_extlen_t		ext_len,
-	struct xfs_owner_info	*oinfo)
+	struct xfs_owner_info	*oinfo,
+	bool			skip_discard)
 {
 	struct xfs_mount	*mp = tp->t_mountp;
 	uint			next_extent;
@@ -79,9 +80,8 @@ xfs_trans_free_extent(
 
 	trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, ext_len);
 
-	error = xfs_free_extent(tp, start_block, ext_len, oinfo,
-			XFS_AG_RESV_NONE);
-
+	error = __xfs_free_extent(tp, start_block, ext_len,
+				  oinfo, XFS_AG_RESV_NONE, skip_discard);
 	/*
 	 * Mark the transaction dirty, even on error. This ensures the
 	 * transaction is aborted, which:
@@ -90,7 +90,7 @@ xfs_trans_free_extent(
 	 * 2.) shuts down the filesystem
 	 */
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	efdp->efd_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
 
 	next_extent = efdp->efd_next_extent;
 	ASSERT(next_extent < efdp->efd_format.efd_nextents);
@@ -155,7 +155,7 @@ xfs_extent_free_log_item(
 	free = container_of(item, struct xfs_extent_free_item, xefi_list);
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	efip->efi_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
 
 	/*
 	 * atomic_inc_return gives us the value after the increment;
@@ -195,7 +195,7 @@ xfs_extent_free_finish_item(
 	error = xfs_trans_free_extent(tp, done_item,
 			free->xefi_startblock,
 			free->xefi_blockcount,
-			&free->xefi_oinfo);
+			&free->xefi_oinfo, free->xefi_skip_discard);
 	kmem_free(free);
 	return error;
 }
@@ -231,9 +231,79 @@ static const struct xfs_defer_op_type xfs_extent_free_defer_type = {
 	.cancel_item	= xfs_extent_free_cancel_item,
 };
 
+/*
+ * AGFL blocks are accounted differently in the reserve pools and are not
+ * inserted into the busy extent list.
+ */
+STATIC int
+xfs_agfl_free_finish_item(
+	struct xfs_trans		*tp,
+	struct xfs_defer_ops		*dop,
+	struct list_head		*item,
+	void				*done_item,
+	void				**state)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_efd_log_item		*efdp = done_item;
+	struct xfs_extent_free_item	*free;
+	struct xfs_extent		*extp;
+	struct xfs_buf			*agbp;
+	int				error;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
+	uint				next_extent;
+
+	free = container_of(item, struct xfs_extent_free_item, xefi_list);
+	ASSERT(free->xefi_blockcount == 1);
+	agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock);
+	agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock);
+
+	trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount);
+
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
+	if (!error)
+		error = xfs_free_agfl_block(tp, agno, agbno, agbp,
+					    &free->xefi_oinfo);
+
+	/*
+	 * Mark the transaction dirty, even on error. This ensures the
+	 * transaction is aborted, which:
+	 *
+	 * 1.) releases the EFI and frees the EFD
+	 * 2.) shuts down the filesystem
+	 */
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
+
+	next_extent = efdp->efd_next_extent;
+	ASSERT(next_extent < efdp->efd_format.efd_nextents);
+	extp = &(efdp->efd_format.efd_extents[next_extent]);
+	extp->ext_start = free->xefi_startblock;
+	extp->ext_len = free->xefi_blockcount;
+	efdp->efd_next_extent++;
+
+	kmem_free(free);
+	return error;
+}
+
+
+/* sub-type with special handling for AGFL deferred frees */
+static const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
+	.type		= XFS_DEFER_OPS_TYPE_AGFL_FREE,
+	.max_items	= XFS_EFI_MAX_FAST_EXTENTS,
+	.diff_items	= xfs_extent_free_diff_items,
+	.create_intent	= xfs_extent_free_create_intent,
+	.abort_intent	= xfs_extent_free_abort_intent,
+	.log_item	= xfs_extent_free_log_item,
+	.create_done	= xfs_extent_free_create_done,
+	.finish_item	= xfs_agfl_free_finish_item,
+	.cancel_item	= xfs_extent_free_cancel_item,
+};
+
 /* Register the deferred op type. */
 void
 xfs_extent_free_init_defer_op(void)
 {
 	xfs_defer_init_op_type(&xfs_extent_free_defer_type);
+	xfs_defer_init_op_type(&xfs_agfl_free_defer_type);
 }
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 07cea592dc01..f7bd7960a90f 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -133,14 +133,13 @@ xfs_trans_log_inode(
 	 * set however, then go ahead and bump the i_version counter
 	 * unconditionally.
 	 */
-	if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
+	if (!test_and_set_bit(XFS_LI_DIRTY, &ip->i_itemp->ili_item.li_flags) &&
 	    IS_I_VERSION(VFS_I(ip))) {
 		if (inode_maybe_inc_iversion(VFS_I(ip), flags & XFS_ILOG_CORE))
 			flags |= XFS_ILOG_CORE;
 	}
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	ip->i_itemp->ili_item.li_desc->lid_flags |= XFS_LID_DIRTY;
 
 	/*
 	 * Always OR in the bits from the ili_last_fields field.
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index be24b0c8a332..9717ae74b36d 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -19,7 +19,6 @@
 #define	__XFS_TRANS_PRIV_H__
 
 struct xfs_log_item;
-struct xfs_log_item_desc;
 struct xfs_mount;
 struct xfs_trans;
 struct xfs_ail;
@@ -119,7 +118,7 @@ xfs_trans_ail_remove(
 
 	spin_lock(&ailp->ail_lock);
 	/* xfs_trans_ail_delete() drops the AIL lock */
-	if (lip->li_flags & XFS_LI_IN_AIL)
+	if (test_bit(XFS_LI_IN_AIL, &lip->li_flags))
 		xfs_trans_ail_delete(ailp, lip, shutdown_type);
 	else
 		spin_unlock(&ailp->ail_lock);
@@ -171,11 +170,10 @@ xfs_clear_li_failed(
 {
 	struct xfs_buf	*bp = lip->li_buf;
 
-	ASSERT(lip->li_flags & XFS_LI_IN_AIL);
+	ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags));
 	lockdep_assert_held(&lip->li_ailp->ail_lock);
 
-	if (lip->li_flags & XFS_LI_FAILED) {
-		lip->li_flags &= ~XFS_LI_FAILED;
+	if (test_and_clear_bit(XFS_LI_FAILED, &lip->li_flags)) {
 		lip->li_buf = NULL;
 		xfs_buf_rele(bp);
 	}
@@ -188,9 +186,8 @@ xfs_set_li_failed(
 {
 	lockdep_assert_held(&lip->li_ailp->ail_lock);
 
-	if (!(lip->li_flags & XFS_LI_FAILED)) {
+	if (!test_and_set_bit(XFS_LI_FAILED, &lip->li_flags)) {
 		xfs_buf_hold(bp);
-		lip->li_flags |= XFS_LI_FAILED;
 		lip->li_buf = bp;
 	}
 }
diff --git a/fs/xfs/xfs_trans_refcount.c b/fs/xfs/xfs_trans_refcount.c
index 94c1877af834..c7f8e82f5bda 100644
--- a/fs/xfs/xfs_trans_refcount.c
+++ b/fs/xfs/xfs_trans_refcount.c
@@ -77,7 +77,7 @@ xfs_trans_log_finish_refcount_update(
 	 * 2.) shuts down the filesystem
 	 */
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	cudp->cud_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags);
 
 	return error;
 }
@@ -154,7 +154,7 @@ xfs_refcount_update_log_item(
 	refc = container_of(item, struct xfs_refcount_intent, ri_list);
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	cuip->cui_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags);
 
 	/*
 	 * atomic_inc_return gives us the value after the increment;
diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c
index 9b577beb43d7..5831ca0c270b 100644
--- a/fs/xfs/xfs_trans_rmap.c
+++ b/fs/xfs/xfs_trans_rmap.c
@@ -117,7 +117,7 @@ xfs_trans_log_finish_rmap_update(
 	 * 2.) shuts down the filesystem
 	 */
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	rudp->rud_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
 
 	return error;
 }
@@ -175,7 +175,7 @@ xfs_rmap_update_log_item(
 	rmap = container_of(item, struct xfs_rmap_intent, ri_list);
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	ruip->rui_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+	set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
 
 	/*
 	 * atomic_inc_return gives us the value after the increment;
diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index 7b289dd00a30..6f69a4f638f8 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -49,11 +49,14 @@
 /* Definitions of the predefined namespace names  */
 
 #define ACPI_UNKNOWN_NAME       (u32) 0x3F3F3F3F	/* Unknown name is "????" */
-#define ACPI_ROOT_NAME          (u32) 0x5F5F5F5C	/* Root name is    "\___" */
-
 #define ACPI_PREFIX_MIXED       (u32) 0x69706341	/* "Acpi" */
 #define ACPI_PREFIX_LOWER       (u32) 0x69706361	/* "acpi" */
 
+/* Root name stuff */
+
+#define ACPI_ROOT_NAME          (u32) 0x5F5F5F5C	/* Root name is    "\___" */
+#define ACPI_ROOT_PATHNAME      "\\___"
+#define ACPI_NAMESPACE_ROOT     "Namespace Root"
 #define ACPI_NS_ROOT_PATH       "\\"
 
 #endif				/* __ACNAMES_H__  */
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 540d35f06ad6..eb1f21af7556 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -98,6 +98,27 @@ void acpi_os_release_lock(acpi_spinlock handle, acpi_cpu_flags flags);
 #endif
 
 /*
+ * RAW spinlock primitives. If the OS does not provide them, fallback to
+ * spinlock primitives
+ */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_raw_lock
+# define acpi_os_create_raw_lock(out_handle)	acpi_os_create_lock(out_handle)
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_delete_raw_lock
+# define acpi_os_delete_raw_lock(handle)	acpi_os_delete_lock(handle)
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_raw_lock
+# define acpi_os_acquire_raw_lock(handle)	acpi_os_acquire_lock(handle)
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_release_raw_lock
+# define acpi_os_release_raw_lock(handle, flags)	\
+	acpi_os_release_lock(handle, flags)
+#endif
+
+/*
  * Semaphore primitives
  */
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_semaphore
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index da0215ea9f44..77d71bd1be39 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -12,7 +12,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20180313
+#define ACPI_CA_VERSION                 0x20180508
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
@@ -753,6 +753,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 						     u32 gpe_number,
 						     acpi_event_status
 						     *event_status))
+ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 1c530f95dc34..2b1bafa197c0 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -245,6 +245,10 @@ typedef u64 acpi_physical_address;
 #define acpi_spinlock                   void *
 #endif
 
+#ifndef acpi_raw_spinlock
+#define acpi_raw_spinlock		acpi_spinlock
+#endif
+
 #ifndef acpi_semaphore
 #define acpi_semaphore                  void *
 #endif
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 2010c0516f27..8e0b8250a139 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -20,14 +20,16 @@
 #include <acpi/pcc.h>
 #include <acpi/processor.h>
 
-/* Only support CPPCv2 for now. */
-#define CPPC_NUM_ENT	21
-#define CPPC_REV	2
+/* Support CPPCv2 and CPPCv3  */
+#define CPPC_V2_REV	2
+#define CPPC_V3_REV	3
+#define CPPC_V2_NUM_ENT	21
+#define CPPC_V3_NUM_ENT	23
 
 #define PCC_CMD_COMPLETE_MASK	(1 << 0)
 #define PCC_ERROR_MASK		(1 << 2)
 
-#define MAX_CPC_REG_ENT 19
+#define MAX_CPC_REG_ENT 21
 
 /* CPPC specific PCC commands. */
 #define	CMD_READ 0
@@ -91,6 +93,8 @@ enum cppc_regs {
 	AUTO_ACT_WINDOW,
 	ENERGY_PERF,
 	REFERENCE_PERF,
+	LOWEST_FREQ,
+	NOMINAL_FREQ,
 };
 
 /*
@@ -104,6 +108,8 @@ struct cppc_perf_caps {
 	u32 nominal_perf;
 	u32 lowest_perf;
 	u32 lowest_nonlinear_perf;
+	u32 lowest_freq;
+	u32 nominal_freq;
 };
 
 struct cppc_perf_ctrls {
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 8feb0c866ee0..1624e2be485c 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -55,22 +55,21 @@ enum {
 /* From drivers/edac/ghes_edac.c */
 
 #ifdef CONFIG_EDAC_GHES
-void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
-				struct cper_sec_mem_err *mem_err);
+void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err);
 
 int ghes_edac_register(struct ghes *ghes, struct device *dev);
 
 void ghes_edac_unregister(struct ghes *ghes);
 
 #else
-static inline void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
+static inline void ghes_edac_report_mem_error(int sev,
 				       struct cper_sec_mem_err *mem_err)
 {
 }
 
 static inline int ghes_edac_register(struct ghes *ghes, struct device *dev)
 {
-	return 0;
+	return -ENODEV;
 }
 
 static inline void ghes_edac_unregister(struct ghes *ghes)
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index a0b232703302..7451b3bca83a 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -102,6 +102,7 @@
 
 #define acpi_cache_t                        struct kmem_cache
 #define acpi_spinlock                       spinlock_t *
+#define acpi_raw_spinlock                   raw_spinlock_t *
 #define acpi_cpu_flags                      unsigned long
 
 /* Use native linux version of acpi_os_allocate_zeroed */
@@ -119,6 +120,10 @@
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_object
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_raw_lock
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_delete_raw_lock
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_raw_lock
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_release_raw_lock
 
 /*
  * OSL interfaces used by debugger/disassembler
diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h
index 7e81475fe034..d754a1b12721 100644
--- a/include/acpi/platform/aclinuxex.h
+++ b/include/acpi/platform/aclinuxex.h
@@ -90,6 +90,36 @@ static inline acpi_thread_id acpi_os_get_thread_id(void)
 		lock ? AE_OK : AE_NO_MEMORY; \
 	})
 
+
+#define acpi_os_create_raw_lock(__handle) \
+	({ \
+		raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \
+		if (lock) { \
+			*(__handle) = lock; \
+			raw_spin_lock_init(*(__handle)); \
+		} \
+		lock ? AE_OK : AE_NO_MEMORY; \
+	})
+
+static inline acpi_cpu_flags acpi_os_acquire_raw_lock(acpi_raw_spinlock lockp)
+{
+	acpi_cpu_flags flags;
+
+	raw_spin_lock_irqsave(lockp, flags);
+	return flags;
+}
+
+static inline void acpi_os_release_raw_lock(acpi_raw_spinlock lockp,
+					    acpi_cpu_flags flags)
+{
+	raw_spin_unlock_irqrestore(lockp, flags);
+}
+
+static inline void acpi_os_delete_raw_lock(acpi_raw_spinlock handle)
+{
+	ACPI_FREE(handle);
+}
+
 static inline u8 acpi_os_readable(void *pointer, acpi_size length)
 {
 	return TRUE;
diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 34a028a7bcc5..87d14476edc2 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -25,6 +25,7 @@ typedef atomic64_t atomic_long_t;
 
 #define ATOMIC_LONG_INIT(i)	ATOMIC64_INIT(i)
 #define ATOMIC_LONG_PFX(x)	atomic64 ## x
+#define ATOMIC_LONG_TYPE	s64
 
 #else
 
@@ -32,6 +33,7 @@ typedef atomic_t atomic_long_t;
 
 #define ATOMIC_LONG_INIT(i)	ATOMIC_INIT(i)
 #define ATOMIC_LONG_PFX(x)	atomic ## x
+#define ATOMIC_LONG_TYPE	int
 
 #endif
 
@@ -90,6 +92,21 @@ ATOMIC_LONG_ADD_SUB_OP(sub, _release)
 #define atomic_long_cmpxchg(l, old, new) \
 	(ATOMIC_LONG_PFX(_cmpxchg)((ATOMIC_LONG_PFX(_t) *)(l), (old), (new)))
 
+
+#define atomic_long_try_cmpxchg_relaxed(l, old, new) \
+	(ATOMIC_LONG_PFX(_try_cmpxchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(l), \
+					   (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new)))
+#define atomic_long_try_cmpxchg_acquire(l, old, new) \
+	(ATOMIC_LONG_PFX(_try_cmpxchg_acquire)((ATOMIC_LONG_PFX(_t) *)(l), \
+					   (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new)))
+#define atomic_long_try_cmpxchg_release(l, old, new) \
+	(ATOMIC_LONG_PFX(_try_cmpxchg_release)((ATOMIC_LONG_PFX(_t) *)(l), \
+					   (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new)))
+#define atomic_long_try_cmpxchg(l, old, new) \
+	(ATOMIC_LONG_PFX(_try_cmpxchg)((ATOMIC_LONG_PFX(_t) *)(l), \
+				       (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new)))
+
+
 #define atomic_long_xchg_relaxed(v, new) \
 	(ATOMIC_LONG_PFX(_xchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(v), (new)))
 #define atomic_long_xchg_acquire(v, new) \
@@ -244,6 +261,8 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
 #define atomic_long_inc_not_zero(l) \
 	ATOMIC_LONG_PFX(_inc_not_zero)((ATOMIC_LONG_PFX(_t) *)(l))
 
+#define atomic_long_cond_read_relaxed(v, c) \
+	ATOMIC_LONG_PFX(_cond_read_relaxed)((ATOMIC_LONG_PFX(_t) *)(v), (c))
 #define atomic_long_cond_read_acquire(v, c) \
 	ATOMIC_LONG_PFX(_cond_read_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (c))
 
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 29458bbb2fa0..2cafdbb9ae4c 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -221,18 +221,17 @@ do {									\
 #endif
 
 /**
- * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * smp_cond_load_relaxed() - (Spin) wait for cond with no ordering guarantees
  * @ptr: pointer to the variable to wait on
  * @cond: boolean expression to wait for
  *
- * Equivalent to using smp_load_acquire() on the condition variable but employs
- * the control dependency of the wait to reduce the barrier on many platforms.
+ * Equivalent to using READ_ONCE() on the condition variable.
  *
  * Due to C lacking lambda expressions we load the value of *ptr into a
  * pre-named variable @VAL to be used in @cond.
  */
-#ifndef smp_cond_load_acquire
-#define smp_cond_load_acquire(ptr, cond_expr) ({		\
+#ifndef smp_cond_load_relaxed
+#define smp_cond_load_relaxed(ptr, cond_expr) ({		\
 	typeof(ptr) __PTR = (ptr);				\
 	typeof(*ptr) VAL;					\
 	for (;;) {						\
@@ -241,10 +240,26 @@ do {									\
 			break;					\
 		cpu_relax();					\
 	}							\
-	smp_acquire__after_ctrl_dep();				\
 	VAL;							\
 })
 #endif
 
+/**
+ * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * @ptr: pointer to the variable to wait on
+ * @cond: boolean expression to wait for
+ *
+ * Equivalent to using smp_load_acquire() on the condition variable but employs
+ * the control dependency of the wait to reduce the barrier on many platforms.
+ */
+#ifndef smp_cond_load_acquire
+#define smp_cond_load_acquire(ptr, cond_expr) ({		\
+	typeof(*ptr) _val;					\
+	_val = smp_cond_load_relaxed(ptr, cond_expr);		\
+	smp_acquire__after_ctrl_dep();				\
+	_val;							\
+})
+#endif
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h
new file mode 100644
index 000000000000..28819451b6d1
--- /dev/null
+++ b/include/asm-generic/compat.h
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* This is an empty stub for 32-bit-only architectures */
diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h
index 880a292d792f..ad2868263867 100644
--- a/include/asm-generic/dma-mapping.h
+++ b/include/asm-generic/dma-mapping.h
@@ -4,7 +4,16 @@
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
+	/*
+	 * Use the non-coherent ops if available.  If an architecture wants a
+	 * more fine-grained selection of operations it will have to implement
+	 * get_arch_dma_ops itself or use the per-device dma_ops.
+	 */
+#ifdef CONFIG_DMA_NONCOHERENT_OPS
+	return &dma_noncoherent_ops;
+#else
 	return &dma_direct_ops;
+#endif
 }
 
 #endif /* _ASM_GENERIC_DMA_MAPPING_H */
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index 719db1968d81..68efb950a918 100644
--- a/include/asm-generic/export.h
+++ b/include/asm-generic/export.h
@@ -19,42 +19,32 @@
 #define KCRC_ALIGN 4
 #endif
 
-#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
-#define KSYM(name) _##name
-#else
-#define KSYM(name) name
-#endif
-
 /*
  * note on .section use: @progbits vs %progbits nastiness doesn't matter,
  * since we immediately emit into those sections anyway.
  */
 .macro ___EXPORT_SYMBOL name,val,sec
 #ifdef CONFIG_MODULES
-	.globl KSYM(__ksymtab_\name)
+	.globl __ksymtab_\name
 	.section ___ksymtab\sec+\name,"a"
 	.balign KSYM_ALIGN
-KSYM(__ksymtab_\name):
-	__put \val, KSYM(__kstrtab_\name)
+__ksymtab_\name:
+	__put \val, __kstrtab_\name
 	.previous
 	.section __ksymtab_strings,"a"
-KSYM(__kstrtab_\name):
-#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
-	.asciz "_\name"
-#else
+__kstrtab_\name:
 	.asciz "\name"
-#endif
 	.previous
 #ifdef CONFIG_MODVERSIONS
 	.section ___kcrctab\sec+\name,"a"
 	.balign KCRC_ALIGN
-KSYM(__kcrctab_\name):
+__kcrctab_\name:
 #if defined(CONFIG_MODULE_REL_CRCS)
-	.long KSYM(__crc_\name) - .
+	.long __crc_\name - .
 #else
-	.long KSYM(__crc_\name)
+	.long __crc_\name
 #endif
-	.weak KSYM(__crc_\name)
+	.weak __crc_\name
 	.previous
 #endif
 #endif
@@ -84,12 +74,12 @@ KSYM(__kcrctab_\name):
 #endif
 
 #define EXPORT_SYMBOL(name)					\
-	__EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)),)
+	__EXPORT_SYMBOL(name, KSYM_FUNC(name),)
 #define EXPORT_SYMBOL_GPL(name) 				\
-	__EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)), _gpl)
+	__EXPORT_SYMBOL(name, KSYM_FUNC(name), _gpl)
 #define EXPORT_DATA_SYMBOL(name)				\
-	__EXPORT_SYMBOL(name, KSYM(name),)
+	__EXPORT_SYMBOL(name, name,)
 #define EXPORT_DATA_SYMBOL_GPL(name)				\
-	__EXPORT_SYMBOL(name, KSYM(name),_gpl)
+	__EXPORT_SYMBOL(name, name,_gpl)
 
 #endif
diff --git a/include/asm-generic/pci.h b/include/asm-generic/pci.h
index 830d7659289b..6bb3cd3d695a 100644
--- a/include/asm-generic/pci.h
+++ b/include/asm-generic/pci.h
@@ -14,12 +14,4 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 }
 #endif /* HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ */
 
-/*
- * By default, assume that no iommu is in use and that the PCI
- * space is mapped to address physical 0.
- */
-#ifndef PCI_DMA_BUS_IS_PHYS
-#define PCI_DMA_BUS_IS_PHYS	(1)
-#endif
-
 #endif /* _ASM_GENERIC_PCI_H */
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index b37b4ad7eb94..9cc457597ddf 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -26,7 +26,6 @@
  * @lock: Pointer to queued spinlock structure
  * Return: 1 if it is locked, 0 otherwise
  */
-#ifndef queued_spin_is_locked
 static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 {
 	/*
@@ -35,7 +34,6 @@ static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 	 */
 	return atomic_read(&lock->val);
 }
-#endif
 
 /**
  * queued_spin_value_unlocked - is the spinlock structure unlocked?
@@ -100,7 +98,7 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 	/*
 	 * unlock() needs release semantics:
 	 */
-	(void)atomic_sub_return_release(_Q_LOCKED_VAL, &lock->val);
+	smp_store_release(&lock->locked, 0);
 }
 #endif
 
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
index 034acd0c4956..0763f065b975 100644
--- a/include/asm-generic/qspinlock_types.h
+++ b/include/asm-generic/qspinlock_types.h
@@ -29,13 +29,41 @@
 #endif
 
 typedef struct qspinlock {
-	atomic_t	val;
+	union {
+		atomic_t val;
+
+		/*
+		 * By using the whole 2nd least significant byte for the
+		 * pending bit, we can allow better optimization of the lock
+		 * acquisition for the pending bit holder.
+		 */
+#ifdef __LITTLE_ENDIAN
+		struct {
+			u8	locked;
+			u8	pending;
+		};
+		struct {
+			u16	locked_pending;
+			u16	tail;
+		};
+#else
+		struct {
+			u16	tail;
+			u16	locked_pending;
+		};
+		struct {
+			u8	reserved[2];
+			u8	pending;
+			u8	locked;
+		};
+#endif
+	};
 } arch_spinlock_t;
 
 /*
  * Initializier
  */
-#define	__ARCH_SPIN_LOCK_UNLOCKED	{ ATOMIC_INIT(0) }
+#define	__ARCH_SPIN_LOCK_UNLOCKED	{ .val = ATOMIC_INIT(0) }
 
 /*
  * Bitfields in the atomic value:
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 278841c75b97..e373e2e10f6a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -64,15 +64,24 @@
  * generates .data.identifier sections, which need to be pulled in with
  * .data. We don't want to pull in .data..other sections, which Linux
  * has defined. Same for text and bss.
+ *
+ * RODATA_MAIN is not used because existing code already defines .rodata.x
+ * sections to be brought in with rodata.
  */
 #ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
 #define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
 #define DATA_MAIN .data .data.[0-9a-zA-Z_]*
+#define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]*
+#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]*
 #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]*
+#define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]*
 #else
 #define TEXT_MAIN .text
 #define DATA_MAIN .data
+#define SDATA_MAIN .sdata
+#define RODATA_MAIN .rodata
 #define BSS_MAIN .bss
+#define SBSS_MAIN .sbss
 #endif
 
 /*
@@ -104,66 +113,66 @@
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 #define MCOUNT_REC()	. = ALIGN(8);				\
-			VMLINUX_SYMBOL(__start_mcount_loc) = .; \
-			*(__mcount_loc)				\
-			VMLINUX_SYMBOL(__stop_mcount_loc) = .;
+			__start_mcount_loc = .;			\
+			KEEP(*(__mcount_loc))			\
+			__stop_mcount_loc = .;
 #else
 #define MCOUNT_REC()
 #endif
 
 #ifdef CONFIG_TRACE_BRANCH_PROFILING
-#define LIKELY_PROFILE()	VMLINUX_SYMBOL(__start_annotated_branch_profile) = .; \
-				*(_ftrace_annotated_branch)			      \
-				VMLINUX_SYMBOL(__stop_annotated_branch_profile) = .;
+#define LIKELY_PROFILE()	__start_annotated_branch_profile = .;	\
+				KEEP(*(_ftrace_annotated_branch))	\
+				__stop_annotated_branch_profile = .;
 #else
 #define LIKELY_PROFILE()
 #endif
 
 #ifdef CONFIG_PROFILE_ALL_BRANCHES
-#define BRANCH_PROFILE()	VMLINUX_SYMBOL(__start_branch_profile) = .;   \
-				*(_ftrace_branch)			      \
-				VMLINUX_SYMBOL(__stop_branch_profile) = .;
+#define BRANCH_PROFILE()	__start_branch_profile = .;		\
+				KEEP(*(_ftrace_branch))			\
+				__stop_branch_profile = .;
 #else
 #define BRANCH_PROFILE()
 #endif
 
 #ifdef CONFIG_KPROBES
 #define KPROBE_BLACKLIST()	. = ALIGN(8);				      \
-				VMLINUX_SYMBOL(__start_kprobe_blacklist) = .; \
+				__start_kprobe_blacklist = .;		      \
 				KEEP(*(_kprobe_blacklist))		      \
-				VMLINUX_SYMBOL(__stop_kprobe_blacklist) = .;
+				__stop_kprobe_blacklist = .;
 #else
 #define KPROBE_BLACKLIST()
 #endif
 
 #ifdef CONFIG_FUNCTION_ERROR_INJECTION
 #define ERROR_INJECT_WHITELIST()	STRUCT_ALIGN();			      \
-			VMLINUX_SYMBOL(__start_error_injection_whitelist) = .;\
+			__start_error_injection_whitelist = .;		      \
 			KEEP(*(_error_injection_whitelist))		      \
-			VMLINUX_SYMBOL(__stop_error_injection_whitelist) = .;
+			__stop_error_injection_whitelist = .;
 #else
 #define ERROR_INJECT_WHITELIST()
 #endif
 
 #ifdef CONFIG_EVENT_TRACING
 #define FTRACE_EVENTS()	. = ALIGN(8);					\
-			VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
+			__start_ftrace_events = .;			\
 			KEEP(*(_ftrace_events))				\
-			VMLINUX_SYMBOL(__stop_ftrace_events) = .;	\
-			VMLINUX_SYMBOL(__start_ftrace_eval_maps) = .;	\
+			__stop_ftrace_events = .;			\
+			__start_ftrace_eval_maps = .;			\
 			KEEP(*(_ftrace_eval_map))			\
-			VMLINUX_SYMBOL(__stop_ftrace_eval_maps) = .;
+			__stop_ftrace_eval_maps = .;
 #else
 #define FTRACE_EVENTS()
 #endif
 
 #ifdef CONFIG_TRACING
-#define TRACE_PRINTKS() VMLINUX_SYMBOL(__start___trace_bprintk_fmt) = .;      \
+#define TRACE_PRINTKS()	 __start___trace_bprintk_fmt = .;      \
 			 KEEP(*(__trace_printk_fmt)) /* Trace_printk fmt' pointer */ \
-			 VMLINUX_SYMBOL(__stop___trace_bprintk_fmt) = .;
-#define TRACEPOINT_STR() VMLINUX_SYMBOL(__start___tracepoint_str) = .;	\
+			 __stop___trace_bprintk_fmt = .;
+#define TRACEPOINT_STR() __start___tracepoint_str = .;	\
 			 KEEP(*(__tracepoint_str)) /* Trace_printk fmt' pointer */ \
-			 VMLINUX_SYMBOL(__stop___tracepoint_str) = .;
+			 __stop___tracepoint_str = .;
 #else
 #define TRACE_PRINTKS()
 #define TRACEPOINT_STR()
@@ -171,27 +180,27 @@
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #define TRACE_SYSCALLS() . = ALIGN(8);					\
-			 VMLINUX_SYMBOL(__start_syscalls_metadata) = .;	\
+			 __start_syscalls_metadata = .;			\
 			 KEEP(*(__syscalls_metadata))			\
-			 VMLINUX_SYMBOL(__stop_syscalls_metadata) = .;
+			 __stop_syscalls_metadata = .;
 #else
 #define TRACE_SYSCALLS()
 #endif
 
 #ifdef CONFIG_BPF_EVENTS
 #define BPF_RAW_TP() STRUCT_ALIGN();					\
-			 VMLINUX_SYMBOL(__start__bpf_raw_tp) = .;	\
+			 __start__bpf_raw_tp = .;			\
 			 KEEP(*(__bpf_raw_tp_map))			\
-			 VMLINUX_SYMBOL(__stop__bpf_raw_tp) = .;
+			 __stop__bpf_raw_tp = .;
 #else
 #define BPF_RAW_TP()
 #endif
 
 #ifdef CONFIG_SERIAL_EARLYCON
-#define EARLYCON_TABLE() STRUCT_ALIGN();			\
-			 VMLINUX_SYMBOL(__earlycon_table) = .;	\
+#define EARLYCON_TABLE() . = ALIGN(8);				\
+			 __earlycon_table = .;			\
 			 KEEP(*(__earlycon_table))		\
-			 VMLINUX_SYMBOL(__earlycon_table_end) = .;
+			 __earlycon_table_end = .;
 #else
 #define EARLYCON_TABLE()
 #endif
@@ -202,7 +211,7 @@
 #define _OF_TABLE_0(name)
 #define _OF_TABLE_1(name)						\
 	. = ALIGN(8);							\
-	VMLINUX_SYMBOL(__##name##_of_table) = .;			\
+	__##name##_of_table = .;					\
 	KEEP(*(__##name##_of_table))					\
 	KEEP(*(__##name##_of_table_end))
 
@@ -217,18 +226,18 @@
 #ifdef CONFIG_ACPI
 #define ACPI_PROBE_TABLE(name)						\
 	. = ALIGN(8);							\
-	VMLINUX_SYMBOL(__##name##_acpi_probe_table) = .;		\
+	__##name##_acpi_probe_table = .;				\
 	KEEP(*(__##name##_acpi_probe_table))				\
-	VMLINUX_SYMBOL(__##name##_acpi_probe_table_end) = .;
+	__##name##_acpi_probe_table_end = .;
 #else
 #define ACPI_PROBE_TABLE(name)
 #endif
 
 #define KERNEL_DTB()							\
 	STRUCT_ALIGN();							\
-	VMLINUX_SYMBOL(__dtb_start) = .;				\
+	__dtb_start = .;						\
 	KEEP(*(.dtb.init.rodata))					\
-	VMLINUX_SYMBOL(__dtb_end) = .;
+	__dtb_end = .;
 
 /*
  * .data section
@@ -238,23 +247,23 @@
 	*(DATA_MAIN)							\
 	*(.ref.data)							\
 	*(.data..shared_aligned) /* percpu related */			\
-	MEM_KEEP(init.data)						\
-	MEM_KEEP(exit.data)						\
+	MEM_KEEP(init.data*)						\
+	MEM_KEEP(exit.data*)						\
 	*(.data.unlikely)						\
-	VMLINUX_SYMBOL(__start_once) = .;				\
+	__start_once = .;						\
 	*(.data.once)							\
-	VMLINUX_SYMBOL(__end_once) = .;					\
+	__end_once = .;							\
 	STRUCT_ALIGN();							\
 	*(__tracepoints)						\
 	/* implement dynamic printk debug */				\
 	. = ALIGN(8);                                                   \
-	VMLINUX_SYMBOL(__start___jump_table) = .;                       \
+	__start___jump_table = .;					\
 	KEEP(*(__jump_table))                                           \
-	VMLINUX_SYMBOL(__stop___jump_table) = .;                        \
+	__stop___jump_table = .;					\
 	. = ALIGN(8);							\
-	VMLINUX_SYMBOL(__start___verbose) = .;                          \
+	__start___verbose = .;						\
 	KEEP(*(__verbose))                                              \
-	VMLINUX_SYMBOL(__stop___verbose) = .;				\
+	__stop___verbose = .;						\
 	LIKELY_PROFILE()		       				\
 	BRANCH_PROFILE()						\
 	TRACE_PRINTKS()							\
@@ -266,10 +275,10 @@
  */
 #define NOSAVE_DATA							\
 	. = ALIGN(PAGE_SIZE);						\
-	VMLINUX_SYMBOL(__nosave_begin) = .;				\
+	__nosave_begin = .;						\
 	*(.data..nosave)						\
 	. = ALIGN(PAGE_SIZE);						\
-	VMLINUX_SYMBOL(__nosave_end) = .;
+	__nosave_end = .;
 
 #define PAGE_ALIGNED_DATA(page_align)					\
 	. = ALIGN(page_align);						\
@@ -286,13 +295,13 @@
 
 #define INIT_TASK_DATA(align)						\
 	. = ALIGN(align);						\
-	VMLINUX_SYMBOL(__start_init_task) = .;				\
-	VMLINUX_SYMBOL(init_thread_union) = .;				\
-	VMLINUX_SYMBOL(init_stack) = .;					\
-	*(.data..init_task)						\
-	*(.data..init_thread_info)					\
-	. = VMLINUX_SYMBOL(__start_init_task) + THREAD_SIZE;		\
-	VMLINUX_SYMBOL(__end_init_task) = .;
+	__start_init_task = .;						\
+	init_thread_union = .;						\
+	init_stack = .;							\
+	KEEP(*(.data..init_task))					\
+	KEEP(*(.data..init_thread_info))				\
+	. = __start_init_task + THREAD_SIZE;				\
+	__end_init_task = .;
 
 /*
  * Allow architectures to handle ro_after_init data on their
@@ -300,9 +309,9 @@
  */
 #ifndef RO_AFTER_INIT_DATA
 #define RO_AFTER_INIT_DATA						\
-	VMLINUX_SYMBOL(__start_ro_after_init) = .;			\
+	__start_ro_after_init = .;					\
 	*(.data..ro_after_init)						\
-	VMLINUX_SYMBOL(__end_ro_after_init) = .;
+	__end_ro_after_init = .;
 #endif
 
 /*
@@ -311,14 +320,14 @@
 #define RO_DATA_SECTION(align)						\
 	. = ALIGN((align));						\
 	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__start_rodata) = .;			\
+		__start_rodata = .;					\
 		*(.rodata) *(.rodata.*)					\
 		RO_AFTER_INIT_DATA	/* Read only after init */	\
 		KEEP(*(__vermagic))	/* Kernel version magic */	\
 		. = ALIGN(8);						\
-		VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .;		\
+		__start___tracepoints_ptrs = .;				\
 		KEEP(*(__tracepoints_ptrs)) /* Tracepoints: pointer array */ \
-		VMLINUX_SYMBOL(__stop___tracepoints_ptrs) = .;		\
+		__stop___tracepoints_ptrs = .;				\
 		*(__tracepoints_strings)/* Tracepoints: strings */	\
 	}								\
 									\
@@ -328,109 +337,109 @@
 									\
 	/* PCI quirks */						\
 	.pci_fixup        : AT(ADDR(.pci_fixup) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__start_pci_fixups_early) = .;		\
+		__start_pci_fixups_early = .;				\
 		KEEP(*(.pci_fixup_early))				\
-		VMLINUX_SYMBOL(__end_pci_fixups_early) = .;		\
-		VMLINUX_SYMBOL(__start_pci_fixups_header) = .;		\
+		__end_pci_fixups_early = .;				\
+		__start_pci_fixups_header = .;				\
 		KEEP(*(.pci_fixup_header))				\
-		VMLINUX_SYMBOL(__end_pci_fixups_header) = .;		\
-		VMLINUX_SYMBOL(__start_pci_fixups_final) = .;		\
+		__end_pci_fixups_header = .;				\
+		__start_pci_fixups_final = .;				\
 		KEEP(*(.pci_fixup_final))				\
-		VMLINUX_SYMBOL(__end_pci_fixups_final) = .;		\
-		VMLINUX_SYMBOL(__start_pci_fixups_enable) = .;		\
+		__end_pci_fixups_final = .;				\
+		__start_pci_fixups_enable = .;				\
 		KEEP(*(.pci_fixup_enable))				\
-		VMLINUX_SYMBOL(__end_pci_fixups_enable) = .;		\
-		VMLINUX_SYMBOL(__start_pci_fixups_resume) = .;		\
+		__end_pci_fixups_enable = .;				\
+		__start_pci_fixups_resume = .;				\
 		KEEP(*(.pci_fixup_resume))				\
-		VMLINUX_SYMBOL(__end_pci_fixups_resume) = .;		\
-		VMLINUX_SYMBOL(__start_pci_fixups_resume_early) = .;	\
+		__end_pci_fixups_resume = .;				\
+		__start_pci_fixups_resume_early = .;			\
 		KEEP(*(.pci_fixup_resume_early))			\
-		VMLINUX_SYMBOL(__end_pci_fixups_resume_early) = .;	\
-		VMLINUX_SYMBOL(__start_pci_fixups_suspend) = .;		\
+		__end_pci_fixups_resume_early = .;			\
+		__start_pci_fixups_suspend = .;				\
 		KEEP(*(.pci_fixup_suspend))				\
-		VMLINUX_SYMBOL(__end_pci_fixups_suspend) = .;		\
-		VMLINUX_SYMBOL(__start_pci_fixups_suspend_late) = .;	\
+		__end_pci_fixups_suspend = .;				\
+		__start_pci_fixups_suspend_late = .;			\
 		KEEP(*(.pci_fixup_suspend_late))			\
-		VMLINUX_SYMBOL(__end_pci_fixups_suspend_late) = .;	\
+		__end_pci_fixups_suspend_late = .;			\
 	}								\
 									\
 	/* Built-in firmware blobs */					\
 	.builtin_fw        : AT(ADDR(.builtin_fw) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__start_builtin_fw) = .;			\
+		__start_builtin_fw = .;					\
 		KEEP(*(.builtin_fw))					\
-		VMLINUX_SYMBOL(__end_builtin_fw) = .;			\
+		__end_builtin_fw = .;					\
 	}								\
 									\
 	TRACEDATA							\
 									\
 	/* Kernel symbol table: Normal symbols */			\
 	__ksymtab         : AT(ADDR(__ksymtab) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__start___ksymtab) = .;			\
+		__start___ksymtab = .;					\
 		KEEP(*(SORT(___ksymtab+*)))				\
-		VMLINUX_SYMBOL(__stop___ksymtab) = .;			\
+		__stop___ksymtab = .;					\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__ksymtab_gpl     : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__start___ksymtab_gpl) = .;		\
+		__start___ksymtab_gpl = .;				\
 		KEEP(*(SORT(___ksymtab_gpl+*)))				\
-		VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .;		\
+		__stop___ksymtab_gpl = .;				\
 	}								\
 									\
 	/* Kernel symbol table: Normal unused symbols */		\
 	__ksymtab_unused  : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__start___ksymtab_unused) = .;		\
+		__start___ksymtab_unused = .;				\
 		KEEP(*(SORT(___ksymtab_unused+*)))			\
-		VMLINUX_SYMBOL(__stop___ksymtab_unused) = .;		\
+		__stop___ksymtab_unused = .;				\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only unused symbols */		\
 	__ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \
-		VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .;	\
+		__start___ksymtab_unused_gpl = .;			\
 		KEEP(*(SORT(___ksymtab_unused_gpl+*)))			\
-		VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .;	\
+		__stop___ksymtab_unused_gpl = .;			\
 	}								\
 									\
 	/* Kernel symbol table: GPL-future-only symbols */		\
 	__ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \
-		VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .;	\
+		__start___ksymtab_gpl_future = .;			\
 		KEEP(*(SORT(___ksymtab_gpl_future+*)))			\
-		VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .;	\
+		__stop___ksymtab_gpl_future = .;			\
 	}								\
 									\
 	/* Kernel symbol table: Normal symbols */			\
 	__kcrctab         : AT(ADDR(__kcrctab) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__start___kcrctab) = .;			\
+		__start___kcrctab = .;					\
 		KEEP(*(SORT(___kcrctab+*)))				\
-		VMLINUX_SYMBOL(__stop___kcrctab) = .;			\
+		__stop___kcrctab = .;					\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__kcrctab_gpl     : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__start___kcrctab_gpl) = .;		\
+		__start___kcrctab_gpl = .;				\
 		KEEP(*(SORT(___kcrctab_gpl+*)))				\
-		VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .;		\
+		__stop___kcrctab_gpl = .;				\
 	}								\
 									\
 	/* Kernel symbol table: Normal unused symbols */		\
 	__kcrctab_unused  : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__start___kcrctab_unused) = .;		\
+		__start___kcrctab_unused = .;				\
 		KEEP(*(SORT(___kcrctab_unused+*)))			\
-		VMLINUX_SYMBOL(__stop___kcrctab_unused) = .;		\
+		__stop___kcrctab_unused = .;				\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only unused symbols */		\
 	__kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \
-		VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .;	\
+		__start___kcrctab_unused_gpl = .;			\
 		KEEP(*(SORT(___kcrctab_unused_gpl+*)))			\
-		VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .;	\
+		__stop___kcrctab_unused_gpl = .;			\
 	}								\
 									\
 	/* Kernel symbol table: GPL-future-only symbols */		\
 	__kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \
-		VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .;	\
+		__start___kcrctab_gpl_future = .;			\
 		KEEP(*(SORT(___kcrctab_gpl_future+*)))			\
-		VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .;	\
+		__stop___kcrctab_gpl_future = .;			\
 	}								\
 									\
 	/* Kernel symbol table: strings */				\
@@ -447,18 +456,18 @@
 									\
 	/* Built-in module parameters. */				\
 	__param : AT(ADDR(__param) - LOAD_OFFSET) {			\
-		VMLINUX_SYMBOL(__start___param) = .;			\
+		__start___param = .;					\
 		KEEP(*(__param))					\
-		VMLINUX_SYMBOL(__stop___param) = .;			\
+		__stop___param = .;					\
 	}								\
 									\
 	/* Built-in module versions. */					\
 	__modver : AT(ADDR(__modver) - LOAD_OFFSET) {			\
-		VMLINUX_SYMBOL(__start___modver) = .;			\
+		__start___modver = .;					\
 		KEEP(*(__modver))					\
-		VMLINUX_SYMBOL(__stop___modver) = .;			\
+		__stop___modver = .;					\
 		. = ALIGN((align));					\
-		VMLINUX_SYMBOL(__end_rodata) = .;			\
+		__end_rodata = .;					\
 	}								\
 	. = ALIGN((align));
 
@@ -469,9 +478,9 @@
 
 #define SECURITY_INIT							\
 	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
-		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
+		__security_initcall_start = .;				\
 		KEEP(*(.security_initcall.init))			\
-		VMLINUX_SYMBOL(__security_initcall_end) = .;		\
+		__security_initcall_end = .;				\
 	}
 
 /*
@@ -487,58 +496,58 @@
 		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
 		*(.text..refcount)					\
 		*(.ref.text)						\
-	MEM_KEEP(init.text)						\
-	MEM_KEEP(exit.text)						\
+	MEM_KEEP(init.text*)						\
+	MEM_KEEP(exit.text*)						\
 
 
 /* sched.text is aling to function alignment to secure we have same
  * address even at second ld pass when generating System.map */
 #define SCHED_TEXT							\
 		ALIGN_FUNCTION();					\
-		VMLINUX_SYMBOL(__sched_text_start) = .;			\
+		__sched_text_start = .;					\
 		*(.sched.text)						\
-		VMLINUX_SYMBOL(__sched_text_end) = .;
+		__sched_text_end = .;
 
 /* spinlock.text is aling to function alignment to secure we have same
  * address even at second ld pass when generating System.map */
 #define LOCK_TEXT							\
 		ALIGN_FUNCTION();					\
-		VMLINUX_SYMBOL(__lock_text_start) = .;			\
+		__lock_text_start = .;					\
 		*(.spinlock.text)					\
-		VMLINUX_SYMBOL(__lock_text_end) = .;
+		__lock_text_end = .;
 
 #define CPUIDLE_TEXT							\
 		ALIGN_FUNCTION();					\
-		VMLINUX_SYMBOL(__cpuidle_text_start) = .;		\
+		__cpuidle_text_start = .;				\
 		*(.cpuidle.text)					\
-		VMLINUX_SYMBOL(__cpuidle_text_end) = .;
+		__cpuidle_text_end = .;
 
 #define KPROBES_TEXT							\
 		ALIGN_FUNCTION();					\
-		VMLINUX_SYMBOL(__kprobes_text_start) = .;		\
+		__kprobes_text_start = .;				\
 		*(.kprobes.text)					\
-		VMLINUX_SYMBOL(__kprobes_text_end) = .;
+		__kprobes_text_end = .;
 
 #define ENTRY_TEXT							\
 		ALIGN_FUNCTION();					\
-		VMLINUX_SYMBOL(__entry_text_start) = .;			\
+		__entry_text_start = .;					\
 		*(.entry.text)						\
-		VMLINUX_SYMBOL(__entry_text_end) = .;
+		__entry_text_end = .;
 
 #define IRQENTRY_TEXT							\
 		ALIGN_FUNCTION();					\
-		VMLINUX_SYMBOL(__irqentry_text_start) = .;		\
+		__irqentry_text_start = .;				\
 		*(.irqentry.text)					\
-		VMLINUX_SYMBOL(__irqentry_text_end) = .;
+		__irqentry_text_end = .;
 
 #define SOFTIRQENTRY_TEXT						\
 		ALIGN_FUNCTION();					\
-		VMLINUX_SYMBOL(__softirqentry_text_start) = .;		\
+		__softirqentry_text_start = .;				\
 		*(.softirqentry.text)					\
-		VMLINUX_SYMBOL(__softirqentry_text_end) = .;
+		__softirqentry_text_end = .;
 
 /* Section used for early init (in .S files) */
-#define HEAD_TEXT  *(.head.text)
+#define HEAD_TEXT  KEEP(*(.head.text))
 
 #define HEAD_TEXT_SECTION							\
 	.head.text : AT(ADDR(.head.text) - LOAD_OFFSET) {		\
@@ -551,9 +560,9 @@
 #define EXCEPTION_TABLE(align)						\
 	. = ALIGN(align);						\
 	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__start___ex_table) = .;			\
+		__start___ex_table = .;					\
 		KEEP(*(__ex_table))					\
-		VMLINUX_SYMBOL(__stop___ex_table) = .;			\
+		__stop___ex_table = .;					\
 	}
 
 /*
@@ -567,11 +576,11 @@
 
 #ifdef CONFIG_CONSTRUCTORS
 #define KERNEL_CTORS()	. = ALIGN(8);			   \
-			VMLINUX_SYMBOL(__ctors_start) = .; \
+			__ctors_start = .;		   \
 			KEEP(*(.ctors))			   \
 			KEEP(*(SORT(.init_array.*)))	   \
 			KEEP(*(.init_array))		   \
-			VMLINUX_SYMBOL(__ctors_end) = .;
+			__ctors_end = .;
 #else
 #define KERNEL_CTORS()
 #endif
@@ -579,11 +588,11 @@
 /* init and exit section handling */
 #define INIT_DATA							\
 	KEEP(*(SORT(___kentry+*)))					\
-	*(.init.data)							\
-	MEM_DISCARD(init.data)						\
+	*(.init.data init.data.*)					\
+	MEM_DISCARD(init.data*)						\
 	KERNEL_CTORS()							\
 	MCOUNT_REC()							\
-	*(.init.rodata)							\
+	*(.init.rodata .init.rodata.*)					\
 	FTRACE_EVENTS()							\
 	TRACE_SYSCALLS()						\
 	KPROBE_BLACKLIST()						\
@@ -602,16 +611,16 @@
 	EARLYCON_TABLE()
 
 #define INIT_TEXT							\
-	*(.init.text)							\
+	*(.init.text .init.text.*)					\
 	*(.text.startup)						\
-	MEM_DISCARD(init.text)
+	MEM_DISCARD(init.text*)
 
 #define EXIT_DATA							\
-	*(.exit.data)							\
+	*(.exit.data .exit.data.*)					\
 	*(.fini_array)							\
 	*(.dtors)							\
-	MEM_DISCARD(exit.data)						\
-	MEM_DISCARD(exit.rodata)
+	MEM_DISCARD(exit.data*)						\
+	MEM_DISCARD(exit.rodata*)
 
 #define EXIT_TEXT							\
 	*(.exit.text)							\
@@ -629,7 +638,7 @@
 	. = ALIGN(sbss_align);						\
 	.sbss : AT(ADDR(.sbss) - LOAD_OFFSET) {				\
 		*(.dynsbss)						\
-		*(.sbss)						\
+		*(SBSS_MAIN)						\
 		*(.scommon)						\
 	}
 
@@ -706,9 +715,9 @@
 #define BUG_TABLE							\
 	. = ALIGN(8);							\
 	__bug_table : AT(ADDR(__bug_table) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__start___bug_table) = .;		\
+		__start___bug_table = .;				\
 		KEEP(*(__bug_table))					\
-		VMLINUX_SYMBOL(__stop___bug_table) = .;			\
+		__stop___bug_table = .;					\
 	}
 #else
 #define BUG_TABLE
@@ -718,22 +727,22 @@
 #define ORC_UNWIND_TABLE						\
 	. = ALIGN(4);							\
 	.orc_unwind_ip : AT(ADDR(.orc_unwind_ip) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__start_orc_unwind_ip) = .;		\
+		__start_orc_unwind_ip = .;				\
 		KEEP(*(.orc_unwind_ip))					\
-		VMLINUX_SYMBOL(__stop_orc_unwind_ip) = .;		\
+		__stop_orc_unwind_ip = .;				\
 	}								\
 	. = ALIGN(6);							\
 	.orc_unwind : AT(ADDR(.orc_unwind) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__start_orc_unwind) = .;			\
+		__start_orc_unwind = .;					\
 		KEEP(*(.orc_unwind))					\
-		VMLINUX_SYMBOL(__stop_orc_unwind) = .;			\
+		__stop_orc_unwind = .;					\
 	}								\
 	. = ALIGN(4);							\
 	.orc_lookup : AT(ADDR(.orc_lookup) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(orc_lookup) = .;				\
+		orc_lookup = .;						\
 		. += (((SIZEOF(.text) + LOOKUP_BLOCK_SIZE - 1) /	\
 			LOOKUP_BLOCK_SIZE) + 1) * 4;			\
-		VMLINUX_SYMBOL(orc_lookup_end) = .;			\
+		orc_lookup_end = .;					\
 	}
 #else
 #define ORC_UNWIND_TABLE
@@ -743,9 +752,9 @@
 #define TRACEDATA							\
 	. = ALIGN(4);							\
 	.tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__tracedata_start) = .;			\
+		__tracedata_start = .;					\
 		KEEP(*(.tracedata))					\
-		VMLINUX_SYMBOL(__tracedata_end) = .;			\
+		__tracedata_end = .;					\
 	}
 #else
 #define TRACEDATA
@@ -753,24 +762,24 @@
 
 #define NOTES								\
 	.notes : AT(ADDR(.notes) - LOAD_OFFSET) {			\
-		VMLINUX_SYMBOL(__start_notes) = .;			\
-		*(.note.*)						\
-		VMLINUX_SYMBOL(__stop_notes) = .;			\
+		__start_notes = .;					\
+		KEEP(*(.note.*))					\
+		__stop_notes = .;					\
 	}
 
 #define INIT_SETUP(initsetup_align)					\
 		. = ALIGN(initsetup_align);				\
-		VMLINUX_SYMBOL(__setup_start) = .;			\
+		__setup_start = .;					\
 		KEEP(*(.init.setup))					\
-		VMLINUX_SYMBOL(__setup_end) = .;
+		__setup_end = .;
 
 #define INIT_CALLS_LEVEL(level)						\
-		VMLINUX_SYMBOL(__initcall##level##_start) = .;		\
+		__initcall##level##_start = .;				\
 		KEEP(*(.initcall##level##.init))			\
 		KEEP(*(.initcall##level##s.init))			\
 
 #define INIT_CALLS							\
-		VMLINUX_SYMBOL(__initcall_start) = .;			\
+		__initcall_start = .;					\
 		KEEP(*(.initcallearly.init))				\
 		INIT_CALLS_LEVEL(0)					\
 		INIT_CALLS_LEVEL(1)					\
@@ -781,22 +790,22 @@
 		INIT_CALLS_LEVEL(rootfs)				\
 		INIT_CALLS_LEVEL(6)					\
 		INIT_CALLS_LEVEL(7)					\
-		VMLINUX_SYMBOL(__initcall_end) = .;
+		__initcall_end = .;
 
 #define CON_INITCALL							\
-		VMLINUX_SYMBOL(__con_initcall_start) = .;		\
+		__con_initcall_start = .;				\
 		KEEP(*(.con_initcall.init))				\
-		VMLINUX_SYMBOL(__con_initcall_end) = .;
+		__con_initcall_end = .;
 
 #define SECURITY_INITCALL						\
-		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
+		__security_initcall_start = .;				\
 		KEEP(*(.security_initcall.init))			\
-		VMLINUX_SYMBOL(__security_initcall_end) = .;
+		__security_initcall_end = .;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 #define INIT_RAM_FS							\
 	. = ALIGN(4);							\
-	VMLINUX_SYMBOL(__initramfs_start) = .;				\
+	__initramfs_start = .;						\
 	KEEP(*(.init.ramfs))						\
 	. = ALIGN(8);							\
 	KEEP(*(.init.ramfs.info))
@@ -851,7 +860,7 @@
  * sharing between subsections for different purposes.
  */
 #define PERCPU_INPUT(cacheline)						\
-	VMLINUX_SYMBOL(__per_cpu_start) = .;				\
+	__per_cpu_start = .;						\
 	*(.data..percpu..first)						\
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
@@ -861,7 +870,7 @@
 	*(.data..percpu)						\
 	*(.data..percpu..shared_aligned)				\
 	PERCPU_DECRYPTED_SECTION					\
-	VMLINUX_SYMBOL(__per_cpu_end) = .;
+	__per_cpu_end = .;
 
 /**
  * PERCPU_VADDR - define output section for percpu area
@@ -888,12 +897,11 @@
  * address, use PERCPU_SECTION.
  */
 #define PERCPU_VADDR(cacheline, vaddr, phdr)				\
-	VMLINUX_SYMBOL(__per_cpu_load) = .;				\
-	.data..percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)		\
-				- LOAD_OFFSET) {			\
+	__per_cpu_load = .;						\
+	.data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) {	\
 		PERCPU_INPUT(cacheline)					\
 	} phdr								\
-	. = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data..percpu);
+	. = __per_cpu_load + SIZEOF(.data..percpu);
 
 /**
  * PERCPU_SECTION - define output section for percpu area, simple version
@@ -910,7 +918,7 @@
 #define PERCPU_SECTION(cacheline)					\
 	. = ALIGN(PAGE_SIZE);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__per_cpu_load) = .;			\
+		__per_cpu_load = .;					\
 		PERCPU_INPUT(cacheline)					\
 	}
 
@@ -949,9 +957,9 @@
 #define INIT_TEXT_SECTION(inittext_align)				\
 	. = ALIGN(inittext_align);					\
 	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(_sinittext) = .;				\
+		_sinittext = .;						\
 		INIT_TEXT						\
-		VMLINUX_SYMBOL(_einittext) = .;				\
+		_einittext = .;						\
 	}
 
 #define INIT_DATA_SECTION(initsetup_align)				\
@@ -966,8 +974,8 @@
 
 #define BSS_SECTION(sbss_align, bss_align, stop_align)			\
 	. = ALIGN(sbss_align);						\
-	VMLINUX_SYMBOL(__bss_start) = .;				\
+	__bss_start = .;						\
 	SBSS(sbss_align)						\
 	BSS(bss_align)							\
 	. = ALIGN(stop_align);						\
-	VMLINUX_SYMBOL(__bss_stop) = .;
+	__bss_stop = .;
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 1aba888241dd..bd5e8ccf1687 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -17,6 +17,14 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 
+/*
+ * Maximum values for blocksize and alignmask, used to allocate
+ * static buffers that are big enough for any combination of
+ * ciphers and architectures.
+ */
+#define MAX_CIPHER_BLOCKSIZE		16
+#define MAX_CIPHER_ALIGNMASK		15
+
 struct crypto_aead;
 struct crypto_instance;
 struct module;
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index 482461d8931d..cc414db9da0a 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -245,8 +245,7 @@ ssize_t af_alg_sendpage(struct socket *sock, struct page *page,
 			int offset, size_t size, int flags);
 void af_alg_free_resources(struct af_alg_async_req *areq);
 void af_alg_async_cb(struct crypto_async_request *_req, int err);
-__poll_t af_alg_poll(struct file *file, struct socket *sock,
-			 poll_table *wait);
+__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events);
 struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
 					   unsigned int areqlen);
 int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
diff --git a/include/crypto/morus1280_glue.h b/include/crypto/morus1280_glue.h
new file mode 100644
index 000000000000..b26dd70efd9a
--- /dev/null
+++ b/include/crypto/morus1280_glue.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * The MORUS-1280 Authenticated-Encryption Algorithm
+ *   Common glue skeleton -- header file
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#ifndef _CRYPTO_MORUS1280_GLUE_H
+#define _CRYPTO_MORUS1280_GLUE_H
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <crypto/algapi.h>
+#include <crypto/aead.h>
+#include <crypto/morus_common.h>
+
+#define MORUS1280_WORD_SIZE 8
+#define MORUS1280_BLOCK_SIZE (MORUS_BLOCK_WORDS * MORUS1280_WORD_SIZE)
+
+struct morus1280_block {
+	u8 bytes[MORUS1280_BLOCK_SIZE];
+};
+
+struct morus1280_glue_ops {
+	void (*init)(void *state, const void *key, const void *iv);
+	void (*ad)(void *state, const void *data, unsigned int length);
+	void (*enc)(void *state, const void *src, void *dst, unsigned int length);
+	void (*dec)(void *state, const void *src, void *dst, unsigned int length);
+	void (*enc_tail)(void *state, const void *src, void *dst, unsigned int length);
+	void (*dec_tail)(void *state, const void *src, void *dst, unsigned int length);
+	void (*final)(void *state, void *tag_xor, u64 assoclen, u64 cryptlen);
+};
+
+struct morus1280_ctx {
+	const struct morus1280_glue_ops *ops;
+	struct morus1280_block key;
+};
+
+void crypto_morus1280_glue_init_ops(struct crypto_aead *aead,
+				    const struct morus1280_glue_ops *ops);
+int crypto_morus1280_glue_setkey(struct crypto_aead *aead, const u8 *key,
+				 unsigned int keylen);
+int crypto_morus1280_glue_setauthsize(struct crypto_aead *tfm,
+				      unsigned int authsize);
+int crypto_morus1280_glue_encrypt(struct aead_request *req);
+int crypto_morus1280_glue_decrypt(struct aead_request *req);
+
+int cryptd_morus1280_glue_setkey(struct crypto_aead *aead, const u8 *key,
+				 unsigned int keylen);
+int cryptd_morus1280_glue_setauthsize(struct crypto_aead *aead,
+				      unsigned int authsize);
+int cryptd_morus1280_glue_encrypt(struct aead_request *req);
+int cryptd_morus1280_glue_decrypt(struct aead_request *req);
+int cryptd_morus1280_glue_init_tfm(struct crypto_aead *aead);
+void cryptd_morus1280_glue_exit_tfm(struct crypto_aead *aead);
+
+#define MORUS1280_DECLARE_ALGS(id, driver_name, priority) \
+	static const struct morus1280_glue_ops crypto_morus1280_##id##_ops = {\
+		.init = crypto_morus1280_##id##_init, \
+		.ad = crypto_morus1280_##id##_ad, \
+		.enc = crypto_morus1280_##id##_enc, \
+		.enc_tail = crypto_morus1280_##id##_enc_tail, \
+		.dec = crypto_morus1280_##id##_dec, \
+		.dec_tail = crypto_morus1280_##id##_dec_tail, \
+		.final = crypto_morus1280_##id##_final, \
+	}; \
+	\
+	static int crypto_morus1280_##id##_init_tfm(struct crypto_aead *tfm) \
+	{ \
+		crypto_morus1280_glue_init_ops(tfm, &crypto_morus1280_##id##_ops); \
+		return 0; \
+	} \
+	\
+	static void crypto_morus1280_##id##_exit_tfm(struct crypto_aead *tfm) \
+	{ \
+	} \
+	\
+	struct aead_alg crypto_morus1280_##id##_algs[] = {\
+		{ \
+			.setkey = crypto_morus1280_glue_setkey, \
+			.setauthsize = crypto_morus1280_glue_setauthsize, \
+			.encrypt = crypto_morus1280_glue_encrypt, \
+			.decrypt = crypto_morus1280_glue_decrypt, \
+			.init = crypto_morus1280_##id##_init_tfm, \
+			.exit = crypto_morus1280_##id##_exit_tfm, \
+			\
+			.ivsize = MORUS_NONCE_SIZE, \
+			.maxauthsize = MORUS_MAX_AUTH_SIZE, \
+			.chunksize = MORUS1280_BLOCK_SIZE, \
+			\
+			.base = { \
+				.cra_flags = CRYPTO_ALG_INTERNAL, \
+				.cra_blocksize = 1, \
+				.cra_ctxsize = sizeof(struct morus1280_ctx), \
+				.cra_alignmask = 0, \
+				\
+				.cra_name = "__morus1280", \
+				.cra_driver_name = "__"driver_name, \
+				\
+				.cra_module = THIS_MODULE, \
+			} \
+		}, { \
+			.setkey = cryptd_morus1280_glue_setkey, \
+			.setauthsize = cryptd_morus1280_glue_setauthsize, \
+			.encrypt = cryptd_morus1280_glue_encrypt, \
+			.decrypt = cryptd_morus1280_glue_decrypt, \
+			.init = cryptd_morus1280_glue_init_tfm, \
+			.exit = cryptd_morus1280_glue_exit_tfm, \
+			\
+			.ivsize = MORUS_NONCE_SIZE, \
+			.maxauthsize = MORUS_MAX_AUTH_SIZE, \
+			.chunksize = MORUS1280_BLOCK_SIZE, \
+			\
+			.base = { \
+				.cra_flags = CRYPTO_ALG_ASYNC, \
+				.cra_blocksize = 1, \
+				.cra_ctxsize = sizeof(struct crypto_aead *), \
+				.cra_alignmask = 0, \
+				\
+				.cra_priority = priority, \
+				\
+				.cra_name = "morus1280", \
+				.cra_driver_name = driver_name, \
+				\
+				.cra_module = THIS_MODULE, \
+			} \
+		} \
+	}
+
+#endif /* _CRYPTO_MORUS1280_GLUE_H */
diff --git a/include/crypto/morus640_glue.h b/include/crypto/morus640_glue.h
new file mode 100644
index 000000000000..90c8db07e740
--- /dev/null
+++ b/include/crypto/morus640_glue.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * The MORUS-640 Authenticated-Encryption Algorithm
+ *   Common glue skeleton -- header file
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#ifndef _CRYPTO_MORUS640_GLUE_H
+#define _CRYPTO_MORUS640_GLUE_H
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <crypto/algapi.h>
+#include <crypto/aead.h>
+#include <crypto/morus_common.h>
+
+#define MORUS640_WORD_SIZE 4
+#define MORUS640_BLOCK_SIZE (MORUS_BLOCK_WORDS * MORUS640_WORD_SIZE)
+
+struct morus640_block {
+	u8 bytes[MORUS640_BLOCK_SIZE];
+};
+
+struct morus640_glue_ops {
+	void (*init)(void *state, const void *key, const void *iv);
+	void (*ad)(void *state, const void *data, unsigned int length);
+	void (*enc)(void *state, const void *src, void *dst, unsigned int length);
+	void (*dec)(void *state, const void *src, void *dst, unsigned int length);
+	void (*enc_tail)(void *state, const void *src, void *dst, unsigned int length);
+	void (*dec_tail)(void *state, const void *src, void *dst, unsigned int length);
+	void (*final)(void *state, void *tag_xor, u64 assoclen, u64 cryptlen);
+};
+
+struct morus640_ctx {
+	const struct morus640_glue_ops *ops;
+	struct morus640_block key;
+};
+
+void crypto_morus640_glue_init_ops(struct crypto_aead *aead,
+				   const struct morus640_glue_ops *ops);
+int crypto_morus640_glue_setkey(struct crypto_aead *aead, const u8 *key,
+				unsigned int keylen);
+int crypto_morus640_glue_setauthsize(struct crypto_aead *tfm,
+				     unsigned int authsize);
+int crypto_morus640_glue_encrypt(struct aead_request *req);
+int crypto_morus640_glue_decrypt(struct aead_request *req);
+
+int cryptd_morus640_glue_setkey(struct crypto_aead *aead, const u8 *key,
+				unsigned int keylen);
+int cryptd_morus640_glue_setauthsize(struct crypto_aead *aead,
+				     unsigned int authsize);
+int cryptd_morus640_glue_encrypt(struct aead_request *req);
+int cryptd_morus640_glue_decrypt(struct aead_request *req);
+int cryptd_morus640_glue_init_tfm(struct crypto_aead *aead);
+void cryptd_morus640_glue_exit_tfm(struct crypto_aead *aead);
+
+#define MORUS640_DECLARE_ALGS(id, driver_name, priority) \
+	static const struct morus640_glue_ops crypto_morus640_##id##_ops = {\
+		.init = crypto_morus640_##id##_init, \
+		.ad = crypto_morus640_##id##_ad, \
+		.enc = crypto_morus640_##id##_enc, \
+		.enc_tail = crypto_morus640_##id##_enc_tail, \
+		.dec = crypto_morus640_##id##_dec, \
+		.dec_tail = crypto_morus640_##id##_dec_tail, \
+		.final = crypto_morus640_##id##_final, \
+	}; \
+	\
+	static int crypto_morus640_##id##_init_tfm(struct crypto_aead *tfm) \
+	{ \
+		crypto_morus640_glue_init_ops(tfm, &crypto_morus640_##id##_ops); \
+		return 0; \
+	} \
+	\
+	static void crypto_morus640_##id##_exit_tfm(struct crypto_aead *tfm) \
+	{ \
+	} \
+	\
+	struct aead_alg crypto_morus640_##id##_algs[] = {\
+		{ \
+			.setkey = crypto_morus640_glue_setkey, \
+			.setauthsize = crypto_morus640_glue_setauthsize, \
+			.encrypt = crypto_morus640_glue_encrypt, \
+			.decrypt = crypto_morus640_glue_decrypt, \
+			.init = crypto_morus640_##id##_init_tfm, \
+			.exit = crypto_morus640_##id##_exit_tfm, \
+			\
+			.ivsize = MORUS_NONCE_SIZE, \
+			.maxauthsize = MORUS_MAX_AUTH_SIZE, \
+			.chunksize = MORUS640_BLOCK_SIZE, \
+			\
+			.base = { \
+				.cra_flags = CRYPTO_ALG_INTERNAL, \
+				.cra_blocksize = 1, \
+				.cra_ctxsize = sizeof(struct morus640_ctx), \
+				.cra_alignmask = 0, \
+				\
+				.cra_name = "__morus640", \
+				.cra_driver_name = "__"driver_name, \
+				\
+				.cra_module = THIS_MODULE, \
+			} \
+		}, { \
+			.setkey = cryptd_morus640_glue_setkey, \
+			.setauthsize = cryptd_morus640_glue_setauthsize, \
+			.encrypt = cryptd_morus640_glue_encrypt, \
+			.decrypt = cryptd_morus640_glue_decrypt, \
+			.init = cryptd_morus640_glue_init_tfm, \
+			.exit = cryptd_morus640_glue_exit_tfm, \
+			\
+			.ivsize = MORUS_NONCE_SIZE, \
+			.maxauthsize = MORUS_MAX_AUTH_SIZE, \
+			.chunksize = MORUS640_BLOCK_SIZE, \
+			\
+			.base = { \
+				.cra_flags = CRYPTO_ALG_ASYNC, \
+				.cra_blocksize = 1, \
+				.cra_ctxsize = sizeof(struct crypto_aead *), \
+				.cra_alignmask = 0, \
+				\
+				.cra_priority = priority, \
+				\
+				.cra_name = "morus640", \
+				.cra_driver_name = driver_name, \
+				\
+				.cra_module = THIS_MODULE, \
+			} \
+		} \
+	}
+
+#endif /* _CRYPTO_MORUS640_GLUE_H */
diff --git a/include/crypto/morus_common.h b/include/crypto/morus_common.h
new file mode 100644
index 000000000000..39f28c749951
--- /dev/null
+++ b/include/crypto/morus_common.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * The MORUS Authenticated-Encryption Algorithm
+ *   Common definitions
+ *
+ * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#ifndef _CRYPTO_MORUS_COMMON_H
+#define _CRYPTO_MORUS_COMMON_H
+
+#define MORUS_BLOCK_WORDS 4
+#define MORUS_STATE_BLOCKS 5
+#define MORUS_NONCE_SIZE 16
+#define MORUS_MAX_AUTH_SIZE 16
+
+#endif /* _CRYPTO_MORUS_COMMON_H */
diff --git a/include/crypto/salsa20.h b/include/crypto/salsa20.h
deleted file mode 100644
index 19ed48aefc86..000000000000
--- a/include/crypto/salsa20.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Common values for the Salsa20 algorithm
- */
-
-#ifndef _CRYPTO_SALSA20_H
-#define _CRYPTO_SALSA20_H
-
-#include <linux/types.h>
-
-#define SALSA20_IV_SIZE		8
-#define SALSA20_MIN_KEY_SIZE	16
-#define SALSA20_MAX_KEY_SIZE	32
-#define SALSA20_BLOCK_SIZE	64
-
-struct crypto_skcipher;
-
-struct salsa20_ctx {
-	u32 initial_state[16];
-};
-
-void crypto_salsa20_init(u32 *state, const struct salsa20_ctx *ctx,
-			 const u8 *iv);
-int crypto_salsa20_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			  unsigned int keysize);
-
-#endif /* _CRYPTO_SALSA20_H */
diff --git a/include/crypto/sm4.h b/include/crypto/sm4.h
index b64e64d20b28..7afd730d16ff 100644
--- a/include/crypto/sm4.h
+++ b/include/crypto/sm4.h
@@ -25,4 +25,7 @@ int crypto_sm4_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 int crypto_sm4_expand_key(struct crypto_sm4_ctx *ctx, const u8 *in_key,
 			  unsigned int key_len);
 
+void crypto_sm4_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in);
+void crypto_sm4_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in);
+
 #endif
diff --git a/include/drm/amd_asic_type.h b/include/drm/amd_asic_type.h
index 6c731c52c071..dd63d08cc54e 100644
--- a/include/drm/amd_asic_type.h
+++ b/include/drm/amd_asic_type.h
@@ -44,8 +44,10 @@ enum amd_asic_type {
 	CHIP_POLARIS10,
 	CHIP_POLARIS11,
 	CHIP_POLARIS12,
+	CHIP_VEGAM,
 	CHIP_VEGA10,
 	CHIP_VEGA12,
+	CHIP_VEGA20,
 	CHIP_RAVEN,
 	CHIP_LAST,
 };
diff --git a/include/drm/bridge/analogix_dp.h b/include/drm/bridge/analogix_dp.h
index e9a1116d2f8e..475b706b49de 100644
--- a/include/drm/bridge/analogix_dp.h
+++ b/include/drm/bridge/analogix_dp.h
@@ -33,7 +33,8 @@ struct analogix_dp_plat_data {
 	struct drm_connector *connector;
 	bool skip_connector;
 
-	int (*power_on)(struct analogix_dp_plat_data *);
+	int (*power_on_start)(struct analogix_dp_plat_data *);
+	int (*power_on_end)(struct analogix_dp_plat_data *);
 	int (*power_off)(struct analogix_dp_plat_data *);
 	int (*attach)(struct analogix_dp_plat_data *, struct drm_bridge *,
 		      struct drm_connector *);
diff --git a/include/drm/bridge/dw_hdmi.h b/include/drm/bridge/dw_hdmi.h
index dd2a8cf7d20b..ccb5aa8468e0 100644
--- a/include/drm/bridge/dw_hdmi.h
+++ b/include/drm/bridge/dw_hdmi.h
@@ -151,7 +151,7 @@ struct dw_hdmi *dw_hdmi_bind(struct platform_device *pdev,
 			     struct drm_encoder *encoder,
 			     const struct dw_hdmi_plat_data *plat_data);
 
-void dw_hdmi_setup_rx_sense(struct device *dev, bool hpd, bool rx_sense);
+void dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense);
 
 void dw_hdmi_set_sample_rate(struct dw_hdmi *hdmi, unsigned int rate);
 void dw_hdmi_audio_enable(struct dw_hdmi *hdmi);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index c6666cd09347..f5099c12c6a6 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -95,14 +95,6 @@ struct dma_buf_attachment;
 struct pci_dev;
 struct pci_controller;
 
-/***********************************************************************/
-/** \name DRM template customization defaults */
-/*@{*/
-
-/***********************************************************************/
-/** \name Internal types and structures */
-/*@{*/
-
 #define DRM_IF_VERSION(maj, min) (maj << 16 | min)
 
 /**
@@ -123,27 +115,13 @@ static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev)
 #define DRM_SWITCH_POWER_CHANGING 2
 #define DRM_SWITCH_POWER_DYNAMIC_OFF 3
 
-static __inline__ int drm_core_check_feature(struct drm_device *dev,
-					     int feature)
+static inline bool drm_core_check_feature(struct drm_device *dev, int feature)
 {
-	return ((dev->driver->driver_features & feature) ? 1 : 0);
+	return dev->driver->driver_features & feature;
 }
 
-/******************************************************************/
-/** \name Internal function definitions */
-/*@{*/
-
-				/* Driver support (drm_drv.h) */
-
-/*
- * These are exported to drivers so that they can implement fencing using
- * DMA quiscent + idle. DMA quiescent usually requires the hardware lock.
- */
-
-/*@}*/
-
 /* returns true if currently okay to sleep */
-static __inline__ bool drm_can_sleep(void)
+static inline bool drm_can_sleep(void)
 {
 	if (in_atomic() || in_dbg_master() || irqs_disabled())
 		return false;
diff --git a/include/drm/drm_blend.h b/include/drm/drm_blend.h
index 17606026590b..330c561c4c11 100644
--- a/include/drm/drm_blend.h
+++ b/include/drm/drm_blend.h
@@ -36,6 +36,9 @@ static inline bool drm_rotation_90_or_270(unsigned int rotation)
 	return rotation & (DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270);
 }
 
+#define DRM_BLEND_ALPHA_OPAQUE		0xffff
+
+int drm_plane_create_alpha_property(struct drm_plane *plane);
 int drm_plane_create_rotation_property(struct drm_plane *plane,
 				       unsigned int rotation,
 				       unsigned int supported_rotations);
diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
index 7c4fa32f3fc6..858ba19a3e29 100644
--- a/include/drm/drm_device.h
+++ b/include/drm/drm_device.h
@@ -38,7 +38,6 @@ struct drm_device {
 	struct device *dev;		/**< Device structure of bus-device */
 	struct drm_driver *driver;	/**< DRM driver managing the device */
 	void *dev_private;		/**< DRM driver private data */
-	struct drm_minor *control;		/**< Control node */
 	struct drm_minor *primary;		/**< Primary node */
 	struct drm_minor *render;		/**< Render node */
 	bool registered;
@@ -46,7 +45,14 @@ struct drm_device {
 	/* currently active master for this device. Protected by master_mutex */
 	struct drm_master *master;
 
-	atomic_t unplugged;			/**< Flag whether dev is dead */
+	/**
+	 * @unplugged:
+	 *
+	 * Flag to tell if the device has been unplugged.
+	 * See drm_dev_enter() and drm_dev_is_unplugged().
+	 */
+	bool unplugged;
+
 	struct inode *anon_inode;		/**< inode for private address-space */
 	char *unique;				/**< unique name of the device */
 	/*@} */
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 62903bae0221..c01564991a9f 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -64,6 +64,11 @@
 /* AUX CH addresses */
 /* DPCD */
 #define DP_DPCD_REV                         0x000
+# define DP_DPCD_REV_10                     0x10
+# define DP_DPCD_REV_11                     0x11
+# define DP_DPCD_REV_12                     0x12
+# define DP_DPCD_REV_13                     0x13
+# define DP_DPCD_REV_14                     0x14
 
 #define DP_MAX_LINK_RATE                    0x001
 
@@ -119,6 +124,7 @@
 # define DP_DPCD_DISPLAY_CONTROL_CAPABLE     (1 << 3) /* edp v1.2 or higher */
 
 #define DP_TRAINING_AUX_RD_INTERVAL         0x00e   /* XXX 1.2? */
+# define DP_TRAINING_AUX_RD_MASK            0x7F    /* XXX 1.2? */
 
 #define DP_ADAPTER_CAP			    0x00f   /* 1.2 */
 # define DP_FORCE_LOAD_SENSE_CAP	    (1 << 0)
@@ -478,6 +484,7 @@
 # define DP_PSR_FRAME_CAPTURE		    (1 << 3)
 # define DP_PSR_SELECTIVE_UPDATE	    (1 << 4)
 # define DP_PSR_IRQ_HPD_WITH_CRC_ERRORS     (1 << 5)
+# define DP_PSR_ENABLE_PSR2		    (1 << 6) /* eDP 1.4a */
 
 #define DP_ADAPTER_CTRL			    0x1a0
 # define DP_ADAPTER_CTRL_FORCE_LOAD_SENSE   (1 << 0)
@@ -794,6 +801,15 @@
 # define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_MASK	(0xf << 4)
 # define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_SHIFT	4
 
+#define DP_LAST_RECEIVED_PSR_SDP	    0x200a /* eDP 1.2 */
+# define DP_PSR_STATE_BIT		    (1 << 0) /* eDP 1.2 */
+# define DP_UPDATE_RFB_BIT		    (1 << 1) /* eDP 1.2 */
+# define DP_CRC_VALID_BIT		    (1 << 2) /* eDP 1.2 */
+# define DP_SU_VALID			    (1 << 3) /* eDP 1.4 */
+# define DP_FIRST_SCAN_LINE_SU_REGION	    (1 << 4) /* eDP 1.4 */
+# define DP_LAST_SCAN_LINE_SU_REGION	    (1 << 5) /* eDP 1.4 */
+# define DP_Y_COORDINATE_VALID		    (1 << 6) /* eDP 1.4a */
+
 #define DP_RECEIVER_ALPM_STATUS		    0x200b  /* eDP 1.4 */
 # define DP_ALPM_LOCK_TIMEOUT_ERROR	    (1 << 0)
 
@@ -967,18 +983,18 @@ int drm_dp_bw_code_to_link_rate(u8 link_bw);
 #define DP_SDP_VSC_EXT_CEA		0x21 /* DP 1.4 */
 /* 0x80+ CEA-861 infoframe types */
 
-struct edp_sdp_header {
+struct dp_sdp_header {
 	u8 HB0; /* Secondary Data Packet ID */
 	u8 HB1; /* Secondary Data Packet Type */
-	u8 HB2; /* 7:5 reserved, 4:0 revision number */
-	u8 HB3; /* 7:5 reserved, 4:0 number of valid data bytes */
+	u8 HB2; /* Secondary Data Packet Specific header, Byte 0 */
+	u8 HB3; /* Secondary Data packet Specific header, Byte 1 */
 } __packed;
 
 #define EDP_SDP_HEADER_REVISION_MASK		0x1F
 #define EDP_SDP_HEADER_VALID_PAYLOAD_BYTES	0x1F
 
 struct edp_vsc_psr {
-	struct edp_sdp_header sdp_header;
+	struct dp_sdp_header sdp_header;
 	u8 DB0; /* Stereo Interface */
 	u8 DB1; /* 0 - PSR State; 1 - Update RFB; 2 - CRC Valid */
 	u8 DB2; /* CRC value bits 7:0 of the R or Cr component */
diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
index d23dcdd1bd95..7e545f5f94d3 100644
--- a/include/drm/drm_drv.h
+++ b/include/drm/drm_drv.h
@@ -624,6 +624,8 @@ void drm_dev_get(struct drm_device *dev);
 void drm_dev_put(struct drm_device *dev);
 void drm_dev_unref(struct drm_device *dev);
 void drm_put_dev(struct drm_device *dev);
+bool drm_dev_enter(struct drm_device *dev, int *idx);
+void drm_dev_exit(int idx);
 void drm_dev_unplug(struct drm_device *dev);
 
 /**
@@ -635,11 +637,16 @@ void drm_dev_unplug(struct drm_device *dev);
  * unplugged, these two functions guarantee that any store before calling
  * drm_dev_unplug() is visible to callers of this function after it completes
  */
-static inline int drm_dev_is_unplugged(struct drm_device *dev)
+static inline bool drm_dev_is_unplugged(struct drm_device *dev)
 {
-	int ret = atomic_read(&dev->unplugged);
-	smp_rmb();
-	return ret;
+	int idx;
+
+	if (drm_dev_enter(dev, &idx)) {
+		drm_dev_exit(idx);
+		return false;
+	}
+
+	return true;
 }
 
 
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index 8d89a9c3748d..b25d12ef120a 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -465,8 +465,6 @@ struct edid *drm_get_edid(struct drm_connector *connector,
 struct edid *drm_get_edid_switcheroo(struct drm_connector *connector,
 				     struct i2c_adapter *adapter);
 struct edid *drm_edid_duplicate(const struct edid *edid);
-void drm_reset_display_info(struct drm_connector *connector);
-u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edid);
 int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid);
 
 u8 drm_match_cea_mode(const struct drm_display_mode *to_match);
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index 5176c3797680..027ac16da3d1 100644
--- a/include/drm/drm_file.h
+++ b/include/drm/drm_file.h
@@ -47,6 +47,9 @@ struct device;
  * header include loops we need it here for now.
  */
 
+/* Note that the order of this enum is ABI (it determines
+ * /dev/dri/renderD* numbers).
+ */
 enum drm_minor_type {
 	DRM_MINOR_PRIMARY,
 	DRM_MINOR_CONTROL,
@@ -182,6 +185,14 @@ struct drm_file {
 	unsigned atomic:1;
 
 	/**
+	 * @aspect_ratio_allowed:
+	 *
+	 * True, if client can handle picture aspect ratios, and has requested
+	 * to pass this information along with the mode.
+	 */
+	unsigned aspect_ratio_allowed:1;
+
+	/**
 	 * @is_master:
 	 *
 	 * This client is the creator of @master. Protected by struct
@@ -348,18 +359,6 @@ static inline bool drm_is_render_client(const struct drm_file *file_priv)
 	return file_priv->minor->type == DRM_MINOR_RENDER;
 }
 
-/**
- * drm_is_control_client - is this an open file of the control node
- * @file_priv: DRM file
- *
- * Control nodes are deprecated and in the process of getting removed from the
- * DRM userspace API. Do not ever use!
- */
-static inline bool drm_is_control_client(const struct drm_file *file_priv)
-{
-	return file_priv->minor->type == DRM_MINOR_CONTROL;
-}
-
 int drm_open(struct inode *inode, struct file *filp);
 ssize_t drm_read(struct file *filp, char __user *buffer,
 		 size_t count, loff_t *offset);
diff --git a/include/drm/drm_gem_framebuffer_helper.h b/include/drm/drm_gem_framebuffer_helper.h
index 5ca7cdc3f527..a38de7eb55b4 100644
--- a/include/drm/drm_gem_framebuffer_helper.h
+++ b/include/drm/drm_gem_framebuffer_helper.h
@@ -10,6 +10,7 @@ struct drm_gem_object;
 struct drm_mode_fb_cmd2;
 struct drm_plane;
 struct drm_plane_state;
+struct drm_simple_display_pipe;
 
 struct drm_gem_object *drm_gem_fb_get_obj(struct drm_framebuffer *fb,
 					  unsigned int plane);
@@ -27,6 +28,8 @@ drm_gem_fb_create(struct drm_device *dev, struct drm_file *file,
 
 int drm_gem_fb_prepare_fb(struct drm_plane *plane,
 			  struct drm_plane_state *state);
+int drm_gem_fb_simple_display_pipe_prepare_fb(struct drm_simple_display_pipe *pipe,
+					      struct drm_plane_state *plane_state);
 
 struct drm_framebuffer *
 drm_gem_fbdev_fb_create(struct drm_device *dev,
diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h
index 562fa7df2637..98e63d870139 100644
--- a/include/drm/drm_hdcp.h
+++ b/include/drm/drm_hdcp.h
@@ -19,7 +19,7 @@
 #define DRM_HDCP_RI_LEN				2
 #define DRM_HDCP_V_PRIME_PART_LEN		4
 #define DRM_HDCP_V_PRIME_NUM_PARTS		5
-#define DRM_HDCP_NUM_DOWNSTREAM(x)		(x & 0x3f)
+#define DRM_HDCP_NUM_DOWNSTREAM(x)		(x & 0x7f)
 #define DRM_HDCP_MAX_CASCADE_EXCEEDED(x)	(x & BIT(3))
 #define DRM_HDCP_MAX_DEVICE_EXCEEDED(x)		(x & BIT(7))
 
diff --git a/include/drm/drm_ioctl.h b/include/drm/drm_ioctl.h
index add42809642a..fafb6f592c4b 100644
--- a/include/drm/drm_ioctl.h
+++ b/include/drm/drm_ioctl.h
@@ -109,13 +109,6 @@ enum drm_ioctl_flags {
 	 */
 	DRM_ROOT_ONLY		= BIT(2),
 	/**
-	 * @DRM_CONTROL_ALLOW:
-	 *
-	 * Deprecated, do not use. Control nodes are in the process of getting
-	 * removed.
-	 */
-	DRM_CONTROL_ALLOW	= BIT(3),
-	/**
 	 * @DRM_UNLOCKED:
 	 *
 	 * Whether &drm_ioctl_desc.func should be called with the DRM BKL held
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
index cf0e7d89bcdf..8fad66f88e4f 100644
--- a/include/drm/drm_legacy.h
+++ b/include/drm/drm_legacy.h
@@ -194,8 +194,8 @@ void drm_legacy_ioremap(struct drm_local_map *map, struct drm_device *dev);
 void drm_legacy_ioremap_wc(struct drm_local_map *map, struct drm_device *dev);
 void drm_legacy_ioremapfree(struct drm_local_map *map, struct drm_device *dev);
 
-static __inline__ struct drm_local_map *drm_legacy_findmap(struct drm_device *dev,
-							   unsigned int token)
+static inline struct drm_local_map *drm_legacy_findmap(struct drm_device *dev,
+						       unsigned int token)
 {
 	struct drm_map_list *_entry;
 	list_for_each_entry(_entry, &dev->maplist, head)
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index 7569f22ffef6..33b3a96d66d0 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -796,6 +796,14 @@ struct drm_mode_config {
 	bool allow_fb_modifiers;
 
 	/**
+	 * @normalize_zpos:
+	 *
+	 * If true the drm core will call drm_atomic_normalize_zpos() as part of
+	 * atomic mode checking from drm_atomic_helper_check()
+	 */
+	bool normalize_zpos;
+
+	/**
 	 * @modifiers_property: Plane property to list support modifier/format
 	 * combination.
 	 */
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index 0d310beae6af..b159fe07fcf9 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -147,6 +147,12 @@ enum drm_mode_status {
 
 #define DRM_MODE_FLAG_3D_MAX	DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF
 
+#define DRM_MODE_MATCH_TIMINGS (1 << 0)
+#define DRM_MODE_MATCH_CLOCK (1 << 1)
+#define DRM_MODE_MATCH_FLAGS (1 << 2)
+#define DRM_MODE_MATCH_3D_FLAGS (1 << 3)
+#define DRM_MODE_MATCH_ASPECT_RATIO (1 << 4)
+
 /**
  * struct drm_display_mode - DRM kernel-internal display mode structure
  * @hdisplay: horizontal display size
@@ -405,6 +411,19 @@ struct drm_display_mode {
 	 * Field for setting the HDMI picture aspect ratio of a mode.
 	 */
 	enum hdmi_picture_aspect picture_aspect_ratio;
+
+	/**
+	 * @export_head:
+	 *
+	 * struct list_head for modes to be exposed to the userspace.
+	 * This is to maintain a list of exposed modes while preparing
+	 * user-mode's list in drm_mode_getconnector ioctl. The purpose of this
+	 * list_head only lies in the ioctl function, and is not expected to be
+	 * used outside the function.
+	 * Once used, the stale pointers are not reset, but left as it is, to
+	 * avoid overhead of protecting it by mode_config.mutex.
+	 */
+	struct list_head export_head;
 };
 
 /**
@@ -490,6 +509,9 @@ void drm_mode_copy(struct drm_display_mode *dst,
 		   const struct drm_display_mode *src);
 struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev,
 					    const struct drm_display_mode *mode);
+bool drm_mode_match(const struct drm_display_mode *mode1,
+		    const struct drm_display_mode *mode2,
+		    unsigned int match_flags);
 bool drm_mode_equal(const struct drm_display_mode *mode1,
 		    const struct drm_display_mode *mode2);
 bool drm_mode_equal_no_clocks(const struct drm_display_mode *mode1,
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index 3e76ca805b0f..35e2a3a79fc5 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -1004,11 +1004,14 @@ struct drm_plane_helper_funcs {
 	 * This function must not block for outstanding rendering, since it is
 	 * called in the context of the atomic IOCTL even for async commits to
 	 * be able to return any errors to userspace. Instead the recommended
-	 * way is to fill out the fence member of the passed-in
+	 * way is to fill out the &drm_plane_state.fence of the passed-in
 	 * &drm_plane_state. If the driver doesn't support native fences then
 	 * equivalent functionality should be implemented through private
 	 * members in the plane structure.
 	 *
+	 * Drivers which always have their buffers pinned should use
+	 * drm_gem_fb_prepare_fb() for this hook.
+	 *
 	 * The helpers will call @cleanup_fb with matching arguments for every
 	 * successful call to this hook.
 	 *
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index f7bf4a48b1c3..26fa50c2a50e 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -43,6 +43,7 @@ struct drm_modeset_acquire_ctx;
  *	plane (in 16.16)
  * @src_w: width of visible portion of plane (in 16.16)
  * @src_h: height of visible portion of plane (in 16.16)
+ * @alpha: opacity of the plane
  * @rotation: rotation of the plane
  * @zpos: priority of the given plane on crtc (optional)
  *	Note that multiple active planes on the same crtc can have an identical
@@ -51,8 +52,8 @@ struct drm_modeset_acquire_ctx;
  *	plane with a lower ID.
  * @normalized_zpos: normalized value of zpos: unique, range from 0 to N-1
  *	where N is the number of active planes for given crtc. Note that
- *	the driver must call drm_atomic_normalize_zpos() to update this before
- *	it can be trusted.
+ *	the driver must set drm_mode_config.normalize_zpos or call
+ *	drm_atomic_normalize_zpos() to update this before it can be trusted.
  * @src: clipped source coordinates of the plane (in 16.16)
  * @dst: clipped destination coordinates of the plane
  * @state: backpointer to global drm_atomic_state
@@ -79,8 +80,15 @@ struct drm_plane_state {
 	/**
 	 * @fence:
 	 *
-	 * Optional fence to wait for before scanning out @fb. Do not write this
-	 * directly, use drm_atomic_set_fence_for_plane()
+	 * Optional fence to wait for before scanning out @fb. The core atomic
+	 * code will set this when userspace is using explicit fencing. Do not
+	 * write this directly for a driver's implicit fence, use
+	 * drm_atomic_set_fence_for_plane() to ensure that an explicit fence is
+	 * preserved.
+	 *
+	 * Drivers should store any implicit fence in this from their
+	 * &drm_plane_helper.prepare_fb callback. See drm_gem_fb_prepare_fb()
+	 * and drm_gem_fb_simple_display_pipe_prepare_fb() for suitable helpers.
 	 */
 	struct dma_fence *fence;
 
@@ -106,6 +114,9 @@ struct drm_plane_state {
 	uint32_t src_x, src_y;
 	uint32_t src_h, src_w;
 
+	/* Plane opacity */
+	u16 alpha;
+
 	/* Plane rotation */
 	unsigned int rotation;
 
@@ -496,6 +507,7 @@ enum drm_plane_type {
  * @funcs: helper functions
  * @properties: property tracking for this plane
  * @type: type of plane (overlay, primary, cursor)
+ * @alpha_property: alpha property for this plane
  * @zpos_property: zpos property for this plane
  * @rotation_property: rotation property for this plane
  * @helper_private: mid-layer private data
@@ -571,6 +583,7 @@ struct drm_plane {
 	 */
 	struct drm_plane_state *state;
 
+	struct drm_property *alpha_property;
 	struct drm_property *zpos_property;
 	struct drm_property *rotation_property;
 
diff --git a/include/drm/drm_property.h b/include/drm/drm_property.h
index d1423c7f3c73..1d5c0b2a8956 100644
--- a/include/drm/drm_property.h
+++ b/include/drm/drm_property.h
@@ -260,7 +260,7 @@ struct drm_property *drm_property_create_object(struct drm_device *dev,
 						uint32_t type);
 struct drm_property *drm_property_create_bool(struct drm_device *dev,
 					      u32 flags, const char *name);
-int drm_property_add_enum(struct drm_property *property, int index,
+int drm_property_add_enum(struct drm_property *property,
 			  uint64_t value, const char *name);
 void drm_property_destroy(struct drm_device *dev, struct drm_property *property);
 
@@ -281,32 +281,6 @@ struct drm_property_blob *drm_property_blob_get(struct drm_property_blob *blob);
 void drm_property_blob_put(struct drm_property_blob *blob);
 
 /**
- * drm_property_reference_blob - acquire a blob property reference
- * @blob: DRM blob property
- *
- * This is a compatibility alias for drm_property_blob_get() and should not be
- * used by new code.
- */
-static inline struct drm_property_blob *
-drm_property_reference_blob(struct drm_property_blob *blob)
-{
-	return drm_property_blob_get(blob);
-}
-
-/**
- * drm_property_unreference_blob - release a blob property reference
- * @blob: DRM blob property
- *
- * This is a compatibility alias for drm_property_blob_put() and should not be
- * used by new code.
- */
-static inline void
-drm_property_unreference_blob(struct drm_property_blob *blob)
-{
-	drm_property_blob_put(blob);
-}
-
-/**
  * drm_property_find - find property object
  * @dev: DRM device
  * @file_priv: drm file to check for lease against.
diff --git a/include/drm/drm_rect.h b/include/drm/drm_rect.h
index 44bc122b9ee0..6c54544a4be7 100644
--- a/include/drm/drm_rect.h
+++ b/include/drm/drm_rect.h
@@ -175,8 +175,7 @@ static inline bool drm_rect_equals(const struct drm_rect *r1,
 
 bool drm_rect_intersect(struct drm_rect *r, const struct drm_rect *clip);
 bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst,
-			  const struct drm_rect *clip,
-			  int hscale, int vscale);
+			  const struct drm_rect *clip);
 int drm_rect_calc_hscale(const struct drm_rect *src,
 			 const struct drm_rect *dst,
 			 int min_hscale, int max_hscale);
diff --git a/include/drm/drm_simple_kms_helper.h b/include/drm/drm_simple_kms_helper.h
index 1b4e352143fd..451960438a29 100644
--- a/include/drm/drm_simple_kms_helper.h
+++ b/include/drm/drm_simple_kms_helper.h
@@ -64,7 +64,8 @@ struct drm_simple_display_pipe_funcs {
 	 * This hook is optional.
 	 */
 	void (*enable)(struct drm_simple_display_pipe *pipe,
-		       struct drm_crtc_state *crtc_state);
+		       struct drm_crtc_state *crtc_state,
+		       struct drm_plane_state *plane_state);
 	/**
 	 * @disable:
 	 *
@@ -115,6 +116,9 @@ struct drm_simple_display_pipe_funcs {
 	 * Optional, called by &drm_plane_helper_funcs.prepare_fb.  Please read
 	 * the documentation for the &drm_plane_helper_funcs.prepare_fb hook for
 	 * more details.
+	 *
+	 * Drivers which always have their buffers pinned should use
+	 * drm_gem_fb_simple_display_pipe_prepare_fb() for this hook.
 	 */
 	int (*prepare_fb)(struct drm_simple_display_pipe *pipe,
 			  struct drm_plane_state *plane_state);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index dfd54fb94e10..dec655894d08 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -43,10 +43,12 @@ enum drm_sched_priority {
 };
 
 /**
- * A scheduler entity is a wrapper around a job queue or a group
- * of other entities. Entities take turns emitting jobs from their
- * job queues to corresponding hardware ring based on scheduling
- * policy.
+ * drm_sched_entity - A wrapper around a job queue (typically attached
+ * to the DRM file_priv).
+ *
+ * Entities will emit jobs in order to their corresponding hardware
+ * ring, and the scheduler will alternate between entities based on
+ * scheduling policy.
 */
 struct drm_sched_entity {
 	struct list_head		list;
@@ -54,7 +56,6 @@ struct drm_sched_entity {
 	spinlock_t			rq_lock;
 	struct drm_gpu_scheduler	*sched;
 
-	spinlock_t			queue_lock;
 	struct spsc_queue		job_queue;
 
 	atomic_t			fence_seq;
@@ -63,6 +64,8 @@ struct drm_sched_entity {
 	struct dma_fence		*dependency;
 	struct dma_fence_cb		cb;
 	atomic_t			*guilty; /* points to ctx's guilty */
+	int            fini_status;
+	struct dma_fence    *last_scheduled;
 };
 
 /**
@@ -78,7 +81,18 @@ struct drm_sched_rq {
 
 struct drm_sched_fence {
 	struct dma_fence		scheduled;
+
+	/* This fence is what will be signaled by the scheduler when
+	 * the job is completed.
+	 *
+	 * When setting up an out fence for the job, you should use
+	 * this, since it's available immediately upon
+	 * drm_sched_job_init(), and the fence returned by the driver
+	 * from run_job() won't be created until the dependencies have
+	 * resolved.
+	 */
 	struct dma_fence		finished;
+
 	struct dma_fence_cb		cb;
 	struct dma_fence		*parent;
 	struct drm_gpu_scheduler	*sched;
@@ -88,6 +102,13 @@ struct drm_sched_fence {
 
 struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
 
+/**
+ * drm_sched_job - A job to be run by an entity.
+ *
+ * A job is created by the driver using drm_sched_job_init(), and
+ * should call drm_sched_entity_push_job() once it wants the scheduler
+ * to schedule the job.
+ */
 struct drm_sched_job {
 	struct spsc_node		queue_node;
 	struct drm_gpu_scheduler	*sched;
@@ -99,6 +120,7 @@ struct drm_sched_job {
 	uint64_t			id;
 	atomic_t			karma;
 	enum drm_sched_priority		s_priority;
+	struct drm_sched_entity  *entity;
 };
 
 static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
@@ -112,10 +134,28 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
  * these functions should be implemented in driver side
 */
 struct drm_sched_backend_ops {
+	/* Called when the scheduler is considering scheduling this
+	 * job next, to get another struct dma_fence for this job to
+	 * block on.  Once it returns NULL, run_job() may be called.
+	 */
 	struct dma_fence *(*dependency)(struct drm_sched_job *sched_job,
 					struct drm_sched_entity *s_entity);
+
+	/* Called to execute the job once all of the dependencies have
+	 * been resolved.  This may be called multiple times, if
+	 * timedout_job() has happened and drm_sched_job_recovery()
+	 * decides to try it again.
+	 */
 	struct dma_fence *(*run_job)(struct drm_sched_job *sched_job);
+
+	/* Called when a job has taken too long to execute, to trigger
+	 * GPU recovery.
+	 */
 	void (*timedout_job)(struct drm_sched_job *sched_job);
+
+	/* Called once the job's finished fence has been signaled and
+	 * it's time to clean it up.
+	 */
 	void (*free_job)(struct drm_sched_job *sched_job);
 };
 
@@ -147,7 +187,11 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched);
 int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 			  struct drm_sched_entity *entity,
 			  struct drm_sched_rq *rq,
-			  uint32_t jobs, atomic_t *guilty);
+			  atomic_t *guilty);
+void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
+			   struct drm_sched_entity *entity);
+void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
+			   struct drm_sched_entity *entity);
 void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity);
 void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 70f0c2535b87..bab70ff6e78b 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -349,6 +349,7 @@
 #define INTEL_KBL_GT2_IDS(info)	\
 	INTEL_VGA_DEVICE(0x5916, info), /* ULT GT2 */ \
 	INTEL_VGA_DEVICE(0x5917, info), /* Mobile GT2 */ \
+	INTEL_VGA_DEVICE(0x591C, info), /* ULX GT2 */ \
 	INTEL_VGA_DEVICE(0x5921, info), /* ULT GT2F */ \
 	INTEL_VGA_DEVICE(0x591E, info), /* ULX GT2 */ \
 	INTEL_VGA_DEVICE(0x5912, info), /* DT  GT2 */ \
diff --git a/include/drm/tinydrm/mipi-dbi.h b/include/drm/tinydrm/mipi-dbi.h
index 44e824af2ef6..b8ba58861986 100644
--- a/include/drm/tinydrm/mipi-dbi.h
+++ b/include/drm/tinydrm/mipi-dbi.h
@@ -67,7 +67,9 @@ int mipi_dbi_init(struct device *dev, struct mipi_dbi *mipi,
 		  const struct drm_simple_display_pipe_funcs *pipe_funcs,
 		  struct drm_driver *driver,
 		  const struct drm_display_mode *mode, unsigned int rotation);
-void mipi_dbi_enable_flush(struct mipi_dbi *mipi);
+void mipi_dbi_enable_flush(struct mipi_dbi *mipi,
+			   struct drm_crtc_state *crtc_state,
+			   struct drm_plane_state *plan_state);
 void mipi_dbi_pipe_disable(struct drm_simple_display_pipe *pipe);
 void mipi_dbi_hw_reset(struct mipi_dbi *mipi);
 bool mipi_dbi_display_is_on(struct mipi_dbi *mipi);
diff --git a/include/drm/tinydrm/tinydrm-helpers.h b/include/drm/tinydrm/tinydrm-helpers.h
index 0a4ddbc04c60..5b96f0b12c8c 100644
--- a/include/drm/tinydrm/tinydrm-helpers.h
+++ b/include/drm/tinydrm/tinydrm-helpers.h
@@ -36,6 +36,11 @@ static inline bool tinydrm_machine_little_endian(void)
 bool tinydrm_merge_clips(struct drm_clip_rect *dst,
 			 struct drm_clip_rect *src, unsigned int num_clips,
 			 unsigned int flags, u32 max_width, u32 max_height);
+int tinydrm_fb_dirty(struct drm_framebuffer *fb,
+		     struct drm_file *file_priv,
+		     unsigned int flags, unsigned int color,
+		     struct drm_clip_rect *clips,
+		     unsigned int num_clips);
 void tinydrm_memcpy(void *dst, void *vaddr, struct drm_framebuffer *fb,
 		    struct drm_clip_rect *clip);
 void tinydrm_swab16(u16 *dst, void *vaddr, struct drm_framebuffer *fb,
diff --git a/include/drm/tinydrm/tinydrm.h b/include/drm/tinydrm/tinydrm.h
index 07a9a11fe19d..56e4a916b5e8 100644
--- a/include/drm/tinydrm/tinydrm.h
+++ b/include/drm/tinydrm/tinydrm.h
@@ -26,6 +26,10 @@ struct tinydrm_device {
 	struct drm_simple_display_pipe pipe;
 	struct mutex dirty_lock;
 	const struct drm_framebuffer_funcs *fb_funcs;
+	int (*fb_dirty)(struct drm_framebuffer *framebuffer,
+			struct drm_file *file_priv, unsigned flags,
+			unsigned color, struct drm_clip_rect *clips,
+			unsigned num_clips);
 };
 
 static inline struct tinydrm_device *
@@ -41,7 +45,7 @@ pipe_to_tinydrm(struct drm_simple_display_pipe *pipe)
  * the &drm_driver structure.
  */
 #define TINYDRM_GEM_DRIVER_OPS \
-	.gem_free_object	= tinydrm_gem_cma_free_object, \
+	.gem_free_object_unlocked = tinydrm_gem_cma_free_object, \
 	.gem_print_info		= drm_gem_cma_print_info, \
 	.gem_vm_ops		= &drm_gem_cma_vm_ops, \
 	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd, \
@@ -91,8 +95,6 @@ void tinydrm_shutdown(struct tinydrm_device *tdev);
 
 void tinydrm_display_pipe_update(struct drm_simple_display_pipe *pipe,
 				 struct drm_plane_state *old_state);
-int tinydrm_display_pipe_prepare_fb(struct drm_simple_display_pipe *pipe,
-				    struct drm_plane_state *plane_state);
 int
 tinydrm_display_pipe_init(struct tinydrm_device *tdev,
 			  const struct drm_simple_display_pipe_funcs *funcs,
diff --git a/include/dt-bindings/clock/stm32mp1-clks.h b/include/dt-bindings/clock/stm32mp1-clks.h
index 86e3ec662ef4..90ec780bfc68 100644
--- a/include/dt-bindings/clock/stm32mp1-clks.h
+++ b/include/dt-bindings/clock/stm32mp1-clks.h
@@ -76,7 +76,7 @@
 #define I2C6		63
 #define USART1		64
 #define RTCAPB		65
-#define TZC		66
+#define TZC1		66
 #define TZPC		67
 #define IWDG1		68
 #define BSEC		69
@@ -123,6 +123,7 @@
 #define CRC1		110
 #define USBH		111
 #define ETHSTP		112
+#define TZC2		113
 
 /* Kernel clocks */
 #define SDMMC1_K	118
@@ -228,7 +229,6 @@
 #define CK_MCO2		212
 
 /* TRACE & DEBUG clocks */
-#define DBG		213
 #define CK_DBG		214
 #define CK_TRACE	215
 
diff --git a/include/dt-bindings/dma/jz4780-dma.h b/include/dt-bindings/dma/jz4780-dma.h
new file mode 100644
index 000000000000..df017fdfb44e
--- /dev/null
+++ b/include/dt-bindings/dma/jz4780-dma.h
@@ -0,0 +1,49 @@
+#ifndef __DT_BINDINGS_DMA_JZ4780_DMA_H__
+#define __DT_BINDINGS_DMA_JZ4780_DMA_H__
+
+/*
+ * Request type numbers for the JZ4780 DMA controller (written to the DRTn
+ * register for the channel).
+ */
+#define JZ4780_DMA_I2S1_TX	0x4
+#define JZ4780_DMA_I2S1_RX	0x5
+#define JZ4780_DMA_I2S0_TX	0x6
+#define JZ4780_DMA_I2S0_RX	0x7
+#define JZ4780_DMA_AUTO		0x8
+#define JZ4780_DMA_SADC_RX	0x9
+#define JZ4780_DMA_UART4_TX	0xc
+#define JZ4780_DMA_UART4_RX	0xd
+#define JZ4780_DMA_UART3_TX	0xe
+#define JZ4780_DMA_UART3_RX	0xf
+#define JZ4780_DMA_UART2_TX	0x10
+#define JZ4780_DMA_UART2_RX	0x11
+#define JZ4780_DMA_UART1_TX	0x12
+#define JZ4780_DMA_UART1_RX	0x13
+#define JZ4780_DMA_UART0_TX	0x14
+#define JZ4780_DMA_UART0_RX	0x15
+#define JZ4780_DMA_SSI0_TX	0x16
+#define JZ4780_DMA_SSI0_RX	0x17
+#define JZ4780_DMA_SSI1_TX	0x18
+#define JZ4780_DMA_SSI1_RX	0x19
+#define JZ4780_DMA_MSC0_TX	0x1a
+#define JZ4780_DMA_MSC0_RX	0x1b
+#define JZ4780_DMA_MSC1_TX	0x1c
+#define JZ4780_DMA_MSC1_RX	0x1d
+#define JZ4780_DMA_MSC2_TX	0x1e
+#define JZ4780_DMA_MSC2_RX	0x1f
+#define JZ4780_DMA_PCM0_TX	0x20
+#define JZ4780_DMA_PCM0_RX	0x21
+#define JZ4780_DMA_SMB0_TX	0x24
+#define JZ4780_DMA_SMB0_RX	0x25
+#define JZ4780_DMA_SMB1_TX	0x26
+#define JZ4780_DMA_SMB1_RX	0x27
+#define JZ4780_DMA_SMB2_TX	0x28
+#define JZ4780_DMA_SMB2_RX	0x29
+#define JZ4780_DMA_SMB3_TX	0x2a
+#define JZ4780_DMA_SMB3_RX	0x2b
+#define JZ4780_DMA_SMB4_TX	0x2c
+#define JZ4780_DMA_SMB4_RX	0x2d
+#define JZ4780_DMA_DES_TX	0x2e
+#define JZ4780_DMA_DES_RX	0x2f
+
+#endif /* __DT_BINDINGS_DMA_JZ4780_DMA_H__ */
diff --git a/include/dt-bindings/phy/phy-qcom-qusb2.h b/include/dt-bindings/phy/phy-qcom-qusb2.h
new file mode 100644
index 000000000000..5c5e4d800cac
--- /dev/null
+++ b/include/dt-bindings/phy/phy-qcom-qusb2.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_QCOM_PHY_QUSB2_H_
+#define _DT_BINDINGS_QCOM_PHY_QUSB2_H_
+
+/* PHY HSTX TRIM bit values (24mA to 15mA) */
+#define QUSB2_V2_HSTX_TRIM_24_0_MA		0x0
+#define QUSB2_V2_HSTX_TRIM_23_4_MA		0x1
+#define QUSB2_V2_HSTX_TRIM_22_8_MA		0x2
+#define QUSB2_V2_HSTX_TRIM_22_2_MA		0x3
+#define QUSB2_V2_HSTX_TRIM_21_6_MA		0x4
+#define QUSB2_V2_HSTX_TRIM_21_0_MA		0x5
+#define QUSB2_V2_HSTX_TRIM_20_4_MA		0x6
+#define QUSB2_V2_HSTX_TRIM_19_8_MA		0x7
+#define QUSB2_V2_HSTX_TRIM_19_2_MA		0x8
+#define QUSB2_V2_HSTX_TRIM_18_6_MA		0x9
+#define QUSB2_V2_HSTX_TRIM_18_0_MA		0xa
+#define QUSB2_V2_HSTX_TRIM_17_4_MA		0xb
+#define QUSB2_V2_HSTX_TRIM_16_8_MA		0xc
+#define QUSB2_V2_HSTX_TRIM_16_2_MA		0xd
+#define QUSB2_V2_HSTX_TRIM_15_6_MA		0xe
+#define QUSB2_V2_HSTX_TRIM_15_0_MA		0xf
+
+/* PHY PREEMPHASIS bit values */
+#define QUSB2_V2_PREEMPHASIS_NONE		0
+#define QUSB2_V2_PREEMPHASIS_5_PERCENT		1
+#define QUSB2_V2_PREEMPHASIS_10_PERCENT		2
+#define QUSB2_V2_PREEMPHASIS_15_PERCENT		3
+
+/* PHY PREEMPHASIS-WIDTH bit values */
+#define QUSB2_V2_PREEMPHASIS_WIDTH_FULL_BIT	0
+#define QUSB2_V2_PREEMPHASIS_WIDTH_HALF_BIT	1
+
+#endif
diff --git a/include/dt-bindings/soc/qcom,apr.h b/include/dt-bindings/soc/qcom,apr.h
new file mode 100644
index 000000000000..006362400c0f
--- /dev/null
+++ b/include/dt-bindings/soc/qcom,apr.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __DT_BINDINGS_QCOM_APR_H
+#define __DT_BINDINGS_QCOM_APR_H
+
+/* Domain IDs */
+#define APR_DOMAIN_SIM		0x1
+#define APR_DOMAIN_PC		0x2
+#define APR_DOMAIN_MODEM	0x3
+#define APR_DOMAIN_ADSP		0x4
+#define APR_DOMAIN_APPS		0x5
+#define APR_DOMAIN_MAX		0x6
+
+/* ADSP service IDs */
+#define APR_SVC_ADSP_CORE	0x3
+#define APR_SVC_AFE		0x4
+#define APR_SVC_VSM		0x5
+#define APR_SVC_VPM		0x6
+#define APR_SVC_ASM		0x7
+#define APR_SVC_ADM		0x8
+#define APR_SVC_ADSP_MVM	0x09
+#define APR_SVC_ADSP_CVS	0x0A
+#define APR_SVC_ADSP_CVP	0x0B
+#define APR_SVC_USM		0x0C
+#define APR_SVC_LSM		0x0D
+#define APR_SVC_VIDC		0x16
+#define APR_SVC_MAX		0x17
+
+#endif /* __DT_BINDINGS_QCOM_APR_H */
diff --git a/include/dt-bindings/sound/fsl-imx-audmux.h b/include/dt-bindings/sound/fsl-imx-audmux.h
index 751fe1416f95..15f138bebe16 100644
--- a/include/dt-bindings/sound/fsl-imx-audmux.h
+++ b/include/dt-bindings/sound/fsl-imx-audmux.h
@@ -25,6 +25,13 @@
 #define MX51_AUDMUX_PORT6		5
 #define MX51_AUDMUX_PORT7		6
 
+/*
+ * TFCSEL/RFCSEL (i.MX27) or TFSEL/TCSEL/RFSEL/RCSEL (i.MX31/51/53/6Q)
+ * can be sourced from Rx/Tx.
+ */
+#define IMX_AUDMUX_RXFS			0x8
+#define IMX_AUDMUX_RXCLK		0x8
+
 /* Register definitions for the i.MX21/27 Digital Audio Multiplexer */
 #define IMX_AUDMUX_V1_PCR_INMMASK(x)	((x) & 0xff)
 #define IMX_AUDMUX_V1_PCR_INMEN		(1 << 8)
diff --git a/include/dt-bindings/sound/qcom,q6afe.h b/include/dt-bindings/sound/qcom,q6afe.h
new file mode 100644
index 000000000000..e2d3892240b8
--- /dev/null
+++ b/include/dt-bindings/sound/qcom,q6afe.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __DT_BINDINGS_Q6_AFE_H__
+#define __DT_BINDINGS_Q6_AFE_H__
+
+/* Audio Front End (AFE) virtual ports IDs */
+#define HDMI_RX		1
+#define SLIMBUS_0_RX    2
+#define SLIMBUS_0_TX    3
+#define SLIMBUS_1_RX    4
+#define SLIMBUS_1_TX    5
+#define SLIMBUS_2_RX    6
+#define SLIMBUS_2_TX    7
+#define SLIMBUS_3_RX    8
+#define SLIMBUS_3_TX    9
+#define SLIMBUS_4_RX    10
+#define SLIMBUS_4_TX    11
+#define SLIMBUS_5_RX    12
+#define SLIMBUS_5_TX    13
+#define SLIMBUS_6_RX    14
+#define SLIMBUS_6_TX    15
+#define PRIMARY_MI2S_RX		16
+#define PRIMARY_MI2S_TX		17
+#define SECONDARY_MI2S_RX	18
+#define SECONDARY_MI2S_TX	19
+#define TERTIARY_MI2S_RX	20
+#define TERTIARY_MI2S_TX	21
+#define QUATERNARY_MI2S_RX	22
+#define QUATERNARY_MI2S_TX	23
+#define PRIMARY_TDM_RX_0	24
+#define PRIMARY_TDM_TX_0	25
+#define PRIMARY_TDM_RX_1	26
+#define PRIMARY_TDM_TX_1	27
+#define PRIMARY_TDM_RX_2	28
+#define PRIMARY_TDM_TX_2	29
+#define PRIMARY_TDM_RX_3	30
+#define PRIMARY_TDM_TX_3	31
+#define PRIMARY_TDM_RX_4	32
+#define PRIMARY_TDM_TX_4	33
+#define PRIMARY_TDM_RX_5	34
+#define PRIMARY_TDM_TX_5	35
+#define PRIMARY_TDM_RX_6	36
+#define PRIMARY_TDM_TX_6	37
+#define PRIMARY_TDM_RX_7	38
+#define PRIMARY_TDM_TX_7	39
+#define SECONDARY_TDM_RX_0	40
+#define SECONDARY_TDM_TX_0	41
+#define SECONDARY_TDM_RX_1	42
+#define SECONDARY_TDM_TX_1	43
+#define SECONDARY_TDM_RX_2	44
+#define SECONDARY_TDM_TX_2	45
+#define SECONDARY_TDM_RX_3	46
+#define SECONDARY_TDM_TX_3	47
+#define SECONDARY_TDM_RX_4	48
+#define SECONDARY_TDM_TX_4	49
+#define SECONDARY_TDM_RX_5	50
+#define SECONDARY_TDM_TX_5	51
+#define SECONDARY_TDM_RX_6	52
+#define SECONDARY_TDM_TX_6	53
+#define SECONDARY_TDM_RX_7	54
+#define SECONDARY_TDM_TX_7	55
+#define TERTIARY_TDM_RX_0	56
+#define TERTIARY_TDM_TX_0	57
+#define TERTIARY_TDM_RX_1	58
+#define TERTIARY_TDM_TX_1	59
+#define TERTIARY_TDM_RX_2	60
+#define TERTIARY_TDM_TX_2	61
+#define TERTIARY_TDM_RX_3	62
+#define TERTIARY_TDM_TX_3	63
+#define TERTIARY_TDM_RX_4	64
+#define TERTIARY_TDM_TX_4	65
+#define TERTIARY_TDM_RX_5	66
+#define TERTIARY_TDM_TX_5	67
+#define TERTIARY_TDM_RX_6	68
+#define TERTIARY_TDM_TX_6	69
+#define TERTIARY_TDM_RX_7	70
+#define TERTIARY_TDM_TX_7	71
+#define QUATERNARY_TDM_RX_0	72
+#define QUATERNARY_TDM_TX_0	73
+#define QUATERNARY_TDM_RX_1	74
+#define QUATERNARY_TDM_TX_1	75
+#define QUATERNARY_TDM_RX_2	76
+#define QUATERNARY_TDM_TX_2	77
+#define QUATERNARY_TDM_RX_3	78
+#define QUATERNARY_TDM_TX_3	79
+#define QUATERNARY_TDM_RX_4	80
+#define QUATERNARY_TDM_TX_4	81
+#define QUATERNARY_TDM_RX_5	82
+#define QUATERNARY_TDM_TX_5	83
+#define QUATERNARY_TDM_RX_6	84
+#define QUATERNARY_TDM_TX_6	85
+#define QUATERNARY_TDM_RX_7	86
+#define QUATERNARY_TDM_TX_7	87
+#define QUINARY_TDM_RX_0	88
+#define QUINARY_TDM_TX_0	89
+#define QUINARY_TDM_RX_1	90
+#define QUINARY_TDM_TX_1	91
+#define QUINARY_TDM_RX_2	92
+#define QUINARY_TDM_TX_2	93
+#define QUINARY_TDM_RX_3	94
+#define QUINARY_TDM_TX_3	95
+#define QUINARY_TDM_RX_4	96
+#define QUINARY_TDM_TX_4	97
+#define QUINARY_TDM_RX_5	98
+#define QUINARY_TDM_TX_5	99
+#define QUINARY_TDM_RX_6	100
+#define QUINARY_TDM_TX_6	101
+#define QUINARY_TDM_RX_7	102
+#define QUINARY_TDM_TX_7	103
+
+#endif /* __DT_BINDINGS_Q6_AFE_H__ */
+
diff --git a/include/dt-bindings/sound/qcom,q6asm.h b/include/dt-bindings/sound/qcom,q6asm.h
new file mode 100644
index 000000000000..1eb77d87c2e8
--- /dev/null
+++ b/include/dt-bindings/sound/qcom,q6asm.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __DT_BINDINGS_Q6_ASM_H__
+#define __DT_BINDINGS_Q6_ASM_H__
+
+#define	MSM_FRONTEND_DAI_MULTIMEDIA1	0
+#define	MSM_FRONTEND_DAI_MULTIMEDIA2	1
+#define	MSM_FRONTEND_DAI_MULTIMEDIA3	2
+#define	MSM_FRONTEND_DAI_MULTIMEDIA4	3
+#define	MSM_FRONTEND_DAI_MULTIMEDIA5	4
+#define	MSM_FRONTEND_DAI_MULTIMEDIA6	5
+#define	MSM_FRONTEND_DAI_MULTIMEDIA7	6
+#define	MSM_FRONTEND_DAI_MULTIMEDIA8	7
+#define	MSM_FRONTEND_DAI_MULTIMEDIA9	8
+#define	MSM_FRONTEND_DAI_MULTIMEDIA10	9
+#define	MSM_FRONTEND_DAI_MULTIMEDIA11	10
+#define	MSM_FRONTEND_DAI_MULTIMEDIA12	11
+#define	MSM_FRONTEND_DAI_MULTIMEDIA13	12
+#define	MSM_FRONTEND_DAI_MULTIMEDIA14	13
+#define	MSM_FRONTEND_DAI_MULTIMEDIA15	14
+#define	MSM_FRONTEND_DAI_MULTIMEDIA16	15
+
+#endif /* __DT_BINDINGS_Q6_ASM_H__ */
diff --git a/include/dt-bindings/sound/rt5640.h b/include/dt-bindings/sound/rt5640.h
new file mode 100644
index 000000000000..154c9b4414f2
--- /dev/null
+++ b/include/dt-bindings/sound/rt5640.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __DT_RT5640_H
+#define __DT_RT5640_H
+
+#define RT5640_DMIC1_DATA_PIN_NONE	0
+#define RT5640_DMIC1_DATA_PIN_IN1P	1
+#define RT5640_DMIC1_DATA_PIN_GPIO3	2
+
+#define RT5640_DMIC2_DATA_PIN_NONE	0
+#define RT5640_DMIC2_DATA_PIN_IN1N	1
+#define RT5640_DMIC2_DATA_PIN_GPIO4	2
+
+#define RT5640_JD_SRC_GPIO1		1
+#define RT5640_JD_SRC_JD1_IN4P		2
+#define RT5640_JD_SRC_JD2_IN4N		3
+#define RT5640_JD_SRC_GPIO2		4
+#define RT5640_JD_SRC_GPIO3		5
+#define RT5640_JD_SRC_GPIO4		6
+
+#define RT5640_OVCD_SF_0P5		0
+#define RT5640_OVCD_SF_0P75		1
+#define RT5640_OVCD_SF_1P0		2
+#define RT5640_OVCD_SF_1P5		3
+
+#endif /* __DT_RT5640_H */
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index e518e4e3dfb5..4b1548129fa2 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -37,10 +37,15 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
 	 * Our PSCI implementation stays the same across versions from
 	 * v0.2 onward, only adding the few mandatory functions (such
 	 * as FEATURES with 1.0) that are required by newer
-	 * revisions. It is thus safe to return the latest.
+	 * revisions. It is thus safe to return the latest, unless
+	 * userspace has instructed us otherwise.
 	 */
-	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) {
+		if (vcpu->kvm->arch.psci_version)
+			return vcpu->kvm->arch.psci_version;
+
 		return KVM_ARM_PSCI_LATEST;
+	}
 
 	return KVM_ARM_PSCI_0_1;
 }
@@ -48,4 +53,11 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
 
 int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
 
+struct kvm_one_reg;
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+
 #endif /* __KVM_ARM_PSCI_H__ */
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 24f03941ada8..e7efe12a81bd 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -131,6 +131,7 @@ struct vgic_irq {
 		u32 mpidr;			/* GICv3 target VCPU */
 	};
 	u8 source;			/* GICv2 SGIs only */
+	u8 active_source;		/* GICv2 SGIs only */
 	u8 priority;
 	enum vgic_irq_config config;	/* Level or edge */
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 15bfb15c2fa5..fd0ea6af9e36 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -578,6 +578,7 @@ int acpi_match_platform_list(const struct acpi_platform_list *plat);
 
 extern void acpi_early_init(void);
 extern void acpi_subsystem_init(void);
+extern void arch_post_acpi_subsys_init(void);
 
 extern int acpi_nvs_register(__u64 start, __u64 size);
 
@@ -899,7 +900,7 @@ static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; }
 static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; }
 static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
 {
-	return -ENODEV;
+	return 0;
 }
 #endif
 
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 9d8aabecfe2d..b83e68dd006f 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -8,8 +8,6 @@ struct kioctx;
 struct kiocb;
 struct mm_struct;
 
-#define KIOCB_KEY		0
-
 typedef int (kiocb_cancel_fn)(struct kiocb *);
 
 /* prototypes */
diff --git a/include/linux/atalk.h b/include/linux/atalk.h
index 40373920ea58..23f805562f4e 100644
--- a/include/linux/atalk.h
+++ b/include/linux/atalk.h
@@ -145,7 +145,12 @@ extern rwlock_t atalk_interfaces_lock;
 
 extern struct atalk_route atrtr_default;
 
-extern const struct file_operations atalk_seq_arp_fops;
+struct aarp_iter_state {
+	int bucket;
+	struct aarp_entry **table;
+};
+
+extern const struct seq_operations aarp_seq_ops;
 
 extern int sysctl_aarp_expiry_time;
 extern int sysctl_aarp_tick_time;
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 8b276fd9a127..01ce3997cb42 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -654,6 +654,7 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 }
 #endif
 
+#define atomic_cond_read_relaxed(v, c)	smp_cond_load_relaxed(&(v)->counter, (c))
 #define atomic_cond_read_acquire(v, c)	smp_cond_load_acquire(&(v)->counter, (c))
 
 #ifdef CONFIG_GENERIC_ATOMIC64
@@ -1075,6 +1076,7 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v
 }
 #endif
 
+#define atomic64_cond_read_relaxed(v, c)	smp_cond_load_relaxed(&(v)->counter, (c))
 #define atomic64_cond_read_acquire(v, c)	smp_cond_load_acquire(&(v)->counter, (c))
 
 #include <asm-generic/atomic-long.h>
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index bfe86b54f6c1..0bd432a4d7bd 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -223,6 +223,11 @@ static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 	set_wb_congested(bdi->wb.congested, sync);
 }
 
+struct wb_lock_cookie {
+	bool locked;
+	unsigned long flags;
+};
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 /**
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f6be4b0b6c18..72ca0f3d39f3 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -347,7 +347,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
 /**
  * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
  * @inode: target inode
- * @lockedp: temp bool output param, to be passed to the end function
+ * @cookie: output param, to be passed to the end function
  *
  * The caller wants to access the wb associated with @inode but isn't
  * holding inode->i_lock, the i_pages lock or wb->list_lock.  This
@@ -355,12 +355,12 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
  * association doesn't change until the transaction is finished with
  * unlocked_inode_to_wb_end().
  *
- * The caller must call unlocked_inode_to_wb_end() with *@lockdep
- * afterwards and can't sleep during transaction.  IRQ may or may not be
- * disabled on return.
+ * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and
+ * can't sleep during the transaction.  IRQs may or may not be disabled on
+ * return.
  */
 static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
 {
 	rcu_read_lock();
 
@@ -368,10 +368,10 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
 	 * Paired with store_release in inode_switch_wb_work_fn() and
 	 * ensures that we see the new wb if we see cleared I_WB_SWITCH.
 	 */
-	*lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+	cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
 
-	if (unlikely(*lockedp))
-		xa_lock_irq(&inode->i_mapping->i_pages);
+	if (unlikely(cookie->locked))
+		xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags);
 
 	/*
 	 * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages
@@ -383,12 +383,13 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
 /**
  * unlocked_inode_to_wb_end - end inode wb access transaction
  * @inode: target inode
- * @locked: *@lockedp from unlocked_inode_to_wb_begin()
+ * @cookie: @cookie from unlocked_inode_to_wb_begin()
  */
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+					    struct wb_lock_cookie *cookie)
 {
-	if (unlikely(locked))
-		xa_unlock_irq(&inode->i_mapping->i_pages);
+	if (unlikely(cookie->locked))
+		xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags);
 
 	rcu_read_unlock();
 }
@@ -435,12 +436,13 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
 }
 
 static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
 {
 	return inode_to_wb(inode);
 }
 
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+					    struct wb_lock_cookie *cookie)
 {
 }
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ce547a25e8ae..397a38aca182 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -67,8 +67,12 @@
 
 #define bio_multiple_segments(bio)				\
 	((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len)
-#define bio_sectors(bio)	((bio)->bi_iter.bi_size >> 9)
-#define bio_end_sector(bio)	((bio)->bi_iter.bi_sector + bio_sectors((bio)))
+
+#define bvec_iter_sectors(iter)	((iter).bi_size >> 9)
+#define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter)))
+
+#define bio_sectors(bio)	bvec_iter_sectors((bio)->bi_iter)
+#define bio_end_sector(bio)	bvec_iter_end_sector((bio)->bi_iter)
 
 /*
  * Return the data direction, READ or WRITE.
@@ -123,6 +127,11 @@ static inline void *bio_data(struct bio *bio)
 	return NULL;
 }
 
+static inline bool bio_full(struct bio *bio)
+{
+	return bio->bi_vcnt >= bio->bi_max_vecs;
+}
+
 /*
  * will die
  */
@@ -406,13 +415,13 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors,
 	return bio_split(bio, sectors, gfp, bs);
 }
 
-extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags);
 enum {
 	BIOSET_NEED_BVECS = BIT(0),
 	BIOSET_NEED_RESCUER = BIT(1),
 };
-extern void bioset_free(struct bio_set *);
-extern mempool_t *biovec_create_pool(int pool_entries);
+extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags);
+extern void bioset_exit(struct bio_set *);
+extern int biovec_init_pool(mempool_t *pool, int pool_entries);
 
 extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *);
 extern void bio_put(struct bio *);
@@ -421,11 +430,11 @@ extern void __bio_clone_fast(struct bio *, struct bio *);
 extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
 extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
-extern struct bio_set *fs_bio_set;
+extern struct bio_set fs_bio_set;
 
 static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 {
-	return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
+	return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
 }
 
 static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
@@ -470,6 +479,10 @@ void bio_chain(struct bio *, struct bio *);
 extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
+bool __bio_try_merge_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int off);
+void __bio_add_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int off);
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
@@ -499,7 +512,10 @@ static inline void bio_flush_dcache_pages(struct bio *bi)
 }
 #endif
 
+extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+			       struct bio *src, struct bvec_iter *src_iter);
 extern void bio_copy_data(struct bio *dst, struct bio *src);
+extern void bio_list_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
 
 extern struct bio *bio_copy_user_iov(struct request_queue *,
@@ -507,7 +523,13 @@ extern struct bio *bio_copy_user_iov(struct request_queue *,
 				     struct iov_iter *,
 				     gfp_t);
 extern int bio_uncopy_user(struct bio *);
-void zero_fill_bio(struct bio *bio);
+void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter);
+
+static inline void zero_fill_bio(struct bio *bio)
+{
+	zero_fill_bio_iter(bio, bio->bi_iter);
+}
+
 extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
 extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
@@ -722,11 +744,11 @@ struct bio_set {
 	struct kmem_cache *bio_slab;
 	unsigned int front_pad;
 
-	mempool_t *bio_pool;
-	mempool_t *bvec_pool;
+	mempool_t bio_pool;
+	mempool_t bvec_pool;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
-	mempool_t *bio_integrity_pool;
-	mempool_t *bvec_integrity_pool;
+	mempool_t bio_integrity_pool;
+	mempool_t bvec_integrity_pool;
 #endif
 
 	/*
@@ -745,6 +767,11 @@ struct biovec_slab {
 	struct kmem_cache *slab;
 };
 
+static inline bool bioset_initialized(struct bio_set *bs)
+{
+	return bs->bio_slab != NULL;
+}
+
 /*
  * a small number of entries is fine, not going to be performance critical.
  * basically we just need to survive
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index e3986f4b3461..fb355173f3c7 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -9,6 +9,9 @@
 struct blk_mq_tags;
 struct blk_flush_queue;
 
+/**
+ * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device
+ */
 struct blk_mq_hw_ctx {
 	struct {
 		spinlock_t		lock;
@@ -256,7 +259,8 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 void blk_mq_complete_request(struct request *rq);
-
+bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
+			   struct bio *bio);
 bool blk_mq_queue_stopped(struct request_queue *q);
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 17b18b91ebac..3c4f390aea4b 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -8,6 +8,7 @@
 
 #include <linux/types.h>
 #include <linux/bvec.h>
+#include <linux/ktime.h>
 
 struct bio_set;
 struct bio;
@@ -90,10 +91,52 @@ static inline bool blk_path_error(blk_status_t error)
 	return true;
 }
 
-struct blk_issue_stat {
-	u64 stat;
+/*
+ * From most significant bit:
+ * 1 bit: reserved for other usage, see below
+ * 12 bits: original size of bio
+ * 51 bits: issue time of bio
+ */
+#define BIO_ISSUE_RES_BITS      1
+#define BIO_ISSUE_SIZE_BITS     12
+#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
+#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
+#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
+#define BIO_ISSUE_SIZE_MASK     \
+	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
+#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
+
+/* Reserved bit for blk-throtl */
+#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
+
+struct bio_issue {
+	u64 value;
 };
 
+static inline u64 __bio_issue_time(u64 time)
+{
+	return time & BIO_ISSUE_TIME_MASK;
+}
+
+static inline u64 bio_issue_time(struct bio_issue *issue)
+{
+	return __bio_issue_time(issue->value);
+}
+
+static inline sector_t bio_issue_size(struct bio_issue *issue)
+{
+	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
+}
+
+static inline void bio_issue_init(struct bio_issue *issue,
+				       sector_t size)
+{
+	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
+	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
+			(ktime_get_ns() & BIO_ISSUE_TIME_MASK) |
+			((u64)size << BIO_ISSUE_SIZE_SHIFT));
+}
+
 /*
  * main unit of I/O for the block layer and lower layers (ie drivers and
  * stacking drivers)
@@ -138,7 +181,7 @@ struct bio {
 	struct cgroup_subsys_state *bi_css;
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	void			*bi_cg_private;
-	struct blk_issue_stat	bi_issue_stat;
+	struct bio_issue	bi_issue;
 #endif
 #endif
 	union {
@@ -186,6 +229,8 @@ struct bio {
 				 * throttling rules. Don't do it again. */
 #define BIO_TRACE_COMPLETION 10	/* bio_endio() should trace the final completion
 				 * of this bio. */
+#define BIO_QUEUE_ENTERED 11	/* can use blk_queue_enter_live() */
+
 /* See BVEC_POOL_OFFSET below before adding new flags */
 
 /*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9af3e0f430bc..bca3a92eb55f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -125,16 +125,23 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
 /* The per-zone write lock is held for this request */
 #define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
-/* timeout is expired */
-#define RQF_MQ_TIMEOUT_EXPIRED	((__force req_flags_t)(1 << 20))
 /* already slept for hybrid poll */
-#define RQF_MQ_POLL_SLEPT	((__force req_flags_t)(1 << 21))
+#define RQF_MQ_POLL_SLEPT	((__force req_flags_t)(1 << 20))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
 	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
 
 /*
+ * Request state for blk-mq.
+ */
+enum mq_rq_state {
+	MQ_RQ_IDLE		= 0,
+	MQ_RQ_IN_FLIGHT		= 1,
+	MQ_RQ_COMPLETE		= 2,
+};
+
+/*
  * Try to put the fields that are referenced together in the same cacheline.
  *
  * If you modify this structure, make sure to update blk_rq_init() and
@@ -205,9 +212,20 @@ struct request {
 
 	struct gendisk *rq_disk;
 	struct hd_struct *part;
-	unsigned long start_time;
-	struct blk_issue_stat issue_stat;
-	/* Number of scatter-gather DMA addr+len pairs after
+	/* Time that I/O was submitted to the kernel. */
+	u64 start_time_ns;
+	/* Time that I/O was submitted to the device. */
+	u64 io_start_time_ns;
+
+#ifdef CONFIG_BLK_WBT
+	unsigned short wbt_flags;
+#endif
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	unsigned short throtl_size;
+#endif
+
+	/*
+	 * Number of scatter-gather DMA addr+len pairs after
 	 * physical address coalescing is performed.
 	 */
 	unsigned short nr_phys_segments;
@@ -219,32 +237,14 @@ struct request {
 	unsigned short write_hint;
 	unsigned short ioprio;
 
-	unsigned int timeout;
-
 	void *special;		/* opaque pointer available for LLD use */
 
 	unsigned int extra_len;	/* length of alignment and padding */
 
-	/*
-	 * On blk-mq, the lower bits of ->gstate (generation number and
-	 * state) carry the MQ_RQ_* state value and the upper bits the
-	 * generation number which is monotonically incremented and used to
-	 * distinguish the reuse instances.
-	 *
-	 * ->gstate_seq allows updates to ->gstate and other fields
-	 * (currently ->deadline) during request start to be read
-	 * atomically from the timeout path, so that it can operate on a
-	 * coherent set of information.
-	 */
-	seqcount_t gstate_seq;
-	u64 gstate;
+	enum mq_rq_state state;
+	refcount_t ref;
 
-	/*
-	 * ->aborted_gstate is used by the timeout to claim a specific
-	 * recycle instance of this request.  See blk_mq_timeout_work().
-	 */
-	struct u64_stats_sync aborted_gstate_sync;
-	u64 aborted_gstate;
+	unsigned int timeout;
 
 	/* access through blk_rq_set_deadline, blk_rq_deadline */
 	unsigned long __deadline;
@@ -267,8 +267,6 @@ struct request {
 
 #ifdef CONFIG_BLK_CGROUP
 	struct request_list *rl;		/* rl this rq is alloced from */
-	unsigned long long start_time_ns;
-	unsigned long long io_start_time_ns;    /* when passed to hardware */
 #endif
 };
 
@@ -328,9 +326,8 @@ typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t);
 typedef void (exit_rq_fn)(struct request_queue *, struct request *);
 
 enum blk_eh_timer_return {
-	BLK_EH_NOT_HANDLED,
-	BLK_EH_HANDLED,
-	BLK_EH_RESET_TIMER,
+	BLK_EH_DONE,		/* drivers has completed the command */
+	BLK_EH_RESET_TIMER,	/* reset timer and try again */
 };
 
 typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *);
@@ -605,6 +602,11 @@ struct request_queue {
 	 * initialized by the low level device driver (e.g. scsi/sd.c).
 	 * Stacking drivers (device mappers) may or may not initialize
 	 * these fields.
+	 *
+	 * Reads of this information must be protected with blk_queue_enter() /
+	 * blk_queue_exit(). Modifying this information is only allowed while
+	 * no requests are being processed. See also blk_mq_freeze_queue() and
+	 * blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
 	unsigned long		*seq_zones_bitmap;
@@ -650,7 +652,7 @@ struct request_queue {
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
-	struct bio_set		*bio_split;
+	struct bio_set		bio_split;
 
 #ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*debugfs_dir;
@@ -737,6 +739,7 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q);
 #define blk_queue_quiesced(q)	test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
 #define blk_queue_preempt_only(q)				\
 	test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags)
+#define blk_queue_fua(q)	test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
 
 extern int blk_set_preempt_only(struct request_queue *q);
 extern void blk_clear_preempt_only(struct request_queue *q);
@@ -961,11 +964,8 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_init_request_from_bio(struct request *req, struct bio *bio);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
-extern struct request *blk_get_request_flags(struct request_queue *,
-					     unsigned int op,
-					     blk_mq_req_flags_t flags);
 extern struct request *blk_get_request(struct request_queue *, unsigned int op,
-				       gfp_t gfp_mask);
+				       blk_mq_req_flags_t flags);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
@@ -1782,48 +1782,6 @@ int kblockd_schedule_work(struct work_struct *work);
 int kblockd_schedule_work_on(int cpu, struct work_struct *work);
 int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 
-#ifdef CONFIG_BLK_CGROUP
-/*
- * This should not be using sched_clock(). A real patch is in progress
- * to fix this up, until that is in place we need to disable preemption
- * around sched_clock() in this function and set_io_start_time_ns().
- */
-static inline void set_start_time_ns(struct request *req)
-{
-	preempt_disable();
-	req->start_time_ns = sched_clock();
-	preempt_enable();
-}
-
-static inline void set_io_start_time_ns(struct request *req)
-{
-	preempt_disable();
-	req->io_start_time_ns = sched_clock();
-	preempt_enable();
-}
-
-static inline uint64_t rq_start_time_ns(struct request *req)
-{
-        return req->start_time_ns;
-}
-
-static inline uint64_t rq_io_start_time_ns(struct request *req)
-{
-        return req->io_start_time_ns;
-}
-#else
-static inline void set_start_time_ns(struct request *req) {}
-static inline void set_io_start_time_ns(struct request *req) {}
-static inline uint64_t rq_start_time_ns(struct request *req)
-{
-	return 0;
-}
-static inline uint64_t rq_io_start_time_ns(struct request *req)
-{
-	return 0;
-}
-#endif
-
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 95a7abd0ee92..469b20e1dd7e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -31,6 +31,7 @@ struct bpf_map_ops {
 	void (*map_release)(struct bpf_map *map, struct file *map_file);
 	void (*map_free)(struct bpf_map *map);
 	int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
+	void (*map_release_uref)(struct bpf_map *map);
 
 	/* funcs callable from userspace and from eBPF programs */
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
@@ -339,8 +340,8 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
 				struct bpf_prog *old_prog);
 int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
-			     __u32 __user *prog_ids, u32 request_cnt,
-			     __u32 __user *prog_cnt);
+			     u32 *prog_ids, u32 request_cnt,
+			     u32 *prog_cnt);
 int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,
@@ -351,6 +352,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 		struct bpf_prog **_prog, *__prog;	\
 		struct bpf_prog_array *_array;		\
 		u32 _ret = 1;				\
+		preempt_disable();			\
 		rcu_read_lock();			\
 		_array = rcu_dereference(array);	\
 		if (unlikely(check_non_null && !_array))\
@@ -362,6 +364,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 		}					\
 _out:							\
 		rcu_read_unlock();			\
+		preempt_enable_no_resched();		\
 		_ret;					\
 	 })
 
@@ -434,7 +437,6 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
 int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 				 void *key, void *value, u64 map_flags);
 int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
-void bpf_fd_array_map_clear(struct bpf_map *map);
 int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 				void *key, void *value, u64 map_flags);
 int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7e61c395fddf..df36b1b08af0 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -142,10 +142,11 @@ struct bpf_verifier_state_list {
 struct bpf_insn_aux_data {
 	union {
 		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
-		struct bpf_map *map_ptr;	/* pointer for call insn into lookup_elem */
+		unsigned long map_state;	/* pointer/poison value for maps */
 		s32 call_imm;			/* saved imm field of call insn */
 	};
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
+	int sanitize_stack_off; /* stack slot to be cleared */
 	bool seen; /* this insn was processed by the verifier */
 };
 
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index d3339dd48b1a..b324e01ccf2d 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -25,6 +25,7 @@
 #define PHY_ID_BCM54612E		0x03625e60
 #define PHY_ID_BCM54616S		0x03625d10
 #define PHY_ID_BCM57780			0x03625d90
+#define PHY_ID_BCM89610			0x03625cd0
 
 #define PHY_ID_BCM7250			0xae025280
 #define PHY_ID_BCM7260			0xae025190
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index 28a7ccc55c89..6aeaf6472665 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -72,8 +72,7 @@ struct bsg_job {
 void bsg_job_done(struct bsg_job *job, int result,
 		  unsigned int reply_payload_rcv_len);
 struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
-		bsg_job_fn *job_fn, int dd_job_size,
-		void (*release)(struct device *));
+		bsg_job_fn *job_fn, int dd_job_size);
 void bsg_job_put(struct bsg_job *job);
 int __must_check bsg_job_get(struct bsg_job *job);
 
diff --git a/include/linux/bsg.h b/include/linux/bsg.h
index 0c7dd9ceb139..dac37b6e00ec 100644
--- a/include/linux/bsg.h
+++ b/include/linux/bsg.h
@@ -17,17 +17,13 @@ struct bsg_ops {
 
 struct bsg_class_device {
 	struct device *class_dev;
-	struct device *parent;
 	int minor;
 	struct request_queue *queue;
-	struct kref ref;
 	const struct bsg_ops *ops;
-	void (*release)(struct device *);
 };
 
 int bsg_register_queue(struct request_queue *q, struct device *parent,
-		const char *name, const struct bsg_ops *ops,
-		void (*release)(struct device *));
+		const char *name, const struct bsg_ops *ops);
 int bsg_scsi_register_queue(struct request_queue *q, struct device *parent);
 void bsg_unregister_queue(struct request_queue *q);
 #else
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 894e5d125de6..96225a77c112 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -205,8 +205,6 @@ void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize);
 int bh_uptodate_or_lock(struct buffer_head *bh);
 int bh_submit_read(struct buffer_head *bh);
-loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset,
-				 loff_t length, int whence);
 
 extern int buffer_heads_over_limit;
 
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 528ccc943cee..96bb32285989 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -77,7 +77,10 @@ struct ceph_osd_data {
 			u32			bio_length;
 		};
 #endif /* CONFIG_BLOCK */
-		struct ceph_bvec_iter	bvec_pos;
+		struct {
+			struct ceph_bvec_iter	bvec_pos;
+			u32			num_bvecs;
+		};
 	};
 };
 
@@ -412,6 +415,10 @@ void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
 				    struct ceph_bio_iter *bio_pos,
 				    u32 bio_length);
 #endif /* CONFIG_BLOCK */
+void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
+				      unsigned int which,
+				      struct bio_vec *bvecs, u32 num_bvecs,
+				      u32 bytes);
 void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
 					 unsigned int which,
 					 struct ceph_bvec_iter *bvec_pos);
@@ -426,7 +433,8 @@ extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
 					bool own_pages);
 void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
 				       unsigned int which,
-				       struct bio_vec *bvecs, u32 bytes);
+				       struct bio_vec *bvecs, u32 num_bvecs,
+				       u32 bytes);
 extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *,
 					unsigned int which,
 					struct page **pages, u64 length,
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index dc5b70449dc6..c0e68f903011 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -105,6 +105,8 @@ enum {
 struct cgroup_file {
 	/* do not access any fields from outside cgroup core */
 	struct kernfs_node *kn;
+	unsigned long notified_at;
+	struct timer_list notify_timer;
 };
 
 /*
@@ -128,6 +130,9 @@ struct cgroup_subsys_state {
 	struct list_head sibling;
 	struct list_head children;
 
+	/* flush target list anchored at cgrp->rstat_css_list */
+	struct list_head rstat_css_node;
+
 	/*
 	 * PI: Subsys-unique ID.  0 is unused and root is always 1.  The
 	 * matching css can be looked up using css_from_id().
@@ -256,12 +261,16 @@ struct css_set {
 	struct rcu_head rcu_head;
 };
 
+struct cgroup_base_stat {
+	struct task_cputime cputime;
+};
+
 /*
- * cgroup basic resource usage statistics.  Accounting is done per-cpu in
- * cgroup_cpu_stat which is then lazily propagated up the hierarchy on
- * reads.
+ * rstat - cgroup scalable recursive statistics.  Accounting is done
+ * per-cpu in cgroup_rstat_cpu which is then lazily propagated up the
+ * hierarchy on reads.
  *
- * When a stat gets updated, the cgroup_cpu_stat and its ancestors are
+ * When a stat gets updated, the cgroup_rstat_cpu and its ancestors are
  * linked into the updated tree.  On the following read, propagation only
  * considers and consumes the updated tree.  This makes reading O(the
  * number of descendants which have been active since last read) instead of
@@ -271,20 +280,24 @@ struct css_set {
  * aren't active and stat may be read frequently.  The combination can
  * become very expensive.  By propagating selectively, increasing reading
  * frequency decreases the cost of each read.
+ *
+ * This struct hosts both the fields which implement the above -
+ * updated_children and updated_next - and the fields which track basic
+ * resource statistics on top of it - bsync, bstat and last_bstat.
  */
-struct cgroup_cpu_stat {
+struct cgroup_rstat_cpu {
 	/*
-	 * ->sync protects all the current counters.  These are the only
-	 * fields which get updated in the hot path.
+	 * ->bsync protects ->bstat.  These are the only fields which get
+	 * updated in the hot path.
 	 */
-	struct u64_stats_sync sync;
-	struct task_cputime cputime;
+	struct u64_stats_sync bsync;
+	struct cgroup_base_stat bstat;
 
 	/*
 	 * Snapshots at the last reading.  These are used to calculate the
 	 * deltas to propagate to the global counters.
 	 */
-	struct task_cputime last_cputime;
+	struct cgroup_base_stat last_bstat;
 
 	/*
 	 * Child cgroups with stat updates on this cpu since the last read
@@ -295,18 +308,12 @@ struct cgroup_cpu_stat {
 	 * to the cgroup makes it unnecessary for each per-cpu struct to
 	 * point back to the associated cgroup.
 	 *
-	 * Protected by per-cpu cgroup_cpu_stat_lock.
+	 * Protected by per-cpu cgroup_rstat_cpu_lock.
 	 */
 	struct cgroup *updated_children;	/* terminated by self cgroup */
 	struct cgroup *updated_next;		/* NULL iff not on the list */
 };
 
-struct cgroup_stat {
-	/* per-cpu statistics are collected into the folowing global counters */
-	struct task_cputime cputime;
-	struct prev_cputime prev_cputime;
-};
-
 struct cgroup {
 	/* self css with NULL ->ss, points back to this cgroup */
 	struct cgroup_subsys_state self;
@@ -406,10 +413,14 @@ struct cgroup {
 	 */
 	struct cgroup *dom_cgrp;
 
+	/* per-cpu recursive resource statistics */
+	struct cgroup_rstat_cpu __percpu *rstat_cpu;
+	struct list_head rstat_css_list;
+
 	/* cgroup basic resource statistics */
-	struct cgroup_cpu_stat __percpu *cpu_stat;
-	struct cgroup_stat pending_stat;	/* pending from children */
-	struct cgroup_stat stat;
+	struct cgroup_base_stat pending_bstat;	/* pending from children */
+	struct cgroup_base_stat bstat;
+	struct prev_cputime prev_cputime;	/* for printing out cputime */
 
 	/*
 	 * list of pidlists, up to two for each namespace (one for procs, one
@@ -570,6 +581,7 @@ struct cgroup_subsys {
 	void (*css_released)(struct cgroup_subsys_state *css);
 	void (*css_free)(struct cgroup_subsys_state *css);
 	void (*css_reset)(struct cgroup_subsys_state *css);
+	void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu);
 	int (*css_extra_stat_show)(struct seq_file *seq,
 				   struct cgroup_subsys_state *css);
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 473e0c0abb86..c9fdf6f57913 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -690,11 +690,19 @@ static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
 	char *buf, size_t buflen) {}
 #endif /* !CONFIG_CGROUPS */
 
+#ifdef CONFIG_CGROUPS
 /*
- * Basic resource stats.
+ * cgroup scalable recursive statistics.
  */
-#ifdef CONFIG_CGROUPS
+void cgroup_rstat_updated(struct cgroup *cgrp, int cpu);
+void cgroup_rstat_flush(struct cgroup *cgrp);
+void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp);
+void cgroup_rstat_flush_hold(struct cgroup *cgrp);
+void cgroup_rstat_flush_release(void);
 
+/*
+ * Basic resource stats.
+ */
 #ifdef CONFIG_CGROUP_CPUACCT
 void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 void cpuacct_account_field(struct task_struct *tsk, int index, u64 val);
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 210a890008f9..1d25e149c1c5 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -765,6 +765,9 @@ int __clk_mux_determine_rate(struct clk_hw *hw,
 int __clk_determine_rate(struct clk_hw *core, struct clk_rate_request *req);
 int __clk_mux_determine_rate_closest(struct clk_hw *hw,
 				     struct clk_rate_request *req);
+int clk_mux_determine_rate_flags(struct clk_hw *hw,
+				 struct clk_rate_request *req,
+				 unsigned long flags);
 void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent);
 void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate,
 			   unsigned long max_rate);
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 081281ad5772..b1a5562b3215 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -7,8 +7,7 @@
  */
 
 #include <linux/types.h>
-
-#ifdef CONFIG_COMPAT
+#include <linux/compat_time.h>
 
 #include <linux/stat.h>
 #include <linux/param.h>	/* for HZ */
@@ -21,8 +20,11 @@
 #include <linux/unistd.h>
 
 #include <asm/compat.h>
+
+#ifdef CONFIG_COMPAT
 #include <asm/siginfo.h>
 #include <asm/signal.h>
+#endif
 
 #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
 /*
@@ -83,6 +85,8 @@
 	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 #endif /* COMPAT_SYSCALL_DEFINEx */
 
+#ifdef CONFIG_COMPAT
+
 #ifndef compat_user_stack_pointer
 #define compat_user_stack_pointer() current_user_stack_pointer()
 #endif
@@ -290,8 +294,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *);
 extern int compat_put_timespec(const struct timespec *, void __user *);
 extern int compat_get_timeval(struct timeval *, const void __user *);
 extern int compat_put_timeval(const struct timeval *, void __user *);
-extern int compat_get_timespec64(struct timespec64 *, const void __user *);
-extern int compat_put_timespec64(const struct timespec64 *, void __user *);
 extern int get_compat_itimerspec64(struct itimerspec64 *its,
 			const struct compat_itimerspec __user *uits);
 extern int put_compat_itimerspec64(const struct itimerspec64 *its,
@@ -330,6 +332,7 @@ extern int put_compat_rusage(const struct rusage *,
 			     struct compat_rusage __user *);
 
 struct compat_siginfo;
+struct __compat_aio_sigset;
 
 struct compat_dirent {
 	u32		d_ino;
@@ -553,6 +556,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id,
 					compat_long_t nr,
 					struct io_event __user *events,
 					struct compat_timespec __user *timeout);
+asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id,
+					compat_long_t min_nr,
+					compat_long_t nr,
+					struct io_event __user *events,
+					struct compat_timespec __user *timeout,
+					const struct __compat_aio_sigset __user *usig);
 
 /* fs/cookies.c */
 asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);
@@ -1016,7 +1025,9 @@ static inline struct compat_timeval ns_to_compat_timeval(s64 nsec)
 #else /* !CONFIG_COMPAT */
 
 #define is_compat_task() (0)
+#ifndef in_compat_syscall
 static inline bool in_compat_syscall(void) { return false; }
+#endif
 
 #endif /* CONFIG_COMPAT */
 
diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h
new file mode 100644
index 000000000000..31f2774f1994
--- /dev/null
+++ b/include/linux/compat_time.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_COMPAT_TIME_H
+#define _LINUX_COMPAT_TIME_H
+
+#include <linux/types.h>
+#include <linux/time64.h>
+
+typedef s32		compat_time_t;
+
+struct compat_timespec {
+	compat_time_t	tv_sec;
+	s32		tv_nsec;
+};
+
+struct compat_timeval {
+	compat_time_t	tv_sec;
+	s32		tv_usec;
+};
+
+extern int compat_get_timespec64(struct timespec64 *, const void __user *);
+extern int compat_put_timespec64(const struct timespec64 *, void __user *);
+
+#endif /* _LINUX_COMPAT_TIME_H */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index ceb96ecab96e..7d98e263e048 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -25,6 +25,9 @@
 #define __SANITIZE_ADDRESS__
 #endif
 
+#undef __no_sanitize_address
+#define __no_sanitize_address __attribute__((no_sanitize("address")))
+
 /* Clang doesn't have a way to turn it off per-function, yet. */
 #ifdef __noretpoline
 #undef __noretpoline
diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h
index edfeaba95429..a1a959ba24ff 100644
--- a/include/linux/coresight-pmu.h
+++ b/include/linux/coresight-pmu.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _LINUX_CORESIGHT_PMU_H
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index d950dad5056a..c265e0468414 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -1,13 +1,6 @@
-/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2012, The Linux Foundation. All rights reserved.
  */
 
 #ifndef _LINUX_CORESIGHT_H
diff --git a/include/linux/cper.h b/include/linux/cper.h
index d14ef4e77c8a..9c703a0abe6e 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -381,7 +381,7 @@ struct cper_sec_proc_generic {
 /* IA32/X64 Processor Error Section */
 struct cper_sec_proc_ia {
 	__u64	validation_bits;
-	__u8	lapic_id;
+	__u64	lapic_id;
 	__u8	cpuid[48];
 };
 
@@ -551,5 +551,7 @@ const char *cper_mem_err_unpack(struct trace_seq *,
 				struct cper_mem_err_compact *);
 void cper_print_proc_arm(const char *pfx,
 			 const struct cper_sec_proc_arm *proc);
+void cper_print_proc_ia(const char *pfx,
+			const struct cper_sec_proc_ia *proc);
 
 #endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 7b01bc11c692..a97a63eef59f 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -53,6 +53,8 @@ extern ssize_t cpu_show_spectre_v1(struct device *dev,
 				   struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_spectre_v2(struct device *dev,
 				   struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
+					  struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 87f48dd932eb..882a9b9e34bc 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -571,7 +571,7 @@ struct governor_attr {
 			 size_t count);
 };
 
-static inline bool cpufreq_can_do_remote_dvfs(struct cpufreq_policy *policy)
+static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy)
 {
 	/*
 	 * Allow remote callbacks if:
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 1eefabf1621f..4325d6fdde9b 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -258,6 +258,7 @@ struct cpuidle_governor {
 
 #ifdef CONFIG_CPU_IDLE
 extern int cpuidle_register_governor(struct cpuidle_governor *gov);
+extern int cpuidle_governor_latency_req(unsigned int cpu);
 #else
 static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 {return 0;}
diff --git a/include/linux/dax.h b/include/linux/dax.h
index f9eb22ad341e..c99692ddd4b5 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -64,10 +64,10 @@ static inline bool dax_write_cache_enabled(struct dax_device *dax_dev)
 struct writeback_control;
 int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
 #if IS_ENABLED(CONFIG_FS_DAX)
-int __bdev_dax_supported(struct super_block *sb, int blocksize);
-static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+bool __bdev_dax_supported(struct block_device *bdev, int blocksize);
+static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize)
 {
-	return __bdev_dax_supported(sb, blocksize);
+	return __bdev_dax_supported(bdev, blocksize);
 }
 
 static inline struct dax_device *fs_dax_get_by_host(const char *host)
@@ -84,9 +84,10 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
 int dax_writeback_mapping_range(struct address_space *mapping,
 		struct block_device *bdev, struct writeback_control *wbc);
 #else
-static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+static inline bool bdev_dax_supported(struct block_device *bdev,
+		int blocksize)
 {
-	return -EOPNOTSUPP;
+	return false;
 }
 
 static inline struct dax_device *fs_dax_get_by_host(const char *host)
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 94acbde17bb1..66c6e17e61e5 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -224,6 +224,7 @@ extern seqlock_t rename_lock;
  * These are the low-level FS interfaces to the dcache..
  */
 extern void d_instantiate(struct dentry *, struct inode *);
+extern void d_instantiate_new(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
 extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 5e335b6203f4..e6c0448ebcc7 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -29,7 +29,7 @@
 
 #ifdef CONFIG_TASK_DELAY_ACCT
 struct task_delay_info {
-	spinlock_t	lock;
+	raw_spinlock_t	lock;
 	unsigned int	flags;	/* Private per-task flags */
 
 	/* For each stat XXX, add following, aligned appropriately
diff --git a/include/linux/device.h b/include/linux/device.h
index 0059b99e1f25..e9d4b43c4ead 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -88,6 +88,8 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @resume:	Called to bring a device on this bus out of sleep mode.
  * @num_vf:	Called to find out how many virtual functions a device on this
  *		bus supports.
+ * @dma_configure:	Called to setup DMA configuration on a device on
+			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
  * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
@@ -96,8 +98,8 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @p:		The private data of the driver core, only the driver core can
  *		touch this.
  * @lock_key:	Lock class key for use by the lock validator
- * @force_dma:	Assume devices on this bus should be set up by dma_configure()
- * 		even if DMA capability is not explicitly described by firmware.
+ * @need_parent_lock:	When probing or removing a device on this bus, the
+ *			device core should lock the device's parent.
  *
  * A bus is a channel between the processor and one or more devices. For the
  * purposes of the device model, all devices are connected via a bus, even if
@@ -130,6 +132,8 @@ struct bus_type {
 
 	int (*num_vf)(struct device *dev);
 
+	int (*dma_configure)(struct device *dev);
+
 	const struct dev_pm_ops *pm;
 
 	const struct iommu_ops *iommu_ops;
@@ -137,7 +141,7 @@ struct bus_type {
 	struct subsys_private *p;
 	struct lock_class_key lock_key;
 
-	bool force_dma;
+	bool need_parent_lock;
 };
 
 extern int __must_check bus_register(struct bus_type *bus);
@@ -256,7 +260,9 @@ enum probe_type {
  *		automatically.
  * @pm:		Power management operations of the device which matched
  *		this driver.
- * @coredump:	Called through sysfs to initiate a device coredump.
+ * @coredump:	Called when sysfs entry is written to. The device driver
+ *		is expected to call the dev_coredump API resulting in a
+ *		uevent.
  * @p:		Driver core's private data, no one other than the driver
  *		core can touch this.
  *
@@ -288,7 +294,7 @@ struct device_driver {
 	const struct attribute_group **groups;
 
 	const struct dev_pm_ops *pm;
-	int (*coredump) (struct device *dev);
+	void (*coredump) (struct device *dev);
 
 	struct driver_private *p;
 };
@@ -902,6 +908,8 @@ struct dev_links_info {
  * @offline:	Set after successful invocation of bus type's .offline().
  * @of_node_reused: Set if the device-tree node is shared with an ancestor
  *              device.
+ * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself
+ *		indicates support for a higher limit in the dma_mask field.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -990,6 +998,7 @@ struct device {
 	bool			offline_disabled:1;
 	bool			offline:1;
 	bool			of_node_reused:1;
+	bool			dma_32bit_limit:1;
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index c7d844f09c3a..a785f2507159 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -30,8 +30,6 @@ struct bus_type;
 
 extern void dma_debug_add_bus(struct bus_type *bus);
 
-extern void dma_debug_init(u32 num_entries);
-
 extern int dma_debug_resize_entries(u32 num_entries);
 
 extern void debug_dma_map_page(struct device *dev, struct page *page,
@@ -100,10 +98,6 @@ static inline void dma_debug_add_bus(struct bus_type *bus)
 {
 }
 
-static inline void dma_debug_init(u32 num_entries)
-{
-}
-
 static inline int dma_debug_resize_entries(u32 num_entries)
 {
 	return 0;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 53ad6a47f513..8d9f33febde5 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -59,6 +59,11 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
-
+int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr);
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index 4c008170fe65..eb9b05aa5aea 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -94,11 +94,11 @@ typedef void (*dma_fence_func_t)(struct dma_fence *fence,
 				 struct dma_fence_cb *cb);
 
 /**
- * struct dma_fence_cb - callback for dma_fence_add_callback
- * @node: used by dma_fence_add_callback to append this struct to fence::cb_list
+ * struct dma_fence_cb - callback for dma_fence_add_callback()
+ * @node: used by dma_fence_add_callback() to append this struct to fence::cb_list
  * @func: dma_fence_func_t to call
  *
- * This struct will be initialized by dma_fence_add_callback, additional
+ * This struct will be initialized by dma_fence_add_callback(), additional
  * data can be passed along by embedding dma_fence_cb in another struct.
  */
 struct dma_fence_cb {
@@ -108,75 +108,143 @@ struct dma_fence_cb {
 
 /**
  * struct dma_fence_ops - operations implemented for fence
- * @get_driver_name: returns the driver name.
- * @get_timeline_name: return the name of the context this fence belongs to.
- * @enable_signaling: enable software signaling of fence.
- * @signaled: [optional] peek whether the fence is signaled, can be null.
- * @wait: custom wait implementation, or dma_fence_default_wait.
- * @release: [optional] called on destruction of fence, can be null
- * @fill_driver_data: [optional] callback to fill in free-form debug info
- * Returns amount of bytes filled, or -errno.
- * @fence_value_str: [optional] fills in the value of the fence as a string
- * @timeline_value_str: [optional] fills in the current value of the timeline
- * as a string
  *
- * Notes on enable_signaling:
- * For fence implementations that have the capability for hw->hw
- * signaling, they can implement this op to enable the necessary
- * irqs, or insert commands into cmdstream, etc.  This is called
- * in the first wait() or add_callback() path to let the fence
- * implementation know that there is another driver waiting on
- * the signal (ie. hw->sw case).
- *
- * This function can be called from atomic context, but not
- * from irq context, so normal spinlocks can be used.
- *
- * A return value of false indicates the fence already passed,
- * or some failure occurred that made it impossible to enable
- * signaling. True indicates successful enabling.
- *
- * fence->error may be set in enable_signaling, but only when false is
- * returned.
- *
- * Calling dma_fence_signal before enable_signaling is called allows
- * for a tiny race window in which enable_signaling is called during,
- * before, or after dma_fence_signal. To fight this, it is recommended
- * that before enable_signaling returns true an extra reference is
- * taken on the fence, to be released when the fence is signaled.
- * This will mean dma_fence_signal will still be called twice, but
- * the second time will be a noop since it was already signaled.
- *
- * Notes on signaled:
- * May set fence->error if returning true.
- *
- * Notes on wait:
- * Must not be NULL, set to dma_fence_default_wait for default implementation.
- * the dma_fence_default_wait implementation should work for any fence, as long
- * as enable_signaling works correctly.
- *
- * Must return -ERESTARTSYS if the wait is intr = true and the wait was
- * interrupted, and remaining jiffies if fence has signaled, or 0 if wait
- * timed out. Can also return other error values on custom implementations,
- * which should be treated as if the fence is signaled. For example a hardware
- * lockup could be reported like that.
- *
- * Notes on release:
- * Can be NULL, this function allows additional commands to run on
- * destruction of the fence. Can be called from irq context.
- * If pointer is set to NULL, kfree will get called instead.
  */
-
 struct dma_fence_ops {
+	/**
+	 * @get_driver_name:
+	 *
+	 * Returns the driver name. This is a callback to allow drivers to
+	 * compute the name at runtime, without having it to store permanently
+	 * for each fence, or build a cache of some sort.
+	 *
+	 * This callback is mandatory.
+	 */
 	const char * (*get_driver_name)(struct dma_fence *fence);
+
+	/**
+	 * @get_timeline_name:
+	 *
+	 * Return the name of the context this fence belongs to. This is a
+	 * callback to allow drivers to compute the name at runtime, without
+	 * having it to store permanently for each fence, or build a cache of
+	 * some sort.
+	 *
+	 * This callback is mandatory.
+	 */
 	const char * (*get_timeline_name)(struct dma_fence *fence);
+
+	/**
+	 * @enable_signaling:
+	 *
+	 * Enable software signaling of fence.
+	 *
+	 * For fence implementations that have the capability for hw->hw
+	 * signaling, they can implement this op to enable the necessary
+	 * interrupts, or insert commands into cmdstream, etc, to avoid these
+	 * costly operations for the common case where only hw->hw
+	 * synchronization is required.  This is called in the first
+	 * dma_fence_wait() or dma_fence_add_callback() path to let the fence
+	 * implementation know that there is another driver waiting on the
+	 * signal (ie. hw->sw case).
+	 *
+	 * This function can be called from atomic context, but not
+	 * from irq context, so normal spinlocks can be used.
+	 *
+	 * A return value of false indicates the fence already passed,
+	 * or some failure occurred that made it impossible to enable
+	 * signaling. True indicates successful enabling.
+	 *
+	 * &dma_fence.error may be set in enable_signaling, but only when false
+	 * is returned.
+	 *
+	 * Since many implementations can call dma_fence_signal() even when before
+	 * @enable_signaling has been called there's a race window, where the
+	 * dma_fence_signal() might result in the final fence reference being
+	 * released and its memory freed. To avoid this, implementations of this
+	 * callback should grab their own reference using dma_fence_get(), to be
+	 * released when the fence is signalled (through e.g. the interrupt
+	 * handler).
+	 *
+	 * This callback is mandatory.
+	 */
 	bool (*enable_signaling)(struct dma_fence *fence);
+
+	/**
+	 * @signaled:
+	 *
+	 * Peek whether the fence is signaled, as a fastpath optimization for
+	 * e.g. dma_fence_wait() or dma_fence_add_callback(). Note that this
+	 * callback does not need to make any guarantees beyond that a fence
+	 * once indicates as signalled must always return true from this
+	 * callback. This callback may return false even if the fence has
+	 * completed already, in this case information hasn't propogated throug
+	 * the system yet. See also dma_fence_is_signaled().
+	 *
+	 * May set &dma_fence.error if returning true.
+	 *
+	 * This callback is optional.
+	 */
 	bool (*signaled)(struct dma_fence *fence);
+
+	/**
+	 * @wait:
+	 *
+	 * Custom wait implementation, or dma_fence_default_wait.
+	 *
+	 * Must not be NULL, set to dma_fence_default_wait for default implementation.
+	 * the dma_fence_default_wait implementation should work for any fence, as long
+	 * as enable_signaling works correctly.
+	 *
+	 * Must return -ERESTARTSYS if the wait is intr = true and the wait was
+	 * interrupted, and remaining jiffies if fence has signaled, or 0 if wait
+	 * timed out. Can also return other error values on custom implementations,
+	 * which should be treated as if the fence is signaled. For example a hardware
+	 * lockup could be reported like that.
+	 *
+	 * This callback is mandatory.
+	 */
 	signed long (*wait)(struct dma_fence *fence,
 			    bool intr, signed long timeout);
+
+	/**
+	 * @release:
+	 *
+	 * Called on destruction of fence to release additional resources.
+	 * Can be called from irq context.  This callback is optional. If it is
+	 * NULL, then dma_fence_free() is instead called as the default
+	 * implementation.
+	 */
 	void (*release)(struct dma_fence *fence);
 
+	/**
+	 * @fill_driver_data:
+	 *
+	 * Callback to fill in free-form debug info.
+	 *
+	 * Returns amount of bytes filled, or negative error on failure.
+	 *
+	 * This callback is optional.
+	 */
 	int (*fill_driver_data)(struct dma_fence *fence, void *data, int size);
+
+	/**
+	 * @fence_value_str:
+	 *
+	 * Callback to fill in free-form debug info specific to this fence, like
+	 * the sequence number.
+	 *
+	 * This callback is optional.
+	 */
 	void (*fence_value_str)(struct dma_fence *fence, char *str, int size);
+
+	/**
+	 * @timeline_value_str:
+	 *
+	 * Fills in the current value of the timeline as a string, like the
+	 * sequence number. This should match what @fill_driver_data prints for
+	 * the most recently signalled fence (assuming no delayed signalling).
+	 */
 	void (*timeline_value_str)(struct dma_fence *fence,
 				   char *str, int size);
 };
@@ -189,7 +257,7 @@ void dma_fence_free(struct dma_fence *fence);
 
 /**
  * dma_fence_put - decreases refcount of the fence
- * @fence:	[in]	fence to reduce refcount of
+ * @fence: fence to reduce refcount of
  */
 static inline void dma_fence_put(struct dma_fence *fence)
 {
@@ -199,7 +267,7 @@ static inline void dma_fence_put(struct dma_fence *fence)
 
 /**
  * dma_fence_get - increases refcount of the fence
- * @fence:	[in]	fence to increase refcount of
+ * @fence: fence to increase refcount of
  *
  * Returns the same fence, with refcount increased by 1.
  */
@@ -213,7 +281,7 @@ static inline struct dma_fence *dma_fence_get(struct dma_fence *fence)
 /**
  * dma_fence_get_rcu - get a fence from a reservation_object_list with
  *                     rcu read lock
- * @fence:	[in]	fence to increase refcount of
+ * @fence: fence to increase refcount of
  *
  * Function returns NULL if no refcount could be obtained, or the fence.
  */
@@ -227,7 +295,7 @@ static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence)
 
 /**
  * dma_fence_get_rcu_safe  - acquire a reference to an RCU tracked fence
- * @fencep:	[in]	pointer to fence to increase refcount of
+ * @fencep: pointer to fence to increase refcount of
  *
  * Function returns NULL if no refcount could be obtained, or the fence.
  * This function handles acquiring a reference to a fence that may be
@@ -289,14 +357,16 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence);
 /**
  * dma_fence_is_signaled_locked - Return an indication if the fence
  *                                is signaled yet.
- * @fence:	[in]	the fence to check
+ * @fence: the fence to check
  *
  * Returns true if the fence was already signaled, false if not. Since this
  * function doesn't enable signaling, it is not guaranteed to ever return
- * true if dma_fence_add_callback, dma_fence_wait or
- * dma_fence_enable_sw_signaling haven't been called before.
+ * true if dma_fence_add_callback(), dma_fence_wait() or
+ * dma_fence_enable_sw_signaling() haven't been called before.
  *
- * This function requires fence->lock to be held.
+ * This function requires &dma_fence.lock to be held.
+ *
+ * See also dma_fence_is_signaled().
  */
 static inline bool
 dma_fence_is_signaled_locked(struct dma_fence *fence)
@@ -314,17 +384,19 @@ dma_fence_is_signaled_locked(struct dma_fence *fence)
 
 /**
  * dma_fence_is_signaled - Return an indication if the fence is signaled yet.
- * @fence:	[in]	the fence to check
+ * @fence: the fence to check
  *
  * Returns true if the fence was already signaled, false if not. Since this
  * function doesn't enable signaling, it is not guaranteed to ever return
- * true if dma_fence_add_callback, dma_fence_wait or
- * dma_fence_enable_sw_signaling haven't been called before.
+ * true if dma_fence_add_callback(), dma_fence_wait() or
+ * dma_fence_enable_sw_signaling() haven't been called before.
  *
  * It's recommended for seqno fences to call dma_fence_signal when the
  * operation is complete, it makes it possible to prevent issues from
  * wraparound between time of issue and time of use by checking the return
  * value of this function before calling hardware-specific wait instructions.
+ *
+ * See also dma_fence_is_signaled_locked().
  */
 static inline bool
 dma_fence_is_signaled(struct dma_fence *fence)
@@ -342,8 +414,8 @@ dma_fence_is_signaled(struct dma_fence *fence)
 
 /**
  * __dma_fence_is_later - return if f1 is chronologically later than f2
- * @f1:	[in]	the first fence's seqno
- * @f2:	[in]	the second fence's seqno from the same context
+ * @f1: the first fence's seqno
+ * @f2: the second fence's seqno from the same context
  *
  * Returns true if f1 is chronologically later than f2. Both fences must be
  * from the same context, since a seqno is not common across contexts.
@@ -355,8 +427,8 @@ static inline bool __dma_fence_is_later(u32 f1, u32 f2)
 
 /**
  * dma_fence_is_later - return if f1 is chronologically later than f2
- * @f1:	[in]	the first fence from the same context
- * @f2:	[in]	the second fence from the same context
+ * @f1: the first fence from the same context
+ * @f2: the second fence from the same context
  *
  * Returns true if f1 is chronologically later than f2. Both fences must be
  * from the same context, since a seqno is not re-used across contexts.
@@ -372,8 +444,8 @@ static inline bool dma_fence_is_later(struct dma_fence *f1,
 
 /**
  * dma_fence_later - return the chronologically later fence
- * @f1:	[in]	the first fence from the same context
- * @f2:	[in]	the second fence from the same context
+ * @f1:	the first fence from the same context
+ * @f2:	the second fence from the same context
  *
  * Returns NULL if both fences are signaled, otherwise the fence that would be
  * signaled last. Both fences must be from the same context, since a seqno is
@@ -398,7 +470,7 @@ static inline struct dma_fence *dma_fence_later(struct dma_fence *f1,
 
 /**
  * dma_fence_get_status_locked - returns the status upon completion
- * @fence: [in]	the dma_fence to query
+ * @fence: the dma_fence to query
  *
  * Drivers can supply an optional error status condition before they signal
  * the fence (to indicate whether the fence was completed due to an error
@@ -422,8 +494,8 @@ int dma_fence_get_status(struct dma_fence *fence);
 
 /**
  * dma_fence_set_error - flag an error condition on the fence
- * @fence: [in]	the dma_fence
- * @error: [in]	the error to store
+ * @fence: the dma_fence
+ * @error: the error to store
  *
  * Drivers can supply an optional error status condition before they signal
  * the fence, to indicate that the fence was completed due to an error
@@ -449,8 +521,8 @@ signed long dma_fence_wait_any_timeout(struct dma_fence **fences,
 
 /**
  * dma_fence_wait - sleep until the fence gets signaled
- * @fence:	[in]	the fence to wait on
- * @intr:	[in]	if true, do an interruptible wait
+ * @fence: the fence to wait on
+ * @intr: if true, do an interruptible wait
  *
  * This function will return -ERESTARTSYS if interrupted by a signal,
  * or 0 if the fence was signaled. Other error values may be
@@ -459,6 +531,8 @@ signed long dma_fence_wait_any_timeout(struct dma_fence **fences,
  * Performs a synchronous wait on this fence. It is assumed the caller
  * directly or indirectly holds a reference to the fence, otherwise the
  * fence might be freed before return, resulting in undefined behavior.
+ *
+ * See also dma_fence_wait_timeout() and dma_fence_wait_any_timeout().
  */
 static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr)
 {
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index 92f20832fd28..e8ca5e654277 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -17,6 +17,7 @@
 #define __DMA_IOMMU_H
 
 #ifdef __KERNEL__
+#include <linux/types.h>
 #include <asm/errno.h>
 
 #ifdef CONFIG_IOMMU_DMA
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index f8ab1c0f589e..f9cc309507d9 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -133,10 +133,10 @@ struct dma_map_ops {
 #ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
 	u64 (*get_required_mask)(struct device *dev);
 #endif
-	int is_phys;
 };
 
 extern const struct dma_map_ops dma_direct_ops;
+extern const struct dma_map_ops dma_noncoherent_ops;
 extern const struct dma_map_ops dma_virt_ops;
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
@@ -502,7 +502,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 
 #ifndef arch_dma_alloc_attrs
-#define arch_dma_alloc_attrs(dev, flag)	(true)
+#define arch_dma_alloc_attrs(dev)	(true)
 #endif
 
 static inline void *dma_alloc_attrs(struct device *dev, size_t size,
@@ -521,7 +521,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-	if (!arch_dma_alloc_attrs(&dev, &flag))
+	if (!arch_dma_alloc_attrs(&dev))
 		return NULL;
 	if (!ops->alloc)
 		return NULL;
@@ -572,14 +572,6 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return 0;
 }
 
-/*
- * This is a hack for the legacy x86 forbid_dac and iommu_sac_force. Please
- * don't use this in new code.
- */
-#ifndef arch_dma_supported
-#define arch_dma_supported(dev, mask)	(1)
-#endif
-
 static inline void dma_check_mask(struct device *dev, u64 mask)
 {
 	if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1)))
@@ -592,9 +584,6 @@ static inline int dma_supported(struct device *dev, u64 mask)
 
 	if (!ops)
 		return 0;
-	if (!arch_dma_supported(dev, mask))
-		return 0;
-
 	if (!ops->dma_supported)
 		return 1;
 	return ops->dma_supported(dev, mask);
@@ -839,7 +828,7 @@ static inline int dma_mmap_wc(struct device *dev,
 #define dma_mmap_writecombine dma_mmap_wc
 #endif
 
-#if defined(CONFIG_NEED_DMA_MAP_STATE) || defined(CONFIG_DMA_API_DEBUG)
+#ifdef CONFIG_NEED_DMA_MAP_STATE
 #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)        dma_addr_t ADDR_NAME
 #define DEFINE_DMA_UNMAP_LEN(LEN_NAME)          __u32 LEN_NAME
 #define dma_unmap_addr(PTR, ADDR_NAME)           ((PTR)->ADDR_NAME)
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
new file mode 100644
index 000000000000..10b2654d549b
--- /dev/null
+++ b/include/linux/dma-noncoherent.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_DMA_NONCOHERENT_H
+#define _LINUX_DMA_NONCOHERENT_H 1
+
+#include <linux/dma-mapping.h>
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs);
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs);
+
+#ifdef CONFIG_DMA_NONCOHERENT_MMAP
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+#else
+#define arch_dma_mmap NULL
+#endif /* CONFIG_DMA_NONCOHERENT_MMAP */
+
+#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction direction);
+#else
+#define arch_dma_cache_sync NULL
+#endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_device(struct device *dev,
+		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_cpu(struct device *dev,
+		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
+
+#endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index f1b7d68ac460..56add823f190 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -395,9 +395,9 @@ typedef struct {
 	u32 attributes;
 	u32 get_bar_attributes;
 	u32 set_bar_attributes;
-	uint64_t romsize;
-	void *romimage;
-} efi_pci_io_protocol_32;
+	u64 romsize;
+	u32 romimage;
+} efi_pci_io_protocol_32_t;
 
 typedef struct {
 	u64 poll_mem;
@@ -415,9 +415,9 @@ typedef struct {
 	u64 attributes;
 	u64 get_bar_attributes;
 	u64 set_bar_attributes;
-	uint64_t romsize;
-	void *romimage;
-} efi_pci_io_protocol_64;
+	u64 romsize;
+	u64 romimage;
+} efi_pci_io_protocol_64_t;
 
 typedef struct {
 	void *poll_mem;
@@ -437,7 +437,7 @@ typedef struct {
 	void *set_bar_attributes;
 	uint64_t romsize;
 	void *romimage;
-} efi_pci_io_protocol;
+} efi_pci_io_protocol_t;
 
 #define EFI_PCI_IO_ATTRIBUTE_ISA_MOTHERBOARD_IO 0x0001
 #define EFI_PCI_IO_ATTRIBUTE_ISA_IO 0x0002
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 6d9e230dffd2..a02deea30185 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -218,8 +218,6 @@ extern void elv_unregister(struct elevator_type *);
 extern ssize_t elv_iosched_show(struct request_queue *, char *);
 extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
 
-extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(struct request_queue *, struct elevator_queue *);
 extern bool elv_bio_merge_ok(struct request *, struct bio *);
 extern struct elevator_queue *elevator_alloc(struct request_queue *,
 					struct elevator_type *);
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index ebe41811ed34..b32cd2062f18 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -310,6 +310,8 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
  *	fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS
  *	instead of the latter), any change to them will be overwritten
  *	by kernel. Returns a negative error code or zero.
+ * @get_fecparam: Get the network device Forward Error Correction parameters.
+ * @set_fecparam: Set the network device Forward Error Correction parameters.
  *
  * All operations are optional (i.e. the function pointer may be set
  * to %NULL) and callers must take this into account.  Callers must
diff --git a/include/linux/export.h b/include/linux/export.h
index 1a1dfdb2a5c6..b768d6dd3c90 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -10,14 +10,8 @@
  * hackers place grumpy comments in header files.
  */
 
-/* Some toolchains use a `_' prefix for all user symbols. */
-#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
-#define __VMLINUX_SYMBOL(x) _##x
-#define __VMLINUX_SYMBOL_STR(x) "_" #x
-#else
 #define __VMLINUX_SYMBOL(x) x
 #define __VMLINUX_SYMBOL_STR(x) #x
-#endif
 
 /* Indirect, so macros are expanded before pasting. */
 #define VMLINUX_SYMBOL(x) __VMLINUX_SYMBOL(x)
@@ -46,14 +40,14 @@ extern struct module __this_module;
 #if defined(CONFIG_MODULE_REL_CRCS)
 #define __CRC_SYMBOL(sym, sec)						\
 	asm("	.section \"___kcrctab" sec "+" #sym "\", \"a\"	\n"	\
-	    "	.weak	" VMLINUX_SYMBOL_STR(__crc_##sym) "	\n"	\
-	    "	.long	" VMLINUX_SYMBOL_STR(__crc_##sym) " - .	\n"	\
+	    "	.weak	__crc_" #sym "				\n"	\
+	    "	.long	__crc_" #sym " - .			\n"	\
 	    "	.previous					\n");
 #else
 #define __CRC_SYMBOL(sym, sec)						\
 	asm("	.section \"___kcrctab" sec "+" #sym "\", \"a\"	\n"	\
-	    "	.weak	" VMLINUX_SYMBOL_STR(__crc_##sym) "	\n"	\
-	    "	.long	" VMLINUX_SYMBOL_STR(__crc_##sym) "	\n"	\
+	    "	.weak	__crc_" #sym "				\n"	\
+	    "	.long	__crc_" #sym "				\n"	\
 	    "	.previous					\n");
 #endif
 #else
@@ -66,7 +60,7 @@ extern struct module __this_module;
 	__CRC_SYMBOL(sym, sec)						\
 	static const char __kstrtab_##sym[]				\
 	__attribute__((section("__ksymtab_strings"), aligned(1)))	\
-	= VMLINUX_SYMBOL_STR(sym);					\
+	= #sym;								\
 	static const struct kernel_symbol __ksymtab_##sym		\
 	__used								\
 	__attribute__((section("___ksymtab" sec "+" #sym), used))	\
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index 41050417cafb..2dd566c91d44 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -42,6 +42,8 @@ struct builtin_fw {
 #if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE))
 int request_firmware(const struct firmware **fw, const char *name,
 		     struct device *device);
+int firmware_request_nowarn(const struct firmware **fw, const char *name,
+			    struct device *device);
 int request_firmware_nowait(
 	struct module *module, bool uevent,
 	const char *name, struct device *device, gfp_t gfp, void *context,
@@ -59,6 +61,14 @@ static inline int request_firmware(const struct firmware **fw,
 {
 	return -EINVAL;
 }
+
+static inline int firmware_request_nowarn(const struct firmware **fw,
+					  const char *name,
+					  struct device *device)
+{
+	return -EINVAL;
+}
+
 static inline int request_firmware_nowait(
 	struct module *module, bool uevent,
 	const char *name, struct device *device, gfp_t gfp, void *context,
diff --git a/include/linux/fpga/altera-pr-ip-core.h b/include/linux/fpga/altera-pr-ip-core.h
index 3810a9033f49..7d4664730d60 100644
--- a/include/linux/fpga/altera-pr-ip-core.h
+++ b/include/linux/fpga/altera-pr-ip-core.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Driver for Altera Partial Reconfiguration IP Core
  *
@@ -5,18 +6,6 @@
  *
  * Based on socfpga-a10.c Copyright (C) 2015-2016 Altera Corporation
  *  by Alan Tull <atull@opensource.altera.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _ALT_PR_IP_CORE_H
diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h
index 3694821a6d2d..ce550fcf6360 100644
--- a/include/linux/fpga/fpga-bridge.h
+++ b/include/linux/fpga/fpga-bridge.h
@@ -62,8 +62,11 @@ int of_fpga_bridge_get_to_list(struct device_node *np,
 			       struct fpga_image_info *info,
 			       struct list_head *bridge_list);
 
-int fpga_bridge_register(struct device *dev, const char *name,
-			 const struct fpga_bridge_ops *br_ops, void *priv);
-void fpga_bridge_unregister(struct device *dev);
+struct fpga_bridge *fpga_bridge_create(struct device *dev, const char *name,
+				       const struct fpga_bridge_ops *br_ops,
+				       void *priv);
+void fpga_bridge_free(struct fpga_bridge *br);
+int fpga_bridge_register(struct fpga_bridge *br);
+void fpga_bridge_unregister(struct fpga_bridge *br);
 
 #endif /* _LINUX_FPGA_BRIDGE_H */
diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h
index 3c6de23aabdf..eec7c2478b0d 100644
--- a/include/linux/fpga/fpga-mgr.h
+++ b/include/linux/fpga/fpga-mgr.h
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * FPGA Framework
  *
  *  Copyright (C) 2013-2016 Altera Corporation
  *  Copyright (C) 2017 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #ifndef _LINUX_FPGA_MGR_H
 #define _LINUX_FPGA_MGR_H
@@ -170,9 +159,11 @@ struct fpga_manager *fpga_mgr_get(struct device *dev);
 
 void fpga_mgr_put(struct fpga_manager *mgr);
 
-int fpga_mgr_register(struct device *dev, const char *name,
-		      const struct fpga_manager_ops *mops, void *priv);
-
-void fpga_mgr_unregister(struct device *dev);
+struct fpga_manager *fpga_mgr_create(struct device *dev, const char *name,
+				     const struct fpga_manager_ops *mops,
+				     void *priv);
+void fpga_mgr_free(struct fpga_manager *mgr);
+int fpga_mgr_register(struct fpga_manager *mgr);
+void fpga_mgr_unregister(struct fpga_manager *mgr);
 
 #endif /*_LINUX_FPGA_MGR_H */
diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h
index b6520318ab9c..d7071cddd727 100644
--- a/include/linux/fpga/fpga-region.h
+++ b/include/linux/fpga/fpga-region.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
 #ifndef _FPGA_REGION_H
 #define _FPGA_REGION_H
 
@@ -14,7 +16,6 @@
  * @info: FPGA image info
  * @priv: private data
  * @get_bridges: optional function to get bridges to a list
- * @groups: optional attribute groups.
  */
 struct fpga_region {
 	struct device dev;
@@ -24,7 +25,6 @@ struct fpga_region {
 	struct fpga_image_info *info;
 	void *priv;
 	int (*get_bridges)(struct fpga_region *region);
-	const struct attribute_group **groups;
 };
 
 #define to_fpga_region(d) container_of(d, struct fpga_region, dev)
@@ -34,7 +34,12 @@ struct fpga_region *fpga_region_class_find(
 	int (*match)(struct device *, const void *));
 
 int fpga_region_program_fpga(struct fpga_region *region);
-int fpga_region_register(struct device *dev, struct fpga_region *region);
-int fpga_region_unregister(struct fpga_region *region);
+
+struct fpga_region
+*fpga_region_create(struct device *dev, struct fpga_manager *mgr,
+		    int (*get_bridges)(struct fpga_region *));
+void fpga_region_free(struct fpga_region *region);
+int fpga_region_register(struct fpga_region *region);
+void fpga_region_unregister(struct fpga_region *region);
 
 #endif /* _FPGA_REGION_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 760d8da1b6c7..7ef7193488b8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -94,7 +94,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 
 /*
  * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
- * to O_WRONLY and O_RDWR via the strange trick in __dentry_open()
+ * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open()
  */
 
 /* file is open for reading */
@@ -1250,7 +1250,7 @@ static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
 }
 
 struct fasync_struct {
-	spinlock_t		fa_lock;
+	rwlock_t		fa_lock;
 	int			magic;
 	int			fa_fd;
 	struct fasync_struct	*fa_next; /* singly linked list */
@@ -1364,9 +1364,9 @@ struct super_block {
 	void                    *s_security;
 #endif
 	const struct xattr_handler **s_xattr;
-
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 	const struct fscrypt_operations	*s_cop;
-
+#endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
 	struct block_device	*s_bdev;
@@ -1597,6 +1597,11 @@ static inline void sb_start_intwrite(struct super_block *sb)
 	__sb_start_write(sb, SB_FREEZE_FS, true);
 }
 
+static inline int sb_start_intwrite_trylock(struct super_block *sb)
+{
+	return __sb_start_write(sb, SB_FREEZE_FS, false);
+}
+
 
 extern bool inode_owner_or_capable(const struct inode *inode);
 
@@ -1711,6 +1716,8 @@ struct file_operations {
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
+	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -2570,7 +2577,7 @@ extern bool is_bad_inode(struct inode *);
 
 #ifdef CONFIG_BLOCK
 extern void check_disk_size_change(struct gendisk *disk,
-				   struct block_device *bdev);
+		struct block_device *bdev, bool verbose);
 extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
 extern int __invalidate_device(struct block_device *, bool);
diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h
index 44b50c04bae9..25b6492de6e5 100644
--- a/include/linux/fscrypt_notsupp.h
+++ b/include/linux/fscrypt_notsupp.h
@@ -64,16 +64,6 @@ static inline void fscrypt_restore_control_page(struct page *page)
 	return;
 }
 
-static inline void fscrypt_set_d_op(struct dentry *dentry)
-{
-	return;
-}
-
-static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
-{
-	return;
-}
-
 /* policy.c */
 static inline int fscrypt_ioctl_set_policy(struct file *filp,
 					   const void __user *arg)
diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h
index 477a7a6504d2..5080cb1bec4c 100644
--- a/include/linux/fscrypt_supp.h
+++ b/include/linux/fscrypt_supp.h
@@ -29,7 +29,7 @@ struct fscrypt_operations {
 	int (*set_context)(struct inode *, const void *, size_t, void *);
 	bool (*dummy_context)(struct inode *);
 	bool (*empty_dir)(struct inode *);
-	unsigned (*max_namelen)(struct inode *);
+	unsigned int max_namelen;
 };
 
 struct fscrypt_ctx {
@@ -74,20 +74,6 @@ static inline struct page *fscrypt_control_page(struct page *page)
 
 extern void fscrypt_restore_control_page(struct page *);
 
-extern const struct dentry_operations fscrypt_d_ops;
-
-static inline void fscrypt_set_d_op(struct dentry *dentry)
-{
-	d_set_d_op(dentry, &fscrypt_d_ops);
-}
-
-static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
-{
-	spin_lock(&dentry->d_lock);
-	dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
-	spin_unlock(&dentry->d_lock);
-}
-
 /* policy.c */
 extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
 extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 9f1edb92c97e..e64c0294f50b 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -217,12 +217,10 @@ struct fsnotify_mark_connector {
 	union {	/* Object pointer [lock] */
 		struct inode *inode;
 		struct vfsmount *mnt;
-	};
-	union {
-		struct hlist_head list;
 		/* Used listing heads to free after srcu period expires */
 		struct fsnotify_mark_connector *destroy_next;
 	};
+	struct hlist_head list;
 };
 
 /*
@@ -248,7 +246,7 @@ struct fsnotify_mark {
 	/* Group this mark is for. Set on mark creation, stable until last ref
 	 * is dropped */
 	struct fsnotify_group *group;
-	/* List of marks by group->i_fsnotify_marks. Also reused for queueing
+	/* List of marks by group->marks_list. Also reused for queueing
 	 * mark into destroy_list when it's waiting for the end of SRCU period
 	 * before it can be freed. [group->mark_mutex] */
 	struct list_head g_list;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index c826b0b5232a..6cb8a5789668 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -368,7 +368,9 @@ static inline void free_part_stats(struct hd_struct *part)
 	part_stat_add(cpu, gendiskp, field, -subnd)
 
 void part_in_flight(struct request_queue *q, struct hd_struct *part,
-			unsigned int inflight[2]);
+		    unsigned int inflight[2]);
+void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+		       unsigned int inflight[2]);
 void part_dec_in_flight(struct request_queue *q, struct hd_struct *part,
 			int rw);
 void part_inc_in_flight(struct request_queue *q, struct hd_struct *part,
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 1a4582b44d32..fc5ab85278d5 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -464,7 +464,7 @@ static inline struct page *
 __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
-	VM_WARN_ON(!node_online(nid));
+	VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid));
 
 	return __alloc_pages(gfp_mask, order, nid);
 }
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 8da3e1f48195..26240a22978a 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -516,6 +516,12 @@ enum hid_type {
 	HID_TYPE_USBNONE
 };
 
+enum hid_battery_status {
+	HID_BATTERY_UNKNOWN = 0,
+	HID_BATTERY_QUERIED,		/* Kernel explicitly queried battery strength */
+	HID_BATTERY_REPORTED,		/* Device sent unsolicited battery strength report */
+};
+
 struct hid_driver;
 struct hid_ll_driver;
 
@@ -558,7 +564,8 @@ struct hid_device {							/* device report descriptor */
 	__s32 battery_max;
 	__s32 battery_report_type;
 	__s32 battery_report_id;
-	bool battery_reported;
+	enum hid_battery_status battery_status;
+	bool battery_avoid_query;
 #endif
 
 	unsigned int status;						/* see STAT flags above */
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 39988924de3a..2f1327c37a63 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -16,7 +16,7 @@
 /*
  * Heterogeneous Memory Management (HMM)
  *
- * See Documentation/vm/hmm.txt for reasons and overview of what HMM is and it
+ * See Documentation/vm/hmm.rst for reasons and overview of what HMM is and it
  * is for. Here we focus on the HMM API description, with some explanation of
  * the underlying implementation.
  *
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index ddf7f9ca86cc..89110d896d72 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -192,13 +192,6 @@ struct host1x_reloc {
 	unsigned long shift;
 };
 
-struct host1x_waitchk {
-	struct host1x_bo *bo;
-	u32 offset;
-	u32 syncpt_id;
-	u32 thresh;
-};
-
 struct host1x_job {
 	/* When refcount goes to zero, job can be freed */
 	struct kref ref;
@@ -209,19 +202,15 @@ struct host1x_job {
 	/* Channel where job is submitted to */
 	struct host1x_channel *channel;
 
-	u32 client;
+	/* client where the job originated */
+	struct host1x_client *client;
 
 	/* Gathers and their memory */
 	struct host1x_job_gather *gathers;
 	unsigned int num_gathers;
 
-	/* Wait checks to be processed at submit time */
-	struct host1x_waitchk *waitchk;
-	unsigned int num_waitchk;
-	u32 waitchk_mask;
-
 	/* Array of handles to be pinned & unpinned */
-	struct host1x_reloc *relocarray;
+	struct host1x_reloc *relocs;
 	unsigned int num_relocs;
 	struct host1x_job_unpin_data *unpins;
 	unsigned int num_unpins;
@@ -261,10 +250,9 @@ struct host1x_job {
 };
 
 struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
-				    u32 num_cmdbufs, u32 num_relocs,
-				    u32 num_waitchks);
-void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *mem_id,
-			   u32 words, u32 offset);
+				    u32 num_cmdbufs, u32 num_relocs);
+void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *bo,
+			   unsigned int words, unsigned int offset);
 struct host1x_job *host1x_job_get(struct host1x_job *job);
 void host1x_job_put(struct host1x_job *job);
 int host1x_job_pin(struct host1x_job *job, struct device *dev);
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index a2656c3ebe81..3892e9c8b2de 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -161,9 +161,11 @@ struct hrtimer_clock_base {
 enum  hrtimer_base_type {
 	HRTIMER_BASE_MONOTONIC,
 	HRTIMER_BASE_REALTIME,
+	HRTIMER_BASE_BOOTTIME,
 	HRTIMER_BASE_TAI,
 	HRTIMER_BASE_MONOTONIC_SOFT,
 	HRTIMER_BASE_REALTIME_SOFT,
+	HRTIMER_BASE_BOOTTIME_SOFT,
 	HRTIMER_BASE_TAI_SOFT,
 	HRTIMER_MAX_CLOCK_BASES,
 };
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 192ed8fbc403..11b5612dc066 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -163,6 +163,7 @@ static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi)
  * 2 . 4  (Windows 8)
  * 3 . 0  (Windows 8 R2)
  * 4 . 0  (Windows 10)
+ * 5 . 0  (Newer Windows 10)
  */
 
 #define VERSION_WS2008  ((0 << 16) | (13))
@@ -170,10 +171,11 @@ static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi)
 #define VERSION_WIN8    ((2 << 16) | (4))
 #define VERSION_WIN8_1    ((3 << 16) | (0))
 #define VERSION_WIN10	((4 << 16) | (0))
+#define VERSION_WIN10_V5 ((5 << 16) | (0))
 
 #define VERSION_INVAL -1
 
-#define VERSION_CURRENT VERSION_WIN10
+#define VERSION_CURRENT VERSION_WIN10_V5
 
 /* Make maximum size of pipe payload of 16K */
 #define MAX_PIPE_DATA_PAYLOAD		(sizeof(u8) * 16384)
@@ -570,7 +572,14 @@ struct vmbus_channel_initiate_contact {
 	struct vmbus_channel_message_header header;
 	u32 vmbus_version_requested;
 	u32 target_vcpu; /* The VCPU the host should respond to */
-	u64 interrupt_page;
+	union {
+		u64 interrupt_page;
+		struct {
+			u8	msg_sint;
+			u8	padding1[3];
+			u32	padding2;
+		};
+	};
 	u64 monitor_page1;
 	u64 monitor_page2;
 } __packed;
@@ -585,6 +594,19 @@ struct vmbus_channel_tl_connect_request {
 struct vmbus_channel_version_response {
 	struct vmbus_channel_message_header header;
 	u8 version_supported;
+
+	u8 connection_state;
+	u16 padding;
+
+	/*
+	 * On new hosts that support VMBus protocol 5.0, we must use
+	 * VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate Contact Message,
+	 * and for subsequent messages, we must use the Message Connection ID
+	 * field in the host-returned Version Response Message.
+	 *
+	 * On old hosts, we should always use VMBUS_MESSAGE_CONNECTION_ID (1).
+	 */
+	u32 msg_conn_id;
 } __packed;
 
 enum vmbus_channel_state {
diff --git a/include/linux/ide.h b/include/linux/ide.h
index ca9d34feb572..c74b0321922a 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -961,7 +961,7 @@ __IDE_PROC_DEVSET(_name, _min, _max, NULL, NULL)
 typedef struct {
 	const char	*name;
 	umode_t		mode;
-	const struct file_operations *proc_fops;
+	int (*show)(struct seq_file *, void *);
 } ide_proc_entry_t;
 
 void proc_ide_create(void);
@@ -973,8 +973,8 @@ void ide_proc_unregister_port(ide_hwif_t *);
 void ide_proc_register_driver(ide_drive_t *, struct ide_driver *);
 void ide_proc_unregister_driver(ide_drive_t *, struct ide_driver *);
 
-extern const struct file_operations ide_capacity_proc_fops;
-extern const struct file_operations ide_geometry_proc_fops;
+int ide_capacity_proc_show(struct seq_file *m, void *v);
+int ide_geometry_proc_show(struct seq_file *m, void *v);
 #else
 static inline void proc_ide_create(void) { ; }
 static inline void proc_ide_destroy(void) { ; }
@@ -1508,8 +1508,6 @@ static inline void ide_set_hwifdata (ide_hwif_t * hwif, void *data)
 	hwif->hwif_data = data;
 }
 
-extern void ide_toggle_bounce(ide_drive_t *drive, int on);
-
 u64 ide_get_lba_addr(struct ide_cmd *, int);
 u8 ide_dump_status(ide_drive_t *, const char *, u8);
 
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index d11f41d5269f..78a5a90b4267 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -663,7 +663,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb)
  * Returns true if the skb is tagged with multiple vlan headers, regardless
  * of whether it is hardware accelerated or not.
  */
-static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
+static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
 {
 	__be16 protocol = skb->protocol;
 
@@ -673,6 +673,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
 		if (likely(!eth_type_vlan(protocol)))
 			return false;
 
+		if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
+			return false;
+
 		veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
 	}
@@ -690,7 +693,7 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
  *
  * Returns features without unsafe ones if the skb has multiple tags.
  */
-static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
+static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
 						    netdev_features_t features)
 {
 	if (skb_vlan_tagged_multi(skb)) {
diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h
index b9e22b7e2f28..d1171db23742 100644
--- a/include/linux/iio/buffer_impl.h
+++ b/include/linux/iio/buffer_impl.h
@@ -53,7 +53,7 @@ struct iio_buffer_access_funcs {
 	int (*request_update)(struct iio_buffer *buffer);
 
 	int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd);
-	int (*set_length)(struct iio_buffer *buffer, int length);
+	int (*set_length)(struct iio_buffer *buffer, unsigned int length);
 
 	int (*enable)(struct iio_buffer *buffer, struct iio_dev *indio_dev);
 	int (*disable)(struct iio_buffer *buffer, struct iio_dev *indio_dev);
@@ -72,10 +72,10 @@ struct iio_buffer_access_funcs {
  */
 struct iio_buffer {
 	/** @length: Number of datums in buffer. */
-	int length;
+	unsigned int length;
 
 	/**  @bytes_per_datum: Size of individual datum including timestamp. */
-	int bytes_per_datum;
+	size_t bytes_per_datum;
 
 	/**
 	 * @access: Buffer access functions associated with the
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5426627f9c55..eeceac3376fc 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -432,11 +432,18 @@ extern bool force_irqthreads;
 #define force_irqthreads	(0)
 #endif
 
-#ifndef __ARCH_SET_SOFTIRQ_PENDING
-#define set_softirq_pending(x) (local_softirq_pending() = (x))
-#define or_softirq_pending(x)  (local_softirq_pending() |= (x))
+#ifndef local_softirq_pending
+
+#ifndef local_softirq_pending_ref
+#define local_softirq_pending_ref irq_stat.__softirq_pending
 #endif
 
+#define local_softirq_pending()	(__this_cpu_read(local_softirq_pending_ref))
+#define set_softirq_pending(x)	(__this_cpu_write(local_softirq_pending_ref, (x)))
+#define or_softirq_pending(x)	(__this_cpu_or(local_softirq_pending_ref, (x)))
+
+#endif /* local_softirq_pending */
+
 /* Some architectures might implement lazy enabling/disabling of
  * interrupts. In some cases, such as stop_machine, we might want
  * to ensure that after a local_irq_disable(), interrupts have
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 19a07de28212..a044a824da85 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 
+struct address_space;
 struct fiemap_extent_info;
 struct inode;
 struct iov_iter;
@@ -18,6 +19,7 @@ struct vm_fault;
 #define IOMAP_DELALLOC	0x02	/* delayed allocation blocks */
 #define IOMAP_MAPPED	0x03	/* blocks allocated at @addr */
 #define IOMAP_UNWRITTEN	0x04	/* blocks allocated at @addr in unwritten state */
+#define IOMAP_INLINE	0x05	/* data inline in the inode */
 
 /*
  * Flags for all iomap mappings:
@@ -26,15 +28,19 @@ struct vm_fault;
  * written data and requires fdatasync to commit them to persistent storage.
  */
 #define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
-#define IOMAP_F_BOUNDARY	0x02	/* mapping ends at metadata boundary */
-#define IOMAP_F_DIRTY		0x04	/* uncommitted metadata */
+#define IOMAP_F_DIRTY		0x02	/* uncommitted metadata */
 
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests:
  */
 #define IOMAP_F_MERGED		0x10	/* contains multiple blocks/extents */
 #define IOMAP_F_SHARED		0x20	/* block shared with another file */
-#define IOMAP_F_DATA_INLINE	0x40	/* data inline in the inode */
+
+/*
+ * Flags from 0x1000 up are for file system specific usage:
+ */
+#define IOMAP_F_PRIVATE		0x1000
+
 
 /*
  * Magic value for addr:
@@ -59,7 +65,7 @@ struct iomap {
 #define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
 #define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
 #define IOMAP_DIRECT		(1 << 4) /* direct I/O */
-#define IOMAP_NOWAIT		(1 << 5) /* Don't wait for writeback */
+#define IOMAP_NOWAIT		(1 << 5) /* do not block */
 
 struct iomap_ops {
 	/*
@@ -95,6 +101,8 @@ loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
 		const struct iomap_ops *ops);
 loff_t iomap_seek_data(struct inode *inode, loff_t offset,
 		const struct iomap_ops *ops);
+sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
+		const struct iomap_ops *ops);
 
 /*
  * Flags for direct I/O ->end_io:
@@ -106,4 +114,15 @@ typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t ret,
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, iomap_dio_end_io_t end_io);
 
+#ifdef CONFIG_SWAP
+struct file;
+struct swap_info_struct;
+
+int iomap_swapfile_activate(struct swap_info_struct *sis,
+		struct file *swap_file, sector_t *pagespan,
+		const struct iomap_ops *ops);
+#else
+# define iomap_swapfile_activate(sis, swapfile, pagespan, ops)	(-EIO)
+#endif /* CONFIG_SWAP */
+
 #endif /* LINUX_IOMAP_H */
diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h
index cb9a9248c8c0..70d01edcbf8b 100644
--- a/include/linux/iommu-helper.h
+++ b/include/linux/iommu-helper.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_IOMMU_HELPER_H
 #define _LINUX_IOMMU_HELPER_H
 
+#include <linux/bug.h>
 #include <linux/kernel.h>
 
 static inline unsigned long iommu_device_max_index(unsigned long size,
@@ -14,9 +15,15 @@ static inline unsigned long iommu_device_max_index(unsigned long size,
 		return size;
 }
 
-extern int iommu_is_span_boundary(unsigned int index, unsigned int nr,
-				  unsigned long shift,
-				  unsigned long boundary_size);
+static inline int iommu_is_span_boundary(unsigned int index, unsigned int nr,
+		unsigned long shift, unsigned long boundary_size)
+{
+	BUG_ON(!is_power_of_2(boundary_size));
+
+	shift = (shift + index) & (boundary_size - 1);
+	return shift + nr > boundary_size;
+}
+
 extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
 				      unsigned long start, unsigned int nr,
 				      unsigned long shift,
diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index 8b0626cec980..41f5c086f670 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -23,8 +23,10 @@
 struct module;
 struct device;
 
-/* Opaque type for a IPMI message user.  One of these is needed to
-   send and receive messages. */
+/*
+ * Opaque type for a IPMI message user.  One of these is needed to
+ * send and receive messages.
+ */
 typedef struct ipmi_user *ipmi_user_t;
 
 /*
@@ -37,28 +39,36 @@ typedef struct ipmi_user *ipmi_user_t;
 struct ipmi_recv_msg {
 	struct list_head link;
 
-	/* The type of message as defined in the "Receive Types"
-	   defines above. */
+	/*
+	 * The type of message as defined in the "Receive Types"
+	 * defines above.
+	 */
 	int              recv_type;
 
-	ipmi_user_t      user;
+	struct ipmi_user *user;
 	struct ipmi_addr addr;
 	long             msgid;
 	struct kernel_ipmi_msg  msg;
 
-	/* The user_msg_data is the data supplied when a message was
-	   sent, if this is a response to a sent message.  If this is
-	   not a response to a sent message, then user_msg_data will
-	   be NULL.  If the user above is NULL, then this will be the
-	   intf. */
+	/*
+	 * The user_msg_data is the data supplied when a message was
+	 * sent, if this is a response to a sent message.  If this is
+	 * not a response to a sent message, then user_msg_data will
+	 * be NULL.  If the user above is NULL, then this will be the
+	 * intf.
+	 */
 	void             *user_msg_data;
 
-	/* Call this when done with the message.  It will presumably free
-	   the message and do any other necessary cleanup. */
+	/*
+	 * Call this when done with the message.  It will presumably free
+	 * the message and do any other necessary cleanup.
+	 */
 	void (*done)(struct ipmi_recv_msg *msg);
 
-	/* Place-holder for the data, don't make any assumptions about
-	   the size or existence of this, since it may change. */
+	/*
+	 * Place-holder for the data, don't make any assumptions about
+	 * the size or existence of this, since it may change.
+	 */
 	unsigned char   msg_data[IPMI_MAX_MSG_LENGTH];
 };
 
@@ -66,54 +76,77 @@ struct ipmi_recv_msg {
 void ipmi_free_recv_msg(struct ipmi_recv_msg *msg);
 
 struct ipmi_user_hndl {
-	/* Routine type to call when a message needs to be routed to
-	   the upper layer.  This will be called with some locks held,
-	   the only IPMI routines that can be called are ipmi_request
-	   and the alloc/free operations.  The handler_data is the
-	   variable supplied when the receive handler was registered. */
+	/*
+	 * Routine type to call when a message needs to be routed to
+	 * the upper layer.  This will be called with some locks held,
+	 * the only IPMI routines that can be called are ipmi_request
+	 * and the alloc/free operations.  The handler_data is the
+	 * variable supplied when the receive handler was registered.
+	 */
 	void (*ipmi_recv_hndl)(struct ipmi_recv_msg *msg,
 			       void                 *user_msg_data);
 
-	/* Called when the interface detects a watchdog pre-timeout.  If
-	   this is NULL, it will be ignored for the user. */
+	/*
+	 * Called when the interface detects a watchdog pre-timeout.  If
+	 * this is NULL, it will be ignored for the user.
+	 */
 	void (*ipmi_watchdog_pretimeout)(void *handler_data);
+
+	/*
+	 * If not NULL, called at panic time after the interface has
+	 * been set up to handle run to completion.
+	 */
+	void (*ipmi_panic_handler)(void *handler_data);
+
+	/*
+	 * Called when the interface has been removed.  After this returns
+	 * the user handle will be invalid.  The interface may or may
+	 * not be usable when this is called, but it will return errors
+	 * if it is not usable.
+	 */
+	void (*shutdown)(void *handler_data);
 };
 
 /* Create a new user of the IPMI layer on the given interface number. */
 int ipmi_create_user(unsigned int          if_num,
 		     const struct ipmi_user_hndl *handler,
 		     void                  *handler_data,
-		     ipmi_user_t           *user);
+		     struct ipmi_user      **user);
 
-/* Destroy the given user of the IPMI layer.  Note that after this
-   function returns, the system is guaranteed to not call any
-   callbacks for the user.  Thus as long as you destroy all the users
-   before you unload a module, you will be safe.  And if you destroy
-   the users before you destroy the callback structures, it should be
-   safe, too. */
-int ipmi_destroy_user(ipmi_user_t user);
+/*
+ * Destroy the given user of the IPMI layer.  Note that after this
+ * function returns, the system is guaranteed to not call any
+ * callbacks for the user.  Thus as long as you destroy all the users
+ * before you unload a module, you will be safe.  And if you destroy
+ * the users before you destroy the callback structures, it should be
+ * safe, too.
+ */
+int ipmi_destroy_user(struct ipmi_user *user);
 
 /* Get the IPMI version of the BMC we are talking to. */
-int ipmi_get_version(ipmi_user_t   user,
+int ipmi_get_version(struct ipmi_user *user,
 		     unsigned char *major,
 		     unsigned char *minor);
 
-/* Set and get the slave address and LUN that we will use for our
-   source messages.  Note that this affects the interface, not just
-   this user, so it will affect all users of this interface.  This is
-   so some initialization code can come in and do the OEM-specific
-   things it takes to determine your address (if not the BMC) and set
-   it for everyone else.  Note that each channel can have its own address. */
-int ipmi_set_my_address(ipmi_user_t   user,
+/*
+ * Set and get the slave address and LUN that we will use for our
+ * source messages.  Note that this affects the interface, not just
+ * this user, so it will affect all users of this interface.  This is
+ * so some initialization code can come in and do the OEM-specific
+ * things it takes to determine your address (if not the BMC) and set
+ * it for everyone else.  Note that each channel can have its own
+ * address.
+ */
+int ipmi_set_my_address(struct ipmi_user *user,
 			unsigned int  channel,
 			unsigned char address);
-int ipmi_get_my_address(ipmi_user_t   user,
+int ipmi_get_my_address(struct ipmi_user *user,
 			unsigned int  channel,
 			unsigned char *address);
-int ipmi_set_my_LUN(ipmi_user_t   user,
+int ipmi_set_my_LUN(struct ipmi_user *user,
 		    unsigned int  channel,
 		    unsigned char LUN);
-int ipmi_get_my_LUN(ipmi_user_t   user,
+int ipmi_get_my_LUN(struct ipmi_user *user,
 		    unsigned int  channel,
 		    unsigned char *LUN);
 
@@ -130,7 +163,7 @@ int ipmi_get_my_LUN(ipmi_user_t   user,
  * it makes no sense to do it here.  However, this can be used if you
  * have unusual requirements.
  */
-int ipmi_request_settime(ipmi_user_t      user,
+int ipmi_request_settime(struct ipmi_user *user,
 			 struct ipmi_addr *addr,
 			 long             msgid,
 			 struct kernel_ipmi_msg  *msg,
@@ -148,7 +181,7 @@ int ipmi_request_settime(ipmi_user_t      user,
  * change as the system changes, so don't use it unless you REALLY
  * have to.
  */
-int ipmi_request_supply_msgs(ipmi_user_t          user,
+int ipmi_request_supply_msgs(struct ipmi_user     *user,
 			     struct ipmi_addr     *addr,
 			     long                 msgid,
 			     struct kernel_ipmi_msg *msg,
@@ -164,7 +197,7 @@ int ipmi_request_supply_msgs(ipmi_user_t          user,
  * way.  This is useful if you need to spin waiting for something to
  * happen in the IPMI driver.
  */
-void ipmi_poll_interface(ipmi_user_t user);
+void ipmi_poll_interface(struct ipmi_user *user);
 
 /*
  * When commands come in to the SMS, the user can register to receive
@@ -175,11 +208,11 @@ void ipmi_poll_interface(ipmi_user_t user);
  * error.  Channels are specified as a bitfield, use IPMI_CHAN_ALL to
  * mean all channels.
  */
-int ipmi_register_for_cmd(ipmi_user_t   user,
+int ipmi_register_for_cmd(struct ipmi_user *user,
 			  unsigned char netfn,
 			  unsigned char cmd,
 			  unsigned int  chans);
-int ipmi_unregister_for_cmd(ipmi_user_t   user,
+int ipmi_unregister_for_cmd(struct ipmi_user *user,
 			    unsigned char netfn,
 			    unsigned char cmd,
 			    unsigned int  chans);
@@ -210,8 +243,8 @@ int ipmi_unregister_for_cmd(ipmi_user_t   user,
  *
  * See the IPMI_MAINTENANCE_MODE_xxx defines for what the mode means.
  */
-int ipmi_get_maintenance_mode(ipmi_user_t user);
-int ipmi_set_maintenance_mode(ipmi_user_t user, int mode);
+int ipmi_get_maintenance_mode(struct ipmi_user *user);
+int ipmi_set_maintenance_mode(struct ipmi_user *user, int mode);
 
 /*
  * When the user is created, it will not receive IPMI events by
@@ -219,7 +252,7 @@ int ipmi_set_maintenance_mode(ipmi_user_t user, int mode);
  * The first user that sets this to TRUE will receive all events that
  * have been queued while no one was waiting for events.
  */
-int ipmi_set_gets_events(ipmi_user_t user, bool val);
+int ipmi_set_gets_events(struct ipmi_user *user, bool val);
 
 /*
  * Called when a new SMI is registered.  This will also be called on
@@ -229,14 +262,18 @@ int ipmi_set_gets_events(ipmi_user_t user, bool val);
 struct ipmi_smi_watcher {
 	struct list_head link;
 
-	/* You must set the owner to the current module, if you are in
-	   a module (generally just set it to "THIS_MODULE"). */
+	/*
+	 * You must set the owner to the current module, if you are in
+	 * a module (generally just set it to "THIS_MODULE").
+	 */
 	struct module *owner;
 
-	/* These two are called with read locks held for the interface
-	   the watcher list.  So you can add and remove users from the
-	   IPMI interface, send messages, etc., but you cannot add
-	   or remove SMI watchers or SMI interfaces. */
+	/*
+	 * These two are called with read locks held for the interface
+	 * the watcher list.  So you can add and remove users from the
+	 * IPMI interface, send messages, etc., but you cannot add
+	 * or remove SMI watchers or SMI interfaces.
+	 */
 	void (*new_smi)(int if_num, struct device *dev);
 	void (*smi_gone)(int if_num);
 };
@@ -244,8 +281,10 @@ struct ipmi_smi_watcher {
 int ipmi_smi_watcher_register(struct ipmi_smi_watcher *watcher);
 int ipmi_smi_watcher_unregister(struct ipmi_smi_watcher *watcher);
 
-/* The following are various helper functions for dealing with IPMI
-   addresses. */
+/*
+ * The following are various helper functions for dealing with IPMI
+ * addresses.
+ */
 
 /* Return the maximum length of an IPMI address given it's type. */
 unsigned int ipmi_addr_length(int addr_type);
@@ -291,7 +330,7 @@ struct ipmi_smi_info {
 	union ipmi_smi_info_union addr_info;
 };
 
-/* This is to get the private info of ipmi_smi_t */
+/* This is to get the private info of struct ipmi_smi */
 extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data);
 
 #endif /* __LINUX_IPMI_H */
diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h
index af457b5a689e..7d5fd38d5282 100644
--- a/include/linux/ipmi_smi.h
+++ b/include/linux/ipmi_smi.h
@@ -22,8 +22,10 @@
 
 struct device;
 
-/* This files describes the interface for IPMI system management interface
-   drivers to bind into the IPMI message handler. */
+/*
+ * This files describes the interface for IPMI system management interface
+ * drivers to bind into the IPMI message handler.
+ */
 
 /* Structure for the low-level drivers. */
 typedef struct ipmi_smi *ipmi_smi_t;
@@ -61,12 +63,20 @@ struct ipmi_smi_msg {
 struct ipmi_smi_handlers {
 	struct module *owner;
 
-	/* The low-level interface cannot start sending messages to
-	   the upper layer until this function is called.  This may
-	   not be NULL, the lower layer must take the interface from
-	   this call. */
-	int (*start_processing)(void       *send_info,
-				ipmi_smi_t new_intf);
+	/*
+	 * The low-level interface cannot start sending messages to
+	 * the upper layer until this function is called.  This may
+	 * not be NULL, the lower layer must take the interface from
+	 * this call.
+	 */
+	int (*start_processing)(void            *send_info,
+				struct ipmi_smi *new_intf);
+
+	/*
+	 * When called, the low-level interface should disable all
+	 * processing, it should be complete shut down when it returns.
+	 */
+	void (*shutdown)(void *send_info);
 
 	/*
 	 * Get the detailed private info of the low level interface and store
@@ -75,25 +85,31 @@ struct ipmi_smi_handlers {
 	 */
 	int (*get_smi_info)(void *send_info, struct ipmi_smi_info *data);
 
-	/* Called to enqueue an SMI message to be sent.  This
-	   operation is not allowed to fail.  If an error occurs, it
-	   should report back the error in a received message.  It may
-	   do this in the current call context, since no write locks
-	   are held when this is run.  Message are delivered one at
-	   a time by the message handler, a new message will not be
-	   delivered until the previous message is returned. */
+	/*
+	 * Called to enqueue an SMI message to be sent.  This
+	 * operation is not allowed to fail.  If an error occurs, it
+	 * should report back the error in a received message.  It may
+	 * do this in the current call context, since no write locks
+	 * are held when this is run.  Message are delivered one at
+	 * a time by the message handler, a new message will not be
+	 * delivered until the previous message is returned.
+	 */
 	void (*sender)(void                *send_info,
 		       struct ipmi_smi_msg *msg);
 
-	/* Called by the upper layer to request that we try to get
-	   events from the BMC we are attached to. */
+	/*
+	 * Called by the upper layer to request that we try to get
+	 * events from the BMC we are attached to.
+	 */
 	void (*request_events)(void *send_info);
 
-	/* Called by the upper layer when some user requires that the
-	   interface watch for events, received messages, watchdog
-	   pretimeouts, or not.  Used by the SMI to know if it should
-	   watch for these.  This may be NULL if the SMI does not
-	   implement it. */
+	/*
+	 * Called by the upper layer when some user requires that the
+	 * interface watch for events, received messages, watchdog
+	 * pretimeouts, or not.  Used by the SMI to know if it should
+	 * watch for these.  This may be NULL if the SMI does not
+	 * implement it.
+	 */
 	void (*set_need_watch)(void *send_info, bool enable);
 
 	/*
@@ -101,30 +117,29 @@ struct ipmi_smi_handlers {
 	 */
 	void (*flush_messages)(void *send_info);
 
-	/* Called when the interface should go into "run to
-	   completion" mode.  If this call sets the value to true, the
-	   interface should make sure that all messages are flushed
-	   out and that none are pending, and any new requests are run
-	   to completion immediately. */
+	/*
+	 * Called when the interface should go into "run to
+	 * completion" mode.  If this call sets the value to true, the
+	 * interface should make sure that all messages are flushed
+	 * out and that none are pending, and any new requests are run
+	 * to completion immediately.
+	 */
 	void (*set_run_to_completion)(void *send_info, bool run_to_completion);
 
-	/* Called to poll for work to do.  This is so upper layers can
-	   poll for operations during things like crash dumps. */
+	/*
+	 * Called to poll for work to do.  This is so upper layers can
+	 * poll for operations during things like crash dumps.
+	 */
 	void (*poll)(void *send_info);
 
-	/* Enable/disable firmware maintenance mode.  Note that this
-	   is *not* the modes defined, this is simply an on/off
-	   setting.  The message handler does the mode handling.  Note
-	   that this is called from interrupt context, so it cannot
-	   block. */
+	/*
+	 * Enable/disable firmware maintenance mode.  Note that this
+	 * is *not* the modes defined, this is simply an on/off
+	 * setting.  The message handler does the mode handling.  Note
+	 * that this is called from interrupt context, so it cannot
+	 * block.
+	 */
 	void (*set_maintenance_mode)(void *send_info, bool enable);
-
-	/* Tell the handler that we are using it/not using it.  The
-	   message handler get the modules that this handler belongs
-	   to; this function lets the SMI claim any modules that it
-	   uses.  These may be NULL if this is not required. */
-	int (*inc_usecount)(void *send_info);
-	void (*dec_usecount)(void *send_info);
 };
 
 struct ipmi_device_id {
@@ -143,7 +158,8 @@ struct ipmi_device_id {
 #define ipmi_version_major(v) ((v)->ipmi_version & 0xf)
 #define ipmi_version_minor(v) ((v)->ipmi_version >> 4)
 
-/* Take a pointer to an IPMI response and extract device id information from
+/*
+ * Take a pointer to an IPMI response and extract device id information from
  * it. @netfn is in the IPMI_NETFN_ format, so may need to be shifted from
  * a SI response.
  */
@@ -187,12 +203,14 @@ static inline int ipmi_demangle_device_id(uint8_t netfn, uint8_t cmd,
 	return 0;
 }
 
-/* Add a low-level interface to the IPMI driver.  Note that if the
-   interface doesn't know its slave address, it should pass in zero.
-   The low-level interface should not deliver any messages to the
-   upper layer until the start_processing() function in the handlers
-   is called, and the lower layer must get the interface from that
-   call. */
+/*
+ * Add a low-level interface to the IPMI driver.  Note that if the
+ * interface doesn't know its slave address, it should pass in zero.
+ * The low-level interface should not deliver any messages to the
+ * upper layer until the start_processing() function in the handlers
+ * is called, and the lower layer must get the interface from that
+ * call.
+ */
 int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
 		      void                     *send_info,
 		      struct device            *dev,
@@ -202,7 +220,7 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
  * Remove a low-level interface from the IPMI driver.  This will
  * return an error if the interface is still in use by a user.
  */
-int ipmi_unregister_smi(ipmi_smi_t intf);
+void ipmi_unregister_smi(struct ipmi_smi *intf);
 
 /*
  * The lower layer reports received messages through this interface.
@@ -210,11 +228,11 @@ int ipmi_unregister_smi(ipmi_smi_t intf);
  * the lower layer gets an error sending a message, it should format
  * an error response in the message response.
  */
-void ipmi_smi_msg_received(ipmi_smi_t          intf,
+void ipmi_smi_msg_received(struct ipmi_smi     *intf,
 			   struct ipmi_smi_msg *msg);
 
 /* The lower layer received a watchdog pre-timeout on interface. */
-void ipmi_smi_watchdog_pretimeout(ipmi_smi_t intf);
+void ipmi_smi_watchdog_pretimeout(struct ipmi_smi *intf);
 
 struct ipmi_smi_msg *ipmi_alloc_smi_msg(void);
 static inline void ipmi_free_smi_msg(struct ipmi_smi_msg *msg)
@@ -222,13 +240,4 @@ static inline void ipmi_free_smi_msg(struct ipmi_smi_msg *msg)
 	msg->done(msg);
 }
 
-#ifdef CONFIG_IPMI_PROC_INTERFACE
-/* Allow the lower layer to add things to the proc filesystem
-   directory for this interface.  Note that the entry will
-   automatically be dstroyed when the interface is destroyed. */
-int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name,
-			    const struct file_operations *proc_ops,
-			    void *data);
-#endif
-
 #endif /* __LINUX_IPMI_SMI_H */
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 65916a305f3d..b2067083aa94 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -512,6 +512,7 @@ enum {
 	IRQCHIP_SKIP_SET_WAKE		= (1 <<  4),
 	IRQCHIP_ONESHOT_SAFE		= (1 <<  5),
 	IRQCHIP_EOI_THREADED		= (1 <<  6),
+	IRQCHIP_SUPPORTS_LEVEL_MSI	= (1 <<  7),
 };
 
 #include <linux/irqdesc.h>
diff --git a/include/linux/irq_cpustat.h b/include/linux/irq_cpustat.h
index 4954948d1973..6e8895cd4d92 100644
--- a/include/linux/irq_cpustat.h
+++ b/include/linux/irq_cpustat.h
@@ -18,15 +18,11 @@
  */
 
 #ifndef __ARCH_IRQ_STAT
-extern irq_cpustat_t irq_stat[];		/* defined in asm/hardirq.h */
-#define __IRQ_STAT(cpu, member)	(irq_stat[cpu].member)
+DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);	/* defined in asm/hardirq.h */
+#define __IRQ_STAT(cpu, member)	(per_cpu(irq_stat.member, cpu))
 #endif
 
-  /* arch independent irq_stat fields */
-#define local_softirq_pending() \
-	__IRQ_STAT(smp_processor_id(), __softirq_pending)
-
-  /* arch dependent irq_stat fields */
+/* arch dependent irq_stat fields */
 #define nmi_count(cpu)		__IRQ_STAT((cpu), __nmi_count)	/* i386 */
 
 #endif	/* __irq_cpustat_h */
diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h
index 0380d899b955..630a57e55db6 100644
--- a/include/linux/irq_sim.h
+++ b/include/linux/irq_sim.h
@@ -1,14 +1,11 @@
-#ifndef _LINUX_IRQ_SIM_H
-#define _LINUX_IRQ_SIM_H
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
- * Copyright (C) 2017 Bartosz Golaszewski <brgl@bgdev.pl>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
+ * Copyright (C) 2017-2018 Bartosz Golaszewski <brgl@bgdev.pl>
  */
 
+#ifndef _LINUX_IRQ_SIM_H
+#define _LINUX_IRQ_SIM_H
+
 #include <linux/irq_work.h>
 #include <linux/device.h>
 
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index f5af3b594e6e..cbb872c1b607 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -587,6 +587,7 @@ struct fwnode_handle;
 int its_cpu_init(void);
 int its_init(struct fwnode_handle *handle, struct rdists *rdists,
 	     struct irq_domain *domain);
+int mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent);
 
 static inline bool gic_enable_sre(void)
 {
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 48c7e86bb556..dccfa65aee96 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -301,7 +301,13 @@ static inline struct irq_domain *irq_find_matching_host(struct device_node *node
 
 static inline struct irq_domain *irq_find_host(struct device_node *node)
 {
-	return irq_find_matching_host(node, DOMAIN_BUS_ANY);
+	struct irq_domain *d;
+
+	d = irq_find_matching_host(node, DOMAIN_BUS_WIRED);
+	if (!d)
+		d = irq_find_matching_host(node, DOMAIN_BUS_ANY);
+
+	return d;
 }
 
 /**
diff --git a/include/linux/isdn/capilli.h b/include/linux/isdn/capilli.h
index 11b57c485854..d75e1ad72964 100644
--- a/include/linux/isdn/capilli.h
+++ b/include/linux/isdn/capilli.h
@@ -50,7 +50,7 @@ struct capi_ctr {
 	u16  (*send_message)(struct capi_ctr *, struct sk_buff *skb);
 	
 	char *(*procinfo)(struct capi_ctr *);
-	const struct file_operations *proc_fops;
+	int (*proc_show)(struct seq_file *, void *);
 
 	/* filled in before calling ready callback */
 	u8 manu[CAPI_MANUFACTURER_LEN];		/* CAPI_GET_MANUFACTURER */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 6a1eb0b0aad9..7aed92624531 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -542,6 +542,7 @@ extern enum system_states {
 	SYSTEM_HALT,
 	SYSTEM_POWER_OFF,
 	SYSTEM_RESTART,
+	SYSTEM_SUSPEND,
 } system_state;
 
 /* This cannot be an enum because some may be used in assembly source. */
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index c1961761311d..2803264c512f 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -62,6 +62,7 @@ void *kthread_probe_data(struct task_struct *k);
 int kthread_park(struct task_struct *k);
 void kthread_unpark(struct task_struct *k);
 void kthread_parkme(void);
+void kthread_park_complete(struct task_struct *k);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6930c63126c7..6d6e79c59e68 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1045,13 +1045,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 
-#ifdef CONFIG_S390
-#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that...
-#elif defined(CONFIG_ARM64)
-#define KVM_MAX_IRQ_ROUTES 4096
-#else
-#define KVM_MAX_IRQ_ROUTES 1024
-#endif
+#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */
 
 bool kvm_arch_can_set_irq_routing(struct kvm *kvm);
 int kvm_set_irq_routing(struct kvm *kvm,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 1795fecdea17..9db904344c75 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -125,9 +125,8 @@ enum {
 	LIBATA_MAX_PRD		= ATA_MAX_PRD / 2,
 	LIBATA_DUMB_MAX_PRD	= ATA_MAX_PRD / 4,	/* Worst case */
 	ATA_DEF_QUEUE		= 1,
-	/* tag ATA_MAX_QUEUE - 1 is reserved for internal commands */
 	ATA_MAX_QUEUE		= 32,
-	ATA_TAG_INTERNAL	= ATA_MAX_QUEUE - 1,
+	ATA_TAG_INTERNAL	= ATA_MAX_QUEUE,
 	ATA_SHORT_PAUSE		= 16,
 
 	ATAPI_MAX_DRAIN		= 16 << 10,
@@ -637,7 +636,8 @@ struct ata_queued_cmd {
 	u8			cdb[ATAPI_CDB_LEN];
 
 	unsigned long		flags;		/* ATA_QCFLAG_xxx */
-	unsigned int		tag;
+	unsigned int		tag;		/* libata core tag */
+	unsigned int		hw_tag;		/* driver tag */
 	unsigned int		n_elem;
 	unsigned int		orig_n_elem;
 
@@ -849,9 +849,9 @@ struct ata_port {
 	unsigned int		udma_mask;
 	unsigned int		cbl;	/* cable type; ATA_CBL_xxx */
 
-	struct ata_queued_cmd	qcmd[ATA_MAX_QUEUE];
+	struct ata_queued_cmd	qcmd[ATA_MAX_QUEUE + 1];
 	unsigned long		sas_tag_allocated; /* for sas tag allocation only */
-	unsigned int		qc_active;
+	u64			qc_active;
 	int			nr_active_links; /* #links with active qcs */
 	unsigned int		sas_last_tag;	/* track next tag hw expects */
 
@@ -1133,7 +1133,6 @@ extern int ata_sas_port_start(struct ata_port *ap);
 extern void ata_sas_port_stop(struct ata_port *ap);
 extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *);
 extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap);
-extern enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd);
 extern int sata_scr_valid(struct ata_link *link);
 extern int sata_scr_read(struct ata_link *link, int reg, u32 *val);
 extern int sata_scr_write(struct ata_link *link, int reg, u32 val);
@@ -1184,7 +1183,7 @@ extern void ata_id_c_string(const u16 *id, unsigned char *s,
 extern unsigned int ata_do_dev_read_id(struct ata_device *dev,
 					struct ata_taskfile *tf, u16 *id);
 extern void ata_qc_complete(struct ata_queued_cmd *qc);
-extern int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active);
+extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active);
 extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd);
 extern int ata_std_bios_param(struct scsi_device *sdev,
 			      struct block_device *bdev,
@@ -1359,7 +1358,6 @@ extern struct device_attribute *ata_common_sdev_attrs[];
 	.proc_name		= drv_name,			\
 	.slave_configure	= ata_scsi_slave_config,	\
 	.slave_destroy		= ata_scsi_slave_destroy,	\
-	.eh_timed_out		= ata_scsi_timed_out,		\
 	.bios_param		= ata_std_bios_param,		\
 	.unlock_native_capacity	= ata_scsi_unlock_native_capacity, \
 	.sdev_attrs		= ata_common_sdev_attrs
@@ -1485,14 +1483,14 @@ extern void ata_port_pbar_desc(struct ata_port *ap, int bar, ssize_t offset,
 			       const char *name);
 #endif
 
-static inline unsigned int ata_tag_valid(unsigned int tag)
+static inline bool ata_tag_internal(unsigned int tag)
 {
-	return (tag < ATA_MAX_QUEUE) ? 1 : 0;
+	return tag == ATA_TAG_INTERNAL;
 }
 
-static inline unsigned int ata_tag_internal(unsigned int tag)
+static inline bool ata_tag_valid(unsigned int tag)
 {
-	return tag == ATA_TAG_INTERNAL;
+	return tag < ATA_MAX_QUEUE || ata_tag_internal(tag);
 }
 
 /*
@@ -1655,7 +1653,7 @@ static inline void ata_qc_set_polling(struct ata_queued_cmd *qc)
 static inline struct ata_queued_cmd *__ata_qc_from_tag(struct ata_port *ap,
 						       unsigned int tag)
 {
-	if (likely(ata_tag_valid(tag)))
+	if (ata_tag_valid(tag))
 		return &ap->qcmd[tag];
 	return NULL;
 }
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 6e0859b9d4d2..e9e0d1c7eaf5 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -489,7 +489,7 @@ typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
 typedef sector_t (nvm_tgt_capacity_fn)(void *);
 typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *,
 				int flags);
-typedef void (nvm_tgt_exit_fn)(void *);
+typedef void (nvm_tgt_exit_fn)(void *, bool);
 typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *);
 typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *);
 
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index 4754f01c1abb..aec44b1d9582 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -186,13 +186,20 @@ static inline bool klp_have_reliable_stack(void)
 	       IS_ENABLED(CONFIG_HAVE_RELIABLE_STACKTRACE);
 }
 
+typedef int (*klp_shadow_ctor_t)(void *obj,
+				 void *shadow_data,
+				 void *ctor_data);
+typedef void (*klp_shadow_dtor_t)(void *obj, void *shadow_data);
+
 void *klp_shadow_get(void *obj, unsigned long id);
-void *klp_shadow_alloc(void *obj, unsigned long id, void *data,
-		       size_t size, gfp_t gfp_flags);
-void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
-			      size_t size, gfp_t gfp_flags);
-void klp_shadow_free(void *obj, unsigned long id);
-void klp_shadow_free_all(unsigned long id);
+void *klp_shadow_alloc(void *obj, unsigned long id,
+		       size_t size, gfp_t gfp_flags,
+		       klp_shadow_ctor_t ctor, void *ctor_data);
+void *klp_shadow_get_or_alloc(void *obj, unsigned long id,
+			      size_t size, gfp_t gfp_flags,
+			      klp_shadow_ctor_t ctor, void *ctor_data);
+void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor);
+void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor);
 
 #else /* !CONFIG_LIVEPATCH */
 
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 9d0b286f3dba..8f1131c8dd54 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -757,6 +757,11 @@
  *	@type contains the requested communications type.
  *	@protocol contains the requested protocol.
  *	@kern set to 1 if a kernel socket.
+ * @socket_socketpair:
+ *	Check permissions before creating a fresh pair of sockets.
+ *	@socka contains the first socket structure.
+ *	@sockb contains the second socket structure.
+ *	Return 0 if permission is granted and the connection was established.
  * @socket_bind:
  *	Check permission before socket protocol layer bind operation is
  *	performed and the socket @sock is bound to the address specified in the
@@ -1656,6 +1661,7 @@ union security_list_options {
 	int (*socket_create)(int family, int type, int protocol, int kern);
 	int (*socket_post_create)(struct socket *sock, int family, int type,
 					int protocol, int kern);
+	int (*socket_socketpair)(struct socket *socka, struct socket *sockb);
 	int (*socket_bind)(struct socket *sock, struct sockaddr *address,
 				int addrlen);
 	int (*socket_connect)(struct socket *sock, struct sockaddr *address,
@@ -1922,6 +1928,7 @@ struct security_hook_heads {
 	struct hlist_head unix_may_send;
 	struct hlist_head socket_create;
 	struct hlist_head socket_post_create;
+	struct hlist_head socket_socketpair;
 	struct hlist_head socket_bind;
 	struct hlist_head socket_connect;
 	struct hlist_head socket_listen;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index e0e49b5b1ee1..2b0265265c28 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -216,6 +216,9 @@ void put_online_mems(void);
 void mem_hotplug_begin(void);
 void mem_hotplug_done(void);
 
+extern void set_zone_contiguous(struct zone *zone);
+extern void clear_zone_contiguous(struct zone *zone);
+
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 #define pfn_to_online_page(pfn)			\
 ({						\
diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index b51f5c430c26..0c964ac107c2 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -25,6 +25,18 @@ typedef struct mempool_s {
 	wait_queue_head_t wait;
 } mempool_t;
 
+static inline bool mempool_initialized(mempool_t *pool)
+{
+	return pool->elements != NULL;
+}
+
+void mempool_exit(mempool_t *pool);
+int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
+		      mempool_free_t *free_fn, void *pool_data,
+		      gfp_t gfp_mask, int node_id);
+int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
+		 mempool_free_t *free_fn, void *pool_data);
+
 extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
 			mempool_free_t *free_fn, void *pool_data);
 extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
@@ -43,6 +55,14 @@ extern void mempool_free(void *element, mempool_t *pool);
  */
 void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data);
 void mempool_free_slab(void *element, void *pool_data);
+
+static inline int
+mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc)
+{
+	return mempool_init(pool, min_nr, mempool_alloc_slab,
+			    mempool_free_slab, (void *) kc);
+}
+
 static inline mempool_t *
 mempool_create_slab_pool(int min_nr, struct kmem_cache *kc)
 {
@@ -56,6 +76,13 @@ mempool_create_slab_pool(int min_nr, struct kmem_cache *kc)
  */
 void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data);
 void mempool_kfree(void *element, void *pool_data);
+
+static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size)
+{
+	return mempool_init(pool, min_nr, mempool_kmalloc,
+			    mempool_kfree, (void *) size);
+}
+
 static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size)
 {
 	return mempool_create(min_nr, mempool_kmalloc, mempool_kfree,
@@ -68,6 +95,13 @@ static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size)
  */
 void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data);
 void mempool_free_pages(void *element, void *pool_data);
+
+static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order)
+{
+	return mempool_init(pool, min_nr, mempool_alloc_pages,
+			    mempool_free_pages, (void *)(long)order);
+}
+
 static inline mempool_t *mempool_create_page_pool(int min_nr, int order)
 {
 	return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages,
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 7b4899c06f49..74ea5e2310a8 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -45,7 +45,7 @@ struct vmem_altmap {
  * must be treated as an opaque object, rather than a "normal" struct page.
  *
  * A more complete discussion of unaddressable memory may be found in
- * include/linux/hmm.h and Documentation/vm/hmm.txt.
+ * include/linux/hmm.h and Documentation/vm/hmm.rst.
  *
  * MEMORY_DEVICE_PUBLIC:
  * Device memory that is cache coherent from device and CPU point of view. This
@@ -67,7 +67,7 @@ enum memory_type {
  *   page_free()
  *
  * Additional notes about MEMORY_DEVICE_PRIVATE may be found in
- * include/linux/hmm.h and Documentation/vm/hmm.txt. There is also a brief
+ * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief
  * explanation in include/linux/memory_hotplug.h.
  *
  * The page_fault() callback must migrate page back, from device memory to
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index 2d4e23c9ea0a..f09e9cf2e4ab 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -197,6 +197,8 @@ struct cros_ec_dev {
 	u32 features[2];
 };
 
+#define to_cros_ec_dev(dev)  container_of(dev, struct cros_ec_dev, class_dev)
+
 /**
  * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device
  *
diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h
index 638222e43e48..54a3cd808f9e 100644
--- a/include/linux/mfd/mc13xxx.h
+++ b/include/linux/mfd/mc13xxx.h
@@ -243,6 +243,8 @@ struct mc13xxx_platform_data {
 #define MC13XXX_ADC0_LICELLCON		(1 << 0)
 #define MC13XXX_ADC0_CHRGICON		(1 << 1)
 #define MC13XXX_ADC0_BATICON		(1 << 2)
+#define MC13XXX_ADC0_ADIN7SEL_DIE	(1 << 4)
+#define MC13XXX_ADC0_ADIN7SEL_UID	(2 << 4)
 #define MC13XXX_ADC0_ADREFEN		(1 << 10)
 #define MC13XXX_ADC0_TSMOD0		(1 << 12)
 #define MC13XXX_ADC0_TSMOD1		(1 << 13)
diff --git a/include/linux/mfd/wm8350/audio.h b/include/linux/mfd/wm8350/audio.h
index bd581c6fa085..0bc41c4c0429 100644
--- a/include/linux/mfd/wm8350/audio.h
+++ b/include/linux/mfd/wm8350/audio.h
@@ -617,11 +617,8 @@ struct wm8350_audio_platform_data {
 	u32 codec_current_charge:2;	/* codec current @ vmid charge */
 };
 
-struct snd_soc_codec;
-
 struct wm8350_codec {
 	struct platform_device *pdev;
-	struct snd_soc_codec *codec;
 	struct wm8350_audio_platform_data *platform_data;
 };
 
diff --git a/include/linux/microchipphy.h b/include/linux/microchipphy.h
index eb492d47f717..8f9c90379732 100644
--- a/include/linux/microchipphy.h
+++ b/include/linux/microchipphy.h
@@ -70,4 +70,12 @@
 #define	LAN88XX_MMD3_CHIP_ID			(32877)
 #define	LAN88XX_MMD3_CHIP_REV			(32878)
 
+/* DSP registers */
+#define PHY_ARDENNES_MMD_DEV_3_PHY_CFG		(0x806A)
+#define PHY_ARDENNES_MMD_DEV_3_PHY_CFG_ZD_DLY_EN_	(0x2000)
+#define LAN88XX_EXT_PAGE_ACCESS_TR		(0x52B5)
+#define LAN88XX_EXT_PAGE_TR_CR			16
+#define LAN88XX_EXT_PAGE_TR_LOW_DATA		17
+#define LAN88XX_EXT_PAGE_TR_HIGH_DATA		18
+
 #endif /* _MICROCHIPPHY_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 767d193c269a..d703774982ca 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1284,25 +1284,9 @@ enum {
 };
 
 static inline const struct cpumask *
-mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector)
+mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector)
 {
-	const struct cpumask *mask;
-	struct irq_desc *desc;
-	unsigned int irq;
-	int eqn;
-	int err;
-
-	err = mlx5_vector2eqn(dev, MLX5_EQ_VEC_COMP_BASE + vector, &eqn, &irq);
-	if (err)
-		return NULL;
-
-	desc = irq_to_desc(irq);
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
-	mask = irq_data_get_effective_affinity_mask(&desc->irq_data);
-#else
-	mask = desc->irq_common_data.affinity;
-#endif
-	return mask;
+	return dev->priv.irq_info[vector].mask;
 }
 
 #endif /* MLX5_DRIVER_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1ac1f06a4be6..02a616e2f17d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2109,7 +2109,6 @@ extern void setup_per_cpu_pageset(void);
 
 extern void zone_pcp_update(struct zone *zone);
 extern void zone_pcp_reset(struct zone *zone);
-extern void setup_zone_pageset(struct zone *zone);
 
 /* page_alloc.c */
 extern int min_free_kbytes;
@@ -2466,6 +2465,13 @@ static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma,
 	return VM_FAULT_NOPAGE;
 }
 
+static inline vm_fault_t vmf_error(int err)
+{
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
+}
+
 struct page *follow_page_mask(struct vm_area_struct *vma,
 			      unsigned long address, unsigned int foll_flags,
 			      unsigned int *page_mask);
@@ -2493,6 +2499,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_MLOCK	0x1000	/* lock present pages */
 #define FOLL_REMOTE	0x2000	/* we are working on non-current tsk/mm */
 #define FOLL_COW	0x4000	/* internal GUP flag */
+#define FOLL_ANON	0x8000	/* don't do file mappings */
 
 static inline int vm_fault_to_errno(int vm_fault, int foll_flags)
 {
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 279b39008a33..de7377815b6b 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -156,6 +156,7 @@ struct sd_switch_caps {
 #define UHS_DDR50_MAX_DTR	50000000
 #define UHS_SDR25_MAX_DTR	UHS_DDR50_MAX_DTR
 #define UHS_SDR12_MAX_DTR	25000000
+#define DEFAULT_SPEED_MAX_DTR	UHS_SDR12_MAX_DTR
 	unsigned int		sd3_bus_mode;
 #define UHS_SDR12_BUS_SPEED	0
 #define HIGH_SPEED_BUS_SPEED	1
@@ -252,6 +253,7 @@ struct mmc_card {
 #define MMC_TYPE_SD_COMBO	3		/* SD combo (IO+mem) card */
 	unsigned int		state;		/* (our) card state */
 	unsigned int		quirks; 	/* card quirks */
+	unsigned int		quirk_max_rate;	/* max rate set by quirks */
 #define MMC_QUIRK_LENIENT_FN0	(1<<0)		/* allow SDIO FN0 writes outside of the VS CCCR range */
 #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1)	/* use func->cur_blksize */
 						/* for byte mode */
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 927519385482..134a6483347a 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -177,6 +177,7 @@ int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd,
 		int retries);
 
 int mmc_hw_reset(struct mmc_host *host);
+int mmc_sw_reset(struct mmc_host *host);
 void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card);
 
 #endif /* LINUX_MMC_CORE_H */
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 85146235231e..64300a48dcce 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -22,6 +22,7 @@
 struct mmc_ios {
 	unsigned int	clock;			/* clock rate */
 	unsigned short	vdd;
+	unsigned int	power_delay_ms;		/* waiting for stable power */
 
 /* vdd stores the bit number of the selected voltage range from below. */
 
@@ -320,6 +321,9 @@ struct mmc_host {
 #define MMC_CAP_UHS_SDR50	(1 << 18)	/* Host supports UHS SDR50 mode */
 #define MMC_CAP_UHS_SDR104	(1 << 19)	/* Host supports UHS SDR104 mode */
 #define MMC_CAP_UHS_DDR50	(1 << 20)	/* Host supports UHS DDR50 mode */
+#define MMC_CAP_UHS		(MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | \
+				 MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | \
+				 MMC_CAP_UHS_DDR50)
 /* (1 << 21) is free for reuse */
 #define MMC_CAP_DRIVER_TYPE_A	(1 << 23)	/* Host supports Driver Type A */
 #define MMC_CAP_DRIVER_TYPE_C	(1 << 24)	/* Host supports Driver Type C */
@@ -345,6 +349,7 @@ struct mmc_host {
 #define MMC_CAP2_HS400_1_2V	(1 << 16)	/* Can support HS400 1.2V */
 #define MMC_CAP2_HS400		(MMC_CAP2_HS400_1_8V | \
 				 MMC_CAP2_HS400_1_2V)
+#define MMC_CAP2_HSX00_1_8V	(MMC_CAP2_HS200_1_8V_SDR | MMC_CAP2_HS400_1_8V)
 #define MMC_CAP2_HSX00_1_2V	(MMC_CAP2_HS200_1_2V_SDR | MMC_CAP2_HS400_1_2V)
 #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17)
 #define MMC_CAP2_NO_WRITE_PROTECT (1 << 18)	/* No physical write protect pin, assume that card is always read-write */
@@ -354,6 +359,7 @@ struct mmc_host {
 #define MMC_CAP2_NO_MMC		(1 << 22)	/* Do not send (e)MMC commands during initialization */
 #define MMC_CAP2_CQE		(1 << 23)	/* Has eMMC command queue engine */
 #define MMC_CAP2_CQE_DCMD	(1 << 24)	/* CQE can issue a direct command */
+#define MMC_CAP2_AVOID_3_3V	(1 << 25)	/* Host must negotiate down from 3.3V */
 
 	int			fixed_drv_type;	/* fixed driver type for non-removable media */
 
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index cdd66a5fbd5e..2836a96e014a 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -55,6 +55,7 @@
 #define SDIO_DEVICE_ID_MARVELL_8688WLAN		0x9104
 #define SDIO_DEVICE_ID_MARVELL_8688BT		0x9105
 #define SDIO_DEVICE_ID_MARVELL_8797_F0		0x9128
+#define SDIO_DEVICE_ID_MARVELL_8887WLAN	0x9134
 
 #define SDIO_VENDOR_ID_SIANO			0x039a
 #define SDIO_DEVICE_ID_SIANO_NOVA_B0		0x0201
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 2d07a1ed5a31..392e6af82701 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -174,7 +174,7 @@ struct mmu_notifier_ops {
 	 * invalidate_range_start()/end() notifiers, as
 	 * invalidate_range() alread catches the points in time when an
 	 * external TLB range needs to be flushed. For more in depth
-	 * discussion on this see Documentation/vm/mmu_notifier.txt
+	 * discussion on this see Documentation/vm/mmu_notifier.rst
 	 *
 	 * Note that this function might be called with just a sub-range
 	 * of what was passed to invalidate_range_start()/end(), if
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 7d361be2e24f..2014bd19f28e 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -471,6 +471,17 @@ struct slim_device_id {
 	kernel_ulong_t driver_data;
 };
 
+#define APR_NAME_SIZE	32
+#define APR_MODULE_PREFIX "apr:"
+
+struct apr_device_id {
+	char name[APR_NAME_SIZE];
+	__u32 domain_id;
+	__u32 svc_id;
+	__u32 svc_version;
+	kernel_ulong_t driver_data;	/* Data private to the driver */
+};
+
 #define SPMI_NAME_SIZE	32
 #define SPMI_MODULE_PREFIX "spmi:"
 
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 1f1bbb5b4679..5839d8062dfc 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -289,6 +289,8 @@ enum {
 	 * MSI_FLAG_ACTIVATE_EARLY has been set.
 	 */
 	MSI_FLAG_MUST_REACTIVATE	= (1 << 5),
+	/* Is level-triggered capable, using two messages */
+	MSI_FLAG_LEVEL_CAPABLE		= (1 << 6),
 };
 
 int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h
index b63fa457febd..3529683f691e 100644
--- a/include/linux/mtd/flashchip.h
+++ b/include/linux/mtd/flashchip.h
@@ -85,6 +85,7 @@ struct flchip {
 	unsigned int write_suspended:1;
 	unsigned int erase_suspended:1;
 	unsigned long in_progress_block_addr;
+	unsigned long in_progress_block_mask;
 
 	struct mutex mutex;
 	wait_queue_head_t wq; /* Wait on here when we're waiting for the chip
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index b5b43f94f311..01b990e4b228 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -312,7 +312,7 @@ void map_destroy(struct mtd_info *mtd);
 ({									\
 	int i, ret = 1;							\
 	for (i = 0; i < map_words(map); i++) {				\
-		if (((val1).x[i] & (val2).x[i]) != (val2).x[i]) {	\
+		if (((val1).x[i] & (val2).x[i]) != (val3).x[i]) {	\
 			ret = 0;					\
 			break;						\
 		}							\
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 5dad59b31244..17c919436f48 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -867,12 +867,18 @@ struct nand_op_instr {
  * tBERS (during an erase) which all of them are u64 values that cannot be
  * divided by usual kernel macros and must be handled with the special
  * DIV_ROUND_UP_ULL() macro.
+ *
+ * Cast to type of dividend is needed here to guarantee that the result won't
+ * be an unsigned long long when the dividend is an unsigned long (or smaller),
+ * which is what the compiler does when it sees ternary operator with 2
+ * different return types (picks the largest type to make sure there's no
+ * loss).
  */
-#define __DIVIDE(dividend, divisor) ({					\
-	sizeof(dividend) == sizeof(u32) ?				\
-		DIV_ROUND_UP(dividend, divisor) :			\
-		DIV_ROUND_UP_ULL(dividend, divisor);			\
-		})
+#define __DIVIDE(dividend, divisor) ({						\
+	(__typeof__(dividend))(sizeof(dividend) <= sizeof(unsigned long) ?	\
+			       DIV_ROUND_UP(dividend, divisor) :		\
+			       DIV_ROUND_UP_ULL(dividend, divisor)); 		\
+	})
 #define PSEC_TO_NSEC(x) __DIVIDE(x, 1000)
 #define PSEC_TO_MSEC(x) __DIVIDE(x, 1000000000)
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 14bc0d5d0ee5..3093dd162424 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -146,9 +146,6 @@ extern void __mutex_init(struct mutex *lock, const char *name,
  */
 static inline bool mutex_is_locked(struct mutex *lock)
 {
-	/*
-	 * XXX think about spin_is_locked
-	 */
 	return __mutex_owner(lock) != NULL;
 }
 
diff --git a/include/linux/net.h b/include/linux/net.h
index 2248a052061d..3fd9d8c16581 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -147,6 +147,7 @@ struct proto_ops {
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
 				      int peer);
+	__poll_t	(*poll_mask) (struct socket *sock, __poll_t events);
 	__poll_t	(*poll)	     (struct file *file, struct socket *sock,
 				      struct poll_table_struct *wait);
 	int		(*ioctl)     (struct socket *sock, unsigned int cmd,
diff --git a/include/linux/node.h b/include/linux/node.h
index 41f171861dcc..6d336e38d155 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -32,9 +32,11 @@ extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages);
+extern int link_mem_sections(int nid, unsigned long start_pfn,
+			     unsigned long nr_pages, bool check_nid);
 #else
-static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
+static inline int link_mem_sections(int nid, unsigned long start_pfn,
+				    unsigned long nr_pages, bool check_nid)
 {
 	return 0;
 }
@@ -57,7 +59,7 @@ static inline int register_one_node(int nid)
 		if (error)
 			return error;
 		/* link memory sections under this node */
-		error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages);
+		error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages, true);
 	}
 
 	return error;
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index e791ebc65c9c..0c5ef54fd416 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -7,6 +7,8 @@
 #define _LINUX_NOSPEC_H
 #include <asm/barrier.h>
 
+struct task_struct;
+
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
  * @index: array element index
@@ -55,4 +57,12 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 									\
 	(typeof(_i)) (_i & _mask);					\
 })
+
+/* Speculation control prctl */
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which);
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+			     unsigned long ctrl);
+/* Speculation control for seccomp enforced mitigation */
+void arch_seccomp_spec_mitigate(struct task_struct *task);
+
 #endif /* _LINUX_NOSPEC_H */
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 6d731110e0db..f35c7bf76143 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -43,9 +43,7 @@
  * in srcu_notifier_call_chain(): no cache bounces and no memory barriers.
  * As compensation, srcu_notifier_chain_unregister() is rather expensive.
  * SRCU notifier chains should be used when the chain will be called very
- * often but notifier_blocks will seldom be removed.  Also, SRCU notifier
- * chains are slightly more difficult to use because they require special
- * runtime initialization.
+ * often but notifier_blocks will seldom be removed.
  */
 
 struct notifier_block;
@@ -91,7 +89,7 @@ struct srcu_notifier_head {
 		(name)->head = NULL;		\
 	} while (0)
 
-/* srcu_notifier_heads must be initialized and cleaned up dynamically */
+/* srcu_notifier_heads must be cleaned up dynamically */
 extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 #define srcu_cleanup_notifier_head(name)	\
 		cleanup_srcu_struct(&(name)->srcu);
@@ -104,7 +102,13 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 		.head = NULL }
 #define RAW_NOTIFIER_INIT(name)	{				\
 		.head = NULL }
-/* srcu_notifier_heads cannot be initialized statically */
+
+#define SRCU_NOTIFIER_INIT(name, pcpu)				\
+	{							\
+		.mutex = __MUTEX_INITIALIZER(name.mutex),	\
+		.head = NULL,					\
+		.srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu),	\
+	}
 
 #define ATOMIC_NOTIFIER_HEAD(name)				\
 	struct atomic_notifier_head name =			\
@@ -116,6 +120,26 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 	struct raw_notifier_head name =				\
 		RAW_NOTIFIER_INIT(name)
 
+#ifdef CONFIG_TREE_SRCU
+#define _SRCU_NOTIFIER_HEAD(name, mod)				\
+	static DEFINE_PER_CPU(struct srcu_data,			\
+			name##_head_srcu_data);			\
+	mod struct srcu_notifier_head name =			\
+			SRCU_NOTIFIER_INIT(name, name##_head_srcu_data)
+
+#else
+#define _SRCU_NOTIFIER_HEAD(name, mod)				\
+	mod struct srcu_notifier_head name =			\
+			SRCU_NOTIFIER_INIT(name, name)
+
+#endif
+
+#define SRCU_NOTIFIER_HEAD(name)				\
+	_SRCU_NOTIFIER_HEAD(name, /* not static */)
+
+#define SRCU_NOTIFIER_HEAD_STATIC(name)				\
+	_SRCU_NOTIFIER_HEAD(name, static)
+
 #ifdef __KERNEL__
 
 extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
diff --git a/include/linux/nubus.h b/include/linux/nubus.h
index 6e8200215321..eba50b057f6f 100644
--- a/include/linux/nubus.h
+++ b/include/linux/nubus.h
@@ -163,7 +163,7 @@ void nubus_seq_write_rsrc_mem(struct seq_file *m,
 unsigned char *nubus_dirptr(const struct nubus_dirent *nd);
 
 /* Declarations relating to driver model objects */
-int nubus_bus_register(void);
+int nubus_parent_device_register(void);
 int nubus_device_register(struct nubus_board *board);
 int nubus_driver_register(struct nubus_driver *ndrv);
 void nubus_driver_unregister(struct nubus_driver *ndrv);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 4112e2bd747f..2950ce957656 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -436,10 +436,19 @@ enum {
 enum {
 	NVME_AER_ERROR			= 0,
 	NVME_AER_SMART			= 1,
+	NVME_AER_NOTICE			= 2,
 	NVME_AER_CSS			= 6,
 	NVME_AER_VS			= 7,
-	NVME_AER_NOTICE_NS_CHANGED	= 0x0002,
-	NVME_AER_NOTICE_FW_ACT_STARTING = 0x0102,
+};
+
+enum {
+	NVME_AER_NOTICE_NS_CHANGED	= 0x00,
+	NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
+};
+
+enum {
+	NVME_AEN_CFG_NS_ATTR		= 1 << 8,
+	NVME_AEN_CFG_FW_ACT		= 1 << 9,
 };
 
 struct nvme_lba_range_type {
@@ -747,6 +756,7 @@ enum {
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
+	NVME_LOG_CHANGED_NS	= 0x04,
 	NVME_LOG_CMD_EFFECTS	= 0x05,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
@@ -755,6 +765,8 @@ enum {
 	NVME_FWACT_ACTV		= (2 << 3),
 };
 
+#define NVME_MAX_CHANGED_NAMESPACES	1024
+
 struct nvme_identify {
 	__u8			opcode;
 	__u8			flags;
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index f89598bc4e1c..24def6ad09bb 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -77,6 +77,9 @@ struct nvmem_device *devm_nvmem_register(struct device *dev,
 
 int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem);
 
+int nvmem_add_cells(struct nvmem_device *nvmem,
+		    const struct nvmem_cell_info *info,
+		    int ncells);
 #else
 
 static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c)
@@ -99,6 +102,14 @@ static inline int
 devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem)
 {
 	return nvmem_unregister(nvmem);
+
+}
+
+static inline int nvmem_add_cells(struct nvmem_device *nvmem,
+				  const struct nvmem_cell_info *info,
+				  int ncells)
+{
+	return -ENOSYS;
 }
 
 #endif /* CONFIG_NVMEM */
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 8da5a1b31ece..165fd302b442 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -55,7 +55,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return of_node_get(cpu_dev->of_node);
 }
 
-int of_dma_configure(struct device *dev, struct device_node *np);
+int of_dma_configure(struct device *dev,
+		     struct device_node *np,
+		     bool force_dma);
 void of_dma_deconfigure(struct device *dev);
 #else /* CONFIG_OF */
 
@@ -105,7 +107,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return NULL;
 }
 
-static inline int of_dma_configure(struct device *dev, struct device_node *np)
+static inline int of_dma_configure(struct device *dev,
+				   struct device_node *np,
+				   bool force_dma)
 {
 	return 0;
 }
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 5bad038ac012..6adac113e96d 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -95,6 +95,8 @@ static inline int check_stable_address_space(struct mm_struct *mm)
 	return 0;
 }
 
+void __oom_reap_task_mm(struct mm_struct *mm);
+
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 73178a2fcee0..55371cb827ad 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -670,7 +670,7 @@ int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
 int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn,
 		  int reg, int len, u32 val);
 
-#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 typedef u64 pci_bus_addr_t;
 #else
 typedef u32 pci_bus_addr_t;
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index b1f37a89e368..79b99d653e03 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -133,7 +133,7 @@ static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
 	lock_release(&sem->rw_sem.dep_map, 1, ip);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	if (!read)
-		sem->rw_sem.owner = NULL;
+		sem->rw_sem.owner = RWSEM_OWNER_UNKNOWN;
 #endif
 }
 
@@ -141,6 +141,10 @@ static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
 					bool read, unsigned long ip)
 {
 	lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+	if (!read)
+		sem->rw_sem.owner = current;
+#endif
 }
 
 #endif
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e71e99eb9a4e..bea0b0cd4bf7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -467,7 +467,7 @@ enum perf_addr_filter_action_t {
  */
 struct perf_addr_filter {
 	struct list_head	entry;
-	struct inode		*inode;
+	struct path		path;
 	unsigned long		offset;
 	unsigned long		size;
 	enum perf_addr_filter_action_t	action;
@@ -1016,6 +1016,14 @@ static inline int is_software_event(struct perf_event *event)
 	return event->event_caps & PERF_EV_CAP_SOFTWARE;
 }
 
+/*
+ * Return 1 for event in sw context, 0 for event in hw context
+ */
+static inline int in_software_context(struct perf_event *event)
+{
+	return event->ctx->pmu->task_ctx_nr == perf_sw_context;
+}
+
 extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index 93d142ad1528..174601554b06 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -186,7 +186,7 @@ struct pktcdvd_device
 	sector_t		current_sector;	/* Keep track of where the elevator is */
 	atomic_t		scan_queue;	/* Set to non-zero when pkt_handle_queue */
 						/* needs to be run. */
-	mempool_t		*rb_pool;	/* mempool for pkt_rb_node allocations */
+	mempool_t		rb_pool;	/* mempool for pkt_rb_node allocations */
 
 	struct packet_iosched   iosched;
 	struct gendisk		*disk;
diff --git a/include/linux/platform_data/clk-st.h b/include/linux/platform_data/clk-st.h
new file mode 100644
index 000000000000..7cdb6a402b35
--- /dev/null
+++ b/include/linux/platform_data/clk-st.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * clock framework for AMD Stoney based clock
+ *
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ */
+
+#ifndef __CLK_ST_H
+#define __CLK_ST_H
+
+#include <linux/compiler.h>
+
+struct st_clk_data {
+	void __iomem *base;
+};
+
+#endif /* __CLK_ST_H */
diff --git a/include/linux/platform_data/tda9950.h b/include/linux/platform_data/tda9950.h
new file mode 100644
index 000000000000..c65efd461102
--- /dev/null
+++ b/include/linux/platform_data/tda9950.h
@@ -0,0 +1,16 @@
+#ifndef LINUX_PLATFORM_DATA_TDA9950_H
+#define LINUX_PLATFORM_DATA_TDA9950_H
+
+struct device;
+
+struct tda9950_glue {
+	struct device *parent;
+	unsigned long irq_flags;
+	void *data;
+	int (*init)(void *);
+	void (*exit)(void *);
+	int (*open)(void *);
+	void (*release)(void *);
+};
+
+#endif
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 49f634d96118..3097c943fab9 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -356,6 +356,8 @@ extern int platform_pm_restore(struct device *dev);
 #define platform_pm_restore		NULL
 #endif
 
+extern int platform_dma_configure(struct device *dev);
+
 #ifdef CONFIG_PM_SLEEP
 #define USE_PLATFORM_PM_SLEEP_OPS \
 	.suspend = platform_pm_suspend, \
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 04dbef9847d3..42e0d649e653 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -47,8 +47,10 @@ struct genpd_power_state {
 };
 
 struct genpd_lock_ops;
+struct dev_pm_opp;
 
 struct generic_pm_domain {
+	struct device dev;
 	struct dev_pm_domain domain;	/* PM domain operations */
 	struct list_head gpd_list_node;	/* Node in the global PM domains list */
 	struct list_head master_links;	/* Links with PM domain as a master */
@@ -67,6 +69,8 @@ struct generic_pm_domain {
 	unsigned int performance_state;	/* Aggregated max performance state */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
+	unsigned int (*opp_to_performance_state)(struct generic_pm_domain *genpd,
+						 struct dev_pm_opp *opp);
 	int (*set_performance_state)(struct generic_pm_domain *genpd,
 				     unsigned int state);
 	struct gpd_dev_ops dev_ops;
@@ -139,21 +143,16 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
 	return to_gpd_data(dev->power.subsys_data->domain_data);
 }
 
-extern int __pm_genpd_add_device(struct generic_pm_domain *genpd,
-				 struct device *dev,
-				 struct gpd_timing_data *td);
-
-extern int pm_genpd_remove_device(struct generic_pm_domain *genpd,
-				  struct device *dev);
-extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
-				  struct generic_pm_domain *new_subdomain);
-extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
-				     struct generic_pm_domain *target);
-extern int pm_genpd_init(struct generic_pm_domain *genpd,
-			 struct dev_power_governor *gov, bool is_off);
-extern int pm_genpd_remove(struct generic_pm_domain *genpd);
-extern int dev_pm_genpd_set_performance_state(struct device *dev,
-					      unsigned int state);
+int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev);
+int pm_genpd_remove_device(struct device *dev);
+int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
+			   struct generic_pm_domain *new_subdomain);
+int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
+			      struct generic_pm_domain *target);
+int pm_genpd_init(struct generic_pm_domain *genpd,
+		  struct dev_power_governor *gov, bool is_off);
+int pm_genpd_remove(struct generic_pm_domain *genpd);
+int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
@@ -163,14 +162,12 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
 {
 	return ERR_PTR(-ENOSYS);
 }
-static inline int __pm_genpd_add_device(struct generic_pm_domain *genpd,
-					struct device *dev,
-					struct gpd_timing_data *td)
+static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
+				      struct device *dev)
 {
 	return -ENOSYS;
 }
-static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd,
-					 struct device *dev)
+static inline int pm_genpd_remove_device(struct device *dev)
 {
 	return -ENOSYS;
 }
@@ -204,15 +201,9 @@ static inline int dev_pm_genpd_set_performance_state(struct device *dev,
 #define pm_domain_always_on_gov		(*(struct dev_power_governor *)(NULL))
 #endif
 
-static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
-				      struct device *dev)
-{
-	return __pm_genpd_add_device(genpd, dev, NULL);
-}
-
 #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP
-extern void pm_genpd_syscore_poweroff(struct device *dev);
-extern void pm_genpd_syscore_poweron(struct device *dev);
+void pm_genpd_syscore_poweroff(struct device *dev);
+void pm_genpd_syscore_poweron(struct device *dev);
 #else
 static inline void pm_genpd_syscore_poweroff(struct device *dev) {}
 static inline void pm_genpd_syscore_poweron(struct device *dev) {}
@@ -236,13 +227,14 @@ int of_genpd_add_provider_simple(struct device_node *np,
 int of_genpd_add_provider_onecell(struct device_node *np,
 				  struct genpd_onecell_data *data);
 void of_genpd_del_provider(struct device_node *np);
-extern int of_genpd_add_device(struct of_phandle_args *args,
-			       struct device *dev);
-extern int of_genpd_add_subdomain(struct of_phandle_args *parent,
-				  struct of_phandle_args *new_subdomain);
-extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
-extern int of_genpd_parse_idle_states(struct device_node *dn,
-			struct genpd_power_state **states, int *n);
+int of_genpd_add_device(struct of_phandle_args *args, struct device *dev);
+int of_genpd_add_subdomain(struct of_phandle_args *parent,
+			   struct of_phandle_args *new_subdomain);
+struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
+int of_genpd_parse_idle_states(struct device_node *dn,
+			       struct genpd_power_state **states, int *n);
+unsigned int of_genpd_opp_to_performance_state(struct device *dev,
+				struct device_node *opp_node);
 
 int genpd_dev_pm_attach(struct device *dev);
 #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
@@ -278,11 +270,18 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn,
 	return -ENODEV;
 }
 
-static inline int genpd_dev_pm_attach(struct device *dev)
+static inline unsigned int
+of_genpd_opp_to_performance_state(struct device *dev,
+				  struct device_node *opp_node)
 {
 	return -ENODEV;
 }
 
+static inline int genpd_dev_pm_attach(struct device *dev)
+{
+	return 0;
+}
+
 static inline
 struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
 {
@@ -291,13 +290,13 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
 
 #ifdef CONFIG_PM
-extern int dev_pm_domain_attach(struct device *dev, bool power_on);
-extern void dev_pm_domain_detach(struct device *dev, bool power_off);
-extern void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
+int dev_pm_domain_attach(struct device *dev, bool power_on);
+void dev_pm_domain_detach(struct device *dev, bool power_off);
+void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
 #else
 static inline int dev_pm_domain_attach(struct device *dev, bool power_on)
 {
-	return -ENODEV;
+	return 0;
 }
 static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
 static inline void dev_pm_domain_set(struct device *dev,
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 6c2d2e88f066..099b31960dec 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -125,8 +125,6 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name);
 void dev_pm_opp_put_clkname(struct opp_table *opp_table);
 struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
 void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table);
-struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev, int (*get_pstate)(struct device *dev, unsigned long rate));
-void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask);
 int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
@@ -247,14 +245,6 @@ static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device
 
 static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {}
 
-static inline struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev,
-		int (*get_pstate)(struct device *dev, unsigned long rate))
-{
-	return ERR_PTR(-ENOTSUPP);
-}
-
-static inline void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table) {}
-
 static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	return ERR_PTR(-ENOTSUPP);
@@ -303,17 +293,25 @@ static inline void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask
 
 #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF)
 int dev_pm_opp_of_add_table(struct device *dev);
+int dev_pm_opp_of_add_table_indexed(struct device *dev, int index);
 void dev_pm_opp_of_remove_table(struct device *dev);
 int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask);
 void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask);
 int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
 struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev);
+struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np);
+struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp);
 #else
 static inline int dev_pm_opp_of_add_table(struct device *dev)
 {
 	return -ENOTSUPP;
 }
 
+static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index)
+{
+	return -ENOTSUPP;
+}
+
 static inline void dev_pm_opp_of_remove_table(struct device *dev)
 {
 }
@@ -336,6 +334,15 @@ static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device
 {
 	return NULL;
 }
+
+static inline struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np)
+{
+	return NULL;
+}
+static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp)
+{
+	return NULL;
+}
 #endif
 
 #endif		/* __LINUX_OPP_H__ */
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index f0fc4700b6ff..db5dbbf7a48d 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -56,8 +56,7 @@ extern void pm_runtime_update_max_time_suspended(struct device *dev,
 						 s64 delta_ns);
 extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
 extern void pm_runtime_clean_up_links(struct device *dev);
-extern void pm_runtime_get_suppliers(struct device *dev);
-extern void pm_runtime_put_suppliers(struct device *dev);
+extern void pm_runtime_resume_suppliers(struct device *dev);
 extern void pm_runtime_new_link(struct device *dev);
 extern void pm_runtime_drop_link(struct device *dev);
 
@@ -173,8 +172,7 @@ static inline unsigned long pm_runtime_autosuspend_expiration(
 static inline void pm_runtime_set_memalloc_noio(struct device *dev,
 						bool enable){}
 static inline void pm_runtime_clean_up_links(struct device *dev) {}
-static inline void pm_runtime_get_suppliers(struct device *dev) {}
-static inline void pm_runtime_put_suppliers(struct device *dev) {}
+static inline void pm_runtime_resume_suppliers(struct device *dev) {}
 static inline void pm_runtime_new_link(struct device *dev) {}
 static inline void pm_runtime_drop_link(struct device *dev) {}
 
diff --git a/include/linux/poll.h b/include/linux/poll.h
index f45ebd017eaa..fdf86b4cbc71 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -74,6 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
 	pt->_key   = ~(__poll_t)0; /* all events enabled */
 }
 
+static inline bool file_has_poll_mask(struct file *file)
+{
+	return file->f_op->get_poll_head && file->f_op->poll_mask;
+}
+
+static inline bool file_can_poll(struct file *file)
+{
+	return file->f_op->poll || file_has_poll_mask(file);
+}
+
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
+
 struct poll_table_entry {
 	struct file *filp;
 	__poll_t key;
@@ -96,8 +108,6 @@ struct poll_wqueues {
 
 extern void poll_initwait(struct poll_wqueues *pwq);
 extern void poll_freewait(struct poll_wqueues *pwq);
-extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
-				 ktime_t *expires, unsigned long slack);
 extern u64 select_estimate_accuracy(struct timespec64 *tv);
 
 #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index f0139b460a72..b21c4bd96b84 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -145,6 +145,7 @@ enum power_supply_property {
 	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
 	POWER_SUPPLY_PROP_TIME_TO_FULL_AVG,
 	POWER_SUPPLY_PROP_TYPE, /* use power_supply.type instead */
+	POWER_SUPPLY_PROP_USB_TYPE,
 	POWER_SUPPLY_PROP_SCOPE,
 	POWER_SUPPLY_PROP_PRECHARGE_CURRENT,
 	POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT,
@@ -170,6 +171,19 @@ enum power_supply_type {
 	POWER_SUPPLY_TYPE_APPLE_BRICK_ID,	/* Apple Charging Method */
 };
 
+enum power_supply_usb_type {
+	POWER_SUPPLY_USB_TYPE_UNKNOWN = 0,
+	POWER_SUPPLY_USB_TYPE_SDP,		/* Standard Downstream Port */
+	POWER_SUPPLY_USB_TYPE_DCP,		/* Dedicated Charging Port */
+	POWER_SUPPLY_USB_TYPE_CDP,		/* Charging Downstream Port */
+	POWER_SUPPLY_USB_TYPE_ACA,		/* Accessory Charger Adapters */
+	POWER_SUPPLY_USB_TYPE_C,		/* Type C Port */
+	POWER_SUPPLY_USB_TYPE_PD,		/* Power Delivery Port */
+	POWER_SUPPLY_USB_TYPE_PD_DRP,		/* PD Dual Role Port */
+	POWER_SUPPLY_USB_TYPE_PD_PPS,		/* PD Programmable Power Supply */
+	POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID,	/* Apple Charging Method */
+};
+
 enum power_supply_notifier_events {
 	PSY_EVENT_PROP_CHANGED,
 };
@@ -185,6 +199,8 @@ struct power_supply;
 /* Run-time specific power supply configuration */
 struct power_supply_config {
 	struct device_node *of_node;
+	struct fwnode_handle *fwnode;
+
 	/* Driver private data */
 	void *drv_data;
 
@@ -196,6 +212,8 @@ struct power_supply_config {
 struct power_supply_desc {
 	const char *name;
 	enum power_supply_type type;
+	enum power_supply_usb_type *usb_types;
+	size_t num_usb_types;
 	enum power_supply_property *properties;
 	size_t num_properties;
 
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 928ef9e4d912..e518352137e7 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -9,6 +9,8 @@
 #include <linux/fs.h>
 
 struct proc_dir_entry;
+struct seq_file;
+struct seq_operations;
 
 #ifdef CONFIG_PROC_FS
 
@@ -23,6 +25,19 @@ extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t,
 extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t,
 					      struct proc_dir_entry *);
 struct proc_dir_entry *proc_create_mount_point(const char *name);
+
+struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, const struct seq_operations *ops,
+		unsigned int state_size, void *data);
+#define proc_create_seq_data(name, mode, parent, ops, data) \
+	proc_create_seq_private(name, mode, parent, ops, 0, data)
+#define proc_create_seq(name, mode, parent, ops) \
+	proc_create_seq_private(name, mode, parent, ops, 0, NULL)
+struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		int (*show)(struct seq_file *, void *), void *data);
+#define proc_create_single(name, mode, parent, show) \
+	proc_create_single_data(name, mode, parent, show, NULL)
  
 extern struct proc_dir_entry *proc_create_data(const char *, umode_t,
 					       struct proc_dir_entry *,
@@ -38,6 +53,15 @@ extern void proc_remove(struct proc_dir_entry *);
 extern void remove_proc_entry(const char *, struct proc_dir_entry *);
 extern int remove_proc_subtree(const char *, struct proc_dir_entry *);
 
+struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, const struct seq_operations *ops,
+		unsigned int state_size, void *data);
+#define proc_create_net(name, mode, parent, state_size, ops) \
+	proc_create_net_data(name, mode, parent, state_size, ops, NULL)
+struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		int (*show)(struct seq_file *, void *), void *data);
+
 #else /* CONFIG_PROC_FS */
 
 static inline void proc_root_init(void)
@@ -57,6 +81,11 @@ static inline struct proc_dir_entry *proc_mkdir_data(const char *name,
 	umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; }
 static inline struct proc_dir_entry *proc_mkdir_mode(const char *name,
 	umode_t mode, struct proc_dir_entry *parent) { return NULL; }
+#define proc_create_seq_private(name, mode, parent, ops, size, data) ({NULL;})
+#define proc_create_seq_data(name, mode, parent, ops, data) ({NULL;})
+#define proc_create_seq(name, mode, parent, ops) ({NULL;})
+#define proc_create_single(name, mode, parent, show) ({NULL;})
+#define proc_create_single_data(name, mode, parent, show, data) ({NULL;})
 #define proc_create(name, mode, parent, proc_fops) ({NULL;})
 #define proc_create_data(name, mode, parent, proc_fops, data) ({NULL;})
 
@@ -69,6 +98,10 @@ static inline void proc_remove(struct proc_dir_entry *de) {}
 #define remove_proc_entry(name, parent) do {} while (0)
 static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; }
 
+#define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;})
+#define proc_create_net(name, mode, parent, state_size, ops) ({NULL;})
+#define proc_create_net_single(name, mode, parent, show, data) ({NULL;})
+
 #endif /* CONFIG_PROC_FS */
 
 struct net;
@@ -83,4 +116,10 @@ struct ns_common;
 int open_related_ns(struct ns_common *ns,
 		   struct ns_common *(*get_ns)(struct ns_common *ns));
 
+/* get the associated pid namespace for a file in procfs */
+static inline struct pid_namespace *proc_pid_ns(struct inode *inode)
+{
+	return inode->i_sb->s_fs_info;
+}
+
 #endif /* _LINUX_PROC_FS_H */
diff --git a/include/linux/property.h b/include/linux/property.h
index 2eea4b310fc2..ac8a1ebc4c1b 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -178,7 +178,7 @@ static inline int fwnode_property_read_u64(const struct fwnode_handle *fwnode,
  * @name: Name of the property.
  * @length: Length of data making up the value.
  * @is_array: True when the property is an array.
- * @is_string: True when property is a string.
+ * @type: Type of the data in unions.
  * @pointer: Pointer to the property (an array of items of the given type).
  * @value: Value of the property (when it is a single item of the given type).
  */
@@ -186,10 +186,9 @@ struct property_entry {
 	const char *name;
 	size_t length;
 	bool is_array;
-	bool is_string;
+	enum dev_prop_type type;
 	union {
 		union {
-			const void *raw_data;
 			const u8 *u8_data;
 			const u16 *u16_data;
 			const u32 *u32_data;
@@ -197,7 +196,6 @@ struct property_entry {
 			const char * const *str;
 		} pointer;
 		union {
-			unsigned long long raw_data;
 			u8 u8_data;
 			u16 u16_data;
 			u32 u32_data;
@@ -213,55 +211,55 @@ struct property_entry {
  * and structs.
  */
 
-#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _val_)	\
-(struct property_entry) {					\
-	.name = _name_,						\
-	.length = ARRAY_SIZE(_val_) * sizeof(_type_),		\
-	.is_array = true,					\
-	.is_string = false,					\
-	{ .pointer = { ._type_##_data = _val_ } },		\
+#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _Type_, _val_)	\
+(struct property_entry) {						\
+	.name = _name_,							\
+	.length = ARRAY_SIZE(_val_) * sizeof(_type_),			\
+	.is_array = true,						\
+	.type = DEV_PROP_##_Type_,					\
+	{ .pointer = { ._type_##_data = _val_ } },			\
 }
 
 #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_)			\
-	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, _val_)
+	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, U8, _val_)
 #define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_)			\
-	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, _val_)
+	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, U16, _val_)
 #define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_)			\
-	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, _val_)
+	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, U32, _val_)
 #define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_)			\
-	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, _val_)
+	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, U64, _val_)
 
 #define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_)		\
 (struct property_entry) {					\
 	.name = _name_,						\
 	.length = ARRAY_SIZE(_val_) * sizeof(const char *),	\
 	.is_array = true,					\
-	.is_string = true,					\
+	.type = DEV_PROP_STRING,				\
 	{ .pointer = { .str = _val_ } },			\
 }
 
-#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _val_)	\
-(struct property_entry) {				\
-	.name = _name_,					\
-	.length = sizeof(_type_),			\
-	.is_string = false,				\
-	{ .value = { ._type_##_data = _val_ } },	\
+#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _Type_, _val_)	\
+(struct property_entry) {					\
+	.name = _name_,						\
+	.length = sizeof(_type_),				\
+	.type = DEV_PROP_##_Type_,				\
+	{ .value = { ._type_##_data = _val_ } },		\
 }
 
 #define PROPERTY_ENTRY_U8(_name_, _val_)		\
-	PROPERTY_ENTRY_INTEGER(_name_, u8, _val_)
+	PROPERTY_ENTRY_INTEGER(_name_, u8, U8, _val_)
 #define PROPERTY_ENTRY_U16(_name_, _val_)		\
-	PROPERTY_ENTRY_INTEGER(_name_, u16, _val_)
+	PROPERTY_ENTRY_INTEGER(_name_, u16, U16, _val_)
 #define PROPERTY_ENTRY_U32(_name_, _val_)		\
-	PROPERTY_ENTRY_INTEGER(_name_, u32, _val_)
+	PROPERTY_ENTRY_INTEGER(_name_, u32, U32, _val_)
 #define PROPERTY_ENTRY_U64(_name_, _val_)		\
-	PROPERTY_ENTRY_INTEGER(_name_, u64, _val_)
+	PROPERTY_ENTRY_INTEGER(_name_, u64, U64, _val_)
 
 #define PROPERTY_ENTRY_STRING(_name_, _val_)		\
 (struct property_entry) {				\
 	.name = _name_,					\
 	.length = sizeof(_val_),			\
-	.is_string = true,				\
+	.type = DEV_PROP_STRING,			\
 	{ .value = { .str = _val_ } },			\
 }
 
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 93addfa34061..827c601841c4 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -54,6 +54,8 @@ enum sev_cmd {
 	SEV_CMD_PDH_CERT_EXPORT		= 0x008,
 	SEV_CMD_PDH_GEN			= 0x009,
 	SEV_CMD_DF_FLUSH		= 0x00A,
+	SEV_CMD_DOWNLOAD_FIRMWARE	= 0x00B,
+	SEV_CMD_GET_ID			= 0x00C,
 
 	/* Guest commands */
 	SEV_CMD_DECOMMISSION		= 0x020,
@@ -130,6 +132,27 @@ struct sev_data_pek_cert_import {
 } __packed;
 
 /**
+ * struct sev_data_download_firmware - DOWNLOAD_FIRMWARE command parameters
+ *
+ * @address: physical address of firmware image
+ * @len: len of the firmware image
+ */
+struct sev_data_download_firmware {
+	u64 address;				/* In */
+	u32 len;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_get_id - GET_ID command parameters
+ *
+ * @address: physical address of region to place unique CPU ID(s)
+ * @len: len of the region
+ */
+struct sev_data_get_id {
+	u64 address;				/* In */
+	u32 len;				/* In/Out */
+} __packed;
+/**
  * struct sev_data_pdh_cert_export - PDH_CERT_EXPORT command parameters
  *
  * @pdh_address: PDH certificate address
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 919b2a0b0307..037bf0ef1ae9 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -345,7 +345,6 @@ extern void user_single_step_siginfo(struct task_struct *tsk,
 static inline void user_single_step_siginfo(struct task_struct *tsk,
 				struct pt_regs *regs, siginfo_t *info)
 {
-	memset(info, 0, sizeof(*info));
 	info->si_signo = SIGTRAP;
 }
 #endif
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index 6bfd2b581f75..af8a61be2d8d 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -26,6 +26,7 @@
 
 #include <linux/compiler.h>
 #include <linux/rbtree.h>
+#include <linux/rcupdate.h>
 
 /*
  * Please note - only struct rb_augment_callbacks and the prototypes for
diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h
index ece43e882b56..7d012faa509a 100644
--- a/include/linux/rbtree_latch.h
+++ b/include/linux/rbtree_latch.h
@@ -35,6 +35,7 @@
 
 #include <linux/rbtree.h>
 #include <linux/seqlock.h>
+#include <linux/rcupdate.h>
 
 struct latch_tree_node {
 	struct rb_node node[2];
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 36360d07f25b..e679b175b411 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -108,7 +108,6 @@ void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
-void rcu_cpu_starting(unsigned int cpu);
 void rcutree_migrate_callbacks(int cpu);
 
 #ifdef CONFIG_RCU_STALL_COMMON
@@ -188,13 +187,13 @@ static inline void exit_tasks_rcu_finish(void) { }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /**
- * cond_resched_rcu_qs - Report potential quiescent states to RCU
+ * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU
  *
  * This macro resembles cond_resched(), except that it is defined to
  * report potential quiescent states to RCU-tasks even if the cond_resched()
  * machinery were to be shut off, as some advocate for PREEMPT kernels.
  */
-#define cond_resched_rcu_qs() \
+#define cond_resched_tasks_rcu_qs() \
 do { \
 	if (!cond_resched()) \
 		rcu_note_voluntary_context_switch_lite(current); \
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index ce9beec35e34..7b3c82e8a625 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -132,5 +132,6 @@ static inline void rcu_all_qs(void) { barrier(); }
 #define rcutree_offline_cpu      NULL
 #define rcutree_dead_cpu         NULL
 #define rcutree_dying_cpu        NULL
+static inline void rcu_cpu_starting(unsigned int cpu) { }
 
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index fd996cdf1833..914655848ef6 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -74,6 +74,7 @@ static inline void synchronize_rcu_bh_expedited(void)
 void rcu_barrier(void);
 void rcu_barrier_bh(void);
 void rcu_barrier_sched(void);
+bool rcu_eqs_special_set(int cpu);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
 unsigned long get_state_synchronize_sched(void);
@@ -100,5 +101,6 @@ int rcutree_online_cpu(unsigned int cpu);
 int rcutree_offline_cpu(unsigned int cpu);
 int rcutree_dead_cpu(unsigned int cpu);
 int rcutree_dying_cpu(unsigned int cpu);
+void rcu_cpu_starting(unsigned int cpu);
 
 #endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 5f7ad0552c03..4f38068ffb71 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -15,6 +15,7 @@
 
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <linux/ktime.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/bug.h>
@@ -587,7 +588,10 @@ struct regmap *__devm_regmap_init_sdw(struct sdw_slave *sdw,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
 				 const char *lock_name);
-
+struct regmap *__devm_regmap_init_slimbus(struct slim_device *slimbus,
+				 const struct regmap_config *config,
+				 struct lock_class_key *lock_key,
+				 const char *lock_name);
 /*
  * Wrapper for regmap_init macros to include a unique lockdep key and name
  * for each call. No-op if CONFIG_LOCKDEP is not set.
@@ -906,6 +910,19 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 	__regmap_lockdep_wrapper(__devm_regmap_init_sdw, #config,	\
 				sdw, config)
 
+/**
+ * devm_regmap_init_slimbus() - Initialise managed register map
+ *
+ * @slimbus: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap. The regmap will be automatically freed by the
+ * device management code.
+ */
+#define devm_regmap_init_slimbus(slimbus, config)			\
+	__regmap_lockdep_wrapper(__devm_regmap_init_slimbus, #config,	\
+				slimbus, config)
 int regmap_mmio_attach_clk(struct regmap *map, struct clk *clk);
 void regmap_mmio_detach_clk(struct regmap *map);
 void regmap_exit(struct regmap *map);
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index d09a9c7af109..dfdaede9139e 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -569,7 +569,7 @@ static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev)
 void rproc_add_subdev(struct rproc *rproc,
 		      struct rproc_subdev *subdev,
 		      int (*probe)(struct rproc_subdev *subdev),
-		      void (*remove)(struct rproc_subdev *subdev, bool graceful));
+		      void (*remove)(struct rproc_subdev *subdev, bool crashed));
 
 void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev);
 
diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h
index bcfdb918cd81..5d83d0c1d06c 100644
--- a/include/linux/restart_block.h
+++ b/include/linux/restart_block.h
@@ -7,6 +7,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <linux/time64.h>
 
 struct timespec;
 struct compat_timespec;
@@ -15,9 +16,7 @@ struct pollfd;
 enum timespec_type {
 	TT_NONE		= 0,
 	TT_NATIVE	= 1,
-#ifdef CONFIG_COMPAT
 	TT_COMPAT	= 2,
-#endif
 };
 
 /*
@@ -40,10 +39,8 @@ struct restart_block {
 			clockid_t clockid;
 			enum timespec_type type;
 			union {
-				struct timespec __user *rmtp;
-#ifdef CONFIG_COMPAT
+				struct __kernel_timespec __user *rmtp;
 				struct compat_timespec __user *compat_rmtp;
-#endif
 			};
 			u64 expires;
 		} nanosleep;
diff --git a/include/linux/rslib.h b/include/linux/rslib.h
index 746580c1939c..5974cedd008c 100644
--- a/include/linux/rslib.h
+++ b/include/linux/rslib.h
@@ -1,28 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * include/linux/rslib.h
- *
- * Overview:
- *   Generic Reed Solomon encoder / decoder library
+ * Generic Reed Solomon encoder / decoder library
  *
  * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de)
  *
  * RS code lifted from reed solomon library written by Phil Karn
  * Copyright 2002 Phil Karn, KA9Q
- *
- * $Id: rslib.h,v 1.4 2005/11/07 11:14:52 gleixner Exp $
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
-
 #ifndef _RSLIB_H_
 #define _RSLIB_H_
 
 #include <linux/list.h>
+#include <linux/types.h>	/* for gfp_t */
+#include <linux/gfp.h>		/* for GFP_KERNEL */
 
 /**
- * struct rs_control - rs control structure
+ * struct rs_codec - rs codec data
  *
  * @mm:		Bits per symbol
  * @nn:		Symbols per block (= (1<<mm)-1)
@@ -36,24 +29,34 @@
  * @gfpoly:	The primitive generator polynominal
  * @gffunc:	Function to generate the field, if non-canonical representation
  * @users:	Users of this structure
- * @list:	List entry for the rs control list
+ * @list:	List entry for the rs codec list
 */
-struct rs_control {
-	int 		mm;
-	int 		nn;
+struct rs_codec {
+	int		mm;
+	int		nn;
 	uint16_t	*alpha_to;
 	uint16_t	*index_of;
 	uint16_t	*genpoly;
-	int 		nroots;
-	int 		fcr;
-	int 		prim;
-	int 		iprim;
+	int		nroots;
+	int		fcr;
+	int		prim;
+	int		iprim;
 	int		gfpoly;
 	int		(*gffunc)(int);
 	int		users;
 	struct list_head list;
 };
 
+/**
+ * struct rs_control - rs control structure per instance
+ * @codec:	The codec used for this instance
+ * @buffers:	Internal scratch buffers used in calls to decode_rs()
+ */
+struct rs_control {
+	struct rs_codec	*codec;
+	uint16_t	buffers[0];
+};
+
 /* General purpose RS codec, 8-bit data width, symbol width 1-15 bit  */
 #ifdef CONFIG_REED_SOLOMON_ENC8
 int encode_rs8(struct rs_control *rs, uint8_t *data, int len, uint16_t *par,
@@ -76,18 +79,37 @@ int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len,
 		uint16_t *corr);
 #endif
 
-/* Create or get a matching rs control structure */
-struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim,
-			   int nroots);
+struct rs_control *init_rs_gfp(int symsize, int gfpoly, int fcr, int prim,
+			       int nroots, gfp_t gfp);
+
+/**
+ * init_rs - Create a RS control struct and initialize it
+ *  @symsize:	the symbol size (number of bits)
+ *  @gfpoly:	the extended Galois field generator polynomial coefficients,
+ *		with the 0th coefficient in the low order bit. The polynomial
+ *		must be primitive;
+ *  @fcr:	the first consecutive root of the rs code generator polynomial
+ *		in index form
+ *  @prim:	primitive element to generate polynomial roots
+ *  @nroots:	RS code generator polynomial degree (number of roots)
+ *
+ * Allocations use GFP_KERNEL.
+ */
+static inline struct rs_control *init_rs(int symsize, int gfpoly, int fcr,
+					 int prim, int nroots)
+{
+	return init_rs_gfp(symsize, gfpoly, fcr, prim, nroots, GFP_KERNEL);
+}
+
 struct rs_control *init_rs_non_canonical(int symsize, int (*func)(int),
-                                         int fcr, int prim, int nroots);
+					 int fcr, int prim, int nroots);
 
 /* Release a rs control structure */
 void free_rs(struct rs_control *rs);
 
 /** modulo replacement for galois field arithmetics
  *
- *  @rs:	the rs control structure
+ *  @rs:	Pointer to the RS codec
  *  @x:		the value to reduce
  *
  *  where
@@ -97,7 +119,7 @@ void free_rs(struct rs_control *rs);
  *  Simple arithmetic modulo would return a wrong result for values
  *  >= 3 * rs->nn
 */
-static inline int rs_modnn(struct rs_control *rs, int x)
+static inline int rs_modnn(struct rs_codec *rs, int x)
 {
 	while (x >= rs->nn) {
 		x -= rs->nn;
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 56707d5ff6ad..ab93b6eae696 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -44,6 +44,12 @@ struct rw_semaphore {
 #endif
 };
 
+/*
+ * Setting bit 0 of the owner field with other non-zero bits will indicate
+ * that the rwsem is writer-owned with an unknown owner.
+ */
+#define RWSEM_OWNER_UNKNOWN	((struct task_struct *)-1L)
+
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 841585f6e5f2..e6539536dea9 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -127,6 +127,12 @@ struct sbitmap_queue {
 	 * @round_robin: Allocate bits in strict round-robin order.
 	 */
 	bool round_robin;
+
+	/**
+	 * @min_shallow_depth: The minimum shallow depth which may be passed to
+	 * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
+	 */
+	unsigned int min_shallow_depth;
 };
 
 /**
@@ -390,6 +396,9 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq);
  * @shallow_depth: The maximum number of bits to allocate from a single word.
  * See sbitmap_get_shallow().
  *
+ * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
+ * initializing @sbq.
+ *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
 int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
@@ -424,6 +433,9 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq,
  * @shallow_depth: The maximum number of bits to allocate from a single word.
  * See sbitmap_get_shallow().
  *
+ * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
+ * initializing @sbq.
+ *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
 static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
@@ -439,6 +451,23 @@ static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
 }
 
 /**
+ * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the
+ * minimum shallow depth that will be used.
+ * @sbq: Bitmap queue in question.
+ * @min_shallow_depth: The minimum shallow depth that will be passed to
+ * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
+ *
+ * sbitmap_queue_clear() batches wakeups as an optimization. The batch size
+ * depends on the depth of the bitmap. Since the shallow allocation functions
+ * effectively operate with a different depth, the shallow depth must be taken
+ * into account when calculating the batch size. This function must be called
+ * with the minimum shallow depth that will be used. Failure to do so can result
+ * in missed wakeups.
+ */
+void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
+				     unsigned int min_shallow_depth);
+
+/**
  * sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a
  * &struct sbitmap_queue.
  * @sbq: Bitmap to free from.
@@ -484,6 +513,13 @@ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq,
 void sbitmap_queue_wake_all(struct sbitmap_queue *sbq);
 
 /**
+ * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue
+ * on a &struct sbitmap_queue.
+ * @sbq: Bitmap queue to wake up.
+ */
+void sbitmap_queue_wake_up(struct sbitmap_queue *sbq);
+
+/**
  * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct
  * seq_file.
  * @sbq: Bitmap queue to show.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b3d697f3b573..14e4f9c12337 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -112,17 +112,36 @@ struct task_group;
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
+/*
+ * Special states are those that do not use the normal wait-loop pattern. See
+ * the comment with set_special_state().
+ */
+#define is_special_task_state(state)				\
+	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD))
+
 #define __set_current_state(state_value)			\
 	do {							\
+		WARN_ON_ONCE(is_special_task_state(state_value));\
 		current->task_state_change = _THIS_IP_;		\
 		current->state = (state_value);			\
 	} while (0)
+
 #define set_current_state(state_value)				\
 	do {							\
+		WARN_ON_ONCE(is_special_task_state(state_value));\
 		current->task_state_change = _THIS_IP_;		\
 		smp_store_mb(current->state, (state_value));	\
 	} while (0)
 
+#define set_special_state(state_value)					\
+	do {								\
+		unsigned long flags; /* may shadow */			\
+		WARN_ON_ONCE(!is_special_task_state(state_value));	\
+		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
+		current->task_state_change = _THIS_IP_;			\
+		current->state = (state_value);				\
+		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
+	} while (0)
 #else
 /*
  * set_current_state() includes a barrier so that the write of current->state
@@ -144,8 +163,8 @@ struct task_group;
  *
  * The above is typically ordered against the wakeup, which does:
  *
- *	need_sleep = false;
- *	wake_up_state(p, TASK_UNINTERRUPTIBLE);
+ *   need_sleep = false;
+ *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
  * Where wake_up_state() (and all other wakeup primitives) imply enough
  * barriers to order the store of the variable against wakeup.
@@ -154,12 +173,33 @@ struct task_group;
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
  * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
  *
- * This is obviously fine, since they both store the exact same value.
+ * However, with slightly different timing the wakeup TASK_RUNNING store can
+ * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not
+ * a problem either because that will result in one extra go around the loop
+ * and our @cond test will save the day.
  *
  * Also see the comments of try_to_wake_up().
  */
-#define __set_current_state(state_value) do { current->state = (state_value); } while (0)
-#define set_current_state(state_value)	 smp_store_mb(current->state, (state_value))
+#define __set_current_state(state_value)				\
+	current->state = (state_value)
+
+#define set_current_state(state_value)					\
+	smp_store_mb(current->state, (state_value))
+
+/*
+ * set_special_state() should be used for those states when the blocking task
+ * can not use the regular condition based wait-loop. In that case we must
+ * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
+ * will not collide with our state change.
+ */
+#define set_special_state(state_value)					\
+	do {								\
+		unsigned long flags; /* may shadow */			\
+		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
+		current->state = (state_value);				\
+		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
+	} while (0)
+
 #endif
 
 /* Task command name length: */
@@ -1393,7 +1433,8 @@ static inline bool is_percpu_thread(void)
 #define PFA_NO_NEW_PRIVS		0	/* May not gain new privileges. */
 #define PFA_SPREAD_PAGE			1	/* Spread page cache over cpuset */
 #define PFA_SPREAD_SLAB			2	/* Spread some slab caches over cpuset */
-
+#define PFA_SPEC_SSB_DISABLE		3	/* Speculative Store Bypass disabled */
+#define PFA_SPEC_SSB_FORCE_DISABLE	4	/* Speculative Store Bypass force disabled*/
 
 #define TASK_PFA_TEST(name, func)					\
 	static inline bool task_##func(struct task_struct *p)		\
@@ -1418,6 +1459,13 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
 TASK_PFA_SET(SPREAD_SLAB, spread_slab)
 TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 
+TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)
+
+TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+
 static inline void
 current_restore_flags(unsigned long orig_flags, unsigned long flags)
 {
@@ -1464,6 +1512,7 @@ static inline int task_nice(const struct task_struct *p)
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
+extern int available_idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
 extern int sched_setattr(struct task_struct *, const struct sched_attr *);
@@ -1613,7 +1662,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
  * explicit rescheduling in places that are safe. The return
  * value indicates whether a reschedule was done in fact.
  * cond_resched_lock() will drop the spinlock before scheduling,
- * cond_resched_softirq() will enable bhs before scheduling.
  */
 #ifndef CONFIG_PREEMPT
 extern int _cond_resched(void);
@@ -1633,13 +1681,6 @@ extern int __cond_resched_lock(spinlock_t *lock);
 	__cond_resched_lock(lock);				\
 })
 
-extern int __cond_resched_softirq(void);
-
-#define cond_resched_softirq() ({					\
-	___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
-	__cond_resched_softirq();					\
-})
-
 static inline void cond_resched_rcu(void)
 {
 #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2c570cd934af..76a8cb4ef178 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -28,7 +28,7 @@ extern struct mm_struct *mm_alloc(void);
  *
  * Use mmdrop() to release the reference acquired by mmgrab().
  *
- * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
  * of &mm_struct.mm_count vs &mm_struct.mm_users.
  */
 static inline void mmgrab(struct mm_struct *mm)
@@ -62,7 +62,7 @@ static inline void mmdrop(struct mm_struct *mm)
  *
  * Use mmput() to release the reference acquired by mmget().
  *
- * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
  * of &mm_struct.mm_count vs &mm_struct.mm_users.
  */
 static inline void mmget(struct mm_struct *mm)
@@ -170,6 +170,17 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
 static inline void fs_reclaim_release(gfp_t gfp_mask) { }
 #endif
 
+/**
+ * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
+ *
+ * This functions marks the beginning of the GFP_NOIO allocation scope.
+ * All further allocations will implicitly drop __GFP_IO flag and so
+ * they are safe for the IO critical section from the allocation recursion
+ * point of view. Use memalloc_noio_restore to end the scope with flags
+ * returned by this function.
+ *
+ * This function is safe to be used from any context.
+ */
 static inline unsigned int memalloc_noio_save(void)
 {
 	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
@@ -177,11 +188,30 @@ static inline unsigned int memalloc_noio_save(void)
 	return flags;
 }
 
+/**
+ * memalloc_noio_restore - Ends the implicit GFP_NOIO scope.
+ * @flags: Flags to restore.
+ *
+ * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
+ * Always make sure that that the given flags is the return value from the
+ * pairing memalloc_noio_save call.
+ */
 static inline void memalloc_noio_restore(unsigned int flags)
 {
 	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
 }
 
+/**
+ * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope.
+ *
+ * This functions marks the beginning of the GFP_NOFS allocation scope.
+ * All further allocations will implicitly drop __GFP_FS flag and so
+ * they are safe for the FS critical section from the allocation recursion
+ * point of view. Use memalloc_nofs_restore to end the scope with flags
+ * returned by this function.
+ *
+ * This function is safe to be used from any context.
+ */
 static inline unsigned int memalloc_nofs_save(void)
 {
 	unsigned int flags = current->flags & PF_MEMALLOC_NOFS;
@@ -189,6 +219,14 @@ static inline unsigned int memalloc_nofs_save(void)
 	return flags;
 }
 
+/**
+ * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope.
+ * @flags: Flags to restore.
+ *
+ * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
+ * Always make sure that that the given flags is the return value from the
+ * pairing memalloc_nofs_save call.
+ */
 static inline void memalloc_nofs_restore(unsigned int flags)
 {
 	current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index a7ce74c74e49..113d1ad1ced7 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -280,7 +280,7 @@ static inline void kernel_signal_stop(void)
 {
 	spin_lock_irq(&current->sighand->siglock);
 	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
-		__set_current_state(TASK_STOPPED);
+		set_special_state(TASK_STOPPED);
 	spin_unlock_irq(&current->sighand->siglock);
 
 	schedule();
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index c723a5c4e3ff..e5320f6c8654 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -4,8 +4,9 @@
 
 #include <uapi/linux/seccomp.h>
 
-#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC | \
-					 SECCOMP_FILTER_FLAG_LOG)
+#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC	| \
+					 SECCOMP_FILTER_FLAG_LOG	| \
+					 SECCOMP_FILTER_FLAG_SPEC_ALLOW)
 
 #ifdef CONFIG_SECCOMP
 
diff --git a/include/linux/security.h b/include/linux/security.h
index 200920f521a1..63030c85ee19 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -220,12 +220,6 @@ int security_quotactl(int cmds, int type, int id, struct super_block *sb);
 int security_quota_on(struct dentry *dentry);
 int security_syslog(int type);
 int security_settime64(const struct timespec64 *ts, const struct timezone *tz);
-static inline int security_settime(const struct timespec *ts, const struct timezone *tz)
-{
-	struct timespec64 ts64 = timespec_to_timespec64(*ts);
-
-	return security_settime64(&ts64, tz);
-}
 int security_vm_enough_memory_mm(struct mm_struct *mm, long pages);
 int security_bprm_set_creds(struct linux_binprm *bprm);
 int security_bprm_check(struct linux_binprm *bprm);
@@ -508,14 +502,6 @@ static inline int security_settime64(const struct timespec64 *ts,
 	return cap_settime(ts, tz);
 }
 
-static inline int security_settime(const struct timespec *ts,
-				   const struct timezone *tz)
-{
-	struct timespec64 ts64 = timespec_to_timespec64(*ts);
-
-	return cap_settime(&ts64, tz);
-}
-
 static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
 {
 	return __vm_enough_memory(mm, pages, cap_vm_enough_memory(mm, pages));
@@ -1191,6 +1177,7 @@ int security_unix_may_send(struct socket *sock,  struct socket *other);
 int security_socket_create(int family, int type, int protocol, int kern);
 int security_socket_post_create(struct socket *sock, int family,
 				int type, int protocol, int kern);
+int security_socket_socketpair(struct socket *socka, struct socket *sockb);
 int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen);
 int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen);
 int security_socket_listen(struct socket *sock, int backlog);
@@ -1262,6 +1249,12 @@ static inline int security_socket_post_create(struct socket *sock,
 	return 0;
 }
 
+static inline int security_socket_socketpair(struct socket *socka,
+					     struct socket *sockb)
+{
+	return 0;
+}
+
 static inline int security_socket_bind(struct socket *sock,
 				       struct sockaddr *address,
 				       int addrlen)
diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h
index 43ccd84127b6..0fdbe1ddd8d1 100644
--- a/include/linux/seq_file_net.h
+++ b/include/linux/seq_file_net.h
@@ -13,12 +13,6 @@ struct seq_net_private {
 #endif
 };
 
-int seq_open_net(struct inode *, struct file *,
-		 const struct seq_operations *, int);
-int single_open_net(struct inode *, struct file *file,
-		int (*show)(struct seq_file *, void *));
-int seq_release_net(struct inode *, struct file *);
-int single_release_net(struct inode *, struct file *);
 static inline struct net *seq_file_net(struct seq_file *seq)
 {
 #ifdef CONFIG_NET_NS
@@ -28,4 +22,17 @@ static inline struct net *seq_file_net(struct seq_file *seq)
 #endif
 }
 
+/*
+ * This one is needed for proc_create_net_single since net is stored directly
+ * in private not as a struct i.e. seq_file_net can't be used.
+ */
+static inline struct net *seq_file_single_net(struct seq_file *seq)
+{
+#ifdef CONFIG_NET_NS
+	return (struct net *)seq->private;
+#else
+	return &init_net;
+#endif
+}
+
 #endif
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index a27ef5f56431..76b9db71e489 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -163,6 +163,7 @@ extern void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl);
 extern int fsl8250_handle_irq(struct uart_port *port);
 int serial8250_handle_irq(struct uart_port *port, unsigned int iir);
 unsigned char serial8250_rx_chars(struct uart_8250_port *up, unsigned char lsr);
+void serial8250_read_char(struct uart_8250_port *up, unsigned char lsr);
 void serial8250_tx_chars(struct uart_8250_port *up);
 unsigned int serial8250_modem_status(struct uart_8250_port *up);
 void serial8250_init_port(struct uart_8250_port *up);
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 1d356105f25a..06ea4eeb09ab 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -233,6 +233,7 @@ struct uart_port {
 #define UPSTAT_AUTORTS		((__force upstat_t) (1 << 2))
 #define UPSTAT_AUTOCTS		((__force upstat_t) (1 << 3))
 #define UPSTAT_AUTOXOFF		((__force upstat_t) (1 << 4))
+#define UPSTAT_SYNC_FIFO	((__force upstat_t) (1 << 5))
 
 	int			hw_stopped;		/* sw-assisted CTS flow state */
 	unsigned int		mctrl;			/* current modem ctrl settings */
@@ -348,13 +349,14 @@ struct earlycon_device {
 };
 
 struct earlycon_id {
-	char	name[16];
+	char	name[15];
+	char	name_term;	/* In case compiler didn't '\0' term name */
 	char	compatible[128];
 	int	(*setup)(struct earlycon_device *, const char *options);
-} __aligned(32);
+};
 
-extern const struct earlycon_id __earlycon_table[];
-extern const struct earlycon_id __earlycon_table_end[];
+extern const struct earlycon_id *__earlycon_table[];
+extern const struct earlycon_id *__earlycon_table_end[];
 
 #if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE)
 #define EARLYCON_USED_OR_UNUSED	__used
@@ -362,12 +364,19 @@ extern const struct earlycon_id __earlycon_table_end[];
 #define EARLYCON_USED_OR_UNUSED	__maybe_unused
 #endif
 
-#define OF_EARLYCON_DECLARE(_name, compat, fn)				\
-	static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name)	\
-	     EARLYCON_USED_OR_UNUSED __section(__earlycon_table)	\
+#define _OF_EARLYCON_DECLARE(_name, compat, fn, unique_id)		\
+	static const struct earlycon_id unique_id			\
+	     EARLYCON_USED_OR_UNUSED __initconst			\
 		= { .name = __stringify(_name),				\
 		    .compatible = compat,				\
-		    .setup = fn  }
+		    .setup = fn  };					\
+	static const struct earlycon_id EARLYCON_USED_OR_UNUSED		\
+		__section(__earlycon_table)				\
+		* const __PASTE(__p, unique_id) = &unique_id
+
+#define OF_EARLYCON_DECLARE(_name, compat, fn)				\
+	_OF_EARLYCON_DECLARE(_name, compat, fn,				\
+			     __UNIQUE_ID(__earlycon_##_name))
 
 #define EARLYCON_DECLARE(_name, fn)	OF_EARLYCON_DECLARE(_name, "", fn)
 
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 388ff2936a87..6794490f25b2 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -75,6 +75,9 @@ struct shrinker {
 #define SHRINKER_NUMA_AWARE	(1 << 0)
 #define SHRINKER_MEMCG_AWARE	(1 << 1)
 
-extern int register_shrinker(struct shrinker *);
-extern void unregister_shrinker(struct shrinker *);
+extern int prealloc_shrinker(struct shrinker *shrinker);
+extern void register_shrinker_prepared(struct shrinker *shrinker);
+extern int register_shrinker(struct shrinker *shrinker);
+extern void unregister_shrinker(struct shrinker *shrinker);
+extern void free_prealloced_shrinker(struct shrinker *shrinker);
 #endif
diff --git a/include/linux/signal.h b/include/linux/signal.h
index a9bc7e1b077e..3c5200137b24 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -28,6 +28,9 @@ enum siginfo_layout {
 	SIL_TIMER,
 	SIL_POLL,
 	SIL_FAULT,
+	SIL_FAULT_MCEERR,
+	SIL_FAULT_BNDERR,
+	SIL_FAULT_PKUERR,
 	SIL_CHLD,
 	SIL_RT,
 	SIL_SYS,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9065477ed255..89198379b39d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3250,8 +3250,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
 				    int *peeked, int *off, int *err);
 struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
 				  int *err);
-__poll_t datagram_poll(struct file *file, struct socket *sock,
-			   struct poll_table_struct *wait);
+__poll_t datagram_poll_mask(struct socket *sock, __poll_t events);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 			   struct iov_iter *to, int size);
 static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h
new file mode 100644
index 000000000000..c5d52e2cb275
--- /dev/null
+++ b/include/linux/soc/qcom/apr.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __QCOM_APR_H_
+#define __QCOM_APR_H_
+
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include <linux/mod_devicetable.h>
+#include <dt-bindings/soc/qcom,apr.h>
+
+extern struct bus_type aprbus;
+
+#define APR_HDR_LEN(hdr_len) ((hdr_len)/4)
+
+/*
+ * HEADER field
+ * version:0:3
+ * header_size : 4:7
+ * message_type : 8:9
+ * reserved: 10:15
+ */
+#define APR_HDR_FIELD(msg_type, hdr_len, ver)\
+	(((msg_type & 0x3) << 8) | ((hdr_len & 0xF) << 4) | (ver & 0xF))
+
+#define APR_HDR_SIZE sizeof(struct apr_hdr)
+#define APR_SEQ_CMD_HDR_FIELD APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD, \
+					    APR_HDR_LEN(APR_HDR_SIZE), \
+					    APR_PKT_VER)
+/* Version */
+#define APR_PKT_VER		0x0
+
+/* Command and Response Types */
+#define APR_MSG_TYPE_EVENT	0x0
+#define APR_MSG_TYPE_CMD_RSP	0x1
+#define APR_MSG_TYPE_SEQ_CMD	0x2
+#define APR_MSG_TYPE_NSEQ_CMD	0x3
+#define APR_MSG_TYPE_MAX	0x04
+
+/* APR Basic Response Message */
+#define APR_BASIC_RSP_RESULT 0x000110E8
+#define APR_RSP_ACCEPTED     0x000100BE
+
+struct aprv2_ibasic_rsp_result_t {
+	uint32_t opcode;
+	uint32_t status;
+};
+
+/* hdr field Ver [0:3], Size [4:7], Message type [8:10] */
+#define APR_HDR_FIELD_VER(h)		(h & 0x000F)
+#define APR_HDR_FIELD_SIZE(h)		((h & 0x00F0) >> 4)
+#define APR_HDR_FIELD_SIZE_BYTES(h)	(((h & 0x00F0) >> 4) * 4)
+#define APR_HDR_FIELD_MT(h)		((h & 0x0300) >> 8)
+
+struct apr_hdr {
+	uint16_t hdr_field;
+	uint16_t pkt_size;
+	uint8_t src_svc;
+	uint8_t src_domain;
+	uint16_t src_port;
+	uint8_t dest_svc;
+	uint8_t dest_domain;
+	uint16_t dest_port;
+	uint32_t token;
+	uint32_t opcode;
+} __packed;
+
+struct apr_pkt {
+	struct apr_hdr hdr;
+	uint8_t payload[];
+};
+
+struct apr_resp_pkt {
+	struct apr_hdr hdr;
+	void *payload;
+	int payload_size;
+};
+
+/* Bits 0 to 15 -- Minor version,  Bits 16 to 31 -- Major version */
+#define APR_SVC_MAJOR_VERSION(v)	((v >> 16) & 0xFF)
+#define APR_SVC_MINOR_VERSION(v)	(v & 0xFF)
+
+struct apr_device {
+	struct device	dev;
+	uint16_t	svc_id;
+	uint16_t	domain_id;
+	uint32_t	version;
+	char name[APR_NAME_SIZE];
+	spinlock_t	lock;
+	struct list_head node;
+};
+
+#define to_apr_device(d) container_of(d, struct apr_device, dev)
+
+struct apr_driver {
+	int	(*probe)(struct apr_device *sl);
+	int	(*remove)(struct apr_device *sl);
+	int	(*callback)(struct apr_device *a,
+			    struct apr_resp_pkt *d);
+	struct device_driver		driver;
+	const struct apr_device_id	*id_table;
+};
+
+#define to_apr_driver(d) container_of(d, struct apr_driver, driver)
+
+/*
+ * use a macro to avoid include chaining to get THIS_MODULE
+ */
+#define apr_driver_register(drv) __apr_driver_register(drv, THIS_MODULE)
+
+int __apr_driver_register(struct apr_driver *drv, struct module *owner);
+void apr_driver_unregister(struct apr_driver *drv);
+
+/**
+ * module_apr_driver() - Helper macro for registering a aprbus driver
+ * @__aprbus_driver: aprbus_driver struct
+ *
+ * Helper macro for aprbus drivers which do not do anything special in
+ * module init/exit. This eliminates a lot of boilerplate. Each module
+ * may only use this macro once, and calling it replaces module_init()
+ * and module_exit()
+ */
+#define module_apr_driver(__apr_driver) \
+	module_driver(__apr_driver, apr_driver_register, \
+			apr_driver_unregister)
+
+int apr_send_pkt(struct apr_device *adev, struct apr_pkt *pkt);
+
+#endif /* __QCOM_APR_H_ */
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index e91fdcf41049..962971e6a9c7 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -23,9 +23,24 @@ struct sdw_slave;
 #define SDW_MASTER_DEV_NUM		14
 
 #define SDW_NUM_DEV_ID_REGISTERS	6
+/* frame shape defines */
 
+/*
+ * Note: The maximum row define in SoundWire spec 1.1 is 23. In order to
+ * fill hole with 0, one more dummy entry is added
+ */
+#define SDW_FRAME_ROWS		24
+#define SDW_FRAME_COLS		8
+#define SDW_FRAME_ROW_COLS		(SDW_FRAME_ROWS * SDW_FRAME_COLS)
+
+#define SDW_FRAME_CTRL_BITS		48
 #define SDW_MAX_DEVICES			11
 
+#define SDW_VALID_PORT_RANGE(n)		(n <= 14 && n >= 1)
+
+#define SDW_DAI_ID_RANGE_START		100
+#define SDW_DAI_ID_RANGE_END		200
+
 /**
  * enum sdw_slave_status - Slave status
  * @SDW_SLAVE_UNATTACHED: Slave is not attached with the bus.
@@ -61,6 +76,30 @@ enum sdw_command_response {
 	SDW_CMD_FAIL_OTHER = 4,
 };
 
+/**
+ * enum sdw_stream_type: data stream type
+ *
+ * @SDW_STREAM_PCM: PCM data stream
+ * @SDW_STREAM_PDM: PDM data stream
+ *
+ * spec doesn't define this, but is used in implementation
+ */
+enum sdw_stream_type {
+	SDW_STREAM_PCM = 0,
+	SDW_STREAM_PDM = 1,
+};
+
+/**
+ * enum sdw_data_direction: Data direction
+ *
+ * @SDW_DATA_DIR_RX: Data into Port
+ * @SDW_DATA_DIR_TX: Data out of Port
+ */
+enum sdw_data_direction {
+	SDW_DATA_DIR_RX = 0,
+	SDW_DATA_DIR_TX = 1,
+};
+
 /*
  * SDW properties, defined in MIPI DisCo spec v1.0
  */
@@ -341,11 +380,92 @@ struct sdw_slave_intr_status {
 };
 
 /**
- * struct sdw_slave_ops - Slave driver callback ops
+ * sdw_reg_bank - SoundWire register banks
+ * @SDW_BANK0: Soundwire register bank 0
+ * @SDW_BANK1: Soundwire register bank 1
+ */
+enum sdw_reg_bank {
+	SDW_BANK0,
+	SDW_BANK1,
+};
+
+/**
+ * struct sdw_bus_conf: Bus configuration
+ *
+ * @clk_freq: Clock frequency, in Hz
+ * @num_rows: Number of rows in frame
+ * @num_cols: Number of columns in frame
+ * @bank: Next register bank
+ */
+struct sdw_bus_conf {
+	unsigned int clk_freq;
+	unsigned int num_rows;
+	unsigned int num_cols;
+	unsigned int bank;
+};
+
+/**
+ * struct sdw_prepare_ch: Prepare/De-prepare Data Port channel
+ *
+ * @num: Port number
+ * @ch_mask: Active channel mask
+ * @prepare: Prepare (true) /de-prepare (false) channel
+ * @bank: Register bank, which bank Slave/Master driver should program for
+ * implementation defined registers. This is always updated to next_bank
+ * value read from bus params.
+ *
+ */
+struct sdw_prepare_ch {
+	unsigned int num;
+	unsigned int ch_mask;
+	bool prepare;
+	unsigned int bank;
+};
+
+/**
+ * enum sdw_port_prep_ops: Prepare operations for Data Port
+ *
+ * @SDW_OPS_PORT_PRE_PREP: Pre prepare operation for the Port
+ * @SDW_OPS_PORT_PREP: Prepare operation for the Port
+ * @SDW_OPS_PORT_POST_PREP: Post prepare operation for the Port
+ */
+enum sdw_port_prep_ops {
+	SDW_OPS_PORT_PRE_PREP = 0,
+	SDW_OPS_PORT_PREP = 1,
+	SDW_OPS_PORT_POST_PREP = 2,
+};
+
+/**
+ * struct sdw_bus_params: Structure holding bus configuration
+ *
+ * @curr_bank: Current bank in use (BANK0/BANK1)
+ * @next_bank: Next bank to use (BANK0/BANK1). next_bank will always be
+ * set to !curr_bank
+ * @max_dr_freq: Maximum double rate clock frequency supported, in Hz
+ * @curr_dr_freq: Current double rate clock frequency, in Hz
+ * @bandwidth: Current bandwidth
+ * @col: Active columns
+ * @row: Active rows
+ */
+struct sdw_bus_params {
+	enum sdw_reg_bank curr_bank;
+	enum sdw_reg_bank next_bank;
+	unsigned int max_dr_freq;
+	unsigned int curr_dr_freq;
+	unsigned int bandwidth;
+	unsigned int col;
+	unsigned int row;
+};
+
+/**
+ * struct sdw_slave_ops: Slave driver callback ops
+ *
  * @read_prop: Read Slave properties
  * @interrupt_callback: Device interrupt notification (invoked in thread
  * context)
  * @update_status: Update Slave status
+ * @bus_config: Update the bus config for Slave
+ * @port_prep: Prepare the port with parameters
  */
 struct sdw_slave_ops {
 	int (*read_prop)(struct sdw_slave *sdw);
@@ -353,6 +473,11 @@ struct sdw_slave_ops {
 			struct sdw_slave_intr_status *status);
 	int (*update_status)(struct sdw_slave *slave,
 			enum sdw_slave_status status);
+	int (*bus_config)(struct sdw_slave *slave,
+			struct sdw_bus_params *params);
+	int (*port_prep)(struct sdw_slave *slave,
+			struct sdw_prepare_ch *prepare_ch,
+			enum sdw_port_prep_ops pre_ops);
 };
 
 /**
@@ -406,6 +531,93 @@ int sdw_handle_slave_status(struct sdw_bus *bus,
  * SDW master structures and APIs
  */
 
+/**
+ * struct sdw_port_params: Data Port parameters
+ *
+ * @num: Port number
+ * @bps: Word length of the Port
+ * @flow_mode: Port Data flow mode
+ * @data_mode: Test modes or normal mode
+ *
+ * This is used to program the Data Port based on Data Port stream
+ * parameters.
+ */
+struct sdw_port_params {
+	unsigned int num;
+	unsigned int bps;
+	unsigned int flow_mode;
+	unsigned int data_mode;
+};
+
+/**
+ * struct sdw_transport_params: Data Port Transport Parameters
+ *
+ * @blk_grp_ctrl_valid: Port implements block group control
+ * @num: Port number
+ * @blk_grp_ctrl: Block group control value
+ * @sample_interval: Sample interval
+ * @offset1: Blockoffset of the payload data
+ * @offset2: Blockoffset of the payload data
+ * @hstart: Horizontal start of the payload data
+ * @hstop: Horizontal stop of the payload data
+ * @blk_pkg_mode: Block per channel or block per port
+ * @lane_ctrl: Data lane Port uses for Data transfer. Currently only single
+ * data lane is supported in bus
+ *
+ * This is used to program the Data Port based on Data Port transport
+ * parameters. All these parameters are banked and can be modified
+ * during a bank switch without any artifacts in audio stream.
+ */
+struct sdw_transport_params {
+	bool blk_grp_ctrl_valid;
+	unsigned int port_num;
+	unsigned int blk_grp_ctrl;
+	unsigned int sample_interval;
+	unsigned int offset1;
+	unsigned int offset2;
+	unsigned int hstart;
+	unsigned int hstop;
+	unsigned int blk_pkg_mode;
+	unsigned int lane_ctrl;
+};
+
+/**
+ * struct sdw_enable_ch: Enable/disable Data Port channel
+ *
+ * @num: Port number
+ * @ch_mask: Active channel mask
+ * @enable: Enable (true) /disable (false) channel
+ */
+struct sdw_enable_ch {
+	unsigned int port_num;
+	unsigned int ch_mask;
+	bool enable;
+};
+
+/**
+ * struct sdw_master_port_ops: Callback functions from bus to Master
+ * driver to set Master Data ports.
+ *
+ * @dpn_set_port_params: Set the Port parameters for the Master Port.
+ * Mandatory callback
+ * @dpn_set_port_transport_params: Set transport parameters for the Master
+ * Port. Mandatory callback
+ * @dpn_port_prep: Port prepare operations for the Master Data Port.
+ * @dpn_port_enable_ch: Enable the channels of Master Port.
+ */
+struct sdw_master_port_ops {
+	int (*dpn_set_port_params)(struct sdw_bus *bus,
+			struct sdw_port_params *port_params,
+			unsigned int bank);
+	int (*dpn_set_port_transport_params)(struct sdw_bus *bus,
+			struct sdw_transport_params *transport_params,
+			enum sdw_reg_bank bank);
+	int (*dpn_port_prep)(struct sdw_bus *bus,
+			struct sdw_prepare_ch *prepare_ch);
+	int (*dpn_port_enable_ch)(struct sdw_bus *bus,
+			struct sdw_enable_ch *enable_ch, unsigned int bank);
+};
+
 struct sdw_msg;
 
 /**
@@ -426,6 +638,9 @@ struct sdw_defer {
  * @xfer_msg: Transfer message callback
  * @xfer_msg_defer: Defer version of transfer message callback
  * @reset_page_addr: Reset the SCP page address registers
+ * @set_bus_conf: Set the bus configuration
+ * @pre_bank_switch: Callback for pre bank switch
+ * @post_bank_switch: Callback for post bank switch
  */
 struct sdw_master_ops {
 	int (*read_prop)(struct sdw_bus *bus);
@@ -437,6 +652,11 @@ struct sdw_master_ops {
 			struct sdw_defer *defer);
 	enum sdw_command_response (*reset_page_addr)
 			(struct sdw_bus *bus, unsigned int dev_num);
+	int (*set_bus_conf)(struct sdw_bus *bus,
+			struct sdw_bus_params *params);
+	int (*pre_bank_switch)(struct sdw_bus *bus);
+	int (*post_bank_switch)(struct sdw_bus *bus);
+
 };
 
 /**
@@ -449,9 +669,15 @@ struct sdw_master_ops {
  * @bus_lock: bus lock
  * @msg_lock: message lock
  * @ops: Master callback ops
+ * @port_ops: Master port callback ops
+ * @params: Current bus parameters
  * @prop: Master properties
+ * @m_rt_list: List of Master instance of all stream(s) running on Bus. This
+ * is used to compute and program bus bandwidth, clock, frame shape,
+ * transport and port parameters
  * @defer_msg: Defer message
  * @clk_stop_timeout: Clock stop timeout computed
+ * @bank_switch_timeout: Bank switch timeout computed
  */
 struct sdw_bus {
 	struct device *dev;
@@ -461,14 +687,118 @@ struct sdw_bus {
 	struct mutex bus_lock;
 	struct mutex msg_lock;
 	const struct sdw_master_ops *ops;
+	const struct sdw_master_port_ops *port_ops;
+	struct sdw_bus_params params;
 	struct sdw_master_prop prop;
+	struct list_head m_rt_list;
 	struct sdw_defer defer_msg;
 	unsigned int clk_stop_timeout;
+	u32 bank_switch_timeout;
 };
 
 int sdw_add_bus_master(struct sdw_bus *bus);
 void sdw_delete_bus_master(struct sdw_bus *bus);
 
+/**
+ * sdw_port_config: Master or Slave Port configuration
+ *
+ * @num: Port number
+ * @ch_mask: channels mask for port
+ */
+struct sdw_port_config {
+	unsigned int num;
+	unsigned int ch_mask;
+};
+
+/**
+ * sdw_stream_config: Master or Slave stream configuration
+ *
+ * @frame_rate: Audio frame rate of the stream, in Hz
+ * @ch_count: Channel count of the stream
+ * @bps: Number of bits per audio sample
+ * @direction: Data direction
+ * @type: Stream type PCM or PDM
+ */
+struct sdw_stream_config {
+	unsigned int frame_rate;
+	unsigned int ch_count;
+	unsigned int bps;
+	enum sdw_data_direction direction;
+	enum sdw_stream_type type;
+};
+
+/**
+ * sdw_stream_state: Stream states
+ *
+ * @SDW_STREAM_ALLOCATED: New stream allocated.
+ * @SDW_STREAM_CONFIGURED: Stream configured
+ * @SDW_STREAM_PREPARED: Stream prepared
+ * @SDW_STREAM_ENABLED: Stream enabled
+ * @SDW_STREAM_DISABLED: Stream disabled
+ * @SDW_STREAM_DEPREPARED: Stream de-prepared
+ * @SDW_STREAM_RELEASED: Stream released
+ */
+enum sdw_stream_state {
+	SDW_STREAM_ALLOCATED = 0,
+	SDW_STREAM_CONFIGURED = 1,
+	SDW_STREAM_PREPARED = 2,
+	SDW_STREAM_ENABLED = 3,
+	SDW_STREAM_DISABLED = 4,
+	SDW_STREAM_DEPREPARED = 5,
+	SDW_STREAM_RELEASED = 6,
+};
+
+/**
+ * sdw_stream_params: Stream parameters
+ *
+ * @rate: Sampling frequency, in Hz
+ * @ch_count: Number of channels
+ * @bps: bits per channel sample
+ */
+struct sdw_stream_params {
+	unsigned int rate;
+	unsigned int ch_count;
+	unsigned int bps;
+};
+
+/**
+ * sdw_stream_runtime: Runtime stream parameters
+ *
+ * @name: SoundWire stream name
+ * @params: Stream parameters
+ * @state: Current state of the stream
+ * @type: Stream type PCM or PDM
+ * @m_rt: Master runtime
+ */
+struct sdw_stream_runtime {
+	char *name;
+	struct sdw_stream_params params;
+	enum sdw_stream_state state;
+	enum sdw_stream_type type;
+	struct sdw_master_runtime *m_rt;
+};
+
+struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name);
+void sdw_release_stream(struct sdw_stream_runtime *stream);
+int sdw_stream_add_master(struct sdw_bus *bus,
+		struct sdw_stream_config *stream_config,
+		struct sdw_port_config *port_config,
+		unsigned int num_ports,
+		struct sdw_stream_runtime *stream);
+int sdw_stream_add_slave(struct sdw_slave *slave,
+		struct sdw_stream_config *stream_config,
+		struct sdw_port_config *port_config,
+		unsigned int num_ports,
+		struct sdw_stream_runtime *stream);
+int sdw_stream_remove_master(struct sdw_bus *bus,
+		struct sdw_stream_runtime *stream);
+int sdw_stream_remove_slave(struct sdw_slave *slave,
+		struct sdw_stream_runtime *stream);
+int sdw_prepare_stream(struct sdw_stream_runtime *stream);
+int sdw_enable_stream(struct sdw_stream_runtime *stream);
+int sdw_disable_stream(struct sdw_stream_runtime *stream);
+int sdw_deprepare_stream(struct sdw_stream_runtime *stream);
+
 /* messaging and data APIs */
 
 int sdw_read(struct sdw_slave *slave, u32 addr);
diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h
index 4b37528f592d..2b9573b8aedd 100644
--- a/include/linux/soundwire/sdw_intel.h
+++ b/include/linux/soundwire/sdw_intel.h
@@ -5,17 +5,31 @@
 #define __SDW_INTEL_H
 
 /**
+ * struct sdw_intel_ops: Intel audio driver callback ops
+ *
+ * @config_stream: configure the stream with the hw_params
+ */
+struct sdw_intel_ops {
+	int (*config_stream)(void *arg, void *substream,
+			void *dai, void *hw_params, int stream_num);
+};
+
+/**
  * struct sdw_intel_res - Soundwire Intel resource structure
  * @mmio_base: mmio base of SoundWire registers
  * @irq: interrupt number
  * @handle: ACPI parent handle
  * @parent: parent device
+ * @ops: callback ops
+ * @arg: callback arg
  */
 struct sdw_intel_res {
 	void __iomem *mmio_base;
 	int irq;
 	acpi_handle handle;
 	struct device *parent;
+	const struct sdw_intel_ops *ops;
+	void *arg;
 };
 
 void *sdw_intel_init(acpi_handle *parent_handle, struct sdw_intel_res *res);
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
new file mode 100644
index 000000000000..bb4bd15ae1f6
--- /dev/null
+++ b/include/linux/spi/spi-mem.h
@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2018 Exceet Electronics GmbH
+ * Copyright (C) 2018 Bootlin
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#ifndef __LINUX_SPI_MEM_H
+#define __LINUX_SPI_MEM_H
+
+#include <linux/spi/spi.h>
+
+#define SPI_MEM_OP_CMD(__opcode, __buswidth)			\
+	{							\
+		.buswidth = __buswidth,				\
+		.opcode = __opcode,				\
+	}
+
+#define SPI_MEM_OP_ADDR(__nbytes, __val, __buswidth)		\
+	{							\
+		.nbytes = __nbytes,				\
+		.val = __val,					\
+		.buswidth = __buswidth,				\
+	}
+
+#define SPI_MEM_OP_NO_ADDR	{ }
+
+#define SPI_MEM_OP_DUMMY(__nbytes, __buswidth)			\
+	{							\
+		.nbytes = __nbytes,				\
+		.buswidth = __buswidth,				\
+	}
+
+#define SPI_MEM_OP_NO_DUMMY	{ }
+
+#define SPI_MEM_OP_DATA_IN(__nbytes, __buf, __buswidth)		\
+	{							\
+		.dir = SPI_MEM_DATA_IN,				\
+		.nbytes = __nbytes,				\
+		.buf.in = __buf,				\
+		.buswidth = __buswidth,				\
+	}
+
+#define SPI_MEM_OP_DATA_OUT(__nbytes, __buf, __buswidth)	\
+	{							\
+		.dir = SPI_MEM_DATA_OUT,			\
+		.nbytes = __nbytes,				\
+		.buf.out = __buf,				\
+		.buswidth = __buswidth,				\
+	}
+
+#define SPI_MEM_OP_NO_DATA	{ }
+
+/**
+ * enum spi_mem_data_dir - describes the direction of a SPI memory data
+ *			   transfer from the controller perspective
+ * @SPI_MEM_DATA_IN: data coming from the SPI memory
+ * @SPI_MEM_DATA_OUT: data sent the SPI memory
+ */
+enum spi_mem_data_dir {
+	SPI_MEM_DATA_IN,
+	SPI_MEM_DATA_OUT,
+};
+
+/**
+ * struct spi_mem_op - describes a SPI memory operation
+ * @cmd.buswidth: number of IO lines used to transmit the command
+ * @cmd.opcode: operation opcode
+ * @addr.nbytes: number of address bytes to send. Can be zero if the operation
+ *		 does not need to send an address
+ * @addr.buswidth: number of IO lines used to transmit the address cycles
+ * @addr.val: address value. This value is always sent MSB first on the bus.
+ *	      Note that only @addr.nbytes are taken into account in this
+ *	      address value, so users should make sure the value fits in the
+ *	      assigned number of bytes.
+ * @dummy.nbytes: number of dummy bytes to send after an opcode or address. Can
+ *		  be zero if the operation does not require dummy bytes
+ * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes
+ * @data.buswidth: number of IO lanes used to send/receive the data
+ * @data.dir: direction of the transfer
+ * @data.buf.in: input buffer
+ * @data.buf.out: output buffer
+ */
+struct spi_mem_op {
+	struct {
+		u8 buswidth;
+		u8 opcode;
+	} cmd;
+
+	struct {
+		u8 nbytes;
+		u8 buswidth;
+		u64 val;
+	} addr;
+
+	struct {
+		u8 nbytes;
+		u8 buswidth;
+	} dummy;
+
+	struct {
+		u8 buswidth;
+		enum spi_mem_data_dir dir;
+		unsigned int nbytes;
+		/* buf.{in,out} must be DMA-able. */
+		union {
+			void *in;
+			const void *out;
+		} buf;
+	} data;
+};
+
+#define SPI_MEM_OP(__cmd, __addr, __dummy, __data)		\
+	{							\
+		.cmd = __cmd,					\
+		.addr = __addr,					\
+		.dummy = __dummy,				\
+		.data = __data,					\
+	}
+
+/**
+ * struct spi_mem - describes a SPI memory device
+ * @spi: the underlying SPI device
+ * @drvpriv: spi_mem_drviver private data
+ *
+ * Extra information that describe the SPI memory device and may be needed by
+ * the controller to properly handle this device should be placed here.
+ *
+ * One example would be the device size since some controller expose their SPI
+ * mem devices through a io-mapped region.
+ */
+struct spi_mem {
+	struct spi_device *spi;
+	void *drvpriv;
+};
+
+/**
+ * struct spi_mem_set_drvdata() - attach driver private data to a SPI mem
+ *				  device
+ * @mem: memory device
+ * @data: data to attach to the memory device
+ */
+static inline void spi_mem_set_drvdata(struct spi_mem *mem, void *data)
+{
+	mem->drvpriv = data;
+}
+
+/**
+ * struct spi_mem_get_drvdata() - get driver private data attached to a SPI mem
+ *				  device
+ * @mem: memory device
+ *
+ * Return: the data attached to the mem device.
+ */
+static inline void *spi_mem_get_drvdata(struct spi_mem *mem)
+{
+	return mem->drvpriv;
+}
+
+/**
+ * struct spi_controller_mem_ops - SPI memory operations
+ * @adjust_op_size: shrink the data xfer of an operation to match controller's
+ *		    limitations (can be alignment of max RX/TX size
+ *		    limitations)
+ * @supports_op: check if an operation is supported by the controller
+ * @exec_op: execute a SPI memory operation
+ *
+ * This interface should be implemented by SPI controllers providing an
+ * high-level interface to execute SPI memory operation, which is usually the
+ * case for QSPI controllers.
+ */
+struct spi_controller_mem_ops {
+	int (*adjust_op_size)(struct spi_mem *mem, struct spi_mem_op *op);
+	bool (*supports_op)(struct spi_mem *mem,
+			    const struct spi_mem_op *op);
+	int (*exec_op)(struct spi_mem *mem,
+		       const struct spi_mem_op *op);
+};
+
+/**
+ * struct spi_mem_driver - SPI memory driver
+ * @spidrv: inherit from a SPI driver
+ * @probe: probe a SPI memory. Usually where detection/initialization takes
+ *	   place
+ * @remove: remove a SPI memory
+ * @shutdown: take appropriate action when the system is shutdown
+ *
+ * This is just a thin wrapper around a spi_driver. The core takes care of
+ * allocating the spi_mem object and forwarding the probe/remove/shutdown
+ * request to the spi_mem_driver. The reason we use this wrapper is because
+ * we might have to stuff more information into the spi_mem struct to let
+ * SPI controllers know more about the SPI memory they interact with, and
+ * having this intermediate layer allows us to do that without adding more
+ * useless fields to the spi_device object.
+ */
+struct spi_mem_driver {
+	struct spi_driver spidrv;
+	int (*probe)(struct spi_mem *mem);
+	int (*remove)(struct spi_mem *mem);
+	void (*shutdown)(struct spi_mem *mem);
+};
+
+#if IS_ENABLED(CONFIG_SPI_MEM)
+int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr,
+				       const struct spi_mem_op *op,
+				       struct sg_table *sg);
+
+void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr,
+					  const struct spi_mem_op *op,
+					  struct sg_table *sg);
+#else
+static inline int
+spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr,
+				   const struct spi_mem_op *op,
+				   struct sg_table *sg)
+{
+	return -ENOTSUPP;
+}
+
+static inline void
+spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr,
+				     const struct spi_mem_op *op,
+				     struct sg_table *sg)
+{
+}
+#endif /* CONFIG_SPI_MEM */
+
+int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op);
+
+bool spi_mem_supports_op(struct spi_mem *mem,
+			 const struct spi_mem_op *op);
+
+int spi_mem_exec_op(struct spi_mem *mem,
+		    const struct spi_mem_op *op);
+
+int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv,
+				       struct module *owner);
+
+void spi_mem_driver_unregister(struct spi_mem_driver *drv);
+
+#define spi_mem_driver_register(__drv)                                  \
+	spi_mem_driver_register_with_owner(__drv, THIS_MODULE)
+
+#define module_spi_mem_driver(__drv)                                    \
+	module_driver(__drv, spi_mem_driver_register,                   \
+		      spi_mem_driver_unregister)
+
+#endif /* __LINUX_SPI_MEM_H */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index bc6bb325d1bf..a64235e05321 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -26,7 +26,7 @@ struct dma_chan;
 struct property_entry;
 struct spi_controller;
 struct spi_transfer;
-struct spi_flash_read_message;
+struct spi_controller_mem_ops;
 
 /*
  * INTERFACES between SPI master-side drivers and SPI slave protocol handlers,
@@ -376,13 +376,11 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  *                    transfer_one callback.
  * @handle_err: the subsystem calls the driver to handle an error that occurs
  *		in the generic implementation of transfer_one_message().
+ * @mem_ops: optimized/dedicated operations for interactions with SPI memory.
+ *	     This field is optional and should only be implemented if the
+ *	     controller has native support for memory like operations.
  * @unprepare_message: undo any work done by prepare_message().
  * @slave_abort: abort the ongoing transfer request on an SPI slave controller
- * @spi_flash_read: to support spi-controller hardwares that provide
- *                  accelerated interface to read from flash devices.
- * @spi_flash_can_dma: analogous to can_dma() interface, but for
- *		       controllers implementing spi_flash_read.
- * @flash_read_supported: spi device supports flash read
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
  *	number. Any individual value may be -ENOENT for CS lines that
  *	are not GPIOs (driven by the SPI controller itself).
@@ -548,11 +546,6 @@ struct spi_controller {
 	int (*unprepare_message)(struct spi_controller *ctlr,
 				 struct spi_message *message);
 	int (*slave_abort)(struct spi_controller *ctlr);
-	int (*spi_flash_read)(struct  spi_device *spi,
-			      struct spi_flash_read_message *msg);
-	bool (*spi_flash_can_dma)(struct spi_device *spi,
-				  struct spi_flash_read_message *msg);
-	bool (*flash_read_supported)(struct spi_device *spi);
 
 	/*
 	 * These hooks are for drivers that use a generic implementation
@@ -564,6 +557,9 @@ struct spi_controller {
 	void (*handle_err)(struct spi_controller *ctlr,
 			   struct spi_message *message);
 
+	/* Optimized handlers for SPI memory-like operations. */
+	const struct spi_controller_mem_ops *mem_ops;
+
 	/* gpio chip select */
 	int			*cs_gpios;
 
@@ -1183,48 +1179,6 @@ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd)
 	return be16_to_cpu(result);
 }
 
-/**
- * struct spi_flash_read_message - flash specific information for
- * spi-masters that provide accelerated flash read interfaces
- * @buf: buffer to read data
- * @from: offset within the flash from where data is to be read
- * @len: length of data to be read
- * @retlen: actual length of data read
- * @read_opcode: read_opcode to be used to communicate with flash
- * @addr_width: number of address bytes
- * @dummy_bytes: number of dummy bytes
- * @opcode_nbits: number of lines to send opcode
- * @addr_nbits: number of lines to send address
- * @data_nbits: number of lines for data
- * @rx_sg: Scatterlist for receive data read from flash
- * @cur_msg_mapped: message has been mapped for DMA
- */
-struct spi_flash_read_message {
-	void *buf;
-	loff_t from;
-	size_t len;
-	size_t retlen;
-	u8 read_opcode;
-	u8 addr_width;
-	u8 dummy_bytes;
-	u8 opcode_nbits;
-	u8 addr_nbits;
-	u8 data_nbits;
-	struct sg_table rx_sg;
-	bool cur_msg_mapped;
-};
-
-/* SPI core interface for flash read support */
-static inline bool spi_flash_read_supported(struct spi_device *spi)
-{
-	return spi->controller->spi_flash_read &&
-	       (!spi->controller->flash_read_supported ||
-	       spi->controller->flash_read_supported(spi));
-}
-
-int spi_flash_read(struct spi_device *spi,
-		   struct spi_flash_read_message *msg);
-
 /*---------------------------------------------------------------------------*/
 
 /*
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 4894d322d258..1e8a46435838 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -380,6 +380,24 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock)
 	raw_spin_trylock_irqsave(spinlock_check(lock), flags); \
 })
 
+/**
+ * spin_is_locked() - Check whether a spinlock is locked.
+ * @lock: Pointer to the spinlock.
+ *
+ * This function is NOT required to provide any memory ordering
+ * guarantees; it could be used for debugging purposes or, when
+ * additional synchronization is needed, accompanied with other
+ * constructs (memory barriers) enforcing the synchronization.
+ *
+ * Returns: 1 if @lock is locked, 0 otherwise.
+ *
+ * Note that the function only tells you that the spinlock is
+ * seen to be locked, not that it is locked on your CPU.
+ *
+ * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n,
+ * the return value is always 0 (see include/linux/spinlock_up.h).
+ * Therefore you should not rely heavily on the return value.
+ */
 static __always_inline int spin_is_locked(spinlock_t *lock)
 {
 	return raw_spin_is_locked(&lock->rlock);
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 33c1c698df09..91494d7e8e41 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -69,11 +69,45 @@ struct srcu_struct { };
 
 void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 		void (*func)(struct rcu_head *head));
-void cleanup_srcu_struct(struct srcu_struct *sp);
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced);
 int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
 
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+static inline void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+	_cleanup_srcu_struct(sp, false);
+}
+
+/**
+ * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.  Also,
+ * all grace-period processing must have completed.
+ *
+ * "Completed" means that the last synchronize_srcu() and
+ * synchronize_srcu_expedited() calls must have returned before the call
+ * to cleanup_srcu_struct_quiesced().  It also means that the callback
+ * from the last call_srcu() must have been invoked before the call to
+ * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help
+ * with this last.  Violating these rules will get you a WARN_ON() splat
+ * (with high probability, anyway), and will also cause the srcu_struct
+ * to be leaked.
+ */
+static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *sp)
+{
+	_cleanup_srcu_struct(sp, true);
+}
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 /**
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 261471f407a5..f41d2fb09f87 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -43,7 +43,7 @@ struct srcu_struct {
 
 void srcu_drive_gp(struct work_struct *wp);
 
-#define __SRCU_STRUCT_INIT(name)					\
+#define __SRCU_STRUCT_INIT(name, __ignored)				\
 {									\
 	.srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq),	\
 	.srcu_cb_tail = &name.srcu_cb_head,				\
@@ -56,9 +56,9 @@ void srcu_drive_gp(struct work_struct *wp);
  * Tree SRCU, which needs some per-CPU data.
  */
 #define DEFINE_SRCU(name) \
-	struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+	struct srcu_struct name = __SRCU_STRUCT_INIT(name, name)
 #define DEFINE_STATIC_SRCU(name) \
-	static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+	static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name)
 
 void synchronize_srcu(struct srcu_struct *sp);
 
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 4eda108abee0..745d4ca4dd50 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -104,9 +104,9 @@ struct srcu_struct {
 #define SRCU_STATE_SCAN1	1
 #define SRCU_STATE_SCAN2	2
 
-#define __SRCU_STRUCT_INIT(name)					\
+#define __SRCU_STRUCT_INIT(name, pcpu_name)				\
 	{								\
-		.sda = &name##_srcu_data,				\
+		.sda = &pcpu_name,					\
 		.lock = __SPIN_LOCK_UNLOCKED(name.lock),		\
 		.srcu_gp_seq_needed = 0 - 1,				\
 		__SRCU_DEP_MAP_INIT(name)				\
@@ -133,7 +133,7 @@ struct srcu_struct {
  */
 #define __DEFINE_SRCU(name, is_static)					\
 	static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\
-	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_data)
 #define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
 #define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)
 
diff --git a/include/linux/string.h b/include/linux/string.h
index dd39a690c841..4a5a0eb7df51 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -147,8 +147,8 @@ extern int memcmp(const void *,const void *,__kernel_size_t);
 extern void * memchr(const void *,int,__kernel_size_t);
 #endif
 #ifndef __HAVE_ARCH_MEMCPY_MCSAFE
-static inline __must_check int memcpy_mcsafe(void *dst, const void *src,
-		size_t cnt)
+static inline __must_check unsigned long memcpy_mcsafe(void *dst,
+		const void *src, size_t cnt)
 {
 	memcpy(dst, src, cnt);
 	return 0;
diff --git a/include/linux/stringhash.h b/include/linux/stringhash.h
index e8f0f852968f..c0c5c5b73dc0 100644
--- a/include/linux/stringhash.h
+++ b/include/linux/stringhash.h
@@ -50,9 +50,9 @@ partial_name_hash(unsigned long c, unsigned long prevhash)
  * losing bits).  This also has the property (wanted by the dcache)
  * that the msbits make a good hash table index.
  */
-static inline unsigned long end_name_hash(unsigned long hash)
+static inline unsigned int end_name_hash(unsigned long hash)
 {
-	return __hash_32((unsigned int)hash);
+	return hash_long(hash, 32);
 }
 
 /*
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index a5704daf5df9..e90b9bd99ded 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -122,8 +122,6 @@ extern struct dentry *rpc_create_cache_dir(struct dentry *,
 					   struct cache_detail *);
 extern void rpc_remove_cache_dir(struct dentry *);
 
-extern int rpc_rmdir(struct dentry *dentry);
-
 struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags);
 void rpc_destroy_pipe_data(struct rpc_pipe *pipe);
 extern struct dentry *rpc_mkpipe_dentry(struct dentry *, const char *, void *,
diff --git a/include/linux/swait.h b/include/linux/swait.h
index c98aaf677466..bf8cb0dee23c 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -5,10 +5,23 @@
 #include <linux/list.h>
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
+#include <linux/wait.h>
 #include <asm/current.h>
 
 /*
- * Simple wait queues
+ * BROKEN wait-queues.
+ *
+ * These "simple" wait-queues are broken garbage, and should never be
+ * used. The comments below claim that they are "similar" to regular
+ * wait-queues, but the semantics are actually completely different, and
+ * every single user we have ever had has been buggy (or pointless).
+ *
+ * A "swake_up()" only wakes up _one_ waiter, which is not at all what
+ * "wake_up()" does, and has led to problems. In other cases, it has
+ * been fine, because there's only ever one waiter (kvm), but in that
+ * case gthe whole "simple" wait-queue is just pointless to begin with,
+ * since there is no "queue". Use "wake_up_process()" with a direct
+ * pointer instead.
  *
  * While these are very similar to regular wait queues (wait.h) the most
  * important difference is that the simple waitqueue allows for deterministic
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2417d288e016..c063443d8638 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -53,7 +53,7 @@ static inline int current_is_kswapd(void)
 
 /*
  * Unaddressable device memory support. See include/linux/hmm.h and
- * Documentation/vm/hmm.txt. Short description is we need struct pages for
+ * Documentation/vm/hmm.rst. Short description is we need struct pages for
  * device memory that is unaddressable (inaccessible) by CPU, so that we can
  * migrate part of a process memory to device memory.
  *
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 70fcda1a9049..390e814fdc8d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -290,6 +290,12 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id,
 				long nr,
 				struct io_event __user *events,
 				struct timespec __user *timeout);
+asmlinkage long sys_io_pgetevents(aio_context_t ctx_id,
+				long min_nr,
+				long nr,
+				struct io_event __user *events,
+				struct timespec __user *timeout,
+				const struct __aio_sigset *sig);
 
 /* fs/xattr.c */
 asmlinkage long sys_setxattr(const char __user *path, const char __user *name,
@@ -536,7 +542,8 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
 				    size_t len);
 
 /* kernel/hrtimer.c */
-asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp);
+asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
+			      struct __kernel_timespec __user *rmtp);
 
 /* kernel/itimer.c */
 asmlinkage long sys_getitimer(int which, struct itimerval __user *value);
@@ -567,14 +574,14 @@ asmlinkage long sys_timer_settime(timer_t timer_id, int flags,
 				struct itimerspec __user *old_setting);
 asmlinkage long sys_timer_delete(timer_t timer_id);
 asmlinkage long sys_clock_settime(clockid_t which_clock,
-				const struct timespec __user *tp);
+				const struct __kernel_timespec __user *tp);
 asmlinkage long sys_clock_gettime(clockid_t which_clock,
-				struct timespec __user *tp);
+				struct __kernel_timespec __user *tp);
 asmlinkage long sys_clock_getres(clockid_t which_clock,
-				struct timespec __user *tp);
+				struct __kernel_timespec __user *tp);
 asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags,
-				const struct timespec __user *rqtp,
-				struct timespec __user *rmtp);
+				const struct __kernel_timespec __user *rqtp,
+				struct __kernel_timespec __user *rmtp);
 
 /* kernel/printk.c */
 asmlinkage long sys_syslog(int type, char __user *buf, int len);
@@ -679,8 +686,8 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info);
 /* ipc/mqueue.c */
 asmlinkage long sys_mq_open(const char __user *name, int oflag, umode_t mode, struct mq_attr __user *attr);
 asmlinkage long sys_mq_unlink(const char __user *name);
-asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout);
-asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout);
+asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct __kernel_timespec __user *abs_timeout);
+asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct __kernel_timespec __user *abs_timeout);
 asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification);
 asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat);
 
@@ -697,7 +704,7 @@ asmlinkage long sys_semget(key_t key, int nsems, int semflg);
 asmlinkage long sys_semctl(int semid, int semnum, int cmd, unsigned long arg);
 asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops,
 				unsigned nsops,
-				const struct timespec __user *timeout);
+				const struct __kernel_timespec __user *timeout);
 asmlinkage long sys_semop(int semid, struct sembuf __user *sops,
 				unsigned nsops);
 
diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h
index 0494db3fd9e8..13770cfe33ad 100644
--- a/include/linux/textsearch.h
+++ b/include/linux/textsearch.h
@@ -62,7 +62,7 @@ struct ts_config
 	int 			flags;
 
 	/**
-	 * get_next_block - fetch next block of data
+	 * @get_next_block: fetch next block of data
 	 * @consumed: number of bytes consumed by the caller
 	 * @dst: destination buffer
 	 * @conf: search configuration
@@ -79,7 +79,7 @@ struct ts_config
 						  struct ts_state *state);
 
 	/**
-	 * finish - finalize/clean a series of get_next_block() calls
+	 * @finish: finalize/clean a series of get_next_block() calls
 	 * @conf: search configuration
 	 * @state: search state
 	 *
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 34f053a150a9..cf2862bd134a 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -43,11 +43,7 @@ enum {
 #define THREAD_ALIGN	THREAD_SIZE
 #endif
 
-#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_ZERO)
-#else
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT)
-#endif
+#define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_ZERO)
 
 /*
  * flag set/clear/test wrappers
diff --git a/include/linux/ti-emif-sram.h b/include/linux/ti-emif-sram.h
index 45bc6b376492..53604b087f2c 100644
--- a/include/linux/ti-emif-sram.h
+++ b/include/linux/ti-emif-sram.h
@@ -60,6 +60,81 @@ struct ti_emif_pm_functions {
 	u32 abort_sr;
 } __packed __aligned(8);
 
+static inline void ti_emif_asm_offsets(void)
+{
+	DEFINE(EMIF_SDCFG_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_sdcfg_val));
+	DEFINE(EMIF_TIMING1_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_timing1_val));
+	DEFINE(EMIF_TIMING2_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_timing2_val));
+	DEFINE(EMIF_TIMING3_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_timing3_val));
+	DEFINE(EMIF_REF_CTRL_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_ref_ctrl_val));
+	DEFINE(EMIF_ZQCFG_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_zqcfg_val));
+	DEFINE(EMIF_PMCR_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_pmcr_val));
+	DEFINE(EMIF_PMCR_SHDW_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_pmcr_shdw_val));
+	DEFINE(EMIF_RD_WR_LEVEL_RAMP_CTRL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_rd_wr_level_ramp_ctrl));
+	DEFINE(EMIF_RD_WR_EXEC_THRESH_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_rd_wr_exec_thresh));
+	DEFINE(EMIF_COS_CONFIG_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_cos_config));
+	DEFINE(EMIF_PRIORITY_TO_COS_MAPPING_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_priority_to_cos_mapping));
+	DEFINE(EMIF_CONNECT_ID_SERV_1_MAP_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_connect_id_serv_1_map));
+	DEFINE(EMIF_CONNECT_ID_SERV_2_MAP_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_connect_id_serv_2_map));
+	DEFINE(EMIF_OCP_CONFIG_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_ocp_config_val));
+	DEFINE(EMIF_LPDDR2_NVM_TIM_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim));
+	DEFINE(EMIF_LPDDR2_NVM_TIM_SHDW_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim_shdw));
+	DEFINE(EMIF_DLL_CALIB_CTRL_VAL_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val));
+	DEFINE(EMIF_DLL_CALIB_CTRL_VAL_SHDW_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val_shdw));
+	DEFINE(EMIF_DDR_PHY_CTLR_1_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_ddr_phy_ctlr_1));
+	DEFINE(EMIF_EXT_PHY_CTRL_VALS_OFFSET,
+	       offsetof(struct emif_regs_amx3, emif_ext_phy_ctrl_vals));
+	DEFINE(EMIF_REGS_AMX3_SIZE, sizeof(struct emif_regs_amx3));
+
+	BLANK();
+
+	DEFINE(EMIF_PM_BASE_ADDR_VIRT_OFFSET,
+	       offsetof(struct ti_emif_pm_data, ti_emif_base_addr_virt));
+	DEFINE(EMIF_PM_BASE_ADDR_PHYS_OFFSET,
+	       offsetof(struct ti_emif_pm_data, ti_emif_base_addr_phys));
+	DEFINE(EMIF_PM_CONFIG_OFFSET,
+	       offsetof(struct ti_emif_pm_data, ti_emif_sram_config));
+	DEFINE(EMIF_PM_REGS_VIRT_OFFSET,
+	       offsetof(struct ti_emif_pm_data, regs_virt));
+	DEFINE(EMIF_PM_REGS_PHYS_OFFSET,
+	       offsetof(struct ti_emif_pm_data, regs_phys));
+	DEFINE(EMIF_PM_DATA_SIZE, sizeof(struct ti_emif_pm_data));
+
+	BLANK();
+
+	DEFINE(EMIF_PM_SAVE_CONTEXT_OFFSET,
+	       offsetof(struct ti_emif_pm_functions, save_context));
+	DEFINE(EMIF_PM_RESTORE_CONTEXT_OFFSET,
+	       offsetof(struct ti_emif_pm_functions, restore_context));
+	DEFINE(EMIF_PM_ENTER_SR_OFFSET,
+	       offsetof(struct ti_emif_pm_functions, enter_sr));
+	DEFINE(EMIF_PM_EXIT_SR_OFFSET,
+	       offsetof(struct ti_emif_pm_functions, exit_sr));
+	DEFINE(EMIF_PM_ABORT_SR_OFFSET,
+	       offsetof(struct ti_emif_pm_functions, abort_sr));
+	DEFINE(EMIF_PM_FUNCTIONS_SIZE, sizeof(struct ti_emif_pm_functions));
+}
+
 struct gen_pool;
 
 int ti_emif_copy_pm_function_table(struct gen_pool *sram_pool, void *dst);
diff --git a/include/linux/time.h b/include/linux/time.h
index 4b62a2c0a661..aed74463592d 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -10,9 +10,9 @@
 extern struct timezone sys_tz;
 
 int get_timespec64(struct timespec64 *ts,
-		const struct timespec __user *uts);
+		const struct __kernel_timespec __user *uts);
 int put_timespec64(const struct timespec64 *ts,
-		struct timespec __user *uts);
+		struct __kernel_timespec __user *uts);
 int get_itimerspec64(struct itimerspec64 *it,
 			const struct itimerspec __user *uit);
 int put_itimerspec64(const struct itimerspec64 *it,
diff --git a/include/linux/time32.h b/include/linux/time32.h
index d2bcd4377b56..0b14f936100a 100644
--- a/include/linux/time32.h
+++ b/include/linux/time32.h
@@ -18,25 +18,14 @@
 /* timespec64 is defined as timespec here */
 static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64)
 {
-	return ts64;
+	return *(const struct timespec *)&ts64;
 }
 
 static inline struct timespec64 timespec_to_timespec64(const struct timespec ts)
 {
-	return ts;
+	return *(const struct timespec64 *)&ts;
 }
 
-# define timespec_equal			timespec64_equal
-# define timespec_compare		timespec64_compare
-# define set_normalized_timespec	set_normalized_timespec64
-# define timespec_add			timespec64_add
-# define timespec_sub			timespec64_sub
-# define timespec_valid			timespec64_valid
-# define timespec_valid_strict		timespec64_valid_strict
-# define timespec_to_ns			timespec64_to_ns
-# define ns_to_timespec			ns_to_timespec64
-# define timespec_add_ns		timespec64_add_ns
-
 #else
 static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64)
 {
@@ -55,6 +44,7 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts)
 	ret.tv_nsec = ts.tv_nsec;
 	return ret;
 }
+#endif
 
 static inline int timespec_equal(const struct timespec *a,
 				 const struct timespec *b)
@@ -159,8 +149,6 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns)
 	a->tv_nsec = ns;
 }
 
-#endif
-
 /**
  * time_to_tm - converts the calendar time to local broken-down time
  *
diff --git a/include/linux/time64.h b/include/linux/time64.h
index 93d39499838e..0a7b2f79cec7 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -2,17 +2,20 @@
 #ifndef _LINUX_TIME64_H
 #define _LINUX_TIME64_H
 
-#include <uapi/linux/time.h>
 #include <linux/math64.h>
 
 typedef __s64 time64_t;
 typedef __u64 timeu64_t;
 
-#if __BITS_PER_LONG == 64
-/* this trick allows us to optimize out timespec64_to_timespec */
-# define timespec64 timespec
-#define itimerspec64 itimerspec
-#else
+/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path
+ * and 32-bit emulation.
+ */
+#ifndef CONFIG_64BIT_TIME
+#define __kernel_timespec timespec
+#endif
+
+#include <uapi/linux/time.h>
+
 struct timespec64 {
 	time64_t	tv_sec;			/* seconds */
 	long		tv_nsec;		/* nanoseconds */
@@ -23,8 +26,6 @@ struct itimerspec64 {
 	struct timespec64 it_value;
 };
 
-#endif
-
 /* Parameters used to convert the timespec values: */
 #define MSEC_PER_SEC	1000L
 #define USEC_PER_MSEC	1000L
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 4b3dca173e89..7acb953298a7 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -52,7 +52,6 @@ struct tk_read_base {
  * @offs_real:		Offset clock monotonic -> clock realtime
  * @offs_boot:		Offset clock monotonic -> clock boottime
  * @offs_tai:		Offset clock monotonic -> clock tai
- * @time_suspended:	Accumulated suspend time
  * @tai_offset:		The current UTC to TAI offset in seconds
  * @clock_was_set_seq:	The sequence number of clock was set events
  * @cs_was_changed_seq:	The sequence number of clocksource change events
@@ -95,7 +94,6 @@ struct timekeeper {
 	ktime_t			offs_real;
 	ktime_t			offs_boot;
 	ktime_t			offs_tai;
-	ktime_t			time_suspended;
 	s32			tai_offset;
 	unsigned int		clock_was_set_seq;
 	u8			cs_was_changed_seq;
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 9737fbec7019..86bc2026efce 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -19,53 +19,43 @@ extern void xtime_update(unsigned long ticks);
 extern int do_settimeofday64(const struct timespec64 *ts);
 extern int do_sys_settimeofday64(const struct timespec64 *tv,
 				 const struct timezone *tz);
-/*
- * Kernel time accessors
- */
-struct timespec64 current_kernel_time64(void);
 
 /*
  * timespec64 based interfaces
  */
-struct timespec64 get_monotonic_coarse64(void);
-extern void getrawmonotonic64(struct timespec64 *ts);
+extern void ktime_get_raw_ts64(struct timespec64 *ts);
 extern void ktime_get_ts64(struct timespec64 *ts);
+extern void ktime_get_real_ts64(struct timespec64 *tv);
+extern void ktime_get_coarse_ts64(struct timespec64 *ts);
+extern void ktime_get_coarse_real_ts64(struct timespec64 *ts);
+
+void getboottime64(struct timespec64 *ts);
+
+/*
+ * time64_t base interfaces
+ */
 extern time64_t ktime_get_seconds(void);
 extern time64_t __ktime_get_real_seconds(void);
 extern time64_t ktime_get_real_seconds(void);
-extern void ktime_get_active_ts64(struct timespec64 *ts);
-
-extern int __getnstimeofday64(struct timespec64 *tv);
-extern void getnstimeofday64(struct timespec64 *tv);
-extern void getboottime64(struct timespec64 *ts);
-
-#define ktime_get_real_ts64(ts)		getnstimeofday64(ts)
-
-/* Clock BOOTTIME compatibility wrappers */
-static inline void get_monotonic_boottime64(struct timespec64 *ts)
-{
-	ktime_get_ts64(ts);
-}
 
 /*
  * ktime_t based interfaces
  */
+
 enum tk_offsets {
 	TK_OFFS_REAL,
+	TK_OFFS_BOOT,
 	TK_OFFS_TAI,
 	TK_OFFS_MAX,
 };
 
 extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_with_offset(enum tk_offsets offs);
+extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs);
 extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs);
 extern ktime_t ktime_get_raw(void);
 extern u32 ktime_get_resolution_ns(void);
 
-/* Clock BOOTTIME compatibility wrappers */
-static inline ktime_t ktime_get_boottime(void) { return ktime_get(); }
-static inline u64 ktime_get_boot_ns(void) { return ktime_get(); }
-
 /**
  * ktime_get_real - get the real (wall-) time in ktime_t format
  */
@@ -74,6 +64,27 @@ static inline ktime_t ktime_get_real(void)
 	return ktime_get_with_offset(TK_OFFS_REAL);
 }
 
+static inline ktime_t ktime_get_coarse_real(void)
+{
+	return ktime_get_coarse_with_offset(TK_OFFS_REAL);
+}
+
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in ktime_t format
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the
+ * time spent in suspend.
+ */
+static inline ktime_t ktime_get_boottime(void)
+{
+	return ktime_get_with_offset(TK_OFFS_BOOT);
+}
+
+static inline ktime_t ktime_get_coarse_boottime(void)
+{
+	return ktime_get_coarse_with_offset(TK_OFFS_BOOT);
+}
+
 /**
  * ktime_get_clocktai - Returns the TAI time of day in ktime_t format
  */
@@ -82,6 +93,11 @@ static inline ktime_t ktime_get_clocktai(void)
 	return ktime_get_with_offset(TK_OFFS_TAI);
 }
 
+static inline ktime_t ktime_get_coarse_clocktai(void)
+{
+	return ktime_get_coarse_with_offset(TK_OFFS_TAI);
+}
+
 /**
  * ktime_mono_to_real - Convert monotonic time to clock realtime
  */
@@ -100,6 +116,11 @@ static inline u64 ktime_get_real_ns(void)
 	return ktime_to_ns(ktime_get_real());
 }
 
+static inline u64 ktime_get_boot_ns(void)
+{
+	return ktime_to_ns(ktime_get_boottime());
+}
+
 static inline u64 ktime_get_tai_ns(void)
 {
 	return ktime_to_ns(ktime_get_clocktai());
@@ -112,16 +133,44 @@ static inline u64 ktime_get_raw_ns(void)
 
 extern u64 ktime_get_mono_fast_ns(void);
 extern u64 ktime_get_raw_fast_ns(void);
+extern u64 ktime_get_boot_fast_ns(void);
 extern u64 ktime_get_real_fast_ns(void);
 
 /*
- * timespec64 interfaces utilizing the ktime based ones
+ * timespec64/time64_t interfaces utilizing the ktime based ones
+ * for API completeness, these could be implemented more efficiently
+ * if needed.
  */
-static inline void timekeeping_clocktai64(struct timespec64 *ts)
+static inline void ktime_get_boottime_ts64(struct timespec64 *ts)
+{
+	*ts = ktime_to_timespec64(ktime_get_boottime());
+}
+
+static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts)
+{
+	*ts = ktime_to_timespec64(ktime_get_coarse_boottime());
+}
+
+static inline time64_t ktime_get_boottime_seconds(void)
+{
+	return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC);
+}
+
+static inline void ktime_get_clocktai_ts64(struct timespec64 *ts)
 {
 	*ts = ktime_to_timespec64(ktime_get_clocktai());
 }
 
+static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts)
+{
+	*ts = ktime_to_timespec64(ktime_get_coarse_clocktai());
+}
+
+static inline time64_t ktime_get_clocktai_seconds(void)
+{
+	return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC);
+}
+
 /*
  * RTC specific
  */
@@ -197,5 +246,30 @@ extern void read_persistent_clock64(struct timespec64 *ts);
 extern void read_boot_clock64(struct timespec64 *ts);
 extern int update_persistent_clock64(struct timespec64 now);
 
+/*
+ * deprecated aliases, don't use in new code
+ */
+#define getnstimeofday64(ts)		ktime_get_real_ts64(ts)
+#define get_monotonic_boottime64(ts)	ktime_get_boottime_ts64(ts)
+#define getrawmonotonic64(ts)		ktime_get_raw_ts64(ts)
+#define timekeeping_clocktai64(ts)	ktime_get_clocktai_ts64(ts)
+
+static inline struct timespec64 current_kernel_time64(void)
+{
+	struct timespec64 ts;
+
+	ktime_get_coarse_real_ts64(&ts);
+
+	return ts;
+}
+
+static inline struct timespec64 get_monotonic_coarse64(void)
+{
+	struct timespec64 ts;
+
+	ktime_get_coarse_ts64(&ts);
+
+	return ts;
+}
 
 #endif
diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h
index af4114d5dc17..8762c2f45f8b 100644
--- a/include/linux/timekeeping32.h
+++ b/include/linux/timekeeping32.h
@@ -9,60 +9,15 @@
 extern void do_gettimeofday(struct timeval *tv);
 unsigned long get_seconds(void);
 
-/* does not take xtime_lock */
-struct timespec __current_kernel_time(void);
-
 static inline struct timespec current_kernel_time(void)
 {
-	struct timespec64 now = current_kernel_time64();
-
-	return timespec64_to_timespec(now);
-}
-
-#if BITS_PER_LONG == 64
-/**
- * Deprecated. Use do_settimeofday64().
- */
-static inline int do_settimeofday(const struct timespec *ts)
-{
-	return do_settimeofday64(ts);
-}
-
-static inline int __getnstimeofday(struct timespec *ts)
-{
-	return __getnstimeofday64(ts);
-}
-
-static inline void getnstimeofday(struct timespec *ts)
-{
-	getnstimeofday64(ts);
-}
-
-static inline void ktime_get_ts(struct timespec *ts)
-{
-	ktime_get_ts64(ts);
-}
-
-static inline void ktime_get_real_ts(struct timespec *ts)
-{
-	getnstimeofday64(ts);
-}
+	struct timespec64 ts64;
 
-static inline void getrawmonotonic(struct timespec *ts)
-{
-	getrawmonotonic64(ts);
-}
+	ktime_get_coarse_real_ts64(&ts64);
 
-static inline struct timespec get_monotonic_coarse(void)
-{
-	return get_monotonic_coarse64();
+	return timespec64_to_timespec(ts64);
 }
 
-static inline void getboottime(struct timespec *ts)
-{
-	return getboottime64(ts);
-}
-#else
 /**
  * Deprecated. Use do_settimeofday64().
  */
@@ -74,20 +29,11 @@ static inline int do_settimeofday(const struct timespec *ts)
 	return do_settimeofday64(&ts64);
 }
 
-static inline int __getnstimeofday(struct timespec *ts)
-{
-	struct timespec64 ts64;
-	int ret = __getnstimeofday64(&ts64);
-
-	*ts = timespec64_to_timespec(ts64);
-	return ret;
-}
-
 static inline void getnstimeofday(struct timespec *ts)
 {
 	struct timespec64 ts64;
 
-	getnstimeofday64(&ts64);
+	ktime_get_real_ts64(&ts64);
 	*ts = timespec64_to_timespec(ts64);
 }
 
@@ -103,7 +49,7 @@ static inline void ktime_get_real_ts(struct timespec *ts)
 {
 	struct timespec64 ts64;
 
-	getnstimeofday64(&ts64);
+	ktime_get_real_ts64(&ts64);
 	*ts = timespec64_to_timespec(ts64);
 }
 
@@ -111,13 +57,17 @@ static inline void getrawmonotonic(struct timespec *ts)
 {
 	struct timespec64 ts64;
 
-	getrawmonotonic64(&ts64);
+	ktime_get_raw_ts64(&ts64);
 	*ts = timespec64_to_timespec(ts64);
 }
 
 static inline struct timespec get_monotonic_coarse(void)
 {
-	return timespec64_to_timespec(get_monotonic_coarse64());
+	struct timespec64 ts64;
+
+	ktime_get_coarse_ts64(&ts64);
+
+	return timespec64_to_timespec(ts64);
 }
 
 static inline void getboottime(struct timespec *ts)
@@ -127,7 +77,6 @@ static inline void getboottime(struct timespec *ts)
 	getboottime64(&ts64);
 	*ts = timespec64_to_timespec(ts64);
 }
-#endif
 
 /*
  * Timespec interfaces utilizing the ktime based ones
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 2448f9cc48a3..7b066fd38248 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -8,8 +8,6 @@
 #include <linux/debugobjects.h>
 #include <linux/stringify.h>
 
-struct tvec_base;
-
 struct timer_list {
 	/*
 	 * All fields that change during normal runtime grouped to the
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 26c152122a42..4a8841963c2e 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -124,6 +124,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step)
 {
 	if (step) {
 		siginfo_t info;
+		clear_siginfo(&info);
 		user_single_step_siginfo(current, regs, &info);
 		force_sig_info(SIGTRAP, &info, current);
 		return;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 47f8af22f216..c56e3978b00f 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -10,6 +10,7 @@
 #include <linux/tty_ldisc.h>
 #include <linux/mutex.h>
 #include <linux/tty_flags.h>
+#include <linux/seq_file.h>
 #include <uapi/linux/tty.h>
 #include <linux/rwsem.h>
 #include <linux/llist.h>
@@ -527,7 +528,7 @@ static inline speed_t tty_get_baud_rate(struct tty_struct *tty)
 }
 
 extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old);
-extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b);
+extern int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b);
 extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt);
 
 extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *);
@@ -535,7 +536,7 @@ extern void tty_ldisc_deref(struct tty_ldisc *);
 extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *);
 extern void tty_ldisc_hangup(struct tty_struct *tty, bool reset);
 extern int tty_ldisc_reinit(struct tty_struct *tty, int disc);
-extern const struct file_operations tty_ldiscs_proc_fops;
+extern const struct seq_operations tty_ldiscs_seq_ops;
 
 extern void tty_wakeup(struct tty_struct *tty);
 extern void tty_ldisc_flush(struct tty_struct *tty);
@@ -701,7 +702,7 @@ extern int tty_unregister_ldisc(int disc);
 extern int tty_set_ldisc(struct tty_struct *tty, int disc);
 extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty);
 extern void tty_ldisc_release(struct tty_struct *tty);
-extern void tty_ldisc_init(struct tty_struct *tty);
+extern int __must_check tty_ldisc_init(struct tty_struct *tty);
 extern void tty_ldisc_deinit(struct tty_struct *tty);
 extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p,
 				 char *f, int count);
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 31c2b5b166de..71dbc891851a 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -293,7 +293,7 @@ struct tty_operations {
 	int (*poll_get_char)(struct tty_driver *driver, int line);
 	void (*poll_put_char)(struct tty_driver *driver, int line, char ch);
 #endif
-	const struct file_operations *proc_fops;
+	int (*proc_show)(struct seq_file *, void *);
 } __randomize_layout;
 
 struct tty_driver {
diff --git a/include/linux/uio.h b/include/linux/uio.h
index e67e12adb136..f5766e853a77 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -154,6 +154,12 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 #define _copy_from_iter_flushcache _copy_from_iter_nocache
 #endif
 
+#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
+size_t _copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i);
+#else
+#define _copy_to_iter_mcsafe _copy_to_iter
+#endif
+
 static __always_inline __must_check
 size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 {
@@ -163,6 +169,15 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 		return _copy_from_iter_flushcache(addr, bytes, i);
 }
 
+static __always_inline __must_check
+size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (unlikely(!check_copy_size(addr, bytes, false)))
+		return 0;
+	else
+		return _copy_to_iter_mcsafe(addr, bytes, i);
+}
+
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 unsigned long iov_iter_gap_alignment(const struct iov_iter *i);
diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h
index 3c85c81b0027..6c5f2074e14f 100644
--- a/include/linux/uio_driver.h
+++ b/include/linux/uio_driver.h
@@ -14,6 +14,7 @@
 #ifndef _UIO_DRIVER_H_
 #define _UIO_DRIVER_H_
 
+#include <linux/device.h>
 #include <linux/fs.h>
 #include <linux/interrupt.h>
 
@@ -68,12 +69,13 @@ struct uio_port {
 
 struct uio_device {
         struct module           *owner;
-        struct device           *dev;
+	struct device		dev;
         int                     minor;
         atomic_t                event;
         struct fasync_struct    *async_queue;
         wait_queue_head_t       wait;
         struct uio_info         *info;
+	spinlock_t		info_lock;
         struct kobject          *map_dir;
         struct kobject          *portio_dir;
 };
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 0173597e59aa..4cdd515a4385 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -490,6 +490,16 @@ enum usb_port_connect_type {
 };
 
 /*
+ * USB port quirks.
+ */
+
+/* For the given port, prefer the old (faster) enumeration scheme. */
+#define USB_PORT_QUIRK_OLD_SCHEME	BIT(0)
+
+/* Decrease TRSTRCY to 10ms during device enumeration. */
+#define USB_PORT_QUIRK_FAST_ENUM	BIT(1)
+
+/*
  * USB 2.0 Link Power Management (LPM) parameters.
  */
 struct usb2_lpm_parameters {
@@ -551,6 +561,8 @@ struct usb3_lpm_parameters {
  * @route: tree topology hex string for use with xHCI
  * @state: device state: configured, not attached, etc.
  * @speed: device speed: high/full/low (or error)
+ * @rx_lanes: number of rx lanes in use, USB 3.2 adds dual-lane support
+ * @tx_lanes: number of tx lanes in use, USB 3.2 adds dual-lane support
  * @tt: Transaction Translator info; used with low/full speed dev, highspeed hub
  * @ttport: device port on that tt hub
  * @toggle: one bit for each endpoint, with ([0] = IN, [1] = OUT) endpoints
@@ -624,6 +636,8 @@ struct usb_device {
 	u32		route;
 	enum usb_device_state	state;
 	enum usb_device_speed	speed;
+	unsigned int		rx_lanes;
+	unsigned int		tx_lanes;
 
 	struct usb_tt	*tt;
 	int		ttport;
diff --git a/include/linux/usb/atmel_usba_udc.h b/include/linux/usb/atmel_usba_udc.h
deleted file mode 100644
index 9bb00df3b53f..000000000000
--- a/include/linux/usb/atmel_usba_udc.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Platform data definitions for Atmel USBA gadget driver.
- */
-#ifndef __LINUX_USB_USBA_H
-#define __LINUX_USB_USBA_H
-
-struct usba_ep_data {
-	char	*name;
-	int	index;
-	int	fifo_size;
-	int	nr_banks;
-	int	can_dma;
-	int	can_isoc;
-};
-
-struct usba_platform_data {
-	int			vbus_pin;
-	int			vbus_pin_inverted;
-	int			num_ep;
-	struct usba_ep_data	ep[0];
-};
-
-#endif /* __LINUX_USB_USBA_H */
diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h
index aaafecf073ff..ba4b3e3327ff 100644
--- a/include/linux/usb/audio-v2.h
+++ b/include/linux/usb/audio-v2.h
@@ -94,7 +94,7 @@ struct uac_clock_selector_descriptor {
 	__u8 bClockID;
 	__u8 bNrInPins;
 	__u8 baCSourceID[];
-	/* bmControls, bAssocTerminal and iClockSource omitted */
+	/* bmControls and iClockSource omitted */
 } __attribute__((packed));
 
 /* 4.7.2.3 Clock Multiplier Descriptor */
@@ -189,6 +189,13 @@ struct uac2_iso_endpoint_descriptor {
 #define UAC2_CONTROL_DATA_OVERRUN	(3 << 2)
 #define UAC2_CONTROL_DATA_UNDERRUN	(3 << 4)
 
+/* 5.2.5.4.2 Connector Control Parameter Block */
+struct uac2_connectors_ctl_blk {
+	__u8 bNrChannels;
+	__le32 bmChannelConfig;
+	__u8 iChannelNames;
+} __attribute__((packed));
+
 /* 6.1 Interrupt Data Message */
 
 #define UAC2_INTERRUPT_DATA_MSG_VENDOR	(1 << 0)
diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h
index a8959aaba0ae..a710e28b5215 100644
--- a/include/linux/usb/audio-v3.h
+++ b/include/linux/usb/audio-v3.h
@@ -221,6 +221,12 @@ struct uac3_iso_endpoint_descriptor {
 	__le16 wLockDelay;
 } __attribute__((packed));
 
+/* 5.2.1.6.1 INSERTION CONTROL PARAMETER BLOCK */
+struct uac3_insertion_ctl_blk {
+	__u8 bSize;
+	__u8 bmConInserted;
+} __attribute__ ((packed));
+
 /* 6.1 INTERRUPT DATA MESSAGE */
 struct uac3_interrupt_data_msg {
 	__u8 bInfo;
@@ -392,4 +398,38 @@ struct uac3_interrupt_data_msg {
 #define UAC3_AC_ACTIVE_INTERFACE_CONTROL	0x01
 #define UAC3_AC_POWER_DOMAIN_CONTROL		0x02
 
+/* A.23.5 TERMINAL CONTROL SELECTORS */
+#define UAC3_TE_UNDEFINED			0x00
+#define UAC3_TE_INSERTION			0x01
+#define UAC3_TE_OVERLOAD			0x02
+#define UAC3_TE_UNDERFLOW			0x03
+#define UAC3_TE_OVERFLOW			0x04
+#define UAC3_TE_LATENCY 			0x05
+
+/* BADD predefined Unit/Terminal values */
+#define UAC3_BADD_IT_ID1	1  /* Input Terminal ID1: bTerminalID = 1 */
+#define UAC3_BADD_FU_ID2	2  /* Feature Unit ID2: bUnitID = 2 */
+#define UAC3_BADD_OT_ID3	3  /* Output Terminal ID3: bTerminalID = 3 */
+#define UAC3_BADD_IT_ID4	4  /* Input Terminal ID4: bTerminalID = 4 */
+#define UAC3_BADD_FU_ID5	5  /* Feature Unit ID5: bUnitID = 5 */
+#define UAC3_BADD_OT_ID6	6  /* Output Terminal ID6: bTerminalID = 6 */
+#define UAC3_BADD_FU_ID7	7  /* Feature Unit ID7: bUnitID = 7 */
+#define UAC3_BADD_MU_ID8	8  /* Mixer Unit ID8: bUnitID = 8 */
+#define UAC3_BADD_CS_ID9	9  /* Clock Source Entity ID9: bClockID = 9 */
+#define UAC3_BADD_PD_ID10	10 /* Power Domain ID10: bPowerDomainID = 10 */
+#define UAC3_BADD_PD_ID11	11 /* Power Domain ID11: bPowerDomainID = 11 */
+
+/* BADD wMaxPacketSize of AS endpoints */
+#define UAC3_BADD_EP_MAXPSIZE_SYNC_MONO_16		0x0060
+#define UAC3_BADD_EP_MAXPSIZE_ASYNC_MONO_16		0x0062
+#define UAC3_BADD_EP_MAXPSIZE_SYNC_MONO_24		0x0090
+#define UAC3_BADD_EP_MAXPSIZE_ASYNC_MONO_24		0x0093
+#define UAC3_BADD_EP_MAXPSIZE_SYNC_STEREO_16		0x00C0
+#define UAC3_BADD_EP_MAXPSIZE_ASYNC_STEREO_16		0x00C4
+#define UAC3_BADD_EP_MAXPSIZE_SYNC_STEREO_24		0x0120
+#define UAC3_BADD_EP_MAXPSIZE_ASYNC_STEREO_24		0x0126
+
+/* BADD sample rate is always fixed to 48kHz */
+#define UAC3_BADD_SAMPLING_RATE				48000
+
 #endif /* __LINUX_USB_AUDIO_V3_H */
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 4b6b9283fa7b..8675e145ea8b 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -52,7 +52,7 @@
 #define USB_GADGET_DELAYED_STATUS       0x7fff	/* Impossibly large value */
 
 /* big enough to hold our biggest descriptor */
-#define USB_COMP_EP0_BUFSIZ	1024
+#define USB_COMP_EP0_BUFSIZ	4096
 
 /* OS feature descriptor length <= 4kB */
 #define USB_COMP_EP0_OS_DESC_BUFSIZ	4096
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 847f423ad9b3..e5cd84a0f84a 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -763,7 +763,7 @@ struct usb_gadget_string_container {
 };
 
 /* put descriptor for string with that id into buf (buflen >= 256) */
-int usb_gadget_get_string(struct usb_gadget_strings *table, int id, u8 *buf);
+int usb_gadget_get_string(const struct usb_gadget_strings *table, int id, u8 *buf);
 
 /*-------------------------------------------------------------------------*/
 
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index aef50cb2ed1b..34a6ded6f319 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -150,7 +150,6 @@ struct usb_hcd {
 	unsigned		rh_pollable:1;	/* may we poll the root hub? */
 	unsigned		msix_enabled:1;	/* driver has MSI-X enabled? */
 	unsigned		msi_enabled:1;	/* driver has MSI enabled? */
-	unsigned		remove_phy:1;	/* auto-remove USB phy */
 	/*
 	 * do not manage the PHY state in the HCD core, instead let the driver
 	 * handle this (for example if the PHY can only be turned on after a
@@ -261,6 +260,7 @@ struct hc_driver {
 #define	HCD_USB25	0x0030		/* Wireless USB 1.0 (USB 2.5)*/
 #define	HCD_USB3	0x0040		/* USB 3.0 */
 #define	HCD_USB31	0x0050		/* USB 3.1 */
+#define	HCD_USB32	0x0060		/* USB 3.2 */
 #define	HCD_MASK	0x0070
 #define	HCD_BH		0x0100		/* URB complete in BH context */
 
diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h
index 9eb908a98033..fc6c77918481 100644
--- a/include/linux/usb/musb.h
+++ b/include/linux/usb/musb.h
@@ -67,28 +67,13 @@ struct musb_hdrc_config {
 	/* MUSB configuration-specific details */
 	unsigned	multipoint:1;	/* multipoint device */
 	unsigned	dyn_fifo:1 __deprecated; /* supports dynamic fifo sizing */
-	unsigned	soft_con:1 __deprecated; /* soft connect required */
-	unsigned	utm_16:1 __deprecated; /* utm data witdh is 16 bits */
-	unsigned	big_endian:1;	/* true if CPU uses big-endian */
-	unsigned	mult_bulk_tx:1;	/* Tx ep required for multbulk pkts */
-	unsigned	mult_bulk_rx:1;	/* Rx ep required for multbulk pkts */
-	unsigned	high_iso_tx:1;	/* Tx ep required for HB iso */
-	unsigned	high_iso_rx:1;	/* Rx ep required for HD iso */
-	unsigned	dma:1 __deprecated; /* supports DMA */
-	unsigned	vendor_req:1 __deprecated; /* vendor registers required */
 
 	/* need to explicitly de-assert the port reset after resume? */
 	unsigned	host_port_deassert_reset_at_resume:1;
 
 	u8		num_eps;	/* number of endpoints _with_ ep0 */
-	u8		dma_channels __deprecated; /* number of dma channels */
-	u8		dyn_fifo_size;	/* dynamic size in bytes */
-	u8		vendor_ctrl __deprecated; /* vendor control reg width */
-	u8		vendor_stat __deprecated; /* vendor status reg witdh */
-	u8		dma_req_chan __deprecated; /* bitmask for required dma channels */
 	u8		ram_bits;	/* ram address size */
 
-	struct musb_hdrc_eps_bits *eps_bits __deprecated;
 	u32		maximum_speed;
 };
 
diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index ff359bdfdc7b..09b570feb297 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -103,8 +103,8 @@ enum pd_ext_msg_type {
 	 (((cnt) & PD_HEADER_CNT_MASK) << PD_HEADER_CNT_SHIFT) |	\
 	 ((ext_hdr) ? PD_HEADER_EXT_HDR : 0))
 
-#define PD_HEADER_LE(type, pwr, data, id, cnt) \
-	cpu_to_le16(PD_HEADER((type), (pwr), (data), PD_REV20, (id), (cnt), (0)))
+#define PD_HEADER_LE(type, pwr, data, rev, id, cnt) \
+	cpu_to_le16(PD_HEADER((type), (pwr), (data), (rev), (id), (cnt), (0)))
 
 static inline unsigned int pd_header_cnt(u16 header)
 {
diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index b7a2625947f5..e4de6bc1f69b 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -157,22 +157,6 @@ struct usb_phy {
 	enum usb_charger_type (*charger_detect)(struct usb_phy *x);
 };
 
-/**
- * struct usb_phy_bind - represent the binding for the phy
- * @dev_name: the device name of the device that will bind to the phy
- * @phy_dev_name: the device name of the phy
- * @index: used if a single controller uses multiple phys
- * @phy: reference to the phy
- * @list: to maintain a linked list of the binding information
- */
-struct usb_phy_bind {
-	const char	*dev_name;
-	const char	*phy_dev_name;
-	u8		index;
-	struct usb_phy	*phy;
-	struct list_head list;
-};
-
 /* for board-specific init logic */
 extern int usb_add_phy(struct usb_phy *, enum usb_phy_type type);
 extern int usb_add_phy_dev(struct usb_phy *);
@@ -234,16 +218,12 @@ usb_phy_vbus_off(struct usb_phy *x)
 extern struct usb_phy *usb_get_phy(enum usb_phy_type type);
 extern struct usb_phy *devm_usb_get_phy(struct device *dev,
 	enum usb_phy_type type);
-extern struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index);
-extern struct usb_phy *devm_usb_get_phy_dev(struct device *dev, u8 index);
 extern struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev,
 	const char *phandle, u8 index);
 extern struct usb_phy *devm_usb_get_phy_by_node(struct device *dev,
 	struct device_node *node, struct notifier_block *nb);
 extern void usb_put_phy(struct usb_phy *);
 extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x);
-extern int usb_bind_phy(const char *dev_name, u8 index,
-				const char *phy_dev_name);
 extern void usb_phy_set_event(struct usb_phy *x, unsigned long event);
 extern void usb_phy_set_charger_current(struct usb_phy *usb_phy,
 					unsigned int mA);
@@ -263,16 +243,6 @@ static inline struct usb_phy *devm_usb_get_phy(struct device *dev,
 	return ERR_PTR(-ENXIO);
 }
 
-static inline struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index)
-{
-	return ERR_PTR(-ENXIO);
-}
-
-static inline struct usb_phy *devm_usb_get_phy_dev(struct device *dev, u8 index)
-{
-	return ERR_PTR(-ENXIO);
-}
-
 static inline struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev,
 	const char *phandle, u8 index)
 {
@@ -293,12 +263,6 @@ static inline void devm_usb_put_phy(struct device *dev, struct usb_phy *x)
 {
 }
 
-static inline int usb_bind_phy(const char *dev_name, u8 index,
-				const char *phy_dev_name)
-{
-	return -EOPNOTSUPP;
-}
-
 static inline void usb_phy_set_event(struct usb_phy *x, unsigned long event)
 {
 }
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index f0d839daeaea..b231b9314240 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -36,6 +36,7 @@ enum typec_cc_polarity {
 /* Time to wait for TCPC to complete transmit */
 #define PD_T_TCPC_TX_TIMEOUT	100		/* in ms	*/
 #define PD_ROLE_SWAP_TIMEOUT	(MSEC_PER_SEC * 10)
+#define PD_PPS_CTRL_TIMEOUT	(MSEC_PER_SEC * 10)
 
 enum tcpm_transmit_status {
 	TCPC_TX_SUCCESS = 0,
@@ -62,9 +63,6 @@ enum tcpm_transmit_type {
  * @snk_pdo:	PDO parameters sent to partner as response to
  *		PD_CTRL_GET_SINK_CAP message
  * @nr_snk_pdo:	Number of entries in @snk_pdo
- * @max_snk_mv:	Maximum acceptable sink voltage in mV
- * @max_snk_ma:	Maximum sink current in mA
- * @max_snk_mw:	Maximum required sink power in mW
  * @operating_snk_mw:
  *		Required operating sink power in mW
  * @type:	Port type (TYPEC_PORT_DFP, TYPEC_PORT_UFP, or
@@ -85,9 +83,6 @@ struct tcpc_config {
 	const u32 *snk_vdo;
 	unsigned int nr_snk_vdo;
 
-	unsigned int max_snk_mv;
-	unsigned int max_snk_ma;
-	unsigned int max_snk_mw;
 	unsigned int operating_snk_mw;
 
 	enum typec_port_type type;
@@ -174,9 +169,6 @@ int tcpm_update_source_capabilities(struct tcpm_port *port, const u32 *pdo,
 				    unsigned int nr_pdo);
 int tcpm_update_sink_capabilities(struct tcpm_port *port, const u32 *pdo,
 				  unsigned int nr_pdo,
-				  unsigned int max_snk_mv,
-				  unsigned int max_snk_ma,
-				  unsigned int max_snk_mw,
 				  unsigned int operating_snk_mw);
 
 void tcpm_vbus_change(struct tcpm_port *port);
diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h
index d641ea1660b7..0c5c3ea8b2d7 100644
--- a/include/linux/usb/tegra_usb_phy.h
+++ b/include/linux/usb/tegra_usb_phy.h
@@ -17,6 +17,7 @@
 #define __TEGRA_USB_PHY_H
 
 #include <linux/clk.h>
+#include <linux/reset.h>
 #include <linux/usb/otg.h>
 
 /*
@@ -76,6 +77,7 @@ struct tegra_usb_phy {
 	bool is_legacy_phy;
 	bool is_ulpi_phy;
 	int reset_gpio;
+	struct reset_control *pad_rst;
 };
 
 void tegra_usb_phy_preresume(struct usb_phy *phy);
diff --git a/include/linux/vbox_utils.h b/include/linux/vbox_utils.h
index c71def6b310f..a240ed2a0372 100644
--- a/include/linux/vbox_utils.h
+++ b/include/linux/vbox_utils.h
@@ -24,24 +24,6 @@ __printf(1, 2) void vbg_debug(const char *fmt, ...);
 #define vbg_debug pr_debug
 #endif
 
-/**
- * Allocate memory for generic request and initialize the request header.
- *
- * Return: the allocated memory
- * @len:		Size of memory block required for the request.
- * @req_type:		The generic request type.
- */
-void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type);
-
-/**
- * Perform a generic request.
- *
- * Return: VBox status code
- * @gdev:		The Guest extension device.
- * @req:		Pointer to the request structure.
- */
-int vbg_req_perform(struct vbg_dev *gdev, void *req);
-
 int vbg_hgcm_connect(struct vbg_dev *gdev,
 		     struct vmmdev_hgcm_service_location *loc,
 		     u32 *client_id, int *vbox_status);
@@ -52,11 +34,6 @@ int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
 		  u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms,
 		  u32 parm_count, int *vbox_status);
 
-int vbg_hgcm_call32(
-	struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
-	struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
-	int *vbox_status);
-
 /**
  * Convert a VirtualBox status code to a standard Linux kernel return value.
  * Return: 0 or negative errno value.
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 988c7355bc22..fa1b5da2804e 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -157,6 +157,9 @@ int virtio_device_freeze(struct virtio_device *dev);
 int virtio_device_restore(struct virtio_device *dev);
 #endif
 
+#define virtio_device_for_each_vq(vdev, vq) \
+	list_for_each_entry(vq, &vdev->vqs, list)
+
 /**
  * virtio_driver - operations for a virtio I/O driver
  * @driver: underlying device driver (populate name and owner).
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index 9318b2166439..2b0072fa5e92 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -305,4 +305,21 @@ do {									\
 	__ret;								\
 })
 
+/**
+ * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit
+ *
+ * @bit: the bit of the word being waited on
+ * @word: the word being waited on, a kernel virtual address
+ *
+ * You can use this helper if bitflags are manipulated atomically rather than
+ * non-atomically under a lock.
+ */
+static inline void clear_and_wake_up_bit(int bit, void *word)
+{
+	clear_bit_unlock(bit, word);
+	/* See wake_up_bit() for which memory barrier you need to use. */
+	smp_mb__after_atomic();
+	wake_up_bit(word, bit);
+}
+
 #endif /* _LINUX_WAIT_BIT_H */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 39a0e215022a..60d673e15632 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -494,6 +494,7 @@ extern unsigned int work_busy(struct work_struct *work);
 extern __printf(1, 2) void set_worker_desc(const char *fmt, ...);
 extern void print_worker_info(const char *log_lvl, struct task_struct *task);
 extern void show_workqueue_state(void);
+extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task);
 
 /**
  * queue_work - queue work on a workqueue
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index d70f77a4b62a..6dad031be3c2 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -46,7 +46,6 @@ struct xattr {
 	size_t value_len;
 };
 
-ssize_t xattr_getsecurity(struct inode *, const char *, void *, size_t);
 ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t);
 ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t);
 ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size);
diff --git a/include/media/i2c/tvp7002.h b/include/media/i2c/tvp7002.h
index 5ee007c1cead..cb213c136089 100644
--- a/include/media/i2c/tvp7002.h
+++ b/include/media/i2c/tvp7002.h
@@ -5,7 +5,7 @@
  * Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
  *
  * This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
  * the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
  * and the TVP7002 driver in the TI LSP 2.10.00.14
  *
diff --git a/include/media/videobuf-core.h b/include/media/videobuf-core.h
index 0bda0adc744f..60a664febba0 100644
--- a/include/media/videobuf-core.h
+++ b/include/media/videobuf-core.h
@@ -1,11 +1,11 @@
 /*
  * generic helper functions for handling video4linux capture buffers
  *
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
  *
  * Highly based on video-buf written originally by:
  * (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
  * (c) 2006 Ted Walther and John Sokol
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/include/media/videobuf-dma-sg.h b/include/media/videobuf-dma-sg.h
index d8b27854e3bf..01bd142b979d 100644
--- a/include/media/videobuf-dma-sg.h
+++ b/include/media/videobuf-dma-sg.h
@@ -6,11 +6,11 @@
  * into PAGE_SIZE chunks).  They also assume the driver does not need
  * to touch the video data.
  *
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
  *
  * Highly based on video-buf written originally by:
  * (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
  * (c) 2006 Ted Walther and John Sokol
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/include/media/videobuf-vmalloc.h b/include/media/videobuf-vmalloc.h
index 486a97efdb56..36c6a4ad3504 100644
--- a/include/media/videobuf-vmalloc.h
+++ b/include/media/videobuf-vmalloc.h
@@ -6,7 +6,7 @@
  * into PAGE_SIZE chunks).  They also assume the driver does not need
  * to touch the video data.
  *
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/include/net/ax25.h b/include/net/ax25.h
index c91bc87931c7..3f9aea8087e3 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -15,6 +15,7 @@
 #include <linux/refcount.h>
 #include <net/neighbour.h>
 #include <net/sock.h>
+#include <linux/seq_file.h>
 
 #define	AX25_T1CLAMPLO  		1
 #define	AX25_T1CLAMPHI 			(30 * HZ)
@@ -399,7 +400,7 @@ int ax25_check_iframes_acked(ax25_cb *, unsigned short);
 /* ax25_route.c */
 void ax25_rt_device_down(struct net_device *);
 int ax25_rt_ioctl(unsigned int, void __user *);
-extern const struct file_operations ax25_route_fops;
+extern const struct seq_operations ax25_rt_seqops;
 ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev);
 int ax25_rt_autobind(ax25_cb *, ax25_address *);
 struct sk_buff *ax25_rt_build_path(struct sk_buff *, ax25_address *,
@@ -455,7 +456,7 @@ unsigned long ax25_display_timer(struct timer_list *);
 extern int  ax25_uid_policy;
 ax25_uid_assoc *ax25_findbyuid(kuid_t);
 int __must_check ax25_uid_ioctl(int, struct sockaddr_ax25 *);
-extern const struct file_operations ax25_uid_fops;
+extern const struct seq_operations ax25_uid_seqops;
 void ax25_uid_free(void);
 
 /* sysctl_net_ax25.c */
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index ec9d6bc65855..53ce8176c313 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -271,7 +271,7 @@ int  bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		     int flags);
 int  bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 			    size_t len, int flags);
-__poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events);
 int  bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int  bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo);
 int  bt_sock_wait_ready(struct sock *sk, unsigned long flags);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index f801fc940b29..b52235158836 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -198,6 +198,7 @@ struct bonding {
 	struct   slave __rcu *primary_slave;
 	struct   bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
 	bool     force_primary;
+	u32      nest_level;
 	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
 	int     (*recv_probe)(const struct sk_buff *, struct bonding *,
 			      struct slave *);
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 71c72a939bf8..c5187438af38 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -121,6 +121,21 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 #endif
 }
 
+static inline void sock_poll_busy_loop(struct socket *sock, __poll_t events)
+{
+	if (sk_can_busy_loop(sock->sk) &&
+	    events && (events & POLL_BUSY_LOOP)) {
+		/* once, only if requested by syscall */
+		sk_busy_loop(sock->sk, 1);
+	}
+}
+
+/* if this socket can poll_ll, tell the system call */
+static inline __poll_t sock_poll_busy_flag(struct socket *sock)
+{
+	return sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0;
+}
+
 /* used in the NIC receive handler to mark the skb */
 static inline void skb_mark_napi_id(struct sk_buff *skb,
 				    struct napi_struct *napi)
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 9a074776f70b..d1fcf2442a42 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -251,7 +251,7 @@ extern struct flow_dissector flow_keys_buf_dissector;
  * This structure is used to hold a digest of the full flow keys. This is a
  * larger "hash" of a flow to allow definitively matching specific flows where
  * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so
- * that it can by used in CB of skb (see sch_choke for an example).
+ * that it can be used in CB of skb (see sch_choke for an example).
  */
 #define FLOW_KEYS_DIGEST_LEN	16
 struct flow_keys_digest {
diff --git a/include/net/ife.h b/include/net/ife.h
index 44b9c00f7223..e117617e3c34 100644
--- a/include/net/ife.h
+++ b/include/net/ife.h
@@ -12,7 +12,8 @@
 void *ife_encode(struct sk_buff *skb, u16 metalen);
 void *ife_decode(struct sk_buff *skb, u16 *metalen);
 
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen);
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+			  u16 *dlen, u16 *totlen);
 int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
 			const void *dval);
 
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 5e86fd9dc857..0e79c3408569 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -394,7 +394,15 @@ void fib6_gc_cleanup(void);
 
 int fib6_init(void);
 
-int ipv6_route_open(struct inode *inode, struct file *file);
+struct ipv6_route_iter {
+	struct seq_net_private p;
+	struct fib6_walker w;
+	loff_t skip;
+	struct fib6_table *tbl;
+	int sernum;
+};
+
+extern const struct seq_operations ipv6_route_seq_ops;
 
 int call_fib6_notifier(struct notifier_block *nb, struct net *net,
 		       enum fib_event_type event_type,
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index eb0bec043c96..aea7a124e66b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -41,18 +41,6 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
 	return net->ipvs;
 }
 
-/* This one needed for single_open_net since net is stored directly in
- * private not as a struct i.e. seq_file_net can't be used.
- */
-static inline struct net *seq_file_single_net(struct seq_file *seq)
-{
-#ifdef CONFIG_NET_NS
-	return (struct net *)seq->private;
-#else
-	return &init_net;
-#endif
-}
-
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
 
diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h
index f4c21b5a1242..b0eaeb02d46d 100644
--- a/include/net/iucv/af_iucv.h
+++ b/include/net/iucv/af_iucv.h
@@ -153,8 +153,6 @@ struct iucv_sock_list {
 	atomic_t	  autobind_name;
 };
 
-__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
-			    poll_table *wait);
 void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
 void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
 void iucv_accept_enqueue(struct sock *parent, struct sock *sk);
diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index 5c40f118c0fa..df528a623548 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb)
 
 struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
 			  struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
 void llc_sk_free(struct sock *sk);
 
 void llc_sk_reset(struct sock *sk);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d2279b2d61aa..b2f3a0c018e7 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2080,7 +2080,7 @@ struct ieee80211_txq {
  *	virtual interface might not be given air time for the transmission of
  *	the frame, as it is not synced with the AP/P2P GO yet, and thus the
  *	deauthentication frame might not be transmitted.
- >
+ *
  * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't
  *	support QoS NDP for AP probing - that's most likely a driver bug.
  *
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index cd368d1b8cb8..a1e28dd5d0bf 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -170,6 +170,7 @@ struct nft_data_desc {
 int nft_data_init(const struct nft_ctx *ctx,
 		  struct nft_data *data, unsigned int size,
 		  struct nft_data_desc *desc, const struct nlattr *nla);
+void nft_data_hold(const struct nft_data *data, enum nft_data_types type);
 void nft_data_release(const struct nft_data *data, enum nft_data_types type);
 int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
 		  enum nft_data_types type, unsigned int len);
@@ -736,6 +737,10 @@ struct nft_expr_ops {
 	int				(*init)(const struct nft_ctx *ctx,
 						const struct nft_expr *expr,
 						const struct nlattr * const tb[]);
+	void				(*activate)(const struct nft_ctx *ctx,
+						    const struct nft_expr *expr);
+	void				(*deactivate)(const struct nft_ctx *ctx,
+						      const struct nft_expr *expr);
 	void				(*destroy)(const struct nft_ctx *ctx,
 						   const struct nft_expr *expr);
 	int				(*dump)(struct sk_buff *skb,
diff --git a/include/net/netrom.h b/include/net/netrom.h
index 0dad2dd5f9d7..5a0714ff500f 100644
--- a/include/net/netrom.h
+++ b/include/net/netrom.h
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <linux/refcount.h>
+#include <linux/seq_file.h>
 
 #define	NR_NETWORK_LEN			15
 #define	NR_TRANSPORT_LEN		5
@@ -216,8 +217,8 @@ struct net_device *nr_dev_get(ax25_address *);
 int nr_rt_ioctl(unsigned int, void __user *);
 void nr_link_failed(ax25_cb *, int);
 int nr_route_frame(struct sk_buff *, ax25_cb *);
-extern const struct file_operations nr_nodes_fops;
-extern const struct file_operations nr_neigh_fops;
+extern const struct seq_operations nr_node_seqops;
+extern const struct seq_operations nr_neigh_seqops;
 void nr_rt_free(void);
 
 /* nr_subr.c */
diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h
index 8639de5750f6..cbee32be1d9c 100644
--- a/include/net/phonet/pn_dev.h
+++ b/include/net/phonet/pn_dev.h
@@ -56,7 +56,7 @@ struct net_device *phonet_route_output(struct net *net, u8 daddr);
 
 #define PN_NO_ADDR	0xff
 
-extern const struct file_operations pn_sock_seq_fops;
-extern const struct file_operations pn_res_seq_fops;
+extern const struct seq_operations pn_sock_seq_ops;
+extern const struct seq_operations pn_res_seq_ops;
 
 #endif
diff --git a/include/net/ping.h b/include/net/ping.h
index 4cd90d6b5c25..fd080e043a6e 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -83,20 +83,9 @@ int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 bool ping_rcv(struct sk_buff *skb);
 
 #ifdef CONFIG_PROC_FS
-struct ping_seq_afinfo {
-	char				*name;
-	sa_family_t			family;
-	const struct file_operations	*seq_fops;
-	const struct seq_operations	seq_ops;
-};
-
-extern const struct file_operations ping_seq_fops;
-
 void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
 void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos);
 void ping_seq_stop(struct seq_file *seq, void *v);
-int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo);
-void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo);
 
 int __init ping_proc_init(void);
 void ping_proc_exit(void);
diff --git a/include/net/raw.h b/include/net/raw.h
index 99d26d0c4a19..9c9fa98a91a4 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -48,7 +48,6 @@ void raw_proc_exit(void);
 struct raw_iter_state {
 	struct seq_net_private p;
 	int bucket;
-	struct raw_hashinfo *h;
 };
 
 static inline struct raw_iter_state *raw_seq_private(struct seq_file *seq)
@@ -58,9 +57,6 @@ static inline struct raw_iter_state *raw_seq_private(struct seq_file *seq)
 void *raw_seq_start(struct seq_file *seq, loff_t *pos);
 void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos);
 void raw_seq_stop(struct seq_file *seq, void *v);
-int raw_seq_open(struct inode *ino, struct file *file,
-		 struct raw_hashinfo *h, const struct seq_operations *ops);
-
 #endif
 
 int raw_hash_sk(struct sock *sk);
diff --git a/include/net/rose.h b/include/net/rose.h
index 04b72681f2ab..cf517d306a28 100644
--- a/include/net/rose.h
+++ b/include/net/rose.h
@@ -200,9 +200,9 @@ void rose_enquiry_response(struct sock *);
 
 /* rose_route.c */
 extern struct rose_neigh *rose_loopback_neigh;
-extern const struct file_operations rose_neigh_fops;
-extern const struct file_operations rose_nodes_fops;
-extern const struct file_operations rose_routes_fops;
+extern const struct seq_operations rose_neigh_seqops;
+extern const struct seq_operations rose_node_seqops;
+extern struct seq_operations rose_route_seqops;
 
 void rose_add_loopback_neigh(void);
 int __must_check rose_add_loopback_node(rose_address *);
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 28b996d63490..e6d349b2a791 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -103,12 +103,13 @@ void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int);
 /*
  * sctp/socket.c
  */
+int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr,
+		      int addr_len, int flags);
 int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 int sctp_inet_listen(struct socket *sock, int backlog);
 void sctp_write_space(struct sock *sk);
 void sctp_data_ready(struct sock *sk);
-__poll_t sctp_poll(struct file *file, struct socket *sock,
-		poll_table *wait);
+__poll_t sctp_poll_mask(struct socket *sock, __poll_t events);
 void sctp_sock_rfree(struct sk_buff *skb);
 void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 		    struct sctp_association *asoc);
diff --git a/include/net/sock.h b/include/net/sock.h
index 74d725fdbe0f..4d2e8ad98985 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1591,8 +1591,6 @@ int sock_no_connect(struct socket *, struct sockaddr *, int, int);
 int sock_no_socketpair(struct socket *, struct socket *);
 int sock_no_accept(struct socket *, struct socket *, int, bool);
 int sock_no_getname(struct socket *, struct sockaddr *, int);
-__poll_t sock_no_poll(struct file *, struct socket *,
-			  struct poll_table_struct *);
 int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
 int sock_no_listen(struct socket *, int);
 int sock_no_shutdown(struct socket *, int);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9c9b3768b350..f88f8a2cab0d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -388,8 +388,7 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
 void tcp_init_transfer(struct sock *sk, int bpf_op);
-__poll_t tcp_poll(struct file *file, struct socket *sock,
-		      struct poll_table_struct *wait);
+__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
 int tcp_setsockopt(struct sock *sk, int level, int optname,
@@ -1747,27 +1746,22 @@ enum tcp_seq_states {
 	TCP_SEQ_STATE_ESTABLISHED,
 };
 
-int tcp_seq_open(struct inode *inode, struct file *file);
+void *tcp_seq_start(struct seq_file *seq, loff_t *pos);
+void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void tcp_seq_stop(struct seq_file *seq, void *v);
 
 struct tcp_seq_afinfo {
-	char				*name;
 	sa_family_t			family;
-	const struct file_operations	*seq_fops;
-	struct seq_operations		seq_ops;
 };
 
 struct tcp_iter_state {
 	struct seq_net_private	p;
-	sa_family_t		family;
 	enum tcp_seq_states	state;
 	struct sock		*syn_wait_sk;
 	int			bucket, offset, sbucket, num;
 	loff_t			last_pos;
 };
 
-int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo);
-void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo);
-
 extern struct request_sock_ops tcp_request_sock_ops;
 extern struct request_sock_ops tcp6_request_sock_ops;
 
diff --git a/include/net/tls.h b/include/net/tls.h
index 3da8e13a6d96..f5fb16da3860 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -97,6 +97,9 @@ struct tls_sw_context {
 	u8 control;
 	bool decrypted;
 
+	char rx_aad_ciphertext[TLS_AAD_SPACE_SIZE];
+	char rx_aad_plaintext[TLS_AAD_SPACE_SIZE];
+
 	/* Sending context */
 	char aad_space[TLS_AAD_SPACE_SIZE];
 
@@ -148,6 +151,7 @@ struct tls_context {
 	struct scatterlist *partially_sent_record;
 	u16 partially_sent_offset;
 	unsigned long flags;
+	bool in_tcp_sendpages;
 
 	u16 pending_open_record_frags;
 	int (*push_pending_record)(struct sock *sk, int flags);
diff --git a/include/net/udp.h b/include/net/udp.h
index 0676b272f6ac..d8ca3b26964d 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -276,7 +276,7 @@ int udp_init_sock(struct sock *sk);
 int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int __udp_disconnect(struct sock *sk, int flags);
 int udp_disconnect(struct sock *sk, int flags);
-__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t udp_poll_mask(struct socket *sock, __poll_t events);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features,
 				       bool is_ipv6);
@@ -408,31 +408,27 @@ do {									\
 #define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0)
 #endif
 
-/* /proc */
-int udp_seq_open(struct inode *inode, struct file *file);
-
+#ifdef CONFIG_PROC_FS
 struct udp_seq_afinfo {
-	char				*name;
 	sa_family_t			family;
 	struct udp_table		*udp_table;
-	const struct file_operations	*seq_fops;
-	struct seq_operations		seq_ops;
 };
 
 struct udp_iter_state {
 	struct seq_net_private  p;
-	sa_family_t		family;
 	int			bucket;
-	struct udp_table	*udp_table;
 };
 
-#ifdef CONFIG_PROC_FS
-int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo);
-void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo);
+void *udp_seq_start(struct seq_file *seq, loff_t *pos);
+void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void udp_seq_stop(struct seq_file *seq, void *v);
+
+extern const struct seq_operations udp_seq_ops;
+extern const struct seq_operations udp6_seq_ops;
 
 int udp4_proc_init(void);
 void udp4_proc_exit(void);
-#endif
+#endif /* CONFIG_PROC_FS */
 
 int udpv4_offload_init(void);
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index a872379b69da..45e75c36b738 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -375,6 +375,7 @@ struct xfrm_input_afinfo {
 int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo);
 int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo);
 
+void xfrm_flush_gc(void);
 void xfrm_state_delete_tunnel(struct xfrm_state *x);
 
 struct xfrm_type {
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 23159dd5be18..a1fd63871d17 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -48,7 +48,6 @@ struct ib_umem {
 	int                     writable;
 	int                     hugetlb;
 	struct work_struct	work;
-	struct pid             *pid;
 	struct mm_struct       *mm;
 	unsigned long		diff;
 	struct ib_umem_odp     *odp_data;
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index 4a4201d997a7..095383a4bd1a 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -411,13 +411,13 @@ static inline int uverbs_attr_get_enum_id(const struct uverbs_attr_bundle *attrs
 static inline void *uverbs_attr_get_obj(const struct uverbs_attr_bundle *attrs_bundle,
 					u16 idx)
 {
-	struct ib_uobject *uobj =
-		uverbs_attr_get(attrs_bundle, idx)->obj_attr.uobject;
+	const struct uverbs_attr *attr;
 
-	if (IS_ERR(uobj))
-		return uobj;
+	attr = uverbs_attr_get(attrs_bundle, idx);
+	if (IS_ERR(attr))
+		return ERR_CAST(attr);
 
-	return uobj->object;
+	return attr->obj_attr.uobject->object;
 }
 
 static inline int uverbs_copy_to(const struct uverbs_attr_bundle *attrs_bundle,
diff --git a/include/scsi/osd_initiator.h b/include/scsi/osd_initiator.h
index a29d3086eb56..86a569d008b2 100644
--- a/include/scsi/osd_initiator.h
+++ b/include/scsi/osd_initiator.h
@@ -148,7 +148,6 @@ struct osd_request {
 		u8 *pad_buff;
 	} out, in;
 
-	gfp_t alloc_flags;
 	unsigned timeout;
 	unsigned retries;
 	unsigned sense_len;
@@ -202,14 +201,11 @@ static inline bool osd_req_is_ver1(struct osd_request *or)
  *
  * @osd_dev:    OSD device that holds the scsi-device and default values
  *              that the request is associated with.
- * @gfp:        The allocation flags to use for request allocation, and all
- *              subsequent allocations. This will be stored at
- *              osd_request->alloc_flags, can be changed by user later
  *
  * Allocate osd_request and initialize all members to the
  * default/initial state.
  */
-struct osd_request *osd_start_request(struct osd_dev *od, gfp_t gfp);
+struct osd_request *osd_start_request(struct osd_dev *od);
 
 enum osd_req_options {
 	OSD_REQ_FUA = 0x08,	/* Force Unit Access */
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 04e0679767f6..e03bd9d41fa8 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -11,8 +11,6 @@ struct scsi_sense_hdr;
 extern void scsi_print_command(struct scsi_cmnd *);
 extern size_t __scsi_format_command(char *, size_t,
 				   const unsigned char *, size_t);
-extern void scsi_show_extd_sense(const struct scsi_device *, const char *,
-				 unsigned char, unsigned char);
 extern void scsi_print_sense_hdr(const struct scsi_device *, const char *,
 				 const struct scsi_sense_hdr *);
 extern void scsi_print_sense(const struct scsi_cmnd *);
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 12f454cb6f61..53b485fe9b67 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -307,7 +307,7 @@ struct scsi_host_template {
 	 * EH_HANDLED:		I fixed the error, please complete the command
 	 * EH_RESET_TIMER:	I need more time, reset the timer and
 	 *			begin counting again
-	 * EH_NOT_HANDLED	Begin normal error recovery
+	 * EH_DONE:		Begin normal error recovery
 	 *
 	 * Status: OPTIONAL
 	 */
diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h
index 50df5b28d2c9..8ee8991aa099 100644
--- a/include/soc/bcm2835/raspberrypi-firmware.h
+++ b/include/soc/bcm2835/raspberrypi-firmware.h
@@ -143,13 +143,13 @@ struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node);
 static inline int rpi_firmware_property(struct rpi_firmware *fw, u32 tag,
 					void *data, size_t len)
 {
-	return 0;
+	return -ENOSYS;
 }
 
 static inline int rpi_firmware_property_list(struct rpi_firmware *fw,
 					     void *data, size_t tag_size)
 {
-	return 0;
+	return -ENOSYS;
 }
 
 static inline struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node)
diff --git a/include/sound/control.h b/include/sound/control.h
index ca13a44ae9d4..6011a58d3e20 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -23,6 +23,7 @@
  */
 
 #include <linux/wait.h>
+#include <linux/nospec.h>
 #include <sound/asound.h>
 
 #define snd_kcontrol_chip(kcontrol) ((kcontrol)->private_data)
@@ -148,12 +149,14 @@ int snd_ctl_get_preferred_subdevice(struct snd_card *card, int type);
 
 static inline unsigned int snd_ctl_get_ioffnum(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
 {
-	return id->numid - kctl->id.numid;
+	unsigned int ioff = id->numid - kctl->id.numid;
+	return array_index_nospec(ioff, kctl->count);
 }
 
 static inline unsigned int snd_ctl_get_ioffidx(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
 {
-	return id->index - kctl->id.index;
+	unsigned int ioff = id->index - kctl->id.index;
+	return array_index_nospec(ioff, kctl->count);
 }
 
 static inline unsigned int snd_ctl_get_ioff(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
diff --git a/include/sound/core.h b/include/sound/core.h
index 5f181b875c2f..36a5934cf4b1 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -51,7 +51,6 @@ struct completion;
  */
 enum snd_device_type {
 	SNDRV_DEV_LOWLEVEL,
-	SNDRV_DEV_CONTROL,
 	SNDRV_DEV_INFO,
 	SNDRV_DEV_BUS,
 	SNDRV_DEV_CODEC,
@@ -62,6 +61,7 @@ enum snd_device_type {
 	SNDRV_DEV_SEQUENCER,
 	SNDRV_DEV_HWDEP,
 	SNDRV_DEV_JACK,
+	SNDRV_DEV_CONTROL,	/* NOTE: this must be the last one */
 };
 
 enum snd_device_state {
diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index 5ebcc51c0a6a..8c1572de44c5 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -1610,7 +1610,7 @@ struct snd_emu10k1_fx8010_pcm {
 	struct snd_pcm_indirect pcm_rec;
 	unsigned int tram_pos;
 	unsigned int tram_shift;
-	struct snd_emu10k1_fx8010_irq *irq;
+	struct snd_emu10k1_fx8010_irq irq;
 };
 
 struct snd_emu10k1_fx8010 {
@@ -1902,7 +1902,7 @@ int snd_emu10k1_fx8010_register_irq_handler(struct snd_emu10k1 *emu,
 					    snd_fx8010_irq_handler_t *handler,
 					    unsigned char gpr_running,
 					    void *private_data,
-					    struct snd_emu10k1_fx8010_irq **r_irq);
+					    struct snd_emu10k1_fx8010_irq *irq);
 int snd_emu10k1_fx8010_unregister_irq_handler(struct snd_emu10k1 *emu,
 					      struct snd_emu10k1_fx8010_irq *irq);
 
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index 06536e01ed94..c052afc27547 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -571,4 +571,9 @@ static inline unsigned int snd_array_index(struct snd_array *array, void *ptr)
 	return (unsigned long)(ptr - array->list) / array->elem_size;
 }
 
+/* a helper macro to iterate for each snd_array element */
+#define snd_array_for_each(array, idx, ptr) \
+	for ((idx) = 0, (ptr) = (array)->list; (idx) < (array)->used; \
+	     (ptr) = snd_array_elem(array, ++(idx)))
+
 #endif /* __SOUND_HDAUDIO_H */
diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index 782d1df34208..9c3db3dce32b 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -34,11 +34,9 @@ struct snd_dma_device {
 	struct device *dev;		/* generic device */
 };
 
-#ifndef snd_dma_pci_data
 #define snd_dma_pci_data(pci)	(&(pci)->dev)
 #define snd_dma_isa_data()	NULL
 #define snd_dma_continuous_data(x)	((struct device *)(__force unsigned long)(x))
-#endif
 
 
 /*
diff --git a/include/sound/omap-pcm.h b/include/sound/omap-pcm.h
deleted file mode 100644
index c1d2f31d71e9..000000000000
--- a/include/sound/omap-pcm.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * omap-pcm.h - OMAP PCM driver
- *
- * Copyright (C) 2014 Texas Instruments, Inc.
- *
- * Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- */
-
-#ifndef __OMAP_PCM_H__
-#define __OMAP_PCM_H__
-
-#if IS_ENABLED(CONFIG_SND_OMAP_SOC)
-int omap_pcm_platform_register(struct device *dev);
-#else
-static inline int omap_pcm_platform_register(struct device *dev)
-{
-	return 0;
-}
-#endif /* CONFIG_SND_OMAP_SOC */
-
-#endif /* __OMAP_PCM_H__ */
diff --git a/include/sound/rt5640.h b/include/sound/rt5640.h
deleted file mode 100644
index e3c84b92ff70..000000000000
--- a/include/sound/rt5640.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * linux/sound/rt5640.h -- Platform data for RT5640
- *
- * Copyright 2011 Realtek Microelectronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __LINUX_SND_RT5640_H
-#define __LINUX_SND_RT5640_H
-
-struct rt5640_platform_data {
-	/* IN1 & IN2 & IN3 can optionally be differential */
-	bool in1_diff;
-	bool in2_diff;
-	bool in3_diff;
-
-	bool dmic_en;
-	bool dmic1_data_pin; /* 0 = IN1P; 1 = GPIO3 */
-	bool dmic2_data_pin; /* 0 = IN1N; 1 = GPIO4 */
-
-	int ldo1_en; /* GPIO for LDO1_EN */
-};
-
-#endif
diff --git a/include/sound/rt5668.h b/include/sound/rt5668.h
new file mode 100644
index 000000000000..f907b78696cf
--- /dev/null
+++ b/include/sound/rt5668.h
@@ -0,0 +1,40 @@
+/*
+ * linux/sound/rt5668.h -- Platform data for RT5668
+ *
+ * Copyright 2018 Realtek Microelectronics
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_SND_RT5668_H
+#define __LINUX_SND_RT5668_H
+
+enum rt5668_dmic1_data_pin {
+	RT5668_DMIC1_NULL,
+	RT5668_DMIC1_DATA_GPIO2,
+	RT5668_DMIC1_DATA_GPIO5,
+};
+
+enum rt5668_dmic1_clk_pin {
+	RT5668_DMIC1_CLK_GPIO1,
+	RT5668_DMIC1_CLK_GPIO3,
+};
+
+enum rt5668_jd_src {
+	RT5668_JD_NULL,
+	RT5668_JD1,
+};
+
+struct rt5668_platform_data {
+
+	int ldo1_en; /* GPIO for LDO1_EN */
+
+	enum rt5668_dmic1_data_pin dmic1_data_pin;
+	enum rt5668_dmic1_clk_pin dmic1_clk_pin;
+	enum rt5668_jd_src jd_src;
+};
+
+#endif
+
diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index 8ad11669e4d8..e6f8c40ed43c 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -170,6 +170,8 @@ struct snd_soc_dai_ops {
 		unsigned int rx_num, unsigned int *rx_slot);
 	int (*set_tristate)(struct snd_soc_dai *dai, int tristate);
 
+	int (*set_sdw_stream)(struct snd_soc_dai *dai,
+			void *stream, int direction);
 	/*
 	 * DAI digital mute - optional.
 	 * Called by soc-core to minimise any pops.
@@ -294,8 +296,8 @@ struct snd_soc_dai {
 	struct snd_soc_dai_driver *driver;
 
 	/* DAI runtime info */
-	unsigned int capture_active:1;		/* stream is in use */
-	unsigned int playback_active:1;		/* stream is in use */
+	unsigned int capture_active;		/* stream usage count */
+	unsigned int playback_active;		/* stream usage count */
 	unsigned int probed:1;
 
 	unsigned int active;
@@ -313,7 +315,6 @@ struct snd_soc_dai {
 	unsigned int sample_bits;
 
 	/* parent platform/codec */
-	struct snd_soc_codec *codec;
 	struct snd_soc_component *component;
 
 	/* CODEC TDM slot masks and params (for fixup) */
@@ -358,4 +359,25 @@ static inline void *snd_soc_dai_get_drvdata(struct snd_soc_dai *dai)
 	return dev_get_drvdata(dai->dev);
 }
 
+/**
+ * snd_soc_dai_set_sdw_stream() - Configures a DAI for SDW stream operation
+ * @dai: DAI
+ * @stream: STREAM
+ * @direction: Stream direction(Playback/Capture)
+ * SoundWire subsystem doesn't have a notion of direction and we reuse
+ * the ASoC stream direction to configure sink/source ports.
+ * Playback maps to source ports and Capture for sink ports.
+ *
+ * This should be invoked with NULL to clear the stream set previously.
+ * Returns 0 on success, a negative error code otherwise.
+ */
+static inline int snd_soc_dai_set_sdw_stream(struct snd_soc_dai *dai,
+				void *stream, int direction)
+{
+	if (dai->driver->ops->set_sdw_stream)
+		return dai->driver->ops->set_sdw_stream(dai, stream, direction);
+	else
+		return -ENOTSUPP;
+}
+
 #endif
diff --git a/include/sound/soc.h b/include/sound/soc.h
index ad266d7e9553..1378dcd2128a 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -401,11 +401,7 @@ struct snd_soc_ops;
 struct snd_soc_pcm_runtime;
 struct snd_soc_dai;
 struct snd_soc_dai_driver;
-struct snd_soc_platform;
 struct snd_soc_dai_link;
-struct snd_soc_platform_driver;
-struct snd_soc_codec;
-struct snd_soc_codec_driver;
 struct snd_soc_component;
 struct snd_soc_component_driver;
 struct soc_enum;
@@ -430,13 +426,6 @@ enum snd_soc_card_subclass {
 	SND_SOC_CARD_CLASS_RUNTIME	= 1,
 };
 
-int snd_soc_codec_set_sysclk(struct snd_soc_codec *codec, int clk_id,
-			     int source, unsigned int freq, int dir);
-int snd_soc_codec_set_pll(struct snd_soc_codec *codec, int pll_id, int source,
-			  unsigned int freq_in, unsigned int freq_out);
-int snd_soc_codec_set_jack(struct snd_soc_codec *codec,
-			   struct snd_soc_jack *jack, void *data);
-
 int snd_soc_register_card(struct snd_soc_card *card);
 int snd_soc_unregister_card(struct snd_soc_card *card);
 int devm_snd_soc_register_card(struct device *dev, struct snd_soc_card *card);
@@ -455,19 +444,6 @@ static inline int snd_soc_resume(struct device *dev)
 }
 #endif
 int snd_soc_poweroff(struct device *dev);
-int snd_soc_register_platform(struct device *dev,
-		const struct snd_soc_platform_driver *platform_drv);
-int devm_snd_soc_register_platform(struct device *dev,
-		const struct snd_soc_platform_driver *platform_drv);
-void snd_soc_unregister_platform(struct device *dev);
-int snd_soc_add_platform(struct device *dev, struct snd_soc_platform *platform,
-		const struct snd_soc_platform_driver *platform_drv);
-void snd_soc_remove_platform(struct snd_soc_platform *platform);
-struct snd_soc_platform *snd_soc_lookup_platform(struct device *dev);
-int snd_soc_register_codec(struct device *dev,
-		const struct snd_soc_codec_driver *codec_drv,
-		struct snd_soc_dai_driver *dai_drv, int num_dai);
-void snd_soc_unregister_codec(struct device *dev);
 int snd_soc_add_component(struct device *dev,
 		struct snd_soc_component *component,
 		const struct snd_soc_component_driver *component_driver,
@@ -482,16 +458,15 @@ int devm_snd_soc_register_component(struct device *dev,
 void snd_soc_unregister_component(struct device *dev);
 struct snd_soc_component *snd_soc_lookup_component(struct device *dev,
 						   const char *driver_name);
-int snd_soc_cache_init(struct snd_soc_codec *codec);
-int snd_soc_cache_exit(struct snd_soc_codec *codec);
 
-int snd_soc_platform_read(struct snd_soc_platform *platform,
-					unsigned int reg);
-int snd_soc_platform_write(struct snd_soc_platform *platform,
-					unsigned int reg, unsigned int val);
 int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num);
 #ifdef CONFIG_SND_SOC_COMPRESS
 int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num);
+#else
+static inline int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
+{
+	return 0;
+}
 #endif
 
 void snd_soc_disconnect_sync(struct device *dev);
@@ -576,23 +551,7 @@ static inline void snd_soc_jack_free_gpios(struct snd_soc_jack *jack, int count,
 }
 #endif
 
-/* codec register bit access */
-int snd_soc_update_bits(struct snd_soc_codec *codec, unsigned int reg,
-				unsigned int mask, unsigned int value);
-int snd_soc_update_bits_locked(struct snd_soc_codec *codec,
-			       unsigned int reg, unsigned int mask,
-			       unsigned int value);
-int snd_soc_test_bits(struct snd_soc_codec *codec, unsigned int reg,
-				unsigned int mask, unsigned int value);
-
 #ifdef CONFIG_SND_SOC_AC97_BUS
-#define snd_soc_alloc_ac97_codec(codec) \
-	snd_soc_alloc_ac97_component(&codec->component)
-#define snd_soc_new_ac97_codec(codec, id, id_mask) \
-	snd_soc_new_ac97_component(&codec->component, id, id_mask)
-#define snd_soc_free_ac97_codec(ac97) \
-	snd_soc_free_ac97_component(ac97)
-
 struct snd_ac97 *snd_soc_alloc_ac97_component(struct snd_soc_component *component);
 struct snd_ac97 *snd_soc_new_ac97_component(struct snd_soc_component *component,
 	unsigned int id, unsigned int id_mask);
@@ -626,10 +585,6 @@ struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
 					       const char *name);
 int snd_soc_add_component_controls(struct snd_soc_component *component,
 	const struct snd_kcontrol_new *controls, unsigned int num_controls);
-int snd_soc_add_codec_controls(struct snd_soc_codec *codec,
-	const struct snd_kcontrol_new *controls, unsigned int num_controls);
-int snd_soc_add_platform_controls(struct snd_soc_platform *platform,
-	const struct snd_kcontrol_new *controls, unsigned int num_controls);
 int snd_soc_add_card_controls(struct snd_soc_card *soc_card,
 	const struct snd_kcontrol_new *controls, int num_controls);
 int snd_soc_add_dai_controls(struct snd_soc_dai *dai,
@@ -862,8 +817,6 @@ struct snd_soc_component {
 
 	unsigned int active;
 
-	unsigned int ignore_pmdown_time:1; /* pmdown_time is ignored at stop */
-	unsigned int registered_as_component:1;
 	unsigned int suspended:1; /* is in suspend PM state */
 
 	struct list_head list;
@@ -875,9 +828,6 @@ struct snd_soc_component {
 	struct list_head dai_list;
 	int num_dai;
 
-	int (*read)(struct snd_soc_component *, unsigned int, unsigned int *);
-	int (*write)(struct snd_soc_component *, unsigned int, unsigned int);
-
 	struct regmap *regmap;
 	int val_bytes;
 
@@ -886,10 +836,6 @@ struct snd_soc_component {
 	/* attached dynamic objects */
 	struct list_head dobj_list;
 
-#ifdef CONFIG_DEBUG_FS
-	struct dentry *debugfs_root;
-#endif
-
 	/*
 	* DO NOT use any of the fields below in drivers, they are temporary and
 	* are going to be removed again soon. If you use them in driver code the
@@ -899,29 +845,11 @@ struct snd_soc_component {
 	/* Don't use these, use snd_soc_component_get_dapm() */
 	struct snd_soc_dapm_context dapm;
 
-	struct snd_soc_codec *codec;
-
-	int (*probe)(struct snd_soc_component *);
-	void (*remove)(struct snd_soc_component *);
-	int (*suspend)(struct snd_soc_component *);
-	int (*resume)(struct snd_soc_component *);
-	int (*pcm_new)(struct snd_soc_component *, struct snd_soc_pcm_runtime *);
-	void (*pcm_free)(struct snd_soc_component *, struct snd_pcm *);
-
-	int (*set_sysclk)(struct snd_soc_component *component,
-			  int clk_id, int source, unsigned int freq, int dir);
-	int (*set_pll)(struct snd_soc_component *component, int pll_id,
-		       int source, unsigned int freq_in, unsigned int freq_out);
-	int (*set_jack)(struct snd_soc_component *component,
-			struct snd_soc_jack *jack,  void *data);
-	int (*set_bias_level)(struct snd_soc_component *component,
-			      enum snd_soc_bias_level level);
-
 	/* machine specific init */
 	int (*init)(struct snd_soc_component *component);
 
 #ifdef CONFIG_DEBUG_FS
-	void (*init_debugfs)(struct snd_soc_component *component);
+	struct dentry *debugfs_root;
 	const char *debugfs_prefix;
 #endif
 };
@@ -938,97 +866,12 @@ snd_soc_rtdcom_lookup(struct snd_soc_pcm_runtime *rtd,
 #define for_each_rtdcom_safe(rtd, rtdcom1, rtdcom2) \
 	list_for_each_entry_safe(rtdcom1, rtdcom2, &(rtd)->component_list, list)
 
-/* SoC Audio Codec device */
-struct snd_soc_codec {
-	struct device *dev;
-	const struct snd_soc_codec_driver *driver;
-
-	struct list_head list;
-
-	/* runtime */
-	unsigned int cache_init:1; /* codec cache has been initialized */
-
-	/* codec IO */
-	void *control_data; /* codec control (i2c/3wire) data */
-	hw_write_t hw_write;
-	void *reg_cache;
-
-	/* component */
-	struct snd_soc_component component;
-};
-
-/* codec driver */
-struct snd_soc_codec_driver {
-
-	/* driver ops */
-	int (*probe)(struct snd_soc_codec *);
-	int (*remove)(struct snd_soc_codec *);
-	int (*suspend)(struct snd_soc_codec *);
-	int (*resume)(struct snd_soc_codec *);
-	struct snd_soc_component_driver component_driver;
-
-	/* codec wide operations */
-	int (*set_sysclk)(struct snd_soc_codec *codec,
-			  int clk_id, int source, unsigned int freq, int dir);
-	int (*set_pll)(struct snd_soc_codec *codec, int pll_id, int source,
-		unsigned int freq_in, unsigned int freq_out);
-	int (*set_jack)(struct snd_soc_codec *codec,
-			struct snd_soc_jack *jack,  void *data);
-
-	/* codec IO */
-	struct regmap *(*get_regmap)(struct device *);
-	unsigned int (*read)(struct snd_soc_codec *, unsigned int);
-	int (*write)(struct snd_soc_codec *, unsigned int, unsigned int);
-	unsigned int reg_cache_size;
-	short reg_cache_step;
-	short reg_word_size;
-	const void *reg_cache_default;
-
-	/* codec bias level */
-	int (*set_bias_level)(struct snd_soc_codec *,
-			      enum snd_soc_bias_level level);
-	bool idle_bias_off;
-	bool suspend_bias_off;
-
-	void (*seq_notifier)(struct snd_soc_dapm_context *,
-			     enum snd_soc_dapm_type, int);
-
-	bool ignore_pmdown_time;  /* Doesn't benefit from pmdown delay */
-};
-
-/* SoC platform interface */
-struct snd_soc_platform_driver {
-
-	int (*probe)(struct snd_soc_platform *);
-	int (*remove)(struct snd_soc_platform *);
-	struct snd_soc_component_driver component_driver;
-
-	/* pcm creation and destruction */
-	int (*pcm_new)(struct snd_soc_pcm_runtime *);
-	void (*pcm_free)(struct snd_pcm *);
-
-	/* platform stream pcm ops */
-	const struct snd_pcm_ops *ops;
-
-	/* platform stream compress ops */
-	const struct snd_compr_ops *compr_ops;
-};
-
 struct snd_soc_dai_link_component {
 	const char *name;
 	struct device_node *of_node;
 	const char *dai_name;
 };
 
-struct snd_soc_platform {
-	struct device *dev;
-	const struct snd_soc_platform_driver *driver;
-
-	struct list_head list;
-
-	struct snd_soc_component component;
-};
-
 struct snd_soc_dai_link {
 	/* config - must be set by machine driver */
 	const char *name;			/* Codec name */
@@ -1276,8 +1119,6 @@ struct snd_soc_pcm_runtime {
 	/* runtime devices */
 	struct snd_pcm *pcm;
 	struct snd_compr *compr;
-	struct snd_soc_codec *codec;
-	struct snd_soc_platform *platform; /* will be removed */
 	struct snd_soc_dai *codec_dai;
 	struct snd_soc_dai *cpu_dai;
 
@@ -1346,32 +1187,6 @@ struct soc_enum {
 };
 
 /**
- * snd_soc_component_to_codec() - Casts a component to the CODEC it is embedded in
- * @component: The component to cast to a CODEC
- *
- * This function must only be used on components that are known to be CODECs.
- * Otherwise the behavior is undefined.
- */
-static inline struct snd_soc_codec *snd_soc_component_to_codec(
-	struct snd_soc_component *component)
-{
-	return container_of(component, struct snd_soc_codec, component);
-}
-
-/**
- * snd_soc_component_to_platform() - Casts a component to the platform it is embedded in
- * @component: The component to cast to a platform
- *
- * This function must only be used on components that are known to be platforms.
- * Otherwise the behavior is undefined.
- */
-static inline struct snd_soc_platform *snd_soc_component_to_platform(
-	struct snd_soc_component *component)
-{
-	return container_of(component, struct snd_soc_platform, component);
-}
-
-/**
  * snd_soc_dapm_to_component() - Casts a DAPM context to the component it is
  *  embedded in
  * @dapm: The DAPM context to cast to the component
@@ -1387,33 +1202,6 @@ static inline struct snd_soc_component *snd_soc_dapm_to_component(
 }
 
 /**
- * snd_soc_dapm_to_codec() - Casts a DAPM context to the CODEC it is embedded in
- * @dapm: The DAPM context to cast to the CODEC
- *
- * This function must only be used on DAPM contexts that are known to be part of
- * a CODEC (e.g. in a CODEC driver). Otherwise the behavior is undefined.
- */
-static inline struct snd_soc_codec *snd_soc_dapm_to_codec(
-	struct snd_soc_dapm_context *dapm)
-{
-	return snd_soc_component_to_codec(snd_soc_dapm_to_component(dapm));
-}
-
-/**
- * snd_soc_dapm_to_platform() - Casts a DAPM context to the platform it is
- *  embedded in
- * @dapm: The DAPM context to cast to the platform.
- *
- * This function must only be used on DAPM contexts that are known to be part of
- * a platform (e.g. in a platform driver). Otherwise the behavior is undefined.
- */
-static inline struct snd_soc_platform *snd_soc_dapm_to_platform(
-	struct snd_soc_dapm_context *dapm)
-{
-	return snd_soc_component_to_platform(snd_soc_dapm_to_component(dapm));
-}
-
-/**
  * snd_soc_component_get_dapm() - Returns the DAPM context associated with a
  *  component
  * @component: The component for which to get the DAPM context
@@ -1425,31 +1213,6 @@ static inline struct snd_soc_dapm_context *snd_soc_component_get_dapm(
 }
 
 /**
- * snd_soc_codec_get_dapm() - Returns the DAPM context for the CODEC
- * @codec: The CODEC for which to get the DAPM context
- *
- * Note: Use this function instead of directly accessing the CODEC's dapm field
- */
-static inline struct snd_soc_dapm_context *snd_soc_codec_get_dapm(
-	struct snd_soc_codec *codec)
-{
-	return snd_soc_component_get_dapm(&codec->component);
-}
-
-/**
- * snd_soc_dapm_init_bias_level() - Initialize CODEC DAPM bias level
- * @codec: The CODEC for which to initialize the DAPM bias level
- * @level: The DAPM level to initialize to
- *
- * Initializes the CODEC DAPM bias level. See snd_soc_dapm_init_bias_level().
- */
-static inline void snd_soc_codec_init_bias_level(struct snd_soc_codec *codec,
-	enum snd_soc_bias_level level)
-{
-	snd_soc_dapm_init_bias_level(snd_soc_codec_get_dapm(codec), level);
-}
-
-/**
  * snd_soc_component_init_bias_level() - Initialize COMPONENT DAPM bias level
  * @component: The COMPONENT for which to initialize the DAPM bias level
  * @level: The DAPM level to initialize to
@@ -1465,18 +1228,6 @@ snd_soc_component_init_bias_level(struct snd_soc_component *component,
 }
 
 /**
- * snd_soc_dapm_get_bias_level() - Get current CODEC DAPM bias level
- * @codec: The CODEC for which to get the DAPM bias level
- *
- * Returns: The current DAPM bias level of the CODEC.
- */
-static inline enum snd_soc_bias_level snd_soc_codec_get_bias_level(
-	struct snd_soc_codec *codec)
-{
-	return snd_soc_dapm_get_bias_level(snd_soc_codec_get_dapm(codec));
-}
-
-/**
  * snd_soc_component_get_bias_level() - Get current COMPONENT DAPM bias level
  * @component: The COMPONENT for which to get the DAPM bias level
  *
@@ -1490,21 +1241,6 @@ snd_soc_component_get_bias_level(struct snd_soc_component *component)
 }
 
 /**
- * snd_soc_codec_force_bias_level() - Set the CODEC DAPM bias level
- * @codec: The CODEC for which to set the level
- * @level: The level to set to
- *
- * Forces the CODEC bias level to a specific state. See
- * snd_soc_dapm_force_bias_level().
- */
-static inline int snd_soc_codec_force_bias_level(struct snd_soc_codec *codec,
-	enum snd_soc_bias_level level)
-{
-	return snd_soc_dapm_force_bias_level(snd_soc_codec_get_dapm(codec),
-		level);
-}
-
-/**
  * snd_soc_component_force_bias_level() - Set the COMPONENT DAPM bias level
  * @component: The COMPONENT for which to set the level
  * @level: The level to set to
@@ -1522,19 +1258,6 @@ snd_soc_component_force_bias_level(struct snd_soc_component *component,
 }
 
 /**
- * snd_soc_dapm_kcontrol_codec() - Returns the codec associated to a kcontrol
- * @kcontrol: The kcontrol
- *
- * This function must only be used on DAPM contexts that are known to be part of
- * a CODEC (e.g. in a CODEC driver). Otherwise the behavior is undefined.
- */
-static inline struct snd_soc_codec *snd_soc_dapm_kcontrol_codec(
-	struct snd_kcontrol *kcontrol)
-{
-	return snd_soc_dapm_to_codec(snd_soc_dapm_kcontrol_dapm(kcontrol));
-}
-
-/**
  * snd_soc_dapm_kcontrol_component() - Returns the component associated to a kcontrol
  * @kcontrol: The kcontrol
  *
@@ -1547,22 +1270,6 @@ static inline struct snd_soc_component *snd_soc_dapm_kcontrol_component(
 	return snd_soc_dapm_to_component(snd_soc_dapm_kcontrol_dapm(kcontrol));
 }
 
-/* codec IO */
-unsigned int snd_soc_read(struct snd_soc_codec *codec, unsigned int reg);
-int snd_soc_write(struct snd_soc_codec *codec, unsigned int reg,
-	unsigned int val);
-
-/**
- * snd_soc_cache_sync() - Sync the register cache with the hardware
- * @codec: CODEC to sync
- *
- * Note: This function will call regcache_sync()
- */
-static inline int snd_soc_cache_sync(struct snd_soc_codec *codec)
-{
-	return regcache_sync(codec->component.regmap);
-}
-
 /**
  * snd_soc_component_cache_sync() - Sync the register cache with the hardware
  * @component: COMPONENT to sync
@@ -1605,37 +1312,6 @@ void snd_soc_component_init_regmap(struct snd_soc_component *component,
 	struct regmap *regmap);
 void snd_soc_component_exit_regmap(struct snd_soc_component *component);
 
-/**
- * snd_soc_codec_init_regmap() - Initialize regmap instance for the CODEC
- * @codec: The CODEC for which to initialize the regmap instance
- * @regmap: The regmap instance that should be used by the CODEC
- *
- * This function allows deferred assignment of the regmap instance that is
- * associated with the CODEC. Only use this if the regmap instance is not yet
- * ready when the CODEC is registered. The function must also be called before
- * the first IO attempt of the CODEC.
- */
-static inline void snd_soc_codec_init_regmap(struct snd_soc_codec *codec,
-	struct regmap *regmap)
-{
-	snd_soc_component_init_regmap(&codec->component, regmap);
-}
-
-/**
- * snd_soc_codec_exit_regmap() - De-initialize regmap instance for the CODEC
- * @codec: The CODEC for which to de-initialize the regmap instance
- *
- * Calls regmap_exit() on the regmap instance associated to the CODEC and
- * removes the regmap instance from the CODEC.
- *
- * This function should only be used if snd_soc_codec_init_regmap() was used to
- * initialize the regmap instance.
- */
-static inline void snd_soc_codec_exit_regmap(struct snd_soc_codec *codec)
-{
-	snd_soc_component_exit_regmap(&codec->component);
-}
-
 #endif
 
 /* device driver data */
@@ -1662,28 +1338,6 @@ static inline void *snd_soc_component_get_drvdata(struct snd_soc_component *c)
 	return dev_get_drvdata(c->dev);
 }
 
-static inline void snd_soc_codec_set_drvdata(struct snd_soc_codec *codec,
-		void *data)
-{
-	snd_soc_component_set_drvdata(&codec->component, data);
-}
-
-static inline void *snd_soc_codec_get_drvdata(struct snd_soc_codec *codec)
-{
-	return snd_soc_component_get_drvdata(&codec->component);
-}
-
-static inline void snd_soc_platform_set_drvdata(struct snd_soc_platform *platform,
-		void *data)
-{
-	snd_soc_component_set_drvdata(&platform->component, data);
-}
-
-static inline void *snd_soc_platform_get_drvdata(struct snd_soc_platform *platform)
-{
-	return snd_soc_component_get_drvdata(&platform->component);
-}
-
 static inline void snd_soc_initialize_card_lists(struct snd_soc_card *card)
 {
 	INIT_LIST_HEAD(&card->widgets);
@@ -1735,20 +1389,15 @@ static inline bool snd_soc_component_is_active(
 	return component->active != 0;
 }
 
-static inline bool snd_soc_codec_is_active(struct snd_soc_codec *codec)
-{
-	return snd_soc_component_is_active(&codec->component);
-}
-
 /**
  * snd_soc_kcontrol_component() - Returns the component that registered the
  *  control
  * @kcontrol: The control for which to get the component
  *
  * Note: This function will work correctly if the control has been registered
- * for a component. Either with snd_soc_add_codec_controls() or
- * snd_soc_add_platform_controls() or via  table based setup for either a
- * CODEC, a platform or component driver. Otherwise the behavior is undefined.
+ * for a component. With snd_soc_add_codec_controls() or via table based
+ * setup for either a CODEC or component driver. Otherwise the behavior is
+ * undefined.
  */
 static inline struct snd_soc_component *snd_soc_kcontrol_component(
 	struct snd_kcontrol *kcontrol)
@@ -1756,34 +1405,6 @@ static inline struct snd_soc_component *snd_soc_kcontrol_component(
 	return snd_kcontrol_chip(kcontrol);
 }
 
-/**
- * snd_soc_kcontrol_codec() - Returns the CODEC that registered the control
- * @kcontrol: The control for which to get the CODEC
- *
- * Note: This function will only work correctly if the control has been
- * registered with snd_soc_add_codec_controls() or via table based setup of
- * snd_soc_codec_driver. Otherwise the behavior is undefined.
- */
-static inline struct snd_soc_codec *snd_soc_kcontrol_codec(
-	struct snd_kcontrol *kcontrol)
-{
-	return snd_soc_component_to_codec(snd_soc_kcontrol_component(kcontrol));
-}
-
-/**
- * snd_soc_kcontrol_platform() - Returns the platform that registered the control
- * @kcontrol: The control for which to get the platform
- *
- * Note: This function will only work correctly if the control has been
- * registered with snd_soc_add_platform_controls() or via table based setup of
- * a snd_soc_platform_driver. Otherwise the behavior is undefined.
- */
-static inline struct snd_soc_platform *snd_soc_kcontrol_platform(
-	struct snd_kcontrol *kcontrol)
-{
-	return snd_soc_component_to_platform(snd_soc_kcontrol_component(kcontrol));
-}
-
 int snd_soc_util_init(void);
 void snd_soc_util_exit(void);
 
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index f0820554caa9..d0a341bc4540 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -575,6 +575,48 @@ TRACE_EVENT(afs_protocol_error,
 		      __entry->call, __entry->error, __entry->where)
 	    );
 
+TRACE_EVENT(afs_cm_no_server,
+	    TP_PROTO(struct afs_call *call, struct sockaddr_rxrpc *srx),
+
+	    TP_ARGS(call, srx),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,			call	)
+		    __field(unsigned int,			op_id	)
+		    __field_struct(struct sockaddr_rxrpc,	srx	)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call->debug_id;
+		    __entry->op_id = call->operation_ID;
+		    memcpy(&__entry->srx, srx, sizeof(__entry->srx));
+			   ),
+
+	    TP_printk("c=%08x op=%u %pISpc",
+		      __entry->call, __entry->op_id, &__entry->srx.transport)
+	    );
+
+TRACE_EVENT(afs_cm_no_server_u,
+	    TP_PROTO(struct afs_call *call, const uuid_t *uuid),
+
+	    TP_ARGS(call, uuid),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,			call	)
+		    __field(unsigned int,			op_id	)
+		    __field_struct(uuid_t,			uuid	)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call->debug_id;
+		    __entry->op_id = call->operation_ID;
+		    memcpy(&__entry->uuid, uuid, sizeof(__entry->uuid));
+			   ),
+
+	    TP_printk("c=%08x op=%u %pU",
+		      __entry->call, __entry->op_id, &__entry->uuid)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h
index ccd1a3bdff46..40c300fe704d 100644
--- a/include/trace/events/asoc.h
+++ b/include/trace/events/asoc.h
@@ -12,7 +12,6 @@
 #define DAPM_ARROW(dir) (((dir) == SND_SOC_DAPM_DIR_OUT) ? "->" : "<-")
 
 struct snd_soc_jack;
-struct snd_soc_codec;
 struct snd_soc_card;
 struct snd_soc_dapm_widget;
 struct snd_soc_dapm_path;
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 965c650a5273..39b94ec965be 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -121,9 +121,9 @@ TRACE_EVENT(btrfs_transaction_commit,
 		__entry->root_objectid	= root->root_key.objectid;
 	),
 
-	TP_printk_btrfs("root = %llu(%s), gen = %llu",
+	TP_printk_btrfs("root=%llu(%s) gen=%llu",
 		  show_root_type(__entry->root_objectid),
-		  (unsigned long long)__entry->generation)
+		  __entry->generation)
 );
 
 DECLARE_EVENT_CLASS(btrfs__inode,
@@ -133,7 +133,7 @@ DECLARE_EVENT_CLASS(btrfs__inode,
 	TP_ARGS(inode),
 
 	TP_STRUCT__entry_btrfs(
-		__field(	ino_t,  ino			)
+		__field(	u64,  ino			)
 		__field(	blkcnt_t,  blocks		)
 		__field(	u64,  disk_i_size		)
 		__field(	u64,  generation		)
@@ -143,7 +143,7 @@ DECLARE_EVENT_CLASS(btrfs__inode,
 	),
 
 	TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
-		__entry->ino	= inode->i_ino;
+		__entry->ino	= btrfs_ino(BTRFS_I(inode));
 		__entry->blocks	= inode->i_blocks;
 		__entry->disk_i_size  = BTRFS_I(inode)->disk_i_size;
 		__entry->generation = BTRFS_I(inode)->generation;
@@ -153,15 +153,15 @@ DECLARE_EVENT_CLASS(btrfs__inode,
 				BTRFS_I(inode)->root->root_key.objectid;
 	),
 
-	TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%lu blocks=%llu "
+	TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%llu blocks=%llu "
 		  "disk_i_size=%llu last_trans=%llu logged_trans=%llu",
 		  show_root_type(__entry->root_objectid),
-		  (unsigned long long)__entry->generation,
-		  (unsigned long)__entry->ino,
+		  __entry->generation,
+		  __entry->ino,
 		  (unsigned long long)__entry->blocks,
-		  (unsigned long long)__entry->disk_i_size,
-		  (unsigned long long)__entry->last_trans,
-		  (unsigned long long)__entry->logged_trans)
+		  __entry->disk_i_size,
+		  __entry->last_trans,
+		  __entry->logged_trans)
 );
 
 DEFINE_EVENT(btrfs__inode, btrfs_inode_new,
@@ -244,23 +244,25 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
 		  "block_len=%llu flags=%s refs=%u "
 		  "compress_type=%u",
 		  show_root_type(__entry->root_objectid),
-		  (unsigned long long)__entry->ino,
-		  (unsigned long long)__entry->start,
-		  (unsigned long long)__entry->len,
-		  (unsigned long long)__entry->orig_start,
+		  __entry->ino,
+		  __entry->start,
+		  __entry->len,
+		  __entry->orig_start,
 		  show_map_type(__entry->block_start),
-		  (unsigned long long)__entry->block_len,
+		  __entry->block_len,
 		  show_map_flags(__entry->flags),
 		  __entry->refs, __entry->compress_type)
 );
 
 TRACE_EVENT(btrfs_handle_em_exist,
 
-	TP_PROTO(const struct extent_map *existing, const struct extent_map *map, u64 start, u64 len),
+	TP_PROTO(struct btrfs_fs_info *fs_info,
+		const struct extent_map *existing, const struct extent_map *map,
+		u64 start, u64 len),
 
-	TP_ARGS(existing, map, start, len),
+	TP_ARGS(fs_info, existing, map, start, len),
 
-	TP_STRUCT__entry(
+	TP_STRUCT__entry_btrfs(
 		__field(	u64,  e_start		)
 		__field(	u64,  e_len		)
 		__field(	u64,  map_start		)
@@ -269,7 +271,7 @@ TRACE_EVENT(btrfs_handle_em_exist,
 		__field(	u64,  len		)
 	),
 
-	TP_fast_assign(
+	TP_fast_assign_btrfs(fs_info,
 		__entry->e_start	= existing->start;
 		__entry->e_len		= existing->len;
 		__entry->map_start	= map->start;
@@ -278,15 +280,15 @@ TRACE_EVENT(btrfs_handle_em_exist,
 		__entry->len		= len;
 	),
 
-	TP_printk("start=%llu len=%llu "
+	TP_printk_btrfs("start=%llu len=%llu "
 		  "existing(start=%llu len=%llu) "
 		  "em(start=%llu len=%llu)",
-		  (unsigned long long)__entry->start,
-		  (unsigned long long)__entry->len,
-		  (unsigned long long)__entry->e_start,
-		  (unsigned long long)__entry->e_len,
-		  (unsigned long long)__entry->map_start,
-		  (unsigned long long)__entry->map_len)
+		  __entry->start,
+		  __entry->len,
+		  __entry->e_start,
+		  __entry->e_len,
+		  __entry->map_start,
+		  __entry->map_len)
 );
 
 /* file extent item */
@@ -443,7 +445,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
 	TP_ARGS(inode, ordered),
 
 	TP_STRUCT__entry_btrfs(
-		__field(	ino_t,  ino		)
+		__field(	u64,  ino		)
 		__field(	u64,  file_offset	)
 		__field(	u64,  start		)
 		__field(	u64,  len		)
@@ -457,7 +459,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
 	),
 
 	TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
-		__entry->ino 		= inode->i_ino;
+		__entry->ino 		= btrfs_ino(BTRFS_I(inode));
 		__entry->file_offset	= ordered->file_offset;
 		__entry->start		= ordered->start;
 		__entry->len		= ordered->len;
@@ -477,13 +479,13 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
 		  "bytes_left=%llu flags=%s compress_type=%d "
 		  "refs=%d",
 		  show_root_type(__entry->root_objectid),
-		  (unsigned long long)__entry->ino,
-		  (unsigned long long)__entry->file_offset,
-		  (unsigned long long)__entry->start,
-		  (unsigned long long)__entry->len,
-		  (unsigned long long)__entry->disk_len,
-		  (unsigned long long)__entry->truncated_len,
-		  (unsigned long long)__entry->bytes_left,
+		  __entry->ino,
+		  __entry->file_offset,
+		  __entry->start,
+		  __entry->len,
+		  __entry->disk_len,
+		  __entry->truncated_len,
+		  __entry->bytes_left,
 		  show_ordered_flags(__entry->flags),
 		  __entry->compress_type, __entry->refs)
 );
@@ -528,7 +530,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 	TP_ARGS(page, inode, wbc),
 
 	TP_STRUCT__entry_btrfs(
-		__field(	ino_t,  ino			)
+		__field(	u64,	ino			)
 		__field(	pgoff_t,  index			)
 		__field(	long,   nr_to_write		)
 		__field(	long,   pages_skipped		)
@@ -542,7 +544,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 	),
 
 	TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
-		__entry->ino		= inode->i_ino;
+		__entry->ino		= btrfs_ino(BTRFS_I(inode));
 		__entry->index		= page->index;
 		__entry->nr_to_write	= wbc->nr_to_write;
 		__entry->pages_skipped	= wbc->pages_skipped;
@@ -556,12 +558,12 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 				 BTRFS_I(inode)->root->root_key.objectid;
 	),
 
-	TP_printk_btrfs("root=%llu(%s) ino=%lu page_index=%lu "
+	TP_printk_btrfs("root=%llu(%s) ino=%llu page_index=%lu "
 		  "nr_to_write=%ld pages_skipped=%ld range_start=%llu "
 		  "range_end=%llu for_kupdate=%d "
 		  "for_reclaim=%d range_cyclic=%d writeback_index=%lu",
 		  show_root_type(__entry->root_objectid),
-		  (unsigned long)__entry->ino, __entry->index,
+		  __entry->ino, __entry->index,
 		  __entry->nr_to_write, __entry->pages_skipped,
 		  __entry->range_start, __entry->range_end,
 		  __entry->for_kupdate,
@@ -584,7 +586,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook,
 	TP_ARGS(page, start, end, uptodate),
 
 	TP_STRUCT__entry_btrfs(
-		__field(	ino_t,	 ino		)
+		__field(	u64,	 ino		)
 		__field(	pgoff_t, index		)
 		__field(	u64,	 start		)
 		__field(	u64,	 end		)
@@ -593,7 +595,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook,
 	),
 
 	TP_fast_assign_btrfs(btrfs_sb(page->mapping->host->i_sb),
-		__entry->ino	= page->mapping->host->i_ino;
+		__entry->ino	= btrfs_ino(BTRFS_I(page->mapping->host));
 		__entry->index	= page->index;
 		__entry->start	= start;
 		__entry->end	= end;
@@ -602,12 +604,12 @@ TRACE_EVENT(btrfs_writepage_end_io_hook,
 			 BTRFS_I(page->mapping->host)->root->root_key.objectid;
 	),
 
-	TP_printk_btrfs("root=%llu(%s) ino=%lu page_index=%lu start=%llu "
+	TP_printk_btrfs("root=%llu(%s) ino=%llu page_index=%lu start=%llu "
 		  "end=%llu uptodate=%d",
 		  show_root_type(__entry->root_objectid),
-		  (unsigned long)__entry->ino, (unsigned long)__entry->index,
-		  (unsigned long long)__entry->start,
-		  (unsigned long long)__entry->end, __entry->uptodate)
+		  __entry->ino, (unsigned long)__entry->index,
+		  __entry->start,
+		  __entry->end, __entry->uptodate)
 );
 
 TRACE_EVENT(btrfs_sync_file,
@@ -617,8 +619,8 @@ TRACE_EVENT(btrfs_sync_file,
 	TP_ARGS(file, datasync),
 
 	TP_STRUCT__entry_btrfs(
-		__field(	ino_t,  ino		)
-		__field(	ino_t,  parent		)
+		__field(	u64,	ino		)
+		__field(	u64,	parent		)
 		__field(	int,    datasync	)
 		__field(	u64,    root_objectid	)
 	),
@@ -628,16 +630,17 @@ TRACE_EVENT(btrfs_sync_file,
 		const struct inode *inode = d_inode(dentry);
 
 		TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb));
-		__entry->ino		= inode->i_ino;
-		__entry->parent		= d_inode(dentry->d_parent)->i_ino;
+		__entry->ino		= btrfs_ino(BTRFS_I(inode));
+		__entry->parent		= btrfs_ino(BTRFS_I(d_inode(dentry->d_parent)));
 		__entry->datasync	= datasync;
 		__entry->root_objectid	=
 				 BTRFS_I(inode)->root->root_key.objectid;
 	),
 
-	TP_printk_btrfs("root=%llu(%s) ino=%ld parent=%ld datasync=%d",
+	TP_printk_btrfs("root=%llu(%s) ino=%llu parent=%llu datasync=%d",
 		  show_root_type(__entry->root_objectid),
-		  (unsigned long)__entry->ino, (unsigned long)__entry->parent,
+		  __entry->ino,
+		  __entry->parent,
 		  __entry->datasync)
 );
 
@@ -655,7 +658,7 @@ TRACE_EVENT(btrfs_sync_fs,
 		__entry->wait	= wait;
 	),
 
-	TP_printk_btrfs("wait = %d", __entry->wait)
+	TP_printk_btrfs("wait=%d", __entry->wait)
 );
 
 TRACE_EVENT(btrfs_add_block_group,
@@ -665,8 +668,7 @@ TRACE_EVENT(btrfs_add_block_group,
 
 	TP_ARGS(fs_info, block_group, create),
 
-	TP_STRUCT__entry(
-		__array(	u8,	fsid,	BTRFS_FSID_SIZE	)
+	TP_STRUCT__entry_btrfs(
 		__field(	u64,	offset			)
 		__field(	u64,	size			)
 		__field(	u64,	flags			)
@@ -675,8 +677,7 @@ TRACE_EVENT(btrfs_add_block_group,
 		__field(	int,	create			)
 	),
 
-	TP_fast_assign(
-		memcpy(__entry->fsid, fs_info->fsid, BTRFS_FSID_SIZE);
+	TP_fast_assign_btrfs(fs_info,
 		__entry->offset		= block_group->key.objectid;
 		__entry->size		= block_group->key.offset;
 		__entry->flags		= block_group->flags;
@@ -686,16 +687,16 @@ TRACE_EVENT(btrfs_add_block_group,
 		__entry->create		= create;
 	),
 
-	TP_printk("%pU: block_group offset=%llu size=%llu "
+	TP_printk_btrfs("block_group offset=%llu size=%llu "
 		  "flags=%llu(%s) bytes_used=%llu bytes_super=%llu "
-		  "create=%d", __entry->fsid,
-		  (unsigned long long)__entry->offset,
-		  (unsigned long long)__entry->size,
-		  (unsigned long long)__entry->flags,
+		  "create=%d",
+		  __entry->offset,
+		  __entry->size,
+		  __entry->flags,
 		  __print_flags((unsigned long)__entry->flags, "|",
 				BTRFS_GROUP_FLAGS),
-		  (unsigned long long)__entry->bytes_used,
-		  (unsigned long long)__entry->bytes_super, __entry->create)
+		  __entry->bytes_used,
+		  __entry->bytes_super, __entry->create)
 );
 
 #define show_ref_action(action)						\
@@ -740,13 +741,13 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref,
 	TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s "
 		  "parent=%llu(%s) ref_root=%llu(%s) level=%d "
 		  "type=%s seq=%llu",
-		  (unsigned long long)__entry->bytenr,
-		  (unsigned long long)__entry->num_bytes,
+		  __entry->bytenr,
+		  __entry->num_bytes,
 		  show_ref_action(__entry->action),
 		  show_root_type(__entry->parent),
 		  show_root_type(__entry->ref_root),
 		  __entry->level, show_ref_type(__entry->type),
-		  (unsigned long long)__entry->seq)
+		  __entry->seq)
 );
 
 DEFINE_EVENT(btrfs_delayed_tree_ref,  add_delayed_tree_ref,
@@ -805,15 +806,15 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref,
 	TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s "
 		  "parent=%llu(%s) ref_root=%llu(%s) owner=%llu "
 		  "offset=%llu type=%s seq=%llu",
-		  (unsigned long long)__entry->bytenr,
-		  (unsigned long long)__entry->num_bytes,
+		  __entry->bytenr,
+		  __entry->num_bytes,
 		  show_ref_action(__entry->action),
 		  show_root_type(__entry->parent),
 		  show_root_type(__entry->ref_root),
-		  (unsigned long long)__entry->owner,
-		  (unsigned long long)__entry->offset,
+		  __entry->owner,
+		  __entry->offset,
 		  show_ref_type(__entry->type),
-		  (unsigned long long)__entry->seq)
+		  __entry->seq)
 );
 
 DEFINE_EVENT(btrfs_delayed_data_ref,  add_delayed_data_ref,
@@ -859,8 +860,8 @@ DECLARE_EVENT_CLASS(btrfs_delayed_ref_head,
 	),
 
 	TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s is_data=%d",
-		  (unsigned long long)__entry->bytenr,
-		  (unsigned long long)__entry->num_bytes,
+		  __entry->bytenr,
+		  __entry->num_bytes,
 		  show_ref_action(__entry->action),
 		  __entry->is_data)
 );
@@ -923,8 +924,8 @@ DECLARE_EVENT_CLASS(btrfs__chunk,
 	TP_printk_btrfs("root=%llu(%s) offset=%llu size=%llu "
 		  "num_stripes=%d sub_stripes=%d type=%s",
 		  show_root_type(__entry->root_objectid),
-		  (unsigned long long)__entry->offset,
-		  (unsigned long long)__entry->size,
+		  __entry->offset,
+		  __entry->size,
 		  __entry->num_stripes, __entry->sub_stripes,
 		  show_chunk_type(__entry->type))
 );
@@ -974,9 +975,9 @@ TRACE_EVENT(btrfs_cow_block,
 		  "(orig_level=%d) cow_buf=%llu (cow_level=%d)",
 		  show_root_type(__entry->root_objectid),
 		  __entry->refs,
-		  (unsigned long long)__entry->buf_start,
+		  __entry->buf_start,
 		  __entry->buf_level,
-		  (unsigned long long)__entry->cow_start,
+		  __entry->cow_start,
 		  __entry->cow_level)
 );
 
@@ -1001,7 +1002,7 @@ TRACE_EVENT(btrfs_space_reservation,
 		__entry->reserve	= reserve;
 	),
 
-	TP_printk_btrfs("%s: %Lu %s %Lu", __get_str(type), __entry->val,
+	TP_printk_btrfs("%s: %llu %s %llu", __get_str(type), __entry->val,
 			__entry->reserve ? "reserve" : "release",
 			__entry->bytes)
 );
@@ -1019,29 +1020,27 @@ TRACE_EVENT(btrfs_trigger_flush,
 
 	TP_ARGS(fs_info, flags, bytes, flush, reason),
 
-	TP_STRUCT__entry(
-		__array(	u8,	fsid,	BTRFS_FSID_SIZE	)
+	TP_STRUCT__entry_btrfs(
 		__field(	u64,	flags			)
 		__field(	u64,	bytes			)
 		__field(	int,	flush			)
 		__string(	reason,	reason			)
 	),
 
-	TP_fast_assign(
-		memcpy(__entry->fsid, fs_info->fsid, BTRFS_FSID_SIZE);
+	TP_fast_assign_btrfs(fs_info,
 		__entry->flags	= flags;
 		__entry->bytes	= bytes;
 		__entry->flush	= flush;
 		__assign_str(reason, reason)
 	),
 
-	TP_printk("%pU: %s: flush=%d(%s) flags=%llu(%s) bytes=%llu",
-		  __entry->fsid, __get_str(reason), __entry->flush,
+	TP_printk_btrfs("%s: flush=%d(%s) flags=%llu(%s) bytes=%llu",
+		  __get_str(reason), __entry->flush,
 		  show_flush_action(__entry->flush),
-		  (unsigned long long)__entry->flags,
+		  __entry->flags,
 		  __print_flags((unsigned long)__entry->flags, "|",
 				BTRFS_GROUP_FLAGS),
-		  (unsigned long long)__entry->bytes)
+		  __entry->bytes)
 );
 
 #define show_flush_state(state)							\
@@ -1060,29 +1059,27 @@ TRACE_EVENT(btrfs_flush_space,
 
 	TP_ARGS(fs_info, flags, num_bytes, state, ret),
 
-	TP_STRUCT__entry(
-		__array(	u8,	fsid,	BTRFS_FSID_SIZE	)
+	TP_STRUCT__entry_btrfs(
 		__field(	u64,	flags			)
 		__field(	u64,	num_bytes		)
 		__field(	int,	state			)
 		__field(	int,	ret			)
 	),
 
-	TP_fast_assign(
-		memcpy(__entry->fsid, fs_info->fsid, BTRFS_FSID_SIZE);
+	TP_fast_assign_btrfs(fs_info,
 		__entry->flags		=	flags;
 		__entry->num_bytes	=	num_bytes;
 		__entry->state		=	state;
 		__entry->ret		=	ret;
 	),
 
-	TP_printk("%pU: state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d",
-		  __entry->fsid, __entry->state,
+	TP_printk_btrfs("state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d",
+		  __entry->state,
 		  show_flush_state(__entry->state),
-		  (unsigned long long)__entry->flags,
+		  __entry->flags,
 		  __print_flags((unsigned long)__entry->flags, "|",
 				BTRFS_GROUP_FLAGS),
-		  (unsigned long long)__entry->num_bytes, __entry->ret)
+		  __entry->num_bytes, __entry->ret)
 );
 
 DECLARE_EVENT_CLASS(btrfs__reserved_extent,
@@ -1103,8 +1100,8 @@ DECLARE_EVENT_CLASS(btrfs__reserved_extent,
 
 	TP_printk_btrfs("root=%llu(%s) start=%llu len=%llu",
 		  show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
-		  (unsigned long long)__entry->start,
-		  (unsigned long long)__entry->len)
+		  __entry->start,
+		  __entry->len)
 );
 
 DEFINE_EVENT(btrfs__reserved_extent,  btrfs_reserved_extent_alloc,
@@ -1140,7 +1137,7 @@ TRACE_EVENT(find_free_extent,
 		__entry->data		= data;
 	),
 
-	TP_printk_btrfs("root=%Lu(%s) len=%Lu empty_size=%Lu flags=%Lu(%s)",
+	TP_printk_btrfs("root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s)",
 		  show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
 		  __entry->num_bytes, __entry->empty_size, __entry->data,
 		  __print_flags((unsigned long)__entry->data, "|",
@@ -1149,11 +1146,10 @@ TRACE_EVENT(find_free_extent,
 
 DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 
-	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct btrfs_block_group_cache *block_group, u64 start,
+	TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
 		 u64 len),
 
-	TP_ARGS(fs_info, block_group, start, len),
+	TP_ARGS(block_group, start, len),
 
 	TP_STRUCT__entry_btrfs(
 		__field(	u64,	bg_objectid		)
@@ -1162,15 +1158,15 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 		__field(	u64,	len			)
 	),
 
-	TP_fast_assign_btrfs(fs_info,
+	TP_fast_assign_btrfs(block_group->fs_info,
 		__entry->bg_objectid	= block_group->key.objectid;
 		__entry->flags		= block_group->flags;
 		__entry->start		= start;
 		__entry->len		= len;
 	),
 
-	TP_printk_btrfs("root=%Lu(%s) block_group=%Lu flags=%Lu(%s) "
-		  "start=%Lu len=%Lu",
+	TP_printk_btrfs("root=%llu(%s) block_group=%llu flags=%llu(%s) "
+		  "start=%llu len=%llu",
 		  show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
 		  __entry->bg_objectid,
 		  __entry->flags, __print_flags((unsigned long)__entry->flags,
@@ -1180,20 +1176,18 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 
 DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent,
 
-	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct btrfs_block_group_cache *block_group, u64 start,
+	TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
 		 u64 len),
 
-	TP_ARGS(fs_info, block_group, start, len)
+	TP_ARGS(block_group, start, len)
 );
 
 DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent_cluster,
 
-	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct btrfs_block_group_cache *block_group, u64 start,
+	TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
 		 u64 len),
 
-	TP_ARGS(fs_info, block_group, start, len)
+	TP_ARGS(block_group, start, len)
 );
 
 TRACE_EVENT(btrfs_find_cluster,
@@ -1221,8 +1215,8 @@ TRACE_EVENT(btrfs_find_cluster,
 		__entry->min_bytes	= min_bytes;
 	),
 
-	TP_printk_btrfs("block_group=%Lu flags=%Lu(%s) start=%Lu len=%Lu "
-		  "empty_size=%Lu min_bytes=%Lu", __entry->bg_objectid,
+	TP_printk_btrfs("block_group=%llu flags=%llu(%s) start=%llu len=%llu "
+		  "empty_size=%llu min_bytes=%llu", __entry->bg_objectid,
 		  __entry->flags,
 		  __print_flags((unsigned long)__entry->flags, "|",
 				BTRFS_GROUP_FLAGS), __entry->start,
@@ -1243,7 +1237,7 @@ TRACE_EVENT(btrfs_failed_cluster_setup,
 		__entry->bg_objectid	= block_group->key.objectid;
 	),
 
-	TP_printk_btrfs("block_group=%Lu", __entry->bg_objectid)
+	TP_printk_btrfs("block_group=%llu", __entry->bg_objectid)
 );
 
 TRACE_EVENT(btrfs_setup_cluster,
@@ -1272,8 +1266,8 @@ TRACE_EVENT(btrfs_setup_cluster,
 		__entry->bitmap		= bitmap;
 	),
 
-	TP_printk_btrfs("block_group=%Lu flags=%Lu(%s) window_start=%Lu "
-		  "size=%Lu max_size=%Lu bitmap=%d",
+	TP_printk_btrfs("block_group=%llu flags=%llu(%s) window_start=%llu "
+		  "size=%llu max_size=%llu bitmap=%d",
 		  __entry->bg_objectid,
 		  __entry->flags,
 		  __print_flags((unsigned long)__entry->flags, "|",
@@ -1476,7 +1470,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data,
 
 	TP_STRUCT__entry_btrfs(
 		__field(	u64,		rootid		)
-		__field(	unsigned long,	ino		)
+		__field(	u64,		ino		)
 		__field(	u64,		start		)
 		__field(	u64,		len		)
 		__field(	u64,		reserved	)
@@ -1485,14 +1479,14 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data,
 
 	TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
 		__entry->rootid		= BTRFS_I(inode)->root->objectid;
-		__entry->ino		= inode->i_ino;
+		__entry->ino		= btrfs_ino(BTRFS_I(inode));
 		__entry->start		= start;
 		__entry->len		= len;
 		__entry->reserved	= reserved;
 		__entry->op		= op;
 	),
 
-	TP_printk_btrfs("root=%llu ino=%lu start=%llu len=%llu reserved=%llu op=%s",
+	TP_printk_btrfs("root=%llu ino=%llu start=%llu len=%llu reserved=%llu op=%s",
 		  __entry->rootid, __entry->ino, __entry->start, __entry->len,
 		  __entry->reserved,
 		  __print_flags((unsigned long)__entry->op, "",
@@ -1584,12 +1578,14 @@ DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_trace_extent,
 
 TRACE_EVENT(btrfs_qgroup_account_extent,
 
-	TP_PROTO(const struct btrfs_fs_info *fs_info, u64 bytenr,
+	TP_PROTO(const struct btrfs_fs_info *fs_info, u64 transid, u64 bytenr,
 		 u64 num_bytes, u64 nr_old_roots, u64 nr_new_roots),
 
-	TP_ARGS(fs_info, bytenr, num_bytes, nr_old_roots, nr_new_roots),
+	TP_ARGS(fs_info, transid, bytenr, num_bytes, nr_old_roots,
+		nr_new_roots),
 
 	TP_STRUCT__entry_btrfs(
+		__field(	u64,  transid			)
 		__field(	u64,  bytenr			)
 		__field(	u64,  num_bytes			)
 		__field(	u64,  nr_old_roots		)
@@ -1597,43 +1593,49 @@ TRACE_EVENT(btrfs_qgroup_account_extent,
 	),
 
 	TP_fast_assign_btrfs(fs_info,
+		__entry->transid	= transid;
 		__entry->bytenr		= bytenr;
 		__entry->num_bytes	= num_bytes;
 		__entry->nr_old_roots	= nr_old_roots;
 		__entry->nr_new_roots	= nr_new_roots;
 	),
 
-	TP_printk_btrfs("bytenr=%llu num_bytes=%llu nr_old_roots=%llu "
-		  "nr_new_roots=%llu",
-		  __entry->bytenr,
-		  __entry->num_bytes,
-		  __entry->nr_old_roots,
-		  __entry->nr_new_roots)
+	TP_printk_btrfs(
+"transid=%llu bytenr=%llu num_bytes=%llu nr_old_roots=%llu nr_new_roots=%llu",
+		__entry->transid,
+		__entry->bytenr,
+		__entry->num_bytes,
+		__entry->nr_old_roots,
+		__entry->nr_new_roots)
 );
 
 TRACE_EVENT(qgroup_update_counters,
 
-	TP_PROTO(const struct btrfs_fs_info *fs_info, u64 qgid,
+	TP_PROTO(const struct btrfs_fs_info *fs_info,
+		 struct btrfs_qgroup *qgroup,
 		 u64 cur_old_count, u64 cur_new_count),
 
-	TP_ARGS(fs_info, qgid, cur_old_count, cur_new_count),
+	TP_ARGS(fs_info, qgroup, cur_old_count, cur_new_count),
 
 	TP_STRUCT__entry_btrfs(
 		__field(	u64,  qgid			)
+		__field(	u64,  old_rfer			)
+		__field(	u64,  old_excl			)
 		__field(	u64,  cur_old_count		)
 		__field(	u64,  cur_new_count		)
 	),
 
 	TP_fast_assign_btrfs(fs_info,
-		__entry->qgid		= qgid;
+		__entry->qgid		= qgroup->qgroupid;
+		__entry->old_rfer	= qgroup->rfer;
+		__entry->old_excl	= qgroup->excl;
 		__entry->cur_old_count	= cur_old_count;
 		__entry->cur_new_count	= cur_new_count;
 	),
 
-	TP_printk_btrfs("qgid=%llu cur_old_count=%llu cur_new_count=%llu",
-		  __entry->qgid,
-		  __entry->cur_old_count,
-		  __entry->cur_new_count)
+	TP_printk_btrfs("qgid=%llu old_rfer=%llu old_excl=%llu cur_old_count=%llu cur_new_count=%llu",
+		  __entry->qgid, __entry->old_rfer, __entry->old_excl,
+		  __entry->cur_old_count, __entry->cur_new_count)
 );
 
 TRACE_EVENT(qgroup_update_reserve,
@@ -1765,14 +1767,14 @@ DECLARE_EVENT_CLASS(btrfs__prelim_ref,
 	),
 
 	TP_printk_btrfs("root_id=%llu key=[%llu,%u,%llu] level=%d count=[%d+%d=%d] parent=%llu wanted_disk_byte=%llu nodes=%llu",
-			(unsigned long long)__entry->root_id,
-			(unsigned long long)__entry->objectid, __entry->type,
-			(unsigned long long)__entry->offset, __entry->level,
+			__entry->root_id,
+			__entry->objectid, __entry->type,
+			__entry->offset, __entry->level,
 			__entry->old_count, __entry->mod_count,
 			__entry->old_count + __entry->mod_count,
-			(unsigned long long)__entry->parent,
-			(unsigned long long)__entry->bytenr,
-			(unsigned long long)__entry->tree_size)
+			__entry->parent,
+			__entry->bytenr,
+			__entry->tree_size)
 );
 
 DEFINE_EVENT(btrfs__prelim_ref, btrfs_prelim_ref_merge,
@@ -1808,8 +1810,51 @@ TRACE_EVENT(btrfs_inode_mod_outstanding_extents,
 
 	TP_printk_btrfs("root=%llu(%s) ino=%llu mod=%d",
 			show_root_type(__entry->root_objectid),
-			(unsigned long long)__entry->ino, __entry->mod)
+			__entry->ino, __entry->mod)
 );
+
+DECLARE_EVENT_CLASS(btrfs__block_group,
+	TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+
+	TP_ARGS(bg_cache),
+
+	TP_STRUCT__entry_btrfs(
+		__field(	u64,	bytenr		)
+		__field(	u64,	len		)
+		__field(	u64,	used		)
+		__field(	u64,	flags		)
+	),
+
+	TP_fast_assign_btrfs(bg_cache->fs_info,
+		__entry->bytenr = bg_cache->key.objectid,
+		__entry->len	= bg_cache->key.offset,
+		__entry->used	= btrfs_block_group_used(&bg_cache->item);
+		__entry->flags	= bg_cache->flags;
+	),
+
+	TP_printk_btrfs("bg bytenr=%llu len=%llu used=%llu flags=%llu(%s)",
+		__entry->bytenr, __entry->len, __entry->used, __entry->flags,
+		__print_flags(__entry->flags, "|", BTRFS_GROUP_FLAGS))
+);
+
+DEFINE_EVENT(btrfs__block_group, btrfs_remove_block_group,
+	TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+
+	TP_ARGS(bg_cache)
+);
+
+DEFINE_EVENT(btrfs__block_group, btrfs_add_unused_block_group,
+	TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+
+	TP_ARGS(bg_cache)
+);
+
+DEFINE_EVENT(btrfs__block_group, btrfs_skip_unused_block_group,
+	TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+
+	TP_ARGS(bg_cache)
+);
+
 #endif /* _TRACE_BTRFS_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/host1x.h b/include/trace/events/host1x.h
index 63116362543c..a37ef73092e5 100644
--- a/include/trace/events/host1x.h
+++ b/include/trace/events/host1x.h
@@ -115,16 +115,15 @@ TRACE_EVENT(host1x_cdma_push_gather,
 );
 
 TRACE_EVENT(host1x_channel_submit,
-	TP_PROTO(const char *name, u32 cmdbufs, u32 relocs, u32 waitchks,
-			u32 syncpt_id, u32 syncpt_incrs),
+	TP_PROTO(const char *name, u32 cmdbufs, u32 relocs, u32 syncpt_id,
+		 u32 syncpt_incrs),
 
-	TP_ARGS(name, cmdbufs, relocs, waitchks, syncpt_id, syncpt_incrs),
+	TP_ARGS(name, cmdbufs, relocs, syncpt_id, syncpt_incrs),
 
 	TP_STRUCT__entry(
 		__field(const char *, name)
 		__field(u32, cmdbufs)
 		__field(u32, relocs)
-		__field(u32, waitchks)
 		__field(u32, syncpt_id)
 		__field(u32, syncpt_incrs)
 	),
@@ -133,15 +132,14 @@ TRACE_EVENT(host1x_channel_submit,
 		__entry->name = name;
 		__entry->cmdbufs = cmdbufs;
 		__entry->relocs = relocs;
-		__entry->waitchks = waitchks;
 		__entry->syncpt_id = syncpt_id;
 		__entry->syncpt_incrs = syncpt_incrs;
 	),
 
-	TP_printk("name=%s, cmdbufs=%u, relocs=%u, waitchks=%d,"
-		"syncpt_id=%u, syncpt_incrs=%u",
-	  __entry->name, __entry->cmdbufs, __entry->relocs, __entry->waitchks,
-	  __entry->syncpt_id, __entry->syncpt_incrs)
+	TP_printk("name=%s, cmdbufs=%u, relocs=%u, syncpt_id=%u, "
+		  "syncpt_incrs=%u",
+		  __entry->name, __entry->cmdbufs, __entry->relocs,
+		  __entry->syncpt_id, __entry->syncpt_incrs)
 );
 
 TRACE_EVENT(host1x_channel_submitted,
diff --git a/include/trace/events/initcall.h b/include/trace/events/initcall.h
index 8d6cf10d27c9..eb903c3f195f 100644
--- a/include/trace/events/initcall.h
+++ b/include/trace/events/initcall.h
@@ -31,7 +31,11 @@ TRACE_EVENT(initcall_start,
 	TP_ARGS(func),
 
 	TP_STRUCT__entry(
-		__field(initcall_t, func)
+		/*
+		 * Use field_struct to avoid is_signed_type()
+		 * comparison of a function pointer
+		 */
+		__field_struct(initcall_t, func)
 	),
 
 	TP_fast_assign(
@@ -48,8 +52,12 @@ TRACE_EVENT(initcall_finish,
 	TP_ARGS(func, ret),
 
 	TP_STRUCT__entry(
-		__field(initcall_t,	func)
-		__field(int,		ret)
+		/*
+		 * Use field_struct to avoid is_signed_type()
+		 * comparison of a function pointer
+		 */
+		__field_struct(initcall_t,	func)
+		__field(int,			ret)
 	),
 
 	TP_fast_assign(
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index d8c33298c153..5936aac357ab 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -84,20 +84,21 @@ TRACE_EVENT(rcu_grace_period,
 );
 
 /*
- * Tracepoint for future grace-period events, including those for no-callbacks
- * CPUs.  The caller should pull the data from the rcu_node structure,
- * other than rcuname, which comes from the rcu_state structure, and event,
- * which is one of the following:
+ * Tracepoint for future grace-period events.  The caller should pull
+ * the data from the rcu_node structure, other than rcuname, which comes
+ * from the rcu_state structure, and event, which is one of the following:
  *
- * "Startleaf": Request a nocb grace period based on leaf-node data.
+ * "Startleaf": Request a grace period based on leaf-node data.
+ * "Prestarted": Someone beat us to the request
  * "Startedleaf": Leaf-node start proved sufficient.
  * "Startedleafroot": Leaf-node start proved sufficient after checking root.
  * "Startedroot": Requested a nocb grace period based on root-node data.
+ * "NoGPkthread": The RCU grace-period kthread has not yet started.
  * "StartWait": Start waiting for the requested grace period.
  * "ResumeWait": Resume waiting after signal.
  * "EndWait": Complete wait.
  * "Cleanup": Clean up rcu_node structure after previous GP.
- * "CleanupMore": Clean up, and another no-CB GP is needed.
+ * "CleanupMore": Clean up, and another GP is needed.
  */
 TRACE_EVENT(rcu_future_grace_period,
 
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 9e96c2fe2793..077e664ac9a2 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -15,6 +15,7 @@
 #define _TRACE_RXRPC_H
 
 #include <linux/tracepoint.h>
+#include <linux/errqueue.h>
 
 /*
  * Define enums for tracing information.
@@ -210,6 +211,20 @@ enum rxrpc_congest_change {
 	rxrpc_cong_saw_nack,
 };
 
+enum rxrpc_tx_fail_trace {
+	rxrpc_tx_fail_call_abort,
+	rxrpc_tx_fail_call_ack,
+	rxrpc_tx_fail_call_data_frag,
+	rxrpc_tx_fail_call_data_nofrag,
+	rxrpc_tx_fail_call_final_resend,
+	rxrpc_tx_fail_conn_abort,
+	rxrpc_tx_fail_conn_challenge,
+	rxrpc_tx_fail_conn_response,
+	rxrpc_tx_fail_reject,
+	rxrpc_tx_fail_version_keepalive,
+	rxrpc_tx_fail_version_reply,
+};
+
 #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */
 
 /*
@@ -437,6 +452,19 @@ enum rxrpc_congest_change {
 	EM(RXRPC_CALL_LOCAL_ERROR,		"LocalError") \
 	E_(RXRPC_CALL_NETWORK_ERROR,		"NetError")
 
+#define rxrpc_tx_fail_traces \
+	EM(rxrpc_tx_fail_call_abort,		"CallAbort") \
+	EM(rxrpc_tx_fail_call_ack,		"CallAck") \
+	EM(rxrpc_tx_fail_call_data_frag,	"CallDataFrag") \
+	EM(rxrpc_tx_fail_call_data_nofrag,	"CallDataNofrag") \
+	EM(rxrpc_tx_fail_call_final_resend,	"CallFinalResend") \
+	EM(rxrpc_tx_fail_conn_abort,		"ConnAbort") \
+	EM(rxrpc_tx_fail_conn_challenge,	"ConnChall") \
+	EM(rxrpc_tx_fail_conn_response,		"ConnResp") \
+	EM(rxrpc_tx_fail_reject,		"Reject") \
+	EM(rxrpc_tx_fail_version_keepalive,	"VerKeepalive") \
+	E_(rxrpc_tx_fail_version_reply,		"VerReply")
+
 /*
  * Export enum symbols via userspace.
  */
@@ -460,6 +488,7 @@ rxrpc_propose_ack_traces;
 rxrpc_propose_ack_outcomes;
 rxrpc_congest_modes;
 rxrpc_congest_changes;
+rxrpc_tx_fail_traces;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -1374,6 +1403,62 @@ TRACE_EVENT(rxrpc_resend,
 		      __entry->anno)
 	    );
 
+TRACE_EVENT(rxrpc_rx_icmp,
+	    TP_PROTO(struct rxrpc_peer *peer, struct sock_extended_err *ee,
+		     struct sockaddr_rxrpc *srx),
+
+	    TP_ARGS(peer, ee, srx),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,			peer	)
+		    __field_struct(struct sock_extended_err,	ee	)
+		    __field_struct(struct sockaddr_rxrpc,	srx	)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->peer = peer->debug_id;
+		    memcpy(&__entry->ee, ee, sizeof(__entry->ee));
+		    memcpy(&__entry->srx, srx, sizeof(__entry->srx));
+			   ),
+
+	    TP_printk("P=%08x o=%u t=%u c=%u i=%u d=%u e=%d %pISp",
+		      __entry->peer,
+		      __entry->ee.ee_origin,
+		      __entry->ee.ee_type,
+		      __entry->ee.ee_code,
+		      __entry->ee.ee_info,
+		      __entry->ee.ee_data,
+		      __entry->ee.ee_errno,
+		      &__entry->srx.transport)
+	    );
+
+TRACE_EVENT(rxrpc_tx_fail,
+	    TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial, int ret,
+		     enum rxrpc_tx_fail_trace what),
+
+	    TP_ARGS(debug_id, serial, ret, what),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		debug_id	)
+		    __field(rxrpc_serial_t,		serial		)
+		    __field(int,			ret		)
+		    __field(enum rxrpc_tx_fail_trace,   what		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->debug_id = debug_id;
+		    __entry->serial = serial;
+		    __entry->ret = ret;
+		    __entry->what = what;
+			   ),
+
+	    TP_printk("c=%08x r=%x ret=%d %s",
+		      __entry->debug_id,
+		      __entry->serial,
+		      __entry->ret,
+		      __print_symbolic(__entry->what, rxrpc_tx_fail_traces))
+	    );
+
 #endif /* _TRACE_RXRPC_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index bc01e06bc716..0be866c91f62 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -435,7 +435,9 @@ TRACE_EVENT(sched_pi_setprio,
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->oldprio	= tsk->prio;
-		__entry->newprio	= pi_task ? pi_task->prio : tsk->prio;
+		__entry->newprio	= pi_task ?
+				min(tsk->normal_prio, pi_task->prio) :
+				tsk->normal_prio;
 		/* XXX SCHED_DEADLINE bits missing */
 	),
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 335d87242439..bbb08a3ef5cc 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -224,6 +224,8 @@ TRACE_EVENT(rpc_stats_latency,
 	TP_ARGS(task, backlog, rtt, execute),
 
 	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
 		__field(u32, xid)
 		__field(int, version)
 		__string(progname, task->tk_client->cl_program->name)
@@ -231,13 +233,11 @@ TRACE_EVENT(rpc_stats_latency,
 		__field(unsigned long, backlog)
 		__field(unsigned long, rtt)
 		__field(unsigned long, execute)
-		__string(addr,
-			 task->tk_xprt->address_strings[RPC_DISPLAY_ADDR])
-		__string(port,
-			 task->tk_xprt->address_strings[RPC_DISPLAY_PORT])
 	),
 
 	TP_fast_assign(
+		__entry->client_id = task->tk_client->cl_clid;
+		__entry->task_id = task->tk_pid;
 		__entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid);
 		__entry->version = task->tk_client->cl_vers;
 		__assign_str(progname, task->tk_client->cl_program->name)
@@ -245,14 +245,10 @@ TRACE_EVENT(rpc_stats_latency,
 		__entry->backlog = ktime_to_us(backlog);
 		__entry->rtt = ktime_to_us(rtt);
 		__entry->execute = ktime_to_us(execute);
-		__assign_str(addr,
-			     task->tk_xprt->address_strings[RPC_DISPLAY_ADDR]);
-		__assign_str(port,
-			     task->tk_xprt->address_strings[RPC_DISPLAY_PORT]);
 	),
 
-	TP_printk("peer=[%s]:%s xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu",
-		__get_str(addr), __get_str(port), __entry->xid,
+	TP_printk("task:%u@%d xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu",
+		__entry->task_id, __entry->client_id, __entry->xid,
 		__get_str(progname), __entry->version, __get_str(procname),
 		__entry->backlog, __entry->rtt, __entry->execute)
 );
diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h
index bf6f82673492..f8260e5c79ad 100644
--- a/include/trace/events/ufs.h
+++ b/include/trace/events/ufs.h
@@ -257,6 +257,33 @@ TRACE_EVENT(ufshcd_command,
 	)
 );
 
+TRACE_EVENT(ufshcd_upiu,
+	TP_PROTO(const char *dev_name, const char *str, void *hdr, void *tsf),
+
+	TP_ARGS(dev_name, str, hdr, tsf),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name)
+		__string(str, str)
+		__array(unsigned char, hdr, 12)
+		__array(unsigned char, tsf, 16)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__assign_str(str, str);
+		memcpy(__entry->hdr, hdr, sizeof(__entry->hdr));
+		memcpy(__entry->tsf, tsf, sizeof(__entry->tsf));
+	),
+
+	TP_printk(
+		"%s: %s: HDR:%s, CDB:%s",
+		__get_str(str), __get_str(dev_name),
+		__print_hex(__entry->hdr, sizeof(__entry->hdr)),
+		__print_hex(__entry->tsf, sizeof(__entry->tsf))
+	)
+);
+
 #endif /* if !defined(_TRACE_UFS_H) || defined(TRACE_HEADER_MULTI_READ) */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
index 2f057a494d93..9a761bc6a251 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h
@@ -25,6 +25,8 @@ DECLARE_EVENT_CLASS(workqueue_work,
 	TP_printk("work struct %p", __entry->work)
 );
 
+struct pool_workqueue;
+
 /**
  * workqueue_queue_work - called when a work gets queued
  * @req_cpu:	the requested cpu
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index 7dd8f34c37df..fdcf88bcf0ea 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -352,22 +352,6 @@ DECLARE_EVENT_CLASS(xen_mmu_pgd,
 DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_pin);
 DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_unpin);
 
-TRACE_EVENT(xen_mmu_flush_tlb_all,
-	    TP_PROTO(int x),
-	    TP_ARGS(x),
-	    TP_STRUCT__entry(__array(char, x, 0)),
-	    TP_fast_assign((void)x),
-	    TP_printk("%s", "")
-	);
-
-TRACE_EVENT(xen_mmu_flush_tlb,
-	    TP_PROTO(int x),
-	    TP_ARGS(x),
-	    TP_STRUCT__entry(__array(char, x, 0)),
-	    TP_fast_assign((void)x),
-	    TP_printk("%s", "")
-	);
-
 TRACE_EVENT(xen_mmu_flush_tlb_one_user,
 	    TP_PROTO(unsigned long addr),
 	    TP_ARGS(addr),
diff --git a/include/uapi/asm-generic/msgbuf.h b/include/uapi/asm-generic/msgbuf.h
index fb306ebdb36f..9fe4881557cb 100644
--- a/include/uapi/asm-generic/msgbuf.h
+++ b/include/uapi/asm-generic/msgbuf.h
@@ -18,31 +18,30 @@
  * On big-endian systems, the padding is in the wrong place.
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
 
 struct msqid64_ds {
 	struct ipc64_perm msg_perm;
+#if __BITS_PER_LONG == 64
 	__kernel_time_t msg_stime;	/* last msgsnd time */
-#if __BITS_PER_LONG != 64
-	unsigned long	__unused1;
-#endif
 	__kernel_time_t msg_rtime;	/* last msgrcv time */
-#if __BITS_PER_LONG != 64
-	unsigned long	__unused2;
-#endif
 	__kernel_time_t msg_ctime;	/* last change time */
-#if __BITS_PER_LONG != 64
-	unsigned long	__unused3;
+#else
+	unsigned long	msg_stime;	/* last msgsnd time */
+	unsigned long	msg_stime_high;
+	unsigned long	msg_rtime;	/* last msgrcv time */
+	unsigned long	msg_rtime_high;
+	unsigned long	msg_ctime;	/* last change time */
+	unsigned long	msg_ctime_high;
 #endif
-	__kernel_ulong_t msg_cbytes;	/* current number of bytes on queue */
-	__kernel_ulong_t msg_qnum;	/* number of messages in queue */
-	__kernel_ulong_t msg_qbytes;	/* max number of bytes on queue */
+	unsigned long	msg_cbytes;	/* current number of bytes on queue */
+	unsigned long	msg_qnum;	/* number of messages in queue */
+	unsigned long	 msg_qbytes;	/* max number of bytes on queue */
 	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
 	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	__kernel_ulong_t __unused4;
-	__kernel_ulong_t __unused5;
+	unsigned long	 __unused4;
+	unsigned long	 __unused5;
 };
 
 #endif /* __ASM_GENERIC_MSGBUF_H */
diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h
index 5e6ea22bd525..f0733a26ebfc 100644
--- a/include/uapi/asm-generic/posix_types.h
+++ b/include/uapi/asm-generic/posix_types.h
@@ -87,6 +87,7 @@ typedef struct {
 typedef __kernel_long_t	__kernel_off_t;
 typedef long long	__kernel_loff_t;
 typedef __kernel_long_t	__kernel_time_t;
+typedef long long __kernel_time64_t;
 typedef __kernel_long_t	__kernel_clock_t;
 typedef int		__kernel_timer_t;
 typedef int		__kernel_clockid_t;
diff --git a/include/uapi/asm-generic/sembuf.h b/include/uapi/asm-generic/sembuf.h
index cbf9cfe977d6..0bae010f1b64 100644
--- a/include/uapi/asm-generic/sembuf.h
+++ b/include/uapi/asm-generic/sembuf.h
@@ -13,23 +13,29 @@
  * everyone just ended up making identical copies without specific
  * optimizations, so we may just as well all use the same one.
  *
- * 64 bit architectures typically define a 64 bit __kernel_time_t,
+ * 64 bit architectures use a 64-bit __kernel_time_t here, while
+ * 32 bit architectures have a pair of unsigned long values.
  * so they do not need the first two padding words.
- * On big-endian systems, the padding is in the wrong place.
  *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
+ * On big-endian systems, the padding is in the wrong place for
+ * historic reasons, so user space has to reconstruct a time_t
+ * value using
+ *
+ * user_semid_ds.sem_otime = kernel_semid64_ds.sem_otime +
+ *		((long long)kernel_semid64_ds.sem_otime_high << 32)
+ *
+ * Pad space is left for 2 miscellaneous 32-bit values
  */
 struct semid64_ds {
 	struct ipc64_perm sem_perm;	/* permissions .. see ipc.h */
+#if __BITS_PER_LONG == 64
 	__kernel_time_t	sem_otime;	/* last semop time */
-#if __BITS_PER_LONG != 64
-	unsigned long	__unused1;
-#endif
 	__kernel_time_t	sem_ctime;	/* last change time */
-#if __BITS_PER_LONG != 64
-	unsigned long	__unused2;
+#else
+	unsigned long	sem_otime;	/* last semop time */
+	unsigned long	sem_otime_high;
+	unsigned long	sem_ctime;	/* last change time */
+	unsigned long	sem_ctime_high;
 #endif
 	unsigned long	sem_nsems;	/* no. of semaphores in array */
 	unsigned long	__unused3;
diff --git a/include/uapi/asm-generic/shmbuf.h b/include/uapi/asm-generic/shmbuf.h
index 2b6c3bb97f97..e504422fc501 100644
--- a/include/uapi/asm-generic/shmbuf.h
+++ b/include/uapi/asm-generic/shmbuf.h
@@ -19,42 +19,41 @@
  *
  *
  * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
  * - 2 miscellaneous 32-bit values
  */
 
 struct shmid64_ds {
 	struct ipc64_perm	shm_perm;	/* operation perms */
 	size_t			shm_segsz;	/* size of segment (bytes) */
+#if __BITS_PER_LONG == 64
 	__kernel_time_t		shm_atime;	/* last attach time */
-#if __BITS_PER_LONG != 64
-	unsigned long		__unused1;
-#endif
 	__kernel_time_t		shm_dtime;	/* last detach time */
-#if __BITS_PER_LONG != 64
-	unsigned long		__unused2;
-#endif
 	__kernel_time_t		shm_ctime;	/* last change time */
-#if __BITS_PER_LONG != 64
-	unsigned long		__unused3;
+#else
+	unsigned long		shm_atime;	/* last attach time */
+	unsigned long		shm_atime_high;
+	unsigned long		shm_dtime;	/* last detach time */
+	unsigned long		shm_dtime_high;
+	unsigned long		shm_ctime;	/* last change time */
+	unsigned long		shm_ctime_high;
 #endif
 	__kernel_pid_t		shm_cpid;	/* pid of creator */
 	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	__kernel_ulong_t	shm_nattch;	/* no. of current attaches */
-	__kernel_ulong_t	__unused4;
-	__kernel_ulong_t	__unused5;
+	unsigned long		shm_nattch;	/* no. of current attaches */
+	unsigned long		__unused4;
+	unsigned long		__unused5;
 };
 
 struct shminfo64 {
-	__kernel_ulong_t	shmmax;
-	__kernel_ulong_t	shmmin;
-	__kernel_ulong_t	shmmni;
-	__kernel_ulong_t	shmseg;
-	__kernel_ulong_t	shmall;
-	__kernel_ulong_t	__unused1;
-	__kernel_ulong_t	__unused2;
-	__kernel_ulong_t	__unused3;
-	__kernel_ulong_t	__unused4;
+	unsigned long		shmmax;
+	unsigned long		shmmin;
+	unsigned long		shmmni;
+	unsigned long		shmseg;
+	unsigned long		shmall;
+	unsigned long		__unused1;
+	unsigned long		__unused2;
+	unsigned long		__unused3;
+	unsigned long		__unused4;
 };
 
 #endif /* __ASM_GENERIC_SHMBUF_H */
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 558b902f18d4..80e2a7227205 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -249,7 +249,8 @@ typedef struct siginfo {
 #define TRAP_TRACE	2	/* process trace trap */
 #define TRAP_BRANCH     3	/* process taken branch trap */
 #define TRAP_HWBKPT     4	/* hardware breakpoint/watchpoint */
-#define NSIGTRAP	4
+#define TRAP_UNK	5	/* undiagnosed trap */
+#define NSIGTRAP	5
 
 /*
  * There is an additional set of SIGTRAP si_codes used by ptrace
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 8bcb186c6f67..42990676a55e 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -732,9 +732,11 @@ __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 #define __NR_statx 291
 __SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
 
 #undef __NR_syscalls
-#define __NR_syscalls 292
+#define __NR_syscalls 293
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index c363b67f2d0a..78b4dd89fcb4 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -78,6 +78,12 @@ extern "C" {
 #define AMDGPU_GEM_DOMAIN_GDS		0x8
 #define AMDGPU_GEM_DOMAIN_GWS		0x10
 #define AMDGPU_GEM_DOMAIN_OA		0x20
+#define AMDGPU_GEM_DOMAIN_MASK		(AMDGPU_GEM_DOMAIN_CPU | \
+					 AMDGPU_GEM_DOMAIN_GTT | \
+					 AMDGPU_GEM_DOMAIN_VRAM | \
+					 AMDGPU_GEM_DOMAIN_GDS | \
+					 AMDGPU_GEM_DOMAIN_GWS | \
+					 AMDGPU_GEM_DOMAIN_OA)
 
 /* Flag that CPU access will be required for the case of VRAM domain */
 #define AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED	(1 << 0)
@@ -95,6 +101,10 @@ extern "C" {
 #define AMDGPU_GEM_CREATE_VM_ALWAYS_VALID	(1 << 6)
 /* Flag that BO sharing will be explicitly synchronized */
 #define AMDGPU_GEM_CREATE_EXPLICIT_SYNC		(1 << 7)
+/* Flag that indicates allocating MQD gart on GFX9, where the mtype
+ * for the second page onward should be set to NC.
+ */
+#define AMDGPU_GEM_CREATE_MQD_GFX9		(1 << 8)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
@@ -520,6 +530,10 @@ union drm_amdgpu_cs {
 /* Preempt flag, IB should set Pre_enb bit if PREEMPT flag detected */
 #define AMDGPU_IB_FLAG_PREEMPT (1<<2)
 
+/* The IB fence should do the L2 writeback but not invalidate any shader
+ * caches (L2/vL1/sL1/I$). */
+#define AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE (1 << 3)
+
 struct drm_amdgpu_cs_chunk_ib {
 	__u32 _pad;
 	/** AMDGPU_IB_FLAG_* */
@@ -620,6 +634,12 @@ struct drm_amdgpu_cs_chunk_data {
 	#define AMDGPU_INFO_FW_ASD		0x0d
 	/* Subquery id: Query VCN firmware version */
 	#define AMDGPU_INFO_FW_VCN		0x0e
+	/* Subquery id: Query GFX RLC SRLC firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_CNTL 0x0f
+	/* Subquery id: Query GFX RLC SRLG firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_GPM_MEM 0x10
+	/* Subquery id: Query GFX RLC SRLS firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_SRM_MEM 0x11
 /* number of bytes moved for TTM migration */
 #define AMDGPU_INFO_NUM_BYTES_MOVED		0x0f
 /* the used VRAM size */
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 6fdff5945c8a..9c660e1688ab 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -680,6 +680,13 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO    4
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 50bcf4214ff9..4b3a1bb58e68 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -93,6 +93,8 @@ extern "C" {
 #define DRM_MODE_PICTURE_ASPECT_NONE		0
 #define DRM_MODE_PICTURE_ASPECT_4_3		1
 #define DRM_MODE_PICTURE_ASPECT_16_9		2
+#define DRM_MODE_PICTURE_ASPECT_64_27		3
+#define DRM_MODE_PICTURE_ASPECT_256_135		4
 
 /* Aspect ratio flag bitmask (4 bits 22:19) */
 #define DRM_MODE_FLAG_PIC_AR_MASK		(0x0F<<19)
@@ -102,6 +104,10 @@ extern "C" {
 			(DRM_MODE_PICTURE_ASPECT_4_3<<19)
 #define  DRM_MODE_FLAG_PIC_AR_16_9 \
 			(DRM_MODE_PICTURE_ASPECT_16_9<<19)
+#define  DRM_MODE_FLAG_PIC_AR_64_27 \
+			(DRM_MODE_PICTURE_ASPECT_64_27<<19)
+#define  DRM_MODE_FLAG_PIC_AR_256_135 \
+			(DRM_MODE_PICTURE_ASPECT_256_135<<19)
 
 #define  DRM_MODE_FLAG_ALL	(DRM_MODE_FLAG_PHSYNC |		\
 				 DRM_MODE_FLAG_NHSYNC |		\
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index 4a54305120e0..3e59b8382dd8 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -135,6 +135,219 @@ struct drm_exynos_g2d_exec {
 	__u64					async;
 };
 
+/* Exynos DRM IPP v2 API */
+
+/**
+ * Enumerate available IPP hardware modules.
+ *
+ * @count_ipps: size of ipp_id array / number of ipp modules (set by driver)
+ * @reserved: padding
+ * @ipp_id_ptr: pointer to ipp_id array or NULL
+ */
+struct drm_exynos_ioctl_ipp_get_res {
+	__u32 count_ipps;
+	__u32 reserved;
+	__u64 ipp_id_ptr;
+};
+
+enum drm_exynos_ipp_format_type {
+	DRM_EXYNOS_IPP_FORMAT_SOURCE		= 0x01,
+	DRM_EXYNOS_IPP_FORMAT_DESTINATION	= 0x02,
+};
+
+struct drm_exynos_ipp_format {
+	__u32 fourcc;
+	__u32 type;
+	__u64 modifier;
+};
+
+enum drm_exynos_ipp_capability {
+	DRM_EXYNOS_IPP_CAP_CROP		= 0x01,
+	DRM_EXYNOS_IPP_CAP_ROTATE	= 0x02,
+	DRM_EXYNOS_IPP_CAP_SCALE	= 0x04,
+	DRM_EXYNOS_IPP_CAP_CONVERT	= 0x08,
+};
+
+/**
+ * Get IPP hardware capabilities and supported image formats.
+ *
+ * @ipp_id: id of IPP module to query
+ * @capabilities: bitmask of drm_exynos_ipp_capability (set by driver)
+ * @reserved: padding
+ * @formats_count: size of formats array (in entries) / number of filled
+ *		   formats (set by driver)
+ * @formats_ptr: pointer to formats array or NULL
+ */
+struct drm_exynos_ioctl_ipp_get_caps {
+	__u32 ipp_id;
+	__u32 capabilities;
+	__u32 reserved;
+	__u32 formats_count;
+	__u64 formats_ptr;
+};
+
+enum drm_exynos_ipp_limit_type {
+	/* size (horizontal/vertial) limits, in pixels (min, max, alignment) */
+	DRM_EXYNOS_IPP_LIMIT_TYPE_SIZE		= 0x0001,
+	/* scale ratio (horizonta/vertial), 16.16 fixed point (min, max) */
+	DRM_EXYNOS_IPP_LIMIT_TYPE_SCALE		= 0x0002,
+
+	/* image buffer area */
+	DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER	= 0x0001 << 16,
+	/* src/dst rectangle area */
+	DRM_EXYNOS_IPP_LIMIT_SIZE_AREA		= 0x0002 << 16,
+	/* src/dst rectangle area when rotation enabled */
+	DRM_EXYNOS_IPP_LIMIT_SIZE_ROTATED	= 0x0003 << 16,
+
+	DRM_EXYNOS_IPP_LIMIT_TYPE_MASK		= 0x000f,
+	DRM_EXYNOS_IPP_LIMIT_SIZE_MASK		= 0x000f << 16,
+};
+
+struct drm_exynos_ipp_limit_val {
+	__u32 min;
+	__u32 max;
+	__u32 align;
+	__u32 reserved;
+};
+
+/**
+ * IPP module limitation.
+ *
+ * @type: limit type (see drm_exynos_ipp_limit_type enum)
+ * @reserved: padding
+ * @h: horizontal limits
+ * @v: vertical limits
+ */
+struct drm_exynos_ipp_limit {
+	__u32 type;
+	__u32 reserved;
+	struct drm_exynos_ipp_limit_val h;
+	struct drm_exynos_ipp_limit_val v;
+};
+
+/**
+ * Get IPP limits for given image format.
+ *
+ * @ipp_id: id of IPP module to query
+ * @fourcc: image format code (see DRM_FORMAT_* in drm_fourcc.h)
+ * @modifier: image format modifier (see DRM_FORMAT_MOD_* in drm_fourcc.h)
+ * @type: source/destination identifier (drm_exynos_ipp_format_flag enum)
+ * @limits_count: size of limits array (in entries) / number of filled entries
+ *		 (set by driver)
+ * @limits_ptr: pointer to limits array or NULL
+ */
+struct drm_exynos_ioctl_ipp_get_limits {
+	__u32 ipp_id;
+	__u32 fourcc;
+	__u64 modifier;
+	__u32 type;
+	__u32 limits_count;
+	__u64 limits_ptr;
+};
+
+enum drm_exynos_ipp_task_id {
+	/* buffer described by struct drm_exynos_ipp_task_buffer */
+	DRM_EXYNOS_IPP_TASK_BUFFER		= 0x0001,
+	/* rectangle described by struct drm_exynos_ipp_task_rect */
+	DRM_EXYNOS_IPP_TASK_RECTANGLE		= 0x0002,
+	/* transformation described by struct drm_exynos_ipp_task_transform */
+	DRM_EXYNOS_IPP_TASK_TRANSFORM		= 0x0003,
+	/* alpha configuration described by struct drm_exynos_ipp_task_alpha */
+	DRM_EXYNOS_IPP_TASK_ALPHA		= 0x0004,
+
+	/* source image data (for buffer and rectangle chunks) */
+	DRM_EXYNOS_IPP_TASK_TYPE_SOURCE		= 0x0001 << 16,
+	/* destination image data (for buffer and rectangle chunks) */
+	DRM_EXYNOS_IPP_TASK_TYPE_DESTINATION	= 0x0002 << 16,
+};
+
+/**
+ * Memory buffer with image data.
+ *
+ * @id: must be DRM_EXYNOS_IPP_TASK_BUFFER
+ * other parameters are same as for AddFB2 generic DRM ioctl
+ */
+struct drm_exynos_ipp_task_buffer {
+	__u32	id;
+	__u32	fourcc;
+	__u32	width, height;
+	__u32	gem_id[4];
+	__u32	offset[4];
+	__u32	pitch[4];
+	__u64	modifier;
+};
+
+/**
+ * Rectangle for processing.
+ *
+ * @id: must be DRM_EXYNOS_IPP_TASK_RECTANGLE
+ * @reserved: padding
+ * @x,@y: left corner in pixels
+ * @w,@h: width/height in pixels
+ */
+struct drm_exynos_ipp_task_rect {
+	__u32	id;
+	__u32	reserved;
+	__u32	x;
+	__u32	y;
+	__u32	w;
+	__u32	h;
+};
+
+/**
+ * Image tranformation description.
+ *
+ * @id: must be DRM_EXYNOS_IPP_TASK_TRANSFORM
+ * @rotation: DRM_MODE_ROTATE_* and DRM_MODE_REFLECT_* values
+ */
+struct drm_exynos_ipp_task_transform {
+	__u32	id;
+	__u32	rotation;
+};
+
+/**
+ * Image global alpha configuration for formats without alpha values.
+ *
+ * @id: must be DRM_EXYNOS_IPP_TASK_ALPHA
+ * @value: global alpha value (0-255)
+ */
+struct drm_exynos_ipp_task_alpha {
+	__u32	id;
+	__u32	value;
+};
+
+enum drm_exynos_ipp_flag {
+	/* generate DRM event after processing */
+	DRM_EXYNOS_IPP_FLAG_EVENT	= 0x01,
+	/* dry run, only check task parameters */
+	DRM_EXYNOS_IPP_FLAG_TEST_ONLY	= 0x02,
+	/* non-blocking processing */
+	DRM_EXYNOS_IPP_FLAG_NONBLOCK	= 0x04,
+};
+
+#define DRM_EXYNOS_IPP_FLAGS (DRM_EXYNOS_IPP_FLAG_EVENT |\
+		DRM_EXYNOS_IPP_FLAG_TEST_ONLY | DRM_EXYNOS_IPP_FLAG_NONBLOCK)
+
+/**
+ * Perform image processing described by array of drm_exynos_ipp_task_*
+ * structures (parameters array).
+ *
+ * @ipp_id: id of IPP module to run the task
+ * @flags: bitmask of drm_exynos_ipp_flag values
+ * @reserved: padding
+ * @params_size: size of parameters array (in bytes)
+ * @params_ptr: pointer to parameters array or NULL
+ * @user_data: (optional) data for drm event
+ */
+struct drm_exynos_ioctl_ipp_commit {
+	__u32 ipp_id;
+	__u32 flags;
+	__u32 reserved;
+	__u32 params_size;
+	__u64 params_ptr;
+	__u64 user_data;
+};
+
 #define DRM_EXYNOS_GEM_CREATE		0x00
 #define DRM_EXYNOS_GEM_MAP		0x01
 /* Reserved 0x03 ~ 0x05 for exynos specific gem ioctl */
@@ -147,6 +360,11 @@ struct drm_exynos_g2d_exec {
 #define DRM_EXYNOS_G2D_EXEC		0x22
 
 /* Reserved 0x30 ~ 0x33 for obsolete Exynos IPP ioctls */
+/* IPP - Image Post Processing */
+#define DRM_EXYNOS_IPP_GET_RESOURCES	0x40
+#define DRM_EXYNOS_IPP_GET_CAPS		0x41
+#define DRM_EXYNOS_IPP_GET_LIMITS	0x42
+#define DRM_EXYNOS_IPP_COMMIT		0x43
 
 #define DRM_IOCTL_EXYNOS_GEM_CREATE		DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_GEM_CREATE, struct drm_exynos_gem_create)
@@ -165,8 +383,20 @@ struct drm_exynos_g2d_exec {
 #define DRM_IOCTL_EXYNOS_G2D_EXEC		DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_G2D_EXEC, struct drm_exynos_g2d_exec)
 
+#define DRM_IOCTL_EXYNOS_IPP_GET_RESOURCES	DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_GET_RESOURCES, \
+		struct drm_exynos_ioctl_ipp_get_res)
+#define DRM_IOCTL_EXYNOS_IPP_GET_CAPS		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_GET_CAPS, struct drm_exynos_ioctl_ipp_get_caps)
+#define DRM_IOCTL_EXYNOS_IPP_GET_LIMITS		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_GET_LIMITS, \
+		struct drm_exynos_ioctl_ipp_get_limits)
+#define DRM_IOCTL_EXYNOS_IPP_COMMIT		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_COMMIT, struct drm_exynos_ioctl_ipp_commit)
+
 /* EXYNOS specific events */
 #define DRM_EXYNOS_G2D_EVENT		0x80000000
+#define DRM_EXYNOS_IPP_EVENT		0x80000002
 
 struct drm_exynos_g2d_event {
 	struct drm_event	base;
@@ -177,6 +407,16 @@ struct drm_exynos_g2d_event {
 	__u32			reserved;
 };
 
+struct drm_exynos_ipp_event {
+	struct drm_event	base;
+	__u64			user_data;
+	__u32			tv_sec;
+	__u32			tv_usec;
+	__u32			ipp_id;
+	__u32			sequence;
+	__u64			reserved;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index d954f8c33321..c4df3c3668b3 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -32,143 +32,615 @@ extern "C" {
 #define DRM_TEGRA_GEM_CREATE_TILED     (1 << 0)
 #define DRM_TEGRA_GEM_CREATE_BOTTOM_UP (1 << 1)
 
+/**
+ * struct drm_tegra_gem_create - parameters for the GEM object creation IOCTL
+ */
 struct drm_tegra_gem_create {
+	/**
+	 * @size:
+	 *
+	 * The size, in bytes, of the buffer object to be created.
+	 */
 	__u64 size;
+
+	/**
+	 * @flags:
+	 *
+	 * A bitmask of flags that influence the creation of GEM objects:
+	 *
+	 * DRM_TEGRA_GEM_CREATE_TILED
+	 *   Use the 16x16 tiling format for this buffer.
+	 *
+	 * DRM_TEGRA_GEM_CREATE_BOTTOM_UP
+	 *   The buffer has a bottom-up layout.
+	 */
 	__u32 flags;
+
+	/**
+	 * @handle:
+	 *
+	 * The handle of the created GEM object. Set by the kernel upon
+	 * successful completion of the IOCTL.
+	 */
 	__u32 handle;
 };
 
+/**
+ * struct drm_tegra_gem_mmap - parameters for the GEM mmap IOCTL
+ */
 struct drm_tegra_gem_mmap {
+	/**
+	 * @handle:
+	 *
+	 * Handle of the GEM object to obtain an mmap offset for.
+	 */
 	__u32 handle;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
 	__u32 pad;
+
+	/**
+	 * @offset:
+	 *
+	 * The mmap offset for the given GEM object. Set by the kernel upon
+	 * successful completion of the IOCTL.
+	 */
 	__u64 offset;
 };
 
+/**
+ * struct drm_tegra_syncpt_read - parameters for the read syncpoint IOCTL
+ */
 struct drm_tegra_syncpt_read {
+	/**
+	 * @id:
+	 *
+	 * ID of the syncpoint to read the current value from.
+	 */
 	__u32 id;
+
+	/**
+	 * @value:
+	 *
+	 * The current syncpoint value. Set by the kernel upon successful
+	 * completion of the IOCTL.
+	 */
 	__u32 value;
 };
 
+/**
+ * struct drm_tegra_syncpt_incr - parameters for the increment syncpoint IOCTL
+ */
 struct drm_tegra_syncpt_incr {
+	/**
+	 * @id:
+	 *
+	 * ID of the syncpoint to increment.
+	 */
 	__u32 id;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
 	__u32 pad;
 };
 
+/**
+ * struct drm_tegra_syncpt_wait - parameters for the wait syncpoint IOCTL
+ */
 struct drm_tegra_syncpt_wait {
+	/**
+	 * @id:
+	 *
+	 * ID of the syncpoint to wait on.
+	 */
 	__u32 id;
+
+	/**
+	 * @thresh:
+	 *
+	 * Threshold value for which to wait.
+	 */
 	__u32 thresh;
+
+	/**
+	 * @timeout:
+	 *
+	 * Timeout, in milliseconds, to wait.
+	 */
 	__u32 timeout;
+
+	/**
+	 * @value:
+	 *
+	 * The new syncpoint value after the wait. Set by the kernel upon
+	 * successful completion of the IOCTL.
+	 */
 	__u32 value;
 };
 
 #define DRM_TEGRA_NO_TIMEOUT	(0xffffffff)
 
+/**
+ * struct drm_tegra_open_channel - parameters for the open channel IOCTL
+ */
 struct drm_tegra_open_channel {
+	/**
+	 * @client:
+	 *
+	 * The client ID for this channel.
+	 */
 	__u32 client;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
 	__u32 pad;
+
+	/**
+	 * @context:
+	 *
+	 * The application context of this channel. Set by the kernel upon
+	 * successful completion of the IOCTL. This context needs to be passed
+	 * to the DRM_TEGRA_CHANNEL_CLOSE or the DRM_TEGRA_SUBMIT IOCTLs.
+	 */
 	__u64 context;
 };
 
+/**
+ * struct drm_tegra_close_channel - parameters for the close channel IOCTL
+ */
 struct drm_tegra_close_channel {
+	/**
+	 * @context:
+	 *
+	 * The application context of this channel. This is obtained from the
+	 * DRM_TEGRA_OPEN_CHANNEL IOCTL.
+	 */
 	__u64 context;
 };
 
+/**
+ * struct drm_tegra_get_syncpt - parameters for the get syncpoint IOCTL
+ */
 struct drm_tegra_get_syncpt {
+	/**
+	 * @context:
+	 *
+	 * The application context identifying the channel for which to obtain
+	 * the syncpoint ID.
+	 */
 	__u64 context;
+
+	/**
+	 * @index:
+	 *
+	 * Index of the client syncpoint for which to obtain the ID.
+	 */
 	__u32 index;
+
+	/**
+	 * @id:
+	 *
+	 * The ID of the given syncpoint. Set by the kernel upon successful
+	 * completion of the IOCTL.
+	 */
 	__u32 id;
 };
 
+/**
+ * struct drm_tegra_get_syncpt_base - parameters for the get wait base IOCTL
+ */
 struct drm_tegra_get_syncpt_base {
+	/**
+	 * @context:
+	 *
+	 * The application context identifying for which channel to obtain the
+	 * wait base.
+	 */
 	__u64 context;
+
+	/**
+	 * @syncpt:
+	 *
+	 * ID of the syncpoint for which to obtain the wait base.
+	 */
 	__u32 syncpt;
+
+	/**
+	 * @id:
+	 *
+	 * The ID of the wait base corresponding to the client syncpoint. Set
+	 * by the kernel upon successful completion of the IOCTL.
+	 */
 	__u32 id;
 };
 
+/**
+ * struct drm_tegra_syncpt - syncpoint increment operation
+ */
 struct drm_tegra_syncpt {
+	/**
+	 * @id:
+	 *
+	 * ID of the syncpoint to operate on.
+	 */
 	__u32 id;
+
+	/**
+	 * @incrs:
+	 *
+	 * Number of increments to perform for the syncpoint.
+	 */
 	__u32 incrs;
 };
 
+/**
+ * struct drm_tegra_cmdbuf - structure describing a command buffer
+ */
 struct drm_tegra_cmdbuf {
+	/**
+	 * @handle:
+	 *
+	 * Handle to a GEM object containing the command buffer.
+	 */
 	__u32 handle;
+
+	/**
+	 * @offset:
+	 *
+	 * Offset, in bytes, into the GEM object identified by @handle at
+	 * which the command buffer starts.
+	 */
 	__u32 offset;
+
+	/**
+	 * @words:
+	 *
+	 * Number of 32-bit words in this command buffer.
+	 */
 	__u32 words;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
 	__u32 pad;
 };
 
+/**
+ * struct drm_tegra_reloc - GEM object relocation structure
+ */
 struct drm_tegra_reloc {
 	struct {
+		/**
+		 * @cmdbuf.handle:
+		 *
+		 * Handle to the GEM object containing the command buffer for
+		 * which to perform this GEM object relocation.
+		 */
 		__u32 handle;
+
+		/**
+		 * @cmdbuf.offset:
+		 *
+		 * Offset, in bytes, into the command buffer at which to
+		 * insert the relocated address.
+		 */
 		__u32 offset;
 	} cmdbuf;
 	struct {
+		/**
+		 * @target.handle:
+		 *
+		 * Handle to the GEM object to be relocated.
+		 */
 		__u32 handle;
+
+		/**
+		 * @target.offset:
+		 *
+		 * Offset, in bytes, into the target GEM object at which the
+		 * relocated data starts.
+		 */
 		__u32 offset;
 	} target;
+
+	/**
+	 * @shift:
+	 *
+	 * The number of bits by which to shift relocated addresses.
+	 */
 	__u32 shift;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
 	__u32 pad;
 };
 
+/**
+ * struct drm_tegra_waitchk - wait check structure
+ */
 struct drm_tegra_waitchk {
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object containing a command stream on which to
+	 * perform the wait check.
+	 */
 	__u32 handle;
+
+	/**
+	 * @offset:
+	 *
+	 * Offset, in bytes, of the location in the command stream to perform
+	 * the wait check on.
+	 */
 	__u32 offset;
+
+	/**
+	 * @syncpt:
+	 *
+	 * ID of the syncpoint to wait check.
+	 */
 	__u32 syncpt;
+
+	/**
+	 * @thresh:
+	 *
+	 * Threshold value for which to check.
+	 */
 	__u32 thresh;
 };
 
+/**
+ * struct drm_tegra_submit - job submission structure
+ */
 struct drm_tegra_submit {
+	/**
+	 * @context:
+	 *
+	 * The application context identifying the channel to use for the
+	 * execution of this job.
+	 */
 	__u64 context;
+
+	/**
+	 * @num_syncpts:
+	 *
+	 * The number of syncpoints operated on by this job. This defines the
+	 * length of the array pointed to by @syncpts.
+	 */
 	__u32 num_syncpts;
+
+	/**
+	 * @num_cmdbufs:
+	 *
+	 * The number of command buffers to execute as part of this job. This
+	 * defines the length of the array pointed to by @cmdbufs.
+	 */
 	__u32 num_cmdbufs;
+
+	/**
+	 * @num_relocs:
+	 *
+	 * The number of relocations to perform before executing this job.
+	 * This defines the length of the array pointed to by @relocs.
+	 */
 	__u32 num_relocs;
+
+	/**
+	 * @num_waitchks:
+	 *
+	 * The number of wait checks to perform as part of this job. This
+	 * defines the length of the array pointed to by @waitchks.
+	 */
 	__u32 num_waitchks;
+
+	/**
+	 * @waitchk_mask:
+	 *
+	 * Bitmask of valid wait checks.
+	 */
 	__u32 waitchk_mask;
+
+	/**
+	 * @timeout:
+	 *
+	 * Timeout, in milliseconds, before this job is cancelled.
+	 */
 	__u32 timeout;
+
+	/**
+	 * @syncpts:
+	 *
+	 * A pointer to an array of &struct drm_tegra_syncpt structures that
+	 * specify the syncpoint operations performed as part of this job.
+	 * The number of elements in the array must be equal to the value
+	 * given by @num_syncpts.
+	 */
 	__u64 syncpts;
+
+	/**
+	 * @cmdbufs:
+	 *
+	 * A pointer to an array of &struct drm_tegra_cmdbuf structures that
+	 * define the command buffers to execute as part of this job. The
+	 * number of elements in the array must be equal to the value given
+	 * by @num_syncpts.
+	 */
 	__u64 cmdbufs;
+
+	/**
+	 * @relocs:
+	 *
+	 * A pointer to an array of &struct drm_tegra_reloc structures that
+	 * specify the relocations that need to be performed before executing
+	 * this job. The number of elements in the array must be equal to the
+	 * value given by @num_relocs.
+	 */
 	__u64 relocs;
+
+	/**
+	 * @waitchks:
+	 *
+	 * A pointer to an array of &struct drm_tegra_waitchk structures that
+	 * specify the wait checks to be performed while executing this job.
+	 * The number of elements in the array must be equal to the value
+	 * given by @num_waitchks.
+	 */
 	__u64 waitchks;
-	__u32 fence;		/* Return value */
 
-	__u32 reserved[5];	/* future expansion */
+	/**
+	 * @fence:
+	 *
+	 * The threshold of the syncpoint associated with this job after it
+	 * has been completed. Set by the kernel upon successful completion of
+	 * the IOCTL. This can be used with the DRM_TEGRA_SYNCPT_WAIT IOCTL to
+	 * wait for this job to be finished.
+	 */
+	__u32 fence;
+
+	/**
+	 * @reserved:
+	 *
+	 * This field is reserved for future use. Must be 0.
+	 */
+	__u32 reserved[5];
 };
 
 #define DRM_TEGRA_GEM_TILING_MODE_PITCH 0
 #define DRM_TEGRA_GEM_TILING_MODE_TILED 1
 #define DRM_TEGRA_GEM_TILING_MODE_BLOCK 2
 
+/**
+ * struct drm_tegra_gem_set_tiling - parameters for the set tiling IOCTL
+ */
 struct drm_tegra_gem_set_tiling {
-	/* input */
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object for which to set the tiling parameters.
+	 */
 	__u32 handle;
+
+	/**
+	 * @mode:
+	 *
+	 * The tiling mode to set. Must be one of:
+	 *
+	 * DRM_TEGRA_GEM_TILING_MODE_PITCH
+	 *   pitch linear format
+	 *
+	 * DRM_TEGRA_GEM_TILING_MODE_TILED
+	 *   16x16 tiling format
+	 *
+	 * DRM_TEGRA_GEM_TILING_MODE_BLOCK
+	 *   16Bx2 tiling format
+	 */
 	__u32 mode;
+
+	/**
+	 * @value:
+	 *
+	 * The value to set for the tiling mode parameter.
+	 */
 	__u32 value;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
 	__u32 pad;
 };
 
+/**
+ * struct drm_tegra_gem_get_tiling - parameters for the get tiling IOCTL
+ */
 struct drm_tegra_gem_get_tiling {
-	/* input */
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object for which to query the tiling parameters.
+	 */
 	__u32 handle;
-	/* output */
+
+	/**
+	 * @mode:
+	 *
+	 * The tiling mode currently associated with the GEM object. Set by
+	 * the kernel upon successful completion of the IOCTL.
+	 */
 	__u32 mode;
+
+	/**
+	 * @value:
+	 *
+	 * The tiling mode parameter currently associated with the GEM object.
+	 * Set by the kernel upon successful completion of the IOCTL.
+	 */
 	__u32 value;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
 	__u32 pad;
 };
 
 #define DRM_TEGRA_GEM_BOTTOM_UP		(1 << 0)
 #define DRM_TEGRA_GEM_FLAGS		(DRM_TEGRA_GEM_BOTTOM_UP)
 
+/**
+ * struct drm_tegra_gem_set_flags - parameters for the set flags IOCTL
+ */
 struct drm_tegra_gem_set_flags {
-	/* input */
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object for which to set the flags.
+	 */
 	__u32 handle;
-	/* output */
+
+	/**
+	 * @flags:
+	 *
+	 * The flags to set for the GEM object.
+	 */
 	__u32 flags;
 };
 
+/**
+ * struct drm_tegra_gem_get_flags - parameters for the get flags IOCTL
+ */
 struct drm_tegra_gem_get_flags {
-	/* input */
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object for which to query the flags.
+	 */
 	__u32 handle;
-	/* output */
+
+	/**
+	 * @flags:
+	 *
+	 * The flags currently associated with the GEM object. Set by the
+	 * kernel upon successful completion of the IOCTL.
+	 */
 	__u32 flags;
 };
 
@@ -193,7 +665,7 @@ struct drm_tegra_gem_get_flags {
 #define DRM_IOCTL_TEGRA_SYNCPT_INCR DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_SYNCPT_INCR, struct drm_tegra_syncpt_incr)
 #define DRM_IOCTL_TEGRA_SYNCPT_WAIT DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_SYNCPT_WAIT, struct drm_tegra_syncpt_wait)
 #define DRM_IOCTL_TEGRA_OPEN_CHANNEL DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_OPEN_CHANNEL, struct drm_tegra_open_channel)
-#define DRM_IOCTL_TEGRA_CLOSE_CHANNEL DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_CLOSE_CHANNEL, struct drm_tegra_open_channel)
+#define DRM_IOCTL_TEGRA_CLOSE_CHANNEL DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_CLOSE_CHANNEL, struct drm_tegra_close_channel)
 #define DRM_IOCTL_TEGRA_GET_SYNCPT DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GET_SYNCPT, struct drm_tegra_get_syncpt)
 #define DRM_IOCTL_TEGRA_SUBMIT DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_SUBMIT, struct drm_tegra_submit)
 #define DRM_IOCTL_TEGRA_GET_SYNCPT_BASE DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GET_SYNCPT_BASE, struct drm_tegra_get_syncpt_base)
diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
new file mode 100644
index 000000000000..7b6627783608
--- /dev/null
+++ b/include/uapi/drm/v3d_drm.h
@@ -0,0 +1,194 @@
+/*
+ * Copyright © 2014-2018 Broadcom
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _V3D_DRM_H_
+#define _V3D_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_V3D_SUBMIT_CL                         0x00
+#define DRM_V3D_WAIT_BO                           0x01
+#define DRM_V3D_CREATE_BO                         0x02
+#define DRM_V3D_MMAP_BO                           0x03
+#define DRM_V3D_GET_PARAM                         0x04
+#define DRM_V3D_GET_BO_OFFSET                     0x05
+
+#define DRM_IOCTL_V3D_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl)
+#define DRM_IOCTL_V3D_WAIT_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo)
+#define DRM_IOCTL_V3D_CREATE_BO           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_CREATE_BO, struct drm_v3d_create_bo)
+#define DRM_IOCTL_V3D_MMAP_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_MMAP_BO, struct drm_v3d_mmap_bo)
+#define DRM_IOCTL_V3D_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_PARAM, struct drm_v3d_get_param)
+#define DRM_IOCTL_V3D_GET_BO_OFFSET       DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_BO_OFFSET, struct drm_v3d_get_bo_offset)
+
+/**
+ * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D
+ * engine.
+ *
+ * This asks the kernel to have the GPU execute an optional binner
+ * command list, and a render command list.
+ */
+struct drm_v3d_submit_cl {
+	/* Pointer to the binner command list.
+	 *
+	 * This is the first set of commands executed, which runs the
+	 * coordinate shader to determine where primitives land on the screen,
+	 * then writes out the state updates and draw calls necessary per tile
+	 * to the tile allocation BO.
+	 */
+	__u32 bcl_start;
+
+	 /** End address of the BCL (first byte after the BCL) */
+	__u32 bcl_end;
+
+	/* Offset of the render command list.
+	 *
+	 * This is the second set of commands executed, which will either
+	 * execute the tiles that have been set up by the BCL, or a fixed set
+	 * of tiles (in the case of RCL-only blits).
+	 */
+	__u32 rcl_start;
+
+	 /** End address of the RCL (first byte after the RCL) */
+	__u32 rcl_end;
+
+	/** An optional sync object to wait on before starting the BCL. */
+	__u32 in_sync_bcl;
+	/** An optional sync object to wait on before starting the RCL. */
+	__u32 in_sync_rcl;
+	/** An optional sync object to place the completion fence in. */
+	__u32 out_sync;
+
+	/* Offset of the tile alloc memory
+	 *
+	 * This is optional on V3D 3.3 (where the CL can set the value) but
+	 * required on V3D 4.1.
+	 */
+	__u32 qma;
+
+	/** Size of the tile alloc memory. */
+	__u32 qms;
+
+	/** Offset of the tile state data array. */
+	__u32 qts;
+
+	/* Pointer to a u32 array of the BOs that are referenced by the job.
+	 */
+	__u64 bo_handles;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	/* Pad, must be zero-filled. */
+	__u32 pad;
+};
+
+/**
+ * struct drm_v3d_wait_bo - ioctl argument for waiting for
+ * completion of the last DRM_V3D_SUBMIT_CL on a BO.
+ *
+ * This is useful for cases where multiple processes might be
+ * rendering to a BO and you want to wait for all rendering to be
+ * completed.
+ */
+struct drm_v3d_wait_bo {
+	__u32 handle;
+	__u32 pad;
+	__u64 timeout_ns;
+};
+
+/**
+ * struct drm_v3d_create_bo - ioctl argument for creating V3D BOs.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_v3d_create_bo {
+	__u32 size;
+	__u32 flags;
+	/** Returned GEM handle for the BO. */
+	__u32 handle;
+	/**
+	 * Returned offset for the BO in the V3D address space.  This offset
+	 * is private to the DRM fd and is valid for the lifetime of the GEM
+	 * handle.
+	 *
+	 * This offset value will always be nonzero, since various HW
+	 * units treat 0 specially.
+	 */
+	__u32 offset;
+};
+
+/**
+ * struct drm_v3d_mmap_bo - ioctl argument for mapping V3D BOs.
+ *
+ * This doesn't actually perform an mmap.  Instead, it returns the
+ * offset you need to use in an mmap on the DRM device node.  This
+ * means that tools like valgrind end up knowing about the mapped
+ * memory.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_v3d_mmap_bo {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 flags;
+	/** offset into the drm node to use for subsequent mmap call. */
+	__u64 offset;
+};
+
+enum drm_v3d_param {
+	DRM_V3D_PARAM_V3D_UIFCFG,
+	DRM_V3D_PARAM_V3D_HUB_IDENT1,
+	DRM_V3D_PARAM_V3D_HUB_IDENT2,
+	DRM_V3D_PARAM_V3D_HUB_IDENT3,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT0,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT1,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT2,
+};
+
+struct drm_v3d_get_param {
+	__u32 param;
+	__u32 pad;
+	__u64 value;
+};
+
+/**
+ * Returns the offset for the BO in the V3D address space for this DRM fd.
+ * This is the same value returned by drm_v3d_create_bo, if that was called
+ * from this DRM fd.
+ */
+struct drm_v3d_get_bo_offset {
+	__u32 handle;
+	__u32 offset;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _V3D_DRM_H_ */
diff --git a/include/uapi/drm/vc4_drm.h b/include/uapi/drm/vc4_drm.h
index b95a0e11cb07..2cac6277a1d7 100644
--- a/include/uapi/drm/vc4_drm.h
+++ b/include/uapi/drm/vc4_drm.h
@@ -183,10 +183,17 @@ struct drm_vc4_submit_cl {
 	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
 	__u32 perfmonid;
 
-	/* Unused field to align this struct on 64 bits. Must be set to 0.
-	 * If one ever needs to add an u32 field to this struct, this field
-	 * can be used.
+	/* Syncobj handle to wait on. If set, processing of this render job
+	 * will not start until the syncobj is signaled. 0 means ignore.
 	 */
+	__u32 in_sync;
+
+	/* Syncobj handle to export fence to. If set, the fence in the syncobj
+	 * will be replaced with a fence that signals upon completion of this
+	 * render job. 0 means ignore.
+	 */
+	__u32 out_sync;
+
 	__u32 pad2;
 };
 
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index a04adbc70ddf..ed0185945bb2 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -29,6 +29,7 @@
 
 #include <linux/types.h>
 #include <linux/fs.h>
+#include <linux/signal.h>
 #include <asm/byteorder.h>
 
 typedef __kernel_ulong_t aio_context_t;
@@ -38,10 +39,8 @@ enum {
 	IOCB_CMD_PWRITE = 1,
 	IOCB_CMD_FSYNC = 2,
 	IOCB_CMD_FDSYNC = 3,
-	/* These two are experimental.
-	 * IOCB_CMD_PREADX = 4,
-	 * IOCB_CMD_POLL = 5,
-	 */
+	/* 4 was the experimental IOCB_CMD_PREADX */
+	IOCB_CMD_POLL = 5,
 	IOCB_CMD_NOOP = 6,
 	IOCB_CMD_PREADV = 7,
 	IOCB_CMD_PWRITEV = 8,
@@ -108,5 +107,10 @@ struct iocb {
 #undef IFBIG
 #undef IFLITTLE
 
+struct __aio_sigset {
+	sigset_t __user	*sigmask;
+	size_t		sigsetsize;
+};
+
 #endif /* __LINUX__AIO_ABI_H */
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c5ec89732a8d..8c317737ba3f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1017,6 +1017,7 @@ struct bpf_prog_info {
 	__aligned_u64 map_ids;
 	char name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
+	__u32 :32;
 	__u64 netns_dev;
 	__u64 netns_ino;
 } __attribute__((aligned(8)));
@@ -1030,6 +1031,7 @@ struct bpf_map_info {
 	__u32 map_flags;
 	char  name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
+	__u32 :32;
 	__u64 netns_dev;
 	__u64 netns_ino;
 } __attribute__((aligned(8)));
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index c8d99b9ca550..5ca1d21fc4a7 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -422,6 +422,21 @@ struct btrfs_ioctl_ino_lookup_args {
 	char name[BTRFS_INO_LOOKUP_PATH_MAX];
 };
 
+#define BTRFS_INO_LOOKUP_USER_PATH_MAX (4080 - BTRFS_VOL_NAME_MAX - 1)
+struct btrfs_ioctl_ino_lookup_user_args {
+	/* in, inode number containing the subvolume of 'subvolid' */
+	__u64 dirid;
+	/* in */
+	__u64 treeid;
+	/* out, name of the subvolume of 'treeid' */
+	char name[BTRFS_VOL_NAME_MAX + 1];
+	/*
+	 * out, constructed path from the directory with which the ioctl is
+	 * called to dirid
+	 */
+	char path[BTRFS_INO_LOOKUP_USER_PATH_MAX];
+};
+
 /* Search criteria for the btrfs SEARCH ioctl family. */
 struct btrfs_ioctl_search_key {
 	/*
@@ -725,6 +740,82 @@ struct btrfs_ioctl_send_args {
 	__u64 reserved[4];		/* in */
 };
 
+/*
+ * Information about a fs tree root.
+ *
+ * All items are filled by the ioctl
+ */
+struct btrfs_ioctl_get_subvol_info_args {
+	/* Id of this subvolume */
+	__u64 treeid;
+
+	/* Name of this subvolume, used to get the real name at mount point */
+	char name[BTRFS_VOL_NAME_MAX + 1];
+
+	/*
+	 * Id of the subvolume which contains this subvolume.
+	 * Zero for top-level subvolume or a deleted subvolume.
+	 */
+	__u64 parent_id;
+
+	/*
+	 * Inode number of the directory which contains this subvolume.
+	 * Zero for top-level subvolume or a deleted subvolume
+	 */
+	__u64 dirid;
+
+	/* Latest transaction id of this subvolume */
+	__u64 generation;
+
+	/* Flags of this subvolume */
+	__u64 flags;
+
+	/* UUID of this subvolume */
+	__u8 uuid[BTRFS_UUID_SIZE];
+
+	/*
+	 * UUID of the subvolume of which this subvolume is a snapshot.
+	 * All zero for a non-snapshot subvolume.
+	 */
+	__u8 parent_uuid[BTRFS_UUID_SIZE];
+
+	/*
+	 * UUID of the subvolume from which this subvolume was received.
+	 * All zero for non-received subvolume.
+	 */
+	__u8 received_uuid[BTRFS_UUID_SIZE];
+
+	/* Transaction id indicating when change/create/send/receive happened */
+	__u64 ctransid;
+	__u64 otransid;
+	__u64 stransid;
+	__u64 rtransid;
+	/* Time corresponding to c/o/s/rtransid */
+	struct btrfs_ioctl_timespec ctime;
+	struct btrfs_ioctl_timespec otime;
+	struct btrfs_ioctl_timespec stime;
+	struct btrfs_ioctl_timespec rtime;
+
+	/* Must be zero */
+	__u64 reserved[8];
+};
+
+#define BTRFS_MAX_ROOTREF_BUFFER_NUM 255
+struct btrfs_ioctl_get_subvol_rootref_args {
+		/* in/out, minimum id of rootref's treeid to be searched */
+		__u64 min_treeid;
+
+		/* out */
+		struct {
+			__u64 treeid;
+			__u64 dirid;
+		} rootref[BTRFS_MAX_ROOTREF_BUFFER_NUM];
+
+		/* out, number of found items */
+		__u8 num_items;
+		__u8 align[7];
+};
+
 /* Error codes as returned by the kernel */
 enum btrfs_err_code {
 	BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET = 1,
@@ -843,5 +934,11 @@ enum btrfs_err_code {
 				   struct btrfs_ioctl_vol_args_v2)
 #define BTRFS_IOC_LOGICAL_INO_V2 _IOWR(BTRFS_IOCTL_MAGIC, 59, \
 					struct btrfs_ioctl_logical_ino_args)
+#define BTRFS_IOC_GET_SUBVOL_INFO _IOR(BTRFS_IOCTL_MAGIC, 60, \
+				struct btrfs_ioctl_get_subvol_info_args)
+#define BTRFS_IOC_GET_SUBVOL_ROOTREF _IOWR(BTRFS_IOCTL_MAGIC, 61, \
+				struct btrfs_ioctl_get_subvol_rootref_args)
+#define BTRFS_IOC_INO_LOOKUP_USER _IOWR(BTRFS_IOCTL_MAGIC, 62, \
+				struct btrfs_ioctl_ino_lookup_user_args)
 
 #endif /* _UAPI_LINUX_BTRFS_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index d2a8313fabd7..73e01918f996 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -242,6 +242,8 @@ struct fsxattr {
 #define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
 #define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
 
+#define FSLABEL_MAX 256	/* Max chars for the interface; each fs may differ */
+
 #define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
 #define	FS_IOC_GETVERSION		_IOR('v', 1, long)
@@ -251,8 +253,10 @@ struct fsxattr {
 #define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
 #define FS_IOC32_GETVERSION		_IOR('v', 1, int)
 #define FS_IOC32_SETVERSION		_IOW('v', 2, int)
-#define FS_IOC_FSGETXATTR		_IOR ('X', 31, struct fsxattr)
-#define FS_IOC_FSSETXATTR		_IOW ('X', 32, struct fsxattr)
+#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
 
 /*
  * File system encryption support
@@ -275,6 +279,8 @@ struct fsxattr {
 #define FS_ENCRYPTION_MODE_AES_256_CTS		4
 #define FS_ENCRYPTION_MODE_AES_128_CBC		5
 #define FS_ENCRYPTION_MODE_AES_128_CTS		6
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8
 
 struct fscrypt_policy {
 	__u8 version;
diff --git a/include/uapi/linux/if_infiniband.h b/include/uapi/linux/if_infiniband.h
index 050b92dcf8cf..0fc33bf30e45 100644
--- a/include/uapi/linux/if_infiniband.h
+++ b/include/uapi/linux/if_infiniband.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
 /*
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 1065006c9bf5..b02c41e53d56 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -676,6 +676,13 @@ struct kvm_ioeventfd {
 	__u8  pad[36];
 };
 
+#define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
+                                              KVM_X86_DISABLE_EXITS_HTL | \
+                                              KVM_X86_DISABLE_EXITS_PAUSE)
+
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
 	/* in */
diff --git a/include/uapi/linux/netfilter/nf_conntrack_tcp.h b/include/uapi/linux/netfilter/nf_conntrack_tcp.h
index 74b91151d494..bcba72def817 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_tcp.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_tcp.h
@@ -46,6 +46,9 @@ enum tcp_conntrack {
 /* Marks possibility for expected RFC5961 challenge ACK */
 #define IP_CT_EXP_CHALLENGE_ACK 		0x40
 
+/* Simultaneous open initialized */
+#define IP_CT_TCP_SIMULTANEOUS_OPEN		0x80
+
 struct nf_ct_tcp_flags {
 	__u8 flags;
 	__u8 mask;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 15daf5e2638d..271b93783d28 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2698,6 +2698,8 @@ enum nl80211_attrs {
 #define NL80211_ATTR_KEYS NL80211_ATTR_KEYS
 #define NL80211_ATTR_FEATURE_FLAGS NL80211_ATTR_FEATURE_FLAGS
 
+#define NL80211_WIPHY_NAME_MAXLEN		64
+
 #define NL80211_MAX_SUPP_RATES			32
 #define NL80211_MAX_SUPP_HT_RATES		77
 #define NL80211_MAX_SUPP_REG_RULES		64
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 912b85b52344..b8e288a1f740 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -650,11 +650,23 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ *   PERF_RECORD_MISC_EXACT_IP           - PERF_RECORD_SAMPLE of precise events
+ *   PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ *   Indicates that the content of PERF_SAMPLE_IP points to
+ *   the actual instruction that triggered the event. See also
+ *   perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ *   Indicates that thread was preempted in TASK_RUNNING state.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT	(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */
diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h
index b19a9c249b15..784c2e3e572e 100644
--- a/include/uapi/linux/ppp-ioctl.h
+++ b/include/uapi/linux/ppp-ioctl.h
@@ -106,7 +106,7 @@ struct pppol2tp_ioc_stats {
 #define PPPIOCGIDLE	_IOR('t', 63, struct ppp_idle) /* get idle time */
 #define PPPIOCNEWUNIT	_IOWR('t', 62, int)	/* create new ppp unit */
 #define PPPIOCATTACH	_IOW('t', 61, int)	/* attach to ppp unit */
-#define PPPIOCDETACH	_IOW('t', 60, int)	/* detach from ppp unit/chan */
+#define PPPIOCDETACH	_IOW('t', 60, int)	/* obsolete, do not use */
 #define PPPIOCSMRRU	_IOW('t', 59, int)	/* set multilink MRU */
 #define PPPIOCCONNECT	_IOW('t', 58, int)	/* connect channel to unit */
 #define PPPIOCDISCONN	_IO('t', 57)		/* disconnect channel */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index af5f8c2df87a..db9f15f5db04 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -207,4 +207,16 @@ struct prctl_mm_map {
 # define PR_SVE_VL_LEN_MASK		0xffff
 # define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
 
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL		52
+#define PR_SET_SPECULATION_CTRL		53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS		0
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED		0
+# define PR_SPEC_PRCTL			(1UL << 0)
+# define PR_SPEC_ENABLE			(1UL << 1)
+# define PR_SPEC_DISABLE		(1UL << 2)
+# define PR_SPEC_FORCE_DISABLE		(1UL << 3)
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h
index 9008f31c7eb6..ac8c60bcc83b 100644
--- a/include/uapi/linux/psp-sev.h
+++ b/include/uapi/linux/psp-sev.h
@@ -30,6 +30,7 @@ enum {
 	SEV_PDH_GEN,
 	SEV_PDH_CERT_EXPORT,
 	SEV_PEK_CERT_IMPORT,
+	SEV_GET_ID,
 
 	SEV_MAX,
 };
@@ -124,6 +125,17 @@ struct sev_user_data_pdh_cert_export {
 } __packed;
 
 /**
+ * struct sev_user_data_get_id - GET_ID command parameters
+ *
+ * @socket1: Buffer to pass unique ID of first socket
+ * @socket2: Buffer to pass unique ID of second socket
+ */
+struct sev_user_data_get_id {
+	__u8 socket1[64];			/* Out */
+	__u8 socket2[64];			/* Out */
+} __packed;
+
+/**
  * struct sev_issue_cmd - SEV ioctl parameters
  *
  * @cmd: SEV commands to execute
diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h
index c34f4490d025..26ee91300e3e 100644
--- a/include/uapi/linux/random.h
+++ b/include/uapi/linux/random.h
@@ -35,6 +35,9 @@
 /* Clear the entropy pool and associated counters.  (Superuser only.) */
 #define RNDCLEARPOOL	_IO( 'R', 0x06 )
 
+/* Reseed CRNG.  (Superuser only.) */
+#define RNDRESEEDCRNG	_IO( 'R', 0x07 )
+
 struct rand_pool_info {
 	int	entropy_count;
 	int	buf_size;
diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h
index a66b213de3d7..20c6bd0b0007 100644
--- a/include/uapi/linux/rds.h
+++ b/include/uapi/linux/rds.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2008 Oracle.  All rights reserved.
  *
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 2a0bd9dd104d..9efc0e73d50b 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -17,8 +17,9 @@
 #define SECCOMP_GET_ACTION_AVAIL	2
 
 /* Valid flags for SECCOMP_SET_MODE_FILTER */
-#define SECCOMP_FILTER_FLAG_TSYNC	1
-#define SECCOMP_FILTER_FLAG_LOG		2
+#define SECCOMP_FILTER_FLAG_TSYNC	(1UL << 0)
+#define SECCOMP_FILTER_FLAG_LOG		(1UL << 1)
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW	(1UL << 2)
 
 /*
  * All BPF programs must return a 32-bit value.
diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h
index 6f0da42fc5ef..83429a05b698 100644
--- a/include/uapi/linux/signalfd.h
+++ b/include/uapi/linux/signalfd.h
@@ -35,6 +35,10 @@ struct signalfd_siginfo {
 	__u64 ssi_stime;
 	__u64 ssi_addr;
 	__u16 ssi_addr_lsb;
+	__u16 __pad2;
+	__s32 ssi_syscall;
+	__u64 ssi_call_addr;
+	__u32 ssi_arch;
 
 	/*
 	 * Pad strcture to 128 bytes. Remember to update the
@@ -45,7 +49,7 @@ struct signalfd_siginfo {
 	 * comes out of a read(2) and we really don't want to have
 	 * a compat on read(2).
 	 */
-	__u8 __pad[46];
+	__u8 __pad[28];
 };
 
 
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 0f272818a4d2..6b58371b1f0d 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -780,24 +780,6 @@ enum {
 	NET_BRIDGE_NF_FILTER_PPPOE_TAGGED = 5,
 };
 
-/* proc/sys/net/irda */
-enum {
-	NET_IRDA_DISCOVERY=1,
-	NET_IRDA_DEVNAME=2,
-	NET_IRDA_DEBUG=3,
-	NET_IRDA_FAST_POLL=4,
-	NET_IRDA_DISCOVERY_SLOTS=5,
-	NET_IRDA_DISCOVERY_TIMEOUT=6,
-	NET_IRDA_SLOT_TIMEOUT=7,
-	NET_IRDA_MAX_BAUD_RATE=8,
-	NET_IRDA_MIN_TX_TURN_TIME=9,
-	NET_IRDA_MAX_TX_DATA_SIZE=10,
-	NET_IRDA_MAX_TX_WINDOW=11,
-	NET_IRDA_MAX_NOREPLY_TIME=12,
-	NET_IRDA_WARN_NOREPLY_TIME=13,
-	NET_IRDA_LAP_KEEPALIVE_TIME=14,
-};
-
 
 /* CTL_FS names: */
 enum
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index 16a296612ba4..fcf936656493 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -42,6 +42,13 @@ struct itimerval {
 	struct timeval it_value;	/* current value */
 };
 
+#ifndef __kernel_timespec
+struct __kernel_timespec {
+	__kernel_time64_t       tv_sec;                 /* seconds */
+	long long               tv_nsec;                /* nanoseconds */
+};
+#endif
+
 /*
  * legacy timeval structure, only embedded in structures that
  * traditionally used 'timeval' to pass time intervals (not absolute
@@ -73,7 +80,6 @@ struct __kernel_old_timeval {
  */
 #define CLOCK_SGI_CYCLE			10
 #define CLOCK_TAI			11
-#define CLOCK_MONOTONIC_ACTIVE		12
 
 #define MAX_CLOCKS			16
 #define CLOCKS_MASK			(CLOCK_REALTIME | CLOCK_MONOTONIC)
diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h
index c6633e97eca4..ff02287495ac 100644
--- a/include/uapi/linux/tls.h
+++ b/include/uapi/linux/tls.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
  *
diff --git a/include/uapi/linux/tty_flags.h b/include/uapi/linux/tty_flags.h
index 6ac609a00dea..900a32e63424 100644
--- a/include/uapi/linux/tty_flags.h
+++ b/include/uapi/linux/tty_flags.h
@@ -13,7 +13,7 @@
  */
 #define ASYNCB_HUP_NOTIFY	 0 /* Notify getty on hangups and closes
 				    * on the callout port */
-#define ASYNCB_FOURPORT		 1 /* Set OU1, OUT2 per AST Fourport settings */
+#define ASYNCB_FOURPORT		 1 /* Set OUT1, OUT2 per AST Fourport settings */
 #define ASYNCB_SAK		 2 /* Secure Attention Key (Orange book) */
 #define ASYNCB_SPLIT_TERMIOS	 3 /* [x] Separate termios for dialin/callout */
 #define ASYNCB_SPD_HI		 4 /* Use 57600 instead of 38400 bps */
diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h
index cd4f0b897a48..2fce8b6876e9 100644
--- a/include/uapi/linux/types.h
+++ b/include/uapi/linux/types.h
@@ -49,11 +49,7 @@ typedef __u32 __bitwise __wsum;
 #define __aligned_be64 __be64 __attribute__((aligned(8)))
 #define __aligned_le64 __le64 __attribute__((aligned(8)))
 
-#ifdef __CHECK_POLL
 typedef unsigned __bitwise __poll_t;
-#else
-typedef unsigned __poll_t;
-#endif
 
 #endif /*  __ASSEMBLY__ */
 #endif /* _UAPI_LINUX_TYPES_H */
diff --git a/include/uapi/linux/usb/audio.h b/include/uapi/linux/usb/audio.h
index 3a78e7145689..13d98e6e0db1 100644
--- a/include/uapi/linux/usb/audio.h
+++ b/include/uapi/linux/usb/audio.h
@@ -285,9 +285,22 @@ static inline __u8 uac_mixer_unit_iChannelNames(struct uac_mixer_unit_descriptor
 static inline __u8 *uac_mixer_unit_bmControls(struct uac_mixer_unit_descriptor *desc,
 					      int protocol)
 {
-	return (protocol == UAC_VERSION_1) ?
-		&desc->baSourceID[desc->bNrInPins + 4] :
-		&desc->baSourceID[desc->bNrInPins + 6];
+	switch (protocol) {
+	case UAC_VERSION_1:
+		return &desc->baSourceID[desc->bNrInPins + 4];
+	case UAC_VERSION_2:
+		return &desc->baSourceID[desc->bNrInPins + 6];
+	case UAC_VERSION_3:
+		return &desc->baSourceID[desc->bNrInPins + 2];
+	default:
+		return NULL;
+	}
+}
+
+static inline __u16 uac3_mixer_unit_wClusterDescrID(struct uac_mixer_unit_descriptor *desc)
+{
+	return (desc->baSourceID[desc->bNrInPins + 1] << 8) |
+		desc->baSourceID[desc->bNrInPins];
 }
 
 static inline __u8 uac_mixer_unit_iMixer(struct uac_mixer_unit_descriptor *desc)
diff --git a/include/uapi/linux/usb/ch11.h b/include/uapi/linux/usb/ch11.h
index 29c120c88747..fb0cd24c392c 100644
--- a/include/uapi/linux/usb/ch11.h
+++ b/include/uapi/linux/usb/ch11.h
@@ -197,6 +197,11 @@ struct usb_port_status {
 #define USB_EXT_PORT_STAT_RX_LANES	0x00000f00
 #define USB_EXT_PORT_STAT_TX_LANES	0x0000f000
 
+#define USB_EXT_PORT_RX_LANES(p) \
+			(((p) & USB_EXT_PORT_STAT_RX_LANES) >> 8)
+#define USB_EXT_PORT_TX_LANES(p) \
+			(((p) & USB_EXT_PORT_STAT_TX_LANES) >> 12)
+
 /*
  * wHubCharacteristics (masks)
  * See USB 2.0 spec Table 11-13, offset 3
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 40297a3181ed..13b8cb563892 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -57,6 +57,21 @@ struct virtio_balloon_config {
 #define VIRTIO_BALLOON_S_HTLB_PGFAIL   9  /* Hugetlb page allocation failures */
 #define VIRTIO_BALLOON_S_NR       10
 
+#define VIRTIO_BALLOON_S_NAMES_WITH_PREFIX(VIRTIO_BALLOON_S_NAMES_prefix) { \
+	VIRTIO_BALLOON_S_NAMES_prefix "swap-in", \
+	VIRTIO_BALLOON_S_NAMES_prefix "swap-out", \
+	VIRTIO_BALLOON_S_NAMES_prefix "major-faults", \
+	VIRTIO_BALLOON_S_NAMES_prefix "minor-faults", \
+	VIRTIO_BALLOON_S_NAMES_prefix "free-memory", \
+	VIRTIO_BALLOON_S_NAMES_prefix "total-memory", \
+	VIRTIO_BALLOON_S_NAMES_prefix "available-memory", \
+	VIRTIO_BALLOON_S_NAMES_prefix "disk-caches", \
+	VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-allocations", \
+	VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-failures" \
+}
+
+#define VIRTIO_BALLOON_S_NAMES VIRTIO_BALLOON_S_NAMES_WITH_PREFIX("")
+
 /*
  * Memory statistics structure.
  * Driver fills an array of these structures and passes to device.
diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h
index 4b04ead26cd9..f43c3c6171ff 100644
--- a/include/uapi/linux/virtio_gpu.h
+++ b/include/uapi/linux/virtio_gpu.h
@@ -260,6 +260,7 @@ struct virtio_gpu_cmd_submit {
 };
 
 #define VIRTIO_GPU_CAPSET_VIRGL 1
+#define VIRTIO_GPU_CAPSET_VIRGL2 2
 
 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */
 struct virtio_gpu_get_capset_info {
diff --git a/include/uapi/rdma/cxgb3-abi.h b/include/uapi/rdma/cxgb3-abi.h
index 9acb4b7a6246..85aed672f43e 100644
--- a/include/uapi/rdma/cxgb3-abi.h
+++ b/include/uapi/rdma/cxgb3-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2006 Chelsio, Inc. All rights reserved.
  *
diff --git a/include/uapi/rdma/cxgb4-abi.h b/include/uapi/rdma/cxgb4-abi.h
index 1fefd0140c26..a159ba8dcf8f 100644
--- a/include/uapi/rdma/cxgb4-abi.h
+++ b/include/uapi/rdma/cxgb4-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2009-2010 Chelsio, Inc. All rights reserved.
  *
diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h
index 7092c8de4bd8..78613b609fa8 100644
--- a/include/uapi/rdma/hns-abi.h
+++ b/include/uapi/rdma/hns-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2016 Hisilicon Limited.
  *
diff --git a/include/uapi/rdma/ib_user_cm.h b/include/uapi/rdma/ib_user_cm.h
index 4a8f9562f7cd..e2709bb8cb18 100644
--- a/include/uapi/rdma/ib_user_cm.h
+++ b/include/uapi/rdma/ib_user_cm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2005 Topspin Communications.  All rights reserved.
  * Copyright (c) 2005 Intel Corporation.  All rights reserved.
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 04e46ea517d3..625545d862d7 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2017-2018, Mellanox Technologies inc.  All rights reserved.
  *
diff --git a/include/uapi/rdma/ib_user_mad.h b/include/uapi/rdma/ib_user_mad.h
index ef92118dad97..90c0cf228020 100644
--- a/include/uapi/rdma/ib_user_mad.h
+++ b/include/uapi/rdma/ib_user_mad.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2004 Topspin Communications.  All rights reserved.
  * Copyright (c) 2005 Voltaire, Inc. All rights reserved.
diff --git a/include/uapi/rdma/ib_user_sa.h b/include/uapi/rdma/ib_user_sa.h
index 0d2607f0cd20..435155d6e1c6 100644
--- a/include/uapi/rdma/ib_user_sa.h
+++ b/include/uapi/rdma/ib_user_sa.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2005 Intel Corporation.  All rights reserved.
  *
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 9be07394fdbe..6aeb03315b0b 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2005 Topspin Communications.  All rights reserved.
  * Copyright (c) 2005, 2006 Cisco Systems.  All rights reserved.
diff --git a/include/uapi/rdma/mlx4-abi.h b/include/uapi/rdma/mlx4-abi.h
index 04f64bc4045f..f74557528175 100644
--- a/include/uapi/rdma/mlx4-abi.h
+++ b/include/uapi/rdma/mlx4-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
  * Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved.
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index cb4a02c4a1ce..fdaf00e20649 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
  *
diff --git a/include/uapi/rdma/mthca-abi.h b/include/uapi/rdma/mthca-abi.h
index ac756cd9e807..91b12e1a6f43 100644
--- a/include/uapi/rdma/mthca-abi.h
+++ b/include/uapi/rdma/mthca-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2005 Topspin Communications.  All rights reserved.
  * Copyright (c) 2005, 2006 Cisco Systems.  All rights reserved.
diff --git a/include/uapi/rdma/nes-abi.h b/include/uapi/rdma/nes-abi.h
index 35bfd4015d07..f80495baa969 100644
--- a/include/uapi/rdma/nes-abi.h
+++ b/include/uapi/rdma/nes-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  * Copyright (c) 2005 Topspin Communications.  All rights reserved.
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
index 8ba098900e9a..24c658b3c790 100644
--- a/include/uapi/rdma/qedr-abi.h
+++ b/include/uapi/rdma/qedr-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /* QLogic qedr NIC Driver
  * Copyright (c) 2015-2016  QLogic Corporation
  *
diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h
index e1269024af47..0d1e78ebad05 100644
--- a/include/uapi/rdma/rdma_user_cm.h
+++ b/include/uapi/rdma/rdma_user_cm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2005-2006 Intel Corporation.  All rights reserved.
  *
diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h
index d223f4164a0f..d92d2721b28c 100644
--- a/include/uapi/rdma/rdma_user_ioctl.h
+++ b/include/uapi/rdma/rdma_user_ioctl.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2016 Mellanox Technologies, LTD. All rights reserved.
  *
diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h
index 1f8a9e7daea4..44ef6a3b7afc 100644
--- a/include/uapi/rdma/rdma_user_rxe.h
+++ b/include/uapi/rdma/rdma_user_rxe.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
  * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
  *
diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h
index 69c37ecbff7e..a74ca232f1fc 100644
--- a/include/uapi/sound/asoc.h
+++ b/include/uapi/sound/asoc.h
@@ -139,6 +139,15 @@
 #define SND_SOC_TPLG_DAI_FLGBIT_SYMMETRIC_CHANNELS      (1 << 1)
 #define SND_SOC_TPLG_DAI_FLGBIT_SYMMETRIC_SAMPLEBITS    (1 << 2)
 
+/* DAI clock gating */
+#define SND_SOC_TPLG_DAI_CLK_GATE_UNDEFINED	0
+#define SND_SOC_TPLG_DAI_CLK_GATE_GATED	1
+#define SND_SOC_TPLG_DAI_CLK_GATE_CONT		2
+
+/* DAI mclk_direction */
+#define SND_SOC_TPLG_MCLK_CO            0 /* for codec, mclk is output */
+#define SND_SOC_TPLG_MCLK_CI            1 /* for codec, mclk is input */
+
 /* DAI physical PCM data formats.
  * Add new formats to the end of the list.
  */
@@ -160,6 +169,18 @@
 #define SND_SOC_TPLG_LNK_FLGBIT_SYMMETRIC_SAMPLEBITS    (1 << 2)
 #define SND_SOC_TPLG_LNK_FLGBIT_VOICE_WAKEUP            (1 << 3)
 
+/* DAI topology BCLK parameter
+ * For the backwards capability, by default codec is bclk master
+ */
+#define SND_SOC_TPLG_BCLK_CM         0 /* codec is bclk master */
+#define SND_SOC_TPLG_BCLK_CS         1 /* codec is bclk slave */
+
+/* DAI topology FSYNC parameter
+ * For the backwards capability, by default codec is fsync master
+ */
+#define SND_SOC_TPLG_FSYNC_CM         0 /* codec is fsync master */
+#define SND_SOC_TPLG_FSYNC_CS         1 /* codec is fsync slave */
+
 /*
  * Block Header.
  * This header precedes all object and object arrays below.
@@ -312,12 +333,12 @@ struct snd_soc_tplg_hw_config {
 	__le32 size;            /* in bytes of this structure */
 	__le32 id;		/* unique ID - - used to match */
 	__le32 fmt;		/* SND_SOC_DAI_FORMAT_ format value */
-	__u8 clock_gated;	/* 1 if clock can be gated to save power */
+	__u8 clock_gated;	/* SND_SOC_TPLG_DAI_CLK_GATE_ value */
 	__u8 invert_bclk;	/* 1 for inverted BCLK, 0 for normal */
 	__u8 invert_fsync;	/* 1 for inverted frame clock, 0 for normal */
-	__u8 bclk_master;	/* 1 for master of BCLK, 0 for slave */
-	__u8 fsync_master;	/* 1 for master of FSYNC, 0 for slave */
-	__u8 mclk_direction;    /* 0 for input, 1 for output */
+	__u8 bclk_master;	/* SND_SOC_TPLG_BCLK_ value */
+	__u8 fsync_master;	/* SND_SOC_TPLG_FSYNC_ value */
+	__u8 mclk_direction;    /* SND_SOC_TPLG_MCLK_ value */
 	__le16 reserved;	/* for 32bit alignment */
 	__le32 mclk_rate;	/* MCLK or SYSCLK freqency in Hz */
 	__le32 bclk_rate;	/* BCLK freqency in Hz */
@@ -552,4 +573,61 @@ struct snd_soc_tplg_dai {
 	__le32 flags;           /* SND_SOC_TPLG_DAI_FLGBIT_* */
 	struct snd_soc_tplg_private priv;
 } __attribute__((packed));
+
+/*
+ * Old version of ABI structs, supported for backward compatibility.
+ */
+
+/* Manifest v4 */
+struct snd_soc_tplg_manifest_v4 {
+	__le32 size;		/* in bytes of this structure */
+	__le32 control_elems;	/* number of control elements */
+	__le32 widget_elems;	/* number of widget elements */
+	__le32 graph_elems;	/* number of graph elements */
+	__le32 pcm_elems;	/* number of PCM elements */
+	__le32 dai_link_elems;	/* number of DAI link elements */
+	struct snd_soc_tplg_private priv;
+} __packed;
+
+/* Stream Capabilities v4 */
+struct snd_soc_tplg_stream_caps_v4 {
+	__le32 size;		/* in bytes of this structure */
+	char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+	__le64 formats;	/* supported formats SNDRV_PCM_FMTBIT_* */
+	__le32 rates;		/* supported rates SNDRV_PCM_RATE_* */
+	__le32 rate_min;	/* min rate */
+	__le32 rate_max;	/* max rate */
+	__le32 channels_min;	/* min channels */
+	__le32 channels_max;	/* max channels */
+	__le32 periods_min;	/* min number of periods */
+	__le32 periods_max;	/* max number of periods */
+	__le32 period_size_min;	/* min period size bytes */
+	__le32 period_size_max;	/* max period size bytes */
+	__le32 buffer_size_min;	/* min buffer size bytes */
+	__le32 buffer_size_max;	/* max buffer size bytes */
+} __packed;
+
+/* PCM v4 */
+struct snd_soc_tplg_pcm_v4 {
+	__le32 size;		/* in bytes of this structure */
+	char pcm_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+	char dai_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+	__le32 pcm_id;		/* unique ID - used to match with DAI link */
+	__le32 dai_id;		/* unique ID - used to match */
+	__le32 playback;	/* supports playback mode */
+	__le32 capture;		/* supports capture mode */
+	__le32 compress;	/* 1 = compressed; 0 = PCM */
+	struct snd_soc_tplg_stream stream[SND_SOC_TPLG_STREAM_CONFIG_MAX]; /* for DAI link */
+	__le32 num_streams;	/* number of streams */
+	struct snd_soc_tplg_stream_caps_v4 caps[2]; /* playback and capture for DAI */
+} __packed;
+
+/* Physical link config v4 */
+struct snd_soc_tplg_link_config_v4 {
+	__le32 size;            /* in bytes of this structure */
+	__le32 id;              /* unique ID - used to match */
+	struct snd_soc_tplg_stream stream[SND_SOC_TPLG_STREAM_CONFIG_MAX]; /* supported configs playback and captrure */
+	__le32 num_streams;     /* number of streams */
+} __packed;
+
 #endif
diff --git a/sound/soc/intel/skylake/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h
index f8d1749a2e0c..f58cafa42f18 100644
--- a/sound/soc/intel/skylake/skl-tplg-interface.h
+++ b/include/uapi/sound/skl-tplg-interface.h
@@ -1,19 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * skl-tplg-interface.h - Intel DSP FW private data interface
  *
  * Copyright (C) 2015 Intel Corp
  * Author: Jeeja KP <jeeja.kp@intel.com>
  *	    Nilofer, Samreen <samreen.nilofer@intel.com>
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 
 #ifndef __HDA_TPLG_INTERFACE_H__
@@ -169,4 +160,78 @@ enum skl_tuple_type {
 	SKL_TYPE_DATA
 };
 
+/* v4 configuration data */
+
+struct skl_dfw_v4_module_pin {
+	u16 module_id;
+	u16 instance_id;
+} __packed;
+
+struct skl_dfw_v4_module_fmt {
+	u32 channels;
+	u32 freq;
+	u32 bit_depth;
+	u32 valid_bit_depth;
+	u32 ch_cfg;
+	u32 interleaving_style;
+	u32 sample_type;
+	u32 ch_map;
+} __packed;
+
+struct skl_dfw_v4_module_caps {
+	u32 set_params:2;
+	u32 rsvd:30;
+	u32 param_id;
+	u32 caps_size;
+	u32 caps[HDA_SST_CFG_MAX];
+} __packed;
+
+struct skl_dfw_v4_pipe {
+	u8 pipe_id;
+	u8 pipe_priority;
+	u16 conn_type:4;
+	u16 rsvd:4;
+	u16 memory_pages:8;
+} __packed;
+
+struct skl_dfw_v4_module {
+	char uuid[SKL_UUID_STR_SZ];
+
+	u16 module_id;
+	u16 instance_id;
+	u32 max_mcps;
+	u32 mem_pages;
+	u32 obs;
+	u32 ibs;
+	u32 vbus_id;
+
+	u32 max_in_queue:8;
+	u32 max_out_queue:8;
+	u32 time_slot:8;
+	u32 core_id:4;
+	u32 rsvd1:4;
+
+	u32 module_type:8;
+	u32 conn_type:4;
+	u32 dev_type:4;
+	u32 hw_conn_type:4;
+	u32 rsvd2:12;
+
+	u32 params_fixup:8;
+	u32 converter:8;
+	u32 input_pin_type:1;
+	u32 output_pin_type:1;
+	u32 is_dynamic_in_pin:1;
+	u32 is_dynamic_out_pin:1;
+	u32 is_loadable:1;
+	u32 rsvd3:11;
+
+	struct skl_dfw_v4_pipe pipe;
+	struct skl_dfw_v4_module_fmt in_fmt[MAX_IN_QUEUE];
+	struct skl_dfw_v4_module_fmt out_fmt[MAX_OUT_QUEUE];
+	struct skl_dfw_v4_module_pin in_pin[MAX_IN_QUEUE];
+	struct skl_dfw_v4_module_pin out_pin[MAX_OUT_QUEUE];
+	struct skl_dfw_v4_module_caps caps;
+} __packed;
+
 #endif
diff --git a/include/uapi/sound/tlv.h b/include/uapi/sound/tlv.h
index be5371f09a62..7d6d65f60a42 100644
--- a/include/uapi/sound/tlv.h
+++ b/include/uapi/sound/tlv.h
@@ -42,6 +42,10 @@
 #define SNDRV_CTL_TLVD_LENGTH(...) \
 	((unsigned int)sizeof((const unsigned int[]) { __VA_ARGS__ }))
 
+/* Accessor offsets for TLV data items */
+#define SNDRV_CTL_TLVO_TYPE		0
+#define SNDRV_CTL_TLVO_LEN		1
+
 #define SNDRV_CTL_TLVD_CONTAINER_ITEM(...) \
 	SNDRV_CTL_TLVD_ITEM(SNDRV_CTL_TLVT_CONTAINER, __VA_ARGS__)
 #define SNDRV_CTL_TLVD_DECLARE_CONTAINER(name, ...) \
@@ -61,6 +65,10 @@
 		SNDRV_CTL_TLVD_DB_SCALE_ITEM(min, step, mute) \
 	}
 
+/* Accessor offsets for min, mute and step items in dB scale type TLV */
+#define SNDRV_CTL_TLVO_DB_SCALE_MIN		2
+#define SNDRV_CTL_TLVO_DB_SCALE_MUTE_AND_STEP	3
+
 /* dB scale specified with min/max values instead of step */
 #define SNDRV_CTL_TLVD_DB_MINMAX_ITEM(min_dB, max_dB) \
 	SNDRV_CTL_TLVD_ITEM(SNDRV_CTL_TLVT_DB_MINMAX, (min_dB), (max_dB))
@@ -75,6 +83,10 @@
 		SNDRV_CTL_TLVD_DB_MINMAX_MUTE_ITEM(min_dB, max_dB) \
 	}
 
+/* Accessor offsets for min, max items in db-minmax types of TLV. */
+#define SNDRV_CTL_TLVO_DB_MINMAX_MIN	2
+#define SNDRV_CTL_TLVO_DB_MINMAX_MAX	3
+
 /* linear volume between min_dB and max_dB (.01dB unit) */
 #define SNDRV_CTL_TLVD_DB_LINEAR_ITEM(min_dB, max_dB) \
 	SNDRV_CTL_TLVD_ITEM(SNDRV_CTL_TLVT_DB_LINEAR, (min_dB), (max_dB))
@@ -83,6 +95,10 @@
 		SNDRV_CTL_TLVD_DB_LINEAR_ITEM(min_dB, max_dB) \
 	}
 
+/* Accessor offsets for min, max items in db-linear type of TLV. */
+#define SNDRV_CTL_TLVO_DB_LINEAR_MIN	2
+#define SNDRV_CTL_TLVO_DB_LINEAR_MAX	3
+
 /* dB range container:
  * Items in dB range container must be ordered by their values and by their
  * dB values. This implies that larger values must correspond with larger
diff --git a/include/xen/interface/io/sndif.h b/include/xen/interface/io/sndif.h
index 5c918276835e..78bb5d9f8d83 100644
--- a/include/xen/interface/io/sndif.h
+++ b/include/xen/interface/io/sndif.h
@@ -38,6 +38,13 @@
 
 /*
  ******************************************************************************
+ *                           Protocol version
+ ******************************************************************************
+ */
+#define XENSND_PROTOCOL_VERSION	2
+
+/*
+ ******************************************************************************
  *                  Feature and Parameter Negotiation
  ******************************************************************************
  *
@@ -106,6 +113,8 @@
  *
  * /local/domain/1/device/vsnd/0/0/0/ring-ref = "386"
  * /local/domain/1/device/vsnd/0/0/0/event-channel = "15"
+ * /local/domain/1/device/vsnd/0/0/0/evt-ring-ref = "1386"
+ * /local/domain/1/device/vsnd/0/0/0/evt-event-channel = "215"
  *
  *------------------------------ Stream 1, capture ----------------------------
  *
@@ -115,6 +124,8 @@
  *
  * /local/domain/1/device/vsnd/0/0/1/ring-ref = "384"
  * /local/domain/1/device/vsnd/0/0/1/event-channel = "13"
+ * /local/domain/1/device/vsnd/0/0/1/evt-ring-ref = "1384"
+ * /local/domain/1/device/vsnd/0/0/1/evt-event-channel = "213"
  *
  *------------------------------- PCM device 1 --------------------------------
  *
@@ -128,6 +139,8 @@
  *
  * /local/domain/1/device/vsnd/0/1/0/ring-ref = "387"
  * /local/domain/1/device/vsnd/0/1/0/event-channel = "151"
+ * /local/domain/1/device/vsnd/0/1/0/evt-ring-ref = "1387"
+ * /local/domain/1/device/vsnd/0/1/0/evt-event-channel = "351"
  *
  *------------------------------- PCM device 2 --------------------------------
  *
@@ -140,6 +153,8 @@
  *
  * /local/domain/1/device/vsnd/0/2/0/ring-ref = "389"
  * /local/domain/1/device/vsnd/0/2/0/event-channel = "152"
+ * /local/domain/1/device/vsnd/0/2/0/evt-ring-ref = "1389"
+ * /local/domain/1/device/vsnd/0/2/0/evt-event-channel = "452"
  *
  ******************************************************************************
  *                            Backend XenBus Nodes
@@ -285,6 +300,23 @@
  *      The Xen grant reference granting permission for the backend to map
  *      a sole page in a single page sized ring buffer.
  *
+ *--------------------- Stream Event Transport Parameters ---------------------
+ *
+ * This communication path is used to deliver asynchronous events from backend
+ * to frontend, set up per stream.
+ *
+ * evt-event-channel
+ *      Values:         <uint32_t>
+ *
+ *      The identifier of the Xen event channel used to signal activity
+ *      in the ring buffer.
+ *
+ * evt-ring-ref
+ *      Values:         <uint32_t>
+ *
+ *      The Xen grant reference granting permission for the backend to map
+ *      a sole page in a single page sized ring buffer.
+ *
  ******************************************************************************
  *                               STATE DIAGRAMS
  ******************************************************************************
@@ -432,6 +464,20 @@
 #define XENSND_OP_GET_VOLUME		5
 #define XENSND_OP_MUTE			6
 #define XENSND_OP_UNMUTE		7
+#define XENSND_OP_TRIGGER		8
+#define XENSND_OP_HW_PARAM_QUERY	9
+
+#define XENSND_OP_TRIGGER_START		0
+#define XENSND_OP_TRIGGER_PAUSE		1
+#define XENSND_OP_TRIGGER_STOP		2
+#define XENSND_OP_TRIGGER_RESUME	3
+
+/*
+ ******************************************************************************
+ *                                 EVENT CODES
+ ******************************************************************************
+ */
+#define XENSND_EVT_CUR_POS		0
 
 /*
  ******************************************************************************
@@ -448,6 +494,8 @@
 #define XENSND_FIELD_VCARD_LONG_NAME	"long-name"
 #define XENSND_FIELD_RING_REF		"ring-ref"
 #define XENSND_FIELD_EVT_CHNL		"event-channel"
+#define XENSND_FIELD_EVT_RING_REF	"evt-ring-ref"
+#define XENSND_FIELD_EVT_EVT_CHNL	"evt-event-channel"
 #define XENSND_FIELD_DEVICE_NAME	"name"
 #define XENSND_FIELD_TYPE		"type"
 #define XENSND_FIELD_STREAM_UNIQUE_ID	"unique-id"
@@ -526,7 +574,7 @@
  *
  *---------------------------------- Requests ---------------------------------
  *
- * All request packets have the same length (32 octets)
+ * All request packets have the same length (64 octets)
  * All request packets have common header:
  *         0                1                 2               3        octet
  * +----------------+----------------+----------------+----------------+
@@ -559,11 +607,13 @@
  * +----------------+----------------+----------------+----------------+
  * |                           gref_directory                          | 24
  * +----------------+----------------+----------------+----------------+
- * |                             reserved                              | 28
+ * |                             period_sz                             | 28
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 32
  * +----------------+----------------+----------------+----------------+
  * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
  * +----------------+----------------+----------------+----------------+
- * |                             reserved                              | 32
+ * |                             reserved                              | 64
  * +----------------+----------------+----------------+----------------+
  *
  * pcm_rate - uint32_t, stream data rate, Hz
@@ -571,6 +621,14 @@
  * pcm_channels - uint8_t, number of channels of this stream,
  *   [channels-min; channels-max]
  * buffer_sz - uint32_t, buffer size to be allocated, octets
+ * period_sz - uint32_t, event period size, octets
+ *   This is the requested value of the period at which frontend would
+ *   like to receive XENSND_EVT_CUR_POS notifications from the backend when
+ *   stream position advances during playback/capture.
+ *   It shows how many octets are expected to be played/captured before
+ *   sending such an event.
+ *   If set to 0 no XENSND_EVT_CUR_POS events are sent by the backend.
+ *
  * gref_directory - grant_ref_t, a reference to the first shared page
  *   describing shared buffer references. At least one page exists. If shared
  *   buffer size  (buffer_sz) exceeds what can be addressed by this single page,
@@ -585,6 +643,7 @@ struct xensnd_open_req {
 	uint16_t reserved;
 	uint32_t buffer_sz;
 	grant_ref_t gref_directory;
+	uint32_t period_sz;
 };
 
 /*
@@ -632,7 +691,7 @@ struct xensnd_page_directory {
  * +----------------+----------------+----------------+----------------+
  * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
  * +----------------+----------------+----------------+----------------+
- * |                             reserved                              | 32
+ * |                             reserved                              | 64
  * +----------------+----------------+----------------+----------------+
  *
  * Request read/write - used for read (for capture) or write (for playback):
@@ -650,7 +709,7 @@ struct xensnd_page_directory {
  * +----------------+----------------+----------------+----------------+
  * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
  * +----------------+----------------+----------------+----------------+
- * |                             reserved                              | 32
+ * |                             reserved                              | 64
  * +----------------+----------------+----------------+----------------+
  *
  * operation - XENSND_OP_READ for read or XENSND_OP_WRITE for write
@@ -673,9 +732,11 @@ struct xensnd_rw_req {
  * +----------------+----------------+----------------+----------------+
  * |                              length                               | 16
  * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
  * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
  * +----------------+----------------+----------------+----------------+
- * |                             reserved                              | 32
+ * |                             reserved                              | 64
  * +----------------+----------------+----------------+----------------+
  *
  * operation - XENSND_OP_SET_VOLUME for volume set
@@ -713,9 +774,11 @@ struct xensnd_rw_req {
  * +----------------+----------------+----------------+----------------+
  * |                              length                               | 16
  * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
  * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
  * +----------------+----------------+----------------+----------------+
- * |                             reserved                              | 32
+ * |                             reserved                              | 64
  * +----------------+----------------+----------------+----------------+
  *
  * operation - XENSND_OP_MUTE for mute or XENSND_OP_UNMUTE for unmute
@@ -743,32 +806,213 @@ struct xensnd_rw_req {
  *
  * The 'struct xensnd_rw_req' is also used for XENSND_OP_SET_VOLUME,
  * XENSND_OP_GET_VOLUME, XENSND_OP_MUTE, XENSND_OP_UNMUTE.
+ *
+ * Request stream running state change - trigger PCM stream running state
+ * to start, stop, pause or resume:
+ *
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |   _OP_TRIGGER  |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |      type      |                     reserved                     | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 16
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * type - uint8_t, XENSND_OP_TRIGGER_XXX value
  */
 
+struct xensnd_trigger_req {
+	uint8_t type;
+};
+
 /*
- *---------------------------------- Responses --------------------------------
+ * Request stream parameter ranges: request intervals and
+ *   masks of supported ranges for stream configuration values.
  *
- * All response packets have the same length (32 octets)
+ *   Sound device configuration for a particular stream is a limited subset
+ *   of the multidimensional configuration available on XenStore, e.g.
+ *   once the frame rate has been selected there is a limited supported range
+ *   for sample rates becomes available (which might be the same set configured
+ *   on XenStore or less). For example, selecting 96kHz sample rate may limit
+ *   number of channels available for such configuration from 4 to 2, etc.
+ *   Thus, each call to XENSND_OP_HW_PARAM_QUERY may reduce configuration
+ *   space making it possible to iteratively get the final stream configuration,
+ *   used in XENSND_OP_OPEN request.
+ *
+ *   See response format for this request.
  *
- * Response for all requests:
  *         0                1                 2               3        octet
  * +----------------+----------------+----------------+----------------+
- * |               id                |    operation   |    reserved    | 4
+ * |               id                | _HW_PARAM_QUERY|    reserved    | 4
  * +----------------+----------------+----------------+----------------+
- * |                              status                               | 8
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                     formats mask low 32-bit                       | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                     formats mask high 32-bit                      | 16
  * +----------------+----------------+----------------+----------------+
- * |                             reserved                              | 12
+ * |                              min rate                             | 20
+ * +----------------+----------------+----------------+----------------+
+ * |                              max rate                             | 24
+ * +----------------+----------------+----------------+----------------+
+ * |                            min channels                           | 28
+ * +----------------+----------------+----------------+----------------+
+ * |                            max channels                           | 32
+ * +----------------+----------------+----------------+----------------+
+ * |                         min buffer frames                         | 36
+ * +----------------+----------------+----------------+----------------+
+ * |                         max buffer frames                         | 40
+ * +----------------+----------------+----------------+----------------+
+ * |                         min period frames                         | 44
+ * +----------------+----------------+----------------+----------------+
+ * |                         max period frames                         | 48
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 52
  * +----------------+----------------+----------------+----------------+
  * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
  * +----------------+----------------+----------------+----------------+
- * |                             reserved                              | 32
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * formats - uint64_t, bit mask representing values of the parameter
+ *     made as bitwise OR of (1 << XENSND_PCM_FORMAT_XXX) values
+ *
+ * For interval parameters:
+ *   min - uint32_t, minimum value of the parameter
+ *   max - uint32_t, maximum value of the parameter
+ *
+ * Frame is defined as a product of the number of channels by the
+ * number of octets per one sample.
+ */
+
+struct xensnd_query_hw_param {
+	uint64_t formats;
+	struct {
+		uint32_t min;
+		uint32_t max;
+	} rates;
+	struct {
+		uint32_t min;
+		uint32_t max;
+	} channels;
+	struct {
+		uint32_t min;
+		uint32_t max;
+	} buffer;
+	struct {
+		uint32_t min;
+		uint32_t max;
+	} period;
+};
+
+/*
+ *---------------------------------- Responses --------------------------------
+ *
+ * All response packets have the same length (64 octets)
+ *
+ * All response packets have common header:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |    operation   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                              status                               | 8
  * +----------------+----------------+----------------+----------------+
  *
  * id - uint16_t, copied from the request
  * operation - uint8_t, XENSND_OP_* - copied from request
  * status - int32_t, response status, zero on success and -XEN_EXX on failure
+ *
+ *
+ * HW parameter query response - response for XENSND_OP_HW_PARAM_QUERY:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |    operation   |    reserved    | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                              status                               | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                     formats mask low 32-bit                       | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                     formats mask high 32-bit                      | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                              min rate                             | 20
+ * +----------------+----------------+----------------+----------------+
+ * |                              max rate                             | 24
+ * +----------------+----------------+----------------+----------------+
+ * |                            min channels                           | 28
+ * +----------------+----------------+----------------+----------------+
+ * |                            max channels                           | 32
+ * +----------------+----------------+----------------+----------------+
+ * |                         min buffer frames                         | 36
+ * +----------------+----------------+----------------+----------------+
+ * |                         max buffer frames                         | 40
+ * +----------------+----------------+----------------+----------------+
+ * |                         min period frames                         | 44
+ * +----------------+----------------+----------------+----------------+
+ * |                         max period frames                         | 48
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 52
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Meaning of the values in this response is the same as for
+ * XENSND_OP_HW_PARAM_QUERY request.
+ */
+
+/*
+ *----------------------------------- Events ----------------------------------
+ *
+ * Events are sent via shared page allocated by the front and propagated by
+ *   evt-event-channel/evt-ring-ref XenStore entries
+ * All event packets have the same length (64 octets)
+ * All event packets have common header:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |      type      |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ *
+ * id - uint16_t, event id, may be used by front
+ * type - uint8_t, type of the event
+ *
+ *
+ * Current stream position - event from back to front when stream's
+ *   playback/capture position has advanced:
+ *         0                1                 2               3        octet
+ * +----------------+----------------+----------------+----------------+
+ * |               id                |   _EVT_CUR_POS |   reserved     | 4
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 8
+ * +----------------+----------------+----------------+----------------+
+ * |                         position low 32-bit                       | 12
+ * +----------------+----------------+----------------+----------------+
+ * |                         position high 32-bit                      | 16
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * |                             reserved                              | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * position - current value of stream's playback/capture position, octets
+ *
  */
 
+struct xensnd_cur_pos_evt {
+	uint64_t position;
+};
+
 struct xensnd_req {
 	uint16_t id;
 	uint8_t operation;
@@ -776,7 +1020,9 @@ struct xensnd_req {
 	union {
 		struct xensnd_open_req open;
 		struct xensnd_rw_req rw;
-		uint8_t reserved[24];
+		struct xensnd_trigger_req trigger;
+		struct xensnd_query_hw_param hw_param;
+		uint8_t reserved[56];
 	} op;
 };
 
@@ -785,9 +1031,53 @@ struct xensnd_resp {
 	uint8_t operation;
 	uint8_t reserved;
 	int32_t status;
-	uint8_t reserved1[24];
+	union {
+		struct xensnd_query_hw_param hw_param;
+		uint8_t reserved1[56];
+	} resp;
+};
+
+struct xensnd_evt {
+	uint16_t id;
+	uint8_t type;
+	uint8_t reserved[5];
+	union {
+		struct xensnd_cur_pos_evt cur_pos;
+		uint8_t reserved[56];
+	} op;
 };
 
 DEFINE_RING_TYPES(xen_sndif, struct xensnd_req, struct xensnd_resp);
 
+/*
+ ******************************************************************************
+ *                        Back to front events delivery
+ ******************************************************************************
+ * In order to deliver asynchronous events from back to front a shared page is
+ * allocated by front and its granted reference propagated to back via
+ * XenStore entries (evt-ring-ref/evt-event-channel).
+ * This page has a common header used by both front and back to synchronize
+ * access and control event's ring buffer, while back being a producer of the
+ * events and front being a consumer. The rest of the page after the header
+ * is used for event packets.
+ *
+ * Upon reception of an event(s) front may confirm its reception
+ * for either each event, group of events or none.
+ */
+
+struct xensnd_event_page {
+	uint32_t in_cons;
+	uint32_t in_prod;
+	uint8_t reserved[56];
+};
+
+#define XENSND_EVENT_PAGE_SIZE XEN_PAGE_SIZE
+#define XENSND_IN_RING_OFFS (sizeof(struct xensnd_event_page))
+#define XENSND_IN_RING_SIZE (XENSND_EVENT_PAGE_SIZE - XENSND_IN_RING_OFFS)
+#define XENSND_IN_RING_LEN (XENSND_IN_RING_SIZE / sizeof(struct xensnd_evt))
+#define XENSND_IN_RING(page) \
+	((struct xensnd_evt *)((char *)(page) + XENSND_IN_RING_OFFS))
+#define XENSND_IN_RING_REF(page, idx) \
+	(XENSND_IN_RING((page))[(idx) % XENSND_IN_RING_LEN])
+
 #endif /* __XEN_PUBLIC_IO_SNDIF_H__ */
diff --git a/init/Kconfig b/init/Kconfig
index f013afc74b11..0274d0d28df7 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1,20 +1,12 @@
-config ARCH
-	string
-	option env="ARCH"
-
-config KERNELVERSION
-	string
-	option env="KERNELVERSION"
-
 config DEFCONFIG_LIST
 	string
 	depends on !UML
 	option defconfig_list
-	default "/lib/modules/$UNAME_RELEASE/.config"
+	default "/lib/modules/$(shell,uname --release)/.config"
 	default "/etc/kernel-config"
-	default "/boot/config-$UNAME_RELEASE"
-	default "$ARCH_DEFCONFIG"
-	default "arch/$ARCH/defconfig"
+	default "/boot/config-$(shell,uname --release)"
+	default ARCH_DEFCONFIG
+	default "arch/$(ARCH)/defconfig"
 
 config CONSTRUCTORS
 	bool
@@ -54,15 +46,6 @@ config INIT_ENV_ARG_LIMIT
 	  Maximum of each of the number of arguments and environment
 	  variables passed to init from the kernel command line.
 
-
-config CROSS_COMPILE
-	string "Cross-compiler tool prefix"
-	help
-	  Same as running 'make CROSS_COMPILE=prefix-' but stored for
-	  default make runs in this kernel build directory.  You don't
-	  need to set this unless you want the configured kernel build
-	  directory to select the cross-compiler automatically.
-
 config COMPILE_TEST
 	bool "Compile also drivers which will not load"
 	depends on !UML
@@ -738,7 +721,7 @@ config CFS_BANDWIDTH
 	  tasks running within the fair group scheduler.  Groups with no limit
 	  set are considered to be unconstrained and will run with no
 	  restriction.
-	  See tip/Documentation/scheduler/sched-bwc.txt for more information.
+	  See Documentation/scheduler/sched-bwc.txt for more information.
 
 config RT_GROUP_SCHED
 	bool "Group scheduling for SCHED_RR/FIFO"
@@ -1038,6 +1021,33 @@ config CC_OPTIMIZE_FOR_SIZE
 
 endchoice
 
+config HAVE_LD_DEAD_CODE_DATA_ELIMINATION
+	bool
+	help
+	  This requires that the arch annotates or otherwise protects
+	  its external entry points from being discarded. Linker scripts
+	  must also merge .text.*, .data.*, and .bss.* correctly into
+	  output sections. Care must be taken not to pull in unrelated
+	  sections (e.g., '.text.init'). Typically '.' in section names
+	  is used to distinguish them from label names / C identifiers.
+
+config LD_DEAD_CODE_DATA_ELIMINATION
+	bool "Dead code and data elimination (EXPERIMENTAL)"
+	depends on HAVE_LD_DEAD_CODE_DATA_ELIMINATION
+	depends on EXPERT
+	help
+	  Select this if the architecture wants to do dead code and
+	  data elimination with the linker by compiling with
+	  -ffunction-sections -fdata-sections, and linking with
+	  --gc-sections.
+
+	  This can reduce on disk and in-memory size of the kernel
+	  code and static data, particularly for small configs and
+	  on small systems. This has the possibility of introducing
+	  silently broken kernel if the required annotations are not
+	  present. This option is not well tested yet, so use at your
+	  own risk.
+
 config SYSCTL
 	bool
 
diff --git a/init/main.c b/init/main.c
index b795aa341a3a..3b4ada11ed52 100644
--- a/init/main.c
+++ b/init/main.c
@@ -91,6 +91,7 @@
 #include <linux/cache.h>
 #include <linux/rodata_test.h>
 #include <linux/jump_label.h>
+#include <linux/mem_encrypt.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -423,7 +424,7 @@ static noinline void __ref rest_init(void)
 
 	/*
 	 * Enable might_sleep() and smp_processor_id() checks.
-	 * They cannot be enabled earlier because with CONFIG_PRREMPT=y
+	 * They cannot be enabled earlier because with CONFIG_PREEMPT=y
 	 * kernel_thread() would trigger might_sleep() splats. With
 	 * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
 	 * already, but it's stuck on the kthreadd_done completion.
@@ -1034,6 +1035,13 @@ __setup("rodata=", set_debug_rodata);
 static void mark_readonly(void)
 {
 	if (rodata_enabled) {
+		/*
+		 * load_module() results in W+X mappings, which are cleaned up
+		 * with call_rcu_sched().  Let's make sure that queued work is
+		 * flushed so that we don't hit false positives looking for
+		 * insecure pages which are W+X.
+		 */
+		rcu_barrier_sched();
 		mark_rodata_ro();
 		rodata_test();
 	} else
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index a808f29d4c5a..c0d58f390c3b 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -691,7 +691,7 @@ static void __do_notify(struct mqueue_inode_info *info)
 	wake_up(&info->wait_q);
 }
 
-static int prepare_timeout(const struct timespec __user *u_abs_timeout,
+static int prepare_timeout(const struct __kernel_timespec __user *u_abs_timeout,
 			   struct timespec64 *ts)
 {
 	if (get_timespec64(ts, u_abs_timeout))
@@ -1128,7 +1128,7 @@ out:
 
 SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 		size_t, msg_len, unsigned int, msg_prio,
-		const struct timespec __user *, u_abs_timeout)
+		const struct __kernel_timespec __user *, u_abs_timeout)
 {
 	struct timespec64 ts, *p = NULL;
 	if (u_abs_timeout) {
@@ -1142,7 +1142,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 
 SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
 		size_t, msg_len, unsigned int __user *, u_msg_prio,
-		const struct timespec __user *, u_abs_timeout)
+		const struct __kernel_timespec __user *, u_abs_timeout)
 {
 	struct timespec64 ts, *p = NULL;
 	if (u_abs_timeout) {
@@ -1420,6 +1420,47 @@ COMPAT_SYSCALL_DEFINE4(mq_open, const char __user *, u_name,
 	return do_mq_open(u_name, oflag, mode, p);
 }
 
+COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
+		       const struct compat_sigevent __user *, u_notification)
+{
+	struct sigevent n, *p = NULL;
+	if (u_notification) {
+		if (get_compat_sigevent(&n, u_notification))
+			return -EFAULT;
+		if (n.sigev_notify == SIGEV_THREAD)
+			n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int);
+		p = &n;
+	}
+	return do_mq_notify(mqdes, p);
+}
+
+COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
+		       const struct compat_mq_attr __user *, u_mqstat,
+		       struct compat_mq_attr __user *, u_omqstat)
+{
+	int ret;
+	struct mq_attr mqstat, omqstat;
+	struct mq_attr *new = NULL, *old = NULL;
+
+	if (u_mqstat) {
+		new = &mqstat;
+		if (get_compat_mq_attr(new, u_mqstat))
+			return -EFAULT;
+	}
+	if (u_omqstat)
+		old = &omqstat;
+
+	ret = do_mq_getsetattr(mqdes, new, old);
+	if (ret || !old)
+		return ret;
+
+	if (put_compat_mq_attr(old, u_omqstat))
+		return -EFAULT;
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
 static int compat_prepare_timeout(const struct compat_timespec __user *p,
 				   struct timespec64 *ts)
 {
@@ -1459,45 +1500,6 @@ COMPAT_SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes,
 	}
 	return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p);
 }
-
-COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
-		       const struct compat_sigevent __user *, u_notification)
-{
-	struct sigevent n, *p = NULL;
-	if (u_notification) {
-		if (get_compat_sigevent(&n, u_notification))
-			return -EFAULT;
-		if (n.sigev_notify == SIGEV_THREAD)
-			n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int);
-		p = &n;
-	}
-	return do_mq_notify(mqdes, p);
-}
-
-COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
-		       const struct compat_mq_attr __user *, u_mqstat,
-		       struct compat_mq_attr __user *, u_omqstat)
-{
-	int ret;
-	struct mq_attr mqstat, omqstat;
-	struct mq_attr *new = NULL, *old = NULL;
-
-	if (u_mqstat) {
-		new = &mqstat;
-		if (get_compat_mq_attr(new, u_mqstat))
-			return -EFAULT;
-	}
-	if (u_omqstat)
-		old = &omqstat;
-
-	ret = do_mq_getsetattr(mqdes, new, old);
-	if (ret || !old)
-		return ret;
-
-	if (put_compat_mq_attr(old, u_omqstat))
-		return -EFAULT;
-	return 0;
-}
 #endif
 
 static const struct inode_operations mqueue_dir_inode_operations = {
diff --git a/ipc/msg.c b/ipc/msg.c
index 56fd1c73eedc..3b6545302598 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -537,6 +537,11 @@ static int msgctl_stat(struct ipc_namespace *ns, int msqid,
 	p->msg_stime  = msq->q_stime;
 	p->msg_rtime  = msq->q_rtime;
 	p->msg_ctime  = msq->q_ctime;
+#ifndef CONFIG_64BIT
+	p->msg_stime_high = msq->q_stime >> 32;
+	p->msg_rtime_high = msq->q_rtime >> 32;
+	p->msg_ctime_high = msq->q_ctime >> 32;
+#endif
 	p->msg_cbytes = msq->q_cbytes;
 	p->msg_qnum   = msq->q_qnum;
 	p->msg_qbytes = msq->q_qbytes;
@@ -646,9 +651,12 @@ static int copy_compat_msqid_to_user(void __user *buf, struct msqid64_ds *in,
 		struct compat_msqid64_ds v;
 		memset(&v, 0, sizeof(v));
 		to_compat_ipc64_perm(&v.msg_perm, &in->msg_perm);
-		v.msg_stime = in->msg_stime;
-		v.msg_rtime = in->msg_rtime;
-		v.msg_ctime = in->msg_ctime;
+		v.msg_stime	 = lower_32_bits(in->msg_stime);
+		v.msg_stime_high = upper_32_bits(in->msg_stime);
+		v.msg_rtime	 = lower_32_bits(in->msg_rtime);
+		v.msg_rtime_high = upper_32_bits(in->msg_rtime);
+		v.msg_ctime	 = lower_32_bits(in->msg_ctime);
+		v.msg_ctime_high = upper_32_bits(in->msg_ctime);
 		v.msg_cbytes = in->msg_cbytes;
 		v.msg_qnum = in->msg_qnum;
 		v.msg_qbytes = in->msg_qbytes;
@@ -758,7 +766,7 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg,
 				WRITE_ONCE(msr->r_msg, ERR_PTR(-E2BIG));
 			} else {
 				ipc_update_pid(&msq->q_lrpid, task_pid(msr->r_tsk));
-				msq->q_rtime = get_seconds();
+				msq->q_rtime = ktime_get_real_seconds();
 
 				wake_q_add(wake_q, msr->r_tsk);
 				WRITE_ONCE(msr->r_msg, msg);
@@ -859,7 +867,7 @@ static long do_msgsnd(int msqid, long mtype, void __user *mtext,
 	}
 
 	ipc_update_pid(&msq->q_lspid, task_tgid(current));
-	msq->q_stime = get_seconds();
+	msq->q_stime = ktime_get_real_seconds();
 
 	if (!pipelined_send(msq, msg, &wake_q)) {
 		/* no one is waiting for this message, enqueue it */
@@ -1087,7 +1095,7 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in
 
 			list_del(&msg->m_list);
 			msq->q_qnum--;
-			msq->q_rtime = get_seconds();
+			msq->q_rtime = ktime_get_real_seconds();
 			ipc_update_pid(&msq->q_lrpid, task_tgid(current));
 			msq->q_cbytes -= msg->m_ts;
 			atomic_sub(msg->m_ts, &ns->msg_bytes);
diff --git a/ipc/sem.c b/ipc/sem.c
index 06be75d9217a..cfd94d48a9aa 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -70,6 +70,7 @@
  *   The worst-case behavior is nevertheless O(N^2) for N wakeups.
  */
 
+#include <linux/compat.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/init.h>
@@ -104,7 +105,7 @@ struct sem {
 					/* that alter the semaphore */
 	struct list_head pending_const; /* pending single-sop operations */
 					/* that do not alter the semaphore*/
-	time_t	sem_otime;	/* candidate for sem_otime */
+	time64_t	 sem_otime;	/* candidate for sem_otime */
 } ____cacheline_aligned_in_smp;
 
 /* One sem_array data structure for each set of semaphores in the system. */
@@ -984,10 +985,10 @@ again:
 static void set_semotime(struct sem_array *sma, struct sembuf *sops)
 {
 	if (sops == NULL) {
-		sma->sems[0].sem_otime = get_seconds();
+		sma->sems[0].sem_otime = ktime_get_real_seconds();
 	} else {
 		sma->sems[sops[0].sem_num].sem_otime =
-							get_seconds();
+						ktime_get_real_seconds();
 	}
 }
 
@@ -1214,6 +1215,7 @@ static int semctl_stat(struct ipc_namespace *ns, int semid,
 			 int cmd, struct semid64_ds *semid64)
 {
 	struct sem_array *sma;
+	time64_t semotime;
 	int id = 0;
 	int err;
 
@@ -1257,8 +1259,13 @@ static int semctl_stat(struct ipc_namespace *ns, int semid,
 	}
 
 	kernel_to_ipc64_perm(&sma->sem_perm, &semid64->sem_perm);
-	semid64->sem_otime = get_semotime(sma);
+	semotime = get_semotime(sma);
+	semid64->sem_otime = semotime;
 	semid64->sem_ctime = sma->sem_ctime;
+#ifndef CONFIG_64BIT
+	semid64->sem_otime_high = semotime >> 32;
+	semid64->sem_ctime_high = sma->sem_ctime >> 32;
+#endif
 	semid64->sem_nsems = sma->sem_nsems;
 
 	ipc_unlock_object(&sma->sem_perm);
@@ -1704,8 +1711,10 @@ static int copy_compat_semid_to_user(void __user *buf, struct semid64_ds *in,
 		struct compat_semid64_ds v;
 		memset(&v, 0, sizeof(v));
 		to_compat_ipc64_perm(&v.sem_perm, &in->sem_perm);
-		v.sem_otime = in->sem_otime;
-		v.sem_ctime = in->sem_ctime;
+		v.sem_otime	 = lower_32_bits(in->sem_otime);
+		v.sem_otime_high = upper_32_bits(in->sem_otime);
+		v.sem_ctime	 = lower_32_bits(in->sem_ctime);
+		v.sem_ctime_high = upper_32_bits(in->sem_ctime);
 		v.sem_nsems = in->sem_nsems;
 		return copy_to_user(buf, &v, sizeof(v));
 	} else {
@@ -2168,7 +2177,7 @@ out_free:
 }
 
 long ksys_semtimedop(int semid, struct sembuf __user *tsops,
-		     unsigned int nsops, const struct timespec __user *timeout)
+		     unsigned int nsops, const struct __kernel_timespec __user *timeout)
 {
 	if (timeout) {
 		struct timespec64 ts;
@@ -2180,12 +2189,12 @@ long ksys_semtimedop(int semid, struct sembuf __user *tsops,
 }
 
 SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
-		unsigned int, nsops, const struct timespec __user *, timeout)
+		unsigned int, nsops, const struct __kernel_timespec __user *, timeout)
 {
 	return ksys_semtimedop(semid, tsops, nsops, timeout);
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems,
 			    unsigned int nsops,
 			    const struct compat_timespec __user *timeout)
diff --git a/ipc/shm.c b/ipc/shm.c
index 3cf48988d68c..29978ee76c2e 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1002,6 +1002,11 @@ static int shmctl_stat(struct ipc_namespace *ns, int shmid,
 	tbuf->shm_atime	= shp->shm_atim;
 	tbuf->shm_dtime	= shp->shm_dtim;
 	tbuf->shm_ctime	= shp->shm_ctim;
+#ifndef CONFIG_64BIT
+	tbuf->shm_atime_high = shp->shm_atim >> 32;
+	tbuf->shm_dtime_high = shp->shm_dtim >> 32;
+	tbuf->shm_ctime_high = shp->shm_ctim >> 32;
+#endif
 	tbuf->shm_cpid	= pid_vnr(shp->shm_cprid);
 	tbuf->shm_lpid	= pid_vnr(shp->shm_lprid);
 	tbuf->shm_nattch = shp->shm_nattch;
@@ -1233,9 +1238,12 @@ static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in,
 		struct compat_shmid64_ds v;
 		memset(&v, 0, sizeof(v));
 		to_compat_ipc64_perm(&v.shm_perm, &in->shm_perm);
-		v.shm_atime = in->shm_atime;
-		v.shm_dtime = in->shm_dtime;
-		v.shm_ctime = in->shm_ctime;
+		v.shm_atime	 = lower_32_bits(in->shm_atime);
+		v.shm_atime_high = upper_32_bits(in->shm_atime);
+		v.shm_dtime	 = lower_32_bits(in->shm_dtime);
+		v.shm_dtime_high = upper_32_bits(in->shm_dtime);
+		v.shm_ctime	 = lower_32_bits(in->shm_ctime);
+		v.shm_ctime_high = upper_32_bits(in->shm_ctime);
 		v.shm_segsz = in->shm_segsz;
 		v.shm_nattch = in->shm_nattch;
 		v.shm_cpid = in->shm_cpid;
@@ -1363,14 +1371,17 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 
 	if (addr) {
 		if (addr & (shmlba - 1)) {
-			/*
-			 * Round down to the nearest multiple of shmlba.
-			 * For sane do_mmap_pgoff() parameters, avoid
-			 * round downs that trigger nil-page and MAP_FIXED.
-			 */
-			if ((shmflg & SHM_RND) && addr >= shmlba)
-				addr &= ~(shmlba - 1);
-			else
+			if (shmflg & SHM_RND) {
+				addr &= ~(shmlba - 1);  /* round down */
+
+				/*
+				 * Ensure that the round-down is non-nil
+				 * when remapping. This can happen for
+				 * cases when addr < shmlba.
+				 */
+				if (!addr && (shmflg & SHM_REMAP))
+					goto out;
+			} else
 #ifndef __ARCH_FORCE_SHMLBA
 				if (addr & ~PAGE_MASK)
 #endif
diff --git a/ipc/syscall.c b/ipc/syscall.c
index 77a883ef2eca..65d405f1ba0c 100644
--- a/ipc/syscall.c
+++ b/ipc/syscall.c
@@ -30,9 +30,14 @@ SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second,
 		return ksys_semtimedop(first, (struct sembuf __user *)ptr,
 				       second, NULL);
 	case SEMTIMEDOP:
-		return ksys_semtimedop(first, (struct sembuf __user *)ptr,
-				       second,
-				       (const struct timespec __user *)fifth);
+		if (IS_ENABLED(CONFIG_64BIT) || !IS_ENABLED(CONFIG_64BIT_TIME))
+			return ksys_semtimedop(first, ptr, second,
+			        (const struct __kernel_timespec __user *)fifth);
+		else if (IS_ENABLED(CONFIG_COMPAT_32BIT_TIME))
+			return compat_ksys_semtimedop(first, ptr, second,
+			        (const struct compat_timespec __user *)fifth);
+		else
+			return -ENOSYS;
 
 	case SEMGET:
 		return ksys_semget(first, second, third);
@@ -130,6 +135,8 @@ COMPAT_SYSCALL_DEFINE6(ipc, u32, call, int, first, int, second,
 		/* struct sembuf is the same on 32 and 64bit :)) */
 		return ksys_semtimedop(first, compat_ptr(ptr), second, NULL);
 	case SEMTIMEDOP:
+		if (!IS_ENABLED(CONFIG_COMPAT_32BIT_TIME))
+			return -ENOSYS;
 		return compat_ksys_semtimedop(first, compat_ptr(ptr), second,
 						compat_ptr(fifth));
 	case SEMGET:
diff --git a/ipc/util.h b/ipc/util.h
index acc5159e96d0..0aba3230d007 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -251,7 +251,7 @@ static inline int compat_ipc_parse_version(int *cmd)
 /* for __ARCH_WANT_SYS_IPC */
 long ksys_semtimedop(int semid, struct sembuf __user *tsops,
 		     unsigned int nsops,
-		     const struct timespec __user *timeout);
+		     const struct __kernel_timespec __user *timeout);
 long ksys_semget(key_t key, int nsems, int semflg);
 long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg);
 long ksys_msgget(key_t key, int msgflg);
@@ -265,10 +265,10 @@ long ksys_shmdt(char __user *shmaddr);
 long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf);
 
 /* for CONFIG_ARCH_WANT_OLD_COMPAT_IPC */
-#ifdef CONFIG_COMPAT
 long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems,
 			    unsigned int nsops,
 			    const struct compat_timespec __user *timeout);
+#ifdef CONFIG_COMPAT
 long compat_ksys_semctl(int semid, int semnum, int cmd, int arg);
 long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr);
 long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz,
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 14750e7c5ee4..027107f4be53 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -476,7 +476,7 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
@@ -495,6 +495,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
+	.map_release_uref = bpf_fd_array_map_clear,
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d315b393abdd..6ef6746a7871 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -218,47 +218,84 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	return 0;
 }
 
-static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
+static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
+				u32 curr, const bool probe_pass)
 {
+	const s64 imm_min = S32_MIN, imm_max = S32_MAX;
+	s64 imm = insn->imm;
+
+	if (curr < pos && curr + imm + 1 > pos)
+		imm += delta;
+	else if (curr > pos + delta && curr + imm + 1 <= pos + delta)
+		imm -= delta;
+	if (imm < imm_min || imm > imm_max)
+		return -ERANGE;
+	if (!probe_pass)
+		insn->imm = imm;
+	return 0;
+}
+
+static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
+				u32 curr, const bool probe_pass)
+{
+	const s32 off_min = S16_MIN, off_max = S16_MAX;
+	s32 off = insn->off;
+
+	if (curr < pos && curr + off + 1 > pos)
+		off += delta;
+	else if (curr > pos + delta && curr + off + 1 <= pos + delta)
+		off -= delta;
+	if (off < off_min || off > off_max)
+		return -ERANGE;
+	if (!probe_pass)
+		insn->off = off;
+	return 0;
+}
+
+static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
+			    const bool probe_pass)
+{
+	u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0);
 	struct bpf_insn *insn = prog->insnsi;
-	u32 i, insn_cnt = prog->len;
-	bool pseudo_call;
-	u8 code;
-	int off;
+	int ret = 0;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
+		u8 code;
+
+		/* In the probing pass we still operate on the original,
+		 * unpatched image in order to check overflows before we
+		 * do any other adjustments. Therefore skip the patchlet.
+		 */
+		if (probe_pass && i == pos) {
+			i += delta + 1;
+			insn++;
+		}
 		code = insn->code;
-		if (BPF_CLASS(code) != BPF_JMP)
-			continue;
-		if (BPF_OP(code) == BPF_EXIT)
+		if (BPF_CLASS(code) != BPF_JMP ||
+		    BPF_OP(code) == BPF_EXIT)
 			continue;
+		/* Adjust offset of jmps if we cross patch boundaries. */
 		if (BPF_OP(code) == BPF_CALL) {
-			if (insn->src_reg == BPF_PSEUDO_CALL)
-				pseudo_call = true;
-			else
+			if (insn->src_reg != BPF_PSEUDO_CALL)
 				continue;
+			ret = bpf_adj_delta_to_imm(insn, pos, delta, i,
+						   probe_pass);
 		} else {
-			pseudo_call = false;
+			ret = bpf_adj_delta_to_off(insn, pos, delta, i,
+						   probe_pass);
 		}
-		off = pseudo_call ? insn->imm : insn->off;
-
-		/* Adjust offset of jmps if we cross boundaries. */
-		if (i < pos && i + off + 1 > pos)
-			off += delta;
-		else if (i > pos + delta && i + off + 1 <= pos + delta)
-			off -= delta;
-
-		if (pseudo_call)
-			insn->imm = off;
-		else
-			insn->off = off;
+		if (ret)
+			break;
 	}
+
+	return ret;
 }
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len)
 {
 	u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
+	const u32 cnt_max = S16_MAX;
 	struct bpf_prog *prog_adj;
 
 	/* Since our patchlet doesn't expand the image, we're done. */
@@ -269,6 +306,15 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 
 	insn_adj_cnt = prog->len + insn_delta;
 
+	/* Reject anything that would potentially let the insn->off
+	 * target overflow when we have excessive program expansions.
+	 * We need to probe here before we do any reallocation where
+	 * we afterwards may not fail anymore.
+	 */
+	if (insn_adj_cnt > cnt_max &&
+	    bpf_adj_branches(prog, off, insn_delta, true))
+		return NULL;
+
 	/* Several new instructions need to be inserted. Make room
 	 * for them. Likely, there's no need for a new allocation as
 	 * last page could have large enough tailroom.
@@ -294,7 +340,11 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 		sizeof(*patch) * insn_rest);
 	memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
 
-	bpf_adj_branches(prog_adj, off, insn_delta);
+	/* We are guaranteed to not fail at this point, otherwise
+	 * the ship has sailed to reverse to the original state. An
+	 * overflow cannot happen at this point.
+	 */
+	BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
 
 	return prog_adj;
 }
@@ -1572,13 +1622,32 @@ int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
 	return cnt;
 }
 
+static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+				     u32 *prog_ids,
+				     u32 request_cnt)
+{
+	int i = 0;
+
+	for (; *prog; prog++) {
+		if (*prog == &dummy_bpf_prog.prog)
+			continue;
+		prog_ids[i] = (*prog)->aux->id;
+		if (++i == request_cnt) {
+			prog++;
+			break;
+		}
+	}
+
+	return !!(*prog);
+}
+
 int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 				__u32 __user *prog_ids, u32 cnt)
 {
 	struct bpf_prog **prog;
 	unsigned long err = 0;
-	u32 i = 0, *ids;
 	bool nospc;
+	u32 *ids;
 
 	/* users of this function are doing:
 	 * cnt = bpf_prog_array_length();
@@ -1595,16 +1664,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 		return -ENOMEM;
 	rcu_read_lock();
 	prog = rcu_dereference(progs)->progs;
-	for (; *prog; prog++) {
-		if (*prog == &dummy_bpf_prog.prog)
-			continue;
-		ids[i] = (*prog)->aux->id;
-		if (++i == cnt) {
-			prog++;
-			break;
-		}
-	}
-	nospc = !!(*prog);
+	nospc = bpf_prog_array_copy_core(prog, ids, cnt);
 	rcu_read_unlock();
 	err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
 	kfree(ids);
@@ -1683,22 +1743,25 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 }
 
 int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
-			     __u32 __user *prog_ids, u32 request_cnt,
-			     __u32 __user *prog_cnt)
+			     u32 *prog_ids, u32 request_cnt,
+			     u32 *prog_cnt)
 {
+	struct bpf_prog **prog;
 	u32 cnt = 0;
 
 	if (array)
 		cnt = bpf_prog_array_length(array);
 
-	if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
-		return -EFAULT;
+	*prog_cnt = cnt;
 
 	/* return early if user requested only program count or nothing to copy */
 	if (!request_cnt || !cnt)
 		return 0;
 
-	return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
+	/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
+	prog = rcu_dereference_check(array, 1)->progs;
+	return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+								     : 0;
 }
 
 static void bpf_prog_free_deferred(struct work_struct *work)
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 8dd9210d7db7..95a84b2f10ce 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -43,6 +43,7 @@
 #include <net/tcp.h>
 #include <linux/ptr_ring.h>
 #include <net/inet_common.h>
+#include <linux/sched/signal.h>
 
 #define SOCK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
@@ -325,6 +326,9 @@ retry:
 			if (ret > 0) {
 				if (apply)
 					apply_bytes -= ret;
+
+				sg->offset += ret;
+				sg->length -= ret;
 				size -= ret;
 				offset += ret;
 				if (uncharge)
@@ -332,8 +336,6 @@ retry:
 				goto retry;
 			}
 
-			sg->length = size;
-			sg->offset = offset;
 			return ret;
 		}
 
@@ -391,7 +393,8 @@ static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 	} while (i != md->sg_end);
 }
 
-static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
+static void free_bytes_sg(struct sock *sk, int bytes,
+			  struct sk_msg_buff *md, bool charge)
 {
 	struct scatterlist *sg = md->sg_data;
 	int i = md->sg_start, free;
@@ -401,11 +404,13 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 		if (bytes < free) {
 			sg[i].length -= bytes;
 			sg[i].offset += bytes;
-			sk_mem_uncharge(sk, bytes);
+			if (charge)
+				sk_mem_uncharge(sk, bytes);
 			break;
 		}
 
-		sk_mem_uncharge(sk, sg[i].length);
+		if (charge)
+			sk_mem_uncharge(sk, sg[i].length);
 		put_page(sg_page(&sg[i]));
 		bytes -= sg[i].length;
 		sg[i].length = 0;
@@ -416,6 +421,7 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 		if (i == MAX_SKB_FRAGS)
 			i = 0;
 	}
+	md->sg_start = i;
 }
 
 static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
@@ -523,8 +529,6 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 	i = md->sg_start;
 
 	do {
-		r->sg_data[i] = md->sg_data[i];
-
 		size = (apply && apply_bytes < md->sg_data[i].length) ?
 			apply_bytes : md->sg_data[i].length;
 
@@ -535,6 +539,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 		}
 
 		sk_mem_charge(sk, size);
+		r->sg_data[i] = md->sg_data[i];
 		r->sg_data[i].length = size;
 		md->sg_data[i].length -= size;
 		md->sg_data[i].offset += size;
@@ -575,10 +580,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 				       struct sk_msg_buff *md,
 				       int flags)
 {
+	bool ingress = !!(md->flags & BPF_F_INGRESS);
 	struct smap_psock *psock;
 	struct scatterlist *sg;
-	int i, err, free = 0;
-	bool ingress = !!(md->flags & BPF_F_INGRESS);
+	int err = 0;
 
 	sg = md->sg_data;
 
@@ -606,16 +611,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 out_rcu:
 	rcu_read_unlock();
 out:
-	i = md->sg_start;
-	while (sg[i].length) {
-		free += sg[i].length;
-		put_page(sg_page(&sg[i]));
-		sg[i].length = 0;
-		i++;
-		if (i == MAX_SKB_FRAGS)
-			i = 0;
-	}
-	return free;
+	free_bytes_sg(NULL, send, md, false);
+	return err;
 }
 
 static inline void bpf_md_init(struct smap_psock *psock)
@@ -700,19 +697,26 @@ more_data:
 		err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
 		lock_sock(sk);
 
+		if (unlikely(err < 0)) {
+			free_start_sg(sk, m);
+			psock->sg_size = 0;
+			if (!cork)
+				*copied -= send;
+		} else {
+			psock->sg_size -= send;
+		}
+
 		if (cork) {
 			free_start_sg(sk, m);
+			psock->sg_size = 0;
 			kfree(m);
 			m = NULL;
+			err = 0;
 		}
-		if (unlikely(err))
-			*copied -= err;
-		else
-			psock->sg_size -= send;
 		break;
 	case __SK_DROP:
 	default:
-		free_bytes_sg(sk, send, m);
+		free_bytes_sg(sk, send, m, true);
 		apply_bytes_dec(psock, send);
 		*copied -= send;
 		psock->sg_size -= send;
@@ -732,6 +736,26 @@ out_err:
 	return err;
 }
 
+static int bpf_wait_data(struct sock *sk,
+			 struct smap_psock *psk, int flags,
+			 long timeo, int *err)
+{
+	int rc;
+
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	rc = sk_wait_event(sk, &timeo,
+			   !list_empty(&psk->ingress) ||
+			   !skb_queue_empty(&sk->sk_receive_queue),
+			   &wait);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+
+	return rc;
+}
+
 static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			   int nonblock, int flags, int *addr_len)
 {
@@ -755,6 +779,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	lock_sock(sk);
+bytes_ready:
 	while (copied != len) {
 		struct scatterlist *sg;
 		struct sk_msg_buff *md;
@@ -809,6 +834,28 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 	}
 
+	if (!copied) {
+		long timeo;
+		int data;
+		int err = 0;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = bpf_wait_data(sk, psock, flags, timeo, &err);
+
+		if (data) {
+			if (!skb_queue_empty(&sk->sk_receive_queue)) {
+				release_sock(sk);
+				smap_release_sock(psock, sk);
+				copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+				return copied;
+			}
+			goto bytes_ready;
+		}
+
+		if (err)
+			copied = err;
+	}
+
 	release_sock(sk);
 	smap_release_sock(psock, sk);
 	return copied;
@@ -1442,9 +1489,6 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	    attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
-	if (attr->value_size > KMALLOC_MAX_SIZE)
-		return ERR_PTR(-E2BIG);
-
 	err = bpf_tcp_ulp_register();
 	if (err && err != -EEXIST)
 		return ERR_PTR(err);
@@ -1659,11 +1703,11 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		 * we increment the refcnt. If this is the case abort with an
 		 * error.
 		 */
-		verdict = bpf_prog_inc_not_zero(stab->bpf_verdict);
+		verdict = bpf_prog_inc_not_zero(verdict);
 		if (IS_ERR(verdict))
 			return PTR_ERR(verdict);
 
-		parse = bpf_prog_inc_not_zero(stab->bpf_parse);
+		parse = bpf_prog_inc_not_zero(parse);
 		if (IS_ERR(parse)) {
 			bpf_prog_put(verdict);
 			return PTR_ERR(parse);
@@ -1671,12 +1715,12 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	}
 
 	if (tx_msg) {
-		tx_msg = bpf_prog_inc_not_zero(stab->bpf_tx_msg);
+		tx_msg = bpf_prog_inc_not_zero(tx_msg);
 		if (IS_ERR(tx_msg)) {
-			if (verdict)
-				bpf_prog_put(verdict);
-			if (parse)
+			if (parse && verdict) {
 				bpf_prog_put(parse);
+				bpf_prog_put(verdict);
+			}
 			return PTR_ERR(tx_msg);
 		}
 	}
@@ -1761,10 +1805,10 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 out_free:
 	smap_release_sock(psock, sock);
 out_progs:
-	if (verdict)
-		bpf_prog_put(verdict);
-	if (parse)
+	if (parse && verdict) {
 		bpf_prog_put(parse);
+		bpf_prog_put(verdict);
+	}
 	if (tx_msg)
 		bpf_prog_put(tx_msg);
 	write_unlock_bh(&sock->sk_callback_lock);
@@ -1834,7 +1878,7 @@ static int sock_map_update_elem(struct bpf_map *map,
 	return err;
 }
 
-static void sock_map_release(struct bpf_map *map, struct file *map_file)
+static void sock_map_release(struct bpf_map *map)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
 	struct bpf_prog *orig;
@@ -1858,7 +1902,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_get_next_key = sock_map_get_next_key,
 	.map_update_elem = sock_map_update_elem,
 	.map_delete_elem = sock_map_delete_elem,
-	.map_release = sock_map_release,
+	.map_release_uref = sock_map_release,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4ca46df19c9a..016ef9025827 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -26,6 +26,7 @@
 #include <linux/cred.h>
 #include <linux/timekeeping.h>
 #include <linux/ctype.h>
+#include <linux/nospec.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
 			   (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -102,12 +103,14 @@ const struct bpf_map_ops bpf_map_offload_ops = {
 static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 {
 	const struct bpf_map_ops *ops;
+	u32 type = attr->map_type;
 	struct bpf_map *map;
 	int err;
 
-	if (attr->map_type >= ARRAY_SIZE(bpf_map_types))
+	if (type >= ARRAY_SIZE(bpf_map_types))
 		return ERR_PTR(-EINVAL);
-	ops = bpf_map_types[attr->map_type];
+	type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types));
+	ops = bpf_map_types[type];
 	if (!ops)
 		return ERR_PTR(-EINVAL);
 
@@ -122,7 +125,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return map;
 	map->ops = ops;
-	map->map_type = attr->map_type;
+	map->map_type = type;
 	return map;
 }
 
@@ -257,8 +260,8 @@ static void bpf_map_free_deferred(struct work_struct *work)
 static void bpf_map_put_uref(struct bpf_map *map)
 {
 	if (atomic_dec_and_test(&map->usercnt)) {
-		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-			bpf_fd_array_map_clear(map);
+		if (map->ops->map_release_uref)
+			map->ops->map_release_uref(map);
 	}
 }
 
@@ -871,11 +874,17 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = {
 
 static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
 {
-	if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
+	const struct bpf_prog_ops *ops;
+
+	if (type >= ARRAY_SIZE(bpf_prog_types))
+		return -EINVAL;
+	type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types));
+	ops = bpf_prog_types[type];
+	if (!ops)
 		return -EINVAL;
 
 	if (!bpf_prog_is_dev_bound(prog->aux))
-		prog->aux->ops = bpf_prog_types[type];
+		prog->aux->ops = ops;
 	else
 		prog->aux->ops = &bpf_offload_prog_ops;
 	prog->type = type;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5dd1dcb902bf..1904e814f282 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -156,7 +156,29 @@ struct bpf_verifier_stack_elem {
 #define BPF_COMPLEXITY_LIMIT_INSNS	131072
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 
-#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
+#define BPF_MAP_PTR_UNPRIV	1UL
+#define BPF_MAP_PTR_POISON	((void *)((0xeB9FUL << 1) +	\
+					  POISON_POINTER_DELTA))
+#define BPF_MAP_PTR(X)		((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
+
+static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
+{
+	return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON;
+}
+
+static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux)
+{
+	return aux->map_state & BPF_MAP_PTR_UNPRIV;
+}
+
+static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux,
+			      const struct bpf_map *map, bool unpriv)
+{
+	BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV);
+	unpriv |= bpf_map_ptr_unpriv(aux);
+	aux->map_state = (unsigned long)map |
+			 (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
+}
 
 struct bpf_call_arg_meta {
 	struct bpf_map *map_ptr;
@@ -978,7 +1000,7 @@ static bool register_is_null(struct bpf_reg_state *reg)
  */
 static int check_stack_write(struct bpf_verifier_env *env,
 			     struct bpf_func_state *state, /* func where register points to */
-			     int off, int size, int value_regno)
+			     int off, int size, int value_regno, int insn_idx)
 {
 	struct bpf_func_state *cur; /* state of the current function */
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
@@ -1017,8 +1039,33 @@ static int check_stack_write(struct bpf_verifier_env *env,
 		state->stack[spi].spilled_ptr = cur->regs[value_regno];
 		state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
 
-		for (i = 0; i < BPF_REG_SIZE; i++)
+		for (i = 0; i < BPF_REG_SIZE; i++) {
+			if (state->stack[spi].slot_type[i] == STACK_MISC &&
+			    !env->allow_ptr_leaks) {
+				int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
+				int soff = (-spi - 1) * BPF_REG_SIZE;
+
+				/* detected reuse of integer stack slot with a pointer
+				 * which means either llvm is reusing stack slot or
+				 * an attacker is trying to exploit CVE-2018-3639
+				 * (speculative store bypass)
+				 * Have to sanitize that slot with preemptive
+				 * store of zero.
+				 */
+				if (*poff && *poff != soff) {
+					/* disallow programs where single insn stores
+					 * into two different stack slots, since verifier
+					 * cannot sanitize them
+					 */
+					verbose(env,
+						"insn %d cannot access two stack slots fp%d and fp%d",
+						insn_idx, *poff, soff);
+					return -EINVAL;
+				}
+				*poff = soff;
+			}
 			state->stack[spi].slot_type[i] = STACK_SPILL;
+		}
 	} else {
 		u8 type = STACK_MISC;
 
@@ -1694,7 +1741,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 
 		if (t == BPF_WRITE)
 			err = check_stack_write(env, state, off, size,
-						value_regno);
+						value_regno, insn_idx);
 		else
 			err = check_stack_read(env, state, off, size,
 					       value_regno);
@@ -2333,6 +2380,29 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	return 0;
 }
 
+static int
+record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
+		int func_id, int insn_idx)
+{
+	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+
+	if (func_id != BPF_FUNC_tail_call &&
+	    func_id != BPF_FUNC_map_lookup_elem)
+		return 0;
+	if (meta->map_ptr == NULL) {
+		verbose(env, "kernel subsystem misconfigured verifier\n");
+		return -EINVAL;
+	}
+
+	if (!BPF_MAP_PTR(aux->map_state))
+		bpf_map_ptr_store(aux, meta->map_ptr,
+				  meta->map_ptr->unpriv_array);
+	else if (BPF_MAP_PTR(aux->map_state) != meta->map_ptr)
+		bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON,
+				  meta->map_ptr->unpriv_array);
+	return 0;
+}
+
 static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 {
 	const struct bpf_func_proto *fn = NULL;
@@ -2387,13 +2457,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
 	if (err)
 		return err;
-	if (func_id == BPF_FUNC_tail_call) {
-		if (meta.map_ptr == NULL) {
-			verbose(env, "verifier bug\n");
-			return -EINVAL;
-		}
-		env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr;
-	}
 	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
 	if (err)
 		return err;
@@ -2404,6 +2467,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	if (err)
 		return err;
 
+	err = record_func_map(env, &meta, func_id, insn_idx);
+	if (err)
+		return err;
+
 	/* Mark slots with STACK_MISC in case of raw mode, stack offset
 	 * is inferred from register state.
 	 */
@@ -2428,8 +2495,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	} else if (fn->ret_type == RET_VOID) {
 		regs[BPF_REG_0].type = NOT_INIT;
 	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
-		struct bpf_insn_aux_data *insn_aux;
-
 		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
 		/* There is no offset yet applied, variable or fixed */
 		mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -2445,11 +2510,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		}
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
 		regs[BPF_REG_0].id = ++env->id_gen;
-		insn_aux = &env->insn_aux_data[insn_idx];
-		if (!insn_aux->map_ptr)
-			insn_aux->map_ptr = meta.map_ptr;
-		else if (insn_aux->map_ptr != meta.map_ptr)
-			insn_aux->map_ptr = BPF_MAP_PTR_POISON;
 	} else {
 		verbose(env, "unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);
@@ -5169,6 +5229,34 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		else
 			continue;
 
+		if (type == BPF_WRITE &&
+		    env->insn_aux_data[i + delta].sanitize_stack_off) {
+			struct bpf_insn patch[] = {
+				/* Sanitize suspicious stack slot with zero.
+				 * There are no memory dependencies for this store,
+				 * since it's only using frame pointer and immediate
+				 * constant of zero
+				 */
+				BPF_ST_MEM(BPF_DW, BPF_REG_FP,
+					   env->insn_aux_data[i + delta].sanitize_stack_off,
+					   0),
+				/* the original STX instruction will immediately
+				 * overwrite the same stack slot with appropriate value
+				 */
+				*insn,
+			};
+
+			cnt = ARRAY_SIZE(patch);
+			new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 		if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
 			continue;
 
@@ -5417,6 +5505,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 	struct bpf_insn *insn = prog->insnsi;
 	const struct bpf_func_proto *fn;
 	const int insn_cnt = prog->len;
+	struct bpf_insn_aux_data *aux;
 	struct bpf_insn insn_buf[16];
 	struct bpf_prog *new_prog;
 	struct bpf_map *map_ptr;
@@ -5491,19 +5580,22 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			insn->imm = 0;
 			insn->code = BPF_JMP | BPF_TAIL_CALL;
 
+			aux = &env->insn_aux_data[i + delta];
+			if (!bpf_map_ptr_unpriv(aux))
+				continue;
+
 			/* instead of changing every JIT dealing with tail_call
 			 * emit two extra insns:
 			 * if (index >= max_entries) goto out;
 			 * index &= array->index_mask;
 			 * to avoid out-of-bounds cpu speculation
 			 */
-			map_ptr = env->insn_aux_data[i + delta].map_ptr;
-			if (map_ptr == BPF_MAP_PTR_POISON) {
+			if (bpf_map_ptr_poisoned(aux)) {
 				verbose(env, "tail_call abusing map_ptr\n");
 				return -EINVAL;
 			}
-			if (!map_ptr->unpriv_array)
-				continue;
+
+			map_ptr = BPF_MAP_PTR(aux->map_state);
 			insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
 						  map_ptr->max_entries, 2);
 			insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
@@ -5527,9 +5619,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 		 */
 		if (prog->jit_requested && BITS_PER_LONG == 64 &&
 		    insn->imm == BPF_FUNC_map_lookup_elem) {
-			map_ptr = env->insn_aux_data[i + delta].map_ptr;
-			if (map_ptr == BPF_MAP_PTR_POISON ||
-			    !map_ptr->ops->map_gen_lookup)
+			aux = &env->insn_aux_data[i + delta];
+			if (bpf_map_ptr_poisoned(aux))
+				goto patch_call_imm;
+
+			map_ptr = BPF_MAP_PTR(aux->map_state);
+			if (!map_ptr->ops->map_gen_lookup)
 				goto patch_call_imm;
 
 			cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile
index 2be89a003185..bfcdae896122 100644
--- a/kernel/cgroup/Makefile
+++ b/kernel/cgroup/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-y := cgroup.o stat.o namespace.o cgroup-v1.o
+obj-y := cgroup.o rstat.o namespace.o cgroup-v1.o
 
 obj-$(CONFIG_CGROUP_FREEZER) += freezer.o
 obj-$(CONFIG_CGROUP_PIDS) += pids.o
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index b928b27050c6..77ff1cd6a252 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -201,13 +201,12 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 int cgroup_task_count(const struct cgroup *cgrp);
 
 /*
- * stat.c
+ * rstat.c
  */
-void cgroup_stat_flush(struct cgroup *cgrp);
-int cgroup_stat_init(struct cgroup *cgrp);
-void cgroup_stat_exit(struct cgroup *cgrp);
-void cgroup_stat_show_cputime(struct seq_file *seq);
-void cgroup_stat_boot(void);
+int cgroup_rstat_init(struct cgroup *cgrp);
+void cgroup_rstat_exit(struct cgroup *cgrp);
+void cgroup_rstat_boot(void);
+void cgroup_base_stat_cputime_show(struct seq_file *seq);
 
 /*
  * namespace.c
@@ -218,9 +217,9 @@ extern const struct proc_ns_operations cgroupns_operations;
  * cgroup-v1.c
  */
 extern struct cftype cgroup1_base_files[];
-extern const struct file_operations proc_cgroupstats_operations;
 extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
 
+int proc_cgroupstats_show(struct seq_file *m, void *v);
 bool cgroup1_ssid_disabled(int ssid);
 void cgroup1_pidlist_destroy_all(struct cgroup *cgrp);
 void cgroup1_release_agent(struct work_struct *work);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index a2c05d2476ac..e06c97f3ed1a 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -682,7 +682,7 @@ struct cftype cgroup1_base_files[] = {
 };
 
 /* Display information about each subsystem and each hierarchy */
-static int proc_cgroupstats_show(struct seq_file *m, void *v)
+int proc_cgroupstats_show(struct seq_file *m, void *v)
 {
 	struct cgroup_subsys *ss;
 	int i;
@@ -705,18 +705,6 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int cgroupstats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_cgroupstats_show, NULL);
-}
-
-const struct file_operations proc_cgroupstats_operations = {
-	.open = cgroupstats_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 /**
  * cgroupstats_build - build and fill cgroupstats
  * @stats: cgroupstats to fill information into
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a662bfcbea0e..acb66713f9b6 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -54,6 +54,7 @@
 #include <linux/proc_ns.h>
 #include <linux/nsproxy.h>
 #include <linux/file.h>
+#include <linux/sched/cputime.h>
 #include <net/sock.h>
 
 #define CREATE_TRACE_POINTS
@@ -61,6 +62,8 @@
 
 #define CGROUP_FILE_NAME_MAX		(MAX_CGROUP_TYPE_NAMELEN +	\
 					 MAX_CFTYPE_NAME + 2)
+/* let's not notify more than 100 times per second */
+#define CGROUP_FILE_NOTIFY_MIN_INTV	DIV_ROUND_UP(HZ, 100)
 
 /*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
@@ -142,14 +145,14 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
 };
 #undef SUBSYS
 
-static DEFINE_PER_CPU(struct cgroup_cpu_stat, cgrp_dfl_root_cpu_stat);
+static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu);
 
 /*
  * The default hierarchy, reserved for the subsystems that are otherwise
  * unattached - it never has more than a single cgroup, and all tasks are
  * part of that cgroup.
  */
-struct cgroup_root cgrp_dfl_root = { .cgrp.cpu_stat = &cgrp_dfl_root_cpu_stat };
+struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu };
 EXPORT_SYMBOL_GPL(cgrp_dfl_root);
 
 /*
@@ -1554,6 +1557,8 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 		spin_lock_irq(&cgroup_file_kn_lock);
 		cfile->kn = NULL;
 		spin_unlock_irq(&cgroup_file_kn_lock);
+
+		del_timer_sync(&cfile->notify_timer);
 	}
 
 	kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
@@ -1573,8 +1578,17 @@ static void css_clear_dir(struct cgroup_subsys_state *css)
 
 	css->flags &= ~CSS_VISIBLE;
 
-	list_for_each_entry(cfts, &css->ss->cfts, node)
+	if (!css->ss) {
+		if (cgroup_on_dfl(cgrp))
+			cfts = cgroup_base_files;
+		else
+			cfts = cgroup1_base_files;
+
 		cgroup_addrm_files(css, cgrp, cfts, false);
+	} else {
+		list_for_each_entry(cfts, &css->ss->cfts, node)
+			cgroup_addrm_files(css, cgrp, cfts, false);
+	}
 }
 
 /**
@@ -1598,14 +1612,16 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
 		else
 			cfts = cgroup1_base_files;
 
-		return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
-	}
-
-	list_for_each_entry(cfts, &css->ss->cfts, node) {
-		ret = cgroup_addrm_files(css, cgrp, cfts, true);
-		if (ret < 0) {
-			failed_cfts = cfts;
-			goto err;
+		ret = cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
+		if (ret < 0)
+			return ret;
+	} else {
+		list_for_each_entry(cfts, &css->ss->cfts, node) {
+			ret = cgroup_addrm_files(css, cgrp, cfts, true);
+			if (ret < 0) {
+				failed_cfts = cfts;
+				goto err;
+			}
 		}
 	}
 
@@ -1782,13 +1798,6 @@ static void cgroup_enable_task_cg_lists(void)
 {
 	struct task_struct *p, *g;
 
-	spin_lock_irq(&css_set_lock);
-
-	if (use_task_css_set_links)
-		goto out_unlock;
-
-	use_task_css_set_links = true;
-
 	/*
 	 * We need tasklist_lock because RCU is not safe against
 	 * while_each_thread(). Besides, a forking task that has passed
@@ -1797,6 +1806,13 @@ static void cgroup_enable_task_cg_lists(void)
 	 * tasklist if we walk through it with RCU.
 	 */
 	read_lock(&tasklist_lock);
+	spin_lock_irq(&css_set_lock);
+
+	if (use_task_css_set_links)
+		goto out_unlock;
+
+	use_task_css_set_links = true;
+
 	do_each_thread(g, p) {
 		WARN_ON_ONCE(!list_empty(&p->cg_list) ||
 			     task_css_set(p) != &init_css_set);
@@ -1824,9 +1840,9 @@ static void cgroup_enable_task_cg_lists(void)
 		}
 		spin_unlock(&p->sighand->siglock);
 	} while_each_thread(g, p);
-	read_unlock(&tasklist_lock);
 out_unlock:
 	spin_unlock_irq(&css_set_lock);
+	read_unlock(&tasklist_lock);
 }
 
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
@@ -1844,6 +1860,8 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	cgrp->dom_cgrp = cgrp;
 	cgrp->max_descendants = INT_MAX;
 	cgrp->max_depth = INT_MAX;
+	INIT_LIST_HEAD(&cgrp->rstat_css_list);
+	prev_cputime_init(&cgrp->prev_cputime);
 
 	for_each_subsys(ss, ssid)
 		INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
@@ -3381,7 +3399,7 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 	struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup;
 	int ret = 0;
 
-	cgroup_stat_show_cputime(seq);
+	cgroup_base_stat_cputime_show(seq);
 #ifdef CONFIG_CGROUP_SCHED
 	ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id);
 #endif
@@ -3521,6 +3539,12 @@ static int cgroup_kn_set_ugid(struct kernfs_node *kn)
 	return kernfs_setattr(kn, &iattr);
 }
 
+static void cgroup_file_notify_timer(struct timer_list *timer)
+{
+	cgroup_file_notify(container_of(timer, struct cgroup_file,
+					notify_timer));
+}
+
 static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 			   struct cftype *cft)
 {
@@ -3547,6 +3571,8 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 	if (cft->file_offset) {
 		struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
+		timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0);
+
 		spin_lock_irq(&cgroup_file_kn_lock);
 		cfile->kn = kn;
 		spin_unlock_irq(&cgroup_file_kn_lock);
@@ -3796,8 +3822,17 @@ void cgroup_file_notify(struct cgroup_file *cfile)
 	unsigned long flags;
 
 	spin_lock_irqsave(&cgroup_file_kn_lock, flags);
-	if (cfile->kn)
-		kernfs_notify(cfile->kn);
+	if (cfile->kn) {
+		unsigned long last = cfile->notified_at;
+		unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV;
+
+		if (time_in_range(jiffies, last, next)) {
+			timer_reduce(&cfile->notify_timer, next);
+		} else {
+			kernfs_notify(cfile->kn);
+			cfile->notified_at = jiffies;
+		}
+	}
 	spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
 }
 
@@ -4560,7 +4595,7 @@ static void css_free_rwork_fn(struct work_struct *work)
 			cgroup_put(cgroup_parent(cgrp));
 			kernfs_put(cgrp->kn);
 			if (cgroup_on_dfl(cgrp))
-				cgroup_stat_exit(cgrp);
+				cgroup_rstat_exit(cgrp);
 			kfree(cgrp);
 		} else {
 			/*
@@ -4587,6 +4622,11 @@ static void css_release_work_fn(struct work_struct *work)
 
 	if (ss) {
 		/* css release path */
+		if (!list_empty(&css->rstat_css_node)) {
+			cgroup_rstat_flush(cgrp);
+			list_del_rcu(&css->rstat_css_node);
+		}
+
 		cgroup_idr_replace(&ss->css_idr, NULL, css->id);
 		if (ss->css_released)
 			ss->css_released(css);
@@ -4597,7 +4637,7 @@ static void css_release_work_fn(struct work_struct *work)
 		trace_cgroup_release(cgrp);
 
 		if (cgroup_on_dfl(cgrp))
-			cgroup_stat_flush(cgrp);
+			cgroup_rstat_flush(cgrp);
 
 		for (tcgrp = cgroup_parent(cgrp); tcgrp;
 		     tcgrp = cgroup_parent(tcgrp))
@@ -4648,6 +4688,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	css->id = -1;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
+	INIT_LIST_HEAD(&css->rstat_css_node);
 	css->serial_nr = css_serial_nr_next++;
 	atomic_set(&css->online_cnt, 0);
 
@@ -4656,6 +4697,9 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 		css_get(css->parent);
 	}
 
+	if (cgroup_on_dfl(cgrp) && ss->css_rstat_flush)
+		list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list);
+
 	BUG_ON(cgroup_css(cgrp, ss));
 }
 
@@ -4757,6 +4801,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 err_list_del:
 	list_del_rcu(&css->sibling);
 err_free_css:
+	list_del_rcu(&css->rstat_css_node);
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
 	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
@@ -4785,7 +4830,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 		goto out_free_cgrp;
 
 	if (cgroup_on_dfl(parent)) {
-		ret = cgroup_stat_init(cgrp);
+		ret = cgroup_rstat_init(cgrp);
 		if (ret)
 			goto out_cancel_ref;
 	}
@@ -4850,7 +4895,7 @@ out_idr_free:
 	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
 out_stat_exit:
 	if (cgroup_on_dfl(parent))
-		cgroup_stat_exit(cgrp);
+		cgroup_rstat_exit(cgrp);
 out_cancel_ref:
 	percpu_ref_exit(&cgrp->self.refcnt);
 out_free_cgrp:
@@ -5090,10 +5135,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	for_each_css(css, ssid, cgrp)
 		kill_css(css);
 
-	/*
-	 * Remove @cgrp directory along with the base files.  @cgrp has an
-	 * extra ref on its kn.
-	 */
+	/* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */
+	css_clear_dir(&cgrp->self);
 	kernfs_remove(cgrp->kn);
 
 	if (parent && cgroup_is_threaded(cgrp))
@@ -5245,7 +5288,7 @@ int __init cgroup_init(void)
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
 
-	cgroup_stat_boot();
+	cgroup_rstat_boot();
 
 	/*
 	 * The latency of the synchronize_sched() is too high for cgroups,
@@ -5335,7 +5378,7 @@ int __init cgroup_init(void)
 	WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup"));
 	WARN_ON(register_filesystem(&cgroup_fs_type));
 	WARN_ON(register_filesystem(&cgroup2_fs_type));
-	WARN_ON(!proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations));
+	WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show));
 
 	return 0;
 }
diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c
index defad3c5e7dc..d3bbb757ee49 100644
--- a/kernel/cgroup/rdma.c
+++ b/kernel/cgroup/rdma.c
@@ -362,35 +362,32 @@ EXPORT_SYMBOL(rdmacg_unregister_device);
 static int parse_resource(char *c, int *intval)
 {
 	substring_t argstr;
-	const char **table = &rdmacg_resource_names[0];
 	char *name, *value = c;
 	size_t len;
-	int ret, i = 0;
+	int ret, i;
 
 	name = strsep(&value, "=");
 	if (!name || !value)
 		return -EINVAL;
 
-	len = strlen(value);
+	i = match_string(rdmacg_resource_names, RDMACG_RESOURCE_MAX, name);
+	if (i < 0)
+		return i;
 
-	for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
-		if (strcmp(table[i], name))
-			continue;
+	len = strlen(value);
 
-		argstr.from = value;
-		argstr.to = value + len;
+	argstr.from = value;
+	argstr.to = value + len;
 
-		ret = match_int(&argstr, intval);
-		if (ret >= 0) {
-			if (*intval < 0)
-				break;
-			return i;
-		}
-		if (strncmp(value, RDMACG_MAX_STR, len) == 0) {
-			*intval = S32_MAX;
-			return i;
-		}
-		break;
+	ret = match_int(&argstr, intval);
+	if (ret >= 0) {
+		if (*intval < 0)
+			return -EINVAL;
+		return i;
+	}
+	if (strncmp(value, RDMACG_MAX_STR, len) == 0) {
+		*intval = S32_MAX;
+		return i;
 	}
 	return -EINVAL;
 }
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
new file mode 100644
index 000000000000..d503d1a9007c
--- /dev/null
+++ b/kernel/cgroup/rstat.c
@@ -0,0 +1,416 @@
+#include "cgroup-internal.h"
+
+#include <linux/sched/cputime.h>
+
+static DEFINE_SPINLOCK(cgroup_rstat_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
+
+static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
+
+static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu)
+{
+	return per_cpu_ptr(cgrp->rstat_cpu, cpu);
+}
+
+/**
+ * cgroup_rstat_updated - keep track of updated rstat_cpu
+ * @cgrp: target cgroup
+ * @cpu: cpu on which rstat_cpu was updated
+ *
+ * @cgrp's rstat_cpu on @cpu was updated.  Put it on the parent's matching
+ * rstat_cpu->updated_children list.  See the comment on top of
+ * cgroup_rstat_cpu definition for details.
+ */
+void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
+{
+	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
+	struct cgroup *parent;
+	unsigned long flags;
+
+	/* nothing to do for root */
+	if (!cgroup_parent(cgrp))
+		return;
+
+	/*
+	 * Paired with the one in cgroup_rstat_cpu_pop_upated().  Either we
+	 * see NULL updated_next or they see our updated stat.
+	 */
+	smp_mb();
+
+	/*
+	 * Because @parent's updated_children is terminated with @parent
+	 * instead of NULL, we can tell whether @cgrp is on the list by
+	 * testing the next pointer for NULL.
+	 */
+	if (cgroup_rstat_cpu(cgrp, cpu)->updated_next)
+		return;
+
+	raw_spin_lock_irqsave(cpu_lock, flags);
+
+	/* put @cgrp and all ancestors on the corresponding updated lists */
+	for (parent = cgroup_parent(cgrp); parent;
+	     cgrp = parent, parent = cgroup_parent(cgrp)) {
+		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+		struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
+
+		/*
+		 * Both additions and removals are bottom-up.  If a cgroup
+		 * is already in the tree, all ancestors are.
+		 */
+		if (rstatc->updated_next)
+			break;
+
+		rstatc->updated_next = prstatc->updated_children;
+		prstatc->updated_children = cgrp;
+	}
+
+	raw_spin_unlock_irqrestore(cpu_lock, flags);
+}
+EXPORT_SYMBOL_GPL(cgroup_rstat_updated);
+
+/**
+ * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree
+ * @pos: current position
+ * @root: root of the tree to traversal
+ * @cpu: target cpu
+ *
+ * Walks the udpated rstat_cpu tree on @cpu from @root.  %NULL @pos starts
+ * the traversal and %NULL return indicates the end.  During traversal,
+ * each returned cgroup is unlinked from the tree.  Must be called with the
+ * matching cgroup_rstat_cpu_lock held.
+ *
+ * The only ordering guarantee is that, for a parent and a child pair
+ * covered by a given traversal, if a child is visited, its parent is
+ * guaranteed to be visited afterwards.
+ */
+static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
+						   struct cgroup *root, int cpu)
+{
+	struct cgroup_rstat_cpu *rstatc;
+	struct cgroup *parent;
+
+	if (pos == root)
+		return NULL;
+
+	/*
+	 * We're gonna walk down to the first leaf and visit/remove it.  We
+	 * can pick whatever unvisited node as the starting point.
+	 */
+	if (!pos)
+		pos = root;
+	else
+		pos = cgroup_parent(pos);
+
+	/* walk down to the first leaf */
+	while (true) {
+		rstatc = cgroup_rstat_cpu(pos, cpu);
+		if (rstatc->updated_children == pos)
+			break;
+		pos = rstatc->updated_children;
+	}
+
+	/*
+	 * Unlink @pos from the tree.  As the updated_children list is
+	 * singly linked, we have to walk it to find the removal point.
+	 * However, due to the way we traverse, @pos will be the first
+	 * child in most cases. The only exception is @root.
+	 */
+	parent = cgroup_parent(pos);
+	if (parent && rstatc->updated_next) {
+		struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
+		struct cgroup_rstat_cpu *nrstatc;
+		struct cgroup **nextp;
+
+		nextp = &prstatc->updated_children;
+		while (true) {
+			nrstatc = cgroup_rstat_cpu(*nextp, cpu);
+			if (*nextp == pos)
+				break;
+
+			WARN_ON_ONCE(*nextp == parent);
+			nextp = &nrstatc->updated_next;
+		}
+
+		*nextp = rstatc->updated_next;
+		rstatc->updated_next = NULL;
+
+		/*
+		 * Paired with the one in cgroup_rstat_cpu_updated().
+		 * Either they see NULL updated_next or we see their
+		 * updated stat.
+		 */
+		smp_mb();
+	}
+
+	return pos;
+}
+
+/* see cgroup_rstat_flush() */
+static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
+	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
+{
+	int cpu;
+
+	lockdep_assert_held(&cgroup_rstat_lock);
+
+	for_each_possible_cpu(cpu) {
+		raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock,
+						       cpu);
+		struct cgroup *pos = NULL;
+
+		raw_spin_lock(cpu_lock);
+		while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) {
+			struct cgroup_subsys_state *css;
+
+			cgroup_base_stat_flush(pos, cpu);
+
+			rcu_read_lock();
+			list_for_each_entry_rcu(css, &pos->rstat_css_list,
+						rstat_css_node)
+				css->ss->css_rstat_flush(css, cpu);
+			rcu_read_unlock();
+		}
+		raw_spin_unlock(cpu_lock);
+
+		/* if @may_sleep, play nice and yield if necessary */
+		if (may_sleep && (need_resched() ||
+				  spin_needbreak(&cgroup_rstat_lock))) {
+			spin_unlock_irq(&cgroup_rstat_lock);
+			if (!cond_resched())
+				cpu_relax();
+			spin_lock_irq(&cgroup_rstat_lock);
+		}
+	}
+}
+
+/**
+ * cgroup_rstat_flush - flush stats in @cgrp's subtree
+ * @cgrp: target cgroup
+ *
+ * Collect all per-cpu stats in @cgrp's subtree into the global counters
+ * and propagate them upwards.  After this function returns, all cgroups in
+ * the subtree have up-to-date ->stat.
+ *
+ * This also gets all cgroups in the subtree including @cgrp off the
+ * ->updated_children lists.
+ *
+ * This function may block.
+ */
+void cgroup_rstat_flush(struct cgroup *cgrp)
+{
+	might_sleep();
+
+	spin_lock_irq(&cgroup_rstat_lock);
+	cgroup_rstat_flush_locked(cgrp, true);
+	spin_unlock_irq(&cgroup_rstat_lock);
+}
+
+/**
+ * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush()
+ * @cgrp: target cgroup
+ *
+ * This function can be called from any context.
+ */
+void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cgroup_rstat_lock, flags);
+	cgroup_rstat_flush_locked(cgrp, false);
+	spin_unlock_irqrestore(&cgroup_rstat_lock, flags);
+}
+
+/**
+ * cgroup_rstat_flush_begin - flush stats in @cgrp's subtree and hold
+ * @cgrp: target cgroup
+ *
+ * Flush stats in @cgrp's subtree and prevent further flushes.  Must be
+ * paired with cgroup_rstat_flush_release().
+ *
+ * This function may block.
+ */
+void cgroup_rstat_flush_hold(struct cgroup *cgrp)
+	__acquires(&cgroup_rstat_lock)
+{
+	might_sleep();
+	spin_lock_irq(&cgroup_rstat_lock);
+	cgroup_rstat_flush_locked(cgrp, true);
+}
+
+/**
+ * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold()
+ */
+void cgroup_rstat_flush_release(void)
+	__releases(&cgroup_rstat_lock)
+{
+	spin_unlock_irq(&cgroup_rstat_lock);
+}
+
+int cgroup_rstat_init(struct cgroup *cgrp)
+{
+	int cpu;
+
+	/* the root cgrp has rstat_cpu preallocated */
+	if (!cgrp->rstat_cpu) {
+		cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu);
+		if (!cgrp->rstat_cpu)
+			return -ENOMEM;
+	}
+
+	/* ->updated_children list is self terminated */
+	for_each_possible_cpu(cpu) {
+		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+
+		rstatc->updated_children = cgrp;
+		u64_stats_init(&rstatc->bsync);
+	}
+
+	return 0;
+}
+
+void cgroup_rstat_exit(struct cgroup *cgrp)
+{
+	int cpu;
+
+	cgroup_rstat_flush(cgrp);
+
+	/* sanity check */
+	for_each_possible_cpu(cpu) {
+		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+
+		if (WARN_ON_ONCE(rstatc->updated_children != cgrp) ||
+		    WARN_ON_ONCE(rstatc->updated_next))
+			return;
+	}
+
+	free_percpu(cgrp->rstat_cpu);
+	cgrp->rstat_cpu = NULL;
+}
+
+void __init cgroup_rstat_boot(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu));
+
+	BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp));
+}
+
+/*
+ * Functions for cgroup basic resource statistics implemented on top of
+ * rstat.
+ */
+static void cgroup_base_stat_accumulate(struct cgroup_base_stat *dst_bstat,
+					struct cgroup_base_stat *src_bstat)
+{
+	dst_bstat->cputime.utime += src_bstat->cputime.utime;
+	dst_bstat->cputime.stime += src_bstat->cputime.stime;
+	dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime;
+}
+
+static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
+{
+	struct cgroup *parent = cgroup_parent(cgrp);
+	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+	struct task_cputime *last_cputime = &rstatc->last_bstat.cputime;
+	struct task_cputime cputime;
+	struct cgroup_base_stat delta;
+	unsigned seq;
+
+	/* fetch the current per-cpu values */
+	do {
+		seq = __u64_stats_fetch_begin(&rstatc->bsync);
+		cputime = rstatc->bstat.cputime;
+	} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
+
+	/* calculate the delta to propgate */
+	delta.cputime.utime = cputime.utime - last_cputime->utime;
+	delta.cputime.stime = cputime.stime - last_cputime->stime;
+	delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime -
+					 last_cputime->sum_exec_runtime;
+	*last_cputime = cputime;
+
+	/* transfer the pending stat into delta */
+	cgroup_base_stat_accumulate(&delta, &cgrp->pending_bstat);
+	memset(&cgrp->pending_bstat, 0, sizeof(cgrp->pending_bstat));
+
+	/* propagate delta into the global stat and the parent's pending */
+	cgroup_base_stat_accumulate(&cgrp->bstat, &delta);
+	if (parent)
+		cgroup_base_stat_accumulate(&parent->pending_bstat, &delta);
+}
+
+static struct cgroup_rstat_cpu *
+cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp)
+{
+	struct cgroup_rstat_cpu *rstatc;
+
+	rstatc = get_cpu_ptr(cgrp->rstat_cpu);
+	u64_stats_update_begin(&rstatc->bsync);
+	return rstatc;
+}
+
+static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp,
+						 struct cgroup_rstat_cpu *rstatc)
+{
+	u64_stats_update_end(&rstatc->bsync);
+	cgroup_rstat_updated(cgrp, smp_processor_id());
+	put_cpu_ptr(rstatc);
+}
+
+void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec)
+{
+	struct cgroup_rstat_cpu *rstatc;
+
+	rstatc = cgroup_base_stat_cputime_account_begin(cgrp);
+	rstatc->bstat.cputime.sum_exec_runtime += delta_exec;
+	cgroup_base_stat_cputime_account_end(cgrp, rstatc);
+}
+
+void __cgroup_account_cputime_field(struct cgroup *cgrp,
+				    enum cpu_usage_stat index, u64 delta_exec)
+{
+	struct cgroup_rstat_cpu *rstatc;
+
+	rstatc = cgroup_base_stat_cputime_account_begin(cgrp);
+
+	switch (index) {
+	case CPUTIME_USER:
+	case CPUTIME_NICE:
+		rstatc->bstat.cputime.utime += delta_exec;
+		break;
+	case CPUTIME_SYSTEM:
+	case CPUTIME_IRQ:
+	case CPUTIME_SOFTIRQ:
+		rstatc->bstat.cputime.stime += delta_exec;
+		break;
+	default:
+		break;
+	}
+
+	cgroup_base_stat_cputime_account_end(cgrp, rstatc);
+}
+
+void cgroup_base_stat_cputime_show(struct seq_file *seq)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	u64 usage, utime, stime;
+
+	if (!cgroup_parent(cgrp))
+		return;
+
+	cgroup_rstat_flush_hold(cgrp);
+	usage = cgrp->bstat.cputime.sum_exec_runtime;
+	cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime);
+	cgroup_rstat_flush_release();
+
+	do_div(usage, NSEC_PER_USEC);
+	do_div(utime, NSEC_PER_USEC);
+	do_div(stime, NSEC_PER_USEC);
+
+	seq_printf(seq, "usage_usec %llu\n"
+		   "user_usec %llu\n"
+		   "system_usec %llu\n",
+		   usage, utime, stime);
+}
diff --git a/kernel/cgroup/stat.c b/kernel/cgroup/stat.c
deleted file mode 100644
index 1e111dd455c4..000000000000
--- a/kernel/cgroup/stat.c
+++ /dev/null
@@ -1,338 +0,0 @@
-#include "cgroup-internal.h"
-
-#include <linux/sched/cputime.h>
-
-static DEFINE_MUTEX(cgroup_stat_mutex);
-static DEFINE_PER_CPU(raw_spinlock_t, cgroup_cpu_stat_lock);
-
-static struct cgroup_cpu_stat *cgroup_cpu_stat(struct cgroup *cgrp, int cpu)
-{
-	return per_cpu_ptr(cgrp->cpu_stat, cpu);
-}
-
-/**
- * cgroup_cpu_stat_updated - keep track of updated cpu_stat
- * @cgrp: target cgroup
- * @cpu: cpu on which cpu_stat was updated
- *
- * @cgrp's cpu_stat on @cpu was updated.  Put it on the parent's matching
- * cpu_stat->updated_children list.  See the comment on top of
- * cgroup_cpu_stat definition for details.
- */
-static void cgroup_cpu_stat_updated(struct cgroup *cgrp, int cpu)
-{
-	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_cpu_stat_lock, cpu);
-	struct cgroup *parent;
-	unsigned long flags;
-
-	/*
-	 * Speculative already-on-list test.  This may race leading to
-	 * temporary inaccuracies, which is fine.
-	 *
-	 * Because @parent's updated_children is terminated with @parent
-	 * instead of NULL, we can tell whether @cgrp is on the list by
-	 * testing the next pointer for NULL.
-	 */
-	if (cgroup_cpu_stat(cgrp, cpu)->updated_next)
-		return;
-
-	raw_spin_lock_irqsave(cpu_lock, flags);
-
-	/* put @cgrp and all ancestors on the corresponding updated lists */
-	for (parent = cgroup_parent(cgrp); parent;
-	     cgrp = parent, parent = cgroup_parent(cgrp)) {
-		struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu);
-		struct cgroup_cpu_stat *pcstat = cgroup_cpu_stat(parent, cpu);
-
-		/*
-		 * Both additions and removals are bottom-up.  If a cgroup
-		 * is already in the tree, all ancestors are.
-		 */
-		if (cstat->updated_next)
-			break;
-
-		cstat->updated_next = pcstat->updated_children;
-		pcstat->updated_children = cgrp;
-	}
-
-	raw_spin_unlock_irqrestore(cpu_lock, flags);
-}
-
-/**
- * cgroup_cpu_stat_pop_updated - iterate and dismantle cpu_stat updated tree
- * @pos: current position
- * @root: root of the tree to traversal
- * @cpu: target cpu
- *
- * Walks the udpated cpu_stat tree on @cpu from @root.  %NULL @pos starts
- * the traversal and %NULL return indicates the end.  During traversal,
- * each returned cgroup is unlinked from the tree.  Must be called with the
- * matching cgroup_cpu_stat_lock held.
- *
- * The only ordering guarantee is that, for a parent and a child pair
- * covered by a given traversal, if a child is visited, its parent is
- * guaranteed to be visited afterwards.
- */
-static struct cgroup *cgroup_cpu_stat_pop_updated(struct cgroup *pos,
-						  struct cgroup *root, int cpu)
-{
-	struct cgroup_cpu_stat *cstat;
-	struct cgroup *parent;
-
-	if (pos == root)
-		return NULL;
-
-	/*
-	 * We're gonna walk down to the first leaf and visit/remove it.  We
-	 * can pick whatever unvisited node as the starting point.
-	 */
-	if (!pos)
-		pos = root;
-	else
-		pos = cgroup_parent(pos);
-
-	/* walk down to the first leaf */
-	while (true) {
-		cstat = cgroup_cpu_stat(pos, cpu);
-		if (cstat->updated_children == pos)
-			break;
-		pos = cstat->updated_children;
-	}
-
-	/*
-	 * Unlink @pos from the tree.  As the updated_children list is
-	 * singly linked, we have to walk it to find the removal point.
-	 * However, due to the way we traverse, @pos will be the first
-	 * child in most cases. The only exception is @root.
-	 */
-	parent = cgroup_parent(pos);
-	if (parent && cstat->updated_next) {
-		struct cgroup_cpu_stat *pcstat = cgroup_cpu_stat(parent, cpu);
-		struct cgroup_cpu_stat *ncstat;
-		struct cgroup **nextp;
-
-		nextp = &pcstat->updated_children;
-		while (true) {
-			ncstat = cgroup_cpu_stat(*nextp, cpu);
-			if (*nextp == pos)
-				break;
-
-			WARN_ON_ONCE(*nextp == parent);
-			nextp = &ncstat->updated_next;
-		}
-
-		*nextp = cstat->updated_next;
-		cstat->updated_next = NULL;
-	}
-
-	return pos;
-}
-
-static void cgroup_stat_accumulate(struct cgroup_stat *dst_stat,
-				   struct cgroup_stat *src_stat)
-{
-	dst_stat->cputime.utime += src_stat->cputime.utime;
-	dst_stat->cputime.stime += src_stat->cputime.stime;
-	dst_stat->cputime.sum_exec_runtime += src_stat->cputime.sum_exec_runtime;
-}
-
-static void cgroup_cpu_stat_flush_one(struct cgroup *cgrp, int cpu)
-{
-	struct cgroup *parent = cgroup_parent(cgrp);
-	struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu);
-	struct task_cputime *last_cputime = &cstat->last_cputime;
-	struct task_cputime cputime;
-	struct cgroup_stat delta;
-	unsigned seq;
-
-	lockdep_assert_held(&cgroup_stat_mutex);
-
-	/* fetch the current per-cpu values */
-	do {
-		seq = __u64_stats_fetch_begin(&cstat->sync);
-		cputime = cstat->cputime;
-	} while (__u64_stats_fetch_retry(&cstat->sync, seq));
-
-	/* accumulate the deltas to propgate */
-	delta.cputime.utime = cputime.utime - last_cputime->utime;
-	delta.cputime.stime = cputime.stime - last_cputime->stime;
-	delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime -
-					 last_cputime->sum_exec_runtime;
-	*last_cputime = cputime;
-
-	/* transfer the pending stat into delta */
-	cgroup_stat_accumulate(&delta, &cgrp->pending_stat);
-	memset(&cgrp->pending_stat, 0, sizeof(cgrp->pending_stat));
-
-	/* propagate delta into the global stat and the parent's pending */
-	cgroup_stat_accumulate(&cgrp->stat, &delta);
-	if (parent)
-		cgroup_stat_accumulate(&parent->pending_stat, &delta);
-}
-
-/* see cgroup_stat_flush() */
-static void cgroup_stat_flush_locked(struct cgroup *cgrp)
-{
-	int cpu;
-
-	lockdep_assert_held(&cgroup_stat_mutex);
-
-	for_each_possible_cpu(cpu) {
-		raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_cpu_stat_lock, cpu);
-		struct cgroup *pos = NULL;
-
-		raw_spin_lock_irq(cpu_lock);
-		while ((pos = cgroup_cpu_stat_pop_updated(pos, cgrp, cpu)))
-			cgroup_cpu_stat_flush_one(pos, cpu);
-		raw_spin_unlock_irq(cpu_lock);
-	}
-}
-
-/**
- * cgroup_stat_flush - flush stats in @cgrp's subtree
- * @cgrp: target cgroup
- *
- * Collect all per-cpu stats in @cgrp's subtree into the global counters
- * and propagate them upwards.  After this function returns, all cgroups in
- * the subtree have up-to-date ->stat.
- *
- * This also gets all cgroups in the subtree including @cgrp off the
- * ->updated_children lists.
- */
-void cgroup_stat_flush(struct cgroup *cgrp)
-{
-	mutex_lock(&cgroup_stat_mutex);
-	cgroup_stat_flush_locked(cgrp);
-	mutex_unlock(&cgroup_stat_mutex);
-}
-
-static struct cgroup_cpu_stat *cgroup_cpu_stat_account_begin(struct cgroup *cgrp)
-{
-	struct cgroup_cpu_stat *cstat;
-
-	cstat = get_cpu_ptr(cgrp->cpu_stat);
-	u64_stats_update_begin(&cstat->sync);
-	return cstat;
-}
-
-static void cgroup_cpu_stat_account_end(struct cgroup *cgrp,
-					struct cgroup_cpu_stat *cstat)
-{
-	u64_stats_update_end(&cstat->sync);
-	cgroup_cpu_stat_updated(cgrp, smp_processor_id());
-	put_cpu_ptr(cstat);
-}
-
-void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec)
-{
-	struct cgroup_cpu_stat *cstat;
-
-	cstat = cgroup_cpu_stat_account_begin(cgrp);
-	cstat->cputime.sum_exec_runtime += delta_exec;
-	cgroup_cpu_stat_account_end(cgrp, cstat);
-}
-
-void __cgroup_account_cputime_field(struct cgroup *cgrp,
-				    enum cpu_usage_stat index, u64 delta_exec)
-{
-	struct cgroup_cpu_stat *cstat;
-
-	cstat = cgroup_cpu_stat_account_begin(cgrp);
-
-	switch (index) {
-	case CPUTIME_USER:
-	case CPUTIME_NICE:
-		cstat->cputime.utime += delta_exec;
-		break;
-	case CPUTIME_SYSTEM:
-	case CPUTIME_IRQ:
-	case CPUTIME_SOFTIRQ:
-		cstat->cputime.stime += delta_exec;
-		break;
-	default:
-		break;
-	}
-
-	cgroup_cpu_stat_account_end(cgrp, cstat);
-}
-
-void cgroup_stat_show_cputime(struct seq_file *seq)
-{
-	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	u64 usage, utime, stime;
-
-	if (!cgroup_parent(cgrp))
-		return;
-
-	mutex_lock(&cgroup_stat_mutex);
-
-	cgroup_stat_flush_locked(cgrp);
-
-	usage = cgrp->stat.cputime.sum_exec_runtime;
-	cputime_adjust(&cgrp->stat.cputime, &cgrp->stat.prev_cputime,
-		       &utime, &stime);
-
-	mutex_unlock(&cgroup_stat_mutex);
-
-	do_div(usage, NSEC_PER_USEC);
-	do_div(utime, NSEC_PER_USEC);
-	do_div(stime, NSEC_PER_USEC);
-
-	seq_printf(seq, "usage_usec %llu\n"
-		   "user_usec %llu\n"
-		   "system_usec %llu\n",
-		   usage, utime, stime);
-}
-
-int cgroup_stat_init(struct cgroup *cgrp)
-{
-	int cpu;
-
-	/* the root cgrp has cpu_stat preallocated */
-	if (!cgrp->cpu_stat) {
-		cgrp->cpu_stat = alloc_percpu(struct cgroup_cpu_stat);
-		if (!cgrp->cpu_stat)
-			return -ENOMEM;
-	}
-
-	/* ->updated_children list is self terminated */
-	for_each_possible_cpu(cpu) {
-		struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu);
-
-		cstat->updated_children = cgrp;
-		u64_stats_init(&cstat->sync);
-	}
-
-	prev_cputime_init(&cgrp->stat.prev_cputime);
-
-	return 0;
-}
-
-void cgroup_stat_exit(struct cgroup *cgrp)
-{
-	int cpu;
-
-	cgroup_stat_flush(cgrp);
-
-	/* sanity check */
-	for_each_possible_cpu(cpu) {
-		struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu);
-
-		if (WARN_ON_ONCE(cstat->updated_children != cgrp) ||
-		    WARN_ON_ONCE(cstat->updated_next))
-			return;
-	}
-
-	free_percpu(cgrp->cpu_stat);
-	cgrp->cpu_stat = NULL;
-}
-
-void __init cgroup_stat_boot(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		raw_spin_lock_init(per_cpu_ptr(&cgroup_cpu_stat_lock, cpu));
-
-	BUG_ON(cgroup_stat_init(&cgrp_dfl_root.cgrp));
-}
diff --git a/kernel/compat.c b/kernel/compat.c
index 6d21894806b4..702aa846ddac 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -34,6 +34,7 @@ int compat_get_timex(struct timex *txc, const struct compat_timex __user *utp)
 {
 	struct compat_timex tx32;
 
+	memset(txc, 0, sizeof(struct timex));
 	if (copy_from_user(&tx32, utp, sizeof(struct compat_timex)))
 		return -EFAULT;
 
@@ -120,50 +121,6 @@ static int __compat_put_timespec(const struct timespec *ts, struct compat_timesp
 			__put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
 
-static int __compat_get_timespec64(struct timespec64 *ts64,
-				   const struct compat_timespec __user *cts)
-{
-	struct compat_timespec ts;
-	int ret;
-
-	ret = copy_from_user(&ts, cts, sizeof(ts));
-	if (ret)
-		return -EFAULT;
-
-	ts64->tv_sec = ts.tv_sec;
-	ts64->tv_nsec = ts.tv_nsec;
-
-	return 0;
-}
-
-static int __compat_put_timespec64(const struct timespec64 *ts64,
-				   struct compat_timespec __user *cts)
-{
-	struct compat_timespec ts = {
-		.tv_sec = ts64->tv_sec,
-		.tv_nsec = ts64->tv_nsec
-	};
-	return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0;
-}
-
-int compat_get_timespec64(struct timespec64 *ts, const void __user *uts)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0;
-	else
-		return __compat_get_timespec64(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_get_timespec64);
-
-int compat_put_timespec64(const struct timespec64 *ts, void __user *uts)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0;
-	else
-		return __compat_put_timespec64(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_put_timespec64);
-
 int compat_get_timeval(struct timeval *tv, const void __user *utv)
 {
 	if (COMPAT_USE_64BIT_TIME)
@@ -367,6 +324,14 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t,  pid, unsigned int, len,
 	return ret;
 }
 
+/* Todo: Delete these extern declarations when get/put_compat_itimerspec64()
+ * are moved to kernel/time/time.c .
+ */
+extern int __compat_get_timespec64(struct timespec64 *ts64,
+				   const struct compat_timespec __user *cts);
+extern int __compat_put_timespec64(const struct timespec64 *ts64,
+				   struct compat_timespec __user *cts);
+
 int get_compat_itimerspec64(struct itimerspec64 *its,
 			const struct compat_itimerspec __user *uits)
 {
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index e2764d767f18..ca8ac2824f0b 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -44,23 +44,24 @@ void __delayacct_tsk_init(struct task_struct *tsk)
 {
 	tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL);
 	if (tsk->delays)
-		spin_lock_init(&tsk->delays->lock);
+		raw_spin_lock_init(&tsk->delays->lock);
 }
 
 /*
  * Finish delay accounting for a statistic using its timestamps (@start),
  * accumalator (@total) and @count
  */
-static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count)
+static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total,
+			  u32 *count)
 {
 	s64 ns = ktime_get_ns() - *start;
 	unsigned long flags;
 
 	if (ns > 0) {
-		spin_lock_irqsave(lock, flags);
+		raw_spin_lock_irqsave(lock, flags);
 		*total += ns;
 		(*count)++;
-		spin_unlock_irqrestore(lock, flags);
+		raw_spin_unlock_irqrestore(lock, flags);
 	}
 }
 
@@ -127,7 +128,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 
 	/* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */
 
-	spin_lock_irqsave(&tsk->delays->lock, flags);
+	raw_spin_lock_irqsave(&tsk->delays->lock, flags);
 	tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
 	d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
 	tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
@@ -137,7 +138,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	d->blkio_count += tsk->delays->blkio_count;
 	d->swapin_count += tsk->delays->swapin_count;
 	d->freepages_count += tsk->delays->freepages_count;
-	spin_unlock_irqrestore(&tsk->delays->lock, flags);
+	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 	return 0;
 }
@@ -147,10 +148,10 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk)
 	__u64 ret;
 	unsigned long flags;
 
-	spin_lock_irqsave(&tsk->delays->lock, flags);
+	raw_spin_lock_irqsave(&tsk->delays->lock, flags);
 	ret = nsec_to_clock_t(tsk->delays->blkio_delay +
 				tsk->delays->swapin_delay);
-	spin_unlock_irqrestore(&tsk->delays->lock, flags);
+	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 	return ret;
 }
 
diff --git a/kernel/dma.c b/kernel/dma.c
index 3506fc34a712..40f152936316 100644
--- a/kernel/dma.c
+++ b/kernel/dma.c
@@ -135,21 +135,9 @@ static int proc_dma_show(struct seq_file *m, void *v)
 }
 #endif /* MAX_DMA_CHANNELS */
 
-static int proc_dma_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, proc_dma_show, NULL);
-}
-
-static const struct file_operations proc_dma_operations = {
-	.open		= proc_dma_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_dma_init(void)
 {
-	proc_create("dma", 0, NULL, &proc_dma_operations);
+	proc_create_single("dma", 0, NULL, proc_dma_show);
 	return 0;
 }
 
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 772a43fea825..c187aa3df3c8 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -119,23 +119,20 @@ int get_callchain_buffers(int event_max_stack)
 		goto exit;
 	}
 
-	if (count > 1) {
-		/* If the allocation failed, give up */
-		if (!callchain_cpus_entries)
-			err = -ENOMEM;
-		/*
-		 * If requesting per event more than the global cap,
-		 * return a different error to help userspace figure
-		 * this out.
-		 *
-		 * And also do it here so that we have &callchain_mutex held.
-		 */
-		if (event_max_stack > sysctl_perf_event_max_stack)
-			err = -EOVERFLOW;
+	/*
+	 * If requesting per event more than the global cap,
+	 * return a different error to help userspace figure
+	 * this out.
+	 *
+	 * And also do it here so that we have &callchain_mutex held.
+	 */
+	if (event_max_stack > sysctl_perf_event_max_stack) {
+		err = -EOVERFLOW;
 		goto exit;
 	}
 
-	err = alloc_callchain_buffers();
+	if (count == 1)
+		err = alloc_callchain_buffers();
 exit:
 	if (err)
 		atomic_dec(&nr_callchain_events);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2d5fe26551f8..08f5e1b42b43 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5120,6 +5120,8 @@ static long perf_compat_ioctl(struct file *file, unsigned int cmd,
 	switch (_IOC_NR(cmd)) {
 	case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
 	case _IOC_NR(PERF_EVENT_IOC_ID):
+	case _IOC_NR(PERF_EVENT_IOC_QUERY_BPF):
+	case _IOC_NR(PERF_EVENT_IOC_MODIFY_ATTRIBUTES):
 		/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
 		if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
 			cmd &= ~IOCSIZE_MASK;
@@ -6668,7 +6670,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		if (filter->inode) {
+		if (filter->path.dentry) {
 			event->addr_filters_offs[count] = 0;
 			restart++;
 		}
@@ -7333,7 +7335,7 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 				     struct file *file, unsigned long offset,
 				     unsigned long size)
 {
-	if (filter->inode != file_inode(file))
+	if (d_inode(filter->path.dentry) != file_inode(file))
 		return false;
 
 	if (filter->offset > offset + size)
@@ -7587,6 +7589,10 @@ static void perf_event_switch(struct task_struct *task,
 		},
 	};
 
+	if (!sched_in && task->state == TASK_RUNNING)
+		switch_event.event_id.header.misc |=
+				PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
+
 	perf_iterate_sb(perf_event_switch_output,
 		       &switch_event,
 		       NULL);
@@ -8682,8 +8688,7 @@ static void free_filters_list(struct list_head *filters)
 	struct perf_addr_filter *filter, *iter;
 
 	list_for_each_entry_safe(filter, iter, filters, entry) {
-		if (filter->inode)
-			iput(filter->inode);
+		path_put(&filter->path);
 		list_del(&filter->entry);
 		kfree(filter);
 	}
@@ -8780,7 +8785,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 		 * Adjust base offset if the filter is associated to a binary
 		 * that needs to be mapped:
 		 */
-		if (filter->inode)
+		if (filter->path.dentry)
 			event->addr_filters_offs[count] =
 				perf_addr_filter_apply(filter, mm);
 
@@ -8854,7 +8859,6 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 {
 	struct perf_addr_filter *filter = NULL;
 	char *start, *orig, *filename = NULL;
-	struct path path;
 	substring_t args[MAX_OPT_ARGS];
 	int state = IF_STATE_ACTION, token;
 	unsigned int kernel = 0;
@@ -8967,19 +8971,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 					goto fail_free_name;
 
 				/* look up the path and grab its inode */
-				ret = kern_path(filename, LOOKUP_FOLLOW, &path);
+				ret = kern_path(filename, LOOKUP_FOLLOW,
+						&filter->path);
 				if (ret)
 					goto fail_free_name;
 
-				filter->inode = igrab(d_inode(path.dentry));
-				path_put(&path);
 				kfree(filename);
 				filename = NULL;
 
 				ret = -EINVAL;
-				if (!filter->inode ||
-				    !S_ISREG(filter->inode->i_mode))
-					/* free_filters_list() will iput() */
+				if (!filter->path.dentry ||
+				    !S_ISREG(d_inode(filter->path.dentry)
+					     ->i_mode))
 					goto fail;
 
 				event->addr_filters.nr_file_filters++;
@@ -10205,9 +10208,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 		 * __u16 sample size limit.
 		 */
 		if (attr->sample_stack_user >= USHRT_MAX)
-			ret = -EINVAL;
+			return -EINVAL;
 		else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
-			ret = -EINVAL;
+			return -EINVAL;
 	}
 
 	if (!attr->sample_max_stack)
@@ -10517,19 +10520,20 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (pmu->task_ctx_nr == perf_sw_context)
 		event->event_caps |= PERF_EV_CAP_SOFTWARE;
 
-	if (group_leader &&
-	    (is_software_event(event) != is_software_event(group_leader))) {
-		if (is_software_event(event)) {
+	if (group_leader) {
+		if (is_software_event(event) &&
+		    !in_software_context(group_leader)) {
 			/*
-			 * If event and group_leader are not both a software
-			 * event, and event is, then group leader is not.
+			 * If the event is a sw event, but the group_leader
+			 * is on hw context.
 			 *
-			 * Allow the addition of software events to !software
-			 * groups, this is safe because software events never
-			 * fail to schedule.
+			 * Allow the addition of software events to hw
+			 * groups, this is safe because software events
+			 * never fail to schedule.
 			 */
-			pmu = group_leader->pmu;
-		} else if (is_software_event(group_leader) &&
+			pmu = group_leader->ctx->pmu;
+		} else if (!is_software_event(event) &&
+			   is_software_event(group_leader) &&
 			   (group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
 			/*
 			 * In case the group is a pure software group, and we
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 6c6b3c48db71..1d8ca9ea9979 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/circ_buf.h>
 #include <linux/poll.h>
+#include <linux/nospec.h>
 
 #include "internal.h"
 
@@ -867,8 +868,10 @@ perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
 			return NULL;
 
 		/* AUX space */
-		if (pgoff >= rb->aux_pgoff)
-			return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]);
+		if (pgoff >= rb->aux_pgoff) {
+			int aux_pgoff = array_index_nospec(pgoff - rb->aux_pgoff, rb->aux_nr_pages);
+			return virt_to_page(rb->aux_pages[aux_pgoff]);
+		}
 	}
 
 	return __perf_mmap_to_page(rb, pgoff);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ce6848e46e94..1725b902983f 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -491,7 +491,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 	if (!uprobe)
 		return NULL;
 
-	uprobe->inode = igrab(inode);
+	uprobe->inode = inode;
 	uprobe->offset = offset;
 	init_rwsem(&uprobe->register_rwsem);
 	init_rwsem(&uprobe->consumer_rwsem);
@@ -502,7 +502,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 	if (cur_uprobe) {
 		kfree(uprobe);
 		uprobe = cur_uprobe;
-		iput(inode);
 	}
 
 	return uprobe;
@@ -701,7 +700,6 @@ static void delete_uprobe(struct uprobe *uprobe)
 	rb_erase(&uprobe->rb_node, &uprobes_tree);
 	spin_unlock(&uprobes_treelock);
 	RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */
-	iput(uprobe->inode);
 	put_uprobe(uprobe);
 }
 
@@ -873,7 +871,8 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u
  * tuple).  Creation refcount stops uprobe_unregister from freeing the
  * @uprobe even before the register operation is complete. Creation
  * refcount is released when the last @uc for the @uprobe
- * unregisters.
+ * unregisters. Caller of uprobe_register() is required to keep @inode
+ * (and the containing mount) referenced.
  *
  * Return errno if it cannot successully install probes
  * else return 0 (success)
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index a5697119290e..33f07c5f2515 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -27,21 +27,9 @@ static int execdomains_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int execdomains_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, execdomains_proc_show, NULL);
-}
-
-static const struct file_operations execdomains_proc_fops = {
-	.open		= execdomains_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int __init proc_execdomains_init(void)
 {
-	proc_create("execdomains", 0, NULL, &execdomains_proc_fops);
+	proc_create_single("execdomains", 0, NULL, execdomains_proc_show);
 	return 0;
 }
 module_init(proc_execdomains_init);
diff --git a/kernel/fork.c b/kernel/fork.c
index 242c8c93d285..a5d21c42acfc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -216,10 +216,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 		if (!s)
 			continue;
 
-#ifdef CONFIG_DEBUG_KMEMLEAK
 		/* Clear stale pointers from reused stack. */
 		memset(s->addr, 0, THREAD_SIZE);
-#endif
+
 		tsk->stack_vm_area = s;
 		return s->addr;
 	}
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index fc4f361a86bb..dd20d0d528d4 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -1,11 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * Copyright (C) 2017 Bartosz Golaszewski <brgl@bgdev.pl>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
+ * Copyright (C) 2017-2018 Bartosz Golaszewski <brgl@bgdev.pl>
  */
 
 #include <linux/slab.h>
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 2a8571f72b17..4ca2fd46645d 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -76,6 +76,19 @@ static inline void irq_chip_write_msi_msg(struct irq_data *data,
 	data->chip->irq_write_msi_msg(data, msg);
 }
 
+static void msi_check_level(struct irq_domain *domain, struct msi_msg *msg)
+{
+	struct msi_domain_info *info = domain->host_data;
+
+	/*
+	 * If the MSI provider has messed with the second message and
+	 * not advertized that it is level-capable, signal the breakage.
+	 */
+	WARN_ON(!((info->flags & MSI_FLAG_LEVEL_CAPABLE) &&
+		  (info->chip->flags & IRQCHIP_SUPPORTS_LEVEL_MSI)) &&
+		(msg[1].address_lo || msg[1].address_hi || msg[1].data));
+}
+
 /**
  * msi_domain_set_affinity - Generic affinity setter function for MSI domains
  * @irq_data:	The irq data associated to the interrupt
@@ -89,13 +102,14 @@ int msi_domain_set_affinity(struct irq_data *irq_data,
 			    const struct cpumask *mask, bool force)
 {
 	struct irq_data *parent = irq_data->parent_data;
-	struct msi_msg msg;
+	struct msi_msg msg[2] = { [1] = { }, };
 	int ret;
 
 	ret = parent->chip->irq_set_affinity(parent, mask, force);
 	if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
-		BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
-		irq_chip_write_msi_msg(irq_data, &msg);
+		BUG_ON(irq_chip_compose_msi_msg(irq_data, msg));
+		msi_check_level(irq_data->domain, msg);
+		irq_chip_write_msi_msg(irq_data, msg);
 	}
 
 	return ret;
@@ -104,20 +118,21 @@ int msi_domain_set_affinity(struct irq_data *irq_data,
 static int msi_domain_activate(struct irq_domain *domain,
 			       struct irq_data *irq_data, bool early)
 {
-	struct msi_msg msg;
+	struct msi_msg msg[2] = { [1] = { }, };
 
-	BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
-	irq_chip_write_msi_msg(irq_data, &msg);
+	BUG_ON(irq_chip_compose_msi_msg(irq_data, msg));
+	msi_check_level(irq_data->domain, msg);
+	irq_chip_write_msi_msg(irq_data, msg);
 	return 0;
 }
 
 static void msi_domain_deactivate(struct irq_domain *domain,
 				  struct irq_data *irq_data)
 {
-	struct msi_msg msg;
+	struct msi_msg msg[2];
 
-	memset(&msg, 0, sizeof(msg));
-	irq_chip_write_msi_msg(irq_data, &msg);
+	memset(msg, 0, sizeof(msg));
+	irq_chip_write_msi_msg(irq_data, msg);
 }
 
 static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 7cb091d81d91..37eda10f5c36 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -185,11 +185,6 @@ static int irq_affinity_list_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode));
 }
 
-static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, irq_affinity_hint_proc_show, PDE_DATA(inode));
-}
-
 static const struct file_operations irq_affinity_proc_fops = {
 	.open		= irq_affinity_proc_open,
 	.read		= seq_read,
@@ -198,13 +193,6 @@ static const struct file_operations irq_affinity_proc_fops = {
 	.write		= irq_affinity_proc_write,
 };
 
-static const struct file_operations irq_affinity_hint_proc_fops = {
-	.open		= irq_affinity_hint_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static const struct file_operations irq_affinity_list_proc_fops = {
 	.open		= irq_affinity_list_proc_open,
 	.read		= seq_read,
@@ -223,32 +211,6 @@ static int irq_effective_aff_list_proc_show(struct seq_file *m, void *v)
 {
 	return show_irq_affinity(EFFECTIVE_LIST, m);
 }
-
-static int irq_effective_aff_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, irq_effective_aff_proc_show, PDE_DATA(inode));
-}
-
-static int irq_effective_aff_list_proc_open(struct inode *inode,
-					    struct file *file)
-{
-	return single_open(file, irq_effective_aff_list_proc_show,
-			   PDE_DATA(inode));
-}
-
-static const struct file_operations irq_effective_aff_proc_fops = {
-	.open		= irq_effective_aff_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static const struct file_operations irq_effective_aff_list_proc_fops = {
-	.open		= irq_effective_aff_list_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 static int default_affinity_show(struct seq_file *m, void *v)
@@ -313,18 +275,6 @@ static int irq_node_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "%d\n", irq_desc_get_node(desc));
 	return 0;
 }
-
-static int irq_node_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, irq_node_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations irq_node_proc_fops = {
-	.open		= irq_node_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 static int irq_spurious_proc_show(struct seq_file *m, void *v)
@@ -337,18 +287,6 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int irq_spurious_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, irq_spurious_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations irq_spurious_proc_fops = {
-	.open		= irq_spurious_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 #define MAX_NAMELEN 128
 
 static int name_unique(unsigned int irq, struct irqaction *new_action)
@@ -421,24 +359,24 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 			 &irq_affinity_proc_fops, irqp);
 
 	/* create /proc/irq/<irq>/affinity_hint */
-	proc_create_data("affinity_hint", 0444, desc->dir,
-			 &irq_affinity_hint_proc_fops, irqp);
+	proc_create_single_data("affinity_hint", 0444, desc->dir,
+			irq_affinity_hint_proc_show, irqp);
 
 	/* create /proc/irq/<irq>/smp_affinity_list */
 	proc_create_data("smp_affinity_list", 0644, desc->dir,
 			 &irq_affinity_list_proc_fops, irqp);
 
-	proc_create_data("node", 0444, desc->dir,
-			 &irq_node_proc_fops, irqp);
+	proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show,
+			irqp);
 # ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
-	proc_create_data("effective_affinity", 0444, desc->dir,
-			 &irq_effective_aff_proc_fops, irqp);
-	proc_create_data("effective_affinity_list", 0444, desc->dir,
-			 &irq_effective_aff_list_proc_fops, irqp);
+	proc_create_single_data("effective_affinity", 0444, desc->dir,
+			irq_effective_aff_proc_show, irqp);
+	proc_create_single_data("effective_affinity_list", 0444, desc->dir,
+			irq_effective_aff_list_proc_show, irqp);
 # endif
 #endif
-	proc_create_data("spurious", 0444, desc->dir,
-			 &irq_spurious_proc_fops, (void *)(long)irq);
+	proc_create_single_data("spurious", 0444, desc->dir,
+			irq_spurious_proc_show, (void *)(long)irq);
 
 out_unlock:
 	mutex_unlock(&register_lock);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 102160ff5c66..ea619021d901 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2428,7 +2428,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	struct kprobe_blacklist_entry *ent =
 		list_entry(v, struct kprobe_blacklist_entry, list);
 
-	seq_printf(m, "0x%p-0x%p\t%ps\n", (void *)ent->start_addr,
+	seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
 		   (void *)ent->end_addr, (void *)ent->start_addr);
 	return 0;
 }
diff --git a/kernel/kthread.c b/kernel/kthread.c
index cd50e99202b0..481951bf091d 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -55,7 +55,6 @@ enum KTHREAD_BITS {
 	KTHREAD_IS_PER_CPU = 0,
 	KTHREAD_SHOULD_STOP,
 	KTHREAD_SHOULD_PARK,
-	KTHREAD_IS_PARKED,
 };
 
 static inline void set_kthread_struct(void *kthread)
@@ -177,14 +176,12 @@ void *kthread_probe_data(struct task_struct *task)
 
 static void __kthread_parkme(struct kthread *self)
 {
-	__set_current_state(TASK_PARKED);
-	while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
-		if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
-			complete(&self->parked);
+	for (;;) {
+		set_current_state(TASK_PARKED);
+		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
+			break;
 		schedule();
-		__set_current_state(TASK_PARKED);
 	}
-	clear_bit(KTHREAD_IS_PARKED, &self->flags);
 	__set_current_state(TASK_RUNNING);
 }
 
@@ -194,6 +191,11 @@ void kthread_parkme(void)
 }
 EXPORT_SYMBOL_GPL(kthread_parkme);
 
+void kthread_park_complete(struct task_struct *k)
+{
+	complete_all(&to_kthread(k)->parked);
+}
+
 static int kthread(void *_create)
 {
 	/* Copy data: it's on kthread's stack */
@@ -450,22 +452,16 @@ void kthread_unpark(struct task_struct *k)
 {
 	struct kthread *kthread = to_kthread(k);
 
-	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	/*
-	 * We clear the IS_PARKED bit here as we don't wait
-	 * until the task has left the park code. So if we'd
-	 * park before that happens we'd see the IS_PARKED bit
-	 * which might be about to be cleared.
+	 * Newly created kthread was parked when the CPU was offline.
+	 * The binding was lost and we need to set it again.
 	 */
-	if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
-		/*
-		 * Newly created kthread was parked when the CPU was offline.
-		 * The binding was lost and we need to set it again.
-		 */
-		if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
-			__kthread_bind(k, kthread->cpu, TASK_PARKED);
-		wake_up_state(k, TASK_PARKED);
-	}
+	if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+		__kthread_bind(k, kthread->cpu, TASK_PARKED);
+
+	reinit_completion(&kthread->parked);
+	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+	wake_up_state(k, TASK_PARKED);
 }
 EXPORT_SYMBOL_GPL(kthread_unpark);
 
@@ -488,12 +484,10 @@ int kthread_park(struct task_struct *k)
 	if (WARN_ON(k->flags & PF_EXITING))
 		return -ENOSYS;
 
-	if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
-		set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
-		if (k != current) {
-			wake_up_process(k);
-			wait_for_completion(&kthread->parked);
-		}
+	set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+	if (k != current) {
+		wake_up_process(k);
+		wait_for_completion(&kthread->parked);
 	}
 
 	return 0;
diff --git a/kernel/livepatch/shadow.c b/kernel/livepatch/shadow.c
index fdac27588d60..83958c814439 100644
--- a/kernel/livepatch/shadow.c
+++ b/kernel/livepatch/shadow.c
@@ -113,8 +113,10 @@ void *klp_shadow_get(void *obj, unsigned long id)
 }
 EXPORT_SYMBOL_GPL(klp_shadow_get);
 
-static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
-		       size_t size, gfp_t gfp_flags, bool warn_on_exist)
+static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id,
+				       size_t size, gfp_t gfp_flags,
+				       klp_shadow_ctor_t ctor, void *ctor_data,
+				       bool warn_on_exist)
 {
 	struct klp_shadow *new_shadow;
 	void *shadow_data;
@@ -125,18 +127,15 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
 	if (shadow_data)
 		goto exists;
 
-	/* Allocate a new shadow variable for use inside the lock below */
+	/*
+	 * Allocate a new shadow variable.  Fill it with zeroes by default.
+	 * More complex setting can be done by @ctor function.  But it is
+	 * called only when the buffer is really used (under klp_shadow_lock).
+	 */
 	new_shadow = kzalloc(size + sizeof(*new_shadow), gfp_flags);
 	if (!new_shadow)
 		return NULL;
 
-	new_shadow->obj = obj;
-	new_shadow->id = id;
-
-	/* Initialize the shadow variable if data provided */
-	if (data)
-		memcpy(new_shadow->data, data, size);
-
 	/* Look for <obj, id> again under the lock */
 	spin_lock_irqsave(&klp_shadow_lock, flags);
 	shadow_data = klp_shadow_get(obj, id);
@@ -150,6 +149,22 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
 		goto exists;
 	}
 
+	new_shadow->obj = obj;
+	new_shadow->id = id;
+
+	if (ctor) {
+		int err;
+
+		err = ctor(obj, new_shadow->data, ctor_data);
+		if (err) {
+			spin_unlock_irqrestore(&klp_shadow_lock, flags);
+			kfree(new_shadow);
+			pr_err("Failed to construct shadow variable <%p, %lx> (%d)\n",
+			       obj, id, err);
+			return NULL;
+		}
+	}
+
 	/* No <obj, id> found, so attach the newly allocated one */
 	hash_add_rcu(klp_shadow_hash, &new_shadow->node,
 		     (unsigned long)new_shadow->obj);
@@ -170,26 +185,32 @@ exists:
  * klp_shadow_alloc() - allocate and add a new shadow variable
  * @obj:	pointer to parent object
  * @id:		data identifier
- * @data:	pointer to data to attach to parent
  * @size:	size of attached data
  * @gfp_flags:	GFP mask for allocation
+ * @ctor:	custom constructor to initialize the shadow data (optional)
+ * @ctor_data:	pointer to any data needed by @ctor (optional)
+ *
+ * Allocates @size bytes for new shadow variable data using @gfp_flags.
+ * The data are zeroed by default.  They are further initialized by @ctor
+ * function if it is not NULL.  The new shadow variable is then added
+ * to the global hashtable.
  *
- * Allocates @size bytes for new shadow variable data using @gfp_flags
- * and copies @size bytes from @data into the new shadow variable's own
- * data space.  If @data is NULL, @size bytes are still allocated, but
- * no copy is performed.  The new shadow variable is then added to the
- * global hashtable.
+ * If an existing <obj, id> shadow variable can be found, this routine will
+ * issue a WARN, exit early and return NULL.
  *
- * If an existing <obj, id> shadow variable can be found, this routine
- * will issue a WARN, exit early and return NULL.
+ * This function guarantees that the constructor function is called only when
+ * the variable did not exist before.  The cost is that @ctor is called
+ * in atomic context under a spin lock.
  *
  * Return: the shadow variable data element, NULL on duplicate or
  * failure.
  */
-void *klp_shadow_alloc(void *obj, unsigned long id, void *data,
-		       size_t size, gfp_t gfp_flags)
+void *klp_shadow_alloc(void *obj, unsigned long id,
+		       size_t size, gfp_t gfp_flags,
+		       klp_shadow_ctor_t ctor, void *ctor_data)
 {
-	return __klp_shadow_get_or_alloc(obj, id, data, size, gfp_flags, true);
+	return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags,
+					 ctor, ctor_data, true);
 }
 EXPORT_SYMBOL_GPL(klp_shadow_alloc);
 
@@ -197,37 +218,51 @@ EXPORT_SYMBOL_GPL(klp_shadow_alloc);
  * klp_shadow_get_or_alloc() - get existing or allocate a new shadow variable
  * @obj:	pointer to parent object
  * @id:		data identifier
- * @data:	pointer to data to attach to parent
  * @size:	size of attached data
  * @gfp_flags:	GFP mask for allocation
+ * @ctor:	custom constructor to initialize the shadow data (optional)
+ * @ctor_data:	pointer to any data needed by @ctor (optional)
  *
  * Returns a pointer to existing shadow data if an <obj, id> shadow
  * variable is already present.  Otherwise, it creates a new shadow
  * variable like klp_shadow_alloc().
  *
- * This function guarantees that only one shadow variable exists with
- * the given @id for the given @obj.  It also guarantees that the shadow
- * variable will be initialized by the given @data only when it did not
- * exist before.
+ * This function guarantees that only one shadow variable exists with the given
+ * @id for the given @obj.  It also guarantees that the constructor function
+ * will be called only when the variable did not exist before.  The cost is
+ * that @ctor is called in atomic context under a spin lock.
  *
  * Return: the shadow variable data element, NULL on failure.
  */
-void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
-			       size_t size, gfp_t gfp_flags)
+void *klp_shadow_get_or_alloc(void *obj, unsigned long id,
+			      size_t size, gfp_t gfp_flags,
+			      klp_shadow_ctor_t ctor, void *ctor_data)
 {
-	return __klp_shadow_get_or_alloc(obj, id, data, size, gfp_flags, false);
+	return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags,
+					 ctor, ctor_data, false);
 }
 EXPORT_SYMBOL_GPL(klp_shadow_get_or_alloc);
 
+static void klp_shadow_free_struct(struct klp_shadow *shadow,
+				   klp_shadow_dtor_t dtor)
+{
+	hash_del_rcu(&shadow->node);
+	if (dtor)
+		dtor(shadow->obj, shadow->data);
+	kfree_rcu(shadow, rcu_head);
+}
+
 /**
  * klp_shadow_free() - detach and free a <obj, id> shadow variable
  * @obj:	pointer to parent object
  * @id:		data identifier
+ * @dtor:	custom callback that can be used to unregister the variable
+ *		and/or free data that the shadow variable points to (optional)
  *
  * This function releases the memory for this <obj, id> shadow variable
  * instance, callers should stop referencing it accordingly.
  */
-void klp_shadow_free(void *obj, unsigned long id)
+void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor)
 {
 	struct klp_shadow *shadow;
 	unsigned long flags;
@@ -239,8 +274,7 @@ void klp_shadow_free(void *obj, unsigned long id)
 			       (unsigned long)obj) {
 
 		if (klp_shadow_match(shadow, obj, id)) {
-			hash_del_rcu(&shadow->node);
-			kfree_rcu(shadow, rcu_head);
+			klp_shadow_free_struct(shadow, dtor);
 			break;
 		}
 	}
@@ -252,11 +286,13 @@ EXPORT_SYMBOL_GPL(klp_shadow_free);
 /**
  * klp_shadow_free_all() - detach and free all <*, id> shadow variables
  * @id:		data identifier
+ * @dtor:	custom callback that can be used to unregister the variable
+ *		and/or free data that the shadow variable points to (optional)
  *
  * This function releases the memory for all <*, id> shadow variable
  * instances, callers should stop referencing them accordingly.
  */
-void klp_shadow_free_all(unsigned long id)
+void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor)
 {
 	struct klp_shadow *shadow;
 	unsigned long flags;
@@ -266,10 +302,8 @@ void klp_shadow_free_all(unsigned long id)
 
 	/* Delete all <*, id> from hash */
 	hash_for_each(klp_shadow_hash, i, shadow, node) {
-		if (klp_shadow_match(shadow, shadow->obj, id)) {
-			hash_del_rcu(&shadow->node);
-			kfree_rcu(shadow, rcu_head);
-		}
+		if (klp_shadow_match(shadow, shadow->obj, id))
+			klp_shadow_free_struct(shadow, dtor);
 	}
 
 	spin_unlock_irqrestore(&klp_shadow_lock, flags);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 023386338269..edcac5de7ebc 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -561,20 +561,24 @@ static void print_lock(struct held_lock *hlock)
 	printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip);
 }
 
-static void lockdep_print_held_locks(struct task_struct *curr)
+static void lockdep_print_held_locks(struct task_struct *p)
 {
-	int i, depth = curr->lockdep_depth;
+	int i, depth = READ_ONCE(p->lockdep_depth);
 
-	if (!depth) {
-		printk("no locks held by %s/%d.\n", curr->comm, task_pid_nr(curr));
+	if (!depth)
+		printk("no locks held by %s/%d.\n", p->comm, task_pid_nr(p));
+	else
+		printk("%d lock%s held by %s/%d:\n", depth,
+		       depth > 1 ? "s" : "", p->comm, task_pid_nr(p));
+	/*
+	 * It's not reliable to print a task's held locks if it's not sleeping
+	 * and it's not the current task.
+	 */
+	if (p->state == TASK_RUNNING && p != current)
 		return;
-	}
-	printk("%d lock%s held by %s/%d:\n",
-		depth, depth > 1 ? "s" : "", curr->comm, task_pid_nr(curr));
-
 	for (i = 0; i < depth; i++) {
 		printk(" #%d: ", i);
-		print_lock(curr->held_locks + i);
+		print_lock(p->held_locks + i);
 	}
 }
 
@@ -4451,8 +4455,6 @@ EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 void debug_show_all_locks(void)
 {
 	struct task_struct *g, *p;
-	int count = 10;
-	int unlock = 1;
 
 	if (unlikely(!debug_locks)) {
 		pr_warn("INFO: lockdep is turned off.\n");
@@ -4460,50 +4462,18 @@ void debug_show_all_locks(void)
 	}
 	pr_warn("\nShowing all locks held in the system:\n");
 
-	/*
-	 * Here we try to get the tasklist_lock as hard as possible,
-	 * if not successful after 2 seconds we ignore it (but keep
-	 * trying). This is to enable a debug printout even if a
-	 * tasklist_lock-holding task deadlocks or crashes.
-	 */
-retry:
-	if (!read_trylock(&tasklist_lock)) {
-		if (count == 10)
-			pr_warn("hm, tasklist_lock locked, retrying... ");
-		if (count) {
-			count--;
-			pr_cont(" #%d", 10-count);
-			mdelay(200);
-			goto retry;
-		}
-		pr_cont(" ignoring it.\n");
-		unlock = 0;
-	} else {
-		if (count != 10)
-			pr_cont(" locked it.\n");
-	}
-
-	do_each_thread(g, p) {
-		/*
-		 * It's not reliable to print a task's held locks
-		 * if it's not sleeping (or if it's not the current
-		 * task):
-		 */
-		if (p->state == TASK_RUNNING && p != current)
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		if (!p->lockdep_depth)
 			continue;
-		if (p->lockdep_depth)
-			lockdep_print_held_locks(p);
-		if (!unlock)
-			if (read_trylock(&tasklist_lock))
-				unlock = 1;
+		lockdep_print_held_locks(p);
 		touch_nmi_watchdog();
-	} while_each_thread(g, p);
+		touch_all_softlockup_watchdogs();
+	}
+	rcu_read_unlock();
 
 	pr_warn("\n");
 	pr_warn("=============================================\n\n");
-
-	if (unlock)
-		read_unlock(&tasklist_lock);
 }
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
 #endif
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index ad69bbc9bd28..3dd980dfba2d 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -101,18 +101,6 @@ static const struct seq_operations lockdep_ops = {
 	.show	= l_show,
 };
 
-static int lockdep_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &lockdep_ops);
-}
-
-static const struct file_operations proc_lockdep_operations = {
-	.open		= lockdep_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 #ifdef CONFIG_PROVE_LOCKING
 static void *lc_start(struct seq_file *m, loff_t *pos)
 {
@@ -170,18 +158,6 @@ static const struct seq_operations lockdep_chains_ops = {
 	.stop	= lc_stop,
 	.show	= lc_show,
 };
-
-static int lockdep_chains_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &lockdep_chains_ops);
-}
-
-static const struct file_operations proc_lockdep_chains_operations = {
-	.open		= lockdep_chains_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
 #endif /* CONFIG_PROVE_LOCKING */
 
 static void lockdep_stats_debug_show(struct seq_file *m)
@@ -355,18 +331,6 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int lockdep_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, lockdep_stats_show, NULL);
-}
-
-static const struct file_operations proc_lockdep_stats_operations = {
-	.open		= lockdep_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 #ifdef CONFIG_LOCK_STAT
 
 struct lock_stat_data {
@@ -682,14 +646,11 @@ static const struct file_operations proc_lock_stat_operations = {
 
 static int __init lockdep_proc_init(void)
 {
-	proc_create("lockdep", S_IRUSR, NULL, &proc_lockdep_operations);
+	proc_create_seq("lockdep", S_IRUSR, NULL, &lockdep_ops);
 #ifdef CONFIG_PROVE_LOCKING
-	proc_create("lockdep_chains", S_IRUSR, NULL,
-		    &proc_lockdep_chains_operations);
+	proc_create_seq("lockdep_chains", S_IRUSR, NULL, &lockdep_chains_ops);
 #endif
-	proc_create("lockdep_stats", S_IRUSR, NULL,
-		    &proc_lockdep_stats_operations);
-
+	proc_create_single("lockdep_stats", S_IRUSR, NULL, lockdep_stats_show);
 #ifdef CONFIG_LOCK_STAT
 	proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL,
 		    &proc_lock_stat_operations);
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index f046b7ce9dd6..5e10153b4d3c 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -23,13 +23,15 @@ struct mcs_spinlock {
 
 #ifndef arch_mcs_spin_lock_contended
 /*
- * Using smp_load_acquire() provides a memory barrier that ensures
- * subsequent operations happen after the lock is acquired.
+ * Using smp_cond_load_acquire() provides the acquire semantics
+ * required so that subsequent operations happen after the
+ * lock is acquired. Additionally, some architectures such as
+ * ARM64 would like to do spin-waiting instead of purely
+ * spinning, and smp_cond_load_acquire() provides that behavior.
  */
 #define arch_mcs_spin_lock_contended(l)					\
 do {									\
-	while (!(smp_load_acquire(l)))					\
-		cpu_relax();						\
+	smp_cond_load_acquire(l, VAL);					\
 } while (0)
 #endif
 
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 2048359f33d2..f44f658ae629 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -139,8 +139,9 @@ static inline bool __mutex_trylock(struct mutex *lock)
 static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
 {
 	unsigned long curr = (unsigned long)current;
+	unsigned long zero = 0UL;
 
-	if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr))
+	if (atomic_long_try_cmpxchg_acquire(&lock->owner, &zero, curr))
 		return true;
 
 	return false;
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index d880296245c5..bfaeb05123ff 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -12,11 +12,11 @@
  * GNU General Public License for more details.
  *
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
- * (C) Copyright 2013-2014 Red Hat, Inc.
+ * (C) Copyright 2013-2014,2018 Red Hat, Inc.
  * (C) Copyright 2015 Intel Corp.
  * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <waiman.long@hpe.com>
+ * Authors: Waiman Long <longman@redhat.com>
  *          Peter Zijlstra <peterz@infradead.org>
  */
 
@@ -33,6 +33,11 @@
 #include <asm/qspinlock.h>
 
 /*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
  * The basic principle of a queue-based spinlock can best be understood
  * by studying a classic queue-based spinlock implementation called the
  * MCS lock. The paper below provides a good description for this kind
@@ -77,6 +82,18 @@
 #endif
 
 /*
+ * The pending bit spinning loop count.
+ * This heuristic is used to limit the number of lockword accesses
+ * made by atomic_cond_read_relaxed when waiting for the lock to
+ * transition out of the "== _Q_PENDING_VAL" state. We don't spin
+ * indefinitely because there's no guarantee that we'll make forward
+ * progress.
+ */
+#ifndef _Q_PENDING_LOOPS
+#define _Q_PENDING_LOOPS	1
+#endif
+
+/*
  * Per-CPU queue node structures; we can never have more than 4 nested
  * contexts: task, softirq, hardirq, nmi.
  *
@@ -114,41 +131,18 @@ static inline __pure struct mcs_spinlock *decode_tail(u32 tail)
 
 #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
 
-/*
- * By using the whole 2nd least significant byte for the pending bit, we
- * can allow better optimization of the lock acquisition for the pending
- * bit holder.
+#if _Q_PENDING_BITS == 8
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
  *
- * This internal structure is also used by the set_locked function which
- * is not restricted to _Q_PENDING_BITS == 8.
+ * *,1,* -> *,0,*
  */
-struct __qspinlock {
-	union {
-		atomic_t val;
-#ifdef __LITTLE_ENDIAN
-		struct {
-			u8	locked;
-			u8	pending;
-		};
-		struct {
-			u16	locked_pending;
-			u16	tail;
-		};
-#else
-		struct {
-			u16	tail;
-			u16	locked_pending;
-		};
-		struct {
-			u8	reserved[2];
-			u8	pending;
-			u8	locked;
-		};
-#endif
-	};
-};
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->pending, 0);
+}
 
-#if _Q_PENDING_BITS == 8
 /**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
@@ -159,9 +153,7 @@ struct __qspinlock {
  */
 static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL);
+	WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
 }
 
 /*
@@ -176,19 +168,28 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
  */
 static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 {
-	struct __qspinlock *l = (void *)lock;
-
 	/*
-	 * Use release semantics to make sure that the MCS node is properly
-	 * initialized before changing the tail code.
+	 * We can use relaxed semantics since the caller ensures that the
+	 * MCS node is properly initialized before updating the tail.
 	 */
-	return (u32)xchg_release(&l->tail,
+	return (u32)xchg_relaxed(&lock->tail,
 				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
 }
 
 #else /* _Q_PENDING_BITS == 8 */
 
 /**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	atomic_andnot(_Q_PENDING_VAL, &lock->val);
+}
+
+/**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
  *
@@ -216,10 +217,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 	for (;;) {
 		new = (val & _Q_LOCKED_PENDING_MASK) | tail;
 		/*
-		 * Use release semantics to make sure that the MCS node is
-		 * properly initialized before changing the tail code.
+		 * We can use relaxed semantics since the caller ensures that
+		 * the MCS node is properly initialized before updating the
+		 * tail.
 		 */
-		old = atomic_cmpxchg_release(&lock->val, val, new);
+		old = atomic_cmpxchg_relaxed(&lock->val, val, new);
 		if (old == val)
 			break;
 
@@ -237,9 +239,7 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
  */
 static __always_inline void set_locked(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+	WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
 }
 
 
@@ -294,86 +294,83 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 {
 	struct mcs_spinlock *prev, *next, *node;
-	u32 new, old, tail;
+	u32 old, tail;
 	int idx;
 
 	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
 
 	if (pv_enabled())
-		goto queue;
+		goto pv_queue;
 
 	if (virt_spin_lock(lock))
 		return;
 
 	/*
-	 * wait for in-progress pending->locked hand-overs
+	 * Wait for in-progress pending->locked hand-overs with a bounded
+	 * number of spins so that we guarantee forward progress.
 	 *
 	 * 0,1,0 -> 0,0,1
 	 */
 	if (val == _Q_PENDING_VAL) {
-		while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL)
-			cpu_relax();
+		int cnt = _Q_PENDING_LOOPS;
+		val = atomic_cond_read_relaxed(&lock->val,
+					       (VAL != _Q_PENDING_VAL) || !cnt--);
 	}
 
 	/*
+	 * If we observe any contention; queue.
+	 */
+	if (val & ~_Q_LOCKED_MASK)
+		goto queue;
+
+	/*
 	 * trylock || pending
 	 *
 	 * 0,0,0 -> 0,0,1 ; trylock
 	 * 0,0,1 -> 0,1,1 ; pending
 	 */
-	for (;;) {
+	val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
+	if (!(val & ~_Q_LOCKED_MASK)) {
 		/*
-		 * If we observe any contention; queue.
+		 * We're pending, wait for the owner to go away.
+		 *
+		 * *,1,1 -> *,1,0
+		 *
+		 * this wait loop must be a load-acquire such that we match the
+		 * store-release that clears the locked bit and create lock
+		 * sequentiality; this is because not all
+		 * clear_pending_set_locked() implementations imply full
+		 * barriers.
 		 */
-		if (val & ~_Q_LOCKED_MASK)
-			goto queue;
-
-		new = _Q_LOCKED_VAL;
-		if (val == new)
-			new |= _Q_PENDING_VAL;
+		if (val & _Q_LOCKED_MASK) {
+			atomic_cond_read_acquire(&lock->val,
+						 !(VAL & _Q_LOCKED_MASK));
+		}
 
 		/*
-		 * Acquire semantic is required here as the function may
-		 * return immediately if the lock was free.
+		 * take ownership and clear the pending bit.
+		 *
+		 * *,1,0 -> *,0,1
 		 */
-		old = atomic_cmpxchg_acquire(&lock->val, val, new);
-		if (old == val)
-			break;
-
-		val = old;
-	}
-
-	/*
-	 * we won the trylock
-	 */
-	if (new == _Q_LOCKED_VAL)
+		clear_pending_set_locked(lock);
+		qstat_inc(qstat_lock_pending, true);
 		return;
+	}
 
 	/*
-	 * we're pending, wait for the owner to go away.
-	 *
-	 * *,1,1 -> *,1,0
-	 *
-	 * this wait loop must be a load-acquire such that we match the
-	 * store-release that clears the locked bit and create lock
-	 * sequentiality; this is because not all clear_pending_set_locked()
-	 * implementations imply full barriers.
-	 */
-	smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_MASK));
-
-	/*
-	 * take ownership and clear the pending bit.
-	 *
-	 * *,1,0 -> *,0,1
+	 * If pending was clear but there are waiters in the queue, then
+	 * we need to undo our setting of pending before we queue ourselves.
 	 */
-	clear_pending_set_locked(lock);
-	return;
+	if (!(val & _Q_PENDING_MASK))
+		clear_pending(lock);
 
 	/*
 	 * End of pending bit optimistic spinning and beginning of MCS
 	 * queuing.
 	 */
 queue:
+	qstat_inc(qstat_lock_slowpath, true);
+pv_queue:
 	node = this_cpu_ptr(&mcs_nodes[0]);
 	idx = node->count++;
 	tail = encode_tail(smp_processor_id(), idx);
@@ -400,12 +397,18 @@ queue:
 		goto release;
 
 	/*
+	 * Ensure that the initialisation of @node is complete before we
+	 * publish the updated tail via xchg_tail() and potentially link
+	 * @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
+	 */
+	smp_wmb();
+
+	/*
+	 * Publish the updated tail.
 	 * We have already touched the queueing cacheline; don't bother with
 	 * pending stuff.
 	 *
 	 * p,*,* -> n,*,*
-	 *
-	 * RELEASE, such that the stores to @node must be complete.
 	 */
 	old = xchg_tail(lock, tail);
 	next = NULL;
@@ -417,14 +420,8 @@ queue:
 	if (old & _Q_TAIL_MASK) {
 		prev = decode_tail(old);
 
-		/*
-		 * We must ensure that the stores to @node are observed before
-		 * the write to prev->next. The address dependency from
-		 * xchg_tail is not sufficient to ensure this because the read
-		 * component of xchg_tail is unordered with respect to the
-		 * initialisation of @node.
-		 */
-		smp_store_release(&prev->next, node);
+		/* Link @node into the waitqueue. */
+		WRITE_ONCE(prev->next, node);
 
 		pv_wait_node(node, prev);
 		arch_mcs_spin_lock_contended(&node->locked);
@@ -453,8 +450,8 @@ queue:
 	 *
 	 * The PV pv_wait_head_or_lock function, if active, will acquire
 	 * the lock and return a non-zero value. So we have to skip the
-	 * smp_cond_load_acquire() call. As the next PV queue head hasn't been
-	 * designated yet, there is no way for the locked value to become
+	 * atomic_cond_read_acquire() call. As the next PV queue head hasn't
+	 * been designated yet, there is no way for the locked value to become
 	 * _Q_SLOW_VAL. So both the set_locked() and the
 	 * atomic_cmpxchg_relaxed() calls will be safe.
 	 *
@@ -464,44 +461,38 @@ queue:
 	if ((val = pv_wait_head_or_lock(lock, node)))
 		goto locked;
 
-	val = smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_PENDING_MASK));
+	val = atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK));
 
 locked:
 	/*
 	 * claim the lock:
 	 *
 	 * n,0,0 -> 0,0,1 : lock, uncontended
-	 * *,0,0 -> *,0,1 : lock, contended
+	 * *,*,0 -> *,*,1 : lock, contended
 	 *
-	 * If the queue head is the only one in the queue (lock value == tail),
-	 * clear the tail code and grab the lock. Otherwise, we only need
-	 * to grab the lock.
+	 * If the queue head is the only one in the queue (lock value == tail)
+	 * and nobody is pending, clear the tail code and grab the lock.
+	 * Otherwise, we only need to grab the lock.
 	 */
-	for (;;) {
-		/* In the PV case we might already have _Q_LOCKED_VAL set */
-		if ((val & _Q_TAIL_MASK) != tail) {
-			set_locked(lock);
-			break;
-		}
-		/*
-		 * The smp_cond_load_acquire() call above has provided the
-		 * necessary acquire semantics required for locking. At most
-		 * two iterations of this loop may be ran.
-		 */
-		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
-		if (old == val)
-			goto release;	/* No contention */
 
-		val = old;
-	}
+	/*
+	 * In the PV case we might already have _Q_LOCKED_VAL set.
+	 *
+	 * The atomic_cond_read_acquire() call above has provided the
+	 * necessary acquire semantics required for locking.
+	 */
+	if (((val & _Q_TAIL_MASK) == tail) &&
+	    atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
+		goto release; /* No contention */
+
+	/* Either somebody is queued behind us or _Q_PENDING_VAL is set */
+	set_locked(lock);
 
 	/*
 	 * contended path; wait for next if not observed yet, release.
 	 */
-	if (!next) {
-		while (!(next = READ_ONCE(node->next)))
-			cpu_relax();
-	}
+	if (!next)
+		next = smp_cond_load_relaxed(&node->next, (VAL));
 
 	arch_mcs_spin_unlock_contended(&next->locked);
 	pv_kick_node(lock, next);
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 6ee477765e6c..5a0cf5f9008c 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -56,11 +56,6 @@ struct pv_node {
 };
 
 /*
- * Include queued spinlock statistics code
- */
-#include "qspinlock_stat.h"
-
-/*
  * Hybrid PV queued/unfair lock
  *
  * By replacing the regular queued_spin_trylock() with the function below,
@@ -87,8 +82,6 @@ struct pv_node {
 #define queued_spin_trylock(l)	pv_hybrid_queued_unfair_trylock(l)
 static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
 	/*
 	 * Stay in unfair lock mode as long as queued mode waiters are
 	 * present in the MCS wait queue but the pending bit isn't set.
@@ -97,7 +90,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 		int val = atomic_read(&lock->val);
 
 		if (!(val & _Q_LOCKED_PENDING_MASK) &&
-		   (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
+		   (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
 			qstat_inc(qstat_pv_lock_stealing, true);
 			return true;
 		}
@@ -117,16 +110,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 #if _Q_PENDING_BITS == 8
 static __always_inline void set_pending(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->pending, 1);
-}
-
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->pending, 0);
+	WRITE_ONCE(lock->pending, 1);
 }
 
 /*
@@ -136,10 +120,8 @@ static __always_inline void clear_pending(struct qspinlock *lock)
  */
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	return !READ_ONCE(l->locked) &&
-	       (cmpxchg_acquire(&l->locked_pending, _Q_PENDING_VAL,
+	return !READ_ONCE(lock->locked) &&
+	       (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL,
 				_Q_LOCKED_VAL) == _Q_PENDING_VAL);
 }
 #else /* _Q_PENDING_BITS == 8 */
@@ -148,11 +130,6 @@ static __always_inline void set_pending(struct qspinlock *lock)
 	atomic_or(_Q_PENDING_VAL, &lock->val);
 }
 
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
-	atomic_andnot(_Q_PENDING_VAL, &lock->val);
-}
-
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 {
 	int val = atomic_read(&lock->val);
@@ -384,7 +361,6 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-	struct __qspinlock *l = (void *)lock;
 
 	/*
 	 * If the vCPU is indeed halted, advance its state to match that of
@@ -413,7 +389,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 	 * the hash table later on at unlock time, no atomic instruction is
 	 * needed.
 	 */
-	WRITE_ONCE(l->locked, _Q_SLOW_VAL);
+	WRITE_ONCE(lock->locked, _Q_SLOW_VAL);
 	(void)pv_hash(lock, pn);
 }
 
@@ -428,7 +404,6 @@ static u32
 pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-	struct __qspinlock *l = (void *)lock;
 	struct qspinlock **lp = NULL;
 	int waitcnt = 0;
 	int loop;
@@ -443,7 +418,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	/*
 	 * Tracking # of slowpath locking operations
 	 */
-	qstat_inc(qstat_pv_lock_slowpath, true);
+	qstat_inc(qstat_lock_slowpath, true);
 
 	for (;; waitcnt++) {
 		/*
@@ -479,13 +454,13 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 			 *
 			 * Matches the smp_rmb() in __pv_queued_spin_unlock().
 			 */
-			if (xchg(&l->locked, _Q_SLOW_VAL) == 0) {
+			if (xchg(&lock->locked, _Q_SLOW_VAL) == 0) {
 				/*
 				 * The lock was free and now we own the lock.
 				 * Change the lock value back to _Q_LOCKED_VAL
 				 * and unhash the table.
 				 */
-				WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+				WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
 				WRITE_ONCE(*lp, NULL);
 				goto gotlock;
 			}
@@ -493,7 +468,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 		WRITE_ONCE(pn->state, vcpu_hashed);
 		qstat_inc(qstat_pv_wait_head, true);
 		qstat_inc(qstat_pv_wait_again, waitcnt);
-		pv_wait(&l->locked, _Q_SLOW_VAL);
+		pv_wait(&lock->locked, _Q_SLOW_VAL);
 
 		/*
 		 * Because of lock stealing, the queue head vCPU may not be
@@ -518,7 +493,6 @@ gotlock:
 __visible void
 __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 {
-	struct __qspinlock *l = (void *)lock;
 	struct pv_node *node;
 
 	if (unlikely(locked != _Q_SLOW_VAL)) {
@@ -547,7 +521,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 	 * Now that we have a reference to the (likely) blocked pv_node,
 	 * release the lock.
 	 */
-	smp_store_release(&l->locked, 0);
+	smp_store_release(&lock->locked, 0);
 
 	/*
 	 * At this point the memory pointed at by lock can be freed/reused,
@@ -573,7 +547,6 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 #ifndef __pv_queued_spin_unlock
 __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
 	u8 locked;
 
 	/*
@@ -581,7 +554,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
 	 * unhash. Otherwise it would be possible to have multiple @lock
 	 * entries, which would be BAD.
 	 */
-	locked = cmpxchg_release(&l->locked, _Q_LOCKED_VAL, 0);
+	locked = cmpxchg_release(&lock->locked, _Q_LOCKED_VAL, 0);
 	if (likely(locked == _Q_LOCKED_VAL))
 		return;
 
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 4a30ef63c607..6bd78c0740fc 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -22,13 +22,14 @@
  *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
  *   pv_latency_kick	- average latency (ns) of vCPU kick operation
  *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
- *   pv_lock_slowpath	- # of locking operations via the slowpath
  *   pv_lock_stealing	- # of lock stealing operations
  *   pv_spurious_wakeup	- # of spurious wakeups in non-head vCPUs
  *   pv_wait_again	- # of wait's after a queue head vCPU kick
  *   pv_wait_early	- # of early vCPU wait's
  *   pv_wait_head	- # of vCPU wait's at the queue head
  *   pv_wait_node	- # of vCPU wait's at a non-head queue node
+ *   lock_pending	- # of locking operations via pending code
+ *   lock_slowpath	- # of locking operations via MCS lock queue
  *
  * Writing to the "reset_counters" file will reset all the above counter
  * values.
@@ -46,13 +47,14 @@ enum qlock_stats {
 	qstat_pv_kick_wake,
 	qstat_pv_latency_kick,
 	qstat_pv_latency_wake,
-	qstat_pv_lock_slowpath,
 	qstat_pv_lock_stealing,
 	qstat_pv_spurious_wakeup,
 	qstat_pv_wait_again,
 	qstat_pv_wait_early,
 	qstat_pv_wait_head,
 	qstat_pv_wait_node,
+	qstat_lock_pending,
+	qstat_lock_slowpath,
 	qstat_num,	/* Total number of statistical counters */
 	qstat_reset_cnts = qstat_num,
 };
@@ -73,12 +75,13 @@ static const char * const qstat_names[qstat_num + 1] = {
 	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
 	[qstat_pv_latency_kick]	   = "pv_latency_kick",
 	[qstat_pv_latency_wake]    = "pv_latency_wake",
-	[qstat_pv_lock_slowpath]   = "pv_lock_slowpath",
 	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
 	[qstat_pv_wait_again]      = "pv_wait_again",
 	[qstat_pv_wait_early]      = "pv_wait_early",
 	[qstat_pv_wait_head]       = "pv_wait_head",
 	[qstat_pv_wait_node]       = "pv_wait_node",
+	[qstat_lock_pending]       = "lock_pending",
+	[qstat_lock_slowpath]      = "lock_slowpath",
 	[qstat_reset_cnts]         = "reset_counters",
 };
 
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index e795908f3607..3064c50e181e 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -347,30 +347,31 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 	}
 }
 
+static inline bool owner_on_cpu(struct task_struct *owner)
+{
+	/*
+	 * As lock holder preemption issue, we both skip spinning if
+	 * task is not on cpu or its cpu is preempted
+	 */
+	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+}
+
 static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 {
 	struct task_struct *owner;
 	bool ret = true;
 
+	BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN));
+
 	if (need_resched())
 		return false;
 
 	rcu_read_lock();
 	owner = READ_ONCE(sem->owner);
-	if (!rwsem_owner_is_writer(owner)) {
-		/*
-		 * Don't spin if the rwsem is readers owned.
-		 */
-		ret = !rwsem_owner_is_reader(owner);
-		goto done;
+	if (owner) {
+		ret = is_rwsem_owner_spinnable(owner) &&
+		      owner_on_cpu(owner);
 	}
-
-	/*
-	 * As lock holder preemption issue, we both skip spinning if task is not
-	 * on cpu or its cpu is preempted
-	 */
-	ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
-done:
 	rcu_read_unlock();
 	return ret;
 }
@@ -382,11 +383,11 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 {
 	struct task_struct *owner = READ_ONCE(sem->owner);
 
-	if (!rwsem_owner_is_writer(owner))
-		goto out;
+	if (!is_rwsem_owner_spinnable(owner))
+		return false;
 
 	rcu_read_lock();
-	while (sem->owner == owner) {
+	while (owner && (READ_ONCE(sem->owner) == owner)) {
 		/*
 		 * Ensure we emit the owner->on_cpu, dereference _after_
 		 * checking sem->owner still matches owner, if that fails,
@@ -399,8 +400,7 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		 * abort spinning when need_resched or owner is not running or
 		 * owner's cpu is preempted.
 		 */
-		if (!owner->on_cpu || need_resched() ||
-				vcpu_is_preempted(task_cpu(owner))) {
+		if (need_resched() || !owner_on_cpu(owner)) {
 			rcu_read_unlock();
 			return false;
 		}
@@ -408,12 +408,12 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		cpu_relax();
 	}
 	rcu_read_unlock();
-out:
+
 	/*
 	 * If there is a new owner or the owner is not set, we continue
 	 * spinning.
 	 */
-	return !rwsem_owner_is_reader(READ_ONCE(sem->owner));
+	return is_rwsem_owner_spinnable(READ_ONCE(sem->owner));
 }
 
 static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 30465a2f2b6c..bc1e507be9ff 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -221,5 +221,3 @@ void up_read_non_owner(struct rw_semaphore *sem)
 EXPORT_SYMBOL(up_read_non_owner);
 
 #endif
-
-
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index a17cba8d94bb..b9d0e72aa80f 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,20 +1,24 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * The owner field of the rw_semaphore structure will be set to
- * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear
+ * RWSEM_READER_OWNED when a reader grabs the lock. A writer will clear
  * the owner field when it unlocks. A reader, on the other hand, will
  * not touch the owner field when it unlocks.
  *
- * In essence, the owner field now has the following 3 states:
+ * In essence, the owner field now has the following 4 states:
  *  1) 0
  *     - lock is free or the owner hasn't set the field yet
  *  2) RWSEM_READER_OWNED
  *     - lock is currently or previously owned by readers (lock is free
  *       or not set by owner yet)
- *  3) Other non-zero value
- *     - a writer owns the lock
+ *  3) RWSEM_ANONYMOUSLY_OWNED bit set with some other bits set as well
+ *     - lock is owned by an anonymous writer, so spinning on the lock
+ *       owner should be disabled.
+ *  4) Other non-zero value
+ *     - a writer owns the lock and other writers can spin on the lock owner.
  */
-#define RWSEM_READER_OWNED	((struct task_struct *)1UL)
+#define RWSEM_ANONYMOUSLY_OWNED	(1UL << 0)
+#define RWSEM_READER_OWNED	((struct task_struct *)RWSEM_ANONYMOUSLY_OWNED)
 
 #ifdef CONFIG_DEBUG_RWSEMS
 # define DEBUG_RWSEMS_WARN_ON(c)	DEBUG_LOCKS_WARN_ON(c)
@@ -51,14 +55,22 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
 		WRITE_ONCE(sem->owner, RWSEM_READER_OWNED);
 }
 
-static inline bool rwsem_owner_is_writer(struct task_struct *owner)
+/*
+ * Return true if the a rwsem waiter can spin on the rwsem's owner
+ * and steal the lock, i.e. the lock is not anonymously owned.
+ * N.B. !owner is considered spinnable.
+ */
+static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
 {
-	return owner && owner != RWSEM_READER_OWNED;
+	return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
 }
 
-static inline bool rwsem_owner_is_reader(struct task_struct *owner)
+/*
+ * Return true if rwsem is owned by an anonymous writer or readers.
+ */
+static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
 {
-	return owner == RWSEM_READER_OWNED;
+	return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
 }
 #else
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
diff --git a/kernel/module.c b/kernel/module.c
index a6e43a5806a1..c9bea7f2b43e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1472,7 +1472,8 @@ static ssize_t module_sect_show(struct module_attribute *mattr,
 {
 	struct module_sect_attr *sattr =
 		container_of(mattr, struct module_sect_attr, mattr);
-	return sprintf(buf, "0x%pK\n", (void *)sattr->address);
+	return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
+		       (void *)sattr->address : NULL);
 }
 
 static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
@@ -3516,6 +3517,11 @@ static noinline int do_init_module(struct module *mod)
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_sched(), but we don't want to slow down the success
 	 * path, so use actual RCU here.
+	 * Note that module_alloc() on most architectures creates W+X page
+	 * mappings which won't be cleaned up until do_free_init() runs.  Any
+	 * code such as mark_rodata_ro() which depends on those mappings to
+	 * be cleaned up needs to sync with the queued work - ie
+	 * rcu_barrier_sched()
 	 */
 	call_rcu_sched(&freeinit->rcu, do_free_init);
 	mutex_unlock(&module_mutex);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 5454cc639a8d..9c85c7822383 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -287,6 +287,8 @@ static int create_image(int platform_mode)
 
 	local_irq_disable();
 
+	system_state = SYSTEM_SUSPEND;
+
 	error = syscore_suspend();
 	if (error) {
 		pr_err("Some system devices failed to power down, aborting hibernation\n");
@@ -317,6 +319,7 @@ static int create_image(int platform_mode)
 	syscore_resume();
 
  Enable_irqs:
+	system_state = SYSTEM_RUNNING;
 	local_irq_enable();
 
  Enable_cpus:
@@ -445,6 +448,7 @@ static int resume_target_kernel(bool platform_mode)
 		goto Enable_cpus;
 
 	local_irq_disable();
+	system_state = SYSTEM_SUSPEND;
 
 	error = syscore_suspend();
 	if (error)
@@ -478,6 +482,7 @@ static int resume_target_kernel(bool platform_mode)
 	syscore_resume();
 
  Enable_irqs:
+	system_state = SYSTEM_RUNNING;
 	local_irq_enable();
 
  Enable_cpus:
@@ -563,6 +568,7 @@ int hibernation_platform_enter(void)
 		goto Enable_cpus;
 
 	local_irq_disable();
+	system_state = SYSTEM_SUSPEND;
 	syscore_suspend();
 	if (pm_wakeup_pending()) {
 		error = -EAGAIN;
@@ -575,6 +581,7 @@ int hibernation_platform_enter(void)
 
  Power_up:
 	syscore_resume();
+	system_state = SYSTEM_RUNNING;
 	local_irq_enable();
 
  Enable_cpus:
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index fa39092b7aea..86d72ffb811b 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -184,7 +184,6 @@ static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
 	c->target_value = value;
 }
 
-static inline int pm_qos_get_value(struct pm_qos_constraints *c);
 static int pm_qos_dbg_show_requests(struct seq_file *s, void *unused)
 {
 	struct pm_qos_object *qos = (struct pm_qos_object *)s->private;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 4c10be0f4843..87331565e505 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -27,6 +27,7 @@
 #include <linux/export.h>
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
+#include <linux/swait.h>
 #include <linux/ftrace.h>
 #include <trace/events/power.h>
 #include <linux/compiler.h>
@@ -57,10 +58,10 @@ EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
 
 static const struct platform_suspend_ops *suspend_ops;
 static const struct platform_s2idle_ops *s2idle_ops;
-static DECLARE_WAIT_QUEUE_HEAD(s2idle_wait_head);
+static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head);
 
 enum s2idle_states __read_mostly s2idle_state;
-static DEFINE_SPINLOCK(s2idle_lock);
+static DEFINE_RAW_SPINLOCK(s2idle_lock);
 
 void s2idle_set_ops(const struct platform_s2idle_ops *ops)
 {
@@ -78,12 +79,12 @@ static void s2idle_enter(void)
 {
 	trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, true);
 
-	spin_lock_irq(&s2idle_lock);
+	raw_spin_lock_irq(&s2idle_lock);
 	if (pm_wakeup_pending())
 		goto out;
 
 	s2idle_state = S2IDLE_STATE_ENTER;
-	spin_unlock_irq(&s2idle_lock);
+	raw_spin_unlock_irq(&s2idle_lock);
 
 	get_online_cpus();
 	cpuidle_resume();
@@ -91,17 +92,17 @@ static void s2idle_enter(void)
 	/* Push all the CPUs into the idle loop. */
 	wake_up_all_idle_cpus();
 	/* Make the current CPU wait so it can enter the idle loop too. */
-	wait_event(s2idle_wait_head,
-		   s2idle_state == S2IDLE_STATE_WAKE);
+	swait_event(s2idle_wait_head,
+		    s2idle_state == S2IDLE_STATE_WAKE);
 
 	cpuidle_pause();
 	put_online_cpus();
 
-	spin_lock_irq(&s2idle_lock);
+	raw_spin_lock_irq(&s2idle_lock);
 
  out:
 	s2idle_state = S2IDLE_STATE_NONE;
-	spin_unlock_irq(&s2idle_lock);
+	raw_spin_unlock_irq(&s2idle_lock);
 
 	trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, false);
 }
@@ -156,12 +157,12 @@ void s2idle_wake(void)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&s2idle_lock, flags);
+	raw_spin_lock_irqsave(&s2idle_lock, flags);
 	if (s2idle_state > S2IDLE_STATE_NONE) {
 		s2idle_state = S2IDLE_STATE_WAKE;
-		wake_up(&s2idle_wait_head);
+		swake_up(&s2idle_wait_head);
 	}
-	spin_unlock_irqrestore(&s2idle_lock, flags);
+	raw_spin_unlock_irqrestore(&s2idle_lock, flags);
 }
 EXPORT_SYMBOL_GPL(s2idle_wake);
 
@@ -428,6 +429,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	arch_suspend_disable_irqs();
 	BUG_ON(!irqs_disabled());
 
+	system_state = SYSTEM_SUSPEND;
+
 	error = syscore_suspend();
 	if (!error) {
 		*wakeup = pm_wakeup_pending();
@@ -443,6 +446,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 		syscore_resume();
 	}
 
+	system_state = SYSTEM_RUNNING;
+
 	arch_suspend_enable_irqs();
 	BUG_ON(irqs_disabled());
 
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 11b4282c2d20..1efcb5b0c3ed 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -269,7 +269,7 @@ static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr,
 	struct bio *bio;
 	int error = 0;
 
-	bio = bio_alloc(__GFP_RECLAIM | __GFP_HIGH, 1);
+	bio = bio_alloc(GFP_NOIO | __GFP_HIGH, 1);
 	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
 	bio_set_dev(bio, hib_resume_bdev);
 	bio_set_op_attrs(bio, op, op_flags);
@@ -376,7 +376,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
 		return -ENOSPC;
 
 	if (hb) {
-		src = (void *)__get_free_page(__GFP_RECLAIM | __GFP_NOWARN |
+		src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN |
 		                              __GFP_NORETRY);
 		if (src) {
 			copy_page(src, buf);
@@ -384,7 +384,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
 			ret = hib_wait_io(hb); /* Free pages */
 			if (ret)
 				return ret;
-			src = (void *)__get_free_page(__GFP_RECLAIM |
+			src = (void *)__get_free_page(GFP_NOIO |
 			                              __GFP_NOWARN |
 			                              __GFP_NORETRY);
 			if (src) {
@@ -691,7 +691,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	nr_threads = num_online_cpus() - 1;
 	nr_threads = clamp_val(nr_threads, 1, LZO_THREADS);
 
-	page = (void *)__get_free_page(__GFP_RECLAIM | __GFP_HIGH);
+	page = (void *)__get_free_page(GFP_NOIO | __GFP_HIGH);
 	if (!page) {
 		pr_err("Failed to allocate LZO page\n");
 		ret = -ENOMEM;
@@ -989,7 +989,7 @@ static int get_swap_reader(struct swap_map_handle *handle,
 		last = tmp;
 
 		tmp->map = (struct swap_map_page *)
-			   __get_free_page(__GFP_RECLAIM | __GFP_HIGH);
+			   __get_free_page(GFP_NOIO | __GFP_HIGH);
 		if (!tmp->map) {
 			release_swap_reader(handle);
 			return -ENOMEM;
@@ -1261,8 +1261,8 @@ static int load_image_lzo(struct swap_map_handle *handle,
 
 	for (i = 0; i < read_pages; i++) {
 		page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ?
-						  __GFP_RECLAIM | __GFP_HIGH :
-						  __GFP_RECLAIM | __GFP_NOWARN |
+						  GFP_NOIO | __GFP_HIGH :
+						  GFP_NOIO | __GFP_NOWARN |
 						  __GFP_NORETRY);
 
 		if (!page[i]) {
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 75c959de4b29..abd225550271 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -186,6 +186,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 		res = PAGE_SIZE - pg_offp;
 	}
 
+	if (!data_of(data->handle)) {
+		res = -EINVAL;
+		goto unlock;
+	}
+
 	res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp,
 			buf, count);
 	if (res > 0)
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
index dfba59be190b..4210152e56f0 100644
--- a/kernel/power/wakelock.c
+++ b/kernel/power/wakelock.c
@@ -188,6 +188,7 @@ static struct wakelock *wakelock_lookup_add(const char *name, size_t len,
 		return ERR_PTR(-ENOMEM);
 	}
 	wl->ws.name = wl->name;
+	wl->ws.last_time = ktime_get();
 	wakeup_source_add(&wl->ws);
 	rb_link_node(&wl->node, parent, node);
 	rb_insert_color(&wl->node, &wakelocks_tree);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 2f4af216bd6e..247808333ba4 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1908,6 +1908,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 		preempt_enable();
 	}
 
+	wake_up_klogd();
 	return printed_len;
 }
 EXPORT_SYMBOL(vprintk_emit);
@@ -2289,9 +2290,7 @@ void console_unlock(void)
 {
 	static char ext_text[CONSOLE_EXT_LOG_MAX];
 	static char text[LOG_LINE_MAX + PREFIX_MAX];
-	static u64 seen_seq;
 	unsigned long flags;
-	bool wake_klogd = false;
 	bool do_cond_resched, retry;
 
 	if (console_suspended) {
@@ -2335,11 +2334,6 @@ again:
 
 		printk_safe_enter_irqsave(flags);
 		raw_spin_lock(&logbuf_lock);
-		if (seen_seq != log_next_seq) {
-			wake_klogd = true;
-			seen_seq = log_next_seq;
-		}
-
 		if (console_seq < log_first_seq) {
 			len = sprintf(text, "** %u printk messages dropped **\n",
 				      (unsigned)(log_first_seq - console_seq));
@@ -2397,7 +2391,7 @@ skip:
 
 		if (console_lock_spinning_disable_and_check()) {
 			printk_safe_exit_irqrestore(flags);
-			goto out;
+			return;
 		}
 
 		printk_safe_exit_irqrestore(flags);
@@ -2429,10 +2423,6 @@ skip:
 
 	if (retry && console_trylock())
 		goto again;
-
-out:
-	if (wake_klogd)
-		wake_up_klogd();
 }
 EXPORT_SYMBOL(console_unlock);
 
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index 3e3c2004bb23..d7d091309054 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -82,6 +82,7 @@ static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s,
 {
 	int add;
 	size_t len;
+	va_list ap;
 
 again:
 	len = atomic_read(&s->len);
@@ -100,7 +101,9 @@ again:
 	if (!len)
 		smp_rmb();
 
-	add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
+	va_copy(ap, args);
+	add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, ap);
+	va_end(ap);
 	if (!add)
 		return 0;
 
@@ -278,7 +281,7 @@ void printk_safe_flush_on_panic(void)
 	 * Make sure that we could access the main ring buffer.
 	 * Do not risk a double release when more CPUs are up.
 	 */
-	if (in_nmi() && raw_spin_is_locked(&logbuf_lock)) {
+	if (raw_spin_is_locked(&logbuf_lock)) {
 		if (num_online_cpus() > 1)
 			return;
 
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7a693e31184a..40cea6735c2d 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -270,6 +270,12 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 	}
 }
 
+/* Returns first leaf rcu_node of the specified RCU flavor. */
+#define rcu_first_leaf_node(rsp) ((rsp)->level[rcu_num_lvls - 1])
+
+/* Is this rcu_node a leaf? */
+#define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
+
 /*
  * Do a full breadth-first scan of the rcu_node structures for the
  * specified rcu_state structure.
@@ -284,8 +290,7 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
  * rcu_node tree with but one rcu_node structure, this loop is a no-op.
  */
 #define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
-	for ((rnp) = &(rsp)->node[0]; \
-	     (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
+	for ((rnp) = &(rsp)->node[0]; !rcu_is_leaf_node(rsp, rnp); (rnp)++)
 
 /*
  * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
@@ -294,7 +299,7 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
  * It is still a leaf node, even if it is also the root node.
  */
 #define rcu_for_each_leaf_node(rsp, rnp) \
-	for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
+	for ((rnp) = rcu_first_leaf_node(rsp); \
 	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
 
 /*
@@ -486,6 +491,7 @@ void rcu_force_quiescent_state(void);
 void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
 extern struct workqueue_struct *rcu_gp_wq;
+extern struct workqueue_struct *rcu_par_gp_wq;
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
 #ifdef CONFIG_RCU_NOCB_CPU
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 88cba7c2956c..5aff271adf1e 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -404,24 +404,6 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
 }
 
 /*
- * Scan the specified rcu_segcblist structure for callbacks that need
- * a grace period later than the one specified by "seq".  We don't look
- * at the RCU_DONE_TAIL or RCU_NEXT_TAIL segments because they don't
- * have a grace-period sequence number.
- */
-bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
-				    unsigned long seq)
-{
-	int i;
-
-	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
-		if (rsclp->tails[i - 1] != rsclp->tails[i] &&
-		    ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
-			return true;
-	return false;
-}
-
-/*
  * Merge the source rcu_segcblist structure into the destination
  * rcu_segcblist structure, then initialize the source.  Any pending
  * callbacks from the source get to start over.  It is best to
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 581c12b63544..948470cef385 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -134,7 +134,5 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
 				   struct rcu_cblist *rclp);
 void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
 bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
-bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
-				    unsigned long seq);
 void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
 			 struct rcu_segcblist *src_rsclp);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 777e7a6a0292..e232846516b3 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -369,7 +369,7 @@ static bool __maybe_unused torturing_tasks(void)
  */
 static void rcu_perf_wait_shutdown(void)
 {
-	cond_resched_rcu_qs();
+	cond_resched_tasks_rcu_qs();
 	if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters)
 		return;
 	while (!torture_must_stop())
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 680c96d8c00f..e628fcfd1bde 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -593,7 +593,12 @@ static void srcu_torture_init(void)
 
 static void srcu_torture_cleanup(void)
 {
-	cleanup_srcu_struct(&srcu_ctld);
+	static DEFINE_TORTURE_RANDOM(rand);
+
+	if (torture_random(&rand) & 0x800)
+		cleanup_srcu_struct(&srcu_ctld);
+	else
+		cleanup_srcu_struct_quiesced(&srcu_ctld);
 	srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
 }
 
@@ -1609,6 +1614,9 @@ static enum cpuhp_state rcutor_hp;
 static void
 rcu_torture_cleanup(void)
 {
+	int flags = 0;
+	unsigned long gpnum = 0;
+	unsigned long completed = 0;
 	int i;
 
 	rcutorture_record_test_transition();
@@ -1639,6 +1647,11 @@ rcu_torture_cleanup(void)
 		fakewriter_tasks = NULL;
 	}
 
+	rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed);
+	srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
+				&flags, &gpnum, &completed);
+	pr_alert("%s:  End-test grace-period state: g%lu c%lu f%#x\n",
+		 cur_ops->name, gpnum, completed, flags);
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
 	for (i = 0; i < ncbflooders; i++)
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 76ac5f50b2c7..622792abe41a 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -86,16 +86,19 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
  * Must invoke this after you are finished using a given srcu_struct that
  * was initialized via init_srcu_struct(), else you leak memory.
  */
-void cleanup_srcu_struct(struct srcu_struct *sp)
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
 {
 	WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
-	flush_work(&sp->srcu_work);
+	if (quiesced)
+		WARN_ON(work_pending(&sp->srcu_work));
+	else
+		flush_work(&sp->srcu_work);
 	WARN_ON(sp->srcu_gp_running);
 	WARN_ON(sp->srcu_gp_waiting);
 	WARN_ON(sp->srcu_cb_head);
 	WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail);
 }
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
 
 /*
  * Removes the count for the old reader from the appropriate element of
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index fb560fca9ef4..b4123d7a2cec 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -366,24 +366,28 @@ static unsigned long srcu_get_delay(struct srcu_struct *sp)
 	return SRCU_INTERVAL;
 }
 
-/**
- * cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @sp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
- */
-void cleanup_srcu_struct(struct srcu_struct *sp)
+/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
 {
 	int cpu;
 
 	if (WARN_ON(!srcu_get_delay(sp)))
-		return; /* Leakage unless caller handles error. */
+		return; /* Just leak it! */
 	if (WARN_ON(srcu_readers_active(sp)))
-		return; /* Leakage unless caller handles error. */
-	flush_delayed_work(&sp->work);
+		return; /* Just leak it! */
+	if (quiesced) {
+		if (WARN_ON(delayed_work_pending(&sp->work)))
+			return; /* Just leak it! */
+	} else {
+		flush_delayed_work(&sp->work);
+	}
 	for_each_possible_cpu(cpu)
-		flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+		if (quiesced) {
+			if (WARN_ON(delayed_work_pending(&per_cpu_ptr(sp->sda, cpu)->work)))
+				return; /* Just leak it! */
+		} else {
+			flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+		}
 	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
 	    WARN_ON(srcu_readers_active(sp))) {
 		pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
@@ -392,7 +396,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp)
 	free_percpu(sp->sda);
 	sp->sda = NULL;
 }
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2a734692a581..aa7cade1b9f3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -524,8 +524,6 @@ module_param(rcu_kick_kthreads, bool, 0644);
 static ulong jiffies_till_sched_qs = HZ / 10;
 module_param(jiffies_till_sched_qs, ulong, 0444);
 
-static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
-				  struct rcu_data *rdp);
 static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp));
 static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(void);
@@ -711,44 +709,6 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 }
 
 /*
- * Is there any need for future grace periods?
- * Interrupts must be disabled.  If the caller does not hold the root
- * rnp_node structure's ->lock, the results are advisory only.
- */
-static int rcu_future_needs_gp(struct rcu_state *rsp)
-{
-	struct rcu_node *rnp = rcu_get_root(rsp);
-	int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
-	int *fp = &rnp->need_future_gp[idx];
-
-	lockdep_assert_irqs_disabled();
-	return READ_ONCE(*fp);
-}
-
-/*
- * Does the current CPU require a not-yet-started grace period?
- * The caller must have disabled interrupts to prevent races with
- * normal callback registry.
- */
-static bool
-cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
-{
-	lockdep_assert_irqs_disabled();
-	if (rcu_gp_in_progress(rsp))
-		return false;  /* No, a grace period is already in progress. */
-	if (rcu_future_needs_gp(rsp))
-		return true;  /* Yes, a no-CBs CPU needs one. */
-	if (!rcu_segcblist_is_enabled(&rdp->cblist))
-		return false;  /* No, this is a no-CBs (or offline) CPU. */
-	if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
-		return true;  /* Yes, CPU has newly registered callbacks. */
-	if (rcu_segcblist_future_gp_needed(&rdp->cblist,
-					   READ_ONCE(rsp->completed)))
-		return true;  /* Yes, CBs for future grace period. */
-	return false; /* No grace period needed. */
-}
-
-/*
  * Enter an RCU extended quiescent state, which can be either the
  * idle loop or adaptive-tickless usermode execution.
  *
@@ -1234,10 +1194,10 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	}
 
 	/*
-	 * Has this CPU encountered a cond_resched_rcu_qs() since the
-	 * beginning of the grace period?  For this to be the case,
-	 * the CPU has to have noticed the current grace period.  This
-	 * might not be the case for nohz_full CPUs looping in the kernel.
+	 * Has this CPU encountered a cond_resched() since the beginning
+	 * of the grace period?  For this to be the case, the CPU has to
+	 * have noticed the current grace period.  This might not be the
+	 * case for nohz_full CPUs looping in the kernel.
 	 */
 	jtsq = jiffies_till_sched_qs;
 	ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
@@ -1642,18 +1602,30 @@ static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
 		return rnp->completed + 1;
 
 	/*
+	 * If the current rcu_node structure believes that RCU is
+	 * idle, and if the rcu_state structure does not yet reflect
+	 * the start of a new grace period, then the next grace period
+	 * will suffice.  The memory barrier is needed to accurately
+	 * sample the rsp->gpnum, and pairs with the second lock
+	 * acquisition in rcu_gp_init(), which is augmented with
+	 * smp_mb__after_unlock_lock() for this purpose.
+	 */
+	if (rnp->gpnum == rnp->completed) {
+		smp_mb(); /* See above block comment. */
+		if (READ_ONCE(rsp->gpnum) == rnp->completed)
+			return rnp->completed + 1;
+	}
+
+	/*
 	 * Otherwise, wait for a possible partial grace period and
 	 * then the subsequent full grace period.
 	 */
 	return rnp->completed + 2;
 }
 
-/*
- * Trace-event helper function for rcu_start_future_gp() and
- * rcu_nocb_wait_gp().
- */
-static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
-				unsigned long c, const char *s)
+/* Trace-event wrapper function for trace_rcu_future_grace_period.  */
+static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+			      unsigned long c, const char *s)
 {
 	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
 				      rnp->completed, c, rnp->level,
@@ -1661,96 +1633,67 @@ static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 }
 
 /*
- * Start some future grace period, as needed to handle newly arrived
+ * Start the specified grace period, as needed to handle newly arrived
  * callbacks.  The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp field.  Returns true if there
+ * rcu_node structure's ->need_future_gp[] field.  Returns true if there
  * is reason to awaken the grace-period kthread.
  *
- * The caller must hold the specified rcu_node structure's ->lock.
+ * The caller must hold the specified rcu_node structure's ->lock, which
+ * is why the caller is responsible for waking the grace-period kthread.
  */
-static bool __maybe_unused
-rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
-		    unsigned long *c_out)
+static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+			      unsigned long c)
 {
-	unsigned long c;
 	bool ret = false;
-	struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
-
-	raw_lockdep_assert_held_rcu_node(rnp);
-
-	/*
-	 * Pick up grace-period number for new callbacks.  If this
-	 * grace period is already marked as needed, return to the caller.
-	 */
-	c = rcu_cbs_completed(rdp->rsp, rnp);
-	trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf"));
-	if (rnp->need_future_gp[c & 0x1]) {
-		trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf"));
-		goto out;
-	}
+	struct rcu_state *rsp = rdp->rsp;
+	struct rcu_node *rnp_root;
 
 	/*
-	 * If either this rcu_node structure or the root rcu_node structure
-	 * believe that a grace period is in progress, then we must wait
-	 * for the one following, which is in "c".  Because our request
-	 * will be noticed at the end of the current grace period, we don't
-	 * need to explicitly start one.  We only do the lockless check
-	 * of rnp_root's fields if the current rcu_node structure thinks
-	 * there is no grace period in flight, and because we hold rnp->lock,
-	 * the only possible change is when rnp_root's two fields are
-	 * equal, in which case rnp_root->gpnum might be concurrently
-	 * incremented.  But that is OK, as it will just result in our
-	 * doing some extra useless work.
+	 * Use funnel locking to either acquire the root rcu_node
+	 * structure's lock or bail out if the need for this grace period
+	 * has already been recorded -- or has already started.  If there
+	 * is already a grace period in progress in a non-leaf node, no
+	 * recording is needed because the end of the grace period will
+	 * scan the leaf rcu_node structures.  Note that rnp->lock must
+	 * not be released.
 	 */
-	if (rnp->gpnum != rnp->completed ||
-	    READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) {
-		rnp->need_future_gp[c & 0x1]++;
-		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
-		goto out;
+	raw_lockdep_assert_held_rcu_node(rnp);
+	trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
+	for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
+		if (rnp_root != rnp)
+			raw_spin_lock_rcu_node(rnp_root);
+		WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum +
+					  need_future_gp_mask(), c));
+		if (need_future_gp_element(rnp_root, c) ||
+		    ULONG_CMP_GE(rnp_root->gpnum, c) ||
+		    (rnp != rnp_root &&
+		     rnp_root->gpnum != rnp_root->completed)) {
+			trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
+			goto unlock_out;
+		}
+		need_future_gp_element(rnp_root, c) = true;
+		if (rnp_root != rnp && rnp_root->parent != NULL)
+			raw_spin_unlock_rcu_node(rnp_root);
+		if (!rnp_root->parent)
+			break;  /* At root, and perhaps also leaf. */
 	}
 
-	/*
-	 * There might be no grace period in progress.  If we don't already
-	 * hold it, acquire the root rcu_node structure's lock in order to
-	 * start one (if needed).
-	 */
-	if (rnp != rnp_root)
-		raw_spin_lock_rcu_node(rnp_root);
-
-	/*
-	 * Get a new grace-period number.  If there really is no grace
-	 * period in progress, it will be smaller than the one we obtained
-	 * earlier.  Adjust callbacks as needed.
-	 */
-	c = rcu_cbs_completed(rdp->rsp, rnp_root);
-	if (!rcu_is_nocb_cpu(rdp->cpu))
-		(void)rcu_segcblist_accelerate(&rdp->cblist, c);
-
-	/*
-	 * If the needed for the required grace period is already
-	 * recorded, trace and leave.
-	 */
-	if (rnp_root->need_future_gp[c & 0x1]) {
-		trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartedroot"));
+	/* If GP already in progress, just leave, otherwise start one. */
+	if (rnp_root->gpnum != rnp_root->completed) {
+		trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
 		goto unlock_out;
 	}
-
-	/* Record the need for the future grace period. */
-	rnp_root->need_future_gp[c & 0x1]++;
-
-	/* If a grace period is not already in progress, start one. */
-	if (rnp_root->gpnum != rnp_root->completed) {
-		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot"));
-	} else {
-		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot"));
-		ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
+	trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
+	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
+	if (!rsp->gp_kthread) {
+		trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
+		goto unlock_out;
 	}
+	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
+	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
 	if (rnp != rnp_root)
 		raw_spin_unlock_rcu_node(rnp_root);
-out:
-	if (c_out != NULL)
-		*c_out = c;
 	return ret;
 }
 
@@ -1758,16 +1701,16 @@ out:
  * Clean up any old requests for the just-ended grace period.  Also return
  * whether any additional grace periods have been requested.
  */
-static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-	int c = rnp->completed;
-	int needmore;
+	unsigned long c = rnp->completed;
+	bool needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
-	rnp->need_future_gp[c & 0x1] = 0;
-	needmore = rnp->need_future_gp[(c + 1) & 0x1];
-	trace_rcu_future_gp(rnp, rdp, c,
-			    needmore ? TPS("CleanupMore") : TPS("Cleanup"));
+	need_future_gp_element(rnp, c) = false;
+	needmore = need_any_future_gp(rnp);
+	trace_rcu_this_gp(rnp, rdp, c,
+			  needmore ? TPS("CleanupMore") : TPS("Cleanup"));
 	return needmore;
 }
 
@@ -1802,6 +1745,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 			       struct rcu_data *rdp)
 {
+	unsigned long c;
 	bool ret = false;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
@@ -1820,8 +1764,9 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 	 * accelerating callback invocation to an earlier grace-period
 	 * number.
 	 */
-	if (rcu_segcblist_accelerate(&rdp->cblist, rcu_cbs_completed(rsp, rnp)))
-		ret = rcu_start_future_gp(rnp, rdp, NULL);
+	c = rcu_cbs_completed(rsp, rnp);
+	if (rcu_segcblist_accelerate(&rdp->cblist, c))
+		ret = rcu_start_this_gp(rnp, rdp, c);
 
 	/* Trace depending on how much we were able to accelerate. */
 	if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
@@ -2049,7 +1994,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq_rcu_node(rnp);
-		cond_resched_rcu_qs();
+		cond_resched_tasks_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
 
@@ -2108,7 +2053,6 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 {
 	unsigned long gp_duration;
 	bool needgp = false;
-	int nocb = 0;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	struct swait_queue_head *sq;
@@ -2147,31 +2091,35 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		if (rnp == rdp->mynode)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
 		/* smp_mb() provided by prior unlock-lock pair. */
-		nocb += rcu_future_gp_cleanup(rsp, rnp);
+		needgp = rcu_future_gp_cleanup(rsp, rnp) || needgp;
 		sq = rcu_nocb_gp_get(rnp);
 		raw_spin_unlock_irq_rcu_node(rnp);
 		rcu_nocb_gp_cleanup(sq);
-		cond_resched_rcu_qs();
+		cond_resched_tasks_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
-	rcu_nocb_gp_set(rnp, nocb);
 
 	/* Declare grace period done. */
 	WRITE_ONCE(rsp->completed, rsp->gpnum);
 	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
 	rsp->gp_state = RCU_GP_IDLE;
+	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(rsp->rda);
+	if (need_any_future_gp(rnp)) {
+		trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
+				  TPS("CleanupMore"));
+		needgp = true;
+	}
 	/* Advance CBs to reduce false positives below. */
-	needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
-	if (needgp || cpu_needs_another_gp(rsp, rdp)) {
+	if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
 		WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
-		trace_rcu_grace_period(rsp->name,
-				       READ_ONCE(rsp->gpnum),
+		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
 				       TPS("newreq"));
 	}
+	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
 	raw_spin_unlock_irq_rcu_node(rnp);
 }
 
@@ -2202,7 +2150,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
-			cond_resched_rcu_qs();
+			cond_resched_tasks_rcu_qs();
 			WRITE_ONCE(rsp->gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
@@ -2247,7 +2195,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 				trace_rcu_grace_period(rsp->name,
 						       READ_ONCE(rsp->gpnum),
 						       TPS("fqsend"));
-				cond_resched_rcu_qs();
+				cond_resched_tasks_rcu_qs();
 				WRITE_ONCE(rsp->gp_activity, jiffies);
 				ret = 0; /* Force full wait till next FQS. */
 				j = jiffies_till_next_fqs;
@@ -2260,7 +2208,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 				}
 			} else {
 				/* Deal with stray signal. */
-				cond_resched_rcu_qs();
+				cond_resched_tasks_rcu_qs();
 				WRITE_ONCE(rsp->gp_activity, jiffies);
 				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
@@ -2283,71 +2231,6 @@ static int __noreturn rcu_gp_kthread(void *arg)
 }
 
 /*
- * Start a new RCU grace period if warranted, re-initializing the hierarchy
- * in preparation for detecting the next grace period.  The caller must hold
- * the root node's ->lock and hard irqs must be disabled.
- *
- * Note that it is legal for a dying CPU (which is marked as offline) to
- * invoke this function.  This can happen when the dying CPU reports its
- * quiescent state.
- *
- * Returns true if the grace-period kthread must be awakened.
- */
-static bool
-rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
-		      struct rcu_data *rdp)
-{
-	raw_lockdep_assert_held_rcu_node(rnp);
-	if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) {
-		/*
-		 * Either we have not yet spawned the grace-period
-		 * task, this CPU does not need another grace period,
-		 * or a grace period is already in progress.
-		 * Either way, don't start a new grace period.
-		 */
-		return false;
-	}
-	WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
-	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
-			       TPS("newreq"));
-
-	/*
-	 * We can't do wakeups while holding the rnp->lock, as that
-	 * could cause possible deadlocks with the rq->lock. Defer
-	 * the wakeup to our caller.
-	 */
-	return true;
-}
-
-/*
- * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's
- * callbacks.  Note that rcu_start_gp_advanced() cannot do this because it
- * is invoked indirectly from rcu_advance_cbs(), which would result in
- * endless recursion -- or would do so if it wasn't for the self-deadlock
- * that is encountered beforehand.
- *
- * Returns true if the grace-period kthread needs to be awakened.
- */
-static bool rcu_start_gp(struct rcu_state *rsp)
-{
-	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
-	struct rcu_node *rnp = rcu_get_root(rsp);
-	bool ret = false;
-
-	/*
-	 * If there is no grace period in progress right now, any
-	 * callbacks we have up to this point will be satisfied by the
-	 * next grace period.  Also, advancing the callbacks reduces the
-	 * probability of false positives from cpu_needs_another_gp()
-	 * resulting in pointless grace periods.  So, advance callbacks
-	 * then start the grace period!
-	 */
-	ret = rcu_advance_cbs(rsp, rnp, rdp) || ret;
-	ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret;
-	return ret;
-}
-
-/*
  * Report a full set of quiescent states to the specified rcu_state data
  * structure.  Invoke rcu_gp_kthread_wake() to awaken the grace-period
  * kthread if another grace period is required.  Whether we wake
@@ -2398,7 +2281,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			return;
 		}
 		WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
-		WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1 &&
+		WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
 			     rcu_preempt_blocked_readers_cgp(rnp));
 		rnp->qsmask &= ~mask;
 		trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
@@ -2782,7 +2665,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rsp, rnp) {
-		cond_resched_rcu_qs();
+		cond_resched_tasks_rcu_qs();
 		mask = 0;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->qsmask == 0) {
@@ -2874,22 +2757,27 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	unsigned long flags;
 	bool needwake;
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
+	struct rcu_node *rnp;
 
 	WARN_ON_ONCE(!rdp->beenonline);
 
 	/* Update RCU state based on any recent quiescent states. */
 	rcu_check_quiescent_state(rsp, rdp);
 
-	/* Does this CPU require a not-yet-started grace period? */
-	local_irq_save(flags);
-	if (cpu_needs_another_gp(rsp, rdp)) {
-		raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */
-		needwake = rcu_start_gp(rsp);
-		raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags);
-		if (needwake)
-			rcu_gp_kthread_wake(rsp);
-	} else {
-		local_irq_restore(flags);
+	/* No grace period and unregistered callbacks? */
+	if (!rcu_gp_in_progress(rsp) &&
+	    rcu_segcblist_is_enabled(&rdp->cblist)) {
+		local_irq_save(flags);
+		if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
+			local_irq_restore(flags);
+		} else {
+			rnp = rdp->mynode;
+			raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
+			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+			if (needwake)
+				rcu_gp_kthread_wake(rsp);
+		}
 	}
 
 	/* If there are callbacks ready, invoke them. */
@@ -2973,11 +2861,11 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 
 		/* Start a new grace period if one not already started. */
 		if (!rcu_gp_in_progress(rsp)) {
-			struct rcu_node *rnp_root = rcu_get_root(rsp);
+			struct rcu_node *rnp = rdp->mynode;
 
-			raw_spin_lock_rcu_node(rnp_root);
-			needwake = rcu_start_gp(rsp);
-			raw_spin_unlock_rcu_node(rnp_root);
+			raw_spin_lock_rcu_node(rnp);
+			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+			raw_spin_unlock_rcu_node(rnp);
 			if (needwake)
 				rcu_gp_kthread_wake(rsp);
 		} else {
@@ -3368,7 +3256,9 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 		return 1;
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
-	if (cpu_needs_another_gp(rsp, rdp))
+	if (!rcu_gp_in_progress(rsp) &&
+	    rcu_segcblist_is_enabled(&rdp->cblist) &&
+	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 		return 1;
 
 	/* Has another RCU grace period completed?  */
@@ -3775,6 +3665,8 @@ int rcutree_dead_cpu(unsigned int cpu)
 	return 0;
 }
 
+static DEFINE_PER_CPU(int, rcu_cpu_started);
+
 /*
  * Mark the specified CPU as being online so that subsequent grace periods
  * (both expedited and normal) will wait on it.  Note that this means that
@@ -3796,6 +3688,11 @@ void rcu_cpu_starting(unsigned int cpu)
 	struct rcu_node *rnp;
 	struct rcu_state *rsp;
 
+	if (per_cpu(rcu_cpu_started, cpu))
+		return;
+
+	per_cpu(rcu_cpu_started, cpu) = 1;
+
 	for_each_rcu_flavor(rsp) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
 		rnp = rdp->mynode;
@@ -3852,6 +3749,8 @@ void rcu_report_dead(unsigned int cpu)
 	preempt_enable();
 	for_each_rcu_flavor(rsp)
 		rcu_cleanup_dying_idle_cpu(cpu, rsp);
+
+	per_cpu(rcu_cpu_started, cpu) = 0;
 }
 
 /* Migrate the dead CPU's callbacks to the current CPU. */
@@ -3861,6 +3760,7 @@ static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
 	struct rcu_data *my_rdp;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
+	bool needwake;
 
 	if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist))
 		return;  /* No callbacks to migrate. */
@@ -3872,12 +3772,15 @@ static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
 		return;
 	}
 	raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
-	rcu_advance_cbs(rsp, rnp_root, rdp); /* Leverage recent GPs. */
-	rcu_advance_cbs(rsp, rnp_root, my_rdp); /* Assign GP to pending CBs. */
+	/* Leverage recent GPs and set GP for new callbacks. */
+	needwake = rcu_advance_cbs(rsp, rnp_root, rdp) ||
+		   rcu_advance_cbs(rsp, rnp_root, my_rdp);
 	rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist);
 	WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
 		     !rcu_segcblist_n_cbs(&my_rdp->cblist));
 	raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags);
+	if (needwake)
+		rcu_gp_kthread_wake(rsp);
 	WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
 		  !rcu_segcblist_empty(&rdp->cblist),
 		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
@@ -4056,7 +3959,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 
 	init_swait_queue_head(&rsp->gp_wq);
 	init_swait_queue_head(&rsp->expedited_wq);
-	rnp = rsp->level[rcu_num_lvls - 1];
+	rnp = rcu_first_leaf_node(rsp);
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
 			rnp++;
@@ -4168,6 +4071,7 @@ static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
 }
 
 struct workqueue_struct *rcu_gp_wq;
+struct workqueue_struct *rcu_par_gp_wq;
 
 void __init rcu_init(void)
 {
@@ -4199,6 +4103,8 @@ void __init rcu_init(void)
 	/* Create workqueue for expedited GPs and for Tree SRCU. */
 	rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!rcu_gp_wq);
+	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
+	WARN_ON(!rcu_par_gp_wq);
 }
 
 #include "tree_exp.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index f491ab4f2e8e..78e051dffc5b 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -58,6 +58,14 @@ struct rcu_dynticks {
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 };
 
+/* Communicate arguments to a workqueue handler. */
+struct rcu_exp_work {
+	smp_call_func_t rew_func;
+	struct rcu_state *rew_rsp;
+	unsigned long rew_s;
+	struct work_struct rew_work;
+};
+
 /* RCU's kthread states for tracing. */
 #define RCU_KTHREAD_STOPPED  0
 #define RCU_KTHREAD_RUNNING  1
@@ -150,15 +158,32 @@ struct rcu_node {
 	struct swait_queue_head nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-	int need_future_gp[2];
-				/* Counts of upcoming no-CB GP requests. */
+	u8 need_future_gp[4];	/* Counts of upcoming GP requests. */
 	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
 
 	spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
 	unsigned long exp_seq_rq;
 	wait_queue_head_t exp_wq[4];
+	struct rcu_exp_work rew;
+	bool exp_need_flush;	/* Need to flush workitem? */
 } ____cacheline_internodealigned_in_smp;
 
+/* Accessors for ->need_future_gp[] array. */
+#define need_future_gp_mask() \
+	(ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
+#define need_future_gp_element(rnp, c) \
+	((rnp)->need_future_gp[(c) & need_future_gp_mask()])
+#define need_any_future_gp(rnp)						\
+({									\
+	int __i;							\
+	bool __nonzero = false;						\
+									\
+	for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++)	\
+		__nonzero = __nonzero ||				\
+			    READ_ONCE((rnp)->need_future_gp[__i]);	\
+	__nonzero;							\
+})
+
 /*
  * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
  * are indexed relative to this interval rather than the global CPU ID space.
@@ -224,10 +249,6 @@ struct rcu_data {
 #ifdef CONFIG_RCU_FAST_NO_HZ
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
-	atomic_long_t exp_workdone0;	/* # done by workqueue. */
-	atomic_long_t exp_workdone1;	/* # done by others #1. */
-	atomic_long_t exp_workdone2;	/* # done by others #2. */
-	atomic_long_t exp_workdone3;	/* # done by others #3. */
 	int exp_dynticks_snap;		/* Double-check need for IPI. */
 
 	/* 6) Callback offloading. */
@@ -408,7 +429,6 @@ extern struct rcu_state rcu_preempt_state;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
-bool rcu_eqs_special_set(int cpu);
 
 #ifdef CONFIG_RCU_BOOST
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@@ -438,7 +458,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static void invoke_rcu_callbacks_kthread(void);
 static bool rcu_is_callbacks_kthread(void);
 #ifdef CONFIG_RCU_BOOST
-static void rcu_preempt_do_callbacks(void);
 static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 						 struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_RCU_BOOST */
@@ -454,7 +473,6 @@ static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
 static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
 static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index f72eefab8543..d40708e8c5d6 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -20,6 +20,8 @@
  * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
  */
 
+#include <linux/lockdep.h>
+
 /*
  * Record the start of an expedited grace period.
  */
@@ -154,15 +156,35 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
  * for the current expedited grace period.  Works only for preemptible
  * RCU -- other RCU implementation use other means.
  *
- * Caller must hold the rcu_state's exp_mutex.
+ * Caller must hold the specificed rcu_node structure's ->lock
  */
 static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
 {
+	raw_lockdep_assert_held_rcu_node(rnp);
+
 	return rnp->exp_tasks == NULL &&
 	       READ_ONCE(rnp->expmask) == 0;
 }
 
 /*
+ * Like sync_rcu_preempt_exp_done(), but this function assumes the caller
+ * doesn't hold the rcu_node's ->lock, and will acquire and release the lock
+ * itself
+ */
+static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp)
+{
+	unsigned long flags;
+	bool ret;
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	ret = sync_rcu_preempt_exp_done(rnp);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+	return ret;
+}
+
+
+/*
  * Report the exit from RCU read-side critical section for the last task
  * that queued itself during or before the current expedited preemptible-RCU
  * grace period.  This event is reported either to the rcu_node structure on
@@ -170,8 +192,7 @@ static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
  * recursively up the tree.  (Calm down, calm down, we do the recursion
  * iteratively!)
  *
- * Caller must hold the rcu_state's exp_mutex and the specified rcu_node
- * structure's ->lock.
+ * Caller must hold the specified rcu_node structure's ->lock.
  */
 static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 				 bool wake, unsigned long flags)
@@ -207,8 +228,6 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 /*
  * Report expedited quiescent state for specified node.  This is a
  * lock-acquisition wrapper function for __rcu_report_exp_rnp().
- *
- * Caller must hold the rcu_state's exp_mutex.
  */
 static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
 					      struct rcu_node *rnp, bool wake)
@@ -221,8 +240,7 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
 
 /*
  * Report expedited quiescent state for multiple CPUs, all covered by the
- * specified leaf rcu_node structure.  Caller must hold the rcu_state's
- * exp_mutex.
+ * specified leaf rcu_node structure.
  */
 static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
 				    unsigned long mask, bool wake)
@@ -248,14 +266,12 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
 }
 
 /* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
-static bool sync_exp_work_done(struct rcu_state *rsp, atomic_long_t *stat,
-			       unsigned long s)
+static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s)
 {
 	if (rcu_exp_gp_seq_done(rsp, s)) {
 		trace_rcu_exp_grace_period(rsp->name, s, TPS("done"));
 		/* Ensure test happens before caller kfree(). */
 		smp_mb__before_atomic(); /* ^^^ */
-		atomic_long_inc(stat);
 		return true;
 	}
 	return false;
@@ -289,7 +305,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 	 * promoting locality and is not strictly needed for correctness.
 	 */
 	for (; rnp != NULL; rnp = rnp->parent) {
-		if (sync_exp_work_done(rsp, &rdp->exp_workdone1, s))
+		if (sync_exp_work_done(rsp, s))
 			return true;
 
 		/* Work not done, either wait here or go up. */
@@ -302,8 +318,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 						  rnp->grplo, rnp->grphi,
 						  TPS("wait"));
 			wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
-				   sync_exp_work_done(rsp,
-						      &rdp->exp_workdone2, s));
+				   sync_exp_work_done(rsp, s));
 			return true;
 		}
 		rnp->exp_seq_rq = s; /* Followers can wait on us. */
@@ -313,7 +328,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 	}
 	mutex_lock(&rsp->exp_mutex);
 fastpath:
-	if (sync_exp_work_done(rsp, &rdp->exp_workdone3, s)) {
+	if (sync_exp_work_done(rsp, s)) {
 		mutex_unlock(&rsp->exp_mutex);
 		return true;
 	}
@@ -362,93 +377,129 @@ static void sync_sched_exp_online_cleanup(int cpu)
 }
 
 /*
- * Select the nodes that the upcoming expedited grace period needs
- * to wait for.
+ * Select the CPUs within the specified rcu_node that the upcoming
+ * expedited grace period needs to wait for.
  */
-static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
-				     smp_call_func_t func)
+static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 {
 	int cpu;
 	unsigned long flags;
+	smp_call_func_t func;
 	unsigned long mask_ofl_test;
 	unsigned long mask_ofl_ipi;
 	int ret;
-	struct rcu_node *rnp;
-
-	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
-	sync_exp_reset_tree(rsp);
-	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select"));
-	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	struct rcu_exp_work *rewp =
+		container_of(wp, struct rcu_exp_work, rew_work);
+	struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
+	struct rcu_state *rsp = rewp->rew_rsp;
 
-		/* Each pass checks a CPU for identity, offline, and idle. */
-		mask_ofl_test = 0;
-		for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
-			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
-			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-			struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
-			int snap;
+	func = rewp->rew_func;
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 
-			if (raw_smp_processor_id() == cpu ||
-			    !(rnp->qsmaskinitnext & mask)) {
+	/* Each pass checks a CPU for identity, offline, and idle. */
+	mask_ofl_test = 0;
+	for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+		unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+		struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+		struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
+		int snap;
+
+		if (raw_smp_processor_id() == cpu ||
+		    !(rnp->qsmaskinitnext & mask)) {
+			mask_ofl_test |= mask;
+		} else {
+			snap = rcu_dynticks_snap(rdtp);
+			if (rcu_dynticks_in_eqs(snap))
 				mask_ofl_test |= mask;
-			} else {
-				snap = rcu_dynticks_snap(rdtp);
-				if (rcu_dynticks_in_eqs(snap))
-					mask_ofl_test |= mask;
-				else
-					rdp->exp_dynticks_snap = snap;
-			}
+			else
+				rdp->exp_dynticks_snap = snap;
 		}
-		mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
-
-		/*
-		 * Need to wait for any blocked tasks as well.  Note that
-		 * additional blocking tasks will also block the expedited
-		 * GP until such time as the ->expmask bits are cleared.
-		 */
-		if (rcu_preempt_has_tasks(rnp))
-			rnp->exp_tasks = rnp->blkd_tasks.next;
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+	mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
 
-		/* IPI the remaining CPUs for expedited quiescent state. */
-		for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
-			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
-			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+	/*
+	 * Need to wait for any blocked tasks as well.	Note that
+	 * additional blocking tasks will also block the expedited GP
+	 * until such time as the ->expmask bits are cleared.
+	 */
+	if (rcu_preempt_has_tasks(rnp))
+		rnp->exp_tasks = rnp->blkd_tasks.next;
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
-			if (!(mask_ofl_ipi & mask))
-				continue;
+	/* IPI the remaining CPUs for expedited quiescent state. */
+	for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+		unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+		struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+
+		if (!(mask_ofl_ipi & mask))
+			continue;
 retry_ipi:
-			if (rcu_dynticks_in_eqs_since(rdp->dynticks,
-						      rdp->exp_dynticks_snap)) {
-				mask_ofl_test |= mask;
-				continue;
-			}
-			ret = smp_call_function_single(cpu, func, rsp, 0);
-			if (!ret) {
-				mask_ofl_ipi &= ~mask;
-				continue;
-			}
-			/* Failed, raced with CPU hotplug operation. */
-			raw_spin_lock_irqsave_rcu_node(rnp, flags);
-			if ((rnp->qsmaskinitnext & mask) &&
-			    (rnp->expmask & mask)) {
-				/* Online, so delay for a bit and try again. */
-				raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-				trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
-				schedule_timeout_uninterruptible(1);
-				goto retry_ipi;
-			}
-			/* CPU really is offline, so we can ignore it. */
-			if (!(rnp->expmask & mask))
-				mask_ofl_ipi &= ~mask;
+		if (rcu_dynticks_in_eqs_since(rdp->dynticks,
+					      rdp->exp_dynticks_snap)) {
+			mask_ofl_test |= mask;
+			continue;
+		}
+		ret = smp_call_function_single(cpu, func, rsp, 0);
+		if (!ret) {
+			mask_ofl_ipi &= ~mask;
+			continue;
+		}
+		/* Failed, raced with CPU hotplug operation. */
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		if ((rnp->qsmaskinitnext & mask) &&
+		    (rnp->expmask & mask)) {
+			/* Online, so delay for a bit and try again. */
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+			trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
+			schedule_timeout_uninterruptible(1);
+			goto retry_ipi;
+		}
+		/* CPU really is offline, so we can ignore it. */
+		if (!(rnp->expmask & mask))
+			mask_ofl_ipi &= ~mask;
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+	/* Report quiescent states for those that went offline. */
+	mask_ofl_test |= mask_ofl_ipi;
+	if (mask_ofl_test)
+		rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
+}
+
+/*
+ * Select the nodes that the upcoming expedited grace period needs
+ * to wait for.
+ */
+static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
+				     smp_call_func_t func)
+{
+	struct rcu_node *rnp;
+
+	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
+	sync_exp_reset_tree(rsp);
+	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select"));
+
+	/* Schedule work for each leaf rcu_node structure. */
+	rcu_for_each_leaf_node(rsp, rnp) {
+		rnp->exp_need_flush = false;
+		if (!READ_ONCE(rnp->expmask))
+			continue; /* Avoid early boot non-existent wq. */
+		rnp->rew.rew_func = func;
+		rnp->rew.rew_rsp = rsp;
+		if (!READ_ONCE(rcu_par_gp_wq) ||
+		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
+			/* No workqueues yet. */
+			sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
+			continue;
 		}
-		/* Report quiescent states for those that went offline. */
-		mask_ofl_test |= mask_ofl_ipi;
-		if (mask_ofl_test)
-			rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
+		INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
+		queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work);
+		rnp->exp_need_flush = true;
 	}
+
+	/* Wait for workqueue jobs (if any) to complete. */
+	rcu_for_each_leaf_node(rsp, rnp)
+		if (rnp->exp_need_flush)
+			flush_work(&rnp->rew.rew_work);
 }
 
 static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
@@ -469,9 +520,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	for (;;) {
 		ret = swait_event_timeout(
 				rsp->expedited_wq,
-				sync_rcu_preempt_exp_done(rnp_root),
+				sync_rcu_preempt_exp_done_unlocked(rnp_root),
 				jiffies_stall);
-		if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root))
+		if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root))
 			return;
 		WARN_ON(ret < 0);  /* workqueues should not be signaled. */
 		if (rcu_cpu_stall_suppress)
@@ -504,7 +555,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 			rcu_for_each_node_breadth_first(rsp, rnp) {
 				if (rnp == rnp_root)
 					continue; /* printed unconditionally */
-				if (sync_rcu_preempt_exp_done(rnp))
+				if (sync_rcu_preempt_exp_done_unlocked(rnp))
 					continue;
 				pr_cont(" l=%u:%d-%d:%#lx/%c",
 					rnp->level, rnp->grplo, rnp->grphi,
@@ -560,14 +611,6 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
 	mutex_unlock(&rsp->exp_wake_mutex);
 }
 
-/* Let the workqueue handler know what it is supposed to do. */
-struct rcu_exp_work {
-	smp_call_func_t rew_func;
-	struct rcu_state *rew_rsp;
-	unsigned long rew_s;
-	struct work_struct rew_work;
-};
-
 /*
  * Common code to drive an expedited grace period forward, used by
  * workqueues and mid-boot-time tasks.
@@ -633,7 +676,7 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
 	rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
 	rnp = rcu_get_root(rsp);
 	wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
-		   sync_exp_work_done(rsp, &rdp->exp_workdone0, s));
+		   sync_exp_work_done(rsp, s));
 	smp_mb(); /* Workqueue actions happen before return. */
 
 	/* Let the next expedited grace period start. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 84fbee4686d3..7fd12039e512 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -182,7 +182,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 
 	raw_lockdep_assert_held_rcu_node(rnp);
 	WARN_ON_ONCE(rdp->mynode != rnp);
-	WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
+	WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
 
 	/*
 	 * Decide where to queue the newly blocked task.  In theory,
@@ -384,6 +384,50 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 }
 
 /*
+ * Preemptible RCU implementation for rcu_read_lock().
+ * Just increment ->rcu_read_lock_nesting, shared state will be updated
+ * if we block.
+ */
+void __rcu_read_lock(void)
+{
+	current->rcu_read_lock_nesting++;
+	barrier();  /* critical section after entry code. */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_lock);
+
+/*
+ * Preemptible RCU implementation for rcu_read_unlock().
+ * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
+ * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
+ * invoke rcu_read_unlock_special() to clean up after a context switch
+ * in an RCU read-side critical section and other special cases.
+ */
+void __rcu_read_unlock(void)
+{
+	struct task_struct *t = current;
+
+	if (t->rcu_read_lock_nesting != 1) {
+		--t->rcu_read_lock_nesting;
+	} else {
+		barrier();  /* critical section before exit code. */
+		t->rcu_read_lock_nesting = INT_MIN;
+		barrier();  /* assign before ->rcu_read_unlock_special load */
+		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
+			rcu_read_unlock_special(t);
+		barrier();  /* ->rcu_read_unlock_special load before assign */
+		t->rcu_read_lock_nesting = 0;
+	}
+#ifdef CONFIG_PROVE_LOCKING
+	{
+		int rrln = READ_ONCE(t->rcu_read_lock_nesting);
+
+		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+	}
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_unlock);
+
+/*
  * Advance a ->blkd_tasks-list pointer to the next entry, instead
  * returning NULL if at the end of the list.
  */
@@ -489,7 +533,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		rnp = t->rcu_blocked_node;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
-		WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
+		WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
@@ -685,15 +729,6 @@ static void rcu_preempt_check_callbacks(void)
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
-#ifdef CONFIG_RCU_BOOST
-
-static void rcu_preempt_do_callbacks(void)
-{
-	rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
-}
-
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
 /**
  * call_rcu() - Queue an RCU callback for invocation after a grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -1140,7 +1175,7 @@ static void rcu_kthread_do_work(void)
 {
 	rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data));
 	rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data));
-	rcu_preempt_do_callbacks();
+	rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
 }
 
 static void rcu_cpu_kthread_setup(unsigned int cpu)
@@ -1607,7 +1642,7 @@ static int rcu_oom_notify(struct notifier_block *self,
 
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
-		cond_resched_rcu_qs();
+		cond_resched_tasks_rcu_qs();
 	}
 
 	/* Unconditionally decrement: no need to wake ourselves up. */
@@ -1780,19 +1815,6 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
 	swake_up_all(sq);
 }
 
-/*
- * Set the root rcu_node structure's ->need_future_gp field
- * based on the sum of those of all rcu_node structures.  This does
- * double-count the root rcu_node structure's requests, but this
- * is necessary to handle the possibility of a rcu_nocb_kthread()
- * having awakened during the time that the rcu_node structures
- * were being updated for the end of the previous grace period.
- */
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
-{
-	rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq;
-}
-
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
 {
 	return &rnp->nocb_gp_wq[rnp->completed & 0x1];
@@ -1966,7 +1988,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeOvf"));
 		} else {
-			wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE,
+			wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE_FORCE,
 					       TPS("WakeOvfIsDeferred"));
 		}
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2048,7 +2070,8 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	struct rcu_node *rnp = rdp->mynode;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	needwake = rcu_start_future_gp(rnp, rdp, &c);
+	c = rcu_cbs_completed(rdp->rsp, rnp);
+	needwake = rcu_start_this_gp(rnp, rdp, c);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	if (needwake)
 		rcu_gp_kthread_wake(rdp->rsp);
@@ -2057,7 +2080,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	 * Wait for the grace period.  Do so interruptibly to avoid messing
 	 * up the load average.
 	 */
-	trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait"));
+	trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
 	for (;;) {
 		swait_event_interruptible(
 			rnp->nocb_gp_wq[c & 0x1],
@@ -2065,9 +2088,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 		if (likely(d))
 			break;
 		WARN_ON(signal_pending(current));
-		trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait"));
+		trace_rcu_this_gp(rnp, rdp, c, TPS("ResumeWait"));
 	}
-	trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait"));
+	trace_rcu_this_gp(rnp, rdp, c, TPS("EndWait"));
 	smp_mb(); /* Ensure that CB invocation happens after GP end. */
 }
 
@@ -2236,7 +2259,7 @@ static int rcu_nocb_kthread(void *arg)
 				cl++;
 			c++;
 			local_bh_enable();
-			cond_resched_rcu_qs();
+			cond_resched_tasks_rcu_qs();
 			list = next;
 		}
 		trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
@@ -2292,7 +2315,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 void __init rcu_init_nohz(void)
 {
 	int cpu;
-	bool need_rcu_nocb_mask = true;
+	bool need_rcu_nocb_mask = false;
 	struct rcu_state *rsp;
 
 #if defined(CONFIG_NO_HZ_FULL)
@@ -2315,7 +2338,7 @@ void __init rcu_init_nohz(void)
 #endif /* #if defined(CONFIG_NO_HZ_FULL) */
 
 	if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
-		pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
+		pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
 		cpumask_and(rcu_nocb_mask, cpu_possible_mask,
 			    rcu_nocb_mask);
 	}
@@ -2495,10 +2518,6 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
 {
 }
 
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
-{
-}
-
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
 {
 	return NULL;
@@ -2587,8 +2606,7 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
 }
 
 /*
- * Bind the grace-period kthread for the sysidle flavor of RCU to the
- * timekeeping CPU.
+ * Bind the RCU grace-period kthreads to the housekeeping CPU.
  */
 static void rcu_bind_gp_kthread(void)
 {
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 68fa19a5e7bd..4c230a60ece4 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -226,54 +226,6 @@ core_initcall(rcu_set_runtime_mode);
 
 #endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */
 
-#ifdef CONFIG_PREEMPT_RCU
-
-/*
- * Preemptible RCU implementation for rcu_read_lock().
- * Just increment ->rcu_read_lock_nesting, shared state will be updated
- * if we block.
- */
-void __rcu_read_lock(void)
-{
-	current->rcu_read_lock_nesting++;
-	barrier();  /* critical section after entry code. */
-}
-EXPORT_SYMBOL_GPL(__rcu_read_lock);
-
-/*
- * Preemptible RCU implementation for rcu_read_unlock().
- * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
- * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
- * invoke rcu_read_unlock_special() to clean up after a context switch
- * in an RCU read-side critical section and other special cases.
- */
-void __rcu_read_unlock(void)
-{
-	struct task_struct *t = current;
-
-	if (t->rcu_read_lock_nesting != 1) {
-		--t->rcu_read_lock_nesting;
-	} else {
-		barrier();  /* critical section before exit code. */
-		t->rcu_read_lock_nesting = INT_MIN;
-		barrier();  /* assign before ->rcu_read_unlock_special load */
-		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
-			rcu_read_unlock_special(t);
-		barrier();  /* ->rcu_read_unlock_special load before assign */
-		t->rcu_read_lock_nesting = 0;
-	}
-#ifdef CONFIG_PROVE_LOCKING
-	{
-		int rrln = READ_ONCE(t->rcu_read_lock_nesting);
-
-		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
-	}
-#endif /* #ifdef CONFIG_PROVE_LOCKING */
-}
-EXPORT_SYMBOL_GPL(__rcu_read_unlock);
-
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
 struct lockdep_map rcu_lock_map =
@@ -624,7 +576,7 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks);
  * grace period has elapsed, in other words after all currently
  * executing rcu-tasks read-side critical sections have elapsed.  These
  * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_rcu_qs(), idle execution, userspace execution, calls
+ * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
  * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
  *
  * This is a very specialized primitive, intended only for a few uses in
diff --git a/kernel/resource.c b/kernel/resource.c
index 2af6c03858b9..b589dda910b3 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -87,7 +87,7 @@ enum { MAX_IORES_LEVEL = 5 };
 static void *r_start(struct seq_file *m, loff_t *pos)
 	__acquires(resource_lock)
 {
-	struct resource *p = m->private;
+	struct resource *p = PDE_DATA(file_inode(m->file));
 	loff_t l = 0;
 	read_lock(&resource_lock);
 	for (p = p->child; p && l < *pos; p = r_next(m, p, &l))
@@ -103,7 +103,7 @@ static void r_stop(struct seq_file *m, void *v)
 
 static int r_show(struct seq_file *m, void *v)
 {
-	struct resource *root = m->private;
+	struct resource *root = PDE_DATA(file_inode(m->file));
 	struct resource *r = v, *p;
 	unsigned long long start, end;
 	int width = root->end < 0x10000 ? 4 : 8;
@@ -135,44 +135,11 @@ static const struct seq_operations resource_op = {
 	.show	= r_show,
 };
 
-static int ioports_open(struct inode *inode, struct file *file)
-{
-	int res = seq_open(file, &resource_op);
-	if (!res) {
-		struct seq_file *m = file->private_data;
-		m->private = &ioport_resource;
-	}
-	return res;
-}
-
-static int iomem_open(struct inode *inode, struct file *file)
-{
-	int res = seq_open(file, &resource_op);
-	if (!res) {
-		struct seq_file *m = file->private_data;
-		m->private = &iomem_resource;
-	}
-	return res;
-}
-
-static const struct file_operations proc_ioports_operations = {
-	.open		= ioports_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations proc_iomem_operations = {
-	.open		= iomem_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int __init ioresources_init(void)
 {
-	proc_create("ioports", 0, NULL, &proc_ioports_operations);
-	proc_create("iomem", 0, NULL, &proc_iomem_operations);
+	proc_create_seq_data("ioports", 0, NULL, &resource_op,
+			&ioport_resource);
+	proc_create_seq_data("iomem", 0, NULL, &resource_op, &iomem_resource);
 	return 0;
 }
 __initcall(ioresources_init);
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 6be6c575b6cd..2d4ff5353ded 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -2,6 +2,7 @@
 /*
  * Auto-group scheduling implementation:
  */
+#include <linux/nospec.h>
 #include "sched.h"
 
 unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
@@ -209,7 +210,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 	static unsigned long next = INITIAL_JIFFIES;
 	struct autogroup *ag;
 	unsigned long shares;
-	int err;
+	int err, idx;
 
 	if (nice < MIN_NICE || nice > MAX_NICE)
 		return -EINVAL;
@@ -227,7 +228,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 
 	next = HZ / 10 + jiffies;
 	ag = autogroup_task_get(p);
-	shares = scale_load(sched_prio_to_weight[nice + 20]);
+
+	idx = array_index_nospec(nice + 20, 40);
+	shares = scale_load(sched_prio_to_weight[idx]);
 
 	down_write(&ag->lock);
 	err = sched_group_set_shares(ag->tg, shares);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5e10aaeebfcc..e9866f86f304 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,6 +7,9 @@
  */
 #include "sched.h"
 
+#include <linux/kthread.h>
+#include <linux/nospec.h>
+
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 
@@ -878,6 +881,33 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 }
 
 #ifdef CONFIG_SMP
+
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+	if (!(p->flags & PF_KTHREAD))
+		return false;
+
+	if (p->nr_cpus_allowed != 1)
+		return false;
+
+	return true;
+}
+
+/*
+ * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * __set_cpus_allowed_ptr() and select_fallback_rq().
+ */
+static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
+{
+	if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+		return false;
+
+	if (is_per_cpu_kthread(p))
+		return cpu_online(cpu);
+
+	return cpu_active(cpu);
+}
+
 /*
  * This is how migration works:
  *
@@ -935,16 +965,8 @@ struct migration_arg {
 static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
 				 struct task_struct *p, int dest_cpu)
 {
-	if (p->flags & PF_KTHREAD) {
-		if (unlikely(!cpu_online(dest_cpu)))
-			return rq;
-	} else {
-		if (unlikely(!cpu_active(dest_cpu)))
-			return rq;
-	}
-
 	/* Affinity changed (again). */
-	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+	if (!is_cpu_allowed(p, dest_cpu))
 		return rq;
 
 	update_rq_clock(rq);
@@ -1473,10 +1495,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	for (;;) {
 		/* Any allowed, online CPU? */
 		for_each_cpu(dest_cpu, &p->cpus_allowed) {
-			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
-				continue;
-			if (!cpu_online(dest_cpu))
+			if (!is_cpu_allowed(p, dest_cpu))
 				continue;
+
 			goto out;
 		}
 
@@ -1539,8 +1560,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	 * [ this allows ->select_task() to simply return task_cpu(p) and
 	 *   not worry about this generic constraint ]
 	 */
-	if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
-		     !cpu_online(cpu)))
+	if (unlikely(!is_cpu_allowed(p, cpu)))
 		cpu = select_fallback_rq(task_cpu(p), p);
 
 	return cpu;
@@ -2174,27 +2194,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
 
-#ifdef CONFIG_NUMA_BALANCING
-	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
-		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
-		p->mm->numa_scan_seq = 0;
-	}
-
-	if (clone_flags & CLONE_VM)
-		p->numa_preferred_nid = current->numa_preferred_nid;
-	else
-		p->numa_preferred_nid = -1;
-
-	p->node_stamp = 0ULL;
-	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
-	p->numa_work.next = &p->numa_work;
-	p->numa_faults = NULL;
-	p->last_task_numa_placement = 0;
-	p->last_sum_exec_runtime = 0;
-
-	p->numa_group = NULL;
-#endif /* CONFIG_NUMA_BALANCING */
+	init_numa_balancing(clone_flags, p);
 }
 
 DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
@@ -2718,20 +2718,28 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 		membarrier_mm_sync_core_before_usermode(mm);
 		mmdrop(mm);
 	}
-	if (unlikely(prev_state == TASK_DEAD)) {
-		if (prev->sched_class->task_dead)
-			prev->sched_class->task_dead(prev);
+	if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
+		switch (prev_state) {
+		case TASK_DEAD:
+			if (prev->sched_class->task_dead)
+				prev->sched_class->task_dead(prev);
 
-		/*
-		 * Remove function-return probe instances associated with this
-		 * task and put them back on the free list.
-		 */
-		kprobe_flush_task(prev);
+			/*
+			 * Remove function-return probe instances associated with this
+			 * task and put them back on the free list.
+			 */
+			kprobe_flush_task(prev);
 
-		/* Task is done with its stack. */
-		put_task_stack(prev);
+			/* Task is done with its stack. */
+			put_task_stack(prev);
 
-		put_task_struct(prev);
+			put_task_struct(prev);
+			break;
+
+		case TASK_PARKED:
+			kthread_park_complete(prev);
+			break;
+		}
 	}
 
 	tick_nohz_task_switch();
@@ -3498,23 +3506,8 @@ static void __sched notrace __schedule(bool preempt)
 
 void __noreturn do_task_dead(void)
 {
-	/*
-	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
-	 * when the following two conditions become true.
-	 *   - There is race condition of mmap_sem (It is acquired by
-	 *     exit_mm()), and
-	 *   - SMI occurs before setting TASK_RUNINNG.
-	 *     (or hypervisor of virtual machine switches to other guest)
-	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
-	 *
-	 * To avoid it, we have to wait for releasing tsk->pi_lock which
-	 * is held by try_to_wake_up()
-	 */
-	raw_spin_lock_irq(&current->pi_lock);
-	raw_spin_unlock_irq(&current->pi_lock);
-
 	/* Causes final put_task_struct in finish_task_switch(): */
-	__set_current_state(TASK_DEAD);
+	set_special_state(TASK_DEAD);
 
 	/* Tell freezer to ignore us: */
 	current->flags |= PF_NOFREEZE;
@@ -4037,6 +4030,23 @@ int idle_cpu(int cpu)
 }
 
 /**
+ * available_idle_cpu - is a given CPU idle for enqueuing work.
+ * @cpu: the CPU in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
+ */
+int available_idle_cpu(int cpu)
+{
+	if (!idle_cpu(cpu))
+		return 0;
+
+	if (vcpu_is_preempted(cpu))
+		return 0;
+
+	return 1;
+}
+
+/**
  * idle_task - return the idle task for a given CPU.
  * @cpu: the processor in question.
  *
@@ -5012,20 +5022,6 @@ int __cond_resched_lock(spinlock_t *lock)
 }
 EXPORT_SYMBOL(__cond_resched_lock);
 
-int __sched __cond_resched_softirq(void)
-{
-	BUG_ON(!in_softirq());
-
-	if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
-		local_bh_enable();
-		preempt_schedule_common();
-		local_bh_disable();
-		return 1;
-	}
-	return 0;
-}
-EXPORT_SYMBOL(__cond_resched_softirq);
-
 /**
  * yield - yield the current processor to other threads.
  *
@@ -6928,11 +6924,15 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
 				     struct cftype *cft, s64 nice)
 {
 	unsigned long weight;
+	int idx;
 
 	if (nice < MIN_NICE || nice > MAX_NICE)
 		return -ERANGE;
 
-	weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO];
+	idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO;
+	idx = array_index_nospec(idx, 40);
+	weight = sched_prio_to_weight[idx];
+
 	return sched_group_set_shares(css_tg(css), scale_load(weight));
 }
 #endif
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index d2c6083304b4..3cde46483f0a 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -51,7 +51,7 @@ struct sugov_cpu {
 	bool			iowait_boost_pending;
 	unsigned int		iowait_boost;
 	unsigned int		iowait_boost_max;
-	u64 last_update;
+	u64			last_update;
 
 	/* The fields below are only needed when sharing a policy: */
 	unsigned long		util_cfs;
@@ -89,46 +89,52 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 	 * schedule the kthread.
 	 */
 	if (sg_policy->policy->fast_switch_enabled &&
-	    !cpufreq_can_do_remote_dvfs(sg_policy->policy))
+	    !cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
-	if (sg_policy->work_in_progress)
-		return false;
-
-	if (unlikely(sg_policy->need_freq_update)) {
-		sg_policy->need_freq_update = false;
-		/*
-		 * This happens when limits change, so forget the previous
-		 * next_freq value and force an update.
-		 */
-		sg_policy->next_freq = UINT_MAX;
+	if (unlikely(sg_policy->need_freq_update))
 		return true;
-	}
 
 	delta_ns = time - sg_policy->last_freq_update_time;
 
 	return delta_ns >= sg_policy->freq_update_delay_ns;
 }
 
-static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
-				unsigned int next_freq)
+static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
+				   unsigned int next_freq)
 {
-	struct cpufreq_policy *policy = sg_policy->policy;
-
 	if (sg_policy->next_freq == next_freq)
-		return;
+		return false;
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
 
-	if (policy->fast_switch_enabled) {
-		next_freq = cpufreq_driver_fast_switch(policy, next_freq);
-		if (!next_freq)
-			return;
+	return true;
+}
 
-		policy->cur = next_freq;
-		trace_cpu_frequency(next_freq, smp_processor_id());
-	} else {
+static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
+			      unsigned int next_freq)
+{
+	struct cpufreq_policy *policy = sg_policy->policy;
+
+	if (!sugov_update_next_freq(sg_policy, time, next_freq))
+		return;
+
+	next_freq = cpufreq_driver_fast_switch(policy, next_freq);
+	if (!next_freq)
+		return;
+
+	policy->cur = next_freq;
+	trace_cpu_frequency(next_freq, smp_processor_id());
+}
+
+static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
+				  unsigned int next_freq)
+{
+	if (!sugov_update_next_freq(sg_policy, time, next_freq))
+		return;
+
+	if (!sg_policy->work_in_progress) {
 		sg_policy->work_in_progress = true;
 		irq_work_queue(&sg_policy->irq_work);
 	}
@@ -165,8 +171,10 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 
 	freq = (freq + (freq >> 2)) * util / max;
 
-	if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
 		return sg_policy->next_freq;
+
+	sg_policy->need_freq_update = false;
 	sg_policy->cached_raw_freq = freq;
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
@@ -183,61 +191,137 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util;
 
-	if (rq->rt.rt_nr_running) {
-		util = sg_cpu->max;
-	} else {
-		util = sg_cpu->util_dl;
-		if (rq->cfs.h_nr_running)
-			util += sg_cpu->util_cfs;
-	}
+	if (rq->rt.rt_nr_running)
+		return sg_cpu->max;
 
 	/*
+	 * Utilization required by DEADLINE must always be granted while, for
+	 * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
+	 * gracefully reduce the frequency when no tasks show up for longer
+	 * periods of time.
+	 *
 	 * Ideally we would like to set util_dl as min/guaranteed freq and
 	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
 	 * ready for such an interface. So, we only do the latter for now.
 	 */
-	return min(util, sg_cpu->max);
+	return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
 }
 
-static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, unsigned int flags)
+/**
+ * sugov_iowait_reset() - Reset the IO boost status of a CPU.
+ * @sg_cpu: the sugov data for the CPU to boost
+ * @time: the update time from the caller
+ * @set_iowait_boost: true if an IO boost has been requested
+ *
+ * The IO wait boost of a task is disabled after a tick since the last update
+ * of a CPU. If a new IO wait boost is requested after more then a tick, then
+ * we enable the boost starting from the minimum frequency, which improves
+ * energy efficiency by ignoring sporadic wakeups from IO.
+ */
+static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
+			       bool set_iowait_boost)
 {
-	if (flags & SCHED_CPUFREQ_IOWAIT) {
-		if (sg_cpu->iowait_boost_pending)
-			return;
+	s64 delta_ns = time - sg_cpu->last_update;
 
-		sg_cpu->iowait_boost_pending = true;
+	/* Reset boost only if a tick has elapsed since last request */
+	if (delta_ns <= TICK_NSEC)
+		return false;
 
-		if (sg_cpu->iowait_boost) {
-			sg_cpu->iowait_boost <<= 1;
-			if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
-				sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
-		} else {
-			sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
-		}
-	} else if (sg_cpu->iowait_boost) {
-		s64 delta_ns = time - sg_cpu->last_update;
+	sg_cpu->iowait_boost = set_iowait_boost
+		? sg_cpu->sg_policy->policy->min : 0;
+	sg_cpu->iowait_boost_pending = set_iowait_boost;
 
-		/* Clear iowait_boost if the CPU apprears to have been idle. */
-		if (delta_ns > TICK_NSEC) {
-			sg_cpu->iowait_boost = 0;
-			sg_cpu->iowait_boost_pending = false;
-		}
+	return true;
+}
+
+/**
+ * sugov_iowait_boost() - Updates the IO boost status of a CPU.
+ * @sg_cpu: the sugov data for the CPU to boost
+ * @time: the update time from the caller
+ * @flags: SCHED_CPUFREQ_IOWAIT if the task is waking up after an IO wait
+ *
+ * Each time a task wakes up after an IO operation, the CPU utilization can be
+ * boosted to a certain utilization which doubles at each "frequent and
+ * successive" wakeup from IO, ranging from the utilization of the minimum
+ * OPP to the utilization of the maximum OPP.
+ * To keep doubling, an IO boost has to be requested at least once per tick,
+ * otherwise we restart from the utilization of the minimum OPP.
+ */
+static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
+			       unsigned int flags)
+{
+	bool set_iowait_boost = flags & SCHED_CPUFREQ_IOWAIT;
+
+	/* Reset boost if the CPU appears to have been idle enough */
+	if (sg_cpu->iowait_boost &&
+	    sugov_iowait_reset(sg_cpu, time, set_iowait_boost))
+		return;
+
+	/* Boost only tasks waking up after IO */
+	if (!set_iowait_boost)
+		return;
+
+	/* Ensure boost doubles only one time at each request */
+	if (sg_cpu->iowait_boost_pending)
+		return;
+	sg_cpu->iowait_boost_pending = true;
+
+	/* Double the boost at each request */
+	if (sg_cpu->iowait_boost) {
+		sg_cpu->iowait_boost <<= 1;
+		if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
+			sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+		return;
 	}
+
+	/* First wakeup after IO: start with minimum boost */
+	sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
 }
 
-static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
-			       unsigned long *max)
+/**
+ * sugov_iowait_apply() - Apply the IO boost to a CPU.
+ * @sg_cpu: the sugov data for the cpu to boost
+ * @time: the update time from the caller
+ * @util: the utilization to (eventually) boost
+ * @max: the maximum value the utilization can be boosted to
+ *
+ * A CPU running a task which woken up after an IO operation can have its
+ * utilization boosted to speed up the completion of those IO operations.
+ * The IO boost value is increased each time a task wakes up from IO, in
+ * sugov_iowait_apply(), and it's instead decreased by this function,
+ * each time an increase has not been requested (!iowait_boost_pending).
+ *
+ * A CPU which also appears to have been idle for at least one tick has also
+ * its IO boost utilization reset.
+ *
+ * This mechanism is designed to boost high frequently IO waiting tasks, while
+ * being more conservative on tasks which does sporadic IO operations.
+ */
+static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+			       unsigned long *util, unsigned long *max)
 {
 	unsigned int boost_util, boost_max;
 
+	/* No boost currently required */
 	if (!sg_cpu->iowait_boost)
 		return;
 
+	/* Reset boost if the CPU appears to have been idle enough */
+	if (sugov_iowait_reset(sg_cpu, time, false))
+		return;
+
+	/*
+	 * An IO waiting task has just woken up:
+	 * allow to further double the boost value
+	 */
 	if (sg_cpu->iowait_boost_pending) {
 		sg_cpu->iowait_boost_pending = false;
 	} else {
+		/*
+		 * Otherwise: reduce the boost value and disable it when we
+		 * reach the minimum.
+		 */
 		sg_cpu->iowait_boost >>= 1;
 		if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
 			sg_cpu->iowait_boost = 0;
@@ -245,9 +329,12 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
 		}
 	}
 
+	/*
+	 * Apply the current boost value: a CPU is boosted only if its current
+	 * utilization is smaller then the current IO boost level.
+	 */
 	boost_util = sg_cpu->iowait_boost;
 	boost_max = sg_cpu->iowait_boost_max;
-
 	if (*util * boost_max < *max * boost_util) {
 		*util = boost_util;
 		*max = boost_max;
@@ -286,7 +373,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	unsigned int next_f;
 	bool busy;
 
-	sugov_set_iowait_boost(sg_cpu, time, flags);
+	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
 	ignore_dl_rate_limit(sg_cpu, sg_policy);
@@ -299,7 +386,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
 	util = sugov_aggregate_util(sg_cpu);
-	sugov_iowait_boost(sg_cpu, &util, &max);
+	sugov_iowait_apply(sg_cpu, time, &util, &max);
 	next_f = get_next_freq(sg_policy, util, max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
@@ -312,7 +399,18 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 		sg_policy->cached_raw_freq = 0;
 	}
 
-	sugov_update_commit(sg_policy, time, next_f);
+	/*
+	 * This code runs under rq->lock for the target CPU, so it won't run
+	 * concurrently on two different CPUs for the same target and it is not
+	 * necessary to acquire the lock in the fast switch case.
+	 */
+	if (sg_policy->policy->fast_switch_enabled) {
+		sugov_fast_switch(sg_policy, time, next_f);
+	} else {
+		raw_spin_lock(&sg_policy->update_lock);
+		sugov_deferred_update(sg_policy, time, next_f);
+		raw_spin_unlock(&sg_policy->update_lock);
+	}
 }
 
 static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
@@ -325,28 +423,12 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
 		unsigned long j_util, j_max;
-		s64 delta_ns;
 
 		sugov_get_util(j_sg_cpu);
-
-		/*
-		 * If the CFS CPU utilization was last updated before the
-		 * previous frequency update and the time elapsed between the
-		 * last update of the CPU utilization and the last frequency
-		 * update is long enough, reset iowait_boost and util_cfs, as
-		 * they are now probably stale. However, still consider the
-		 * CPU contribution if it has some DEADLINE utilization
-		 * (util_dl).
-		 */
-		delta_ns = time - j_sg_cpu->last_update;
-		if (delta_ns > TICK_NSEC) {
-			j_sg_cpu->iowait_boost = 0;
-			j_sg_cpu->iowait_boost_pending = false;
-		}
-
 		j_max = j_sg_cpu->max;
 		j_util = sugov_aggregate_util(j_sg_cpu);
-		sugov_iowait_boost(j_sg_cpu, &j_util, &j_max);
+		sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
+
 		if (j_util * max > j_max * util) {
 			util = j_util;
 			max = j_max;
@@ -365,14 +447,18 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
 
 	raw_spin_lock(&sg_policy->update_lock);
 
-	sugov_set_iowait_boost(sg_cpu, time, flags);
+	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
 	ignore_dl_rate_limit(sg_cpu, sg_policy);
 
 	if (sugov_should_update_freq(sg_policy, time)) {
 		next_f = sugov_next_freq_shared(sg_cpu, time);
-		sugov_update_commit(sg_policy, time, next_f);
+
+		if (sg_policy->policy->fast_switch_enabled)
+			sugov_fast_switch(sg_policy, time, next_f);
+		else
+			sugov_deferred_update(sg_policy, time, next_f);
 	}
 
 	raw_spin_unlock(&sg_policy->update_lock);
@@ -381,13 +467,27 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
 static void sugov_work(struct kthread_work *work)
 {
 	struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
+	unsigned int freq;
+	unsigned long flags;
+
+	/*
+	 * Hold sg_policy->update_lock shortly to handle the case where:
+	 * incase sg_policy->next_freq is read here, and then updated by
+	 * sugov_deferred_update() just before work_in_progress is set to false
+	 * here, we may miss queueing the new update.
+	 *
+	 * Note: If a work was queued after the update_lock is released,
+	 * sugov_work() will just be called again by kthread_work code; and the
+	 * request will be proceed before the sugov thread sleeps.
+	 */
+	raw_spin_lock_irqsave(&sg_policy->update_lock, flags);
+	freq = sg_policy->next_freq;
+	sg_policy->work_in_progress = false;
+	raw_spin_unlock_irqrestore(&sg_policy->update_lock, flags);
 
 	mutex_lock(&sg_policy->work_lock);
-	__cpufreq_driver_target(sg_policy->policy, sg_policy->next_freq,
-				CPUFREQ_RELATION_L);
+	__cpufreq_driver_target(sg_policy->policy, freq, CPUFREQ_RELATION_L);
 	mutex_unlock(&sg_policy->work_lock);
-
-	sg_policy->work_in_progress = false;
 }
 
 static void sugov_irq_work(struct irq_work *irq_work)
@@ -396,19 +496,6 @@ static void sugov_irq_work(struct irq_work *irq_work)
 
 	sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
 
-	/*
-	 * For RT tasks, the schedutil governor shoots the frequency to maximum.
-	 * Special care must be taken to ensure that this kthread doesn't result
-	 * in the same behavior.
-	 *
-	 * This is (mostly) guaranteed by the work_in_progress flag. The flag is
-	 * updated only at the end of the sugov_work() function and before that
-	 * the schedutil governor rejects all other frequency scaling requests.
-	 *
-	 * There is a very rare case though, where the RT thread yields right
-	 * after the work_in_progress flag is cleared. The effects of that are
-	 * neglected for now.
-	 */
 	kthread_queue_work(&sg_policy->worker, &sg_policy->work);
 }
 
@@ -523,11 +610,7 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
 	}
 
 	sg_policy->thread = thread;
-
-	/* Kthread is bound to all CPUs by default */
-	if (!policy->dvfs_possible_from_any_cpu)
-		kthread_bind_mask(thread, policy->related_cpus);
-
+	kthread_bind_mask(thread, policy->related_cpus);
 	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
 	mutex_init(&sg_policy->work_lock);
 
@@ -670,7 +753,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 
 	sg_policy->freq_update_delay_ns	= sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
 	sg_policy->last_freq_update_time	= 0;
-	sg_policy->next_freq			= UINT_MAX;
+	sg_policy->next_freq			= 0;
 	sg_policy->work_in_progress		= false;
 	sg_policy->need_freq_update		= false;
 	sg_policy->cached_raw_freq		= 0;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e7b3008b85bb..fbfc3f1d368a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1117,7 +1117,7 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
  * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
  * So, overflow is not an issue here.
  */
-u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
+static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
 {
 	u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
 	u64 u_act;
@@ -1259,6 +1259,9 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 
 	rq = task_rq_lock(p, &rf);
 
+	sched_clock_tick();
+	update_rq_clock(rq);
+
 	if (!dl_task(p) || p->state == TASK_DEAD) {
 		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 
@@ -1278,9 +1281,6 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 	if (dl_se->dl_non_contending == 0)
 		goto unlock;
 
-	sched_clock_tick();
-	update_rq_clock(rq);
-
 	sub_running_bw(dl_se, &rq->dl);
 	dl_se->dl_non_contending = 0;
 unlock:
@@ -2731,8 +2731,6 @@ bool dl_cpu_busy(unsigned int cpu)
 #endif
 
 #ifdef CONFIG_SCHED_DEBUG
-extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
-
 void print_dl_stats(struct seq_file *m, int cpu)
 {
 	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 15b10e210a6b..e593b4118578 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -823,35 +823,9 @@ static const struct seq_operations sched_debug_sops = {
 	.show		= sched_debug_show,
 };
 
-static int sched_debug_release(struct inode *inode, struct file *file)
-{
-	seq_release(inode, file);
-
-	return 0;
-}
-
-static int sched_debug_open(struct inode *inode, struct file *filp)
-{
-	int ret = 0;
-
-	ret = seq_open(filp, &sched_debug_sops);
-
-	return ret;
-}
-
-static const struct file_operations sched_debug_fops = {
-	.open		= sched_debug_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= sched_debug_release,
-};
-
 static int __init init_sched_debug_procfs(void)
 {
-	struct proc_dir_entry *pe;
-
-	pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops);
-	if (!pe)
+	if (!proc_create_seq("sched_debug", 0444, NULL, &sched_debug_sops))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 54dc31e7ab9b..e497c05aab7f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1139,6 +1139,47 @@ static unsigned int task_scan_max(struct task_struct *p)
 	return max(smin, smax);
 }
 
+void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+	int mm_users = 0;
+	struct mm_struct *mm = p->mm;
+
+	if (mm) {
+		mm_users = atomic_read(&mm->mm_users);
+		if (mm_users == 1) {
+			mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
+			mm->numa_scan_seq = 0;
+		}
+	}
+	p->node_stamp			= 0;
+	p->numa_scan_seq		= mm ? mm->numa_scan_seq : 0;
+	p->numa_scan_period		= sysctl_numa_balancing_scan_delay;
+	p->numa_work.next		= &p->numa_work;
+	p->numa_faults			= NULL;
+	p->numa_group			= NULL;
+	p->last_task_numa_placement	= 0;
+	p->last_sum_exec_runtime	= 0;
+
+	/* New address space, reset the preferred nid */
+	if (!(clone_flags & CLONE_VM)) {
+		p->numa_preferred_nid = -1;
+		return;
+	}
+
+	/*
+	 * New thread, keep existing numa_preferred_nid which should be copied
+	 * already by arch_dup_task_struct but stagger when scans start.
+	 */
+	if (mm) {
+		unsigned int delay;
+
+		delay = min_t(unsigned int, task_scan_max(current),
+			current->numa_scan_period * mm_users * NSEC_PER_MSEC);
+		delay += 2 * TICK_NSEC;
+		p->node_stamp = delay;
+	}
+}
+
 static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 {
 	rq->nr_numa_running += (p->numa_preferred_nid != -1);
@@ -1854,7 +1895,6 @@ static int task_numa_migrate(struct task_struct *p)
 static void numa_migrate_preferred(struct task_struct *p)
 {
 	unsigned long interval = HZ;
-	unsigned long numa_migrate_retry;
 
 	/* This task has no NUMA fault statistics yet */
 	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
@@ -1862,18 +1902,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 
 	/* Periodically retry migrating the task to the preferred node */
 	interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
-	numa_migrate_retry = jiffies + interval;
-
-	/*
-	 * Check that the new retry threshold is after the current one. If
-	 * the retry is in the future, it implies that wake_affine has
-	 * temporarily asked NUMA balancing to backoff from placement.
-	 */
-	if (numa_migrate_retry > p->numa_migrate_retry)
-		return;
-
-	/* Safe to try placing the task on the preferred node */
-	p->numa_migrate_retry = numa_migrate_retry;
+	p->numa_migrate_retry = jiffies + interval;
 
 	/* Success if task is already running on preferred CPU */
 	if (task_node(p) == p->numa_preferred_nid)
@@ -5357,6 +5386,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 
 	/*
+	 * The code below (indirectly) updates schedutil which looks at
+	 * the cfs_rq utilization to select a frequency.
+	 * Let's add the task's estimated utilization to the cfs_rq's
+	 * estimated utilization, before we update schedutil.
+	 */
+	util_est_enqueue(&rq->cfs, p);
+
+	/*
 	 * If in_iowait is set, the code below may not trigger any cpufreq
 	 * utilization updates, so do it here explicitly with the IOWAIT flag
 	 * passed.
@@ -5397,7 +5434,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (!se)
 		add_nr_running(rq, 1);
 
-	util_est_enqueue(&rq->cfs, p);
 	hrtick_update(rq);
 }
 
@@ -5870,8 +5906,8 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
 	 * a cpufreq perspective, it's better to have higher utilisation
 	 * on one CPU.
 	 */
-	if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
-		return idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
+	if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
+		return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
 
 	if (sync && cpu_rq(this_cpu)->nr_running == 1)
 		return this_cpu;
@@ -5922,48 +5958,6 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
 	return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
-	unsigned long interval;
-
-	if (!static_branch_likely(&sched_numa_balancing))
-		return;
-
-	/* If balancing has no preference then continue gathering data */
-	if (p->numa_preferred_nid == -1)
-		return;
-
-	/*
-	 * If the wakeup is not affecting locality then it is neutral from
-	 * the perspective of NUMA balacing so continue gathering data.
-	 */
-	if (cpu_to_node(prev_cpu) == cpu_to_node(target))
-		return;
-
-	/*
-	 * Temporarily prevent NUMA balancing trying to place waker/wakee after
-	 * wakee has been moved by wake_affine. This will potentially allow
-	 * related tasks to converge and update their data placement. The
-	 * 4 * numa_scan_period is to allow the two-pass filter to migrate
-	 * hot data to the wakers node.
-	 */
-	interval = max(sysctl_numa_balancing_scan_delay,
-			 p->numa_scan_period << 2);
-	p->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-
-	interval = max(sysctl_numa_balancing_scan_delay,
-			 current->numa_scan_period << 2);
-	current->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-}
-#else
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
-}
-#endif
-
 static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int this_cpu, int prev_cpu, int sync)
 {
@@ -5979,7 +5973,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	if (target == nr_cpumask_bits)
 		return prev_cpu;
 
-	update_wa_numa_placement(p, prev_cpu, target);
 	schedstat_inc(sd->ttwu_move_affine);
 	schedstat_inc(p->se.statistics.nr_wakeups_affine);
 	return target;
@@ -6157,7 +6150,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 
 	/* Traverse only the allowed CPUs */
 	for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
-		if (idle_cpu(i)) {
+		if (available_idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
 			if (idle && idle->exit_latency < min_exit_latency) {
@@ -6199,6 +6192,13 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 	if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
 		return prev_cpu;
 
+	/*
+	 * We need task's util for capacity_spare_wake, sync it up to prev_cpu's
+	 * last_update_time.
+	 */
+	if (!(sd_flag & SD_BALANCE_FORK))
+		sync_entity_load_avg(&p->se);
+
 	while (sd) {
 		struct sched_group *group;
 		struct sched_domain *tmp;
@@ -6279,7 +6279,7 @@ void __update_idle_core(struct rq *rq)
 		if (cpu == core)
 			continue;
 
-		if (!idle_cpu(cpu))
+		if (!available_idle_cpu(cpu))
 			goto unlock;
 	}
 
@@ -6311,7 +6311,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
 			cpumask_clear_cpu(cpu, cpus);
-			if (!idle_cpu(cpu))
+			if (!available_idle_cpu(cpu))
 				idle = false;
 		}
 
@@ -6340,7 +6340,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
-		if (idle_cpu(cpu))
+		if (available_idle_cpu(cpu))
 			return cpu;
 	}
 
@@ -6403,7 +6403,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 			return -1;
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
-		if (idle_cpu(cpu))
+		if (available_idle_cpu(cpu))
 			break;
 	}
 
@@ -6423,13 +6423,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	struct sched_domain *sd;
 	int i, recent_used_cpu;
 
-	if (idle_cpu(target))
+	if (available_idle_cpu(target))
 		return target;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
-	if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
+	if (prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev))
 		return prev;
 
 	/* Check a recently used CPU as a potential idle candidate: */
@@ -6437,7 +6437,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	if (recent_used_cpu != prev &&
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
-	    idle_cpu(recent_used_cpu) &&
+	    available_idle_cpu(recent_used_cpu) &&
 	    cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) {
 		/*
 		 * Replace recent_used_cpu with prev as it is a potential
@@ -6613,7 +6613,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 static int
 select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
 {
-	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
+	struct sched_domain *tmp, *sd = NULL;
 	int cpu = smp_processor_id();
 	int new_cpu = prev_cpu;
 	int want_affine = 0;
@@ -6636,7 +6636,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 		 */
 		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
 		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
-			affine_sd = tmp;
+			if (cpu != prev_cpu)
+				new_cpu = wake_affine(tmp, p, cpu, prev_cpu, sync);
+
+			sd = NULL; /* Prefer wake_affine over balance flags */
 			break;
 		}
 
@@ -6646,33 +6649,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			break;
 	}
 
-	if (affine_sd) {
-		sd = NULL; /* Prefer wake_affine over balance flags */
-		if (cpu == prev_cpu)
-			goto pick_cpu;
-
-		new_cpu = wake_affine(affine_sd, p, cpu, prev_cpu, sync);
-	}
-
-	if (sd && !(sd_flag & SD_BALANCE_FORK)) {
-		/*
-		 * We're going to need the task's util for capacity_spare_wake
-		 * in find_idlest_group. Sync it up to prev_cpu's
-		 * last_update_time.
-		 */
-		sync_entity_load_avg(&p->se);
-	}
+	if (unlikely(sd)) {
+		/* Slow path */
+		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
+	} else if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
+		/* Fast path */
 
-	if (!sd) {
-pick_cpu:
-		if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
-			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
+		new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
-			if (want_affine)
-				current->recent_used_cpu = cpu;
-		}
-	} else {
-		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
+		if (want_affine)
+			current->recent_used_cpu = cpu;
 	}
 	rcu_read_unlock();
 
@@ -9847,6 +9833,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
 	if (curr_cost > this_rq->max_idle_balance_cost)
 		this_rq->max_idle_balance_cost = curr_cost;
 
+out:
 	/*
 	 * While browsing the domains, we released the rq lock, a task could
 	 * have been enqueued in the meantime. Since we're not going idle,
@@ -9855,7 +9842,6 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
 	if (this_rq->cfs.h_nr_running && !pulled_task)
 		pulled_task = 1;
 
-out:
 	/* Move the next balance forward */
 	if (time_after(this_rq->next_balance, next_balance))
 		this_rq->next_balance = next_balance;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7aef6b4e885a..ef3c4e6f5345 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2701,8 +2701,6 @@ int sched_rr_handler(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_SCHED_DEBUG
-extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
-
 void print_rt_stats(struct seq_file *m, int cpu)
 {
 	rt_rq_iter_t iter;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 15750c222ca2..6601baf2361c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -983,7 +983,7 @@ static inline void rq_clock_skip_update(struct rq *rq)
 }
 
 /*
- * See rt task throttoling, which is the only time a skip
+ * See rt task throttling, which is the only time a skip
  * request is cancelled.
  */
 static inline void rq_clock_cancel_skipupdate(struct rq *rq)
@@ -1069,6 +1069,12 @@ enum numa_faults_stats {
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
+#else
+static inline void
+init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #ifdef CONFIG_SMP
@@ -2025,8 +2031,9 @@ extern bool sched_debug_enabled;
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
 #ifdef CONFIG_NUMA_BALANCING
 extern void
 show_numa_stats(struct task_struct *p, struct seq_file *m);
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index ab112cbfd7c8..750fb3c67eed 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -120,22 +120,9 @@ static const struct seq_operations schedstat_sops = {
 	.show  = show_schedstat,
 };
 
-static int schedstat_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &schedstat_sops);
-}
-
-static const struct file_operations proc_schedstat_operations = {
-	.open    = schedstat_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-};
-
 static int __init proc_schedstat_init(void)
 {
-	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
-
+	proc_create_seq("schedstat", 0, NULL, &schedstat_sops);
 	return 0;
 }
 subsys_initcall(proc_schedstat_init);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 64cc564f5255..61a1125c1ae4 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1708,7 +1708,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	rcu_read_unlock();
 
 	if (rq && sched_debug_enabled) {
-		pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
+		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
 			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
 	}
 
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index dc77548167ef..e691d9a6c58d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -19,6 +19,8 @@
 #include <linux/compat.h>
 #include <linux/coredump.h>
 #include <linux/kmemleak.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/seccomp.h>
@@ -227,8 +229,11 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
 	return true;
 }
 
+void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { }
+
 static inline void seccomp_assign_mode(struct task_struct *task,
-				       unsigned long seccomp_mode)
+				       unsigned long seccomp_mode,
+				       unsigned long flags)
 {
 	assert_spin_locked(&task->sighand->siglock);
 
@@ -238,6 +243,9 @@ static inline void seccomp_assign_mode(struct task_struct *task,
 	 * filter) is set.
 	 */
 	smp_mb__before_atomic();
+	/* Assume default seccomp processes want spec flaw mitigation. */
+	if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
+		arch_seccomp_spec_mitigate(task);
 	set_tsk_thread_flag(task, TIF_SECCOMP);
 }
 
@@ -305,7 +313,7 @@ static inline pid_t seccomp_can_sync_threads(void)
  * without dropping the locks.
  *
  */
-static inline void seccomp_sync_threads(void)
+static inline void seccomp_sync_threads(unsigned long flags)
 {
 	struct task_struct *thread, *caller;
 
@@ -346,7 +354,8 @@ static inline void seccomp_sync_threads(void)
 		 * allow one thread to transition the other.
 		 */
 		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
-			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER,
+					    flags);
 	}
 }
 
@@ -469,7 +478,7 @@ static long seccomp_attach_filter(unsigned int flags,
 
 	/* Now that the new filter is in place, synchronize to all threads. */
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
-		seccomp_sync_threads();
+		seccomp_sync_threads(flags);
 
 	return 0;
 }
@@ -818,7 +827,7 @@ static long seccomp_set_mode_strict(void)
 #ifdef TIF_NOTSC
 	disable_TSC();
 #endif
-	seccomp_assign_mode(current, seccomp_mode);
+	seccomp_assign_mode(current, seccomp_mode, 0);
 	ret = 0;
 
 out:
@@ -876,7 +885,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	/* Do not free the successfully attached filter. */
 	prepared = NULL;
 
-	seccomp_assign_mode(current, seccomp_mode);
+	seccomp_assign_mode(current, seccomp_mode, flags);
 out:
 	spin_unlock_irq(&current->sighand->siglock);
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
diff --git a/kernel/signal.c b/kernel/signal.c
index d4ccea599692..0f865d67415d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1539,7 +1539,6 @@ int send_sig_fault(int sig, int code, void __user *addr
 	return send_sig_info(info.si_signo, &info, t);
 }
 
-#if defined(BUS_MCEERR_AO) && defined(BUS_MCEERR_AR)
 int force_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t)
 {
 	struct siginfo info;
@@ -1568,9 +1567,7 @@ int send_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *
 	return send_sig_info(info.si_signo, &info, t);
 }
 EXPORT_SYMBOL(send_sig_mceerr);
-#endif
 
-#ifdef SEGV_BNDERR
 int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper)
 {
 	struct siginfo info;
@@ -1584,7 +1581,6 @@ int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper)
 	info.si_upper = upper;
 	return force_sig_info(info.si_signo, &info, current);
 }
-#endif
 
 #ifdef SEGV_PKUERR
 int force_sig_pkuerr(void __user *addr, u32 pkey)
@@ -1961,14 +1957,27 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 			return;
 	}
 
+	set_special_state(TASK_TRACED);
+
 	/*
 	 * We're committing to trapping.  TRACED should be visible before
 	 * TRAPPING is cleared; otherwise, the tracer might fail do_wait().
 	 * Also, transition to TRACED and updates to ->jobctl should be
 	 * atomic with respect to siglock and should be done after the arch
 	 * hook as siglock is released and regrabbed across it.
+	 *
+	 *     TRACER				    TRACEE
+	 *
+	 *     ptrace_attach()
+	 * [L]   wait_on_bit(JOBCTL_TRAPPING)	[S] set_special_state(TRACED)
+	 *     do_wait()
+	 *       set_current_state()                smp_wmb();
+	 *       ptrace_do_wait()
+	 *         wait_task_stopped()
+	 *           task_stopped_code()
+	 * [L]         task_is_traced()		[S] task_clear_jobctl_trapping();
 	 */
-	set_current_state(TASK_TRACED);
+	smp_wmb();
 
 	current->last_siginfo = info;
 	current->exit_code = exit_code;
@@ -2176,7 +2185,7 @@ static bool do_signal_stop(int signr)
 		if (task_participate_group_stop(current))
 			notify = CLD_STOPPED;
 
-		__set_current_state(TASK_STOPPED);
+		set_special_state(TASK_STOPPED);
 		spin_unlock_irq(&current->sighand->siglock);
 
 		/*
@@ -2824,8 +2833,19 @@ enum siginfo_layout siginfo_layout(int sig, int si_code)
 			[SIGPOLL] = { NSIGPOLL, SIL_POLL },
 			[SIGSYS]  = { NSIGSYS,  SIL_SYS },
 		};
-		if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit))
+		if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit)) {
 			layout = filter[sig].layout;
+			/* Handle the exceptions */
+			if ((sig == SIGBUS) &&
+			    (si_code >= BUS_MCEERR_AR) && (si_code <= BUS_MCEERR_AO))
+				layout = SIL_FAULT_MCEERR;
+			else if ((sig == SIGSEGV) && (si_code == SEGV_BNDERR))
+				layout = SIL_FAULT_BNDERR;
+#ifdef SEGV_PKUERR
+			else if ((sig == SIGSEGV) && (si_code == SEGV_PKUERR))
+				layout = SIL_FAULT_PKUERR;
+#endif
+		}
 		else if (si_code <= NSIGPOLL)
 			layout = SIL_POLL;
 	} else {
@@ -2835,104 +2855,15 @@ enum siginfo_layout siginfo_layout(int sig, int si_code)
 			layout = SIL_POLL;
 		else if (si_code < 0)
 			layout = SIL_RT;
-		/* Tests to support buggy kernel ABIs */
-#ifdef TRAP_FIXME
-		if ((sig == SIGTRAP) && (si_code == TRAP_FIXME))
-			layout = SIL_FAULT;
-#endif
-#ifdef FPE_FIXME
-		if ((sig == SIGFPE) && (si_code == FPE_FIXME))
-			layout = SIL_FAULT;
-#endif
 	}
 	return layout;
 }
 
 int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 {
-	int err;
-
-	if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t)))
+	if (copy_to_user(to, from , sizeof(struct siginfo)))
 		return -EFAULT;
-	if (from->si_code < 0)
-		return __copy_to_user(to, from, sizeof(siginfo_t))
-			? -EFAULT : 0;
-	/*
-	 * If you change siginfo_t structure, please be sure
-	 * this code is fixed accordingly.
-	 * Please remember to update the signalfd_copyinfo() function
-	 * inside fs/signalfd.c too, in case siginfo_t changes.
-	 * It should never copy any pad contained in the structure
-	 * to avoid security leaks, but must copy the generic
-	 * 3 ints plus the relevant union member.
-	 */
-	err = __put_user(from->si_signo, &to->si_signo);
-	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user(from->si_code, &to->si_code);
-	switch (siginfo_layout(from->si_signo, from->si_code)) {
-	case SIL_KILL:
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		break;
-	case SIL_TIMER:
-		/* Unreached SI_TIMER is negative */
-		break;
-	case SIL_POLL:
-		err |= __put_user(from->si_band, &to->si_band);
-		err |= __put_user(from->si_fd, &to->si_fd);
-		break;
-	case SIL_FAULT:
-		err |= __put_user(from->si_addr, &to->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		err |= __put_user(from->si_trapno, &to->si_trapno);
-#endif
-#ifdef __ia64__
-		err |= __put_user(from->si_imm, &to->si_imm);
-		err |= __put_user(from->si_flags, &to->si_flags);
-		err |= __put_user(from->si_isr, &to->si_isr);
-#endif
-		/*
-		 * Other callers might not initialize the si_lsb field,
-		 * so check explicitly for the right codes here.
-		 */
-#ifdef BUS_MCEERR_AR
-		if (from->si_signo == SIGBUS && from->si_code == BUS_MCEERR_AR)
-			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
-#endif
-#ifdef BUS_MCEERR_AO
-		if (from->si_signo == SIGBUS && from->si_code == BUS_MCEERR_AO)
-			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
-#endif
-#ifdef SEGV_BNDERR
-		if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) {
-			err |= __put_user(from->si_lower, &to->si_lower);
-			err |= __put_user(from->si_upper, &to->si_upper);
-		}
-#endif
-#ifdef SEGV_PKUERR
-		if (from->si_signo == SIGSEGV && from->si_code == SEGV_PKUERR)
-			err |= __put_user(from->si_pkey, &to->si_pkey);
-#endif
-		break;
-	case SIL_CHLD:
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user(from->si_status, &to->si_status);
-		err |= __put_user(from->si_utime, &to->si_utime);
-		err |= __put_user(from->si_stime, &to->si_stime);
-		break;
-	case SIL_RT:
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user(from->si_ptr, &to->si_ptr);
-		break;
-	case SIL_SYS:
-		err |= __put_user(from->si_call_addr, &to->si_call_addr);
-		err |= __put_user(from->si_syscall, &to->si_syscall);
-		err |= __put_user(from->si_arch, &to->si_arch);
-		break;
-	}
-	return err;
+	return 0;
 }
 
 #ifdef CONFIG_COMPAT
@@ -2971,27 +2902,28 @@ int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
 #ifdef __ARCH_SI_TRAPNO
 		new.si_trapno = from->si_trapno;
 #endif
-#ifdef BUS_MCEERR_AR
-		if ((from->si_signo == SIGBUS) && (from->si_code == BUS_MCEERR_AR))
-			new.si_addr_lsb = from->si_addr_lsb;
-#endif
-#ifdef BUS_MCEERR_AO
-		if ((from->si_signo == SIGBUS) && (from->si_code == BUS_MCEERR_AO))
-			new.si_addr_lsb = from->si_addr_lsb;
+		break;
+	case SIL_FAULT_MCEERR:
+		new.si_addr = ptr_to_compat(from->si_addr);
+#ifdef __ARCH_SI_TRAPNO
+		new.si_trapno = from->si_trapno;
 #endif
-#ifdef SEGV_BNDERR
-		if ((from->si_signo == SIGSEGV) &&
-		    (from->si_code == SEGV_BNDERR)) {
-			new.si_lower = ptr_to_compat(from->si_lower);
-			new.si_upper = ptr_to_compat(from->si_upper);
-		}
+		new.si_addr_lsb = from->si_addr_lsb;
+		break;
+	case SIL_FAULT_BNDERR:
+		new.si_addr = ptr_to_compat(from->si_addr);
+#ifdef __ARCH_SI_TRAPNO
+		new.si_trapno = from->si_trapno;
 #endif
-#ifdef SEGV_PKUERR
-		if ((from->si_signo == SIGSEGV) &&
-		    (from->si_code == SEGV_PKUERR))
-			new.si_pkey = from->si_pkey;
+		new.si_lower = ptr_to_compat(from->si_lower);
+		new.si_upper = ptr_to_compat(from->si_upper);
+		break;
+	case SIL_FAULT_PKUERR:
+		new.si_addr = ptr_to_compat(from->si_addr);
+#ifdef __ARCH_SI_TRAPNO
+		new.si_trapno = from->si_trapno;
 #endif
-
+		new.si_pkey = from->si_pkey;
 		break;
 	case SIL_CHLD:
 		new.si_pid    = from->si_pid;
@@ -3057,24 +2989,28 @@ int copy_siginfo_from_user32(struct siginfo *to,
 #ifdef __ARCH_SI_TRAPNO
 		to->si_trapno = from.si_trapno;
 #endif
-#ifdef BUS_MCEERR_AR
-		if ((from.si_signo == SIGBUS) && (from.si_code == BUS_MCEERR_AR))
-			to->si_addr_lsb = from.si_addr_lsb;
-#endif
-#ifdef BUS_MCEER_AO
-		if ((from.si_signo == SIGBUS) && (from.si_code == BUS_MCEERR_AO))
-			to->si_addr_lsb = from.si_addr_lsb;
+		break;
+	case SIL_FAULT_MCEERR:
+		to->si_addr = compat_ptr(from.si_addr);
+#ifdef __ARCH_SI_TRAPNO
+		to->si_trapno = from.si_trapno;
 #endif
-#ifdef SEGV_BNDERR
-		if ((from.si_signo == SIGSEGV) && (from.si_code == SEGV_BNDERR)) {
-			to->si_lower = compat_ptr(from.si_lower);
-			to->si_upper = compat_ptr(from.si_upper);
-		}
+		to->si_addr_lsb = from.si_addr_lsb;
+		break;
+	case SIL_FAULT_BNDERR:
+		to->si_addr = compat_ptr(from.si_addr);
+#ifdef __ARCH_SI_TRAPNO
+		to->si_trapno = from.si_trapno;
 #endif
-#ifdef SEGV_PKUERR
-		if ((from.si_signo == SIGSEGV) && (from.si_code == SEGV_PKUERR))
-			to->si_pkey = from.si_pkey;
+		to->si_lower = compat_ptr(from.si_lower);
+		to->si_upper = compat_ptr(from.si_upper);
+		break;
+	case SIL_FAULT_PKUERR:
+		to->si_addr = compat_ptr(from.si_addr);
+#ifdef __ARCH_SI_TRAPNO
+		to->si_trapno = from.si_trapno;
 #endif
+		to->si_pkey = from.si_pkey;
 		break;
 	case SIL_CHLD:
 		to->si_pid    = from.si_pid;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 177de3640c78..de2f57fddc04 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -49,8 +49,8 @@
  */
 
 #ifndef __ARCH_IRQ_STAT
-irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
-EXPORT_SYMBOL(irq_stat);
+DEFINE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
 #endif
 
 static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
@@ -145,8 +145,7 @@ static void __local_bh_enable(unsigned int cnt)
 }
 
 /*
- * Special-case - softirqs can safely be enabled in
- * cond_resched_softirq(), or by __do_softirq(),
+ * Special-case - softirqs can safely be enabled by __do_softirq(),
  * without processing still-pending softirqs:
  */
 void _local_bh_enable(void)
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index b7591261652d..f89014a2c238 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -21,6 +21,7 @@
 #include <linux/smpboot.h>
 #include <linux/atomic.h>
 #include <linux/nmi.h>
+#include <linux/sched/wake_q.h>
 
 /*
  * Structure to determine completion condition and record errors.  May
@@ -36,7 +37,7 @@ struct cpu_stop_done {
 struct cpu_stopper {
 	struct task_struct	*thread;
 
-	spinlock_t		lock;
+	raw_spinlock_t		lock;
 	bool			enabled;	/* is this stopper enabled? */
 	struct list_head	works;		/* list of pending works */
 
@@ -65,26 +66,30 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done)
 }
 
 static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
-					struct cpu_stop_work *work)
+					struct cpu_stop_work *work,
+					struct wake_q_head *wakeq)
 {
 	list_add_tail(&work->list, &stopper->works);
-	wake_up_process(stopper->thread);
+	wake_q_add(wakeq, stopper->thread);
 }
 
 /* queue @work to @stopper.  if offline, @work is completed immediately */
 static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+	DEFINE_WAKE_Q(wakeq);
 	unsigned long flags;
 	bool enabled;
 
-	spin_lock_irqsave(&stopper->lock, flags);
+	raw_spin_lock_irqsave(&stopper->lock, flags);
 	enabled = stopper->enabled;
 	if (enabled)
-		__cpu_stop_queue_work(stopper, work);
+		__cpu_stop_queue_work(stopper, work, &wakeq);
 	else if (work->done)
 		cpu_stop_signal_done(work->done);
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	raw_spin_unlock_irqrestore(&stopper->lock, flags);
+
+	wake_up_q(&wakeq);
 
 	return enabled;
 }
@@ -229,10 +234,11 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 {
 	struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
 	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+	DEFINE_WAKE_Q(wakeq);
 	int err;
 retry:
-	spin_lock_irq(&stopper1->lock);
-	spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
+	raw_spin_lock_irq(&stopper1->lock);
+	raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
 
 	err = -ENOENT;
 	if (!stopper1->enabled || !stopper2->enabled)
@@ -252,17 +258,20 @@ retry:
 			goto unlock;
 
 	err = 0;
-	__cpu_stop_queue_work(stopper1, work1);
-	__cpu_stop_queue_work(stopper2, work2);
+	__cpu_stop_queue_work(stopper1, work1, &wakeq);
+	__cpu_stop_queue_work(stopper2, work2, &wakeq);
 unlock:
-	spin_unlock(&stopper2->lock);
-	spin_unlock_irq(&stopper1->lock);
+	raw_spin_unlock(&stopper2->lock);
+	raw_spin_unlock_irq(&stopper1->lock);
 
 	if (unlikely(err == -EDEADLK)) {
 		while (stop_cpus_in_progress)
 			cpu_relax();
 		goto retry;
 	}
+
+	wake_up_q(&wakeq);
+
 	return err;
 }
 /**
@@ -448,9 +457,9 @@ static int cpu_stop_should_run(unsigned int cpu)
 	unsigned long flags;
 	int run;
 
-	spin_lock_irqsave(&stopper->lock, flags);
+	raw_spin_lock_irqsave(&stopper->lock, flags);
 	run = !list_empty(&stopper->works);
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 	return run;
 }
 
@@ -461,13 +470,13 @@ static void cpu_stopper_thread(unsigned int cpu)
 
 repeat:
 	work = NULL;
-	spin_lock_irq(&stopper->lock);
+	raw_spin_lock_irq(&stopper->lock);
 	if (!list_empty(&stopper->works)) {
 		work = list_first_entry(&stopper->works,
 					struct cpu_stop_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_irq(&stopper->lock);
+	raw_spin_unlock_irq(&stopper->lock);
 
 	if (work) {
 		cpu_stop_fn_t fn = work->fn;
@@ -541,7 +550,7 @@ static int __init cpu_stop_init(void)
 	for_each_possible_cpu(cpu) {
 		struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 
-		spin_lock_init(&stopper->lock);
+		raw_spin_lock_init(&stopper->lock);
 		INIT_LIST_HEAD(&stopper->works);
 	}
 
diff --git a/kernel/sys.c b/kernel/sys.c
index ad692183dfe9..d1b2b8d934bb 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -61,6 +61,8 @@
 #include <linux/uidgid.h>
 #include <linux/cred.h>
 
+#include <linux/nospec.h>
+
 #include <linux/kmsg_dump.h>
 /* Move somewhere else to avoid recompiling? */
 #include <generated/utsrelease.h>
@@ -69,6 +71,9 @@
 #include <asm/io.h>
 #include <asm/unistd.h>
 
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
 #include "uid16.h"
 
 #ifndef SET_UNALIGN_CTL
@@ -1451,6 +1456,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
 
+	resource = array_index_nospec(resource, RLIM_NLIMITS);
 	task_lock(current->group_leader);
 	x = current->signal->rlim[resource];
 	task_unlock(current->group_leader);
@@ -1470,6 +1476,7 @@ COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
 
+	resource = array_index_nospec(resource, RLIM_NLIMITS);
 	task_lock(current->group_leader);
 	r = current->signal->rlim[resource];
 	task_unlock(current->group_leader);
@@ -2242,6 +2249,17 @@ static int propagate_has_child_subreaper(struct task_struct *p, void *data)
 	return 1;
 }
 
+int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which)
+{
+	return -EINVAL;
+}
+
+int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
+				    unsigned long ctrl)
+{
+	return -EINVAL;
+}
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2450,6 +2468,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SVE_GET_VL:
 		error = SVE_GET_VL();
 		break;
+	case PR_GET_SPECULATION_CTRL:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_spec_ctrl_get(me, arg2);
+		break;
+	case PR_SET_SPECULATION_CTRL:
+		if (arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
+		break;
 	default:
 		error = -EINVAL;
 		break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 9791364925dc..183169c2a75b 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -43,7 +43,9 @@ COND_SYSCALL(io_submit);
 COND_SYSCALL_COMPAT(io_submit);
 COND_SYSCALL(io_cancel);
 COND_SYSCALL(io_getevents);
+COND_SYSCALL(io_pgetevents);
 COND_SYSCALL_COMPAT(io_getevents);
+COND_SYSCALL_COMPAT(io_pgetevents);
 
 /* fs/xattr.c */
 
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index e8c0dab4fd65..07148b497451 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -704,24 +704,6 @@ static const struct bin_table bin_net_netfilter_table[] = {
 	{}
 };
 
-static const struct bin_table bin_net_irda_table[] = {
-	{ CTL_INT,	NET_IRDA_DISCOVERY,		"discovery" },
-	{ CTL_STR,	NET_IRDA_DEVNAME,		"devname" },
-	{ CTL_INT,	NET_IRDA_DEBUG,			"debug" },
-	{ CTL_INT,	NET_IRDA_FAST_POLL,		"fast_poll_increase" },
-	{ CTL_INT,	NET_IRDA_DISCOVERY_SLOTS,	"discovery_slots" },
-	{ CTL_INT,	NET_IRDA_DISCOVERY_TIMEOUT,	"discovery_timeout" },
-	{ CTL_INT,	NET_IRDA_SLOT_TIMEOUT,		"slot_timeout" },
-	{ CTL_INT,	NET_IRDA_MAX_BAUD_RATE,		"max_baud_rate" },
-	{ CTL_INT,	NET_IRDA_MIN_TX_TURN_TIME,	"min_tx_turn_time" },
-	{ CTL_INT,	NET_IRDA_MAX_TX_DATA_SIZE,	"max_tx_data_size" },
-	{ CTL_INT,	NET_IRDA_MAX_TX_WINDOW,		"max_tx_window" },
-	{ CTL_INT,	NET_IRDA_MAX_NOREPLY_TIME,	"max_noreply_time" },
-	{ CTL_INT,	NET_IRDA_WARN_NOREPLY_TIME,	"warn_noreply_time" },
-	{ CTL_INT,	NET_IRDA_LAP_KEEPALIVE_TIME,	"lap_keepalive_time" },
-	{}
-};
-
 static const struct bin_table bin_net_table[] = {
 	{ CTL_DIR,	NET_CORE,		"core",		bin_net_core_table },
 	/* NET_ETHER not used */
@@ -743,7 +725,7 @@ static const struct bin_table bin_net_table[] = {
 	{ CTL_DIR,	NET_LLC,		"llc",		bin_net_llc_table },
 	{ CTL_DIR,	NET_NETFILTER,		"netfilter",	bin_net_netfilter_table },
 	/* NET_DCCP "dccp" no longer used */
-	{ CTL_DIR,	NET_IRDA,		"irda",		bin_net_irda_table },
+	/* NET_IRDA "irda" no longer used */
 	{ CTL_INT,	2089,			"nf_conntrack_max" },
 	{}
 };
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 0e974cface0b..f89a78e2792b 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -119,8 +119,15 @@ static DEFINE_SPINLOCK(watchdog_lock);
 static int watchdog_running;
 static atomic_t watchdog_reset_pending;
 
-static int clocksource_watchdog_kthread(void *data);
-static void __clocksource_change_rating(struct clocksource *cs, int rating);
+static void inline clocksource_watchdog_lock(unsigned long *flags)
+{
+	spin_lock_irqsave(&watchdog_lock, *flags);
+}
+
+static void inline clocksource_watchdog_unlock(unsigned long *flags)
+{
+	spin_unlock_irqrestore(&watchdog_lock, *flags);
+}
 
 /*
  * Interval: 0.5sec Threshold: 0.0625s
@@ -128,23 +135,24 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating);
 #define WATCHDOG_INTERVAL (HZ >> 1)
 #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4)
 
-static void clocksource_watchdog_work(struct work_struct *work)
-{
-	/*
-	 * If kthread_run fails the next watchdog scan over the
-	 * watchdog_list will find the unstable clock again.
-	 */
-	kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog");
-}
-
 static void __clocksource_unstable(struct clocksource *cs)
 {
 	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
 	cs->flags |= CLOCK_SOURCE_UNSTABLE;
 
+	/*
+	 * If the clocksource is registered clocksource_watchdog_work() will
+	 * re-rate and re-select.
+	 */
+	if (list_empty(&cs->list)) {
+		cs->rating = 0;
+		return;
+	}
+
 	if (cs->mark_unstable)
 		cs->mark_unstable(cs);
 
+	/* kick clocksource_watchdog_work() */
 	if (finished_booting)
 		schedule_work(&watchdog_work);
 }
@@ -153,10 +161,8 @@ static void __clocksource_unstable(struct clocksource *cs)
  * clocksource_mark_unstable - mark clocksource unstable via watchdog
  * @cs:		clocksource to be marked unstable
  *
- * This function is called instead of clocksource_change_rating from
- * cpu hotplug code to avoid a deadlock between the clocksource mutex
- * and the cpu hotplug mutex. It defers the update of the clocksource
- * to the watchdog thread.
+ * This function is called by the x86 TSC code to mark clocksources as unstable;
+ * it defers demotion and re-selection to a work.
  */
 void clocksource_mark_unstable(struct clocksource *cs)
 {
@@ -164,7 +170,7 @@ void clocksource_mark_unstable(struct clocksource *cs)
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
-		if (list_empty(&cs->wd_list))
+		if (!list_empty(&cs->list) && list_empty(&cs->wd_list))
 			list_add(&cs->wd_list, &watchdog_list);
 		__clocksource_unstable(cs);
 	}
@@ -319,9 +325,8 @@ static void clocksource_resume_watchdog(void)
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
 {
-	unsigned long flags;
+	INIT_LIST_HEAD(&cs->wd_list);
 
-	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 		/* cs is a clocksource to be watched. */
 		list_add(&cs->wd_list, &watchdog_list);
@@ -331,7 +336,6 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 	}
-	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
 static void clocksource_select_watchdog(bool fallback)
@@ -373,9 +377,6 @@ static void clocksource_select_watchdog(bool fallback)
 
 static void clocksource_dequeue_watchdog(struct clocksource *cs)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs != watchdog) {
 		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 			/* cs is a watched clocksource. */
@@ -384,21 +385,21 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs)
 			clocksource_stop_watchdog();
 		}
 	}
-	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
-static int __clocksource_watchdog_kthread(void)
+static void __clocksource_change_rating(struct clocksource *cs, int rating);
+
+static int __clocksource_watchdog_work(void)
 {
 	struct clocksource *cs, *tmp;
 	unsigned long flags;
-	LIST_HEAD(unstable);
 	int select = 0;
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
 		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
 			list_del_init(&cs->wd_list);
-			list_add(&cs->wd_list, &unstable);
+			__clocksource_change_rating(cs, 0);
 			select = 1;
 		}
 		if (cs->flags & CLOCK_SOURCE_RESELECT) {
@@ -410,21 +411,15 @@ static int __clocksource_watchdog_kthread(void)
 	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 
-	/* Needs to be done outside of watchdog lock */
-	list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
-		list_del_init(&cs->wd_list);
-		__clocksource_change_rating(cs, 0);
-	}
 	return select;
 }
 
-static int clocksource_watchdog_kthread(void *data)
+static void clocksource_watchdog_work(struct work_struct *work)
 {
 	mutex_lock(&clocksource_mutex);
-	if (__clocksource_watchdog_kthread())
+	if (__clocksource_watchdog_work())
 		clocksource_select();
 	mutex_unlock(&clocksource_mutex);
-	return 0;
 }
 
 static bool clocksource_is_watchdog(struct clocksource *cs)
@@ -443,10 +438,13 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 static void clocksource_select_watchdog(bool fallback) { }
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
-static inline int __clocksource_watchdog_kthread(void) { return 0; }
+static inline int __clocksource_watchdog_work(void) { return 0; }
 static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
 void clocksource_mark_unstable(struct clocksource *cs) { }
 
+static inline void clocksource_watchdog_lock(unsigned long *flags) { }
+static inline void clocksource_watchdog_unlock(unsigned long *flags) { }
+
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 /**
@@ -674,7 +672,7 @@ static int __init clocksource_done_booting(void)
 	/*
 	 * Run the watchdog first to eliminate unstable clock sources
 	 */
-	__clocksource_watchdog_kthread();
+	__clocksource_watchdog_work();
 	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
@@ -779,14 +777,19 @@ EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
  */
 int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
+	unsigned long flags;
 
 	/* Initialize mult/shift and max_idle_ns */
 	__clocksource_update_freq_scale(cs, scale, freq);
 
 	/* Add clocksource to the clocksource list */
 	mutex_lock(&clocksource_mutex);
+
+	clocksource_watchdog_lock(&flags);
 	clocksource_enqueue(cs);
 	clocksource_enqueue_watchdog(cs);
+	clocksource_watchdog_unlock(&flags);
+
 	clocksource_select();
 	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
@@ -808,8 +811,13 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating)
  */
 void clocksource_change_rating(struct clocksource *cs, int rating)
 {
+	unsigned long flags;
+
 	mutex_lock(&clocksource_mutex);
+	clocksource_watchdog_lock(&flags);
 	__clocksource_change_rating(cs, rating);
+	clocksource_watchdog_unlock(&flags);
+
 	clocksource_select();
 	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
@@ -821,6 +829,8 @@ EXPORT_SYMBOL(clocksource_change_rating);
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
+	unsigned long flags;
+
 	if (clocksource_is_watchdog(cs)) {
 		/* Select and try to install a replacement watchdog. */
 		clocksource_select_watchdog(true);
@@ -834,8 +844,12 @@ static int clocksource_unbind(struct clocksource *cs)
 		if (curr_clocksource == cs)
 			return -EBUSY;
 	}
+
+	clocksource_watchdog_lock(&flags);
 	clocksource_dequeue_watchdog(cs);
 	list_del_init(&cs->list);
+	clocksource_watchdog_unlock(&flags);
+
 	return 0;
 }
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index eda1210ce50f..055a4a728c00 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -91,6 +91,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get_real,
 		},
 		{
+			.index = HRTIMER_BASE_BOOTTIME,
+			.clockid = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+		},
+		{
 			.index = HRTIMER_BASE_TAI,
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
@@ -106,6 +111,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get_real,
 		},
 		{
+			.index = HRTIMER_BASE_BOOTTIME_SOFT,
+			.clockid = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+		},
+		{
 			.index = HRTIMER_BASE_TAI_SOFT,
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
@@ -119,7 +129,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
-	[CLOCK_BOOTTIME]	= HRTIMER_BASE_MONOTONIC,
+	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
 	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
 };
 
@@ -571,12 +581,14 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_
 static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 {
 	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
 	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
 
 	ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq,
-						   offs_real, offs_tai);
+					    offs_real, offs_boot, offs_tai);
 
 	base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real;
+	base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot;
 	base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai;
 
 	return now;
@@ -1747,8 +1759,10 @@ out:
 	return ret;
 }
 
-SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
-		struct timespec __user *, rmtp)
+#if !defined(CONFIG_64BIT_TIME) || defined(CONFIG_64BIT)
+
+SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp,
+		struct __kernel_timespec __user *, rmtp)
 {
 	struct timespec64 tu;
 
@@ -1763,7 +1777,9 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
 	return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
 }
 
-#ifdef CONFIG_COMPAT
+#endif
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
 
 COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
 		       struct compat_timespec __user *, rmtp)
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 2541bd89f20e..5a6251ac6f7a 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1205,10 +1205,12 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 			   u64 *newval, u64 *oldval)
 {
 	u64 now;
+	int ret;
 
 	WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
+	ret = cpu_timer_sample_group(clock_idx, tsk, &now);
 
-	if (oldval && cpu_timer_sample_group(clock_idx, tsk, &now) != -EINVAL) {
+	if (oldval && ret != -EINVAL) {
 		/*
 		 * We are setting itimer. The *oldval is absolute and we update
 		 * it to be relative, *newval argument is relative and we update
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index e0dbae98db9d..26aa9569e24a 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -59,7 +59,7 @@ SYS_NI(alarm);
  */
 
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
-		const struct timespec __user *, tp)
+		const struct __kernel_timespec __user *, tp)
 {
 	struct timespec64 new_tp;
 
@@ -83,8 +83,6 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 	case CLOCK_BOOTTIME:
 		get_monotonic_boottime64(tp);
 		break;
-	case CLOCK_MONOTONIC_ACTIVE:
-		ktime_get_active_ts64(tp);
 	default:
 		return -EINVAL;
 	}
@@ -92,7 +90,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 	return 0;
 }
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
-		struct timespec __user *, tp)
+		struct __kernel_timespec __user *, tp)
 {
 	int ret;
 	struct timespec64 kernel_tp;
@@ -106,7 +104,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 	return 0;
 }
 
-SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct timespec __user *, tp)
+SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct __kernel_timespec __user *, tp)
 {
 	struct timespec64 rtn_tp = {
 		.tv_sec = 0,
@@ -126,8 +124,8 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct timespec __us
 }
 
 SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
-		const struct timespec __user *, rqtp,
-		struct timespec __user *, rmtp)
+		const struct __kernel_timespec __user *, rqtp,
+		struct __kernel_timespec __user *, rmtp)
 {
 	struct timespec64 t;
 
@@ -160,7 +158,9 @@ COMPAT_SYS_NI(timer_settime);
 COMPAT_SYS_NI(timer_gettime);
 COMPAT_SYS_NI(getitimer);
 COMPAT_SYS_NI(setitimer);
+#endif
 
+#ifdef CONFIG_COMPAT_32BIT_TIME
 COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 		       struct compat_timespec __user *, tp)
 {
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index b6899b5060bd..e08ce3f27447 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -252,16 +252,15 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
 	return 0;
 }
 
-static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
 {
-	timekeeping_clocktai64(tp);
+	get_monotonic_boottime64(tp);
 	return 0;
 }
 
-static int posix_get_monotonic_active(clockid_t which_clock,
-				      struct timespec64 *tp)
+static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
 {
-	ktime_get_active_ts64(tp);
+	timekeeping_clocktai64(tp);
 	return 0;
 }
 
@@ -1041,7 +1040,7 @@ void exit_itimers(struct signal_struct *sig)
 }
 
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
-		const struct timespec __user *, tp)
+		const struct __kernel_timespec __user *, tp)
 {
 	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec64 new_tp;
@@ -1056,7 +1055,7 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 }
 
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
-		struct timespec __user *,tp)
+		struct __kernel_timespec __user *, tp)
 {
 	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec64 kernel_tp;
@@ -1097,7 +1096,7 @@ SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
 }
 
 SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
-		struct timespec __user *, tp)
+		struct __kernel_timespec __user *, tp)
 {
 	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec64 rtn_tp;
@@ -1114,7 +1113,7 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
 	return error;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 
 COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock,
 		       struct compat_timespec __user *, tp)
@@ -1149,6 +1148,10 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
 	return err;
 }
 
+#endif
+
+#ifdef CONFIG_COMPAT
+
 COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock,
 		       struct compat_timex __user *, utp)
 {
@@ -1173,6 +1176,10 @@ COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock,
 	return err;
 }
 
+#endif
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
 COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
 		       struct compat_timespec __user *, tp)
 {
@@ -1204,8 +1211,8 @@ static int common_nsleep(const clockid_t which_clock, int flags,
 }
 
 SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
-		const struct timespec __user *, rqtp,
-		struct timespec __user *, rmtp)
+		const struct __kernel_timespec __user *, rqtp,
+		struct __kernel_timespec __user *, rmtp)
 {
 	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec64 t;
@@ -1228,7 +1235,8 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	return kc->nsleep(which_clock, flags, &t);
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
 COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 		       struct compat_timespec __user *, rqtp,
 		       struct compat_timespec __user *, rmtp)
@@ -1253,6 +1261,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 
 	return kc->nsleep(which_clock, flags, &t);
 }
+
 #endif
 
 static const struct k_clock clock_realtime = {
@@ -1317,9 +1326,19 @@ static const struct k_clock clock_tai = {
 	.timer_arm		= common_hrtimer_arm,
 };
 
-static const struct k_clock clock_monotonic_active = {
+static const struct k_clock clock_boottime = {
 	.clock_getres		= posix_get_hrtimer_res,
-	.clock_get		= posix_get_monotonic_active,
+	.clock_get		= posix_get_boottime,
+	.nsleep			= common_nsleep,
+	.timer_create		= common_timer_create,
+	.timer_set		= common_timer_set,
+	.timer_get		= common_timer_get,
+	.timer_del		= common_timer_del,
+	.timer_rearm		= common_hrtimer_rearm,
+	.timer_forward		= common_hrtimer_forward,
+	.timer_remaining	= common_hrtimer_remaining,
+	.timer_try_to_cancel	= common_hrtimer_try_to_cancel,
+	.timer_arm		= common_hrtimer_arm,
 };
 
 static const struct k_clock * const posix_clocks[] = {
@@ -1330,11 +1349,10 @@ static const struct k_clock * const posix_clocks[] = {
 	[CLOCK_MONOTONIC_RAW]		= &clock_monotonic_raw,
 	[CLOCK_REALTIME_COARSE]		= &clock_realtime_coarse,
 	[CLOCK_MONOTONIC_COARSE]	= &clock_monotonic_coarse,
-	[CLOCK_BOOTTIME]		= &clock_monotonic,
+	[CLOCK_BOOTTIME]		= &clock_boottime,
 	[CLOCK_REALTIME_ALARM]		= &alarm_clock,
 	[CLOCK_BOOTTIME_ALARM]		= &alarm_clock,
 	[CLOCK_TAI]			= &clock_tai,
-	[CLOCK_MONOTONIC_ACTIVE]	= &clock_monotonic_active,
 };
 
 static const struct k_clock *clockid_to_kclock(const clockid_t id)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index b398c2ea69b2..aa2094d5dd27 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -612,6 +612,14 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 	now = ktime_get();
 	/* Find all expired events */
 	for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
+		/*
+		 * Required for !SMP because for_each_cpu() reports
+		 * unconditionally CPU0 as set on UP kernels.
+		 */
+		if (!IS_ENABLED(CONFIG_SMP) &&
+		    cpumask_empty(tick_broadcast_oneshot_mask))
+			break;
+
 		td = &per_cpu(tick_cpu_device, cpu);
 		if (td->evtdev->next_event <= now) {
 			cpumask_set_cpu(cpu, tmpmask);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 099572ca4a8f..b7005dd21ec1 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -277,7 +277,8 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
 	 */
 	return !curdev ||
 		newdev->rating > curdev->rating ||
-	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
+	       (!cpumask_equal(curdev->cpumask, newdev->cpumask) &&
+	        !tick_check_percpu(curdev, newdev, smp_processor_id()));
 }
 
 /*
@@ -419,19 +420,6 @@ void tick_suspend_local(void)
 	clockevents_shutdown(td->evtdev);
 }
 
-static void tick_forward_next_period(void)
-{
-	ktime_t delta, now = ktime_get();
-	u64 n;
-
-	delta = ktime_sub(now, tick_next_period);
-	n = ktime_divns(delta, tick_period);
-	tick_next_period += n * tick_period;
-	if (tick_next_period < now)
-		tick_next_period += tick_period;
-	tick_sched_forward_next_period();
-}
-
 /**
  * tick_resume_local - Resume the local tick device
  *
@@ -444,8 +432,6 @@ void tick_resume_local(void)
 	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	bool broadcast = tick_resume_check_broadcast();
 
-	tick_forward_next_period();
-
 	clockevents_tick_resume(td->evtdev);
 	if (!broadcast) {
 		if (td->mode == TICKDEV_MODE_PERIODIC)
@@ -505,6 +491,7 @@ void tick_freeze(void)
 	if (tick_freeze_depth == num_online_cpus()) {
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), true);
+		system_state = SYSTEM_SUSPEND;
 		timekeeping_suspend();
 	} else {
 		tick_suspend_local();
@@ -528,6 +515,7 @@ void tick_unfreeze(void)
 
 	if (tick_freeze_depth == num_online_cpus()) {
 		timekeeping_resume();
+		system_state = SYSTEM_RUNNING;
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), false);
 	} else {
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 21efab7485ca..e277284c2831 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -141,12 +141,6 @@ static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
 #endif /* !(BROADCAST && ONESHOT) */
 
-#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
-extern void tick_sched_forward_next_period(void);
-#else
-static inline void tick_sched_forward_next_period(void) { }
-#endif
-
 /* NO_HZ_FULL internal */
 #ifdef CONFIG_NO_HZ_FULL
 extern void tick_nohz_init(void);
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index c1f518e7aa80..6fe615d57ebb 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -82,16 +82,15 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
 		    !tick_device_is_functional(dev)) {
 
-		printk(KERN_INFO "Clockevents: "
-		       "could not switch to one-shot mode:");
+		pr_info("Clockevents: could not switch to one-shot mode:");
 		if (!dev) {
-			printk(" no tick device\n");
+			pr_cont(" no tick device\n");
 		} else {
 			if (!tick_device_is_functional(dev))
-				printk(" %s is not functional.\n", dev->name);
+				pr_cont(" %s is not functional.\n", dev->name);
 			else
-				printk(" %s does not support one-shot mode.\n",
-				       dev->name);
+				pr_cont(" %s does not support one-shot mode.\n",
+					dev->name);
 		}
 		return -EINVAL;
 	}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 646645e981f9..da9455a6b42b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -52,15 +52,6 @@ struct tick_sched *tick_get_tick_sched(int cpu)
 static ktime_t last_jiffies_update;
 
 /*
- * Called after resume. Make sure that jiffies are not fast forwarded due to
- * clock monotonic being forwarded by the suspended time.
- */
-void tick_sched_forward_next_period(void)
-{
-	last_jiffies_update = tick_next_period;
-}
-
-/*
  * Must be called with interrupts disabled !
  */
 static void tick_do_update_jiffies64(ktime_t now)
@@ -804,12 +795,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 		return;
 	}
 
-	hrtimer_set_expires(&ts->sched_timer, tick);
-
-	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
-		hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
-	else
+	if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+		hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+	} else {
+		hrtimer_set_expires(&ts->sched_timer, tick);
 		tick_program_event(tick, 1);
+	}
 }
 
 static void tick_nohz_retain_tick(struct tick_sched *ts)
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 3044d48ebe56..6fa99213fc72 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -407,7 +407,6 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0,
 }
 EXPORT_SYMBOL(mktime64);
 
-#if __BITS_PER_LONG == 32
 /**
  * set_normalized_timespec - set timespec sec and nsec parts and normalize
  *
@@ -468,7 +467,6 @@ struct timespec ns_to_timespec(const s64 nsec)
 	return ts;
 }
 EXPORT_SYMBOL(ns_to_timespec);
-#endif
 
 /**
  * ns_to_timeval - Convert nanoseconds to timeval
@@ -853,9 +851,9 @@ struct timespec64 timespec64_add_safe(const struct timespec64 lhs,
 }
 
 int get_timespec64(struct timespec64 *ts,
-		   const struct timespec __user *uts)
+		   const struct __kernel_timespec __user *uts)
 {
-	struct timespec kts;
+	struct __kernel_timespec kts;
 	int ret;
 
 	ret = copy_from_user(&kts, uts, sizeof(kts));
@@ -863,6 +861,11 @@ int get_timespec64(struct timespec64 *ts,
 		return -EFAULT;
 
 	ts->tv_sec = kts.tv_sec;
+
+	/* Zero out the padding for 32 bit systems or in compat mode */
+	if (IS_ENABLED(CONFIG_64BIT_TIME) && (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()))
+		kts.tv_nsec &= 0xFFFFFFFFUL;
+
 	ts->tv_nsec = kts.tv_nsec;
 
 	return 0;
@@ -870,16 +873,61 @@ int get_timespec64(struct timespec64 *ts,
 EXPORT_SYMBOL_GPL(get_timespec64);
 
 int put_timespec64(const struct timespec64 *ts,
-		   struct timespec __user *uts)
+		   struct __kernel_timespec __user *uts)
 {
-	struct timespec kts = {
+	struct __kernel_timespec kts = {
 		.tv_sec = ts->tv_sec,
 		.tv_nsec = ts->tv_nsec
 	};
+
 	return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0;
 }
 EXPORT_SYMBOL_GPL(put_timespec64);
 
+int __compat_get_timespec64(struct timespec64 *ts64,
+				   const struct compat_timespec __user *cts)
+{
+	struct compat_timespec ts;
+	int ret;
+
+	ret = copy_from_user(&ts, cts, sizeof(ts));
+	if (ret)
+		return -EFAULT;
+
+	ts64->tv_sec = ts.tv_sec;
+	ts64->tv_nsec = ts.tv_nsec;
+
+	return 0;
+}
+
+int __compat_put_timespec64(const struct timespec64 *ts64,
+				   struct compat_timespec __user *cts)
+{
+	struct compat_timespec ts = {
+		.tv_sec = ts64->tv_sec,
+		.tv_nsec = ts64->tv_nsec
+	};
+	return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0;
+}
+
+int compat_get_timespec64(struct timespec64 *ts, const void __user *uts)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0;
+	else
+		return __compat_get_timespec64(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_get_timespec64);
+
+int compat_put_timespec64(const struct timespec64 *ts, void __user *uts)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0;
+	else
+		return __compat_put_timespec64(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_put_timespec64);
+
 int get_itimerspec64(struct itimerspec64 *it,
 			const struct itimerspec __user *uit)
 {
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ca90219a1e73..4786df904c22 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -138,12 +138,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
 
 static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 {
-	/* Update both bases so mono and raw stay coupled. */
-	tk->tkr_mono.base += delta;
-	tk->tkr_raw.base += delta;
-
-	/* Accumulate time spent in suspend */
-	tk->time_suspended += delta;
+	tk->offs_boot = ktime_add(tk->offs_boot, delta);
 }
 
 /*
@@ -473,6 +468,36 @@ u64 ktime_get_raw_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
 
+/**
+ * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
+ *
+ * To keep it NMI safe since we're accessing from tracing, we're not using a
+ * separate timekeeper with updates to monotonic clock and boot offset
+ * protected with seqlocks. This has the following minor side effects:
+ *
+ * (1) Its possible that a timestamp be taken after the boot offset is updated
+ * but before the timekeeper is updated. If this happens, the new boot offset
+ * is added to the old timekeeping making the clock appear to update slightly
+ * earlier:
+ *    CPU 0                                        CPU 1
+ *    timekeeping_inject_sleeptime64()
+ *    __timekeeping_inject_sleeptime(tk, delta);
+ *                                                 timestamp();
+ *    timekeeping_update(tk, TK_CLEAR_NTP...);
+ *
+ * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
+ * partially updated.  Since the tk->offs_boot update is a rare event, this
+ * should be a rare occurrence which postprocessing should be able to handle.
+ */
+u64 notrace ktime_get_boot_fast_ns(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot));
+}
+EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
+
+
 /*
  * See comment for __ktime_get_fast_ns() vs. timestamp ordering
  */
@@ -680,18 +705,19 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 }
 
 /**
- * __getnstimeofday64 - Returns the time of day in a timespec64.
+ * ktime_get_real_ts64 - Returns the time of day in a timespec64.
  * @ts:		pointer to the timespec to be set
  *
- * Updates the time of day in the timespec.
- * Returns 0 on success, or -ve when suspended (timespec will be undefined).
+ * Returns the time of day in a timespec64 (WARN if suspended).
  */
-int __getnstimeofday64(struct timespec64 *ts)
+void ktime_get_real_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long seq;
 	u64 nsecs;
 
+	WARN_ON(timekeeping_suspended);
+
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
@@ -702,28 +728,8 @@ int __getnstimeofday64(struct timespec64 *ts)
 
 	ts->tv_nsec = 0;
 	timespec64_add_ns(ts, nsecs);
-
-	/*
-	 * Do not bail out early, in case there were callers still using
-	 * the value, even in the face of the WARN_ON.
-	 */
-	if (unlikely(timekeeping_suspended))
-		return -EAGAIN;
-	return 0;
 }
-EXPORT_SYMBOL(__getnstimeofday64);
-
-/**
- * getnstimeofday64 - Returns the time of day in a timespec64.
- * @ts:		pointer to the timespec64 to be set
- *
- * Returns the time of day in a timespec64 (WARN if suspended).
- */
-void getnstimeofday64(struct timespec64 *ts)
-{
-	WARN_ON(__getnstimeofday64(ts));
-}
-EXPORT_SYMBOL(getnstimeofday64);
+EXPORT_SYMBOL(ktime_get_real_ts64);
 
 ktime_t ktime_get(void)
 {
@@ -764,6 +770,7 @@ EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);
 
 static ktime_t *offsets[TK_OFFS_MAX] = {
 	[TK_OFFS_REAL]	= &tk_core.timekeeper.offs_real,
+	[TK_OFFS_BOOT]	= &tk_core.timekeeper.offs_boot,
 	[TK_OFFS_TAI]	= &tk_core.timekeeper.offs_tai,
 };
 
@@ -788,6 +795,25 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs)
 }
 EXPORT_SYMBOL_GPL(ktime_get_with_offset);
 
+ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	unsigned int seq;
+	ktime_t base, *offset = offsets[offs];
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+		base = ktime_add(tk->tkr_mono.base, *offset);
+
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	return base;
+
+}
+EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
+
 /**
  * ktime_mono_to_any() - convert mononotic time to any other time
  * @tmono:	time to convert.
@@ -861,39 +887,6 @@ void ktime_get_ts64(struct timespec64 *ts)
 EXPORT_SYMBOL_GPL(ktime_get_ts64);
 
 /**
- * ktime_get_active_ts64 - Get the active non-suspended monotonic clock
- * @ts:		pointer to timespec variable
- *
- * The function calculates the monotonic clock from the realtime clock and
- * the wall_to_monotonic offset, subtracts the accumulated suspend time and
- * stores the result in normalized timespec64 format in the variable
- * pointed to by @ts.
- */
-void ktime_get_active_ts64(struct timespec64 *ts)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
-	struct timespec64 tomono, tsusp;
-	u64 nsec, nssusp;
-	unsigned int seq;
-
-	WARN_ON(timekeeping_suspended);
-
-	do {
-		seq = read_seqcount_begin(&tk_core.seq);
-		ts->tv_sec = tk->xtime_sec;
-		nsec = timekeeping_get_ns(&tk->tkr_mono);
-		tomono = tk->wall_to_monotonic;
-		nssusp = tk->time_suspended;
-	} while (read_seqcount_retry(&tk_core.seq, seq));
-
-	ts->tv_sec += tomono.tv_sec;
-	ts->tv_nsec = 0;
-	timespec64_add_ns(ts, nsec + tomono.tv_nsec);
-	tsusp = ns_to_timespec64(nssusp);
-	*ts = timespec64_sub(*ts, tsusp);
-}
-
-/**
  * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC
  *
  * Returns the seconds portion of CLOCK_MONOTONIC with a single non
@@ -1417,12 +1410,12 @@ int timekeeping_notify(struct clocksource *clock)
 }
 
 /**
- * getrawmonotonic64 - Returns the raw monotonic time in a timespec
+ * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec
  * @ts:		pointer to the timespec64 to be set
  *
  * Returns the raw monotonic time (completely un-modified by ntp)
  */
-void getrawmonotonic64(struct timespec64 *ts)
+void ktime_get_raw_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long seq;
@@ -1438,7 +1431,7 @@ void getrawmonotonic64(struct timespec64 *ts)
 	ts->tv_nsec = 0;
 	timespec64_add_ns(ts, nsecs);
 }
-EXPORT_SYMBOL(getrawmonotonic64);
+EXPORT_SYMBOL(ktime_get_raw_ts64);
 
 
 /**
@@ -1593,6 +1586,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 		return;
 	}
 	tk_xtime_add(tk, delta);
+	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
 	tk_update_sleep_time(tk, timespec64_to_ktime(*delta));
 	tk_debug_account_sleep_time(delta);
 }
@@ -2125,7 +2119,7 @@ out:
 void getboottime64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended);
+	ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);
 
 	*ts = ktime_to_timespec64(t);
 }
@@ -2139,30 +2133,20 @@ unsigned long get_seconds(void)
 }
 EXPORT_SYMBOL(get_seconds);
 
-struct timespec __current_kernel_time(void)
+void ktime_get_coarse_real_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-
-	return timespec64_to_timespec(tk_xtime(tk));
-}
-
-struct timespec64 current_kernel_time64(void)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
-	struct timespec64 now;
 	unsigned long seq;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		now = tk_xtime(tk);
+		*ts = tk_xtime(tk);
 	} while (read_seqcount_retry(&tk_core.seq, seq));
-
-	return now;
 }
-EXPORT_SYMBOL(current_kernel_time64);
+EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
 
-struct timespec64 get_monotonic_coarse64(void)
+void ktime_get_coarse_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct timespec64 now, mono;
@@ -2175,12 +2159,10 @@ struct timespec64 get_monotonic_coarse64(void)
 		mono = tk->wall_to_monotonic;
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
-	set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec,
+	set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
 				now.tv_nsec + mono.tv_nsec);
-
-	return now;
 }
-EXPORT_SYMBOL(get_monotonic_coarse64);
+EXPORT_SYMBOL(ktime_get_coarse_ts64);
 
 /*
  * Must hold jiffies_lock
@@ -2195,6 +2177,7 @@ void do_timer(unsigned long ticks)
  * ktime_get_update_offsets_now - hrtimer helper
  * @cwsseq:	pointer to check and store the clock was set sequence number
  * @offs_real:	pointer to storage for monotonic -> realtime offset
+ * @offs_boot:	pointer to storage for monotonic -> boottime offset
  * @offs_tai:	pointer to storage for monotonic -> clock tai offset
  *
  * Returns current monotonic time and updates the offsets if the
@@ -2204,7 +2187,7 @@ void do_timer(unsigned long ticks)
  * Called from hrtimer_interrupt() or retrigger_next_event()
  */
 ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
-				     ktime_t *offs_tai)
+				     ktime_t *offs_boot, ktime_t *offs_tai)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned int seq;
@@ -2221,6 +2204,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
 		if (*cwsseq != tk->clock_was_set_seq) {
 			*cwsseq = tk->clock_was_set_seq;
 			*offs_real = tk->offs_real;
+			*offs_boot = tk->offs_boot;
 			*offs_tai = tk->offs_tai;
 		}
 
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 79b67f5e0343..7a9b4eb7a1d5 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -6,6 +6,7 @@
  */
 extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
 					    ktime_t *offs_real,
+					    ktime_t *offs_boot,
 					    ktime_t *offs_tai);
 
 extern int timekeeping_valid_for_hres(void);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 4a4fd567fb26..cc2d23e6ff61 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1251,18 +1251,18 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  *
  * Note: For !irqsafe timers, you must not hold locks that are held in
  *   interrupt context while calling this function. Even if the lock has
- *   nothing to do with the timer in question.  Here's why:
+ *   nothing to do with the timer in question.  Here's why::
  *
  *    CPU0                             CPU1
  *    ----                             ----
- *                                   <SOFTIRQ>
- *                                   call_timer_fn();
- *                                     base->running_timer = mytimer;
- *  spin_lock_irq(somelock);
+ *                                     <SOFTIRQ>
+ *                                       call_timer_fn();
+ *                                       base->running_timer = mytimer;
+ *    spin_lock_irq(somelock);
  *                                     <IRQ>
  *                                        spin_lock(somelock);
- *  del_timer_sync(mytimer);
- *   while (base->running_timer == mytimer);
+ *    del_timer_sync(mytimer);
+ *    while (base->running_timer == mytimer);
  *
  * Now del_timer_sync() will never return and never release somelock.
  * The interrupt on the other CPU is waiting to grab somelock but
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 0ed768b56c60..d647dabdac97 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -28,8 +28,6 @@ struct timer_list_iter {
 	u64 now;
 };
 
-typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes);
-
 /*
  * This allows printing both to /proc/timer_list and
  * to the console (on SysRq-Q):
@@ -372,24 +370,12 @@ static const struct seq_operations timer_list_sops = {
 	.show = timer_list_show,
 };
 
-static int timer_list_open(struct inode *inode, struct file *filp)
-{
-	return seq_open_private(filp, &timer_list_sops,
-			sizeof(struct timer_list_iter));
-}
-
-static const struct file_operations timer_list_fops = {
-	.open		= timer_list_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
-
 static int __init init_timer_list_procfs(void)
 {
 	struct proc_dir_entry *pe;
 
-	pe = proc_create("timer_list", 0400, NULL, &timer_list_fops);
+	pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
+			sizeof(struct timer_list_iter), NULL);
 	if (!pe)
 		return -ENOMEM;
 	return 0;
diff --git a/kernel/torture.c b/kernel/torture.c
index 37b94012a3f8..3de1efbecd6a 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -574,7 +574,7 @@ void stutter_wait(const char *title)
 {
 	int spt;
 
-	cond_resched_rcu_qs();
+	cond_resched_tasks_rcu_qs();
 	spt = READ_ONCE(stutter_pause_test);
 	for (; spt; spt = READ_ONCE(stutter_pause_test)) {
 		if (spt == 1) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d88e96d4e12c..56ba0f2a01db 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -977,6 +977,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 {
 	struct perf_event_query_bpf __user *uquery = info;
 	struct perf_event_query_bpf query = {};
+	u32 *ids, prog_cnt, ids_len;
 	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -985,16 +986,32 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 		return -EINVAL;
 	if (copy_from_user(&query, uquery, sizeof(query)))
 		return -EFAULT;
-	if (query.ids_len > BPF_TRACE_MAX_PROGS)
+
+	ids_len = query.ids_len;
+	if (ids_len > BPF_TRACE_MAX_PROGS)
 		return -E2BIG;
+	ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN);
+	if (!ids)
+		return -ENOMEM;
+	/*
+	 * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which
+	 * is required when user only wants to check for uquery->prog_cnt.
+	 * There is no need to check for it since the case is handled
+	 * gracefully in bpf_prog_array_copy_info.
+	 */
 
 	mutex_lock(&bpf_event_mutex);
 	ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
-				       uquery->ids,
-				       query.ids_len,
-				       &uquery->prog_cnt);
+				       ids,
+				       ids_len,
+				       &prog_cnt);
 	mutex_unlock(&bpf_event_mutex);
 
+	if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) ||
+	    copy_to_user(uquery->ids, ids, ids_len * sizeof(u32)))
+		ret = -EFAULT;
+
+	kfree(ids);
 	return ret;
 }
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 16bbf062018f..8d83bcf9ef69 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5514,10 +5514,10 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
 	ftrace_create_filter_files(&global_ops, d_tracer);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	trace_create_file("set_graph_function", 0444, d_tracer,
+	trace_create_file("set_graph_function", 0644, d_tracer,
 				    NULL,
 				    &ftrace_graph_fops);
-	trace_create_file("set_graph_notrace", 0444, d_tracer,
+	trace_create_file("set_graph_notrace", 0644, d_tracer,
 				    NULL,
 				    &ftrace_graph_notrace_fops);
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dfbcf9ee1447..bcd93031d042 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -893,7 +893,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 EXPORT_SYMBOL_GPL(__trace_bputs);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-static void tracing_snapshot_instance(struct trace_array *tr)
+void tracing_snapshot_instance(struct trace_array *tr)
 {
 	struct tracer *tracer = tr->current_trace;
 	unsigned long flags;
@@ -949,7 +949,7 @@ static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
 					struct trace_buffer *size_buf, int cpu_id);
 static void set_buffer_entries(struct trace_buffer *buf, unsigned long val);
 
-static int alloc_snapshot(struct trace_array *tr)
+int tracing_alloc_snapshot_instance(struct trace_array *tr)
 {
 	int ret;
 
@@ -995,7 +995,7 @@ int tracing_alloc_snapshot(void)
 	struct trace_array *tr = &global_trace;
 	int ret;
 
-	ret = alloc_snapshot(tr);
+	ret = tracing_alloc_snapshot_instance(tr);
 	WARN_ON(ret < 0);
 
 	return ret;
@@ -1165,7 +1165,7 @@ static struct {
 	{ trace_clock,			"perf",		1 },
 	{ ktime_get_mono_fast_ns,	"mono",		1 },
 	{ ktime_get_raw_fast_ns,	"mono_raw",	1 },
-	{ ktime_get_mono_fast_ns,	"boot",		1 },
+	{ ktime_get_boot_fast_ns,	"boot",		1 },
 	ARCH_TRACE_CLOCKS
 };
 
@@ -5408,7 +5408,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 	if (t->use_max_tr && !had_max_tr) {
-		ret = alloc_snapshot(tr);
+		ret = tracing_alloc_snapshot_instance(tr);
 		if (ret < 0)
 			goto out;
 	}
@@ -6451,7 +6451,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		}
 #endif
 		if (!tr->allocated_snapshot) {
-			ret = alloc_snapshot(tr);
+			ret = tracing_alloc_snapshot_instance(tr);
 			if (ret < 0)
 				break;
 		}
@@ -7179,7 +7179,7 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash,
 		return ret;
 
  out_reg:
-	ret = alloc_snapshot(tr);
+	ret = tracing_alloc_snapshot_instance(tr);
 	if (ret < 0)
 		goto out;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6fb46a06c9dc..507954b4e058 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1817,6 +1817,17 @@ static inline void __init trace_event_init(void) { }
 static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { }
 #endif
 
+#ifdef CONFIG_TRACER_SNAPSHOT
+void tracing_snapshot_instance(struct trace_array *tr);
+int tracing_alloc_snapshot_instance(struct trace_array *tr);
+#else
+static inline void tracing_snapshot_instance(struct trace_array *tr) { }
+static inline int tracing_alloc_snapshot_instance(struct trace_array *tr)
+{
+	return 0;
+}
+#endif
+
 extern struct trace_iterator *tracepoint_print_iter;
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 22fee766081b..80e0b2aca703 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -159,13 +159,13 @@ static int benchmark_event_kthread(void *arg)
 		 * wants to run, schedule in, but if the CPU is idle,
 		 * we'll keep burning cycles.
 		 *
-		 * Note the _rcu_qs() version of cond_resched() will
+		 * Note the tasks_rcu_qs() version of cond_resched() will
 		 * notify synchronize_rcu_tasks() that this thread has
 		 * passed a quiescent state for rcu_tasks. Otherwise
 		 * this thread will never voluntarily schedule which would
 		 * block synchronize_rcu_tasks() indefinitely.
 		 */
-		cond_resched();
+		cond_resched_tasks_rcu_qs();
 	}
 
 	return 0;
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e954ae3d82c0..e3a658bac10f 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -356,7 +356,7 @@ FTRACE_ENTRY(hwlat, hwlat_entry,
 		__field(	unsigned int,		seqnum		)
 	),
 
-	F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
+	F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n",
 		 __entry->seqnum,
 		 __entry->tv_sec,
 		 __entry->tv_nsec,
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 9b4716bb8bb0..7d306b74230f 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -762,6 +762,9 @@ static int regex_match_full(char *str, struct regex *r, int len)
 
 static int regex_match_front(char *str, struct regex *r, int len)
 {
+	if (len < r->len)
+		return 0;
+
 	if (strncmp(str, r->pattern, r->len) == 0)
 		return 1;
 	return 0;
@@ -1499,14 +1502,14 @@ static int process_preds(struct trace_event_call *call,
 		return ret;
 	}
 
-	if (!nr_preds) {
-		prog = NULL;
-	} else {
-		prog = predicate_parse(filter_string, nr_parens, nr_preds,
+	if (!nr_preds)
+		return -EINVAL;
+
+	prog = predicate_parse(filter_string, nr_parens, nr_preds,
 			       parse_pred, call, pe);
-		if (IS_ERR(prog))
-			return PTR_ERR(prog);
-	}
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
 	rcu_assign_pointer(filter->prog, prog);
 	return 0;
 }
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0d7b3ffbecc2..b9061ed59bbd 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2466,6 +2466,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 		else if (strcmp(modifier, "usecs") == 0)
 			*flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
 		else {
+			hist_err("Invalid field modifier: ", modifier);
 			field = ERR_PTR(-EINVAL);
 			goto out;
 		}
@@ -2481,6 +2482,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 	else {
 		field = trace_find_event_field(file->event_call, field_name);
 		if (!field || !field->size) {
+			hist_err("Couldn't find field: ", field_name);
 			field = ERR_PTR(-EINVAL);
 			goto out;
 		}
@@ -4913,6 +4915,16 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 		seq_printf(m, "%s", field_name);
 	} else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP)
 		seq_puts(m, "common_timestamp");
+
+	if (hist_field->flags) {
+		if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) &&
+		    !(hist_field->flags & HIST_FIELD_FL_EXPR)) {
+			const char *flags = get_hist_field_flags(hist_field);
+
+			if (flags)
+				seq_printf(m, ".%s", flags);
+		}
+	}
 }
 
 static int event_hist_trigger_print(struct seq_file *m,
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d251cabcf69a..8b5bdcf64871 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -483,9 +483,10 @@ clear_event_triggers(struct trace_array *tr)
 	struct trace_event_file *file;
 
 	list_for_each_entry(file, &tr->events, list) {
-		struct event_trigger_data *data;
-		list_for_each_entry_rcu(data, &file->triggers, list) {
+		struct event_trigger_data *data, *n;
+		list_for_each_entry_safe(data, n, &file->triggers, list) {
 			trace_event_trigger_enable_disable(file, 0);
+			list_del_rcu(&data->list);
 			if (data->ops->free)
 				data->ops->free(data->ops, data);
 		}
@@ -642,6 +643,7 @@ event_trigger_callback(struct event_command *cmd_ops,
 	trigger_data->count = -1;
 	trigger_data->ops = trigger_ops;
 	trigger_data->cmd_ops = cmd_ops;
+	trigger_data->private_data = file;
 	INIT_LIST_HEAD(&trigger_data->list);
 	INIT_LIST_HEAD(&trigger_data->named_list);
 
@@ -1053,7 +1055,12 @@ static void
 snapshot_trigger(struct event_trigger_data *data, void *rec,
 		 struct ring_buffer_event *event)
 {
-	tracing_snapshot();
+	struct trace_event_file *file = data->private_data;
+
+	if (file)
+		tracing_snapshot_instance(file->tr);
+	else
+		tracing_snapshot();
 }
 
 static void
@@ -1076,7 +1083,7 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
 {
 	int ret = register_trigger(glob, ops, data, file);
 
-	if (ret > 0 && tracing_alloc_snapshot() != 0) {
+	if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) {
 		unregister_trigger(glob, ops, data, file);
 		ret = 0;
 	}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 1cd3fb4d70f8..02aed76e0978 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -512,8 +512,6 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
 	if (ret == 0)
 		tk->tp.flags |= TP_FLAG_REGISTERED;
 	else {
-		pr_warn("Could not insert probe at %s+%lu: %d\n",
-			trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
 		if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
 			pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
 			ret = 0;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 3c7bfc4bf5e9..4237eba4ef20 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -472,7 +472,7 @@ static __init int stack_trace_init(void)
 			NULL, &stack_trace_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	trace_create_file("stack_trace_filter", 0444, d_tracer,
+	trace_create_file("stack_trace_filter", 0644, d_tracer,
 			  &trace_ops, &stack_trace_filter_fops);
 #endif
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 34fd0e0ec51d..ac892878dbe6 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -55,6 +55,7 @@ struct trace_uprobe {
 	struct list_head		list;
 	struct trace_uprobe_filter	filter;
 	struct uprobe_consumer		consumer;
+	struct path			path;
 	struct inode			*inode;
 	char				*filename;
 	unsigned long			offset;
@@ -289,7 +290,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
 	for (i = 0; i < tu->tp.nr_args; i++)
 		traceprobe_free_probe_arg(&tu->tp.args[i]);
 
-	iput(tu->inode);
+	path_put(&tu->path);
 	kfree(tu->tp.call.class->system);
 	kfree(tu->tp.call.name);
 	kfree(tu->filename);
@@ -363,7 +364,6 @@ end:
 static int create_trace_uprobe(int argc, char **argv)
 {
 	struct trace_uprobe *tu;
-	struct inode *inode;
 	char *arg, *event, *group, *filename;
 	char buf[MAX_EVENT_NAME_LEN];
 	struct path path;
@@ -371,7 +371,6 @@ static int create_trace_uprobe(int argc, char **argv)
 	bool is_delete, is_return;
 	int i, ret;
 
-	inode = NULL;
 	ret = 0;
 	is_delete = false;
 	is_return = false;
@@ -437,21 +436,16 @@ static int create_trace_uprobe(int argc, char **argv)
 	}
 	/* Find the last occurrence, in case the path contains ':' too. */
 	arg = strrchr(argv[1], ':');
-	if (!arg) {
-		ret = -EINVAL;
-		goto fail_address_parse;
-	}
+	if (!arg)
+		return -EINVAL;
 
 	*arg++ = '\0';
 	filename = argv[1];
 	ret = kern_path(filename, LOOKUP_FOLLOW, &path);
 	if (ret)
-		goto fail_address_parse;
-
-	inode = igrab(d_real_inode(path.dentry));
-	path_put(&path);
+		return ret;
 
-	if (!inode || !S_ISREG(inode->i_mode)) {
+	if (!d_is_reg(path.dentry)) {
 		ret = -EINVAL;
 		goto fail_address_parse;
 	}
@@ -490,7 +484,7 @@ static int create_trace_uprobe(int argc, char **argv)
 		goto fail_address_parse;
 	}
 	tu->offset = offset;
-	tu->inode = inode;
+	tu->path = path;
 	tu->filename = kstrdup(filename, GFP_KERNEL);
 
 	if (!tu->filename) {
@@ -558,7 +552,7 @@ error:
 	return ret;
 
 fail_address_parse:
-	iput(inode);
+	path_put(&path);
 
 	pr_info("Failed to parse address or file.\n");
 
@@ -922,6 +916,7 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
 		goto err_flags;
 
 	tu->consumer.filter = filter;
+	tu->inode = d_real_inode(tu->path.dentry);
 	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
 	if (ret)
 		goto err_buffer;
@@ -967,6 +962,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
 	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
+	tu->inode = NULL;
 	tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE;
 
 	uprobe_buffer_disable();
@@ -1337,7 +1333,6 @@ struct trace_event_call *
 create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 {
 	struct trace_uprobe *tu;
-	struct inode *inode;
 	struct path path;
 	int ret;
 
@@ -1345,11 +1340,8 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 	if (ret)
 		return ERR_PTR(ret);
 
-	inode = igrab(d_inode(path.dentry));
-	path_put(&path);
-
-	if (!inode || !S_ISREG(inode->i_mode)) {
-		iput(inode);
+	if (!d_is_reg(path.dentry)) {
+		path_put(&path);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -1364,11 +1356,12 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 	if (IS_ERR(tu)) {
 		pr_info("Failed to allocate trace_uprobe.(%d)\n",
 			(int)PTR_ERR(tu));
+		path_put(&path);
 		return ERR_CAST(tu);
 	}
 
 	tu->offset = offs;
-	tu->inode = inode;
+	tu->path = path;
 	tu->filename = kstrdup(name, GFP_KERNEL);
 	init_trace_event_call(tu, &tu->tp.call);
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 671b13457387..1e37da2e0c25 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -207,7 +207,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
 			lockdep_is_held(&tracepoints_mutex));
 	old = func_add(&tp_funcs, func, prio);
 	if (IS_ERR(old)) {
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
 		return PTR_ERR(old);
 	}
 
@@ -239,7 +239,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 			lockdep_is_held(&tracepoints_mutex));
 	old = func_remove(&tp_funcs, func);
 	if (IS_ERR(old)) {
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
 		return PTR_ERR(old);
 	}
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ca7959be8aaa..7ea75529eabb 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -66,7 +66,7 @@ enum {
 	 * be executing on any CPU.  The pool behaves as an unbound one.
 	 *
 	 * Note that DISASSOCIATED should be flipped only while holding
-	 * attach_mutex to avoid changing binding state while
+	 * wq_pool_attach_mutex to avoid changing binding state while
 	 * worker_attach_to_pool() is in progress.
 	 */
 	POOL_MANAGER_ACTIVE	= 1 << 0,	/* being managed */
@@ -123,7 +123,7 @@ enum {
  *    cpu or grabbing pool->lock is enough for read access.  If
  *    POOL_DISASSOCIATED is set, it's identical to L.
  *
- * A: pool->attach_mutex protected.
+ * A: wq_pool_attach_mutex protected.
  *
  * PL: wq_pool_mutex protected.
  *
@@ -166,7 +166,6 @@ struct worker_pool {
 						/* L: hash of busy workers */
 
 	struct worker		*manager;	/* L: purely informational */
-	struct mutex		attach_mutex;	/* attach/detach exclusion */
 	struct list_head	workers;	/* A: attached workers */
 	struct completion	*detach_completion; /* all workers detached */
 
@@ -297,6 +296,7 @@ static bool wq_numa_enabled;		/* unbound NUMA affinity enabled */
 static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
 
 static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
+static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */
 static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
 static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */
 
@@ -399,14 +399,14 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
  * @worker: iteration cursor
  * @pool: worker_pool to iterate workers of
  *
- * This must be called with @pool->attach_mutex.
+ * This must be called with wq_pool_attach_mutex.
  *
  * The if/else clause exists only for the lockdep assertion and can be
  * ignored.
  */
 #define for_each_pool_worker(worker, pool)				\
 	list_for_each_entry((worker), &(pool)->workers, node)		\
-		if (({ lockdep_assert_held(&pool->attach_mutex); false; })) { } \
+		if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \
 		else
 
 /**
@@ -1724,7 +1724,7 @@ static struct worker *alloc_worker(int node)
 static void worker_attach_to_pool(struct worker *worker,
 				   struct worker_pool *pool)
 {
-	mutex_lock(&pool->attach_mutex);
+	mutex_lock(&wq_pool_attach_mutex);
 
 	/*
 	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
@@ -1733,37 +1733,40 @@ static void worker_attach_to_pool(struct worker *worker,
 	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
 
 	/*
-	 * The pool->attach_mutex ensures %POOL_DISASSOCIATED remains
-	 * stable across this function.  See the comments above the
-	 * flag definition for details.
+	 * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains
+	 * stable across this function.  See the comments above the flag
+	 * definition for details.
 	 */
 	if (pool->flags & POOL_DISASSOCIATED)
 		worker->flags |= WORKER_UNBOUND;
 
 	list_add_tail(&worker->node, &pool->workers);
+	worker->pool = pool;
 
-	mutex_unlock(&pool->attach_mutex);
+	mutex_unlock(&wq_pool_attach_mutex);
 }
 
 /**
  * worker_detach_from_pool() - detach a worker from its pool
  * @worker: worker which is attached to its pool
- * @pool: the pool @worker is attached to
  *
  * Undo the attaching which had been done in worker_attach_to_pool().  The
  * caller worker shouldn't access to the pool after detached except it has
  * other reference to the pool.
  */
-static void worker_detach_from_pool(struct worker *worker,
-				    struct worker_pool *pool)
+static void worker_detach_from_pool(struct worker *worker)
 {
+	struct worker_pool *pool = worker->pool;
 	struct completion *detach_completion = NULL;
 
-	mutex_lock(&pool->attach_mutex);
+	mutex_lock(&wq_pool_attach_mutex);
+
 	list_del(&worker->node);
+	worker->pool = NULL;
+
 	if (list_empty(&pool->workers))
 		detach_completion = pool->detach_completion;
-	mutex_unlock(&pool->attach_mutex);
+	mutex_unlock(&wq_pool_attach_mutex);
 
 	/* clear leftover flags without pool->lock after it is detached */
 	worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND);
@@ -1799,7 +1802,6 @@ static struct worker *create_worker(struct worker_pool *pool)
 	if (!worker)
 		goto fail;
 
-	worker->pool = pool;
 	worker->id = id;
 
 	if (pool->cpu >= 0)
@@ -2086,6 +2088,12 @@ __acquires(&pool->lock)
 	worker->current_pwq = pwq;
 	work_color = get_work_color(work);
 
+	/*
+	 * Record wq name for cmdline and debug reporting, may get
+	 * overridden through set_worker_desc().
+	 */
+	strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN);
+
 	list_del_init(&work->entry);
 
 	/*
@@ -2181,7 +2189,6 @@ __acquires(&pool->lock)
 	worker->current_work = NULL;
 	worker->current_func = NULL;
 	worker->current_pwq = NULL;
-	worker->desc_valid = false;
 	pwq_dec_nr_in_flight(pwq, work_color);
 }
 
@@ -2206,6 +2213,16 @@ static void process_scheduled_works(struct worker *worker)
 	}
 }
 
+static void set_pf_worker(bool val)
+{
+	mutex_lock(&wq_pool_attach_mutex);
+	if (val)
+		current->flags |= PF_WQ_WORKER;
+	else
+		current->flags &= ~PF_WQ_WORKER;
+	mutex_unlock(&wq_pool_attach_mutex);
+}
+
 /**
  * worker_thread - the worker thread function
  * @__worker: self
@@ -2224,7 +2241,7 @@ static int worker_thread(void *__worker)
 	struct worker_pool *pool = worker->pool;
 
 	/* tell the scheduler that this is a workqueue worker */
-	worker->task->flags |= PF_WQ_WORKER;
+	set_pf_worker(true);
 woke_up:
 	spin_lock_irq(&pool->lock);
 
@@ -2232,11 +2249,11 @@ woke_up:
 	if (unlikely(worker->flags & WORKER_DIE)) {
 		spin_unlock_irq(&pool->lock);
 		WARN_ON_ONCE(!list_empty(&worker->entry));
-		worker->task->flags &= ~PF_WQ_WORKER;
+		set_pf_worker(false);
 
 		set_task_comm(worker->task, "kworker/dying");
 		ida_simple_remove(&pool->worker_ida, worker->id);
-		worker_detach_from_pool(worker, pool);
+		worker_detach_from_pool(worker);
 		kfree(worker);
 		return 0;
 	}
@@ -2335,7 +2352,7 @@ static int rescuer_thread(void *__rescuer)
 	 * Mark rescuer as worker too.  As WORKER_PREP is never cleared, it
 	 * doesn't participate in concurrency management.
 	 */
-	rescuer->task->flags |= PF_WQ_WORKER;
+	set_pf_worker(true);
 repeat:
 	set_current_state(TASK_IDLE);
 
@@ -2367,7 +2384,6 @@ repeat:
 		worker_attach_to_pool(rescuer, pool);
 
 		spin_lock_irq(&pool->lock);
-		rescuer->pool = pool;
 
 		/*
 		 * Slurp in all works issued via this workqueue and
@@ -2417,10 +2433,9 @@ repeat:
 		if (need_more_worker(pool))
 			wake_up_worker(pool);
 
-		rescuer->pool = NULL;
 		spin_unlock_irq(&pool->lock);
 
-		worker_detach_from_pool(rescuer, pool);
+		worker_detach_from_pool(rescuer);
 
 		spin_lock_irq(&wq_mayday_lock);
 	}
@@ -2429,7 +2444,7 @@ repeat:
 
 	if (should_stop) {
 		__set_current_state(TASK_RUNNING);
-		rescuer->task->flags &= ~PF_WQ_WORKER;
+		set_pf_worker(false);
 		return 0;
 	}
 
@@ -3271,7 +3286,6 @@ static int init_worker_pool(struct worker_pool *pool)
 
 	timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0);
 
-	mutex_init(&pool->attach_mutex);
 	INIT_LIST_HEAD(&pool->workers);
 
 	ida_init(&pool->worker_ida);
@@ -3354,10 +3368,10 @@ static void put_unbound_pool(struct worker_pool *pool)
 	WARN_ON(pool->nr_workers || pool->nr_idle);
 	spin_unlock_irq(&pool->lock);
 
-	mutex_lock(&pool->attach_mutex);
+	mutex_lock(&wq_pool_attach_mutex);
 	if (!list_empty(&pool->workers))
 		pool->detach_completion = &detach_completion;
-	mutex_unlock(&pool->attach_mutex);
+	mutex_unlock(&wq_pool_attach_mutex);
 
 	if (pool->detach_completion)
 		wait_for_completion(pool->detach_completion);
@@ -4347,7 +4361,6 @@ void set_worker_desc(const char *fmt, ...)
 		va_start(args, fmt);
 		vsnprintf(worker->desc, sizeof(worker->desc), fmt, args);
 		va_end(args);
-		worker->desc_valid = true;
 	}
 }
 
@@ -4371,7 +4384,6 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
 	char desc[WORKER_DESC_LEN] = { };
 	struct pool_workqueue *pwq = NULL;
 	struct workqueue_struct *wq = NULL;
-	bool desc_valid = false;
 	struct worker *worker;
 
 	if (!(task->flags & PF_WQ_WORKER))
@@ -4384,22 +4396,18 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
 	worker = kthread_probe_data(task);
 
 	/*
-	 * Carefully copy the associated workqueue's workfn and name.  Keep
-	 * the original last '\0' in case the original contains garbage.
+	 * Carefully copy the associated workqueue's workfn, name and desc.
+	 * Keep the original last '\0' in case the original is garbage.
 	 */
 	probe_kernel_read(&fn, &worker->current_func, sizeof(fn));
 	probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq));
 	probe_kernel_read(&wq, &pwq->wq, sizeof(wq));
 	probe_kernel_read(name, wq->name, sizeof(name) - 1);
-
-	/* copy worker description */
-	probe_kernel_read(&desc_valid, &worker->desc_valid, sizeof(desc_valid));
-	if (desc_valid)
-		probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
+	probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
 
 	if (fn || name[0] || desc[0]) {
 		printk("%sWorkqueue: %s %pf", log_lvl, name, fn);
-		if (desc[0])
+		if (strcmp(name, desc))
 			pr_cont(" (%s)", desc);
 		pr_cont("\n");
 	}
@@ -4579,6 +4587,47 @@ void show_workqueue_state(void)
 	rcu_read_unlock_sched();
 }
 
+/* used to show worker information through /proc/PID/{comm,stat,status} */
+void wq_worker_comm(char *buf, size_t size, struct task_struct *task)
+{
+	int off;
+
+	/* always show the actual comm */
+	off = strscpy(buf, task->comm, size);
+	if (off < 0)
+		return;
+
+	/* stabilize PF_WQ_WORKER and worker pool association */
+	mutex_lock(&wq_pool_attach_mutex);
+
+	if (task->flags & PF_WQ_WORKER) {
+		struct worker *worker = kthread_data(task);
+		struct worker_pool *pool = worker->pool;
+
+		if (pool) {
+			spin_lock_irq(&pool->lock);
+			/*
+			 * ->desc tracks information (wq name or
+			 * set_worker_desc()) for the latest execution.  If
+			 * current, prepend '+', otherwise '-'.
+			 */
+			if (worker->desc[0] != '\0') {
+				if (worker->current_work)
+					scnprintf(buf + off, size - off, "+%s",
+						  worker->desc);
+				else
+					scnprintf(buf + off, size - off, "-%s",
+						  worker->desc);
+			}
+			spin_unlock_irq(&pool->lock);
+		}
+	}
+
+	mutex_unlock(&wq_pool_attach_mutex);
+}
+
+#ifdef CONFIG_SMP
+
 /*
  * CPU hotplug.
  *
@@ -4600,7 +4649,7 @@ static void unbind_workers(int cpu)
 	struct worker *worker;
 
 	for_each_cpu_worker_pool(pool, cpu) {
-		mutex_lock(&pool->attach_mutex);
+		mutex_lock(&wq_pool_attach_mutex);
 		spin_lock_irq(&pool->lock);
 
 		/*
@@ -4616,7 +4665,7 @@ static void unbind_workers(int cpu)
 		pool->flags |= POOL_DISASSOCIATED;
 
 		spin_unlock_irq(&pool->lock);
-		mutex_unlock(&pool->attach_mutex);
+		mutex_unlock(&wq_pool_attach_mutex);
 
 		/*
 		 * Call schedule() so that we cross rq->lock and thus can
@@ -4657,7 +4706,7 @@ static void rebind_workers(struct worker_pool *pool)
 {
 	struct worker *worker;
 
-	lockdep_assert_held(&pool->attach_mutex);
+	lockdep_assert_held(&wq_pool_attach_mutex);
 
 	/*
 	 * Restore CPU affinity of all workers.  As all idle workers should
@@ -4727,7 +4776,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
 	static cpumask_t cpumask;
 	struct worker *worker;
 
-	lockdep_assert_held(&pool->attach_mutex);
+	lockdep_assert_held(&wq_pool_attach_mutex);
 
 	/* is @cpu allowed for @pool? */
 	if (!cpumask_test_cpu(cpu, pool->attrs->cpumask))
@@ -4762,14 +4811,14 @@ int workqueue_online_cpu(unsigned int cpu)
 	mutex_lock(&wq_pool_mutex);
 
 	for_each_pool(pool, pi) {
-		mutex_lock(&pool->attach_mutex);
+		mutex_lock(&wq_pool_attach_mutex);
 
 		if (pool->cpu == cpu)
 			rebind_workers(pool);
 		else if (pool->cpu < 0)
 			restore_unbound_workers_cpumask(pool, cpu);
 
-		mutex_unlock(&pool->attach_mutex);
+		mutex_unlock(&wq_pool_attach_mutex);
 	}
 
 	/* update NUMA affinity of unbound workqueues */
@@ -4799,8 +4848,6 @@ int workqueue_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_SMP
-
 struct work_for_cpu {
 	struct work_struct work;
 	long (*fn)(void *);
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index d390d1be3748..66fbb5a9e633 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -31,13 +31,12 @@ struct worker {
 	struct work_struct	*current_work;	/* L: work being processed */
 	work_func_t		current_func;	/* L: current_work's fn */
 	struct pool_workqueue	*current_pwq; /* L: current_work's pwq */
-	bool			desc_valid;	/* ->desc is valid */
 	struct list_head	scheduled;	/* L: scheduled works */
 
 	/* 64 bytes boundary on 64bit, 32 on 32bit */
 
 	struct task_struct	*task;		/* I: worker task */
-	struct worker_pool	*pool;		/* I: the associated pool */
+	struct worker_pool	*pool;		/* A: the associated pool */
 						/* L: for rescuers */
 	struct list_head	node;		/* A: anchored at pool->workers */
 						/* A: runs through worker->node */
diff --git a/lib/Kconfig b/lib/Kconfig
index 5fe577673b98..7a913937888b 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -429,15 +429,50 @@ config SGL_ALLOC
 	bool
 	default n
 
+config NEED_SG_DMA_LENGTH
+	bool
+
+config NEED_DMA_MAP_STATE
+	bool
+
+config ARCH_DMA_ADDR_T_64BIT
+	def_bool 64BIT || PHYS_ADDR_T_64BIT
+
+config IOMMU_HELPER
+	bool
+
+config ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	bool
+
+config ARCH_HAS_SYNC_DMA_FOR_CPU
+	bool
+	select NEED_DMA_MAP_STATE
+
 config DMA_DIRECT_OPS
 	bool
-	depends on HAS_DMA && (!64BIT || ARCH_DMA_ADDR_T_64BIT)
-	default n
+	depends on HAS_DMA
+
+config DMA_NONCOHERENT_OPS
+	bool
+	depends on HAS_DMA
+	select DMA_DIRECT_OPS
+
+config DMA_NONCOHERENT_MMAP
+	bool
+	depends on DMA_NONCOHERENT_OPS
+
+config DMA_NONCOHERENT_CACHE_SYNC
+	bool
+	depends on DMA_NONCOHERENT_OPS
 
 config DMA_VIRT_OPS
 	bool
-	depends on HAS_DMA && (!64BIT || ARCH_DMA_ADDR_T_64BIT)
-	default n
+	depends on HAS_DMA
+
+config SWIOTLB
+	bool
+	select DMA_DIRECT_OPS
+	select NEED_DMA_MAP_STATE
 
 config CHECK_SIGNATURE
 	bool
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c40c7b734cd1..76555479ae36 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1634,7 +1634,7 @@ config PROVIDE_OHCI1394_DMA_INIT
 
 config DMA_API_DEBUG
 	bool "Enable debugging of DMA-API usage"
-	depends on HAVE_DMA_API_DEBUG
+	select NEED_DMA_MAP_STATE
 	help
 	  Enable this option to debug the use of the DMA API by device drivers.
 	  With this option you will be able to detect common bugs in device
@@ -1651,6 +1651,23 @@ config DMA_API_DEBUG
 
 	  If unsure, say N.
 
+config DMA_API_DEBUG_SG
+	bool "Debug DMA scatter-gather usage"
+	default y
+	depends on DMA_API_DEBUG
+	help
+	  Perform extra checking that callers of dma_map_sg() have respected the
+	  appropriate segment length/boundary limits for the given device when
+	  preparing DMA scatterlists.
+
+	  This is particularly likely to have been overlooked in cases where the
+	  dma_map_sg() API is used for general bulk mapping of pages rather than
+	  preparing literal scatter-gather descriptors, where there is a risk of
+	  unexpected behaviour from DMA API implementations if the scatterlist
+	  is technically out-of-spec.
+
+	  If unsure, say N.
+
 menuconfig RUNTIME_TESTING_MENU
 	bool "Runtime Testing"
 	def_bool y
diff --git a/lib/Makefile b/lib/Makefile
index ce20696d5a92..9f18c8152281 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -30,6 +30,7 @@ lib-$(CONFIG_PRINTK) += dump_stack.o
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
 lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o
+lib-$(CONFIG_DMA_NONCOHERENT_OPS) += dma-noncoherent.o
 lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o
 
 lib-y	+= kobject.o klist.o
@@ -147,7 +148,7 @@ obj-$(CONFIG_AUDIT_GENERIC) += audit.o
 obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
 
 obj-$(CONFIG_SWIOTLB) += swiotlb.o
-obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
+obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
 obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 7f5cdc1e6b29..c007d25bee09 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -41,6 +41,11 @@
 #define HASH_FN_SHIFT   13
 #define HASH_FN_MASK    (HASH_SIZE - 1)
 
+/* allow architectures to override this if absolutely required */
+#ifndef PREALLOC_DMA_DEBUG_ENTRIES
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+#endif
+
 enum {
 	dma_debug_single,
 	dma_debug_page,
@@ -127,7 +132,7 @@ static u32 min_free_entries;
 static u32 nr_total_entries;
 
 /* number of preallocated entries requested by kernel cmdline */
-static u32 req_entries;
+static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
 
 /* debugfs dentry's for the stuff above */
 static struct dentry *dma_debug_dent        __read_mostly;
@@ -439,7 +444,6 @@ void debug_dma_dump_mappings(struct device *dev)
 		spin_unlock_irqrestore(&bucket->lock, flags);
 	}
 }
-EXPORT_SYMBOL(debug_dma_dump_mappings);
 
 /*
  * For each mapping (initial cacheline in the case of
@@ -748,7 +752,6 @@ int dma_debug_resize_entries(u32 num_entries)
 
 	return ret;
 }
-EXPORT_SYMBOL(dma_debug_resize_entries);
 
 /*
  * DMA-API debugging init code
@@ -1004,10 +1007,7 @@ void dma_debug_add_bus(struct bus_type *bus)
 	bus_register_notifier(bus, nb);
 }
 
-/*
- * Let the architectures decide how many entries should be preallocated.
- */
-void dma_debug_init(u32 num_entries)
+static int dma_debug_init(void)
 {
 	int i;
 
@@ -1015,7 +1015,7 @@ void dma_debug_init(u32 num_entries)
 	 * called to set dma_debug_initialized
 	 */
 	if (global_disable)
-		return;
+		return 0;
 
 	for (i = 0; i < HASH_SIZE; ++i) {
 		INIT_LIST_HEAD(&dma_entry_hash[i].list);
@@ -1026,17 +1026,14 @@ void dma_debug_init(u32 num_entries)
 		pr_err("DMA-API: error creating debugfs entries - disabling\n");
 		global_disable = true;
 
-		return;
+		return 0;
 	}
 
-	if (req_entries)
-		num_entries = req_entries;
-
-	if (prealloc_memory(num_entries) != 0) {
+	if (prealloc_memory(nr_prealloc_entries) != 0) {
 		pr_err("DMA-API: debugging out of memory error - disabled\n");
 		global_disable = true;
 
-		return;
+		return 0;
 	}
 
 	nr_total_entries = num_free_entries;
@@ -1044,7 +1041,9 @@ void dma_debug_init(u32 num_entries)
 	dma_debug_initialized = true;
 
 	pr_info("DMA-API: debugging enabled by kernel config\n");
+	return 0;
 }
+core_initcall(dma_debug_init);
 
 static __init int dma_debug_cmdline(char *str)
 {
@@ -1061,16 +1060,10 @@ static __init int dma_debug_cmdline(char *str)
 
 static __init int dma_debug_entries_cmdline(char *str)
 {
-	int res;
-
 	if (!str)
 		return -EINVAL;
-
-	res = get_option(&str, &req_entries);
-
-	if (!res)
-		req_entries = 0;
-
+	if (!get_option(&str, &nr_prealloc_entries))
+		nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
 	return 0;
 }
 
@@ -1293,6 +1286,32 @@ out:
 	put_hash_bucket(bucket, &flags);
 }
 
+static void check_sg_segment(struct device *dev, struct scatterlist *sg)
+{
+#ifdef CONFIG_DMA_API_DEBUG_SG
+	unsigned int max_seg = dma_get_max_seg_size(dev);
+	u64 start, end, boundary = dma_get_seg_boundary(dev);
+
+	/*
+	 * Either the driver forgot to set dma_parms appropriately, or
+	 * whoever generated the list forgot to check them.
+	 */
+	if (sg->length > max_seg)
+		err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n",
+			   sg->length, max_seg);
+	/*
+	 * In some cases this could potentially be the DMA API
+	 * implementation's fault, but it would usually imply that
+	 * the scatterlist was built inappropriately to begin with.
+	 */
+	start = sg_dma_address(sg);
+	end = start + sg_dma_len(sg) - 1;
+	if ((start ^ end) & ~boundary)
+		err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n",
+			   start, end, boundary);
+#endif
+}
+
 void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 			size_t size, int direction, dma_addr_t dma_addr,
 			bool map_single)
@@ -1423,6 +1442,8 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 			check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
 		}
 
+		check_sg_segment(dev, s);
+
 		add_dma_entry(entry);
 	}
 }
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index c0bba30fef0a..8be8106270c2 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -34,6 +34,13 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
 		const char *caller)
 {
 	if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
+		if (!dev->dma_mask) {
+			dev_err(dev,
+				"%s: call on device without dma_mask\n",
+				caller);
+			return false;
+		}
+
 		if (*dev->dma_mask >= DMA_BIT_MASK(32)) {
 			dev_err(dev,
 				"%s: overflow %pad+%zu of device mask %llx\n",
@@ -84,7 +91,15 @@ again:
 		__free_pages(page, page_order);
 		page = NULL;
 
-		if (dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+		    dev->coherent_dma_mask < DMA_BIT_MASK(64) &&
+		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
+			gfp |= GFP_DMA32;
+			goto again;
+		}
+
+		if (IS_ENABLED(CONFIG_ZONE_DMA) &&
+		    dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
 		    !(gfp & GFP_DMA)) {
 			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
 			goto again;
@@ -120,7 +135,7 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		free_pages((unsigned long)cpu_addr, page_order);
 }
 
-static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir,
 		unsigned long attrs)
 {
@@ -131,8 +146,8 @@ static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 	return dma_addr;
 }
 
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	int i;
 	struct scatterlist *sg;
@@ -164,10 +179,16 @@ int dma_direct_supported(struct device *dev, u64 mask)
 	if (mask < DMA_BIT_MASK(32))
 		return 0;
 #endif
+	/*
+	 * Various PCI/PCIe bridges have broken support for > 32bit DMA even
+	 * if the device itself might support it.
+	 */
+	if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
+		return 0;
 	return 1;
 }
 
-static int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
+int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr == DIRECT_MAPPING_ERROR;
 }
@@ -179,6 +200,5 @@ const struct dma_map_ops dma_direct_ops = {
 	.map_sg			= dma_direct_map_sg,
 	.dma_supported		= dma_direct_supported,
 	.mapping_error		= dma_direct_mapping_error,
-	.is_phys		= 1,
 };
 EXPORT_SYMBOL(dma_direct_ops);
diff --git a/lib/dma-noncoherent.c b/lib/dma-noncoherent.c
new file mode 100644
index 000000000000..79e9a757387f
--- /dev/null
+++ b/lib/dma-noncoherent.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without providing cache
+ * coherence.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/scatterlist.h>
+
+static void dma_noncoherent_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	dma_addr_t addr;
+
+	addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+	if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(dev, page_to_phys(page) + offset,
+				size, dir);
+	return addr;
+}
+
+static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs);
+	if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir);
+	return nents;
+}
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir);
+}
+#endif
+
+const struct dma_map_ops dma_noncoherent_ops = {
+	.alloc			= arch_dma_alloc,
+	.free			= arch_dma_free,
+	.mmap			= arch_dma_mmap,
+	.sync_single_for_device	= dma_noncoherent_sync_single_for_device,
+	.sync_sg_for_device	= dma_noncoherent_sync_sg_for_device,
+	.map_page		= dma_noncoherent_map_page,
+	.map_sg			= dma_noncoherent_map_sg,
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+	.sync_single_for_cpu	= dma_noncoherent_sync_single_for_cpu,
+	.sync_sg_for_cpu	= dma_noncoherent_sync_sg_for_cpu,
+	.unmap_page		= dma_noncoherent_unmap_page,
+	.unmap_sg		= dma_noncoherent_unmap_sg,
+#endif
+	.dma_supported		= dma_direct_supported,
+	.mapping_error		= dma_direct_mapping_error,
+	.cache_sync		= arch_dma_cache_sync,
+};
+EXPORT_SYMBOL(dma_noncoherent_ops);
diff --git a/lib/errseq.c b/lib/errseq.c
index df782418b333..81f9e33aa7e7 100644
--- a/lib/errseq.c
+++ b/lib/errseq.c
@@ -111,27 +111,22 @@ EXPORT_SYMBOL(errseq_set);
  * errseq_sample() - Grab current errseq_t value.
  * @eseq: Pointer to errseq_t to be sampled.
  *
- * This function allows callers to sample an errseq_t value, marking it as
- * "seen" if required.
+ * This function allows callers to initialise their errseq_t variable.
+ * If the error has been "seen", new callers will not see an old error.
+ * If there is an unseen error in @eseq, the caller of this function will
+ * see it the next time it checks for an error.
  *
+ * Context: Any context.
  * Return: The current errseq value.
  */
 errseq_t errseq_sample(errseq_t *eseq)
 {
 	errseq_t old = READ_ONCE(*eseq);
-	errseq_t new = old;
 
-	/*
-	 * For the common case of no errors ever having been set, we can skip
-	 * marking the SEEN bit. Once an error has been set, the value will
-	 * never go back to zero.
-	 */
-	if (old != 0) {
-		new |= ERRSEQ_SEEN;
-		if (old != new)
-			cmpxchg(eseq, old, new);
-	}
-	return new;
+	/* If nobody has seen this error yet, then we can be the first. */
+	if (!(old & ERRSEQ_SEEN))
+		old = 0;
+	return old;
 }
 EXPORT_SYMBOL(errseq_sample);
 
diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c
index 5985a25e6cbc..5367ffa5c18f 100644
--- a/lib/find_bit_benchmark.c
+++ b/lib/find_bit_benchmark.c
@@ -132,7 +132,12 @@ static int __init find_bit_test(void)
 	test_find_next_bit(bitmap, BITMAP_LEN);
 	test_find_next_zero_bit(bitmap, BITMAP_LEN);
 	test_find_last_bit(bitmap, BITMAP_LEN);
-	test_find_first_bit(bitmap, BITMAP_LEN);
+
+	/*
+	 * test_find_first_bit() may take some time, so
+	 * traverse only part of bitmap to avoid soft lockup.
+	 */
+	test_find_first_bit(bitmap, BITMAP_LEN / 10);
 	test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN);
 
 	pr_err("\nStart testing find_bit() with sparse bitmap\n");
diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index 23633c0fda4a..92a9f243c0e2 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c
@@ -3,19 +3,8 @@
  * IOMMU helper functions for the free area management
  */
 
-#include <linux/export.h>
 #include <linux/bitmap.h>
-#include <linux/bug.h>
-
-int iommu_is_span_boundary(unsigned int index, unsigned int nr,
-			   unsigned long shift,
-			   unsigned long boundary_size)
-{
-	BUG_ON(!is_power_of_2(boundary_size));
-
-	shift = (shift + index) & (boundary_size - 1);
-	return shift + nr > boundary_size;
-}
+#include <linux/iommu-helper.h>
 
 unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
 			       unsigned long start, unsigned int nr,
@@ -38,4 +27,3 @@ again:
 	}
 	return -1;
 }
-EXPORT_SYMBOL(iommu_area_alloc);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 970212670b6a..7e43cd54c84c 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -573,6 +573,67 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 }
 EXPORT_SYMBOL(_copy_to_iter);
 
+#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
+static int copyout_mcsafe(void __user *to, const void *from, size_t n)
+{
+	if (access_ok(VERIFY_WRITE, to, n)) {
+		kasan_check_read(from, n);
+		n = copy_to_user_mcsafe((__force void *) to, from, n);
+	}
+	return n;
+}
+
+static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
+		const char *from, size_t len)
+{
+	unsigned long ret;
+	char *to;
+
+	to = kmap_atomic(page);
+	ret = memcpy_mcsafe(to + offset, from, len);
+	kunmap_atomic(to);
+
+	return ret;
+}
+
+size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
+{
+	const char *from = addr;
+	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
+
+	if (unlikely(i->type & ITER_PIPE)) {
+		WARN_ON(1);
+		return 0;
+	}
+	if (iter_is_iovec(i))
+		might_fault();
+	iterate_and_advance(i, bytes, v,
+		copyout_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		({
+		rem = memcpy_mcsafe_to_page(v.bv_page, v.bv_offset,
+                               (from += v.bv_len) - v.bv_len, v.bv_len);
+		if (rem) {
+			curr_addr = (unsigned long) from;
+			bytes = curr_addr - s_addr - rem;
+			return bytes;
+		}
+		}),
+		({
+		rem = memcpy_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len,
+				v.iov_len);
+		if (rem) {
+			curr_addr = (unsigned long) from;
+			bytes = curr_addr - s_addr - rem;
+			return bytes;
+		}
+		})
+	)
+
+	return bytes;
+}
+EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe);
+#endif /* CONFIG_ARCH_HAS_UACCESS_MCSAFE */
+
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
@@ -1012,7 +1073,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
 }
 EXPORT_SYMBOL(iov_iter_gap_alignment);
 
-static inline size_t __pipe_get_pages(struct iov_iter *i,
+static inline ssize_t __pipe_get_pages(struct iov_iter *i,
 				size_t maxsize,
 				struct page **pages,
 				int idx,
@@ -1102,7 +1163,7 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
 		   size_t *start)
 {
 	struct page **p;
-	size_t n;
+	ssize_t n;
 	int idx;
 	int npages;
 
diff --git a/lib/kobject.c b/lib/kobject.c
index e1d1f290bf35..18989b5b3b56 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -233,13 +233,12 @@ static int kobject_add_internal(struct kobject *kobj)
 
 		/* be noisy on error issues */
 		if (error == -EEXIST)
-			WARN(1,
-			     "%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
-			     __func__, kobject_name(kobj));
+			pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
+			       __func__, kobject_name(kobj));
 		else
-			WARN(1, "%s failed for %s (error: %d parent: %s)\n",
-			     __func__, kobject_name(kobj), error,
-			     parent ? kobject_name(parent) : "'none'");
+			pr_err("%s failed for %s (error: %d parent: %s)\n",
+			       __func__, kobject_name(kobj), error,
+			       parent ? kobject_name(parent) : "'none'");
 	} else
 		kobj->state_in_sysfs = 1;
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index da9e10c827df..a9e41aed6de4 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1612,11 +1612,9 @@ static void set_iter_tags(struct radix_tree_iter *iter,
 static void __rcu **skip_siblings(struct radix_tree_node **nodep,
 			void __rcu **slot, struct radix_tree_iter *iter)
 {
-	void *sib = node_to_entry(slot - 1);
-
 	while (iter->index < iter->next_index) {
 		*nodep = rcu_dereference_raw(*slot);
-		if (*nodep && *nodep != sib)
+		if (*nodep && !is_sibling_entry(iter->node, *nodep))
 			return slot;
 		slot++;
 		iter->index = __radix_tree_iter_add(iter, 1);
@@ -1631,7 +1629,7 @@ void __rcu **__radix_tree_next_slot(void __rcu **slot,
 				struct radix_tree_iter *iter, unsigned flags)
 {
 	unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK;
-	struct radix_tree_node *node = rcu_dereference_raw(*slot);
+	struct radix_tree_node *node;
 
 	slot = skip_siblings(&node, slot, iter);
 
@@ -2036,10 +2034,12 @@ void *radix_tree_delete_item(struct radix_tree_root *root,
 			     unsigned long index, void *item)
 {
 	struct radix_tree_node *node = NULL;
-	void __rcu **slot;
+	void __rcu **slot = NULL;
 	void *entry;
 
 	entry = __radix_tree_lookup(root, index, &node, &slot);
+	if (!slot)
+		return NULL;
 	if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE,
 						get_slot_offset(node, slot))))
 		return NULL;
diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c
index 0ec3f257ffdf..1db74eb098d0 100644
--- a/lib/reed_solomon/decode_rs.c
+++ b/lib/reed_solomon/decode_rs.c
@@ -1,22 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * lib/reed_solomon/decode_rs.c
- *
- * Overview:
- *   Generic Reed Solomon encoder / decoder library
+ * Generic Reed Solomon encoder / decoder library
  *
  * Copyright 2002, Phil Karn, KA9Q
  * May be used under the terms of the GNU General Public License (GPL)
  *
  * Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de)
  *
- * $Id: decode_rs.c,v 1.7 2005/11/07 11:14:59 gleixner Exp $
- *
- */
-
-/* Generic data width independent code which is included by the
- * wrappers.
+ * Generic data width independent code which is included by the wrappers.
  */
 {
+	struct rs_codec *rs = rsc->codec;
 	int deg_lambda, el, deg_omega;
 	int i, j, r, k, pad;
 	int nn = rs->nn;
@@ -27,16 +21,22 @@
 	uint16_t *alpha_to = rs->alpha_to;
 	uint16_t *index_of = rs->index_of;
 	uint16_t u, q, tmp, num1, num2, den, discr_r, syn_error;
-	/* Err+Eras Locator poly and syndrome poly The maximum value
-	 * of nroots is 8. So the necessary stack size will be about
-	 * 220 bytes max.
-	 */
-	uint16_t lambda[nroots + 1], syn[nroots];
-	uint16_t b[nroots + 1], t[nroots + 1], omega[nroots + 1];
-	uint16_t root[nroots], reg[nroots + 1], loc[nroots];
 	int count = 0;
 	uint16_t msk = (uint16_t) rs->nn;
 
+	/*
+	 * The decoder buffers are in the rs control struct. They are
+	 * arrays sized [nroots + 1]
+	 */
+	uint16_t *lambda = rsc->buffers + RS_DECODE_LAMBDA * (nroots + 1);
+	uint16_t *syn = rsc->buffers + RS_DECODE_SYN * (nroots + 1);
+	uint16_t *b = rsc->buffers + RS_DECODE_B * (nroots + 1);
+	uint16_t *t = rsc->buffers + RS_DECODE_T * (nroots + 1);
+	uint16_t *omega = rsc->buffers + RS_DECODE_OMEGA * (nroots + 1);
+	uint16_t *root = rsc->buffers + RS_DECODE_ROOT * (nroots + 1);
+	uint16_t *reg = rsc->buffers + RS_DECODE_REG * (nroots + 1);
+	uint16_t *loc = rsc->buffers + RS_DECODE_LOC * (nroots + 1);
+
 	/* Check length parameter for validity */
 	pad = nn - nroots - len;
 	BUG_ON(pad < 0 || pad >= nn);
diff --git a/lib/reed_solomon/encode_rs.c b/lib/reed_solomon/encode_rs.c
index 0b5b1a6728ec..9112d46e869e 100644
--- a/lib/reed_solomon/encode_rs.c
+++ b/lib/reed_solomon/encode_rs.c
@@ -1,23 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * lib/reed_solomon/encode_rs.c
- *
- * Overview:
- *   Generic Reed Solomon encoder / decoder library
+ * Generic Reed Solomon encoder / decoder library
  *
  * Copyright 2002, Phil Karn, KA9Q
  * May be used under the terms of the GNU General Public License (GPL)
  *
  * Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de)
  *
- * $Id: encode_rs.c,v 1.5 2005/11/07 11:14:59 gleixner Exp $
- *
- */
-
-/* Generic data width independent code which is included by the
- * wrappers.
- * int encode_rsX (struct rs_control *rs, uintX_t *data, int len, uintY_t *par)
+ * Generic data width independent code which is included by the wrappers.
  */
 {
+	struct rs_codec *rs = rsc->codec;
 	int i, j, pad;
 	int nn = rs->nn;
 	int nroots = rs->nroots;
diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c
index 06d04cfa9339..dfcf54242fb9 100644
--- a/lib/reed_solomon/reed_solomon.c
+++ b/lib/reed_solomon/reed_solomon.c
@@ -1,43 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * lib/reed_solomon/reed_solomon.c
- *
- * Overview:
- *   Generic Reed Solomon encoder / decoder library
+ * Generic Reed Solomon encoder / decoder library
  *
  * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de)
  *
  * Reed Solomon code lifted from reed solomon library written by Phil Karn
  * Copyright 2002 Phil Karn, KA9Q
  *
- * $Id: rslib.c,v 1.7 2005/11/07 11:14:59 gleixner Exp $
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Description:
  *
  * The generic Reed Solomon library provides runtime configurable
  * encoding / decoding of RS codes.
- * Each user must call init_rs to get a pointer to a rs_control
- * structure for the given rs parameters. This structure is either
- * generated or a already available matching control structure is used.
- * If a structure is generated then the polynomial arrays for
- * fast encoding / decoding are built. This can take some time so
- * make sure not to call this function from a time critical path.
- * Usually a module / driver should initialize the necessary
- * rs_control structure on module / driver init and release it
- * on exit.
- * The encoding puts the calculated syndrome into a given syndrome
- * buffer.
- * The decoding is a two step process. The first step calculates
- * the syndrome over the received (data + syndrome) and calls the
- * second stage, which does the decoding / error correction itself.
- * Many hw encoders provide a syndrome calculation over the received
- * data + syndrome and can call the second stage directly.
  *
+ * Each user must call init_rs to get a pointer to a rs_control structure
+ * for the given rs parameters. The control struct is unique per instance.
+ * It points to a codec which can be shared by multiple control structures.
+ * If a codec is newly allocated then the polynomial arrays for fast
+ * encoding / decoding are built. This can take some time so make sure not
+ * to call this function from a time critical path.  Usually a module /
+ * driver should initialize the necessary rs_control structure on module /
+ * driver init and release it on exit.
+ *
+ * The encoding puts the calculated syndrome into a given syndrome buffer.
+ *
+ * The decoding is a two step process. The first step calculates the
+ * syndrome over the received (data + syndrome) and calls the second stage,
+ * which does the decoding / error correction itself.  Many hw encoders
+ * provide a syndrome calculation over the received data + syndrome and can
+ * call the second stage directly.
  */
-
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -46,32 +37,44 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 
-/* This list holds all currently allocated rs control structures */
-static LIST_HEAD (rslist);
+enum {
+	RS_DECODE_LAMBDA,
+	RS_DECODE_SYN,
+	RS_DECODE_B,
+	RS_DECODE_T,
+	RS_DECODE_OMEGA,
+	RS_DECODE_ROOT,
+	RS_DECODE_REG,
+	RS_DECODE_LOC,
+	RS_DECODE_NUM_BUFFERS
+};
+
+/* This list holds all currently allocated rs codec structures */
+static LIST_HEAD(codec_list);
 /* Protection for the list */
 static DEFINE_MUTEX(rslistlock);
 
 /**
- * rs_init - Initialize a Reed-Solomon codec
+ * codec_init - Initialize a Reed-Solomon codec
  * @symsize:	symbol size, bits (1-8)
  * @gfpoly:	Field generator polynomial coefficients
  * @gffunc:	Field generator function
  * @fcr:	first root of RS code generator polynomial, index form
  * @prim:	primitive element to generate polynomial roots
  * @nroots:	RS code generator polynomial degree (number of roots)
+ * @gfp:	GFP_ flags for allocations
  *
- * Allocate a control structure and the polynom arrays for faster
+ * Allocate a codec structure and the polynom arrays for faster
  * en/decoding. Fill the arrays according to the given parameters.
  */
-static struct rs_control *rs_init(int symsize, int gfpoly, int (*gffunc)(int),
-                                  int fcr, int prim, int nroots)
+static struct rs_codec *codec_init(int symsize, int gfpoly, int (*gffunc)(int),
+				   int fcr, int prim, int nroots, gfp_t gfp)
 {
-	struct rs_control *rs;
 	int i, j, sr, root, iprim;
+	struct rs_codec *rs;
 
-	/* Allocate the control structure */
-	rs = kmalloc(sizeof (struct rs_control), GFP_KERNEL);
-	if (rs == NULL)
+	rs = kzalloc(sizeof(*rs), gfp);
+	if (!rs)
 		return NULL;
 
 	INIT_LIST_HEAD(&rs->list);
@@ -85,17 +88,17 @@ static struct rs_control *rs_init(int symsize, int gfpoly, int (*gffunc)(int),
 	rs->gffunc = gffunc;
 
 	/* Allocate the arrays */
-	rs->alpha_to = kmalloc(sizeof(uint16_t) * (rs->nn + 1), GFP_KERNEL);
+	rs->alpha_to = kmalloc(sizeof(uint16_t) * (rs->nn + 1), gfp);
 	if (rs->alpha_to == NULL)
-		goto errrs;
+		goto err;
 
-	rs->index_of = kmalloc(sizeof(uint16_t) * (rs->nn + 1), GFP_KERNEL);
+	rs->index_of = kmalloc(sizeof(uint16_t) * (rs->nn + 1), gfp);
 	if (rs->index_of == NULL)
-		goto erralp;
+		goto err;
 
-	rs->genpoly = kmalloc(sizeof(uint16_t) * (rs->nroots + 1), GFP_KERNEL);
+	rs->genpoly = kmalloc(sizeof(uint16_t) * (rs->nroots + 1), gfp);
 	if(rs->genpoly == NULL)
-		goto erridx;
+		goto err;
 
 	/* Generate Galois field lookup tables */
 	rs->index_of[0] = rs->nn;	/* log(zero) = -inf */
@@ -120,7 +123,7 @@ static struct rs_control *rs_init(int symsize, int gfpoly, int (*gffunc)(int),
 	}
 	/* If it's not primitive, exit */
 	if(sr != rs->alpha_to[0])
-		goto errpol;
+		goto err;
 
 	/* Find prim-th root of 1, used in decoding */
 	for(iprim = 1; (iprim % prim) != 0; iprim += rs->nn);
@@ -148,42 +151,52 @@ static struct rs_control *rs_init(int symsize, int gfpoly, int (*gffunc)(int),
 	/* convert rs->genpoly[] to index form for quicker encoding */
 	for (i = 0; i <= nroots; i++)
 		rs->genpoly[i] = rs->index_of[rs->genpoly[i]];
+
+	rs->users = 1;
+	list_add(&rs->list, &codec_list);
 	return rs;
 
-	/* Error exit */
-errpol:
+err:
 	kfree(rs->genpoly);
-erridx:
 	kfree(rs->index_of);
-erralp:
 	kfree(rs->alpha_to);
-errrs:
 	kfree(rs);
 	return NULL;
 }
 
 
 /**
- *  free_rs - Free the rs control structure, if it is no longer used
- *  @rs:	the control structure which is not longer used by the
+ *  free_rs - Free the rs control structure
+ *  @rs:	The control structure which is not longer used by the
  *		caller
+ *
+ * Free the control structure. If @rs is the last user of the associated
+ * codec, free the codec as well.
  */
 void free_rs(struct rs_control *rs)
 {
+	struct rs_codec *cd;
+
+	if (!rs)
+		return;
+
+	cd = rs->codec;
 	mutex_lock(&rslistlock);
-	rs->users--;
-	if(!rs->users) {
-		list_del(&rs->list);
-		kfree(rs->alpha_to);
-		kfree(rs->index_of);
-		kfree(rs->genpoly);
-		kfree(rs);
+	cd->users--;
+	if(!cd->users) {
+		list_del(&cd->list);
+		kfree(cd->alpha_to);
+		kfree(cd->index_of);
+		kfree(cd->genpoly);
+		kfree(cd);
 	}
 	mutex_unlock(&rslistlock);
+	kfree(rs);
 }
+EXPORT_SYMBOL_GPL(free_rs);
 
 /**
- * init_rs_internal - Find a matching or allocate a new rs control structure
+ * init_rs_internal - Allocate rs control, find a matching codec or allocate a new one
  *  @symsize:	the symbol size (number of bits)
  *  @gfpoly:	the extended Galois field generator polynomial coefficients,
  *		with the 0th coefficient in the low order bit. The polynomial
@@ -191,55 +204,69 @@ void free_rs(struct rs_control *rs)
  *  @gffunc:	pointer to function to generate the next field element,
  *		or the multiplicative identity element if given 0.  Used
  *		instead of gfpoly if gfpoly is 0
- *  @fcr:  	the first consecutive root of the rs code generator polynomial
+ *  @fcr:	the first consecutive root of the rs code generator polynomial
  *		in index form
  *  @prim:	primitive element to generate polynomial roots
  *  @nroots:	RS code generator polynomial degree (number of roots)
+ *  @gfp:	GFP_ flags for allocations
  */
 static struct rs_control *init_rs_internal(int symsize, int gfpoly,
-                                           int (*gffunc)(int), int fcr,
-                                           int prim, int nroots)
+					   int (*gffunc)(int), int fcr,
+					   int prim, int nroots, gfp_t gfp)
 {
-	struct list_head	*tmp;
-	struct rs_control	*rs;
+	struct list_head *tmp;
+	struct rs_control *rs;
+	unsigned int bsize;
 
 	/* Sanity checks */
 	if (symsize < 1)
 		return NULL;
 	if (fcr < 0 || fcr >= (1<<symsize))
-    		return NULL;
+		return NULL;
 	if (prim <= 0 || prim >= (1<<symsize))
-    		return NULL;
+		return NULL;
 	if (nroots < 0 || nroots >= (1<<symsize))
 		return NULL;
 
+	/*
+	 * The decoder needs buffers in each control struct instance to
+	 * avoid variable size or large fixed size allocations on
+	 * stack. Size the buffers to arrays of [nroots + 1].
+	 */
+	bsize = sizeof(uint16_t) * RS_DECODE_NUM_BUFFERS * (nroots + 1);
+	rs = kzalloc(sizeof(*rs) + bsize, gfp);
+	if (!rs)
+		return NULL;
+
 	mutex_lock(&rslistlock);
 
 	/* Walk through the list and look for a matching entry */
-	list_for_each(tmp, &rslist) {
-		rs = list_entry(tmp, struct rs_control, list);
-		if (symsize != rs->mm)
+	list_for_each(tmp, &codec_list) {
+		struct rs_codec *cd = list_entry(tmp, struct rs_codec, list);
+
+		if (symsize != cd->mm)
 			continue;
-		if (gfpoly != rs->gfpoly)
+		if (gfpoly != cd->gfpoly)
 			continue;
-		if (gffunc != rs->gffunc)
+		if (gffunc != cd->gffunc)
 			continue;
-		if (fcr != rs->fcr)
+		if (fcr != cd->fcr)
 			continue;
-		if (prim != rs->prim)
+		if (prim != cd->prim)
 			continue;
-		if (nroots != rs->nroots)
+		if (nroots != cd->nroots)
 			continue;
 		/* We have a matching one already */
-		rs->users++;
+		cd->users++;
+		rs->codec = cd;
 		goto out;
 	}
 
 	/* Create a new one */
-	rs = rs_init(symsize, gfpoly, gffunc, fcr, prim, nroots);
-	if (rs) {
-		rs->users = 1;
-		list_add(&rs->list, &rslist);
+	rs->codec = codec_init(symsize, gfpoly, gffunc, fcr, prim, nroots, gfp);
+	if (!rs->codec) {
+		kfree(rs);
+		rs = NULL;
 	}
 out:
 	mutex_unlock(&rslistlock);
@@ -247,45 +274,48 @@ out:
 }
 
 /**
- * init_rs - Find a matching or allocate a new rs control structure
+ * init_rs_gfp - Create a RS control struct and initialize it
  *  @symsize:	the symbol size (number of bits)
  *  @gfpoly:	the extended Galois field generator polynomial coefficients,
  *		with the 0th coefficient in the low order bit. The polynomial
  *		must be primitive;
- *  @fcr:  	the first consecutive root of the rs code generator polynomial
+ *  @fcr:	the first consecutive root of the rs code generator polynomial
  *		in index form
  *  @prim:	primitive element to generate polynomial roots
  *  @nroots:	RS code generator polynomial degree (number of roots)
+ *  @gfp:	GFP_ flags for allocations
  */
-struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim,
-                           int nroots)
+struct rs_control *init_rs_gfp(int symsize, int gfpoly, int fcr, int prim,
+			       int nroots, gfp_t gfp)
 {
-	return init_rs_internal(symsize, gfpoly, NULL, fcr, prim, nroots);
+	return init_rs_internal(symsize, gfpoly, NULL, fcr, prim, nroots, gfp);
 }
+EXPORT_SYMBOL_GPL(init_rs_gfp);
 
 /**
- * init_rs_non_canonical - Find a matching or allocate a new rs control
- *                         structure, for fields with non-canonical
- *                         representation
+ * init_rs_non_canonical - Allocate rs control struct for fields with
+ *                         non-canonical representation
  *  @symsize:	the symbol size (number of bits)
  *  @gffunc:	pointer to function to generate the next field element,
  *		or the multiplicative identity element if given 0.  Used
  *		instead of gfpoly if gfpoly is 0
- *  @fcr:  	the first consecutive root of the rs code generator polynomial
+ *  @fcr:	the first consecutive root of the rs code generator polynomial
  *		in index form
  *  @prim:	primitive element to generate polynomial roots
  *  @nroots:	RS code generator polynomial degree (number of roots)
  */
 struct rs_control *init_rs_non_canonical(int symsize, int (*gffunc)(int),
-                                         int fcr, int prim, int nroots)
+					 int fcr, int prim, int nroots)
 {
-	return init_rs_internal(symsize, 0, gffunc, fcr, prim, nroots);
+	return init_rs_internal(symsize, 0, gffunc, fcr, prim, nroots,
+				GFP_KERNEL);
 }
+EXPORT_SYMBOL_GPL(init_rs_non_canonical);
 
 #ifdef CONFIG_REED_SOLOMON_ENC8
 /**
  *  encode_rs8 - Calculate the parity for data values (8bit data width)
- *  @rs:	the rs control structure
+ *  @rsc:	the rs control structure
  *  @data:	data field of a given type
  *  @len:	data length
  *  @par:	parity data, must be initialized by caller (usually all 0)
@@ -295,7 +325,7 @@ struct rs_control *init_rs_non_canonical(int symsize, int (*gffunc)(int),
  *  symbol size > 8. The calling code must take care of encoding of the
  *  syndrome result for storage itself.
  */
-int encode_rs8(struct rs_control *rs, uint8_t *data, int len, uint16_t *par,
+int encode_rs8(struct rs_control *rsc, uint8_t *data, int len, uint16_t *par,
 	       uint16_t invmsk)
 {
 #include "encode_rs.c"
@@ -306,7 +336,7 @@ EXPORT_SYMBOL_GPL(encode_rs8);
 #ifdef CONFIG_REED_SOLOMON_DEC8
 /**
  *  decode_rs8 - Decode codeword (8bit data width)
- *  @rs:	the rs control structure
+ *  @rsc:	the rs control structure
  *  @data:	data field of a given type
  *  @par:	received parity data field
  *  @len:	data length
@@ -319,9 +349,14 @@ EXPORT_SYMBOL_GPL(encode_rs8);
  *  The syndrome and parity uses a uint16_t data type to enable
  *  symbol size > 8. The calling code must take care of decoding of the
  *  syndrome result and the received parity before calling this code.
+ *
+ *  Note: The rs_control struct @rsc contains buffers which are used for
+ *  decoding, so the caller has to ensure that decoder invocations are
+ *  serialized.
+ *
  *  Returns the number of corrected bits or -EBADMSG for uncorrectable errors.
  */
-int decode_rs8(struct rs_control *rs, uint8_t *data, uint16_t *par, int len,
+int decode_rs8(struct rs_control *rsc, uint8_t *data, uint16_t *par, int len,
 	       uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk,
 	       uint16_t *corr)
 {
@@ -333,7 +368,7 @@ EXPORT_SYMBOL_GPL(decode_rs8);
 #ifdef CONFIG_REED_SOLOMON_ENC16
 /**
  *  encode_rs16 - Calculate the parity for data values (16bit data width)
- *  @rs:	the rs control structure
+ *  @rsc:	the rs control structure
  *  @data:	data field of a given type
  *  @len:	data length
  *  @par:	parity data, must be initialized by caller (usually all 0)
@@ -341,7 +376,7 @@ EXPORT_SYMBOL_GPL(decode_rs8);
  *
  *  Each field in the data array contains up to symbol size bits of valid data.
  */
-int encode_rs16(struct rs_control *rs, uint16_t *data, int len, uint16_t *par,
+int encode_rs16(struct rs_control *rsc, uint16_t *data, int len, uint16_t *par,
 	uint16_t invmsk)
 {
 #include "encode_rs.c"
@@ -352,7 +387,7 @@ EXPORT_SYMBOL_GPL(encode_rs16);
 #ifdef CONFIG_REED_SOLOMON_DEC16
 /**
  *  decode_rs16 - Decode codeword (16bit data width)
- *  @rs:	the rs control structure
+ *  @rsc:	the rs control structure
  *  @data:	data field of a given type
  *  @par:	received parity data field
  *  @len:	data length
@@ -363,9 +398,14 @@ EXPORT_SYMBOL_GPL(encode_rs16);
  *  @corr:	buffer to store correction bitmask on eras_pos
  *
  *  Each field in the data array contains up to symbol size bits of valid data.
+ *
+ *  Note: The rc_control struct @rsc contains buffers which are used for
+ *  decoding, so the caller has to ensure that decoder invocations are
+ *  serialized.
+ *
  *  Returns the number of corrected bits or -EBADMSG for uncorrectable errors.
  */
-int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len,
+int decode_rs16(struct rs_control *rsc, uint16_t *data, uint16_t *par, int len,
 		uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk,
 		uint16_t *corr)
 {
@@ -374,10 +414,6 @@ int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len,
 EXPORT_SYMBOL_GPL(decode_rs16);
 #endif
 
-EXPORT_SYMBOL_GPL(init_rs);
-EXPORT_SYMBOL_GPL(init_rs_non_canonical);
-EXPORT_SYMBOL_GPL(free_rs);
-
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Reed Solomon encoder/decoder");
 MODULE_AUTHOR("Phil Karn, Thomas Gleixner");
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index e6a9c06ec70c..6fdc6267f4a8 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -270,18 +270,33 @@ void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m)
 }
 EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
 
-static unsigned int sbq_calc_wake_batch(unsigned int depth)
+static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
+					unsigned int depth)
 {
 	unsigned int wake_batch;
+	unsigned int shallow_depth;
 
 	/*
 	 * For each batch, we wake up one queue. We need to make sure that our
-	 * batch size is small enough that the full depth of the bitmap is
-	 * enough to wake up all of the queues.
+	 * batch size is small enough that the full depth of the bitmap,
+	 * potentially limited by a shallow depth, is enough to wake up all of
+	 * the queues.
+	 *
+	 * Each full word of the bitmap has bits_per_word bits, and there might
+	 * be a partial word. There are depth / bits_per_word full words and
+	 * depth % bits_per_word bits left over. In bitwise arithmetic:
+	 *
+	 * bits_per_word = 1 << shift
+	 * depth / bits_per_word = depth >> shift
+	 * depth % bits_per_word = depth & ((1 << shift) - 1)
+	 *
+	 * Each word can be limited to sbq->min_shallow_depth bits.
 	 */
-	wake_batch = SBQ_WAKE_BATCH;
-	if (wake_batch > depth / SBQ_WAIT_QUEUES)
-		wake_batch = max(1U, depth / SBQ_WAIT_QUEUES);
+	shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth);
+	depth = ((depth >> sbq->sb.shift) * shallow_depth +
+		 min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth));
+	wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1,
+			     SBQ_WAKE_BATCH);
 
 	return wake_batch;
 }
@@ -307,7 +322,8 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 			*per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth;
 	}
 
-	sbq->wake_batch = sbq_calc_wake_batch(depth);
+	sbq->min_shallow_depth = UINT_MAX;
+	sbq->wake_batch = sbq_calc_wake_batch(sbq, depth);
 	atomic_set(&sbq->wake_index, 0);
 
 	sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node);
@@ -327,21 +343,28 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);
 
-void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
+static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
+					    unsigned int depth)
 {
-	unsigned int wake_batch = sbq_calc_wake_batch(depth);
+	unsigned int wake_batch = sbq_calc_wake_batch(sbq, depth);
 	int i;
 
 	if (sbq->wake_batch != wake_batch) {
 		WRITE_ONCE(sbq->wake_batch, wake_batch);
 		/*
-		 * Pairs with the memory barrier in sbq_wake_up() to ensure that
-		 * the batch size is updated before the wait counts.
+		 * Pairs with the memory barrier in sbitmap_queue_wake_up()
+		 * to ensure that the batch size is updated before the wait
+		 * counts.
 		 */
 		smp_mb__before_atomic();
 		for (i = 0; i < SBQ_WAIT_QUEUES; i++)
 			atomic_set(&sbq->ws[i].wait_cnt, 1);
 	}
+}
+
+void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
+{
+	sbitmap_queue_update_wake_batch(sbq, depth);
 	sbitmap_resize(&sbq->sb, depth);
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_resize);
@@ -380,6 +403,8 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
 	unsigned int hint, depth;
 	int nr;
 
+	WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth);
+
 	hint = this_cpu_read(*sbq->alloc_hint);
 	depth = READ_ONCE(sbq->sb.depth);
 	if (unlikely(hint >= depth)) {
@@ -403,6 +428,14 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
 }
 EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow);
 
+void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
+				     unsigned int min_shallow_depth)
+{
+	sbq->min_shallow_depth = min_shallow_depth;
+	sbitmap_queue_update_wake_batch(sbq, sbq->sb.depth);
+}
+EXPORT_SYMBOL_GPL(sbitmap_queue_min_shallow_depth);
+
 static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
 {
 	int i, wake_index;
@@ -425,52 +458,67 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
 	return NULL;
 }
 
-static void sbq_wake_up(struct sbitmap_queue *sbq)
+static bool __sbq_wake_up(struct sbitmap_queue *sbq)
 {
 	struct sbq_wait_state *ws;
 	unsigned int wake_batch;
 	int wait_cnt;
 
-	/*
-	 * Pairs with the memory barrier in set_current_state() to ensure the
-	 * proper ordering of clear_bit()/waitqueue_active() in the waker and
-	 * test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the
-	 * waiter. See the comment on waitqueue_active(). This is __after_atomic
-	 * because we just did clear_bit_unlock() in the caller.
-	 */
-	smp_mb__after_atomic();
-
 	ws = sbq_wake_ptr(sbq);
 	if (!ws)
-		return;
+		return false;
 
 	wait_cnt = atomic_dec_return(&ws->wait_cnt);
 	if (wait_cnt <= 0) {
+		int ret;
+
 		wake_batch = READ_ONCE(sbq->wake_batch);
+
 		/*
 		 * Pairs with the memory barrier in sbitmap_queue_resize() to
 		 * ensure that we see the batch size update before the wait
 		 * count is reset.
 		 */
 		smp_mb__before_atomic();
+
 		/*
-		 * If there are concurrent callers to sbq_wake_up(), the last
-		 * one to decrement the wait count below zero will bump it back
-		 * up. If there is a concurrent resize, the count reset will
-		 * either cause the cmpxchg to fail or overwrite after the
-		 * cmpxchg.
+		 * For concurrent callers of this, the one that failed the
+		 * atomic_cmpxhcg() race should call this function again
+		 * to wakeup a new batch on a different 'ws'.
 		 */
-		atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wait_cnt + wake_batch);
-		sbq_index_atomic_inc(&sbq->wake_index);
-		wake_up_nr(&ws->wait, wake_batch);
+		ret = atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wake_batch);
+		if (ret == wait_cnt) {
+			sbq_index_atomic_inc(&sbq->wake_index);
+			wake_up_nr(&ws->wait, wake_batch);
+			return false;
+		}
+
+		return true;
 	}
+
+	return false;
+}
+
+void sbitmap_queue_wake_up(struct sbitmap_queue *sbq)
+{
+	while (__sbq_wake_up(sbq))
+		;
 }
+EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up);
 
 void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
 			 unsigned int cpu)
 {
 	sbitmap_clear_bit_unlock(&sbq->sb, nr);
-	sbq_wake_up(sbq);
+	/*
+	 * Pairs with the memory barrier in set_current_state() to ensure the
+	 * proper ordering of clear_bit_unlock()/waitqueue_active() in the waker
+	 * and test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the
+	 * waiter. See the comment on waitqueue_active().
+	 */
+	smp_mb__after_atomic();
+	sbitmap_queue_wake_up(sbq);
+
 	if (likely(!sbq->round_robin && nr < sbq->sb.depth))
 		*per_cpu_ptr(sbq->alloc_hint, cpu) = nr;
 }
@@ -482,7 +530,7 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq)
 
 	/*
 	 * Pairs with the memory barrier in set_current_state() like in
-	 * sbq_wake_up().
+	 * sbitmap_queue_wake_up().
 	 */
 	smp_mb();
 	wake_index = atomic_read(&sbq->wake_index);
@@ -528,5 +576,6 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m)
 	seq_puts(m, "}\n");
 
 	seq_printf(m, "round_robin=%d\n", sbq->round_robin);
+	seq_printf(m, "min_shallow_depth=%u\n", sbq->min_shallow_depth);
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_show);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index fece57566d45..04b68d9dffac 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -593,9 +593,8 @@ found:
 }
 
 /*
- * Allocates bounce buffer and returns its kernel virtual address.
+ * Allocates bounce buffer and returns its physical address.
  */
-
 static phys_addr_t
 map_single(struct device *hwdev, phys_addr_t phys, size_t size,
 	   enum dma_data_direction dir, unsigned long attrs)
@@ -614,7 +613,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size,
 }
 
 /*
- * dma_addr is the kernel virtual address of the bounce buffer to unmap.
+ * tlb_addr is the physical address of the bounce buffer to unmap.
  */
 void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 			      size_t size, enum dma_data_direction dir,
@@ -692,7 +691,6 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 	}
 }
 
-#ifdef CONFIG_DMA_DIRECT_OPS
 static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
 		size_t size)
 {
@@ -714,7 +712,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
 
 	phys_addr = swiotlb_tbl_map_single(dev,
 			__phys_to_dma(dev, io_tlb_start),
-			0, size, DMA_FROM_DEVICE, 0);
+			0, size, DMA_FROM_DEVICE, attrs);
 	if (phys_addr == SWIOTLB_MAP_ERROR)
 		goto out_warn;
 
@@ -727,7 +725,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
 
 out_unmap:
 	dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
-		(unsigned long long)(dev ? dev->coherent_dma_mask : 0),
+		(unsigned long long)dev->coherent_dma_mask,
 		(unsigned long long)*dma_handle);
 
 	/*
@@ -737,7 +735,7 @@ out_unmap:
 	swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
 			DMA_ATTR_SKIP_CPU_SYNC);
 out_warn:
-	if ((attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
+	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
 		dev_warn(dev,
 			"swiotlb: coherent allocation failed, size=%zu\n",
 			size);
@@ -764,7 +762,6 @@ static bool swiotlb_free_buffer(struct device *dev, size_t size,
 				 DMA_ATTR_SKIP_CPU_SYNC);
 	return true;
 }
-#endif
 
 static void
 swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
@@ -1045,7 +1042,6 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask)
 	return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
 }
 
-#ifdef CONFIG_DMA_DIRECT_OPS
 void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
 {
@@ -1089,4 +1085,3 @@ const struct dma_map_ops swiotlb_dma_ops = {
 	.unmap_page		= swiotlb_unmap_page,
 	.dma_supported		= dma_direct_supported,
 };
-#endif /* CONFIG_DMA_DIRECT_OPS */
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index de16f7869fb1..6cd7d0740005 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -331,23 +331,32 @@ static void noinline __init test_mem_optimisations(void)
 	unsigned int start, nbits;
 
 	for (start = 0; start < 1024; start += 8) {
-		memset(bmap1, 0x5a, sizeof(bmap1));
-		memset(bmap2, 0x5a, sizeof(bmap2));
 		for (nbits = 0; nbits < 1024 - start; nbits += 8) {
+			memset(bmap1, 0x5a, sizeof(bmap1));
+			memset(bmap2, 0x5a, sizeof(bmap2));
+
 			bitmap_set(bmap1, start, nbits);
 			__bitmap_set(bmap2, start, nbits);
-			if (!bitmap_equal(bmap1, bmap2, 1024))
+			if (!bitmap_equal(bmap1, bmap2, 1024)) {
 				printk("set not equal %d %d\n", start, nbits);
-			if (!__bitmap_equal(bmap1, bmap2, 1024))
+				failed_tests++;
+			}
+			if (!__bitmap_equal(bmap1, bmap2, 1024)) {
 				printk("set not __equal %d %d\n", start, nbits);
+				failed_tests++;
+			}
 
 			bitmap_clear(bmap1, start, nbits);
 			__bitmap_clear(bmap2, start, nbits);
-			if (!bitmap_equal(bmap1, bmap2, 1024))
+			if (!bitmap_equal(bmap1, bmap2, 1024)) {
 				printk("clear not equal %d %d\n", start, nbits);
-			if (!__bitmap_equal(bmap1, bmap2, 1024))
+				failed_tests++;
+			}
+			if (!__bitmap_equal(bmap1, bmap2, 1024)) {
 				printk("clear not __equal %d %d\n", start,
 									nbits);
+				failed_tests++;
+			}
 		}
 	}
 }
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 71ebfa43ad05..cea592f402ed 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -204,7 +204,7 @@ test_string(void)
 #if BITS_PER_LONG == 64
 
 #define PTR_WIDTH 16
-#define PTR ((void *)0xffff0123456789ab)
+#define PTR ((void *)0xffff0123456789abUL)
 #define PTR_STR "ffff0123456789ab"
 #define ZEROS "00000000"	/* hex 32 zero bits */
 
diff --git a/lib/textsearch.c b/lib/textsearch.c
index 0b79908dfe89..5939549c0e7b 100644
--- a/lib/textsearch.c
+++ b/lib/textsearch.c
@@ -10,7 +10,10 @@
  * 		Pablo Neira Ayuso <pablo@netfilter.org>
  *
  * ==========================================================================
- *
+ */
+
+/**
+ * DOC: ts_intro
  * INTRODUCTION
  *
  *   The textsearch infrastructure provides text searching facilities for
@@ -19,7 +22,9 @@
  *
  * ARCHITECTURE
  *
- *      User
+ * .. code-block:: none
+ *
+ *     User
  *     +----------------+
  *     |        finish()|<--------------(6)-----------------+
  *     |get_next_block()|<--------------(5)---------------+ |
@@ -33,21 +38,21 @@
  *     |             (3)|----->| find()/next() |-----------+          |
  *     |             (7)|----->| destroy()     |----------------------+
  *     +----------------+      +---------------+
- *  
- *   (1) User configures a search by calling _prepare() specifying the
- *       search parameters such as the pattern and algorithm name.
+ *
+ *   (1) User configures a search by calling textsearch_prepare() specifying
+ *       the search parameters such as the pattern and algorithm name.
  *   (2) Core requests the algorithm to allocate and initialize a search
  *       configuration according to the specified parameters.
- *   (3) User starts the search(es) by calling _find() or _next() to
- *       fetch subsequent occurrences. A state variable is provided
- *       to the algorithm to store persistent variables.
+ *   (3) User starts the search(es) by calling textsearch_find() or
+ *       textsearch_next() to fetch subsequent occurrences. A state variable
+ *       is provided to the algorithm to store persistent variables.
  *   (4) Core eventually resets the search offset and forwards the find()
  *       request to the algorithm.
  *   (5) Algorithm calls get_next_block() provided by the user continuously
  *       to fetch the data to be searched in block by block.
  *   (6) Algorithm invokes finish() after the last call to get_next_block
  *       to clean up any leftovers from get_next_block. (Optional)
- *   (7) User destroys the configuration by calling _destroy().
+ *   (7) User destroys the configuration by calling textsearch_destroy().
  *   (8) Core notifies the algorithm to destroy algorithm specific
  *       allocations. (Optional)
  *
@@ -62,9 +67,10 @@
  *   amount of times and even in parallel as long as a separate struct
  *   ts_state variable is provided to every instance.
  *
- *   The actual search is performed by either calling textsearch_find_-
- *   continuous() for linear data or by providing an own get_next_block()
- *   implementation and calling textsearch_find(). Both functions return
+ *   The actual search is performed by either calling
+ *   textsearch_find_continuous() for linear data or by providing
+ *   an own get_next_block() implementation and
+ *   calling textsearch_find(). Both functions return
  *   the position of the first occurrence of the pattern or UINT_MAX if
  *   no match was found. Subsequent occurrences can be found by calling
  *   textsearch_next() regardless of the linearity of the data.
@@ -72,7 +78,7 @@
  *   Once you're done using a configuration it must be given back via
  *   textsearch_destroy.
  *
- * EXAMPLE
+ * EXAMPLE::
  *
  *   int pos;
  *   struct ts_config *conf;
@@ -87,13 +93,13 @@
  *       goto errout;
  *   }
  *
- *   pos = textsearch_find_continuous(conf, &state, example, strlen(example));
+ *   pos = textsearch_find_continuous(conf, \&state, example, strlen(example));
  *   if (pos != UINT_MAX)
- *       panic("Oh my god, dancing chickens at %d\n", pos);
+ *       panic("Oh my god, dancing chickens at \%d\n", pos);
  *
  *   textsearch_destroy(conf);
- * ==========================================================================
  */
+/* ========================================================================== */
 
 #include <linux/module.h>
 #include <linux/types.h>
@@ -225,7 +231,7 @@ static unsigned int get_linear_data(unsigned int consumed, const u8 **dst,
  *
  * Returns the position of first occurrence of the pattern or
  * %UINT_MAX if no occurrence was found.
- */ 
+ */
 unsigned int textsearch_find_continuous(struct ts_config *conf,
 					struct ts_state *state,
 					const void *data, unsigned int len)
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 30c0cb8cc9bc..a48aaa79d352 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -703,6 +703,22 @@ char *symbol_string(char *buf, char *end, void *ptr,
 #endif
 }
 
+static const struct printf_spec default_str_spec = {
+	.field_width = -1,
+	.precision = -1,
+};
+
+static const struct printf_spec default_flag_spec = {
+	.base = 16,
+	.precision = -1,
+	.flags = SPECIAL | SMALL,
+};
+
+static const struct printf_spec default_dec_spec = {
+	.base = 10,
+	.precision = -1,
+};
+
 static noinline_for_stack
 char *resource_string(char *buf, char *end, struct resource *res,
 		      struct printf_spec spec, const char *fmt)
@@ -732,21 +748,11 @@ char *resource_string(char *buf, char *end, struct resource *res,
 		.precision = -1,
 		.flags = SMALL | ZEROPAD,
 	};
-	static const struct printf_spec dec_spec = {
-		.base = 10,
-		.precision = -1,
-		.flags = 0,
-	};
 	static const struct printf_spec str_spec = {
 		.field_width = -1,
 		.precision = 10,
 		.flags = LEFT,
 	};
-	static const struct printf_spec flag_spec = {
-		.base = 16,
-		.precision = -1,
-		.flags = SPECIAL | SMALL,
-	};
 
 	/* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8)
 	 * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */
@@ -770,10 +776,10 @@ char *resource_string(char *buf, char *end, struct resource *res,
 		specp = &mem_spec;
 	} else if (res->flags & IORESOURCE_IRQ) {
 		p = string(p, pend, "irq ", str_spec);
-		specp = &dec_spec;
+		specp = &default_dec_spec;
 	} else if (res->flags & IORESOURCE_DMA) {
 		p = string(p, pend, "dma ", str_spec);
-		specp = &dec_spec;
+		specp = &default_dec_spec;
 	} else if (res->flags & IORESOURCE_BUS) {
 		p = string(p, pend, "bus ", str_spec);
 		specp = &bus_spec;
@@ -803,7 +809,7 @@ char *resource_string(char *buf, char *end, struct resource *res,
 			p = string(p, pend, " disabled", str_spec);
 	} else {
 		p = string(p, pend, " flags ", str_spec);
-		p = number(p, pend, res->flags, flag_spec);
+		p = number(p, pend, res->flags, default_flag_spec);
 	}
 	*p++ = ']';
 	*p = '\0';
@@ -913,9 +919,6 @@ char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap,
 	int cur, rbot, rtop;
 	bool first = true;
 
-	/* reused to print numbers */
-	spec = (struct printf_spec){ .base = 10 };
-
 	rbot = cur = find_first_bit(bitmap, nr_bits);
 	while (cur < nr_bits) {
 		rtop = cur;
@@ -930,13 +933,13 @@ char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap,
 		}
 		first = false;
 
-		buf = number(buf, end, rbot, spec);
+		buf = number(buf, end, rbot, default_dec_spec);
 		if (rbot < rtop) {
 			if (buf < end)
 				*buf = '-';
 			buf++;
 
-			buf = number(buf, end, rtop, spec);
+			buf = number(buf, end, rtop, default_dec_spec);
 		}
 
 		rbot = cur;
@@ -1354,11 +1357,9 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
 	return string(buf, end, uuid, spec);
 }
 
-int kptr_restrict __read_mostly;
-
 static noinline_for_stack
-char *restricted_pointer(char *buf, char *end, const void *ptr,
-			 struct printf_spec spec)
+char *pointer_string(char *buf, char *end, const void *ptr,
+		     struct printf_spec spec)
 {
 	spec.base = 16;
 	spec.flags |= SMALL;
@@ -1367,6 +1368,15 @@ char *restricted_pointer(char *buf, char *end, const void *ptr,
 		spec.flags |= ZEROPAD;
 	}
 
+	return number(buf, end, (unsigned long int)ptr, spec);
+}
+
+int kptr_restrict __read_mostly;
+
+static noinline_for_stack
+char *restricted_pointer(char *buf, char *end, const void *ptr,
+			 struct printf_spec spec)
+{
 	switch (kptr_restrict) {
 	case 0:
 		/* Always print %pK values */
@@ -1378,8 +1388,11 @@ char *restricted_pointer(char *buf, char *end, const void *ptr,
 		 * kptr_restrict==1 cannot be used in IRQ context
 		 * because its test for CAP_SYSLOG would be meaningless.
 		 */
-		if (in_irq() || in_serving_softirq() || in_nmi())
+		if (in_irq() || in_serving_softirq() || in_nmi()) {
+			if (spec.field_width == -1)
+				spec.field_width = 2 * sizeof(ptr);
 			return string(buf, end, "pK-error", spec);
+		}
 
 		/*
 		 * Only print the real pointer value if the current
@@ -1404,7 +1417,7 @@ char *restricted_pointer(char *buf, char *end, const void *ptr,
 		break;
 	}
 
-	return number(buf, end, (unsigned long)ptr, spec);
+	return pointer_string(buf, end, ptr, spec);
 }
 
 static noinline_for_stack
@@ -1456,9 +1469,6 @@ char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec,
 		return string(buf, end, NULL, spec);
 
 	switch (fmt[1]) {
-	case 'r':
-		return number(buf, end, clk_get_rate(clk), spec);
-
 	case 'n':
 	default:
 #ifdef CONFIG_COMMON_CLK
@@ -1474,23 +1484,13 @@ char *format_flags(char *buf, char *end, unsigned long flags,
 					const struct trace_print_flags *names)
 {
 	unsigned long mask;
-	const struct printf_spec strspec = {
-		.field_width = -1,
-		.precision = -1,
-	};
-	const struct printf_spec numspec = {
-		.flags = SPECIAL|SMALL,
-		.field_width = -1,
-		.precision = -1,
-		.base = 16,
-	};
 
 	for ( ; flags && names->name; names++) {
 		mask = names->mask;
 		if ((flags & mask) != mask)
 			continue;
 
-		buf = string(buf, end, names->name, strspec);
+		buf = string(buf, end, names->name, default_str_spec);
 
 		flags &= ~mask;
 		if (flags) {
@@ -1501,7 +1501,7 @@ char *format_flags(char *buf, char *end, unsigned long flags,
 	}
 
 	if (flags)
-		buf = number(buf, end, flags, numspec);
+		buf = number(buf, end, flags, default_flag_spec);
 
 	return buf;
 }
@@ -1548,22 +1548,18 @@ char *device_node_gen_full_name(const struct device_node *np, char *buf, char *e
 {
 	int depth;
 	const struct device_node *parent = np->parent;
-	static const struct printf_spec strspec = {
-		.field_width = -1,
-		.precision = -1,
-	};
 
 	/* special case for root node */
 	if (!parent)
-		return string(buf, end, "/", strspec);
+		return string(buf, end, "/", default_str_spec);
 
 	for (depth = 0; parent->parent; depth++)
 		parent = parent->parent;
 
 	for ( ; depth >= 0; depth--) {
-		buf = string(buf, end, "/", strspec);
+		buf = string(buf, end, "/", default_str_spec);
 		buf = string(buf, end, device_node_name_for_depth(np, depth),
-			     strspec);
+			     default_str_spec);
 	}
 	return buf;
 }
@@ -1655,33 +1651,22 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	return widen_string(buf, buf - buf_start, end, spec);
 }
 
-static noinline_for_stack
-char *pointer_string(char *buf, char *end, const void *ptr,
-		     struct printf_spec spec)
-{
-	spec.base = 16;
-	spec.flags |= SMALL;
-	if (spec.field_width == -1) {
-		spec.field_width = 2 * sizeof(ptr);
-		spec.flags |= ZEROPAD;
-	}
+static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key);
+static siphash_key_t ptr_key __read_mostly;
 
-	return number(buf, end, (unsigned long int)ptr, spec);
+static void enable_ptr_key_workfn(struct work_struct *work)
+{
+	get_random_bytes(&ptr_key, sizeof(ptr_key));
+	/* Needs to run from preemptible context */
+	static_branch_disable(&not_filled_random_ptr_key);
 }
 
-static bool have_filled_random_ptr_key __read_mostly;
-static siphash_key_t ptr_key __read_mostly;
+static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
 
 static void fill_random_ptr_key(struct random_ready_callback *unused)
 {
-	get_random_bytes(&ptr_key, sizeof(ptr_key));
-	/*
-	 * have_filled_random_ptr_key==true is dependent on get_random_bytes().
-	 * ptr_to_id() needs to see have_filled_random_ptr_key==true
-	 * after get_random_bytes() returns.
-	 */
-	smp_mb();
-	WRITE_ONCE(have_filled_random_ptr_key, true);
+	/* This may be in an interrupt handler. */
+	queue_work(system_unbound_wq, &enable_ptr_key_work);
 }
 
 static struct random_ready_callback random_ready = {
@@ -1695,7 +1680,8 @@ static int __init initialize_ptr_random(void)
 	if (!ret) {
 		return 0;
 	} else if (ret == -EALREADY) {
-		fill_random_ptr_key(&random_ready);
+		/* This is in preemptible context */
+		enable_ptr_key_workfn(&enable_ptr_key_work);
 		return 0;
 	}
 
@@ -1706,13 +1692,13 @@ early_initcall(initialize_ptr_random);
 /* Maps a pointer to a 32 bit unique identifier. */
 static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
 {
+	const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)";
 	unsigned long hashval;
-	const int default_width = 2 * sizeof(ptr);
 
-	if (unlikely(!have_filled_random_ptr_key)) {
-		spec.field_width = default_width;
+	if (static_branch_unlikely(&not_filled_random_ptr_key)) {
+		spec.field_width = 2 * sizeof(ptr);
 		/* string length must be less than default_width */
-		return string(buf, end, "(ptrval)", spec);
+		return string(buf, end, str, spec);
 	}
 
 #ifdef CONFIG_64BIT
@@ -1725,15 +1711,7 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
 #else
 	hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key);
 #endif
-
-	spec.flags |= SMALL;
-	if (spec.field_width == -1) {
-		spec.field_width = default_width;
-		spec.flags |= ZEROPAD;
-	}
-	spec.base = 16;
-
-	return number(buf, end, hashval, spec);
+	return pointer_string(buf, end, (const void *)hashval, spec);
 }
 
 /*
@@ -1746,10 +1724,10 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
  *
  * Right now we handle:
  *
- * - 'F' For symbolic function descriptor pointers with offset
- * - 'f' For simple symbolic function names without offset
- * - 'S' For symbolic direct pointers with offset
- * - 's' For symbolic direct pointers without offset
+ * - 'S' For symbolic direct pointers (or function descriptors) with offset
+ * - 's' For symbolic direct pointers (or function descriptors) without offset
+ * - 'F' Same as 'S'
+ * - 'f' Same as 's'
  * - '[FfSs]R' as above with __builtin_extract_return_addr() translation
  * - 'B' For backtraced symbolic direct pointers with offset
  * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref]
@@ -1846,10 +1824,6 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
  * ** When making changes please also update:
  *	Documentation/core-api/printk-formats.rst
  *
- * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
- * function pointers are really function descriptors, which contain a
- * pointer to the real address.
- *
  * Note: The default behaviour (unadorned %p) is to hash the address,
  * rendering it useful as a unique identifier.
  */
@@ -2125,6 +2099,7 @@ qualifier:
 
 	case 'x':
 		spec->flags |= SMALL;
+		/* fall through */
 
 	case 'X':
 		spec->base = 16;
@@ -3083,8 +3058,10 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
 			break;
 		case 'i':
 			base = 0;
+			/* fall through */
 		case 'd':
 			is_sign = true;
+			/* fall through */
 		case 'u':
 			break;
 		case '%':
diff --git a/mm/Kconfig b/mm/Kconfig
index d5004d82a1d6..3e0b6e87f65d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -266,7 +266,7 @@ config ARCH_ENABLE_THP_MIGRATION
 	bool
 
 config PHYS_ADDR_T_64BIT
-	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
+	def_bool 64BIT
 
 config BOUNCE
 	bool "Enable bounce buffers"
@@ -305,7 +305,7 @@ config KSM
 	  the many instances by a single page with that content, so
 	  saving memory until one or another app needs to modify the content.
 	  Recommended for use with KVM, or with other duplicative applications.
-	  See Documentation/vm/ksm.txt for more information: KSM is inactive
+	  See Documentation/vm/ksm.rst for more information: KSM is inactive
 	  until a program has madvised that an area is MADV_MERGEABLE, and
 	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
 
@@ -530,7 +530,7 @@ config MEM_SOFT_DIRTY
 	  into a page just as regular dirty bit, but unlike the latter
 	  it can be cleared by hands.
 
-	  See Documentation/vm/soft-dirty.txt for more details.
+	  See Documentation/admin-guide/mm/soft-dirty.rst for more details.
 
 config ZSWAP
 	bool "Compressed cache for swap pages (EXPERIMENTAL)"
@@ -636,6 +636,7 @@ config DEFERRED_STRUCT_PAGE_INIT
 	default n
 	depends on NO_BOOTMEM
 	depends on !FLATMEM
+	depends on !NEED_PER_CPU_KM
 	help
 	  Ordinarily all struct pages are initialised during early boot in a
 	  single thread. On very large machines this can take a considerable
@@ -656,7 +657,8 @@ config IDLE_PAGE_TRACKING
 	  be useful to tune memory cgroup limits and/or for job placement
 	  within a compute cluster.
 
-	  See Documentation/vm/idle_page_tracking.txt for more details.
+	  See Documentation/admin-guide/mm/idle_page_tracking.rst for
+	  more details.
 
 # arch_add_memory() comprehends device memory
 config ARCH_HAS_ZONE_DEVICE
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 023190c69dce..8fe3ebd6ac00 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -115,6 +115,7 @@ static int bdi_debug_register(struct backing_dev_info *bdi, const char *name)
 					       bdi, &bdi_debug_stats_fops);
 	if (!bdi->debug_stats) {
 		debugfs_remove(bdi->debug_dir);
+		bdi->debug_dir = NULL;
 		return -ENOMEM;
 	}
 
@@ -383,7 +384,7 @@ static void wb_shutdown(struct bdi_writeback *wb)
 	 * the barrier provided by test_and_clear_bit() above.
 	 */
 	smp_wmb();
-	clear_bit(WB_shutting_down, &wb->state);
+	clear_and_wake_up_bit(WB_shutting_down, &wb->state);
 }
 
 static void wb_exit(struct bdi_writeback *wb)
@@ -411,6 +412,7 @@ static void wb_exit(struct bdi_writeback *wb)
  * protected.
  */
 static DEFINE_SPINLOCK(cgwb_lock);
+static struct workqueue_struct *cgwb_release_wq;
 
 /**
  * wb_congested_get_create - get or create a wb_congested
@@ -521,7 +523,7 @@ static void cgwb_release(struct percpu_ref *refcnt)
 {
 	struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback,
 						refcnt);
-	schedule_work(&wb->release_work);
+	queue_work(cgwb_release_wq, &wb->release_work);
 }
 
 static void cgwb_kill(struct bdi_writeback *wb)
@@ -783,6 +785,21 @@ static void cgwb_bdi_register(struct backing_dev_info *bdi)
 	spin_unlock_irq(&cgwb_lock);
 }
 
+static int __init cgwb_init(void)
+{
+	/*
+	 * There can be many concurrent release work items overwhelming
+	 * system_wq.  Put them in a separate wq and limit concurrency.
+	 * There's no point in executing many of these in parallel.
+	 */
+	cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1);
+	if (!cgwb_release_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+subsys_initcall(cgwb_init);
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static int cgwb_bdi_init(struct backing_dev_info *bdi)
diff --git a/mm/cleancache.c b/mm/cleancache.c
index f7b9fdc79d97..126548b5a292 100644
--- a/mm/cleancache.c
+++ b/mm/cleancache.c
@@ -3,7 +3,7 @@
  *
  * This code provides the generic "frontend" layer to call a matching
  * "backend" driver implementation of cleancache.  See
- * Documentation/vm/cleancache.txt for more information.
+ * Documentation/vm/cleancache.rst for more information.
  *
  * Copyright (C) 2009-2010 Oracle Corp. All rights reserved.
  * Author: Dan Magenheimer
diff --git a/mm/cma.c b/mm/cma.c
index aa40e6c7b042..5809bbe360d7 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -39,7 +39,6 @@
 #include <trace/events/cma.h>
 
 #include "cma.h"
-#include "internal.h"
 
 struct cma cma_areas[MAX_CMA_AREAS];
 unsigned cma_area_count;
@@ -110,25 +109,23 @@ static int __init cma_activate_area(struct cma *cma)
 	if (!cma->bitmap)
 		return -ENOMEM;
 
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+
 	do {
 		unsigned j;
 
 		base_pfn = pfn;
-		if (!pfn_valid(base_pfn))
-			goto err;
-
-		zone = page_zone(pfn_to_page(base_pfn));
 		for (j = pageblock_nr_pages; j; --j, pfn++) {
-			if (!pfn_valid(pfn))
-				goto err;
-
+			WARN_ON_ONCE(!pfn_valid(pfn));
 			/*
-			 * In init_cma_reserved_pageblock(), present_pages
-			 * is adjusted with assumption that all pages in
-			 * the pageblock come from a single zone.
+			 * alloc_contig_range requires the pfn range
+			 * specified to be in the same zone. Make this
+			 * simple by forcing the entire CMA resv range
+			 * to be in the same zone.
 			 */
 			if (page_zone(pfn_to_page(pfn)) != zone)
-				goto err;
+				goto not_in_zone;
 		}
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
@@ -142,7 +139,7 @@ static int __init cma_activate_area(struct cma *cma)
 
 	return 0;
 
-err:
+not_in_zone:
 	pr_err("CMA area %s could not be activated\n", cma->name);
 	kfree(cma->bitmap);
 	cma->count = 0;
@@ -152,41 +149,6 @@ err:
 static int __init cma_init_reserved_areas(void)
 {
 	int i;
-	struct zone *zone;
-	pg_data_t *pgdat;
-
-	if (!cma_area_count)
-		return 0;
-
-	for_each_online_pgdat(pgdat) {
-		unsigned long start_pfn = UINT_MAX, end_pfn = 0;
-
-		zone = &pgdat->node_zones[ZONE_MOVABLE];
-
-		/*
-		 * In this case, we cannot adjust the zone range
-		 * since it is now maximum node span and we don't
-		 * know original zone range.
-		 */
-		if (populated_zone(zone))
-			continue;
-
-		for (i = 0; i < cma_area_count; i++) {
-			if (pfn_to_nid(cma_areas[i].base_pfn) !=
-				pgdat->node_id)
-				continue;
-
-			start_pfn = min(start_pfn, cma_areas[i].base_pfn);
-			end_pfn = max(end_pfn, cma_areas[i].base_pfn +
-						cma_areas[i].count);
-		}
-
-		if (!end_pfn)
-			continue;
-
-		zone->zone_start_pfn = start_pfn;
-		zone->spanned_pages = end_pfn - start_pfn;
-	}
 
 	for (i = 0; i < cma_area_count; i++) {
 		int ret = cma_activate_area(&cma_areas[i]);
@@ -195,32 +157,9 @@ static int __init cma_init_reserved_areas(void)
 			return ret;
 	}
 
-	/*
-	 * Reserved pages for ZONE_MOVABLE are now activated and
-	 * this would change ZONE_MOVABLE's managed page counter and
-	 * the other zones' present counter. We need to re-calculate
-	 * various zone information that depends on this initialization.
-	 */
-	build_all_zonelists(NULL);
-	for_each_populated_zone(zone) {
-		if (zone_idx(zone) == ZONE_MOVABLE) {
-			zone_pcp_reset(zone);
-			setup_zone_pageset(zone);
-		} else
-			zone_pcp_update(zone);
-
-		set_zone_contiguous(zone);
-	}
-
-	/*
-	 * We need to re-init per zone wmark by calling
-	 * init_per_zone_wmark_min() but doesn't call here because it is
-	 * registered on core_initcall and it will be called later than us.
-	 */
-
 	return 0;
 }
-pure_initcall(cma_init_reserved_areas);
+core_initcall(cma_init_reserved_areas);
 
 /**
  * cma_init_reserved_mem() - create custom contiguous area from reserved memory
diff --git a/mm/compaction.c b/mm/compaction.c
index 028b7210a669..29bd1df18b98 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1450,12 +1450,14 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order,
 	 * if compaction succeeds.
 	 * For costly orders, we require low watermark instead of min for
 	 * compaction to proceed to increase its chances.
+	 * ALLOC_CMA is used, as pages in CMA pageblocks are considered
+	 * suitable migration targets
 	 */
 	watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ?
 				low_wmark_pages(zone) : min_wmark_pages(zone);
 	watermark += compact_gap(order);
 	if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx,
-						0, wmark_target))
+						ALLOC_CMA, wmark_target))
 		return COMPACT_SKIPPED;
 
 	return COMPACT_CONTINUE;
diff --git a/mm/filemap.c b/mm/filemap.c
index 9276bdb2343c..0604cb02e6f3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -786,7 +786,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 	VM_BUG_ON_PAGE(!PageLocked(new), new);
 	VM_BUG_ON_PAGE(new->mapping, new);
 
-	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+	error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
 	if (!error) {
 		struct address_space *mapping = old->mapping;
 		void (*freepage)(struct page *);
@@ -842,7 +842,7 @@ static int __add_to_page_cache_locked(struct page *page,
 			return error;
 	}
 
-	error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+	error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
 	if (error) {
 		if (!huge)
 			mem_cgroup_cancel_charge(page, memcg, false);
@@ -1585,8 +1585,7 @@ no_page:
 		if (fgp_flags & FGP_ACCESSED)
 			__SetPageReferenced(page);
 
-		err = add_to_page_cache_lru(page, mapping, offset,
-				gfp_mask & GFP_RECLAIM_MASK);
+		err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
 		if (unlikely(err)) {
 			put_page(page);
 			page = NULL;
@@ -2387,7 +2386,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
 		if (!page)
 			return -ENOMEM;
 
-		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL);
+		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
 		if (ret == 0)
 			ret = mapping->a_ops->readpage(file, page);
 		else if (ret == -EEXIST)
diff --git a/mm/frontswap.c b/mm/frontswap.c
index fec8b5044040..4f5476a0f955 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -3,7 +3,7 @@
  *
  * This code provides the generic "frontend" layer to call a matching
  * "backend" driver implementation of frontswap.  See
- * Documentation/vm/frontswap.txt for more information.
+ * Documentation/vm/frontswap.rst for more information.
  *
  * Copyright (C) 2009-2012 Oracle Corp.  All rights reserved.
  * Author: Dan Magenheimer
diff --git a/mm/gup.c b/mm/gup.c
index 76af4cfeaf68..541904a7c60f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -544,6 +544,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if (vm_flags & (VM_IO | VM_PFNMAP))
 		return -EFAULT;
 
+	if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
+		return -EFAULT;
+
 	if (write) {
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))
diff --git a/mm/hmm.c b/mm/hmm.c
index 486dc394a5a3..e63e353830e8 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -37,7 +37,7 @@
 
 #if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC)
 /*
- * Device private memory see HMM (Documentation/vm/hmm.txt) or hmm.h
+ * Device private memory see HMM (Documentation/vm/hmm.rst) or hmm.h
  */
 DEFINE_STATIC_KEY_FALSE(device_private_key);
 EXPORT_SYMBOL(device_private_key);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 14ed6ee5e02f..ac5591d8622c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1185,7 +1185,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd,
 	 * mmu_notifier_invalidate_range_end() happens which can lead to a
 	 * device seeing memory write in different order than CPU.
 	 *
-	 * See Documentation/vm/mmu_notifier.txt
+	 * See Documentation/vm/mmu_notifier.rst
 	 */
 	pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
 
@@ -2037,7 +2037,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	 * replacing a zero pmd write protected page with a zero pte write
 	 * protected page.
 	 *
-	 * See Documentation/vm/mmu_notifier.txt
+	 * See Documentation/vm/mmu_notifier.rst
 	 */
 	pmdp_huge_clear_flush(vma, haddr, pmd);
 
@@ -2431,7 +2431,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		__split_huge_page_tail(head, i, lruvec, list);
 		/* Some pages can be beyond i_size: drop them from page cache */
 		if (head[i].index >= end) {
-			__ClearPageDirty(head + i);
+			ClearPageDirty(head + i);
 			__delete_from_page_cache(head + i, NULL);
 			if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
 				shmem_uncharge(head->mapping->host, 1);
@@ -2925,7 +2925,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 		pmde = maybe_pmd_mkwrite(pmde, vma);
 
 	flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
-	page_add_anon_rmap(new, vma, mmun_start, true);
+	if (PageAnon(new))
+		page_add_anon_rmap(new, vma, mmun_start, true);
+	else
+		page_add_file_rmap(new, true);
 	set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
 	if (vma->vm_flags & VM_LOCKED)
 		mlock_vma_page(new);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 218679138255..129088710510 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3291,7 +3291,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 				 * table protection not changing it to point
 				 * to a new page.
 				 *
-				 * See Documentation/vm/mmu_notifier.txt
+				 * See Documentation/vm/mmu_notifier.rst
 				 */
 				huge_ptep_set_wrprotect(src, addr, src_pte);
 			}
@@ -4357,7 +4357,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * No need to call mmu_notifier_invalidate_range() we are downgrading
 	 * page table protection not changing it to point to a new page.
 	 *
-	 * See Documentation/vm/mmu_notifier.txt
+	 * See Documentation/vm/mmu_notifier.rst
 	 */
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	mmu_notifier_invalidate_range_end(mm, start, end);
diff --git a/mm/internal.h b/mm/internal.h
index 62d8c34e63d5..9e3654d70289 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -53,7 +53,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 			     unsigned long addr, unsigned long end,
 			     struct zap_details *details);
 
-extern int __do_page_cache_readahead(struct address_space *mapping,
+extern unsigned int __do_page_cache_readahead(struct address_space *mapping,
 		struct file *filp, pgoff_t offset, unsigned long nr_to_read,
 		unsigned long lookahead_size);
 
@@ -168,9 +168,6 @@ extern void post_alloc_hook(struct page *page, unsigned int order,
 					gfp_t gfp_flags);
 extern int user_min_free_kbytes;
 
-extern void set_zone_contiguous(struct zone *zone);
-extern void clear_zone_contiguous(struct zone *zone);
-
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
 /*
@@ -498,6 +495,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HARDER		0x10 /* try to alloc harder */
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
+#define ALLOC_CMA		0x80 /* allow allocations from CMA areas */
 
 enum ttu_flags;
 struct tlbflush_unmap_batch;
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index bc0e68f7dc75..f185455b3406 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -792,6 +792,40 @@ DEFINE_ASAN_SET_SHADOW(f5);
 DEFINE_ASAN_SET_SHADOW(f8);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+static bool shadow_mapped(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if (pgd_none(*pgd))
+		return false;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return false;
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return false;
+
+	/*
+	 * We can't use pud_large() or pud_huge(), the first one is
+	 * arch-specific, the last one depends on HUGETLB_PAGE.  So let's abuse
+	 * pud_bad(), if pud is bad then it's bad because it's huge.
+	 */
+	if (pud_bad(*pud))
+		return true;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return false;
+
+	if (pmd_bad(*pmd))
+		return true;
+	pte = pte_offset_kernel(pmd, addr);
+	return !pte_none(*pte);
+}
+
 static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 			unsigned long action, void *data)
 {
@@ -813,6 +847,14 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 	case MEM_GOING_ONLINE: {
 		void *ret;
 
+		/*
+		 * If shadow is mapped already than it must have been mapped
+		 * during the boot. This could happen if we onlining previously
+		 * offlined memory.
+		 */
+		if (shadow_mapped(shadow_start))
+			return NOTIFY_OK;
+
 		ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
 					shadow_end, GFP_KERNEL,
 					PAGE_KERNEL, VM_NO_GUARD,
@@ -824,8 +866,26 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 		kmemleak_ignore(ret);
 		return NOTIFY_OK;
 	}
-	case MEM_OFFLINE:
-		vfree((void *)shadow_start);
+	case MEM_CANCEL_ONLINE:
+	case MEM_OFFLINE: {
+		struct vm_struct *vm;
+
+		/*
+		 * shadow_start was either mapped during boot by kasan_init()
+		 * or during memory online by __vmalloc_node_range().
+		 * In the latter case we can use vfree() to free shadow.
+		 * Non-NULL result of the find_vm_area() will tell us if
+		 * that was the second case.
+		 *
+		 * Currently it's not possible to free shadow mapped
+		 * during boot by kasan_init(). It's because the code
+		 * to do that hasn't been written yet. So we'll just
+		 * leak the memory.
+		 */
+		vm = find_vm_area((void *)shadow_start);
+		if (vm)
+			vfree((void *)shadow_start);
+	}
 	}
 
 	return NOTIFY_OK;
@@ -838,5 +898,5 @@ static int __init kasan_memhotplug_init(void)
 	return 0;
 }
 
-module_init(kasan_memhotplug_init);
+core_initcall(kasan_memhotplug_init);
 #endif
diff --git a/mm/ksm.c b/mm/ksm.c
index e3cbf9a92f3c..7d6558f3bac9 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -51,7 +51,9 @@
 #define DO_NUMA(x)	do { } while (0)
 #endif
 
-/*
+/**
+ * DOC: Overview
+ *
  * A few notes about the KSM scanning process,
  * to make it easier to understand the data structures below:
  *
@@ -67,6 +69,21 @@
  * this tree is fully assured to be working (except when pages are unmapped),
  * and therefore this tree is called the stable tree.
  *
+ * The stable tree node includes information required for reverse
+ * mapping from a KSM page to virtual addresses that map this page.
+ *
+ * In order to avoid large latencies of the rmap walks on KSM pages,
+ * KSM maintains two types of nodes in the stable tree:
+ *
+ * * the regular nodes that keep the reverse mapping structures in a
+ *   linked list
+ * * the "chains" that link nodes ("dups") that represent the same
+ *   write protected memory content, but each "dup" corresponds to a
+ *   different KSM page copy of that content
+ *
+ * Internally, the regular nodes, "dups" and "chains" are represented
+ * using the same :c:type:`struct stable_node` structure.
+ *
  * In addition to the stable tree, KSM uses a second data structure called the
  * unstable tree: this tree holds pointers to pages which have been found to
  * be "unchanged for a period of time".  The unstable tree sorts these pages
@@ -1049,7 +1066,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 		 * No need to notify as we are downgrading page table to read
 		 * only not changing it to point to a new page.
 		 *
-		 * See Documentation/vm/mmu_notifier.txt
+		 * See Documentation/vm/mmu_notifier.rst
 		 */
 		entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte);
 		/*
@@ -1145,7 +1162,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	 * No need to notify as we are replacing a read only page with another
 	 * read only page with the same content.
 	 *
-	 * See Documentation/vm/mmu_notifier.txt
+	 * See Documentation/vm/mmu_notifier.rst
 	 */
 	ptep_clear_flush(vma, addr, ptep);
 	set_pte_at_notify(mm, addr, ptep, newpte);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e074f7c637aa..1695f38630f1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2192,7 +2192,7 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 {
 	struct memcg_kmem_cache_create_work *cw;
 
-	cw = kmalloc(sizeof(*cw), GFP_NOWAIT);
+	cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
 	if (!cw)
 		return;
 
@@ -3849,7 +3849,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	if (ret)
 		goto out_put_css;
 
-	efile.file->f_op->poll(efile.file, &event->pt);
+	vfs_poll(efile.file, &event->pt);
 
 	spin_lock(&memcg->event_list_lock);
 	list_add(&event->list, &memcg->event_list);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f74826cdceea..25982467800b 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1158,7 +1158,7 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online)
 		 * nodes have to go through register_node.
 		 * TODO clean up this mess.
 		 */
-		ret = link_mem_sections(nid, start_pfn, nr_pages);
+		ret = link_mem_sections(nid, start_pfn, nr_pages, false);
 register_fail:
 		/*
 		 * If sysfs file of new node can't create, cpu on the node
diff --git a/mm/mempool.c b/mm/mempool.c
index 5c9dce34719b..b54f2c20e5e0 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -138,6 +138,28 @@ static void *remove_element(mempool_t *pool, gfp_t flags)
 }
 
 /**
+ * mempool_exit - exit a mempool initialized with mempool_init()
+ * @pool:      pointer to the memory pool which was initialized with
+ *             mempool_init().
+ *
+ * Free all reserved elements in @pool and @pool itself.  This function
+ * only sleeps if the free_fn() function sleeps.
+ *
+ * May be called on a zeroed but uninitialized mempool (i.e. allocated with
+ * kzalloc()).
+ */
+void mempool_exit(mempool_t *pool)
+{
+	while (pool->curr_nr) {
+		void *element = remove_element(pool, GFP_KERNEL);
+		pool->free(element, pool->pool_data);
+	}
+	kfree(pool->elements);
+	pool->elements = NULL;
+}
+EXPORT_SYMBOL(mempool_exit);
+
+/**
  * mempool_destroy - deallocate a memory pool
  * @pool:      pointer to the memory pool which was allocated via
  *             mempool_create().
@@ -150,15 +172,65 @@ void mempool_destroy(mempool_t *pool)
 	if (unlikely(!pool))
 		return;
 
-	while (pool->curr_nr) {
-		void *element = remove_element(pool, GFP_KERNEL);
-		pool->free(element, pool->pool_data);
-	}
-	kfree(pool->elements);
+	mempool_exit(pool);
 	kfree(pool);
 }
 EXPORT_SYMBOL(mempool_destroy);
 
+int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
+		      mempool_free_t *free_fn, void *pool_data,
+		      gfp_t gfp_mask, int node_id)
+{
+	spin_lock_init(&pool->lock);
+	pool->min_nr	= min_nr;
+	pool->pool_data = pool_data;
+	pool->alloc	= alloc_fn;
+	pool->free	= free_fn;
+	init_waitqueue_head(&pool->wait);
+
+	pool->elements = kmalloc_array_node(min_nr, sizeof(void *),
+					    gfp_mask, node_id);
+	if (!pool->elements)
+		return -ENOMEM;
+
+	/*
+	 * First pre-allocate the guaranteed number of buffers.
+	 */
+	while (pool->curr_nr < pool->min_nr) {
+		void *element;
+
+		element = pool->alloc(gfp_mask, pool->pool_data);
+		if (unlikely(!element)) {
+			mempool_exit(pool);
+			return -ENOMEM;
+		}
+		add_element(pool, element);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mempool_init_node);
+
+/**
+ * mempool_init - initialize a memory pool
+ * @min_nr:    the minimum number of elements guaranteed to be
+ *             allocated for this pool.
+ * @alloc_fn:  user-defined element-allocation function.
+ * @free_fn:   user-defined element-freeing function.
+ * @pool_data: optional private data available to the user-defined functions.
+ *
+ * Like mempool_create(), but initializes the pool in (i.e. embedded in another
+ * structure).
+ */
+int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
+		 mempool_free_t *free_fn, void *pool_data)
+{
+	return mempool_init_node(pool, min_nr, alloc_fn, free_fn,
+				 pool_data, GFP_KERNEL, NUMA_NO_NODE);
+
+}
+EXPORT_SYMBOL(mempool_init);
+
 /**
  * mempool_create - create a memory pool
  * @min_nr:    the minimum number of elements guaranteed to be
@@ -186,35 +258,17 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
 			       gfp_t gfp_mask, int node_id)
 {
 	mempool_t *pool;
+
 	pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id);
 	if (!pool)
 		return NULL;
-	pool->elements = kmalloc_array_node(min_nr, sizeof(void *),
-				      gfp_mask, node_id);
-	if (!pool->elements) {
+
+	if (mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data,
+			      gfp_mask, node_id)) {
 		kfree(pool);
 		return NULL;
 	}
-	spin_lock_init(&pool->lock);
-	pool->min_nr = min_nr;
-	pool->pool_data = pool_data;
-	init_waitqueue_head(&pool->wait);
-	pool->alloc = alloc_fn;
-	pool->free = free_fn;
 
-	/*
-	 * First pre-allocate the guaranteed number of buffers.
-	 */
-	while (pool->curr_nr < pool->min_nr) {
-		void *element;
-
-		element = pool->alloc(gfp_mask, pool->pool_data);
-		if (unlikely(!element)) {
-			mempool_destroy(pool);
-			return NULL;
-		}
-		add_element(pool, element);
-	}
 	return pool;
 }
 EXPORT_SYMBOL(mempool_create_node);
diff --git a/mm/migrate.c b/mm/migrate.c
index f65dd69e1fd1..8c0af0f7cab1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -472,7 +472,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	pslot = radix_tree_lookup_slot(&mapping->i_pages,
  					page_index(page));
 
-	expected_count += 1 + page_has_private(page);
+	expected_count += hpage_nr_pages(page) + page_has_private(page);
 	if (page_count(page) != expected_count ||
 		radix_tree_deref_slot_protected(pslot,
 					&mapping->i_pages.xa_lock) != page) {
@@ -505,7 +505,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 */
 	newpage->index = page->index;
 	newpage->mapping = page->mapping;
-	get_page(newpage);	/* add cache reference */
+	page_ref_add(newpage, hpage_nr_pages(page)); /* add cache reference */
 	if (PageSwapBacked(page)) {
 		__SetPageSwapBacked(newpage);
 		if (PageSwapCache(page)) {
@@ -524,13 +524,24 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	}
 
 	radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
+	if (PageTransHuge(page)) {
+		int i;
+		int index = page_index(page);
+
+		for (i = 1; i < HPAGE_PMD_NR; i++) {
+			pslot = radix_tree_lookup_slot(&mapping->i_pages,
+						       index + i);
+			radix_tree_replace_slot(&mapping->i_pages, pslot,
+						newpage + i);
+		}
+	}
 
 	/*
 	 * Drop cache reference from old page by unfreezing
 	 * to one less reference.
 	 * We know this isn't the last reference.
 	 */
-	page_ref_unfreeze(page, expected_count - 1);
+	page_ref_unfreeze(page, expected_count - hpage_nr_pages(page));
 
 	xa_unlock(&mapping->i_pages);
 	/* Leave irq disabled to prevent preemption while updating stats */
@@ -1622,6 +1633,9 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 		current_node = NUMA_NO_NODE;
 	}
 out_flush:
+	if (list_empty(&pagelist))
+		return err;
+
 	/* Make sure we do not overwrite the existing error */
 	err1 = do_move_pages_to_node(mm, &pagelist, current_node);
 	if (!err1)
diff --git a/mm/mmap.c b/mm/mmap.c
index 188f195883b9..d817764a9974 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -100,11 +100,20 @@ pgprot_t protection_map[16] __ro_after_init = {
 	__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
 };
 
+#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT
+static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
+{
+	return prot;
+}
+#endif
+
 pgprot_t vm_get_page_prot(unsigned long vm_flags)
 {
-	return __pgprot(pgprot_val(protection_map[vm_flags &
+	pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags &
 				(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
 			pgprot_val(arch_vm_get_page_prot(vm_flags)));
+
+	return arch_filter_pgprot(ret);
 }
 EXPORT_SYMBOL(vm_get_page_prot);
 
@@ -1315,6 +1324,35 @@ static inline int mlock_future_check(struct mm_struct *mm,
 	return 0;
 }
 
+static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
+{
+	if (S_ISREG(inode->i_mode))
+		return MAX_LFS_FILESIZE;
+
+	if (S_ISBLK(inode->i_mode))
+		return MAX_LFS_FILESIZE;
+
+	/* Special "we do even unsigned file positions" case */
+	if (file->f_mode & FMODE_UNSIGNED_OFFSET)
+		return 0;
+
+	/* Yes, random drivers might want more. But I'm tired of buggy drivers */
+	return ULONG_MAX;
+}
+
+static inline bool file_mmap_ok(struct file *file, struct inode *inode,
+				unsigned long pgoff, unsigned long len)
+{
+	u64 maxsize = file_mmap_size_max(file, inode);
+
+	if (maxsize && len > maxsize)
+		return false;
+	maxsize -= len;
+	if (pgoff > maxsize >> PAGE_SHIFT)
+		return false;
+	return true;
+}
+
 /*
  * The caller must hold down_write(&current->mm->mmap_sem).
  */
@@ -1400,6 +1438,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 		struct inode *inode = file_inode(file);
 		unsigned long flags_mask;
 
+		if (!file_mmap_ok(file, inode, pgoff, len))
+			return -EOVERFLOW;
+
 		flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
 
 		switch (flags & MAP_TYPE) {
@@ -2787,7 +2828,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	unsigned long ret = -EINVAL;
 	struct file *file;
 
-	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n",
+	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.rst.\n",
 		     current->comm, current->pid);
 
 	if (prot)
@@ -3015,6 +3056,32 @@ void exit_mmap(struct mm_struct *mm)
 	/* mm's last user has gone, and its about to be pulled down */
 	mmu_notifier_release(mm);
 
+	if (unlikely(mm_is_oom_victim(mm))) {
+		/*
+		 * Manually reap the mm to free as much memory as possible.
+		 * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard
+		 * this mm from further consideration.  Taking mm->mmap_sem for
+		 * write after setting MMF_OOM_SKIP will guarantee that the oom
+		 * reaper will not run on this mm again after mmap_sem is
+		 * dropped.
+		 *
+		 * Nothing can be holding mm->mmap_sem here and the above call
+		 * to mmu_notifier_release(mm) ensures mmu notifier callbacks in
+		 * __oom_reap_task_mm() will not block.
+		 *
+		 * This needs to be done before calling munlock_vma_pages_all(),
+		 * which clears VM_LOCKED, otherwise the oom reaper cannot
+		 * reliably test it.
+		 */
+		mutex_lock(&oom_lock);
+		__oom_reap_task_mm(mm);
+		mutex_unlock(&oom_lock);
+
+		set_bit(MMF_OOM_SKIP, &mm->flags);
+		down_write(&mm->mmap_sem);
+		up_write(&mm->mmap_sem);
+	}
+
 	if (mm->locked_vm) {
 		vma = mm->mmap;
 		while (vma) {
@@ -3036,24 +3103,6 @@ void exit_mmap(struct mm_struct *mm)
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);
-
-	if (unlikely(mm_is_oom_victim(mm))) {
-		/*
-		 * Wait for oom_reap_task() to stop working on this
-		 * mm. Because MMF_OOM_SKIP is already set before
-		 * calling down_read(), oom_reap_task() will not run
-		 * on this "mm" post up_write().
-		 *
-		 * mm_is_oom_victim() cannot be set from under us
-		 * either because victim->mm is already set to NULL
-		 * under task_lock before calling mmput and oom_mm is
-		 * set not NULL by the OOM killer only if victim->mm
-		 * is found not NULL while holding the task_lock.
-		 */
-		set_bit(MMF_OOM_SKIP, &mm->flags);
-		down_write(&mm->mmap_sem);
-		up_write(&mm->mmap_sem);
-	}
 	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, 0, -1);
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ff992fa8760a..8ba6cb88cf58 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -469,7 +469,6 @@ bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
 	return false;
 }
 
-
 #ifdef CONFIG_MMU
 /*
  * OOM Reaper kernel thread which tries to reap the memory used by the OOM
@@ -480,16 +479,54 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
 static struct task_struct *oom_reaper_list;
 static DEFINE_SPINLOCK(oom_reaper_lock);
 
-static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+void __oom_reap_task_mm(struct mm_struct *mm)
 {
-	struct mmu_gather tlb;
 	struct vm_area_struct *vma;
+
+	/*
+	 * Tell all users of get_user/copy_from_user etc... that the content
+	 * is no longer stable. No barriers really needed because unmapping
+	 * should imply barriers already and the reader would hit a page fault
+	 * if it stumbled over a reaped memory.
+	 */
+	set_bit(MMF_UNSTABLE, &mm->flags);
+
+	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
+		if (!can_madv_dontneed_vma(vma))
+			continue;
+
+		/*
+		 * Only anonymous pages have a good chance to be dropped
+		 * without additional steps which we cannot afford as we
+		 * are OOM already.
+		 *
+		 * We do not even care about fs backed pages because all
+		 * which are reclaimable have already been reclaimed and
+		 * we do not want to block exit_mmap by keeping mm ref
+		 * count elevated without a good reason.
+		 */
+		if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+			const unsigned long start = vma->vm_start;
+			const unsigned long end = vma->vm_end;
+			struct mmu_gather tlb;
+
+			tlb_gather_mmu(&tlb, mm, start, end);
+			mmu_notifier_invalidate_range_start(mm, start, end);
+			unmap_page_range(&tlb, vma, start, end, NULL);
+			mmu_notifier_invalidate_range_end(mm, start, end);
+			tlb_finish_mmu(&tlb, start, end);
+		}
+	}
+}
+
+static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+{
 	bool ret = true;
 
 	/*
 	 * We have to make sure to not race with the victim exit path
 	 * and cause premature new oom victim selection:
-	 * __oom_reap_task_mm		exit_mm
+	 * oom_reap_task_mm		exit_mm
 	 *   mmget_not_zero
 	 *				  mmput
 	 *				    atomic_dec_and_test
@@ -534,39 +571,8 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 
 	trace_start_task_reaping(tsk->pid);
 
-	/*
-	 * Tell all users of get_user/copy_from_user etc... that the content
-	 * is no longer stable. No barriers really needed because unmapping
-	 * should imply barriers already and the reader would hit a page fault
-	 * if it stumbled over a reaped memory.
-	 */
-	set_bit(MMF_UNSTABLE, &mm->flags);
-
-	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
-		if (!can_madv_dontneed_vma(vma))
-			continue;
+	__oom_reap_task_mm(mm);
 
-		/*
-		 * Only anonymous pages have a good chance to be dropped
-		 * without additional steps which we cannot afford as we
-		 * are OOM already.
-		 *
-		 * We do not even care about fs backed pages because all
-		 * which are reclaimable have already been reclaimed and
-		 * we do not want to block exit_mmap by keeping mm ref
-		 * count elevated without a good reason.
-		 */
-		if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
-			const unsigned long start = vma->vm_start;
-			const unsigned long end = vma->vm_end;
-
-			tlb_gather_mmu(&tlb, mm, start, end);
-			mmu_notifier_invalidate_range_start(mm, start, end);
-			unmap_page_range(&tlb, vma, start, end, NULL);
-			mmu_notifier_invalidate_range_end(mm, start, end);
-			tlb_finish_mmu(&tlb, start, end);
-		}
-	}
 	pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
 			task_pid_nr(tsk), tsk->comm,
 			K(get_mm_counter(mm, MM_ANONPAGES)),
@@ -587,14 +593,13 @@ static void oom_reap_task(struct task_struct *tsk)
 	struct mm_struct *mm = tsk->signal->oom_mm;
 
 	/* Retry the down_read_trylock(mmap_sem) a few times */
-	while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm))
+	while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
 		schedule_timeout_idle(HZ/10);
 
 	if (attempts <= MAX_OOM_REAP_RETRIES ||
 	    test_bit(MMF_OOM_SKIP, &mm->flags))
 		goto done;
 
-
 	pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
 		task_pid_nr(tsk), tsk->comm);
 	debug_show_all_locks();
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5c1a3279e63f..337c6afb3345 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2502,13 +2502,13 @@ void account_page_redirty(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 		current->nr_dirtied--;
 		dec_node_page_state(page, NR_DIRTIED);
 		dec_wb_stat(wb, WB_DIRTIED);
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 	}
 }
 EXPORT_SYMBOL(account_page_redirty);
@@ -2614,15 +2614,15 @@ void __cancel_dirty_page(struct page *page)
 	if (mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
 		lock_page_memcg(page);
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 
 		if (TestClearPageDirty(page))
 			account_page_cleaned(page, mapping, wb);
 
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 		unlock_page_memcg(page);
 	} else {
 		ClearPageDirty(page);
@@ -2654,7 +2654,7 @@ int clear_page_dirty_for_io(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
 		/*
 		 * Yes, Virginia, this is indeed insane.
@@ -2691,14 +2691,14 @@ int clear_page_dirty_for_io(struct page *page)
 		 * always locked coming in here, so we get the desired
 		 * exclusion.
 		 */
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 		if (TestClearPageDirty(page)) {
 			dec_lruvec_page_state(page, NR_FILE_DIRTY);
 			dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 			dec_wb_stat(wb, WB_RECLAIMABLE);
 			ret = 1;
 		}
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 		return ret;
 	}
 	return TestClearPageDirty(page);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 905db9d7962f..22320ea27489 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1743,38 +1743,16 @@ void __init page_alloc_init_late(void)
 }
 
 #ifdef CONFIG_CMA
-static void __init adjust_present_page_count(struct page *page, long count)
-{
-	struct zone *zone = page_zone(page);
-
-	/* We don't need to hold a lock since it is boot-up process */
-	zone->present_pages += count;
-}
-
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
 void __init init_cma_reserved_pageblock(struct page *page)
 {
 	unsigned i = pageblock_nr_pages;
-	unsigned long pfn = page_to_pfn(page);
 	struct page *p = page;
-	int nid = page_to_nid(page);
-
-	/*
-	 * ZONE_MOVABLE will steal present pages from other zones by
-	 * changing page links so page_zone() is changed. Before that,
-	 * we need to adjust previous zone's page count first.
-	 */
-	adjust_present_page_count(page, -pageblock_nr_pages);
 
 	do {
 		__ClearPageReserved(p);
 		set_page_count(p, 0);
-
-		/* Steal pages from other zones */
-		set_page_links(p, ZONE_MOVABLE, nid, pfn);
-	} while (++p, ++pfn, --i);
-
-	adjust_present_page_count(page, pageblock_nr_pages);
+	} while (++p, --i);
 
 	set_pageblock_migratetype(page, MIGRATE_CMA);
 
@@ -2889,7 +2867,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 		 * exists.
 		 */
 		watermark = min_wmark_pages(zone) + (1UL << order);
-		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+		if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
 			return 0;
 
 		__mod_zone_freepage_state(zone, -(1UL << order), mt);
@@ -3165,6 +3143,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 	}
 
 
+#ifdef CONFIG_CMA
+	/* If allocation can't use CMA areas don't use free CMA pages */
+	if (!(alloc_flags & ALLOC_CMA))
+		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
 	/*
 	 * Check watermarks for an order-0 allocation request. If these
 	 * are not met, then a high-order request also cannot go ahead
@@ -3191,8 +3175,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		}
 
 #ifdef CONFIG_CMA
-		if (!list_empty(&area->free_list[MIGRATE_CMA]))
+		if ((alloc_flags & ALLOC_CMA) &&
+		    !list_empty(&area->free_list[MIGRATE_CMA])) {
 			return true;
+		}
 #endif
 		if (alloc_harder &&
 			!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
@@ -3212,6 +3198,13 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 		unsigned long mark, int classzone_idx, unsigned int alloc_flags)
 {
 	long free_pages = zone_page_state(z, NR_FREE_PAGES);
+	long cma_pages = 0;
+
+#ifdef CONFIG_CMA
+	/* If allocation can't use CMA areas don't use free CMA pages */
+	if (!(alloc_flags & ALLOC_CMA))
+		cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
 
 	/*
 	 * Fast check for order-0 only. If this fails then the reserves
@@ -3220,7 +3213,7 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	 * the caller is !atomic then it'll uselessly search the free
 	 * list. That corner case is then slower but it is harmless.
 	 */
-	if (!order && free_pages > mark + z->lowmem_reserve[classzone_idx])
+	if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
 		return true;
 
 	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
@@ -3856,6 +3849,10 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
+#ifdef CONFIG_CMA
+	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+		alloc_flags |= ALLOC_CMA;
+#endif
 	return alloc_flags;
 }
 
@@ -4322,6 +4319,9 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 	if (should_fail_alloc_page(gfp_mask, order))
 		return false;
 
+	if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
+		*alloc_flags |= ALLOC_CMA;
+
 	return true;
 }
 
@@ -6204,7 +6204,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 {
 	enum zone_type j;
 	int nid = pgdat->node_id;
-	unsigned long node_end_pfn = 0;
 
 	pgdat_resize_init(pgdat);
 #ifdef CONFIG_NUMA_BALANCING
@@ -6232,13 +6231,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, freesize, memmap_pages;
 		unsigned long zone_start_pfn = zone->zone_start_pfn;
-		unsigned long movable_size = 0;
 
 		size = zone->spanned_pages;
 		realsize = freesize = zone->present_pages;
-		if (zone_end_pfn(zone) > node_end_pfn)
-			node_end_pfn = zone_end_pfn(zone);
-
 
 		/*
 		 * Adjust freesize so that it accounts for how much memory
@@ -6287,30 +6282,12 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		zone_seqlock_init(zone);
 		zone_pcp_init(zone);
 
-		/*
-		 * The size of the CMA area is unknown now so we need to
-		 * prepare the memory for the usemap at maximum.
-		 */
-		if (IS_ENABLED(CONFIG_CMA) && j == ZONE_MOVABLE &&
-			pgdat->node_spanned_pages) {
-			movable_size = node_end_pfn - pgdat->node_start_pfn;
-		}
-
-		if (!size && !movable_size)
+		if (!size)
 			continue;
 
 		set_pageblock_order();
-		if (movable_size) {
-			zone->zone_start_pfn = pgdat->node_start_pfn;
-			zone->spanned_pages = movable_size;
-			setup_usemap(pgdat, zone,
-				pgdat->node_start_pfn, movable_size);
-			init_currently_empty_zone(zone,
-				pgdat->node_start_pfn, movable_size);
-		} else {
-			setup_usemap(pgdat, zone, zone_start_pfn, size);
-			init_currently_empty_zone(zone, zone_start_pfn, size);
-		}
+		setup_usemap(pgdat, zone, zone_start_pfn, size);
+		init_currently_empty_zone(zone, zone_start_pfn, size);
 		memmap_init(size, nid, j, zone_start_pfn);
 	}
 }
@@ -7621,11 +7598,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 	unsigned long pfn, iter, found;
 
 	/*
-	 * For avoiding noise data, lru_add_drain_all() should be called
-	 * If ZONE_MOVABLE, the zone never contains unmovable pages
+	 * TODO we could make this much more efficient by not checking every
+	 * page in the range if we know all of them are in MOVABLE_ZONE and
+	 * that the movable zone guarantees that pages are migratable but
+	 * the later is not the case right now unfortunatelly. E.g. movablecore
+	 * can still lead to having bootmem allocations in zone_movable.
 	 */
-	if (zone_idx(zone) == ZONE_MOVABLE)
-		return false;
 
 	/*
 	 * CMA allocations (alloc_contig_range) really need to mark isolate
@@ -7646,7 +7624,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		page = pfn_to_page(check);
 
 		if (PageReserved(page))
-			return true;
+			goto unmovable;
 
 		/*
 		 * Hugepages are not in LRU lists, but they're movable.
@@ -7696,9 +7674,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		 * page at boot.
 		 */
 		if (found > count)
-			return true;
+			goto unmovable;
 	}
 	return false;
+unmovable:
+	WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
+	return true;
 }
 
 bool is_pageblock_removable_nolock(struct page *page)
@@ -7951,7 +7932,7 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 }
 #endif
 
-#if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * The zone indicated has a new number of managed_pages; batch sizes and percpu
  * page high values need to be recalulated.
diff --git a/mm/readahead.c b/mm/readahead.c
index 539bbb6c1fad..e273f0de3376 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -140,23 +140,23 @@ out:
 }
 
 /*
- * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates all
- * the pages first, then submits them all for I/O. This avoids the very bad
+ * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates
+ * the pages first, then submits them for I/O. This avoids the very bad
  * behaviour which would occur if page allocations are causing VM writeback.
  * We really don't want to intermingle reads and writes like that.
  *
  * Returns the number of pages requested, or the maximum amount of I/O allowed.
  */
-int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
-			pgoff_t offset, unsigned long nr_to_read,
-			unsigned long lookahead_size)
+unsigned int __do_page_cache_readahead(struct address_space *mapping,
+		struct file *filp, pgoff_t offset, unsigned long nr_to_read,
+		unsigned long lookahead_size)
 {
 	struct inode *inode = mapping->host;
 	struct page *page;
 	unsigned long end_index;	/* The last page we want to read */
 	LIST_HEAD(page_pool);
 	int page_idx;
-	int ret = 0;
+	unsigned int nr_pages = 0;
 	loff_t isize = i_size_read(inode);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
 
@@ -177,8 +177,18 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->i_pages, page_offset);
 		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page))
+		if (page && !radix_tree_exceptional_entry(page)) {
+			/*
+			 * Page already present?  Kick off the current batch of
+			 * contiguous pages before continuing with the next
+			 * batch.
+			 */
+			if (nr_pages)
+				read_pages(mapping, filp, &page_pool, nr_pages,
+						gfp_mask);
+			nr_pages = 0;
 			continue;
+		}
 
 		page = __page_cache_alloc(gfp_mask);
 		if (!page)
@@ -187,7 +197,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 		list_add(&page->lru, &page_pool);
 		if (page_idx == nr_to_read - lookahead_size)
 			SetPageReadahead(page);
-		ret++;
+		nr_pages++;
 	}
 
 	/*
@@ -195,11 +205,11 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	 * uptodate then the caller will launch readpage again, and
 	 * will then handle the error.
 	 */
-	if (ret)
-		read_pages(mapping, filp, &page_pool, ret, gfp_mask);
+	if (nr_pages)
+		read_pages(mapping, filp, &page_pool, nr_pages, gfp_mask);
 	BUG_ON(!list_empty(&page_pool));
 out:
-	return ret;
+	return nr_pages;
 }
 
 /*
@@ -223,16 +233,11 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
 	nr_to_read = min(nr_to_read, max_pages);
 	while (nr_to_read) {
-		int err;
-
 		unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE;
 
 		if (this_chunk > nr_to_read)
 			this_chunk = nr_to_read;
-		err = __do_page_cache_readahead(mapping, filp,
-						offset, this_chunk, 0);
-		if (err < 0)
-			return err;
+		__do_page_cache_readahead(mapping, filp, offset, this_chunk, 0);
 
 		offset += this_chunk;
 		nr_to_read -= this_chunk;
diff --git a/mm/rmap.c b/mm/rmap.c
index f0dd4e4565bc..6db729dc4c50 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -942,7 +942,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 		 * downgrading page table protection not changing it to point
 		 * to a new page.
 		 *
-		 * See Documentation/vm/mmu_notifier.txt
+		 * See Documentation/vm/mmu_notifier.rst
 		 */
 		if (ret)
 			(*cleaned)++;
@@ -1374,9 +1374,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		if (!pvmw.pte && (flags & TTU_MIGRATION)) {
 			VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
 
-			if (!PageAnon(page))
-				continue;
-
 			set_pmd_migration_entry(&pvmw, page);
 			continue;
 		}
@@ -1602,7 +1599,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * point at new page while a device still is using this
 			 * page.
 			 *
-			 * See Documentation/vm/mmu_notifier.txt
+			 * See Documentation/vm/mmu_notifier.rst
 			 */
 			dec_mm_counter(mm, mm_counter_file(page));
 		}
@@ -1612,7 +1609,7 @@ discard:
 		 * done above for all cases requiring it to happen under page
 		 * table lock before mmu_notifier_invalidate_range_end()
 		 *
-		 * See Documentation/vm/mmu_notifier.txt
+		 * See Documentation/vm/mmu_notifier.rst
 		 */
 		page_remove_rmap(subpage, PageHuge(page));
 		put_page(page);
diff --git a/mm/sparse.c b/mm/sparse.c
index 62eef264a7bd..73dc2fcc0eab 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -629,7 +629,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 	unsigned long pfn;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		unsigned long section_nr = pfn_to_section_nr(start_pfn);
+		unsigned long section_nr = pfn_to_section_nr(pfn);
 		struct mem_section *ms;
 
 		/*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index cc2cf04d9018..78a015fcec3b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3112,6 +3112,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	unsigned long *frontswap_map = NULL;
 	struct page *page = NULL;
 	struct inode *inode = NULL;
+	bool inced_nr_rotate_swap = false;
 
 	if (swap_flags & ~SWAP_FLAGS_VALID)
 		return -EINVAL;
@@ -3215,8 +3216,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 			cluster = per_cpu_ptr(p->percpu_cluster, cpu);
 			cluster_set_null(&cluster->index);
 		}
-	} else
+	} else {
 		atomic_inc(&nr_rotate_swap);
+		inced_nr_rotate_swap = true;
+	}
 
 	error = swap_cgroup_swapon(p->type, maxpages);
 	if (error)
@@ -3307,6 +3310,8 @@ bad_swap:
 	vfree(swap_map);
 	kvfree(cluster_info);
 	kvfree(frontswap_map);
+	if (inced_nr_rotate_swap)
+		atomic_dec(&nr_rotate_swap);
 	if (swap_file) {
 		if (inode && S_ISREG(inode->i_mode)) {
 			inode_unlock(inode);
diff --git a/mm/util.c b/mm/util.c
index 45fc3169e7b0..c2d0a7cdb189 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -621,7 +621,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed);
  * succeed and -ENOMEM implies there is not.
  *
  * We currently support three overcommit policies, which are set via the
- * vm.overcommit_memory sysctl.  See Documentation/vm/overcommit-accounting
+ * vm.overcommit_memory sysctl.  See Documentation/vm/overcommit-accounting.rst
  *
  * Strict overcommit modes added 2002 Feb 26 by Alan Cox.
  * Additional code 2002 Jul 20 by Robert Love.
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ebff729cc956..63a5f502da08 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2751,25 +2751,14 @@ static const struct seq_operations vmalloc_op = {
 	.show = s_show,
 };
 
-static int vmalloc_open(struct inode *inode, struct file *file)
+static int __init proc_vmalloc_init(void)
 {
 	if (IS_ENABLED(CONFIG_NUMA))
-		return seq_open_private(file, &vmalloc_op,
-					nr_node_ids * sizeof(unsigned int));
+		proc_create_seq_private("vmallocinfo", S_IRUSR, NULL,
+				&vmalloc_op,
+				nr_node_ids * sizeof(unsigned int), NULL);
 	else
-		return seq_open(file, &vmalloc_op);
-}
-
-static const struct file_operations proc_vmalloc_operations = {
-	.open		= vmalloc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
-
-static int __init proc_vmalloc_init(void)
-{
-	proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations);
+		proc_create_seq("vmallocinfo", S_IRUSR, NULL, &vmalloc_op);
 	return 0;
 }
 module_init(proc_vmalloc_init);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8b920ce3ae02..9270a4370d54 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -303,7 +303,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone
 /*
  * Add a shrinker callback to be called from the vm.
  */
-int register_shrinker(struct shrinker *shrinker)
+int prealloc_shrinker(struct shrinker *shrinker)
 {
 	size_t size = sizeof(*shrinker->nr_deferred);
 
@@ -313,10 +313,29 @@ int register_shrinker(struct shrinker *shrinker)
 	shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
 	if (!shrinker->nr_deferred)
 		return -ENOMEM;
+	return 0;
+}
+
+void free_prealloced_shrinker(struct shrinker *shrinker)
+{
+	kfree(shrinker->nr_deferred);
+	shrinker->nr_deferred = NULL;
+}
 
+void register_shrinker_prepared(struct shrinker *shrinker)
+{
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
 	up_write(&shrinker_rwsem);
+}
+
+int register_shrinker(struct shrinker *shrinker)
+{
+	int err = prealloc_shrinker(shrinker);
+
+	if (err)
+		return err;
+	register_shrinker_prepared(shrinker);
 	return 0;
 }
 EXPORT_SYMBOL(register_shrinker);
@@ -1399,7 +1418,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 				return ret;
 
 			mapping = page_mapping(page);
-			migrate_dirty = mapping && mapping->a_ops->migratepage;
+			migrate_dirty = !mapping || mapping->a_ops->migratepage;
 			unlock_page(page);
 			if (!migrate_dirty)
 				return ret;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 536332e988b8..75eda9c2b260 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = {
 	"nr_vmscan_immediate_reclaim",
 	"nr_dirtied",
 	"nr_written",
-	"nr_indirectly_reclaimable",
+	"", /* nr_indirectly_reclaimable */
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
@@ -1516,18 +1516,6 @@ static const struct seq_operations fragmentation_op = {
 	.show	= frag_show,
 };
 
-static int fragmentation_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &fragmentation_op);
-}
-
-static const struct file_operations buddyinfo_file_operations = {
-	.open		= fragmentation_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static const struct seq_operations pagetypeinfo_op = {
 	.start	= frag_start,
 	.next	= frag_next,
@@ -1535,18 +1523,6 @@ static const struct seq_operations pagetypeinfo_op = {
 	.show	= pagetypeinfo_show,
 };
 
-static int pagetypeinfo_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &pagetypeinfo_op);
-}
-
-static const struct file_operations pagetypeinfo_file_operations = {
-	.open		= pagetypeinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
 {
 	int zid;
@@ -1663,18 +1639,6 @@ static const struct seq_operations zoneinfo_op = {
 	.show	= zoneinfo_show,
 };
 
-static int zoneinfo_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &zoneinfo_op);
-}
-
-static const struct file_operations zoneinfo_file_operations = {
-	.open		= zoneinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 enum writeback_stat_item {
 	NR_DIRTY_THRESHOLD,
 	NR_DIRTY_BG_THRESHOLD,
@@ -1740,6 +1704,10 @@ static int vmstat_show(struct seq_file *m, void *arg)
 	unsigned long *l = arg;
 	unsigned long off = l - (unsigned long *)m->private;
 
+	/* Skip hidden vmstat items. */
+	if (*vmstat_text[off] == '\0')
+		return 0;
+
 	seq_puts(m, vmstat_text[off]);
 	seq_put_decimal_ull(m, " ", *l);
 	seq_putc(m, '\n');
@@ -1758,18 +1726,6 @@ static const struct seq_operations vmstat_op = {
 	.stop	= vmstat_stop,
 	.show	= vmstat_show,
 };
-
-static int vmstat_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &vmstat_op);
-}
-
-static const struct file_operations vmstat_file_operations = {
-	.open		= vmstat_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SMP
@@ -2016,10 +1972,10 @@ void __init init_mm_internals(void)
 	start_shepherd_timer();
 #endif
 #ifdef CONFIG_PROC_FS
-	proc_create("buddyinfo", 0444, NULL, &buddyinfo_file_operations);
-	proc_create("pagetypeinfo", 0444, NULL, &pagetypeinfo_file_operations);
-	proc_create("vmstat", 0444, NULL, &vmstat_file_operations);
-	proc_create("zoneinfo", 0444, NULL, &zoneinfo_file_operations);
+	proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
+	proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op);
+	proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
+	proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op);
 #endif
 }
 
diff --git a/mm/z3fold.c b/mm/z3fold.c
index c0bca6153b95..4b366d181f35 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -144,7 +144,8 @@ enum z3fold_page_flags {
 	PAGE_HEADLESS = 0,
 	MIDDLE_CHUNK_MAPPED,
 	NEEDS_COMPACTING,
-	PAGE_STALE
+	PAGE_STALE,
+	UNDER_RECLAIM
 };
 
 /*****************
@@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page,
 	clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
 	clear_bit(NEEDS_COMPACTING, &page->private);
 	clear_bit(PAGE_STALE, &page->private);
+	clear_bit(UNDER_RECLAIM, &page->private);
 
 	spin_lock_init(&zhdr->page_lock);
 	kref_init(&zhdr->refcount);
@@ -756,6 +758,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		atomic64_dec(&pool->pages_nr);
 		return;
 	}
+	if (test_bit(UNDER_RECLAIM, &page->private)) {
+		z3fold_page_unlock(zhdr);
+		return;
+	}
 	if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
 		z3fold_page_unlock(zhdr);
 		return;
@@ -840,6 +846,8 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 			kref_get(&zhdr->refcount);
 			list_del_init(&zhdr->buddy);
 			zhdr->cpu = -1;
+			set_bit(UNDER_RECLAIM, &page->private);
+			break;
 		}
 
 		list_del_init(&page->lru);
@@ -887,25 +895,35 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 				goto next;
 		}
 next:
-		spin_lock(&pool->lock);
 		if (test_bit(PAGE_HEADLESS, &page->private)) {
 			if (ret == 0) {
-				spin_unlock(&pool->lock);
 				free_z3fold_page(page);
 				return 0;
 			}
-		} else if (kref_put(&zhdr->refcount, release_z3fold_page)) {
-			atomic64_dec(&pool->pages_nr);
+			spin_lock(&pool->lock);
+			list_add(&page->lru, &pool->lru);
+			spin_unlock(&pool->lock);
+		} else {
+			z3fold_page_lock(zhdr);
+			clear_bit(UNDER_RECLAIM, &page->private);
+			if (kref_put(&zhdr->refcount,
+					release_z3fold_page_locked)) {
+				atomic64_dec(&pool->pages_nr);
+				return 0;
+			}
+			/*
+			 * if we are here, the page is still not completely
+			 * free. Take the global pool lock then to be able
+			 * to add it back to the lru list
+			 */
+			spin_lock(&pool->lock);
+			list_add(&page->lru, &pool->lru);
 			spin_unlock(&pool->lock);
-			return 0;
+			z3fold_page_unlock(zhdr);
 		}
 
-		/*
-		 * Add to the beginning of LRU.
-		 * Pool lock has to be kept here to ensure the page has
-		 * not already been released
-		 */
-		list_add(&page->lru, &pool->lru);
+		/* We started off locked to we need to lock the pool back */
+		spin_lock(&pool->lock);
 	}
 	spin_unlock(&pool->lock);
 	return -EAGAIN;
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index a627a5db2125..d36e8c4b7f56 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -73,35 +73,6 @@ static const struct seq_operations vlan_seq_ops = {
 	.show = vlan_seq_show,
 };
 
-static int vlan_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &vlan_seq_ops,
-			sizeof(struct seq_net_private));
-}
-
-static const struct file_operations vlan_fops = {
-	.open    = vlan_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
-/*
- *	/proc/net/vlan/<device> file and inode operations
- */
-
-static int vlandev_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, vlandev_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations vlandev_fops = {
-	.open    = vlandev_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release,
-};
-
 /*
  * Proc filesystem directory entries.
  */
@@ -148,8 +119,9 @@ int __net_init vlan_proc_init(struct net *net)
 	if (!vn->proc_vlan_dir)
 		goto err;
 
-	vn->proc_vlan_conf = proc_create(name_conf, S_IFREG | 0600,
-					 vn->proc_vlan_dir, &vlan_fops);
+	vn->proc_vlan_conf = proc_create_net(name_conf, S_IFREG | 0600,
+			vn->proc_vlan_dir, &vlan_seq_ops,
+			sizeof(struct seq_net_private));
 	if (!vn->proc_vlan_conf)
 		goto err;
 	return 0;
@@ -171,9 +143,8 @@ int vlan_proc_add_dev(struct net_device *vlandev)
 
 	if (!strcmp(vlandev->name, name_conf))
 		return -EINVAL;
-	vlan->dent =
-		proc_create_data(vlandev->name, S_IFREG | 0600,
-				 vn->proc_vlan_dir, &vlandev_fops, vlandev);
+	vlan->dent = proc_create_single_data(vlandev->name, S_IFREG | 0600,
+			vn->proc_vlan_dir, vlandev_seq_show, vlandev);
 	if (!vlan->dent)
 		return -ENOBUFS;
 	return 0;
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
index 38aa6345bdfa..b718db2085b2 100644
--- a/net/9p/trans_common.c
+++ b/net/9p/trans_common.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 
 /**
- *  p9_release_req_pages - Release pages after the transaction.
+ *  p9_release_pages - Release pages after the transaction.
  */
 void p9_release_pages(struct page **pages, int nr_pages)
 {
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 0cfba919d167..588bf88c3305 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -231,7 +231,7 @@ static void p9_conn_cancel(struct p9_conn *m, int err)
 static __poll_t
 p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
 {
-	__poll_t ret, n;
+	__poll_t ret;
 	struct p9_trans_fd *ts = NULL;
 
 	if (client && client->status == Connected)
@@ -243,19 +243,9 @@ p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
 		return EPOLLERR;
 	}
 
-	if (!ts->rd->f_op->poll)
-		ret = DEFAULT_POLLMASK;
-	else
-		ret = ts->rd->f_op->poll(ts->rd, pt);
-
-	if (ts->rd != ts->wr) {
-		if (!ts->wr->f_op->poll)
-			n = DEFAULT_POLLMASK;
-		else
-			n = ts->wr->f_op->poll(ts->wr, pt);
-		ret = (ret & ~EPOLLOUT) | (n & ~EPOLLIN);
-	}
-
+	ret = vfs_poll(ts->rd, pt);
+	if (ts->rd != ts->wr)
+		ret = (ret & ~EPOLLOUT) | (vfs_poll(ts->wr, pt) & ~EPOLLIN);
 	return ret;
 }
 
@@ -1092,8 +1082,8 @@ static struct p9_trans_module p9_fd_trans = {
 };
 
 /**
- * p9_poll_proc - poll worker thread
- * @a: thread state and arguments
+ * p9_poll_workfn - poll worker thread
+ * @work: work queue
  *
  * polls all v9fs transports for new events and queues the appropriate
  * work to the work queue
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 6d8e3031978f..3d414acb7015 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -68,8 +68,6 @@
  * @pd: Protection Domain pointer
  * @qp: Queue Pair pointer
  * @cq: Completion Queue pointer
- * @dm_mr: DMA Memory Region pointer
- * @lkey: The local access only memory region key
  * @timeout: Number of uSecs to wait for connection management events
  * @privport: Whether a privileged port may be used
  * @port: The port to use
@@ -632,7 +630,7 @@ static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma)
 }
 
 /**
- * trans_create_rdma - Transport method for creating atransport instance
+ * rdma_create_trans - Transport method for creating a transport instance
  * @client: client instance
  * @addr: IP address string
  * @args: Mount options string
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 3aa5a93ad107..4d0372263e5d 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -60,7 +60,6 @@ static atomic_t vp_pinned = ATOMIC_INIT(0);
 
 /**
  * struct virtio_chan - per-instance transport information
- * @initialized: whether the channel is initialized
  * @inuse: whether the channel is in use
  * @lock: protects multiple elements within this structure
  * @client: client instance
@@ -385,8 +384,8 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
  * @uidata: user bffer that should be ued for zero copy read
  * @uodata: user buffer that shoud be user for zero copy write
  * @inlen: read buffer size
- * @olen: write buffer size
- * @hdrlen: reader header size, This is the size of response protocol data
+ * @outlen: write buffer size
+ * @in_hdr_len: reader header size, This is the size of response protocol data
  *
  */
 static int
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index 086a4abdfa7c..0f19960390a6 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -485,7 +485,7 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev,
 
 static int xen_9pfs_front_resume(struct xenbus_device *dev)
 {
-	dev_warn(&dev->dev, "suspsend/resume unsupported\n");
+	dev_warn(&dev->dev, "suspend/resume unsupported\n");
 	return 0;
 }
 
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index d4c1021e74e1..49a16cee2aae 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -907,11 +907,6 @@ void aarp_device_down(struct net_device *dev)
 }
 
 #ifdef CONFIG_PROC_FS
-struct aarp_iter_state {
-	int bucket;
-	struct aarp_entry **table;
-};
-
 /*
  * Get the aarp entry that is in the chain described
  * by the iterator.
@@ -1033,25 +1028,12 @@ static int aarp_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations aarp_seq_ops = {
+const struct seq_operations aarp_seq_ops = {
 	.start  = aarp_seq_start,
 	.next   = aarp_seq_next,
 	.stop   = aarp_seq_stop,
 	.show   = aarp_seq_show,
 };
-
-static int aarp_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_private(file, &aarp_seq_ops,
-			sizeof(struct aarp_iter_state));
-}
-
-const struct file_operations atalk_seq_arp_fops = {
-	.open           = aarp_seq_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release	= seq_release_private,
-};
 #endif
 
 /* General module cleanup. Called from cleanup_module() in ddp.c. */
diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
index 7214aea14cb3..8006295f8bd7 100644
--- a/net/appletalk/atalk_proc.c
+++ b/net/appletalk/atalk_proc.c
@@ -210,42 +210,6 @@ static const struct seq_operations atalk_seq_socket_ops = {
 	.show   = atalk_seq_socket_show,
 };
 
-static int atalk_seq_interface_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_interface_ops);
-}
-
-static int atalk_seq_route_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_route_ops);
-}
-
-static int atalk_seq_socket_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_socket_ops);
-}
-
-static const struct file_operations atalk_seq_interface_fops = {
-	.open		= atalk_seq_interface_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations atalk_seq_route_fops = {
-	.open		= atalk_seq_route_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations atalk_seq_socket_fops = {
-	.open		= atalk_seq_socket_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static struct proc_dir_entry *atalk_proc_dir;
 
 int __init atalk_proc_init(void)
@@ -257,22 +221,23 @@ int __init atalk_proc_init(void)
 	if (!atalk_proc_dir)
 		goto out;
 
-	p = proc_create("interface", 0444, atalk_proc_dir,
-			&atalk_seq_interface_fops);
+	p = proc_create_seq("interface", 0444, atalk_proc_dir,
+			&atalk_seq_interface_ops);
 	if (!p)
 		goto out_interface;
 
-	p = proc_create("route", 0444, atalk_proc_dir,
-			&atalk_seq_route_fops);
+	p = proc_create_seq("route", 0444, atalk_proc_dir,
+			&atalk_seq_route_ops);
 	if (!p)
 		goto out_route;
 
-	p = proc_create("socket", 0444, atalk_proc_dir,
-			&atalk_seq_socket_fops);
+	p = proc_create_seq("socket", 0444, atalk_proc_dir,
+			&atalk_seq_socket_ops);
 	if (!p)
 		goto out_socket;
 
-	p = proc_create("arp", 0444, atalk_proc_dir, &atalk_seq_arp_fops);
+	p = proc_create_seq_private("arp", 0444, atalk_proc_dir, &aarp_seq_ops,
+			sizeof(struct aarp_iter_state), NULL);
 	if (!p)
 		goto out_arp;
 
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 9b6bc5abe946..55fdba05d7d9 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1869,7 +1869,7 @@ static const struct proto_ops atalk_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= atalk_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.ioctl		= atalk_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= atalk_compat_ioctl,
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index fd94bea36ee8..36b3adacc0dd 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -818,18 +818,6 @@ static const struct seq_operations br2684_seq_ops = {
 	.show = br2684_seq_show,
 };
 
-static int br2684_proc_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &br2684_seq_ops);
-}
-
-static const struct file_operations br2684_proc_ops = {
-	.open = br2684_proc_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 extern struct proc_dir_entry *atm_proc_root;	/* from proc.c */
 #endif /* CONFIG_PROC_FS */
 
@@ -837,7 +825,7 @@ static int __init br2684_init(void)
 {
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry *p;
-	p = proc_create("br2684", 0, atm_proc_root, &br2684_proc_ops);
+	p = proc_create_seq("br2684", 0, atm_proc_root, &br2684_seq_ops);
 	if (p == NULL)
 		return -ENOMEM;
 #endif
diff --git a/net/atm/clip.c b/net/atm/clip.c
index f07dbc632222..66caa48a27c2 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -863,20 +863,6 @@ static const struct seq_operations arp_seq_ops = {
 	.stop	= neigh_seq_stop,
 	.show	= clip_seq_show,
 };
-
-static int arp_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &arp_seq_ops,
-			    sizeof(struct clip_seq_state));
-}
-
-static const struct file_operations arp_seq_fops = {
-	.open		= arp_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-	.owner		= THIS_MODULE
-};
 #endif
 
 static void atm_clip_exit_noproc(void);
@@ -893,7 +879,8 @@ static int __init atm_clip_init(void)
 	{
 		struct proc_dir_entry *p;
 
-		p = proc_create("arp", 0444, atm_proc_root, &arp_seq_fops);
+		p = proc_create_net("arp", 0444, atm_proc_root, &arp_seq_ops,
+				sizeof(struct clip_seq_state));
 		if (!p) {
 			pr_err("Unable to initialize /proc/net/atm/arp\n");
 			atm_clip_exit_noproc();
diff --git a/net/atm/common.c b/net/atm/common.c
index fc78a0508ae1..1f2af59935db 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -648,16 +648,11 @@ out:
 	return error;
 }
 
-__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t vcc_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
-	struct atm_vcc *vcc;
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
-
-	vcc = ATM_SD(sock);
+	struct atm_vcc *vcc = ATM_SD(sock);
+	__poll_t mask = 0;
 
 	/* exceptional events */
 	if (sk->sk_err)
diff --git a/net/atm/common.h b/net/atm/common.h
index 5850649068bb..526796ad230f 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -17,7 +17,7 @@ int vcc_connect(struct socket *sock, int itf, short vpi, int vci);
 int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		int flags);
 int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len);
-__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t vcc_poll_mask(struct socket *sock, __poll_t events);
 int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_setsockopt(struct socket *sock, int level, int optname,
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 01d5d20a6eb1..5a95fcf6f9b6 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -41,6 +41,9 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 };
 #include <linux/module.h>
 #include <linux/init.h>
 
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
 #include "lec.h"
 #include "lec_arpc.h"
 #include "resources.h"
@@ -687,8 +690,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
 	bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc));
 	if (bytes_left != 0)
 		pr_info("copy from user failed for %d bytes\n", bytes_left);
-	if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF ||
-	    !dev_lec[ioc_data.dev_num])
+	if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF)
+		return -EINVAL;
+	ioc_data.dev_num = array_index_nospec(ioc_data.dev_num, MAX_LEC_ITF);
+	if (!dev_lec[ioc_data.dev_num])
 		return -EINVAL;
 	vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL);
 	if (!vpriv)
@@ -985,18 +990,6 @@ static const struct seq_operations lec_seq_ops = {
 	.stop = lec_seq_stop,
 	.show = lec_seq_show,
 };
-
-static int lec_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_private(file, &lec_seq_ops, sizeof(struct lec_state));
-}
-
-static const struct file_operations lec_seq_fops = {
-	.open = lec_seq_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release_private,
-};
 #endif
 
 static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
@@ -1042,7 +1035,8 @@ static int __init lane_module_init(void)
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry *p;
 
-	p = proc_create("lec", 0444, atm_proc_root, &lec_seq_fops);
+	p = proc_create_seq_private("lec", 0444, atm_proc_root, &lec_seq_ops,
+			sizeof(struct lec_state), NULL);
 	if (!p) {
 		pr_err("Unable to initialize /proc/net/atm/lec\n");
 		return -ENOMEM;
diff --git a/net/atm/proc.c b/net/atm/proc.c
index 55410c00c7e2..0b0495a41bbe 100644
--- a/net/atm/proc.c
+++ b/net/atm/proc.c
@@ -68,7 +68,6 @@ static void atm_dev_info(struct seq_file *seq, const struct atm_dev *dev)
 struct vcc_state {
 	int bucket;
 	struct sock *sk;
-	int family;
 };
 
 static inline int compare_family(struct sock *sk, int family)
@@ -106,23 +105,13 @@ out:
 	return (l < 0);
 }
 
-static inline void *vcc_walk(struct vcc_state *state, loff_t l)
+static inline void *vcc_walk(struct seq_file *seq, loff_t l)
 {
-	return __vcc_walk(&state->sk, state->family, &state->bucket, l) ?
-	       state : NULL;
-}
-
-static int __vcc_seq_open(struct inode *inode, struct file *file,
-	int family, const struct seq_operations *ops)
-{
-	struct vcc_state *state;
-
-	state = __seq_open_private(file, ops, sizeof(*state));
-	if (state == NULL)
-		return -ENOMEM;
+	struct vcc_state *state = seq->private;
+	int family = (uintptr_t)(PDE_DATA(file_inode(seq->file)));
 
-	state->family = family;
-	return 0;
+	return __vcc_walk(&state->sk, family, &state->bucket, l) ?
+	       state : NULL;
 }
 
 static void *vcc_seq_start(struct seq_file *seq, loff_t *pos)
@@ -133,7 +122,7 @@ static void *vcc_seq_start(struct seq_file *seq, loff_t *pos)
 
 	read_lock(&vcc_sklist_lock);
 	state->sk = SEQ_START_TOKEN;
-	return left ? vcc_walk(state, left) : SEQ_START_TOKEN;
+	return left ? vcc_walk(seq, left) : SEQ_START_TOKEN;
 }
 
 static void vcc_seq_stop(struct seq_file *seq, void *v)
@@ -144,9 +133,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v)
 
 static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct vcc_state *state = seq->private;
-
-	v = vcc_walk(state, 1);
+	v = vcc_walk(seq, 1);
 	*pos += !!PTR_ERR(v);
 	return v;
 }
@@ -257,18 +244,6 @@ static const struct seq_operations atm_dev_seq_ops = {
 	.show	= atm_dev_seq_show,
 };
 
-static int atm_dev_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atm_dev_seq_ops);
-}
-
-static const struct file_operations devices_seq_fops = {
-	.open		= atm_dev_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int pvc_seq_show(struct seq_file *seq, void *v)
 {
 	static char atm_pvc_banner[] =
@@ -292,18 +267,6 @@ static const struct seq_operations pvc_seq_ops = {
 	.show	= pvc_seq_show,
 };
 
-static int pvc_seq_open(struct inode *inode, struct file *file)
-{
-	return __vcc_seq_open(inode, file, PF_ATMPVC, &pvc_seq_ops);
-}
-
-static const struct file_operations pvc_seq_fops = {
-	.open		= pvc_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
-
 static int vcc_seq_show(struct seq_file *seq, void *v)
 {
 	if (v == SEQ_START_TOKEN) {
@@ -326,18 +289,6 @@ static const struct seq_operations vcc_seq_ops = {
 	.show	= vcc_seq_show,
 };
 
-static int vcc_seq_open(struct inode *inode, struct file *file)
-{
-	return __vcc_seq_open(inode, file, 0, &vcc_seq_ops);
-}
-
-static const struct file_operations vcc_seq_fops = {
-	.open		= vcc_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
-
 static int svc_seq_show(struct seq_file *seq, void *v)
 {
 	static const char atm_svc_banner[] =
@@ -361,18 +312,6 @@ static const struct seq_operations svc_seq_ops = {
 	.show	= svc_seq_show,
 };
 
-static int svc_seq_open(struct inode *inode, struct file *file)
-{
-	return __vcc_seq_open(inode, file, PF_ATMSVC, &svc_seq_ops);
-}
-
-static const struct file_operations svc_seq_fops = {
-	.open		= svc_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
-
 static ssize_t proc_dev_atm_read(struct file *file, char __user *buf,
 				 size_t count, loff_t *pos)
 {
@@ -440,58 +379,22 @@ void atm_proc_dev_deregister(struct atm_dev *dev)
 	kfree(dev->proc_name);
 }
 
-static struct atm_proc_entry {
-	char *name;
-	const struct file_operations *proc_fops;
-	struct proc_dir_entry *dirent;
-} atm_proc_ents[] = {
-	{ .name = "devices",	.proc_fops = &devices_seq_fops },
-	{ .name = "pvc",	.proc_fops = &pvc_seq_fops },
-	{ .name = "svc",	.proc_fops = &svc_seq_fops },
-	{ .name = "vc",		.proc_fops = &vcc_seq_fops },
-	{ .name = NULL,		.proc_fops = NULL }
-};
-
-static void atm_proc_dirs_remove(void)
-{
-	static struct atm_proc_entry *e;
-
-	for (e = atm_proc_ents; e->name; e++) {
-		if (e->dirent)
-			remove_proc_entry(e->name, atm_proc_root);
-	}
-	remove_proc_entry("atm", init_net.proc_net);
-}
-
 int __init atm_proc_init(void)
 {
-	static struct atm_proc_entry *e;
-	int ret;
-
 	atm_proc_root = proc_net_mkdir(&init_net, "atm", init_net.proc_net);
 	if (!atm_proc_root)
-		goto err_out;
-	for (e = atm_proc_ents; e->name; e++) {
-		struct proc_dir_entry *dirent;
-
-		dirent = proc_create(e->name, 0444,
-				     atm_proc_root, e->proc_fops);
-		if (!dirent)
-			goto err_out_remove;
-		e->dirent = dirent;
-	}
-	ret = 0;
-out:
-	return ret;
-
-err_out_remove:
-	atm_proc_dirs_remove();
-err_out:
-	ret = -ENOMEM;
-	goto out;
+		return -ENOMEM;
+	proc_create_seq("devices", 0444, atm_proc_root, &atm_dev_seq_ops);
+	proc_create_seq_private("pvc", 0444, atm_proc_root, &pvc_seq_ops,
+			sizeof(struct vcc_state), (void *)(uintptr_t)PF_ATMPVC);
+	proc_create_seq_private("svc", 0444, atm_proc_root, &svc_seq_ops,
+			sizeof(struct vcc_state), (void *)(uintptr_t)PF_ATMSVC);
+	proc_create_seq_private("vc", 0444, atm_proc_root, &vcc_seq_ops,
+			sizeof(struct vcc_state), NULL);
+	return 0;
 }
 
 void atm_proc_exit(void)
 {
-	atm_proc_dirs_remove();
+	remove_proc_subtree("atm", init_net.proc_net);
 }
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 2cb10af16afc..9f75092fe778 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -113,7 +113,7 @@ static const struct proto_ops pvc_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	pvc_getname,
-	.poll =		vcc_poll,
+	.poll_mask =	vcc_poll_mask,
 	.ioctl =	vcc_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = vcc_compat_ioctl,
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 2f91b766ac42..53f4ad7087b1 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -636,7 +636,7 @@ static const struct proto_ops svc_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	svc_accept,
 	.getname =	svc_getname,
-	.poll =		vcc_poll,
+	.poll_mask =	vcc_poll_mask,
 	.ioctl =	svc_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl =	svc_compat_ioctl,
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 2b41366fcad2..d1d2442ce573 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1924,19 +1924,6 @@ static const struct seq_operations ax25_info_seqops = {
 	.stop = ax25_info_stop,
 	.show = ax25_info_show,
 };
-
-static int ax25_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &ax25_info_seqops);
-}
-
-static const struct file_operations ax25_info_fops = {
-	.open = ax25_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 #endif
 
 static const struct net_proto_family ax25_family_ops = {
@@ -1954,7 +1941,7 @@ static const struct proto_ops ax25_proto_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= ax25_accept,
 	.getname	= ax25_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.ioctl		= ax25_ioctl,
 	.listen		= ax25_listen,
 	.shutdown	= ax25_shutdown,
@@ -1989,10 +1976,10 @@ static int __init ax25_init(void)
 	dev_add_pack(&ax25_packet_type);
 	register_netdevice_notifier(&ax25_dev_notifier);
 
-	proc_create("ax25_route", 0444, init_net.proc_net,
-		    &ax25_route_fops);
-	proc_create("ax25", 0444, init_net.proc_net, &ax25_info_fops);
-	proc_create("ax25_calls", 0444, init_net.proc_net, &ax25_uid_fops);
+	proc_create_seq("ax25_route", 0444, init_net.proc_net, &ax25_rt_seqops);
+	proc_create_seq("ax25", 0444, init_net.proc_net, &ax25_info_seqops);
+	proc_create_seq("ax25_calls", 0444, init_net.proc_net,
+			&ax25_uid_seqops);
 out:
 	return rc;
 }
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index 525558972fd9..a0eff323af12 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -323,25 +323,12 @@ static int ax25_rt_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations ax25_rt_seqops = {
+const struct seq_operations ax25_rt_seqops = {
 	.start = ax25_rt_seq_start,
 	.next = ax25_rt_seq_next,
 	.stop = ax25_rt_seq_stop,
 	.show = ax25_rt_seq_show,
 };
-
-static int ax25_rt_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &ax25_rt_seqops);
-}
-
-const struct file_operations ax25_route_fops = {
-	.open = ax25_rt_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 #endif
 
 /*
diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c
index 4ebe91ba317a..99d02e390e43 100644
--- a/net/ax25/ax25_uid.c
+++ b/net/ax25/ax25_uid.c
@@ -181,25 +181,12 @@ static int ax25_uid_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations ax25_uid_seqops = {
+const struct seq_operations ax25_uid_seqops = {
 	.start = ax25_uid_seq_start,
 	.next = ax25_uid_seq_next,
 	.stop = ax25_uid_seq_stop,
 	.show = ax25_uid_seq_show,
 };
-
-static int ax25_uid_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &ax25_uid_seqops);
-}
-
-const struct file_operations ax25_uid_fops = {
-	.open = ax25_uid_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 #endif
 
 /*
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index a11d3d89f012..a35f597e8c8b 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -1536,7 +1536,7 @@ out:
 
 	if (!ret && primary_if)
 		*primary_if = hard_iface;
-	else
+	else if (hard_iface)
 		batadv_hardif_put(hard_iface);
 
 	return ret;
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 0225616d5771..3986551397ca 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -862,7 +862,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
 	struct batadv_orig_node_vlan *vlan;
 	u8 *tt_change_ptr;
 
-	rcu_read_lock();
+	spin_lock_bh(&orig_node->vlan_list_lock);
 	hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) {
 		num_vlan++;
 		num_entries += atomic_read(&vlan->tt.num_entries);
@@ -900,7 +900,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
 	*tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr;
 
 out:
-	rcu_read_unlock();
+	spin_unlock_bh(&orig_node->vlan_list_lock);
 	return tvlv_len;
 }
 
@@ -931,15 +931,20 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 	struct batadv_tvlv_tt_vlan_data *tt_vlan;
 	struct batadv_softif_vlan *vlan;
 	u16 num_vlan = 0;
-	u16 num_entries = 0;
+	u16 vlan_entries = 0;
+	u16 total_entries = 0;
 	u16 tvlv_len;
 	u8 *tt_change_ptr;
 	int change_offset;
 
-	rcu_read_lock();
+	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
 	hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) {
+		vlan_entries = atomic_read(&vlan->tt.num_entries);
+		if (vlan_entries < 1)
+			continue;
+
 		num_vlan++;
-		num_entries += atomic_read(&vlan->tt.num_entries);
+		total_entries += vlan_entries;
 	}
 
 	change_offset = sizeof(**tt_data);
@@ -947,7 +952,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 
 	/* if tt_len is negative, allocate the space needed by the full table */
 	if (*tt_len < 0)
-		*tt_len = batadv_tt_len(num_entries);
+		*tt_len = batadv_tt_len(total_entries);
 
 	tvlv_len = *tt_len;
 	tvlv_len += change_offset;
@@ -964,6 +969,10 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 
 	tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1);
 	hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) {
+		vlan_entries = atomic_read(&vlan->tt.num_entries);
+		if (vlan_entries < 1)
+			continue;
+
 		tt_vlan->vid = htons(vlan->vid);
 		tt_vlan->crc = htonl(vlan->tt.crc);
 
@@ -974,7 +983,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 	*tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr;
 
 out:
-	rcu_read_unlock();
+	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
 	return tvlv_len;
 }
 
@@ -1538,6 +1547,8 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry,
  *  handled by a given originator
  * @entry: the TT global entry to check
  * @orig_node: the originator to search in the list
+ * @flags: a pointer to store TT flags for the given @entry received
+ *  from @orig_node
  *
  * find out if an orig_node is already in the list of a tt_global_entry.
  *
@@ -1545,7 +1556,8 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry,
  */
 static bool
 batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry,
-				const struct batadv_orig_node *orig_node)
+				const struct batadv_orig_node *orig_node,
+				u8 *flags)
 {
 	struct batadv_tt_orig_list_entry *orig_entry;
 	bool found = false;
@@ -1553,6 +1565,10 @@ batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry,
 	orig_entry = batadv_tt_global_orig_entry_find(entry, orig_node);
 	if (orig_entry) {
 		found = true;
+
+		if (flags)
+			*flags = orig_entry->flags;
+
 		batadv_tt_orig_list_entry_put(orig_entry);
 	}
 
@@ -1731,7 +1747,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
 			if (!(common->flags & BATADV_TT_CLIENT_TEMP))
 				goto out;
 			if (batadv_tt_global_entry_has_orig(tt_global_entry,
-							    orig_node))
+							    orig_node, NULL))
 				goto out_remove;
 			batadv_tt_global_del_orig_list(tt_global_entry);
 			goto add_orig_entry;
@@ -2880,23 +2896,46 @@ unlock:
 }
 
 /**
- * batadv_tt_local_valid() - verify that given tt entry is a valid one
+ * batadv_tt_local_valid() - verify local tt entry and get flags
  * @entry_ptr: to be checked local tt entry
  * @data_ptr: not used but definition required to satisfy the callback prototype
+ * @flags: a pointer to store TT flags for this client to
+ *
+ * Checks the validity of the given local TT entry. If it is, then the provided
+ * flags pointer is updated.
  *
  * Return: true if the entry is a valid, false otherwise.
  */
-static bool batadv_tt_local_valid(const void *entry_ptr, const void *data_ptr)
+static bool batadv_tt_local_valid(const void *entry_ptr,
+				  const void *data_ptr,
+				  u8 *flags)
 {
 	const struct batadv_tt_common_entry *tt_common_entry = entry_ptr;
 
 	if (tt_common_entry->flags & BATADV_TT_CLIENT_NEW)
 		return false;
+
+	if (flags)
+		*flags = tt_common_entry->flags;
+
 	return true;
 }
 
+/**
+ * batadv_tt_global_valid() - verify global tt entry and get flags
+ * @entry_ptr: to be checked global tt entry
+ * @data_ptr: an orig_node object (may be NULL)
+ * @flags: a pointer to store TT flags for this client to
+ *
+ * Checks the validity of the given global TT entry. If it is, then the provided
+ * flags pointer is updated either with the common (summed) TT flags if data_ptr
+ * is NULL or the specific, per originator TT flags otherwise.
+ *
+ * Return: true if the entry is a valid, false otherwise.
+ */
 static bool batadv_tt_global_valid(const void *entry_ptr,
-				   const void *data_ptr)
+				   const void *data_ptr,
+				   u8 *flags)
 {
 	const struct batadv_tt_common_entry *tt_common_entry = entry_ptr;
 	const struct batadv_tt_global_entry *tt_global_entry;
@@ -2910,7 +2949,8 @@ static bool batadv_tt_global_valid(const void *entry_ptr,
 				       struct batadv_tt_global_entry,
 				       common);
 
-	return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node);
+	return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node,
+					       flags);
 }
 
 /**
@@ -2920,25 +2960,34 @@ static bool batadv_tt_global_valid(const void *entry_ptr,
  * @hash: hash table containing the tt entries
  * @tt_len: expected tvlv tt data buffer length in number of bytes
  * @tvlv_buff: pointer to the buffer to fill with the TT data
- * @valid_cb: function to filter tt change entries
+ * @valid_cb: function to filter tt change entries and to return TT flags
  * @cb_data: data passed to the filter function as argument
+ *
+ * Fills the tvlv buff with the tt entries from the specified hash. If valid_cb
+ * is not provided then this becomes a no-op.
  */
 static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv,
 				    struct batadv_hashtable *hash,
 				    void *tvlv_buff, u16 tt_len,
 				    bool (*valid_cb)(const void *,
-						     const void *),
+						     const void *,
+						     u8 *flags),
 				    void *cb_data)
 {
 	struct batadv_tt_common_entry *tt_common_entry;
 	struct batadv_tvlv_tt_change *tt_change;
 	struct hlist_head *head;
 	u16 tt_tot, tt_num_entries = 0;
+	u8 flags;
+	bool ret;
 	u32 i;
 
 	tt_tot = batadv_tt_entries(tt_len);
 	tt_change = (struct batadv_tvlv_tt_change *)tvlv_buff;
 
+	if (!valid_cb)
+		return;
+
 	rcu_read_lock();
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
@@ -2948,11 +2997,12 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv,
 			if (tt_tot == tt_num_entries)
 				break;
 
-			if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data)))
+			ret = valid_cb(tt_common_entry, cb_data, &flags);
+			if (!ret)
 				continue;
 
 			ether_addr_copy(tt_change->addr, tt_common_entry->addr);
-			tt_change->flags = tt_common_entry->flags;
+			tt_change->flags = flags;
 			tt_change->vid = htons(tt_common_entry->vid);
 			memset(tt_change->reserved, 0,
 			       sizeof(tt_change->reserved));
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 84d92a077834..510ab4f55df5 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -437,16 +437,13 @@ static inline __poll_t bt_accept_poll(struct sock *parent)
 	return 0;
 }
 
-__poll_t bt_sock_poll(struct file *file, struct socket *sock,
-			  poll_table *wait)
+__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
 	BT_DBG("sock %p, sk %p", sock, sk);
 
-	poll_wait(file, sk_sleep(sk), wait);
-
 	if (sk->sk_state == BT_LISTEN)
 		return bt_accept_poll(sk);
 
@@ -478,7 +475,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
 
 	return mask;
 }
-EXPORT_SYMBOL(bt_sock_poll);
+EXPORT_SYMBOL(bt_sock_poll_mask);
 
 int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
@@ -605,15 +602,10 @@ int bt_sock_wait_ready(struct sock *sk, unsigned long flags)
 EXPORT_SYMBOL(bt_sock_wait_ready);
 
 #ifdef CONFIG_PROC_FS
-struct bt_seq_state {
-	struct bt_sock_list *l;
-};
-
 static void *bt_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(seq->private->l->lock)
 {
-	struct bt_seq_state *s = seq->private;
-	struct bt_sock_list *l = s->l;
+	struct bt_sock_list *l = PDE_DATA(file_inode(seq->file));
 
 	read_lock(&l->lock);
 	return seq_hlist_start_head(&l->head, *pos);
@@ -621,8 +613,7 @@ static void *bt_seq_start(struct seq_file *seq, loff_t *pos)
 
 static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct bt_seq_state *s = seq->private;
-	struct bt_sock_list *l = s->l;
+	struct bt_sock_list *l = PDE_DATA(file_inode(seq->file));
 
 	return seq_hlist_next(v, &l->head, pos);
 }
@@ -630,16 +621,14 @@ static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static void bt_seq_stop(struct seq_file *seq, void *v)
 	__releases(seq->private->l->lock)
 {
-	struct bt_seq_state *s = seq->private;
-	struct bt_sock_list *l = s->l;
+	struct bt_sock_list *l = PDE_DATA(file_inode(seq->file));
 
 	read_unlock(&l->lock);
 }
 
 static int bt_seq_show(struct seq_file *seq, void *v)
 {
-	struct bt_seq_state *s = seq->private;
-	struct bt_sock_list *l = s->l;
+	struct bt_sock_list *l = PDE_DATA(file_inode(seq->file));
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq ,"sk               RefCnt Rmem   Wmem   User   Inode  Parent");
@@ -681,35 +670,13 @@ static const struct seq_operations bt_seq_ops = {
 	.show  = bt_seq_show,
 };
 
-static int bt_seq_open(struct inode *inode, struct file *file)
-{
-	struct bt_sock_list *sk_list;
-	struct bt_seq_state *s;
-
-	sk_list = PDE_DATA(inode);
-	s = __seq_open_private(file, &bt_seq_ops,
-			       sizeof(struct bt_seq_state));
-	if (!s)
-		return -ENOMEM;
-
-	s->l = sk_list;
-	return 0;
-}
-
-static const struct file_operations bt_fops = {
-	.open = bt_seq_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release_private
-};
-
 int bt_procfs_init(struct net *net, const char *name,
 		   struct bt_sock_list *sk_list,
 		   int (* seq_show)(struct seq_file *, void *))
 {
 	sk_list->custom_seq_show = seq_show;
 
-	if (!proc_create_data(name, 0, net->proc_net, &bt_fops, sk_list))
+	if (!proc_create_seq_data(name, 0, net->proc_net, &bt_seq_ops, sk_list))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index b5116fa9835e..00deacdcb51c 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/net/bluetooth/bnep/sock.c
@@ -175,7 +175,6 @@ static const struct proto_ops bnep_sock_ops = {
 	.getname	= sock_no_getname,
 	.sendmsg	= sock_no_sendmsg,
 	.recvmsg	= sock_no_recvmsg,
-	.poll		= sock_no_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c
index 426a92f02db4..eb41556002e3 100644
--- a/net/bluetooth/cmtp/capi.c
+++ b/net/bluetooth/cmtp/capi.c
@@ -521,18 +521,6 @@ static int cmtp_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int cmtp_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, cmtp_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations cmtp_proc_fops = {
-	.open		= cmtp_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 int cmtp_attach_device(struct cmtp_session *session)
 {
 	unsigned char buf[4];
@@ -571,7 +559,7 @@ int cmtp_attach_device(struct cmtp_session *session)
 	session->ctrl.send_message  = cmtp_send_message;
 
 	session->ctrl.procinfo      = cmtp_procinfo;
-	session->ctrl.proc_fops = &cmtp_proc_fops;
+	session->ctrl.proc_show     = cmtp_proc_show;
 
 	if (attach_capi_ctr(&session->ctrl) < 0) {
 		BT_ERR("Can't attach new controller");
diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c
index ce86a7bae844..e08f28fadd65 100644
--- a/net/bluetooth/cmtp/sock.c
+++ b/net/bluetooth/cmtp/sock.c
@@ -178,7 +178,6 @@ static const struct proto_ops cmtp_sock_ops = {
 	.getname	= sock_no_getname,
 	.sendmsg	= sock_no_sendmsg,
 	.recvmsg	= sock_no_recvmsg,
-	.poll		= sock_no_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 1506e1632394..d6c099861538 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1975,7 +1975,7 @@ static const struct proto_ops hci_sock_ops = {
 	.sendmsg	= hci_sock_sendmsg,
 	.recvmsg	= hci_sock_recvmsg,
 	.ioctl		= hci_sock_ioctl,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= hci_sock_setsockopt,
diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c
index 008ba439bd62..1eaac01f85de 100644
--- a/net/bluetooth/hidp/sock.c
+++ b/net/bluetooth/hidp/sock.c
@@ -208,7 +208,6 @@ static const struct proto_ops hidp_sock_ops = {
 	.getname	= sock_no_getname,
 	.sendmsg	= sock_no_sendmsg,
 	.recvmsg	= sock_no_recvmsg,
-	.poll		= sock_no_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 686bdc6b35b0..742a190034e6 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1653,7 +1653,7 @@ static const struct proto_ops l2cap_sock_ops = {
 	.getname	= l2cap_sock_getname,
 	.sendmsg	= l2cap_sock_sendmsg,
 	.recvmsg	= l2cap_sock_recvmsg,
-	.poll		= bt_sock_poll,
+	.poll_mask	= bt_sock_poll_mask,
 	.ioctl		= bt_sock_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index d606e9212291..1cf57622473a 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -1049,7 +1049,7 @@ static const struct proto_ops rfcomm_sock_ops = {
 	.setsockopt	= rfcomm_sock_setsockopt,
 	.getsockopt	= rfcomm_sock_getsockopt,
 	.ioctl		= rfcomm_sock_ioctl,
-	.poll		= bt_sock_poll,
+	.poll_mask	= bt_sock_poll_mask,
 	.socketpair	= sock_no_socketpair,
 	.mmap		= sock_no_mmap
 };
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 413b8ee49fec..d60dbc61d170 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1197,7 +1197,7 @@ static const struct proto_ops sco_sock_ops = {
 	.getname	= sco_sock_getname,
 	.sendmsg	= sco_sock_sendmsg,
 	.recvmsg	= sco_sock_recvmsg,
-	.poll		= bt_sock_poll,
+	.poll_mask	= bt_sock_poll_mask,
 	.ioctl		= bt_sock_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 82c1a6f430b3..5bb6681fa91e 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -518,8 +518,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 		return -ELOOP;
 	}
 
-	/* Device is already being bridged */
-	if (br_port_exists(dev))
+	/* Device has master upper dev */
+	if (netdev_master_upper_dev_get(dev))
 		return -EBUSY;
 
 	/* No bridging devices that dislike that (e.g. wireless) */
diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c
index 47ba98db145d..46c1fe7637ea 100644
--- a/net/bridge/netfilter/ebt_stp.c
+++ b/net/bridge/netfilter/ebt_stp.c
@@ -161,8 +161,8 @@ static int ebt_stp_mt_check(const struct xt_mtchk_param *par)
 	/* Make sure the match only receives stp frames */
 	if (!par->nft_compat &&
 	    (!ether_addr_equal(e->destmac, eth_stp_addr) ||
-	     !is_broadcast_ether_addr(e->destmsk) ||
-	     !(e->bitmask & EBT_DESTMAC)))
+	     !(e->bitmask & EBT_DESTMAC) ||
+	     !is_broadcast_ether_addr(e->destmsk)))
 		return -EINVAL;
 
 	return 0;
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 032e0fe45940..6ba639f6c51d 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1825,13 +1825,14 @@ static int compat_table_info(const struct ebt_table_info *info,
 {
 	unsigned int size = info->entries_size;
 	const void *entries = info->entries;
-	int ret;
 
 	newinfo->entries_size = size;
-
-	ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries);
-	if (ret)
-		return ret;
+	if (info->nentries) {
+		int ret = xt_compat_init_offsets(NFPROTO_BRIDGE,
+						 info->nentries);
+		if (ret)
+			return ret;
+	}
 
 	return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
 							entries, newinfo);
@@ -1953,7 +1954,8 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
 	int off, pad = 0;
 	unsigned int size_kern, match_size = mwt->match_size;
 
-	strlcpy(name, mwt->u.name, sizeof(name));
+	if (strscpy(name, mwt->u.name, sizeof(name)) < 0)
+		return -EINVAL;
 
 	if (state->buf_kern_start)
 		dst = state->buf_kern_start + state->buf_kern_offset;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index a6fb1b3bcad9..c7991867d622 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -934,15 +934,11 @@ static int caif_release(struct socket *sock)
 }
 
 /* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
-static __poll_t caif_poll(struct file *file,
-			      struct socket *sock, poll_table *wait)
+static __poll_t caif_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
-	__poll_t mask;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	__poll_t mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err)
@@ -976,7 +972,7 @@ static const struct proto_ops caif_seqpacket_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = sock_no_getname,
-	.poll = caif_poll,
+	.poll_mask = caif_poll_mask,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = sock_no_shutdown,
@@ -997,7 +993,7 @@ static const struct proto_ops caif_stream_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = sock_no_getname,
-	.poll = caif_poll,
+	.poll_mask = caif_poll_mask,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = sock_no_shutdown,
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 53ecda10b790..13e2ae6be620 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -174,7 +174,7 @@ static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow,
 		flow == CAIF_CTRLCMD_DEINIT_RSP ? "CLOSE/DEINIT" :
 		flow == CAIF_CTRLCMD_INIT_FAIL_RSP ? "OPEN_FAIL" :
 		flow == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND ?
-		 "REMOTE_SHUTDOWN" : "UKNOWN CTRL COMMAND");
+		 "REMOTE_SHUTDOWN" : "UNKNOWN CTRL COMMAND");
 
 
 
diff --git a/net/can/bcm.c b/net/can/bcm.c
index ac5e5e34fee3..97fedff3f0c4 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -239,18 +239,6 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 	seq_putc(m, '\n');
 	return 0;
 }
-
-static int bcm_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, bcm_proc_show);
-}
-
-static const struct file_operations bcm_proc_fops = {
-	.open		= bcm_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif /* CONFIG_PROC_FS */
 
 /*
@@ -1606,9 +1594,9 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 	if (net->can.bcmproc_dir) {
 		/* unique socket address as filename */
 		sprintf(bo->procname, "%lu", sock_i_ino(sk));
-		bo->bcm_proc_read = proc_create_data(bo->procname, 0644,
+		bo->bcm_proc_read = proc_create_net_single(bo->procname, 0644,
 						     net->can.bcmproc_dir,
-						     &bcm_proc_fops, sk);
+						     bcm_proc_show, sk);
 		if (!bo->bcm_proc_read) {
 			ret = -ENOMEM;
 			goto fail;
@@ -1669,7 +1657,7 @@ static const struct proto_ops bcm_ops = {
 	.socketpair    = sock_no_socketpair,
 	.accept        = sock_no_accept,
 	.getname       = sock_no_getname,
-	.poll          = datagram_poll,
+	.poll_mask     = datagram_poll_mask,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,
diff --git a/net/can/proc.c b/net/can/proc.c
index fdf704e9bb8c..70fea17bb04c 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -270,18 +270,6 @@ static int can_stats_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int can_stats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, can_stats_proc_show);
-}
-
-static const struct file_operations can_stats_proc_fops = {
-	.open		= can_stats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int can_reset_stats_proc_show(struct seq_file *m, void *v)
 {
 	struct net *net = m->private;
@@ -303,36 +291,12 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int can_reset_stats_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, can_reset_stats_proc_show);
-}
-
-static const struct file_operations can_reset_stats_proc_fops = {
-	.open		= can_reset_stats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int can_version_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "%s\n", CAN_VERSION_STRING);
 	return 0;
 }
 
-static int can_version_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, can_version_proc_show);
-}
-
-static const struct file_operations can_version_proc_fops = {
-	.open		= can_version_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx,
 					     struct net_device *dev,
 					     struct can_dev_rcv_lists *d)
@@ -373,18 +337,6 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int can_rcvlist_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, can_rcvlist_proc_show);
-}
-
-static const struct file_operations can_rcvlist_proc_fops = {
-	.open		= can_rcvlist_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static inline void can_rcvlist_proc_show_array(struct seq_file *m,
 					       struct net_device *dev,
 					       struct hlist_head *rcv_array,
@@ -440,19 +392,6 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int can_rcvlist_sff_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, can_rcvlist_sff_proc_show);
-}
-
-static const struct file_operations can_rcvlist_sff_proc_fops = {
-	.open		= can_rcvlist_sff_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-
 static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
 {
 	struct net_device *dev;
@@ -483,18 +422,6 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, can_rcvlist_eff_proc_show);
-}
-
-static const struct file_operations can_rcvlist_eff_proc_fops = {
-	.open		= can_rcvlist_eff_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /*
  * can_init_proc - create main CAN proc directory and procfs entries
  */
@@ -510,37 +437,29 @@ void can_init_proc(struct net *net)
 	}
 
 	/* own procfs entries from the AF_CAN core */
-	net->can.pde_version     = proc_create(CAN_PROC_VERSION, 0644,
-					       net->can.proc_dir,
-					       &can_version_proc_fops);
-	net->can.pde_stats       = proc_create(CAN_PROC_STATS, 0644,
-					       net->can.proc_dir,
-					       &can_stats_proc_fops);
-	net->can.pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644,
-					       net->can.proc_dir,
-					       &can_reset_stats_proc_fops);
-	net->can.pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644,
-						    net->can.proc_dir,
-						    &can_rcvlist_proc_fops,
-						    (void *)RX_ERR);
-	net->can.pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644,
-						    net->can.proc_dir,
-						    &can_rcvlist_proc_fops,
-						    (void *)RX_ALL);
-	net->can.pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644,
-						    net->can.proc_dir,
-						    &can_rcvlist_proc_fops,
-						    (void *)RX_FIL);
-	net->can.pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644,
-						    net->can.proc_dir,
-						    &can_rcvlist_proc_fops,
-						    (void *)RX_INV);
-	net->can.pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644,
-					       net->can.proc_dir,
-					       &can_rcvlist_eff_proc_fops);
-	net->can.pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644,
-					       net->can.proc_dir,
-					       &can_rcvlist_sff_proc_fops);
+	net->can.pde_version = proc_create_net_single(CAN_PROC_VERSION, 0644,
+			net->can.proc_dir, can_version_proc_show, NULL);
+	net->can.pde_stats = proc_create_net_single(CAN_PROC_STATS, 0644,
+			net->can.proc_dir, can_stats_proc_show, NULL);
+	net->can.pde_reset_stats = proc_create_net_single(CAN_PROC_RESET_STATS,
+			0644, net->can.proc_dir, can_reset_stats_proc_show,
+			NULL);
+	net->can.pde_rcvlist_err = proc_create_net_single(CAN_PROC_RCVLIST_ERR,
+			0644, net->can.proc_dir, can_rcvlist_proc_show,
+			(void *)RX_ERR);
+	net->can.pde_rcvlist_all = proc_create_net_single(CAN_PROC_RCVLIST_ALL,
+			0644, net->can.proc_dir, can_rcvlist_proc_show,
+			(void *)RX_ALL);
+	net->can.pde_rcvlist_fil = proc_create_net_single(CAN_PROC_RCVLIST_FIL,
+			0644, net->can.proc_dir, can_rcvlist_proc_show,
+			(void *)RX_FIL);
+	net->can.pde_rcvlist_inv = proc_create_net_single(CAN_PROC_RCVLIST_INV,
+			0644, net->can.proc_dir, can_rcvlist_proc_show,
+			(void *)RX_INV);
+	net->can.pde_rcvlist_eff = proc_create_net_single(CAN_PROC_RCVLIST_EFF,
+			0644, net->can.proc_dir, can_rcvlist_eff_proc_show, NULL);
+	net->can.pde_rcvlist_sff = proc_create_net_single(CAN_PROC_RCVLIST_SFF,
+			0644, net->can.proc_dir, can_rcvlist_sff_proc_show, NULL);
 }
 
 /*
diff --git a/net/can/raw.c b/net/can/raw.c
index 1051eee82581..fd7e2f49ea6a 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -843,7 +843,7 @@ static const struct proto_ops raw_ops = {
 	.socketpair    = sock_no_socketpair,
 	.accept        = sock_no_accept,
 	.getname       = raw_getname,
-	.poll          = datagram_poll,
+	.poll_mask     = datagram_poll_mask,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index fcb40c12b1f8..3b3d33ea9ed8 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2569,6 +2569,11 @@ static int try_write(struct ceph_connection *con)
 	int ret = 1;
 
 	dout("try_write start %p state %lu\n", con, con->state);
+	if (con->state != CON_STATE_PREOPEN &&
+	    con->state != CON_STATE_CONNECTING &&
+	    con->state != CON_STATE_NEGOTIATING &&
+	    con->state != CON_STATE_OPEN)
+		return 0;
 
 more:
 	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
@@ -2594,6 +2599,8 @@ more:
 	}
 
 more_kvec:
+	BUG_ON(!con->sock);
+
 	/* kvec data queued? */
 	if (con->out_kvec_left) {
 		ret = write_partial_kvec(con);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index b3dac24412d3..21ac6e3b96bb 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -209,6 +209,14 @@ static void reopen_session(struct ceph_mon_client *monc)
 	__open_session(monc);
 }
 
+static void un_backoff(struct ceph_mon_client *monc)
+{
+	monc->hunt_mult /= 2; /* reduce by 50% */
+	if (monc->hunt_mult < 1)
+		monc->hunt_mult = 1;
+	dout("%s hunt_mult now %d\n", __func__, monc->hunt_mult);
+}
+
 /*
  * Reschedule delayed work timer.
  */
@@ -963,6 +971,7 @@ static void delayed_work(struct work_struct *work)
 		if (!monc->hunting) {
 			ceph_con_keepalive(&monc->con);
 			__validate_auth(monc);
+			un_backoff(monc);
 		}
 
 		if (is_auth &&
@@ -1123,9 +1132,8 @@ static void finish_hunting(struct ceph_mon_client *monc)
 		dout("%s found mon%d\n", __func__, monc->cur_mon);
 		monc->hunting = false;
 		monc->had_a_connection = true;
-		monc->hunt_mult /= 2; /* reduce by 50% */
-		if (monc->hunt_mult < 1)
-			monc->hunt_mult = 1;
+		un_backoff(monc);
+		__schedule_delayed(monc);
 	}
 }
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index ea2a6c9fb7ce..d2667e5dddc3 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -157,10 +157,12 @@ static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data,
 #endif /* CONFIG_BLOCK */
 
 static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
-				     struct ceph_bvec_iter *bvec_pos)
+				     struct ceph_bvec_iter *bvec_pos,
+				     u32 num_bvecs)
 {
 	osd_data->type = CEPH_OSD_DATA_TYPE_BVECS;
 	osd_data->bvec_pos = *bvec_pos;
+	osd_data->num_bvecs = num_bvecs;
 }
 
 #define osd_req_op_data(oreq, whch, typ, fld)				\
@@ -237,6 +239,22 @@ void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
 EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio);
 #endif /* CONFIG_BLOCK */
 
+void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
+				      unsigned int which,
+				      struct bio_vec *bvecs, u32 num_bvecs,
+				      u32 bytes)
+{
+	struct ceph_osd_data *osd_data;
+	struct ceph_bvec_iter it = {
+		.bvecs = bvecs,
+		.iter = { .bi_size = bytes },
+	};
+
+	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
+	ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs);
+}
+EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs);
+
 void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
 					 unsigned int which,
 					 struct ceph_bvec_iter *bvec_pos)
@@ -244,7 +262,7 @@ void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
 	struct ceph_osd_data *osd_data;
 
 	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
-	ceph_osd_data_bvecs_init(osd_data, bvec_pos);
+	ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0);
 }
 EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos);
 
@@ -287,7 +305,8 @@ EXPORT_SYMBOL(osd_req_op_cls_request_data_pages);
 
 void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
 				       unsigned int which,
-				       struct bio_vec *bvecs, u32 bytes)
+				       struct bio_vec *bvecs, u32 num_bvecs,
+				       u32 bytes)
 {
 	struct ceph_osd_data *osd_data;
 	struct ceph_bvec_iter it = {
@@ -296,7 +315,7 @@ void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
 	};
 
 	osd_data = osd_req_op_data(osd_req, which, cls, request_data);
-	ceph_osd_data_bvecs_init(osd_data, &it);
+	ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs);
 	osd_req->r_ops[which].cls.indata_len += bytes;
 	osd_req->r_ops[which].indata_len += bytes;
 }
diff --git a/net/compat.c b/net/compat.c
index 5ae7437d3853..7242cce5631b 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -377,7 +377,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
 	    optname == SO_ATTACH_REUSEPORT_CBPF)
 		return do_set_attach_filter(sock, level, optname,
 					    optval, optlen);
-	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+	if (!COMPAT_USE_64BIT_TIME &&
+	    (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
 		return do_set_sock_timeout(sock, level, optname, optval, optlen);
 
 	return sock_setsockopt(sock, level, optname, optval, optlen);
@@ -448,7 +449,8 @@ static int do_get_sock_timeout(struct socket *sock, int level, int optname,
 static int compat_sock_getsockopt(struct socket *sock, int level, int optname,
 				char __user *optval, int __user *optlen)
 {
-	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+	if (!COMPAT_USE_64BIT_TIME &&
+	    (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
 		return do_get_sock_timeout(sock, level, optname, optval, optlen);
 	return sock_getsockopt(sock, level, optname, optval, optlen);
 }
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9938952c5c78..f19bf3dc2bd6 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -819,9 +819,8 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
 
 /**
  * 	datagram_poll - generic datagram poll
- *	@file: file struct
  *	@sock: socket
- *	@wait: poll table
+ *	@events to wait for
  *
  *	Datagram poll: Again totally generic. This also handles
  *	sequenced packet sockets providing the socket receive queue
@@ -831,14 +830,10 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
  *	and you use a different write policy from sock_writeable()
  *	then please supply your own write_space callback.
  */
-__poll_t datagram_poll(struct file *file, struct socket *sock,
-			   poll_table *wait)
+__poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	__poll_t mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -871,4 +866,4 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 
 	return mask;
 }
-EXPORT_SYMBOL(datagram_poll);
+EXPORT_SYMBOL(datagram_poll_mask);
diff --git a/net/core/dev.c b/net/core/dev.c
index 969462ebb296..983b277a1229 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2124,7 +2124,7 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
 		int i, j;
 
 		for (i = count, j = offset; i--; j++) {
-			if (!remove_xps_queue(dev_maps, cpu, j))
+			if (!remove_xps_queue(dev_maps, tci, j))
 				break;
 		}
 
@@ -2884,11 +2884,7 @@ void netdev_rx_csum_fault(struct net_device *dev)
 EXPORT_SYMBOL(netdev_rx_csum_fault);
 #endif
 
-/* Actually, we should eliminate this check as soon as we know, that:
- * 1. IOMMU is present and allows to map all the memory.
- * 2. No high memory really exists on this machine.
- */
-
+/* XXX: check that highmem exists at all on the given machine. */
 static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_HIGHMEM
@@ -2902,20 +2898,6 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 				return 1;
 		}
 	}
-
-	if (PCI_DMA_BUS_IS_PHYS) {
-		struct device *pdev = dev->dev.parent;
-
-		if (!pdev)
-			return 0;
-		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-			dma_addr_t addr = page_to_phys(skb_frag_page(frag));
-
-			if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask)
-				return 1;
-		}
-	}
 #endif
 	return 0;
 }
@@ -2969,7 +2951,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb,
 }
 EXPORT_SYMBOL(passthru_features_check);
 
-static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+static netdev_features_t dflt_features_check(struct sk_buff *skb,
 					     struct net_device *dev,
 					     netdev_features_t features)
 {
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index e3e6a3e2ca22..d884d8f5f0e5 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -839,7 +839,7 @@ void dev_mc_flush(struct net_device *dev)
 EXPORT_SYMBOL(dev_mc_flush);
 
 /**
- *	dev_mc_flush - Init multicast address list
+ *	dev_mc_init - Init multicast address list
  *	@dev: device
  *
  *	Init multicast address list.
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 03416e6dd5d7..ba02f0dfe85c 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1032,6 +1032,11 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
 		info_size = sizeof(info);
 		if (copy_from_user(&info, useraddr, info_size))
 			return -EFAULT;
+		/* Since malicious users may modify the original data,
+		 * we need to check whether FLOW_RSS is still requested.
+		 */
+		if (!(info.flow_type & FLOW_RSS))
+			return -EINVAL;
 	}
 
 	if (info.cmd == ETHTOOL_GRXCLSRLALL) {
diff --git a/net/core/filter.c b/net/core/filter.c
index d31aff93270d..201ff36b17a8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -481,11 +481,18 @@ do_pass:
 
 #define BPF_EMIT_JMP							\
 	do {								\
+		const s32 off_min = S16_MIN, off_max = S16_MAX;		\
+		s32 off;						\
+									\
 		if (target >= len || target < 0)			\
 			goto err;					\
-		insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0;	\
+		off = addrs ? addrs[target] - addrs[i] - 1 : 0;		\
 		/* Adjust pc relative offset for 2nd or 3rd insn. */	\
-		insn->off -= insn - tmp_insns;				\
+		off -= insn - tmp_insns;				\
+		/* Reject anything not fitting into insn->off. */	\
+		if (off < off_min || off > off_max)			\
+			goto err;					\
+		insn->off = off;					\
 	} while (0)
 
 		case BPF_JMP | BPF_JA:
@@ -3240,6 +3247,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
 	skb_dst_set(skb, (struct dst_entry *) md);
 
 	info = &md->u.tun_info;
+	memset(info, 0, sizeof(*info));
 	info->mode = IP_TUNNEL_INFO_TX;
 
 	info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7b7a14abba28..1fb43bff417d 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -55,10 +55,11 @@ static void neigh_timer_handler(struct timer_list *t);
 static void __neigh_notify(struct neighbour *n, int type, int flags,
 			   u32 pid);
 static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+				    struct net_device *dev);
 
 #ifdef CONFIG_PROC_FS
-static const struct file_operations neigh_stat_seq_fops;
+static const struct seq_operations neigh_stat_seq_ops;
 #endif
 
 /*
@@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 {
 	write_lock_bh(&tbl->lock);
 	neigh_flush_dev(tbl, dev);
-	pneigh_ifdown(tbl, dev);
-	write_unlock_bh(&tbl->lock);
+	pneigh_ifdown_and_unlock(tbl, dev);
 
 	del_timer_sync(&tbl->proxy_timer);
 	pneigh_queue_purge(&tbl->proxy_queue);
@@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
 	return -ENOENT;
 }
 
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+				    struct net_device *dev)
 {
-	struct pneigh_entry *n, **np;
+	struct pneigh_entry *n, **np, *freelist = NULL;
 	u32 h;
 
 	for (h = 0; h <= PNEIGH_HASHMASK; h++) {
@@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 		while ((n = *np) != NULL) {
 			if (!dev || n->dev == dev) {
 				*np = n->next;
-				if (tbl->pdestructor)
-					tbl->pdestructor(n);
-				if (n->dev)
-					dev_put(n->dev);
-				kfree(n);
+				n->next = freelist;
+				freelist = n;
 				continue;
 			}
 			np = &n->next;
 		}
 	}
+	write_unlock_bh(&tbl->lock);
+	while ((n = freelist)) {
+		freelist = n->next;
+		n->next = NULL;
+		if (tbl->pdestructor)
+			tbl->pdestructor(n);
+		if (n->dev)
+			dev_put(n->dev);
+		kfree(n);
+	}
 	return -ENOENT;
 }
 
@@ -1550,8 +1558,8 @@ void neigh_table_init(int index, struct neigh_table *tbl)
 		panic("cannot create neighbour cache statistics");
 
 #ifdef CONFIG_PROC_FS
-	if (!proc_create_data(tbl->id, 0, init_net.proc_net_stat,
-			      &neigh_stat_seq_fops, tbl))
+	if (!proc_create_seq_data(tbl->id, 0, init_net.proc_net_stat,
+			      &neigh_stat_seq_ops, tbl))
 		panic("cannot create neighbour proc dir entry");
 #endif
 
@@ -2323,12 +2331,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 
 	err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
 	if (!err) {
-		if (tb[NDA_IFINDEX])
+		if (tb[NDA_IFINDEX]) {
+			if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
+				return -EINVAL;
 			filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
-
-		if (tb[NDA_MASTER])
+		}
+		if (tb[NDA_MASTER]) {
+			if (nla_len(tb[NDA_MASTER]) != sizeof(u32))
+				return -EINVAL;
 			filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
-
+		}
 		if (filter_idx || filter_master_idx)
 			flags |= NLM_F_DUMP_FILTERED;
 	}
@@ -2774,7 +2786,7 @@ EXPORT_SYMBOL(neigh_seq_stop);
 
 static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	struct neigh_table *tbl = seq->private;
+	struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
 	int cpu;
 
 	if (*pos == 0)
@@ -2791,7 +2803,7 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
 
 static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct neigh_table *tbl = seq->private;
+	struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
 	int cpu;
 
 	for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
@@ -2810,7 +2822,7 @@ static void neigh_stat_seq_stop(struct seq_file *seq, void *v)
 
 static int neigh_stat_seq_show(struct seq_file *seq, void *v)
 {
-	struct neigh_table *tbl = seq->private;
+	struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
 	struct neigh_statistics *st = v;
 
 	if (v == SEQ_START_TOKEN) {
@@ -2849,25 +2861,6 @@ static const struct seq_operations neigh_stat_seq_ops = {
 	.stop	= neigh_stat_seq_stop,
 	.show	= neigh_stat_seq_show,
 };
-
-static int neigh_stat_seq_open(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &neigh_stat_seq_ops);
-
-	if (!ret) {
-		struct seq_file *sf = file->private_data;
-		sf->private = PDE_DATA(inode);
-	}
-	return ret;
-};
-
-static const struct file_operations neigh_stat_seq_fops = {
-	.open 	 = neigh_stat_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
 #endif /* CONFIG_PROC_FS */
 
 static inline size_t neigh_nlmsg_size(void)
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 9737302907b1..63881f72ef71 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -175,19 +175,6 @@ static const struct seq_operations dev_seq_ops = {
 	.show  = dev_seq_show,
 };
 
-static int dev_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &dev_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations dev_seq_fops = {
-	.open    = dev_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 static const struct seq_operations softnet_seq_ops = {
 	.start = softnet_seq_start,
 	.next  = softnet_seq_next,
@@ -195,18 +182,6 @@ static const struct seq_operations softnet_seq_ops = {
 	.show  = softnet_seq_show,
 };
 
-static int softnet_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &softnet_seq_ops);
-}
-
-static const struct file_operations softnet_seq_fops = {
-	.open    = softnet_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-};
-
 static void *ptype_get_idx(loff_t pos)
 {
 	struct packet_type *pt = NULL;
@@ -297,30 +272,18 @@ static const struct seq_operations ptype_seq_ops = {
 	.show  = ptype_seq_show,
 };
 
-static int ptype_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ptype_seq_ops,
-			sizeof(struct seq_net_private));
-}
-
-static const struct file_operations ptype_seq_fops = {
-	.open    = ptype_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
-
 static int __net_init dev_proc_net_init(struct net *net)
 {
 	int rc = -ENOMEM;
 
-	if (!proc_create("dev", 0444, net->proc_net, &dev_seq_fops))
+	if (!proc_create_net("dev", 0444, net->proc_net, &dev_seq_ops,
+			sizeof(struct seq_net_private)))
 		goto out;
-	if (!proc_create("softnet_stat", 0444, net->proc_net,
-			 &softnet_seq_fops))
+	if (!proc_create_seq("softnet_stat", 0444, net->proc_net,
+			 &softnet_seq_ops))
 		goto out_dev;
-	if (!proc_create("ptype", 0444, net->proc_net, &ptype_seq_fops))
+	if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops,
+			sizeof(struct seq_net_private)))
 		goto out_softnet;
 
 	if (wext_proc_init(net))
@@ -377,22 +340,10 @@ static const struct seq_operations dev_mc_seq_ops = {
 	.show  = dev_mc_seq_show,
 };
 
-static int dev_mc_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &dev_mc_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations dev_mc_seq_fops = {
-	.open    = dev_mc_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 static int __net_init dev_mc_net_init(struct net *net)
 {
-	if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops))
+	if (!proc_create_net("dev_mcast", 0, net->proc_net, &dev_mc_seq_ops,
+			sizeof(struct seq_net_private)))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index c476f0794132..bb7e80f4ced3 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1214,9 +1214,6 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 	cpumask_var_t mask;
 	unsigned long index;
 
-	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
-		return -ENOMEM;
-
 	index = get_netdev_queue_index(queue);
 
 	if (dev->num_tc) {
@@ -1226,6 +1223,9 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 			return -EINVAL;
 	}
 
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
 	rcu_read_lock();
 	dev_maps = rcu_dereference(dev->xps_maps);
 	if (dev_maps) {
diff --git a/net/core/sock.c b/net/core/sock.c
index 6444525f610c..2aed99a541d5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1606,7 +1606,7 @@ static void __sk_free(struct sock *sk)
 	if (likely(sk->sk_net_refcnt))
 		sock_inuse_add(sock_net(sk), -1);
 
-	if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
+	if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk)))
 		sock_diag_broadcast_destroy(sk);
 	else
 		sk_destruct(sk);
@@ -2567,12 +2567,6 @@ int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
 }
 EXPORT_SYMBOL(sock_no_getname);
 
-__poll_t sock_no_poll(struct file *file, struct socket *sock, poll_table *pt)
-{
-	return 0;
-}
-EXPORT_SYMBOL(sock_no_poll);
-
 int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
 	return -EOPNOTSUPP;
@@ -3439,22 +3433,10 @@ static const struct seq_operations proto_seq_ops = {
 	.show   = proto_seq_show,
 };
 
-static int proto_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &proto_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations proto_seq_fops = {
-	.open		= proto_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 static __net_init int proto_init_net(struct net *net)
 {
-	if (!proc_create("protocols", 0444, net->proc_net, &proto_seq_fops))
+	if (!proc_create_net("protocols", 0444, net->proc_net, &proto_seq_ops,
+			sizeof(struct seq_net_private)))
 		return -ENOMEM;
 
 	return 0;
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 92d016e87816..385f153fe031 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -126,6 +126,16 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val)
 						  DCCPF_SEQ_WMAX));
 }
 
+static void dccp_tasklet_schedule(struct sock *sk)
+{
+	struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet;
+
+	if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
+		sock_hold(sk);
+		__tasklet_schedule(t);
+	}
+}
+
 static void ccid2_hc_tx_rto_expire(struct timer_list *t)
 {
 	struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer);
@@ -166,7 +176,7 @@ static void ccid2_hc_tx_rto_expire(struct timer_list *t)
 
 	/* if we were blocked before, we may now send cwnd=1 packet */
 	if (sender_was_blocked)
-		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+		dccp_tasklet_schedule(sk);
 	/* restart backed-off timer */
 	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
 out:
@@ -706,7 +716,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 done:
 	/* check if incoming Acks allow pending packets to be sent */
 	if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
-		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+		dccp_tasklet_schedule(sk);
 	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index f91e3816806b..0ea2ee56ac1b 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -316,8 +316,7 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		 int flags, int *addr_len);
 void dccp_shutdown(struct sock *sk, int how);
 int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll(struct file *file, struct socket *sock,
-		       poll_table *wait);
+__poll_t dccp_poll_mask(struct socket *sock, __poll_t events);
 int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 void dccp_req_err(struct sock *sk, u64 seq);
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b08feb219b44..a9e478cd3787 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -984,7 +984,7 @@ static const struct proto_ops inet_dccp_ops = {
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,
 	/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
-	.poll		   = dccp_poll,
+	.poll_mask	   = dccp_poll_mask,
 	.ioctl		   = inet_ioctl,
 	/* FIXME: work on inet_listen to rename it to sock_common_listen */
 	.listen		   = inet_dccp_listen,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6344f1b18a6a..17fc4e0166ba 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1070,7 +1070,7 @@ static const struct proto_ops inet6_dccp_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet6_getname,
-	.poll		   = dccp_poll,
+	.poll_mask	   = dccp_poll_mask,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = inet_dccp_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 84cd4e3fd01b..ca21c1c76da0 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -283,9 +283,7 @@ int dccp_disconnect(struct sock *sk, int flags)
 
 	dccp_clear_xmit_timers(sk);
 	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
 	dp->dccps_hc_rx_ccid = NULL;
-	dp->dccps_hc_tx_ccid = NULL;
 
 	__skb_queue_purge(&sk->sk_receive_queue);
 	__skb_queue_purge(&sk->sk_write_queue);
@@ -314,20 +312,11 @@ int dccp_disconnect(struct sock *sk, int flags)
 
 EXPORT_SYMBOL_GPL(dccp_disconnect);
 
-/*
- *	Wait for a DCCP event.
- *
- *	Note that we don't need to lock the socket, as the upper poll layers
- *	take care of normal races (between the test and the event) and we don't
- *	go look at any of the socket buffers directly.
- */
-__poll_t dccp_poll(struct file *file, struct socket *sock,
-		       poll_table *wait)
+__poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
 {
 	__poll_t mask;
 	struct sock *sk = sock->sk;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
 	if (sk->sk_state == DCCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
@@ -369,7 +358,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
 	return mask;
 }
 
-EXPORT_SYMBOL_GPL(dccp_poll);
+EXPORT_SYMBOL_GPL(dccp_poll_mask);
 
 int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index b50a8732ff43..1501a20a94ca 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -232,6 +232,7 @@ static void dccp_write_xmitlet(unsigned long data)
 	else
 		dccp_write_xmit(sk);
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 static void dccp_write_xmit_timer(struct timer_list *t)
@@ -240,7 +241,6 @@ static void dccp_write_xmit_timer(struct timer_list *t)
 	struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
 
 	dccp_write_xmitlet((unsigned long)sk);
-	sock_put(sk);
 }
 
 void dccp_init_xmit_timers(struct sock *sk)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 32751602767f..9a686d890bfa 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1207,11 +1207,11 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer)
 }
 
 
-static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table  *wait)
+static __poll_t dn_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct dn_scp *scp = DN_SK(sk);
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = datagram_poll_mask(sock, events);
 
 	if (!skb_queue_empty(&scp->other_receive_queue))
 		mask |= EPOLLRDBAND;
@@ -2314,19 +2314,6 @@ static const struct seq_operations dn_socket_seq_ops = {
 	.stop	= dn_socket_seq_stop,
 	.show	= dn_socket_seq_show,
 };
-
-static int dn_socket_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_private(file, &dn_socket_seq_ops,
-			sizeof(struct dn_iter_state));
-}
-
-static const struct file_operations dn_socket_seq_fops = {
-	.open		= dn_socket_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
 #endif
 
 static const struct net_proto_family	dn_family_ops = {
@@ -2344,7 +2331,7 @@ static const struct proto_ops dn_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	dn_accept,
 	.getname =	dn_getname,
-	.poll =		dn_poll,
+	.poll_mask =	dn_poll_mask,
 	.ioctl =	dn_ioctl,
 	.listen =	dn_listen,
 	.shutdown =	dn_shutdown,
@@ -2383,7 +2370,9 @@ static int __init decnet_init(void)
 	dev_add_pack(&dn_dix_packet_type);
 	register_netdevice_notifier(&dn_dev_notifier);
 
-	proc_create("decnet", 0444, init_net.proc_net, &dn_socket_seq_fops);
+	proc_create_seq_private("decnet", 0444, init_net.proc_net,
+			&dn_socket_seq_ops, sizeof(struct dn_iter_state),
+			NULL);
 	dn_register_sysctl();
 out:
 	return rc;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index c03b046478c3..bfd43e8f2c06 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -1382,19 +1382,6 @@ static const struct seq_operations dn_dev_seq_ops = {
 	.stop	= dn_dev_seq_stop,
 	.show	= dn_dev_seq_show,
 };
-
-static int dn_dev_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &dn_dev_seq_ops);
-}
-
-static const struct file_operations dn_dev_seq_fops = {
-	.open	 = dn_dev_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
 #endif /* CONFIG_PROC_FS */
 
 static int addr[2];
@@ -1424,7 +1411,7 @@ void __init dn_dev_init(void)
 	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETADDR,
 			     NULL, dn_nl_dump_ifaddr, 0);
 
-	proc_create("decnet_dev", 0444, init_net.proc_net, &dn_dev_seq_fops);
+	proc_create_seq("decnet_dev", 0444, init_net.proc_net, &dn_dev_seq_ops);
 
 #ifdef CONFIG_SYSCTL
 	{
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index 13156165afa3..94b306f6d551 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -589,27 +589,13 @@ static const struct seq_operations dn_neigh_seq_ops = {
 	.stop  = neigh_seq_stop,
 	.show  = dn_neigh_seq_show,
 };
-
-static int dn_neigh_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &dn_neigh_seq_ops,
-			    sizeof(struct neigh_seq_state));
-}
-
-static const struct file_operations dn_neigh_seq_fops = {
-	.open		= dn_neigh_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 #endif
 
 void __init dn_neigh_init(void)
 {
 	neigh_table_init(NEIGH_DN_TABLE, &dn_neigh_table);
-	proc_create("decnet_neigh", 0444, init_net.proc_net,
-		    &dn_neigh_seq_fops);
+	proc_create_net("decnet_neigh", 0444, init_net.proc_net,
+			&dn_neigh_seq_ops, sizeof(struct neigh_seq_state));
 }
 
 void __exit dn_neigh_cleanup(void)
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index eca0cc6b761f..e74765024d88 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1852,20 +1852,6 @@ static const struct seq_operations dn_rt_cache_seq_ops = {
 	.stop	= dn_rt_cache_seq_stop,
 	.show	= dn_rt_cache_seq_show,
 };
-
-static int dn_rt_cache_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_private(file, &dn_rt_cache_seq_ops,
-			sizeof(struct dn_rt_cache_iter_state));
-}
-
-static const struct file_operations dn_rt_cache_seq_fops = {
-	.open	 = dn_rt_cache_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_private,
-};
-
 #endif /* CONFIG_PROC_FS */
 
 void __init dn_route_init(void)
@@ -1918,8 +1904,9 @@ void __init dn_route_init(void)
 
 	dn_dst_ops.gc_thresh = (dn_rt_hash_mask + 1);
 
-	proc_create("decnet_cache", 0444, init_net.proc_net,
-		    &dn_rt_cache_seq_fops);
+	proc_create_seq_private("decnet_cache", 0444, init_net.proc_net,
+			&dn_rt_cache_seq_ops,
+			sizeof(struct dn_rt_cache_iter_state), NULL);
 
 #ifdef CONFIG_DECNET_ROUTER
 	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETROUTE,
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 8396705deffc..40c851693f77 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -91,9 +91,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 
 			next_opt = memchr(opt, '#', end - opt) ?: end;
 			opt_len = next_opt - opt;
-			if (!opt_len) {
-				printk(KERN_WARNING
-				       "Empty option to dns_resolver key\n");
+			if (opt_len <= 0 || opt_len > 128) {
+				pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
+						    opt_len);
 				return -EINVAL;
 			}
 
@@ -127,10 +127,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 			}
 
 		bad_option_value:
-			printk(KERN_WARNING
-			       "Option '%*.*s' to dns_resolver key:"
-			       " bad/missing value\n",
-			       opt_nlen, opt_nlen, opt);
+			pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n",
+					    opt_nlen, opt_nlen, opt);
 			return -EINVAL;
 		} while (opt = next_opt + 1, opt < end);
 	}
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index adf50fbc4c13..47725250b4ca 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -258,11 +258,13 @@ static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst)
 static int dsa_port_setup(struct dsa_port *dp)
 {
 	struct dsa_switch *ds = dp->ds;
-	int err;
+	int err = 0;
 
 	memset(&dp->devlink_port, 0, sizeof(dp->devlink_port));
 
-	err = devlink_port_register(ds->devlink, &dp->devlink_port, dp->index);
+	if (dp->type != DSA_PORT_TYPE_UNUSED)
+		err = devlink_port_register(ds->devlink, &dp->devlink_port,
+					    dp->index);
 	if (err)
 		return err;
 
@@ -293,7 +295,8 @@ static int dsa_port_setup(struct dsa_port *dp)
 
 static void dsa_port_teardown(struct dsa_port *dp)
 {
-	devlink_port_unregister(&dp->devlink_port);
+	if (dp->type != DSA_PORT_TYPE_UNUSED)
+		devlink_port_unregister(&dp->devlink_port);
 
 	switch (dp->type) {
 	case DSA_PORT_TYPE_UNUSED:
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
index b8d95cb71c25..44a7e16bf3b5 100644
--- a/net/ieee802154/6lowpan/6lowpan_i.h
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -20,8 +20,8 @@ typedef unsigned __bitwise lowpan_rx_result;
 struct frag_lowpan_compare_key {
 	u16 tag;
 	u16 d_size;
-	const struct ieee802154_addr src;
-	const struct ieee802154_addr dst;
+	struct ieee802154_addr src;
+	struct ieee802154_addr dst;
 };
 
 /* Equivalent of ipv4 struct ipq
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 1790b65944b3..2cc224106b69 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -75,14 +75,14 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
-	struct frag_lowpan_compare_key key = {
-		.tag = cb->d_tag,
-		.d_size = cb->d_size,
-		.src = *src,
-		.dst = *dst,
-	};
+	struct frag_lowpan_compare_key key = {};
 	struct inet_frag_queue *q;
 
+	key.tag = cb->d_tag;
+	key.d_size = cb->d_size;
+	key.src = *src;
+	key.dst = *dst;
+
 	q = inet_frag_find(&ieee802154_lowpan->frags, &key);
 	if (!q)
 		return NULL;
@@ -372,7 +372,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 	struct lowpan_frag_queue *fq;
 	struct net *net = dev_net(skb->dev);
 	struct lowpan_802154_cb *cb = lowpan_802154_cb(skb);
-	struct ieee802154_hdr hdr;
+	struct ieee802154_hdr hdr = {};
 	int err;
 
 	if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0)
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index a60658c85a9a..a0768d2759b8 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -423,7 +423,7 @@ static const struct proto_ops ieee802154_raw_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = sock_no_getname,
-	.poll		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.ioctl		   = ieee802154_sock_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = sock_no_shutdown,
@@ -969,7 +969,7 @@ static const struct proto_ops ieee802154_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = sock_no_getname,
-	.poll		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.ioctl		   = ieee802154_sock_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = sock_no_shutdown,
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7d1ec76e7f43..13bbf8cb6a39 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
 	int total_pull;
 	u16 ifehdrln;
 
+	if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+		return NULL;
+
 	ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
 	ifehdrln = ntohs(ifehdr->metalen);
 	total_pull = skb->dev->hard_header_len + ifehdrln;
@@ -92,12 +95,43 @@ struct meta_tlvhdr {
 	__be16 len;
 };
 
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+				 const unsigned char *ifehdr_end)
+{
+	const struct meta_tlvhdr *tlv;
+	u16 tlvlen;
+
+	if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+		return false;
+
+	tlv = (const struct meta_tlvhdr *)skbdata;
+	tlvlen = ntohs(tlv->len);
+
+	/* tlv length field is inc header, check on minimum */
+	if (tlvlen < NLA_HDRLEN)
+		return false;
+
+	/* overflow by NLA_ALIGN check */
+	if (NLA_ALIGN(tlvlen) < tlvlen)
+		return false;
+
+	if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+		return false;
+
+	return true;
+}
+
 /* Caller takes care of presenting data in network order
  */
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+			  u16 *dlen, u16 *totlen)
 {
-	struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+	struct meta_tlvhdr *tlv;
+
+	if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+		return NULL;
 
+	tlv = (struct meta_tlvhdr *)skbdata;
 	*dlen = ntohs(tlv->len) - NLA_HDRLEN;
 	*attrtype = ntohs(tlv->type);
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index eaed0367e669..8a59428e63ab 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -986,7 +986,7 @@ const struct proto_ops inet_stream_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,
-	.poll		   = tcp_poll,
+	.poll_mask	   = tcp_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = inet_listen,
 	.shutdown	   = inet_shutdown,
@@ -1018,7 +1018,7 @@ const struct proto_ops inet_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = inet_getname,
-	.poll		   = udp_poll,
+	.poll_mask	   = udp_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
@@ -1039,7 +1039,7 @@ EXPORT_SYMBOL(inet_dgram_ops);
 
 /*
  * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
- * udp_poll
+ * udp_poll_mask
  */
 static const struct proto_ops inet_sockraw_ops = {
 	.family		   = PF_INET,
@@ -1050,7 +1050,7 @@ static const struct proto_ops inet_sockraw_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = inet_getname,
-	.poll		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index bf6c2d4d4fdc..e90c89ef8c08 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1418,23 +1418,12 @@ static const struct seq_operations arp_seq_ops = {
 	.show	= arp_seq_show,
 };
 
-static int arp_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &arp_seq_ops,
-			    sizeof(struct neigh_seq_state));
-}
-
-static const struct file_operations arp_seq_fops = {
-	.open           = arp_seq_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release	= seq_release_net,
-};
-
+/* ------------------------------------------------------------------------ */
 
 static int __net_init arp_net_init(struct net *net)
 {
-	if (!proc_create("arp", 0444, net->proc_net, &arp_seq_fops))
+	if (!proc_create_net("arp", 0444, net->proc_net, &arp_seq_ops,
+			sizeof(struct neigh_seq_state)))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index f05afaf3235c..e66172aaf241 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -326,10 +326,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 				 u8 tos, int oif, struct net_device *dev,
 				 int rpf, struct in_device *idev, u32 *itag)
 {
+	struct net *net = dev_net(dev);
+	struct flow_keys flkeys;
 	int ret, no_addr;
 	struct fib_result res;
 	struct flowi4 fl4;
-	struct net *net = dev_net(dev);
 	bool dev_match;
 
 	fl4.flowi4_oif = 0;
@@ -347,6 +348,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	no_addr = idev->ifa_list == NULL;
 
 	fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
+	if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) {
+		fl4.flowi4_proto = 0;
+		fl4.fl4_sport = 0;
+		fl4.fl4_dport = 0;
+	}
 
 	trace_fib_validate_source(dev, &fl4);
 
@@ -643,6 +649,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_ENCAP]		= { .type = NLA_NESTED },
 	[RTA_UID]		= { .type = NLA_U32 },
 	[RTA_MARK]		= { .type = NLA_U32 },
+	[RTA_TABLE]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 3dcffd3ce98c..99c23a0cb8ca 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2348,18 +2348,6 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int fib_triestat_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, fib_triestat_seq_show);
-}
-
-static const struct file_operations fib_triestat_fops = {
-	.open	= fib_triestat_seq_open,
-	.read	= seq_read,
-	.llseek	= seq_lseek,
-	.release = single_release_net,
-};
-
 static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos)
 {
 	struct fib_trie_iter *iter = seq->private;
@@ -2533,19 +2521,6 @@ static const struct seq_operations fib_trie_seq_ops = {
 	.show   = fib_trie_seq_show,
 };
 
-static int fib_trie_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &fib_trie_seq_ops,
-			    sizeof(struct fib_trie_iter));
-}
-
-static const struct file_operations fib_trie_fops = {
-	.open   = fib_trie_seq_open,
-	.read   = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release_net,
-};
-
 struct fib_route_iter {
 	struct seq_net_private p;
 	struct fib_table *main_tb;
@@ -2726,29 +2701,18 @@ static const struct seq_operations fib_route_seq_ops = {
 	.show   = fib_route_seq_show,
 };
 
-static int fib_route_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &fib_route_seq_ops,
-			    sizeof(struct fib_route_iter));
-}
-
-static const struct file_operations fib_route_fops = {
-	.open   = fib_route_seq_open,
-	.read   = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release_net,
-};
-
 int __net_init fib_proc_init(struct net *net)
 {
-	if (!proc_create("fib_trie", 0444, net->proc_net, &fib_trie_fops))
+	if (!proc_create_net("fib_trie", 0444, net->proc_net, &fib_trie_seq_ops,
+			sizeof(struct fib_trie_iter)))
 		goto out1;
 
-	if (!proc_create("fib_triestat", 0444, net->proc_net,
-			 &fib_triestat_fops))
+	if (!proc_create_net_single("fib_triestat", 0444, net->proc_net,
+			fib_triestat_seq_show, NULL))
 		goto out2;
 
-	if (!proc_create("route", 0444, net->proc_net, &fib_route_fops))
+	if (!proc_create_net("route", 0444, net->proc_net, &fib_route_seq_ops,
+			sizeof(struct fib_route_iter)))
 		goto out3;
 
 	return 0;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b26a81a7de42..85b617b655bc 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2829,19 +2829,6 @@ static const struct seq_operations igmp_mc_seq_ops = {
 	.show	=	igmp_mc_seq_show,
 };
 
-static int igmp_mc_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &igmp_mc_seq_ops,
-			sizeof(struct igmp_mc_iter_state));
-}
-
-static const struct file_operations igmp_mc_seq_fops = {
-	.open		=	igmp_mc_seq_open,
-	.read		=	seq_read,
-	.llseek		=	seq_lseek,
-	.release	=	seq_release_net,
-};
-
 struct igmp_mcf_iter_state {
 	struct seq_net_private p;
 	struct net_device *dev;
@@ -2975,29 +2962,17 @@ static const struct seq_operations igmp_mcf_seq_ops = {
 	.show	=	igmp_mcf_seq_show,
 };
 
-static int igmp_mcf_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &igmp_mcf_seq_ops,
-			sizeof(struct igmp_mcf_iter_state));
-}
-
-static const struct file_operations igmp_mcf_seq_fops = {
-	.open		=	igmp_mcf_seq_open,
-	.read		=	seq_read,
-	.llseek		=	seq_lseek,
-	.release	=	seq_release_net,
-};
-
 static int __net_init igmp_net_init(struct net *net)
 {
 	struct proc_dir_entry *pde;
 	int err;
 
-	pde = proc_create("igmp", 0444, net->proc_net, &igmp_mc_seq_fops);
+	pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops,
+			sizeof(struct igmp_mc_iter_state));
 	if (!pde)
 		goto out_igmp;
-	pde = proc_create("mcfilter", 0444, net->proc_net,
-			  &igmp_mcf_seq_fops);
+	pde = proc_create_net("mcfilter", 0444, net->proc_net,
+			&igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state));
 	if (!pde)
 		goto out_mcfilter;
 	err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET,
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 9c169bb2444d..f200b304f76c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -722,10 +722,12 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 		erspan_build_header(skb, ntohl(tunnel->parms.o_key),
 				    tunnel->index,
 				    truncate, true);
-	else
+	else if (tunnel->erspan_ver == 2)
 		erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key),
 				       tunnel->dir, tunnel->hwid,
 				       truncate, true);
+	else
+		goto free_skb;
 
 	tunnel->parms.o_flags &= ~TUNNEL_KEY;
 	__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN));
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4c11b810a447..d54abc097800 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1045,7 +1045,8 @@ alloc_new_skb:
 		if (copy > length)
 			copy = length;
 
-		if (!(rt->dst.dev->features&NETIF_F_SG)) {
+		if (!(rt->dst.dev->features&NETIF_F_SG) &&
+		    skb_tailroom(skb) >= copy) {
 			unsigned int off;
 
 			off = skb->len;
@@ -1109,6 +1110,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
+	rt = *rtp;
+	if (unlikely(!rt))
+		return -EFAULT;
+
 	/*
 	 * setup for corking.
 	 */
@@ -1124,9 +1129,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		cork->flags |= IPCORK_OPT;
 		cork->addr = ipc->addr;
 	}
-	rt = *rtp;
-	if (unlikely(!rt))
-		return -EFAULT;
+
 	/*
 	 * We steal reference to this route, caller should not release it
 	 */
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5ad2d8ed3a3f..57bbb060faaf 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -505,8 +505,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	int err;
 	int copied;
 
-	WARN_ON_ONCE(sk->sk_family == AF_INET6);
-
 	err = -EAGAIN;
 	skb = sock_dequeue_err_skb(sk);
 	if (!skb)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 6b0e362cc99b..38d906baf1df 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -328,7 +328,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 	if (tdev) {
 		hlen = tdev->hard_header_len + tdev->needed_headroom;
-		mtu = tdev->mtu;
+		mtu = min(tdev->mtu, IP_MAX_MTU);
 	}
 
 	dev->needed_headroom = t_hlen + hlen;
@@ -362,7 +362,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	nt = netdev_priv(dev);
 	t_hlen = nt->hlen + sizeof(struct iphdr);
 	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
+	dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
 	ip_tunnel_add(itn, nt);
 	return nt;
 
@@ -930,7 +930,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
-	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
+	int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
 
 	if (new_mtu < ETH_MIN_MTU)
 		return -EINVAL;
@@ -1107,7 +1107,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 
 	mtu = ip_tunnel_bind_dev(dev);
 	if (tb[IFLA_MTU]) {
-		unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen;
+		unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen;
 
 		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
 			    (unsigned int)(max - sizeof(struct iphdr)));
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 43f620feb1c4..bbcbcc113d19 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1282,18 +1282,6 @@ static int pnp_seq_show(struct seq_file *seq, void *v)
 			   &ic_servaddr);
 	return 0;
 }
-
-static int pnp_seq_open(struct inode *indoe, struct file *file)
-{
-	return single_open(file, pnp_seq_show, NULL);
-}
-
-static const struct file_operations pnp_seq_fops = {
-	.open		= pnp_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif /* CONFIG_PROC_FS */
 
 /*
@@ -1369,7 +1357,7 @@ static int __init ip_auto_config(void)
 	unsigned int i;
 
 #ifdef CONFIG_PROC_FS
-	proc_create("pnp", 0444, init_net.proc_net, &pnp_seq_fops);
+	proc_create_single("pnp", 0444, init_net.proc_net, pnp_seq_show);
 #endif /* CONFIG_PROC_FS */
 
 	if (!ic_enable)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 2fb4de3f7f66..37c4f885ff7b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2828,19 +2828,6 @@ static const struct seq_operations ipmr_vif_seq_ops = {
 	.show  = ipmr_vif_seq_show,
 };
 
-static int ipmr_vif_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ipmr_vif_seq_ops,
-			    sizeof(struct mr_vif_iter));
-}
-
-static const struct file_operations ipmr_vif_fops = {
-	.open    = ipmr_vif_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct net *net = seq_file_net(seq);
@@ -2900,19 +2887,6 @@ static const struct seq_operations ipmr_mfc_seq_ops = {
 	.stop  = mr_mfc_seq_stop,
 	.show  = ipmr_mfc_seq_show,
 };
-
-static int ipmr_mfc_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ipmr_mfc_seq_ops,
-			    sizeof(struct mr_mfc_iter));
-}
-
-static const struct file_operations ipmr_mfc_fops = {
-	.open    = ipmr_mfc_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
 #endif
 
 #ifdef CONFIG_IP_PIMSM_V2
@@ -2977,9 +2951,11 @@ static int __net_init ipmr_net_init(struct net *net)
 
 #ifdef CONFIG_PROC_FS
 	err = -ENOMEM;
-	if (!proc_create("ip_mr_vif", 0, net->proc_net, &ipmr_vif_fops))
+	if (!proc_create_net("ip_mr_vif", 0, net->proc_net, &ipmr_vif_seq_ops,
+			sizeof(struct mr_vif_iter)))
 		goto proc_vif_fail;
-	if (!proc_create("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_fops))
+	if (!proc_create_net("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops,
+			sizeof(struct mr_mfc_iter)))
 		goto proc_cache_fail;
 #endif
 	return 0;
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 4fe97723b53f..30221701614c 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -43,7 +43,10 @@ mr_table_alloc(struct net *net, u32 id,
 	write_pnet(&mrt->net, net);
 
 	mrt->ops = *ops;
-	rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params);
+	if (rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params)) {
+		kfree(mrt);
+		return NULL;
+	}
 	INIT_LIST_HEAD(&mrt->mfc_cache_list);
 	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 44b308d93ec2..e85f35b89c49 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -34,6 +34,7 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
 MODULE_DESCRIPTION("IPv4 packet filter");
+MODULE_ALIAS("ipt_icmp");
 
 void *ipt_alloc_initial_table(const struct xt_table *info)
 {
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index fd01f13c896a..12843c9ef142 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -89,10 +89,10 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 			return true ^ invert;
 	}
 
+	memset(&flow, 0, sizeof(flow));
 	flow.flowi4_iif = LOOPBACK_IFINDEX;
 	flow.daddr = iph->saddr;
 	flow.saddr = rpfilter_get_saddr(iph->daddr);
-	flow.flowi4_oif = 0;
 	flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
 	flow.flowi4_tos = RT_TOS(iph->tos);
 	flow.flowi4_scope = RT_SCOPE_UNIVERSE;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 05e47d777009..2ed64bca54e3 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.addr = faddr = daddr;
 
 	if (ipc.opt && ipc.opt->opt.srr) {
-		if (!daddr)
-			return -EINVAL;
+		if (!daddr) {
+			err = -EINVAL;
+			goto out_free;
+		}
 		faddr = ipc.opt->opt.faddr;
 	}
 	tos = get_rttos(&ipc, inet);
@@ -842,6 +844,7 @@ back_from_confirm:
 
 out:
 	ip_rt_put(rt);
+out_free:
 	if (free)
 		kfree(ipc.opt);
 	if (!err) {
@@ -1147,58 +1150,24 @@ static int ping_v4_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int ping_seq_open(struct inode *inode, struct file *file)
-{
-	struct ping_seq_afinfo *afinfo = PDE_DATA(inode);
-	return seq_open_net(inode, file, &afinfo->seq_ops,
-			   sizeof(struct ping_iter_state));
-}
-
-const struct file_operations ping_seq_fops = {
-	.open		= ping_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-EXPORT_SYMBOL_GPL(ping_seq_fops);
-
-static struct ping_seq_afinfo ping_v4_seq_afinfo = {
-	.name		= "icmp",
-	.family		= AF_INET,
-	.seq_fops	= &ping_seq_fops,
-	.seq_ops	= {
-		.start		= ping_v4_seq_start,
-		.show		= ping_v4_seq_show,
-		.next		= ping_seq_next,
-		.stop		= ping_seq_stop,
-	},
+static const struct seq_operations ping_v4_seq_ops = {
+	.start		= ping_v4_seq_start,
+	.show		= ping_v4_seq_show,
+	.next		= ping_seq_next,
+	.stop		= ping_seq_stop,
 };
 
-int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo)
+static int __net_init ping_v4_proc_init_net(struct net *net)
 {
-	struct proc_dir_entry *p;
-	p = proc_create_data(afinfo->name, 0444, net->proc_net,
-			     afinfo->seq_fops, afinfo);
-	if (!p)
+	if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops,
+			sizeof(struct ping_iter_state)))
 		return -ENOMEM;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ping_proc_register);
-
-void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo)
-{
-	remove_proc_entry(afinfo->name, net->proc_net);
-}
-EXPORT_SYMBOL_GPL(ping_proc_unregister);
-
-static int __net_init ping_v4_proc_init_net(struct net *net)
-{
-	return ping_proc_register(net, &ping_v4_seq_afinfo);
-}
 
 static void __net_exit ping_v4_proc_exit_net(struct net *net)
 {
-	ping_proc_unregister(net, &ping_v4_seq_afinfo);
+	remove_proc_entry("icmp", net->proc_net);
 }
 
 static struct pernet_operations ping_v4_net_ops = {
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index a058de677e94..573e43c8ed87 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -77,18 +77,6 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int sockstat_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, sockstat_seq_show);
-}
-
-static const struct file_operations sockstat_seq_fops = {
-	.open	 = sockstat_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release_net,
-};
-
 /* snmp items */
 static const struct snmp_mib snmp4_ipstats_list[] = {
 	SNMP_MIB_ITEM("InReceives", IPSTATS_MIB_INPKTS),
@@ -460,20 +448,6 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int snmp_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, snmp_seq_show);
-}
-
-static const struct file_operations snmp_seq_fops = {
-	.open	 = snmp_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release_net,
-};
-
-
-
 /*
  *	Output /proc/net/netstat
  */
@@ -507,26 +481,16 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int netstat_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, netstat_seq_show);
-}
-
-static const struct file_operations netstat_seq_fops = {
-	.open	 = netstat_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release_net,
-};
-
 static __net_init int ip_proc_init_net(struct net *net)
 {
-	if (!proc_create("sockstat", 0444, net->proc_net,
-			 &sockstat_seq_fops))
+	if (!proc_create_net_single("sockstat", 0444, net->proc_net,
+			sockstat_seq_show, NULL))
 		goto out_sockstat;
-	if (!proc_create("netstat", 0444, net->proc_net, &netstat_seq_fops))
+	if (!proc_create_net_single("netstat", 0444, net->proc_net,
+			netstat_seq_show, NULL))
 		goto out_netstat;
-	if (!proc_create("snmp", 0444, net->proc_net, &snmp_seq_fops))
+	if (!proc_create_net_single("snmp", 0444, net->proc_net, snmp_seq_show,
+			NULL))
 		goto out_snmp;
 
 	return 0;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 1b4d3355624a..abb3c9490c55 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1003,11 +1003,12 @@ struct proto raw_prot = {
 static struct sock *raw_get_first(struct seq_file *seq)
 {
 	struct sock *sk;
+	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
 	struct raw_iter_state *state = raw_seq_private(seq);
 
 	for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE;
 			++state->bucket) {
-		sk_for_each(sk, &state->h->ht[state->bucket])
+		sk_for_each(sk, &h->ht[state->bucket])
 			if (sock_net(sk) == seq_file_net(seq))
 				goto found;
 	}
@@ -1018,6 +1019,7 @@ found:
 
 static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
 {
+	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
 	struct raw_iter_state *state = raw_seq_private(seq);
 
 	do {
@@ -1027,7 +1029,7 @@ try_again:
 	} while (sk && sock_net(sk) != seq_file_net(seq));
 
 	if (!sk && ++state->bucket < RAW_HTABLE_SIZE) {
-		sk = sk_head(&state->h->ht[state->bucket]);
+		sk = sk_head(&h->ht[state->bucket]);
 		goto try_again;
 	}
 	return sk;
@@ -1045,9 +1047,9 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
 
 void *raw_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	struct raw_iter_state *state = raw_seq_private(seq);
+	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
 
-	read_lock(&state->h->lock);
+	read_lock(&h->lock);
 	return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
 }
 EXPORT_SYMBOL_GPL(raw_seq_start);
@@ -1067,9 +1069,9 @@ EXPORT_SYMBOL_GPL(raw_seq_next);
 
 void raw_seq_stop(struct seq_file *seq, void *v)
 {
-	struct raw_iter_state *state = raw_seq_private(seq);
+	struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
 
-	read_unlock(&state->h->lock);
+	read_unlock(&h->lock);
 }
 EXPORT_SYMBOL_GPL(raw_seq_stop);
 
@@ -1110,37 +1112,10 @@ static const struct seq_operations raw_seq_ops = {
 	.show  = raw_seq_show,
 };
 
-int raw_seq_open(struct inode *ino, struct file *file,
-		 struct raw_hashinfo *h, const struct seq_operations *ops)
-{
-	int err;
-	struct raw_iter_state *i;
-
-	err = seq_open_net(ino, file, ops, sizeof(struct raw_iter_state));
-	if (err < 0)
-		return err;
-
-	i = raw_seq_private((struct seq_file *)file->private_data);
-	i->h = h;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(raw_seq_open);
-
-static int raw_v4_seq_open(struct inode *inode, struct file *file)
-{
-	return raw_seq_open(inode, file, &raw_v4_hashinfo, &raw_seq_ops);
-}
-
-static const struct file_operations raw_seq_fops = {
-	.open	 = raw_v4_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
 static __net_init int raw_init_net(struct net *net)
 {
-	if (!proc_create("raw", 0444, net->proc_net, &raw_seq_fops))
+	if (!proc_create_net_data("raw", 0444, net->proc_net, &raw_seq_ops,
+			sizeof(struct raw_iter_state), &raw_v4_hashinfo))
 		return -ENOMEM;
 
 	return 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ccb25d80f679..75fb8864be67 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -360,18 +360,6 @@ static int rt_acct_proc_show(struct seq_file *m, void *v)
 	kfree(dst);
 	return 0;
 }
-
-static int rt_acct_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, rt_acct_proc_show, NULL);
-}
-
-static const struct file_operations rt_acct_proc_fops = {
-	.open		= rt_acct_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 static int __net_init ip_rt_do_proc_init(struct net *net)
@@ -389,7 +377,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
 		goto err2;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
-	pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
+	pde = proc_create_single("rt_acct", 0, net->proc_net,
+			rt_acct_proc_show);
 	if (!pde)
 		goto err3;
 #endif
@@ -709,7 +698,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 		fnhe->fnhe_gw = gw;
 		fnhe->fnhe_pmtu = pmtu;
 		fnhe->fnhe_mtu_locked = lock;
-		fnhe->fnhe_expires = expires;
+		fnhe->fnhe_expires = max(1UL, expires);
 
 		/* Exception created; mark the cached routes for the nexthop
 		 * stale, so anyone caching it rechecks if this exception
@@ -1297,6 +1286,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 {
 	struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
@@ -1310,8 +1329,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 
 	for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
 	     fnhe = rcu_dereference(fnhe->fnhe_next)) {
-		if (fnhe->fnhe_daddr == daddr)
+		if (fnhe->fnhe_daddr == daddr) {
+			if (fnhe->fnhe_expires &&
+			    time_after(jiffies, fnhe->fnhe_expires)) {
+				ip_del_fnhe(nh, daddr);
+				break;
+			}
 			return fnhe;
+		}
 	}
 	return NULL;
 }
@@ -1339,6 +1364,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 			fnhe->fnhe_gw = 0;
 			fnhe->fnhe_pmtu = 0;
 			fnhe->fnhe_expires = 0;
+			fnhe->fnhe_mtu_locked = false;
 			fnhe_flush_routes(fnhe);
 			orig = NULL;
 		}
@@ -1636,36 +1662,6 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
-{
-	struct fnhe_hash_bucket *hash;
-	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
-	u32 hval = fnhe_hashfun(daddr);
-
-	spin_lock_bh(&fnhe_lock);
-
-	hash = rcu_dereference_protected(nh->nh_exceptions,
-					 lockdep_is_held(&fnhe_lock));
-	hash += hval;
-
-	fnhe_p = &hash->chain;
-	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
-	while (fnhe) {
-		if (fnhe->fnhe_daddr == daddr) {
-			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
-				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
-			fnhe_flush_routes(fnhe);
-			kfree_rcu(fnhe, rcu);
-			break;
-		}
-		fnhe_p = &fnhe->fnhe_next;
-		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
-						 lockdep_is_held(&fnhe_lock));
-	}
-
-	spin_unlock_bh(&fnhe_lock);
-}
-
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1719,20 +1715,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe) {
+		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-			if (rth && rth->dst.expires &&
-			    time_after(jiffies, rth->dst.expires)) {
-				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
-				fnhe = NULL;
-			} else {
-				goto rt_cache;
-			}
-		}
-
-		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-
-rt_cache:
+		else
+			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -1964,8 +1950,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.saddr = saddr;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
 
-	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys))
+	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
 		flkeys = &_flkeys;
+	} else {
+		fl4.flowi4_proto = 0;
+		fl4.fl4_sport = 0;
+		fl4.fl4_dport = 0;
+	}
 
 	err = fib_lookup(net, &fl4, res, 0);
 	if (err != 0) {
@@ -2216,39 +2207,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
 		 * be set to the loopback interface as well.
 		 */
-		fi = NULL;
+		do_cache = false;
 	}
 
 	fnhe = NULL;
 	do_cache &= fi != NULL;
-	if (do_cache) {
+	if (fi) {
 		struct rtable __rcu **prth;
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
+		if (!do_cache)
+			goto add;
 		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-			rth = rcu_dereference(*prth);
-			if (rth && rth->dst.expires &&
-			    time_after(jiffies, rth->dst.expires)) {
-				ip_del_fnhe(nh, fl4->daddr);
-				fnhe = NULL;
-			} else {
-				goto rt_cache;
+		} else {
+			if (unlikely(fl4->flowi4_flags &
+				     FLOWI_FLAG_KNOWN_NH &&
+				     !(nh->nh_gw &&
+				       nh->nh_scope == RT_SCOPE_LINK))) {
+				do_cache = false;
+				goto add;
 			}
+			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
-
-		if (unlikely(fl4->flowi4_flags &
-			     FLOWI_FLAG_KNOWN_NH &&
-			     !(nh->nh_gw &&
-			       nh->nh_scope == RT_SCOPE_LINK))) {
-			do_cache = false;
-			goto add;
-		}
-		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
-
-rt_cache:
 		if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
 			return rth;
 	}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bccc4c270087..dec47e6789e7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -494,32 +494,21 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 }
 
 /*
- *	Wait for a TCP event.
- *
- *	Note that we don't need to lock the socket, as the upper poll layers
- *	take care of normal races (between the test and the event) and we don't
- *	go look at any of the socket buffers directly.
+ * Socket is not locked. We are protected from async events by poll logic and
+ * correct handling of state changes made by other threads is impossible in
+ * any case.
  */
-__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
 {
-	__poll_t mask;
 	struct sock *sk = sock->sk;
 	const struct tcp_sock *tp = tcp_sk(sk);
+	__poll_t mask = 0;
 	int state;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
-
 	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
-	/* Socket is not locked. We are protected from async events
-	 * by poll logic and correct handling of state changes
-	 * made by other threads is impossible in any case.
-	 */
-
-	mask = 0;
-
 	/*
 	 * EPOLLHUP is certainly not done right. But poll() doesn't
 	 * have a notion of HUP in just one direction, and for a
@@ -600,7 +589,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	return mask;
 }
-EXPORT_SYMBOL(tcp_poll);
+EXPORT_SYMBOL(tcp_poll_mask);
 
 int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
@@ -697,7 +686,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 {
 	return skb->len < size_goal &&
 	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
-	       skb != tcp_write_queue_head(sk) &&
+	       !tcp_rtx_queue_empty(sk) &&
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
 }
 
@@ -1204,7 +1193,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 			uarg->zerocopy = 0;
 	}
 
-	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
+	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+	    !tp->repair) {
 		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
@@ -2368,6 +2358,7 @@ void tcp_write_queue_purge(struct sock *sk)
 	INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
 	sk_mem_reclaim(sk);
 	tcp_clear_all_retrans_hints(tcp_sk(sk));
+	tcp_sk(sk)->packets_out = 0;
 }
 
 int tcp_disconnect(struct sock *sk, int flags)
@@ -2417,7 +2408,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
-	tp->packets_out = 0;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
@@ -2673,7 +2663,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_REPAIR_QUEUE:
 		if (!tp->repair)
 			err = -EPERM;
-		else if (val < TCP_QUEUES_NR)
+		else if ((unsigned int)val < TCP_QUEUES_NR)
 			tp->repair_queue = val;
 		else
 			err = -EINVAL;
@@ -2813,8 +2803,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
-		/* Read the IP->Key mappings from userspace */
-		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+		if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+			err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+		else
+			err = -EINVAL;
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 158d105e76da..58e2f479ffb4 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -806,7 +806,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
 			}
 		}
 	}
-	bbr->idle_restart = 0;
+	/* Restart after idle ends only once we process a new S/ACK for data */
+	if (rs->delivered > 0)
+		bbr->idle_restart = 0;
 }
 
 static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 367def6ddeda..e51c644484dc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3868,11 +3868,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
 	int length = (th->doff << 2) - sizeof(*th);
 	const u8 *ptr = (const u8 *)(th + 1);
 
-	/* If the TCP option is too short, we can short cut */
-	if (length < TCPOLEN_MD5SIG)
-		return NULL;
-
-	while (length > 0) {
+	/* If not enough data remaining, we can short cut */
+	while (length >= TCPOLEN_MD5SIG) {
 		int opcode = *ptr++;
 		int opsize;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f70586b50838..2c970626b398 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1961,6 +1961,7 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock);
  */
 static void *listening_get_next(struct seq_file *seq, void *cur)
 {
+	struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct inet_listen_hashbucket *ilb;
@@ -1983,7 +1984,7 @@ get_sk:
 	sk_for_each_from(sk) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
-		if (sk->sk_family == st->family)
+		if (sk->sk_family == afinfo->family)
 			return sk;
 	}
 	spin_unlock(&ilb->lock);
@@ -2020,6 +2021,7 @@ static inline bool empty_bucket(const struct tcp_iter_state *st)
  */
 static void *established_get_first(struct seq_file *seq)
 {
+	struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	void *rc = NULL;
@@ -2036,7 +2038,7 @@ static void *established_get_first(struct seq_file *seq)
 
 		spin_lock_bh(lock);
 		sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
-			if (sk->sk_family != st->family ||
+			if (sk->sk_family != afinfo->family ||
 			    !net_eq(sock_net(sk), net)) {
 				continue;
 			}
@@ -2051,6 +2053,7 @@ out:
 
 static void *established_get_next(struct seq_file *seq, void *cur)
 {
+	struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
 	struct sock *sk = cur;
 	struct hlist_nulls_node *node;
 	struct tcp_iter_state *st = seq->private;
@@ -2062,7 +2065,8 @@ static void *established_get_next(struct seq_file *seq, void *cur)
 	sk = sk_nulls_next(sk);
 
 	sk_nulls_for_each_from(sk, node) {
-		if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
+		if (sk->sk_family == afinfo->family &&
+		    net_eq(sock_net(sk), net))
 			return sk;
 	}
 
@@ -2135,7 +2139,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
 	return rc;
 }
 
-static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
+void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct tcp_iter_state *st = seq->private;
 	void *rc;
@@ -2156,8 +2160,9 @@ out:
 	st->last_pos = *pos;
 	return rc;
 }
+EXPORT_SYMBOL(tcp_seq_start);
 
-static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct tcp_iter_state *st = seq->private;
 	void *rc = NULL;
@@ -2186,8 +2191,9 @@ out:
 	st->last_pos = *pos;
 	return rc;
 }
+EXPORT_SYMBOL(tcp_seq_next);
 
-static void tcp_seq_stop(struct seq_file *seq, void *v)
+void tcp_seq_stop(struct seq_file *seq, void *v)
 {
 	struct tcp_iter_state *st = seq->private;
 
@@ -2202,47 +2208,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 		break;
 	}
 }
-
-int tcp_seq_open(struct inode *inode, struct file *file)
-{
-	struct tcp_seq_afinfo *afinfo = PDE_DATA(inode);
-	struct tcp_iter_state *s;
-	int err;
-
-	err = seq_open_net(inode, file, &afinfo->seq_ops,
-			  sizeof(struct tcp_iter_state));
-	if (err < 0)
-		return err;
-
-	s = ((struct seq_file *)file->private_data)->private;
-	s->family		= afinfo->family;
-	s->last_pos		= 0;
-	return 0;
-}
-EXPORT_SYMBOL(tcp_seq_open);
-
-int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
-{
-	int rc = 0;
-	struct proc_dir_entry *p;
-
-	afinfo->seq_ops.start		= tcp_seq_start;
-	afinfo->seq_ops.next		= tcp_seq_next;
-	afinfo->seq_ops.stop		= tcp_seq_stop;
-
-	p = proc_create_data(afinfo->name, 0444, net->proc_net,
-			     afinfo->seq_fops, afinfo);
-	if (!p)
-		rc = -ENOMEM;
-	return rc;
-}
-EXPORT_SYMBOL(tcp_proc_register);
-
-void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
-{
-	remove_proc_entry(afinfo->name, net->proc_net);
-}
-EXPORT_SYMBOL(tcp_proc_unregister);
+EXPORT_SYMBOL(tcp_seq_stop);
 
 static void get_openreq4(const struct request_sock *req,
 			 struct seq_file *f, int i)
@@ -2377,30 +2343,28 @@ out:
 	return 0;
 }
 
-static const struct file_operations tcp_afinfo_seq_fops = {
-	.open    = tcp_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net
+static const struct seq_operations tcp4_seq_ops = {
+	.show		= tcp4_seq_show,
+	.start		= tcp_seq_start,
+	.next		= tcp_seq_next,
+	.stop		= tcp_seq_stop,
 };
 
 static struct tcp_seq_afinfo tcp4_seq_afinfo = {
-	.name		= "tcp",
 	.family		= AF_INET,
-	.seq_fops	= &tcp_afinfo_seq_fops,
-	.seq_ops	= {
-		.show		= tcp4_seq_show,
-	},
 };
 
 static int __net_init tcp4_proc_init_net(struct net *net)
 {
-	return tcp_proc_register(net, &tcp4_seq_afinfo);
+	if (!proc_create_net_data("tcp", 0444, net->proc_net, &tcp4_seq_ops,
+			sizeof(struct tcp_iter_state), &tcp4_seq_afinfo))
+		return -ENOMEM;
+	return 0;
 }
 
 static void __net_exit tcp4_proc_exit_net(struct net *net)
 {
-	tcp_proc_unregister(net, &tcp4_seq_afinfo);
+	remove_proc_entry("tcp", net->proc_net);
 }
 
 static struct pernet_operations tcp4_net_ops = {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 383cac0ff0ec..d07e34f8e309 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2833,8 +2833,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		return -EBUSY;
 
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
-		if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
-			BUG();
+		if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
+			WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
 		if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
 			return -ENOMEM;
 	}
@@ -3342,6 +3344,7 @@ static void tcp_connect_init(struct sock *sk)
 	sock_reset_flag(sk, SOCK_DONE);
 	tp->snd_wnd = 0;
 	tcp_init_wl(tp, 0);
+	tcp_write_queue_purge(sk);
 	tp->snd_una = tp->write_seq;
 	tp->snd_sml = tp->write_seq;
 	tp->snd_up = tp->write_seq;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24b5c59b1c53..675433eb53a8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -401,9 +401,9 @@ static int compute_score(struct sock *sk, struct net *net,
 		bool dev_match = (sk->sk_bound_dev_if == dif ||
 				  sk->sk_bound_dev_if == sdif);
 
-		if (exact_dif && !dev_match)
+		if (!dev_match)
 			return -1;
-		if (sk->sk_bound_dev_if && dev_match)
+		if (sk->sk_bound_dev_if)
 			score += 4;
 	}
 
@@ -952,8 +952,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
 
 	if (ipc.opt && ipc.opt->opt.srr) {
-		if (!daddr)
-			return -EINVAL;
+		if (!daddr) {
+			err = -EINVAL;
+			goto out_free;
+		}
 		faddr = ipc.opt->opt.faddr;
 		connected = 0;
 	}
@@ -1074,6 +1076,7 @@ do_append_data:
 
 out:
 	ip_rt_put(rt);
+out_free:
 	if (free)
 		kfree(ipc.opt);
 	if (!err)
@@ -2498,7 +2501,7 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
  * 	udp_poll - wait for a UDP event.
  *	@file - file struct
  *	@sock - socket
- *	@wait - poll table
+ *	@events - events to wait for
  *
  *	This is same as datagram poll, except for the special case of
  *	blocking sockets. If application is using a blocking fd
@@ -2507,23 +2510,23 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
  *	but then block when reading it. Add special case code
  *	to work around these arguably broken applications.
  */
-__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t udp_poll_mask(struct socket *sock, __poll_t events)
 {
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = datagram_poll_mask(sock, events);
 	struct sock *sk = sock->sk;
 
 	if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Check for false positives due to checksum errors */
-	if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
+	if ((mask & EPOLLRDNORM) && !(sock->file->f_flags & O_NONBLOCK) &&
 	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
 		mask &= ~(EPOLLIN | EPOLLRDNORM);
 
 	return mask;
 
 }
-EXPORT_SYMBOL(udp_poll);
+EXPORT_SYMBOL(udp_poll_mask);
 
 int udp_abort(struct sock *sk, int err)
 {
@@ -2579,12 +2582,13 @@ EXPORT_SYMBOL(udp_prot);
 static struct sock *udp_get_first(struct seq_file *seq, int start)
 {
 	struct sock *sk;
+	struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
 	struct udp_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 
-	for (state->bucket = start; state->bucket <= state->udp_table->mask;
+	for (state->bucket = start; state->bucket <= afinfo->udp_table->mask;
 	     ++state->bucket) {
-		struct udp_hslot *hslot = &state->udp_table->hash[state->bucket];
+		struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket];
 
 		if (hlist_empty(&hslot->head))
 			continue;
@@ -2593,7 +2597,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
 		sk_for_each(sk, &hslot->head) {
 			if (!net_eq(sock_net(sk), net))
 				continue;
-			if (sk->sk_family == state->family)
+			if (sk->sk_family == afinfo->family)
 				goto found;
 		}
 		spin_unlock_bh(&hslot->lock);
@@ -2605,16 +2609,17 @@ found:
 
 static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
 {
+	struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
 	struct udp_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 
 	do {
 		sk = sk_next(sk);
-	} while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family));
+	} while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != afinfo->family));
 
 	if (!sk) {
-		if (state->bucket <= state->udp_table->mask)
-			spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
+		if (state->bucket <= afinfo->udp_table->mask)
+			spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock);
 		return udp_get_first(seq, state->bucket + 1);
 	}
 	return sk;
@@ -2630,15 +2635,16 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
 	return pos ? NULL : sk;
 }
 
-static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
+void *udp_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct udp_iter_state *state = seq->private;
 	state->bucket = MAX_UDP_PORTS;
 
 	return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
 }
+EXPORT_SYMBOL(udp_seq_start);
 
-static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct sock *sk;
 
@@ -2650,56 +2656,17 @@ static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++*pos;
 	return sk;
 }
+EXPORT_SYMBOL(udp_seq_next);
 
-static void udp_seq_stop(struct seq_file *seq, void *v)
+void udp_seq_stop(struct seq_file *seq, void *v)
 {
+	struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
 	struct udp_iter_state *state = seq->private;
 
-	if (state->bucket <= state->udp_table->mask)
-		spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
+	if (state->bucket <= afinfo->udp_table->mask)
+		spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock);
 }
-
-int udp_seq_open(struct inode *inode, struct file *file)
-{
-	struct udp_seq_afinfo *afinfo = PDE_DATA(inode);
-	struct udp_iter_state *s;
-	int err;
-
-	err = seq_open_net(inode, file, &afinfo->seq_ops,
-			   sizeof(struct udp_iter_state));
-	if (err < 0)
-		return err;
-
-	s = ((struct seq_file *)file->private_data)->private;
-	s->family		= afinfo->family;
-	s->udp_table		= afinfo->udp_table;
-	return err;
-}
-EXPORT_SYMBOL(udp_seq_open);
-
-/* ------------------------------------------------------------------------ */
-int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo)
-{
-	struct proc_dir_entry *p;
-	int rc = 0;
-
-	afinfo->seq_ops.start		= udp_seq_start;
-	afinfo->seq_ops.next		= udp_seq_next;
-	afinfo->seq_ops.stop		= udp_seq_stop;
-
-	p = proc_create_data(afinfo->name, 0444, net->proc_net,
-			     afinfo->seq_fops, afinfo);
-	if (!p)
-		rc = -ENOMEM;
-	return rc;
-}
-EXPORT_SYMBOL(udp_proc_register);
-
-void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo)
-{
-	remove_proc_entry(afinfo->name, net->proc_net);
-}
-EXPORT_SYMBOL(udp_proc_unregister);
+EXPORT_SYMBOL(udp_seq_stop);
 
 /* ------------------------------------------------------------------------ */
 static void udp4_format_sock(struct sock *sp, struct seq_file *f,
@@ -2739,32 +2706,30 @@ int udp4_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct file_operations udp_afinfo_seq_fops = {
-	.open     = udp_seq_open,
-	.read     = seq_read,
-	.llseek   = seq_lseek,
-	.release  = seq_release_net
+const struct seq_operations udp_seq_ops = {
+	.start		= udp_seq_start,
+	.next		= udp_seq_next,
+	.stop		= udp_seq_stop,
+	.show		= udp4_seq_show,
 };
+EXPORT_SYMBOL(udp_seq_ops);
 
-/* ------------------------------------------------------------------------ */
 static struct udp_seq_afinfo udp4_seq_afinfo = {
-	.name		= "udp",
 	.family		= AF_INET,
 	.udp_table	= &udp_table,
-	.seq_fops	= &udp_afinfo_seq_fops,
-	.seq_ops	= {
-		.show		= udp4_seq_show,
-	},
 };
 
 static int __net_init udp4_proc_init_net(struct net *net)
 {
-	return udp_proc_register(net, &udp4_seq_afinfo);
+	if (!proc_create_net_data("udp", 0444, net->proc_net, &udp_seq_ops,
+			sizeof(struct udp_iter_state), &udp4_seq_afinfo))
+		return -ENOMEM;
+	return 0;
 }
 
 static void __net_exit udp4_proc_exit_net(struct net *net)
 {
-	udp_proc_unregister(net, &udp4_seq_afinfo);
+	remove_proc_entry("udp", net->proc_net);
 }
 
 static struct pernet_operations udp4_net_ops = {
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index f96614e9b9a5..8545457752fb 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -14,6 +14,7 @@
 #define pr_fmt(fmt) "UDPLite: " fmt
 
 #include <linux/export.h>
+#include <linux/proc_fs.h>
 #include "udp_impl.h"
 
 struct udp_table 	udplite_table __read_mostly;
@@ -73,32 +74,22 @@ static struct inet_protosw udplite4_protosw = {
 };
 
 #ifdef CONFIG_PROC_FS
-
-static const struct file_operations udplite_afinfo_seq_fops = {
-	.open     = udp_seq_open,
-	.read     = seq_read,
-	.llseek   = seq_lseek,
-	.release  = seq_release_net
-};
-
 static struct udp_seq_afinfo udplite4_seq_afinfo = {
-	.name		= "udplite",
 	.family		= AF_INET,
 	.udp_table 	= &udplite_table,
-	.seq_fops	= &udplite_afinfo_seq_fops,
-	.seq_ops	= {
-		.show		= udp4_seq_show,
-	},
 };
 
 static int __net_init udplite4_proc_init_net(struct net *net)
 {
-	return udp_proc_register(net, &udplite4_seq_afinfo);
+	if (!proc_create_net_data("udplite", 0444, net->proc_net, &udp_seq_ops,
+			sizeof(struct udp_iter_state), &udplite4_seq_afinfo))
+		return -ENOMEM;
+	return 0;
 }
 
 static void __net_exit udplite4_proc_exit_net(struct net *net)
 {
-	udp_proc_unregister(net, &udplite4_seq_afinfo);
+	remove_proc_entry("udplite", net->proc_net);
 }
 
 static struct pernet_operations udplite4_net_ops = {
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 6794ddf0547c..11e4e80cf7e9 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -34,16 +34,15 @@ config IPV6_ROUTE_INFO
 	bool "IPv6: Route Information (RFC 4191) support"
 	depends on IPV6_ROUTER_PREF
 	---help---
-	  This is experimental support of Route Information.
+	  Support of Route Information.
 
 	  If unsure, say N.
 
 config IPV6_OPTIMISTIC_DAD
 	bool "IPv6: Enable RFC 4429 Optimistic DAD"
 	---help---
-	  This is experimental support for optimistic Duplicate
-	  Address Detection.  It allows for autoconfigured addresses
-	  to be used more quickly.
+	  Support for optimistic Duplicate Address Detection. It allows for
+	  autoconfigured addresses to be used more quickly.
 
 	  If unsure, say N.
 
@@ -280,7 +279,7 @@ config IPV6_MROUTE
 	depends on IPV6
 	select IP_MROUTE_COMMON
 	---help---
-	  Experimental support for IPv6 multicast forwarding.
+	  Support for IPv6 multicast forwarding.
 	  If unsure, say N.
 
 config IPV6_MROUTE_MULTIPLE_TABLES
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 78cef00c9596..1b5ea3379d9b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4254,22 +4254,10 @@ static const struct seq_operations if6_seq_ops = {
 	.stop	= if6_seq_stop,
 };
 
-static int if6_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &if6_seq_ops,
-			    sizeof(struct if6_iter_state));
-}
-
-static const struct file_operations if6_fops = {
-	.open		= if6_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 static int __net_init if6_proc_net_init(struct net *net)
 {
-	if (!proc_create("if_inet6", 0444, net->proc_net, &if6_fops))
+	if (!proc_create_net("if_inet6", 0444, net->proc_net, &if6_seq_ops,
+			sizeof(struct if6_iter_state)))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8da0b513f188..d443c18b45fe 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -571,7 +571,7 @@ const struct proto_ops inet6_stream_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = inet_accept,		/* ok		*/
 	.getname	   = inet6_getname,
-	.poll		   = tcp_poll,			/* ok		*/
+	.poll_mask	   = tcp_poll_mask,		/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = inet_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
@@ -601,7 +601,7 @@ const struct proto_ops inet6_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = sock_no_accept,		/* a do nothing	*/
 	.getname	   = inet6_getname,
-	.poll		   = udp_poll,			/* ok		*/
+	.poll_mask	   = udp_poll_mask,		/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index bbcabbba9bd8..ebeaf47d5c8d 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -529,22 +529,10 @@ static const struct seq_operations ac6_seq_ops = {
 	.show	=	ac6_seq_show,
 };
 
-static int ac6_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ac6_seq_ops,
-			    sizeof(struct ac6_iter_state));
-}
-
-static const struct file_operations ac6_seq_fops = {
-	.open		=	ac6_seq_open,
-	.read		=	seq_read,
-	.llseek		=	seq_lseek,
-	.release	=	seq_release_net,
-};
-
 int __net_init ac6_proc_init(struct net *net)
 {
-	if (!proc_create("anycast6", 0444, net->proc_net, &ac6_seq_fops))
+	if (!proc_create_net("anycast6", 0444, net->proc_net, &ac6_seq_ops,
+			sizeof(struct ac6_iter_state)))
 		return -ENOMEM;
 
 	return 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index deab2db6692e..01372dd74e38 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2209,15 +2209,6 @@ void fib6_gc_cleanup(void)
 }
 
 #ifdef CONFIG_PROC_FS
-
-struct ipv6_route_iter {
-	struct seq_net_private p;
-	struct fib6_walker w;
-	loff_t skip;
-	struct fib6_table *tbl;
-	int sernum;
-};
-
 static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 {
 	struct rt6_info *rt = v;
@@ -2383,17 +2374,10 @@ static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
 	rcu_read_unlock_bh();
 }
 
-static const struct seq_operations ipv6_route_seq_ops = {
+const struct seq_operations ipv6_route_seq_ops = {
 	.start	= ipv6_route_seq_start,
 	.next	= ipv6_route_seq_next,
 	.stop	= ipv6_route_seq_stop,
 	.show	= ipv6_route_seq_show
 };
-
-int ipv6_route_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ipv6_route_seq_ops,
-			    sizeof(struct ipv6_route_iter));
-}
-
 #endif /* CONFIG_PROC_FS */
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index c05c4e82a7ca..3eee7637bdfe 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -754,6 +754,10 @@ static struct ip6_flowlabel *ip6fl_get_idx(struct seq_file *seq, loff_t pos)
 static void *ip6fl_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
+	struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
+
+	state->pid_ns = proc_pid_ns(file_inode(seq->file));
+
 	rcu_read_lock_bh();
 	return *pos ? ip6fl_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
 }
@@ -808,44 +812,10 @@ static const struct seq_operations ip6fl_seq_ops = {
 	.show	=	ip6fl_seq_show,
 };
 
-static int ip6fl_seq_open(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq;
-	struct ip6fl_iter_state *state;
-	int err;
-
-	err = seq_open_net(inode, file, &ip6fl_seq_ops,
-			   sizeof(struct ip6fl_iter_state));
-
-	if (!err) {
-		seq = file->private_data;
-		state = ip6fl_seq_private(seq);
-		rcu_read_lock();
-		state->pid_ns = get_pid_ns(task_active_pid_ns(current));
-		rcu_read_unlock();
-	}
-	return err;
-}
-
-static int ip6fl_seq_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq = file->private_data;
-	struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
-	put_pid_ns(state->pid_ns);
-	return seq_release_net(inode, file);
-}
-
-static const struct file_operations ip6fl_seq_fops = {
-	.open		=	ip6fl_seq_open,
-	.read		=	seq_read,
-	.llseek		=	seq_lseek,
-	.release	=	ip6fl_seq_release,
-};
-
 static int __net_init ip6_flowlabel_proc_init(struct net *net)
 {
-	if (!proc_create("ip6_flowlabel", 0444, net->proc_net,
-			 &ip6fl_seq_fops))
+	if (!proc_create_net("ip6_flowlabel", 0444, net->proc_net,
+			&ip6fl_seq_ops, sizeof(struct ip6fl_iter_state)))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 69727bc168cb..458de353f5d9 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -71,6 +71,7 @@ struct ip6gre_net {
 	struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE];
 
 	struct ip6_tnl __rcu *collect_md_tun;
+	struct ip6_tnl __rcu *collect_md_tun_erspan;
 	struct net_device *fb_tunnel_dev;
 };
 
@@ -81,6 +82,7 @@ static int ip6gre_tunnel_init(struct net_device *dev);
 static void ip6gre_tunnel_setup(struct net_device *dev);
 static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t);
 static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu);
+static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu);
 
 /* Tunnel hash table */
 
@@ -232,7 +234,12 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 	if (cand)
 		return cand;
 
-	t = rcu_dereference(ign->collect_md_tun);
+	if (gre_proto == htons(ETH_P_ERSPAN) ||
+	    gre_proto == htons(ETH_P_ERSPAN2))
+		t = rcu_dereference(ign->collect_md_tun_erspan);
+	else
+		t = rcu_dereference(ign->collect_md_tun);
+
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
@@ -261,6 +268,31 @@ static struct ip6_tnl __rcu **__ip6gre_bucket(struct ip6gre_net *ign,
 	return &ign->tunnels[prio][h];
 }
 
+static void ip6gre_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ign->collect_md_tun, t);
+}
+
+static void ip6erspan_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ign->collect_md_tun_erspan, t);
+}
+
+static void ip6gre_tunnel_unlink_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ign->collect_md_tun, NULL);
+}
+
+static void ip6erspan_tunnel_unlink_md(struct ip6gre_net *ign,
+				       struct ip6_tnl *t)
+{
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ign->collect_md_tun_erspan, NULL);
+}
+
 static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign,
 		const struct ip6_tnl *t)
 {
@@ -271,9 +303,6 @@ static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t)
 {
 	struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t);
 
-	if (t->parms.collect_md)
-		rcu_assign_pointer(ign->collect_md_tun, t);
-
 	rcu_assign_pointer(t->next, rtnl_dereference(*tp));
 	rcu_assign_pointer(*tp, t);
 }
@@ -283,9 +312,6 @@ static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t)
 	struct ip6_tnl __rcu **tp;
 	struct ip6_tnl *iter;
 
-	if (t->parms.collect_md)
-		rcu_assign_pointer(ign->collect_md_tun, NULL);
-
 	for (tp = ip6gre_bucket(ign, t);
 	     (iter = rtnl_dereference(*tp)) != NULL;
 	     tp = &iter->next) {
@@ -374,11 +400,23 @@ failed_free:
 	return NULL;
 }
 
+static void ip6erspan_tunnel_uninit(struct net_device *dev)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
+
+	ip6erspan_tunnel_unlink_md(ign, t);
+	ip6gre_tunnel_unlink(ign, t);
+	dst_cache_reset(&t->dst_cache);
+	dev_put(dev);
+}
+
 static void ip6gre_tunnel_uninit(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
+	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
 	dst_cache_reset(&t->dst_cache);
 	dev_put(dev);
@@ -698,6 +736,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 	else
 		fl6->daddr = tunnel->parms.raddr;
 
+	if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
+		return -ENOMEM;
+
 	/* Push GRE header. */
 	protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
 
@@ -908,7 +949,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 		truncate = true;
 	}
 
-	if (skb_cow_head(skb, dev->needed_headroom))
+	if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
 		goto tx_err;
 
 	t->parms.o_flags &= ~TUNNEL_KEY;
@@ -979,11 +1020,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 			erspan_build_header(skb, ntohl(t->parms.o_key),
 					    t->parms.index,
 					    truncate, false);
-		else
+		else if (t->parms.erspan_ver == 2)
 			erspan_build_header_v2(skb, ntohl(t->parms.o_key),
 					       t->parms.dir,
 					       t->parms.hwid,
 					       truncate, false);
+		else
+			goto tx_err;
+
 		fl6.daddr = t->parms.raddr;
 	}
 
@@ -1019,12 +1063,11 @@ tx_err:
 	return NETDEV_TX_OK;
 }
 
-static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+static void ip6gre_tnl_link_config_common(struct ip6_tnl *t)
 {
 	struct net_device *dev = t->dev;
 	struct __ip6_tnl_parm *p = &t->parms;
 	struct flowi6 *fl6 = &t->fl.u.ip6;
-	int t_hlen;
 
 	if (dev->type != ARPHRD_ETHER) {
 		memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
@@ -1051,12 +1094,13 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 		dev->flags |= IFF_POINTOPOINT;
 	else
 		dev->flags &= ~IFF_POINTOPOINT;
+}
 
-	t->tun_hlen = gre_calc_hlen(t->parms.o_flags);
-
-	t->hlen = t->encap_hlen + t->tun_hlen;
-
-	t_hlen = t->hlen + sizeof(struct ipv6hdr);
+static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
+					 int t_hlen)
+{
+	const struct __ip6_tnl_parm *p = &t->parms;
+	struct net_device *dev = t->dev;
 
 	if (p->flags & IP6_TNL_F_CAP_XMIT) {
 		int strict = (ipv6_addr_type(&p->raddr) &
@@ -1088,8 +1132,26 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 	}
 }
 
-static int ip6gre_tnl_change(struct ip6_tnl *t,
-	const struct __ip6_tnl_parm *p, int set_mtu)
+static int ip6gre_calc_hlen(struct ip6_tnl *tunnel)
+{
+	int t_hlen;
+
+	tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
+	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
+
+	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+	tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+	return t_hlen;
+}
+
+static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+{
+	ip6gre_tnl_link_config_common(t);
+	ip6gre_tnl_link_config_route(t, set_mtu, ip6gre_calc_hlen(t));
+}
+
+static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t,
+				     const struct __ip6_tnl_parm *p)
 {
 	t->parms.laddr = p->laddr;
 	t->parms.raddr = p->raddr;
@@ -1105,6 +1167,12 @@ static int ip6gre_tnl_change(struct ip6_tnl *t,
 	t->parms.o_flags = p->o_flags;
 	t->parms.fwmark = p->fwmark;
 	dst_cache_reset(&t->dst_cache);
+}
+
+static int ip6gre_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p,
+			     int set_mtu)
+{
+	ip6gre_tnl_copy_tnl_parm(t, p);
 	ip6gre_tnl_link_config(t, set_mtu);
 	return 0;
 }
@@ -1381,11 +1449,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 		return ret;
 	}
 
-	tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
-	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
-	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
-
-	dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+	t_hlen = ip6gre_calc_hlen(tunnel);
 	dev->mtu = ETH_DATA_LEN - t_hlen;
 	if (dev->type == ARPHRD_ETHER)
 		dev->mtu -= ETH_HLEN;
@@ -1728,6 +1792,19 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
 	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
+static int ip6erspan_calc_hlen(struct ip6_tnl *tunnel)
+{
+	int t_hlen;
+
+	tunnel->tun_hlen = 8;
+	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
+		       erspan_hdr_len(tunnel->parms.erspan_ver);
+
+	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+	tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+	return t_hlen;
+}
+
 static int ip6erspan_tap_init(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
@@ -1751,12 +1828,7 @@ static int ip6erspan_tap_init(struct net_device *dev)
 		return ret;
 	}
 
-	tunnel->tun_hlen = 8;
-	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
-		       erspan_hdr_len(tunnel->parms.erspan_ver);
-	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
-
-	dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+	t_hlen = ip6erspan_calc_hlen(tunnel);
 	dev->mtu = ETH_DATA_LEN - t_hlen;
 	if (dev->type == ARPHRD_ETHER)
 		dev->mtu -= ETH_HLEN;
@@ -1764,14 +1836,14 @@ static int ip6erspan_tap_init(struct net_device *dev)
 		dev->mtu -= 8;
 
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
-	ip6gre_tnl_link_config(tunnel, 1);
+	ip6erspan_tnl_link_config(tunnel, 1);
 
 	return 0;
 }
 
 static const struct net_device_ops ip6erspan_netdev_ops = {
 	.ndo_init =		ip6erspan_tap_init,
-	.ndo_uninit =		ip6gre_tunnel_uninit,
+	.ndo_uninit =		ip6erspan_tunnel_uninit,
 	.ndo_start_xmit =	ip6erspan_tunnel_xmit,
 	.ndo_set_mac_address =	eth_mac_addr,
 	.ndo_validate_addr =	eth_validate_addr,
@@ -1835,13 +1907,11 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
 	return ret;
 }
 
-static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
-			  struct netlink_ext_ack *extack)
+static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
+				 struct nlattr *tb[], struct nlattr *data[],
+				 struct netlink_ext_ack *extack)
 {
 	struct ip6_tnl *nt;
-	struct net *net = dev_net(dev);
-	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	struct ip_tunnel_encap ipencap;
 	int err;
 
@@ -1854,16 +1924,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 			return err;
 	}
 
-	ip6gre_netlink_parms(data, &nt->parms);
-
-	if (nt->parms.collect_md) {
-		if (rtnl_dereference(ign->collect_md_tun))
-			return -EEXIST;
-	} else {
-		if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
-			return -EEXIST;
-	}
-
 	if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
 		eth_hw_addr_random(dev);
 
@@ -1874,51 +1934,94 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 	if (err)
 		goto out;
 
-	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
-
 	if (tb[IFLA_MTU])
 		ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
 
 	dev_hold(dev);
-	ip6gre_tunnel_link(ign, nt);
 
 out:
 	return err;
 }
 
-static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
-			     struct nlattr *data[],
-			     struct netlink_ext_ack *extack)
+static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[],
+			  struct netlink_ext_ack *extack)
+{
+	struct ip6_tnl *nt = netdev_priv(dev);
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign;
+	int err;
+
+	ip6gre_netlink_parms(data, &nt->parms);
+	ign = net_generic(net, ip6gre_net_id);
+
+	if (nt->parms.collect_md) {
+		if (rtnl_dereference(ign->collect_md_tun))
+			return -EEXIST;
+	} else {
+		if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+			return -EEXIST;
+	}
+
+	err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+	if (!err) {
+		ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
+		ip6gre_tunnel_link_md(ign, nt);
+		ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt);
+	}
+	return err;
+}
+
+static struct ip6_tnl *
+ip6gre_changelink_common(struct net_device *dev, struct nlattr *tb[],
+			 struct nlattr *data[], struct __ip6_tnl_parm *p_p,
+			 struct netlink_ext_ack *extack)
 {
 	struct ip6_tnl *t, *nt = netdev_priv(dev);
 	struct net *net = nt->net;
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
-	struct __ip6_tnl_parm p;
 	struct ip_tunnel_encap ipencap;
 
 	if (dev == ign->fb_tunnel_dev)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	if (ip6gre_netlink_encap_parms(data, &ipencap)) {
 		int err = ip6_tnl_encap_setup(nt, &ipencap);
 
 		if (err < 0)
-			return err;
+			return ERR_PTR(err);
 	}
 
-	ip6gre_netlink_parms(data, &p);
+	ip6gre_netlink_parms(data, p_p);
 
-	t = ip6gre_tunnel_locate(net, &p, 0);
+	t = ip6gre_tunnel_locate(net, p_p, 0);
 
 	if (t) {
 		if (t->dev != dev)
-			return -EEXIST;
+			return ERR_PTR(-EEXIST);
 	} else {
 		t = nt;
 	}
 
+	return t;
+}
+
+static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
+			     struct nlattr *data[],
+			     struct netlink_ext_ack *extack)
+{
+	struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id);
+	struct __ip6_tnl_parm p;
+	struct ip6_tnl *t;
+
+	t = ip6gre_changelink_common(dev, tb, data, &p, extack);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+
+	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
 	ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+	ip6gre_tunnel_link_md(ign, t);
 	ip6gre_tunnel_link(ign, t);
 	return 0;
 }
@@ -2068,6 +2171,69 @@ static void ip6erspan_tap_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 }
 
+static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
+			     struct nlattr *tb[], struct nlattr *data[],
+			     struct netlink_ext_ack *extack)
+{
+	struct ip6_tnl *nt = netdev_priv(dev);
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign;
+	int err;
+
+	ip6gre_netlink_parms(data, &nt->parms);
+	ign = net_generic(net, ip6gre_net_id);
+
+	if (nt->parms.collect_md) {
+		if (rtnl_dereference(ign->collect_md_tun_erspan))
+			return -EEXIST;
+	} else {
+		if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+			return -EEXIST;
+	}
+
+	err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+	if (!err) {
+		ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]);
+		ip6erspan_tunnel_link_md(ign, nt);
+		ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt);
+	}
+	return err;
+}
+
+static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+{
+	ip6gre_tnl_link_config_common(t);
+	ip6gre_tnl_link_config_route(t, set_mtu, ip6erspan_calc_hlen(t));
+}
+
+static int ip6erspan_tnl_change(struct ip6_tnl *t,
+				const struct __ip6_tnl_parm *p, int set_mtu)
+{
+	ip6gre_tnl_copy_tnl_parm(t, p);
+	ip6erspan_tnl_link_config(t, set_mtu);
+	return 0;
+}
+
+static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[],
+				struct nlattr *data[],
+				struct netlink_ext_ack *extack)
+{
+	struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id);
+	struct __ip6_tnl_parm p;
+	struct ip6_tnl *t;
+
+	t = ip6gre_changelink_common(dev, tb, data, &p, extack);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+
+	ip6gre_tunnel_unlink_md(ign, t);
+	ip6gre_tunnel_unlink(ign, t);
+	ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]);
+	ip6erspan_tunnel_link_md(ign, t);
+	ip6gre_tunnel_link(ign, t);
+	return 0;
+}
+
 static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
 	.kind		= "ip6gre",
 	.maxtype	= IFLA_GRE_MAX,
@@ -2104,8 +2270,8 @@ static struct rtnl_link_ops ip6erspan_tap_ops __read_mostly = {
 	.priv_size	= sizeof(struct ip6_tnl),
 	.setup		= ip6erspan_tap_setup,
 	.validate	= ip6erspan_tap_validate,
-	.newlink	= ip6gre_newlink,
-	.changelink	= ip6gre_changelink,
+	.newlink	= ip6erspan_newlink,
+	.changelink	= ip6erspan_changelink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
 	.get_link_net	= ip6_tnl_get_link_net,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 2e891d2c30ef..7b6d1689087b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1503,7 +1503,8 @@ alloc_new_skb:
 		if (copy > length)
 			copy = length;
 
-		if (!(rt->dst.dev->features&NETIF_F_SG)) {
+		if (!(rt->dst.dev->features&NETIF_F_SG) &&
+		    skb_tailroom(skb) >= copy) {
 			unsigned int off;
 
 			off = skb->len;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index da66aaac51ce..00e138a44cbb 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1692,8 +1692,13 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
 		if (new_mtu < ETH_MIN_MTU)
 			return -EINVAL;
 	}
-	if (new_mtu > 0xFFF8 - dev->hard_header_len)
-		return -EINVAL;
+	if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) {
+		if (new_mtu > IP6_MAX_MTU - dev->hard_header_len)
+			return -EINVAL;
+	} else {
+		if (new_mtu > IP_MAX_MTU - dev->hard_header_len)
+			return -EINVAL;
+	}
 	dev->mtu = new_mtu;
 	return 0;
 }
@@ -1841,7 +1846,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		dev->mtu -= 8;
 	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = 0xFFF8 - dev->hard_header_len;
+	dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len;
 
 	return 0;
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index c214ffec02f0..ca957dd93a29 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -669,7 +669,7 @@ static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu)
 	else
 		mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr);
 
-	dev->mtu = max_t(int, mtu, IPV6_MIN_MTU);
+	dev->mtu = max_t(int, mtu, IPV4_MIN_MTU);
 }
 
 /**
@@ -881,7 +881,7 @@ static void vti6_dev_setup(struct net_device *dev)
 	dev->priv_destructor = vti6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
-	dev->min_mtu = IPV6_MIN_MTU;
+	dev->min_mtu = IPV4_MIN_MTU;
 	dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr);
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 298fd8b6ed17..4a15529d33eb 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -439,19 +439,6 @@ static const struct seq_operations ip6mr_vif_seq_ops = {
 	.show  = ip6mr_vif_seq_show,
 };
 
-static int ip6mr_vif_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ip6mr_vif_seq_ops,
-			    sizeof(struct mr_vif_iter));
-}
-
-static const struct file_operations ip6mr_vif_fops = {
-	.open    = ip6mr_vif_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct net *net = seq_file_net(seq);
@@ -512,19 +499,6 @@ static const struct seq_operations ipmr_mfc_seq_ops = {
 	.stop  = mr_mfc_seq_stop,
 	.show  = ipmr_mfc_seq_show,
 };
-
-static int ipmr_mfc_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ipmr_mfc_seq_ops,
-			    sizeof(struct mr_mfc_iter));
-}
-
-static const struct file_operations ip6mr_mfc_fops = {
-	.open    = ipmr_mfc_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
 #endif
 
 #ifdef CONFIG_IPV6_PIMSM_V2
@@ -1316,9 +1290,11 @@ static int __net_init ip6mr_net_init(struct net *net)
 
 #ifdef CONFIG_PROC_FS
 	err = -ENOMEM;
-	if (!proc_create("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_fops))
+	if (!proc_create_net("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_seq_ops,
+			sizeof(struct mr_vif_iter)))
 		goto proc_vif_fail;
-	if (!proc_create("ip6_mr_cache", 0, net->proc_net, &ip6mr_mfc_fops))
+	if (!proc_create_net("ip6_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops,
+			sizeof(struct mr_mfc_iter)))
 		goto proc_cache_fail;
 #endif
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 793159d77d8a..975021df7c1c 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2749,19 +2749,6 @@ static const struct seq_operations igmp6_mc_seq_ops = {
 	.show	=	igmp6_mc_seq_show,
 };
 
-static int igmp6_mc_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &igmp6_mc_seq_ops,
-			    sizeof(struct igmp6_mc_iter_state));
-}
-
-static const struct file_operations igmp6_mc_seq_fops = {
-	.open		=	igmp6_mc_seq_open,
-	.read		=	seq_read,
-	.llseek		=	seq_lseek,
-	.release	=	seq_release_net,
-};
-
 struct igmp6_mcf_iter_state {
 	struct seq_net_private p;
 	struct net_device *dev;
@@ -2903,28 +2890,17 @@ static const struct seq_operations igmp6_mcf_seq_ops = {
 	.show	=	igmp6_mcf_seq_show,
 };
 
-static int igmp6_mcf_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &igmp6_mcf_seq_ops,
-			    sizeof(struct igmp6_mcf_iter_state));
-}
-
-static const struct file_operations igmp6_mcf_seq_fops = {
-	.open		=	igmp6_mcf_seq_open,
-	.read		=	seq_read,
-	.llseek		=	seq_lseek,
-	.release	=	seq_release_net,
-};
-
 static int __net_init igmp6_proc_init(struct net *net)
 {
 	int err;
 
 	err = -ENOMEM;
-	if (!proc_create("igmp6", 0444, net->proc_net, &igmp6_mc_seq_fops))
+	if (!proc_create_net("igmp6", 0444, net->proc_net, &igmp6_mc_seq_ops,
+			sizeof(struct igmp6_mc_iter_state)))
 		goto out;
-	if (!proc_create("mcfilter6", 0444, net->proc_net,
-			 &igmp6_mcf_seq_fops))
+	if (!proc_create_net("mcfilter6", 0444, net->proc_net,
+			&igmp6_mcf_seq_ops,
+			sizeof(struct igmp6_mcf_iter_state)))
 		goto out_proc_net_igmp6;
 
 	err = 0;
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ccbfa83e4bb0..ce77bcc2490c 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -48,6 +48,34 @@ config NFT_CHAIN_ROUTE_IPV6
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
+if NF_NAT_IPV6
+
+config NFT_CHAIN_NAT_IPV6
+	tristate "IPv6 nf_tables nat chain support"
+	help
+	  This option enables the "nat" chain for IPv6 in nf_tables. This
+	  chain type is used to perform Network Address Translation (NAT)
+	  packet transformations such as the source, destination address and
+	  source and destination ports.
+
+config NFT_MASQ_IPV6
+	tristate "IPv6 masquerade support for nf_tables"
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV6
+	help
+	  This is the expression that provides IPv4 masquerading support for
+	  nf_tables.
+
+config NFT_REDIR_IPV6
+	tristate "IPv6 redirect support for nf_tables"
+	depends on NFT_REDIR
+	select NF_NAT_REDIRECT
+	help
+	  This is the expression that provides IPv4 redirect support for
+	  nf_tables.
+
+endif # NF_NAT_IPV6
+
 config NFT_REJECT_IPV6
 	select NF_REJECT_IPV6
 	default NFT_REJECT
@@ -107,39 +135,12 @@ config NF_NAT_IPV6
 
 if NF_NAT_IPV6
 
-config NFT_CHAIN_NAT_IPV6
-	depends on NF_TABLES_IPV6
-	tristate "IPv6 nf_tables nat chain support"
-	help
-	  This option enables the "nat" chain for IPv6 in nf_tables. This
-	  chain type is used to perform Network Address Translation (NAT)
-	  packet transformations such as the source, destination address and
-	  source and destination ports.
-
 config NF_NAT_MASQUERADE_IPV6
 	tristate "IPv6 masquerade support"
 	help
 	  This is the kernel functionality to provide NAT in the masquerade
 	  flavour (automatic source address selection) for IPv6.
 
-config NFT_MASQ_IPV6
-	tristate "IPv6 masquerade support for nf_tables"
-	depends on NF_TABLES_IPV6
-	depends on NFT_MASQ
-	select NF_NAT_MASQUERADE_IPV6
-	help
-	  This is the expression that provides IPv4 masquerading support for
-	  nf_tables.
-
-config NFT_REDIR_IPV6
-	tristate "IPv6 redirect support for nf_tables"
-	depends on NF_TABLES_IPV6
-	depends on NFT_REDIR
-	select NF_NAT_REDIRECT
-	help
-	  This is the expression that provides IPv4 redirect support for
-	  nf_tables.
-
 endif # NF_NAT_IPV6
 
 config IP6_NF_IPTABLES
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 65c9e1a58305..97f79dc943d7 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -38,6 +38,7 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
 MODULE_DESCRIPTION("IPv6 packet filter");
+MODULE_ALIAS("ip6t_icmp6");
 
 void *ip6t_alloc_initial_table(const struct xt_table *info)
 {
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 746eeae7f581..96f56bf49a30 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -24,6 +24,7 @@
 #include <net/protocol.h>
 #include <net/udp.h>
 #include <net/transp_v6.h>
+#include <linux/proc_fs.h>
 #include <net/ping.h>
 
 /* Compatibility glue so we can support IPv6 when it's compiled as a module */
@@ -215,26 +216,24 @@ static int ping_v6_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static struct ping_seq_afinfo ping_v6_seq_afinfo = {
-	.name		= "icmp6",
-	.family		= AF_INET6,
-	.seq_fops       = &ping_seq_fops,
-	.seq_ops	= {
-		.start		= ping_v6_seq_start,
-		.show		= ping_v6_seq_show,
-		.next		= ping_seq_next,
-		.stop		= ping_seq_stop,
-	},
+static const struct seq_operations ping_v6_seq_ops = {
+	.start		= ping_v6_seq_start,
+	.show		= ping_v6_seq_show,
+	.next		= ping_seq_next,
+	.stop		= ping_seq_stop,
 };
 
 static int __net_init ping_v6_proc_init_net(struct net *net)
 {
-	return ping_proc_register(net, &ping_v6_seq_afinfo);
+	if (!proc_create_net("icmp6", 0444, net->proc_net, &ping_v6_seq_ops,
+			sizeof(struct ping_iter_state)))
+		return -ENOMEM;
+	return 0;
 }
 
 static void __net_init ping_v6_proc_exit_net(struct net *net)
 {
-	return ping_proc_unregister(net, &ping_v6_seq_afinfo);
+	remove_proc_entry("icmp6", net->proc_net);
 }
 
 static struct pernet_operations ping_v6_net_ops = {
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index a85f7e0b14b1..2356b4af7309 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -53,18 +53,6 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int sockstat6_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, sockstat6_seq_show);
-}
-
-static const struct file_operations sockstat6_seq_fops = {
-	.open	 = sockstat6_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release_net,
-};
-
 static const struct snmp_mib snmp6_ipstats_list[] = {
 /* ipv6 mib according to RFC 2465 */
 	SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INPKTS),
@@ -242,18 +230,6 @@ static int snmp6_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int snmp6_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, snmp6_seq_show);
-}
-
-static const struct file_operations snmp6_seq_fops = {
-	.open	 = snmp6_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release_net,
-};
-
 static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
 {
 	struct inet6_dev *idev = (struct inet6_dev *)seq->private;
@@ -267,18 +243,6 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int snmp6_dev_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, snmp6_dev_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations snmp6_dev_seq_fops = {
-	.open	 = snmp6_dev_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release,
-};
-
 int snmp6_register_dev(struct inet6_dev *idev)
 {
 	struct proc_dir_entry *p;
@@ -291,9 +255,8 @@ int snmp6_register_dev(struct inet6_dev *idev)
 	if (!net->mib.proc_net_devsnmp6)
 		return -ENOENT;
 
-	p = proc_create_data(idev->dev->name, 0444,
-			     net->mib.proc_net_devsnmp6,
-			     &snmp6_dev_seq_fops, idev);
+	p = proc_create_single_data(idev->dev->name, 0444,
+			net->mib.proc_net_devsnmp6, snmp6_dev_seq_show, idev);
 	if (!p)
 		return -ENOMEM;
 
@@ -315,11 +278,12 @@ int snmp6_unregister_dev(struct inet6_dev *idev)
 
 static int __net_init ipv6_proc_init_net(struct net *net)
 {
-	if (!proc_create("sockstat6", 0444, net->proc_net,
-			 &sockstat6_seq_fops))
+	if (!proc_create_net_single("sockstat6", 0444, net->proc_net,
+			sockstat6_seq_show, NULL))
 		return -ENOMEM;
 
-	if (!proc_create("snmp6", 0444, net->proc_net, &snmp6_seq_fops))
+	if (!proc_create_net_single("snmp6", 0444, net->proc_net,
+			snmp6_seq_show, NULL))
 		goto proc_snmp6_fail;
 
 	net->mib.proc_net_devsnmp6 = proc_mkdir("dev_snmp6", net->proc_net);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5eb9b08947ed..ce6f0d15b5dd 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1304,21 +1304,10 @@ static const struct seq_operations raw6_seq_ops = {
 	.show =		raw6_seq_show,
 };
 
-static int raw6_seq_open(struct inode *inode, struct file *file)
-{
-	return raw_seq_open(inode, file, &raw_v6_hashinfo, &raw6_seq_ops);
-}
-
-static const struct file_operations raw6_seq_fops = {
-	.open =		raw6_seq_open,
-	.read =		seq_read,
-	.llseek =	seq_lseek,
-	.release =	seq_release_net,
-};
-
 static int __net_init raw6_init_net(struct net *net)
 {
-	if (!proc_create("raw6", 0444, net->proc_net, &raw6_seq_fops))
+	if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops,
+			sizeof(struct raw_iter_state), &raw_v6_hashinfo))
 		return -ENOMEM;
 
 	return 0;
@@ -1345,7 +1334,7 @@ void raw6_proc_exit(void)
 }
 #endif	/* CONFIG_PROC_FS */
 
-/* Same as inet6_dgram_ops, sans udp_poll.  */
+/* Same as inet6_dgram_ops, sans udp_poll_mask.  */
 const struct proto_ops inet6_sockraw_ops = {
 	.family		   = PF_INET6,
 	.owner		   = THIS_MODULE,
@@ -1355,7 +1344,7 @@ const struct proto_ops inet6_sockraw_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = sock_no_accept,		/* a do nothing	*/
 	.getname	   = inet6_getname,
-	.poll		   = datagram_poll,		/* ok		*/
+	.poll_mask	   = datagram_poll_mask,	/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 49b954d6d0fa..a6598762d2c1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1835,11 +1835,16 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
 	const struct ipv6hdr *inner_iph;
 	const struct icmp6hdr *icmph;
 	struct ipv6hdr _inner_iph;
+	struct icmp6hdr _icmph;
 
 	if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6))
 		goto out;
 
-	icmph = icmp6_hdr(skb);
+	icmph = skb_header_pointer(skb, skb_transport_offset(skb),
+				   sizeof(_icmph), &_icmph);
+	if (!icmph)
+		goto out;
+
 	if (icmph->icmp6_type != ICMPV6_DEST_UNREACH &&
 	    icmph->icmp6_type != ICMPV6_PKT_TOOBIG &&
 	    icmph->icmp6_type != ICMPV6_TIME_EXCEED &&
@@ -3975,6 +3980,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
 
 static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_GATEWAY]           = { .len = sizeof(struct in6_addr) },
+	[RTA_PREFSRC]		= { .len = sizeof(struct in6_addr) },
 	[RTA_OIF]               = { .type = NLA_U32 },
 	[RTA_IIF]		= { .type = NLA_U32 },
 	[RTA_PRIORITY]          = { .type = NLA_U32 },
@@ -3986,6 +3992,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_EXPIRES]		= { .type = NLA_U32 },
 	[RTA_UID]		= { .type = NLA_U32 },
 	[RTA_MARK]		= { .type = NLA_U32 },
+	[RTA_TABLE]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4855,14 +4862,6 @@ static int ip6_route_dev_notify(struct notifier_block *this,
  */
 
 #ifdef CONFIG_PROC_FS
-
-static const struct file_operations ipv6_route_proc_fops = {
-	.open		= ipv6_route_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 static int rt6_stats_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = (struct net *)seq->private;
@@ -4877,18 +4876,6 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int rt6_stats_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, rt6_stats_seq_show);
-}
-
-static const struct file_operations rt6_stats_seq_fops = {
-	.open	 = rt6_stats_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release_net,
-};
 #endif	/* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SYSCTL
@@ -5093,8 +5080,10 @@ static void __net_exit ip6_route_net_exit(struct net *net)
 static int __net_init ip6_route_net_init_late(struct net *net)
 {
 #ifdef CONFIG_PROC_FS
-	proc_create("ipv6_route", 0, net->proc_net, &ipv6_route_proc_fops);
-	proc_create("rt6_stats", 0444, net->proc_net, &rt6_stats_seq_fops);
+	proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops,
+			sizeof(struct ipv6_route_iter));
+	proc_create_net_single("rt6_stats", 0444, net->proc_net,
+			rt6_stats_seq_show, NULL);
 #endif
 	return 0;
 }
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index f343e6f0fc95..bf4763fd68c2 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -103,7 +103,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	hdrlen = (osrh->hdrlen + 1) << 3;
 	tot_len = hdrlen + sizeof(*hdr);
 
-	err = skb_cow_head(skb, tot_len);
+	err = skb_cow_head(skb, tot_len + skb->mac_len);
 	if (unlikely(err))
 		return err;
 
@@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	isrh->nexthdr = proto;
 
 	hdr->daddr = isrh->segments[isrh->first_segment];
-	set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+	set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
 
 #ifdef CONFIG_IPV6_SEG6_HMAC
 	if (sr_has_hmac(isrh)) {
@@ -161,7 +161,7 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 
 	hdrlen = (osrh->hdrlen + 1) << 3;
 
-	err = skb_cow_head(skb, hdrlen);
+	err = skb_cow_head(skb, hdrlen + skb->mac_len);
 	if (unlikely(err))
 		return err;
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 2afce37a7177..e9400ffa7875 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1371,7 +1371,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
 	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->min_mtu		= IPV6_MIN_MTU;
-	dev->max_mtu		= 0xFFF8 - t_hlen;
+	dev->max_mtu		= IP6_MAX_MTU - t_hlen;
 	dev->flags		= IFF_NOARP;
 	netif_keep_dst(dev);
 	dev->addr_len		= 4;
@@ -1583,7 +1583,8 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 	if (tb[IFLA_MTU]) {
 		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
 
-		if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len)
+		if (mtu >= IPV6_MIN_MTU &&
+		    mtu <= IP6_MAX_MTU - dev->hard_header_len)
 			dev->mtu = mtu;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6d664d83cd16..d2ce66b23430 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1909,30 +1909,28 @@ out:
 	return 0;
 }
 
-static const struct file_operations tcp6_afinfo_seq_fops = {
-	.open    = tcp_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net
+static const struct seq_operations tcp6_seq_ops = {
+	.show		= tcp6_seq_show,
+	.start		= tcp_seq_start,
+	.next		= tcp_seq_next,
+	.stop		= tcp_seq_stop,
 };
 
 static struct tcp_seq_afinfo tcp6_seq_afinfo = {
-	.name		= "tcp6",
 	.family		= AF_INET6,
-	.seq_fops	= &tcp6_afinfo_seq_fops,
-	.seq_ops	= {
-		.show		= tcp6_seq_show,
-	},
 };
 
 int __net_init tcp6_proc_init(struct net *net)
 {
-	return tcp_proc_register(net, &tcp6_seq_afinfo);
+	if (!proc_create_net_data("tcp6", 0444, net->proc_net, &tcp6_seq_ops,
+			sizeof(struct tcp_iter_state), &tcp6_seq_afinfo))
+		return -ENOMEM;
+	return 0;
 }
 
 void tcp6_proc_exit(struct net *net)
 {
-	tcp_proc_unregister(net, &tcp6_seq_afinfo);
+	remove_proc_entry("tcp6", net->proc_net);
 }
 #endif
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4ec76a87aeb8..00e2112da26d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -148,9 +148,9 @@ static int compute_score(struct sock *sk, struct net *net,
 		bool dev_match = (sk->sk_bound_dev_if == dif ||
 				  sk->sk_bound_dev_if == sdif);
 
-		if (exact_dif && !dev_match)
+		if (!dev_match)
 			return -1;
-		if (sk->sk_bound_dev_if && dev_match)
+		if (sk->sk_bound_dev_if)
 			score++;
 	}
 
@@ -1480,31 +1480,30 @@ int udp6_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct file_operations udp6_afinfo_seq_fops = {
-	.open     = udp_seq_open,
-	.read     = seq_read,
-	.llseek   = seq_lseek,
-	.release  = seq_release_net
+const struct seq_operations udp6_seq_ops = {
+	.start		= udp_seq_start,
+	.next		= udp_seq_next,
+	.stop		= udp_seq_stop,
+	.show		= udp6_seq_show,
 };
+EXPORT_SYMBOL(udp6_seq_ops);
 
 static struct udp_seq_afinfo udp6_seq_afinfo = {
-	.name		= "udp6",
 	.family		= AF_INET6,
 	.udp_table	= &udp_table,
-	.seq_fops	= &udp6_afinfo_seq_fops,
-	.seq_ops	= {
-		.show		= udp6_seq_show,
-	},
 };
 
 int __net_init udp6_proc_init(struct net *net)
 {
-	return udp_proc_register(net, &udp6_seq_afinfo);
+	if (!proc_create_net_data("udp6", 0444, net->proc_net, &udp6_seq_ops,
+			sizeof(struct udp_iter_state), &udp6_seq_afinfo))
+		return -ENOMEM;
+	return 0;
 }
 
 void udp6_proc_exit(struct net *net)
 {
-	udp_proc_unregister(net, &udp6_seq_afinfo);
+	remove_proc_entry("udp6", net->proc_net);
 }
 #endif /* CONFIG_PROC_FS */
 
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 14ae32bb1f3d..5000ad6878e6 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -12,6 +12,7 @@
  *		2 of the License, or (at your option) any later version.
  */
 #include <linux/export.h>
+#include <linux/proc_fs.h>
 #include "udp_impl.h"
 
 static int udplitev6_rcv(struct sk_buff *skb)
@@ -92,32 +93,23 @@ void udplitev6_exit(void)
 }
 
 #ifdef CONFIG_PROC_FS
-
-static const struct file_operations udplite6_afinfo_seq_fops = {
-	.open     = udp_seq_open,
-	.read     = seq_read,
-	.llseek   = seq_lseek,
-	.release  = seq_release_net
-};
-
 static struct udp_seq_afinfo udplite6_seq_afinfo = {
-	.name		= "udplite6",
 	.family		= AF_INET6,
 	.udp_table	= &udplite_table,
-	.seq_fops	= &udplite6_afinfo_seq_fops,
-	.seq_ops	= {
-		.show		= udp6_seq_show,
-	},
 };
 
 static int __net_init udplite6_proc_init_net(struct net *net)
 {
-	return udp_proc_register(net, &udplite6_seq_afinfo);
+	if (!proc_create_net_data("udplite6", 0444, net->proc_net,
+			&udp6_seq_ops, sizeof(struct udp_iter_state),
+			&udplite6_seq_afinfo))
+		return -ENOMEM;
+	return 0;
 }
 
 static void __net_exit udplite6_proc_exit_net(struct net *net)
 {
-	udp_proc_unregister(net, &udplite6_seq_afinfo);
+	remove_proc_entry("udplite6", net->proc_net);
 }
 
 static struct pernet_operations udplite6_net_ops = {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 416fe67271a9..86dba282a147 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -126,7 +126,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 	struct flowi6 *fl6 = &fl->u.ip6;
 	int onlyproto = 0;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
-	u16 offset = sizeof(*hdr);
+	u32 offset = sizeof(*hdr);
 	struct ipv6_opt_hdr *exthdr;
 	const unsigned char *nh = skb_network_header(skb);
 	u16 nhoff = IP6CB(skb)->nhoff;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index f85f0d7480ac..4a46df8441c9 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -341,6 +341,9 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
 	struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
 	unsigned int i;
 
+	xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
+	xfrm_flush_gc();
+
 	for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
 		WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 893a022f9620..68e86257a549 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1488,14 +1488,11 @@ static inline __poll_t iucv_accept_poll(struct sock *parent)
 	return 0;
 }
 
-__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
-			    poll_table *wait)
+static __poll_t iucv_sock_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
-
 	if (sk->sk_state == IUCV_LISTEN)
 		return iucv_accept_poll(sk);
 
@@ -2388,7 +2385,7 @@ static const struct proto_ops iucv_sock_ops = {
 	.getname	= iucv_sock_getname,
 	.sendmsg	= iucv_sock_sendmsg,
 	.recvmsg	= iucv_sock_recvmsg,
-	.poll		= iucv_sock_poll,
+	.poll_mask	= iucv_sock_poll_mask,
 	.ioctl		= sock_no_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,
diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c
index 1fac92543094..370da2f80e3c 100644
--- a/net/kcm/kcmproc.c
+++ b/net/kcm/kcmproc.c
@@ -15,12 +15,6 @@
 #include <net/tcp.h>
 
 #ifdef CONFIG_PROC_FS
-struct kcm_seq_muxinfo {
-	char				*name;
-	const struct file_operations	*seq_fops;
-	const struct seq_operations	seq_ops;
-};
-
 static struct kcm_mux *kcm_get_first(struct seq_file *seq)
 {
 	struct net *net = seq_file_net(seq);
@@ -86,14 +80,6 @@ struct kcm_proc_mux_state {
 	int idx;
 };
 
-static int kcm_seq_open(struct inode *inode, struct file *file)
-{
-	struct kcm_seq_muxinfo *muxinfo = PDE_DATA(inode);
-
-	return seq_open_net(inode, file, &muxinfo->seq_ops,
-			   sizeof(struct kcm_proc_mux_state));
-}
-
 static void kcm_format_mux_header(struct seq_file *seq)
 {
 	struct net *net = seq_file_net(seq);
@@ -246,44 +232,13 @@ static int kcm_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct file_operations kcm_seq_fops = {
-	.open		= kcm_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
+static const struct seq_operations kcm_seq_ops = {
+	.show	= kcm_seq_show,
+	.start	= kcm_seq_start,
+	.next	= kcm_seq_next,
+	.stop	= kcm_seq_stop,
 };
 
-static struct kcm_seq_muxinfo kcm_seq_muxinfo = {
-	.name		= "kcm",
-	.seq_fops	= &kcm_seq_fops,
-	.seq_ops	= {
-		.show	= kcm_seq_show,
-		.start	= kcm_seq_start,
-		.next	= kcm_seq_next,
-		.stop	= kcm_seq_stop,
-	}
-};
-
-static int kcm_proc_register(struct net *net, struct kcm_seq_muxinfo *muxinfo)
-{
-	struct proc_dir_entry *p;
-	int rc = 0;
-
-	p = proc_create_data(muxinfo->name, 0444, net->proc_net,
-			     muxinfo->seq_fops, muxinfo);
-	if (!p)
-		rc = -ENOMEM;
-	return rc;
-}
-EXPORT_SYMBOL(kcm_proc_register);
-
-static void kcm_proc_unregister(struct net *net,
-				struct kcm_seq_muxinfo *muxinfo)
-{
-	remove_proc_entry(muxinfo->name, net->proc_net);
-}
-EXPORT_SYMBOL(kcm_proc_unregister);
-
 static int kcm_stats_seq_show(struct seq_file *seq, void *v)
 {
 	struct kcm_psock_stats psock_stats;
@@ -390,30 +345,14 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int kcm_stats_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, kcm_stats_seq_show);
-}
-
-static const struct file_operations kcm_stats_seq_fops = {
-	.open    = kcm_stats_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release_net,
-};
-
 static int kcm_proc_init_net(struct net *net)
 {
-	int err;
-
-	if (!proc_create("kcm_stats", 0444, net->proc_net,
-			 &kcm_stats_seq_fops)) {
-		err = -ENOMEM;
+	if (!proc_create_net_single("kcm_stats", 0444, net->proc_net,
+			 kcm_stats_seq_show, NULL))
 		goto out_kcm_stats;
-	}
 
-	err = kcm_proc_register(net, &kcm_seq_muxinfo);
-	if (err)
+	if (!proc_create_net("kcm", 0444, net->proc_net, &kcm_seq_ops,
+			sizeof(struct kcm_proc_mux_state)))
 		goto out_kcm;
 
 	return 0;
@@ -421,12 +360,12 @@ static int kcm_proc_init_net(struct net *net)
 out_kcm:
 	remove_proc_entry("kcm_stats", net->proc_net);
 out_kcm_stats:
-	return err;
+	return -ENOMEM;
 }
 
 static void kcm_proc_exit_net(struct net *net)
 {
-	kcm_proc_unregister(net, &kcm_seq_muxinfo);
+	remove_proc_entry("kcm", net->proc_net);
 	remove_proc_entry("kcm_stats", net->proc_net);
 }
 
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index dc76bc346829..84b7d5c6fec8 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1336,9 +1336,9 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
 	struct list_head *head;
 	int index = 0;
 
-	/* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
-	 * we set sk_state, otherwise epoll_wait always returns right away with
-	 * EPOLLHUP
+	/* For SOCK_SEQPACKET sock type, datagram_poll_mask checks the sk_state,
+	 * so  we set sk_state, otherwise epoll_wait always returns right away
+	 * with EPOLLHUP
 	 */
 	kcm->sk.sk_state = TCP_ESTABLISHED;
 
@@ -1671,7 +1671,7 @@ static struct file *kcm_clone(struct socket *osock)
 	__module_get(newsock->ops->owner);
 
 	newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL,
-			 &kcm_proto, true);
+			 &kcm_proto, false);
 	if (!newsk) {
 		sock_release(newsock);
 		return ERR_PTR(-ENOMEM);
@@ -1903,7 +1903,7 @@ static const struct proto_ops kcm_dgram_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	sock_no_getname,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	kcm_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -1924,7 +1924,7 @@ static const struct proto_ops kcm_seqpacket_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	sock_no_getname,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	kcm_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 7e2e7188e7f4..8bdc1cbe490a 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -437,6 +437,24 @@ static int verify_address_len(const void *p)
 	return 0;
 }
 
+static inline int sadb_key_len(const struct sadb_key *key)
+{
+	int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8);
+
+	return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes,
+			    sizeof(uint64_t));
+}
+
+static int verify_key_len(const void *p)
+{
+	const struct sadb_key *key = p;
+
+	if (sadb_key_len(key) > key->sadb_key_len)
+		return -EINVAL;
+
+	return 0;
+}
+
 static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx)
 {
 	return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) +
@@ -533,16 +551,25 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void *
 				return -EINVAL;
 			if (ext_hdrs[ext_type-1] != NULL)
 				return -EINVAL;
-			if (ext_type == SADB_EXT_ADDRESS_SRC ||
-			    ext_type == SADB_EXT_ADDRESS_DST ||
-			    ext_type == SADB_EXT_ADDRESS_PROXY ||
-			    ext_type == SADB_X_EXT_NAT_T_OA) {
+			switch (ext_type) {
+			case SADB_EXT_ADDRESS_SRC:
+			case SADB_EXT_ADDRESS_DST:
+			case SADB_EXT_ADDRESS_PROXY:
+			case SADB_X_EXT_NAT_T_OA:
 				if (verify_address_len(p))
 					return -EINVAL;
-			}
-			if (ext_type == SADB_X_EXT_SEC_CTX) {
+				break;
+			case SADB_X_EXT_SEC_CTX:
 				if (verify_sec_ctx_len(p))
 					return -EINVAL;
+				break;
+			case SADB_EXT_KEY_AUTH:
+			case SADB_EXT_KEY_ENCRYPT:
+				if (verify_key_len(p))
+					return -EINVAL;
+				break;
+			default:
+				break;
 			}
 			ext_hdrs[ext_type-1] = (void *) p;
 		}
@@ -1104,14 +1131,12 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 	key = ext_hdrs[SADB_EXT_KEY_AUTH - 1];
 	if (key != NULL &&
 	    sa->sadb_sa_auth != SADB_X_AALG_NULL &&
-	    ((key->sadb_key_bits+7) / 8 == 0 ||
-	     (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t)))
+	    key->sadb_key_bits == 0)
 		return ERR_PTR(-EINVAL);
 	key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1];
 	if (key != NULL &&
 	    sa->sadb_sa_encrypt != SADB_EALG_NULL &&
-	    ((key->sadb_key_bits+7) / 8 == 0 ||
-	     (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t)))
+	    key->sadb_key_bits == 0)
 		return ERR_PTR(-EINVAL);
 
 	x = xfrm_state_alloc(net);
@@ -3726,7 +3751,7 @@ static const struct proto_ops pfkey_ops = {
 
 	/* Now the operations that really occur. */
 	.release	=	pfkey_release,
-	.poll		=	datagram_poll,
+	.poll_mask	=	datagram_poll_mask,
 	.sendmsg	=	pfkey_sendmsg,
 	.recvmsg	=	pfkey_recvmsg,
 };
@@ -3787,24 +3812,12 @@ static const struct seq_operations pfkey_seq_ops = {
 	.show	= pfkey_seq_show,
 };
 
-static int pfkey_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &pfkey_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations pfkey_proc_ops = {
-	.open	 = pfkey_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
 static int __net_init pfkey_init_proc(struct net *net)
 {
 	struct proc_dir_entry *e;
 
-	e = proc_create("pfkey", 0, net->proc_net, &pfkey_proc_ops);
+	e = proc_create_net("pfkey", 0, net->proc_net, &pfkey_seq_ops,
+			sizeof(struct seq_net_private));
 	if (e == NULL)
 		return -ENOMEM;
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 0fbd3ee26165..40261cb68e83 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -183,6 +183,26 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
 
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
+{
+	const struct l2tp_net *pn = l2tp_pernet(net);
+	struct l2tp_tunnel *tunnel;
+	int count = 0;
+
+	rcu_read_lock_bh();
+	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
+		if (++count > nth) {
+			l2tp_tunnel_inc_refcount(tunnel);
+			rcu_read_unlock_bh();
+			return tunnel;
+		}
+	}
+	rcu_read_unlock_bh();
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth);
+
 /* Lookup a session. A new reference is held on the returned session. */
 struct l2tp_session *l2tp_session_get(const struct net *net,
 				      struct l2tp_tunnel *tunnel,
@@ -335,26 +355,6 @@ err_tlock:
 }
 EXPORT_SYMBOL_GPL(l2tp_session_register);
 
-struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth)
-{
-	struct l2tp_net *pn = l2tp_pernet(net);
-	struct l2tp_tunnel *tunnel;
-	int count = 0;
-
-	rcu_read_lock_bh();
-	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (++count > nth) {
-			rcu_read_unlock_bh();
-			return tunnel;
-		}
-	}
-
-	rcu_read_unlock_bh();
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_find_nth);
-
 /*****************************************************************************
  * Receive data handling
  *****************************************************************************/
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index ba33cbec71eb..c199020f8a8a 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -212,6 +212,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
 }
 
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
+
 void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
 struct l2tp_session *l2tp_session_get(const struct net *net,
@@ -220,7 +222,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net,
 struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 						const char *ifname);
-struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
 
 int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 72e713da4733..7f1e842ef05a 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -47,7 +47,11 @@ struct l2tp_dfs_seq_data {
 
 static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 {
-	pd->tunnel = l2tp_tunnel_find_nth(pd->net, pd->tunnel_idx);
+	/* Drop reference taken during previous invocation */
+	if (pd->tunnel)
+		l2tp_tunnel_dec_refcount(pd->tunnel);
+
+	pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx);
 	pd->tunnel_idx++;
 }
 
@@ -96,7 +100,17 @@ static void *l2tp_dfs_seq_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void l2tp_dfs_seq_stop(struct seq_file *p, void *v)
 {
-	/* nothing to do */
+	struct l2tp_dfs_seq_data *pd = v;
+
+	if (!pd || pd == SEQ_START_TOKEN)
+		return;
+
+	/* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
+	if (pd->tunnel) {
+		l2tp_tunnel_dec_refcount(pd->tunnel);
+		pd->tunnel = NULL;
+		pd->session = NULL;
+	}
 }
 
 static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index a9c05b2bc1b0..181073bf6925 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -613,7 +613,7 @@ static const struct proto_ops l2tp_ip_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = l2tp_ip_getname,
-	.poll		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 957369192ca1..336e4c00abbc 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -754,7 +754,7 @@ static const struct proto_ops l2tp_ip6_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = l2tp_ip6_getname,
-	.poll		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index b05dbd9ffcb2..6616c9fd292f 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -487,14 +487,17 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
 	struct net *net = sock_net(skb->sk);
 
 	for (;;) {
-		tunnel = l2tp_tunnel_find_nth(net, ti);
+		tunnel = l2tp_tunnel_get_nth(net, ti);
 		if (tunnel == NULL)
 			goto out;
 
 		if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid,
 					cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					tunnel, L2TP_CMD_TUNNEL_GET) < 0)
+					tunnel, L2TP_CMD_TUNNEL_GET) < 0) {
+			l2tp_tunnel_dec_refcount(tunnel);
 			goto out;
+		}
+		l2tp_tunnel_dec_refcount(tunnel);
 
 		ti++;
 	}
@@ -848,7 +851,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 	for (;;) {
 		if (tunnel == NULL) {
-			tunnel = l2tp_tunnel_find_nth(net, ti);
+			tunnel = l2tp_tunnel_get_nth(net, ti);
 			if (tunnel == NULL)
 				goto out;
 		}
@@ -856,6 +859,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 		session = l2tp_session_get_nth(tunnel, si);
 		if (session == NULL) {
 			ti++;
+			l2tp_tunnel_dec_refcount(tunnel);
 			tunnel = NULL;
 			si = 0;
 			continue;
@@ -865,6 +869,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					 session, L2TP_CMD_SESSION_GET) < 0) {
 			l2tp_session_dec_refcount(session);
+			l2tp_tunnel_dec_refcount(tunnel);
 			break;
 		}
 		l2tp_session_dec_refcount(session);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 896bbca9bdaa..3d8ca1231f8f 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -619,6 +619,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	lock_sock(sk);
 
 	error = -EINVAL;
+
+	if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+		goto end;
+
 	if (sp->sa_protocol != PX_PROTO_OL2TP)
 		goto end;
 
@@ -1551,16 +1558,19 @@ struct pppol2tp_seq_data {
 
 static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 {
+	/* Drop reference taken during previous invocation */
+	if (pd->tunnel)
+		l2tp_tunnel_dec_refcount(pd->tunnel);
+
 	for (;;) {
-		pd->tunnel = l2tp_tunnel_find_nth(net, pd->tunnel_idx);
+		pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx);
 		pd->tunnel_idx++;
 
-		if (pd->tunnel == NULL)
-			break;
+		/* Only accept L2TPv2 tunnels */
+		if (!pd->tunnel || pd->tunnel->version == 2)
+			return;
 
-		/* Ignore L2TPv3 tunnels */
-		if (pd->tunnel->version < 3)
-			break;
+		l2tp_tunnel_dec_refcount(pd->tunnel);
 	}
 }
 
@@ -1609,7 +1619,17 @@ static void *pppol2tp_seq_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void pppol2tp_seq_stop(struct seq_file *p, void *v)
 {
-	/* nothing to do */
+	struct pppol2tp_seq_data *pd = v;
+
+	if (!pd || pd == SEQ_START_TOKEN)
+		return;
+
+	/* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
+	if (pd->tunnel) {
+		l2tp_tunnel_dec_refcount(pd->tunnel);
+		pd->tunnel = NULL;
+		pd->session = NULL;
+	}
 }
 
 static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
@@ -1722,24 +1742,6 @@ static const struct seq_operations pppol2tp_seq_ops = {
 	.stop		= pppol2tp_seq_stop,
 	.show		= pppol2tp_seq_show,
 };
-
-/* Called when our /proc file is opened. We allocate data for use when
- * iterating our tunnel / session contexts and store it in the private
- * data of the seq_file.
- */
-static int pppol2tp_proc_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &pppol2tp_seq_ops,
-			    sizeof(struct pppol2tp_seq_data));
-}
-
-static const struct file_operations pppol2tp_proc_fops = {
-	.open		= pppol2tp_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 #endif /* CONFIG_PROC_FS */
 
 /*****************************************************************************
@@ -1751,8 +1753,8 @@ static __net_init int pppol2tp_init_net(struct net *net)
 	struct proc_dir_entry *pde;
 	int err = 0;
 
-	pde = proc_create("pppol2tp", 0444, net->proc_net,
-			  &pppol2tp_proc_fops);
+	pde = proc_create_net("pppol2tp", 0444, net->proc_net,
+			&pppol2tp_seq_ops, sizeof(struct pppol2tp_seq_data));
 	if (!pde) {
 		err = -ENOMEM;
 		goto out;
@@ -1786,7 +1788,7 @@ static const struct proto_ops pppol2tp_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pppol2tp_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= pppol2tp_setsockopt,
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 01dcc0823d1f..804de8490186 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -199,9 +199,19 @@ static int llc_ui_release(struct socket *sock)
 		llc->laddr.lsap, llc->daddr.lsap);
 	if (!llc_send_disc(sk))
 		llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
-	if (!sock_flag(sk, SOCK_ZAPPED))
+	if (!sock_flag(sk, SOCK_ZAPPED)) {
+		struct llc_sap *sap = llc->sap;
+
+		/* Hold this for release_sock(), so that llc_backlog_rcv()
+		 * could still use it.
+		 */
+		llc_sap_hold(sap);
 		llc_sap_remove_socket(llc->sap, sk);
-	release_sock(sk);
+		release_sock(sk);
+		llc_sap_put(sap);
+	} else {
+		release_sock(sk);
+	}
 	if (llc->dev)
 		dev_put(llc->dev);
 	sock_put(sk);
@@ -920,6 +930,9 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (size > llc->dev->mtu)
 		size = llc->dev->mtu;
 	copied = size - hdrlen;
+	rc = -EINVAL;
+	if (copied < 0)
+		goto release;
 	release_sock(sk);
 	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
 	lock_sock(sk);
@@ -1179,7 +1192,7 @@ static const struct proto_ops llc_ui_ops = {
 	.socketpair  = sock_no_socketpair,
 	.accept      = llc_ui_accept,
 	.getname     = llc_ui_getname,
-	.poll	     = datagram_poll,
+	.poll_mask   = datagram_poll_mask,
 	.ioctl       = llc_ui_ioctl,
 	.listen      = llc_ui_listen,
 	.shutdown    = llc_ui_shutdown,
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index 163121192aca..4d78375f9872 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb)
 
 int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
 {
-	struct llc_sock *llc = llc_sk(sk);
-
-	del_timer(&llc->pf_cycle_timer.timer);
-	del_timer(&llc->ack_timer.timer);
-	del_timer(&llc->rej_sent_timer.timer);
-	del_timer(&llc->busy_state_timer.timer);
-	llc->ack_must_be_send = 0;
-	llc->ack_pf = 0;
+	llc_sk_stop_all_timers(sk, false);
 	return 0;
 }
 
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 110e32bcb399..c0ac522b48a1 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -961,6 +961,26 @@ out:
 	return sk;
 }
 
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+	struct llc_sock *llc = llc_sk(sk);
+
+	if (sync) {
+		del_timer_sync(&llc->pf_cycle_timer.timer);
+		del_timer_sync(&llc->ack_timer.timer);
+		del_timer_sync(&llc->rej_sent_timer.timer);
+		del_timer_sync(&llc->busy_state_timer.timer);
+	} else {
+		del_timer(&llc->pf_cycle_timer.timer);
+		del_timer(&llc->ack_timer.timer);
+		del_timer(&llc->rej_sent_timer.timer);
+		del_timer(&llc->busy_state_timer.timer);
+	}
+
+	llc->ack_must_be_send = 0;
+	llc->ack_pf = 0;
+}
+
 /**
  *	llc_sk_free - Frees a LLC socket
  *	@sk - socket to free
@@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk)
 
 	llc->state = LLC_CONN_OUT_OF_SVC;
 	/* Stop all (possibly) running timers */
-	llc_conn_ac_stop_all_timers(sk, NULL);
+	llc_sk_stop_all_timers(sk, true);
 #ifdef DEBUG_LLC_CONN_ALLOC
 	printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
 		skb_queue_len(&llc->pdu_unack_q),
diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c
index 62ea0aed94b4..f3a36c16a5e7 100644
--- a/net/llc/llc_proc.c
+++ b/net/llc/llc_proc.c
@@ -214,30 +214,6 @@ static const struct seq_operations llc_seq_core_ops = {
 	.show   = llc_seq_core_show,
 };
 
-static int llc_seq_socket_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &llc_seq_socket_ops);
-}
-
-static int llc_seq_core_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &llc_seq_core_ops);
-}
-
-static const struct file_operations llc_seq_socket_fops = {
-	.open		= llc_seq_socket_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations llc_seq_core_fops = {
-	.open		= llc_seq_core_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static struct proc_dir_entry *llc_proc_dir;
 
 int __init llc_proc_init(void)
@@ -249,11 +225,11 @@ int __init llc_proc_init(void)
 	if (!llc_proc_dir)
 		goto out;
 
-	p = proc_create("socket", 0444, llc_proc_dir, &llc_seq_socket_fops);
+	p = proc_create_seq("socket", 0444, llc_proc_dir, &llc_seq_socket_ops);
 	if (!p)
 		goto out_socket;
 
-	p = proc_create("core", 0444, llc_proc_dir, &llc_seq_core_fops);
+	p = proc_create_seq("core", 0444, llc_proc_dir, &llc_seq_core_ops);
 	if (!p)
 		goto out_core;
 
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 595c662a61e8..ac4295296514 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -8,6 +8,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
  * Copyright(c) 2015-2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -970,6 +971,9 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
 
 		sta->ampdu_mlme.addba_req_num[tid] = 0;
 
+		tid_tx->timeout =
+			le16_to_cpu(mgmt->u.action.u.addba_resp.timeout);
+
 		if (tid_tx->timeout) {
 			mod_timer(&tid_tx->session_timer,
 				  TU_TO_EXP_TIME(tid_tx->timeout));
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 0f6c9ca59062..5b5b0f95ffd1 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -401,7 +401,7 @@ u32 mesh_plink_deactivate(struct sta_info *sta)
 
 static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
 			       struct sta_info *sta,
-			       struct ieee802_11_elems *elems, bool insert)
+			       struct ieee802_11_elems *elems)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_supported_band *sband;
@@ -447,7 +447,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
 		sta->sta.bandwidth = IEEE80211_STA_RX_BW_20;
 	}
 
-	if (insert)
+	if (!test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
 		rate_control_rate_init(sta);
 	else
 		rate_control_rate_update(local, sband, sta, changed);
@@ -551,7 +551,7 @@ mesh_sta_info_get(struct ieee80211_sub_if_data *sdata,
 	rcu_read_lock();
 	sta = sta_info_get(sdata, addr);
 	if (sta) {
-		mesh_sta_info_init(sdata, sta, elems, false);
+		mesh_sta_info_init(sdata, sta, elems);
 	} else {
 		rcu_read_unlock();
 		/* can't run atomic */
@@ -561,7 +561,7 @@ mesh_sta_info_get(struct ieee80211_sub_if_data *sdata,
 			return NULL;
 		}
 
-		mesh_sta_info_init(sdata, sta, elems, true);
+		mesh_sta_info_init(sdata, sta, elems);
 
 		if (sta_info_insert_rcu(sta))
 			return NULL;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 69449db7e283..233068756502 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -36,6 +36,7 @@
 #define IEEE80211_AUTH_TIMEOUT		(HZ / 5)
 #define IEEE80211_AUTH_TIMEOUT_LONG	(HZ / 2)
 #define IEEE80211_AUTH_TIMEOUT_SHORT	(HZ / 10)
+#define IEEE80211_AUTH_TIMEOUT_SAE	(HZ * 2)
 #define IEEE80211_AUTH_MAX_TRIES	3
 #define IEEE80211_AUTH_WAIT_ASSOC	(HZ * 5)
 #define IEEE80211_ASSOC_TIMEOUT		(HZ / 5)
@@ -1787,7 +1788,7 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 		params[ac].acm = acm;
 		params[ac].uapsd = uapsd;
 
-		if (params->cw_min == 0 ||
+		if (params[ac].cw_min == 0 ||
 		    params[ac].cw_min > params[ac].cw_max) {
 			sdata_info(sdata,
 				   "AP has invalid WMM params (CWmin/max=%d/%d for ACI %d), using defaults\n",
@@ -3814,16 +3815,19 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata)
 			    tx_flags);
 
 	if (tx_flags == 0) {
-		auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
-		auth_data->timeout_started = true;
-		run_again(sdata, auth_data->timeout);
+		if (auth_data->algorithm == WLAN_AUTH_SAE)
+			auth_data->timeout = jiffies +
+				IEEE80211_AUTH_TIMEOUT_SAE;
+		else
+			auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
 	} else {
 		auth_data->timeout =
 			round_jiffies_up(jiffies + IEEE80211_AUTH_TIMEOUT_LONG);
-		auth_data->timeout_started = true;
-		run_again(sdata, auth_data->timeout);
 	}
 
+	auth_data->timeout_started = true;
+	run_again(sdata, auth_data->timeout);
+
 	return 0;
 }
 
@@ -3894,8 +3898,15 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
 		ifmgd->status_received = false;
 		if (ifmgd->auth_data && ieee80211_is_auth(fc)) {
 			if (status_acked) {
-				ifmgd->auth_data->timeout =
-					jiffies + IEEE80211_AUTH_TIMEOUT_SHORT;
+				if (ifmgd->auth_data->algorithm ==
+				    WLAN_AUTH_SAE)
+					ifmgd->auth_data->timeout =
+						jiffies +
+						IEEE80211_AUTH_TIMEOUT_SAE;
+				else
+					ifmgd->auth_data->timeout =
+						jiffies +
+						IEEE80211_AUTH_TIMEOUT_SHORT;
 				run_again(sdata, ifmgd->auth_data->timeout);
 			} else {
 				ifmgd->auth_data->timeout = jiffies - 1;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 535de3161a78..05a265cd573d 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4,6 +4,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -1135,7 +1136,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
 	}
 
 	/* reset session timer */
-	if (reset_agg_timer && tid_tx->timeout)
+	if (reset_agg_timer)
 		tid_tx->last_tx = jiffies;
 
 	return queued;
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 8d7e849d4825..41cede4041d3 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -215,7 +215,7 @@ err:
 static int ncsi_pkg_info_all_nl(struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
-	struct nlattr *attrs[NCSI_ATTR_MAX];
+	struct nlattr *attrs[NCSI_ATTR_MAX + 1];
 	struct ncsi_package *np, *package;
 	struct ncsi_dev_priv *ndp;
 	unsigned int package_id;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 704b3832dbad..44d8a55e9721 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -594,6 +594,7 @@ config NFT_QUOTA
 config NFT_REJECT
 	default m if NETFILTER_ADVANCED=n
 	tristate "Netfilter nf_tables reject support"
+	depends on !NF_TABLES_INET || (IPV6!=m || m)
 	help
 	  This option adds the "reject" expression that you can use to
 	  explicitly deny and notify via TCP reset/ICMP informational errors
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 0f6b8172fb9a..206fb2c4c319 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -585,7 +585,8 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
 EXPORT_SYMBOL(nf_nat_decode_session_hook);
 #endif
 
-static void __net_init __netfilter_net_init(struct nf_hook_entries **e, int max)
+static void __net_init
+__netfilter_net_init(struct nf_hook_entries __rcu **e, int max)
 {
 	int h;
 
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 1c98c907bc63..c3db074fc1f7 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -587,25 +587,13 @@ static const struct seq_operations ip_vs_app_seq_ops = {
 	.stop  = ip_vs_app_seq_stop,
 	.show  = ip_vs_app_seq_show,
 };
-
-static int ip_vs_app_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ip_vs_app_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations ip_vs_app_fops = {
-	.open	 = ip_vs_app_open,
-	.read	 = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
 #endif
 
 int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs)
 {
 	INIT_LIST_HEAD(&ipvs->app_list);
-	proc_create("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_fops);
+	proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops,
+			sizeof(struct seq_net_private));
 	return 0;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 370abbf6f421..61c3a389da89 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -232,7 +232,10 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
 static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
 {
 	unsigned int hash;
-	bool ret;
+	bool ret = false;
+
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		return refcount_dec_if_one(&cp->refcnt);
 
 	hash = ip_vs_conn_hashkey_conn(cp);
 
@@ -240,15 +243,13 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
 	spin_lock(&cp->lock);
 
 	if (cp->flags & IP_VS_CONN_F_HASHED) {
-		ret = false;
 		/* Decrease refcnt and unlink conn only if we are last user */
 		if (refcount_dec_if_one(&cp->refcnt)) {
 			hlist_del_rcu(&cp->c_list);
 			cp->flags &= ~IP_VS_CONN_F_HASHED;
 			ret = true;
 		}
-	} else
-		ret = refcount_read(&cp->refcnt) ? false : true;
+	}
 
 	spin_unlock(&cp->lock);
 	ct_write_unlock_bh(hash);
@@ -454,12 +455,6 @@ ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
 }
 EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto);
 
-static void __ip_vs_conn_put_notimer(struct ip_vs_conn *cp)
-{
-	__ip_vs_conn_put(cp);
-	ip_vs_conn_expire(&cp->timer);
-}
-
 /*
  *      Put back the conn and restart its timer with its timeout
  */
@@ -478,7 +473,7 @@ void ip_vs_conn_put(struct ip_vs_conn *cp)
 	    (refcount_read(&cp->refcnt) == 1) &&
 	    !timer_pending(&cp->timer))
 		/* expire connection immediately */
-		__ip_vs_conn_put_notimer(cp);
+		ip_vs_conn_expire(&cp->timer);
 	else
 		__ip_vs_conn_put_timer(cp);
 }
@@ -1136,19 +1131,6 @@ static const struct seq_operations ip_vs_conn_seq_ops = {
 	.show  = ip_vs_conn_seq_show,
 };
 
-static int ip_vs_conn_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ip_vs_conn_seq_ops,
-			    sizeof(struct ip_vs_iter_state));
-}
-
-static const struct file_operations ip_vs_conn_fops = {
-	.open    = ip_vs_conn_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 static const char *ip_vs_origin_name(unsigned int flags)
 {
 	if (flags & IP_VS_CONN_F_SYNC)
@@ -1212,20 +1194,6 @@ static const struct seq_operations ip_vs_conn_sync_seq_ops = {
 	.stop  = ip_vs_conn_seq_stop,
 	.show  = ip_vs_conn_sync_seq_show,
 };
-
-static int ip_vs_conn_sync_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops,
-			    sizeof(struct ip_vs_iter_state));
-}
-
-static const struct file_operations ip_vs_conn_sync_fops = {
-	.open    = ip_vs_conn_sync_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 #endif
 
 
@@ -1385,9 +1353,11 @@ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs)
 {
 	atomic_set(&ipvs->conn_count, 0);
 
-	proc_create("ip_vs_conn", 0, ipvs->net->proc_net, &ip_vs_conn_fops);
-	proc_create("ip_vs_conn_sync", 0, ipvs->net->proc_net,
-		    &ip_vs_conn_sync_fops);
+	proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net,
+			&ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state));
+	proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net,
+			&ip_vs_conn_sync_seq_ops,
+			sizeof(struct ip_vs_iter_state));
 	return 0;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5f6f73cf2174..0679dd101e72 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -119,6 +119,8 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		struct ip_vs_cpu_stats *s;
 		struct ip_vs_service *svc;
 
+		local_bh_disable();
+
 		s = this_cpu_ptr(dest->stats.cpustats);
 		u64_stats_update_begin(&s->syncp);
 		s->cnt.inpkts++;
@@ -137,6 +139,8 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		s->cnt.inpkts++;
 		s->cnt.inbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
+
+		local_bh_enable();
 	}
 }
 
@@ -151,6 +155,8 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		struct ip_vs_cpu_stats *s;
 		struct ip_vs_service *svc;
 
+		local_bh_disable();
+
 		s = this_cpu_ptr(dest->stats.cpustats);
 		u64_stats_update_begin(&s->syncp);
 		s->cnt.outpkts++;
@@ -169,6 +175,8 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		s->cnt.outpkts++;
 		s->cnt.outbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
+
+		local_bh_enable();
 	}
 }
 
@@ -179,6 +187,8 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 	struct netns_ipvs *ipvs = svc->ipvs;
 	struct ip_vs_cpu_stats *s;
 
+	local_bh_disable();
+
 	s = this_cpu_ptr(cp->dest->stats.cpustats);
 	u64_stats_update_begin(&s->syncp);
 	s->cnt.conns++;
@@ -193,6 +203,8 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 	u64_stats_update_begin(&s->syncp);
 	s->cnt.conns++;
 	u64_stats_update_end(&s->syncp);
+
+	local_bh_enable();
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5ebde4b15810..141b1509c948 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2109,19 +2109,6 @@ static const struct seq_operations ip_vs_info_seq_ops = {
 	.show  = ip_vs_info_seq_show,
 };
 
-static int ip_vs_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ip_vs_info_seq_ops,
-			sizeof(struct ip_vs_iter));
-}
-
-static const struct file_operations ip_vs_info_fops = {
-	.open    = ip_vs_info_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 static int ip_vs_stats_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
@@ -2154,18 +2141,6 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int ip_vs_stats_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, ip_vs_stats_show);
-}
-
-static const struct file_operations ip_vs_stats_fops = {
-	.open = ip_vs_stats_seq_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release_net,
-};
-
 static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
@@ -2221,18 +2196,6 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, ip_vs_stats_percpu_show);
-}
-
-static const struct file_operations ip_vs_stats_percpu_fops = {
-	.open = ip_vs_stats_percpu_seq_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release_net,
-};
 #endif
 
 /*
@@ -2381,14 +2344,12 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 			struct ipvs_sync_daemon_cfg cfg;
 
 			memset(&cfg, 0, sizeof(cfg));
-			strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
-				sizeof(cfg.mcast_ifn));
+			ret = -EINVAL;
+			if (strscpy(cfg.mcast_ifn, dm->mcast_ifn,
+				    sizeof(cfg.mcast_ifn)) <= 0)
+				goto out_dec;
 			cfg.syncid = dm->syncid;
-			rtnl_lock();
-			mutex_lock(&ipvs->sync_mutex);
 			ret = start_sync_thread(ipvs, &cfg, dm->state);
-			mutex_unlock(&ipvs->sync_mutex);
-			rtnl_unlock();
 		} else {
 			mutex_lock(&ipvs->sync_mutex);
 			ret = stop_sync_thread(ipvs, dm->state);
@@ -2424,12 +2385,19 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		}
 	}
 
+	if ((cmd == IP_VS_SO_SET_ADD || cmd == IP_VS_SO_SET_EDIT) &&
+	    strnlen(usvc.sched_name, IP_VS_SCHEDNAME_MAXLEN) ==
+	    IP_VS_SCHEDNAME_MAXLEN) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	/* Check for valid protocol: TCP or UDP or SCTP, even for fwmark!=0 */
 	if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP &&
 	    usvc.protocol != IPPROTO_SCTP) {
-		pr_err("set_ctl: invalid protocol: %d %pI4:%d %s\n",
+		pr_err("set_ctl: invalid protocol: %d %pI4:%d\n",
 		       usvc.protocol, &usvc.addr.ip,
-		       ntohs(usvc.port), usvc.sched_name);
+		       ntohs(usvc.port));
 		ret = -EFAULT;
 		goto out_unlock;
 	}
@@ -2851,7 +2819,7 @@ static const struct nla_policy ip_vs_cmd_policy[IPVS_CMD_ATTR_MAX + 1] = {
 static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = {
 	[IPVS_DAEMON_ATTR_STATE]	= { .type = NLA_U32 },
 	[IPVS_DAEMON_ATTR_MCAST_IFN]	= { .type = NLA_NUL_STRING,
-					    .len = IP_VS_IFNAME_MAXLEN },
+					    .len = IP_VS_IFNAME_MAXLEN - 1 },
 	[IPVS_DAEMON_ATTR_SYNC_ID]	= { .type = NLA_U32 },
 	[IPVS_DAEMON_ATTR_SYNC_MAXLEN]	= { .type = NLA_U16 },
 	[IPVS_DAEMON_ATTR_MCAST_GROUP]	= { .type = NLA_U32 },
@@ -2869,7 +2837,7 @@ static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = {
 	[IPVS_SVC_ATTR_PORT]		= { .type = NLA_U16 },
 	[IPVS_SVC_ATTR_FWMARK]		= { .type = NLA_U32 },
 	[IPVS_SVC_ATTR_SCHED_NAME]	= { .type = NLA_NUL_STRING,
-					    .len = IP_VS_SCHEDNAME_MAXLEN },
+					    .len = IP_VS_SCHEDNAME_MAXLEN - 1 },
 	[IPVS_SVC_ATTR_PE_NAME]		= { .type = NLA_NUL_STRING,
 					    .len = IP_VS_PENAME_MAXLEN },
 	[IPVS_SVC_ATTR_FLAGS]		= { .type = NLA_BINARY,
@@ -3481,12 +3449,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
 	if (ipvs->mixed_address_family_dests > 0)
 		return -EINVAL;
 
-	rtnl_lock();
-	mutex_lock(&ipvs->sync_mutex);
 	ret = start_sync_thread(ipvs, &c,
 				nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
-	mutex_unlock(&ipvs->sync_mutex);
-	rtnl_unlock();
 	return ret;
 }
 
@@ -4038,10 +4002,12 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
 
 	spin_lock_init(&ipvs->tot_stats.lock);
 
-	proc_create("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_fops);
-	proc_create("ip_vs_stats", 0, ipvs->net->proc_net, &ip_vs_stats_fops);
-	proc_create("ip_vs_stats_percpu", 0, ipvs->net->proc_net,
-		    &ip_vs_stats_percpu_fops);
+	proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops,
+			sizeof(struct ip_vs_iter));
+	proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net,
+			ip_vs_stats_show, NULL);
+	proc_create_net_single("ip_vs_stats_percpu", 0, ipvs->net->proc_net,
+			ip_vs_stats_percpu_show, NULL);
 
 	if (ip_vs_control_net_init_sysctl(ipvs))
 		goto err;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index fbaf3bd05b2e..001501e25625 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -49,6 +49,7 @@
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 
 #include <asm/unaligned.h>		/* Used for ntoh_seq and hton_seq */
 
@@ -1360,15 +1361,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val)
 /*
  *      Specifiy default interface for outgoing multicasts
  */
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
 {
-	struct net_device *dev;
 	struct inet_sock *inet = inet_sk(sk);
-	struct net *net = sock_net(sk);
-
-	dev = __dev_get_by_name(net, ifname);
-	if (!dev)
-		return -ENODEV;
 
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
 		return -EINVAL;
@@ -1396,19 +1391,14 @@ static int set_mcast_if(struct sock *sk, char *ifname)
  *      in the in_addr structure passed in as a parameter.
  */
 static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
 {
-	struct net *net = sock_net(sk);
 	struct ip_mreqn mreq;
-	struct net_device *dev;
 	int ret;
 
 	memset(&mreq, 0, sizeof(mreq));
 	memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
 
-	dev = __dev_get_by_name(net, ifname);
-	if (!dev)
-		return -ENODEV;
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
 		return -EINVAL;
 
@@ -1423,15 +1413,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 
 #ifdef CONFIG_IP_VS_IPV6
 static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
-			     char *ifname)
+			     struct net_device *dev)
 {
-	struct net *net = sock_net(sk);
-	struct net_device *dev;
 	int ret;
 
-	dev = __dev_get_by_name(net, ifname);
-	if (!dev)
-		return -ENODEV;
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
 		return -EINVAL;
 
@@ -1443,24 +1428,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
 }
 #endif
 
-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
 {
-	struct net *net = sock_net(sock->sk);
-	struct net_device *dev;
 	__be32 addr;
 	struct sockaddr_in sin;
 
-	dev = __dev_get_by_name(net, ifname);
-	if (!dev)
-		return -ENODEV;
-
 	addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
 	if (!addr)
 		pr_err("You probably need to specify IP address on "
 		       "multicast interface.\n");
 
 	IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
-		  ifname, &addr);
+		  dev->name, &addr);
 
 	/* Now bind the socket with the address of multicast interface */
 	sin.sin_family	     = AF_INET;
@@ -1493,7 +1472,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
 /*
  *      Set up sending multicast socket over UDP
  */
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+			  struct net_device *dev, struct socket **sock_ret)
 {
 	/* multicast addr */
 	union ipvs_sockaddr mcast_addr;
@@ -1505,9 +1485,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
 				  IPPROTO_UDP, &sock);
 	if (result < 0) {
 		pr_err("Error during creation of socket; terminating\n");
-		return ERR_PTR(result);
+		goto error;
 	}
-	result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+	*sock_ret = sock;
+	result = set_mcast_if(sock->sk, dev);
 	if (result < 0) {
 		pr_err("Error setting outbound mcast interface\n");
 		goto error;
@@ -1522,7 +1503,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
 		set_sock_size(sock->sk, 1, result);
 
 	if (AF_INET == ipvs->mcfg.mcast_af)
-		result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+		result = bind_mcastif_addr(sock, dev);
 	else
 		result = 0;
 	if (result < 0) {
@@ -1538,19 +1519,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
 		goto error;
 	}
 
-	return sock;
+	return 0;
 
 error:
-	sock_release(sock);
-	return ERR_PTR(result);
+	return result;
 }
 
 
 /*
  *      Set up receiving multicast socket over UDP
  */
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
-					int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+			     struct net_device *dev, struct socket **sock_ret)
 {
 	/* multicast addr */
 	union ipvs_sockaddr mcast_addr;
@@ -1562,8 +1542,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
 				  IPPROTO_UDP, &sock);
 	if (result < 0) {
 		pr_err("Error during creation of socket; terminating\n");
-		return ERR_PTR(result);
+		goto error;
 	}
+	*sock_ret = sock;
 	/* it is equivalent to the REUSEADDR option in user-space */
 	sock->sk->sk_reuse = SK_CAN_REUSE;
 	result = sysctl_sync_sock_size(ipvs);
@@ -1571,7 +1552,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
 		set_sock_size(sock->sk, 0, result);
 
 	get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
-	sock->sk->sk_bound_dev_if = ifindex;
+	sock->sk->sk_bound_dev_if = dev->ifindex;
 	result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
 	if (result < 0) {
 		pr_err("Error binding to the multicast addr\n");
@@ -1582,21 +1563,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
 #ifdef CONFIG_IP_VS_IPV6
 	if (ipvs->bcfg.mcast_af == AF_INET6)
 		result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
-					   ipvs->bcfg.mcast_ifn);
+					   dev);
 	else
 #endif
 		result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
-					  ipvs->bcfg.mcast_ifn);
+					  dev);
 	if (result < 0) {
 		pr_err("Error joining to the multicast group\n");
 		goto error;
 	}
 
-	return sock;
+	return 0;
 
 error:
-	sock_release(sock);
-	return ERR_PTR(result);
+	return result;
 }
 
 
@@ -1778,13 +1758,12 @@ static int sync_thread_backup(void *data)
 int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		      int state)
 {
-	struct ip_vs_sync_thread_data *tinfo;
+	struct ip_vs_sync_thread_data *tinfo = NULL;
 	struct task_struct **array = NULL, *task;
-	struct socket *sock;
 	struct net_device *dev;
 	char *name;
 	int (*threadfn)(void *data);
-	int id, count, hlen;
+	int id = 0, count, hlen;
 	int result = -ENOMEM;
 	u16 mtu, min_mtu;
 
@@ -1792,6 +1771,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
 		  sizeof(struct ip_vs_sync_conn_v0));
 
+	/* Do not hold one mutex and then to block on another */
+	for (;;) {
+		rtnl_lock();
+		if (mutex_trylock(&ipvs->sync_mutex))
+			break;
+		rtnl_unlock();
+		mutex_lock(&ipvs->sync_mutex);
+		if (rtnl_trylock())
+			break;
+		mutex_unlock(&ipvs->sync_mutex);
+	}
+
 	if (!ipvs->sync_state) {
 		count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
 		ipvs->threads_mask = count - 1;
@@ -1810,7 +1801,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
 	if (!dev) {
 		pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
-		return -ENODEV;
+		result = -ENODEV;
+		goto out_early;
 	}
 	hlen = (AF_INET6 == c->mcast_af) ?
 	       sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
@@ -1827,26 +1819,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		c->sync_maxlen = mtu - hlen;
 
 	if (state == IP_VS_STATE_MASTER) {
+		result = -EEXIST;
 		if (ipvs->ms)
-			return -EEXIST;
+			goto out_early;
 
 		ipvs->mcfg = *c;
 		name = "ipvs-m:%d:%d";
 		threadfn = sync_thread_master;
 	} else if (state == IP_VS_STATE_BACKUP) {
+		result = -EEXIST;
 		if (ipvs->backup_threads)
-			return -EEXIST;
+			goto out_early;
 
 		ipvs->bcfg = *c;
 		name = "ipvs-b:%d:%d";
 		threadfn = sync_thread_backup;
 	} else {
-		return -EINVAL;
+		result = -EINVAL;
+		goto out_early;
 	}
 
 	if (state == IP_VS_STATE_MASTER) {
 		struct ipvs_master_sync_state *ms;
 
+		result = -ENOMEM;
 		ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL);
 		if (!ipvs->ms)
 			goto out;
@@ -1862,39 +1858,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	} else {
 		array = kcalloc(count, sizeof(struct task_struct *),
 				GFP_KERNEL);
+		result = -ENOMEM;
 		if (!array)
 			goto out;
 	}
 
-	tinfo = NULL;
 	for (id = 0; id < count; id++) {
-		if (state == IP_VS_STATE_MASTER)
-			sock = make_send_sock(ipvs, id);
-		else
-			sock = make_receive_sock(ipvs, id, dev->ifindex);
-		if (IS_ERR(sock)) {
-			result = PTR_ERR(sock);
-			goto outtinfo;
-		}
+		result = -ENOMEM;
 		tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
 		if (!tinfo)
-			goto outsocket;
+			goto out;
 		tinfo->ipvs = ipvs;
-		tinfo->sock = sock;
+		tinfo->sock = NULL;
 		if (state == IP_VS_STATE_BACKUP) {
 			tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
 					     GFP_KERNEL);
 			if (!tinfo->buf)
-				goto outtinfo;
+				goto out;
 		} else {
 			tinfo->buf = NULL;
 		}
 		tinfo->id = id;
+		if (state == IP_VS_STATE_MASTER)
+			result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+		else
+			result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+		if (result < 0)
+			goto out;
 
 		task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
 		if (IS_ERR(task)) {
 			result = PTR_ERR(task);
-			goto outtinfo;
+			goto out;
 		}
 		tinfo = NULL;
 		if (state == IP_VS_STATE_MASTER)
@@ -1911,20 +1906,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	ipvs->sync_state |= state;
 	spin_unlock_bh(&ipvs->sync_buff_lock);
 
+	mutex_unlock(&ipvs->sync_mutex);
+	rtnl_unlock();
+
 	/* increase the module use count */
 	ip_vs_use_count_inc();
 
 	return 0;
 
-outsocket:
-	sock_release(sock);
-
-outtinfo:
-	if (tinfo) {
-		sock_release(tinfo->sock);
-		kfree(tinfo->buf);
-		kfree(tinfo);
-	}
+out:
+	/* We do not need RTNL lock anymore, release it here so that
+	 * sock_release below and in the kthreads can use rtnl_lock
+	 * to leave the mcast group.
+	 */
+	rtnl_unlock();
 	count = id;
 	while (count-- > 0) {
 		if (state == IP_VS_STATE_MASTER)
@@ -1932,13 +1927,23 @@ outtinfo:
 		else
 			kthread_stop(array[count]);
 	}
-	kfree(array);
-
-out:
 	if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
 		kfree(ipvs->ms);
 		ipvs->ms = NULL;
 	}
+	mutex_unlock(&ipvs->sync_mutex);
+	if (tinfo) {
+		if (tinfo->sock)
+			sock_release(tinfo->sock);
+		kfree(tinfo->buf);
+		kfree(tinfo);
+	}
+	kfree(array);
+	return result;
+
+out_early:
+	mutex_unlock(&ipvs->sync_mutex);
+	rtnl_unlock();
 	return result;
 }
 
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 8ef21d9f9a00..853b23206bb7 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -252,7 +252,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
 static inline int expect_matches(const struct nf_conntrack_expect *a,
 				 const struct nf_conntrack_expect *b)
 {
-	return a->master == b->master && a->class == b->class &&
+	return a->master == b->master &&
 	       nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
 	       nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
 	       net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
@@ -421,6 +421,9 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
 	h = nf_ct_expect_dst_hash(net, &expect->tuple);
 	hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
 		if (expect_matches(i, expect)) {
+			if (i->class != expect->class)
+				return -EALREADY;
+
 			if (nf_ct_remove_expect(i))
 				break;
 		} else if (expect_clash(i, expect)) {
@@ -641,19 +644,6 @@ static const struct seq_operations exp_seq_ops = {
 	.stop = exp_seq_stop,
 	.show = exp_seq_show
 };
-
-static int exp_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &exp_seq_ops,
-			sizeof(struct ct_expect_iter_state));
-}
-
-static const struct file_operations exp_file_ops = {
-	.open    = exp_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
 #endif /* CONFIG_NF_CONNTRACK_PROCFS */
 
 static int exp_proc_init(struct net *net)
@@ -663,8 +653,8 @@ static int exp_proc_init(struct net *net)
 	kuid_t root_uid;
 	kgid_t root_gid;
 
-	proc = proc_create("nf_conntrack_expect", 0440, net->proc_net,
-			   &exp_file_ops);
+	proc = proc_create_net("nf_conntrack_expect", 0440, net->proc_net,
+			&exp_seq_ops, sizeof(struct ct_expect_iter_state));
 	if (!proc)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 9fe0ddc333fb..277bbfe26478 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -9,6 +9,7 @@
  *      2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
+#include <linux/kmemleak.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
@@ -71,6 +72,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 	rcu_read_unlock();
 
 	alloc = max(newlen, NF_CT_EXT_PREALLOC);
+	kmemleak_not_leak(old);
 	new = __krealloc(old, alloc, gfp);
 	if (!new)
 		return NULL;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index e97cdc1cf98c..8e67910185a0 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -981,6 +981,17 @@ static int tcp_packet(struct nf_conn *ct,
 			return NF_ACCEPT; /* Don't change state */
 		}
 		break;
+	case TCP_CONNTRACK_SYN_SENT2:
+		/* tcp_conntracks table is not smart enough to handle
+		 * simultaneous open.
+		 */
+		ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN;
+		break;
+	case TCP_CONNTRACK_SYN_RECV:
+		if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET &&
+		    ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN)
+			new_state = TCP_CONNTRACK_ESTABLISHED;
+		break;
 	case TCP_CONNTRACK_CLOSE:
 		if (index == TCP_RST_SET
 		    && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 4dbb5bad4363..908e51e2dc2b 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -938,11 +938,19 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 				       datalen, rtp_exp, rtcp_exp,
 				       mediaoff, medialen, daddr);
 	else {
-		if (nf_ct_expect_related(rtp_exp) == 0) {
-			if (nf_ct_expect_related(rtcp_exp) != 0)
-				nf_ct_unexpect_related(rtp_exp);
-			else
+		/* -EALREADY handling works around end-points that send
+		 * SDP messages with identical port but different media type,
+		 * we pretend expectation was set up.
+		 */
+		int errp = nf_ct_expect_related(rtp_exp);
+
+		if (errp == 0 || errp == -EALREADY) {
+			int errcp = nf_ct_expect_related(rtcp_exp);
+
+			if (errcp == 0 || errcp == -EALREADY)
 				ret = NF_ACCEPT;
+			else if (errp == 0)
+				nf_ct_unexpect_related(rtp_exp);
 		}
 	}
 	nf_ct_expect_put(rtcp_exp);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 037fec54c850..b642c0b2495c 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -375,19 +375,6 @@ static const struct seq_operations ct_seq_ops = {
 	.show  = ct_seq_show
 };
 
-static int ct_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ct_seq_ops,
-			sizeof(struct ct_iter_state));
-}
-
-static const struct file_operations ct_file_ops = {
-	.open    = ct_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 static void *ct_cpu_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct net *net = seq_file_net(seq);
@@ -467,26 +454,14 @@ static const struct seq_operations ct_cpu_seq_ops = {
 	.show	= ct_cpu_seq_show,
 };
 
-static int ct_cpu_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &ct_cpu_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations ct_cpu_seq_fops = {
-	.open	 = ct_cpu_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
 static int nf_conntrack_standalone_init_proc(struct net *net)
 {
 	struct proc_dir_entry *pde;
 	kuid_t root_uid;
 	kgid_t root_gid;
 
-	pde = proc_create("nf_conntrack", 0440, net->proc_net, &ct_file_ops);
+	pde = proc_create_net("nf_conntrack", 0440, net->proc_net, &ct_seq_ops,
+			sizeof(struct ct_iter_state));
 	if (!pde)
 		goto out_nf_conntrack;
 
@@ -495,8 +470,8 @@ static int nf_conntrack_standalone_init_proc(struct net *net)
 	if (uid_valid(root_uid) && gid_valid(root_gid))
 		proc_set_user(pde, root_uid, root_gid);
 
-	pde = proc_create("nf_conntrack", 0444, net->proc_net_stat,
-			  &ct_cpu_seq_fops);
+	pde = proc_create_net("nf_conntrack", 0444, net->proc_net_stat,
+			&ct_cpu_seq_ops, sizeof(struct seq_net_private));
 	if (!pde)
 		goto out_stat_nf_conntrack;
 	return 0;
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 6d0357817cda..426457047578 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -394,21 +394,6 @@ static const struct seq_operations nflog_seq_ops = {
 	.stop	= seq_stop,
 	.show	= seq_show,
 };
-
-static int nflog_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &nflog_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations nflog_file_ops = {
-	.open	 = nflog_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
-
 #endif /* PROC_FS */
 
 #ifdef CONFIG_SYSCTL
@@ -549,8 +534,8 @@ static int __net_init nf_log_net_init(struct net *net)
 	int ret = -ENOMEM;
 
 #ifdef CONFIG_PROC_FS
-	if (!proc_create("nf_log", 0444,
-			 net->nf.proc_netfilter, &nflog_file_ops))
+	if (!proc_create_net("nf_log", 0444, net->nf.proc_netfilter,
+			&nflog_seq_ops, sizeof(struct seq_net_private)))
 		return ret;
 #endif
 	ret = netfilter_log_sysctl_init(net);
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 6039b350abbe..8ff4d22f10b2 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -310,23 +310,10 @@ static const struct seq_operations synproxy_cpu_seq_ops = {
 	.show		= synproxy_cpu_seq_show,
 };
 
-static int synproxy_cpu_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &synproxy_cpu_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations synproxy_cpu_seq_fops = {
-	.open		= synproxy_cpu_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 static int __net_init synproxy_proc_init(struct net *net)
 {
-	if (!proc_create("synproxy", 0444, net->proc_net_stat,
-			 &synproxy_cpu_seq_fops))
+	if (!proc_create_net("synproxy", 0444, net->proc_net_stat,
+			&synproxy_cpu_seq_ops, sizeof(struct seq_net_private)))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9134cc429ad4..501e48a7965b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -214,6 +214,34 @@ static int nft_delchain(struct nft_ctx *ctx)
 	return err;
 }
 
+static void nft_rule_expr_activate(const struct nft_ctx *ctx,
+				   struct nft_rule *rule)
+{
+	struct nft_expr *expr;
+
+	expr = nft_expr_first(rule);
+	while (expr != nft_expr_last(rule) && expr->ops) {
+		if (expr->ops->activate)
+			expr->ops->activate(ctx, expr);
+
+		expr = nft_expr_next(expr);
+	}
+}
+
+static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
+				     struct nft_rule *rule)
+{
+	struct nft_expr *expr;
+
+	expr = nft_expr_first(rule);
+	while (expr != nft_expr_last(rule) && expr->ops) {
+		if (expr->ops->deactivate)
+			expr->ops->deactivate(ctx, expr);
+
+		expr = nft_expr_next(expr);
+	}
+}
+
 static int
 nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule)
 {
@@ -259,6 +287,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule)
 		nft_trans_destroy(trans);
 		return err;
 	}
+	nft_rule_expr_deactivate(ctx, rule);
 
 	return 0;
 }
@@ -1269,8 +1298,10 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain,
 		rcu_assign_pointer(chain->stats, newstats);
 		synchronize_rcu();
 		free_percpu(oldstats);
-	} else
+	} else {
 		rcu_assign_pointer(chain->stats, newstats);
+		static_branch_inc(&nft_counters_enabled);
+	}
 }
 
 static void nf_tables_chain_destroy(struct nft_ctx *ctx)
@@ -2238,6 +2269,13 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	kfree(rule);
 }
 
+static void nf_tables_rule_release(const struct nft_ctx *ctx,
+				   struct nft_rule *rule)
+{
+	nft_rule_expr_deactivate(ctx, rule);
+	nf_tables_rule_destroy(ctx, rule);
+}
+
 #define NFT_RULE_MAXEXPRS	128
 
 static struct nft_expr_info *info;
@@ -2361,43 +2399,48 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
-		if (nft_is_active_next(net, old_rule)) {
-			trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
-						   old_rule);
-			if (trans == NULL) {
-				err = -ENOMEM;
-				goto err2;
-			}
-			nft_deactivate_next(net, old_rule);
-			chain->use--;
-			list_add_tail_rcu(&rule->list, &old_rule->list);
-		} else {
+		if (!nft_is_active_next(net, old_rule)) {
 			err = -ENOENT;
 			goto err2;
 		}
-	} else if (nlh->nlmsg_flags & NLM_F_APPEND)
-		if (old_rule)
-			list_add_rcu(&rule->list, &old_rule->list);
-		else
-			list_add_tail_rcu(&rule->list, &chain->rules);
-	else {
-		if (old_rule)
-			list_add_tail_rcu(&rule->list, &old_rule->list);
-		else
-			list_add_rcu(&rule->list, &chain->rules);
-	}
+		trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+					   old_rule);
+		if (trans == NULL) {
+			err = -ENOMEM;
+			goto err2;
+		}
+		nft_deactivate_next(net, old_rule);
+		chain->use--;
 
-	if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
-		err = -ENOMEM;
-		goto err3;
+		if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+			err = -ENOMEM;
+			goto err2;
+		}
+
+		list_add_tail_rcu(&rule->list, &old_rule->list);
+	} else {
+		if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+			err = -ENOMEM;
+			goto err2;
+		}
+
+		if (nlh->nlmsg_flags & NLM_F_APPEND) {
+			if (old_rule)
+				list_add_rcu(&rule->list, &old_rule->list);
+			else
+				list_add_tail_rcu(&rule->list, &chain->rules);
+		 } else {
+			if (old_rule)
+				list_add_tail_rcu(&rule->list, &old_rule->list);
+			else
+				list_add_rcu(&rule->list, &chain->rules);
+		}
 	}
 	chain->use++;
 	return 0;
 
-err3:
-	list_del_rcu(&rule->list);
 err2:
-	nf_tables_rule_destroy(&ctx, rule);
+	nf_tables_rule_release(&ctx, rule);
 err1:
 	for (i = 0; i < n; i++) {
 		if (info[i].ops != NULL)
@@ -3207,18 +3250,20 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 
 	err = ops->init(set, &desc, nla);
 	if (err < 0)
-		goto err2;
+		goto err3;
 
 	err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
 	if (err < 0)
-		goto err3;
+		goto err4;
 
 	list_add_tail_rcu(&set->list, &table->sets);
 	table->use++;
 	return 0;
 
-err3:
+err4:
 	ops->destroy(set);
+err3:
+	kfree(set->name);
 err2:
 	kvfree(set);
 err1:
@@ -4037,8 +4082,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^
 			    nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) ||
 			    nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^
-			    nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF))
-				return -EBUSY;
+			    nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) {
+				err = -EBUSY;
+				goto err5;
+			}
 			if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
 			     nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) &&
 			     memcmp(nft_set_ext_data(ext),
@@ -4123,7 +4170,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
  *	NFT_GOTO verdicts. This function must be called on active data objects
  *	from the second phase of the commit protocol.
  */
-static void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
+void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
 {
 	if (type == NFT_DATA_VERDICT) {
 		switch (data->verdict.code) {
@@ -4661,7 +4708,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 			if (idx > s_idx)
 				memset(&cb->args[1], 0,
 				       sizeof(cb->args) - sizeof(cb->args[0]));
-			if (filter && filter->table[0] &&
+			if (filter && filter->table &&
 			    strcmp(filter->table, table->name))
 				goto cont;
 			if (filter &&
@@ -5335,7 +5382,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
 			if (idx > s_idx)
 				memset(&cb->args[1], 0,
 				       sizeof(cb->args) - sizeof(cb->args[0]));
-			if (filter && filter->table[0] &&
+			if (filter && filter->table &&
 			    strcmp(filter->table, table->name))
 				goto cont;
 
@@ -5738,7 +5785,7 @@ static void nft_chain_commit_update(struct nft_trans *trans)
 	struct nft_base_chain *basechain;
 
 	if (nft_trans_chain_name(trans))
-		strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
+		swap(trans->ctx.chain->name, nft_trans_chain_name(trans));
 
 	if (!nft_is_base_chain(trans->ctx.chain))
 		return;
@@ -5754,7 +5801,7 @@ static void nft_chain_commit_update(struct nft_trans *trans)
 	}
 }
 
-static void nf_tables_commit_release(struct nft_trans *trans)
+static void nft_commit_release(struct nft_trans *trans)
 {
 	switch (trans->msg_type) {
 	case NFT_MSG_DELTABLE:
@@ -5783,6 +5830,21 @@ static void nf_tables_commit_release(struct nft_trans *trans)
 	kfree(trans);
 }
 
+static void nf_tables_commit_release(struct net *net)
+{
+	struct nft_trans *trans, *next;
+
+	if (list_empty(&net->nft.commit_list))
+		return;
+
+	synchronize_rcu();
+
+	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+		list_del(&trans->list);
+		nft_commit_release(trans);
+	}
+}
+
 static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 {
 	struct nft_trans *trans, *next;
@@ -5913,13 +5975,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 		}
 	}
 
-	synchronize_rcu();
-
-	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
-		list_del(&trans->list);
-		nf_tables_commit_release(trans);
-	}
-
+	nf_tables_commit_release(net);
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
 
 	return 0;
@@ -5999,10 +6055,12 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb)
 		case NFT_MSG_NEWRULE:
 			trans->ctx.chain->use--;
 			list_del_rcu(&nft_trans_rule(trans)->list);
+			nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans));
 			break;
 		case NFT_MSG_DELRULE:
 			trans->ctx.chain->use++;
 			nft_clear(trans->ctx.net, nft_trans_rule(trans));
+			nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans));
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSET:
@@ -6578,7 +6636,7 @@ int __nft_release_basechain(struct nft_ctx *ctx)
 	list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) {
 		list_del(&rule->list);
 		ctx->chain->use--;
-		nf_tables_rule_destroy(ctx, rule);
+		nf_tables_rule_release(ctx, rule);
 	}
 	list_del(&ctx->chain->list);
 	ctx->table->use--;
@@ -6616,7 +6674,7 @@ static void __nft_release_tables(struct net *net)
 			list_for_each_entry_safe(rule, nr, &chain->rules, list) {
 				list_del(&rule->list);
 				chain->use--;
-				nf_tables_rule_destroy(&ctx, rule);
+				nf_tables_rule_release(&ctx, rule);
 			}
 		}
 		list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) {
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index dfd0bf3810d2..40e744572283 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -119,14 +119,21 @@ DEFINE_STATIC_KEY_FALSE(nft_counters_enabled);
 static noinline void nft_update_chain_stats(const struct nft_chain *chain,
 					    const struct nft_pktinfo *pkt)
 {
+	struct nft_base_chain *base_chain;
 	struct nft_stats *stats;
 
+	base_chain = nft_base_chain(chain);
+	if (!base_chain->stats)
+		return;
+
 	local_bh_disable();
-	stats = this_cpu_ptr(rcu_dereference(nft_base_chain(chain)->stats));
-	u64_stats_update_begin(&stats->syncp);
-	stats->pkts++;
-	stats->bytes += pkt->skb->len;
-	u64_stats_update_end(&stats->syncp);
+	stats = this_cpu_ptr(rcu_dereference(base_chain->stats));
+	if (stats) {
+		u64_stats_update_begin(&stats->syncp);
+		stats->pkts++;
+		stats->bytes += pkt->skb->len;
+		u64_stats_update_end(&stats->syncp);
+	}
 	local_bh_enable();
 }
 
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index b9505bcd3827..a0e5adf0b3b6 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -115,7 +115,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
 		nfacct->flags = flags;
 	}
 
-	strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX);
+	nla_strlcpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
 
 	if (tb[NFACCT_BYTES]) {
 		atomic64_set(&nfacct->bytes,
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 4a4b293fb2e5..cb5b5f207777 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -149,8 +149,8 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
 	    !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
 		return -EINVAL;
 
-	strncpy(expect_policy->name,
-		nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN);
+	nla_strlcpy(expect_policy->name,
+		    tb[NFCTH_POLICY_NAME], NF_CT_HELPER_NAME_LEN);
 	expect_policy->max_expected =
 		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
 	if (expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
@@ -234,7 +234,8 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 	if (ret < 0)
 		goto err1;
 
-	strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
+	nla_strlcpy(helper->name,
+		    tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN);
 	size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
 	if (size > FIELD_SIZEOF(struct nf_conn_help, data)) {
 		ret = -ENOMEM;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 7b46aa4c478d..c14822b9729f 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -1046,20 +1046,6 @@ static const struct seq_operations nful_seq_ops = {
 	.stop	= seq_stop,
 	.show	= seq_show,
 };
-
-static int nful_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &nful_seq_ops,
-			    sizeof(struct iter_state));
-}
-
-static const struct file_operations nful_file_ops = {
-	.open	 = nful_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
 #endif /* PROC_FS */
 
 static int __net_init nfnl_log_net_init(struct net *net)
@@ -1077,8 +1063,8 @@ static int __net_init nfnl_log_net_init(struct net *net)
 	spin_lock_init(&log->instances_lock);
 
 #ifdef CONFIG_PROC_FS
-	proc = proc_create("nfnetlink_log", 0440,
-			   net->nf.proc_netfilter, &nful_file_ops);
+	proc = proc_create_net("nfnetlink_log", 0440, net->nf.proc_netfilter,
+			&nful_seq_ops, sizeof(struct iter_state));
 	if (!proc)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 74a04638ef03..494a9ab35cb6 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1469,20 +1469,6 @@ static const struct seq_operations nfqnl_seq_ops = {
 	.stop	= seq_stop,
 	.show	= seq_show,
 };
-
-static int nfqnl_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &nfqnl_seq_ops,
-			sizeof(struct iter_state));
-}
-
-static const struct file_operations nfqnl_file_ops = {
-	.open	 = nfqnl_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
 #endif /* PROC_FS */
 
 static int __net_init nfnl_queue_net_init(struct net *net)
@@ -1496,8 +1482,8 @@ static int __net_init nfnl_queue_net_init(struct net *net)
 	spin_lock_init(&q->instances_lock);
 
 #ifdef CONFIG_PROC_FS
-	if (!proc_create("nfnetlink_queue", 0440,
-			 net->nf.proc_netfilter, &nfqnl_file_ops))
+	if (!proc_create_net("nfnetlink_queue", 0440, net->nf.proc_netfilter,
+			&nfqnl_seq_ops, sizeof(struct iter_state)))
 		return -ENOMEM;
 #endif
 	nf_register_queue_handler(net, &nfqh);
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 8e23726b9081..1d99a1efdafc 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -27,14 +27,31 @@ struct nft_xt {
 	struct list_head	head;
 	struct nft_expr_ops	ops;
 	unsigned int		refcnt;
+
+	/* Unlike other expressions, ops doesn't have static storage duration.
+	 * nft core assumes they do.  We use kfree_rcu so that nft core can
+	 * can check expr->ops->size even after nft_compat->destroy() frees
+	 * the nft_xt struct that holds the ops structure.
+	 */
+	struct rcu_head		rcu_head;
+};
+
+/* Used for matches where *info is larger than X byte */
+#define NFT_MATCH_LARGE_THRESH	192
+
+struct nft_xt_match_priv {
+	void *info;
 };
 
-static void nft_xt_put(struct nft_xt *xt)
+static bool nft_xt_put(struct nft_xt *xt)
 {
 	if (--xt->refcnt == 0) {
 		list_del(&xt->head);
-		kfree(xt);
+		kfree_rcu(xt, rcu_head);
+		return true;
 	}
+
+	return false;
 }
 
 static int nft_compat_chain_validate_dependency(const char *tablename,
@@ -226,6 +243,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	struct xt_target *target = expr->ops->data;
 	struct xt_tgchk_param par;
 	size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO]));
+	struct nft_xt *nft_xt;
 	u16 proto = 0;
 	bool inv = false;
 	union nft_entry e = {};
@@ -236,25 +254,22 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (ctx->nla[NFTA_RULE_COMPAT]) {
 		ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv);
 		if (ret < 0)
-			goto err;
+			return ret;
 	}
 
 	nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv);
 
 	ret = xt_check_target(&par, size, proto, inv);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	/* The standard target cannot be used */
-	if (target->target == NULL) {
-		ret = -EINVAL;
-		goto err;
-	}
+	if (!target->target)
+		return -EINVAL;
 
+	nft_xt = container_of(expr->ops, struct nft_xt, ops);
+	nft_xt->refcnt++;
 	return 0;
-err:
-	module_put(target->me);
-	return ret;
 }
 
 static void
@@ -271,8 +286,8 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
 	if (par.target->destroy != NULL)
 		par.target->destroy(&par);
 
-	nft_xt_put(container_of(expr->ops, struct nft_xt, ops));
-	module_put(target->me);
+	if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
+		module_put(target->me);
 }
 
 static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr)
@@ -316,11 +331,11 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 	return 0;
 }
 
-static void nft_match_eval(const struct nft_expr *expr,
-			   struct nft_regs *regs,
-			   const struct nft_pktinfo *pkt)
+static void __nft_match_eval(const struct nft_expr *expr,
+			     struct nft_regs *regs,
+			     const struct nft_pktinfo *pkt,
+			     void *info)
 {
-	void *info = nft_expr_priv(expr);
 	struct xt_match *match = expr->ops->data;
 	struct sk_buff *skb = pkt->skb;
 	bool ret;
@@ -344,6 +359,22 @@ static void nft_match_eval(const struct nft_expr *expr,
 	}
 }
 
+static void nft_match_large_eval(const struct nft_expr *expr,
+				 struct nft_regs *regs,
+				 const struct nft_pktinfo *pkt)
+{
+	struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+
+	__nft_match_eval(expr, regs, pkt, priv->info);
+}
+
+static void nft_match_eval(const struct nft_expr *expr,
+			   struct nft_regs *regs,
+			   const struct nft_pktinfo *pkt)
+{
+	__nft_match_eval(expr, regs, pkt, nft_expr_priv(expr));
+}
+
 static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
 	[NFTA_MATCH_NAME]	= { .type = NLA_NUL_STRING },
 	[NFTA_MATCH_REV]	= { .type = NLA_U32 },
@@ -404,13 +435,14 @@ static void match_compat_from_user(struct xt_match *m, void *in, void *out)
 }
 
 static int
-nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		const struct nlattr * const tb[])
+__nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+		 const struct nlattr * const tb[],
+		 void *info)
 {
-	void *info = nft_expr_priv(expr);
 	struct xt_match *match = expr->ops->data;
 	struct xt_mtchk_param par;
 	size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO]));
+	struct nft_xt *nft_xt;
 	u16 proto = 0;
 	bool inv = false;
 	union nft_entry e = {};
@@ -421,26 +453,50 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (ctx->nla[NFTA_RULE_COMPAT]) {
 		ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv);
 		if (ret < 0)
-			goto err;
+			return ret;
 	}
 
 	nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
 
 	ret = xt_check_match(&par, size, proto, inv);
 	if (ret < 0)
-		goto err;
+		return ret;
 
+	nft_xt = container_of(expr->ops, struct nft_xt, ops);
+	nft_xt->refcnt++;
 	return 0;
-err:
-	module_put(match->me);
+}
+
+static int
+nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+	       const struct nlattr * const tb[])
+{
+	return __nft_match_init(ctx, expr, tb, nft_expr_priv(expr));
+}
+
+static int
+nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+		     const struct nlattr * const tb[])
+{
+	struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+	struct xt_match *m = expr->ops->data;
+	int ret;
+
+	priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL);
+	if (!priv->info)
+		return -ENOMEM;
+
+	ret = __nft_match_init(ctx, expr, tb, priv->info);
+	if (ret)
+		kfree(priv->info);
 	return ret;
 }
 
 static void
-nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+__nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
+		    void *info)
 {
 	struct xt_match *match = expr->ops->data;
-	void *info = nft_expr_priv(expr);
 	struct xt_mtdtor_param par;
 
 	par.net = ctx->net;
@@ -450,13 +506,28 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
 	if (par.match->destroy != NULL)
 		par.match->destroy(&par);
 
-	nft_xt_put(container_of(expr->ops, struct nft_xt, ops));
-	module_put(match->me);
+	if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
+		module_put(match->me);
 }
 
-static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static void
+nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+	__nft_match_destroy(ctx, expr, nft_expr_priv(expr));
+}
+
+static void
+nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+	struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+
+	__nft_match_destroy(ctx, expr, priv->info);
+	kfree(priv->info);
+}
+
+static int __nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr,
+			    void *info)
 {
-	void *info = nft_expr_priv(expr);
 	struct xt_match *match = expr->ops->data;
 
 	if (nla_put_string(skb, NFTA_MATCH_NAME, match->name) ||
@@ -470,6 +541,18 @@ nla_put_failure:
 	return -1;
 }
 
+static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	return __nft_match_dump(skb, expr, nft_expr_priv(expr));
+}
+
+static int nft_match_large_dump(struct sk_buff *skb, const struct nft_expr *e)
+{
+	struct nft_xt_match_priv *priv = nft_expr_priv(e);
+
+	return __nft_match_dump(skb, e, priv->info);
+}
+
 static int nft_match_validate(const struct nft_ctx *ctx,
 			      const struct nft_expr *expr,
 			      const struct nft_data **data)
@@ -637,6 +720,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 {
 	struct nft_xt *nft_match;
 	struct xt_match *match;
+	unsigned int matchsize;
 	char *mt_name;
 	u32 rev, family;
 	int err;
@@ -654,13 +738,8 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	list_for_each_entry(nft_match, &nft_match_list, head) {
 		struct xt_match *match = nft_match->ops.data;
 
-		if (nft_match_cmp(match, mt_name, rev, family)) {
-			if (!try_module_get(match->me))
-				return ERR_PTR(-ENOENT);
-
-			nft_match->refcnt++;
+		if (nft_match_cmp(match, mt_name, rev, family))
 			return &nft_match->ops;
-		}
 	}
 
 	match = xt_request_find_match(family, mt_name, rev);
@@ -679,9 +758,8 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	nft_match->refcnt = 1;
+	nft_match->refcnt = 0;
 	nft_match->ops.type = &nft_match_type;
-	nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
 	nft_match->ops.eval = nft_match_eval;
 	nft_match->ops.init = nft_match_init;
 	nft_match->ops.destroy = nft_match_destroy;
@@ -689,6 +767,18 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	nft_match->ops.validate = nft_match_validate;
 	nft_match->ops.data = match;
 
+	matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
+	if (matchsize > NFT_MATCH_LARGE_THRESH) {
+		matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv));
+
+		nft_match->ops.eval = nft_match_large_eval;
+		nft_match->ops.init = nft_match_large_init;
+		nft_match->ops.destroy = nft_match_large_destroy;
+		nft_match->ops.dump = nft_match_large_dump;
+	}
+
+	nft_match->ops.size = matchsize;
+
 	list_add(&nft_match->head, &nft_match_list);
 
 	return &nft_match->ops;
@@ -739,13 +829,8 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	list_for_each_entry(nft_target, &nft_target_list, head) {
 		struct xt_target *target = nft_target->ops.data;
 
-		if (nft_target_cmp(target, tg_name, rev, family)) {
-			if (!try_module_get(target->me))
-				return ERR_PTR(-ENOENT);
-
-			nft_target->refcnt++;
+		if (nft_target_cmp(target, tg_name, rev, family))
 			return &nft_target->ops;
-		}
 	}
 
 	target = xt_request_find_target(family, tg_name, rev);
@@ -764,7 +849,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	nft_target->refcnt = 1;
+	nft_target->refcnt = 0;
 	nft_target->ops.type = &nft_target_type;
 	nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
 	nft_target->ops.init = nft_target_init;
@@ -823,6 +908,32 @@ err_match:
 
 static void __exit nft_compat_module_exit(void)
 {
+	struct nft_xt *xt, *next;
+
+	/* list should be empty here, it can be non-empty only in case there
+	 * was an error that caused nft_xt expr to not be initialized fully
+	 * and noone else requested the same expression later.
+	 *
+	 * In this case, the lists contain 0-refcount entries that still
+	 * hold module reference.
+	 */
+	list_for_each_entry_safe(xt, next, &nft_target_list, head) {
+		struct xt_target *target = xt->ops.data;
+
+		if (WARN_ON_ONCE(xt->refcnt))
+			continue;
+		module_put(target->me);
+		kfree(xt);
+	}
+
+	list_for_each_entry_safe(xt, next, &nft_match_list, head) {
+		struct xt_match *match = xt->ops.data;
+
+		if (WARN_ON_ONCE(xt->refcnt))
+			continue;
+		module_put(match->me);
+		kfree(xt);
+	}
 	nfnetlink_subsys_unregister(&nfnl_compat_subsys);
 	nft_unregister_expr(&nft_target_type);
 	nft_unregister_expr(&nft_match_type);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index ea737fd789e8..5c0de704bad5 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -880,22 +880,26 @@ static int nft_ct_helper_obj_dump(struct sk_buff *skb,
 				  struct nft_object *obj, bool reset)
 {
 	const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
-	const struct nf_conntrack_helper *helper = priv->helper4;
+	const struct nf_conntrack_helper *helper;
 	u16 family;
 
+	if (priv->helper4 && priv->helper6) {
+		family = NFPROTO_INET;
+		helper = priv->helper4;
+	} else if (priv->helper6) {
+		family = NFPROTO_IPV6;
+		helper = priv->helper6;
+	} else {
+		family = NFPROTO_IPV4;
+		helper = priv->helper4;
+	}
+
 	if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name))
 		return -1;
 
 	if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto))
 		return -1;
 
-	if (priv->helper4 && priv->helper6)
-		family = NFPROTO_INET;
-	else if (priv->helper6)
-		family = NFPROTO_IPV6;
-	else
-		family = NFPROTO_IPV4;
-
 	if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family)))
 		return -1;
 
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 4717d7796927..aa87ff8beae8 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -69,8 +69,16 @@ err1:
 	return err;
 }
 
-static void nft_immediate_destroy(const struct nft_ctx *ctx,
-				  const struct nft_expr *expr)
+static void nft_immediate_activate(const struct nft_ctx *ctx,
+				   const struct nft_expr *expr)
+{
+	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+	return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg));
+}
+
+static void nft_immediate_deactivate(const struct nft_ctx *ctx,
+				     const struct nft_expr *expr)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
 
@@ -108,7 +116,8 @@ static const struct nft_expr_ops nft_imm_ops = {
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
 	.eval		= nft_immediate_eval,
 	.init		= nft_immediate_init,
-	.destroy	= nft_immediate_destroy,
+	.activate	= nft_immediate_activate,
+	.deactivate	= nft_immediate_deactivate,
 	.dump		= nft_immediate_dump,
 	.validate	= nft_immediate_validate,
 };
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index a9fc298ef4c3..72f13a1144dd 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -51,10 +51,13 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost)
 	return !limit->invert;
 }
 
+/* Use same default as in iptables. */
+#define NFT_LIMIT_PKT_BURST_DEFAULT	5
+
 static int nft_limit_init(struct nft_limit *limit,
-			  const struct nlattr * const tb[])
+			  const struct nlattr * const tb[], bool pkts)
 {
-	u64 unit;
+	u64 unit, tokens;
 
 	if (tb[NFTA_LIMIT_RATE] == NULL ||
 	    tb[NFTA_LIMIT_UNIT] == NULL)
@@ -68,18 +71,25 @@ static int nft_limit_init(struct nft_limit *limit,
 
 	if (tb[NFTA_LIMIT_BURST])
 		limit->burst = ntohl(nla_get_be32(tb[NFTA_LIMIT_BURST]));
-	else
-		limit->burst = 0;
+
+	if (pkts && limit->burst == 0)
+		limit->burst = NFT_LIMIT_PKT_BURST_DEFAULT;
 
 	if (limit->rate + limit->burst < limit->rate)
 		return -EOVERFLOW;
 
-	/* The token bucket size limits the number of tokens can be
-	 * accumulated. tokens_max specifies the bucket size.
-	 * tokens_max = unit * (rate + burst) / rate.
-	 */
-	limit->tokens = div_u64(limit->nsecs * (limit->rate + limit->burst),
-				limit->rate);
+	if (pkts) {
+		tokens = div_u64(limit->nsecs, limit->rate) * limit->burst;
+	} else {
+		/* The token bucket size limits the number of tokens can be
+		 * accumulated. tokens_max specifies the bucket size.
+		 * tokens_max = unit * (rate + burst) / rate.
+		 */
+		tokens = div_u64(limit->nsecs * (limit->rate + limit->burst),
+				 limit->rate);
+	}
+
+	limit->tokens = tokens;
 	limit->tokens_max = limit->tokens;
 
 	if (tb[NFTA_LIMIT_FLAGS]) {
@@ -144,7 +154,7 @@ static int nft_limit_pkts_init(const struct nft_ctx *ctx,
 	struct nft_limit_pkts *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_limit_init(&priv->limit, tb);
+	err = nft_limit_init(&priv->limit, tb, true);
 	if (err < 0)
 		return err;
 
@@ -185,7 +195,7 @@ static int nft_limit_bytes_init(const struct nft_ctx *ctx,
 {
 	struct nft_limit *priv = nft_expr_priv(expr);
 
-	return nft_limit_init(priv, tb);
+	return nft_limit_init(priv, tb, false);
 }
 
 static int nft_limit_bytes_dump(struct sk_buff *skb,
@@ -246,7 +256,7 @@ static int nft_limit_obj_pkts_init(const struct nft_ctx *ctx,
 	struct nft_limit_pkts *priv = nft_obj_data(obj);
 	int err;
 
-	err = nft_limit_init(&priv->limit, tb);
+	err = nft_limit_init(&priv->limit, tb, true);
 	if (err < 0)
 		return err;
 
@@ -289,7 +299,7 @@ static int nft_limit_obj_bytes_init(const struct nft_ctx *ctx,
 {
 	struct nft_limit *priv = nft_obj_data(obj);
 
-	return nft_limit_init(priv, tb);
+	return nft_limit_init(priv, tb, false);
 }
 
 static int nft_limit_obj_bytes_dump(struct sk_buff *skb,
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 8fb91940e2e7..204af9899482 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -234,7 +234,7 @@ void nft_meta_set_eval(const struct nft_expr *expr,
 	struct sk_buff *skb = pkt->skb;
 	u32 *sreg = &regs->data[meta->sreg];
 	u32 value = *sreg;
-	u8 pkt_type;
+	u8 value8;
 
 	switch (meta->key) {
 	case NFT_META_MARK:
@@ -244,15 +244,17 @@ void nft_meta_set_eval(const struct nft_expr *expr,
 		skb->priority = value;
 		break;
 	case NFT_META_PKTTYPE:
-		pkt_type = nft_reg_load8(sreg);
+		value8 = nft_reg_load8(sreg);
 
-		if (skb->pkt_type != pkt_type &&
-		    skb_pkt_type_ok(pkt_type) &&
+		if (skb->pkt_type != value8 &&
+		    skb_pkt_type_ok(value8) &&
 		    skb_pkt_type_ok(skb->pkt_type))
-			skb->pkt_type = pkt_type;
+			skb->pkt_type = value8;
 		break;
 	case NFT_META_NFTRACE:
-		skb->nf_trace = !!value;
+		value8 = nft_reg_load8(sreg);
+
+		skb->nf_trace = !!value8;
 		break;
 	default:
 		WARN_ON(1);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 71325fef647d..55cb4d197184 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -183,6 +183,9 @@ struct xt_match *xt_find_match(u8 af, const char *name, u8 revision)
 	struct xt_match *m;
 	int err = -ENOENT;
 
+	if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN)
+		return ERR_PTR(-EINVAL);
+
 	mutex_lock(&xt[af].mutex);
 	list_for_each_entry(m, &xt[af].match, list) {
 		if (strcmp(m->name, name) == 0) {
@@ -229,6 +232,9 @@ struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
 	struct xt_target *t;
 	int err = -ENOENT;
 
+	if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN)
+		return ERR_PTR(-EINVAL);
+
 	mutex_lock(&xt[af].mutex);
 	list_for_each_entry(t, &xt[af].target, list) {
 		if (strcmp(t->name, name) == 0) {
@@ -1489,15 +1495,10 @@ void *xt_unregister_table(struct xt_table *table)
 EXPORT_SYMBOL_GPL(xt_unregister_table);
 
 #ifdef CONFIG_PROC_FS
-struct xt_names_priv {
-	struct seq_net_private p;
-	u_int8_t af;
-};
 static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	struct xt_names_priv *priv = seq->private;
 	struct net *net = seq_file_net(seq);
-	u_int8_t af = priv->af;
+	u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file));
 
 	mutex_lock(&xt[af].mutex);
 	return seq_list_start(&net->xt.tables[af], *pos);
@@ -1505,17 +1506,15 @@ static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos)
 
 static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct xt_names_priv *priv = seq->private;
 	struct net *net = seq_file_net(seq);
-	u_int8_t af = priv->af;
+	u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file));
 
 	return seq_list_next(v, &net->xt.tables[af], pos);
 }
 
 static void xt_table_seq_stop(struct seq_file *seq, void *v)
 {
-	struct xt_names_priv *priv = seq->private;
-	u_int8_t af = priv->af;
+	u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file));
 
 	mutex_unlock(&xt[af].mutex);
 }
@@ -1536,34 +1535,13 @@ static const struct seq_operations xt_table_seq_ops = {
 	.show	= xt_table_seq_show,
 };
 
-static int xt_table_open(struct inode *inode, struct file *file)
-{
-	int ret;
-	struct xt_names_priv *priv;
-
-	ret = seq_open_net(inode, file, &xt_table_seq_ops,
-			   sizeof(struct xt_names_priv));
-	if (!ret) {
-		priv = ((struct seq_file *)file->private_data)->private;
-		priv->af = (unsigned long)PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static const struct file_operations xt_table_ops = {
-	.open	 = xt_table_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
 /*
  * Traverse state for ip{,6}_{tables,matches} for helping crossing
  * the multi-AF mutexes.
  */
 struct nf_mttg_trav {
 	struct list_head *head, *curr;
-	uint8_t class, nfproto;
+	uint8_t class;
 };
 
 enum {
@@ -1580,6 +1558,7 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
 		[MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC,
 		[MTTG_TRAV_NFP_SPEC]   = MTTG_TRAV_DONE,
 	};
+	uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file));
 	struct nf_mttg_trav *trav = seq->private;
 
 	switch (trav->class) {
@@ -1594,9 +1573,9 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
 		if (trav->curr != trav->head)
 			break;
 		mutex_unlock(&xt[NFPROTO_UNSPEC].mutex);
-		mutex_lock(&xt[trav->nfproto].mutex);
+		mutex_lock(&xt[nfproto].mutex);
 		trav->head = trav->curr = is_target ?
-			&xt[trav->nfproto].target : &xt[trav->nfproto].match;
+			&xt[nfproto].target : &xt[nfproto].match;
 		trav->class = next_class[trav->class];
 		break;
 	case MTTG_TRAV_NFP_SPEC:
@@ -1628,6 +1607,7 @@ static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos,
 
 static void xt_mttg_seq_stop(struct seq_file *seq, void *v)
 {
+	uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file));
 	struct nf_mttg_trav *trav = seq->private;
 
 	switch (trav->class) {
@@ -1635,7 +1615,7 @@ static void xt_mttg_seq_stop(struct seq_file *seq, void *v)
 		mutex_unlock(&xt[NFPROTO_UNSPEC].mutex);
 		break;
 	case MTTG_TRAV_NFP_SPEC:
-		mutex_unlock(&xt[trav->nfproto].mutex);
+		mutex_unlock(&xt[nfproto].mutex);
 		break;
 	}
 }
@@ -1674,24 +1654,6 @@ static const struct seq_operations xt_match_seq_ops = {
 	.show	= xt_match_seq_show,
 };
 
-static int xt_match_open(struct inode *inode, struct file *file)
-{
-	struct nf_mttg_trav *trav;
-	trav = __seq_open_private(file, &xt_match_seq_ops, sizeof(*trav));
-	if (!trav)
-		return -ENOMEM;
-
-	trav->nfproto = (unsigned long)PDE_DATA(inode);
-	return 0;
-}
-
-static const struct file_operations xt_match_ops = {
-	.open	 = xt_match_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_private,
-};
-
 static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	return xt_mttg_seq_start(seq, pos, true);
@@ -1726,24 +1688,6 @@ static const struct seq_operations xt_target_seq_ops = {
 	.show	= xt_target_seq_show,
 };
 
-static int xt_target_open(struct inode *inode, struct file *file)
-{
-	struct nf_mttg_trav *trav;
-	trav = __seq_open_private(file, &xt_target_seq_ops, sizeof(*trav));
-	if (!trav)
-		return -ENOMEM;
-
-	trav->nfproto = (unsigned long)PDE_DATA(inode);
-	return 0;
-}
-
-static const struct file_operations xt_target_ops = {
-	.open	 = xt_target_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_private,
-};
-
 #define FORMAT_TABLES	"_tables_names"
 #define	FORMAT_MATCHES	"_tables_matches"
 #define FORMAT_TARGETS 	"_tables_targets"
@@ -1807,8 +1751,9 @@ int xt_proto_init(struct net *net, u_int8_t af)
 
 	strlcpy(buf, xt_prefix[af], sizeof(buf));
 	strlcat(buf, FORMAT_TABLES, sizeof(buf));
-	proc = proc_create_data(buf, 0440, net->proc_net, &xt_table_ops,
-				(void *)(unsigned long)af);
+	proc = proc_create_net_data(buf, 0440, net->proc_net, &xt_table_seq_ops,
+			sizeof(struct seq_net_private),
+			(void *)(unsigned long)af);
 	if (!proc)
 		goto out;
 	if (uid_valid(root_uid) && gid_valid(root_gid))
@@ -1816,8 +1761,9 @@ int xt_proto_init(struct net *net, u_int8_t af)
 
 	strlcpy(buf, xt_prefix[af], sizeof(buf));
 	strlcat(buf, FORMAT_MATCHES, sizeof(buf));
-	proc = proc_create_data(buf, 0440, net->proc_net, &xt_match_ops,
-				(void *)(unsigned long)af);
+	proc = proc_create_seq_private(buf, 0440, net->proc_net,
+			&xt_match_seq_ops, sizeof(struct nf_mttg_trav),
+			(void *)(unsigned long)af);
 	if (!proc)
 		goto out_remove_tables;
 	if (uid_valid(root_uid) && gid_valid(root_gid))
@@ -1825,8 +1771,9 @@ int xt_proto_init(struct net *net, u_int8_t af)
 
 	strlcpy(buf, xt_prefix[af], sizeof(buf));
 	strlcat(buf, FORMAT_TARGETS, sizeof(buf));
-	proc = proc_create_data(buf, 0440, net->proc_net, &xt_target_ops,
-				(void *)(unsigned long)af);
+	proc = proc_create_seq_private(buf, 0440, net->proc_net,
+			 &xt_target_seq_ops, sizeof(struct nf_mttg_trav),
+			 (void *)(unsigned long)af);
 	if (!proc)
 		goto out_remove_matches;
 	if (uid_valid(root_uid) && gid_valid(root_gid))
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 773da82190dc..94df000abb92 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -36,11 +36,10 @@ MODULE_ALIAS("ipt_connmark");
 MODULE_ALIAS("ip6t_connmark");
 
 static unsigned int
-connmark_tg_shift(struct sk_buff *skb,
-		const struct xt_connmark_tginfo1 *info,
-		u8 shift_bits, u8 shift_dir)
+connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
 {
 	enum ip_conntrack_info ctinfo;
+	u_int32_t new_targetmark;
 	struct nf_conn *ct;
 	u_int32_t newmark;
 
@@ -51,34 +50,39 @@ connmark_tg_shift(struct sk_buff *skb,
 	switch (info->mode) {
 	case XT_CONNMARK_SET:
 		newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
-		if (shift_dir == D_SHIFT_RIGHT)
-			newmark >>= shift_bits;
+		if (info->shift_dir == D_SHIFT_RIGHT)
+			newmark >>= info->shift_bits;
 		else
-			newmark <<= shift_bits;
+			newmark <<= info->shift_bits;
+
 		if (ct->mark != newmark) {
 			ct->mark = newmark;
 			nf_conntrack_event_cache(IPCT_MARK, ct);
 		}
 		break;
 	case XT_CONNMARK_SAVE:
-		newmark = (ct->mark & ~info->ctmask) ^
-			  (skb->mark & info->nfmask);
-		if (shift_dir == D_SHIFT_RIGHT)
-			newmark >>= shift_bits;
+		new_targetmark = (skb->mark & info->nfmask);
+		if (info->shift_dir == D_SHIFT_RIGHT)
+			new_targetmark >>= info->shift_bits;
 		else
-			newmark <<= shift_bits;
+			new_targetmark <<= info->shift_bits;
+
+		newmark = (ct->mark & ~info->ctmask) ^
+			  new_targetmark;
 		if (ct->mark != newmark) {
 			ct->mark = newmark;
 			nf_conntrack_event_cache(IPCT_MARK, ct);
 		}
 		break;
 	case XT_CONNMARK_RESTORE:
-		newmark = (skb->mark & ~info->nfmask) ^
-			  (ct->mark & info->ctmask);
-		if (shift_dir == D_SHIFT_RIGHT)
-			newmark >>= shift_bits;
+		new_targetmark = (ct->mark & info->ctmask);
+		if (info->shift_dir == D_SHIFT_RIGHT)
+			new_targetmark >>= info->shift_bits;
 		else
-			newmark <<= shift_bits;
+			new_targetmark <<= info->shift_bits;
+
+		newmark = (skb->mark & ~info->nfmask) ^
+			  new_targetmark;
 		skb->mark = newmark;
 		break;
 	}
@@ -89,8 +93,14 @@ static unsigned int
 connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct xt_connmark_tginfo1 *info = par->targinfo;
-
-	return connmark_tg_shift(skb, info, 0, 0);
+	const struct xt_connmark_tginfo2 info2 = {
+		.ctmark	= info->ctmark,
+		.ctmask	= info->ctmask,
+		.nfmask	= info->nfmask,
+		.mode	= info->mode,
+	};
+
+	return connmark_tg_shift(skb, &info2);
 }
 
 static unsigned int
@@ -98,8 +108,7 @@ connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct xt_connmark_tginfo2 *info = par->targinfo;
 
-	return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info,
-				 info->shift_bits, info->shift_dir);
+	return connmark_tg_shift(skb, info);
 }
 
 static int connmark_tg_check(const struct xt_tgchk_param *par)
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 0cd73567e7ff..9b16402f29af 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -57,9 +57,9 @@ static inline struct hashlimit_net *hashlimit_pernet(struct net *net)
 }
 
 /* need to declare this at the top */
-static const struct file_operations dl_file_ops_v2;
-static const struct file_operations dl_file_ops_v1;
-static const struct file_operations dl_file_ops;
+static const struct seq_operations dl_seq_ops_v2;
+static const struct seq_operations dl_seq_ops_v1;
+static const struct seq_operations dl_seq_ops;
 
 /* hash table crap */
 struct dsthash_dst {
@@ -272,7 +272,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
 {
 	struct hashlimit_net *hashlimit_net = hashlimit_pernet(net);
 	struct xt_hashlimit_htable *hinfo;
-	const struct file_operations *fops;
+	const struct seq_operations *ops;
 	unsigned int size, i;
 	int ret;
 
@@ -321,19 +321,19 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
 
 	switch (revision) {
 	case 1:
-		fops = &dl_file_ops_v1;
+		ops = &dl_seq_ops_v1;
 		break;
 	case 2:
-		fops = &dl_file_ops_v2;
+		ops = &dl_seq_ops_v2;
 		break;
 	default:
-		fops = &dl_file_ops;
+		ops = &dl_seq_ops;
 	}
 
-	hinfo->pde = proc_create_data(name, 0,
+	hinfo->pde = proc_create_seq_data(name, 0,
 		(family == NFPROTO_IPV4) ?
 		hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit,
-		fops, hinfo);
+		ops, hinfo);
 	if (hinfo->pde == NULL) {
 		kfree(hinfo->name);
 		vfree(hinfo);
@@ -1057,7 +1057,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
 static void *dl_seq_start(struct seq_file *s, loff_t *pos)
 	__acquires(htable->lock)
 {
-	struct xt_hashlimit_htable *htable = s->private;
+	struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
 	unsigned int *bucket;
 
 	spin_lock_bh(&htable->lock);
@@ -1074,7 +1074,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos)
 
 static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
-	struct xt_hashlimit_htable *htable = s->private;
+	struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
 	unsigned int *bucket = v;
 
 	*pos = ++(*bucket);
@@ -1088,7 +1088,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos)
 static void dl_seq_stop(struct seq_file *s, void *v)
 	__releases(htable->lock)
 {
-	struct xt_hashlimit_htable *htable = s->private;
+	struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
 	unsigned int *bucket = v;
 
 	if (!IS_ERR(bucket))
@@ -1130,7 +1130,7 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family,
 static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family,
 			       struct seq_file *s)
 {
-	const struct xt_hashlimit_htable *ht = s->private;
+	struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private));
 
 	spin_lock(&ent->lock);
 	/* recalculate to show accurate numbers */
@@ -1145,7 +1145,7 @@ static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family,
 static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family,
 			       struct seq_file *s)
 {
-	const struct xt_hashlimit_htable *ht = s->private;
+	struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private));
 
 	spin_lock(&ent->lock);
 	/* recalculate to show accurate numbers */
@@ -1160,7 +1160,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family,
 static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family,
 			    struct seq_file *s)
 {
-	const struct xt_hashlimit_htable *ht = s->private;
+	struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private));
 
 	spin_lock(&ent->lock);
 	/* recalculate to show accurate numbers */
@@ -1174,7 +1174,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family,
 
 static int dl_seq_show_v2(struct seq_file *s, void *v)
 {
-	struct xt_hashlimit_htable *htable = s->private;
+	struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
 	unsigned int *bucket = (unsigned int *)v;
 	struct dsthash_ent *ent;
 
@@ -1188,7 +1188,7 @@ static int dl_seq_show_v2(struct seq_file *s, void *v)
 
 static int dl_seq_show_v1(struct seq_file *s, void *v)
 {
-	struct xt_hashlimit_htable *htable = s->private;
+	struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
 	unsigned int *bucket = v;
 	struct dsthash_ent *ent;
 
@@ -1202,7 +1202,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v)
 
 static int dl_seq_show(struct seq_file *s, void *v)
 {
-	struct xt_hashlimit_htable *htable = s->private;
+	struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
 	unsigned int *bucket = v;
 	struct dsthash_ent *ent;
 
@@ -1235,62 +1235,6 @@ static const struct seq_operations dl_seq_ops = {
 	.show  = dl_seq_show
 };
 
-static int dl_proc_open_v2(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &dl_seq_ops_v2);
-
-	if (!ret) {
-		struct seq_file *sf = file->private_data;
-
-		sf->private = PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static int dl_proc_open_v1(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &dl_seq_ops_v1);
-
-	if (!ret) {
-		struct seq_file *sf = file->private_data;
-		sf->private = PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static int dl_proc_open(struct inode *inode, struct file *file)
-{
-	int ret = seq_open(file, &dl_seq_ops);
-
-	if (!ret) {
-		struct seq_file *sf = file->private_data;
-
-		sf->private = PDE_DATA(inode);
-	}
-	return ret;
-}
-
-static const struct file_operations dl_file_ops_v2 = {
-	.open    = dl_proc_open_v2,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release
-};
-
-static const struct file_operations dl_file_ops_v1 = {
-	.open    = dl_proc_open_v1,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release
-};
-
-static const struct file_operations dl_file_ops = {
-	.open    = dl_proc_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release
-};
-
 static int __net_init hashlimit_proc_net_init(struct net *net)
 {
 	struct hashlimit_net *hashlimit_net = hashlimit_pernet(net);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 55342c4d5cec..1189b84413d5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2606,13 +2606,13 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 {
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
-			 "sk       Eth Pid    Groups   "
-			 "Rmem     Wmem     Dump     Locks     Drops     Inode\n");
+			 "sk               Eth Pid        Groups   "
+			 "Rmem     Wmem     Dump  Locks    Drops    Inode\n");
 	} else {
 		struct sock *s = v;
 		struct netlink_sock *nlk = nlk_sk(s);
 
-		seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %d %-8d %-8d %-8lu\n",
+		seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8d %-8lu\n",
 			   s,
 			   s->sk_protocol,
 			   nlk->portid,
@@ -2635,21 +2635,6 @@ static const struct seq_operations netlink_seq_ops = {
 	.stop   = netlink_seq_stop,
 	.show   = netlink_seq_show,
 };
-
-
-static int netlink_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &netlink_seq_ops,
-				sizeof(struct nl_seq_iter));
-}
-
-static const struct file_operations netlink_seq_fops = {
-	.open		= netlink_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 #endif
 
 int netlink_register_notifier(struct notifier_block *nb)
@@ -2673,7 +2658,7 @@ static const struct proto_ops netlink_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	netlink_getname,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	netlink_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -2694,7 +2679,8 @@ static const struct net_proto_family netlink_family_ops = {
 static int __net_init netlink_net_init(struct net *net)
 {
 #ifdef CONFIG_PROC_FS
-	if (!proc_create("netlink", 0, net->proc_net, &netlink_seq_fops))
+	if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops,
+			sizeof(struct nl_seq_iter)))
 		return -ENOMEM;
 #endif
 	return 0;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 4221d98a314b..b97eb766a1d5 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1338,18 +1338,6 @@ static const struct seq_operations nr_info_seqops = {
 	.stop = nr_info_stop,
 	.show = nr_info_show,
 };
-
-static int nr_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &nr_info_seqops);
-}
-
-static const struct file_operations nr_info_fops = {
-	.open = nr_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
 #endif	/* CONFIG_PROC_FS */
 
 static const struct net_proto_family nr_family_ops = {
@@ -1367,7 +1355,7 @@ static const struct proto_ops nr_proto_ops = {
 	.socketpair	=	sock_no_socketpair,
 	.accept		=	nr_accept,
 	.getname	=	nr_getname,
-	.poll		=	datagram_poll,
+	.poll_mask	=	datagram_poll_mask,
 	.ioctl		=	nr_ioctl,
 	.listen		=	nr_listen,
 	.shutdown	=	sock_no_shutdown,
@@ -1450,9 +1438,9 @@ static int __init nr_proto_init(void)
 
 	nr_loopback_init();
 
-	proc_create("nr", 0444, init_net.proc_net, &nr_info_fops);
-	proc_create("nr_neigh", 0444, init_net.proc_net, &nr_neigh_fops);
-	proc_create("nr_nodes", 0444, init_net.proc_net, &nr_nodes_fops);
+	proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops);
+	proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops);
+	proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops);
 out:
 	return rc;
 fail:
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index b5a7dcb30991..6485f593e2f0 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -888,25 +888,13 @@ static int nr_node_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations nr_node_seqops = {
+const struct seq_operations nr_node_seqops = {
 	.start = nr_node_start,
 	.next = nr_node_next,
 	.stop = nr_node_stop,
 	.show = nr_node_show,
 };
 
-static int nr_node_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &nr_node_seqops);
-}
-
-const struct file_operations nr_nodes_fops = {
-	.open = nr_node_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 static void *nr_neigh_start(struct seq_file *seq, loff_t *pos)
 {
 	spin_lock_bh(&nr_neigh_list_lock);
@@ -954,25 +942,12 @@ static int nr_neigh_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations nr_neigh_seqops = {
+const struct seq_operations nr_neigh_seqops = {
 	.start = nr_neigh_start,
 	.next = nr_neigh_next,
 	.stop = nr_neigh_stop,
 	.show = nr_neigh_show,
 };
-
-static int nr_neigh_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &nr_neigh_seqops);
-}
-
-const struct file_operations nr_neigh_fops = {
-	.open = nr_neigh_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 #endif
 
 /*
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index ea0c0c6f1874..ab5bb14b49af 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -548,16 +548,13 @@ static inline __poll_t llcp_accept_poll(struct sock *parent)
 	return 0;
 }
 
-static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
-				   poll_table *wait)
+static __poll_t llcp_sock_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
 	pr_debug("%p\n", sk);
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
-
 	if (sk->sk_state == LLCP_LISTEN)
 		return llcp_accept_poll(sk);
 
@@ -899,7 +896,7 @@ static const struct proto_ops llcp_sock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = llcp_sock_accept,
 	.getname        = llcp_sock_getname,
-	.poll           = llcp_sock_poll,
+	.poll_mask      = llcp_sock_poll_mask,
 	.ioctl          = sock_no_ioctl,
 	.listen         = llcp_sock_listen,
 	.shutdown       = sock_no_shutdown,
@@ -919,7 +916,7 @@ static const struct proto_ops llcp_rawsock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = llcp_sock_getname,
-	.poll           = llcp_sock_poll,
+	.poll_mask      = llcp_sock_poll_mask,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index e2188deb08dc..60c322531c49 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -284,7 +284,7 @@ static const struct proto_ops rawsock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = sock_no_getname,
-	.poll           = datagram_poll,
+	.poll_mask      = datagram_poll_mask,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,
@@ -304,7 +304,7 @@ static const struct proto_ops rawsock_raw_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = sock_no_getname,
-	.poll           = datagram_poll,
+	.poll_mask      = datagram_poll_mask,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,
diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c
index d7da99a0b0b8..9696ef96b719 100644
--- a/net/nsh/nsh.c
+++ b/net/nsh/nsh.c
@@ -57,6 +57,8 @@ int nsh_pop(struct sk_buff *skb)
 		return -ENOMEM;
 	nh = (struct nshhdr *)(skb->data);
 	length = nsh_hdr_len(nh);
+	if (length < NSH_BASE_HDR_LEN)
+		return -EINVAL;
 	inner_proto = tun_p_to_eth_p(nh->np);
 	if (!pskb_may_pull(skb, length))
 		return -ENOMEM;
@@ -90,6 +92,8 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb,
 	if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN)))
 		goto out;
 	nsh_len = nsh_hdr_len(nsh_hdr(skb));
+	if (nsh_len < NSH_BASE_HDR_LEN)
+		goto out;
 	if (unlikely(!pskb_may_pull(skb, nsh_len)))
 		goto out;
 
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 7322aa1e382e..492ab0c36f7c 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1712,13 +1712,10 @@ static void nlattr_set(struct nlattr *attr, u8 val,
 
 	/* The nlattr stream should already have been validated */
 	nla_for_each_nested(nla, attr, rem) {
-		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
-			if (tbl[nla_type(nla)].next)
-				tbl = tbl[nla_type(nla)].next;
-			nlattr_set(nla, val, tbl);
-		} else {
+		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
+			nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl);
+		else
 			memset(nla_data(nla), val, nla_len(nla));
-		}
 
 		if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE)
 			*(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 616cb9c18f88..674390b1f084 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -329,11 +329,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
 	skb_set_queue_mapping(skb, queue_index);
 }
 
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
  * or from a context in which asynchronous accesses to the packet
  * socket is not possible (packet_create()).
  */
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
 
@@ -348,8 +348,13 @@ static void register_prot_hook(struct sock *sk)
 	}
 }
 
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held.   If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+	lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+	__register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
  * the po->bind_lock and do a synchronize_net to make sure no
  * asynchronous packet processing paths still refer to the elements
  * of po->prot_hook.  If the sync parameter is false, it is the
@@ -359,6 +364,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
 {
 	struct packet_sock *po = pkt_sk(sk);
 
+	lockdep_assert_held_once(&po->bind_lock);
+
 	po->running = 0;
 
 	if (po->fanout)
@@ -2896,13 +2903,15 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (skb == NULL)
 		goto out_unlock;
 
-	skb_set_network_header(skb, reserve);
+	skb_reset_network_header(skb);
 
 	err = -EINVAL;
 	if (sock->type == SOCK_DGRAM) {
 		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
 		if (unlikely(offset < 0))
 			goto out_free;
+	} else if (reserve) {
+		skb_reserve(skb, -reserve);
 	}
 
 	/* Returns -EFAULT on error */
@@ -3008,6 +3017,7 @@ static int packet_release(struct socket *sock)
 
 	packet_flush_mclist(sk);
 
+	lock_sock(sk);
 	if (po->rx_ring.pg_vec) {
 		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 0);
@@ -3017,6 +3027,7 @@ static int packet_release(struct socket *sock)
 		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 1);
 	}
+	release_sock(sk);
 
 	f = fanout_release(sk);
 
@@ -3250,7 +3261,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 
 	if (proto) {
 		po->prot_hook.type = proto;
-		register_prot_hook(sk);
+		__register_prot_hook(sk);
 	}
 
 	mutex_lock(&net->packet.sklist_lock);
@@ -3643,6 +3654,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		union tpacket_req_u req_u;
 		int len;
 
+		lock_sock(sk);
 		switch (po->tp_version) {
 		case TPACKET_V1:
 		case TPACKET_V2:
@@ -3653,12 +3665,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			len = sizeof(req_u.req3);
 			break;
 		}
-		if (optlen < len)
-			return -EINVAL;
-		if (copy_from_user(&req_u.req, optval, len))
-			return -EFAULT;
-		return packet_set_ring(sk, &req_u, 0,
-			optname == PACKET_TX_RING);
+		if (optlen < len) {
+			ret = -EINVAL;
+		} else {
+			if (copy_from_user(&req_u.req, optval, len))
+				ret = -EFAULT;
+			else
+				ret = packet_set_ring(sk, &req_u, 0,
+						    optname == PACKET_TX_RING);
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_COPY_THRESH:
 	{
@@ -3724,12 +3741,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
-		po->tp_loss = !!val;
-		return 0;
+
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_loss = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_AUXDATA:
 	{
@@ -3740,7 +3763,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
+		lock_sock(sk);
 		po->auxdata = !!val;
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_ORIGDEV:
@@ -3752,7 +3777,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
+		lock_sock(sk);
 		po->origdev = !!val;
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_VNET_HDR:
@@ -3761,15 +3788,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (sock->type != SOCK_RAW)
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (optlen < sizeof(val))
 			return -EINVAL;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
-		po->has_vnet_hdr = !!val;
-		return 0;
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->has_vnet_hdr = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_TIMESTAMP:
 	{
@@ -3807,11 +3839,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
-		po->tp_tx_has_off = !!val;
+
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_tx_has_off = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_QDISC_BYPASS:
@@ -4072,12 +4110,11 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd,
 	return 0;
 }
 
-static __poll_t packet_poll(struct file *file, struct socket *sock,
-				poll_table *wait)
+static __poll_t packet_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = datagram_poll_mask(sock, events);
 
 	spin_lock_bh(&sk->sk_receive_queue.lock);
 	if (po->rx_ring.pg_vec) {
@@ -4208,8 +4245,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	/* Added to avoid minimal code churn */
 	struct tpacket_req *req = &req_u->req;
 
-	lock_sock(sk);
-
 	rb = tx_ring ? &po->tx_ring : &po->rx_ring;
 	rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
@@ -4347,7 +4382,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
-	release_sock(sk);
 	return err;
 }
 
@@ -4422,7 +4456,7 @@ static const struct proto_ops packet_ops_spkt = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	packet_getname_spkt,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	packet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -4443,7 +4477,7 @@ static const struct proto_ops packet_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	packet_getname,
-	.poll =		packet_poll,
+	.poll_mask =	packet_poll_mask,
 	.ioctl =	packet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -4521,20 +4555,6 @@ static const struct seq_operations packet_seq_ops = {
 	.stop	= packet_seq_stop,
 	.show	= packet_seq_show,
 };
-
-static int packet_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &packet_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations packet_seq_fops = {
-	.open		= packet_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 #endif
 
 static int __net_init packet_net_init(struct net *net)
@@ -4542,7 +4562,8 @@ static int __net_init packet_net_init(struct net *net)
 	mutex_init(&net->packet.sklist_lock);
 	INIT_HLIST_HEAD(&net->packet.sklist);
 
-	if (!proc_create("packet", 0, net->proc_net, &packet_seq_fops))
+	if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops,
+			sizeof(struct seq_net_private)))
 		return -ENOMEM;
 
 	return 0;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index a1d2b2319ae9..3bb7c5fb3bff 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -112,10 +112,12 @@ struct packet_sock {
 	int			copy_thresh;
 	spinlock_t		bind_lock;
 	struct mutex		pg_vec_lock;
-	unsigned int		running:1,	/* prot_hook is attached*/
-				auxdata:1,
+	unsigned int		running;	/* bind_lock must be held */
+	unsigned int		auxdata:1,	/* writer must hold sock lock */
 				origdev:1,
-				has_vnet_hdr:1;
+				has_vnet_hdr:1,
+				tp_loss:1,
+				tp_tx_has_off:1;
 	int			pressure;
 	int			ifindex;	/* bound device		*/
 	__be16			num;
@@ -125,8 +127,6 @@ struct packet_sock {
 	enum tpacket_versions	tp_version;
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
-	unsigned int		tp_loss:1;
-	unsigned int		tp_tx_has_off:1;
 	unsigned int		tp_tstamp;
 	struct net_device __rcu	*cached_dev;
 	int			(*xmit)(struct sk_buff *skb);
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 77787512fc32..6cb4f602ab71 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -320,7 +320,8 @@ static int __net_init phonet_init_net(struct net *net)
 {
 	struct phonet_net *pnn = phonet_pernet(net);
 
-	if (!proc_create("phonet", 0, net->proc_net, &pn_sock_seq_fops))
+	if (!proc_create_net("phonet", 0, net->proc_net, &pn_sock_seq_ops,
+			sizeof(struct seq_net_private)))
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&pnn->pndevs.list);
@@ -351,7 +352,8 @@ int __init phonet_device_init(void)
 	if (err)
 		return err;
 
-	proc_create("pnresource", 0, init_net.proc_net, &pn_res_seq_fops);
+	proc_create_net("pnresource", 0, init_net.proc_net, &pn_res_seq_ops,
+			sizeof(struct seq_net_private));
 	register_netdevice_notifier(&phonet_device_notifier);
 	err = phonet_netlink_register();
 	if (err)
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index f9b40e6a18a5..c295c4e20f01 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -340,15 +340,12 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
 	return sizeof(struct sockaddr_pn);
 }
 
-static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
-					poll_table *wait)
+static __poll_t pn_socket_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct pep_sock *pn = pep_sk(sk);
 	__poll_t mask = 0;
 
-	poll_wait(file, sk_sleep(sk), wait);
-
 	if (sk->sk_state == TCP_CLOSE)
 		return EPOLLERR;
 	if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -448,7 +445,7 @@ const struct proto_ops phonet_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pn_socket_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.ioctl		= pn_socket_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
@@ -473,7 +470,7 @@ const struct proto_ops phonet_stream_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= pn_socket_accept,
 	.getname	= pn_socket_getname,
-	.poll		= pn_socket_poll,
+	.poll_mask	= pn_socket_poll_mask,
 	.ioctl		= pn_socket_ioctl,
 	.listen		= pn_socket_listen,
 	.shutdown	= sock_no_shutdown,
@@ -620,25 +617,12 @@ static int pn_sock_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations pn_sock_seq_ops = {
+const struct seq_operations pn_sock_seq_ops = {
 	.start = pn_sock_seq_start,
 	.next = pn_sock_seq_next,
 	.stop = pn_sock_seq_stop,
 	.show = pn_sock_seq_show,
 };
-
-static int pn_sock_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &pn_sock_seq_ops,
-				sizeof(struct seq_net_private));
-}
-
-const struct file_operations pn_sock_seq_fops = {
-	.open = pn_sock_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release_net,
-};
 #endif
 
 static struct  {
@@ -802,23 +786,10 @@ static int pn_res_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations pn_res_seq_ops = {
+const struct seq_operations pn_res_seq_ops = {
 	.start = pn_res_seq_start,
 	.next = pn_res_seq_next,
 	.stop = pn_res_seq_stop,
 	.show = pn_res_seq_show,
 };
-
-static int pn_res_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &pn_res_seq_ops,
-				sizeof(struct seq_net_private));
-}
-
-const struct file_operations pn_res_seq_fops = {
-	.open = pn_res_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release_net,
-};
 #endif
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index b33e5aeb4c06..1b5025ea5b04 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1023,7 +1023,7 @@ static const struct proto_ops qrtr_proto_ops = {
 	.recvmsg	= qrtr_recvmsg,
 	.getname	= qrtr_getname,
 	.ioctl		= qrtr_ioctl,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
 	.getsockopt	= sock_no_getsockopt,
@@ -1135,3 +1135,4 @@ module_exit(qrtr_proto_fini);
 
 MODULE_DESCRIPTION("Qualcomm IPC-router driver");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_NETPROTO(PF_QIPCRTR);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index eea1d8611b20..13b38ad0fa4a 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -547,7 +547,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
 		 ic->i_send_cq, ic->i_recv_cq);
 
-	return ret;
+	goto out;
 
 sends_out:
 	vfree(ic->i_sends);
@@ -572,6 +572,7 @@ send_cq_out:
 		ic->i_send_cq = NULL;
 rds_ibdev_out:
 	rds_ib_remove_conn(rds_ibdev, conn);
+out:
 	rds_ib_dev_put(rds_ibdev);
 
 	return ret;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index de50e2126e40..dc67458b52f0 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -558,6 +558,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg,
 		struct rds_cmsg_rx_trace t;
 		int i, j;
 
+		memset(&t, 0, sizeof(t));
 		inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock();
 		t.rx_traces =  rs->rs_rx_traces;
 		for (i = 0; i < rs->rs_rx_traces; i++) {
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 41bd496531d4..00192a996be0 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -137,13 +137,18 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 
 	ret = rfkill_register(rfkill->rfkill_dev);
 	if (ret < 0)
-		return ret;
+		goto err_destroy;
 
 	platform_set_drvdata(pdev, rfkill);
 
 	dev_info(&pdev->dev, "%s device registered.\n", rfkill->name);
 
 	return 0;
+
+err_destroy:
+	rfkill_destroy(rfkill->rfkill_dev);
+
+	return ret;
 }
 
 static int rfkill_gpio_remove(struct platform_device *pdev)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 9ff5e0a76593..5b73fea849df 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1453,18 +1453,6 @@ static const struct seq_operations rose_info_seqops = {
 	.stop = rose_info_stop,
 	.show = rose_info_show,
 };
-
-static int rose_info_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &rose_info_seqops);
-}
-
-static const struct file_operations rose_info_fops = {
-	.open = rose_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
 #endif	/* CONFIG_PROC_FS */
 
 static const struct net_proto_family rose_family_ops = {
@@ -1482,7 +1470,7 @@ static const struct proto_ops rose_proto_ops = {
 	.socketpair	=	sock_no_socketpair,
 	.accept		=	rose_accept,
 	.getname	=	rose_getname,
-	.poll		=	datagram_poll,
+	.poll_mask	=	datagram_poll_mask,
 	.ioctl		=	rose_ioctl,
 	.listen		=	rose_listen,
 	.shutdown	=	sock_no_shutdown,
@@ -1567,13 +1555,13 @@ static int __init rose_proto_init(void)
 
 	rose_add_loopback_neigh();
 
-	proc_create("rose", 0444, init_net.proc_net, &rose_info_fops);
-	proc_create("rose_neigh", 0444, init_net.proc_net,
-		    &rose_neigh_fops);
-	proc_create("rose_nodes", 0444, init_net.proc_net,
-		    &rose_nodes_fops);
-	proc_create("rose_routes", 0444, init_net.proc_net,
-		    &rose_routes_fops);
+	proc_create_seq("rose", 0444, init_net.proc_net, &rose_info_seqops);
+	proc_create_seq("rose_neigh", 0444, init_net.proc_net,
+		    &rose_neigh_seqops);
+	proc_create_seq("rose_nodes", 0444, init_net.proc_net,
+		    &rose_node_seqops);
+	proc_create_seq("rose_routes", 0444, init_net.proc_net,
+		    &rose_route_seqops);
 out:
 	return rc;
 fail:
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 178619ddab68..77e9f85a2c92 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -1143,25 +1143,13 @@ static int rose_node_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations rose_node_seqops = {
+const struct seq_operations rose_node_seqops = {
 	.start = rose_node_start,
 	.next = rose_node_next,
 	.stop = rose_node_stop,
 	.show = rose_node_show,
 };
 
-static int rose_nodes_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &rose_node_seqops);
-}
-
-const struct file_operations rose_nodes_fops = {
-	.open = rose_nodes_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 static void *rose_neigh_start(struct seq_file *seq, loff_t *pos)
 	__acquires(rose_neigh_list_lock)
 {
@@ -1226,26 +1214,13 @@ static int rose_neigh_show(struct seq_file *seq, void *v)
 }
 
 
-static const struct seq_operations rose_neigh_seqops = {
+const struct seq_operations rose_neigh_seqops = {
 	.start = rose_neigh_start,
 	.next = rose_neigh_next,
 	.stop = rose_neigh_stop,
 	.show = rose_neigh_show,
 };
 
-static int rose_neigh_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &rose_neigh_seqops);
-}
-
-const struct file_operations rose_neigh_fops = {
-	.open = rose_neigh_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
-
 static void *rose_route_start(struct seq_file *seq, loff_t *pos)
 	__acquires(rose_route_list_lock)
 {
@@ -1311,25 +1286,12 @@ static int rose_route_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations rose_route_seqops = {
+struct seq_operations rose_route_seqops = {
 	.start = rose_route_start,
 	.next = rose_route_next,
 	.stop = rose_route_stop,
 	.show = rose_route_show,
 };
-
-static int rose_route_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &rose_route_seqops);
-}
-
-const struct file_operations rose_routes_fops = {
-	.open = rose_route_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
-
 #endif /* CONFIG_PROC_FS */
 
 /*
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 9a2c8e7c000e..3b1ac93efee2 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -313,7 +313,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
 	cp.key			= key;
-	cp.security_level	= 0;
+	cp.security_level	= rx->min_sec_level;
 	cp.exclusive		= false;
 	cp.upgrade		= upgrade;
 	cp.service_id		= srx->srx_service;
@@ -734,15 +734,11 @@ static int rxrpc_getsockopt(struct socket *sock, int level, int optname,
 /*
  * permit an RxRPC socket to be polled
  */
-static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
-			       poll_table *wait)
+static __poll_t rxrpc_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct rxrpc_sock *rx = rxrpc_sk(sk);
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	__poll_t mask = 0;
 
 	/* the socket is readable if there are any messages waiting on the Rx
 	 * queue */
@@ -949,7 +945,7 @@ static const struct proto_ops rxrpc_rpc_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= sock_no_getname,
-	.poll		= rxrpc_poll,
+	.poll_mask	= rxrpc_poll_mask,
 	.ioctl		= sock_no_ioctl,
 	.listen		= rxrpc_listen,
 	.shutdown	= rxrpc_shutdown,
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 90d7079e0aa9..29923ec2189c 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -476,6 +476,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_SEND_PING,		/* A ping will need to be sent */
 	RXRPC_CALL_PINGING,		/* Ping in process */
 	RXRPC_CALL_RETRANS_TIMEOUT,	/* Retransmission due to timeout occurred */
+	RXRPC_CALL_BEGAN_RX_TIMER,	/* We began the expect_rx_by timer */
 };
 
 /*
@@ -1050,8 +1051,8 @@ void __rxrpc_queue_peer_error(struct rxrpc_peer *);
 /*
  * proc.c
  */
-extern const struct file_operations rxrpc_call_seq_fops;
-extern const struct file_operations rxrpc_connection_seq_fops;
+extern const struct seq_operations rxrpc_call_seq_ops;
+extern const struct seq_operations rxrpc_connection_seq_ops;
 
 /*
  * recvmsg.c
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index c717152070df..1350f1be8037 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -40,7 +40,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	} __attribute__((packed)) pkt;
 	struct rxrpc_ackinfo ack_info;
 	size_t len;
-	int ioc;
+	int ret, ioc;
 	u32 serial, mtu, call_id, padding;
 
 	_enter("%d", conn->debug_id);
@@ -135,10 +135,13 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 		break;
 	}
 
-	kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
+	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
 	conn->params.peer->last_tx_at = ktime_get_real();
+	if (ret < 0)
+		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+				    rxrpc_tx_fail_call_final_resend);
+
 	_leave("");
-	return;
 }
 
 /*
@@ -236,6 +239,8 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
 	if (ret < 0) {
+		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+				    rxrpc_tx_fail_conn_abort);
 		_debug("sendmsg failed: %d", ret);
 		return -EAGAIN;
 	}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 0410d2277ca2..b5fd6381313d 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -971,7 +971,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
 	if (timo) {
 		unsigned long now = jiffies, expect_rx_by;
 
-		expect_rx_by = jiffies + timo;
+		expect_rx_by = now + timo;
 		WRITE_ONCE(call->expect_rx_by, expect_rx_by);
 		rxrpc_reduce_call_timer(call, expect_rx_by, now,
 					rxrpc_timer_set_for_normal);
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
index 93b5d910b4a1..8325f1b86840 100644
--- a/net/rxrpc/local_event.c
+++ b/net/rxrpc/local_event.c
@@ -71,7 +71,8 @@ static void rxrpc_send_version_request(struct rxrpc_local *local,
 
 	ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
 	if (ret < 0)
-		_debug("sendmsg failed: %d", ret);
+		trace_rxrpc_tx_fail(local->debug_id, 0, ret,
+				    rxrpc_tx_fail_version_reply);
 
 	_leave("");
 }
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 8b54e9531d52..b493e6b62740 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -134,22 +134,49 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		}
 	}
 
-	/* we want to receive ICMP errors */
-	opt = 1;
-	ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
-				(char *) &opt, sizeof(opt));
-	if (ret < 0) {
-		_debug("setsockopt failed");
-		goto error;
-	}
+	switch (local->srx.transport.family) {
+	case AF_INET:
+		/* we want to receive ICMP errors */
+		opt = 1;
+		ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+					(char *) &opt, sizeof(opt));
+		if (ret < 0) {
+			_debug("setsockopt failed");
+			goto error;
+		}
 
-	/* we want to set the don't fragment bit */
-	opt = IP_PMTUDISC_DO;
-	ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
-				(char *) &opt, sizeof(opt));
-	if (ret < 0) {
-		_debug("setsockopt failed");
-		goto error;
+		/* we want to set the don't fragment bit */
+		opt = IP_PMTUDISC_DO;
+		ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+					(char *) &opt, sizeof(opt));
+		if (ret < 0) {
+			_debug("setsockopt failed");
+			goto error;
+		}
+		break;
+
+	case AF_INET6:
+		/* we want to receive ICMP errors */
+		opt = 1;
+		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+					(char *) &opt, sizeof(opt));
+		if (ret < 0) {
+			_debug("setsockopt failed");
+			goto error;
+		}
+
+		/* we want to set the don't fragment bit */
+		opt = IPV6_PMTUDISC_DO;
+		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+					(char *) &opt, sizeof(opt));
+		if (ret < 0) {
+			_debug("setsockopt failed");
+			goto error;
+		}
+		break;
+
+	default:
+		BUG();
 	}
 
 	/* set the socket up */
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index c7a023fb22d0..5d6a773db973 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -97,8 +97,11 @@ static __net_init int rxrpc_init_net(struct net *net)
 	if (!rxnet->proc_net)
 		goto err_proc;
 
-	proc_create("calls", 0444, rxnet->proc_net, &rxrpc_call_seq_fops);
-	proc_create("conns", 0444, rxnet->proc_net, &rxrpc_connection_seq_fops);
+	proc_create_net("calls", 0444, rxnet->proc_net, &rxrpc_call_seq_ops,
+			sizeof(struct seq_net_private));
+	proc_create_net("conns", 0444, rxnet->proc_net,
+			&rxrpc_connection_seq_ops,
+			sizeof(struct seq_net_private));
 	return 0;
 
 err_proc:
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 7f1fc04775b3..f03de1c59ba3 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -210,6 +210,9 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	if (ping)
 		call->ping_time = now;
 	conn->params.peer->last_tx_at = ktime_get_real();
+	if (ret < 0)
+		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+				    rxrpc_tx_fail_call_ack);
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		if (ret < 0) {
@@ -294,6 +297,10 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	ret = kernel_sendmsg(conn->params.local->socket,
 			     &msg, iov, 1, sizeof(pkt));
 	conn->params.peer->last_tx_at = ktime_get_real();
+	if (ret < 0)
+		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+				    rxrpc_tx_fail_call_abort);
+
 
 	rxrpc_put_connection(conn);
 	return ret;
@@ -387,6 +394,9 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	conn->params.peer->last_tx_at = ktime_get_real();
 
 	up_read(&conn->params.local->defrag_sem);
+	if (ret < 0)
+		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+				    rxrpc_tx_fail_call_data_nofrag);
 	if (ret == -EMSGSIZE)
 		goto send_fragmentable;
 
@@ -414,6 +424,17 @@ done:
 							rxrpc_timer_set_for_lost_ack);
 			}
 		}
+
+		if (sp->hdr.seq == 1 &&
+		    !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER,
+				      &call->flags)) {
+			unsigned long nowj = jiffies, expect_rx_by;
+
+			expect_rx_by = nowj + call->next_rx_timo;
+			WRITE_ONCE(call->expect_rx_by, expect_rx_by);
+			rxrpc_reduce_call_timer(call, expect_rx_by, nowj,
+						rxrpc_timer_set_for_normal);
+		}
 	}
 
 	rxrpc_set_keepalive(call);
@@ -465,6 +486,10 @@ send_fragmentable:
 #endif
 	}
 
+	if (ret < 0)
+		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+				    rxrpc_tx_fail_call_data_frag);
+
 	up_write(&conn->params.local->defrag_sem);
 	goto done;
 }
@@ -482,6 +507,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
 	struct kvec iov[2];
 	size_t size;
 	__be32 code;
+	int ret;
 
 	_enter("%d", local->debug_id);
 
@@ -516,7 +542,10 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
 			whdr.flags	^= RXRPC_CLIENT_INITIATED;
 			whdr.flags	&= RXRPC_CLIENT_INITIATED;
 
-			kernel_sendmsg(local->socket, &msg, iov, 2, size);
+			ret = kernel_sendmsg(local->socket, &msg, iov, 2, size);
+			if (ret < 0)
+				trace_rxrpc_tx_fail(local->debug_id, 0, ret,
+						    rxrpc_tx_fail_reject);
 		}
 
 		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
@@ -567,7 +596,8 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
 
 	ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len);
 	if (ret < 0)
-		_debug("sendmsg failed: %d", ret);
+		trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
+				    rxrpc_tx_fail_version_keepalive);
 
 	peer->last_tx_at = ktime_get_real();
 	_leave("");
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 78c2f95d1f22..0ed8b651cec2 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -28,39 +28,39 @@ static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
  * Find the peer associated with an ICMP packet.
  */
 static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
-						     const struct sk_buff *skb)
+						     const struct sk_buff *skb,
+						     struct sockaddr_rxrpc *srx)
 {
 	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
-	struct sockaddr_rxrpc srx;
 
 	_enter("");
 
-	memset(&srx, 0, sizeof(srx));
-	srx.transport_type = local->srx.transport_type;
-	srx.transport_len = local->srx.transport_len;
-	srx.transport.family = local->srx.transport.family;
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
 
 	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
 	 * versa?
 	 */
-	switch (srx.transport.family) {
+	switch (srx->transport.family) {
 	case AF_INET:
-		srx.transport.sin.sin_port = serr->port;
+		srx->transport.sin.sin_port = serr->port;
 		switch (serr->ee.ee_origin) {
 		case SO_EE_ORIGIN_ICMP:
 			_net("Rx ICMP");
-			memcpy(&srx.transport.sin.sin_addr,
+			memcpy(&srx->transport.sin.sin_addr,
 			       skb_network_header(skb) + serr->addr_offset,
 			       sizeof(struct in_addr));
 			break;
 		case SO_EE_ORIGIN_ICMP6:
 			_net("Rx ICMP6 on v4 sock");
-			memcpy(&srx.transport.sin.sin_addr,
+			memcpy(&srx->transport.sin.sin_addr,
 			       skb_network_header(skb) + serr->addr_offset + 12,
 			       sizeof(struct in_addr));
 			break;
 		default:
-			memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr,
+			memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr,
 			       sizeof(struct in_addr));
 			break;
 		}
@@ -68,25 +68,25 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 
 #ifdef CONFIG_AF_RXRPC_IPV6
 	case AF_INET6:
-		srx.transport.sin6.sin6_port = serr->port;
+		srx->transport.sin6.sin6_port = serr->port;
 		switch (serr->ee.ee_origin) {
 		case SO_EE_ORIGIN_ICMP6:
 			_net("Rx ICMP6");
-			memcpy(&srx.transport.sin6.sin6_addr,
+			memcpy(&srx->transport.sin6.sin6_addr,
 			       skb_network_header(skb) + serr->addr_offset,
 			       sizeof(struct in6_addr));
 			break;
 		case SO_EE_ORIGIN_ICMP:
 			_net("Rx ICMP on v6 sock");
-			srx.transport.sin6.sin6_addr.s6_addr32[0] = 0;
-			srx.transport.sin6.sin6_addr.s6_addr32[1] = 0;
-			srx.transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
-			memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12,
+			srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
+			srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
+			srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
+			memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12,
 			       skb_network_header(skb) + serr->addr_offset,
 			       sizeof(struct in_addr));
 			break;
 		default:
-			memcpy(&srx.transport.sin6.sin6_addr,
+			memcpy(&srx->transport.sin6.sin6_addr,
 			       &ipv6_hdr(skb)->saddr,
 			       sizeof(struct in6_addr));
 			break;
@@ -98,7 +98,7 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 		BUG();
 	}
 
-	return rxrpc_lookup_peer_rcu(local, &srx);
+	return rxrpc_lookup_peer_rcu(local, srx);
 }
 
 /*
@@ -146,6 +146,7 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *se
 void rxrpc_error_report(struct sock *sk)
 {
 	struct sock_exterr_skb *serr;
+	struct sockaddr_rxrpc srx;
 	struct rxrpc_local *local = sk->sk_user_data;
 	struct rxrpc_peer *peer;
 	struct sk_buff *skb;
@@ -166,7 +167,7 @@ void rxrpc_error_report(struct sock *sk)
 	}
 
 	rcu_read_lock();
-	peer = rxrpc_lookup_peer_icmp_rcu(local, skb);
+	peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
 	if (peer && !rxrpc_get_peer_maybe(peer))
 		peer = NULL;
 	if (!peer) {
@@ -176,6 +177,8 @@ void rxrpc_error_report(struct sock *sk)
 		return;
 	}
 
+	trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
+
 	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
 	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
 	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
@@ -209,9 +212,6 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
 
 	ee = &serr->ee;
 
-	_net("Rx Error o=%d t=%d c=%d e=%d",
-	     ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
-
 	err = ee->ee_errno;
 
 	switch (ee->ee_origin) {
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 7e45db058823..d9fca8c4bcdc 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -115,26 +115,13 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static const struct seq_operations rxrpc_call_seq_ops = {
+const struct seq_operations rxrpc_call_seq_ops = {
 	.start  = rxrpc_call_seq_start,
 	.next   = rxrpc_call_seq_next,
 	.stop   = rxrpc_call_seq_stop,
 	.show   = rxrpc_call_seq_show,
 };
 
-static int rxrpc_call_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &rxrpc_call_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-const struct file_operations rxrpc_call_seq_fops = {
-	.open		= rxrpc_call_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 /*
  * generate a list of extant virtual connections in /proc/net/rxrpc_conns
  */
@@ -207,23 +194,9 @@ print:
 	return 0;
 }
 
-static const struct seq_operations rxrpc_connection_seq_ops = {
+const struct seq_operations rxrpc_connection_seq_ops = {
 	.start  = rxrpc_connection_seq_start,
 	.next   = rxrpc_connection_seq_next,
 	.stop   = rxrpc_connection_seq_stop,
 	.show   = rxrpc_connection_seq_show,
 };
-
-
-static int rxrpc_connection_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &rxrpc_connection_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-const struct file_operations rxrpc_connection_seq_fops = {
-	.open		= rxrpc_connection_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 588fea0dd362..6c0ae27fff84 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -664,7 +664,8 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
 	if (ret < 0) {
-		_debug("sendmsg failed: %d", ret);
+		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+				    rxrpc_tx_fail_conn_challenge);
 		return -EAGAIN;
 	}
 
@@ -719,7 +720,8 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len);
 	if (ret < 0) {
-		_debug("sendmsg failed: %d", ret);
+		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+				    rxrpc_tx_fail_conn_response);
 		return -EAGAIN;
 	}
 
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 206e802ccbdc..be01f9c5d963 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -223,6 +223,15 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 
 	ret = rxrpc_send_data_packet(call, skb, false);
 	if (ret < 0) {
+		switch (ret) {
+		case -ENETUNREACH:
+		case -EHOSTUNREACH:
+		case -ECONNREFUSED:
+			rxrpc_set_call_completion(call,
+						  RXRPC_CALL_LOCAL_ERROR,
+						  0, ret);
+			goto out;
+		}
 		_debug("need instant resend %d", ret);
 		rxrpc_instant_resend(call, ix);
 	} else {
@@ -241,6 +250,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 					rxrpc_timer_set_for_send);
 	}
 
+out:
 	rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
 	_leave("");
 }
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index a5994cf0512b..8527cfdc446d 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -652,7 +652,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
 		}
 	}
 
-	return 0;
+	return -ENOENT;
 }
 
 static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
@@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 		u16 mtype;
 		u16 dlen;
 
-		curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+		curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+						&dlen, NULL);
+		if (!curr_data) {
+			qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+			return TC_ACT_SHOT;
+		}
 
 		if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
 			/* abuse overlimits to count when we receive metadata
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index ddf69fc01bdf..6138d1d71900 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -121,7 +121,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		return 0;
 
 	if (!flags) {
-		tcf_idr_release(*a, bind);
+		if (exists)
+			tcf_idr_release(*a, bind);
 		return -EINVAL;
 	}
 
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index bbcbdce732cc..ad050d7d4b46 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -131,8 +131,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	if (exists && bind)
 		return 0;
 
-	if (!lflags)
+	if (!lflags) {
+		if (exists)
+			tcf_idr_release(*a, bind);
 		return -EINVAL;
+	}
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 853604685965..1fb39e1f9d07 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -161,6 +161,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			case htons(ETH_P_8021AD):
 				break;
 			default:
+				if (exists)
+					tcf_idr_release(*a, bind);
 				return -EPROTONOSUPPORT;
 			}
 		} else {
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b66754f52a9f..a57e112d9b3e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -152,8 +152,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
 			NL_SET_ERR_MSG(extack, "TC classifier not found");
 			err = -ENOENT;
 		}
-		goto errout;
 #endif
+		goto errout;
 	}
 	tp->classify = tp->ops->classify;
 	tp->protocol = protocol;
@@ -1588,7 +1588,7 @@ int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
 		return ret;
 	ok_count = ret;
 
-	if (!exts)
+	if (!exts || ok_count)
 		return ok_count;
 	ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
 	if (ret < 0)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index d964e60c730e..c79f6e71512e 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -977,7 +977,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	return 0;
 
 errout_idr:
-	if (fnew->handle)
+	if (!fold)
 		idr_remove(&head->handle_idr, fnew->handle);
 errout:
 	tcf_exts_destroy(&fnew->exts);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 106dae7e4818..54eca685420f 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -2092,23 +2092,11 @@ static int psched_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int psched_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, psched_show, NULL);
-}
-
-static const struct file_operations psched_fops = {
-	.open = psched_open,
-	.read  = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 static int __net_init psched_net_init(struct net *net)
 {
 	struct proc_dir_entry *e;
 
-	e = proc_create("psched", 0, net->proc_net, &psched_fops);
+	e = proc_create_single("psched", 0, net->proc_net, psched_show);
 	if (e == NULL)
 		return -ENOMEM;
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index a366e4c9413a..4808713c73b9 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -128,6 +128,28 @@ static bool fq_flow_is_detached(const struct fq_flow *f)
 	return f->next == &detached;
 }
 
+static bool fq_flow_is_throttled(const struct fq_flow *f)
+{
+	return f->next == &throttled;
+}
+
+static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
+{
+	if (head->first)
+		head->last->next = flow;
+	else
+		head->first = flow;
+	head->last = flow;
+	flow->next = NULL;
+}
+
+static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f)
+{
+	rb_erase(&f->rate_node, &q->delayed);
+	q->throttled_flows--;
+	fq_flow_add_tail(&q->old_flows, f);
+}
+
 static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
 {
 	struct rb_node **p = &q->delayed.rb_node, *parent = NULL;
@@ -155,15 +177,6 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
 
 static struct kmem_cache *fq_flow_cachep __read_mostly;
 
-static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
-{
-	if (head->first)
-		head->last->next = flow;
-	else
-		head->first = flow;
-	head->last = flow;
-	flow->next = NULL;
-}
 
 /* limit number of collected flows per round */
 #define FQ_GC_MAX 8
@@ -267,6 +280,8 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 				     f->socket_hash != sk->sk_hash)) {
 				f->credit = q->initial_quantum;
 				f->socket_hash = sk->sk_hash;
+				if (fq_flow_is_throttled(f))
+					fq_flow_unset_throttled(q, f);
 				f->time_next_packet = 0ULL;
 			}
 			return f;
@@ -438,9 +453,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
 			q->time_next_delayed_flow = f->time_next_packet;
 			break;
 		}
-		rb_erase(p, &q->delayed);
-		q->throttled_flows--;
-		fq_flow_add_tail(&q->old_flows, f);
+		fq_flow_unset_throttled(q, f);
 	}
 }
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 16644b3d2362..56c181c3feeb 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -222,10 +222,11 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
 					 extack);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
-	}
 
-	if (child != &noop_qdisc)
+		/* child is fifo, no need to check for noop_qdisc */
 		qdisc_hash_add(child, true);
+	}
+
 	sch_tree_lock(sch);
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 03225a8df973..6f74a426f159 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -383,6 +383,9 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 			err = PTR_ERR(child);
 			goto done;
 		}
+
+		/* child is fifo, no need to check for noop_qdisc */
+		qdisc_hash_add(child, true);
 	}
 
 	sch_tree_lock(sch);
@@ -391,8 +394,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
-		if (child != &noop_qdisc)
-			qdisc_hash_add(child, true);
 	}
 	q->limit = qopt->limit;
 	if (tb[TCA_TBF_PBURST])
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 837806dd5799..a47179da24e6 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1024,8 +1024,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 	struct sctp_endpoint *ep;
 	struct sctp_chunk *chunk;
 	struct sctp_inq *inqueue;
-	int state;
+	int first_time = 1;	/* is this the first time through the loop */
 	int error = 0;
+	int state;
 
 	/* The association should be held so we should be safe. */
 	ep = asoc->ep;
@@ -1036,6 +1037,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		state = asoc->state;
 		subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);
 
+		/* If the first chunk in the packet is AUTH, do special
+		 * processing specified in Section 6.3 of SCTP-AUTH spec
+		 */
+		if (first_time && subtype.chunk == SCTP_CID_AUTH) {
+			struct sctp_chunkhdr *next_hdr;
+
+			next_hdr = sctp_inq_peek(inqueue);
+			if (!next_hdr)
+				goto normal;
+
+			/* If the next chunk is COOKIE-ECHO, skip the AUTH
+			 * chunk while saving a pointer to it so we can do
+			 * Authentication later (during cookie-echo
+			 * processing).
+			 */
+			if (next_hdr->type == SCTP_CID_COOKIE_ECHO) {
+				chunk->auth_chunk = skb_clone(chunk->skb,
+							      GFP_ATOMIC);
+				chunk->auth = 1;
+				continue;
+			}
+		}
+
+normal:
 		/* SCTP-AUTH, Section 6.3:
 		 *    The receiver has a list of chunk types which it expects
 		 *    to be received only after an AUTH-chunk.  This list has
@@ -1074,6 +1099,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		/* If there is an error on chunk, discard this packet. */
 		if (error && chunk)
 			chunk->pdiscard = 1;
+
+		if (first_time)
+			first_time = 0;
 	}
 	sctp_association_put(asoc);
 }
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 23ebc5318edc..eb93ffe2408b 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -217,7 +217,7 @@ new_skb:
 	skb_pull(chunk->skb, sizeof(*ch));
 	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
 
-	if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) {
+	if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) {
 		/* This is not a singleton */
 		chunk->singleton = 0;
 	} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 31083b5035ec..7339918a805d 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -556,46 +556,49 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
 	addr->v6.sin6_scope_id = 0;
 }
 
-/* Compare addresses exactly.
- * v4-mapped-v6 is also in consideration.
- */
-static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
-			    const union sctp_addr *addr2)
+static int __sctp_v6_cmp_addr(const union sctp_addr *addr1,
+			      const union sctp_addr *addr2)
 {
 	if (addr1->sa.sa_family != addr2->sa.sa_family) {
 		if (addr1->sa.sa_family == AF_INET &&
 		    addr2->sa.sa_family == AF_INET6 &&
-		    ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) {
-			if (addr2->v6.sin6_port == addr1->v4.sin_port &&
-			    addr2->v6.sin6_addr.s6_addr32[3] ==
-			    addr1->v4.sin_addr.s_addr)
-				return 1;
-		}
+		    ipv6_addr_v4mapped(&addr2->v6.sin6_addr) &&
+		    addr2->v6.sin6_addr.s6_addr32[3] ==
+		    addr1->v4.sin_addr.s_addr)
+			return 1;
+
 		if (addr2->sa.sa_family == AF_INET &&
 		    addr1->sa.sa_family == AF_INET6 &&
-		    ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) {
-			if (addr1->v6.sin6_port == addr2->v4.sin_port &&
-			    addr1->v6.sin6_addr.s6_addr32[3] ==
-			    addr2->v4.sin_addr.s_addr)
-				return 1;
-		}
+		    ipv6_addr_v4mapped(&addr1->v6.sin6_addr) &&
+		    addr1->v6.sin6_addr.s6_addr32[3] ==
+		    addr2->v4.sin_addr.s_addr)
+			return 1;
+
 		return 0;
 	}
-	if (addr1->v6.sin6_port != addr2->v6.sin6_port)
-		return 0;
+
 	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
 		return 0;
+
 	/* If this is a linklocal address, compare the scope_id. */
-	if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
-		if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
-		    (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) {
-			return 0;
-		}
-	}
+	if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
+	    addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)
+		return 0;
 
 	return 1;
 }
 
+/* Compare addresses exactly.
+ * v4-mapped-v6 is also in consideration.
+ */
+static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
+			    const union sctp_addr *addr2)
+{
+	return __sctp_v6_cmp_addr(addr1, addr2) &&
+	       addr1->v6.sin6_port == addr2->v6.sin6_port;
+}
+
 /* Initialize addr struct to INADDR_ANY. */
 static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port)
 {
@@ -875,8 +878,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 			       const union sctp_addr *addr2,
 			       struct sctp_sock *opt)
 {
-	struct sctp_af *af1, *af2;
 	struct sock *sk = sctp_opt2sk(opt);
+	struct sctp_af *af1, *af2;
 
 	af1 = sctp_get_af_specific(addr1->sa.sa_family);
 	af2 = sctp_get_af_specific(addr2->sa.sa_family);
@@ -892,10 +895,10 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 	if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
 		return 1;
 
-	if (addr1->sa.sa_family != addr2->sa.sa_family)
-		return 0;
+	if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET)
+		return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr;
 
-	return af1->cmp_addr(addr1, addr2);
+	return __sctp_v6_cmp_addr(addr1, addr2);
 }
 
 /* Verify that the provided sockaddr looks bindable.   Common verification,
@@ -1003,11 +1006,11 @@ static const struct proto_ops inet6_seqpacket_ops = {
 	.owner		   = THIS_MODULE,
 	.release	   = inet6_release,
 	.bind		   = inet6_bind,
-	.connect	   = inet_dgram_connect,
+	.connect	   = sctp_inet_connect,
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = sctp_getname,
-	.poll		   = sctp_poll,
+	.poll_mask	   = sctp_poll_mask,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c
index fd2684ad94c8..a6179b26b80c 100644
--- a/net/sctp/objcnt.c
+++ b/net/sctp/objcnt.c
@@ -108,25 +108,13 @@ static const struct seq_operations sctp_objcnt_seq_ops = {
 	.show  = sctp_objcnt_seq_show,
 };
 
-static int sctp_objcnt_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &sctp_objcnt_seq_ops);
-}
-
-static const struct file_operations sctp_objcnt_ops = {
-	.open	 = sctp_objcnt_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
 /* Initialize the objcount in the proc filesystem.  */
 void sctp_dbg_objcnt_init(struct net *net)
 {
 	struct proc_dir_entry *ent;
 
-	ent = proc_create("sctp_dbg_objcnt", 0,
-			  net->sctp.proc_net_sctp, &sctp_objcnt_ops);
+	ent = proc_create_seq("sctp_dbg_objcnt", 0,
+			  net->sctp.proc_net_sctp, &sctp_objcnt_seq_ops);
 	if (!ent)
 		pr_warn("sctp_dbg_objcnt: Unable to create /proc entry.\n");
 }
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 1d9ccc6dab2b..ef5c9a82d4e8 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -88,19 +88,6 @@ static int sctp_snmp_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-/* Initialize the seq file operations for 'snmp' object. */
-static int sctp_snmp_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, sctp_snmp_seq_show);
-}
-
-static const struct file_operations sctp_snmp_seq_fops = {
-	.open	 = sctp_snmp_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release_net,
-};
-
 /* Dump local addresses of an association/endpoint. */
 static void sctp_seq_dump_local_addrs(struct seq_file *seq, struct sctp_ep_common *epb)
 {
@@ -225,21 +212,6 @@ static const struct seq_operations sctp_eps_ops = {
 	.show  = sctp_eps_seq_show,
 };
 
-
-/* Initialize the seq file operations for 'eps' object. */
-static int sctp_eps_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &sctp_eps_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations sctp_eps_seq_fops = {
-	.open	 = sctp_eps_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
 struct sctp_ht_iter {
 	struct seq_net_private p;
 	struct rhashtable_iter hti;
@@ -338,20 +310,6 @@ static const struct seq_operations sctp_assoc_ops = {
 	.show  = sctp_assocs_seq_show,
 };
 
-/* Initialize the seq file operations for 'assocs' object. */
-static int sctp_assocs_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &sctp_assoc_ops,
-			    sizeof(struct sctp_ht_iter));
-}
-
-static const struct file_operations sctp_assocs_seq_fops = {
-	.open	 = sctp_assocs_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release_net,
-};
-
 static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 {
 	struct sctp_association *assoc;
@@ -431,36 +389,23 @@ static const struct seq_operations sctp_remaddr_ops = {
 	.show  = sctp_remaddr_seq_show,
 };
 
-static int sctp_remaddr_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &sctp_remaddr_ops,
-			    sizeof(struct sctp_ht_iter));
-}
-
-static const struct file_operations sctp_remaddr_seq_fops = {
-	.open = sctp_remaddr_seq_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release_net,
-};
-
 /* Set up the proc fs entry for the SCTP protocol. */
 int __net_init sctp_proc_init(struct net *net)
 {
 	net->sctp.proc_net_sctp = proc_net_mkdir(net, "sctp", net->proc_net);
 	if (!net->sctp.proc_net_sctp)
 		return -ENOMEM;
-	if (!proc_create("snmp", 0444, net->sctp.proc_net_sctp,
-			 &sctp_snmp_seq_fops))
+	if (!proc_create_net_single("snmp", 0444, net->sctp.proc_net_sctp,
+			 sctp_snmp_seq_show, NULL))
 		goto cleanup;
-	if (!proc_create("eps", 0444, net->sctp.proc_net_sctp,
-			 &sctp_eps_seq_fops))
+	if (!proc_create_net("eps", 0444, net->sctp.proc_net_sctp,
+			&sctp_eps_ops, sizeof(struct seq_net_private)))
 		goto cleanup;
-	if (!proc_create("assocs", 0444, net->sctp.proc_net_sctp,
-			 &sctp_assocs_seq_fops))
+	if (!proc_create_net("assocs", 0444, net->sctp.proc_net_sctp,
+			&sctp_assoc_ops, sizeof(struct sctp_ht_iter)))
 		goto cleanup;
-	if (!proc_create("remaddr", 0444, net->sctp.proc_net_sctp,
-			 &sctp_remaddr_seq_fops))
+	if (!proc_create_net("remaddr", 0444, net->sctp.proc_net_sctp,
+			&sctp_remaddr_ops, sizeof(struct sctp_ht_iter)))
 		goto cleanup;
 	return 0;
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index d685f8456762..11d93377ba5e 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1012,11 +1012,11 @@ static const struct proto_ops inet_seqpacket_ops = {
 	.owner		   = THIS_MODULE,
 	.release	   = inet_release,	/* Needs to be wrapped... */
 	.bind		   = inet_bind,
-	.connect	   = inet_dgram_connect,
+	.connect	   = sctp_inet_connect,
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,	/* Semantics are different.  */
-	.poll		   = sctp_poll,
+	.poll_mask	   = sctp_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,	/* Looks harmless.  */
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 5a4fb1dc8400..e62addb60434 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1152,7 +1152,7 @@ struct sctp_chunk *sctp_make_violation_max_retrans(
 					const struct sctp_association *asoc,
 					const struct sctp_chunk *chunk)
 {
-	static const char error[] = "Association exceeded its max_retans count";
+	static const char error[] = "Association exceeded its max_retrans count";
 	size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr);
 	struct sctp_chunk *retval;
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index dd0594a10961..c9ae3404b1bb 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -153,10 +153,7 @@ static enum sctp_disposition sctp_sf_violation_chunk(
 					struct sctp_cmd_seq *commands);
 
 static enum sctp_ierror sctp_sf_authenticate(
-					struct net *net,
-					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
-					const union sctp_subtype type,
 					struct sctp_chunk *chunk);
 
 static enum sctp_disposition __sctp_sf_do_9_1_abort(
@@ -626,6 +623,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net,
 	return SCTP_DISPOSITION_CONSUME;
 }
 
+static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk,
+				   const struct sctp_association *asoc)
+{
+	struct sctp_chunk auth;
+
+	if (!chunk->auth_chunk)
+		return true;
+
+	/* SCTP-AUTH:  auth_chunk pointer is only set when the cookie-echo
+	 * is supposed to be authenticated and we have to do delayed
+	 * authentication.  We've just recreated the association using
+	 * the information in the cookie and now it's much easier to
+	 * do the authentication.
+	 */
+
+	/* Make sure that we and the peer are AUTH capable */
+	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+		return false;
+
+	/* set-up our fake chunk so that we can process it */
+	auth.skb = chunk->auth_chunk;
+	auth.asoc = chunk->asoc;
+	auth.sctp_hdr = chunk->sctp_hdr;
+	auth.chunk_hdr = (struct sctp_chunkhdr *)
+				skb_push(chunk->auth_chunk,
+					 sizeof(struct sctp_chunkhdr));
+	skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
+	auth.transport = chunk->transport;
+
+	return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR;
+}
+
 /*
  * Respond to a normal COOKIE ECHO chunk.
  * We are the side that is being asked for an association.
@@ -763,37 +792,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 	if (error)
 		goto nomem_init;
 
-	/* SCTP-AUTH:  auth_chunk pointer is only set when the cookie-echo
-	 * is supposed to be authenticated and we have to do delayed
-	 * authentication.  We've just recreated the association using
-	 * the information in the cookie and now it's much easier to
-	 * do the authentication.
-	 */
-	if (chunk->auth_chunk) {
-		struct sctp_chunk auth;
-		enum sctp_ierror ret;
-
-		/* Make sure that we and the peer are AUTH capable */
-		if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
-			sctp_association_free(new_asoc);
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-		}
-
-		/* set-up our fake chunk so that we can process it */
-		auth.skb = chunk->auth_chunk;
-		auth.asoc = chunk->asoc;
-		auth.sctp_hdr = chunk->sctp_hdr;
-		auth.chunk_hdr = (struct sctp_chunkhdr *)
-					skb_push(chunk->auth_chunk,
-						 sizeof(struct sctp_chunkhdr));
-		skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
-		auth.transport = chunk->transport;
-
-		ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-		if (ret != SCTP_IERROR_NO_ERROR) {
-			sctp_association_free(new_asoc);
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-		}
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) {
+		sctp_association_free(new_asoc);
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
 	}
 
 	repl = sctp_make_cookie_ack(new_asoc, chunk);
@@ -1794,13 +1795,18 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
 			       GFP_ATOMIC))
 		goto nomem;
 
+	if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC))
+		goto nomem;
+
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Make sure no new addresses are being added during the
 	 * restart.  Though this is a pretty complicated attack
 	 * since you'd have to get inside the cookie.
 	 */
-	if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) {
+	if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands))
 		return SCTP_DISPOSITION_CONSUME;
-	}
 
 	/* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes
 	 * the peer has restarted (Action A), it MUST NOT setup a new
@@ -1906,6 +1912,12 @@ static enum sctp_disposition sctp_sf_do_dupcook_b(
 			       GFP_ATOMIC))
 		goto nomem;
 
+	if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC))
+		goto nomem;
+
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Update the content of current association.  */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
@@ -2003,6 +2015,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 	 * a COOKIE ACK.
 	 */
 
+	if (!sctp_auth_chunk_verify(net, chunk, asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Don't accidentally move back into established state. */
 	if (asoc->state < SCTP_STATE_ESTABLISHED) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
@@ -2050,7 +2065,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 		}
 	}
 
-	repl = sctp_make_cookie_ack(new_asoc, chunk);
+	repl = sctp_make_cookie_ack(asoc, chunk);
 	if (!repl)
 		goto nomem;
 
@@ -4165,10 +4180,7 @@ gen_shutdown:
  * The return value is the disposition of the chunk.
  */
 static enum sctp_ierror sctp_sf_authenticate(
-					struct net *net,
-					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
-					const union sctp_subtype type,
 					struct sctp_chunk *chunk)
 {
 	struct sctp_shared_key *sh_key = NULL;
@@ -4269,7 +4281,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net,
 						  commands);
 
 	auth_hdr = (struct sctp_authhdr *)chunk->skb->data;
-	error = sctp_sf_authenticate(net, ep, asoc, type, chunk);
+	error = sctp_sf_authenticate(asoc, chunk);
 	switch (error) {
 	case SCTP_IERROR_AUTH_BAD_HMAC:
 		/* Generate the ERROR chunk and discard the rest
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 80835ac26d2c..bf747094d26b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1086,7 +1086,7 @@ out:
  */
 static int __sctp_connect(struct sock *sk,
 			  struct sockaddr *kaddrs,
-			  int addrs_size,
+			  int addrs_size, int flags,
 			  sctp_assoc_t *assoc_id)
 {
 	struct net *net = sock_net(sk);
@@ -1104,7 +1104,6 @@ static int __sctp_connect(struct sock *sk,
 	union sctp_addr *sa_addr = NULL;
 	void *addr_buf;
 	unsigned short port;
-	unsigned int f_flags = 0;
 
 	sp = sctp_sk(sk);
 	ep = sp->ep;
@@ -1254,13 +1253,7 @@ static int __sctp_connect(struct sock *sk,
 	sp->pf->to_sk_daddr(sa_addr, sk);
 	sk->sk_err = 0;
 
-	/* in-kernel sockets don't generally have a file allocated to them
-	 * if all they do is call sock_create_kern().
-	 */
-	if (sk->sk_socket->file)
-		f_flags = sk->sk_socket->file->f_flags;
-
-	timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK);
+	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
 
 	if (assoc_id)
 		*assoc_id = asoc->assoc_id;
@@ -1348,7 +1341,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 				      sctp_assoc_t *assoc_id)
 {
 	struct sockaddr *kaddrs;
-	int err = 0;
+	int err = 0, flags = 0;
 
 	pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n",
 		 __func__, sk, addrs, addrs_size);
@@ -1367,7 +1360,13 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 	if (err)
 		goto out_free;
 
-	err = __sctp_connect(sk, kaddrs, addrs_size, assoc_id);
+	/* in-kernel sockets don't generally have a file allocated to them
+	 * if all they do is call sock_create_kern().
+	 */
+	if (sk->sk_socket->file)
+		flags = sk->sk_socket->file->f_flags;
+
+	err = __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id);
 
 out_free:
 	kvfree(kaddrs);
@@ -4397,16 +4396,26 @@ out_nounlock:
  * len: the size of the address.
  */
 static int sctp_connect(struct sock *sk, struct sockaddr *addr,
-			int addr_len)
+			int addr_len, int flags)
 {
-	int err = 0;
+	struct inet_sock *inet = inet_sk(sk);
 	struct sctp_af *af;
+	int err = 0;
 
 	lock_sock(sk);
 
 	pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk,
 		 addr, addr_len);
 
+	/* We may need to bind the socket. */
+	if (!inet->inet_num) {
+		if (sk->sk_prot->get_port(sk, 0)) {
+			release_sock(sk);
+			return -EAGAIN;
+		}
+		inet->inet_sport = htons(inet->inet_num);
+	}
+
 	/* Validate addr_len before calling common connect/connectx routine. */
 	af = sctp_get_af_specific(addr->sa_family);
 	if (!af || addr_len < af->sockaddr_len) {
@@ -4415,13 +4424,25 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr,
 		/* Pass correct addr len to common routine (so it knows there
 		 * is only one address being passed.
 		 */
-		err = __sctp_connect(sk, addr, af->sockaddr_len, NULL);
+		err = __sctp_connect(sk, addr, af->sockaddr_len, flags, NULL);
 	}
 
 	release_sock(sk);
 	return err;
 }
 
+int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr,
+		      int addr_len, int flags)
+{
+	if (addr_len < sizeof(uaddr->sa_family))
+		return -EINVAL;
+
+	if (uaddr->sa_family == AF_UNSPEC)
+		return -EOPNOTSUPP;
+
+	return sctp_connect(sock->sk, uaddr, addr_len, flags);
+}
+
 /* FIXME: Write comments. */
 static int sctp_disconnect(struct sock *sk, int flags)
 {
@@ -7701,14 +7722,12 @@ out:
  * here, again, by modeling the current TCP/UDP code.  We don't have
  * a good way to test with it yet.
  */
-__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t sctp_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct sctp_sock *sp = sctp_sk(sk);
 	__poll_t mask;
 
-	poll_wait(file, sk_sleep(sk), wait);
-
 	sock_rps_record_flow(sk);
 
 	/* A TCP-style listening socket becomes readable when the accept queue
@@ -8724,7 +8743,6 @@ struct proto sctp_prot = {
 	.name        =	"SCTP",
 	.owner       =	THIS_MODULE,
 	.close       =	sctp_close,
-	.connect     =	sctp_connect,
 	.disconnect  =	sctp_disconnect,
 	.accept      =	sctp_accept,
 	.ioctl       =	sctp_ioctl,
@@ -8767,7 +8785,6 @@ struct proto sctpv6_prot = {
 	.name		= "SCTPv6",
 	.owner		= THIS_MODULE,
 	.close		= sctp_close,
-	.connect	= sctp_connect,
 	.disconnect	= sctp_disconnect,
 	.accept		= sctp_accept,
 	.ioctl		= sctp_ioctl,
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index f799043abec9..f1f1d1b232ba 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -240,6 +240,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new)
 
 	new->out = NULL;
 	new->in  = NULL;
+	new->outcnt = 0;
+	new->incnt  = 0;
 }
 
 static int sctp_send_reconf(struct sctp_association *asoc,
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 84207ad33e8e..8cb7d9858270 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -715,7 +715,6 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	return event;
 
 fail_mark:
-	sctp_chunk_put(chunk);
 	kfree_skb(skb);
 fail:
 	return NULL;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5f8046c62d90..544bab42f925 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -292,6 +292,17 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc)
 	smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC);
 }
 
+/* register a new rmb */
+static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc)
+{
+	/* register memory region for new rmb */
+	if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) {
+		rmb_desc->regerr = 1;
+		return -EFAULT;
+	}
+	return 0;
+}
+
 static int smc_clnt_conf_first_link(struct smc_sock *smc)
 {
 	struct smc_link_group *lgr = smc->conn.lgr;
@@ -321,9 +332,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 
 	smc_wr_remember_qp_attr(link);
 
-	rc = smc_wr_reg_send(link,
-			     smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]);
-	if (rc)
+	if (smc_reg_rmb(link, smc->conn.rmb_desc))
 		return SMC_CLC_DECL_INTERR;
 
 	/* send CONFIRM LINK response over RoCE fabric */
@@ -473,13 +482,8 @@ static int smc_connect_rdma(struct smc_sock *smc)
 			goto decline_rdma_unlock;
 		}
 	} else {
-		struct smc_buf_desc *buf_desc = smc->conn.rmb_desc;
-
-		if (!buf_desc->reused) {
-			/* register memory region for new rmb */
-			rc = smc_wr_reg_send(link,
-					     buf_desc->mr_rx[SMC_SINGLE_LINK]);
-			if (rc) {
+		if (!smc->conn.rmb_desc->reused) {
+			if (smc_reg_rmb(link, smc->conn.rmb_desc)) {
 				reason_code = SMC_CLC_DECL_INTERR;
 				goto decline_rdma_unlock;
 			}
@@ -719,9 +723,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 
 	link = &lgr->lnk[SMC_SINGLE_LINK];
 
-	rc = smc_wr_reg_send(link,
-			     smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]);
-	if (rc)
+	if (smc_reg_rmb(link, smc->conn.rmb_desc))
 		return SMC_CLC_DECL_INTERR;
 
 	/* send CONFIRM LINK request to client over the RoCE fabric */
@@ -854,13 +856,8 @@ static void smc_listen_work(struct work_struct *work)
 	smc_rx_init(new_smc);
 
 	if (local_contact != SMC_FIRST_CONTACT) {
-		struct smc_buf_desc *buf_desc = new_smc->conn.rmb_desc;
-
-		if (!buf_desc->reused) {
-			/* register memory region for new rmb */
-			rc = smc_wr_reg_send(link,
-					     buf_desc->mr_rx[SMC_SINGLE_LINK]);
-			if (rc) {
+		if (!new_smc->conn.rmb_desc->reused) {
+			if (smc_reg_rmb(link, new_smc->conn.rmb_desc)) {
 				reason_code = SMC_CLC_DECL_INTERR;
 				goto decline_rdma_unlock;
 			}
@@ -978,10 +975,6 @@ static void smc_tcp_listen_work(struct work_struct *work)
 	}
 
 out:
-	if (lsmc->clcsock) {
-		sock_release(lsmc->clcsock);
-		lsmc->clcsock = NULL;
-	}
 	release_sock(lsk);
 	sock_put(&lsmc->sk); /* sock_hold in smc_listen */
 }
@@ -1170,13 +1163,15 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 		/* delegate to CLC child sock */
 		release_sock(sk);
 		mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
-		/* if non-blocking connect finished ... */
 		lock_sock(sk);
-		if ((sk->sk_state == SMC_INIT) && (mask & EPOLLOUT)) {
-			sk->sk_err = smc->clcsock->sk->sk_err;
-			if (sk->sk_err) {
-				mask |= EPOLLERR;
-			} else {
+		sk->sk_err = smc->clcsock->sk->sk_err;
+		if (sk->sk_err) {
+			mask |= EPOLLERR;
+		} else {
+			/* if non-blocking connect finished ... */
+			if (sk->sk_state == SMC_INIT &&
+			    mask & EPOLLOUT &&
+			    smc->clcsock->sk->sk_state != TCP_CLOSE) {
 				rc = smc_connect_rdma(smc);
 				if (rc < 0)
 					mask |= EPOLLERR;
@@ -1259,14 +1254,12 @@ static int smc_shutdown(struct socket *sock, int how)
 		rc = smc_close_shutdown_write(smc);
 		break;
 	case SHUT_RD:
-		if (sk->sk_state == SMC_LISTEN)
-			rc = smc_close_active(smc);
-		else
-			rc = 0;
-			/* nothing more to do because peer is not involved */
+		rc = 0;
+		/* nothing more to do because peer is not involved */
 		break;
 	}
-	rc1 = kernel_sock_shutdown(smc->clcsock, how);
+	if (smc->clcsock)
+		rc1 = kernel_sock_shutdown(smc->clcsock, how);
 	/* map sock_shutdown_cmd constants to sk_shutdown value range */
 	sk->sk_shutdown |= how + 1;
 
@@ -1322,8 +1315,11 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page,
 
 	smc = smc_sk(sk);
 	lock_sock(sk);
-	if (sk->sk_state != SMC_ACTIVE)
+	if (sk->sk_state != SMC_ACTIVE) {
+		release_sock(sk);
 		goto out;
+	}
+	release_sock(sk);
 	if (smc->use_fallback)
 		rc = kernel_sendpage(smc->clcsock, page, offset,
 				     size, flags);
@@ -1331,7 +1327,6 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page,
 		rc = sock_no_sendpage(sock, page, offset, size, flags);
 
 out:
-	release_sock(sk);
 	return rc;
 }
 
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index f44f6803f7ff..d4bd01bb44e1 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -32,6 +32,9 @@
 
 static u32 smc_lgr_num;			/* unique link group number */
 
+static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk,
+			 bool is_rmb);
+
 static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
 {
 	/* client link group creation always follows the server link group
@@ -234,9 +237,22 @@ static void smc_buf_unuse(struct smc_connection *conn)
 		conn->sndbuf_size = 0;
 	}
 	if (conn->rmb_desc) {
-		conn->rmb_desc->reused = true;
-		conn->rmb_desc->used = 0;
-		conn->rmbe_size = 0;
+		if (!conn->rmb_desc->regerr) {
+			conn->rmb_desc->reused = 1;
+			conn->rmb_desc->used = 0;
+			conn->rmbe_size = 0;
+		} else {
+			/* buf registration failed, reuse not possible */
+			struct smc_link_group *lgr = conn->lgr;
+			struct smc_link *lnk;
+
+			write_lock_bh(&lgr->rmbs_lock);
+			list_del(&conn->rmb_desc->list);
+			write_unlock_bh(&lgr->rmbs_lock);
+
+			lnk = &lgr->lnk[SMC_SINGLE_LINK];
+			smc_buf_free(conn->rmb_desc, lnk, true);
+		}
 	}
 }
 
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 07e2a393e6d9..5dfcb15d529f 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -123,7 +123,8 @@ struct smc_buf_desc {
 						 */
 	u32			order;		/* allocation order */
 	u32			used;		/* currently used / unused */
-	bool			reused;		/* new created / reused */
+	u8			reused	: 1;	/* new created / reused */
+	u8			regerr	: 1;	/* err during registration */
 };
 
 struct smc_rtoken {				/* address/key of remote RMB */
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 74568cdbca70..d7b88b2d1b22 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -245,40 +245,45 @@ out:
 static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem,
 			       struct nlattr *tb[])
 {
-	char *string, *ibname = NULL;
-	int rc = 0;
+	char *string, *ibname;
+	int rc;
 
 	memset(pnetelem, 0, sizeof(*pnetelem));
 	INIT_LIST_HEAD(&pnetelem->list);
-	if (tb[SMC_PNETID_NAME]) {
-		string = (char *)nla_data(tb[SMC_PNETID_NAME]);
-		if (!smc_pnetid_valid(string, pnetelem->pnet_name)) {
-			rc = -EINVAL;
-			goto error;
-		}
-	}
-	if (tb[SMC_PNETID_ETHNAME]) {
-		string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
-		pnetelem->ndev = dev_get_by_name(net, string);
-		if (!pnetelem->ndev)
-			return -ENOENT;
-	}
-	if (tb[SMC_PNETID_IBNAME]) {
-		ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
-		ibname = strim(ibname);
-		pnetelem->smcibdev = smc_pnet_find_ib(ibname);
-		if (!pnetelem->smcibdev) {
-			rc = -ENOENT;
-			goto error;
-		}
-	}
-	if (tb[SMC_PNETID_IBPORT]) {
-		pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
-		if (pnetelem->ib_port > SMC_MAX_PORTS) {
-			rc = -EINVAL;
-			goto error;
-		}
-	}
+
+	rc = -EINVAL;
+	if (!tb[SMC_PNETID_NAME])
+		goto error;
+	string = (char *)nla_data(tb[SMC_PNETID_NAME]);
+	if (!smc_pnetid_valid(string, pnetelem->pnet_name))
+		goto error;
+
+	rc = -EINVAL;
+	if (!tb[SMC_PNETID_ETHNAME])
+		goto error;
+	rc = -ENOENT;
+	string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
+	pnetelem->ndev = dev_get_by_name(net, string);
+	if (!pnetelem->ndev)
+		goto error;
+
+	rc = -EINVAL;
+	if (!tb[SMC_PNETID_IBNAME])
+		goto error;
+	rc = -ENOENT;
+	ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
+	ibname = strim(ibname);
+	pnetelem->smcibdev = smc_pnet_find_ib(ibname);
+	if (!pnetelem->smcibdev)
+		goto error;
+
+	rc = -EINVAL;
+	if (!tb[SMC_PNETID_IBPORT])
+		goto error;
+	pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
+	if (pnetelem->ib_port < 1 || pnetelem->ib_port > SMC_MAX_PORTS)
+		goto error;
+
 	return 0;
 
 error:
@@ -307,6 +312,8 @@ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
 	void *hdr;
 	int rc;
 
+	if (!info->attrs[SMC_PNETID_NAME])
+		return -EINVAL;
 	pnetelem = smc_pnet_find_pnetid(
 				(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
 	if (!pnetelem)
@@ -359,6 +366,8 @@ static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info)
 
 static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info)
 {
+	if (!info->attrs[SMC_PNETID_NAME])
+		return -EINVAL;
 	return smc_pnet_remove_by_pnetid(
 				(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
 }
diff --git a/net/socket.c b/net/socket.c
index f10f1d947c78..af57d85bcb48 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -117,8 +117,10 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
 static int sock_mmap(struct file *file, struct vm_area_struct *vma);
 
 static int sock_close(struct inode *inode, struct file *file);
-static __poll_t sock_poll(struct file *file,
-			      struct poll_table_struct *wait);
+static struct wait_queue_head *sock_get_poll_head(struct file *file,
+		__poll_t events);
+static __poll_t sock_poll_mask(struct file *file, __poll_t);
+static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait);
 static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 #ifdef CONFIG_COMPAT
 static long compat_sock_ioctl(struct file *file,
@@ -141,6 +143,8 @@ static const struct file_operations socket_file_ops = {
 	.llseek =	no_llseek,
 	.read_iter =	sock_read_iter,
 	.write_iter =	sock_write_iter,
+	.get_poll_head = sock_get_poll_head,
+	.poll_mask =	sock_poll_mask,
 	.poll =		sock_poll,
 	.unlocked_ioctl = sock_ioctl,
 #ifdef CONFIG_COMPAT
@@ -1114,27 +1118,48 @@ out_release:
 }
 EXPORT_SYMBOL(sock_create_lite);
 
-/* No kernel lock held - perfect */
-static __poll_t sock_poll(struct file *file, poll_table *wait)
+static struct wait_queue_head *sock_get_poll_head(struct file *file,
+		__poll_t events)
 {
-	__poll_t busy_flag = 0;
-	struct socket *sock;
+	struct socket *sock = file->private_data;
+
+	if (!sock->ops->poll_mask)
+		return NULL;
+	sock_poll_busy_loop(sock, events);
+	return sk_sleep(sock->sk);
+}
+
+static __poll_t sock_poll_mask(struct file *file, __poll_t events)
+{
+	struct socket *sock = file->private_data;
 
 	/*
-	 *      We can't return errors to poll, so it's either yes or no.
+	 * We need to be sure we are in sync with the socket flags modification.
+	 *
+	 * This memory barrier is paired in the wq_has_sleeper.
 	 */
-	sock = file->private_data;
+	smp_mb();
 
-	if (sk_can_busy_loop(sock->sk)) {
-		/* this socket can poll_ll so tell the system call */
-		busy_flag = POLL_BUSY_LOOP;
+	/* this socket can poll_ll so tell the system call */
+	return sock->ops->poll_mask(sock, events) |
+		(sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0);
+}
+
+/* No kernel lock held - perfect */
+static __poll_t sock_poll(struct file *file, poll_table *wait)
+{
+	struct socket *sock = file->private_data;
+	__poll_t events = poll_requested_events(wait), mask = 0;
 
-		/* once, only if requested by syscall */
-		if (wait && (wait->_key & POLL_BUSY_LOOP))
-			sk_busy_loop(sock->sk, 1);
+	if (sock->ops->poll) {
+		sock_poll_busy_loop(sock, events);
+		mask = sock->ops->poll(file, sock, wait);
+	} else if (sock->ops->poll_mask) {
+		sock_poll_wait(file, sock_get_poll_head(file, events), wait);
+		mask = sock->ops->poll_mask(sock, events);
 	}
 
-	return busy_flag | sock->ops->poll(file, sock, wait);
+	return mask | sock_poll_busy_flag(sock);
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1420,6 +1445,13 @@ int __sys_socketpair(int family, int type, int protocol, int __user *usockvec)
 		goto out;
 	}
 
+	err = security_socket_socketpair(sock1, sock2);
+	if (unlikely(err)) {
+		sock_release(sock2);
+		sock_release(sock1);
+		goto out;
+	}
+
 	err = sock1->ops->socketpair(sock1, sock2);
 	if (unlikely(err < 0)) {
 		sock_release(sock2);
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index b9283ce5cd85..092bebc70048 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
 
 static void strp_start_timer(struct strparser *strp, long timeo)
 {
-	if (timeo)
+	if (timeo && timeo != LONG_MAX)
 		mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
 }
 
@@ -296,9 +296,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 					strp_start_timer(strp, timeo);
 				}
 
+				stm->accum_len += cand_len;
 				strp->need_bytes = stm->strp.full_len -
 						       stm->accum_len;
-				stm->accum_len += cand_len;
 				stm->early_eaten = cand_len;
 				STRP_STATS_ADD(strp->stats.bytes, cand_len);
 				desc->count = 0; /* Stop reading socket */
@@ -321,6 +321,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 		/* Hurray, we have a new message! */
 		cancel_delayed_work(&strp->msg_timer_work);
 		strp->skb_head = NULL;
+		strp->need_bytes = 0;
 		STRP_STATS_INCR(strp->stats.msgs);
 
 		/* Give skb to upper layer */
@@ -410,9 +411,7 @@ void strp_data_ready(struct strparser *strp)
 		return;
 
 	if (strp->need_bytes) {
-		if (strp_peek_len(strp) >= strp->need_bytes)
-			strp->need_bytes = 0;
-		else
+		if (strp_peek_len(strp) < strp->need_bytes)
 			return;
 	}
 
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 0f08934b2cea..4fda18d47e2c 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -609,22 +609,6 @@ static int __rpc_rmdir(struct inode *dir, struct dentry *dentry)
 	return ret;
 }
 
-int rpc_rmdir(struct dentry *dentry)
-{
-	struct dentry *parent;
-	struct inode *dir;
-	int error;
-
-	parent = dget_parent(dentry);
-	dir = d_inode(parent);
-	inode_lock_nested(dir, I_MUTEX_PARENT);
-	error = __rpc_rmdir(dir, dentry);
-	inode_unlock(dir);
-	dput(parent);
-	return error;
-}
-EXPORT_SYMBOL_GPL(rpc_rmdir);
-
 static int __rpc_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int ret;
@@ -1375,6 +1359,7 @@ rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry)
 	struct dentry *clnt_dir = pipe_dentry->d_parent;
 	struct dentry *gssd_dir = clnt_dir->d_parent;
 
+	dget(pipe_dentry);
 	__rpc_rmpipe(d_inode(clnt_dir), pipe_dentry);
 	__rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1);
 	__rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1);
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 5cc68a824f45..f2f63959fddd 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -72,6 +72,7 @@ fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr)
 	if (IS_ERR(mr->fmr.fm_mr))
 		goto out_fmr_err;
 
+	INIT_LIST_HEAD(&mr->mr_list);
 	return 0;
 
 out_fmr_err:
@@ -102,10 +103,6 @@ fmr_op_release_mr(struct rpcrdma_mr *mr)
 	LIST_HEAD(unmap_list);
 	int rc;
 
-	/* Ensure MW is not on any rl_registered list */
-	if (!list_empty(&mr->mr_list))
-		list_del(&mr->mr_list);
-
 	kfree(mr->fmr.fm_physaddrs);
 	kfree(mr->mr_sg);
 
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index c5743a0960be..c59c5c788db0 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -110,6 +110,7 @@ frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr)
 	if (!mr->mr_sg)
 		goto out_list_err;
 
+	INIT_LIST_HEAD(&mr->mr_list);
 	sg_init_table(mr->mr_sg, depth);
 	init_completion(&frwr->fr_linv_done);
 	return 0;
@@ -133,10 +134,6 @@ frwr_op_release_mr(struct rpcrdma_mr *mr)
 {
 	int rc;
 
-	/* Ensure MR is not on any rl_registered list */
-	if (!list_empty(&mr->mr_list))
-		list_del(&mr->mr_list);
-
 	rc = ib_dereg_mr(mr->frwr.fr_mr);
 	if (rc)
 		pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n",
@@ -195,7 +192,7 @@ frwr_op_recover_mr(struct rpcrdma_mr *mr)
 	return;
 
 out_release:
-	pr_err("rpcrdma: FRWR reset failed %d, %p release\n", rc, mr);
+	pr_err("rpcrdma: FRWR reset failed %d, %p released\n", rc, mr);
 	r_xprt->rx_stats.mrs_orphaned++;
 
 	spin_lock(&r_xprt->rx_buf.rb_mrlock);
@@ -476,7 +473,7 @@ frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs)
 
 	list_for_each_entry(mr, mrs, mr_list)
 		if (mr->mr_handle == rep->rr_inv_rkey) {
-			list_del(&mr->mr_list);
+			list_del_init(&mr->mr_list);
 			trace_xprtrdma_remoteinv(mr);
 			mr->frwr.fr_state = FRWR_IS_INVALID;
 			rpcrdma_mr_unmap_and_put(mr);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index fe5eaca2d197..c345d365af88 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1254,6 +1254,11 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf)
 		list_del(&mr->mr_all);
 
 		spin_unlock(&buf->rb_mrlock);
+
+		/* Ensure MW is not on any rl_registered list */
+		if (!list_empty(&mr->mr_list))
+			list_del(&mr->mr_list);
+
 		ia->ri_ops->ro_release_mr(mr);
 		count++;
 		spin_lock(&buf->rb_mrlock);
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 3d3b423fa9c1..cb41b12a3bf8 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -380,7 +380,7 @@ rpcrdma_mr_pop(struct list_head *list)
 	struct rpcrdma_mr *mr;
 
 	mr = list_first_entry(list, struct rpcrdma_mr, mr_list);
-	list_del(&mr->mr_list);
+	list_del_init(&mr->mr_list);
 	return mr;
 }
 
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 32dc33a94bc7..5453e564da82 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -777,7 +777,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
 
 	ret = tipc_bearer_get_name(net, bearer_name, bearer_id);
 	if (ret || !mon)
-		return -EINVAL;
+		return 0;
 
 	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
 			  NLM_F_MULTI, TIPC_NL_MON_GET);
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index b1fe20972aa9..dd1c4fa2eb78 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -241,7 +241,8 @@ err:
 static struct publication *tipc_service_remove_publ(struct net *net,
 						    struct tipc_service *sc,
 						    u32 lower, u32 upper,
-						    u32 node, u32 key)
+						    u32 node, u32 key,
+						    struct service_range **rng)
 {
 	struct tipc_subscription *sub, *tmp;
 	struct service_range *sr;
@@ -275,19 +276,15 @@ static struct publication *tipc_service_remove_publ(struct net *net,
 
 	list_del(&p->all_publ);
 	list_del(&p->local_publ);
-
-	/* Remove service range item if this was its last publication */
-	if (list_empty(&sr->all_publ)) {
+	if (list_empty(&sr->all_publ))
 		last = true;
-		rb_erase(&sr->tree_node, &sc->ranges);
-		kfree(sr);
-	}
 
 	/* Notify any waiting subscriptions */
 	list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) {
 		tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_WITHDRAWN,
 					p->port, p->node, p->scope, last);
 	}
+	*rng = sr;
 	return p;
 }
 
@@ -379,13 +376,20 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
 					     u32 node, u32 key)
 {
 	struct tipc_service *sc = tipc_service_find(net, type);
+	struct service_range *sr = NULL;
 	struct publication *p = NULL;
 
 	if (!sc)
 		return NULL;
 
 	spin_lock_bh(&sc->lock);
-	p = tipc_service_remove_publ(net, sc, lower, upper, node, key);
+	p = tipc_service_remove_publ(net, sc, lower, upper, node, key, &sr);
+
+	/* Remove service range item if this was its last publication */
+	if (sr && list_empty(&sr->all_publ)) {
+		rb_erase(&sr->tree_node, &sc->ranges);
+		kfree(sr);
+	}
 
 	/* Delete service item if this no more publications and subscriptions */
 	if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) {
@@ -665,13 +669,14 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower,
 /**
  * tipc_nametbl_subscribe - add a subscription object to the name table
  */
-void tipc_nametbl_subscribe(struct tipc_subscription *sub)
+bool tipc_nametbl_subscribe(struct tipc_subscription *sub)
 {
 	struct name_table *nt = tipc_name_table(sub->net);
 	struct tipc_net *tn = tipc_net(sub->net);
 	struct tipc_subscr *s = &sub->evt.s;
 	u32 type = tipc_sub_read(s, seq.type);
 	struct tipc_service *sc;
+	bool res = true;
 
 	spin_lock_bh(&tn->nametbl_lock);
 	sc = tipc_service_find(sub->net, type);
@@ -685,8 +690,10 @@ void tipc_nametbl_subscribe(struct tipc_subscription *sub)
 		pr_warn("Failed to subscribe for {%u,%u,%u}\n", type,
 			tipc_sub_read(s, seq.lower),
 			tipc_sub_read(s, seq.upper));
+		res = false;
 	}
 	spin_unlock_bh(&tn->nametbl_lock);
+	return res;
 }
 
 /**
@@ -744,16 +751,17 @@ int tipc_nametbl_init(struct net *net)
 static void tipc_service_delete(struct net *net, struct tipc_service *sc)
 {
 	struct service_range *sr, *tmpr;
-	struct publication *p, *tmpb;
+	struct publication *p, *tmp;
 
 	spin_lock_bh(&sc->lock);
 	rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) {
-		list_for_each_entry_safe(p, tmpb,
-					 &sr->all_publ, all_publ) {
+		list_for_each_entry_safe(p, tmp, &sr->all_publ, all_publ) {
 			tipc_service_remove_publ(net, sc, p->lower, p->upper,
-						 p->node, p->key);
+						 p->node, p->key, &sr);
 			kfree_rcu(p, rcu);
 		}
+		rb_erase(&sr->tree_node, &sc->ranges);
+		kfree(sr);
 	}
 	hlist_del_init_rcu(&sc->service_list);
 	spin_unlock_bh(&sc->lock);
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 4b14fc28d9e2..0febba41da86 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -126,7 +126,7 @@ struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type,
 struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
 					     u32 lower, u32 upper,
 					     u32 node, u32 key);
-void tipc_nametbl_subscribe(struct tipc_subscription *s);
+bool tipc_nametbl_subscribe(struct tipc_subscription *s);
 void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
 int tipc_nametbl_init(struct net *net);
 void tipc_nametbl_stop(struct net *net);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 856f9e97ea29..4fbaa0464405 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -252,6 +252,8 @@ int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
 		u64 *w0 = (u64 *)&node_id[0];
 		u64 *w1 = (u64 *)&node_id[8];
 
+		if (!attrs[TIPC_NLA_NET_NODEID_W1])
+			return -EINVAL;
 		*w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]);
 		*w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]);
 		tipc_net_init(net, node_id, 0);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index b76f13f6fea1..6ff2254088f6 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -79,7 +79,10 @@ const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
 
 const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
 	[TIPC_NLA_NET_UNSPEC]		= { .type = NLA_UNSPEC },
-	[TIPC_NLA_NET_ID]		= { .type = NLA_U32 }
+	[TIPC_NLA_NET_ID]		= { .type = NLA_U32 },
+	[TIPC_NLA_NET_ADDR]		= { .type = NLA_U32 },
+	[TIPC_NLA_NET_NODEID]		= { .type = NLA_U64 },
+	[TIPC_NLA_NET_NODEID_W1]	= { .type = NLA_U64 },
 };
 
 const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
diff --git a/net/tipc/node.c b/net/tipc/node.c
index c77dd2f3c589..f29549de9245 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1950,6 +1950,7 @@ out:
 int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
+	struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1];
 	struct tipc_nl_msg msg;
 	char *name;
 	int err;
@@ -1957,9 +1958,19 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
 	msg.portid = info->snd_portid;
 	msg.seq = info->snd_seq;
 
-	if (!info->attrs[TIPC_NLA_LINK_NAME])
+	if (!info->attrs[TIPC_NLA_LINK])
 		return -EINVAL;
-	name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]);
+
+	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
+			       info->attrs[TIPC_NLA_LINK],
+			       tipc_nl_link_policy, info->extack);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_LINK_NAME])
+		return -EINVAL;
+
+	name = nla_data(attrs[TIPC_NLA_LINK_NAME]);
 
 	msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!msg.skb)
@@ -2232,8 +2243,8 @@ int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb)
 	struct net *net = sock_net(skb->sk);
 	u32 prev_bearer = cb->args[0];
 	struct tipc_nl_msg msg;
+	int bearer_id;
 	int err;
-	int i;
 
 	if (prev_bearer == MAX_BEARERS)
 		return 0;
@@ -2243,16 +2254,13 @@ int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb)
 	msg.seq = cb->nlh->nlmsg_seq;
 
 	rtnl_lock();
-	for (i = prev_bearer; i < MAX_BEARERS; i++) {
-		prev_bearer = i;
-		err = __tipc_nl_add_monitor(net, &msg, prev_bearer);
+	for (bearer_id = prev_bearer; bearer_id < MAX_BEARERS; bearer_id++) {
+		err = __tipc_nl_add_monitor(net, &msg, bearer_id);
 		if (err)
-			goto out;
+			break;
 	}
-
-out:
 	rtnl_unlock();
-	cb->args[0] = prev_bearer;
+	cb->args[0] = bearer_id;
 
 	return skb->len;
 }
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1fd1c8b5ce03..3bb45042e833 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -692,10 +692,9 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 }
 
 /**
- * tipc_poll - read and possibly block on pollmask
+ * tipc_poll - read pollmask
  * @file: file structure associated with the socket
  * @sock: socket for which to calculate the poll bits
- * @wait: ???
  *
  * Returns pollmask value
  *
@@ -709,15 +708,12 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
  * imply that the operation will succeed, merely that it should be performed
  * and will not block.
  */
-static __poll_t tipc_poll(struct file *file, struct socket *sock,
-			      poll_table *wait)
+static __poll_t tipc_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
 	__poll_t revents = 0;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
-
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -1278,7 +1274,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	struct tipc_msg *hdr = &tsk->phdr;
 	struct tipc_name_seq *seq;
 	struct sk_buff_head pkts;
-	u32 dnode, dport;
+	u32 dport, dnode = 0;
 	u32 type, inst;
 	int mtu, rc;
 
@@ -1348,6 +1344,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 		msg_set_destnode(hdr, dnode);
 		msg_set_destport(hdr, dest->addr.id.ref);
 		msg_set_hdr_sz(hdr, BASIC_H_SIZE);
+	} else {
+		return -EINVAL;
 	}
 
 	/* Block or return if destination link is congested */
@@ -1514,10 +1512,10 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 
 	srcaddr->sock.family = AF_TIPC;
 	srcaddr->sock.addrtype = TIPC_ADDR_ID;
+	srcaddr->sock.scope = 0;
 	srcaddr->sock.addr.id.ref = msg_origport(hdr);
 	srcaddr->sock.addr.id.node = msg_orignode(hdr);
 	srcaddr->sock.addr.name.domain = 0;
-	srcaddr->sock.scope = 0;
 	m->msg_namelen = sizeof(struct sockaddr_tipc);
 
 	if (!msg_in_group(hdr))
@@ -1526,6 +1524,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 	/* Group message users may also want to know sending member's id */
 	srcaddr->member.family = AF_TIPC;
 	srcaddr->member.addrtype = TIPC_ADDR_NAME;
+	srcaddr->member.scope = 0;
 	srcaddr->member.addr.name.name.type = msg_nametype(hdr);
 	srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
 	srcaddr->member.addr.name.domain = 0;
@@ -3025,7 +3024,7 @@ static const struct proto_ops msg_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= tipc_getname,
-	.poll		= tipc_poll,
+	.poll_mask	= tipc_poll_mask,
 	.ioctl		= tipc_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= tipc_shutdown,
@@ -3046,7 +3045,7 @@ static const struct proto_ops packet_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
-	.poll		= tipc_poll,
+	.poll_mask	= tipc_poll_mask,
 	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
@@ -3067,7 +3066,7 @@ static const struct proto_ops stream_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
-	.poll		= tipc_poll,
+	.poll_mask	= tipc_poll_mask,
 	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index b7d80bc5f4ab..f340e53da625 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -153,7 +153,10 @@ struct tipc_subscription *tipc_sub_subscribe(struct net *net,
 	memcpy(&sub->evt.s, s, sizeof(*s));
 	spin_lock_init(&sub->lock);
 	kref_init(&sub->kref);
-	tipc_nametbl_subscribe(sub);
+	if (!tipc_nametbl_subscribe(sub)) {
+		kfree(sub);
+		return NULL;
+	}
 	timer_setup(&sub->timer, tipc_sub_timeout, 0);
 	timeout = tipc_sub_read(&sub->evt.s, timeout);
 	if (timeout != TIPC_WAIT_FOREVER)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 0d379970960e..20cd93be6236 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -114,6 +114,7 @@ int tls_push_sg(struct sock *sk,
 	size = sg->length - offset;
 	offset += sg->offset;
 
+	ctx->in_tcp_sendpages = true;
 	while (1) {
 		if (sg_is_last(sg))
 			sendpage_flags = flags;
@@ -134,6 +135,7 @@ retry:
 			offset -= sg->offset;
 			ctx->partially_sent_offset = offset;
 			ctx->partially_sent_record = (void *)sg;
+			ctx->in_tcp_sendpages = false;
 			return ret;
 		}
 
@@ -148,6 +150,8 @@ retry:
 	}
 
 	clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags);
+	ctx->in_tcp_sendpages = false;
+	ctx->sk_write_space(sk);
 
 	return 0;
 }
@@ -217,6 +221,10 @@ static void tls_write_space(struct sock *sk)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
 
+	/* We are already sending pages, ignore notification */
+	if (ctx->in_tcp_sendpages)
+		return;
+
 	if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) {
 		gfp_t sk_allocation = sk->sk_allocation;
 		int rc;
@@ -241,16 +249,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	struct tls_context *ctx = tls_get_ctx(sk);
 	long timeo = sock_sndtimeo(sk, 0);
 	void (*sk_proto_close)(struct sock *sk, long timeout);
+	bool free_ctx = false;
 
 	lock_sock(sk);
 	sk_proto_close = ctx->sk_proto_close;
 
-	if (ctx->conf == TLS_HW_RECORD)
-		goto skip_tx_cleanup;
-
-	if (ctx->conf == TLS_BASE) {
-		kfree(ctx);
-		ctx = NULL;
+	if (ctx->conf == TLS_BASE || ctx->conf == TLS_HW_RECORD) {
+		free_ctx = true;
 		goto skip_tx_cleanup;
 	}
 
@@ -287,7 +292,7 @@ skip_tx_cleanup:
 	/* free ctx for TLS_HW_RECORD, used by tcp_set_state
 	 * for sk->sk_prot->unhash [tls_hw_unhash]
 	 */
-	if (ctx && ctx->conf == TLS_HW_RECORD)
+	if (free_ctx)
 		kfree(ctx);
 }
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4dc766b03f00..e1c93ce74e0f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -41,6 +41,8 @@
 #include <net/strparser.h>
 #include <net/tls.h>
 
+#define MAX_IV_SIZE	TLS_CIPHER_AES_GCM_128_IV_SIZE
+
 static int tls_do_decryption(struct sock *sk,
 			     struct scatterlist *sgin,
 			     struct scatterlist *sgout,
@@ -673,12 +675,11 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
-	char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + tls_ctx->rx.iv_size];
+	char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + MAX_IV_SIZE];
 	struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2];
 	struct scatterlist *sgin = &sgin_arr[0];
 	struct strp_msg *rxm = strp_msg(skb);
 	int ret, nsg = ARRAY_SIZE(sgin_arr);
-	char aad_recv[TLS_AAD_SPACE_SIZE];
 	struct sk_buff *unused;
 
 	ret = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
@@ -696,13 +697,13 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 	}
 
 	sg_init_table(sgin, nsg);
-	sg_set_buf(&sgin[0], aad_recv, sizeof(aad_recv));
+	sg_set_buf(&sgin[0], ctx->rx_aad_ciphertext, TLS_AAD_SPACE_SIZE);
 
 	nsg = skb_to_sgvec(skb, &sgin[1],
 			   rxm->offset + tls_ctx->rx.prepend_size,
 			   rxm->full_len - tls_ctx->rx.prepend_size);
 
-	tls_make_aad(aad_recv,
+	tls_make_aad(ctx->rx_aad_ciphertext,
 		     rxm->full_len - tls_ctx->rx.overhead_size,
 		     tls_ctx->rx.rec_seq,
 		     tls_ctx->rx.rec_seq_size,
@@ -801,12 +802,12 @@ int tls_sw_recvmsg(struct sock *sk,
 			if (to_copy <= len && page_count < MAX_SKB_FRAGS &&
 			    likely(!(flags & MSG_PEEK)))  {
 				struct scatterlist sgin[MAX_SKB_FRAGS + 1];
-				char unused[21];
 				int pages = 0;
 
 				zc = true;
 				sg_init_table(sgin, MAX_SKB_FRAGS + 1);
-				sg_set_buf(&sgin[0], unused, 13);
+				sg_set_buf(&sgin[0], ctx->rx_aad_plaintext,
+					   TLS_AAD_SPACE_SIZE);
 
 				err = zerocopy_from_iter(sk, &msg->msg_iter,
 							 to_copy, &pages,
@@ -1094,6 +1095,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		goto free_priv;
 	}
 
+	/* Sanity-check the IV size for stack allocations. */
+	if (iv_size > MAX_IV_SIZE) {
+		rc = -EINVAL;
+		goto free_priv;
+	}
+
 	cctx->prepend_size = TLS_HEADER_SIZE + nonce_size;
 	cctx->tag_size = tag_size;
 	cctx->overhead_size = cctx->prepend_size + cctx->tag_size;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 68bb70a62afe..95b02a71fd47 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -638,9 +638,8 @@ static int unix_stream_connect(struct socket *, struct sockaddr *,
 static int unix_socketpair(struct socket *, struct socket *);
 static int unix_accept(struct socket *, struct socket *, int, bool);
 static int unix_getname(struct socket *, struct sockaddr *, int);
-static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
-static __poll_t unix_dgram_poll(struct file *, struct socket *,
-				    poll_table *);
+static __poll_t unix_poll_mask(struct socket *, __poll_t);
+static __poll_t unix_dgram_poll_mask(struct socket *, __poll_t);
 static int unix_ioctl(struct socket *, unsigned int, unsigned long);
 static int unix_shutdown(struct socket *, int);
 static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
@@ -681,7 +680,7 @@ static const struct proto_ops unix_stream_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	unix_accept,
 	.getname =	unix_getname,
-	.poll =		unix_poll,
+	.poll_mask =	unix_poll_mask,
 	.ioctl =	unix_ioctl,
 	.listen =	unix_listen,
 	.shutdown =	unix_shutdown,
@@ -704,7 +703,7 @@ static const struct proto_ops unix_dgram_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	unix_getname,
-	.poll =		unix_dgram_poll,
+	.poll_mask =	unix_dgram_poll_mask,
 	.ioctl =	unix_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	unix_shutdown,
@@ -726,7 +725,7 @@ static const struct proto_ops unix_seqpacket_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	unix_accept,
 	.getname =	unix_getname,
-	.poll =		unix_dgram_poll,
+	.poll_mask =	unix_dgram_poll_mask,
 	.ioctl =	unix_ioctl,
 	.listen =	unix_listen,
 	.shutdown =	unix_shutdown,
@@ -2630,13 +2629,10 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	return err;
 }
 
-static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
+static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	__poll_t mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err)
@@ -2665,15 +2661,11 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 	return mask;
 }
 
-static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
-				    poll_table *wait)
+static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk, *other;
-	unsigned int writable;
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	int writable;
+	__poll_t mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -2699,7 +2691,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 	}
 
 	/* No write status requested, avoid expensive OUT tests. */
-	if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
+	if (!(events & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
 		return mask;
 
 	writable = unix_writable(sk);
@@ -2852,20 +2844,6 @@ static const struct seq_operations unix_seq_ops = {
 	.stop   = unix_seq_stop,
 	.show   = unix_seq_show,
 };
-
-static int unix_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &unix_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations unix_seq_fops = {
-	.open		= unix_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
-};
-
 #endif
 
 static const struct net_proto_family unix_family_ops = {
@@ -2884,7 +2862,8 @@ static int __net_init unix_net_init(struct net *net)
 		goto out;
 
 #ifdef CONFIG_PROC_FS
-	if (!proc_create("unix", 0, net->proc_net, &unix_seq_fops)) {
+	if (!proc_create_net("unix", 0, net->proc_net, &unix_seq_ops,
+			sizeof(struct seq_net_private))) {
 		unix_sysctl_unregister(net);
 		goto out;
 	}
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index aac9b8f6552e..bb5d5fa68c35 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -850,18 +850,11 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	return err;
 }
 
-static __poll_t vsock_poll(struct file *file, struct socket *sock,
-			       poll_table *wait)
+static __poll_t vsock_poll_mask(struct socket *sock, __poll_t events)
 {
-	struct sock *sk;
-	__poll_t mask;
-	struct vsock_sock *vsk;
-
-	sk = sock->sk;
-	vsk = vsock_sk(sk);
-
-	poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	struct sock *sk = sock->sk;
+	struct vsock_sock *vsk = vsock_sk(sk);
+	__poll_t mask = 0;
 
 	if (sk->sk_err)
 		/* Signify that there has been an error on this socket. */
@@ -1091,7 +1084,7 @@ static const struct proto_ops vsock_dgram_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = vsock_getname,
-	.poll = vsock_poll,
+	.poll_mask = vsock_poll_mask,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = vsock_shutdown,
@@ -1849,7 +1842,7 @@ static const struct proto_ops vsock_stream_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = vsock_accept,
 	.getname = vsock_getname,
-	.poll = vsock_poll,
+	.poll_mask = vsock_poll_mask,
 	.ioctl = sock_no_ioctl,
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,
@@ -2018,7 +2011,13 @@ const struct vsock_transport *vsock_core_get_transport(void)
 }
 EXPORT_SYMBOL_GPL(vsock_core_get_transport);
 
+static void __exit vsock_exit(void)
+{
+	/* Do nothing.  This function makes this module removable. */
+}
+
 module_init(vsock_init_tables);
+module_exit(vsock_exit);
 
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMware Virtual Socket Family");
diff --git a/net/wireless/core.c b/net/wireless/core.c
index a6f3cac8c640..c0fd8a85e7f7 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -95,6 +95,9 @@ static int cfg80211_dev_check_name(struct cfg80211_registered_device *rdev,
 
 	ASSERT_RTNL();
 
+	if (strlen(newname) > NL80211_WIPHY_NAME_MAXLEN)
+		return -EINVAL;
+
 	/* prohibit calling the thing phy%d when %d is not its number */
 	sscanf(newname, PHY_NAME "%d%n", &wiphy_idx, &taken);
 	if (taken == strlen(newname) && wiphy_idx != rdev->wiphy_idx) {
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ff28f8feeb09..7c5135a92d76 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9214,6 +9214,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 
 	if (nla_get_flag(info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])) {
 		if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) {
+			kzfree(connkeys);
 			GENL_SET_ERR_MSG(info,
 					 "external auth requires connection ownership");
 			return -EINVAL;
@@ -15554,7 +15555,8 @@ void cfg80211_ft_event(struct net_device *netdev,
 	if (!ft_event->target_ap)
 		return;
 
-	msg = nlmsg_new(100 + ft_event->ric_ies_len, GFP_KERNEL);
+	msg = nlmsg_new(100 + ft_event->ies_len + ft_event->ric_ies_len,
+			GFP_KERNEL);
 	if (!msg)
 		return;
 
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 16c7e4ef5820..5fcec5c94eb7 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -916,6 +916,9 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr,
 	const struct fwdb_header *hdr = regdb;
 	const struct fwdb_country *country;
 
+	if (!regdb)
+		return -ENODATA;
+
 	if (IS_ERR(regdb))
 		return PTR_ERR(regdb);
 
@@ -1026,6 +1029,7 @@ static int regdb_query_country(const struct fwdb_header *db,
 
 			if (!tmp_rd) {
 				kfree(regdom);
+				kfree(wmm_ptrs);
 				return -ENOMEM;
 			}
 			regdom = tmp_rd;
diff --git a/net/wireless/wext-proc.c b/net/wireless/wext-proc.c
index b4c464594a5e..cadcf8613af2 100644
--- a/net/wireless/wext-proc.c
+++ b/net/wireless/wext-proc.c
@@ -126,24 +126,11 @@ static const struct seq_operations wireless_seq_ops = {
 	.show  = wireless_dev_seq_show,
 };
 
-static int seq_open_wireless(struct inode *inode, struct file *file)
-{
-	return seq_open_net(inode, file, &wireless_seq_ops,
-			    sizeof(struct seq_net_private));
-}
-
-static const struct file_operations wireless_seq_fops = {
-	.open    = seq_open_wireless,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_net,
-};
-
 int __net_init wext_proc_init(struct net *net)
 {
 	/* Create /proc/net/wireless entry */
-	if (!proc_create("wireless", 0444, net->proc_net,
-			 &wireless_seq_fops))
+	if (!proc_create_net("wireless", 0444, net->proc_net,
+			&wireless_seq_ops, sizeof(struct seq_net_private)))
 		return -ENOMEM;
 
 	return 0;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index d49aa79b7997..f93365ae0fdd 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1750,7 +1750,7 @@ static const struct proto_ops x25_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	x25_accept,
 	.getname =	x25_getname,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	x25_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = compat_x25_ioctl,
diff --git a/net/x25/x25_proc.c b/net/x25/x25_proc.c
index 64b415e93f6a..da52c9dc256c 100644
--- a/net/x25/x25_proc.c
+++ b/net/x25/x25_proc.c
@@ -171,57 +171,21 @@ static const struct seq_operations x25_seq_forward_ops = {
 	.show   = x25_seq_forward_show,
 };
 
-static int x25_seq_socket_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &x25_seq_socket_ops);
-}
-
-static int x25_seq_route_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &x25_seq_route_ops);
-}
-
-static int x25_seq_forward_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &x25_seq_forward_ops);
-}
-
-static const struct file_operations x25_seq_socket_fops = {
-	.open		= x25_seq_socket_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations x25_seq_route_fops = {
-	.open		= x25_seq_route_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations x25_seq_forward_fops = {
-	.open		= x25_seq_forward_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 int __init x25_proc_init(void)
 {
 	if (!proc_mkdir("x25", init_net.proc_net))
 		return -ENOMEM;
 
-	if (!proc_create("x25/route", 0444, init_net.proc_net,
-			 &x25_seq_route_fops))
+	if (!proc_create_seq("x25/route", 0444, init_net.proc_net,
+			 &x25_seq_route_ops))
 		goto out;
 
-	if (!proc_create("x25/socket", 0444, init_net.proc_net,
-			 &x25_seq_socket_fops))
+	if (!proc_create_seq("x25/socket", 0444, init_net.proc_net,
+			 &x25_seq_socket_ops))
 		goto out;
 
-	if (!proc_create("x25/forward", 0444, init_net.proc_net,
-			 &x25_seq_forward_fops))
+	if (!proc_create_seq("x25/forward", 0444, init_net.proc_net,
+			 &x25_seq_forward_ops))
 		goto out;
 	return 0;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 40b54cc64243..5f48251c1319 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1658,7 +1658,6 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len;
 	}
 
-out:
 	return &xdst0->u.dst;
 
 put_states:
@@ -1667,8 +1666,8 @@ put_states:
 free_dst:
 	if (xdst0)
 		dst_release_immediate(&xdst0->u.dst);
-	xdst0 = ERR_PTR(err);
-	goto out;
+
+	return ERR_PTR(err);
 }
 
 static int xfrm_expand_policies(const struct flowi *fl, u16 family,
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
index ed06903cd84d..178318d2e120 100644
--- a/net/xfrm/xfrm_proc.c
+++ b/net/xfrm/xfrm_proc.c
@@ -65,22 +65,10 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int xfrm_statistics_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, xfrm_statistics_seq_show);
-}
-
-static const struct file_operations xfrm_statistics_seq_fops = {
-	.open	 = xfrm_statistics_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release_net,
-};
-
 int __net_init xfrm_proc_init(struct net *net)
 {
-	if (!proc_create("xfrm_stat", 0444, net->proc_net,
-			 &xfrm_statistics_seq_fops))
+	if (!proc_create_net_single("xfrm_stat", 0444, net->proc_net,
+			 xfrm_statistics_seq_show, NULL))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f9d2f2233f09..6c177ae7a6d9 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2175,6 +2175,12 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
 	return afinfo;
 }
 
+void xfrm_flush_gc(void)
+{
+	flush_work(&xfrm_state_gc_work);
+}
+EXPORT_SYMBOL(xfrm_flush_gc);
+
 /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
 void xfrm_state_delete_tunnel(struct xfrm_state *x)
 {
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4d6a6edd4bf6..092947676143 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -255,7 +255,7 @@ $(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
 $(obj)/%.o: $(src)/%.c
 	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
 		-I$(srctree)/tools/testing/selftests/bpf/ \
-		-D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
+		-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
 		-D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c
index 830c55514f9f..49b13553eaae 100644
--- a/samples/livepatch/livepatch-shadow-fix1.c
+++ b/samples/livepatch/livepatch-shadow-fix1.c
@@ -56,6 +56,21 @@ struct dummy {
 	unsigned long jiffies_expire;
 };
 
+/*
+ * The constructor makes more sense together with klp_shadow_get_or_alloc().
+ * In this example, it would be safe to assign the pointer also to the shadow
+ * variable returned by klp_shadow_alloc().  But we wanted to show the more
+ * complicated use of the API.
+ */
+static int shadow_leak_ctor(void *obj, void *shadow_data, void *ctor_data)
+{
+	void **shadow_leak = shadow_data;
+	void *leak = ctor_data;
+
+	*shadow_leak = leak;
+	return 0;
+}
+
 struct dummy *livepatch_fix1_dummy_alloc(void)
 {
 	struct dummy *d;
@@ -74,7 +89,8 @@ struct dummy *livepatch_fix1_dummy_alloc(void)
 	 * pointer to handle resource release.
 	 */
 	leak = kzalloc(sizeof(int), GFP_KERNEL);
-	klp_shadow_alloc(d, SV_LEAK, &leak, sizeof(leak), GFP_KERNEL);
+	klp_shadow_alloc(d, SV_LEAK, sizeof(leak), GFP_KERNEL,
+			 shadow_leak_ctor, leak);
 
 	pr_info("%s: dummy @ %p, expires @ %lx\n",
 		__func__, d, d->jiffies_expire);
@@ -82,9 +98,19 @@ struct dummy *livepatch_fix1_dummy_alloc(void)
 	return d;
 }
 
+static void livepatch_fix1_dummy_leak_dtor(void *obj, void *shadow_data)
+{
+	void *d = obj;
+	void **shadow_leak = shadow_data;
+
+	kfree(*shadow_leak);
+	pr_info("%s: dummy @ %p, prevented leak @ %p\n",
+			 __func__, d, *shadow_leak);
+}
+
 void livepatch_fix1_dummy_free(struct dummy *d)
 {
-	void **shadow_leak, *leak;
+	void **shadow_leak;
 
 	/*
 	 * Patch: fetch the saved SV_LEAK shadow variable, detach and
@@ -93,15 +119,10 @@ void livepatch_fix1_dummy_free(struct dummy *d)
 	 * was loaded.)
 	 */
 	shadow_leak = klp_shadow_get(d, SV_LEAK);
-	if (shadow_leak) {
-		leak = *shadow_leak;
-		klp_shadow_free(d, SV_LEAK);
-		kfree(leak);
-		pr_info("%s: dummy @ %p, prevented leak @ %p\n",
-			 __func__, d, leak);
-	} else {
+	if (shadow_leak)
+		klp_shadow_free(d, SV_LEAK, livepatch_fix1_dummy_leak_dtor);
+	else
 		pr_info("%s: dummy @ %p leaked!\n", __func__, d);
-	}
 
 	kfree(d);
 }
@@ -147,7 +168,7 @@ static int livepatch_shadow_fix1_init(void)
 static void livepatch_shadow_fix1_exit(void)
 {
 	/* Cleanup any existing SV_LEAK shadow variables */
-	klp_shadow_free_all(SV_LEAK);
+	klp_shadow_free_all(SV_LEAK, livepatch_fix1_dummy_leak_dtor);
 
 	WARN_ON(klp_unregister_patch(&patch));
 }
diff --git a/samples/livepatch/livepatch-shadow-fix2.c b/samples/livepatch/livepatch-shadow-fix2.c
index ff9948f0ec00..b34c7bf83356 100644
--- a/samples/livepatch/livepatch-shadow-fix2.c
+++ b/samples/livepatch/livepatch-shadow-fix2.c
@@ -53,39 +53,42 @@ struct dummy {
 bool livepatch_fix2_dummy_check(struct dummy *d, unsigned long jiffies)
 {
 	int *shadow_count;
-	int count;
 
 	/*
 	 * Patch: handle in-flight dummy structures, if they do not
 	 * already have a SV_COUNTER shadow variable, then attach a
 	 * new one.
 	 */
-	count = 0;
 	shadow_count = klp_shadow_get_or_alloc(d, SV_COUNTER,
-					       &count, sizeof(count),
-					       GFP_NOWAIT);
+				sizeof(*shadow_count), GFP_NOWAIT,
+				NULL, NULL);
 	if (shadow_count)
 		*shadow_count += 1;
 
 	return time_after(jiffies, d->jiffies_expire);
 }
 
+static void livepatch_fix2_dummy_leak_dtor(void *obj, void *shadow_data)
+{
+	void *d = obj;
+	void **shadow_leak = shadow_data;
+
+	kfree(*shadow_leak);
+	pr_info("%s: dummy @ %p, prevented leak @ %p\n",
+			 __func__, d, *shadow_leak);
+}
+
 void livepatch_fix2_dummy_free(struct dummy *d)
 {
-	void **shadow_leak, *leak;
+	void **shadow_leak;
 	int *shadow_count;
 
 	/* Patch: copy the memory leak patch from the fix1 module. */
 	shadow_leak = klp_shadow_get(d, SV_LEAK);
-	if (shadow_leak) {
-		leak = *shadow_leak;
-		klp_shadow_free(d, SV_LEAK);
-		kfree(leak);
-		pr_info("%s: dummy @ %p, prevented leak @ %p\n",
-			 __func__, d, leak);
-	} else {
+	if (shadow_leak)
+		klp_shadow_free(d, SV_LEAK, livepatch_fix2_dummy_leak_dtor);
+	else
 		pr_info("%s: dummy @ %p leaked!\n", __func__, d);
-	}
 
 	/*
 	 * Patch: fetch the SV_COUNTER shadow variable and display
@@ -95,7 +98,7 @@ void livepatch_fix2_dummy_free(struct dummy *d)
 	if (shadow_count) {
 		pr_info("%s: dummy @ %p, check counter = %d\n",
 			__func__, d, *shadow_count);
-		klp_shadow_free(d, SV_COUNTER);
+		klp_shadow_free(d, SV_COUNTER, NULL);
 	}
 
 	kfree(d);
@@ -142,7 +145,7 @@ static int livepatch_shadow_fix2_init(void)
 static void livepatch_shadow_fix2_exit(void)
 {
 	/* Cleanup any existing SV_COUNTER shadow variables */
-	klp_shadow_free_all(SV_COUNTER);
+	klp_shadow_free_all(SV_COUNTER, NULL);
 
 	WARN_ON(klp_unregister_patch(&patch));
 }
diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile
index 9bf2881bd11b..fa53f4d77834 100644
--- a/samples/sockmap/Makefile
+++ b/samples/sockmap/Makefile
@@ -65,11 +65,14 @@ $(src)/*.c: verify_target_bpf
 # asm/sysreg.h - inline assembly used by it is incompatible with llvm.
 # But, there is no easy way to fix it, so just exclude it since it is
 # useless for BPF samples.
+#
+# -target bpf option required with SK_MSG programs, this is to ensure
+#  reading 'void *' data types for data and data_end are __u64 reads.
 $(obj)/%.o: $(src)/%.c
 	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
 		-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
 		-Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
-		-Wno-unknown-warning-option \
-		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
+		-Wno-unknown-warning-option -O2 -target bpf \
+		-emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 50cee534fd64..c8156d61678c 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -8,8 +8,6 @@ squote  := '
 empty   :=
 space   := $(empty) $(empty)
 space_escape := _-_SPACE_-_
-right_paren := )
-left_paren := (
 pound := \#
 
 ###
@@ -57,7 +55,6 @@ kecho := $($(quiet)kecho)
 #   to specify a valid file as first prerequisite (often the kbuild file)
 define filechk
 	$(Q)set -e;				\
-	$(kecho) '  CHK     $@';		\
 	mkdir -p $(dir $@);			\
 	$(filechk_$(1)) < $< > $@.tmp;		\
 	if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
@@ -83,71 +80,6 @@ cc-cross-prefix =  \
 			echo $(c);                                    \
 		fi)))
 
-# Tools for caching Makefile variables that are "expensive" to compute.
-#
-# Here we want to help deal with variables that take a long time to compute
-# by making it easy to store these variables in a cache.
-#
-# The canonical example here is testing for compiler flags.  On a simple system
-# each call to the compiler takes 10 ms, but on a system with a compiler that's
-# called through various wrappers it can take upwards of 100 ms.  If we have
-# 100 calls to the compiler this can take 1 second (on a simple system) or 10
-# seconds (on a complicated system).
-#
-# The "cache" will be in Makefile syntax and can be directly included.
-# Any time we try to reference a variable that's not in the cache we'll
-# calculate it and store it in the cache for next time.
-
-# Include values from last time
-make-cache := $(if $(KBUILD_EXTMOD),$(KBUILD_EXTMOD)/,$(if $(obj),$(obj)/)).cache.mk
-$(make-cache): ;
--include $(make-cache)
-
-cached-data := $(filter __cached_%, $(.VARIABLES))
-
-# If cache exceeds 1000 lines, shrink it down to 500.
-ifneq ($(word 1000,$(cached-data)),)
-$(shell tail -n 500 $(make-cache) > $(make-cache).tmp; \
-	mv $(make-cache).tmp $(make-cache))
-endif
-
-create-cache-dir := $(if $(KBUILD_SRC),$(if $(cache-data),,1))
-
-# Usage: $(call __sanitize-opt,Hello=Hola$(comma)Goodbye Adios)
-#
-# Convert all '$', ')', '(', '\', '=', ' ', ',', ':' to '_'
-__sanitize-opt = $(subst $$,_,$(subst $(right_paren),_,$(subst $(left_paren),_,$(subst \,_,$(subst =,_,$(subst $(space),_,$(subst $(comma),_,$(subst :,_,$(1)))))))))
-
-# Usage:   $(call shell-cached,shell_command)
-# Example: $(call shell-cached,md5sum /usr/bin/gcc)
-#
-# If we've already seen a call to this exact shell command (even in a
-# previous invocation of make!) we'll return the value.  If not, we'll
-# compute it and store the result for future runs.
-#
-# This is a bit of voodoo, but basic explanation is that if the variable
-# was undefined then we'll evaluate the shell command and store the result
-# into the variable.  We'll then store that value in the cache and finally
-# output the value.
-#
-# NOTE: The $$(2) here isn't actually a parameter to __run-and-store.  We
-# happen to know that the caller will have their shell command in $(2) so the
-# result of "call"ing this will produce a reference to that $(2).  The reason
-# for this strangeness is to avoid an extra level of eval (and escaping) of
-# $(2).
-define __run-and-store
-ifeq ($(origin $(1)),undefined)
-  $$(eval $(1) := $$(shell $$(2)))
-ifeq ($(create-cache-dir),1)
-  $$(shell mkdir -p $(dir $(make-cache)))
-  $$(eval create-cache-dir :=)
-endif
-  $$(shell echo '$(1) := $$($(1))' >> $(make-cache))
-endif
-endef
-__shell-cached = $(eval $(call __run-and-store,$(1)))$($(1))
-shell-cached = $(call __shell-cached,__cached_$(call __sanitize-opt,$(1)),$(1))
-
 # output directory for tests below
 TMPOUT := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/)
 
@@ -155,36 +87,30 @@ TMPOUT := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/)
 # Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
 # Exit code chooses option. "$$TMP" serves as a temporary file and is
 # automatically cleaned up.
-__try-run = set -e;			\
+try-run = $(shell set -e;		\
 	TMP="$(TMPOUT).$$$$.tmp";	\
 	TMPO="$(TMPOUT).$$$$.o";	\
 	if ($(1)) >/dev/null 2>&1;	\
 	then echo "$(2)";		\
 	else echo "$(3)";		\
 	fi;				\
-	rm -f "$$TMP" "$$TMPO"
-
-try-run = $(shell $(__try-run))
-
-# try-run-cached
-# This works like try-run, but the result is cached.
-try-run-cached = $(call shell-cached,$(__try-run))
+	rm -f "$$TMP" "$$TMPO")
 
 # as-option
 # Usage: cflags-y += $(call as-option,-Wa$(comma)-isa=foo,)
 
-as-option = $(call try-run-cached,\
+as-option = $(call try-run,\
 	$(CC) $(KBUILD_CFLAGS) $(1) -c -x assembler /dev/null -o "$$TMP",$(1),$(2))
 
 # as-instr
 # Usage: cflags-y += $(call as-instr,instr,option1,option2)
 
-as-instr = $(call try-run-cached,\
+as-instr = $(call try-run,\
 	printf "%b\n" "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
 
 # __cc-option
 # Usage: MY_CFLAGS += $(call __cc-option,$(CC),$(MY_CFLAGS),-march=winchip-c6,-march=i586)
-__cc-option = $(call try-run-cached,\
+__cc-option = $(call try-run,\
 	$(1) -Werror $(2) $(3) -c -x c /dev/null -o "$$TMP",$(3),$(4))
 
 # Do not attempt to build with gcc plugins during cc-option tests.
@@ -204,23 +130,23 @@ hostcc-option = $(call __cc-option, $(HOSTCC),\
 
 # cc-option-yn
 # Usage: flag := $(call cc-option-yn,-march=winchip-c6)
-cc-option-yn = $(call try-run-cached,\
+cc-option-yn = $(call try-run,\
 	$(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
 
 # cc-disable-warning
 # Usage: cflags-y += $(call cc-disable-warning,unused-but-set-variable)
-cc-disable-warning = $(call try-run-cached,\
+cc-disable-warning = $(call try-run,\
 	$(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
 
 # cc-name
 # Expands to either gcc or clang
-cc-name = $(call shell-cached,$(CC) -v 2>&1 | grep -q "clang version" && echo clang || echo gcc)
+cc-name = $(shell $(CC) -v 2>&1 | grep -q "clang version" && echo clang || echo gcc)
 
 # cc-version
-cc-version = $(call shell-cached,$(CONFIG_SHELL) $(srctree)/scripts/gcc-version.sh $(CC))
+cc-version = $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-version.sh $(CC))
 
 # cc-fullversion
-cc-fullversion = $(call shell-cached,$(CONFIG_SHELL) \
+cc-fullversion = $(shell $(CONFIG_SHELL) \
 	$(srctree)/scripts/gcc-version.sh -p $(CC))
 
 # cc-ifversion
@@ -233,21 +159,21 @@ cc-if-fullversion = $(shell [ $(cc-fullversion) $(1) $(2) ] && echo $(3) || echo
 
 # cc-ldoption
 # Usage: ldflags += $(call cc-ldoption, -Wl$(comma)--hash-style=both)
-cc-ldoption = $(call try-run-cached,\
+cc-ldoption = $(call try-run,\
 	$(CC) $(1) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
 
 # ld-option
 # Usage: LDFLAGS += $(call ld-option, -X)
-ld-option = $(call try-run-cached, $(LD) $(LDFLAGS) $(1) -v,$(1),$(2))
+ld-option = $(call try-run, $(LD) $(LDFLAGS) $(1) -v,$(1),$(2))
 
 # ar-option
 # Usage: KBUILD_ARFLAGS := $(call ar-option,D)
 # Important: no spaces around options
-ar-option = $(call try-run-cached, $(AR) rc$(1) "$$TMP",$(1),$(2))
+ar-option = $(call try-run, $(AR) rc$(1) "$$TMP",$(1),$(2))
 
 # ld-version
 # Note this is mainly for HJ Lu's 3 number binutil versions
-ld-version = $(call shell-cached,$(LD) --version | $(srctree)/scripts/ld-version.sh)
+ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh)
 
 # ld-ifversion
 # Usage:  $(call ld-ifversion, -ge, 22252, y)
diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include
new file mode 100644
index 000000000000..bf7c0c9fa3a4
--- /dev/null
+++ b/scripts/Kconfig.include
@@ -0,0 +1,27 @@
+# Kconfig helper macros
+
+# Convenient variables
+comma       := ,
+quote       := "
+squote      := '
+empty       :=
+space       := $(empty) $(empty)
+dollar      := $
+right_paren := )
+left_paren  := (
+
+# $(if-success,<command>,<then>,<else>)
+# Return <then> if <command> exits with 0, <else> otherwise.
+if-success = $(shell,{ $(1); } >/dev/null 2>&1 && echo "$(2)" || echo "$(3)")
+
+# $(success,<command>)
+# Return y if <command> exits with 0, n otherwise
+success = $(if-success,$(1),y,n)
+
+# $(cc-option,<flag>)
+# Return y if the compiler supports <flag>, n otherwise
+cc-option = $(success,$(CC) -Werror $(1) -E -x c /dev/null -o /dev/null)
+
+# $(ld-option,<flag>)
+# Return y if the linker supports <flag>, n otherwise
+ld-option = $(success,$(LD) -v $(1))
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 8bdb1dc4072c..753b9add56f5 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -147,7 +147,6 @@ $(obj)/%.i: $(src)/%.c FORCE
 cmd_gensymtypes_c =                                                         \
     $(CPP) -D__GENKSYMS__ $(c_flags) $< |                                   \
     $(GENKSYMS) $(if $(1), -T $(2))                                         \
-     $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX))             \
      $(patsubst y,-R,$(CONFIG_MODULE_REL_CRCS))                             \
      $(if $(KBUILD_PRESERVE),-p)                                            \
      -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null))
@@ -355,7 +354,6 @@ cmd_gensymtypes_S =                                                         \
      sed 's/.*___EXPORT_SYMBOL[[:space:]]*\([a-zA-Z0-9_]*\)[[:space:]]*,.*/EXPORT_SYMBOL(\1);/' ) | \
     $(CPP) -D__GENKSYMS__ $(c_flags) -xc - |                                \
     $(GENKSYMS) $(if $(1), -T $(2))                                         \
-     $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX))             \
      $(patsubst y,-R,$(CONFIG_MODULE_REL_CRCS))                             \
      $(if $(KBUILD_PRESERVE),-p)                                            \
      -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null))
@@ -487,15 +485,10 @@ targets += $(lib-target)
 
 dummy-object = $(obj)/.lib_exports.o
 ksyms-lds = $(dot-target).lds
-ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
-ref_prefix = EXTERN(_
-else
-ref_prefix = EXTERN(
-endif
 
 quiet_cmd_export_list = EXPORTS $@
 cmd_export_list = $(OBJDUMP) -h $< | \
-	sed -ne '/___ksymtab/s/.*+\([^ ]*\).*/$(ref_prefix)\1)/p' >$(ksyms-lds);\
+	sed -ne '/___ksymtab/s/.*+\([^ ]*\).*/EXTERN(\1)/p' >$(ksyms-lds);\
 	rm -f $(dummy-object);\
 	echo | $(CC) $(a_flags) -c -o $(dummy-object) -x assembler -;\
 	$(LD) $(ld_flags) -r -o $@ -T $(ksyms-lds) $(dummy-object);\
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index b2a95af7df18..7f5c86246138 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -14,7 +14,7 @@ ifdef CONFIG_GCC_PLUGINS
   endif
 
   ifdef CONFIG_GCC_PLUGIN_SANCOV
-    ifeq ($(CFLAGS_KCOV),)
+    ifeq ($(strip $(CFLAGS_KCOV)),)
       # It is needed because of the gcc-plugin.sh and gcc version checks.
       gcc-plugin-$(CONFIG_GCC_PLUGIN_SANCOV)           += sancov_plugin.so
 
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 07d07409f16f..5af34a2b0cd9 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -196,7 +196,7 @@ $(obj)/%.tab.c: $(src)/%.y FORCE
 	$(call if_changed,bison)
 
 quiet_cmd_bison_h = YACC    $@
-      cmd_bison_h = bison -o/dev/null --defines=$@ -t -l $<
+      cmd_bison_h = $(YACC) -o/dev/null --defines=$@ -t -l $<
 
 $(obj)/%.tab.h: $(src)/%.y FORCE
 	$(call if_changed,bison_h)
diff --git a/scripts/adjust_autoksyms.sh b/scripts/adjust_autoksyms.sh
index 016b3c48a4ec..6e6d63957da3 100755
--- a/scripts/adjust_autoksyms.sh
+++ b/scripts/adjust_autoksyms.sh
@@ -61,9 +61,6 @@ for mod in "$MODVERDIR"/*.mod; do
 	sed -n -e '3{s/ /\n/g;/^$/!p;}' "$mod"
 done | sort -u |
 while read sym; do
-	if [ -n "$CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX" ]; then
-		sym="${sym#_}"
-	fi
 	echo "#define __KSYM_${sym} 1"
 done >> "$new_ksyms_file"
 
diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c
index f387538c58bc..850966f3d602 100644
--- a/scripts/basic/fixdep.c
+++ b/scripts/basic/fixdep.c
@@ -115,7 +115,7 @@ static void usage(void)
  */
 static void print_dep(const char *m, int slen, const char *dir)
 {
-	int c, i;
+	int c, prev_c = '/', i;
 
 	printf("    $(wildcard %s/", dir);
 	for (i = 0; i < slen; i++) {
@@ -124,7 +124,9 @@ static void print_dep(const char *m, int slen, const char *dir)
 			c = '/';
 		else
 			c = tolower(c);
-		putchar(c);
+		if (c != '/' || prev_c != '/')
+			putchar(c);
+		prev_c = c;
 	}
 	printf(".h) \\\n");
 }
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index e16d6713f236..e6033d3c48d3 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -5041,7 +5041,7 @@ sub process {
 				$tmp_stmt =~ s/\b(typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g;
 				$tmp_stmt =~ s/\#+\s*$arg\b//g;
 				$tmp_stmt =~ s/\b$arg\s*\#\#//g;
-				my $use_cnt = $tmp_stmt =~ s/\b$arg\b//g;
+				my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g;
 				if ($use_cnt > 1) {
 					CHK("MACRO_ARG_REUSE",
 					    "Macro argument reuse '$arg' - possible side-effects?\n" . "$herectx");
@@ -5121,16 +5121,6 @@ sub process {
 			}
 		}
 
-# make sure symbols are always wrapped with VMLINUX_SYMBOL() ...
-# all assignments may have only one of the following with an assignment:
-#	.
-#	ALIGN(...)
-#	VMLINUX_SYMBOL(...)
-		if ($realfile eq 'vmlinux.lds.h' && $line =~ /(?:(?:^|\s)$Ident\s*=|=\s*$Ident(?:\s|$))/) {
-			WARN("MISSING_VMLINUX_SYMBOL",
-			     "vmlinux.lds.h needs VMLINUX_SYMBOL() around C-visible symbols\n" . $herecurr);
-		}
-
 # check for redundant bracing round if etc
 		if ($line =~ /(^.*)\bif\b/ && $1 !~ /else\s*$/) {
 			my ($level, $endln, @chunks) =
diff --git a/scripts/coccinelle/api/drm-get-put.cocci b/scripts/coccinelle/api/drm-get-put.cocci
index ceb71ea7f61c..3a09c97ad87d 100644
--- a/scripts/coccinelle/api/drm-get-put.cocci
+++ b/scripts/coccinelle/api/drm-get-put.cocci
@@ -40,12 +40,6 @@ expression object;
 - drm_gem_object_unreference_unlocked(object)
 + drm_gem_object_put_unlocked(object)
 |
-- drm_property_reference_blob(object)
-+ drm_property_blob_get(object)
-|
-- drm_property_unreference_blob(object)
-+ drm_property_blob_put(object)
-|
 - drm_dev_unref(object)
 + drm_dev_put(object)
 )
@@ -72,10 +66,6 @@ __drm_gem_object_unreference(object)
 |
 drm_gem_object_unreference_unlocked(object)
 |
-drm_property_unreference_blob@p(object)
-|
-drm_property_reference_blob@p(object)
-|
 drm_dev_unref@p(object)
 )
 
diff --git a/scripts/coccinelle/locks/mini_lock.cocci b/scripts/coccinelle/locks/mini_lock.cocci
index 47f649b0ea87..19c6ee5b986b 100644
--- a/scripts/coccinelle/locks/mini_lock.cocci
+++ b/scripts/coccinelle/locks/mini_lock.cocci
@@ -67,12 +67,14 @@ identifier lock,unlock;
 @@
 
 *lock(E1@p,...);
-<+... when != E1
+... when != E1
+    when any
 if (...) {
   ... when != E1
 *  return@r ...;
 }
-...+>
+... when != E1
+    when any
 *unlock@up(E1,...);
 
 @script:python depends on org@
diff --git a/scripts/coccinelle/null/deref_null.cocci b/scripts/coccinelle/null/deref_null.cocci
index b16ccb7663a7..cbc6184e69ef 100644
--- a/scripts/coccinelle/null/deref_null.cocci
+++ b/scripts/coccinelle/null/deref_null.cocci
@@ -14,18 +14,10 @@ virtual context
 virtual org
 virtual report
 
-@ifm@
-expression *E;
-statement S1,S2;
-position p1;
-@@
-
-if@p1 ((E == NULL && ...) || ...) S1 else S2
-
 // The following two rules are separate, because both can match a single
 // expression in different ways
 @pr1 expression@
-expression *ifm.E;
+expression E;
 identifier f;
 position p1;
 @@
@@ -33,7 +25,7 @@ position p1;
  (E != NULL && ...) ? <+...E->f@p1...+> : ...
 
 @pr2 expression@
-expression *ifm.E;
+expression E;
 identifier f;
 position p2;
 @@
@@ -46,6 +38,14 @@ position p2;
  sizeof(<+...E->f@p2...+>)
 )
 
+@ifm@
+expression *E;
+statement S1,S2;
+position p1;
+@@
+
+if@p1 ((E == NULL && ...) || ...) S1 else S2
+
 // For org and report modes
 
 @r depends on !context && (org || report) exists@
@@ -212,16 +212,8 @@ else S3
 // The following three rules are duplicates of ifm, pr1 and pr2 respectively.
 // It is need because the previous rule as already made a "change".
 
-@ifm1 depends on context && !org && !report@
-expression *E;
-statement S1,S2;
-position p1;
-@@
-
-if@p1 ((E == NULL && ...) || ...) S1 else S2
-
 @pr11 depends on context && !org && !report expression@
-expression *ifm1.E;
+expression E;
 identifier f;
 position p1;
 @@
@@ -229,7 +221,7 @@ position p1;
  (E != NULL && ...) ? <+...E->f@p1...+> : ...
 
 @pr12 depends on context && !org && !report expression@
-expression *ifm1.E;
+expression E;
 identifier f;
 position p2;
 @@
@@ -242,6 +234,14 @@ position p2;
  sizeof(<+...E->f@p2...+>)
 )
 
+@ifm1 depends on context && !org && !report@
+expression *E;
+statement S1,S2;
+position p1;
+@@
+
+if@p1 ((E == NULL && ...) || ...) S1 else S2
+
 @depends on context && !org && !report exists@
 expression subE <= ifm1.E;
 expression *ifm1.E;
diff --git a/scripts/depmod.sh b/scripts/depmod.sh
index 9831cca31240..1a6f85e0e6e1 100755
--- a/scripts/depmod.sh
+++ b/scripts/depmod.sh
@@ -3,36 +3,17 @@
 #
 # A depmod wrapper used by the toplevel Makefile
 
-if test $# -ne 3; then
-	echo "Usage: $0 /sbin/depmod <kernelrelease> <symbolprefix>" >&2
+if test $# -ne 2; then
+	echo "Usage: $0 /sbin/depmod <kernelrelease>" >&2
 	exit 1
 fi
 DEPMOD=$1
 KERNELRELEASE=$2
-SYMBOL_PREFIX=$3
 
 if ! test -r System.map -a -x "$DEPMOD"; then
 	exit 0
 fi
 
-# older versions of depmod don't support -P <symbol-prefix>
-# support was added in module-init-tools 3.13
-if test -n "$SYMBOL_PREFIX"; then
-	release=$("$DEPMOD" --version)
-	package=$(echo "$release" | cut -d' ' -f 1)
-	if test "$package" = "module-init-tools"; then
-		version=$(echo "$release" | cut -d' ' -f 2)
-		later=$(printf '%s\n' "$version" "3.13" | sort -V | tail -n 1)
-		if test "$later" != "$version"; then
-			# module-init-tools < 3.13, drop the symbol prefix
-			SYMBOL_PREFIX=""
-		fi
-	fi
-	if test -n "$SYMBOL_PREFIX"; then
-		SYMBOL_PREFIX="-P $SYMBOL_PREFIX"
-	fi
-fi
-
 # older versions of depmod require the version string to start with three
 # numbers, so we cheat with a symlink here
 depmod_hack_needed=true
@@ -55,7 +36,7 @@ set -- -ae -F System.map
 if test -n "$INSTALL_MOD_PATH"; then
 	set -- "$@" -b "$INSTALL_MOD_PATH"
 fi
-"$DEPMOD" "$@" "$KERNELRELEASE" $SYMBOL_PREFIX
+"$DEPMOD" "$@" "$KERNELRELEASE"
 ret=$?
 
 if $depmod_hack_needed; then
diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check
index bc1659900e89..2520bc14ffac 100755
--- a/scripts/documentation-file-ref-check
+++ b/scripts/documentation-file-ref-check
@@ -1,15 +1,116 @@
-#!/bin/sh
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+#
 # Treewide grep for references to files under Documentation, and report
 # non-existing files in stderr.
 
-for f in $(git ls-files); do
-	for ref in $(grep -ho "Documentation/[A-Za-z0-9_.,~/*+-]*" "$f"); do
-		# presume trailing . and , are not part of the name
-		ref=${ref%%[.,]}
-
-		# use ls to handle wildcards
-		if ! ls $ref >/dev/null 2>&1; then
-			echo "$f: $ref" >&2
-		fi
-	done
-done
+use warnings;
+use strict;
+use Getopt::Long qw(:config no_auto_abbrev);
+
+my $scriptname = $0;
+$scriptname =~ s,.*/([^/]+/),$1,;
+
+# Parse arguments
+my $help = 0;
+my $fix = 0;
+
+GetOptions(
+	'fix' => \$fix,
+	'h|help|usage' => \$help,
+);
+
+if ($help != 0) {
+    print "$scriptname [--help] [--fix-rst]\n";
+    exit -1;
+}
+
+# Step 1: find broken references
+print "Finding broken references. This may take a while...  " if ($fix);
+
+my %broken_ref;
+
+open IN, "git grep 'Documentation/'|"
+     or die "Failed to run git grep";
+while (<IN>) {
+	next if (!m/^([^:]+):(.*)/);
+
+	my $f = $1;
+	my $ln = $2;
+
+	# Makefiles contain nasty expressions to parse docs
+	next if ($f =~ m/Makefile/);
+	# Skip this script
+	next if ($f eq $scriptname);
+
+	if ($ln =~ m,\b(\S*)(Documentation/[A-Za-z0-9\_\.\,\~/\*+-]*),) {
+		my $prefix = $1;
+		my $ref = $2;
+		my $base = $2;
+
+		$ref =~ s/[\,\.]+$//;
+
+		my $fulref = "$prefix$ref";
+
+		$fulref =~ s/^(\<file|ref)://;
+		$fulref =~ s/^[\'\`]+//;
+		$fulref =~ s,^\$\(.*\)/,,;
+		$base =~ s,.*/,,;
+
+		# Remove URL false-positives
+		next if ($fulref =~ m/^http/);
+
+		# Check if exists, evaluating wildcards
+		next if (grep -e, glob("$ref $fulref"));
+
+		if ($fix) {
+			if (!($ref =~ m/(devicetree|scripts|Kconfig|Kbuild)/)) {
+				$broken_ref{$ref}++;
+			}
+		} else {
+			print STDERR "$f: $fulref\n";
+		}
+	}
+}
+
+exit 0 if (!$fix);
+
+# Step 2: Seek for file name alternatives
+print "Auto-fixing broken references. Please double-check the results\n";
+
+foreach my $ref (keys %broken_ref) {
+	my $new =$ref;
+
+	# get just the basename
+	$new =~ s,.*/,,;
+
+	# Seek for the same name on another place, as it may have been moved
+	my $f="";
+
+	$f = qx(find . -iname $new) if ($new);
+
+	# usual reason for breakage: file renamed to .rst
+	if (!$f) {
+		$new =~ s/\.txt$/.rst/;
+		$f=qx(find . -iname $new) if ($new);
+	}
+
+	my @find = split /\s+/, $f;
+
+	if (!$f) {
+		print STDERR "ERROR: Didn't find a replacement for $ref\n";
+	} elsif (scalar(@find) > 1) {
+		print STDERR "WARNING: Won't auto-replace, as found multiple files close to $ref:\n";
+		foreach my $j (@find) {
+			$j =~ s,^./,,;
+			print STDERR "    $j\n";
+		}
+	} else {
+		$f = $find[0];
+		$f =~ s,^./,,;
+		print "INFO: Replacing $ref to $f\n";
+		foreach my $j (qx(git grep -l $ref)) {
+			qx(sed "s\@$ref\@$f\@g" -i $j);
+		}
+	}
+}
diff --git a/scripts/dtc/checks.c b/scripts/dtc/checks.c
index c07ba4da9e36..815eaf140ab5 100644
--- a/scripts/dtc/checks.c
+++ b/scripts/dtc/checks.c
@@ -787,10 +787,9 @@ static void check_pci_bridge(struct check *c, struct dt_info *dti, struct node *
 		FAIL(c, dti, node, "incorrect #size-cells for PCI bridge");
 
 	prop = get_property(node, "bus-range");
-	if (!prop) {
-		FAIL(c, dti, node, "missing bus-range for PCI bridge");
+	if (!prop)
 		return;
-	}
+
 	if (prop->val.len != (sizeof(cell_t) * 2)) {
 		FAIL_PROP(c, dti, node, prop, "value must be 2 cells");
 		return;
diff --git a/scripts/extract_xc3028.pl b/scripts/extract_xc3028.pl
index 61d9b256c658..a1c51b7e4baf 100755
--- a/scripts/extract_xc3028.pl
+++ b/scripts/extract_xc3028.pl
@@ -1,6 +1,6 @@
 #!/usr/bin/env perl
 
-# Copyright (c) Mauro Carvalho Chehab <mchehab@infradead.org>
+# Copyright (c) Mauro Carvalho Chehab <mchehab@kernel.org>
 # Released under GPLv2
 #
 # In order to use, you need to:
diff --git a/scripts/faddr2line b/scripts/faddr2line
index 9e5735a4d3a5..a0149db00be7 100755
--- a/scripts/faddr2line
+++ b/scripts/faddr2line
@@ -56,7 +56,7 @@ command -v ${SIZE} >/dev/null 2>&1 || die "size isn't installed"
 command -v ${NM} >/dev/null 2>&1 || die "nm isn't installed"
 
 usage() {
-	echo "usage: faddr2line <object file> <func+offset> <func+offset>..." >&2
+	echo "usage: faddr2line [--list] <object file> <func+offset> <func+offset>..." >&2
 	exit 1
 }
 
@@ -166,12 +166,25 @@ __faddr2line() {
 		local file_lines=$(${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;")
 		[[ -z $file_lines ]] && return
 
+		if [[ $LIST = 0 ]]; then
+			echo "$file_lines" | while read -r line
+			do
+				echo $line
+			done
+			DONE=1;
+			return
+		fi
+
 		# show each line with context
 		echo "$file_lines" | while read -r line
 		do
+			echo
 			echo $line
-			eval $(echo $line | awk -F "[ :]" '{printf("n1=%d;n2=%d;f=%s",$NF-5, $NF+5, $(NF-1))}')
-			awk 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") {printf("%d\t%s\n", NR, $0)}' $f
+			n=$(echo $line | sed 's/.*:\([0-9]\+\).*/\1/g')
+			n1=$[$n-5]
+			n2=$[$n+5]
+			f=$(echo $line | sed 's/.*at \(.\+\):.*/\1/g')
+			awk 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") { if (NR=='$n') printf(">%d<", NR); else printf(" %d ", NR); printf("\t%s\n", $0)}' $f
 		done
 
 		DONE=1
@@ -182,6 +195,10 @@ __faddr2line() {
 [[ $# -lt 2 ]] && usage
 
 objfile=$1
+
+LIST=0
+[[ "$objfile" == "--list" ]] && LIST=1 && shift && objfile=$1
+
 [[ ! -f $objfile ]] && die "can't find objfile $objfile"
 shift
 
diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile
index ef0287e42957..03b7ce97de14 100644
--- a/scripts/genksyms/Makefile
+++ b/scripts/genksyms/Makefile
@@ -14,14 +14,14 @@ genksyms-objs	:= genksyms.o parse.tab.o lex.lex.o
 # so that 'bison: not found' will be displayed if it is missing.
 ifeq ($(findstring 1,$(KBUILD_ENABLE_EXTRA_GCC_CHECKS)),)
 
-quiet_cmd_bison_no_warn = $(quet_cmd_bison)
+quiet_cmd_bison_no_warn = $(quiet_cmd_bison)
       cmd_bison_no_warn = $(YACC) --version >/dev/null; \
 			  $(cmd_bison) 2>/dev/null
 
 $(obj)/parse.tab.c: $(src)/parse.y FORCE
 	$(call if_changed,bison_no_warn)
 
-quiet_cmd_bison_h_no_warn = $(quet_cmd_bison_h)
+quiet_cmd_bison_h_no_warn = $(quiet_cmd_bison_h)
       cmd_bison_h_no_warn = $(YACC) --version >/dev/null; \
 			    $(cmd_bison_h) 2>/dev/null
 
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index c9235d8340f1..e007840f45b9 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -45,7 +45,6 @@ int in_source_file;
 
 static int flag_debug, flag_dump_defs, flag_reference, flag_dump_types,
 	   flag_preserve, flag_warnings, flag_rel_crcs;
-static const char *mod_prefix = "";
 
 static int errors;
 static int nsyms;
@@ -693,10 +692,10 @@ void export_symbol(const char *name)
 			fputs(">\n", debugfile);
 
 		/* Used as a linker script. */
-		printf(!flag_rel_crcs ? "%s__crc_%s = 0x%08lx;\n" :
+		printf(!flag_rel_crcs ? "__crc_%s = 0x%08lx;\n" :
 		       "SECTIONS { .rodata : ALIGN(4) { "
-		       "%s__crc_%s = .; LONG(0x%08lx); } }\n",
-		       mod_prefix, name, crc);
+		       "__crc_%s = .; LONG(0x%08lx); } }\n",
+		       name, crc);
 	}
 }
 
@@ -769,7 +768,6 @@ int main(int argc, char **argv)
 
 #ifdef __GNU_LIBRARY__
 	struct option long_opts[] = {
-		{"symbol-prefix", 1, 0, 's'},
 		{"debug", 0, 0, 'd'},
 		{"warnings", 0, 0, 'w'},
 		{"quiet", 0, 0, 'q'},
@@ -789,9 +787,6 @@ int main(int argc, char **argv)
 	while ((o = getopt(argc, argv, "s:dwqVDr:T:phR")) != EOF)
 #endif				/* __GNU_LIBRARY__ */
 		switch (o) {
-		case 's':
-			mod_prefix = optarg;
-			break;
 		case 'd':
 			flag_debug++;
 			break;
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 5abfbf1b8fe2..a9186a98a37d 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -62,7 +62,6 @@ static struct sym_entry *table;
 static unsigned int table_size, table_cnt;
 static int all_symbols = 0;
 static int absolute_percpu = 0;
-static char symbol_prefix_char = '\0';
 static int base_relative = 0;
 
 int token_profit[0x10000];
@@ -75,7 +74,6 @@ unsigned char best_table_len[256];
 static void usage(void)
 {
 	fprintf(stderr, "Usage: kallsyms [--all-symbols] "
-			"[--symbol-prefix=<prefix char>] "
 			"[--base-relative] < in.map > out.S\n");
 	exit(1);
 }
@@ -113,28 +111,22 @@ static int check_symbol_range(const char *sym, unsigned long long addr,
 
 static int read_symbol(FILE *in, struct sym_entry *s)
 {
-	char str[500];
-	char *sym, stype;
+	char sym[500], stype;
 	int rc;
 
-	rc = fscanf(in, "%llx %c %499s\n", &s->addr, &stype, str);
+	rc = fscanf(in, "%llx %c %499s\n", &s->addr, &stype, sym);
 	if (rc != 3) {
-		if (rc != EOF && fgets(str, 500, in) == NULL)
+		if (rc != EOF && fgets(sym, 500, in) == NULL)
 			fprintf(stderr, "Read error or end of file.\n");
 		return -1;
 	}
-	if (strlen(str) > KSYM_NAME_LEN) {
+	if (strlen(sym) > KSYM_NAME_LEN) {
 		fprintf(stderr, "Symbol %s too long for kallsyms (%zu vs %d).\n"
 				"Please increase KSYM_NAME_LEN both in kernel and kallsyms.c\n",
-			str, strlen(str), KSYM_NAME_LEN);
+			sym, strlen(sym), KSYM_NAME_LEN);
 		return -1;
 	}
 
-	sym = str;
-	/* skip prefix char */
-	if (symbol_prefix_char && str[0] == symbol_prefix_char)
-		sym++;
-
 	/* Ignore most absolute/undefined (?) symbols. */
 	if (strcmp(sym, "_text") == 0)
 		_text = s->addr;
@@ -155,7 +147,7 @@ static int read_symbol(FILE *in, struct sym_entry *s)
 		 is_arm_mapping_symbol(sym))
 		return -1;
 	/* exclude also MIPS ELF local symbols ($L123 instead of .L123) */
-	else if (str[0] == '$')
+	else if (sym[0] == '$')
 		return -1;
 	/* exclude debugging symbols */
 	else if (stype == 'N' || stype == 'n')
@@ -163,14 +155,14 @@ static int read_symbol(FILE *in, struct sym_entry *s)
 
 	/* include the type field in the symbol name, so that it gets
 	 * compressed together */
-	s->len = strlen(str) + 1;
+	s->len = strlen(sym) + 1;
 	s->sym = malloc(s->len + 1);
 	if (!s->sym) {
 		fprintf(stderr, "kallsyms failure: "
 			"unable to allocate required amount of memory\n");
 		exit(EXIT_FAILURE);
 	}
-	strcpy((char *)s->sym + 1, str);
+	strcpy((char *)s->sym + 1, sym);
 	s->sym[0] = stype;
 
 	s->percpu_absolute = 0;
@@ -233,11 +225,6 @@ static int symbol_valid(struct sym_entry *s)
 	int i;
 	char *sym_name = (char *)s->sym + 1;
 
-	/* skip prefix char */
-	if (symbol_prefix_char && *sym_name == symbol_prefix_char)
-		sym_name++;
-
-
 	/* if --all-symbols is not specified, then symbols outside the text
 	 * and inittext sections are discarded */
 	if (!all_symbols) {
@@ -302,15 +289,9 @@ static void read_map(FILE *in)
 
 static void output_label(char *label)
 {
-	if (symbol_prefix_char)
-		printf(".globl %c%s\n", symbol_prefix_char, label);
-	else
-		printf(".globl %s\n", label);
+	printf(".globl %s\n", label);
 	printf("\tALGN\n");
-	if (symbol_prefix_char)
-		printf("%c%s:\n", symbol_prefix_char, label);
-	else
-		printf("%s:\n", label);
+	printf("%s:\n", label);
 }
 
 /* uncompress a compressed symbol. When this function is called, the best table
@@ -424,7 +405,7 @@ static void write_src(void)
 	}
 
 	output_label("kallsyms_num_syms");
-	printf("\tPTR\t%d\n", table_cnt);
+	printf("\tPTR\t%u\n", table_cnt);
 	printf("\n");
 
 	/* table of offset markers, that give the offset in the compressed stream
@@ -768,13 +749,7 @@ int main(int argc, char **argv)
 				all_symbols = 1;
 			else if (strcmp(argv[i], "--absolute-percpu") == 0)
 				absolute_percpu = 1;
-			else if (strncmp(argv[i], "--symbol-prefix=", 16) == 0) {
-				char *p = &argv[i][16];
-				/* skip quote */
-				if ((*p == '"' && *(p+2) == '"') || (*p == '\'' && *(p+2) == '\''))
-					p++;
-				symbol_prefix_char = *p;
-			} else if (strcmp(argv[i], "--base-relative") == 0)
+			else if (strcmp(argv[i], "--base-relative") == 0)
 				base_relative = 1;
 			else
 				usage();
diff --git a/scripts/kconfig/.gitignore b/scripts/kconfig/.gitignore
index 2da579edcbaf..0aabc1d6a182 100644
--- a/scripts/kconfig/.gitignore
+++ b/scripts/kconfig/.gitignore
@@ -2,9 +2,6 @@
 # Generated files
 #
 *.moc
-gconf.glade.h
-*.pot
-*.mo
 
 #
 # configuration programs
@@ -14,4 +11,3 @@ mconf
 nconf
 qconf
 gconf
-kxgettext
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 5def8779d7d8..a3ac2c91331c 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -3,7 +3,7 @@
 # Kernel configuration targets
 # These targets are used from top-level makefile
 
-PHONY += xconfig gconfig menuconfig config syncconfig update-po-config \
+PHONY += xconfig gconfig menuconfig config syncconfig \
 	localmodconfig localyesconfig
 
 ifdef KBUILD_KCONFIG
@@ -55,29 +55,6 @@ localyesconfig localmodconfig: $(obj)/conf
 	fi
 	$(Q)rm -f .tmp.config
 
-# Create new linux.pot file
-# Adjust charset to UTF-8 in .po file to accept UTF-8 in Kconfig files
-update-po-config: $(obj)/kxgettext $(obj)/gconf.glade.h
-	$(Q)$(kecho) "  GEN     config.pot"
-	$(Q)xgettext --default-domain=linux                         \
-	    --add-comments --keyword=_ --keyword=N_                 \
-	    --from-code=UTF-8                                       \
-	    --files-from=$(srctree)/scripts/kconfig/POTFILES.in     \
-	    --directory=$(srctree) --directory=$(objtree)           \
-	    --output $(obj)/config.pot
-	$(Q)sed -i s/CHARSET/UTF-8/ $(obj)/config.pot
-	$(Q)(for i in `ls $(srctree)/arch/*/Kconfig      \
-	    $(srctree)/arch/*/um/Kconfig`;               \
-	    do                                           \
-		$(kecho) "  GEN     $$i";                    \
-		$(obj)/kxgettext $$i                     \
-		     >> $(obj)/config.pot;               \
-	    done )
-	$(Q)$(kecho) "  GEN     linux.pot"
-	$(Q)msguniq --sort-by-file --to-code=UTF-8 $(obj)/config.pot \
-	    --output $(obj)/linux.pot
-	$(Q)rm -f $(obj)/config.pot
-
 # These targets map 1:1 to the commandline options of 'conf'
 simple-targets := oldconfig allnoconfig allyesconfig allmodconfig \
 	alldefconfig randconfig listnewconfig olddefconfig
@@ -151,8 +128,7 @@ clean-dirs += tests/.cache
 # Help text used by make help
 help:
 	@echo  '  config	  - Update current config utilising a line-oriented program'
-	@echo  '  nconfig         - Update current config utilising a ncurses menu based'
-	@echo  '                    program'
+	@echo  '  nconfig         - Update current config utilising a ncurses menu based program'
 	@echo  '  menuconfig	  - Update current config utilising a menu based program'
 	@echo  '  xconfig	  - Update current config utilising a Qt based front-end'
 	@echo  '  gconfig	  - Update current config utilising a GTK+ based front-end'
@@ -172,141 +148,77 @@ help:
 	@echo  '  kvmconfig	  - Enable additional options for kvm guest kernel support'
 	@echo  '  xenconfig       - Enable additional options for xen dom0 and guest kernel support'
 	@echo  '  tinyconfig	  - Configure the tiniest possible kernel'
-
-# lxdialog stuff
-check-lxdialog  := $(srctree)/$(src)/lxdialog/check-lxdialog.sh
-
-# Use recursively expanded variables so we do not call gcc unless
-# we really need to do so. (Do not call gcc as part of make mrproper)
-HOST_EXTRACFLAGS += $(shell $(CONFIG_SHELL) $(check-lxdialog) -ccflags) \
-                    -DLOCALE
+	@echo  '  testconfig	  - Run Kconfig unit tests (requires python3 and pytest)'
 
 # ===========================================================================
 # Shared Makefile for the various kconfig executables:
 # conf:	  Used for defconfig, oldconfig and related targets
-# nconf:  Used for the nconfig target.
-#         Utilizes ncurses
-# mconf:  Used for the menuconfig target
-#         Utilizes the lxdialog package
-# qconf:  Used for the xconfig target
-#         Based on Qt which needs to be installed to compile it
-# gconf:  Used for the gconfig target
-#         Based on GTK+ which needs to be installed to compile it
 # object files used by all kconfig flavours
 
-lxdialog := lxdialog/checklist.o lxdialog/util.o lxdialog/inputbox.o
-lxdialog += lxdialog/textbox.o lxdialog/yesno.o lxdialog/menubox.o
-
 conf-objs	:= conf.o  zconf.tab.o
-mconf-objs     := mconf.o zconf.tab.o $(lxdialog)
-nconf-objs     := nconf.o zconf.tab.o nconf.gui.o
-kxgettext-objs	:= kxgettext.o zconf.tab.o
-qconf-cxxobjs	:= qconf.o
-qconf-objs	:= zconf.tab.o
-gconf-objs	:= gconf.o zconf.tab.o
 
-hostprogs-y := conf nconf mconf kxgettext qconf gconf
+hostprogs-y := conf
 
 targets		+= zconf.lex.c
-clean-files	:= qconf.moc .tmp_qtcheck .tmp_gtkcheck
-clean-files	+= gconf.glade.h
-clean-files     += config.pot linux.pot
-
-# Check that we have the required ncurses stuff installed for lxdialog (menuconfig)
-PHONY += $(obj)/dochecklxdialog
-$(addprefix $(obj)/, mconf.o $(lxdialog)): $(obj)/dochecklxdialog
-$(obj)/dochecklxdialog:
-	$(Q)$(CONFIG_SHELL) $(check-lxdialog) -check $(HOSTCC) $(HOST_EXTRACFLAGS) $(HOSTLOADLIBES_mconf)
-
-always := dochecklxdialog
-
-# Add environment specific flags
-HOST_EXTRACFLAGS += $(shell $(CONFIG_SHELL) $(srctree)/$(src)/check.sh $(HOSTCC) $(HOSTCFLAGS))
-HOST_EXTRACXXFLAGS += $(shell $(CONFIG_SHELL) $(srctree)/$(src)/check.sh $(HOSTCXX) $(HOSTCXXFLAGS))
 
 # generated files seem to need this to find local include files
 HOSTCFLAGS_zconf.lex.o	:= -I$(src)
 HOSTCFLAGS_zconf.tab.o	:= -I$(src)
 
-HOSTLOADLIBES_qconf	= $(KC_QT_LIBS)
-HOSTCXXFLAGS_qconf.o	= $(KC_QT_CFLAGS)
-
-HOSTLOADLIBES_gconf	= `pkg-config --libs gtk+-2.0 gmodule-2.0 libglade-2.0`
-HOSTCFLAGS_gconf.o	= `pkg-config --cflags gtk+-2.0 gmodule-2.0 libglade-2.0` \
-                          -Wno-missing-prototypes
-
-HOSTLOADLIBES_mconf   = $(shell $(CONFIG_SHELL) $(check-lxdialog) -ldflags $(HOSTCC))
-
-HOSTLOADLIBES_nconf	= $(shell \
-				pkg-config --libs menuw panelw ncursesw 2>/dev/null \
-				|| pkg-config --libs menu panel ncurses 2>/dev/null \
-				|| echo "-lmenu -lpanel -lncurses"  )
-$(obj)/qconf.o: $(obj)/.tmp_qtcheck
-
-ifeq ($(MAKECMDGOALS),xconfig)
-$(obj)/.tmp_qtcheck: $(src)/Makefile
--include $(obj)/.tmp_qtcheck
-
-# Qt needs some extra effort...
-$(obj)/.tmp_qtcheck:
-	@set -e; $(kecho) "  CHECK   qt"; \
-	if pkg-config --exists Qt5Core; then \
-	    cflags="-std=c++11 -fPIC `pkg-config --cflags Qt5Core Qt5Gui Qt5Widgets`"; \
-	    libs=`pkg-config --libs Qt5Core Qt5Gui Qt5Widgets`; \
-	    moc=`pkg-config --variable=host_bins Qt5Core`/moc; \
-	elif pkg-config --exists QtCore; then \
-	    cflags=`pkg-config --cflags QtCore QtGui`; \
-	    libs=`pkg-config --libs QtCore QtGui`; \
-	    moc=`pkg-config --variable=moc_location QtCore`; \
-	else \
-	    echo >&2 "*"; \
-	    echo >&2 "* Could not find Qt via pkg-config."; \
-	    echo >&2 "* Please install either Qt 4.8 or 5.x. and make sure it's in PKG_CONFIG_PATH"; \
-	    echo >&2 "*"; \
-	    exit 1; \
-	fi; \
-	echo "KC_QT_CFLAGS=$$cflags" > $@; \
-	echo "KC_QT_LIBS=$$libs" >> $@; \
-	echo "KC_QT_MOC=$$moc" >> $@
-endif
+# nconf: Used for the nconfig target based on ncurses
+hostprogs-y	+= nconf
+nconf-objs	:= nconf.o zconf.tab.o nconf.gui.o
 
-$(obj)/gconf.o: $(obj)/.tmp_gtkcheck
-
-ifeq ($(MAKECMDGOALS),gconfig)
--include $(obj)/.tmp_gtkcheck
-
-# GTK+ needs some extra effort, too...
-$(obj)/.tmp_gtkcheck:
-	@if `pkg-config --exists gtk+-2.0 gmodule-2.0 libglade-2.0`; then		\
-		if `pkg-config --atleast-version=2.0.0 gtk+-2.0`; then			\
-			touch $@;								\
-		else									\
-			echo >&2 "*"; 							\
-			echo >&2 "* GTK+ is present but version >= 2.0.0 is required.";	\
-			echo >&2 "*";							\
-			false;								\
-		fi									\
-	else										\
-		echo >&2 "*"; 								\
-		echo >&2 "* Unable to find the GTK+ installation. Please make sure that"; 	\
-		echo >&2 "* the GTK+ 2.0 development package is correctly installed..."; 	\
-		echo >&2 "* You need gtk+-2.0, glib-2.0 and libglade-2.0."; 		\
-		echo >&2 "*"; 								\
-		false;									\
-	fi
-endif
+HOSTLOADLIBES_nconf	= $(shell . $(obj)/.nconf-cfg && echo $$libs)
+HOSTCFLAGS_nconf.o	= $(shell . $(obj)/.nconf-cfg && echo $$cflags)
+HOSTCFLAGS_nconf.gui.o	= $(shell . $(obj)/.nconf-cfg && echo $$cflags)
 
-$(obj)/zconf.tab.o: $(obj)/zconf.lex.c
+$(obj)/nconf.o: $(obj)/.nconf-cfg
+
+# mconf: Used for the menuconfig target based on lxdialog
+hostprogs-y	+= mconf
+lxdialog	:= checklist.o inputbox.o menubox.o textbox.o util.o yesno.o
+mconf-objs	:= mconf.o zconf.tab.o $(addprefix lxdialog/, $(lxdialog))
 
-$(obj)/qconf.o: $(obj)/qconf.moc
+HOSTLOADLIBES_mconf = $(shell . $(obj)/.mconf-cfg && echo $$libs)
+$(foreach f, mconf.o $(lxdialog), \
+  $(eval HOSTCFLAGS_$f = $$(shell . $(obj)/.mconf-cfg && echo $$$$cflags)))
+
+$(addprefix $(obj)/, mconf.o $(lxdialog)): $(obj)/.mconf-cfg
+
+# qconf: Used for the xconfig target based on Qt
+hostprogs-y	+= qconf
+qconf-cxxobjs	:= qconf.o
+qconf-objs	:= zconf.tab.o
+
+HOSTLOADLIBES_qconf	= $(shell . $(obj)/.qconf-cfg && echo $$libs)
+HOSTCXXFLAGS_qconf.o	= $(shell . $(obj)/.qconf-cfg && echo $$cflags)
+
+$(obj)/qconf.o: $(obj)/.qconf-cfg $(obj)/qconf.moc
 
 quiet_cmd_moc = MOC     $@
-      cmd_moc = $(KC_QT_MOC) -i $< -o $@
+      cmd_moc = $(shell . $(obj)/.qconf-cfg && echo $$moc) -i $< -o $@
 
-$(obj)/%.moc: $(src)/%.h $(obj)/.tmp_qtcheck
+$(obj)/%.moc: $(src)/%.h $(obj)/.qconf-cfg
 	$(call cmd,moc)
 
-# Extract gconf menu items for i18n support
-$(obj)/gconf.glade.h: $(obj)/gconf.glade
-	$(Q)intltool-extract --type=gettext/glade --srcdir=$(srctree) \
-	$(obj)/gconf.glade
+# gconf: Used for the gconfig target based on GTK+
+hostprogs-y	+= gconf
+gconf-objs	:= gconf.o zconf.tab.o
+
+HOSTLOADLIBES_gconf = $(shell . $(obj)/.gconf-cfg && echo $$libs)
+HOSTCFLAGS_gconf.o  = $(shell . $(obj)/.gconf-cfg && echo $$cflags)
+
+$(obj)/gconf.o: $(obj)/.gconf-cfg
+
+$(obj)/zconf.tab.o: $(obj)/zconf.lex.c
+
+# check if necessary packages are available, and configure build flags
+define filechk_conf_cfg
+	$(CONFIG_SHELL) $<
+endef
+
+$(obj)/.%conf-cfg: $(src)/%conf-cfg.sh FORCE
+	$(call filechk,conf_cfg)
+
+clean-files += .*conf-cfg
diff --git a/scripts/kconfig/POTFILES.in b/scripts/kconfig/POTFILES.in
deleted file mode 100644
index 967457396990..000000000000
--- a/scripts/kconfig/POTFILES.in
+++ /dev/null
@@ -1,12 +0,0 @@
-scripts/kconfig/lxdialog/checklist.c
-scripts/kconfig/lxdialog/inputbox.c
-scripts/kconfig/lxdialog/menubox.c
-scripts/kconfig/lxdialog/textbox.c
-scripts/kconfig/lxdialog/util.c
-scripts/kconfig/lxdialog/yesno.c
-scripts/kconfig/mconf.c
-scripts/kconfig/conf.c
-scripts/kconfig/confdata.c
-scripts/kconfig/gconf.c
-scripts/kconfig/gconf.glade.h
-scripts/kconfig/qconf.cc
diff --git a/scripts/kconfig/check.sh b/scripts/kconfig/check.sh
deleted file mode 100755
index 97f0fee7d173..000000000000
--- a/scripts/kconfig/check.sh
+++ /dev/null
@@ -1,14 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Needed for systems without gettext
-$* -x c -o /dev/null - > /dev/null 2>&1 << EOF
-#include <libintl.h>
-int main()
-{
-	gettext("");
-	return 0;
-}
-EOF
-if [ ! "$?" -eq "0"  ]; then
-	echo -DKBUILD_NO_NLS;
-fi
diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 283eeedaa4fa..671ff5364497 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -3,7 +3,6 @@
  * Released under the terms of the GNU GPL v2.0.
  */
 
-#include <locale.h>
 #include <ctype.h>
 #include <limits.h>
 #include <stdio.h>
@@ -86,7 +85,7 @@ static int conf_askvalue(struct symbol *sym, const char *def)
 	enum symbol_type type = sym_get_type(sym);
 
 	if (!sym_has_value(sym))
-		printf(_("(NEW) "));
+		printf("(NEW) ");
 
 	line[0] = '\n';
 	line[1] = 0;
@@ -133,7 +132,7 @@ static int conf_string(struct menu *menu)
 	const char *def;
 
 	while (1) {
-		printf("%*s%s ", indent - 1, "", _(menu->prompt->text));
+		printf("%*s%s ", indent - 1, "", menu->prompt->text);
 		printf("(%s) ", sym->name);
 		def = sym_get_string_value(sym);
 		if (sym_get_string_value(sym))
@@ -166,7 +165,7 @@ static int conf_sym(struct menu *menu)
 	tristate oldval, newval;
 
 	while (1) {
-		printf("%*s%s ", indent - 1, "", _(menu->prompt->text));
+		printf("%*s%s ", indent - 1, "", menu->prompt->text);
 		if (sym->name)
 			printf("(%s) ", sym->name);
 		putchar('[');
@@ -251,7 +250,7 @@ static int conf_choice(struct menu *menu)
 		case no:
 			return 1;
 		case mod:
-			printf("%*s%s\n", indent - 1, "", _(menu_get_prompt(menu)));
+			printf("%*s%s\n", indent - 1, "", menu_get_prompt(menu));
 			return 0;
 		case yes:
 			break;
@@ -261,7 +260,7 @@ static int conf_choice(struct menu *menu)
 	while (1) {
 		int cnt, def;
 
-		printf("%*s%s\n", indent - 1, "", _(menu_get_prompt(menu)));
+		printf("%*s%s\n", indent - 1, "", menu_get_prompt(menu));
 		def_sym = sym_get_choice_value(sym);
 		cnt = def = 0;
 		line[0] = 0;
@@ -269,7 +268,7 @@ static int conf_choice(struct menu *menu)
 			if (!menu_is_visible(child))
 				continue;
 			if (!child->sym) {
-				printf("%*c %s\n", indent, '*', _(menu_get_prompt(child)));
+				printf("%*c %s\n", indent, '*', menu_get_prompt(child));
 				continue;
 			}
 			cnt++;
@@ -278,14 +277,14 @@ static int conf_choice(struct menu *menu)
 				printf("%*c", indent, '>');
 			} else
 				printf("%*c", indent, ' ');
-			printf(" %d. %s", cnt, _(menu_get_prompt(child)));
+			printf(" %d. %s", cnt, menu_get_prompt(child));
 			if (child->sym->name)
 				printf(" (%s)", child->sym->name);
 			if (!sym_has_value(child->sym))
-				printf(_(" (NEW)"));
+				printf(" (NEW)");
 			printf("\n");
 		}
-		printf(_("%*schoice"), indent - 1, "");
+		printf("%*schoice", indent - 1, "");
 		if (cnt == 1) {
 			printf("[1]: 1\n");
 			goto conf_childs;
@@ -372,7 +371,7 @@ static void conf(struct menu *menu)
 			if (prompt)
 				printf("%*c\n%*c %s\n%*c\n",
 					indent, '*',
-					indent, '*', _(prompt),
+					indent, '*', prompt,
 					indent, '*');
 		default:
 			;
@@ -437,7 +436,7 @@ static void check_conf(struct menu *menu)
 				}
 			} else {
 				if (!conf_cnt++)
-					printf(_("*\n* Restart config...\n*\n"));
+					printf("*\n* Restart config...\n*\n");
 				rootEntry = menu_get_parent_menu(menu);
 				conf(rootEntry);
 			}
@@ -498,10 +497,6 @@ int main(int ac, char **av)
 	const char *name, *defconfig_file = NULL /* gcc uninit */;
 	struct stat tmpstat;
 
-	setlocale(LC_ALL, "");
-	bindtextdomain(PACKAGE, LOCALEDIR);
-	textdomain(PACKAGE);
-
 	tty_stdio = isatty(0) && isatty(1);
 
 	while ((opt = getopt_long(ac, av, "s", long_opts, NULL)) != -1) {
@@ -559,7 +554,7 @@ int main(int ac, char **av)
 		}
 	}
 	if (ac == optind) {
-		fprintf(stderr, _("%s: Kconfig file missing\n"), av[0]);
+		fprintf(stderr, "%s: Kconfig file missing\n", av[0]);
 		conf_usage(progname);
 		exit(1);
 	}
@@ -569,12 +564,12 @@ int main(int ac, char **av)
 	if (sync_kconfig) {
 		name = conf_get_configname();
 		if (stat(name, &tmpstat)) {
-			fprintf(stderr, _("***\n"
+			fprintf(stderr, "***\n"
 				"*** Configuration file \"%s\" not found!\n"
 				"***\n"
 				"*** Please run some configurator (e.g. \"make oldconfig\" or\n"
 				"*** \"make menuconfig\" or \"make xconfig\").\n"
-				"***\n"), name);
+				"***\n", name);
 			exit(1);
 		}
 	}
@@ -585,9 +580,9 @@ int main(int ac, char **av)
 			defconfig_file = conf_get_default_confname();
 		if (conf_read(defconfig_file)) {
 			fprintf(stderr,
-				_("***\n"
+				"***\n"
 				  "*** Can't find default configuration \"%s\"!\n"
-				  "***\n"),
+				  "***\n",
 				defconfig_file);
 			exit(1);
 		}
@@ -611,7 +606,7 @@ int main(int ac, char **av)
 		if ((strcmp(name, "") != 0) && (strcmp(name, "1") != 0)) {
 			if (conf_read_simple(name, S_DEF_USER)) {
 				fprintf(stderr,
-					_("*** Can't read seed configuration \"%s\"!\n"),
+					"*** Can't read seed configuration \"%s\"!\n",
 					name);
 				exit(1);
 			}
@@ -628,7 +623,7 @@ int main(int ac, char **av)
 		if (conf_read_simple(name, S_DEF_USER) &&
 		    conf_read_simple("all.config", S_DEF_USER)) {
 			fprintf(stderr,
-				_("*** KCONFIG_ALLCONFIG set, but no \"%s\" or \"all.config\" file found\n"),
+				"*** KCONFIG_ALLCONFIG set, but no \"%s\" or \"all.config\" file found\n",
 				name);
 			exit(1);
 		}
@@ -642,7 +637,7 @@ int main(int ac, char **av)
 			name = getenv("KCONFIG_NOSILENTUPDATE");
 			if (name && *name) {
 				fprintf(stderr,
-					_("\n*** The configuration requires explicit update.\n\n"));
+					"\n*** The configuration requires explicit update.\n\n");
 				return 1;
 			}
 		}
@@ -694,22 +689,22 @@ int main(int ac, char **av)
 		 * All other commands are only used to generate a config.
 		 */
 		if (conf_get_changed() && conf_write(NULL)) {
-			fprintf(stderr, _("\n*** Error during writing of the configuration.\n\n"));
+			fprintf(stderr, "\n*** Error during writing of the configuration.\n\n");
 			exit(1);
 		}
 		if (conf_write_autoconf()) {
-			fprintf(stderr, _("\n*** Error during update of the configuration.\n\n"));
+			fprintf(stderr, "\n*** Error during update of the configuration.\n\n");
 			return 1;
 		}
 	} else if (input_mode == savedefconfig) {
 		if (conf_write_defconfig(defconfig_file)) {
-			fprintf(stderr, _("n*** Error while saving defconfig to: %s\n\n"),
+			fprintf(stderr, "n*** Error while saving defconfig to: %s\n\n",
 				defconfig_file);
 			return 1;
 		}
 	} else if (input_mode != listnewconfig) {
 		if (conf_write(NULL)) {
-			fprintf(stderr, _("\n*** Error during writing of the configuration.\n\n"));
+			fprintf(stderr, "\n*** Error during writing of the configuration.\n\n");
 			exit(1);
 		}
 	}
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index df26c7b0fe13..39e20974f4a3 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -30,7 +30,7 @@ static void conf_message(const char *fmt, ...)
 static const char *conf_filename;
 static int conf_lineno, conf_warnings;
 
-const char conf_defname[] = "arch/$ARCH/defconfig";
+const char conf_defname[] = "arch/$(ARCH)/defconfig";
 
 static void conf_warning(const char *fmt, ...)
 {
@@ -81,39 +81,13 @@ const char *conf_get_autoconfig_name(void)
 	return name ? name : "include/config/auto.conf";
 }
 
-static char *conf_expand_value(const char *in)
-{
-	struct symbol *sym;
-	const char *src;
-	static char res_value[SYMBOL_MAXLENGTH];
-	char *dst, name[SYMBOL_MAXLENGTH];
-
-	res_value[0] = 0;
-	dst = name;
-	while ((src = strchr(in, '$'))) {
-		strncat(res_value, in, src - in);
-		src++;
-		dst = name;
-		while (isalnum(*src) || *src == '_')
-			*dst++ = *src++;
-		*dst = 0;
-		sym = sym_lookup(name, 0);
-		sym_calc_value(sym);
-		strcat(res_value, sym_get_string_value(sym));
-		in = src;
-	}
-	strcat(res_value, in);
-
-	return res_value;
-}
-
 char *conf_get_default_confname(void)
 {
 	struct stat buf;
 	static char fullname[PATH_MAX+1];
 	char *env, *name;
 
-	name = conf_expand_value(conf_defname);
+	name = expand_string(conf_defname);
 	env = getenv(SRCTREE);
 	if (env) {
 		sprintf(fullname, "%s/%s", env, name);
@@ -274,10 +248,11 @@ int conf_read_simple(const char *name, int def)
 			if (expr_calc_value(prop->visible.expr) == no ||
 			    prop->expr->type != E_SYMBOL)
 				continue;
-			name = conf_expand_value(prop->expr->left.sym->name);
+			sym_calc_value(prop->expr->left.sym);
+			name = sym_get_string_value(prop->expr->left.sym);
 			in = zconf_fopen(name);
 			if (in) {
-				conf_message(_("using defaults found in %s"),
+				conf_message("using defaults found in %s",
 					 name);
 				goto load;
 			}
@@ -745,7 +720,7 @@ int conf_write(const char *name)
 	struct menu *menu;
 	const char *basename;
 	const char *str;
-	char dirname[PATH_MAX+1], tmpname[PATH_MAX+1], newname[PATH_MAX+1];
+	char dirname[PATH_MAX+1], tmpname[PATH_MAX+22], newname[PATH_MAX+8];
 	char *env;
 
 	dirname[0] = 0;
@@ -831,7 +806,7 @@ next:
 			return 1;
 	}
 
-	conf_message(_("configuration written to %s"), newname);
+	conf_message("configuration written to %s", newname);
 
 	sym_set_change_count(0);
 
diff --git a/scripts/kconfig/gconf-cfg.sh b/scripts/kconfig/gconf-cfg.sh
new file mode 100755
index 000000000000..533b3d8f8f08
--- /dev/null
+++ b/scripts/kconfig/gconf-cfg.sh
@@ -0,0 +1,23 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+PKG="gtk+-2.0 gmodule-2.0 libglade-2.0"
+
+if ! pkg-config --exists $PKG; then
+	echo >&2 "*"
+	echo >&2 "* Unable to find the GTK+ installation. Please make sure that"
+	echo >&2 "* the GTK+ 2.0 development package is correctly installed."
+	echo >&2 "* You need $PKG"
+	echo >&2 "*"
+	exit 1
+fi
+
+if ! pkg-config --atleast-version=2.0.0 gtk+-2.0; then
+	echo >&2 "*"
+	echo >&2 "* GTK+ is present but version >= 2.0.0 is required."
+	echo >&2 "*"
+	exit 1
+fi
+
+echo cflags=\"$(pkg-config --cflags $PKG)\"
+echo libs=\"$(pkg-config --libs $PKG)\"
diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c
index cfddddb9c9d7..610c4ab54d76 100644
--- a/scripts/kconfig/gconf.c
+++ b/scripts/kconfig/gconf.c
@@ -137,7 +137,7 @@ void init_main_window(const gchar * glade_file)
 
 	xml = glade_xml_new(glade_file, "window1", NULL);
 	if (!xml)
-		g_error(_("GUI loading failed !\n"));
+		g_error("GUI loading failed !\n");
 	glade_xml_signal_autoconnect(xml);
 
 	main_wnd = glade_xml_get_widget(xml, "window1");
@@ -233,7 +233,7 @@ void init_left_tree(void)
 
 	column = gtk_tree_view_column_new();
 	gtk_tree_view_append_column(view, column);
-	gtk_tree_view_column_set_title(column, _("Options"));
+	gtk_tree_view_column_set_title(column, "Options");
 
 	renderer = gtk_cell_renderer_toggle_new();
 	gtk_tree_view_column_pack_start(GTK_TREE_VIEW_COLUMN(column),
@@ -276,7 +276,7 @@ void init_right_tree(void)
 
 	column = gtk_tree_view_column_new();
 	gtk_tree_view_append_column(view, column);
-	gtk_tree_view_column_set_title(column, _("Options"));
+	gtk_tree_view_column_set_title(column, "Options");
 
 	renderer = gtk_cell_renderer_pixbuf_new();
 	gtk_tree_view_column_pack_start(GTK_TREE_VIEW_COLUMN(column),
@@ -305,7 +305,7 @@ void init_right_tree(void)
 
 	renderer = gtk_cell_renderer_text_new();
 	gtk_tree_view_insert_column_with_attributes(view, -1,
-						    _("Name"), renderer,
+						    "Name", renderer,
 						    "text", COL_NAME,
 						    "foreground-gdk",
 						    COL_COLOR, NULL);
@@ -329,7 +329,7 @@ void init_right_tree(void)
 						    COL_COLOR, NULL);
 	renderer = gtk_cell_renderer_text_new();
 	gtk_tree_view_insert_column_with_attributes(view, -1,
-						    _("Value"), renderer,
+						    "Value", renderer,
 						    "text", COL_VALUE,
 						    "editable",
 						    COL_EDIT,
@@ -368,7 +368,7 @@ static void text_insert_help(struct menu *menu)
 {
 	GtkTextBuffer *buffer;
 	GtkTextIter start, end;
-	const char *prompt = _(menu_get_prompt(menu));
+	const char *prompt = menu_get_prompt(menu);
 	struct gstr help = str_new();
 
 	menu_get_ext_help(menu, &help);
@@ -422,7 +422,7 @@ gboolean on_window1_delete_event(GtkWidget * widget, GdkEvent * event,
 	if (!conf_get_changed())
 		return FALSE;
 
-	dialog = gtk_dialog_new_with_buttons(_("Warning !"),
+	dialog = gtk_dialog_new_with_buttons("Warning !",
 					     GTK_WINDOW(main_wnd),
 					     (GtkDialogFlags)
 					     (GTK_DIALOG_MODAL |
@@ -436,7 +436,7 @@ gboolean on_window1_delete_event(GtkWidget * widget, GdkEvent * event,
 	gtk_dialog_set_default_response(GTK_DIALOG(dialog),
 					GTK_RESPONSE_CANCEL);
 
-	label = gtk_label_new(_("\nSave configuration ?\n"));
+	label = gtk_label_new("\nSave configuration ?\n");
 	gtk_container_add(GTK_CONTAINER(GTK_DIALOG(dialog)->vbox), label);
 	gtk_widget_show(label);
 
@@ -496,7 +496,7 @@ load_filename(GtkFileSelection * file_selector, gpointer user_data)
 					     (user_data));
 
 	if (conf_read(fn))
-		text_insert_msg(_("Error"), _("Unable to load configuration !"));
+		text_insert_msg("Error", "Unable to load configuration !");
 	else
 		display_tree(&rootmenu);
 }
@@ -505,7 +505,7 @@ void on_load1_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	GtkWidget *fs;
 
-	fs = gtk_file_selection_new(_("Load file..."));
+	fs = gtk_file_selection_new("Load file...");
 	g_signal_connect(GTK_OBJECT(GTK_FILE_SELECTION(fs)->ok_button),
 			 "clicked",
 			 G_CALLBACK(load_filename), (gpointer) fs);
@@ -524,7 +524,7 @@ void on_load1_activate(GtkMenuItem * menuitem, gpointer user_data)
 void on_save_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	if (conf_write(NULL))
-		text_insert_msg(_("Error"), _("Unable to save configuration !"));
+		text_insert_msg("Error", "Unable to save configuration !");
 }
 
 
@@ -537,7 +537,7 @@ store_filename(GtkFileSelection * file_selector, gpointer user_data)
 					     (user_data));
 
 	if (conf_write(fn))
-		text_insert_msg(_("Error"), _("Unable to save configuration !"));
+		text_insert_msg("Error", "Unable to save configuration !");
 
 	gtk_widget_destroy(GTK_WIDGET(user_data));
 }
@@ -546,7 +546,7 @@ void on_save_as1_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	GtkWidget *fs;
 
-	fs = gtk_file_selection_new(_("Save file as..."));
+	fs = gtk_file_selection_new("Save file as...");
 	g_signal_connect(GTK_OBJECT(GTK_FILE_SELECTION(fs)->ok_button),
 			 "clicked",
 			 G_CALLBACK(store_filename), (gpointer) fs);
@@ -639,7 +639,7 @@ on_set_option_mode3_activate(GtkMenuItem *menuitem, gpointer user_data)
 void on_introduction1_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	GtkWidget *dialog;
-	const gchar *intro_text = _(
+	const gchar *intro_text = 
 	    "Welcome to gkc, the GTK+ graphical configuration tool\n"
 	    "For each option, a blank box indicates the feature is disabled, a\n"
 	    "check indicates it is enabled, and a dot indicates that it is to\n"
@@ -654,7 +654,7 @@ void on_introduction1_activate(GtkMenuItem * menuitem, gpointer user_data)
 	    "option.\n"
 	    "\n"
 	    "Toggling Show Debug Info under the Options menu will show \n"
-	    "the dependencies, which you can then match by examining other options.");
+	    "the dependencies, which you can then match by examining other options.";
 
 	dialog = gtk_message_dialog_new(GTK_WINDOW(main_wnd),
 					GTK_DIALOG_DESTROY_WITH_PARENT,
@@ -671,8 +671,8 @@ void on_about1_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	GtkWidget *dialog;
 	const gchar *about_text =
-	    _("gkc is copyright (c) 2002 Romain Lievin <roms@lpg.ticalc.org>.\n"
-	      "Based on the source code from Roman Zippel.\n");
+	    "gkc is copyright (c) 2002 Romain Lievin <roms@lpg.ticalc.org>.\n"
+	      "Based on the source code from Roman Zippel.\n";
 
 	dialog = gtk_message_dialog_new(GTK_WINDOW(main_wnd),
 					GTK_DIALOG_DESTROY_WITH_PARENT,
@@ -689,9 +689,9 @@ void on_license1_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	GtkWidget *dialog;
 	const gchar *license_text =
-	    _("gkc is released under the terms of the GNU GPL v2.\n"
+	    "gkc is released under the terms of the GNU GPL v2.\n"
 	      "For more information, please see the source code or\n"
-	      "visit http://www.fsf.org/licenses/licenses.html\n");
+	      "visit http://www.fsf.org/licenses/licenses.html\n";
 
 	dialog = gtk_message_dialog_new(GTK_WINDOW(main_wnd),
 					GTK_DIALOG_DESTROY_WITH_PARENT,
@@ -1049,7 +1049,7 @@ static gchar **fill_row(struct menu *menu)
 	bzero(row, sizeof(row));
 
 	row[COL_OPTION] =
-	    g_strdup_printf("%s %s", _(menu_get_prompt(menu)),
+	    g_strdup_printf("%s %s", menu_get_prompt(menu),
 			    sym && !sym_has_value(sym) ? "(NEW)" : "");
 
 	if (opt_mode == OPT_ALL && !menu_is_visible(menu))
@@ -1102,7 +1102,7 @@ static gchar **fill_row(struct menu *menu)
 
 		if (def_menu)
 			row[COL_VALUE] =
-			    g_strdup(_(menu_get_prompt(def_menu)));
+			    g_strdup(menu_get_prompt(def_menu));
 	}
 	if (sym->flags & SYMBOL_CHOICEVAL)
 		row[COL_BTNRAD] = GINT_TO_POINTER(TRUE);
@@ -1447,10 +1447,6 @@ int main(int ac, char *av[])
 	char *env;
 	gchar *glade_file;
 
-	bindtextdomain(PACKAGE, LOCALEDIR);
-	bind_textdomain_codeset(PACKAGE, "UTF-8");
-	textdomain(PACKAGE);
-
 	/* GTK stuffs */
 	gtk_set_locale();
 	gtk_init(&ac, &av);
diff --git a/scripts/kconfig/kconf_id.c b/scripts/kconfig/kconf_id.c
index 3ea9c5f9f730..b3e0ea0ac732 100644
--- a/scripts/kconfig/kconf_id.c
+++ b/scripts/kconfig/kconf_id.c
@@ -32,7 +32,6 @@ static struct kconf_id kconf_id_array[] = {
 	{ "on",			T_ON,			TF_PARAM },
 	{ "modules",		T_OPT_MODULES,		TF_OPTION },
 	{ "defconfig_list",	T_OPT_DEFCONFIG_LIST,	TF_OPTION },
-	{ "env",		T_OPT_ENV,		TF_OPTION },
 	{ "allnoconfig_y",	T_OPT_ALLNOCONFIG_Y,	TF_OPTION },
 };
 
diff --git a/scripts/kconfig/kxgettext.c b/scripts/kconfig/kxgettext.c
deleted file mode 100644
index 240880a89111..000000000000
--- a/scripts/kconfig/kxgettext.c
+++ /dev/null
@@ -1,235 +0,0 @@
-/*
- * Arnaldo Carvalho de Melo <acme@conectiva.com.br>, 2005
- *
- * Released under the terms of the GNU GPL v2.0
- */
-
-#include <stdlib.h>
-#include <string.h>
-
-#include "lkc.h"
-
-static char *escape(const char* text, char *bf, int len)
-{
-	char *bfp = bf;
-	int multiline = strchr(text, '\n') != NULL;
-	int eol = 0;
-	int textlen = strlen(text);
-
-	if ((textlen > 0) && (text[textlen-1] == '\n'))
-		eol = 1;
-
-	*bfp++ = '"';
-	--len;
-
-	if (multiline) {
-		*bfp++ = '"';
-		*bfp++ = '\n';
-		*bfp++ = '"';
-		len -= 3;
-	}
-
-	while (*text != '\0' && len > 1) {
-		if (*text == '"')
-			*bfp++ = '\\';
-		else if (*text == '\n') {
-			*bfp++ = '\\';
-			*bfp++ = 'n';
-			*bfp++ = '"';
-			*bfp++ = '\n';
-			*bfp++ = '"';
-			len -= 5;
-			++text;
-			goto next;
-		}
-		else if (*text == '\\') {
-			*bfp++ = '\\';
-			len--;
-		}
-		*bfp++ = *text++;
-next:
-		--len;
-	}
-
-	if (multiline && eol)
-		bfp -= 3;
-
-	*bfp++ = '"';
-	*bfp = '\0';
-
-	return bf;
-}
-
-struct file_line {
-	struct file_line *next;
-	const char *file;
-	int lineno;
-};
-
-static struct file_line *file_line__new(const char *file, int lineno)
-{
-	struct file_line *self = malloc(sizeof(*self));
-
-	if (self == NULL)
-		goto out;
-
-	self->file   = file;
-	self->lineno = lineno;
-	self->next   = NULL;
-out:
-	return self;
-}
-
-struct message {
-	const char	 *msg;
-	const char	 *option;
-	struct message	 *next;
-	struct file_line *files;
-};
-
-static struct message *message__list;
-
-static struct message *message__new(const char *msg, char *option,
-				    const char *file, int lineno)
-{
-	struct message *self = malloc(sizeof(*self));
-
-	if (self == NULL)
-		goto out;
-
-	self->files = file_line__new(file, lineno);
-	if (self->files == NULL)
-		goto out_fail;
-
-	self->msg = xstrdup(msg);
-	if (self->msg == NULL)
-		goto out_fail_msg;
-
-	self->option = option;
-	self->next = NULL;
-out:
-	return self;
-out_fail_msg:
-	free(self->files);
-out_fail:
-	free(self);
-	self = NULL;
-	goto out;
-}
-
-static struct message *mesage__find(const char *msg)
-{
-	struct message *m = message__list;
-
-	while (m != NULL) {
-		if (strcmp(m->msg, msg) == 0)
-			break;
-		m = m->next;
-	}
-
-	return m;
-}
-
-static int message__add_file_line(struct message *self, const char *file,
-				  int lineno)
-{
-	int rc = -1;
-	struct file_line *fl = file_line__new(file, lineno);
-
-	if (fl == NULL)
-		goto out;
-
-	fl->next    = self->files;
-	self->files = fl;
-	rc = 0;
-out:
-	return rc;
-}
-
-static int message__add(const char *msg, char *option, const char *file,
-			int lineno)
-{
-	int rc = 0;
-	char bf[16384];
-	char *escaped = escape(msg, bf, sizeof(bf));
-	struct message *m = mesage__find(escaped);
-
-	if (m != NULL)
-		rc = message__add_file_line(m, file, lineno);
-	else {
-		m = message__new(escaped, option, file, lineno);
-
-		if (m != NULL) {
-			m->next	      = message__list;
-			message__list = m;
-		} else
-			rc = -1;
-	}
-	return rc;
-}
-
-static void menu_build_message_list(struct menu *menu)
-{
-	struct menu *child;
-
-	message__add(menu_get_prompt(menu), NULL,
-		     menu->file == NULL ? "Root Menu" : menu->file->name,
-		     menu->lineno);
-
-	if (menu->sym != NULL && menu_has_help(menu))
-		message__add(menu_get_help(menu), menu->sym->name,
-			     menu->file == NULL ? "Root Menu" : menu->file->name,
-			     menu->lineno);
-
-	for (child = menu->list; child != NULL; child = child->next)
-		if (child->prompt != NULL)
-			menu_build_message_list(child);
-}
-
-static void message__print_file_lineno(struct message *self)
-{
-	struct file_line *fl = self->files;
-
-	putchar('\n');
-	if (self->option != NULL)
-		printf("# %s:00000\n", self->option);
-
-	printf("#: %s:%d", fl->file, fl->lineno);
-	fl = fl->next;
-
-	while (fl != NULL) {
-		printf(", %s:%d", fl->file, fl->lineno);
-		fl = fl->next;
-	}
-
-	putchar('\n');
-}
-
-static void message__print_gettext_msgid_msgstr(struct message *self)
-{
-	message__print_file_lineno(self);
-
-	printf("msgid %s\n"
-	       "msgstr \"\"\n", self->msg);
-}
-
-static void menu__xgettext(void)
-{
-	struct message *m = message__list;
-
-	while (m != NULL) {
-		/* skip empty lines ("") */
-		if (strlen(m->msg) > sizeof("\"\""))
-			message__print_gettext_msgid_msgstr(m);
-		m = m->next;
-	}
-}
-
-int main(int ac, char **av)
-{
-	conf_parse(av[1]);
-
-	menu_build_message_list(menu_get_root_menu(NULL));
-	menu__xgettext();
-	return 0;
-}
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index f4394af6e4b8..ed3ff88e60ba 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -8,15 +8,6 @@
 
 #include "expr.h"
 
-#ifndef KBUILD_NO_NLS
-# include <libintl.h>
-#else
-static inline const char *gettext(const char *txt) { return txt; }
-static inline void textdomain(const char *domainname) {}
-static inline void bindtextdomain(const char *name, const char *dir) {}
-static inline char *bind_textdomain_codeset(const char *dn, char *c) { return c; }
-#endif
-
 #ifdef __cplusplus
 extern "C" {
 #endif
@@ -29,11 +20,6 @@ extern "C" {
 #define PACKAGE "linux"
 #endif
 
-#define LOCALEDIR "/usr/share/locale"
-
-#define _(text) gettext(text)
-#define N_(text) (text)
-
 #ifndef CONFIG_
 #define CONFIG_ "CONFIG_"
 #endif
@@ -58,7 +44,6 @@ enum conf_def_mode {
 
 #define T_OPT_MODULES		1
 #define T_OPT_DEFCONFIG_LIST	2
-#define T_OPT_ENV		3
 #define T_OPT_ALLNOCONFIG_Y	4
 
 struct kconf_id {
@@ -117,6 +102,7 @@ void *xmalloc(size_t size);
 void *xcalloc(size_t nmemb, size_t size);
 void *xrealloc(void *p, size_t size);
 char *xstrdup(const char *s);
+char *xstrndup(const char *s, size_t n);
 
 struct gstr {
 	size_t len;
@@ -134,9 +120,6 @@ void str_printf(struct gstr *gs, const char *fmt, ...);
 const char *str_get(struct gstr *gs);
 
 /* symbol.c */
-extern struct expr *sym_env_list;
-
-void sym_init(void);
 void sym_clear_all_valid(void);
 struct symbol *sym_choice_default(struct symbol *sym);
 const char *sym_get_string_default(struct symbol *sym);
diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h
index 9dc8abfb1dc3..a8b7a330587e 100644
--- a/scripts/kconfig/lkc_proto.h
+++ b/scripts/kconfig/lkc_proto.h
@@ -31,7 +31,6 @@ extern struct symbol * symbol_hash[SYMBOL_HASHSIZE];
 
 struct symbol * sym_lookup(const char *name, int flags);
 struct symbol * sym_find(const char *name);
-char *sym_expand_string_value(const char *in);
 const char * sym_escape_string_value(const char *in);
 struct symbol ** sym_re_search(const char *pattern);
 const char * sym_type_name(enum symbol_type type);
@@ -49,5 +48,19 @@ const char * sym_get_string_value(struct symbol *sym);
 
 const char * prop_get_type_name(enum prop_type type);
 
+/* preprocess.c */
+enum variable_flavor {
+	VAR_SIMPLE,
+	VAR_RECURSIVE,
+	VAR_APPEND,
+};
+void env_write_dep(FILE *f, const char *auto_conf_name);
+void variable_add(const char *name, const char *value,
+		  enum variable_flavor flavor);
+void variable_all_del(void);
+char *expand_string(const char *in);
+char *expand_dollar(const char **str);
+char *expand_one_token(const char **str);
+
 /* expr.c */
 void expr_print(struct expr *e, void (*fn)(void *, struct symbol *, const char *), void *data, int prevtoken);
diff --git a/scripts/kconfig/lxdialog/check-lxdialog.sh b/scripts/kconfig/lxdialog/check-lxdialog.sh
deleted file mode 100755
index 6c0bcd9c472d..000000000000
--- a/scripts/kconfig/lxdialog/check-lxdialog.sh
+++ /dev/null
@@ -1,93 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Check ncurses compatibility
-
-# What library to link
-ldflags()
-{
-	pkg-config --libs ncursesw 2>/dev/null && exit
-	pkg-config --libs ncurses 2>/dev/null && exit
-	for ext in so a dll.a dylib ; do
-		for lib in ncursesw ncurses curses ; do
-			$cc -print-file-name=lib${lib}.${ext} | grep -q /
-			if [ $? -eq 0 ]; then
-				echo "-l${lib}"
-				exit
-			fi
-		done
-	done
-	exit 1
-}
-
-# Where is ncurses.h?
-ccflags()
-{
-	if pkg-config --cflags ncursesw 2>/dev/null; then
-		echo '-DCURSES_LOC="<ncurses.h>" -DNCURSES_WIDECHAR=1'
-	elif pkg-config --cflags ncurses 2>/dev/null; then
-		echo '-DCURSES_LOC="<ncurses.h>"'
-	elif [ -f /usr/include/ncursesw/curses.h ]; then
-		echo '-I/usr/include/ncursesw -DCURSES_LOC="<curses.h>"'
-		echo ' -DNCURSES_WIDECHAR=1'
-	elif [ -f /usr/include/ncurses/ncurses.h ]; then
-		echo '-I/usr/include/ncurses -DCURSES_LOC="<ncurses.h>"'
-	elif [ -f /usr/include/ncurses/curses.h ]; then
-		echo '-I/usr/include/ncurses -DCURSES_LOC="<curses.h>"'
-	elif [ -f /usr/include/ncurses.h ]; then
-		echo '-DCURSES_LOC="<ncurses.h>"'
-	else
-		echo '-DCURSES_LOC="<curses.h>"'
-	fi
-}
-
-# Temp file, try to clean up after us
-tmp=.lxdialog.tmp
-trap "rm -f $tmp" 0 1 2 3 15
-
-# Check if we can link to ncurses
-check() {
-        $cc -x c - -o $tmp 2>/dev/null <<'EOF'
-#include CURSES_LOC
-main() {}
-EOF
-	if [ $? != 0 ]; then
-	    echo " *** Unable to find the ncurses libraries or the"       1>&2
-	    echo " *** required header files."                            1>&2
-	    echo " *** 'make menuconfig' requires the ncurses libraries." 1>&2
-	    echo " *** "                                                  1>&2
-	    echo " *** Install ncurses (ncurses-devel or libncurses-dev " 1>&2
-	    echo " *** depending on your distribution) and try again."    1>&2
-	    echo " *** "                                                  1>&2
-	    exit 1
-	fi
-}
-
-usage() {
-	printf "Usage: $0 [-check compiler options|-ccflags|-ldflags compiler options]\n"
-}
-
-if [ $# -eq 0 ]; then
-	usage
-	exit 1
-fi
-
-cc=""
-case "$1" in
-	"-check")
-		shift
-		cc="$@"
-		check
-		;;
-	"-ccflags")
-		ccflags
-		;;
-	"-ldflags")
-		shift
-		cc="$@"
-		ldflags
-		;;
-	"*")
-		usage
-		exit 1
-		;;
-esac
diff --git a/scripts/kconfig/lxdialog/checklist.c b/scripts/kconfig/lxdialog/checklist.c
index 8d016faa28d7..2e96323ad11b 100644
--- a/scripts/kconfig/lxdialog/checklist.c
+++ b/scripts/kconfig/lxdialog/checklist.c
@@ -103,8 +103,8 @@ static void print_buttons(WINDOW * dialog, int height, int width, int selected)
 	int x = width / 2 - 11;
 	int y = height - 2;
 
-	print_button(dialog, gettext("Select"), y, x, selected == 0);
-	print_button(dialog, gettext(" Help "), y, x + 14, selected == 1);
+	print_button(dialog, "Select", y, x, selected == 0);
+	print_button(dialog, " Help ", y, x + 14, selected == 1);
 
 	wmove(dialog, y, x + 1 + 14 * selected);
 	wrefresh(dialog);
diff --git a/scripts/kconfig/lxdialog/dialog.h b/scripts/kconfig/lxdialog/dialog.h
index fcffd5b41fb0..0b00be5abaa6 100644
--- a/scripts/kconfig/lxdialog/dialog.h
+++ b/scripts/kconfig/lxdialog/dialog.h
@@ -26,16 +26,10 @@
 #include <string.h>
 #include <stdbool.h>
 
-#ifndef KBUILD_NO_NLS
-# include <libintl.h>
-#else
-# define gettext(Msgid) ((const char *) (Msgid))
-#endif
-
 #ifdef __sun__
 #define CURS_MACROS
 #endif
-#include CURSES_LOC
+#include <ncurses.h>
 
 /*
  * Colors in ncurses 1.9.9e do not work properly since foreground and
diff --git a/scripts/kconfig/lxdialog/inputbox.c b/scripts/kconfig/lxdialog/inputbox.c
index d58de1dc5360..fe82ff6d744e 100644
--- a/scripts/kconfig/lxdialog/inputbox.c
+++ b/scripts/kconfig/lxdialog/inputbox.c
@@ -31,8 +31,8 @@ static void print_buttons(WINDOW * dialog, int height, int width, int selected)
 	int x = width / 2 - 11;
 	int y = height - 2;
 
-	print_button(dialog, gettext("  Ok  "), y, x, selected == 0);
-	print_button(dialog, gettext(" Help "), y, x + 14, selected == 1);
+	print_button(dialog, "  Ok  ", y, x, selected == 0);
+	print_button(dialog, " Help ", y, x + 14, selected == 1);
 
 	wmove(dialog, y, x + 1 + 14 * selected);
 	wrefresh(dialog);
diff --git a/scripts/kconfig/lxdialog/menubox.c b/scripts/kconfig/lxdialog/menubox.c
index 11ae9ad7ac7b..d70cab36137e 100644
--- a/scripts/kconfig/lxdialog/menubox.c
+++ b/scripts/kconfig/lxdialog/menubox.c
@@ -157,11 +157,11 @@ static void print_buttons(WINDOW * win, int height, int width, int selected)
 	int x = width / 2 - 28;
 	int y = height - 2;
 
-	print_button(win, gettext("Select"), y, x, selected == 0);
-	print_button(win, gettext(" Exit "), y, x + 12, selected == 1);
-	print_button(win, gettext(" Help "), y, x + 24, selected == 2);
-	print_button(win, gettext(" Save "), y, x + 36, selected == 3);
-	print_button(win, gettext(" Load "), y, x + 48, selected == 4);
+	print_button(win, "Select", y, x, selected == 0);
+	print_button(win, " Exit ", y, x + 12, selected == 1);
+	print_button(win, " Help ", y, x + 24, selected == 2);
+	print_button(win, " Save ", y, x + 36, selected == 3);
+	print_button(win, " Load ", y, x + 48, selected == 4);
 
 	wmove(win, y, x + 1 + 12 * selected);
 	wrefresh(win);
diff --git a/scripts/kconfig/lxdialog/textbox.c b/scripts/kconfig/lxdialog/textbox.c
index 1773319b95e7..88d2818ed956 100644
--- a/scripts/kconfig/lxdialog/textbox.c
+++ b/scripts/kconfig/lxdialog/textbox.c
@@ -129,7 +129,7 @@ do_resize:
 
 	print_title(dialog, title, width);
 
-	print_button(dialog, gettext(" Exit "), height - 2, width / 2 - 4, TRUE);
+	print_button(dialog, " Exit ", height - 2, width / 2 - 4, TRUE);
 	wnoutrefresh(dialog);
 	getyx(dialog, cur_y, cur_x);	/* Save cursor position */
 
diff --git a/scripts/kconfig/lxdialog/yesno.c b/scripts/kconfig/lxdialog/yesno.c
index 676fb2f824a3..cd1223c903d1 100644
--- a/scripts/kconfig/lxdialog/yesno.c
+++ b/scripts/kconfig/lxdialog/yesno.c
@@ -29,8 +29,8 @@ static void print_buttons(WINDOW * dialog, int height, int width, int selected)
 	int x = width / 2 - 10;
 	int y = height - 2;
 
-	print_button(dialog, gettext(" Yes "), y, x, selected == 0);
-	print_button(dialog, gettext("  No  "), y, x + 13, selected == 1);
+	print_button(dialog, " Yes ", y, x, selected == 0);
+	print_button(dialog, "  No  ", y, x + 13, selected == 1);
 
 	wmove(dialog, y, x + 1 + 13 * selected);
 	wrefresh(dialog);
diff --git a/scripts/kconfig/mconf-cfg.sh b/scripts/kconfig/mconf-cfg.sh
new file mode 100755
index 000000000000..e6f9facd0077
--- /dev/null
+++ b/scripts/kconfig/mconf-cfg.sh
@@ -0,0 +1,44 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+PKG="ncursesw"
+PKG2="ncurses"
+
+if pkg-config --exists $PKG; then
+	echo cflags=\"$(pkg-config --cflags $PKG)\"
+	echo libs=\"$(pkg-config --libs $PKG)\"
+	exit 0
+fi
+
+if pkg-config --exists $PKG2; then
+	echo cflags=\"$(pkg-config --cflags $PKG2)\"
+	echo libs=\"$(pkg-config --libs $PKG2)\"
+	exit 0
+fi
+
+# Unfortunately, some distributions (e.g. openSUSE) cannot find ncurses
+# by pkg-config.
+if [ -f /usr/include/ncursesw/ncurses.h ]; then
+	echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncursesw\"
+	echo libs=\"-lncursesw\"
+	exit 0
+fi
+
+if [ -f /usr/include/ncurses/ncurses.h ]; then
+	echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncurses\"
+	echo libs=\"-lncurses\"
+	exit 0
+fi
+
+if [ -f /usr/include/ncurses.h ]; then
+	echo cflags=\"-D_GNU_SOURCE\"
+	echo libs=\"-lncurses\"
+	exit 0
+fi
+
+echo >&2 "*"
+echo >&2 "* Unable to find the ncurses package."
+echo >&2 "* Install ncurses (ncurses-devel or libncurses-dev"
+echo >&2 "* depending on your distribution)."
+echo >&2 "*"
+exit 1
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index c829be8bb19f..5294ed159b98 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -17,12 +17,11 @@
 #include <string.h>
 #include <signal.h>
 #include <unistd.h>
-#include <locale.h>
 
 #include "lkc.h"
 #include "lxdialog/dialog.h"
 
-static const char mconf_readme[] = N_(
+static const char mconf_readme[] =
 "Overview\n"
 "--------\n"
 "This interface lets you select features and parameters for the build.\n"
@@ -171,37 +170,37 @@ static const char mconf_readme[] = N_(
 " blackbg    => selects a color scheme with black background\n"
 " classic    => theme with blue background. The classic look\n"
 " bluetitle  => an LCD friendly version of classic. (default)\n"
-"\n"),
-menu_instructions[] = N_(
+"\n",
+menu_instructions[] =
 	"Arrow keys navigate the menu.  "
 	"<Enter> selects submenus ---> (or empty submenus ----).  "
 	"Highlighted letters are hotkeys.  "
 	"Pressing <Y> includes, <N> excludes, <M> modularizes features.  "
 	"Press <Esc><Esc> to exit, <?> for Help, </> for Search.  "
-	"Legend: [*] built-in  [ ] excluded  <M> module  < > module capable"),
-radiolist_instructions[] = N_(
+	"Legend: [*] built-in  [ ] excluded  <M> module  < > module capable",
+radiolist_instructions[] =
 	"Use the arrow keys to navigate this window or "
 	"press the hotkey of the item you wish to select "
 	"followed by the <SPACE BAR>. "
-	"Press <?> for additional information about this option."),
-inputbox_instructions_int[] = N_(
+	"Press <?> for additional information about this option.",
+inputbox_instructions_int[] =
 	"Please enter a decimal value. "
 	"Fractions will not be accepted.  "
-	"Use the <TAB> key to move from the input field to the buttons below it."),
-inputbox_instructions_hex[] = N_(
+	"Use the <TAB> key to move from the input field to the buttons below it.",
+inputbox_instructions_hex[] =
 	"Please enter a hexadecimal value. "
-	"Use the <TAB> key to move from the input field to the buttons below it."),
-inputbox_instructions_string[] = N_(
+	"Use the <TAB> key to move from the input field to the buttons below it.",
+inputbox_instructions_string[] =
 	"Please enter a string value. "
-	"Use the <TAB> key to move from the input field to the buttons below it."),
-setmod_text[] = N_(
+	"Use the <TAB> key to move from the input field to the buttons below it.",
+setmod_text[] =
 	"This feature depends on another which has been configured as a module.\n"
-	"As a result, this feature will be built as a module."),
-load_config_text[] = N_(
+	"As a result, this feature will be built as a module.",
+load_config_text[] =
 	"Enter the name of the configuration file you wish to load.  "
 	"Accept the name shown to restore the configuration you "
-	"last retrieved.  Leave blank to abort."),
-load_config_help[] = N_(
+	"last retrieved.  Leave blank to abort.",
+load_config_help[] =
 	"\n"
 	"For various reasons, one may wish to keep several different\n"
 	"configurations available on a single machine.\n"
@@ -211,11 +210,11 @@ load_config_help[] = N_(
 	"configuration.\n"
 	"\n"
 	"If you are uncertain, then you have probably never used alternate\n"
-	"configuration files. You should therefore leave this blank to abort.\n"),
-save_config_text[] = N_(
+	"configuration files. You should therefore leave this blank to abort.\n",
+save_config_text[] =
 	"Enter a filename to which this configuration should be saved "
-	"as an alternate.  Leave blank to abort."),
-save_config_help[] = N_(
+	"as an alternate.  Leave blank to abort.",
+save_config_help[] =
 	"\n"
 	"For various reasons, one may wish to keep different configurations\n"
 	"available on a single machine.\n"
@@ -225,8 +224,8 @@ save_config_help[] = N_(
 	"configuration options you have selected at that time.\n"
 	"\n"
 	"If you are uncertain what all this means then you should probably\n"
-	"leave this blank.\n"),
-search_help[] = N_(
+	"leave this blank.\n",
+search_help[] =
 	"\n"
 	"Search for symbols and display their relations.\n"
 	"Regular expressions are allowed.\n"
@@ -271,7 +270,7 @@ search_help[] = N_(
 	"Examples: USB	=> find all symbols containing USB\n"
 	"          ^USB => find all symbols starting with USB\n"
 	"          USB$ => find all symbols ending with USB\n"
-	"\n");
+	"\n";
 
 static int indent;
 static struct menu *current_menu;
@@ -400,19 +399,19 @@ static void search_conf(void)
 	struct subtitle_part stpart;
 
 	title = str_new();
-	str_printf( &title, _("Enter (sub)string or regexp to search for "
-			      "(with or without \"%s\")"), CONFIG_);
+	str_printf( &title, "Enter (sub)string or regexp to search for "
+			      "(with or without \"%s\")", CONFIG_);
 
 again:
 	dialog_clear();
-	dres = dialog_inputbox(_("Search Configuration Parameter"),
+	dres = dialog_inputbox("Search Configuration Parameter",
 			      str_get(&title),
 			      10, 75, "");
 	switch (dres) {
 	case 0:
 		break;
 	case 1:
-		show_helptext(_("Search Configuration"), search_help);
+		show_helptext("Search Configuration", search_help);
 		goto again;
 	default:
 		str_free(&title);
@@ -443,7 +442,7 @@ again:
 
 		res = get_relations_str(sym_arr, &head);
 		set_subtitle();
-		dres = show_textbox_ext(_("Search Results"), (char *)
+		dres = show_textbox_ext("Search Results", (char *)
 					str_get(&res), 0, 0, keys, &vscroll,
 					&hscroll, &update_text, (void *)
 					&data);
@@ -491,7 +490,7 @@ static void build_conf(struct menu *menu)
 			switch (prop->type) {
 			case P_MENU:
 				child_count++;
-				prompt = _(prompt);
+				prompt = prompt;
 				if (single_menu_mode) {
 					item_make("%s%*c%s",
 						  menu->data ? "-->" : "++>",
@@ -508,7 +507,7 @@ static void build_conf(struct menu *menu)
 			case P_COMMENT:
 				if (prompt) {
 					child_count++;
-					item_make("   %*c*** %s ***", indent + 1, ' ', _(prompt));
+					item_make("   %*c*** %s ***", indent + 1, ' ', prompt);
 					item_set_tag(':');
 					item_set_data(menu);
 				}
@@ -516,7 +515,7 @@ static void build_conf(struct menu *menu)
 			default:
 				if (prompt) {
 					child_count++;
-					item_make("---%*c%s", indent + 1, ' ', _(prompt));
+					item_make("---%*c%s", indent + 1, ' ', prompt);
 					item_set_tag(':');
 					item_set_data(menu);
 				}
@@ -560,10 +559,10 @@ static void build_conf(struct menu *menu)
 			item_set_data(menu);
 		}
 
-		item_add_str("%*c%s", indent + 1, ' ', _(menu_get_prompt(menu)));
+		item_add_str("%*c%s", indent + 1, ' ', menu_get_prompt(menu));
 		if (val == yes) {
 			if (def_menu) {
-				item_add_str(" (%s)", _(menu_get_prompt(def_menu)));
+				item_add_str(" (%s)", menu_get_prompt(def_menu));
 				item_add_str("  --->");
 				if (def_menu->list) {
 					indent += 2;
@@ -575,7 +574,7 @@ static void build_conf(struct menu *menu)
 		}
 	} else {
 		if (menu == current_menu) {
-			item_make("---%*c%s", indent + 1, ' ', _(menu_get_prompt(menu)));
+			item_make("---%*c%s", indent + 1, ' ', menu_get_prompt(menu));
 			item_set_tag(':');
 			item_set_data(menu);
 			goto conf_childs;
@@ -618,17 +617,17 @@ static void build_conf(struct menu *menu)
 				tmp = indent - tmp + 4;
 				if (tmp < 0)
 					tmp = 0;
-				item_add_str("%*c%s%s", tmp, ' ', _(menu_get_prompt(menu)),
+				item_add_str("%*c%s%s", tmp, ' ', menu_get_prompt(menu),
 					     (sym_has_value(sym) || !sym_is_changable(sym)) ?
-					     "" : _(" (NEW)"));
+					     "" : " (NEW)");
 				item_set_tag('s');
 				item_set_data(menu);
 				goto conf_childs;
 			}
 		}
-		item_add_str("%*c%s%s", indent + 1, ' ', _(menu_get_prompt(menu)),
+		item_add_str("%*c%s%s", indent + 1, ' ', menu_get_prompt(menu),
 			  (sym_has_value(sym) || !sym_is_changable(sym)) ?
-			  "" : _(" (NEW)"));
+			  "" : " (NEW)");
 		if (menu->prompt->type == P_MENU) {
 			item_add_str("  %s", menu_is_empty(menu) ? "----" : "--->");
 			return;
@@ -665,8 +664,8 @@ static void conf(struct menu *menu, struct menu *active_menu)
 			break;
 		set_subtitle();
 		dialog_clear();
-		res = dialog_menu(prompt ? _(prompt) : _("Main Menu"),
-				  _(menu_instructions),
+		res = dialog_menu(prompt ? prompt : "Main Menu",
+				  menu_instructions,
 				  active_menu, &s_scroll);
 		if (res == 1 || res == KEY_ESC || res == -ERRDISPLAYTOOSMALL)
 			break;
@@ -708,7 +707,7 @@ static void conf(struct menu *menu, struct menu *active_menu)
 				show_help(submenu);
 			else {
 				reset_subtitle();
-				show_helptext(_("README"), _(mconf_readme));
+				show_helptext("README", mconf_readme);
 			}
 			break;
 		case 3:
@@ -793,13 +792,13 @@ static void show_help(struct menu *menu)
 	help.max_width = getmaxx(stdscr) - 10;
 	menu_get_ext_help(menu, &help);
 
-	show_helptext(_(menu_get_prompt(menu)), str_get(&help));
+	show_helptext(menu_get_prompt(menu), str_get(&help));
 	str_free(&help);
 }
 
 static void conf_choice(struct menu *menu)
 {
-	const char *prompt = _(menu_get_prompt(menu));
+	const char *prompt = menu_get_prompt(menu);
 	struct menu *child;
 	struct symbol *active;
 
@@ -814,9 +813,9 @@ static void conf_choice(struct menu *menu)
 			if (!menu_is_visible(child))
 				continue;
 			if (child->sym)
-				item_make("%s", _(menu_get_prompt(child)));
+				item_make("%s", menu_get_prompt(child));
 			else {
-				item_make("*** %s ***", _(menu_get_prompt(child)));
+				item_make("*** %s ***", menu_get_prompt(child));
 				item_set_tag(':');
 			}
 			item_set_data(child);
@@ -826,8 +825,8 @@ static void conf_choice(struct menu *menu)
 				item_set_tag('X');
 		}
 		dialog_clear();
-		res = dialog_checklist(prompt ? _(prompt) : _("Main Menu"),
-					_(radiolist_instructions),
+		res = dialog_checklist(prompt ? prompt : "Main Menu",
+					radiolist_instructions,
 					MENUBOX_HEIGTH_MIN,
 					MENUBOX_WIDTH_MIN,
 					CHECKLIST_HEIGTH_MIN);
@@ -868,26 +867,26 @@ static void conf_string(struct menu *menu)
 
 		switch (sym_get_type(menu->sym)) {
 		case S_INT:
-			heading = _(inputbox_instructions_int);
+			heading = inputbox_instructions_int;
 			break;
 		case S_HEX:
-			heading = _(inputbox_instructions_hex);
+			heading = inputbox_instructions_hex;
 			break;
 		case S_STRING:
-			heading = _(inputbox_instructions_string);
+			heading = inputbox_instructions_string;
 			break;
 		default:
-			heading = _("Internal mconf error!");
+			heading = "Internal mconf error!";
 		}
 		dialog_clear();
-		res = dialog_inputbox(prompt ? _(prompt) : _("Main Menu"),
+		res = dialog_inputbox(prompt ? prompt : "Main Menu",
 				      heading, 10, 75,
 				      sym_get_string_value(menu->sym));
 		switch (res) {
 		case 0:
 			if (sym_set_string_value(menu->sym, dialog_input_result))
 				return;
-			show_textbox(NULL, _("You have made an invalid entry."), 5, 43);
+			show_textbox(NULL, "You have made an invalid entry.", 5, 43);
 			break;
 		case 1:
 			show_help(menu);
@@ -915,10 +914,10 @@ static void conf_load(void)
 				sym_set_change_count(1);
 				return;
 			}
-			show_textbox(NULL, _("File does not exist!"), 5, 38);
+			show_textbox(NULL, "File does not exist!", 5, 38);
 			break;
 		case 1:
-			show_helptext(_("Load Alternate Configuration"), load_config_help);
+			show_helptext("Load Alternate Configuration", load_config_help);
 			break;
 		case KEY_ESC:
 			return;
@@ -941,10 +940,10 @@ static void conf_save(void)
 				set_config_filename(dialog_input_result);
 				return;
 			}
-			show_textbox(NULL, _("Can't create file!  Probably a nonexistent directory."), 5, 60);
+			show_textbox(NULL, "Can't create file!  Probably a nonexistent directory.", 5, 60);
 			break;
 		case 1:
-			show_helptext(_("Save Alternate Configuration"), save_config_help);
+			show_helptext("Save Alternate Configuration", save_config_help);
 			break;
 		case KEY_ESC:
 			return;
@@ -961,8 +960,8 @@ static int handle_exit(void)
 	dialog_clear();
 	if (conf_get_changed())
 		res = dialog_yesno(NULL,
-				   _("Do you wish to save your new configuration?\n"
-				     "(Press <ESC><ESC> to continue kernel configuration.)"),
+				   "Do you wish to save your new configuration?\n"
+				     "(Press <ESC><ESC> to continue kernel configuration.)",
 				   6, 60);
 	else
 		res = -1;
@@ -972,26 +971,26 @@ static int handle_exit(void)
 	switch (res) {
 	case 0:
 		if (conf_write(filename)) {
-			fprintf(stderr, _("\n\n"
+			fprintf(stderr, "\n\n"
 					  "Error while writing of the configuration.\n"
 					  "Your configuration changes were NOT saved."
-					  "\n\n"));
+					  "\n\n");
 			return 1;
 		}
 		/* fall through */
 	case -1:
 		if (!silent)
-			printf(_("\n\n"
+			printf("\n\n"
 				 "*** End of the configuration.\n"
 				 "*** Execute 'make' to start the build or try 'make help'."
-				 "\n\n"));
+				 "\n\n");
 		res = 0;
 		break;
 	default:
 		if (!silent)
-			fprintf(stderr, _("\n\n"
+			fprintf(stderr, "\n\n"
 					  "Your configuration changes were NOT saved."
-					  "\n\n"));
+					  "\n\n");
 		if (res != KEY_ESC)
 			res = 0;
 	}
@@ -1009,10 +1008,6 @@ int main(int ac, char **av)
 	char *mode;
 	int res;
 
-	setlocale(LC_ALL, "");
-	bindtextdomain(PACKAGE, LOCALEDIR);
-	textdomain(PACKAGE);
-
 	signal(SIGINT, sig_handler);
 
 	if (ac > 1 && strcmp(av[1], "-s") == 0) {
@@ -1031,8 +1026,8 @@ int main(int ac, char **av)
 	}
 
 	if (init_dialog(NULL)) {
-		fprintf(stderr, N_("Your display is too small to run Menuconfig!\n"));
-		fprintf(stderr, N_("It must be at least 19 lines by 80 columns.\n"));
+		fprintf(stderr, "Your display is too small to run Menuconfig!\n");
+		fprintf(stderr, "It must be at least 19 lines by 80 columns.\n");
 		return 1;
 	}
 
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 5c5c1374b151..379a119dcd1e 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -214,9 +214,6 @@ void menu_add_option(int token, char *arg)
 			zconf_error("trying to redefine defconfig symbol");
 		sym_defconfig_list->flags |= SYMBOL_AUTO;
 		break;
-	case T_OPT_ENV:
-		prop_add_env(arg);
-		break;
 	case T_OPT_ALLNOCONFIG_Y:
 		current_entry->sym->flags |= SYMBOL_ALLNOCONFIG_Y;
 		break;
@@ -711,7 +708,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
 	struct menu *submenu[8], *menu, *location = NULL;
 	struct jump_key *jump = NULL;
 
-	str_printf(r, _("Prompt: %s\n"), _(prop->text));
+	str_printf(r, "Prompt: %s\n", prop->text);
 	menu = prop->menu->parent;
 	for (i = 0; menu != &rootmenu && i < 8; menu = menu->parent) {
 		bool accessible = menu_is_visible(menu);
@@ -744,16 +741,16 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
 	}
 
 	if (i > 0) {
-		str_printf(r, _("  Location:\n"));
+		str_printf(r, "  Location:\n");
 		for (j = 4; --i >= 0; j += 2) {
 			menu = submenu[i];
 			if (jump && menu == location)
 				jump->offset = strlen(r->s);
 			str_printf(r, "%*c-> %s", j, ' ',
-				   _(menu_get_prompt(menu)));
+				   menu_get_prompt(menu));
 			if (menu->sym) {
 				str_printf(r, " (%s [=%s])", menu->sym->name ?
-					menu->sym->name : _("<choice>"),
+					menu->sym->name : "<choice>",
 					sym_get_string_value(menu->sym));
 			}
 			str_append(r, "\n");
@@ -817,23 +814,23 @@ static void get_symbol_str(struct gstr *r, struct symbol *sym,
 
 	prop = get_symbol_prop(sym);
 	if (prop) {
-		str_printf(r, _("  Defined at %s:%d\n"), prop->menu->file->name,
+		str_printf(r, "  Defined at %s:%d\n", prop->menu->file->name,
 			prop->menu->lineno);
 		if (!expr_is_yes(prop->visible.expr)) {
-			str_append(r, _("  Depends on: "));
+			str_append(r, "  Depends on: ");
 			expr_gstr_print(prop->visible.expr, r);
 			str_append(r, "\n");
 		}
 	}
 
-	get_symbol_props_str(r, sym, P_SELECT, _("  Selects: "));
+	get_symbol_props_str(r, sym, P_SELECT, "  Selects: ");
 	if (sym->rev_dep.expr) {
 		expr_gstr_print_revdep(sym->rev_dep.expr, r, yes, "  Selected by [y]:\n");
 		expr_gstr_print_revdep(sym->rev_dep.expr, r, mod, "  Selected by [m]:\n");
 		expr_gstr_print_revdep(sym->rev_dep.expr, r, no, "  Selected by [n]:\n");
 	}
 
-	get_symbol_props_str(r, sym, P_IMPLY, _("  Implies: "));
+	get_symbol_props_str(r, sym, P_IMPLY, "  Implies: ");
 	if (sym->implied.expr) {
 		expr_gstr_print_revdep(sym->implied.expr, r, yes, "  Implied by [y]:\n");
 		expr_gstr_print_revdep(sym->implied.expr, r, mod, "  Implied by [m]:\n");
@@ -852,7 +849,7 @@ struct gstr get_relations_str(struct symbol **sym_arr, struct list_head *head)
 	for (i = 0; sym_arr && (sym = sym_arr[i]); i++)
 		get_symbol_str(&res, sym, head);
 	if (!i)
-		str_append(&res, _("No matches found.\n"));
+		str_append(&res, "No matches found.\n");
 	return res;
 }
 
@@ -867,7 +864,7 @@ void menu_get_ext_help(struct menu *menu, struct gstr *help)
 			str_printf(help, "%s%s:\n\n", CONFIG_, sym->name);
 		help_text = menu_get_help(menu);
 	}
-	str_printf(help, "%s\n", _(help_text));
+	str_printf(help, "%s\n", help_text);
 	if (sym)
 		get_symbol_str(help, sym, NULL);
 }
diff --git a/scripts/kconfig/nconf-cfg.sh b/scripts/kconfig/nconf-cfg.sh
new file mode 100644
index 000000000000..42f5ac73548e
--- /dev/null
+++ b/scripts/kconfig/nconf-cfg.sh
@@ -0,0 +1,44 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+PKG="ncursesw menuw panelw"
+PKG2="ncurses menu panel"
+
+if pkg-config --exists $PKG; then
+	echo cflags=\"$(pkg-config --cflags $PKG)\"
+	echo libs=\"$(pkg-config --libs $PKG)\"
+	exit 0
+fi
+
+if pkg-config --exists $PKG2; then
+	echo cflags=\"$(pkg-config --cflags $PKG2)\"
+	echo libs=\"$(pkg-config --libs $PKG2)\"
+	exit 0
+fi
+
+# Unfortunately, some distributions (e.g. openSUSE) cannot find ncurses
+# by pkg-config.
+if [ -f /usr/include/ncursesw/ncurses.h ]; then
+	echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncursesw\"
+	echo libs=\"-lncursesw -lmenuw -lpanelw\"
+	exit 0
+fi
+
+if [ -f /usr/include/ncurses/ncurses.h ]; then
+	echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncurses\"
+	echo libs=\"-lncurses -lmenu -lpanel\"
+	exit 0
+fi
+
+if [ -f /usr/include/ncurses.h ]; then
+	echo cflags=\"-D_GNU_SOURCE\"
+	echo libs=\"-lncurses -lmenu -lpanel\"
+	exit 0
+fi
+
+echo >&2 "*"
+echo >&2 "* Unable to find the ncurses package."
+echo >&2 "* Install ncurses (ncurses-devel or libncurses-dev"
+echo >&2 "* depending on your distribution)."
+echo >&2 "*"
+exit 1
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index 003114779815..97b78445584b 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -15,7 +15,7 @@
 #include "nconf.h"
 #include <ctype.h>
 
-static const char nconf_global_help[] = N_(
+static const char nconf_global_help[] =
 "Help windows\n"
 "------------\n"
 "o  Global help:  Unless in a data entry window, pressing <F1> will give \n"
@@ -130,8 +130,8 @@ static const char nconf_global_help[] = N_(
 "\n"
 "Note that this mode can eventually be a little more CPU expensive than\n"
 "the default mode, especially with a larger number of unfolded submenus.\n"
-"\n"),
-menu_no_f_instructions[] = N_(
+"\n",
+menu_no_f_instructions[] =
 "Legend:  [*] built-in  [ ] excluded  <M> module  < > module capable.\n"
 "Submenus are designated by a trailing \"--->\", empty ones by \"----\".\n"
 "\n"
@@ -147,8 +147,8 @@ menu_no_f_instructions[] = N_(
 "You do not have function keys support.\n"
 "Press <1> instead of <F1>, <2> instead of <F2>, etc.\n"
 "For verbose global help use key <1>.\n"
-"For help related to the current menu entry press <?> or <h>.\n"),
-menu_instructions[] = N_(
+"For help related to the current menu entry press <?> or <h>.\n",
+menu_instructions[] =
 "Legend:  [*] built-in  [ ] excluded  <M> module  < > module capable.\n"
 "Submenus are designated by a trailing \"--->\", empty ones by \"----\".\n"
 "\n"
@@ -163,30 +163,30 @@ menu_instructions[] = N_(
 "\n"
 "Pressing <1> may be used instead of <F1>, <2> instead of <F2>, etc.\n"
 "For verbose global help press <F1>.\n"
-"For help related to the current menu entry press <?> or <h>.\n"),
-radiolist_instructions[] = N_(
+"For help related to the current menu entry press <?> or <h>.\n",
+radiolist_instructions[] =
 "Press <Up>, <Down>, <Home> or <End> to navigate a radiolist, select\n"
 "with <Space>.\n"
 "For help related to the current entry press <?> or <h>.\n"
-"For global help press <F1>.\n"),
-inputbox_instructions_int[] = N_(
+"For global help press <F1>.\n",
+inputbox_instructions_int[] =
 "Please enter a decimal value.\n"
 "Fractions will not be accepted.\n"
-"Press <Enter> to apply, <Esc> to cancel."),
-inputbox_instructions_hex[] = N_(
+"Press <Enter> to apply, <Esc> to cancel.",
+inputbox_instructions_hex[] =
 "Please enter a hexadecimal value.\n"
-"Press <Enter> to apply, <Esc> to cancel."),
-inputbox_instructions_string[] = N_(
+"Press <Enter> to apply, <Esc> to cancel.",
+inputbox_instructions_string[] =
 "Please enter a string value.\n"
-"Press <Enter> to apply, <Esc> to cancel."),
-setmod_text[] = N_(
+"Press <Enter> to apply, <Esc> to cancel.",
+setmod_text[] =
 "This feature depends on another feature which has been configured as a\n"
-"module.  As a result, the current feature will be built as a module too."),
-load_config_text[] = N_(
+"module.  As a result, the current feature will be built as a module too.",
+load_config_text[] =
 "Enter the name of the configuration file you wish to load.\n"
 "Accept the name shown to restore the configuration you last\n"
-"retrieved.  Leave empty to abort."),
-load_config_help[] = N_(
+"retrieved.  Leave empty to abort.",
+load_config_help[] =
 "For various reasons, one may wish to keep several different\n"
 "configurations available on a single machine.\n"
 "\n"
@@ -194,11 +194,11 @@ load_config_help[] = N_(
 "default one, entering its name here will allow you to load and modify\n"
 "that configuration.\n"
 "\n"
-"Leave empty to abort.\n"),
-save_config_text[] = N_(
+"Leave empty to abort.\n",
+save_config_text[] =
 "Enter a filename to which this configuration should be saved\n"
-"as an alternate.  Leave empty to abort."),
-save_config_help[] = N_(
+"as an alternate.  Leave empty to abort.",
+save_config_help[] =
 "For various reasons, one may wish to keep several different\n"
 "configurations available on a single machine.\n"
 "\n"
@@ -206,8 +206,8 @@ save_config_help[] = N_(
 "and use the current configuration as an alternate to whatever\n"
 "configuration options you have selected at that time.\n"
 "\n"
-"Leave empty to abort.\n"),
-search_help[] = N_(
+"Leave empty to abort.\n",
+search_help[] =
 "Search for symbols (configuration variable names CONFIG_*) and display\n"
 "their relations.  Regular expressions are supported.\n"
 "Example:  Search for \"^FOO\".\n"
@@ -244,7 +244,7 @@ search_help[] = N_(
 "USB  => find all symbols containing USB\n"
 "^USB => find all symbols starting with USB\n"
 "USB$ => find all symbols ending with USB\n"
-"\n");
+"\n";
 
 struct mitem {
 	char str[256];
@@ -388,7 +388,7 @@ static void print_function_line(void)
 static void handle_f1(int *key, struct menu *current_item)
 {
 	show_scroll_win(main_window,
-			_("Global help"), _(nconf_global_help));
+			"Global help", nconf_global_help);
 	return;
 }
 
@@ -403,8 +403,8 @@ static void handle_f2(int *key, struct menu *current_item)
 static void handle_f3(int *key, struct menu *current_item)
 {
 	show_scroll_win(main_window,
-			_("Short help"),
-			_(current_instructions));
+			"Short help",
+			current_instructions);
 	return;
 }
 
@@ -412,7 +412,7 @@ static void handle_f3(int *key, struct menu *current_item)
 static void handle_f4(int *key, struct menu *current_item)
 {
 	int res = btn_dialog(main_window,
-			_("Show all symbols?"),
+			"Show all symbols?",
 			2,
 			"   <Show All>   ",
 			"<Don't show all>");
@@ -653,8 +653,8 @@ static int do_exit(void)
 		return 0;
 	}
 	res = btn_dialog(main_window,
-			_("Do you wish to save your new configuration?\n"
-				"<ESC> to cancel and resume nconfig."),
+			"Do you wish to save your new configuration?\n"
+				"<ESC> to cancel and resume nconfig.",
 			2,
 			"   <save>   ",
 			"<don't save>");
@@ -670,15 +670,15 @@ static int do_exit(void)
 		if (res)
 			btn_dialog(
 				main_window,
-				_("Error during writing of configuration.\n"
-				  "Your configuration changes were NOT saved."),
+				"Error during writing of configuration.\n"
+				  "Your configuration changes were NOT saved.",
 				  1,
 				  "<OK>");
 		break;
 	default:
 		btn_dialog(
 			main_window,
-			_("Your configuration changes were NOT saved."),
+			"Your configuration changes were NOT saved.",
 			1,
 			"<OK>");
 		break;
@@ -697,12 +697,12 @@ static void search_conf(void)
 	int dres;
 
 	title = str_new();
-	str_printf( &title, _("Enter (sub)string or regexp to search for "
-			      "(with or without \"%s\")"), CONFIG_);
+	str_printf( &title, "Enter (sub)string or regexp to search for "
+			      "(with or without \"%s\")", CONFIG_);
 
 again:
 	dres = dialog_inputbox(main_window,
-			_("Search Configuration Parameter"),
+			"Search Configuration Parameter",
 			str_get(&title),
 			"", &dialog_input_result, &dialog_input_result_len);
 	switch (dres) {
@@ -710,7 +710,7 @@ again:
 		break;
 	case 1:
 		show_scroll_win(main_window,
-				_("Search Configuration"), search_help);
+				"Search Configuration", search_help);
 		goto again;
 	default:
 		str_free(&title);
@@ -726,7 +726,7 @@ again:
 	res = get_relations_str(sym_arr, NULL);
 	free(sym_arr);
 	show_scroll_win(main_window,
-			_("Search Results"), str_get(&res));
+			"Search Results", str_get(&res));
 	str_free(&res);
 	str_free(&title);
 }
@@ -754,7 +754,7 @@ static void build_conf(struct menu *menu)
 			switch (ptype) {
 			case P_MENU:
 				child_count++;
-				prompt = _(prompt);
+				prompt = prompt;
 				if (single_menu_mode) {
 					item_make(menu, 'm',
 						"%s%*c%s",
@@ -775,7 +775,7 @@ static void build_conf(struct menu *menu)
 					item_make(menu, ':',
 						"   %*c*** %s ***",
 						indent + 1, ' ',
-						_(prompt));
+						prompt);
 				}
 				break;
 			default:
@@ -783,7 +783,7 @@ static void build_conf(struct menu *menu)
 					child_count++;
 					item_make(menu, ':', "---%*c%s",
 						indent + 1, ' ',
-						_(prompt));
+						prompt);
 				}
 			}
 		} else
@@ -829,11 +829,11 @@ static void build_conf(struct menu *menu)
 		}
 
 		item_add_str("%*c%s", indent + 1,
-				' ', _(menu_get_prompt(menu)));
+				' ', menu_get_prompt(menu));
 		if (val == yes) {
 			if (def_menu) {
 				item_add_str(" (%s)",
-					_(menu_get_prompt(def_menu)));
+					menu_get_prompt(def_menu));
 				item_add_str("  --->");
 				if (def_menu->list) {
 					indent += 2;
@@ -847,7 +847,7 @@ static void build_conf(struct menu *menu)
 		if (menu == current_menu) {
 			item_make(menu, ':',
 				"---%*c%s", indent + 1,
-				' ', _(menu_get_prompt(menu)));
+				' ', menu_get_prompt(menu));
 			goto conf_childs;
 		}
 		child_count++;
@@ -894,17 +894,17 @@ static void build_conf(struct menu *menu)
 				if (tmp < 0)
 					tmp = 0;
 				item_add_str("%*c%s%s", tmp, ' ',
-						_(menu_get_prompt(menu)),
+						menu_get_prompt(menu),
 						(sym_has_value(sym) ||
 						 !sym_is_changable(sym)) ? "" :
-						_(" (NEW)"));
+						" (NEW)");
 				goto conf_childs;
 			}
 		}
 		item_add_str("%*c%s%s", indent + 1, ' ',
-				_(menu_get_prompt(menu)),
+				menu_get_prompt(menu),
 				(sym_has_value(sym) || !sym_is_changable(sym)) ?
-				"" : _(" (NEW)"));
+				"" : " (NEW)");
 		if (menu->prompt && menu->prompt->type == P_MENU) {
 			item_add_str("  %s", menu_is_empty(menu) ? "----" : "--->");
 			return;
@@ -1086,8 +1086,8 @@ static void conf(struct menu *menu)
 		if (!child_count)
 			break;
 
-		show_menu(prompt ? _(prompt) : _("Main Menu"),
-				_(menu_instructions),
+		show_menu(prompt ? prompt : "Main Menu",
+				menu_instructions,
 				current_index, &last_top_row);
 		keypad((menu_win(curses_menu)), TRUE);
 		while (!global_exit) {
@@ -1227,13 +1227,13 @@ static void show_help(struct menu *menu)
 
 	help = str_new();
 	menu_get_ext_help(menu, &help);
-	show_scroll_win(main_window, _(menu_get_prompt(menu)), str_get(&help));
+	show_scroll_win(main_window, menu_get_prompt(menu), str_get(&help));
 	str_free(&help);
 }
 
 static void conf_choice(struct menu *menu)
 {
-	const char *prompt = _(menu_get_prompt(menu));
+	const char *prompt = menu_get_prompt(menu);
 	struct menu *child = NULL;
 	struct symbol *active;
 	int selected_index = 0;
@@ -1256,13 +1256,13 @@ static void conf_choice(struct menu *menu)
 
 			if (child->sym == sym_get_choice_value(menu->sym))
 				item_make(child, ':', "<X> %s",
-						_(menu_get_prompt(child)));
+						menu_get_prompt(child));
 			else if (child->sym)
 				item_make(child, ':', "    %s",
-						_(menu_get_prompt(child)));
+						menu_get_prompt(child));
 			else
 				item_make(child, ':', "*** %s ***",
-						_(menu_get_prompt(child)));
+						menu_get_prompt(child));
 
 			if (child->sym == active){
 				last_top_row = top_row(curses_menu);
@@ -1270,8 +1270,8 @@ static void conf_choice(struct menu *menu)
 			}
 			i++;
 		}
-		show_menu(prompt ? _(prompt) : _("Choice Menu"),
-				_(radiolist_instructions),
+		show_menu(prompt ? prompt : "Choice Menu",
+				radiolist_instructions,
 				selected_index,
 				&last_top_row);
 		while (!global_exit) {
@@ -1358,19 +1358,19 @@ static void conf_string(struct menu *menu)
 
 		switch (sym_get_type(menu->sym)) {
 		case S_INT:
-			heading = _(inputbox_instructions_int);
+			heading = inputbox_instructions_int;
 			break;
 		case S_HEX:
-			heading = _(inputbox_instructions_hex);
+			heading = inputbox_instructions_hex;
 			break;
 		case S_STRING:
-			heading = _(inputbox_instructions_string);
+			heading = inputbox_instructions_string;
 			break;
 		default:
-			heading = _("Internal nconf error!");
+			heading = "Internal nconf error!";
 		}
 		res = dialog_inputbox(main_window,
-				prompt ? _(prompt) : _("Main Menu"),
+				prompt ? prompt : "Main Menu",
 				heading,
 				sym_get_string_value(menu->sym),
 				&dialog_input_result,
@@ -1381,7 +1381,7 @@ static void conf_string(struct menu *menu)
 						dialog_input_result))
 				return;
 			btn_dialog(main_window,
-				_("You have made an invalid entry."), 0);
+				"You have made an invalid entry.", 0);
 			break;
 		case 1:
 			show_help(menu);
@@ -1410,11 +1410,11 @@ static void conf_load(void)
 				sym_set_change_count(1);
 				return;
 			}
-			btn_dialog(main_window, _("File does not exist!"), 0);
+			btn_dialog(main_window, "File does not exist!", 0);
 			break;
 		case 1:
 			show_scroll_win(main_window,
-					_("Load Alternate Configuration"),
+					"Load Alternate Configuration",
 					load_config_help);
 			break;
 		case KEY_EXIT:
@@ -1441,13 +1441,13 @@ static void conf_save(void)
 				set_config_filename(dialog_input_result);
 				return;
 			}
-			btn_dialog(main_window, _("Can't create file! "
-				"Probably a nonexistent directory."),
+			btn_dialog(main_window, "Can't create file! "
+				"Probably a nonexistent directory.",
 				1, "<OK>");
 			break;
 		case 1:
 			show_scroll_win(main_window,
-				_("Save Alternate Configuration"),
+				"Save Alternate Configuration",
 				save_config_help);
 			break;
 		case KEY_EXIT:
@@ -1480,10 +1480,6 @@ int main(int ac, char **av)
 	int lines, columns;
 	char *mode;
 
-	setlocale(LC_ALL, "");
-	bindtextdomain(PACKAGE, LOCALEDIR);
-	textdomain(PACKAGE);
-
 	if (ac > 1 && strcmp(av[1], "-s") == 0) {
 		/* Silence conf_read() until the real callback is set up */
 		conf_set_message_callback(NULL);
@@ -1541,8 +1537,8 @@ int main(int ac, char **av)
 	/* check for KEY_FUNC(1) */
 	if (has_key(KEY_F(1)) == FALSE) {
 		show_scroll_win(main_window,
-				_("Instructions"),
-				_(menu_no_f_instructions));
+				"Instructions",
+				menu_no_f_instructions);
 	}
 
 	conf_set_message_callback(conf_message_callback);
diff --git a/scripts/kconfig/nconf.h b/scripts/kconfig/nconf.h
index 9f6f21d3b0d4..2b9e19f603c4 100644
--- a/scripts/kconfig/nconf.h
+++ b/scripts/kconfig/nconf.h
@@ -14,7 +14,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <locale.h>
 #include <ncurses.h>
 #include <menu.h>
 #include <panel.h>
diff --git a/scripts/kconfig/preprocess.c b/scripts/kconfig/preprocess.c
new file mode 100644
index 000000000000..65da87fce907
--- /dev/null
+++ b/scripts/kconfig/preprocess.c
@@ -0,0 +1,572 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2018 Masahiro Yamada <yamada.masahiro@socionext.com>
+
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "list.h"
+
+#define ARRAY_SIZE(arr)		(sizeof(arr) / sizeof((arr)[0]))
+
+static char *expand_string_with_args(const char *in, int argc, char *argv[]);
+
+static void __attribute__((noreturn)) pperror(const char *format, ...)
+{
+	va_list ap;
+
+	fprintf(stderr, "%s:%d: ", current_file->name, yylineno);
+	va_start(ap, format);
+	vfprintf(stderr, format, ap);
+	va_end(ap);
+	fprintf(stderr, "\n");
+
+	exit(1);
+}
+
+/*
+ * Environment variables
+ */
+static LIST_HEAD(env_list);
+
+struct env {
+	char *name;
+	char *value;
+	struct list_head node;
+};
+
+static void env_add(const char *name, const char *value)
+{
+	struct env *e;
+
+	e = xmalloc(sizeof(*e));
+	e->name = xstrdup(name);
+	e->value = xstrdup(value);
+
+	list_add_tail(&e->node, &env_list);
+}
+
+static void env_del(struct env *e)
+{
+	list_del(&e->node);
+	free(e->name);
+	free(e->value);
+	free(e);
+}
+
+/* The returned pointer must be freed when done */
+static char *env_expand(const char *name)
+{
+	struct env *e;
+	const char *value;
+
+	if (!*name)
+		return NULL;
+
+	list_for_each_entry(e, &env_list, node) {
+		if (!strcmp(name, e->name))
+			return xstrdup(e->value);
+	}
+
+	value = getenv(name);
+	if (!value)
+		return NULL;
+
+	/*
+	 * We need to remember all referenced environment variables.
+	 * They will be written out to include/config/auto.conf.cmd
+	 */
+	env_add(name, value);
+
+	return xstrdup(value);
+}
+
+void env_write_dep(FILE *f, const char *autoconfig_name)
+{
+	struct env *e, *tmp;
+
+	list_for_each_entry_safe(e, tmp, &env_list, node) {
+		fprintf(f, "ifneq \"$(%s)\" \"%s\"\n", e->name, e->value);
+		fprintf(f, "%s: FORCE\n", autoconfig_name);
+		fprintf(f, "endif\n");
+		env_del(e);
+	}
+}
+
+/*
+ * Built-in functions
+ */
+struct function {
+	const char *name;
+	unsigned int min_args;
+	unsigned int max_args;
+	char *(*func)(int argc, char *argv[]);
+};
+
+static char *do_error_if(int argc, char *argv[])
+{
+	if (!strcmp(argv[0], "y"))
+		pperror("%s", argv[1]);
+
+	return NULL;
+}
+
+static char *do_filename(int argc, char *argv[])
+{
+	return xstrdup(current_file->name);
+}
+
+static char *do_info(int argc, char *argv[])
+{
+	printf("%s\n", argv[0]);
+
+	return xstrdup("");
+}
+
+static char *do_lineno(int argc, char *argv[])
+{
+	char buf[16];
+
+	sprintf(buf, "%d", yylineno);
+
+	return xstrdup(buf);
+}
+
+static char *do_shell(int argc, char *argv[])
+{
+	FILE *p;
+	char buf[256];
+	char *cmd;
+	size_t nread;
+	int i;
+
+	cmd = argv[0];
+
+	p = popen(cmd, "r");
+	if (!p) {
+		perror(cmd);
+		exit(1);
+	}
+
+	nread = fread(buf, 1, sizeof(buf), p);
+	if (nread == sizeof(buf))
+		nread--;
+
+	/* remove trailing new lines */
+	while (buf[nread - 1] == '\n')
+		nread--;
+
+	buf[nread] = 0;
+
+	/* replace a new line with a space */
+	for (i = 0; i < nread; i++) {
+		if (buf[i] == '\n')
+			buf[i] = ' ';
+	}
+
+	if (pclose(p) == -1) {
+		perror(cmd);
+		exit(1);
+	}
+
+	return xstrdup(buf);
+}
+
+static char *do_warning_if(int argc, char *argv[])
+{
+	if (!strcmp(argv[0], "y"))
+		fprintf(stderr, "%s:%d: %s\n",
+			current_file->name, yylineno, argv[1]);
+
+	return xstrdup("");
+}
+
+static const struct function function_table[] = {
+	/* Name		MIN	MAX	Function */
+	{ "error-if",	2,	2,	do_error_if },
+	{ "filename",	0,	0,	do_filename },
+	{ "info",	1,	1,	do_info },
+	{ "lineno",	0,	0,	do_lineno },
+	{ "shell",	1,	1,	do_shell },
+	{ "warning-if",	2,	2,	do_warning_if },
+};
+
+#define FUNCTION_MAX_ARGS		16
+
+static char *function_expand(const char *name, int argc, char *argv[])
+{
+	const struct function *f;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(function_table); i++) {
+		f = &function_table[i];
+		if (strcmp(f->name, name))
+			continue;
+
+		if (argc < f->min_args)
+			pperror("too few function arguments passed to '%s'",
+				name);
+
+		if (argc > f->max_args)
+			pperror("too many function arguments passed to '%s'",
+				name);
+
+		return f->func(argc, argv);
+	}
+
+	return NULL;
+}
+
+/*
+ * Variables (and user-defined functions)
+ */
+static LIST_HEAD(variable_list);
+
+struct variable {
+	char *name;
+	char *value;
+	enum variable_flavor flavor;
+	int exp_count;
+	struct list_head node;
+};
+
+static struct variable *variable_lookup(const char *name)
+{
+	struct variable *v;
+
+	list_for_each_entry(v, &variable_list, node) {
+		if (!strcmp(name, v->name))
+			return v;
+	}
+
+	return NULL;
+}
+
+static char *variable_expand(const char *name, int argc, char *argv[])
+{
+	struct variable *v;
+	char *res;
+
+	v = variable_lookup(name);
+	if (!v)
+		return NULL;
+
+	if (argc == 0 && v->exp_count)
+		pperror("Recursive variable '%s' references itself (eventually)",
+			name);
+
+	if (v->exp_count > 1000)
+		pperror("Too deep recursive expansion");
+
+	v->exp_count++;
+
+	if (v->flavor == VAR_RECURSIVE)
+		res = expand_string_with_args(v->value, argc, argv);
+	else
+		res = xstrdup(v->value);
+
+	v->exp_count--;
+
+	return res;
+}
+
+void variable_add(const char *name, const char *value,
+		  enum variable_flavor flavor)
+{
+	struct variable *v;
+	char *new_value;
+	bool append = false;
+
+	v = variable_lookup(name);
+	if (v) {
+		/* For defined variables, += inherits the existing flavor */
+		if (flavor == VAR_APPEND) {
+			flavor = v->flavor;
+			append = true;
+		} else {
+			free(v->value);
+		}
+	} else {
+		/* For undefined variables, += assumes the recursive flavor */
+		if (flavor == VAR_APPEND)
+			flavor = VAR_RECURSIVE;
+
+		v = xmalloc(sizeof(*v));
+		v->name = xstrdup(name);
+		v->exp_count = 0;
+		list_add_tail(&v->node, &variable_list);
+	}
+
+	v->flavor = flavor;
+
+	if (flavor == VAR_SIMPLE)
+		new_value = expand_string(value);
+	else
+		new_value = xstrdup(value);
+
+	if (append) {
+		v->value = xrealloc(v->value,
+				    strlen(v->value) + strlen(new_value) + 2);
+		strcat(v->value, " ");
+		strcat(v->value, new_value);
+		free(new_value);
+	} else {
+		v->value = new_value;
+	}
+}
+
+static void variable_del(struct variable *v)
+{
+	list_del(&v->node);
+	free(v->name);
+	free(v->value);
+	free(v);
+}
+
+void variable_all_del(void)
+{
+	struct variable *v, *tmp;
+
+	list_for_each_entry_safe(v, tmp, &variable_list, node)
+		variable_del(v);
+}
+
+/*
+ * Evaluate a clause with arguments.  argc/argv are arguments from the upper
+ * function call.
+ *
+ * Returned string must be freed when done
+ */
+static char *eval_clause(const char *str, size_t len, int argc, char *argv[])
+{
+	char *tmp, *name, *res, *endptr, *prev, *p;
+	int new_argc = 0;
+	char *new_argv[FUNCTION_MAX_ARGS];
+	int nest = 0;
+	int i;
+	unsigned long n;
+
+	tmp = xstrndup(str, len);
+
+	/*
+	 * If variable name is '1', '2', etc.  It is generally an argument
+	 * from a user-function call (i.e. local-scope variable).  If not
+	 * available, then look-up global-scope variables.
+	 */
+	n = strtoul(tmp, &endptr, 10);
+	if (!*endptr && n > 0 && n <= argc) {
+		res = xstrdup(argv[n - 1]);
+		goto free_tmp;
+	}
+
+	prev = p = tmp;
+
+	/*
+	 * Split into tokens
+	 * The function name and arguments are separated by a comma.
+	 * For example, if the function call is like this:
+	 *   $(foo,$(x),$(y))
+	 *
+	 * The input string for this helper should be:
+	 *   foo,$(x),$(y)
+	 *
+	 * and split into:
+	 *   new_argv[0] = 'foo'
+	 *   new_argv[1] = '$(x)'
+	 *   new_argv[2] = '$(y)'
+	 */
+	while (*p) {
+		if (nest == 0 && *p == ',') {
+			*p = 0;
+			if (new_argc >= FUNCTION_MAX_ARGS)
+				pperror("too many function arguments");
+			new_argv[new_argc++] = prev;
+			prev = p + 1;
+		} else if (*p == '(') {
+			nest++;
+		} else if (*p == ')') {
+			nest--;
+		}
+
+		p++;
+	}
+	new_argv[new_argc++] = prev;
+
+	/*
+	 * Shift arguments
+	 * new_argv[0] represents a function name or a variable name.  Put it
+	 * into 'name', then shift the rest of the arguments.  This simplifies
+	 * 'const' handling.
+	 */
+	name = expand_string_with_args(new_argv[0], argc, argv);
+	new_argc--;
+	for (i = 0; i < new_argc; i++)
+		new_argv[i] = expand_string_with_args(new_argv[i + 1],
+						      argc, argv);
+
+	/* Search for variables */
+	res = variable_expand(name, new_argc, new_argv);
+	if (res)
+		goto free;
+
+	/* Look for built-in functions */
+	res = function_expand(name, new_argc, new_argv);
+	if (res)
+		goto free;
+
+	/* Last, try environment variable */
+	if (new_argc == 0) {
+		res = env_expand(name);
+		if (res)
+			goto free;
+	}
+
+	res = xstrdup("");
+free:
+	for (i = 0; i < new_argc; i++)
+		free(new_argv[i]);
+	free(name);
+free_tmp:
+	free(tmp);
+
+	return res;
+}
+
+/*
+ * Expand a string that follows '$'
+ *
+ * For example, if the input string is
+ *     ($(FOO)$($(BAR)))$(BAZ)
+ * this helper evaluates
+ *     $($(FOO)$($(BAR)))
+ * and returns a new string containing the expansion (note that the string is
+ * recursively expanded), also advancing 'str' to point to the next character
+ * after the corresponding closing parenthesis, in this case, *str will be
+ *     $(BAR)
+ */
+static char *expand_dollar_with_args(const char **str, int argc, char *argv[])
+{
+	const char *p = *str;
+	const char *q;
+	int nest = 0;
+
+	/*
+	 * In Kconfig, variable/function references always start with "$(".
+	 * Neither single-letter variables as in $A nor curly braces as in ${CC}
+	 * are supported.  '$' not followed by '(' loses its special meaning.
+	 */
+	if (*p != '(') {
+		*str = p;
+		return xstrdup("$");
+	}
+
+	p++;
+	q = p;
+	while (*q) {
+		if (*q == '(') {
+			nest++;
+		} else if (*q == ')') {
+			if (nest-- == 0)
+				break;
+		}
+		q++;
+	}
+
+	if (!*q)
+		pperror("unterminated reference to '%s': missing ')'", p);
+
+	/* Advance 'str' to after the expanded initial portion of the string */
+	*str = q + 1;
+
+	return eval_clause(p, q - p, argc, argv);
+}
+
+char *expand_dollar(const char **str)
+{
+	return expand_dollar_with_args(str, 0, NULL);
+}
+
+static char *__expand_string(const char **str, bool (*is_end)(char c),
+			     int argc, char *argv[])
+{
+	const char *in, *p;
+	char *expansion, *out;
+	size_t in_len, out_len;
+
+	out = xmalloc(1);
+	*out = 0;
+	out_len = 1;
+
+	p = in = *str;
+
+	while (1) {
+		if (*p == '$') {
+			in_len = p - in;
+			p++;
+			expansion = expand_dollar_with_args(&p, argc, argv);
+			out_len += in_len + strlen(expansion);
+			out = xrealloc(out, out_len);
+			strncat(out, in, in_len);
+			strcat(out, expansion);
+			free(expansion);
+			in = p;
+			continue;
+		}
+
+		if (is_end(*p))
+			break;
+
+		p++;
+	}
+
+	in_len = p - in;
+	out_len += in_len;
+	out = xrealloc(out, out_len);
+	strncat(out, in, in_len);
+
+	/* Advance 'str' to the end character */
+	*str = p;
+
+	return out;
+}
+
+static bool is_end_of_str(char c)
+{
+	return !c;
+}
+
+/*
+ * Expand variables and functions in the given string.  Undefined variables
+ * expand to an empty string.
+ * The returned string must be freed when done.
+ */
+static char *expand_string_with_args(const char *in, int argc, char *argv[])
+{
+	return __expand_string(&in, is_end_of_str, argc, argv);
+}
+
+char *expand_string(const char *in)
+{
+	return expand_string_with_args(in, 0, NULL);
+}
+
+static bool is_end_of_token(char c)
+{
+	/* Why are '.' and '/' valid characters for symbols? */
+	return !(isalnum(c) || c == '_' || c == '-' || c == '.' || c == '/');
+}
+
+/*
+ * Expand variables in a token.  The parsing stops when a token separater
+ * (in most cases, it is a whitespace) is encountered.  'str' is updated to
+ * point to the next character.
+ *
+ * The returned string must be freed when done.
+ */
+char *expand_one_token(const char **str)
+{
+	return __expand_string(str, is_end_of_token, 0, NULL);
+}
diff --git a/scripts/kconfig/qconf-cfg.sh b/scripts/kconfig/qconf-cfg.sh
new file mode 100755
index 000000000000..0862e1562536
--- /dev/null
+++ b/scripts/kconfig/qconf-cfg.sh
@@ -0,0 +1,25 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+PKG="Qt5Core Qt5Gui Qt5Widgets"
+PKG2="QtCore QtGui"
+
+if pkg-config --exists $PKG; then
+	echo cflags=\"-std=c++11 -fPIC $(pkg-config --cflags Qt5Core Qt5Gui Qt5Widgets)\"
+	echo libs=\"$(pkg-config --libs $PKG)\"
+	echo moc=\"$(pkg-config --variable=host_bins Qt5Core)/moc\"
+	exit 0
+fi
+
+if pkg-config --exists $PKG2; then
+	echo cflags=\"$(pkg-config --cflags $PKG2)\"
+	echo libs=\"$(pkg-config --libs $PKG2)\"
+	echo moc=\"$(pkg-config --variable=moc_location QtCore)\"
+	exit 0
+fi
+
+echo >&2 "*"
+echo >&2 "* Could not find Qt via pkg-config."
+echo >&2 "* Please install either Qt 4.8 or 5.x. and make sure it's in PKG_CONFIG_PATH"
+echo >&2 "*"
+exit 1
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index ae6c72546411..ad9c22dd04f5 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -34,10 +34,6 @@
 #include "qconf.moc"
 #include "images.c"
 
-#ifdef _
-# undef _
-# define _ qgettext
-#endif
 
 static QApplication *configApp;
 static ConfigSettings *configSettings;
@@ -46,12 +42,7 @@ QAction *ConfigMainWindow::saveAction;
 
 static inline QString qgettext(const char* str)
 {
-	return QString::fromLocal8Bit(gettext(str));
-}
-
-static inline QString qgettext(const QString& str)
-{
-	return QString::fromLocal8Bit(gettext(str.toLatin1()));
+	return QString::fromLocal8Bit(str);
 }
 
 ConfigSettings::ConfigSettings()
@@ -127,7 +118,7 @@ void ConfigItem::updateMenu(void)
 
 	sym = menu->sym;
 	prop = menu->prompt;
-	prompt = _(menu_get_prompt(menu));
+	prompt = qgettext(menu_get_prompt(menu));
 
 	if (prop) switch (prop->type) {
 	case P_MENU:
@@ -216,7 +207,7 @@ void ConfigItem::updateMenu(void)
 		break;
 	}
 	if (!sym_has_value(sym) && visible)
-		prompt += _(" (NEW)");
+		prompt += " (NEW)";
 set_prompt:
 	setText(promptColIdx, prompt);
 }
@@ -327,7 +318,7 @@ ConfigList::ConfigList(ConfigView* p, const char *name)
 	setVerticalScrollMode(ScrollPerPixel);
 	setHorizontalScrollMode(ScrollPerPixel);
 
-	setHeaderLabels(QStringList() << _("Option") << _("Name") << "N" << "M" << "Y" << _("Value"));
+	setHeaderLabels(QStringList() << "Option" << "Name" << "N" << "M" << "Y" << "Value");
 
 	connect(this, SIGNAL(itemSelectionChanged(void)),
 		SLOT(updateSelection(void)));
@@ -883,7 +874,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e)
 			QAction *action;
 
 			headerPopup = new QMenu(this);
-			action = new QAction(_("Show Name"), this);
+			action = new QAction("Show Name", this);
 			  action->setCheckable(true);
 			  connect(action, SIGNAL(toggled(bool)),
 				  parent(), SLOT(setShowName(bool)));
@@ -891,7 +882,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e)
 				  action, SLOT(setOn(bool)));
 			  action->setChecked(showName);
 			  headerPopup->addAction(action);
-			action = new QAction(_("Show Range"), this);
+			action = new QAction("Show Range", this);
 			  action->setCheckable(true);
 			  connect(action, SIGNAL(toggled(bool)),
 				  parent(), SLOT(setShowRange(bool)));
@@ -899,7 +890,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e)
 				  action, SLOT(setOn(bool)));
 			  action->setChecked(showRange);
 			  headerPopup->addAction(action);
-			action = new QAction(_("Show Data"), this);
+			action = new QAction("Show Data", this);
 			  action->setCheckable(true);
 			  connect(action, SIGNAL(toggled(bool)),
 				  parent(), SLOT(setShowData(bool)));
@@ -1086,7 +1077,7 @@ void ConfigInfoView::menuInfo(void)
 	if (sym) {
 		if (_menu->prompt) {
 			head += "<big><b>";
-			head += print_filter(_(_menu->prompt->text));
+			head += print_filter(_menu->prompt->text);
 			head += "</b></big>";
 			if (sym->name) {
 				head += " (";
@@ -1117,7 +1108,7 @@ void ConfigInfoView::menuInfo(void)
 		str_free(&help_gstr);
 	} else if (_menu->prompt) {
 		head += "<big><b>";
-		head += print_filter(_(_menu->prompt->text));
+		head += print_filter(_menu->prompt->text);
 		head += "</b></big><br><br>";
 		if (showDebug()) {
 			if (_menu->prompt->visible.expr) {
@@ -1152,7 +1143,7 @@ QString ConfigInfoView::debug_info(struct symbol *sym)
 		case P_PROMPT:
 		case P_MENU:
 			debug += QString().sprintf("prompt: <a href=\"m%p\">", prop->menu);
-			debug += print_filter(_(prop->text));
+			debug += print_filter(prop->text);
 			debug += "</a><br>";
 			break;
 		case P_DEFAULT:
@@ -1234,7 +1225,7 @@ void ConfigInfoView::expr_print_help(void *data, struct symbol *sym, const char
 QMenu* ConfigInfoView::createStandardContextMenu(const QPoint & pos)
 {
 	QMenu* popup = Parent::createStandardContextMenu(pos);
-	QAction* action = new QAction(_("Show Debug Info"), popup);
+	QAction* action = new QAction("Show Debug Info", popup);
 	  action->setCheckable(true);
 	  connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool)));
 	  connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool)));
@@ -1261,11 +1252,11 @@ ConfigSearchWindow::ConfigSearchWindow(ConfigMainWindow* parent, const char *nam
 	QHBoxLayout* layout2 = new QHBoxLayout(0);
 	layout2->setContentsMargins(0, 0, 0, 0);
 	layout2->setSpacing(6);
-	layout2->addWidget(new QLabel(_("Find:"), this));
+	layout2->addWidget(new QLabel("Find:", this));
 	editField = new QLineEdit(this);
 	connect(editField, SIGNAL(returnPressed()), SLOT(search()));
 	layout2->addWidget(editField);
-	searchButton = new QPushButton(_("Search"), this);
+	searchButton = new QPushButton("Search", this);
 	searchButton->setAutoDefault(false);
 	connect(searchButton, SIGNAL(clicked()), SLOT(search()));
 	layout2->addWidget(searchButton);
@@ -1387,44 +1378,44 @@ ConfigMainWindow::ConfigMainWindow(void)
 	toolBar = new QToolBar("Tools", this);
 	addToolBar(toolBar);
 
-	backAction = new QAction(QPixmap(xpm_back), _("Back"), this);
+	backAction = new QAction(QPixmap(xpm_back), "Back", this);
 	  connect(backAction, SIGNAL(triggered(bool)), SLOT(goBack()));
 	  backAction->setEnabled(false);
-	QAction *quitAction = new QAction(_("&Quit"), this);
+	QAction *quitAction = new QAction("&Quit", this);
 	quitAction->setShortcut(Qt::CTRL + Qt::Key_Q);
 	  connect(quitAction, SIGNAL(triggered(bool)), SLOT(close()));
-	QAction *loadAction = new QAction(QPixmap(xpm_load), _("&Load"), this);
+	QAction *loadAction = new QAction(QPixmap(xpm_load), "&Load", this);
 	loadAction->setShortcut(Qt::CTRL + Qt::Key_L);
 	  connect(loadAction, SIGNAL(triggered(bool)), SLOT(loadConfig()));
-	saveAction = new QAction(QPixmap(xpm_save), _("&Save"), this);
+	saveAction = new QAction(QPixmap(xpm_save), "&Save", this);
 	saveAction->setShortcut(Qt::CTRL + Qt::Key_S);
 	  connect(saveAction, SIGNAL(triggered(bool)), SLOT(saveConfig()));
 	conf_set_changed_callback(conf_changed);
 	// Set saveAction's initial state
 	conf_changed();
-	QAction *saveAsAction = new QAction(_("Save &As..."), this);
+	QAction *saveAsAction = new QAction("Save &As...", this);
 	  connect(saveAsAction, SIGNAL(triggered(bool)), SLOT(saveConfigAs()));
-	QAction *searchAction = new QAction(_("&Find"), this);
+	QAction *searchAction = new QAction("&Find", this);
 	searchAction->setShortcut(Qt::CTRL + Qt::Key_F);
 	  connect(searchAction, SIGNAL(triggered(bool)), SLOT(searchConfig()));
-	singleViewAction = new QAction(QPixmap(xpm_single_view), _("Single View"), this);
+	singleViewAction = new QAction(QPixmap(xpm_single_view), "Single View", this);
 	singleViewAction->setCheckable(true);
 	  connect(singleViewAction, SIGNAL(triggered(bool)), SLOT(showSingleView()));
-	splitViewAction = new QAction(QPixmap(xpm_split_view), _("Split View"), this);
+	splitViewAction = new QAction(QPixmap(xpm_split_view), "Split View", this);
 	splitViewAction->setCheckable(true);
 	  connect(splitViewAction, SIGNAL(triggered(bool)), SLOT(showSplitView()));
-	fullViewAction = new QAction(QPixmap(xpm_tree_view), _("Full View"), this);
+	fullViewAction = new QAction(QPixmap(xpm_tree_view), "Full View", this);
 	fullViewAction->setCheckable(true);
 	  connect(fullViewAction, SIGNAL(triggered(bool)), SLOT(showFullView()));
 
-	QAction *showNameAction = new QAction(_("Show Name"), this);
+	QAction *showNameAction = new QAction("Show Name", this);
 	  showNameAction->setCheckable(true);
 	  connect(showNameAction, SIGNAL(toggled(bool)), configView, SLOT(setShowName(bool)));
 	  showNameAction->setChecked(configView->showName());
-	QAction *showRangeAction = new QAction(_("Show Range"), this);
+	QAction *showRangeAction = new QAction("Show Range", this);
 	  showRangeAction->setCheckable(true);
 	  connect(showRangeAction, SIGNAL(toggled(bool)), configView, SLOT(setShowRange(bool)));
-	QAction *showDataAction = new QAction(_("Show Data"), this);
+	QAction *showDataAction = new QAction("Show Data", this);
 	  showDataAction->setCheckable(true);
 	  connect(showDataAction, SIGNAL(toggled(bool)), configView, SLOT(setShowData(bool)));
 
@@ -1435,21 +1426,21 @@ ConfigMainWindow::ConfigMainWindow(void)
 	connect(optGroup, SIGNAL(triggered(QAction *)), menuView,
 		SLOT(setOptionMode(QAction *)));
 
-	configView->showNormalAction = new QAction(_("Show Normal Options"), optGroup);
-	configView->showAllAction = new QAction(_("Show All Options"), optGroup);
-	configView->showPromptAction = new QAction(_("Show Prompt Options"), optGroup);
+	configView->showNormalAction = new QAction("Show Normal Options", optGroup);
+	configView->showAllAction = new QAction("Show All Options", optGroup);
+	configView->showPromptAction = new QAction("Show Prompt Options", optGroup);
 	configView->showNormalAction->setCheckable(true);
 	configView->showAllAction->setCheckable(true);
 	configView->showPromptAction->setCheckable(true);
 
-	QAction *showDebugAction = new QAction( _("Show Debug Info"), this);
+	QAction *showDebugAction = new QAction("Show Debug Info", this);
 	  showDebugAction->setCheckable(true);
 	  connect(showDebugAction, SIGNAL(toggled(bool)), helpText, SLOT(setShowDebug(bool)));
 	  showDebugAction->setChecked(helpText->showDebug());
 
-	QAction *showIntroAction = new QAction( _("Introduction"), this);
+	QAction *showIntroAction = new QAction("Introduction", this);
 	  connect(showIntroAction, SIGNAL(triggered(bool)), SLOT(showIntro()));
-	QAction *showAboutAction = new QAction( _("About"), this);
+	QAction *showAboutAction = new QAction("About", this);
 	  connect(showAboutAction, SIGNAL(triggered(bool)), SLOT(showAbout()));
 
 	// init tool bar
@@ -1463,7 +1454,7 @@ ConfigMainWindow::ConfigMainWindow(void)
 	toolBar->addAction(fullViewAction);
 
 	// create config menu
-	QMenu* config = menu->addMenu(_("&File"));
+	QMenu* config = menu->addMenu("&File");
 	config->addAction(loadAction);
 	config->addAction(saveAction);
 	config->addAction(saveAsAction);
@@ -1471,11 +1462,11 @@ ConfigMainWindow::ConfigMainWindow(void)
 	config->addAction(quitAction);
 
 	// create edit menu
-	QMenu* editMenu = menu->addMenu(_("&Edit"));
+	QMenu* editMenu = menu->addMenu("&Edit");
 	editMenu->addAction(searchAction);
 
 	// create options menu
-	QMenu* optionMenu = menu->addMenu(_("&Option"));
+	QMenu* optionMenu = menu->addMenu("&Option");
 	optionMenu->addAction(showNameAction);
 	optionMenu->addAction(showRangeAction);
 	optionMenu->addAction(showDataAction);
@@ -1486,7 +1477,7 @@ ConfigMainWindow::ConfigMainWindow(void)
 
 	// create help menu
 	menu->addSeparator();
-	QMenu* helpMenu = menu->addMenu(_("&Help"));
+	QMenu* helpMenu = menu->addMenu("&Help");
 	helpMenu->addAction(showIntroAction);
 	helpMenu->addAction(showAboutAction);
 
@@ -1534,14 +1525,14 @@ void ConfigMainWindow::loadConfig(void)
 	if (s.isNull())
 		return;
 	if (conf_read(QFile::encodeName(s)))
-		QMessageBox::information(this, "qconf", _("Unable to load configuration!"));
+		QMessageBox::information(this, "qconf", "Unable to load configuration!");
 	ConfigView::updateListAll();
 }
 
 bool ConfigMainWindow::saveConfig(void)
 {
 	if (conf_write(NULL)) {
-		QMessageBox::information(this, "qconf", _("Unable to save configuration!"));
+		QMessageBox::information(this, "qconf", "Unable to save configuration!");
 		return false;
 	}
 	return true;
@@ -1723,11 +1714,11 @@ void ConfigMainWindow::closeEvent(QCloseEvent* e)
 		e->accept();
 		return;
 	}
-	QMessageBox mb("qconf", _("Save configuration?"), QMessageBox::Warning,
+	QMessageBox mb("qconf", "Save configuration?", QMessageBox::Warning,
 			QMessageBox::Yes | QMessageBox::Default, QMessageBox::No, QMessageBox::Cancel | QMessageBox::Escape);
-	mb.setButtonText(QMessageBox::Yes, _("&Save Changes"));
-	mb.setButtonText(QMessageBox::No, _("&Discard Changes"));
-	mb.setButtonText(QMessageBox::Cancel, _("Cancel Exit"));
+	mb.setButtonText(QMessageBox::Yes, "&Save Changes");
+	mb.setButtonText(QMessageBox::No, "&Discard Changes");
+	mb.setButtonText(QMessageBox::Cancel, "Cancel Exit");
 	switch (mb.exec()) {
 	case QMessageBox::Yes:
 		if (saveConfig())
@@ -1746,7 +1737,7 @@ void ConfigMainWindow::closeEvent(QCloseEvent* e)
 
 void ConfigMainWindow::showIntro(void)
 {
-	static const QString str = _("Welcome to the qconf graphical configuration tool.\n\n"
+	static const QString str = "Welcome to the qconf graphical configuration tool.\n\n"
 		"For each option, a blank box indicates the feature is disabled, a check\n"
 		"indicates it is enabled, and a dot indicates that it is to be compiled\n"
 		"as a module.  Clicking on the box will cycle through the three states.\n\n"
@@ -1756,16 +1747,16 @@ void ConfigMainWindow::showIntro(void)
 		"options must be enabled to support the option you are interested in, you can\n"
 		"still view the help of a grayed-out option.\n\n"
 		"Toggling Show Debug Info under the Options menu will show the dependencies,\n"
-		"which you can then match by examining other options.\n\n");
+		"which you can then match by examining other options.\n\n";
 
 	QMessageBox::information(this, "qconf", str);
 }
 
 void ConfigMainWindow::showAbout(void)
 {
-	static const QString str = _("qconf is Copyright (C) 2002 Roman Zippel <zippel@linux-m68k.org>.\n"
+	static const QString str = "qconf is Copyright (C) 2002 Roman Zippel <zippel@linux-m68k.org>.\n"
 		"Copyright (C) 2015 Boris Barbulovski <bbarbulovski@gmail.com>.\n\n"
-		"Bug reports and feature request can also be entered at http://bugzilla.kernel.org/\n");
+		"Bug reports and feature request can also be entered at http://bugzilla.kernel.org/\n";
 
 	QMessageBox::information(this, "qconf", str);
 }
@@ -1826,7 +1817,7 @@ static const char *progname;
 
 static void usage(void)
 {
-	printf(_("%s [-s] <config>\n").toLatin1().constData(), progname);
+	printf("%s [-s] <config>\n", progname);
 	exit(0);
 }
 
@@ -1835,9 +1826,6 @@ int main(int ac, char** av)
 	ConfigMainWindow* v;
 	const char *name;
 
-	bindtextdomain(PACKAGE, LOCALEDIR);
-	textdomain(PACKAGE);
-
 	progname = av[0];
 	configApp = new QApplication(ac, av);
 	if (ac > 1 && av[1][0] == '-') {
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index f0b2e3b3102d..7c9a88e91cfa 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -33,33 +33,6 @@ struct symbol *sym_defconfig_list;
 struct symbol *modules_sym;
 tristate modules_val;
 
-struct expr *sym_env_list;
-
-static void sym_add_default(struct symbol *sym, const char *def)
-{
-	struct property *prop = prop_alloc(P_DEFAULT, sym);
-
-	prop->expr = expr_alloc_symbol(sym_lookup(def, SYMBOL_CONST));
-}
-
-void sym_init(void)
-{
-	struct symbol *sym;
-	struct utsname uts;
-	static bool inited = false;
-
-	if (inited)
-		return;
-	inited = true;
-
-	uname(&uts);
-
-	sym = sym_lookup("UNAME_RELEASE", 0);
-	sym->type = S_STRING;
-	sym->flags |= SYMBOL_AUTO;
-	sym_add_default(sym, uts.release);
-}
-
 enum symbol_type sym_get_type(struct symbol *sym)
 {
 	enum symbol_type type = sym->type;
@@ -906,59 +879,6 @@ struct symbol *sym_find(const char *name)
 	return symbol;
 }
 
-/*
- * Expand symbol's names embedded in the string given in argument. Symbols'
- * name to be expanded shall be prefixed by a '$'. Unknown symbol expands to
- * the empty string.
- */
-char *sym_expand_string_value(const char *in)
-{
-	const char *src;
-	char *res;
-	size_t reslen;
-
-	/*
-	 * Note: 'in' might come from a token that's about to be
-	 * freed, so make sure to always allocate a new string
-	 */
-	reslen = strlen(in) + 1;
-	res = xmalloc(reslen);
-	res[0] = '\0';
-
-	while ((src = strchr(in, '$'))) {
-		char *p, name[SYMBOL_MAXLENGTH];
-		const char *symval = "";
-		struct symbol *sym;
-		size_t newlen;
-
-		strncat(res, in, src - in);
-		src++;
-
-		p = name;
-		while (isalnum(*src) || *src == '_')
-			*p++ = *src++;
-		*p = '\0';
-
-		sym = sym_find(name);
-		if (sym != NULL) {
-			sym_calc_value(sym);
-			symval = sym_get_string_value(sym);
-		}
-
-		newlen = strlen(res) + strlen(symval) + strlen(src) + 1;
-		if (newlen > reslen) {
-			reslen = newlen;
-			res = xrealloc(res, reslen);
-		}
-
-		strcat(res, symval);
-		in = src;
-	}
-	strcat(res, in);
-
-	return res;
-}
-
 const char *sym_escape_string_value(const char *in)
 {
 	const char *p;
@@ -1401,32 +1321,3 @@ const char *prop_get_type_name(enum prop_type type)
 	}
 	return "unknown";
 }
-
-static void prop_add_env(const char *env)
-{
-	struct symbol *sym, *sym2;
-	struct property *prop;
-	char *p;
-
-	sym = current_entry->sym;
-	sym->flags |= SYMBOL_AUTO;
-	for_all_properties(sym, prop, P_ENV) {
-		sym2 = prop_get_symbol(prop);
-		if (strcmp(sym2->name, env))
-			menu_warn(current_entry, "redefining environment symbol from %s",
-				  sym2->name);
-		return;
-	}
-
-	prop = prop_alloc(P_ENV, sym);
-	prop->expr = expr_alloc_symbol(sym_lookup(env, SYMBOL_CONST));
-
-	sym_env_list = expr_alloc_one(E_LIST, sym_env_list);
-	sym_env_list->right.sym = sym;
-
-	p = getenv(env);
-	if (p)
-		sym_add_default(sym, p);
-	else
-		menu_warn(current_entry, "environment variable %s undefined", env);
-}
diff --git a/scripts/kconfig/tests/no_write_if_dep_unmet/expected_config b/scripts/kconfig/tests/no_write_if_dep_unmet/expected_config
index 0d15e41da475..473228810c35 100644
--- a/scripts/kconfig/tests/no_write_if_dep_unmet/expected_config
+++ b/scripts/kconfig/tests/no_write_if_dep_unmet/expected_config
@@ -1,5 +1,5 @@
 #
 # Automatically generated file; DO NOT EDIT.
-# Linux Kernel Configuration
+# Main menu
 #
 # CONFIG_A is not set
diff --git a/scripts/kconfig/tests/preprocess/builtin_func/Kconfig b/scripts/kconfig/tests/preprocess/builtin_func/Kconfig
new file mode 100644
index 000000000000..baa328827911
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/builtin_func/Kconfig
@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# 'info' prints the argument to stdout.
+$(info,hello world 0)
+
+# 'warning-if', if the first argument is y, sends the second argument to stderr,
+# and the message is prefixed with the current file name and line number.
+$(warning-if,y,hello world 1)
+
+# 'error-if' is similar, but it terminates the parsing immediately.
+# The following is just no-op since the first argument is not y.
+$(error-if,n,this should not be printed)
+
+# Shorthand
+warning = $(warning-if,y,$(1))
+
+# 'shell' executes a command, and returns its stdout.
+$(warning,$(shell,echo hello world 3))
+
+# Every newline in the output is replaced with a space,
+# but any trailing newlines are deleted.
+$(warning,$(shell,printf 'hello\nworld\n\n4\n\n\n'))
+
+# 'filename' is expanded to the currently parsed file name,
+# 'lineno' to the line number.
+$(warning,filename=$(filename))
+$(warning,lineno=$(lineno))
diff --git a/scripts/kconfig/tests/preprocess/builtin_func/__init__.py b/scripts/kconfig/tests/preprocess/builtin_func/__init__.py
new file mode 100644
index 000000000000..2e53ba08fca1
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/builtin_func/__init__.py
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+"""
+Built-in function tests.
+"""
+
+def test(conf):
+    assert conf.oldaskconfig() == 0
+    assert conf.stdout_contains('expected_stdout')
+    assert conf.stderr_matches('expected_stderr')
diff --git a/scripts/kconfig/tests/preprocess/builtin_func/expected_stderr b/scripts/kconfig/tests/preprocess/builtin_func/expected_stderr
new file mode 100644
index 000000000000..33ea9ca38400
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/builtin_func/expected_stderr
@@ -0,0 +1,5 @@
+Kconfig:8: hello world 1
+Kconfig:18: hello world 3
+Kconfig:22: hello world  4
+Kconfig:26: filename=Kconfig
+Kconfig:27: lineno=27
diff --git a/scripts/kconfig/tests/preprocess/builtin_func/expected_stdout b/scripts/kconfig/tests/preprocess/builtin_func/expected_stdout
new file mode 100644
index 000000000000..82de3a7e97de
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/builtin_func/expected_stdout
@@ -0,0 +1 @@
+hello world 0
diff --git a/scripts/kconfig/tests/preprocess/circular_expansion/Kconfig b/scripts/kconfig/tests/preprocess/circular_expansion/Kconfig
new file mode 100644
index 000000000000..6838997c23ba
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/circular_expansion/Kconfig
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+X = $(Y)
+Y = $(X)
+$(info $(X))
diff --git a/scripts/kconfig/tests/preprocess/circular_expansion/__init__.py b/scripts/kconfig/tests/preprocess/circular_expansion/__init__.py
new file mode 100644
index 000000000000..419bda3e075c
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/circular_expansion/__init__.py
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+"""
+Detect circular variable expansion.
+
+If a recursively expanded variable references itself (eventually),
+it should fail with an error message.
+"""
+
+def test(conf):
+    assert conf.oldaskconfig() != 0
+    assert conf.stderr_matches('expected_stderr')
diff --git a/scripts/kconfig/tests/preprocess/circular_expansion/expected_stderr b/scripts/kconfig/tests/preprocess/circular_expansion/expected_stderr
new file mode 100644
index 000000000000..cde68fa989d0
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/circular_expansion/expected_stderr
@@ -0,0 +1 @@
+Kconfig:5: Recursive variable 'X' references itself (eventually)
diff --git a/scripts/kconfig/tests/preprocess/escape/Kconfig b/scripts/kconfig/tests/preprocess/escape/Kconfig
new file mode 100644
index 000000000000..4e3f44445544
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/escape/Kconfig
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Shorthand
+warning = $(warning-if,y,$(1))
+
+# You can not pass commas directly to a function since they are treated as
+# delimiters. You can use the following trick to do so.
+comma   := ,
+$(warning,hello$(comma) world)
+
+# Like Make, single quotes, double quotes, spaces are treated verbatim.
+# The following prints the text as-is.
+$(warning,  ' " '"   ' ''' "'")
+
+# Unlike Make, '$' has special meaning only when it is followed by '('.
+# No need to escape '$' itself.
+$(warning,$)
+$(warning,$$)
+$ := 1
+$(warning,$($))
+
+# You need a trick to escape '$' followed by '('
+# The following should print "$(X)". It should not be expanded further.
+dollar := $
+$(warning,$(dollar)(X))
+
+# You need a trick to treat unbalanced parentheses.
+# The following should print "(".
+left_paren := (
+$(warning,$(left_paren))
+
+# A simple expanded should not be expanded multiple times.
+# The following should print "$(X)". It should not be expanded further.
+Y := $(dollar)(X)
+$(warning,$(Y))
+
+# The following should print "$(X)" as well.
+Y = $(dollar)(X)
+$(warning,$(Y))
+
+# The following should print "$(".
+# It should not be emit "unterminated reference" error.
+unterminated := $(dollar)(
+$(warning,$(unterminated))
diff --git a/scripts/kconfig/tests/preprocess/escape/__init__.py b/scripts/kconfig/tests/preprocess/escape/__init__.py
new file mode 100644
index 000000000000..7ee8e747f546
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/escape/__init__.py
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+"""
+Escape sequence tests.
+"""
+
+def test(conf):
+    assert conf.oldaskconfig() == 0
+    assert conf.stderr_matches('expected_stderr')
diff --git a/scripts/kconfig/tests/preprocess/escape/expected_stderr b/scripts/kconfig/tests/preprocess/escape/expected_stderr
new file mode 100644
index 000000000000..1c00957ddaa9
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/escape/expected_stderr
@@ -0,0 +1,10 @@
+Kconfig:9: hello, world
+Kconfig:13:   ' " '"   ' ''' "'"
+Kconfig:17: $
+Kconfig:18: $$
+Kconfig:20: 1
+Kconfig:25: $(X)
+Kconfig:30: (
+Kconfig:35: $(X)
+Kconfig:39: $(X)
+Kconfig:44: $(
diff --git a/scripts/kconfig/tests/preprocess/variable/Kconfig b/scripts/kconfig/tests/preprocess/variable/Kconfig
new file mode 100644
index 000000000000..9ce2f95cbd24
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/variable/Kconfig
@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Shorthand
+warning = $(warning-if,y,$(1))
+
+# Simply expanded variable.
+X := 1
+SIMPLE := $(X)
+X := 2
+$(warning,SIMPLE = $(SIMPLE))
+
+# Recursively expanded variable.
+X := 1
+RECURSIVE = $(X)
+X := 2
+$(warning,RECURSIVE = $(RECURSIVE))
+
+# Append something to a simply expanded variable.
+Y := 3
+SIMPLE += $(Y)
+Y := 4
+$(warning,SIMPLE = $(SIMPLE))
+
+# Append something to a recursively expanded variable.
+Y := 3
+RECURSIVE += $(Y)
+Y := 4
+$(warning,RECURSIVE = $(RECURSIVE))
+
+# Use += operator to an undefined variable.
+# This works as a recursively expanded variable.
+Y := 3
+UNDEFINED_VARIABLE += $(Y)
+Y := 4
+$(warning,UNDEFINED_VARIABLE = $(UNDEFINED_VARIABLE))
+
+# You can use variable references for the lefthand side of assignment statement.
+X := A
+Y := B
+$(X)$(Y) := 5
+$(warning,AB = $(AB))
+
+# User-defined function.
+greeting = $(1), my name is $(2).
+$(warning,$(greeting,Hello,John))
+
+# The number of arguments is not checked for user-defined functions.
+# If some arguments are optional, it is useful to pass fewer parameters.
+# $(2) will be blank in this case.
+$(warning,$(greeting,Hello))
+
+# Unreferenced parameters are just ignored.
+$(warning,$(greeting,Hello,John,ignored,ignored))
diff --git a/scripts/kconfig/tests/preprocess/variable/__init__.py b/scripts/kconfig/tests/preprocess/variable/__init__.py
new file mode 100644
index 000000000000..e88b1708d6d4
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/variable/__init__.py
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+"""
+Variable and user-defined function tests.
+"""
+
+def test(conf):
+    assert conf.oldaskconfig() == 0
+    assert conf.stderr_matches('expected_stderr')
diff --git a/scripts/kconfig/tests/preprocess/variable/expected_stderr b/scripts/kconfig/tests/preprocess/variable/expected_stderr
new file mode 100644
index 000000000000..a4841c3fdff5
--- /dev/null
+++ b/scripts/kconfig/tests/preprocess/variable/expected_stderr
@@ -0,0 +1,9 @@
+Kconfig:10: SIMPLE = 1
+Kconfig:16: RECURSIVE = 2
+Kconfig:22: SIMPLE = 1 3
+Kconfig:28: RECURSIVE = 2 4
+Kconfig:35: UNDEFINED_VARIABLE = 4
+Kconfig:41: AB = 5
+Kconfig:45: Hello, my name is John.
+Kconfig:50: Hello, my name is .
+Kconfig:53: Hello, my name is John.
diff --git a/scripts/kconfig/util.c b/scripts/kconfig/util.c
index c6f6e21b809f..a365594770d9 100644
--- a/scripts/kconfig/util.c
+++ b/scripts/kconfig/util.c
@@ -14,18 +14,16 @@
 struct file *file_lookup(const char *name)
 {
 	struct file *file;
-	char *file_name = sym_expand_string_value(name);
 
 	for (file = file_list; file; file = file->next) {
 		if (!strcmp(name, file->name)) {
-			free(file_name);
 			return file;
 		}
 	}
 
 	file = xmalloc(sizeof(*file));
 	memset(file, 0, sizeof(*file));
-	file->name = file_name;
+	file->name = xstrdup(name);
 	file->next = file_list;
 	file_list = file;
 	return file;
@@ -34,8 +32,6 @@ struct file *file_lookup(const char *name)
 /* write a dependency file as used by kbuild to track dependencies */
 int file_write_dep(const char *name)
 {
-	struct symbol *sym, *env_sym;
-	struct expr *e;
 	struct file *file;
 	FILE *out;
 
@@ -54,21 +50,7 @@ int file_write_dep(const char *name)
 	fprintf(out, "\n%s: \\\n"
 		     "\t$(deps_config)\n\n", conf_get_autoconfig_name());
 
-	expr_list_for_each_sym(sym_env_list, e, sym) {
-		struct property *prop;
-		const char *value;
-
-		prop = sym_get_env_prop(sym);
-		env_sym = prop_get_symbol(prop);
-		if (!env_sym)
-			continue;
-		value = getenv(env_sym->name);
-		if (!value)
-			value = "";
-		fprintf(out, "ifneq \"$(%s)\" \"%s\"\n", env_sym->name, value);
-		fprintf(out, "%s: FORCE\n", conf_get_autoconfig_name());
-		fprintf(out, "endif\n");
-	}
+	env_write_dep(out, conf_get_autoconfig_name());
 
 	fprintf(out, "\n$(deps_config): ;\n");
 	fclose(out);
@@ -165,3 +147,14 @@ char *xstrdup(const char *s)
 	fprintf(stderr, "Out of memory.\n");
 	exit(1);
 }
+
+char *xstrndup(const char *s, size_t n)
+{
+	char *p;
+
+	p = strndup(s, n);
+	if (p)
+		return p;
+	fprintf(stderr, "Out of memory.\n");
+	exit(1);
+}
diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l
index 045093d827e1..25bd2b89fe3f 100644
--- a/scripts/kconfig/zconf.l
+++ b/scripts/kconfig/zconf.l
@@ -1,13 +1,13 @@
 %option nostdinit noyywrap never-interactive full ecs
 %option 8bit nodefault yylineno
-%option noinput
-%x COMMAND HELP STRING PARAM
+%x COMMAND HELP STRING PARAM ASSIGN_VAL
 %{
 /*
  * Copyright (C) 2002 Roman Zippel <zippel@linux-m68k.org>
  * Released under the terms of the GNU GPL v2.0.
  */
 
+#include <assert.h>
 #include <limits.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -35,6 +35,8 @@ struct buffer *current_buf;
 
 static int last_ts, first_ts;
 
+static char *expand_token(const char *in, size_t n);
+static void append_expanded_string(const char *in);
 static void zconf_endhelp(void);
 static void zconf_endfile(void);
 
@@ -101,17 +103,28 @@ n	[A-Za-z0-9_-]
 <COMMAND>{
 	{n}+	{
 		const struct kconf_id *id = kconf_id_lookup(yytext, yyleng);
-		BEGIN(PARAM);
 		current_pos.file = current_file;
 		current_pos.lineno = yylineno;
 		if (id && id->flags & TF_COMMAND) {
+			BEGIN(PARAM);
 			yylval.id = id;
 			return id->token;
 		}
 		alloc_string(yytext, yyleng);
 		yylval.string = text;
-		return T_WORD;
+		return T_VARIABLE;
 	}
+	({n}|$)+	{
+		/* this token includes at least one '$' */
+		yylval.string = expand_token(yytext, yyleng);
+		if (strlen(yylval.string))
+			return T_VARIABLE;
+		free(yylval.string);
+	}
+	"="	{ BEGIN(ASSIGN_VAL); yylval.flavor = VAR_RECURSIVE; return T_ASSIGN; }
+	":="	{ BEGIN(ASSIGN_VAL); yylval.flavor = VAR_SIMPLE; return T_ASSIGN; }
+	"+="	{ BEGIN(ASSIGN_VAL); yylval.flavor = VAR_APPEND; return T_ASSIGN; }
+	[[:blank:]]+
 	.	warn_ignored_character(*yytext);
 	\n	{
 		BEGIN(INITIAL);
@@ -119,6 +132,16 @@ n	[A-Za-z0-9_-]
 	}
 }
 
+<ASSIGN_VAL>{
+	[^[:blank:]\n]+.*	{
+		alloc_string(yytext, yyleng);
+		yylval.string = text;
+		return T_ASSIGN_VAL;
+	}
+	\n	{ BEGIN(INITIAL); return T_EOL; }
+	.
+}
+
 <PARAM>{
 	"&&"	return T_AND;
 	"||"	return T_OR;
@@ -147,6 +170,13 @@ n	[A-Za-z0-9_-]
 		yylval.string = text;
 		return T_WORD;
 	}
+	({n}|[/.$])+	{
+		/* this token includes at least one '$' */
+		yylval.string = expand_token(yytext, yyleng);
+		if (strlen(yylval.string))
+			return T_WORD;
+		free(yylval.string);
+	}
 	#.*	/* comment */
 	\\\n	;
 	[[:blank:]]+
@@ -157,12 +187,13 @@ n	[A-Za-z0-9_-]
 }
 
 <STRING>{
-	[^'"\\\n]+/\n	{
+	"$".*	append_expanded_string(yytext);
+	[^$'"\\\n]+/\n	{
 		append_string(yytext, yyleng);
 		yylval.string = text;
 		return T_WORD_QUOTE;
 	}
-	[^'"\\\n]+	{
+	[^$'"\\\n]+	{
 		append_string(yytext, yyleng);
 	}
 	\\.?/\n	{
@@ -249,6 +280,58 @@ n	[A-Za-z0-9_-]
 }
 
 %%
+static char *expand_token(const char *in, size_t n)
+{
+	char *out;
+	int c;
+	char c2;
+	const char *rest, *end;
+
+	new_string();
+	append_string(in, n);
+
+	/* get the whole line because we do not know the end of token. */
+	while ((c = input()) != EOF) {
+		if (c == '\n') {
+			unput(c);
+			break;
+		}
+		c2 = c;
+		append_string(&c2, 1);
+	}
+
+	rest = text;
+	out = expand_one_token(&rest);
+
+	/* push back unused characters to the input stream */
+	end = rest + strlen(rest);
+	while (end > rest)
+		unput(*--end);
+
+	free(text);
+
+	return out;
+}
+
+static void append_expanded_string(const char *str)
+{
+	const char *end;
+	char *res;
+
+	str++;
+
+	res = expand_dollar(&str);
+
+	/* push back unused characters to the input stream */
+	end = str + strlen(str);
+	while (end > str)
+		unput(*--end);
+
+	append_string(res, strlen(res));
+
+	free(res);
+}
+
 void zconf_starthelp(void)
 {
 	new_string();
diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y
index ad6305b0f40c..6f9b0aa32a82 100644
--- a/scripts/kconfig/zconf.y
+++ b/scripts/kconfig/zconf.y
@@ -41,6 +41,7 @@ static struct menu *current_menu, *current_entry;
 	struct expr *expr;
 	struct menu *menu;
 	const struct kconf_id *id;
+	enum variable_flavor flavor;
 }
 
 %token <id>T_MAINMENU
@@ -77,6 +78,9 @@ static struct menu *current_menu, *current_entry;
 %token T_CLOSE_PAREN
 %token T_OPEN_PAREN
 %token T_EOL
+%token <string> T_VARIABLE
+%token <flavor> T_ASSIGN
+%token <string> T_ASSIGN_VAL
 
 %left T_OR
 %left T_AND
@@ -92,7 +96,7 @@ static struct menu *current_menu, *current_entry;
 %type <id> end
 %type <id> option_name
 %type <menu> if_entry menu_entry choice_entry
-%type <string> symbol_option_arg word_opt
+%type <string> symbol_option_arg word_opt assign_val
 
 %destructor {
 	fprintf(stderr, "%s:%d: missing end statement for this entry\n",
@@ -109,7 +113,7 @@ static struct menu *current_menu, *current_entry;
 %%
 input: nl start | start;
 
-start: mainmenu_stmt stmt_list | no_mainmenu_stmt stmt_list;
+start: mainmenu_stmt stmt_list | stmt_list;
 
 /* mainmenu entry */
 
@@ -118,19 +122,6 @@ mainmenu_stmt: T_MAINMENU prompt nl
 	menu_add_prompt(P_MENU, $2, NULL);
 };
 
-/* Default main menu, if there's no mainmenu entry */
-
-no_mainmenu_stmt: /* empty */
-{
-	/*
-	 * Hack: Keep the main menu title on the heap so we can safely free it
-	 * later regardless of whether it comes from the 'prompt' in
-	 * mainmenu_stmt or here
-	 */
-	menu_add_prompt(P_MENU, xstrdup("Linux Kernel Configuration"), NULL);
-};
-
-
 stmt_list:
 	  /* empty */
 	| stmt_list common_stmt
@@ -156,6 +147,7 @@ common_stmt:
 	| config_stmt
 	| menuconfig_stmt
 	| source_stmt
+	| assignment_stmt
 ;
 
 option_error:
@@ -524,31 +516,42 @@ symbol:	  nonconst_symbol
 word_opt: /* empty */			{ $$ = NULL; }
 	| T_WORD
 
+/* assignment statement */
+
+assignment_stmt:  T_VARIABLE T_ASSIGN assign_val T_EOL	{ variable_add($1, $3, $2); free($1); free($3); }
+
+assign_val:
+	/* empty */		{ $$ = xstrdup(""); };
+	| T_ASSIGN_VAL
+;
+
 %%
 
 void conf_parse(const char *name)
 {
-	const char *tmp;
 	struct symbol *sym;
 	int i;
 
 	zconf_initscan(name);
 
-	sym_init();
 	_menu_init();
 
 	if (getenv("ZCONF_DEBUG"))
 		yydebug = 1;
 	yyparse();
+
+	/* Variables are expanded in the parse phase. We can free them here. */
+	variable_all_del();
+
 	if (yynerrs)
 		exit(1);
 	if (!modules_sym)
 		modules_sym = sym_find( "n" );
 
-	tmp = rootmenu.prompt->text;
-	rootmenu.prompt->text = _(rootmenu.prompt->text);
-	rootmenu.prompt->text = sym_expand_string_value(rootmenu.prompt->text);
-	free((char*)tmp);
+	if (!menu_has_prompt(&rootmenu)) {
+		current_entry = &rootmenu;
+		menu_add_prompt(P_MENU, "Main menu", NULL);
+	}
 
 	menu_finalize(&rootmenu);
 	for_all_symbols(i, sym) {
@@ -780,3 +783,4 @@ void zconfdump(FILE *out)
 #include "expr.c"
 #include "symbol.c"
 #include "menu.c"
+#include "preprocess.c"
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 9045823c7be7..4bf811c09f59 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -121,10 +121,6 @@ kallsyms()
 	info KSYM ${2}
 	local kallsymopt;
 
-	if [ -n "${CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX}" ]; then
-		kallsymopt="${kallsymopt} --symbol-prefix=_"
-	fi
-
 	if [ -n "${CONFIG_KALLSYMS_ALL}" ]; then
 		kallsymopt="${kallsymopt} --all-symbols"
 	fi
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index 9fad6afe4c41..6667f7b491d6 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -139,6 +139,9 @@ int main(void)
 	DEVID(hv_vmbus_device_id);
 	DEVID_FIELD(hv_vmbus_device_id, guid);
 
+	DEVID(rpmsg_device_id);
+	DEVID_FIELD(rpmsg_device_id, name);
+
 	DEVID(i2c_device_id);
 	DEVID_FIELD(i2c_device_id, name);
 
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index b9beeaa4695b..52fd54a8fe39 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -944,6 +944,17 @@ static int do_vmbus_entry(const char *filename, void *symval,
 }
 ADD_TO_DEVTABLE("vmbus", hv_vmbus_device_id, do_vmbus_entry);
 
+/* Looks like: rpmsg:S */
+static int do_rpmsg_entry(const char *filename, void *symval,
+			  char *alias)
+{
+	DEF_FIELD_ADDR(symval, rpmsg_device_id, name);
+	sprintf(alias, RPMSG_DEVICE_MODALIAS_FMT, *name);
+
+	return 1;
+}
+ADD_TO_DEVTABLE("rpmsg", rpmsg_device_id, do_rpmsg_entry);
+
 /* Looks like: i2c:S */
 static int do_i2c_entry(const char *filename, void *symval,
 			char *alias)
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 4ff08a0ef5d3..1663fb19343a 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -19,9 +19,7 @@
 #include <stdbool.h>
 #include <errno.h>
 #include "modpost.h"
-#include "../../include/generated/autoconf.h"
 #include "../../include/linux/license.h"
-#include "../../include/linux/export.h"
 
 /* Are we using CONFIG_MODVERSIONS? */
 static int modversions = 0;
@@ -123,7 +121,7 @@ void *do_nofail(void *ptr, const char *expr)
 /* A list of all modules we processed */
 static struct module *modules;
 
-static struct module *find_module(char *modname)
+static struct module *find_module(const char *modname)
 {
 	struct module *mod;
 
@@ -591,35 +589,32 @@ static void parse_elf_finish(struct elf_info *info)
 static int ignore_undef_symbol(struct elf_info *info, const char *symname)
 {
 	/* ignore __this_module, it will be resolved shortly */
-	if (strcmp(symname, VMLINUX_SYMBOL_STR(__this_module)) == 0)
+	if (strcmp(symname, "__this_module") == 0)
 		return 1;
 	/* ignore global offset table */
 	if (strcmp(symname, "_GLOBAL_OFFSET_TABLE_") == 0)
 		return 1;
 	if (info->hdr->e_machine == EM_PPC)
 		/* Special register function linked on all modules during final link of .ko */
-		if (strncmp(symname, "_restgpr_", sizeof("_restgpr_") - 1) == 0 ||
-		    strncmp(symname, "_savegpr_", sizeof("_savegpr_") - 1) == 0 ||
-		    strncmp(symname, "_rest32gpr_", sizeof("_rest32gpr_") - 1) == 0 ||
-		    strncmp(symname, "_save32gpr_", sizeof("_save32gpr_") - 1) == 0 ||
-		    strncmp(symname, "_restvr_", sizeof("_restvr_") - 1) == 0 ||
-		    strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0)
+		if (strstarts(symname, "_restgpr_") ||
+		    strstarts(symname, "_savegpr_") ||
+		    strstarts(symname, "_rest32gpr_") ||
+		    strstarts(symname, "_save32gpr_") ||
+		    strstarts(symname, "_restvr_") ||
+		    strstarts(symname, "_savevr_"))
 			return 1;
 	if (info->hdr->e_machine == EM_PPC64)
 		/* Special register function linked on all modules during final link of .ko */
-		if (strncmp(symname, "_restgpr0_", sizeof("_restgpr0_") - 1) == 0 ||
-		    strncmp(symname, "_savegpr0_", sizeof("_savegpr0_") - 1) == 0 ||
-		    strncmp(symname, "_restvr_", sizeof("_restvr_") - 1) == 0 ||
-		    strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0 ||
+		if (strstarts(symname, "_restgpr0_") ||
+		    strstarts(symname, "_savegpr0_") ||
+		    strstarts(symname, "_restvr_") ||
+		    strstarts(symname, "_savevr_") ||
 		    strcmp(symname, ".TOC.") == 0)
 			return 1;
 	/* Do not ignore this symbol */
 	return 0;
 }
 
-#define CRC_PFX     VMLINUX_SYMBOL_STR(__crc_)
-#define KSYMTAB_PFX VMLINUX_SYMBOL_STR(__ksymtab_)
-
 static void handle_modversions(struct module *mod, struct elf_info *info,
 			       Elf_Sym *sym, const char *symname)
 {
@@ -628,13 +623,13 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 	bool is_crc = false;
 
 	if ((!is_vmlinux(mod->name) || mod->is_dot_o) &&
-	    strncmp(symname, "__ksymtab", 9) == 0)
+	    strstarts(symname, "__ksymtab"))
 		export = export_from_secname(info, get_secindex(info, sym));
 	else
 		export = export_from_sec(info, get_secindex(info, sym));
 
 	/* CRC'd symbol */
-	if (strncmp(symname, CRC_PFX, strlen(CRC_PFX)) == 0) {
+	if (strstarts(symname, "__crc_")) {
 		is_crc = true;
 		crc = (unsigned int) sym->st_value;
 		if (sym->st_shndx != SHN_UNDEF && sym->st_shndx != SHN_ABS) {
@@ -647,13 +642,13 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 				info->sechdrs[sym->st_shndx].sh_addr : 0);
 			crc = *crcp;
 		}
-		sym_update_crc(symname + strlen(CRC_PFX), mod, crc,
+		sym_update_crc(symname + strlen("__crc_"), mod, crc,
 				export);
 	}
 
 	switch (sym->st_shndx) {
 	case SHN_COMMON:
-		if (!strncmp(symname, "__gnu_lto_", sizeof("__gnu_lto_")-1)) {
+		if (strstarts(symname, "__gnu_lto_")) {
 			/* Should warn here, but modpost runs before the linker */
 		} else
 			warn("\"%s\" [%s] is COMMON symbol\n", symname, mod->name);
@@ -685,15 +680,10 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 		}
 #endif
 
-#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
-		if (symname[0] != '_')
-			break;
-		else
-			symname++;
-#endif
 		if (is_crc) {
 			const char *e = is_vmlinux(mod->name) ?"":".ko";
-			warn("EXPORT symbol \"%s\" [%s%s] version generation failed, symbol will not be versioned.\n", symname + strlen(CRC_PFX), mod->name, e);
+			warn("EXPORT symbol \"%s\" [%s%s] version generation failed, symbol will not be versioned.\n",
+			     symname + strlen("__crc_"), mod->name, e);
 		}
 		mod->unres = alloc_symbol(symname,
 					  ELF_ST_BIND(sym->st_info) == STB_WEAK,
@@ -701,13 +691,13 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 		break;
 	default:
 		/* All exported symbols */
-		if (strncmp(symname, KSYMTAB_PFX, strlen(KSYMTAB_PFX)) == 0) {
-			sym_add_exported(symname + strlen(KSYMTAB_PFX), mod,
+		if (strstarts(symname, "__ksymtab_")) {
+			sym_add_exported(symname + strlen("__ksymtab_"), mod,
 					export);
 		}
-		if (strcmp(symname, VMLINUX_SYMBOL_STR(init_module)) == 0)
+		if (strcmp(symname, "init_module") == 0)
 			mod->has_init = 1;
-		if (strcmp(symname, VMLINUX_SYMBOL_STR(cleanup_module)) == 0)
+		if (strcmp(symname, "cleanup_module") == 0)
 			mod->has_cleanup = 1;
 		break;
 	}
@@ -734,16 +724,17 @@ static char *next_string(char *string, unsigned long *secsize)
 	return string;
 }
 
-static char *get_next_modinfo(void *modinfo, unsigned long modinfo_len,
-			      const char *tag, char *info)
+static char *get_next_modinfo(struct elf_info *info, const char *tag,
+			      char *prev)
 {
 	char *p;
 	unsigned int taglen = strlen(tag);
-	unsigned long size = modinfo_len;
+	char *modinfo = info->modinfo;
+	unsigned long size = info->modinfo_len;
 
-	if (info) {
-		size -= info - (char *)modinfo;
-		modinfo = next_string(info, &size);
+	if (prev) {
+		size -= prev - modinfo;
+		modinfo = next_string(prev, &size);
 	}
 
 	for (p = modinfo; p; p = next_string(p, &size)) {
@@ -753,11 +744,10 @@ static char *get_next_modinfo(void *modinfo, unsigned long modinfo_len,
 	return NULL;
 }
 
-static char *get_modinfo(void *modinfo, unsigned long modinfo_len,
-			 const char *tag)
+static char *get_modinfo(struct elf_info *info, const char *tag)
 
 {
-	return get_next_modinfo(modinfo, modinfo_len, tag, NULL);
+	return get_next_modinfo(info, tag, NULL);
 }
 
 /**
@@ -1181,13 +1171,13 @@ static int secref_whitelist(const struct sectioncheck *mismatch,
 	/* Check for pattern 1 */
 	if (match(tosec, init_data_sections) &&
 	    match(fromsec, data_sections) &&
-	    (strncmp(fromsym, "__param", strlen("__param")) == 0))
+	    strstarts(fromsym, "__param"))
 		return 0;
 
 	/* Check for pattern 1a */
 	if (strcmp(tosec, ".init.text") == 0 &&
 	    match(fromsec, data_sections) &&
-	    (strncmp(fromsym, "__param_ops_", strlen("__param_ops_")) == 0))
+	    strstarts(fromsym, "__param_ops_"))
 		return 0;
 
 	/* Check for pattern 2 */
@@ -1542,8 +1532,7 @@ static void default_mismatch_handler(const char *modname, struct elf_info *elf,
 	from = find_elf_symbol2(elf, r->r_offset, fromsec);
 	fromsym = sym_name(elf, from);
 
-	if (!strncmp(fromsym, "reference___initcall",
-		     sizeof("reference___initcall")-1))
+	if (strstarts(fromsym, "reference___initcall"))
 		return;
 
 	tosec = sec_name(elf, get_secindex(elf, sym));
@@ -1940,7 +1929,7 @@ static char *remove_dot(char *s)
 	return s;
 }
 
-static void read_symbols(char *modname)
+static void read_symbols(const char *modname)
 {
 	const char *symname;
 	char *version;
@@ -1961,7 +1950,7 @@ static void read_symbols(char *modname)
 		mod->skip = 1;
 	}
 
-	license = get_modinfo(info.modinfo, info.modinfo_len, "license");
+	license = get_modinfo(&info, "license");
 	if (!license && !is_vmlinux(modname))
 		warn("modpost: missing MODULE_LICENSE() in %s\n"
 		     "see include/linux/module.h for "
@@ -1973,8 +1962,7 @@ static void read_symbols(char *modname)
 			mod->gpl_compatible = 0;
 			break;
 		}
-		license = get_next_modinfo(info.modinfo, info.modinfo_len,
-					   "license", license);
+		license = get_next_modinfo(&info, "license", license);
 	}
 
 	for (sym = info.symtab_start; sym < info.symtab_stop; sym++) {
@@ -1983,11 +1971,10 @@ static void read_symbols(char *modname)
 		handle_modversions(mod, &info, sym, symname);
 		handle_moddevtable(mod, &info, sym, symname);
 	}
-	if (!is_vmlinux(modname) ||
-	     (is_vmlinux(modname) && vmlinux_section_warnings))
+	if (!is_vmlinux(modname) || vmlinux_section_warnings)
 		check_sec_ref(mod, modname, &info);
 
-	version = get_modinfo(info.modinfo, info.modinfo_len, "version");
+	version = get_modinfo(&info, "version");
 	if (version)
 		maybe_frob_rcs_version(modname, version, info.modinfo,
 				       version - (char *)info.hdr);
@@ -2174,9 +2161,7 @@ static void add_retpoline(struct buffer *b)
 
 static void add_staging_flag(struct buffer *b, const char *name)
 {
-	static const char *staging_dir = "drivers/staging";
-
-	if (strncmp(staging_dir, name, strlen(staging_dir)) == 0)
+	if (strstarts(name, "drivers/staging"))
 		buf_printf(b, "\nMODULE_INFO(staging, \"Y\");\n");
 }
 
@@ -2230,7 +2215,7 @@ static int add_versions(struct buffer *b, struct module *mod)
 			err = 1;
 			break;
 		}
-		buf_printf(b, "\t{ %#8x, __VMLINUX_SYMBOL_STR(%s) },\n",
+		buf_printf(b, "\t{ %#8x, \"%s\" },\n",
 			   s->crc, s->name);
 	}
 
diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c
index 944418da9fe3..0f6dcb4011a8 100644
--- a/scripts/mod/sumversion.c
+++ b/scripts/mod/sumversion.c
@@ -330,14 +330,7 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md)
 		goto out;
 	}
 
-	/* There will be a line like so:
-		deps_drivers/net/dummy.o := \
-		  drivers/net/dummy.c \
-		    $(wildcard include/config/net/fastroute.h) \
-		  include/linux/module.h \
-
-	   Sum all files in the same dir or subdirs.
-	*/
+	/* Sum all files in the same dir or subdirs. */
 	while ((line = get_next_line(&pos, file, flen)) != NULL) {
 		char* p = line;
 
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 6adb3a16ba3b..985d72d1ab34 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -71,22 +71,21 @@ if [ "$ARCH" = "um" ] ; then
 	packagename=user-mode-linux-$version
 fi
 
-# Try to determine maintainer and email values
-if [ -n "$DEBEMAIL" ]; then
-       email=$DEBEMAIL
-elif [ -n "$EMAIL" ]; then
-       email=$EMAIL
-else
-       email=$(id -nu)@$(hostname -f 2>/dev/null || hostname)
-fi
-if [ -n "$DEBFULLNAME" ]; then
-       name=$DEBFULLNAME
-elif [ -n "$NAME" ]; then
-       name=$NAME
+email=${DEBEMAIL-$EMAIL}
+
+# use email string directly if it contains <email>
+if echo $email | grep -q '<.*>'; then
+	maintainer=$email
 else
-       name="Anonymous"
+	# or construct the maintainer string
+	user=${KBUILD_BUILD_USER-$(id -nu)}
+	name=${DEBFULLNAME-$user}
+	if [ -z "$email" ]; then
+		buildhost=${KBUILD_BUILD_HOST-$(hostname -f 2>/dev/null || hostname)}
+		email="$user@$buildhost"
+	fi
+	maintainer="$name <$email>"
 fi
-maintainer="$name <$email>"
 
 # Try to determine distribution
 if [ -n "$KDEB_CHANGELOG_DIST" ]; then
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 8c9691c3329e..895c40e8679f 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -500,7 +500,7 @@ do_file(char const *const fname)
 	gpfx = 0;
 	switch (w2(ehdr->e_machine)) {
 	default:
-		fprintf(stderr, "unrecognized e_machine %d %s\n",
+		fprintf(stderr, "unrecognized e_machine %u %s\n",
 			w2(ehdr->e_machine), fname);
 		fail_file();
 		break;
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index b9897e2be404..2e7793735e14 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -441,7 +441,7 @@ static unsigned find_secsym_ndx(unsigned const txtndx,
 			return symp - sym0;
 		}
 	}
-	fprintf(stderr, "Cannot find symbol for section %d: %s.\n",
+	fprintf(stderr, "Cannot find symbol for section %u: %s.\n",
 		txtndx, txtname);
 	fail_file();
 }
diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py
new file mode 100755
index 000000000000..7deaef297f52
--- /dev/null
+++ b/scripts/spdxcheck.py
@@ -0,0 +1,284 @@
+#!/usr/bin/env python
+# SPDX-License-Identifier: GPL-2.0
+# Copyright Thomas Gleixner <tglx@linutronix.de>
+
+from argparse import ArgumentParser
+from ply import lex, yacc
+import traceback
+import sys
+import git
+import re
+import os
+
+class ParserException(Exception):
+    def __init__(self, tok, txt):
+        self.tok = tok
+        self.txt = txt
+
+class SPDXException(Exception):
+    def __init__(self, el, txt):
+        self.el = el
+        self.txt = txt
+
+class SPDXdata(object):
+    def __init__(self):
+        self.license_files = 0
+        self.exception_files = 0
+        self.licenses = [ ]
+        self.exceptions = { }
+
+# Read the spdx data from the LICENSES directory
+def read_spdxdata(repo):
+
+    # The subdirectories of LICENSES in the kernel source
+    license_dirs = [ "preferred", "other", "exceptions" ]
+    lictree = repo.heads.master.commit.tree['LICENSES']
+
+    spdx = SPDXdata()
+
+    for d in license_dirs:
+        for el in lictree[d].traverse():
+            if not os.path.isfile(el.path):
+                continue
+
+            exception = None
+            for l in open(el.path).readlines():
+                if l.startswith('Valid-License-Identifier:'):
+                    lid = l.split(':')[1].strip().upper()
+                    if lid in spdx.licenses:
+                        raise SPDXException(el, 'Duplicate License Identifier: %s' %lid)
+                    else:
+                        spdx.licenses.append(lid)
+
+                elif l.startswith('SPDX-Exception-Identifier:'):
+                    exception = l.split(':')[1].strip().upper()
+                    spdx.exceptions[exception] = []
+
+                elif l.startswith('SPDX-Licenses:'):
+                    for lic in l.split(':')[1].upper().strip().replace(' ', '').replace('\t', '').split(','):
+                        if not lic in spdx.licenses:
+                            raise SPDXException(None, 'Exception %s missing license %s' %(ex, lic))
+                        spdx.exceptions[exception].append(lic)
+
+                elif l.startswith("License-Text:"):
+                    if exception:
+                        if not len(spdx.exceptions[exception]):
+                            raise SPDXException(el, 'Exception %s is missing SPDX-Licenses' %excid)
+                        spdx.exception_files += 1
+                    else:
+                        spdx.license_files += 1
+                    break
+    return spdx
+
+class id_parser(object):
+
+    reserved = [ 'AND', 'OR', 'WITH' ]
+    tokens = [ 'LPAR', 'RPAR', 'ID', 'EXC' ] + reserved
+
+    precedence = ( ('nonassoc', 'AND', 'OR'), )
+
+    t_ignore = ' \t'
+
+    def __init__(self, spdx):
+        self.spdx = spdx
+        self.lasttok = None
+        self.lastid = None
+        self.lexer = lex.lex(module = self, reflags = re.UNICODE)
+        # Initialize the parser. No debug file and no parser rules stored on disk
+        # The rules are small enough to be generated on the fly
+        self.parser = yacc.yacc(module = self, write_tables = False, debug = False)
+        self.lines_checked = 0
+        self.checked = 0
+        self.spdx_valid = 0
+        self.spdx_errors = 0
+        self.curline = 0
+        self.deepest = 0
+
+    # Validate License and Exception IDs
+    def validate(self, tok):
+        id = tok.value.upper()
+        if tok.type == 'ID':
+            if not id in self.spdx.licenses:
+                raise ParserException(tok, 'Invalid License ID')
+            self.lastid = id
+        elif tok.type == 'EXC':
+            if not self.spdx.exceptions.has_key(id):
+                raise ParserException(tok, 'Invalid Exception ID')
+            if self.lastid not in self.spdx.exceptions[id]:
+                raise ParserException(tok, 'Exception not valid for license %s' %self.lastid)
+            self.lastid = None
+        elif tok.type != 'WITH':
+            self.lastid = None
+
+    # Lexer functions
+    def t_RPAR(self, tok):
+        r'\)'
+        self.lasttok = tok.type
+        return tok
+
+    def t_LPAR(self, tok):
+        r'\('
+        self.lasttok = tok.type
+        return tok
+
+    def t_ID(self, tok):
+        r'[A-Za-z.0-9\-+]+'
+
+        if self.lasttok == 'EXC':
+            print(tok)
+            raise ParserException(tok, 'Missing parentheses')
+
+        tok.value = tok.value.strip()
+        val = tok.value.upper()
+
+        if val in self.reserved:
+            tok.type = val
+        elif self.lasttok == 'WITH':
+            tok.type = 'EXC'
+
+        self.lasttok = tok.type
+        self.validate(tok)
+        return tok
+
+    def t_error(self, tok):
+        raise ParserException(tok, 'Invalid token')
+
+    def p_expr(self, p):
+        '''expr : ID
+                | ID WITH EXC
+                | expr AND expr
+                | expr OR expr
+                | LPAR expr RPAR'''
+        pass
+
+    def p_error(self, p):
+        if not p:
+            raise ParserException(None, 'Unfinished license expression')
+        else:
+            raise ParserException(p, 'Syntax error')
+
+    def parse(self, expr):
+        self.lasttok = None
+        self.lastid = None
+        self.parser.parse(expr, lexer = self.lexer)
+
+    def parse_lines(self, fd, maxlines, fname):
+        self.checked += 1
+        self.curline = 0
+        try:
+            for line in fd:
+                self.curline += 1
+                if self.curline > maxlines:
+                    break
+                self.lines_checked += 1
+                if line.find("SPDX-License-Identifier:") < 0:
+                    continue
+                expr = line.split(':')[1].replace('*/', '').strip()
+                self.parse(expr)
+                self.spdx_valid += 1
+                #
+                # Should we check for more SPDX ids in the same file and
+                # complain if there are any?
+                #
+                break
+
+        except ParserException as pe:
+            if pe.tok:
+                col = line.find(expr) + pe.tok.lexpos
+                tok = pe.tok.value
+                sys.stdout.write('%s: %d:%d %s: %s\n' %(fname, self.curline, col, pe.txt, tok))
+            else:
+                sys.stdout.write('%s: %d:0 %s\n' %(fname, self.curline, col, pe.txt))
+            self.spdx_errors += 1
+
+def scan_git_tree(tree):
+    for el in tree.traverse():
+        # Exclude stuff which would make pointless noise
+        # FIXME: Put this somewhere more sensible
+        if el.path.startswith("LICENSES"):
+            continue
+        if el.path.find("license-rules.rst") >= 0:
+            continue
+        if el.path == 'scripts/checkpatch.pl':
+            continue
+        if not os.path.isfile(el.path):
+            continue
+        parser.parse_lines(open(el.path), args.maxlines, el.path)
+
+def scan_git_subtree(tree, path):
+    for p in path.strip('/').split('/'):
+        tree = tree[p]
+    scan_git_tree(tree)
+
+if __name__ == '__main__':
+
+    ap = ArgumentParser(description='SPDX expression checker')
+    ap.add_argument('path', nargs='*', help='Check path or file. If not given full git tree scan. For stdin use "-"')
+    ap.add_argument('-m', '--maxlines', type=int, default=15,
+                    help='Maximum number of lines to scan in a file. Default 15')
+    ap.add_argument('-v', '--verbose', action='store_true', help='Verbose statistics output')
+    args = ap.parse_args()
+
+    # Sanity check path arguments
+    if '-' in args.path and len(args.path) > 1:
+        sys.stderr.write('stdin input "-" must be the only path argument\n')
+        sys.exit(1)
+
+    try:
+        # Use git to get the valid license expressions
+        repo = git.Repo(os.getcwd())
+        assert not repo.bare
+
+        # Initialize SPDX data
+        spdx = read_spdxdata(repo)
+
+        # Initilize the parser
+        parser = id_parser(spdx)
+
+    except SPDXException as se:
+        if se.el:
+            sys.stderr.write('%s: %s\n' %(se.el.path, se.txt))
+        else:
+            sys.stderr.write('%s\n' %se.txt)
+        sys.exit(1)
+
+    except Exception as ex:
+        sys.stderr.write('FAIL: %s\n' %ex)
+        sys.stderr.write('%s\n' %traceback.format_exc())
+        sys.exit(1)
+
+    try:
+        if len(args.path) and args.path[0] == '-':
+            parser.parse_lines(sys.stdin, args.maxlines, '-')
+        else:
+            if args.path:
+                for p in args.path:
+                    if os.path.isfile(p):
+                        parser.parse_lines(open(p), args.maxlines, p)
+                    elif os.path.isdir(p):
+                        scan_git_subtree(repo.head.reference.commit.tree, p)
+                    else:
+                        sys.stderr.write('path %s does not exist\n' %p)
+                        sys.exit(1)
+            else:
+                # Full git tree scan
+                scan_git_tree(repo.head.commit.tree)
+
+            if args.verbose:
+                sys.stderr.write('\n')
+                sys.stderr.write('License files:     %12d\n' %spdx.license_files)
+                sys.stderr.write('Exception files:   %12d\n' %spdx.exception_files)
+                sys.stderr.write('License IDs        %12d\n' %len(spdx.licenses))
+                sys.stderr.write('Exception IDs      %12d\n' %len(spdx.exceptions))
+                sys.stderr.write('\n')
+                sys.stderr.write('Files checked:     %12d\n' %parser.checked)
+                sys.stderr.write('Lines checked:     %12d\n' %parser.lines_checked)
+                sys.stderr.write('Files with SPDX:   %12d\n' %parser.spdx_valid)
+                sys.stderr.write('Files with errors: %12d\n' %parser.spdx_errors)
+
+            sys.exit(0)
+
+    except Exception as ex:
+        sys.stderr.write('FAIL: %s\n' %ex)
+        sys.stderr.write('%s\n' %traceback.format_exc())
+        sys.exit(1)
diff --git a/scripts/split-man.pl b/scripts/split-man.pl
index bfe16cbe42df..c3db607ee9ec 100755
--- a/scripts/split-man.pl
+++ b/scripts/split-man.pl
@@ -1,7 +1,7 @@
 #!/usr/bin/perl
 # SPDX-License-Identifier: GPL-2.0
 #
-# Author: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+# Author: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
 #
 # Produce manpages from kernel-doc.
 # See Documentation/doc-guide/kernel-doc.rst for instructions
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 78e546ff689c..e587610d1492 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -28,20 +28,11 @@ fi
 # ignore userspace tools
 ignore="$ignore ( -path ${tree}tools ) -prune -o"
 
-# Find all available archs
-find_all_archs()
-{
-	ALLSOURCE_ARCHS=""
-	for arch in `ls ${tree}arch`; do
-		ALLSOURCE_ARCHS="${ALLSOURCE_ARCHS} "${arch##\/}
-	done
-}
-
 # Detect if ALLSOURCE_ARCHS is set. If not, we assume SRCARCH
 if [ "${ALLSOURCE_ARCHS}" = "" ]; then
 	ALLSOURCE_ARCHS=${SRCARCH}
 elif [ "${ALLSOURCE_ARCHS}" = "all" ]; then
-	find_all_archs
+	ALLSOURCE_ARCHS=$(find ${tree}arch/ -mindepth 1 -maxdepth 1 -type d -printf '%f ')
 fi
 
 # find sources in arch/$ARCH
diff --git a/scripts/ver_linux b/scripts/ver_linux
index 545ec7388eb7..7227994ccf63 100755
--- a/scripts/ver_linux
+++ b/scripts/ver_linux
@@ -13,36 +13,34 @@ BEGIN {
 	system("uname -a")
 	printf("\n")
 
-	printversion("GNU C", version("gcc -dumpversion 2>&1"))
-	printversion("GNU Make", version("make --version 2>&1"))
-	printversion("Binutils", version("ld -v 2>&1"))
-	printversion("Util-linux", version("mount --version 2>&1"))
-	printversion("Mount", version("mount --version 2>&1"))
-	printversion("Module-init-tools", version("depmod -V  2>&1"))
-	printversion("E2fsprogs", version("tune2fs 2>&1"))
-	printversion("Jfsutils", version("fsck.jfs -V 2>&1"))
-	printversion("Reiserfsprogs", version("reiserfsck -V 2>&1"))
-	printversion("Reiser4fsprogs", version("fsck.reiser4 -V 2>&1"))
-	printversion("Xfsprogs", version("xfs_db -V 2>&1"))
-	printversion("Pcmciautils", version("pccardctl -V 2>&1"))
-	printversion("Pcmcia-cs", version("cardmgr -V 2>&1"))
-	printversion("Quota-tools", version("quota -V 2>&1"))
-	printversion("PPP", version("pppd --version 2>&1"))
-	printversion("Isdn4k-utils", version("isdnctrl 2>&1"))
-	printversion("Nfs-utils", version("showmount --version 2>&1"))
+	printversion("GNU C", version("gcc -dumpversion"))
+	printversion("GNU Make", version("make --version"))
+	printversion("Binutils", version("ld -v"))
+	printversion("Util-linux", version("mount --version"))
+	printversion("Mount", version("mount --version"))
+	printversion("Module-init-tools", version("depmod -V"))
+	printversion("E2fsprogs", version("tune2fs"))
+	printversion("Jfsutils", version("fsck.jfs -V"))
+	printversion("Reiserfsprogs", version("reiserfsck -V"))
+	printversion("Reiser4fsprogs", version("fsck.reiser4 -V"))
+	printversion("Xfsprogs", version("xfs_db -V"))
+	printversion("Pcmciautils", version("pccardctl -V"))
+	printversion("Pcmcia-cs", version("cardmgr -V"))
+	printversion("Quota-tools", version("quota -V"))
+	printversion("PPP", version("pppd --version"))
+	printversion("Isdn4k-utils", version("isdnctrl"))
+	printversion("Nfs-utils", version("showmount --version"))
 
-	if (system("test -r /proc/self/maps") == 0) {
-		while (getline <"/proc/self/maps" > 0) {
-			n = split($0, procmaps, "/")
-			if (/libc.*so$/ && match(procmaps[n], /[0-9]+([.]?[0-9]+)+/)) {
-				ver = substr(procmaps[n], RSTART, RLENGTH)
-				printversion("Linux C Library", ver)
-				break
-			}
+	while (getline <"/proc/self/maps" > 0) {
+		n = split($0, procmaps, "/")
+		if (/libc.*so$/ && match(procmaps[n], /[0-9]+([.]?[0-9]+)+/)) {
+			ver = substr(procmaps[n], RSTART, RLENGTH)
+			printversion("Linux C Library", ver)
+			break
 		}
 	}
 
-	printversion("Dynamic linker (ldd)", version("ldd --version 2>&1"))
+	printversion("Dynamic linker (ldd)", version("ldd --version"))
 
 	while ("ldconfig -p 2>/dev/null" | getline > 0) {
 		if (/(libg|stdc)[+]+\.so/) {
@@ -50,28 +48,25 @@ BEGIN {
 			break
 		}
 	}
-	if (system("test -r " libcpp) == 0)
-		printversion("Linux C++ Library", version("readlink " libcpp))
-
-	printversion("Procps", version("ps --version 2>&1"))
-	printversion("Net-tools", version("ifconfig --version 2>&1"))
-	printversion("Kbd", version("loadkeys -V 2>&1"))
-	printversion("Console-tools", version("loadkeys -V 2>&1"))
-	printversion("Oprofile", version("oprofiled --version 2>&1"))
-	printversion("Sh-utils", version("expr --v 2>&1"))
-	printversion("Udev", version("udevadm --version 2>&1"))
-	printversion("Wireless-tools", version("iwconfig --version 2>&1"))
+	printversion("Linux C++ Library", version("readlink " libcpp))
+	printversion("Procps", version("ps --version"))
+	printversion("Net-tools", version("ifconfig --version"))
+	printversion("Kbd", version("loadkeys -V"))
+	printversion("Console-tools", version("loadkeys -V"))
+	printversion("Oprofile", version("oprofiled --version"))
+	printversion("Sh-utils", version("expr --v"))
+	printversion("Udev", version("udevadm --version"))
+	printversion("Wireless-tools", version("iwconfig --version"))
 
-	if (system("test -r /proc/modules") == 0) {
-		while ("sort /proc/modules" | getline > 0) {
-			mods = mods sep $1
-			sep = " "
-		}
-		printversion("Modules Loaded", mods)
+	while ("sort /proc/modules" | getline > 0) {
+		mods = mods sep $1
+		sep = " "
 	}
+	printversion("Modules Loaded", mods)
 }
 
 function version(cmd,    ver) {
+	cmd = cmd " 2>&1"
 	while (cmd | getline > 0) {
 		if (!/ver_linux/ && match($0, /[0-9]+([.]?[0-9]+)+/)) {
 			ver = substr($0, RSTART, RLENGTH)
diff --git a/security/commoncap.c b/security/commoncap.c
index 48620c93d697..f4c33abd9959 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -449,6 +449,8 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
 				magic |= VFS_CAP_FLAGS_EFFECTIVE;
 			memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
 			cap->magic_etc = cpu_to_le32(magic);
+		} else {
+			size = -ENOMEM;
 		}
 	}
 	kfree(tmpbuf);
@@ -917,6 +919,8 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 int cap_inode_setxattr(struct dentry *dentry, const char *name,
 		       const void *value, size_t size, int flags)
 {
+	struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
+
 	/* Ignore non-security xattrs */
 	if (strncmp(name, XATTR_SECURITY_PREFIX,
 			sizeof(XATTR_SECURITY_PREFIX) - 1) != 0)
@@ -929,7 +933,7 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name,
 	if (strcmp(name, XATTR_NAME_CAPS) == 0)
 		return 0;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 	return 0;
 }
@@ -947,6 +951,8 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name,
  */
 int cap_inode_removexattr(struct dentry *dentry, const char *name)
 {
+	struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
+
 	/* Ignore non-security xattrs */
 	if (strncmp(name, XATTR_SECURITY_PREFIX,
 			sizeof(XATTR_SECURITY_PREFIX) - 1) != 0)
@@ -962,7 +968,7 @@ int cap_inode_removexattr(struct dentry *dentry, const char *name)
 		return 0;
 	}
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 	return 0;
 }
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index a46fba322340..facf9cdd577d 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -200,7 +200,8 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 	int size;
 	bool ima_present = false;
 
-	if (!(inode->i_opflags & IOP_XATTR))
+	if (!(inode->i_opflags & IOP_XATTR) ||
+	    inode->i_sb->s_user_ns != &init_user_ns)
 		return -EOPNOTSUPP;
 
 	desc = init_desc(type);
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 933623784ccd..2806e70d7f8f 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -22,6 +22,7 @@
 #include <keys/user-type.h>
 #include <keys/big_key-type.h>
 #include <crypto/aead.h>
+#include <crypto/gcm.h>
 
 struct big_key_buf {
 	unsigned int		nr_pages;
@@ -85,6 +86,7 @@ struct key_type key_type_big_key = {
  * Crypto names for big_key data authenticated encryption
  */
 static const char big_key_alg_name[] = "gcm(aes)";
+#define BIG_KEY_IV_SIZE		GCM_AES_IV_SIZE
 
 /*
  * Crypto algorithms for big_key data authenticated encryption
@@ -109,7 +111,7 @@ static int big_key_crypt(enum big_key_op op, struct big_key_buf *buf, size_t dat
 	 * an .update function, so there's no chance we'll wind up reusing the
 	 * key to encrypt updated data. Simply put: one key, one encryption.
 	 */
-	u8 zero_nonce[crypto_aead_ivsize(big_key_aead)];
+	u8 zero_nonce[BIG_KEY_IV_SIZE];
 
 	aead_req = aead_request_alloc(big_key_aead, GFP_KERNEL);
 	if (!aead_req)
@@ -425,6 +427,13 @@ static int __init big_key_init(void)
 		pr_err("Can't alloc crypto: %d\n", ret);
 		return ret;
 	}
+
+	if (unlikely(crypto_aead_ivsize(big_key_aead) != BIG_KEY_IV_SIZE)) {
+		WARN(1, "big key algorithm changed?");
+		ret = -EINVAL;
+		goto free_aead;
+	}
+
 	ret = crypto_aead_setauthsize(big_key_aead, ENC_AUTHTAG_SIZE);
 	if (ret < 0) {
 		pr_err("Can't set crypto auth tag len: %d\n", ret);
diff --git a/security/keys/dh.c b/security/keys/dh.c
index d1ea9f325f94..f7403821db7f 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -162,8 +162,8 @@ static int kdf_ctr(struct kdf_sdesc *sdesc, const u8 *src, unsigned int slen,
 			goto err;
 
 		if (zlen && h) {
-			u8 tmpbuffer[h];
-			size_t chunk = min_t(size_t, zlen, h);
+			u8 tmpbuffer[32];
+			size_t chunk = min_t(size_t, zlen, sizeof(tmpbuffer));
 			memset(tmpbuffer, 0, chunk);
 
 			do {
@@ -173,7 +173,7 @@ static int kdf_ctr(struct kdf_sdesc *sdesc, const u8 *src, unsigned int slen,
 					goto err;
 
 				zlen -= chunk;
-				chunk = min_t(size_t, zlen, h);
+				chunk = min_t(size_t, zlen, sizeof(tmpbuffer));
 			} while (zlen);
 		}
 
@@ -183,24 +183,13 @@ static int kdf_ctr(struct kdf_sdesc *sdesc, const u8 *src, unsigned int slen,
 				goto err;
 		}
 
-		if (dlen < h) {
-			u8 tmpbuffer[h];
-
-			err = crypto_shash_final(desc, tmpbuffer);
-			if (err)
-				goto err;
-			memcpy(dst, tmpbuffer, dlen);
-			memzero_explicit(tmpbuffer, h);
-			return 0;
-		} else {
-			err = crypto_shash_final(desc, dst);
-			if (err)
-				goto err;
+		err = crypto_shash_final(desc, dst);
+		if (err)
+			goto err;
 
-			dlen -= h;
-			dst += h;
-			counter = cpu_to_be32(be32_to_cpu(counter) + 1);
-		}
+		dlen -= h;
+		dst += h;
+		counter = cpu_to_be32(be32_to_cpu(counter) + 1);
 	}
 
 	return 0;
@@ -216,14 +205,16 @@ static int keyctl_dh_compute_kdf(struct kdf_sdesc *sdesc,
 {
 	uint8_t *outbuf = NULL;
 	int ret;
+	size_t outbuf_len = round_up(buflen,
+			             crypto_shash_digestsize(sdesc->shash.tfm));
 
-	outbuf = kmalloc(buflen, GFP_KERNEL);
+	outbuf = kmalloc(outbuf_len, GFP_KERNEL);
 	if (!outbuf) {
 		ret = -ENOMEM;
 		goto err;
 	}
 
-	ret = kdf_ctr(sdesc, kbuf, kbuflen, outbuf, buflen, lzero);
+	ret = kdf_ctr(sdesc, kbuf, kbuflen, outbuf, outbuf_len, lzero);
 	if (ret)
 		goto err;
 
diff --git a/security/keys/proc.c b/security/keys/proc.c
index fbc4af5c6c9f..5af2934965d8 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -18,7 +18,6 @@
 #include <asm/errno.h>
 #include "internal.h"
 
-static int proc_keys_open(struct inode *inode, struct file *file);
 static void *proc_keys_start(struct seq_file *p, loff_t *_pos);
 static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos);
 static void proc_keys_stop(struct seq_file *p, void *v);
@@ -31,14 +30,6 @@ static const struct seq_operations proc_keys_ops = {
 	.show	= proc_keys_show,
 };
 
-static const struct file_operations proc_keys_fops = {
-	.open		= proc_keys_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static int proc_key_users_open(struct inode *inode, struct file *file);
 static void *proc_key_users_start(struct seq_file *p, loff_t *_pos);
 static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos);
 static void proc_key_users_stop(struct seq_file *p, void *v);
@@ -51,13 +42,6 @@ static const struct seq_operations proc_key_users_ops = {
 	.show	= proc_key_users_show,
 };
 
-static const struct file_operations proc_key_users_fops = {
-	.open		= proc_key_users_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 /*
  * Declare the /proc files.
  */
@@ -65,11 +49,11 @@ static int __init key_proc_init(void)
 {
 	struct proc_dir_entry *p;
 
-	p = proc_create("keys", 0, NULL, &proc_keys_fops);
+	p = proc_create_seq("keys", 0, NULL, &proc_keys_ops);
 	if (!p)
 		panic("Cannot create /proc/keys\n");
 
-	p = proc_create("key-users", 0, NULL, &proc_key_users_fops);
+	p = proc_create_seq("key-users", 0, NULL, &proc_key_users_ops);
 	if (!p)
 		panic("Cannot create /proc/key-users\n");
 
@@ -96,11 +80,6 @@ static struct rb_node *key_serial_next(struct seq_file *p, struct rb_node *n)
 	return n;
 }
 
-static int proc_keys_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &proc_keys_ops);
-}
-
 static struct key *find_ge_key(struct seq_file *p, key_serial_t id)
 {
 	struct user_namespace *user_ns = seq_user_ns(p);
@@ -293,15 +272,6 @@ static struct rb_node *key_user_first(struct user_namespace *user_ns, struct rb_
 	return __key_user_next(user_ns, n);
 }
 
-/*
- * Implement "/proc/key-users" to provides a list of the key users and their
- * quotas.
- */
-static int proc_key_users_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &proc_key_users_ops);
-}
-
 static void *proc_key_users_start(struct seq_file *p, loff_t *_pos)
 	__acquires(key_user_lock)
 {
diff --git a/security/security.c b/security/security.c
index 7bc2fde023a7..68f46d849abe 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1358,6 +1358,12 @@ int security_socket_post_create(struct socket *sock, int family,
 						protocol, kern);
 }
 
+int security_socket_socketpair(struct socket *socka, struct socket *sockb)
+{
+	return call_int_hook(socket_socketpair, 0, socka, sockb);
+}
+EXPORT_SYMBOL(security_socket_socketpair);
+
 int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen)
 {
 	return call_int_hook(socket_bind, 0, sock, address, addrlen);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4cafe6a19167..7df0f2ee1e88 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -274,11 +274,10 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
  * Try reloading inode security labels that have been marked as invalid.  The
  * @may_sleep parameter indicates when sleeping and thus reloading labels is
  * allowed; when set to false, returns -ECHILD when the label is
- * invalid.  The @opt_dentry parameter should be set to a dentry of the inode;
- * when no dentry is available, set it to NULL instead.
+ * invalid.  The @dentry parameter should be set to a dentry of the inode.
  */
 static int __inode_security_revalidate(struct inode *inode,
-				       struct dentry *opt_dentry,
+				       struct dentry *dentry,
 				       bool may_sleep)
 {
 	struct inode_security_struct *isec = inode->i_security;
@@ -295,7 +294,7 @@ static int __inode_security_revalidate(struct inode *inode,
 		 * @opt_dentry is NULL and no dentry for this inode can be
 		 * found; in that case, continue using the old label.
 		 */
-		inode_doinit_with_dentry(inode, opt_dentry);
+		inode_doinit_with_dentry(inode, dentry);
 	}
 	return 0;
 }
@@ -1568,8 +1567,15 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 			/* Called from d_instantiate or d_splice_alias. */
 			dentry = dget(opt_dentry);
 		} else {
-			/* Called from selinux_complete_init, try to find a dentry. */
+			/*
+			 * Called from selinux_complete_init, try to find a dentry.
+			 * Some filesystems really want a connected one, so try
+			 * that first.  We could split SECURITY_FS_USE_XATTR in
+			 * two, depending upon that...
+			 */
 			dentry = d_find_alias(inode);
+			if (!dentry)
+				dentry = d_find_any_alias(inode);
 		}
 		if (!dentry) {
 			/*
@@ -1674,14 +1680,19 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 		if ((sbsec->flags & SE_SBGENFS) && !S_ISLNK(inode->i_mode)) {
 			/* We must have a dentry to determine the label on
 			 * procfs inodes */
-			if (opt_dentry)
+			if (opt_dentry) {
 				/* Called from d_instantiate or
 				 * d_splice_alias. */
 				dentry = dget(opt_dentry);
-			else
+			} else {
 				/* Called from selinux_complete_init, try to
-				 * find a dentry. */
+				 * find a dentry.  Some filesystems really want
+				 * a connected one, so try that first.
+				 */
 				dentry = d_find_alias(inode);
+				if (!dentry)
+					dentry = d_find_any_alias(inode);
+			}
 			/*
 			 * This can be hit on boot when a file is accessed
 			 * before the policy is loaded.  When we load policy we
@@ -4569,6 +4580,18 @@ static int selinux_socket_post_create(struct socket *sock, int family,
 	return err;
 }
 
+static int selinux_socket_socketpair(struct socket *socka,
+				     struct socket *sockb)
+{
+	struct sk_security_struct *sksec_a = socka->sk->sk_security;
+	struct sk_security_struct *sksec_b = sockb->sk->sk_security;
+
+	sksec_a->peer_sid = sksec_b->sid;
+	sksec_b->peer_sid = sksec_a->sid;
+
+	return 0;
+}
+
 /* Range of port numbers used to automatically bind.
    Need to determine whether we should perform a name_bind
    permission check between the socket and the port number. */
@@ -4576,6 +4599,7 @@ static int selinux_socket_post_create(struct socket *sock, int family,
 static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen)
 {
 	struct sock *sk = sock->sk;
+	struct sk_security_struct *sksec = sk->sk_security;
 	u16 family;
 	int err;
 
@@ -4587,11 +4611,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 	family = sk->sk_family;
 	if (family == PF_INET || family == PF_INET6) {
 		char *addrp;
-		struct sk_security_struct *sksec = sk->sk_security;
 		struct common_audit_data ad;
 		struct lsm_network_audit net = {0,};
 		struct sockaddr_in *addr4 = NULL;
 		struct sockaddr_in6 *addr6 = NULL;
+		u16 family_sa = address->sa_family;
 		unsigned short snum;
 		u32 sid, node_perm;
 
@@ -4601,11 +4625,20 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 		 * need to check address->sa_family as it is possible to have
 		 * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET.
 		 */
-		switch (address->sa_family) {
+		switch (family_sa) {
+		case AF_UNSPEC:
 		case AF_INET:
 			if (addrlen < sizeof(struct sockaddr_in))
 				return -EINVAL;
 			addr4 = (struct sockaddr_in *)address;
+			if (family_sa == AF_UNSPEC) {
+				/* see __inet_bind(), we only want to allow
+				 * AF_UNSPEC if the address is INADDR_ANY
+				 */
+				if (addr4->sin_addr.s_addr != htonl(INADDR_ANY))
+					goto err_af;
+				family_sa = AF_INET;
+			}
 			snum = ntohs(addr4->sin_port);
 			addrp = (char *)&addr4->sin_addr.s_addr;
 			break;
@@ -4617,15 +4650,14 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 			addrp = (char *)&addr6->sin6_addr.s6_addr;
 			break;
 		default:
-			/* Note that SCTP services expect -EINVAL, whereas
-			 * others expect -EAFNOSUPPORT.
-			 */
-			if (sksec->sclass == SECCLASS_SCTP_SOCKET)
-				return -EINVAL;
-			else
-				return -EAFNOSUPPORT;
+			goto err_af;
 		}
 
+		ad.type = LSM_AUDIT_DATA_NET;
+		ad.u.net = &net;
+		ad.u.net->sport = htons(snum);
+		ad.u.net->family = family_sa;
+
 		if (snum) {
 			int low, high;
 
@@ -4637,10 +4669,6 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 						      snum, &sid);
 				if (err)
 					goto out;
-				ad.type = LSM_AUDIT_DATA_NET;
-				ad.u.net = &net;
-				ad.u.net->sport = htons(snum);
-				ad.u.net->family = family;
 				err = avc_has_perm(&selinux_state,
 						   sksec->sid, sid,
 						   sksec->sclass,
@@ -4672,16 +4700,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 			break;
 		}
 
-		err = sel_netnode_sid(addrp, family, &sid);
+		err = sel_netnode_sid(addrp, family_sa, &sid);
 		if (err)
 			goto out;
 
-		ad.type = LSM_AUDIT_DATA_NET;
-		ad.u.net = &net;
-		ad.u.net->sport = htons(snum);
-		ad.u.net->family = family;
-
-		if (address->sa_family == AF_INET)
+		if (family_sa == AF_INET)
 			ad.u.net->v4info.saddr = addr4->sin_addr.s_addr;
 		else
 			ad.u.net->v6info.saddr = addr6->sin6_addr;
@@ -4694,6 +4717,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 	}
 out:
 	return err;
+err_af:
+	/* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */
+	if (sksec->sclass == SECCLASS_SCTP_SOCKET)
+		return -EINVAL;
+	return -EAFNOSUPPORT;
 }
 
 /* This supports connect(2) and SCTP connect services such as sctp_connectx(3)
@@ -4771,7 +4799,7 @@ static int selinux_socket_connect_helper(struct socket *sock,
 		ad.type = LSM_AUDIT_DATA_NET;
 		ad.u.net = &net;
 		ad.u.net->dport = htons(snum);
-		ad.u.net->family = sk->sk_family;
+		ad.u.net->family = address->sa_family;
 		err = avc_has_perm(&selinux_state,
 				   sksec->sid, sid, sksec->sclass, perm, &ad);
 		if (err)
@@ -5272,6 +5300,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname,
 	while (walk_size < addrlen) {
 		addr = addr_buf;
 		switch (addr->sa_family) {
+		case AF_UNSPEC:
 		case AF_INET:
 			len = sizeof(struct sockaddr_in);
 			break;
@@ -5279,7 +5308,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname,
 			len = sizeof(struct sockaddr_in6);
 			break;
 		default:
-			return -EAFNOSUPPORT;
+			return -EINVAL;
 		}
 
 		err = -EINVAL;
@@ -6999,6 +7028,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 
 	LSM_HOOK_INIT(socket_create, selinux_socket_create),
 	LSM_HOOK_INIT(socket_post_create, selinux_socket_post_create),
+	LSM_HOOK_INIT(socket_socketpair, selinux_socket_socketpair),
 	LSM_HOOK_INIT(socket_bind, selinux_socket_bind),
 	LSM_HOOK_INIT(socket_connect, selinux_socket_connect),
 	LSM_HOOK_INIT(socket_listen, selinux_socket_listen),
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 8057e19dc15f..3ce225e3f142 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1494,7 +1494,7 @@ static int security_context_to_sid_core(struct selinux_state *state,
 				      scontext_len, &context, def_sid);
 	if (rc == -EINVAL && force) {
 		context.str = str;
-		context.len = scontext_len;
+		context.len = strlen(str) + 1;
 		str = NULL;
 	} else if (rc)
 		goto out_unlock;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 0b414836bebd..dcb976f98df2 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -2842,6 +2842,27 @@ static int smack_socket_post_create(struct socket *sock, int family,
 	return smack_netlabel(sock->sk, SMACK_CIPSO_SOCKET);
 }
 
+/**
+ * smack_socket_socketpair - create socket pair
+ * @socka: one socket
+ * @sockb: another socket
+ *
+ * Cross reference the peer labels for SO_PEERSEC
+ *
+ * Returns 0 on success, and error code otherwise
+ */
+static int smack_socket_socketpair(struct socket *socka,
+		                   struct socket *sockb)
+{
+	struct socket_smack *asp = socka->sk->sk_security;
+	struct socket_smack *bsp = sockb->sk->sk_security;
+
+	asp->smk_packet = bsp->smk_out;
+	bsp->smk_packet = asp->smk_out;
+
+	return 0;
+}
+
 #ifdef SMACK_IPV6_PORT_LABELING
 /**
  * smack_socket_bind - record port binding information.
@@ -4724,6 +4745,7 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(unix_may_send, smack_unix_may_send),
 
 	LSM_HOOK_INIT(socket_post_create, smack_socket_post_create),
+	LSM_HOOK_INIT(socket_socketpair, smack_socket_socketpair),
 #ifdef SMACK_IPV6_PORT_LABELING
 	LSM_HOOK_INIT(socket_bind, smack_socket_bind),
 #endif
diff --git a/sound/Kconfig b/sound/Kconfig
index 6833db9002ec..1140e9988fc5 100644
--- a/sound/Kconfig
+++ b/sound/Kconfig
@@ -96,6 +96,8 @@ source "sound/x86/Kconfig"
 
 source "sound/synth/Kconfig"
 
+source "sound/xen/Kconfig"
+
 endif # SND
 
 endif # !UML
diff --git a/sound/Makefile b/sound/Makefile
index 99d8c31262c8..797ecdcd35e2 100644
--- a/sound/Makefile
+++ b/sound/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_SOUND) += soundcore.o
 obj-$(CONFIG_DMASOUND) += oss/dmasound/
 obj-$(CONFIG_SND) += core/ i2c/ drivers/ isa/ pci/ ppc/ arm/ sh/ synth/ usb/ \
-	firewire/ sparc/ spi/ parisc/ pcmcia/ mips/ soc/ atmel/ hda/ x86/
+	firewire/ sparc/ spi/ parisc/ pcmcia/ mips/ soc/ atmel/ hda/ x86/ xen/
 obj-$(CONFIG_SND_AOA) += aoa/
 
 # This one must be compilable even if sound is configured out
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 4563432badba..4b01a37c836e 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -1001,7 +1001,7 @@ static int snd_compress_proc_init(struct snd_compr *compr)
 					   compr->card->proc_root);
 	if (!entry)
 		return -ENOMEM;
-	entry->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	entry->mode = S_IFDIR | 0555;
 	if (snd_info_register(entry) < 0) {
 		snd_info_free_entry(entry);
 		return -ENOMEM;
diff --git a/sound/core/control.c b/sound/core/control.c
index 69734b0eafd0..9aa15bfc7936 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1492,7 +1492,7 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file,
                              int op_flag)
 {
 	struct snd_ctl_tlv header;
-	unsigned int *container;
+	unsigned int __user *container;
 	unsigned int container_size;
 	struct snd_kcontrol *kctl;
 	struct snd_ctl_elem_id id;
diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c
index a848836a5de0..507fd5210c1c 100644
--- a/sound/core/control_compat.c
+++ b/sound/core/control_compat.c
@@ -396,8 +396,7 @@ static int snd_ctl_elem_add_compat(struct snd_ctl_file *file,
 	if (copy_from_user(&data->id, &data32->id, sizeof(data->id)) ||
 	    copy_from_user(&data->type, &data32->type, 3 * sizeof(u32)))
 		goto error;
-	if (get_user(data->owner, &data32->owner) ||
-	    get_user(data->type, &data32->type))
+	if (get_user(data->owner, &data32->owner))
 		goto error;
 	switch (data->type) {
 	case SNDRV_CTL_ELEM_TYPE_BOOLEAN:
diff --git a/sound/core/device.c b/sound/core/device.c
index cb0e46f66cc9..535102d564e3 100644
--- a/sound/core/device.c
+++ b/sound/core/device.c
@@ -240,6 +240,15 @@ void snd_device_free_all(struct snd_card *card)
 
 	if (snd_BUG_ON(!card))
 		return;
+	list_for_each_entry_safe_reverse(dev, next, &card->devices, list) {
+		/* exception: free ctl and lowlevel stuff later */
+		if (dev->type == SNDRV_DEV_CONTROL ||
+		    dev->type == SNDRV_DEV_LOWLEVEL)
+			continue;
+		__snd_device_free(dev);
+	}
+
+	/* free all */
 	list_for_each_entry_safe_reverse(dev, next, &card->devices, list)
 		__snd_device_free(dev);
 }
diff --git a/sound/core/info.c b/sound/core/info.c
index 4b36767af9e1..fe502bc5e6d2 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -454,7 +454,7 @@ static struct snd_info_entry *create_subdir(struct module *mod,
 	entry = snd_info_create_module_entry(mod, name, NULL);
 	if (!entry)
 		return NULL;
-	entry->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	entry->mode = S_IFDIR | 0555;
 	if (snd_info_register(entry) < 0) {
 		snd_info_free_entry(entry);
 		return NULL;
@@ -470,7 +470,7 @@ int __init snd_info_init(void)
 	snd_proc_root = snd_info_create_entry("asound", NULL);
 	if (!snd_proc_root)
 		return -ENOMEM;
-	snd_proc_root->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	snd_proc_root->mode = S_IFDIR | 0555;
 	snd_proc_root->p = proc_mkdir("asound", NULL);
 	if (!snd_proc_root->p)
 		goto error;
@@ -716,7 +716,7 @@ snd_info_create_entry(const char *name, struct snd_info_entry *parent)
 		kfree(entry);
 		return NULL;
 	}
-	entry->mode = S_IFREG | S_IRUGO;
+	entry->mode = S_IFREG | 0444;
 	entry->content = SNDRV_INFO_CONTENT_TEXT;
 	mutex_init(&entry->access);
 	INIT_LIST_HEAD(&entry->children);
diff --git a/sound/core/init.c b/sound/core/init.c
index 79b4df1c1dc7..4849c611c0fe 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -703,7 +703,7 @@ card_id_store_attr(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(id, S_IRUGO | S_IWUSR, card_id_show_attr, card_id_store_attr);
+static DEVICE_ATTR(id, 0644, card_id_show_attr, card_id_store_attr);
 
 static ssize_t
 card_number_show_attr(struct device *dev,
@@ -713,7 +713,7 @@ card_number_show_attr(struct device *dev,
 	return scnprintf(buf, PAGE_SIZE, "%i\n", card->number);
 }
 
-static DEVICE_ATTR(number, S_IRUGO, card_number_show_attr, NULL);
+static DEVICE_ATTR(number, 0444, card_number_show_attr, NULL);
 
 static struct attribute *card_dev_attrs[] = {
 	&dev_attr_id.attr,
diff --git a/sound/core/oss/mixer_oss.c b/sound/core/oss/mixer_oss.c
index 379bf486ccc7..64d904bee8bb 100644
--- a/sound/core/oss/mixer_oss.c
+++ b/sound/core/oss/mixer_oss.c
@@ -1247,7 +1247,7 @@ static void snd_mixer_oss_proc_init(struct snd_mixer_oss *mixer)
 	if (! entry)
 		return;
 	entry->content = SNDRV_INFO_CONTENT_TEXT;
-	entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+	entry->mode = S_IFREG | 0644;
 	entry->c.text.read = snd_mixer_oss_proc_read;
 	entry->c.text.write = snd_mixer_oss_proc_write;
 	entry->private_data = mixer;
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 1980f68246cb..905a53c1cde5 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -3045,7 +3045,7 @@ static void snd_pcm_oss_proc_init(struct snd_pcm *pcm)
 			continue;
 		if ((entry = snd_info_create_card_entry(pcm->card, "oss", pstr->proc_root)) != NULL) {
 			entry->content = SNDRV_INFO_CONTENT_TEXT;
-			entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+			entry->mode = S_IFREG | 0644;
 			entry->c.text.read = snd_pcm_oss_proc_read;
 			entry->c.text.write = snd_pcm_oss_proc_write;
 			entry->private_data = pstr;
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 66ac89aad681..c352bfb973cc 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -530,7 +530,7 @@ static int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr)
 					   pcm->card->proc_root);
 	if (!entry)
 		return -ENOMEM;
-	entry->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	entry->mode = S_IFDIR | 0555;
 	if (snd_info_register(entry) < 0) {
 		snd_info_free_entry(entry);
 		return -ENOMEM;
@@ -552,7 +552,7 @@ static int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr)
 	if (entry) {
 		entry->c.text.read = snd_pcm_xrun_debug_read;
 		entry->c.text.write = snd_pcm_xrun_debug_write;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 		entry->private_data = pstr;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
@@ -590,7 +590,7 @@ static int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream)
 					   substream->pstr->proc_root);
 	if (!entry)
 		return -ENOMEM;
-	entry->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	entry->mode = S_IFDIR | 0555;
 	if (snd_info_register(entry) < 0) {
 		snd_info_free_entry(entry);
 		return -ENOMEM;
@@ -647,7 +647,7 @@ static int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream)
 		entry->private_data = substream;
 		entry->c.text.read = NULL;
 		entry->c.text.write = snd_pcm_xrun_injection_write;
-		entry->mode = S_IFREG | S_IWUSR;
+		entry->mode = S_IFREG | 0200;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
 			entry = NULL;
@@ -1087,7 +1087,7 @@ static ssize_t show_pcm_class(struct device *dev,
         return snprintf(buf, PAGE_SIZE, "%s\n", str);
 }
 
-static DEVICE_ATTR(pcm_class, S_IRUGO, show_pcm_class, NULL);
+static DEVICE_ATTR(pcm_class, 0444, show_pcm_class, NULL);
 static struct attribute *pcm_dev_attrs[] = {
 	&dev_attr_pcm_class.attr,
 	NULL
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index b719d0bd833e..39d853bfa5ac 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -27,10 +27,11 @@ static int snd_pcm_ioctl_delay_compat(struct snd_pcm_substream *substream,
 				      s32 __user *src)
 {
 	snd_pcm_sframes_t delay;
+	int err;
 
-	delay = snd_pcm_delay(substream);
-	if (delay < 0)
-		return delay;
+	err = snd_pcm_delay(substream, &delay);
+	if (err)
+		return err;
 	if (put_user(delay, src))
 		return -EFAULT;
 	return 0;
@@ -44,10 +45,7 @@ static int snd_pcm_ioctl_rewind_compat(struct snd_pcm_substream *substream,
 
 	if (get_user(frames, src))
 		return -EFAULT;
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		err = snd_pcm_playback_rewind(substream, frames);
-	else
-		err = snd_pcm_capture_rewind(substream, frames);
+	err = snd_pcm_rewind(substream, frames);
 	if (put_user(err, src))
 		return -EFAULT;
 	return err < 0 ? err : 0;
@@ -61,10 +59,7 @@ static int snd_pcm_ioctl_forward_compat(struct snd_pcm_substream *substream,
 
 	if (get_user(frames, src))
 		return -EFAULT;
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		err = snd_pcm_playback_forward(substream, frames);
-	else
-		err = snd_pcm_capture_forward(substream, frames);
+	err = snd_pcm_forward(substream, frames);
 	if (put_user(err, src))
 		return -EFAULT;
 	return err < 0 ? err : 0;
@@ -422,6 +417,8 @@ static int snd_pcm_ioctl_xfern_compat(struct snd_pcm_substream *substream,
 		return -ENOTTY;
 	if (substream->stream != dir)
 		return -EINVAL;
+	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN)
+		return -EBADFD;
 
 	if ((ch = substream->runtime->channels) > 128)
 		return -EINVAL;
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index f4a19509cccf..44b5ae833082 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -191,10 +191,7 @@ int snd_pcm_update_state(struct snd_pcm_substream *substream,
 {
 	snd_pcm_uframes_t avail;
 
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		avail = snd_pcm_playback_avail(runtime);
-	else
-		avail = snd_pcm_capture_avail(runtime);
+	avail = snd_pcm_avail(substream);
 	if (avail > runtime->avail_max)
 		runtime->avail_max = avail;
 	if (runtime->status->state == SNDRV_PCM_STATE_DRAINING) {
@@ -1856,10 +1853,7 @@ static int wait_for_avail(struct snd_pcm_substream *substream,
 		 * This check must happen after been added to the waitqueue
 		 * and having current state be INTERRUPTIBLE.
 		 */
-		if (is_playback)
-			avail = snd_pcm_playback_avail(runtime);
-		else
-			avail = snd_pcm_capture_avail(runtime);
+		avail = snd_pcm_avail(substream);
 		if (avail >= runtime->twake)
 			break;
 		snd_pcm_stream_unlock_irq(substream);
@@ -2175,10 +2169,7 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream,
 	runtime->twake = runtime->control->avail_min ? : 1;
 	if (runtime->status->state == SNDRV_PCM_STATE_RUNNING)
 		snd_pcm_update_hw_ptr(substream);
-	if (is_playback)
-		avail = snd_pcm_playback_avail(runtime);
-	else
-		avail = snd_pcm_capture_avail(runtime);
+	avail = snd_pcm_avail(substream);
 	while (size > 0) {
 		snd_pcm_uframes_t frames, appl_ptr, appl_ofs;
 		snd_pcm_uframes_t cont;
diff --git a/sound/core/pcm_local.h b/sound/core/pcm_local.h
index 16f254732b2a..7a499d02df6c 100644
--- a/sound/core/pcm_local.h
+++ b/sound/core/pcm_local.h
@@ -36,6 +36,24 @@ int snd_pcm_update_hw_ptr(struct snd_pcm_substream *substream);
 void snd_pcm_playback_silence(struct snd_pcm_substream *substream,
 			      snd_pcm_uframes_t new_hw_ptr);
 
+static inline snd_pcm_uframes_t
+snd_pcm_avail(struct snd_pcm_substream *substream)
+{
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		return snd_pcm_playback_avail(substream->runtime);
+	else
+		return snd_pcm_capture_avail(substream->runtime);
+}
+
+static inline snd_pcm_uframes_t
+snd_pcm_hw_avail(struct snd_pcm_substream *substream)
+{
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		return snd_pcm_playback_hw_avail(substream->runtime);
+	else
+		return snd_pcm_capture_hw_avail(substream->runtime);
+}
+
 #ifdef CONFIG_SND_PCM_TIMER
 void snd_pcm_timer_resolution_change(struct snd_pcm_substream *substream);
 void snd_pcm_timer_init(struct snd_pcm_substream *substream);
diff --git a/sound/core/pcm_memory.c b/sound/core/pcm_memory.c
index ae33e456708c..4b5356a10315 100644
--- a/sound/core/pcm_memory.c
+++ b/sound/core/pcm_memory.c
@@ -201,7 +201,7 @@ static inline void preallocate_info_init(struct snd_pcm_substream *substream)
 	if ((entry = snd_info_create_card_entry(substream->pcm->card, "prealloc", substream->proc_root)) != NULL) {
 		entry->c.text.read = snd_pcm_lib_preallocate_proc_read;
 		entry->c.text.write = snd_pcm_lib_preallocate_proc_write;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 		entry->private_data = substream;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 35ffccea94c3..04c6301394d0 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -99,6 +99,57 @@ static inline void down_write_nonblock(struct rw_semaphore *lock)
 		cond_resched();
 }
 
+#define PCM_LOCK_DEFAULT	0
+#define PCM_LOCK_IRQ	1
+#define PCM_LOCK_IRQSAVE	2
+
+static unsigned long __snd_pcm_stream_lock_mode(struct snd_pcm_substream *substream,
+						unsigned int mode)
+{
+	unsigned long flags = 0;
+	if (substream->pcm->nonatomic) {
+		down_read_nested(&snd_pcm_link_rwsem, SINGLE_DEPTH_NESTING);
+		mutex_lock(&substream->self_group.mutex);
+	} else {
+		switch (mode) {
+		case PCM_LOCK_DEFAULT:
+			read_lock(&snd_pcm_link_rwlock);
+			break;
+		case PCM_LOCK_IRQ:
+			read_lock_irq(&snd_pcm_link_rwlock);
+			break;
+		case PCM_LOCK_IRQSAVE:
+			read_lock_irqsave(&snd_pcm_link_rwlock, flags);
+			break;
+		}
+		spin_lock(&substream->self_group.lock);
+	}
+	return flags;
+}
+
+static void __snd_pcm_stream_unlock_mode(struct snd_pcm_substream *substream,
+					 unsigned int mode, unsigned long flags)
+{
+	if (substream->pcm->nonatomic) {
+		mutex_unlock(&substream->self_group.mutex);
+		up_read(&snd_pcm_link_rwsem);
+	} else {
+		spin_unlock(&substream->self_group.lock);
+
+		switch (mode) {
+		case PCM_LOCK_DEFAULT:
+			read_unlock(&snd_pcm_link_rwlock);
+			break;
+		case PCM_LOCK_IRQ:
+			read_unlock_irq(&snd_pcm_link_rwlock);
+			break;
+		case PCM_LOCK_IRQSAVE:
+			read_unlock_irqrestore(&snd_pcm_link_rwlock, flags);
+			break;
+		}
+	}
+}
+
 /**
  * snd_pcm_stream_lock - Lock the PCM stream
  * @substream: PCM substream
@@ -109,13 +160,7 @@ static inline void down_write_nonblock(struct rw_semaphore *lock)
  */
 void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
 {
-	if (substream->pcm->nonatomic) {
-		down_read_nested(&snd_pcm_link_rwsem, SINGLE_DEPTH_NESTING);
-		mutex_lock(&substream->self_group.mutex);
-	} else {
-		read_lock(&snd_pcm_link_rwlock);
-		spin_lock(&substream->self_group.lock);
-	}
+	__snd_pcm_stream_lock_mode(substream, PCM_LOCK_DEFAULT);
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_lock);
 
@@ -127,13 +172,7 @@ EXPORT_SYMBOL_GPL(snd_pcm_stream_lock);
  */
 void snd_pcm_stream_unlock(struct snd_pcm_substream *substream)
 {
-	if (substream->pcm->nonatomic) {
-		mutex_unlock(&substream->self_group.mutex);
-		up_read(&snd_pcm_link_rwsem);
-	} else {
-		spin_unlock(&substream->self_group.lock);
-		read_unlock(&snd_pcm_link_rwlock);
-	}
+	__snd_pcm_stream_unlock_mode(substream, PCM_LOCK_DEFAULT, 0);
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock);
 
@@ -147,9 +186,7 @@ EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock);
  */
 void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
 {
-	if (!substream->pcm->nonatomic)
-		local_irq_disable();
-	snd_pcm_stream_lock(substream);
+	__snd_pcm_stream_lock_mode(substream, PCM_LOCK_IRQ);
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq);
 
@@ -161,19 +198,13 @@ EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq);
  */
 void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
 {
-	snd_pcm_stream_unlock(substream);
-	if (!substream->pcm->nonatomic)
-		local_irq_enable();
+	__snd_pcm_stream_unlock_mode(substream, PCM_LOCK_IRQ, 0);
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq);
 
 unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream)
 {
-	unsigned long flags = 0;
-	if (!substream->pcm->nonatomic)
-		local_irq_save(flags);
-	snd_pcm_stream_lock(substream);
-	return flags;
+	return __snd_pcm_stream_lock_mode(substream, PCM_LOCK_IRQSAVE);
 }
 EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave);
 
@@ -187,9 +218,7 @@ EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave);
 void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
 				      unsigned long flags)
 {
-	snd_pcm_stream_unlock(substream);
-	if (!substream->pcm->nonatomic)
-		local_irq_restore(flags);
+	__snd_pcm_stream_unlock_mode(substream, PCM_LOCK_IRQSAVE, flags);
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore);
 
@@ -857,6 +886,18 @@ static int snd_pcm_sw_params_user(struct snd_pcm_substream *substream,
 	return err;
 }
 
+static inline snd_pcm_uframes_t
+snd_pcm_calc_delay(struct snd_pcm_substream *substream)
+{
+	snd_pcm_uframes_t delay;
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		delay = snd_pcm_playback_hw_avail(substream->runtime);
+	else
+		delay = snd_pcm_capture_avail(substream->runtime);
+	return delay + substream->runtime->delay;
+}
+
 int snd_pcm_status(struct snd_pcm_substream *substream,
 		   struct snd_pcm_status *status)
 {
@@ -908,21 +949,9 @@ int snd_pcm_status(struct snd_pcm_substream *substream,
  _tstamp_end:
 	status->appl_ptr = runtime->control->appl_ptr;
 	status->hw_ptr = runtime->status->hw_ptr;
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		status->avail = snd_pcm_playback_avail(runtime);
-		if (runtime->status->state == SNDRV_PCM_STATE_RUNNING ||
-		    runtime->status->state == SNDRV_PCM_STATE_DRAINING) {
-			status->delay = runtime->buffer_size - status->avail;
-			status->delay += runtime->delay;
-		} else
-			status->delay = 0;
-	} else {
-		status->avail = snd_pcm_capture_avail(runtime);
-		if (runtime->status->state == SNDRV_PCM_STATE_RUNNING)
-			status->delay = status->avail + runtime->delay;
-		else
-			status->delay = 0;
-	}
+	status->avail = snd_pcm_avail(substream);
+	status->delay = snd_pcm_running(substream) ?
+		snd_pcm_calc_delay(substream) : 0;
 	status->avail_max = runtime->avail_max;
 	status->overrange = runtime->overrange;
 	runtime->avail_max = 0;
@@ -2610,10 +2639,9 @@ static snd_pcm_sframes_t rewind_appl_ptr(struct snd_pcm_substream *substream,
 	return ret < 0 ? 0 : frames;
 }
 
-static snd_pcm_sframes_t snd_pcm_playback_rewind(struct snd_pcm_substream *substream,
-						 snd_pcm_uframes_t frames)
+static snd_pcm_sframes_t snd_pcm_rewind(struct snd_pcm_substream *substream,
+					snd_pcm_uframes_t frames)
 {
-	struct snd_pcm_runtime *runtime = substream->runtime;
 	snd_pcm_sframes_t ret;
 
 	if (frames == 0)
@@ -2623,51 +2651,14 @@ static snd_pcm_sframes_t snd_pcm_playback_rewind(struct snd_pcm_substream *subst
 	ret = do_pcm_hwsync(substream);
 	if (!ret)
 		ret = rewind_appl_ptr(substream, frames,
-				      snd_pcm_playback_hw_avail(runtime));
+				      snd_pcm_hw_avail(substream));
 	snd_pcm_stream_unlock_irq(substream);
 	return ret;
 }
 
-static snd_pcm_sframes_t snd_pcm_capture_rewind(struct snd_pcm_substream *substream,
-						snd_pcm_uframes_t frames)
+static snd_pcm_sframes_t snd_pcm_forward(struct snd_pcm_substream *substream,
+					 snd_pcm_uframes_t frames)
 {
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	snd_pcm_sframes_t ret;
-
-	if (frames == 0)
-		return 0;
-
-	snd_pcm_stream_lock_irq(substream);
-	ret = do_pcm_hwsync(substream);
-	if (!ret)
-		ret = rewind_appl_ptr(substream, frames,
-				      snd_pcm_capture_hw_avail(runtime));
-	snd_pcm_stream_unlock_irq(substream);
-	return ret;
-}
-
-static snd_pcm_sframes_t snd_pcm_playback_forward(struct snd_pcm_substream *substream,
-						  snd_pcm_uframes_t frames)
-{
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	snd_pcm_sframes_t ret;
-
-	if (frames == 0)
-		return 0;
-
-	snd_pcm_stream_lock_irq(substream);
-	ret = do_pcm_hwsync(substream);
-	if (!ret)
-		ret = forward_appl_ptr(substream, frames,
-				       snd_pcm_playback_avail(runtime));
-	snd_pcm_stream_unlock_irq(substream);
-	return ret;
-}
-
-static snd_pcm_sframes_t snd_pcm_capture_forward(struct snd_pcm_substream *substream,
-						 snd_pcm_uframes_t frames)
-{
-	struct snd_pcm_runtime *runtime = substream->runtime;
 	snd_pcm_sframes_t ret;
 
 	if (frames == 0)
@@ -2677,7 +2668,7 @@ static snd_pcm_sframes_t snd_pcm_capture_forward(struct snd_pcm_substream *subst
 	ret = do_pcm_hwsync(substream);
 	if (!ret)
 		ret = forward_appl_ptr(substream, frames,
-				       snd_pcm_capture_avail(runtime));
+				       snd_pcm_avail(substream));
 	snd_pcm_stream_unlock_irq(substream);
 	return ret;
 }
@@ -2692,23 +2683,20 @@ static int snd_pcm_hwsync(struct snd_pcm_substream *substream)
 	return err;
 }
 		
-static snd_pcm_sframes_t snd_pcm_delay(struct snd_pcm_substream *substream)
+static int snd_pcm_delay(struct snd_pcm_substream *substream,
+			 snd_pcm_sframes_t *delay)
 {
-	struct snd_pcm_runtime *runtime = substream->runtime;
 	int err;
 	snd_pcm_sframes_t n = 0;
 
 	snd_pcm_stream_lock_irq(substream);
 	err = do_pcm_hwsync(substream);
-	if (!err) {
-		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-			n = snd_pcm_playback_hw_avail(runtime);
-		else
-			n = snd_pcm_capture_avail(runtime);
-		n += runtime->delay;
-	}
+	if (!err)
+		n = snd_pcm_calc_delay(substream);
 	snd_pcm_stream_unlock_irq(substream);
-	return err < 0 ? err : n;
+	if (!err)
+		*delay = n;
+	return err;
 }
 		
 static int snd_pcm_sync_ptr(struct snd_pcm_substream *substream,
@@ -2751,6 +2739,7 @@ static int snd_pcm_sync_ptr(struct snd_pcm_substream *substream,
 	sync_ptr.s.status.hw_ptr = status->hw_ptr;
 	sync_ptr.s.status.tstamp = status->tstamp;
 	sync_ptr.s.status.suspended_state = status->suspended_state;
+	sync_ptr.s.status.audio_tstamp = status->audio_tstamp;
 	snd_pcm_stream_unlock_irq(substream);
 	if (copy_to_user(_sync_ptr, &sync_ptr, sizeof(sync_ptr)))
 		return -EFAULT;
@@ -2830,10 +2819,7 @@ static int snd_pcm_rewind_ioctl(struct snd_pcm_substream *substream,
 		return -EFAULT;
 	if (put_user(0, _frames))
 		return -EFAULT;
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		result = snd_pcm_playback_rewind(substream, frames);
-	else
-		result = snd_pcm_capture_rewind(substream, frames);
+	result = snd_pcm_rewind(substream, frames);
 	__put_user(result, _frames);
 	return result < 0 ? result : 0;
 }
@@ -2848,10 +2834,7 @@ static int snd_pcm_forward_ioctl(struct snd_pcm_substream *substream,
 		return -EFAULT;
 	if (put_user(0, _frames))
 		return -EFAULT;
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		result = snd_pcm_playback_forward(substream, frames);
-	else
-		result = snd_pcm_capture_forward(substream, frames);
+	result = snd_pcm_forward(substream, frames);
 	__put_user(result, _frames);
 	return result < 0 ? result : 0;
 }
@@ -2916,11 +2899,13 @@ static int snd_pcm_common_ioctl(struct file *file,
 		return snd_pcm_hwsync(substream);
 	case SNDRV_PCM_IOCTL_DELAY:
 	{
-		snd_pcm_sframes_t delay = snd_pcm_delay(substream);
+		snd_pcm_sframes_t delay;
 		snd_pcm_sframes_t __user *res = arg;
+		int err;
 
-		if (delay < 0)
-			return delay;
+		err = snd_pcm_delay(substream, &delay);
+		if (err)
+			return err;
 		if (put_user(delay, res))
 			return -EFAULT;
 		return 0;
@@ -2992,7 +2977,7 @@ int snd_pcm_kernel_ioctl(struct snd_pcm_substream *substream,
 		/* provided only for OSS; capture-only and no value returned */
 		if (substream->stream != SNDRV_PCM_STREAM_CAPTURE)
 			return -EINVAL;
-		result = snd_pcm_capture_forward(substream, *frames);
+		result = snd_pcm_forward(substream, *frames);
 		return result < 0 ? result : 0;
 	}
 	case SNDRV_PCM_IOCTL_HW_PARAMS:
@@ -3008,13 +2993,7 @@ int snd_pcm_kernel_ioctl(struct snd_pcm_substream *substream,
 	case SNDRV_PCM_IOCTL_DROP:
 		return snd_pcm_drop(substream);
 	case SNDRV_PCM_IOCTL_DELAY:
-	{
-		result = snd_pcm_delay(substream);
-		if (result < 0)
-			return result;
-		*frames = result;
-		return 0;
-	}
+		return snd_pcm_delay(substream, frames);
 	default:
 		return -EINVAL;
 	}
@@ -3140,82 +3119,46 @@ static ssize_t snd_pcm_writev(struct kiocb *iocb, struct iov_iter *from)
 	return result;
 }
 
-static __poll_t snd_pcm_playback_poll(struct file *file, poll_table * wait)
+static __poll_t snd_pcm_poll(struct file *file, poll_table *wait)
 {
 	struct snd_pcm_file *pcm_file;
 	struct snd_pcm_substream *substream;
 	struct snd_pcm_runtime *runtime;
-        __poll_t mask;
+	__poll_t mask, ok;
 	snd_pcm_uframes_t avail;
 
 	pcm_file = file->private_data;
 
 	substream = pcm_file->substream;
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		ok = EPOLLOUT | EPOLLWRNORM;
+	else
+		ok = EPOLLIN | EPOLLRDNORM;
 	if (PCM_RUNTIME_CHECK(substream))
-		return EPOLLOUT | EPOLLWRNORM | EPOLLERR;
-	runtime = substream->runtime;
+		return ok | EPOLLERR;
 
-	poll_wait(file, &runtime->sleep, wait);
-
-	snd_pcm_stream_lock_irq(substream);
-	avail = snd_pcm_playback_avail(runtime);
-	switch (runtime->status->state) {
-	case SNDRV_PCM_STATE_RUNNING:
-	case SNDRV_PCM_STATE_PREPARED:
-	case SNDRV_PCM_STATE_PAUSED:
-		if (avail >= runtime->control->avail_min) {
-			mask = EPOLLOUT | EPOLLWRNORM;
-			break;
-		}
-		/* Fall through */
-	case SNDRV_PCM_STATE_DRAINING:
-		mask = 0;
-		break;
-	default:
-		mask = EPOLLOUT | EPOLLWRNORM | EPOLLERR;
-		break;
-	}
-	snd_pcm_stream_unlock_irq(substream);
-	return mask;
-}
-
-static __poll_t snd_pcm_capture_poll(struct file *file, poll_table * wait)
-{
-	struct snd_pcm_file *pcm_file;
-	struct snd_pcm_substream *substream;
-	struct snd_pcm_runtime *runtime;
-        __poll_t mask;
-	snd_pcm_uframes_t avail;
-
-	pcm_file = file->private_data;
-
-	substream = pcm_file->substream;
-	if (PCM_RUNTIME_CHECK(substream))
-		return EPOLLIN | EPOLLRDNORM | EPOLLERR;
 	runtime = substream->runtime;
-
 	poll_wait(file, &runtime->sleep, wait);
 
+	mask = 0;
 	snd_pcm_stream_lock_irq(substream);
-	avail = snd_pcm_capture_avail(runtime);
+	avail = snd_pcm_avail(substream);
 	switch (runtime->status->state) {
 	case SNDRV_PCM_STATE_RUNNING:
 	case SNDRV_PCM_STATE_PREPARED:
 	case SNDRV_PCM_STATE_PAUSED:
-		if (avail >= runtime->control->avail_min) {
-			mask = EPOLLIN | EPOLLRDNORM;
-			break;
-		}
-		mask = 0;
+		if (avail >= runtime->control->avail_min)
+			mask = ok;
 		break;
 	case SNDRV_PCM_STATE_DRAINING:
-		if (avail > 0) {
-			mask = EPOLLIN | EPOLLRDNORM;
-			break;
+		if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+			mask = ok;
+			if (!avail)
+				mask |= EPOLLERR;
 		}
-		/* Fall through */
+		break;
 	default:
-		mask = EPOLLIN | EPOLLRDNORM | EPOLLERR;
+		mask = ok | EPOLLERR;
 		break;
 	}
 	snd_pcm_stream_unlock_irq(substream);
@@ -3234,7 +3177,7 @@ static __poll_t snd_pcm_capture_poll(struct file *file, poll_table * wait)
 /*
  * mmap status record
  */
-static int snd_pcm_mmap_status_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_status_fault(struct vm_fault *vmf)
 {
 	struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
 	struct snd_pcm_runtime *runtime;
@@ -3270,7 +3213,7 @@ static int snd_pcm_mmap_status(struct snd_pcm_substream *substream, struct file
 /*
  * mmap control record
  */
-static int snd_pcm_mmap_control_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_control_fault(struct vm_fault *vmf)
 {
 	struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
 	struct snd_pcm_runtime *runtime;
@@ -3359,7 +3302,7 @@ snd_pcm_default_page_ops(struct snd_pcm_substream *substream, unsigned long ofs)
 /*
  * fault callback for mmapping a RAM page
  */
-static int snd_pcm_mmap_data_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_data_fault(struct vm_fault *vmf)
 {
 	struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
 	struct snd_pcm_runtime *runtime;
@@ -3707,7 +3650,7 @@ const struct file_operations snd_pcm_f_ops[2] = {
 		.open =			snd_pcm_playback_open,
 		.release =		snd_pcm_release,
 		.llseek =		no_llseek,
-		.poll =			snd_pcm_playback_poll,
+		.poll =			snd_pcm_poll,
 		.unlocked_ioctl =	snd_pcm_ioctl,
 		.compat_ioctl = 	snd_pcm_ioctl_compat,
 		.mmap =			snd_pcm_mmap,
@@ -3721,7 +3664,7 @@ const struct file_operations snd_pcm_f_ops[2] = {
 		.open =			snd_pcm_capture_open,
 		.release =		snd_pcm_release,
 		.llseek =		no_llseek,
-		.poll =			snd_pcm_capture_poll,
+		.poll =			snd_pcm_poll,
 		.unlocked_ioctl =	snd_pcm_ioctl,
 		.compat_ioctl = 	snd_pcm_ioctl_compat,
 		.mmap =			snd_pcm_mmap,
diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c
index f69764d7cdd7..e30e30ba6e39 100644
--- a/sound/core/rawmidi_compat.c
+++ b/sound/core/rawmidi_compat.c
@@ -36,8 +36,6 @@ static int snd_rawmidi_ioctl_params_compat(struct snd_rawmidi_file *rfile,
 	struct snd_rawmidi_params params;
 	unsigned int val;
 
-	if (rfile->output == NULL)
-		return -EINVAL;
 	if (get_user(params.stream, &src->stream) ||
 	    get_user(params.buffer_size, &src->buffer_size) ||
 	    get_user(params.avail_min, &src->avail_min) ||
@@ -46,8 +44,12 @@ static int snd_rawmidi_ioctl_params_compat(struct snd_rawmidi_file *rfile,
 	params.no_active_sensing = val;
 	switch (params.stream) {
 	case SNDRV_RAWMIDI_STREAM_OUTPUT:
+		if (!rfile->output)
+			return -EINVAL;
 		return snd_rawmidi_output_params(rfile->output, &params);
 	case SNDRV_RAWMIDI_STREAM_INPUT:
+		if (!rfile->input)
+			return -EINVAL;
 		return snd_rawmidi_input_params(rfile->input, &params);
 	}
 	return -EINVAL;
@@ -67,16 +69,18 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile,
 	int err;
 	struct snd_rawmidi_status status;
 
-	if (rfile->output == NULL)
-		return -EINVAL;
 	if (get_user(status.stream, &src->stream))
 		return -EFAULT;
 
 	switch (status.stream) {
 	case SNDRV_RAWMIDI_STREAM_OUTPUT:
+		if (!rfile->output)
+			return -EINVAL;
 		err = snd_rawmidi_output_status(rfile->output, &status);
 		break;
 	case SNDRV_RAWMIDI_STREAM_INPUT:
+		if (!rfile->input)
+			return -EINVAL;
 		err = snd_rawmidi_input_status(rfile->input, &status);
 		break;
 	default:
@@ -112,16 +116,18 @@ static int snd_rawmidi_ioctl_status_x32(struct snd_rawmidi_file *rfile,
 	int err;
 	struct snd_rawmidi_status status;
 
-	if (rfile->output == NULL)
-		return -EINVAL;
 	if (get_user(status.stream, &src->stream))
 		return -EFAULT;
 
 	switch (status.stream) {
 	case SNDRV_RAWMIDI_STREAM_OUTPUT:
+		if (!rfile->output)
+			return -EINVAL;
 		err = snd_rawmidi_output_status(rfile->output, &status);
 		break;
 	case SNDRV_RAWMIDI_STREAM_INPUT:
+		if (!rfile->input)
+			return -EINVAL;
 		err = snd_rawmidi_input_status(rfile->input, &status);
 		break;
 	default:
diff --git a/sound/core/seq/oss/seq_oss_event.c b/sound/core/seq/oss/seq_oss_event.c
index c3908862bc8b..86ca584c27b2 100644
--- a/sound/core/seq/oss/seq_oss_event.c
+++ b/sound/core/seq/oss/seq_oss_event.c
@@ -26,6 +26,7 @@
 #include <sound/seq_oss_legacy.h>
 #include "seq_oss_readq.h"
 #include "seq_oss_writeq.h"
+#include <linux/nospec.h>
 
 
 /*
@@ -287,10 +288,10 @@ note_on_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, st
 {
 	struct seq_oss_synthinfo *info;
 
-	if (!snd_seq_oss_synth_is_valid(dp, dev))
+	info = snd_seq_oss_synth_info(dp, dev);
+	if (!info)
 		return -ENXIO;
 
-	info = &dp->synths[dev];
 	switch (info->arg.event_passing) {
 	case SNDRV_SEQ_OSS_PROCESS_EVENTS:
 		if (! info->ch || ch < 0 || ch >= info->nr_voices) {
@@ -298,6 +299,7 @@ note_on_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, st
 			return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev);
 		}
 
+		ch = array_index_nospec(ch, info->nr_voices);
 		if (note == 255 && info->ch[ch].note >= 0) {
 			/* volume control */
 			int type;
@@ -347,10 +349,10 @@ note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, s
 {
 	struct seq_oss_synthinfo *info;
 
-	if (!snd_seq_oss_synth_is_valid(dp, dev))
+	info = snd_seq_oss_synth_info(dp, dev);
+	if (!info)
 		return -ENXIO;
 
-	info = &dp->synths[dev];
 	switch (info->arg.event_passing) {
 	case SNDRV_SEQ_OSS_PROCESS_EVENTS:
 		if (! info->ch || ch < 0 || ch >= info->nr_voices) {
@@ -358,6 +360,7 @@ note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, s
 			return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev);
 		}
 
+		ch = array_index_nospec(ch, info->nr_voices);
 		if (info->ch[ch].note >= 0) {
 			note = info->ch[ch].note;
 			info->ch[ch].vel = 0;
@@ -381,7 +384,7 @@ note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, s
 static int
 set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note, int vel, struct snd_seq_event *ev)
 {
-	if (! snd_seq_oss_synth_is_valid(dp, dev))
+	if (!snd_seq_oss_synth_info(dp, dev))
 		return -ENXIO;
 	
 	ev->type = type;
@@ -399,7 +402,7 @@ set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note,
 static int
 set_control_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int param, int val, struct snd_seq_event *ev)
 {
-	if (! snd_seq_oss_synth_is_valid(dp, dev))
+	if (!snd_seq_oss_synth_info(dp, dev))
 		return -ENXIO;
 	
 	ev->type = type;
diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c
index b30b2139e3f0..9debd1b8fd28 100644
--- a/sound/core/seq/oss/seq_oss_midi.c
+++ b/sound/core/seq/oss/seq_oss_midi.c
@@ -29,6 +29,7 @@
 #include "../seq_lock.h"
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/nospec.h>
 
 
 /*
@@ -315,6 +316,7 @@ get_mididev(struct seq_oss_devinfo *dp, int dev)
 {
 	if (dev < 0 || dev >= dp->max_mididev)
 		return NULL;
+	dev = array_index_nospec(dev, dp->max_mididev);
 	return get_mdev(dev);
 }
 
diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c
index cd0e0ebbfdb1..278ebb993122 100644
--- a/sound/core/seq/oss/seq_oss_synth.c
+++ b/sound/core/seq/oss/seq_oss_synth.c
@@ -26,6 +26,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/nospec.h>
 
 /*
  * constants
@@ -339,17 +340,13 @@ snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp)
 	dp->max_synthdev = 0;
 }
 
-/*
- * check if the specified device is MIDI mapped device
- */
-static int
-is_midi_dev(struct seq_oss_devinfo *dp, int dev)
+static struct seq_oss_synthinfo *
+get_synthinfo_nospec(struct seq_oss_devinfo *dp, int dev)
 {
 	if (dev < 0 || dev >= dp->max_synthdev)
-		return 0;
-	if (dp->synths[dev].is_midi)
-		return 1;
-	return 0;
+		return NULL;
+	dev = array_index_nospec(dev, SNDRV_SEQ_OSS_MAX_SYNTH_DEVS);
+	return &dp->synths[dev];
 }
 
 /*
@@ -359,14 +356,20 @@ static struct seq_oss_synth *
 get_synthdev(struct seq_oss_devinfo *dp, int dev)
 {
 	struct seq_oss_synth *rec;
-	if (dev < 0 || dev >= dp->max_synthdev)
-		return NULL;
-	if (! dp->synths[dev].opened)
+	struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev);
+
+	if (!info)
 		return NULL;
-	if (dp->synths[dev].is_midi)
-		return &midi_synth_dev;
-	if ((rec = get_sdev(dev)) == NULL)
+	if (!info->opened)
 		return NULL;
+	if (info->is_midi) {
+		rec = &midi_synth_dev;
+		snd_use_lock_use(&rec->use_lock);
+	} else {
+		rec = get_sdev(dev);
+		if (!rec)
+			return NULL;
+	}
 	if (! rec->opened) {
 		snd_use_lock_free(&rec->use_lock);
 		return NULL;
@@ -402,10 +405,8 @@ snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev)
 	struct seq_oss_synth *rec;
 	struct seq_oss_synthinfo *info;
 
-	if (snd_BUG_ON(dev < 0 || dev >= dp->max_synthdev))
-		return;
-	info = &dp->synths[dev];
-	if (! info->opened)
+	info = get_synthinfo_nospec(dp, dev);
+	if (!info || !info->opened)
 		return;
 	if (info->sysex)
 		info->sysex->len = 0; /* reset sysex */
@@ -454,12 +455,14 @@ snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt,
 			    const char __user *buf, int p, int c)
 {
 	struct seq_oss_synth *rec;
+	struct seq_oss_synthinfo *info;
 	int rc;
 
-	if (dev < 0 || dev >= dp->max_synthdev)
+	info = get_synthinfo_nospec(dp, dev);
+	if (!info)
 		return -ENXIO;
 
-	if (is_midi_dev(dp, dev))
+	if (info->is_midi)
 		return 0;
 	if ((rec = get_synthdev(dp, dev)) == NULL)
 		return -ENXIO;
@@ -467,24 +470,25 @@ snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt,
 	if (rec->oper.load_patch == NULL)
 		rc = -ENXIO;
 	else
-		rc = rec->oper.load_patch(&dp->synths[dev].arg, fmt, buf, p, c);
+		rc = rec->oper.load_patch(&info->arg, fmt, buf, p, c);
 	snd_use_lock_free(&rec->use_lock);
 	return rc;
 }
 
 /*
- * check if the device is valid synth device
+ * check if the device is valid synth device and return the synth info
  */
-int
-snd_seq_oss_synth_is_valid(struct seq_oss_devinfo *dp, int dev)
+struct seq_oss_synthinfo *
+snd_seq_oss_synth_info(struct seq_oss_devinfo *dp, int dev)
 {
 	struct seq_oss_synth *rec;
+
 	rec = get_synthdev(dp, dev);
 	if (rec) {
 		snd_use_lock_free(&rec->use_lock);
-		return 1;
+		return get_synthinfo_nospec(dp, dev);
 	}
-	return 0;
+	return NULL;
 }
 
 
@@ -499,16 +503,18 @@ snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf,
 	int i, send;
 	unsigned char *dest;
 	struct seq_oss_synth_sysex *sysex;
+	struct seq_oss_synthinfo *info;
 
-	if (! snd_seq_oss_synth_is_valid(dp, dev))
+	info = snd_seq_oss_synth_info(dp, dev);
+	if (!info)
 		return -ENXIO;
 
-	sysex = dp->synths[dev].sysex;
+	sysex = info->sysex;
 	if (sysex == NULL) {
 		sysex = kzalloc(sizeof(*sysex), GFP_KERNEL);
 		if (sysex == NULL)
 			return -ENOMEM;
-		dp->synths[dev].sysex = sysex;
+		info->sysex = sysex;
 	}
 
 	send = 0;
@@ -553,10 +559,12 @@ snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf,
 int
 snd_seq_oss_synth_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_event *ev)
 {
-	if (! snd_seq_oss_synth_is_valid(dp, dev))
+	struct seq_oss_synthinfo *info = snd_seq_oss_synth_info(dp, dev);
+
+	if (!info)
 		return -EINVAL;
-	snd_seq_oss_fill_addr(dp, ev, dp->synths[dev].arg.addr.client,
-			      dp->synths[dev].arg.addr.port);
+	snd_seq_oss_fill_addr(dp, ev, info->arg.addr.client,
+			      info->arg.addr.port);
 	return 0;
 }
 
@@ -568,16 +576,18 @@ int
 snd_seq_oss_synth_ioctl(struct seq_oss_devinfo *dp, int dev, unsigned int cmd, unsigned long addr)
 {
 	struct seq_oss_synth *rec;
+	struct seq_oss_synthinfo *info;
 	int rc;
 
-	if (is_midi_dev(dp, dev))
+	info = get_synthinfo_nospec(dp, dev);
+	if (!info || info->is_midi)
 		return -ENXIO;
 	if ((rec = get_synthdev(dp, dev)) == NULL)
 		return -ENXIO;
 	if (rec->oper.ioctl == NULL)
 		rc = -ENXIO;
 	else
-		rc = rec->oper.ioctl(&dp->synths[dev].arg, cmd, addr);
+		rc = rec->oper.ioctl(&info->arg, cmd, addr);
 	snd_use_lock_free(&rec->use_lock);
 	return rc;
 }
@@ -589,7 +599,10 @@ snd_seq_oss_synth_ioctl(struct seq_oss_devinfo *dp, int dev, unsigned int cmd, u
 int
 snd_seq_oss_synth_raw_event(struct seq_oss_devinfo *dp, int dev, unsigned char *data, struct snd_seq_event *ev)
 {
-	if (! snd_seq_oss_synth_is_valid(dp, dev) || is_midi_dev(dp, dev))
+	struct seq_oss_synthinfo *info;
+
+	info = snd_seq_oss_synth_info(dp, dev);
+	if (!info || info->is_midi)
 		return -ENXIO;
 	ev->type = SNDRV_SEQ_EVENT_OSS;
 	memcpy(ev->data.raw8.d, data, 8);
diff --git a/sound/core/seq/oss/seq_oss_synth.h b/sound/core/seq/oss/seq_oss_synth.h
index 74ac55f166b6..a63f9e22974d 100644
--- a/sound/core/seq/oss/seq_oss_synth.h
+++ b/sound/core/seq/oss/seq_oss_synth.h
@@ -37,7 +37,8 @@ void snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp);
 void snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev);
 int snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt,
 				 const char __user *buf, int p, int c);
-int snd_seq_oss_synth_is_valid(struct seq_oss_devinfo *dp, int dev);
+struct seq_oss_synthinfo *snd_seq_oss_synth_info(struct seq_oss_devinfo *dp,
+						 int dev);
 int snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf,
 			    struct snd_seq_event *ev);
 int snd_seq_oss_synth_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_event *ev);
diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c
index d21ece9f8d73..24d90abfc64d 100644
--- a/sound/core/seq/seq_ports.c
+++ b/sound/core/seq/seq_ports.c
@@ -669,7 +669,7 @@ int snd_seq_event_port_attach(int client,
 	/* Set up the port */
 	memset(&portinfo, 0, sizeof(portinfo));
 	portinfo.addr.client = client;
-	strlcpy(portinfo.name, portname ? portname : "Unamed port",
+	strlcpy(portinfo.name, portname ? portname : "Unnamed port",
 		sizeof(portinfo.name));
 
 	portinfo.capability = cap;
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index 23167578231f..f587d0e27476 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -371,9 +371,7 @@ static int initialize_timer(struct snd_seq_timer *tmr)
 
 	tmr->ticks = 1;
 	if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) {
-		unsigned long r = t->hw.resolution;
-		if (! r && t->hw.c_resolution)
-			r = t->hw.c_resolution(t);
+		unsigned long r = snd_timer_resolution(tmr->timeri);
 		if (r) {
 			tmr->ticks = (unsigned int)(1000000000uL / (r * freq));
 			if (! tmr->ticks)
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index f48a4cd24ffc..289ae6bb81d9 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -174,12 +174,12 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream,
 			}
 			return;
 		}
+		spin_lock_irqsave(&substream->runtime->lock, flags);
 		if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) {
 			if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0)
-				return;
+				goto out;
 			vmidi->event.type = SNDRV_SEQ_EVENT_NONE;
 		}
-		spin_lock_irqsave(&substream->runtime->lock, flags);
 		while (1) {
 			count = __snd_rawmidi_transmit_peek(substream, buf, sizeof(buf));
 			if (count <= 0)
diff --git a/sound/core/timer.c b/sound/core/timer.c
index dc87728c5b74..665089c45560 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -427,25 +427,35 @@ int snd_timer_close(struct snd_timer_instance *timeri)
 }
 EXPORT_SYMBOL(snd_timer_close);
 
+static unsigned long snd_timer_hw_resolution(struct snd_timer *timer)
+{
+	if (timer->hw.c_resolution)
+		return timer->hw.c_resolution(timer);
+	else
+		return timer->hw.resolution;
+}
+
 unsigned long snd_timer_resolution(struct snd_timer_instance *timeri)
 {
 	struct snd_timer * timer;
+	unsigned long ret = 0;
+	unsigned long flags;
 
 	if (timeri == NULL)
 		return 0;
 	timer = timeri->timer;
 	if (timer) {
-		if (timer->hw.c_resolution)
-			return timer->hw.c_resolution(timer);
-		return timer->hw.resolution;
+		spin_lock_irqsave(&timer->lock, flags);
+		ret = snd_timer_hw_resolution(timer);
+		spin_unlock_irqrestore(&timer->lock, flags);
 	}
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(snd_timer_resolution);
 
 static void snd_timer_notify1(struct snd_timer_instance *ti, int event)
 {
-	struct snd_timer *timer;
+	struct snd_timer *timer = ti->timer;
 	unsigned long resolution = 0;
 	struct snd_timer_instance *ts;
 	struct timespec tstamp;
@@ -457,14 +467,14 @@ static void snd_timer_notify1(struct snd_timer_instance *ti, int event)
 	if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_START ||
 		       event > SNDRV_TIMER_EVENT_PAUSE))
 		return;
-	if (event == SNDRV_TIMER_EVENT_START ||
-	    event == SNDRV_TIMER_EVENT_CONTINUE)
-		resolution = snd_timer_resolution(ti);
+	if (timer &&
+	    (event == SNDRV_TIMER_EVENT_START ||
+	     event == SNDRV_TIMER_EVENT_CONTINUE))
+		resolution = snd_timer_hw_resolution(timer);
 	if (ti->ccallback)
 		ti->ccallback(ti, event, &tstamp, resolution);
 	if (ti->flags & SNDRV_TIMER_IFLG_SLAVE)
 		return;
-	timer = ti->timer;
 	if (timer == NULL)
 		return;
 	if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE)
@@ -592,7 +602,7 @@ static int snd_timer_stop1(struct snd_timer_instance *timeri, bool stop)
 	else
 		timeri->flags |= SNDRV_TIMER_IFLG_PAUSED;
 	snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP :
-			  SNDRV_TIMER_EVENT_CONTINUE);
+			  SNDRV_TIMER_EVENT_PAUSE);
  unlock:
 	spin_unlock_irqrestore(&timer->lock, flags);
 	return result;
@@ -614,7 +624,7 @@ static int snd_timer_stop_slave(struct snd_timer_instance *timeri, bool stop)
 		list_del_init(&timeri->ack_list);
 		list_del_init(&timeri->active_list);
 		snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP :
-				  SNDRV_TIMER_EVENT_CONTINUE);
+				  SNDRV_TIMER_EVENT_PAUSE);
 		spin_unlock(&timeri->timer->lock);
 	}
 	spin_unlock_irqrestore(&slave_active_lock, flags);
@@ -771,10 +781,7 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left)
 	spin_lock_irqsave(&timer->lock, flags);
 
 	/* remember the current resolution */
-	if (timer->hw.c_resolution)
-		resolution = timer->hw.c_resolution(timer);
-	else
-		resolution = timer->hw.resolution;
+	resolution = snd_timer_hw_resolution(timer);
 
 	/* loop for all active instances
 	 * Here we cannot use list_for_each_entry because the active_list of a
@@ -1014,12 +1021,8 @@ void snd_timer_notify(struct snd_timer *timer, int event, struct timespec *tstam
 	spin_lock_irqsave(&timer->lock, flags);
 	if (event == SNDRV_TIMER_EVENT_MSTART ||
 	    event == SNDRV_TIMER_EVENT_MCONTINUE ||
-	    event == SNDRV_TIMER_EVENT_MRESUME) {
-		if (timer->hw.c_resolution)
-			resolution = timer->hw.c_resolution(timer);
-		else
-			resolution = timer->hw.resolution;
-	}
+	    event == SNDRV_TIMER_EVENT_MRESUME)
+		resolution = snd_timer_hw_resolution(timer);
 	list_for_each_entry(ti, &timer->active_list_head, active_list) {
 		if (ti->ccallback)
 			ti->ccallback(ti, event, tstamp, resolution);
@@ -1656,10 +1659,8 @@ static int snd_timer_user_gstatus(struct file *file,
 	mutex_lock(&register_mutex);
 	t = snd_timer_find(&tid);
 	if (t != NULL) {
-		if (t->hw.c_resolution)
-			gstatus.resolution = t->hw.c_resolution(t);
-		else
-			gstatus.resolution = t->hw.resolution;
+		spin_lock_irq(&t->lock);
+		gstatus.resolution = snd_timer_hw_resolution(t);
 		if (t->hw.precise_resolution) {
 			t->hw.precise_resolution(t, &gstatus.resolution_num,
 						 &gstatus.resolution_den);
@@ -1667,6 +1668,7 @@ static int snd_timer_user_gstatus(struct file *file,
 			gstatus.resolution_num = gstatus.resolution;
 			gstatus.resolution_den = 1000000000uL;
 		}
+		spin_unlock_irq(&t->lock);
 	} else {
 		err = -ENODEV;
 	}
diff --git a/sound/core/vmaster.c b/sound/core/vmaster.c
index 9e96186742d0..58fa3f94722a 100644
--- a/sound/core/vmaster.c
+++ b/sound/core/vmaster.c
@@ -421,13 +421,15 @@ struct snd_kcontrol *snd_ctl_make_virtual_master(char *name,
 	kctl->private_free = master_free;
 
 	/* additional (constant) TLV read */
-	if (tlv &&
-	    (tlv[0] == SNDRV_CTL_TLVT_DB_SCALE ||
-	     tlv[0] == SNDRV_CTL_TLVT_DB_MINMAX ||
-	     tlv[0] == SNDRV_CTL_TLVT_DB_MINMAX_MUTE)) {
-		kctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_TLV_READ;
-		memcpy(master->tlv, tlv, sizeof(master->tlv));
-		kctl->tlv.p = master->tlv;
+	if (tlv) {
+		unsigned int type = tlv[SNDRV_CTL_TLVO_TYPE];
+		if (type == SNDRV_CTL_TLVT_DB_SCALE ||
+		    type == SNDRV_CTL_TLVT_DB_MINMAX ||
+		    type == SNDRV_CTL_TLVT_DB_MINMAX_MUTE) {
+			kctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_TLV_READ;
+			memcpy(master->tlv, tlv, sizeof(master->tlv));
+			kctl->tlv.p = master->tlv;
+		}
 	}
 
 	return kctl;
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 58e349fc893f..78a2fdc38531 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -768,20 +768,7 @@ static int loopback_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static const struct snd_pcm_ops loopback_playback_ops = {
-	.open =		loopback_open,
-	.close =	loopback_close,
-	.ioctl =	snd_pcm_lib_ioctl,
-	.hw_params =	loopback_hw_params,
-	.hw_free =	loopback_hw_free,
-	.prepare =	loopback_prepare,
-	.trigger =	loopback_trigger,
-	.pointer =	loopback_pointer,
-	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
-};
-
-static const struct snd_pcm_ops loopback_capture_ops = {
+static const struct snd_pcm_ops loopback_pcm_ops = {
 	.open =		loopback_open,
 	.close =	loopback_close,
 	.ioctl =	snd_pcm_lib_ioctl,
@@ -804,8 +791,8 @@ static int loopback_pcm_new(struct loopback *loopback,
 			  substreams, substreams, &pcm);
 	if (err < 0)
 		return err;
-	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &loopback_playback_ops);
-	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &loopback_capture_ops);
+	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &loopback_pcm_ops);
+	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &loopback_pcm_ops);
 
 	pcm->private_data = loopback;
 	pcm->info_flags = 0;
@@ -831,9 +818,11 @@ static int loopback_rate_shift_get(struct snd_kcontrol *kcontrol,
 {
 	struct loopback *loopback = snd_kcontrol_chip(kcontrol);
 	
+	mutex_lock(&loopback->cable_lock);
 	ucontrol->value.integer.value[0] =
 		loopback->setup[kcontrol->id.subdevice]
 			       [kcontrol->id.device].rate_shift;
+	mutex_unlock(&loopback->cable_lock);
 	return 0;
 }
 
@@ -865,9 +854,11 @@ static int loopback_notify_get(struct snd_kcontrol *kcontrol,
 {
 	struct loopback *loopback = snd_kcontrol_chip(kcontrol);
 	
+	mutex_lock(&loopback->cable_lock);
 	ucontrol->value.integer.value[0] =
 		loopback->setup[kcontrol->id.subdevice]
 			       [kcontrol->id.device].notify;
+	mutex_unlock(&loopback->cable_lock);
 	return 0;
 }
 
@@ -879,12 +870,14 @@ static int loopback_notify_put(struct snd_kcontrol *kcontrol,
 	int change = 0;
 
 	val = ucontrol->value.integer.value[0] ? 1 : 0;
+	mutex_lock(&loopback->cable_lock);
 	if (val != loopback->setup[kcontrol->id.subdevice]
 				[kcontrol->id.device].notify) {
 		loopback->setup[kcontrol->id.subdevice]
 			[kcontrol->id.device].notify = val;
 		change = 1;
 	}
+	mutex_unlock(&loopback->cable_lock);
 	return change;
 }
 
@@ -892,15 +885,18 @@ static int loopback_active_get(struct snd_kcontrol *kcontrol,
 			       struct snd_ctl_elem_value *ucontrol)
 {
 	struct loopback *loopback = snd_kcontrol_chip(kcontrol);
-	struct loopback_cable *cable = loopback->cables
-			[kcontrol->id.subdevice][kcontrol->id.device ^ 1];
+	struct loopback_cable *cable;
+
 	unsigned int val = 0;
 
+	mutex_lock(&loopback->cable_lock);
+	cable = loopback->cables[kcontrol->id.subdevice][kcontrol->id.device ^ 1];
 	if (cable != NULL) {
 		unsigned int running = cable->running ^ cable->pause;
 
 		val = (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) ? 1 : 0;
 	}
+	mutex_unlock(&loopback->cable_lock);
 	ucontrol->value.integer.value[0] = val;
 	return 0;
 }
@@ -943,9 +939,11 @@ static int loopback_rate_get(struct snd_kcontrol *kcontrol,
 {
 	struct loopback *loopback = snd_kcontrol_chip(kcontrol);
 	
+	mutex_lock(&loopback->cable_lock);
 	ucontrol->value.integer.value[0] =
 		loopback->setup[kcontrol->id.subdevice]
 			       [kcontrol->id.device].rate;
+	mutex_unlock(&loopback->cable_lock);
 	return 0;
 }
 
@@ -965,9 +963,11 @@ static int loopback_channels_get(struct snd_kcontrol *kcontrol,
 {
 	struct loopback *loopback = snd_kcontrol_chip(kcontrol);
 	
+	mutex_lock(&loopback->cable_lock);
 	ucontrol->value.integer.value[0] =
 		loopback->setup[kcontrol->id.subdevice]
 			       [kcontrol->id.device].channels;
+	mutex_unlock(&loopback->cable_lock);
 	return 0;
 }
 
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index 8fb9a54fe8ba..9af154db530a 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -1042,7 +1042,7 @@ static void dummy_proc_init(struct snd_dummy *chip)
 	if (!snd_card_proc_new(chip->card, "dummy_pcm", &entry)) {
 		snd_info_set_text_ops(entry, chip, dummy_proc_read);
 		entry->c.text.write = dummy_proc_write;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 		entry->private_data = chip;
 	}
 }
diff --git a/sound/drivers/mts64.c b/sound/drivers/mts64.c
index f32e81342247..b68e71ca7abd 100644
--- a/sound/drivers/mts64.c
+++ b/sound/drivers/mts64.c
@@ -41,11 +41,11 @@ static bool enable[SNDRV_CARDS] = SNDRV_DEFAULT_ENABLE_PNP;
 static struct platform_device *platform_devices[SNDRV_CARDS]; 
 static int device_count;
 
-module_param_array(index, int, NULL, S_IRUGO);
+module_param_array(index, int, NULL, 0444);
 MODULE_PARM_DESC(index, "Index value for " CARD_NAME " soundcard.");
-module_param_array(id, charp, NULL, S_IRUGO);
+module_param_array(id, charp, NULL, 0444);
 MODULE_PARM_DESC(id, "ID string for " CARD_NAME " soundcard.");
-module_param_array(enable, bool, NULL, S_IRUGO);
+module_param_array(enable, bool, NULL, 0444);
 MODULE_PARM_DESC(enable, "Enable " CARD_NAME " soundcard.");
 
 MODULE_AUTHOR("Matthias Koenig <mk@phasorlab.de>");
diff --git a/sound/drivers/opl3/opl3_synth.c b/sound/drivers/opl3/opl3_synth.c
index ddcc1a325a61..42920a243328 100644
--- a/sound/drivers/opl3/opl3_synth.c
+++ b/sound/drivers/opl3/opl3_synth.c
@@ -21,6 +21,7 @@
 
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/nospec.h>
 #include <sound/opl3.h>
 #include <sound/asound_fm.h>
 
@@ -448,7 +449,7 @@ static int snd_opl3_set_voice(struct snd_opl3 * opl3, struct snd_dm_fm_voice * v
 {
 	unsigned short reg_side;
 	unsigned char op_offset;
-	unsigned char voice_offset;
+	unsigned char voice_offset, voice_op;
 
 	unsigned short opl3_reg;
 	unsigned char reg_val;
@@ -473,7 +474,9 @@ static int snd_opl3_set_voice(struct snd_opl3 * opl3, struct snd_dm_fm_voice * v
 		voice_offset = voice->voice - MAX_OPL2_VOICES;
 	}
 	/* Get register offset of operator */
-	op_offset = snd_opl3_regmap[voice_offset][voice->op];
+	voice_offset = array_index_nospec(voice_offset, MAX_OPL2_VOICES);
+	voice_op = array_index_nospec(voice->op, 4);
+	op_offset = snd_opl3_regmap[voice_offset][voice_op];
 
 	reg_val = 0x00;
 	/* Set amplitude modulation (tremolo) effect */
diff --git a/sound/drivers/opl4/opl4_proc.c b/sound/drivers/opl4/opl4_proc.c
index cd2c07fa2ef4..16b24091d799 100644
--- a/sound/drivers/opl4/opl4_proc.c
+++ b/sound/drivers/opl4/opl4_proc.c
@@ -104,7 +104,7 @@ int snd_opl4_create_proc(struct snd_opl4 *opl4)
 	if (entry) {
 		if (opl4->hardware < OPL3_HW_OPL4_ML) {
 			/* OPL4 can access 4 MB external ROM/SRAM */
-			entry->mode |= S_IWUSR;
+			entry->mode |= 0200;
 			entry->size = 4 * 1024 * 1024;
 		} else {
 			/* OPL4-ML has 1 MB internal ROM */
diff --git a/sound/drivers/portman2x4.c b/sound/drivers/portman2x4.c
index ec8a94325ef6..3cdf0a88d71b 100644
--- a/sound/drivers/portman2x4.c
+++ b/sound/drivers/portman2x4.c
@@ -60,11 +60,11 @@ static bool enable[SNDRV_CARDS] = SNDRV_DEFAULT_ENABLE_PNP;
 static struct platform_device *platform_devices[SNDRV_CARDS]; 
 static int device_count;
 
-module_param_array(index, int, NULL, S_IRUGO);
+module_param_array(index, int, NULL, 0444);
 MODULE_PARM_DESC(index, "Index value for " CARD_NAME " soundcard.");
-module_param_array(id, charp, NULL, S_IRUGO);
+module_param_array(id, charp, NULL, 0444);
 MODULE_PARM_DESC(id, "ID string for " CARD_NAME " soundcard.");
-module_param_array(enable, bool, NULL, S_IRUGO);
+module_param_array(enable, bool, NULL, 0444);
 MODULE_PARM_DESC(enable, "Enable " CARD_NAME " soundcard.");
 
 MODULE_AUTHOR("Levent Guendogdu, Tobias Gehrig, Matthias Koenig");
diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index 4a1dc145327b..cb9acfe60f6a 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -773,8 +773,6 @@ static void amdtp_stream_first_callback(struct fw_iso_context *context,
 	u32 cycle;
 	unsigned int packets;
 
-	s->max_payload_length = amdtp_stream_get_max_payload(s);
-
 	/*
 	 * For in-stream, first packet has come.
 	 * For out-stream, prepared to transmit first packet
@@ -879,6 +877,9 @@ int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
 
 	amdtp_stream_update(s);
 
+	if (s->direction == AMDTP_IN_STREAM)
+		s->max_payload_length = amdtp_stream_get_max_payload(s);
+
 	if (s->flags & CIP_NO_HEADER)
 		s->tag = TAG_NO_CIP_HEADER;
 	else
diff --git a/sound/firewire/bebob/bebob_proc.c b/sound/firewire/bebob/bebob_proc.c
index ec24f96794f5..8096891af913 100644
--- a/sound/firewire/bebob/bebob_proc.c
+++ b/sound/firewire/bebob/bebob_proc.c
@@ -183,7 +183,7 @@ void snd_bebob_proc_init(struct snd_bebob *bebob)
 					  bebob->card->proc_root);
 	if (root == NULL)
 		return;
-	root->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	root->mode = S_IFDIR | 0555;
 	if (snd_info_register(root) < 0) {
 		snd_info_free_entry(root);
 		return;
diff --git a/sound/firewire/dice/Makefile b/sound/firewire/dice/Makefile
index 55b4be9b0034..37062a233f6a 100644
--- a/sound/firewire/dice/Makefile
+++ b/sound/firewire/dice/Makefile
@@ -1,3 +1,4 @@
 snd-dice-objs := dice-transaction.o dice-stream.o dice-proc.o dice-midi.o \
-		 dice-pcm.o dice-hwdep.o dice.o
+		 dice-pcm.o dice-hwdep.o dice.o dice-tcelectronic.o \
+		 dice-alesis.o dice-extension.o dice-mytek.o
 obj-$(CONFIG_SND_DICE) += snd-dice.o
diff --git a/sound/firewire/dice/dice-alesis.c b/sound/firewire/dice/dice-alesis.c
new file mode 100644
index 000000000000..b2efb1c71a98
--- /dev/null
+++ b/sound/firewire/dice/dice-alesis.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dice-alesis.c - a part of driver for DICE based devices
+ *
+ * Copyright (c) 2018 Takashi Sakamoto
+ */
+
+#include "dice.h"
+
+static const unsigned int
+alesis_io14_tx_pcm_chs[MAX_STREAMS][SND_DICE_RATE_MODE_COUNT] = {
+	{6, 6, 4},	/* Tx0 = Analog + S/PDIF. */
+	{8, 4, 0},	/* Tx1 = ADAT1. */
+};
+
+static const unsigned int
+alesis_io26_tx_pcm_chs[MAX_STREAMS][SND_DICE_RATE_MODE_COUNT] = {
+	{10, 10, 8},	/* Tx0 = Analog + S/PDIF. */
+	{16, 8, 0},	/* Tx1 = ADAT1 + ADAT2. */
+};
+
+int snd_dice_detect_alesis_formats(struct snd_dice *dice)
+{
+	__be32 reg;
+	u32 data;
+	int i;
+	int err;
+
+	err = snd_dice_transaction_read_tx(dice, TX_NUMBER_AUDIO, &reg,
+					   sizeof(reg));
+	if (err < 0)
+		return err;
+	data = be32_to_cpu(reg);
+
+	if (data == 4 || data == 6) {
+		memcpy(dice->tx_pcm_chs, alesis_io14_tx_pcm_chs,
+				MAX_STREAMS * SND_DICE_RATE_MODE_COUNT *
+				sizeof(unsigned int));
+	} else {
+		memcpy(dice->rx_pcm_chs, alesis_io26_tx_pcm_chs,
+				MAX_STREAMS * SND_DICE_RATE_MODE_COUNT *
+				sizeof(unsigned int));
+	}
+
+	for (i = 0; i < SND_DICE_RATE_MODE_COUNT; ++i)
+		dice->rx_pcm_chs[0][i] = 8;
+
+	dice->tx_midi_ports[0] = 1;
+	dice->rx_midi_ports[0] = 1;
+
+	return 0;
+}
diff --git a/sound/firewire/dice/dice-extension.c b/sound/firewire/dice/dice-extension.c
new file mode 100644
index 000000000000..a63fcbc875ad
--- /dev/null
+++ b/sound/firewire/dice/dice-extension.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dice-extension.c - a part of driver for DICE based devices
+ *
+ * Copyright (c) 2018 Takashi Sakamoto
+ */
+
+#include "dice.h"
+
+/* For TCD2210/2220, TCAT defines extension of application protocol. */
+
+#define DICE_EXT_APP_SPACE		0xffffe0200000uLL
+
+#define DICE_EXT_APP_CAPS_OFFSET	0x00
+#define DICE_EXT_APP_CAPS_SIZE		0x04
+#define DICE_EXT_APP_CMD_OFFSET		0x08
+#define DICE_EXT_APP_CMD_SIZE		0x0c
+#define DICE_EXT_APP_MIXER_OFFSET	0x10
+#define DICE_EXT_APP_MIXER_SIZE		0x14
+#define DICE_EXT_APP_PEAK_OFFSET	0x18
+#define DICE_EXT_APP_PEAK_SIZE		0x1c
+#define DICE_EXT_APP_ROUTER_OFFSET	0x20
+#define DICE_EXT_APP_ROUTER_SIZE	0x24
+#define DICE_EXT_APP_STREAM_OFFSET	0x28
+#define DICE_EXT_APP_STREAM_SIZE	0x2c
+#define DICE_EXT_APP_CURRENT_OFFSET	0x30
+#define DICE_EXT_APP_CURRENT_SIZE	0x34
+#define DICE_EXT_APP_STANDALONE_OFFSET	0x38
+#define DICE_EXT_APP_STANDALONE_SIZE	0x3c
+#define DICE_EXT_APP_APPLICATION_OFFSET	0x40
+#define DICE_EXT_APP_APPLICATION_SIZE	0x44
+
+#define EXT_APP_STREAM_TX_NUMBER	0x0000
+#define EXT_APP_STREAM_RX_NUMBER	0x0004
+#define EXT_APP_STREAM_ENTRIES		0x0008
+#define EXT_APP_STREAM_ENTRY_SIZE	0x010c
+#define  EXT_APP_NUMBER_AUDIO		0x0000
+#define  EXT_APP_NUMBER_MIDI		0x0004
+#define  EXT_APP_NAMES			0x0008
+#define   EXT_APP_NAMES_SIZE		256
+#define  EXT_APP_AC3			0x0108
+
+#define EXT_APP_CONFIG_LOW_ROUTER	0x0000
+#define EXT_APP_CONFIG_LOW_STREAM	0x1000
+#define EXT_APP_CONFIG_MIDDLE_ROUTER	0x2000
+#define EXT_APP_CONFIG_MIDDLE_STREAM	0x3000
+#define EXT_APP_CONFIG_HIGH_ROUTER	0x4000
+#define EXT_APP_CONFIG_HIGH_STREAM	0x5000
+
+static inline int read_transaction(struct snd_dice *dice, u64 section_addr,
+				   u32 offset, void *buf, size_t len)
+{
+	return snd_fw_transaction(dice->unit,
+				  len == 4 ? TCODE_READ_QUADLET_REQUEST :
+					     TCODE_READ_BLOCK_REQUEST,
+				  section_addr + offset, buf, len, 0);
+}
+
+static int read_stream_entries(struct snd_dice *dice, u64 section_addr,
+			       u32 base_offset, unsigned int stream_count,
+			       unsigned int mode,
+			       unsigned int pcm_channels[MAX_STREAMS][3],
+			       unsigned int midi_ports[MAX_STREAMS])
+{
+	u32 entry_offset;
+	__be32 reg[2];
+	int err;
+	int i;
+
+	for (i = 0; i < stream_count; ++i) {
+		entry_offset = base_offset + i * EXT_APP_STREAM_ENTRY_SIZE;
+		err = read_transaction(dice, section_addr,
+				    entry_offset + EXT_APP_NUMBER_AUDIO,
+				    reg, sizeof(reg));
+		if (err < 0)
+			return err;
+		pcm_channels[i][mode] = be32_to_cpu(reg[0]);
+		midi_ports[i] = max(midi_ports[i], be32_to_cpu(reg[1]));
+	}
+
+	return 0;
+}
+
+static int detect_stream_formats(struct snd_dice *dice, u64 section_addr)
+{
+	u32 base_offset;
+	__be32 reg[2];
+	unsigned int stream_count;
+	int mode;
+	int err = 0;
+
+	for (mode = 0; mode < SND_DICE_RATE_MODE_COUNT; ++mode) {
+		unsigned int cap;
+
+		/*
+		 * Some models report stream formats at highest mode, however
+		 * they don't support the mode. Check clock capabilities.
+		 */
+		if (mode == 2) {
+			cap = CLOCK_CAP_RATE_176400 | CLOCK_CAP_RATE_192000;
+		} else if (mode == 1) {
+			cap = CLOCK_CAP_RATE_88200 | CLOCK_CAP_RATE_96000;
+		} else {
+			cap = CLOCK_CAP_RATE_32000 | CLOCK_CAP_RATE_44100 |
+			      CLOCK_CAP_RATE_48000;
+		}
+		if (!(cap & dice->clock_caps))
+			continue;
+
+		base_offset = 0x2000 * mode + 0x1000;
+
+		err = read_transaction(dice, section_addr,
+				       base_offset + EXT_APP_STREAM_TX_NUMBER,
+				       &reg, sizeof(reg));
+		if (err < 0)
+			break;
+
+		base_offset += EXT_APP_STREAM_ENTRIES;
+		stream_count = be32_to_cpu(reg[0]);
+		err = read_stream_entries(dice, section_addr, base_offset,
+					  stream_count, mode,
+					  dice->tx_pcm_chs,
+					  dice->tx_midi_ports);
+		if (err < 0)
+			break;
+
+		base_offset += stream_count * EXT_APP_STREAM_ENTRY_SIZE;
+		stream_count = be32_to_cpu(reg[1]);
+		err = read_stream_entries(dice, section_addr, base_offset,
+					  stream_count,
+					  mode, dice->rx_pcm_chs,
+					  dice->rx_midi_ports);
+		if (err < 0)
+			break;
+	}
+
+	return err;
+}
+
+int snd_dice_detect_extension_formats(struct snd_dice *dice)
+{
+	__be32 *pointers;
+	unsigned int i;
+	u64 section_addr;
+	int err;
+
+	pointers = kmalloc_array(9, sizeof(__be32) * 2, GFP_KERNEL);
+	if (pointers == NULL)
+		return -ENOMEM;
+
+	err = snd_fw_transaction(dice->unit, TCODE_READ_BLOCK_REQUEST,
+				 DICE_EXT_APP_SPACE, pointers,
+				 9 * sizeof(__be32) * 2, 0);
+	if (err < 0)
+		goto end;
+
+	/* Check two of them for offset have the same value or not. */
+	for (i = 0; i < 9; ++i) {
+		int j;
+
+		for (j = i + 1; j < 9; ++j) {
+			if (pointers[i * 2] == pointers[j * 2])
+				goto end;
+		}
+	}
+
+	section_addr = DICE_EXT_APP_SPACE + be32_to_cpu(pointers[12]) * 4;
+	err = detect_stream_formats(dice, section_addr);
+end:
+	kfree(pointers);
+	return err;
+}
diff --git a/sound/firewire/dice/dice-interface.h b/sound/firewire/dice/dice-interface.h
index 15a484b05298..9cad3d608229 100644
--- a/sound/firewire/dice/dice-interface.h
+++ b/sound/firewire/dice/dice-interface.h
@@ -175,13 +175,18 @@
 #define GLOBAL_SAMPLE_RATE		0x05c
 
 /*
+ * Some old firmware versions do not have the following global registers.
+ * Windows drivers produced by TCAT lost backward compatibility in its
+ * early release because they can handle firmware only which supports the
+ * following registers.
+ */
+
+/*
  * The version of the DICE driver specification that this device conforms to;
  * read-only.
  */
 #define GLOBAL_VERSION			0x060
 
-/* Some old firmware versions do not have the following global registers: */
-
 /*
  * Supported sample rates and clock sources; read-only.
  */
diff --git a/sound/firewire/dice/dice-midi.c b/sound/firewire/dice/dice-midi.c
index 8ff6da3c51f7..84eca8a51a02 100644
--- a/sound/firewire/dice/dice-midi.c
+++ b/sound/firewire/dice/dice-midi.c
@@ -101,27 +101,18 @@ int snd_dice_create_midi(struct snd_dice *dice)
 		.close		= midi_close,
 		.trigger	= midi_playback_trigger,
 	};
-	__be32 reg;
 	struct snd_rawmidi *rmidi;
 	struct snd_rawmidi_str *str;
 	unsigned int midi_in_ports, midi_out_ports;
+	int i;
 	int err;
 
-	/*
-	 * Use the number of MIDI conformant data channel at current sampling
-	 * transfer frequency.
-	 */
-	err = snd_dice_transaction_read_tx(dice, TX_NUMBER_MIDI,
-					   &reg, sizeof(reg));
-	if (err < 0)
-		return err;
-	midi_in_ports = be32_to_cpu(reg);
-
-	err = snd_dice_transaction_read_rx(dice, RX_NUMBER_MIDI,
-					   &reg, sizeof(reg));
-	if (err < 0)
-		return err;
-	midi_out_ports = be32_to_cpu(reg);
+	midi_in_ports = 0;
+	midi_out_ports = 0;
+	for (i = 0; i < MAX_STREAMS; ++i) {
+		midi_in_ports = max(midi_in_ports, dice->tx_midi_ports[i]);
+		midi_out_ports = max(midi_out_ports, dice->rx_midi_ports[i]);
+	}
 
 	if (midi_in_ports + midi_out_ports == 0)
 		return 0;
diff --git a/sound/firewire/dice/dice-mytek.c b/sound/firewire/dice/dice-mytek.c
new file mode 100644
index 000000000000..eb7d5492d10b
--- /dev/null
+++ b/sound/firewire/dice/dice-mytek.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dice-mytek.c - a part of driver for DICE based devices
+ *
+ * Copyright (c) 2018 Melvin Vermeeren
+ */
+
+#include "dice.h"
+
+struct dice_mytek_spec {
+	unsigned int tx_pcm_chs[MAX_STREAMS][SND_DICE_RATE_MODE_COUNT];
+	unsigned int rx_pcm_chs[MAX_STREAMS][SND_DICE_RATE_MODE_COUNT];
+};
+
+static const struct dice_mytek_spec stereo_192_dsd_dac = {
+	/* AES, TOSLINK, SPDIF, ADAT inputs on device */
+	.tx_pcm_chs = {{8, 8, 8}, {0, 0, 0} },
+	/* PCM 44.1-192, native DSD64/DSD128 to device */
+	.rx_pcm_chs = {{4, 4, 4}, {0, 0, 0} }
+};
+
+/*
+ * Mytek has a few other firewire-capable devices, though newer models appear
+ * to lack the port more often than not. As I don't have access to any of them
+ * they are missing here. An example is the Mytek 8x192 ADDA, which is DICE.
+ */
+
+int snd_dice_detect_mytek_formats(struct snd_dice *dice)
+{
+	int i;
+	const struct dice_mytek_spec *dev;
+
+	dev = &stereo_192_dsd_dac;
+
+	memcpy(dice->tx_pcm_chs, dev->tx_pcm_chs,
+	       MAX_STREAMS * SND_DICE_RATE_MODE_COUNT * sizeof(unsigned int));
+	memcpy(dice->rx_pcm_chs, dev->rx_pcm_chs,
+	       MAX_STREAMS * SND_DICE_RATE_MODE_COUNT * sizeof(unsigned int));
+
+	for (i = 0; i < MAX_STREAMS; ++i) {
+		dice->tx_midi_ports[i] = 0;
+		dice->rx_midi_ports[i] = 0;
+	}
+
+	return 0;
+}
diff --git a/sound/firewire/dice/dice-pcm.c b/sound/firewire/dice/dice-pcm.c
index 7cb9e9713ac3..80351b29fe0d 100644
--- a/sound/firewire/dice/dice-pcm.c
+++ b/sound/firewire/dice/dice-pcm.c
@@ -9,43 +9,115 @@
 
 #include "dice.h"
 
+static int dice_rate_constraint(struct snd_pcm_hw_params *params,
+				struct snd_pcm_hw_rule *rule)
+{
+	struct snd_pcm_substream *substream = rule->private;
+	struct snd_dice *dice = substream->private_data;
+	unsigned int index = substream->pcm->device;
+
+	const struct snd_interval *c =
+		hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_CHANNELS);
+	struct snd_interval *r =
+		hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval rates = {
+		.min = UINT_MAX, .max = 0, .integer = 1
+	};
+	unsigned int *pcm_channels;
+	enum snd_dice_rate_mode mode;
+	unsigned int i, rate;
+
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+		pcm_channels = dice->tx_pcm_chs[index];
+	else
+		pcm_channels = dice->rx_pcm_chs[index];
+
+	for (i = 0; i < ARRAY_SIZE(snd_dice_rates); ++i) {
+		rate = snd_dice_rates[i];
+		if (snd_dice_stream_get_rate_mode(dice, rate, &mode) < 0)
+			continue;
+
+		if (!snd_interval_test(c, pcm_channels[mode]))
+			continue;
+
+		rates.min = min(rates.min, rate);
+		rates.max = max(rates.max, rate);
+	}
+
+	return snd_interval_refine(r, &rates);
+}
+
+static int dice_channels_constraint(struct snd_pcm_hw_params *params,
+				    struct snd_pcm_hw_rule *rule)
+{
+	struct snd_pcm_substream *substream = rule->private;
+	struct snd_dice *dice = substream->private_data;
+	unsigned int index = substream->pcm->device;
+
+	const struct snd_interval *r =
+		hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval *c =
+		hw_param_interval(params, SNDRV_PCM_HW_PARAM_CHANNELS);
+	struct snd_interval channels = {
+		.min = UINT_MAX, .max = 0, .integer = 1
+	};
+	unsigned int *pcm_channels;
+	enum snd_dice_rate_mode mode;
+	unsigned int i, rate;
+
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+		pcm_channels = dice->tx_pcm_chs[index];
+	else
+		pcm_channels = dice->rx_pcm_chs[index];
+
+	for (i = 0; i < ARRAY_SIZE(snd_dice_rates); ++i) {
+		rate = snd_dice_rates[i];
+		if (snd_dice_stream_get_rate_mode(dice, rate, &mode) < 0)
+			continue;
+
+		if (!snd_interval_test(r, rate))
+			continue;
+
+		channels.min = min(channels.min, pcm_channels[mode]);
+		channels.max = max(channels.max, pcm_channels[mode]);
+	}
+
+	return snd_interval_refine(c, &channels);
+}
+
 static int limit_channels_and_rates(struct snd_dice *dice,
 				    struct snd_pcm_runtime *runtime,
 				    enum amdtp_stream_direction dir,
-				    unsigned int index, unsigned int size)
+				    unsigned int index)
 {
 	struct snd_pcm_hardware *hw = &runtime->hw;
-	struct amdtp_stream *stream;
-	unsigned int rate;
-	__be32 reg;
-	int err;
-
-	/*
-	 * Retrieve current Multi Bit Linear Audio data channel and limit to
-	 * it.
-	 */
-	if (dir == AMDTP_IN_STREAM) {
-		stream = &dice->tx_stream[index];
-		err = snd_dice_transaction_read_tx(dice,
-				size * index + TX_NUMBER_AUDIO,
-				&reg, sizeof(reg));
-	} else {
-		stream = &dice->rx_stream[index];
-		err = snd_dice_transaction_read_rx(dice,
-				size * index + RX_NUMBER_AUDIO,
-				&reg, sizeof(reg));
+	unsigned int *pcm_channels;
+	unsigned int i;
+
+	if (dir == AMDTP_IN_STREAM)
+		pcm_channels = dice->tx_pcm_chs[index];
+	else
+		pcm_channels = dice->rx_pcm_chs[index];
+
+	hw->channels_min = UINT_MAX;
+	hw->channels_max = 0;
+
+	for (i = 0; i < ARRAY_SIZE(snd_dice_rates); ++i) {
+		enum snd_dice_rate_mode mode;
+		unsigned int rate, channels;
+
+		rate = snd_dice_rates[i];
+		if (snd_dice_stream_get_rate_mode(dice, rate, &mode) < 0)
+			continue;
+		hw->rates |= snd_pcm_rate_to_rate_bit(rate);
+
+		channels = pcm_channels[mode];
+		if (channels == 0)
+			continue;
+		hw->channels_min = min(hw->channels_min, channels);
+		hw->channels_max = max(hw->channels_max, channels);
 	}
-	if (err < 0)
-		return err;
 
-	hw->channels_min = hw->channels_max = be32_to_cpu(reg);
-
-	/* Retrieve current sampling transfer frequency and limit to it. */
-	err = snd_dice_transaction_get_rate(dice, &rate);
-	if (err < 0)
-		return err;
-
-	hw->rates = snd_pcm_rate_to_rate_bit(rate);
 	snd_pcm_limit_hw_rates(runtime);
 
 	return 0;
@@ -56,36 +128,34 @@ static int init_hw_info(struct snd_dice *dice,
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_pcm_hardware *hw = &runtime->hw;
+	unsigned int index = substream->pcm->device;
 	enum amdtp_stream_direction dir;
 	struct amdtp_stream *stream;
-	__be32 reg[2];
-	unsigned int count, size;
 	int err;
 
 	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
 		hw->formats = AM824_IN_PCM_FORMAT_BITS;
 		dir = AMDTP_IN_STREAM;
-		stream = &dice->tx_stream[substream->pcm->device];
-		err = snd_dice_transaction_read_tx(dice, TX_NUMBER, reg,
-						   sizeof(reg));
+		stream = &dice->tx_stream[index];
 	} else {
 		hw->formats = AM824_OUT_PCM_FORMAT_BITS;
 		dir = AMDTP_OUT_STREAM;
-		stream = &dice->rx_stream[substream->pcm->device];
-		err = snd_dice_transaction_read_rx(dice, RX_NUMBER, reg,
-						   sizeof(reg));
+		stream = &dice->rx_stream[index];
 	}
 
+	err = limit_channels_and_rates(dice, substream->runtime, dir,
+				       index);
 	if (err < 0)
 		return err;
 
-	count = min_t(unsigned int, be32_to_cpu(reg[0]), MAX_STREAMS);
-	if (substream->pcm->device >= count)
-		return -ENXIO;
-
-	size = be32_to_cpu(reg[1]) * 4;
-	err = limit_channels_and_rates(dice, substream->runtime, dir,
-				       substream->pcm->device, size);
+	err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
+				  dice_rate_constraint, substream,
+				  SNDRV_PCM_HW_PARAM_CHANNELS, -1);
+	if (err < 0)
+		return err;
+	err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
+				  dice_channels_constraint, substream,
+				  SNDRV_PCM_HW_PARAM_RATE, -1);
 	if (err < 0)
 		return err;
 
@@ -95,6 +165,8 @@ static int init_hw_info(struct snd_dice *dice,
 static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_dice *dice = substream->private_data;
+	unsigned int source;
+	bool internal;
 	int err;
 
 	err = snd_dice_stream_lock_try(dice);
@@ -105,6 +177,43 @@ static int pcm_open(struct snd_pcm_substream *substream)
 	if (err < 0)
 		goto err_locked;
 
+	err = snd_dice_transaction_get_clock_source(dice, &source);
+	if (err < 0)
+		goto err_locked;
+	switch (source) {
+	case CLOCK_SOURCE_AES1:
+	case CLOCK_SOURCE_AES2:
+	case CLOCK_SOURCE_AES3:
+	case CLOCK_SOURCE_AES4:
+	case CLOCK_SOURCE_AES_ANY:
+	case CLOCK_SOURCE_ADAT:
+	case CLOCK_SOURCE_TDIF:
+	case CLOCK_SOURCE_WC:
+		internal = false;
+		break;
+	default:
+		internal = true;
+		break;
+	}
+
+	/*
+	 * When source of clock is not internal or any PCM streams are running,
+	 * available sampling rate is limited at current sampling rate.
+	 */
+	if (!internal ||
+	    amdtp_stream_pcm_running(&dice->tx_stream[0]) ||
+	    amdtp_stream_pcm_running(&dice->tx_stream[1]) ||
+	    amdtp_stream_pcm_running(&dice->rx_stream[0]) ||
+	    amdtp_stream_pcm_running(&dice->rx_stream[1])) {
+		unsigned int rate;
+
+		err = snd_dice_transaction_get_rate(dice, &rate);
+		if (err < 0)
+			goto err_locked;
+		substream->runtime->hw.rate_min = rate;
+		substream->runtime->hw.rate_max = rate;
+	}
+
 	snd_pcm_set_sync(substream);
 end:
 	return err;
@@ -318,37 +427,19 @@ int snd_dice_create_pcm(struct snd_dice *dice)
 		.page      = snd_pcm_lib_get_vmalloc_page,
 		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
-	__be32 reg;
 	struct snd_pcm *pcm;
-	unsigned int i, max_capture, max_playback, capture, playback;
+	unsigned int capture, playback;
+	int i, j;
 	int err;
 
-	/* Check whether PCM substreams are required. */
-	if (dice->force_two_pcms) {
-		max_capture = max_playback = 2;
-	} else {
-		max_capture = max_playback = 0;
-		err = snd_dice_transaction_read_tx(dice, TX_NUMBER, &reg,
-						   sizeof(reg));
-		if (err < 0)
-			return err;
-		max_capture = min_t(unsigned int, be32_to_cpu(reg), MAX_STREAMS);
-
-		err = snd_dice_transaction_read_rx(dice, RX_NUMBER, &reg,
-						   sizeof(reg));
-		if (err < 0)
-			return err;
-		max_playback = min_t(unsigned int, be32_to_cpu(reg), MAX_STREAMS);
-	}
-
 	for (i = 0; i < MAX_STREAMS; i++) {
 		capture = playback = 0;
-		if (i < max_capture)
-			capture = 1;
-		if (i < max_playback)
-			playback = 1;
-		if (capture == 0 && playback == 0)
-			break;
+		for (j = 0; j < SND_DICE_RATE_MODE_COUNT; ++j) {
+			if (dice->tx_pcm_chs[i][j] > 0)
+				capture = 1;
+			if (dice->rx_pcm_chs[i][j] > 0)
+				playback = 1;
+		}
 
 		err = snd_pcm_new(dice->card, "DICE", i, playback, capture,
 				  &pcm);
diff --git a/sound/firewire/dice/dice-proc.c b/sound/firewire/dice/dice-proc.c
index f5c1d1bced59..bb870fc73f99 100644
--- a/sound/firewire/dice/dice-proc.c
+++ b/sound/firewire/dice/dice-proc.c
@@ -148,12 +148,12 @@ static void dice_proc_read(struct snd_info_entry *entry,
 				   >> CLOCK_RATE_SHIFT));
 	snd_iprintf(buffer, "  ext status: %08x\n", buf.global.extended_status);
 	snd_iprintf(buffer, "  sample rate: %u\n", buf.global.sample_rate);
-	snd_iprintf(buffer, "  version: %u.%u.%u.%u\n",
-		    (buf.global.version >> 24) & 0xff,
-		    (buf.global.version >> 16) & 0xff,
-		    (buf.global.version >>  8) & 0xff,
-		    (buf.global.version >>  0) & 0xff);
 	if (quadlets >= 90) {
+		snd_iprintf(buffer, "  version: %u.%u.%u.%u\n",
+			    (buf.global.version >> 24) & 0xff,
+			    (buf.global.version >> 16) & 0xff,
+			    (buf.global.version >>  8) & 0xff,
+			    (buf.global.version >>  0) & 0xff);
 		snd_iprintf(buffer, "  clock caps:");
 		for (i = 0; i <= 6; ++i)
 			if (buf.global.clock_caps & (1 << i))
@@ -243,10 +243,74 @@ static void dice_proc_read(struct snd_info_entry *entry,
 	}
 }
 
-void snd_dice_create_proc(struct snd_dice *dice)
+static void dice_proc_read_formation(struct snd_info_entry *entry,
+				     struct snd_info_buffer *buffer)
+{
+	static const char *const rate_labels[] = {
+		[SND_DICE_RATE_MODE_LOW]	= "low",
+		[SND_DICE_RATE_MODE_MIDDLE]	= "middle",
+		[SND_DICE_RATE_MODE_HIGH]	= "high",
+	};
+	struct snd_dice *dice = entry->private_data;
+	int i, j;
+
+	snd_iprintf(buffer, "Output stream from unit:\n");
+	for (i = 0; i < SND_DICE_RATE_MODE_COUNT; ++i)
+		snd_iprintf(buffer, "\t%s", rate_labels[i]);
+	snd_iprintf(buffer, "\tMIDI\n");
+	for (i = 0; i < MAX_STREAMS; ++i) {
+		snd_iprintf(buffer, "Tx %u:", i);
+		for (j = 0; j < SND_DICE_RATE_MODE_COUNT; ++j)
+			snd_iprintf(buffer, "\t%u", dice->tx_pcm_chs[i][j]);
+		snd_iprintf(buffer, "\t%u\n", dice->tx_midi_ports[i]);
+	}
+
+	snd_iprintf(buffer, "Input stream to unit:\n");
+	for (i = 0; i < SND_DICE_RATE_MODE_COUNT; ++i)
+		snd_iprintf(buffer, "\t%s", rate_labels[i]);
+	snd_iprintf(buffer, "\n");
+	for (i = 0; i < MAX_STREAMS; ++i) {
+		snd_iprintf(buffer, "Rx %u:", i);
+		for (j = 0; j < SND_DICE_RATE_MODE_COUNT; ++j)
+			snd_iprintf(buffer, "\t%u", dice->rx_pcm_chs[i][j]);
+		snd_iprintf(buffer, "\t%u\n", dice->rx_midi_ports[i]);
+	}
+}
+
+static void add_node(struct snd_dice *dice, struct snd_info_entry *root,
+		     const char *name,
+		     void (*op)(struct snd_info_entry *entry,
+				struct snd_info_buffer *buffer))
 {
 	struct snd_info_entry *entry;
 
-	if (!snd_card_proc_new(dice->card, "dice", &entry))
-		snd_info_set_text_ops(entry, dice, dice_proc_read);
+	entry = snd_info_create_card_entry(dice->card, name, root);
+	if (!entry)
+		return;
+
+	snd_info_set_text_ops(entry, dice, op);
+	if (snd_info_register(entry) < 0)
+		snd_info_free_entry(entry);
+}
+
+void snd_dice_create_proc(struct snd_dice *dice)
+{
+	struct snd_info_entry *root;
+
+	/*
+	 * All nodes are automatically removed at snd_card_disconnect(),
+	 * by following to link list.
+	 */
+	root = snd_info_create_card_entry(dice->card, "firewire",
+					  dice->card->proc_root);
+	if (!root)
+		return;
+	root->mode = S_IFDIR | 0555;
+	if (snd_info_register(root) < 0) {
+		snd_info_free_entry(root);
+		return;
+	}
+
+	add_node(dice, root, "dice", dice_proc_read);
+	add_node(dice, root, "formation", dice_proc_read_formation);
 }
diff --git a/sound/firewire/dice/dice-stream.c b/sound/firewire/dice/dice-stream.c
index 8573289c381e..c3c892c5c7ff 100644
--- a/sound/firewire/dice/dice-stream.c
+++ b/sound/firewire/dice/dice-stream.c
@@ -30,13 +30,43 @@ const unsigned int snd_dice_rates[SND_DICE_RATES_COUNT] = {
 	[6] = 192000,
 };
 
+int snd_dice_stream_get_rate_mode(struct snd_dice *dice, unsigned int rate,
+				  enum snd_dice_rate_mode *mode)
+{
+	/* Corresponding to each entry in snd_dice_rates. */
+	static const enum snd_dice_rate_mode modes[] = {
+		[0] = SND_DICE_RATE_MODE_LOW,
+		[1] = SND_DICE_RATE_MODE_LOW,
+		[2] = SND_DICE_RATE_MODE_LOW,
+		[3] = SND_DICE_RATE_MODE_MIDDLE,
+		[4] = SND_DICE_RATE_MODE_MIDDLE,
+		[5] = SND_DICE_RATE_MODE_HIGH,
+		[6] = SND_DICE_RATE_MODE_HIGH,
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(snd_dice_rates); i++) {
+		if (!(dice->clock_caps & BIT(i)))
+			continue;
+		if (snd_dice_rates[i] != rate)
+			continue;
+
+		*mode = modes[i];
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 /*
  * This operation has an effect to synchronize GLOBAL_STATUS/GLOBAL_SAMPLE_RATE
  * to GLOBAL_STATUS. Especially, just after powering on, these are different.
  */
-static int ensure_phase_lock(struct snd_dice *dice)
+static int ensure_phase_lock(struct snd_dice *dice, unsigned int rate)
 {
 	__be32 reg, nominal;
+	u32 data;
+	int i;
 	int err;
 
 	err = snd_dice_transaction_read_global(dice, GLOBAL_CLOCK_SELECT,
@@ -44,9 +74,21 @@ static int ensure_phase_lock(struct snd_dice *dice)
 	if (err < 0)
 		return err;
 
+	data = be32_to_cpu(reg);
+
+	data &= ~CLOCK_RATE_MASK;
+	for (i = 0; i < ARRAY_SIZE(snd_dice_rates); ++i) {
+		if (snd_dice_rates[i] == rate)
+			break;
+	}
+	if (i == ARRAY_SIZE(snd_dice_rates))
+		return -EINVAL;
+	data |= i << CLOCK_RATE_SHIFT;
+
 	if (completion_done(&dice->clock_accepted))
 		reinit_completion(&dice->clock_accepted);
 
+	reg = cpu_to_be32(data);
 	err = snd_dice_transaction_write_global(dice, GLOBAL_CLOCK_SELECT,
 						&reg, sizeof(reg));
 	if (err < 0)
@@ -192,6 +234,7 @@ static int start_streams(struct snd_dice *dice, enum amdtp_stream_direction dir,
 			 unsigned int rate, struct reg_params *params)
 {
 	__be32 reg[2];
+	enum snd_dice_rate_mode mode;
 	unsigned int i, pcm_chs, midi_ports;
 	struct amdtp_stream *streams;
 	struct fw_iso_resources *resources;
@@ -206,12 +249,23 @@ static int start_streams(struct snd_dice *dice, enum amdtp_stream_direction dir,
 		resources = dice->rx_resources;
 	}
 
+	err = snd_dice_stream_get_rate_mode(dice, rate, &mode);
+	if (err < 0)
+		return err;
+
 	for (i = 0; i < params->count; i++) {
+		unsigned int pcm_cache;
+		unsigned int midi_cache;
+
 		if (dir == AMDTP_IN_STREAM) {
+			pcm_cache = dice->tx_pcm_chs[i][mode];
+			midi_cache = dice->tx_midi_ports[i];
 			err = snd_dice_transaction_read_tx(dice,
 					params->size * i + TX_NUMBER_AUDIO,
 					reg, sizeof(reg));
 		} else {
+			pcm_cache = dice->rx_pcm_chs[i][mode];
+			midi_cache = dice->rx_midi_ports[i];
 			err = snd_dice_transaction_read_rx(dice,
 					params->size * i + RX_NUMBER_AUDIO,
 					reg, sizeof(reg));
@@ -221,6 +275,14 @@ static int start_streams(struct snd_dice *dice, enum amdtp_stream_direction dir,
 		pcm_chs = be32_to_cpu(reg[0]);
 		midi_ports = be32_to_cpu(reg[1]);
 
+		/* These are important for developer of this driver. */
+		if (pcm_chs != pcm_cache || midi_ports != midi_cache) {
+			dev_info(&dice->unit->device,
+				 "cache mismatch: pcm: %u:%u, midi: %u:%u\n",
+				 pcm_chs, pcm_cache, midi_ports, midi_cache);
+			return -EPROTO;
+		}
+
 		err = keep_resources(dice, dir, i, rate, pcm_chs, midi_ports);
 		if (err < 0)
 			return err;
@@ -256,6 +318,68 @@ static int start_streams(struct snd_dice *dice, enum amdtp_stream_direction dir,
 	return err;
 }
 
+static int start_duplex_streams(struct snd_dice *dice, unsigned int rate)
+{
+	struct reg_params tx_params, rx_params;
+	int i;
+	int err;
+
+	err = get_register_params(dice, &tx_params, &rx_params);
+	if (err < 0)
+		return err;
+
+	/* Stop transmission. */
+	stop_streams(dice, AMDTP_IN_STREAM, &tx_params);
+	stop_streams(dice, AMDTP_OUT_STREAM, &rx_params);
+	snd_dice_transaction_clear_enable(dice);
+	release_resources(dice);
+
+	err = ensure_phase_lock(dice, rate);
+	if (err < 0) {
+		dev_err(&dice->unit->device, "fail to ensure phase lock\n");
+		return err;
+	}
+
+	/* Likely to have changed stream formats. */
+	err = get_register_params(dice, &tx_params, &rx_params);
+	if (err < 0)
+		return err;
+
+	/* Start both streams. */
+	err = start_streams(dice, AMDTP_IN_STREAM, rate, &tx_params);
+	if (err < 0)
+		goto error;
+	err = start_streams(dice, AMDTP_OUT_STREAM, rate, &rx_params);
+	if (err < 0)
+		goto error;
+
+	err = snd_dice_transaction_set_enable(dice);
+	if (err < 0) {
+		dev_err(&dice->unit->device, "fail to enable interface\n");
+		goto error;
+	}
+
+	for (i = 0; i < MAX_STREAMS; i++) {
+		if ((i < tx_params.count &&
+		    !amdtp_stream_wait_callback(&dice->tx_stream[i],
+						CALLBACK_TIMEOUT)) ||
+		    (i < rx_params.count &&
+		     !amdtp_stream_wait_callback(&dice->rx_stream[i],
+						 CALLBACK_TIMEOUT))) {
+			err = -ETIMEDOUT;
+			goto error;
+		}
+	}
+
+	return 0;
+error:
+	stop_streams(dice, AMDTP_IN_STREAM, &tx_params);
+	stop_streams(dice, AMDTP_OUT_STREAM, &rx_params);
+	snd_dice_transaction_clear_enable(dice);
+	release_resources(dice);
+	return err;
+}
+
 /*
  * MEMO: After this function, there're two states of streams:
  *  - None streams are running.
@@ -265,17 +389,13 @@ int snd_dice_stream_start_duplex(struct snd_dice *dice, unsigned int rate)
 {
 	unsigned int curr_rate;
 	unsigned int i;
-	struct reg_params tx_params, rx_params;
-	bool need_to_start;
+	enum snd_dice_rate_mode mode;
 	int err;
 
 	if (dice->substreams_counter == 0)
 		return -EIO;
 
-	err = get_register_params(dice, &tx_params, &rx_params);
-	if (err < 0)
-		return err;
-
+	/* Check sampling transmission frequency. */
 	err = snd_dice_transaction_get_rate(dice, &curr_rate);
 	if (err < 0) {
 		dev_err(&dice->unit->device,
@@ -285,72 +405,36 @@ int snd_dice_stream_start_duplex(struct snd_dice *dice, unsigned int rate)
 	if (rate == 0)
 		rate = curr_rate;
 	if (rate != curr_rate)
-		return -EINVAL;
+		goto restart;
 
-	/* Judge to need to restart streams. */
-	for (i = 0; i < MAX_STREAMS; i++) {
-		if (i < tx_params.count) {
-			if (amdtp_streaming_error(&dice->tx_stream[i]) ||
-			    !amdtp_stream_running(&dice->tx_stream[i]))
-				break;
-		}
-		if (i < rx_params.count) {
-			if (amdtp_streaming_error(&dice->rx_stream[i]) ||
-			    !amdtp_stream_running(&dice->rx_stream[i]))
-				break;
-		}
+	/* Check error of packet streaming. */
+	for (i = 0; i < MAX_STREAMS; ++i) {
+		if (amdtp_streaming_error(&dice->tx_stream[i]))
+			break;
+		if (amdtp_streaming_error(&dice->rx_stream[i]))
+			break;
 	}
-	need_to_start = (i < MAX_STREAMS);
-
-	if (need_to_start) {
-		/* Stop transmission. */
-		snd_dice_transaction_clear_enable(dice);
-		stop_streams(dice, AMDTP_IN_STREAM, &tx_params);
-		stop_streams(dice, AMDTP_OUT_STREAM, &rx_params);
-		release_resources(dice);
-
-		err = ensure_phase_lock(dice);
-		if (err < 0) {
-			dev_err(&dice->unit->device,
-				"fail to ensure phase lock\n");
-			return err;
-		}
-
-		/* Start both streams. */
-		err = start_streams(dice, AMDTP_IN_STREAM, rate, &tx_params);
-		if (err < 0)
-			goto error;
-		err = start_streams(dice, AMDTP_OUT_STREAM, rate, &rx_params);
-		if (err < 0)
-			goto error;
-
-		err = snd_dice_transaction_set_enable(dice);
-		if (err < 0) {
-			dev_err(&dice->unit->device,
-				"fail to enable interface\n");
-			goto error;
-		}
+	if (i < MAX_STREAMS)
+		goto restart;
 
-		for (i = 0; i < MAX_STREAMS; i++) {
-			if ((i < tx_params.count &&
-			    !amdtp_stream_wait_callback(&dice->tx_stream[i],
-							CALLBACK_TIMEOUT)) ||
-			    (i < rx_params.count &&
-			     !amdtp_stream_wait_callback(&dice->rx_stream[i],
-							 CALLBACK_TIMEOUT))) {
-				err = -ETIMEDOUT;
-				goto error;
-			}
-		}
+	/* Check required streams are running or not. */
+	err = snd_dice_stream_get_rate_mode(dice, rate, &mode);
+	if (err < 0)
+		return err;
+	for (i = 0; i < MAX_STREAMS; ++i) {
+		if (dice->tx_pcm_chs[i][mode] > 0 &&
+		    !amdtp_stream_running(&dice->tx_stream[i]))
+			break;
+		if (dice->rx_pcm_chs[i][mode] > 0 &&
+		    !amdtp_stream_running(&dice->rx_stream[i]))
+			break;
 	}
+	if (i < MAX_STREAMS)
+		goto restart;
 
-	return err;
-error:
-	snd_dice_transaction_clear_enable(dice);
-	stop_streams(dice, AMDTP_IN_STREAM, &tx_params);
-	stop_streams(dice, AMDTP_OUT_STREAM, &rx_params);
-	release_resources(dice);
-	return err;
+	return 0;
+restart:
+	return start_duplex_streams(dice, rate);
 }
 
 /*
@@ -435,7 +519,7 @@ int snd_dice_stream_init_duplex(struct snd_dice *dice)
 		err = init_stream(dice, AMDTP_IN_STREAM, i);
 		if (err < 0) {
 			for (; i >= 0; i--)
-				destroy_stream(dice, AMDTP_OUT_STREAM, i);
+				destroy_stream(dice, AMDTP_IN_STREAM, i);
 			goto end;
 		}
 	}
@@ -484,6 +568,69 @@ void snd_dice_stream_update_duplex(struct snd_dice *dice)
 	}
 }
 
+int snd_dice_stream_detect_current_formats(struct snd_dice *dice)
+{
+	unsigned int rate;
+	enum snd_dice_rate_mode mode;
+	__be32 reg[2];
+	struct reg_params tx_params, rx_params;
+	int i;
+	int err;
+
+	/* If extended protocol is available, detect detail spec. */
+	err = snd_dice_detect_extension_formats(dice);
+	if (err >= 0)
+		return err;
+
+	/*
+	 * Available stream format is restricted at current mode of sampling
+	 * clock.
+	 */
+	err = snd_dice_transaction_get_rate(dice, &rate);
+	if (err < 0)
+		return err;
+
+	err = snd_dice_stream_get_rate_mode(dice, rate, &mode);
+	if (err < 0)
+		return err;
+
+	/*
+	 * Just after owning the unit (GLOBAL_OWNER), the unit can return
+	 * invalid stream formats. Selecting clock parameters have an effect
+	 * for the unit to refine it.
+	 */
+	err = ensure_phase_lock(dice, rate);
+	if (err < 0)
+		return err;
+
+	err = get_register_params(dice, &tx_params, &rx_params);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < tx_params.count; ++i) {
+		err = snd_dice_transaction_read_tx(dice,
+				tx_params.size * i + TX_NUMBER_AUDIO,
+				reg, sizeof(reg));
+		if (err < 0)
+			return err;
+		dice->tx_pcm_chs[i][mode] = be32_to_cpu(reg[0]);
+		dice->tx_midi_ports[i] = max_t(unsigned int,
+				be32_to_cpu(reg[1]), dice->tx_midi_ports[i]);
+	}
+	for (i = 0; i < rx_params.count; ++i) {
+		err = snd_dice_transaction_read_rx(dice,
+				rx_params.size * i + RX_NUMBER_AUDIO,
+				reg, sizeof(reg));
+		if (err < 0)
+			return err;
+		dice->rx_pcm_chs[i][mode] = be32_to_cpu(reg[0]);
+		dice->rx_midi_ports[i] = max_t(unsigned int,
+				be32_to_cpu(reg[1]), dice->rx_midi_ports[i]);
+	}
+
+	return 0;
+}
+
 static void dice_lock_changed(struct snd_dice *dice)
 {
 	dice->dev_lock_changed = true;
diff --git a/sound/firewire/dice/dice-tcelectronic.c b/sound/firewire/dice/dice-tcelectronic.c
new file mode 100644
index 000000000000..a8875d24ba2a
--- /dev/null
+++ b/sound/firewire/dice/dice-tcelectronic.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dice-tc_electronic.c - a part of driver for DICE based devices
+ *
+ * Copyright (c) 2018 Takashi Sakamoto
+ */
+
+#include "dice.h"
+
+struct dice_tc_spec {
+	unsigned int tx_pcm_chs[MAX_STREAMS][SND_DICE_RATE_MODE_COUNT];
+	unsigned int rx_pcm_chs[MAX_STREAMS][SND_DICE_RATE_MODE_COUNT];
+	bool has_midi;
+};
+
+static const struct dice_tc_spec desktop_konnekt6 = {
+	.tx_pcm_chs = {{6, 6, 2}, {0, 0, 0} },
+	.rx_pcm_chs = {{6, 6, 4}, {0, 0, 0} },
+	.has_midi = false,
+};
+
+static const struct dice_tc_spec impact_twin = {
+	.tx_pcm_chs = {{14, 10, 6}, {0, 0, 0} },
+	.rx_pcm_chs = {{14, 10, 6}, {0, 0, 0} },
+	.has_midi = true,
+};
+
+static const struct dice_tc_spec konnekt_8 = {
+	.tx_pcm_chs = {{4, 4, 3}, {0, 0, 0} },
+	.rx_pcm_chs = {{4, 4, 3}, {0, 0, 0} },
+	.has_midi = true,
+};
+
+static const struct dice_tc_spec konnekt_24d = {
+	.tx_pcm_chs = {{16, 16, 6}, {0, 0, 0} },
+	.rx_pcm_chs = {{16, 16, 6}, {0, 0, 0} },
+	.has_midi = true,
+};
+
+static const struct dice_tc_spec konnekt_live = {
+	.tx_pcm_chs = {{16, 16, 16}, {0, 0, 0} },
+	.rx_pcm_chs = {{16, 16, 16}, {0, 0, 0} },
+	.has_midi = true,
+};
+
+static const struct dice_tc_spec studio_konnekt_48 = {
+	.tx_pcm_chs = {{16, 16, 8}, {16, 16, 7} },
+	.rx_pcm_chs = {{16, 16, 8}, {14, 14, 7} },
+	.has_midi = true,
+};
+
+static const struct dice_tc_spec digital_konnekt_x32 = {
+	.tx_pcm_chs = {{16, 16, 4}, {0, 0, 0} },
+	.rx_pcm_chs = {{16, 16, 4}, {0, 0, 0} },
+	.has_midi = false,
+};
+
+int snd_dice_detect_tcelectronic_formats(struct snd_dice *dice)
+{
+	static const struct {
+		u32 model_id;
+		const struct dice_tc_spec *spec;
+	} *entry, entries[] = {
+		{0x00000020, &konnekt_24d},
+		{0x00000021, &konnekt_8},
+		{0x00000022, &studio_konnekt_48},
+		{0x00000023, &konnekt_live},
+		{0x00000024, &desktop_konnekt6},
+		{0x00000027, &impact_twin},
+		{0x00000030, &digital_konnekt_x32},
+	};
+	struct fw_csr_iterator it;
+	int key, val, model_id;
+	int i;
+
+	model_id = 0;
+	fw_csr_iterator_init(&it, dice->unit->directory);
+	while (fw_csr_iterator_next(&it, &key, &val)) {
+		if (key == CSR_MODEL) {
+			model_id = val;
+			break;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(entries); ++i) {
+		entry = entries + i;
+		if (entry->model_id == model_id)
+			break;
+	}
+	if (i == ARRAY_SIZE(entries))
+		return -ENODEV;
+
+	memcpy(dice->tx_pcm_chs, entry->spec->tx_pcm_chs,
+	       MAX_STREAMS * SND_DICE_RATE_MODE_COUNT * sizeof(unsigned int));
+	memcpy(dice->rx_pcm_chs, entry->spec->rx_pcm_chs,
+	       MAX_STREAMS * SND_DICE_RATE_MODE_COUNT * sizeof(unsigned int));
+
+	if (entry->spec->has_midi) {
+		dice->tx_midi_ports[0] = 1;
+		dice->rx_midi_ports[0] = 1;
+	}
+
+	return 0;
+}
diff --git a/sound/firewire/dice/dice-transaction.c b/sound/firewire/dice/dice-transaction.c
index 0f0350320ae8..b7e138b5abcf 100644
--- a/sound/firewire/dice/dice-transaction.c
+++ b/sound/firewire/dice/dice-transaction.c
@@ -265,7 +265,7 @@ int snd_dice_transaction_reinit(struct snd_dice *dice)
 static int get_subaddrs(struct snd_dice *dice)
 {
 	static const int min_values[10] = {
-		10, 0x64 / 4,
+		10, 0x60 / 4,
 		10, 0x18 / 4,
 		10, 0x18 / 4,
 		0, 0,
@@ -301,33 +301,40 @@ static int get_subaddrs(struct snd_dice *dice)
 		}
 	}
 
-	/*
-	 * Check that the implemented DICE driver specification major version
-	 * number matches.
-	 */
-	err = snd_fw_transaction(dice->unit, TCODE_READ_QUADLET_REQUEST,
-				 DICE_PRIVATE_SPACE +
-				 be32_to_cpu(pointers[0]) * 4 + GLOBAL_VERSION,
-				 &version, sizeof(version), 0);
-	if (err < 0)
-		goto end;
+	if (be32_to_cpu(pointers[1]) > 0x18) {
+		/*
+		 * Check that the implemented DICE driver specification major
+		 * version number matches.
+		 */
+		err = snd_fw_transaction(dice->unit, TCODE_READ_QUADLET_REQUEST,
+				DICE_PRIVATE_SPACE +
+				be32_to_cpu(pointers[0]) * 4 + GLOBAL_VERSION,
+				&version, sizeof(version), 0);
+		if (err < 0)
+			goto end;
 
-	if ((version & cpu_to_be32(0xff000000)) != cpu_to_be32(0x01000000)) {
-		dev_err(&dice->unit->device,
-			"unknown DICE version: 0x%08x\n", be32_to_cpu(version));
-		err = -ENODEV;
-		goto end;
+		if ((version & cpu_to_be32(0xff000000)) !=
+						cpu_to_be32(0x01000000)) {
+			dev_err(&dice->unit->device,
+				"unknown DICE version: 0x%08x\n",
+				be32_to_cpu(version));
+			err = -ENODEV;
+			goto end;
+		}
+
+		/* Set up later. */
+		dice->clock_caps = 1;
 	}
 
 	dice->global_offset = be32_to_cpu(pointers[0]) * 4;
 	dice->tx_offset = be32_to_cpu(pointers[2]) * 4;
 	dice->rx_offset = be32_to_cpu(pointers[4]) * 4;
-	dice->sync_offset = be32_to_cpu(pointers[6]) * 4;
-	dice->rsrv_offset = be32_to_cpu(pointers[8]) * 4;
 
-	/* Set up later. */
-	if (be32_to_cpu(pointers[1]) * 4 >= GLOBAL_CLOCK_CAPABILITIES + 4)
-		dice->clock_caps = 1;
+	/* Old firmware doesn't support these fields. */
+	if (pointers[7])
+		dice->sync_offset = be32_to_cpu(pointers[6]) * 4;
+	if (pointers[9])
+		dice->rsrv_offset = be32_to_cpu(pointers[8]) * 4;
 end:
 	kfree(pointers);
 	return err;
diff --git a/sound/firewire/dice/dice.c b/sound/firewire/dice/dice.c
index 4ddb4cdd054b..774eb2205668 100644
--- a/sound/firewire/dice/dice.c
+++ b/sound/firewire/dice/dice.c
@@ -14,41 +14,16 @@ MODULE_LICENSE("GPL v2");
 #define OUI_WEISS		0x001c6a
 #define OUI_LOUD		0x000ff2
 #define OUI_FOCUSRITE		0x00130e
-#define OUI_TCELECTRONIC	0x001486
+#define OUI_TCELECTRONIC	0x000166
+#define OUI_ALESIS		0x000595
+#define OUI_MAUDIO		0x000d6c
+#define OUI_MYTEK		0x001ee8
 
 #define DICE_CATEGORY_ID	0x04
 #define WEISS_CATEGORY_ID	0x00
 #define LOUD_CATEGORY_ID	0x10
 
-/*
- * Some models support several isochronous channels, while these streams are not
- * always available. In this case, add the model name to this list.
- */
-static bool force_two_pcm_support(struct fw_unit *unit)
-{
-	static const char *const models[] = {
-		/* TC Electronic models. */
-		"StudioKonnekt48",
-		/* Focusrite models. */
-		"SAFFIRE_PRO_40",
-		"LIQUID_SAFFIRE_56",
-		"SAFFIRE_PRO_40_1",
-	};
-	char model[32];
-	unsigned int i;
-	int err;
-
-	err = fw_csr_string(unit->directory, CSR_MODEL, model, sizeof(model));
-	if (err < 0)
-		return false;
-
-	for (i = 0; i < ARRAY_SIZE(models); i++) {
-		if (strcmp(models[i], model) == 0)
-			break;
-	}
-
-	return i < ARRAY_SIZE(models);
-}
+#define MODEL_ALESIS_IO_BOTH	0x000001
 
 static int check_dice_category(struct fw_unit *unit)
 {
@@ -75,11 +50,6 @@ static int check_dice_category(struct fw_unit *unit)
 		}
 	}
 
-	if (vendor == OUI_FOCUSRITE || vendor == OUI_TCELECTRONIC) {
-		if (force_two_pcm_support(unit))
-			return 0;
-	}
-
 	if (vendor == OUI_WEISS)
 		category = WEISS_CATEGORY_ID;
 	else if (vendor == OUI_LOUD)
@@ -186,9 +156,6 @@ static void do_registration(struct work_struct *work)
 	if (err < 0)
 		return;
 
-	if (force_two_pcm_support(dice->unit))
-		dice->force_two_pcms = true;
-
 	err = snd_dice_transaction_init(dice);
 	if (err < 0)
 		goto error;
@@ -199,6 +166,10 @@ static void do_registration(struct work_struct *work)
 
 	dice_card_strings(dice);
 
+	err = dice->detect_formats(dice);
+	if (err < 0)
+		goto error;
+
 	err = snd_dice_stream_init_duplex(dice);
 	if (err < 0)
 		goto error;
@@ -239,14 +210,17 @@ error:
 		 "Sound card registration failed: %d\n", err);
 }
 
-static int dice_probe(struct fw_unit *unit, const struct ieee1394_device_id *id)
+static int dice_probe(struct fw_unit *unit,
+		      const struct ieee1394_device_id *entry)
 {
 	struct snd_dice *dice;
 	int err;
 
-	err = check_dice_category(unit);
-	if (err < 0)
-		return -ENODEV;
+	if (!entry->driver_data) {
+		err = check_dice_category(unit);
+		if (err < 0)
+			return -ENODEV;
+	}
 
 	/* Allocate this independent of sound card instance. */
 	dice = kzalloc(sizeof(struct snd_dice), GFP_KERNEL);
@@ -256,6 +230,13 @@ static int dice_probe(struct fw_unit *unit, const struct ieee1394_device_id *id)
 	dice->unit = fw_unit_get(unit);
 	dev_set_drvdata(&unit->device, dice);
 
+	if (!entry->driver_data) {
+		dice->detect_formats = snd_dice_stream_detect_current_formats;
+	} else {
+		dice->detect_formats =
+				(snd_dice_detect_formats_t)entry->driver_data;
+	}
+
 	spin_lock_init(&dice->lock);
 	mutex_init(&dice->mutex);
 	init_completion(&dice->clock_accepted);
@@ -313,16 +294,97 @@ static void dice_bus_reset(struct fw_unit *unit)
 #define DICE_INTERFACE	0x000001
 
 static const struct ieee1394_device_id dice_id_table[] = {
+	/* M-Audio Profire 2626 has a different value in version field. */
 	{
-		.match_flags = IEEE1394_MATCH_VERSION,
-		.version     = DICE_INTERFACE,
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_MAUDIO,
+		.model_id	= 0x000010,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_extension_formats,
 	},
-	/* M-Audio Profire 610/2626 has a different value in version field. */
+	/* M-Audio Profire 610 has a different value in version field. */
 	{
 		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
-				  IEEE1394_MATCH_SPECIFIER_ID,
-		.vendor_id	= 0x000d6c,
-		.specifier_id	= 0x000d6c,
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_MAUDIO,
+		.model_id	= 0x000011,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_extension_formats,
+	},
+	/* TC Electronic Konnekt 24D. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_TCELECTRONIC,
+		.model_id	= 0x000020,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_tcelectronic_formats,
+	},
+	/* TC Electronic Konnekt 8. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_TCELECTRONIC,
+		.model_id	= 0x000021,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_tcelectronic_formats,
+	},
+	/* TC Electronic Studio Konnekt 48. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_TCELECTRONIC,
+		.model_id	= 0x000022,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_tcelectronic_formats,
+	},
+	/* TC Electronic Konnekt Live. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_TCELECTRONIC,
+		.model_id	= 0x000023,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_tcelectronic_formats,
+	},
+	/* TC Electronic Desktop Konnekt 6. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_TCELECTRONIC,
+		.model_id	= 0x000024,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_tcelectronic_formats,
+	},
+	/* TC Electronic Impact Twin. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_TCELECTRONIC,
+		.model_id	= 0x000027,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_tcelectronic_formats,
+	},
+	/* TC Electronic Digital Konnekt x32. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_TCELECTRONIC,
+		.model_id	= 0x000030,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_tcelectronic_formats,
+	},
+	/* Alesis iO14/iO26. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_ALESIS,
+		.model_id	= MODEL_ALESIS_IO_BOTH,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_alesis_formats,
+	},
+	/* Mytek Stereo 192 DSD-DAC. */
+	{
+		.match_flags	= IEEE1394_MATCH_VENDOR_ID |
+				  IEEE1394_MATCH_MODEL_ID,
+		.vendor_id	= OUI_MYTEK,
+		.model_id	= 0x000002,
+		.driver_data = (kernel_ulong_t)snd_dice_detect_mytek_formats,
+	},
+	{
+		.match_flags = IEEE1394_MATCH_VERSION,
+		.version     = DICE_INTERFACE,
 	},
 	{ }
 };
diff --git a/sound/firewire/dice/dice.h b/sound/firewire/dice/dice.h
index da00e75e09d4..83353a3559e8 100644
--- a/sound/firewire/dice/dice.h
+++ b/sound/firewire/dice/dice.h
@@ -63,6 +63,16 @@
  */
 #define MAX_STREAMS	2
 
+enum snd_dice_rate_mode {
+	SND_DICE_RATE_MODE_LOW = 0,
+	SND_DICE_RATE_MODE_MIDDLE,
+	SND_DICE_RATE_MODE_HIGH,
+	SND_DICE_RATE_MODE_COUNT,
+};
+
+struct snd_dice;
+typedef int (*snd_dice_detect_formats_t)(struct snd_dice *dice);
+
 struct snd_dice {
 	struct snd_card *card;
 	struct fw_unit *unit;
@@ -80,6 +90,11 @@ struct snd_dice {
 	unsigned int rsrv_offset;
 
 	unsigned int clock_caps;
+	unsigned int tx_pcm_chs[MAX_STREAMS][SND_DICE_RATE_MODE_COUNT];
+	unsigned int rx_pcm_chs[MAX_STREAMS][SND_DICE_RATE_MODE_COUNT];
+	unsigned int tx_midi_ports[MAX_STREAMS];
+	unsigned int rx_midi_ports[MAX_STREAMS];
+	snd_dice_detect_formats_t detect_formats;
 
 	struct fw_address_handler notification_handler;
 	int owner_generation;
@@ -98,8 +113,6 @@ struct snd_dice {
 	bool global_enabled;
 	struct completion clock_accepted;
 	unsigned int substreams_counter;
-
-	bool force_two_pcms;
 };
 
 enum snd_dice_addr_type {
@@ -190,11 +203,14 @@ void snd_dice_transaction_destroy(struct snd_dice *dice);
 #define SND_DICE_RATES_COUNT	7
 extern const unsigned int snd_dice_rates[SND_DICE_RATES_COUNT];
 
+int snd_dice_stream_get_rate_mode(struct snd_dice *dice, unsigned int rate,
+				  enum snd_dice_rate_mode *mode);
 int snd_dice_stream_start_duplex(struct snd_dice *dice, unsigned int rate);
 void snd_dice_stream_stop_duplex(struct snd_dice *dice);
 int snd_dice_stream_init_duplex(struct snd_dice *dice);
 void snd_dice_stream_destroy_duplex(struct snd_dice *dice);
 void snd_dice_stream_update_duplex(struct snd_dice *dice);
+int snd_dice_stream_detect_current_formats(struct snd_dice *dice);
 
 int snd_dice_stream_lock_try(struct snd_dice *dice);
 void snd_dice_stream_lock_release(struct snd_dice *dice);
@@ -207,4 +223,9 @@ void snd_dice_create_proc(struct snd_dice *dice);
 
 int snd_dice_create_midi(struct snd_dice *dice);
 
+int snd_dice_detect_tcelectronic_formats(struct snd_dice *dice);
+int snd_dice_detect_alesis_formats(struct snd_dice *dice);
+int snd_dice_detect_extension_formats(struct snd_dice *dice);
+int snd_dice_detect_mytek_formats(struct snd_dice *dice);
+
 #endif
diff --git a/sound/firewire/digi00x/digi00x-proc.c b/sound/firewire/digi00x/digi00x-proc.c
index a1d601f31165..6996d5a6ff5f 100644
--- a/sound/firewire/digi00x/digi00x-proc.c
+++ b/sound/firewire/digi00x/digi00x-proc.c
@@ -79,7 +79,7 @@ void snd_dg00x_proc_init(struct snd_dg00x *dg00x)
 	if (root == NULL)
 		return;
 
-	root->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	root->mode = S_IFDIR | 0555;
 	if (snd_info_register(root) < 0) {
 		snd_info_free_entry(root);
 		return;
diff --git a/sound/firewire/fireface/ff-proc.c b/sound/firewire/fireface/ff-proc.c
index 69441d121f71..40ccbfd8ef89 100644
--- a/sound/firewire/fireface/ff-proc.c
+++ b/sound/firewire/fireface/ff-proc.c
@@ -52,7 +52,7 @@ void snd_ff_proc_init(struct snd_ff *ff)
 					  ff->card->proc_root);
 	if (root == NULL)
 		return;
-	root->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	root->mode = S_IFDIR | 0555;
 	if (snd_info_register(root) < 0) {
 		snd_info_free_entry(root);
 		return;
diff --git a/sound/firewire/fireworks/fireworks_proc.c b/sound/firewire/fireworks/fireworks_proc.c
index 9c21f31b8b21..779ecec5af62 100644
--- a/sound/firewire/fireworks/fireworks_proc.c
+++ b/sound/firewire/fireworks/fireworks_proc.c
@@ -219,7 +219,7 @@ void snd_efw_proc_init(struct snd_efw *efw)
 					  efw->card->proc_root);
 	if (root == NULL)
 		return;
-	root->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	root->mode = S_IFDIR | 0555;
 	if (snd_info_register(root) < 0) {
 		snd_info_free_entry(root);
 		return;
diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c
index 46092fa3ff9b..3919e186a30b 100644
--- a/sound/firewire/isight.c
+++ b/sound/firewire/isight.c
@@ -569,18 +569,20 @@ static int isight_create_mixer(struct isight *isight)
 		return err;
 	isight->gain_max = be32_to_cpu(value);
 
-	isight->gain_tlv[0] = SNDRV_CTL_TLVT_DB_MINMAX;
-	isight->gain_tlv[1] = 2 * sizeof(unsigned int);
+	isight->gain_tlv[SNDRV_CTL_TLVO_TYPE] = SNDRV_CTL_TLVT_DB_MINMAX;
+	isight->gain_tlv[SNDRV_CTL_TLVO_LEN] = 2 * sizeof(unsigned int);
 
 	err = reg_read(isight, REG_GAIN_DB_START, &value);
 	if (err < 0)
 		return err;
-	isight->gain_tlv[2] = (s32)be32_to_cpu(value) * 100;
+	isight->gain_tlv[SNDRV_CTL_TLVO_DB_MINMAX_MIN] =
+						(s32)be32_to_cpu(value) * 100;
 
 	err = reg_read(isight, REG_GAIN_DB_END, &value);
 	if (err < 0)
 		return err;
-	isight->gain_tlv[3] = (s32)be32_to_cpu(value) * 100;
+	isight->gain_tlv[SNDRV_CTL_TLVO_DB_MINMAX_MAX] =
+						(s32)be32_to_cpu(value) * 100;
 
 	ctl = snd_ctl_new1(&gain_control, isight);
 	if (ctl)
diff --git a/sound/firewire/motu/motu-proc.c b/sound/firewire/motu/motu-proc.c
index 4edc064999ed..ab6830a6d242 100644
--- a/sound/firewire/motu/motu-proc.c
+++ b/sound/firewire/motu/motu-proc.c
@@ -107,7 +107,7 @@ void snd_motu_proc_init(struct snd_motu *motu)
 					  motu->card->proc_root);
 	if (root == NULL)
 		return;
-	root->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	root->mode = S_IFDIR | 0555;
 	if (snd_info_register(root) < 0) {
 		snd_info_free_entry(root);
 		return;
diff --git a/sound/firewire/oxfw/oxfw-proc.c b/sound/firewire/oxfw/oxfw-proc.c
index 8ba4f9f262b8..27dac071bc73 100644
--- a/sound/firewire/oxfw/oxfw-proc.c
+++ b/sound/firewire/oxfw/oxfw-proc.c
@@ -103,7 +103,7 @@ void snd_oxfw_proc_init(struct snd_oxfw *oxfw)
 					  oxfw->card->proc_root);
 	if (root == NULL)
 		return;
-	root->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	root->mode = S_IFDIR | 0555;
 	if (snd_info_register(root) < 0) {
 		snd_info_free_entry(root);
 		return;
diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c
index 413ab6313bb6..1e5b2c802635 100644
--- a/sound/firewire/oxfw/oxfw.c
+++ b/sound/firewire/oxfw/oxfw.c
@@ -49,7 +49,6 @@ static bool detect_loud_models(struct fw_unit *unit)
 		"Tapco LINK.firewire 4x6",
 		"U.420"};
 	char model[32];
-	unsigned int i;
 	int err;
 
 	err = fw_csr_string(unit->directory, CSR_MODEL,
@@ -57,12 +56,7 @@ static bool detect_loud_models(struct fw_unit *unit)
 	if (err < 0)
 		return false;
 
-	for (i = 0; i < ARRAY_SIZE(models); i++) {
-		if (strcmp(models[i], model) == 0)
-			break;
-	}
-
-	return (i < ARRAY_SIZE(models));
+	return match_string(models, ARRAY_SIZE(models), model) >= 0;
 }
 
 static int name_card(struct snd_oxfw *oxfw)
diff --git a/sound/firewire/tascam/tascam-proc.c b/sound/firewire/tascam/tascam-proc.c
index bfd4a4c06914..fee3bf32a0da 100644
--- a/sound/firewire/tascam/tascam-proc.c
+++ b/sound/firewire/tascam/tascam-proc.c
@@ -78,7 +78,7 @@ void snd_tscm_proc_init(struct snd_tscm *tscm)
 					  tscm->card->proc_root);
 	if (root == NULL)
 		return;
-	root->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	root->mode = S_IFDIR | 0555;
 	if (snd_info_register(root) < 0) {
 		snd_info_free_entry(root);
 		return;
diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c
index 47a358fab132..419e285e0226 100644
--- a/sound/hda/hdac_regmap.c
+++ b/sound/hda/hdac_regmap.c
@@ -65,10 +65,10 @@ static bool hda_writeable_reg(struct device *dev, unsigned int reg)
 {
 	struct hdac_device *codec = dev_to_hdac_dev(dev);
 	unsigned int verb = get_verb(reg);
+	const unsigned int *v;
 	int i;
 
-	for (i = 0; i < codec->vendor_verbs.used; i++) {
-		unsigned int *v = snd_array_elem(&codec->vendor_verbs, i);
+	snd_array_for_each(&codec->vendor_verbs, i, v) {
 		if (verb == *v)
 			return true;
 	}
diff --git a/sound/isa/cmi8328.c b/sound/isa/cmi8328.c
index d09e456107ad..de6ef1b1cf0e 100644
--- a/sound/isa/cmi8328.c
+++ b/sound/isa/cmi8328.c
@@ -192,7 +192,7 @@ static int snd_cmi8328_mixer(struct snd_wss *chip)
 }
 
 /* find index of an item in "-1"-ended array */
-int array_find(int array[], int item)
+static int array_find(int array[], int item)
 {
 	int i;
 
@@ -203,7 +203,7 @@ int array_find(int array[], int item)
 	return -1;
 }
 /* the same for long */
-int array_find_l(long array[], long item)
+static int array_find_l(long array[], long item)
 {
 	int i;
 
diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c
index 45e561c425bf..6c584d9b6c42 100644
--- a/sound/isa/msnd/msnd_pinnacle.c
+++ b/sound/isa/msnd/msnd_pinnacle.c
@@ -757,9 +757,9 @@ static int snd_msnd_pinnacle_cfg_reset(int cfg)
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
 
-module_param_array(index, int, NULL, S_IRUGO);
+module_param_array(index, int, NULL, 0444);
 MODULE_PARM_DESC(index, "Index value for msnd_pinnacle soundcard.");
-module_param_array(id, charp, NULL, S_IRUGO);
+module_param_array(id, charp, NULL, 0444);
 MODULE_PARM_DESC(id, "ID string for msnd_pinnacle soundcard.");
 
 static long io[SNDRV_CARDS] = SNDRV_DEFAULT_PORT;
@@ -801,22 +801,22 @@ MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(INITCODEFILE);
 MODULE_FIRMWARE(PERMCODEFILE);
 
-module_param_hw_array(io, long, ioport, NULL, S_IRUGO);
+module_param_hw_array(io, long, ioport, NULL, 0444);
 MODULE_PARM_DESC(io, "IO port #");
-module_param_hw_array(irq, int, irq, NULL, S_IRUGO);
-module_param_hw_array(mem, long, iomem, NULL, S_IRUGO);
-module_param_array(write_ndelay, int, NULL, S_IRUGO);
-module_param(calibrate_signal, int, S_IRUGO);
+module_param_hw_array(irq, int, irq, NULL, 0444);
+module_param_hw_array(mem, long, iomem, NULL, 0444);
+module_param_array(write_ndelay, int, NULL, 0444);
+module_param(calibrate_signal, int, 0444);
 #ifndef MSND_CLASSIC
-module_param_array(digital, int, NULL, S_IRUGO);
-module_param_hw_array(cfg, long, ioport, NULL, S_IRUGO);
-module_param_array(reset, int, 0, S_IRUGO);
-module_param_hw_array(mpu_io, long, ioport, NULL, S_IRUGO);
-module_param_hw_array(mpu_irq, int, irq, NULL, S_IRUGO);
-module_param_hw_array(ide_io0, long, ioport, NULL, S_IRUGO);
-module_param_hw_array(ide_io1, long, ioport, NULL, S_IRUGO);
-module_param_hw_array(ide_irq, int, irq, NULL, S_IRUGO);
-module_param_hw_array(joystick_io, long, ioport, NULL, S_IRUGO);
+module_param_array(digital, int, NULL, 0444);
+module_param_hw_array(cfg, long, ioport, NULL, 0444);
+module_param_array(reset, int, 0, 0444);
+module_param_hw_array(mpu_io, long, ioport, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
+module_param_hw_array(ide_io0, long, ioport, NULL, 0444);
+module_param_hw_array(ide_io1, long, ioport, NULL, 0444);
+module_param_hw_array(ide_irq, int, irq, NULL, 0444);
+module_param_hw_array(joystick_io, long, ioport, NULL, 0444);
 #endif
 
 
diff --git a/sound/isa/sc6000.c b/sound/isa/sc6000.c
index c09d9b914efe..a985e9183be9 100644
--- a/sound/isa/sc6000.c
+++ b/sound/isa/sc6000.c
@@ -592,7 +592,7 @@ static int snd_sc6000_probe(struct device *devptr, unsigned int dev)
 	*vport = devm_ioport_map(devptr, port[dev], 0x10);
 	if (*vport == NULL) {
 		snd_printk(KERN_ERR PFX
-			   "I/O port cannot be iomaped.\n");
+			   "I/O port cannot be iomapped.\n");
 		err = -EBUSY;
 		goto err_unmap1;
 	}
@@ -607,7 +607,7 @@ static int snd_sc6000_probe(struct device *devptr, unsigned int dev)
 	vmss_port = devm_ioport_map(devptr, mss_port[dev], 4);
 	if (!vmss_port) {
 		snd_printk(KERN_ERR PFX
-			   "MSS port I/O cannot be iomaped.\n");
+			   "MSS port I/O cannot be iomapped.\n");
 		err = -EBUSY;
 		goto err_unmap2;
 	}
diff --git a/sound/pci/ac97/ac97_proc.c b/sound/pci/ac97/ac97_proc.c
index 6320bf084e47..e120a11c69e8 100644
--- a/sound/pci/ac97/ac97_proc.c
+++ b/sound/pci/ac97/ac97_proc.c
@@ -448,7 +448,7 @@ void snd_ac97_proc_init(struct snd_ac97 * ac97)
 	if ((entry = snd_info_create_card_entry(ac97->bus->card, name, ac97->bus->proc)) != NULL) {
 		snd_info_set_text_ops(entry, ac97, snd_ac97_proc_regs_read);
 #ifdef CONFIG_SND_DEBUG
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 		entry->c.text.write = snd_ac97_proc_regs_write;
 #endif
 		if (snd_info_register(entry) < 0) {
@@ -474,7 +474,7 @@ void snd_ac97_bus_proc_init(struct snd_ac97_bus * bus)
 
 	sprintf(name, "codec97#%d", bus->num);
 	if ((entry = snd_info_create_card_entry(bus->card, name, bus->card->proc_root)) != NULL) {
-		entry->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+		entry->mode = S_IFDIR | 0555;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
 			entry = NULL;
diff --git a/sound/pci/ad1889.c b/sound/pci/ad1889.c
index 0bf2c04eeada..d9c54c08e2db 100644
--- a/sound/pci/ad1889.c
+++ b/sound/pci/ad1889.c
@@ -258,7 +258,7 @@ snd_ad1889_ac97_ready(struct snd_ad1889 *chip)
 	
 	while (!(ad1889_readw(chip, AD_AC97_ACIC) & AD_AC97_ACIC_ACRDY) 
 			&& --retry)
-		mdelay(1);
+		usleep_range(1000, 2000);
 	if (!retry) {
 		dev_err(chip->card->dev, "[%s] Link is not ready.\n",
 			__func__);
@@ -872,7 +872,7 @@ snd_ad1889_init(struct snd_ad1889 *chip)
 	ad1889_writew(chip, AD_DS_CCS, AD_DS_CCS_CLKEN); /* turn on clock */
 	ad1889_readw(chip, AD_DS_CCS);	/* flush posted write */
 
-	mdelay(10);
+	usleep_range(10000, 11000);
 
 	/* enable Master and Target abort interrupts */
 	ad1889_writel(chip, AD_DMA_DISR, AD_DMA_DISR_PMAE | AD_DMA_DISR_PTAE);
diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c
index 720361455c60..64e0961f93ba 100644
--- a/sound/pci/asihpi/asihpi.c
+++ b/sound/pci/asihpi/asihpi.c
@@ -69,27 +69,27 @@ static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
 static bool enable[SNDRV_CARDS] = SNDRV_DEFAULT_ENABLE_PNP;
 static bool enable_hpi_hwdep = 1;
 
-module_param_array(index, int, NULL, S_IRUGO);
+module_param_array(index, int, NULL, 0444);
 MODULE_PARM_DESC(index, "ALSA index value for AudioScience soundcard.");
 
-module_param_array(id, charp, NULL, S_IRUGO);
+module_param_array(id, charp, NULL, 0444);
 MODULE_PARM_DESC(id, "ALSA ID string for AudioScience soundcard.");
 
-module_param_array(enable, bool, NULL, S_IRUGO);
+module_param_array(enable, bool, NULL, 0444);
 MODULE_PARM_DESC(enable, "ALSA enable AudioScience soundcard.");
 
-module_param(enable_hpi_hwdep, bool, S_IRUGO|S_IWUSR);
+module_param(enable_hpi_hwdep, bool, 0644);
 MODULE_PARM_DESC(enable_hpi_hwdep,
 		"ALSA enable HPI hwdep for AudioScience soundcard ");
 
 /* identify driver */
 #ifdef KERNEL_ALSA_BUILD
 static char *build_info = "Built using headers from kernel source";
-module_param(build_info, charp, S_IRUGO);
+module_param(build_info, charp, 0444);
 MODULE_PARM_DESC(build_info, "Built using headers from kernel source");
 #else
 static char *build_info = "Built within ALSA source";
-module_param(build_info, charp, S_IRUGO);
+module_param(build_info, charp, 0444);
 MODULE_PARM_DESC(build_info, "Built within ALSA source");
 #endif
 
diff --git a/sound/pci/asihpi/hpimsginit.c b/sound/pci/asihpi/hpimsginit.c
index 7eb617175fde..a31a70dccecf 100644
--- a/sound/pci/asihpi/hpimsginit.c
+++ b/sound/pci/asihpi/hpimsginit.c
@@ -23,6 +23,7 @@
 
 #include "hpi_internal.h"
 #include "hpimsginit.h"
+#include <linux/nospec.h>
 
 /* The actual message size for each object type */
 static u16 msg_size[HPI_OBJ_MAXINDEX + 1] = HPI_MESSAGE_SIZE_BY_OBJECT;
@@ -39,10 +40,12 @@ static void hpi_init_message(struct hpi_message *phm, u16 object,
 {
 	u16 size;
 
-	if ((object > 0) && (object <= HPI_OBJ_MAXINDEX))
+	if ((object > 0) && (object <= HPI_OBJ_MAXINDEX)) {
+		object = array_index_nospec(object, HPI_OBJ_MAXINDEX + 1);
 		size = msg_size[object];
-	else
+	} else {
 		size = sizeof(*phm);
+	}
 
 	memset(phm, 0, size);
 	phm->size = size;
@@ -66,10 +69,12 @@ void hpi_init_response(struct hpi_response *phr, u16 object, u16 function,
 {
 	u16 size;
 
-	if ((object > 0) && (object <= HPI_OBJ_MAXINDEX))
+	if ((object > 0) && (object <= HPI_OBJ_MAXINDEX)) {
+		object = array_index_nospec(object, HPI_OBJ_MAXINDEX + 1);
 		size = res_size[object];
-	else
+	} else {
 		size = sizeof(*phr);
+	}
 
 	memset(phr, 0, sizeof(*phr));
 	phr->size = size;
diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c
index 5badd08e1d69..7d049569012c 100644
--- a/sound/pci/asihpi/hpioctl.c
+++ b/sound/pci/asihpi/hpioctl.c
@@ -33,6 +33,7 @@
 #include <linux/stringify.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
+#include <linux/nospec.h>
 
 #ifdef MODULE_FIRMWARE
 MODULE_FIRMWARE("asihpi/dsp5000.bin");
@@ -45,14 +46,14 @@ MODULE_FIRMWARE("asihpi/dsp8900.bin");
 #endif
 
 static int prealloc_stream_buf;
-module_param(prealloc_stream_buf, int, S_IRUGO);
+module_param(prealloc_stream_buf, int, 0444);
 MODULE_PARM_DESC(prealloc_stream_buf,
 	"Preallocate size for per-adapter stream buffer");
 
 /* Allow the debug level to be changed after module load.
  E.g.   echo 2 > /sys/module/asihpi/parameters/hpiDebugLevel
 */
-module_param(hpi_debug_level, int, S_IRUGO | S_IWUSR);
+module_param(hpi_debug_level, int, 0644);
 MODULE_PARM_DESC(hpi_debug_level, "debug verbosity 0..5");
 
 /* List of adapters found */
@@ -186,7 +187,8 @@ long asihpi_hpi_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		struct hpi_adapter *pa = NULL;
 
 		if (hm->h.adapter_index < ARRAY_SIZE(adapters))
-			pa = &adapters[hm->h.adapter_index];
+			pa = &adapters[array_index_nospec(hm->h.adapter_index,
+							  ARRAY_SIZE(adapters))];
 
 		if (!pa || !pa->adapter || !pa->adapter->type) {
 			hpi_init_response(&hr->r0, hm->h.object,
diff --git a/sound/pci/ca0106/ca0106_proc.c b/sound/pci/ca0106/ca0106_proc.c
index 9b2b8b38122f..a2c85cc37972 100644
--- a/sound/pci/ca0106/ca0106_proc.c
+++ b/sound/pci/ca0106/ca0106_proc.c
@@ -431,7 +431,7 @@ int snd_ca0106_proc_init(struct snd_ca0106 *emu)
 	if(! snd_card_proc_new(emu->card, "ca0106_reg32", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_ca0106_proc_reg_read32);
 		entry->c.text.write = snd_ca0106_proc_reg_write32;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if(! snd_card_proc_new(emu->card, "ca0106_reg16", &entry))
 		snd_info_set_text_ops(entry, emu, snd_ca0106_proc_reg_read16);
@@ -440,12 +440,12 @@ int snd_ca0106_proc_init(struct snd_ca0106 *emu)
 	if(! snd_card_proc_new(emu->card, "ca0106_regs1", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_ca0106_proc_reg_read1);
 		entry->c.text.write = snd_ca0106_proc_reg_write;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if(! snd_card_proc_new(emu->card, "ca0106_i2c", &entry)) {
 		entry->c.text.write = snd_ca0106_proc_i2c_write;
 		entry->private_data = emu;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if(! snd_card_proc_new(emu->card, "ca0106_regs2", &entry)) 
 		snd_info_set_text_ops(entry, emu, snd_ca0106_proc_reg_read2);
diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c
index 26a657870664..452cc79b44af 100644
--- a/sound/pci/cmipci.c
+++ b/sound/pci/cmipci.c
@@ -1139,7 +1139,7 @@ static int save_mixer_state(struct cmipci *cm)
 		struct snd_ctl_elem_value *val;
 		unsigned int i;
 
-		val = kmalloc(sizeof(*val), GFP_ATOMIC);
+		val = kmalloc(sizeof(*val), GFP_KERNEL);
 		if (!val)
 			return -ENOMEM;
 		for (i = 0; i < CM_SAVED_MIXERS; i++) {
diff --git a/sound/pci/cs46xx/cs46xx.c b/sound/pci/cs46xx/cs46xx.c
index 655fbea1692c..4910d3f46d4b 100644
--- a/sound/pci/cs46xx/cs46xx.c
+++ b/sound/pci/cs46xx/cs46xx.c
@@ -58,7 +58,7 @@ MODULE_PARM_DESC(id, "ID string for the CS46xx soundcard.");
 module_param_array(enable, bool, NULL, 0444);
 MODULE_PARM_DESC(enable, "Enable CS46xx soundcard.");
 module_param_array(external_amp, bool, NULL, 0444);
-MODULE_PARM_DESC(external_amp, "Force to enable external amplifer.");
+MODULE_PARM_DESC(external_amp, "Force to enable external amplifier.");
 module_param_array(thinkpad, bool, NULL, 0444);
 MODULE_PARM_DESC(thinkpad, "Force to enable Thinkpad's CLKRUN control.");
 module_param_array(mmap_valid, bool, NULL, 0444);
diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c
index 0020fd0efc46..ed1251c5f449 100644
--- a/sound/pci/cs46xx/cs46xx_lib.c
+++ b/sound/pci/cs46xx/cs46xx_lib.c
@@ -2849,7 +2849,7 @@ static int snd_cs46xx_proc_init(struct snd_card *card, struct snd_cs46xx *chip)
 			entry->private_data = chip;
 			entry->c.ops = &snd_cs46xx_proc_io_ops;
 			entry->size = region->size;
-			entry->mode = S_IFREG | S_IRUSR;
+			entry->mode = S_IFREG | 0400;
 		}
 	}
 #ifdef CONFIG_SND_CS46XX_NEW_DSP
diff --git a/sound/pci/cs46xx/dsp_spos.c b/sound/pci/cs46xx/dsp_spos.c
index aa61615288ff..c44eadef64ae 100644
--- a/sound/pci/cs46xx/dsp_spos.c
+++ b/sound/pci/cs46xx/dsp_spos.c
@@ -798,7 +798,7 @@ int cs46xx_dsp_proc_init (struct snd_card *card, struct snd_cs46xx *chip)
 
 	if ((entry = snd_info_create_card_entry(card, "dsp", card->proc_root)) != NULL) {
 		entry->content = SNDRV_INFO_CONTENT_TEXT;
-		entry->mode = S_IFDIR | S_IRUGO | S_IXUGO;
+		entry->mode = S_IFDIR | 0555;
       
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
@@ -814,7 +814,7 @@ int cs46xx_dsp_proc_init (struct snd_card *card, struct snd_cs46xx *chip)
 	if ((entry = snd_info_create_card_entry(card, "spos_symbols", ins->proc_dsp_dir)) != NULL) {
 		entry->content = SNDRV_INFO_CONTENT_TEXT;
 		entry->private_data = chip;
-		entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+		entry->mode = S_IFREG | 0644;
 		entry->c.text.read = cs46xx_dsp_proc_symbol_table_read;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
@@ -826,7 +826,7 @@ int cs46xx_dsp_proc_init (struct snd_card *card, struct snd_cs46xx *chip)
 	if ((entry = snd_info_create_card_entry(card, "spos_modules", ins->proc_dsp_dir)) != NULL) {
 		entry->content = SNDRV_INFO_CONTENT_TEXT;
 		entry->private_data = chip;
-		entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+		entry->mode = S_IFREG | 0644;
 		entry->c.text.read = cs46xx_dsp_proc_modules_read;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
@@ -838,7 +838,7 @@ int cs46xx_dsp_proc_init (struct snd_card *card, struct snd_cs46xx *chip)
 	if ((entry = snd_info_create_card_entry(card, "parameter", ins->proc_dsp_dir)) != NULL) {
 		entry->content = SNDRV_INFO_CONTENT_TEXT;
 		entry->private_data = chip;
-		entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+		entry->mode = S_IFREG | 0644;
 		entry->c.text.read = cs46xx_dsp_proc_parameter_dump_read;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
@@ -850,7 +850,7 @@ int cs46xx_dsp_proc_init (struct snd_card *card, struct snd_cs46xx *chip)
 	if ((entry = snd_info_create_card_entry(card, "sample", ins->proc_dsp_dir)) != NULL) {
 		entry->content = SNDRV_INFO_CONTENT_TEXT;
 		entry->private_data = chip;
-		entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+		entry->mode = S_IFREG | 0644;
 		entry->c.text.read = cs46xx_dsp_proc_sample_dump_read;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
@@ -862,7 +862,7 @@ int cs46xx_dsp_proc_init (struct snd_card *card, struct snd_cs46xx *chip)
 	if ((entry = snd_info_create_card_entry(card, "task_tree", ins->proc_dsp_dir)) != NULL) {
 		entry->content = SNDRV_INFO_CONTENT_TEXT;
 		entry->private_data = chip;
-		entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+		entry->mode = S_IFREG | 0644;
 		entry->c.text.read = cs46xx_dsp_proc_task_tree_read;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
@@ -874,7 +874,7 @@ int cs46xx_dsp_proc_init (struct snd_card *card, struct snd_cs46xx *chip)
 	if ((entry = snd_info_create_card_entry(card, "scb_info", ins->proc_dsp_dir)) != NULL) {
 		entry->content = SNDRV_INFO_CONTENT_TEXT;
 		entry->private_data = chip;
-		entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+		entry->mode = S_IFREG | 0644;
 		entry->c.text.read = cs46xx_dsp_proc_scb_read;
 		if (snd_info_register(entry) < 0) {
 			snd_info_free_entry(entry);
diff --git a/sound/pci/cs46xx/dsp_spos_scb_lib.c b/sound/pci/cs46xx/dsp_spos_scb_lib.c
index 7488e1b7a770..abb01ce66983 100644
--- a/sound/pci/cs46xx/dsp_spos_scb_lib.c
+++ b/sound/pci/cs46xx/dsp_spos_scb_lib.c
@@ -271,7 +271,7 @@ void cs46xx_dsp_proc_register_scb_desc (struct snd_cs46xx *chip,
       
 			entry->content = SNDRV_INFO_CONTENT_TEXT;
 			entry->private_data = scb_info;
-			entry->mode = S_IFREG | S_IRUGO | S_IWUSR;
+			entry->mode = S_IFREG | 0644;
       
 			entry->c.text.read = cs46xx_dsp_proc_scb_info_read;
       
diff --git a/sound/pci/ctxfi/cttimer.c b/sound/pci/ctxfi/cttimer.c
index 08e874e9a7f6..2099e9ce441a 100644
--- a/sound/pci/ctxfi/cttimer.c
+++ b/sound/pci/ctxfi/cttimer.c
@@ -17,7 +17,7 @@
 
 static bool use_system_timer;
 MODULE_PARM_DESC(use_system_timer, "Force to use system-timer");
-module_param(use_system_timer, bool, S_IRUGO);
+module_param(use_system_timer, bool, 0444);
 
 struct ct_timer_ops {
 	void (*init)(struct ct_timer_instance *);
diff --git a/sound/pci/ctxfi/xfi.c b/sound/pci/ctxfi/xfi.c
index f2f32779de98..b2874220be1b 100644
--- a/sound/pci/ctxfi/xfi.c
+++ b/sound/pci/ctxfi/xfi.c
@@ -26,9 +26,9 @@ MODULE_SUPPORTED_DEVICE("{{Creative Labs, Sound Blaster X-Fi}");
 static unsigned int reference_rate = 48000;
 static unsigned int multiple = 2;
 MODULE_PARM_DESC(reference_rate, "Reference rate (default=48000)");
-module_param(reference_rate, uint, S_IRUGO);
+module_param(reference_rate, uint, 0444);
 MODULE_PARM_DESC(multiple, "Rate multiplier (default=2)");
-module_param(multiple, uint, S_IRUGO);
+module_param(multiple, uint, 0444);
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index 0935a5c8741f..358ef7dcf410 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -59,7 +59,7 @@ static int get_firmware(const struct firmware **fw_entry,
 	dev_dbg(chip->card->dev,
 		"firmware requested: %s\n", card_fw[fw_index].data);
 	snprintf(name, sizeof(name), "ea/%s", card_fw[fw_index].data);
-	err = request_firmware(fw_entry, name, pci_device(chip));
+	err = request_firmware(fw_entry, name, &chip->pci->dev);
 	if (err < 0)
 		dev_err(chip->card->dev,
 			"get_firmware(): Firmware not available (%d)\n", err);
diff --git a/sound/pci/echoaudio/echoaudio.h b/sound/pci/echoaudio/echoaudio.h
index 152ce158583c..44b390a667d5 100644
--- a/sound/pci/echoaudio/echoaudio.h
+++ b/sound/pci/echoaudio/echoaudio.h
@@ -559,10 +559,4 @@ static inline int monitor_index(const struct echoaudio *chip, int out, int in)
 	return out * num_busses_in(chip) + in;
 }
 
-
-#ifndef pci_device
-#define pci_device(chip) (&chip->pci->dev)
-#endif
-
-
 #endif /* _ECHOAUDIO_H_ */
diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c
index 2c2b12a06177..611589cbdad6 100644
--- a/sound/pci/emu10k1/emu10k1x.c
+++ b/sound/pci/emu10k1/emu10k1x.c
@@ -1070,7 +1070,7 @@ static int snd_emu10k1x_proc_init(struct emu10k1x *emu)
 	if(! snd_card_proc_new(emu->card, "emu10k1x_regs", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_emu10k1x_proc_reg_read);
 		entry->c.text.write = snd_emu10k1x_proc_reg_write;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 		entry->private_data = emu;
 	}
 	
diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c
index a2b56b188be4..b45a01bb73e5 100644
--- a/sound/pci/emu10k1/emufx.c
+++ b/sound/pci/emu10k1/emufx.c
@@ -170,7 +170,7 @@ static char *audigy_outs[32] = {
 	/* 0x0f */ "Rear Right",
 	/* 0x10 */ "AC97 Front Left",
 	/* 0x11 */ "AC97 Front Right",
-	/* 0x12 */ "ADC Caputre Left",
+	/* 0x12 */ "ADC Capture Left",
 	/* 0x13 */ "ADC Capture Right",
 	/* 0x14 */ NULL,
 	/* 0x15 */ NULL,
@@ -421,14 +421,10 @@ int snd_emu10k1_fx8010_register_irq_handler(struct snd_emu10k1 *emu,
 					    snd_fx8010_irq_handler_t *handler,
 					    unsigned char gpr_running,
 					    void *private_data,
-					    struct snd_emu10k1_fx8010_irq **r_irq)
+					    struct snd_emu10k1_fx8010_irq *irq)
 {
-	struct snd_emu10k1_fx8010_irq *irq;
 	unsigned long flags;
 	
-	irq = kmalloc(sizeof(*irq), GFP_ATOMIC);
-	if (irq == NULL)
-		return -ENOMEM;
 	irq->handler = handler;
 	irq->gpr_running = gpr_running;
 	irq->private_data = private_data;
@@ -443,8 +439,6 @@ int snd_emu10k1_fx8010_register_irq_handler(struct snd_emu10k1 *emu,
 		emu->fx8010.irq_handlers = irq;
 	}
 	spin_unlock_irqrestore(&emu->fx8010.irq_lock, flags);
-	if (r_irq)
-		*r_irq = irq;
 	return 0;
 }
 
@@ -468,7 +462,6 @@ int snd_emu10k1_fx8010_unregister_irq_handler(struct snd_emu10k1 *emu,
 			tmp->next = tmp->next->next;
 	}
 	spin_unlock_irqrestore(&emu->fx8010.irq_lock, flags);
-	kfree(irq);
 	return 0;
 }
 
diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index cefe613ef7b7..d39458ab251f 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -1724,7 +1724,7 @@ static int snd_emu10k1_fx8010_playback_trigger(struct snd_pcm_substream *substre
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-		snd_emu10k1_fx8010_unregister_irq_handler(emu, pcm->irq); pcm->irq = NULL;
+		snd_emu10k1_fx8010_unregister_irq_handler(emu, &pcm->irq);
 		snd_emu10k1_ptr_write(emu, emu->gpr_base + pcm->gpr_trigger, 0, 0);
 		pcm->tram_pos = INITIAL_TRAM_POS(pcm->buffer_size);
 		pcm->tram_shift = 0;
diff --git a/sound/pci/emu10k1/emuproc.c b/sound/pci/emu10k1/emuproc.c
index bde0d1954f56..b57008031792 100644
--- a/sound/pci/emu10k1/emuproc.c
+++ b/sound/pci/emu10k1/emuproc.c
@@ -135,7 +135,7 @@ static void snd_emu10k1_proc_read(struct snd_info_entry *entry,
 		/* 15 */ "Rear Right",
 		/* 16 */ "AC97 Front Left",
 		/* 17 */ "AC97 Front Right",
-		/* 18 */ "ADC Caputre Left",
+		/* 18 */ "ADC Capture Left",
 		/* 19 */ "ADC Capture Right",
 		/* 20 */ "???",
 		/* 21 */ "???",
@@ -574,32 +574,32 @@ int snd_emu10k1_proc_init(struct snd_emu10k1 *emu)
 	if (! snd_card_proc_new(emu->card, "io_regs", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_emu_proc_io_reg_read);
 		entry->c.text.write = snd_emu_proc_io_reg_write;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if (! snd_card_proc_new(emu->card, "ptr_regs00a", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_emu_proc_ptr_reg_read00a);
 		entry->c.text.write = snd_emu_proc_ptr_reg_write00;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if (! snd_card_proc_new(emu->card, "ptr_regs00b", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_emu_proc_ptr_reg_read00b);
 		entry->c.text.write = snd_emu_proc_ptr_reg_write00;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if (! snd_card_proc_new(emu->card, "ptr_regs20a", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_emu_proc_ptr_reg_read20a);
 		entry->c.text.write = snd_emu_proc_ptr_reg_write20;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if (! snd_card_proc_new(emu->card, "ptr_regs20b", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_emu_proc_ptr_reg_read20b);
 		entry->c.text.write = snd_emu_proc_ptr_reg_write20;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if (! snd_card_proc_new(emu->card, "ptr_regs20c", &entry)) {
 		snd_info_set_text_ops(entry, emu, snd_emu_proc_ptr_reg_read20c);
 		entry->c.text.write = snd_emu_proc_ptr_reg_write20;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 #endif
 	
@@ -621,35 +621,35 @@ int snd_emu10k1_proc_init(struct snd_emu10k1 *emu)
 	if (! snd_card_proc_new(emu->card, "fx8010_gpr", &entry)) {
 		entry->content = SNDRV_INFO_CONTENT_DATA;
 		entry->private_data = emu;
-		entry->mode = S_IFREG | S_IRUGO /*| S_IWUSR*/;
+		entry->mode = S_IFREG | 0444 /*| S_IWUSR*/;
 		entry->size = emu->audigy ? A_TOTAL_SIZE_GPR : TOTAL_SIZE_GPR;
 		entry->c.ops = &snd_emu10k1_proc_ops_fx8010;
 	}
 	if (! snd_card_proc_new(emu->card, "fx8010_tram_data", &entry)) {
 		entry->content = SNDRV_INFO_CONTENT_DATA;
 		entry->private_data = emu;
-		entry->mode = S_IFREG | S_IRUGO /*| S_IWUSR*/;
+		entry->mode = S_IFREG | 0444 /*| S_IWUSR*/;
 		entry->size = emu->audigy ? A_TOTAL_SIZE_TANKMEM_DATA : TOTAL_SIZE_TANKMEM_DATA ;
 		entry->c.ops = &snd_emu10k1_proc_ops_fx8010;
 	}
 	if (! snd_card_proc_new(emu->card, "fx8010_tram_addr", &entry)) {
 		entry->content = SNDRV_INFO_CONTENT_DATA;
 		entry->private_data = emu;
-		entry->mode = S_IFREG | S_IRUGO /*| S_IWUSR*/;
+		entry->mode = S_IFREG | 0444 /*| S_IWUSR*/;
 		entry->size = emu->audigy ? A_TOTAL_SIZE_TANKMEM_ADDR : TOTAL_SIZE_TANKMEM_ADDR ;
 		entry->c.ops = &snd_emu10k1_proc_ops_fx8010;
 	}
 	if (! snd_card_proc_new(emu->card, "fx8010_code", &entry)) {
 		entry->content = SNDRV_INFO_CONTENT_DATA;
 		entry->private_data = emu;
-		entry->mode = S_IFREG | S_IRUGO /*| S_IWUSR*/;
+		entry->mode = S_IFREG | 0444 /*| S_IWUSR*/;
 		entry->size = emu->audigy ? A_TOTAL_SIZE_CODE : TOTAL_SIZE_CODE;
 		entry->c.ops = &snd_emu10k1_proc_ops_fx8010;
 	}
 	if (! snd_card_proc_new(emu->card, "fx8010_acode", &entry)) {
 		entry->content = SNDRV_INFO_CONTENT_TEXT;
 		entry->private_data = emu;
-		entry->mode = S_IFREG | S_IRUGO /*| S_IWUSR*/;
+		entry->mode = S_IFREG | 0444 /*| S_IWUSR*/;
 		entry->c.text.read = snd_emu10k1_proc_acode_read;
 	}
 	return 0;
diff --git a/sound/pci/emu10k1/memory.c b/sound/pci/emu10k1/memory.c
index 5865f3b90b34..dbc7d8d0e1c4 100644
--- a/sound/pci/emu10k1/memory.c
+++ b/sound/pci/emu10k1/memory.c
@@ -248,13 +248,13 @@ __found_pages:
 static int is_valid_page(struct snd_emu10k1 *emu, dma_addr_t addr)
 {
 	if (addr & ~emu->dma_mask) {
-		dev_err(emu->card->dev,
+		dev_err_ratelimited(emu->card->dev,
 			"max memory size is 0x%lx (addr = 0x%lx)!!\n",
 			emu->dma_mask, (unsigned long)addr);
 		return 0;
 	}
 	if (addr & (EMUPAGESIZE-1)) {
-		dev_err(emu->card->dev, "page is not aligned\n");
+		dev_err_ratelimited(emu->card->dev, "page is not aligned\n");
 		return 0;
 	}
 	return 1;
@@ -345,7 +345,7 @@ snd_emu10k1_alloc_pages(struct snd_emu10k1 *emu, struct snd_pcm_substream *subst
 		else
 			addr = snd_pcm_sgbuf_get_addr(substream, ofs);
 		if (! is_valid_page(emu, addr)) {
-			dev_err(emu->card->dev,
+			dev_err_ratelimited(emu->card->dev,
 				"emu: failure page = %d\n", idx);
 			mutex_unlock(&hdr->block_mutex);
 			return NULL;
diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index f7a492c382d9..4235907b7858 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -127,11 +127,15 @@ comment "Set to Y if you want auto-loading the codec driver"
 
 config SND_HDA_CODEC_HDMI
 	tristate "Build HDMI/DisplayPort HD-audio codec support"
+	select SND_DYNAMIC_MINORS
 	help
 	  Say Y or M here to include HDMI and DisplayPort HD-audio codec
 	  support in snd-hda-intel driver.  This includes all AMD/ATI,
 	  Intel and Nvidia HDMI/DisplayPort codecs.
 
+	  Note that this option mandatorily enables CONFIG_SND_DYNAMIC_MINORS
+	  to assure the multiple streams for DP-MST support.
+
 comment "Set to Y if you want auto-loading the codec driver"
 	depends on SND_HDA=y && SND_HDA_CODEC_HDMI=m
 
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index d3ea73171a3d..b9a6b66aeb0e 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -793,11 +793,11 @@ EXPORT_SYMBOL_GPL(snd_hda_add_verbs);
  */
 void snd_hda_apply_verbs(struct hda_codec *codec)
 {
+	const struct hda_verb **v;
 	int i;
-	for (i = 0; i < codec->verbs.used; i++) {
-		struct hda_verb **v = snd_array_elem(&codec->verbs, i);
+
+	snd_array_for_each(&codec->verbs, i, v)
 		snd_hda_sequence_write(codec, *v);
-	}
 }
 EXPORT_SYMBOL_GPL(snd_hda_apply_verbs);
 
@@ -890,10 +890,10 @@ EXPORT_SYMBOL_GPL(snd_hda_apply_fixup);
 static bool pin_config_match(struct hda_codec *codec,
 			     const struct hda_pintbl *pins)
 {
+	const struct hda_pincfg *pin;
 	int i;
 
-	for (i = 0; i < codec->init_pins.used; i++) {
-		struct hda_pincfg *pin = snd_array_elem(&codec->init_pins, i);
+	snd_array_for_each(&codec->init_pins, i, pin) {
 		hda_nid_t nid = pin->nid;
 		u32 cfg = pin->cfg;
 		const struct hda_pintbl *t_pins;
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 5bc3a7468e17..08151f3c0b13 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -481,9 +481,10 @@ static struct hda_pincfg *look_up_pincfg(struct hda_codec *codec,
 					 struct snd_array *array,
 					 hda_nid_t nid)
 {
+	struct hda_pincfg *pin;
 	int i;
-	for (i = 0; i < array->used; i++) {
-		struct hda_pincfg *pin = snd_array_elem(array, i);
+
+	snd_array_for_each(array, i, pin) {
 		if (pin->nid == nid)
 			return pin;
 	}
@@ -618,14 +619,15 @@ EXPORT_SYMBOL_GPL(snd_hda_codec_get_pin_target);
  */
 void snd_hda_shutup_pins(struct hda_codec *codec)
 {
+	const struct hda_pincfg *pin;
 	int i;
+
 	/* don't shut up pins when unloading the driver; otherwise it breaks
 	 * the default pin setup at the next load of the driver
 	 */
 	if (codec->bus->shutdown)
 		return;
-	for (i = 0; i < codec->init_pins.used; i++) {
-		struct hda_pincfg *pin = snd_array_elem(&codec->init_pins, i);
+	snd_array_for_each(&codec->init_pins, i, pin) {
 		/* use read here for syncing after issuing each verb */
 		snd_hda_codec_read(codec, pin->nid, 0,
 				   AC_VERB_SET_PIN_WIDGET_CONTROL, 0);
@@ -638,13 +640,14 @@ EXPORT_SYMBOL_GPL(snd_hda_shutup_pins);
 /* Restore the pin controls cleared previously via snd_hda_shutup_pins() */
 static void restore_shutup_pins(struct hda_codec *codec)
 {
+	const struct hda_pincfg *pin;
 	int i;
+
 	if (!codec->pins_shutup)
 		return;
 	if (codec->bus->shutdown)
 		return;
-	for (i = 0; i < codec->init_pins.used; i++) {
-		struct hda_pincfg *pin = snd_array_elem(&codec->init_pins, i);
+	snd_array_for_each(&codec->init_pins, i, pin) {
 		snd_hda_codec_write(codec, pin->nid, 0,
 				    AC_VERB_SET_PIN_WIDGET_CONTROL,
 				    pin->ctrl);
@@ -697,8 +700,7 @@ get_hda_cvt_setup(struct hda_codec *codec, hda_nid_t nid)
 	struct hda_cvt_setup *p;
 	int i;
 
-	for (i = 0; i < codec->cvt_setups.used; i++) {
-		p = snd_array_elem(&codec->cvt_setups, i);
+	snd_array_for_each(&codec->cvt_setups, i, p) {
 		if (p->nid == nid)
 			return p;
 	}
@@ -1076,8 +1078,7 @@ void snd_hda_codec_setup_stream(struct hda_codec *codec, hda_nid_t nid,
 	/* make other inactive cvts with the same stream-tag dirty */
 	type = get_wcaps_type(get_wcaps(codec, nid));
 	list_for_each_codec(c, codec->bus) {
-		for (i = 0; i < c->cvt_setups.used; i++) {
-			p = snd_array_elem(&c->cvt_setups, i);
+		snd_array_for_each(&c->cvt_setups, i, p) {
 			if (!p->active && p->stream_tag == stream_tag &&
 			    get_wcaps_type(get_wcaps(c, p->nid)) == type)
 				p->dirty = 1;
@@ -1140,12 +1141,11 @@ static void really_cleanup_stream(struct hda_codec *codec,
 static void purify_inactive_streams(struct hda_codec *codec)
 {
 	struct hda_codec *c;
+	struct hda_cvt_setup *p;
 	int i;
 
 	list_for_each_codec(c, codec->bus) {
-		for (i = 0; i < c->cvt_setups.used; i++) {
-			struct hda_cvt_setup *p;
-			p = snd_array_elem(&c->cvt_setups, i);
+		snd_array_for_each(&c->cvt_setups, i, p) {
 			if (p->dirty)
 				really_cleanup_stream(c, p);
 		}
@@ -1156,10 +1156,10 @@ static void purify_inactive_streams(struct hda_codec *codec)
 /* clean up all streams; called from suspend */
 static void hda_cleanup_all_streams(struct hda_codec *codec)
 {
+	struct hda_cvt_setup *p;
 	int i;
 
-	for (i = 0; i < codec->cvt_setups.used; i++) {
-		struct hda_cvt_setup *p = snd_array_elem(&codec->cvt_setups, i);
+	snd_array_for_each(&codec->cvt_setups, i, p) {
 		if (p->stream_tag)
 			really_cleanup_stream(codec, p);
 	}
@@ -1493,10 +1493,10 @@ static void get_ctl_amp_tlv(struct snd_kcontrol *kcontrol, unsigned int *tlv)
 	val1 = ((int)val1) * ((int)val2);
 	if (min_mute || (caps & AC_AMPCAP_MIN_MUTE))
 		val2 |= TLV_DB_SCALE_MUTE;
-	tlv[0] = SNDRV_CTL_TLVT_DB_SCALE;
-	tlv[1] = 2 * sizeof(unsigned int);
-	tlv[2] = val1;
-	tlv[3] = val2;
+	tlv[SNDRV_CTL_TLVO_TYPE] = SNDRV_CTL_TLVT_DB_SCALE;
+	tlv[SNDRV_CTL_TLVO_LEN] = 2 * sizeof(unsigned int);
+	tlv[SNDRV_CTL_TLVO_DB_SCALE_MIN] = val1;
+	tlv[SNDRV_CTL_TLVO_DB_SCALE_MUTE_AND_STEP] = val2;
 }
 
 /**
@@ -1544,10 +1544,10 @@ void snd_hda_set_vmaster_tlv(struct hda_codec *codec, hda_nid_t nid, int dir,
 	nums = (caps & AC_AMPCAP_NUM_STEPS) >> AC_AMPCAP_NUM_STEPS_SHIFT;
 	step = (caps & AC_AMPCAP_STEP_SIZE) >> AC_AMPCAP_STEP_SIZE_SHIFT;
 	step = (step + 1) * 25;
-	tlv[0] = SNDRV_CTL_TLVT_DB_SCALE;
-	tlv[1] = 2 * sizeof(unsigned int);
-	tlv[2] = -nums * step;
-	tlv[3] = step;
+	tlv[SNDRV_CTL_TLVO_TYPE] = SNDRV_CTL_TLVT_DB_SCALE;
+	tlv[SNDRV_CTL_TLVO_LEN] = 2 * sizeof(unsigned int);
+	tlv[SNDRV_CTL_TLVO_DB_SCALE_MIN] = -nums * step;
+	tlv[SNDRV_CTL_TLVO_DB_SCALE_MUTE_AND_STEP] = step;
 }
 EXPORT_SYMBOL_GPL(snd_hda_set_vmaster_tlv);
 
@@ -1845,10 +1845,10 @@ static int init_slave_0dB(struct snd_kcontrol *slave,
 	} else if (kctl->vd[0].access & SNDRV_CTL_ELEM_ACCESS_TLV_READ)
 		tlv = kctl->tlv.p;
 
-	if (!tlv || tlv[0] != SNDRV_CTL_TLVT_DB_SCALE)
+	if (!tlv || tlv[SNDRV_CTL_TLVO_TYPE] != SNDRV_CTL_TLVT_DB_SCALE)
 		return 0;
 
-	step = tlv[3];
+	step = tlv[SNDRV_CTL_TLVO_DB_SCALE_MUTE_AND_STEP];
 	step &= ~TLV_DB_SCALE_MUTE;
 	if (!step)
 		return 0;
@@ -1860,7 +1860,7 @@ static int init_slave_0dB(struct snd_kcontrol *slave,
 	}
 
 	arg->step = step;
-	val = -tlv[2] / step;
+	val = -tlv[SNDRV_CTL_TLVO_DB_SCALE_MIN] / step;
 	if (val > 0) {
 		put_kctl_with_value(slave, val);
 		return val;
@@ -2175,6 +2175,8 @@ static int snd_hda_spdif_default_get(struct snd_kcontrol *kcontrol,
 	int idx = kcontrol->private_value;
 	struct hda_spdif_out *spdif;
 
+	if (WARN_ON(codec->spdif_out.used <= idx))
+		return -EINVAL;
 	mutex_lock(&codec->spdif_mutex);
 	spdif = snd_array_elem(&codec->spdif_out, idx);
 	ucontrol->value.iec958.status[0] = spdif->status & 0xff;
@@ -2282,6 +2284,8 @@ static int snd_hda_spdif_default_put(struct snd_kcontrol *kcontrol,
 	unsigned short val;
 	int change;
 
+	if (WARN_ON(codec->spdif_out.used <= idx))
+		return -EINVAL;
 	mutex_lock(&codec->spdif_mutex);
 	spdif = snd_array_elem(&codec->spdif_out, idx);
 	nid = spdif->nid;
@@ -2308,6 +2312,8 @@ static int snd_hda_spdif_out_switch_get(struct snd_kcontrol *kcontrol,
 	int idx = kcontrol->private_value;
 	struct hda_spdif_out *spdif;
 
+	if (WARN_ON(codec->spdif_out.used <= idx))
+		return -EINVAL;
 	mutex_lock(&codec->spdif_mutex);
 	spdif = snd_array_elem(&codec->spdif_out, idx);
 	ucontrol->value.integer.value[0] = spdif->ctls & AC_DIG1_ENABLE;
@@ -2336,6 +2342,8 @@ static int snd_hda_spdif_out_switch_put(struct snd_kcontrol *kcontrol,
 	unsigned short val;
 	int change;
 
+	if (WARN_ON(codec->spdif_out.used <= idx))
+		return -EINVAL;
 	mutex_lock(&codec->spdif_mutex);
 	spdif = snd_array_elem(&codec->spdif_out, idx);
 	nid = spdif->nid;
@@ -2461,10 +2469,10 @@ EXPORT_SYMBOL_GPL(snd_hda_create_dig_out_ctls);
 struct hda_spdif_out *snd_hda_spdif_out_of_nid(struct hda_codec *codec,
 					       hda_nid_t nid)
 {
+	struct hda_spdif_out *spdif;
 	int i;
-	for (i = 0; i < codec->spdif_out.used; i++) {
-		struct hda_spdif_out *spdif =
-				snd_array_elem(&codec->spdif_out, i);
+
+	snd_array_for_each(&codec->spdif_out, i, spdif) {
 		if (spdif->nid == nid)
 			return spdif;
 	}
@@ -2483,6 +2491,8 @@ void snd_hda_spdif_ctls_unassign(struct hda_codec *codec, int idx)
 {
 	struct hda_spdif_out *spdif;
 
+	if (WARN_ON(codec->spdif_out.used <= idx))
+		return;
 	mutex_lock(&codec->spdif_mutex);
 	spdif = snd_array_elem(&codec->spdif_out, idx);
 	spdif->nid = (u16)-1;
@@ -2503,6 +2513,8 @@ void snd_hda_spdif_ctls_assign(struct hda_codec *codec, int idx, hda_nid_t nid)
 	struct hda_spdif_out *spdif;
 	unsigned short val;
 
+	if (WARN_ON(codec->spdif_out.used <= idx))
+		return;
 	mutex_lock(&codec->spdif_mutex);
 	spdif = snd_array_elem(&codec->spdif_out, idx);
 	if (spdif->nid != nid) {
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index d1eb14842340..a12e594d4e3b 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -748,8 +748,10 @@ int snd_hda_attach_pcm_stream(struct hda_bus *_bus, struct hda_codec *codec,
 		return err;
 	strlcpy(pcm->name, cpcm->name, sizeof(pcm->name));
 	apcm = kzalloc(sizeof(*apcm), GFP_KERNEL);
-	if (apcm == NULL)
+	if (apcm == NULL) {
+		snd_device_free(chip->card, pcm);
 		return -ENOMEM;
+	}
 	apcm->chip = chip;
 	apcm->pcm = pcm;
 	apcm->codec = codec;
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 5cc65093d941..db773e219aaa 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -264,10 +264,10 @@ static struct nid_path *get_nid_path(struct hda_codec *codec,
 				     int anchor_nid)
 {
 	struct hda_gen_spec *spec = codec->spec;
+	struct nid_path *path;
 	int i;
 
-	for (i = 0; i < spec->paths.used; i++) {
-		struct nid_path *path = snd_array_elem(&spec->paths, i);
+	snd_array_for_each(&spec->paths, i, path) {
 		if (path->depth <= 0)
 			continue;
 		if ((!from_nid || path->path[0] == from_nid) &&
@@ -325,10 +325,10 @@ EXPORT_SYMBOL_GPL(snd_hda_get_path_from_idx);
 static bool is_dac_already_used(struct hda_codec *codec, hda_nid_t nid)
 {
 	struct hda_gen_spec *spec = codec->spec;
+	const struct nid_path *path;
 	int i;
 
-	for (i = 0; i < spec->paths.used; i++) {
-		struct nid_path *path = snd_array_elem(&spec->paths, i);
+	snd_array_for_each(&spec->paths, i, path) {
 		if (path->path[0] == nid)
 			return true;
 	}
@@ -351,11 +351,11 @@ static bool is_reachable_path(struct hda_codec *codec,
 static bool is_ctl_used(struct hda_codec *codec, unsigned int val, int type)
 {
 	struct hda_gen_spec *spec = codec->spec;
+	const struct nid_path *path;
 	int i;
 
 	val &= AMP_VAL_COMPARE_MASK;
-	for (i = 0; i < spec->paths.used; i++) {
-		struct nid_path *path = snd_array_elem(&spec->paths, i);
+	snd_array_for_each(&spec->paths, i, path) {
 		if ((path->ctls[type] & AMP_VAL_COMPARE_MASK) == val)
 			return true;
 	}
@@ -638,13 +638,13 @@ static bool is_active_nid(struct hda_codec *codec, hda_nid_t nid,
 {
 	struct hda_gen_spec *spec = codec->spec;
 	int type = get_wcaps_type(get_wcaps(codec, nid));
+	const struct nid_path *path;
 	int i, n;
 
 	if (nid == codec->core.afg)
 		return true;
 
-	for (n = 0; n < spec->paths.used; n++) {
-		struct nid_path *path = snd_array_elem(&spec->paths, n);
+	snd_array_for_each(&spec->paths, n, path) {
 		if (!path->active)
 			continue;
 		if (codec->power_save_node) {
@@ -2065,7 +2065,7 @@ static int parse_output_paths(struct hda_codec *codec)
 			snd_hda_set_vmaster_tlv(codec, spec->vmaster_nid,
 						HDA_OUTPUT, spec->vmaster_tlv);
 			if (spec->dac_min_mute)
-				spec->vmaster_tlv[3] |= TLV_DB_SCALE_MUTE;
+				spec->vmaster_tlv[SNDRV_CTL_TLVO_DB_SCALE_MUTE_AND_STEP] |= TLV_DB_SCALE_MUTE;
 		}
 	}
 
@@ -2696,10 +2696,10 @@ static const struct snd_kcontrol_new out_jack_mode_enum = {
 static bool find_kctl_name(struct hda_codec *codec, const char *name, int idx)
 {
 	struct hda_gen_spec *spec = codec->spec;
+	const struct snd_kcontrol_new *kctl;
 	int i;
 
-	for (i = 0; i < spec->kctls.used; i++) {
-		struct snd_kcontrol_new *kctl = snd_array_elem(&spec->kctls, i);
+	snd_array_for_each(&spec->kctls, i, kctl) {
 		if (!strcmp(kctl->name, name) && kctl->index == idx)
 			return true;
 	}
@@ -4021,8 +4021,7 @@ static hda_nid_t set_path_power(struct hda_codec *codec, hda_nid_t nid,
 	struct nid_path *path;
 	int n;
 
-	for (n = 0; n < spec->paths.used; n++) {
-		path = snd_array_elem(&spec->paths, n);
+	snd_array_for_each(&spec->paths, n, path) {
 		if (!path->depth)
 			continue;
 		if (path->path[0] == nid ||
@@ -5831,10 +5830,10 @@ static void init_digital(struct hda_codec *codec)
  */
 static void clear_unsol_on_unused_pins(struct hda_codec *codec)
 {
+	const struct hda_pincfg *pin;
 	int i;
 
-	for (i = 0; i < codec->init_pins.used; i++) {
-		struct hda_pincfg *pin = snd_array_elem(&codec->init_pins, i);
+	snd_array_for_each(&codec->init_pins, i, pin) {
 		hda_nid_t nid = pin->nid;
 		if (is_jack_detectable(codec, nid) &&
 		    !snd_hda_jack_tbl_get(codec, nid))
diff --git a/sound/pci/hda/hda_hwdep.c b/sound/pci/hda/hda_hwdep.c
index 57df06e76968..cc009a4a3d1d 100644
--- a/sound/pci/hda/hda_hwdep.c
+++ b/sound/pci/hda/hda_hwdep.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/nospec.h>
 #include <sound/core.h>
 #include "hda_codec.h"
 #include "hda_local.h"
@@ -51,7 +52,16 @@ static int get_wcap_ioctl(struct hda_codec *codec,
 	
 	if (get_user(verb, &arg->verb))
 		return -EFAULT;
-	res = get_wcaps(codec, verb >> 24);
+	/* open-code get_wcaps(verb>>24) with nospec */
+	verb >>= 24;
+	if (verb < codec->core.start_nid ||
+	    verb >= codec->core.start_nid + codec->core.num_nodes) {
+		res = 0;
+	} else {
+		verb -= codec->core.start_nid;
+		verb = array_index_nospec(verb, codec->core.num_nodes);
+		res = codec->wcaps[verb];
+	}
 	if (put_user(res, &arg->res))
 		return -EFAULT;
 	return 0;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 7a111a1b5836..1ae1850b3bfd 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1647,7 +1647,8 @@ static void azx_check_snoop_available(struct azx *chip)
 		 */
 		u8 val;
 		pci_read_config_byte(chip->pci, 0x42, &val);
-		if (!(val & 0x80) && chip->pci->revision == 0x30)
+		if (!(val & 0x80) && (chip->pci->revision == 0x30 ||
+				      chip->pci->revision == 0x20))
 			snoop = false;
 	}
 
@@ -2208,7 +2209,20 @@ static struct snd_pci_quirk power_save_blacklist[] = {
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
+	SND_PCI_QUIRK(0x1849, 0x7662, "Asrock H81M-HDS", 0),
+	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0),
+	/* https://bugzilla.redhat.com/show_bug.cgi?id=1581607 */
+	SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", 0),
+	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
+	/* Note the P55A-UD3 and Z87-D3HP share the subsys id for the HDA dev */
+	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte P55A-UD3 / Z87-D3HP", 0),
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=199607 */
+	SND_PCI_QUIRK(0x8086, 0x2057, "Intel NUC5i7RYB", 0),
+	/* https://bugzilla.redhat.com/show_bug.cgi?id=1520902 */
+	SND_PCI_QUIRK(0x8086, 0x2068, "Intel NUC7i3BNB", 0),
+	/* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */
+	SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */
 	SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0),
 	{}
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index 321e78baa63c..9bd935216c18 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -622,8 +622,10 @@ snd_hda_check_power_state(struct hda_codec *codec, hda_nid_t nid,
 {
 	return snd_hdac_check_power_state(&codec->core, nid, target_state);
 }
-static inline bool snd_hda_sync_power_state(struct hda_codec *codec,
-			   hda_nid_t nid, unsigned int target_state)
+
+static inline unsigned int snd_hda_sync_power_state(struct hda_codec *codec,
+						    hda_nid_t nid,
+						    unsigned int target_state)
 {
 	return snd_hdac_sync_power_state(&codec->core, nid, target_state);
 }
diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c
index 9b7efece4484..6ec79c58d48d 100644
--- a/sound/pci/hda/hda_sysfs.c
+++ b/sound/pci/hda/hda_sysfs.c
@@ -80,10 +80,10 @@ static ssize_t pin_configs_show(struct hda_codec *codec,
 				struct snd_array *list,
 				char *buf)
 {
+	const struct hda_pincfg *pin;
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
-	for (i = 0; i < list->used; i++) {
-		struct hda_pincfg *pin = snd_array_elem(list, i);
+	snd_array_for_each(list, i, pin) {
 		len += sprintf(buf + len, "0x%02x 0x%08x\n",
 			       pin->nid, pin->cfg);
 	}
@@ -217,10 +217,10 @@ static ssize_t init_verbs_show(struct device *dev,
 			       char *buf)
 {
 	struct hda_codec *codec = dev_get_drvdata(dev);
+	const struct hda_verb *v;
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
-	for (i = 0; i < codec->init_verbs.used; i++) {
-		struct hda_verb *v = snd_array_elem(&codec->init_verbs, i);
+	snd_array_for_each(&codec->init_verbs, i, v) {
 		len += snprintf(buf + len, PAGE_SIZE - len,
 				"0x%02x 0x%03x 0x%04x\n",
 				v->nid, v->verb, v->param);
@@ -267,10 +267,10 @@ static ssize_t hints_show(struct device *dev,
 			  char *buf)
 {
 	struct hda_codec *codec = dev_get_drvdata(dev);
+	const struct hda_hint *hint;
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
-	for (i = 0; i < codec->hints.used; i++) {
-		struct hda_hint *hint = snd_array_elem(&codec->hints, i);
+	snd_array_for_each(&codec->hints, i, hint) {
 		len += snprintf(buf + len, PAGE_SIZE - len,
 				"%s = %s\n", hint->key, hint->val);
 	}
@@ -280,10 +280,10 @@ static ssize_t hints_show(struct device *dev,
 
 static struct hda_hint *get_hint(struct hda_codec *codec, const char *key)
 {
+	struct hda_hint *hint;
 	int i;
 
-	for (i = 0; i < codec->hints.used; i++) {
-		struct hda_hint *hint = snd_array_elem(&codec->hints, i);
+	snd_array_for_each(&codec->hints, i, hint) {
 		if (!strcmp(hint->key, key))
 			return hint;
 	}
@@ -783,13 +783,13 @@ void snd_hda_sysfs_init(struct hda_codec *codec)
 void snd_hda_sysfs_clear(struct hda_codec *codec)
 {
 #ifdef CONFIG_SND_HDA_RECONFIG
+	struct hda_hint *hint;
 	int i;
 
 	/* clear init verbs */
 	snd_array_free(&codec->init_verbs);
 	/* clear hints */
-	for (i = 0; i < codec->hints.used; i++) {
-		struct hda_hint *hint = snd_array_elem(&codec->hints, i);
+	snd_array_for_each(&codec->hints, i, hint) {
 		kfree(hint->key); /* we don't need to free hint->val */
 	}
 	snd_array_free(&codec->hints);
diff --git a/sound/pci/hda/hp_x360_helper.c b/sound/pci/hda/hp_x360_helper.c
new file mode 100644
index 000000000000..969542c57358
--- /dev/null
+++ b/sound/pci/hda/hp_x360_helper.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Fixes for HP X360 laptops with top B&O speakers
+ * to be included from codec driver
+ */
+
+static void alc295_fixup_hp_top_speakers(struct hda_codec *codec,
+		const struct hda_fixup *fix, int action)
+{
+	static const struct hda_pintbl pincfgs[] = {
+		{ 0x17, 0x90170110 },
+		{ }
+	};
+	static const struct coef_fw alc295_hp_speakers_coefs[] = {
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0000), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x003f), WRITE_COEF(0x28, 0x1000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0004), WRITE_COEF(0x28, 0x0600), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006a), WRITE_COEF(0x28, 0x0006), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006c), WRITE_COEF(0x28, 0xc0c0), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0008), WRITE_COEF(0x28, 0xb000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x002e), WRITE_COEF(0x28, 0x0800), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006a), WRITE_COEF(0x28, 0x00c1), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006c), WRITE_COEF(0x28, 0x0320), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0039), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x003b), WRITE_COEF(0x28, 0xffff), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x003c), WRITE_COEF(0x28, 0xffd0), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x003a), WRITE_COEF(0x28, 0x1dfe), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0080), WRITE_COEF(0x28, 0x0880), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x003a), WRITE_COEF(0x28, 0x0dfe), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0018), WRITE_COEF(0x28, 0x0219), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006a), WRITE_COEF(0x28, 0x005d), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006c), WRITE_COEF(0x28, 0x9142), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c0), WRITE_COEF(0x28, 0x01ce), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c1), WRITE_COEF(0x28, 0xed0c), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c2), WRITE_COEF(0x28, 0x1c00), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c3), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c4), WRITE_COEF(0x28, 0x0200), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c5), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c6), WRITE_COEF(0x28, 0x0399), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c7), WRITE_COEF(0x28, 0x2330), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c8), WRITE_COEF(0x28, 0x1e5d), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00c9), WRITE_COEF(0x28, 0x6eff), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00ca), WRITE_COEF(0x28, 0x01c0), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00cb), WRITE_COEF(0x28, 0xed0c), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00cc), WRITE_COEF(0x28, 0x1c00), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00cd), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00ce), WRITE_COEF(0x28, 0x0200), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00cf), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00d0), WRITE_COEF(0x28, 0x0399), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00d1), WRITE_COEF(0x28, 0x2330), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00d2), WRITE_COEF(0x28, 0x1e5d), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x00d3), WRITE_COEF(0x28, 0x6eff), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0062), WRITE_COEF(0x28, 0x8000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0063), WRITE_COEF(0x28, 0x5f5f), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0064), WRITE_COEF(0x28, 0x1000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0065), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0066), WRITE_COEF(0x28, 0x4004), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0067), WRITE_COEF(0x28, 0x0802), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0068), WRITE_COEF(0x28, 0x890f), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0069), WRITE_COEF(0x28, 0xe021), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0070), WRITE_COEF(0x28, 0x8012), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0071), WRITE_COEF(0x28, 0x3450), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0072), WRITE_COEF(0x28, 0x0123), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0073), WRITE_COEF(0x28, 0x4543), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0074), WRITE_COEF(0x28, 0x2100), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0075), WRITE_COEF(0x28, 0x4321), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0076), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0050), WRITE_COEF(0x28, 0x8200), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x003a), WRITE_COEF(0x28, 0x1dfe), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0051), WRITE_COEF(0x28, 0x0707), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0052), WRITE_COEF(0x28, 0x4090), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006a), WRITE_COEF(0x28, 0x0090), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006c), WRITE_COEF(0x28, 0x721f), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0012), WRITE_COEF(0x28, 0xebeb), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x009e), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0060), WRITE_COEF(0x28, 0x2213), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006a), WRITE_COEF(0x28, 0x0006), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x006c), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x003f), WRITE_COEF(0x28, 0x3000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0004), WRITE_COEF(0x28, 0x0500), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0040), WRITE_COEF(0x28, 0x800c), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0046), WRITE_COEF(0x28, 0xc22e), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x004b), WRITE_COEF(0x28, 0x0000), WRITE_COEF(0x29, 0xb024),
+		WRITE_COEF(0x24, 0x0012), WRITE_COEF(0x26, 0x0050), WRITE_COEF(0x28, 0x82ec), WRITE_COEF(0x29, 0xb024),
+	};
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		snd_hda_apply_pincfgs(codec, pincfgs);
+		alc295_fixup_disable_dac3(codec, fix, action);
+		break;
+	case HDA_FIXUP_ACT_INIT:
+		alc_process_coef_fw(codec, alc295_hp_speakers_coefs);
+		break;
+	}
+}
diff --git a/sound/pci/hda/local.h b/sound/pci/hda/local.h
deleted file mode 100644
index 3b8b7d78f9e0..000000000000
--- a/sound/pci/hda/local.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- */
-
-#ifndef __HDAC_LOCAL_H
-#define __HDAC_LOCAL_H
-
-int hdac_read_parm(struct hdac_device *codec, hda_nid_t nid, int parm);
-
-#define get_wcaps(codec, nid) \
-	hdac_read_parm(codec, nid, AC_PAR_AUDIO_WIDGET_CAP)
-/* get the widget type from widget capability bits */
-static inline int get_wcaps_type(unsigned int wcaps)
-{
-	if (!wcaps)
-		return -1; /* invalid type */
-	return (wcaps & AC_WCAP_TYPE) >> AC_WCAP_TYPE_SHIFT;
-}
-
-#define get_pin_caps(codec, nid) \
-	hdac_read_parm(codec, nid, AC_PAR_PIN_CAP)
-
-static inline
-unsigned int get_pin_cfg(struct hdac_device *codec, hda_nid_t nid)
-{
-	unsigned int val;
-
-	if (snd_hdac_read(codec, nid, AC_VERB_GET_CONFIG_DEFAULT, 0, &val))
-		return -1;
-	return val;
-}
-
-#define get_amp_caps(codec, nid, dir) \
-	hdac_read_parm(codec, nid, (dir) == HDA_OUTPUT ? \
-		       AC_PAR_AMP_OUT_CAP : AC_PAR_AMP_IN_CAP)
-
-#define get_power_caps(codec, nid) \
-	hdac_read_parm(codec, nid, AC_PAR_POWER_STATE)
-
-#endif /* __HDAC_LOCAL_H */
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 768ea8651993..292e2c592c17 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -28,6 +28,9 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/io.h>
+#include <linux/pci.h>
 #include <sound/core.h>
 #include "hda_codec.h"
 #include "hda_local.h"
@@ -39,9 +42,15 @@
 /* Enable this to see controls for tuning purpose. */
 /*#define ENABLE_TUNING_CONTROLS*/
 
+#ifdef ENABLE_TUNING_CONTROLS
+#include <sound/tlv.h>
+#endif
+
 #define FLOAT_ZERO	0x00000000
 #define FLOAT_ONE	0x3f800000
 #define FLOAT_TWO	0x40000000
+#define FLOAT_THREE     0x40400000
+#define FLOAT_EIGHT     0x41000000
 #define FLOAT_MINUS_5	0xc0a00000
 
 #define UNSOL_TAG_DSP	0x16
@@ -72,16 +81,22 @@
 #define SCP_GET    1
 
 #define EFX_FILE   "ctefx.bin"
+#define SBZ_EFX_FILE   "ctefx-sbz.bin"
+#define R3DI_EFX_FILE  "ctefx-r3di.bin"
 
 #ifdef CONFIG_SND_HDA_CODEC_CA0132_DSP
 MODULE_FIRMWARE(EFX_FILE);
+MODULE_FIRMWARE(SBZ_EFX_FILE);
+MODULE_FIRMWARE(R3DI_EFX_FILE);
 #endif
 
-static char *dirstr[2] = { "Playback", "Capture" };
+static const char *const dirstr[2] = { "Playback", "Capture" };
 
+#define NUM_OF_OUTPUTS 3
 enum {
 	SPEAKER_OUT,
-	HEADPHONE_OUT
+	HEADPHONE_OUT,
+	SURROUND_OUT
 };
 
 enum {
@@ -89,6 +104,15 @@ enum {
 	LINE_MIC_IN
 };
 
+/* Strings for Input Source Enum Control */
+static const char *const in_src_str[3] = {"Rear Mic", "Line", "Front Mic" };
+#define IN_SRC_NUM_OF_INPUTS 3
+enum {
+	REAR_MIC,
+	REAR_LINE_IN,
+	FRONT_MIC,
+};
+
 enum {
 #define VNODE_START_NID    0x80
 	VNID_SPK = VNODE_START_NID,			/* Speaker vnid */
@@ -122,13 +146,28 @@ enum {
 	VOICEFX = IN_EFFECT_END_NID,
 	PLAY_ENHANCEMENT,
 	CRYSTAL_VOICE,
-	EFFECT_END_NID
+	EFFECT_END_NID,
+	OUTPUT_SOURCE_ENUM,
+	INPUT_SOURCE_ENUM,
+	XBASS_XOVER,
+	EQ_PRESET_ENUM,
+	SMART_VOLUME_ENUM,
+	MIC_BOOST_ENUM
 #define EFFECTS_COUNT  (EFFECT_END_NID - EFFECT_START_NID)
 };
 
 /* Effects values size*/
 #define EFFECT_VALS_MAX_COUNT 12
 
+/*
+ * Default values for the effect slider controls, they are in order of their
+ * effect NID's. Surround, Crystalizer, Dialog Plus, Smart Volume, and then
+ * X-bass.
+ */
+static const unsigned int effect_slider_defaults[] = {67, 65, 50, 74, 50};
+/* Amount of effect level sliders for ca0132_alt controls. */
+#define EFFECT_LEVEL_SLIDERS 5
+
 /* Latency introduced by DSP blocks in milliseconds. */
 #define DSP_CAPTURE_INIT_LATENCY        0
 #define DSP_CRYSTAL_VOICE_LATENCY       124
@@ -150,7 +189,7 @@ struct ct_effect {
 #define EFX_DIR_OUT 0
 #define EFX_DIR_IN  1
 
-static struct ct_effect ca0132_effects[EFFECTS_COUNT] = {
+static const struct ct_effect ca0132_effects[EFFECTS_COUNT] = {
 	{ .name = "Surround",
 	  .nid = SURROUND,
 	  .mid = 0x96,
@@ -277,7 +316,7 @@ struct ct_tuning_ctl {
 	unsigned int def_val;/*effect default values*/
 };
 
-static struct ct_tuning_ctl ca0132_tuning_ctls[] = {
+static const struct ct_tuning_ctl ca0132_tuning_ctls[] = {
 	{ .name = "Wedge Angle",
 	  .parent_nid = VOICE_FOCUS,
 	  .nid = WEDGE_ANGLE,
@@ -392,14 +431,14 @@ struct ct_voicefx_preset {
 	unsigned int vals[VOICEFX_MAX_PARAM_COUNT];
 };
 
-static struct ct_voicefx ca0132_voicefx = {
+static const struct ct_voicefx ca0132_voicefx = {
 	.name = "VoiceFX Capture Switch",
 	.nid = VOICEFX,
 	.mid = 0x95,
 	.reqs = {10, 11, 12, 13, 14, 15, 16, 17, 18}
 };
 
-static struct ct_voicefx_preset ca0132_voicefx_presets[] = {
+static const struct ct_voicefx_preset ca0132_voicefx_presets[] = {
 	{ .name = "Neutral",
 	  .vals = { 0x00000000, 0x43C80000, 0x44AF0000,
 		    0x44FA0000, 0x3F800000, 0x3F800000,
@@ -472,6 +511,161 @@ static struct ct_voicefx_preset ca0132_voicefx_presets[] = {
 	}
 };
 
+/* ca0132 EQ presets, taken from Windows Sound Blaster Z Driver */
+
+#define EQ_PRESET_MAX_PARAM_COUNT 11
+
+struct ct_eq {
+	char *name;
+	hda_nid_t nid;
+	int mid;
+	int reqs[EQ_PRESET_MAX_PARAM_COUNT]; /*effect module request*/
+};
+
+struct ct_eq_preset {
+	char *name; /*preset name*/
+	unsigned int vals[EQ_PRESET_MAX_PARAM_COUNT];
+};
+
+static const struct ct_eq ca0132_alt_eq_enum = {
+	.name = "FX: Equalizer Preset Switch",
+	.nid = EQ_PRESET_ENUM,
+	.mid = 0x96,
+	.reqs = {10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20}
+};
+
+
+static const struct ct_eq_preset ca0132_alt_eq_presets[] = {
+	{ .name = "Flat",
+	 .vals = { 0x00000000, 0x00000000, 0x00000000,
+		   0x00000000, 0x00000000, 0x00000000,
+		   0x00000000, 0x00000000, 0x00000000,
+		   0x00000000, 0x00000000	     }
+	},
+	{ .name = "Acoustic",
+	 .vals = { 0x00000000, 0x00000000, 0x3F8CCCCD,
+		   0x40000000, 0x00000000, 0x00000000,
+		   0x00000000, 0x00000000, 0x40000000,
+		   0x40000000, 0x40000000	     }
+	},
+	{ .name = "Classical",
+	 .vals = { 0x00000000, 0x00000000, 0x40C00000,
+		   0x40C00000, 0x40466666, 0x00000000,
+		   0x00000000, 0x00000000, 0x00000000,
+		   0x40466666, 0x40466666	     }
+	},
+	{ .name = "Country",
+	 .vals = { 0x00000000, 0xBF99999A, 0x00000000,
+		   0x3FA66666, 0x3FA66666, 0x3F8CCCCD,
+		   0x00000000, 0x00000000, 0x40000000,
+		   0x40466666, 0x40800000	     }
+	},
+	{ .name = "Dance",
+	 .vals = { 0x00000000, 0xBF99999A, 0x40000000,
+		   0x40466666, 0x40866666, 0xBF99999A,
+		   0xBF99999A, 0x00000000, 0x00000000,
+		   0x40800000, 0x40800000	     }
+	},
+	{ .name = "Jazz",
+	 .vals = { 0x00000000, 0x00000000, 0x00000000,
+		   0x3F8CCCCD, 0x40800000, 0x40800000,
+		   0x40800000, 0x00000000, 0x3F8CCCCD,
+		   0x40466666, 0x40466666	     }
+	},
+	{ .name = "New Age",
+	 .vals = { 0x00000000, 0x00000000, 0x40000000,
+		   0x40000000, 0x00000000, 0x00000000,
+		   0x00000000, 0x3F8CCCCD, 0x40000000,
+		   0x40000000, 0x40000000	     }
+	},
+	{ .name = "Pop",
+	 .vals = { 0x00000000, 0xBFCCCCCD, 0x00000000,
+		   0x40000000, 0x40000000, 0x00000000,
+		   0xBF99999A, 0xBF99999A, 0x00000000,
+		   0x40466666, 0x40C00000	     }
+	},
+	{ .name = "Rock",
+	 .vals = { 0x00000000, 0xBF99999A, 0xBF99999A,
+		   0x3F8CCCCD, 0x40000000, 0xBF99999A,
+		   0xBF99999A, 0x00000000, 0x00000000,
+		   0x40800000, 0x40800000	     }
+	},
+	{ .name = "Vocal",
+	 .vals = { 0x00000000, 0xC0000000, 0xBF99999A,
+		   0xBF99999A, 0x00000000, 0x40466666,
+		   0x40800000, 0x40466666, 0x00000000,
+		   0x00000000, 0x3F8CCCCD	     }
+	}
+};
+
+/* DSP command sequences for ca0132_alt_select_out */
+#define ALT_OUT_SET_MAX_COMMANDS 9 /* Max number of commands in sequence */
+struct ca0132_alt_out_set {
+	char *name; /*preset name*/
+	unsigned char commands;
+	unsigned int mids[ALT_OUT_SET_MAX_COMMANDS];
+	unsigned int reqs[ALT_OUT_SET_MAX_COMMANDS];
+	unsigned int vals[ALT_OUT_SET_MAX_COMMANDS];
+};
+
+static const struct ca0132_alt_out_set alt_out_presets[] = {
+	{ .name = "Line Out",
+	  .commands = 7,
+	  .mids = { 0x96, 0x96, 0x96, 0x8F,
+		    0x96, 0x96, 0x96 },
+	  .reqs = { 0x19, 0x17, 0x18, 0x01,
+		    0x1F, 0x15, 0x3A },
+	  .vals = { 0x3F000000, 0x42A00000, 0x00000000,
+		    0x00000000, 0x00000000, 0x00000000,
+		    0x00000000 }
+	},
+	{ .name = "Headphone",
+	  .commands = 7,
+	  .mids = { 0x96, 0x96, 0x96, 0x8F,
+		    0x96, 0x96, 0x96 },
+	  .reqs = { 0x19, 0x17, 0x18, 0x01,
+		    0x1F, 0x15, 0x3A },
+	  .vals = { 0x3F000000, 0x42A00000, 0x00000000,
+		    0x00000000, 0x00000000, 0x00000000,
+		    0x00000000 }
+	},
+	{ .name = "Surround",
+	  .commands = 8,
+	  .mids = { 0x96, 0x8F, 0x96, 0x96,
+		    0x96, 0x96, 0x96, 0x96 },
+	  .reqs = { 0x18, 0x01, 0x1F, 0x15,
+		    0x3A, 0x1A, 0x1B, 0x1C },
+	  .vals = { 0x00000000, 0x00000000, 0x00000000,
+		    0x00000000, 0x00000000, 0x00000000,
+		    0x00000000, 0x00000000 }
+	}
+};
+
+/*
+ * DSP volume setting structs. Req 1 is left volume, req 2 is right volume,
+ * and I don't know what the third req is, but it's always zero. I assume it's
+ * some sort of update or set command to tell the DSP there's new volume info.
+ */
+#define DSP_VOL_OUT 0
+#define DSP_VOL_IN  1
+
+struct ct_dsp_volume_ctl {
+	hda_nid_t vnid;
+	int mid; /* module ID*/
+	unsigned int reqs[3]; /* scp req ID */
+};
+
+static const struct ct_dsp_volume_ctl ca0132_alt_vol_ctls[] = {
+	{ .vnid = VNID_SPK,
+	  .mid = 0x32,
+	  .reqs = {3, 4, 2}
+	},
+	{ .vnid = VNID_MIC,
+	  .mid = 0x37,
+	  .reqs = {2, 3, 1}
+	}
+};
+
 enum hda_cmd_vendor_io {
 	/* for DspIO node */
 	VENDOR_DSPIO_SCP_WRITE_DATA_LOW      = 0x000,
@@ -698,11 +892,12 @@ enum dsp_download_state {
  */
 
 struct ca0132_spec {
-	struct snd_kcontrol_new *mixers[5];
+	const struct snd_kcontrol_new *mixers[5];
 	unsigned int num_mixers;
 	const struct hda_verb *base_init_verbs;
 	const struct hda_verb *base_exit_verbs;
 	const struct hda_verb *chip_init_verbs;
+	const struct hda_verb *sbz_init_verbs;
 	struct hda_verb *spec_init_verbs;
 	struct auto_pin_cfg autocfg;
 
@@ -719,6 +914,7 @@ struct ca0132_spec {
 	hda_nid_t shared_mic_nid;
 	hda_nid_t shared_out_nid;
 	hda_nid_t unsol_tag_hp;
+	hda_nid_t unsol_tag_front_hp; /* for desktop ca0132 codecs */
 	hda_nid_t unsol_tag_amic1;
 
 	/* chip access */
@@ -734,6 +930,9 @@ struct ca0132_spec {
 	unsigned int scp_resp_header;
 	unsigned int scp_resp_data[4];
 	unsigned int scp_resp_count;
+	bool alt_firmware_present;
+	bool startup_check_entered;
+	bool dsp_reload;
 
 	/* mixer and effects related */
 	unsigned char dmic_ctl;
@@ -746,6 +945,17 @@ struct ca0132_spec {
 	long effects_switch[EFFECTS_COUNT];
 	long voicefx_val;
 	long cur_mic_boost;
+	/* ca0132_alt control related values */
+	unsigned char in_enum_val;
+	unsigned char out_enum_val;
+	unsigned char mic_boost_enum_val;
+	unsigned char smart_volume_setting;
+	long fx_ctl_val[EFFECT_LEVEL_SLIDERS];
+	long xbass_xover_freq;
+	long eq_preset_val;
+	unsigned int tlv[4];
+	struct hda_vmaster_mute_hook vmaster_mute;
+
 
 	struct hda_codec *codec;
 	struct delayed_work unsol_hp_work;
@@ -754,6 +964,25 @@ struct ca0132_spec {
 #ifdef ENABLE_TUNING_CONTROLS
 	long cur_ctl_vals[TUNING_CTLS_COUNT];
 #endif
+	/*
+	 * Sound Blaster Z PCI region 2 iomem, used for input and output
+	 * switching, and other unknown commands.
+	 */
+	void __iomem *mem_base;
+
+	/*
+	 * Whether or not to use the alt functions like alt_select_out,
+	 * alt_select_in, etc. Only used on desktop codecs for now, because of
+	 * surround sound support.
+	 */
+	bool use_alt_functions;
+
+	/*
+	 * Whether or not to use alt controls:	volume effect sliders, EQ
+	 * presets, smart volume presets, and new control names with FX prefix.
+	 * Renames PlayEnhancement and CrystalVoice too.
+	 */
+	bool use_alt_controls;
 };
 
 /*
@@ -762,6 +991,8 @@ struct ca0132_spec {
 enum {
 	QUIRK_NONE,
 	QUIRK_ALIENWARE,
+	QUIRK_SBZ,
+	QUIRK_R3DI,
 };
 
 static const struct hda_pintbl alienware_pincfgs[] = {
@@ -778,10 +1009,44 @@ static const struct hda_pintbl alienware_pincfgs[] = {
 	{}
 };
 
+/* Sound Blaster Z pin configs taken from Windows Driver */
+static const struct hda_pintbl sbz_pincfgs[] = {
+	{ 0x0b, 0x01017010 }, /* Port G -- Lineout FRONT L/R */
+	{ 0x0c, 0x014510f0 }, /* SPDIF Out 1 */
+	{ 0x0d, 0x014510f0 }, /* Digital Out */
+	{ 0x0e, 0x01c510f0 }, /* SPDIF In */
+	{ 0x0f, 0x0221701f }, /* Port A -- BackPanel HP */
+	{ 0x10, 0x01017012 }, /* Port D -- Center/LFE or FP Hp */
+	{ 0x11, 0x01017014 }, /* Port B -- LineMicIn2 / Rear L/R */
+	{ 0x12, 0x01a170f0 }, /* Port C -- LineIn1 */
+	{ 0x13, 0x908700f0 }, /* What U Hear In*/
+	{ 0x18, 0x50d000f0 }, /* N/A */
+	{}
+};
+
+/* Recon3D integrated pin configs taken from Windows Driver */
+static const struct hda_pintbl r3di_pincfgs[] = {
+	{ 0x0b, 0x01014110 }, /* Port G -- Lineout FRONT L/R */
+	{ 0x0c, 0x014510f0 }, /* SPDIF Out 1 */
+	{ 0x0d, 0x014510f0 }, /* Digital Out */
+	{ 0x0e, 0x41c520f0 }, /* SPDIF In */
+	{ 0x0f, 0x0221401f }, /* Port A -- BackPanel HP */
+	{ 0x10, 0x01016011 }, /* Port D -- Center/LFE or FP Hp */
+	{ 0x11, 0x01011014 }, /* Port B -- LineMicIn2 / Rear L/R */
+	{ 0x12, 0x02a090f0 }, /* Port C -- LineIn1 */
+	{ 0x13, 0x908700f0 }, /* What U Hear In*/
+	{ 0x18, 0x500000f0 }, /* N/A */
+	{}
+};
+
 static const struct snd_pci_quirk ca0132_quirks[] = {
 	SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE),
 	SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE),
 	SND_PCI_QUIRK(0x1028, 0x0708, "Alienware 15 R2 2016", QUIRK_ALIENWARE),
+	SND_PCI_QUIRK(0x1102, 0x0010, "Sound Blaster Z", QUIRK_SBZ),
+	SND_PCI_QUIRK(0x1102, 0x0023, "Sound Blaster Z", QUIRK_SBZ),
+	SND_PCI_QUIRK(0x1458, 0xA016, "Recon3Di", QUIRK_R3DI),
+	SND_PCI_QUIRK(0x1458, 0xA036, "Recon3Di", QUIRK_R3DI),
 	{}
 };
 
@@ -965,6 +1230,29 @@ exit:
 }
 
 /*
+ * Write given value to the given address through the chip I/O widget.
+ * not protected by the Mutex
+ */
+static int chipio_write_no_mutex(struct hda_codec *codec,
+		unsigned int chip_addx, const unsigned int data)
+{
+	int err;
+
+
+	/* write the address, and if successful proceed to write data */
+	err = chipio_write_address(codec, chip_addx);
+	if (err < 0)
+		goto exit;
+
+	err = chipio_write_data(codec, data);
+	if (err < 0)
+		goto exit;
+
+exit:
+	return err;
+}
+
+/*
  * Write multiple values to the given address through the chip I/O widget.
  * protected by the Mutex
  */
@@ -1058,6 +1346,81 @@ static void chipio_set_control_param(struct hda_codec *codec,
 }
 
 /*
+ * Set chip parameters through the chip I/O widget. NO MUTEX.
+ */
+static void chipio_set_control_param_no_mutex(struct hda_codec *codec,
+		enum control_param_id param_id, int param_val)
+{
+	int val;
+
+	if ((param_id < 32) && (param_val < 8)) {
+		val = (param_val << 5) | (param_id);
+		snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+				    VENDOR_CHIPIO_PARAM_SET, val);
+	} else {
+		if (chipio_send(codec, VENDOR_CHIPIO_STATUS, 0) == 0) {
+			snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+					    VENDOR_CHIPIO_PARAM_EX_ID_SET,
+					    param_id);
+			snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+					    VENDOR_CHIPIO_PARAM_EX_VALUE_SET,
+					    param_val);
+		}
+	}
+}
+/*
+ * Connect stream to a source point, and then connect
+ * that source point to a destination point.
+ */
+static void chipio_set_stream_source_dest(struct hda_codec *codec,
+				int streamid, int source_point, int dest_point)
+{
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_STREAM_ID, streamid);
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_STREAM_SOURCE_CONN_POINT, source_point);
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_STREAM_DEST_CONN_POINT, dest_point);
+}
+
+/*
+ * Set number of channels in the selected stream.
+ */
+static void chipio_set_stream_channels(struct hda_codec *codec,
+				int streamid, unsigned int channels)
+{
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_STREAM_ID, streamid);
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_STREAMS_CHANNELS, channels);
+}
+
+/*
+ * Enable/Disable audio stream.
+ */
+static void chipio_set_stream_control(struct hda_codec *codec,
+				int streamid, int enable)
+{
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_STREAM_ID, streamid);
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_STREAM_CONTROL, enable);
+}
+
+
+/*
+ * Set sampling rate of the connection point. NO MUTEX.
+ */
+static void chipio_set_conn_rate_no_mutex(struct hda_codec *codec,
+				int connid, enum ca0132_sample_rate rate)
+{
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_CONN_POINT_ID, connid);
+	chipio_set_control_param_no_mutex(codec,
+			CONTROL_PARAM_CONN_POINT_SAMPLE_RATE, rate);
+}
+
+/*
  * Set sampling rate of the connection point.
  */
 static void chipio_set_conn_rate(struct hda_codec *codec,
@@ -1420,8 +1783,8 @@ static int dspio_send_scp_message(struct hda_codec *codec,
  * Returns zero or a negative error code.
  */
 static int dspio_scp(struct hda_codec *codec,
-		int mod_id, int req, int dir, void *data, unsigned int len,
-		void *reply, unsigned int *reply_len)
+		int mod_id, int src_id, int req, int dir, const void *data,
+		unsigned int len, void *reply, unsigned int *reply_len)
 {
 	int status = 0;
 	struct scp_msg scp_send, scp_reply;
@@ -1445,7 +1808,7 @@ static int dspio_scp(struct hda_codec *codec,
 		return -EINVAL;
 	}
 
-	scp_send.hdr = make_scp_header(mod_id, 0x20, (dir == SCP_GET), req,
+	scp_send.hdr = make_scp_header(mod_id, src_id, (dir == SCP_GET), req,
 				       0, 0, 0, len/sizeof(unsigned int));
 	if (data != NULL && len > 0) {
 		len = min((unsigned int)(sizeof(scp_send.data)), len);
@@ -1502,15 +1865,24 @@ static int dspio_scp(struct hda_codec *codec,
  * Set DSP parameters
  */
 static int dspio_set_param(struct hda_codec *codec, int mod_id,
-			int req, void *data, unsigned int len)
+			int src_id, int req, const void *data, unsigned int len)
 {
-	return dspio_scp(codec, mod_id, req, SCP_SET, data, len, NULL, NULL);
+	return dspio_scp(codec, mod_id, src_id, req, SCP_SET, data, len, NULL,
+			NULL);
 }
 
 static int dspio_set_uint_param(struct hda_codec *codec, int mod_id,
-			int req, unsigned int data)
+			int req, const unsigned int data)
 {
-	return dspio_set_param(codec, mod_id, req, &data, sizeof(unsigned int));
+	return dspio_set_param(codec, mod_id, 0x20, req, &data,
+			sizeof(unsigned int));
+}
+
+static int dspio_set_uint_param_no_source(struct hda_codec *codec, int mod_id,
+			int req, const unsigned int data)
+{
+	return dspio_set_param(codec, mod_id, 0x00, req, &data,
+			sizeof(unsigned int));
 }
 
 /*
@@ -1522,8 +1894,9 @@ static int dspio_alloc_dma_chan(struct hda_codec *codec, unsigned int *dma_chan)
 	unsigned int size = sizeof(dma_chan);
 
 	codec_dbg(codec, "     dspio_alloc_dma_chan() -- begin\n");
-	status = dspio_scp(codec, MASTERCONTROL, MASTERCONTROL_ALLOC_DMA_CHAN,
-			SCP_GET, NULL, 0, dma_chan, &size);
+	status = dspio_scp(codec, MASTERCONTROL, 0x20,
+			MASTERCONTROL_ALLOC_DMA_CHAN, SCP_GET, NULL, 0,
+			dma_chan, &size);
 
 	if (status < 0) {
 		codec_dbg(codec, "dspio_alloc_dma_chan: SCP Failed\n");
@@ -1552,8 +1925,9 @@ static int dspio_free_dma_chan(struct hda_codec *codec, unsigned int dma_chan)
 	codec_dbg(codec, "     dspio_free_dma_chan() -- begin\n");
 	codec_dbg(codec, "dspio_free_dma_chan: chan=%d\n", dma_chan);
 
-	status = dspio_scp(codec, MASTERCONTROL, MASTERCONTROL_ALLOC_DMA_CHAN,
-			   SCP_SET, &dma_chan, sizeof(dma_chan), NULL, &dummy);
+	status = dspio_scp(codec, MASTERCONTROL, 0x20,
+			MASTERCONTROL_ALLOC_DMA_CHAN, SCP_SET, &dma_chan,
+			sizeof(dma_chan), NULL, &dummy);
 
 	if (status < 0) {
 		codec_dbg(codec, "dspio_free_dma_chan: SCP Failed\n");
@@ -2575,14 +2949,16 @@ exit:
  */
 static void dspload_post_setup(struct hda_codec *codec)
 {
+	struct ca0132_spec *spec = codec->spec;
 	codec_dbg(codec, "---- dspload_post_setup ------\n");
+	if (!spec->use_alt_functions) {
+		/*set DSP speaker to 2.0 configuration*/
+		chipio_write(codec, XRAM_XRAM_INST_OFFSET(0x18), 0x08080080);
+		chipio_write(codec, XRAM_XRAM_INST_OFFSET(0x19), 0x3f800000);
 
-	/*set DSP speaker to 2.0 configuration*/
-	chipio_write(codec, XRAM_XRAM_INST_OFFSET(0x18), 0x08080080);
-	chipio_write(codec, XRAM_XRAM_INST_OFFSET(0x19), 0x3f800000);
-
-	/*update write pointer*/
-	chipio_write(codec, XRAM_XRAM_INST_OFFSET(0x29), 0x00000002);
+		/*update write pointer*/
+		chipio_write(codec, XRAM_XRAM_INST_OFFSET(0x29), 0x00000002);
+	}
 }
 
 /**
@@ -2690,6 +3066,170 @@ static bool dspload_wait_loaded(struct hda_codec *codec)
 }
 
 /*
+ * Setup GPIO for the other variants of Core3D.
+ */
+
+/*
+ * Sets up the GPIO pins so that they are discoverable. If this isn't done,
+ * the card shows as having no GPIO pins.
+ */
+static void ca0132_gpio_init(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+
+	switch (spec->quirk) {
+	case QUIRK_SBZ:
+		snd_hda_codec_write(codec, 0x01, 0, 0x793, 0x00);
+		snd_hda_codec_write(codec, 0x01, 0, 0x794, 0x53);
+		snd_hda_codec_write(codec, 0x01, 0, 0x790, 0x23);
+		break;
+	case QUIRK_R3DI:
+		snd_hda_codec_write(codec, 0x01, 0, 0x793, 0x00);
+		snd_hda_codec_write(codec, 0x01, 0, 0x794, 0x5B);
+		break;
+	}
+
+}
+
+/* Sets the GPIO for audio output. */
+static void ca0132_gpio_setup(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+
+	switch (spec->quirk) {
+	case QUIRK_SBZ:
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_DIRECTION, 0x07);
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_MASK, 0x07);
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_DATA, 0x04);
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_DATA, 0x06);
+		break;
+	case QUIRK_R3DI:
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_DIRECTION, 0x1E);
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_MASK, 0x1F);
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_DATA, 0x0C);
+		break;
+	}
+}
+
+/*
+ * GPIO control functions for the Recon3D integrated.
+ */
+
+enum r3di_gpio_bit {
+	/* Bit 1 - Switch between front/rear mic. 0 = rear, 1 = front */
+	R3DI_MIC_SELECT_BIT = 1,
+	/* Bit 2 - Switch between headphone/line out. 0 = Headphone, 1 = Line */
+	R3DI_OUT_SELECT_BIT = 2,
+	/*
+	 * I dunno what this actually does, but it stays on until the dsp
+	 * is downloaded.
+	 */
+	R3DI_GPIO_DSP_DOWNLOADING = 3,
+	/*
+	 * Same as above, no clue what it does, but it comes on after the dsp
+	 * is downloaded.
+	 */
+	R3DI_GPIO_DSP_DOWNLOADED = 4
+};
+
+enum r3di_mic_select {
+	/* Set GPIO bit 1 to 0 for rear mic */
+	R3DI_REAR_MIC = 0,
+	/* Set GPIO bit 1 to 1 for front microphone*/
+	R3DI_FRONT_MIC = 1
+};
+
+enum r3di_out_select {
+	/* Set GPIO bit 2 to 0 for headphone */
+	R3DI_HEADPHONE_OUT = 0,
+	/* Set GPIO bit 2 to 1 for speaker */
+	R3DI_LINE_OUT = 1
+};
+enum r3di_dsp_status {
+	/* Set GPIO bit 3 to 1 until DSP is downloaded */
+	R3DI_DSP_DOWNLOADING = 0,
+	/* Set GPIO bit 4 to 1 once DSP is downloaded */
+	R3DI_DSP_DOWNLOADED = 1
+};
+
+
+static void r3di_gpio_mic_set(struct hda_codec *codec,
+		enum r3di_mic_select cur_mic)
+{
+	unsigned int cur_gpio;
+
+	/* Get the current GPIO Data setup */
+	cur_gpio = snd_hda_codec_read(codec, 0x01, 0, AC_VERB_GET_GPIO_DATA, 0);
+
+	switch (cur_mic) {
+	case R3DI_REAR_MIC:
+		cur_gpio &= ~(1 << R3DI_MIC_SELECT_BIT);
+		break;
+	case R3DI_FRONT_MIC:
+		cur_gpio |= (1 << R3DI_MIC_SELECT_BIT);
+		break;
+	}
+	snd_hda_codec_write(codec, codec->core.afg, 0,
+			    AC_VERB_SET_GPIO_DATA, cur_gpio);
+}
+
+static void r3di_gpio_out_set(struct hda_codec *codec,
+		enum r3di_out_select cur_out)
+{
+	unsigned int cur_gpio;
+
+	/* Get the current GPIO Data setup */
+	cur_gpio = snd_hda_codec_read(codec, 0x01, 0, AC_VERB_GET_GPIO_DATA, 0);
+
+	switch (cur_out) {
+	case R3DI_HEADPHONE_OUT:
+		cur_gpio &= ~(1 << R3DI_OUT_SELECT_BIT);
+		break;
+	case R3DI_LINE_OUT:
+		cur_gpio |= (1 << R3DI_OUT_SELECT_BIT);
+		break;
+	}
+	snd_hda_codec_write(codec, codec->core.afg, 0,
+			    AC_VERB_SET_GPIO_DATA, cur_gpio);
+}
+
+static void r3di_gpio_dsp_status_set(struct hda_codec *codec,
+		enum r3di_dsp_status dsp_status)
+{
+	unsigned int cur_gpio;
+
+	/* Get the current GPIO Data setup */
+	cur_gpio = snd_hda_codec_read(codec, 0x01, 0, AC_VERB_GET_GPIO_DATA, 0);
+
+	switch (dsp_status) {
+	case R3DI_DSP_DOWNLOADING:
+		cur_gpio |= (1 << R3DI_GPIO_DSP_DOWNLOADING);
+		snd_hda_codec_write(codec, codec->core.afg, 0,
+				AC_VERB_SET_GPIO_DATA, cur_gpio);
+		break;
+	case R3DI_DSP_DOWNLOADED:
+		/* Set DOWNLOADING bit to 0. */
+		cur_gpio &= ~(1 << R3DI_GPIO_DSP_DOWNLOADING);
+
+		snd_hda_codec_write(codec, codec->core.afg, 0,
+				AC_VERB_SET_GPIO_DATA, cur_gpio);
+
+		cur_gpio |= (1 << R3DI_GPIO_DSP_DOWNLOADED);
+		break;
+	}
+
+	snd_hda_codec_write(codec, codec->core.afg, 0,
+			    AC_VERB_SET_GPIO_DATA, cur_gpio);
+}
+
+/*
  * PCM callbacks
  */
 static int ca0132_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
@@ -2852,6 +3392,24 @@ static unsigned int ca0132_capture_pcm_delay(struct hda_pcm_stream *info,
 	  .tlv = { .c = ca0132_volume_tlv }, \
 	  .private_value = HDA_COMPOSE_AMP_VAL(nid, channel, 0, dir) }
 
+/*
+ * Creates a mixer control that uses defaults of HDA_CODEC_VOL except for the
+ * volume put, which is used for setting the DSP volume. This was done because
+ * the ca0132 functions were taking too much time and causing lag.
+ */
+#define CA0132_ALT_CODEC_VOL_MONO(xname, nid, channel, dir) \
+	{ .iface = SNDRV_CTL_ELEM_IFACE_MIXER, \
+	  .name = xname, \
+	  .subdevice = HDA_SUBDEV_AMP_FLAG, \
+	  .access = SNDRV_CTL_ELEM_ACCESS_READWRITE | \
+			SNDRV_CTL_ELEM_ACCESS_TLV_READ | \
+			SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK, \
+	  .info = snd_hda_mixer_amp_volume_info, \
+	  .get = snd_hda_mixer_amp_volume_get, \
+	  .put = ca0132_alt_volume_put, \
+	  .tlv = { .c = snd_hda_mixer_amp_tlv }, \
+	  .private_value = HDA_COMPOSE_AMP_VAL(nid, channel, 0, dir) }
+
 #define CA0132_CODEC_MUTE_MONO(xname, nid, channel, dir) \
 	{ .iface = SNDRV_CTL_ELEM_IFACE_MIXER, \
 	  .name = xname, \
@@ -2864,9 +3422,88 @@ static unsigned int ca0132_capture_pcm_delay(struct hda_pcm_stream *info,
 /* stereo */
 #define CA0132_CODEC_VOL(xname, nid, dir) \
 	CA0132_CODEC_VOL_MONO(xname, nid, 3, dir)
+#define CA0132_ALT_CODEC_VOL(xname, nid, dir) \
+	CA0132_ALT_CODEC_VOL_MONO(xname, nid, 3, dir)
 #define CA0132_CODEC_MUTE(xname, nid, dir) \
 	CA0132_CODEC_MUTE_MONO(xname, nid, 3, dir)
 
+/* lookup tables */
+/*
+ * Lookup table with decibel values for the DSP. When volume is changed in
+ * Windows, the DSP is also sent the dB value in floating point. In Windows,
+ * these values have decimal points, probably because the Windows driver
+ * actually uses floating point. We can't here, so I made a lookup table of
+ * values -90 to 9. -90 is the lowest decibel value for both the ADC's and the
+ * DAC's, and 9 is the maximum.
+ */
+static const unsigned int float_vol_db_lookup[] = {
+0xC2B40000, 0xC2B20000, 0xC2B00000, 0xC2AE0000, 0xC2AC0000, 0xC2AA0000,
+0xC2A80000, 0xC2A60000, 0xC2A40000, 0xC2A20000, 0xC2A00000, 0xC29E0000,
+0xC29C0000, 0xC29A0000, 0xC2980000, 0xC2960000, 0xC2940000, 0xC2920000,
+0xC2900000, 0xC28E0000, 0xC28C0000, 0xC28A0000, 0xC2880000, 0xC2860000,
+0xC2840000, 0xC2820000, 0xC2800000, 0xC27C0000, 0xC2780000, 0xC2740000,
+0xC2700000, 0xC26C0000, 0xC2680000, 0xC2640000, 0xC2600000, 0xC25C0000,
+0xC2580000, 0xC2540000, 0xC2500000, 0xC24C0000, 0xC2480000, 0xC2440000,
+0xC2400000, 0xC23C0000, 0xC2380000, 0xC2340000, 0xC2300000, 0xC22C0000,
+0xC2280000, 0xC2240000, 0xC2200000, 0xC21C0000, 0xC2180000, 0xC2140000,
+0xC2100000, 0xC20C0000, 0xC2080000, 0xC2040000, 0xC2000000, 0xC1F80000,
+0xC1F00000, 0xC1E80000, 0xC1E00000, 0xC1D80000, 0xC1D00000, 0xC1C80000,
+0xC1C00000, 0xC1B80000, 0xC1B00000, 0xC1A80000, 0xC1A00000, 0xC1980000,
+0xC1900000, 0xC1880000, 0xC1800000, 0xC1700000, 0xC1600000, 0xC1500000,
+0xC1400000, 0xC1300000, 0xC1200000, 0xC1100000, 0xC1000000, 0xC0E00000,
+0xC0C00000, 0xC0A00000, 0xC0800000, 0xC0400000, 0xC0000000, 0xBF800000,
+0x00000000, 0x3F800000, 0x40000000, 0x40400000, 0x40800000, 0x40A00000,
+0x40C00000, 0x40E00000, 0x41000000, 0x41100000
+};
+
+/*
+ * This table counts from float 0 to 1 in increments of .01, which is
+ * useful for a few different sliders.
+ */
+static const unsigned int float_zero_to_one_lookup[] = {
+0x00000000, 0x3C23D70A, 0x3CA3D70A, 0x3CF5C28F, 0x3D23D70A, 0x3D4CCCCD,
+0x3D75C28F, 0x3D8F5C29, 0x3DA3D70A, 0x3DB851EC, 0x3DCCCCCD, 0x3DE147AE,
+0x3DF5C28F, 0x3E051EB8, 0x3E0F5C29, 0x3E19999A, 0x3E23D70A, 0x3E2E147B,
+0x3E3851EC, 0x3E428F5C, 0x3E4CCCCD, 0x3E570A3D, 0x3E6147AE, 0x3E6B851F,
+0x3E75C28F, 0x3E800000, 0x3E851EB8, 0x3E8A3D71, 0x3E8F5C29, 0x3E947AE1,
+0x3E99999A, 0x3E9EB852, 0x3EA3D70A, 0x3EA8F5C3, 0x3EAE147B, 0x3EB33333,
+0x3EB851EC, 0x3EBD70A4, 0x3EC28F5C, 0x3EC7AE14, 0x3ECCCCCD, 0x3ED1EB85,
+0x3ED70A3D, 0x3EDC28F6, 0x3EE147AE, 0x3EE66666, 0x3EEB851F, 0x3EF0A3D7,
+0x3EF5C28F, 0x3EFAE148, 0x3F000000, 0x3F028F5C, 0x3F051EB8, 0x3F07AE14,
+0x3F0A3D71, 0x3F0CCCCD, 0x3F0F5C29, 0x3F11EB85, 0x3F147AE1, 0x3F170A3D,
+0x3F19999A, 0x3F1C28F6, 0x3F1EB852, 0x3F2147AE, 0x3F23D70A, 0x3F266666,
+0x3F28F5C3, 0x3F2B851F, 0x3F2E147B, 0x3F30A3D7, 0x3F333333, 0x3F35C28F,
+0x3F3851EC, 0x3F3AE148, 0x3F3D70A4, 0x3F400000, 0x3F428F5C, 0x3F451EB8,
+0x3F47AE14, 0x3F4A3D71, 0x3F4CCCCD, 0x3F4F5C29, 0x3F51EB85, 0x3F547AE1,
+0x3F570A3D, 0x3F59999A, 0x3F5C28F6, 0x3F5EB852, 0x3F6147AE, 0x3F63D70A,
+0x3F666666, 0x3F68F5C3, 0x3F6B851F, 0x3F6E147B, 0x3F70A3D7, 0x3F733333,
+0x3F75C28F, 0x3F7851EC, 0x3F7AE148, 0x3F7D70A4, 0x3F800000
+};
+
+/*
+ * This table counts from float 10 to 1000, which is the range of the x-bass
+ * crossover slider in Windows.
+ */
+static const unsigned int float_xbass_xover_lookup[] = {
+0x41200000, 0x41A00000, 0x41F00000, 0x42200000, 0x42480000, 0x42700000,
+0x428C0000, 0x42A00000, 0x42B40000, 0x42C80000, 0x42DC0000, 0x42F00000,
+0x43020000, 0x430C0000, 0x43160000, 0x43200000, 0x432A0000, 0x43340000,
+0x433E0000, 0x43480000, 0x43520000, 0x435C0000, 0x43660000, 0x43700000,
+0x437A0000, 0x43820000, 0x43870000, 0x438C0000, 0x43910000, 0x43960000,
+0x439B0000, 0x43A00000, 0x43A50000, 0x43AA0000, 0x43AF0000, 0x43B40000,
+0x43B90000, 0x43BE0000, 0x43C30000, 0x43C80000, 0x43CD0000, 0x43D20000,
+0x43D70000, 0x43DC0000, 0x43E10000, 0x43E60000, 0x43EB0000, 0x43F00000,
+0x43F50000, 0x43FA0000, 0x43FF0000, 0x44020000, 0x44048000, 0x44070000,
+0x44098000, 0x440C0000, 0x440E8000, 0x44110000, 0x44138000, 0x44160000,
+0x44188000, 0x441B0000, 0x441D8000, 0x44200000, 0x44228000, 0x44250000,
+0x44278000, 0x442A0000, 0x442C8000, 0x442F0000, 0x44318000, 0x44340000,
+0x44368000, 0x44390000, 0x443B8000, 0x443E0000, 0x44408000, 0x44430000,
+0x44458000, 0x44480000, 0x444A8000, 0x444D0000, 0x444F8000, 0x44520000,
+0x44548000, 0x44570000, 0x44598000, 0x445C0000, 0x445E8000, 0x44610000,
+0x44638000, 0x44660000, 0x44688000, 0x446B0000, 0x446D8000, 0x44700000,
+0x44728000, 0x44750000, 0x44778000, 0x447A0000
+};
+
 /* The following are for tuning of products */
 #ifdef ENABLE_TUNING_CONTROLS
 
@@ -2942,7 +3579,7 @@ static int tuning_ctl_set(struct hda_codec *codec, hda_nid_t nid,
 			break;
 
 	snd_hda_power_up(codec);
-	dspio_set_param(codec, ca0132_tuning_ctls[i].mid,
+	dspio_set_param(codec, ca0132_tuning_ctls[i].mid, 0x20,
 			ca0132_tuning_ctls[i].req,
 			&(lookup[idx]), sizeof(unsigned int));
 	snd_hda_power_down(codec);
@@ -3068,8 +3705,8 @@ static int equalizer_ctl_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const DECLARE_TLV_DB_SCALE(voice_focus_db_scale, 2000, 100, 0);
-static const DECLARE_TLV_DB_SCALE(eq_db_scale, -2400, 100, 0);
+static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(voice_focus_db_scale, 2000, 100, 0);
+static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(eq_db_scale, -2400, 100, 0);
 
 static int add_tuning_control(struct hda_codec *codec,
 				hda_nid_t pnid, hda_nid_t nid,
@@ -3207,7 +3844,7 @@ static int ca0132_select_out(struct hda_codec *codec)
 				    pin_ctl & ~PIN_HP);
 		/* enable speaker node */
 		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[0], 0,
-					     AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+				AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
 		snd_hda_set_pin_ctl(codec, spec->out_pins[0],
 				    pin_ctl | PIN_OUT);
 	} else {
@@ -3251,13 +3888,209 @@ exit:
 	return err < 0 ? err : 0;
 }
 
+/*
+ * This function behaves similarly to the ca0132_select_out funciton above,
+ * except with a few differences. It adds the ability to select the current
+ * output with an enumerated control "output source" if the auto detect
+ * mute switch is set to off. If the auto detect mute switch is enabled, it
+ * will detect either headphone or lineout(SPEAKER_OUT) from jack detection.
+ * It also adds the ability to auto-detect the front headphone port. The only
+ * way to select surround is to disable auto detect, and set Surround with the
+ * enumerated control.
+ */
+static int ca0132_alt_select_out(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned int pin_ctl;
+	int jack_present;
+	int auto_jack;
+	unsigned int i;
+	unsigned int tmp;
+	int err;
+	/* Default Headphone is rear headphone */
+	hda_nid_t headphone_nid = spec->out_pins[1];
+
+	codec_dbg(codec, "%s\n", __func__);
+
+	snd_hda_power_up_pm(codec);
+
+	auto_jack = spec->vnode_lswitch[VNID_HP_ASEL - VNODE_START_NID];
+
+	/*
+	 * If headphone rear or front is plugged in, set to headphone.
+	 * If neither is plugged in, set to rear line out. Only if
+	 * hp/speaker auto detect is enabled.
+	 */
+	if (auto_jack) {
+		jack_present = snd_hda_jack_detect(codec, spec->unsol_tag_hp) ||
+			   snd_hda_jack_detect(codec, spec->unsol_tag_front_hp);
+
+		if (jack_present)
+			spec->cur_out_type = HEADPHONE_OUT;
+		else
+			spec->cur_out_type = SPEAKER_OUT;
+	} else
+		spec->cur_out_type = spec->out_enum_val;
+
+	/* Begin DSP output switch */
+	tmp = FLOAT_ONE;
+	err = dspio_set_uint_param(codec, 0x96, 0x3A, tmp);
+	if (err < 0)
+		goto exit;
+
+	switch (spec->cur_out_type) {
+	case SPEAKER_OUT:
+		codec_dbg(codec, "%s speaker\n", __func__);
+		/*speaker out config*/
+		switch (spec->quirk) {
+		case QUIRK_SBZ:
+			writew(0x0007, spec->mem_base + 0x320);
+			writew(0x0104, spec->mem_base + 0x320);
+			writew(0x0101, spec->mem_base + 0x320);
+			chipio_set_control_param(codec, 0x0D, 0x18);
+			break;
+		case QUIRK_R3DI:
+			chipio_set_control_param(codec, 0x0D, 0x24);
+			r3di_gpio_out_set(codec, R3DI_LINE_OUT);
+			break;
+		}
+
+		/* disable headphone node */
+		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[1], 0,
+					AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_set_pin_ctl(codec, spec->out_pins[1],
+				    pin_ctl & ~PIN_HP);
+		/* enable line-out node */
+		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[0], 0,
+				AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_set_pin_ctl(codec, spec->out_pins[0],
+				    pin_ctl | PIN_OUT);
+		/* Enable EAPD */
+		snd_hda_codec_write(codec, spec->out_pins[0], 0,
+			AC_VERB_SET_EAPD_BTLENABLE, 0x01);
+
+		/* If PlayEnhancement is enabled, set different source */
+		if (spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID])
+			dspio_set_uint_param(codec, 0x80, 0x04, FLOAT_ONE);
+		else
+			dspio_set_uint_param(codec, 0x80, 0x04, FLOAT_EIGHT);
+		break;
+	case HEADPHONE_OUT:
+		codec_dbg(codec, "%s hp\n", __func__);
+		/* Headphone out config*/
+		switch (spec->quirk) {
+		case QUIRK_SBZ:
+			writew(0x0107, spec->mem_base + 0x320);
+			writew(0x0104, spec->mem_base + 0x320);
+			writew(0x0001, spec->mem_base + 0x320);
+			chipio_set_control_param(codec, 0x0D, 0x12);
+			break;
+		case QUIRK_R3DI:
+			chipio_set_control_param(codec, 0x0D, 0x21);
+			r3di_gpio_out_set(codec, R3DI_HEADPHONE_OUT);
+			break;
+		}
+
+		snd_hda_codec_write(codec, spec->out_pins[0], 0,
+			AC_VERB_SET_EAPD_BTLENABLE, 0x00);
+
+		/* disable speaker*/
+		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[0], 0,
+					AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_set_pin_ctl(codec, spec->out_pins[0],
+				pin_ctl & ~PIN_HP);
+
+		/* enable headphone, either front or rear */
+
+		if (snd_hda_jack_detect(codec, spec->unsol_tag_front_hp))
+			headphone_nid = spec->out_pins[2];
+		else if (snd_hda_jack_detect(codec, spec->unsol_tag_hp))
+			headphone_nid = spec->out_pins[1];
+
+		pin_ctl = snd_hda_codec_read(codec, headphone_nid, 0,
+					AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_set_pin_ctl(codec, headphone_nid,
+				    pin_ctl | PIN_HP);
+
+		if (spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID])
+			dspio_set_uint_param(codec, 0x80, 0x04, FLOAT_ONE);
+		else
+			dspio_set_uint_param(codec, 0x80, 0x04, FLOAT_ZERO);
+		break;
+	case SURROUND_OUT:
+		codec_dbg(codec, "%s surround\n", __func__);
+		/* Surround out config*/
+		switch (spec->quirk) {
+		case QUIRK_SBZ:
+			writew(0x0007, spec->mem_base + 0x320);
+			writew(0x0104, spec->mem_base + 0x320);
+			writew(0x0101, spec->mem_base + 0x320);
+			chipio_set_control_param(codec, 0x0D, 0x18);
+			break;
+		case QUIRK_R3DI:
+			chipio_set_control_param(codec, 0x0D, 0x24);
+			r3di_gpio_out_set(codec, R3DI_LINE_OUT);
+			break;
+		}
+		/* enable line out node */
+		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[0], 0,
+				AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_set_pin_ctl(codec, spec->out_pins[0],
+						pin_ctl | PIN_OUT);
+		/* Disable headphone out */
+		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[1], 0,
+					AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_set_pin_ctl(codec, spec->out_pins[1],
+				    pin_ctl & ~PIN_HP);
+		/* Enable EAPD on line out */
+		snd_hda_codec_write(codec, spec->out_pins[0], 0,
+			AC_VERB_SET_EAPD_BTLENABLE, 0x01);
+		/* enable center/lfe out node */
+		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[2], 0,
+					AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_set_pin_ctl(codec, spec->out_pins[2],
+				    pin_ctl | PIN_OUT);
+		/* Now set rear surround node as out. */
+		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[3], 0,
+					AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+		snd_hda_set_pin_ctl(codec, spec->out_pins[3],
+				    pin_ctl | PIN_OUT);
+
+		if (spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID])
+			dspio_set_uint_param(codec, 0x80, 0x04, FLOAT_ONE);
+		else
+			dspio_set_uint_param(codec, 0x80, 0x04, FLOAT_EIGHT);
+		break;
+	}
+
+	/* run through the output dsp commands for line-out */
+	for (i = 0; i < alt_out_presets[spec->cur_out_type].commands; i++) {
+		err = dspio_set_uint_param(codec,
+		alt_out_presets[spec->cur_out_type].mids[i],
+		alt_out_presets[spec->cur_out_type].reqs[i],
+		alt_out_presets[spec->cur_out_type].vals[i]);
+
+		if (err < 0)
+			goto exit;
+	}
+
+exit:
+	snd_hda_power_down_pm(codec);
+
+	return err < 0 ? err : 0;
+}
+
 static void ca0132_unsol_hp_delayed(struct work_struct *work)
 {
 	struct ca0132_spec *spec = container_of(
 		to_delayed_work(work), struct ca0132_spec, unsol_hp_work);
 	struct hda_jack_tbl *jack;
 
-	ca0132_select_out(spec->codec);
+	if (spec->use_alt_functions)
+		ca0132_alt_select_out(spec->codec);
+	else
+		ca0132_select_out(spec->codec);
+
 	jack = snd_hda_jack_tbl_get(spec->codec, spec->unsol_tag_hp);
 	if (jack) {
 		jack->block_report = 0;
@@ -3268,6 +4101,10 @@ static void ca0132_unsol_hp_delayed(struct work_struct *work)
 static void ca0132_set_dmic(struct hda_codec *codec, int enable);
 static int ca0132_mic_boost_set(struct hda_codec *codec, long val);
 static int ca0132_effects_set(struct hda_codec *codec, hda_nid_t nid, long val);
+static void resume_mic1(struct hda_codec *codec, unsigned int oldval);
+static int stop_mic1(struct hda_codec *codec);
+static int ca0132_cvoice_switch_set(struct hda_codec *codec);
+static int ca0132_alt_mic_boost_set(struct hda_codec *codec, long val);
 
 /*
  * Select the active VIP source
@@ -3310,6 +4147,71 @@ static int ca0132_set_vipsource(struct hda_codec *codec, int val)
 	return 1;
 }
 
+static int ca0132_alt_set_vipsource(struct hda_codec *codec, int val)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned int tmp;
+
+	if (spec->dsp_state != DSP_DOWNLOADED)
+		return 0;
+
+	codec_dbg(codec, "%s\n", __func__);
+
+	chipio_set_stream_control(codec, 0x03, 0);
+	chipio_set_stream_control(codec, 0x04, 0);
+
+	/* if CrystalVoice is off, vipsource should be 0 */
+	if (!spec->effects_switch[CRYSTAL_VOICE - EFFECT_START_NID] ||
+	    (val == 0) || spec->in_enum_val == REAR_LINE_IN) {
+		codec_dbg(codec, "%s: off.", __func__);
+		chipio_set_control_param(codec, CONTROL_PARAM_VIP_SOURCE, 0);
+
+		tmp = FLOAT_ZERO;
+		dspio_set_uint_param(codec, 0x80, 0x05, tmp);
+
+		chipio_set_conn_rate(codec, MEM_CONNID_MICIN1, SR_96_000);
+		chipio_set_conn_rate(codec, MEM_CONNID_MICOUT1, SR_96_000);
+		if (spec->quirk == QUIRK_R3DI)
+			chipio_set_conn_rate(codec, 0x0F, SR_96_000);
+
+
+		if (spec->in_enum_val == REAR_LINE_IN)
+			tmp = FLOAT_ZERO;
+		else {
+			if (spec->quirk == QUIRK_SBZ)
+				tmp = FLOAT_THREE;
+			else
+				tmp = FLOAT_ONE;
+		}
+
+		dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+
+	} else {
+		codec_dbg(codec, "%s: on.", __func__);
+		chipio_set_conn_rate(codec, MEM_CONNID_MICIN1, SR_16_000);
+		chipio_set_conn_rate(codec, MEM_CONNID_MICOUT1, SR_16_000);
+		if (spec->quirk == QUIRK_R3DI)
+			chipio_set_conn_rate(codec, 0x0F, SR_16_000);
+
+		if (spec->effects_switch[VOICE_FOCUS - EFFECT_START_NID])
+			tmp = FLOAT_TWO;
+		else
+			tmp = FLOAT_ONE;
+		dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+
+		tmp = FLOAT_ONE;
+		dspio_set_uint_param(codec, 0x80, 0x05, tmp);
+
+		msleep(20);
+		chipio_set_control_param(codec, CONTROL_PARAM_VIP_SOURCE, val);
+	}
+
+	chipio_set_stream_control(codec, 0x03, 1);
+	chipio_set_stream_control(codec, 0x04, 1);
+
+	return 1;
+}
+
 /*
  * Select the active microphone.
  * If autodetect is enabled, mic will be selected based on jack detection.
@@ -3363,6 +4265,125 @@ static int ca0132_select_mic(struct hda_codec *codec)
 }
 
 /*
+ * Select the active input.
+ * Mic detection isn't used, because it's kind of pointless on the SBZ.
+ * The front mic has no jack-detection, so the only way to switch to it
+ * is to do it manually in alsamixer.
+ */
+static int ca0132_alt_select_in(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned int tmp;
+
+	codec_dbg(codec, "%s\n", __func__);
+
+	snd_hda_power_up_pm(codec);
+
+	chipio_set_stream_control(codec, 0x03, 0);
+	chipio_set_stream_control(codec, 0x04, 0);
+
+	spec->cur_mic_type = spec->in_enum_val;
+
+	switch (spec->cur_mic_type) {
+	case REAR_MIC:
+		switch (spec->quirk) {
+		case QUIRK_SBZ:
+			writew(0x0000, spec->mem_base + 0x320);
+			tmp = FLOAT_THREE;
+			break;
+		case QUIRK_R3DI:
+			r3di_gpio_mic_set(codec, R3DI_REAR_MIC);
+			tmp = FLOAT_ONE;
+			break;
+		default:
+			tmp = FLOAT_ONE;
+			break;
+		}
+
+		chipio_set_conn_rate(codec, MEM_CONNID_MICIN1, SR_96_000);
+		chipio_set_conn_rate(codec, MEM_CONNID_MICOUT1, SR_96_000);
+		if (spec->quirk == QUIRK_R3DI)
+			chipio_set_conn_rate(codec, 0x0F, SR_96_000);
+
+		dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+
+		chipio_set_stream_control(codec, 0x03, 1);
+		chipio_set_stream_control(codec, 0x04, 1);
+
+		if (spec->quirk == QUIRK_SBZ) {
+			chipio_write(codec, 0x18B098, 0x0000000C);
+			chipio_write(codec, 0x18B09C, 0x0000000C);
+		}
+		ca0132_alt_mic_boost_set(codec, spec->mic_boost_enum_val);
+		break;
+	case REAR_LINE_IN:
+		ca0132_mic_boost_set(codec, 0);
+		switch (spec->quirk) {
+		case QUIRK_SBZ:
+			writew(0x0000, spec->mem_base + 0x320);
+			break;
+		case QUIRK_R3DI:
+			r3di_gpio_mic_set(codec, R3DI_REAR_MIC);
+			break;
+		}
+
+		chipio_set_conn_rate(codec, MEM_CONNID_MICIN1, SR_96_000);
+		chipio_set_conn_rate(codec, MEM_CONNID_MICOUT1, SR_96_000);
+		if (spec->quirk == QUIRK_R3DI)
+			chipio_set_conn_rate(codec, 0x0F, SR_96_000);
+
+		tmp = FLOAT_ZERO;
+		dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+
+		if (spec->quirk == QUIRK_SBZ) {
+			chipio_write(codec, 0x18B098, 0x00000000);
+			chipio_write(codec, 0x18B09C, 0x00000000);
+		}
+
+		chipio_set_stream_control(codec, 0x03, 1);
+		chipio_set_stream_control(codec, 0x04, 1);
+		break;
+	case FRONT_MIC:
+		switch (spec->quirk) {
+		case QUIRK_SBZ:
+			writew(0x0100, spec->mem_base + 0x320);
+			writew(0x0005, spec->mem_base + 0x320);
+			tmp = FLOAT_THREE;
+			break;
+		case QUIRK_R3DI:
+			r3di_gpio_mic_set(codec, R3DI_FRONT_MIC);
+			tmp = FLOAT_ONE;
+			break;
+		default:
+			tmp = FLOAT_ONE;
+			break;
+		}
+
+		chipio_set_conn_rate(codec, MEM_CONNID_MICIN1, SR_96_000);
+		chipio_set_conn_rate(codec, MEM_CONNID_MICOUT1, SR_96_000);
+		if (spec->quirk == QUIRK_R3DI)
+			chipio_set_conn_rate(codec, 0x0F, SR_96_000);
+
+		dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+
+		chipio_set_stream_control(codec, 0x03, 1);
+		chipio_set_stream_control(codec, 0x04, 1);
+
+		if (spec->quirk == QUIRK_SBZ) {
+			chipio_write(codec, 0x18B098, 0x0000000C);
+			chipio_write(codec, 0x18B09C, 0x000000CC);
+		}
+		ca0132_alt_mic_boost_set(codec, spec->mic_boost_enum_val);
+		break;
+	}
+	ca0132_cvoice_switch_set(codec);
+
+	snd_hda_power_down_pm(codec);
+	return 0;
+
+}
+
+/*
  * Check if VNODE settings take effect immediately.
  */
 static bool ca0132_is_vnode_effective(struct hda_codec *codec,
@@ -3418,7 +4439,7 @@ static int ca0132_voicefx_set(struct hda_codec *codec, int enable)
 static int ca0132_effects_set(struct hda_codec *codec, hda_nid_t nid, long val)
 {
 	struct ca0132_spec *spec = codec->spec;
-	unsigned int on;
+	unsigned int on, tmp;
 	int num_fx = OUT_EFFECTS_COUNT + IN_EFFECTS_COUNT;
 	int err = 0;
 	int idx = nid - EFFECT_START_NID;
@@ -3442,6 +4463,46 @@ static int ca0132_effects_set(struct hda_codec *codec, hda_nid_t nid, long val)
 		/* Voice Focus applies to 2-ch Mic, Digital Mic */
 		if ((nid == VOICE_FOCUS) && (spec->cur_mic_type != DIGITAL_MIC))
 			val = 0;
+
+		/* If Voice Focus on SBZ, set to two channel. */
+		if ((nid == VOICE_FOCUS) && (spec->quirk == QUIRK_SBZ)
+				&& (spec->cur_mic_type != REAR_LINE_IN)) {
+			if (spec->effects_switch[CRYSTAL_VOICE -
+						 EFFECT_START_NID]) {
+
+				if (spec->effects_switch[VOICE_FOCUS -
+							 EFFECT_START_NID]) {
+					tmp = FLOAT_TWO;
+					val = 1;
+				} else
+					tmp = FLOAT_ONE;
+
+				dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+			}
+		}
+		/*
+		 * For SBZ noise reduction, there's an extra command
+		 * to module ID 0x47. No clue why.
+		 */
+		if ((nid == NOISE_REDUCTION) && (spec->quirk == QUIRK_SBZ)
+				&& (spec->cur_mic_type != REAR_LINE_IN)) {
+			if (spec->effects_switch[CRYSTAL_VOICE -
+						 EFFECT_START_NID]) {
+				if (spec->effects_switch[NOISE_REDUCTION -
+							 EFFECT_START_NID])
+					tmp = FLOAT_ONE;
+				else
+					tmp = FLOAT_ZERO;
+			} else
+				tmp = FLOAT_ZERO;
+
+			dspio_set_uint_param(codec, 0x47, 0x00, tmp);
+		}
+
+		/* If rear line in disable effects. */
+		if (spec->use_alt_functions &&
+				spec->in_enum_val == REAR_LINE_IN)
+			val = 0;
 	}
 
 	codec_dbg(codec, "ca0132_effect_set: nid=0x%x, val=%ld\n",
@@ -3469,6 +4530,9 @@ static int ca0132_pe_switch_set(struct hda_codec *codec)
 	codec_dbg(codec, "ca0132_pe_switch_set: val=%ld\n",
 		    spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID]);
 
+	if (spec->use_alt_functions)
+		ca0132_alt_select_out(codec);
+
 	i = OUT_EFFECT_START_NID - EFFECT_START_NID;
 	nid = OUT_EFFECT_START_NID;
 	/* PE affects all out effects */
@@ -3526,7 +4590,10 @@ static int ca0132_cvoice_switch_set(struct hda_codec *codec)
 
 	/* set correct vipsource */
 	oldval = stop_mic1(codec);
-	ret |= ca0132_set_vipsource(codec, 1);
+	if (spec->use_alt_functions)
+		ret |= ca0132_alt_set_vipsource(codec, 1);
+	else
+		ret |= ca0132_set_vipsource(codec, 1);
 	resume_mic1(codec, oldval);
 	return ret;
 }
@@ -3546,6 +4613,16 @@ static int ca0132_mic_boost_set(struct hda_codec *codec, long val)
 	return ret;
 }
 
+static int ca0132_alt_mic_boost_set(struct hda_codec *codec, long val)
+{
+	struct ca0132_spec *spec = codec->spec;
+	int ret = 0;
+
+	ret = snd_hda_codec_amp_update(codec, spec->input_pins[0], 0,
+				HDA_INPUT, 0, HDA_AMP_VOLMASK, val);
+	return ret;
+}
+
 static int ca0132_vnode_switch_set(struct snd_kcontrol *kcontrol,
 				struct snd_ctl_elem_value *ucontrol)
 {
@@ -3560,8 +4637,12 @@ static int ca0132_vnode_switch_set(struct snd_kcontrol *kcontrol,
 	if (nid == VNID_HP_SEL) {
 		auto_jack =
 			spec->vnode_lswitch[VNID_HP_ASEL - VNODE_START_NID];
-		if (!auto_jack)
-			ca0132_select_out(codec);
+		if (!auto_jack) {
+			if (spec->use_alt_functions)
+				ca0132_alt_select_out(codec);
+			else
+				ca0132_select_out(codec);
+		}
 		return 1;
 	}
 
@@ -3574,7 +4655,10 @@ static int ca0132_vnode_switch_set(struct snd_kcontrol *kcontrol,
 	}
 
 	if (nid == VNID_HP_ASEL) {
-		ca0132_select_out(codec);
+		if (spec->use_alt_functions)
+			ca0132_alt_select_out(codec);
+		else
+			ca0132_select_out(codec);
 		return 1;
 	}
 
@@ -3602,6 +4686,432 @@ static int ca0132_vnode_switch_set(struct snd_kcontrol *kcontrol,
 	return ret;
 }
 /* End of control change helpers. */
+/*
+ * Below I've added controls to mess with the effect levels, I've only enabled
+ * them on the Sound Blaster Z, but they would probably also work on the
+ * Chromebook. I figured they were probably tuned specifically for it, and left
+ * out for a reason.
+ */
+
+/* Sets DSP effect level from the sliders above the controls */
+static int ca0132_alt_slider_ctl_set(struct hda_codec *codec, hda_nid_t nid,
+			  const unsigned int *lookup, int idx)
+{
+	int i = 0;
+	unsigned int y;
+	/*
+	 * For X_BASS, req 2 is actually crossover freq instead of
+	 * effect level
+	 */
+	if (nid == X_BASS)
+		y = 2;
+	else
+		y = 1;
+
+	snd_hda_power_up(codec);
+	if (nid == XBASS_XOVER) {
+		for (i = 0; i < OUT_EFFECTS_COUNT; i++)
+			if (ca0132_effects[i].nid == X_BASS)
+				break;
+
+		dspio_set_param(codec, ca0132_effects[i].mid, 0x20,
+				ca0132_effects[i].reqs[1],
+				&(lookup[idx - 1]), sizeof(unsigned int));
+	} else {
+		/* Find the actual effect structure */
+		for (i = 0; i < OUT_EFFECTS_COUNT; i++)
+			if (nid == ca0132_effects[i].nid)
+				break;
+
+		dspio_set_param(codec, ca0132_effects[i].mid, 0x20,
+				ca0132_effects[i].reqs[y],
+				&(lookup[idx]), sizeof(unsigned int));
+	}
+
+	snd_hda_power_down(codec);
+
+	return 0;
+}
+
+static int ca0132_alt_xbass_xover_slider_ctl_get(struct snd_kcontrol *kcontrol,
+			  struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	long *valp = ucontrol->value.integer.value;
+
+	*valp = spec->xbass_xover_freq;
+	return 0;
+}
+
+static int ca0132_alt_slider_ctl_get(struct snd_kcontrol *kcontrol,
+			  struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	hda_nid_t nid = get_amp_nid(kcontrol);
+	long *valp = ucontrol->value.integer.value;
+	int idx = nid - OUT_EFFECT_START_NID;
+
+	*valp = spec->fx_ctl_val[idx];
+	return 0;
+}
+
+/*
+ * The X-bass crossover starts at 10hz, so the min is 1. The
+ * frequency is set in multiples of 10.
+ */
+static int ca0132_alt_xbass_xover_slider_info(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_info *uinfo)
+{
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
+	uinfo->count = 1;
+	uinfo->value.integer.min = 1;
+	uinfo->value.integer.max = 100;
+	uinfo->value.integer.step = 1;
+
+	return 0;
+}
+
+static int ca0132_alt_effect_slider_info(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_info *uinfo)
+{
+	int chs = get_amp_channels(kcontrol);
+
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
+	uinfo->count = chs == 3 ? 2 : 1;
+	uinfo->value.integer.min = 0;
+	uinfo->value.integer.max = 100;
+	uinfo->value.integer.step = 1;
+
+	return 0;
+}
+
+static int ca0132_alt_xbass_xover_slider_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	hda_nid_t nid = get_amp_nid(kcontrol);
+	long *valp = ucontrol->value.integer.value;
+	int idx;
+
+	/* any change? */
+	if (spec->xbass_xover_freq == *valp)
+		return 0;
+
+	spec->xbass_xover_freq = *valp;
+
+	idx = *valp;
+	ca0132_alt_slider_ctl_set(codec, nid, float_xbass_xover_lookup, idx);
+
+	return 0;
+}
+
+static int ca0132_alt_effect_slider_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	hda_nid_t nid = get_amp_nid(kcontrol);
+	long *valp = ucontrol->value.integer.value;
+	int idx;
+
+	idx = nid - EFFECT_START_NID;
+	/* any change? */
+	if (spec->fx_ctl_val[idx] == *valp)
+		return 0;
+
+	spec->fx_ctl_val[idx] = *valp;
+
+	idx = *valp;
+	ca0132_alt_slider_ctl_set(codec, nid, float_zero_to_one_lookup, idx);
+
+	return 0;
+}
+
+
+/*
+ * Mic Boost Enum for alternative ca0132 codecs. I didn't like that the original
+ * only has off or full 30 dB, and didn't like making a volume slider that has
+ * traditional 0-100 in alsamixer that goes in big steps. I like enum better.
+ */
+#define MIC_BOOST_NUM_OF_STEPS 4
+#define MIC_BOOST_ENUM_MAX_STRLEN 10
+
+static int ca0132_alt_mic_boost_info(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_info *uinfo)
+{
+	char *sfx = "dB";
+	char namestr[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED;
+	uinfo->count = 1;
+	uinfo->value.enumerated.items = MIC_BOOST_NUM_OF_STEPS;
+	if (uinfo->value.enumerated.item >= MIC_BOOST_NUM_OF_STEPS)
+		uinfo->value.enumerated.item = MIC_BOOST_NUM_OF_STEPS - 1;
+	sprintf(namestr, "%d %s", (uinfo->value.enumerated.item * 10), sfx);
+	strcpy(uinfo->value.enumerated.name, namestr);
+	return 0;
+}
+
+static int ca0132_alt_mic_boost_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+
+	ucontrol->value.enumerated.item[0] = spec->mic_boost_enum_val;
+	return 0;
+}
+
+static int ca0132_alt_mic_boost_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	int sel = ucontrol->value.enumerated.item[0];
+	unsigned int items = MIC_BOOST_NUM_OF_STEPS;
+
+	if (sel >= items)
+		return 0;
+
+	codec_dbg(codec, "ca0132_alt_mic_boost: boost=%d\n",
+		    sel);
+
+	spec->mic_boost_enum_val = sel;
+
+	if (spec->in_enum_val != REAR_LINE_IN)
+		ca0132_alt_mic_boost_set(codec, spec->mic_boost_enum_val);
+
+	return 1;
+}
+
+
+/*
+ * Input Select Control for alternative ca0132 codecs. This exists because
+ * front microphone has no auto-detect, and we need a way to set the rear
+ * as line-in
+ */
+static int ca0132_alt_input_source_info(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_info *uinfo)
+{
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED;
+	uinfo->count = 1;
+	uinfo->value.enumerated.items = IN_SRC_NUM_OF_INPUTS;
+	if (uinfo->value.enumerated.item >= IN_SRC_NUM_OF_INPUTS)
+		uinfo->value.enumerated.item = IN_SRC_NUM_OF_INPUTS - 1;
+	strcpy(uinfo->value.enumerated.name,
+			in_src_str[uinfo->value.enumerated.item]);
+	return 0;
+}
+
+static int ca0132_alt_input_source_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+
+	ucontrol->value.enumerated.item[0] = spec->in_enum_val;
+	return 0;
+}
+
+static int ca0132_alt_input_source_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	int sel = ucontrol->value.enumerated.item[0];
+	unsigned int items = IN_SRC_NUM_OF_INPUTS;
+
+	if (sel >= items)
+		return 0;
+
+	codec_dbg(codec, "ca0132_alt_input_select: sel=%d, preset=%s\n",
+		    sel, in_src_str[sel]);
+
+	spec->in_enum_val = sel;
+
+	ca0132_alt_select_in(codec);
+
+	return 1;
+}
+
+/* Sound Blaster Z Output Select Control */
+static int ca0132_alt_output_select_get_info(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_info *uinfo)
+{
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED;
+	uinfo->count = 1;
+	uinfo->value.enumerated.items = NUM_OF_OUTPUTS;
+	if (uinfo->value.enumerated.item >= NUM_OF_OUTPUTS)
+		uinfo->value.enumerated.item = NUM_OF_OUTPUTS - 1;
+	strcpy(uinfo->value.enumerated.name,
+			alt_out_presets[uinfo->value.enumerated.item].name);
+	return 0;
+}
+
+static int ca0132_alt_output_select_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+
+	ucontrol->value.enumerated.item[0] = spec->out_enum_val;
+	return 0;
+}
+
+static int ca0132_alt_output_select_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	int sel = ucontrol->value.enumerated.item[0];
+	unsigned int items = NUM_OF_OUTPUTS;
+	unsigned int auto_jack;
+
+	if (sel >= items)
+		return 0;
+
+	codec_dbg(codec, "ca0132_alt_output_select: sel=%d, preset=%s\n",
+		    sel, alt_out_presets[sel].name);
+
+	spec->out_enum_val = sel;
+
+	auto_jack = spec->vnode_lswitch[VNID_HP_ASEL - VNODE_START_NID];
+
+	if (!auto_jack)
+		ca0132_alt_select_out(codec);
+
+	return 1;
+}
+
+/*
+ * Smart Volume output setting control. Three different settings, Normal,
+ * which takes the value from the smart volume slider. The two others, loud
+ * and night, disregard the slider value and have uneditable values.
+ */
+#define NUM_OF_SVM_SETTINGS 3
+static const char *const out_svm_set_enum_str[3] = {"Normal", "Loud", "Night" };
+
+static int ca0132_alt_svm_setting_info(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_info *uinfo)
+{
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED;
+	uinfo->count = 1;
+	uinfo->value.enumerated.items = NUM_OF_SVM_SETTINGS;
+	if (uinfo->value.enumerated.item >= NUM_OF_SVM_SETTINGS)
+		uinfo->value.enumerated.item = NUM_OF_SVM_SETTINGS - 1;
+	strcpy(uinfo->value.enumerated.name,
+			out_svm_set_enum_str[uinfo->value.enumerated.item]);
+	return 0;
+}
+
+static int ca0132_alt_svm_setting_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+
+	ucontrol->value.enumerated.item[0] = spec->smart_volume_setting;
+	return 0;
+}
+
+static int ca0132_alt_svm_setting_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	int sel = ucontrol->value.enumerated.item[0];
+	unsigned int items = NUM_OF_SVM_SETTINGS;
+	unsigned int idx = SMART_VOLUME - EFFECT_START_NID;
+	unsigned int tmp;
+
+	if (sel >= items)
+		return 0;
+
+	codec_dbg(codec, "ca0132_alt_svm_setting: sel=%d, preset=%s\n",
+		    sel, out_svm_set_enum_str[sel]);
+
+	spec->smart_volume_setting = sel;
+
+	switch (sel) {
+	case 0:
+		tmp = FLOAT_ZERO;
+		break;
+	case 1:
+		tmp = FLOAT_ONE;
+		break;
+	case 2:
+		tmp = FLOAT_TWO;
+		break;
+	default:
+		tmp = FLOAT_ZERO;
+		break;
+	}
+	/* Req 2 is the Smart Volume Setting req. */
+	dspio_set_uint_param(codec, ca0132_effects[idx].mid,
+			ca0132_effects[idx].reqs[2], tmp);
+	return 1;
+}
+
+/* Sound Blaster Z EQ preset controls */
+static int ca0132_alt_eq_preset_info(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_info *uinfo)
+{
+	unsigned int items = ARRAY_SIZE(ca0132_alt_eq_presets);
+
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED;
+	uinfo->count = 1;
+	uinfo->value.enumerated.items = items;
+	if (uinfo->value.enumerated.item >= items)
+		uinfo->value.enumerated.item = items - 1;
+	strcpy(uinfo->value.enumerated.name,
+		ca0132_alt_eq_presets[uinfo->value.enumerated.item].name);
+	return 0;
+}
+
+static int ca0132_alt_eq_preset_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+
+	ucontrol->value.enumerated.item[0] = spec->eq_preset_val;
+	return 0;
+}
+
+static int ca0132_alt_eq_preset_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	int i, err = 0;
+	int sel = ucontrol->value.enumerated.item[0];
+	unsigned int items = ARRAY_SIZE(ca0132_alt_eq_presets);
+
+	if (sel >= items)
+		return 0;
+
+	codec_dbg(codec, "%s: sel=%d, preset=%s\n", __func__, sel,
+			ca0132_alt_eq_presets[sel].name);
+	/*
+	 * Idx 0 is default.
+	 * Default needs to qualify with CrystalVoice state.
+	 */
+	for (i = 0; i < EQ_PRESET_MAX_PARAM_COUNT; i++) {
+		err = dspio_set_uint_param(codec, ca0132_alt_eq_enum.mid,
+				ca0132_alt_eq_enum.reqs[i],
+				ca0132_alt_eq_presets[sel].vals[i]);
+		if (err < 0)
+			break;
+	}
+
+	if (err >= 0)
+		spec->eq_preset_val = sel;
+
+	return 1;
+}
 
 static int ca0132_voicefx_info(struct snd_kcontrol *kcontrol,
 				 struct snd_ctl_elem_info *uinfo)
@@ -3753,10 +5263,15 @@ static int ca0132_switch_put(struct snd_kcontrol *kcontrol,
 	/* mic boost */
 	if (nid == spec->input_pins[0]) {
 		spec->cur_mic_boost = *valp;
+		if (spec->use_alt_functions) {
+			if (spec->in_enum_val != REAR_LINE_IN)
+				changed = ca0132_mic_boost_set(codec, *valp);
+		} else {
+			/* Mic boost does not apply to Digital Mic */
+			if (spec->cur_mic_type != DIGITAL_MIC)
+				changed = ca0132_mic_boost_set(codec, *valp);
+		}
 
-		/* Mic boost does not apply to Digital Mic */
-		if (spec->cur_mic_type != DIGITAL_MIC)
-			changed = ca0132_mic_boost_set(codec, *valp);
 		goto exit;
 	}
 
@@ -3768,6 +5283,41 @@ exit:
 /*
  * Volume related
  */
+/*
+ * Sets the internal DSP decibel level to match the DAC for output, and the
+ * ADC for input. Currently only the SBZ sets dsp capture volume level, and
+ * all alternative codecs set DSP playback volume.
+ */
+static void ca0132_alt_dsp_volume_put(struct hda_codec *codec, hda_nid_t nid)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned int dsp_dir;
+	unsigned int lookup_val;
+
+	if (nid == VNID_SPK)
+		dsp_dir = DSP_VOL_OUT;
+	else
+		dsp_dir = DSP_VOL_IN;
+
+	lookup_val = spec->vnode_lvol[nid - VNODE_START_NID];
+
+	dspio_set_uint_param(codec,
+		ca0132_alt_vol_ctls[dsp_dir].mid,
+		ca0132_alt_vol_ctls[dsp_dir].reqs[0],
+		float_vol_db_lookup[lookup_val]);
+
+	lookup_val = spec->vnode_rvol[nid - VNODE_START_NID];
+
+	dspio_set_uint_param(codec,
+		ca0132_alt_vol_ctls[dsp_dir].mid,
+		ca0132_alt_vol_ctls[dsp_dir].reqs[1],
+		float_vol_db_lookup[lookup_val]);
+
+	dspio_set_uint_param(codec,
+		ca0132_alt_vol_ctls[dsp_dir].mid,
+		ca0132_alt_vol_ctls[dsp_dir].reqs[2], FLOAT_ZERO);
+}
+
 static int ca0132_volume_info(struct snd_kcontrol *kcontrol,
 			      struct snd_ctl_elem_info *uinfo)
 {
@@ -3869,6 +5419,51 @@ static int ca0132_volume_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
+/*
+ * This function is the same as the one above, because using an if statement
+ * inside of the above volume control for the DSP volume would cause too much
+ * lag. This is a lot more smooth.
+ */
+static int ca0132_alt_volume_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct ca0132_spec *spec = codec->spec;
+	hda_nid_t nid = get_amp_nid(kcontrol);
+	int ch = get_amp_channels(kcontrol);
+	long *valp = ucontrol->value.integer.value;
+	hda_nid_t vnid = 0;
+	int changed = 1;
+
+	switch (nid) {
+	case 0x02:
+		vnid = VNID_SPK;
+		break;
+	case 0x07:
+		vnid = VNID_MIC;
+		break;
+	}
+
+	/* store the left and right volume */
+	if (ch & 1) {
+		spec->vnode_lvol[vnid - VNODE_START_NID] = *valp;
+		valp++;
+	}
+	if (ch & 2) {
+		spec->vnode_rvol[vnid - VNODE_START_NID] = *valp;
+		valp++;
+	}
+
+	snd_hda_power_up(codec);
+	ca0132_alt_dsp_volume_put(codec, vnid);
+	mutex_lock(&codec->control_mutex);
+	changed = snd_hda_mixer_amp_volume_put(kcontrol, ucontrol);
+	mutex_unlock(&codec->control_mutex);
+	snd_hda_power_down(codec);
+
+	return changed;
+}
+
 static int ca0132_volume_tlv(struct snd_kcontrol *kcontrol, int op_flag,
 			     unsigned int size, unsigned int __user *tlv)
 {
@@ -3907,14 +5502,59 @@ static int ca0132_volume_tlv(struct snd_kcontrol *kcontrol, int op_flag,
 	return err;
 }
 
+/* Add volume slider control for effect level */
+static int ca0132_alt_add_effect_slider(struct hda_codec *codec, hda_nid_t nid,
+					const char *pfx, int dir)
+{
+	char namestr[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+	int type = dir ? HDA_INPUT : HDA_OUTPUT;
+	struct snd_kcontrol_new knew =
+		HDA_CODEC_VOLUME_MONO(namestr, nid, 1, 0, type);
+
+	sprintf(namestr, "FX: %s %s Volume", pfx, dirstr[dir]);
+
+	knew.tlv.c = 0;
+	knew.tlv.p = 0;
+
+	switch (nid) {
+	case XBASS_XOVER:
+		knew.info = ca0132_alt_xbass_xover_slider_info;
+		knew.get = ca0132_alt_xbass_xover_slider_ctl_get;
+		knew.put = ca0132_alt_xbass_xover_slider_put;
+		break;
+	default:
+		knew.info = ca0132_alt_effect_slider_info;
+		knew.get = ca0132_alt_slider_ctl_get;
+		knew.put = ca0132_alt_effect_slider_put;
+		knew.private_value =
+			HDA_COMPOSE_AMP_VAL(nid, 1, 0, type);
+		break;
+	}
+
+	return snd_hda_ctl_add(codec, nid, snd_ctl_new1(&knew, codec));
+}
+
+/*
+ * Added FX: prefix for the alternative codecs, because otherwise the surround
+ * effect would conflict with the Surround sound volume control. Also seems more
+ * clear as to what the switches do. Left alone for others.
+ */
 static int add_fx_switch(struct hda_codec *codec, hda_nid_t nid,
 			 const char *pfx, int dir)
 {
+	struct ca0132_spec *spec = codec->spec;
 	char namestr[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
 	int type = dir ? HDA_INPUT : HDA_OUTPUT;
 	struct snd_kcontrol_new knew =
 		CA0132_CODEC_MUTE_MONO(namestr, nid, 1, type);
-	sprintf(namestr, "%s %s Switch", pfx, dirstr[dir]);
+	/* If using alt_controls, add FX: prefix. But, don't add FX:
+	 * prefix to OutFX or InFX enable controls.
+	 */
+	if ((spec->use_alt_controls) && (nid <= IN_EFFECT_END_NID))
+		sprintf(namestr, "FX: %s %s Switch", pfx, dirstr[dir]);
+	else
+		sprintf(namestr, "%s %s Switch", pfx, dirstr[dir]);
+
 	return snd_hda_ctl_add(codec, nid, snd_ctl_new1(&knew, codec));
 }
 
@@ -3929,11 +5569,141 @@ static int add_voicefx(struct hda_codec *codec)
 	return snd_hda_ctl_add(codec, VOICEFX, snd_ctl_new1(&knew, codec));
 }
 
+/* Create the EQ Preset control */
+static int add_ca0132_alt_eq_presets(struct hda_codec *codec)
+{
+	struct snd_kcontrol_new knew =
+		HDA_CODEC_MUTE_MONO(ca0132_alt_eq_enum.name,
+				    EQ_PRESET_ENUM, 1, 0, HDA_OUTPUT);
+	knew.info = ca0132_alt_eq_preset_info;
+	knew.get = ca0132_alt_eq_preset_get;
+	knew.put = ca0132_alt_eq_preset_put;
+	return snd_hda_ctl_add(codec, EQ_PRESET_ENUM,
+				snd_ctl_new1(&knew, codec));
+}
+
+/*
+ * Add enumerated control for the three different settings of the smart volume
+ * output effect. Normal just uses the slider value, and loud and night are
+ * their own things that ignore that value.
+ */
+static int ca0132_alt_add_svm_enum(struct hda_codec *codec)
+{
+	struct snd_kcontrol_new knew =
+		HDA_CODEC_MUTE_MONO("FX: Smart Volume Setting",
+				    SMART_VOLUME_ENUM, 1, 0, HDA_OUTPUT);
+	knew.info = ca0132_alt_svm_setting_info;
+	knew.get = ca0132_alt_svm_setting_get;
+	knew.put = ca0132_alt_svm_setting_put;
+	return snd_hda_ctl_add(codec, SMART_VOLUME_ENUM,
+				snd_ctl_new1(&knew, codec));
+
+}
+
+/*
+ * Create an Output Select enumerated control for codecs with surround
+ * out capabilities.
+ */
+static int ca0132_alt_add_output_enum(struct hda_codec *codec)
+{
+	struct snd_kcontrol_new knew =
+		HDA_CODEC_MUTE_MONO("Output Select",
+				    OUTPUT_SOURCE_ENUM, 1, 0, HDA_OUTPUT);
+	knew.info = ca0132_alt_output_select_get_info;
+	knew.get = ca0132_alt_output_select_get;
+	knew.put = ca0132_alt_output_select_put;
+	return snd_hda_ctl_add(codec, OUTPUT_SOURCE_ENUM,
+				snd_ctl_new1(&knew, codec));
+}
+
+/*
+ * Create an Input Source enumerated control for the alternate ca0132 codecs
+ * because the front microphone has no auto-detect, and Line-in has to be set
+ * somehow.
+ */
+static int ca0132_alt_add_input_enum(struct hda_codec *codec)
+{
+	struct snd_kcontrol_new knew =
+		HDA_CODEC_MUTE_MONO("Input Source",
+				    INPUT_SOURCE_ENUM, 1, 0, HDA_INPUT);
+	knew.info = ca0132_alt_input_source_info;
+	knew.get = ca0132_alt_input_source_get;
+	knew.put = ca0132_alt_input_source_put;
+	return snd_hda_ctl_add(codec, INPUT_SOURCE_ENUM,
+				snd_ctl_new1(&knew, codec));
+}
+
+/*
+ * Add mic boost enumerated control. Switches through 0dB to 30dB. This adds
+ * more control than the original mic boost, which is either full 30dB or off.
+ */
+static int ca0132_alt_add_mic_boost_enum(struct hda_codec *codec)
+{
+	struct snd_kcontrol_new knew =
+		HDA_CODEC_MUTE_MONO("Mic Boost Capture Switch",
+				    MIC_BOOST_ENUM, 1, 0, HDA_INPUT);
+	knew.info = ca0132_alt_mic_boost_info;
+	knew.get = ca0132_alt_mic_boost_get;
+	knew.put = ca0132_alt_mic_boost_put;
+	return snd_hda_ctl_add(codec, MIC_BOOST_ENUM,
+				snd_ctl_new1(&knew, codec));
+
+}
+
+/*
+ * Need to create slave controls for the alternate codecs that have surround
+ * capabilities.
+ */
+static const char * const ca0132_alt_slave_pfxs[] = {
+	"Front", "Surround", "Center", "LFE", NULL,
+};
+
+/*
+ * Also need special channel map, because the default one is incorrect.
+ * I think this has to do with the pin for rear surround being 0x11,
+ * and the center/lfe being 0x10. Usually the pin order is the opposite.
+ */
+const struct snd_pcm_chmap_elem ca0132_alt_chmaps[] = {
+	{ .channels = 2,
+	  .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR } },
+	{ .channels = 4,
+	  .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR,
+		   SNDRV_CHMAP_RL, SNDRV_CHMAP_RR } },
+	{ .channels = 6,
+	  .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR,
+		   SNDRV_CHMAP_FC, SNDRV_CHMAP_LFE,
+		   SNDRV_CHMAP_RL, SNDRV_CHMAP_RR } },
+	{ }
+};
+
+/* Add the correct chmap for streams with 6 channels. */
+static void ca0132_alt_add_chmap_ctls(struct hda_codec *codec)
+{
+	int err = 0;
+	struct hda_pcm *pcm;
+
+	list_for_each_entry(pcm, &codec->pcm_list_head, list) {
+		struct hda_pcm_stream *hinfo =
+			&pcm->stream[SNDRV_PCM_STREAM_PLAYBACK];
+		struct snd_pcm_chmap *chmap;
+		const struct snd_pcm_chmap_elem *elem;
+
+		elem = ca0132_alt_chmaps;
+		if (hinfo->channels_max == 6) {
+			err = snd_pcm_add_chmap_ctls(pcm->pcm,
+					SNDRV_PCM_STREAM_PLAYBACK,
+					elem, hinfo->channels_max, 0, &chmap);
+			if (err < 0)
+				codec_dbg(codec, "snd_pcm_add_chmap_ctls failed!");
+		}
+	}
+}
+
 /*
  * When changing Node IDs for Mixer Controls below, make sure to update
  * Node IDs in ca0132_config() as well.
  */
-static struct snd_kcontrol_new ca0132_mixer[] = {
+static const struct snd_kcontrol_new ca0132_mixer[] = {
 	CA0132_CODEC_VOL("Master Playback Volume", VNID_SPK, HDA_OUTPUT),
 	CA0132_CODEC_MUTE("Master Playback Switch", VNID_SPK, HDA_OUTPUT),
 	CA0132_CODEC_VOL("Capture Volume", VNID_MIC, HDA_INPUT),
@@ -3955,10 +5725,55 @@ static struct snd_kcontrol_new ca0132_mixer[] = {
 	{ } /* end */
 };
 
+/*
+ * SBZ specific control mixer. Removes auto-detect for mic, and adds surround
+ * controls. Also sets both the Front Playback and Capture Volume controls to
+ * alt so they set the DSP's decibel level.
+ */
+static const struct snd_kcontrol_new sbz_mixer[] = {
+	CA0132_ALT_CODEC_VOL("Front Playback Volume", 0x02, HDA_OUTPUT),
+	CA0132_CODEC_MUTE("Front Playback Switch", VNID_SPK, HDA_OUTPUT),
+	HDA_CODEC_VOLUME("Surround Playback Volume", 0x04, 0, HDA_OUTPUT),
+	HDA_CODEC_MUTE("Surround Playback Switch", 0x04, 0, HDA_OUTPUT),
+	HDA_CODEC_VOLUME_MONO("Center Playback Volume", 0x03, 1, 0, HDA_OUTPUT),
+	HDA_CODEC_MUTE_MONO("Center Playback Switch", 0x03, 1, 0, HDA_OUTPUT),
+	HDA_CODEC_VOLUME_MONO("LFE Playback Volume", 0x03, 2, 0, HDA_OUTPUT),
+	HDA_CODEC_MUTE_MONO("LFE Playback Switch", 0x03, 2, 0, HDA_OUTPUT),
+	CA0132_ALT_CODEC_VOL("Capture Volume", 0x07, HDA_INPUT),
+	CA0132_CODEC_MUTE("Capture Switch", VNID_MIC, HDA_INPUT),
+	HDA_CODEC_VOLUME("What U Hear Capture Volume", 0x0a, 0, HDA_INPUT),
+	HDA_CODEC_MUTE("What U Hear Capture Switch", 0x0a, 0, HDA_INPUT),
+	CA0132_CODEC_MUTE_MONO("HP/Speaker Auto Detect Playback Switch",
+				VNID_HP_ASEL, 1, HDA_OUTPUT),
+	{ } /* end */
+};
+
+/*
+ * Same as the Sound Blaster Z, except doesn't use the alt volume for capture
+ * because it doesn't set decibel levels for the DSP for capture.
+ */
+static const struct snd_kcontrol_new r3di_mixer[] = {
+	CA0132_ALT_CODEC_VOL("Front Playback Volume", 0x02, HDA_OUTPUT),
+	CA0132_CODEC_MUTE("Front Playback Switch", VNID_SPK, HDA_OUTPUT),
+	HDA_CODEC_VOLUME("Surround Playback Volume", 0x04, 0, HDA_OUTPUT),
+	HDA_CODEC_MUTE("Surround Playback Switch", 0x04, 0, HDA_OUTPUT),
+	HDA_CODEC_VOLUME_MONO("Center Playback Volume", 0x03, 1, 0, HDA_OUTPUT),
+	HDA_CODEC_MUTE_MONO("Center Playback Switch", 0x03, 1, 0, HDA_OUTPUT),
+	HDA_CODEC_VOLUME_MONO("LFE Playback Volume", 0x03, 2, 0, HDA_OUTPUT),
+	HDA_CODEC_MUTE_MONO("LFE Playback Switch", 0x03, 2, 0, HDA_OUTPUT),
+	CA0132_CODEC_VOL("Capture Volume", VNID_MIC, HDA_INPUT),
+	CA0132_CODEC_MUTE("Capture Switch", VNID_MIC, HDA_INPUT),
+	HDA_CODEC_VOLUME("What U Hear Capture Volume", 0x0a, 0, HDA_INPUT),
+	HDA_CODEC_MUTE("What U Hear Capture Switch", 0x0a, 0, HDA_INPUT),
+	CA0132_CODEC_MUTE_MONO("HP/Speaker Auto Detect Playback Switch",
+				VNID_HP_ASEL, 1, HDA_OUTPUT),
+	{ } /* end */
+};
+
 static int ca0132_build_controls(struct hda_codec *codec)
 {
 	struct ca0132_spec *spec = codec->spec;
-	int i, num_fx;
+	int i, num_fx, num_sliders;
 	int err = 0;
 
 	/* Add Mixer controls */
@@ -3967,29 +5782,94 @@ static int ca0132_build_controls(struct hda_codec *codec)
 		if (err < 0)
 			return err;
 	}
+	/* Setup vmaster with surround slaves for desktop ca0132 devices */
+	if (spec->use_alt_functions) {
+		snd_hda_set_vmaster_tlv(codec, spec->dacs[0], HDA_OUTPUT,
+					spec->tlv);
+		snd_hda_add_vmaster(codec, "Master Playback Volume",
+					spec->tlv, ca0132_alt_slave_pfxs,
+					"Playback Volume");
+		err = __snd_hda_add_vmaster(codec, "Master Playback Switch",
+					    NULL, ca0132_alt_slave_pfxs,
+					    "Playback Switch",
+					    true, &spec->vmaster_mute.sw_kctl);
+
+	}
 
 	/* Add in and out effects controls.
 	 * VoiceFX, PE and CrystalVoice are added separately.
 	 */
 	num_fx = OUT_EFFECTS_COUNT + IN_EFFECTS_COUNT;
 	for (i = 0; i < num_fx; i++) {
+		/* SBZ breaks if Echo Cancellation is used */
+		if (spec->quirk == QUIRK_SBZ) {
+			if (i == (ECHO_CANCELLATION - IN_EFFECT_START_NID +
+						OUT_EFFECTS_COUNT))
+				continue;
+		}
+
 		err = add_fx_switch(codec, ca0132_effects[i].nid,
 				    ca0132_effects[i].name,
 				    ca0132_effects[i].direct);
 		if (err < 0)
 			return err;
 	}
+	/*
+	 * If codec has use_alt_controls set to true, add effect level sliders,
+	 * EQ presets, and Smart Volume presets. Also, change names to add FX
+	 * prefix, and change PlayEnhancement and CrystalVoice to match.
+	 */
+	if (spec->use_alt_controls) {
+		ca0132_alt_add_svm_enum(codec);
+		add_ca0132_alt_eq_presets(codec);
+		err = add_fx_switch(codec, PLAY_ENHANCEMENT,
+					"Enable OutFX", 0);
+		if (err < 0)
+			return err;
 
-	err = add_fx_switch(codec, PLAY_ENHANCEMENT, "PlayEnhancement", 0);
-	if (err < 0)
-		return err;
+		err = add_fx_switch(codec, CRYSTAL_VOICE,
+					"Enable InFX", 1);
+		if (err < 0)
+			return err;
 
-	err = add_fx_switch(codec, CRYSTAL_VOICE, "CrystalVoice", 1);
-	if (err < 0)
-		return err;
+		num_sliders = OUT_EFFECTS_COUNT - 1;
+		for (i = 0; i < num_sliders; i++) {
+			err = ca0132_alt_add_effect_slider(codec,
+					    ca0132_effects[i].nid,
+					    ca0132_effects[i].name,
+					    ca0132_effects[i].direct);
+			if (err < 0)
+				return err;
+		}
+
+		err = ca0132_alt_add_effect_slider(codec, XBASS_XOVER,
+					"X-Bass Crossover", EFX_DIR_OUT);
 
+		if (err < 0)
+			return err;
+	} else {
+		err = add_fx_switch(codec, PLAY_ENHANCEMENT,
+					"PlayEnhancement", 0);
+		if (err < 0)
+			return err;
+
+		err = add_fx_switch(codec, CRYSTAL_VOICE,
+					"CrystalVoice", 1);
+		if (err < 0)
+			return err;
+	}
 	add_voicefx(codec);
 
+	/*
+	 * If the codec uses alt_functions, you need the enumerated controls
+	 * to select the new outputs and inputs, plus add the new mic boost
+	 * setting control.
+	 */
+	if (spec->use_alt_functions) {
+		ca0132_alt_add_output_enum(codec);
+		ca0132_alt_add_input_enum(codec);
+		ca0132_alt_add_mic_boost_enum(codec);
+	}
 #ifdef ENABLE_TUNING_CONTROLS
 	add_tuning_ctls(codec);
 #endif
@@ -4014,6 +5894,10 @@ static int ca0132_build_controls(struct hda_codec *codec)
 		if (err < 0)
 			return err;
 	}
+
+	if (spec->use_alt_functions)
+		ca0132_alt_add_chmap_ctls(codec);
+
 	return 0;
 }
 
@@ -4068,6 +5952,11 @@ static int ca0132_build_pcms(struct hda_codec *codec)
 	info = snd_hda_codec_pcm_new(codec, "CA0132 Analog");
 	if (!info)
 		return -ENOMEM;
+	if (spec->use_alt_functions) {
+		info->own_chmap = true;
+		info->stream[SNDRV_PCM_STREAM_PLAYBACK].chmap
+			= ca0132_alt_chmaps;
+	}
 	info->stream[SNDRV_PCM_STREAM_PLAYBACK] = ca0132_pcm_analog_playback;
 	info->stream[SNDRV_PCM_STREAM_PLAYBACK].nid = spec->dacs[0];
 	info->stream[SNDRV_PCM_STREAM_PLAYBACK].channels_max =
@@ -4076,12 +5965,16 @@ static int ca0132_build_pcms(struct hda_codec *codec)
 	info->stream[SNDRV_PCM_STREAM_CAPTURE].substreams = 1;
 	info->stream[SNDRV_PCM_STREAM_CAPTURE].nid = spec->adcs[0];
 
-	info = snd_hda_codec_pcm_new(codec, "CA0132 Analog Mic-In2");
-	if (!info)
-		return -ENOMEM;
-	info->stream[SNDRV_PCM_STREAM_CAPTURE] = ca0132_pcm_analog_capture;
-	info->stream[SNDRV_PCM_STREAM_CAPTURE].substreams = 1;
-	info->stream[SNDRV_PCM_STREAM_CAPTURE].nid = spec->adcs[1];
+	/* With the DSP enabled, desktops don't use this ADC. */
+	if (spec->use_alt_functions) {
+		info = snd_hda_codec_pcm_new(codec, "CA0132 Analog Mic-In2");
+		if (!info)
+			return -ENOMEM;
+		info->stream[SNDRV_PCM_STREAM_CAPTURE] =
+			ca0132_pcm_analog_capture;
+		info->stream[SNDRV_PCM_STREAM_CAPTURE].substreams = 1;
+		info->stream[SNDRV_PCM_STREAM_CAPTURE].nid = spec->adcs[1];
+	}
 
 	info = snd_hda_codec_pcm_new(codec, "CA0132 What U Hear");
 	if (!info)
@@ -4288,6 +6181,196 @@ static void ca0132_refresh_widget_caps(struct hda_codec *codec)
 }
 
 /*
+ * Recon3Di r3di_setup_defaults sub functions.
+ */
+
+static void r3di_dsp_scp_startup(struct hda_codec *codec)
+{
+	unsigned int tmp;
+
+	tmp = 0x00000000;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0A, tmp);
+
+	tmp = 0x00000001;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0B, tmp);
+
+	tmp = 0x00000004;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0C, tmp);
+
+	tmp = 0x00000005;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0C, tmp);
+
+	tmp = 0x00000000;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0C, tmp);
+
+}
+
+static void r3di_dsp_initial_mic_setup(struct hda_codec *codec)
+{
+	unsigned int tmp;
+
+	/* Mic 1 Setup */
+	chipio_set_conn_rate(codec, MEM_CONNID_MICIN1, SR_96_000);
+	chipio_set_conn_rate(codec, MEM_CONNID_MICOUT1, SR_96_000);
+	/* This ConnPointID is unique to Recon3Di. Haven't seen it elsewhere */
+	chipio_set_conn_rate(codec, 0x0F, SR_96_000);
+	tmp = FLOAT_ONE;
+	dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+
+	/* Mic 2 Setup, even though it isn't connected on SBZ */
+	chipio_set_conn_rate(codec, MEM_CONNID_MICIN2, SR_96_000);
+	chipio_set_conn_rate(codec, MEM_CONNID_MICOUT2, SR_96_000);
+	chipio_set_conn_rate(codec, 0x0F, SR_96_000);
+	tmp = FLOAT_ZERO;
+	dspio_set_uint_param(codec, 0x80, 0x01, tmp);
+}
+
+/*
+ * Initialize Sound Blaster Z analog microphones.
+ */
+static void sbz_init_analog_mics(struct hda_codec *codec)
+{
+	unsigned int tmp;
+
+	/* Mic 1 Setup */
+	chipio_set_conn_rate(codec, MEM_CONNID_MICIN1, SR_96_000);
+	chipio_set_conn_rate(codec, MEM_CONNID_MICOUT1, SR_96_000);
+	tmp = FLOAT_THREE;
+	dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+
+	/* Mic 2 Setup, even though it isn't connected on SBZ */
+	chipio_set_conn_rate(codec, MEM_CONNID_MICIN2, SR_96_000);
+	chipio_set_conn_rate(codec, MEM_CONNID_MICOUT2, SR_96_000);
+	tmp = FLOAT_ZERO;
+	dspio_set_uint_param(codec, 0x80, 0x01, tmp);
+
+}
+
+/*
+ * Sets the source of stream 0x14 to connpointID 0x48, and the destination
+ * connpointID to 0x91. If this isn't done, the destination is 0x71, and
+ * you get no sound. I'm guessing this has to do with the Sound Blaster Z
+ * having an updated DAC, which changes the destination to that DAC.
+ */
+static void sbz_connect_streams(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+
+	mutex_lock(&spec->chipio_mutex);
+
+	codec_dbg(codec, "Connect Streams entered, mutex locked and loaded.\n");
+
+	chipio_set_stream_channels(codec, 0x0C, 6);
+	chipio_set_stream_control(codec, 0x0C, 1);
+
+	/* This value is 0x43 for 96khz, and 0x83 for 192khz. */
+	chipio_write_no_mutex(codec, 0x18a020, 0x00000043);
+
+	/* Setup stream 0x14 with it's source and destination points */
+	chipio_set_stream_source_dest(codec, 0x14, 0x48, 0x91);
+	chipio_set_conn_rate_no_mutex(codec, 0x48, SR_96_000);
+	chipio_set_conn_rate_no_mutex(codec, 0x91, SR_96_000);
+	chipio_set_stream_channels(codec, 0x14, 2);
+	chipio_set_stream_control(codec, 0x14, 1);
+
+	codec_dbg(codec, "Connect Streams exited, mutex released.\n");
+
+	mutex_unlock(&spec->chipio_mutex);
+
+}
+
+/*
+ * Write data through ChipIO to setup proper stream destinations.
+ * Not sure how it exactly works, but it seems to direct data
+ * to different destinations. Example is f8 to c0, e0 to c0.
+ * All I know is, if you don't set these, you get no sound.
+ */
+static void sbz_chipio_startup_data(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+
+	mutex_lock(&spec->chipio_mutex);
+	codec_dbg(codec, "Startup Data entered, mutex locked and loaded.\n");
+
+	/* These control audio output */
+	chipio_write_no_mutex(codec, 0x190060, 0x0001f8c0);
+	chipio_write_no_mutex(codec, 0x190064, 0x0001f9c1);
+	chipio_write_no_mutex(codec, 0x190068, 0x0001fac6);
+	chipio_write_no_mutex(codec, 0x19006c, 0x0001fbc7);
+	/* Signal to update I think */
+	chipio_write_no_mutex(codec, 0x19042c, 0x00000001);
+
+	chipio_set_stream_channels(codec, 0x0C, 6);
+	chipio_set_stream_control(codec, 0x0C, 1);
+	/* No clue what these control */
+	chipio_write_no_mutex(codec, 0x190030, 0x0001e0c0);
+	chipio_write_no_mutex(codec, 0x190034, 0x0001e1c1);
+	chipio_write_no_mutex(codec, 0x190038, 0x0001e4c2);
+	chipio_write_no_mutex(codec, 0x19003c, 0x0001e5c3);
+	chipio_write_no_mutex(codec, 0x190040, 0x0001e2c4);
+	chipio_write_no_mutex(codec, 0x190044, 0x0001e3c5);
+	chipio_write_no_mutex(codec, 0x190048, 0x0001e8c6);
+	chipio_write_no_mutex(codec, 0x19004c, 0x0001e9c7);
+	chipio_write_no_mutex(codec, 0x190050, 0x0001ecc8);
+	chipio_write_no_mutex(codec, 0x190054, 0x0001edc9);
+	chipio_write_no_mutex(codec, 0x190058, 0x0001eaca);
+	chipio_write_no_mutex(codec, 0x19005c, 0x0001ebcb);
+
+	chipio_write_no_mutex(codec, 0x19042c, 0x00000001);
+
+	codec_dbg(codec, "Startup Data exited, mutex released.\n");
+	mutex_unlock(&spec->chipio_mutex);
+}
+
+/*
+ * Sound Blaster Z uses these after DSP is loaded. Weird SCP commands
+ * without a 0x20 source like normal.
+ */
+static void sbz_dsp_scp_startup(struct hda_codec *codec)
+{
+	unsigned int tmp;
+
+	tmp = 0x00000003;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0C, tmp);
+
+	tmp = 0x00000000;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0A, tmp);
+
+	tmp = 0x00000001;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0B, tmp);
+
+	tmp = 0x00000004;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0C, tmp);
+
+	tmp = 0x00000005;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0C, tmp);
+
+	tmp = 0x00000000;
+	dspio_set_uint_param_no_source(codec, 0x80, 0x0C, tmp);
+
+}
+
+static void sbz_dsp_initial_mic_setup(struct hda_codec *codec)
+{
+	unsigned int tmp;
+
+	chipio_set_stream_control(codec, 0x03, 0);
+	chipio_set_stream_control(codec, 0x04, 0);
+
+	chipio_set_conn_rate(codec, MEM_CONNID_MICIN1, SR_96_000);
+	chipio_set_conn_rate(codec, MEM_CONNID_MICOUT1, SR_96_000);
+
+	tmp = FLOAT_THREE;
+	dspio_set_uint_param(codec, 0x80, 0x00, tmp);
+
+	chipio_set_stream_control(codec, 0x03, 1);
+	chipio_set_stream_control(codec, 0x04, 1);
+
+	chipio_write(codec, 0x18b098, 0x0000000c);
+	chipio_write(codec, 0x18b09C, 0x0000000c);
+}
+
+/*
  * Setup default parameters for DSP
  */
 static void ca0132_setup_defaults(struct hda_codec *codec)
@@ -4332,16 +6415,159 @@ static void ca0132_setup_defaults(struct hda_codec *codec)
 }
 
 /*
+ * Setup default parameters for Recon3Di DSP.
+ */
+
+static void r3di_setup_defaults(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned int tmp;
+	int num_fx;
+	int idx, i;
+
+	if (spec->dsp_state != DSP_DOWNLOADED)
+		return;
+
+	r3di_dsp_scp_startup(codec);
+
+	r3di_dsp_initial_mic_setup(codec);
+
+	/*remove DSP headroom*/
+	tmp = FLOAT_ZERO;
+	dspio_set_uint_param(codec, 0x96, 0x3C, tmp);
+
+	/* set WUH source */
+	tmp = FLOAT_TWO;
+	dspio_set_uint_param(codec, 0x31, 0x00, tmp);
+	chipio_set_conn_rate(codec, MEM_CONNID_WUH, SR_48_000);
+
+	/* Set speaker source? */
+	dspio_set_uint_param(codec, 0x32, 0x00, tmp);
+
+	r3di_gpio_dsp_status_set(codec, R3DI_DSP_DOWNLOADED);
+
+	/* Setup effect defaults */
+	num_fx = OUT_EFFECTS_COUNT + IN_EFFECTS_COUNT + 1;
+	for (idx = 0; idx < num_fx; idx++) {
+		for (i = 0; i <= ca0132_effects[idx].params; i++) {
+			dspio_set_uint_param(codec,
+					ca0132_effects[idx].mid,
+					ca0132_effects[idx].reqs[i],
+					ca0132_effects[idx].def_vals[i]);
+		}
+	}
+
+}
+
+/*
+ * Setup default parameters for the Sound Blaster Z DSP. A lot more going on
+ * than the Chromebook setup.
+ */
+static void sbz_setup_defaults(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned int tmp, stream_format;
+	int num_fx;
+	int idx, i;
+
+	if (spec->dsp_state != DSP_DOWNLOADED)
+		return;
+
+	sbz_dsp_scp_startup(codec);
+
+	sbz_init_analog_mics(codec);
+
+	sbz_connect_streams(codec);
+
+	sbz_chipio_startup_data(codec);
+
+	chipio_set_stream_control(codec, 0x03, 1);
+	chipio_set_stream_control(codec, 0x04, 1);
+
+	/*
+	 * Sets internal input loopback to off, used to have a switch to
+	 * enable input loopback, but turned out to be way too buggy.
+	 */
+	tmp = FLOAT_ONE;
+	dspio_set_uint_param(codec, 0x37, 0x08, tmp);
+	dspio_set_uint_param(codec, 0x37, 0x10, tmp);
+
+	/*remove DSP headroom*/
+	tmp = FLOAT_ZERO;
+	dspio_set_uint_param(codec, 0x96, 0x3C, tmp);
+
+	/* set WUH source */
+	tmp = FLOAT_TWO;
+	dspio_set_uint_param(codec, 0x31, 0x00, tmp);
+	chipio_set_conn_rate(codec, MEM_CONNID_WUH, SR_48_000);
+
+	/* Set speaker source? */
+	dspio_set_uint_param(codec, 0x32, 0x00, tmp);
+
+	sbz_dsp_initial_mic_setup(codec);
+
+
+	/* out, in effects + voicefx */
+	num_fx = OUT_EFFECTS_COUNT + IN_EFFECTS_COUNT + 1;
+	for (idx = 0; idx < num_fx; idx++) {
+		for (i = 0; i <= ca0132_effects[idx].params; i++) {
+			dspio_set_uint_param(codec,
+					ca0132_effects[idx].mid,
+					ca0132_effects[idx].reqs[i],
+					ca0132_effects[idx].def_vals[i]);
+		}
+	}
+
+	/*
+	 * Have to make a stream to bind the sound output to, otherwise
+	 * you'll get dead audio. Before I did this, it would bind to an
+	 * audio input, and would never work
+	 */
+	stream_format = snd_hdac_calc_stream_format(48000, 2,
+			SNDRV_PCM_FORMAT_S32_LE, 32, 0);
+
+	snd_hda_codec_setup_stream(codec, spec->dacs[0], spec->dsp_stream_id,
+					0, stream_format);
+
+	snd_hda_codec_cleanup_stream(codec, spec->dacs[0]);
+
+	snd_hda_codec_setup_stream(codec, spec->dacs[0], spec->dsp_stream_id,
+					0, stream_format);
+
+	snd_hda_codec_cleanup_stream(codec, spec->dacs[0]);
+}
+
+/*
  * Initialization of flags in chip
  */
 static void ca0132_init_flags(struct hda_codec *codec)
 {
-	chipio_set_control_flag(codec, CONTROL_FLAG_IDLE_ENABLE, 0);
-	chipio_set_control_flag(codec, CONTROL_FLAG_PORT_A_COMMON_MODE, 0);
-	chipio_set_control_flag(codec, CONTROL_FLAG_PORT_D_COMMON_MODE, 0);
-	chipio_set_control_flag(codec, CONTROL_FLAG_PORT_A_10KOHM_LOAD, 0);
-	chipio_set_control_flag(codec, CONTROL_FLAG_PORT_D_10KOHM_LOAD, 0);
-	chipio_set_control_flag(codec, CONTROL_FLAG_ADC_C_HIGH_PASS, 1);
+	struct ca0132_spec *spec = codec->spec;
+
+	if (spec->use_alt_functions) {
+		chipio_set_control_flag(codec, CONTROL_FLAG_DSP_96KHZ, 1);
+		chipio_set_control_flag(codec, CONTROL_FLAG_DAC_96KHZ, 1);
+		chipio_set_control_flag(codec, CONTROL_FLAG_ADC_B_96KHZ, 1);
+		chipio_set_control_flag(codec, CONTROL_FLAG_ADC_C_96KHZ, 1);
+		chipio_set_control_flag(codec, CONTROL_FLAG_SRC_RATE_96KHZ, 1);
+		chipio_set_control_flag(codec, CONTROL_FLAG_IDLE_ENABLE, 0);
+		chipio_set_control_flag(codec, CONTROL_FLAG_SPDIF2OUT, 0);
+		chipio_set_control_flag(codec,
+				CONTROL_FLAG_PORT_D_10KOHM_LOAD, 0);
+		chipio_set_control_flag(codec,
+				CONTROL_FLAG_PORT_A_10KOHM_LOAD, 1);
+	} else {
+		chipio_set_control_flag(codec, CONTROL_FLAG_IDLE_ENABLE, 0);
+		chipio_set_control_flag(codec,
+				CONTROL_FLAG_PORT_A_COMMON_MODE, 0);
+		chipio_set_control_flag(codec,
+				CONTROL_FLAG_PORT_D_COMMON_MODE, 0);
+		chipio_set_control_flag(codec,
+				CONTROL_FLAG_PORT_A_10KOHM_LOAD, 0);
+		chipio_set_control_flag(codec,
+				CONTROL_FLAG_PORT_D_10KOHM_LOAD, 0);
+		chipio_set_control_flag(codec, CONTROL_FLAG_ADC_C_HIGH_PASS, 1);
+	}
 }
 
 /*
@@ -4349,6 +6575,16 @@ static void ca0132_init_flags(struct hda_codec *codec)
  */
 static void ca0132_init_params(struct hda_codec *codec)
 {
+	struct ca0132_spec *spec = codec->spec;
+
+	if (spec->use_alt_functions) {
+		chipio_set_conn_rate(codec, MEM_CONNID_WUH, SR_48_000);
+		chipio_set_conn_rate(codec, 0x0B, SR_48_000);
+		chipio_set_control_param(codec, CONTROL_PARAM_SPDIF1_SOURCE, 0);
+		chipio_set_control_param(codec, 0, 0);
+		chipio_set_control_param(codec, CONTROL_PARAM_VIP_SOURCE, 0);
+	}
+
 	chipio_set_control_param(codec, CONTROL_PARAM_PORTA_160OHM_GAIN, 6);
 	chipio_set_control_param(codec, CONTROL_PARAM_PORTD_160OHM_GAIN, 6);
 }
@@ -4370,11 +6606,49 @@ static void ca0132_set_dsp_msr(struct hda_codec *codec, bool is96k)
 static bool ca0132_download_dsp_images(struct hda_codec *codec)
 {
 	bool dsp_loaded = false;
+	struct ca0132_spec *spec = codec->spec;
 	const struct dsp_image_seg *dsp_os_image;
 	const struct firmware *fw_entry;
-
-	if (request_firmware(&fw_entry, EFX_FILE, codec->card->dev) != 0)
-		return false;
+	/*
+	 * Alternate firmwares for different variants. The Recon3Di apparently
+	 * can use the default firmware, but I'll leave the option in case
+	 * it needs it again.
+	 */
+	switch (spec->quirk) {
+	case QUIRK_SBZ:
+		if (request_firmware(&fw_entry, SBZ_EFX_FILE,
+					codec->card->dev) != 0) {
+			codec_dbg(codec, "SBZ alt firmware not detected. ");
+			spec->alt_firmware_present = false;
+		} else {
+			codec_dbg(codec, "Sound Blaster Z firmware selected.");
+			spec->alt_firmware_present = true;
+		}
+		break;
+	case QUIRK_R3DI:
+		if (request_firmware(&fw_entry, R3DI_EFX_FILE,
+					codec->card->dev) != 0) {
+			codec_dbg(codec, "Recon3Di alt firmware not detected.");
+			spec->alt_firmware_present = false;
+		} else {
+			codec_dbg(codec, "Recon3Di firmware selected.");
+			spec->alt_firmware_present = true;
+		}
+		break;
+	default:
+		spec->alt_firmware_present = false;
+		break;
+	}
+	/*
+	 * Use default ctefx.bin if no alt firmware is detected, or if none
+	 * exists for your particular codec.
+	 */
+	if (!spec->alt_firmware_present) {
+		codec_dbg(codec, "Default firmware selected.");
+		if (request_firmware(&fw_entry, EFX_FILE,
+					codec->card->dev) != 0)
+			return false;
+	}
 
 	dsp_os_image = (struct dsp_image_seg *)(fw_entry->data);
 	if (dspload_image(codec, dsp_os_image, 0, 0, true, 0)) {
@@ -4402,13 +6676,17 @@ static void ca0132_download_dsp(struct hda_codec *codec)
 		return; /* don't retry failures */
 
 	chipio_enable_clocks(codec);
-	spec->dsp_state = DSP_DOWNLOADING;
-	if (!ca0132_download_dsp_images(codec))
-		spec->dsp_state = DSP_DOWNLOAD_FAILED;
-	else
-		spec->dsp_state = DSP_DOWNLOADED;
+	if (spec->dsp_state != DSP_DOWNLOADED) {
+		spec->dsp_state = DSP_DOWNLOADING;
 
-	if (spec->dsp_state == DSP_DOWNLOADED)
+		if (!ca0132_download_dsp_images(codec))
+			spec->dsp_state = DSP_DOWNLOAD_FAILED;
+		else
+			spec->dsp_state = DSP_DOWNLOADED;
+	}
+
+	/* For codecs using alt functions, this is already done earlier */
+	if (spec->dsp_state == DSP_DOWNLOADED && (!spec->use_alt_functions))
 		ca0132_set_dsp_msr(codec, true);
 }
 
@@ -4454,6 +6732,10 @@ static void ca0132_init_unsol(struct hda_codec *codec)
 					    amic_callback);
 	snd_hda_jack_detect_enable_callback(codec, UNSOL_TAG_DSP,
 					    ca0132_process_dsp_response);
+	/* Front headphone jack detection */
+	if (spec->use_alt_functions)
+		snd_hda_jack_detect_enable_callback(codec,
+			spec->unsol_tag_front_hp, hp_callback);
 }
 
 /*
@@ -4476,7 +6758,8 @@ static struct hda_verb ca0132_base_exit_verbs[] = {
 	{}
 };
 
-/* Other verbs tables.  Sends after DSP download. */
+/* Other verbs tables. Sends after DSP download. */
+
 static struct hda_verb ca0132_init_verbs0[] = {
 	/* chip init verbs */
 	{0x15, 0x70D, 0xF0},
@@ -4506,8 +6789,27 @@ static struct hda_verb ca0132_init_verbs0[] = {
 	{0x15, 0x546, 0xC9},
 	{0x15, 0x53B, 0xCE},
 	{0x15, 0x5E8, 0xC9},
-	{0x15, 0x717, 0x0D},
-	{0x15, 0x718, 0x20},
+	{}
+};
+
+/* Extra init verbs for SBZ */
+static struct hda_verb sbz_init_verbs[] = {
+	{0x15, 0x70D, 0x20},
+	{0x15, 0x70E, 0x19},
+	{0x15, 0x707, 0x00},
+	{0x15, 0x539, 0xCE},
+	{0x15, 0x546, 0xC9},
+	{0x15, 0x70D, 0xB7},
+	{0x15, 0x70E, 0x09},
+	{0x15, 0x707, 0x10},
+	{0x15, 0x70D, 0xAF},
+	{0x15, 0x70E, 0x09},
+	{0x15, 0x707, 0x01},
+	{0x15, 0x707, 0x05},
+	{0x15, 0x70D, 0x73},
+	{0x15, 0x70E, 0x09},
+	{0x15, 0x707, 0x14},
+	{0x15, 0x6FF, 0xC4},
 	{}
 };
 
@@ -4521,7 +6823,11 @@ static void ca0132_init_chip(struct hda_codec *codec)
 	mutex_init(&spec->chipio_mutex);
 
 	spec->cur_out_type = SPEAKER_OUT;
-	spec->cur_mic_type = DIGITAL_MIC;
+	if (!spec->use_alt_functions)
+		spec->cur_mic_type = DIGITAL_MIC;
+	else
+		spec->cur_mic_type = REAR_MIC;
+
 	spec->cur_mic_boost = 0;
 
 	for (i = 0; i < VNODES_COUNT; i++) {
@@ -4539,6 +6845,15 @@ static void ca0132_init_chip(struct hda_codec *codec)
 		on = (unsigned int)ca0132_effects[i].reqs[0];
 		spec->effects_switch[i] = on ? 1 : 0;
 	}
+	/*
+	 * Sets defaults for the effect slider controls, only for alternative
+	 * ca0132 codecs. Also sets x-bass crossover frequency to 80hz.
+	 */
+	if (spec->use_alt_controls) {
+		spec->xbass_xover_freq = 8;
+		for (i = 0; i < EFFECT_LEVEL_SLIDERS; i++)
+			spec->fx_ctl_val[i] = effect_slider_defaults[i];
+	}
 
 	spec->voicefx_val = 0;
 	spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID] = 1;
@@ -4549,6 +6864,120 @@ static void ca0132_init_chip(struct hda_codec *codec)
 #endif
 }
 
+/*
+ * Recon3Di exit specific commands.
+ */
+/* prevents popping noise on shutdown */
+static void r3di_gpio_shutdown(struct hda_codec *codec)
+{
+	snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA, 0x00);
+}
+
+/*
+ * Sound Blaster Z exit specific commands.
+ */
+static void sbz_region2_exit(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned int i;
+
+	for (i = 0; i < 4; i++)
+		writeb(0x0, spec->mem_base + 0x100);
+	for (i = 0; i < 8; i++)
+		writeb(0xb3, spec->mem_base + 0x304);
+	/*
+	 * I believe these are GPIO, with the right most hex digit being the
+	 * gpio pin, and the second digit being on or off. We see this more in
+	 * the input/output select functions.
+	 */
+	writew(0x0000, spec->mem_base + 0x320);
+	writew(0x0001, spec->mem_base + 0x320);
+	writew(0x0104, spec->mem_base + 0x320);
+	writew(0x0005, spec->mem_base + 0x320);
+	writew(0x0007, spec->mem_base + 0x320);
+}
+
+static void sbz_set_pin_ctl_default(struct hda_codec *codec)
+{
+	hda_nid_t pins[5] = {0x0B, 0x0C, 0x0E, 0x12, 0x13};
+	unsigned int i;
+
+	snd_hda_codec_write(codec, 0x11, 0,
+			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x40);
+
+	for (i = 0; i < 5; i++)
+		snd_hda_codec_write(codec, pins[i], 0,
+				AC_VERB_SET_PIN_WIDGET_CONTROL, 0x00);
+}
+
+static void sbz_clear_unsolicited(struct hda_codec *codec)
+{
+	hda_nid_t pins[7] = {0x0B, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13};
+	unsigned int i;
+
+	for (i = 0; i < 7; i++) {
+		snd_hda_codec_write(codec, pins[i], 0,
+				AC_VERB_SET_UNSOLICITED_ENABLE, 0x00);
+	}
+}
+
+/* On shutdown, sends commands in sets of three */
+static void sbz_gpio_shutdown_commands(struct hda_codec *codec, int dir,
+							int mask, int data)
+{
+	if (dir >= 0)
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_DIRECTION, dir);
+	if (mask >= 0)
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_MASK, mask);
+
+	if (data >= 0)
+		snd_hda_codec_write(codec, 0x01, 0,
+				AC_VERB_SET_GPIO_DATA, data);
+}
+
+static void sbz_exit_chip(struct hda_codec *codec)
+{
+	chipio_set_stream_control(codec, 0x03, 0);
+	chipio_set_stream_control(codec, 0x04, 0);
+
+	/* Mess with GPIO */
+	sbz_gpio_shutdown_commands(codec, 0x07, 0x07, -1);
+	sbz_gpio_shutdown_commands(codec, 0x07, 0x07, 0x05);
+	sbz_gpio_shutdown_commands(codec, 0x07, 0x07, 0x01);
+
+	chipio_set_stream_control(codec, 0x14, 0);
+	chipio_set_stream_control(codec, 0x0C, 0);
+
+	chipio_set_conn_rate(codec, 0x41, SR_192_000);
+	chipio_set_conn_rate(codec, 0x91, SR_192_000);
+
+	chipio_write(codec, 0x18a020, 0x00000083);
+
+	sbz_gpio_shutdown_commands(codec, 0x07, 0x07, 0x03);
+	sbz_gpio_shutdown_commands(codec, 0x07, 0x07, 0x07);
+	sbz_gpio_shutdown_commands(codec, 0x07, 0x07, 0x06);
+
+	chipio_set_stream_control(codec, 0x0C, 0);
+
+	chipio_set_control_param(codec, 0x0D, 0x24);
+
+	sbz_clear_unsolicited(codec);
+	sbz_set_pin_ctl_default(codec);
+
+	snd_hda_codec_write(codec, 0x0B, 0,
+		AC_VERB_SET_EAPD_BTLENABLE, 0x00);
+
+	if (dspload_is_loaded(codec))
+		dsp_reset(codec);
+
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+		VENDOR_CHIPIO_CT_EXTENSIONS_ENABLE, 0x00);
+
+	sbz_region2_exit(codec);
+}
+
 static void ca0132_exit_chip(struct hda_codec *codec)
 {
 	/* put any chip cleanup stuffs here. */
@@ -4557,28 +6986,264 @@ static void ca0132_exit_chip(struct hda_codec *codec)
 		dsp_reset(codec);
 }
 
+/*
+ * This fixes a problem that was hard to reproduce. Very rarely, I would
+ * boot up, and there would be no sound, but the DSP indicated it had loaded
+ * properly. I did a few memory dumps to see if anything was different, and
+ * there were a few areas of memory uninitialized with a1a2a3a4. This function
+ * checks if those areas are uninitialized, and if they are, it'll attempt to
+ * reload the card 3 times. Usually it fixes by the second.
+ */
+static void sbz_dsp_startup_check(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned int dsp_data_check[4];
+	unsigned int cur_address = 0x390;
+	unsigned int i;
+	unsigned int failure = 0;
+	unsigned int reload = 3;
+
+	if (spec->startup_check_entered)
+		return;
+
+	spec->startup_check_entered = true;
+
+	for (i = 0; i < 4; i++) {
+		chipio_read(codec, cur_address, &dsp_data_check[i]);
+		cur_address += 0x4;
+	}
+	for (i = 0; i < 4; i++) {
+		if (dsp_data_check[i] == 0xa1a2a3a4)
+			failure = 1;
+	}
+
+	codec_dbg(codec, "Startup Check: %d ", failure);
+	if (failure)
+		codec_info(codec, "DSP not initialized properly. Attempting to fix.");
+	/*
+	 * While the failure condition is true, and we haven't reached our
+	 * three reload limit, continue trying to reload the driver and
+	 * fix the issue.
+	 */
+	while (failure && (reload != 0)) {
+		codec_info(codec, "Reloading... Tries left: %d", reload);
+		sbz_exit_chip(codec);
+		spec->dsp_state = DSP_DOWNLOAD_INIT;
+		codec->patch_ops.init(codec);
+		failure = 0;
+		for (i = 0; i < 4; i++) {
+			chipio_read(codec, cur_address, &dsp_data_check[i]);
+			cur_address += 0x4;
+		}
+		for (i = 0; i < 4; i++) {
+			if (dsp_data_check[i] == 0xa1a2a3a4)
+				failure = 1;
+		}
+		reload--;
+	}
+
+	if (!failure && reload < 3)
+		codec_info(codec, "DSP fixed.");
+
+	if (!failure)
+		return;
+
+	codec_info(codec, "DSP failed to initialize properly. Either try a full shutdown or a suspend to clear the internal memory.");
+}
+
+/*
+ * This is for the extra volume verbs 0x797 (left) and 0x798 (right). These add
+ * extra precision for decibel values. If you had the dB value in floating point
+ * you would take the value after the decimal point, multiply by 64, and divide
+ * by 2. So for 8.59, it's (59 * 64) / 100. Useful if someone wanted to
+ * implement fixed point or floating point dB volumes. For now, I'll set them
+ * to 0 just incase a value has lingered from a boot into Windows.
+ */
+static void ca0132_alt_vol_setup(struct hda_codec *codec)
+{
+	snd_hda_codec_write(codec, 0x02, 0, 0x797, 0x00);
+	snd_hda_codec_write(codec, 0x02, 0, 0x798, 0x00);
+	snd_hda_codec_write(codec, 0x03, 0, 0x797, 0x00);
+	snd_hda_codec_write(codec, 0x03, 0, 0x798, 0x00);
+	snd_hda_codec_write(codec, 0x04, 0, 0x797, 0x00);
+	snd_hda_codec_write(codec, 0x04, 0, 0x798, 0x00);
+	snd_hda_codec_write(codec, 0x07, 0, 0x797, 0x00);
+	snd_hda_codec_write(codec, 0x07, 0, 0x798, 0x00);
+}
+
+/*
+ * Extra commands that don't really fit anywhere else.
+ */
+static void sbz_pre_dsp_setup(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+
+	writel(0x00820680, spec->mem_base + 0x01C);
+	writel(0x00820680, spec->mem_base + 0x01C);
+
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfc);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfd);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfe);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xff);
+
+	chipio_write(codec, 0x18b0a4, 0x000000c2);
+
+	snd_hda_codec_write(codec, 0x11, 0,
+			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x44);
+}
+
+/*
+ * Extra commands that don't really fit anywhere else.
+ */
+static void r3di_pre_dsp_setup(struct hda_codec *codec)
+{
+	chipio_write(codec, 0x18b0a4, 0x000000c2);
+
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_ADDRESS_LOW, 0x1E);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_ADDRESS_HIGH, 0x1C);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_DATA_WRITE, 0x5B);
+
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_ADDRESS_LOW, 0x20);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_ADDRESS_HIGH, 0x19);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_DATA_WRITE, 0x00);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_DATA_WRITE, 0x40);
+
+	snd_hda_codec_write(codec, 0x11, 0,
+			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x04);
+}
+
+
+/*
+ * These are sent before the DSP is downloaded. Not sure
+ * what they do, or if they're necessary. Could possibly
+ * be removed. Figure they're better to leave in.
+ */
+static void sbz_region2_startup(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+
+	writel(0x00000000, spec->mem_base + 0x400);
+	writel(0x00000000, spec->mem_base + 0x408);
+	writel(0x00000000, spec->mem_base + 0x40C);
+	writel(0x00880680, spec->mem_base + 0x01C);
+	writel(0x00000083, spec->mem_base + 0xC0C);
+	writel(0x00000030, spec->mem_base + 0xC00);
+	writel(0x00000000, spec->mem_base + 0xC04);
+	writel(0x00000003, spec->mem_base + 0xC0C);
+	writel(0x00000003, spec->mem_base + 0xC0C);
+	writel(0x00000003, spec->mem_base + 0xC0C);
+	writel(0x00000003, spec->mem_base + 0xC0C);
+	writel(0x000000C1, spec->mem_base + 0xC08);
+	writel(0x000000F1, spec->mem_base + 0xC08);
+	writel(0x00000001, spec->mem_base + 0xC08);
+	writel(0x000000C7, spec->mem_base + 0xC08);
+	writel(0x000000C1, spec->mem_base + 0xC08);
+	writel(0x00000080, spec->mem_base + 0xC04);
+}
+
+/*
+ * Extra init functions for alternative ca0132 codecs. Done
+ * here so they don't clutter up the main ca0132_init function
+ * anymore than they have to.
+ */
+static void ca0132_alt_init(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+
+	ca0132_alt_vol_setup(codec);
+
+	switch (spec->quirk) {
+	case QUIRK_SBZ:
+		codec_dbg(codec, "SBZ alt_init");
+		ca0132_gpio_init(codec);
+		sbz_pre_dsp_setup(codec);
+		snd_hda_sequence_write(codec, spec->chip_init_verbs);
+		snd_hda_sequence_write(codec, spec->sbz_init_verbs);
+		break;
+	case QUIRK_R3DI:
+		codec_dbg(codec, "R3DI alt_init");
+		ca0132_gpio_init(codec);
+		ca0132_gpio_setup(codec);
+		r3di_gpio_dsp_status_set(codec, R3DI_DSP_DOWNLOADING);
+		r3di_pre_dsp_setup(codec);
+		snd_hda_sequence_write(codec, spec->chip_init_verbs);
+		snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0, 0x6FF, 0xC4);
+		break;
+	}
+}
+
 static int ca0132_init(struct hda_codec *codec)
 {
 	struct ca0132_spec *spec = codec->spec;
 	struct auto_pin_cfg *cfg = &spec->autocfg;
 	int i;
+	bool dsp_loaded;
+
+	/*
+	 * If the DSP is already downloaded, and init has been entered again,
+	 * there's only two reasons for it. One, the codec has awaken from a
+	 * suspended state, and in that case dspload_is_loaded will return
+	 * false, and the init will be ran again. The other reason it gets
+	 * re entered is on startup for some reason it triggers a suspend and
+	 * resume state. In this case, it will check if the DSP is downloaded,
+	 * and not run the init function again. For codecs using alt_functions,
+	 * it will check if the DSP is loaded properly.
+	 */
+	if (spec->dsp_state == DSP_DOWNLOADED) {
+		dsp_loaded = dspload_is_loaded(codec);
+		if (!dsp_loaded) {
+			spec->dsp_reload = true;
+			spec->dsp_state = DSP_DOWNLOAD_INIT;
+		} else {
+			if (spec->quirk == QUIRK_SBZ)
+				sbz_dsp_startup_check(codec);
+			return 0;
+		}
+	}
 
 	if (spec->dsp_state != DSP_DOWNLOAD_FAILED)
 		spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->curr_chip_addx = INVALID_CHIP_ADDRESS;
 
+	if (spec->quirk == QUIRK_SBZ)
+		sbz_region2_startup(codec);
+
 	snd_hda_power_up_pm(codec);
 
 	ca0132_init_unsol(codec);
-
 	ca0132_init_params(codec);
 	ca0132_init_flags(codec);
+
 	snd_hda_sequence_write(codec, spec->base_init_verbs);
+
+	if (spec->quirk != QUIRK_NONE)
+		ca0132_alt_init(codec);
+
 	ca0132_download_dsp(codec);
+
 	ca0132_refresh_widget_caps(codec);
-	ca0132_setup_defaults(codec);
-	ca0132_init_analog_mic2(codec);
-	ca0132_init_dmic(codec);
+
+	if (spec->quirk == QUIRK_SBZ)
+		writew(0x0107, spec->mem_base + 0x320);
+
+	switch (spec->quirk) {
+	case QUIRK_R3DI:
+		r3di_setup_defaults(codec);
+		break;
+	case QUIRK_NONE:
+	case QUIRK_ALIENWARE:
+		ca0132_setup_defaults(codec);
+		ca0132_init_analog_mic2(codec);
+		ca0132_init_dmic(codec);
+		break;
+	}
 
 	for (i = 0; i < spec->num_outputs; i++)
 		init_output(codec, spec->out_pins[i], spec->dacs[0]);
@@ -4590,14 +7255,45 @@ static int ca0132_init(struct hda_codec *codec)
 
 	init_input(codec, cfg->dig_in_pin, spec->dig_in);
 
-	snd_hda_sequence_write(codec, spec->chip_init_verbs);
-	snd_hda_sequence_write(codec, spec->spec_init_verbs);
+	if (!spec->use_alt_functions) {
+		snd_hda_sequence_write(codec, spec->chip_init_verbs);
+		snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_PARAM_EX_ID_SET, 0x0D);
+		snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_PARAM_EX_VALUE_SET, 0x20);
+	}
 
-	ca0132_select_out(codec);
-	ca0132_select_mic(codec);
+	if (spec->quirk == QUIRK_SBZ)
+		ca0132_gpio_setup(codec);
+
+	snd_hda_sequence_write(codec, spec->spec_init_verbs);
+	switch (spec->quirk) {
+	case QUIRK_SBZ:
+		sbz_setup_defaults(codec);
+		ca0132_alt_select_out(codec);
+		ca0132_alt_select_in(codec);
+		break;
+	case QUIRK_R3DI:
+		ca0132_alt_select_out(codec);
+		ca0132_alt_select_in(codec);
+		break;
+	default:
+		ca0132_select_out(codec);
+		ca0132_select_mic(codec);
+		break;
+	}
 
 	snd_hda_jack_report_sync(codec);
 
+	/*
+	 * Re set the PlayEnhancement switch on a resume event, because the
+	 * controls will not be reloaded.
+	 */
+	if (spec->dsp_reload) {
+		spec->dsp_reload = false;
+		ca0132_pe_switch_set(codec);
+	}
+
 	snd_hda_power_down_pm(codec);
 
 	return 0;
@@ -4609,19 +7305,39 @@ static void ca0132_free(struct hda_codec *codec)
 
 	cancel_delayed_work_sync(&spec->unsol_hp_work);
 	snd_hda_power_up(codec);
-	snd_hda_sequence_write(codec, spec->base_exit_verbs);
-	ca0132_exit_chip(codec);
+	switch (spec->quirk) {
+	case QUIRK_SBZ:
+		sbz_exit_chip(codec);
+		break;
+	case QUIRK_R3DI:
+		r3di_gpio_shutdown(codec);
+		snd_hda_sequence_write(codec, spec->base_exit_verbs);
+		ca0132_exit_chip(codec);
+		break;
+	default:
+		snd_hda_sequence_write(codec, spec->base_exit_verbs);
+		ca0132_exit_chip(codec);
+		break;
+	}
 	snd_hda_power_down(codec);
+	if (spec->mem_base)
+		iounmap(spec->mem_base);
 	kfree(spec->spec_init_verbs);
 	kfree(codec->spec);
 }
 
+static void ca0132_reboot_notify(struct hda_codec *codec)
+{
+	codec->patch_ops.free(codec);
+}
+
 static const struct hda_codec_ops ca0132_patch_ops = {
 	.build_controls = ca0132_build_controls,
 	.build_pcms = ca0132_build_pcms,
 	.init = ca0132_init,
 	.free = ca0132_free,
 	.unsol_event = snd_hda_jack_unsol_event,
+	.reboot_notify = ca0132_reboot_notify,
 };
 
 static void ca0132_config(struct hda_codec *codec)
@@ -4635,9 +7351,14 @@ static void ca0132_config(struct hda_codec *codec)
 
 	spec->multiout.dac_nids = spec->dacs;
 	spec->multiout.num_dacs = 3;
-	spec->multiout.max_channels = 2;
 
-	if (spec->quirk == QUIRK_ALIENWARE) {
+	if (!spec->use_alt_functions)
+		spec->multiout.max_channels = 2;
+	else
+		spec->multiout.max_channels = 6;
+
+	switch (spec->quirk) {
+	case QUIRK_ALIENWARE:
 		codec_dbg(codec, "ca0132_config: QUIRK_ALIENWARE applied.\n");
 		snd_hda_apply_pincfgs(codec, alienware_pincfgs);
 
@@ -4657,7 +7378,71 @@ static void ca0132_config(struct hda_codec *codec)
 		spec->input_pins[2] = 0x13;
 		spec->shared_mic_nid = 0x7;
 		spec->unsol_tag_amic1 = 0x11;
-	} else {
+		break;
+	case QUIRK_SBZ:
+		codec_dbg(codec, "%s: QUIRK_SBZ applied.\n", __func__);
+		snd_hda_apply_pincfgs(codec, sbz_pincfgs);
+
+		spec->num_outputs = 2;
+		spec->out_pins[0] = 0x0B; /* Line out */
+		spec->out_pins[1] = 0x0F; /* Rear headphone out */
+		spec->out_pins[2] = 0x10; /* Front Headphone / Center/LFE*/
+		spec->out_pins[3] = 0x11; /* Rear surround */
+		spec->shared_out_nid = 0x2;
+		spec->unsol_tag_hp = spec->out_pins[1];
+		spec->unsol_tag_front_hp = spec->out_pins[2];
+
+		spec->adcs[0] = 0x7; /* Rear Mic / Line-in */
+		spec->adcs[1] = 0x8; /* Front Mic, but only if no DSP */
+		spec->adcs[2] = 0xa; /* what u hear */
+
+		spec->num_inputs = 2;
+		spec->input_pins[0] = 0x12; /* Rear Mic / Line-in */
+		spec->input_pins[1] = 0x13; /* What U Hear */
+		spec->shared_mic_nid = 0x7;
+		spec->unsol_tag_amic1 = spec->input_pins[0];
+
+		/* SPDIF I/O */
+		spec->dig_out = 0x05;
+		spec->multiout.dig_out_nid = spec->dig_out;
+		cfg->dig_out_pins[0] = 0x0c;
+		cfg->dig_outs = 1;
+		cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
+		spec->dig_in = 0x09;
+		cfg->dig_in_pin = 0x0e;
+		cfg->dig_in_type = HDA_PCM_TYPE_SPDIF;
+		break;
+	case QUIRK_R3DI:
+		codec_dbg(codec, "%s: QUIRK_R3DI applied.\n", __func__);
+		snd_hda_apply_pincfgs(codec, r3di_pincfgs);
+
+		spec->num_outputs = 2;
+		spec->out_pins[0] = 0x0B; /* Line out */
+		spec->out_pins[1] = 0x0F; /* Rear headphone out */
+		spec->out_pins[2] = 0x10; /* Front Headphone / Center/LFE*/
+		spec->out_pins[3] = 0x11; /* Rear surround */
+		spec->shared_out_nid = 0x2;
+		spec->unsol_tag_hp = spec->out_pins[1];
+		spec->unsol_tag_front_hp = spec->out_pins[2];
+
+		spec->adcs[0] = 0x07; /* Rear Mic / Line-in */
+		spec->adcs[1] = 0x08; /* Front Mic, but only if no DSP */
+		spec->adcs[2] = 0x0a; /* what u hear */
+
+		spec->num_inputs = 2;
+		spec->input_pins[0] = 0x12; /* Rear Mic / Line-in */
+		spec->input_pins[1] = 0x13; /* What U Hear */
+		spec->shared_mic_nid = 0x7;
+		spec->unsol_tag_amic1 = spec->input_pins[0];
+
+		/* SPDIF I/O */
+		spec->dig_out = 0x05;
+		spec->multiout.dig_out_nid = spec->dig_out;
+		cfg->dig_out_pins[0] = 0x0c;
+		cfg->dig_outs = 1;
+		cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
+		break;
+	default:
 		spec->num_outputs = 2;
 		spec->out_pins[0] = 0x0b; /* speaker out */
 		spec->out_pins[1] = 0x10; /* headphone out */
@@ -4684,6 +7469,7 @@ static void ca0132_config(struct hda_codec *codec)
 		spec->dig_in = 0x09;
 		cfg->dig_in_pin = 0x0e;
 		cfg->dig_in_type = HDA_PCM_TYPE_SPDIF;
+		break;
 	}
 }
 
@@ -4694,6 +7480,8 @@ static int ca0132_prepare_verbs(struct hda_codec *codec)
 	struct ca0132_spec *spec = codec->spec;
 
 	spec->chip_init_verbs = ca0132_init_verbs0;
+	if (spec->quirk == QUIRK_SBZ)
+		spec->sbz_init_verbs = sbz_init_verbs;
 	spec->spec_init_verbs = kzalloc(sizeof(struct hda_verb) * NUM_SPEC_VERBS, GFP_KERNEL);
 	if (!spec->spec_init_verbs)
 		return -ENOMEM;
@@ -4757,9 +7545,46 @@ static int patch_ca0132(struct hda_codec *codec)
 	else
 		spec->quirk = QUIRK_NONE;
 
+	/* Setup BAR Region 2 for Sound Blaster Z */
+	if (spec->quirk == QUIRK_SBZ) {
+		spec->mem_base = pci_iomap(codec->bus->pci, 2, 0xC20);
+		if (spec->mem_base == NULL) {
+			codec_warn(codec, "pci_iomap failed!");
+			codec_info(codec, "perhaps this is not an SBZ?");
+			spec->quirk = QUIRK_NONE;
+		}
+	}
+
 	spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->num_mixers = 1;
-	spec->mixers[0] = ca0132_mixer;
+
+	/* Set which mixers each quirk uses. */
+	switch (spec->quirk) {
+	case QUIRK_SBZ:
+		spec->mixers[0] = sbz_mixer;
+		snd_hda_codec_set_name(codec, "Sound Blaster Z");
+		break;
+	case QUIRK_R3DI:
+		spec->mixers[0] = r3di_mixer;
+		snd_hda_codec_set_name(codec, "Recon3Di");
+		break;
+	default:
+		spec->mixers[0] = ca0132_mixer;
+		break;
+	}
+
+	/* Setup whether or not to use alt functions/controls */
+	switch (spec->quirk) {
+	case QUIRK_SBZ:
+	case QUIRK_R3DI:
+		spec->use_alt_controls = true;
+		spec->use_alt_functions = true;
+		break;
+	default:
+		spec->use_alt_controls = false;
+		spec->use_alt_functions = false;
+		break;
+	}
 
 	spec->base_init_verbs = ca0132_base_init_verbs;
 	spec->base_exit_verbs = ca0132_base_exit_verbs;
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 5b4dbcec6de8..dbf9910c5269 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -588,6 +588,7 @@ static void cxt_fixup_olpc_xo(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
 	struct conexant_spec *spec = codec->spec;
+	struct snd_kcontrol_new *kctl;
 	int i;
 
 	if (action != HDA_FIXUP_ACT_PROBE)
@@ -606,9 +607,7 @@ static void cxt_fixup_olpc_xo(struct hda_codec *codec,
 	snd_hda_codec_set_pin_target(codec, 0x1a, PIN_VREF50);
 
 	/* override mic boost control */
-	for (i = 0; i < spec->gen.kctls.used; i++) {
-		struct snd_kcontrol_new *kctl =
-			snd_array_elem(&spec->gen.kctls, i);
+	snd_array_for_each(&spec->gen.kctls, i, kctl) {
 		if (!strcmp(kctl->name, "Mic Boost Volume")) {
 			kctl->put = olpc_xo_mic_boost_put;
 			break;
@@ -965,6 +964,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
 	SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
@@ -998,6 +998,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
 	{ .id = CXT_FIXUP_MUTE_LED_EAPD, .name = "mute-led-eapd" },
 	{ .id = CXT_FIXUP_HP_DOCK, .name = "hp-dock" },
 	{ .id = CXT_FIXUP_MUTE_LED_GPIO, .name = "mute-led-gpio" },
+	{ .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" },
 	{}
 };
 
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index b4f1b6e88305..8840daf9c6a3 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -510,7 +510,7 @@ static int eld_proc_new(struct hdmi_spec_per_pin *per_pin, int index)
 
 	snd_info_set_text_ops(entry, per_pin, print_eld_info);
 	entry->c.text.write = write_eld_info;
-	entry->mode |= S_IWUSR;
+	entry->mode |= 0200;
 	per_pin->proc_entry = entry;
 
 	return 0;
@@ -1383,6 +1383,8 @@ static void hdmi_pcm_setup_pin(struct hdmi_spec *spec,
 		pcm = get_pcm_rec(spec, per_pin->pcm_idx);
 	else
 		return;
+	if (!pcm->pcm)
+		return;
 	if (!test_bit(per_pin->pcm_idx, &spec->pcm_in_use))
 		return;
 
@@ -2151,8 +2153,13 @@ static int generic_hdmi_build_controls(struct hda_codec *codec)
 	int dev, err;
 	int pin_idx, pcm_idx;
 
-
 	for (pcm_idx = 0; pcm_idx < spec->pcm_used; pcm_idx++) {
+		if (!get_pcm_rec(spec, pcm_idx)->pcm) {
+			/* no PCM: mark this for skipping permanently */
+			set_bit(pcm_idx, &spec->pcm_bitmap);
+			continue;
+		}
+
 		err = generic_hdmi_build_jack(codec, pcm_idx);
 		if (err < 0)
 			return err;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index aef1f52db7d9..d64dcb9a4c99 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -331,6 +331,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 		/* fallthrough */
 	case 0x10ec0215:
 	case 0x10ec0233:
+	case 0x10ec0235:
 	case 0x10ec0236:
 	case 0x10ec0255:
 	case 0x10ec0256:
@@ -2362,6 +2363,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
 	SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),
@@ -2828,6 +2830,7 @@ static int find_ext_mic_pin(struct hda_codec *codec);
 
 static void alc286_shutup(struct hda_codec *codec)
 {
+	const struct hda_pincfg *pin;
 	int i;
 	int mic_pin = find_ext_mic_pin(codec);
 	/* don't shut up pins when unloading the driver; otherwise it breaks
@@ -2835,8 +2838,7 @@ static void alc286_shutup(struct hda_codec *codec)
 	 */
 	if (codec->bus->shutdown)
 		return;
-	for (i = 0; i < codec->init_pins.used; i++) {
-		struct hda_pincfg *pin = snd_array_elem(&codec->init_pins, i);
+	snd_array_for_each(&codec->init_pins, i, pin) {
 		/* use read here for syncing after issuing each verb */
 		if (pin->nid != mic_pin)
 			snd_hda_codec_read(codec, pin->nid, 0,
@@ -3651,30 +3653,37 @@ static void alc269_fixup_hp_mute_led(struct hda_codec *codec,
 	}
 }
 
-static void alc269_fixup_hp_mute_led_mic1(struct hda_codec *codec,
-				const struct hda_fixup *fix, int action)
+static void alc269_fixup_hp_mute_led_micx(struct hda_codec *codec,
+					  const struct hda_fixup *fix,
+					  int action, hda_nid_t pin)
 {
 	struct alc_spec *spec = codec->spec;
+
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->mute_led_polarity = 0;
-		spec->mute_led_nid = 0x18;
+		spec->mute_led_nid = pin;
 		spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
 		spec->gen.vmaster_mute_enum = 1;
 		codec->power_filter = led_power_filter;
 	}
 }
 
+static void alc269_fixup_hp_mute_led_mic1(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	alc269_fixup_hp_mute_led_micx(codec, fix, action, 0x18);
+}
+
 static void alc269_fixup_hp_mute_led_mic2(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
-	struct alc_spec *spec = codec->spec;
-	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->mute_led_polarity = 0;
-		spec->mute_led_nid = 0x19;
-		spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
-		spec->gen.vmaster_mute_enum = 1;
-		codec->power_filter = led_power_filter;
-	}
+	alc269_fixup_hp_mute_led_micx(codec, fix, action, 0x19);
+}
+
+static void alc269_fixup_hp_mute_led_mic3(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	alc269_fixup_hp_mute_led_micx(codec, fix, action, 0x1b);
 }
 
 /* update LED status via GPIO */
@@ -3831,7 +3840,7 @@ static void alc280_fixup_hp_gpio4(struct hda_codec *codec,
 	}
 }
 
-#if IS_REACHABLE(INPUT)
+#if IS_REACHABLE(CONFIG_INPUT)
 static void gpio2_mic_hotkey_event(struct hda_codec *codec,
 				   struct hda_jack_callback *event)
 {
@@ -5385,6 +5394,9 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec,
 /* for dell wmi mic mute led */
 #include "dell_wmi_helper.c"
 
+/* for alc295_fixup_hp_top_speakers */
+#include "hp_x360_helper.c"
+
 enum {
 	ALC269_FIXUP_SONY_VAIO,
 	ALC275_FIXUP_SONY_VAIO_GPIO2,
@@ -5411,6 +5423,7 @@ enum {
 	ALC269_FIXUP_HP_MUTE_LED,
 	ALC269_FIXUP_HP_MUTE_LED_MIC1,
 	ALC269_FIXUP_HP_MUTE_LED_MIC2,
+	ALC269_FIXUP_HP_MUTE_LED_MIC3,
 	ALC269_FIXUP_HP_GPIO_LED,
 	ALC269_FIXUP_HP_GPIO_MIC1_LED,
 	ALC269_FIXUP_HP_LINE1_MIC1_LED,
@@ -5504,6 +5517,7 @@ enum {
 	ALC298_FIXUP_TPT470_DOCK,
 	ALC255_FIXUP_DUMMY_LINEOUT_VERB,
 	ALC255_FIXUP_DELL_HEADSET_MIC,
+	ALC295_FIXUP_HP_X360,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -5670,6 +5684,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_hp_mute_led_mic2,
 	},
+	[ALC269_FIXUP_HP_MUTE_LED_MIC3] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_hp_mute_led_mic3,
+	},
 	[ALC269_FIXUP_HP_GPIO_LED] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_hp_gpio_led,
@@ -6370,7 +6388,15 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */
 			{ }
 		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC
 	},
+	[ALC295_FIXUP_HP_X360] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc295_fixup_hp_top_speakers,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HP_MUTE_LED_MIC3
+	}
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -6490,6 +6516,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC),
+	SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360),
 	SND_PCI_QUIRK(0x103c, 0x82bf, "HP", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x82c0, "HP", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
@@ -6573,8 +6600,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+	SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+	SND_PCI_QUIRK(0x17aa, 0x3138, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
-	SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
@@ -6746,6 +6774,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x1b, 0x01111010},
 		{0x1e, 0x01451130},
 		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
+		{0x12, 0x90a60140},
+		{0x14, 0x90170110},
+		{0x19, 0x02a11030},
+		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60140},
 		{0x14, 0x90170110},
@@ -7157,8 +7190,11 @@ static int patch_alc269(struct hda_codec *codec)
 	case 0x10ec0298:
 		spec->codec_variant = ALC269_TYPE_ALC298;
 		break;
+	case 0x10ec0235:
 	case 0x10ec0255:
 		spec->codec_variant = ALC269_TYPE_ALC255;
+		spec->shutup = alc256_shutup;
+		spec->init_hook = alc256_init;
 		break;
 	case 0x10ec0236:
 	case 0x10ec0256:
diff --git a/sound/pci/ice1712/pontis.c b/sound/pci/ice1712/pontis.c
index 5101f40f6fbd..93b8cfc6636f 100644
--- a/sound/pci/ice1712/pontis.c
+++ b/sound/pci/ice1712/pontis.c
@@ -662,7 +662,7 @@ static void wm_proc_init(struct snd_ice1712 *ice)
 	struct snd_info_entry *entry;
 	if (! snd_card_proc_new(ice->card, "wm_codec", &entry)) {
 		snd_info_set_text_ops(entry, ice, wm_proc_regs_read);
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 		entry->c.text.write = wm_proc_regs_write;
 	}
 }
diff --git a/sound/pci/ice1712/prodigy_hifi.c b/sound/pci/ice1712/prodigy_hifi.c
index 8dabd4d0211d..d7366ade5a25 100644
--- a/sound/pci/ice1712/prodigy_hifi.c
+++ b/sound/pci/ice1712/prodigy_hifi.c
@@ -926,7 +926,7 @@ static void wm_proc_init(struct snd_ice1712 *ice)
 	struct snd_info_entry *entry;
 	if (!snd_card_proc_new(ice->card, "wm_codec", &entry)) {
 		snd_info_set_text_ops(entry, ice, wm_proc_regs_read);
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 		entry->c.text.write = wm_proc_regs_write;
 	}
 }
diff --git a/sound/pci/lola/lola_proc.c b/sound/pci/lola/lola_proc.c
index c241dc06dd92..904e3c4f4dfe 100644
--- a/sound/pci/lola/lola_proc.c
+++ b/sound/pci/lola/lola_proc.c
@@ -214,7 +214,7 @@ void lola_proc_debug_new(struct lola *chip)
 		snd_info_set_text_ops(entry, chip, lola_proc_codec_read);
 	if (!snd_card_proc_new(chip->card, "codec_rw", &entry)) {
 		snd_info_set_text_ops(entry, chip, lola_proc_codec_rw_read);
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 		entry->c.text.write = lola_proc_codec_rw_write;
 	}
 	if (!snd_card_proc_new(chip->card, "regs", &entry))
diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c
index 4ca12665ff73..81af21ac1439 100644
--- a/sound/pci/oxygen/oxygen_mixer.c
+++ b/sound/pci/oxygen/oxygen_mixer.c
@@ -1052,10 +1052,10 @@ static int add_controls(struct oxygen *chip,
 		[CONTROL_CD_CAPTURE_SWITCH] = "CD Capture Switch",
 		[CONTROL_AUX_CAPTURE_SWITCH] = "Aux Capture Switch",
 	};
-	unsigned int i, j;
+	unsigned int i;
 	struct snd_kcontrol_new template;
 	struct snd_kcontrol *ctl;
-	int err;
+	int j, err;
 
 	for (i = 0; i < count; ++i) {
 		template = controls[i];
@@ -1086,11 +1086,11 @@ static int add_controls(struct oxygen *chip,
 		err = snd_ctl_add(chip->card, ctl);
 		if (err < 0)
 			return err;
-		for (j = 0; j < CONTROL_COUNT; ++j)
-			if (!strcmp(ctl->id.name, known_ctl_names[j])) {
-				chip->controls[j] = ctl;
-				ctl->private_free = oxygen_any_ctl_free;
-			}
+		j = match_string(known_ctl_names, CONTROL_COUNT, ctl->id.name);
+		if (j >= 0) {
+			chip->controls[j] = ctl;
+			ctl->private_free = oxygen_any_ctl_free;
+		}
 	}
 	return 0;
 }
diff --git a/sound/pci/pcxhr/pcxhr.c b/sound/pci/pcxhr/pcxhr.c
index f9ae72f28ddc..e57da4036231 100644
--- a/sound/pci/pcxhr/pcxhr.c
+++ b/sound/pci/pcxhr/pcxhr.c
@@ -1465,7 +1465,7 @@ static void pcxhr_proc_init(struct snd_pcxhr *chip)
 	    !snd_card_proc_new(chip->card, "gpio", &entry)) {
 		snd_info_set_text_ops(entry, chip, pcxhr_proc_gpio_read);
 		entry->c.text.write = pcxhr_proc_gpo_write;
-		entry->mode |= S_IWUSR;
+		entry->mode |= 0200;
 	}
 	if (!snd_card_proc_new(chip->card, "ltc", &entry))
 		snd_info_set_text_ops(entry, chip, pcxhr_proc_ltc);
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 4c59983158e0..11b5b5e0e058 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -137,6 +137,7 @@
 #include <linux/pci.h>
 #include <linux/math64.h>
 #include <linux/io.h>
+#include <linux/nospec.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
@@ -5698,40 +5699,43 @@ static int snd_hdspm_channel_info(struct snd_pcm_substream *substream,
 		struct snd_pcm_channel_info *info)
 {
 	struct hdspm *hdspm = snd_pcm_substream_chip(substream);
+	unsigned int channel = info->channel;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		if (snd_BUG_ON(info->channel >= hdspm->max_channels_out)) {
+		if (snd_BUG_ON(channel >= hdspm->max_channels_out)) {
 			dev_info(hdspm->card->dev,
 				 "snd_hdspm_channel_info: output channel out of range (%d)\n",
-				 info->channel);
+				 channel);
 			return -EINVAL;
 		}
 
-		if (hdspm->channel_map_out[info->channel] < 0) {
+		channel = array_index_nospec(channel, hdspm->max_channels_out);
+		if (hdspm->channel_map_out[channel] < 0) {
 			dev_info(hdspm->card->dev,
 				 "snd_hdspm_channel_info: output channel %d mapped out\n",
-				 info->channel);
+				 channel);
 			return -EINVAL;
 		}
 
-		info->offset = hdspm->channel_map_out[info->channel] *
+		info->offset = hdspm->channel_map_out[channel] *
 			HDSPM_CHANNEL_BUFFER_BYTES;
 	} else {
-		if (snd_BUG_ON(info->channel >= hdspm->max_channels_in)) {
+		if (snd_BUG_ON(channel >= hdspm->max_channels_in)) {
 			dev_info(hdspm->card->dev,
 				 "snd_hdspm_channel_info: input channel out of range (%d)\n",
-				 info->channel);
+				 channel);
 			return -EINVAL;
 		}
 
-		if (hdspm->channel_map_in[info->channel] < 0) {
+		channel = array_index_nospec(channel, hdspm->max_channels_in);
+		if (hdspm->channel_map_in[channel] < 0) {
 			dev_info(hdspm->card->dev,
 				 "snd_hdspm_channel_info: input channel %d mapped out\n",
-				 info->channel);
+				 channel);
 			return -EINVAL;
 		}
 
-		info->offset = hdspm->channel_map_in[info->channel] *
+		info->offset = hdspm->channel_map_in[channel] *
 			HDSPM_CHANNEL_BUFFER_BYTES;
 	}
 
diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c
index df648b1d9217..edd765e22377 100644
--- a/sound/pci/rme9652/rme9652.c
+++ b/sound/pci/rme9652/rme9652.c
@@ -26,6 +26,7 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/nospec.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
@@ -2071,9 +2072,10 @@ static int snd_rme9652_channel_info(struct snd_pcm_substream *substream,
 	if (snd_BUG_ON(info->channel >= RME9652_NCHANNELS))
 		return -EINVAL;
 
-	if ((chn = rme9652->channel_map[info->channel]) < 0) {
+	chn = rme9652->channel_map[array_index_nospec(info->channel,
+						      RME9652_NCHANNELS)];
+	if (chn < 0)
 		return -EINVAL;
-	}
 
 	info->offset = chn * RME9652_CHANNEL_BUFFER_BYTES;
 	info->first = 0;
diff --git a/sound/soc/Makefile b/sound/soc/Makefile
index 8d92492183d2..06389a5385d7 100644
--- a/sound/soc/Makefile
+++ b/sound/soc/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-snd-soc-core-objs := soc-core.o soc-dapm.o soc-jack.o soc-cache.o soc-utils.o
+snd-soc-core-objs := soc-core.o soc-dapm.o soc-jack.o soc-utils.o
 snd-soc-core-objs += soc-pcm.o soc-io.o soc-devres.o soc-ops.o
 snd-soc-core-$(CONFIG_SND_SOC_COMPRESS) += soc-compress.o
 
diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c
index b205c782e494..ccddc6650b9c 100644
--- a/sound/soc/amd/acp-da7219-max98357a.c
+++ b/sound/soc/amd/acp-da7219-max98357a.c
@@ -33,17 +33,19 @@
 #include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/i2c.h>
+#include <linux/input.h>
 #include <linux/acpi.h>
 
+#include "acp.h"
 #include "../codecs/da7219.h"
 #include "../codecs/da7219-aad.h"
 
-#define CZ_PLAT_CLK 24000000
-#define MCLK_RATE 24576000
+#define CZ_PLAT_CLK 25000000
 #define DUAL_CHANNEL		2
 
 static struct snd_soc_jack cz_jack;
-struct clk *da7219_dai_clk;
+static struct clk *da7219_dai_clk;
+extern int bt_uart_enable;
 
 static int cz_da7219_init(struct snd_soc_pcm_runtime *rtd)
 {
@@ -62,7 +64,7 @@ static int cz_da7219_init(struct snd_soc_pcm_runtime *rtd)
 	}
 
 	ret = snd_soc_dai_set_pll(codec_dai, 0, DA7219_SYSCLK_PLL,
-				  CZ_PLAT_CLK, MCLK_RATE);
+				  CZ_PLAT_CLK, DA7219_PLL_FREQ_OUT_98304);
 	if (ret < 0) {
 		dev_err(rtd->dev, "can't set codec pll: %d\n", ret);
 		return ret;
@@ -80,13 +82,17 @@ static int cz_da7219_init(struct snd_soc_pcm_runtime *rtd)
 		return ret;
 	}
 
+	snd_jack_set_key(cz_jack.jack, SND_JACK_BTN_0, KEY_PLAYPAUSE);
+	snd_jack_set_key(cz_jack.jack, SND_JACK_BTN_1, KEY_VOLUMEUP);
+	snd_jack_set_key(cz_jack.jack, SND_JACK_BTN_2, KEY_VOLUMEDOWN);
+	snd_jack_set_key(cz_jack.jack, SND_JACK_BTN_3, KEY_VOICECOMMAND);
+
 	da7219_aad_jack_det(component, &cz_jack);
 
 	return 0;
 }
 
-static int cz_da7219_hw_params(struct snd_pcm_substream *substream,
-			     struct snd_pcm_hw_params *params)
+static int da7219_clk_enable(struct snd_pcm_substream *substream)
 {
 	int ret = 0;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -100,11 +106,9 @@ static int cz_da7219_hw_params(struct snd_pcm_substream *substream,
 	return ret;
 }
 
-static int cz_da7219_hw_free(struct snd_pcm_substream *substream)
+static void da7219_clk_disable(void)
 {
 	clk_disable_unprepare(da7219_dai_clk);
-
-	return 0;
 }
 
 static const unsigned int channels[] = {
@@ -127,9 +131,12 @@ static const struct snd_pcm_hw_constraint_list constraints_channels = {
 	.mask = 0,
 };
 
-static int cz_fe_startup(struct snd_pcm_substream *substream)
+static int cz_da7219_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
 
 	/*
 	 * On this platform for PCM device we support stereo
@@ -141,23 +148,58 @@ static int cz_fe_startup(struct snd_pcm_substream *substream)
 	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
 				   &constraints_rates);
 
-	return 0;
+	machine->i2s_instance = I2S_BT_INSTANCE;
+	return da7219_clk_enable(substream);
+}
+
+static void cz_da7219_shutdown(struct snd_pcm_substream *substream)
+{
+	da7219_clk_disable();
+}
+
+static int cz_max_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
+
+	machine->i2s_instance = I2S_SP_INSTANCE;
+	return da7219_clk_enable(substream);
+}
+
+static void cz_max_shutdown(struct snd_pcm_substream *substream)
+{
+	da7219_clk_disable();
+}
+
+static int cz_dmic_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
+
+	machine->i2s_instance = I2S_SP_INSTANCE;
+	return da7219_clk_enable(substream);
+}
+
+static void cz_dmic_shutdown(struct snd_pcm_substream *substream)
+{
+	da7219_clk_disable();
 }
 
-static struct snd_soc_ops cz_da7219_cap_ops = {
-	.hw_params = cz_da7219_hw_params,
-	.hw_free = cz_da7219_hw_free,
-	.startup = cz_fe_startup,
+static const struct snd_soc_ops cz_da7219_cap_ops = {
+	.startup = cz_da7219_startup,
+	.shutdown = cz_da7219_shutdown,
 };
 
-static struct snd_soc_ops cz_max_play_ops = {
-	.hw_params = cz_da7219_hw_params,
-	.hw_free = cz_da7219_hw_free,
+static const struct snd_soc_ops cz_max_play_ops = {
+	.startup = cz_max_startup,
+	.shutdown = cz_max_shutdown,
 };
 
-static struct snd_soc_ops cz_dmic_cap_ops = {
-	.hw_params = cz_da7219_hw_params,
-	.hw_free = cz_da7219_hw_free,
+static const struct snd_soc_ops cz_dmic_cap_ops = {
+	.startup = cz_dmic_startup,
+	.shutdown = cz_dmic_shutdown,
 };
 
 static struct snd_soc_dai_link cz_dai_7219_98357[] = {
@@ -240,10 +282,16 @@ static int cz_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct snd_soc_card *card;
+	struct acp_platform_info *machine;
 
+	machine = devm_kzalloc(&pdev->dev, sizeof(struct acp_platform_info),
+			       GFP_KERNEL);
+	if (!machine)
+		return -ENOMEM;
 	card = &cz_card;
 	cz_card.dev = &pdev->dev;
 	platform_set_drvdata(pdev, card);
+	snd_soc_card_set_drvdata(card, machine);
 	ret = devm_snd_soc_register_card(&pdev->dev, &cz_card);
 	if (ret) {
 		dev_err(&pdev->dev,
@@ -251,6 +299,8 @@ static int cz_probe(struct platform_device *pdev)
 				cz_card.name, ret);
 		return ret;
 	}
+	bt_uart_enable = !device_property_read_bool(&pdev->dev,
+						    "bt-pad-enable");
 	return 0;
 }
 
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 540088d317f2..77203841c535 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -37,12 +37,14 @@
 #define MAX_BUFFER (PLAYBACK_MAX_PERIOD_SIZE * PLAYBACK_MAX_NUM_PERIODS)
 #define MIN_BUFFER MAX_BUFFER
 
-#define ST_PLAYBACK_MAX_PERIOD_SIZE 8192
+#define ST_PLAYBACK_MAX_PERIOD_SIZE 4096
 #define ST_CAPTURE_MAX_PERIOD_SIZE  ST_PLAYBACK_MAX_PERIOD_SIZE
 #define ST_MAX_BUFFER (ST_PLAYBACK_MAX_PERIOD_SIZE * PLAYBACK_MAX_NUM_PERIODS)
 #define ST_MIN_BUFFER ST_MAX_BUFFER
 
 #define DRV_NAME "acp_audio_dma"
+bool bt_uart_enable = true;
+EXPORT_SYMBOL(bt_uart_enable);
 
 static const struct snd_pcm_hardware acp_pcm_hardware_playback = {
 	.info = SNDRV_PCM_INFO_INTERLEAVED |
@@ -130,7 +132,8 @@ static void acp_reg_write(u32 val, void __iomem *acp_mmio, u32 reg)
 	writel(val, acp_mmio + (reg * 4));
 }
 
-/* Configure a given dma channel parameters - enable/disable,
+/*
+ * Configure a given dma channel parameters - enable/disable,
  * number of descriptors, priority
  */
 static void config_acp_dma_channel(void __iomem *acp_mmio, u8 ch_num,
@@ -149,11 +152,12 @@ static void config_acp_dma_channel(void __iomem *acp_mmio, u8 ch_num,
 			& dscr_strt_idx),
 			acp_mmio, mmACP_DMA_DSCR_STRT_IDX_0 + ch_num);
 
-	/* program a DMA channel with the number of descriptors to be
+	/*
+	 * program a DMA channel with the number of descriptors to be
 	 * processed in the transfer
-	*/
+	 */
 	acp_reg_write(ACP_DMA_DSCR_CNT_0__DMAChDscrCnt_MASK & num_dscrs,
-		acp_mmio, mmACP_DMA_DSCR_CNT_0 + ch_num);
+		      acp_mmio, mmACP_DMA_DSCR_CNT_0 + ch_num);
 
 	/* set DMA channel priority */
 	acp_reg_write(priority_level, acp_mmio, mmACP_DMA_PRIO_0 + ch_num);
@@ -180,13 +184,15 @@ static void config_dma_descriptor_in_sram(void __iomem *acp_mmio,
 	acp_reg_write(descr_info->xfer_val, acp_mmio, mmACP_SRBM_Targ_Idx_Data);
 }
 
-/* Initialize the DMA descriptor information for transfer between
+/*
+ * Initialize the DMA descriptor information for transfer between
  * system memory <-> ACP SRAM
  */
 static void set_acp_sysmem_dma_descriptors(void __iomem *acp_mmio,
-					u32 size, int direction, u32 pte_offset,
-					u16 ch, u32 sram_bank,
-					u16 dma_dscr_idx, u32 asic_type)
+					   u32 size, int direction,
+					   u32 pte_offset, u16 ch,
+					   u32 sram_bank, u16 dma_dscr_idx,
+					   u32 asic_type)
 {
 	u16 i;
 	acp_dma_dscr_transfer_t dmadscr[NUM_DSCRS_PER_CHANNEL];
@@ -195,58 +201,58 @@ static void set_acp_sysmem_dma_descriptors(void __iomem *acp_mmio,
 		dmadscr[i].xfer_val = 0;
 		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
 			dma_dscr_idx = dma_dscr_idx + i;
-			dmadscr[i].dest = sram_bank + (i * (size/2));
+			dmadscr[i].dest = sram_bank + (i * (size / 2));
 			dmadscr[i].src = ACP_INTERNAL_APERTURE_WINDOW_0_ADDRESS
-				+ (pte_offset * SZ_4K) + (i * (size/2));
+				+ (pte_offset * SZ_4K) + (i * (size / 2));
 			switch (asic_type) {
 			case CHIP_STONEY:
 				dmadscr[i].xfer_val |=
-				(ACP_DMA_ATTRIBUTES_DAGB_GARLIC_TO_SHAREDMEM  << 16) |
+				(ACP_DMA_ATTR_DAGB_GARLIC_TO_SHAREDMEM  << 16) |
 				(size / 2);
 				break;
 			default:
 				dmadscr[i].xfer_val |=
-				(ACP_DMA_ATTRIBUTES_DAGB_ONION_TO_SHAREDMEM  << 16) |
+				(ACP_DMA_ATTR_DAGB_ONION_TO_SHAREDMEM  << 16) |
 				(size / 2);
 			}
 		} else {
 			dma_dscr_idx = dma_dscr_idx + i;
-			dmadscr[i].src = sram_bank + (i * (size/2));
+			dmadscr[i].src = sram_bank + (i * (size / 2));
 			dmadscr[i].dest =
 			ACP_INTERNAL_APERTURE_WINDOW_0_ADDRESS +
-			(pte_offset * SZ_4K) + (i * (size/2));
+			(pte_offset * SZ_4K) + (i * (size / 2));
 			switch (asic_type) {
 			case CHIP_STONEY:
 				dmadscr[i].xfer_val |=
 				BIT(22) |
-				(ACP_DMA_ATTRIBUTES_SHARED_MEM_TO_DAGB_GARLIC << 16) |
+				(ACP_DMA_ATTR_SHARED_MEM_TO_DAGB_GARLIC << 16) |
 				(size / 2);
 				break;
 			default:
 				dmadscr[i].xfer_val |=
 				BIT(22) |
-				(ACP_DMA_ATTRIBUTES_SHAREDMEM_TO_DAGB_ONION << 16) |
+				(ACP_DMA_ATTR_SHAREDMEM_TO_DAGB_ONION << 16) |
 				(size / 2);
 			}
 		}
 		config_dma_descriptor_in_sram(acp_mmio, dma_dscr_idx,
-						&dmadscr[i]);
+					      &dmadscr[i]);
 	}
 	config_acp_dma_channel(acp_mmio, ch,
-				dma_dscr_idx - 1,
-				NUM_DSCRS_PER_CHANNEL,
-				ACP_DMA_PRIORITY_LEVEL_NORMAL);
+			       dma_dscr_idx - 1,
+			       NUM_DSCRS_PER_CHANNEL,
+			       ACP_DMA_PRIORITY_LEVEL_NORMAL);
 }
 
-/* Initialize the DMA descriptor information for transfer between
+/*
+ * Initialize the DMA descriptor information for transfer between
  * ACP SRAM <-> I2S
  */
 static void set_acp_to_i2s_dma_descriptors(void __iomem *acp_mmio, u32 size,
-						int direction, u32 sram_bank,
-						u16 destination, u16 ch,
-						u16 dma_dscr_idx, u32 asic_type)
+					   int direction, u32 sram_bank,
+					   u16 destination, u16 ch,
+					   u16 dma_dscr_idx, u32 asic_type)
 {
-
 	u16 i;
 	acp_dma_dscr_transfer_t dmadscr[NUM_DSCRS_PER_CHANNEL];
 
@@ -254,7 +260,7 @@ static void set_acp_to_i2s_dma_descriptors(void __iomem *acp_mmio, u32 size,
 		dmadscr[i].xfer_val = 0;
 		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
 			dma_dscr_idx = dma_dscr_idx + i;
-			dmadscr[i].src = sram_bank  + (i * (size/2));
+			dmadscr[i].src = sram_bank  + (i * (size / 2));
 			/* dmadscr[i].dest is unused by hardware. */
 			dmadscr[i].dest = 0;
 			dmadscr[i].xfer_val |= BIT(22) | (destination << 16) |
@@ -269,12 +275,12 @@ static void set_acp_to_i2s_dma_descriptors(void __iomem *acp_mmio, u32 size,
 				(destination << 16) | (size / 2);
 		}
 		config_dma_descriptor_in_sram(acp_mmio, dma_dscr_idx,
-						&dmadscr[i]);
+					      &dmadscr[i]);
 	}
 	/* Configure the DMA channel with the above descriptore */
 	config_acp_dma_channel(acp_mmio, ch, dma_dscr_idx - 1,
-				NUM_DSCRS_PER_CHANNEL,
-				ACP_DMA_PRIORITY_LEVEL_NORMAL);
+			       NUM_DSCRS_PER_CHANNEL,
+			       ACP_DMA_PRIORITY_LEVEL_NORMAL);
 }
 
 /* Create page table entries in ACP SRAM for the allocated memory */
@@ -291,7 +297,7 @@ static void acp_pte_config(void __iomem *acp_mmio, struct page *pg,
 	for (page_idx = 0; page_idx < (num_of_pages); page_idx++) {
 		/* Load the low address of page int ACP SRAM through SRBM */
 		acp_reg_write((offset + (page_idx * 8)),
-			acp_mmio, mmACP_SRBM_Targ_Idx_Addr);
+			      acp_mmio, mmACP_SRBM_Targ_Idx_Addr);
 		addr = page_to_phys(pg);
 
 		low = lower_32_bits(addr);
@@ -301,7 +307,7 @@ static void acp_pte_config(void __iomem *acp_mmio, struct page *pg,
 
 		/* Load the High address of page int ACP SRAM through SRBM */
 		acp_reg_write((offset + (page_idx * 8) + 4),
-			acp_mmio, mmACP_SRBM_Targ_Idx_Addr);
+			      acp_mmio, mmACP_SRBM_Targ_Idx_Addr);
 
 		/* page enable in ACP */
 		high |= BIT(31);
@@ -313,59 +319,25 @@ static void acp_pte_config(void __iomem *acp_mmio, struct page *pg,
 }
 
 static void config_acp_dma(void __iomem *acp_mmio,
-			struct audio_substream_data *audio_config,
-			u32 asic_type)
+			   struct audio_substream_data *rtd,
+			   u32 asic_type)
 {
-	u32 pte_offset, sram_bank;
-	u16 ch1, ch2, destination, dma_dscr_idx;
-
-	if (audio_config->direction == SNDRV_PCM_STREAM_PLAYBACK) {
-		pte_offset = ACP_PLAYBACK_PTE_OFFSET;
-		ch1 = SYSRAM_TO_ACP_CH_NUM;
-		ch2 = ACP_TO_I2S_DMA_CH_NUM;
-		sram_bank = ACP_SHARED_RAM_BANK_1_ADDRESS;
-		destination = TO_ACP_I2S_1;
-
-	} else {
-		pte_offset = ACP_CAPTURE_PTE_OFFSET;
-		ch1 = SYSRAM_TO_ACP_CH_NUM;
-		ch2 = ACP_TO_I2S_DMA_CH_NUM;
-		switch (asic_type) {
-		case CHIP_STONEY:
-			sram_bank = ACP_SHARED_RAM_BANK_3_ADDRESS;
-			break;
-		default:
-			sram_bank = ACP_SHARED_RAM_BANK_5_ADDRESS;
-		}
-		destination = FROM_ACP_I2S_1;
-	}
-
-	acp_pte_config(acp_mmio, audio_config->pg, audio_config->num_of_pages,
-			pte_offset);
-	if (audio_config->direction == SNDRV_PCM_STREAM_PLAYBACK)
-		dma_dscr_idx = PLAYBACK_START_DMA_DESCR_CH12;
-	else
-		dma_dscr_idx = CAPTURE_START_DMA_DESCR_CH14;
-
+	acp_pte_config(acp_mmio, rtd->pg, rtd->num_of_pages,
+		       rtd->pte_offset);
 	/* Configure System memory <-> ACP SRAM DMA descriptors */
-	set_acp_sysmem_dma_descriptors(acp_mmio, audio_config->size,
-				       audio_config->direction, pte_offset,
-					ch1, sram_bank, dma_dscr_idx, asic_type);
-
-	if (audio_config->direction == SNDRV_PCM_STREAM_PLAYBACK)
-		dma_dscr_idx = PLAYBACK_START_DMA_DESCR_CH13;
-	else
-		dma_dscr_idx = CAPTURE_START_DMA_DESCR_CH15;
+	set_acp_sysmem_dma_descriptors(acp_mmio, rtd->size,
+				       rtd->direction, rtd->pte_offset,
+				       rtd->ch1, rtd->sram_bank,
+				       rtd->dma_dscr_idx_1, asic_type);
 	/* Configure ACP SRAM <-> I2S DMA descriptors */
-	set_acp_to_i2s_dma_descriptors(acp_mmio, audio_config->size,
-					audio_config->direction, sram_bank,
-					destination, ch2, dma_dscr_idx,
-					asic_type);
+	set_acp_to_i2s_dma_descriptors(acp_mmio, rtd->size,
+				       rtd->direction, rtd->sram_bank,
+				       rtd->destination, rtd->ch2,
+				       rtd->dma_dscr_idx_2, asic_type);
 }
 
 /* Start a given DMA channel transfer */
-static void acp_dma_start(void __iomem *acp_mmio,
-			 u16 ch_num, bool is_circular)
+static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
 {
 	u32 dma_ctrl;
 
@@ -375,7 +347,8 @@ static void acp_dma_start(void __iomem *acp_mmio,
 	/* Invalidating the DAGB cache */
 	acp_reg_write(1, acp_mmio, mmACP_DAGB_ATU_CTRL);
 
-	/* configure the DMA channel and start the DMA transfer
+	/*
+	 * configure the DMA channel and start the DMA transfer
 	 * set dmachrun bit to start the transfer and enable the
 	 * interrupt on completion of the dma transfer
 	 */
@@ -385,6 +358,9 @@ static void acp_dma_start(void __iomem *acp_mmio,
 	case ACP_TO_I2S_DMA_CH_NUM:
 	case ACP_TO_SYSRAM_CH_NUM:
 	case I2S_TO_ACP_DMA_CH_NUM:
+	case ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM:
+	case ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM:
+	case I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM:
 		dma_ctrl |= ACP_DMA_CNTL_0__DMAChIOCEn_MASK;
 		break;
 	default:
@@ -392,11 +368,8 @@ static void acp_dma_start(void __iomem *acp_mmio,
 		break;
 	}
 
-	/* enable  for ACP SRAM to/from I2S DMA channel */
-	if (is_circular == true)
-		dma_ctrl |= ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
-	else
-		dma_ctrl &= ~ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
+	/* circular for both DMA channel */
+	dma_ctrl |= ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
 
 	acp_reg_write(dma_ctrl, acp_mmio, mmACP_DMA_CNTL_0 + ch_num);
 }
@@ -410,9 +383,10 @@ static int acp_dma_stop(void __iomem *acp_mmio, u8 ch_num)
 
 	dma_ctrl = acp_reg_read(acp_mmio, mmACP_DMA_CNTL_0 + ch_num);
 
-	/* clear the dma control register fields before writing zero
+	/*
+	 * clear the dma control register fields before writing zero
 	 * in reset bit
-	*/
+	 */
 	dma_ctrl &= ~ACP_DMA_CNTL_0__DMAChRun_MASK;
 	dma_ctrl &= ~ACP_DMA_CNTL_0__DMAChIOCEn_MASK;
 
@@ -420,9 +394,10 @@ static int acp_dma_stop(void __iomem *acp_mmio, u8 ch_num)
 	dma_ch_sts = acp_reg_read(acp_mmio, mmACP_DMA_CH_STS);
 
 	if (dma_ch_sts & BIT(ch_num)) {
-		/* set the reset bit for this channel to stop the dma
-		*  transfer
-		*/
+		/*
+		 * set the reset bit for this channel to stop the dma
+		 *  transfer
+		 */
 		dma_ctrl |= ACP_DMA_CNTL_0__DMAChRst_MASK;
 		acp_reg_write(dma_ctrl, acp_mmio, mmACP_DMA_CNTL_0 + ch_num);
 	}
@@ -431,13 +406,14 @@ static int acp_dma_stop(void __iomem *acp_mmio, u8 ch_num)
 	while (true) {
 		dma_ch_sts = acp_reg_read(acp_mmio, mmACP_DMA_CH_STS);
 		if (!(dma_ch_sts & BIT(ch_num))) {
-			/* clear the reset flag after successfully stopping
-			* the dma transfer and break from the loop
-			*/
+			/*
+			 * clear the reset flag after successfully stopping
+			 * the dma transfer and break from the loop
+			 */
 			dma_ctrl &= ~ACP_DMA_CNTL_0__DMAChRst_MASK;
 
 			acp_reg_write(dma_ctrl, acp_mmio, mmACP_DMA_CNTL_0
-								+ ch_num);
+				      + ch_num);
 			break;
 		}
 		if (--count == 0) {
@@ -450,7 +426,7 @@ static int acp_dma_stop(void __iomem *acp_mmio, u8 ch_num)
 }
 
 static void acp_set_sram_bank_state(void __iomem *acp_mmio, u16 bank,
-					bool power_on)
+				    bool power_on)
 {
 	u32 val, req_reg, sts_reg, sts_reg_mask;
 	u32 loops = 1000;
@@ -530,7 +506,7 @@ static int acp_init(void __iomem *acp_mmio, u32 asic_type)
 
 	while (true) {
 		val = acp_reg_read(acp_mmio, mmACP_STATUS);
-		if (val & (u32) 0x1)
+		if (val & (u32)0x1)
 			break;
 		if (--count == 0) {
 			pr_err("Failed to reset ACP\n");
@@ -544,13 +520,20 @@ static int acp_init(void __iomem *acp_mmio, u32 asic_type)
 	val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
 	acp_reg_write(val, acp_mmio, mmACP_SOFT_RESET);
 
+	/* For BT instance change pins from UART to BT */
+	if (!bt_uart_enable) {
+		val = acp_reg_read(acp_mmio, mmACP_BT_UART_PAD_SEL);
+		val |= ACP_BT_UART_PAD_SELECT_MASK;
+		acp_reg_write(val, acp_mmio, mmACP_BT_UART_PAD_SEL);
+	}
+
 	/* initiailize Onion control DAGB register */
 	acp_reg_write(ACP_ONION_CNTL_DEFAULT, acp_mmio,
-			mmACP_AXI2DAGB_ONION_CNTL);
+		      mmACP_AXI2DAGB_ONION_CNTL);
 
 	/* initiailize Garlic control DAGB registers */
 	acp_reg_write(ACP_GARLIC_CNTL_DEFAULT, acp_mmio,
-			mmACP_AXI2DAGB_GARLIC_CNTL);
+		      mmACP_AXI2DAGB_GARLIC_CNTL);
 
 	sram_pte_offset = ACP_DAGB_GRP_SRAM_BASE_ADDRESS |
 			ACP_DAGB_BASE_ADDR_GRP_1__AXI2DAGBSnoopSel_MASK |
@@ -558,17 +541,18 @@ static int acp_init(void __iomem *acp_mmio, u32 asic_type)
 			ACP_DAGB_BASE_ADDR_GRP_1__AXI2DAGBGrpEnable_MASK;
 	acp_reg_write(sram_pte_offset,  acp_mmio, mmACP_DAGB_BASE_ADDR_GRP_1);
 	acp_reg_write(ACP_PAGE_SIZE_4K_ENABLE, acp_mmio,
-			mmACP_DAGB_PAGE_SIZE_GRP_1);
+		      mmACP_DAGB_PAGE_SIZE_GRP_1);
 
 	acp_reg_write(ACP_SRAM_BASE_ADDRESS, acp_mmio,
-			mmACP_DMA_DESC_BASE_ADDR);
+		      mmACP_DMA_DESC_BASE_ADDR);
 
 	/* Num of descriptiors in SRAM 0x4, means 256 descriptors;(64 * 4) */
 	acp_reg_write(0x4, acp_mmio, mmACP_DMA_DESC_MAX_NUM_DSCR);
 	acp_reg_write(ACP_EXTERNAL_INTR_CNTL__DMAIOCMask_MASK,
-		acp_mmio, mmACP_EXTERNAL_INTR_CNTL);
+		      acp_mmio, mmACP_EXTERNAL_INTR_CNTL);
 
-       /* When ACP_TILE_P1 is turned on, all SRAM banks get turned on.
+       /*
+	* When ACP_TILE_P1 is turned on, all SRAM banks get turned on.
 	* Now, turn off all of them. This can't be done in 'poweron' of
 	* ACP pm domain, as this requires ACP to be initialized.
 	* For Stoney, Memory gating is disabled,i.e SRAM Banks
@@ -606,7 +590,7 @@ static int acp_deinit(void __iomem *acp_mmio)
 		}
 		udelay(100);
 	}
-	/** Disable ACP clock */
+	/* Disable ACP clock */
 	val = acp_reg_read(acp_mmio, mmACP_CONTROL);
 	val &= ~ACP_CONTROL__ClkEn_MASK;
 	acp_reg_write(val, acp_mmio, mmACP_CONTROL);
@@ -615,7 +599,7 @@ static int acp_deinit(void __iomem *acp_mmio)
 
 	while (true) {
 		val = acp_reg_read(acp_mmio, mmACP_STATUS);
-		if (!(val & (u32) 0x1))
+		if (!(val & (u32)0x1))
 			break;
 		if (--count == 0) {
 			pr_err("Failed to reset ACP\n");
@@ -629,7 +613,6 @@ static int acp_deinit(void __iomem *acp_mmio)
 /* ACP DMA irq handler routine for playback, capture usecases */
 static irqreturn_t dma_irq_handler(int irq, void *arg)
 {
-	u16 dscr_idx;
 	u32 intr_flag, ext_intr_status;
 	struct audio_drv_data *irq_data;
 	void __iomem *acp_mmio;
@@ -646,41 +629,45 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 
 	if ((intr_flag & BIT(ACP_TO_I2S_DMA_CH_NUM)) != 0) {
 		valid_irq = true;
-		if (acp_reg_read(acp_mmio, mmACP_DMA_CUR_DSCR_13) ==
-				PLAYBACK_START_DMA_DESCR_CH13)
-			dscr_idx = PLAYBACK_END_DMA_DESCR_CH12;
-		else
-			dscr_idx = PLAYBACK_START_DMA_DESCR_CH12;
-		config_acp_dma_channel(acp_mmio, SYSRAM_TO_ACP_CH_NUM, dscr_idx,
-				       1, 0);
-		acp_dma_start(acp_mmio, SYSRAM_TO_ACP_CH_NUM, false);
-
 		snd_pcm_period_elapsed(irq_data->play_i2ssp_stream);
-
 		acp_reg_write((intr_flag & BIT(ACP_TO_I2S_DMA_CH_NUM)) << 16,
-				acp_mmio, mmACP_EXTERNAL_INTR_STAT);
+			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) != 0) {
+	if ((intr_flag & BIT(ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM)) != 0) {
 		valid_irq = true;
-		if (acp_reg_read(acp_mmio, mmACP_DMA_CUR_DSCR_15) ==
-				CAPTURE_START_DMA_DESCR_CH15)
-			dscr_idx = CAPTURE_END_DMA_DESCR_CH14;
-		else
-			dscr_idx = CAPTURE_START_DMA_DESCR_CH14;
-		config_acp_dma_channel(acp_mmio, ACP_TO_SYSRAM_CH_NUM, dscr_idx,
-				       1, 0);
-		acp_dma_start(acp_mmio, ACP_TO_SYSRAM_CH_NUM, false);
+		snd_pcm_period_elapsed(irq_data->play_i2sbt_stream);
+		acp_reg_write((intr_flag &
+			      BIT(ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM)) << 16,
+			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
+	}
 
+	if ((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) != 0) {
+		valid_irq = true;
+		snd_pcm_period_elapsed(irq_data->capture_i2ssp_stream);
 		acp_reg_write((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) << 16,
-				acp_mmio, mmACP_EXTERNAL_INTR_STAT);
+			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
 	if ((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) != 0) {
 		valid_irq = true;
-		snd_pcm_period_elapsed(irq_data->capture_i2ssp_stream);
 		acp_reg_write((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) << 16,
-				acp_mmio, mmACP_EXTERNAL_INTR_STAT);
+			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
+	}
+
+	if ((intr_flag & BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) != 0) {
+		valid_irq = true;
+		snd_pcm_period_elapsed(irq_data->capture_i2sbt_stream);
+		acp_reg_write((intr_flag &
+			      BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) << 16,
+			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
+	}
+
+	if ((intr_flag & BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) != 0) {
+		valid_irq = true;
+		acp_reg_write((intr_flag &
+			      BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) << 16,
+			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
 	if (valid_irq)
@@ -695,11 +682,12 @@ static int acp_dma_open(struct snd_pcm_substream *substream)
 	int ret = 0;
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd, DRV_NAME);
+	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
+								    DRV_NAME);
 	struct audio_drv_data *intr_data = dev_get_drvdata(component->dev);
 	struct audio_substream_data *adata =
 		kzalloc(sizeof(struct audio_substream_data), GFP_KERNEL);
-	if (adata == NULL)
+	if (!adata)
 		return -ENOMEM;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
@@ -731,17 +719,19 @@ static int acp_dma_open(struct snd_pcm_substream *substream)
 	adata->acp_mmio = intr_data->acp_mmio;
 	runtime->private_data = adata;
 
-	/* Enable ACP irq, when neither playback or capture streams are
+	/*
+	 * Enable ACP irq, when neither playback or capture streams are
 	 * active by the time when a new stream is being opened.
 	 * This enablement is not required for another stream, if current
 	 * stream is not closed
-	*/
-	if (!intr_data->play_i2ssp_stream && !intr_data->capture_i2ssp_stream)
+	 */
+	if (!intr_data->play_i2ssp_stream && !intr_data->capture_i2ssp_stream &&
+	    !intr_data->play_i2sbt_stream && !intr_data->capture_i2sbt_stream)
 		acp_reg_write(1, adata->acp_mmio, mmACP_EXTERNAL_INTR_ENB);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		intr_data->play_i2ssp_stream = substream;
-		/* For Stoney, Memory gating is disabled,i.e SRAM Banks
+		/*
+		 * For Stoney, Memory gating is disabled,i.e SRAM Banks
 		 * won't be turned off. The default state for SRAM banks is ON.
 		 * Setting SRAM bank state code skipped for STONEY platform.
 		 */
@@ -751,7 +741,6 @@ static int acp_dma_open(struct snd_pcm_substream *substream)
 							bank, true);
 		}
 	} else {
-		intr_data->capture_i2ssp_stream = substream;
 		if (intr_data->asic_type != CHIP_STONEY) {
 			for (bank = 5; bank <= 8; bank++)
 				acp_set_sram_bank_state(intr_data->acp_mmio,
@@ -772,8 +761,11 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_runtime *runtime;
 	struct audio_substream_data *rtd;
 	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd, DRV_NAME);
+	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
+								    DRV_NAME);
 	struct audio_drv_data *adata = dev_get_drvdata(component->dev);
+	struct snd_soc_card *card = prtd->card;
+	struct acp_platform_info *pinfo = snd_soc_card_get_drvdata(card);
 
 	runtime = substream->runtime;
 	rtd = runtime->private_data;
@@ -781,14 +773,111 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 	if (WARN_ON(!rtd))
 		return -EINVAL;
 
+	rtd->i2s_instance = pinfo->i2s_instance;
 	if (adata->asic_type == CHIP_STONEY) {
-		val = acp_reg_read(adata->acp_mmio, mmACP_I2S_16BIT_RESOLUTION_EN);
-		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-			val |= ACP_I2S_SP_16BIT_RESOLUTION_EN;
-		else
-			val |= ACP_I2S_MIC_16BIT_RESOLUTION_EN;
-		acp_reg_write(val, adata->acp_mmio, mmACP_I2S_16BIT_RESOLUTION_EN);
+		val = acp_reg_read(adata->acp_mmio,
+				   mmACP_I2S_16BIT_RESOLUTION_EN);
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+			switch (rtd->i2s_instance) {
+			case I2S_BT_INSTANCE:
+				val |= ACP_I2S_BT_16BIT_RESOLUTION_EN;
+				break;
+			case I2S_SP_INSTANCE:
+			default:
+				val |= ACP_I2S_SP_16BIT_RESOLUTION_EN;
+			}
+		} else {
+			switch (rtd->i2s_instance) {
+			case I2S_BT_INSTANCE:
+				val |= ACP_I2S_BT_16BIT_RESOLUTION_EN;
+				break;
+			case I2S_SP_INSTANCE:
+			default:
+				val |= ACP_I2S_MIC_16BIT_RESOLUTION_EN;
+			}
+		}
+		acp_reg_write(val, adata->acp_mmio,
+			      mmACP_I2S_16BIT_RESOLUTION_EN);
+	}
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		switch (rtd->i2s_instance) {
+		case I2S_BT_INSTANCE:
+			rtd->pte_offset = ACP_ST_BT_PLAYBACK_PTE_OFFSET;
+			rtd->ch1 = SYSRAM_TO_ACP_BT_INSTANCE_CH_NUM;
+			rtd->ch2 = ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM;
+			rtd->sram_bank = ACP_SRAM_BANK_3_ADDRESS;
+			rtd->destination = TO_BLUETOOTH;
+			rtd->dma_dscr_idx_1 = PLAYBACK_START_DMA_DESCR_CH8;
+			rtd->dma_dscr_idx_2 = PLAYBACK_START_DMA_DESCR_CH9;
+			rtd->byte_cnt_high_reg_offset =
+					mmACP_I2S_BT_TRANSMIT_BYTE_CNT_HIGH;
+			rtd->byte_cnt_low_reg_offset =
+					mmACP_I2S_BT_TRANSMIT_BYTE_CNT_LOW;
+			adata->play_i2sbt_stream = substream;
+			break;
+		case I2S_SP_INSTANCE:
+		default:
+			switch (adata->asic_type) {
+			case CHIP_STONEY:
+				rtd->pte_offset = ACP_ST_PLAYBACK_PTE_OFFSET;
+				break;
+			default:
+				rtd->pte_offset = ACP_PLAYBACK_PTE_OFFSET;
+			}
+			rtd->ch1 = SYSRAM_TO_ACP_CH_NUM;
+			rtd->ch2 = ACP_TO_I2S_DMA_CH_NUM;
+			rtd->sram_bank = ACP_SRAM_BANK_1_ADDRESS;
+			rtd->destination = TO_ACP_I2S_1;
+			rtd->dma_dscr_idx_1 = PLAYBACK_START_DMA_DESCR_CH12;
+			rtd->dma_dscr_idx_2 = PLAYBACK_START_DMA_DESCR_CH13;
+			rtd->byte_cnt_high_reg_offset =
+					mmACP_I2S_TRANSMIT_BYTE_CNT_HIGH;
+			rtd->byte_cnt_low_reg_offset =
+					mmACP_I2S_TRANSMIT_BYTE_CNT_LOW;
+			adata->play_i2ssp_stream = substream;
+		}
+	} else {
+		switch (rtd->i2s_instance) {
+		case I2S_BT_INSTANCE:
+			rtd->pte_offset = ACP_ST_BT_CAPTURE_PTE_OFFSET;
+			rtd->ch1 = ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM;
+			rtd->ch2 = I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM;
+			rtd->sram_bank = ACP_SRAM_BANK_4_ADDRESS;
+			rtd->destination = FROM_BLUETOOTH;
+			rtd->dma_dscr_idx_1 = CAPTURE_START_DMA_DESCR_CH10;
+			rtd->dma_dscr_idx_2 = CAPTURE_START_DMA_DESCR_CH11;
+			rtd->byte_cnt_high_reg_offset =
+					mmACP_I2S_BT_RECEIVE_BYTE_CNT_HIGH;
+			rtd->byte_cnt_low_reg_offset =
+					mmACP_I2S_BT_RECEIVE_BYTE_CNT_LOW;
+			adata->capture_i2sbt_stream = substream;
+			break;
+		case I2S_SP_INSTANCE:
+		default:
+			rtd->pte_offset = ACP_CAPTURE_PTE_OFFSET;
+			rtd->ch1 = ACP_TO_SYSRAM_CH_NUM;
+			rtd->ch2 = I2S_TO_ACP_DMA_CH_NUM;
+			switch (adata->asic_type) {
+			case CHIP_STONEY:
+				rtd->pte_offset = ACP_ST_CAPTURE_PTE_OFFSET;
+				rtd->sram_bank = ACP_SRAM_BANK_2_ADDRESS;
+				break;
+			default:
+				rtd->pte_offset = ACP_CAPTURE_PTE_OFFSET;
+				rtd->sram_bank = ACP_SRAM_BANK_5_ADDRESS;
+			}
+			rtd->destination = FROM_ACP_I2S_1;
+			rtd->dma_dscr_idx_1 = CAPTURE_START_DMA_DESCR_CH14;
+			rtd->dma_dscr_idx_2 = CAPTURE_START_DMA_DESCR_CH15;
+			rtd->byte_cnt_high_reg_offset =
+					mmACP_I2S_RECEIVED_BYTE_CNT_HIGH;
+			rtd->byte_cnt_low_reg_offset =
+					mmACP_I2S_RECEIVED_BYTE_CNT_LOW;
+			adata->capture_i2ssp_stream = substream;
+		}
 	}
+
 	size = params_buffer_bytes(params);
 	status = snd_pcm_lib_malloc_pages(substream, size);
 	if (status < 0)
@@ -797,7 +886,7 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 	memset(substream->runtime->dma_area, 0, params_buffer_bytes(params));
 	pg = virt_to_page(substream->dma_buffer.area);
 
-	if (pg != NULL) {
+	if (pg) {
 		acp_set_sram_bank_state(rtd->acp_mmio, 0, true);
 		/* Save for runtime private data */
 		rtd->pg = pg;
@@ -822,26 +911,15 @@ static int acp_dma_hw_free(struct snd_pcm_substream *substream)
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static u64 acp_get_byte_count(void __iomem *acp_mmio, int stream)
+static u64 acp_get_byte_count(struct audio_substream_data *rtd)
 {
-	union acp_dma_count playback_dma_count;
-	union acp_dma_count capture_dma_count;
-	u64 bytescount = 0;
+	union acp_dma_count byte_count;
 
-	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		playback_dma_count.bcount.high = acp_reg_read(acp_mmio,
-					mmACP_I2S_TRANSMIT_BYTE_CNT_HIGH);
-		playback_dma_count.bcount.low  = acp_reg_read(acp_mmio,
-					mmACP_I2S_TRANSMIT_BYTE_CNT_LOW);
-		bytescount = playback_dma_count.bytescount;
-	} else {
-		capture_dma_count.bcount.high = acp_reg_read(acp_mmio,
-					mmACP_I2S_RECEIVED_BYTE_CNT_HIGH);
-		capture_dma_count.bcount.low  = acp_reg_read(acp_mmio,
-					mmACP_I2S_RECEIVED_BYTE_CNT_LOW);
-		bytescount = capture_dma_count.bytescount;
-	}
-	return bytescount;
+	byte_count.bcount.high = acp_reg_read(rtd->acp_mmio,
+					      rtd->byte_cnt_high_reg_offset);
+	byte_count.bcount.low  = acp_reg_read(rtd->acp_mmio,
+					      rtd->byte_cnt_low_reg_offset);
+	return byte_count.bytescount;
 }
 
 static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
@@ -857,15 +935,10 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 		return -EINVAL;
 
 	buffersize = frames_to_bytes(runtime, runtime->buffer_size);
-	bytescount = acp_get_byte_count(rtd->acp_mmio, substream->stream);
+	bytescount = acp_get_byte_count(rtd);
 
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		if (bytescount > rtd->i2ssp_renderbytescount)
-			bytescount = bytescount - rtd->i2ssp_renderbytescount;
-	} else {
-		if (bytescount > rtd->i2ssp_capturebytescount)
-			bytescount = bytescount - rtd->i2ssp_capturebytescount;
-	}
+	if (bytescount > rtd->bytescount)
+		bytescount -= rtd->bytescount;
 	pos = do_div(bytescount, buffersize);
 	return bytes_to_frames(runtime, pos);
 }
@@ -883,34 +956,25 @@ static int acp_dma_prepare(struct snd_pcm_substream *substream)
 
 	if (!rtd)
 		return -EINVAL;
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		config_acp_dma_channel(rtd->acp_mmio, SYSRAM_TO_ACP_CH_NUM,
-					PLAYBACK_START_DMA_DESCR_CH12,
-					NUM_DSCRS_PER_CHANNEL, 0);
-		config_acp_dma_channel(rtd->acp_mmio, ACP_TO_I2S_DMA_CH_NUM,
-					PLAYBACK_START_DMA_DESCR_CH13,
-					NUM_DSCRS_PER_CHANNEL, 0);
-	} else {
-		config_acp_dma_channel(rtd->acp_mmio, ACP_TO_SYSRAM_CH_NUM,
-					CAPTURE_START_DMA_DESCR_CH14,
-					NUM_DSCRS_PER_CHANNEL, 0);
-		config_acp_dma_channel(rtd->acp_mmio, I2S_TO_ACP_DMA_CH_NUM,
-					CAPTURE_START_DMA_DESCR_CH15,
-					NUM_DSCRS_PER_CHANNEL, 0);
-	}
+
+	config_acp_dma_channel(rtd->acp_mmio,
+			       rtd->ch1,
+			       rtd->dma_dscr_idx_1,
+			       NUM_DSCRS_PER_CHANNEL, 0);
+	config_acp_dma_channel(rtd->acp_mmio,
+			       rtd->ch2,
+			       rtd->dma_dscr_idx_2,
+			       NUM_DSCRS_PER_CHANNEL, 0);
 	return 0;
 }
 
 static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	int ret;
-	u32 loops = 4000;
 	u64 bytescount = 0;
 
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *prtd = substream->private_data;
 	struct audio_substream_data *rtd = runtime->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd, DRV_NAME);
 
 	if (!rtd)
 		return -EINVAL;
@@ -918,59 +982,40 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 	case SNDRV_PCM_TRIGGER_RESUME:
-		bytescount = acp_get_byte_count(rtd->acp_mmio,
-						substream->stream);
+		bytescount = acp_get_byte_count(rtd);
+		if (rtd->bytescount == 0)
+			rtd->bytescount = bytescount;
 		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-			if (rtd->i2ssp_renderbytescount == 0)
-				rtd->i2ssp_renderbytescount = bytescount;
-			acp_dma_start(rtd->acp_mmio,
-						SYSRAM_TO_ACP_CH_NUM, false);
-			while (acp_reg_read(rtd->acp_mmio, mmACP_DMA_CH_STS) &
-						BIT(SYSRAM_TO_ACP_CH_NUM)) {
-				if (!loops--) {
-					dev_err(component->dev,
-						"acp dma start timeout\n");
-					return -ETIMEDOUT;
-				}
-				cpu_relax();
-			}
-
-			acp_dma_start(rtd->acp_mmio,
-					ACP_TO_I2S_DMA_CH_NUM, true);
-
+			acp_dma_start(rtd->acp_mmio, rtd->ch1);
+			acp_dma_start(rtd->acp_mmio, rtd->ch2);
 		} else {
-			if (rtd->i2ssp_capturebytescount == 0)
-				rtd->i2ssp_capturebytescount = bytescount;
-			acp_dma_start(rtd->acp_mmio,
-					    I2S_TO_ACP_DMA_CH_NUM, true);
+			acp_dma_start(rtd->acp_mmio, rtd->ch2);
+			acp_dma_start(rtd->acp_mmio, rtd->ch1);
 		}
 		ret = 0;
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-		/* Need to stop only circular DMA channels :
-		 * ACP_TO_I2S_DMA_CH_NUM / I2S_TO_ACP_DMA_CH_NUM. Non-circular
-		 * channels will stopped automatically after its transfer
-		 * completes : SYSRAM_TO_ACP_CH_NUM / ACP_TO_SYSRAM_CH_NUM
+		/* For playback, non circular dma should be stopped first
+		 * i.e Sysram to acp dma transfer channel(rtd->ch1) should be
+		 * stopped before stopping cirular dma which is acp sram to i2s
+		 * fifo dma transfer channel(rtd->ch2). Where as in Capture
+		 * scenario, i2s fifo to acp sram dma channel(rtd->ch2) stopped
+		 * first before stopping acp sram to sysram which is circular
+		 * dma(rtd->ch1).
 		 */
 		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-			ret = acp_dma_stop(rtd->acp_mmio,
-						SYSRAM_TO_ACP_CH_NUM);
-			ret = acp_dma_stop(rtd->acp_mmio,
-					ACP_TO_I2S_DMA_CH_NUM);
-			rtd->i2ssp_renderbytescount = 0;
+			acp_dma_stop(rtd->acp_mmio, rtd->ch1);
+			ret =  acp_dma_stop(rtd->acp_mmio, rtd->ch2);
 		} else {
-			ret = acp_dma_stop(rtd->acp_mmio,
-					I2S_TO_ACP_DMA_CH_NUM);
-			ret = acp_dma_stop(rtd->acp_mmio,
-						ACP_TO_SYSRAM_CH_NUM);
-			rtd->i2ssp_capturebytescount = 0;
+			acp_dma_stop(rtd->acp_mmio, rtd->ch2);
+			ret = acp_dma_stop(rtd->acp_mmio, rtd->ch1);
 		}
+		rtd->bytescount = 0;
 		break;
 	default:
 		ret = -EINVAL;
-
 	}
 	return ret;
 }
@@ -978,26 +1023,27 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 static int acp_dma_new(struct snd_soc_pcm_runtime *rtd)
 {
 	int ret;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
+	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd,
+								    DRV_NAME);
 	struct audio_drv_data *adata = dev_get_drvdata(component->dev);
 
 	switch (adata->asic_type) {
 	case CHIP_STONEY:
 		ret = snd_pcm_lib_preallocate_pages_for_all(rtd->pcm,
-							SNDRV_DMA_TYPE_DEV,
-							NULL, ST_MIN_BUFFER,
-							ST_MAX_BUFFER);
+							    SNDRV_DMA_TYPE_DEV,
+							    NULL, ST_MIN_BUFFER,
+							    ST_MAX_BUFFER);
 		break;
 	default:
 		ret = snd_pcm_lib_preallocate_pages_for_all(rtd->pcm,
-							SNDRV_DMA_TYPE_DEV,
-							NULL, MIN_BUFFER,
-							MAX_BUFFER);
+							    SNDRV_DMA_TYPE_DEV,
+							    NULL, MIN_BUFFER,
+							    MAX_BUFFER);
 		break;
 	}
 	if (ret < 0)
 		dev_err(component->dev,
-				"buffer preallocation failer error:%d\n", ret);
+			"buffer preallocation failure error:%d\n", ret);
 	return ret;
 }
 
@@ -1007,38 +1053,55 @@ static int acp_dma_close(struct snd_pcm_substream *substream)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
 	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd, DRV_NAME);
+	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
+								    DRV_NAME);
 	struct audio_drv_data *adata = dev_get_drvdata(component->dev);
 
-	kfree(rtd);
-
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		adata->play_i2ssp_stream = NULL;
-		/* For Stoney, Memory gating is disabled,i.e SRAM Banks
-		 * won't be turned off. The default state for SRAM banks is ON.
-		 * Setting SRAM bank state code skipped for STONEY platform.
-		 * added condition checks for Carrizo platform only
-		 */
-		if (adata->asic_type != CHIP_STONEY) {
-			for (bank = 1; bank <= 4; bank++)
-				acp_set_sram_bank_state(adata->acp_mmio, bank,
-				false);
+		switch (rtd->i2s_instance) {
+		case I2S_BT_INSTANCE:
+			adata->play_i2sbt_stream = NULL;
+			break;
+		case I2S_SP_INSTANCE:
+		default:
+			adata->play_i2ssp_stream = NULL;
+			/*
+			 * For Stoney, Memory gating is disabled,i.e SRAM Banks
+			 * won't be turned off. The default state for SRAM banks
+			 * is ON.Setting SRAM bank state code skipped for STONEY
+			 * platform. Added condition checks for Carrizo platform
+			 * only.
+			 */
+			if (adata->asic_type != CHIP_STONEY) {
+				for (bank = 1; bank <= 4; bank++)
+					acp_set_sram_bank_state(adata->acp_mmio,
+								bank, false);
+			}
 		}
 	} else  {
-		adata->capture_i2ssp_stream = NULL;
-		if (adata->asic_type != CHIP_STONEY) {
-			for (bank = 5; bank <= 8; bank++)
-				acp_set_sram_bank_state(adata->acp_mmio, bank,
-						     false);
+		switch (rtd->i2s_instance) {
+		case I2S_BT_INSTANCE:
+			adata->capture_i2sbt_stream = NULL;
+			break;
+		case I2S_SP_INSTANCE:
+		default:
+			adata->capture_i2ssp_stream = NULL;
+			if (adata->asic_type != CHIP_STONEY) {
+				for (bank = 5; bank <= 8; bank++)
+					acp_set_sram_bank_state(adata->acp_mmio,
+								bank, false);
+			}
 		}
 	}
 
-	/* Disable ACP irq, when the current stream is being closed and
+	/*
+	 * Disable ACP irq, when the current stream is being closed and
 	 * another stream is also not active.
-	*/
-	if (!adata->play_i2ssp_stream && !adata->capture_i2ssp_stream)
+	 */
+	if (!adata->play_i2ssp_stream && !adata->capture_i2ssp_stream &&
+	    !adata->play_i2sbt_stream && !adata->capture_i2sbt_stream)
 		acp_reg_write(0, adata->acp_mmio, mmACP_EXTERNAL_INTR_ENB);
-
+	kfree(rtd);
 	return 0;
 }
 
@@ -1054,7 +1117,7 @@ static const struct snd_pcm_ops acp_dma_ops = {
 	.prepare = acp_dma_prepare,
 };
 
-static struct snd_soc_component_driver acp_asoc_platform = {
+static const struct snd_soc_component_driver acp_asoc_platform = {
 	.name = DRV_NAME,
 	.ops = &acp_dma_ops,
 	.pcm_new = acp_dma_new,
@@ -1073,8 +1136,8 @@ static int acp_audio_probe(struct platform_device *pdev)
 	}
 
 	audio_drv_data = devm_kzalloc(&pdev->dev, sizeof(struct audio_drv_data),
-					GFP_KERNEL);
-	if (audio_drv_data == NULL)
+				      GFP_KERNEL);
+	if (!audio_drv_data)
 		return -ENOMEM;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1082,13 +1145,16 @@ static int acp_audio_probe(struct platform_device *pdev)
 	if (IS_ERR(audio_drv_data->acp_mmio))
 		return PTR_ERR(audio_drv_data->acp_mmio);
 
-	/* The following members gets populated in device 'open'
+	/*
+	 * The following members gets populated in device 'open'
 	 * function. Till then interrupts are disabled in 'acp_init'
 	 * and device doesn't generate any interrupts.
 	 */
 
 	audio_drv_data->play_i2ssp_stream = NULL;
 	audio_drv_data->capture_i2ssp_stream = NULL;
+	audio_drv_data->play_i2sbt_stream = NULL;
+	audio_drv_data->capture_i2sbt_stream = NULL;
 
 	audio_drv_data->asic_type =  *pdata;
 
@@ -1099,7 +1165,7 @@ static int acp_audio_probe(struct platform_device *pdev)
 	}
 
 	status = devm_request_irq(&pdev->dev, res->start, dma_irq_handler,
-					0, "ACP_IRQ", &pdev->dev);
+				  0, "ACP_IRQ", &pdev->dev);
 	if (status) {
 		dev_err(&pdev->dev, "ACP IRQ request failed\n");
 		return status;
@@ -1115,7 +1181,7 @@ static int acp_audio_probe(struct platform_device *pdev)
 	}
 
 	status = devm_snd_soc_register_component(&pdev->dev,
-						&acp_asoc_platform, NULL, 0);
+						 &acp_asoc_platform, NULL, 0);
 	if (status != 0) {
 		dev_err(&pdev->dev, "Fail to register ALSA platform device\n");
 		return status;
@@ -1145,6 +1211,7 @@ static int acp_pcm_resume(struct device *dev)
 {
 	u16 bank;
 	int status;
+	struct audio_substream_data *rtd;
 	struct audio_drv_data *adata = dev_get_drvdata(dev);
 
 	status = acp_init(adata->acp_mmio, adata->asic_type);
@@ -1154,28 +1221,40 @@ static int acp_pcm_resume(struct device *dev)
 	}
 
 	if (adata->play_i2ssp_stream && adata->play_i2ssp_stream->runtime) {
-		/* For Stoney, Memory gating is disabled,i.e SRAM Banks
+		/*
+		 * For Stoney, Memory gating is disabled,i.e SRAM Banks
 		 * won't be turned off. The default state for SRAM banks is ON.
 		 * Setting SRAM bank state code skipped for STONEY platform.
 		 */
 		if (adata->asic_type != CHIP_STONEY) {
 			for (bank = 1; bank <= 4; bank++)
 				acp_set_sram_bank_state(adata->acp_mmio, bank,
-						true);
+							true);
 		}
-		config_acp_dma(adata->acp_mmio,
-			adata->play_i2ssp_stream->runtime->private_data,
-			adata->asic_type);
+		rtd = adata->play_i2ssp_stream->runtime->private_data;
+		config_acp_dma(adata->acp_mmio, rtd, adata->asic_type);
 	}
-	if (adata->capture_i2ssp_stream && adata->capture_i2ssp_stream->runtime) {
+	if (adata->capture_i2ssp_stream &&
+	    adata->capture_i2ssp_stream->runtime) {
 		if (adata->asic_type != CHIP_STONEY) {
 			for (bank = 5; bank <= 8; bank++)
 				acp_set_sram_bank_state(adata->acp_mmio, bank,
-						true);
+							true);
+		}
+		rtd =  adata->capture_i2ssp_stream->runtime->private_data;
+		config_acp_dma(adata->acp_mmio, rtd, adata->asic_type);
+	}
+	if (adata->asic_type != CHIP_CARRIZO) {
+		if (adata->play_i2sbt_stream &&
+		    adata->play_i2sbt_stream->runtime) {
+			rtd = adata->play_i2sbt_stream->runtime->private_data;
+			config_acp_dma(adata->acp_mmio, rtd, adata->asic_type);
+		}
+		if (adata->capture_i2sbt_stream &&
+		    adata->capture_i2sbt_stream->runtime) {
+			rtd = adata->capture_i2sbt_stream->runtime->private_data;
+			config_acp_dma(adata->acp_mmio, rtd, adata->asic_type);
 		}
-		config_acp_dma(adata->acp_mmio,
-			adata->capture_i2ssp_stream->runtime->private_data,
-			adata->asic_type);
 	}
 	acp_reg_write(1, adata->acp_mmio, mmACP_EXTERNAL_INTR_ENB);
 	return 0;
diff --git a/sound/soc/amd/acp.h b/sound/soc/amd/acp.h
index ba01510eb818..9cd3e96c84d4 100644
--- a/sound/soc/amd/acp.h
+++ b/sound/soc/amd/acp.h
@@ -10,17 +10,30 @@
 #define ACP_PLAYBACK_PTE_OFFSET			10
 #define ACP_CAPTURE_PTE_OFFSET			0
 
+/* Playback and Capture Offset for Stoney */
+#define ACP_ST_PLAYBACK_PTE_OFFSET	0x04
+#define ACP_ST_CAPTURE_PTE_OFFSET	0x00
+#define ACP_ST_BT_PLAYBACK_PTE_OFFSET	0x08
+#define ACP_ST_BT_CAPTURE_PTE_OFFSET	0x0c
+
 #define ACP_GARLIC_CNTL_DEFAULT			0x00000FB4
 #define ACP_ONION_CNTL_DEFAULT			0x00000FB4
 
 #define ACP_PHYSICAL_BASE			0x14000
 
-/* Playback SRAM address (as a destination in dma descriptor) */
-#define ACP_SHARED_RAM_BANK_1_ADDRESS		0x4002000
-
-/* Capture SRAM address (as a source in dma descriptor) */
-#define ACP_SHARED_RAM_BANK_5_ADDRESS		0x400A000
-#define ACP_SHARED_RAM_BANK_3_ADDRESS		0x4006000
+/*
+ * In case of I2S SP controller instance, Stoney uses SRAM bank 1 for
+ * playback and SRAM Bank 2 for capture where as in case of BT I2S
+ * Instance, Stoney uses SRAM Bank 3 for playback & SRAM Bank 4 will
+ * be used for capture. Carrizo uses I2S SP controller instance. SRAM Banks
+ * 1, 2, 3, 4 will be used for playback & SRAM Banks 5, 6, 7, 8 will be used
+ * for capture scenario.
+ */
+#define ACP_SRAM_BANK_1_ADDRESS		0x4002000
+#define ACP_SRAM_BANK_2_ADDRESS		0x4004000
+#define ACP_SRAM_BANK_3_ADDRESS		0x4006000
+#define ACP_SRAM_BANK_4_ADDRESS		0x4008000
+#define ACP_SRAM_BANK_5_ADDRESS		0x400A000
 
 #define ACP_DMA_RESET_TIME			10000
 #define ACP_CLOCK_EN_TIME_OUT_VALUE		0x000000FF
@@ -35,8 +48,13 @@
 
 #define TO_ACP_I2S_1   0x2
 #define TO_ACP_I2S_2   0x4
+#define TO_BLUETOOTH   0x3
 #define FROM_ACP_I2S_1 0xa
 #define FROM_ACP_I2S_2 0xb
+#define FROM_BLUETOOTH 0xb
+
+#define I2S_SP_INSTANCE                 0x01
+#define I2S_BT_INSTANCE                 0x02
 
 #define ACP_TILE_ON_MASK                0x03
 #define ACP_TILE_OFF_MASK               0x02
@@ -57,6 +75,14 @@
 #define ACP_TO_SYSRAM_CH_NUM 14
 #define I2S_TO_ACP_DMA_CH_NUM 15
 
+/* Playback DMA Channels for I2S BT instance */
+#define SYSRAM_TO_ACP_BT_INSTANCE_CH_NUM  8
+#define ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM 9
+
+/* Capture DMA Channels for I2S BT Instance */
+#define ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM 10
+#define I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM 11
+
 #define NUM_DSCRS_PER_CHANNEL 2
 
 #define PLAYBACK_START_DMA_DESCR_CH12 0
@@ -69,9 +95,23 @@
 #define CAPTURE_START_DMA_DESCR_CH15 6
 #define CAPTURE_END_DMA_DESCR_CH15 7
 
+/* I2S BT Instance DMA Descriptors */
+#define PLAYBACK_START_DMA_DESCR_CH8 8
+#define PLAYBACK_END_DMA_DESCR_CH8 9
+#define PLAYBACK_START_DMA_DESCR_CH9 10
+#define PLAYBACK_END_DMA_DESCR_CH9 11
+
+#define CAPTURE_START_DMA_DESCR_CH10 12
+#define CAPTURE_END_DMA_DESCR_CH10 13
+#define CAPTURE_START_DMA_DESCR_CH11 14
+#define CAPTURE_END_DMA_DESCR_CH11 15
+
 #define mmACP_I2S_16BIT_RESOLUTION_EN       0x5209
 #define ACP_I2S_MIC_16BIT_RESOLUTION_EN 0x01
 #define ACP_I2S_SP_16BIT_RESOLUTION_EN	0x02
+#define ACP_I2S_BT_16BIT_RESOLUTION_EN	0x04
+#define ACP_BT_UART_PAD_SELECT_MASK	0x1
+
 enum acp_dma_priority_level {
 	/* 0x0 Specifies the DMA channel is given normal priority */
 	ACP_DMA_PRIORITY_LEVEL_NORMAL = 0x0,
@@ -84,20 +124,39 @@ struct audio_substream_data {
 	struct page *pg;
 	unsigned int order;
 	u16 num_of_pages;
+	u16 i2s_instance;
 	u16 direction;
+	u16 ch1;
+	u16 ch2;
+	u16 destination;
+	u16 dma_dscr_idx_1;
+	u16 dma_dscr_idx_2;
+	u32 pte_offset;
+	u32 sram_bank;
+	u32 byte_cnt_high_reg_offset;
+	u32 byte_cnt_low_reg_offset;
 	uint64_t size;
-	u64 i2ssp_renderbytescount;
-	u64 i2ssp_capturebytescount;
+	u64 bytescount;
 	void __iomem *acp_mmio;
 };
 
 struct audio_drv_data {
 	struct snd_pcm_substream *play_i2ssp_stream;
 	struct snd_pcm_substream *capture_i2ssp_stream;
+	struct snd_pcm_substream *play_i2sbt_stream;
+	struct snd_pcm_substream *capture_i2sbt_stream;
 	void __iomem *acp_mmio;
 	u32 asic_type;
 };
 
+/*
+ * this structure used for platform data transfer between machine driver
+ * and dma driver
+ */
+struct acp_platform_info {
+	u16 i2s_instance;
+};
+
 union acp_dma_count {
 	struct {
 	u32 low;
@@ -115,23 +174,25 @@ enum {
 };
 
 enum {
-	ACP_DMA_ATTRIBUTES_SHAREDMEM_TO_DAGB_ONION = 0x0,
-	ACP_DMA_ATTRIBUTES_SHARED_MEM_TO_DAGB_GARLIC = 0x1,
-	ACP_DMA_ATTRIBUTES_DAGB_ONION_TO_SHAREDMEM = 0x8,
-	ACP_DMA_ATTRIBUTES_DAGB_GARLIC_TO_SHAREDMEM = 0x9,
-	ACP_DMA_ATTRIBUTES_FORCE_SIZE = 0xF
+	ACP_DMA_ATTR_SHAREDMEM_TO_DAGB_ONION = 0x0,
+	ACP_DMA_ATTR_SHARED_MEM_TO_DAGB_GARLIC = 0x1,
+	ACP_DMA_ATTR_DAGB_ONION_TO_SHAREDMEM = 0x8,
+	ACP_DMA_ATTR_DAGB_GARLIC_TO_SHAREDMEM = 0x9,
+	ACP_DMA_ATTR_FORCE_SIZE = 0xF
 };
 
 typedef struct acp_dma_dscr_transfer {
 	/* Specifies the source memory location for the DMA data transfer. */
 	u32 src;
-	/* Specifies the destination memory location to where the data will
+	/*
+	 * Specifies the destination memory location to where the data will
 	 * be transferred.
-	*/
+	 */
 	u32 dest;
-	/* Specifies the number of bytes need to be transferred
-	* from source to destination memory.Transfer direction & IOC enable
-	*/
+	/*
+	 * Specifies the number of bytes need to be transferred
+	 * from source to destination memory.Transfer direction & IOC enable
+	 */
 	u32 xfer_val;
 	/* Reserved for future use */
 	u32 reserved;
diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig
index dcee145dd179..64b784e96f84 100644
--- a/sound/soc/atmel/Kconfig
+++ b/sound/soc/atmel/Kconfig
@@ -88,4 +88,13 @@ config SND_ATMEL_SOC_TSE850_PCM5142
 	help
 	  Say Y if you want to add support for the ASoC driver for the
 	  Axentia TSE-850 with a PCM5142 codec.
+
+config SND_ATMEL_SOC_I2S
+	tristate "Atmel ASoC driver for boards using I2S"
+	depends on OF && (ARCH_AT91 || COMPILE_TEST)
+	select SND_SOC_GENERIC_DMAENGINE_PCM
+	select REGMAP_MMIO
+	help
+	  Say Y or M if you want to add support for Atmel ASoc driver for boards
+	  using I2S.
 endif
diff --git a/sound/soc/atmel/Makefile b/sound/soc/atmel/Makefile
index 4440646416e8..cd87cb4bcff5 100644
--- a/sound/soc/atmel/Makefile
+++ b/sound/soc/atmel/Makefile
@@ -3,10 +3,12 @@
 snd-soc-atmel-pcm-pdc-objs := atmel-pcm-pdc.o
 snd-soc-atmel-pcm-dma-objs := atmel-pcm-dma.o
 snd-soc-atmel_ssc_dai-objs := atmel_ssc_dai.o
+snd-soc-atmel-i2s-objs := atmel-i2s.o
 
 obj-$(CONFIG_SND_ATMEL_SOC_PDC) += snd-soc-atmel-pcm-pdc.o
 obj-$(CONFIG_SND_ATMEL_SOC_DMA) += snd-soc-atmel-pcm-dma.o
 obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o
+obj-$(CONFIG_SND_ATMEL_SOC_I2S) += snd-soc-atmel-i2s.o
 
 # AT91 Machine Support
 snd-soc-sam9g20-wm8731-objs := sam9g20_wm8731.o
diff --git a/sound/soc/atmel/atmel-i2s.c b/sound/soc/atmel/atmel-i2s.c
new file mode 100644
index 000000000000..5d3b5af9fd92
--- /dev/null
+++ b/sound/soc/atmel/atmel-i2s.c
@@ -0,0 +1,765 @@
+/*
+ * Driver for Atmel I2S controller
+ *
+ * Copyright (C) 2015 Atmel Corporation
+ *
+ * Author: Cyrille Pitchen <cyrille.pitchen@atmel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/mfd/syscon.h>
+
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/initval.h>
+#include <sound/soc.h>
+#include <sound/dmaengine_pcm.h>
+
+#define ATMEL_I2SC_MAX_TDM_CHANNELS	8
+
+/*
+ * ---- I2S Controller Register map ----
+ */
+#define ATMEL_I2SC_CR		0x0000	/* Control Register */
+#define ATMEL_I2SC_MR		0x0004	/* Mode Register */
+#define ATMEL_I2SC_SR		0x0008	/* Status Register */
+#define ATMEL_I2SC_SCR		0x000c	/* Status Clear Register */
+#define ATMEL_I2SC_SSR		0x0010	/* Status Set Register */
+#define ATMEL_I2SC_IER		0x0014	/* Interrupt Enable Register */
+#define ATMEL_I2SC_IDR		0x0018	/* Interrupt Disable Register */
+#define ATMEL_I2SC_IMR		0x001c	/* Interrupt Mask Register */
+#define ATMEL_I2SC_RHR		0x0020	/* Receiver Holding Register */
+#define ATMEL_I2SC_THR		0x0024	/* Transmitter Holding Register */
+#define ATMEL_I2SC_VERSION	0x0028	/* Version Register */
+
+/*
+ * ---- Control Register (Write-only) ----
+ */
+#define ATMEL_I2SC_CR_RXEN	BIT(0)	/* Receiver Enable */
+#define ATMEL_I2SC_CR_RXDIS	BIT(1)	/* Receiver Disable */
+#define ATMEL_I2SC_CR_CKEN	BIT(2)	/* Clock Enable */
+#define ATMEL_I2SC_CR_CKDIS	BIT(3)	/* Clock Disable */
+#define ATMEL_I2SC_CR_TXEN	BIT(4)	/* Transmitter Enable */
+#define ATMEL_I2SC_CR_TXDIS	BIT(5)	/* Transmitter Disable */
+#define ATMEL_I2SC_CR_SWRST	BIT(7)	/* Software Reset */
+
+/*
+ * ---- Mode Register (Read/Write) ----
+ */
+#define ATMEL_I2SC_MR_MODE_MASK		GENMASK(0, 0)
+#define ATMEL_I2SC_MR_MODE_SLAVE	(0 << 0)
+#define ATMEL_I2SC_MR_MODE_MASTER	(1 << 0)
+
+#define ATMEL_I2SC_MR_DATALENGTH_MASK		GENMASK(4, 2)
+#define ATMEL_I2SC_MR_DATALENGTH_32_BITS	(0 << 2)
+#define ATMEL_I2SC_MR_DATALENGTH_24_BITS	(1 << 2)
+#define ATMEL_I2SC_MR_DATALENGTH_20_BITS	(2 << 2)
+#define ATMEL_I2SC_MR_DATALENGTH_18_BITS	(3 << 2)
+#define ATMEL_I2SC_MR_DATALENGTH_16_BITS	(4 << 2)
+#define ATMEL_I2SC_MR_DATALENGTH_16_BITS_COMPACT	(5 << 2)
+#define ATMEL_I2SC_MR_DATALENGTH_8_BITS		(6 << 2)
+#define ATMEL_I2SC_MR_DATALENGTH_8_BITS_COMPACT	(7 << 2)
+
+#define ATMEL_I2SC_MR_FORMAT_MASK	GENMASK(7, 6)
+#define ATMEL_I2SC_MR_FORMAT_I2S	(0 << 6)
+#define ATMEL_I2SC_MR_FORMAT_LJ		(1 << 6)  /* Left Justified */
+#define ATMEL_I2SC_MR_FORMAT_TDM	(2 << 6)
+#define ATMEL_I2SC_MR_FORMAT_TDMLJ	(3 << 6)
+
+/* Left audio samples duplicated to right audio channel */
+#define ATMEL_I2SC_MR_RXMONO		BIT(8)
+
+/* Receiver uses one DMA channel ... */
+#define ATMEL_I2SC_MR_RXDMA_MASK	GENMASK(9, 9)
+#define ATMEL_I2SC_MR_RXDMA_SINGLE	(0 << 9)  /* for all audio channels */
+#define ATMEL_I2SC_MR_RXDMA_MULTIPLE	(1 << 9)  /* per audio channel */
+
+/* I2SDO output of I2SC is internally connected to I2SDI input */
+#define ATMEL_I2SC_MR_RXLOOP		BIT(10)
+
+/* Left audio samples duplicated to right audio channel */
+#define ATMEL_I2SC_MR_TXMONO		BIT(12)
+
+/* Transmitter uses one DMA channel ... */
+#define ATMEL_I2SC_MR_TXDMA_MASK	GENMASK(13, 13)
+#define ATMEL_I2SC_MR_TXDMA_SINGLE	(0 << 13)  /* for all audio channels */
+#define ATMEL_I2SC_MR_TXDME_MULTIPLE	(1 << 13)  /* per audio channel */
+
+/* x sample transmitted when underrun */
+#define ATMEL_I2SC_MR_TXSAME_MASK	GENMASK(14, 14)
+#define ATMEL_I2SC_MR_TXSAME_ZERO	(0 << 14)  /* Zero sample */
+#define ATMEL_I2SC_MR_TXSAME_PREVIOUS	(1 << 14)  /* Previous sample */
+
+/* Audio Clock to I2SC Master Clock ratio */
+#define ATMEL_I2SC_MR_IMCKDIV_MASK	GENMASK(21, 16)
+#define ATMEL_I2SC_MR_IMCKDIV(div) \
+	(((div) << 16) & ATMEL_I2SC_MR_IMCKDIV_MASK)
+
+/* Master Clock to fs ratio */
+#define ATMEL_I2SC_MR_IMCKFS_MASK	GENMASK(29, 24)
+#define ATMEL_I2SC_MR_IMCKFS(fs) \
+	(((fs) << 24) & ATMEL_I2SC_MR_IMCKFS_MASK)
+
+/* Master Clock mode */
+#define ATMEL_I2SC_MR_IMCKMODE_MASK	GENMASK(30, 30)
+/* 0: No master clock generated (selected clock drives I2SCK pin) */
+#define ATMEL_I2SC_MR_IMCKMODE_I2SCK	(0 << 30)
+/* 1: master clock generated (internally generated clock drives I2SMCK pin) */
+#define ATMEL_I2SC_MR_IMCKMODE_I2SMCK	(1 << 30)
+
+/* Slot Width */
+/* 0: slot is 32 bits wide for DATALENGTH = 18/20/24 bits. */
+/* 1: slot is 24 bits wide for DATALENGTH = 18/20/24 bits. */
+#define ATMEL_I2SC_MR_IWS		BIT(31)
+
+/*
+ * ---- Status Registers ----
+ */
+#define ATMEL_I2SC_SR_RXEN	BIT(0)	/* Receiver Enabled */
+#define ATMEL_I2SC_SR_RXRDY	BIT(1)	/* Receive Ready */
+#define ATMEL_I2SC_SR_RXOR	BIT(2)	/* Receive Overrun */
+
+#define ATMEL_I2SC_SR_TXEN	BIT(4)	/* Transmitter Enabled */
+#define ATMEL_I2SC_SR_TXRDY	BIT(5)	/* Transmit Ready */
+#define ATMEL_I2SC_SR_TXUR	BIT(6)	/* Transmit Underrun */
+
+/* Receive Overrun Channel */
+#define ATMEL_I2SC_SR_RXORCH_MASK	GENMASK(15, 8)
+#define ATMEL_I2SC_SR_RXORCH(ch)	(1 << (((ch) & 0x7) + 8))
+
+/* Transmit Underrun Channel */
+#define ATMEL_I2SC_SR_TXURCH_MASK	GENMASK(27, 20)
+#define ATMEL_I2SC_SR_TXURCH(ch)	(1 << (((ch) & 0x7) + 20))
+
+/*
+ * ---- Interrupt Enable/Disable/Mask Registers ----
+ */
+#define ATMEL_I2SC_INT_RXRDY	ATMEL_I2SC_SR_RXRDY
+#define ATMEL_I2SC_INT_RXOR	ATMEL_I2SC_SR_RXOR
+#define ATMEL_I2SC_INT_TXRDY	ATMEL_I2SC_SR_TXRDY
+#define ATMEL_I2SC_INT_TXUR	ATMEL_I2SC_SR_TXUR
+
+static const struct regmap_config atmel_i2s_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = ATMEL_I2SC_VERSION,
+};
+
+struct atmel_i2s_gck_param {
+	int		fs;
+	unsigned long	mck;
+	int		imckdiv;
+	int		imckfs;
+};
+
+#define I2S_MCK_12M288		12288000UL
+#define I2S_MCK_11M2896		11289600UL
+
+/* mck = (32 * (imckfs+1) / (imckdiv+1)) * fs */
+static const struct atmel_i2s_gck_param gck_params[] = {
+	/* mck = 12.288MHz */
+	{  8000, I2S_MCK_12M288, 0, 47},	/* mck = 1536 fs */
+	{ 16000, I2S_MCK_12M288, 1, 47},	/* mck =  768 fs */
+	{ 24000, I2S_MCK_12M288, 3, 63},	/* mck =  512 fs */
+	{ 32000, I2S_MCK_12M288, 3, 47},	/* mck =  384 fs */
+	{ 48000, I2S_MCK_12M288, 7, 63},	/* mck =  256 fs */
+	{ 64000, I2S_MCK_12M288, 7, 47},	/* mck =  192 fs */
+	{ 96000, I2S_MCK_12M288, 7, 31},	/* mck =  128 fs */
+	{192000, I2S_MCK_12M288, 7, 15},	/* mck =   64 fs */
+
+	/* mck = 11.2896MHz */
+	{ 11025, I2S_MCK_11M2896, 1, 63},	/* mck = 1024 fs */
+	{ 22050, I2S_MCK_11M2896, 3, 63},	/* mck =  512 fs */
+	{ 44100, I2S_MCK_11M2896, 7, 63},	/* mck =  256 fs */
+	{ 88200, I2S_MCK_11M2896, 7, 31},	/* mck =  128 fs */
+	{176400, I2S_MCK_11M2896, 7, 15},	/* mck =   64 fs */
+};
+
+struct atmel_i2s_dev;
+
+struct atmel_i2s_caps {
+	int	(*mck_init)(struct atmel_i2s_dev *, struct device_node *np);
+};
+
+struct atmel_i2s_dev {
+	struct device				*dev;
+	struct regmap				*regmap;
+	struct clk				*pclk;
+	struct clk				*gclk;
+	struct clk				*aclk;
+	struct snd_dmaengine_dai_dma_data	playback;
+	struct snd_dmaengine_dai_dma_data	capture;
+	unsigned int				fmt;
+	const struct atmel_i2s_gck_param	*gck_param;
+	const struct atmel_i2s_caps		*caps;
+};
+
+static irqreturn_t atmel_i2s_interrupt(int irq, void *dev_id)
+{
+	struct atmel_i2s_dev *dev = dev_id;
+	unsigned int sr, imr, pending, ch, mask;
+	irqreturn_t ret = IRQ_NONE;
+
+	regmap_read(dev->regmap, ATMEL_I2SC_SR, &sr);
+	regmap_read(dev->regmap, ATMEL_I2SC_IMR, &imr);
+	pending = sr & imr;
+
+	if (!pending)
+		return IRQ_NONE;
+
+	if (pending & ATMEL_I2SC_INT_RXOR) {
+		mask = ATMEL_I2SC_SR_RXOR;
+
+		for (ch = 0; ch < ATMEL_I2SC_MAX_TDM_CHANNELS; ++ch) {
+			if (sr & ATMEL_I2SC_SR_RXORCH(ch)) {
+				mask |= ATMEL_I2SC_SR_RXORCH(ch);
+				dev_err(dev->dev,
+					"RX overrun on channel %d\n", ch);
+			}
+		}
+		regmap_write(dev->regmap, ATMEL_I2SC_SCR, mask);
+		ret = IRQ_HANDLED;
+	}
+
+	if (pending & ATMEL_I2SC_INT_TXUR) {
+		mask = ATMEL_I2SC_SR_TXUR;
+
+		for (ch = 0; ch < ATMEL_I2SC_MAX_TDM_CHANNELS; ++ch) {
+			if (sr & ATMEL_I2SC_SR_TXURCH(ch)) {
+				mask |= ATMEL_I2SC_SR_TXURCH(ch);
+				dev_err(dev->dev,
+					"TX underrun on channel %d\n", ch);
+			}
+		}
+		regmap_write(dev->regmap, ATMEL_I2SC_SCR, mask);
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+#define ATMEL_I2S_RATES		SNDRV_PCM_RATE_8000_192000
+
+#define ATMEL_I2S_FORMATS	(SNDRV_PCM_FMTBIT_S8 |		\
+				 SNDRV_PCM_FMTBIT_S16_LE |	\
+				 SNDRV_PCM_FMTBIT_S18_3LE |	\
+				 SNDRV_PCM_FMTBIT_S20_3LE |	\
+				 SNDRV_PCM_FMTBIT_S24_3LE |	\
+				 SNDRV_PCM_FMTBIT_S24_LE |	\
+				 SNDRV_PCM_FMTBIT_S32_LE)
+
+static int atmel_i2s_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct atmel_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+
+	dev->fmt = fmt;
+	return 0;
+}
+
+static int atmel_i2s_prepare(struct snd_pcm_substream *substream,
+			     struct snd_soc_dai *dai)
+{
+	struct atmel_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+	bool is_playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	unsigned int rhr, sr = 0;
+
+	if (is_playback) {
+		regmap_read(dev->regmap, ATMEL_I2SC_SR, &sr);
+		if (sr & ATMEL_I2SC_SR_RXRDY) {
+			/*
+			 * The RX Ready flag should not be set. However if here,
+			 * we flush (read) the Receive Holding Register to start
+			 * from a clean state.
+			 */
+			dev_dbg(dev->dev, "RXRDY is set\n");
+			regmap_read(dev->regmap, ATMEL_I2SC_RHR, &rhr);
+		}
+	}
+
+	return 0;
+}
+
+static int atmel_i2s_get_gck_param(struct atmel_i2s_dev *dev, int fs)
+{
+	int i, best;
+
+	if (!dev->gclk || !dev->aclk) {
+		dev_err(dev->dev, "cannot generate the I2S Master Clock\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Find the best possible settings to generate the I2S Master Clock
+	 * from the PLL Audio.
+	 */
+	dev->gck_param = NULL;
+	best = INT_MAX;
+	for (i = 0; i < ARRAY_SIZE(gck_params); ++i) {
+		const struct atmel_i2s_gck_param *gck_param = &gck_params[i];
+		int val = abs(fs - gck_param->fs);
+
+		if (val < best) {
+			best = val;
+			dev->gck_param = gck_param;
+		}
+	}
+
+	return 0;
+}
+
+static int atmel_i2s_hw_params(struct snd_pcm_substream *substream,
+			       struct snd_pcm_hw_params *params,
+			       struct snd_soc_dai *dai)
+{
+	struct atmel_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+	bool is_playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	unsigned int mr = 0;
+	int ret;
+
+	switch (dev->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		mr |= ATMEL_I2SC_MR_FORMAT_I2S;
+		break;
+
+	default:
+		dev_err(dev->dev, "unsupported bus format\n");
+		return -EINVAL;
+	}
+
+	switch (dev->fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		/* codec is slave, so cpu is master */
+		mr |= ATMEL_I2SC_MR_MODE_MASTER;
+		ret = atmel_i2s_get_gck_param(dev, params_rate(params));
+		if (ret)
+			return ret;
+		break;
+
+	case SND_SOC_DAIFMT_CBM_CFM:
+		/* codec is master, so cpu is slave */
+		mr |= ATMEL_I2SC_MR_MODE_SLAVE;
+		dev->gck_param = NULL;
+		break;
+
+	default:
+		dev_err(dev->dev, "unsupported master/slave mode\n");
+		return -EINVAL;
+	}
+
+	switch (params_channels(params)) {
+	case 1:
+		if (is_playback)
+			mr |= ATMEL_I2SC_MR_TXMONO;
+		else
+			mr |= ATMEL_I2SC_MR_RXMONO;
+		break;
+	case 2:
+		break;
+	default:
+		dev_err(dev->dev, "unsupported number of audio channels\n");
+		return -EINVAL;
+	}
+
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S8:
+		mr |= ATMEL_I2SC_MR_DATALENGTH_8_BITS;
+		break;
+
+	case SNDRV_PCM_FORMAT_S16_LE:
+		mr |= ATMEL_I2SC_MR_DATALENGTH_16_BITS;
+		break;
+
+	case SNDRV_PCM_FORMAT_S18_3LE:
+		mr |= ATMEL_I2SC_MR_DATALENGTH_18_BITS | ATMEL_I2SC_MR_IWS;
+		break;
+
+	case SNDRV_PCM_FORMAT_S20_3LE:
+		mr |= ATMEL_I2SC_MR_DATALENGTH_20_BITS | ATMEL_I2SC_MR_IWS;
+		break;
+
+	case SNDRV_PCM_FORMAT_S24_3LE:
+		mr |= ATMEL_I2SC_MR_DATALENGTH_24_BITS | ATMEL_I2SC_MR_IWS;
+		break;
+
+	case SNDRV_PCM_FORMAT_S24_LE:
+		mr |= ATMEL_I2SC_MR_DATALENGTH_24_BITS;
+		break;
+
+	case SNDRV_PCM_FORMAT_S32_LE:
+		mr |= ATMEL_I2SC_MR_DATALENGTH_32_BITS;
+		break;
+
+	default:
+		dev_err(dev->dev, "unsupported size/endianness for audio samples\n");
+		return -EINVAL;
+	}
+
+	return regmap_write(dev->regmap, ATMEL_I2SC_MR, mr);
+}
+
+static int atmel_i2s_switch_mck_generator(struct atmel_i2s_dev *dev,
+					  bool enabled)
+{
+	unsigned int mr, mr_mask;
+	unsigned long aclk_rate;
+	int ret;
+
+	mr = 0;
+	mr_mask = (ATMEL_I2SC_MR_IMCKDIV_MASK |
+		   ATMEL_I2SC_MR_IMCKFS_MASK |
+		   ATMEL_I2SC_MR_IMCKMODE_MASK);
+
+	if (!enabled) {
+		/* Disable the I2S Master Clock generator. */
+		ret = regmap_write(dev->regmap, ATMEL_I2SC_CR,
+				   ATMEL_I2SC_CR_CKDIS);
+		if (ret)
+			return ret;
+
+		/* Reset the I2S Master Clock generator settings. */
+		ret = regmap_update_bits(dev->regmap, ATMEL_I2SC_MR,
+					 mr_mask, mr);
+		if (ret)
+			return ret;
+
+		/* Disable/unprepare the PMC generated clock. */
+		clk_disable_unprepare(dev->gclk);
+
+		/* Disable/unprepare the PLL audio clock. */
+		clk_disable_unprepare(dev->aclk);
+		return 0;
+	}
+
+	if (!dev->gck_param)
+		return -EINVAL;
+
+	aclk_rate = dev->gck_param->mck * (dev->gck_param->imckdiv + 1);
+
+	/* Fist change the PLL audio clock frequency ... */
+	ret = clk_set_rate(dev->aclk, aclk_rate);
+	if (ret)
+		return ret;
+
+	/*
+	 * ... then set the PMC generated clock rate to the very same frequency
+	 * to set the gclk parent to aclk.
+	 */
+	ret = clk_set_rate(dev->gclk, aclk_rate);
+	if (ret)
+		return ret;
+
+	/* Prepare and enable the PLL audio clock first ... */
+	ret = clk_prepare_enable(dev->aclk);
+	if (ret)
+		return ret;
+
+	/* ... then prepare and enable the PMC generated clock. */
+	ret = clk_prepare_enable(dev->gclk);
+	if (ret)
+		return ret;
+
+	/* Update the Mode Register to generate the I2S Master Clock. */
+	mr |= ATMEL_I2SC_MR_IMCKDIV(dev->gck_param->imckdiv);
+	mr |= ATMEL_I2SC_MR_IMCKFS(dev->gck_param->imckfs);
+	mr |= ATMEL_I2SC_MR_IMCKMODE_I2SMCK;
+	ret = regmap_update_bits(dev->regmap, ATMEL_I2SC_MR, mr_mask, mr);
+	if (ret)
+		return ret;
+
+	/* Finally enable the I2S Master Clock generator. */
+	return regmap_write(dev->regmap, ATMEL_I2SC_CR,
+			    ATMEL_I2SC_CR_CKEN);
+}
+
+static int atmel_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
+			     struct snd_soc_dai *dai)
+{
+	struct atmel_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+	bool is_playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	bool is_master, mck_enabled;
+	unsigned int cr, mr;
+	int err;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		cr = is_playback ? ATMEL_I2SC_CR_TXEN : ATMEL_I2SC_CR_RXEN;
+		mck_enabled = true;
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		cr = is_playback ? ATMEL_I2SC_CR_TXDIS : ATMEL_I2SC_CR_RXDIS;
+		mck_enabled = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Read the Mode Register to retrieve the master/slave state. */
+	err = regmap_read(dev->regmap, ATMEL_I2SC_MR, &mr);
+	if (err)
+		return err;
+	is_master = (mr & ATMEL_I2SC_MR_MODE_MASK) == ATMEL_I2SC_MR_MODE_MASTER;
+
+	/* If master starts, enable the audio clock. */
+	if (is_master && mck_enabled)
+		err = atmel_i2s_switch_mck_generator(dev, true);
+	if (err)
+		return err;
+
+	err = regmap_write(dev->regmap, ATMEL_I2SC_CR, cr);
+	if (err)
+		return err;
+
+	/* If master stops, disable the audio clock. */
+	if (is_master && !mck_enabled)
+		err = atmel_i2s_switch_mck_generator(dev, false);
+
+	return err;
+}
+
+static const struct snd_soc_dai_ops atmel_i2s_dai_ops = {
+	.prepare	= atmel_i2s_prepare,
+	.trigger	= atmel_i2s_trigger,
+	.hw_params	= atmel_i2s_hw_params,
+	.set_fmt	= atmel_i2s_set_dai_fmt,
+};
+
+static int atmel_i2s_dai_probe(struct snd_soc_dai *dai)
+{
+	struct atmel_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+
+	snd_soc_dai_init_dma_data(dai, &dev->playback, &dev->capture);
+	return 0;
+}
+
+static struct snd_soc_dai_driver atmel_i2s_dai = {
+	.probe	= atmel_i2s_dai_probe,
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 2,
+		.rates = ATMEL_I2S_RATES,
+		.formats = ATMEL_I2S_FORMATS,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 2,
+		.rates = ATMEL_I2S_RATES,
+		.formats = ATMEL_I2S_FORMATS,
+	},
+	.ops = &atmel_i2s_dai_ops,
+	.symmetric_rates = 1,
+};
+
+static const struct snd_soc_component_driver atmel_i2s_component = {
+	.name	= "atmel-i2s",
+};
+
+static int atmel_i2s_sama5d2_mck_init(struct atmel_i2s_dev *dev,
+				      struct device_node *np)
+{
+	struct clk *muxclk;
+	int err;
+
+	if (!dev->gclk)
+		return 0;
+
+	/* muxclk is optional, so we return error for probe defer only */
+	muxclk = devm_clk_get(dev->dev, "muxclk");
+	if (IS_ERR(muxclk)) {
+		err = PTR_ERR(muxclk);
+		if (err == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_warn(dev->dev,
+			 "failed to get the I2S clock control: %d\n", err);
+		return 0;
+	}
+
+	return clk_set_parent(muxclk, dev->gclk);
+}
+
+static const struct atmel_i2s_caps atmel_i2s_sama5d2_caps = {
+	.mck_init = atmel_i2s_sama5d2_mck_init,
+};
+
+static const struct of_device_id atmel_i2s_dt_ids[] = {
+	{
+		.compatible = "atmel,sama5d2-i2s",
+		.data = (void *)&atmel_i2s_sama5d2_caps,
+	},
+
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(of, atmel_i2s_dt_ids);
+
+static int atmel_i2s_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const struct of_device_id *match;
+	struct atmel_i2s_dev *dev;
+	struct resource *mem;
+	struct regmap *regmap;
+	void __iomem *base;
+	int irq;
+	int err = -ENXIO;
+	unsigned int pcm_flags = 0;
+	unsigned int version;
+
+	/* Get memory for driver data. */
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	/* Get hardware capabilities. */
+	match = of_match_node(atmel_i2s_dt_ids, np);
+	if (match)
+		dev->caps = match->data;
+
+	/* Map I/O registers. */
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	regmap = devm_regmap_init_mmio(&pdev->dev, base,
+				       &atmel_i2s_regmap_config);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/* Request IRQ. */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	err = devm_request_irq(&pdev->dev, irq, atmel_i2s_interrupt, 0,
+			       dev_name(&pdev->dev), dev);
+	if (err)
+		return err;
+
+	/* Get the peripheral clock. */
+	dev->pclk = devm_clk_get(&pdev->dev, "pclk");
+	if (IS_ERR(dev->pclk)) {
+		err = PTR_ERR(dev->pclk);
+		dev_err(&pdev->dev,
+			"failed to get the peripheral clock: %d\n", err);
+		return err;
+	}
+
+	/* Get audio clocks to generate the I2S Master Clock (I2S_MCK) */
+	dev->aclk = devm_clk_get(&pdev->dev, "aclk");
+	dev->gclk = devm_clk_get(&pdev->dev, "gclk");
+	if (IS_ERR(dev->aclk) && IS_ERR(dev->gclk)) {
+		if (PTR_ERR(dev->aclk) == -EPROBE_DEFER ||
+		    PTR_ERR(dev->gclk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		/* Master Mode not supported */
+		dev->aclk = NULL;
+		dev->gclk = NULL;
+	} else if (IS_ERR(dev->gclk)) {
+		err = PTR_ERR(dev->gclk);
+		dev_err(&pdev->dev,
+			"failed to get the PMC generated clock: %d\n", err);
+		return err;
+	} else if (IS_ERR(dev->aclk)) {
+		err = PTR_ERR(dev->aclk);
+		dev_err(&pdev->dev,
+			"failed to get the PLL audio clock: %d\n", err);
+		return err;
+	}
+
+	dev->dev = &pdev->dev;
+	dev->regmap = regmap;
+	platform_set_drvdata(pdev, dev);
+
+	/* Do hardware specific settings to initialize I2S_MCK generator */
+	if (dev->caps && dev->caps->mck_init) {
+		err = dev->caps->mck_init(dev, np);
+		if (err)
+			return err;
+	}
+
+	/* Enable the peripheral clock. */
+	err = clk_prepare_enable(dev->pclk);
+	if (err)
+		return err;
+
+	/* Get IP version. */
+	regmap_read(dev->regmap, ATMEL_I2SC_VERSION, &version);
+	dev_info(&pdev->dev, "hw version: %#x\n", version);
+
+	/* Enable error interrupts. */
+	regmap_write(dev->regmap, ATMEL_I2SC_IER,
+		     ATMEL_I2SC_INT_RXOR | ATMEL_I2SC_INT_TXUR);
+
+	err = devm_snd_soc_register_component(&pdev->dev,
+					      &atmel_i2s_component,
+					      &atmel_i2s_dai, 1);
+	if (err) {
+		dev_err(&pdev->dev, "failed to register DAI: %d\n", err);
+		clk_disable_unprepare(dev->pclk);
+		return err;
+	}
+
+	/* Prepare DMA config. */
+	dev->playback.addr	= (dma_addr_t)mem->start + ATMEL_I2SC_THR;
+	dev->playback.maxburst	= 1;
+	dev->capture.addr	= (dma_addr_t)mem->start + ATMEL_I2SC_RHR;
+	dev->capture.maxburst	= 1;
+
+	if (of_property_match_string(np, "dma-names", "rx-tx") == 0)
+		pcm_flags |= SND_DMAENGINE_PCM_FLAG_HALF_DUPLEX;
+	err = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, pcm_flags);
+	if (err) {
+		dev_err(&pdev->dev, "failed to register PCM: %d\n", err);
+		clk_disable_unprepare(dev->pclk);
+		return err;
+	}
+
+	return 0;
+}
+
+static int atmel_i2s_remove(struct platform_device *pdev)
+{
+	struct atmel_i2s_dev *dev = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(dev->pclk);
+
+	return 0;
+}
+
+static struct platform_driver atmel_i2s_driver = {
+	.driver		= {
+		.name	= "atmel_i2s",
+		.of_match_table	= of_match_ptr(atmel_i2s_dt_ids),
+	},
+	.probe		= atmel_i2s_probe,
+	.remove		= atmel_i2s_remove,
+};
+module_platform_driver(atmel_i2s_driver);
+
+MODULE_DESCRIPTION("Atmel I2S Controller driver");
+MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@atmel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index a1e2c5682dcd..d3b69682d9c2 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -820,7 +820,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 		if (ret < 0) {
 			printk(KERN_WARNING
 					"atmel_ssc_dai: request_irq failure\n");
-			pr_debug("Atmel_ssc_dai: Stoping clock\n");
+			pr_debug("Atmel_ssc_dai: Stopping clock\n");
 			clk_disable(ssc_p->ssc->clk);
 			return ret;
 		}
@@ -1002,8 +1002,7 @@ static const struct snd_soc_component_driver atmel_ssc_component = {
 
 static int asoc_ssc_init(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct ssc_device *ssc = platform_get_drvdata(pdev);
+	struct ssc_device *ssc = dev_get_drvdata(dev);
 	int ret;
 
 	ret = snd_soc_register_component(dev, &atmel_ssc_component,
@@ -1033,8 +1032,7 @@ err:
 
 static void asoc_ssc_exit(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct ssc_device *ssc = platform_get_drvdata(pdev);
+	struct ssc_device *ssc = dev_get_drvdata(dev);
 
 	if (ssc->pdata->use_dma)
 		atmel_pcm_dma_platform_unregister(dev);
diff --git a/sound/soc/bcm/Kconfig b/sound/soc/bcm/Kconfig
index edf367100ebd..02f50b7a966f 100644
--- a/sound/soc/bcm/Kconfig
+++ b/sound/soc/bcm/Kconfig
@@ -11,9 +11,8 @@ config SND_BCM2835_SOC_I2S
 config SND_SOC_CYGNUS
 	tristate "SoC platform audio for Broadcom Cygnus chips"
 	depends on ARCH_BCM_CYGNUS || COMPILE_TEST
-	depends on HAS_DMA
 	help
 	  Say Y if you want to add support for ASoC audio on Broadcom
 	  Cygnus chips (bcm958300, bcm958305, bcm911360)
 
-	  If you don't know what to do here, say N.
\ No newline at end of file
+	  If you don't know what to do here, say N.
diff --git a/sound/soc/cirrus/Kconfig b/sound/soc/cirrus/Kconfig
index c7cd60f009e9..e09199124c36 100644
--- a/sound/soc/cirrus/Kconfig
+++ b/sound/soc/cirrus/Kconfig
@@ -9,6 +9,23 @@ config SND_EP93XX_SOC
 config SND_EP93XX_SOC_I2S
 	tristate
 
+if SND_EP93XX_SOC_I2S
+
+config SND_EP93XX_SOC_I2S_WATCHDOG
+	bool "IRQ based underflow watchdog workaround"
+	default y
+	help
+	  I2S controller on EP93xx seems to have undocumented HW issue.
+	  Underflow of internal I2S controller FIFO could confuse the
+	  state machine and the whole stream can be shifted by one byte
+	  until I2S is disabled. This option enables IRQ based watchdog
+	  which disables and re-enables I2S in case of underflow and
+	  fills FIFO with zeroes.
+
+	  If you are unsure how to answer this question, answer Y.
+
+endif # if SND_EP93XX_SOC_I2S
+
 config SND_EP93XX_SOC_AC97
 	tristate
 	select AC97_BUS
diff --git a/sound/soc/cirrus/edb93xx.c b/sound/soc/cirrus/edb93xx.c
index c53bd6f2c2d7..3d011abaa266 100644
--- a/sound/soc/cirrus/edb93xx.c
+++ b/sound/soc/cirrus/edb93xx.c
@@ -67,7 +67,7 @@ static struct snd_soc_dai_link edb93xx_dai = {
 	.cpu_dai_name	= "ep93xx-i2s",
 	.codec_name	= "spi0.0",
 	.codec_dai_name	= "cs4271-hifi",
-	.dai_fmt	= SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_IF |
+	.dai_fmt	= SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
 			  SND_SOC_DAIFMT_CBS_CFS,
 	.ops		= &edb93xx_ops,
 };
diff --git a/sound/soc/cirrus/ep93xx-i2s.c b/sound/soc/cirrus/ep93xx-i2s.c
index 934f8aefdd90..0918c5da575a 100644
--- a/sound/soc/cirrus/ep93xx-i2s.c
+++ b/sound/soc/cirrus/ep93xx-i2s.c
@@ -35,8 +35,12 @@
 
 #define EP93XX_I2S_TXCLKCFG		0x00
 #define EP93XX_I2S_RXCLKCFG		0x04
+#define EP93XX_I2S_GLSTS		0x08
 #define EP93XX_I2S_GLCTRL		0x0C
 
+#define EP93XX_I2S_I2STX0LFT		0x10
+#define EP93XX_I2S_I2STX0RT		0x14
+
 #define EP93XX_I2S_TXLINCTRLDATA	0x28
 #define EP93XX_I2S_TXCTRL		0x2C
 #define EP93XX_I2S_TXWRDLEN		0x30
@@ -51,7 +55,17 @@
 #define EP93XX_I2S_WRDLEN_24		(1 << 0)
 #define EP93XX_I2S_WRDLEN_32		(2 << 0)
 
-#define EP93XX_I2S_LINCTRLDATA_R_JUST	(1 << 2) /* Right justify */
+#define EP93XX_I2S_RXLINCTRLDATA_R_JUST	BIT(1) /* Right justify */
+
+#define EP93XX_I2S_TXLINCTRLDATA_R_JUST	BIT(2) /* Right justify */
+
+/*
+ * Transmit empty interrupt level select:
+ * 0 - Generate interrupt when FIFO is half empty
+ * 1 - Generate interrupt when FIFO is empty
+ */
+#define EP93XX_I2S_TXCTRL_TXEMPTY_LVL	BIT(0)
+#define EP93XX_I2S_TXCTRL_TXUFIE	BIT(1) /* Transmit interrupt enable */
 
 #define EP93XX_I2S_CLKCFG_LRS		(1 << 0) /* lrclk polarity */
 #define EP93XX_I2S_CLKCFG_CKP		(1 << 1) /* Bit clock polarity */
@@ -59,6 +73,8 @@
 #define EP93XX_I2S_CLKCFG_MASTER	(1 << 3) /* Master mode */
 #define EP93XX_I2S_CLKCFG_NBCG		(1 << 4) /* Not bit clock gating */
 
+#define EP93XX_I2S_GLSTS_TX0_FIFO_FULL	BIT(12)
+
 struct ep93xx_i2s_info {
 	struct clk			*mclk;
 	struct clk			*sclk;
@@ -96,7 +112,6 @@ static inline unsigned ep93xx_i2s_read_reg(struct ep93xx_i2s_info *info,
 static void ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream)
 {
 	unsigned base_reg;
-	int i;
 
 	if ((ep93xx_i2s_read_reg(info, EP93XX_I2S_TX0EN) & 0x1) == 0 &&
 	    (ep93xx_i2s_read_reg(info, EP93XX_I2S_RX0EN) & 0x1) == 0) {
@@ -109,27 +124,36 @@ static void ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream)
 		ep93xx_i2s_write_reg(info, EP93XX_I2S_GLCTRL, 1);
 	}
 
-	/* Enable fifos */
+	/* Enable fifo */
 	if (stream == SNDRV_PCM_STREAM_PLAYBACK)
 		base_reg = EP93XX_I2S_TX0EN;
 	else
 		base_reg = EP93XX_I2S_RX0EN;
-	for (i = 0; i < 3; i++)
-		ep93xx_i2s_write_reg(info, base_reg + (i * 4), 1);
+	ep93xx_i2s_write_reg(info, base_reg, 1);
+
+	/* Enable TX IRQs (FIFO empty or underflow) */
+	if (IS_ENABLED(CONFIG_SND_EP93XX_SOC_I2S_WATCHDOG) &&
+	    stream == SNDRV_PCM_STREAM_PLAYBACK)
+		ep93xx_i2s_write_reg(info, EP93XX_I2S_TXCTRL,
+				     EP93XX_I2S_TXCTRL_TXEMPTY_LVL |
+				     EP93XX_I2S_TXCTRL_TXUFIE);
 }
 
 static void ep93xx_i2s_disable(struct ep93xx_i2s_info *info, int stream)
 {
 	unsigned base_reg;
-	int i;
 
-	/* Disable fifos */
+	/* Disable IRQs */
+	if (IS_ENABLED(CONFIG_SND_EP93XX_SOC_I2S_WATCHDOG) &&
+	    stream == SNDRV_PCM_STREAM_PLAYBACK)
+		ep93xx_i2s_write_reg(info, EP93XX_I2S_TXCTRL, 0);
+
+	/* Disable fifo */
 	if (stream == SNDRV_PCM_STREAM_PLAYBACK)
 		base_reg = EP93XX_I2S_TX0EN;
 	else
 		base_reg = EP93XX_I2S_RX0EN;
-	for (i = 0; i < 3; i++)
-		ep93xx_i2s_write_reg(info, base_reg + (i * 4), 0);
+	ep93xx_i2s_write_reg(info, base_reg, 0);
 
 	if ((ep93xx_i2s_read_reg(info, EP93XX_I2S_TX0EN) & 0x1) == 0 &&
 	    (ep93xx_i2s_read_reg(info, EP93XX_I2S_RX0EN) & 0x1) == 0) {
@@ -143,6 +167,37 @@ static void ep93xx_i2s_disable(struct ep93xx_i2s_info *info, int stream)
 	}
 }
 
+/*
+ * According to documentation I2S controller can handle underflow conditions
+ * just fine, but in reality the state machine is sometimes confused so that
+ * the whole stream is shifted by one byte. The watchdog below disables the TX
+ * FIFO, fills the buffer with zeroes and re-enables the FIFO. State machine
+ * is being reset and by filling the buffer we get some time before next
+ * underflow happens.
+ */
+static irqreturn_t ep93xx_i2s_interrupt(int irq, void *dev_id)
+{
+	struct ep93xx_i2s_info *info = dev_id;
+
+	/* Disable FIFO */
+	ep93xx_i2s_write_reg(info, EP93XX_I2S_TX0EN, 0);
+	/*
+	 * Fill TX FIFO with zeroes, this way we can defer next IRQs as much as
+	 * possible and get more time for DMA to catch up. Actually there are
+	 * only 8 samples in this FIFO, so even on 8kHz maximum deferral here is
+	 * 1ms.
+	 */
+	while (!(ep93xx_i2s_read_reg(info, EP93XX_I2S_GLSTS) &
+		 EP93XX_I2S_GLSTS_TX0_FIFO_FULL)) {
+		ep93xx_i2s_write_reg(info, EP93XX_I2S_I2STX0LFT, 0);
+		ep93xx_i2s_write_reg(info, EP93XX_I2S_I2STX0RT, 0);
+	}
+	/* Re-enable FIFO */
+	ep93xx_i2s_write_reg(info, EP93XX_I2S_TX0EN, 1);
+
+	return IRQ_HANDLED;
+}
+
 static int ep93xx_i2s_dai_probe(struct snd_soc_dai *dai)
 {
 	struct ep93xx_i2s_info *info = snd_soc_dai_get_drvdata(dai);
@@ -170,25 +225,25 @@ static int ep93xx_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 				  unsigned int fmt)
 {
 	struct ep93xx_i2s_info *info = snd_soc_dai_get_drvdata(cpu_dai);
-	unsigned int clk_cfg, lin_ctrl;
+	unsigned int clk_cfg;
+	unsigned int txlin_ctrl = 0;
+	unsigned int rxlin_ctrl = 0;
 
 	clk_cfg  = ep93xx_i2s_read_reg(info, EP93XX_I2S_RXCLKCFG);
-	lin_ctrl = ep93xx_i2s_read_reg(info, EP93XX_I2S_RXLINCTRLDATA);
 
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		clk_cfg |= EP93XX_I2S_CLKCFG_REL;
-		lin_ctrl &= ~EP93XX_I2S_LINCTRLDATA_R_JUST;
 		break;
 
 	case SND_SOC_DAIFMT_LEFT_J:
 		clk_cfg &= ~EP93XX_I2S_CLKCFG_REL;
-		lin_ctrl &= ~EP93XX_I2S_LINCTRLDATA_R_JUST;
 		break;
 
 	case SND_SOC_DAIFMT_RIGHT_J:
 		clk_cfg &= ~EP93XX_I2S_CLKCFG_REL;
-		lin_ctrl |= EP93XX_I2S_LINCTRLDATA_R_JUST;
+		rxlin_ctrl |= EP93XX_I2S_RXLINCTRLDATA_R_JUST;
+		txlin_ctrl |= EP93XX_I2S_TXLINCTRLDATA_R_JUST;
 		break;
 
 	default:
@@ -213,32 +268,32 @@ static int ep93xx_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
 	case SND_SOC_DAIFMT_NB_NF:
 		/* Negative bit clock, lrclk low on left word */
-		clk_cfg &= ~(EP93XX_I2S_CLKCFG_CKP | EP93XX_I2S_CLKCFG_REL);
+		clk_cfg &= ~(EP93XX_I2S_CLKCFG_CKP | EP93XX_I2S_CLKCFG_LRS);
 		break;
 
 	case SND_SOC_DAIFMT_NB_IF:
 		/* Negative bit clock, lrclk low on right word */
 		clk_cfg &= ~EP93XX_I2S_CLKCFG_CKP;
-		clk_cfg |= EP93XX_I2S_CLKCFG_REL;
+		clk_cfg |= EP93XX_I2S_CLKCFG_LRS;
 		break;
 
 	case SND_SOC_DAIFMT_IB_NF:
 		/* Positive bit clock, lrclk low on left word */
 		clk_cfg |= EP93XX_I2S_CLKCFG_CKP;
-		clk_cfg &= ~EP93XX_I2S_CLKCFG_REL;
+		clk_cfg &= ~EP93XX_I2S_CLKCFG_LRS;
 		break;
 
 	case SND_SOC_DAIFMT_IB_IF:
 		/* Positive bit clock, lrclk low on right word */
-		clk_cfg |= EP93XX_I2S_CLKCFG_CKP | EP93XX_I2S_CLKCFG_REL;
+		clk_cfg |= EP93XX_I2S_CLKCFG_CKP | EP93XX_I2S_CLKCFG_LRS;
 		break;
 	}
 
 	/* Write new register values */
 	ep93xx_i2s_write_reg(info, EP93XX_I2S_RXCLKCFG, clk_cfg);
 	ep93xx_i2s_write_reg(info, EP93XX_I2S_TXCLKCFG, clk_cfg);
-	ep93xx_i2s_write_reg(info, EP93XX_I2S_RXLINCTRLDATA, lin_ctrl);
-	ep93xx_i2s_write_reg(info, EP93XX_I2S_TXLINCTRLDATA, lin_ctrl);
+	ep93xx_i2s_write_reg(info, EP93XX_I2S_RXLINCTRLDATA, rxlin_ctrl);
+	ep93xx_i2s_write_reg(info, EP93XX_I2S_TXLINCTRLDATA, txlin_ctrl);
 	return 0;
 }
 
@@ -392,6 +447,17 @@ static int ep93xx_i2s_probe(struct platform_device *pdev)
 	if (IS_ERR(info->regs))
 		return PTR_ERR(info->regs);
 
+	if (IS_ENABLED(CONFIG_SND_EP93XX_SOC_I2S_WATCHDOG)) {
+		int irq = platform_get_irq(pdev, 0);
+		if (irq <= 0)
+			return irq < 0 ? irq : -ENODEV;
+
+		err = devm_request_irq(&pdev->dev, irq, ep93xx_i2s_interrupt, 0,
+				       pdev->name, info);
+		if (err)
+			return err;
+	}
+
 	info->mclk = clk_get(&pdev->dev, "mclk");
 	if (IS_ERR(info->mclk)) {
 		err = PTR_ERR(info->mclk);
diff --git a/sound/soc/cirrus/snappercl15.c b/sound/soc/cirrus/snappercl15.c
index 2334ec19e7eb..11ff7b2672b2 100644
--- a/sound/soc/cirrus/snappercl15.c
+++ b/sound/soc/cirrus/snappercl15.c
@@ -72,7 +72,7 @@ static struct snd_soc_dai_link snappercl15_dai = {
 	.codec_dai_name	= "tlv320aic23-hifi",
 	.codec_name	= "tlv320aic23-codec.0-001a",
 	.platform_name	= "ep93xx-i2s",
-	.dai_fmt	= SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_IF |
+	.dai_fmt	= SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
 			  SND_SOC_DAIFMT_CBS_CFS,
 	.ops		= &snappercl15_ops,
 };
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 9548f63ca531..63cf62e9c9aa 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -106,6 +106,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_MAX9877 if I2C
 	select SND_SOC_MC13783 if MFD_MC13XXX
 	select SND_SOC_ML26124 if I2C
+	select SND_SOC_MT6351 if MTK_PMIC_WRAP
 	select SND_SOC_NAU8540 if I2C
 	select SND_SOC_NAU8810 if I2C
 	select SND_SOC_NAU8824 if I2C
@@ -126,6 +127,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_RT274 if I2C
 	select SND_SOC_RT286 if I2C
 	select SND_SOC_RT298 if I2C
+	select SND_SOC_RT1305 if I2C
 	select SND_SOC_RT5514 if I2C
 	select SND_SOC_RT5616 if I2C
 	select SND_SOC_RT5631 if I2C
@@ -136,12 +138,14 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_RT5660 if I2C
 	select SND_SOC_RT5663 if I2C
 	select SND_SOC_RT5665 if I2C
+	select SND_SOC_RT5668 if I2C
 	select SND_SOC_RT5670 if I2C
 	select SND_SOC_RT5677 if I2C && SPI_MASTER
 	select SND_SOC_SGTL5000 if I2C
 	select SND_SOC_SI476X if MFD_SI476X_CORE
 	select SND_SOC_SIRF_AUDIO_CODEC
 	select SND_SOC_SPDIF
+	select SND_SOC_SSM2305
 	select SND_SOC_SSM2518 if I2C
 	select SND_SOC_SSM2602_SPI if SPI_MASTER
 	select SND_SOC_SSM2602_I2C if I2C
@@ -168,6 +172,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_TPA6130A2 if I2C
 	select SND_SOC_TLV320DAC33 if I2C
 	select SND_SOC_TSCS42XX if I2C
+	select SND_SOC_TSCS454 if I2C
 	select SND_SOC_TS3A227E if I2C
 	select SND_SOC_TWL4030 if TWL4030_CORE
 	select SND_SOC_TWL6040 if TWL6040_CORE
@@ -770,8 +775,10 @@ config SND_SOC_RL6231
 	default y if SND_SOC_RT5660=y
 	default y if SND_SOC_RT5663=y
 	default y if SND_SOC_RT5665=y
+	default y if SND_SOC_RT5668=y
 	default y if SND_SOC_RT5670=y
 	default y if SND_SOC_RT5677=y
+	default y if SND_SOC_RT1305=y
 	default m if SND_SOC_RT5514=m
 	default m if SND_SOC_RT5616=m
 	default m if SND_SOC_RT5640=m
@@ -781,8 +788,10 @@ config SND_SOC_RL6231
 	default m if SND_SOC_RT5660=m
 	default m if SND_SOC_RT5663=m
 	default m if SND_SOC_RT5665=m
+	default m if SND_SOC_RT5668=m
 	default m if SND_SOC_RT5670=m
 	default m if SND_SOC_RT5677=m
+	default m if SND_SOC_RT1305=m
 
 config SND_SOC_RL6347A
 	tristate
@@ -805,6 +814,9 @@ config SND_SOC_RT298
 	tristate
 	depends on I2C
 
+config SND_SOC_RT1305
+	tristate
+
 config SND_SOC_RT5514
 	tristate
 
@@ -844,6 +856,9 @@ config SND_SOC_RT5663
 config SND_SOC_RT5665
 	tristate
 
+config SND_SOC_RT5668
+	tristate
+
 config SND_SOC_RT5670
 	tristate
 
@@ -883,6 +898,12 @@ config SND_SOC_SIRF_AUDIO_CODEC
 config SND_SOC_SPDIF
 	tristate "S/PDIF CODEC"
 
+config SND_SOC_SSM2305
+	tristate "Analog Devices SSM2305 Class-D Amplifier"
+	help
+	  Enable support for Analog Devices SSM2305 filterless
+	  high-efficiency mono Class-D audio power amplifiers.
+
 config SND_SOC_SSM2518
 	tristate
 
@@ -1011,6 +1032,13 @@ config SND_SOC_TSCS42XX
 	help
 	  Add support for Tempo Semiconductor's TSCS42xx audio CODEC.
 
+config SND_SOC_TSCS454
+	tristate "Tempo Semiconductor TSCS454 CODEC"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  Add support for Tempo Semiconductor's TSCS454 audio CODEC.
+
 config SND_SOC_TWL4030
 	select MFD_TWL4030_AUDIO
 	tristate
@@ -1111,7 +1139,7 @@ config SND_SOC_WM8776
 	depends on SND_SOC_I2C_AND_SPI
 
 config SND_SOC_WM8782
-	tristate
+	tristate "Wolfson Microelectronics WM8782 ADC"
 
 config SND_SOC_WM8804
 	tristate
@@ -1247,6 +1275,9 @@ config SND_SOC_MC13783
 config SND_SOC_ML26124
 	tristate
 
+config SND_SOC_MT6351
+	tristate "MediaTek MT6351 Codec"
+
 config SND_SOC_NAU8540
        tristate "Nuvoton Technology Corporation NAU85L40 CODEC"
        depends on I2C
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index e849d1495308..e023fdf85221 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -102,6 +102,7 @@ snd-soc-mc13783-objs := mc13783.o
 snd-soc-ml26124-objs := ml26124.o
 snd-soc-msm8916-analog-objs := msm8916-wcd-analog.o
 snd-soc-msm8916-digital-objs := msm8916-wcd-digital.o
+snd-soc-mt6351-objs := mt6351.o
 snd-soc-nau8540-objs := nau8540.o
 snd-soc-nau8810-objs := nau8810.o
 snd-soc-nau8824-objs := nau8824.o
@@ -126,6 +127,7 @@ snd-soc-pcm512x-i2c-objs := pcm512x-i2c.o
 snd-soc-pcm512x-spi-objs := pcm512x-spi.o
 snd-soc-rl6231-objs := rl6231.o
 snd-soc-rl6347a-objs := rl6347a.o
+snd-soc-rt1305-objs := rt1305.o
 snd-soc-rt274-objs := rt274.o
 snd-soc-rt286-objs := rt286.o
 snd-soc-rt298-objs := rt298.o
@@ -140,6 +142,7 @@ snd-soc-rt5659-objs := rt5659.o
 snd-soc-rt5660-objs := rt5660.o
 snd-soc-rt5663-objs := rt5663.o
 snd-soc-rt5665-objs := rt5665.o
+snd-soc-rt5668-objs := rt5668.o
 snd-soc-rt5670-objs := rt5670.o
 snd-soc-rt5677-objs := rt5677.o
 snd-soc-rt5677-spi-objs := rt5677-spi.o
@@ -153,6 +156,7 @@ snd-soc-si476x-objs := si476x.o
 snd-soc-sirf-audio-codec-objs := sirf-audio-codec.o
 snd-soc-spdif-tx-objs := spdif_transmitter.o
 snd-soc-spdif-rx-objs := spdif_receiver.o
+snd-soc-ssm2305-objs := ssm2305.o
 snd-soc-ssm2518-objs := ssm2518.o
 snd-soc-ssm2602-objs := ssm2602.o
 snd-soc-ssm2602-spi-objs := ssm2602-spi.o
@@ -180,6 +184,7 @@ snd-soc-tlv320aic32x4-spi-objs := tlv320aic32x4-spi.o
 snd-soc-tlv320aic3x-objs := tlv320aic3x.o
 snd-soc-tlv320dac33-objs := tlv320dac33.o
 snd-soc-tscs42xx-objs := tscs42xx.o
+snd-soc-tscs454-objs := tscs454.o
 snd-soc-ts3a227e-objs := ts3a227e.o
 snd-soc-twl4030-objs := twl4030.o
 snd-soc-twl6040-objs := twl6040.o
@@ -355,6 +360,7 @@ obj-$(CONFIG_SND_SOC_MC13783)	+= snd-soc-mc13783.o
 obj-$(CONFIG_SND_SOC_ML26124)	+= snd-soc-ml26124.o
 obj-$(CONFIG_SND_SOC_MSM8916_WCD_ANALOG) +=snd-soc-msm8916-analog.o
 obj-$(CONFIG_SND_SOC_MSM8916_WCD_DIGITAL) +=snd-soc-msm8916-digital.o
+obj-$(CONFIG_SND_SOC_MT6351)	+= snd-soc-mt6351.o
 obj-$(CONFIG_SND_SOC_NAU8540)   += snd-soc-nau8540.o
 obj-$(CONFIG_SND_SOC_NAU8810)   += snd-soc-nau8810.o
 obj-$(CONFIG_SND_SOC_NAU8824)   += snd-soc-nau8824.o
@@ -379,6 +385,7 @@ obj-$(CONFIG_SND_SOC_PCM512x_I2C)	+= snd-soc-pcm512x-i2c.o
 obj-$(CONFIG_SND_SOC_PCM512x_SPI)	+= snd-soc-pcm512x-spi.o
 obj-$(CONFIG_SND_SOC_RL6231)	+= snd-soc-rl6231.o
 obj-$(CONFIG_SND_SOC_RL6347A)	+= snd-soc-rl6347a.o
+obj-$(CONFIG_SND_SOC_RT1305)	+= snd-soc-rt1305.o
 obj-$(CONFIG_SND_SOC_RT274)	+= snd-soc-rt274.o
 obj-$(CONFIG_SND_SOC_RT286)	+= snd-soc-rt286.o
 obj-$(CONFIG_SND_SOC_RT298)	+= snd-soc-rt298.o
@@ -394,6 +401,7 @@ obj-$(CONFIG_SND_SOC_RT5659)	+= snd-soc-rt5659.o
 obj-$(CONFIG_SND_SOC_RT5660)	+= snd-soc-rt5660.o
 obj-$(CONFIG_SND_SOC_RT5663)	+= snd-soc-rt5663.o
 obj-$(CONFIG_SND_SOC_RT5665)	+= snd-soc-rt5665.o
+obj-$(CONFIG_SND_SOC_RT5668)	+= snd-soc-rt5668.o
 obj-$(CONFIG_SND_SOC_RT5670)	+= snd-soc-rt5670.o
 obj-$(CONFIG_SND_SOC_RT5677)	+= snd-soc-rt5677.o
 obj-$(CONFIG_SND_SOC_RT5677_SPI)	+= snd-soc-rt5677-spi.o
@@ -404,6 +412,7 @@ obj-$(CONFIG_SND_SOC_SIGMADSP_REGMAP)	+= snd-soc-sigmadsp-regmap.o
 obj-$(CONFIG_SND_SOC_SI476X)	+= snd-soc-si476x.o
 obj-$(CONFIG_SND_SOC_SPDIF)	+= snd-soc-spdif-rx.o snd-soc-spdif-tx.o
 obj-$(CONFIG_SND_SOC_SIRF_AUDIO_CODEC) += sirf-audio-codec.o
+obj-$(CONFIG_SND_SOC_SSM2305)	+= snd-soc-ssm2305.o
 obj-$(CONFIG_SND_SOC_SSM2518)	+= snd-soc-ssm2518.o
 obj-$(CONFIG_SND_SOC_SSM2602)	+= snd-soc-ssm2602.o
 obj-$(CONFIG_SND_SOC_SSM2602_SPI)	+= snd-soc-ssm2602-spi.o
@@ -432,6 +441,7 @@ obj-$(CONFIG_SND_SOC_TLV320AIC32X4_SPI)	+= snd-soc-tlv320aic32x4-spi.o
 obj-$(CONFIG_SND_SOC_TLV320AIC3X)	+= snd-soc-tlv320aic3x.o
 obj-$(CONFIG_SND_SOC_TLV320DAC33)	+= snd-soc-tlv320dac33.o
 obj-$(CONFIG_SND_SOC_TSCS42XX)	+= snd-soc-tscs42xx.o
+obj-$(CONFIG_SND_SOC_TSCS454)	+= snd-soc-tscs454.o
 obj-$(CONFIG_SND_SOC_TS3A227E)	+= snd-soc-ts3a227e.o
 obj-$(CONFIG_SND_SOC_TWL4030)	+= snd-soc-twl4030.o
 obj-$(CONFIG_SND_SOC_TWL6040)	+= snd-soc-twl6040.o
diff --git a/sound/soc/codecs/adau17x1.c b/sound/soc/codecs/adau17x1.c
index 80c2a06285bb..ae41edd1c406 100644
--- a/sound/soc/codecs/adau17x1.c
+++ b/sound/soc/codecs/adau17x1.c
@@ -502,7 +502,7 @@ static int adau17x1_hw_params(struct snd_pcm_substream *substream,
 	}
 
 	if (adau->sigmadsp) {
-		ret = adau17x1_setup_firmware(adau, params_rate(params));
+		ret = adau17x1_setup_firmware(component, params_rate(params));
 		if (ret < 0)
 			return ret;
 	}
@@ -835,26 +835,49 @@ bool adau17x1_volatile_register(struct device *dev, unsigned int reg)
 }
 EXPORT_SYMBOL_GPL(adau17x1_volatile_register);
 
-int adau17x1_setup_firmware(struct adau *adau, unsigned int rate)
+int adau17x1_setup_firmware(struct snd_soc_component *component,
+	unsigned int rate)
 {
 	int ret;
-	int dspsr;
+	int dspsr, dsp_run;
+	struct adau *adau = snd_soc_component_get_drvdata(component);
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
+
+	/* Check if sample rate is the same as before. If it is there is no
+	 * point in performing the below steps as the call to
+	 * sigmadsp_setup(...) will return directly when it finds the sample
+	 * rate to be the same as before. By checking this we can prevent an
+	 * audiable popping noise which occours when toggling DSP_RUN.
+	 */
+	if (adau->sigmadsp->current_samplerate == rate)
+		return 0;
+
+	snd_soc_dapm_mutex_lock(dapm);
 
 	ret = regmap_read(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, &dspsr);
 	if (ret)
-		return ret;
+		goto err;
+
+	ret = regmap_read(adau->regmap, ADAU17X1_DSP_RUN, &dsp_run);
+	if (ret)
+		goto err;
 
 	regmap_write(adau->regmap, ADAU17X1_DSP_ENABLE, 1);
 	regmap_write(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, 0xf);
+	regmap_write(adau->regmap, ADAU17X1_DSP_RUN, 0);
 
 	ret = sigmadsp_setup(adau->sigmadsp, rate);
 	if (ret) {
 		regmap_write(adau->regmap, ADAU17X1_DSP_ENABLE, 0);
-		return ret;
+		goto err;
 	}
 	regmap_write(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, dspsr);
+	regmap_write(adau->regmap, ADAU17X1_DSP_RUN, dsp_run);
 
-	return 0;
+err:
+	snd_soc_dapm_mutex_unlock(dapm);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(adau17x1_setup_firmware);
 
diff --git a/sound/soc/codecs/adau17x1.h b/sound/soc/codecs/adau17x1.h
index a7b1cb770814..e6fe87beec07 100644
--- a/sound/soc/codecs/adau17x1.h
+++ b/sound/soc/codecs/adau17x1.h
@@ -68,7 +68,8 @@ int adau17x1_resume(struct snd_soc_component *component);
 
 extern const struct snd_soc_dai_ops adau17x1_dai_ops;
 
-int adau17x1_setup_firmware(struct adau *adau, unsigned int rate);
+int adau17x1_setup_firmware(struct snd_soc_component *component,
+	unsigned int rate);
 bool adau17x1_has_dsp(struct adau *adau);
 
 #define ADAU17X1_CLOCK_CONTROL			0x4000
diff --git a/sound/soc/codecs/cs35l35.c b/sound/soc/codecs/cs35l35.c
index a4a2cb171bdf..bd6226bde45f 100644
--- a/sound/soc/codecs/cs35l35.c
+++ b/sound/soc/codecs/cs35l35.c
@@ -1105,6 +1105,7 @@ static struct regmap_config cs35l35_regmap = {
 	.readable_reg = cs35l35_readable_register,
 	.precious_reg = cs35l35_precious_register,
 	.cache_type = REGCACHE_RBTREE,
+	.use_single_rw = true,
 };
 
 static irqreturn_t cs35l35_irq(int irq, void *data)
diff --git a/sound/soc/codecs/cs43130.c b/sound/soc/codecs/cs43130.c
index feca0a672976..80dc42197154 100644
--- a/sound/soc/codecs/cs43130.c
+++ b/sound/soc/codecs/cs43130.c
@@ -1733,10 +1733,10 @@ static ssize_t cs43130_show_ac_r(struct device *dev,
 	return cs43130_show_ac(dev, buf, HP_RIGHT);
 }
 
-static DEVICE_ATTR(hpload_dc_l, S_IRUGO, cs43130_show_dc_l, NULL);
-static DEVICE_ATTR(hpload_dc_r, S_IRUGO, cs43130_show_dc_r, NULL);
-static DEVICE_ATTR(hpload_ac_l, S_IRUGO, cs43130_show_ac_l, NULL);
-static DEVICE_ATTR(hpload_ac_r, S_IRUGO, cs43130_show_ac_r, NULL);
+static DEVICE_ATTR(hpload_dc_l, 0444, cs43130_show_dc_l, NULL);
+static DEVICE_ATTR(hpload_dc_r, 0444, cs43130_show_dc_r, NULL);
+static DEVICE_ATTR(hpload_ac_l, 0444, cs43130_show_ac_l, NULL);
+static DEVICE_ATTR(hpload_ac_r, 0444, cs43130_show_ac_r, NULL);
 
 static struct reg_sequence hp_en_cal_seq[] = {
 	{CS43130_INT_MASK_4, CS43130_INT_MASK_ALL},
diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c
index 865f64c40b79..fb515aaa54fc 100644
--- a/sound/soc/codecs/max98088.c
+++ b/sound/soc/codecs/max98088.c
@@ -1382,15 +1382,12 @@ static const char *eq_mode_name[] = {"EQ1 Mode", "EQ2 Mode"};
 
 static int max98088_get_channel(struct snd_soc_component *component, const char *name)
 {
-	int i;
+	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(eq_mode_name); i++)
-		if (strcmp(name, eq_mode_name[i]) == 0)
-			return i;
-
-	/* Shouldn't happen */
-	dev_err(component->dev, "Bad EQ channel name '%s'\n", name);
-	return -EINVAL;
+	ret = match_string(eq_mode_name, ARRAY_SIZE(eq_mode_name), name);
+	if (ret < 0)
+		dev_err(component->dev, "Bad EQ channel name '%s'\n", name);
+	return ret;
 }
 
 static void max98088_setup_eq1(struct snd_soc_component *component)
diff --git a/sound/soc/codecs/max98095.c b/sound/soc/codecs/max98095.c
index 6bf2d0ba864f..3b3a10da7f40 100644
--- a/sound/soc/codecs/max98095.c
+++ b/sound/soc/codecs/max98095.c
@@ -1634,15 +1634,12 @@ static const char *bq_mode_name[] = {"Biquad1 Mode", "Biquad2 Mode"};
 static int max98095_get_bq_channel(struct snd_soc_component *component,
 				   const char *name)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(bq_mode_name); i++)
-		if (strcmp(name, bq_mode_name[i]) == 0)
-			return i;
+	int ret;
 
-	/* Shouldn't happen */
-	dev_err(component->dev, "Bad biquad channel name '%s'\n", name);
-	return -EINVAL;
+	ret = match_string(bq_mode_name, ARRAY_SIZE(bq_mode_name), name);
+	if (ret < 0)
+		dev_err(component->dev, "Bad biquad channel name '%s'\n", name);
+	return ret;
 }
 
 static int max98095_put_bq_enum(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/codecs/max9860.c b/sound/soc/codecs/max9860.c
index 5bbf889ad98e..de3d44e9199b 100644
--- a/sound/soc/codecs/max9860.c
+++ b/sound/soc/codecs/max9860.c
@@ -1,23 +1,14 @@
-/*
- * Driver for the MAX9860 Mono Audio Voice Codec
- *
- * https://datasheets.maximintegrated.com/en/ds/MAX9860.pdf
- *
- * The driver does not support sidetone since the DVST register field is
- * backwards with the mute near the maximum level instead of the minimum.
- *
- * Author: Peter Rosin <peda@axentia.s>
- *         Copyright 2016 Axentia Technologies
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Driver for the MAX9860 Mono Audio Voice Codec
+//
+// https://datasheets.maximintegrated.com/en/ds/MAX9860.pdf
+//
+// The driver does not support sidetone since the DVST register field is
+// backwards with the mute near the maximum level instead of the minimum.
+//
+// Author: Peter Rosin <peda@axentia.s>
+//         Copyright 2016 Axentia Technologies
 
 #include <linux/init.h>
 #include <linux/module.h>
@@ -443,7 +434,8 @@ static int max9860_hw_params(struct snd_pcm_substream *substream,
 		ret = regmap_update_bits(max9860->regmap, MAX9860_AUDIOCLKHIGH,
 					 MAX9860_PLL, MAX9860_PLL);
 		if (ret) {
-			dev_err(component->dev, "Failed to enable PLL: %d\n", ret);
+			dev_err(component->dev, "Failed to enable PLL: %d\n",
+				ret);
 			return ret;
 		}
 	}
@@ -515,7 +507,8 @@ static int max9860_set_bias_level(struct snd_soc_component *component,
 		ret = regmap_update_bits(max9860->regmap, MAX9860_PWRMAN,
 					 MAX9860_SHDN, MAX9860_SHDN);
 		if (ret) {
-			dev_err(component->dev, "Failed to remove SHDN: %d\n", ret);
+			dev_err(component->dev, "Failed to remove SHDN: %d\n",
+				ret);
 			return ret;
 		}
 		break;
@@ -598,8 +591,7 @@ static const struct dev_pm_ops max9860_pm_ops = {
 	SET_RUNTIME_PM_OPS(max9860_suspend, max9860_resume, NULL)
 };
 
-static int max9860_probe(struct i2c_client *i2c,
-			 const struct i2c_device_id *id)
+static int max9860_probe(struct i2c_client *i2c)
 {
 	struct device *dev = &i2c->dev;
 	struct max9860_priv *max9860;
@@ -698,7 +690,7 @@ static int max9860_probe(struct i2c_client *i2c,
 	pm_runtime_idle(dev);
 
 	ret = devm_snd_soc_register_component(dev, &max9860_component_driver,
-				     &max9860_dai, 1);
+					      &max9860_dai, 1);
 	if (ret) {
 		dev_err(dev, "Failed to register CODEC: %d\n", ret);
 		goto err_pm;
@@ -736,7 +728,7 @@ static const struct of_device_id max9860_of_match[] = {
 MODULE_DEVICE_TABLE(of, max9860_of_match);
 
 static struct i2c_driver max9860_i2c_driver = {
-	.probe	        = max9860_probe,
+	.probe_new      = max9860_probe,
 	.remove         = max9860_remove,
 	.id_table       = max9860_i2c_id,
 	.driver         = {
diff --git a/sound/soc/codecs/max9860.h b/sound/soc/codecs/max9860.h
index 22041bd67a7d..e07b905eaf50 100644
--- a/sound/soc/codecs/max9860.h
+++ b/sound/soc/codecs/max9860.h
@@ -1,17 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Driver for the MAX9860 Mono Audio Voice Codec
  *
  * Author: Peter Rosin <peda@axentia.s>
  *         Copyright 2016 Axentia Technologies
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 
 #ifndef _SND_SOC_MAX9860
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index 12ee83d52405..b7cf7cce95fe 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -1187,7 +1187,8 @@ static int pm8916_wcd_analog_spmi_probe(struct platform_device *pdev)
 		return irq;
 	}
 
-	ret = devm_request_irq(dev, irq, pm8916_mbhc_switch_irq_handler,
+	ret = devm_request_threaded_irq(dev, irq, NULL,
+			       pm8916_mbhc_switch_irq_handler,
 			       IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING |
 			       IRQF_ONESHOT,
 			       "mbhc switch irq", priv);
@@ -1201,7 +1202,8 @@ static int pm8916_wcd_analog_spmi_probe(struct platform_device *pdev)
 			return irq;
 		}
 
-		ret = devm_request_irq(dev, irq, mbhc_btn_press_irq_handler,
+		ret = devm_request_threaded_irq(dev, irq, NULL,
+				       mbhc_btn_press_irq_handler,
 				       IRQF_TRIGGER_RISING |
 				       IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 				       "mbhc btn press irq", priv);
@@ -1214,7 +1216,8 @@ static int pm8916_wcd_analog_spmi_probe(struct platform_device *pdev)
 			return irq;
 		}
 
-		ret = devm_request_irq(dev, irq, mbhc_btn_release_irq_handler,
+		ret = devm_request_threaded_irq(dev, irq, NULL,
+				       mbhc_btn_release_irq_handler,
 				       IRQF_TRIGGER_RISING |
 				       IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 				       "mbhc btn release irq", priv);
diff --git a/sound/soc/codecs/mt6351.c b/sound/soc/codecs/mt6351.c
new file mode 100644
index 000000000000..f73dcd753584
--- /dev/null
+++ b/sound/soc/codecs/mt6351.c
@@ -0,0 +1,1505 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// mt6351.c  --  mt6351 ALSA SoC audio codec driver
+//
+// Copyright (c) 2018 MediaTek Inc.
+// Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/delay.h>
+
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/soc.h>
+#include <sound/tlv.h>
+
+#include "mt6351.h"
+
+/* MT6351_TOP_CLKSQ */
+#define RG_CLKSQ_EN_AUD_BIT (0)
+
+/* MT6351_TOP_CKPDN_CON0 */
+#define RG_AUDNCP_CK_PDN_BIT (12)
+#define RG_AUDIF_CK_PDN_BIT (13)
+#define RG_AUD_CK_PDN_BIT (14)
+#define RG_ZCD13M_CK_PDN_BIT (15)
+
+/* MT6351_AUDDEC_ANA_CON0 */
+#define RG_AUDDACLPWRUP_VAUDP32_BIT (0)
+#define RG_AUDDACRPWRUP_VAUDP32_BIT (1)
+#define RG_AUD_DAC_PWR_UP_VA32_BIT (2)
+#define RG_AUD_DAC_PWL_UP_VA32_BIT (3)
+
+#define RG_AUDHSPWRUP_VAUDP32_BIT (4)
+
+#define RG_AUDHPLPWRUP_VAUDP32_BIT (5)
+#define RG_AUDHPRPWRUP_VAUDP32_BIT (6)
+
+#define RG_AUDHSMUXINPUTSEL_VAUDP32_SFT (7)
+#define RG_AUDHSMUXINPUTSEL_VAUDP32_MASK (0x3)
+
+#define RG_AUDHPLMUXINPUTSEL_VAUDP32_SFT (9)
+#define RG_AUDHPLMUXINPUTSEL_VAUDP32_MASK (0x3)
+
+#define RG_AUDHPRMUXINPUTSEL_VAUDP32_SFT (11)
+#define RG_AUDHPRMUXINPUTSEL_VAUDP32_MASK (0x3)
+
+#define RG_AUDHSSCDISABLE_VAUDP32 (13)
+#define RG_AUDHPLSCDISABLE_VAUDP32_BIT (14)
+#define RG_AUDHPRSCDISABLE_VAUDP32_BIT (15)
+
+/* MT6351_AUDDEC_ANA_CON1 */
+#define RG_HSOUTPUTSTBENH_VAUDP32_BIT (8)
+
+/* MT6351_AUDDEC_ANA_CON3 */
+#define RG_AUDLOLPWRUP_VAUDP32_BIT (2)
+
+#define RG_AUDLOLMUXINPUTSEL_VAUDP32_SFT (3)
+#define RG_AUDLOLMUXINPUTSEL_VAUDP32_MASK (0x3)
+
+#define RG_AUDLOLSCDISABLE_VAUDP32_BIT (5)
+#define RG_LOOUTPUTSTBENH_VAUDP32_BIT (9)
+
+/* MT6351_AUDDEC_ANA_CON6 */
+#define RG_ABIDEC_RSVD0_VAUDP32_HPL_BIT (8)
+#define RG_ABIDEC_RSVD0_VAUDP32_HPR_BIT (9)
+#define RG_ABIDEC_RSVD0_VAUDP32_HS_BIT (10)
+#define RG_ABIDEC_RSVD0_VAUDP32_LOL_BIT (11)
+
+/* MT6351_AUDDEC_ANA_CON9 */
+#define RG_AUDIBIASPWRDN_VAUDP32_BIT (8)
+#define RG_RSTB_DECODER_VA32_BIT (9)
+#define RG_AUDGLB_PWRDN_VA32_BIT (12)
+
+#define RG_LCLDO_DEC_EN_VA32_BIT (13)
+#define RG_LCLDO_DEC_REMOTE_SENSE_VA18_BIT (15)
+/* MT6351_AUDDEC_ANA_CON10 */
+#define RG_NVREG_EN_VAUDP32_BIT (8)
+
+#define RG_AUDGLB_LP2_VOW_EN_VA32 10
+
+/* MT6351_AFE_UL_DL_CON0 */
+#define RG_AFE_ON_BIT (0)
+
+/* MT6351_AFE_DL_SRC2_CON0_L */
+#define RG_DL_2_SRC_ON_TMP_CTL_PRE_BIT (0)
+
+/* MT6351_AFE_UL_SRC_CON0_L */
+#define UL_SRC_ON_TMP_CTL (0)
+
+/* MT6351_AFE_TOP_CON0 */
+#define RG_DL_SINE_ON_SFT (0)
+#define RG_DL_SINE_ON_MASK (0x1)
+
+#define RG_UL_SINE_ON_SFT (1)
+#define RG_UL_SINE_ON_MASK (0x1)
+
+/* MT6351_AUDIO_TOP_CON0 */
+#define AUD_TOP_PDN_RESERVED_BIT 0
+#define AUD_TOP_PWR_CLK_DIS_CTL_BIT 2
+#define AUD_TOP_PDN_ADC_CTL_BIT 5
+#define AUD_TOP_PDN_DAC_CTL_BIT 6
+#define AUD_TOP_PDN_AFE_CTL_BIT 7
+
+/* MT6351_AFE_SGEN_CFG0 */
+#define SGEN_C_MUTE_SW_CTL_BIT 6
+#define SGEN_C_DAC_EN_CTL_BIT 7
+
+/* MT6351_AFE_NCP_CFG0 */
+#define RG_NCP_ON_BIT 0
+
+/* MT6351_LDO_VUSB33_CON0 */
+#define RG_VUSB33_EN 1
+#define RG_VUSB33_ON_CTRL 3
+
+/* MT6351_LDO_VA18_CON0 */
+#define RG_VA18_EN 1
+#define RG_VA18_ON_CTRL 3
+
+/* MT6351_AUDENC_ANA_CON0 */
+#define RG_AUDPREAMPLON 0
+#define RG_AUDPREAMPLDCCEN 1
+#define RG_AUDPREAMPLDCPRECHARGE 2
+
+#define RG_AUDPREAMPLINPUTSEL_SFT (4)
+#define RG_AUDPREAMPLINPUTSEL_MASK (0x3)
+
+#define RG_AUDADCLPWRUP 12
+
+#define RG_AUDADCLINPUTSEL_SFT (13)
+#define RG_AUDADCLINPUTSEL_MASK (0x3)
+
+/* MT6351_AUDENC_ANA_CON1 */
+#define RG_AUDPREAMPRON 0
+#define RG_AUDPREAMPRDCCEN 1
+#define RG_AUDPREAMPRDCPRECHARGE 2
+
+#define RG_AUDPREAMPRINPUTSEL_SFT (4)
+#define RG_AUDPREAMPRINPUTSEL_MASK (0x3)
+
+#define RG_AUDADCRPWRUP 12
+
+#define RG_AUDADCRINPUTSEL_SFT (13)
+#define RG_AUDADCRINPUTSEL_MASK (0x3)
+
+/* MT6351_AUDENC_ANA_CON3 */
+#define RG_AUDADCCLKRSTB 6
+
+/* MT6351_AUDENC_ANA_CON9 */
+#define RG_AUDPWDBMICBIAS0 0
+#define RG_AUDMICBIAS0VREF 4
+#define RG_AUDMICBIAS0LOWPEN 7
+
+#define RG_AUDPWDBMICBIAS2 8
+#define RG_AUDMICBIAS2VREF 12
+#define RG_AUDMICBIAS2LOWPEN 15
+
+/* MT6351_AUDENC_ANA_CON10 */
+#define RG_AUDPWDBMICBIAS1 0
+#define RG_AUDMICBIAS1DCSW1NEN 2
+#define RG_AUDMICBIAS1VREF 4
+#define RG_AUDMICBIAS1LOWPEN 7
+
+enum {
+	AUDIO_ANALOG_VOLUME_HSOUTL,
+	AUDIO_ANALOG_VOLUME_HSOUTR,
+	AUDIO_ANALOG_VOLUME_HPOUTL,
+	AUDIO_ANALOG_VOLUME_HPOUTR,
+	AUDIO_ANALOG_VOLUME_LINEOUTL,
+	AUDIO_ANALOG_VOLUME_LINEOUTR,
+	AUDIO_ANALOG_VOLUME_MICAMP1,
+	AUDIO_ANALOG_VOLUME_MICAMP2,
+	AUDIO_ANALOG_VOLUME_TYPE_MAX
+};
+
+/* Supply subseq */
+enum {
+	SUPPLY_SUBSEQ_SETTING,
+	SUPPLY_SUBSEQ_ENABLE,
+	SUPPLY_SUBSEQ_MICBIAS,
+};
+
+#define REG_STRIDE 2
+
+struct mt6351_priv {
+	struct device *dev;
+	struct regmap *regmap;
+
+	unsigned int dl_rate;
+	unsigned int ul_rate;
+
+	int ana_gain[AUDIO_ANALOG_VOLUME_TYPE_MAX];
+
+	int hp_en_counter;
+};
+
+static void set_hp_gain_zero(struct snd_soc_component *cmpnt)
+{
+	regmap_update_bits(cmpnt->regmap, MT6351_ZCD_CON2,
+			   0x1f << 7, 0x8 << 7);
+	regmap_update_bits(cmpnt->regmap, MT6351_ZCD_CON2,
+			   0x1f << 0, 0x8 << 0);
+}
+
+static unsigned int get_cap_reg_val(struct snd_soc_component *cmpnt,
+				    unsigned int rate)
+{
+	switch (rate) {
+	case 8000:
+		return 0;
+	case 16000:
+		return 1;
+	case 32000:
+		return 2;
+	case 48000:
+		return 3;
+	case 96000:
+		return 4;
+	case 192000:
+		return 5;
+	default:
+		dev_warn(cmpnt->dev, "%s(), error rate %d, return 3",
+			 __func__, rate);
+		return 3;
+	}
+}
+
+static unsigned int get_play_reg_val(struct snd_soc_component *cmpnt,
+				     unsigned int rate)
+{
+	switch (rate) {
+	case 8000:
+		return 0;
+	case 11025:
+		return 1;
+	case 12000:
+		return 2;
+	case 16000:
+		return 3;
+	case 22050:
+		return 4;
+	case 24000:
+		return 5;
+	case 32000:
+		return 6;
+	case 44100:
+		return 7;
+	case 48000:
+	case 96000:
+	case 192000:
+		return 8;
+	default:
+		dev_warn(cmpnt->dev, "%s(), error rate %d, return 8",
+			 __func__, rate);
+		return 8;
+	}
+}
+
+static int mt6351_codec_dai_hw_params(struct snd_pcm_substream *substream,
+				      struct snd_pcm_hw_params *params,
+				      struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *cmpnt = dai->component;
+	struct mt6351_priv *priv = snd_soc_component_get_drvdata(cmpnt);
+	unsigned int rate = params_rate(params);
+
+	dev_dbg(priv->dev, "%s(), substream->stream %d, rate %d\n",
+		__func__, substream->stream, rate);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		priv->dl_rate = rate;
+	else if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+		priv->ul_rate = rate;
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops mt6351_codec_dai_ops = {
+	.hw_params = mt6351_codec_dai_hw_params,
+};
+
+#define MT6351_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S16_BE |\
+			SNDRV_PCM_FMTBIT_U16_LE | SNDRV_PCM_FMTBIT_U16_BE |\
+			SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S24_BE |\
+			SNDRV_PCM_FMTBIT_U24_LE | SNDRV_PCM_FMTBIT_U24_BE |\
+			SNDRV_PCM_FMTBIT_S32_LE | SNDRV_PCM_FMTBIT_S32_BE |\
+			SNDRV_PCM_FMTBIT_U32_LE | SNDRV_PCM_FMTBIT_U32_BE)
+
+static struct snd_soc_dai_driver mt6351_dai_driver[] = {
+	{
+		.name = "mt6351-snd-codec-aif1",
+		.playback = {
+			.stream_name = "AIF1 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_48000 |
+				 SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = MT6351_FORMATS,
+		},
+		.capture = {
+			.stream_name = "AIF1 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 |
+				 SNDRV_PCM_RATE_32000 |
+				 SNDRV_PCM_RATE_48000 |
+				 SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = MT6351_FORMATS,
+		},
+		.ops = &mt6351_codec_dai_ops,
+	},
+};
+
+enum {
+	HP_GAIN_SET_ZERO,
+	HP_GAIN_RESTORE,
+};
+
+static void hp_gain_ramp_set(struct snd_soc_component *cmpnt, int hp_gain_ctl)
+{
+	struct mt6351_priv *priv = snd_soc_component_get_drvdata(cmpnt);
+	int idx, old_idx, offset, reg_idx;
+
+	if (hp_gain_ctl == HP_GAIN_SET_ZERO) {
+		idx = 8;	/* 0dB */
+		old_idx = priv->ana_gain[AUDIO_ANALOG_VOLUME_HPOUTL];
+	} else {
+		idx = priv->ana_gain[AUDIO_ANALOG_VOLUME_HPOUTL];
+		old_idx = 8;	/* 0dB */
+	}
+	dev_dbg(priv->dev, "%s(), idx %d, old_idx %d\n",
+		__func__, idx, old_idx);
+
+	if (idx > old_idx)
+		offset = idx - old_idx;
+	else
+		offset = old_idx - idx;
+
+	reg_idx = old_idx;
+
+	while (offset > 0) {
+		reg_idx = idx > old_idx ? reg_idx + 1 : reg_idx - 1;
+
+		/* check valid range, and set value */
+		if ((reg_idx >= 0 && reg_idx <= 0x12) || reg_idx == 0x1f) {
+			regmap_update_bits(cmpnt->regmap,
+					   MT6351_ZCD_CON2,
+					   0xf9f,
+					   (reg_idx << 7) | reg_idx);
+			usleep_range(100, 120);
+		}
+		offset--;
+	}
+}
+
+static void hp_zcd_enable(struct snd_soc_component *cmpnt)
+{
+	/* Enable ZCD, for minimize pop noise */
+	/* when adjust gain during HP buffer on */
+	regmap_update_bits(cmpnt->regmap, MT6351_ZCD_CON0, 0x7 << 8, 0x1 << 8);
+	regmap_update_bits(cmpnt->regmap, MT6351_ZCD_CON0, 0x1 << 7, 0x0 << 7);
+
+	/* timeout, 1=5ms, 0=30ms */
+	regmap_update_bits(cmpnt->regmap, MT6351_ZCD_CON0, 0x1 << 6, 0x1 << 6);
+
+	regmap_update_bits(cmpnt->regmap, MT6351_ZCD_CON0, 0x3 << 4, 0x0 << 4);
+	regmap_update_bits(cmpnt->regmap, MT6351_ZCD_CON0, 0x7 << 1, 0x5 << 1);
+	regmap_update_bits(cmpnt->regmap, MT6351_ZCD_CON0, 0x1 << 0, 0x1 << 0);
+}
+
+static void hp_zcd_disable(struct snd_soc_component *cmpnt)
+{
+	regmap_write(cmpnt->regmap, MT6351_ZCD_CON0, 0x0000);
+}
+
+static const DECLARE_TLV_DB_SCALE(playback_tlv, -1000, 100, 0);
+static const DECLARE_TLV_DB_SCALE(pga_tlv, 0, 600, 0);
+
+static const struct snd_kcontrol_new mt6351_snd_controls[] = {
+	/* dl pga gain */
+	SOC_DOUBLE_TLV("Headphone Volume",
+		       MT6351_ZCD_CON2, 0, 7, 0x12, 1,
+		       playback_tlv),
+	SOC_DOUBLE_TLV("Lineout Volume",
+		       MT6351_ZCD_CON1, 0, 7, 0x12, 1,
+		       playback_tlv),
+	SOC_SINGLE_TLV("Handset Volume",
+		       MT6351_ZCD_CON3, 0, 0x12, 1,
+		       playback_tlv),
+       /* ul pga gain */
+	SOC_DOUBLE_R_TLV("PGA Volume",
+			 MT6351_AUDENC_ANA_CON0, MT6351_AUDENC_ANA_CON1,
+			 8, 4, 0,
+			 pga_tlv),
+};
+
+/* MUX */
+
+/* LOL MUX */
+static const char *const lo_in_mux_map[] = {
+	"Open", "Mute", "Playback", "Test Mode",
+};
+
+static int lo_in_mux_map_value[] = {
+	0x0, 0x1, 0x2, 0x3,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(lo_in_mux_map_enum,
+				  MT6351_AUDDEC_ANA_CON3,
+				  RG_AUDLOLMUXINPUTSEL_VAUDP32_SFT,
+				  RG_AUDLOLMUXINPUTSEL_VAUDP32_MASK,
+				  lo_in_mux_map,
+				  lo_in_mux_map_value);
+
+static const struct snd_kcontrol_new lo_in_mux_control =
+	SOC_DAPM_ENUM("In Select", lo_in_mux_map_enum);
+
+/*HP MUX */
+static const char *const hp_in_mux_map[] = {
+	"Open", "LoudSPK Playback", "Audio Playback", "Test Mode",
+};
+
+static int hp_in_mux_map_value[] = {
+	0x0, 0x1, 0x2, 0x3,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(hpl_in_mux_map_enum,
+				  MT6351_AUDDEC_ANA_CON0,
+				  RG_AUDHPLMUXINPUTSEL_VAUDP32_SFT,
+				  RG_AUDHPLMUXINPUTSEL_VAUDP32_MASK,
+				  hp_in_mux_map,
+				  hp_in_mux_map_value);
+
+static const struct snd_kcontrol_new hpl_in_mux_control =
+	SOC_DAPM_ENUM("HPL Select", hpl_in_mux_map_enum);
+
+static SOC_VALUE_ENUM_SINGLE_DECL(hpr_in_mux_map_enum,
+				  MT6351_AUDDEC_ANA_CON0,
+				  RG_AUDHPRMUXINPUTSEL_VAUDP32_SFT,
+				  RG_AUDHPRMUXINPUTSEL_VAUDP32_MASK,
+				  hp_in_mux_map,
+				  hp_in_mux_map_value);
+
+static const struct snd_kcontrol_new hpr_in_mux_control =
+	SOC_DAPM_ENUM("HPR Select", hpr_in_mux_map_enum);
+
+/* RCV MUX */
+static const char *const rcv_in_mux_map[] = {
+	"Open", "Mute", "Voice Playback", "Test Mode",
+};
+
+static int rcv_in_mux_map_value[] = {
+	0x0, 0x1, 0x2, 0x3,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(rcv_in_mux_map_enum,
+				  MT6351_AUDDEC_ANA_CON0,
+				  RG_AUDHSMUXINPUTSEL_VAUDP32_SFT,
+				  RG_AUDHSMUXINPUTSEL_VAUDP32_MASK,
+				  rcv_in_mux_map,
+				  rcv_in_mux_map_value);
+
+static const struct snd_kcontrol_new rcv_in_mux_control =
+	SOC_DAPM_ENUM("RCV Select", rcv_in_mux_map_enum);
+
+/* DAC In MUX */
+static const char *const dac_in_mux_map[] = {
+	"Normal Path", "Sgen",
+};
+
+static int dac_in_mux_map_value[] = {
+	0x0, 0x1,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(dac_in_mux_map_enum,
+				  MT6351_AFE_TOP_CON0,
+				  RG_DL_SINE_ON_SFT,
+				  RG_DL_SINE_ON_MASK,
+				  dac_in_mux_map,
+				  dac_in_mux_map_value);
+
+static const struct snd_kcontrol_new dac_in_mux_control =
+	SOC_DAPM_ENUM("DAC Select", dac_in_mux_map_enum);
+
+/* AIF Out MUX */
+static SOC_VALUE_ENUM_SINGLE_DECL(aif_out_mux_map_enum,
+				  MT6351_AFE_TOP_CON0,
+				  RG_UL_SINE_ON_SFT,
+				  RG_UL_SINE_ON_MASK,
+				  dac_in_mux_map,
+				  dac_in_mux_map_value);
+
+static const struct snd_kcontrol_new aif_out_mux_control =
+	SOC_DAPM_ENUM("AIF Out Select", aif_out_mux_map_enum);
+
+/* ADC L MUX */
+static const char *const adc_left_mux_map[] = {
+	"Idle", "AIN0", "Left Preamplifier", "Idle_1",
+};
+
+static int adc_left_mux_map_value[] = {
+	0x0, 0x1, 0x2, 0x3,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(adc_left_mux_map_enum,
+				  MT6351_AUDENC_ANA_CON0,
+				  RG_AUDADCLINPUTSEL_SFT,
+				  RG_AUDADCLINPUTSEL_MASK,
+				  adc_left_mux_map,
+				  adc_left_mux_map_value);
+
+static const struct snd_kcontrol_new adc_left_mux_control =
+	SOC_DAPM_ENUM("ADC L Select", adc_left_mux_map_enum);
+
+/* ADC R MUX */
+static const char *const adc_right_mux_map[] = {
+	"Idle", "AIN0", "Right Preamplifier", "Idle_1",
+};
+
+static int adc_right_mux_map_value[] = {
+	0x0, 0x1, 0x2, 0x3,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(adc_right_mux_map_enum,
+				  MT6351_AUDENC_ANA_CON1,
+				  RG_AUDADCRINPUTSEL_SFT,
+				  RG_AUDADCRINPUTSEL_MASK,
+				  adc_right_mux_map,
+				  adc_right_mux_map_value);
+
+static const struct snd_kcontrol_new adc_right_mux_control =
+	SOC_DAPM_ENUM("ADC R Select", adc_right_mux_map_enum);
+
+/* PGA L MUX */
+static const char *const pga_left_mux_map[] = {
+	"None", "AIN0", "AIN1", "AIN2",
+};
+
+static int pga_left_mux_map_value[] = {
+	0x0, 0x1, 0x2, 0x3,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(pga_left_mux_map_enum,
+				  MT6351_AUDENC_ANA_CON0,
+				  RG_AUDPREAMPLINPUTSEL_SFT,
+				  RG_AUDPREAMPLINPUTSEL_MASK,
+				  pga_left_mux_map,
+				  pga_left_mux_map_value);
+
+static const struct snd_kcontrol_new pga_left_mux_control =
+	SOC_DAPM_ENUM("PGA L Select", pga_left_mux_map_enum);
+
+/* PGA R MUX */
+static const char *const pga_right_mux_map[] = {
+	"None", "AIN0", "AIN3", "AIN2",
+};
+
+static int pga_right_mux_map_value[] = {
+	0x0, 0x1, 0x2, 0x3,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(pga_right_mux_map_enum,
+				  MT6351_AUDENC_ANA_CON1,
+				  RG_AUDPREAMPRINPUTSEL_SFT,
+				  RG_AUDPREAMPRINPUTSEL_MASK,
+				  pga_right_mux_map,
+				  pga_right_mux_map_value);
+
+static const struct snd_kcontrol_new pga_right_mux_control =
+	SOC_DAPM_ENUM("PGA R Select", pga_right_mux_map_enum);
+
+static int mt_reg_set_clr_event(struct snd_soc_dapm_widget *w,
+				struct snd_kcontrol *kcontrol,
+				int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		if (w->on_val) {
+			/* SET REG */
+			regmap_update_bits(cmpnt->regmap,
+					   w->reg + REG_STRIDE,
+					   0x1 << w->shift,
+					   0x1 << w->shift);
+		} else {
+			/* CLR REG */
+			regmap_update_bits(cmpnt->regmap,
+					   w->reg + REG_STRIDE * 2,
+					   0x1 << w->shift,
+					   0x1 << w->shift);
+		}
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		if (w->off_val) {
+			/* SET REG */
+			regmap_update_bits(cmpnt->regmap,
+					   w->reg + REG_STRIDE,
+					   0x1 << w->shift,
+					   0x1 << w->shift);
+		} else {
+			/* CLR REG */
+			regmap_update_bits(cmpnt->regmap,
+					   w->reg + REG_STRIDE * 2,
+					   0x1 << w->shift,
+					   0x1 << w->shift);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int mt_ncp_event(struct snd_soc_dapm_widget *w,
+			struct snd_kcontrol *kcontrol,
+			int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_NCP_CFG1,
+				   0xffff, 0x1515);
+		/* NCP: ck1 and ck2 clock frequecy adjust configure */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_NCP_CFG0,
+				   0xfffe, 0x8C00);
+		break;
+	case SND_SOC_DAPM_POST_PMU:
+		usleep_range(250, 270);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int mt_sgen_event(struct snd_soc_dapm_widget *w,
+			 struct snd_kcontrol *kcontrol,
+			 int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_SGEN_CFG0,
+				   0xffef, 0x0008);
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_SGEN_CFG1,
+				   0xffff, 0x0101);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int mt_aif_in_event(struct snd_soc_dapm_widget *w,
+			   struct snd_kcontrol *kcontrol,
+			   int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+	struct mt6351_priv *priv = snd_soc_component_get_drvdata(cmpnt);
+
+	dev_dbg(priv->dev, "%s(), event 0x%x, rate %d\n",
+		__func__, event, priv->dl_rate);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* sdm audio fifo clock power on */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFUNC_AUD_CON2,
+				   0xffff, 0x0006);
+		/* scrambler clock on enable */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFUNC_AUD_CON0,
+				   0xffff, 0xC3A1);
+		/* sdm power on */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFUNC_AUD_CON2,
+				   0xffff, 0x0003);
+		/* sdm fifo enable */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFUNC_AUD_CON2,
+				   0xffff, 0x000B);
+		/* set attenuation gain */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_DL_SDM_CON1,
+				   0xffff, 0x001E);
+
+		regmap_write(cmpnt->regmap, MT6351_AFE_PMIC_NEWIF_CFG0,
+			     (get_play_reg_val(cmpnt, priv->dl_rate) << 12) |
+			     0x330);
+		regmap_write(cmpnt->regmap, MT6351_AFE_DL_SRC2_CON0_H,
+			     (get_play_reg_val(cmpnt, priv->dl_rate) << 12) |
+			     0x300);
+
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_PMIC_NEWIF_CFG2,
+				   0x8000, 0x8000);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int mt_hp_event(struct snd_soc_dapm_widget *w,
+		       struct snd_kcontrol *kcontrol,
+		       int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+	struct mt6351_priv *priv = snd_soc_component_get_drvdata(cmpnt);
+	int reg;
+
+	dev_dbg(priv->dev, "%s(), event 0x%x, hp_en_counter %d\n",
+		__func__, event, priv->hp_en_counter);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		priv->hp_en_counter++;
+		if (priv->hp_en_counter > 1)
+			break;	/* already enabled, do nothing */
+		else if (priv->hp_en_counter <= 0)
+			dev_err(priv->dev, "%s(), hp_en_counter %d <= 0\n",
+				__func__,
+				priv->hp_en_counter);
+
+		hp_zcd_disable(cmpnt);
+
+		/* from yoyo HQA script */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON6,
+				   0x0700, 0x0700);
+
+		/* save target gain to restore after hardware open complete */
+		regmap_read(cmpnt->regmap, MT6351_ZCD_CON2, &reg);
+		priv->ana_gain[AUDIO_ANALOG_VOLUME_HPOUTL] = reg & 0x1f;
+		priv->ana_gain[AUDIO_ANALOG_VOLUME_HPOUTR] = (reg >> 7) & 0x1f;
+
+		/* Set HPR/HPL gain as minimum (~ -40dB) */
+		regmap_update_bits(cmpnt->regmap,
+				   MT6351_ZCD_CON2, 0xffff, 0x0F9F);
+		/* Set HS gain as minimum (~ -40dB) */
+		regmap_update_bits(cmpnt->regmap,
+				   MT6351_ZCD_CON3, 0xffff, 0x001F);
+		/* De_OSC of HP */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON2,
+				   0x0001, 0x0001);
+		/* enable output STBENH */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON1,
+				   0xffff, 0x2000);
+		/* De_OSC of voice, enable output STBENH */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON1,
+				   0xffff, 0x2100);
+		/* Enable voice driver */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON0,
+				   0x0010, 0xE090);
+		/* Enable pre-charge buffer  */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON1,
+				   0xffff, 0x2140);
+
+		usleep_range(50, 60);
+
+		/* Apply digital DC compensation value to DAC */
+		set_hp_gain_zero(cmpnt);
+
+		/* Enable HPR/HPL */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON1,
+				   0xffff, 0x2100);
+		/* Disable pre-charge buffer */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON1,
+				   0xffff, 0x2000);
+		/* Disable De_OSC of voice */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON0,
+				   0x0010, 0xF4EF);
+		/* Disable voice buffer */
+
+		/* from yoyo HQ */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON6,
+				   0x0700, 0x0300);
+
+		/* Enable ZCD, for minimize pop noise */
+		/* when adjust gain during HP buffer on */
+		hp_zcd_enable(cmpnt);
+
+		/* apply volume setting */
+		hp_gain_ramp_set(cmpnt, HP_GAIN_RESTORE);
+
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		priv->hp_en_counter--;
+		if (priv->hp_en_counter > 0)
+			break;	/* still being used, don't close */
+		else if (priv->hp_en_counter < 0)
+			dev_err(priv->dev, "%s(), hp_en_counter %d <= 0\n",
+				__func__,
+				priv->hp_en_counter);
+
+		/* Disable AUD_ZCD */
+		hp_zcd_disable(cmpnt);
+
+		/* Set HPR/HPL gain as -1dB, step by step */
+		hp_gain_ramp_set(cmpnt, HP_GAIN_SET_ZERO);
+
+		set_hp_gain_zero(cmpnt);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		if (priv->hp_en_counter > 0)
+			break;	/* still being used, don't close */
+		else if (priv->hp_en_counter < 0)
+			dev_err(priv->dev, "%s(), hp_en_counter %d <= 0\n",
+				__func__,
+				priv->hp_en_counter);
+
+		/* reset*/
+		regmap_update_bits(cmpnt->regmap,
+				   MT6351_AUDDEC_ANA_CON6,
+				   0x0700,
+				   0x0000);
+		/* De_OSC of HP */
+		regmap_update_bits(cmpnt->regmap,
+				   MT6351_AUDDEC_ANA_CON2,
+				   0x0001,
+				   0x0000);
+
+		/* apply volume setting */
+		hp_gain_ramp_set(cmpnt, HP_GAIN_RESTORE);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int mt_aif_out_event(struct snd_soc_dapm_widget *w,
+			    struct snd_kcontrol *kcontrol,
+			    int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+	struct mt6351_priv *priv = snd_soc_component_get_drvdata(cmpnt);
+
+	dev_dbg(priv->dev, "%s(), event 0x%x, rate %d\n",
+		__func__, event, priv->ul_rate);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* dcclk_div=11'b00100000011, dcclk_ref_ck_sel=2'b00 */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_DCCLK_CFG0,
+				   0xffff, 0x2062);
+		/* dcclk_pdn=1'b0 */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_DCCLK_CFG0,
+				   0xffff, 0x2060);
+		/* dcclk_gen_on=1'b1 */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_DCCLK_CFG0,
+				   0xffff, 0x2061);
+
+		/* UL sample rate and mode configure */
+		regmap_update_bits(cmpnt->regmap, MT6351_AFE_UL_SRC_CON0_H,
+				   0x000E,
+				   get_cap_reg_val(cmpnt, priv->ul_rate) << 1);
+
+		/* fixed 260k path for 8/16/32/48 */
+		if (priv->ul_rate <= 48000) {
+			/* anc ul path src on */
+			regmap_update_bits(cmpnt->regmap,
+					   MT6351_AFE_HPANC_CFG0,
+					   0x1 << 1,
+					   0x1 << 1);
+			/* ANC clk pdn release */
+			regmap_update_bits(cmpnt->regmap,
+					   MT6351_AFE_HPANC_CFG0,
+					   0x1 << 0,
+					   0x0 << 0);
+		}
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		/* fixed 260k path for 8/16/32/48 */
+		if (priv->ul_rate <= 48000) {
+			/* anc ul path src on */
+			regmap_update_bits(cmpnt->regmap,
+					   MT6351_AFE_HPANC_CFG0,
+					   0x1 << 1,
+					   0x0 << 1);
+			/* ANC clk pdn release */
+			regmap_update_bits(cmpnt->regmap,
+					   MT6351_AFE_HPANC_CFG0,
+					   0x1 << 0,
+					   0x1 << 0);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int mt_adc_clkgen_event(struct snd_soc_dapm_widget *w,
+			       struct snd_kcontrol *kcontrol,
+			       int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* Audio ADC clock gen. mode: 00_divided by 2 (Normal) */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON3,
+				   0x3 << 4, 0x0);
+		break;
+	case SND_SOC_DAPM_POST_PMU:
+		/* ADC CLK from: 00_13MHz from CLKSQ (Default) */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON3,
+				   0x3 << 2, 0x0);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int mt_pga_left_event(struct snd_soc_dapm_widget *w,
+			     struct snd_kcontrol *kcontrol,
+			     int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* Audio L PGA precharge on */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON0,
+				   0x3 << RG_AUDPREAMPLDCPRECHARGE,
+				   0x1 << RG_AUDPREAMPLDCPRECHARGE);
+		/* Audio L PGA mode: 1_DCC */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON0,
+				   0x3 << RG_AUDPREAMPLDCCEN,
+				   0x1 << RG_AUDPREAMPLDCCEN);
+		break;
+	case SND_SOC_DAPM_POST_PMU:
+		usleep_range(100, 120);
+		/* Audio L PGA precharge off */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON0,
+				   0x3 << RG_AUDPREAMPLDCPRECHARGE,
+				   0x0 << RG_AUDPREAMPLDCPRECHARGE);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int mt_pga_right_event(struct snd_soc_dapm_widget *w,
+			      struct snd_kcontrol *kcontrol,
+			      int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* Audio R PGA precharge on */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON1,
+				   0x3 << RG_AUDPREAMPRDCPRECHARGE,
+				   0x1 << RG_AUDPREAMPRDCPRECHARGE);
+		/* Audio R PGA mode: 1_DCC */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON1,
+				   0x3 << RG_AUDPREAMPRDCCEN,
+				   0x1 << RG_AUDPREAMPRDCCEN);
+		break;
+	case SND_SOC_DAPM_POST_PMU:
+		usleep_range(100, 120);
+		/* Audio R PGA precharge off */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON1,
+				   0x3 << RG_AUDPREAMPRDCPRECHARGE,
+				   0x0 << RG_AUDPREAMPRDCPRECHARGE);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int mt_mic_bias_0_event(struct snd_soc_dapm_widget *w,
+			       struct snd_kcontrol *kcontrol,
+			       int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* MIC Bias 0 LowPower: 0_Normal */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON9,
+				   0x3 << RG_AUDMICBIAS0LOWPEN, 0x0);
+		/* MISBIAS0 = 1P9V */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON9,
+				   0x7 << RG_AUDMICBIAS0VREF,
+				   0x2 << RG_AUDMICBIAS0VREF);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		/* MISBIAS0 = 1P97 */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON9,
+				   0x7 << RG_AUDMICBIAS0VREF,
+				   0x0 << RG_AUDMICBIAS0VREF);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int mt_mic_bias_1_event(struct snd_soc_dapm_widget *w,
+			       struct snd_kcontrol *kcontrol,
+			       int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* MIC Bias 1 LowPower: 0_Normal */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON10,
+				   0x3 << RG_AUDMICBIAS1LOWPEN, 0x0);
+		/* MISBIAS1 = 2P7V */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON10,
+				   0x7 << RG_AUDMICBIAS1VREF,
+				   0x7 << RG_AUDMICBIAS1VREF);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		/* MISBIAS1 = 1P7V */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON10,
+				   0x7 << RG_AUDMICBIAS1VREF,
+				   0x0 << RG_AUDMICBIAS1VREF);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int mt_mic_bias_2_event(struct snd_soc_dapm_widget *w,
+			       struct snd_kcontrol *kcontrol,
+			       int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* MIC Bias 2 LowPower: 0_Normal */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON9,
+				   0x3 << RG_AUDMICBIAS2LOWPEN, 0x0);
+		/* MISBIAS2 = 1P9V */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON9,
+				   0x7 << RG_AUDMICBIAS2VREF,
+				   0x2 << RG_AUDMICBIAS2VREF);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		/* MISBIAS2 = 1P97 */
+		regmap_update_bits(cmpnt->regmap, MT6351_AUDENC_ANA_CON9,
+				   0x7 << RG_AUDMICBIAS2VREF,
+				   0x0 << RG_AUDMICBIAS2VREF);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+/* DAPM Kcontrols */
+static const struct snd_kcontrol_new mt_lineout_control =
+	SOC_DAPM_SINGLE("Switch", MT6351_AUDDEC_ANA_CON3,
+			RG_AUDLOLPWRUP_VAUDP32_BIT, 1, 0);
+
+/* DAPM Widgets */
+static const struct snd_soc_dapm_widget mt6351_dapm_widgets[] = {
+	/* Digital Clock */
+	SND_SOC_DAPM_SUPPLY("AUDIO_TOP_AFE_CTL", MT6351_AUDIO_TOP_CON0,
+			    AUD_TOP_PDN_AFE_CTL_BIT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("AUDIO_TOP_DAC_CTL", MT6351_AUDIO_TOP_CON0,
+			    AUD_TOP_PDN_DAC_CTL_BIT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("AUDIO_TOP_ADC_CTL", MT6351_AUDIO_TOP_CON0,
+			    AUD_TOP_PDN_ADC_CTL_BIT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("AUDIO_TOP_PWR_CLK", MT6351_AUDIO_TOP_CON0,
+			    AUD_TOP_PWR_CLK_DIS_CTL_BIT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("AUDIO_TOP_PDN_RESERVED", MT6351_AUDIO_TOP_CON0,
+			    AUD_TOP_PDN_RESERVED_BIT, 1, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("NCP", MT6351_AFE_NCP_CFG0,
+			    RG_NCP_ON_BIT, 0,
+			    mt_ncp_event,
+			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+
+	SND_SOC_DAPM_SUPPLY("DL Digital Clock", SND_SOC_NOPM,
+			    0, 0, NULL, 0),
+
+	/* Global Supply*/
+	SND_SOC_DAPM_SUPPLY("AUDGLB", MT6351_AUDDEC_ANA_CON9,
+			    RG_AUDGLB_PWRDN_VA32_BIT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKSQ Audio", MT6351_TOP_CLKSQ,
+			    RG_CLKSQ_EN_AUD_BIT, 0,
+			    mt_reg_set_clr_event,
+			    SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_SUPPLY("ZCD13M_CK", MT6351_TOP_CKPDN_CON0,
+			    RG_ZCD13M_CK_PDN_BIT, 1,
+			    mt_reg_set_clr_event,
+			    SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_SUPPLY("AUD_CK", MT6351_TOP_CKPDN_CON0,
+			    RG_AUD_CK_PDN_BIT, 1,
+			    mt_reg_set_clr_event,
+			    SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_SUPPLY("AUDIF_CK", MT6351_TOP_CKPDN_CON0,
+			    RG_AUDIF_CK_PDN_BIT, 1,
+			    mt_reg_set_clr_event,
+			    SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_SUPPLY("AUDNCP_CK", MT6351_TOP_CKPDN_CON0,
+			    RG_AUDNCP_CK_PDN_BIT, 1,
+			    mt_reg_set_clr_event,
+			    SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+
+	SND_SOC_DAPM_SUPPLY("AFE_ON", MT6351_AFE_UL_DL_CON0, RG_AFE_ON_BIT, 0,
+			    NULL, 0),
+
+	/* AIF Rx*/
+	SND_SOC_DAPM_AIF_IN_E("AIF_RX", "AIF1 Playback", 0,
+			      MT6351_AFE_DL_SRC2_CON0_L,
+			      RG_DL_2_SRC_ON_TMP_CTL_PRE_BIT, 0,
+			      mt_aif_in_event, SND_SOC_DAPM_PRE_PMU),
+
+	/* DL Supply */
+	SND_SOC_DAPM_SUPPLY("DL Power Supply", SND_SOC_NOPM,
+			    0, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("NV Regulator", MT6351_AUDDEC_ANA_CON10,
+			    RG_NVREG_EN_VAUDP32_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("AUD_CLK", MT6351_AUDDEC_ANA_CON9,
+			    RG_RSTB_DECODER_VA32_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("IBIST", MT6351_AUDDEC_ANA_CON9,
+			    RG_AUDIBIASPWRDN_VAUDP32_BIT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("LDO", MT6351_AUDDEC_ANA_CON9,
+			    RG_LCLDO_DEC_EN_VA32_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("LDO_REMOTE_SENSE", MT6351_AUDDEC_ANA_CON9,
+			    RG_LCLDO_DEC_REMOTE_SENSE_VA18_BIT, 0, NULL, 0),
+
+	/* DAC */
+	SND_SOC_DAPM_MUX("DAC In Mux", SND_SOC_NOPM, 0, 0, &dac_in_mux_control),
+
+	SND_SOC_DAPM_DAC("DACL", NULL, MT6351_AUDDEC_ANA_CON0,
+			 RG_AUDDACLPWRUP_VAUDP32_BIT, 0),
+	SND_SOC_DAPM_SUPPLY("DACL_BIASGEN", MT6351_AUDDEC_ANA_CON0,
+			    RG_AUD_DAC_PWL_UP_VA32_BIT, 0, NULL, 0),
+
+	SND_SOC_DAPM_DAC("DACR", NULL, MT6351_AUDDEC_ANA_CON0,
+			 RG_AUDDACRPWRUP_VAUDP32_BIT, 0),
+	SND_SOC_DAPM_SUPPLY("DACR_BIASGEN", MT6351_AUDDEC_ANA_CON0,
+			    RG_AUD_DAC_PWR_UP_VA32_BIT, 0, NULL, 0),
+	/* LOL */
+	SND_SOC_DAPM_MUX("LOL Mux", SND_SOC_NOPM, 0, 0, &lo_in_mux_control),
+
+	SND_SOC_DAPM_SUPPLY("LO Stability Enh", MT6351_AUDDEC_ANA_CON3,
+			    RG_LOOUTPUTSTBENH_VAUDP32_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("LOL Bias Gen", MT6351_AUDDEC_ANA_CON6,
+			    RG_ABIDEC_RSVD0_VAUDP32_LOL_BIT, 0, NULL, 0),
+
+	SND_SOC_DAPM_OUT_DRV("LOL Buffer", MT6351_AUDDEC_ANA_CON3,
+			     RG_AUDLOLPWRUP_VAUDP32_BIT, 0, NULL, 0),
+
+	/* Headphone */
+	SND_SOC_DAPM_MUX("HPL Mux", SND_SOC_NOPM, 0, 0, &hpl_in_mux_control),
+	SND_SOC_DAPM_MUX("HPR Mux", SND_SOC_NOPM, 0, 0, &hpr_in_mux_control),
+
+	SND_SOC_DAPM_OUT_DRV_E("HPL Power", MT6351_AUDDEC_ANA_CON0,
+			       RG_AUDHPLPWRUP_VAUDP32_BIT, 0, NULL, 0,
+			       mt_hp_event,
+			       SND_SOC_DAPM_PRE_PMU |
+			       SND_SOC_DAPM_PRE_PMD |
+			       SND_SOC_DAPM_POST_PMD),
+	SND_SOC_DAPM_OUT_DRV_E("HPR Power", MT6351_AUDDEC_ANA_CON0,
+			       RG_AUDHPRPWRUP_VAUDP32_BIT, 0, NULL, 0,
+			       mt_hp_event,
+			       SND_SOC_DAPM_PRE_PMU |
+			       SND_SOC_DAPM_PRE_PMD |
+			       SND_SOC_DAPM_POST_PMD),
+
+	/* Receiver */
+	SND_SOC_DAPM_MUX("RCV Mux", SND_SOC_NOPM, 0, 0, &rcv_in_mux_control),
+
+	SND_SOC_DAPM_SUPPLY("RCV Stability Enh", MT6351_AUDDEC_ANA_CON1,
+			    RG_HSOUTPUTSTBENH_VAUDP32_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("RCV Bias Gen", MT6351_AUDDEC_ANA_CON6,
+			    RG_ABIDEC_RSVD0_VAUDP32_HS_BIT, 0, NULL, 0),
+
+	SND_SOC_DAPM_OUT_DRV("RCV Buffer", MT6351_AUDDEC_ANA_CON0,
+			     RG_AUDHSPWRUP_VAUDP32_BIT, 0, NULL, 0),
+
+	/* Outputs */
+	SND_SOC_DAPM_OUTPUT("Receiver"),
+	SND_SOC_DAPM_OUTPUT("Headphone L"),
+	SND_SOC_DAPM_OUTPUT("Headphone R"),
+	SND_SOC_DAPM_OUTPUT("LINEOUT L"),
+
+	/* SGEN */
+	SND_SOC_DAPM_SUPPLY("SGEN DL Enable", MT6351_AFE_SGEN_CFG0,
+			    SGEN_C_DAC_EN_CTL_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("SGEN MUTE", MT6351_AFE_SGEN_CFG0,
+			    SGEN_C_MUTE_SW_CTL_BIT, 1,
+			    mt_sgen_event, SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_SUPPLY("SGEN DL SRC", MT6351_AFE_DL_SRC2_CON0_L,
+			    RG_DL_2_SRC_ON_TMP_CTL_PRE_BIT, 0, NULL, 0),
+
+	SND_SOC_DAPM_INPUT("SGEN DL"),
+
+	/* Uplinks */
+	SND_SOC_DAPM_AIF_OUT_E("AIF1TX", "AIF1 Capture", 0,
+			       MT6351_AFE_UL_SRC_CON0_L,
+			       UL_SRC_ON_TMP_CTL, 0,
+			       mt_aif_out_event,
+			       SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD),
+
+	SND_SOC_DAPM_SUPPLY_S("VUSB33_LDO", SUPPLY_SUBSEQ_ENABLE,
+			      MT6351_LDO_VUSB33_CON0, RG_VUSB33_EN, 0,
+			      NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("VUSB33_LDO_CTRL", SUPPLY_SUBSEQ_SETTING,
+			      MT6351_LDO_VUSB33_CON0, RG_VUSB33_ON_CTRL, 1,
+			      NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY_S("VA18_LDO", SUPPLY_SUBSEQ_ENABLE,
+			      MT6351_LDO_VA18_CON0, RG_VA18_EN, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("VA18_LDO_CTRL", SUPPLY_SUBSEQ_SETTING,
+			      MT6351_LDO_VA18_CON0, RG_VA18_ON_CTRL, 1,
+			      NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY_S("ADC CLKGEN", SUPPLY_SUBSEQ_ENABLE,
+			      MT6351_AUDENC_ANA_CON3, RG_AUDADCCLKRSTB, 0,
+			      mt_adc_clkgen_event,
+			      SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+
+	/* Uplinks MUX */
+	SND_SOC_DAPM_MUX("AIF Out Mux", SND_SOC_NOPM, 0, 0,
+			 &aif_out_mux_control),
+
+	SND_SOC_DAPM_MUX("ADC L Mux", SND_SOC_NOPM, 0, 0,
+			 &adc_left_mux_control),
+	SND_SOC_DAPM_MUX("ADC R Mux", SND_SOC_NOPM, 0, 0,
+			 &adc_right_mux_control),
+
+	SND_SOC_DAPM_ADC("ADC L", NULL,
+			 MT6351_AUDENC_ANA_CON0, RG_AUDADCLPWRUP, 0),
+	SND_SOC_DAPM_ADC("ADC R", NULL,
+			 MT6351_AUDENC_ANA_CON1, RG_AUDADCRPWRUP, 0),
+
+	SND_SOC_DAPM_MUX("PGA L Mux", SND_SOC_NOPM, 0, 0,
+			 &pga_left_mux_control),
+	SND_SOC_DAPM_MUX("PGA R Mux", SND_SOC_NOPM, 0, 0,
+			 &pga_right_mux_control),
+
+	SND_SOC_DAPM_PGA_E("PGA L", MT6351_AUDENC_ANA_CON0, RG_AUDPREAMPLON, 0,
+			   NULL, 0,
+			   mt_pga_left_event,
+			   SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+	SND_SOC_DAPM_PGA_E("PGA R", MT6351_AUDENC_ANA_CON1, RG_AUDPREAMPRON, 0,
+			   NULL, 0,
+			   mt_pga_right_event,
+			   SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+
+	/* main mic mic bias */
+	SND_SOC_DAPM_SUPPLY_S("Mic Bias 0", SUPPLY_SUBSEQ_MICBIAS,
+			      MT6351_AUDENC_ANA_CON9, RG_AUDPWDBMICBIAS0, 0,
+			      mt_mic_bias_0_event,
+			      SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+	/* ref mic mic bias */
+	SND_SOC_DAPM_SUPPLY_S("Mic Bias 2", SUPPLY_SUBSEQ_MICBIAS,
+			      MT6351_AUDENC_ANA_CON9, RG_AUDPWDBMICBIAS2, 0,
+			      mt_mic_bias_2_event,
+			      SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+	/* headset mic1/2 mic bias */
+	SND_SOC_DAPM_SUPPLY_S("Mic Bias 1", SUPPLY_SUBSEQ_MICBIAS,
+			      MT6351_AUDENC_ANA_CON10, RG_AUDPWDBMICBIAS1, 0,
+			      mt_mic_bias_1_event,
+			      SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+	SND_SOC_DAPM_SUPPLY_S("Mic Bias 1 DCC pull high", SUPPLY_SUBSEQ_MICBIAS,
+			      MT6351_AUDENC_ANA_CON10,
+			      RG_AUDMICBIAS1DCSW1NEN, 0,
+			      NULL, 0),
+
+	/* UL input */
+	SND_SOC_DAPM_INPUT("AIN0"),
+	SND_SOC_DAPM_INPUT("AIN1"),
+	SND_SOC_DAPM_INPUT("AIN2"),
+	SND_SOC_DAPM_INPUT("AIN3"),
+};
+
+static const struct snd_soc_dapm_route mt6351_dapm_routes[] = {
+	/* Capture */
+	{"AIF1TX", NULL, "AIF Out Mux"},
+	{"AIF1TX", NULL, "VUSB33_LDO"},
+	{"VUSB33_LDO", NULL, "VUSB33_LDO_CTRL"},
+	{"AIF1TX", NULL, "VA18_LDO"},
+	{"VA18_LDO", NULL, "VA18_LDO_CTRL"},
+
+	{"AIF1TX", NULL, "AUDGLB"},
+	{"AIF1TX", NULL, "CLKSQ Audio"},
+
+	{"AIF1TX", NULL, "AFE_ON"},
+
+	{"AIF1TX", NULL, "AUDIO_TOP_AFE_CTL"},
+	{"AIF1TX", NULL, "AUDIO_TOP_ADC_CTL"},
+	{"AIF1TX", NULL, "AUDIO_TOP_PWR_CLK"},
+	{"AIF1TX", NULL, "AUDIO_TOP_PDN_RESERVED"},
+
+	{"AIF Out Mux", "Normal Path", "ADC L"},
+	{"AIF Out Mux", "Normal Path", "ADC R"},
+
+	{"ADC L", NULL, "ADC L Mux"},
+	{"ADC L", NULL, "AUD_CK"},
+	{"ADC L", NULL, "AUDIF_CK"},
+	{"ADC L", NULL, "ADC CLKGEN"},
+	{"ADC R", NULL, "ADC R Mux"},
+	{"ADC R", NULL, "AUD_CK"},
+	{"ADC R", NULL, "AUDIF_CK"},
+	{"ADC R", NULL, "ADC CLKGEN"},
+
+	{"ADC L Mux", "AIN0", "AIN0"},
+	{"ADC L Mux", "Left Preamplifier", "PGA L"},
+
+	{"ADC R Mux", "AIN0", "AIN0"},
+	{"ADC R Mux", "Right Preamplifier", "PGA R"},
+
+	{"PGA L", NULL, "PGA L Mux"},
+	{"PGA R", NULL, "PGA R Mux"},
+
+	{"PGA L Mux", "AIN0", "AIN0"},
+	{"PGA L Mux", "AIN1", "AIN1"},
+	{"PGA L Mux", "AIN2", "AIN2"},
+
+	{"PGA R Mux", "AIN0", "AIN0"},
+	{"PGA R Mux", "AIN3", "AIN3"},
+	{"PGA R Mux", "AIN2", "AIN2"},
+
+	{"AIN0", NULL, "Mic Bias 0"},
+	{"AIN2", NULL, "Mic Bias 2"},
+
+	{"AIN1", NULL, "Mic Bias 1"},
+	{"AIN1", NULL, "Mic Bias 1 DCC pull high"},
+
+	/* DL Supply */
+	{"DL Power Supply", NULL, "AUDGLB"},
+	{"DL Power Supply", NULL, "CLKSQ Audio"},
+	{"DL Power Supply", NULL, "ZCD13M_CK"},
+	{"DL Power Supply", NULL, "AUD_CK"},
+	{"DL Power Supply", NULL, "AUDIF_CK"},
+	{"DL Power Supply", NULL, "AUDNCP_CK"},
+
+	{"DL Power Supply", NULL, "NV Regulator"},
+	{"DL Power Supply", NULL, "AUD_CLK"},
+	{"DL Power Supply", NULL, "IBIST"},
+	{"DL Power Supply", NULL, "LDO"},
+	{"LDO", NULL, "LDO_REMOTE_SENSE"},
+
+	/* DL Digital Supply */
+	{"DL Digital Clock", NULL, "AUDIO_TOP_AFE_CTL"},
+	{"DL Digital Clock", NULL, "AUDIO_TOP_DAC_CTL"},
+	{"DL Digital Clock", NULL, "AUDIO_TOP_PWR_CLK"},
+	{"DL Digital Clock", NULL, "AUDIO_TOP_PDN_RESERVED"},
+	{"DL Digital Clock", NULL, "NCP"},
+	{"DL Digital Clock", NULL, "AFE_ON"},
+
+	{"AIF_RX", NULL, "DL Digital Clock"},
+
+	/* DL Path */
+	{"DAC In Mux", "Normal Path", "AIF_RX"},
+
+	{"DAC In Mux", "Sgen", "SGEN DL"},
+	{"SGEN DL", NULL, "SGEN DL SRC"},
+	{"SGEN DL", NULL, "SGEN MUTE"},
+	{"SGEN DL", NULL, "SGEN DL Enable"},
+	{"SGEN DL", NULL, "DL Digital Clock"},
+
+	{"DACL", NULL, "DAC In Mux"},
+	{"DACL", NULL, "DL Power Supply"},
+	{"DACL", NULL, "DACL_BIASGEN"},
+
+	{"DACR", NULL, "DAC In Mux"},
+	{"DACR", NULL, "DL Power Supply"},
+	{"DACR", NULL, "DACR_BIASGEN"},
+
+	{"LOL Mux", "Playback", "DACL"},
+
+	{"LOL Buffer", NULL, "LOL Mux"},
+	{"LOL Buffer", NULL, "LO Stability Enh"},
+	{"LOL Buffer", NULL, "LOL Bias Gen"},
+
+	{"LINEOUT L", NULL, "LOL Buffer"},
+
+	/* Headphone Path */
+	{"HPL Mux", "Audio Playback", "DACL"},
+	{"HPR Mux", "Audio Playback", "DACR"},
+
+	{"HPL Mux", "LoudSPK Playback", "DACL"},
+	{"HPR Mux", "LoudSPK Playback", "DACR"},
+
+	{"HPL Power", NULL, "HPL Mux"},
+	{"HPR Power", NULL, "HPR Mux"},
+
+	{"Headphone L", NULL, "HPL Power"},
+	{"Headphone R", NULL, "HPR Power"},
+
+	/* Receiver Path */
+	{"RCV Mux", "Voice Playback", "DACL"},
+
+	{"RCV Buffer", NULL, "RCV Mux"},
+	{"RCV Buffer", NULL, "RCV Stability Enh"},
+	{"RCV Buffer", NULL, "RCV Bias Gen"},
+
+	{"Receiver", NULL, "RCV Buffer"},
+};
+
+static int mt6351_codec_init_reg(struct snd_soc_component *cmpnt)
+{
+	int ret = 0;
+
+	/* Disable CLKSQ 26MHz */
+	regmap_update_bits(cmpnt->regmap, MT6351_TOP_CLKSQ, 0x0001, 0x0);
+	/* disable AUDGLB */
+	regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON9,
+			   0x1000, 0x1000);
+	/* Turn off AUDNCP_CLKDIV engine clock,Turn off AUD 26M */
+	regmap_update_bits(cmpnt->regmap, MT6351_TOP_CKPDN_CON0_SET,
+			   0x3800, 0x3800);
+	/* Disable HeadphoneL/HeadphoneR/voice short circuit protection */
+	regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON0,
+			   0xe000, 0xe000);
+	/* [5] = 1, disable LO buffer left short circuit protection */
+	regmap_update_bits(cmpnt->regmap, MT6351_AUDDEC_ANA_CON3,
+			   0x20, 0x20);
+	/* Reverse the PMIC clock*/
+	regmap_update_bits(cmpnt->regmap, MT6351_AFE_PMIC_NEWIF_CFG2,
+			   0x8000, 0x8000);
+	return ret;
+}
+
+static int mt6351_codec_probe(struct snd_soc_component *cmpnt)
+{
+	struct mt6351_priv *priv = snd_soc_component_get_drvdata(cmpnt);
+
+	snd_soc_component_init_regmap(cmpnt, priv->regmap);
+
+	mt6351_codec_init_reg(cmpnt);
+	return 0;
+}
+
+static const struct snd_soc_component_driver mt6351_soc_component_driver = {
+	.probe = mt6351_codec_probe,
+	.controls = mt6351_snd_controls,
+	.num_controls = ARRAY_SIZE(mt6351_snd_controls),
+	.dapm_widgets = mt6351_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(mt6351_dapm_widgets),
+	.dapm_routes = mt6351_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(mt6351_dapm_routes),
+};
+
+static int mt6351_codec_driver_probe(struct platform_device *pdev)
+{
+	struct mt6351_priv *priv;
+
+	priv = devm_kzalloc(&pdev->dev,
+			    sizeof(struct mt6351_priv),
+			    GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev_set_drvdata(&pdev->dev, priv);
+
+	priv->dev = &pdev->dev;
+
+	priv->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!priv->regmap)
+		return -ENODEV;
+
+	dev_dbg(priv->dev, "%s(), dev name %s\n",
+		__func__, dev_name(&pdev->dev));
+
+	return devm_snd_soc_register_component(&pdev->dev,
+					       &mt6351_soc_component_driver,
+					       mt6351_dai_driver,
+					       ARRAY_SIZE(mt6351_dai_driver));
+}
+
+static const struct of_device_id mt6351_of_match[] = {
+	{.compatible = "mediatek,mt6351-sound",},
+	{}
+};
+
+static struct platform_driver mt6351_codec_driver = {
+	.driver = {
+		.name = "mt6351-sound",
+		.of_match_table = mt6351_of_match,
+	},
+	.probe = mt6351_codec_driver_probe,
+};
+
+module_platform_driver(mt6351_codec_driver)
+
+/* Module information */
+MODULE_DESCRIPTION("MT6351 ALSA SoC codec driver");
+MODULE_AUTHOR("KaiChieh Chuang <kaichieh.chuang@mediatek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/mt6351.h b/sound/soc/codecs/mt6351.h
new file mode 100644
index 000000000000..04b2ab694ec7
--- /dev/null
+++ b/sound/soc/codecs/mt6351.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mt6351.h  --  mt6351 ALSA SoC audio codec driver
+ *
+ * Copyright (c) 2018 MediaTek Inc.
+ * Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+ */
+
+#ifndef __MT6351_H__
+#define __MT6351_H__
+
+#define MT6351_AFE_UL_DL_CON0               (0x2000 + 0x0000)
+#define MT6351_AFE_DL_SRC2_CON0_H           (0x2000 + 0x0002)
+#define MT6351_AFE_DL_SRC2_CON0_L           (0x2000 + 0x0004)
+#define MT6351_AFE_DL_SDM_CON0              (0x2000 + 0x0006)
+#define MT6351_AFE_DL_SDM_CON1              (0x2000 + 0x0008)
+#define MT6351_AFE_UL_SRC_CON0_H            (0x2000 + 0x000a)
+#define MT6351_AFE_UL_SRC_CON0_L            (0x2000 + 0x000c)
+#define MT6351_AFE_UL_SRC_CON1_H            (0x2000 + 0x000e)
+#define MT6351_AFE_UL_SRC_CON1_L            (0x2000 + 0x0010)
+#define MT6351_AFE_TOP_CON0                 (0x2000 + 0x0012)
+#define MT6351_AUDIO_TOP_CON0               (0x2000 + 0x0014)
+#define MT6351_AFE_DL_SRC_MON0              (0x2000 + 0x0016)
+#define MT6351_AFE_DL_SDM_TEST0             (0x2000 + 0x0018)
+#define MT6351_AFE_MON_DEBUG0               (0x2000 + 0x001a)
+#define MT6351_AFUNC_AUD_CON0               (0x2000 + 0x001c)
+#define MT6351_AFUNC_AUD_CON1               (0x2000 + 0x001e)
+#define MT6351_AFUNC_AUD_CON2               (0x2000 + 0x0020)
+#define MT6351_AFUNC_AUD_CON3               (0x2000 + 0x0022)
+#define MT6351_AFUNC_AUD_CON4               (0x2000 + 0x0024)
+#define MT6351_AFUNC_AUD_MON0               (0x2000 + 0x0026)
+#define MT6351_AFUNC_AUD_MON1               (0x2000 + 0x0028)
+#define MT6351_AFE_UP8X_FIFO_CFG0           (0x2000 + 0x002c)
+#define MT6351_AFE_UP8X_FIFO_LOG_MON0       (0x2000 + 0x002e)
+#define MT6351_AFE_UP8X_FIFO_LOG_MON1       (0x2000 + 0x0030)
+#define MT6351_AFE_DL_DC_COMP_CFG0          (0x2000 + 0x0032)
+#define MT6351_AFE_DL_DC_COMP_CFG1          (0x2000 + 0x0034)
+#define MT6351_AFE_DL_DC_COMP_CFG2          (0x2000 + 0x0036)
+#define MT6351_AFE_PMIC_NEWIF_CFG0          (0x2000 + 0x0038)
+#define MT6351_AFE_PMIC_NEWIF_CFG1          (0x2000 + 0x003a)
+#define MT6351_AFE_PMIC_NEWIF_CFG2          (0x2000 + 0x003c)
+#define MT6351_AFE_PMIC_NEWIF_CFG3          (0x2000 + 0x003e)
+#define MT6351_AFE_SGEN_CFG0                (0x2000 + 0x0040)
+#define MT6351_AFE_SGEN_CFG1                (0x2000 + 0x0042)
+#define MT6351_AFE_ADDA2_UP8X_FIFO_LOG_MON0 (0x2000 + 0x004c)
+#define MT6351_AFE_ADDA2_UP8X_FIFO_LOG_MON1 (0x2000 + 0x004e)
+#define MT6351_AFE_ADDA2_PMIC_NEWIF_CFG0    (0x2000 + 0x0050)
+#define MT6351_AFE_ADDA2_PMIC_NEWIF_CFG1    (0x2000 + 0x0052)
+#define MT6351_AFE_ADDA2_PMIC_NEWIF_CFG2    (0x2000 + 0x0054)
+#define MT6351_AFE_DCCLK_CFG0               (0x2000 + 0x0090)
+#define MT6351_AFE_DCCLK_CFG1               (0x2000 + 0x0092)
+#define MT6351_AFE_HPANC_CFG0               (0x2000 + 0x0094)
+#define MT6351_AFE_NCP_CFG0                 (0x2000 + 0x0096)
+#define MT6351_AFE_NCP_CFG1                 (0x2000 + 0x0098)
+
+#define MT6351_TOP_CKPDN_CON0      0x023A
+#define MT6351_TOP_CKPDN_CON0_SET  0x023C
+#define MT6351_TOP_CKPDN_CON0_CLR  0x023E
+
+#define MT6351_TOP_CLKSQ           0x029A
+#define MT6351_TOP_CLKSQ_SET       0x029C
+#define MT6351_TOP_CLKSQ_CLR       0x029E
+
+#define MT6351_ZCD_CON0            0x0800
+#define MT6351_ZCD_CON1            0x0802
+#define MT6351_ZCD_CON2            0x0804
+#define MT6351_ZCD_CON3            0x0806
+#define MT6351_ZCD_CON4            0x0808
+#define MT6351_ZCD_CON5            0x080A
+
+#define MT6351_LDO_VA18_CON0       0x0A00
+#define MT6351_LDO_VA18_CON1       0x0A02
+#define MT6351_LDO_VUSB33_CON0     0x0A16
+#define MT6351_LDO_VUSB33_CON1     0x0A18
+
+#define MT6351_AUDDEC_ANA_CON0     0x0CF2
+#define MT6351_AUDDEC_ANA_CON1     0x0CF4
+#define MT6351_AUDDEC_ANA_CON2     0x0CF6
+#define MT6351_AUDDEC_ANA_CON3     0x0CF8
+#define MT6351_AUDDEC_ANA_CON4     0x0CFA
+#define MT6351_AUDDEC_ANA_CON5     0x0CFC
+#define MT6351_AUDDEC_ANA_CON6     0x0CFE
+#define MT6351_AUDDEC_ANA_CON7     0x0D00
+#define MT6351_AUDDEC_ANA_CON8     0x0D02
+#define MT6351_AUDDEC_ANA_CON9     0x0D04
+#define MT6351_AUDDEC_ANA_CON10    0x0D06
+
+#define MT6351_AUDENC_ANA_CON0     0x0D08
+#define MT6351_AUDENC_ANA_CON1     0x0D0A
+#define MT6351_AUDENC_ANA_CON2     0x0D0C
+#define MT6351_AUDENC_ANA_CON3     0x0D0E
+#define MT6351_AUDENC_ANA_CON4     0x0D10
+#define MT6351_AUDENC_ANA_CON5     0x0D12
+#define MT6351_AUDENC_ANA_CON6     0x0D14
+#define MT6351_AUDENC_ANA_CON7     0x0D16
+#define MT6351_AUDENC_ANA_CON8     0x0D18
+#define MT6351_AUDENC_ANA_CON9     0x0D1A
+#define MT6351_AUDENC_ANA_CON10    0x0D1C
+#define MT6351_AUDENC_ANA_CON11    0x0D1E
+#define MT6351_AUDENC_ANA_CON12    0x0D20
+#define MT6351_AUDENC_ANA_CON13    0x0D22
+#define MT6351_AUDENC_ANA_CON14    0x0D24
+#define MT6351_AUDENC_ANA_CON15    0x0D26
+#define MT6351_AUDENC_ANA_CON16    0x0D28
+#endif
diff --git a/sound/soc/codecs/nau8810.c b/sound/soc/codecs/nau8810.c
index ca2ba1c7bb9a..bfd74b86c9d2 100644
--- a/sound/soc/codecs/nau8810.c
+++ b/sound/soc/codecs/nau8810.c
@@ -373,9 +373,11 @@ static const struct snd_kcontrol_new nau8810_mono_mixer_controls[] = {
 };
 
 /* PGA Mute */
-static const struct snd_kcontrol_new nau8810_inpga_mute[] = {
+static const struct snd_kcontrol_new nau8810_pgaboost_mixer_controls[] = {
 	SOC_DAPM_SINGLE("PGA Mute Switch", NAU8810_REG_PGAGAIN,
-		NAU8810_PGAMT_SFT, 1, 0),
+		NAU8810_PGAMT_SFT, 1, 1),
+	SOC_DAPM_SINGLE("PMIC PGA Switch", NAU8810_REG_ADCBOOST,
+		NAU8810_PMICBSTGAIN_SFT, 0x7, 0),
 };
 
 /* Input PGA */
@@ -386,11 +388,6 @@ static const struct snd_kcontrol_new nau8810_inpga[] = {
 		NAU8810_PMICPGA_SFT, 1, 0),
 };
 
-/* Mic Input boost vol */
-static const struct snd_kcontrol_new nau8810_mic_boost_controls =
-	SOC_DAPM_SINGLE("Mic Volume", NAU8810_REG_ADCBOOST,
-		NAU8810_PMICBSTGAIN_SFT, 0x7, 0);
-
 /* Loopback Switch */
 static const struct snd_kcontrol_new nau8810_loopback =
 	SOC_DAPM_SINGLE("Switch", NAU8810_REG_COMP,
@@ -429,8 +426,8 @@ static const struct snd_soc_dapm_widget nau8810_dapm_widgets[] = {
 		NAU8810_PGA_EN_SFT, 0, nau8810_inpga,
 		ARRAY_SIZE(nau8810_inpga)),
 	SND_SOC_DAPM_MIXER("Input Boost Stage", NAU8810_REG_POWER2,
-		NAU8810_BST_EN_SFT, 0, nau8810_inpga_mute,
-		ARRAY_SIZE(nau8810_inpga_mute)),
+		NAU8810_BST_EN_SFT, 0, nau8810_pgaboost_mixer_controls,
+		ARRAY_SIZE(nau8810_pgaboost_mixer_controls)),
 
 	SND_SOC_DAPM_SUPPLY("Mic Bias", NAU8810_REG_POWER1,
 		NAU8810_MICBIAS_EN_SFT, 0, NULL, 0),
@@ -469,8 +466,8 @@ static const struct snd_soc_dapm_route nau8810_dapm_routes[] = {
 	/* Input Boost Stage */
 	{"ADC", NULL, "Input Boost Stage"},
 	{"ADC", NULL, "PLL", check_mclk_select_pll},
-	{"Input Boost Stage", NULL, "Input PGA"},
-	{"Input Boost Stage", NULL, "MICP"},
+	{"Input Boost Stage", "PGA Mute Switch", "Input PGA"},
+	{"Input Boost Stage", "PMIC PGA Switch", "MICP"},
 
 	/* Input PGA */
 	{"Input PGA", NULL, "Mic Bias"},
diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c
index 637e9527805f..6bd14453f06e 100644
--- a/sound/soc/codecs/nau8824.c
+++ b/sound/soc/codecs/nau8824.c
@@ -205,11 +205,11 @@ static int nau8824_sema_acquire(struct nau8824 *nau8824, long timeout)
 	if (timeout) {
 		ret = down_timeout(&nau8824->jd_sem, timeout);
 		if (ret < 0)
-			dev_warn(nau8824->dev, "Acquire semaphone timeout\n");
+			dev_warn(nau8824->dev, "Acquire semaphore timeout\n");
 	} else {
 		ret = down_interruptible(&nau8824->jd_sem);
 		if (ret < 0)
-			dev_warn(nau8824->dev, "Acquire semaphone fail\n");
+			dev_warn(nau8824->dev, "Acquire semaphore fail\n");
 	}
 
 	return ret;
@@ -409,6 +409,15 @@ static const struct snd_kcontrol_new nau8824_snd_controls[] = {
 
 	SOC_SINGLE("DACL LR Mix", NAU8824_REG_DAC_MUTE_CTRL, 0, 1, 0),
 	SOC_SINGLE("DACR LR Mix", NAU8824_REG_DAC_MUTE_CTRL, 1, 1, 0),
+
+	SOC_SINGLE("THD for key media",
+		NAU8824_REG_VDET_THRESHOLD_1, 8, 0xff, 0),
+	SOC_SINGLE("THD for key voice command",
+		NAU8824_REG_VDET_THRESHOLD_1, 0, 0xff, 0),
+	SOC_SINGLE("THD for key volume up",
+		NAU8824_REG_VDET_THRESHOLD_2, 8, 0xff, 0),
+	SOC_SINGLE("THD for key volume down",
+		NAU8824_REG_VDET_THRESHOLD_2, 0, 0xff, 0),
 };
 
 static int nau8824_output_dac_event(struct snd_soc_dapm_widget *w,
diff --git a/sound/soc/codecs/pcm1789.c b/sound/soc/codecs/pcm1789.c
index 507ac9412d6c..21f15219b3ad 100644
--- a/sound/soc/codecs/pcm1789.c
+++ b/sound/soc/codecs/pcm1789.c
@@ -3,7 +3,7 @@
 // Copyright (C) 2018 Bootlin
 // Mylène Josserand <mylene.josserand@bootlin.com>
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/workqueue.h>
 
diff --git a/sound/soc/codecs/pcm512x-i2c.c b/sound/soc/codecs/pcm512x-i2c.c
index 5f9c069569d5..0fe5ced841a3 100644
--- a/sound/soc/codecs/pcm512x-i2c.c
+++ b/sound/soc/codecs/pcm512x-i2c.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/i2c.h>
+#include <linux/acpi.h>
 
 #include "pcm512x.h"
 
@@ -52,6 +53,7 @@ static const struct i2c_device_id pcm512x_i2c_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, pcm512x_i2c_id);
 
+#if defined(CONFIG_OF)
 static const struct of_device_id pcm512x_of_match[] = {
 	{ .compatible = "ti,pcm5121", },
 	{ .compatible = "ti,pcm5122", },
@@ -60,6 +62,18 @@ static const struct of_device_id pcm512x_of_match[] = {
 	{ }
 };
 MODULE_DEVICE_TABLE(of, pcm512x_of_match);
+#endif
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id pcm512x_acpi_match[] = {
+	{ "104C5121", 0 },
+	{ "104C5122", 0 },
+	{ "104C5141", 0 },
+	{ "104C5142", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, pcm512x_acpi_match);
+#endif
 
 static struct i2c_driver pcm512x_i2c_driver = {
 	.probe 		= pcm512x_i2c_probe,
@@ -67,7 +81,8 @@ static struct i2c_driver pcm512x_i2c_driver = {
 	.id_table	= pcm512x_i2c_id,
 	.driver		= {
 		.name	= "pcm512x",
-		.of_match_table = pcm512x_of_match,
+		.of_match_table = of_match_ptr(pcm512x_of_match),
+		.acpi_match_table = ACPI_PTR(pcm512x_acpi_match),
 		.pm     = &pcm512x_pm_ops,
 	},
 };
diff --git a/sound/soc/codecs/rt1305.c b/sound/soc/codecs/rt1305.c
new file mode 100644
index 000000000000..f4c8c45f4010
--- /dev/null
+++ b/sound/soc/codecs/rt1305.c
@@ -0,0 +1,1191 @@
+/*
+ * rt1305.c  --  RT1305 ALSA SoC amplifier component driver
+ *
+ * Copyright 2018 Realtek Semiconductor Corp.
+ * Author: Shuming Fan <shumingf@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/pm.h>
+#include <linux/acpi.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+#include <linux/of_gpio.h>
+#include <linux/platform_device.h>
+#include <linux/firmware.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+
+#include "rl6231.h"
+#include "rt1305.h"
+
+
+#define RT1305_PR_RANGE_BASE (0xff + 1)
+#define RT1305_PR_SPACING 0x100
+
+#define RT1305_PR_BASE (RT1305_PR_RANGE_BASE + (0 * RT1305_PR_SPACING))
+
+
+static const struct regmap_range_cfg rt1305_ranges[] = {
+	{
+		.name = "PR",
+		.range_min = RT1305_PR_BASE,
+		.range_max = RT1305_PR_BASE + 0xff,
+		.selector_reg = RT1305_PRIV_INDEX,
+		.selector_mask = 0xff,
+		.selector_shift = 0x0,
+		.window_start = RT1305_PRIV_DATA,
+		.window_len = 0x1,
+	},
+};
+
+
+static const struct reg_sequence init_list[] = {
+
+	{ RT1305_PR_BASE + 0xcf, 0x5548 },
+	{ RT1305_PR_BASE + 0x5d, 0x0442 },
+	{ RT1305_PR_BASE + 0xc1, 0x0320 },
+
+	{ RT1305_POWER_STATUS, 0x0000 },
+
+	{ RT1305_SPK_TEMP_PROTECTION_1, 0xd6de },
+	{ RT1305_SPK_TEMP_PROTECTION_2, 0x0707 },
+	{ RT1305_SPK_TEMP_PROTECTION_3, 0x4090 },
+
+	{ RT1305_DAC_SET_1, 0xdfdf },	/* 4 ohm 2W  */
+	{ RT1305_ADC_SET_3, 0x0219 },
+	{ RT1305_ADC_SET_1, 0x170f },	/* 0.2 ohm RSense*/
+
+};
+#define RT1305_INIT_REG_LEN ARRAY_SIZE(init_list)
+
+struct rt1305_priv {
+	struct snd_soc_component *component;
+	struct regmap *regmap;
+
+	int sysclk;
+	int sysclk_src;
+	int lrck;
+	int bclk;
+	int master;
+
+	int pll_src;
+	int pll_in;
+	int pll_out;
+};
+
+static const struct reg_default rt1305_reg[] = {
+
+	{ 0x04, 0x0400 },
+	{ 0x05, 0x0880 },
+	{ 0x06, 0x0000 },
+	{ 0x07, 0x3100 },
+	{ 0x08, 0x8000 },
+	{ 0x09, 0x0000 },
+	{ 0x0a, 0x087e },
+	{ 0x0b, 0x0020 },
+	{ 0x0c, 0x0802 },
+	{ 0x0d, 0x0020 },
+	{ 0x10, 0x1d1d },
+	{ 0x11, 0x1d1d },
+	{ 0x12, 0xffff },
+	{ 0x14, 0x000c },
+	{ 0x16, 0x1717 },
+	{ 0x17, 0x4000 },
+	{ 0x18, 0x0019 },
+	{ 0x20, 0x0000 },
+	{ 0x22, 0x0000 },
+	{ 0x24, 0x0000 },
+	{ 0x26, 0x0000 },
+	{ 0x28, 0x0000 },
+	{ 0x2a, 0x4000 },
+	{ 0x2b, 0x3000 },
+	{ 0x2d, 0x6000 },
+	{ 0x2e, 0x0000 },
+	{ 0x2f, 0x8000 },
+	{ 0x32, 0x0000 },
+	{ 0x39, 0x0001 },
+	{ 0x3a, 0x0000 },
+	{ 0x3b, 0x1020 },
+	{ 0x3c, 0x0000 },
+	{ 0x3d, 0x0000 },
+	{ 0x3e, 0x4c00 },
+	{ 0x3f, 0x3000 },
+	{ 0x40, 0x000c },
+	{ 0x42, 0x0400 },
+	{ 0x46, 0xc22c },
+	{ 0x47, 0x0000 },
+	{ 0x4b, 0x0000 },
+	{ 0x4c, 0x0300 },
+	{ 0x4f, 0xf000 },
+	{ 0x50, 0xc200 },
+	{ 0x51, 0x1f1f },
+	{ 0x52, 0x01f0 },
+	{ 0x53, 0x407f },
+	{ 0x54, 0xffff },
+	{ 0x58, 0x4005 },
+	{ 0x5e, 0x0000 },
+	{ 0x5f, 0x0000 },
+	{ 0x60, 0xee13 },
+	{ 0x62, 0x0000 },
+	{ 0x63, 0x5f5f },
+	{ 0x64, 0x0040 },
+	{ 0x65, 0x4000 },
+	{ 0x66, 0x4004 },
+	{ 0x67, 0x0306 },
+	{ 0x68, 0x8c04 },
+	{ 0x69, 0xe021 },
+	{ 0x6a, 0x0000 },
+	{ 0x6c, 0xaaaa },
+	{ 0x70, 0x0333 },
+	{ 0x71, 0x3330 },
+	{ 0x72, 0x3333 },
+	{ 0x73, 0x3300 },
+	{ 0x74, 0x0000 },
+	{ 0x75, 0x0000 },
+	{ 0x76, 0x0000 },
+	{ 0x7a, 0x0003 },
+	{ 0x7c, 0x10ec },
+	{ 0x7e, 0x6251 },
+	{ 0x80, 0x0800 },
+	{ 0x81, 0x4000 },
+	{ 0x82, 0x0000 },
+	{ 0x90, 0x7a01 },
+	{ 0x91, 0x8431 },
+	{ 0x92, 0x0180 },
+	{ 0x93, 0x0000 },
+	{ 0x94, 0x0000 },
+	{ 0x95, 0x0000 },
+	{ 0x96, 0x0000 },
+	{ 0x97, 0x0000 },
+	{ 0x98, 0x0000 },
+	{ 0x99, 0x0000 },
+	{ 0x9a, 0x0000 },
+	{ 0x9b, 0x0000 },
+	{ 0x9c, 0x0000 },
+	{ 0x9d, 0x0000 },
+	{ 0x9e, 0x0000 },
+	{ 0x9f, 0x0000 },
+	{ 0xa0, 0x0000 },
+	{ 0xb0, 0x8200 },
+	{ 0xb1, 0x00ff },
+	{ 0xb2, 0x0008 },
+	{ 0xc0, 0x0200 },
+	{ 0xc1, 0x0000 },
+	{ 0xc2, 0x0000 },
+	{ 0xc3, 0x0000 },
+	{ 0xc4, 0x0000 },
+	{ 0xc5, 0x0000 },
+	{ 0xc6, 0x0000 },
+	{ 0xc7, 0x0000 },
+	{ 0xc8, 0x0000 },
+	{ 0xc9, 0x0000 },
+	{ 0xca, 0x0200 },
+	{ 0xcb, 0x0000 },
+	{ 0xcc, 0x0000 },
+	{ 0xcd, 0x0000 },
+	{ 0xce, 0x0000 },
+	{ 0xcf, 0x0000 },
+	{ 0xd0, 0x0000 },
+	{ 0xd1, 0x0000 },
+	{ 0xd2, 0x0000 },
+	{ 0xd3, 0x0000 },
+	{ 0xd4, 0x0200 },
+	{ 0xd5, 0x0000 },
+	{ 0xd6, 0x0000 },
+	{ 0xd7, 0x0000 },
+	{ 0xd8, 0x0000 },
+	{ 0xd9, 0x0000 },
+	{ 0xda, 0x0000 },
+	{ 0xdb, 0x0000 },
+	{ 0xdc, 0x0000 },
+	{ 0xdd, 0x0000 },
+	{ 0xde, 0x0200 },
+	{ 0xdf, 0x0000 },
+	{ 0xe0, 0x0000 },
+	{ 0xe1, 0x0000 },
+	{ 0xe2, 0x0000 },
+	{ 0xe3, 0x0000 },
+	{ 0xe4, 0x0000 },
+	{ 0xe5, 0x0000 },
+	{ 0xe6, 0x0000 },
+	{ 0xe7, 0x0000 },
+	{ 0xe8, 0x0200 },
+	{ 0xe9, 0x0000 },
+	{ 0xea, 0x0000 },
+	{ 0xeb, 0x0000 },
+	{ 0xec, 0x0000 },
+	{ 0xed, 0x0000 },
+	{ 0xee, 0x0000 },
+	{ 0xef, 0x0000 },
+	{ 0xf0, 0x0000 },
+	{ 0xf1, 0x0000 },
+	{ 0xf2, 0x0200 },
+	{ 0xf3, 0x0000 },
+	{ 0xf4, 0x0000 },
+	{ 0xf5, 0x0000 },
+	{ 0xf6, 0x0000 },
+	{ 0xf7, 0x0000 },
+	{ 0xf8, 0x0000 },
+	{ 0xf9, 0x0000 },
+	{ 0xfa, 0x0000 },
+	{ 0xfb, 0x0000 },
+};
+
+static int rt1305_reg_init(struct snd_soc_component *component)
+{
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+
+	regmap_multi_reg_write(rt1305->regmap, init_list, RT1305_INIT_REG_LEN);
+	return 0;
+}
+
+static bool rt1305_volatile_register(struct device *dev, unsigned int reg)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rt1305_ranges); i++) {
+		if (reg >= rt1305_ranges[i].range_min &&
+			reg <= rt1305_ranges[i].range_max) {
+			return true;
+		}
+	}
+
+	switch (reg) {
+	case RT1305_RESET:
+	case RT1305_SPDIF_IN_SET_1:
+	case RT1305_SPDIF_IN_SET_2:
+	case RT1305_SPDIF_IN_SET_3:
+	case RT1305_POWER_CTRL_2:
+	case RT1305_CLOCK_DETECT:
+	case RT1305_BIQUAD_SET_1:
+	case RT1305_BIQUAD_SET_2:
+	case RT1305_EQ_SET_2:
+	case RT1305_SPK_TEMP_PROTECTION_0:
+	case RT1305_SPK_TEMP_PROTECTION_2:
+	case RT1305_SPK_DC_DETECT_1:
+	case RT1305_SILENCE_DETECT:
+	case RT1305_VERSION_ID:
+	case RT1305_VENDOR_ID:
+	case RT1305_DEVICE_ID:
+	case RT1305_EFUSE_1:
+	case RT1305_EFUSE_3:
+	case RT1305_DC_CALIB_1:
+	case RT1305_DC_CALIB_3:
+	case RT1305_DAC_OFFSET_1:
+	case RT1305_DAC_OFFSET_2:
+	case RT1305_DAC_OFFSET_3:
+	case RT1305_DAC_OFFSET_4:
+	case RT1305_DAC_OFFSET_5:
+	case RT1305_DAC_OFFSET_6:
+	case RT1305_DAC_OFFSET_7:
+	case RT1305_DAC_OFFSET_8:
+	case RT1305_DAC_OFFSET_9:
+	case RT1305_DAC_OFFSET_10:
+	case RT1305_DAC_OFFSET_11:
+	case RT1305_TRIM_1:
+	case RT1305_TRIM_2:
+		return true;
+
+	default:
+		return false;
+	}
+}
+
+static bool rt1305_readable_register(struct device *dev, unsigned int reg)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rt1305_ranges); i++) {
+		if (reg >= rt1305_ranges[i].range_min &&
+			reg <= rt1305_ranges[i].range_max) {
+			return true;
+		}
+	}
+
+	switch (reg) {
+	case RT1305_RESET:
+	case RT1305_CLK_1 ... RT1305_CAL_EFUSE_CLOCK:
+	case RT1305_PLL0_1 ... RT1305_PLL1_2:
+	case RT1305_MIXER_CTRL_1:
+	case RT1305_MIXER_CTRL_2:
+	case RT1305_DAC_SET_1:
+	case RT1305_DAC_SET_2:
+	case RT1305_ADC_SET_1:
+	case RT1305_ADC_SET_2:
+	case RT1305_ADC_SET_3:
+	case RT1305_PATH_SET:
+	case RT1305_SPDIF_IN_SET_1:
+	case RT1305_SPDIF_IN_SET_2:
+	case RT1305_SPDIF_IN_SET_3:
+	case RT1305_SPDIF_OUT_SET_1:
+	case RT1305_SPDIF_OUT_SET_2:
+	case RT1305_SPDIF_OUT_SET_3:
+	case RT1305_I2S_SET_1:
+	case RT1305_I2S_SET_2:
+	case RT1305_PBTL_MONO_MODE_SRC:
+	case RT1305_MANUALLY_I2C_DEVICE:
+	case RT1305_POWER_STATUS:
+	case RT1305_POWER_CTRL_1:
+	case RT1305_POWER_CTRL_2:
+	case RT1305_POWER_CTRL_3:
+	case RT1305_POWER_CTRL_4:
+	case RT1305_POWER_CTRL_5:
+	case RT1305_CLOCK_DETECT:
+	case RT1305_BIQUAD_SET_1:
+	case RT1305_BIQUAD_SET_2:
+	case RT1305_ADJUSTED_HPF_1:
+	case RT1305_ADJUSTED_HPF_2:
+	case RT1305_EQ_SET_1:
+	case RT1305_EQ_SET_2:
+	case RT1305_SPK_TEMP_PROTECTION_0:
+	case RT1305_SPK_TEMP_PROTECTION_1:
+	case RT1305_SPK_TEMP_PROTECTION_2:
+	case RT1305_SPK_TEMP_PROTECTION_3:
+	case RT1305_SPK_DC_DETECT_1:
+	case RT1305_SPK_DC_DETECT_2:
+	case RT1305_LOUDNESS:
+	case RT1305_THERMAL_FOLD_BACK_1:
+	case RT1305_THERMAL_FOLD_BACK_2:
+	case RT1305_SILENCE_DETECT ... RT1305_SPK_EXCURSION_LIMITER_7:
+	case RT1305_VERSION_ID:
+	case RT1305_VENDOR_ID:
+	case RT1305_DEVICE_ID:
+	case RT1305_EFUSE_1:
+	case RT1305_EFUSE_2:
+	case RT1305_EFUSE_3:
+	case RT1305_DC_CALIB_1:
+	case RT1305_DC_CALIB_2:
+	case RT1305_DC_CALIB_3:
+	case RT1305_DAC_OFFSET_1 ... RT1305_DAC_OFFSET_14:
+	case RT1305_TRIM_1:
+	case RT1305_TRIM_2:
+	case RT1305_TUNE_INTERNAL_OSC:
+	case RT1305_BIQUAD1_H0_L_28_16 ... RT1305_BIQUAD3_A2_R_15_0:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -9435, 37, 0);
+
+static const char * const rt1305_rx_data_ch_select[] = {
+	"LR",
+	"RL",
+	"Copy L",
+	"Copy R",
+};
+
+static SOC_ENUM_SINGLE_DECL(rt1305_rx_data_ch_enum, RT1305_I2S_SET_2, 2,
+	rt1305_rx_data_ch_select);
+
+static void rt1305_reset(struct regmap *regmap)
+{
+	regmap_write(regmap, RT1305_RESET, 0);
+}
+
+static const struct snd_kcontrol_new rt1305_snd_controls[] = {
+	SOC_DOUBLE_TLV("DAC Playback Volume", RT1305_DAC_SET_1,
+			8, 0, 0xff, 0, dac_vol_tlv),
+
+	/* I2S Data Channel Selection */
+	SOC_ENUM("RX Channel Select", rt1305_rx_data_ch_enum),
+};
+
+static int rt1305_is_rc_clk_from_pll(struct snd_soc_dapm_widget *source,
+			 struct snd_soc_dapm_widget *sink)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(source->dapm);
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+	unsigned int val;
+
+	snd_soc_component_read(component, RT1305_CLK_1, &val);
+
+	if (rt1305->sysclk_src == RT1305_FS_SYS_PRE_S_PLL1 &&
+		(val & RT1305_SEL_PLL_SRC_2_RCCLK))
+		return 1;
+	else
+		return 0;
+}
+
+static int rt1305_is_sys_clk_from_pll(struct snd_soc_dapm_widget *source,
+			 struct snd_soc_dapm_widget *sink)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(source->dapm);
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+
+	if (rt1305->sysclk_src == RT1305_FS_SYS_PRE_S_PLL1)
+		return 1;
+	else
+		return 0;
+}
+
+static int rt1305_classd_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		snd_soc_component_update_bits(component, RT1305_POWER_CTRL_1,
+			RT1305_POW_PDB_JD_MASK, RT1305_POW_PDB_JD);
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		snd_soc_component_update_bits(component, RT1305_POWER_CTRL_1,
+			RT1305_POW_PDB_JD_MASK, 0);
+		usleep_range(150000, 200000);
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static const struct snd_kcontrol_new rt1305_sto_dac_l =
+	SOC_DAPM_SINGLE("Switch", RT1305_DAC_SET_2,
+		RT1305_DVOL_MUTE_L_EN_SFT, 1, 1);
+
+static const struct snd_kcontrol_new rt1305_sto_dac_r =
+	SOC_DAPM_SINGLE("Switch", RT1305_DAC_SET_2,
+		RT1305_DVOL_MUTE_R_EN_SFT, 1, 1);
+
+static const struct snd_soc_dapm_widget rt1305_dapm_widgets[] = {
+	SND_SOC_DAPM_SUPPLY("PLL0", RT1305_POWER_CTRL_1,
+		RT1305_POW_PLL0_EN_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL1", RT1305_POWER_CTRL_1,
+		RT1305_POW_PLL1_EN_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("MBIAS", RT1305_POWER_CTRL_1,
+		RT1305_POW_MBIAS_LV_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("BG MBIAS", RT1305_POWER_CTRL_1,
+		RT1305_POW_BG_MBIAS_LV_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("LDO2", RT1305_POWER_CTRL_1,
+		RT1305_POW_LDO2_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("BG2", RT1305_POWER_CTRL_1,
+		RT1305_POW_BG2_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("LDO2 IB2", RT1305_POWER_CTRL_1,
+		RT1305_POW_LDO2_IB2_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("VREF", RT1305_POWER_CTRL_1,
+		RT1305_POW_VREF_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("VREF1", RT1305_POWER_CTRL_1,
+		RT1305_POW_VREF1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("VREF2", RT1305_POWER_CTRL_1,
+		RT1305_POW_VREF2_BIT, 0, NULL, 0),
+
+
+	SND_SOC_DAPM_SUPPLY("DISC VREF", RT1305_POWER_CTRL_2,
+		RT1305_POW_DISC_VREF_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("FASTB VREF", RT1305_POWER_CTRL_2,
+		RT1305_POW_FASTB_VREF_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ULTRA FAST VREF", RT1305_POWER_CTRL_2,
+		RT1305_POW_ULTRA_FAST_VREF_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CHOP DAC", RT1305_POWER_CTRL_2,
+		RT1305_POW_CKXEN_DAC_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CKGEN DAC", RT1305_POWER_CTRL_2,
+		RT1305_POW_EN_CKGEN_DAC_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLAMP", RT1305_POWER_CTRL_2,
+		RT1305_POW_CLAMP_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("BUFL", RT1305_POWER_CTRL_2,
+		RT1305_POW_BUFL_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("BUFR", RT1305_POWER_CTRL_2,
+		RT1305_POW_BUFR_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CKGEN ADC", RT1305_POWER_CTRL_2,
+		RT1305_POW_EN_CKGEN_ADC_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC3 L", RT1305_POWER_CTRL_2,
+		RT1305_POW_ADC3_L_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC3 R", RT1305_POWER_CTRL_2,
+		RT1305_POW_ADC3_R_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("TRIOSC", RT1305_POWER_CTRL_2,
+		RT1305_POW_TRIOSC_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("AVDD1", RT1305_POWER_CTRL_2,
+		RT1305_POR_AVDD1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("AVDD2", RT1305_POWER_CTRL_2,
+		RT1305_POR_AVDD2_BIT, 0, NULL, 0),
+
+
+	SND_SOC_DAPM_SUPPLY("VSENSE R", RT1305_POWER_CTRL_3,
+		RT1305_POW_VSENSE_RCH_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("VSENSE L", RT1305_POWER_CTRL_3,
+		RT1305_POW_VSENSE_LCH_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ISENSE R", RT1305_POWER_CTRL_3,
+		RT1305_POW_ISENSE_RCH_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ISENSE L", RT1305_POWER_CTRL_3,
+		RT1305_POW_ISENSE_LCH_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("POR AVDD1", RT1305_POWER_CTRL_3,
+		RT1305_POW_POR_AVDD1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("POR AVDD2", RT1305_POWER_CTRL_3,
+		RT1305_POW_POR_AVDD2_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("VCM 6172", RT1305_POWER_CTRL_3,
+		RT1305_EN_VCM_6172_BIT, 0, NULL, 0),
+
+
+	/* Audio Interface */
+	SND_SOC_DAPM_AIF_IN("AIF1RX", "AIF1 Playback", 0, SND_SOC_NOPM, 0, 0),
+
+	/* Digital Interface */
+	SND_SOC_DAPM_SUPPLY("DAC L Power", RT1305_POWER_CTRL_2,
+		RT1305_POW_DAC1_L_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DAC R Power", RT1305_POWER_CTRL_2,
+		RT1305_POW_DAC1_R_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_DAC("DAC", NULL, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_SWITCH("DAC L", SND_SOC_NOPM, 0, 0, &rt1305_sto_dac_l),
+	SND_SOC_DAPM_SWITCH("DAC R", SND_SOC_NOPM, 0, 0, &rt1305_sto_dac_r),
+
+	/* Output Lines */
+	SND_SOC_DAPM_PGA_E("CLASS D", SND_SOC_NOPM, 0, 0, NULL, 0,
+		rt1305_classd_event,
+		SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMU),
+	SND_SOC_DAPM_OUTPUT("SPOL"),
+	SND_SOC_DAPM_OUTPUT("SPOR"),
+};
+
+static const struct snd_soc_dapm_route rt1305_dapm_routes[] = {
+
+	{ "DAC", NULL, "AIF1RX" },
+
+	{ "DAC", NULL, "PLL0", rt1305_is_rc_clk_from_pll },
+	{ "DAC", NULL, "PLL1", rt1305_is_sys_clk_from_pll },
+
+	{ "DAC", NULL, "MBIAS" },
+	{ "DAC", NULL, "BG MBIAS" },
+	{ "DAC", NULL, "LDO2" },
+	{ "DAC", NULL, "BG2" },
+	{ "DAC", NULL, "LDO2 IB2" },
+	{ "DAC", NULL, "VREF" },
+	{ "DAC", NULL, "VREF1" },
+	{ "DAC", NULL, "VREF2" },
+
+	{ "DAC", NULL, "DISC VREF" },
+	{ "DAC", NULL, "FASTB VREF" },
+	{ "DAC", NULL, "ULTRA FAST VREF" },
+	{ "DAC", NULL, "CHOP DAC" },
+	{ "DAC", NULL, "CKGEN DAC" },
+	{ "DAC", NULL, "CLAMP" },
+	{ "DAC", NULL, "CKGEN ADC" },
+	{ "DAC", NULL, "TRIOSC" },
+	{ "DAC", NULL, "AVDD1" },
+	{ "DAC", NULL, "AVDD2" },
+
+	{ "DAC", NULL, "POR AVDD1" },
+	{ "DAC", NULL, "POR AVDD2" },
+	{ "DAC", NULL, "VCM 6172" },
+
+	{ "DAC L", "Switch", "DAC" },
+	{ "DAC R", "Switch", "DAC" },
+
+	{ "DAC R", NULL, "VSENSE R" },
+	{ "DAC L", NULL, "VSENSE L" },
+	{ "DAC R", NULL, "ISENSE R" },
+	{ "DAC L", NULL, "ISENSE L" },
+	{ "DAC L", NULL, "ADC3 L" },
+	{ "DAC R", NULL, "ADC3 R" },
+	{ "DAC L", NULL, "BUFL" },
+	{ "DAC R", NULL, "BUFR" },
+	{ "DAC L", NULL, "DAC L Power" },
+	{ "DAC R", NULL, "DAC R Power" },
+
+	{ "CLASS D", NULL, "DAC L" },
+	{ "CLASS D", NULL, "DAC R" },
+
+	{ "SPOL", NULL, "CLASS D" },
+	{ "SPOR", NULL, "CLASS D" },
+};
+
+static int rt1305_get_clk_info(int sclk, int rate)
+{
+	int i, pd[] = {1, 2, 3, 4, 6, 8, 12, 16};
+
+	if (sclk <= 0 || rate <= 0)
+		return -EINVAL;
+
+	rate = rate << 8;
+	for (i = 0; i < ARRAY_SIZE(pd); i++)
+		if (sclk == rate * pd[i])
+			return i;
+
+	return -EINVAL;
+}
+
+static int rt1305_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+	unsigned int val_len = 0, val_clk, mask_clk;
+	int pre_div, bclk_ms, frame_size;
+
+	rt1305->lrck = params_rate(params);
+	pre_div = rt1305_get_clk_info(rt1305->sysclk, rt1305->lrck);
+	if (pre_div < 0) {
+		dev_warn(component->dev, "Force using PLL ");
+		snd_soc_dai_set_pll(dai, 0, RT1305_PLL1_S_BCLK,
+			rt1305->lrck * 64, rt1305->lrck * 256);
+		snd_soc_dai_set_sysclk(dai, RT1305_FS_SYS_PRE_S_PLL1,
+			rt1305->lrck * 256, SND_SOC_CLOCK_IN);
+		pre_div = 0;
+	}
+	frame_size = snd_soc_params_to_frame_size(params);
+	if (frame_size < 0) {
+		dev_err(component->dev, "Unsupported frame size: %d\n",
+			frame_size);
+		return -EINVAL;
+	}
+
+	bclk_ms = frame_size > 32;
+	rt1305->bclk = rt1305->lrck * (32 << bclk_ms);
+
+	dev_dbg(component->dev, "bclk_ms is %d and pre_div is %d for iis %d\n",
+				bclk_ms, pre_div, dai->id);
+
+	dev_dbg(component->dev, "lrck is %dHz and pre_div is %d for iis %d\n",
+				rt1305->lrck, pre_div, dai->id);
+
+	switch (params_width(params)) {
+	case 16:
+		val_len |= RT1305_I2S_DL_SEL_16B;
+		break;
+	case 20:
+		val_len |= RT1305_I2S_DL_SEL_20B;
+		break;
+	case 24:
+		val_len |= RT1305_I2S_DL_SEL_24B;
+		break;
+	case 8:
+		val_len |= RT1305_I2S_DL_SEL_8B;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case RT1305_AIF1:
+		mask_clk = RT1305_DIV_FS_SYS_MASK;
+		val_clk = pre_div << RT1305_DIV_FS_SYS_SFT;
+		snd_soc_component_update_bits(component, RT1305_I2S_SET_2,
+			RT1305_I2S_DL_SEL_MASK,
+			val_len);
+		break;
+	default:
+		dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
+		return -EINVAL;
+	}
+
+	snd_soc_component_update_bits(component, RT1305_CLK_2,
+		mask_clk, val_clk);
+
+	return 0;
+}
+
+static int rt1305_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+	unsigned int reg_val = 0, reg1_val = 0;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		reg_val |= RT1305_SEL_I2S_OUT_MODE_M;
+		rt1305->master = 1;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		reg_val |= RT1305_SEL_I2S_OUT_MODE_S;
+		rt1305->master = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		reg1_val |= RT1305_I2S_BCLK_INV;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		reg1_val |= RT1305_I2S_DF_SEL_LEFT;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		reg1_val |= RT1305_I2S_DF_SEL_PCM_A;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		reg1_val |= RT1305_I2S_DF_SEL_PCM_B;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case RT1305_AIF1:
+		snd_soc_component_update_bits(component, RT1305_I2S_SET_1,
+			RT1305_SEL_I2S_OUT_MODE_MASK, reg_val);
+		snd_soc_component_update_bits(component, RT1305_I2S_SET_2,
+			RT1305_I2S_DF_SEL_MASK | RT1305_I2S_BCLK_MASK,
+			reg1_val);
+		break;
+	default:
+		dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int rt1305_set_component_sysclk(struct snd_soc_component *component,
+		int clk_id, int source, unsigned int freq, int dir)
+{
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+	unsigned int reg_val = 0;
+
+	if (freq == rt1305->sysclk && clk_id == rt1305->sysclk_src)
+		return 0;
+
+	switch (clk_id) {
+	case RT1305_FS_SYS_PRE_S_MCLK:
+		reg_val |= RT1305_SEL_FS_SYS_PRE_MCLK;
+		snd_soc_component_update_bits(component,
+			RT1305_CLOCK_DETECT, RT1305_SEL_CLK_DET_SRC_MASK,
+			RT1305_SEL_CLK_DET_SRC_MCLK);
+		break;
+	case RT1305_FS_SYS_PRE_S_PLL1:
+		reg_val |= RT1305_SEL_FS_SYS_PRE_PLL;
+		break;
+	case RT1305_FS_SYS_PRE_S_RCCLK:
+		reg_val |= RT1305_SEL_FS_SYS_PRE_RCCLK;
+		break;
+	default:
+		dev_err(component->dev, "Invalid clock id (%d)\n", clk_id);
+		return -EINVAL;
+	}
+	snd_soc_component_update_bits(component, RT1305_CLK_1,
+		RT1305_SEL_FS_SYS_PRE_MASK, reg_val);
+	rt1305->sysclk = freq;
+	rt1305->sysclk_src = clk_id;
+
+	dev_dbg(component->dev, "Sysclk is %dHz and clock id is %d\n",
+		freq, clk_id);
+
+	return 0;
+}
+
+static int rt1305_set_component_pll(struct snd_soc_component *component,
+		int pll_id, int source, unsigned int freq_in,
+		unsigned int freq_out)
+{
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+	struct rl6231_pll_code pll_code;
+	int ret;
+
+	if (source == rt1305->pll_src && freq_in == rt1305->pll_in &&
+	    freq_out == rt1305->pll_out)
+		return 0;
+
+	if (!freq_in || !freq_out) {
+		dev_dbg(component->dev, "PLL disabled\n");
+
+		rt1305->pll_in = 0;
+		rt1305->pll_out = 0;
+		snd_soc_component_update_bits(component, RT1305_CLK_1,
+			RT1305_SEL_FS_SYS_PRE_MASK | RT1305_SEL_PLL_SRC_1_MASK,
+			RT1305_SEL_FS_SYS_PRE_PLL | RT1305_SEL_PLL_SRC_1_BCLK);
+		return 0;
+	}
+
+	switch (source) {
+	case RT1305_PLL2_S_MCLK:
+		snd_soc_component_update_bits(component, RT1305_CLK_1,
+			RT1305_SEL_PLL_SRC_2_MASK | RT1305_SEL_PLL_SRC_1_MASK |
+			RT1305_DIV_PLL_SRC_2_MASK,
+			RT1305_SEL_PLL_SRC_2_MCLK | RT1305_SEL_PLL_SRC_1_PLL2);
+		snd_soc_component_update_bits(component,
+			RT1305_CLOCK_DETECT, RT1305_SEL_CLK_DET_SRC_MASK,
+			RT1305_SEL_CLK_DET_SRC_MCLK);
+		break;
+	case RT1305_PLL1_S_BCLK:
+		snd_soc_component_update_bits(component,
+			RT1305_CLK_1, RT1305_SEL_PLL_SRC_1_MASK,
+			RT1305_SEL_PLL_SRC_1_BCLK);
+		break;
+	case RT1305_PLL2_S_RCCLK:
+		snd_soc_component_update_bits(component, RT1305_CLK_1,
+			RT1305_SEL_PLL_SRC_2_MASK | RT1305_SEL_PLL_SRC_1_MASK |
+			RT1305_DIV_PLL_SRC_2_MASK,
+			RT1305_SEL_PLL_SRC_2_RCCLK | RT1305_SEL_PLL_SRC_1_PLL2);
+		freq_in = 98304000;
+		break;
+	default:
+		dev_err(component->dev, "Unknown PLL Source %d\n", source);
+		return -EINVAL;
+	}
+
+	ret = rl6231_pll_calc(freq_in, freq_out, &pll_code);
+	if (ret < 0) {
+		dev_err(component->dev, "Unsupport input clock %d\n", freq_in);
+		return ret;
+	}
+
+	dev_dbg(component->dev, "bypass=%d m=%d n=%d k=%d\n",
+		pll_code.m_bp, (pll_code.m_bp ? 0 : pll_code.m_code),
+		pll_code.n_code, pll_code.k_code);
+
+	snd_soc_component_write(component, RT1305_PLL1_1,
+		(pll_code.m_bp ? 0 : pll_code.m_code) << RT1305_PLL_1_M_SFT |
+		pll_code.m_bp << RT1305_PLL_1_M_BYPASS_SFT |
+		pll_code.n_code);
+	snd_soc_component_write(component, RT1305_PLL1_2,
+		pll_code.k_code);
+
+	rt1305->pll_in = freq_in;
+	rt1305->pll_out = freq_out;
+	rt1305->pll_src = source;
+
+	return 0;
+}
+
+static int rt1305_probe(struct snd_soc_component *component)
+{
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+
+	rt1305->component = component;
+
+	/* initial settings */
+	rt1305_reg_init(component);
+
+	return 0;
+}
+
+static void rt1305_remove(struct snd_soc_component *component)
+{
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+
+	rt1305_reset(rt1305->regmap);
+}
+
+#ifdef CONFIG_PM
+static int rt1305_suspend(struct snd_soc_component *component)
+{
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt1305->regmap, true);
+	regcache_mark_dirty(rt1305->regmap);
+
+	return 0;
+}
+
+static int rt1305_resume(struct snd_soc_component *component)
+{
+	struct rt1305_priv *rt1305 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt1305->regmap, false);
+	regcache_sync(rt1305->regmap);
+
+	return 0;
+}
+#else
+#define rt1305_suspend NULL
+#define rt1305_resume NULL
+#endif
+
+#define RT1305_STEREO_RATES SNDRV_PCM_RATE_8000_192000
+#define RT1305_FORMATS (SNDRV_PCM_FMTBIT_S8 | \
+			SNDRV_PCM_FMTBIT_S20_3LE | SNDRV_PCM_FMTBIT_S16_LE | \
+			SNDRV_PCM_FMTBIT_S24_LE)
+
+static const struct snd_soc_dai_ops rt1305_aif_dai_ops = {
+	.hw_params = rt1305_hw_params,
+	.set_fmt = rt1305_set_dai_fmt,
+};
+
+static struct snd_soc_dai_driver rt1305_dai[] = {
+	{
+		.name = "rt1305-aif",
+		.playback = {
+			.stream_name = "AIF1 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT1305_STEREO_RATES,
+			.formats = RT1305_FORMATS,
+		},
+		.ops = &rt1305_aif_dai_ops,
+	},
+};
+
+static const struct snd_soc_component_driver soc_component_dev_rt1305 = {
+	.probe = rt1305_probe,
+	.remove = rt1305_remove,
+	.suspend = rt1305_suspend,
+	.resume = rt1305_resume,
+	.controls = rt1305_snd_controls,
+	.num_controls = ARRAY_SIZE(rt1305_snd_controls),
+	.dapm_widgets = rt1305_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(rt1305_dapm_widgets),
+	.dapm_routes = rt1305_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(rt1305_dapm_routes),
+	.set_sysclk = rt1305_set_component_sysclk,
+	.set_pll = rt1305_set_component_pll,
+	.use_pmdown_time	= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static const struct regmap_config rt1305_regmap = {
+	.reg_bits = 8,
+	.val_bits = 16,
+	.max_register = RT1305_MAX_REG + 1 + (ARRAY_SIZE(rt1305_ranges) *
+					       RT1305_PR_SPACING),
+	.volatile_reg = rt1305_volatile_register,
+	.readable_reg = rt1305_readable_register,
+	.cache_type = REGCACHE_RBTREE,
+	.reg_defaults = rt1305_reg,
+	.num_reg_defaults = ARRAY_SIZE(rt1305_reg),
+	.ranges = rt1305_ranges,
+	.num_ranges = ARRAY_SIZE(rt1305_ranges),
+	.use_single_rw = true,
+};
+
+#if defined(CONFIG_OF)
+static const struct of_device_id rt1305_of_match[] = {
+	{ .compatible = "realtek,rt1305", },
+	{ .compatible = "realtek,rt1306", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, rt1305_of_match);
+#endif
+
+#ifdef CONFIG_ACPI
+static struct acpi_device_id rt1305_acpi_match[] = {
+	{"10EC1305", 0,},
+	{"10EC1306", 0,},
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, rt1305_acpi_match);
+#endif
+
+static const struct i2c_device_id rt1305_i2c_id[] = {
+	{ "rt1305", 0 },
+	{ "rt1306", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, rt1305_i2c_id);
+
+static void rt1305_calibrate(struct rt1305_priv *rt1305)
+{
+	unsigned int valmsb, vallsb, offsetl, offsetr;
+	unsigned int rh, rl, rhl, r0ohm;
+	u64 r0l, r0r;
+
+	regcache_cache_bypass(rt1305->regmap, true);
+
+	rt1305_reset(rt1305->regmap);
+	regmap_write(rt1305->regmap, RT1305_ADC_SET_3, 0x0219);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xcf, 0x5548);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xc1, 0x0320);
+	regmap_write(rt1305->regmap, RT1305_CLOCK_DETECT, 0x1000);
+	regmap_write(rt1305->regmap, RT1305_CLK_1, 0x0600);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xffd0);
+	regmap_write(rt1305->regmap, RT1305_EFUSE_1, 0x0080);
+	regmap_write(rt1305->regmap, RT1305_EFUSE_1, 0x0880);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_1, 0x0dfe);
+
+	/* Sin Gen */
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x5d, 0x0442);
+
+	regmap_write(rt1305->regmap, RT1305_CAL_EFUSE_CLOCK, 0xb000);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xc3, 0xd4a0);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xcc, 0x00cc);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xc1, 0x0320);
+	regmap_write(rt1305->regmap, RT1305_POWER_STATUS, 0x0000);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_2, 0xffff);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xfc20);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x06, 0x00c0);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xfca0);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xfce0);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xfcf0);
+
+	/* EFUSE read */
+	regmap_write(rt1305->regmap, RT1305_EFUSE_1, 0x0080);
+	regmap_write(rt1305->regmap, RT1305_EFUSE_1, 0x0880);
+	regmap_write(rt1305->regmap, RT1305_EFUSE_1, 0x0880);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xfce0);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xfca0);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xfc20);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x06, 0x0000);
+	regmap_write(rt1305->regmap, RT1305_EFUSE_1, 0x0000);
+
+	regmap_read(rt1305->regmap, RT1305_DAC_OFFSET_5, &valmsb);
+	regmap_read(rt1305->regmap, RT1305_DAC_OFFSET_6, &vallsb);
+	offsetl = valmsb << 16 | vallsb;
+	regmap_read(rt1305->regmap, RT1305_DAC_OFFSET_7, &valmsb);
+	regmap_read(rt1305->regmap, RT1305_DAC_OFFSET_8, &vallsb);
+	offsetr = valmsb << 16 | vallsb;
+	pr_info("DC offsetl=0x%x, offsetr=0x%x\n", offsetl, offsetr);
+
+	/* R0 calibration */
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x5d, 0x9542);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0xfcf0);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_2, 0xffff);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_1, 0x1dfe);
+	regmap_write(rt1305->regmap, RT1305_SILENCE_DETECT, 0x0e13);
+	regmap_write(rt1305->regmap, RT1305_CLK_1, 0x0650);
+
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x50, 0x0064);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x51, 0x0770);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x52, 0xc30c);
+	regmap_write(rt1305->regmap, RT1305_SPK_TEMP_PROTECTION_1, 0x8200);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xd4, 0xfb00);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xd4, 0xff80);
+	msleep(2000);
+	regmap_read(rt1305->regmap, RT1305_PR_BASE + 0x55, &rh);
+	regmap_read(rt1305->regmap, RT1305_PR_BASE + 0x56, &rl);
+	rhl = (rh << 16) | rl;
+	r0ohm = (rhl*10) / 33554432;
+
+	pr_debug("Left_rhl = 0x%x rh=0x%x rl=0x%x\n", rhl, rh, rl);
+	pr_info("Left channel %d.%dohm\n", (r0ohm/10), (r0ohm%10));
+
+	r0l = 562949953421312;
+	if (rhl != 0)
+		do_div(r0l, rhl);
+	pr_debug("Left_r0 = 0x%llx\n", r0l);
+
+	regmap_write(rt1305->regmap, RT1305_SPK_TEMP_PROTECTION_1, 0x9200);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xd4, 0xfb00);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xd4, 0xff80);
+	msleep(2000);
+	regmap_read(rt1305->regmap, RT1305_PR_BASE + 0x55, &rh);
+	regmap_read(rt1305->regmap, RT1305_PR_BASE + 0x56, &rl);
+	rhl = (rh << 16) | rl;
+	r0ohm = (rhl*10) / 33554432;
+
+	pr_debug("Right_rhl = 0x%x rh=0x%x rl=0x%x\n", rhl, rh, rl);
+	pr_info("Right channel %d.%dohm\n", (r0ohm/10), (r0ohm%10));
+
+	r0r = 562949953421312;
+	if (rhl != 0)
+		do_div(r0r, rhl);
+	pr_debug("Right_r0 = 0x%llx\n", r0r);
+
+	regmap_write(rt1305->regmap, RT1305_SPK_TEMP_PROTECTION_1, 0xc2ec);
+
+	if ((r0l > R0_UPPER) && (r0l < R0_LOWER) &&
+		(r0r > R0_UPPER) && (r0r < R0_LOWER)) {
+		regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x4e,
+			(r0l >> 16) & 0xffff);
+		regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x4f,
+			r0l & 0xffff);
+		regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xfe,
+			((r0r >> 16) & 0xffff) | 0xf800);
+		regmap_write(rt1305->regmap, RT1305_PR_BASE + 0xfd,
+			r0r & 0xffff);
+	} else {
+		pr_err("R0 calibration failed\n");
+	}
+
+	/* restore some registers */
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_1, 0x0dfe);
+	usleep_range(200000, 400000);
+	regmap_write(rt1305->regmap, RT1305_PR_BASE + 0x5d, 0x0442);
+	regmap_write(rt1305->regmap, RT1305_CLOCK_DETECT, 0x3000);
+	regmap_write(rt1305->regmap, RT1305_CLK_1, 0x0400);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_1, 0x0000);
+	regmap_write(rt1305->regmap, RT1305_CAL_EFUSE_CLOCK, 0x8000);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_2, 0x1020);
+	regmap_write(rt1305->regmap, RT1305_POWER_CTRL_3, 0x0000);
+
+	regcache_cache_bypass(rt1305->regmap, false);
+}
+
+static int rt1305_i2c_probe(struct i2c_client *i2c,
+		    const struct i2c_device_id *id)
+{
+	struct rt1305_priv *rt1305;
+	int ret;
+	unsigned int val;
+
+	rt1305 = devm_kzalloc(&i2c->dev, sizeof(struct rt1305_priv),
+				GFP_KERNEL);
+	if (rt1305 == NULL)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, rt1305);
+
+	rt1305->regmap = devm_regmap_init_i2c(i2c, &rt1305_regmap);
+	if (IS_ERR(rt1305->regmap)) {
+		ret = PTR_ERR(rt1305->regmap);
+		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	regmap_read(rt1305->regmap, RT1305_DEVICE_ID, &val);
+	if (val != RT1305_DEVICE_ID_NUM) {
+		dev_err(&i2c->dev,
+			"Device with ID register %x is not rt1305\n", val);
+		return -ENODEV;
+	}
+
+	rt1305_reset(rt1305->regmap);
+	rt1305_calibrate(rt1305);
+
+	return snd_soc_register_component(&i2c->dev, &soc_component_dev_rt1305,
+			rt1305_dai, ARRAY_SIZE(rt1305_dai));
+}
+
+static int rt1305_i2c_remove(struct i2c_client *i2c)
+{
+	snd_soc_unregister_component(&i2c->dev);
+
+	return 0;
+}
+
+static void rt1305_i2c_shutdown(struct i2c_client *client)
+{
+	struct rt1305_priv *rt1305 = i2c_get_clientdata(client);
+
+	rt1305_reset(rt1305->regmap);
+}
+
+
+static struct i2c_driver rt1305_i2c_driver = {
+	.driver = {
+		.name = "rt1305",
+#if defined(CONFIG_OF)
+		.of_match_table = rt1305_of_match,
+#endif
+#if defined(CONFIG_ACPI)
+		.acpi_match_table = ACPI_PTR(rt1305_acpi_match)
+#endif
+	},
+	.probe = rt1305_i2c_probe,
+	.remove   = rt1305_i2c_remove,
+	.shutdown = rt1305_i2c_shutdown,
+	.id_table = rt1305_i2c_id,
+};
+module_i2c_driver(rt1305_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC RT1305 amplifier driver");
+MODULE_AUTHOR("Shuming Fan <shumingf@realtek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/rt1305.h b/sound/soc/codecs/rt1305.h
new file mode 100644
index 000000000000..bde86f97729a
--- /dev/null
+++ b/sound/soc/codecs/rt1305.h
@@ -0,0 +1,276 @@
+/*
+ * RT1305.h  --  RT1305 ALSA SoC amplifier component driver
+ *
+ * Copyright 2018 Realtek Semiconductor Corp.
+ * Author: Shuming Fan <shumingf@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _RT1305_H_
+#define _RT1305_H_
+
+#define RT1305_DEVICE_ID_NUM 0x6251
+
+#define RT1305_RESET				0x00
+#define RT1305_CLK_1				0x04
+#define RT1305_CLK_2				0x05
+#define RT1305_CLK_3				0x06
+#define RT1305_DFLL_REG				0x07
+#define RT1305_CAL_EFUSE_CLOCK	0x08
+#define RT1305_PLL0_1				0x0a
+#define RT1305_PLL0_2				0x0b
+#define RT1305_PLL1_1				0x0c
+#define RT1305_PLL1_2				0x0d
+#define RT1305_MIXER_CTRL_1 0x10
+#define RT1305_MIXER_CTRL_2 0x11
+#define RT1305_DAC_SET_1             0x12
+#define RT1305_DAC_SET_2             0x14
+#define RT1305_ADC_SET_1            0x16
+#define RT1305_ADC_SET_2            0x17
+#define RT1305_ADC_SET_3            0x18
+#define RT1305_PATH_SET             0x20
+#define RT1305_SPDIF_IN_SET_1                 0x22
+#define RT1305_SPDIF_IN_SET_2                 0x24
+#define RT1305_SPDIF_IN_SET_3                 0x26
+#define RT1305_SPDIF_OUT_SET_1                 0x28
+#define RT1305_SPDIF_OUT_SET_2                 0x2a
+#define RT1305_SPDIF_OUT_SET_3                 0x2b
+#define RT1305_I2S_SET_1                       0x2d
+#define RT1305_I2S_SET_2                      0x2e
+#define RT1305_PBTL_MONO_MODE_SRC            0x2f
+#define RT1305_MANUALLY_I2C_DEVICE 0x32
+#define RT1305_POWER_STATUS                  0x39
+#define RT1305_POWER_CTRL_1                  0x3a
+#define RT1305_POWER_CTRL_2                  0x3b
+#define RT1305_POWER_CTRL_3                  0x3c
+#define RT1305_POWER_CTRL_4                  0x3d
+#define RT1305_POWER_CTRL_5                  0x3e
+#define RT1305_CLOCK_DETECT                  0x3f
+#define RT1305_BIQUAD_SET_1                  0x40
+#define RT1305_BIQUAD_SET_2                  0x42
+#define RT1305_ADJUSTED_HPF_1             0x46
+#define RT1305_ADJUSTED_HPF_2               0x47
+#define RT1305_EQ_SET_1                  0x4b
+#define RT1305_EQ_SET_2                  0x4c
+#define RT1305_SPK_TEMP_PROTECTION_0 0x4f
+#define RT1305_SPK_TEMP_PROTECTION_1 0x50
+#define RT1305_SPK_TEMP_PROTECTION_2 0x51
+#define RT1305_SPK_TEMP_PROTECTION_3 0x52
+#define RT1305_SPK_DC_DETECT_1                  0x53
+#define RT1305_SPK_DC_DETECT_2                  0x54
+#define RT1305_LOUDNESS 0x58
+#define RT1305_THERMAL_FOLD_BACK_1 0x5e
+#define RT1305_THERMAL_FOLD_BACK_2 0x5f
+#define RT1305_SILENCE_DETECT                  0x60
+#define RT1305_ALC_DRC_1                  0x62
+#define RT1305_ALC_DRC_2                  0x63
+#define RT1305_ALC_DRC_3                  0x64
+#define RT1305_ALC_DRC_4                  0x65
+#define RT1305_PRIV_INDEX			0x6a
+#define RT1305_PRIV_DATA			0x6c
+#define RT1305_SPK_EXCURSION_LIMITER_7 0x76
+#define RT1305_VERSION_ID			0x7a
+#define RT1305_VENDOR_ID			0x7c
+#define RT1305_DEVICE_ID			0x7e
+#define RT1305_EFUSE_1                  0x80
+#define RT1305_EFUSE_2                  0x81
+#define RT1305_EFUSE_3                  0x82
+#define RT1305_DC_CALIB_1                  0x90
+#define RT1305_DC_CALIB_2                  0x91
+#define RT1305_DC_CALIB_3                  0x92
+#define RT1305_DAC_OFFSET_1            0x93
+#define RT1305_DAC_OFFSET_2            0x94
+#define RT1305_DAC_OFFSET_3            0x95
+#define RT1305_DAC_OFFSET_4            0x96
+#define RT1305_DAC_OFFSET_5            0x97
+#define RT1305_DAC_OFFSET_6            0x98
+#define RT1305_DAC_OFFSET_7            0x99
+#define RT1305_DAC_OFFSET_8            0x9a
+#define RT1305_DAC_OFFSET_9            0x9b
+#define RT1305_DAC_OFFSET_10            0x9c
+#define RT1305_DAC_OFFSET_11            0x9d
+#define RT1305_DAC_OFFSET_12            0x9e
+#define RT1305_DAC_OFFSET_13            0x9f
+#define RT1305_DAC_OFFSET_14            0xa0
+#define RT1305_TRIM_1                  0xb0
+#define RT1305_TRIM_2                  0xb1
+#define RT1305_TUNE_INTERNAL_OSC             0xb2
+#define RT1305_BIQUAD1_H0_L_28_16 0xc0
+#define RT1305_BIQUAD3_A2_R_15_0 0xfb
+#define RT1305_MAX_REG	                 0xff
+
+/* CLOCK-1 (0x04) */
+#define RT1305_SEL_PLL_SRC_2_MASK			(0x1 << 15)
+#define RT1305_SEL_PLL_SRC_2_SFT			15
+#define RT1305_SEL_PLL_SRC_2_MCLK			(0x0 << 15)
+#define RT1305_SEL_PLL_SRC_2_RCCLK			(0x1 << 15)
+#define RT1305_DIV_PLL_SRC_2_MASK			(0x3 << 13)
+#define RT1305_DIV_PLL_SRC_2_SFT			13
+#define RT1305_SEL_PLL_SRC_1_MASK			(0x3 << 10)
+#define RT1305_SEL_PLL_SRC_1_SFT			10
+#define RT1305_SEL_PLL_SRC_1_PLL2			(0x0 << 10)
+#define RT1305_SEL_PLL_SRC_1_BCLK			(0x1 << 10)
+#define RT1305_SEL_PLL_SRC_1_DFLL			(0x2 << 10)
+#define RT1305_SEL_FS_SYS_PRE_MASK			(0x3 << 8)
+#define RT1305_SEL_FS_SYS_PRE_SFT			8
+#define RT1305_SEL_FS_SYS_PRE_MCLK			(0x0 << 8)
+#define RT1305_SEL_FS_SYS_PRE_PLL			(0x1 << 8)
+#define RT1305_SEL_FS_SYS_PRE_RCCLK			(0x2 << 8)
+#define RT1305_DIV_FS_SYS_MASK				(0x7 << 4)
+#define RT1305_DIV_FS_SYS_SFT				4
+
+/* PLL1M/N/K Code-1 (0x0c) */
+#define RT1305_PLL_1_M_SFT		12
+#define RT1305_PLL_1_M_BYPASS_MASK			(0x1 << 11)
+#define RT1305_PLL_1_M_BYPASS_SFT		11
+#define RT1305_PLL_1_M_BYPASS			(0x1 << 11)
+#define RT1305_PLL_1_N_MASK			(0x1ff << 0)
+
+/* DAC Setting (0x14) */
+#define RT1305_DVOL_MUTE_L_EN_SFT		15
+#define RT1305_DVOL_MUTE_R_EN_SFT		14
+
+/* I2S Setting-1 (0x2d) */
+#define RT1305_SEL_I2S_OUT_MODE_MASK		(0x1 << 15)
+#define RT1305_SEL_I2S_OUT_MODE_SFT			15
+#define RT1305_SEL_I2S_OUT_MODE_S			(0x0 << 15)
+#define RT1305_SEL_I2S_OUT_MODE_M			(0x1 << 15)
+
+/* I2S Setting-2 (0x2e) */
+#define RT1305_I2S_DF_SEL_MASK			(0x3 << 12)
+#define RT1305_I2S_DF_SEL_SFT			12
+#define RT1305_I2S_DF_SEL_I2S			(0x0 << 12)
+#define RT1305_I2S_DF_SEL_LEFT			(0x1 << 12)
+#define RT1305_I2S_DF_SEL_PCM_A			(0x2 << 12)
+#define RT1305_I2S_DF_SEL_PCM_B			(0x3 << 12)
+#define RT1305_I2S_DL_SEL_MASK			(0x3 << 10)
+#define RT1305_I2S_DL_SEL_SFT			10
+#define RT1305_I2S_DL_SEL_16B			(0x0 << 10)
+#define RT1305_I2S_DL_SEL_20B			(0x1 << 10)
+#define RT1305_I2S_DL_SEL_24B			(0x2 << 10)
+#define RT1305_I2S_DL_SEL_8B			(0x3 << 10)
+#define RT1305_I2S_BCLK_MASK		(0x1 << 9)
+#define RT1305_I2S_BCLK_SFT			9
+#define RT1305_I2S_BCLK_NORMAL		(0x0 << 9)
+#define RT1305_I2S_BCLK_INV			(0x1 << 9)
+
+/* Power Control-1 (0x3a) */
+#define RT1305_POW_PDB_JD_MASK				(0x1 << 12)
+#define RT1305_POW_PDB_JD				(0x1 << 12)
+#define RT1305_POW_PDB_JD_BIT			12
+#define RT1305_POW_PLL0_EN				(0x1 << 11)
+#define RT1305_POW_PLL0_EN_BIT			11
+#define RT1305_POW_PLL1_EN				(0x1 << 10)
+#define RT1305_POW_PLL1_EN_BIT			10
+#define RT1305_POW_PDB_JD_POLARITY				(0x1 << 9)
+#define RT1305_POW_PDB_JD_POLARITY_BIT			9
+#define RT1305_POW_MBIAS_LV				(0x1 << 8)
+#define RT1305_POW_MBIAS_LV_BIT			8
+#define RT1305_POW_BG_MBIAS_LV				(0x1 << 7)
+#define RT1305_POW_BG_MBIAS_LV_BIT			7
+#define RT1305_POW_LDO2				(0x1 << 6)
+#define RT1305_POW_LDO2_BIT			6
+#define RT1305_POW_BG2				(0x1 << 5)
+#define RT1305_POW_BG2_BIT			5
+#define RT1305_POW_LDO2_IB2				(0x1 << 4)
+#define RT1305_POW_LDO2_IB2_BIT			4
+#define RT1305_POW_VREF				(0x1 << 3)
+#define RT1305_POW_VREF_BIT			3
+#define RT1305_POW_VREF1				(0x1 << 2)
+#define RT1305_POW_VREF1_BIT			2
+#define RT1305_POW_VREF2				(0x1 << 1)
+#define RT1305_POW_VREF2_BIT			1
+
+/* Power Control-2 (0x3b) */
+#define RT1305_POW_DISC_VREF           (1 << 15)
+#define RT1305_POW_DISC_VREF_BIT       15
+#define RT1305_POW_FASTB_VREF          (1 << 14)
+#define RT1305_POW_FASTB_VREF_BIT          14
+#define RT1305_POW_ULTRA_FAST_VREF     (1 << 13)
+#define RT1305_POW_ULTRA_FAST_VREF_BIT     13
+#define RT1305_POW_CKXEN_DAC           (1 << 12)
+#define RT1305_POW_CKXEN_DAC_BIT           12
+#define RT1305_POW_EN_CKGEN_DAC        (1 << 11)
+#define RT1305_POW_EN_CKGEN_DAC_BIT        11
+#define RT1305_POW_DAC1_L          (1 << 10)
+#define RT1305_POW_DAC1_L_BIT          10
+#define RT1305_POW_DAC1_R          (1 << 9)
+#define RT1305_POW_DAC1_R_BIT          9
+#define RT1305_POW_CLAMP           (1 << 8)
+#define RT1305_POW_CLAMP_BIT           8
+#define RT1305_POW_BUFL            (1 << 7)
+#define RT1305_POW_BUFL_BIT            7
+#define RT1305_POW_BUFR              (1 << 6)
+#define RT1305_POW_BUFR_BIT              6
+#define RT1305_POW_EN_CKGEN_ADC       (1 << 5)
+#define RT1305_POW_EN_CKGEN_ADC_BIT       5
+#define RT1305_POW_ADC3_L             (1 << 4)
+#define RT1305_POW_ADC3_L_BIT             4
+#define RT1305_POW_ADC3_R             (1 << 3)
+#define RT1305_POW_ADC3_R_BIT             3
+#define RT1305_POW_TRIOSC               (1 << 2)
+#define RT1305_POW_TRIOSC_BIT               2
+#define RT1305_POR_AVDD1              (1 << 1)
+#define RT1305_POR_AVDD1_BIT              1
+#define RT1305_POR_AVDD2           (1 << 0)
+#define RT1305_POR_AVDD2_BIT           0
+
+/* Power Control-3 (0x3c) */
+#define RT1305_POW_VSENSE_RCH           (1 << 15)
+#define RT1305_POW_VSENSE_RCH_BIT        15
+#define RT1305_POW_VSENSE_LCH           (1 << 14)
+#define RT1305_POW_VSENSE_LCH_BIT           14
+#define RT1305_POW_ISENSE_RCH            (1 << 13)
+#define RT1305_POW_ISENSE_RCH_BIT          13
+#define RT1305_POW_ISENSE_LCH            (1 << 12)
+#define RT1305_POW_ISENSE_LCH_BIT            12
+#define RT1305_POW_POR_AVDD1            (1 << 11)
+#define RT1305_POW_POR_AVDD1_BIT          11
+#define RT1305_POW_POR_AVDD2            (1 << 10)
+#define RT1305_POW_POR_AVDD2_BIT            10
+#define RT1305_EN_K_HV            (1 << 9)
+#define RT1305_EN_K_HV_BIT           9
+#define RT1305_EN_PRE_K_HV            (1 << 8)
+#define RT1305_EN_PRE_K_HV_BIT           8
+#define RT1305_EN_EFUSE_1P8V            (1 << 7)
+#define RT1305_EN_EFUSE_1P8V_BIT           7
+#define RT1305_EN_EFUSE_5V             (1 << 6)
+#define RT1305_EN_EFUSE_5V_BIT           6
+#define RT1305_EN_VCM_6172           (1 << 5)
+#define RT1305_EN_VCM_6172_BIT          5
+#define RT1305_POR_EFUSE           (1 << 4)
+#define RT1305_POR_EFUSE_BIT             4
+
+/* Clock Detect (0x3f) */
+#define RT1305_SEL_CLK_DET_SRC_MASK			(0x1 << 12)
+#define RT1305_SEL_CLK_DET_SRC_SFT			12
+#define RT1305_SEL_CLK_DET_SRC_MCLK			(0x0 << 12)
+#define RT1305_SEL_CLK_DET_SRC_BCLK			(0x1 << 12)
+
+
+/* System Clock Source */
+enum {
+	RT1305_FS_SYS_PRE_S_MCLK,
+	RT1305_FS_SYS_PRE_S_PLL1,
+	RT1305_FS_SYS_PRE_S_RCCLK,	/* 98.304M Hz */
+};
+
+/* PLL Source 1/2 */
+enum {
+	RT1305_PLL1_S_BCLK,
+	RT1305_PLL2_S_MCLK,
+	RT1305_PLL2_S_RCCLK,	/* 98.304M Hz */
+};
+
+enum {
+	RT1305_AIF1,
+	RT1305_AIFS
+};
+
+#define R0_UPPER 0x2E8BA2 //5.5 ohm
+#define R0_LOWER 0x666666 //2.5 ohm
+
+#endif		/* end of _RT1305_H_ */
diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c
index e8a66b03faab..1570b91bf018 100644
--- a/sound/soc/codecs/rt5514.c
+++ b/sound/soc/codecs/rt5514.c
@@ -89,6 +89,7 @@ static const struct reg_default rt5514_reg[] = {
 	{RT5514_PLL3_CALIB_CTRL5,	0x40220012},
 	{RT5514_DELAY_BUF_CTRL1,	0x7fff006a},
 	{RT5514_DELAY_BUF_CTRL3,	0x00000000},
+	{RT5514_ASRC_IN_CTRL1,		0x00000003},
 	{RT5514_DOWNFILTER0_CTRL1,	0x00020c2f},
 	{RT5514_DOWNFILTER0_CTRL2,	0x00020c2f},
 	{RT5514_DOWNFILTER0_CTRL3,	0x10000362},
@@ -181,6 +182,7 @@ static bool rt5514_readable_register(struct device *dev, unsigned int reg)
 	case RT5514_PLL3_CALIB_CTRL5:
 	case RT5514_DELAY_BUF_CTRL1:
 	case RT5514_DELAY_BUF_CTRL3:
+	case RT5514_ASRC_IN_CTRL1:
 	case RT5514_DOWNFILTER0_CTRL1:
 	case RT5514_DOWNFILTER0_CTRL2:
 	case RT5514_DOWNFILTER0_CTRL3:
@@ -238,6 +240,7 @@ static bool rt5514_i2c_readable_register(struct device *dev,
 	case RT5514_DSP_MAPPING | RT5514_PLL3_CALIB_CTRL5:
 	case RT5514_DSP_MAPPING | RT5514_DELAY_BUF_CTRL1:
 	case RT5514_DSP_MAPPING | RT5514_DELAY_BUF_CTRL3:
+	case RT5514_DSP_MAPPING | RT5514_ASRC_IN_CTRL1:
 	case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL1:
 	case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL2:
 	case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL3:
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index 05567426f211..8bf8d360c25f 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -24,6 +24,7 @@
 #include <linux/spi/spi.h>
 #include <linux/acpi.h>
 #include <sound/core.h>
+#include <sound/jack.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
@@ -476,20 +477,6 @@ static int set_dmic_clk(struct snd_soc_dapm_widget *w,
 	return idx;
 }
 
-static int is_sys_clk_from_pll(struct snd_soc_dapm_widget *source,
-			 struct snd_soc_dapm_widget *sink)
-{
-	struct snd_soc_component *component = snd_soc_dapm_to_component(source->dapm);
-	unsigned int val;
-
-	val = snd_soc_component_read32(component, RT5640_GLB_CLK);
-	val &= RT5640_SCLK_SRC_MASK;
-	if (val == RT5640_SCLK_SRC_PLL1)
-		return 1;
-	else
-		return 0;
-}
-
 static int is_using_asrc(struct snd_soc_dapm_widget *source,
 			 struct snd_soc_dapm_widget *sink)
 {
@@ -1071,9 +1058,6 @@ static int rt5640_hp_post_event(struct snd_soc_dapm_widget *w,
 }
 
 static const struct snd_soc_dapm_widget rt5640_dapm_widgets[] = {
-	SND_SOC_DAPM_SUPPLY("PLL1", RT5640_PWR_ANLG2,
-			RT5640_PWR_PLL_BIT, 0, NULL, 0),
-
 	/* ASRC */
 	SND_SOC_DAPM_SUPPLY_S("Stereo Filter ASRC", 1, RT5640_ASRC_1,
 			 15, 0, NULL, 0),
@@ -1427,22 +1411,18 @@ static const struct snd_soc_dapm_route rt5640_dapm_routes[] = {
 	{"Stereo ADC MIXL", "ADC1 Switch", "Stereo ADC L1 Mux"},
 	{"Stereo ADC MIXL", "ADC2 Switch", "Stereo ADC L2 Mux"},
 	{"Stereo ADC MIXL", NULL, "Stereo Filter"},
-	{"Stereo Filter", NULL, "PLL1", is_sys_clk_from_pll},
 
 	{"Stereo ADC MIXR", "ADC1 Switch", "Stereo ADC R1 Mux"},
 	{"Stereo ADC MIXR", "ADC2 Switch", "Stereo ADC R2 Mux"},
 	{"Stereo ADC MIXR", NULL, "Stereo Filter"},
-	{"Stereo Filter", NULL, "PLL1", is_sys_clk_from_pll},
 
 	{"Mono ADC MIXL", "ADC1 Switch", "Mono ADC L1 Mux"},
 	{"Mono ADC MIXL", "ADC2 Switch", "Mono ADC L2 Mux"},
 	{"Mono ADC MIXL", NULL, "Mono Left Filter"},
-	{"Mono Left Filter", NULL, "PLL1", is_sys_clk_from_pll},
 
 	{"Mono ADC MIXR", "ADC1 Switch", "Mono ADC R1 Mux"},
 	{"Mono ADC MIXR", "ADC2 Switch", "Mono ADC R2 Mux"},
 	{"Mono ADC MIXR", NULL, "Mono Right Filter"},
-	{"Mono Right Filter", NULL, "PLL1", is_sys_clk_from_pll},
 
 	{"IF2 ADC L", NULL, "Mono ADC MIXL"},
 	{"IF2 ADC R", NULL, "Mono ADC MIXR"},
@@ -1512,10 +1492,8 @@ static const struct snd_soc_dapm_route rt5640_dapm_routes[] = {
 	{"DIG MIXR", "DAC R1 Switch", "DAC MIXR"},
 
 	{"DAC L1", NULL, "Stereo DAC MIXL"},
-	{"DAC L1", NULL, "PLL1", is_sys_clk_from_pll},
 	{"DAC L1", NULL, "DAC L1 Power"},
 	{"DAC R1", NULL, "Stereo DAC MIXR"},
-	{"DAC R1", NULL, "PLL1", is_sys_clk_from_pll},
 	{"DAC R1", NULL, "DAC R1 Power"},
 
 	{"SPK MIXL", "REC MIXL Switch", "RECMIXL"},
@@ -1622,10 +1600,8 @@ static const struct snd_soc_dapm_route rt5640_specific_dapm_routes[] = {
 	{"DIG MIXL", "DAC L2 Switch", "DAC L2 Mux"},
 
 	{"DAC L2", NULL, "Mono DAC MIXL"},
-	{"DAC L2", NULL, "PLL1", is_sys_clk_from_pll},
 	{"DAC L2", NULL, "DAC L2 Power"},
 	{"DAC R2", NULL, "Mono DAC MIXR"},
-	{"DAC R2", NULL, "PLL1", is_sys_clk_from_pll},
 	{"DAC R2", NULL, "DAC R2 Power"},
 
 	{"SPK MIXL", "DAC L2 Switch", "DAC L2"},
@@ -1861,6 +1837,7 @@ static int rt5640_set_dai_sysclk(struct snd_soc_dai *dai,
 	struct snd_soc_component *component = dai->component;
 	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
 	unsigned int reg_val = 0;
+	unsigned int pll_bit = 0;
 
 	if (freq == rt5640->sysclk && clk_id == rt5640->sysclk_src)
 		return 0;
@@ -1871,6 +1848,7 @@ static int rt5640_set_dai_sysclk(struct snd_soc_dai *dai,
 		break;
 	case RT5640_SCLK_S_PLL1:
 		reg_val |= RT5640_SCLK_SRC_PLL1;
+		pll_bit |= RT5640_PWR_PLL;
 		break;
 	case RT5640_SCLK_S_RCCLK:
 		reg_val |= RT5640_SCLK_SRC_RCCLK;
@@ -1879,6 +1857,8 @@ static int rt5640_set_dai_sysclk(struct snd_soc_dai *dai,
 		dev_err(component->dev, "Invalid clock id (%d)\n", clk_id);
 		return -EINVAL;
 	}
+	snd_soc_component_update_bits(component, RT5640_PWR_ANLG2,
+		RT5640_PWR_PLL, pll_bit);
 	snd_soc_component_update_bits(component, RT5640_GLB_CLK,
 		RT5640_SCLK_SRC_MASK, reg_val);
 	rt5640->sysclk = freq;
@@ -2114,10 +2094,376 @@ int rt5640_sel_asrc_clk_src(struct snd_soc_component *component,
 }
 EXPORT_SYMBOL_GPL(rt5640_sel_asrc_clk_src);
 
+static void rt5640_enable_micbias1_for_ovcd(struct snd_soc_component *component)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
+
+	snd_soc_dapm_mutex_lock(dapm);
+	snd_soc_dapm_force_enable_pin_unlocked(dapm, "LDO2");
+	snd_soc_dapm_force_enable_pin_unlocked(dapm, "MICBIAS1");
+	/* OVCD is unreliable when used with RCCLK as sysclk-source */
+	snd_soc_dapm_force_enable_pin_unlocked(dapm, "Platform Clock");
+	snd_soc_dapm_sync_unlocked(dapm);
+	snd_soc_dapm_mutex_unlock(dapm);
+}
+
+static void rt5640_disable_micbias1_for_ovcd(struct snd_soc_component *component)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
+
+	snd_soc_dapm_mutex_lock(dapm);
+	snd_soc_dapm_disable_pin_unlocked(dapm, "Platform Clock");
+	snd_soc_dapm_disable_pin_unlocked(dapm, "MICBIAS1");
+	snd_soc_dapm_disable_pin_unlocked(dapm, "LDO2");
+	snd_soc_dapm_sync_unlocked(dapm);
+	snd_soc_dapm_mutex_unlock(dapm);
+}
+
+static void rt5640_enable_micbias1_ovcd_irq(struct snd_soc_component *component)
+{
+	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
+
+	snd_soc_component_update_bits(component, RT5640_IRQ_CTRL2,
+		RT5640_IRQ_MB1_OC_MASK, RT5640_IRQ_MB1_OC_NOR);
+	rt5640->ovcd_irq_enabled = true;
+}
+
+static void rt5640_disable_micbias1_ovcd_irq(struct snd_soc_component *component)
+{
+	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
+
+	snd_soc_component_update_bits(component, RT5640_IRQ_CTRL2,
+		RT5640_IRQ_MB1_OC_MASK, RT5640_IRQ_MB1_OC_BP);
+	rt5640->ovcd_irq_enabled = false;
+}
+
+static void rt5640_clear_micbias1_ovcd(struct snd_soc_component *component)
+{
+	snd_soc_component_update_bits(component, RT5640_IRQ_CTRL2,
+		RT5640_MB1_OC_STATUS, 0);
+}
+
+static bool rt5640_micbias1_ovcd(struct snd_soc_component *component)
+{
+	int val;
+
+	val = snd_soc_component_read32(component, RT5640_IRQ_CTRL2);
+	dev_dbg(component->dev, "irq ctrl2 %#04x\n", val);
+
+	return (val & RT5640_MB1_OC_STATUS);
+}
+
+static bool rt5640_jack_inserted(struct snd_soc_component *component)
+{
+	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
+	int val;
+
+	val = snd_soc_component_read32(component, RT5640_INT_IRQ_ST);
+	dev_dbg(component->dev, "irq status %#04x\n", val);
+
+	if (rt5640->jd_inverted)
+		return !(val & RT5640_JD_STATUS);
+	else
+		return (val & RT5640_JD_STATUS);
+}
+
+/* Jack detect and button-press timings */
+#define JACK_SETTLE_TIME	100 /* milli seconds */
+#define JACK_DETECT_COUNT	5
+#define JACK_DETECT_MAXCOUNT	20  /* Aprox. 2 seconds worth of tries */
+#define JACK_UNPLUG_TIME	80  /* milli seconds */
+#define BP_POLL_TIME		10  /* milli seconds */
+#define BP_POLL_MAXCOUNT	200 /* assume something is wrong after this */
+#define BP_THRESHOLD		3
+
+static void rt5640_start_button_press_work(struct snd_soc_component *component)
+{
+	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
+
+	rt5640->poll_count = 0;
+	rt5640->press_count = 0;
+	rt5640->release_count = 0;
+	rt5640->pressed = false;
+	rt5640->press_reported = false;
+	rt5640_clear_micbias1_ovcd(component);
+	schedule_delayed_work(&rt5640->bp_work, msecs_to_jiffies(BP_POLL_TIME));
+}
+
+static void rt5640_button_press_work(struct work_struct *work)
+{
+	struct rt5640_priv *rt5640 =
+		container_of(work, struct rt5640_priv, bp_work.work);
+	struct snd_soc_component *component = rt5640->component;
+
+	/* Check the jack was not removed underneath us */
+	if (!rt5640_jack_inserted(component))
+		return;
+
+	if (rt5640_micbias1_ovcd(component)) {
+		rt5640->release_count = 0;
+		rt5640->press_count++;
+		/* Remember till after JACK_UNPLUG_TIME wait */
+		if (rt5640->press_count >= BP_THRESHOLD)
+			rt5640->pressed = true;
+		rt5640_clear_micbias1_ovcd(component);
+	} else {
+		rt5640->press_count = 0;
+		rt5640->release_count++;
+	}
+
+	/*
+	 * The pins get temporarily shorted on jack unplug, so we poll for
+	 * at least JACK_UNPLUG_TIME milli-seconds before reporting a press.
+	 */
+	rt5640->poll_count++;
+	if (rt5640->poll_count < (JACK_UNPLUG_TIME / BP_POLL_TIME)) {
+		schedule_delayed_work(&rt5640->bp_work,
+				      msecs_to_jiffies(BP_POLL_TIME));
+		return;
+	}
+
+	if (rt5640->pressed && !rt5640->press_reported) {
+		dev_dbg(component->dev, "headset button press\n");
+		snd_soc_jack_report(rt5640->jack, SND_JACK_BTN_0,
+				    SND_JACK_BTN_0);
+		rt5640->press_reported = true;
+	}
+
+	if (rt5640->release_count >= BP_THRESHOLD) {
+		if (rt5640->press_reported) {
+			dev_dbg(component->dev, "headset button release\n");
+			snd_soc_jack_report(rt5640->jack, 0, SND_JACK_BTN_0);
+		}
+		/* Re-enable OVCD IRQ to detect next press */
+		rt5640_enable_micbias1_ovcd_irq(component);
+		return; /* Stop polling */
+	}
+
+	schedule_delayed_work(&rt5640->bp_work, msecs_to_jiffies(BP_POLL_TIME));
+}
+
+static int rt5640_detect_headset(struct snd_soc_component *component)
+{
+	int i, headset_count = 0, headphone_count = 0;
+
+	/*
+	 * We get the insertion event before the jack is fully inserted at which
+	 * point the second ring on a TRRS connector may short the 2nd ring and
+	 * sleeve contacts, also the overcurrent detection is not entirely
+	 * reliable. So we try several times with a wait in between until we
+	 * detect the same type JACK_DETECT_COUNT times in a row.
+	 */
+	for (i = 0; i < JACK_DETECT_MAXCOUNT; i++) {
+		/* Clear any previous over-current status flag */
+		rt5640_clear_micbias1_ovcd(component);
+
+		msleep(JACK_SETTLE_TIME);
+
+		/* Check the jack is still connected before checking ovcd */
+		if (!rt5640_jack_inserted(component))
+			return 0;
+
+		if (rt5640_micbias1_ovcd(component)) {
+			/*
+			 * Over current detected, there is a short between the
+			 * 2nd ring contact and the ground, so a TRS connector
+			 * without a mic contact and thus plain headphones.
+			 */
+			dev_dbg(component->dev, "jack mic-gnd shorted\n");
+			headset_count = 0;
+			headphone_count++;
+			if (headphone_count == JACK_DETECT_COUNT)
+				return SND_JACK_HEADPHONE;
+		} else {
+			dev_dbg(component->dev, "jack mic-gnd open\n");
+			headphone_count = 0;
+			headset_count++;
+			if (headset_count == JACK_DETECT_COUNT)
+				return SND_JACK_HEADSET;
+		}
+	}
+
+	dev_err(component->dev, "Error detecting headset vs headphones, bad contact?, assuming headphones\n");
+	return SND_JACK_HEADPHONE;
+}
+
+static void rt5640_jack_work(struct work_struct *work)
+{
+	struct rt5640_priv *rt5640 =
+		container_of(work, struct rt5640_priv, jack_work);
+	struct snd_soc_component *component = rt5640->component;
+	int status;
+
+	if (!rt5640_jack_inserted(component)) {
+		/* Jack removed, or spurious IRQ? */
+		if (rt5640->jack->status & SND_JACK_HEADPHONE) {
+			if (rt5640->jack->status & SND_JACK_MICROPHONE) {
+				cancel_delayed_work_sync(&rt5640->bp_work);
+				rt5640_disable_micbias1_ovcd_irq(component);
+				rt5640_disable_micbias1_for_ovcd(component);
+			}
+			snd_soc_jack_report(rt5640->jack, 0,
+					    SND_JACK_HEADSET | SND_JACK_BTN_0);
+			dev_dbg(component->dev, "jack unplugged\n");
+		}
+	} else if (!(rt5640->jack->status & SND_JACK_HEADPHONE)) {
+		/* Jack inserted */
+		WARN_ON(rt5640->ovcd_irq_enabled);
+		rt5640_enable_micbias1_for_ovcd(component);
+		status = rt5640_detect_headset(component);
+		if (status == SND_JACK_HEADSET) {
+			/* Enable ovcd IRQ for button press detect. */
+			rt5640_enable_micbias1_ovcd_irq(component);
+		} else {
+			/* No more need for overcurrent detect. */
+			rt5640_disable_micbias1_for_ovcd(component);
+		}
+		dev_dbg(component->dev, "detect status %#02x\n", status);
+		snd_soc_jack_report(rt5640->jack, status, SND_JACK_HEADSET);
+	} else if (rt5640->ovcd_irq_enabled && rt5640_micbias1_ovcd(component)) {
+		dev_dbg(component->dev, "OVCD IRQ\n");
+
+		/*
+		 * The ovcd IRQ keeps firing while the button is pressed, so
+		 * we disable it and start polling the button until released.
+		 *
+		 * The disable will make the IRQ pin 0 again and since we get
+		 * IRQs on both edges (so as to detect both jack plugin and
+		 * unplug) this means we will immediately get another IRQ.
+		 * The ovcd_irq_enabled check above makes the 2ND IRQ a NOP.
+		 */
+		rt5640_disable_micbias1_ovcd_irq(component);
+		rt5640_start_button_press_work(component);
+
+		/*
+		 * If the jack-detect IRQ flag goes high (unplug) after our
+		 * above rt5640_jack_inserted() check and before we have
+		 * disabled the OVCD IRQ, the IRQ pin will stay high and as
+		 * we react to edges, we miss the unplug event -> recheck.
+		 */
+		queue_work(system_long_wq, &rt5640->jack_work);
+	}
+}
+
+static irqreturn_t rt5640_irq(int irq, void *data)
+{
+	struct rt5640_priv *rt5640 = data;
+
+	if (rt5640->jack)
+		queue_work(system_long_wq, &rt5640->jack_work);
+
+	return IRQ_HANDLED;
+}
+
+static void rt5640_cancel_work(void *data)
+{
+	struct rt5640_priv *rt5640 = data;
+
+	cancel_work_sync(&rt5640->jack_work);
+	cancel_delayed_work_sync(&rt5640->bp_work);
+}
+
+static void rt5640_enable_jack_detect(struct snd_soc_component *component,
+				      struct snd_soc_jack *jack)
+{
+	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
+
+	/* Select JD-source */
+	snd_soc_component_update_bits(component, RT5640_JD_CTRL,
+		RT5640_JD_MASK, rt5640->jd_src);
+
+	/* Selecting GPIO01 as an interrupt */
+	snd_soc_component_update_bits(component, RT5640_GPIO_CTRL1,
+		RT5640_GP1_PIN_MASK, RT5640_GP1_PIN_IRQ);
+
+	/* Set GPIO1 output */
+	snd_soc_component_update_bits(component, RT5640_GPIO_CTRL3,
+		RT5640_GP1_PF_MASK, RT5640_GP1_PF_OUT);
+
+	/* Enabling jd2 in general control 1 */
+	snd_soc_component_write(component, RT5640_DUMMY1, 0x3f41);
+
+	/* Enabling jd2 in general control 2 */
+	snd_soc_component_write(component, RT5640_DUMMY2, 0x4001);
+
+	snd_soc_component_write(component, RT5640_PR_BASE + RT5640_BIAS_CUR4,
+		0xa800 | rt5640->ovcd_sf);
+
+	snd_soc_component_update_bits(component, RT5640_MICBIAS,
+		RT5640_MIC1_OVTH_MASK | RT5640_MIC1_OVCD_MASK,
+		rt5640->ovcd_th | RT5640_MIC1_OVCD_EN);
+
+	/*
+	 * The over-current-detect is only reliable in detecting the absence
+	 * of over-current, when the mic-contact in the jack is short-circuited,
+	 * the hardware periodically retries if it can apply the bias-current
+	 * leading to the ovcd status flip-flopping 1-0-1 with it being 0 about
+	 * 10% of the time, as we poll the ovcd status bit we might hit that
+	 * 10%, so we enable sticky mode and when checking OVCD we clear the
+	 * status, msleep() a bit and then check to get a reliable reading.
+	 */
+	snd_soc_component_update_bits(component, RT5640_IRQ_CTRL2,
+		RT5640_MB1_OC_STKY_MASK, RT5640_MB1_OC_STKY_EN);
+
+	/*
+	 * All IRQs get or-ed together, so we need the jack IRQ to report 0
+	 * when a jack is inserted so that the OVCD IRQ then toggles the IRQ
+	 * pin 0/1 instead of it being stuck to 1. So we invert the JD polarity
+	 * on systems where the hardware does not already do this.
+	 */
+	if (rt5640->jd_inverted)
+		snd_soc_component_write(component, RT5640_IRQ_CTRL1,
+					RT5640_IRQ_JD_NOR);
+	else
+		snd_soc_component_write(component, RT5640_IRQ_CTRL1,
+					RT5640_IRQ_JD_NOR | RT5640_JD_P_INV);
+
+	rt5640->jack = jack;
+	if (rt5640->jack->status & SND_JACK_MICROPHONE) {
+		rt5640_enable_micbias1_for_ovcd(component);
+		rt5640_enable_micbias1_ovcd_irq(component);
+	}
+
+	enable_irq(rt5640->irq);
+	/* sync initial jack state */
+	queue_work(system_long_wq, &rt5640->jack_work);
+}
+
+static void rt5640_disable_jack_detect(struct snd_soc_component *component)
+{
+	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
+
+	disable_irq(rt5640->irq);
+	rt5640_cancel_work(rt5640);
+
+	if (rt5640->jack->status & SND_JACK_MICROPHONE) {
+		rt5640_disable_micbias1_ovcd_irq(component);
+		rt5640_disable_micbias1_for_ovcd(component);
+		snd_soc_jack_report(rt5640->jack, 0, SND_JACK_BTN_0);
+	}
+
+	rt5640->jack = NULL;
+}
+
+static int rt5640_set_jack(struct snd_soc_component *component,
+			   struct snd_soc_jack *jack, void *data)
+{
+	if (jack)
+		rt5640_enable_jack_detect(component, jack);
+	else
+		rt5640_disable_jack_detect(component);
+
+	return 0;
+}
+
 static int rt5640_probe(struct snd_soc_component *component)
 {
 	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
 	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
+	u32 dmic1_data_pin = 0;
+	u32 dmic2_data_pin = 0;
+	bool dmic_en = false;
+	u32 val;
 
 	/* Check if MCLK provided */
 	rt5640->mclk = devm_clk_get(component->dev, "mclk");
@@ -2159,9 +2505,86 @@ static int rt5640_probe(struct snd_soc_component *component)
 		return -ENODEV;
 	}
 
-	if (rt5640->pdata.dmic_en)
-		rt5640_dmic_enable(component, rt5640->pdata.dmic1_data_pin,
-					  rt5640->pdata.dmic2_data_pin);
+	/*
+	 * Note on some platforms the platform code may need to add device-props
+	 * rather then relying only on properties set by the firmware.
+	 * Therefor the property parsing MUST be done here, rather then from
+	 * rt5640_i2c_probe(), so that the platform-code can attach extra
+	 * properties before calling snd_soc_register_card().
+	 */
+	if (device_property_read_bool(component->dev, "realtek,in1-differential"))
+		snd_soc_component_update_bits(component, RT5640_IN1_IN2,
+					      RT5640_IN_DF1, RT5640_IN_DF1);
+
+	if (device_property_read_bool(component->dev, "realtek,in2-differential"))
+		snd_soc_component_update_bits(component, RT5640_IN3_IN4,
+					      RT5640_IN_DF2, RT5640_IN_DF2);
+
+	if (device_property_read_bool(component->dev, "realtek,in3-differential"))
+		snd_soc_component_update_bits(component, RT5640_IN1_IN2,
+					      RT5640_IN_DF2, RT5640_IN_DF2);
+
+	if (device_property_read_u32(component->dev, "realtek,dmic1-data-pin",
+				     &val) == 0 && val) {
+		dmic1_data_pin = val - 1;
+		dmic_en = true;
+	}
+
+	if (device_property_read_u32(component->dev, "realtek,dmic2-data-pin",
+				     &val) == 0 && val) {
+		dmic2_data_pin = val - 1;
+		dmic_en = true;
+	}
+
+	if (dmic_en)
+		rt5640_dmic_enable(component, dmic1_data_pin, dmic2_data_pin);
+
+	if (device_property_read_u32(component->dev,
+				     "realtek,jack-detect-source", &val) == 0) {
+		if (val <= RT5640_JD_SRC_GPIO4)
+			rt5640->jd_src = val << RT5640_JD_SFT;
+		else
+			dev_warn(component->dev, "Warning: Invalid jack-detect-source value: %d, leaving jack-detect disabled\n",
+				 val);
+	}
+
+	if (!device_property_read_bool(component->dev, "realtek,jack-detect-not-inverted"))
+		rt5640->jd_inverted = true;
+
+	/*
+	 * Testing on various boards has shown that good defaults for the OVCD
+	 * threshold and scale-factor are 2000µA and 0.75. For an effective
+	 * limit of 1500µA, this seems to be more reliable then 1500µA and 1.0.
+	 */
+	rt5640->ovcd_th = RT5640_MIC1_OVTH_2000UA;
+	rt5640->ovcd_sf = RT5640_MIC_OVCD_SF_0P75;
+
+	if (device_property_read_u32(component->dev,
+			"realtek,over-current-threshold-microamp", &val) == 0) {
+		switch (val) {
+		case 600:
+			rt5640->ovcd_th = RT5640_MIC1_OVTH_600UA;
+			break;
+		case 1500:
+			rt5640->ovcd_th = RT5640_MIC1_OVTH_1500UA;
+			break;
+		case 2000:
+			rt5640->ovcd_th = RT5640_MIC1_OVTH_2000UA;
+			break;
+		default:
+			dev_warn(component->dev, "Warning: Invalid over-current-threshold-microamp value: %d, defaulting to 2000uA\n",
+				 val);
+		}
+	}
+
+	if (device_property_read_u32(component->dev,
+			"realtek,over-current-scale-factor", &val) == 0) {
+		if (val <= RT5640_OVCD_SF_1P5)
+			rt5640->ovcd_sf = val << RT5640_MIC_OVCD_SF_SFT;
+		else
+			dev_warn(component->dev, "Warning: Invalid over-current-scale-factor value: %d, defaulting to 0.75\n",
+				 val);
+	}
 
 	return 0;
 }
@@ -2180,8 +2603,8 @@ static int rt5640_suspend(struct snd_soc_component *component)
 	rt5640_reset(component);
 	regcache_cache_only(rt5640->regmap, true);
 	regcache_mark_dirty(rt5640->regmap);
-	if (gpio_is_valid(rt5640->pdata.ldo1_en))
-		gpio_set_value_cansleep(rt5640->pdata.ldo1_en, 0);
+	if (gpio_is_valid(rt5640->ldo1_en))
+		gpio_set_value_cansleep(rt5640->ldo1_en, 0);
 
 	return 0;
 }
@@ -2190,8 +2613,8 @@ static int rt5640_resume(struct snd_soc_component *component)
 {
 	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
 
-	if (gpio_is_valid(rt5640->pdata.ldo1_en)) {
-		gpio_set_value_cansleep(rt5640->pdata.ldo1_en, 1);
+	if (gpio_is_valid(rt5640->ldo1_en)) {
+		gpio_set_value_cansleep(rt5640->ldo1_en, 1);
 		msleep(400);
 	}
 
@@ -2263,6 +2686,7 @@ static const struct snd_soc_component_driver soc_component_dev_rt5640 = {
 	.suspend		= rt5640_suspend,
 	.resume			= rt5640_resume,
 	.set_bias_level		= rt5640_set_bias_level,
+	.set_jack		= rt5640_set_jack,
 	.controls		= rt5640_snd_controls,
 	.num_controls		= ARRAY_SIZE(rt5640_snd_controls),
 	.dapm_widgets		= rt5640_dapm_widgets,
@@ -2323,22 +2747,16 @@ MODULE_DEVICE_TABLE(acpi, rt5640_acpi_match);
 
 static int rt5640_parse_dt(struct rt5640_priv *rt5640, struct device_node *np)
 {
-	rt5640->pdata.in1_diff = of_property_read_bool(np,
-					"realtek,in1-differential");
-	rt5640->pdata.in2_diff = of_property_read_bool(np,
-					"realtek,in2-differential");
-
-	rt5640->pdata.ldo1_en = of_get_named_gpio(np,
-					"realtek,ldo1-en-gpios", 0);
+	rt5640->ldo1_en = of_get_named_gpio(np, "realtek,ldo1-en-gpios", 0);
 	/*
 	 * LDO1_EN is optional (it may be statically tied on the board).
 	 * -ENOENT means that the property doesn't exist, i.e. there is no
 	 * GPIO, so is not an error. Any other error code means the property
 	 * exists, but could not be parsed.
 	 */
-	if (!gpio_is_valid(rt5640->pdata.ldo1_en) &&
-			(rt5640->pdata.ldo1_en != -ENOENT))
-		return rt5640->pdata.ldo1_en;
+	if (!gpio_is_valid(rt5640->ldo1_en) &&
+			(rt5640->ldo1_en != -ENOENT))
+		return rt5640->ldo1_en;
 
 	return 0;
 }
@@ -2346,7 +2764,6 @@ static int rt5640_parse_dt(struct rt5640_priv *rt5640, struct device_node *np)
 static int rt5640_i2c_probe(struct i2c_client *i2c,
 		    const struct i2c_device_id *id)
 {
-	struct rt5640_platform_data *pdata = dev_get_platdata(&i2c->dev);
 	struct rt5640_priv *rt5640;
 	int ret;
 	unsigned int val;
@@ -2358,22 +2775,12 @@ static int rt5640_i2c_probe(struct i2c_client *i2c,
 		return -ENOMEM;
 	i2c_set_clientdata(i2c, rt5640);
 
-	if (pdata) {
-		rt5640->pdata = *pdata;
-		/*
-		 * Translate zero'd out (default) pdata value to an invalid
-		 * GPIO ID. This makes the pdata and DT paths consistent in
-		 * terms of the value left in this field when no GPIO is
-		 * specified, but means we can't actually use GPIO 0.
-		 */
-		if (!rt5640->pdata.ldo1_en)
-			rt5640->pdata.ldo1_en = -EINVAL;
-	} else if (i2c->dev.of_node) {
+	if (i2c->dev.of_node) {
 		ret = rt5640_parse_dt(rt5640, i2c->dev.of_node);
 		if (ret)
 			return ret;
 	} else
-		rt5640->pdata.ldo1_en = -EINVAL;
+		rt5640->ldo1_en = -EINVAL;
 
 	rt5640->regmap = devm_regmap_init_i2c(i2c, &rt5640_regmap);
 	if (IS_ERR(rt5640->regmap)) {
@@ -2383,13 +2790,13 @@ static int rt5640_i2c_probe(struct i2c_client *i2c,
 		return ret;
 	}
 
-	if (gpio_is_valid(rt5640->pdata.ldo1_en)) {
-		ret = devm_gpio_request_one(&i2c->dev, rt5640->pdata.ldo1_en,
+	if (gpio_is_valid(rt5640->ldo1_en)) {
+		ret = devm_gpio_request_one(&i2c->dev, rt5640->ldo1_en,
 					    GPIOF_OUT_INIT_HIGH,
 					    "RT5640 LDO1_EN");
 		if (ret < 0) {
 			dev_err(&i2c->dev, "Failed to request LDO1_EN %d: %d\n",
-				rt5640->pdata.ldo1_en, ret);
+				rt5640->ldo1_en, ret);
 			return ret;
 		}
 		msleep(400);
@@ -2412,19 +2819,27 @@ static int rt5640_i2c_probe(struct i2c_client *i2c,
 	regmap_update_bits(rt5640->regmap, RT5640_DUMMY1,
 				RT5640_MCLK_DET, RT5640_MCLK_DET);
 
-	if (rt5640->pdata.in1_diff)
-		regmap_update_bits(rt5640->regmap, RT5640_IN1_IN2,
-					RT5640_IN_DF1, RT5640_IN_DF1);
-
-	if (rt5640->pdata.in2_diff)
-		regmap_update_bits(rt5640->regmap, RT5640_IN3_IN4,
-					RT5640_IN_DF2, RT5640_IN_DF2);
+	rt5640->hp_mute = 1;
+	rt5640->irq = i2c->irq;
+	INIT_DELAYED_WORK(&rt5640->bp_work, rt5640_button_press_work);
+	INIT_WORK(&rt5640->jack_work, rt5640_jack_work);
 
-	if (rt5640->pdata.in3_diff)
-		regmap_update_bits(rt5640->regmap, RT5640_IN1_IN2,
-					RT5640_IN_DF2, RT5640_IN_DF2);
+	/* Make sure work is stopped on probe-error / remove */
+	ret = devm_add_action_or_reset(&i2c->dev, rt5640_cancel_work, rt5640);
+	if (ret)
+		return ret;
 
-	rt5640->hp_mute = 1;
+	ret = devm_request_irq(&i2c->dev, rt5640->irq, rt5640_irq,
+			       IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+			       | IRQF_ONESHOT, "rt5640", rt5640);
+	if (ret == 0) {
+		/* Gets re-enabled by rt5640_set_jack() */
+		disable_irq(rt5640->irq);
+	} else {
+		dev_warn(&i2c->dev, "Failed to reguest IRQ %d: %d\n",
+			 rt5640->irq, ret);
+		rt5640->irq = -ENXIO;
+	}
 
 	return devm_snd_soc_register_component(&i2c->dev,
 				      &soc_component_dev_rt5640,
diff --git a/sound/soc/codecs/rt5640.h b/sound/soc/codecs/rt5640.h
index c473e8ae2eda..e29e3e7d61b0 100644
--- a/sound/soc/codecs/rt5640.h
+++ b/sound/soc/codecs/rt5640.h
@@ -13,7 +13,8 @@
 #define _RT5640_H
 
 #include <linux/clk.h>
-#include <sound/rt5640.h>
+#include <linux/workqueue.h>
+#include <dt-bindings/sound/rt5640.h>
 
 /* Info */
 #define RT5640_RESET				0x00
@@ -146,6 +147,7 @@
 
 
 /* Index of Codec Private Register definition */
+#define RT5640_BIAS_CUR4			0x15
 #define RT5640_CHPUMP_INT_REG1			0x24
 #define RT5640_MAMP_INT_REG2			0x37
 #define RT5640_3D_SPK				0x63
@@ -1607,10 +1609,17 @@
 #define RT5640_MB2_OC_P_SFT			6
 #define RT5640_MB2_OC_P_NOR			(0x0 << 6)
 #define RT5640_MB2_OC_P_INV			(0x1 << 6)
-#define RT5640_MB1_OC_CLR			(0x1 << 3)
-#define RT5640_MB1_OC_CLR_SFT			3
-#define RT5640_MB2_OC_CLR			(0x1 << 2)
-#define RT5640_MB2_OC_CLR_SFT			2
+#define RT5640_MB1_OC_STATUS			(0x1 << 3)
+#define RT5640_MB1_OC_STATUS_SFT		3
+#define RT5640_MB2_OC_STATUS			(0x1 << 2)
+#define RT5640_MB2_OC_STATUS_SFT		2
+
+/* GPIO and Internal Status (0xbf) */
+#define RT5640_GPIO1_STATUS			(0x1 << 8)
+#define RT5640_GPIO2_STATUS			(0x1 << 7)
+#define RT5640_JD_STATUS			(0x1 << 4)
+#define RT5640_OVT_STATUS			(0x1 << 3)
+#define RT5640_CLS_D_OVCD_STATUS		(0x1 << 0)
 
 /* GPIO Control 1 (0xc0) */
 #define RT5640_GP1_PIN_MASK			(0x1 << 15)
@@ -1978,6 +1987,15 @@
 #define RT5640_MCLK_DET				(0x1 << 11)
 
 /* Codec Private Register definition */
+
+/* MIC Over current threshold scale factor (0x15) */
+#define RT5640_MIC_OVCD_SF_MASK			(0x3 << 8)
+#define RT5640_MIC_OVCD_SF_SFT			8
+#define RT5640_MIC_OVCD_SF_0P5			(0x0 << 8)
+#define RT5640_MIC_OVCD_SF_0P75			(0x1 << 8)
+#define RT5640_MIC_OVCD_SF_1P0			(0x2 << 8)
+#define RT5640_MIC_OVCD_SF_1P5			(0x3 << 8)
+
 /* 3D Speaker Control (0x63) */
 #define RT5640_3D_SPK_MASK			(0x1 << 15)
 #define RT5640_3D_SPK_SFT			15
@@ -2103,10 +2121,11 @@ enum {
 
 struct rt5640_priv {
 	struct snd_soc_component *component;
-	struct rt5640_platform_data pdata;
 	struct regmap *regmap;
 	struct clk *mclk;
 
+	int ldo1_en; /* GPIO for LDO1_EN */
+	int irq;
 	int sysclk;
 	int sysclk_src;
 	int lrck[RT5640_AIFS];
@@ -2119,6 +2138,21 @@ struct rt5640_priv {
 
 	bool hp_mute;
 	bool asrc_en;
+
+	/* Jack and button detect data */
+	bool ovcd_irq_enabled;
+	bool pressed;
+	bool press_reported;
+	int press_count;
+	int release_count;
+	int poll_count;
+	struct delayed_work bp_work;
+	struct work_struct jack_work;
+	struct snd_soc_jack *jack;
+	unsigned int jd_src;
+	bool jd_inverted;
+	unsigned int ovcd_th;
+	unsigned int ovcd_sf;
 };
 
 int rt5640_dmic_enable(struct snd_soc_component *component,
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index bc8d829ce45b..712384581ebf 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3652,6 +3652,11 @@ static const struct rt5645_platform_data asus_t100ha_platform_data = {
 	.inv_jd1_1 = true,
 };
 
+static const struct rt5645_platform_data lenovo_ideapad_miix_310_pdata = {
+	.jd_mode = 3,
+	.in2_diff = true,
+};
+
 static const struct rt5645_platform_data jd_mode3_platform_data = {
 	.jd_mode = 3,
 };
@@ -3735,6 +3740,24 @@ static const struct dmi_system_id dmi_platform_data[] = {
 		},
 		.driver_data = (void *)&jd_mode3_platform_data,
 	},
+	{
+		.ident = "Lenovo Ideapad Miix 310",
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80SG"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"),
+		},
+		.driver_data = (void *)&lenovo_ideapad_miix_310_pdata,
+	},
+	{
+		.ident = "Lenovo Ideapad Miix 320",
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80XF"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 320-10ICR"),
+		},
+		.driver_data = (void *)&intel_braswell_platform_data,
+	},
 	{ }
 };
 
diff --git a/sound/soc/codecs/rt5663.c b/sound/soc/codecs/rt5663.c
index 20c0aeea6ca3..9bd24ad42240 100644
--- a/sound/soc/codecs/rt5663.c
+++ b/sound/soc/codecs/rt5663.c
@@ -72,6 +72,8 @@ struct rt5663_priv {
 static const struct reg_sequence rt5663_patch_list[] = {
 	{ 0x002a, 0x8020 },
 	{ 0x0086, 0x0028 },
+	{ 0x0117, 0x0f28 },
+	{ 0x02fb, 0x8089 },
 };
 
 static const struct reg_default rt5663_v2_reg[] = {
@@ -593,7 +595,7 @@ static const struct reg_default rt5663_reg[] = {
 	{ 0x0113, 0x2000 },
 	{ 0x0114, 0x0000 },
 	{ 0x0116, 0x0000 },
-	{ 0x0117, 0x0f00 },
+	{ 0x0117, 0x0f28 },
 	{ 0x0118, 0x0006 },
 	{ 0x0125, 0x2424 },
 	{ 0x0126, 0x5550 },
@@ -693,7 +695,7 @@ static const struct reg_default rt5663_reg[] = {
 	{ 0x0251, 0x0000 },
 	{ 0x0252, 0x028a },
 	{ 0x02fa, 0x0000 },
-	{ 0x02fb, 0x00a4 },
+	{ 0x02fb, 0x8089 },
 	{ 0x02fc, 0x0300 },
 	{ 0x0300, 0x0000 },
 	{ 0x03d0, 0x0000 },
@@ -1556,6 +1558,14 @@ static int rt5663_jack_detect(struct snd_soc_component *component, int jack_inse
 			RT5663_PWR_MB_MASK | RT5663_LDO1_DVO_MASK |
 			RT5663_AMP_HP_MASK, RT5663_PWR_MB |
 			RT5663_LDO1_DVO_0_9V | RT5663_AMP_HP_3X);
+		snd_soc_component_update_bits(component, RT5663_PWR_ANLG_1,
+			RT5663_PWR_VREF1_MASK | RT5663_PWR_VREF2_MASK |
+			RT5663_PWR_FV1_MASK | RT5663_PWR_FV2_MASK,
+			RT5663_PWR_VREF1 | RT5663_PWR_VREF2);
+		msleep(20);
+		snd_soc_component_update_bits(component, RT5663_PWR_ANLG_1,
+			RT5663_PWR_FV1_MASK | RT5663_PWR_FV2_MASK,
+			RT5663_PWR_FV1 | RT5663_PWR_FV2);
 		snd_soc_component_update_bits(component, RT5663_AUTO_1MRC_CLK,
 			RT5663_IRQ_POW_SAV_MASK, RT5663_IRQ_POW_SAV_EN);
 		snd_soc_component_update_bits(component, RT5663_IRQ_1,
@@ -1613,7 +1623,10 @@ static int rt5663_jack_detect(struct snd_soc_component *component, int jack_inse
 			break;
 		default:
 			rt5663->jack_type = SND_JACK_HEADPHONE;
-
+			snd_soc_component_update_bits(component,
+				RT5663_PWR_ANLG_1,
+				RT5663_PWR_MB_MASK | RT5663_PWR_VREF1_MASK |
+				RT5663_PWR_VREF2_MASK, 0);
 			if (rt5663->pdata.impedance_sensing_num)
 				break;
 
@@ -1638,6 +1651,9 @@ static int rt5663_jack_detect(struct snd_soc_component *component, int jack_inse
 		if (rt5663->jack_type == SND_JACK_HEADSET)
 			rt5663_enable_push_button_irq(component, false);
 		rt5663->jack_type = 0;
+		snd_soc_component_update_bits(component, RT5663_PWR_ANLG_1,
+			RT5663_PWR_MB_MASK | RT5663_PWR_VREF1_MASK |
+			RT5663_PWR_VREF2_MASK, 0);
 	}
 
 	dev_dbg(component->dev, "jack_type = %d\n", rt5663->jack_type);
@@ -1840,8 +1856,8 @@ static irqreturn_t rt5663_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-int rt5663_set_jack_detect(struct snd_soc_component *component,
-	struct snd_soc_jack *hs_jack)
+static int rt5663_set_jack_detect(struct snd_soc_component *component,
+	struct snd_soc_jack *hs_jack, void *data)
 {
 	struct rt5663_priv *rt5663 = snd_soc_component_get_drvdata(component);
 
@@ -1851,7 +1867,6 @@ int rt5663_set_jack_detect(struct snd_soc_component *component,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(rt5663_set_jack_detect);
 
 static bool rt5663_check_jd_status(struct snd_soc_component *component)
 {
@@ -2307,6 +2322,8 @@ static int rt5663_hp_event(struct snd_soc_dapm_widget *w,
 				RT5663_HP_SIG_SRC1_MASK,
 				RT5663_HP_SIG_SRC1_SILENCE);
 		} else {
+			snd_soc_component_update_bits(component,
+				RT5663_DACREF_LDO, 0x3e0e, 0x3a0a);
 			snd_soc_component_write(component, RT5663_DEPOP_2, 0x3003);
 			snd_soc_component_update_bits(component, RT5663_HP_CHARGE_PUMP_1,
 				RT5663_OVCD_HP_MASK, RT5663_OVCD_HP_DIS);
@@ -2332,6 +2349,8 @@ static int rt5663_hp_event(struct snd_soc_dapm_widget *w,
 			snd_soc_component_update_bits(component, RT5663_DEPOP_1, 0x3000, 0x0);
 			snd_soc_component_update_bits(component, RT5663_HP_CHARGE_PUMP_1,
 				RT5663_OVCD_HP_MASK, RT5663_OVCD_HP_EN);
+			snd_soc_component_update_bits(component,
+				RT5663_DACREF_LDO, 0x3e0e, 0);
 		}
 		break;
 
@@ -3086,9 +3105,17 @@ static int rt5663_set_bias_level(struct snd_soc_component *component,
 		break;
 
 	case SND_SOC_BIAS_OFF:
-		snd_soc_component_update_bits(component, RT5663_PWR_ANLG_1,
-			RT5663_PWR_VREF1_MASK | RT5663_PWR_VREF2_MASK |
-			RT5663_PWR_FV1 | RT5663_PWR_FV2, 0x0);
+		if (rt5663->jack_type != SND_JACK_HEADSET)
+			snd_soc_component_update_bits(component,
+				RT5663_PWR_ANLG_1,
+				RT5663_PWR_VREF1_MASK | RT5663_PWR_VREF2_MASK |
+				RT5663_PWR_FV1 | RT5663_PWR_FV2 |
+				RT5663_PWR_MB_MASK, 0);
+		else
+			snd_soc_component_update_bits(component,
+				RT5663_PWR_ANLG_1,
+				RT5663_PWR_FV1_MASK | RT5663_PWR_FV2_MASK,
+				RT5663_PWR_FV1 | RT5663_PWR_FV2);
 		break;
 
 	default:
@@ -3216,10 +3243,10 @@ static const struct snd_soc_component_driver soc_component_dev_rt5663 = {
 	.num_dapm_widgets	= ARRAY_SIZE(rt5663_dapm_widgets),
 	.dapm_routes		= rt5663_dapm_routes,
 	.num_dapm_routes	= ARRAY_SIZE(rt5663_dapm_routes),
+	.set_jack		= rt5663_set_jack_detect,
 	.use_pmdown_time	= 1,
 	.endianness		= 1,
 	.non_legacy_dai_naming	= 1,
-
 };
 
 static const struct regmap_config rt5663_v2_regmap = {
@@ -3310,6 +3337,7 @@ static void rt5663_calibrate(struct rt5663_priv *rt5663)
 	regmap_write(rt5663->regmap, RT5663_HP_IMP_SEN_19, 0x000c);
 	regmap_write(rt5663->regmap, RT5663_DUMMY_1, 0x0324);
 	regmap_write(rt5663->regmap, RT5663_DIG_MISC, 0x8001);
+	regmap_write(rt5663->regmap, RT5663_VREFADJ_OP, 0x0f28);
 	regmap_write(rt5663->regmap, RT5663_PWR_ANLG_1, 0xa23b);
 	msleep(30);
 	regmap_write(rt5663->regmap, RT5663_PWR_ANLG_1, 0xf23b);
@@ -3344,6 +3372,7 @@ static void rt5663_calibrate(struct rt5663_priv *rt5663)
 	regmap_write(rt5663->regmap, RT5663_PWR_ANLG_2, 0x8003);
 	regmap_write(rt5663->regmap, RT5663_PWR_ANLG_3, 0x018c);
 	regmap_write(rt5663->regmap, RT5663_HP_CHARGE_PUMP_1, 0x1e32);
+	regmap_write(rt5663->regmap, RT5663_DUMMY_2, 0x8089);
 	regmap_write(rt5663->regmap, RT5663_DACREF_LDO, 0x3b0b);
 	msleep(40);
 	regmap_write(rt5663->regmap, RT5663_STO_DAC_MIXER, 0x0000);
@@ -3578,15 +3607,9 @@ static int rt5663_i2c_probe(struct i2c_client *i2c,
 		regmap_update_bits(rt5663->regmap, RT5663_GPIO_1,
 			RT5663_GPIO1_TYPE_MASK, RT5663_GPIO1_TYPE_EN);
 		regmap_write(rt5663->regmap, RT5663_VREF_RECMIX, 0x0032);
-		regmap_write(rt5663->regmap, RT5663_PWR_ANLG_1, 0xa2be);
-		msleep(20);
-		regmap_write(rt5663->regmap, RT5663_PWR_ANLG_1, 0xf2be);
 		regmap_update_bits(rt5663->regmap, RT5663_GPIO_2,
 			RT5663_GP1_PIN_CONF_MASK | RT5663_SEL_GPIO1_MASK,
 			RT5663_GP1_PIN_CONF_OUTPUT | RT5663_SEL_GPIO1_EN);
-		/* DACREF LDO control */
-		regmap_update_bits(rt5663->regmap, RT5663_DACREF_LDO, 0x3e0e,
-			0x3a0a);
 		regmap_update_bits(rt5663->regmap, RT5663_RECMIX,
 			RT5663_RECMIX1_BST1_MASK, RT5663_RECMIX1_BST1_ON);
 		regmap_update_bits(rt5663->regmap, RT5663_TDM_2,
diff --git a/sound/soc/codecs/rt5663.h b/sound/soc/codecs/rt5663.h
index 865203cc2034..794cf3fadf31 100644
--- a/sound/soc/codecs/rt5663.h
+++ b/sound/soc/codecs/rt5663.h
@@ -1125,8 +1125,6 @@ enum {
 	RT5663_AD_STEREO_FILTER = 0x2,
 };
 
-int rt5663_set_jack_detect(struct snd_soc_component *component,
-	struct snd_soc_jack *hs_jack);
 int rt5663_sel_asrc_clk_src(struct snd_soc_component *component,
 	unsigned int filter_mask, unsigned int clk_src);
 
diff --git a/sound/soc/codecs/rt5668.c b/sound/soc/codecs/rt5668.c
new file mode 100644
index 000000000000..3c19d03f2446
--- /dev/null
+++ b/sound/soc/codecs/rt5668.c
@@ -0,0 +1,2639 @@
+/*
+ * rt5668.c  --  RT5668B ALSA SoC audio component driver
+ *
+ * Copyright 2018 Realtek Semiconductor Corp.
+ * Author: Bard Liao <bardliao@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/pm.h>
+#include <linux/i2c.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/acpi.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/regulator/consumer.h>
+#include <linux/mutex.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/jack.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+#include <sound/rt5668.h>
+
+#include "rl6231.h"
+#include "rt5668.h"
+
+#define RT5668_NUM_SUPPLIES 3
+
+static const char *rt5668_supply_names[RT5668_NUM_SUPPLIES] = {
+	"AVDD",
+	"MICVDD",
+	"VBAT",
+};
+
+struct rt5668_priv {
+	struct snd_soc_component *component;
+	struct rt5668_platform_data pdata;
+	struct regmap *regmap;
+	struct snd_soc_jack *hs_jack;
+	struct regulator_bulk_data supplies[RT5668_NUM_SUPPLIES];
+	struct delayed_work jack_detect_work;
+	struct delayed_work jd_check_work;
+	struct mutex calibrate_mutex;
+
+	int sysclk;
+	int sysclk_src;
+	int lrck[RT5668_AIFS];
+	int bclk[RT5668_AIFS];
+	int master[RT5668_AIFS];
+
+	int pll_src;
+	int pll_in;
+	int pll_out;
+
+	int jack_type;
+};
+
+static const struct reg_default rt5668_reg[] = {
+	{0x0002, 0x8080},
+	{0x0003, 0x8000},
+	{0x0005, 0x0000},
+	{0x0006, 0x0000},
+	{0x0008, 0x800f},
+	{0x000b, 0x0000},
+	{0x0010, 0x4040},
+	{0x0011, 0x0000},
+	{0x0012, 0x1404},
+	{0x0013, 0x1000},
+	{0x0014, 0xa00a},
+	{0x0015, 0x0404},
+	{0x0016, 0x0404},
+	{0x0019, 0xafaf},
+	{0x001c, 0x2f2f},
+	{0x001f, 0x0000},
+	{0x0022, 0x5757},
+	{0x0023, 0x0039},
+	{0x0024, 0x000b},
+	{0x0026, 0xc0c4},
+	{0x0029, 0x8080},
+	{0x002a, 0xa0a0},
+	{0x002b, 0x0300},
+	{0x0030, 0x0000},
+	{0x003c, 0x0080},
+	{0x0044, 0x0c0c},
+	{0x0049, 0x0000},
+	{0x0061, 0x0000},
+	{0x0062, 0x0000},
+	{0x0063, 0x003f},
+	{0x0064, 0x0000},
+	{0x0065, 0x0000},
+	{0x0066, 0x0030},
+	{0x0067, 0x0000},
+	{0x006b, 0x0000},
+	{0x006c, 0x0000},
+	{0x006d, 0x2200},
+	{0x006e, 0x0a10},
+	{0x0070, 0x8000},
+	{0x0071, 0x8000},
+	{0x0073, 0x0000},
+	{0x0074, 0x0000},
+	{0x0075, 0x0002},
+	{0x0076, 0x0001},
+	{0x0079, 0x0000},
+	{0x007a, 0x0000},
+	{0x007b, 0x0000},
+	{0x007c, 0x0100},
+	{0x007e, 0x0000},
+	{0x0080, 0x0000},
+	{0x0081, 0x0000},
+	{0x0082, 0x0000},
+	{0x0083, 0x0000},
+	{0x0084, 0x0000},
+	{0x0085, 0x0000},
+	{0x0086, 0x0005},
+	{0x0087, 0x0000},
+	{0x0088, 0x0000},
+	{0x008c, 0x0003},
+	{0x008d, 0x0000},
+	{0x008e, 0x0060},
+	{0x008f, 0x1000},
+	{0x0091, 0x0c26},
+	{0x0092, 0x0073},
+	{0x0093, 0x0000},
+	{0x0094, 0x0080},
+	{0x0098, 0x0000},
+	{0x009a, 0x0000},
+	{0x009b, 0x0000},
+	{0x009c, 0x0000},
+	{0x009d, 0x0000},
+	{0x009e, 0x100c},
+	{0x009f, 0x0000},
+	{0x00a0, 0x0000},
+	{0x00a3, 0x0002},
+	{0x00a4, 0x0001},
+	{0x00ae, 0x2040},
+	{0x00af, 0x0000},
+	{0x00b6, 0x0000},
+	{0x00b7, 0x0000},
+	{0x00b8, 0x0000},
+	{0x00b9, 0x0002},
+	{0x00be, 0x0000},
+	{0x00c0, 0x0160},
+	{0x00c1, 0x82a0},
+	{0x00c2, 0x0000},
+	{0x00d0, 0x0000},
+	{0x00d1, 0x2244},
+	{0x00d2, 0x3300},
+	{0x00d3, 0x2200},
+	{0x00d4, 0x0000},
+	{0x00d9, 0x0009},
+	{0x00da, 0x0000},
+	{0x00db, 0x0000},
+	{0x00dc, 0x00c0},
+	{0x00dd, 0x2220},
+	{0x00de, 0x3131},
+	{0x00df, 0x3131},
+	{0x00e0, 0x3131},
+	{0x00e2, 0x0000},
+	{0x00e3, 0x4000},
+	{0x00e4, 0x0aa0},
+	{0x00e5, 0x3131},
+	{0x00e6, 0x3131},
+	{0x00e7, 0x3131},
+	{0x00e8, 0x3131},
+	{0x00ea, 0xb320},
+	{0x00eb, 0x0000},
+	{0x00f0, 0x0000},
+	{0x00f1, 0x00d0},
+	{0x00f2, 0x00d0},
+	{0x00f6, 0x0000},
+	{0x00fa, 0x0000},
+	{0x00fb, 0x0000},
+	{0x00fc, 0x0000},
+	{0x00fd, 0x0000},
+	{0x00fe, 0x10ec},
+	{0x00ff, 0x6530},
+	{0x0100, 0xa0a0},
+	{0x010b, 0x0000},
+	{0x010c, 0xae00},
+	{0x010d, 0xaaa0},
+	{0x010e, 0x8aa2},
+	{0x010f, 0x02a2},
+	{0x0110, 0xc000},
+	{0x0111, 0x04a2},
+	{0x0112, 0x2800},
+	{0x0113, 0x0000},
+	{0x0117, 0x0100},
+	{0x0125, 0x0410},
+	{0x0132, 0x6026},
+	{0x0136, 0x5555},
+	{0x0138, 0x3700},
+	{0x013a, 0x2000},
+	{0x013b, 0x2000},
+	{0x013c, 0x2005},
+	{0x013f, 0x0000},
+	{0x0142, 0x0000},
+	{0x0145, 0x0002},
+	{0x0146, 0x0000},
+	{0x0147, 0x0000},
+	{0x0148, 0x0000},
+	{0x0149, 0x0000},
+	{0x0150, 0x79a1},
+	{0x0151, 0x0000},
+	{0x0160, 0x4ec0},
+	{0x0161, 0x0080},
+	{0x0162, 0x0200},
+	{0x0163, 0x0800},
+	{0x0164, 0x0000},
+	{0x0165, 0x0000},
+	{0x0166, 0x0000},
+	{0x0167, 0x000f},
+	{0x0168, 0x000f},
+	{0x0169, 0x0021},
+	{0x0190, 0x413d},
+	{0x0194, 0x0000},
+	{0x0195, 0x0000},
+	{0x0197, 0x0022},
+	{0x0198, 0x0000},
+	{0x0199, 0x0000},
+	{0x01af, 0x0000},
+	{0x01b0, 0x0400},
+	{0x01b1, 0x0000},
+	{0x01b2, 0x0000},
+	{0x01b3, 0x0000},
+	{0x01b4, 0x0000},
+	{0x01b5, 0x0000},
+	{0x01b6, 0x01c3},
+	{0x01b7, 0x02a0},
+	{0x01b8, 0x03e9},
+	{0x01b9, 0x1389},
+	{0x01ba, 0xc351},
+	{0x01bb, 0x0009},
+	{0x01bc, 0x0018},
+	{0x01bd, 0x002a},
+	{0x01be, 0x004c},
+	{0x01bf, 0x0097},
+	{0x01c0, 0x433d},
+	{0x01c1, 0x2800},
+	{0x01c2, 0x0000},
+	{0x01c3, 0x0000},
+	{0x01c4, 0x0000},
+	{0x01c5, 0x0000},
+	{0x01c6, 0x0000},
+	{0x01c7, 0x0000},
+	{0x01c8, 0x40af},
+	{0x01c9, 0x0702},
+	{0x01ca, 0x0000},
+	{0x01cb, 0x0000},
+	{0x01cc, 0x5757},
+	{0x01cd, 0x5757},
+	{0x01ce, 0x5757},
+	{0x01cf, 0x5757},
+	{0x01d0, 0x5757},
+	{0x01d1, 0x5757},
+	{0x01d2, 0x5757},
+	{0x01d3, 0x5757},
+	{0x01d4, 0x5757},
+	{0x01d5, 0x5757},
+	{0x01d6, 0x0000},
+	{0x01d7, 0x0008},
+	{0x01d8, 0x0029},
+	{0x01d9, 0x3333},
+	{0x01da, 0x0000},
+	{0x01db, 0x0004},
+	{0x01dc, 0x0000},
+	{0x01de, 0x7c00},
+	{0x01df, 0x0320},
+	{0x01e0, 0x06a1},
+	{0x01e1, 0x0000},
+	{0x01e2, 0x0000},
+	{0x01e3, 0x0000},
+	{0x01e4, 0x0000},
+	{0x01e6, 0x0001},
+	{0x01e7, 0x0000},
+	{0x01e8, 0x0000},
+	{0x01ea, 0x0000},
+	{0x01eb, 0x0000},
+	{0x01ec, 0x0000},
+	{0x01ed, 0x0000},
+	{0x01ee, 0x0000},
+	{0x01ef, 0x0000},
+	{0x01f0, 0x0000},
+	{0x01f1, 0x0000},
+	{0x01f2, 0x0000},
+	{0x01f3, 0x0000},
+	{0x01f4, 0x0000},
+	{0x0210, 0x6297},
+	{0x0211, 0xa005},
+	{0x0212, 0x824c},
+	{0x0213, 0xf7ff},
+	{0x0214, 0xf24c},
+	{0x0215, 0x0102},
+	{0x0216, 0x00a3},
+	{0x0217, 0x0048},
+	{0x0218, 0xa2c0},
+	{0x0219, 0x0400},
+	{0x021a, 0x00c8},
+	{0x021b, 0x00c0},
+	{0x021c, 0x0000},
+	{0x0250, 0x4500},
+	{0x0251, 0x40b3},
+	{0x0252, 0x0000},
+	{0x0253, 0x0000},
+	{0x0254, 0x0000},
+	{0x0255, 0x0000},
+	{0x0256, 0x0000},
+	{0x0257, 0x0000},
+	{0x0258, 0x0000},
+	{0x0259, 0x0000},
+	{0x025a, 0x0005},
+	{0x0270, 0x0000},
+	{0x02ff, 0x0110},
+	{0x0300, 0x001f},
+	{0x0301, 0x032c},
+	{0x0302, 0x5f21},
+	{0x0303, 0x4000},
+	{0x0304, 0x4000},
+	{0x0305, 0x06d5},
+	{0x0306, 0x8000},
+	{0x0307, 0x0700},
+	{0x0310, 0x4560},
+	{0x0311, 0xa4a8},
+	{0x0312, 0x7418},
+	{0x0313, 0x0000},
+	{0x0314, 0x0006},
+	{0x0315, 0xffff},
+	{0x0316, 0xc400},
+	{0x0317, 0x0000},
+	{0x03c0, 0x7e00},
+	{0x03c1, 0x8000},
+	{0x03c2, 0x8000},
+	{0x03c3, 0x8000},
+	{0x03c4, 0x8000},
+	{0x03c5, 0x8000},
+	{0x03c6, 0x8000},
+	{0x03c7, 0x8000},
+	{0x03c8, 0x8000},
+	{0x03c9, 0x8000},
+	{0x03ca, 0x8000},
+	{0x03cb, 0x8000},
+	{0x03cc, 0x8000},
+	{0x03d0, 0x0000},
+	{0x03d1, 0x0000},
+	{0x03d2, 0x0000},
+	{0x03d3, 0x0000},
+	{0x03d4, 0x2000},
+	{0x03d5, 0x2000},
+	{0x03d6, 0x0000},
+	{0x03d7, 0x0000},
+	{0x03d8, 0x2000},
+	{0x03d9, 0x2000},
+	{0x03da, 0x2000},
+	{0x03db, 0x2000},
+	{0x03dc, 0x0000},
+	{0x03dd, 0x0000},
+	{0x03de, 0x0000},
+	{0x03df, 0x2000},
+	{0x03e0, 0x0000},
+	{0x03e1, 0x0000},
+	{0x03e2, 0x0000},
+	{0x03e3, 0x0000},
+	{0x03e4, 0x0000},
+	{0x03e5, 0x0000},
+	{0x03e6, 0x0000},
+	{0x03e7, 0x0000},
+	{0x03e8, 0x0000},
+	{0x03e9, 0x0000},
+	{0x03ea, 0x0000},
+	{0x03eb, 0x0000},
+	{0x03ec, 0x0000},
+	{0x03ed, 0x0000},
+	{0x03ee, 0x0000},
+	{0x03ef, 0x0000},
+	{0x03f0, 0x0800},
+	{0x03f1, 0x0800},
+	{0x03f2, 0x0800},
+	{0x03f3, 0x0800},
+};
+
+static bool rt5668_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case RT5668_RESET:
+	case RT5668_CBJ_CTRL_2:
+	case RT5668_INT_ST_1:
+	case RT5668_4BTN_IL_CMD_1:
+	case RT5668_AJD1_CTRL:
+	case RT5668_HP_CALIB_CTRL_1:
+	case RT5668_DEVICE_ID:
+	case RT5668_I2C_MODE:
+	case RT5668_HP_CALIB_CTRL_10:
+	case RT5668_EFUSE_CTRL_2:
+	case RT5668_JD_TOP_VC_VTRL:
+	case RT5668_HP_IMP_SENS_CTRL_19:
+	case RT5668_IL_CMD_1:
+	case RT5668_SAR_IL_CMD_2:
+	case RT5668_SAR_IL_CMD_4:
+	case RT5668_SAR_IL_CMD_10:
+	case RT5668_SAR_IL_CMD_11:
+	case RT5668_EFUSE_CTRL_6...RT5668_EFUSE_CTRL_11:
+	case RT5668_HP_CALIB_STA_1...RT5668_HP_CALIB_STA_11:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool rt5668_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case RT5668_RESET:
+	case RT5668_VERSION_ID:
+	case RT5668_VENDOR_ID:
+	case RT5668_DEVICE_ID:
+	case RT5668_HP_CTRL_1:
+	case RT5668_HP_CTRL_2:
+	case RT5668_HPL_GAIN:
+	case RT5668_HPR_GAIN:
+	case RT5668_I2C_CTRL:
+	case RT5668_CBJ_BST_CTRL:
+	case RT5668_CBJ_CTRL_1:
+	case RT5668_CBJ_CTRL_2:
+	case RT5668_CBJ_CTRL_3:
+	case RT5668_CBJ_CTRL_4:
+	case RT5668_CBJ_CTRL_5:
+	case RT5668_CBJ_CTRL_6:
+	case RT5668_CBJ_CTRL_7:
+	case RT5668_DAC1_DIG_VOL:
+	case RT5668_STO1_ADC_DIG_VOL:
+	case RT5668_STO1_ADC_BOOST:
+	case RT5668_HP_IMP_GAIN_1:
+	case RT5668_HP_IMP_GAIN_2:
+	case RT5668_SIDETONE_CTRL:
+	case RT5668_STO1_ADC_MIXER:
+	case RT5668_AD_DA_MIXER:
+	case RT5668_STO1_DAC_MIXER:
+	case RT5668_A_DAC1_MUX:
+	case RT5668_DIG_INF2_DATA:
+	case RT5668_REC_MIXER:
+	case RT5668_CAL_REC:
+	case RT5668_ALC_BACK_GAIN:
+	case RT5668_PWR_DIG_1:
+	case RT5668_PWR_DIG_2:
+	case RT5668_PWR_ANLG_1:
+	case RT5668_PWR_ANLG_2:
+	case RT5668_PWR_ANLG_3:
+	case RT5668_PWR_MIXER:
+	case RT5668_PWR_VOL:
+	case RT5668_CLK_DET:
+	case RT5668_RESET_LPF_CTRL:
+	case RT5668_RESET_HPF_CTRL:
+	case RT5668_DMIC_CTRL_1:
+	case RT5668_I2S1_SDP:
+	case RT5668_I2S2_SDP:
+	case RT5668_ADDA_CLK_1:
+	case RT5668_ADDA_CLK_2:
+	case RT5668_I2S1_F_DIV_CTRL_1:
+	case RT5668_I2S1_F_DIV_CTRL_2:
+	case RT5668_TDM_CTRL:
+	case RT5668_TDM_ADDA_CTRL_1:
+	case RT5668_TDM_ADDA_CTRL_2:
+	case RT5668_DATA_SEL_CTRL_1:
+	case RT5668_TDM_TCON_CTRL:
+	case RT5668_GLB_CLK:
+	case RT5668_PLL_CTRL_1:
+	case RT5668_PLL_CTRL_2:
+	case RT5668_PLL_TRACK_1:
+	case RT5668_PLL_TRACK_2:
+	case RT5668_PLL_TRACK_3:
+	case RT5668_PLL_TRACK_4:
+	case RT5668_PLL_TRACK_5:
+	case RT5668_PLL_TRACK_6:
+	case RT5668_PLL_TRACK_11:
+	case RT5668_SDW_REF_CLK:
+	case RT5668_DEPOP_1:
+	case RT5668_DEPOP_2:
+	case RT5668_HP_CHARGE_PUMP_1:
+	case RT5668_HP_CHARGE_PUMP_2:
+	case RT5668_MICBIAS_1:
+	case RT5668_MICBIAS_2:
+	case RT5668_PLL_TRACK_12:
+	case RT5668_PLL_TRACK_14:
+	case RT5668_PLL2_CTRL_1:
+	case RT5668_PLL2_CTRL_2:
+	case RT5668_PLL2_CTRL_3:
+	case RT5668_PLL2_CTRL_4:
+	case RT5668_RC_CLK_CTRL:
+	case RT5668_I2S_M_CLK_CTRL_1:
+	case RT5668_I2S2_F_DIV_CTRL_1:
+	case RT5668_I2S2_F_DIV_CTRL_2:
+	case RT5668_EQ_CTRL_1:
+	case RT5668_EQ_CTRL_2:
+	case RT5668_IRQ_CTRL_1:
+	case RT5668_IRQ_CTRL_2:
+	case RT5668_IRQ_CTRL_3:
+	case RT5668_IRQ_CTRL_4:
+	case RT5668_INT_ST_1:
+	case RT5668_GPIO_CTRL_1:
+	case RT5668_GPIO_CTRL_2:
+	case RT5668_GPIO_CTRL_3:
+	case RT5668_HP_AMP_DET_CTRL_1:
+	case RT5668_HP_AMP_DET_CTRL_2:
+	case RT5668_MID_HP_AMP_DET:
+	case RT5668_LOW_HP_AMP_DET:
+	case RT5668_DELAY_BUF_CTRL:
+	case RT5668_SV_ZCD_1:
+	case RT5668_SV_ZCD_2:
+	case RT5668_IL_CMD_1:
+	case RT5668_IL_CMD_2:
+	case RT5668_IL_CMD_3:
+	case RT5668_IL_CMD_4:
+	case RT5668_IL_CMD_5:
+	case RT5668_IL_CMD_6:
+	case RT5668_4BTN_IL_CMD_1:
+	case RT5668_4BTN_IL_CMD_2:
+	case RT5668_4BTN_IL_CMD_3:
+	case RT5668_4BTN_IL_CMD_4:
+	case RT5668_4BTN_IL_CMD_5:
+	case RT5668_4BTN_IL_CMD_6:
+	case RT5668_4BTN_IL_CMD_7:
+	case RT5668_ADC_STO1_HP_CTRL_1:
+	case RT5668_ADC_STO1_HP_CTRL_2:
+	case RT5668_AJD1_CTRL:
+	case RT5668_JD1_THD:
+	case RT5668_JD2_THD:
+	case RT5668_JD_CTRL_1:
+	case RT5668_DUMMY_1:
+	case RT5668_DUMMY_2:
+	case RT5668_DUMMY_3:
+	case RT5668_DAC_ADC_DIG_VOL1:
+	case RT5668_BIAS_CUR_CTRL_2:
+	case RT5668_BIAS_CUR_CTRL_3:
+	case RT5668_BIAS_CUR_CTRL_4:
+	case RT5668_BIAS_CUR_CTRL_5:
+	case RT5668_BIAS_CUR_CTRL_6:
+	case RT5668_BIAS_CUR_CTRL_7:
+	case RT5668_BIAS_CUR_CTRL_8:
+	case RT5668_BIAS_CUR_CTRL_9:
+	case RT5668_BIAS_CUR_CTRL_10:
+	case RT5668_VREF_REC_OP_FB_CAP_CTRL:
+	case RT5668_CHARGE_PUMP_1:
+	case RT5668_DIG_IN_CTRL_1:
+	case RT5668_PAD_DRIVING_CTRL:
+	case RT5668_SOFT_RAMP_DEPOP:
+	case RT5668_CHOP_DAC:
+	case RT5668_CHOP_ADC:
+	case RT5668_CALIB_ADC_CTRL:
+	case RT5668_VOL_TEST:
+	case RT5668_SPKVDD_DET_STA:
+	case RT5668_TEST_MODE_CTRL_1:
+	case RT5668_TEST_MODE_CTRL_2:
+	case RT5668_TEST_MODE_CTRL_3:
+	case RT5668_TEST_MODE_CTRL_4:
+	case RT5668_TEST_MODE_CTRL_5:
+	case RT5668_PLL1_INTERNAL:
+	case RT5668_PLL2_INTERNAL:
+	case RT5668_STO_NG2_CTRL_1:
+	case RT5668_STO_NG2_CTRL_2:
+	case RT5668_STO_NG2_CTRL_3:
+	case RT5668_STO_NG2_CTRL_4:
+	case RT5668_STO_NG2_CTRL_5:
+	case RT5668_STO_NG2_CTRL_6:
+	case RT5668_STO_NG2_CTRL_7:
+	case RT5668_STO_NG2_CTRL_8:
+	case RT5668_STO_NG2_CTRL_9:
+	case RT5668_STO_NG2_CTRL_10:
+	case RT5668_STO1_DAC_SIL_DET:
+	case RT5668_SIL_PSV_CTRL1:
+	case RT5668_SIL_PSV_CTRL2:
+	case RT5668_SIL_PSV_CTRL3:
+	case RT5668_SIL_PSV_CTRL4:
+	case RT5668_SIL_PSV_CTRL5:
+	case RT5668_HP_IMP_SENS_CTRL_01:
+	case RT5668_HP_IMP_SENS_CTRL_02:
+	case RT5668_HP_IMP_SENS_CTRL_03:
+	case RT5668_HP_IMP_SENS_CTRL_04:
+	case RT5668_HP_IMP_SENS_CTRL_05:
+	case RT5668_HP_IMP_SENS_CTRL_06:
+	case RT5668_HP_IMP_SENS_CTRL_07:
+	case RT5668_HP_IMP_SENS_CTRL_08:
+	case RT5668_HP_IMP_SENS_CTRL_09:
+	case RT5668_HP_IMP_SENS_CTRL_10:
+	case RT5668_HP_IMP_SENS_CTRL_11:
+	case RT5668_HP_IMP_SENS_CTRL_12:
+	case RT5668_HP_IMP_SENS_CTRL_13:
+	case RT5668_HP_IMP_SENS_CTRL_14:
+	case RT5668_HP_IMP_SENS_CTRL_15:
+	case RT5668_HP_IMP_SENS_CTRL_16:
+	case RT5668_HP_IMP_SENS_CTRL_17:
+	case RT5668_HP_IMP_SENS_CTRL_18:
+	case RT5668_HP_IMP_SENS_CTRL_19:
+	case RT5668_HP_IMP_SENS_CTRL_20:
+	case RT5668_HP_IMP_SENS_CTRL_21:
+	case RT5668_HP_IMP_SENS_CTRL_22:
+	case RT5668_HP_IMP_SENS_CTRL_23:
+	case RT5668_HP_IMP_SENS_CTRL_24:
+	case RT5668_HP_IMP_SENS_CTRL_25:
+	case RT5668_HP_IMP_SENS_CTRL_26:
+	case RT5668_HP_IMP_SENS_CTRL_27:
+	case RT5668_HP_IMP_SENS_CTRL_28:
+	case RT5668_HP_IMP_SENS_CTRL_29:
+	case RT5668_HP_IMP_SENS_CTRL_30:
+	case RT5668_HP_IMP_SENS_CTRL_31:
+	case RT5668_HP_IMP_SENS_CTRL_32:
+	case RT5668_HP_IMP_SENS_CTRL_33:
+	case RT5668_HP_IMP_SENS_CTRL_34:
+	case RT5668_HP_IMP_SENS_CTRL_35:
+	case RT5668_HP_IMP_SENS_CTRL_36:
+	case RT5668_HP_IMP_SENS_CTRL_37:
+	case RT5668_HP_IMP_SENS_CTRL_38:
+	case RT5668_HP_IMP_SENS_CTRL_39:
+	case RT5668_HP_IMP_SENS_CTRL_40:
+	case RT5668_HP_IMP_SENS_CTRL_41:
+	case RT5668_HP_IMP_SENS_CTRL_42:
+	case RT5668_HP_IMP_SENS_CTRL_43:
+	case RT5668_HP_LOGIC_CTRL_1:
+	case RT5668_HP_LOGIC_CTRL_2:
+	case RT5668_HP_LOGIC_CTRL_3:
+	case RT5668_HP_CALIB_CTRL_1:
+	case RT5668_HP_CALIB_CTRL_2:
+	case RT5668_HP_CALIB_CTRL_3:
+	case RT5668_HP_CALIB_CTRL_4:
+	case RT5668_HP_CALIB_CTRL_5:
+	case RT5668_HP_CALIB_CTRL_6:
+	case RT5668_HP_CALIB_CTRL_7:
+	case RT5668_HP_CALIB_CTRL_9:
+	case RT5668_HP_CALIB_CTRL_10:
+	case RT5668_HP_CALIB_CTRL_11:
+	case RT5668_HP_CALIB_STA_1:
+	case RT5668_HP_CALIB_STA_2:
+	case RT5668_HP_CALIB_STA_3:
+	case RT5668_HP_CALIB_STA_4:
+	case RT5668_HP_CALIB_STA_5:
+	case RT5668_HP_CALIB_STA_6:
+	case RT5668_HP_CALIB_STA_7:
+	case RT5668_HP_CALIB_STA_8:
+	case RT5668_HP_CALIB_STA_9:
+	case RT5668_HP_CALIB_STA_10:
+	case RT5668_HP_CALIB_STA_11:
+	case RT5668_SAR_IL_CMD_1:
+	case RT5668_SAR_IL_CMD_2:
+	case RT5668_SAR_IL_CMD_3:
+	case RT5668_SAR_IL_CMD_4:
+	case RT5668_SAR_IL_CMD_5:
+	case RT5668_SAR_IL_CMD_6:
+	case RT5668_SAR_IL_CMD_7:
+	case RT5668_SAR_IL_CMD_8:
+	case RT5668_SAR_IL_CMD_9:
+	case RT5668_SAR_IL_CMD_10:
+	case RT5668_SAR_IL_CMD_11:
+	case RT5668_SAR_IL_CMD_12:
+	case RT5668_SAR_IL_CMD_13:
+	case RT5668_EFUSE_CTRL_1:
+	case RT5668_EFUSE_CTRL_2:
+	case RT5668_EFUSE_CTRL_3:
+	case RT5668_EFUSE_CTRL_4:
+	case RT5668_EFUSE_CTRL_5:
+	case RT5668_EFUSE_CTRL_6:
+	case RT5668_EFUSE_CTRL_7:
+	case RT5668_EFUSE_CTRL_8:
+	case RT5668_EFUSE_CTRL_9:
+	case RT5668_EFUSE_CTRL_10:
+	case RT5668_EFUSE_CTRL_11:
+	case RT5668_JD_TOP_VC_VTRL:
+	case RT5668_DRC1_CTRL_0:
+	case RT5668_DRC1_CTRL_1:
+	case RT5668_DRC1_CTRL_2:
+	case RT5668_DRC1_CTRL_3:
+	case RT5668_DRC1_CTRL_4:
+	case RT5668_DRC1_CTRL_5:
+	case RT5668_DRC1_CTRL_6:
+	case RT5668_DRC1_HARD_LMT_CTRL_1:
+	case RT5668_DRC1_HARD_LMT_CTRL_2:
+	case RT5668_DRC1_PRIV_1:
+	case RT5668_DRC1_PRIV_2:
+	case RT5668_DRC1_PRIV_3:
+	case RT5668_DRC1_PRIV_4:
+	case RT5668_DRC1_PRIV_5:
+	case RT5668_DRC1_PRIV_6:
+	case RT5668_DRC1_PRIV_7:
+	case RT5668_DRC1_PRIV_8:
+	case RT5668_EQ_AUTO_RCV_CTRL1:
+	case RT5668_EQ_AUTO_RCV_CTRL2:
+	case RT5668_EQ_AUTO_RCV_CTRL3:
+	case RT5668_EQ_AUTO_RCV_CTRL4:
+	case RT5668_EQ_AUTO_RCV_CTRL5:
+	case RT5668_EQ_AUTO_RCV_CTRL6:
+	case RT5668_EQ_AUTO_RCV_CTRL7:
+	case RT5668_EQ_AUTO_RCV_CTRL8:
+	case RT5668_EQ_AUTO_RCV_CTRL9:
+	case RT5668_EQ_AUTO_RCV_CTRL10:
+	case RT5668_EQ_AUTO_RCV_CTRL11:
+	case RT5668_EQ_AUTO_RCV_CTRL12:
+	case RT5668_EQ_AUTO_RCV_CTRL13:
+	case RT5668_ADC_L_EQ_LPF1_A1:
+	case RT5668_R_EQ_LPF1_A1:
+	case RT5668_L_EQ_LPF1_H0:
+	case RT5668_R_EQ_LPF1_H0:
+	case RT5668_L_EQ_BPF1_A1:
+	case RT5668_R_EQ_BPF1_A1:
+	case RT5668_L_EQ_BPF1_A2:
+	case RT5668_R_EQ_BPF1_A2:
+	case RT5668_L_EQ_BPF1_H0:
+	case RT5668_R_EQ_BPF1_H0:
+	case RT5668_L_EQ_BPF2_A1:
+	case RT5668_R_EQ_BPF2_A1:
+	case RT5668_L_EQ_BPF2_A2:
+	case RT5668_R_EQ_BPF2_A2:
+	case RT5668_L_EQ_BPF2_H0:
+	case RT5668_R_EQ_BPF2_H0:
+	case RT5668_L_EQ_BPF3_A1:
+	case RT5668_R_EQ_BPF3_A1:
+	case RT5668_L_EQ_BPF3_A2:
+	case RT5668_R_EQ_BPF3_A2:
+	case RT5668_L_EQ_BPF3_H0:
+	case RT5668_R_EQ_BPF3_H0:
+	case RT5668_L_EQ_BPF4_A1:
+	case RT5668_R_EQ_BPF4_A1:
+	case RT5668_L_EQ_BPF4_A2:
+	case RT5668_R_EQ_BPF4_A2:
+	case RT5668_L_EQ_BPF4_H0:
+	case RT5668_R_EQ_BPF4_H0:
+	case RT5668_L_EQ_HPF1_A1:
+	case RT5668_R_EQ_HPF1_A1:
+	case RT5668_L_EQ_HPF1_H0:
+	case RT5668_R_EQ_HPF1_H0:
+	case RT5668_L_EQ_PRE_VOL:
+	case RT5668_R_EQ_PRE_VOL:
+	case RT5668_L_EQ_POST_VOL:
+	case RT5668_R_EQ_POST_VOL:
+	case RT5668_I2C_MODE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const DECLARE_TLV_DB_SCALE(hp_vol_tlv, -2250, 150, 0);
+static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0);
+static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0);
+
+/* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */
+static const DECLARE_TLV_DB_RANGE(bst_tlv,
+	0, 0, TLV_DB_SCALE_ITEM(0, 0, 0),
+	1, 1, TLV_DB_SCALE_ITEM(2000, 0, 0),
+	2, 2, TLV_DB_SCALE_ITEM(2400, 0, 0),
+	3, 5, TLV_DB_SCALE_ITEM(3000, 500, 0),
+	6, 6, TLV_DB_SCALE_ITEM(4400, 0, 0),
+	7, 7, TLV_DB_SCALE_ITEM(5000, 0, 0),
+	8, 8, TLV_DB_SCALE_ITEM(5200, 0, 0)
+);
+
+/* Interface data select */
+static const char * const rt5668_data_select[] = {
+	"L/R", "R/L", "L/L", "R/R"
+};
+
+static SOC_ENUM_SINGLE_DECL(rt5668_if2_adc_enum,
+	RT5668_DIG_INF2_DATA, RT5668_IF2_ADC_SEL_SFT, rt5668_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5668_if1_01_adc_enum,
+	RT5668_TDM_ADDA_CTRL_1, RT5668_IF1_ADC1_SEL_SFT, rt5668_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5668_if1_23_adc_enum,
+	RT5668_TDM_ADDA_CTRL_1, RT5668_IF1_ADC2_SEL_SFT, rt5668_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5668_if1_45_adc_enum,
+	RT5668_TDM_ADDA_CTRL_1, RT5668_IF1_ADC3_SEL_SFT, rt5668_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5668_if1_67_adc_enum,
+	RT5668_TDM_ADDA_CTRL_1, RT5668_IF1_ADC4_SEL_SFT, rt5668_data_select);
+
+static const struct snd_kcontrol_new rt5668_if2_adc_swap_mux =
+	SOC_DAPM_ENUM("IF2 ADC Swap Mux", rt5668_if2_adc_enum);
+
+static const struct snd_kcontrol_new rt5668_if1_01_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 01 ADC Swap Mux", rt5668_if1_01_adc_enum);
+
+static const struct snd_kcontrol_new rt5668_if1_23_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 23 ADC Swap Mux", rt5668_if1_23_adc_enum);
+
+static const struct snd_kcontrol_new rt5668_if1_45_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 45 ADC Swap Mux", rt5668_if1_45_adc_enum);
+
+static const struct snd_kcontrol_new rt5668_if1_67_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 67 ADC Swap Mux", rt5668_if1_67_adc_enum);
+
+static void rt5668_reset(struct regmap *regmap)
+{
+	regmap_write(regmap, RT5668_RESET, 0);
+	regmap_write(regmap, RT5668_I2C_MODE, 1);
+}
+/**
+ * rt5668_sel_asrc_clk_src - select ASRC clock source for a set of filters
+ * @component: SoC audio component device.
+ * @filter_mask: mask of filters.
+ * @clk_src: clock source
+ *
+ * The ASRC function is for asynchronous MCLK and LRCK. Also, since RT5668 can
+ * only support standard 32fs or 64fs i2s format, ASRC should be enabled to
+ * support special i2s clock format such as Intel's 100fs(100 * sampling rate).
+ * ASRC function will track i2s clock and generate a corresponding system clock
+ * for codec. This function provides an API to select the clock source for a
+ * set of filters specified by the mask. And the component driver will turn on
+ * ASRC for these filters if ASRC is selected as their clock source.
+ */
+int rt5668_sel_asrc_clk_src(struct snd_soc_component *component,
+		unsigned int filter_mask, unsigned int clk_src)
+{
+
+	switch (clk_src) {
+	case RT5668_CLK_SEL_SYS:
+	case RT5668_CLK_SEL_I2S1_ASRC:
+	case RT5668_CLK_SEL_I2S2_ASRC:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (filter_mask & RT5668_DA_STEREO1_FILTER) {
+		snd_soc_component_update_bits(component, RT5668_PLL_TRACK_2,
+			RT5668_FILTER_CLK_SEL_MASK,
+			clk_src << RT5668_FILTER_CLK_SEL_SFT);
+	}
+
+	if (filter_mask & RT5668_AD_STEREO1_FILTER) {
+		snd_soc_component_update_bits(component, RT5668_PLL_TRACK_3,
+			RT5668_FILTER_CLK_SEL_MASK,
+			clk_src << RT5668_FILTER_CLK_SEL_SFT);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rt5668_sel_asrc_clk_src);
+
+static int rt5668_button_detect(struct snd_soc_component *component)
+{
+	int btn_type, val;
+
+	val = snd_soc_component_read32(component, RT5668_4BTN_IL_CMD_1);
+	btn_type = val & 0xfff0;
+	snd_soc_component_write(component, RT5668_4BTN_IL_CMD_1, val);
+	pr_debug("%s btn_type=%x\n", __func__, btn_type);
+
+	return btn_type;
+}
+
+static void rt5668_enable_push_button_irq(struct snd_soc_component *component,
+		bool enable)
+{
+	if (enable) {
+		snd_soc_component_update_bits(component, RT5668_SAR_IL_CMD_1,
+			RT5668_SAR_BUTT_DET_MASK, RT5668_SAR_BUTT_DET_EN);
+		snd_soc_component_update_bits(component, RT5668_SAR_IL_CMD_13,
+			RT5668_SAR_SOUR_MASK, RT5668_SAR_SOUR_BTN);
+		snd_soc_component_write(component, RT5668_IL_CMD_1, 0x0040);
+		snd_soc_component_update_bits(component, RT5668_4BTN_IL_CMD_2,
+			RT5668_4BTN_IL_MASK | RT5668_4BTN_IL_RST_MASK,
+			RT5668_4BTN_IL_EN | RT5668_4BTN_IL_NOR);
+		snd_soc_component_update_bits(component, RT5668_IRQ_CTRL_3,
+			RT5668_IL_IRQ_MASK, RT5668_IL_IRQ_EN);
+	} else {
+		snd_soc_component_update_bits(component, RT5668_IRQ_CTRL_3,
+			RT5668_IL_IRQ_MASK, RT5668_IL_IRQ_DIS);
+		snd_soc_component_update_bits(component, RT5668_SAR_IL_CMD_1,
+			RT5668_SAR_BUTT_DET_MASK, RT5668_SAR_BUTT_DET_DIS);
+		snd_soc_component_update_bits(component, RT5668_4BTN_IL_CMD_2,
+			RT5668_4BTN_IL_MASK, RT5668_4BTN_IL_DIS);
+		snd_soc_component_update_bits(component, RT5668_4BTN_IL_CMD_2,
+			RT5668_4BTN_IL_RST_MASK, RT5668_4BTN_IL_RST);
+		snd_soc_component_update_bits(component, RT5668_SAR_IL_CMD_13,
+			RT5668_SAR_SOUR_MASK, RT5668_SAR_SOUR_TYPE);
+	}
+}
+
+/**
+ * rt5668_headset_detect - Detect headset.
+ * @component: SoC audio component device.
+ * @jack_insert: Jack insert or not.
+ *
+ * Detect whether is headset or not when jack inserted.
+ *
+ * Returns detect status.
+ */
+static int rt5668_headset_detect(struct snd_soc_component *component,
+		int jack_insert)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+	struct snd_soc_dapm_context *dapm =
+		snd_soc_component_get_dapm(component);
+	unsigned int val, count;
+
+	if (jack_insert) {
+		snd_soc_dapm_force_enable_pin(dapm, "CBJ Power");
+		snd_soc_dapm_sync(dapm);
+		snd_soc_component_update_bits(component, RT5668_CBJ_CTRL_1,
+			RT5668_TRIG_JD_MASK, RT5668_TRIG_JD_HIGH);
+
+		count = 0;
+		val = snd_soc_component_read32(component, RT5668_CBJ_CTRL_2)
+			& RT5668_JACK_TYPE_MASK;
+		while (val == 0 && count < 50) {
+			usleep_range(10000, 15000);
+			val = snd_soc_component_read32(component,
+				RT5668_CBJ_CTRL_2) & RT5668_JACK_TYPE_MASK;
+			count++;
+		}
+
+		switch (val) {
+		case 0x1:
+		case 0x2:
+			rt5668->jack_type = SND_JACK_HEADSET;
+			rt5668_enable_push_button_irq(component, true);
+			break;
+		default:
+			rt5668->jack_type = SND_JACK_HEADPHONE;
+		}
+
+	} else {
+		rt5668_enable_push_button_irq(component, false);
+		snd_soc_component_update_bits(component, RT5668_CBJ_CTRL_1,
+			RT5668_TRIG_JD_MASK, RT5668_TRIG_JD_LOW);
+		snd_soc_dapm_disable_pin(dapm, "CBJ Power");
+		snd_soc_dapm_sync(dapm);
+
+		rt5668->jack_type = 0;
+	}
+
+	dev_dbg(component->dev, "jack_type = %d\n", rt5668->jack_type);
+	return rt5668->jack_type;
+}
+
+static irqreturn_t rt5668_irq(int irq, void *data)
+{
+	struct rt5668_priv *rt5668 = data;
+
+	mod_delayed_work(system_power_efficient_wq,
+			&rt5668->jack_detect_work, msecs_to_jiffies(250));
+
+	return IRQ_HANDLED;
+}
+
+static void rt5668_jd_check_handler(struct work_struct *work)
+{
+	struct rt5668_priv *rt5668 = container_of(work, struct rt5668_priv,
+		jd_check_work.work);
+
+	if (snd_soc_component_read32(rt5668->component, RT5668_AJD1_CTRL)
+		& RT5668_JDH_RS_MASK) {
+		/* jack out */
+		rt5668->jack_type = rt5668_headset_detect(rt5668->component, 0);
+
+		snd_soc_jack_report(rt5668->hs_jack, rt5668->jack_type,
+				SND_JACK_HEADSET |
+				SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+				SND_JACK_BTN_2 | SND_JACK_BTN_3);
+	} else {
+		schedule_delayed_work(&rt5668->jd_check_work, 500);
+	}
+}
+
+static int rt5668_set_jack_detect(struct snd_soc_component *component,
+	struct snd_soc_jack *hs_jack, void *data)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+
+	switch (rt5668->pdata.jd_src) {
+	case RT5668_JD1:
+		snd_soc_component_update_bits(component, RT5668_CBJ_CTRL_2,
+			RT5668_EXT_JD_SRC, RT5668_EXT_JD_SRC_MANUAL);
+		snd_soc_component_write(component, RT5668_CBJ_CTRL_1, 0xd002);
+		snd_soc_component_update_bits(component, RT5668_CBJ_CTRL_3,
+			RT5668_CBJ_IN_BUF_EN, RT5668_CBJ_IN_BUF_EN);
+		snd_soc_component_update_bits(component, RT5668_SAR_IL_CMD_1,
+			RT5668_SAR_POW_MASK, RT5668_SAR_POW_EN);
+		regmap_update_bits(rt5668->regmap, RT5668_GPIO_CTRL_1,
+			RT5668_GP1_PIN_MASK, RT5668_GP1_PIN_IRQ);
+		regmap_update_bits(rt5668->regmap, RT5668_RC_CLK_CTRL,
+				RT5668_POW_IRQ | RT5668_POW_JDH |
+				RT5668_POW_ANA, RT5668_POW_IRQ |
+				RT5668_POW_JDH | RT5668_POW_ANA);
+		regmap_update_bits(rt5668->regmap, RT5668_PWR_ANLG_2,
+			RT5668_PWR_JDH | RT5668_PWR_JDL,
+			RT5668_PWR_JDH | RT5668_PWR_JDL);
+		regmap_update_bits(rt5668->regmap, RT5668_IRQ_CTRL_2,
+			RT5668_JD1_EN_MASK | RT5668_JD1_POL_MASK,
+			RT5668_JD1_EN | RT5668_JD1_POL_NOR);
+		mod_delayed_work(system_power_efficient_wq,
+			   &rt5668->jack_detect_work, msecs_to_jiffies(250));
+		break;
+
+	case RT5668_JD_NULL:
+		regmap_update_bits(rt5668->regmap, RT5668_IRQ_CTRL_2,
+			RT5668_JD1_EN_MASK, RT5668_JD1_DIS);
+		regmap_update_bits(rt5668->regmap, RT5668_RC_CLK_CTRL,
+				RT5668_POW_JDH | RT5668_POW_JDL, 0);
+		break;
+
+	default:
+		dev_warn(component->dev, "Wrong JD source\n");
+		break;
+	}
+
+	rt5668->hs_jack = hs_jack;
+
+	return 0;
+}
+
+static void rt5668_jack_detect_handler(struct work_struct *work)
+{
+	struct rt5668_priv *rt5668 =
+		container_of(work, struct rt5668_priv, jack_detect_work.work);
+	int val, btn_type;
+
+	while (!rt5668->component)
+		usleep_range(10000, 15000);
+
+	while (!rt5668->component->card->instantiated)
+		usleep_range(10000, 15000);
+
+	mutex_lock(&rt5668->calibrate_mutex);
+
+	val = snd_soc_component_read32(rt5668->component, RT5668_AJD1_CTRL)
+		& RT5668_JDH_RS_MASK;
+	if (!val) {
+		/* jack in */
+		if (rt5668->jack_type == 0) {
+			/* jack was out, report jack type */
+			rt5668->jack_type =
+				rt5668_headset_detect(rt5668->component, 1);
+		} else {
+			/* jack is already in, report button event */
+			rt5668->jack_type = SND_JACK_HEADSET;
+			btn_type = rt5668_button_detect(rt5668->component);
+			/**
+			 * rt5668 can report three kinds of button behavior,
+			 * one click, double click and hold. However,
+			 * currently we will report button pressed/released
+			 * event. So all the three button behaviors are
+			 * treated as button pressed.
+			 */
+			switch (btn_type) {
+			case 0x8000:
+			case 0x4000:
+			case 0x2000:
+				rt5668->jack_type |= SND_JACK_BTN_0;
+				break;
+			case 0x1000:
+			case 0x0800:
+			case 0x0400:
+				rt5668->jack_type |= SND_JACK_BTN_1;
+				break;
+			case 0x0200:
+			case 0x0100:
+			case 0x0080:
+				rt5668->jack_type |= SND_JACK_BTN_2;
+				break;
+			case 0x0040:
+			case 0x0020:
+			case 0x0010:
+				rt5668->jack_type |= SND_JACK_BTN_3;
+				break;
+			case 0x0000: /* unpressed */
+				break;
+			default:
+				btn_type = 0;
+				dev_err(rt5668->component->dev,
+					"Unexpected button code 0x%04x\n",
+					btn_type);
+				break;
+			}
+		}
+	} else {
+		/* jack out */
+		rt5668->jack_type = rt5668_headset_detect(rt5668->component, 0);
+	}
+
+	snd_soc_jack_report(rt5668->hs_jack, rt5668->jack_type,
+			SND_JACK_HEADSET |
+			    SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+			    SND_JACK_BTN_2 | SND_JACK_BTN_3);
+
+	if (rt5668->jack_type & (SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+		SND_JACK_BTN_2 | SND_JACK_BTN_3))
+		schedule_delayed_work(&rt5668->jd_check_work, 0);
+	else
+		cancel_delayed_work_sync(&rt5668->jd_check_work);
+
+	mutex_unlock(&rt5668->calibrate_mutex);
+}
+
+static const struct snd_kcontrol_new rt5668_snd_controls[] = {
+	/* Headphone Output Volume */
+	SOC_DOUBLE_R_TLV("Headphone Playback Volume", RT5668_HPL_GAIN,
+		RT5668_HPR_GAIN, RT5668_G_HP_SFT, 15, 1, hp_vol_tlv),
+
+	/* DAC Digital Volume */
+	SOC_DOUBLE_TLV("DAC1 Playback Volume", RT5668_DAC1_DIG_VOL,
+		RT5668_L_VOL_SFT, RT5668_R_VOL_SFT, 175, 0, dac_vol_tlv),
+
+	/* IN Boost Volume */
+	SOC_SINGLE_TLV("CBJ Boost Volume", RT5668_CBJ_BST_CTRL,
+		RT5668_BST_CBJ_SFT, 8, 0, bst_tlv),
+
+	/* ADC Digital Volume Control */
+	SOC_DOUBLE("STO1 ADC Capture Switch", RT5668_STO1_ADC_DIG_VOL,
+		RT5668_L_MUTE_SFT, RT5668_R_MUTE_SFT, 1, 1),
+	SOC_DOUBLE_TLV("STO1 ADC Capture Volume", RT5668_STO1_ADC_DIG_VOL,
+		RT5668_L_VOL_SFT, RT5668_R_VOL_SFT, 127, 0, adc_vol_tlv),
+
+	/* ADC Boost Volume Control */
+	SOC_DOUBLE_TLV("STO1 ADC Boost Gain Volume", RT5668_STO1_ADC_BOOST,
+		RT5668_STO1_ADC_L_BST_SFT, RT5668_STO1_ADC_R_BST_SFT,
+		3, 0, adc_bst_tlv),
+};
+
+
+static int rt5668_div_sel(struct rt5668_priv *rt5668,
+			  int target, const int div[], int size)
+{
+	int i;
+
+	if (rt5668->sysclk < target) {
+		pr_err("sysclk rate %d is too low\n",
+			rt5668->sysclk);
+		return 0;
+	}
+
+	for (i = 0; i < size - 1; i++) {
+		pr_info("div[%d]=%d\n", i, div[i]);
+		if (target * div[i] == rt5668->sysclk)
+			return i;
+		if (target * div[i + 1] > rt5668->sysclk) {
+			pr_err("can't find div for sysclk %d\n",
+				rt5668->sysclk);
+			return i;
+		}
+	}
+
+	if (target * div[i] < rt5668->sysclk)
+		pr_err("sysclk rate %d is too high\n",
+			rt5668->sysclk);
+
+	return size - 1;
+
+}
+
+/**
+ * set_dmic_clk - Set parameter of dmic.
+ *
+ * @w: DAPM widget.
+ * @kcontrol: The kcontrol of this widget.
+ * @event: Event id.
+ *
+ * Choose dmic clock between 1MHz and 3MHz.
+ * It is better for clock to approximate 3MHz.
+ */
+static int set_dmic_clk(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+	int idx = -EINVAL;
+	static const int div[] = {2, 4, 6, 8, 12, 16, 24, 32, 48, 64, 96, 128};
+
+	idx = rt5668_div_sel(rt5668, 1500000, div, ARRAY_SIZE(div));
+
+	snd_soc_component_update_bits(component, RT5668_DMIC_CTRL_1,
+		RT5668_DMIC_CLK_MASK, idx << RT5668_DMIC_CLK_SFT);
+
+	return 0;
+}
+
+static int set_filter_clk(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+	int ref, val, reg, idx = -EINVAL;
+	static const int div[] = {1, 2, 3, 4, 6, 8, 12, 16, 24, 32, 48};
+
+	val = snd_soc_component_read32(component, RT5668_GPIO_CTRL_1) &
+		RT5668_GP4_PIN_MASK;
+	if (w->shift == RT5668_PWR_ADC_S1F_BIT &&
+		val == RT5668_GP4_PIN_ADCDAT2)
+		ref = 256 * rt5668->lrck[RT5668_AIF2];
+	else
+		ref = 256 * rt5668->lrck[RT5668_AIF1];
+
+	idx = rt5668_div_sel(rt5668, ref, div, ARRAY_SIZE(div));
+
+	if (w->shift == RT5668_PWR_ADC_S1F_BIT)
+		reg = RT5668_PLL_TRACK_3;
+	else
+		reg = RT5668_PLL_TRACK_2;
+
+	snd_soc_component_update_bits(component, reg,
+		RT5668_FILTER_CLK_SEL_MASK, idx << RT5668_FILTER_CLK_SEL_SFT);
+
+	return 0;
+}
+
+static int is_sys_clk_from_pll1(struct snd_soc_dapm_widget *w,
+			 struct snd_soc_dapm_widget *sink)
+{
+	unsigned int val;
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	val = snd_soc_component_read32(component, RT5668_GLB_CLK);
+	val &= RT5668_SCLK_SRC_MASK;
+	if (val == RT5668_SCLK_SRC_PLL1)
+		return 1;
+	else
+		return 0;
+}
+
+static int is_using_asrc(struct snd_soc_dapm_widget *w,
+			 struct snd_soc_dapm_widget *sink)
+{
+	unsigned int reg, shift, val;
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (w->shift) {
+	case RT5668_ADC_STO1_ASRC_SFT:
+		reg = RT5668_PLL_TRACK_3;
+		shift = RT5668_FILTER_CLK_SEL_SFT;
+		break;
+	case RT5668_DAC_STO1_ASRC_SFT:
+		reg = RT5668_PLL_TRACK_2;
+		shift = RT5668_FILTER_CLK_SEL_SFT;
+		break;
+	default:
+		return 0;
+	}
+
+	val = (snd_soc_component_read32(component, reg) >> shift) & 0xf;
+	switch (val) {
+	case RT5668_CLK_SEL_I2S1_ASRC:
+	case RT5668_CLK_SEL_I2S2_ASRC:
+		return 1;
+	default:
+		return 0;
+	}
+
+}
+
+/* Digital Mixer */
+static const struct snd_kcontrol_new rt5668_sto1_adc_l_mix[] = {
+	SOC_DAPM_SINGLE("ADC1 Switch", RT5668_STO1_ADC_MIXER,
+			RT5668_M_STO1_ADC_L1_SFT, 1, 1),
+	SOC_DAPM_SINGLE("ADC2 Switch", RT5668_STO1_ADC_MIXER,
+			RT5668_M_STO1_ADC_L2_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5668_sto1_adc_r_mix[] = {
+	SOC_DAPM_SINGLE("ADC1 Switch", RT5668_STO1_ADC_MIXER,
+			RT5668_M_STO1_ADC_R1_SFT, 1, 1),
+	SOC_DAPM_SINGLE("ADC2 Switch", RT5668_STO1_ADC_MIXER,
+			RT5668_M_STO1_ADC_R2_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5668_dac_l_mix[] = {
+	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5668_AD_DA_MIXER,
+			RT5668_M_ADCMIX_L_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC1 Switch", RT5668_AD_DA_MIXER,
+			RT5668_M_DAC1_L_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5668_dac_r_mix[] = {
+	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5668_AD_DA_MIXER,
+			RT5668_M_ADCMIX_R_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC1 Switch", RT5668_AD_DA_MIXER,
+			RT5668_M_DAC1_R_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5668_sto1_dac_l_mix[] = {
+	SOC_DAPM_SINGLE("DAC L1 Switch", RT5668_STO1_DAC_MIXER,
+			RT5668_M_DAC_L1_STO_L_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC R1 Switch", RT5668_STO1_DAC_MIXER,
+			RT5668_M_DAC_R1_STO_L_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5668_sto1_dac_r_mix[] = {
+	SOC_DAPM_SINGLE("DAC L1 Switch", RT5668_STO1_DAC_MIXER,
+			RT5668_M_DAC_L1_STO_R_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC R1 Switch", RT5668_STO1_DAC_MIXER,
+			RT5668_M_DAC_R1_STO_R_SFT, 1, 1),
+};
+
+/* Analog Input Mixer */
+static const struct snd_kcontrol_new rt5668_rec1_l_mix[] = {
+	SOC_DAPM_SINGLE("CBJ Switch", RT5668_REC_MIXER,
+			RT5668_M_CBJ_RM1_L_SFT, 1, 1),
+};
+
+/* STO1 ADC1 Source */
+/* MX-26 [13] [5] */
+static const char * const rt5668_sto1_adc1_src[] = {
+	"DAC MIX", "ADC"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5668_sto1_adc1l_enum, RT5668_STO1_ADC_MIXER,
+	RT5668_STO1_ADC1L_SRC_SFT, rt5668_sto1_adc1_src);
+
+static const struct snd_kcontrol_new rt5668_sto1_adc1l_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC1L Source", rt5668_sto1_adc1l_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5668_sto1_adc1r_enum, RT5668_STO1_ADC_MIXER,
+	RT5668_STO1_ADC1R_SRC_SFT, rt5668_sto1_adc1_src);
+
+static const struct snd_kcontrol_new rt5668_sto1_adc1r_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC1L Source", rt5668_sto1_adc1r_enum);
+
+/* STO1 ADC Source */
+/* MX-26 [11:10] [3:2] */
+static const char * const rt5668_sto1_adc_src[] = {
+	"ADC1 L", "ADC1 R"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5668_sto1_adcl_enum, RT5668_STO1_ADC_MIXER,
+	RT5668_STO1_ADCL_SRC_SFT, rt5668_sto1_adc_src);
+
+static const struct snd_kcontrol_new rt5668_sto1_adcl_mux =
+	SOC_DAPM_ENUM("Stereo1 ADCL Source", rt5668_sto1_adcl_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5668_sto1_adcr_enum, RT5668_STO1_ADC_MIXER,
+	RT5668_STO1_ADCR_SRC_SFT, rt5668_sto1_adc_src);
+
+static const struct snd_kcontrol_new rt5668_sto1_adcr_mux =
+	SOC_DAPM_ENUM("Stereo1 ADCR Source", rt5668_sto1_adcr_enum);
+
+/* STO1 ADC2 Source */
+/* MX-26 [12] [4] */
+static const char * const rt5668_sto1_adc2_src[] = {
+	"DAC MIX", "DMIC"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5668_sto1_adc2l_enum, RT5668_STO1_ADC_MIXER,
+	RT5668_STO1_ADC2L_SRC_SFT, rt5668_sto1_adc2_src);
+
+static const struct snd_kcontrol_new rt5668_sto1_adc2l_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC2L Source", rt5668_sto1_adc2l_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5668_sto1_adc2r_enum, RT5668_STO1_ADC_MIXER,
+	RT5668_STO1_ADC2R_SRC_SFT, rt5668_sto1_adc2_src);
+
+static const struct snd_kcontrol_new rt5668_sto1_adc2r_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC2R Source", rt5668_sto1_adc2r_enum);
+
+/* MX-79 [6:4] I2S1 ADC data location */
+static const unsigned int rt5668_if1_adc_slot_values[] = {
+	0,
+	2,
+	4,
+	6,
+};
+
+static const char * const rt5668_if1_adc_slot_src[] = {
+	"Slot 0", "Slot 2", "Slot 4", "Slot 6"
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(rt5668_if1_adc_slot_enum,
+	RT5668_TDM_CTRL, RT5668_TDM_ADC_LCA_SFT, RT5668_TDM_ADC_LCA_MASK,
+	rt5668_if1_adc_slot_src, rt5668_if1_adc_slot_values);
+
+static const struct snd_kcontrol_new rt5668_if1_adc_slot_mux =
+	SOC_DAPM_ENUM("IF1 ADC Slot location", rt5668_if1_adc_slot_enum);
+
+/* Analog DAC L1 Source, Analog DAC R1 Source*/
+/* MX-2B [4], MX-2B [0]*/
+static const char * const rt5668_alg_dac1_src[] = {
+	"Stereo1 DAC Mixer", "DAC1"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5668_alg_dac_l1_enum, RT5668_A_DAC1_MUX,
+	RT5668_A_DACL1_SFT, rt5668_alg_dac1_src);
+
+static const struct snd_kcontrol_new rt5668_alg_dac_l1_mux =
+	SOC_DAPM_ENUM("Analog DAC L1 Source", rt5668_alg_dac_l1_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5668_alg_dac_r1_enum, RT5668_A_DAC1_MUX,
+	RT5668_A_DACR1_SFT, rt5668_alg_dac1_src);
+
+static const struct snd_kcontrol_new rt5668_alg_dac_r1_mux =
+	SOC_DAPM_ENUM("Analog DAC R1 Source", rt5668_alg_dac_r1_enum);
+
+/* Out Switch */
+static const struct snd_kcontrol_new hpol_switch =
+	SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5668_HP_CTRL_1,
+					RT5668_L_MUTE_SFT, 1, 1);
+static const struct snd_kcontrol_new hpor_switch =
+	SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5668_HP_CTRL_1,
+					RT5668_R_MUTE_SFT, 1, 1);
+
+static int rt5668_hp_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		snd_soc_component_write(component,
+			RT5668_HP_LOGIC_CTRL_2, 0x0012);
+		snd_soc_component_write(component,
+			RT5668_HP_CTRL_2, 0x6000);
+		snd_soc_component_update_bits(component, RT5668_STO_NG2_CTRL_1,
+			RT5668_NG2_EN_MASK, RT5668_NG2_EN);
+		snd_soc_component_update_bits(component,
+			RT5668_DEPOP_1, 0x60, 0x60);
+		break;
+
+	case SND_SOC_DAPM_POST_PMD:
+		snd_soc_component_update_bits(component,
+			RT5668_DEPOP_1, 0x60, 0x0);
+		snd_soc_component_write(component,
+			RT5668_HP_CTRL_2, 0x0000);
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+
+}
+
+static int set_dmic_power(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		/*Add delay to avoid pop noise*/
+		msleep(150);
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static int rt5655_set_verf(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		switch (w->shift) {
+		case RT5668_PWR_VREF1_BIT:
+			snd_soc_component_update_bits(component,
+				RT5668_PWR_ANLG_1, RT5668_PWR_FV1, 0);
+			break;
+
+		case RT5668_PWR_VREF2_BIT:
+			snd_soc_component_update_bits(component,
+				RT5668_PWR_ANLG_1, RT5668_PWR_FV2, 0);
+			break;
+
+		default:
+			break;
+		}
+		break;
+
+	case SND_SOC_DAPM_POST_PMU:
+		usleep_range(15000, 20000);
+		switch (w->shift) {
+		case RT5668_PWR_VREF1_BIT:
+			snd_soc_component_update_bits(component,
+				RT5668_PWR_ANLG_1, RT5668_PWR_FV1,
+				RT5668_PWR_FV1);
+			break;
+
+		case RT5668_PWR_VREF2_BIT:
+			snd_soc_component_update_bits(component,
+				RT5668_PWR_ANLG_1, RT5668_PWR_FV2,
+				RT5668_PWR_FV2);
+			break;
+
+		default:
+			break;
+		}
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static const unsigned int rt5668_adcdat_pin_values[] = {
+	1,
+	3,
+};
+
+static const char * const rt5668_adcdat_pin_select[] = {
+	"ADCDAT1",
+	"ADCDAT2",
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(rt5668_adcdat_pin_enum,
+	RT5668_GPIO_CTRL_1, RT5668_GP4_PIN_SFT, RT5668_GP4_PIN_MASK,
+	rt5668_adcdat_pin_select, rt5668_adcdat_pin_values);
+
+static const struct snd_kcontrol_new rt5668_adcdat_pin_ctrl =
+	SOC_DAPM_ENUM("ADCDAT", rt5668_adcdat_pin_enum);
+
+static const struct snd_soc_dapm_widget rt5668_dapm_widgets[] = {
+	SND_SOC_DAPM_SUPPLY("LDO2", RT5668_PWR_ANLG_3, RT5668_PWR_LDO2_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL1", RT5668_PWR_ANLG_3, RT5668_PWR_PLL_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL2B", RT5668_PWR_ANLG_3, RT5668_PWR_PLL2B_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL2F", RT5668_PWR_ANLG_3, RT5668_PWR_PLL2F_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Vref1", RT5668_PWR_ANLG_1, RT5668_PWR_VREF1_BIT, 0,
+		rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+	SND_SOC_DAPM_SUPPLY("Vref2", RT5668_PWR_ANLG_1, RT5668_PWR_VREF2_BIT, 0,
+		rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+
+	/* ASRC */
+	SND_SOC_DAPM_SUPPLY_S("DAC STO1 ASRC", 1, RT5668_PLL_TRACK_1,
+		RT5668_DAC_STO1_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("ADC STO1 ASRC", 1, RT5668_PLL_TRACK_1,
+		RT5668_ADC_STO1_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("AD ASRC", 1, RT5668_PLL_TRACK_1,
+		RT5668_AD_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("DA ASRC", 1, RT5668_PLL_TRACK_1,
+		RT5668_DA_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("DMIC ASRC", 1, RT5668_PLL_TRACK_1,
+		RT5668_DMIC_ASRC_SFT, 0, NULL, 0),
+
+	/* Input Side */
+	SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5668_PWR_ANLG_2, RT5668_PWR_MB1_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("MICBIAS2", RT5668_PWR_ANLG_2, RT5668_PWR_MB2_BIT,
+		0, NULL, 0),
+
+	/* Input Lines */
+	SND_SOC_DAPM_INPUT("DMIC L1"),
+	SND_SOC_DAPM_INPUT("DMIC R1"),
+
+	SND_SOC_DAPM_INPUT("IN1P"),
+
+	SND_SOC_DAPM_SUPPLY("DMIC CLK", SND_SOC_NOPM, 0, 0,
+		set_dmic_clk, SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_SUPPLY("DMIC1 Power", RT5668_DMIC_CTRL_1,
+		RT5668_DMIC_1_EN_SFT, 0, set_dmic_power, SND_SOC_DAPM_POST_PMU),
+
+	/* Boost */
+	SND_SOC_DAPM_PGA("BST1 CBJ", SND_SOC_NOPM,
+		0, 0, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("CBJ Power", RT5668_PWR_ANLG_3,
+		RT5668_PWR_CBJ_BIT, 0, NULL, 0),
+
+	/* REC Mixer */
+	SND_SOC_DAPM_MIXER("RECMIX1L", SND_SOC_NOPM, 0, 0, rt5668_rec1_l_mix,
+		ARRAY_SIZE(rt5668_rec1_l_mix)),
+	SND_SOC_DAPM_SUPPLY("RECMIX1L Power", RT5668_PWR_ANLG_2,
+		RT5668_PWR_RM1_L_BIT, 0, NULL, 0),
+
+	/* ADCs */
+	SND_SOC_DAPM_ADC("ADC1 L", NULL, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_ADC("ADC1 R", NULL, SND_SOC_NOPM, 0, 0),
+
+	SND_SOC_DAPM_SUPPLY("ADC1 L Power", RT5668_PWR_DIG_1,
+		RT5668_PWR_ADC_L1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC1 R Power", RT5668_PWR_DIG_1,
+		RT5668_PWR_ADC_R1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC1 clock", RT5668_CHOP_ADC,
+		RT5668_CKGEN_ADC1_SFT, 0, NULL, 0),
+
+	/* ADC Mux */
+	SND_SOC_DAPM_MUX("Stereo1 ADC L1 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5668_sto1_adc1l_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R1 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5668_sto1_adc1r_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC L2 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5668_sto1_adc2l_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R2 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5668_sto1_adc2r_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC L Mux", SND_SOC_NOPM, 0, 0,
+		&rt5668_sto1_adcl_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R Mux", SND_SOC_NOPM, 0, 0,
+		&rt5668_sto1_adcr_mux),
+	SND_SOC_DAPM_MUX("IF1_ADC Mux", SND_SOC_NOPM, 0, 0,
+		&rt5668_if1_adc_slot_mux),
+
+	/* ADC Mixer */
+	SND_SOC_DAPM_SUPPLY("ADC Stereo1 Filter", RT5668_PWR_DIG_2,
+		RT5668_PWR_ADC_S1F_BIT, 0, set_filter_clk,
+		SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_MIXER("Stereo1 ADC MIXL", RT5668_STO1_ADC_DIG_VOL,
+		RT5668_L_MUTE_SFT, 1, rt5668_sto1_adc_l_mix,
+		ARRAY_SIZE(rt5668_sto1_adc_l_mix)),
+	SND_SOC_DAPM_MIXER("Stereo1 ADC MIXR", RT5668_STO1_ADC_DIG_VOL,
+		RT5668_R_MUTE_SFT, 1, rt5668_sto1_adc_r_mix,
+		ARRAY_SIZE(rt5668_sto1_adc_r_mix)),
+
+	/* ADC PGA */
+	SND_SOC_DAPM_PGA("Stereo1 ADC MIX", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	/* Digital Interface */
+	SND_SOC_DAPM_SUPPLY("I2S1", RT5668_PWR_DIG_1, RT5668_PWR_I2S1_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("I2S2", RT5668_PWR_DIG_1, RT5668_PWR_I2S2_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1 L", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1 R", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	/* Digital Interface Select */
+	SND_SOC_DAPM_MUX("IF1 01 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5668_if1_01_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 23 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5668_if1_23_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 45 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5668_if1_45_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 67 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5668_if1_67_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF2 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5668_if2_adc_swap_mux),
+
+	SND_SOC_DAPM_MUX("ADCDAT Mux", SND_SOC_NOPM, 0, 0,
+			&rt5668_adcdat_pin_ctrl),
+
+	/* Audio Interface */
+	SND_SOC_DAPM_AIF_OUT("AIF1TX", "AIF1 Capture", 0,
+		RT5668_I2S1_SDP, RT5668_SEL_ADCDAT_SFT, 1),
+	SND_SOC_DAPM_AIF_OUT("AIF2TX", "AIF2 Capture", 0,
+		RT5668_I2S2_SDP, RT5668_I2S2_PIN_CFG_SFT, 1),
+	SND_SOC_DAPM_AIF_IN("AIF1RX", "AIF1 Playback", 0, SND_SOC_NOPM, 0, 0),
+
+	/* Output Side */
+	/* DAC mixer before sound effect  */
+	SND_SOC_DAPM_MIXER("DAC1 MIXL", SND_SOC_NOPM, 0, 0,
+		rt5668_dac_l_mix, ARRAY_SIZE(rt5668_dac_l_mix)),
+	SND_SOC_DAPM_MIXER("DAC1 MIXR", SND_SOC_NOPM, 0, 0,
+		rt5668_dac_r_mix, ARRAY_SIZE(rt5668_dac_r_mix)),
+
+	/* DAC channel Mux */
+	SND_SOC_DAPM_MUX("DAC L1 Source", SND_SOC_NOPM, 0, 0,
+		&rt5668_alg_dac_l1_mux),
+	SND_SOC_DAPM_MUX("DAC R1 Source", SND_SOC_NOPM, 0, 0,
+		&rt5668_alg_dac_r1_mux),
+
+	/* DAC Mixer */
+	SND_SOC_DAPM_SUPPLY("DAC Stereo1 Filter", RT5668_PWR_DIG_2,
+		RT5668_PWR_DAC_S1F_BIT, 0, set_filter_clk,
+		SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_MIXER("Stereo1 DAC MIXL", SND_SOC_NOPM, 0, 0,
+		rt5668_sto1_dac_l_mix, ARRAY_SIZE(rt5668_sto1_dac_l_mix)),
+	SND_SOC_DAPM_MIXER("Stereo1 DAC MIXR", SND_SOC_NOPM, 0, 0,
+		rt5668_sto1_dac_r_mix, ARRAY_SIZE(rt5668_sto1_dac_r_mix)),
+
+	/* DACs */
+	SND_SOC_DAPM_DAC("DAC L1", NULL, RT5668_PWR_DIG_1,
+		RT5668_PWR_DAC_L1_BIT, 0),
+	SND_SOC_DAPM_DAC("DAC R1", NULL, RT5668_PWR_DIG_1,
+		RT5668_PWR_DAC_R1_BIT, 0),
+	SND_SOC_DAPM_SUPPLY_S("DAC 1 Clock", 3, RT5668_CHOP_DAC,
+		RT5668_CKGEN_DAC1_SFT, 0, NULL, 0),
+
+	/* HPO */
+	SND_SOC_DAPM_PGA_S("HP Amp", 1, SND_SOC_NOPM, 0, 0, rt5668_hp_event,
+		SND_SOC_DAPM_POST_PMD | SND_SOC_DAPM_PRE_PMU),
+
+	SND_SOC_DAPM_SUPPLY("HP Amp L", RT5668_PWR_ANLG_1,
+		RT5668_PWR_HA_L_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("HP Amp R", RT5668_PWR_ANLG_1,
+		RT5668_PWR_HA_R_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("Charge Pump", 1, RT5668_DEPOP_1,
+		RT5668_PUMP_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("Capless", 2, RT5668_DEPOP_1,
+		RT5668_CAPLESS_EN_SFT, 0, NULL, 0),
+
+	SND_SOC_DAPM_SWITCH("HPOL Playback", SND_SOC_NOPM, 0, 0,
+		&hpol_switch),
+	SND_SOC_DAPM_SWITCH("HPOR Playback", SND_SOC_NOPM, 0, 0,
+		&hpor_switch),
+
+	/* CLK DET */
+	SND_SOC_DAPM_SUPPLY("CLKDET SYS", RT5668_CLK_DET,
+		RT5668_SYS_CLK_DET_SFT,	0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET PLL1", RT5668_CLK_DET,
+		RT5668_PLL1_CLK_DET_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET PLL2", RT5668_CLK_DET,
+		RT5668_PLL2_CLK_DET_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET", RT5668_CLK_DET,
+		RT5668_POW_CLK_DET_SFT, 0, NULL, 0),
+
+	/* Output Lines */
+	SND_SOC_DAPM_OUTPUT("HPOL"),
+	SND_SOC_DAPM_OUTPUT("HPOR"),
+
+};
+
+static const struct snd_soc_dapm_route rt5668_dapm_routes[] = {
+	/*PLL*/
+	{"ADC Stereo1 Filter", NULL, "PLL1", is_sys_clk_from_pll1},
+	{"DAC Stereo1 Filter", NULL, "PLL1", is_sys_clk_from_pll1},
+
+	/*ASRC*/
+	{"ADC Stereo1 Filter", NULL, "ADC STO1 ASRC", is_using_asrc},
+	{"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc},
+	{"ADC STO1 ASRC", NULL, "AD ASRC"},
+	{"DAC STO1 ASRC", NULL, "DA ASRC"},
+
+	/*Vref*/
+	{"MICBIAS1", NULL, "Vref1"},
+	{"MICBIAS1", NULL, "Vref2"},
+	{"MICBIAS2", NULL, "Vref1"},
+	{"MICBIAS2", NULL, "Vref2"},
+
+	{"CLKDET SYS", NULL, "CLKDET"},
+
+	{"IN1P", NULL, "LDO2"},
+
+	{"BST1 CBJ", NULL, "IN1P"},
+	{"BST1 CBJ", NULL, "CBJ Power"},
+	{"CBJ Power", NULL, "Vref2"},
+
+	{"RECMIX1L", "CBJ Switch", "BST1 CBJ"},
+	{"RECMIX1L", NULL, "RECMIX1L Power"},
+
+	{"ADC1 L", NULL, "RECMIX1L"},
+	{"ADC1 L", NULL, "ADC1 L Power"},
+	{"ADC1 L", NULL, "ADC1 clock"},
+
+	{"DMIC L1", NULL, "DMIC CLK"},
+	{"DMIC L1", NULL, "DMIC1 Power"},
+	{"DMIC R1", NULL, "DMIC CLK"},
+	{"DMIC R1", NULL, "DMIC1 Power"},
+	{"DMIC CLK", NULL, "DMIC ASRC"},
+
+	{"Stereo1 ADC L Mux", "ADC1 L", "ADC1 L"},
+	{"Stereo1 ADC L Mux", "ADC1 R", "ADC1 R"},
+	{"Stereo1 ADC R Mux", "ADC1 L", "ADC1 L"},
+	{"Stereo1 ADC R Mux", "ADC1 R", "ADC1 R"},
+
+	{"Stereo1 ADC L1 Mux", "ADC", "Stereo1 ADC L Mux"},
+	{"Stereo1 ADC L1 Mux", "DAC MIX", "Stereo1 DAC MIXL"},
+	{"Stereo1 ADC L2 Mux", "DMIC", "DMIC L1"},
+	{"Stereo1 ADC L2 Mux", "DAC MIX", "Stereo1 DAC MIXL"},
+
+	{"Stereo1 ADC R1 Mux", "ADC", "Stereo1 ADC R Mux"},
+	{"Stereo1 ADC R1 Mux", "DAC MIX", "Stereo1 DAC MIXR"},
+	{"Stereo1 ADC R2 Mux", "DMIC", "DMIC R1"},
+	{"Stereo1 ADC R2 Mux", "DAC MIX", "Stereo1 DAC MIXR"},
+
+	{"Stereo1 ADC MIXL", "ADC1 Switch", "Stereo1 ADC L1 Mux"},
+	{"Stereo1 ADC MIXL", "ADC2 Switch", "Stereo1 ADC L2 Mux"},
+	{"Stereo1 ADC MIXL", NULL, "ADC Stereo1 Filter"},
+
+	{"Stereo1 ADC MIXR", "ADC1 Switch", "Stereo1 ADC R1 Mux"},
+	{"Stereo1 ADC MIXR", "ADC2 Switch", "Stereo1 ADC R2 Mux"},
+	{"Stereo1 ADC MIXR", NULL, "ADC Stereo1 Filter"},
+
+	{"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXL"},
+	{"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXR"},
+
+	{"IF1 01 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+
+	{"IF1_ADC Mux", "Slot 0", "IF1 01 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 2", "IF1 23 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 4", "IF1 45 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 6", "IF1 67 ADC Swap Mux"},
+	{"IF1_ADC Mux", NULL, "I2S1"},
+	{"ADCDAT Mux", "ADCDAT1", "IF1_ADC Mux"},
+	{"AIF1TX", NULL, "ADCDAT Mux"},
+	{"IF2 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"ADCDAT Mux", "ADCDAT2", "IF2 ADC Swap Mux"},
+	{"AIF2TX", NULL, "ADCDAT Mux"},
+
+	{"IF1 DAC1 L", NULL, "AIF1RX"},
+	{"IF1 DAC1 L", NULL, "I2S1"},
+	{"IF1 DAC1 L", NULL, "DAC Stereo1 Filter"},
+	{"IF1 DAC1 R", NULL, "AIF1RX"},
+	{"IF1 DAC1 R", NULL, "I2S1"},
+	{"IF1 DAC1 R", NULL, "DAC Stereo1 Filter"},
+
+	{"DAC1 MIXL", "Stereo ADC Switch", "Stereo1 ADC MIXL"},
+	{"DAC1 MIXL", "DAC1 Switch", "IF1 DAC1 L"},
+	{"DAC1 MIXR", "Stereo ADC Switch", "Stereo1 ADC MIXR"},
+	{"DAC1 MIXR", "DAC1 Switch", "IF1 DAC1 R"},
+
+	{"Stereo1 DAC MIXL", "DAC L1 Switch", "DAC1 MIXL"},
+	{"Stereo1 DAC MIXL", "DAC R1 Switch", "DAC1 MIXR"},
+
+	{"Stereo1 DAC MIXR", "DAC R1 Switch", "DAC1 MIXR"},
+	{"Stereo1 DAC MIXR", "DAC L1 Switch", "DAC1 MIXL"},
+
+	{"DAC L1 Source", "DAC1", "DAC1 MIXL"},
+	{"DAC L1 Source", "Stereo1 DAC Mixer", "Stereo1 DAC MIXL"},
+	{"DAC R1 Source", "DAC1", "DAC1 MIXR"},
+	{"DAC R1 Source", "Stereo1 DAC Mixer", "Stereo1 DAC MIXR"},
+
+	{"DAC L1", NULL, "DAC L1 Source"},
+	{"DAC R1", NULL, "DAC R1 Source"},
+
+	{"DAC L1", NULL, "DAC 1 Clock"},
+	{"DAC R1", NULL, "DAC 1 Clock"},
+
+	{"HP Amp", NULL, "DAC L1"},
+	{"HP Amp", NULL, "DAC R1"},
+	{"HP Amp", NULL, "HP Amp L"},
+	{"HP Amp", NULL, "HP Amp R"},
+	{"HP Amp", NULL, "Capless"},
+	{"HP Amp", NULL, "Charge Pump"},
+	{"HP Amp", NULL, "CLKDET SYS"},
+	{"HP Amp", NULL, "CBJ Power"},
+	{"HP Amp", NULL, "Vref2"},
+	{"HPOL Playback", "Switch", "HP Amp"},
+	{"HPOR Playback", "Switch", "HP Amp"},
+	{"HPOL", NULL, "HPOL Playback"},
+	{"HPOR", NULL, "HPOR Playback"},
+};
+
+static int rt5668_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+			unsigned int rx_mask, int slots, int slot_width)
+{
+	struct snd_soc_component *component = dai->component;
+	unsigned int val = 0;
+
+	switch (slots) {
+	case 4:
+		val |= RT5668_TDM_TX_CH_4;
+		val |= RT5668_TDM_RX_CH_4;
+		break;
+	case 6:
+		val |= RT5668_TDM_TX_CH_6;
+		val |= RT5668_TDM_RX_CH_6;
+		break;
+	case 8:
+		val |= RT5668_TDM_TX_CH_8;
+		val |= RT5668_TDM_RX_CH_8;
+		break;
+	case 2:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	snd_soc_component_update_bits(component, RT5668_TDM_CTRL,
+		RT5668_TDM_TX_CH_MASK | RT5668_TDM_RX_CH_MASK, val);
+
+	switch (slot_width) {
+	case 16:
+		val = RT5668_TDM_CL_16;
+		break;
+	case 20:
+		val = RT5668_TDM_CL_20;
+		break;
+	case 24:
+		val = RT5668_TDM_CL_24;
+		break;
+	case 32:
+		val = RT5668_TDM_CL_32;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	snd_soc_component_update_bits(component, RT5668_TDM_TCON_CTRL,
+		RT5668_TDM_CL_MASK, val);
+
+	return 0;
+}
+
+
+static int rt5668_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+	unsigned int len_1 = 0, len_2 = 0;
+	int pre_div, frame_size;
+
+	rt5668->lrck[dai->id] = params_rate(params);
+	pre_div = rl6231_get_clk_info(rt5668->sysclk, rt5668->lrck[dai->id]);
+
+	frame_size = snd_soc_params_to_frame_size(params);
+	if (frame_size < 0) {
+		dev_err(component->dev, "Unsupported frame size: %d\n",
+			frame_size);
+		return -EINVAL;
+	}
+
+	dev_dbg(dai->dev, "lrck is %dHz and pre_div is %d for iis %d\n",
+				rt5668->lrck[dai->id], pre_div, dai->id);
+
+	switch (params_width(params)) {
+	case 16:
+		break;
+	case 20:
+		len_1 |= RT5668_I2S1_DL_20;
+		len_2 |= RT5668_I2S2_DL_20;
+		break;
+	case 24:
+		len_1 |= RT5668_I2S1_DL_24;
+		len_2 |= RT5668_I2S2_DL_24;
+		break;
+	case 32:
+		len_1 |= RT5668_I2S1_DL_32;
+		len_2 |= RT5668_I2S2_DL_24;
+		break;
+	case 8:
+		len_1 |= RT5668_I2S2_DL_8;
+		len_2 |= RT5668_I2S2_DL_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case RT5668_AIF1:
+		snd_soc_component_update_bits(component, RT5668_I2S1_SDP,
+			RT5668_I2S1_DL_MASK, len_1);
+		if (rt5668->master[RT5668_AIF1]) {
+			snd_soc_component_update_bits(component,
+				RT5668_ADDA_CLK_1, RT5668_I2S_M_DIV_MASK,
+				pre_div << RT5668_I2S_M_DIV_SFT);
+		}
+		if (params_channels(params) == 1) /* mono mode */
+			snd_soc_component_update_bits(component,
+				RT5668_I2S1_SDP, RT5668_I2S1_MONO_MASK,
+				RT5668_I2S1_MONO_EN);
+		else
+			snd_soc_component_update_bits(component,
+				RT5668_I2S1_SDP, RT5668_I2S1_MONO_MASK,
+				RT5668_I2S1_MONO_DIS);
+		break;
+	case RT5668_AIF2:
+		snd_soc_component_update_bits(component, RT5668_I2S2_SDP,
+			RT5668_I2S2_DL_MASK, len_2);
+		if (rt5668->master[RT5668_AIF2]) {
+			snd_soc_component_update_bits(component,
+				RT5668_I2S_M_CLK_CTRL_1, RT5668_I2S2_M_PD_MASK,
+				pre_div << RT5668_I2S2_M_PD_SFT);
+		}
+		if (params_channels(params) == 1) /* mono mode */
+			snd_soc_component_update_bits(component,
+				RT5668_I2S2_SDP, RT5668_I2S2_MONO_MASK,
+				RT5668_I2S2_MONO_EN);
+		else
+			snd_soc_component_update_bits(component,
+				RT5668_I2S2_SDP, RT5668_I2S2_MONO_MASK,
+				RT5668_I2S2_MONO_DIS);
+		break;
+	default:
+		dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rt5668_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+	unsigned int reg_val = 0, tdm_ctrl = 0;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		rt5668->master[dai->id] = 1;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		rt5668->master[dai->id] = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		reg_val |= RT5668_I2S_BP_INV;
+		tdm_ctrl |= RT5668_TDM_S_BP_INV;
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		if (dai->id == RT5668_AIF1)
+			tdm_ctrl |= RT5668_TDM_S_LP_INV | RT5668_TDM_M_BP_INV;
+		else
+			return -EINVAL;
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		if (dai->id == RT5668_AIF1)
+			tdm_ctrl |= RT5668_TDM_S_BP_INV | RT5668_TDM_S_LP_INV |
+				    RT5668_TDM_M_BP_INV | RT5668_TDM_M_LP_INV;
+		else
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		reg_val |= RT5668_I2S_DF_LEFT;
+		tdm_ctrl |= RT5668_TDM_DF_LEFT;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		reg_val |= RT5668_I2S_DF_PCM_A;
+		tdm_ctrl |= RT5668_TDM_DF_PCM_A;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		reg_val |= RT5668_I2S_DF_PCM_B;
+		tdm_ctrl |= RT5668_TDM_DF_PCM_B;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case RT5668_AIF1:
+		snd_soc_component_update_bits(component, RT5668_I2S1_SDP,
+			RT5668_I2S_DF_MASK, reg_val);
+		snd_soc_component_update_bits(component, RT5668_TDM_TCON_CTRL,
+			RT5668_TDM_MS_MASK | RT5668_TDM_S_BP_MASK |
+			RT5668_TDM_DF_MASK | RT5668_TDM_M_BP_MASK |
+			RT5668_TDM_M_LP_MASK | RT5668_TDM_S_LP_MASK,
+			tdm_ctrl | rt5668->master[dai->id]);
+		break;
+	case RT5668_AIF2:
+		if (rt5668->master[dai->id] == 0)
+			reg_val |= RT5668_I2S2_MS_S;
+		snd_soc_component_update_bits(component, RT5668_I2S2_SDP,
+			RT5668_I2S2_MS_MASK | RT5668_I2S_BP_MASK |
+			RT5668_I2S_DF_MASK, reg_val);
+		break;
+	default:
+		dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int rt5668_set_component_sysclk(struct snd_soc_component *component,
+		int clk_id, int source, unsigned int freq, int dir)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+	unsigned int reg_val = 0, src = 0;
+
+	if (freq == rt5668->sysclk && clk_id == rt5668->sysclk_src)
+		return 0;
+
+	switch (clk_id) {
+	case RT5668_SCLK_S_MCLK:
+		reg_val |= RT5668_SCLK_SRC_MCLK;
+		src = RT5668_CLK_SRC_MCLK;
+		break;
+	case RT5668_SCLK_S_PLL1:
+		reg_val |= RT5668_SCLK_SRC_PLL1;
+		src = RT5668_CLK_SRC_PLL1;
+		break;
+	case RT5668_SCLK_S_PLL2:
+		reg_val |= RT5668_SCLK_SRC_PLL2;
+		src = RT5668_CLK_SRC_PLL2;
+		break;
+	case RT5668_SCLK_S_RCCLK:
+		reg_val |= RT5668_SCLK_SRC_RCCLK;
+		src = RT5668_CLK_SRC_RCCLK;
+		break;
+	default:
+		dev_err(component->dev, "Invalid clock id (%d)\n", clk_id);
+		return -EINVAL;
+	}
+	snd_soc_component_update_bits(component, RT5668_GLB_CLK,
+		RT5668_SCLK_SRC_MASK, reg_val);
+
+	if (rt5668->master[RT5668_AIF2]) {
+		snd_soc_component_update_bits(component,
+			RT5668_I2S_M_CLK_CTRL_1, RT5668_I2S2_SRC_MASK,
+			src << RT5668_I2S2_SRC_SFT);
+	}
+
+	rt5668->sysclk = freq;
+	rt5668->sysclk_src = clk_id;
+
+	dev_dbg(component->dev, "Sysclk is %dHz and clock id is %d\n",
+		freq, clk_id);
+
+	return 0;
+}
+
+static int rt5668_set_component_pll(struct snd_soc_component *component,
+		int pll_id, int source, unsigned int freq_in,
+		unsigned int freq_out)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+	struct rl6231_pll_code pll_code;
+	int ret;
+
+	if (source == rt5668->pll_src && freq_in == rt5668->pll_in &&
+	    freq_out == rt5668->pll_out)
+		return 0;
+
+	if (!freq_in || !freq_out) {
+		dev_dbg(component->dev, "PLL disabled\n");
+
+		rt5668->pll_in = 0;
+		rt5668->pll_out = 0;
+		snd_soc_component_update_bits(component, RT5668_GLB_CLK,
+			RT5668_SCLK_SRC_MASK, RT5668_SCLK_SRC_MCLK);
+		return 0;
+	}
+
+	switch (source) {
+	case RT5668_PLL1_S_MCLK:
+		snd_soc_component_update_bits(component, RT5668_GLB_CLK,
+			RT5668_PLL1_SRC_MASK, RT5668_PLL1_SRC_MCLK);
+		break;
+	case RT5668_PLL1_S_BCLK1:
+		snd_soc_component_update_bits(component, RT5668_GLB_CLK,
+				RT5668_PLL1_SRC_MASK, RT5668_PLL1_SRC_BCLK1);
+		break;
+	default:
+		dev_err(component->dev, "Unknown PLL Source %d\n", source);
+		return -EINVAL;
+	}
+
+	ret = rl6231_pll_calc(freq_in, freq_out, &pll_code);
+	if (ret < 0) {
+		dev_err(component->dev, "Unsupport input clock %d\n", freq_in);
+		return ret;
+	}
+
+	dev_dbg(component->dev, "bypass=%d m=%d n=%d k=%d\n",
+		pll_code.m_bp, (pll_code.m_bp ? 0 : pll_code.m_code),
+		pll_code.n_code, pll_code.k_code);
+
+	snd_soc_component_write(component, RT5668_PLL_CTRL_1,
+		pll_code.n_code << RT5668_PLL_N_SFT | pll_code.k_code);
+	snd_soc_component_write(component, RT5668_PLL_CTRL_2,
+		(pll_code.m_bp ? 0 : pll_code.m_code) << RT5668_PLL_M_SFT |
+		pll_code.m_bp << RT5668_PLL_M_BP_SFT);
+
+	rt5668->pll_in = freq_in;
+	rt5668->pll_out = freq_out;
+	rt5668->pll_src = source;
+
+	return 0;
+}
+
+static int rt5668_set_bclk_ratio(struct snd_soc_dai *dai, unsigned int ratio)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+
+	rt5668->bclk[dai->id] = ratio;
+
+	switch (ratio) {
+	case 64:
+		snd_soc_component_update_bits(component, RT5668_ADDA_CLK_2,
+			RT5668_I2S2_BCLK_MS2_MASK,
+			RT5668_I2S2_BCLK_MS2_64);
+		break;
+	case 32:
+		snd_soc_component_update_bits(component, RT5668_ADDA_CLK_2,
+			RT5668_I2S2_BCLK_MS2_MASK,
+			RT5668_I2S2_BCLK_MS2_32);
+		break;
+	default:
+		dev_err(dai->dev, "Invalid bclk ratio %d\n", ratio);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rt5668_set_bias_level(struct snd_soc_component *component,
+			enum snd_soc_bias_level level)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		regmap_update_bits(rt5668->regmap, RT5668_PWR_ANLG_1,
+			RT5668_PWR_MB | RT5668_PWR_BG,
+			RT5668_PWR_MB | RT5668_PWR_BG);
+		regmap_update_bits(rt5668->regmap, RT5668_PWR_DIG_1,
+			RT5668_DIG_GATE_CTRL | RT5668_PWR_LDO,
+			RT5668_DIG_GATE_CTRL | RT5668_PWR_LDO);
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		regmap_update_bits(rt5668->regmap, RT5668_PWR_ANLG_1,
+			RT5668_PWR_MB, RT5668_PWR_MB);
+		regmap_update_bits(rt5668->regmap, RT5668_PWR_DIG_1,
+			RT5668_DIG_GATE_CTRL, RT5668_DIG_GATE_CTRL);
+		break;
+	case SND_SOC_BIAS_OFF:
+		regmap_update_bits(rt5668->regmap, RT5668_PWR_DIG_1,
+			RT5668_DIG_GATE_CTRL | RT5668_PWR_LDO, 0);
+		regmap_update_bits(rt5668->regmap, RT5668_PWR_ANLG_1,
+			RT5668_PWR_MB | RT5668_PWR_BG, 0);
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int rt5668_probe(struct snd_soc_component *component)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+
+	rt5668->component = component;
+
+	return 0;
+}
+
+static void rt5668_remove(struct snd_soc_component *component)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+
+	rt5668_reset(rt5668->regmap);
+}
+
+#ifdef CONFIG_PM
+static int rt5668_suspend(struct snd_soc_component *component)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt5668->regmap, true);
+	regcache_mark_dirty(rt5668->regmap);
+	return 0;
+}
+
+static int rt5668_resume(struct snd_soc_component *component)
+{
+	struct rt5668_priv *rt5668 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt5668->regmap, false);
+	regcache_sync(rt5668->regmap);
+
+	return 0;
+}
+#else
+#define rt5668_suspend NULL
+#define rt5668_resume NULL
+#endif
+
+#define RT5668_STEREO_RATES SNDRV_PCM_RATE_8000_192000
+#define RT5668_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE | \
+		SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S8)
+
+static const struct snd_soc_dai_ops rt5668_aif1_dai_ops = {
+	.hw_params = rt5668_hw_params,
+	.set_fmt = rt5668_set_dai_fmt,
+	.set_tdm_slot = rt5668_set_tdm_slot,
+};
+
+static const struct snd_soc_dai_ops rt5668_aif2_dai_ops = {
+	.hw_params = rt5668_hw_params,
+	.set_fmt = rt5668_set_dai_fmt,
+	.set_bclk_ratio = rt5668_set_bclk_ratio,
+};
+
+static struct snd_soc_dai_driver rt5668_dai[] = {
+	{
+		.name = "rt5668-aif1",
+		.id = RT5668_AIF1,
+		.playback = {
+			.stream_name = "AIF1 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5668_STEREO_RATES,
+			.formats = RT5668_FORMATS,
+		},
+		.capture = {
+			.stream_name = "AIF1 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5668_STEREO_RATES,
+			.formats = RT5668_FORMATS,
+		},
+		.ops = &rt5668_aif1_dai_ops,
+	},
+	{
+		.name = "rt5668-aif2",
+		.id = RT5668_AIF2,
+		.capture = {
+			.stream_name = "AIF2 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5668_STEREO_RATES,
+			.formats = RT5668_FORMATS,
+		},
+		.ops = &rt5668_aif2_dai_ops,
+	},
+};
+
+static const struct snd_soc_component_driver soc_component_dev_rt5668 = {
+	.probe = rt5668_probe,
+	.remove = rt5668_remove,
+	.suspend = rt5668_suspend,
+	.resume = rt5668_resume,
+	.set_bias_level = rt5668_set_bias_level,
+	.controls = rt5668_snd_controls,
+	.num_controls = ARRAY_SIZE(rt5668_snd_controls),
+	.dapm_widgets = rt5668_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(rt5668_dapm_widgets),
+	.dapm_routes = rt5668_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(rt5668_dapm_routes),
+	.set_sysclk = rt5668_set_component_sysclk,
+	.set_pll = rt5668_set_component_pll,
+	.set_jack = rt5668_set_jack_detect,
+	.use_pmdown_time	= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static const struct regmap_config rt5668_regmap = {
+	.reg_bits = 16,
+	.val_bits = 16,
+	.max_register = RT5668_I2C_MODE,
+	.volatile_reg = rt5668_volatile_register,
+	.readable_reg = rt5668_readable_register,
+	.cache_type = REGCACHE_RBTREE,
+	.reg_defaults = rt5668_reg,
+	.num_reg_defaults = ARRAY_SIZE(rt5668_reg),
+	.use_single_rw = true,
+};
+
+static const struct i2c_device_id rt5668_i2c_id[] = {
+	{"rt5668b", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, rt5668_i2c_id);
+
+static int rt5668_parse_dt(struct rt5668_priv *rt5668, struct device *dev)
+{
+
+	of_property_read_u32(dev->of_node, "realtek,dmic1-data-pin",
+		&rt5668->pdata.dmic1_data_pin);
+	of_property_read_u32(dev->of_node, "realtek,dmic1-clk-pin",
+		&rt5668->pdata.dmic1_clk_pin);
+	of_property_read_u32(dev->of_node, "realtek,jd-src",
+		&rt5668->pdata.jd_src);
+
+	rt5668->pdata.ldo1_en = of_get_named_gpio(dev->of_node,
+		"realtek,ldo1-en-gpios", 0);
+
+	return 0;
+}
+
+static void rt5668_calibrate(struct rt5668_priv *rt5668)
+{
+	int value, count;
+
+	mutex_lock(&rt5668->calibrate_mutex);
+
+	rt5668_reset(rt5668->regmap);
+	regmap_write(rt5668->regmap, RT5668_PWR_ANLG_1, 0xa2bf);
+	usleep_range(15000, 20000);
+	regmap_write(rt5668->regmap, RT5668_PWR_ANLG_1, 0xf2bf);
+	regmap_write(rt5668->regmap, RT5668_MICBIAS_2, 0x0380);
+	regmap_write(rt5668->regmap, RT5668_PWR_DIG_1, 0x8001);
+	regmap_write(rt5668->regmap, RT5668_TEST_MODE_CTRL_1, 0x0000);
+	regmap_write(rt5668->regmap, RT5668_STO1_DAC_MIXER, 0x2080);
+	regmap_write(rt5668->regmap, RT5668_STO1_ADC_MIXER, 0x4040);
+	regmap_write(rt5668->regmap, RT5668_DEPOP_1, 0x0069);
+	regmap_write(rt5668->regmap, RT5668_CHOP_DAC, 0x3000);
+	regmap_write(rt5668->regmap, RT5668_HP_CTRL_2, 0x6000);
+	regmap_write(rt5668->regmap, RT5668_HP_CHARGE_PUMP_1, 0x0f26);
+	regmap_write(rt5668->regmap, RT5668_CALIB_ADC_CTRL, 0x7f05);
+	regmap_write(rt5668->regmap, RT5668_STO1_ADC_MIXER, 0x686c);
+	regmap_write(rt5668->regmap, RT5668_CAL_REC, 0x0d0d);
+	regmap_write(rt5668->regmap, RT5668_HP_CALIB_CTRL_9, 0x000f);
+	regmap_write(rt5668->regmap, RT5668_PWR_DIG_1, 0x8d01);
+	regmap_write(rt5668->regmap, RT5668_HP_CALIB_CTRL_2, 0x0321);
+	regmap_write(rt5668->regmap, RT5668_HP_LOGIC_CTRL_2, 0x0004);
+	regmap_write(rt5668->regmap, RT5668_HP_CALIB_CTRL_1, 0x7c00);
+	regmap_write(rt5668->regmap, RT5668_HP_CALIB_CTRL_3, 0x06a1);
+	regmap_write(rt5668->regmap, RT5668_A_DAC1_MUX, 0x0311);
+	regmap_write(rt5668->regmap, RT5668_RESET_HPF_CTRL, 0x0000);
+	regmap_write(rt5668->regmap, RT5668_ADC_STO1_HP_CTRL_1, 0x3320);
+
+	regmap_write(rt5668->regmap, RT5668_HP_CALIB_CTRL_1, 0xfc00);
+
+	for (count = 0; count < 60; count++) {
+		regmap_read(rt5668->regmap, RT5668_HP_CALIB_STA_1, &value);
+		if (!(value & 0x8000))
+			break;
+
+		usleep_range(10000, 10005);
+	}
+
+	if (count >= 60)
+		pr_err("HP Calibration Failure\n");
+
+	/* restore settings */
+	regmap_write(rt5668->regmap, RT5668_STO1_ADC_MIXER, 0xc0c4);
+	regmap_write(rt5668->regmap, RT5668_PWR_DIG_1, 0x0000);
+
+	mutex_unlock(&rt5668->calibrate_mutex);
+
+}
+
+static int rt5668_i2c_probe(struct i2c_client *i2c,
+		    const struct i2c_device_id *id)
+{
+	struct rt5668_platform_data *pdata = dev_get_platdata(&i2c->dev);
+	struct rt5668_priv *rt5668;
+	int i, ret;
+	unsigned int val;
+
+	rt5668 = devm_kzalloc(&i2c->dev, sizeof(struct rt5668_priv),
+		GFP_KERNEL);
+
+	if (rt5668 == NULL)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, rt5668);
+
+	if (pdata)
+		rt5668->pdata = *pdata;
+	else
+		rt5668_parse_dt(rt5668, &i2c->dev);
+
+	rt5668->regmap = devm_regmap_init_i2c(i2c, &rt5668_regmap);
+	if (IS_ERR(rt5668->regmap)) {
+		ret = PTR_ERR(rt5668->regmap);
+		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(rt5668->supplies); i++)
+		rt5668->supplies[i].supply = rt5668_supply_names[i];
+
+	ret = devm_regulator_bulk_get(&i2c->dev, ARRAY_SIZE(rt5668->supplies),
+				      rt5668->supplies);
+	if (ret != 0) {
+		dev_err(&i2c->dev, "Failed to request supplies: %d\n", ret);
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(rt5668->supplies),
+				    rt5668->supplies);
+	if (ret != 0) {
+		dev_err(&i2c->dev, "Failed to enable supplies: %d\n", ret);
+		return ret;
+	}
+
+	if (gpio_is_valid(rt5668->pdata.ldo1_en)) {
+		if (devm_gpio_request_one(&i2c->dev, rt5668->pdata.ldo1_en,
+					  GPIOF_OUT_INIT_HIGH, "rt5668"))
+			dev_err(&i2c->dev, "Fail gpio_request gpio_ldo\n");
+	}
+
+	/* Sleep for 300 ms miniumum */
+	usleep_range(300000, 350000);
+
+	regmap_write(rt5668->regmap, RT5668_I2C_MODE, 0x1);
+	usleep_range(10000, 15000);
+
+	regmap_read(rt5668->regmap, RT5668_DEVICE_ID, &val);
+	if (val != DEVICE_ID) {
+		pr_err("Device with ID register %x is not rt5668\n", val);
+		return -ENODEV;
+	}
+
+	rt5668_reset(rt5668->regmap);
+
+	rt5668_calibrate(rt5668);
+
+	regmap_write(rt5668->regmap, RT5668_DEPOP_1, 0x0000);
+
+	/* DMIC pin*/
+	if (rt5668->pdata.dmic1_data_pin != RT5668_DMIC1_NULL) {
+		switch (rt5668->pdata.dmic1_data_pin) {
+		case RT5668_DMIC1_DATA_GPIO2: /* share with LRCK2 */
+			regmap_update_bits(rt5668->regmap, RT5668_DMIC_CTRL_1,
+				RT5668_DMIC_1_DP_MASK, RT5668_DMIC_1_DP_GPIO2);
+			regmap_update_bits(rt5668->regmap, RT5668_GPIO_CTRL_1,
+				RT5668_GP2_PIN_MASK, RT5668_GP2_PIN_DMIC_SDA);
+			break;
+
+		case RT5668_DMIC1_DATA_GPIO5: /* share with DACDAT1 */
+			regmap_update_bits(rt5668->regmap, RT5668_DMIC_CTRL_1,
+				RT5668_DMIC_1_DP_MASK, RT5668_DMIC_1_DP_GPIO5);
+			regmap_update_bits(rt5668->regmap, RT5668_GPIO_CTRL_1,
+				RT5668_GP5_PIN_MASK, RT5668_GP5_PIN_DMIC_SDA);
+			break;
+
+		default:
+			dev_dbg(&i2c->dev, "invalid DMIC_DAT pin\n");
+			break;
+		}
+
+		switch (rt5668->pdata.dmic1_clk_pin) {
+		case RT5668_DMIC1_CLK_GPIO1: /* share with IRQ */
+			regmap_update_bits(rt5668->regmap, RT5668_GPIO_CTRL_1,
+				RT5668_GP1_PIN_MASK, RT5668_GP1_PIN_DMIC_CLK);
+			break;
+
+		case RT5668_DMIC1_CLK_GPIO3: /* share with BCLK2 */
+			regmap_update_bits(rt5668->regmap, RT5668_GPIO_CTRL_1,
+				RT5668_GP3_PIN_MASK, RT5668_GP3_PIN_DMIC_CLK);
+			break;
+
+		default:
+			dev_dbg(&i2c->dev, "invalid DMIC_CLK pin\n");
+			break;
+		}
+	}
+
+	regmap_update_bits(rt5668->regmap, RT5668_PWR_ANLG_1,
+			RT5668_LDO1_DVO_MASK | RT5668_HP_DRIVER_MASK,
+			RT5668_LDO1_DVO_14 | RT5668_HP_DRIVER_5X);
+	regmap_write(rt5668->regmap, RT5668_MICBIAS_2, 0x0380);
+	regmap_update_bits(rt5668->regmap, RT5668_GPIO_CTRL_1,
+			RT5668_GP4_PIN_MASK | RT5668_GP5_PIN_MASK,
+			RT5668_GP4_PIN_ADCDAT1 | RT5668_GP5_PIN_DACDAT1);
+	regmap_write(rt5668->regmap, RT5668_TEST_MODE_CTRL_1, 0x0000);
+
+	INIT_DELAYED_WORK(&rt5668->jack_detect_work,
+				rt5668_jack_detect_handler);
+	INIT_DELAYED_WORK(&rt5668->jd_check_work,
+				rt5668_jd_check_handler);
+
+	mutex_init(&rt5668->calibrate_mutex);
+
+	if (i2c->irq) {
+		ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL,
+			rt5668_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+			| IRQF_ONESHOT, "rt5668", rt5668);
+		if (ret)
+			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
+
+	}
+
+	return snd_soc_register_component(&i2c->dev, &soc_component_dev_rt5668,
+			rt5668_dai, ARRAY_SIZE(rt5668_dai));
+}
+
+static int rt5668_i2c_remove(struct i2c_client *i2c)
+{
+	snd_soc_unregister_component(&i2c->dev);
+
+	return 0;
+}
+
+static void rt5668_i2c_shutdown(struct i2c_client *client)
+{
+	struct rt5668_priv *rt5668 = i2c_get_clientdata(client);
+
+	rt5668_reset(rt5668->regmap);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id rt5668_of_match[] = {
+	{.compatible = "realtek,rt5668b"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, rt5668_of_match);
+#endif
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id rt5668_acpi_match[] = {
+	{"10EC5668", 0,},
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, rt5668_acpi_match);
+#endif
+
+static struct i2c_driver rt5668_i2c_driver = {
+	.driver = {
+		.name = "rt5668b",
+		.of_match_table = of_match_ptr(rt5668_of_match),
+		.acpi_match_table = ACPI_PTR(rt5668_acpi_match),
+	},
+	.probe = rt5668_i2c_probe,
+	.remove = rt5668_i2c_remove,
+	.shutdown = rt5668_i2c_shutdown,
+	.id_table = rt5668_i2c_id,
+};
+module_i2c_driver(rt5668_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC RT5668B driver");
+MODULE_AUTHOR("Bard Liao <bardliao@realtek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/rt5668.h b/sound/soc/codecs/rt5668.h
new file mode 100644
index 000000000000..3e7bcfd569ec
--- /dev/null
+++ b/sound/soc/codecs/rt5668.h
@@ -0,0 +1,1318 @@
+/*
+ * rt5668.h  --  RT5668/RT5658 ALSA SoC audio driver
+ *
+ * Copyright 2018 Realtek Microelectronics
+ * Author: Bard Liao <bardliao@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __RT5668_H__
+#define __RT5668_H__
+
+#include <sound/rt5668.h>
+
+#define DEVICE_ID 0x6530
+
+/* Info */
+#define RT5668_RESET				0x0000
+#define RT5668_VERSION_ID			0x00fd
+#define RT5668_VENDOR_ID			0x00fe
+#define RT5668_DEVICE_ID			0x00ff
+/*  I/O - Output */
+#define RT5668_HP_CTRL_1			0x0002
+#define RT5668_HP_CTRL_2			0x0003
+#define RT5668_HPL_GAIN				0x0005
+#define RT5668_HPR_GAIN				0x0006
+
+#define RT5668_I2C_CTRL				0x0008
+
+/* I/O - Input */
+#define RT5668_CBJ_BST_CTRL			0x000b
+#define RT5668_CBJ_CTRL_1			0x0010
+#define RT5668_CBJ_CTRL_2			0x0011
+#define RT5668_CBJ_CTRL_3			0x0012
+#define RT5668_CBJ_CTRL_4			0x0013
+#define RT5668_CBJ_CTRL_5			0x0014
+#define RT5668_CBJ_CTRL_6			0x0015
+#define RT5668_CBJ_CTRL_7			0x0016
+/* I/O - ADC/DAC/DMIC */
+#define RT5668_DAC1_DIG_VOL			0x0019
+#define RT5668_STO1_ADC_DIG_VOL			0x001c
+#define RT5668_STO1_ADC_BOOST			0x001f
+#define RT5668_HP_IMP_GAIN_1			0x0022
+#define RT5668_HP_IMP_GAIN_2			0x0023
+/* Mixer - D-D */
+#define RT5668_SIDETONE_CTRL			0x0024
+#define RT5668_STO1_ADC_MIXER			0x0026
+#define RT5668_AD_DA_MIXER			0x0029
+#define RT5668_STO1_DAC_MIXER			0x002a
+#define RT5668_A_DAC1_MUX			0x002b
+#define RT5668_DIG_INF2_DATA			0x0030
+/* Mixer - ADC */
+#define RT5668_REC_MIXER			0x003c
+#define RT5668_CAL_REC				0x0044
+#define RT5668_ALC_BACK_GAIN			0x0049
+/* Power */
+#define RT5668_PWR_DIG_1			0x0061
+#define RT5668_PWR_DIG_2			0x0062
+#define RT5668_PWR_ANLG_1			0x0063
+#define RT5668_PWR_ANLG_2			0x0064
+#define RT5668_PWR_ANLG_3			0x0065
+#define RT5668_PWR_MIXER			0x0066
+#define RT5668_PWR_VOL				0x0067
+/* Clock Detect */
+#define RT5668_CLK_DET				0x006b
+/* Filter Auto Reset */
+#define RT5668_RESET_LPF_CTRL			0x006c
+#define RT5668_RESET_HPF_CTRL			0x006d
+/* DMIC */
+#define RT5668_DMIC_CTRL_1			0x006e
+/* Format - ADC/DAC */
+#define RT5668_I2S1_SDP				0x0070
+#define RT5668_I2S2_SDP				0x0071
+#define RT5668_ADDA_CLK_1			0x0073
+#define RT5668_ADDA_CLK_2			0x0074
+#define RT5668_I2S1_F_DIV_CTRL_1		0x0075
+#define RT5668_I2S1_F_DIV_CTRL_2		0x0076
+/* Format - TDM Control */
+#define RT5668_TDM_CTRL				0x0079
+#define RT5668_TDM_ADDA_CTRL_1			0x007a
+#define RT5668_TDM_ADDA_CTRL_2			0x007b
+#define RT5668_DATA_SEL_CTRL_1			0x007c
+#define RT5668_TDM_TCON_CTRL			0x007e
+/* Function - Analog */
+#define RT5668_GLB_CLK				0x0080
+#define RT5668_PLL_CTRL_1			0x0081
+#define RT5668_PLL_CTRL_2			0x0082
+#define RT5668_PLL_TRACK_1			0x0083
+#define RT5668_PLL_TRACK_2			0x0084
+#define RT5668_PLL_TRACK_3			0x0085
+#define RT5668_PLL_TRACK_4			0x0086
+#define RT5668_PLL_TRACK_5			0x0087
+#define RT5668_PLL_TRACK_6			0x0088
+#define RT5668_PLL_TRACK_11			0x008c
+#define RT5668_SDW_REF_CLK			0x008d
+#define RT5668_DEPOP_1				0x008e
+#define RT5668_DEPOP_2				0x008f
+#define RT5668_HP_CHARGE_PUMP_1			0x0091
+#define RT5668_HP_CHARGE_PUMP_2			0x0092
+#define RT5668_MICBIAS_1			0x0093
+#define RT5668_MICBIAS_2			0x0094
+#define RT5668_PLL_TRACK_12			0x0098
+#define RT5668_PLL_TRACK_14			0x009a
+#define RT5668_PLL2_CTRL_1			0x009b
+#define RT5668_PLL2_CTRL_2			0x009c
+#define RT5668_PLL2_CTRL_3			0x009d
+#define RT5668_PLL2_CTRL_4			0x009e
+#define RT5668_RC_CLK_CTRL			0x009f
+#define RT5668_I2S_M_CLK_CTRL_1			0x00a0
+#define RT5668_I2S2_F_DIV_CTRL_1		0x00a3
+#define RT5668_I2S2_F_DIV_CTRL_2		0x00a4
+/* Function - Digital */
+#define RT5668_EQ_CTRL_1			0x00ae
+#define RT5668_EQ_CTRL_2			0x00af
+#define RT5668_IRQ_CTRL_1			0x00b6
+#define RT5668_IRQ_CTRL_2			0x00b7
+#define RT5668_IRQ_CTRL_3			0x00b8
+#define RT5668_IRQ_CTRL_4			0x00b9
+#define RT5668_INT_ST_1				0x00be
+#define RT5668_GPIO_CTRL_1			0x00c0
+#define RT5668_GPIO_CTRL_2			0x00c1
+#define RT5668_GPIO_CTRL_3			0x00c2
+#define RT5668_HP_AMP_DET_CTRL_1		0x00d0
+#define RT5668_HP_AMP_DET_CTRL_2		0x00d1
+#define RT5668_MID_HP_AMP_DET			0x00d2
+#define RT5668_LOW_HP_AMP_DET			0x00d3
+#define RT5668_DELAY_BUF_CTRL			0x00d4
+#define RT5668_SV_ZCD_1				0x00d9
+#define RT5668_SV_ZCD_2				0x00da
+#define RT5668_IL_CMD_1				0x00db
+#define RT5668_IL_CMD_2				0x00dc
+#define RT5668_IL_CMD_3				0x00dd
+#define RT5668_IL_CMD_4				0x00de
+#define RT5668_IL_CMD_5				0x00df
+#define RT5668_IL_CMD_6				0x00e0
+#define RT5668_4BTN_IL_CMD_1			0x00e2
+#define RT5668_4BTN_IL_CMD_2			0x00e3
+#define RT5668_4BTN_IL_CMD_3			0x00e4
+#define RT5668_4BTN_IL_CMD_4			0x00e5
+#define RT5668_4BTN_IL_CMD_5			0x00e6
+#define RT5668_4BTN_IL_CMD_6			0x00e7
+#define RT5668_4BTN_IL_CMD_7			0x00e8
+
+#define RT5668_ADC_STO1_HP_CTRL_1		0x00ea
+#define RT5668_ADC_STO1_HP_CTRL_2		0x00eb
+#define RT5668_AJD1_CTRL			0x00f0
+#define RT5668_JD1_THD				0x00f1
+#define RT5668_JD2_THD				0x00f2
+#define RT5668_JD_CTRL_1			0x00f6
+/* General Control */
+#define RT5668_DUMMY_1				0x00fa
+#define RT5668_DUMMY_2				0x00fb
+#define RT5668_DUMMY_3				0x00fc
+
+#define RT5668_DAC_ADC_DIG_VOL1			0x0100
+#define RT5668_BIAS_CUR_CTRL_2			0x010b
+#define RT5668_BIAS_CUR_CTRL_3			0x010c
+#define RT5668_BIAS_CUR_CTRL_4			0x010d
+#define RT5668_BIAS_CUR_CTRL_5			0x010e
+#define RT5668_BIAS_CUR_CTRL_6			0x010f
+#define RT5668_BIAS_CUR_CTRL_7			0x0110
+#define RT5668_BIAS_CUR_CTRL_8			0x0111
+#define RT5668_BIAS_CUR_CTRL_9			0x0112
+#define RT5668_BIAS_CUR_CTRL_10			0x0113
+#define RT5668_VREF_REC_OP_FB_CAP_CTRL		0x0117
+#define RT5668_CHARGE_PUMP_1			0x0125
+#define RT5668_DIG_IN_CTRL_1			0x0132
+#define RT5668_PAD_DRIVING_CTRL			0x0136
+#define RT5668_SOFT_RAMP_DEPOP			0x0138
+#define RT5668_CHOP_DAC				0x013a
+#define RT5668_CHOP_ADC				0x013b
+#define RT5668_CALIB_ADC_CTRL			0x013c
+#define RT5668_VOL_TEST				0x013f
+#define RT5668_SPKVDD_DET_STA			0x0142
+#define RT5668_TEST_MODE_CTRL_1			0x0145
+#define RT5668_TEST_MODE_CTRL_2			0x0146
+#define RT5668_TEST_MODE_CTRL_3			0x0147
+#define RT5668_TEST_MODE_CTRL_4			0x0148
+#define RT5668_TEST_MODE_CTRL_5			0x0149
+#define RT5668_PLL1_INTERNAL			0x0150
+#define RT5668_PLL2_INTERNAL			0x0151
+#define RT5668_STO_NG2_CTRL_1			0x0160
+#define RT5668_STO_NG2_CTRL_2			0x0161
+#define RT5668_STO_NG2_CTRL_3			0x0162
+#define RT5668_STO_NG2_CTRL_4			0x0163
+#define RT5668_STO_NG2_CTRL_5			0x0164
+#define RT5668_STO_NG2_CTRL_6			0x0165
+#define RT5668_STO_NG2_CTRL_7			0x0166
+#define RT5668_STO_NG2_CTRL_8			0x0167
+#define RT5668_STO_NG2_CTRL_9			0x0168
+#define RT5668_STO_NG2_CTRL_10			0x0169
+#define RT5668_STO1_DAC_SIL_DET			0x0190
+#define RT5668_SIL_PSV_CTRL1			0x0194
+#define RT5668_SIL_PSV_CTRL2			0x0195
+#define RT5668_SIL_PSV_CTRL3			0x0197
+#define RT5668_SIL_PSV_CTRL4			0x0198
+#define RT5668_SIL_PSV_CTRL5			0x0199
+#define RT5668_HP_IMP_SENS_CTRL_01		0x01af
+#define RT5668_HP_IMP_SENS_CTRL_02		0x01b0
+#define RT5668_HP_IMP_SENS_CTRL_03		0x01b1
+#define RT5668_HP_IMP_SENS_CTRL_04		0x01b2
+#define RT5668_HP_IMP_SENS_CTRL_05		0x01b3
+#define RT5668_HP_IMP_SENS_CTRL_06		0x01b4
+#define RT5668_HP_IMP_SENS_CTRL_07		0x01b5
+#define RT5668_HP_IMP_SENS_CTRL_08		0x01b6
+#define RT5668_HP_IMP_SENS_CTRL_09		0x01b7
+#define RT5668_HP_IMP_SENS_CTRL_10		0x01b8
+#define RT5668_HP_IMP_SENS_CTRL_11		0x01b9
+#define RT5668_HP_IMP_SENS_CTRL_12		0x01ba
+#define RT5668_HP_IMP_SENS_CTRL_13		0x01bb
+#define RT5668_HP_IMP_SENS_CTRL_14		0x01bc
+#define RT5668_HP_IMP_SENS_CTRL_15		0x01bd
+#define RT5668_HP_IMP_SENS_CTRL_16		0x01be
+#define RT5668_HP_IMP_SENS_CTRL_17		0x01bf
+#define RT5668_HP_IMP_SENS_CTRL_18		0x01c0
+#define RT5668_HP_IMP_SENS_CTRL_19		0x01c1
+#define RT5668_HP_IMP_SENS_CTRL_20		0x01c2
+#define RT5668_HP_IMP_SENS_CTRL_21		0x01c3
+#define RT5668_HP_IMP_SENS_CTRL_22		0x01c4
+#define RT5668_HP_IMP_SENS_CTRL_23		0x01c5
+#define RT5668_HP_IMP_SENS_CTRL_24		0x01c6
+#define RT5668_HP_IMP_SENS_CTRL_25		0x01c7
+#define RT5668_HP_IMP_SENS_CTRL_26		0x01c8
+#define RT5668_HP_IMP_SENS_CTRL_27		0x01c9
+#define RT5668_HP_IMP_SENS_CTRL_28		0x01ca
+#define RT5668_HP_IMP_SENS_CTRL_29		0x01cb
+#define RT5668_HP_IMP_SENS_CTRL_30		0x01cc
+#define RT5668_HP_IMP_SENS_CTRL_31		0x01cd
+#define RT5668_HP_IMP_SENS_CTRL_32		0x01ce
+#define RT5668_HP_IMP_SENS_CTRL_33		0x01cf
+#define RT5668_HP_IMP_SENS_CTRL_34		0x01d0
+#define RT5668_HP_IMP_SENS_CTRL_35		0x01d1
+#define RT5668_HP_IMP_SENS_CTRL_36		0x01d2
+#define RT5668_HP_IMP_SENS_CTRL_37		0x01d3
+#define RT5668_HP_IMP_SENS_CTRL_38		0x01d4
+#define RT5668_HP_IMP_SENS_CTRL_39		0x01d5
+#define RT5668_HP_IMP_SENS_CTRL_40		0x01d6
+#define RT5668_HP_IMP_SENS_CTRL_41		0x01d7
+#define RT5668_HP_IMP_SENS_CTRL_42		0x01d8
+#define RT5668_HP_IMP_SENS_CTRL_43		0x01d9
+#define RT5668_HP_LOGIC_CTRL_1			0x01da
+#define RT5668_HP_LOGIC_CTRL_2			0x01db
+#define RT5668_HP_LOGIC_CTRL_3			0x01dc
+#define RT5668_HP_CALIB_CTRL_1			0x01de
+#define RT5668_HP_CALIB_CTRL_2			0x01df
+#define RT5668_HP_CALIB_CTRL_3			0x01e0
+#define RT5668_HP_CALIB_CTRL_4			0x01e1
+#define RT5668_HP_CALIB_CTRL_5			0x01e2
+#define RT5668_HP_CALIB_CTRL_6			0x01e3
+#define RT5668_HP_CALIB_CTRL_7			0x01e4
+#define RT5668_HP_CALIB_CTRL_9			0x01e6
+#define RT5668_HP_CALIB_CTRL_10			0x01e7
+#define RT5668_HP_CALIB_CTRL_11			0x01e8
+#define RT5668_HP_CALIB_STA_1			0x01ea
+#define RT5668_HP_CALIB_STA_2			0x01eb
+#define RT5668_HP_CALIB_STA_3			0x01ec
+#define RT5668_HP_CALIB_STA_4			0x01ed
+#define RT5668_HP_CALIB_STA_5			0x01ee
+#define RT5668_HP_CALIB_STA_6			0x01ef
+#define RT5668_HP_CALIB_STA_7			0x01f0
+#define RT5668_HP_CALIB_STA_8			0x01f1
+#define RT5668_HP_CALIB_STA_9			0x01f2
+#define RT5668_HP_CALIB_STA_10			0x01f3
+#define RT5668_HP_CALIB_STA_11			0x01f4
+#define RT5668_SAR_IL_CMD_1			0x0210
+#define RT5668_SAR_IL_CMD_2			0x0211
+#define RT5668_SAR_IL_CMD_3			0x0212
+#define RT5668_SAR_IL_CMD_4			0x0213
+#define RT5668_SAR_IL_CMD_5			0x0214
+#define RT5668_SAR_IL_CMD_6			0x0215
+#define RT5668_SAR_IL_CMD_7			0x0216
+#define RT5668_SAR_IL_CMD_8			0x0217
+#define RT5668_SAR_IL_CMD_9			0x0218
+#define RT5668_SAR_IL_CMD_10			0x0219
+#define RT5668_SAR_IL_CMD_11			0x021a
+#define RT5668_SAR_IL_CMD_12			0x021b
+#define RT5668_SAR_IL_CMD_13			0x021c
+#define RT5668_EFUSE_CTRL_1			0x0250
+#define RT5668_EFUSE_CTRL_2			0x0251
+#define RT5668_EFUSE_CTRL_3			0x0252
+#define RT5668_EFUSE_CTRL_4			0x0253
+#define RT5668_EFUSE_CTRL_5			0x0254
+#define RT5668_EFUSE_CTRL_6			0x0255
+#define RT5668_EFUSE_CTRL_7			0x0256
+#define RT5668_EFUSE_CTRL_8			0x0257
+#define RT5668_EFUSE_CTRL_9			0x0258
+#define RT5668_EFUSE_CTRL_10			0x0259
+#define RT5668_EFUSE_CTRL_11			0x025a
+#define RT5668_JD_TOP_VC_VTRL			0x0270
+#define RT5668_DRC1_CTRL_0			0x02ff
+#define RT5668_DRC1_CTRL_1			0x0300
+#define RT5668_DRC1_CTRL_2			0x0301
+#define RT5668_DRC1_CTRL_3			0x0302
+#define RT5668_DRC1_CTRL_4			0x0303
+#define RT5668_DRC1_CTRL_5			0x0304
+#define RT5668_DRC1_CTRL_6			0x0305
+#define RT5668_DRC1_HARD_LMT_CTRL_1		0x0306
+#define RT5668_DRC1_HARD_LMT_CTRL_2		0x0307
+#define RT5668_DRC1_PRIV_1			0x0310
+#define RT5668_DRC1_PRIV_2			0x0311
+#define RT5668_DRC1_PRIV_3			0x0312
+#define RT5668_DRC1_PRIV_4			0x0313
+#define RT5668_DRC1_PRIV_5			0x0314
+#define RT5668_DRC1_PRIV_6			0x0315
+#define RT5668_DRC1_PRIV_7			0x0316
+#define RT5668_DRC1_PRIV_8			0x0317
+#define RT5668_EQ_AUTO_RCV_CTRL1		0x03c0
+#define RT5668_EQ_AUTO_RCV_CTRL2		0x03c1
+#define RT5668_EQ_AUTO_RCV_CTRL3		0x03c2
+#define RT5668_EQ_AUTO_RCV_CTRL4		0x03c3
+#define RT5668_EQ_AUTO_RCV_CTRL5		0x03c4
+#define RT5668_EQ_AUTO_RCV_CTRL6		0x03c5
+#define RT5668_EQ_AUTO_RCV_CTRL7		0x03c6
+#define RT5668_EQ_AUTO_RCV_CTRL8		0x03c7
+#define RT5668_EQ_AUTO_RCV_CTRL9		0x03c8
+#define RT5668_EQ_AUTO_RCV_CTRL10		0x03c9
+#define RT5668_EQ_AUTO_RCV_CTRL11		0x03ca
+#define RT5668_EQ_AUTO_RCV_CTRL12		0x03cb
+#define RT5668_EQ_AUTO_RCV_CTRL13		0x03cc
+#define RT5668_ADC_L_EQ_LPF1_A1			0x03d0
+#define RT5668_R_EQ_LPF1_A1			0x03d1
+#define RT5668_L_EQ_LPF1_H0			0x03d2
+#define RT5668_R_EQ_LPF1_H0			0x03d3
+#define RT5668_L_EQ_BPF1_A1			0x03d4
+#define RT5668_R_EQ_BPF1_A1			0x03d5
+#define RT5668_L_EQ_BPF1_A2			0x03d6
+#define RT5668_R_EQ_BPF1_A2			0x03d7
+#define RT5668_L_EQ_BPF1_H0			0x03d8
+#define RT5668_R_EQ_BPF1_H0			0x03d9
+#define RT5668_L_EQ_BPF2_A1			0x03da
+#define RT5668_R_EQ_BPF2_A1			0x03db
+#define RT5668_L_EQ_BPF2_A2			0x03dc
+#define RT5668_R_EQ_BPF2_A2			0x03dd
+#define RT5668_L_EQ_BPF2_H0			0x03de
+#define RT5668_R_EQ_BPF2_H0			0x03df
+#define RT5668_L_EQ_BPF3_A1			0x03e0
+#define RT5668_R_EQ_BPF3_A1			0x03e1
+#define RT5668_L_EQ_BPF3_A2			0x03e2
+#define RT5668_R_EQ_BPF3_A2			0x03e3
+#define RT5668_L_EQ_BPF3_H0			0x03e4
+#define RT5668_R_EQ_BPF3_H0			0x03e5
+#define RT5668_L_EQ_BPF4_A1			0x03e6
+#define RT5668_R_EQ_BPF4_A1			0x03e7
+#define RT5668_L_EQ_BPF4_A2			0x03e8
+#define RT5668_R_EQ_BPF4_A2			0x03e9
+#define RT5668_L_EQ_BPF4_H0			0x03ea
+#define RT5668_R_EQ_BPF4_H0			0x03eb
+#define RT5668_L_EQ_HPF1_A1			0x03ec
+#define RT5668_R_EQ_HPF1_A1			0x03ed
+#define RT5668_L_EQ_HPF1_H0			0x03ee
+#define RT5668_R_EQ_HPF1_H0			0x03ef
+#define RT5668_L_EQ_PRE_VOL			0x03f0
+#define RT5668_R_EQ_PRE_VOL			0x03f1
+#define RT5668_L_EQ_POST_VOL			0x03f2
+#define RT5668_R_EQ_POST_VOL			0x03f3
+#define RT5668_I2C_MODE				0xffff
+
+
+/* global definition */
+#define RT5668_L_MUTE				(0x1 << 15)
+#define RT5668_L_MUTE_SFT			15
+#define RT5668_VOL_L_MUTE			(0x1 << 14)
+#define RT5668_VOL_L_SFT			14
+#define RT5668_R_MUTE				(0x1 << 7)
+#define RT5668_R_MUTE_SFT			7
+#define RT5668_VOL_R_MUTE			(0x1 << 6)
+#define RT5668_VOL_R_SFT			6
+#define RT5668_L_VOL_MASK			(0x3f << 8)
+#define RT5668_L_VOL_SFT			8
+#define RT5668_R_VOL_MASK			(0x3f)
+#define RT5668_R_VOL_SFT			0
+
+/*Headphone Amp L/R Analog Gain and Digital NG2 Gain Control (0x0005 0x0006)*/
+#define RT5668_G_HP				(0xf << 8)
+#define RT5668_G_HP_SFT				8
+#define RT5668_G_STO_DA_DMIX			(0xf)
+#define RT5668_G_STO_DA_SFT			0
+
+/* CBJ Control (0x000b) */
+#define RT5668_BST_CBJ_MASK			(0xf << 8)
+#define RT5668_BST_CBJ_SFT			8
+
+/* Embeeded Jack and Type Detection Control 1 (0x0010) */
+#define RT5668_EMB_JD_EN			(0x1 << 15)
+#define RT5668_EMB_JD_EN_SFT			15
+#define RT5668_EMB_JD_RST			(0x1 << 14)
+#define RT5668_JD_MODE				(0x1 << 13)
+#define RT5668_JD_MODE_SFT			13
+#define RT5668_DET_TYPE				(0x1 << 12)
+#define RT5668_DET_TYPE_SFT			12
+#define RT5668_POLA_EXT_JD_MASK			(0x1 << 11)
+#define RT5668_POLA_EXT_JD_LOW			(0x1 << 11)
+#define RT5668_POLA_EXT_JD_HIGH			(0x0 << 11)
+#define RT5668_EXT_JD_DIG			(0x1 << 9)
+#define RT5668_POL_FAST_OFF_MASK		(0x1 << 8)
+#define RT5668_POL_FAST_OFF_HIGH		(0x1 << 8)
+#define RT5668_POL_FAST_OFF_LOW			(0x0 << 8)
+#define RT5668_FAST_OFF_MASK			(0x1 << 7)
+#define RT5668_FAST_OFF_EN			(0x1 << 7)
+#define RT5668_FAST_OFF_DIS			(0x0 << 7)
+#define RT5668_VREF_POW_MASK			(0x1 << 6)
+#define RT5668_VREF_POW_FSM			(0x0 << 6)
+#define RT5668_VREF_POW_REG			(0x1 << 6)
+#define RT5668_MB1_PATH_MASK			(0x1 << 5)
+#define RT5668_CTRL_MB1_REG			(0x1 << 5)
+#define RT5668_CTRL_MB1_FSM			(0x0 << 5)
+#define RT5668_MB2_PATH_MASK			(0x1 << 4)
+#define RT5668_CTRL_MB2_REG			(0x1 << 4)
+#define RT5668_CTRL_MB2_FSM			(0x0 << 4)
+#define RT5668_TRIG_JD_MASK			(0x1 << 3)
+#define RT5668_TRIG_JD_HIGH			(0x1 << 3)
+#define RT5668_TRIG_JD_LOW			(0x0 << 3)
+#define RT5668_MIC_CAP_MASK			(0x1 << 1)
+#define RT5668_MIC_CAP_HS			(0x1 << 1)
+#define RT5668_MIC_CAP_HP			(0x0 << 1)
+#define RT5668_MIC_CAP_SRC_MASK			(0x1)
+#define RT5668_MIC_CAP_SRC_REG			(0x1)
+#define RT5668_MIC_CAP_SRC_ANA			(0x0)
+
+/* Embeeded Jack and Type Detection Control 2 (0x0011) */
+#define RT5668_EXT_JD_SRC			(0x7 << 4)
+#define RT5668_EXT_JD_SRC_SFT			4
+#define RT5668_EXT_JD_SRC_GPIO_JD1		(0x0 << 4)
+#define RT5668_EXT_JD_SRC_GPIO_JD2		(0x1 << 4)
+#define RT5668_EXT_JD_SRC_JDH			(0x2 << 4)
+#define RT5668_EXT_JD_SRC_JDL			(0x3 << 4)
+#define RT5668_EXT_JD_SRC_MANUAL		(0x4 << 4)
+#define RT5668_JACK_TYPE_MASK			(0x3)
+
+/* Combo Jack and Type Detection Control 3 (0x0012) */
+#define RT5668_CBJ_IN_BUF_EN			(0x1 << 7)
+
+/* Combo Jack and Type Detection Control 4 (0x0013) */
+#define RT5668_SEL_SHT_MID_TON_MASK		(0x3 << 12)
+#define RT5668_SEL_SHT_MID_TON_2		(0x0 << 12)
+#define RT5668_SEL_SHT_MID_TON_3		(0x1 << 12)
+#define RT5668_CBJ_JD_TEST_MASK			(0x1 << 6)
+#define RT5668_CBJ_JD_TEST_NORM			(0x0 << 6)
+#define RT5668_CBJ_JD_TEST_MODE			(0x1 << 6)
+
+/* DAC1 Digital Volume (0x0019) */
+#define RT5668_DAC_L1_VOL_MASK			(0xff << 8)
+#define RT5668_DAC_L1_VOL_SFT			8
+#define RT5668_DAC_R1_VOL_MASK			(0xff)
+#define RT5668_DAC_R1_VOL_SFT			0
+
+/* ADC Digital Volume Control (0x001c) */
+#define RT5668_ADC_L_VOL_MASK			(0x7f << 8)
+#define RT5668_ADC_L_VOL_SFT			8
+#define RT5668_ADC_R_VOL_MASK			(0x7f)
+#define RT5668_ADC_R_VOL_SFT			0
+
+/* Stereo1 ADC Boost Gain Control (0x001f) */
+#define RT5668_STO1_ADC_L_BST_MASK		(0x3 << 14)
+#define RT5668_STO1_ADC_L_BST_SFT		14
+#define RT5668_STO1_ADC_R_BST_MASK		(0x3 << 12)
+#define RT5668_STO1_ADC_R_BST_SFT		12
+
+/* Sidetone Control (0x0024) */
+#define RT5668_ST_SRC_SEL			(0x1 << 8)
+#define RT5668_ST_SRC_SFT			8
+#define RT5668_ST_EN_MASK			(0x1 << 6)
+#define RT5668_ST_DIS				(0x0 << 6)
+#define RT5668_ST_EN				(0x1 << 6)
+#define RT5668_ST_EN_SFT			6
+
+/* Stereo1 ADC Mixer Control (0x0026) */
+#define RT5668_M_STO1_ADC_L1			(0x1 << 15)
+#define RT5668_M_STO1_ADC_L1_SFT		15
+#define RT5668_M_STO1_ADC_L2			(0x1 << 14)
+#define RT5668_M_STO1_ADC_L2_SFT		14
+#define RT5668_STO1_ADC1L_SRC_MASK		(0x1 << 13)
+#define RT5668_STO1_ADC1L_SRC_SFT		13
+#define RT5668_STO1_ADC1_SRC_ADC		(0x1 << 13)
+#define RT5668_STO1_ADC1_SRC_DACMIX		(0x0 << 13)
+#define RT5668_STO1_ADC2L_SRC_MASK		(0x1 << 12)
+#define RT5668_STO1_ADC2L_SRC_SFT		12
+#define RT5668_STO1_ADCL_SRC_MASK		(0x3 << 10)
+#define RT5668_STO1_ADCL_SRC_SFT		10
+#define RT5668_STO1_DD_L_SRC_MASK		(0x1 << 9)
+#define RT5668_STO1_DD_L_SRC_SFT		9
+#define RT5668_STO1_DMIC_SRC_MASK		(0x1 << 8)
+#define RT5668_STO1_DMIC_SRC_SFT		8
+#define RT5668_STO1_DMIC_SRC_DMIC2		(0x1 << 8)
+#define RT5668_STO1_DMIC_SRC_DMIC1		(0x0 << 8)
+#define RT5668_M_STO1_ADC_R1			(0x1 << 7)
+#define RT5668_M_STO1_ADC_R1_SFT		7
+#define RT5668_M_STO1_ADC_R2			(0x1 << 6)
+#define RT5668_M_STO1_ADC_R2_SFT		6
+#define RT5668_STO1_ADC1R_SRC_MASK		(0x1 << 5)
+#define RT5668_STO1_ADC1R_SRC_SFT		5
+#define RT5668_STO1_ADC2R_SRC_MASK		(0x1 << 4)
+#define RT5668_STO1_ADC2R_SRC_SFT		4
+#define RT5668_STO1_ADCR_SRC_MASK		(0x3 << 2)
+#define RT5668_STO1_ADCR_SRC_SFT		2
+
+/* ADC Mixer to DAC Mixer Control (0x0029) */
+#define RT5668_M_ADCMIX_L			(0x1 << 15)
+#define RT5668_M_ADCMIX_L_SFT			15
+#define RT5668_M_DAC1_L				(0x1 << 14)
+#define RT5668_M_DAC1_L_SFT			14
+#define RT5668_DAC1_R_SEL_MASK			(0x1 << 10)
+#define RT5668_DAC1_R_SEL_SFT			10
+#define RT5668_DAC1_L_SEL_MASK			(0x1 << 8)
+#define RT5668_DAC1_L_SEL_SFT			8
+#define RT5668_M_ADCMIX_R			(0x1 << 7)
+#define RT5668_M_ADCMIX_R_SFT			7
+#define RT5668_M_DAC1_R				(0x1 << 6)
+#define RT5668_M_DAC1_R_SFT			6
+
+/* Stereo1 DAC Mixer Control (0x002a) */
+#define RT5668_M_DAC_L1_STO_L			(0x1 << 15)
+#define RT5668_M_DAC_L1_STO_L_SFT		15
+#define RT5668_G_DAC_L1_STO_L_MASK		(0x1 << 14)
+#define RT5668_G_DAC_L1_STO_L_SFT		14
+#define RT5668_M_DAC_R1_STO_L			(0x1 << 13)
+#define RT5668_M_DAC_R1_STO_L_SFT		13
+#define RT5668_G_DAC_R1_STO_L_MASK		(0x1 << 12)
+#define RT5668_G_DAC_R1_STO_L_SFT		12
+#define RT5668_M_DAC_L1_STO_R			(0x1 << 7)
+#define RT5668_M_DAC_L1_STO_R_SFT		7
+#define RT5668_G_DAC_L1_STO_R_MASK		(0x1 << 6)
+#define RT5668_G_DAC_L1_STO_R_SFT		6
+#define RT5668_M_DAC_R1_STO_R			(0x1 << 5)
+#define RT5668_M_DAC_R1_STO_R_SFT		5
+#define RT5668_G_DAC_R1_STO_R_MASK		(0x1 << 4)
+#define RT5668_G_DAC_R1_STO_R_SFT		4
+
+/* Analog DAC1 Input Source Control (0x002b) */
+#define RT5668_M_ST_STO_L			(0x1 << 9)
+#define RT5668_M_ST_STO_L_SFT			9
+#define RT5668_M_ST_STO_R			(0x1 << 8)
+#define RT5668_M_ST_STO_R_SFT			8
+#define RT5668_DAC_L1_SRC_MASK			(0x3 << 4)
+#define RT5668_A_DACL1_SFT			4
+#define RT5668_DAC_R1_SRC_MASK			(0x3)
+#define RT5668_A_DACR1_SFT			0
+
+/* Digital Interface Data Control (0x0030) */
+#define RT5668_IF2_ADC_SEL_MASK			(0x3 << 0)
+#define RT5668_IF2_ADC_SEL_SFT			0
+
+/* REC Left Mixer Control 2 (0x003c) */
+#define RT5668_G_CBJ_RM1_L			(0x7 << 10)
+#define RT5668_G_CBJ_RM1_L_SFT			10
+#define RT5668_M_CBJ_RM1_L			(0x1 << 7)
+#define RT5668_M_CBJ_RM1_L_SFT			7
+
+/* Power Management for Digital 1 (0x0061) */
+#define RT5668_PWR_I2S1				(0x1 << 15)
+#define RT5668_PWR_I2S1_BIT			15
+#define RT5668_PWR_I2S2				(0x1 << 14)
+#define RT5668_PWR_I2S2_BIT			14
+#define RT5668_PWR_DAC_L1			(0x1 << 11)
+#define RT5668_PWR_DAC_L1_BIT			11
+#define RT5668_PWR_DAC_R1			(0x1 << 10)
+#define RT5668_PWR_DAC_R1_BIT			10
+#define RT5668_PWR_LDO				(0x1 << 8)
+#define RT5668_PWR_LDO_BIT			8
+#define RT5668_PWR_ADC_L1			(0x1 << 4)
+#define RT5668_PWR_ADC_L1_BIT			4
+#define RT5668_PWR_ADC_R1			(0x1 << 3)
+#define RT5668_PWR_ADC_R1_BIT			3
+#define RT5668_DIG_GATE_CTRL			(0x1 << 0)
+#define RT5668_DIG_GATE_CTRL_SFT		0
+
+
+/* Power Management for Digital 2 (0x0062) */
+#define RT5668_PWR_ADC_S1F			(0x1 << 15)
+#define RT5668_PWR_ADC_S1F_BIT			15
+#define RT5668_PWR_DAC_S1F			(0x1 << 10)
+#define RT5668_PWR_DAC_S1F_BIT			10
+
+/* Power Management for Analog 1 (0x0063) */
+#define RT5668_PWR_VREF1			(0x1 << 15)
+#define RT5668_PWR_VREF1_BIT			15
+#define RT5668_PWR_FV1				(0x1 << 14)
+#define RT5668_PWR_FV1_BIT			14
+#define RT5668_PWR_VREF2			(0x1 << 13)
+#define RT5668_PWR_VREF2_BIT			13
+#define RT5668_PWR_FV2				(0x1 << 12)
+#define RT5668_PWR_FV2_BIT			12
+#define RT5668_LDO1_DBG_MASK			(0x3 << 10)
+#define RT5668_PWR_MB				(0x1 << 9)
+#define RT5668_PWR_MB_BIT			9
+#define RT5668_PWR_BG				(0x1 << 7)
+#define RT5668_PWR_BG_BIT			7
+#define RT5668_LDO1_BYPASS_MASK			(0x1 << 6)
+#define RT5668_LDO1_BYPASS			(0x1 << 6)
+#define RT5668_LDO1_NOT_BYPASS			(0x0 << 6)
+#define RT5668_PWR_MA_BIT			6
+#define RT5668_LDO1_DVO_MASK			(0x3 << 4)
+#define RT5668_LDO1_DVO_09			(0x0 << 4)
+#define RT5668_LDO1_DVO_10			(0x1 << 4)
+#define RT5668_LDO1_DVO_12			(0x2 << 4)
+#define RT5668_LDO1_DVO_14			(0x3 << 4)
+#define RT5668_HP_DRIVER_MASK			(0x3 << 2)
+#define RT5668_HP_DRIVER_1X			(0x0 << 2)
+#define RT5668_HP_DRIVER_3X			(0x1 << 2)
+#define RT5668_HP_DRIVER_5X			(0x3 << 2)
+#define RT5668_PWR_HA_L				(0x1 << 1)
+#define RT5668_PWR_HA_L_BIT			1
+#define RT5668_PWR_HA_R				(0x1 << 0)
+#define RT5668_PWR_HA_R_BIT			0
+
+/* Power Management for Analog 2 (0x0064) */
+#define RT5668_PWR_MB1				(0x1 << 11)
+#define RT5668_PWR_MB1_PWR_DOWN			(0x0 << 11)
+#define RT5668_PWR_MB1_BIT			11
+#define RT5668_PWR_MB2				(0x1 << 10)
+#define RT5668_PWR_MB2_PWR_DOWN			(0x0 << 10)
+#define RT5668_PWR_MB2_BIT			10
+#define RT5668_PWR_JDH				(0x1 << 3)
+#define RT5668_PWR_JDH_BIT			3
+#define RT5668_PWR_JDL				(0x1 << 2)
+#define RT5668_PWR_JDL_BIT			2
+#define RT5668_PWR_RM1_L			(0x1 << 1)
+#define RT5668_PWR_RM1_L_BIT			1
+
+/* Power Management for Analog 3 (0x0065) */
+#define RT5668_PWR_CBJ				(0x1 << 9)
+#define RT5668_PWR_CBJ_BIT			9
+#define RT5668_PWR_PLL				(0x1 << 6)
+#define RT5668_PWR_PLL_BIT			6
+#define RT5668_PWR_PLL2B			(0x1 << 5)
+#define RT5668_PWR_PLL2B_BIT			5
+#define RT5668_PWR_PLL2F			(0x1 << 4)
+#define RT5668_PWR_PLL2F_BIT			4
+#define RT5668_PWR_LDO2				(0x1 << 2)
+#define RT5668_PWR_LDO2_BIT			2
+#define RT5668_PWR_DET_SPKVDD			(0x1 << 1)
+#define RT5668_PWR_DET_SPKVDD_BIT		1
+
+/* Power Management for Mixer (0x0066) */
+#define RT5668_PWR_STO1_DAC_L			(0x1 << 5)
+#define RT5668_PWR_STO1_DAC_L_BIT		5
+#define RT5668_PWR_STO1_DAC_R			(0x1 << 4)
+#define RT5668_PWR_STO1_DAC_R_BIT		4
+
+/* MCLK and System Clock Detection Control (0x006b) */
+#define RT5668_SYS_CLK_DET			(0x1 << 15)
+#define RT5668_SYS_CLK_DET_SFT			15
+#define RT5668_PLL1_CLK_DET			(0x1 << 14)
+#define RT5668_PLL1_CLK_DET_SFT			14
+#define RT5668_PLL2_CLK_DET			(0x1 << 13)
+#define RT5668_PLL2_CLK_DET_SFT			13
+#define RT5668_POW_CLK_DET2_SFT			8
+#define RT5668_POW_CLK_DET_SFT			0
+
+/* Digital Microphone Control 1 (0x006e) */
+#define RT5668_DMIC_1_EN_MASK			(0x1 << 15)
+#define RT5668_DMIC_1_EN_SFT			15
+#define RT5668_DMIC_1_DIS			(0x0 << 15)
+#define RT5668_DMIC_1_EN			(0x1 << 15)
+#define RT5668_DMIC_1_DP_MASK			(0x3 << 4)
+#define RT5668_DMIC_1_DP_SFT			4
+#define RT5668_DMIC_1_DP_GPIO2			(0x0 << 4)
+#define RT5668_DMIC_1_DP_GPIO5			(0x1 << 4)
+#define RT5668_DMIC_CLK_MASK			(0xf << 0)
+#define RT5668_DMIC_CLK_SFT			0
+
+/* I2S1 Audio Serial Data Port Control (0x0070) */
+#define RT5668_SEL_ADCDAT_MASK			(0x1 << 15)
+#define RT5668_SEL_ADCDAT_OUT			(0x0 << 15)
+#define RT5668_SEL_ADCDAT_IN			(0x1 << 15)
+#define RT5668_SEL_ADCDAT_SFT			15
+#define RT5668_I2S1_TX_CHL_MASK			(0x7 << 12)
+#define RT5668_I2S1_TX_CHL_SFT			12
+#define RT5668_I2S1_TX_CHL_16			(0x0 << 12)
+#define RT5668_I2S1_TX_CHL_20			(0x1 << 12)
+#define RT5668_I2S1_TX_CHL_24			(0x2 << 12)
+#define RT5668_I2S1_TX_CHL_32			(0x3 << 12)
+#define RT5668_I2S1_TX_CHL_8			(0x4 << 12)
+#define RT5668_I2S1_RX_CHL_MASK			(0x7 << 8)
+#define RT5668_I2S1_RX_CHL_SFT			8
+#define RT5668_I2S1_RX_CHL_16			(0x0 << 8)
+#define RT5668_I2S1_RX_CHL_20			(0x1 << 8)
+#define RT5668_I2S1_RX_CHL_24			(0x2 << 8)
+#define RT5668_I2S1_RX_CHL_32			(0x3 << 8)
+#define RT5668_I2S1_RX_CHL_8			(0x4 << 8)
+#define RT5668_I2S1_MONO_MASK			(0x1 << 7)
+#define RT5668_I2S1_MONO_EN			(0x1 << 7)
+#define RT5668_I2S1_MONO_DIS			(0x0 << 7)
+#define RT5668_I2S2_MONO_MASK			(0x1 << 6)
+#define RT5668_I2S2_MONO_EN			(0x1 << 6)
+#define RT5668_I2S2_MONO_DIS			(0x0 << 6)
+#define RT5668_I2S1_DL_MASK			(0x7 << 4)
+#define RT5668_I2S1_DL_SFT			4
+#define RT5668_I2S1_DL_16			(0x0 << 4)
+#define RT5668_I2S1_DL_20			(0x1 << 4)
+#define RT5668_I2S1_DL_24			(0x2 << 4)
+#define RT5668_I2S1_DL_32			(0x3 << 4)
+#define RT5668_I2S1_DL_8			(0x4 << 4)
+
+/* I2S1/2 Audio Serial Data Port Control (0x0070)(0x0071) */
+#define RT5668_I2S2_MS_MASK			(0x1 << 15)
+#define RT5668_I2S2_MS_SFT			15
+#define RT5668_I2S2_MS_M			(0x0 << 15)
+#define RT5668_I2S2_MS_S			(0x1 << 15)
+#define RT5668_I2S2_PIN_CFG_MASK		(0x1 << 14)
+#define RT5668_I2S2_PIN_CFG_SFT			14
+#define RT5668_I2S2_CLK_SEL_MASK		(0x1 << 11)
+#define RT5668_I2S2_CLK_SEL_SFT			11
+#define RT5668_I2S2_OUT_MASK			(0x1 << 9)
+#define RT5668_I2S2_OUT_SFT			9
+#define RT5668_I2S2_OUT_UM			(0x0 << 9)
+#define RT5668_I2S2_OUT_M			(0x1 << 9)
+#define RT5668_I2S_BP_MASK			(0x1 << 8)
+#define RT5668_I2S_BP_SFT			8
+#define RT5668_I2S_BP_NOR			(0x0 << 8)
+#define RT5668_I2S_BP_INV			(0x1 << 8)
+#define RT5668_I2S2_MONO_EN			(0x1 << 6)
+#define RT5668_I2S2_MONO_DIS			(0x0 << 6)
+#define RT5668_I2S2_DL_MASK			(0x3 << 4)
+#define RT5668_I2S2_DL_SFT			4
+#define RT5668_I2S2_DL_16			(0x0 << 4)
+#define RT5668_I2S2_DL_20			(0x1 << 4)
+#define RT5668_I2S2_DL_24			(0x2 << 4)
+#define RT5668_I2S2_DL_8			(0x3 << 4)
+#define RT5668_I2S_DF_MASK			(0x7)
+#define RT5668_I2S_DF_SFT			0
+#define RT5668_I2S_DF_I2S			(0x0)
+#define RT5668_I2S_DF_LEFT			(0x1)
+#define RT5668_I2S_DF_PCM_A			(0x2)
+#define RT5668_I2S_DF_PCM_B			(0x3)
+#define RT5668_I2S_DF_PCM_A_N			(0x6)
+#define RT5668_I2S_DF_PCM_B_N			(0x7)
+
+/* ADC/DAC Clock Control 1 (0x0073) */
+#define RT5668_ADC_OSR_MASK			(0xf << 12)
+#define RT5668_ADC_OSR_SFT			12
+#define RT5668_ADC_OSR_D_1			(0x0 << 12)
+#define RT5668_ADC_OSR_D_2			(0x1 << 12)
+#define RT5668_ADC_OSR_D_4			(0x2 << 12)
+#define RT5668_ADC_OSR_D_6			(0x3 << 12)
+#define RT5668_ADC_OSR_D_8			(0x4 << 12)
+#define RT5668_ADC_OSR_D_12			(0x5 << 12)
+#define RT5668_ADC_OSR_D_16			(0x6 << 12)
+#define RT5668_ADC_OSR_D_24			(0x7 << 12)
+#define RT5668_ADC_OSR_D_32			(0x8 << 12)
+#define RT5668_ADC_OSR_D_48			(0x9 << 12)
+#define RT5668_I2S_M_DIV_MASK			(0xf << 12)
+#define RT5668_I2S_M_DIV_SFT			8
+#define RT5668_I2S_M_D_1			(0x0 << 8)
+#define RT5668_I2S_M_D_2			(0x1 << 8)
+#define RT5668_I2S_M_D_3			(0x2 << 8)
+#define RT5668_I2S_M_D_4			(0x3 << 8)
+#define RT5668_I2S_M_D_6			(0x4 << 8)
+#define RT5668_I2S_M_D_8			(0x5 << 8)
+#define RT5668_I2S_M_D_12			(0x6 << 8)
+#define RT5668_I2S_M_D_16			(0x7 << 8)
+#define RT5668_I2S_M_D_24			(0x8 << 8)
+#define RT5668_I2S_M_D_32			(0x9 << 8)
+#define RT5668_I2S_M_D_48			(0x10 << 8)
+#define RT5668_I2S_CLK_SRC_MASK			(0x7 << 4)
+#define RT5668_I2S_CLK_SRC_SFT			4
+#define RT5668_I2S_CLK_SRC_MCLK			(0x0 << 4)
+#define RT5668_I2S_CLK_SRC_PLL1			(0x1 << 4)
+#define RT5668_I2S_CLK_SRC_PLL2			(0x2 << 4)
+#define RT5668_I2S_CLK_SRC_SDW			(0x3 << 4)
+#define RT5668_I2S_CLK_SRC_RCCLK		(0x4 << 4) /* 25M */
+#define RT5668_DAC_OSR_MASK			(0xf << 0)
+#define RT5668_DAC_OSR_SFT			0
+#define RT5668_DAC_OSR_D_1			(0x0 << 0)
+#define RT5668_DAC_OSR_D_2			(0x1 << 0)
+#define RT5668_DAC_OSR_D_4			(0x2 << 0)
+#define RT5668_DAC_OSR_D_6			(0x3 << 0)
+#define RT5668_DAC_OSR_D_8			(0x4 << 0)
+#define RT5668_DAC_OSR_D_12			(0x5 << 0)
+#define RT5668_DAC_OSR_D_16			(0x6 << 0)
+#define RT5668_DAC_OSR_D_24			(0x7 << 0)
+#define RT5668_DAC_OSR_D_32			(0x8 << 0)
+#define RT5668_DAC_OSR_D_48			(0x9 << 0)
+
+/* ADC/DAC Clock Control 2 (0x0074) */
+#define RT5668_I2S2_BCLK_MS2_MASK		(0x1 << 11)
+#define RT5668_I2S2_BCLK_MS2_SFT		11
+#define RT5668_I2S2_BCLK_MS2_32			(0x0 << 11)
+#define RT5668_I2S2_BCLK_MS2_64			(0x1 << 11)
+
+
+/* TDM control 1 (0x0079) */
+#define RT5668_TDM_TX_CH_MASK			(0x3 << 12)
+#define RT5668_TDM_TX_CH_2			(0x0 << 12)
+#define RT5668_TDM_TX_CH_4			(0x1 << 12)
+#define RT5668_TDM_TX_CH_6			(0x2 << 12)
+#define RT5668_TDM_TX_CH_8			(0x3 << 12)
+#define RT5668_TDM_RX_CH_MASK			(0x3 << 8)
+#define RT5668_TDM_RX_CH_2			(0x0 << 8)
+#define RT5668_TDM_RX_CH_4			(0x1 << 8)
+#define RT5668_TDM_RX_CH_6			(0x2 << 8)
+#define RT5668_TDM_RX_CH_8			(0x3 << 8)
+#define RT5668_TDM_ADC_LCA_MASK			(0xf << 4)
+#define RT5668_TDM_ADC_LCA_SFT			4
+#define RT5668_TDM_ADC_DL_SFT			0
+
+/* TDM control 3 (0x007a) */
+#define RT5668_IF1_ADC1_SEL_SFT			14
+#define RT5668_IF1_ADC2_SEL_SFT			12
+#define RT5668_IF1_ADC3_SEL_SFT			10
+#define RT5668_IF1_ADC4_SEL_SFT			8
+#define RT5668_TDM_ADC_SEL_SFT			4
+
+/* TDM/I2S control (0x007e) */
+#define RT5668_TDM_S_BP_MASK			(0x1 << 15)
+#define RT5668_TDM_S_BP_SFT			15
+#define RT5668_TDM_S_BP_NOR			(0x0 << 15)
+#define RT5668_TDM_S_BP_INV			(0x1 << 15)
+#define RT5668_TDM_S_LP_MASK			(0x1 << 14)
+#define RT5668_TDM_S_LP_SFT			14
+#define RT5668_TDM_S_LP_NOR			(0x0 << 14)
+#define RT5668_TDM_S_LP_INV			(0x1 << 14)
+#define RT5668_TDM_DF_MASK			(0x7 << 11)
+#define RT5668_TDM_DF_SFT			11
+#define RT5668_TDM_DF_I2S			(0x0 << 11)
+#define RT5668_TDM_DF_LEFT			(0x1 << 11)
+#define RT5668_TDM_DF_PCM_A			(0x2 << 11)
+#define RT5668_TDM_DF_PCM_B			(0x3 << 11)
+#define RT5668_TDM_DF_PCM_A_N			(0x6 << 11)
+#define RT5668_TDM_DF_PCM_B_N			(0x7 << 11)
+#define RT5668_TDM_CL_MASK			(0x3 << 4)
+#define RT5668_TDM_CL_16			(0x0 << 4)
+#define RT5668_TDM_CL_20			(0x1 << 4)
+#define RT5668_TDM_CL_24			(0x2 << 4)
+#define RT5668_TDM_CL_32			(0x3 << 4)
+#define RT5668_TDM_M_BP_MASK			(0x1 << 2)
+#define RT5668_TDM_M_BP_SFT			2
+#define RT5668_TDM_M_BP_NOR			(0x0 << 2)
+#define RT5668_TDM_M_BP_INV			(0x1 << 2)
+#define RT5668_TDM_M_LP_MASK			(0x1 << 1)
+#define RT5668_TDM_M_LP_SFT			1
+#define RT5668_TDM_M_LP_NOR			(0x0 << 1)
+#define RT5668_TDM_M_LP_INV			(0x1 << 1)
+#define RT5668_TDM_MS_MASK			(0x1 << 0)
+#define RT5668_TDM_MS_SFT			0
+#define RT5668_TDM_MS_M				(0x0 << 0)
+#define RT5668_TDM_MS_S				(0x1 << 0)
+
+/* Global Clock Control (0x0080) */
+#define RT5668_SCLK_SRC_MASK			(0x7 << 13)
+#define RT5668_SCLK_SRC_SFT			13
+#define RT5668_SCLK_SRC_MCLK			(0x0 << 13)
+#define RT5668_SCLK_SRC_PLL1			(0x1 << 13)
+#define RT5668_SCLK_SRC_PLL2			(0x2 << 13)
+#define RT5668_SCLK_SRC_SDW			(0x3 << 13)
+#define RT5668_SCLK_SRC_RCCLK			(0x4 << 13)
+#define RT5668_PLL1_SRC_MASK			(0x3 << 10)
+#define RT5668_PLL1_SRC_SFT			10
+#define RT5668_PLL1_SRC_MCLK			(0x0 << 10)
+#define RT5668_PLL1_SRC_BCLK1			(0x1 << 10)
+#define RT5668_PLL1_SRC_SDW			(0x2 << 10)
+#define RT5668_PLL1_SRC_RC			(0x3 << 10)
+#define RT5668_PLL2_SRC_MASK			(0x3 << 8)
+#define RT5668_PLL2_SRC_SFT			8
+#define RT5668_PLL2_SRC_MCLK			(0x0 << 8)
+#define RT5668_PLL2_SRC_BCLK1			(0x1 << 8)
+#define RT5668_PLL2_SRC_SDW			(0x2 << 8)
+#define RT5668_PLL2_SRC_RC			(0x3 << 8)
+
+
+
+#define RT5668_PLL_INP_MAX			40000000
+#define RT5668_PLL_INP_MIN			256000
+/* PLL M/N/K Code Control 1 (0x0081) */
+#define RT5668_PLL_N_MAX			0x001ff
+#define RT5668_PLL_N_MASK			(RT5668_PLL_N_MAX << 7)
+#define RT5668_PLL_N_SFT			7
+#define RT5668_PLL_K_MAX			0x001f
+#define RT5668_PLL_K_MASK			(RT5668_PLL_K_MAX)
+#define RT5668_PLL_K_SFT			0
+
+/* PLL M/N/K Code Control 2 (0x0082) */
+#define RT5668_PLL_M_MAX			0x00f
+#define RT5668_PLL_M_MASK			(RT5668_PLL_M_MAX << 12)
+#define RT5668_PLL_M_SFT			12
+#define RT5668_PLL_M_BP				(0x1 << 11)
+#define RT5668_PLL_M_BP_SFT			11
+#define RT5668_PLL_K_BP				(0x1 << 10)
+#define RT5668_PLL_K_BP_SFT			10
+
+/* PLL tracking mode 1 (0x0083) */
+#define RT5668_DA_ASRC_MASK			(0x1 << 13)
+#define RT5668_DA_ASRC_SFT			13
+#define RT5668_DAC_STO1_ASRC_MASK		(0x1 << 12)
+#define RT5668_DAC_STO1_ASRC_SFT		12
+#define RT5668_AD_ASRC_MASK			(0x1 << 8)
+#define RT5668_AD_ASRC_SFT			8
+#define RT5668_AD_ASRC_SEL_MASK			(0x1 << 4)
+#define RT5668_AD_ASRC_SEL_SFT			4
+#define RT5668_DMIC_ASRC_MASK			(0x1 << 3)
+#define RT5668_DMIC_ASRC_SFT			3
+#define RT5668_ADC_STO1_ASRC_MASK		(0x1 << 2)
+#define RT5668_ADC_STO1_ASRC_SFT		2
+#define RT5668_DA_ASRC_SEL_MASK			(0x1 << 0)
+#define RT5668_DA_ASRC_SEL_SFT			0
+
+/* PLL tracking mode 2 3 (0x0084)(0x0085)*/
+#define RT5668_FILTER_CLK_SEL_MASK		(0x7 << 12)
+#define RT5668_FILTER_CLK_SEL_SFT		12
+
+/* ASRC Control 4 (0x0086) */
+#define RT5668_ASRCIN_FTK_N1_MASK		(0x3 << 14)
+#define RT5668_ASRCIN_FTK_N1_SFT		14
+#define RT5668_ASRCIN_FTK_N2_MASK		(0x3 << 12)
+#define RT5668_ASRCIN_FTK_N2_SFT		12
+#define RT5668_ASRCIN_FTK_M1_MASK		(0x7 << 8)
+#define RT5668_ASRCIN_FTK_M1_SFT		8
+#define RT5668_ASRCIN_FTK_M2_MASK		(0x7 << 4)
+#define RT5668_ASRCIN_FTK_M2_SFT		4
+
+/* SoundWire reference clk (0x008d) */
+#define RT5668_PLL2_OUT_MASK			(0x1 << 8)
+#define RT5668_PLL2_OUT_98M			(0x0 << 8)
+#define RT5668_PLL2_OUT_49M			(0x1 << 8)
+#define RT5668_SDW_REF_2_MASK			(0xf << 4)
+#define RT5668_SDW_REF_2_SFT			4
+#define RT5668_SDW_REF_2_48K			(0x0 << 4)
+#define RT5668_SDW_REF_2_96K			(0x1 << 4)
+#define RT5668_SDW_REF_2_192K			(0x2 << 4)
+#define RT5668_SDW_REF_2_32K			(0x3 << 4)
+#define RT5668_SDW_REF_2_24K			(0x4 << 4)
+#define RT5668_SDW_REF_2_16K			(0x5 << 4)
+#define RT5668_SDW_REF_2_12K			(0x6 << 4)
+#define RT5668_SDW_REF_2_8K			(0x7 << 4)
+#define RT5668_SDW_REF_2_44K			(0x8 << 4)
+#define RT5668_SDW_REF_2_88K			(0x9 << 4)
+#define RT5668_SDW_REF_2_176K			(0xa << 4)
+#define RT5668_SDW_REF_2_353K			(0xb << 4)
+#define RT5668_SDW_REF_2_22K			(0xc << 4)
+#define RT5668_SDW_REF_2_384K			(0xd << 4)
+#define RT5668_SDW_REF_2_11K			(0xe << 4)
+#define RT5668_SDW_REF_1_MASK			(0xf << 0)
+#define RT5668_SDW_REF_1_SFT			0
+#define RT5668_SDW_REF_1_48K			(0x0 << 0)
+#define RT5668_SDW_REF_1_96K			(0x1 << 0)
+#define RT5668_SDW_REF_1_192K			(0x2 << 0)
+#define RT5668_SDW_REF_1_32K			(0x3 << 0)
+#define RT5668_SDW_REF_1_24K			(0x4 << 0)
+#define RT5668_SDW_REF_1_16K			(0x5 << 0)
+#define RT5668_SDW_REF_1_12K			(0x6 << 0)
+#define RT5668_SDW_REF_1_8K			(0x7 << 0)
+#define RT5668_SDW_REF_1_44K			(0x8 << 0)
+#define RT5668_SDW_REF_1_88K			(0x9 << 0)
+#define RT5668_SDW_REF_1_176K			(0xa << 0)
+#define RT5668_SDW_REF_1_353K			(0xb << 0)
+#define RT5668_SDW_REF_1_22K			(0xc << 0)
+#define RT5668_SDW_REF_1_384K			(0xd << 0)
+#define RT5668_SDW_REF_1_11K			(0xe << 0)
+
+/* Depop Mode Control 1 (0x008e) */
+#define RT5668_PUMP_EN				(0x1 << 3)
+#define RT5668_PUMP_EN_SFT				3
+#define RT5668_CAPLESS_EN			(0x1 << 0)
+#define RT5668_CAPLESS_EN_SFT			0
+
+/* Depop Mode Control 2 (0x8f) */
+#define RT5668_RAMP_MASK			(0x1 << 12)
+#define RT5668_RAMP_SFT				12
+#define RT5668_RAMP_DIS				(0x0 << 12)
+#define RT5668_RAMP_EN				(0x1 << 12)
+#define RT5668_BPS_MASK				(0x1 << 11)
+#define RT5668_BPS_SFT				11
+#define RT5668_BPS_DIS				(0x0 << 11)
+#define RT5668_BPS_EN				(0x1 << 11)
+#define RT5668_FAST_UPDN_MASK			(0x1 << 10)
+#define RT5668_FAST_UPDN_SFT			10
+#define RT5668_FAST_UPDN_DIS			(0x0 << 10)
+#define RT5668_FAST_UPDN_EN			(0x1 << 10)
+#define RT5668_VLO_MASK				(0x1 << 7)
+#define RT5668_VLO_SFT				7
+#define RT5668_VLO_3V				(0x0 << 7)
+#define RT5668_VLO_33V				(0x1 << 7)
+
+/* HPOUT charge pump 1 (0x0091) */
+#define RT5668_OSW_L_MASK			(0x1 << 11)
+#define RT5668_OSW_L_SFT			11
+#define RT5668_OSW_L_DIS			(0x0 << 11)
+#define RT5668_OSW_L_EN				(0x1 << 11)
+#define RT5668_OSW_R_MASK			(0x1 << 10)
+#define RT5668_OSW_R_SFT			10
+#define RT5668_OSW_R_DIS			(0x0 << 10)
+#define RT5668_OSW_R_EN				(0x1 << 10)
+#define RT5668_PM_HP_MASK			(0x3 << 8)
+#define RT5668_PM_HP_SFT			8
+#define RT5668_PM_HP_LV				(0x0 << 8)
+#define RT5668_PM_HP_MV				(0x1 << 8)
+#define RT5668_PM_HP_HV				(0x2 << 8)
+#define RT5668_IB_HP_MASK			(0x3 << 6)
+#define RT5668_IB_HP_SFT			6
+#define RT5668_IB_HP_125IL			(0x0 << 6)
+#define RT5668_IB_HP_25IL			(0x1 << 6)
+#define RT5668_IB_HP_5IL			(0x2 << 6)
+#define RT5668_IB_HP_1IL			(0x3 << 6)
+
+/* Micbias Control1 (0x93) */
+#define RT5668_MIC1_OV_MASK			(0x3 << 14)
+#define RT5668_MIC1_OV_SFT			14
+#define RT5668_MIC1_OV_2V7			(0x0 << 14)
+#define RT5668_MIC1_OV_2V4			(0x1 << 14)
+#define RT5668_MIC1_OV_2V25			(0x3 << 14)
+#define RT5668_MIC1_OV_1V8			(0x4 << 14)
+#define RT5668_MIC1_CLK_MASK			(0x1 << 13)
+#define RT5668_MIC1_CLK_SFT			13
+#define RT5668_MIC1_CLK_DIS			(0x0 << 13)
+#define RT5668_MIC1_CLK_EN			(0x1 << 13)
+#define RT5668_MIC1_OVCD_MASK			(0x1 << 12)
+#define RT5668_MIC1_OVCD_SFT			12
+#define RT5668_MIC1_OVCD_DIS			(0x0 << 12)
+#define RT5668_MIC1_OVCD_EN			(0x1 << 12)
+#define RT5668_MIC1_OVTH_MASK			(0x3 << 10)
+#define RT5668_MIC1_OVTH_SFT			10
+#define RT5668_MIC1_OVTH_768UA			(0x0 << 10)
+#define RT5668_MIC1_OVTH_960UA			(0x1 << 10)
+#define RT5668_MIC1_OVTH_1152UA			(0x2 << 10)
+#define RT5668_MIC1_OVTH_1960UA			(0x3 << 10)
+#define RT5668_MIC2_OV_MASK			(0x3 << 8)
+#define RT5668_MIC2_OV_SFT			8
+#define RT5668_MIC2_OV_2V7			(0x0 << 8)
+#define RT5668_MIC2_OV_2V4			(0x1 << 8)
+#define RT5668_MIC2_OV_2V25			(0x3 << 8)
+#define RT5668_MIC2_OV_1V8			(0x4 << 8)
+#define RT5668_MIC2_CLK_MASK			(0x1 << 7)
+#define RT5668_MIC2_CLK_SFT			7
+#define RT5668_MIC2_CLK_DIS			(0x0 << 7)
+#define RT5668_MIC2_CLK_EN			(0x1 << 7)
+#define RT5668_MIC2_OVTH_MASK			(0x3 << 4)
+#define RT5668_MIC2_OVTH_SFT			4
+#define RT5668_MIC2_OVTH_768UA			(0x0 << 4)
+#define RT5668_MIC2_OVTH_960UA			(0x1 << 4)
+#define RT5668_MIC2_OVTH_1152UA			(0x2 << 4)
+#define RT5668_MIC2_OVTH_1960UA			(0x3 << 4)
+#define RT5668_PWR_MB_MASK			(0x1 << 3)
+#define RT5668_PWR_MB_SFT			3
+#define RT5668_PWR_MB_PD			(0x0 << 3)
+#define RT5668_PWR_MB_PU			(0x1 << 3)
+
+/* Micbias Control2 (0x0094) */
+#define RT5668_PWR_CLK25M_MASK			(0x1 << 9)
+#define RT5668_PWR_CLK25M_SFT			9
+#define RT5668_PWR_CLK25M_PD			(0x0 << 9)
+#define RT5668_PWR_CLK25M_PU			(0x1 << 9)
+#define RT5668_PWR_CLK1M_MASK			(0x1 << 8)
+#define RT5668_PWR_CLK1M_SFT			8
+#define RT5668_PWR_CLK1M_PD			(0x0 << 8)
+#define RT5668_PWR_CLK1M_PU			(0x1 << 8)
+
+/* RC Clock Control (0x009f) */
+#define RT5668_POW_IRQ				(0x1 << 15)
+#define RT5668_POW_JDH				(0x1 << 14)
+#define RT5668_POW_JDL				(0x1 << 13)
+#define RT5668_POW_ANA				(0x1 << 12)
+
+/* I2S Master Mode Clock Control 1 (0x00a0) */
+#define RT5668_CLK_SRC_MCLK			(0x0)
+#define RT5668_CLK_SRC_PLL1			(0x1)
+#define RT5668_CLK_SRC_PLL2			(0x2)
+#define RT5668_CLK_SRC_SDW			(0x3)
+#define RT5668_CLK_SRC_RCCLK			(0x4)
+#define RT5668_I2S_PD_1				(0x0)
+#define RT5668_I2S_PD_2				(0x1)
+#define RT5668_I2S_PD_3				(0x2)
+#define RT5668_I2S_PD_4				(0x3)
+#define RT5668_I2S_PD_6				(0x4)
+#define RT5668_I2S_PD_8				(0x5)
+#define RT5668_I2S_PD_12			(0x6)
+#define RT5668_I2S_PD_16			(0x7)
+#define RT5668_I2S_PD_24			(0x8)
+#define RT5668_I2S_PD_32			(0x9)
+#define RT5668_I2S_PD_48			(0xa)
+#define RT5668_I2S2_SRC_MASK			(0x3 << 4)
+#define RT5668_I2S2_SRC_SFT			4
+#define RT5668_I2S2_M_PD_MASK			(0xf << 0)
+#define RT5668_I2S2_M_PD_SFT			0
+
+/* IRQ Control 1 (0x00b6) */
+#define RT5668_JD1_PULSE_EN_MASK		(0x1 << 10)
+#define RT5668_JD1_PULSE_EN_SFT			10
+#define RT5668_JD1_PULSE_DIS			(0x0 << 10)
+#define RT5668_JD1_PULSE_EN			(0x1 << 10)
+
+/* IRQ Control 2 (0x00b7) */
+#define RT5668_JD1_EN_MASK			(0x1 << 15)
+#define RT5668_JD1_EN_SFT			15
+#define RT5668_JD1_DIS				(0x0 << 15)
+#define RT5668_JD1_EN				(0x1 << 15)
+#define RT5668_JD1_POL_MASK			(0x1 << 13)
+#define RT5668_JD1_POL_NOR			(0x0 << 13)
+#define RT5668_JD1_POL_INV			(0x1 << 13)
+
+/* IRQ Control 3 (0x00b8) */
+#define RT5668_IL_IRQ_MASK			(0x1 << 7)
+#define RT5668_IL_IRQ_DIS			(0x0 << 7)
+#define RT5668_IL_IRQ_EN			(0x1 << 7)
+
+/* GPIO Control 1 (0x00c0) */
+#define RT5668_GP1_PIN_MASK			(0x3 << 14)
+#define RT5668_GP1_PIN_SFT			14
+#define RT5668_GP1_PIN_GPIO1			(0x0 << 14)
+#define RT5668_GP1_PIN_IRQ			(0x1 << 14)
+#define RT5668_GP1_PIN_DMIC_CLK			(0x2 << 14)
+#define RT5668_GP2_PIN_MASK			(0x3 << 12)
+#define RT5668_GP2_PIN_SFT			12
+#define RT5668_GP2_PIN_GPIO2			(0x0 << 12)
+#define RT5668_GP2_PIN_LRCK2			(0x1 << 12)
+#define RT5668_GP2_PIN_DMIC_SDA			(0x2 << 12)
+#define RT5668_GP3_PIN_MASK			(0x3 << 10)
+#define RT5668_GP3_PIN_SFT			10
+#define RT5668_GP3_PIN_GPIO3			(0x0 << 10)
+#define RT5668_GP3_PIN_BCLK2			(0x1 << 10)
+#define RT5668_GP3_PIN_DMIC_CLK			(0x2 << 10)
+#define RT5668_GP4_PIN_MASK			(0x3 << 8)
+#define RT5668_GP4_PIN_SFT			8
+#define RT5668_GP4_PIN_GPIO4			(0x0 << 8)
+#define RT5668_GP4_PIN_ADCDAT1			(0x1 << 8)
+#define RT5668_GP4_PIN_DMIC_CLK			(0x2 << 8)
+#define RT5668_GP4_PIN_ADCDAT2			(0x3 << 8)
+#define RT5668_GP5_PIN_MASK			(0x3 << 6)
+#define RT5668_GP5_PIN_SFT			6
+#define RT5668_GP5_PIN_GPIO5			(0x0 << 6)
+#define RT5668_GP5_PIN_DACDAT1			(0x1 << 6)
+#define RT5668_GP5_PIN_DMIC_SDA			(0x2 << 6)
+#define RT5668_GP6_PIN_MASK			(0x1 << 5)
+#define RT5668_GP6_PIN_SFT			5
+#define RT5668_GP6_PIN_GPIO6			(0x0 << 5)
+#define RT5668_GP6_PIN_LRCK1			(0x1 << 5)
+
+/* GPIO Control 2 (0x00c1)*/
+#define RT5668_GP1_PF_MASK			(0x1 << 15)
+#define RT5668_GP1_PF_IN			(0x0 << 15)
+#define RT5668_GP1_PF_OUT			(0x1 << 15)
+#define RT5668_GP1_OUT_MASK			(0x1 << 14)
+#define RT5668_GP1_OUT_L			(0x0 << 14)
+#define RT5668_GP1_OUT_H			(0x1 << 14)
+#define RT5668_GP2_PF_MASK			(0x1 << 13)
+#define RT5668_GP2_PF_IN			(0x0 << 13)
+#define RT5668_GP2_PF_OUT			(0x1 << 13)
+#define RT5668_GP2_OUT_MASK			(0x1 << 12)
+#define RT5668_GP2_OUT_L			(0x0 << 12)
+#define RT5668_GP2_OUT_H			(0x1 << 12)
+#define RT5668_GP3_PF_MASK			(0x1 << 11)
+#define RT5668_GP3_PF_IN			(0x0 << 11)
+#define RT5668_GP3_PF_OUT			(0x1 << 11)
+#define RT5668_GP3_OUT_MASK			(0x1 << 10)
+#define RT5668_GP3_OUT_L			(0x0 << 10)
+#define RT5668_GP3_OUT_H			(0x1 << 10)
+#define RT5668_GP4_PF_MASK			(0x1 << 9)
+#define RT5668_GP4_PF_IN			(0x0 << 9)
+#define RT5668_GP4_PF_OUT			(0x1 << 9)
+#define RT5668_GP4_OUT_MASK			(0x1 << 8)
+#define RT5668_GP4_OUT_L			(0x0 << 8)
+#define RT5668_GP4_OUT_H			(0x1 << 8)
+#define RT5668_GP5_PF_MASK			(0x1 << 7)
+#define RT5668_GP5_PF_IN			(0x0 << 7)
+#define RT5668_GP5_PF_OUT			(0x1 << 7)
+#define RT5668_GP5_OUT_MASK			(0x1 << 6)
+#define RT5668_GP5_OUT_L			(0x0 << 6)
+#define RT5668_GP5_OUT_H			(0x1 << 6)
+#define RT5668_GP6_PF_MASK			(0x1 << 5)
+#define RT5668_GP6_PF_IN			(0x0 << 5)
+#define RT5668_GP6_PF_OUT			(0x1 << 5)
+#define RT5668_GP6_OUT_MASK			(0x1 << 4)
+#define RT5668_GP6_OUT_L			(0x0 << 4)
+#define RT5668_GP6_OUT_H			(0x1 << 4)
+
+
+/* GPIO Status (0x00c2) */
+#define RT5668_GP6_STA				(0x1 << 6)
+#define RT5668_GP5_STA				(0x1 << 5)
+#define RT5668_GP4_STA				(0x1 << 4)
+#define RT5668_GP3_STA				(0x1 << 3)
+#define RT5668_GP2_STA				(0x1 << 2)
+#define RT5668_GP1_STA				(0x1 << 1)
+
+/* Soft volume and zero cross control 1 (0x00d9) */
+#define RT5668_SV_MASK				(0x1 << 15)
+#define RT5668_SV_SFT				15
+#define RT5668_SV_DIS				(0x0 << 15)
+#define RT5668_SV_EN				(0x1 << 15)
+#define RT5668_ZCD_MASK				(0x1 << 10)
+#define RT5668_ZCD_SFT				10
+#define RT5668_ZCD_PD				(0x0 << 10)
+#define RT5668_ZCD_PU				(0x1 << 10)
+#define RT5668_SV_DLY_MASK			(0xf)
+#define RT5668_SV_DLY_SFT			0
+
+/* Soft volume and zero cross control 2 (0x00da) */
+#define RT5668_ZCD_BST1_CBJ_MASK		(0x1 << 7)
+#define RT5668_ZCD_BST1_CBJ_SFT			7
+#define RT5668_ZCD_BST1_CBJ_DIS			(0x0 << 7)
+#define RT5668_ZCD_BST1_CBJ_EN			(0x1 << 7)
+#define RT5668_ZCD_RECMIX_MASK			(0x1)
+#define RT5668_ZCD_RECMIX_SFT			0
+#define RT5668_ZCD_RECMIX_DIS			(0x0)
+#define RT5668_ZCD_RECMIX_EN			(0x1)
+
+/* 4 Button Inline Command Control 2 (0x00e3) */
+#define RT5668_4BTN_IL_MASK			(0x1 << 15)
+#define RT5668_4BTN_IL_EN			(0x1 << 15)
+#define RT5668_4BTN_IL_DIS			(0x0 << 15)
+#define RT5668_4BTN_IL_RST_MASK			(0x1 << 14)
+#define RT5668_4BTN_IL_NOR			(0x1 << 14)
+#define RT5668_4BTN_IL_RST			(0x0 << 14)
+
+/* Analog JD Control (0x00f0) */
+#define RT5668_JDH_RS_MASK			(0x1 << 4)
+#define RT5668_JDH_NO_PLUG			(0x1 << 4)
+#define RT5668_JDH_PLUG				(0x0 << 4)
+
+/* Chopper and Clock control for DAC (0x013a)*/
+#define RT5668_CKXEN_DAC1_MASK			(0x1 << 13)
+#define RT5668_CKXEN_DAC1_SFT			13
+#define RT5668_CKGEN_DAC1_MASK			(0x1 << 12)
+#define RT5668_CKGEN_DAC1_SFT			12
+
+/* Chopper and Clock control for ADC (0x013b)*/
+#define RT5668_CKXEN_ADC1_MASK			(0x1 << 13)
+#define RT5668_CKXEN_ADC1_SFT			13
+#define RT5668_CKGEN_ADC1_MASK			(0x1 << 12)
+#define RT5668_CKGEN_ADC1_SFT			12
+
+/* Volume test (0x013f)*/
+#define RT5668_SEL_CLK_VOL_MASK			(0x1 << 15)
+#define RT5668_SEL_CLK_VOL_EN			(0x1 << 15)
+#define RT5668_SEL_CLK_VOL_DIS			(0x0 << 15)
+
+/* Test Mode Control 1 (0x0145) */
+#define RT5668_AD2DA_LB_MASK			(0x1 << 10)
+#define RT5668_AD2DA_LB_SFT			10
+
+/* Stereo Noise Gate Control 1 (0x0160) */
+#define RT5668_NG2_EN_MASK			(0x1 << 15)
+#define RT5668_NG2_EN				(0x1 << 15)
+#define RT5668_NG2_DIS				(0x0 << 15)
+
+/* Stereo1 DAC Silence Detection Control (0x0190) */
+#define RT5668_DEB_STO_DAC_MASK			(0x7 << 4)
+#define RT5668_DEB_80_MS			(0x0 << 4)
+
+/* SAR ADC Inline Command Control 1 (0x0210) */
+#define RT5668_SAR_BUTT_DET_MASK		(0x1 << 15)
+#define RT5668_SAR_BUTT_DET_EN			(0x1 << 15)
+#define RT5668_SAR_BUTT_DET_DIS			(0x0 << 15)
+#define RT5668_SAR_BUTDET_MODE_MASK		(0x1 << 14)
+#define RT5668_SAR_BUTDET_POW_SAV		(0x1 << 14)
+#define RT5668_SAR_BUTDET_POW_NORM		(0x0 << 14)
+#define RT5668_SAR_BUTDET_RST_MASK		(0x1 << 13)
+#define RT5668_SAR_BUTDET_RST_NORMAL		(0x1 << 13)
+#define RT5668_SAR_BUTDET_RST			(0x0 << 13)
+#define RT5668_SAR_POW_MASK			(0x1 << 12)
+#define RT5668_SAR_POW_EN			(0x1 << 12)
+#define RT5668_SAR_POW_DIS			(0x0 << 12)
+#define RT5668_SAR_RST_MASK			(0x1 << 11)
+#define RT5668_SAR_RST_NORMAL			(0x1 << 11)
+#define RT5668_SAR_RST				(0x0 << 11)
+#define RT5668_SAR_BYPASS_MASK			(0x1 << 10)
+#define RT5668_SAR_BYPASS_EN			(0x1 << 10)
+#define RT5668_SAR_BYPASS_DIS			(0x0 << 10)
+#define RT5668_SAR_SEL_MB1_MASK			(0x1 << 9)
+#define RT5668_SAR_SEL_MB1_SEL			(0x1 << 9)
+#define RT5668_SAR_SEL_MB1_NOSEL		(0x0 << 9)
+#define RT5668_SAR_SEL_MB2_MASK			(0x1 << 8)
+#define RT5668_SAR_SEL_MB2_SEL			(0x1 << 8)
+#define RT5668_SAR_SEL_MB2_NOSEL		(0x0 << 8)
+#define RT5668_SAR_SEL_MODE_MASK		(0x1 << 7)
+#define RT5668_SAR_SEL_MODE_CMP			(0x1 << 7)
+#define RT5668_SAR_SEL_MODE_ADC			(0x0 << 7)
+#define RT5668_SAR_SEL_MB1_MB2_MASK		(0x1 << 5)
+#define RT5668_SAR_SEL_MB1_MB2_AUTO		(0x1 << 5)
+#define RT5668_SAR_SEL_MB1_MB2_MANU		(0x0 << 5)
+#define RT5668_SAR_SEL_SIGNAL_MASK		(0x1 << 4)
+#define RT5668_SAR_SEL_SIGNAL_AUTO		(0x1 << 4)
+#define RT5668_SAR_SEL_SIGNAL_MANU		(0x0 << 4)
+
+/* SAR ADC Inline Command Control 13 (0x021c) */
+#define RT5668_SAR_SOUR_MASK			(0x3f)
+#define RT5668_SAR_SOUR_BTN			(0x3f)
+#define RT5668_SAR_SOUR_TYPE			(0x0)
+
+
+/* System Clock Source */
+enum {
+	RT5668_SCLK_S_MCLK,
+	RT5668_SCLK_S_PLL1,
+	RT5668_SCLK_S_PLL2,
+	RT5668_SCLK_S_RCCLK,
+};
+
+/* PLL Source */
+enum {
+	RT5668_PLL1_S_MCLK,
+	RT5668_PLL1_S_BCLK1,
+	RT5668_PLL1_S_RCCLK,
+};
+
+enum {
+	RT5668_AIF1,
+	RT5668_AIF2,
+	RT5668_AIFS
+};
+
+/* filter mask */
+enum {
+	RT5668_DA_STEREO1_FILTER = 0x1,
+	RT5668_AD_STEREO1_FILTER = (0x1 << 1),
+};
+
+enum {
+	RT5668_CLK_SEL_SYS,
+	RT5668_CLK_SEL_I2S1_ASRC,
+	RT5668_CLK_SEL_I2S2_ASRC,
+};
+
+int rt5668_sel_asrc_clk_src(struct snd_soc_component *component,
+		unsigned int filter_mask, unsigned int clk_src);
+
+#endif /* __RT5668_H__ */
diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index dc7df337d5f8..732ef928b25d 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -71,7 +71,7 @@ static const struct regmap_range_cfg rt5670_ranges[] = {
 
 static const struct reg_sequence init_list[] = {
 	{ RT5670_PR_BASE + 0x14, 0x9a8a },
-	{ RT5670_PR_BASE + 0x38, 0x3ba1 },
+	{ RT5670_PR_BASE + 0x38, 0x1fe1 },
 	{ RT5670_PR_BASE + 0x3d, 0x3640 },
 	{ 0x8a, 0x0123 },
 };
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index bc1a23dd7c2d..8a0181a2db08 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -5006,13 +5006,6 @@ static const struct regmap_config rt5677_regmap = {
 	.num_ranges = ARRAY_SIZE(rt5677_ranges),
 };
 
-static const struct i2c_device_id rt5677_i2c_id[] = {
-	{ "rt5677", RT5677 },
-	{ "rt5676", RT5676 },
-	{ }
-};
-MODULE_DEVICE_TABLE(i2c, rt5677_i2c_id);
-
 static const struct of_device_id rt5677_of_match[] = {
 	{ .compatible = "realtek,rt5677", RT5677 },
 	{ }
@@ -5130,8 +5123,7 @@ static void rt5677_free_irq(struct i2c_client *i2c)
 		regmap_del_irq_chip(i2c->irq, rt5677->irq_data);
 }
 
-static int rt5677_i2c_probe(struct i2c_client *i2c,
-		    const struct i2c_device_id *id)
+static int rt5677_i2c_probe(struct i2c_client *i2c)
 {
 	struct rt5677_priv *rt5677;
 	int ret;
@@ -5278,9 +5270,8 @@ static struct i2c_driver rt5677_i2c_driver = {
 		.of_match_table = rt5677_of_match,
 		.acpi_match_table = ACPI_PTR(rt5677_acpi_match),
 	},
-	.probe = rt5677_i2c_probe,
+	.probe_new = rt5677_i2c_probe,
 	.remove   = rt5677_i2c_remove,
-	.id_table = rt5677_i2c_id,
 };
 module_i2c_driver(rt5677_i2c_driver);
 
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 7c1d65830c05..60764f6201b1 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1,12 +1,8 @@
-/*
- * sgtl5000.c  --  SGTL5000 ALSA SoC Audio driver
- *
- * Copyright 2010-2011 Freescale Semiconductor, Inc. All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// sgtl5000.c  --  SGTL5000 ALSA SoC Audio driver
+//
+// Copyright 2010-2011 Freescale Semiconductor, Inc. All Rights Reserved.
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -457,7 +453,7 @@ static int dac_put_volsw(struct snd_kcontrol *kcontrol,
  * avc_put_threshold function: register_value = 10^(dB/20) * 0.636 * 2^15 ==>
  * dB = ( fls(register_value) - 14.347 ) * 6.02
  *
- * As this calculation is expensive and the threshold dB values may not exeed
+ * As this calculation is expensive and the threshold dB values may not exceed
  * 0 to 96 we use pre-calculated values.
  */
 static int avc_get_threshold(struct snd_kcontrol *kcontrol,
@@ -490,7 +486,7 @@ static int avc_get_threshold(struct snd_kcontrol *kcontrol,
  *
  * The register value is calculated by following formula:
  *                                    register_value = 10^(dB/20) * 0.636 * 2^15
- * As this calculation is expensive and the threshold dB values may not exeed
+ * As this calculation is expensive and the threshold dB values may not exceed
  * 0 to 96 we use pre-calculated values.
  */
 static int avc_put_threshold(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index 28cf637155bb..18cae08bbd3a 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * sgtl5000.h - SGTL5000 audio codec interface
  *
  * Copyright 2010-2011 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef _SGTL5000_H
diff --git a/sound/soc/codecs/ssm2305.c b/sound/soc/codecs/ssm2305.c
new file mode 100644
index 000000000000..2968959c4b75
--- /dev/null
+++ b/sound/soc/codecs/ssm2305.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Analog Devices SSM2305 Amplifier Driver
+//
+// Copyright (C) 2018 Pengutronix, Marco Felsch <kernel@pengutronix.de>
+//
+
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <sound/soc.h>
+
+#define DRV_NAME "ssm2305"
+
+struct ssm2305 {
+	/* shutdown gpio  */
+	struct gpio_desc *gpiod_shutdown;
+};
+
+static int ssm2305_power_event(struct snd_soc_dapm_widget *w,
+			       struct snd_kcontrol *kctrl, int event)
+{
+	struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
+	struct ssm2305 *data = snd_soc_component_get_drvdata(c);
+
+	gpiod_set_value_cansleep(data->gpiod_shutdown,
+				 SND_SOC_DAPM_EVENT_ON(event));
+
+	return 0;
+}
+
+static const struct snd_soc_dapm_widget ssm2305_dapm_widgets[] = {
+	/* Stereo input/output */
+	SND_SOC_DAPM_INPUT("L_IN"),
+	SND_SOC_DAPM_INPUT("R_IN"),
+	SND_SOC_DAPM_OUTPUT("L_OUT"),
+	SND_SOC_DAPM_OUTPUT("R_OUT"),
+
+	SND_SOC_DAPM_SUPPLY("Power", SND_SOC_NOPM, 0, 0, ssm2305_power_event,
+			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+};
+
+static const struct snd_soc_dapm_route ssm2305_dapm_routes[] = {
+	{ "L_OUT", NULL, "L_IN" },
+	{ "R_OUT", NULL, "R_IN" },
+	{ "L_IN", NULL, "Power" },
+	{ "R_IN", NULL, "Power" },
+};
+
+static const struct snd_soc_component_driver ssm2305_component_driver = {
+	.dapm_widgets		= ssm2305_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(ssm2305_dapm_widgets),
+	.dapm_routes		= ssm2305_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(ssm2305_dapm_routes),
+};
+
+static int ssm2305_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ssm2305 *priv;
+	int err;
+
+	/* Allocate the private data */
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, priv);
+
+	/* Get shutdown gpio */
+	priv->gpiod_shutdown = devm_gpiod_get(dev, "shutdown",
+					      GPIOD_OUT_LOW);
+	if (IS_ERR(priv->gpiod_shutdown)) {
+		err = PTR_ERR(priv->gpiod_shutdown);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get 'shutdown' gpio: %d\n",
+				err);
+		return err;
+	}
+
+	return devm_snd_soc_register_component(dev, &ssm2305_component_driver,
+					       NULL, 0);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id ssm2305_of_match[] = {
+	{ .compatible = "adi,ssm2305", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ssm2305_of_match);
+#endif
+
+static struct platform_driver ssm2305_driver = {
+	.driver = {
+		.name = DRV_NAME,
+		.of_match_table = of_match_ptr(ssm2305_of_match),
+	},
+	.probe = ssm2305_probe,
+};
+
+module_platform_driver(ssm2305_driver);
+
+MODULE_DESCRIPTION("ASoC SSM2305 amplifier driver");
+MODULE_AUTHOR("Marco Felsch <m.felsch@pengutronix.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/tas6424.c b/sound/soc/codecs/tas6424.c
index 4f3a16c520a2..14999b999fd3 100644
--- a/sound/soc/codecs/tas6424.c
+++ b/sound/soc/codecs/tas6424.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/regulator/consumer.h>
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -43,6 +44,8 @@ struct tas6424_data {
 	unsigned int last_fault1;
 	unsigned int last_fault2;
 	unsigned int last_warn;
+	struct gpio_desc *standby_gpio;
+	struct gpio_desc *mute_gpio;
 };
 
 /*
@@ -61,6 +64,8 @@ static const struct snd_kcontrol_new tas6424_snd_controls[] = {
 		       TAS6424_CH3_VOL_CTRL, 0, 0xff, 0, dac_tlv),
 	SOC_SINGLE_TLV("Speaker Driver CH4 Playback Volume",
 		       TAS6424_CH4_VOL_CTRL, 0, 0xff, 0, dac_tlv),
+	SOC_SINGLE_STROBE("Auto Diagnostics Switch", TAS6424_DC_DIAG_CTRL1,
+			  TAS6424_LDGBYPASS_SHIFT, 1),
 };
 
 static int tas6424_dac_event(struct snd_soc_dapm_widget *w,
@@ -249,10 +254,16 @@ static int tas6424_set_dai_tdm_slot(struct snd_soc_dai *dai,
 static int tas6424_mute(struct snd_soc_dai *dai, int mute)
 {
 	struct snd_soc_component *component = dai->component;
+	struct tas6424_data *tas6424 = snd_soc_component_get_drvdata(component);
 	unsigned int val;
 
 	dev_dbg(component->dev, "%s() mute=%d\n", __func__, mute);
 
+	if (tas6424->mute_gpio) {
+		gpiod_set_value_cansleep(tas6424->mute_gpio, mute);
+		return 0;
+	}
+
 	if (mute)
 		val = TAS6424_ALL_STATE_MUTE;
 	else
@@ -287,6 +298,12 @@ static int tas6424_power_on(struct snd_soc_component *component)
 {
 	struct tas6424_data *tas6424 = snd_soc_component_get_drvdata(component);
 	int ret;
+	u8 chan_states;
+	int no_auto_diags = 0;
+	unsigned int reg_val;
+
+	if (!regmap_read(tas6424->regmap, TAS6424_DC_DIAG_CTRL1, &reg_val))
+		no_auto_diags = reg_val & TAS6424_LDGBYPASS_MASK;
 
 	ret = regulator_bulk_enable(ARRAY_SIZE(tas6424->supplies),
 				    tas6424->supplies);
@@ -303,12 +320,25 @@ static int tas6424_power_on(struct snd_soc_component *component)
 		return ret;
 	}
 
-	snd_soc_component_write(component, TAS6424_CH_STATE_CTRL, TAS6424_ALL_STATE_MUTE);
+	if (tas6424->mute_gpio) {
+		gpiod_set_value_cansleep(tas6424->mute_gpio, 0);
+		/*
+		 * channels are muted via the mute pin.  Don't also mute
+		 * them via the registers so that subsequent register
+		 * access is not necessary to un-mute the channels
+		 */
+		chan_states = TAS6424_ALL_STATE_PLAY;
+	} else {
+		chan_states = TAS6424_ALL_STATE_MUTE;
+	}
+	snd_soc_component_write(component, TAS6424_CH_STATE_CTRL, chan_states);
 
 	/* any time we come out of HIZ, the output channels automatically run DC
-	 * load diagnostics, wait here until this completes
+	 * load diagnostics if autodiagnotics are enabled. wait here until this
+	 * completes.
 	 */
-	msleep(230);
+	if (!no_auto_diags)
+		msleep(230);
 
 	return 0;
 }
@@ -627,6 +657,38 @@ static int tas6424_i2c_probe(struct i2c_client *client,
 		return ret;
 	}
 
+	/*
+	 * Get control of the standby pin and set it LOW to take the codec
+	 * out of the stand-by mode.
+	 * Note: The actual pin polarity is taken care of in the GPIO lib
+	 * according the polarity specified in the DTS.
+	 */
+	tas6424->standby_gpio = devm_gpiod_get_optional(dev, "standby",
+						      GPIOD_OUT_LOW);
+	if (IS_ERR(tas6424->standby_gpio)) {
+		if (PTR_ERR(tas6424->standby_gpio) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_info(dev, "failed to get standby GPIO: %ld\n",
+			PTR_ERR(tas6424->standby_gpio));
+		tas6424->standby_gpio = NULL;
+	}
+
+	/*
+	 * Get control of the mute pin and set it HIGH in order to start with
+	 * all the output muted.
+	 * Note: The actual pin polarity is taken care of in the GPIO lib
+	 * according the polarity specified in the DTS.
+	 */
+	tas6424->mute_gpio = devm_gpiod_get_optional(dev, "mute",
+						      GPIOD_OUT_HIGH);
+	if (IS_ERR(tas6424->mute_gpio)) {
+		if (PTR_ERR(tas6424->mute_gpio) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_info(dev, "failed to get nmute GPIO: %ld\n",
+			PTR_ERR(tas6424->mute_gpio));
+		tas6424->mute_gpio = NULL;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(tas6424->supplies); i++)
 		tas6424->supplies[i].supply = tas6424_supply_names[i];
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(tas6424->supplies),
@@ -671,6 +733,10 @@ static int tas6424_i2c_remove(struct i2c_client *client)
 
 	cancel_delayed_work_sync(&tas6424->fault_check_work);
 
+	/* put the codec in stand-by */
+	if (tas6424->standby_gpio)
+		gpiod_set_value_cansleep(tas6424->standby_gpio, 1);
+
 	ret = regulator_bulk_disable(ARRAY_SIZE(tas6424->supplies),
 				     tas6424->supplies);
 	if (ret < 0) {
diff --git a/sound/soc/codecs/tas6424.h b/sound/soc/codecs/tas6424.h
index 430588328a06..b5958c45ed0e 100644
--- a/sound/soc/codecs/tas6424.h
+++ b/sound/soc/codecs/tas6424.h
@@ -111,6 +111,10 @@
 					 TAS6424_CH3_STATE_DIAG | \
 					 TAS6424_CH4_STATE_DIAG)
 
+/* TAS6424_DC_DIAG_CTRL1 */
+#define TAS6424_LDGBYPASS_SHIFT		0
+#define TAS6424_LDGBYPASS_MASK		BIT(TAS6424_LDGBYPASS_SHIFT)
+
 /* TAS6424_GLOB_FAULT1_REG */
 #define TAS6424_FAULT_CLOCK		BIT(4)
 #define TAS6424_FAULT_PVDD_OV		BIT(3)
diff --git a/sound/soc/codecs/tfa9879.c b/sound/soc/codecs/tfa9879.c
index 6d213c6d3920..abc114a3ae2b 100644
--- a/sound/soc/codecs/tfa9879.c
+++ b/sound/soc/codecs/tfa9879.c
@@ -1,15 +1,9 @@
-/*
- * tfa9879.c  --  driver for NXP Semiconductors TFA9879
- *
- * Copyright (C) 2014 Axentia Technologies AB
- * Author: Peter Rosin <peda@axentia.se>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// tfa9879.c  --  driver for NXP Semiconductors TFA9879
+//
+// Copyright (C) 2014 Axentia Technologies AB
+// Author: Peter Rosin <peda@axentia.se>
 
 #include <linux/module.h>
 #include <linux/init.h>
@@ -88,13 +82,14 @@ static int tfa9879_hw_params(struct snd_pcm_substream *substream,
 	}
 
 	if (tfa9879->lsb_justified)
-		snd_soc_component_update_bits(component, TFA9879_SERIAL_INTERFACE_1,
-				    TFA9879_I2S_SET_MASK,
-				    i2s_set << TFA9879_I2S_SET_SHIFT);
+		snd_soc_component_update_bits(component,
+					      TFA9879_SERIAL_INTERFACE_1,
+					      TFA9879_I2S_SET_MASK,
+					      i2s_set << TFA9879_I2S_SET_SHIFT);
 
 	snd_soc_component_update_bits(component, TFA9879_SERIAL_INTERFACE_1,
-			    TFA9879_I2S_FS_MASK,
-			    fs << TFA9879_I2S_FS_SHIFT);
+				      TFA9879_I2S_FS_MASK,
+				      fs << TFA9879_I2S_FS_SHIFT);
 	return 0;
 }
 
@@ -103,8 +98,8 @@ static int tfa9879_digital_mute(struct snd_soc_dai *dai, int mute)
 	struct snd_soc_component *component = dai->component;
 
 	snd_soc_component_update_bits(component, TFA9879_MISC_CONTROL,
-			    TFA9879_S_MUTE_MASK,
-			    !!mute << TFA9879_S_MUTE_SHIFT);
+				      TFA9879_S_MUTE_MASK,
+				      !!mute << TFA9879_S_MUTE_SHIFT);
 
 	return 0;
 }
@@ -152,11 +147,11 @@ static int tfa9879_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	}
 
 	snd_soc_component_update_bits(component, TFA9879_SERIAL_INTERFACE_1,
-			    TFA9879_SCK_POL_MASK,
-			    sck_pol << TFA9879_SCK_POL_SHIFT);
+				      TFA9879_SCK_POL_MASK,
+				      sck_pol << TFA9879_SCK_POL_SHIFT);
 	snd_soc_component_update_bits(component, TFA9879_SERIAL_INTERFACE_1,
-			    TFA9879_I2S_SET_MASK,
-			    i2s_set << TFA9879_I2S_SET_SHIFT);
+				      TFA9879_I2S_SET_MASK,
+				      i2s_set << TFA9879_I2S_SET_SHIFT);
 	return 0;
 }
 
@@ -276,8 +271,7 @@ static struct snd_soc_dai_driver tfa9879_dai = {
 	.ops = &tfa9879_dai_ops,
 };
 
-static int tfa9879_i2c_probe(struct i2c_client *i2c,
-			     const struct i2c_device_id *id)
+static int tfa9879_i2c_probe(struct i2c_client *i2c)
 {
 	struct tfa9879_priv *tfa9879;
 	int i;
@@ -298,7 +292,7 @@ static int tfa9879_i2c_probe(struct i2c_client *i2c,
 			     tfa9879_regs[i].reg, tfa9879_regs[i].def);
 
 	return devm_snd_soc_register_component(&i2c->dev, &tfa9879_component,
-				      &tfa9879_dai, 1);
+					       &tfa9879_dai, 1);
 }
 
 static const struct i2c_device_id tfa9879_i2c_id[] = {
@@ -318,7 +312,7 @@ static struct i2c_driver tfa9879_i2c_driver = {
 		.name = "tfa9879",
 		.of_match_table = tfa9879_of_match,
 	},
-	.probe = tfa9879_i2c_probe,
+	.probe_new = tfa9879_i2c_probe,
 	.id_table = tfa9879_i2c_id,
 };
 
diff --git a/sound/soc/codecs/tfa9879.h b/sound/soc/codecs/tfa9879.h
index 3408c90c4628..66c88d0396fe 100644
--- a/sound/soc/codecs/tfa9879.h
+++ b/sound/soc/codecs/tfa9879.h
@@ -1,14 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * tfa9879.h  --  driver for NXP Semiconductors TFA9879
  *
  * Copyright (C) 2014 Axentia Technologies AB
  * Author: Peter Rosin <peda@axentia.se>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
  */
 
 #ifndef _TFA9879_H
diff --git a/sound/soc/codecs/tscs42xx.c b/sound/soc/codecs/tscs42xx.c
index bbfc73a79b18..d18ff17719cc 100644
--- a/sound/soc/codecs/tscs42xx.c
+++ b/sound/soc/codecs/tscs42xx.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
+#include <linux/clk.h>
 #include <sound/tlv.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
@@ -31,7 +32,6 @@ struct tscs42xx {
 
 	int bclk_ratio;
 	int samplerate;
-	unsigned int blrcm;
 	struct mutex audio_params_lock;
 
 	u8 coeff_ram[COEFF_RAM_SIZE];
@@ -42,7 +42,8 @@ struct tscs42xx {
 
 	struct regmap *regmap;
 
-	struct device *dev;
+	struct clk *sysclk;
+	int sysclk_src_id;
 };
 
 struct coeff_ram_ctl {
@@ -204,7 +205,8 @@ static int power_up_audio_plls(struct snd_soc_component *component)
 		break;
 	default:
 		ret = -EINVAL;
-		dev_err(component->dev, "Unrecognized PLL output freq (%d)\n", ret);
+		dev_err(component->dev,
+				"Unrecognized PLL output freq (%d)\n", ret);
 		return ret;
 	}
 
@@ -261,7 +263,8 @@ exit:
 static int coeff_ram_get(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
+	struct snd_soc_component *component =
+		snd_soc_kcontrol_component(kcontrol);
 	struct tscs42xx *tscs42xx = snd_soc_component_get_drvdata(component);
 	struct coeff_ram_ctl *ctl =
 		(struct coeff_ram_ctl *)kcontrol->private_value;
@@ -280,7 +283,8 @@ static int coeff_ram_get(struct snd_kcontrol *kcontrol,
 static int coeff_ram_put(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
+	struct snd_soc_component *component =
+		snd_soc_kcontrol_component(kcontrol);
 	struct tscs42xx *tscs42xx = snd_soc_component_get_drvdata(component);
 	struct coeff_ram_ctl *ctl =
 		(struct coeff_ram_ctl *)kcontrol->private_value;
@@ -363,7 +367,8 @@ static int dapm_micb_event(struct snd_soc_dapm_widget *w,
 static int pll_event(struct snd_soc_dapm_widget *w,
 		     struct snd_kcontrol *kcontrol, int event)
 {
-	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
 	int ret;
 
 	if (SND_SOC_DAPM_EVENT_ON(event))
@@ -377,7 +382,8 @@ static int pll_event(struct snd_soc_dapm_widget *w,
 static int dac_event(struct snd_soc_dapm_widget *w,
 		     struct snd_kcontrol *kcontrol, int event)
 {
-	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
 	struct tscs42xx *tscs42xx = snd_soc_component_get_drvdata(component);
 	int ret;
 
@@ -819,16 +825,19 @@ static int setup_sample_format(struct snd_soc_component *component,
 		dev_err(component->dev, "Unsupported format width (%d)\n", ret);
 		return ret;
 	}
-	ret = snd_soc_component_update_bits(component, R_AIC1, RM_AIC1_WL, width);
+	ret = snd_soc_component_update_bits(component,
+			R_AIC1, RM_AIC1_WL, width);
 	if (ret < 0) {
-		dev_err(component->dev, "Failed to set sample width (%d)\n", ret);
+		dev_err(component->dev,
+				"Failed to set sample width (%d)\n", ret);
 		return ret;
 	}
 
 	return 0;
 }
 
-static int setup_sample_rate(struct snd_soc_component *component, unsigned int rate)
+static int setup_sample_rate(struct snd_soc_component *component,
+		unsigned int rate)
 {
 	struct tscs42xx *tscs42xx = snd_soc_component_get_drvdata(component);
 	unsigned int br, bm;
@@ -881,24 +890,32 @@ static int setup_sample_rate(struct snd_soc_component *component, unsigned int r
 	}
 
 	/* DAC and ADC share bit and frame clock */
-	ret = snd_soc_component_update_bits(component, R_DACSR, RM_DACSR_DBR, br);
+	ret = snd_soc_component_update_bits(component,
+			R_DACSR, RM_DACSR_DBR, br);
 	if (ret < 0) {
-		dev_err(component->dev, "Failed to update register (%d)\n", ret);
+		dev_err(component->dev,
+				"Failed to update register (%d)\n", ret);
 		return ret;
 	}
-	ret = snd_soc_component_update_bits(component, R_DACSR, RM_DACSR_DBM, bm);
+	ret = snd_soc_component_update_bits(component,
+			R_DACSR, RM_DACSR_DBM, bm);
 	if (ret < 0) {
-		dev_err(component->dev, "Failed to update register (%d)\n", ret);
+		dev_err(component->dev,
+				"Failed to update register (%d)\n", ret);
 		return ret;
 	}
-	ret = snd_soc_component_update_bits(component, R_ADCSR, RM_DACSR_DBR, br);
+	ret = snd_soc_component_update_bits(component,
+			R_ADCSR, RM_DACSR_DBR, br);
 	if (ret < 0) {
-		dev_err(component->dev, "Failed to update register (%d)\n", ret);
+		dev_err(component->dev,
+				"Failed to update register (%d)\n", ret);
 		return ret;
 	}
-	ret = snd_soc_component_update_bits(component, R_ADCSR, RM_DACSR_DBM, bm);
+	ret = snd_soc_component_update_bits(component,
+			R_ADCSR, RM_DACSR_DBM, bm);
 	if (ret < 0) {
-		dev_err(component->dev, "Failed to update register (%d)\n", ret);
+		dev_err(component->dev,
+				"Failed to update register (%d)\n", ret);
 		return ret;
 	}
 
@@ -1076,7 +1093,8 @@ static int tscs42xx_hw_params(struct snd_pcm_substream *substream,
 
 	ret = setup_sample_rate(component, params_rate(params));
 	if (ret < 0) {
-		dev_err(component->dev, "Failed to setup sample rate (%d)\n", ret);
+		dev_err(component->dev,
+				"Failed to setup sample rate (%d)\n", ret);
 		return ret;
 	}
 
@@ -1087,7 +1105,8 @@ static inline int dac_mute(struct snd_soc_component *component)
 {
 	int ret;
 
-	ret = snd_soc_component_update_bits(component, R_CNVRTR1, RM_CNVRTR1_DACMU,
+	ret = snd_soc_component_update_bits(component,
+			R_CNVRTR1, RM_CNVRTR1_DACMU,
 		RV_CNVRTR1_DACMU_ENABLE);
 	if (ret < 0) {
 		dev_err(component->dev, "Failed to mute DAC (%d)\n",
@@ -1102,7 +1121,8 @@ static inline int dac_unmute(struct snd_soc_component *component)
 {
 	int ret;
 
-	ret = snd_soc_component_update_bits(component, R_CNVRTR1, RM_CNVRTR1_DACMU,
+	ret = snd_soc_component_update_bits(component,
+			R_CNVRTR1, RM_CNVRTR1_DACMU,
 		RV_CNVRTR1_DACMU_DISABLE);
 	if (ret < 0) {
 		dev_err(component->dev, "Failed to unmute DAC (%d)\n",
@@ -1117,8 +1137,8 @@ static inline int adc_mute(struct snd_soc_component *component)
 {
 	int ret;
 
-	ret = snd_soc_component_update_bits(component, R_CNVRTR0, RM_CNVRTR0_ADCMU,
-		RV_CNVRTR0_ADCMU_ENABLE);
+	ret = snd_soc_component_update_bits(component,
+			R_CNVRTR0, RM_CNVRTR0_ADCMU, RV_CNVRTR0_ADCMU_ENABLE);
 	if (ret < 0) {
 		dev_err(component->dev, "Failed to mute ADC (%d)\n",
 				ret);
@@ -1132,8 +1152,8 @@ static inline int adc_unmute(struct snd_soc_component *component)
 {
 	int ret;
 
-	ret = snd_soc_component_update_bits(component, R_CNVRTR0, RM_CNVRTR0_ADCMU,
-		RV_CNVRTR0_ADCMU_DISABLE);
+	ret = snd_soc_component_update_bits(component,
+			R_CNVRTR0, RM_CNVRTR0_ADCMU, RV_CNVRTR0_ADCMU_DISABLE);
 	if (ret < 0) {
 		dev_err(component->dev, "Failed to unmute ADC (%d)\n",
 				ret);
@@ -1171,8 +1191,8 @@ static int tscs42xx_set_dai_fmt(struct snd_soc_dai *codec_dai,
 	/* Slave mode not supported since it needs always-on frame clock */
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBM_CFM:
-		ret = snd_soc_component_update_bits(component, R_AIC1, RM_AIC1_MS,
-				RV_AIC1_MS_MASTER);
+		ret = snd_soc_component_update_bits(component,
+				R_AIC1, RM_AIC1_MS, RV_AIC1_MS_MASTER);
 		if (ret < 0) {
 			dev_err(component->dev,
 				"Failed to set codec DAI master (%d)\n", ret);
@@ -1211,14 +1231,18 @@ static int tscs42xx_set_dai_bclk_ratio(struct snd_soc_dai *codec_dai,
 		return -EINVAL;
 	}
 
-	ret = snd_soc_component_update_bits(component, R_DACSR, RM_DACSR_DBCM, value);
+	ret = snd_soc_component_update_bits(component,
+			R_DACSR, RM_DACSR_DBCM, value);
 	if (ret < 0) {
-		dev_err(component->dev, "Failed to set DAC BCLK ratio (%d)\n", ret);
+		dev_err(component->dev,
+				"Failed to set DAC BCLK ratio (%d)\n", ret);
 		return ret;
 	}
-	ret = snd_soc_component_update_bits(component, R_ADCSR, RM_ADCSR_ABCM, value);
+	ret = snd_soc_component_update_bits(component,
+			R_ADCSR, RM_ADCSR_ABCM, value);
 	if (ret < 0) {
-		dev_err(component->dev, "Failed to set ADC BCLK ratio (%d)\n", ret);
+		dev_err(component->dev,
+				"Failed to set ADC BCLK ratio (%d)\n", ret);
 		return ret;
 	}
 
@@ -1231,13 +1255,46 @@ static int tscs42xx_set_dai_bclk_ratio(struct snd_soc_dai *codec_dai,
 	return 0;
 }
 
-static int tscs42xx_set_dai_sysclk(struct snd_soc_dai *codec_dai,
-	int clk_id, unsigned int freq, int dir)
+static const struct snd_soc_dai_ops tscs42xx_dai_ops = {
+	.hw_params	= tscs42xx_hw_params,
+	.mute_stream	= tscs42xx_mute_stream,
+	.set_fmt	= tscs42xx_set_dai_fmt,
+	.set_bclk_ratio = tscs42xx_set_dai_bclk_ratio,
+};
+
+static int part_is_valid(struct tscs42xx *tscs42xx)
 {
-	struct snd_soc_component *component = codec_dai->component;
+	int val;
 	int ret;
+	unsigned int reg;
+
+	ret = regmap_read(tscs42xx->regmap, R_DEVIDH, &reg);
+	if (ret < 0)
+		return ret;
+
+	val = reg << 8;
+	ret = regmap_read(tscs42xx->regmap, R_DEVIDL, &reg);
+	if (ret < 0)
+		return ret;
+
+	val |= reg;
+
+	switch (val) {
+	case 0x4A74:
+	case 0x4A73:
+		return true;
+	default:
+		return false;
+	};
+}
 
-	switch (clk_id) {
+static int set_sysclk(struct snd_soc_component *component)
+{
+	struct tscs42xx *tscs42xx = snd_soc_component_get_drvdata(component);
+	unsigned long freq;
+	int ret;
+
+	switch (tscs42xx->sysclk_src_id) {
 	case TSCS42XX_PLL_SRC_XTAL:
 	case TSCS42XX_PLL_SRC_MCLK1:
 		ret = snd_soc_component_write(component, R_PLLREFSEL,
@@ -1265,6 +1322,7 @@ static int tscs42xx_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 		return -EINVAL;
 	}
 
+	freq = clk_get_rate(tscs42xx->sysclk);
 	ret = set_pll_ctl_from_input_freq(component, freq);
 	if (ret < 0) {
 		dev_err(component->dev,
@@ -1275,41 +1333,13 @@ static int tscs42xx_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 	return 0;
 }
 
-static const struct snd_soc_dai_ops tscs42xx_dai_ops = {
-	.hw_params	= tscs42xx_hw_params,
-	.mute_stream	= tscs42xx_mute_stream,
-	.set_fmt	= tscs42xx_set_dai_fmt,
-	.set_bclk_ratio = tscs42xx_set_dai_bclk_ratio,
-	.set_sysclk	= tscs42xx_set_dai_sysclk,
-};
-
-static int part_is_valid(struct tscs42xx *tscs42xx)
+static int tscs42xx_probe(struct snd_soc_component *component)
 {
-	int val;
-	int ret;
-	unsigned int reg;
-
-	ret = regmap_read(tscs42xx->regmap, R_DEVIDH, &reg);
-	if (ret < 0)
-		return ret;
-
-	val = reg << 8;
-	ret = regmap_read(tscs42xx->regmap, R_DEVIDL, &reg);
-	if (ret < 0)
-		return ret;
-
-	val |= reg;
-
-	switch (val) {
-	case 0x4A74:
-	case 0x4A73:
-		return true;
-	default:
-		return false;
-	};
+	return set_sysclk(component);
 }
 
-static struct snd_soc_component_driver soc_codec_dev_tscs42xx = {
+static const struct snd_soc_component_driver soc_codec_dev_tscs42xx = {
+	.probe			= tscs42xx_probe,
 	.dapm_widgets		= tscs42xx_dapm_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(tscs42xx_dapm_widgets),
 	.dapm_routes		= tscs42xx_intercon,
@@ -1367,11 +1397,15 @@ static const struct reg_sequence tscs42xx_patch[] = {
 	{ R_AIC2, RV_AIC2_BLRCM_DAC_BCLK_LRCLK_SHARED },
 };
 
+static char const * const src_names[TSCS42XX_PLL_SRC_CNT] = {
+	"xtal", "mclk1", "mclk2"};
+
 static int tscs42xx_i2c_probe(struct i2c_client *i2c,
 		const struct i2c_device_id *id)
 {
 	struct tscs42xx *tscs42xx;
-	int ret = 0;
+	int src;
+	int ret;
 
 	tscs42xx = devm_kzalloc(&i2c->dev, sizeof(*tscs42xx), GFP_KERNEL);
 	if (!tscs42xx) {
@@ -1381,12 +1415,29 @@ static int tscs42xx_i2c_probe(struct i2c_client *i2c,
 		return ret;
 	}
 	i2c_set_clientdata(i2c, tscs42xx);
-	tscs42xx->dev = &i2c->dev;
+
+	for (src = TSCS42XX_PLL_SRC_XTAL; src < TSCS42XX_PLL_SRC_CNT; src++) {
+		tscs42xx->sysclk = devm_clk_get(&i2c->dev, src_names[src]);
+		if (!IS_ERR(tscs42xx->sysclk)) {
+			break;
+		} else if (PTR_ERR(tscs42xx->sysclk) != -ENOENT) {
+			ret = PTR_ERR(tscs42xx->sysclk);
+			dev_err(&i2c->dev, "Failed to get sysclk (%d)\n", ret);
+			return ret;
+		}
+	}
+	if (src == TSCS42XX_PLL_SRC_CNT) {
+		ret = -EINVAL;
+		dev_err(&i2c->dev, "Failed to get a valid clock name (%d)\n",
+				ret);
+		return ret;
+	}
+	tscs42xx->sysclk_src_id = src;
 
 	tscs42xx->regmap = devm_regmap_init_i2c(i2c, &tscs42xx_regmap);
 	if (IS_ERR(tscs42xx->regmap)) {
 		ret = PTR_ERR(tscs42xx->regmap);
-		dev_err(tscs42xx->dev, "Failed to allocate regmap (%d)\n", ret);
+		dev_err(&i2c->dev, "Failed to allocate regmap (%d)\n", ret);
 		return ret;
 	}
 
@@ -1394,21 +1445,21 @@ static int tscs42xx_i2c_probe(struct i2c_client *i2c,
 
 	ret = part_is_valid(tscs42xx);
 	if (ret <= 0) {
-		dev_err(tscs42xx->dev, "No valid part (%d)\n", ret);
+		dev_err(&i2c->dev, "No valid part (%d)\n", ret);
 		ret = -ENODEV;
 		return ret;
 	}
 
 	ret = regmap_write(tscs42xx->regmap, R_RESET, RV_RESET_ENABLE);
 	if (ret < 0) {
-		dev_err(tscs42xx->dev, "Failed to reset device (%d)\n", ret);
+		dev_err(&i2c->dev, "Failed to reset device (%d)\n", ret);
 		return ret;
 	}
 
 	ret = regmap_register_patch(tscs42xx->regmap, tscs42xx_patch,
 			ARRAY_SIZE(tscs42xx_patch));
 	if (ret < 0) {
-		dev_err(tscs42xx->dev, "Failed to apply patch (%d)\n", ret);
+		dev_err(&i2c->dev, "Failed to apply patch (%d)\n", ret);
 		return ret;
 	}
 
@@ -1416,10 +1467,10 @@ static int tscs42xx_i2c_probe(struct i2c_client *i2c,
 	mutex_init(&tscs42xx->coeff_ram_lock);
 	mutex_init(&tscs42xx->pll_lock);
 
-	ret = devm_snd_soc_register_component(tscs42xx->dev, &soc_codec_dev_tscs42xx,
-			&tscs42xx_dai, 1);
+	ret = devm_snd_soc_register_component(&i2c->dev,
+			&soc_codec_dev_tscs42xx, &tscs42xx_dai, 1);
 	if (ret) {
-		dev_err(tscs42xx->dev, "Failed to register codec (%d)\n", ret);
+		dev_err(&i2c->dev, "Failed to register codec (%d)\n", ret);
 		return ret;
 	}
 
diff --git a/sound/soc/codecs/tscs42xx.h b/sound/soc/codecs/tscs42xx.h
index d4a30bcbf64b..814c8f3c4a68 100644
--- a/sound/soc/codecs/tscs42xx.h
+++ b/sound/soc/codecs/tscs42xx.h
@@ -7,10 +7,10 @@
 #define __WOOKIE_H__
 
 enum {
-	TSCS42XX_PLL_SRC_NONE,
 	TSCS42XX_PLL_SRC_XTAL,
 	TSCS42XX_PLL_SRC_MCLK1,
 	TSCS42XX_PLL_SRC_MCLK2,
+	TSCS42XX_PLL_SRC_CNT,
 };
 
 #define R_HPVOLL        0x0
diff --git a/sound/soc/codecs/tscs454.c b/sound/soc/codecs/tscs454.c
new file mode 100644
index 000000000000..ff85a0bf6170
--- /dev/null
+++ b/sound/soc/codecs/tscs454.c
@@ -0,0 +1,3497 @@
+// SPDX-License-Identifier: GPL-2.0
+// tscs454.c -- TSCS454 ALSA SoC Audio driver
+// Copyright 2018 Tempo Semiconductor, Inc.
+// Author: Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
+
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/regmap.h>
+#include <linux/i2c.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/mutex.h>
+
+#include <sound/tlv.h>
+#include <sound/pcm_params.h>
+#include <sound/pcm.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+
+#include "tscs454.h"
+
+static const unsigned int PLL_48K_RATE = (48000 * 256);
+static const unsigned int PLL_44_1K_RATE = (44100 * 256);
+
+#define COEFF_SIZE 3
+#define BIQUAD_COEFF_COUNT 5
+#define BIQUAD_SIZE (COEFF_SIZE * BIQUAD_COEFF_COUNT)
+
+#define COEFF_RAM_MAX_ADDR 0xcd
+#define COEFF_RAM_COEFF_COUNT (COEFF_RAM_MAX_ADDR + 1)
+#define COEFF_RAM_SIZE (COEFF_SIZE * COEFF_RAM_COEFF_COUNT)
+
+enum {
+	TSCS454_DAI1_ID,
+	TSCS454_DAI2_ID,
+	TSCS454_DAI3_ID,
+	TSCS454_DAI_COUNT,
+};
+
+struct pll {
+	int id;
+	unsigned int users;
+	struct mutex lock;
+};
+
+static inline void pll_init(struct pll *pll, int id)
+{
+	pll->id = id;
+	mutex_init(&pll->lock);
+}
+
+struct internal_rate {
+	struct pll *pll;
+};
+
+struct aif {
+	unsigned int id;
+	bool master;
+	struct pll *pll;
+};
+
+static inline void aif_init(struct aif *aif, unsigned int id)
+{
+	aif->id = id;
+}
+
+struct coeff_ram {
+	u8 cache[COEFF_RAM_SIZE];
+	bool synced;
+	struct mutex lock;
+};
+
+static inline void init_coeff_ram_cache(u8 *cache)
+{
+	static const u8 norm_addrs[] = { 0x00, 0x05, 0x0a, 0x0f, 0x14, 0x19,
+		0x1f, 0x20, 0x25, 0x2a, 0x2f, 0x34, 0x39, 0x3f, 0x40, 0x45,
+		0x4a, 0x4f, 0x54, 0x59, 0x5f, 0x60, 0x65, 0x6a, 0x6f, 0x74,
+		0x79, 0x7f, 0x80, 0x85, 0x8c, 0x91, 0x96, 0x97, 0x9c, 0xa3,
+		0xa8, 0xad, 0xaf, 0xb0, 0xb5, 0xba, 0xbf, 0xc4, 0xc9};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(norm_addrs); i++)
+		cache[((norm_addrs[i] + 1) * COEFF_SIZE) - 1] = 0x40;
+}
+
+static inline void coeff_ram_init(struct coeff_ram *ram)
+{
+	init_coeff_ram_cache(ram->cache);
+	mutex_init(&ram->lock);
+}
+
+struct aifs_status {
+	u8 streams;
+};
+
+static inline void set_aif_status_active(struct aifs_status *status,
+		int aif_id, bool playback)
+{
+	u8 mask = 0x01 << (aif_id * 2 + !playback);
+
+	status->streams |= mask;
+}
+
+static inline void set_aif_status_inactive(struct aifs_status *status,
+		int aif_id, bool playback)
+{
+	u8 mask = ~(0x01 << (aif_id * 2 + !playback));
+
+	status->streams &= mask;
+}
+
+static bool aifs_active(struct aifs_status *status)
+{
+	return status->streams;
+}
+
+static bool aif_active(struct aifs_status *status, int aif_id)
+{
+	return (0x03 << aif_id * 2) & status->streams;
+}
+
+struct tscs454 {
+	struct regmap *regmap;
+	struct aif aifs[TSCS454_DAI_COUNT];
+
+	struct aifs_status aifs_status;
+	struct mutex aifs_status_lock;
+
+	struct pll pll1;
+	struct pll pll2;
+	struct internal_rate internal_rate;
+
+	struct coeff_ram dac_ram;
+	struct coeff_ram spk_ram;
+	struct coeff_ram sub_ram;
+
+	struct clk *sysclk;
+	int sysclk_src_id;
+	unsigned int bclk_freq;
+};
+
+struct coeff_ram_ctl {
+	unsigned int addr;
+	struct soc_bytes_ext bytes_ext;
+};
+
+static const struct reg_sequence tscs454_patch[] = {
+	/* Assign ASRC out of the box so DAI 1 just works */
+	{ R_AUDIOMUX1, FV_ASRCIMUX_I2S1 | FV_I2S2MUX_I2S2 },
+	{ R_AUDIOMUX2, FV_ASRCOMUX_I2S1 | FV_DACMUX_I2S1 | FV_I2S3MUX_I2S3 },
+	{ R_AUDIOMUX3, FV_CLSSDMUX_I2S1 | FV_SUBMUX_I2S1_LR },
+	{ R_TDMCTL0, FV_TDMMD_256 },
+	{ VIRT_ADDR(0x0A, 0x13), 1 << 3 },
+};
+
+static bool tscs454_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case R_PLLSTAT:
+
+	case R_SPKCRRDL:
+	case R_SPKCRRDM:
+	case R_SPKCRRDH:
+	case R_SPKCRS:
+
+	case R_DACCRRDL:
+	case R_DACCRRDM:
+	case R_DACCRRDH:
+	case R_DACCRS:
+
+	case R_SUBCRRDL:
+	case R_SUBCRRDM:
+	case R_SUBCRRDH:
+	case R_SUBCRS:
+		return true;
+	default:
+		return false;
+	};
+}
+
+static bool tscs454_writable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case R_SPKCRRDL:
+	case R_SPKCRRDM:
+	case R_SPKCRRDH:
+
+	case R_DACCRRDL:
+	case R_DACCRRDM:
+	case R_DACCRRDH:
+
+	case R_SUBCRRDL:
+	case R_SUBCRRDM:
+	case R_SUBCRRDH:
+		return false;
+	default:
+		return true;
+	};
+}
+
+static bool tscs454_readable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case R_SPKCRWDL:
+	case R_SPKCRWDM:
+	case R_SPKCRWDH:
+
+	case R_DACCRWDL:
+	case R_DACCRWDM:
+	case R_DACCRWDH:
+
+	case R_SUBCRWDL:
+	case R_SUBCRWDM:
+	case R_SUBCRWDH:
+		return false;
+	default:
+		return true;
+	};
+}
+
+static bool tscs454_precious(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case R_SPKCRWDL:
+	case R_SPKCRWDM:
+	case R_SPKCRWDH:
+	case R_SPKCRRDL:
+	case R_SPKCRRDM:
+	case R_SPKCRRDH:
+
+	case R_DACCRWDL:
+	case R_DACCRWDM:
+	case R_DACCRWDH:
+	case R_DACCRRDL:
+	case R_DACCRRDM:
+	case R_DACCRRDH:
+
+	case R_SUBCRWDL:
+	case R_SUBCRWDM:
+	case R_SUBCRWDH:
+	case R_SUBCRRDL:
+	case R_SUBCRRDM:
+	case R_SUBCRRDH:
+		return true;
+	default:
+		return false;
+	};
+}
+
+static const struct regmap_range_cfg tscs454_regmap_range_cfg = {
+	.name = "Pages",
+	.range_min = VIRT_BASE,
+	.range_max = VIRT_ADDR(0xFE, 0x02),
+	.selector_reg = R_PAGESEL,
+	.selector_mask = 0xff,
+	.selector_shift = 0,
+	.window_start = 0,
+	.window_len = 0x100,
+};
+
+static struct regmap_config const tscs454_regmap_cfg = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.writeable_reg = tscs454_writable,
+	.readable_reg = tscs454_readable,
+	.volatile_reg = tscs454_volatile,
+	.precious_reg = tscs454_precious,
+	.ranges = &tscs454_regmap_range_cfg,
+	.num_ranges = 1,
+	.max_register = VIRT_ADDR(0xFE, 0x02),
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static inline int tscs454_data_init(struct tscs454 *tscs454,
+		struct i2c_client *i2c)
+{
+	int i;
+	int ret;
+
+	tscs454->regmap = devm_regmap_init_i2c(i2c, &tscs454_regmap_cfg);
+	if (IS_ERR(tscs454->regmap)) {
+		ret = PTR_ERR(tscs454->regmap);
+		return ret;
+	}
+
+	for (i = 0; i < TSCS454_DAI_COUNT; i++)
+		aif_init(&tscs454->aifs[i], i);
+
+	mutex_init(&tscs454->aifs_status_lock);
+	pll_init(&tscs454->pll1, 1);
+	pll_init(&tscs454->pll2, 2);
+
+	coeff_ram_init(&tscs454->dac_ram);
+	coeff_ram_init(&tscs454->spk_ram);
+	coeff_ram_init(&tscs454->sub_ram);
+
+	return 0;
+}
+
+struct reg_setting {
+	unsigned int addr;
+	unsigned int val;
+};
+
+static int coeff_ram_get(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component =
+		snd_soc_kcontrol_component(kcontrol);
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	struct coeff_ram_ctl *ctl =
+		(struct coeff_ram_ctl *)kcontrol->private_value;
+	struct soc_bytes_ext *params = &ctl->bytes_ext;
+	u8 *coeff_ram;
+	struct mutex *coeff_ram_lock;
+
+	if (strstr(kcontrol->id.name, "DAC")) {
+		coeff_ram = tscs454->dac_ram.cache;
+		coeff_ram_lock = &tscs454->dac_ram.lock;
+	} else if (strstr(kcontrol->id.name, "Speaker")) {
+		coeff_ram = tscs454->spk_ram.cache;
+		coeff_ram_lock = &tscs454->spk_ram.lock;
+	} else if (strstr(kcontrol->id.name, "Sub")) {
+		coeff_ram = tscs454->sub_ram.cache;
+		coeff_ram_lock = &tscs454->sub_ram.lock;
+	} else {
+		return -EINVAL;
+	}
+
+	mutex_lock(coeff_ram_lock);
+
+	memcpy(ucontrol->value.bytes.data,
+		&coeff_ram[ctl->addr * COEFF_SIZE], params->max);
+
+	mutex_unlock(coeff_ram_lock);
+
+	return 0;
+}
+
+#define DACCRSTAT_MAX_TRYS 10
+static int write_coeff_ram(struct snd_soc_component *component, u8 *coeff_ram,
+		unsigned int r_stat, unsigned int r_addr, unsigned int r_wr,
+		unsigned int coeff_addr, unsigned int coeff_cnt)
+{
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	unsigned int val;
+	int cnt;
+	int trys;
+	int ret;
+
+	for (cnt = 0; cnt < coeff_cnt; cnt++, coeff_addr++) {
+
+		for (trys = 0; trys < DACCRSTAT_MAX_TRYS; trys++) {
+			ret = snd_soc_component_read(component, r_stat, &val);
+			if (ret < 0) {
+				dev_err(component->dev,
+					"Failed to read stat (%d)\n", ret);
+				return ret;
+			}
+			if (!val)
+				break;
+		}
+
+		if (trys == DACCRSTAT_MAX_TRYS) {
+			ret = -EIO;
+			dev_err(component->dev,
+				"Coefficient write error (%d)\n", ret);
+			return ret;
+		}
+
+		ret = regmap_write(tscs454->regmap, r_addr, coeff_addr);
+		if (ret < 0) {
+			dev_err(component->dev,
+				"Failed to write dac ram address (%d)\n", ret);
+			return ret;
+		}
+
+		ret = regmap_bulk_write(tscs454->regmap, r_wr,
+			&coeff_ram[coeff_addr * COEFF_SIZE],
+			COEFF_SIZE);
+		if (ret < 0) {
+			dev_err(component->dev,
+				"Failed to write dac ram (%d)\n", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int coeff_ram_put(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component =
+		snd_soc_kcontrol_component(kcontrol);
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	struct coeff_ram_ctl *ctl =
+		(struct coeff_ram_ctl *)kcontrol->private_value;
+	struct soc_bytes_ext *params = &ctl->bytes_ext;
+	unsigned int coeff_cnt = params->max / COEFF_SIZE;
+	u8 *coeff_ram;
+	struct mutex *coeff_ram_lock;
+	bool *coeff_ram_synced;
+	unsigned int r_stat;
+	unsigned int r_addr;
+	unsigned int r_wr;
+	unsigned int val;
+	int ret;
+
+	if (strstr(kcontrol->id.name, "DAC")) {
+		coeff_ram = tscs454->dac_ram.cache;
+		coeff_ram_lock = &tscs454->dac_ram.lock;
+		coeff_ram_synced = &tscs454->dac_ram.synced;
+		r_stat = R_DACCRS;
+		r_addr = R_DACCRADD;
+		r_wr = R_DACCRWDL;
+	} else if (strstr(kcontrol->id.name, "Speaker")) {
+		coeff_ram = tscs454->spk_ram.cache;
+		coeff_ram_lock = &tscs454->spk_ram.lock;
+		coeff_ram_synced = &tscs454->spk_ram.synced;
+		r_stat = R_SPKCRS;
+		r_addr = R_SPKCRADD;
+		r_wr = R_SPKCRWDL;
+	} else if (strstr(kcontrol->id.name, "Sub")) {
+		coeff_ram = tscs454->sub_ram.cache;
+		coeff_ram_lock = &tscs454->sub_ram.lock;
+		coeff_ram_synced = &tscs454->sub_ram.synced;
+		r_stat = R_SUBCRS;
+		r_addr = R_SUBCRADD;
+		r_wr = R_SUBCRWDL;
+	} else {
+		return -EINVAL;
+	}
+
+	mutex_lock(coeff_ram_lock);
+
+	*coeff_ram_synced = false;
+
+	memcpy(&coeff_ram[ctl->addr * COEFF_SIZE],
+		ucontrol->value.bytes.data, params->max);
+
+	mutex_lock(&tscs454->pll1.lock);
+	mutex_lock(&tscs454->pll2.lock);
+
+	ret = snd_soc_component_read(component, R_PLLSTAT, &val);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to read PLL status (%d)\n",
+				ret);
+		goto exit;
+	}
+	if (val) { /* PLLs locked */
+		ret = write_coeff_ram(component, coeff_ram,
+			r_stat, r_addr, r_wr,
+			ctl->addr, coeff_cnt);
+		if (ret < 0) {
+			dev_err(component->dev,
+				"Failed to flush coeff ram cache (%d)\n", ret);
+			goto exit;
+		}
+		*coeff_ram_synced = true;
+	}
+
+	ret = 0;
+exit:
+	mutex_unlock(&tscs454->pll2.lock);
+	mutex_unlock(&tscs454->pll1.lock);
+	mutex_unlock(coeff_ram_lock);
+
+	return ret;
+}
+
+static inline int coeff_ram_sync(struct snd_soc_component *component,
+		struct tscs454 *tscs454)
+{
+	int ret;
+
+	mutex_lock(&tscs454->dac_ram.lock);
+	if (!tscs454->dac_ram.synced) {
+		ret = write_coeff_ram(component, tscs454->dac_ram.cache,
+				R_DACCRS, R_DACCRADD, R_DACCRWDL,
+				0x00, COEFF_RAM_COEFF_COUNT);
+		if (ret < 0) {
+			mutex_unlock(&tscs454->dac_ram.lock);
+			return ret;
+		}
+	}
+	mutex_unlock(&tscs454->dac_ram.lock);
+
+	mutex_lock(&tscs454->spk_ram.lock);
+	if (!tscs454->spk_ram.synced) {
+		ret = write_coeff_ram(component, tscs454->spk_ram.cache,
+				R_SPKCRS, R_SPKCRADD, R_SPKCRWDL,
+				0x00, COEFF_RAM_COEFF_COUNT);
+		if (ret < 0) {
+			mutex_unlock(&tscs454->spk_ram.lock);
+			return ret;
+		}
+	}
+	mutex_unlock(&tscs454->spk_ram.lock);
+
+	mutex_lock(&tscs454->sub_ram.lock);
+	if (!tscs454->sub_ram.synced) {
+		ret = write_coeff_ram(component, tscs454->sub_ram.cache,
+				R_SUBCRS, R_SUBCRADD, R_SUBCRWDL,
+				0x00, COEFF_RAM_COEFF_COUNT);
+		if (ret < 0) {
+			mutex_unlock(&tscs454->sub_ram.lock);
+			return ret;
+		}
+	}
+	mutex_unlock(&tscs454->sub_ram.lock);
+
+	return 0;
+}
+
+#define PLL_REG_SETTINGS_COUNT 11
+struct pll_ctl {
+	int freq_in;
+	struct reg_setting settings[PLL_REG_SETTINGS_COUNT];
+};
+
+#define PLL_CTL(f, t, c1, r1, o1, f1l, f1h, c2, r2, o2, f2l, f2h)	\
+	{								\
+		.freq_in = f,						\
+		.settings = {						\
+			{R_PLL1CTL,	c1},				\
+			{R_PLL1RDIV,	r1},				\
+			{R_PLL1ODIV,	o1},				\
+			{R_PLL1FDIVL,	f1l},				\
+			{R_PLL1FDIVH,	f1h},				\
+			{R_PLL2CTL,	c2},				\
+			{R_PLL2RDIV,	r2},				\
+			{R_PLL2ODIV,	o2},				\
+			{R_PLL2FDIVL,	f2l},				\
+			{R_PLL2FDIVH,	f2h},				\
+			{R_TIMEBASE,	t},				\
+		},							\
+	}
+
+static const struct pll_ctl pll_ctls[] = {
+	PLL_CTL(1411200, 0x05,
+		0xB9, 0x07, 0x02, 0xC3, 0x04,
+		0x5A, 0x02, 0x03, 0xE0, 0x01),
+	PLL_CTL(1536000, 0x05,
+		0x5A, 0x02, 0x03, 0xE0, 0x01,
+		0x5A, 0x02, 0x03, 0xB9, 0x01),
+	PLL_CTL(2822400, 0x0A,
+		0x63, 0x07, 0x04, 0xC3, 0x04,
+		0x62, 0x07, 0x03, 0x48, 0x03),
+	PLL_CTL(3072000, 0x0B,
+		0x62, 0x07, 0x03, 0x48, 0x03,
+		0x5A, 0x04, 0x03, 0xB9, 0x01),
+	PLL_CTL(5644800, 0x15,
+		0x63, 0x0E, 0x04, 0xC3, 0x04,
+		0x5A, 0x08, 0x03, 0xE0, 0x01),
+	PLL_CTL(6144000, 0x17,
+		0x5A, 0x08, 0x03, 0xE0, 0x01,
+		0x5A, 0x08, 0x03, 0xB9, 0x01),
+	PLL_CTL(12000000, 0x2E,
+		0x5B, 0x19, 0x03, 0x00, 0x03,
+		0x6A, 0x19, 0x05, 0x98, 0x04),
+	PLL_CTL(19200000, 0x4A,
+		0x53, 0x14, 0x03, 0x80, 0x01,
+		0x5A, 0x19, 0x03, 0xB9, 0x01),
+	PLL_CTL(22000000, 0x55,
+		0x6A, 0x37, 0x05, 0x00, 0x06,
+		0x62, 0x26, 0x03, 0x49, 0x02),
+	PLL_CTL(22579200, 0x57,
+		0x62, 0x31, 0x03, 0x20, 0x03,
+		0x53, 0x1D, 0x03, 0xB3, 0x01),
+	PLL_CTL(24000000, 0x5D,
+		0x53, 0x19, 0x03, 0x80, 0x01,
+		0x5B, 0x19, 0x05, 0x4C, 0x02),
+	PLL_CTL(24576000, 0x5F,
+		0x53, 0x1D, 0x03, 0xB3, 0x01,
+		0x62, 0x40, 0x03, 0x72, 0x03),
+	PLL_CTL(27000000, 0x68,
+		0x62, 0x4B, 0x03, 0x00, 0x04,
+		0x6A, 0x7D, 0x03, 0x20, 0x06),
+	PLL_CTL(36000000, 0x8C,
+		0x5B, 0x4B, 0x03, 0x00, 0x03,
+		0x6A, 0x7D, 0x03, 0x98, 0x04),
+	PLL_CTL(11289600, 0x2B,
+		0x6A, 0x31, 0x03, 0x40, 0x06,
+		0x5A, 0x12, 0x03, 0x1C, 0x02),
+	PLL_CTL(26000000, 0x65,
+		0x63, 0x41, 0x05, 0x00, 0x06,
+		0x5A, 0x26, 0x03, 0xEF, 0x01),
+	PLL_CTL(12288000, 0x2F,
+		0x5A, 0x12, 0x03, 0x1C, 0x02,
+		0x62, 0x20, 0x03, 0x72, 0x03),
+	PLL_CTL(40000000, 0x9B,
+		0xA2, 0x7D, 0x03, 0x80, 0x04,
+		0x63, 0x7D, 0x05, 0xE4, 0x06),
+	PLL_CTL(512000, 0x01,
+		0x62, 0x01, 0x03, 0xD0, 0x02,
+		0x5B, 0x01, 0x04, 0x72, 0x03),
+	PLL_CTL(705600, 0x02,
+		0x62, 0x02, 0x03, 0x15, 0x04,
+		0x62, 0x01, 0x04, 0x80, 0x02),
+	PLL_CTL(1024000, 0x03,
+		0x62, 0x02, 0x03, 0xD0, 0x02,
+		0x5B, 0x02, 0x04, 0x72, 0x03),
+	PLL_CTL(2048000, 0x07,
+		0x62, 0x04, 0x03, 0xD0, 0x02,
+		0x5B, 0x04, 0x04, 0x72, 0x03),
+	PLL_CTL(2400000, 0x08,
+		0x62, 0x05, 0x03, 0x00, 0x03,
+		0x63, 0x05, 0x05, 0x98, 0x04),
+};
+
+static inline const struct pll_ctl *get_pll_ctl(unsigned long freq_in)
+{
+	int i;
+	struct pll_ctl const *pll_ctl = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(pll_ctls); ++i)
+		if (pll_ctls[i].freq_in == freq_in) {
+			pll_ctl = &pll_ctls[i];
+			break;
+		}
+
+	return pll_ctl;
+}
+
+enum {
+	PLL_INPUT_XTAL = 0,
+	PLL_INPUT_MCLK1,
+	PLL_INPUT_MCLK2,
+	PLL_INPUT_BCLK,
+};
+
+static int set_sysclk(struct snd_soc_component *component)
+{
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	struct pll_ctl const *pll_ctl;
+	unsigned long freq;
+	int i;
+	int ret;
+
+	if (tscs454->sysclk_src_id < PLL_INPUT_BCLK)
+		freq = clk_get_rate(tscs454->sysclk);
+	else
+		freq = tscs454->bclk_freq;
+	pll_ctl = get_pll_ctl(freq);
+	if (!pll_ctl) {
+		ret = -EINVAL;
+		dev_err(component->dev,
+				"Invalid PLL input %lu (%d)\n", freq, ret);
+		return ret;
+	}
+
+	for (i = 0; i < PLL_REG_SETTINGS_COUNT; ++i) {
+		ret = snd_soc_component_write(component,
+				pll_ctl->settings[i].addr,
+				pll_ctl->settings[i].val);
+		if (ret < 0) {
+			dev_err(component->dev,
+					"Failed to set pll setting (%d)\n",
+					ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static inline void reserve_pll(struct pll *pll)
+{
+	mutex_lock(&pll->lock);
+	pll->users++;
+	mutex_unlock(&pll->lock);
+}
+
+static inline void free_pll(struct pll *pll)
+{
+	mutex_lock(&pll->lock);
+	pll->users--;
+	mutex_unlock(&pll->lock);
+}
+
+static int pll_connected(struct snd_soc_dapm_widget *source,
+		struct snd_soc_dapm_widget *sink)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(source->dapm);
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	int users;
+
+	if (strstr(source->name, "PLL 1")) {
+		mutex_lock(&tscs454->pll1.lock);
+		users = tscs454->pll1.users;
+		mutex_unlock(&tscs454->pll1.lock);
+		dev_dbg(component->dev, "%s(): PLL 1 users = %d\n", __func__,
+				users);
+	} else {
+		mutex_lock(&tscs454->pll2.lock);
+		users = tscs454->pll2.users;
+		mutex_unlock(&tscs454->pll2.lock);
+		dev_dbg(component->dev, "%s(): PLL 2 users = %d\n", __func__,
+				users);
+	}
+
+	return users;
+}
+
+/*
+ * PLL must be enabled after power up and must be disabled before power down
+ * for proper clock switching.
+ */
+static int pll_power_event(struct snd_soc_dapm_widget *w,
+		struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	bool enable;
+	bool pll1;
+	unsigned int msk;
+	unsigned int val;
+	int ret;
+
+	if (strstr(w->name, "PLL 1"))
+		pll1 = true;
+	else
+		pll1 = false;
+
+	msk = pll1 ? FM_PLLCTL_PLL1CLKEN : FM_PLLCTL_PLL2CLKEN;
+
+	if (event == SND_SOC_DAPM_POST_PMU)
+		enable = true;
+	else
+		enable = false;
+
+	if (enable)
+		val = pll1 ? FV_PLL1CLKEN_ENABLE : FV_PLL2CLKEN_ENABLE;
+	else
+		val = pll1 ? FV_PLL1CLKEN_DISABLE : FV_PLL2CLKEN_DISABLE;
+
+	ret = snd_soc_component_update_bits(component, R_PLLCTL, msk, val);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to %s PLL %d  (%d)\n",
+				enable ? "enable" : "disable",
+				pll1 ? 1 : 2,
+				ret);
+		return ret;
+	}
+
+	if (enable) {
+		msleep(20); // Wait for lock
+		ret = coeff_ram_sync(component, tscs454);
+		if (ret < 0) {
+			dev_err(component->dev,
+					"Failed to sync coeff ram (%d)\n", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static inline int aif_set_master(struct snd_soc_component *component,
+		unsigned int aif_id, bool master)
+{
+	unsigned int reg;
+	unsigned int mask;
+	unsigned int val;
+	int ret;
+
+	switch (aif_id) {
+	case TSCS454_DAI1_ID:
+		reg = R_I2SP1CTL;
+		break;
+	case TSCS454_DAI2_ID:
+		reg = R_I2SP2CTL;
+		break;
+	case TSCS454_DAI3_ID:
+		reg = R_I2SP3CTL;
+		break;
+	default:
+		ret = -ENODEV;
+		dev_err(component->dev, "Unknown DAI %d (%d)\n", aif_id, ret);
+		return ret;
+	}
+	mask = FM_I2SPCTL_PORTMS;
+	val = master ? FV_PORTMS_MASTER : FV_PORTMS_SLAVE;
+
+	ret = snd_soc_component_update_bits(component, reg, mask, val);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to set DAI %d to %s (%d)\n",
+			aif_id, master ? "master" : "slave", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline
+int aif_prepare(struct snd_soc_component *component, struct aif *aif)
+{
+	int ret;
+
+	ret = aif_set_master(component, aif->id, aif->master);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static inline int aif_free(struct snd_soc_component *component,
+		struct aif *aif, bool playback)
+{
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+
+	mutex_lock(&tscs454->aifs_status_lock);
+
+	dev_dbg(component->dev, "%s(): aif %d\n", __func__, aif->id);
+
+	set_aif_status_inactive(&tscs454->aifs_status, aif->id, playback);
+
+	dev_dbg(component->dev, "Set aif %d inactive. Streams status is 0x%x\n",
+		aif->id, tscs454->aifs_status.streams);
+
+	if (!aif_active(&tscs454->aifs_status, aif->id)) {
+		/* Do config in slave mode */
+		aif_set_master(component, aif->id, false);
+		dev_dbg(component->dev, "Freeing pll %d from aif %d\n",
+				aif->pll->id, aif->id);
+		free_pll(aif->pll);
+	}
+
+	if (!aifs_active(&tscs454->aifs_status)) {
+		dev_dbg(component->dev, "Freeing pll %d from ir\n",
+				tscs454->internal_rate.pll->id);
+		free_pll(tscs454->internal_rate.pll);
+	}
+
+	mutex_unlock(&tscs454->aifs_status_lock);
+
+	return 0;
+}
+
+/* R_PLLCTL PG 0 ADDR 0x15 */
+static char const * const bclk_sel_txt[] = {
+		"BCLK 1", "BCLK 2", "BCLK 3"};
+
+static struct soc_enum const bclk_sel_enum =
+		SOC_ENUM_SINGLE(R_PLLCTL, FB_PLLCTL_BCLKSEL,
+				ARRAY_SIZE(bclk_sel_txt), bclk_sel_txt);
+
+/* R_ISRC PG 0 ADDR 0x16 */
+static char const * const isrc_br_txt[] = {
+		"44.1kHz", "48kHz"};
+
+static struct soc_enum const isrc_br_enum =
+		SOC_ENUM_SINGLE(R_ISRC, FB_ISRC_IBR,
+				ARRAY_SIZE(isrc_br_txt), isrc_br_txt);
+
+static char const * const isrc_bm_txt[] = {
+		"0.25x", "0.5x", "1.0x", "2.0x"};
+
+static struct soc_enum const isrc_bm_enum =
+		SOC_ENUM_SINGLE(R_ISRC, FB_ISRC_IBM,
+				ARRAY_SIZE(isrc_bm_txt), isrc_bm_txt);
+
+/* R_SCLKCTL PG 0 ADDR 0x18 */
+static char const * const modular_rate_txt[] = {
+	"Reserved", "Half", "Full", "Auto",};
+
+static struct soc_enum const adc_modular_rate_enum =
+	SOC_ENUM_SINGLE(R_SCLKCTL, FB_SCLKCTL_ASDM,
+			ARRAY_SIZE(modular_rate_txt), modular_rate_txt);
+
+static struct soc_enum const dac_modular_rate_enum =
+	SOC_ENUM_SINGLE(R_SCLKCTL, FB_SCLKCTL_DSDM,
+			ARRAY_SIZE(modular_rate_txt), modular_rate_txt);
+
+/* R_I2SIDCTL PG 0 ADDR 0x38 */
+static char const * const data_ctrl_txt[] = {
+	"L/R", "L/L", "R/R", "R/L"};
+
+static struct soc_enum const data_in_ctrl_enums[] = {
+	SOC_ENUM_SINGLE(R_I2SIDCTL, FB_I2SIDCTL_I2SI1DCTL,
+			ARRAY_SIZE(data_ctrl_txt), data_ctrl_txt),
+	SOC_ENUM_SINGLE(R_I2SIDCTL, FB_I2SIDCTL_I2SI2DCTL,
+			ARRAY_SIZE(data_ctrl_txt), data_ctrl_txt),
+	SOC_ENUM_SINGLE(R_I2SIDCTL, FB_I2SIDCTL_I2SI3DCTL,
+			ARRAY_SIZE(data_ctrl_txt), data_ctrl_txt),
+};
+
+/* R_I2SODCTL PG 0 ADDR 0x39 */
+static struct soc_enum const data_out_ctrl_enums[] = {
+	SOC_ENUM_SINGLE(R_I2SODCTL, FB_I2SODCTL_I2SO1DCTL,
+			ARRAY_SIZE(data_ctrl_txt), data_ctrl_txt),
+	SOC_ENUM_SINGLE(R_I2SODCTL, FB_I2SODCTL_I2SO2DCTL,
+			ARRAY_SIZE(data_ctrl_txt), data_ctrl_txt),
+	SOC_ENUM_SINGLE(R_I2SODCTL, FB_I2SODCTL_I2SO3DCTL,
+			ARRAY_SIZE(data_ctrl_txt), data_ctrl_txt),
+};
+
+/* R_AUDIOMUX1 PG 0 ADDR 0x3A */
+static char const * const asrc_mux_txt[] = {
+		"None", "DAI 1", "DAI 2", "DAI 3"};
+
+static struct soc_enum const asrc_in_mux_enum =
+		SOC_ENUM_SINGLE(R_AUDIOMUX1, FB_AUDIOMUX1_ASRCIMUX,
+				ARRAY_SIZE(asrc_mux_txt), asrc_mux_txt);
+
+static char const * const dai_mux_txt[] = {
+		"CH 0_1", "CH 2_3", "CH 4_5", "ADC/DMic 1",
+		"DMic 2", "ClassD", "DAC", "Sub"};
+
+static struct soc_enum const dai2_mux_enum =
+		SOC_ENUM_SINGLE(R_AUDIOMUX1, FB_AUDIOMUX1_I2S2MUX,
+				ARRAY_SIZE(dai_mux_txt), dai_mux_txt);
+
+static struct snd_kcontrol_new const dai2_mux_dapm_enum =
+		SOC_DAPM_ENUM("DAI 2 Mux",  dai2_mux_enum);
+
+static struct soc_enum const dai1_mux_enum =
+		SOC_ENUM_SINGLE(R_AUDIOMUX1, FB_AUDIOMUX1_I2S1MUX,
+				ARRAY_SIZE(dai_mux_txt), dai_mux_txt);
+
+static struct snd_kcontrol_new const dai1_mux_dapm_enum =
+		SOC_DAPM_ENUM("DAI 1 Mux", dai1_mux_enum);
+
+/* R_AUDIOMUX2 PG 0 ADDR 0x3B */
+static struct soc_enum const asrc_out_mux_enum =
+		SOC_ENUM_SINGLE(R_AUDIOMUX2, FB_AUDIOMUX2_ASRCOMUX,
+				ARRAY_SIZE(asrc_mux_txt), asrc_mux_txt);
+
+static struct soc_enum const dac_mux_enum =
+		SOC_ENUM_SINGLE(R_AUDIOMUX2, FB_AUDIOMUX2_DACMUX,
+				ARRAY_SIZE(dai_mux_txt), dai_mux_txt);
+
+static struct snd_kcontrol_new const dac_mux_dapm_enum =
+		SOC_DAPM_ENUM("DAC Mux", dac_mux_enum);
+
+static struct soc_enum const dai3_mux_enum =
+		SOC_ENUM_SINGLE(R_AUDIOMUX2, FB_AUDIOMUX2_I2S3MUX,
+				ARRAY_SIZE(dai_mux_txt), dai_mux_txt);
+
+static struct snd_kcontrol_new const dai3_mux_dapm_enum =
+		SOC_DAPM_ENUM("DAI 3 Mux", dai3_mux_enum);
+
+/* R_AUDIOMUX3 PG 0 ADDR 0x3C */
+static char const * const sub_mux_txt[] = {
+		"CH 0", "CH 1", "CH 0 + 1",
+		"CH 2", "CH 3", "CH 2 + 3",
+		"CH 4", "CH 5", "CH 4 + 5",
+		"ADC/DMic 1 Left", "ADC/DMic 1 Right",
+		"ADC/DMic 1 Left Plus Right",
+		"DMic 2 Left", "DMic 2 Right", "DMic 2 Left Plus Right",
+		"ClassD Left", "ClassD Right", "ClassD Left Plus Right"};
+
+static struct soc_enum const sub_mux_enum =
+		SOC_ENUM_SINGLE(R_AUDIOMUX3, FB_AUDIOMUX3_SUBMUX,
+				ARRAY_SIZE(sub_mux_txt), sub_mux_txt);
+
+static struct snd_kcontrol_new const sub_mux_dapm_enum =
+		SOC_DAPM_ENUM("Sub Mux", sub_mux_enum);
+
+static struct soc_enum const classd_mux_enum =
+		SOC_ENUM_SINGLE(R_AUDIOMUX3, FB_AUDIOMUX3_CLSSDMUX,
+				ARRAY_SIZE(dai_mux_txt), dai_mux_txt);
+
+static struct snd_kcontrol_new const classd_mux_dapm_enum =
+		SOC_DAPM_ENUM("ClassD Mux", classd_mux_enum);
+
+/* R_HSDCTL1 PG 1 ADDR 0x01 */
+static char const * const jack_type_txt[] = {
+		"3 Terminal", "4 Terminal"};
+
+static struct soc_enum const hp_jack_type_enum =
+		SOC_ENUM_SINGLE(R_HSDCTL1, FB_HSDCTL1_HPJKTYPE,
+				ARRAY_SIZE(jack_type_txt), jack_type_txt);
+
+static char const * const hs_det_pol_txt[] = {
+		"Rising", "Falling"};
+
+static struct soc_enum const hs_det_pol_enum =
+		SOC_ENUM_SINGLE(R_HSDCTL1, FB_HSDCTL1_HSDETPOL,
+				ARRAY_SIZE(hs_det_pol_txt), hs_det_pol_txt);
+
+/* R_HSDCTL1 PG 1 ADDR 0x02 */
+static char const * const hs_mic_bias_force_txt[] = {
+		"Off", "Ring", "Sleeve"};
+
+static struct soc_enum const hs_mic_bias_force_enum =
+		SOC_ENUM_SINGLE(R_HSDCTL2, FB_HSDCTL2_FMICBIAS1,
+				ARRAY_SIZE(hs_mic_bias_force_txt),
+				hs_mic_bias_force_txt);
+
+static char const * const plug_type_txt[] = {
+		"OMTP", "CTIA", "Reserved", "Headphone"};
+
+static struct soc_enum const plug_type_force_enum =
+		SOC_ENUM_SINGLE(R_HSDCTL2, FB_HSDCTL2_FPLUGTYPE,
+		ARRAY_SIZE(plug_type_txt), plug_type_txt);
+
+
+/* R_CH0AIC PG 1 ADDR 0x06 */
+static char const * const in_bst_mux_txt[] = {
+		"Input 1", "Input 2", "Input 3", "D2S"};
+
+static struct soc_enum const in_bst_mux_ch0_enum =
+		SOC_ENUM_SINGLE(R_CH0AIC, FB_CH0AIC_INSELL,
+				ARRAY_SIZE(in_bst_mux_txt),
+				in_bst_mux_txt);
+static struct snd_kcontrol_new const in_bst_mux_ch0_dapm_enum =
+		SOC_DAPM_ENUM("Input Boost Channel 0 Enum",
+				in_bst_mux_ch0_enum);
+
+static DECLARE_TLV_DB_SCALE(in_bst_vol_tlv_arr, 0, 1000, 0);
+
+static char const * const adc_mux_txt[] = {
+		"Input 1 Boost Bypass", "Input 2 Boost Bypass",
+		"Input 3 Boost Bypass", "Input Boost"};
+
+static struct soc_enum const adc_mux_ch0_enum =
+		SOC_ENUM_SINGLE(R_CH0AIC, FB_CH0AIC_LADCIN,
+				ARRAY_SIZE(adc_mux_txt), adc_mux_txt);
+static struct snd_kcontrol_new const adc_mux_ch0_dapm_enum =
+		SOC_DAPM_ENUM("ADC Channel 0 Enum", adc_mux_ch0_enum);
+
+static char const * const in_proc_mux_txt[] = {
+		"ADC", "DMic"};
+
+static struct soc_enum const in_proc_ch0_enum =
+		SOC_ENUM_SINGLE(R_CH0AIC, FB_CH0AIC_IPCH0S,
+				ARRAY_SIZE(in_proc_mux_txt), in_proc_mux_txt);
+static struct snd_kcontrol_new const in_proc_mux_ch0_dapm_enum =
+		SOC_DAPM_ENUM("Input Processor Channel 0 Enum",
+				in_proc_ch0_enum);
+
+/* R_CH1AIC PG 1 ADDR 0x07 */
+static struct soc_enum const in_bst_mux_ch1_enum =
+		SOC_ENUM_SINGLE(R_CH1AIC, FB_CH1AIC_INSELR,
+				ARRAY_SIZE(in_bst_mux_txt),
+				in_bst_mux_txt);
+static struct snd_kcontrol_new const in_bst_mux_ch1_dapm_enum =
+		SOC_DAPM_ENUM("Input Boost Channel 1 Enum",
+				in_bst_mux_ch1_enum);
+
+static struct soc_enum const adc_mux_ch1_enum =
+		SOC_ENUM_SINGLE(R_CH1AIC, FB_CH1AIC_RADCIN,
+				ARRAY_SIZE(adc_mux_txt), adc_mux_txt);
+static struct snd_kcontrol_new const adc_mux_ch1_dapm_enum =
+		SOC_DAPM_ENUM("ADC Channel 1 Enum", adc_mux_ch1_enum);
+
+static struct soc_enum const in_proc_ch1_enum =
+		SOC_ENUM_SINGLE(R_CH1AIC, FB_CH1AIC_IPCH1S,
+				ARRAY_SIZE(in_proc_mux_txt), in_proc_mux_txt);
+static struct snd_kcontrol_new const in_proc_mux_ch1_dapm_enum =
+		SOC_DAPM_ENUM("Input Processor Channel 1 Enum",
+				in_proc_ch1_enum);
+
+/* R_ICTL0 PG 1 ADDR 0x0A */
+static char const * const pol_txt[] = {
+		"Normal", "Invert"};
+
+static struct soc_enum const in_pol_ch1_enum =
+		SOC_ENUM_SINGLE(R_ICTL0, FB_ICTL0_IN0POL,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+static struct soc_enum const in_pol_ch0_enum =
+		SOC_ENUM_SINGLE(R_ICTL0, FB_ICTL0_IN1POL,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+static char const * const in_proc_ch_sel_txt[] = {
+		"Normal", "Mono Mix to Channel 0",
+		"Mono Mix to Channel 1", "Add"};
+
+static struct soc_enum const in_proc_ch01_sel_enum =
+		SOC_ENUM_SINGLE(R_ICTL0, FB_ICTL0_INPCH10SEL,
+				ARRAY_SIZE(in_proc_ch_sel_txt),
+				in_proc_ch_sel_txt);
+
+/* R_ICTL1 PG 1 ADDR 0x0B */
+static struct soc_enum const in_pol_ch3_enum =
+		SOC_ENUM_SINGLE(R_ICTL1, FB_ICTL1_IN2POL,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+static struct soc_enum const in_pol_ch2_enum =
+		SOC_ENUM_SINGLE(R_ICTL1, FB_ICTL1_IN3POL,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+static struct soc_enum const in_proc_ch23_sel_enum =
+		SOC_ENUM_SINGLE(R_ICTL1, FB_ICTL1_INPCH32SEL,
+				ARRAY_SIZE(in_proc_ch_sel_txt),
+				in_proc_ch_sel_txt);
+
+/* R_MICBIAS PG 1 ADDR 0x0C */
+static char const * const mic_bias_txt[] = {
+		"2.5V", "2.1V", "1.8V", "Vdd"};
+
+static struct soc_enum const mic_bias_2_enum =
+		SOC_ENUM_SINGLE(R_MICBIAS, FB_MICBIAS_MICBOV2,
+				ARRAY_SIZE(mic_bias_txt), mic_bias_txt);
+
+static struct soc_enum const mic_bias_1_enum =
+		SOC_ENUM_SINGLE(R_MICBIAS, FB_MICBIAS_MICBOV1,
+				ARRAY_SIZE(mic_bias_txt), mic_bias_txt);
+
+/* R_PGACTL0 PG 1 ADDR 0x0D */
+/* R_PGACTL1 PG 1 ADDR 0x0E */
+/* R_PGACTL2 PG 1 ADDR 0x0F */
+/* R_PGACTL3 PG 1 ADDR 0x10 */
+static DECLARE_TLV_DB_SCALE(in_pga_vol_tlv_arr, -1725, 75, 0);
+
+/* R_ICH0VOL PG1 ADDR 0x12 */
+/* R_ICH1VOL PG1 ADDR 0x13 */
+/* R_ICH2VOL PG1 ADDR 0x14 */
+/* R_ICH3VOL PG1 ADDR 0x15 */
+static DECLARE_TLV_DB_MINMAX(in_vol_tlv_arr, -7125, 2400);
+
+/* R_ASRCILVOL PG1 ADDR 0x16 */
+/* R_ASRCIRVOL PG1 ADDR 0x17 */
+/* R_ASRCOLVOL PG1 ADDR 0x18 */
+/* R_ASRCORVOL PG1 ADDR 0x19 */
+static DECLARE_TLV_DB_MINMAX(asrc_vol_tlv_arr, -9562, 600);
+
+/* R_ALCCTL0 PG1 ADDR 0x1D */
+static char const * const alc_mode_txt[] = {
+		"ALC", "Limiter"};
+
+static struct soc_enum const alc_mode_enum =
+		SOC_ENUM_SINGLE(R_ALCCTL0, FB_ALCCTL0_ALCMODE,
+				ARRAY_SIZE(alc_mode_txt), alc_mode_txt);
+
+static char const * const alc_ref_text[] = {
+		"Channel 0", "Channel 1", "Channel 2", "Channel 3", "Peak"};
+
+static struct soc_enum const alc_ref_enum =
+		SOC_ENUM_SINGLE(R_ALCCTL0, FB_ALCCTL0_ALCREF,
+				ARRAY_SIZE(alc_ref_text), alc_ref_text);
+
+/* R_ALCCTL1 PG 1 ADDR 0x1E */
+static DECLARE_TLV_DB_SCALE(alc_max_gain_tlv_arr, -1200, 600, 0);
+static DECLARE_TLV_DB_SCALE(alc_target_tlv_arr, -2850, 150, 0);
+
+/* R_ALCCTL2 PG 1 ADDR 0x1F */
+static DECLARE_TLV_DB_SCALE(alc_min_gain_tlv_arr, -1725, 600, 0);
+
+/* R_NGATE PG 1 ADDR 0x21 */
+static DECLARE_TLV_DB_SCALE(ngth_tlv_arr, -7650, 150, 0);
+
+static char const * const ngate_type_txt[] = {
+		"PGA Constant", "ADC Mute"};
+
+static struct soc_enum const ngate_type_enum =
+		SOC_ENUM_SINGLE(R_NGATE, FB_NGATE_NGG,
+				ARRAY_SIZE(ngate_type_txt), ngate_type_txt);
+
+/* R_DMICCTL PG 1 ADDR 0x22 */
+static char const * const dmic_mono_sel_txt[] = {
+		"Stereo", "Mono"};
+
+static struct soc_enum const dmic_mono_sel_enum =
+		SOC_ENUM_SINGLE(R_DMICCTL, FB_DMICCTL_DMONO,
+			ARRAY_SIZE(dmic_mono_sel_txt), dmic_mono_sel_txt);
+
+/* R_DACCTL PG 2 ADDR 0x01 */
+static struct soc_enum const dac_pol_r_enum =
+		SOC_ENUM_SINGLE(R_DACCTL, FB_DACCTL_DACPOLR,
+			ARRAY_SIZE(pol_txt), pol_txt);
+
+static struct soc_enum const dac_pol_l_enum =
+		SOC_ENUM_SINGLE(R_DACCTL, FB_DACCTL_DACPOLL,
+			ARRAY_SIZE(pol_txt), pol_txt);
+
+static char const * const dac_dith_txt[] = {
+		"Half", "Full", "Disabled", "Static"};
+
+static struct soc_enum const dac_dith_enum =
+		SOC_ENUM_SINGLE(R_DACCTL, FB_DACCTL_DACDITH,
+			ARRAY_SIZE(dac_dith_txt), dac_dith_txt);
+
+/* R_SPKCTL PG 2 ADDR 0x02 */
+static struct soc_enum const spk_pol_r_enum =
+		SOC_ENUM_SINGLE(R_SPKCTL, FB_SPKCTL_SPKPOLR,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+static struct soc_enum const spk_pol_l_enum =
+		SOC_ENUM_SINGLE(R_SPKCTL, FB_SPKCTL_SPKPOLL,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_SUBCTL PG 2 ADDR 0x03 */
+static struct soc_enum const sub_pol_enum =
+		SOC_ENUM_SINGLE(R_SUBCTL, FB_SUBCTL_SUBPOL,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_MVOLL PG 2 ADDR 0x08 */
+/* R_MVOLR PG 2 ADDR 0x09 */
+static DECLARE_TLV_DB_MINMAX(mvol_tlv_arr, -9562, 0);
+
+/* R_HPVOLL PG 2 ADDR 0x0A */
+/* R_HPVOLR PG 2 ADDR 0x0B */
+static DECLARE_TLV_DB_SCALE(hp_vol_tlv_arr, -8850, 75, 0);
+
+/* R_SPKVOLL PG 2 ADDR 0x0C */
+/* R_SPKVOLR PG 2 ADDR 0x0D */
+static DECLARE_TLV_DB_SCALE(spk_vol_tlv_arr, -7725, 75, 0);
+
+/* R_SPKEQFILT PG 3 ADDR 0x01 */
+static char const * const eq_txt[] = {
+	"Pre Scale",
+	"Pre Scale + EQ Band 0",
+	"Pre Scale + EQ Band 0 - 1",
+	"Pre Scale + EQ Band 0 - 2",
+	"Pre Scale + EQ Band 0 - 3",
+	"Pre Scale + EQ Band 0 - 4",
+	"Pre Scale + EQ Band 0 - 5",
+};
+
+static struct soc_enum const spk_eq_enums[] = {
+	SOC_ENUM_SINGLE(R_SPKEQFILT, FB_SPKEQFILT_EQ2BE,
+		ARRAY_SIZE(eq_txt), eq_txt),
+	SOC_ENUM_SINGLE(R_SPKEQFILT, FB_SPKEQFILT_EQ1BE,
+		ARRAY_SIZE(eq_txt), eq_txt),
+};
+
+/* R_SPKMBCCTL PG 3 ADDR 0x0B */
+static char const * const lvl_mode_txt[] = {
+		"Average", "Peak"};
+
+static struct soc_enum const spk_mbc3_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCCTL, FB_SPKMBCCTL_LVLMODE3,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static char const * const win_sel_txt[] = {
+		"512", "64"};
+
+static struct soc_enum const spk_mbc3_win_sel_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCCTL, FB_SPKMBCCTL_WINSEL3,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+static struct soc_enum const spk_mbc2_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCCTL, FB_SPKMBCCTL_LVLMODE2,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const spk_mbc2_win_sel_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCCTL, FB_SPKMBCCTL_WINSEL2,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+static struct soc_enum const spk_mbc1_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCCTL, FB_SPKMBCCTL_LVLMODE1,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const spk_mbc1_win_sel_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCCTL, FB_SPKMBCCTL_WINSEL1,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+/* R_SPKMBCMUG1 PG 3 ADDR 0x0C */
+static struct soc_enum const spk_mbc1_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCMUG1, FB_SPKMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+static DECLARE_TLV_DB_MINMAX(mbc_mug_tlv_arr, -4650, 0);
+
+/* R_SPKMBCTHR1 PG 3 ADDR 0x0D */
+static DECLARE_TLV_DB_MINMAX(thr_tlv_arr, -9562, 0);
+
+/* R_SPKMBCRAT1 PG 3 ADDR 0x0E */
+static char const * const comp_rat_txt[] = {
+		"Reserved", "1.5:1", "2:1", "3:1", "4:1", "5:1", "6:1",
+		"7:1", "8:1", "9:1", "10:1", "11:1", "12:1", "13:1", "14:1",
+		"15:1", "16:1", "17:1", "18:1", "19:1", "20:1"};
+
+static struct soc_enum const spk_mbc1_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCRAT1, FB_SPKMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_SPKMBCMUG2 PG 3 ADDR 0x13 */
+static struct soc_enum const spk_mbc2_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCMUG2, FB_SPKMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_SPKMBCRAT2 PG 3 ADDR 0x15 */
+static struct soc_enum const spk_mbc2_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCRAT2, FB_SPKMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_SPKMBCMUG3 PG 3 ADDR 0x1A */
+static struct soc_enum const spk_mbc3_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCMUG3, FB_SPKMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_SPKMBCRAT3 PG 3 ADDR 0x1C */
+static struct soc_enum const spk_mbc3_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_SPKMBCRAT3, FB_SPKMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_SPKCLECTL PG 3 ADDR 0x21 */
+static struct soc_enum const spk_cle_lvl_mode_enum =
+		SOC_ENUM_SINGLE(R_SPKCLECTL, FB_SPKCLECTL_LVLMODE,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const spk_cle_win_sel_enum =
+		SOC_ENUM_SINGLE(R_SPKCLECTL, FB_SPKCLECTL_WINSEL,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+/* R_SPKCLEMUG PG 3 ADDR 0x22 */
+static DECLARE_TLV_DB_MINMAX(cle_mug_tlv_arr, 0, 4650);
+
+/* R_SPKCOMPRAT PG 3 ADDR 0x24 */
+static struct soc_enum const spk_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_SPKCOMPRAT, FB_SPKCOMPRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_SPKEXPTHR PG 3 ADDR 0x2F */
+static char const * const exp_rat_txt[] = {
+		"Reserved", "Reserved", "1:2", "1:3",
+		"1:4", "1:5", "1:6", "1:7"};
+
+static struct soc_enum const spk_exp_rat_enum =
+		SOC_ENUM_SINGLE(R_SPKEXPRAT, FB_SPKEXPRAT_RATIO,
+				ARRAY_SIZE(exp_rat_txt), exp_rat_txt);
+
+/* R_DACEQFILT PG 4 ADDR 0x01 */
+static struct soc_enum const dac_eq_enums[] = {
+	SOC_ENUM_SINGLE(R_DACEQFILT, FB_DACEQFILT_EQ2BE,
+		ARRAY_SIZE(eq_txt), eq_txt),
+	SOC_ENUM_SINGLE(R_DACEQFILT, FB_DACEQFILT_EQ1BE,
+		ARRAY_SIZE(eq_txt), eq_txt),
+};
+
+/* R_DACMBCCTL PG 4 ADDR 0x0B */
+static struct soc_enum const dac_mbc3_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_DACMBCCTL, FB_DACMBCCTL_LVLMODE3,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const dac_mbc3_win_sel_enum =
+		SOC_ENUM_SINGLE(R_DACMBCCTL, FB_DACMBCCTL_WINSEL3,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+static struct soc_enum const dac_mbc2_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_DACMBCCTL, FB_DACMBCCTL_LVLMODE2,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const dac_mbc2_win_sel_enum =
+		SOC_ENUM_SINGLE(R_DACMBCCTL, FB_DACMBCCTL_WINSEL2,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+static struct soc_enum const dac_mbc1_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_DACMBCCTL, FB_DACMBCCTL_LVLMODE1,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const dac_mbc1_win_sel_enum =
+		SOC_ENUM_SINGLE(R_DACMBCCTL, FB_DACMBCCTL_WINSEL1,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+/* R_DACMBCMUG1 PG 4 ADDR 0x0C */
+static struct soc_enum const dac_mbc1_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_DACMBCMUG1, FB_DACMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_DACMBCRAT1 PG 4 ADDR 0x0E */
+static struct soc_enum const dac_mbc1_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_DACMBCRAT1, FB_DACMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_DACMBCMUG2 PG 4 ADDR 0x13 */
+static struct soc_enum const dac_mbc2_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_DACMBCMUG2, FB_DACMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_DACMBCRAT2 PG 4 ADDR 0x15 */
+static struct soc_enum const dac_mbc2_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_DACMBCRAT2, FB_DACMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_DACMBCMUG3 PG 4 ADDR 0x1A */
+static struct soc_enum const dac_mbc3_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_DACMBCMUG3, FB_DACMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_DACMBCRAT3 PG 4 ADDR 0x1C */
+static struct soc_enum const dac_mbc3_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_DACMBCRAT3, FB_DACMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_DACCLECTL PG 4 ADDR 0x21 */
+static struct soc_enum const dac_cle_lvl_mode_enum =
+		SOC_ENUM_SINGLE(R_DACCLECTL, FB_DACCLECTL_LVLMODE,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const dac_cle_win_sel_enum =
+		SOC_ENUM_SINGLE(R_DACCLECTL, FB_DACCLECTL_WINSEL,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+/* R_DACCOMPRAT PG 4 ADDR 0x24 */
+static struct soc_enum const dac_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_DACCOMPRAT, FB_DACCOMPRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_DACEXPRAT PG 4 ADDR 0x30 */
+static struct soc_enum const dac_exp_rat_enum =
+		SOC_ENUM_SINGLE(R_DACEXPRAT, FB_DACEXPRAT_RATIO,
+				ARRAY_SIZE(exp_rat_txt), exp_rat_txt);
+
+/* R_SUBEQFILT PG 5 ADDR 0x01 */
+static struct soc_enum const sub_eq_enums[] = {
+	SOC_ENUM_SINGLE(R_SUBEQFILT, FB_SUBEQFILT_EQ2BE,
+		ARRAY_SIZE(eq_txt), eq_txt),
+	SOC_ENUM_SINGLE(R_SUBEQFILT, FB_SUBEQFILT_EQ1BE,
+		ARRAY_SIZE(eq_txt), eq_txt),
+};
+
+/* R_SUBMBCCTL PG 5 ADDR 0x0B */
+static struct soc_enum const sub_mbc3_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCCTL, FB_SUBMBCCTL_LVLMODE3,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const sub_mbc3_win_sel_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCCTL, FB_SUBMBCCTL_WINSEL3,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+static struct soc_enum const sub_mbc2_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCCTL, FB_SUBMBCCTL_LVLMODE2,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const sub_mbc2_win_sel_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCCTL, FB_SUBMBCCTL_WINSEL2,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+static struct soc_enum const sub_mbc1_lvl_det_mode_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCCTL, FB_SUBMBCCTL_LVLMODE1,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+
+static struct soc_enum const sub_mbc1_win_sel_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCCTL, FB_SUBMBCCTL_WINSEL1,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+/* R_SUBMBCMUG1 PG 5 ADDR 0x0C */
+static struct soc_enum const sub_mbc1_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCMUG1, FB_SUBMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_SUBMBCRAT1 PG 5 ADDR 0x0E */
+static struct soc_enum const sub_mbc1_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCRAT1, FB_SUBMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_SUBMBCMUG2 PG 5 ADDR 0x13 */
+static struct soc_enum const sub_mbc2_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCMUG2, FB_SUBMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_SUBMBCRAT2 PG 5 ADDR 0x15 */
+static struct soc_enum const sub_mbc2_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCRAT2, FB_SUBMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_SUBMBCMUG3 PG 5 ADDR 0x1A */
+static struct soc_enum const sub_mbc3_phase_pol_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCMUG3, FB_SUBMBCMUG_PHASE,
+				ARRAY_SIZE(pol_txt), pol_txt);
+
+/* R_SUBMBCRAT3 PG 5 ADDR 0x1C */
+static struct soc_enum const sub_mbc3_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_SUBMBCRAT3, FB_SUBMBCRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_SUBCLECTL PG 5 ADDR 0x21 */
+static struct soc_enum const sub_cle_lvl_mode_enum =
+		SOC_ENUM_SINGLE(R_SUBCLECTL, FB_SUBCLECTL_LVLMODE,
+				ARRAY_SIZE(lvl_mode_txt), lvl_mode_txt);
+static struct soc_enum const sub_cle_win_sel_enum =
+		SOC_ENUM_SINGLE(R_SUBCLECTL, FB_SUBCLECTL_WINSEL,
+				ARRAY_SIZE(win_sel_txt), win_sel_txt);
+
+/* R_SUBCOMPRAT PG 5 ADDR 0x24 */
+static struct soc_enum const sub_comp_rat_enum =
+		SOC_ENUM_SINGLE(R_SUBCOMPRAT, FB_SUBCOMPRAT_RATIO,
+				ARRAY_SIZE(comp_rat_txt), comp_rat_txt);
+
+/* R_SUBEXPRAT PG 5 ADDR 0x30 */
+static struct soc_enum const sub_exp_rat_enum =
+		SOC_ENUM_SINGLE(R_SUBEXPRAT, FB_SUBEXPRAT_RATIO,
+				ARRAY_SIZE(exp_rat_txt), exp_rat_txt);
+
+static int bytes_info_ext(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_info *ucontrol)
+{
+	struct coeff_ram_ctl *ctl =
+		(struct coeff_ram_ctl *)kcontrol->private_value;
+	struct soc_bytes_ext *params = &ctl->bytes_ext;
+
+	ucontrol->type = SNDRV_CTL_ELEM_TYPE_BYTES;
+	ucontrol->count = params->max;
+
+	return 0;
+}
+
+/* CH 0_1 Input Mux */
+static char const * const ch_0_1_mux_txt[] = {"DAI 1", "TDM 0_1"};
+
+static struct soc_enum const ch_0_1_mux_enum =
+		SOC_ENUM_SINGLE(SND_SOC_NOPM, 0,
+				ARRAY_SIZE(ch_0_1_mux_txt), ch_0_1_mux_txt);
+
+static struct snd_kcontrol_new const ch_0_1_mux_dapm_enum =
+		SOC_DAPM_ENUM("CH 0_1 Input Mux", ch_0_1_mux_enum);
+
+/* CH 2_3 Input Mux */
+static char const * const ch_2_3_mux_txt[] = {"DAI 2", "TDM 2_3"};
+
+static struct soc_enum const ch_2_3_mux_enum =
+		SOC_ENUM_SINGLE(SND_SOC_NOPM, 0,
+				ARRAY_SIZE(ch_2_3_mux_txt), ch_2_3_mux_txt);
+
+static struct snd_kcontrol_new const ch_2_3_mux_dapm_enum =
+		SOC_DAPM_ENUM("CH 2_3 Input Mux", ch_2_3_mux_enum);
+
+/* CH 4_5 Input Mux */
+static char const * const ch_4_5_mux_txt[] = {"DAI 3", "TDM 4_5"};
+
+static struct soc_enum const ch_4_5_mux_enum =
+		SOC_ENUM_SINGLE(SND_SOC_NOPM, 0,
+				ARRAY_SIZE(ch_4_5_mux_txt), ch_4_5_mux_txt);
+
+static struct snd_kcontrol_new const ch_4_5_mux_dapm_enum =
+		SOC_DAPM_ENUM("CH 4_5 Input Mux", ch_4_5_mux_enum);
+
+#define COEFF_RAM_CTL(xname, xcount, xaddr) \
+{	.iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \
+	.info = bytes_info_ext, \
+	.get = coeff_ram_get, .put = coeff_ram_put, \
+	.private_value = (unsigned long)&(struct coeff_ram_ctl) { \
+		.addr = xaddr, \
+		.bytes_ext = {.max = xcount, }, \
+	} \
+}
+
+static struct snd_kcontrol_new const tscs454_snd_controls[] = {
+	/* R_PLLCTL PG 0 ADDR 0x15 */
+	SOC_ENUM("PLL BCLK Input", bclk_sel_enum),
+	/* R_ISRC PG 0 ADDR 0x16 */
+	SOC_ENUM("Internal Rate", isrc_br_enum),
+	SOC_ENUM("Internal Rate Multiple", isrc_bm_enum),
+	/* R_SCLKCTL PG 0 ADDR 0x18 */
+	SOC_ENUM("ADC Modular Rate", adc_modular_rate_enum),
+	SOC_ENUM("DAC Modular Rate", dac_modular_rate_enum),
+	/* R_ASRC PG 0 ADDR 0x28 */
+	SOC_SINGLE("ASRC Out High Bandwidth Switch",
+			R_ASRC, FB_ASRC_ASRCOBW, 1, 0),
+	SOC_SINGLE("ASRC In High Bandwidth Switch",
+			R_ASRC, FB_ASRC_ASRCIBW, 1, 0),
+	/* R_I2SIDCTL PG 0 ADDR 0x38 */
+	SOC_ENUM("I2S 1 Data In Control", data_in_ctrl_enums[0]),
+	SOC_ENUM("I2S 2 Data In Control", data_in_ctrl_enums[1]),
+	SOC_ENUM("I2S 3 Data In Control", data_in_ctrl_enums[2]),
+	/* R_I2SODCTL PG 0 ADDR 0x39 */
+	SOC_ENUM("I2S 1 Data Out Control", data_out_ctrl_enums[0]),
+	SOC_ENUM("I2S 2 Data Out Control", data_out_ctrl_enums[1]),
+	SOC_ENUM("I2S 3 Data Out Control", data_out_ctrl_enums[2]),
+	/* R_AUDIOMUX1 PG 0 ADDR 0x3A */
+	SOC_ENUM("ASRC In", asrc_in_mux_enum),
+	/* R_AUDIOMUX2 PG 0 ADDR 0x3B */
+	SOC_ENUM("ASRC Out", asrc_out_mux_enum),
+	/* R_HSDCTL1 PG 1 ADDR 0x01 */
+	SOC_ENUM("Headphone Jack Type", hp_jack_type_enum),
+	SOC_ENUM("Headset Detection Polarity", hs_det_pol_enum),
+	SOC_SINGLE("Headphone Detection Switch",
+			R_HSDCTL1, FB_HSDCTL1_HPID_EN, 1, 0),
+	SOC_SINGLE("Headset OMTP/CTIA Switch",
+			R_HSDCTL1, FB_HSDCTL1_GBLHS_EN, 1, 0),
+	/* R_HSDCTL1 PG 1 ADDR 0x02 */
+	SOC_ENUM("Headset Mic Bias Force", hs_mic_bias_force_enum),
+	SOC_SINGLE("Manual Mic Bias Switch",
+			R_HSDCTL2, FB_HSDCTL2_MB1MODE, 1, 0),
+	SOC_SINGLE("Ring/Sleeve Auto Switch",
+			R_HSDCTL2, FB_HSDCTL2_SWMODE, 1, 0),
+	SOC_ENUM("Manual Mode Plug Type", plug_type_force_enum),
+	/* R_CH0AIC PG 1 ADDR 0x06 */
+	SOC_SINGLE_TLV("Input Boost Channel 0 Volume", R_CH0AIC,
+			FB_CHAIC_MICBST, 0x3, 0, in_bst_vol_tlv_arr),
+	/* R_CH1AIC PG 1 ADDR 0x07 */
+	SOC_SINGLE_TLV("Input Boost Channel 1 Volume", R_CH1AIC,
+			FB_CHAIC_MICBST, 0x3, 0, in_bst_vol_tlv_arr),
+	/* R_CH2AIC PG 1 ADDR 0x08 */
+	SOC_SINGLE_TLV("Input Boost Channel 2 Volume", R_CH2AIC,
+			FB_CHAIC_MICBST, 0x3, 0, in_bst_vol_tlv_arr),
+	/* R_CH3AIC PG 1 ADDR 0x09 */
+	SOC_SINGLE_TLV("Input Boost Channel 3 Volume", R_CH3AIC,
+			FB_CHAIC_MICBST, 0x3, 0, in_bst_vol_tlv_arr),
+	/* R_ICTL0 PG 1 ADDR 0x0A */
+	SOC_ENUM("Input Channel 1 Polarity", in_pol_ch1_enum),
+	SOC_ENUM("Input Channel 0 Polarity", in_pol_ch0_enum),
+	SOC_ENUM("Input Processor Channel 0/1 Operation",
+			in_proc_ch01_sel_enum),
+	SOC_SINGLE("Input Channel 1 Mute Switch",
+			R_ICTL0, FB_ICTL0_IN1MUTE, 1, 0),
+	SOC_SINGLE("Input Channel 0 Mute Switch",
+			R_ICTL0, FB_ICTL0_IN0MUTE, 1, 0),
+	SOC_SINGLE("Input Channel 1 HPF Disable Switch",
+			R_ICTL0, FB_ICTL0_IN1HP, 1, 0),
+	SOC_SINGLE("Input Channel 0 HPF Disable Switch",
+			R_ICTL0, FB_ICTL0_IN0HP, 1, 0),
+	/* R_ICTL1 PG 1 ADDR 0x0B */
+	SOC_ENUM("Input Channel 3 Polarity", in_pol_ch3_enum),
+	SOC_ENUM("Input Channel 2 Polarity", in_pol_ch2_enum),
+	SOC_ENUM("Input Processor Channel 2/3 Operation",
+			in_proc_ch23_sel_enum),
+	SOC_SINGLE("Input Channel 3 Mute Switch",
+			R_ICTL1, FB_ICTL1_IN3MUTE, 1, 0),
+	SOC_SINGLE("Input Channel 2 Mute Switch",
+			R_ICTL1, FB_ICTL1_IN2MUTE, 1, 0),
+	SOC_SINGLE("Input Channel 3 HPF Disable Switch",
+			R_ICTL1, FB_ICTL1_IN3HP, 1, 0),
+	SOC_SINGLE("Input Channel 2 HPF Disable Switch",
+			R_ICTL1, FB_ICTL1_IN2HP, 1, 0),
+	/* R_MICBIAS PG 1 ADDR 0x0C */
+	SOC_ENUM("Mic Bias 2 Voltage", mic_bias_2_enum),
+	SOC_ENUM("Mic Bias 1 Voltage", mic_bias_1_enum),
+	/* R_PGACTL0 PG 1 ADDR 0x0D */
+	SOC_SINGLE("Input Channel 0 PGA Mute Switch",
+			R_PGACTL0, FB_PGACTL_PGAMUTE, 1, 0),
+	SOC_SINGLE_TLV("Input Channel 0 PGA Volume", R_PGACTL0,
+			FB_PGACTL_PGAVOL,
+			FM_PGACTL_PGAVOL, 0, in_pga_vol_tlv_arr),
+	/* R_PGACTL1 PG 1 ADDR 0x0E */
+	SOC_SINGLE("Input Channel 1 PGA Mute Switch",
+			R_PGACTL1, FB_PGACTL_PGAMUTE, 1, 0),
+	SOC_SINGLE_TLV("Input Channel 1 PGA Volume", R_PGACTL1,
+			FB_PGACTL_PGAVOL,
+			FM_PGACTL_PGAVOL, 0, in_pga_vol_tlv_arr),
+	/* R_PGACTL2 PG 1 ADDR 0x0F */
+	SOC_SINGLE("Input Channel 2 PGA Mute Switch",
+			R_PGACTL2, FB_PGACTL_PGAMUTE, 1, 0),
+	SOC_SINGLE_TLV("Input Channel 2 PGA Volume", R_PGACTL2,
+			FB_PGACTL_PGAVOL,
+			FM_PGACTL_PGAVOL, 0, in_pga_vol_tlv_arr),
+	/* R_PGACTL3 PG 1 ADDR 0x10 */
+	SOC_SINGLE("Input Channel 3 PGA Mute Switch",
+			R_PGACTL3, FB_PGACTL_PGAMUTE, 1, 0),
+	SOC_SINGLE_TLV("Input Channel 3 PGA Volume", R_PGACTL3,
+			FB_PGACTL_PGAVOL,
+			FM_PGACTL_PGAVOL, 0, in_pga_vol_tlv_arr),
+	/* R_ICH0VOL PG 1 ADDR 0x12 */
+	SOC_SINGLE_TLV("Input Channel 0 Volume", R_ICH0VOL,
+			FB_ICHVOL_ICHVOL, FM_ICHVOL_ICHVOL, 0, in_vol_tlv_arr),
+	/* R_ICH1VOL PG 1 ADDR 0x13 */
+	SOC_SINGLE_TLV("Input Channel 1 Volume", R_ICH1VOL,
+			FB_ICHVOL_ICHVOL, FM_ICHVOL_ICHVOL, 0, in_vol_tlv_arr),
+	/* R_ICH2VOL PG 1 ADDR 0x14 */
+	SOC_SINGLE_TLV("Input Channel 2 Volume", R_ICH2VOL,
+			FB_ICHVOL_ICHVOL, FM_ICHVOL_ICHVOL, 0, in_vol_tlv_arr),
+	/* R_ICH3VOL PG 1 ADDR 0x15 */
+	SOC_SINGLE_TLV("Input Channel 3 Volume", R_ICH3VOL,
+			FB_ICHVOL_ICHVOL, FM_ICHVOL_ICHVOL, 0, in_vol_tlv_arr),
+	/* R_ASRCILVOL PG 1 ADDR 0x16 */
+	SOC_SINGLE_TLV("ASRC Input Left Volume", R_ASRCILVOL,
+			FB_ASRCILVOL_ASRCILVOL, FM_ASRCILVOL_ASRCILVOL,
+			0, asrc_vol_tlv_arr),
+	/* R_ASRCIRVOL PG 1 ADDR 0x17 */
+	SOC_SINGLE_TLV("ASRC Input Right Volume", R_ASRCIRVOL,
+			FB_ASRCIRVOL_ASRCIRVOL, FM_ASRCIRVOL_ASRCIRVOL,
+			0, asrc_vol_tlv_arr),
+	/* R_ASRCOLVOL PG 1 ADDR 0x18 */
+	SOC_SINGLE_TLV("ASRC Output Left Volume", R_ASRCOLVOL,
+			FB_ASRCOLVOL_ASRCOLVOL, FM_ASRCOLVOL_ASRCOLVOL,
+			0, asrc_vol_tlv_arr),
+	/* R_ASRCORVOL PG 1 ADDR 0x19 */
+	SOC_SINGLE_TLV("ASRC Output Right Volume", R_ASRCORVOL,
+			FB_ASRCORVOL_ASRCOLVOL, FM_ASRCORVOL_ASRCOLVOL,
+			0, asrc_vol_tlv_arr),
+	/* R_IVOLCTLU PG 1 ADDR 0x1C */
+	/* R_ALCCTL0 PG 1 ADDR 0x1D */
+	SOC_ENUM("ALC Mode", alc_mode_enum),
+	SOC_ENUM("ALC Reference", alc_ref_enum),
+	SOC_SINGLE("Input Channel 3 ALC Switch",
+			R_ALCCTL0, FB_ALCCTL0_ALCEN3, 1, 0),
+	SOC_SINGLE("Input Channel 2 ALC Switch",
+			R_ALCCTL0, FB_ALCCTL0_ALCEN2, 1, 0),
+	SOC_SINGLE("Input Channel 1 ALC Switch",
+			R_ALCCTL0, FB_ALCCTL0_ALCEN1, 1, 0),
+	SOC_SINGLE("Input Channel 0 ALC Switch",
+			R_ALCCTL0, FB_ALCCTL0_ALCEN0, 1, 0),
+	/* R_ALCCTL1 PG 1 ADDR 0x1E */
+	SOC_SINGLE_TLV("ALC Max Gain Volume", R_ALCCTL1,
+			FB_ALCCTL1_MAXGAIN, FM_ALCCTL1_MAXGAIN,
+			0, alc_max_gain_tlv_arr),
+	SOC_SINGLE_TLV("ALC Target Volume", R_ALCCTL1,
+			FB_ALCCTL1_ALCL, FM_ALCCTL1_ALCL,
+			0, alc_target_tlv_arr),
+	/* R_ALCCTL2 PG 1 ADDR 0x1F */
+	SOC_SINGLE("ALC Zero Cross Switch",
+			R_ALCCTL2, FB_ALCCTL2_ALCZC, 1, 0),
+	SOC_SINGLE_TLV("ALC Min Gain Volume", R_ALCCTL2,
+			FB_ALCCTL2_MINGAIN, FM_ALCCTL2_MINGAIN,
+			0, alc_min_gain_tlv_arr),
+	SOC_SINGLE_RANGE("ALC Hold", R_ALCCTL2,
+			FB_ALCCTL2_HLD, 0, FM_ALCCTL2_HLD, 0),
+	/* R_ALCCTL3 PG 1 ADDR 0x20 */
+	SOC_SINGLE_RANGE("ALC Decay", R_ALCCTL3,
+			FB_ALCCTL3_DCY, 0, FM_ALCCTL3_DCY, 0),
+	SOC_SINGLE_RANGE("ALC Attack", R_ALCCTL3,
+			FB_ALCCTL3_ATK, 0, FM_ALCCTL3_ATK, 0),
+	/* R_NGATE PG 1 ADDR 0x21 */
+	SOC_SINGLE_TLV("Noise Gate Threshold Volume", R_NGATE,
+			FB_NGATE_NGTH, FM_NGATE_NGTH, 0, ngth_tlv_arr),
+	SOC_ENUM("Noise Gate Type", ngate_type_enum),
+	SOC_SINGLE("Noise Gate Switch", R_NGATE, FB_NGATE_NGAT, 1, 0),
+	/* R_DMICCTL PG 1 ADDR 0x22 */
+	SOC_SINGLE("Digital Mic 2 Switch", R_DMICCTL, FB_DMICCTL_DMIC2EN, 1, 0),
+	SOC_SINGLE("Digital Mic 1 Switch", R_DMICCTL, FB_DMICCTL_DMIC1EN, 1, 0),
+	SOC_ENUM("Digital Mic Mono Select", dmic_mono_sel_enum),
+	/* R_DACCTL PG 2 ADDR 0x01 */
+	SOC_ENUM("DAC Polarity Left", dac_pol_r_enum),
+	SOC_ENUM("DAC Polarity Right", dac_pol_l_enum),
+	SOC_ENUM("DAC Dither", dac_dith_enum),
+	SOC_SINGLE("DAC Mute Switch", R_DACCTL, FB_DACCTL_DACMUTE, 1, 0),
+	SOC_SINGLE("DAC De-Emphasis Switch", R_DACCTL, FB_DACCTL_DACDEM, 1, 0),
+	/* R_SPKCTL PG 2 ADDR 0x02 */
+	SOC_ENUM("Speaker Polarity Right", spk_pol_r_enum),
+	SOC_ENUM("Speaker Polarity Left", spk_pol_l_enum),
+	SOC_SINGLE("Speaker Mute Switch", R_SPKCTL, FB_SPKCTL_SPKMUTE, 1, 0),
+	SOC_SINGLE("Speaker De-Emphasis Switch",
+			R_SPKCTL, FB_SPKCTL_SPKDEM, 1, 0),
+	/* R_SUBCTL PG 2 ADDR 0x03 */
+	SOC_ENUM("Sub Polarity", sub_pol_enum),
+	SOC_SINGLE("SUB Mute Switch", R_SUBCTL, FB_SUBCTL_SUBMUTE, 1, 0),
+	SOC_SINGLE("Sub De-Emphasis Switch", R_SUBCTL, FB_SUBCTL_SUBDEM, 1, 0),
+	/* R_DCCTL PG 2 ADDR 0x04 */
+	SOC_SINGLE("Sub DC Removal Switch", R_DCCTL, FB_DCCTL_SUBDCBYP, 1, 1),
+	SOC_SINGLE("DAC DC Removal Switch", R_DCCTL, FB_DCCTL_DACDCBYP, 1, 1),
+	SOC_SINGLE("Speaker DC Removal Switch",
+			R_DCCTL, FB_DCCTL_SPKDCBYP, 1, 1),
+	SOC_SINGLE("DC Removal Coefficient Switch", R_DCCTL, FB_DCCTL_DCCOEFSEL,
+			FM_DCCTL_DCCOEFSEL, 0),
+	/* R_OVOLCTLU PG 2 ADDR 0x06 */
+	SOC_SINGLE("Output Fade Switch", R_OVOLCTLU, FB_OVOLCTLU_OFADE, 1, 0),
+	/* R_MVOLL PG 2 ADDR 0x08 */
+	/* R_MVOLR PG 2 ADDR 0x09 */
+	SOC_DOUBLE_R_TLV("Master Volume", R_MVOLL, R_MVOLR,
+			FB_MVOLL_MVOL_L, FM_MVOLL_MVOL_L, 0, mvol_tlv_arr),
+	/* R_HPVOLL PG 2 ADDR 0x0A */
+	/* R_HPVOLR PG 2 ADDR 0x0B */
+	SOC_DOUBLE_R_TLV("Headphone Volume", R_HPVOLL, R_HPVOLR,
+			FB_HPVOLL_HPVOL_L, FM_HPVOLL_HPVOL_L, 0,
+			hp_vol_tlv_arr),
+	/* R_SPKVOLL PG 2 ADDR 0x0C */
+	/* R_SPKVOLR PG 2 ADDR 0x0D */
+	SOC_DOUBLE_R_TLV("Speaker Volume", R_SPKVOLL, R_SPKVOLR,
+			FB_SPKVOLL_SPKVOL_L, FM_SPKVOLL_SPKVOL_L, 0,
+			spk_vol_tlv_arr),
+	/* R_SUBVOL PG 2 ADDR 0x10 */
+	SOC_SINGLE_TLV("Sub Volume", R_SUBVOL,
+			FB_SUBVOL_SUBVOL, FM_SUBVOL_SUBVOL, 0, spk_vol_tlv_arr),
+	/* R_SPKEQFILT PG 3 ADDR 0x01 */
+	SOC_SINGLE("Speaker EQ 2 Switch",
+			R_SPKEQFILT, FB_SPKEQFILT_EQ2EN, 1, 0),
+	SOC_ENUM("Speaker EQ 2 Band", spk_eq_enums[0]),
+	SOC_SINGLE("Speaker EQ 1 Switch",
+			R_SPKEQFILT, FB_SPKEQFILT_EQ1EN, 1, 0),
+	SOC_ENUM("Speaker EQ 1 Band", spk_eq_enums[1]),
+	/* R_SPKMBCEN PG 3 ADDR 0x0A */
+	SOC_SINGLE("Speaker MBC 3 Switch",
+			R_SPKMBCEN, FB_SPKMBCEN_MBCEN3, 1, 0),
+	SOC_SINGLE("Speaker MBC 2 Switch",
+			R_SPKMBCEN, FB_SPKMBCEN_MBCEN2, 1, 0),
+	SOC_SINGLE("Speaker MBC 1 Switch",
+			R_SPKMBCEN, FB_SPKMBCEN_MBCEN1, 1, 0),
+	/* R_SPKMBCCTL PG 3 ADDR 0x0B */
+	SOC_ENUM("Speaker MBC 3 Mode", spk_mbc3_lvl_det_mode_enum),
+	SOC_ENUM("Speaker MBC 3 Window", spk_mbc3_win_sel_enum),
+	SOC_ENUM("Speaker MBC 2 Mode", spk_mbc2_lvl_det_mode_enum),
+	SOC_ENUM("Speaker MBC 2 Window", spk_mbc2_win_sel_enum),
+	SOC_ENUM("Speaker MBC 1 Mode", spk_mbc1_lvl_det_mode_enum),
+	SOC_ENUM("Speaker MBC 1 Window", spk_mbc1_win_sel_enum),
+	/* R_SPKMBCMUG1 PG 3 ADDR 0x0C */
+	SOC_ENUM("Speaker MBC 1 Phase Polarity", spk_mbc1_phase_pol_enum),
+	SOC_SINGLE_TLV("Speaker MBC1 Make-Up Gain Volume", R_SPKMBCMUG1,
+			FB_SPKMBCMUG_MUGAIN, FM_SPKMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_SPKMBCTHR1 PG 3 ADDR 0x0D */
+	SOC_SINGLE_TLV("Speaker MBC 1 Compressor Threshold Volume",
+			R_SPKMBCTHR1, FB_SPKMBCTHR_THRESH, FM_SPKMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SPKMBCRAT1 PG 3 ADDR 0x0E */
+	SOC_ENUM("Speaker MBC 1 Compressor Ratio", spk_mbc1_comp_rat_enum),
+	/* R_SPKMBCATK1L PG 3 ADDR 0x0F */
+	/* R_SPKMBCATK1H PG 3 ADDR 0x10 */
+	SND_SOC_BYTES("Speaker MBC 1 Attack", R_SPKMBCATK1L, 2),
+	/* R_SPKMBCREL1L PG 3 ADDR 0x11 */
+	/* R_SPKMBCREL1H PG 3 ADDR 0x12 */
+	SND_SOC_BYTES("Speaker MBC 1 Release", R_SPKMBCREL1L, 2),
+	/* R_SPKMBCMUG2 PG 3 ADDR 0x13 */
+	SOC_ENUM("Speaker MBC 2 Phase Polarity", spk_mbc2_phase_pol_enum),
+	SOC_SINGLE_TLV("Speaker MBC2 Make-Up Gain Volume", R_SPKMBCMUG2,
+			FB_SPKMBCMUG_MUGAIN, FM_SPKMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_SPKMBCTHR2 PG 3 ADDR 0x14 */
+	SOC_SINGLE_TLV("Speaker MBC 2 Compressor Threshold Volume",
+			R_SPKMBCTHR2, FB_SPKMBCTHR_THRESH, FM_SPKMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SPKMBCRAT2 PG 3 ADDR 0x15 */
+	SOC_ENUM("Speaker MBC 2 Compressor Ratio", spk_mbc2_comp_rat_enum),
+	/* R_SPKMBCATK2L PG 3 ADDR 0x16 */
+	/* R_SPKMBCATK2H PG 3 ADDR 0x17 */
+	SND_SOC_BYTES("Speaker MBC 2 Attack", R_SPKMBCATK2L, 2),
+	/* R_SPKMBCREL2L PG 3 ADDR 0x18 */
+	/* R_SPKMBCREL2H PG 3 ADDR 0x19 */
+	SND_SOC_BYTES("Speaker MBC 2 Release", R_SPKMBCREL2L, 2),
+	/* R_SPKMBCMUG3 PG 3 ADDR 0x1A */
+	SOC_ENUM("Speaker MBC 3 Phase Polarity", spk_mbc3_phase_pol_enum),
+	SOC_SINGLE_TLV("Speaker MBC 3 Make-Up Gain Volume", R_SPKMBCMUG3,
+			FB_SPKMBCMUG_MUGAIN, FM_SPKMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_SPKMBCTHR3 PG 3 ADDR 0x1B */
+	SOC_SINGLE_TLV("Speaker MBC 3 Threshold Volume", R_SPKMBCTHR3,
+			FB_SPKMBCTHR_THRESH, FM_SPKMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SPKMBCRAT3 PG 3 ADDR 0x1C */
+	SOC_ENUM("Speaker MBC 3 Compressor Ratio", spk_mbc3_comp_rat_enum),
+	/* R_SPKMBCATK3L PG 3 ADDR 0x1D */
+	/* R_SPKMBCATK3H PG 3 ADDR 0x1E */
+	SND_SOC_BYTES("Speaker MBC 3 Attack", R_SPKMBCATK3L, 3),
+	/* R_SPKMBCREL3L PG 3 ADDR 0x1F */
+	/* R_SPKMBCREL3H PG 3 ADDR 0x20 */
+	SND_SOC_BYTES("Speaker MBC 3 Release", R_SPKMBCREL3L, 3),
+	/* R_SPKCLECTL PG 3 ADDR 0x21 */
+	SOC_ENUM("Speaker CLE Level Mode", spk_cle_lvl_mode_enum),
+	SOC_ENUM("Speaker CLE Window", spk_cle_win_sel_enum),
+	SOC_SINGLE("Speaker CLE Expander Switch",
+			R_SPKCLECTL, FB_SPKCLECTL_EXPEN, 1, 0),
+	SOC_SINGLE("Speaker CLE Limiter Switch",
+			R_SPKCLECTL, FB_SPKCLECTL_LIMEN, 1, 0),
+	SOC_SINGLE("Speaker CLE Compressor Switch",
+			R_SPKCLECTL, FB_SPKCLECTL_COMPEN, 1, 0),
+	/* R_SPKCLEMUG PG 3 ADDR 0x22 */
+	SOC_SINGLE_TLV("Speaker CLE Make-Up Gain Volume", R_SPKCLEMUG,
+			FB_SPKCLEMUG_MUGAIN, FM_SPKCLEMUG_MUGAIN,
+			0, cle_mug_tlv_arr),
+	/* R_SPKCOMPTHR PG 3 ADDR 0x23 */
+	SOC_SINGLE_TLV("Speaker Compressor Threshold Volume", R_SPKCOMPTHR,
+			FB_SPKCOMPTHR_THRESH, FM_SPKCOMPTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SPKCOMPRAT PG 3 ADDR 0x24 */
+	SOC_ENUM("Speaker Compressor Ratio", spk_comp_rat_enum),
+	/* R_SPKCOMPATKL PG 3 ADDR 0x25 */
+	/* R_SPKCOMPATKH PG 3 ADDR 0x26 */
+	SND_SOC_BYTES("Speaker Compressor Attack", R_SPKCOMPATKL, 2),
+	/* R_SPKCOMPRELL PG 3 ADDR 0x27 */
+	/* R_SPKCOMPRELH PG 3 ADDR 0x28 */
+	SND_SOC_BYTES("Speaker Compressor Release", R_SPKCOMPRELL, 2),
+	/* R_SPKLIMTHR PG 3 ADDR 0x29 */
+	SOC_SINGLE_TLV("Speaker Limiter Threshold Volume", R_SPKLIMTHR,
+			FB_SPKLIMTHR_THRESH, FM_SPKLIMTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SPKLIMTGT PG 3 ADDR 0x2A */
+	SOC_SINGLE_TLV("Speaker Limiter Target Volume", R_SPKLIMTGT,
+			FB_SPKLIMTGT_TARGET, FM_SPKLIMTGT_TARGET,
+			0, thr_tlv_arr),
+	/* R_SPKLIMATKL PG 3 ADDR 0x2B */
+	/* R_SPKLIMATKH PG 3 ADDR 0x2C */
+	SND_SOC_BYTES("Speaker Limiter Attack", R_SPKLIMATKL, 2),
+	/* R_SPKLIMRELL PG 3 ADDR 0x2D */
+	/* R_SPKLIMRELR PG 3 ADDR 0x2E */
+	SND_SOC_BYTES("Speaker Limiter Release", R_SPKLIMRELL, 2),
+	/* R_SPKEXPTHR PG 3 ADDR 0x2F */
+	SOC_SINGLE_TLV("Speaker Expander Threshold Volume", R_SPKEXPTHR,
+			FB_SPKEXPTHR_THRESH, FM_SPKEXPTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SPKEXPRAT PG 3 ADDR 0x30 */
+	SOC_ENUM("Speaker Expander Ratio", spk_exp_rat_enum),
+	/* R_SPKEXPATKL PG 3 ADDR 0x31 */
+	/* R_SPKEXPATKR PG 3 ADDR 0x32 */
+	SND_SOC_BYTES("Speaker Expander Attack", R_SPKEXPATKL, 2),
+	/* R_SPKEXPRELL PG 3 ADDR 0x33 */
+	/* R_SPKEXPRELR PG 3 ADDR 0x34 */
+	SND_SOC_BYTES("Speaker Expander Release", R_SPKEXPRELL, 2),
+	/* R_SPKFXCTL PG 3 ADDR 0x35 */
+	SOC_SINGLE("Speaker 3D Switch", R_SPKFXCTL, FB_SPKFXCTL_3DEN, 1, 0),
+	SOC_SINGLE("Speaker Treble Enhancement Switch",
+			R_SPKFXCTL, FB_SPKFXCTL_TEEN, 1, 0),
+	SOC_SINGLE("Speaker Treble NLF Switch",
+			R_SPKFXCTL, FB_SPKFXCTL_TNLFBYP, 1, 1),
+	SOC_SINGLE("Speaker Bass Enhancement Switch",
+			R_SPKFXCTL, FB_SPKFXCTL_BEEN, 1, 0),
+	SOC_SINGLE("Speaker Bass NLF Switch",
+			R_SPKFXCTL, FB_SPKFXCTL_BNLFBYP, 1, 1),
+	/* R_DACEQFILT PG 4 ADDR 0x01 */
+	SOC_SINGLE("DAC EQ 2 Switch",
+			R_DACEQFILT, FB_DACEQFILT_EQ2EN, 1, 0),
+	SOC_ENUM("DAC EQ 2 Band", dac_eq_enums[0]),
+	SOC_SINGLE("DAC EQ 1 Switch", R_DACEQFILT, FB_DACEQFILT_EQ1EN, 1, 0),
+	SOC_ENUM("DAC EQ 1 Band", dac_eq_enums[1]),
+	/* R_DACMBCEN PG 4 ADDR 0x0A */
+	SOC_SINGLE("DAC MBC 3 Switch", R_DACMBCEN, FB_DACMBCEN_MBCEN3, 1, 0),
+	SOC_SINGLE("DAC MBC 2 Switch", R_DACMBCEN, FB_DACMBCEN_MBCEN2, 1, 0),
+	SOC_SINGLE("DAC MBC 1 Switch", R_DACMBCEN, FB_DACMBCEN_MBCEN1, 1, 0),
+	/* R_DACMBCCTL PG 4 ADDR 0x0B */
+	SOC_ENUM("DAC MBC 3 Mode", dac_mbc3_lvl_det_mode_enum),
+	SOC_ENUM("DAC MBC 3 Window", dac_mbc3_win_sel_enum),
+	SOC_ENUM("DAC MBC 2 Mode", dac_mbc2_lvl_det_mode_enum),
+	SOC_ENUM("DAC MBC 2 Window", dac_mbc2_win_sel_enum),
+	SOC_ENUM("DAC MBC 1 Mode", dac_mbc1_lvl_det_mode_enum),
+	SOC_ENUM("DAC MBC 1 Window", dac_mbc1_win_sel_enum),
+	/* R_DACMBCMUG1 PG 4 ADDR 0x0C */
+	SOC_ENUM("DAC MBC 1 Phase Polarity", dac_mbc1_phase_pol_enum),
+	SOC_SINGLE_TLV("DAC MBC 1 Make-Up Gain Volume", R_DACMBCMUG1,
+			FB_DACMBCMUG_MUGAIN, FM_DACMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_DACMBCTHR1 PG 4 ADDR 0x0D */
+	SOC_SINGLE_TLV("DAC MBC 1 Compressor Threshold Volume", R_DACMBCTHR1,
+			FB_DACMBCTHR_THRESH, FM_DACMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_DACMBCRAT1 PG 4 ADDR 0x0E */
+	SOC_ENUM("DAC MBC 1 Compressor Ratio", dac_mbc1_comp_rat_enum),
+	/* R_DACMBCATK1L PG 4 ADDR 0x0F */
+	/* R_DACMBCATK1H PG 4 ADDR 0x10 */
+	SND_SOC_BYTES("DAC MBC 1 Attack", R_DACMBCATK1L, 2),
+	/* R_DACMBCREL1L PG 4 ADDR 0x11 */
+	/* R_DACMBCREL1H PG 4 ADDR 0x12 */
+	SND_SOC_BYTES("DAC MBC 1 Release", R_DACMBCREL1L, 2),
+	/* R_DACMBCMUG2 PG 4 ADDR 0x13 */
+	SOC_ENUM("DAC MBC 2 Phase Polarity", dac_mbc2_phase_pol_enum),
+	SOC_SINGLE_TLV("DAC MBC 2 Make-Up Gain Volume", R_DACMBCMUG2,
+			FB_DACMBCMUG_MUGAIN, FM_DACMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_DACMBCTHR2 PG 4 ADDR 0x14 */
+	SOC_SINGLE_TLV("DAC MBC 2 Compressor Threshold Volume", R_DACMBCTHR2,
+			FB_DACMBCTHR_THRESH, FM_DACMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_DACMBCRAT2 PG 4 ADDR 0x15 */
+	SOC_ENUM("DAC MBC 2 Compressor Ratio", dac_mbc2_comp_rat_enum),
+	/* R_DACMBCATK2L PG 4 ADDR 0x16 */
+	/* R_DACMBCATK2H PG 4 ADDR 0x17 */
+	SND_SOC_BYTES("DAC MBC 2 Attack", R_DACMBCATK2L, 2),
+	/* R_DACMBCREL2L PG 4 ADDR 0x18 */
+	/* R_DACMBCREL2H PG 4 ADDR 0x19 */
+	SND_SOC_BYTES("DAC MBC 2 Release", R_DACMBCREL2L, 2),
+	/* R_DACMBCMUG3 PG 4 ADDR 0x1A */
+	SOC_ENUM("DAC MBC 3 Phase Polarity", dac_mbc3_phase_pol_enum),
+	SOC_SINGLE_TLV("DAC MBC 3 Make-Up Gain Volume", R_DACMBCMUG3,
+			FB_DACMBCMUG_MUGAIN, FM_DACMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_DACMBCTHR3 PG 4 ADDR 0x1B */
+	SOC_SINGLE_TLV("DAC MBC 3 Threshold Volume", R_DACMBCTHR3,
+			FB_DACMBCTHR_THRESH, FM_DACMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_DACMBCRAT3 PG 4 ADDR 0x1C */
+	SOC_ENUM("DAC MBC 3 Compressor Ratio", dac_mbc3_comp_rat_enum),
+	/* R_DACMBCATK3L PG 4 ADDR 0x1D */
+	/* R_DACMBCATK3H PG 4 ADDR 0x1E */
+	SND_SOC_BYTES("DAC MBC 3 Attack", R_DACMBCATK3L, 3),
+	/* R_DACMBCREL3L PG 4 ADDR 0x1F */
+	/* R_DACMBCREL3H PG 4 ADDR 0x20 */
+	SND_SOC_BYTES("DAC MBC 3 Release", R_DACMBCREL3L, 3),
+	/* R_DACCLECTL PG 4 ADDR 0x21 */
+	SOC_ENUM("DAC CLE Level Mode", dac_cle_lvl_mode_enum),
+	SOC_ENUM("DAC CLE Window", dac_cle_win_sel_enum),
+	SOC_SINGLE("DAC CLE Expander Switch",
+			R_DACCLECTL, FB_DACCLECTL_EXPEN, 1, 0),
+	SOC_SINGLE("DAC CLE Limiter Switch",
+			R_DACCLECTL, FB_DACCLECTL_LIMEN, 1, 0),
+	SOC_SINGLE("DAC CLE Compressor Switch",
+			R_DACCLECTL, FB_DACCLECTL_COMPEN, 1, 0),
+	/* R_DACCLEMUG PG 4 ADDR 0x22 */
+	SOC_SINGLE_TLV("DAC CLE Make-Up Gain Volume", R_DACCLEMUG,
+			FB_DACCLEMUG_MUGAIN, FM_DACCLEMUG_MUGAIN,
+			0, cle_mug_tlv_arr),
+	/* R_DACCOMPTHR PG 4 ADDR 0x23 */
+	SOC_SINGLE_TLV("DAC Compressor Threshold Volume", R_DACCOMPTHR,
+			FB_DACCOMPTHR_THRESH, FM_DACCOMPTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_DACCOMPRAT PG 4 ADDR 0x24 */
+	SOC_ENUM("DAC Compressor Ratio", dac_comp_rat_enum),
+	/* R_DACCOMPATKL PG 4 ADDR 0x25 */
+	/* R_DACCOMPATKH PG 4 ADDR 0x26 */
+	SND_SOC_BYTES("DAC Compressor Attack", R_DACCOMPATKL, 2),
+	/* R_DACCOMPRELL PG 4 ADDR 0x27 */
+	/* R_DACCOMPRELH PG 4 ADDR 0x28 */
+	SND_SOC_BYTES("DAC Compressor Release", R_DACCOMPRELL, 2),
+	/* R_DACLIMTHR PG 4 ADDR 0x29 */
+	SOC_SINGLE_TLV("DAC Limiter Threshold Volume", R_DACLIMTHR,
+			FB_DACLIMTHR_THRESH, FM_DACLIMTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_DACLIMTGT PG 4 ADDR 0x2A */
+	SOC_SINGLE_TLV("DAC Limiter Target Volume", R_DACLIMTGT,
+			FB_DACLIMTGT_TARGET, FM_DACLIMTGT_TARGET,
+			0, thr_tlv_arr),
+	/* R_DACLIMATKL PG 4 ADDR 0x2B */
+	/* R_DACLIMATKH PG 4 ADDR 0x2C */
+	SND_SOC_BYTES("DAC Limiter Attack", R_DACLIMATKL, 2),
+	/* R_DACLIMRELL PG 4 ADDR 0x2D */
+	/* R_DACLIMRELR PG 4 ADDR 0x2E */
+	SND_SOC_BYTES("DAC Limiter Release", R_DACLIMRELL, 2),
+	/* R_DACEXPTHR PG 4 ADDR 0x2F */
+	SOC_SINGLE_TLV("DAC Expander Threshold Volume", R_DACEXPTHR,
+			FB_DACEXPTHR_THRESH, FM_DACEXPTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_DACEXPRAT PG 4 ADDR 0x30 */
+	SOC_ENUM("DAC Expander Ratio", dac_exp_rat_enum),
+	/* R_DACEXPATKL PG 4 ADDR 0x31 */
+	/* R_DACEXPATKR PG 4 ADDR 0x32 */
+	SND_SOC_BYTES("DAC Expander Attack", R_DACEXPATKL, 2),
+	/* R_DACEXPRELL PG 4 ADDR 0x33 */
+	/* R_DACEXPRELR PG 4 ADDR 0x34 */
+	SND_SOC_BYTES("DAC Expander Release", R_DACEXPRELL, 2),
+	/* R_DACFXCTL PG 4 ADDR 0x35 */
+	SOC_SINGLE("DAC 3D Switch", R_DACFXCTL, FB_DACFXCTL_3DEN, 1, 0),
+	SOC_SINGLE("DAC Treble Enhancement Switch",
+			R_DACFXCTL, FB_DACFXCTL_TEEN, 1, 0),
+	SOC_SINGLE("DAC Treble NLF Switch",
+			R_DACFXCTL, FB_DACFXCTL_TNLFBYP, 1, 1),
+	SOC_SINGLE("DAC Bass Enhancement Switch",
+			R_DACFXCTL, FB_DACFXCTL_BEEN, 1, 0),
+	SOC_SINGLE("DAC Bass NLF Switch",
+			R_DACFXCTL, FB_DACFXCTL_BNLFBYP, 1, 1),
+	/* R_SUBEQFILT PG 5 ADDR 0x01 */
+	SOC_SINGLE("Sub EQ 2 Switch",
+			R_SUBEQFILT, FB_SUBEQFILT_EQ2EN, 1, 0),
+	SOC_ENUM("Sub EQ 2 Band", sub_eq_enums[0]),
+	SOC_SINGLE("Sub EQ 1 Switch", R_SUBEQFILT, FB_SUBEQFILT_EQ1EN, 1, 0),
+	SOC_ENUM("Sub EQ 1 Band", sub_eq_enums[1]),
+	/* R_SUBMBCEN PG 5 ADDR 0x0A */
+	SOC_SINGLE("Sub MBC 3 Switch", R_SUBMBCEN, FB_SUBMBCEN_MBCEN3, 1, 0),
+	SOC_SINGLE("Sub MBC 2 Switch", R_SUBMBCEN, FB_SUBMBCEN_MBCEN2, 1, 0),
+	SOC_SINGLE("Sub MBC 1 Switch", R_SUBMBCEN, FB_SUBMBCEN_MBCEN1, 1, 0),
+	/* R_SUBMBCCTL PG 5 ADDR 0x0B */
+	SOC_ENUM("Sub MBC 3 Mode", sub_mbc3_lvl_det_mode_enum),
+	SOC_ENUM("Sub MBC 3 Window", sub_mbc3_win_sel_enum),
+	SOC_ENUM("Sub MBC 2 Mode", sub_mbc2_lvl_det_mode_enum),
+	SOC_ENUM("Sub MBC 2 Window", sub_mbc2_win_sel_enum),
+	SOC_ENUM("Sub MBC 1 Mode", sub_mbc1_lvl_det_mode_enum),
+	SOC_ENUM("Sub MBC 1 Window", sub_mbc1_win_sel_enum),
+	/* R_SUBMBCMUG1 PG 5 ADDR 0x0C */
+	SOC_ENUM("Sub MBC 1 Phase Polarity", sub_mbc1_phase_pol_enum),
+	SOC_SINGLE_TLV("Sub MBC 1 Make-Up Gain Volume", R_SUBMBCMUG1,
+			FB_SUBMBCMUG_MUGAIN, FM_SUBMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_SUBMBCTHR1 PG 5 ADDR 0x0D */
+	SOC_SINGLE_TLV("Sub MBC 1 Compressor Threshold Volume", R_SUBMBCTHR1,
+			FB_SUBMBCTHR_THRESH, FM_SUBMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SUBMBCRAT1 PG 5 ADDR 0x0E */
+	SOC_ENUM("Sub MBC 1 Compressor Ratio", sub_mbc1_comp_rat_enum),
+	/* R_SUBMBCATK1L PG 5 ADDR 0x0F */
+	/* R_SUBMBCATK1H PG 5 ADDR 0x10 */
+	SND_SOC_BYTES("Sub MBC 1 Attack", R_SUBMBCATK1L, 2),
+	/* R_SUBMBCREL1L PG 5 ADDR 0x11 */
+	/* R_SUBMBCREL1H PG 5 ADDR 0x12 */
+	SND_SOC_BYTES("Sub MBC 1 Release", R_SUBMBCREL1L, 2),
+	/* R_SUBMBCMUG2 PG 5 ADDR 0x13 */
+	SOC_ENUM("Sub MBC 2 Phase Polarity", sub_mbc2_phase_pol_enum),
+	SOC_SINGLE_TLV("Sub MBC 2 Make-Up Gain Volume", R_SUBMBCMUG2,
+			FB_SUBMBCMUG_MUGAIN, FM_SUBMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_SUBMBCTHR2 PG 5 ADDR 0x14 */
+	SOC_SINGLE_TLV("Sub MBC 2 Compressor Threshold Volume", R_SUBMBCTHR2,
+			FB_SUBMBCTHR_THRESH, FM_SUBMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SUBMBCRAT2 PG 5 ADDR 0x15 */
+	SOC_ENUM("Sub MBC 2 Compressor Ratio", sub_mbc2_comp_rat_enum),
+	/* R_SUBMBCATK2L PG 5 ADDR 0x16 */
+	/* R_SUBMBCATK2H PG 5 ADDR 0x17 */
+	SND_SOC_BYTES("Sub MBC 2 Attack", R_SUBMBCATK2L, 2),
+	/* R_SUBMBCREL2L PG 5 ADDR 0x18 */
+	/* R_SUBMBCREL2H PG 5 ADDR 0x19 */
+	SND_SOC_BYTES("Sub MBC 2 Release", R_SUBMBCREL2L, 2),
+	/* R_SUBMBCMUG3 PG 5 ADDR 0x1A */
+	SOC_ENUM("Sub MBC 3 Phase Polarity", sub_mbc3_phase_pol_enum),
+	SOC_SINGLE_TLV("Sub MBC 3 Make-Up Gain Volume", R_SUBMBCMUG3,
+			FB_SUBMBCMUG_MUGAIN, FM_SUBMBCMUG_MUGAIN,
+			0, mbc_mug_tlv_arr),
+	/* R_SUBMBCTHR3 PG 5 ADDR 0x1B */
+	SOC_SINGLE_TLV("Sub MBC 3 Threshold Volume", R_SUBMBCTHR3,
+			FB_SUBMBCTHR_THRESH, FM_SUBMBCTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SUBMBCRAT3 PG 5 ADDR 0x1C */
+	SOC_ENUM("Sub MBC 3 Compressor Ratio", sub_mbc3_comp_rat_enum),
+	/* R_SUBMBCATK3L PG 5 ADDR 0x1D */
+	/* R_SUBMBCATK3H PG 5 ADDR 0x1E */
+	SND_SOC_BYTES("Sub MBC 3 Attack", R_SUBMBCATK3L, 3),
+	/* R_SUBMBCREL3L PG 5 ADDR 0x1F */
+	/* R_SUBMBCREL3H PG 5 ADDR 0x20 */
+	SND_SOC_BYTES("Sub MBC 3 Release", R_SUBMBCREL3L, 3),
+	/* R_SUBCLECTL PG 5 ADDR 0x21 */
+	SOC_ENUM("Sub CLE Level Mode", sub_cle_lvl_mode_enum),
+	SOC_ENUM("Sub CLE Window", sub_cle_win_sel_enum),
+	SOC_SINGLE("Sub CLE Expander Switch",
+			R_SUBCLECTL, FB_SUBCLECTL_EXPEN, 1, 0),
+	SOC_SINGLE("Sub CLE Limiter Switch",
+			R_SUBCLECTL, FB_SUBCLECTL_LIMEN, 1, 0),
+	SOC_SINGLE("Sub CLE Compressor Switch",
+			R_SUBCLECTL, FB_SUBCLECTL_COMPEN, 1, 0),
+	/* R_SUBCLEMUG PG 5 ADDR 0x22 */
+	SOC_SINGLE_TLV("Sub CLE Make-Up Gain Volume", R_SUBCLEMUG,
+			FB_SUBCLEMUG_MUGAIN, FM_SUBCLEMUG_MUGAIN,
+			0, cle_mug_tlv_arr),
+	/* R_SUBCOMPTHR PG 5 ADDR 0x23 */
+	SOC_SINGLE_TLV("Sub Compressor Threshold Volume", R_SUBCOMPTHR,
+			FB_SUBCOMPTHR_THRESH, FM_SUBCOMPTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SUBCOMPRAT PG 5 ADDR 0x24 */
+	SOC_ENUM("Sub Compressor Ratio", sub_comp_rat_enum),
+	/* R_SUBCOMPATKL PG 5 ADDR 0x25 */
+	/* R_SUBCOMPATKH PG 5 ADDR 0x26 */
+	SND_SOC_BYTES("Sub Compressor Attack", R_SUBCOMPATKL, 2),
+	/* R_SUBCOMPRELL PG 5 ADDR 0x27 */
+	/* R_SUBCOMPRELH PG 5 ADDR 0x28 */
+	SND_SOC_BYTES("Sub Compressor Release", R_SUBCOMPRELL, 2),
+	/* R_SUBLIMTHR PG 5 ADDR 0x29 */
+	SOC_SINGLE_TLV("Sub Limiter Threshold Volume", R_SUBLIMTHR,
+			FB_SUBLIMTHR_THRESH, FM_SUBLIMTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SUBLIMTGT PG 5 ADDR 0x2A */
+	SOC_SINGLE_TLV("Sub Limiter Target Volume", R_SUBLIMTGT,
+			FB_SUBLIMTGT_TARGET, FM_SUBLIMTGT_TARGET,
+			0, thr_tlv_arr),
+	/* R_SUBLIMATKL PG 5 ADDR 0x2B */
+	/* R_SUBLIMATKH PG 5 ADDR 0x2C */
+	SND_SOC_BYTES("Sub Limiter Attack", R_SUBLIMATKL, 2),
+	/* R_SUBLIMRELL PG 5 ADDR 0x2D */
+	/* R_SUBLIMRELR PG 5 ADDR 0x2E */
+	SND_SOC_BYTES("Sub Limiter Release", R_SUBLIMRELL, 2),
+	/* R_SUBEXPTHR PG 5 ADDR 0x2F */
+	SOC_SINGLE_TLV("Sub Expander Threshold Volume", R_SUBEXPTHR,
+			FB_SUBEXPTHR_THRESH, FM_SUBEXPTHR_THRESH,
+			0, thr_tlv_arr),
+	/* R_SUBEXPRAT PG 5 ADDR 0x30 */
+	SOC_ENUM("Sub Expander Ratio", sub_exp_rat_enum),
+	/* R_SUBEXPATKL PG 5 ADDR 0x31 */
+	/* R_SUBEXPATKR PG 5 ADDR 0x32 */
+	SND_SOC_BYTES("Sub Expander Attack", R_SUBEXPATKL, 2),
+	/* R_SUBEXPRELL PG 5 ADDR 0x33 */
+	/* R_SUBEXPRELR PG 5 ADDR 0x34 */
+	SND_SOC_BYTES("Sub Expander Release", R_SUBEXPRELL, 2),
+	/* R_SUBFXCTL PG 5 ADDR 0x35 */
+	SOC_SINGLE("Sub Treble Enhancement Switch",
+			R_SUBFXCTL, FB_SUBFXCTL_TEEN, 1, 0),
+	SOC_SINGLE("Sub Treble NLF Switch",
+			R_SUBFXCTL, FB_SUBFXCTL_TNLFBYP, 1, 1),
+	SOC_SINGLE("Sub Bass Enhancement Switch",
+			R_SUBFXCTL, FB_SUBFXCTL_BEEN, 1, 0),
+	SOC_SINGLE("Sub Bass NLF Switch",
+			R_SUBFXCTL, FB_SUBFXCTL_BNLFBYP, 1, 1),
+	COEFF_RAM_CTL("DAC Cascade 1 Left BiQuad 1", BIQUAD_SIZE, 0x00),
+	COEFF_RAM_CTL("DAC Cascade 1 Left BiQuad 2", BIQUAD_SIZE, 0x05),
+	COEFF_RAM_CTL("DAC Cascade 1 Left BiQuad 3", BIQUAD_SIZE, 0x0a),
+	COEFF_RAM_CTL("DAC Cascade 1 Left BiQuad 4", BIQUAD_SIZE, 0x0f),
+	COEFF_RAM_CTL("DAC Cascade 1 Left BiQuad 5", BIQUAD_SIZE, 0x14),
+	COEFF_RAM_CTL("DAC Cascade 1 Left BiQuad 6", BIQUAD_SIZE, 0x19),
+
+	COEFF_RAM_CTL("DAC Cascade 1 Right BiQuad 1", BIQUAD_SIZE, 0x20),
+	COEFF_RAM_CTL("DAC Cascade 1 Right BiQuad 2", BIQUAD_SIZE, 0x25),
+	COEFF_RAM_CTL("DAC Cascade 1 Right BiQuad 3", BIQUAD_SIZE, 0x2a),
+	COEFF_RAM_CTL("DAC Cascade 1 Right BiQuad 4", BIQUAD_SIZE, 0x2f),
+	COEFF_RAM_CTL("DAC Cascade 1 Right BiQuad 5", BIQUAD_SIZE, 0x34),
+	COEFF_RAM_CTL("DAC Cascade 1 Right BiQuad 6", BIQUAD_SIZE, 0x39),
+
+	COEFF_RAM_CTL("DAC Cascade 1 Left Prescale", COEFF_SIZE, 0x1f),
+	COEFF_RAM_CTL("DAC Cascade 1 Right Prescale", COEFF_SIZE, 0x3f),
+
+	COEFF_RAM_CTL("DAC Cascade 2 Left BiQuad 1", BIQUAD_SIZE, 0x40),
+	COEFF_RAM_CTL("DAC Cascade 2 Left BiQuad 2", BIQUAD_SIZE, 0x45),
+	COEFF_RAM_CTL("DAC Cascade 2 Left BiQuad 3", BIQUAD_SIZE, 0x4a),
+	COEFF_RAM_CTL("DAC Cascade 2 Left BiQuad 4", BIQUAD_SIZE, 0x4f),
+	COEFF_RAM_CTL("DAC Cascade 2 Left BiQuad 5", BIQUAD_SIZE, 0x54),
+	COEFF_RAM_CTL("DAC Cascade 2 Left BiQuad 6", BIQUAD_SIZE, 0x59),
+
+	COEFF_RAM_CTL("DAC Cascade 2 Right BiQuad 1", BIQUAD_SIZE, 0x60),
+	COEFF_RAM_CTL("DAC Cascade 2 Right BiQuad 2", BIQUAD_SIZE, 0x65),
+	COEFF_RAM_CTL("DAC Cascade 2 Right BiQuad 3", BIQUAD_SIZE, 0x6a),
+	COEFF_RAM_CTL("DAC Cascade 2 Right BiQuad 4", BIQUAD_SIZE, 0x6f),
+	COEFF_RAM_CTL("DAC Cascade 2 Right BiQuad 5", BIQUAD_SIZE, 0x74),
+	COEFF_RAM_CTL("DAC Cascade 2 Right BiQuad 6", BIQUAD_SIZE, 0x79),
+
+	COEFF_RAM_CTL("DAC Cascade 2 Left Prescale", COEFF_SIZE, 0x5f),
+	COEFF_RAM_CTL("DAC Cascade 2 Right Prescale", COEFF_SIZE, 0x7f),
+
+	COEFF_RAM_CTL("DAC Bass Extraction BiQuad 1", BIQUAD_SIZE, 0x80),
+	COEFF_RAM_CTL("DAC Bass Extraction BiQuad 2", BIQUAD_SIZE, 0x85),
+
+	COEFF_RAM_CTL("DAC Bass Non Linear Function 1", COEFF_SIZE, 0x8a),
+	COEFF_RAM_CTL("DAC Bass Non Linear Function 2", COEFF_SIZE, 0x8b),
+
+	COEFF_RAM_CTL("DAC Bass Limiter BiQuad", BIQUAD_SIZE, 0x8c),
+
+	COEFF_RAM_CTL("DAC Bass Cut Off BiQuad", BIQUAD_SIZE, 0x91),
+
+	COEFF_RAM_CTL("DAC Bass Mix", COEFF_SIZE, 0x96),
+
+	COEFF_RAM_CTL("DAC Treb Extraction BiQuad 1", BIQUAD_SIZE, 0x97),
+	COEFF_RAM_CTL("DAC Treb Extraction BiQuad 2", BIQUAD_SIZE, 0x9c),
+
+	COEFF_RAM_CTL("DAC Treb Non Linear Function 1", COEFF_SIZE, 0xa1),
+	COEFF_RAM_CTL("DAC Treb Non Linear Function 2", COEFF_SIZE, 0xa2),
+
+	COEFF_RAM_CTL("DAC Treb Limiter BiQuad", BIQUAD_SIZE, 0xa3),
+
+	COEFF_RAM_CTL("DAC Treb Cut Off BiQuad", BIQUAD_SIZE, 0xa8),
+
+	COEFF_RAM_CTL("DAC Treb Mix", COEFF_SIZE, 0xad),
+
+	COEFF_RAM_CTL("DAC 3D", COEFF_SIZE, 0xae),
+
+	COEFF_RAM_CTL("DAC 3D Mix", COEFF_SIZE, 0xaf),
+
+	COEFF_RAM_CTL("DAC MBC 1 BiQuad 1", BIQUAD_SIZE, 0xb0),
+	COEFF_RAM_CTL("DAC MBC 1 BiQuad 2", BIQUAD_SIZE, 0xb5),
+
+	COEFF_RAM_CTL("DAC MBC 2 BiQuad 1", BIQUAD_SIZE, 0xba),
+	COEFF_RAM_CTL("DAC MBC 2 BiQuad 2", BIQUAD_SIZE, 0xbf),
+
+	COEFF_RAM_CTL("DAC MBC 3 BiQuad 1", BIQUAD_SIZE, 0xc4),
+	COEFF_RAM_CTL("DAC MBC 3 BiQuad 2", BIQUAD_SIZE, 0xc9),
+
+	COEFF_RAM_CTL("Speaker Cascade 1 Left BiQuad 1", BIQUAD_SIZE, 0x00),
+	COEFF_RAM_CTL("Speaker Cascade 1 Left BiQuad 2", BIQUAD_SIZE, 0x05),
+	COEFF_RAM_CTL("Speaker Cascade 1 Left BiQuad 3", BIQUAD_SIZE, 0x0a),
+	COEFF_RAM_CTL("Speaker Cascade 1 Left BiQuad 4", BIQUAD_SIZE, 0x0f),
+	COEFF_RAM_CTL("Speaker Cascade 1 Left BiQuad 5", BIQUAD_SIZE, 0x14),
+	COEFF_RAM_CTL("Speaker Cascade 1 Left BiQuad 6", BIQUAD_SIZE, 0x19),
+
+	COEFF_RAM_CTL("Speaker Cascade 1 Right BiQuad 1", BIQUAD_SIZE, 0x20),
+	COEFF_RAM_CTL("Speaker Cascade 1 Right BiQuad 2", BIQUAD_SIZE, 0x25),
+	COEFF_RAM_CTL("Speaker Cascade 1 Right BiQuad 3", BIQUAD_SIZE, 0x2a),
+	COEFF_RAM_CTL("Speaker Cascade 1 Right BiQuad 4", BIQUAD_SIZE, 0x2f),
+	COEFF_RAM_CTL("Speaker Cascade 1 Right BiQuad 5", BIQUAD_SIZE, 0x34),
+	COEFF_RAM_CTL("Speaker Cascade 1 Right BiQuad 6", BIQUAD_SIZE, 0x39),
+
+	COEFF_RAM_CTL("Speaker Cascade 1 Left Prescale", COEFF_SIZE, 0x1f),
+	COEFF_RAM_CTL("Speaker Cascade 1 Right Prescale", COEFF_SIZE, 0x3f),
+
+	COEFF_RAM_CTL("Speaker Cascade 2 Left BiQuad 1", BIQUAD_SIZE, 0x40),
+	COEFF_RAM_CTL("Speaker Cascade 2 Left BiQuad 2", BIQUAD_SIZE, 0x45),
+	COEFF_RAM_CTL("Speaker Cascade 2 Left BiQuad 3", BIQUAD_SIZE, 0x4a),
+	COEFF_RAM_CTL("Speaker Cascade 2 Left BiQuad 4", BIQUAD_SIZE, 0x4f),
+	COEFF_RAM_CTL("Speaker Cascade 2 Left BiQuad 5", BIQUAD_SIZE, 0x54),
+	COEFF_RAM_CTL("Speaker Cascade 2 Left BiQuad 6", BIQUAD_SIZE, 0x59),
+
+	COEFF_RAM_CTL("Speaker Cascade 2 Right BiQuad 1", BIQUAD_SIZE, 0x60),
+	COEFF_RAM_CTL("Speaker Cascade 2 Right BiQuad 2", BIQUAD_SIZE, 0x65),
+	COEFF_RAM_CTL("Speaker Cascade 2 Right BiQuad 3", BIQUAD_SIZE, 0x6a),
+	COEFF_RAM_CTL("Speaker Cascade 2 Right BiQuad 4", BIQUAD_SIZE, 0x6f),
+	COEFF_RAM_CTL("Speaker Cascade 2 Right BiQuad 5", BIQUAD_SIZE, 0x74),
+	COEFF_RAM_CTL("Speaker Cascade 2 Right BiQuad 6", BIQUAD_SIZE, 0x79),
+
+	COEFF_RAM_CTL("Speaker Cascade 2 Left Prescale", COEFF_SIZE, 0x5f),
+	COEFF_RAM_CTL("Speaker Cascade 2 Right Prescale", COEFF_SIZE, 0x7f),
+
+	COEFF_RAM_CTL("Speaker Bass Extraction BiQuad 1", BIQUAD_SIZE, 0x80),
+	COEFF_RAM_CTL("Speaker Bass Extraction BiQuad 2", BIQUAD_SIZE, 0x85),
+
+	COEFF_RAM_CTL("Speaker Bass Non Linear Function 1", COEFF_SIZE, 0x8a),
+	COEFF_RAM_CTL("Speaker Bass Non Linear Function 2", COEFF_SIZE, 0x8b),
+
+	COEFF_RAM_CTL("Speaker Bass Limiter BiQuad", BIQUAD_SIZE, 0x8c),
+
+	COEFF_RAM_CTL("Speaker Bass Cut Off BiQuad", BIQUAD_SIZE, 0x91),
+
+	COEFF_RAM_CTL("Speaker Bass Mix", COEFF_SIZE, 0x96),
+
+	COEFF_RAM_CTL("Speaker Treb Extraction BiQuad 1", BIQUAD_SIZE, 0x97),
+	COEFF_RAM_CTL("Speaker Treb Extraction BiQuad 2", BIQUAD_SIZE, 0x9c),
+
+	COEFF_RAM_CTL("Speaker Treb Non Linear Function 1", COEFF_SIZE, 0xa1),
+	COEFF_RAM_CTL("Speaker Treb Non Linear Function 2", COEFF_SIZE, 0xa2),
+
+	COEFF_RAM_CTL("Speaker Treb Limiter BiQuad", BIQUAD_SIZE, 0xa3),
+
+	COEFF_RAM_CTL("Speaker Treb Cut Off BiQuad", BIQUAD_SIZE, 0xa8),
+
+	COEFF_RAM_CTL("Speaker Treb Mix", COEFF_SIZE, 0xad),
+
+	COEFF_RAM_CTL("Speaker 3D", COEFF_SIZE, 0xae),
+
+	COEFF_RAM_CTL("Speaker 3D Mix", COEFF_SIZE, 0xaf),
+
+	COEFF_RAM_CTL("Speaker MBC 1 BiQuad 1", BIQUAD_SIZE, 0xb0),
+	COEFF_RAM_CTL("Speaker MBC 1 BiQuad 2", BIQUAD_SIZE, 0xb5),
+
+	COEFF_RAM_CTL("Speaker MBC 2 BiQuad 1", BIQUAD_SIZE, 0xba),
+	COEFF_RAM_CTL("Speaker MBC 2 BiQuad 2", BIQUAD_SIZE, 0xbf),
+
+	COEFF_RAM_CTL("Speaker MBC 3 BiQuad 1", BIQUAD_SIZE, 0xc4),
+	COEFF_RAM_CTL("Speaker MBC 3 BiQuad 2", BIQUAD_SIZE, 0xc9),
+
+	COEFF_RAM_CTL("Sub Cascade 1 Left BiQuad 1", BIQUAD_SIZE, 0x00),
+	COEFF_RAM_CTL("Sub Cascade 1 Left BiQuad 2", BIQUAD_SIZE, 0x05),
+	COEFF_RAM_CTL("Sub Cascade 1 Left BiQuad 3", BIQUAD_SIZE, 0x0a),
+	COEFF_RAM_CTL("Sub Cascade 1 Left BiQuad 4", BIQUAD_SIZE, 0x0f),
+	COEFF_RAM_CTL("Sub Cascade 1 Left BiQuad 5", BIQUAD_SIZE, 0x14),
+	COEFF_RAM_CTL("Sub Cascade 1 Left BiQuad 6", BIQUAD_SIZE, 0x19),
+
+	COEFF_RAM_CTL("Sub Cascade 1 Right BiQuad 1", BIQUAD_SIZE, 0x20),
+	COEFF_RAM_CTL("Sub Cascade 1 Right BiQuad 2", BIQUAD_SIZE, 0x25),
+	COEFF_RAM_CTL("Sub Cascade 1 Right BiQuad 3", BIQUAD_SIZE, 0x2a),
+	COEFF_RAM_CTL("Sub Cascade 1 Right BiQuad 4", BIQUAD_SIZE, 0x2f),
+	COEFF_RAM_CTL("Sub Cascade 1 Right BiQuad 5", BIQUAD_SIZE, 0x34),
+	COEFF_RAM_CTL("Sub Cascade 1 Right BiQuad 6", BIQUAD_SIZE, 0x39),
+
+	COEFF_RAM_CTL("Sub Cascade 1 Left Prescale", COEFF_SIZE, 0x1f),
+	COEFF_RAM_CTL("Sub Cascade 1 Right Prescale", COEFF_SIZE, 0x3f),
+
+	COEFF_RAM_CTL("Sub Cascade 2 Left BiQuad 1", BIQUAD_SIZE, 0x40),
+	COEFF_RAM_CTL("Sub Cascade 2 Left BiQuad 2", BIQUAD_SIZE, 0x45),
+	COEFF_RAM_CTL("Sub Cascade 2 Left BiQuad 3", BIQUAD_SIZE, 0x4a),
+	COEFF_RAM_CTL("Sub Cascade 2 Left BiQuad 4", BIQUAD_SIZE, 0x4f),
+	COEFF_RAM_CTL("Sub Cascade 2 Left BiQuad 5", BIQUAD_SIZE, 0x54),
+	COEFF_RAM_CTL("Sub Cascade 2 Left BiQuad 6", BIQUAD_SIZE, 0x59),
+
+	COEFF_RAM_CTL("Sub Cascade 2 Right BiQuad 1", BIQUAD_SIZE, 0x60),
+	COEFF_RAM_CTL("Sub Cascade 2 Right BiQuad 2", BIQUAD_SIZE, 0x65),
+	COEFF_RAM_CTL("Sub Cascade 2 Right BiQuad 3", BIQUAD_SIZE, 0x6a),
+	COEFF_RAM_CTL("Sub Cascade 2 Right BiQuad 4", BIQUAD_SIZE, 0x6f),
+	COEFF_RAM_CTL("Sub Cascade 2 Right BiQuad 5", BIQUAD_SIZE, 0x74),
+	COEFF_RAM_CTL("Sub Cascade 2 Right BiQuad 6", BIQUAD_SIZE, 0x79),
+
+	COEFF_RAM_CTL("Sub Cascade 2 Left Prescale", COEFF_SIZE, 0x5f),
+	COEFF_RAM_CTL("Sub Cascade 2 Right Prescale", COEFF_SIZE, 0x7f),
+
+	COEFF_RAM_CTL("Sub Bass Extraction BiQuad 1", BIQUAD_SIZE, 0x80),
+	COEFF_RAM_CTL("Sub Bass Extraction BiQuad 2", BIQUAD_SIZE, 0x85),
+
+	COEFF_RAM_CTL("Sub Bass Non Linear Function 1", COEFF_SIZE, 0x8a),
+	COEFF_RAM_CTL("Sub Bass Non Linear Function 2", COEFF_SIZE, 0x8b),
+
+	COEFF_RAM_CTL("Sub Bass Limiter BiQuad", BIQUAD_SIZE, 0x8c),
+
+	COEFF_RAM_CTL("Sub Bass Cut Off BiQuad", BIQUAD_SIZE, 0x91),
+
+	COEFF_RAM_CTL("Sub Bass Mix", COEFF_SIZE, 0x96),
+
+	COEFF_RAM_CTL("Sub Treb Extraction BiQuad 1", BIQUAD_SIZE, 0x97),
+	COEFF_RAM_CTL("Sub Treb Extraction BiQuad 2", BIQUAD_SIZE, 0x9c),
+
+	COEFF_RAM_CTL("Sub Treb Non Linear Function 1", COEFF_SIZE, 0xa1),
+	COEFF_RAM_CTL("Sub Treb Non Linear Function 2", COEFF_SIZE, 0xa2),
+
+	COEFF_RAM_CTL("Sub Treb Limiter BiQuad", BIQUAD_SIZE, 0xa3),
+
+	COEFF_RAM_CTL("Sub Treb Cut Off BiQuad", BIQUAD_SIZE, 0xa8),
+
+	COEFF_RAM_CTL("Sub Treb Mix", COEFF_SIZE, 0xad),
+
+	COEFF_RAM_CTL("Sub 3D", COEFF_SIZE, 0xae),
+
+	COEFF_RAM_CTL("Sub 3D Mix", COEFF_SIZE, 0xaf),
+
+	COEFF_RAM_CTL("Sub MBC 1 BiQuad 1", BIQUAD_SIZE, 0xb0),
+	COEFF_RAM_CTL("Sub MBC 1 BiQuad 2", BIQUAD_SIZE, 0xb5),
+
+	COEFF_RAM_CTL("Sub MBC 2 BiQuad 1", BIQUAD_SIZE, 0xba),
+	COEFF_RAM_CTL("Sub MBC 2 BiQuad 2", BIQUAD_SIZE, 0xbf),
+
+	COEFF_RAM_CTL("Sub MBC 3 BiQuad 1", BIQUAD_SIZE, 0xc4),
+	COEFF_RAM_CTL("Sub MBC 3 BiQuad 2", BIQUAD_SIZE, 0xc9),
+};
+
+static struct snd_soc_dapm_widget const tscs454_dapm_widgets[] = {
+	/* R_PLLCTL PG 0 ADDR 0x15 */
+	SND_SOC_DAPM_SUPPLY("PLL 1 Power", R_PLLCTL, FB_PLLCTL_PU_PLL1, 0,
+			pll_power_event,
+			SND_SOC_DAPM_POST_PMU|SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_SUPPLY("PLL 2 Power", R_PLLCTL, FB_PLLCTL_PU_PLL2, 0,
+			pll_power_event,
+			SND_SOC_DAPM_POST_PMU|SND_SOC_DAPM_PRE_PMD),
+	/* R_I2SPINC0 PG 0 ADDR 0x22 */
+	SND_SOC_DAPM_AIF_OUT("DAI 3 Out", "DAI 3 Capture", 0,
+			R_I2SPINC0, FB_I2SPINC0_SDO3TRI, 1),
+	SND_SOC_DAPM_AIF_OUT("DAI 2 Out", "DAI 2 Capture", 0,
+			R_I2SPINC0, FB_I2SPINC0_SDO2TRI, 1),
+	SND_SOC_DAPM_AIF_OUT("DAI 1 Out", "DAI 1 Capture", 0,
+			R_I2SPINC0, FB_I2SPINC0_SDO1TRI, 1),
+	/* R_PWRM0 PG 0 ADDR 0x33 */
+	SND_SOC_DAPM_ADC("Input Processor Channel 3", NULL,
+			R_PWRM0, FB_PWRM0_INPROC3PU, 0),
+	SND_SOC_DAPM_ADC("Input Processor Channel 2", NULL,
+			R_PWRM0, FB_PWRM0_INPROC2PU, 0),
+	SND_SOC_DAPM_ADC("Input Processor Channel 1", NULL,
+			R_PWRM0, FB_PWRM0_INPROC1PU, 0),
+	SND_SOC_DAPM_ADC("Input Processor Channel 0", NULL,
+			R_PWRM0, FB_PWRM0_INPROC0PU, 0),
+	SND_SOC_DAPM_SUPPLY("Mic Bias 2",
+			R_PWRM0, FB_PWRM0_MICB2PU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Mic Bias 1", R_PWRM0,
+			FB_PWRM0_MICB1PU, 0, NULL, 0),
+	/* R_PWRM1 PG 0 ADDR 0x34 */
+	SND_SOC_DAPM_SUPPLY("Sub Power", R_PWRM1, FB_PWRM1_SUBPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Headphone Left Power",
+			R_PWRM1, FB_PWRM1_HPLPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Headphone Right Power",
+			R_PWRM1, FB_PWRM1_HPRPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Speaker Left Power",
+			R_PWRM1, FB_PWRM1_SPKLPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Speaker Right Power",
+			R_PWRM1, FB_PWRM1_SPKRPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Differential Input 2 Power",
+			R_PWRM1, FB_PWRM1_D2S2PU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Differential Input 1 Power",
+			R_PWRM1, FB_PWRM1_D2S1PU, 0, NULL, 0),
+	/* R_PWRM2 PG 0 ADDR 0x35 */
+	SND_SOC_DAPM_SUPPLY("DAI 3 Out Power",
+			R_PWRM2, FB_PWRM2_I2S3OPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DAI 2 Out Power",
+			R_PWRM2, FB_PWRM2_I2S2OPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DAI 1 Out Power",
+			R_PWRM2, FB_PWRM2_I2S1OPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DAI 3 In Power",
+			R_PWRM2, FB_PWRM2_I2S3IPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DAI 2 In Power",
+			R_PWRM2, FB_PWRM2_I2S2IPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DAI 1 In Power",
+			R_PWRM2, FB_PWRM2_I2S1IPU, 0, NULL, 0),
+	/* R_PWRM3 PG 0 ADDR 0x36 */
+	SND_SOC_DAPM_SUPPLY("Line Out Left Power",
+			R_PWRM3, FB_PWRM3_LLINEPU, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Line Out Right Power",
+			R_PWRM3, FB_PWRM3_RLINEPU, 0, NULL, 0),
+	/* R_PWRM4 PG 0 ADDR 0x37 */
+	SND_SOC_DAPM_DAC("Sub", NULL, R_PWRM4, FB_PWRM4_OPSUBPU, 0),
+	SND_SOC_DAPM_DAC("DAC Left", NULL, R_PWRM4, FB_PWRM4_OPDACLPU, 0),
+	SND_SOC_DAPM_DAC("DAC Right", NULL, R_PWRM4, FB_PWRM4_OPDACRPU, 0),
+	SND_SOC_DAPM_DAC("ClassD Left", NULL, R_PWRM4, FB_PWRM4_OPSPKLPU, 0),
+	SND_SOC_DAPM_DAC("ClassD Right", NULL, R_PWRM4, FB_PWRM4_OPSPKRPU, 0),
+	/* R_AUDIOMUX1  PG 0 ADDR 0x3A */
+	SND_SOC_DAPM_MUX("DAI 2 Out Mux", SND_SOC_NOPM, 0, 0,
+			&dai2_mux_dapm_enum),
+	SND_SOC_DAPM_MUX("DAI 1 Out Mux", SND_SOC_NOPM, 0, 0,
+			&dai1_mux_dapm_enum),
+	/* R_AUDIOMUX2 PG 0 ADDR 0x3B */
+	SND_SOC_DAPM_MUX("DAC Mux", SND_SOC_NOPM, 0, 0,
+			&dac_mux_dapm_enum),
+	SND_SOC_DAPM_MUX("DAI 3 Out Mux", SND_SOC_NOPM, 0, 0,
+			&dai3_mux_dapm_enum),
+	/* R_AUDIOMUX3 PG 0 ADDR 0x3C */
+	SND_SOC_DAPM_MUX("Sub Mux", SND_SOC_NOPM, 0, 0,
+			&sub_mux_dapm_enum),
+	SND_SOC_DAPM_MUX("Speaker Mux", SND_SOC_NOPM, 0, 0,
+			&classd_mux_dapm_enum),
+	/* R_HSDCTL1 PG 1 ADDR 0x01 */
+	SND_SOC_DAPM_SUPPLY("GHS Detect Power", R_HSDCTL1,
+			FB_HSDCTL1_CON_DET_PWD, 1, NULL, 0),
+	/* R_CH0AIC PG 1 ADDR 0x06 */
+	SND_SOC_DAPM_MUX("Input Boost Channel 0 Mux", SND_SOC_NOPM, 0, 0,
+			&in_bst_mux_ch0_dapm_enum),
+	SND_SOC_DAPM_MUX("ADC Channel 0 Mux", SND_SOC_NOPM, 0, 0,
+			&adc_mux_ch0_dapm_enum),
+	SND_SOC_DAPM_MUX("Input Processor Channel 0 Mux", SND_SOC_NOPM, 0, 0,
+			&in_proc_mux_ch0_dapm_enum),
+	/* R_CH1AIC PG 1 ADDR 0x07 */
+	SND_SOC_DAPM_MUX("Input Boost Channel 1 Mux", SND_SOC_NOPM, 0, 0,
+			&in_bst_mux_ch1_dapm_enum),
+	SND_SOC_DAPM_MUX("ADC Channel 1 Mux", SND_SOC_NOPM, 0, 0,
+			&adc_mux_ch1_dapm_enum),
+	SND_SOC_DAPM_MUX("Input Processor Channel 1 Mux", SND_SOC_NOPM, 0, 0,
+			&in_proc_mux_ch1_dapm_enum),
+	/* Virtual */
+	SND_SOC_DAPM_AIF_IN("DAI 3 In", "DAI 3 Playback", 0,
+			SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("DAI 2 In", "DAI 2 Playback", 0,
+			SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("DAI 1 In", "DAI 1 Playback", 0,
+			SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_SUPPLY("PLLs", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_OUTPUT("Sub Out"),
+	SND_SOC_DAPM_OUTPUT("Headphone Left"),
+	SND_SOC_DAPM_OUTPUT("Headphone Right"),
+	SND_SOC_DAPM_OUTPUT("Speaker Left"),
+	SND_SOC_DAPM_OUTPUT("Speaker Right"),
+	SND_SOC_DAPM_OUTPUT("Line Out Left"),
+	SND_SOC_DAPM_OUTPUT("Line Out Right"),
+	SND_SOC_DAPM_INPUT("D2S 2"),
+	SND_SOC_DAPM_INPUT("D2S 1"),
+	SND_SOC_DAPM_INPUT("Line In 1 Left"),
+	SND_SOC_DAPM_INPUT("Line In 1 Right"),
+	SND_SOC_DAPM_INPUT("Line In 2 Left"),
+	SND_SOC_DAPM_INPUT("Line In 2 Right"),
+	SND_SOC_DAPM_INPUT("Line In 3 Left"),
+	SND_SOC_DAPM_INPUT("Line In 3 Right"),
+	SND_SOC_DAPM_INPUT("DMic 1"),
+	SND_SOC_DAPM_INPUT("DMic 2"),
+
+	SND_SOC_DAPM_MUX("CH 0_1 Mux", SND_SOC_NOPM, 0, 0,
+			&ch_0_1_mux_dapm_enum),
+	SND_SOC_DAPM_MUX("CH 2_3 Mux", SND_SOC_NOPM, 0, 0,
+			&ch_2_3_mux_dapm_enum),
+	SND_SOC_DAPM_MUX("CH 4_5 Mux", SND_SOC_NOPM, 0, 0,
+			&ch_4_5_mux_dapm_enum),
+};
+
+static struct snd_soc_dapm_route const tscs454_intercon[] = {
+	/* PLLs */
+	{"PLLs", NULL, "PLL 1 Power", pll_connected},
+	{"PLLs", NULL, "PLL 2 Power", pll_connected},
+	/* Inputs */
+	{"DAI 3 In", NULL, "DAI 3 In Power"},
+	{"DAI 2 In", NULL, "DAI 2 In Power"},
+	{"DAI 1 In", NULL, "DAI 1 In Power"},
+	/* Outputs */
+	{"DAI 3 Out", NULL, "DAI 3 Out Power"},
+	{"DAI 2 Out", NULL, "DAI 2 Out Power"},
+	{"DAI 1 Out", NULL, "DAI 1 Out Power"},
+	/* Ch Muxing */
+	{"CH 0_1 Mux", "DAI 1", "DAI 1 In"},
+	{"CH 0_1 Mux", "TDM 0_1", "DAI 1 In"},
+	{"CH 2_3 Mux", "DAI 2", "DAI 2 In"},
+	{"CH 2_3 Mux", "TDM 2_3", "DAI 1 In"},
+	{"CH 4_5 Mux", "DAI 3", "DAI 2 In"},
+	{"CH 4_5 Mux", "TDM 4_5", "DAI 1 In"},
+	/* In/Out Muxing */
+	{"DAI 1 Out Mux", "CH 0_1", "CH 0_1 Mux"},
+	{"DAI 1 Out Mux", "CH 2_3", "CH 2_3 Mux"},
+	{"DAI 1 Out Mux", "CH 4_5", "CH 4_5 Mux"},
+	{"DAI 2 Out Mux", "CH 0_1", "CH 0_1 Mux"},
+	{"DAI 2 Out Mux", "CH 2_3", "CH 2_3 Mux"},
+	{"DAI 2 Out Mux", "CH 4_5", "CH 4_5 Mux"},
+	{"DAI 3 Out Mux", "CH 0_1", "CH 0_1 Mux"},
+	{"DAI 3 Out Mux", "CH 2_3", "CH 2_3 Mux"},
+	{"DAI 3 Out Mux", "CH 4_5", "CH 4_5 Mux"},
+	/******************
+	 * Playback Paths *
+	 ******************/
+	/* DAC Path */
+	{"DAC Mux", "CH 4_5", "CH 4_5 Mux"},
+	{"DAC Mux", "CH 2_3", "CH 2_3 Mux"},
+	{"DAC Mux", "CH 0_1", "CH 0_1 Mux"},
+	{"DAC Left", NULL, "DAC Mux"},
+	{"DAC Right", NULL, "DAC Mux"},
+	{"DAC Left", NULL, "PLLs"},
+	{"DAC Right", NULL, "PLLs"},
+	{"Headphone Left", NULL, "Headphone Left Power"},
+	{"Headphone Right", NULL, "Headphone Right Power"},
+	{"Headphone Left", NULL, "DAC Left"},
+	{"Headphone Right", NULL, "DAC Right"},
+	/* Line Out */
+	{"Line Out Left", NULL, "Line Out Left Power"},
+	{"Line Out Right", NULL, "Line Out Right Power"},
+	{"Line Out Left", NULL, "DAC Left"},
+	{"Line Out Right", NULL, "DAC Right"},
+	/* ClassD Path */
+	{"Speaker Mux", "CH 4_5", "CH 4_5 Mux"},
+	{"Speaker Mux", "CH 2_3", "CH 2_3 Mux"},
+	{"Speaker Mux", "CH 0_1", "CH 0_1 Mux"},
+	{"ClassD Left", NULL, "Speaker Mux"},
+	{"ClassD Right", NULL, "Speaker Mux"},
+	{"ClassD Left", NULL, "PLLs"},
+	{"ClassD Right", NULL, "PLLs"},
+	{"Speaker Left", NULL, "Speaker Left Power"},
+	{"Speaker Right", NULL, "Speaker Right Power"},
+	{"Speaker Left", NULL, "ClassD Left"},
+	{"Speaker Right", NULL, "ClassD Right"},
+	/* Sub Path */
+	{"Sub Mux", "CH 4", "CH 4_5 Mux"},
+	{"Sub Mux", "CH 5", "CH 4_5 Mux"},
+	{"Sub Mux", "CH 4 + 5", "CH 4_5 Mux"},
+	{"Sub Mux", "CH 2", "CH 2_3 Mux"},
+	{"Sub Mux", "CH 3", "CH 2_3 Mux"},
+	{"Sub Mux", "CH 2 + 3", "CH 2_3 Mux"},
+	{"Sub Mux", "CH 0", "CH 0_1 Mux"},
+	{"Sub Mux", "CH 1", "CH 0_1 Mux"},
+	{"Sub Mux", "CH 0 + 1", "CH 0_1 Mux"},
+	{"Sub Mux", "ADC/DMic 1 Left", "Input Processor Channel 0"},
+	{"Sub Mux", "ADC/DMic 1 Right", "Input Processor Channel 1"},
+	{"Sub Mux", "ADC/DMic 1 Left Plus Right", "Input Processor Channel 0"},
+	{"Sub Mux", "ADC/DMic 1 Left Plus Right", "Input Processor Channel 1"},
+	{"Sub Mux", "DMic 2 Left", "DMic 2"},
+	{"Sub Mux", "DMic 2 Right", "DMic 2"},
+	{"Sub Mux", "DMic 2 Left Plus Right", "DMic 2"},
+	{"Sub Mux", "ClassD Left", "ClassD Left"},
+	{"Sub Mux", "ClassD Right", "ClassD Right"},
+	{"Sub Mux", "ClassD Left Plus Right", "ClassD Left"},
+	{"Sub Mux", "ClassD Left Plus Right", "ClassD Right"},
+	{"Sub", NULL, "Sub Mux"},
+	{"Sub", NULL, "PLLs"},
+	{"Sub Out", NULL, "Sub Power"},
+	{"Sub Out", NULL, "Sub"},
+	/*****************
+	 * Capture Paths *
+	 *****************/
+	{"Input Boost Channel 0 Mux", "Input 3", "Line In 3 Left"},
+	{"Input Boost Channel 0 Mux", "Input 2", "Line In 2 Left"},
+	{"Input Boost Channel 0 Mux", "Input 1", "Line In 1 Left"},
+	{"Input Boost Channel 0 Mux", "D2S", "D2S 1"},
+
+	{"Input Boost Channel 1 Mux", "Input 3", "Line In 3 Right"},
+	{"Input Boost Channel 1 Mux", "Input 2", "Line In 2 Right"},
+	{"Input Boost Channel 1 Mux", "Input 1", "Line In 1 Right"},
+	{"Input Boost Channel 1 Mux", "D2S", "D2S 2"},
+
+	{"ADC Channel 0 Mux", "Input 3 Boost Bypass", "Line In 3 Left"},
+	{"ADC Channel 0 Mux", "Input 2 Boost Bypass", "Line In 2 Left"},
+	{"ADC Channel 0 Mux", "Input 1 Boost Bypass", "Line In 1 Left"},
+	{"ADC Channel 0 Mux", "Input Boost", "Input Boost Channel 0 Mux"},
+
+	{"ADC Channel 1 Mux", "Input 3 Boost Bypass", "Line In 3 Right"},
+	{"ADC Channel 1 Mux", "Input 2 Boost Bypass", "Line In 2 Right"},
+	{"ADC Channel 1 Mux", "Input 1 Boost Bypass", "Line In 1 Right"},
+	{"ADC Channel 1 Mux", "Input Boost", "Input Boost Channel 1 Mux"},
+
+	{"Input Processor Channel 0 Mux", "ADC", "ADC Channel 0 Mux"},
+	{"Input Processor Channel 0 Mux", "DMic", "DMic 1"},
+
+	{"Input Processor Channel 0", NULL, "PLLs"},
+	{"Input Processor Channel 0", NULL, "Input Processor Channel 0 Mux"},
+
+	{"Input Processor Channel 1 Mux", "ADC", "ADC Channel 1 Mux"},
+	{"Input Processor Channel 1 Mux", "DMic", "DMic 1"},
+
+	{"Input Processor Channel 1", NULL, "PLLs"},
+	{"Input Processor Channel 1", NULL, "Input Processor Channel 1 Mux"},
+
+	{"Input Processor Channel 2", NULL, "PLLs"},
+	{"Input Processor Channel 2", NULL, "DMic 2"},
+
+	{"Input Processor Channel 3", NULL, "PLLs"},
+	{"Input Processor Channel 3", NULL, "DMic 2"},
+
+	{"DAI 1 Out Mux", "ADC/DMic 1", "Input Processor Channel 0"},
+	{"DAI 1 Out Mux", "ADC/DMic 1", "Input Processor Channel 1"},
+	{"DAI 1 Out Mux", "DMic 2", "Input Processor Channel 2"},
+	{"DAI 1 Out Mux", "DMic 2", "Input Processor Channel 3"},
+
+	{"DAI 2 Out Mux", "ADC/DMic 1", "Input Processor Channel 0"},
+	{"DAI 2 Out Mux", "ADC/DMic 1", "Input Processor Channel 1"},
+	{"DAI 2 Out Mux", "DMic 2", "Input Processor Channel 2"},
+	{"DAI 2 Out Mux", "DMic 2", "Input Processor Channel 3"},
+
+	{"DAI 3 Out Mux", "ADC/DMic 1", "Input Processor Channel 0"},
+	{"DAI 3 Out Mux", "ADC/DMic 1", "Input Processor Channel 1"},
+	{"DAI 3 Out Mux", "DMic 2", "Input Processor Channel 2"},
+	{"DAI 3 Out Mux", "DMic 2", "Input Processor Channel 3"},
+
+	{"DAI 1 Out", NULL, "DAI 1 Out Mux"},
+	{"DAI 2 Out", NULL, "DAI 2 Out Mux"},
+	{"DAI 3 Out", NULL, "DAI 3 Out Mux"},
+};
+
+/* This is used when BCLK is sourcing the PLLs */
+static int tscs454_set_sysclk(struct snd_soc_dai *dai,
+		int clk_id, unsigned int freq, int dir)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	unsigned int val;
+	int bclk_dai;
+	int ret;
+
+	dev_dbg(component->dev, "%s(): freq = %u\n", __func__, freq);
+
+	ret = snd_soc_component_read(component, R_PLLCTL, &val);
+	if (ret < 0)
+		return ret;
+
+	bclk_dai = (val & FM_PLLCTL_BCLKSEL) >> FB_PLLCTL_BCLKSEL;
+	if (bclk_dai != dai->id)
+		return 0;
+
+	tscs454->bclk_freq = freq;
+	return set_sysclk(component);
+}
+
+static int tscs454_set_bclk_ratio(struct snd_soc_dai *dai,
+		unsigned int ratio)
+{
+	unsigned int mask;
+	int ret;
+	struct snd_soc_component *component = dai->component;
+	unsigned int val;
+	int shift;
+
+	dev_dbg(component->dev, "set_bclk_ratio() id = %d ratio = %u\n",
+			dai->id, ratio);
+
+	switch (dai->id) {
+	case TSCS454_DAI1_ID:
+		mask = FM_I2SCMC_BCMP1;
+		shift = FB_I2SCMC_BCMP1;
+		break;
+	case TSCS454_DAI2_ID:
+		mask = FM_I2SCMC_BCMP2;
+		shift = FB_I2SCMC_BCMP2;
+		break;
+	case TSCS454_DAI3_ID:
+		mask = FM_I2SCMC_BCMP3;
+		shift = FB_I2SCMC_BCMP3;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Unknown audio interface (%d)\n", ret);
+		return ret;
+	}
+
+	switch (ratio) {
+	case 32:
+		val = I2SCMC_BCMP_32X;
+		break;
+	case 40:
+		val = I2SCMC_BCMP_40X;
+		break;
+	case 64:
+		val = I2SCMC_BCMP_64X;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Unsupported bclk ratio (%d)\n", ret);
+		return ret;
+	}
+
+	ret = snd_soc_component_update_bits(component,
+			R_I2SCMC, mask, val << shift);
+	if (ret < 0) {
+		dev_err(component->dev,
+				"Failed to set DAI BCLK ratio (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline int set_aif_master_from_fmt(struct snd_soc_component *component,
+		struct aif *aif, unsigned int fmt)
+{
+	int ret;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		aif->master = true;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		aif->master = false;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Unsupported format (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline int set_aif_tdm_delay(struct snd_soc_component *component,
+		unsigned int dai_id, bool delay)
+{
+	unsigned int reg;
+	int ret;
+
+	switch (dai_id) {
+	case TSCS454_DAI1_ID:
+		reg = R_TDMCTL0;
+		break;
+	case TSCS454_DAI2_ID:
+		reg = R_PCMP2CTL0;
+		break;
+	case TSCS454_DAI3_ID:
+		reg = R_PCMP3CTL0;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev,
+				"DAI %d unknown (%d)\n", dai_id + 1, ret);
+		return ret;
+	}
+	ret = snd_soc_component_update_bits(component,
+			reg, FM_TDMCTL0_BDELAY, delay);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to setup tdm format (%d)\n",
+				ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline int set_aif_format_from_fmt(struct snd_soc_component *component,
+		unsigned int dai_id, unsigned int fmt)
+{
+	unsigned int reg;
+	unsigned int val;
+	int ret;
+
+	switch (dai_id) {
+	case TSCS454_DAI1_ID:
+		reg = R_I2SP1CTL;
+		break;
+	case TSCS454_DAI2_ID:
+		reg = R_I2SP2CTL;
+		break;
+	case TSCS454_DAI3_ID:
+		reg = R_I2SP3CTL;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev,
+				"DAI %d unknown (%d)\n", dai_id + 1, ret);
+		return ret;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_RIGHT_J:
+		val = FV_FORMAT_RIGHT;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		val = FV_FORMAT_LEFT;
+		break;
+	case SND_SOC_DAIFMT_I2S:
+		val = FV_FORMAT_I2S;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		ret = set_aif_tdm_delay(component, dai_id, true);
+		if (ret < 0)
+			return ret;
+		val = FV_FORMAT_TDM;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		ret = set_aif_tdm_delay(component, dai_id, false);
+		if (ret < 0)
+			return ret;
+		val = FV_FORMAT_TDM;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Format unsupported (%d)\n", ret);
+		return ret;
+	}
+
+	ret = snd_soc_component_update_bits(component,
+			reg, FM_I2SPCTL_FORMAT, val);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to set DAI %d format (%d)\n",
+				dai_id + 1, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline int
+set_aif_clock_format_from_fmt(struct snd_soc_component *component,
+		unsigned int dai_id, unsigned int fmt)
+{
+	unsigned int reg;
+	unsigned int val;
+	int ret;
+
+	switch (dai_id) {
+	case TSCS454_DAI1_ID:
+		reg = R_I2SP1CTL;
+		break;
+	case TSCS454_DAI2_ID:
+		reg = R_I2SP2CTL;
+		break;
+	case TSCS454_DAI3_ID:
+		reg = R_I2SP3CTL;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev,
+				"DAI %d unknown (%d)\n", dai_id + 1, ret);
+		return ret;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		val = FV_BCLKP_NOT_INVERTED | FV_LRCLKP_NOT_INVERTED;
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		val = FV_BCLKP_NOT_INVERTED | FV_LRCLKP_INVERTED;
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		val = FV_BCLKP_INVERTED | FV_LRCLKP_NOT_INVERTED;
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		val = FV_BCLKP_INVERTED | FV_LRCLKP_INVERTED;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Format unknown (%d)\n", ret);
+		return ret;
+	}
+
+	ret = snd_soc_component_update_bits(component, reg,
+			FM_I2SPCTL_BCLKP | FM_I2SPCTL_LRCLKP, val);
+	if (ret < 0) {
+		dev_err(component->dev,
+				"Failed to set clock polarity for DAI%d (%d)\n",
+				dai_id + 1, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int tscs454_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	struct aif *aif = &tscs454->aifs[dai->id];
+	int ret;
+
+	ret = set_aif_master_from_fmt(component, aif, fmt);
+	if (ret < 0)
+		return ret;
+
+	ret = set_aif_format_from_fmt(component, dai->id, fmt);
+	if (ret < 0)
+		return ret;
+
+	ret = set_aif_clock_format_from_fmt(component, dai->id, fmt);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int tscs454_dai1_set_tdm_slot(struct snd_soc_dai *dai,
+		unsigned int tx_mask, unsigned int rx_mask, int slots,
+		int slot_width)
+{
+	struct snd_soc_component *component = dai->component;
+	unsigned int val;
+	int ret;
+
+	if (!slots)
+		return 0;
+
+	if (tx_mask >= (1 << slots) || rx_mask >= (1 << slots)) {
+		ret = -EINVAL;
+		dev_err(component->dev, "Invalid TDM slot mask (%d)\n", ret);
+		return ret;
+	}
+
+	switch (slots) {
+	case 2:
+		val = FV_TDMSO_2 | FV_TDMSI_2;
+		break;
+	case 4:
+		val = FV_TDMSO_4 | FV_TDMSI_4;
+		break;
+	case 6:
+		val = FV_TDMSO_6 | FV_TDMSI_6;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Invalid number of slots (%d)\n", ret);
+		return ret;
+	}
+
+	switch (slot_width) {
+	case 16:
+		val = val | FV_TDMDSS_16;
+		break;
+	case 24:
+		val = val | FV_TDMDSS_24;
+		break;
+	case 32:
+		val = val | FV_TDMDSS_32;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Invalid TDM slot width (%d)\n", ret);
+		return ret;
+	}
+	ret = snd_soc_component_write(component, R_TDMCTL1, val);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to set slots (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int tscs454_dai23_set_tdm_slot(struct snd_soc_dai *dai,
+		unsigned int tx_mask, unsigned int rx_mask, int slots,
+		int slot_width)
+{
+	struct snd_soc_component *component = dai->component;
+	unsigned int reg;
+	unsigned int val;
+	int ret;
+
+	if (!slots)
+		return 0;
+
+	if (tx_mask >= (1 << slots) || rx_mask >= (1 << slots)) {
+		ret = -EINVAL;
+		dev_err(component->dev, "Invalid TDM slot mask (%d)\n", ret);
+		return ret;
+	}
+
+	switch (dai->id) {
+	case TSCS454_DAI2_ID:
+		reg = R_PCMP2CTL1;
+		break;
+	case TSCS454_DAI3_ID:
+		reg = R_PCMP3CTL1;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Unrecognized interface %d (%d)\n",
+				dai->id, ret);
+		return ret;
+	}
+
+	switch (slots) {
+	case 1:
+		val = FV_PCMSOP_1 | FV_PCMSIP_1;
+		break;
+	case 2:
+		val = FV_PCMSOP_2 | FV_PCMSIP_2;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Invalid number of slots (%d)\n", ret);
+		return ret;
+	}
+
+	switch (slot_width) {
+	case 16:
+		val = val | FV_PCMDSSP_16;
+		break;
+	case 24:
+		val = val | FV_PCMDSSP_24;
+		break;
+	case 32:
+		val = val | FV_PCMDSSP_32;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Invalid TDM slot width (%d)\n", ret);
+		return ret;
+	}
+	ret = snd_soc_component_write(component, reg, val);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to set slots (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int set_aif_fs(struct snd_soc_component *component,
+		unsigned int id,
+		unsigned int rate)
+{
+	unsigned int reg;
+	unsigned int br;
+	unsigned int bm;
+	int ret;
+
+	switch (rate) {
+	case 8000:
+		br = FV_I2SMBR_32;
+		bm = FV_I2SMBM_0PT25;
+		break;
+	case 16000:
+		br = FV_I2SMBR_32;
+		bm = FV_I2SMBM_0PT5;
+		break;
+	case 24000:
+		br = FV_I2SMBR_48;
+		bm = FV_I2SMBM_0PT5;
+		break;
+	case 32000:
+		br = FV_I2SMBR_32;
+		bm = FV_I2SMBM_1;
+		break;
+	case 48000:
+		br = FV_I2SMBR_48;
+		bm = FV_I2SMBM_1;
+		break;
+	case 96000:
+		br = FV_I2SMBR_48;
+		bm = FV_I2SMBM_2;
+		break;
+	case 11025:
+		br = FV_I2SMBR_44PT1;
+		bm = FV_I2SMBM_0PT25;
+		break;
+	case 22050:
+		br = FV_I2SMBR_44PT1;
+		bm = FV_I2SMBM_0PT5;
+		break;
+	case 44100:
+		br = FV_I2SMBR_44PT1;
+		bm = FV_I2SMBM_1;
+		break;
+	case 88200:
+		br = FV_I2SMBR_44PT1;
+		bm = FV_I2SMBM_2;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Unsupported sample rate (%d)\n", ret);
+		return ret;
+	}
+
+	switch (id) {
+	case TSCS454_DAI1_ID:
+		reg = R_I2S1MRATE;
+		break;
+	case TSCS454_DAI2_ID:
+		reg = R_I2S2MRATE;
+		break;
+	case TSCS454_DAI3_ID:
+		reg = R_I2S3MRATE;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "DAI ID not recognized (%d)\n", ret);
+		return ret;
+	}
+
+	ret = snd_soc_component_update_bits(component, reg,
+			FM_I2SMRATE_I2SMBR | FM_I2SMRATE_I2SMBM, br|bm);
+	if (ret < 0) {
+		dev_err(component->dev,
+				"Failed to update register (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int set_aif_sample_format(struct snd_soc_component *component,
+		snd_pcm_format_t format,
+		int aif_id)
+{
+	unsigned int reg;
+	unsigned int width;
+	int ret;
+
+	switch (format) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		width = FV_WL_16;
+		break;
+	case SNDRV_PCM_FORMAT_S20_3LE:
+		width = FV_WL_20;
+		break;
+	case SNDRV_PCM_FORMAT_S24_3LE:
+		width = FV_WL_24;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+	case SNDRV_PCM_FORMAT_S32_LE:
+		width = FV_WL_32;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Unsupported format width (%d)\n", ret);
+		return ret;
+	}
+
+	switch (aif_id) {
+	case TSCS454_DAI1_ID:
+		reg = R_I2SP1CTL;
+		break;
+	case TSCS454_DAI2_ID:
+		reg = R_I2SP2CTL;
+		break;
+	case TSCS454_DAI3_ID:
+		reg = R_I2SP3CTL;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "AIF ID not recognized (%d)\n", ret);
+		return ret;
+	}
+
+	ret = snd_soc_component_update_bits(component,
+			reg, FM_I2SPCTL_WL, width);
+	if (ret < 0) {
+		dev_err(component->dev,
+				"Failed to set sample width (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int tscs454_hw_params(struct snd_pcm_substream *substream,
+		struct snd_pcm_hw_params *params,
+		struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	unsigned int fs = params_rate(params);
+	struct aif *aif = &tscs454->aifs[dai->id];
+	unsigned int val;
+	int ret;
+
+	mutex_lock(&tscs454->aifs_status_lock);
+
+	dev_dbg(component->dev, "%s(): aif %d fs = %u\n", __func__,
+			aif->id, fs);
+
+	if (!aif_active(&tscs454->aifs_status, aif->id)) {
+		if (PLL_44_1K_RATE % fs)
+			aif->pll = &tscs454->pll1;
+		else
+			aif->pll = &tscs454->pll2;
+
+		dev_dbg(component->dev, "Reserving pll %d for aif %d\n",
+				aif->pll->id, aif->id);
+
+		reserve_pll(aif->pll);
+	}
+
+	if (!aifs_active(&tscs454->aifs_status)) { /* First active aif */
+		ret = snd_soc_component_read(component, R_ISRC, &val);
+		if (ret < 0)
+			goto exit;
+
+		if ((val & FM_ISRC_IBR) == FV_IBR_48)
+			tscs454->internal_rate.pll = &tscs454->pll1;
+		else
+			tscs454->internal_rate.pll = &tscs454->pll2;
+
+		dev_dbg(component->dev, "Reserving pll %d for ir\n",
+				tscs454->internal_rate.pll->id);
+
+		reserve_pll(tscs454->internal_rate.pll);
+	}
+
+	ret = set_aif_fs(component, aif->id, fs);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to set aif fs (%d)\n", ret);
+		goto exit;
+	}
+
+	ret = set_aif_sample_format(component, params_format(params), aif->id);
+	if (ret < 0) {
+		dev_err(component->dev,
+				"Failed to set aif sample format (%d)\n", ret);
+		goto exit;
+	}
+
+	set_aif_status_active(&tscs454->aifs_status, aif->id,
+			substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+
+	dev_dbg(component->dev, "Set aif %d active. Streams status is 0x%x\n",
+		aif->id, tscs454->aifs_status.streams);
+
+	ret = 0;
+exit:
+	mutex_unlock(&tscs454->aifs_status_lock);
+
+	return ret;
+}
+
+static int tscs454_hw_free(struct snd_pcm_substream *substream,
+		struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	struct aif *aif = &tscs454->aifs[dai->id];
+
+	return aif_free(component, aif,
+			substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+}
+
+static int tscs454_prepare(struct snd_pcm_substream *substream,
+		struct snd_soc_dai *dai)
+{
+	int ret;
+	struct snd_soc_component *component = dai->component;
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	struct aif *aif = &tscs454->aifs[dai->id];
+
+	ret = aif_prepare(component, aif);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static struct snd_soc_dai_ops const tscs454_dai1_ops = {
+	.set_sysclk	= tscs454_set_sysclk,
+	.set_bclk_ratio = tscs454_set_bclk_ratio,
+	.set_fmt	= tscs454_set_dai_fmt,
+	.set_tdm_slot	= tscs454_dai1_set_tdm_slot,
+	.hw_params	= tscs454_hw_params,
+	.hw_free	= tscs454_hw_free,
+	.prepare	= tscs454_prepare,
+};
+
+static struct snd_soc_dai_ops const tscs454_dai23_ops = {
+	.set_sysclk	= tscs454_set_sysclk,
+	.set_bclk_ratio = tscs454_set_bclk_ratio,
+	.set_fmt	= tscs454_set_dai_fmt,
+	.set_tdm_slot	= tscs454_dai23_set_tdm_slot,
+	.hw_params	= tscs454_hw_params,
+	.hw_free	= tscs454_hw_free,
+	.prepare	= tscs454_prepare,
+};
+
+static int tscs454_probe(struct snd_soc_component *component)
+{
+	struct tscs454 *tscs454 = snd_soc_component_get_drvdata(component);
+	unsigned int val;
+	int ret = 0;
+
+	switch (tscs454->sysclk_src_id) {
+	case PLL_INPUT_XTAL:
+		val = FV_PLLISEL_XTAL;
+		break;
+	case PLL_INPUT_MCLK1:
+		val = FV_PLLISEL_MCLK1;
+		break;
+	case PLL_INPUT_MCLK2:
+		val = FV_PLLISEL_MCLK2;
+		break;
+	case PLL_INPUT_BCLK:
+		val = FV_PLLISEL_BCLK;
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(component->dev, "Invalid sysclk src id (%d)\n", ret);
+		return ret;
+	}
+
+	ret = snd_soc_component_update_bits(component, R_PLLCTL,
+			FM_PLLCTL_PLLISEL, val);
+	if (ret < 0) {
+		dev_err(component->dev, "Failed to set PLL input (%d)\n", ret);
+		return ret;
+	}
+
+	if (tscs454->sysclk_src_id < PLL_INPUT_BCLK)
+		ret = set_sysclk(component);
+
+	return ret;
+}
+
+static const struct snd_soc_component_driver soc_component_dev_tscs454 = {
+	.probe =	tscs454_probe,
+	.dapm_widgets = tscs454_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(tscs454_dapm_widgets),
+	.dapm_routes = tscs454_intercon,
+	.num_dapm_routes = ARRAY_SIZE(tscs454_intercon),
+	.controls =	tscs454_snd_controls,
+	.num_controls = ARRAY_SIZE(tscs454_snd_controls),
+};
+
+#define TSCS454_RATES SNDRV_PCM_RATE_8000_96000
+
+#define TSCS454_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE \
+	| SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_S24_LE \
+	| SNDRV_PCM_FMTBIT_S32_LE)
+
+static struct snd_soc_dai_driver tscs454_dais[] = {
+	{
+		.name = "tscs454-dai1",
+		.id = TSCS454_DAI1_ID,
+		.playback = {
+			.stream_name = "DAI 1 Playback",
+			.channels_min = 1,
+			.channels_max = 6,
+			.rates = TSCS454_RATES,
+			.formats = TSCS454_FORMATS,},
+		.capture = {
+			.stream_name = "DAI 1 Capture",
+			.channels_min = 1,
+			.channels_max = 6,
+			.rates = TSCS454_RATES,
+			.formats = TSCS454_FORMATS,},
+		.ops = &tscs454_dai1_ops,
+		.symmetric_rates = 1,
+		.symmetric_channels = 1,
+		.symmetric_samplebits = 1,
+	},
+	{
+		.name = "tscs454-dai2",
+		.id = TSCS454_DAI2_ID,
+		.playback = {
+			.stream_name = "DAI 2 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = TSCS454_RATES,
+			.formats = TSCS454_FORMATS,},
+		.capture = {
+			.stream_name = "DAI 2 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = TSCS454_RATES,
+			.formats = TSCS454_FORMATS,},
+		.ops = &tscs454_dai23_ops,
+		.symmetric_rates = 1,
+		.symmetric_channels = 1,
+		.symmetric_samplebits = 1,
+	},
+	{
+		.name = "tscs454-dai3",
+		.id = TSCS454_DAI3_ID,
+		.playback = {
+			.stream_name = "DAI 3 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = TSCS454_RATES,
+			.formats = TSCS454_FORMATS,},
+		.capture = {
+			.stream_name = "DAI 3 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = TSCS454_RATES,
+			.formats = TSCS454_FORMATS,},
+		.ops = &tscs454_dai23_ops,
+		.symmetric_rates = 1,
+		.symmetric_channels = 1,
+		.symmetric_samplebits = 1,
+	},
+};
+
+static char const * const src_names[] = {
+	"xtal", "mclk1", "mclk2", "bclk"};
+
+static int tscs454_i2c_probe(struct i2c_client *i2c,
+		const struct i2c_device_id *id)
+{
+	struct tscs454 *tscs454;
+	int src;
+	int ret;
+
+	tscs454 = devm_kzalloc(&i2c->dev, sizeof(*tscs454), GFP_KERNEL);
+	if (!tscs454)
+		return -ENOMEM;
+
+	ret = tscs454_data_init(tscs454, i2c);
+	if (ret < 0)
+		return ret;
+
+	i2c_set_clientdata(i2c, tscs454);
+
+	for (src = PLL_INPUT_XTAL; src < PLL_INPUT_BCLK; src++) {
+		tscs454->sysclk = devm_clk_get(&i2c->dev, src_names[src]);
+		if (!IS_ERR(tscs454->sysclk)) {
+			break;
+		} else if (PTR_ERR(tscs454->sysclk) != -ENOENT) {
+			ret = PTR_ERR(tscs454->sysclk);
+			dev_err(&i2c->dev, "Failed to get sysclk (%d)\n", ret);
+			return ret;
+		}
+	}
+	dev_dbg(&i2c->dev, "PLL input is %s\n", src_names[src]);
+	tscs454->sysclk_src_id = src;
+
+	ret = regmap_write(tscs454->regmap,
+			R_RESET, FV_RESET_PWR_ON_DEFAULTS);
+	if (ret < 0) {
+		dev_err(&i2c->dev, "Failed to reset the component (%d)\n", ret);
+		return ret;
+	}
+	regcache_mark_dirty(tscs454->regmap);
+
+	ret = regmap_register_patch(tscs454->regmap, tscs454_patch,
+			ARRAY_SIZE(tscs454_patch));
+	if (ret < 0) {
+		dev_err(&i2c->dev, "Failed to apply patch (%d)\n", ret);
+		return ret;
+	}
+	/* Sync pg sel reg with cache */
+	regmap_write(tscs454->regmap, R_PAGESEL, 0x00);
+
+	ret = snd_soc_register_component(&i2c->dev, &soc_component_dev_tscs454,
+			tscs454_dais, ARRAY_SIZE(tscs454_dais));
+	if (ret) {
+		dev_err(&i2c->dev, "Failed to register component (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct i2c_device_id tscs454_i2c_id[] = {
+	{ "tscs454", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, tscs454_i2c_id);
+
+static const struct of_device_id tscs454_of_match[] = {
+	{ .compatible = "tempo,tscs454", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tscs454_of_match);
+
+static struct i2c_driver tscs454_i2c_driver = {
+	.driver = {
+		.name = "tscs454",
+		.of_match_table = tscs454_of_match,
+	},
+	.probe =    tscs454_i2c_probe,
+	.id_table = tscs454_i2c_id,
+};
+
+module_i2c_driver(tscs454_i2c_driver);
+
+MODULE_AUTHOR("Tempo Semiconductor <steven.eckhoff.opensource@gmail.com");
+MODULE_DESCRIPTION("ASoC TSCS454 driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/tscs454.h b/sound/soc/codecs/tscs454.h
new file mode 100644
index 000000000000..1142d73d3168
--- /dev/null
+++ b/sound/soc/codecs/tscs454.h
@@ -0,0 +1,2323 @@
+// SPDX-License-Identifier: GPL-2.0
+// tscs454.h -- TSCS454 ALSA SoC Audio driver
+// Copyright 2018 Tempo Semiconductor, Inc.
+// Author: Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
+
+#ifndef __REDWOODPUBLIC_H__
+#define __REDWOODPUBLIC_H__
+
+#define VIRT_BASE 0x00
+#define PAGE_LEN 0x100
+#define VIRT_PAGE_BASE(page) (VIRT_BASE + (PAGE_LEN * page))
+#define VIRT_ADDR(page, address) (VIRT_PAGE_BASE(page) + address)
+#define ADDR(page, virt_address) (virt_address - VIRT_PAGE_BASE(page))
+
+#define R_PAGESEL                       0x0
+#define R_RESET                         VIRT_ADDR(0x0, 0x1)
+#define R_IRQEN                         VIRT_ADDR(0x0, 0x2)
+#define R_IRQMASK                       VIRT_ADDR(0x0, 0x3)
+#define R_IRQSTAT                       VIRT_ADDR(0x0, 0x4)
+#define R_DEVADD0                       VIRT_ADDR(0x0, 0x6)
+#define R_DEVID                         VIRT_ADDR(0x0, 0x8)
+#define R_DEVREV                        VIRT_ADDR(0x0, 0x9)
+#define R_PLLSTAT                       VIRT_ADDR(0x0, 0x0A)
+#define R_PLL1CTL                       VIRT_ADDR(0x0, 0x0B)
+#define R_PLL1RDIV                      VIRT_ADDR(0x0, 0x0C)
+#define R_PLL1ODIV                      VIRT_ADDR(0x0, 0x0D)
+#define R_PLL1FDIVL                     VIRT_ADDR(0x0, 0x0E)
+#define R_PLL1FDIVH                     VIRT_ADDR(0x0, 0x0F)
+#define R_PLL2CTL                       VIRT_ADDR(0x0, 0x10)
+#define R_PLL2RDIV                      VIRT_ADDR(0x0, 0x11)
+#define R_PLL2ODIV                      VIRT_ADDR(0x0, 0x12)
+#define R_PLL2FDIVL                     VIRT_ADDR(0x0, 0x13)
+#define R_PLL2FDIVH                     VIRT_ADDR(0x0, 0x14)
+#define R_PLLCTL                        VIRT_ADDR(0x0, 0x15)
+#define R_ISRC                          VIRT_ADDR(0x0, 0x16)
+#define R_SCLKCTL                       VIRT_ADDR(0x0, 0x18)
+#define R_TIMEBASE                      VIRT_ADDR(0x0, 0x19)
+#define R_I2SP1CTL                      VIRT_ADDR(0x0, 0x1A)
+#define R_I2SP2CTL                      VIRT_ADDR(0x0, 0x1B)
+#define R_I2SP3CTL                      VIRT_ADDR(0x0, 0x1C)
+#define R_I2S1MRATE                     VIRT_ADDR(0x0, 0x1D)
+#define R_I2S2MRATE                     VIRT_ADDR(0x0, 0x1E)
+#define R_I2S3MRATE                     VIRT_ADDR(0x0, 0x1F)
+#define R_I2SCMC                        VIRT_ADDR(0x0, 0x20)
+#define R_MCLK2PINC                     VIRT_ADDR(0x0, 0x21)
+#define R_I2SPINC0                      VIRT_ADDR(0x0, 0x22)
+#define R_I2SPINC1                      VIRT_ADDR(0x0, 0x23)
+#define R_I2SPINC2                      VIRT_ADDR(0x0, 0x24)
+#define R_GPIOCTL0                      VIRT_ADDR(0x0, 0x25)
+#define R_GPIOCTL1                      VIRT_ADDR(0x0, 0x26)
+#define R_ASRC                          VIRT_ADDR(0x0, 0x28)
+#define R_TDMCTL0                       VIRT_ADDR(0x0, 0x2D)
+#define R_TDMCTL1                       VIRT_ADDR(0x0, 0x2E)
+#define R_PCMP2CTL0                     VIRT_ADDR(0x0, 0x2F)
+#define R_PCMP2CTL1                     VIRT_ADDR(0x0, 0x30)
+#define R_PCMP3CTL0                     VIRT_ADDR(0x0, 0x31)
+#define R_PCMP3CTL1                     VIRT_ADDR(0x0, 0x32)
+#define R_PWRM0                         VIRT_ADDR(0x0, 0x33)
+#define R_PWRM1                         VIRT_ADDR(0x0, 0x34)
+#define R_PWRM2                         VIRT_ADDR(0x0, 0x35)
+#define R_PWRM3                         VIRT_ADDR(0x0, 0x36)
+#define R_PWRM4                         VIRT_ADDR(0x0, 0x37)
+#define R_I2SIDCTL                      VIRT_ADDR(0x0, 0x38)
+#define R_I2SODCTL                      VIRT_ADDR(0x0, 0x39)
+#define R_AUDIOMUX1                     VIRT_ADDR(0x0, 0x3A)
+#define R_AUDIOMUX2                     VIRT_ADDR(0x0, 0x3B)
+#define R_AUDIOMUX3                     VIRT_ADDR(0x0, 0x3C)
+#define R_HSDCTL1                       VIRT_ADDR(0x1, 0x1)
+#define R_HSDCTL2                       VIRT_ADDR(0x1, 0x2)
+#define R_HSDSTAT                       VIRT_ADDR(0x1, 0x3)
+#define R_HSDDELAY                      VIRT_ADDR(0x1, 0x4)
+#define R_BUTCTL                        VIRT_ADDR(0x1, 0x5)
+#define R_CH0AIC                        VIRT_ADDR(0x1, 0x6)
+#define R_CH1AIC                        VIRT_ADDR(0x1, 0x7)
+#define R_CH2AIC                        VIRT_ADDR(0x1, 0x8)
+#define R_CH3AIC                        VIRT_ADDR(0x1, 0x9)
+#define R_ICTL0                         VIRT_ADDR(0x1, 0x0A)
+#define R_ICTL1                         VIRT_ADDR(0x1, 0x0B)
+#define R_MICBIAS                       VIRT_ADDR(0x1, 0x0C)
+#define R_PGACTL0                       VIRT_ADDR(0x1, 0x0D)
+#define R_PGACTL1                       VIRT_ADDR(0x1, 0x0E)
+#define R_PGACTL2                       VIRT_ADDR(0x1, 0x0F)
+#define R_PGACTL3                       VIRT_ADDR(0x1, 0x10)
+#define R_PGAZ                          VIRT_ADDR(0x1, 0x11)
+#define R_ICH0VOL                       VIRT_ADDR(0x1, 0x12)
+#define R_ICH1VOL                       VIRT_ADDR(0x1, 0x13)
+#define R_ICH2VOL                       VIRT_ADDR(0x1, 0x14)
+#define R_ICH3VOL                       VIRT_ADDR(0x1, 0x15)
+#define R_ASRCILVOL                     VIRT_ADDR(0x1, 0x16)
+#define R_ASRCIRVOL                     VIRT_ADDR(0x1, 0x17)
+#define R_ASRCOLVOL                     VIRT_ADDR(0x1, 0x18)
+#define R_ASRCORVOL                     VIRT_ADDR(0x1, 0x19)
+#define R_IVOLCTLU                      VIRT_ADDR(0x1, 0x1C)
+#define R_ALCCTL0                       VIRT_ADDR(0x1, 0x1D)
+#define R_ALCCTL1                       VIRT_ADDR(0x1, 0x1E)
+#define R_ALCCTL2                       VIRT_ADDR(0x1, 0x1F)
+#define R_ALCCTL3                       VIRT_ADDR(0x1, 0x20)
+#define R_NGATE                         VIRT_ADDR(0x1, 0x21)
+#define R_DMICCTL                       VIRT_ADDR(0x1, 0x22)
+#define R_DACCTL                        VIRT_ADDR(0x2, 0x1)
+#define R_SPKCTL                        VIRT_ADDR(0x2, 0x2)
+#define R_SUBCTL                        VIRT_ADDR(0x2, 0x3)
+#define R_DCCTL                         VIRT_ADDR(0x2, 0x4)
+#define R_OVOLCTLU                      VIRT_ADDR(0x2, 0x6)
+#define R_MUTEC                         VIRT_ADDR(0x2, 0x7)
+#define R_MVOLL                         VIRT_ADDR(0x2, 0x8)
+#define R_MVOLR                         VIRT_ADDR(0x2, 0x9)
+#define R_HPVOLL                        VIRT_ADDR(0x2, 0x0A)
+#define R_HPVOLR                        VIRT_ADDR(0x2, 0x0B)
+#define R_SPKVOLL                       VIRT_ADDR(0x2, 0x0C)
+#define R_SPKVOLR                       VIRT_ADDR(0x2, 0x0D)
+#define R_SUBVOL                        VIRT_ADDR(0x2, 0x10)
+#define R_COP0                          VIRT_ADDR(0x2, 0x11)
+#define R_COP1                          VIRT_ADDR(0x2, 0x12)
+#define R_COPSTAT                       VIRT_ADDR(0x2, 0x13)
+#define R_PWM0                          VIRT_ADDR(0x2, 0x14)
+#define R_PWM1                          VIRT_ADDR(0x2, 0x15)
+#define R_PWM2                          VIRT_ADDR(0x2, 0x16)
+#define R_PWM3                          VIRT_ADDR(0x2, 0x17)
+#define R_HPSW                          VIRT_ADDR(0x2, 0x18)
+#define R_THERMTS                       VIRT_ADDR(0x2, 0x19)
+#define R_THERMSPK1                     VIRT_ADDR(0x2, 0x1A)
+#define R_THERMSTAT                     VIRT_ADDR(0x2, 0x1B)
+#define R_SCSTAT                        VIRT_ADDR(0x2, 0x1C)
+#define R_SDMON                         VIRT_ADDR(0x2, 0x1D)
+#define R_SPKEQFILT                     VIRT_ADDR(0x3, 0x1)
+#define R_SPKCRWDL                      VIRT_ADDR(0x3, 0x2)
+#define R_SPKCRWDM                      VIRT_ADDR(0x3, 0x3)
+#define R_SPKCRWDH                      VIRT_ADDR(0x3, 0x4)
+#define R_SPKCRRDL                      VIRT_ADDR(0x3, 0x5)
+#define R_SPKCRRDM                      VIRT_ADDR(0x3, 0x6)
+#define R_SPKCRRDH                      VIRT_ADDR(0x3, 0x7)
+#define R_SPKCRADD                      VIRT_ADDR(0x3, 0x8)
+#define R_SPKCRS                        VIRT_ADDR(0x3, 0x9)
+#define R_SPKMBCEN                      VIRT_ADDR(0x3, 0x0A)
+#define R_SPKMBCCTL                     VIRT_ADDR(0x3, 0x0B)
+#define R_SPKMBCMUG1                    VIRT_ADDR(0x3, 0x0C)
+#define R_SPKMBCTHR1                    VIRT_ADDR(0x3, 0x0D)
+#define R_SPKMBCRAT1                    VIRT_ADDR(0x3, 0x0E)
+#define R_SPKMBCATK1L                   VIRT_ADDR(0x3, 0x0F)
+#define R_SPKMBCATK1H                   VIRT_ADDR(0x3, 0x10)
+#define R_SPKMBCREL1L                   VIRT_ADDR(0x3, 0x11)
+#define R_SPKMBCREL1H                   VIRT_ADDR(0x3, 0x12)
+#define R_SPKMBCMUG2                    VIRT_ADDR(0x3, 0x13)
+#define R_SPKMBCTHR2                    VIRT_ADDR(0x3, 0x14)
+#define R_SPKMBCRAT2                    VIRT_ADDR(0x3, 0x15)
+#define R_SPKMBCATK2L                   VIRT_ADDR(0x3, 0x16)
+#define R_SPKMBCATK2H                   VIRT_ADDR(0x3, 0x17)
+#define R_SPKMBCREL2L                   VIRT_ADDR(0x3, 0x18)
+#define R_SPKMBCREL2H                   VIRT_ADDR(0x3, 0x19)
+#define R_SPKMBCMUG3                    VIRT_ADDR(0x3, 0x1A)
+#define R_SPKMBCTHR3                    VIRT_ADDR(0x3, 0x1B)
+#define R_SPKMBCRAT3                    VIRT_ADDR(0x3, 0x1C)
+#define R_SPKMBCATK3L                   VIRT_ADDR(0x3, 0x1D)
+#define R_SPKMBCATK3H                   VIRT_ADDR(0x3, 0x1E)
+#define R_SPKMBCREL3L                   VIRT_ADDR(0x3, 0x1F)
+#define R_SPKMBCREL3H                   VIRT_ADDR(0x3, 0x20)
+#define R_SPKCLECTL                     VIRT_ADDR(0x3, 0x21)
+#define R_SPKCLEMUG                     VIRT_ADDR(0x3, 0x22)
+#define R_SPKCOMPTHR                    VIRT_ADDR(0x3, 0x23)
+#define R_SPKCOMPRAT                    VIRT_ADDR(0x3, 0x24)
+#define R_SPKCOMPATKL                   VIRT_ADDR(0x3, 0x25)
+#define R_SPKCOMPATKH                   VIRT_ADDR(0x3, 0x26)
+#define R_SPKCOMPRELL                   VIRT_ADDR(0x3, 0x27)
+#define R_SPKCOMPRELH                   VIRT_ADDR(0x3, 0x28)
+#define R_SPKLIMTHR                     VIRT_ADDR(0x3, 0x29)
+#define R_SPKLIMTGT                     VIRT_ADDR(0x3, 0x2A)
+#define R_SPKLIMATKL                    VIRT_ADDR(0x3, 0x2B)
+#define R_SPKLIMATKH                    VIRT_ADDR(0x3, 0x2C)
+#define R_SPKLIMRELL                    VIRT_ADDR(0x3, 0x2D)
+#define R_SPKLIMRELH                    VIRT_ADDR(0x3, 0x2E)
+#define R_SPKEXPTHR                     VIRT_ADDR(0x3, 0x2F)
+#define R_SPKEXPRAT                     VIRT_ADDR(0x3, 0x30)
+#define R_SPKEXPATKL                    VIRT_ADDR(0x3, 0x31)
+#define R_SPKEXPATKH                    VIRT_ADDR(0x3, 0x32)
+#define R_SPKEXPRELL                    VIRT_ADDR(0x3, 0x33)
+#define R_SPKEXPRELH                    VIRT_ADDR(0x3, 0x34)
+#define R_SPKFXCTL                      VIRT_ADDR(0x3, 0x35)
+#define R_DACEQFILT                     VIRT_ADDR(0x4, 0x1)
+#define R_DACCRWDL                      VIRT_ADDR(0x4, 0x2)
+#define R_DACCRWDM                      VIRT_ADDR(0x4, 0x3)
+#define R_DACCRWDH                      VIRT_ADDR(0x4, 0x4)
+#define R_DACCRRDL                      VIRT_ADDR(0x4, 0x5)
+#define R_DACCRRDM                      VIRT_ADDR(0x4, 0x6)
+#define R_DACCRRDH                      VIRT_ADDR(0x4, 0x7)
+#define R_DACCRADD                      VIRT_ADDR(0x4, 0x8)
+#define R_DACCRS                        VIRT_ADDR(0x4, 0x9)
+#define R_DACMBCEN                      VIRT_ADDR(0x4, 0x0A)
+#define R_DACMBCCTL                     VIRT_ADDR(0x4, 0x0B)
+#define R_DACMBCMUG1                    VIRT_ADDR(0x4, 0x0C)
+#define R_DACMBCTHR1                    VIRT_ADDR(0x4, 0x0D)
+#define R_DACMBCRAT1                    VIRT_ADDR(0x4, 0x0E)
+#define R_DACMBCATK1L                   VIRT_ADDR(0x4, 0x0F)
+#define R_DACMBCATK1H                   VIRT_ADDR(0x4, 0x10)
+#define R_DACMBCREL1L                   VIRT_ADDR(0x4, 0x11)
+#define R_DACMBCREL1H                   VIRT_ADDR(0x4, 0x12)
+#define R_DACMBCMUG2                    VIRT_ADDR(0x4, 0x13)
+#define R_DACMBCTHR2                    VIRT_ADDR(0x4, 0x14)
+#define R_DACMBCRAT2                    VIRT_ADDR(0x4, 0x15)
+#define R_DACMBCATK2L                   VIRT_ADDR(0x4, 0x16)
+#define R_DACMBCATK2H                   VIRT_ADDR(0x4, 0x17)
+#define R_DACMBCREL2L                   VIRT_ADDR(0x4, 0x18)
+#define R_DACMBCREL2H                   VIRT_ADDR(0x4, 0x19)
+#define R_DACMBCMUG3                    VIRT_ADDR(0x4, 0x1A)
+#define R_DACMBCTHR3                    VIRT_ADDR(0x4, 0x1B)
+#define R_DACMBCRAT3                    VIRT_ADDR(0x4, 0x1C)
+#define R_DACMBCATK3L                   VIRT_ADDR(0x4, 0x1D)
+#define R_DACMBCATK3H                   VIRT_ADDR(0x4, 0x1E)
+#define R_DACMBCREL3L                   VIRT_ADDR(0x4, 0x1F)
+#define R_DACMBCREL3H                   VIRT_ADDR(0x4, 0x20)
+#define R_DACCLECTL                     VIRT_ADDR(0x4, 0x21)
+#define R_DACCLEMUG                     VIRT_ADDR(0x4, 0x22)
+#define R_DACCOMPTHR                    VIRT_ADDR(0x4, 0x23)
+#define R_DACCOMPRAT                    VIRT_ADDR(0x4, 0x24)
+#define R_DACCOMPATKL                   VIRT_ADDR(0x4, 0x25)
+#define R_DACCOMPATKH                   VIRT_ADDR(0x4, 0x26)
+#define R_DACCOMPRELL                   VIRT_ADDR(0x4, 0x27)
+#define R_DACCOMPRELH                   VIRT_ADDR(0x4, 0x28)
+#define R_DACLIMTHR                     VIRT_ADDR(0x4, 0x29)
+#define R_DACLIMTGT                     VIRT_ADDR(0x4, 0x2A)
+#define R_DACLIMATKL                    VIRT_ADDR(0x4, 0x2B)
+#define R_DACLIMATKH                    VIRT_ADDR(0x4, 0x2C)
+#define R_DACLIMRELL                    VIRT_ADDR(0x4, 0x2D)
+#define R_DACLIMRELH                    VIRT_ADDR(0x4, 0x2E)
+#define R_DACEXPTHR                     VIRT_ADDR(0x4, 0x2F)
+#define R_DACEXPRAT                     VIRT_ADDR(0x4, 0x30)
+#define R_DACEXPATKL                    VIRT_ADDR(0x4, 0x31)
+#define R_DACEXPATKH                    VIRT_ADDR(0x4, 0x32)
+#define R_DACEXPRELL                    VIRT_ADDR(0x4, 0x33)
+#define R_DACEXPRELH                    VIRT_ADDR(0x4, 0x34)
+#define R_DACFXCTL                      VIRT_ADDR(0x4, 0x35)
+#define R_SUBEQFILT                     VIRT_ADDR(0x5, 0x1)
+#define R_SUBCRWDL                      VIRT_ADDR(0x5, 0x2)
+#define R_SUBCRWDM                      VIRT_ADDR(0x5, 0x3)
+#define R_SUBCRWDH                      VIRT_ADDR(0x5, 0x4)
+#define R_SUBCRRDL                      VIRT_ADDR(0x5, 0x5)
+#define R_SUBCRRDM                      VIRT_ADDR(0x5, 0x6)
+#define R_SUBCRRDH                      VIRT_ADDR(0x5, 0x7)
+#define R_SUBCRADD                      VIRT_ADDR(0x5, 0x8)
+#define R_SUBCRS                        VIRT_ADDR(0x5, 0x9)
+#define R_SUBMBCEN                      VIRT_ADDR(0x5, 0x0A)
+#define R_SUBMBCCTL                     VIRT_ADDR(0x5, 0x0B)
+#define R_SUBMBCMUG1                    VIRT_ADDR(0x5, 0x0C)
+#define R_SUBMBCTHR1                    VIRT_ADDR(0x5, 0x0D)
+#define R_SUBMBCRAT1                    VIRT_ADDR(0x5, 0x0E)
+#define R_SUBMBCATK1L                   VIRT_ADDR(0x5, 0x0F)
+#define R_SUBMBCATK1H                   VIRT_ADDR(0x5, 0x10)
+#define R_SUBMBCREL1L                   VIRT_ADDR(0x5, 0x11)
+#define R_SUBMBCREL1H                   VIRT_ADDR(0x5, 0x12)
+#define R_SUBMBCMUG2                    VIRT_ADDR(0x5, 0x13)
+#define R_SUBMBCTHR2                    VIRT_ADDR(0x5, 0x14)
+#define R_SUBMBCRAT2                    VIRT_ADDR(0x5, 0x15)
+#define R_SUBMBCATK2L                   VIRT_ADDR(0x5, 0x16)
+#define R_SUBMBCATK2H                   VIRT_ADDR(0x5, 0x17)
+#define R_SUBMBCREL2L                   VIRT_ADDR(0x5, 0x18)
+#define R_SUBMBCREL2H                   VIRT_ADDR(0x5, 0x19)
+#define R_SUBMBCMUG3                    VIRT_ADDR(0x5, 0x1A)
+#define R_SUBMBCTHR3                    VIRT_ADDR(0x5, 0x1B)
+#define R_SUBMBCRAT3                    VIRT_ADDR(0x5, 0x1C)
+#define R_SUBMBCATK3L                   VIRT_ADDR(0x5, 0x1D)
+#define R_SUBMBCATK3H                   VIRT_ADDR(0x5, 0x1E)
+#define R_SUBMBCREL3L                   VIRT_ADDR(0x5, 0x1F)
+#define R_SUBMBCREL3H                   VIRT_ADDR(0x5, 0x20)
+#define R_SUBCLECTL                     VIRT_ADDR(0x5, 0x21)
+#define R_SUBCLEMUG                     VIRT_ADDR(0x5, 0x22)
+#define R_SUBCOMPTHR                    VIRT_ADDR(0x5, 0x23)
+#define R_SUBCOMPRAT                    VIRT_ADDR(0x5, 0x24)
+#define R_SUBCOMPATKL                   VIRT_ADDR(0x5, 0x25)
+#define R_SUBCOMPATKH                   VIRT_ADDR(0x5, 0x26)
+#define R_SUBCOMPRELL                   VIRT_ADDR(0x5, 0x27)
+#define R_SUBCOMPRELH                   VIRT_ADDR(0x5, 0x28)
+#define R_SUBLIMTHR                     VIRT_ADDR(0x5, 0x29)
+#define R_SUBLIMTGT                     VIRT_ADDR(0x5, 0x2A)
+#define R_SUBLIMATKL                    VIRT_ADDR(0x5, 0x2B)
+#define R_SUBLIMATKH                    VIRT_ADDR(0x5, 0x2C)
+#define R_SUBLIMRELL                    VIRT_ADDR(0x5, 0x2D)
+#define R_SUBLIMRELH                    VIRT_ADDR(0x5, 0x2E)
+#define R_SUBEXPTHR                     VIRT_ADDR(0x5, 0x2F)
+#define R_SUBEXPRAT                     VIRT_ADDR(0x5, 0x30)
+#define R_SUBEXPATKL                    VIRT_ADDR(0x5, 0x31)
+#define R_SUBEXPATKH                    VIRT_ADDR(0x5, 0x32)
+#define R_SUBEXPRELL                    VIRT_ADDR(0x5, 0x33)
+#define R_SUBEXPRELH                    VIRT_ADDR(0x5, 0x34)
+#define R_SUBFXCTL                      VIRT_ADDR(0x5, 0x35)
+
+// *** PLLCTL ***
+#define FB_PLLCTL_VCCI_PLL                                  6
+#define FM_PLLCTL_VCCI_PLL                                  0xC0
+
+#define FB_PLLCTL_RZ_PLL                                    3
+#define FM_PLLCTL_RZ_PLL                                    0x38
+
+#define FB_PLLCTL_CP_PLL                                    0
+#define FM_PLLCTL_CP_PLL                                    0x7
+
+// *** PLLRDIV ***
+#define FB_PLLRDIV_REFDIV_PLL                               0
+#define FM_PLLRDIV_REFDIV_PLL                               0xFF
+
+// *** PLLODIV ***
+#define FB_PLLODIV_OUTDIV_PLL                               0
+#define FM_PLLODIV_OUTDIV_PLL                               0xFF
+
+// *** PLLFDIVL ***
+#define FB_PLLFDIVL_FBDIVL_PLL                              0
+#define FM_PLLFDIVL_FBDIVL_PLL                              0xFF
+
+// *** PLLFDIVH ***
+#define FB_PLLFDIVH_FBDIVH_PLL                              0
+#define FM_PLLFDIVH_FBDIVH_PLL                              0xF
+
+// *** I2SPCTL ***
+#define FB_I2SPCTL_BCLKSTAT                                 7
+#define FM_I2SPCTL_BCLKSTAT                                 0x80
+#define FV_BCLKSTAT_LOST                                    0x80
+#define FV_BCLKSTAT_NOT_LOST                                0x0
+
+#define FB_I2SPCTL_BCLKP                                    6
+#define FM_I2SPCTL_BCLKP                                    0x40
+#define FV_BCLKP_NOT_INVERTED                               0x0
+#define FV_BCLKP_INVERTED                                   0x40
+
+#define FB_I2SPCTL_PORTMS                                   5
+#define FM_I2SPCTL_PORTMS                                   0x20
+#define FV_PORTMS_SLAVE                                     0x0
+#define FV_PORTMS_MASTER                                    0x20
+
+#define FB_I2SPCTL_LRCLKP                                   4
+#define FM_I2SPCTL_LRCLKP                                   0x10
+#define FV_LRCLKP_NOT_INVERTED                              0x0
+#define FV_LRCLKP_INVERTED                                  0x10
+
+#define FB_I2SPCTL_WL                                       2
+#define FM_I2SPCTL_WL                                       0xC
+#define FV_WL_16                                            0x0
+#define FV_WL_20                                            0x4
+#define FV_WL_24                                            0x8
+#define FV_WL_32                                            0xC
+
+#define FB_I2SPCTL_FORMAT                                   0
+#define FM_I2SPCTL_FORMAT                                   0x3
+#define FV_FORMAT_RIGHT                                     0x0
+#define FV_FORMAT_LEFT                                      0x1
+#define FV_FORMAT_I2S                                       0x2
+#define FV_FORMAT_TDM                                       0x3
+
+// *** I2SMRATE ***
+#define FB_I2SMRATE_I2SMCLKHALF                             7
+#define FM_I2SMRATE_I2SMCLKHALF                             0x80
+#define FV_I2SMCLKHALF_I2S1MCLKDIV_DIV_2                    0x0
+#define FV_I2SMCLKHALF_I2S1MCLKDIV_ONLY                     0x80
+
+#define FB_I2SMRATE_I2SMCLKDIV                              5
+#define FM_I2SMRATE_I2SMCLKDIV                              0x60
+#define FV_I2SMCLKDIV_125                                   0x0
+#define FV_I2SMCLKDIV_128                                   0x20
+#define FV_I2SMCLKDIV_136                                   0x40
+#define FV_I2SMCLKDIV_192                                   0x60
+
+#define FB_I2SMRATE_I2SMBR                                  3
+#define FM_I2SMRATE_I2SMBR                                  0x18
+#define FV_I2SMBR_32                                        0x0
+#define FV_I2SMBR_44PT1                                     0x8
+#define FV_I2SMBR_48                                        0x10
+#define FV_I2SMBR_MCLK_MODE                                 0x18
+
+#define FB_I2SMRATE_I2SMBM                                  0
+#define FM_I2SMRATE_I2SMBM                                  0x3
+#define FV_I2SMBM_0PT25                                     0x0
+#define FV_I2SMBM_0PT5                                      0x1
+#define FV_I2SMBM_1                                         0x2
+#define FV_I2SMBM_2                                         0x3
+
+// *** PCMPCTL0 ***
+#define FB_PCMPCTL0_PCMFLENP                                2
+#define FM_PCMPCTL0_PCMFLENP                                0x4
+#define FV_PCMFLENP_128                                     0x0
+#define FV_PCMFLENP_256                                     0x4
+
+#define FB_PCMPCTL0_SLSYNCP                                 1
+#define FM_PCMPCTL0_SLSYNCP                                 0x2
+#define FV_SLSYNCP_SHORT                                    0x0
+#define FV_SLSYNCP_LONG                                     0x2
+
+#define FB_PCMPCTL0_BDELAYP                                 0
+#define FM_PCMPCTL0_BDELAYP                                 0x1
+#define FV_BDELAYP_NO_DELAY                                 0x0
+#define FV_BDELAYP_1BCLK_DELAY                              0x1
+
+// *** PCMPCTL1 ***
+#define FB_PCMPCTL1_PCMMOMP                                 6
+#define FM_PCMPCTL1_PCMMOMP                                 0x40
+
+#define FB_PCMPCTL1_PCMSOP                                  5
+#define FM_PCMPCTL1_PCMSOP                                  0x20
+#define FV_PCMSOP_1                                         0x0
+#define FV_PCMSOP_2                                         0x20
+
+#define FB_PCMPCTL1_PCMDSSP                                 3
+#define FM_PCMPCTL1_PCMDSSP                                 0x18
+#define FV_PCMDSSP_16                                       0x0
+#define FV_PCMDSSP_24                                       0x8
+#define FV_PCMDSSP_32                                       0x10
+
+#define FB_PCMPCTL1_PCMMIMP                                 1
+#define FM_PCMPCTL1_PCMMIMP                                 0x2
+
+#define FB_PCMPCTL1_PCMSIP                                  0
+#define FM_PCMPCTL1_PCMSIP                                  0x1
+#define FV_PCMSIP_1                                         0x0
+#define FV_PCMSIP_2                                         0x1
+
+// *** CHAIC ***
+#define FB_CHAIC_MICBST                                     4
+#define FM_CHAIC_MICBST                                     0x30
+
+// *** PGACTL ***
+#define FB_PGACTL_PGAMUTE                                   7
+#define FM_PGACTL_PGAMUTE                                   0x80
+
+#define FB_PGACTL_PGAVOL                                    0
+#define FM_PGACTL_PGAVOL                                    0x3F
+
+// *** ICHVOL ***
+#define FB_ICHVOL_ICHVOL                                    0
+#define FM_ICHVOL_ICHVOL                                    0xFF
+
+// *** SPKMBCMUG ***
+#define FB_SPKMBCMUG_PHASE                                  5
+#define FM_SPKMBCMUG_PHASE                                  0x20
+
+#define FB_SPKMBCMUG_MUGAIN                                 0
+#define FM_SPKMBCMUG_MUGAIN                                 0x1F
+
+// *** SPKMBCTHR ***
+#define FB_SPKMBCTHR_THRESH                                 0
+#define FM_SPKMBCTHR_THRESH                                 0xFF
+
+// *** SPKMBCRAT ***
+#define FB_SPKMBCRAT_RATIO                                  0
+#define FM_SPKMBCRAT_RATIO                                  0x1F
+
+// *** SPKMBCATKL ***
+#define FB_SPKMBCATKL_TCATKL                                0
+#define FM_SPKMBCATKL_TCATKL                                0xFF
+
+// *** SPKMBCATKH ***
+#define FB_SPKMBCATKH_TCATKH                                0
+#define FM_SPKMBCATKH_TCATKH                                0xFF
+
+// *** SPKMBCRELL ***
+#define FB_SPKMBCRELL_TCRELL                                0
+#define FM_SPKMBCRELL_TCRELL                                0xFF
+
+// *** SPKMBCRELH ***
+#define FB_SPKMBCRELH_TCRELH                                0
+#define FM_SPKMBCRELH_TCRELH                                0xFF
+
+// *** DACMBCMUG ***
+#define FB_DACMBCMUG_PHASE                                  5
+#define FM_DACMBCMUG_PHASE                                  0x20
+
+#define FB_DACMBCMUG_MUGAIN                                 0
+#define FM_DACMBCMUG_MUGAIN                                 0x1F
+
+// *** DACMBCTHR ***
+#define FB_DACMBCTHR_THRESH                                 0
+#define FM_DACMBCTHR_THRESH                                 0xFF
+
+// *** DACMBCRAT ***
+#define FB_DACMBCRAT_RATIO                                  0
+#define FM_DACMBCRAT_RATIO                                  0x1F
+
+// *** DACMBCATKL ***
+#define FB_DACMBCATKL_TCATKL                                0
+#define FM_DACMBCATKL_TCATKL                                0xFF
+
+// *** DACMBCATKH ***
+#define FB_DACMBCATKH_TCATKH                                0
+#define FM_DACMBCATKH_TCATKH                                0xFF
+
+// *** DACMBCRELL ***
+#define FB_DACMBCRELL_TCRELL                                0
+#define FM_DACMBCRELL_TCRELL                                0xFF
+
+// *** DACMBCRELH ***
+#define FB_DACMBCRELH_TCRELH                                0
+#define FM_DACMBCRELH_TCRELH                                0xFF
+
+// *** SUBMBCMUG ***
+#define FB_SUBMBCMUG_PHASE                                  5
+#define FM_SUBMBCMUG_PHASE                                  0x20
+
+#define FB_SUBMBCMUG_MUGAIN                                 0
+#define FM_SUBMBCMUG_MUGAIN                                 0x1F
+
+// *** SUBMBCTHR ***
+#define FB_SUBMBCTHR_THRESH                                 0
+#define FM_SUBMBCTHR_THRESH                                 0xFF
+
+// *** SUBMBCRAT ***
+#define FB_SUBMBCRAT_RATIO                                  0
+#define FM_SUBMBCRAT_RATIO                                  0x1F
+
+// *** SUBMBCATKL ***
+#define FB_SUBMBCATKL_TCATKL                                0
+#define FM_SUBMBCATKL_TCATKL                                0xFF
+
+// *** SUBMBCATKH ***
+#define FB_SUBMBCATKH_TCATKH                                0
+#define FM_SUBMBCATKH_TCATKH                                0xFF
+
+// *** SUBMBCRELL ***
+#define FB_SUBMBCRELL_TCRELL                                0
+#define FM_SUBMBCRELL_TCRELL                                0xFF
+
+// *** SUBMBCRELH ***
+#define FB_SUBMBCRELH_TCRELH                                0
+#define FM_SUBMBCRELH_TCRELH                                0xFF
+
+// *** PAGESEL ***
+#define FB_PAGESEL_PAGESEL                                  0
+#define FM_PAGESEL_PAGESEL                                  0xFF
+
+// *** RESET ***
+#define FB_RESET_RESET                                      0
+#define FM_RESET_RESET                                      0xFF
+#define FV_RESET_PWR_ON_DEFAULTS                            0x85
+
+// *** IRQEN ***
+#define FB_IRQEN_THRMINTEN                                  6
+#define FM_IRQEN_THRMINTEN                                  0x40
+#define FV_THRMINTEN_ENABLED                                0x40
+#define FV_THRMINTEN_DISABLED                               0x0
+
+#define FB_IRQEN_HBPINTEN                                   5
+#define FM_IRQEN_HBPINTEN                                   0x20
+#define FV_HBPINTEN_ENABLED                                 0x20
+#define FV_HBPINTEN_DISABLED                                0x0
+
+#define FB_IRQEN_HSDINTEN                                   4
+#define FM_IRQEN_HSDINTEN                                   0x10
+#define FV_HSDINTEN_ENABLED                                 0x10
+#define FV_HSDINTEN_DISABLED                                0x0
+
+#define FB_IRQEN_HPDINTEN                                   3
+#define FM_IRQEN_HPDINTEN                                   0x8
+#define FV_HPDINTEN_ENABLED                                 0x8
+#define FV_HPDINTEN_DISABLED                                0x0
+
+#define FB_IRQEN_GPIO3INTEN                                 1
+#define FM_IRQEN_GPIO3INTEN                                 0x2
+#define FV_GPIO3INTEN_ENABLED                               0x2
+#define FV_GPIO3INTEN_DISABLED                              0x0
+
+#define FB_IRQEN_GPIO2INTEN                                 0
+#define FM_IRQEN_GPIO2INTEN                                 0x1
+#define FV_GPIO2INTEN_ENABLED                               0x1
+#define FV_GPIO2INTEN_DISABLED                              0x0
+
+#define IRQEN_GPIOINTEN_ENABLED                             0x1
+#define IRQEN_GPIOINTEN_DISABLED                            0x0
+
+// *** IRQMASK ***
+#define FB_IRQMASK_THRMIM                                   6
+#define FM_IRQMASK_THRMIM                                   0x40
+#define FV_THRMIM_MASKED                                    0x0
+#define FV_THRMIM_NOT_MASKED                                0x40
+
+#define FB_IRQMASK_HBPIM                                    5
+#define FM_IRQMASK_HBPIM                                    0x20
+#define FV_HBPIM_MASKED                                     0x0
+#define FV_HBPIM_NOT_MASKED                                 0x20
+
+#define FB_IRQMASK_HSDIM                                    4
+#define FM_IRQMASK_HSDIM                                    0x10
+#define FV_HSDIM_MASKED                                     0x0
+#define FV_HSDIM_NOT_MASKED                                 0x10
+
+#define FB_IRQMASK_HPDIM                                    3
+#define FM_IRQMASK_HPDIM                                    0x8
+#define FV_HPDIM_MASKED                                     0x0
+#define FV_HPDIM_NOT_MASKED                                 0x8
+
+#define FB_IRQMASK_GPIO3M                                   1
+#define FM_IRQMASK_GPIO3M                                   0x2
+#define FV_GPIO3M_MASKED                                    0x0
+#define FV_GPIO3M_NOT_MASKED                                0x2
+
+#define FB_IRQMASK_GPIO2M                                   0
+#define FM_IRQMASK_GPIO2M                                   0x1
+#define FV_GPIO2M_MASKED                                    0x0
+#define FV_GPIO2M_NOT_MASKED                                0x1
+
+#define IRQMASK_GPIOM_MASKED                                0x0
+#define IRQMASK_GPIOM_NOT_MASKED                            0x1
+
+// *** IRQSTAT ***
+#define FB_IRQSTAT_THRMINT                                  6
+#define FM_IRQSTAT_THRMINT                                  0x40
+#define FV_THRMINT_INTERRUPTED                              0x40
+#define FV_THRMINT_NOT_INTERRUPTED                          0x0
+
+#define FB_IRQSTAT_HBPINT                                   5
+#define FM_IRQSTAT_HBPINT                                   0x20
+#define FV_HBPINT_INTERRUPTED                               0x20
+#define FV_HBPINT_NOT_INTERRUPTED                           0x0
+
+#define FB_IRQSTAT_HSDINT                                   4
+#define FM_IRQSTAT_HSDINT                                   0x10
+#define FV_HSDINT_INTERRUPTED                               0x10
+#define FV_HSDINT_NOT_INTERRUPTED                           0x0
+
+#define FB_IRQSTAT_HPDINT                                   3
+#define FM_IRQSTAT_HPDINT                                   0x8
+#define FV_HPDINT_INTERRUPTED                               0x8
+#define FV_HPDINT_NOT_INTERRUPTED                           0x0
+
+#define FB_IRQSTAT_GPIO3INT                                 1
+#define FM_IRQSTAT_GPIO3INT                                 0x2
+#define FV_GPIO3INT_INTERRUPTED                             0x2
+#define FV_GPIO3INT_NOT_INTERRUPTED                         0x0
+
+#define FB_IRQSTAT_GPIO2INT                                 0
+#define FM_IRQSTAT_GPIO2INT                                 0x1
+#define FV_GPIO2INT_INTERRUPTED                             0x1
+#define FV_GPIO2INT_NOT_INTERRUPTED                         0x0
+
+#define IRQSTAT_GPIOINT_INTERRUPTED                         0x1
+#define IRQSTAT_GPIOINT_NOT_INTERRUPTED                     0x0
+
+// *** DEVADD0 ***
+#define FB_DEVADD0_DEVADD0                                  1
+#define FM_DEVADD0_DEVADD0                                  0xFE
+
+#define FB_DEVADD0_I2C_ADDRLK                               0
+#define FM_DEVADD0_I2C_ADDRLK                               0x1
+#define FV_I2C_ADDRLK_LOCK                                  0x1
+
+// *** DEVID ***
+#define FB_DEVID_DEV_ID                                     0
+#define FM_DEVID_DEV_ID                                     0xFF
+
+// *** DEVREV ***
+#define FB_DEVREV_MAJ_REV                                   4
+#define FM_DEVREV_MAJ_REV                                   0xF0
+
+#define FB_DEVREV_MIN_REV                                   0
+#define FM_DEVREV_MIN_REV                                   0xF
+
+// *** PLLSTAT ***
+#define FB_PLLSTAT_PLL2LK                                   1
+#define FM_PLLSTAT_PLL2LK                                   0x2
+#define FV_PLL2LK_LOCKED                                    0x2
+#define FV_PLL2LK_UNLOCKED                                  0x0
+
+#define FB_PLLSTAT_PLL1LK                                   0
+#define FM_PLLSTAT_PLL1LK                                   0x1
+#define FV_PLL1LK_LOCKED                                    0x1
+#define FV_PLL1LK_UNLOCKED                                  0x0
+
+#define PLLSTAT_PLLLK_LOCKED                                0x1
+#define PLLSTAT_PLLLK_UNLOCKED                              0x0
+
+// *** PLLCTL ***
+#define FB_PLLCTL_PU_PLL2                                   7
+#define FM_PLLCTL_PU_PLL2                                   0x80
+#define FV_PU_PLL2_PWR_UP                                   0x80
+#define FV_PU_PLL2_PWR_DWN                                  0x0
+
+#define FB_PLLCTL_PU_PLL1                                   6
+#define FM_PLLCTL_PU_PLL1                                   0x40
+#define FV_PU_PLL1_PWR_UP                                   0x40
+#define FV_PU_PLL1_PWR_DWN                                  0x0
+
+#define FB_PLLCTL_PLL2CLKEN                                 5
+#define FM_PLLCTL_PLL2CLKEN                                 0x20
+#define FV_PLL2CLKEN_ENABLE                                 0x20
+#define FV_PLL2CLKEN_DISABLE                                0x0
+
+#define FB_PLLCTL_PLL1CLKEN                                 4
+#define FM_PLLCTL_PLL1CLKEN                                 0x10
+#define FV_PLL1CLKEN_ENABLE                                 0x10
+#define FV_PLL1CLKEN_DISABLE                                0x0
+
+#define FB_PLLCTL_BCLKSEL                                   2
+#define FM_PLLCTL_BCLKSEL                                   0xC
+#define FV_BCLKSEL_BCLK1                                    0x0
+#define FV_BCLKSEL_BCLK2                                    0x4
+#define FV_BCLKSEL_BCLK3                                    0x8
+
+#define FB_PLLCTL_PLLISEL                                   0
+#define FM_PLLCTL_PLLISEL                                   0x3
+#define FV_PLLISEL_XTAL                                     0x0
+#define FV_PLLISEL_MCLK1                                    0x1
+#define FV_PLLISEL_MCLK2                                    0x2
+#define FV_PLLISEL_BCLK                                     0x3
+
+#define PLLCTL_PU_PLL_PWR_UP                                0x1
+#define PLLCTL_PU_PLL_PWR_DWN                               0x0
+#define PLLCTL_PLLCLKEN_ENABLE                              0x1
+#define PLLCTL_PLLCLKEN_DISABLE                             0x0
+
+// *** ISRC ***
+#define FB_ISRC_IBR                                         2
+#define FM_ISRC_IBR                                         0x4
+#define FV_IBR_44PT1                                        0x0
+#define FV_IBR_48                                           0x4
+
+#define FB_ISRC_IBM                                         0
+#define FM_ISRC_IBM                                         0x3
+#define FV_IBM_0PT25                                        0x0
+#define FV_IBM_0PT5                                         0x1
+#define FV_IBM_1                                            0x2
+#define FV_IBM_2                                            0x3
+
+// *** SCLKCTL ***
+#define FB_SCLKCTL_ASDM                                     6
+#define FM_SCLKCTL_ASDM                                     0xC0
+#define FV_ASDM_HALF                                        0x40
+#define FV_ASDM_FULL                                        0x80
+#define FV_ASDM_AUTO                                        0xC0
+
+#define FB_SCLKCTL_DSDM                                     4
+#define FM_SCLKCTL_DSDM                                     0x30
+#define FV_DSDM_HALF                                        0x10
+#define FV_DSDM_FULL                                        0x20
+#define FV_DSDM_AUTO                                        0x30
+
+// *** TIMEBASE ***
+#define FB_TIMEBASE_TIMEBASE                                0
+#define FM_TIMEBASE_TIMEBASE                                0xFF
+
+// *** I2SCMC ***
+#define FB_I2SCMC_BCMP3                                     4
+#define FM_I2SCMC_BCMP3                                     0x30
+#define FV_BCMP3_AUTO                                       0x0
+#define FV_BCMP3_32X                                        0x10
+#define FV_BCMP3_40X                                        0x20
+#define FV_BCMP3_64X                                        0x30
+
+#define FB_I2SCMC_BCMP2                                     2
+#define FM_I2SCMC_BCMP2                                     0xC
+#define FV_BCMP2_AUTO                                       0x0
+#define FV_BCMP2_32X                                        0x4
+#define FV_BCMP2_40X                                        0x8
+#define FV_BCMP2_64X                                        0xC
+
+#define FB_I2SCMC_BCMP1                                     0
+#define FM_I2SCMC_BCMP1                                     0x3
+#define FV_BCMP1_AUTO                                       0x0
+#define FV_BCMP1_32X                                        0x1
+#define FV_BCMP1_40X                                        0x2
+#define FV_BCMP1_64X                                        0x3
+
+#define I2SCMC_BCMP_AUTO                                    0x0
+#define I2SCMC_BCMP_32X                                     0x1
+#define I2SCMC_BCMP_40X                                     0x2
+#define I2SCMC_BCMP_64X                                     0x3
+
+// *** MCLK2PINC ***
+#define FB_MCLK2PINC_SLEWOUT                                4
+#define FM_MCLK2PINC_SLEWOUT                                0xF0
+
+#define FB_MCLK2PINC_MCLK2IO                                2
+#define FM_MCLK2PINC_MCLK2IO                                0x4
+#define FV_MCLK2IO_INPUT                                    0x0
+#define FV_MCLK2IO_OUTPUT                                   0x4
+
+#define FB_MCLK2PINC_MCLK2OS                                0
+#define FM_MCLK2PINC_MCLK2OS                                0x3
+#define FV_MCLK2OS_24PT576                                  0x0
+#define FV_MCLK2OS_22PT5792                                 0x1
+#define FV_MCLK2OS_PLL2                                     0x2
+
+// *** I2SPINC0 ***
+#define FB_I2SPINC0_SDO3TRI                                 7
+#define FM_I2SPINC0_SDO3TRI                                 0x80
+
+#define FB_I2SPINC0_SDO2TRI                                 6
+#define FM_I2SPINC0_SDO2TRI                                 0x40
+
+#define FB_I2SPINC0_SDO1TRI                                 5
+#define FM_I2SPINC0_SDO1TRI                                 0x20
+
+#define FB_I2SPINC0_PCM3TRI                                 2
+#define FM_I2SPINC0_PCM3TRI                                 0x4
+
+#define FB_I2SPINC0_PCM2TRI                                 1
+#define FM_I2SPINC0_PCM2TRI                                 0x2
+
+#define FB_I2SPINC0_PCM1TRI                                 0
+#define FM_I2SPINC0_PCM1TRI                                 0x1
+
+// *** I2SPINC1 ***
+#define FB_I2SPINC1_SDO3PDD                                 2
+#define FM_I2SPINC1_SDO3PDD                                 0x4
+
+#define FB_I2SPINC1_SDO2PDD                                 1
+#define FM_I2SPINC1_SDO2PDD                                 0x2
+
+#define FB_I2SPINC1_SDO1PDD                                 0
+#define FM_I2SPINC1_SDO1PDD                                 0x1
+
+// *** I2SPINC2 ***
+#define FB_I2SPINC2_LR3PDD                                  5
+#define FM_I2SPINC2_LR3PDD                                  0x20
+
+#define FB_I2SPINC2_BC3PDD                                  4
+#define FM_I2SPINC2_BC3PDD                                  0x10
+
+#define FB_I2SPINC2_LR2PDD                                  3
+#define FM_I2SPINC2_LR2PDD                                  0x8
+
+#define FB_I2SPINC2_BC2PDD                                  2
+#define FM_I2SPINC2_BC2PDD                                  0x4
+
+#define FB_I2SPINC2_LR1PDD                                  1
+#define FM_I2SPINC2_LR1PDD                                  0x2
+
+#define FB_I2SPINC2_BC1PDD                                  0
+#define FM_I2SPINC2_BC1PDD                                  0x1
+
+// *** GPIOCTL0 ***
+#define FB_GPIOCTL0_GPIO3INTP                               7
+#define FM_GPIOCTL0_GPIO3INTP                               0x80
+
+#define FB_GPIOCTL0_GPIO2INTP                               6
+#define FM_GPIOCTL0_GPIO2INTP                               0x40
+
+#define FB_GPIOCTL0_GPIO3CFG                                5
+#define FM_GPIOCTL0_GPIO3CFG                                0x20
+
+#define FB_GPIOCTL0_GPIO2CFG                                4
+#define FM_GPIOCTL0_GPIO2CFG                                0x10
+
+#define FB_GPIOCTL0_GPIO3IO                                 3
+#define FM_GPIOCTL0_GPIO3IO                                 0x8
+
+#define FB_GPIOCTL0_GPIO2IO                                 2
+#define FM_GPIOCTL0_GPIO2IO                                 0x4
+
+#define FB_GPIOCTL0_GPIO1IO                                 1
+#define FM_GPIOCTL0_GPIO1IO                                 0x2
+
+#define FB_GPIOCTL0_GPIO0IO                                 0
+#define FM_GPIOCTL0_GPIO0IO                                 0x1
+
+// *** GPIOCTL1 ***
+#define FB_GPIOCTL1_GPIO3                                   7
+#define FM_GPIOCTL1_GPIO3                                   0x80
+
+#define FB_GPIOCTL1_GPIO2                                   6
+#define FM_GPIOCTL1_GPIO2                                   0x40
+
+#define FB_GPIOCTL1_GPIO1                                   5
+#define FM_GPIOCTL1_GPIO1                                   0x20
+
+#define FB_GPIOCTL1_GPIO0                                   4
+#define FM_GPIOCTL1_GPIO0                                   0x10
+
+#define FB_GPIOCTL1_GPIO3RD                                 3
+#define FM_GPIOCTL1_GPIO3RD                                 0x8
+
+#define FB_GPIOCTL1_GPIO2RD                                 2
+#define FM_GPIOCTL1_GPIO2RD                                 0x4
+
+#define FB_GPIOCTL1_GPIO1RD                                 1
+#define FM_GPIOCTL1_GPIO1RD                                 0x2
+
+#define FB_GPIOCTL1_GPIO0RD                                 0
+#define FM_GPIOCTL1_GPIO0RD                                 0x1
+
+// *** ASRC ***
+#define FB_ASRC_ASRCOBW                                     7
+#define FM_ASRC_ASRCOBW                                     0x80
+
+#define FB_ASRC_ASRCIBW                                     6
+#define FM_ASRC_ASRCIBW                                     0x40
+
+#define FB_ASRC_ASRCOB                                      5
+#define FM_ASRC_ASRCOB                                      0x20
+#define FV_ASRCOB_ACTIVE                                    0x0
+#define FV_ASRCOB_BYPASSED                                  0x20
+
+#define FB_ASRC_ASRCIB                                      4
+#define FM_ASRC_ASRCIB                                      0x10
+#define FV_ASRCIB_ACTIVE                                    0x0
+#define FV_ASRCIB_BYPASSED                                  0x10
+
+#define FB_ASRC_ASRCOL                                      3
+#define FM_ASRC_ASRCOL                                      0x8
+
+#define FB_ASRC_ASRCIL                                      2
+#define FM_ASRC_ASRCIL                                      0x4
+
+// *** TDMCTL0 ***
+#define FB_TDMCTL0_TDMMD                                    2
+#define FM_TDMCTL0_TDMMD                                    0x4
+#define FV_TDMMD_200                                        0x0
+#define FV_TDMMD_256                                        0x4
+
+#define FB_TDMCTL0_SLSYNC                                   1
+#define FM_TDMCTL0_SLSYNC                                   0x2
+#define FV_SLSYNC_SHORT                                     0x0
+#define FV_SLSYNC_LONG                                      0x2
+
+#define FB_TDMCTL0_BDELAY                                   0
+#define FM_TDMCTL0_BDELAY                                   0x1
+#define FV_BDELAY_NO_DELAY                                  0x0
+#define FV_BDELAY_1BCLK_DELAY                               0x1
+
+// *** TDMCTL1 ***
+#define FB_TDMCTL1_TDMSO                                    5
+#define FM_TDMCTL1_TDMSO                                    0x60
+#define FV_TDMSO_2                                          0x0
+#define FV_TDMSO_4                                          0x20
+#define FV_TDMSO_6                                          0x40
+
+#define FB_TDMCTL1_TDMDSS                                   3
+#define FM_TDMCTL1_TDMDSS                                   0x18
+#define FV_TDMDSS_16                                        0x0
+#define FV_TDMDSS_24                                        0x10
+#define FV_TDMDSS_32                                        0x18
+
+#define FB_TDMCTL1_TDMSI                                    0
+#define FM_TDMCTL1_TDMSI                                    0x3
+#define FV_TDMSI_2                                          0x0
+#define FV_TDMSI_4                                          0x1
+#define FV_TDMSI_6                                          0x2
+
+// *** PWRM0 ***
+#define FB_PWRM0_INPROC3PU                                  6
+#define FM_PWRM0_INPROC3PU                                  0x40
+
+#define FB_PWRM0_INPROC2PU                                  5
+#define FM_PWRM0_INPROC2PU                                  0x20
+
+#define FB_PWRM0_INPROC1PU                                  4
+#define FM_PWRM0_INPROC1PU                                  0x10
+
+#define FB_PWRM0_INPROC0PU                                  3
+#define FM_PWRM0_INPROC0PU                                  0x8
+
+#define FB_PWRM0_MICB2PU                                    2
+#define FM_PWRM0_MICB2PU                                    0x4
+
+#define FB_PWRM0_MICB1PU                                    1
+#define FM_PWRM0_MICB1PU                                    0x2
+
+#define FB_PWRM0_MCLKPEN                                    0
+#define FM_PWRM0_MCLKPEN                                    0x1
+
+// *** PWRM1 ***
+#define FB_PWRM1_SUBPU                                      7
+#define FM_PWRM1_SUBPU                                      0x80
+
+#define FB_PWRM1_HPLPU                                      6
+#define FM_PWRM1_HPLPU                                      0x40
+
+#define FB_PWRM1_HPRPU                                      5
+#define FM_PWRM1_HPRPU                                      0x20
+
+#define FB_PWRM1_SPKLPU                                     4
+#define FM_PWRM1_SPKLPU                                     0x10
+
+#define FB_PWRM1_SPKRPU                                     3
+#define FM_PWRM1_SPKRPU                                     0x8
+
+#define FB_PWRM1_D2S2PU                                     2
+#define FM_PWRM1_D2S2PU                                     0x4
+
+#define FB_PWRM1_D2S1PU                                     1
+#define FM_PWRM1_D2S1PU                                     0x2
+
+#define FB_PWRM1_VREFPU                                     0
+#define FM_PWRM1_VREFPU                                     0x1
+
+// *** PWRM2 ***
+#define FB_PWRM2_I2S3OPU                                    5
+#define FM_PWRM2_I2S3OPU                                    0x20
+#define FV_I2S3OPU_PWR_DOWN                                 0x0
+#define FV_I2S3OPU_PWR_UP                                   0x20
+
+#define FB_PWRM2_I2S2OPU                                    4
+#define FM_PWRM2_I2S2OPU                                    0x10
+#define FV_I2S2OPU_PWR_DOWN                                 0x0
+#define FV_I2S2OPU_PWR_UP                                   0x10
+
+#define FB_PWRM2_I2S1OPU                                    3
+#define FM_PWRM2_I2S1OPU                                    0x8
+#define FV_I2S1OPU_PWR_DOWN                                 0x0
+#define FV_I2S1OPU_PWR_UP                                   0x8
+
+#define FB_PWRM2_I2S3IPU                                    2
+#define FM_PWRM2_I2S3IPU                                    0x4
+#define FV_I2S3IPU_PWR_DOWN                                 0x0
+#define FV_I2S3IPU_PWR_UP                                   0x4
+
+#define FB_PWRM2_I2S2IPU                                    1
+#define FM_PWRM2_I2S2IPU                                    0x2
+#define FV_I2S2IPU_PWR_DOWN                                 0x0
+#define FV_I2S2IPU_PWR_UP                                   0x2
+
+#define FB_PWRM2_I2S1IPU                                    0
+#define FM_PWRM2_I2S1IPU                                    0x1
+#define FV_I2S1IPU_PWR_DOWN                                 0x0
+#define FV_I2S1IPU_PWR_UP                                   0x1
+
+#define PWRM2_I2SOPU_PWR_DOWN                               0x0
+#define PWRM2_I2SOPU_PWR_UP                                 0x1
+#define PWRM2_I2SIPU_PWR_DOWN                               0x0
+#define PWRM2_I2SIPU_PWR_UP                                 0x1
+
+// *** PWRM3 ***
+#define FB_PWRM3_BGSBUP                                     6
+#define FM_PWRM3_BGSBUP                                     0x40
+#define FV_BGSBUP_ON                                        0x0
+#define FV_BGSBUP_OFF                                       0x40
+
+#define FB_PWRM3_VGBAPU                                     5
+#define FM_PWRM3_VGBAPU                                     0x20
+#define FV_VGBAPU_ON                                        0x0
+#define FV_VGBAPU_OFF                                       0x20
+
+#define FB_PWRM3_LLINEPU                                    4
+#define FM_PWRM3_LLINEPU                                    0x10
+
+#define FB_PWRM3_RLINEPU                                    3
+#define FM_PWRM3_RLINEPU                                    0x8
+
+// *** PWRM4 ***
+#define FB_PWRM4_OPSUBPU                                    4
+#define FM_PWRM4_OPSUBPU                                    0x10
+
+#define FB_PWRM4_OPDACLPU                                   3
+#define FM_PWRM4_OPDACLPU                                   0x8
+
+#define FB_PWRM4_OPDACRPU                                   2
+#define FM_PWRM4_OPDACRPU                                   0x4
+
+#define FB_PWRM4_OPSPKLPU                                   1
+#define FM_PWRM4_OPSPKLPU                                   0x2
+
+#define FB_PWRM4_OPSPKRPU                                   0
+#define FM_PWRM4_OPSPKRPU                                   0x1
+
+// *** I2SIDCTL ***
+#define FB_I2SIDCTL_I2SI3DCTL                               4
+#define FM_I2SIDCTL_I2SI3DCTL                               0x30
+
+#define FB_I2SIDCTL_I2SI2DCTL                               2
+#define FM_I2SIDCTL_I2SI2DCTL                               0xC
+
+#define FB_I2SIDCTL_I2SI1DCTL                               0
+#define FM_I2SIDCTL_I2SI1DCTL                               0x3
+
+// *** I2SODCTL ***
+#define FB_I2SODCTL_I2SO3DCTL                               4
+#define FM_I2SODCTL_I2SO3DCTL                               0x30
+
+#define FB_I2SODCTL_I2SO2DCTL                               2
+#define FM_I2SODCTL_I2SO2DCTL                               0xC
+
+#define FB_I2SODCTL_I2SO1DCTL                               0
+#define FM_I2SODCTL_I2SO1DCTL                               0x3
+
+// *** AUDIOMUX1 ***
+#define FB_AUDIOMUX1_ASRCIMUX                               6
+#define FM_AUDIOMUX1_ASRCIMUX                               0xC0
+#define FV_ASRCIMUX_NONE                                    0x0
+#define FV_ASRCIMUX_I2S1                                    0x40
+#define FV_ASRCIMUX_I2S2                                    0x80
+#define FV_ASRCIMUX_I2S3                                    0xC0
+
+#define FB_AUDIOMUX1_I2S2MUX                                3
+#define FM_AUDIOMUX1_I2S2MUX                                0x38
+#define FV_I2S2MUX_I2S1                                     0x0
+#define FV_I2S2MUX_I2S2                                     0x8
+#define FV_I2S2MUX_I2S3                                     0x10
+#define FV_I2S2MUX_ADC_DMIC                                 0x18
+#define FV_I2S2MUX_DMIC2                                    0x20
+#define FV_I2S2MUX_CLASSD_DSP                               0x28
+#define FV_I2S2MUX_DAC_DSP                                  0x30
+#define FV_I2S2MUX_SUB_DSP                                  0x38
+
+#define FB_AUDIOMUX1_I2S1MUX                                0
+#define FM_AUDIOMUX1_I2S1MUX                                0x7
+#define FV_I2S1MUX_I2S1                                     0x0
+#define FV_I2S1MUX_I2S2                                     0x1
+#define FV_I2S1MUX_I2S3                                     0x2
+#define FV_I2S1MUX_ADC_DMIC                                 0x3
+#define FV_I2S1MUX_DMIC2                                    0x4
+#define FV_I2S1MUX_CLASSD_DSP                               0x5
+#define FV_I2S1MUX_DAC_DSP                                  0x6
+#define FV_I2S1MUX_SUB_DSP                                  0x7
+
+#define AUDIOMUX1_I2SMUX_I2S1                               0x0
+#define AUDIOMUX1_I2SMUX_I2S2                               0x1
+#define AUDIOMUX1_I2SMUX_I2S3                               0x2
+#define AUDIOMUX1_I2SMUX_ADC_DMIC                           0x3
+#define AUDIOMUX1_I2SMUX_DMIC2                              0x4
+#define AUDIOMUX1_I2SMUX_CLASSD_DSP                         0x5
+#define AUDIOMUX1_I2SMUX_DAC_DSP                            0x6
+#define AUDIOMUX1_I2SMUX_SUB_DSP                            0x7
+
+// *** AUDIOMUX2 ***
+#define FB_AUDIOMUX2_ASRCOMUX                               6
+#define FM_AUDIOMUX2_ASRCOMUX                               0xC0
+#define FV_ASRCOMUX_NONE                                    0x0
+#define FV_ASRCOMUX_I2S1                                    0x40
+#define FV_ASRCOMUX_I2S2                                    0x80
+#define FV_ASRCOMUX_I2S3                                    0xC0
+
+#define FB_AUDIOMUX2_DACMUX                                 3
+#define FM_AUDIOMUX2_DACMUX                                 0x38
+#define FV_DACMUX_I2S1                                      0x0
+#define FV_DACMUX_I2S2                                      0x8
+#define FV_DACMUX_I2S3                                      0x10
+#define FV_DACMUX_ADC_DMIC                                  0x18
+#define FV_DACMUX_DMIC2                                     0x20
+#define FV_DACMUX_CLASSD_DSP                                0x28
+#define FV_DACMUX_DAC_DSP                                   0x30
+#define FV_DACMUX_SUB_DSP                                   0x38
+
+#define FB_AUDIOMUX2_I2S3MUX                                0
+#define FM_AUDIOMUX2_I2S3MUX                                0x7
+#define FV_I2S3MUX_I2S1                                     0x0
+#define FV_I2S3MUX_I2S2                                     0x1
+#define FV_I2S3MUX_I2S3                                     0x2
+#define FV_I2S3MUX_ADC_DMIC                                 0x3
+#define FV_I2S3MUX_DMIC2                                    0x4
+#define FV_I2S3MUX_CLASSD_DSP                               0x5
+#define FV_I2S3MUX_DAC_DSP                                  0x6
+#define FV_I2S3MUX_SUB_DSP                                  0x7
+
+// *** AUDIOMUX3 ***
+#define FB_AUDIOMUX3_SUBMUX                                 3
+#define FM_AUDIOMUX3_SUBMUX                                 0xF8
+#define FV_SUBMUX_I2S1_L                                    0x0
+#define FV_SUBMUX_I2S1_R                                    0x8
+#define FV_SUBMUX_I2S1_LR                                   0x10
+#define FV_SUBMUX_I2S2_L                                    0x18
+#define FV_SUBMUX_I2S2_R                                    0x20
+#define FV_SUBMUX_I2S2_LR                                   0x28
+#define FV_SUBMUX_I2S3_L                                    0x30
+#define FV_SUBMUX_I2S3_R                                    0x38
+#define FV_SUBMUX_I2S3_LR                                   0x40
+#define FV_SUBMUX_ADC_DMIC_L                                0x48
+#define FV_SUBMUX_ADC_DMIC_R                                0x50
+#define FV_SUBMUX_ADC_DMIC_LR                               0x58
+#define FV_SUBMUX_DMIC_L                                    0x60
+#define FV_SUBMUX_DMIC_R                                    0x68
+#define FV_SUBMUX_DMIC_LR                                   0x70
+#define FV_SUBMUX_CLASSD_DSP_L                              0x78
+#define FV_SUBMUX_CLASSD_DSP_R                              0x80
+#define FV_SUBMUX_CLASSD_DSP_LR                             0x88
+
+#define FB_AUDIOMUX3_CLSSDMUX                               0
+#define FM_AUDIOMUX3_CLSSDMUX                               0x7
+#define FV_CLSSDMUX_I2S1                                    0x0
+#define FV_CLSSDMUX_I2S2                                    0x1
+#define FV_CLSSDMUX_I2S3                                    0x2
+#define FV_CLSSDMUX_ADC_DMIC                                0x3
+#define FV_CLSSDMUX_DMIC2                                   0x4
+#define FV_CLSSDMUX_CLASSD_DSP                              0x5
+#define FV_CLSSDMUX_DAC_DSP                                 0x6
+#define FV_CLSSDMUX_SUB_DSP                                 0x7
+
+// *** HSDCTL1 ***
+#define FB_HSDCTL1_HPJKTYPE                                 7
+#define FM_HSDCTL1_HPJKTYPE                                 0x80
+
+#define FB_HSDCTL1_CON_DET_PWD                              6
+#define FM_HSDCTL1_CON_DET_PWD                              0x40
+
+#define FB_HSDCTL1_DETCYC                                   4
+#define FM_HSDCTL1_DETCYC                                   0x30
+
+#define FB_HSDCTL1_HPDLYBYP                                 3
+#define FM_HSDCTL1_HPDLYBYP                                 0x8
+
+#define FB_HSDCTL1_HSDETPOL                                 2
+#define FM_HSDCTL1_HSDETPOL                                 0x4
+
+#define FB_HSDCTL1_HPID_EN                                  1
+#define FM_HSDCTL1_HPID_EN                                  0x2
+
+#define FB_HSDCTL1_GBLHS_EN                                 0
+#define FM_HSDCTL1_GBLHS_EN                                 0x1
+
+// *** HSDCTL2 ***
+#define FB_HSDCTL2_FMICBIAS1                                6
+#define FM_HSDCTL2_FMICBIAS1                                0xC0
+
+#define FB_HSDCTL2_MB1MODE                                  5
+#define FM_HSDCTL2_MB1MODE                                  0x20
+#define FV_MB1MODE_AUTO                                     0x0
+#define FV_MB1MODE_MANUAL                                   0x20
+
+#define FB_HSDCTL2_FORCETRG                                 4
+#define FM_HSDCTL2_FORCETRG                                 0x10
+
+#define FB_HSDCTL2_SWMODE                                   3
+#define FM_HSDCTL2_SWMODE                                   0x8
+
+#define FB_HSDCTL2_GHSHIZ                                   2
+#define FM_HSDCTL2_GHSHIZ                                   0x4
+
+#define FB_HSDCTL2_FPLUGTYPE                                0
+#define FM_HSDCTL2_FPLUGTYPE                                0x3
+
+// *** HSDSTAT ***
+#define FB_HSDSTAT_MBIAS1DRV                                5
+#define FM_HSDSTAT_MBIAS1DRV                                0x60
+
+#define FB_HSDSTAT_HSDETSTAT                                3
+#define FM_HSDSTAT_HSDETSTAT                                0x8
+
+#define FB_HSDSTAT_PLUGTYPE                                 1
+#define FM_HSDSTAT_PLUGTYPE                                 0x6
+
+#define FB_HSDSTAT_HSDETDONE                                0
+#define FM_HSDSTAT_HSDETDONE                                0x1
+
+// *** HSDDELAY ***
+#define FB_HSDDELAY_T_STABLE                                0
+#define FM_HSDDELAY_T_STABLE                                0x7
+
+// *** BUTCTL ***
+#define FB_BUTCTL_BPUSHSTAT                                 7
+#define FM_BUTCTL_BPUSHSTAT                                 0x80
+
+#define FB_BUTCTL_BPUSHDET                                  6
+#define FM_BUTCTL_BPUSHDET                                  0x40
+
+#define FB_BUTCTL_BPUSHEN                                   5
+#define FM_BUTCTL_BPUSHEN                                   0x20
+
+#define FB_BUTCTL_BSTABLE_L                                 3
+#define FM_BUTCTL_BSTABLE_L                                 0x18
+
+#define FB_BUTCTL_BSTABLE_S                                 0
+#define FM_BUTCTL_BSTABLE_S                                 0x7
+
+// *** CH0AIC ***
+#define FB_CH0AIC_INSELL                                    6
+#define FM_CH0AIC_INSELL                                    0xC0
+
+#define FB_CH0AIC_MICBST0                                   4
+#define FM_CH0AIC_MICBST0                                   0x30
+
+#define FB_CH0AIC_LADCIN                                    2
+#define FM_CH0AIC_LADCIN                                    0xC
+
+#define FB_CH0AIC_IN_BYPS_L_SEL                             1
+#define FM_CH0AIC_IN_BYPS_L_SEL                             0x2
+
+#define FB_CH0AIC_IPCH0S                                    0
+#define FM_CH0AIC_IPCH0S                                    0x1
+
+// *** CH1AIC ***
+#define FB_CH1AIC_INSELR                                    6
+#define FM_CH1AIC_INSELR                                    0xC0
+
+#define FB_CH1AIC_MICBST1                                   4
+#define FM_CH1AIC_MICBST1                                   0x30
+
+#define FB_CH1AIC_RADCIN                                    2
+#define FM_CH1AIC_RADCIN                                    0xC
+
+#define FB_CH1AIC_IN_BYPS_R_SEL                             1
+#define FM_CH1AIC_IN_BYPS_R_SEL                             0x2
+
+#define FB_CH1AIC_IPCH1S                                    0
+#define FM_CH1AIC_IPCH1S                                    0x1
+
+// *** ICTL0 ***
+#define FB_ICTL0_IN1POL                                     7
+#define FM_ICTL0_IN1POL                                     0x80
+
+#define FB_ICTL0_IN0POL                                     6
+#define FM_ICTL0_IN0POL                                     0x40
+
+#define FB_ICTL0_INPCH10SEL                                 4
+#define FM_ICTL0_INPCH10SEL                                 0x30
+
+#define FB_ICTL0_IN1MUTE                                    3
+#define FM_ICTL0_IN1MUTE                                    0x8
+
+#define FB_ICTL0_IN0MUTE                                    2
+#define FM_ICTL0_IN0MUTE                                    0x4
+
+#define FB_ICTL0_IN1HP                                      1
+#define FM_ICTL0_IN1HP                                      0x2
+
+#define FB_ICTL0_IN0HP                                      0
+#define FM_ICTL0_IN0HP                                      0x1
+
+// *** ICTL1 ***
+#define FB_ICTL1_IN3POL                                     7
+#define FM_ICTL1_IN3POL                                     0x80
+
+#define FB_ICTL1_IN2POL                                     6
+#define FM_ICTL1_IN2POL                                     0x40
+
+#define FB_ICTL1_INPCH32SEL                                 4
+#define FM_ICTL1_INPCH32SEL                                 0x30
+
+#define FB_ICTL1_IN3MUTE                                    3
+#define FM_ICTL1_IN3MUTE                                    0x8
+
+#define FB_ICTL1_IN2MUTE                                    2
+#define FM_ICTL1_IN2MUTE                                    0x4
+
+#define FB_ICTL1_IN3HP                                      1
+#define FM_ICTL1_IN3HP                                      0x2
+
+#define FB_ICTL1_IN2HP                                      0
+#define FM_ICTL1_IN2HP                                      0x1
+
+// *** MICBIAS ***
+#define FB_MICBIAS_MICBOV2                                  4
+#define FM_MICBIAS_MICBOV2                                  0x30
+
+#define FB_MICBIAS_MICBOV1                                  6
+#define FM_MICBIAS_MICBOV1                                  0xC0
+
+#define FB_MICBIAS_SPARE1                                   2
+#define FM_MICBIAS_SPARE1                                   0xC
+
+#define FB_MICBIAS_SPARE2                                   0
+#define FM_MICBIAS_SPARE2                                   0x3
+
+// *** PGAZ ***
+#define FB_PGAZ_INHPOR                                      1
+#define FM_PGAZ_INHPOR                                      0x2
+
+#define FB_PGAZ_TOEN                                        0
+#define FM_PGAZ_TOEN                                        0x1
+
+// *** ASRCILVOL ***
+#define FB_ASRCILVOL_ASRCILVOL                              0
+#define FM_ASRCILVOL_ASRCILVOL                              0xFF
+
+// *** ASRCIRVOL ***
+#define FB_ASRCIRVOL_ASRCIRVOL                              0
+#define FM_ASRCIRVOL_ASRCIRVOL                              0xFF
+
+// *** ASRCOLVOL ***
+#define FB_ASRCOLVOL_ASRCOLVOL                              0
+#define FM_ASRCOLVOL_ASRCOLVOL                              0xFF
+
+// *** ASRCORVOL ***
+#define FB_ASRCORVOL_ASRCOLVOL                              0
+#define FM_ASRCORVOL_ASRCOLVOL                              0xFF
+
+// *** IVOLCTLU ***
+#define FB_IVOLCTLU_IFADE                                   3
+#define FM_IVOLCTLU_IFADE                                   0x8
+
+#define FB_IVOLCTLU_INPVOLU                                 2
+#define FM_IVOLCTLU_INPVOLU                                 0x4
+
+#define FB_IVOLCTLU_PGAVOLU                                 1
+#define FM_IVOLCTLU_PGAVOLU                                 0x2
+
+#define FB_IVOLCTLU_ASRCVOLU                                0
+#define FM_IVOLCTLU_ASRCVOLU                                0x1
+
+// *** ALCCTL0 ***
+#define FB_ALCCTL0_ALCMODE                                  7
+#define FM_ALCCTL0_ALCMODE                                  0x80
+
+#define FB_ALCCTL0_ALCREF                                   4
+#define FM_ALCCTL0_ALCREF                                   0x70
+
+#define FB_ALCCTL0_ALCEN3                                   3
+#define FM_ALCCTL0_ALCEN3                                   0x8
+
+#define FB_ALCCTL0_ALCEN2                                   2
+#define FM_ALCCTL0_ALCEN2                                   0x4
+
+#define FB_ALCCTL0_ALCEN1                                   1
+#define FM_ALCCTL0_ALCEN1                                   0x2
+
+#define FB_ALCCTL0_ALCEN0                                   0
+#define FM_ALCCTL0_ALCEN0                                   0x1
+
+// *** ALCCTL1 ***
+#define FB_ALCCTL1_MAXGAIN                                  4
+#define FM_ALCCTL1_MAXGAIN                                  0x70
+
+#define FB_ALCCTL1_ALCL                                     0
+#define FM_ALCCTL1_ALCL                                     0xF
+
+// *** ALCCTL2 ***
+#define FB_ALCCTL2_ALCZC                                    7
+#define FM_ALCCTL2_ALCZC                                    0x80
+
+#define FB_ALCCTL2_MINGAIN                                  4
+#define FM_ALCCTL2_MINGAIN                                  0x70
+
+#define FB_ALCCTL2_HLD                                      0
+#define FM_ALCCTL2_HLD                                      0xF
+
+// *** ALCCTL3 ***
+#define FB_ALCCTL3_DCY                                      4
+#define FM_ALCCTL3_DCY                                      0xF0
+
+#define FB_ALCCTL3_ATK                                      0
+#define FM_ALCCTL3_ATK                                      0xF
+
+// *** NGATE ***
+#define FB_NGATE_NGTH                                       3
+#define FM_NGATE_NGTH                                       0xF8
+
+#define FB_NGATE_NGG                                        1
+#define FM_NGATE_NGG                                        0x6
+
+#define FB_NGATE_NGAT                                       0
+#define FM_NGATE_NGAT                                       0x1
+
+// *** DMICCTL ***
+#define FB_DMICCTL_DMIC2EN                                  7
+#define FM_DMICCTL_DMIC2EN                                  0x80
+
+#define FB_DMICCTL_DMIC1EN                                  6
+#define FM_DMICCTL_DMIC1EN                                  0x40
+
+#define FB_DMICCTL_DMONO                                    4
+#define FM_DMICCTL_DMONO                                    0x10
+
+#define FB_DMICCTL_DMDCLK                                   2
+#define FM_DMICCTL_DMDCLK                                   0xC
+
+#define FB_DMICCTL_DMRATE                                   0
+#define FM_DMICCTL_DMRATE                                   0x3
+
+// *** DACCTL ***
+#define FB_DACCTL_DACPOLR                                   7
+#define FM_DACCTL_DACPOLR                                   0x80
+#define FV_DACPOLR_NORMAL                                   0x0
+#define FV_DACPOLR_INVERTED                                 0x80
+
+#define FB_DACCTL_DACPOLL                                   6
+#define FM_DACCTL_DACPOLL                                   0x40
+#define FV_DACPOLL_NORMAL                                   0x0
+#define FV_DACPOLL_INVERTED                                 0x40
+
+#define FB_DACCTL_DACDITH                                   4
+#define FM_DACCTL_DACDITH                                   0x30
+#define FV_DACDITH_DYNAMIC_HALF                             0x0
+#define FV_DACDITH_DYNAMIC_FULL                             0x10
+#define FV_DACDITH_DISABLED                                 0x20
+#define FV_DACDITH_STATIC                                   0x30
+
+#define FB_DACCTL_DACMUTE                                   3
+#define FM_DACCTL_DACMUTE                                   0x8
+#define FV_DACMUTE_ENABLE                                   0x8
+#define FV_DACMUTE_DISABLE                                  0x0
+
+#define FB_DACCTL_DACDEM                                    2
+#define FM_DACCTL_DACDEM                                    0x4
+#define FV_DACDEM_ENABLE                                    0x4
+#define FV_DACDEM_DISABLE                                   0x0
+
+#define FB_DACCTL_ABYPASS                                   0
+#define FM_DACCTL_ABYPASS                                   0x1
+
+// *** SPKCTL ***
+#define FB_SPKCTL_SPKPOLR                                   7
+#define FM_SPKCTL_SPKPOLR                                   0x80
+#define FV_SPKPOLR_NORMAL                                   0x0
+#define FV_SPKPOLR_INVERTED                                 0x80
+
+#define FB_SPKCTL_SPKPOLL                                   6
+#define FM_SPKCTL_SPKPOLL                                   0x40
+#define FV_SPKPOLL_NORMAL                                   0x0
+#define FV_SPKPOLL_INVERTED                                 0x40
+
+#define FB_SPKCTL_SPKMUTE                                   3
+#define FM_SPKCTL_SPKMUTE                                   0x8
+#define FV_SPKMUTE_ENABLE                                   0x8
+#define FV_SPKMUTE_DISABLE                                  0x0
+
+#define FB_SPKCTL_SPKDEM                                    2
+#define FM_SPKCTL_SPKDEM                                    0x4
+#define FV_SPKDEM_ENABLE                                    0x4
+#define FV_SPKDEM_DISABLE                                   0x0
+
+// *** SUBCTL ***
+#define FB_SUBCTL_SUBPOL                                    7
+#define FM_SUBCTL_SUBPOL                                    0x80
+
+#define FB_SUBCTL_SUBMUTE                                   3
+#define FM_SUBCTL_SUBMUTE                                   0x8
+
+#define FB_SUBCTL_SUBDEM                                    2
+#define FM_SUBCTL_SUBDEM                                    0x4
+
+#define FB_SUBCTL_SUBMUX                                    1
+#define FM_SUBCTL_SUBMUX                                    0x2
+
+#define FB_SUBCTL_SUBILMDIS                                 0
+#define FM_SUBCTL_SUBILMDIS                                 0x1
+
+// *** DCCTL ***
+#define FB_DCCTL_SUBDCBYP                                   7
+#define FM_DCCTL_SUBDCBYP                                   0x80
+
+#define FB_DCCTL_DACDCBYP                                   6
+#define FM_DCCTL_DACDCBYP                                   0x40
+
+#define FB_DCCTL_SPKDCBYP                                   5
+#define FM_DCCTL_SPKDCBYP                                   0x20
+
+#define FB_DCCTL_DCCOEFSEL                                  0
+#define FM_DCCTL_DCCOEFSEL                                  0x7
+
+// *** OVOLCTLU ***
+#define FB_OVOLCTLU_OFADE                                   4
+#define FM_OVOLCTLU_OFADE                                   0x10
+
+#define FB_OVOLCTLU_SUBVOLU                                 3
+#define FM_OVOLCTLU_SUBVOLU                                 0x8
+
+#define FB_OVOLCTLU_MVOLU                                   2
+#define FM_OVOLCTLU_MVOLU                                   0x4
+
+#define FB_OVOLCTLU_SPKVOLU                                 1
+#define FM_OVOLCTLU_SPKVOLU                                 0x2
+
+#define FB_OVOLCTLU_HPVOLU                                  0
+#define FM_OVOLCTLU_HPVOLU                                  0x1
+
+// *** MUTEC ***
+#define FB_MUTEC_ZDSTAT                                     7
+#define FM_MUTEC_ZDSTAT                                     0x80
+
+#define FB_MUTEC_ZDLEN                                      4
+#define FM_MUTEC_ZDLEN                                      0x30
+
+#define FB_MUTEC_APWD                                       3
+#define FM_MUTEC_APWD                                       0x8
+
+#define FB_MUTEC_AMUTE                                      2
+#define FM_MUTEC_AMUTE                                      0x4
+
+// *** MVOLL ***
+#define FB_MVOLL_MVOL_L                                     0
+#define FM_MVOLL_MVOL_L                                     0xFF
+
+// *** MVOLR ***
+#define FB_MVOLR_MVOL_R                                     0
+#define FM_MVOLR_MVOL_R                                     0xFF
+
+// *** HPVOLL ***
+#define FB_HPVOLL_HPVOL_L                                   0
+#define FM_HPVOLL_HPVOL_L                                   0x7F
+
+// *** HPVOLR ***
+#define FB_HPVOLR_HPVOL_R                                   0
+#define FM_HPVOLR_HPVOL_R                                   0x7F
+
+// *** SPKVOLL ***
+#define FB_SPKVOLL_SPKVOL_L                                 0
+#define FM_SPKVOLL_SPKVOL_L                                 0x7F
+
+// *** SPKVOLR ***
+#define FB_SPKVOLR_SPKVOL_R                                 0
+#define FM_SPKVOLR_SPKVOL_R                                 0x7F
+
+// *** SUBVOL ***
+#define FB_SUBVOL_SUBVOL                                    0
+#define FM_SUBVOL_SUBVOL                                    0x7F
+
+// *** COP0 ***
+#define FB_COP0_COPATTEN                                    7
+#define FM_COP0_COPATTEN                                    0x80
+
+#define FB_COP0_COPGAIN                                     6
+#define FM_COP0_COPGAIN                                     0x40
+
+#define FB_COP0_HDELTAEN                                    5
+#define FM_COP0_HDELTAEN                                    0x20
+
+#define FB_COP0_COPTARGET                                   0
+#define FM_COP0_COPTARGET                                   0x1F
+
+// *** COP1 ***
+#define FB_COP1_HDCOMPMODE                                  6
+#define FM_COP1_HDCOMPMODE                                  0x40
+
+#define FB_COP1_AVGLENGTH                                   2
+#define FM_COP1_AVGLENGTH                                   0x3C
+
+#define FB_COP1_MONRATE                                     0
+#define FM_COP1_MONRATE                                     0x3
+
+// *** COPSTAT ***
+#define FB_COPSTAT_HDELTADET                                7
+#define FM_COPSTAT_HDELTADET                                0x80
+
+#define FB_COPSTAT_UV                                       6
+#define FM_COPSTAT_UV                                       0x40
+
+#define FB_COPSTAT_COPADJ                                   0
+#define FM_COPSTAT_COPADJ                                   0x3F
+
+// *** PWM0 ***
+#define FB_PWM0_SCTO                                        6
+#define FM_PWM0_SCTO                                        0xC0
+
+#define FB_PWM0_UVLO                                        5
+#define FM_PWM0_UVLO                                        0x20
+
+#define FB_PWM0_BFDIS                                       3
+#define FM_PWM0_BFDIS                                       0x8
+
+#define FB_PWM0_PWMMODE                                     2
+#define FM_PWM0_PWMMODE                                     0x4
+
+#define FB_PWM0_NOOFFSET                                    0
+#define FM_PWM0_NOOFFSET                                    0x1
+
+// *** PWM1 ***
+#define FB_PWM1_DITHPOS                                     4
+#define FM_PWM1_DITHPOS                                     0x70
+
+#define FB_PWM1_DYNDITH                                     1
+#define FM_PWM1_DYNDITH                                     0x2
+
+#define FB_PWM1_DITHDIS                                     0
+#define FM_PWM1_DITHDIS                                     0x1
+
+// *** PWM2 ***
+// *** PWM3 ***
+#define FB_PWM3_PWMMUX                                      6
+#define FM_PWM3_PWMMUX                                      0xC0
+
+#define FB_PWM3_CVALUE                                      0
+#define FM_PWM3_CVALUE                                      0x7
+
+// *** HPSW ***
+#define FB_HPSW_HPDETSTATE                                  4
+#define FM_HPSW_HPDETSTATE                                  0x10
+
+#define FB_HPSW_HPSWEN                                      2
+#define FM_HPSW_HPSWEN                                      0xC
+
+#define FB_HPSW_HPSWPOL                                     1
+#define FM_HPSW_HPSWPOL                                     0x2
+
+#define FB_HPSW_TSDEN                                       0
+#define FM_HPSW_TSDEN                                       0x1
+
+// *** THERMTS ***
+#define FB_THERMTS_TRIPHS                                   7
+#define FM_THERMTS_TRIPHS                                   0x80
+
+#define FB_THERMTS_TRIPLS                                   6
+#define FM_THERMTS_TRIPLS                                   0x40
+
+#define FB_THERMTS_TRIPSPLIT                                4
+#define FM_THERMTS_TRIPSPLIT                                0x30
+
+#define FB_THERMTS_TRIPSHIFT                                2
+#define FM_THERMTS_TRIPSHIFT                                0xC
+
+#define FB_THERMTS_TSPOLL                                   0
+#define FM_THERMTS_TSPOLL                                   0x3
+
+// *** THERMSPK1 ***
+#define FB_THERMSPK1_FORCEPWD                               7
+#define FM_THERMSPK1_FORCEPWD                               0x80
+
+#define FB_THERMSPK1_INSTCUTMODE                            6
+#define FM_THERMSPK1_INSTCUTMODE                            0x40
+
+#define FB_THERMSPK1_INCRATIO                               4
+#define FM_THERMSPK1_INCRATIO                               0x30
+
+#define FB_THERMSPK1_INCSTEP                                2
+#define FM_THERMSPK1_INCSTEP                                0xC
+
+#define FB_THERMSPK1_DECSTEP                                0
+#define FM_THERMSPK1_DECSTEP                                0x3
+
+// *** THERMSTAT ***
+#define FB_THERMSTAT_FPWDS                                  7
+#define FM_THERMSTAT_FPWDS                                  0x80
+
+#define FB_THERMSTAT_VOLSTAT                                0
+#define FM_THERMSTAT_VOLSTAT                                0x7F
+
+// *** SCSTAT ***
+#define FB_SCSTAT_ESDF                                      3
+#define FM_SCSTAT_ESDF                                      0x18
+
+#define FB_SCSTAT_CPF                                       2
+#define FM_SCSTAT_CPF                                       0x4
+
+#define FB_SCSTAT_CLSDF                                     0
+#define FM_SCSTAT_CLSDF                                     0x3
+
+// *** SDMON ***
+#define FB_SDMON_SDFORCE                                    7
+#define FM_SDMON_SDFORCE                                    0x80
+
+#define FB_SDMON_SDVALUE                                    0
+#define FM_SDMON_SDVALUE                                    0x1F
+
+// *** SPKEQFILT ***
+#define FB_SPKEQFILT_EQ2EN                                  7
+#define FM_SPKEQFILT_EQ2EN                                  0x80
+#define FV_EQ2EN_ENABLE                                     0x80
+#define FV_EQ2EN_DISABLE                                    0x0
+
+#define FB_SPKEQFILT_EQ2BE                                  4
+#define FM_SPKEQFILT_EQ2BE                                  0x70
+
+#define FB_SPKEQFILT_EQ1EN                                  3
+#define FM_SPKEQFILT_EQ1EN                                  0x8
+#define FV_EQ1EN_ENABLE                                     0x8
+#define FV_EQ1EN_DISABLE                                    0x0
+
+#define FB_SPKEQFILT_EQ1BE                                  0
+#define FM_SPKEQFILT_EQ1BE                                  0x7
+
+#define SPKEQFILT_EQEN_ENABLE                               0x1
+#define SPKEQFILT_EQEN_DISABLE                              0x0
+
+// *** SPKCRWDL ***
+#define FB_SPKCRWDL_WDATA_L                                 0
+#define FM_SPKCRWDL_WDATA_L                                 0xFF
+
+// *** SPKCRWDM ***
+#define FB_SPKCRWDM_WDATA_M                                 0
+#define FM_SPKCRWDM_WDATA_M                                 0xFF
+
+// *** SPKCRWDH ***
+#define FB_SPKCRWDH_WDATA_H                                 0
+#define FM_SPKCRWDH_WDATA_H                                 0xFF
+
+// *** SPKCRRDL ***
+#define FB_SPKCRRDL_RDATA_L                                 0
+#define FM_SPKCRRDL_RDATA_L                                 0xFF
+
+// *** SPKCRRDM ***
+#define FB_SPKCRRDM_RDATA_M                                 0
+#define FM_SPKCRRDM_RDATA_M                                 0xFF
+
+// *** SPKCRRDH ***
+#define FB_SPKCRRDH_RDATA_H                                 0
+#define FM_SPKCRRDH_RDATA_H                                 0xFF
+
+// *** SPKCRADD ***
+#define FB_SPKCRADD_ADDRESS                                 0
+#define FM_SPKCRADD_ADDRESS                                 0xFF
+
+// *** SPKCRS ***
+#define FB_SPKCRS_ACCSTAT                                   7
+#define FM_SPKCRS_ACCSTAT                                   0x80
+
+// *** SPKMBCEN ***
+#define FB_SPKMBCEN_MBCEN3                                  2
+#define FM_SPKMBCEN_MBCEN3                                  0x4
+#define FV_MBCEN3_ENABLE                                    0x4
+#define FV_MBCEN3_DISABLE                                   0x0
+
+#define FB_SPKMBCEN_MBCEN2                                  1
+#define FM_SPKMBCEN_MBCEN2                                  0x2
+#define FV_MBCEN2_ENABLE                                    0x2
+#define FV_MBCEN2_DISABLE                                   0x0
+
+#define FB_SPKMBCEN_MBCEN1                                  0
+#define FM_SPKMBCEN_MBCEN1                                  0x1
+#define FV_MBCEN1_ENABLE                                    0x1
+#define FV_MBCEN1_DISABLE                                   0x0
+
+#define SPKMBCEN_MBCEN_ENABLE                               0x1
+#define SPKMBCEN_MBCEN_DISABLE                              0x0
+
+// *** SPKMBCCTL ***
+#define FB_SPKMBCCTL_LVLMODE3                               5
+#define FM_SPKMBCCTL_LVLMODE3                               0x20
+
+#define FB_SPKMBCCTL_WINSEL3                                4
+#define FM_SPKMBCCTL_WINSEL3                                0x10
+
+#define FB_SPKMBCCTL_LVLMODE2                               3
+#define FM_SPKMBCCTL_LVLMODE2                               0x8
+
+#define FB_SPKMBCCTL_WINSEL2                                2
+#define FM_SPKMBCCTL_WINSEL2                                0x4
+
+#define FB_SPKMBCCTL_LVLMODE1                               1
+#define FM_SPKMBCCTL_LVLMODE1                               0x2
+
+#define FB_SPKMBCCTL_WINSEL1                                0
+#define FM_SPKMBCCTL_WINSEL1                                0x1
+
+// *** SPKCLECTL ***
+#define FB_SPKCLECTL_LVLMODE                                4
+#define FM_SPKCLECTL_LVLMODE                                0x10
+
+#define FB_SPKCLECTL_WINSEL                                 3
+#define FM_SPKCLECTL_WINSEL                                 0x8
+
+#define FB_SPKCLECTL_EXPEN                                  2
+#define FM_SPKCLECTL_EXPEN                                  0x4
+#define FV_EXPEN_ENABLE                                     0x4
+#define FV_EXPEN_DISABLE                                    0x0
+
+#define FB_SPKCLECTL_LIMEN                                  1
+#define FM_SPKCLECTL_LIMEN                                  0x2
+#define FV_LIMEN_ENABLE                                     0x2
+#define FV_LIMEN_DISABLE                                    0x0
+
+#define FB_SPKCLECTL_COMPEN                                 0
+#define FM_SPKCLECTL_COMPEN                                 0x1
+#define FV_COMPEN_ENABLE                                    0x1
+#define FV_COMPEN_DISABLE                                   0x0
+
+// *** SPKCLEMUG ***
+#define FB_SPKCLEMUG_MUGAIN                                 0
+#define FM_SPKCLEMUG_MUGAIN                                 0x1F
+
+// *** SPKCOMPTHR ***
+#define FB_SPKCOMPTHR_THRESH                                0
+#define FM_SPKCOMPTHR_THRESH                                0xFF
+
+// *** SPKCOMPRAT ***
+#define FB_SPKCOMPRAT_RATIO                                 0
+#define FM_SPKCOMPRAT_RATIO                                 0x1F
+
+// *** SPKCOMPATKL ***
+#define FB_SPKCOMPATKL_TCATKL                               0
+#define FM_SPKCOMPATKL_TCATKL                               0xFF
+
+// *** SPKCOMPATKH ***
+#define FB_SPKCOMPATKH_TCATKH                               0
+#define FM_SPKCOMPATKH_TCATKH                               0xFF
+
+// *** SPKCOMPRELL ***
+#define FB_SPKCOMPRELL_TCRELL                               0
+#define FM_SPKCOMPRELL_TCRELL                               0xFF
+
+// *** SPKCOMPRELH ***
+#define FB_SPKCOMPRELH_TCRELH                               0
+#define FM_SPKCOMPRELH_TCRELH                               0xFF
+
+// *** SPKLIMTHR ***
+#define FB_SPKLIMTHR_THRESH                                 0
+#define FM_SPKLIMTHR_THRESH                                 0xFF
+
+// *** SPKLIMTGT ***
+#define FB_SPKLIMTGT_TARGET                                 0
+#define FM_SPKLIMTGT_TARGET                                 0xFF
+
+// *** SPKLIMATKL ***
+#define FB_SPKLIMATKL_TCATKL                                0
+#define FM_SPKLIMATKL_TCATKL                                0xFF
+
+// *** SPKLIMATKH ***
+#define FB_SPKLIMATKH_TCATKH                                0
+#define FM_SPKLIMATKH_TCATKH                                0xFF
+
+// *** SPKLIMRELL ***
+#define FB_SPKLIMRELL_TCRELL                                0
+#define FM_SPKLIMRELL_TCRELL                                0xFF
+
+// *** SPKLIMRELH ***
+#define FB_SPKLIMRELH_TCRELH                                0
+#define FM_SPKLIMRELH_TCRELH                                0xFF
+
+// *** SPKEXPTHR ***
+#define FB_SPKEXPTHR_THRESH                                 0
+#define FM_SPKEXPTHR_THRESH                                 0xFF
+
+// *** SPKEXPRAT ***
+#define FB_SPKEXPRAT_RATIO                                  0
+#define FM_SPKEXPRAT_RATIO                                  0x7
+
+// *** SPKEXPATKL ***
+#define FB_SPKEXPATKL_TCATKL                                0
+#define FM_SPKEXPATKL_TCATKL                                0xFF
+
+// *** SPKEXPATKH ***
+#define FB_SPKEXPATKH_TCATKH                                0
+#define FM_SPKEXPATKH_TCATKH                                0xFF
+
+// *** SPKEXPRELL ***
+#define FB_SPKEXPRELL_TCRELL                                0
+#define FM_SPKEXPRELL_TCRELL                                0xFF
+
+// *** SPKEXPRELH ***
+#define FB_SPKEXPRELH_TCRELH                                0
+#define FM_SPKEXPRELH_TCRELH                                0xFF
+
+// *** SPKFXCTL ***
+#define FB_SPKFXCTL_3DEN                                    4
+#define FM_SPKFXCTL_3DEN                                    0x10
+
+#define FB_SPKFXCTL_TEEN                                    3
+#define FM_SPKFXCTL_TEEN                                    0x8
+
+#define FB_SPKFXCTL_TNLFBYP                                 2
+#define FM_SPKFXCTL_TNLFBYP                                 0x4
+
+#define FB_SPKFXCTL_BEEN                                    1
+#define FM_SPKFXCTL_BEEN                                    0x2
+
+#define FB_SPKFXCTL_BNLFBYP                                 0
+#define FM_SPKFXCTL_BNLFBYP                                 0x1
+
+// *** DACEQFILT ***
+#define FB_DACEQFILT_EQ2EN                                  7
+#define FM_DACEQFILT_EQ2EN                                  0x80
+#define FV_EQ2EN_ENABLE                                     0x80
+#define FV_EQ2EN_DISABLE                                    0x0
+
+#define FB_DACEQFILT_EQ2BE                                  4
+#define FM_DACEQFILT_EQ2BE                                  0x70
+
+#define FB_DACEQFILT_EQ1EN                                  3
+#define FM_DACEQFILT_EQ1EN                                  0x8
+#define FV_EQ1EN_ENABLE                                     0x8
+#define FV_EQ1EN_DISABLE                                    0x0
+
+#define FB_DACEQFILT_EQ1BE                                  0
+#define FM_DACEQFILT_EQ1BE                                  0x7
+
+#define DACEQFILT_EQEN_ENABLE                               0x1
+#define DACEQFILT_EQEN_DISABLE                              0x0
+
+// *** DACCRWDL ***
+#define FB_DACCRWDL_WDATA_L                                 0
+#define FM_DACCRWDL_WDATA_L                                 0xFF
+
+// *** DACCRWDM ***
+#define FB_DACCRWDM_WDATA_M                                 0
+#define FM_DACCRWDM_WDATA_M                                 0xFF
+
+// *** DACCRWDH ***
+#define FB_DACCRWDH_WDATA_H                                 0
+#define FM_DACCRWDH_WDATA_H                                 0xFF
+
+// *** DACCRRDL ***
+#define FB_DACCRRDL_RDATA_L                                 0
+#define FM_DACCRRDL_RDATA_L                                 0xFF
+
+// *** DACCRRDM ***
+#define FB_DACCRRDM_RDATA_M                                 0
+#define FM_DACCRRDM_RDATA_M                                 0xFF
+
+// *** DACCRRDH ***
+#define FB_DACCRRDH_RDATA_H                                 0
+#define FM_DACCRRDH_RDATA_H                                 0xFF
+
+// *** DACCRADD ***
+#define FB_DACCRADD_ADDRESS                                 0
+#define FM_DACCRADD_ADDRESS                                 0xFF
+
+// *** DACCRS ***
+#define FB_DACCRS_ACCSTAT                                   7
+#define FM_DACCRS_ACCSTAT                                   0x80
+
+// *** DACMBCEN ***
+#define FB_DACMBCEN_MBCEN3                                  2
+#define FM_DACMBCEN_MBCEN3                                  0x4
+#define FV_MBCEN3_ENABLE                                    0x4
+#define FV_MBCEN3_DISABLE                                   0x0
+
+#define FB_DACMBCEN_MBCEN2                                  1
+#define FM_DACMBCEN_MBCEN2                                  0x2
+#define FV_MBCEN2_ENABLE                                    0x2
+#define FV_MBCEN2_DISABLE                                   0x0
+
+#define FB_DACMBCEN_MBCEN1                                  0
+#define FM_DACMBCEN_MBCEN1                                  0x1
+#define FV_MBCEN1_ENABLE                                    0x1
+#define FV_MBCEN1_DISABLE                                   0x0
+
+#define DACMBCEN_MBCEN_ENABLE                               0x1
+#define DACMBCEN_MBCEN_DISABLE                              0x0
+
+// *** DACMBCCTL ***
+#define FB_DACMBCCTL_LVLMODE3                               5
+#define FM_DACMBCCTL_LVLMODE3                               0x20
+
+#define FB_DACMBCCTL_WINSEL3                                4
+#define FM_DACMBCCTL_WINSEL3                                0x10
+
+#define FB_DACMBCCTL_LVLMODE2                               3
+#define FM_DACMBCCTL_LVLMODE2                               0x8
+
+#define FB_DACMBCCTL_WINSEL2                                2
+#define FM_DACMBCCTL_WINSEL2                                0x4
+
+#define FB_DACMBCCTL_LVLMODE1                               1
+#define FM_DACMBCCTL_LVLMODE1                               0x2
+
+#define FB_DACMBCCTL_WINSEL1                                0
+#define FM_DACMBCCTL_WINSEL1                                0x1
+
+// *** DACCLECTL ***
+#define FB_DACCLECTL_LVLMODE                                4
+#define FM_DACCLECTL_LVLMODE                                0x10
+
+#define FB_DACCLECTL_WINSEL                                 3
+#define FM_DACCLECTL_WINSEL                                 0x8
+
+#define FB_DACCLECTL_EXPEN                                  2
+#define FM_DACCLECTL_EXPEN                                  0x4
+#define FV_EXPEN_ENABLE                                     0x4
+#define FV_EXPEN_DISABLE                                    0x0
+
+#define FB_DACCLECTL_LIMEN                                  1
+#define FM_DACCLECTL_LIMEN                                  0x2
+#define FV_LIMEN_ENABLE                                     0x2
+#define FV_LIMEN_DISABLE                                    0x0
+
+#define FB_DACCLECTL_COMPEN                                 0
+#define FM_DACCLECTL_COMPEN                                 0x1
+#define FV_COMPEN_ENABLE                                    0x1
+#define FV_COMPEN_DISABLE                                   0x0
+
+// *** DACCLEMUG ***
+#define FB_DACCLEMUG_MUGAIN                                 0
+#define FM_DACCLEMUG_MUGAIN                                 0x1F
+
+// *** DACCOMPTHR ***
+#define FB_DACCOMPTHR_THRESH                                0
+#define FM_DACCOMPTHR_THRESH                                0xFF
+
+// *** DACCOMPRAT ***
+#define FB_DACCOMPRAT_RATIO                                 0
+#define FM_DACCOMPRAT_RATIO                                 0x1F
+
+// *** DACCOMPATKL ***
+#define FB_DACCOMPATKL_TCATKL                               0
+#define FM_DACCOMPATKL_TCATKL                               0xFF
+
+// *** DACCOMPATKH ***
+#define FB_DACCOMPATKH_TCATKH                               0
+#define FM_DACCOMPATKH_TCATKH                               0xFF
+
+// *** DACCOMPRELL ***
+#define FB_DACCOMPRELL_TCRELL                               0
+#define FM_DACCOMPRELL_TCRELL                               0xFF
+
+// *** DACCOMPRELH ***
+#define FB_DACCOMPRELH_TCRELH                               0
+#define FM_DACCOMPRELH_TCRELH                               0xFF
+
+// *** DACLIMTHR ***
+#define FB_DACLIMTHR_THRESH                                 0
+#define FM_DACLIMTHR_THRESH                                 0xFF
+
+// *** DACLIMTGT ***
+#define FB_DACLIMTGT_TARGET                                 0
+#define FM_DACLIMTGT_TARGET                                 0xFF
+
+// *** DACLIMATKL ***
+#define FB_DACLIMATKL_TCATKL                                0
+#define FM_DACLIMATKL_TCATKL                                0xFF
+
+// *** DACLIMATKH ***
+#define FB_DACLIMATKH_TCATKH                                0
+#define FM_DACLIMATKH_TCATKH                                0xFF
+
+// *** DACLIMRELL ***
+#define FB_DACLIMRELL_TCRELL                                0
+#define FM_DACLIMRELL_TCRELL                                0xFF
+
+// *** DACLIMRELH ***
+#define FB_DACLIMRELH_TCRELH                                0
+#define FM_DACLIMRELH_TCRELH                                0xFF
+
+// *** DACEXPTHR ***
+#define FB_DACEXPTHR_THRESH                                 0
+#define FM_DACEXPTHR_THRESH                                 0xFF
+
+// *** DACEXPRAT ***
+#define FB_DACEXPRAT_RATIO                                  0
+#define FM_DACEXPRAT_RATIO                                  0x7
+
+// *** DACEXPATKL ***
+#define FB_DACEXPATKL_TCATKL                                0
+#define FM_DACEXPATKL_TCATKL                                0xFF
+
+// *** DACEXPATKH ***
+#define FB_DACEXPATKH_TCATKH                                0
+#define FM_DACEXPATKH_TCATKH                                0xFF
+
+// *** DACEXPRELL ***
+#define FB_DACEXPRELL_TCRELL                                0
+#define FM_DACEXPRELL_TCRELL                                0xFF
+
+// *** DACEXPRELH ***
+#define FB_DACEXPRELH_TCRELH                                0
+#define FM_DACEXPRELH_TCRELH                                0xFF
+
+// *** DACFXCTL ***
+#define FB_DACFXCTL_3DEN                                    4
+#define FM_DACFXCTL_3DEN                                    0x10
+
+#define FB_DACFXCTL_TEEN                                    3
+#define FM_DACFXCTL_TEEN                                    0x8
+
+#define FB_DACFXCTL_TNLFBYP                                 2
+#define FM_DACFXCTL_TNLFBYP                                 0x4
+
+#define FB_DACFXCTL_BEEN                                    1
+#define FM_DACFXCTL_BEEN                                    0x2
+
+#define FB_DACFXCTL_BNLFBYP                                 0
+#define FM_DACFXCTL_BNLFBYP                                 0x1
+
+// *** SUBEQFILT ***
+#define FB_SUBEQFILT_EQ2EN                                  7
+#define FM_SUBEQFILT_EQ2EN                                  0x80
+#define FV_EQ2EN_ENABLE                                     0x80
+#define FV_EQ2EN_DISABLE                                    0x0
+
+#define FB_SUBEQFILT_EQ2BE                                  4
+#define FM_SUBEQFILT_EQ2BE                                  0x70
+
+#define FB_SUBEQFILT_EQ1EN                                  3
+#define FM_SUBEQFILT_EQ1EN                                  0x8
+#define FV_EQ1EN_ENABLE                                     0x8
+#define FV_EQ1EN_DISABLE                                    0x0
+
+#define FB_SUBEQFILT_EQ1BE                                  0
+#define FM_SUBEQFILT_EQ1BE                                  0x7
+
+#define SUBEQFILT_EQEN_ENABLE                               0x1
+#define SUBEQFILT_EQEN_DISABLE                              0x0
+
+// *** SUBCRWDL ***
+#define FB_SUBCRWDL_WDATA_L                                 0
+#define FM_SUBCRWDL_WDATA_L                                 0xFF
+
+// *** SUBCRWDM ***
+#define FB_SUBCRWDM_WDATA_M                                 0
+#define FM_SUBCRWDM_WDATA_M                                 0xFF
+
+// *** SUBCRWDH ***
+#define FB_SUBCRWDH_WDATA_H                                 0
+#define FM_SUBCRWDH_WDATA_H                                 0xFF
+
+// *** SUBCRRDL ***
+#define FB_SUBCRRDL_RDATA_L                                 0
+#define FM_SUBCRRDL_RDATA_L                                 0xFF
+
+// *** SUBCRRDM ***
+#define FB_SUBCRRDM_RDATA_M                                 0
+#define FM_SUBCRRDM_RDATA_M                                 0xFF
+
+// *** SUBCRRDH ***
+#define FB_SUBCRRDH_RDATA_H                                 0
+#define FM_SUBCRRDH_RDATA_H                                 0xFF
+
+// *** SUBCRADD ***
+#define FB_SUBCRADD_ADDRESS                                 0
+#define FM_SUBCRADD_ADDRESS                                 0xFF
+
+// *** SUBCRS ***
+#define FB_SUBCRS_ACCSTAT                                   7
+#define FM_SUBCRS_ACCSTAT                                   0x80
+
+// *** SUBMBCEN ***
+#define FB_SUBMBCEN_MBCEN3                                  2
+#define FM_SUBMBCEN_MBCEN3                                  0x4
+#define FV_MBCEN3_ENABLE                                    0x4
+#define FV_MBCEN3_DISABLE                                   0x0
+
+#define FB_SUBMBCEN_MBCEN2                                  1
+#define FM_SUBMBCEN_MBCEN2                                  0x2
+#define FV_MBCEN2_ENABLE                                    0x2
+#define FV_MBCEN2_DISABLE                                   0x0
+
+#define FB_SUBMBCEN_MBCEN1                                  0
+#define FM_SUBMBCEN_MBCEN1                                  0x1
+#define FV_MBCEN1_ENABLE                                    0x1
+#define FV_MBCEN1_DISABLE                                   0x0
+
+#define SUBMBCEN_MBCEN_ENABLE                               0x1
+#define SUBMBCEN_MBCEN_DISABLE                              0x0
+
+// *** SUBMBCCTL ***
+#define FB_SUBMBCCTL_LVLMODE3                               5
+#define FM_SUBMBCCTL_LVLMODE3                               0x20
+
+#define FB_SUBMBCCTL_WINSEL3                                4
+#define FM_SUBMBCCTL_WINSEL3                                0x10
+
+#define FB_SUBMBCCTL_LVLMODE2                               3
+#define FM_SUBMBCCTL_LVLMODE2                               0x8
+
+#define FB_SUBMBCCTL_WINSEL2                                2
+#define FM_SUBMBCCTL_WINSEL2                                0x4
+
+#define FB_SUBMBCCTL_LVLMODE1                               1
+#define FM_SUBMBCCTL_LVLMODE1                               0x2
+
+#define FB_SUBMBCCTL_WINSEL1                                0
+#define FM_SUBMBCCTL_WINSEL1                                0x1
+
+// *** SUBCLECTL ***
+#define FB_SUBCLECTL_LVLMODE                                4
+#define FM_SUBCLECTL_LVLMODE                                0x10
+
+#define FB_SUBCLECTL_WINSEL                                 3
+#define FM_SUBCLECTL_WINSEL                                 0x8
+
+#define FB_SUBCLECTL_EXPEN                                  2
+#define FM_SUBCLECTL_EXPEN                                  0x4
+#define FV_EXPEN_ENABLE                                     0x4
+#define FV_EXPEN_DISABLE                                    0x0
+
+#define FB_SUBCLECTL_LIMEN                                  1
+#define FM_SUBCLECTL_LIMEN                                  0x2
+#define FV_LIMEN_ENABLE                                     0x2
+#define FV_LIMEN_DISABLE                                    0x0
+
+#define FB_SUBCLECTL_COMPEN                                 0
+#define FM_SUBCLECTL_COMPEN                                 0x1
+#define FV_COMPEN_ENABLE                                    0x1
+#define FV_COMPEN_DISABLE                                   0x0
+
+// *** SUBCLEMUG ***
+#define FB_SUBCLEMUG_MUGAIN                                 0
+#define FM_SUBCLEMUG_MUGAIN                                 0x1F
+
+// *** SUBCOMPTHR ***
+#define FB_SUBCOMPTHR_THRESH                                0
+#define FM_SUBCOMPTHR_THRESH                                0xFF
+
+// *** SUBCOMPRAT ***
+#define FB_SUBCOMPRAT_RATIO                                 0
+#define FM_SUBCOMPRAT_RATIO                                 0x1F
+
+// *** SUBCOMPATKL ***
+#define FB_SUBCOMPATKL_TCATKL                               0
+#define FM_SUBCOMPATKL_TCATKL                               0xFF
+
+// *** SUBCOMPATKH ***
+#define FB_SUBCOMPATKH_TCATKH                               0
+#define FM_SUBCOMPATKH_TCATKH                               0xFF
+
+// *** SUBCOMPRELL ***
+#define FB_SUBCOMPRELL_TCRELL                               0
+#define FM_SUBCOMPRELL_TCRELL                               0xFF
+
+// *** SUBCOMPRELH ***
+#define FB_SUBCOMPRELH_TCRELH                               0
+#define FM_SUBCOMPRELH_TCRELH                               0xFF
+
+// *** SUBLIMTHR ***
+#define FB_SUBLIMTHR_THRESH                                 0
+#define FM_SUBLIMTHR_THRESH                                 0xFF
+
+// *** SUBLIMTGT ***
+#define FB_SUBLIMTGT_TARGET                                 0
+#define FM_SUBLIMTGT_TARGET                                 0xFF
+
+// *** SUBLIMATKL ***
+#define FB_SUBLIMATKL_TCATKL                                0
+#define FM_SUBLIMATKL_TCATKL                                0xFF
+
+// *** SUBLIMATKH ***
+#define FB_SUBLIMATKH_TCATKH                                0
+#define FM_SUBLIMATKH_TCATKH                                0xFF
+
+// *** SUBLIMRELL ***
+#define FB_SUBLIMRELL_TCRELL                                0
+#define FM_SUBLIMRELL_TCRELL                                0xFF
+
+// *** SUBLIMRELH ***
+#define FB_SUBLIMRELH_TCRELH                                0
+#define FM_SUBLIMRELH_TCRELH                                0xFF
+
+// *** SUBEXPTHR ***
+#define FB_SUBEXPTHR_THRESH                                 0
+#define FM_SUBEXPTHR_THRESH                                 0xFF
+
+// *** SUBEXPRAT ***
+#define FB_SUBEXPRAT_RATIO                                  0
+#define FM_SUBEXPRAT_RATIO                                  0x7
+
+// *** SUBEXPATKL ***
+#define FB_SUBEXPATKL_TCATKL                                0
+#define FM_SUBEXPATKL_TCATKL                                0xFF
+
+// *** SUBEXPATKH ***
+#define FB_SUBEXPATKH_TCATKH                                0
+#define FM_SUBEXPATKH_TCATKH                                0xFF
+
+// *** SUBEXPRELL ***
+#define FB_SUBEXPRELL_TCRELL                                0
+#define FM_SUBEXPRELL_TCRELL                                0xFF
+
+// *** SUBEXPRELH ***
+#define FB_SUBEXPRELH_TCRELH                                0
+#define FM_SUBEXPRELH_TCRELH                                0xFF
+
+// *** SUBFXCTL ***
+#define FB_SUBFXCTL_TEEN                                    3
+#define FM_SUBFXCTL_TEEN                                    0x8
+
+#define FB_SUBFXCTL_TNLFBYP                                 2
+#define FM_SUBFXCTL_TNLFBYP                                 0x4
+
+#define FB_SUBFXCTL_BEEN                                    1
+#define FM_SUBFXCTL_BEEN                                    0x2
+
+#define FB_SUBFXCTL_BNLFBYP                                 0
+#define FM_SUBFXCTL_BNLFBYP                                 0x1
+
+#endif /* __REDWOODPUBLIC_H__ */
diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c
index d5f4bbf27182..3663b9fd4d65 100644
--- a/sound/soc/codecs/wm2200.c
+++ b/sound/soc/codecs/wm2200.c
@@ -1155,8 +1155,8 @@ SOC_DOUBLE_R_TLV("IN3 Digital Volume", WM2200_ADC_DIGITAL_VOLUME_3L,
 SND_SOC_BYTES_MASK("EQL Coefficients", WM2200_EQL_1, 20, WM2200_EQL_ENA),
 SND_SOC_BYTES_MASK("EQR Coefficients", WM2200_EQR_1, 20, WM2200_EQR_ENA),
 
-SND_SOC_BYTES("LHPF1 Coefficeints", WM2200_HPLPF1_2, 1),
-SND_SOC_BYTES("LHPF2 Coefficeints", WM2200_HPLPF2_2, 1),
+SND_SOC_BYTES("LHPF1 Coefficients", WM2200_HPLPF1_2, 1),
+SND_SOC_BYTES("LHPF2 Coefficients", WM2200_HPLPF2_2, 1),
 
 SOC_SINGLE("OUT1 High Performance Switch", WM2200_DAC_DIGITAL_VOLUME_1L,
 	   WM2200_OUT1_OSR_SHIFT, 1, 0),
diff --git a/sound/soc/codecs/wm5100.c b/sound/soc/codecs/wm5100.c
index 87f9a99ce978..ba89d9d711f7 100644
--- a/sound/soc/codecs/wm5100.c
+++ b/sound/soc/codecs/wm5100.c
@@ -573,10 +573,10 @@ SND_SOC_BYTES_MASK("EQ4 Coefficients", WM5100_EQ4_1, 20, WM5100_EQ4_ENA),
 SND_SOC_BYTES_MASK("DRC Coefficients", WM5100_DRC1_CTRL1, 5,
 		   WM5100_DRCL_ENA | WM5100_DRCR_ENA),
 
-SND_SOC_BYTES("LHPF1 Coefficeints", WM5100_HPLPF1_2, 1),
-SND_SOC_BYTES("LHPF2 Coefficeints", WM5100_HPLPF2_2, 1),
-SND_SOC_BYTES("LHPF3 Coefficeints", WM5100_HPLPF3_2, 1),
-SND_SOC_BYTES("LHPF4 Coefficeints", WM5100_HPLPF4_2, 1),
+SND_SOC_BYTES("LHPF1 Coefficients", WM5100_HPLPF1_2, 1),
+SND_SOC_BYTES("LHPF2 Coefficients", WM5100_HPLPF2_2, 1),
+SND_SOC_BYTES("LHPF3 Coefficients", WM5100_HPLPF3_2, 1),
+SND_SOC_BYTES("LHPF4 Coefficients", WM5100_HPLPF4_2, 1),
 
 SOC_SINGLE("HPOUT1 High Performance Switch", WM5100_OUT_VOLUME_1L,
 	   WM5100_OUT1_OSR_SHIFT, 1, 0),
diff --git a/sound/soc/codecs/wm8782.c b/sound/soc/codecs/wm8782.c
index 7949703f3d04..317db9a149a7 100644
--- a/sound/soc/codecs/wm8782.c
+++ b/sound/soc/codecs/wm8782.c
@@ -67,9 +67,18 @@ static int wm8782_probe(struct platform_device *pdev)
 			&soc_component_dev_wm8782, &wm8782_dai, 1);
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id wm8782_of_match[] = {
+	{ .compatible = "wlf,wm8782", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wm8782_of_match);
+#endif
+
 static struct platform_driver wm8782_codec_driver = {
 	.driver = {
 		.name = "wm8782",
+		.of_match_table = of_match_ptr(wm8782_of_match),
 	},
 	.probe = wm8782_probe,
 };
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 20fdcae06c6b..f13ef334c0d7 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -596,7 +596,7 @@ static const struct snd_kcontrol_new wm8904_adc_snd_controls[] = {
 SOC_DOUBLE_R_TLV("Digital Capture Volume", WM8904_ADC_DIGITAL_VOLUME_LEFT,
 		 WM8904_ADC_DIGITAL_VOLUME_RIGHT, 1, 119, 0, digital_tlv),
 
-SOC_ENUM("Left Caputure Mode", lin_mode),
+SOC_ENUM("Left Capture Mode", lin_mode),
 SOC_ENUM("Right Capture Mode", rin_mode),
 
 /* No TLV since it depends on mode */
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 82b0927e6ed7..2175dccdf388 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -627,22 +627,21 @@ static void wm_adsp2_init_debugfs(struct wm_adsp *dsp,
 	if (!root)
 		goto err;
 
-	if (!debugfs_create_bool("booted", S_IRUGO, root, &dsp->booted))
+	if (!debugfs_create_bool("booted", 0444, root, &dsp->booted))
 		goto err;
 
-	if (!debugfs_create_bool("running", S_IRUGO, root, &dsp->running))
+	if (!debugfs_create_bool("running", 0444, root, &dsp->running))
 		goto err;
 
-	if (!debugfs_create_x32("fw_id", S_IRUGO, root, &dsp->fw_id))
+	if (!debugfs_create_x32("fw_id", 0444, root, &dsp->fw_id))
 		goto err;
 
-	if (!debugfs_create_x32("fw_version", S_IRUGO, root,
-				&dsp->fw_id_version))
+	if (!debugfs_create_x32("fw_version", 0444, root, &dsp->fw_id_version))
 		goto err;
 
 	for (i = 0; i < ARRAY_SIZE(wm_adsp_debugfs_fops); ++i) {
 		if (!debugfs_create_file(wm_adsp_debugfs_fops[i].name,
-					 S_IRUGO, root, dsp,
+					 0444, root, dsp,
 					 &wm_adsp_debugfs_fops[i].fops))
 			goto err;
 	}
@@ -2666,9 +2665,9 @@ int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol,
 	dsp->preloaded = ucontrol->value.integer.value[0];
 
 	if (ucontrol->value.integer.value[0])
-		snd_soc_dapm_force_enable_pin(dapm, preload);
+		snd_soc_component_force_enable_pin(component, preload);
 	else
-		snd_soc_dapm_disable_pin(dapm, preload);
+		snd_soc_component_disable_pin(component, preload);
 
 	snd_soc_dapm_sync(dapm);
 
@@ -2852,11 +2851,11 @@ EXPORT_SYMBOL_GPL(wm_adsp2_event);
 
 int wm_adsp2_component_probe(struct wm_adsp *dsp, struct snd_soc_component *component)
 {
-	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
 	char preload[32];
 
 	snprintf(preload, ARRAY_SIZE(preload), "DSP%d Preload", dsp->num);
-	snd_soc_dapm_disable_pin(dapm, preload);
+
+	snd_soc_component_disable_pin(component, preload);
 
 	wm_adsp2_init_debugfs(dsp, component);
 
diff --git a/sound/soc/davinci/Kconfig b/sound/soc/davinci/Kconfig
index 6b732d8e5896..778faff28e0e 100644
--- a/sound/soc/davinci/Kconfig
+++ b/sound/soc/davinci/Kconfig
@@ -24,7 +24,7 @@ config SND_DAVINCI_SOC_I2S
 
 config SND_DAVINCI_SOC_MCASP
 	tristate "Multichannel Audio Serial Port (McASP) support"
-	depends on SND_OMAP_SOC || SND_EDMA_SOC
+	depends on SND_SDMA_SOC || SND_EDMA_SOC
 	help
 	  Say Y or M here if you want to have support for McASP IP found in
 	  various Texas Instruments SoCs like:
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 03ba218160ca..1f96c9dbe9c4 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -36,9 +36,9 @@
 #include <sound/initval.h>
 #include <sound/soc.h>
 #include <sound/dmaengine_pcm.h>
-#include <sound/omap-pcm.h>
 
 #include "edma-pcm.h"
+#include "../omap/sdma-pcm.h"
 #include "davinci-mcasp.h"
 
 #define MCASP_MAX_AFIFO_DEPTH	64
@@ -789,7 +789,7 @@ static int mcasp_common_hw_param(struct davinci_mcasp *mcasp, int stream,
 					rx_ser < max_active_serializers) {
 			mcasp_clr_bits(mcasp, DAVINCI_MCASP_PDIR_REG, AXR(i));
 			rx_ser++;
-		} else {
+		} else if (mcasp->serial_dir[i] == INACTIVE_MODE) {
 			mcasp_mod_bits(mcasp, DAVINCI_MCASP_XRSRCTL_REG(i),
 				       SRMOD_INACTIVE, SRMOD_MASK);
 		}
@@ -2048,10 +2048,10 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 #endif
 		break;
 	case PCM_SDMA:
-#if IS_BUILTIN(CONFIG_SND_OMAP_SOC) || \
+#if IS_BUILTIN(CONFIG_SND_SDMA_SOC) || \
 	(IS_MODULE(CONFIG_SND_DAVINCI_SOC_MCASP) && \
-	 IS_MODULE(CONFIG_SND_OMAP_SOC))
-		ret = omap_pcm_platform_register(&pdev->dev);
+	 IS_MODULE(CONFIG_SND_SDMA_SOC))
+		ret = sdma_pcm_platform_register(&pdev->dev, NULL, NULL);
 #else
 		dev_err(&pdev->dev, "Missing SND_SDMA_SOC\n");
 		ret = -EINVAL;
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index 40a700493f4c..8f43110373b8 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -1,12 +1,8 @@
-/*
- * Freescale ESAI ALSA SoC Digital Audio Interface (DAI) driver
- *
- * Copyright (C) 2014 Freescale Semiconductor, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale ESAI ALSA SoC Digital Audio Interface (DAI) driver
+//
+// Copyright (C) 2014 Freescale Semiconductor, Inc.
 
 #include <linux/clk.h>
 #include <linux/dmaengine.h>
@@ -144,6 +140,13 @@ static int fsl_esai_divisor_cal(struct snd_soc_dai *dai, bool tx, u32 ratio,
 
 	psr = ratio <= 256 * maxfp ? ESAI_xCCR_xPSR_BYPASS : ESAI_xCCR_xPSR_DIV8;
 
+	/* Do not loop-search if PM (1 ~ 256) alone can serve the ratio */
+	if (ratio <= 256) {
+		pm = ratio;
+		fp = 1;
+		goto out;
+	}
+
 	/* Set the max fluctuation -- 0.1% of the max devisor */
 	savesub = (psr ? 1 : 8)  * 256 * maxfp / 1000;
 
@@ -219,6 +222,12 @@ static int fsl_esai_set_dai_sysclk(struct snd_soc_dai *dai, int clk_id,
 	unsigned long clk_rate;
 	int ret;
 
+	if (freq == 0) {
+		dev_err(dai->dev, "%sput freq of HCK%c should not be 0Hz\n",
+			in ? "in" : "out", tx ? 'T' : 'R');
+		return -EINVAL;
+	}
+
 	/* Bypass divider settings if the requirement doesn't change */
 	if (freq == esai_priv->hck_rate[tx] && dir == esai_priv->hck_dir[tx])
 		return 0;
diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h
index 5e793bbb6b02..f873588d9045 100644
--- a/sound/soc/fsl/fsl_esai.h
+++ b/sound/soc/fsl/fsl_esai.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * fsl_esai.h - ALSA ESAI interface for the Freescale i.MX SoC
  *
  * Copyright (C) 2014 Freescale Semiconductor, Inc.
  *
  * Author: Nicolin Chen <Guangyu.Chen@freescale.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #ifndef _FSL_ESAI_DAI_H
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 18e5ce81527d..4163f2cfc06f 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -1,14 +1,8 @@
-/*
- * Freescale ALSA SoC Digital Audio Interface (SAI) driver.
- *
- * Copyright 2012-2015 Freescale Semiconductor, Inc.
- *
- * This program is free software, you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation, either version 2 of the License, or(at your
- * option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Freescale ALSA SoC Digital Audio Interface (SAI) driver.
+//
+// Copyright 2012-2015 Freescale Semiconductor, Inc.
 
 #include <linux/clk.h>
 #include <linux/delay.h>
diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h
index d9ed7be8cb34..24cb156bf995 100644
--- a/sound/soc/fsl/fsl_sai.h
+++ b/sound/soc/fsl/fsl_sai.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2012-2013 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __FSL_SAI_H
diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c
index 4f7469c1864c..9b59d87b61bf 100644
--- a/sound/soc/fsl/fsl_spdif.c
+++ b/sound/soc/fsl/fsl_spdif.c
@@ -1,17 +1,13 @@
-/*
- * Freescale S/PDIF ALSA SoC Digital Audio Interface (DAI) driver
- *
- * Copyright (C) 2013 Freescale Semiconductor, Inc.
- *
- * Based on stmp3xxx_spdif_dai.c
- * Vladimir Barinov <vbarinov@embeddedalley.com>
- * Copyright 2008 SigmaTel, Inc
- * Copyright 2008 Embedded Alley Solutions, Inc
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program  is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale S/PDIF ALSA SoC Digital Audio Interface (DAI) driver
+//
+// Copyright (C) 2013 Freescale Semiconductor, Inc.
+//
+// Based on stmp3xxx_spdif_dai.c
+// Vladimir Barinov <vbarinov@embeddedalley.com>
+// Copyright 2008 SigmaTel, Inc
+// Copyright 2008 Embedded Alley Solutions, Inc
 
 #include <linux/bitrev.h>
 #include <linux/clk.h>
diff --git a/sound/soc/fsl/fsl_spdif.h b/sound/soc/fsl/fsl_spdif.h
index 00bd3514c610..7666dabaccfd 100644
--- a/sound/soc/fsl/fsl_spdif.h
+++ b/sound/soc/fsl/fsl_spdif.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * fsl_spdif.h - ALSA S/PDIF interface for the Freescale i.MX SoC
  *
@@ -8,10 +9,6 @@
  * Based on fsl_ssi.h
  * Author: Timur Tabi <timur@freescale.com>
  * Copyright 2007-2008 Freescale Semiconductor, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program  is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #ifndef _FSL_SPDIF_DAI_H
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 0823b08923b5..0a648229e643 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -1,34 +1,29 @@
-/*
- * Freescale SSI ALSA SoC Digital Audio Interface (DAI) driver
- *
- * Author: Timur Tabi <timur@freescale.com>
- *
- * Copyright 2007-2010 Freescale Semiconductor, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- *
- *
- * Some notes why imx-pcm-fiq is used instead of DMA on some boards:
- *
- * The i.MX SSI core has some nasty limitations in AC97 mode. While most
- * sane processor vendors have a FIFO per AC97 slot, the i.MX has only
- * one FIFO which combines all valid receive slots. We cannot even select
- * which slots we want to receive. The WM9712 with which this driver
- * was developed with always sends GPIO status data in slot 12 which
- * we receive in our (PCM-) data stream. The only chance we have is to
- * manually skip this data in the FIQ handler. With sampling rates different
- * from 48000Hz not every frame has valid receive data, so the ratio
- * between pcm data and GPIO status data changes. Our FIQ handler is not
- * able to handle this, hence this driver only works with 48000Hz sampling
- * rate.
- * Reading and writing AC97 registers is another challenge. The core
- * provides us status bits when the read register is updated with *another*
- * value. When we read the same register two times (and the register still
- * contains the same value) these status bits are not set. We work
- * around this by not polling these bits but only wait a fixed delay.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale SSI ALSA SoC Digital Audio Interface (DAI) driver
+//
+// Author: Timur Tabi <timur@freescale.com>
+//
+// Copyright 2007-2010 Freescale Semiconductor, Inc.
+//
+// Some notes why imx-pcm-fiq is used instead of DMA on some boards:
+//
+// The i.MX SSI core has some nasty limitations in AC97 mode. While most
+// sane processor vendors have a FIFO per AC97 slot, the i.MX has only
+// one FIFO which combines all valid receive slots. We cannot even select
+// which slots we want to receive. The WM9712 with which this driver
+// was developed with always sends GPIO status data in slot 12 which
+// we receive in our (PCM-) data stream. The only chance we have is to
+// manually skip this data in the FIQ handler. With sampling rates different
+// from 48000Hz not every frame has valid receive data, so the ratio
+// between pcm data and GPIO status data changes. Our FIQ handler is not
+// able to handle this, hence this driver only works with 48000Hz sampling
+// rate.
+// Reading and writing AC97 registers is another challenge. The core
+// provides us status bits when the read register is updated with *another*
+// value. When we read the same register two times (and the register still
+// contains the same value) these status bits are not set. We work
+// around this by not polling these bits but only wait a fixed delay.
 
 #include <linux/init.h>
 #include <linux/io.h>
@@ -217,6 +212,7 @@ struct fsl_ssi_soc_data {
  * @dai_fmt: DAI configuration this device is currently used with
  * @streams: Mask of current active streams: BIT(TX) and BIT(RX)
  * @i2s_net: I2S and Network mode configurations of SCR register
+ *           (this is the initial settings based on the DAI format)
  * @synchronous: Use synchronous mode - both of TX and RX use STCK and SFCK
  * @use_dma: DMA is used or FIQ with stream filter
  * @use_dual_fifo: DMA with support for dual FIFO mode
@@ -384,8 +380,7 @@ static irqreturn_t fsl_ssi_isr(int irq, void *dev_id)
 {
 	struct fsl_ssi *ssi = dev_id;
 	struct regmap *regs = ssi->regs;
-	__be32 sisr;
-	__be32 sisr2;
+	u32 sisr, sisr2;
 
 	regmap_read(regs, REG_SSI_SISR, &sisr);
 
@@ -829,16 +824,23 @@ static int fsl_ssi_hw_params(struct snd_pcm_substream *substream,
 	}
 
 	if (!fsl_ssi_is_ac97(ssi)) {
+		/*
+		 * Keep the ssi->i2s_net intact while having a local variable
+		 * to override settings for special use cases. Otherwise, the
+		 * ssi->i2s_net will lose the settings for regular use cases.
+		 */
+		u8 i2s_net = ssi->i2s_net;
+
 		/* Normal + Network mode to send 16-bit data in 32-bit frames */
 		if (fsl_ssi_is_i2s_cbm_cfs(ssi) && sample_size == 16)
-			ssi->i2s_net = SSI_SCR_I2S_MODE_NORMAL | SSI_SCR_NET;
+			i2s_net = SSI_SCR_I2S_MODE_NORMAL | SSI_SCR_NET;
 
 		/* Use Normal mode to send mono data at 1st slot of 2 slots */
 		if (channels == 1)
-			ssi->i2s_net = SSI_SCR_I2S_MODE_NORMAL;
+			i2s_net = SSI_SCR_I2S_MODE_NORMAL;
 
 		regmap_update_bits(regs, REG_SSI_SCR,
-				   SSI_SCR_I2S_NET_MASK, ssi->i2s_net);
+				   SSI_SCR_I2S_NET_MASK, i2s_net);
 	}
 
 	/* In synchronous mode, the SSI uses STCCR for capture */
diff --git a/sound/soc/fsl/fsl_ssi.h b/sound/soc/fsl/fsl_ssi.h
index 18f8dd5209d5..0bdda608d414 100644
--- a/sound/soc/fsl/fsl_ssi.h
+++ b/sound/soc/fsl/fsl_ssi.h
@@ -1,12 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * fsl_ssi.h - ALSA SSI interface for the Freescale MPC8610 and i.MX SoC
  *
  * Author: Timur Tabi <timur@freescale.com>
  *
- * Copyright 2007-2008 Freescale Semiconductor, Inc.  This file is licensed
- * under the terms of the GNU General Public License version 2.  This
- * program is licensed "as is" without any warranty of any kind, whether
- * express or implied.
+ * Copyright 2007-2008 Freescale Semiconductor, Inc.
  */
 
 #ifndef _MPC8610_I2S_H
diff --git a/sound/soc/fsl/fsl_ssi_dbg.c b/sound/soc/fsl/fsl_ssi_dbg.c
index 7aac63e2c561..1255dfe19eef 100644
--- a/sound/soc/fsl/fsl_ssi_dbg.c
+++ b/sound/soc/fsl/fsl_ssi_dbg.c
@@ -1,14 +1,10 @@
-/*
- * Freescale SSI ALSA SoC Digital Audio Interface (DAI) debugging functions
- *
- * Copyright 2014 Markus Pargmann <mpa@pengutronix.de>, Pengutronix
- *
- * Splitted from fsl_ssi.c
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale SSI ALSA SoC Digital Audio Interface (DAI) debugging functions
+//
+// Copyright 2014 Markus Pargmann <mpa@pengutronix.de>, Pengutronix
+//
+// Split from fsl_ssi.c
 
 #include <linux/debugfs.h>
 #include <linux/device.h>
@@ -146,7 +142,7 @@ int fsl_ssi_debugfs_create(struct fsl_ssi_dbg *ssi_dbg, struct device *dev)
 	if (!ssi_dbg->dbg_dir)
 		return -ENOMEM;
 
-	ssi_dbg->dbg_stats = debugfs_create_file("stats", S_IRUGO,
+	ssi_dbg->dbg_stats = debugfs_create_file("stats", 0444,
 						 ssi_dbg->dbg_dir, ssi_dbg,
 						 &fsl_ssi_stats_ops);
 	if (!ssi_dbg->dbg_stats) {
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 6959a74a6f49..4a516c428b3d 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -135,6 +135,18 @@ static void asoc_simple_card_shutdown(struct snd_pcm_substream *substream)
 	asoc_simple_card_clk_disable(&dai_props->codec_dai);
 }
 
+static int asoc_simple_set_clk_rate(struct asoc_simple_dai *simple_dai,
+				    unsigned long rate)
+{
+	if (!simple_dai->clk)
+		return 0;
+
+	if (clk_get_rate(simple_dai->clk) == rate)
+		return 0;
+
+	return clk_set_rate(simple_dai->clk, rate);
+}
+
 static int asoc_simple_card_hw_params(struct snd_pcm_substream *substream,
 				      struct snd_pcm_hw_params *params)
 {
@@ -154,6 +166,15 @@ static int asoc_simple_card_hw_params(struct snd_pcm_substream *substream,
 
 	if (mclk_fs) {
 		mclk = params_rate(params) * mclk_fs;
+
+		ret = asoc_simple_set_clk_rate(&dai_props->codec_dai, mclk);
+		if (ret < 0)
+			return ret;
+
+		ret = asoc_simple_set_clk_rate(&dai_props->cpu_dai, mclk);
+		if (ret < 0)
+			return ret;
+
 		ret = snd_soc_dai_set_sysclk(codec_dai, 0, mclk,
 					     SND_SOC_CLOCK_IN);
 		if (ret && ret != -ENOTSUPP)
diff --git a/sound/soc/hisilicon/hi6210-i2s.c b/sound/soc/hisilicon/hi6210-i2s.c
index 07a57209e055..53344a3b7a60 100644
--- a/sound/soc/hisilicon/hi6210-i2s.c
+++ b/sound/soc/hisilicon/hi6210-i2s.c
@@ -498,7 +498,7 @@ static int hi6210_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
 			hi6210_i2s_txctrl(cpu_dai, 0);
 		break;
 	default:
-		dev_err(cpu_dai->dev, "uknown cmd\n");
+		dev_err(cpu_dai->dev, "unknown cmd\n");
 		return -EINVAL;
 	}
 	return 0;
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index ceb105cbd461..0caa1f4eb94d 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -61,7 +61,7 @@ config SND_SOC_INTEL_HASWELL
 
 config SND_SOC_INTEL_BAYTRAIL
 	tristate "Baytrail (legacy) Platforms"
-	depends on DMADEVICES && ACPI
+	depends on DMADEVICES && ACPI && SND_SST_ATOM_HIFI2_PLATFORM=n
 	select SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_SST_ACPI
 	select SND_SOC_INTEL_SST_FIRMWARE
@@ -72,24 +72,28 @@ config SND_SOC_INTEL_BAYTRAIL
 	  for Baytrail Chromebooks but this option is now deprecated and is
 	  not recommended, use SND_SST_ATOM_HIFI2_PLATFORM instead.
 
+config SND_SST_ATOM_HIFI2_PLATFORM
+	tristate
+	select SND_SOC_COMPRESS
+
 config SND_SST_ATOM_HIFI2_PLATFORM_PCI
-	tristate "PCI HiFi2 (Medfield, Merrifield) Platforms"
+	tristate "PCI HiFi2 (Merrifield) Platforms"
 	depends on X86 && PCI
 	select SND_SST_IPC_PCI
-	select SND_SOC_COMPRESS
+	select SND_SST_ATOM_HIFI2_PLATFORM
 	help
-	  If you have a Intel Medfield or Merrifield/Edison platform, then
+	  If you have a Intel Merrifield/Edison platform, then
 	  enable this option by saying Y or m. Distros will typically not
-	  enable this option: Medfield devices are not available to
-	  developers and while Merrifield/Edison can run a mainline kernel with
-	  limited functionality it will require a firmware file which
-	  is not in the standard firmware tree
+	  enable this option: while Merrifield/Edison can run a mainline
+	  kernel with limited functionality it will require a firmware file
+	  which is not in the standard firmware tree
 
-config SND_SST_ATOM_HIFI2_PLATFORM
+config SND_SST_ATOM_HIFI2_PLATFORM_ACPI
 	tristate "ACPI HiFi2 (Baytrail, Cherrytrail) Platforms"
+	default ACPI
 	depends on X86 && ACPI
 	select SND_SST_IPC_ACPI
-	select SND_SOC_COMPRESS
+	select SND_SST_ATOM_HIFI2_PLATFORM
 	select SND_SOC_ACPI_INTEL_MATCH
 	select IOSF_MBI
 	help
diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index 668c0934e942..40eb979d5ac1 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -571,7 +571,7 @@ static int broxton_audio_probe(struct platform_device *pdev)
 {
 	struct bxt_card_private *ctx;
 
-	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index c7e9024e65ef..b68c289558a8 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -593,7 +593,7 @@ static int broxton_audio_probe(struct platform_device *pdev)
 		}
 	}
 
-	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/byt-max98090.c b/sound/soc/intel/boards/byt-max98090.c
index 0f8b8209c020..f1283634b22b 100644
--- a/sound/soc/intel/boards/byt-max98090.c
+++ b/sound/soc/intel/boards/byt-max98090.c
@@ -151,7 +151,7 @@ static int byt_max98090_probe(struct platform_device *pdev)
 	struct byt_max98090_private *priv;
 	int ret_val;
 
-	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_ATOMIC);
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		dev_err(&pdev->dev, "allocation failed\n");
 		return -ENOMEM;
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index 305e7f4fe55a..adc26dfc7d65 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -243,7 +243,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 	int i;
 	int ret = 0;
 
-	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_ATOMIC);
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index a8d8bff788e7..33065ba294a9 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -17,6 +17,7 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -25,6 +26,7 @@
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
+#include <linux/input.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
 #include <asm/platform_sst_audio.h>
@@ -33,6 +35,7 @@
 #include <sound/soc.h>
 #include <sound/jack.h>
 #include <sound/soc-acpi.h>
+#include <dt-bindings/sound/rt5640.h>
 #include "../../codecs/rt5640.h"
 #include "../atom/sst-atom-controls.h"
 #include "../common/sst-dsp.h"
@@ -44,17 +47,53 @@ enum {
 	BYT_RT5640_IN3_MAP,
 };
 
-#define BYT_RT5640_MAP(quirk)	((quirk) &  GENMASK(7, 0))
-#define BYT_RT5640_DMIC_EN	BIT(16)
-#define BYT_RT5640_MONO_SPEAKER BIT(17)
-#define BYT_RT5640_DIFF_MIC     BIT(18) /* defaut is single-ended */
-#define BYT_RT5640_SSP2_AIF2    BIT(19) /* default is using AIF1  */
-#define BYT_RT5640_SSP0_AIF1    BIT(20)
-#define BYT_RT5640_SSP0_AIF2    BIT(21)
-#define BYT_RT5640_MCLK_EN	BIT(22)
-#define BYT_RT5640_MCLK_25MHZ	BIT(23)
+enum {
+	BYT_RT5640_JD_SRC_GPIO1		= (RT5640_JD_SRC_GPIO1 << 4),
+	BYT_RT5640_JD_SRC_JD1_IN4P	= (RT5640_JD_SRC_JD1_IN4P << 4),
+	BYT_RT5640_JD_SRC_JD2_IN4N	= (RT5640_JD_SRC_JD2_IN4N << 4),
+	BYT_RT5640_JD_SRC_GPIO2		= (RT5640_JD_SRC_GPIO2 << 4),
+	BYT_RT5640_JD_SRC_GPIO3		= (RT5640_JD_SRC_GPIO3 << 4),
+	BYT_RT5640_JD_SRC_GPIO4		= (RT5640_JD_SRC_GPIO4 << 4),
+};
+
+enum {
+	BYT_RT5640_OVCD_TH_600UA	= (6 << 8),
+	BYT_RT5640_OVCD_TH_1500UA	= (15 << 8),
+	BYT_RT5640_OVCD_TH_2000UA	= (20 << 8),
+};
+
+enum {
+	BYT_RT5640_OVCD_SF_0P5		= (RT5640_OVCD_SF_0P5 << 13),
+	BYT_RT5640_OVCD_SF_0P75		= (RT5640_OVCD_SF_0P75 << 13),
+	BYT_RT5640_OVCD_SF_1P0		= (RT5640_OVCD_SF_1P0 << 13),
+	BYT_RT5640_OVCD_SF_1P5		= (RT5640_OVCD_SF_1P5 << 13),
+};
+
+#define BYT_RT5640_MAP(quirk)		((quirk) &  GENMASK(3, 0))
+#define BYT_RT5640_JDSRC(quirk)		(((quirk) & GENMASK(7, 4)) >> 4)
+#define BYT_RT5640_OVCD_TH(quirk)	(((quirk) & GENMASK(12, 8)) >> 8)
+#define BYT_RT5640_OVCD_SF(quirk)	(((quirk) & GENMASK(14, 13)) >> 13)
+#define BYT_RT5640_JD_NOT_INV		BIT(16)
+#define BYT_RT5640_MONO_SPEAKER		BIT(17)
+#define BYT_RT5640_DIFF_MIC		BIT(18) /* default is single-ended */
+#define BYT_RT5640_SSP2_AIF2		BIT(19) /* default is using AIF1  */
+#define BYT_RT5640_SSP0_AIF1		BIT(20)
+#define BYT_RT5640_SSP0_AIF2		BIT(21)
+#define BYT_RT5640_MCLK_EN		BIT(22)
+#define BYT_RT5640_MCLK_25MHZ		BIT(23)
+
+#define BYTCR_INPUT_DEFAULTS				\
+	(BYT_RT5640_IN3_MAP |				\
+	 BYT_RT5640_JD_SRC_JD1_IN4P |			\
+	 BYT_RT5640_OVCD_TH_2000UA |			\
+	 BYT_RT5640_OVCD_SF_0P75 |			\
+	 BYT_RT5640_DIFF_MIC)
+
+/* in-diff or dmic-pin + jdsrc + ovcd-th + -sf + jd-inv + terminating entry */
+#define MAX_NO_PROPS 6
 
 struct byt_rt5640_private {
+	struct snd_soc_jack jack;
 	struct clk *mclk;
 };
 static bool is_bytcr;
@@ -67,7 +106,6 @@ MODULE_PARM_DESC(quirk, "Board-specific quirk override");
 static void log_quirks(struct device *dev)
 {
 	int map;
-	bool has_dmic = false;
 	bool has_mclk = false;
 	bool has_ssp0 = false;
 	bool has_ssp0_aif1 = false;
@@ -78,11 +116,9 @@ static void log_quirks(struct device *dev)
 	switch (map) {
 	case BYT_RT5640_DMIC1_MAP:
 		dev_info(dev, "quirk DMIC1_MAP enabled\n");
-		has_dmic = true;
 		break;
 	case BYT_RT5640_DMIC2_MAP:
 		dev_info(dev, "quirk DMIC2_MAP enabled\n");
-		has_dmic = true;
 		break;
 	case BYT_RT5640_IN1_MAP:
 		dev_info(dev, "quirk IN1_MAP enabled\n");
@@ -94,20 +130,20 @@ static void log_quirks(struct device *dev)
 		dev_err(dev, "quirk map 0x%x is not supported, microphone input will not work\n", map);
 		break;
 	}
-	if (byt_rt5640_quirk & BYT_RT5640_DMIC_EN) {
-		if (has_dmic)
-			dev_info(dev, "quirk DMIC enabled\n");
-		else
-			dev_err(dev, "quirk DMIC enabled but no DMIC input set, will be ignored\n");
+	if (BYT_RT5640_JDSRC(byt_rt5640_quirk)) {
+		dev_info(dev, "quirk realtek,jack-detect-source %ld\n",
+			 BYT_RT5640_JDSRC(byt_rt5640_quirk));
+		dev_info(dev, "quirk realtek,over-current-threshold-microamp %ld\n",
+			 BYT_RT5640_OVCD_TH(byt_rt5640_quirk) * 100);
+		dev_info(dev, "quirk realtek,over-current-scale-factor %ld\n",
+			 BYT_RT5640_OVCD_SF(byt_rt5640_quirk));
 	}
+	if (byt_rt5640_quirk & BYT_RT5640_JD_NOT_INV)
+		dev_info(dev, "quirk JD_NOT_INV enabled\n");
 	if (byt_rt5640_quirk & BYT_RT5640_MONO_SPEAKER)
 		dev_info(dev, "quirk MONO_SPEAKER enabled\n");
-	if (byt_rt5640_quirk & BYT_RT5640_DIFF_MIC) {
-		if (!has_dmic)
-			dev_info(dev, "quirk DIFF_MIC enabled\n");
-		else
-			dev_info(dev, "quirk DIFF_MIC enabled but DMIC input selected, will be ignored\n");
-	}
+	if (byt_rt5640_quirk & BYT_RT5640_DIFF_MIC)
+		dev_info(dev, "quirk DIFF_MIC enabled\n");
 	if (byt_rt5640_quirk & BYT_RT5640_SSP0_AIF1) {
 		dev_info(dev, "quirk SSP0_AIF1 enabled\n");
 		has_ssp0 = true;
@@ -141,6 +177,52 @@ static void log_quirks(struct device *dev)
 	}
 }
 
+static int byt_rt5640_prepare_and_enable_pll1(struct snd_soc_dai *codec_dai,
+					      int rate)
+{
+	int ret;
+
+	/* Configure the PLL before selecting it */
+	if (!(byt_rt5640_quirk & BYT_RT5640_MCLK_EN)) {
+		/* use bitclock as PLL input */
+		if ((byt_rt5640_quirk & BYT_RT5640_SSP0_AIF1) ||
+		    (byt_rt5640_quirk & BYT_RT5640_SSP0_AIF2)) {
+			/* 2x16 bit slots on SSP0 */
+			ret = snd_soc_dai_set_pll(codec_dai, 0,
+						  RT5640_PLL1_S_BCLK1,
+						  rate * 32, rate * 512);
+		} else {
+			/* 2x15 bit slots on SSP2 */
+			ret = snd_soc_dai_set_pll(codec_dai, 0,
+						  RT5640_PLL1_S_BCLK1,
+						  rate * 50, rate * 512);
+		}
+	} else {
+		if (byt_rt5640_quirk & BYT_RT5640_MCLK_25MHZ) {
+			ret = snd_soc_dai_set_pll(codec_dai, 0,
+						  RT5640_PLL1_S_MCLK,
+						  25000000, rate * 512);
+		} else {
+			ret = snd_soc_dai_set_pll(codec_dai, 0,
+						  RT5640_PLL1_S_MCLK,
+						  19200000, rate * 512);
+		}
+	}
+
+	if (ret < 0) {
+		dev_err(codec_dai->component->dev, "can't set pll: %d\n", ret);
+		return ret;
+	}
+
+	ret = snd_soc_dai_set_sysclk(codec_dai, RT5640_SCLK_S_PLL1,
+				     rate * 512, SND_SOC_CLOCK_IN);
+	if (ret < 0) {
+		dev_err(codec_dai->component->dev, "can't set clock %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
 
 #define BYT_CODEC_DAI1	"rt5640-aif1"
 #define BYT_CODEC_DAI2	"rt5640-aif2"
@@ -173,9 +255,7 @@ static int platform_clock_control(struct snd_soc_dapm_widget *w,
 				return ret;
 			}
 		}
-		ret = snd_soc_dai_set_sysclk(codec_dai, RT5640_SCLK_S_PLL1,
-					     48000 * 512,
-					     SND_SOC_CLOCK_IN);
+		ret = byt_rt5640_prepare_and_enable_pll1(codec_dai, 48000);
 	} else {
 		/*
 		 * Set codec clock source to internal clock before
@@ -295,79 +375,72 @@ static const struct snd_kcontrol_new byt_rt5640_controls[] = {
 	SOC_DAPM_PIN_SWITCH("Speaker"),
 };
 
+static struct snd_soc_jack_pin rt5640_pins[] = {
+	{
+		.pin	= "Headphone",
+		.mask	= SND_JACK_HEADPHONE,
+	},
+	{
+		.pin	= "Headset Mic",
+		.mask	= SND_JACK_MICROPHONE,
+	},
+};
+
 static int byt_rt5640_aif1_hw_params(struct snd_pcm_substream *substream,
 					struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_dai *codec_dai = rtd->codec_dai;
-	int ret;
+	struct snd_soc_dai *dai = rtd->codec_dai;
 
-	ret = snd_soc_dai_set_sysclk(codec_dai, RT5640_SCLK_S_PLL1,
-				     params_rate(params) * 512,
-				     SND_SOC_CLOCK_IN);
-
-	if (ret < 0) {
-		dev_err(rtd->dev, "can't set codec clock %d\n", ret);
-		return ret;
-	}
-
-	if (!(byt_rt5640_quirk & BYT_RT5640_MCLK_EN)) {
-		/* use bitclock as PLL input */
-		if ((byt_rt5640_quirk & BYT_RT5640_SSP0_AIF1) ||
-			(byt_rt5640_quirk & BYT_RT5640_SSP0_AIF2)) {
-
-			/* 2x16 bit slots on SSP0 */
-			ret = snd_soc_dai_set_pll(codec_dai, 0,
-						RT5640_PLL1_S_BCLK1,
-						params_rate(params) * 32,
-						params_rate(params) * 512);
-		} else {
-			/* 2x15 bit slots on SSP2 */
-			ret = snd_soc_dai_set_pll(codec_dai, 0,
-						RT5640_PLL1_S_BCLK1,
-						params_rate(params) * 50,
-						params_rate(params) * 512);
-		}
-	} else {
-		if (byt_rt5640_quirk & BYT_RT5640_MCLK_25MHZ) {
-			ret = snd_soc_dai_set_pll(codec_dai, 0,
-						RT5640_PLL1_S_MCLK,
-						25000000,
-						params_rate(params) * 512);
-		} else {
-			ret = snd_soc_dai_set_pll(codec_dai, 0,
-						RT5640_PLL1_S_MCLK,
-						19200000,
-						params_rate(params) * 512);
-		}
-	}
-
-	if (ret < 0) {
-		dev_err(rtd->dev, "can't set codec pll: %d\n", ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int byt_rt5640_quirk_cb(const struct dmi_system_id *id)
-{
-	byt_rt5640_quirk = (unsigned long)id->driver_data;
-	return 1;
+	return byt_rt5640_prepare_and_enable_pll1(dai, params_rate(params));
 }
 
+/* Please keep this list alphabetically sorted */
 static const struct dmi_system_id byt_rt5640_quirk_table[] = {
+	{	/* Acer Iconia Tab 8 W1-810 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Iconia W1-810"),
+		},
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD1_IN4P |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"),
+		},
+		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+						 BYT_RT5640_MCLK_EN |
+						 BYT_RT5640_SSP0_AIF1),
+
+	},
+	{
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ARCHOS"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ARCHOS 80 Cesium"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
-		.callback = byt_rt5640_quirk_cb,
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"),
 		},
 		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
 					BYT_RT5640_MCLK_EN),
 	},
 	{
-		.callback = byt_rt5640_quirk_cb,
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"),
@@ -378,18 +451,38 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF2 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* Chuwi Vi8 (CWI506) */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Insyde"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "i86"),
+			/* The above are too generic, also match BIOS info */
+			DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.D86JLBNR"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
-		.callback = byt_rt5640_quirk_cb,
 		.matches = {
-			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "DellInc."),
+			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Max B3 PLATFORM"),
+		},
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP),
+	},
+	{
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Venue 8 Pro 5830"),
 		},
-		.driver_data = (void *)(BYT_RT5640_DMIC2_MAP |
-					BYT_RT5640_DMIC_EN |
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_MONO_SPEAKER |
 					BYT_RT5640_MCLK_EN),
 	},
 	{
-		.callback = byt_rt5640_quirk_cb,
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HP ElitePad 1000 G2"),
@@ -397,17 +490,112 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
 					BYT_RT5640_MCLK_EN),
 	},
-	{
-		.callback = byt_rt5640_quirk_cb,
+	{	/* HP Pavilion x2 10-n000nd */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Max B3 PLATFORM"),
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HP Pavilion x2 Detachable"),
 		},
 		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
-					BYT_RT5640_DMIC_EN),
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_1500UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* HP Stream 7 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HP Stream 7 Tablet"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_JD_NOT_INV |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* I.T.Works TW891 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "TW891"),
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "To be filled by O.E.M."),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "TW891"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* Lamina I8270 / T701BR.SE */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Lamina"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "T701BR.SE"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_JD_NOT_INV |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* MSI S100 tablet */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "S100"),
+		},
+		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_DIFF_MIC |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* Pipo W4 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+			/* The above are too generic, also match BIOS info */
+			DMI_MATCH(DMI_BIOS_VERSION, "V8L_WIN32_CHIPHD"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* Point of View Mobii TAB-P800W (V2.0) */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+			/* The above are too generic, also match BIOS info */
+			DMI_EXACT_MATCH(DMI_BIOS_VERSION, "3BAIR1014"),
+			DMI_EXACT_MATCH(DMI_BIOS_DATE, "10/24/2014"),
+		},
+		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_DIFF_MIC |
+					BYT_RT5640_SSP0_AIF2 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* Point of View Mobii TAB-P800W (V2.1) */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+			/* The above are too generic, also match BIOS info */
+			DMI_EXACT_MATCH(DMI_BIOS_VERSION, "3BAIR1013"),
+			DMI_EXACT_MATCH(DMI_BIOS_DATE, "08/22/2014"),
+		},
+		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_DIFF_MIC |
+					BYT_RT5640_SSP0_AIF2 |
+					BYT_RT5640_MCLK_EN),
 	},
 	{
-		.callback = byt_rt5640_quirk_cb,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"),
 			DMI_MATCH(DMI_BOARD_NAME, "tPAD"),
@@ -416,23 +604,23 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_MCLK_EN |
 					BYT_RT5640_SSP0_AIF1),
 	},
-	{
-		.callback = byt_rt5640_quirk_cb,
+	{	/* Toshiba Satellite Click Mini L9W-B */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"),
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SATELLITE Click Mini L9W-B"),
 		},
-		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
-						 BYT_RT5640_MCLK_EN |
-						 BYT_RT5640_SSP0_AIF1),
-
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_1500UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
 	},
-	{
-		.callback = byt_rt5640_quirk_cb,
+	{	/* Catch-all for generic Insyde tablets, must be last */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
 		},
-		.driver_data = (void *)(BYT_RT5640_IN3_MAP |
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
 					BYT_RT5640_MCLK_EN |
 					BYT_RT5640_SSP0_AIF1),
 
@@ -440,6 +628,64 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 	{}
 };
 
+/*
+ * Note this MUST be called before snd_soc_register_card(), so that the props
+ * are in place before the codec component driver's probe function parses them.
+ */
+static int byt_rt5640_add_codec_device_props(const char *i2c_dev_name)
+{
+	struct property_entry props[MAX_NO_PROPS] = {};
+	struct device *i2c_dev;
+	int ret, cnt = 0;
+
+	i2c_dev = bus_find_device_by_name(&i2c_bus_type, NULL, i2c_dev_name);
+	if (!i2c_dev)
+		return -EPROBE_DEFER;
+
+	switch (BYT_RT5640_MAP(byt_rt5640_quirk)) {
+	case BYT_RT5640_DMIC1_MAP:
+		props[cnt++] = PROPERTY_ENTRY_U32("realtek,dmic1-data-pin",
+						  RT5640_DMIC1_DATA_PIN_IN1P);
+		break;
+	case BYT_RT5640_DMIC2_MAP:
+		props[cnt++] = PROPERTY_ENTRY_U32("realtek,dmic2-data-pin",
+						  RT5640_DMIC2_DATA_PIN_IN1N);
+		break;
+	case BYT_RT5640_IN1_MAP:
+		if (byt_rt5640_quirk & BYT_RT5640_DIFF_MIC)
+			props[cnt++] =
+				PROPERTY_ENTRY_BOOL("realtek,in1-differential");
+		break;
+	case BYT_RT5640_IN3_MAP:
+		if (byt_rt5640_quirk & BYT_RT5640_DIFF_MIC)
+			props[cnt++] =
+				PROPERTY_ENTRY_BOOL("realtek,in3-differential");
+		break;
+	}
+
+	if (BYT_RT5640_JDSRC(byt_rt5640_quirk)) {
+		props[cnt++] = PROPERTY_ENTRY_U32(
+				    "realtek,jack-detect-source",
+				    BYT_RT5640_JDSRC(byt_rt5640_quirk));
+
+		props[cnt++] = PROPERTY_ENTRY_U32(
+				    "realtek,over-current-threshold-microamp",
+				    BYT_RT5640_OVCD_TH(byt_rt5640_quirk) * 100);
+
+		props[cnt++] = PROPERTY_ENTRY_U32(
+				    "realtek,over-current-scale-factor",
+				    BYT_RT5640_OVCD_SF(byt_rt5640_quirk));
+	}
+
+	if (byt_rt5640_quirk & BYT_RT5640_JD_NOT_INV)
+		props[cnt++] = PROPERTY_ENTRY_BOOL("realtek,jack-detect-not-inverted");
+
+	ret = device_add_properties(i2c_dev, props);
+	put_device(i2c_dev);
+
+	return ret;
+}
+
 static int byt_rt5640_init(struct snd_soc_pcm_runtime *runtime)
 {
 	struct snd_soc_card *card = runtime->card;
@@ -451,6 +697,11 @@ static int byt_rt5640_init(struct snd_soc_pcm_runtime *runtime)
 
 	card->dapm.idle_bias_off = true;
 
+	/* Start with RC clk for jack-detect (we disable MCLK below) */
+	if (byt_rt5640_quirk & BYT_RT5640_MCLK_EN)
+		snd_soc_component_update_bits(component, RT5640_GLB_CLK,
+			RT5640_SCLK_SRC_MASK, RT5640_SCLK_SRC_RCCLK);
+
 	rt5640_sel_asrc_clk_src(component,
 				RT5640_DA_STEREO_FILTER |
 				RT5640_DA_MONO_L_FILTER	|
@@ -521,17 +772,6 @@ static int byt_rt5640_init(struct snd_soc_pcm_runtime *runtime)
 	if (ret)
 		return ret;
 
-	if (byt_rt5640_quirk & BYT_RT5640_DIFF_MIC) {
-		snd_soc_component_update_bits(component,  RT5640_IN1_IN2, RT5640_IN_DF1,
-				    RT5640_IN_DF1);
-	}
-
-	if (byt_rt5640_quirk & BYT_RT5640_DMIC_EN) {
-		ret = rt5640_dmic_enable(component, 0, 0);
-		if (ret)
-			return ret;
-	}
-
 	snd_soc_dapm_ignore_suspend(&card->dapm, "Headphone");
 	snd_soc_dapm_ignore_suspend(&card->dapm, "Speaker");
 
@@ -555,11 +795,27 @@ static int byt_rt5640_init(struct snd_soc_pcm_runtime *runtime)
 		else
 			ret = clk_set_rate(priv->mclk, 19200000);
 
-		if (ret)
+		if (ret) {
 			dev_err(card->dev, "unable to set MCLK rate\n");
+			return ret;
+		}
 	}
 
-	return ret;
+	if (BYT_RT5640_JDSRC(byt_rt5640_quirk)) {
+		ret = snd_soc_card_jack_new(card, "Headset",
+					    SND_JACK_HEADSET | SND_JACK_BTN_0,
+					    &priv->jack, rt5640_pins,
+					    ARRAY_SIZE(rt5640_pins));
+		if (ret) {
+			dev_err(card->dev, "Jack creation failed %d\n", ret);
+			return ret;
+		}
+		snd_jack_set_key(priv->jack.jack, SND_JACK_BTN_0,
+				 KEY_PLAYPAUSE);
+		snd_soc_component_set_jack(component, &priv->jack, NULL);
+	}
+
+	return 0;
 }
 
 static const struct snd_soc_pcm_stream byt_rt5640_dai_params = {
@@ -701,6 +957,48 @@ static struct snd_soc_dai_link byt_rt5640_dais[] = {
 };
 
 /* SoC card */
+static char byt_rt5640_codec_name[SND_ACPI_I2C_ID_LEN];
+static char byt_rt5640_codec_aif_name[12]; /*  = "rt5640-aif[1|2]" */
+static char byt_rt5640_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
+static char byt_rt5640_long_name[40]; /* = "bytcr-rt5640-*-spk-*-mic" */
+
+static int byt_rt5640_suspend(struct snd_soc_card *card)
+{
+	struct snd_soc_component *component;
+
+	if (!BYT_RT5640_JDSRC(byt_rt5640_quirk))
+		return 0;
+
+	list_for_each_entry(component, &card->component_dev_list, card_list) {
+		if (!strcmp(component->name, byt_rt5640_codec_name)) {
+			dev_dbg(component->dev, "disabling jack detect before suspend\n");
+			snd_soc_component_set_jack(component, NULL, NULL);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int byt_rt5640_resume(struct snd_soc_card *card)
+{
+	struct byt_rt5640_private *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_component *component;
+
+	if (!BYT_RT5640_JDSRC(byt_rt5640_quirk))
+		return 0;
+
+	list_for_each_entry(component, &card->component_dev_list, card_list) {
+		if (!strcmp(component->name, byt_rt5640_codec_name)) {
+			dev_dbg(component->dev, "re-enabling jack detect after resume\n");
+			snd_soc_component_set_jack(component, &priv->jack, NULL);
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static struct snd_soc_card byt_rt5640_card = {
 	.name = "bytcr-rt5640",
 	.owner = THIS_MODULE,
@@ -711,12 +1009,10 @@ static struct snd_soc_card byt_rt5640_card = {
 	.dapm_routes = byt_rt5640_audio_map,
 	.num_dapm_routes = ARRAY_SIZE(byt_rt5640_audio_map),
 	.fully_routed = true,
+	.suspend_pre = byt_rt5640_suspend,
+	.resume_post = byt_rt5640_resume,
 };
 
-static char byt_rt5640_codec_name[SND_ACPI_I2C_ID_LEN];
-static char byt_rt5640_codec_aif_name[12]; /*  = "rt5640-aif[1|2]" */
-static char byt_rt5640_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
-
 static bool is_valleyview(void)
 {
 	static const struct x86_cpu_id cpu_ids[] = {
@@ -736,6 +1032,8 @@ struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 
 static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 {
+	const char * const map_name[] = { "dmic1", "dmic2", "in1", "in3" };
+	const struct dmi_system_id *dmi_id;
 	struct byt_rt5640_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *i2c_name = NULL;
@@ -744,7 +1042,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	int i;
 
 	is_bytcr = false;
-	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_ATOMIC);
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
@@ -829,20 +1127,29 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 		}
 
 		/* change defaults for Baytrail-CR capture */
-		byt_rt5640_quirk |= BYT_RT5640_IN1_MAP;
-		byt_rt5640_quirk |= BYT_RT5640_DIFF_MIC;
+		byt_rt5640_quirk |= BYTCR_INPUT_DEFAULTS;
 	} else {
-		byt_rt5640_quirk |= (BYT_RT5640_DMIC1_MAP |
-				BYT_RT5640_DMIC_EN);
+		byt_rt5640_quirk |= BYT_RT5640_DMIC1_MAP |
+				    BYT_RT5640_JD_SRC_JD2_IN4N |
+				    BYT_RT5640_OVCD_TH_2000UA |
+				    BYT_RT5640_OVCD_SF_0P75;
 	}
 
 	/* check quirks before creating card */
-	dmi_check_system(byt_rt5640_quirk_table);
+	dmi_id = dmi_first_match(byt_rt5640_quirk_table);
+	if (dmi_id)
+		byt_rt5640_quirk = (unsigned long)dmi_id->driver_data;
 	if (quirk_override) {
 		dev_info(&pdev->dev, "Overriding quirk 0x%x => 0x%x\n",
 			 (unsigned int)byt_rt5640_quirk, quirk_override);
 		byt_rt5640_quirk = quirk_override;
 	}
+
+	/* Must be called before register_card, also see declaration comment. */
+	ret_val = byt_rt5640_add_codec_device_props(byt_rt5640_codec_name);
+	if (ret_val)
+		return ret_val;
+
 	log_quirks(&pdev->dev);
 
 	if ((byt_rt5640_quirk & BYT_RT5640_SSP2_AIF2) ||
@@ -889,6 +1196,13 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 		}
 	}
 
+	snprintf(byt_rt5640_long_name, sizeof(byt_rt5640_long_name),
+		 "bytcr-rt5640-%s-spk-%s-mic",
+		 (byt_rt5640_quirk & BYT_RT5640_MONO_SPEAKER) ?
+			"mono" : "stereo",
+		 map_name[BYT_RT5640_MAP(byt_rt5640_quirk)]);
+	byt_rt5640_card.long_name = byt_rt5640_long_name;
+
 	ret_val = devm_snd_soc_register_card(&pdev->dev, &byt_rt5640_card);
 
 	if (ret_val) {
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 1b1997f1d60c..987720e203f9 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -706,6 +706,7 @@ static struct snd_soc_card byt_rt5651_card = {
 static char byt_rt5651_codec_name[SND_ACPI_I2C_ID_LEN];
 static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
 static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
+static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-spk-*-mic" */
 
 static bool is_valleyview(void)
 {
@@ -726,6 +727,10 @@ struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 
 static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 {
+	const char * const intmic_name[] =
+		{ "dmic", "in1", "in2", "in12", "in1", "in2" };
+	const char * const hsmic_name[] =
+		{  "in2", "in2", "in1",  "in3", "in3", "in3" };
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *i2c_name = NULL;
@@ -734,7 +739,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	int dai_index = 0;
 	int i;
 
-	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_ATOMIC);
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
@@ -856,9 +861,10 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	if (byt_rt5651_quirk & BYT_RT5651_MCLK_EN) {
 		priv->mclk = devm_clk_get(&pdev->dev, "pmc_plt_clk_3");
 		if (IS_ERR(priv->mclk)) {
+			ret_val = PTR_ERR(priv->mclk);
 			dev_err(&pdev->dev,
-				"Failed to get MCLK from pmc_plt_clk_3: %ld\n",
-				PTR_ERR(priv->mclk));
+				"Failed to get MCLK from pmc_plt_clk_3: %d\n",
+				ret_val);
 			/*
 			 * Fall back to bit clock usage for -ENOENT (clock not
 			 * available likely due to missing dependencies), bail
@@ -870,6 +876,12 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 		}
 	}
 
+	snprintf(byt_rt5651_long_name, sizeof(byt_rt5651_long_name),
+		 "bytcr-rt5651-%s-intmic-%s-hsmic",
+		 intmic_name[BYT_RT5651_MAP(byt_rt5651_quirk)],
+		 hsmic_name[BYT_RT5651_MAP(byt_rt5651_quirk)]);
+	byt_rt5651_card.long_name = byt_rt5651_long_name;
+
 	ret_val = devm_snd_soc_register_card(&pdev->dev, &byt_rt5651_card);
 
 	if (ret_val) {
diff --git a/sound/soc/intel/boards/cht_bsw_max98090_ti.c b/sound/soc/intel/boards/cht_bsw_max98090_ti.c
index d3e1c7e12004..db6976f4ddaa 100644
--- a/sound/soc/intel/boards/cht_bsw_max98090_ti.c
+++ b/sound/soc/intel/boards/cht_bsw_max98090_ti.c
@@ -391,7 +391,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	int ret_val = 0;
 	struct cht_mc_private *drv;
 
-	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_ATOMIC);
+	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
 	if (!drv)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/cht_bsw_nau8824.c b/sound/soc/intel/boards/cht_bsw_nau8824.c
index 680f2b3a24f9..30c46977d53c 100644
--- a/sound/soc/intel/boards/cht_bsw_nau8824.c
+++ b/sound/soc/intel/boards/cht_bsw_nau8824.c
@@ -120,7 +120,7 @@ static int cht_codec_init(struct snd_soc_pcm_runtime *runtime)
 	 * KEY_VOLUMEUP
 	 * KEY_VOLUMEDOWN
 	 */
-	jack_type = SND_JACK_HEADPHONE | SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+	jack_type = SND_JACK_HEADSET | SND_JACK_BTN_0 | SND_JACK_BTN_1 |
 		SND_JACK_BTN_2 | SND_JACK_BTN_3;
 	ret = snd_soc_card_jack_new(runtime->card, "Headset", jack_type, jack,
 		cht_bsw_jack_pins, ARRAY_SIZE(cht_bsw_jack_pins));
@@ -248,7 +248,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	struct cht_mc_private *drv;
 	int ret_val;
 
-	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_ATOMIC);
+	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
 	if (!drv)
 		return -ENOMEM;
 	snd_soc_card_set_drvdata(&snd_soc_card_cht, drv);
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index 49ba1a956a06..f5a5ea6a093c 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -539,7 +539,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	int ret_val = 0;
 	int i;
 
-	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_ATOMIC);
+	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
 	if (!drv)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c
index e68ec32720a4..e5aa13058dd7 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5672.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5672.c
@@ -189,13 +189,6 @@ static int cht_codec_init(struct snd_soc_pcm_runtime *runtime)
 	if (devm_acpi_dev_add_driver_gpios(component->dev, cht_rt5672_gpios))
 		dev_warn(runtime->dev, "Unable to add GPIO mapping table\n");
 
-	/* TDM 4 slots 24 bit, set Rx & Tx bitmask to 4 active slots */
-	ret = snd_soc_dai_set_tdm_slot(codec_dai, 0xF, 0xF, 4, 24);
-	if (ret < 0) {
-		dev_err(runtime->dev, "can't set codec TDM slot %d\n", ret);
-		return ret;
-	}
-
 	/* Select codec ASRC clock source to track I2S1 clock, because codec
 	 * is in slave mode and 100fs I2S format (BCLK = 100 * LRCLK) cannot
 	 * be supported by RT5672. Otherwise, ASRC will be disabled and cause
@@ -252,6 +245,7 @@ static int cht_codec_fixup(struct snd_soc_pcm_runtime *rtd,
 			SNDRV_PCM_HW_PARAM_RATE);
 	struct snd_interval *channels = hw_param_interval(params,
 						SNDRV_PCM_HW_PARAM_CHANNELS);
+	int ret;
 
 	/* The DSP will covert the FE rate to 48k, stereo, 24bits */
 	rate->min = rate->max = 48000;
@@ -259,6 +253,26 @@ static int cht_codec_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP2 to 24-bit */
 	params_set_format(params, SNDRV_PCM_FORMAT_S24_LE);
+
+	/*
+	 * Default mode for SSP configuration is TDM 4 slot
+	 */
+	ret = snd_soc_dai_set_fmt(rtd->codec_dai,
+				  SND_SOC_DAIFMT_DSP_B |
+				  SND_SOC_DAIFMT_IB_NF |
+				  SND_SOC_DAIFMT_CBS_CFS);
+	if (ret < 0) {
+		dev_err(rtd->dev, "can't set format to TDM %d\n", ret);
+		return ret;
+	}
+
+	/* TDM 4 slots 24 bit, set Rx & Tx bitmask to 4 active slots */
+	ret = snd_soc_dai_set_tdm_slot(rtd->codec_dai, 0xF, 0xF, 4, 24);
+	if (ret < 0) {
+		dev_err(rtd->dev, "can't set codec TDM slot %d\n", ret);
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -315,8 +329,6 @@ static struct snd_soc_dai_link cht_dailink[] = {
 		.nonatomic = true,
 		.codec_dai_name = "rt5670-aif1",
 		.codec_name = "i2c-10EC5670:00",
-		.dai_fmt = SND_SOC_DAIFMT_DSP_B | SND_SOC_DAIFMT_IB_NF
-					| SND_SOC_DAIFMT_CBS_CFS,
 		.init = cht_codec_init,
 		.be_hw_params_fixup = cht_codec_fixup,
 		.dpcm_playback = 1,
diff --git a/sound/soc/intel/boards/kbl_da7219_max98357a.c b/sound/soc/intel/boards/kbl_da7219_max98357a.c
index e84baafd5f63..94294c27d1db 100644
--- a/sound/soc/intel/boards/kbl_da7219_max98357a.c
+++ b/sound/soc/intel/boards/kbl_da7219_max98357a.c
@@ -65,14 +65,6 @@ static int platform_clock_control(struct snd_soc_dapm_widget *w,
 		return -EIO;
 	}
 
-	/* Configure sysclk for codec */
-	ret = snd_soc_dai_set_sysclk(codec_dai, DA7219_CLKSRC_MCLK, 24576000,
-				     SND_SOC_CLOCK_IN);
-	if (ret) {
-		dev_err(card->dev, "can't set codec sysclk configuration\n");
-		return ret;
-	}
-
 	if (SND_SOC_DAPM_EVENT_OFF(event)) {
 		ret = snd_soc_dai_set_pll(codec_dai, 0,
 				     DA7219_SYSCLK_MCLK, 0, 0);
@@ -169,9 +161,18 @@ static int kabylake_da7219_codec_init(struct snd_soc_pcm_runtime *rtd)
 {
 	struct kbl_codec_private *ctx = snd_soc_card_get_drvdata(rtd->card);
 	struct snd_soc_component *component = rtd->codec_dai->component;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
 	struct snd_soc_jack *jack;
 	int ret;
 
+	/* Configure sysclk for codec */
+	ret = snd_soc_dai_set_sysclk(codec_dai, DA7219_CLKSRC_MCLK, 24576000,
+						SND_SOC_CLOCK_IN);
+	if (ret) {
+		dev_err(rtd->dev, "can't set codec sysclk configuration\n");
+		return ret;
+	}
+
 	/*
 	 * Headset buttons map to the google Reference headset.
 	 * These can be configured by userspace.
@@ -572,7 +573,7 @@ static int kabylake_audio_probe(struct platform_device *pdev)
 {
 	struct kbl_codec_private *ctx;
 
-	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c
index 0e6b7e79441c..3a61252fe450 100644
--- a/sound/soc/intel/boards/kbl_rt5663_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c
@@ -299,7 +299,8 @@ static int kabylake_rt5663_codec_init(struct snd_soc_pcm_runtime *rtd)
 	snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEUP);
 	snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOLUMEDOWN);
 
-	rt5663_set_jack_detect(component, &ctx->kabylake_headset);
+	snd_soc_component_set_jack(component, &ctx->kabylake_headset, NULL);
+
 	return ret;
 }
 
@@ -972,7 +973,7 @@ static int kabylake_audio_probe(struct platform_device *pdev)
 	struct skl_machine_pdata *pdata;
 	int ret;
 
-	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
index 69c3d8446f06..92f5fb2ae0a3 100644
--- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
@@ -200,7 +200,7 @@ static int kabylake_rt5663_codec_init(struct snd_soc_pcm_runtime *rtd)
 	snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEUP);
 	snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOLUMEDOWN);
 
-	rt5663_set_jack_detect(component, &ctx->kabylake_headset);
+	snd_soc_component_set_jack(component, &ctx->kabylake_headset, NULL);
 
 	ret = snd_soc_dapm_ignore_suspend(&rtd->card->dapm, "DMIC");
 	if (ret)
@@ -651,7 +651,7 @@ static int kabylake_audio_probe(struct platform_device *pdev)
 	struct kbl_codec_private *ctx;
 	struct skl_machine_pdata *pdata;
 
-	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/skl_nau88l25_max98357a.c b/sound/soc/intel/boards/skl_nau88l25_max98357a.c
index 9a7a0646bffe..3ff6646cfa21 100644
--- a/sound/soc/intel/boards/skl_nau88l25_max98357a.c
+++ b/sound/soc/intel/boards/skl_nau88l25_max98357a.c
@@ -643,7 +643,7 @@ static int skylake_audio_probe(struct platform_device *pdev)
 	struct skl_nau8825_private *ctx;
 	struct skl_machine_pdata *pdata;
 
-	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/skl_nau88l25_ssm4567.c b/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
index 212ac8971e55..b0610bba3cfa 100644
--- a/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
+++ b/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
@@ -696,7 +696,7 @@ static int skylake_audio_probe(struct platform_device *pdev)
 	struct skl_nau88125_private *ctx;
 	struct skl_machine_pdata *pdata;
 
-	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/boards/skl_rt286.c b/sound/soc/intel/boards/skl_rt286.c
index 737d5615b0ef..38a1495c29cf 100644
--- a/sound/soc/intel/boards/skl_rt286.c
+++ b/sound/soc/intel/boards/skl_rt286.c
@@ -527,7 +527,7 @@ static int skylake_audio_probe(struct platform_device *pdev)
 {
 	struct skl_rt286_private *ctx;
 
-	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
diff --git a/sound/soc/intel/skylake/skl-debug.c b/sound/soc/intel/skylake/skl-debug.c
index a016455a6ddb..5d7ac2ee7a3c 100644
--- a/sound/soc/intel/skylake/skl-debug.c
+++ b/sound/soc/intel/skylake/skl-debug.c
@@ -15,10 +15,10 @@
 
 #include <linux/pci.h>
 #include <linux/debugfs.h>
+#include <uapi/sound/skl-tplg-interface.h>
 #include "skl.h"
 #include "skl-sst-dsp.h"
 #include "skl-sst-ipc.h"
-#include "skl-tplg-interface.h"
 #include "skl-topology.h"
 #include "../common/sst-dsp.h"
 #include "../common/sst-dsp-priv.h"
@@ -142,8 +142,8 @@ static ssize_t module_read(struct file *file, char __user *user_buf,
 			mconfig->max_out_queue, ret, false);
 
 	ret += snprintf(buf + ret, MOD_BUF - ret,
-			"Other:\n\tDomain %d\n\tHomogenous Input %s\n\t"
-			"Homogenous Output %s\n\tIn Queue Mask %d\n\t"
+			"Other:\n\tDomain %d\n\tHomogeneous Input %s\n\t"
+			"Homogeneous Output %s\n\tIn Queue Mask %d\n\t"
 			"Out Queue Mask %d\n\tDMA ID %d\n\tMem Pages %d\n\t"
 			"Module Type %d\n\tModule State %d\n",
 			mconfig->domain,
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index 57d4a58522a6..d5f9c30eba32 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -21,6 +21,7 @@
 #include <linux/pci.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
+#include <uapi/sound/skl-tplg-interface.h>
 #include "skl-sst-dsp.h"
 #include "cnl-sst-dsp.h"
 #include "skl-sst-ipc.h"
@@ -28,7 +29,6 @@
 #include "../common/sst-dsp.h"
 #include "../common/sst-dsp-priv.h"
 #include "skl-topology.h"
-#include "skl-tplg-interface.h"
 
 static int skl_alloc_dma_buf(struct device *dev,
 		struct snd_dma_buffer *dmab, size_t size)
@@ -225,7 +225,7 @@ static const struct skl_dsp_ops dsp_ops[] = {
 		.id = 0x9d71,
 		.num_cores = 2,
 		.loader_ops = skl_get_loader_ops,
-		.init = kbl_sst_dsp_init,
+		.init = skl_sst_dsp_init,
 		.init_fw = skl_sst_init_fw,
 		.cleanup = skl_sst_dsp_cleanup
 	},
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index 15cb8ac3e374..afa86b9e4dcf 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -268,15 +268,31 @@ static int skl_pcm_prepare(struct snd_pcm_substream *substream,
 {
 	struct skl *skl = get_skl_ctx(dai->dev);
 	struct skl_module_cfg *mconfig;
+	int ret;
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
 
 	mconfig = skl_tplg_fe_get_cpr_module(dai, substream->stream);
 
-	/* In case of XRUN recovery, reset the FW pipe to clean state */
-	if (mconfig && (substream->runtime->status->state ==
-					SNDRV_PCM_STATE_XRUN))
-		skl_reset_pipe(skl->skl_sst, mconfig->pipe);
+	/*
+	 * In case of XRUN recovery or in the case when the application
+	 * calls prepare another time, reset the FW pipe to clean state
+	 */
+	if (mconfig &&
+		(substream->runtime->status->state == SNDRV_PCM_STATE_XRUN ||
+		 mconfig->pipe->state == SKL_PIPE_CREATED ||
+		 mconfig->pipe->state == SKL_PIPE_PAUSED)) {
+
+		ret = skl_reset_pipe(skl->skl_sst, mconfig->pipe);
+
+		if (ret < 0)
+			return ret;
+
+		ret = skl_pcm_host_dma_prepare(dai->dev,
+					mconfig->pipe->p_params);
+		if (ret < 0)
+			return ret;
+	}
 
 	return 0;
 }
@@ -366,9 +382,21 @@ static int skl_pcm_hw_free(struct snd_pcm_substream *substream,
 {
 	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
+	struct skl *skl = get_skl_ctx(dai->dev);
+	struct skl_module_cfg *mconfig;
+	int ret;
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
 
+	mconfig = skl_tplg_fe_get_cpr_module(dai, substream->stream);
+
+	if (mconfig) {
+		ret = skl_reset_pipe(skl->skl_sst, mconfig->pipe);
+		if (ret < 0)
+			dev_err(dai->dev, "%s:Reset failed ret =%d",
+						__func__, ret);
+	}
+
 	snd_hdac_stream_cleanup(hdac_stream(stream));
 	hdac_stream(stream)->prepared = 0;
 
diff --git a/sound/soc/intel/skylake/skl-sst-dsp.h b/sound/soc/intel/skylake/skl-sst-dsp.h
index 12fc9a73dc8a..e1d6f6719f7e 100644
--- a/sound/soc/intel/skylake/skl-sst-dsp.h
+++ b/sound/soc/intel/skylake/skl-sst-dsp.h
@@ -231,9 +231,6 @@ int skl_dsp_boot(struct sst_dsp *ctx);
 int skl_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 		const char *fw_name, struct skl_dsp_loader_ops dsp_ops,
 		struct skl_sst **dsp);
-int kbl_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
-		const char *fw_name, struct skl_dsp_loader_ops dsp_ops,
-		struct skl_sst **dsp);
 int bxt_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 		const char *fw_name, struct skl_dsp_loader_ops dsp_ops,
 		struct skl_sst **dsp);
diff --git a/sound/soc/intel/skylake/skl-sst.c b/sound/soc/intel/skylake/skl-sst.c
index 5a7e41b65ef3..5951bbdf1f1a 100644
--- a/sound/soc/intel/skylake/skl-sst.c
+++ b/sound/soc/intel/skylake/skl-sst.c
@@ -390,7 +390,7 @@ out:
 }
 
 static int
-kbl_load_library(struct sst_dsp *ctx, struct skl_lib_info *linfo, int lib_count)
+skl_load_library(struct sst_dsp *ctx, struct skl_lib_info *linfo, int lib_count)
 {
 	struct skl_sst *skl = ctx->thread_context;
 	struct firmware stripped_fw;
@@ -508,16 +508,7 @@ static const struct skl_dsp_fw_ops skl_fw_ops = {
 	.set_state_D3 = skl_set_dsp_D3,
 	.load_fw = skl_load_base_firmware,
 	.get_fw_errcode = skl_get_errorcode,
-	.load_mod = skl_load_module,
-	.unload_mod = skl_unload_module,
-};
-
-static const struct skl_dsp_fw_ops kbl_fw_ops = {
-	.set_state_D0 = skl_set_dsp_D0,
-	.set_state_D3 = skl_set_dsp_D3,
-	.load_fw = skl_load_base_firmware,
-	.get_fw_errcode = skl_get_errorcode,
-	.load_library = kbl_load_library,
+	.load_library = skl_load_library,
 	.load_mod = skl_load_module,
 	.unload_mod = skl_unload_module,
 };
@@ -573,27 +564,6 @@ int skl_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 }
 EXPORT_SYMBOL_GPL(skl_sst_dsp_init);
 
-int kbl_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
-		const char *fw_name, struct skl_dsp_loader_ops dsp_ops,
-		struct skl_sst **dsp)
-{
-	struct sst_dsp *sst;
-	int ret;
-
-	ret = skl_sst_dsp_init(dev, mmio_base, irq, fw_name, dsp_ops, dsp);
-	if (ret < 0) {
-		dev_err(dev, "%s: Init failed %d\n", __func__, ret);
-		return ret;
-	}
-
-	sst = (*dsp)->dsp;
-	sst->fw_ops = kbl_fw_ops;
-
-	return 0;
-
-}
-EXPORT_SYMBOL_GPL(kbl_sst_dsp_init);
-
 int skl_sst_init_fw(struct device *dev, struct skl_sst *ctx)
 {
 	int ret;
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index 3b1dca419883..2c5129782959 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -19,14 +19,15 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/firmware.h>
+#include <linux/uuid.h>
 #include <sound/soc.h>
 #include <sound/soc-topology.h>
 #include <uapi/sound/snd_sst_tokens.h>
+#include <uapi/sound/skl-tplg-interface.h>
 #include "skl-sst-dsp.h"
 #include "skl-sst-ipc.h"
 #include "skl-topology.h"
 #include "skl.h"
-#include "skl-tplg-interface.h"
 #include "../common/sst-dsp.h"
 #include "../common/sst-dsp-priv.h"
 
@@ -2724,6 +2725,167 @@ static int skl_tplg_get_desc_blocks(struct device *dev,
 	return -EINVAL;
 }
 
+/* Functions to parse private data from configuration file format v4 */
+
+/*
+ * Add pipeline from topology binary into driver pipeline list
+ *
+ * If already added we return that instance
+ * Otherwise we create a new instance and add into driver list
+ */
+static int skl_tplg_add_pipe_v4(struct device *dev,
+				struct skl_module_cfg *mconfig, struct skl *skl,
+				struct skl_dfw_v4_pipe *dfw_pipe)
+{
+	struct skl_pipeline *ppl;
+	struct skl_pipe *pipe;
+	struct skl_pipe_params *params;
+
+	list_for_each_entry(ppl, &skl->ppl_list, node) {
+		if (ppl->pipe->ppl_id == dfw_pipe->pipe_id) {
+			mconfig->pipe = ppl->pipe;
+			return 0;
+		}
+	}
+
+	ppl = devm_kzalloc(dev, sizeof(*ppl), GFP_KERNEL);
+	if (!ppl)
+		return -ENOMEM;
+
+	pipe = devm_kzalloc(dev, sizeof(*pipe), GFP_KERNEL);
+	if (!pipe)
+		return -ENOMEM;
+
+	params = devm_kzalloc(dev, sizeof(*params), GFP_KERNEL);
+	if (!params)
+		return -ENOMEM;
+
+	pipe->ppl_id = dfw_pipe->pipe_id;
+	pipe->memory_pages = dfw_pipe->memory_pages;
+	pipe->pipe_priority = dfw_pipe->pipe_priority;
+	pipe->conn_type = dfw_pipe->conn_type;
+	pipe->state = SKL_PIPE_INVALID;
+	pipe->p_params = params;
+	INIT_LIST_HEAD(&pipe->w_list);
+
+	ppl->pipe = pipe;
+	list_add(&ppl->node, &skl->ppl_list);
+
+	mconfig->pipe = pipe;
+
+	return 0;
+}
+
+static void skl_fill_module_pin_info_v4(struct skl_dfw_v4_module_pin *dfw_pin,
+					struct skl_module_pin *m_pin,
+					bool is_dynamic, int max_pin)
+{
+	int i;
+
+	for (i = 0; i < max_pin; i++) {
+		m_pin[i].id.module_id = dfw_pin[i].module_id;
+		m_pin[i].id.instance_id = dfw_pin[i].instance_id;
+		m_pin[i].in_use = false;
+		m_pin[i].is_dynamic = is_dynamic;
+		m_pin[i].pin_state = SKL_PIN_UNBIND;
+	}
+}
+
+static void skl_tplg_fill_fmt_v4(struct skl_module_pin_fmt *dst_fmt,
+				 struct skl_dfw_v4_module_fmt *src_fmt,
+				 int pins)
+{
+	int i;
+
+	for (i = 0; i < pins; i++) {
+		dst_fmt[i].fmt.channels  = src_fmt[i].channels;
+		dst_fmt[i].fmt.s_freq = src_fmt[i].freq;
+		dst_fmt[i].fmt.bit_depth = src_fmt[i].bit_depth;
+		dst_fmt[i].fmt.valid_bit_depth = src_fmt[i].valid_bit_depth;
+		dst_fmt[i].fmt.ch_cfg = src_fmt[i].ch_cfg;
+		dst_fmt[i].fmt.ch_map = src_fmt[i].ch_map;
+		dst_fmt[i].fmt.interleaving_style =
+						src_fmt[i].interleaving_style;
+		dst_fmt[i].fmt.sample_type = src_fmt[i].sample_type;
+	}
+}
+
+static int skl_tplg_get_pvt_data_v4(struct snd_soc_tplg_dapm_widget *tplg_w,
+				    struct skl *skl, struct device *dev,
+				    struct skl_module_cfg *mconfig)
+{
+	struct skl_dfw_v4_module *dfw =
+				(struct skl_dfw_v4_module *)tplg_w->priv.data;
+	int ret;
+
+	dev_dbg(dev, "Parsing Skylake v4 widget topology data\n");
+
+	ret = guid_parse(dfw->uuid, (guid_t *)mconfig->guid);
+	if (ret)
+		return ret;
+	mconfig->id.module_id = -1;
+	mconfig->id.instance_id = dfw->instance_id;
+	mconfig->module->resources[0].cps = dfw->max_mcps;
+	mconfig->module->resources[0].ibs = dfw->ibs;
+	mconfig->module->resources[0].obs = dfw->obs;
+	mconfig->core_id = dfw->core_id;
+	mconfig->module->max_input_pins = dfw->max_in_queue;
+	mconfig->module->max_output_pins = dfw->max_out_queue;
+	mconfig->module->loadable = dfw->is_loadable;
+	skl_tplg_fill_fmt_v4(mconfig->module->formats[0].inputs, dfw->in_fmt,
+			     MAX_IN_QUEUE);
+	skl_tplg_fill_fmt_v4(mconfig->module->formats[0].outputs, dfw->out_fmt,
+			     MAX_OUT_QUEUE);
+
+	mconfig->params_fixup = dfw->params_fixup;
+	mconfig->converter = dfw->converter;
+	mconfig->m_type = dfw->module_type;
+	mconfig->vbus_id = dfw->vbus_id;
+	mconfig->module->resources[0].is_pages = dfw->mem_pages;
+
+	ret = skl_tplg_add_pipe_v4(dev, mconfig, skl, &dfw->pipe);
+	if (ret)
+		return ret;
+
+	mconfig->dev_type = dfw->dev_type;
+	mconfig->hw_conn_type = dfw->hw_conn_type;
+	mconfig->time_slot = dfw->time_slot;
+	mconfig->formats_config.caps_size = dfw->caps.caps_size;
+
+	mconfig->m_in_pin = devm_kzalloc(dev,
+				MAX_IN_QUEUE * sizeof(*mconfig->m_in_pin),
+				GFP_KERNEL);
+	if (!mconfig->m_in_pin)
+		return -ENOMEM;
+
+	mconfig->m_out_pin = devm_kzalloc(dev,
+				MAX_OUT_QUEUE * sizeof(*mconfig->m_out_pin),
+				GFP_KERNEL);
+	if (!mconfig->m_out_pin)
+		return -ENOMEM;
+
+	skl_fill_module_pin_info_v4(dfw->in_pin, mconfig->m_in_pin,
+				    dfw->is_dynamic_in_pin,
+				    mconfig->module->max_input_pins);
+	skl_fill_module_pin_info_v4(dfw->out_pin, mconfig->m_out_pin,
+				    dfw->is_dynamic_out_pin,
+				    mconfig->module->max_output_pins);
+
+	if (mconfig->formats_config.caps_size) {
+		mconfig->formats_config.set_params = dfw->caps.set_params;
+		mconfig->formats_config.param_id = dfw->caps.param_id;
+		mconfig->formats_config.caps =
+		devm_kzalloc(dev, mconfig->formats_config.caps_size,
+			     GFP_KERNEL);
+		if (!mconfig->formats_config.caps)
+			return -ENOMEM;
+		memcpy(mconfig->formats_config.caps, dfw->caps.caps,
+		       dfw->caps.caps_size);
+	}
+
+	return 0;
+}
+
 /*
  * Parse the private data for the token and corresponding value.
  * The private data can have multiple data blocks. So, a data block
@@ -2739,6 +2901,13 @@ static int skl_tplg_get_pvt_data(struct snd_soc_tplg_dapm_widget *tplg_w,
 	char *data;
 	int ret;
 
+	/*
+	 * v4 configuration files have a valid UUID at the start of
+	 * the widget's private data.
+	 */
+	if (uuid_is_valid((char *)tplg_w->priv.data))
+		return skl_tplg_get_pvt_data_v4(tplg_w, skl, dev, mconfig);
+
 	/* Read the NUM_DATA_BLOCKS descriptor */
 	array = (struct snd_soc_tplg_vendor_array *)tplg_w->priv.data;
 	ret = skl_tplg_get_desc_blocks(dev, array);
diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h
index b1e0667c0ae0..6d7e0569695f 100644
--- a/sound/soc/intel/skylake/skl-topology.h
+++ b/sound/soc/intel/skylake/skl-topology.h
@@ -25,8 +25,8 @@
 
 #include <sound/hdaudio_ext.h>
 #include <sound/soc.h>
+#include <uapi/sound/skl-tplg-interface.h>
 #include "skl.h"
-#include "skl-tplg-interface.h"
 
 #define BITS_PER_BYTE 8
 #define MAX_TS_GROUPS 8
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index abf324747b29..f0d9793f872a 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -127,10 +127,17 @@ static void skl_clock_power_gating(struct device *dev, bool enable)
  */
 static int skl_init_chip(struct hdac_bus *bus, bool full_reset)
 {
+	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
+	struct hdac_ext_link *hlink;
 	int ret;
 
 	skl_enable_miscbdcge(bus->dev, false);
 	ret = snd_hdac_bus_init_chip(bus, full_reset);
+
+	/* Reset stream-to-link mapping */
+	list_for_each_entry(hlink, &ebus->hlink_list, list)
+		bus->io_ops->reg_writel(0, hlink->ml_addr + AZX_REG_ML_LOSIDV);
+
 	skl_enable_miscbdcge(bus->dev, true);
 
 	return ret;
diff --git a/sound/soc/kirkwood/Kconfig b/sound/soc/kirkwood/Kconfig
index bc3c7b5ac752..132bb83f8e99 100644
--- a/sound/soc/kirkwood/Kconfig
+++ b/sound/soc/kirkwood/Kconfig
@@ -1,7 +1,6 @@
 config SND_KIRKWOOD_SOC
 	tristate "SoC Audio for the Marvell Kirkwood and Dove chips"
 	depends on ARCH_DOVE || ARCH_MVEBU || COMPILE_TEST
-	depends on HAS_DMA
 	help
 	  Say Y or M if you want to add support for codecs attached to
 	  the Kirkwood I2S interface. You will also need to select the
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 5c68797f36c4..e731d40afcce 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -32,6 +32,26 @@ config SND_SOC_MT2701_WM8960
 	  Select Y if you have such device.
 	  If unsure select "N".
 
+config SND_SOC_MT6797
+	tristate "ASoC support for Mediatek MT6797 chip"
+	depends on ARCH_MEDIATEK
+	select SND_SOC_MEDIATEK
+	help
+	  This adds ASoC driver for Mediatek MT6797 boards
+	  that can be used with other codecs.
+	  Select Y if you have such device.
+	  If unsure select "N".
+
+config SND_SOC_MT6797_MT6351
+	tristate "ASoc Audio driver for MT6797 with MT6351 codec"
+	depends on SND_SOC_MT6797 && MTK_PMIC_WRAP
+	select SND_SOC_MT6351
+	help
+	  This adds ASoC driver for Mediatek MT6797 boards
+	  with the MT6351 codecs.
+	  Select Y if you have such device.
+	  If unsure select "N".
+
 config SND_SOC_MT8173
 	tristate "ASoC support for Mediatek MT8173 chip"
 	depends on ARCH_MEDIATEK
diff --git a/sound/soc/mediatek/Makefile b/sound/soc/mediatek/Makefile
index 6bcab35dc828..3bb2c47532f4 100644
--- a/sound/soc/mediatek/Makefile
+++ b/sound/soc/mediatek/Makefile
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_SND_SOC_MEDIATEK) += common/
 obj-$(CONFIG_SND_SOC_MT2701) += mt2701/
+obj-$(CONFIG_SND_SOC_MT6797) += mt6797/
 obj-$(CONFIG_SND_SOC_MT8173) += mt8173/
diff --git a/sound/soc/mediatek/common/Makefile b/sound/soc/mediatek/common/Makefile
index a55d33bc7b01..cdadabc5fd16 100644
--- a/sound/soc/mediatek/common/Makefile
+++ b/sound/soc/mediatek/common/Makefile
@@ -1,16 +1,4 @@
-#
-# Copyright (C) 2015 MediaTek Inc.
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License version 2 as
-# published by the Free Software Foundation.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-
+# SPDX-License-Identifier: GPL-2.0
 # platform driver
 snd-soc-mtk-common-objs := mtk-afe-platform-driver.o mtk-afe-fe-dai.o
 obj-$(CONFIG_SND_SOC_MEDIATEK) += snd-soc-mtk-common.o
diff --git a/sound/soc/mediatek/common/mtk-afe-fe-dai.c b/sound/soc/mediatek/common/mtk-afe-fe-dai.c
index c91e5f4cd902..cf4978be062f 100644
--- a/sound/soc/mediatek/common/mtk-afe-fe-dai.c
+++ b/sound/soc/mediatek/common/mtk-afe-fe-dai.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mtk-afe-fe-dais.c  --  Mediatek afe fe dai operator
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>
@@ -44,8 +36,7 @@ int mtk_afe_fe_startup(struct snd_pcm_substream *substream,
 		       struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	int memif_num = rtd->cpu_dai->id;
 	struct mtk_base_afe_memif *memif = &afe->memif[memif_num];
@@ -107,8 +98,7 @@ void mtk_afe_fe_shutdown(struct snd_pcm_substream *substream,
 			 struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
 	int irq_id;
 
@@ -131,8 +121,7 @@ int mtk_afe_fe_hw_params(struct snd_pcm_substream *substream,
 			 struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
 	int msb_at_bit33 = 0;
 	int ret, fs = 0;
@@ -196,8 +185,7 @@ int mtk_afe_fe_trigger(struct snd_pcm_substream *substream, int cmd,
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime * const runtime = substream->runtime;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
 	struct mtk_base_afe_irq *irqs = &afe->irqs[memif->irq_usage];
 	const struct mtk_base_irq_data *irq_data = irqs->irq_data;
@@ -260,8 +248,7 @@ int mtk_afe_fe_prepare(struct snd_pcm_substream *substream,
 		       struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd  = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
 	int hd_audio = 0;
 
@@ -333,7 +320,7 @@ EXPORT_SYMBOL_GPL(mtk_dynamic_irq_release);
 
 int mtk_afe_dai_suspend(struct snd_soc_dai *dai)
 {
-	struct mtk_base_afe *afe = dev_get_drvdata(dai->dev);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct device *dev = afe->dev;
 	struct regmap *regmap = afe->regmap;
 	int i;
@@ -358,7 +345,7 @@ EXPORT_SYMBOL_GPL(mtk_afe_dai_suspend);
 
 int mtk_afe_dai_resume(struct snd_soc_dai *dai)
 {
-	struct mtk_base_afe *afe = dev_get_drvdata(dai->dev);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct device *dev = afe->dev;
 	struct regmap *regmap = afe->regmap;
 	int i = 0;
@@ -383,4 +370,3 @@ EXPORT_SYMBOL_GPL(mtk_afe_dai_resume);
 MODULE_DESCRIPTION("Mediatek simple fe dai operator");
 MODULE_AUTHOR("Garlic Tseng <garlic.tseng@mediatek.com>");
 MODULE_LICENSE("GPL v2");
-
diff --git a/sound/soc/mediatek/common/mtk-afe-fe-dai.h b/sound/soc/mediatek/common/mtk-afe-fe-dai.h
index 28cb17854da1..55074fb9861a 100644
--- a/sound/soc/mediatek/common/mtk-afe-fe-dai.h
+++ b/sound/soc/mediatek/common/mtk-afe-fe-dai.h
@@ -1,17 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * mtk-afe-fe-dais.h  --  Mediatek afe fe dai operator definition
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _MTK_AFE_FE_DAI_H_
diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
index 53215b52e4f2..51ec4ff6ed95 100644
--- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c
+++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mtk-afe-platform-driver.c  --  Mediatek afe platform driver
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>
@@ -21,6 +13,86 @@
 #include "mtk-afe-platform-driver.h"
 #include "mtk-base-afe.h"
 
+int mtk_afe_combine_sub_dai(struct mtk_base_afe *afe)
+{
+	struct snd_soc_dai_driver *sub_dai_drivers;
+	size_t num_dai_drivers = 0, dai_idx = 0;
+	int i;
+
+	if (!afe->sub_dais) {
+		dev_err(afe->dev, "%s(), sub_dais == NULL\n", __func__);
+		return -EINVAL;
+	}
+
+	/* calcualte total dai driver size */
+	for (i = 0; i < afe->num_sub_dais; i++) {
+		if (afe->sub_dais[i].dai_drivers &&
+		    afe->sub_dais[i].num_dai_drivers != 0)
+			num_dai_drivers += afe->sub_dais[i].num_dai_drivers;
+	}
+
+	dev_info(afe->dev, "%s(), num of dai %zd\n", __func__, num_dai_drivers);
+
+	/* combine sub_dais */
+	afe->num_dai_drivers = num_dai_drivers;
+	afe->dai_drivers = devm_kcalloc(afe->dev,
+					num_dai_drivers,
+					sizeof(struct snd_soc_dai_driver),
+					GFP_KERNEL);
+	if (!afe->dai_drivers)
+		return -ENOMEM;
+
+	for (i = 0; i < afe->num_sub_dais; i++) {
+		if (afe->sub_dais[i].dai_drivers &&
+		    afe->sub_dais[i].num_dai_drivers != 0) {
+			sub_dai_drivers = afe->sub_dais[i].dai_drivers;
+			/* dai driver */
+			memcpy(&afe->dai_drivers[dai_idx],
+			       sub_dai_drivers,
+			       afe->sub_dais[i].num_dai_drivers *
+			       sizeof(struct snd_soc_dai_driver));
+			dai_idx += afe->sub_dais[i].num_dai_drivers;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mtk_afe_combine_sub_dai);
+
+int mtk_afe_add_sub_dai_control(struct snd_soc_component *component)
+{
+	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	int i;
+
+	if (!afe->sub_dais) {
+		dev_err(afe->dev, "%s(), sub_dais == NULL\n", __func__);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < afe->num_sub_dais; i++) {
+		if (afe->sub_dais[i].controls)
+			snd_soc_add_component_controls(component,
+				afe->sub_dais[i].controls,
+				afe->sub_dais[i].num_controls);
+
+		if (afe->sub_dais[i].dapm_widgets)
+			snd_soc_dapm_new_controls(&component->dapm,
+				afe->sub_dais[i].dapm_widgets,
+				afe->sub_dais[i].num_dapm_widgets);
+
+		if (afe->sub_dais[i].dapm_routes)
+			snd_soc_dapm_add_routes(&component->dapm,
+				afe->sub_dais[i].dapm_routes,
+				afe->sub_dais[i].num_dapm_routes);
+	}
+
+	snd_soc_dapm_new_widgets(component->dapm.card);
+
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(mtk_afe_add_sub_dai_control);
+
 static snd_pcm_uframes_t mtk_afe_pcm_pointer
 			 (struct snd_pcm_substream *substream)
 {
@@ -56,28 +128,31 @@ POINTER_RETURN_FRAMES:
 	return bytes_to_frames(substream->runtime, pcm_ptr_bytes);
 }
 
-static const struct snd_pcm_ops mtk_afe_pcm_ops = {
+const struct snd_pcm_ops mtk_afe_pcm_ops = {
 	.ioctl = snd_pcm_lib_ioctl,
 	.pointer = mtk_afe_pcm_pointer,
 };
+EXPORT_SYMBOL_GPL(mtk_afe_pcm_ops);
 
-static int mtk_afe_pcm_new(struct snd_soc_pcm_runtime *rtd)
+int mtk_afe_pcm_new(struct snd_soc_pcm_runtime *rtd)
 {
 	size_t size;
-	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
 	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
 	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
 
 	size = afe->mtk_afe_hardware->buffer_bytes_max;
 	return snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						     card->dev, size, size);
+						     afe->dev,
+						     size, size);
 }
+EXPORT_SYMBOL_GPL(mtk_afe_pcm_new);
 
-static void mtk_afe_pcm_free(struct snd_pcm *pcm)
+void mtk_afe_pcm_free(struct snd_pcm *pcm)
 {
 	snd_pcm_lib_preallocate_free_for_all(pcm);
 }
+EXPORT_SYMBOL_GPL(mtk_afe_pcm_free);
 
 const struct snd_soc_component_driver mtk_afe_pcm_platform = {
 	.name = AFE_PCM_NAME,
diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.h b/sound/soc/mediatek/common/mtk-afe-platform-driver.h
index 8dcdbed959ea..88df6797732f 100644
--- a/sound/soc/mediatek/common/mtk-afe-platform-driver.h
+++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.h
@@ -1,24 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * mtk-afe-platform-driver.h  --  Mediatek afe platform driver definition
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _MTK_AFE_PLATFORM_DRIVER_H_
 #define _MTK_AFE_PLATFORM_DRIVER_H_
 
 #define AFE_PCM_NAME "mtk-afe-pcm"
+extern const struct snd_pcm_ops mtk_afe_pcm_ops;
 extern const struct snd_soc_component_driver mtk_afe_pcm_platform;
 
+struct mtk_base_afe;
+struct snd_pcm;
+struct snd_soc_component;
+struct snd_soc_pcm_runtime;
+
+
+int mtk_afe_pcm_new(struct snd_soc_pcm_runtime *rtd);
+void mtk_afe_pcm_free(struct snd_pcm *pcm);
+
+int mtk_afe_combine_sub_dai(struct mtk_base_afe *afe);
+int mtk_afe_add_sub_dai_control(struct snd_soc_component *component);
 #endif
 
diff --git a/sound/soc/mediatek/common/mtk-base-afe.h b/sound/soc/mediatek/common/mtk-base-afe.h
index 3a78f6f17195..bcf562f029b6 100644
--- a/sound/soc/mediatek/common/mtk-base-afe.h
+++ b/sound/soc/mediatek/common/mtk-base-afe.h
@@ -1,22 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * mtk-base-afe.h  --  Mediatek base afe structure
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _MTK_BASE_AFE_H_
 #define _MTK_BASE_AFE_H_
 
+#define MTK_STREAM_NUM (SNDRV_PCM_STREAM_LAST + 1)
+
 struct mtk_base_memif_data {
 	int id;
 	const char *name;
@@ -54,6 +48,7 @@ struct mtk_base_irq_data {
 struct device;
 struct mtk_base_afe_memif;
 struct mtk_base_afe_irq;
+struct mtk_base_afe_dai;
 struct regmap;
 struct snd_pcm_substream;
 struct snd_soc_dai;
@@ -77,6 +72,11 @@ struct mtk_base_afe {
 	struct mtk_base_afe_irq *irqs;
 	int irqs_size;
 
+	struct mtk_base_afe_dai *sub_dais;
+	int num_sub_dais;
+	struct snd_soc_dai_driver *dai_drivers;
+	unsigned int num_dai_drivers;
+
 	const struct snd_pcm_hardware *mtk_afe_hardware;
 	int (*memif_fs)(struct snd_pcm_substream *substream,
 			unsigned int rate);
@@ -100,5 +100,17 @@ struct mtk_base_afe_irq {
 	int irq_occupyed;
 };
 
+struct mtk_base_afe_dai {
+	struct snd_soc_dai_driver *dai_drivers;
+	unsigned int num_dai_drivers;
+
+	const struct snd_kcontrol_new *controls;
+	unsigned int num_controls;
+	const struct snd_soc_dapm_widget *dapm_widgets;
+	unsigned int num_dapm_widgets;
+	const struct snd_soc_dapm_route *dapm_routes;
+	unsigned int num_dapm_routes;
+};
+
 #endif
 
diff --git a/sound/soc/mediatek/mt2701/Makefile b/sound/soc/mediatek/mt2701/Makefile
index c91deb6aca21..21d5e697cfa7 100644
--- a/sound/soc/mediatek/mt2701/Makefile
+++ b/sound/soc/mediatek/mt2701/Makefile
@@ -1,16 +1,4 @@
-#
-# Copyright (C) 2015 MediaTek Inc.
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License version 2 as
-# published by the Free Software Foundation.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-
+# SPDX-License-Identifier: GPL-2.0
 # platform driver
 snd-soc-mt2701-afe-objs := mt2701-afe-pcm.o mt2701-afe-clock-ctrl.o
 obj-$(CONFIG_SND_SOC_MT2701) += snd-soc-mt2701-afe.o
diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.c b/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.c
index 949fc3a1d025..ae620890bb3a 100644
--- a/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.c
+++ b/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.c
@@ -1,17 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mt2701-afe-clock-ctrl.c  --  Mediatek 2701 afe clock ctrl
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ *	   Ryder Lee <ryder.lee@mediatek.com>
  */
 
 #include "mt2701-afe-common.h"
@@ -43,8 +36,9 @@ int mt2701_init_clock(struct mtk_base_afe *afe)
 	}
 
 	/* Get I2S related clocks */
-	for (i = 0; i < MT2701_I2S_NUM; i++) {
+	for (i = 0; i < afe_priv->soc->i2s_num; i++) {
 		struct mt2701_i2s_path *i2s_path = &afe_priv->i2s_path[i];
+		struct clk *i2s_ck;
 		char name[13];
 
 		snprintf(name, sizeof(name), "i2s%d_src_sel", i);
@@ -69,18 +63,20 @@ int mt2701_init_clock(struct mtk_base_afe *afe)
 		}
 
 		snprintf(name, sizeof(name), "i2so%d_hop_ck", i);
-		i2s_path->hop_ck[I2S_OUT] = devm_clk_get(afe->dev, name);
-		if (IS_ERR(i2s_path->hop_ck[I2S_OUT])) {
+		i2s_ck = devm_clk_get(afe->dev, name);
+		if (IS_ERR(i2s_ck)) {
 			dev_err(afe->dev, "failed to get %s\n", name);
-			return PTR_ERR(i2s_path->hop_ck[I2S_OUT]);
+			return PTR_ERR(i2s_ck);
 		}
+		i2s_path->hop_ck[SNDRV_PCM_STREAM_PLAYBACK] = i2s_ck;
 
 		snprintf(name, sizeof(name), "i2si%d_hop_ck", i);
-		i2s_path->hop_ck[I2S_IN] = devm_clk_get(afe->dev, name);
-		if (IS_ERR(i2s_path->hop_ck[I2S_IN])) {
+		i2s_ck = devm_clk_get(afe->dev, name);
+		if (IS_ERR(i2s_ck)) {
 			dev_err(afe->dev, "failed to get %s\n", name);
-			return PTR_ERR(i2s_path->hop_ck[I2S_IN]);
+			return PTR_ERR(i2s_ck);
 		}
+		i2s_path->hop_ck[SNDRV_PCM_STREAM_CAPTURE] = i2s_ck;
 
 		snprintf(name, sizeof(name), "asrc%d_out_ck", i);
 		i2s_path->asrco_ck = devm_clk_get(afe->dev, name);
@@ -102,10 +98,10 @@ int mt2701_init_clock(struct mtk_base_afe *afe)
 	return 0;
 }
 
-int mt2701_afe_enable_i2s(struct mtk_base_afe *afe, int id, int dir)
+int mt2701_afe_enable_i2s(struct mtk_base_afe *afe,
+			  struct mt2701_i2s_path *i2s_path,
+			  int dir)
 {
-	struct mt2701_afe_private *afe_priv = afe->platform_priv;
-	struct mt2701_i2s_path *i2s_path = &afe_priv->i2s_path[id];
 	int ret;
 
 	ret = clk_prepare_enable(i2s_path->asrco_ck);
@@ -128,11 +124,10 @@ err_hop_ck:
 	return ret;
 }
 
-void mt2701_afe_disable_i2s(struct mtk_base_afe *afe, int id, int dir)
+void mt2701_afe_disable_i2s(struct mtk_base_afe *afe,
+			    struct mt2701_i2s_path *i2s_path,
+			    int dir)
 {
-	struct mt2701_afe_private *afe_priv = afe->platform_priv;
-	struct mt2701_i2s_path *i2s_path = &afe_priv->i2s_path[id];
-
 	clk_disable_unprepare(i2s_path->hop_ck[dir]);
 	clk_disable_unprepare(i2s_path->asrco_ck);
 }
@@ -272,27 +267,32 @@ int mt2701_afe_disable_clock(struct mtk_base_afe *afe)
 	return 0;
 }
 
-void mt2701_mclk_configuration(struct mtk_base_afe *afe, int id, int domain,
-			       int mclk)
+int mt2701_mclk_configuration(struct mtk_base_afe *afe, int id)
+
 {
 	struct mt2701_afe_private *priv = afe->platform_priv;
 	struct mt2701_i2s_path *i2s_path = &priv->i2s_path[id];
-	int ret;
+	int ret = -EINVAL;
 
 	/* Set mclk source */
-	if (domain == 0)
+	if (!(MT2701_PLL_DOMAIN_0_RATE % i2s_path->mclk_rate))
 		ret = clk_set_parent(i2s_path->sel_ck,
 				     priv->base_ck[MT2701_TOP_AUD_MCLK_SRC0]);
-	else
+	else if (!(MT2701_PLL_DOMAIN_1_RATE % i2s_path->mclk_rate))
 		ret = clk_set_parent(i2s_path->sel_ck,
 				     priv->base_ck[MT2701_TOP_AUD_MCLK_SRC1]);
 
-	if (ret)
-		dev_err(afe->dev, "failed to set domain%d mclk source %d\n",
-			domain, ret);
+	if (ret) {
+		dev_err(afe->dev, "failed to set mclk source\n");
+		return ret;
+	}
 
 	/* Set mclk divider */
-	ret = clk_set_rate(i2s_path->div_ck, mclk);
-	if (ret)
+	ret = clk_set_rate(i2s_path->div_ck, i2s_path->mclk_rate);
+	if (ret) {
 		dev_err(afe->dev, "failed to set mclk divider %d\n", ret);
+		return ret;
+	}
+
+	return 0;
 }
diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.h b/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.h
index 15417d9d6597..580fead2ab05 100644
--- a/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.h
+++ b/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.h
@@ -1,37 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * mt2701-afe-clock-ctrl.h  --  Mediatek 2701 afe clock ctrl definition
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ *	   Ryder Lee <ryder.lee@mediatek.com>
  */
 
 #ifndef _MT2701_AFE_CLOCK_CTRL_H_
 #define _MT2701_AFE_CLOCK_CTRL_H_
 
 struct mtk_base_afe;
+struct mt2701_i2s_path;
 
 int mt2701_init_clock(struct mtk_base_afe *afe);
 int mt2701_afe_enable_clock(struct mtk_base_afe *afe);
 int mt2701_afe_disable_clock(struct mtk_base_afe *afe);
 
-int mt2701_afe_enable_i2s(struct mtk_base_afe *afe, int id, int dir);
-void mt2701_afe_disable_i2s(struct mtk_base_afe *afe, int id, int dir);
+int mt2701_afe_enable_i2s(struct mtk_base_afe *afe,
+			  struct mt2701_i2s_path *path,
+			  int dir);
+void mt2701_afe_disable_i2s(struct mtk_base_afe *afe,
+			    struct mt2701_i2s_path *path,
+			    int dir);
 int mt2701_afe_enable_mclk(struct mtk_base_afe *afe, int id);
 void mt2701_afe_disable_mclk(struct mtk_base_afe *afe, int id);
 
 int mt2701_enable_btmrg_clk(struct mtk_base_afe *afe);
 void mt2701_disable_btmrg_clk(struct mtk_base_afe *afe);
 
-void mt2701_mclk_configuration(struct mtk_base_afe *afe, int id, int domain,
-			       int mclk);
+int mt2701_mclk_configuration(struct mtk_base_afe *afe, int id);
 
 #endif
diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-common.h b/sound/soc/mediatek/mt2701/mt2701-afe-common.h
index ae8ddeacfbfe..d44faba27d3c 100644
--- a/sound/soc/mediatek/mt2701/mt2701-afe-common.h
+++ b/sound/soc/mediatek/mt2701/mt2701-afe-common.h
@@ -1,17 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * mt2701-afe-common.h  --  Mediatek 2701 audio driver definitions
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _MT_2701_AFE_COMMON_H_
@@ -23,10 +15,8 @@
 #include "mt2701-reg.h"
 #include "../common/mtk-base-afe.h"
 
-#define MT2701_STREAM_DIR_NUM (SNDRV_PCM_STREAM_LAST + 1)
 #define MT2701_PLL_DOMAIN_0_RATE	98304000
 #define MT2701_PLL_DOMAIN_1_RATE	90316800
-#define MT2701_I2S_NUM	4
 
 enum {
 	MT2701_MEMIF_DL1,
@@ -100,30 +90,30 @@ struct mt2701_i2s_data {
 	int i2s_asrc_fs_mask;
 };
 
-enum mt2701_i2s_dir {
-	I2S_OUT,
-	I2S_IN,
-	I2S_DIR_NUM,
-};
-
 struct mt2701_i2s_path {
-	int dai_id;
 	int mclk_rate;
-	int on[I2S_DIR_NUM];
-	int occupied[I2S_DIR_NUM];
-	const struct mt2701_i2s_data *i2s_data[I2S_DIR_NUM];
-	struct clk *hop_ck[I2S_DIR_NUM];
+	int on[MTK_STREAM_NUM];
+	int occupied[MTK_STREAM_NUM];
+	const struct mt2701_i2s_data *i2s_data[MTK_STREAM_NUM];
+	struct clk *hop_ck[MTK_STREAM_NUM];
 	struct clk *sel_ck;
 	struct clk *div_ck;
 	struct clk *mclk_ck;
 	struct clk *asrco_ck;
 };
 
+struct mt2701_soc_variants {
+	bool has_one_heart_mode;
+	int i2s_num;
+};
+
 struct mt2701_afe_private {
-	struct mt2701_i2s_path i2s_path[MT2701_I2S_NUM];
+	struct mt2701_i2s_path *i2s_path;
 	struct clk *base_ck[MT2701_BASE_CLK_NUM];
 	struct clk *mrgif_ck;
-	bool mrg_enable[MT2701_STREAM_DIR_NUM];
+	bool mrg_enable[MTK_STREAM_NUM];
+
+	const struct mt2701_soc_variants *soc;
 };
 
 #endif
diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c b/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c
index 73cce33fa439..828d11c30c6a 100644
--- a/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c
+++ b/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c
@@ -1,18 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Mediatek ALSA SoC AFE platform driver for 2701
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *             Ir Lian <ir.lian@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ *	   Ir Lian <ir.lian@mediatek.com>
+ *	   Ryder Lee <ryder.lee@mediatek.com>
  */
 
 #include <linux/delay.h>
@@ -20,6 +13,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 
 #include "mt2701-afe-common.h"
@@ -36,7 +30,7 @@ static const struct snd_pcm_hardware mt2701_afe_hardware = {
 	.period_bytes_max = 1024 * 256,
 	.periods_min = 4,
 	.periods_max = 1024,
-	.buffer_bytes_max = 1024 * 1024 * 16,
+	.buffer_bytes_max = 1024 * 1024,
 	.fifo_size = 0,
 };
 
@@ -68,9 +62,10 @@ static const struct mt2701_afe_rate mt2701_afe_i2s_rates[] = {
 
 static int mt2701_dai_num_to_i2s(struct mtk_base_afe *afe, int num)
 {
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
 	int val = num - MT2701_IO_I2S;
 
-	if (val < 0 || val >= MT2701_I2S_NUM) {
+	if (val < 0 || val >= afe_priv->soc->i2s_num) {
 		dev_err(afe->dev, "%s, num not available, num %d, val %d\n",
 			__func__, num, val);
 		return -EINVAL;
@@ -92,44 +87,26 @@ static int mt2701_afe_i2s_fs(unsigned int sample_rate)
 static int mt2701_afe_i2s_startup(struct snd_pcm_substream *substream,
 				  struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
 	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+	bool mode = afe_priv->soc->has_one_heart_mode;
 
 	if (i2s_num < 0)
 		return i2s_num;
 
-	return mt2701_afe_enable_mclk(afe, i2s_num);
+	return mt2701_afe_enable_mclk(afe, mode ? 1 : i2s_num);
 }
 
-static int mt2701_afe_i2s_path_shutdown(struct snd_pcm_substream *substream,
-					struct snd_soc_dai *dai,
-					int i2s_num,
-					int dir_invert)
+static int mt2701_afe_i2s_path_disable(struct mtk_base_afe *afe,
+				       struct mt2701_i2s_path *i2s_path,
+				       int stream_dir)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
-	struct mt2701_afe_private *afe_priv = afe->platform_priv;
-	struct mt2701_i2s_path *i2s_path = &afe_priv->i2s_path[i2s_num];
-	const struct mt2701_i2s_data *i2s_data;
-	int stream_dir = substream->stream;
-
-	if (dir_invert)	{
-		if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK)
-			stream_dir = SNDRV_PCM_STREAM_CAPTURE;
-		else
-			stream_dir = SNDRV_PCM_STREAM_PLAYBACK;
-	}
-	i2s_data = i2s_path->i2s_data[stream_dir];
+	const struct mt2701_i2s_data *i2s_data = i2s_path->i2s_data[stream_dir];
 
-	i2s_path->on[stream_dir]--;
-	if (i2s_path->on[stream_dir] < 0) {
-		dev_warn(afe->dev, "i2s_path->on: %d, dir: %d\n",
-			 i2s_path->on[stream_dir], stream_dir);
+	if (--i2s_path->on[stream_dir] < 0)
 		i2s_path->on[stream_dir] = 0;
-	}
+
 	if (i2s_path->on[stream_dir])
 		return 0;
 
@@ -137,7 +114,7 @@ static int mt2701_afe_i2s_path_shutdown(struct snd_pcm_substream *substream,
 	regmap_update_bits(afe->regmap, i2s_data->i2s_ctrl_reg,
 			   ASYS_I2S_CON_I2S_EN, 0);
 
-	mt2701_afe_disable_i2s(afe, i2s_num, stream_dir);
+	mt2701_afe_disable_i2s(afe, i2s_path, stream_dir);
 
 	return 0;
 }
@@ -145,12 +122,11 @@ static int mt2701_afe_i2s_path_shutdown(struct snd_pcm_substream *substream,
 static void mt2701_afe_i2s_shutdown(struct snd_pcm_substream *substream,
 				    struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt2701_afe_private *afe_priv = afe->platform_priv;
 	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
 	struct mt2701_i2s_path *i2s_path;
+	bool mode = afe_priv->soc->has_one_heart_mode;
 
 	if (i2s_num < 0)
 		return;
@@ -160,50 +136,33 @@ static void mt2701_afe_i2s_shutdown(struct snd_pcm_substream *substream,
 	if (i2s_path->occupied[substream->stream])
 		i2s_path->occupied[substream->stream] = 0;
 	else
-		goto I2S_UNSTART;
+		goto exit;
 
-	mt2701_afe_i2s_path_shutdown(substream, dai, i2s_num, 0);
+	mt2701_afe_i2s_path_disable(afe, i2s_path, substream->stream);
 
 	/* need to disable i2s-out path when disable i2s-in */
 	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
-		mt2701_afe_i2s_path_shutdown(substream, dai, i2s_num, 1);
+		mt2701_afe_i2s_path_disable(afe, i2s_path, !substream->stream);
 
-I2S_UNSTART:
+exit:
 	/* disable mclk */
-	mt2701_afe_disable_mclk(afe, i2s_num);
+	mt2701_afe_disable_mclk(afe, mode ? 1 : i2s_num);
 }
 
-static int mt2701_i2s_path_prepare_enable(struct snd_pcm_substream *substream,
-					  struct snd_soc_dai *dai,
-					  int i2s_num,
-					  int dir_invert)
+static int mt2701_i2s_path_enable(struct mtk_base_afe *afe,
+				  struct mt2701_i2s_path *i2s_path,
+				  int stream_dir, int rate)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	const struct mt2701_i2s_data *i2s_data = i2s_path->i2s_data[stream_dir];
 	struct mt2701_afe_private *afe_priv = afe->platform_priv;
-	struct mt2701_i2s_path *i2s_path = &afe_priv->i2s_path[i2s_num];
-	const struct mt2701_i2s_data *i2s_data;
-	struct snd_pcm_runtime * const runtime = substream->runtime;
 	int reg, fs, w_len = 1; /* now we support bck 64bits only */
-	int stream_dir = substream->stream;
-	unsigned int mask = 0, val = 0;
-
-	if (dir_invert) {
-		if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK)
-			stream_dir = SNDRV_PCM_STREAM_CAPTURE;
-		else
-			stream_dir = SNDRV_PCM_STREAM_PLAYBACK;
-	}
-	i2s_data = i2s_path->i2s_data[stream_dir];
+	unsigned int mask, val;
 
 	/* no need to enable if already done */
-	i2s_path->on[stream_dir]++;
-
-	if (i2s_path->on[stream_dir] != 1)
+	if (++i2s_path->on[stream_dir] != 1)
 		return 0;
 
-	fs = mt2701_afe_i2s_fs(runtime->rate);
+	fs = mt2701_afe_i2s_fs(rate);
 
 	mask = ASYS_I2S_CON_FS |
 	       ASYS_I2S_CON_I2S_COUPLE_MODE | /* 0 */
@@ -217,22 +176,24 @@ static int mt2701_i2s_path_prepare_enable(struct snd_pcm_substream *substream,
 	if (stream_dir == SNDRV_PCM_STREAM_CAPTURE) {
 		mask |= ASYS_I2S_IN_PHASE_FIX;
 		val |= ASYS_I2S_IN_PHASE_FIX;
+		reg = ASMI_TIMING_CON1;
+	} else {
+		if (afe_priv->soc->has_one_heart_mode) {
+			mask |= ASYS_I2S_CON_ONE_HEART_MODE;
+			val |= ASYS_I2S_CON_ONE_HEART_MODE;
+		}
+		reg = ASMO_TIMING_CON1;
 	}
 
 	regmap_update_bits(afe->regmap, i2s_data->i2s_ctrl_reg, mask, val);
 
-	if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK)
-		reg = ASMO_TIMING_CON1;
-	else
-		reg = ASMI_TIMING_CON1;
-
 	regmap_update_bits(afe->regmap, reg,
 			   i2s_data->i2s_asrc_fs_mask
 			   << i2s_data->i2s_asrc_fs_shift,
 			   fs << i2s_data->i2s_asrc_fs_shift);
 
 	/* enable i2s */
-	mt2701_afe_enable_i2s(afe, i2s_num, stream_dir);
+	mt2701_afe_enable_i2s(afe, i2s_path, stream_dir);
 
 	/* reset i2s hw status before enable */
 	regmap_update_bits(afe->regmap, i2s_data->i2s_ctrl_reg,
@@ -249,45 +210,33 @@ static int mt2701_i2s_path_prepare_enable(struct snd_pcm_substream *substream,
 static int mt2701_afe_i2s_prepare(struct snd_pcm_substream *substream,
 				  struct snd_soc_dai *dai)
 {
-	int clk_domain;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt2701_afe_private *afe_priv = afe->platform_priv;
-	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+	int ret, i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
 	struct mt2701_i2s_path *i2s_path;
-	int mclk_rate;
+	bool mode = afe_priv->soc->has_one_heart_mode;
 
 	if (i2s_num < 0)
 		return i2s_num;
 
 	i2s_path = &afe_priv->i2s_path[i2s_num];
-	mclk_rate = i2s_path->mclk_rate;
 
 	if (i2s_path->occupied[substream->stream])
 		return -EBUSY;
+
+	ret = mt2701_mclk_configuration(afe, mode ? 1 : i2s_num);
+	if (ret)
+		return ret;
+
 	i2s_path->occupied[substream->stream] = 1;
 
-	if (MT2701_PLL_DOMAIN_0_RATE % mclk_rate == 0) {
-		clk_domain = 0;
-	} else if (MT2701_PLL_DOMAIN_1_RATE % mclk_rate == 0) {
-		clk_domain = 1;
-	} else {
-		dev_err(dai->dev, "%s() bad mclk rate %d\n",
-			__func__, mclk_rate);
-		return -EINVAL;
-	}
-	mt2701_mclk_configuration(afe, i2s_num, clk_domain, mclk_rate);
+	/* need to enable i2s-out path when enable i2s-in */
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+		mt2701_i2s_path_enable(afe, i2s_path, !substream->stream,
+				       substream->runtime->rate);
 
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		mt2701_i2s_path_prepare_enable(substream, dai, i2s_num, 0);
-	} else {
-		/* need to enable i2s-out path when enable i2s-in */
-		/* prepare for another direction "out" */
-		mt2701_i2s_path_prepare_enable(substream, dai, i2s_num, 1);
-		/* prepare for "in" */
-		mt2701_i2s_path_prepare_enable(substream, dai, i2s_num, 0);
-	}
+	mt2701_i2s_path_enable(afe, i2s_path, substream->stream,
+			       substream->runtime->rate);
 
 	return 0;
 }
@@ -295,30 +244,29 @@ static int mt2701_afe_i2s_prepare(struct snd_pcm_substream *substream,
 static int mt2701_afe_i2s_set_sysclk(struct snd_soc_dai *dai, int clk_id,
 				     unsigned int freq, int dir)
 {
-	struct mtk_base_afe *afe = dev_get_drvdata(dai->dev);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt2701_afe_private *afe_priv = afe->platform_priv;
 	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+	bool mode = afe_priv->soc->has_one_heart_mode;
 
 	if (i2s_num < 0)
 		return i2s_num;
 
 	/* mclk */
 	if (dir == SND_SOC_CLOCK_IN) {
-		dev_warn(dai->dev,
-			 "%s() warning: mt2701 doesn't support mclk input\n",
-			__func__);
+		dev_warn(dai->dev, "The SoCs doesn't support mclk input\n");
 		return -EINVAL;
 	}
-	afe_priv->i2s_path[i2s_num].mclk_rate = freq;
+
+	afe_priv->i2s_path[mode ? 1 : i2s_num].mclk_rate = freq;
+
 	return 0;
 }
 
 static int mt2701_btmrg_startup(struct snd_pcm_substream *substream,
 				struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt2701_afe_private *afe_priv = afe->platform_priv;
 	int ret;
 
@@ -327,6 +275,7 @@ static int mt2701_btmrg_startup(struct snd_pcm_substream *substream,
 		return ret;
 
 	afe_priv->mrg_enable[substream->stream] = 1;
+
 	return 0;
 }
 
@@ -334,17 +283,14 @@ static int mt2701_btmrg_hw_params(struct snd_pcm_substream *substream,
 				  struct snd_pcm_hw_params *params,
 				  struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	int stream_fs;
 	u32 val, msk;
 
 	stream_fs = params_rate(params);
 
-	if ((stream_fs != 8000) && (stream_fs != 16000)) {
-		dev_err(afe->dev, "%s() btmgr not support this stream_fs %d\n",
-			__func__, stream_fs);
+	if (stream_fs != 8000 && stream_fs != 16000) {
+		dev_err(afe->dev, "unsupported rate %d\n", stream_fs);
 		return -EINVAL;
 	}
 
@@ -378,9 +324,7 @@ static int mt2701_btmrg_hw_params(struct snd_pcm_substream *substream,
 static void mt2701_btmrg_shutdown(struct snd_pcm_substream *substream,
 				  struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt2701_afe_private *afe_priv = afe->platform_priv;
 
 	/* if the other direction stream is not occupied */
@@ -393,28 +337,26 @@ static void mt2701_btmrg_shutdown(struct snd_pcm_substream *substream,
 				   AFE_MRGIF_CON_MRG_I2S_EN, 0);
 		mt2701_disable_btmrg_clk(afe);
 	}
+
 	afe_priv->mrg_enable[substream->stream] = 0;
 }
 
 static int mt2701_simple_fe_startup(struct snd_pcm_substream *substream,
 				    struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
-	int stream_dir = substream->stream;
-	int memif_num = rtd->cpu_dai->id;
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mtk_base_afe_memif *memif_tmp;
+	int stream_dir = substream->stream;
 
 	/* can't run single DL & DLM at the same time */
 	if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK) {
 		memif_tmp = &afe->memif[MT2701_MEMIF_DLM];
 		if (memif_tmp->substream) {
-			dev_warn(afe->dev, "%s memif is not available, stream_dir %d, memif_num %d\n",
-				 __func__, stream_dir, memif_num);
+			dev_warn(afe->dev, "memif is not available");
 			return -EBUSY;
 		}
 	}
+
 	return mtk_afe_fe_startup(substream, dai);
 }
 
@@ -422,27 +364,23 @@ static int mt2701_simple_fe_hw_params(struct snd_pcm_substream *substream,
 				      struct snd_pcm_hw_params *params,
 				      struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	int stream_dir = substream->stream;
 
 	/* single DL use PAIR_INTERLEAVE */
-	if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK) {
+	if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK)
 		regmap_update_bits(afe->regmap,
 				   AFE_MEMIF_PBUF_SIZE,
 				   AFE_MEMIF_PBUF_SIZE_DLM_MASK,
 				   AFE_MEMIF_PBUF_SIZE_PAIR_INTERLEAVE);
-	}
+
 	return mtk_afe_fe_hw_params(substream, params, dai);
 }
 
 static int mt2701_dlm_fe_startup(struct snd_pcm_substream *substream,
 				 struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mtk_base_afe_memif *memif_tmp;
 	const struct mtk_base_memif_data *memif_data;
 	int i;
@@ -468,9 +406,7 @@ static int mt2701_dlm_fe_startup(struct snd_pcm_substream *substream,
 static void mt2701_dlm_fe_shutdown(struct snd_pcm_substream *substream,
 				   struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	const struct mtk_base_memif_data *memif_data;
 	int i;
 
@@ -481,6 +417,7 @@ static void mt2701_dlm_fe_shutdown(struct snd_pcm_substream *substream,
 				   1 << memif_data->agent_disable_shift,
 				   1 << memif_data->agent_disable_shift);
 	}
+
 	return mtk_afe_fe_shutdown(substream, dai);
 }
 
@@ -488,9 +425,7 @@ static int mt2701_dlm_fe_hw_params(struct snd_pcm_substream *substream,
 				   struct snd_pcm_hw_params *params,
 				   struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	int channels = params_channels(params);
 
 	regmap_update_bits(afe->regmap,
@@ -512,9 +447,7 @@ static int mt2701_dlm_fe_hw_params(struct snd_pcm_substream *substream,
 static int mt2701_dlm_fe_trigger(struct snd_pcm_substream *substream,
 				 int cmd, struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mtk_base_afe_memif *memif_tmp = &afe->memif[MT2701_MEMIF_DL1];
 
 	switch (cmd) {
@@ -547,6 +480,7 @@ static int mt2701_memif_fs(struct snd_pcm_substream *substream,
 		fs = mt2701_afe_i2s_fs(rate);
 	else
 		fs = (rate == 16000 ? 1 : 0);
+
 	return fs;
 }
 
@@ -1024,7 +958,17 @@ static const struct snd_soc_dapm_route mt2701_afe_pcm_routes[] = {
 	{ "O31", "I35 Switch", "I35" },
 };
 
+static int mt2701_afe_pcm_probe(struct snd_soc_component *component)
+{
+	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+
+	snd_soc_component_init_regmap(component, afe->regmap);
+
+	return 0;
+}
+
 static const struct snd_soc_component_driver mt2701_afe_pcm_dai_component = {
+	.probe = mt2701_afe_pcm_probe,
 	.name = "mt2701-afe-pcm-dai",
 	.dapm_widgets = mt2701_afe_pcm_widgets,
 	.num_dapm_widgets = ARRAY_SIZE(mt2701_afe_pcm_widgets),
@@ -1324,63 +1268,24 @@ static const struct mtk_base_irq_data irq_data[MT2701_IRQ_ASYS_END] = {
 	}
 };
 
-static const struct mt2701_i2s_data mt2701_i2s_data[MT2701_I2S_NUM][2] = {
+static const struct mt2701_i2s_data mt2701_i2s_data[][2] = {
 	{
-		{
-			.i2s_ctrl_reg = ASYS_I2SO1_CON,
-			.i2s_asrc_fs_shift = 0,
-			.i2s_asrc_fs_mask = 0x1f,
-
-		},
-		{
-			.i2s_ctrl_reg = ASYS_I2SIN1_CON,
-			.i2s_asrc_fs_shift = 0,
-			.i2s_asrc_fs_mask = 0x1f,
-
-		},
+		{ ASYS_I2SO1_CON, 0, 0x1f },
+		{ ASYS_I2SIN1_CON, 0, 0x1f },
 	},
 	{
-		{
-			.i2s_ctrl_reg = ASYS_I2SO2_CON,
-			.i2s_asrc_fs_shift = 5,
-			.i2s_asrc_fs_mask = 0x1f,
-
-		},
-		{
-			.i2s_ctrl_reg = ASYS_I2SIN2_CON,
-			.i2s_asrc_fs_shift = 5,
-			.i2s_asrc_fs_mask = 0x1f,
-
-		},
+		{ ASYS_I2SO2_CON, 5, 0x1f },
+		{ ASYS_I2SIN2_CON, 5, 0x1f },
 	},
 	{
-		{
-			.i2s_ctrl_reg = ASYS_I2SO3_CON,
-			.i2s_asrc_fs_shift = 10,
-			.i2s_asrc_fs_mask = 0x1f,
-
-		},
-		{
-			.i2s_ctrl_reg = ASYS_I2SIN3_CON,
-			.i2s_asrc_fs_shift = 10,
-			.i2s_asrc_fs_mask = 0x1f,
-
-		},
+		{ ASYS_I2SO3_CON, 10, 0x1f },
+		{ ASYS_I2SIN3_CON, 10, 0x1f },
 	},
 	{
-		{
-			.i2s_ctrl_reg = ASYS_I2SO4_CON,
-			.i2s_asrc_fs_shift = 15,
-			.i2s_asrc_fs_mask = 0x1f,
-
-		},
-		{
-			.i2s_ctrl_reg = ASYS_I2SIN4_CON,
-			.i2s_asrc_fs_shift = 15,
-			.i2s_asrc_fs_mask = 0x1f,
-
-		},
+		{ ASYS_I2SO4_CON, 15, 0x1f },
+		{ ASYS_I2SIN4_CON, 15, 0x1f },
 	},
+	/* TODO - extend control registers supported by newer SoCs */
 };
 
 static irqreturn_t mt2701_asys_isr(int irq_id, void *dev)
@@ -1398,10 +1303,12 @@ static irqreturn_t mt2701_asys_isr(int irq_id, void *dev)
 		memif = &afe->memif[id];
 		if (memif->irq_usage < 0)
 			continue;
+
 		irq = &afe->irqs[memif->irq_usage];
-		if (status & 1 << (irq->irq_data->irq_clr_shift))
+		if (status & 1 << irq->irq_data->irq_clr_shift)
 			snd_pcm_period_elapsed(memif->substream);
 	}
+
 	return IRQ_HANDLED;
 }
 
@@ -1419,22 +1326,6 @@ static int mt2701_afe_runtime_resume(struct device *dev)
 	return mt2701_afe_enable_clock(afe);
 }
 
-static int mt2701_afe_add_component(struct mtk_base_afe *afe)
-{
-	struct snd_soc_component *component;
-
-	component = kzalloc(sizeof(*component), GFP_KERNEL);
-	if (!component)
-		return -ENOMEM;
-
-	component->regmap = afe->regmap;
-
-	return snd_soc_add_component(afe->dev, component,
-				     &mt2701_afe_pcm_dai_component,
-				     mt2701_afe_pcm_dais,
-				     ARRAY_SIZE(mt2701_afe_pcm_dais));
-}
-
 static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev)
 {
 	struct mtk_base_afe *afe;
@@ -1452,9 +1343,16 @@ static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	afe_priv = afe->platform_priv;
+	afe_priv->soc = of_device_get_match_data(&pdev->dev);
 	afe->dev = &pdev->dev;
 	dev = afe->dev;
 
+	afe_priv->i2s_path = devm_kzalloc(dev, afe_priv->soc->i2s_num *
+					  sizeof(struct mt2701_i2s_path),
+					  GFP_KERNEL);
+	if (!afe_priv->i2s_path)
+		return -ENOMEM;
+
 	irq_id = platform_get_irq_byname(pdev, "asys");
 	if (irq_id < 0) {
 		dev_err(dev, "unable to get ASYS IRQ\n");
@@ -1499,11 +1397,11 @@ static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev)
 		afe->irqs[i].irq_data = &irq_data[i];
 
 	/* I2S initialize */
-	for (i = 0; i < MT2701_I2S_NUM; i++) {
-		afe_priv->i2s_path[i].i2s_data[I2S_OUT]
-			= &mt2701_i2s_data[i][I2S_OUT];
-		afe_priv->i2s_path[i].i2s_data[I2S_IN]
-			= &mt2701_i2s_data[i][I2S_IN];
+	for (i = 0; i < afe_priv->soc->i2s_num; i++) {
+		afe_priv->i2s_path[i].i2s_data[SNDRV_PCM_STREAM_PLAYBACK] =
+			&mt2701_i2s_data[i][SNDRV_PCM_STREAM_PLAYBACK];
+		afe_priv->i2s_path[i].i2s_data[SNDRV_PCM_STREAM_CAPTURE] =
+			&mt2701_i2s_data[i][SNDRV_PCM_STREAM_CAPTURE];
 	}
 
 	afe->mtk_afe_hardware = &mt2701_afe_hardware;
@@ -1538,7 +1436,10 @@ static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev)
 		goto err_platform;
 	}
 
-	ret = mt2701_afe_add_component(afe);
+	ret = devm_snd_soc_register_component(&pdev->dev,
+					 &mt2701_afe_pcm_dai_component,
+					 mt2701_afe_pcm_dais,
+					 ARRAY_SIZE(mt2701_afe_pcm_dais));
 	if (ret) {
 		dev_warn(dev, "err_dai_component\n");
 		goto err_platform;
@@ -1564,8 +1465,18 @@ static int mt2701_afe_pcm_dev_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct mt2701_soc_variants mt2701_soc_v1 = {
+	.i2s_num = 4,
+};
+
+static const struct mt2701_soc_variants mt2701_soc_v2 = {
+	.has_one_heart_mode = true,
+	.i2s_num = 4,
+};
+
 static const struct of_device_id mt2701_afe_pcm_dt_match[] = {
-	{ .compatible = "mediatek,mt2701-audio", },
+	{ .compatible = "mediatek,mt2701-audio", .data = &mt2701_soc_v1 },
+	{ .compatible = "mediatek,mt7622-audio", .data = &mt2701_soc_v2 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, mt2701_afe_pcm_dt_match);
diff --git a/sound/soc/mediatek/mt2701/mt2701-cs42448.c b/sound/soc/mediatek/mt2701/mt2701-cs42448.c
index 70f61d53fe05..666282b865a8 100644
--- a/sound/soc/mediatek/mt2701/mt2701-cs42448.c
+++ b/sound/soc/mediatek/mt2701/mt2701-cs42448.c
@@ -1,19 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mt2701-cs42448.c  --  MT2701 CS42448 ALSA SoC machine driver
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Ir Lian <ir.lian@mediatek.com>
- *              Garlic Tseng <garlic.tseng@mediatek.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ *	   Garlic Tseng <garlic.tseng@mediatek.com>
  */
 
 #include <linux/module.h>
diff --git a/sound/soc/mediatek/mt2701/mt2701-reg.h b/sound/soc/mediatek/mt2701/mt2701-reg.h
index 18e676974f22..c84d14cdd7ae 100644
--- a/sound/soc/mediatek/mt2701/mt2701-reg.h
+++ b/sound/soc/mediatek/mt2701/mt2701-reg.h
@@ -1,17 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * mt2701-reg.h  --  Mediatek 2701 audio driver reg definition
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Garlic Tseng <garlic.tseng@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _MT2701_REG_H_
@@ -138,6 +130,7 @@
 #define ASYS_I2S_CON_FS_SET(x)		((x) << 8)
 #define ASYS_I2S_CON_RESET		(0x1 << 30)
 #define ASYS_I2S_CON_I2S_EN		(0x1 << 0)
+#define ASYS_I2S_CON_ONE_HEART_MODE	(0x1 << 16)
 #define ASYS_I2S_CON_I2S_COUPLE_MODE	(0x1 << 17)
 /* 0:EIAJ 1:I2S */
 #define ASYS_I2S_CON_I2S_MODE		(0x1 << 3)
diff --git a/sound/soc/mediatek/mt2701/mt2701-wm8960.c b/sound/soc/mediatek/mt2701/mt2701-wm8960.c
index a08ce2323bdc..89f34efd9747 100644
--- a/sound/soc/mediatek/mt2701/mt2701-wm8960.c
+++ b/sound/soc/mediatek/mt2701/mt2701-wm8960.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mt2701-wm8960.c  --  MT2701 WM8960 ALSA SoC machine driver
  *
  * Copyright (c) 2017 MediaTek Inc.
  * Author: Ryder Lee <ryder.lee@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>
diff --git a/sound/soc/mediatek/mt6797/Makefile b/sound/soc/mediatek/mt6797/Makefile
new file mode 100644
index 000000000000..bf6e179ea93f
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/Makefile
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# platform driver
+snd-soc-mt6797-afe-objs := \
+	mt6797-afe-pcm.o \
+	mt6797-afe-clk.o \
+	mt6797-dai-pcm.o \
+	mt6797-dai-hostless.o \
+	mt6797-dai-adda.o
+
+obj-$(CONFIG_SND_SOC_MT6797) += snd-soc-mt6797-afe.o
+
+# machine driver
+obj-$(CONFIG_SND_SOC_MT6797_MT6351) += mt6797-mt6351.o
diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-clk.c b/sound/soc/mediatek/mt6797/mt6797-afe-clk.c
new file mode 100644
index 000000000000..6f3e6acfcfab
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-clk.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// mt6797-afe-clk.c  --  Mediatek 6797 afe clock ctrl
+//
+// Copyright (c) 2018 MediaTek Inc.
+// Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+
+#include <linux/clk.h>
+
+#include "mt6797-afe-common.h"
+#include "mt6797-afe-clk.h"
+
+enum {
+	CLK_INFRA_SYS_AUD,
+	CLK_INFRA_SYS_AUD_26M,
+	CLK_TOP_MUX_AUD,
+	CLK_TOP_MUX_AUD_BUS,
+	CLK_TOP_SYSPLL3_D4,
+	CLK_TOP_SYSPLL1_D4,
+	CLK_CLK26M,
+	CLK_NUM
+};
+
+static const char *aud_clks[CLK_NUM] = {
+	[CLK_INFRA_SYS_AUD] = "infra_sys_audio_clk",
+	[CLK_INFRA_SYS_AUD_26M] = "infra_sys_audio_26m",
+	[CLK_TOP_MUX_AUD] = "top_mux_audio",
+	[CLK_TOP_MUX_AUD_BUS] = "top_mux_aud_intbus",
+	[CLK_TOP_SYSPLL3_D4] = "top_sys_pll3_d4",
+	[CLK_TOP_SYSPLL1_D4] = "top_sys_pll1_d4",
+	[CLK_CLK26M] = "top_clk26m_clk",
+};
+
+int mt6797_init_clock(struct mtk_base_afe *afe)
+{
+	struct mt6797_afe_private *afe_priv = afe->platform_priv;
+	int i;
+
+	afe_priv->clk = devm_kcalloc(afe->dev, CLK_NUM, sizeof(*afe_priv->clk),
+				     GFP_KERNEL);
+	if (!afe_priv->clk)
+		return -ENOMEM;
+
+	for (i = 0; i < CLK_NUM; i++) {
+		afe_priv->clk[i] = devm_clk_get(afe->dev, aud_clks[i]);
+		if (IS_ERR(afe_priv->clk[i])) {
+			dev_err(afe->dev, "%s(), devm_clk_get %s fail, ret %ld\n",
+				__func__, aud_clks[i],
+				PTR_ERR(afe_priv->clk[i]));
+			return PTR_ERR(afe_priv->clk[i]);
+		}
+	}
+
+	return 0;
+}
+
+int mt6797_afe_enable_clock(struct mtk_base_afe *afe)
+{
+	struct mt6797_afe_private *afe_priv = afe->platform_priv;
+	int ret;
+
+	ret = clk_prepare_enable(afe_priv->clk[CLK_INFRA_SYS_AUD]);
+	if (ret) {
+		dev_err(afe->dev, "%s(), clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[CLK_INFRA_SYS_AUD], ret);
+		goto CLK_INFRA_SYS_AUDIO_ERR;
+	}
+
+	ret = clk_prepare_enable(afe_priv->clk[CLK_INFRA_SYS_AUD_26M]);
+	if (ret) {
+		dev_err(afe->dev, "%s(), clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[CLK_INFRA_SYS_AUD_26M], ret);
+		goto CLK_INFRA_SYS_AUD_26M_ERR;
+	}
+
+	ret = clk_prepare_enable(afe_priv->clk[CLK_TOP_MUX_AUD]);
+	if (ret) {
+		dev_err(afe->dev, "%s(), clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[CLK_TOP_MUX_AUD], ret);
+		goto CLK_MUX_AUDIO_ERR;
+	}
+
+	ret = clk_set_parent(afe_priv->clk[CLK_TOP_MUX_AUD],
+			     afe_priv->clk[CLK_CLK26M]);
+	if (ret) {
+		dev_err(afe->dev, "%s(), clk_set_parent %s-%s fail %d\n",
+			__func__, aud_clks[CLK_TOP_MUX_AUD],
+			aud_clks[CLK_CLK26M], ret);
+		goto CLK_MUX_AUDIO_ERR;
+	}
+
+	ret = clk_prepare_enable(afe_priv->clk[CLK_TOP_MUX_AUD_BUS]);
+	if (ret) {
+		dev_err(afe->dev, "%s(), clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[CLK_TOP_MUX_AUD_BUS], ret);
+		goto CLK_MUX_AUDIO_INTBUS_ERR;
+	}
+
+	return ret;
+
+CLK_MUX_AUDIO_INTBUS_ERR:
+	clk_disable_unprepare(afe_priv->clk[CLK_TOP_MUX_AUD_BUS]);
+CLK_MUX_AUDIO_ERR:
+	clk_disable_unprepare(afe_priv->clk[CLK_TOP_MUX_AUD]);
+CLK_INFRA_SYS_AUD_26M_ERR:
+	clk_disable_unprepare(afe_priv->clk[CLK_INFRA_SYS_AUD_26M]);
+CLK_INFRA_SYS_AUDIO_ERR:
+	clk_disable_unprepare(afe_priv->clk[CLK_INFRA_SYS_AUD]);
+
+	return 0;
+}
+
+int mt6797_afe_disable_clock(struct mtk_base_afe *afe)
+{
+	struct mt6797_afe_private *afe_priv = afe->platform_priv;
+
+	clk_disable_unprepare(afe_priv->clk[CLK_TOP_MUX_AUD_BUS]);
+	clk_disable_unprepare(afe_priv->clk[CLK_TOP_MUX_AUD]);
+	clk_disable_unprepare(afe_priv->clk[CLK_INFRA_SYS_AUD_26M]);
+	clk_disable_unprepare(afe_priv->clk[CLK_INFRA_SYS_AUD]);
+
+	return 0;
+}
diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-clk.h b/sound/soc/mediatek/mt6797/mt6797-afe-clk.h
new file mode 100644
index 000000000000..a6f0cb572711
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-clk.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mt6797-afe-clk.h  --  Mediatek 6797 afe clock ctrl definition
+ *
+ * Copyright (c) 2018 MediaTek Inc.
+ * Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+ */
+
+#ifndef _MT6797_AFE_CLK_H_
+#define _MT6797_AFE_CLK_H_
+
+struct mtk_base_afe;
+
+int mt6797_init_clock(struct mtk_base_afe *afe);
+int mt6797_afe_enable_clock(struct mtk_base_afe *afe);
+int mt6797_afe_disable_clock(struct mtk_base_afe *afe);
+#endif
diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-common.h b/sound/soc/mediatek/mt6797/mt6797-afe-common.h
new file mode 100644
index 000000000000..22eb7b455cf1
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-common.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mt6797-afe-common.h  --  Mediatek 6797 audio driver definitions
+ *
+ * Copyright (c) 2018 MediaTek Inc.
+ * Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+ */
+
+#ifndef _MT_6797_AFE_COMMON_H_
+#define _MT_6797_AFE_COMMON_H_
+
+#include <sound/soc.h>
+#include <linux/regmap.h>
+#include "../common/mtk-base-afe.h"
+
+enum {
+	MT6797_MEMIF_DL1,
+	MT6797_MEMIF_DL2,
+	MT6797_MEMIF_DL3,
+	MT6797_MEMIF_VUL,
+	MT6797_MEMIF_AWB,
+	MT6797_MEMIF_VUL12,
+	MT6797_MEMIF_DAI,
+	MT6797_MEMIF_MOD_DAI,
+	MT6797_MEMIF_NUM,
+	MT6797_DAI_ADDA = MT6797_MEMIF_NUM,
+	MT6797_DAI_PCM_1,
+	MT6797_DAI_PCM_2,
+	MT6797_DAI_HOSTLESS_LPBK,
+	MT6797_DAI_HOSTLESS_SPEECH,
+	MT6797_DAI_NUM,
+};
+
+enum {
+	MT6797_IRQ_1,
+	MT6797_IRQ_2,
+	MT6797_IRQ_3,
+	MT6797_IRQ_4,
+	MT6797_IRQ_7,
+	MT6797_IRQ_NUM,
+};
+
+struct clk;
+
+struct mt6797_afe_private {
+	struct clk **clk;
+};
+
+unsigned int mt6797_general_rate_transform(struct device *dev,
+					   unsigned int rate);
+unsigned int mt6797_rate_transform(struct device *dev,
+				   unsigned int rate, int aud_blk);
+
+/* dai register */
+int mt6797_dai_adda_register(struct mtk_base_afe *afe);
+int mt6797_dai_pcm_register(struct mtk_base_afe *afe);
+int mt6797_dai_hostless_register(struct mtk_base_afe *afe);
+#endif
diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c b/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
new file mode 100644
index 000000000000..6c5dd9fc9976
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
@@ -0,0 +1,914 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Mediatek ALSA SoC AFE platform driver for 6797
+//
+// Copyright (c) 2018 MediaTek Inc.
+// Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pm_runtime.h>
+
+#include "mt6797-afe-common.h"
+#include "mt6797-afe-clk.h"
+#include "mt6797-interconnection.h"
+#include "mt6797-reg.h"
+#include "../common/mtk-afe-platform-driver.h"
+#include "../common/mtk-afe-fe-dai.h"
+
+enum {
+	MTK_AFE_RATE_8K = 0,
+	MTK_AFE_RATE_11K = 1,
+	MTK_AFE_RATE_12K = 2,
+	MTK_AFE_RATE_384K = 3,
+	MTK_AFE_RATE_16K = 4,
+	MTK_AFE_RATE_22K = 5,
+	MTK_AFE_RATE_24K = 6,
+	MTK_AFE_RATE_130K = 7,
+	MTK_AFE_RATE_32K = 8,
+	MTK_AFE_RATE_44K = 9,
+	MTK_AFE_RATE_48K = 10,
+	MTK_AFE_RATE_88K = 11,
+	MTK_AFE_RATE_96K = 12,
+	MTK_AFE_RATE_174K = 13,
+	MTK_AFE_RATE_192K = 14,
+	MTK_AFE_RATE_260K = 15,
+};
+
+enum {
+	MTK_AFE_DAI_MEMIF_RATE_8K = 0,
+	MTK_AFE_DAI_MEMIF_RATE_16K = 1,
+	MTK_AFE_DAI_MEMIF_RATE_32K = 2,
+};
+
+enum {
+	MTK_AFE_PCM_RATE_8K = 0,
+	MTK_AFE_PCM_RATE_16K = 1,
+	MTK_AFE_PCM_RATE_32K = 2,
+	MTK_AFE_PCM_RATE_48K = 3,
+};
+
+unsigned int mt6797_general_rate_transform(struct device *dev,
+					   unsigned int rate)
+{
+	switch (rate) {
+	case 8000:
+		return MTK_AFE_RATE_8K;
+	case 11025:
+		return MTK_AFE_RATE_11K;
+	case 12000:
+		return MTK_AFE_RATE_12K;
+	case 16000:
+		return MTK_AFE_RATE_16K;
+	case 22050:
+		return MTK_AFE_RATE_22K;
+	case 24000:
+		return MTK_AFE_RATE_24K;
+	case 32000:
+		return MTK_AFE_RATE_32K;
+	case 44100:
+		return MTK_AFE_RATE_44K;
+	case 48000:
+		return MTK_AFE_RATE_48K;
+	case 88200:
+		return MTK_AFE_RATE_88K;
+	case 96000:
+		return MTK_AFE_RATE_96K;
+	case 130000:
+		return MTK_AFE_RATE_130K;
+	case 176400:
+		return MTK_AFE_RATE_174K;
+	case 192000:
+		return MTK_AFE_RATE_192K;
+	case 260000:
+		return MTK_AFE_RATE_260K;
+	default:
+		dev_warn(dev, "%s(), rate %u invalid, use %d!!!\n",
+			 __func__, rate, MTK_AFE_RATE_48K);
+		return MTK_AFE_RATE_48K;
+	}
+}
+
+static unsigned int dai_memif_rate_transform(struct device *dev,
+					     unsigned int rate)
+{
+	switch (rate) {
+	case 8000:
+		return MTK_AFE_DAI_MEMIF_RATE_8K;
+	case 16000:
+		return MTK_AFE_DAI_MEMIF_RATE_16K;
+	case 32000:
+		return MTK_AFE_DAI_MEMIF_RATE_32K;
+	default:
+		dev_warn(dev, "%s(), rate %u invalid, use %d!!!\n",
+			 __func__, rate, MTK_AFE_DAI_MEMIF_RATE_16K);
+		return MTK_AFE_DAI_MEMIF_RATE_16K;
+	}
+}
+
+unsigned int mt6797_rate_transform(struct device *dev,
+				   unsigned int rate, int aud_blk)
+{
+	switch (aud_blk) {
+	case MT6797_MEMIF_DAI:
+	case MT6797_MEMIF_MOD_DAI:
+		return dai_memif_rate_transform(dev, rate);
+	default:
+		return mt6797_general_rate_transform(dev, rate);
+	}
+}
+
+static const struct snd_pcm_hardware mt6797_afe_hardware = {
+	.info = SNDRV_PCM_INFO_MMAP |
+		SNDRV_PCM_INFO_INTERLEAVED |
+		SNDRV_PCM_INFO_MMAP_VALID,
+	.formats = SNDRV_PCM_FMTBIT_S16_LE |
+		   SNDRV_PCM_FMTBIT_S24_LE |
+		   SNDRV_PCM_FMTBIT_S32_LE,
+	.period_bytes_min = 256,
+	.period_bytes_max = 4 * 48 * 1024,
+	.periods_min = 2,
+	.periods_max = 256,
+	.buffer_bytes_max = 8 * 48 * 1024,
+	.fifo_size = 0,
+};
+
+static int mt6797_memif_fs(struct snd_pcm_substream *substream,
+			   unsigned int rate)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_component *component =
+		snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
+	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	int id = rtd->cpu_dai->id;
+
+	return mt6797_rate_transform(afe->dev, rate, id);
+}
+
+static int mt6797_irq_fs(struct snd_pcm_substream *substream, unsigned int rate)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_component *component =
+		snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
+	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+
+	return mt6797_general_rate_transform(afe->dev, rate);
+}
+
+#define MTK_PCM_RATES (SNDRV_PCM_RATE_8000_48000 |\
+		       SNDRV_PCM_RATE_88200 |\
+		       SNDRV_PCM_RATE_96000 |\
+		       SNDRV_PCM_RATE_176400 |\
+		       SNDRV_PCM_RATE_192000)
+
+#define MTK_PCM_DAI_RATES (SNDRV_PCM_RATE_8000 |\
+			   SNDRV_PCM_RATE_16000 |\
+			   SNDRV_PCM_RATE_32000)
+
+#define MTK_PCM_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
+			 SNDRV_PCM_FMTBIT_S24_LE |\
+			 SNDRV_PCM_FMTBIT_S32_LE)
+
+static struct snd_soc_dai_driver mt6797_memif_dai_driver[] = {
+	/* FE DAIs: memory intefaces to CPU */
+	{
+		.name = "DL1",
+		.id = MT6797_MEMIF_DL1,
+		.playback = {
+			.stream_name = "DL1",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_afe_fe_ops,
+	},
+	{
+		.name = "DL2",
+		.id = MT6797_MEMIF_DL2,
+		.playback = {
+			.stream_name = "DL2",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_afe_fe_ops,
+	},
+	{
+		.name = "DL3",
+		.id = MT6797_MEMIF_DL3,
+		.playback = {
+			.stream_name = "DL3",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_afe_fe_ops,
+	},
+	{
+		.name = "UL1",
+		.id = MT6797_MEMIF_VUL12,
+		.capture = {
+			.stream_name = "UL1",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_afe_fe_ops,
+	},
+	{
+		.name = "UL2",
+		.id = MT6797_MEMIF_AWB,
+		.capture = {
+			.stream_name = "UL2",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_afe_fe_ops,
+	},
+	{
+		.name = "UL3",
+		.id = MT6797_MEMIF_VUL,
+		.capture = {
+			.stream_name = "UL3",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_afe_fe_ops,
+	},
+	{
+		.name = "UL_MONO_1",
+		.id = MT6797_MEMIF_MOD_DAI,
+		.capture = {
+			.stream_name = "UL_MONO_1",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = MTK_PCM_DAI_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_afe_fe_ops,
+	},
+	{
+		.name = "UL_MONO_2",
+		.id = MT6797_MEMIF_DAI,
+		.capture = {
+			.stream_name = "UL_MONO_2",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = MTK_PCM_DAI_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_afe_fe_ops,
+	},
+};
+
+/* dma widget & routes*/
+static const struct snd_kcontrol_new memif_ul1_ch1_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN21,
+				    I_ADDA_UL_CH1, 1, 0),
+};
+
+static const struct snd_kcontrol_new memif_ul1_ch2_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN22,
+				    I_ADDA_UL_CH2, 1, 0),
+};
+
+static const struct snd_kcontrol_new memif_ul2_ch1_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN5,
+				    I_ADDA_UL_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL1_CH1", AFE_CONN5,
+				    I_DL1_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH1", AFE_CONN5,
+				    I_DL2_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL3_CH1", AFE_CONN5,
+				    I_DL3_CH1, 1, 0),
+};
+
+static const struct snd_kcontrol_new memif_ul2_ch2_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN6,
+				    I_ADDA_UL_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL1_CH2", AFE_CONN6,
+				    I_DL1_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH2", AFE_CONN6,
+				    I_DL2_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL3_CH2", AFE_CONN6,
+				    I_DL3_CH2, 1, 0),
+};
+
+static const struct snd_kcontrol_new memif_ul3_ch1_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN9,
+				    I_ADDA_UL_CH1, 1, 0),
+};
+
+static const struct snd_kcontrol_new memif_ul3_ch2_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN10,
+				    I_ADDA_UL_CH2, 1, 0),
+};
+
+static const struct snd_kcontrol_new memif_ul_mono_1_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN12,
+				    I_ADDA_UL_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN12,
+				    I_ADDA_UL_CH2, 1, 0),
+};
+
+static const struct snd_kcontrol_new memif_ul_mono_2_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN11,
+				    I_ADDA_UL_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN11,
+				    I_ADDA_UL_CH2, 1, 0),
+};
+
+static const struct snd_soc_dapm_widget mt6797_memif_widgets[] = {
+	/* memif */
+	SND_SOC_DAPM_MIXER("UL1_CH1", SND_SOC_NOPM, 0, 0,
+			   memif_ul1_ch1_mix, ARRAY_SIZE(memif_ul1_ch1_mix)),
+	SND_SOC_DAPM_MIXER("UL1_CH2", SND_SOC_NOPM, 0, 0,
+			   memif_ul1_ch2_mix, ARRAY_SIZE(memif_ul1_ch2_mix)),
+
+	SND_SOC_DAPM_MIXER("UL2_CH1", SND_SOC_NOPM, 0, 0,
+			   memif_ul2_ch1_mix, ARRAY_SIZE(memif_ul2_ch1_mix)),
+	SND_SOC_DAPM_MIXER("UL2_CH2", SND_SOC_NOPM, 0, 0,
+			   memif_ul2_ch2_mix, ARRAY_SIZE(memif_ul2_ch2_mix)),
+
+	SND_SOC_DAPM_MIXER("UL3_CH1", SND_SOC_NOPM, 0, 0,
+			   memif_ul3_ch1_mix, ARRAY_SIZE(memif_ul3_ch1_mix)),
+	SND_SOC_DAPM_MIXER("UL3_CH2", SND_SOC_NOPM, 0, 0,
+			   memif_ul3_ch2_mix, ARRAY_SIZE(memif_ul3_ch2_mix)),
+
+	SND_SOC_DAPM_MIXER("UL_MONO_1_CH1", SND_SOC_NOPM, 0, 0,
+			   memif_ul_mono_1_mix,
+			   ARRAY_SIZE(memif_ul_mono_1_mix)),
+
+	SND_SOC_DAPM_MIXER("UL_MONO_2_CH1", SND_SOC_NOPM, 0, 0,
+			   memif_ul_mono_2_mix,
+			   ARRAY_SIZE(memif_ul_mono_2_mix)),
+};
+
+static const struct snd_soc_dapm_route mt6797_memif_routes[] = {
+	/* capture */
+	{"UL1", NULL, "UL1_CH1"},
+	{"UL1", NULL, "UL1_CH2"},
+	{"UL1_CH1", "ADDA_UL_CH1", "ADDA Capture"},
+	{"UL1_CH2", "ADDA_UL_CH2", "ADDA Capture"},
+
+	{"UL2", NULL, "UL2_CH1"},
+	{"UL2", NULL, "UL2_CH2"},
+	{"UL2_CH1", "ADDA_UL_CH1", "ADDA Capture"},
+	{"UL2_CH2", "ADDA_UL_CH2", "ADDA Capture"},
+
+	{"UL3", NULL, "UL3_CH1"},
+	{"UL3", NULL, "UL3_CH2"},
+	{"UL3_CH1", "ADDA_UL_CH1", "ADDA Capture"},
+	{"UL3_CH2", "ADDA_UL_CH2", "ADDA Capture"},
+
+	{"UL_MONO_1", NULL, "UL_MONO_1_CH1"},
+	{"UL_MONO_1_CH1", "ADDA_UL_CH1", "ADDA Capture"},
+	{"UL_MONO_1_CH1", "ADDA_UL_CH2", "ADDA Capture"},
+
+	{"UL_MONO_2", NULL, "UL_MONO_2_CH1"},
+	{"UL_MONO_2_CH1", "ADDA_UL_CH1", "ADDA Capture"},
+	{"UL_MONO_2_CH1", "ADDA_UL_CH2", "ADDA Capture"},
+};
+
+static const struct snd_soc_component_driver mt6797_afe_pcm_dai_component = {
+	.name = "mt6797-afe-pcm-dai",
+};
+
+static const struct mtk_base_memif_data memif_data[MT6797_MEMIF_NUM] = {
+	[MT6797_MEMIF_DL1] = {
+		.name = "DL1",
+		.id = MT6797_MEMIF_DL1,
+		.reg_ofs_base = AFE_DL1_BASE,
+		.reg_ofs_cur = AFE_DL1_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = DL1_MODE_SFT,
+		.fs_maskbit = DL1_MODE_MASK,
+		.mono_reg = AFE_DAC_CON1,
+		.mono_shift = DL1_DATA_SFT,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = DL1_ON_SFT,
+		.hd_reg = AFE_MEMIF_HD_MODE,
+		.hd_shift = DL1_HD_SFT,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	[MT6797_MEMIF_DL2] = {
+		.name = "DL2",
+		.id = MT6797_MEMIF_DL2,
+		.reg_ofs_base = AFE_DL2_BASE,
+		.reg_ofs_cur = AFE_DL2_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = DL2_MODE_SFT,
+		.fs_maskbit = DL2_MODE_MASK,
+		.mono_reg = AFE_DAC_CON1,
+		.mono_shift = DL2_DATA_SFT,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = DL2_ON_SFT,
+		.hd_reg = AFE_MEMIF_HD_MODE,
+		.hd_shift = DL2_HD_SFT,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	[MT6797_MEMIF_DL3] = {
+		.name = "DL3",
+		.id = MT6797_MEMIF_DL3,
+		.reg_ofs_base = AFE_DL3_BASE,
+		.reg_ofs_cur = AFE_DL3_CUR,
+		.fs_reg = AFE_DAC_CON0,
+		.fs_shift = DL3_MODE_SFT,
+		.fs_maskbit = DL3_MODE_MASK,
+		.mono_reg = AFE_DAC_CON1,
+		.mono_shift = DL3_DATA_SFT,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = DL3_ON_SFT,
+		.hd_reg = AFE_MEMIF_HD_MODE,
+		.hd_shift = DL3_HD_SFT,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	[MT6797_MEMIF_VUL] = {
+		.name = "VUL",
+		.id = MT6797_MEMIF_VUL,
+		.reg_ofs_base = AFE_VUL_BASE,
+		.reg_ofs_cur = AFE_VUL_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = VUL_MODE_SFT,
+		.fs_maskbit = VUL_MODE_MASK,
+		.mono_reg = AFE_DAC_CON1,
+		.mono_shift = VUL_DATA_SFT,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = VUL_ON_SFT,
+		.hd_reg = AFE_MEMIF_HD_MODE,
+		.hd_shift = VUL_HD_SFT,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	[MT6797_MEMIF_AWB] = {
+		.name = "AWB",
+		.id = MT6797_MEMIF_AWB,
+		.reg_ofs_base = AFE_AWB_BASE,
+		.reg_ofs_cur = AFE_AWB_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = AWB_MODE_SFT,
+		.fs_maskbit = AWB_MODE_MASK,
+		.mono_reg = AFE_DAC_CON1,
+		.mono_shift = AWB_DATA_SFT,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = AWB_ON_SFT,
+		.hd_reg = AFE_MEMIF_HD_MODE,
+		.hd_shift = AWB_HD_SFT,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	[MT6797_MEMIF_VUL12] = {
+		.name = "VUL12",
+		.id = MT6797_MEMIF_VUL12,
+		.reg_ofs_base = AFE_VUL_D2_BASE,
+		.reg_ofs_cur = AFE_VUL_D2_CUR,
+		.fs_reg = AFE_DAC_CON0,
+		.fs_shift = VUL_DATA2_MODE_SFT,
+		.fs_maskbit = VUL_DATA2_MODE_MASK,
+		.mono_reg = AFE_DAC_CON0,
+		.mono_shift = VUL_DATA2_DATA_SFT,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = VUL_DATA2_ON_SFT,
+		.hd_reg = AFE_MEMIF_HD_MODE,
+		.hd_shift = VUL_DATA2_HD_SFT,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	[MT6797_MEMIF_DAI] = {
+		.name = "DAI",
+		.id = MT6797_MEMIF_DAI,
+		.reg_ofs_base = AFE_DAI_BASE,
+		.reg_ofs_cur = AFE_DAI_CUR,
+		.fs_reg = AFE_DAC_CON0,
+		.fs_shift = DAI_MODE_SFT,
+		.fs_maskbit = DAI_MODE_MASK,
+		.mono_reg = -1,
+		.mono_shift = 0,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = DAI_ON_SFT,
+		.hd_reg = AFE_MEMIF_HD_MODE,
+		.hd_shift = DAI_HD_SFT,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	[MT6797_MEMIF_MOD_DAI] = {
+		.name = "MOD_DAI",
+		.id = MT6797_MEMIF_MOD_DAI,
+		.reg_ofs_base = AFE_MOD_DAI_BASE,
+		.reg_ofs_cur = AFE_MOD_DAI_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = MOD_DAI_MODE_SFT,
+		.fs_maskbit = MOD_DAI_MODE_MASK,
+		.mono_reg = -1,
+		.mono_shift = 0,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = MOD_DAI_ON_SFT,
+		.hd_reg = AFE_MEMIF_HD_MODE,
+		.hd_shift = MOD_DAI_HD_SFT,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+};
+
+static const struct mtk_base_irq_data irq_data[MT6797_IRQ_NUM] = {
+	[MT6797_IRQ_1] = {
+		.id = MT6797_IRQ_1,
+		.irq_cnt_reg = AFE_IRQ_MCU_CNT1,
+		.irq_cnt_shift = AFE_IRQ_MCU_CNT1_SFT,
+		.irq_cnt_maskbit = AFE_IRQ_MCU_CNT1_MASK,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = IRQ1_MCU_MODE_SFT,
+		.irq_fs_maskbit = IRQ1_MCU_MODE_MASK,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = IRQ1_MCU_ON_SFT,
+		.irq_clr_reg = AFE_IRQ_MCU_CLR,
+		.irq_clr_shift = IRQ1_MCU_CLR_SFT,
+	},
+	[MT6797_IRQ_2] = {
+		.id = MT6797_IRQ_2,
+		.irq_cnt_reg = AFE_IRQ_MCU_CNT2,
+		.irq_cnt_shift = AFE_IRQ_MCU_CNT2_SFT,
+		.irq_cnt_maskbit = AFE_IRQ_MCU_CNT2_MASK,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = IRQ2_MCU_MODE_SFT,
+		.irq_fs_maskbit = IRQ2_MCU_MODE_MASK,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = IRQ2_MCU_ON_SFT,
+		.irq_clr_reg = AFE_IRQ_MCU_CLR,
+		.irq_clr_shift = IRQ2_MCU_CLR_SFT,
+	},
+	[MT6797_IRQ_3] = {
+		.id = MT6797_IRQ_3,
+		.irq_cnt_reg = AFE_IRQ_MCU_CNT3,
+		.irq_cnt_shift = AFE_IRQ_MCU_CNT3_SFT,
+		.irq_cnt_maskbit = AFE_IRQ_MCU_CNT3_MASK,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = IRQ3_MCU_MODE_SFT,
+		.irq_fs_maskbit = IRQ3_MCU_MODE_MASK,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = IRQ3_MCU_ON_SFT,
+		.irq_clr_reg = AFE_IRQ_MCU_CLR,
+		.irq_clr_shift = IRQ3_MCU_CLR_SFT,
+	},
+	[MT6797_IRQ_4] = {
+		.id = MT6797_IRQ_4,
+		.irq_cnt_reg = AFE_IRQ_MCU_CNT4,
+		.irq_cnt_shift = AFE_IRQ_MCU_CNT4_SFT,
+		.irq_cnt_maskbit = AFE_IRQ_MCU_CNT4_MASK,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = IRQ4_MCU_MODE_SFT,
+		.irq_fs_maskbit = IRQ4_MCU_MODE_MASK,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = IRQ4_MCU_ON_SFT,
+		.irq_clr_reg = AFE_IRQ_MCU_CLR,
+		.irq_clr_shift = IRQ4_MCU_CLR_SFT,
+	},
+	[MT6797_IRQ_7] = {
+		.id = MT6797_IRQ_7,
+		.irq_cnt_reg = AFE_IRQ_MCU_CNT7,
+		.irq_cnt_shift = AFE_IRQ_MCU_CNT7_SFT,
+		.irq_cnt_maskbit = AFE_IRQ_MCU_CNT7_MASK,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = IRQ7_MCU_MODE_SFT,
+		.irq_fs_maskbit = IRQ7_MCU_MODE_MASK,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = IRQ7_MCU_ON_SFT,
+		.irq_clr_reg = AFE_IRQ_MCU_CLR,
+		.irq_clr_shift = IRQ7_MCU_CLR_SFT,
+	},
+};
+
+static const struct regmap_config mt6797_afe_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = AFE_MAX_REGISTER,
+};
+
+static irqreturn_t mt6797_afe_irq_handler(int irq_id, void *dev)
+{
+	struct mtk_base_afe *afe = dev;
+	struct mtk_base_afe_irq *irq;
+	unsigned int status;
+	unsigned int mcu_en;
+	int ret;
+	int i;
+	irqreturn_t irq_ret = IRQ_HANDLED;
+
+	/* get irq that is sent to MCU */
+	regmap_read(afe->regmap, AFE_IRQ_MCU_EN, &mcu_en);
+
+	ret = regmap_read(afe->regmap, AFE_IRQ_MCU_STATUS, &status);
+	if (ret || (status & mcu_en) == 0) {
+		dev_err(afe->dev, "%s(), irq status err, ret %d, status 0x%x, mcu_en 0x%x\n",
+			__func__, ret, status, mcu_en);
+
+		/* only clear IRQ which is sent to MCU */
+		status = mcu_en & AFE_IRQ_STATUS_BITS;
+
+		irq_ret = IRQ_NONE;
+		goto err_irq;
+	}
+
+	for (i = 0; i < MT6797_MEMIF_NUM; i++) {
+		struct mtk_base_afe_memif *memif = &afe->memif[i];
+
+		if (!memif->substream)
+			continue;
+
+		irq = &afe->irqs[memif->irq_usage];
+
+		if (status & (1 << irq->irq_data->irq_en_shift))
+			snd_pcm_period_elapsed(memif->substream);
+	}
+
+err_irq:
+	/* clear irq */
+	regmap_write(afe->regmap,
+		     AFE_IRQ_MCU_CLR,
+		     status & AFE_IRQ_STATUS_BITS);
+
+	return irq_ret;
+}
+
+static int mt6797_afe_runtime_suspend(struct device *dev)
+{
+	struct mtk_base_afe *afe = dev_get_drvdata(dev);
+	unsigned int afe_on_retm;
+	int retry = 0;
+
+	/* disable AFE */
+	regmap_update_bits(afe->regmap, AFE_DAC_CON0, AFE_ON_MASK_SFT, 0x0);
+	do {
+		regmap_read(afe->regmap, AFE_DAC_CON0, &afe_on_retm);
+		if ((afe_on_retm & AFE_ON_RETM_MASK_SFT) == 0)
+			break;
+
+		udelay(10);
+	} while (++retry < 100000);
+
+	if (retry)
+		dev_warn(afe->dev, "%s(), retry %d\n", __func__, retry);
+
+	/* make sure all irq status are cleared */
+	regmap_update_bits(afe->regmap, AFE_IRQ_MCU_CLR, 0xffff, 0xffff);
+
+	return mt6797_afe_disable_clock(afe);
+}
+
+static int mt6797_afe_runtime_resume(struct device *dev)
+{
+	struct mtk_base_afe *afe = dev_get_drvdata(dev);
+	int ret;
+
+	ret = mt6797_afe_enable_clock(afe);
+	if (ret)
+		return ret;
+
+	/* irq signal to mcu only */
+	regmap_write(afe->regmap, AFE_IRQ_MCU_EN, AFE_IRQ_MCU_EN_MASK_SFT);
+
+	/* force all memif use normal mode */
+	regmap_update_bits(afe->regmap, AFE_MEMIF_HDALIGN,
+			   0x7ff << 16, 0x7ff << 16);
+	/* force cpu use normal mode when access sram data */
+	regmap_update_bits(afe->regmap, AFE_MEMIF_MSB,
+			   CPU_COMPACT_MODE_MASK_SFT, 0);
+	/* force cpu use 8_24 format when writing 32bit data */
+	regmap_update_bits(afe->regmap, AFE_MEMIF_MSB,
+			   CPU_HD_ALIGN_MASK_SFT, 0);
+
+	/* set all output port to 24bit */
+	regmap_update_bits(afe->regmap, AFE_CONN_24BIT,
+			   0x3fffffff, 0x3fffffff);
+
+	/* enable AFE */
+	regmap_update_bits(afe->regmap, AFE_DAC_CON0,
+			   AFE_ON_MASK_SFT,
+			   0x1 << AFE_ON_SFT);
+
+	return 0;
+}
+
+static int mt6797_afe_component_probe(struct snd_soc_component *component)
+{
+	return mtk_afe_add_sub_dai_control(component);
+}
+
+static const struct snd_soc_component_driver mt6797_afe_component = {
+	.name = AFE_PCM_NAME,
+	.ops = &mtk_afe_pcm_ops,
+	.pcm_new = mtk_afe_pcm_new,
+	.pcm_free = mtk_afe_pcm_free,
+	.probe = mt6797_afe_component_probe,
+};
+
+static int mt6797_afe_pcm_dev_probe(struct platform_device *pdev)
+{
+	struct mtk_base_afe *afe;
+	struct mt6797_afe_private *afe_priv;
+	struct resource *res;
+	struct device *dev;
+	int i, irq_id, ret;
+
+	afe = devm_kzalloc(&pdev->dev, sizeof(*afe), GFP_KERNEL);
+	if (!afe)
+		return -ENOMEM;
+
+	afe->platform_priv = devm_kzalloc(&pdev->dev, sizeof(*afe_priv),
+					  GFP_KERNEL);
+	if (!afe->platform_priv)
+		return -ENOMEM;
+
+	afe_priv = afe->platform_priv;
+	afe->dev = &pdev->dev;
+	dev = afe->dev;
+
+	/* initial audio related clock */
+	ret = mt6797_init_clock(afe);
+	if (ret) {
+		dev_err(dev, "init clock error\n");
+		return ret;
+	}
+
+	/* regmap init */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	afe->base_addr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(afe->base_addr))
+		return PTR_ERR(afe->base_addr);
+
+	afe->regmap = devm_regmap_init_mmio(&pdev->dev, afe->base_addr,
+					    &mt6797_afe_regmap_config);
+	if (IS_ERR(afe->regmap))
+		return PTR_ERR(afe->regmap);
+
+	/* init memif */
+	afe->memif_size = MT6797_MEMIF_NUM;
+	afe->memif = devm_kcalloc(dev, afe->memif_size, sizeof(*afe->memif),
+				  GFP_KERNEL);
+	if (!afe->memif)
+		return -ENOMEM;
+
+	for (i = 0; i < afe->memif_size; i++) {
+		afe->memif[i].data = &memif_data[i];
+		afe->memif[i].irq_usage = -1;
+	}
+
+	mutex_init(&afe->irq_alloc_lock);
+
+	/* irq initialize */
+	afe->irqs_size = MT6797_IRQ_NUM;
+	afe->irqs = devm_kcalloc(dev, afe->irqs_size, sizeof(*afe->irqs),
+				 GFP_KERNEL);
+	if (!afe->irqs)
+		return -ENOMEM;
+
+	for (i = 0; i < afe->irqs_size; i++)
+		afe->irqs[i].irq_data = &irq_data[i];
+
+	/* request irq */
+	irq_id = platform_get_irq(pdev, 0);
+	if (!irq_id) {
+		dev_err(dev, "%s no irq found\n", dev->of_node->name);
+		return -ENXIO;
+	}
+	ret = devm_request_irq(dev, irq_id, mt6797_afe_irq_handler,
+			       IRQF_TRIGGER_NONE, "asys-isr", (void *)afe);
+	if (ret) {
+		dev_err(dev, "could not request_irq for asys-isr\n");
+		return ret;
+	}
+
+	/* init sub_dais */
+	afe->num_sub_dais = MT6797_DAI_NUM;
+	afe->sub_dais = devm_kcalloc(dev, afe->num_sub_dais,
+				     sizeof(*afe->sub_dais),
+				     GFP_KERNEL);
+	if (!afe->sub_dais)
+		return -ENOMEM;
+
+	mt6797_dai_adda_register(afe);
+	mt6797_dai_pcm_register(afe);
+	mt6797_dai_hostless_register(afe);
+
+	afe->sub_dais[MT6797_MEMIF_DL1].dai_drivers = mt6797_memif_dai_driver;
+	afe->sub_dais[MT6797_MEMIF_DL1].num_dai_drivers =
+		ARRAY_SIZE(mt6797_memif_dai_driver);
+	afe->sub_dais[MT6797_MEMIF_DL1].dapm_widgets = mt6797_memif_widgets;
+	afe->sub_dais[MT6797_MEMIF_DL1].num_dapm_widgets =
+		ARRAY_SIZE(mt6797_memif_widgets);
+	afe->sub_dais[MT6797_MEMIF_DL1].dapm_routes = mt6797_memif_routes;
+	afe->sub_dais[MT6797_MEMIF_DL1].num_dapm_routes =
+		ARRAY_SIZE(mt6797_memif_routes);
+
+	/* init dai_driver and component_driver */
+	mtk_afe_combine_sub_dai(afe);
+
+	afe->mtk_afe_hardware = &mt6797_afe_hardware;
+	afe->memif_fs = mt6797_memif_fs;
+	afe->irq_fs = mt6797_irq_fs;
+
+	afe->runtime_resume = mt6797_afe_runtime_resume;
+	afe->runtime_suspend = mt6797_afe_runtime_suspend;
+
+	platform_set_drvdata(pdev, afe);
+
+	pm_runtime_enable(dev);
+	if (!pm_runtime_enabled(dev))
+		goto err_pm_disable;
+	pm_runtime_get_sync(&pdev->dev);
+
+	/* register component */
+	ret = devm_snd_soc_register_component(dev, &mt6797_afe_component,
+					      NULL, 0);
+	if (ret) {
+		dev_warn(dev, "err_platform\n");
+		goto err_pm_disable;
+	}
+
+	ret = devm_snd_soc_register_component(afe->dev,
+				     &mt6797_afe_pcm_dai_component,
+				     afe->dai_drivers,
+				     afe->num_dai_drivers);
+	if (ret) {
+		dev_warn(dev, "err_dai_component\n");
+		goto err_pm_disable;
+	}
+
+	return 0;
+
+err_pm_disable:
+	pm_runtime_disable(dev);
+
+	return ret;
+}
+
+static int mt6797_afe_pcm_dev_remove(struct platform_device *pdev)
+{
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		mt6797_afe_runtime_suspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id mt6797_afe_pcm_dt_match[] = {
+	{ .compatible = "mediatek,mt6797-audio", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mt6797_afe_pcm_dt_match);
+
+static const struct dev_pm_ops mt6797_afe_pm_ops = {
+	SET_RUNTIME_PM_OPS(mt6797_afe_runtime_suspend,
+			   mt6797_afe_runtime_resume, NULL)
+};
+
+static struct platform_driver mt6797_afe_pcm_driver = {
+	.driver = {
+		   .name = "mt6797-audio",
+		   .of_match_table = mt6797_afe_pcm_dt_match,
+#ifdef CONFIG_PM
+		   .pm = &mt6797_afe_pm_ops,
+#endif
+	},
+	.probe = mt6797_afe_pcm_dev_probe,
+	.remove = mt6797_afe_pcm_dev_remove,
+};
+
+module_platform_driver(mt6797_afe_pcm_driver);
+
+MODULE_DESCRIPTION("Mediatek ALSA SoC AFE platform driver for 6797");
+MODULE_AUTHOR("KaiChieh Chuang <kaichieh.chuang@mediatek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-adda.c b/sound/soc/mediatek/mt6797/mt6797-dai-adda.c
new file mode 100644
index 000000000000..ad083265ce94
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-adda.c
@@ -0,0 +1,396 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// MediaTek ALSA SoC Audio DAI ADDA Control
+//
+// Copyright (c) 2018 MediaTek Inc.
+// Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+
+#include <linux/regmap.h>
+#include <linux/delay.h>
+#include "mt6797-afe-common.h"
+#include "mt6797-interconnection.h"
+#include "mt6797-reg.h"
+
+enum {
+	MTK_AFE_ADDA_DL_RATE_8K = 0,
+	MTK_AFE_ADDA_DL_RATE_11K = 1,
+	MTK_AFE_ADDA_DL_RATE_12K = 2,
+	MTK_AFE_ADDA_DL_RATE_16K = 3,
+	MTK_AFE_ADDA_DL_RATE_22K = 4,
+	MTK_AFE_ADDA_DL_RATE_24K = 5,
+	MTK_AFE_ADDA_DL_RATE_32K = 6,
+	MTK_AFE_ADDA_DL_RATE_44K = 7,
+	MTK_AFE_ADDA_DL_RATE_48K = 8,
+	MTK_AFE_ADDA_DL_RATE_96K = 9,
+	MTK_AFE_ADDA_DL_RATE_192K = 10,
+};
+
+enum {
+	MTK_AFE_ADDA_UL_RATE_8K = 0,
+	MTK_AFE_ADDA_UL_RATE_16K = 1,
+	MTK_AFE_ADDA_UL_RATE_32K = 2,
+	MTK_AFE_ADDA_UL_RATE_48K = 3,
+	MTK_AFE_ADDA_UL_RATE_96K = 4,
+	MTK_AFE_ADDA_UL_RATE_192K = 5,
+	MTK_AFE_ADDA_UL_RATE_48K_HD = 6,
+};
+
+static unsigned int adda_dl_rate_transform(struct mtk_base_afe *afe,
+					   unsigned int rate)
+{
+	switch (rate) {
+	case 8000:
+		return MTK_AFE_ADDA_DL_RATE_8K;
+	case 11025:
+		return MTK_AFE_ADDA_DL_RATE_11K;
+	case 12000:
+		return MTK_AFE_ADDA_DL_RATE_12K;
+	case 16000:
+		return MTK_AFE_ADDA_DL_RATE_16K;
+	case 22050:
+		return MTK_AFE_ADDA_DL_RATE_22K;
+	case 24000:
+		return MTK_AFE_ADDA_DL_RATE_24K;
+	case 32000:
+		return MTK_AFE_ADDA_DL_RATE_32K;
+	case 44100:
+		return MTK_AFE_ADDA_DL_RATE_44K;
+	case 48000:
+		return MTK_AFE_ADDA_DL_RATE_48K;
+	case 96000:
+		return MTK_AFE_ADDA_DL_RATE_96K;
+	case 192000:
+		return MTK_AFE_ADDA_DL_RATE_192K;
+	default:
+		dev_warn(afe->dev, "%s(), rate %d invalid, use 48kHz!!!\n",
+			 __func__, rate);
+		return MTK_AFE_ADDA_DL_RATE_48K;
+	}
+}
+
+static unsigned int adda_ul_rate_transform(struct mtk_base_afe *afe,
+					   unsigned int rate)
+{
+	switch (rate) {
+	case 8000:
+		return MTK_AFE_ADDA_UL_RATE_8K;
+	case 16000:
+		return MTK_AFE_ADDA_UL_RATE_16K;
+	case 32000:
+		return MTK_AFE_ADDA_UL_RATE_32K;
+	case 48000:
+		return MTK_AFE_ADDA_UL_RATE_48K;
+	case 96000:
+		return MTK_AFE_ADDA_UL_RATE_96K;
+	case 192000:
+		return MTK_AFE_ADDA_UL_RATE_192K;
+	default:
+		dev_warn(afe->dev, "%s(), rate %d invalid, use 48kHz!!!\n",
+			 __func__, rate);
+		return MTK_AFE_ADDA_UL_RATE_48K;
+	}
+}
+
+/* dai component */
+static const struct snd_kcontrol_new mtk_adda_dl_ch1_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("DL1_CH1", AFE_CONN3, I_DL1_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH1", AFE_CONN3, I_DL2_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL3_CH1", AFE_CONN3, I_DL3_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN3,
+				    I_ADDA_UL_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN3,
+				    I_ADDA_UL_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("PCM_1_CAP_CH1", AFE_CONN3,
+				    I_PCM_1_CAP_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("PCM_2_CAP_CH1", AFE_CONN3,
+				    I_PCM_2_CAP_CH1, 1, 0),
+};
+
+static const struct snd_kcontrol_new mtk_adda_dl_ch2_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("DL1_CH1", AFE_CONN4, I_DL1_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL1_CH2", AFE_CONN4, I_DL1_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH1", AFE_CONN4, I_DL2_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH2", AFE_CONN4, I_DL2_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL3_CH1", AFE_CONN4, I_DL3_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL3_CH2", AFE_CONN4, I_DL3_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN4,
+				    I_ADDA_UL_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN4,
+				    I_ADDA_UL_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("PCM_1_CAP_CH1", AFE_CONN4,
+				    I_PCM_1_CAP_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("PCM_2_CAP_CH1", AFE_CONN4,
+				    I_PCM_2_CAP_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("PCM_1_CAP_CH2", AFE_CONN4,
+				    I_PCM_1_CAP_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("PCM_2_CAP_CH2", AFE_CONN4,
+				    I_PCM_2_CAP_CH2, 1, 0),
+};
+
+static int mtk_adda_ul_event(struct snd_soc_dapm_widget *w,
+			     struct snd_kcontrol *kcontrol,
+			     int event)
+{
+	struct snd_soc_component *cmpnt = snd_soc_dapm_to_component(w->dapm);
+	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(cmpnt);
+
+	dev_dbg(afe->dev, "%s(), name %s, event 0x%x\n",
+		__func__, w->name, event);
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMD:
+		/* should delayed 1/fs(smallest is 8k) = 125us before afe off */
+		usleep_range(125, 135);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+enum {
+	SUPPLY_SEQ_AUD_TOP_PDN,
+	SUPPLY_SEQ_ADDA_AFE_ON,
+	SUPPLY_SEQ_ADDA_DL_ON,
+	SUPPLY_SEQ_ADDA_UL_ON,
+};
+
+static const struct snd_soc_dapm_widget mtk_dai_adda_widgets[] = {
+	/* adda */
+	SND_SOC_DAPM_MIXER("ADDA_DL_CH1", SND_SOC_NOPM, 0, 0,
+			   mtk_adda_dl_ch1_mix,
+			   ARRAY_SIZE(mtk_adda_dl_ch1_mix)),
+	SND_SOC_DAPM_MIXER("ADDA_DL_CH2", SND_SOC_NOPM, 0, 0,
+			   mtk_adda_dl_ch2_mix,
+			   ARRAY_SIZE(mtk_adda_dl_ch2_mix)),
+
+	SND_SOC_DAPM_SUPPLY_S("ADDA Enable", SUPPLY_SEQ_ADDA_AFE_ON,
+			      AFE_ADDA_UL_DL_CON0, ADDA_AFE_ON_SFT, 0,
+			      NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY_S("ADDA Playback Enable", SUPPLY_SEQ_ADDA_DL_ON,
+			      AFE_ADDA_DL_SRC2_CON0,
+			      DL_2_SRC_ON_TMP_CTL_PRE_SFT, 0,
+			      NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY_S("ADDA Capture Enable", SUPPLY_SEQ_ADDA_UL_ON,
+			      AFE_ADDA_UL_SRC_CON0,
+			      UL_SRC_ON_TMP_CTL_SFT, 0,
+			      mtk_adda_ul_event,
+			      SND_SOC_DAPM_POST_PMD),
+
+	SND_SOC_DAPM_SUPPLY_S("aud_dac_clk", SUPPLY_SEQ_AUD_TOP_PDN,
+			      AUDIO_TOP_CON0, PDN_DAC_SFT, 1,
+			      NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("aud_dac_predis_clk", SUPPLY_SEQ_AUD_TOP_PDN,
+			      AUDIO_TOP_CON0, PDN_DAC_PREDIS_SFT, 1,
+			      NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY_S("aud_adc_clk", SUPPLY_SEQ_AUD_TOP_PDN,
+			      AUDIO_TOP_CON0, PDN_ADC_SFT, 1,
+			      NULL, 0),
+
+	SND_SOC_DAPM_CLOCK_SUPPLY("mtkaif_26m_clk"),
+};
+
+static const struct snd_soc_dapm_route mtk_dai_adda_routes[] = {
+	/* playback */
+	{"ADDA_DL_CH1", "DL1_CH1", "DL1"},
+	{"ADDA_DL_CH2", "DL1_CH1", "DL1"},
+	{"ADDA_DL_CH2", "DL1_CH2", "DL1"},
+
+	{"ADDA_DL_CH1", "DL2_CH1", "DL2"},
+	{"ADDA_DL_CH2", "DL2_CH1", "DL2"},
+	{"ADDA_DL_CH2", "DL2_CH2", "DL2"},
+
+	{"ADDA_DL_CH1", "DL3_CH1", "DL3"},
+	{"ADDA_DL_CH2", "DL3_CH1", "DL3"},
+	{"ADDA_DL_CH2", "DL3_CH2", "DL3"},
+
+	{"ADDA Playback", NULL, "ADDA_DL_CH1"},
+	{"ADDA Playback", NULL, "ADDA_DL_CH2"},
+
+	/* adda enable */
+	{"ADDA Playback", NULL, "ADDA Enable"},
+	{"ADDA Playback", NULL, "ADDA Playback Enable"},
+	{"ADDA Capture", NULL, "ADDA Enable"},
+	{"ADDA Capture", NULL, "ADDA Capture Enable"},
+
+	/* clk */
+	{"ADDA Playback", NULL, "mtkaif_26m_clk"},
+	{"ADDA Playback", NULL, "aud_dac_clk"},
+	{"ADDA Playback", NULL, "aud_dac_predis_clk"},
+
+	{"ADDA Capture", NULL, "mtkaif_26m_clk"},
+	{"ADDA Capture", NULL, "aud_adc_clk"},
+};
+
+/* dai ops */
+static int mtk_dai_adda_hw_params(struct snd_pcm_substream *substream,
+				  struct snd_pcm_hw_params *params,
+				  struct snd_soc_dai *dai)
+{
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
+	unsigned int rate = params_rate(params);
+
+	dev_dbg(afe->dev, "%s(), id %d, stream %d, rate %d\n",
+		__func__, dai->id, substream->stream, rate);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		unsigned int dl_src2_con0 = 0;
+		unsigned int dl_src2_con1 = 0;
+
+		/* clean predistortion */
+		regmap_write(afe->regmap, AFE_ADDA_PREDIS_CON0, 0);
+		regmap_write(afe->regmap, AFE_ADDA_PREDIS_CON1, 0);
+
+		/* set input sampling rate */
+		dl_src2_con0 = adda_dl_rate_transform(afe, rate) << 28;
+
+		/* set output mode */
+		switch (rate) {
+		case 192000:
+			dl_src2_con0 |= (0x1 << 24); /* UP_SAMPLING_RATE_X2 */
+			dl_src2_con0 |= 1 << 14;
+			break;
+		case 96000:
+			dl_src2_con0 |= (0x2 << 24); /* UP_SAMPLING_RATE_X4 */
+			dl_src2_con0 |= 1 << 14;
+			break;
+		default:
+			dl_src2_con0 |= (0x3 << 24); /* UP_SAMPLING_RATE_X8 */
+			break;
+		}
+
+		/* turn off mute function */
+		dl_src2_con0 |= (0x03 << 11);
+
+		/* set voice input data if input sample rate is 8k or 16k */
+		if (rate == 8000 || rate == 16000)
+			dl_src2_con0 |= 0x01 << 5;
+
+		if (rate < 96000) {
+			/* SA suggest apply -0.3db to audio/speech path */
+			dl_src2_con1 = 0xf74f0000;
+		} else {
+			/* SA suggest apply -0.3db to audio/speech path
+			 * with DL gain set to half,
+			 * 0xFFFF = 0dB -> 0x8000 = 0dB when 96k, 192k
+			 */
+			dl_src2_con1 = 0x7ba70000;
+		}
+
+		/* turn on down-link gain */
+		dl_src2_con0 = dl_src2_con0 | (0x01 << 1);
+
+		regmap_write(afe->regmap, AFE_ADDA_DL_SRC2_CON0, dl_src2_con0);
+		regmap_write(afe->regmap, AFE_ADDA_DL_SRC2_CON1, dl_src2_con1);
+	} else {
+		unsigned int voice_mode = 0;
+		unsigned int ul_src_con0 = 0;	/* default value */
+
+		/* Using Internal ADC */
+		regmap_update_bits(afe->regmap,
+				   AFE_ADDA_TOP_CON0,
+				   0x1 << 0,
+				   0x0 << 0);
+
+		voice_mode = adda_ul_rate_transform(afe, rate);
+
+		ul_src_con0 |= (voice_mode << 17) & (0x7 << 17);
+
+		/* up8x txif sat on */
+		regmap_write(afe->regmap, AFE_ADDA_NEWIF_CFG0, 0x03F87201);
+
+		if (rate >= 96000) {	/* hires */
+			/* use hires format [1 0 23] */
+			regmap_update_bits(afe->regmap,
+					   AFE_ADDA_NEWIF_CFG0,
+					   0x1 << 5,
+					   0x1 << 5);
+
+			regmap_update_bits(afe->regmap,
+					   AFE_ADDA_NEWIF_CFG2,
+					   0xf << 28,
+					   voice_mode << 28);
+		} else {	/* normal 8~48k */
+			/* use fixed 260k anc path */
+			regmap_update_bits(afe->regmap,
+					   AFE_ADDA_NEWIF_CFG2,
+					   0xf << 28,
+					   8 << 28);
+
+			/* ul_use_cic_out */
+			ul_src_con0 |= 0x1 << 20;
+		}
+
+		regmap_update_bits(afe->regmap,
+				   AFE_ADDA_NEWIF_CFG2,
+				   0xf << 28,
+				   8 << 28);
+
+		regmap_update_bits(afe->regmap,
+				   AFE_ADDA_UL_SRC_CON0,
+				   0xfffffffe,
+				   ul_src_con0);
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops mtk_dai_adda_ops = {
+	.hw_params = mtk_dai_adda_hw_params,
+};
+
+/* dai driver */
+#define MTK_ADDA_PLAYBACK_RATES (SNDRV_PCM_RATE_8000_48000 |\
+				 SNDRV_PCM_RATE_96000 |\
+				 SNDRV_PCM_RATE_192000)
+
+#define MTK_ADDA_CAPTURE_RATES (SNDRV_PCM_RATE_8000 |\
+				SNDRV_PCM_RATE_16000 |\
+				SNDRV_PCM_RATE_32000 |\
+				SNDRV_PCM_RATE_48000 |\
+				SNDRV_PCM_RATE_96000 |\
+				SNDRV_PCM_RATE_192000)
+
+#define MTK_ADDA_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
+			  SNDRV_PCM_FMTBIT_S24_LE |\
+			  SNDRV_PCM_FMTBIT_S32_LE)
+
+static struct snd_soc_dai_driver mtk_dai_adda_driver[] = {
+	{
+		.name = "ADDA",
+		.id = MT6797_DAI_ADDA,
+		.playback = {
+			.stream_name = "ADDA Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_ADDA_PLAYBACK_RATES,
+			.formats = MTK_ADDA_FORMATS,
+		},
+		.capture = {
+			.stream_name = "ADDA Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_ADDA_CAPTURE_RATES,
+			.formats = MTK_ADDA_FORMATS,
+		},
+		.ops = &mtk_dai_adda_ops,
+	},
+};
+
+int mt6797_dai_adda_register(struct mtk_base_afe *afe)
+{
+	int id = MT6797_DAI_ADDA;
+
+	afe->sub_dais[id].dai_drivers = mtk_dai_adda_driver;
+	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_adda_driver);
+
+	afe->sub_dais[id].dapm_widgets = mtk_dai_adda_widgets;
+	afe->sub_dais[id].num_dapm_widgets = ARRAY_SIZE(mtk_dai_adda_widgets);
+	afe->sub_dais[id].dapm_routes = mtk_dai_adda_routes;
+	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_adda_routes);
+	return 0;
+}
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c b/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c
new file mode 100644
index 000000000000..4cf985b15a11
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// MediaTek ALSA SoC Audio DAI Hostless Control
+//
+// Copyright (c) 2018 MediaTek Inc.
+// Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+
+#include "mt6797-afe-common.h"
+
+/* dai component */
+static const struct snd_soc_dapm_route mtk_dai_hostless_routes[] = {
+	/* Hostless ADDA Loopback */
+	{"ADDA_DL_CH1", "ADDA_UL_CH1", "Hostless LPBK DL"},
+	{"ADDA_DL_CH1", "ADDA_UL_CH2", "Hostless LPBK DL"},
+	{"ADDA_DL_CH2", "ADDA_UL_CH1", "Hostless LPBK DL"},
+	{"ADDA_DL_CH2", "ADDA_UL_CH2", "Hostless LPBK DL"},
+	{"Hostless LPBK UL", NULL, "ADDA Capture"},
+
+	/* Hostless Speech */
+	{"ADDA_DL_CH1", "PCM_1_CAP_CH1", "Hostless Speech DL"},
+	{"ADDA_DL_CH2", "PCM_1_CAP_CH1", "Hostless Speech DL"},
+	{"ADDA_DL_CH2", "PCM_1_CAP_CH2", "Hostless Speech DL"},
+	{"ADDA_DL_CH1", "PCM_2_CAP_CH1", "Hostless Speech DL"},
+	{"ADDA_DL_CH2", "PCM_2_CAP_CH1", "Hostless Speech DL"},
+	{"ADDA_DL_CH2", "PCM_2_CAP_CH2", "Hostless Speech DL"},
+	{"PCM_1_PB_CH1", "ADDA_UL_CH1", "Hostless Speech DL"},
+	{"PCM_1_PB_CH2", "ADDA_UL_CH2", "Hostless Speech DL"},
+	{"PCM_2_PB_CH1", "ADDA_UL_CH1", "Hostless Speech DL"},
+	{"PCM_2_PB_CH2", "ADDA_UL_CH2", "Hostless Speech DL"},
+
+	{"Hostless Speech UL", NULL, "PCM 1 Capture"},
+	{"Hostless Speech UL", NULL, "PCM 2 Capture"},
+	{"Hostless Speech UL", NULL, "ADDA Capture"},
+};
+
+/* dai ops */
+static int mtk_dai_hostless_startup(struct snd_pcm_substream *substream,
+				    struct snd_soc_dai *dai)
+{
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
+
+	return snd_soc_set_runtime_hwparams(substream, afe->mtk_afe_hardware);
+}
+
+static const struct snd_soc_dai_ops mtk_dai_hostless_ops = {
+	.startup = mtk_dai_hostless_startup,
+};
+
+/* dai driver */
+#define MTK_HOSTLESS_RATES (SNDRV_PCM_RATE_8000_48000 |\
+			   SNDRV_PCM_RATE_88200 |\
+			   SNDRV_PCM_RATE_96000 |\
+			   SNDRV_PCM_RATE_176400 |\
+			   SNDRV_PCM_RATE_192000)
+
+#define MTK_HOSTLESS_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
+			     SNDRV_PCM_FMTBIT_S24_LE |\
+			     SNDRV_PCM_FMTBIT_S32_LE)
+
+static struct snd_soc_dai_driver mtk_dai_hostless_driver[] = {
+	{
+		.name = "Hostless LPBK DAI",
+		.id = MT6797_DAI_HOSTLESS_LPBK,
+		.playback = {
+			.stream_name = "Hostless LPBK DL",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_HOSTLESS_RATES,
+			.formats = MTK_HOSTLESS_FORMATS,
+		},
+		.capture = {
+			.stream_name = "Hostless LPBK UL",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_HOSTLESS_RATES,
+			.formats = MTK_HOSTLESS_FORMATS,
+		},
+		.ops = &mtk_dai_hostless_ops,
+	},
+	{
+		.name = "Hostless Speech DAI",
+		.id = MT6797_DAI_HOSTLESS_SPEECH,
+		.playback = {
+			.stream_name = "Hostless Speech DL",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_HOSTLESS_RATES,
+			.formats = MTK_HOSTLESS_FORMATS,
+		},
+		.capture = {
+			.stream_name = "Hostless Speech UL",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_HOSTLESS_RATES,
+			.formats = MTK_HOSTLESS_FORMATS,
+		},
+		.ops = &mtk_dai_hostless_ops,
+	},
+};
+
+int mt6797_dai_hostless_register(struct mtk_base_afe *afe)
+{
+	int id = MT6797_DAI_HOSTLESS_LPBK;
+
+	afe->sub_dais[id].dai_drivers = mtk_dai_hostless_driver;
+	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_hostless_driver);
+
+	afe->sub_dais[id].dapm_routes = mtk_dai_hostless_routes;
+	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_hostless_routes);
+
+	return 0;
+}
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c b/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c
new file mode 100644
index 000000000000..16d5b5067204
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// MediaTek ALSA SoC Audio DAI I2S Control
+//
+// Copyright (c) 2018 MediaTek Inc.
+// Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+
+#include <linux/regmap.h>
+#include <sound/pcm_params.h>
+#include "mt6797-afe-common.h"
+#include "mt6797-interconnection.h"
+#include "mt6797-reg.h"
+
+enum AUD_TX_LCH_RPT {
+	AUD_TX_LCH_RPT_NO_REPEAT = 0,
+	AUD_TX_LCH_RPT_REPEAT = 1
+};
+
+enum AUD_VBT_16K_MODE {
+	AUD_VBT_16K_MODE_DISABLE = 0,
+	AUD_VBT_16K_MODE_ENABLE = 1
+};
+
+enum AUD_EXT_MODEM {
+	AUD_EXT_MODEM_SELECT_INTERNAL = 0,
+	AUD_EXT_MODEM_SELECT_EXTERNAL = 1
+};
+
+enum AUD_PCM_SYNC_TYPE {
+	/* bck sync length = 1 */
+	AUD_PCM_ONE_BCK_CYCLE_SYNC = 0,
+	/* bck sync length = PCM_INTF_CON1[9:13] */
+	AUD_PCM_EXTENDED_BCK_CYCLE_SYNC = 1
+};
+
+enum AUD_BT_MODE {
+	AUD_BT_MODE_DUAL_MIC_ON_TX = 0,
+	AUD_BT_MODE_SINGLE_MIC_ON_TX = 1
+};
+
+enum AUD_PCM_AFIFO_SRC {
+	/* slave mode & external modem uses different crystal */
+	AUD_PCM_AFIFO_ASRC = 0,
+	/* slave mode & external modem uses the same crystal */
+	AUD_PCM_AFIFO_AFIFO = 1
+};
+
+enum AUD_PCM_CLOCK_SOURCE {
+	AUD_PCM_CLOCK_MASTER_MODE = 0,
+	AUD_PCM_CLOCK_SLAVE_MODE = 1
+};
+
+enum AUD_PCM_WLEN {
+	AUD_PCM_WLEN_PCM_32_BCK_CYCLES = 0,
+	AUD_PCM_WLEN_PCM_64_BCK_CYCLES = 1
+};
+
+enum AUD_PCM_MODE {
+	AUD_PCM_MODE_PCM_MODE_8K = 0,
+	AUD_PCM_MODE_PCM_MODE_16K = 1,
+	AUD_PCM_MODE_PCM_MODE_32K = 2,
+	AUD_PCM_MODE_PCM_MODE_48K = 3,
+};
+
+enum AUD_PCM_FMT {
+	AUD_PCM_FMT_I2S = 0,
+	AUD_PCM_FMT_EIAJ = 1,
+	AUD_PCM_FMT_PCM_MODE_A = 2,
+	AUD_PCM_FMT_PCM_MODE_B = 3
+};
+
+enum AUD_BCLK_OUT_INV {
+	AUD_BCLK_OUT_INV_NO_INVERSE = 0,
+	AUD_BCLK_OUT_INV_INVERSE = 1
+};
+
+enum AUD_PCM_EN {
+	AUD_PCM_EN_DISABLE = 0,
+	AUD_PCM_EN_ENABLE = 1
+};
+
+/* dai component */
+static const struct snd_kcontrol_new mtk_pcm_1_playback_ch1_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN7,
+				    I_ADDA_UL_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH1", AFE_CONN7,
+				    I_DL2_CH1, 1, 0),
+};
+
+static const struct snd_kcontrol_new mtk_pcm_1_playback_ch2_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN8,
+				    I_ADDA_UL_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH2", AFE_CONN8,
+				    I_DL2_CH2, 1, 0),
+};
+
+static const struct snd_kcontrol_new mtk_pcm_1_playback_ch4_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("DL1_CH1", AFE_CONN27,
+				    I_DL1_CH1, 1, 0),
+};
+
+static const struct snd_kcontrol_new mtk_pcm_2_playback_ch1_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH1", AFE_CONN17,
+				    I_ADDA_UL_CH1, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH1", AFE_CONN17,
+				    I_DL2_CH1, 1, 0),
+};
+
+static const struct snd_kcontrol_new mtk_pcm_2_playback_ch2_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("ADDA_UL_CH2", AFE_CONN18,
+				    I_ADDA_UL_CH2, 1, 0),
+	SOC_DAPM_SINGLE_AUTODISABLE("DL2_CH2", AFE_CONN18,
+				    I_DL2_CH2, 1, 0),
+};
+
+static const struct snd_kcontrol_new mtk_pcm_2_playback_ch4_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("DL1_CH1", AFE_CONN24,
+				    I_DL1_CH1, 1, 0),
+};
+
+static const struct snd_soc_dapm_widget mtk_dai_pcm_widgets[] = {
+	/* inter-connections */
+	SND_SOC_DAPM_MIXER("PCM_1_PB_CH1", SND_SOC_NOPM, 0, 0,
+			   mtk_pcm_1_playback_ch1_mix,
+			   ARRAY_SIZE(mtk_pcm_1_playback_ch1_mix)),
+	SND_SOC_DAPM_MIXER("PCM_1_PB_CH2", SND_SOC_NOPM, 0, 0,
+			   mtk_pcm_1_playback_ch2_mix,
+			   ARRAY_SIZE(mtk_pcm_1_playback_ch2_mix)),
+	SND_SOC_DAPM_MIXER("PCM_1_PB_CH4", SND_SOC_NOPM, 0, 0,
+			   mtk_pcm_1_playback_ch4_mix,
+			   ARRAY_SIZE(mtk_pcm_1_playback_ch4_mix)),
+	SND_SOC_DAPM_MIXER("PCM_2_PB_CH1", SND_SOC_NOPM, 0, 0,
+			   mtk_pcm_2_playback_ch1_mix,
+			   ARRAY_SIZE(mtk_pcm_2_playback_ch1_mix)),
+	SND_SOC_DAPM_MIXER("PCM_2_PB_CH2", SND_SOC_NOPM, 0, 0,
+			   mtk_pcm_2_playback_ch2_mix,
+			   ARRAY_SIZE(mtk_pcm_2_playback_ch2_mix)),
+	SND_SOC_DAPM_MIXER("PCM_2_PB_CH4", SND_SOC_NOPM, 0, 0,
+			   mtk_pcm_2_playback_ch4_mix,
+			   ARRAY_SIZE(mtk_pcm_2_playback_ch4_mix)),
+
+	SND_SOC_DAPM_SUPPLY("PCM_1_EN", PCM_INTF_CON1, PCM_EN_SFT, 0,
+			    NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("PCM_2_EN", PCM2_INTF_CON, PCM2_EN_SFT, 0,
+			    NULL, 0),
+
+	SND_SOC_DAPM_INPUT("MD1_TO_AFE"),
+	SND_SOC_DAPM_INPUT("MD2_TO_AFE"),
+	SND_SOC_DAPM_OUTPUT("AFE_TO_MD1"),
+	SND_SOC_DAPM_OUTPUT("AFE_TO_MD2"),
+};
+
+static const struct snd_soc_dapm_route mtk_dai_pcm_routes[] = {
+	{"PCM 1 Playback", NULL, "PCM_1_PB_CH1"},
+	{"PCM 1 Playback", NULL, "PCM_1_PB_CH2"},
+	{"PCM 1 Playback", NULL, "PCM_1_PB_CH4"},
+	{"PCM 2 Playback", NULL, "PCM_2_PB_CH1"},
+	{"PCM 2 Playback", NULL, "PCM_2_PB_CH2"},
+	{"PCM 2 Playback", NULL, "PCM_2_PB_CH4"},
+
+	{"PCM 1 Playback", NULL, "PCM_1_EN"},
+	{"PCM 2 Playback", NULL, "PCM_2_EN"},
+	{"PCM 1 Capture", NULL, "PCM_1_EN"},
+	{"PCM 2 Capture", NULL, "PCM_2_EN"},
+
+	{"AFE_TO_MD1", NULL, "PCM 2 Playback"},
+	{"AFE_TO_MD2", NULL, "PCM 1 Playback"},
+	{"PCM 2 Capture", NULL, "MD1_TO_AFE"},
+	{"PCM 1 Capture", NULL, "MD2_TO_AFE"},
+
+	{"PCM_1_PB_CH1", "DL2_CH1", "DL2"},
+	{"PCM_1_PB_CH2", "DL2_CH2", "DL2"},
+	{"PCM_1_PB_CH4", "DL1_CH1", "DL1"},
+	{"PCM_2_PB_CH1", "DL2_CH1", "DL2"},
+	{"PCM_2_PB_CH2", "DL2_CH2", "DL2"},
+	{"PCM_2_PB_CH4", "DL1_CH1", "DL1"},
+};
+
+/* dai ops */
+static int mtk_dai_pcm_hw_params(struct snd_pcm_substream *substream,
+				 struct snd_pcm_hw_params *params,
+				 struct snd_soc_dai *dai)
+{
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
+	unsigned int rate = params_rate(params);
+	unsigned int rate_reg = mt6797_rate_transform(afe->dev, rate, dai->id);
+	unsigned int pcm_con = 0;
+
+	dev_dbg(afe->dev, "%s(), id %d, stream %d, rate %d, rate_reg %d, widget active p %d, c %d\n",
+		__func__,
+		dai->id,
+		substream->stream,
+		rate,
+		rate_reg,
+		dai->playback_widget->active,
+		dai->capture_widget->active);
+
+	if (dai->playback_widget->active || dai->capture_widget->active)
+		return 0;
+
+	switch (dai->id) {
+	case MT6797_DAI_PCM_1:
+		pcm_con |= AUD_BCLK_OUT_INV_NO_INVERSE << PCM_BCLK_OUT_INV_SFT;
+		pcm_con |= AUD_TX_LCH_RPT_NO_REPEAT << PCM_TX_LCH_RPT_SFT;
+		pcm_con |= AUD_VBT_16K_MODE_DISABLE << PCM_VBT_16K_MODE_SFT;
+		pcm_con |= AUD_EXT_MODEM_SELECT_INTERNAL << PCM_EXT_MODEM_SFT;
+		pcm_con |= 0 << PCM_SYNC_LENGTH_SFT;
+		pcm_con |= AUD_PCM_ONE_BCK_CYCLE_SYNC << PCM_SYNC_TYPE_SFT;
+		pcm_con |= AUD_BT_MODE_DUAL_MIC_ON_TX << PCM_BT_MODE_SFT;
+		pcm_con |= AUD_PCM_AFIFO_AFIFO << PCM_BYP_ASRC_SFT;
+		pcm_con |= AUD_PCM_CLOCK_SLAVE_MODE << PCM_SLAVE_SFT;
+		pcm_con |= rate_reg << PCM_MODE_SFT;
+		pcm_con |= AUD_PCM_FMT_PCM_MODE_B << PCM_FMT_SFT;
+
+		regmap_update_bits(afe->regmap, PCM_INTF_CON1,
+				   0xfffffffe, pcm_con);
+		break;
+	case MT6797_DAI_PCM_2:
+		pcm_con |= AUD_TX_LCH_RPT_NO_REPEAT << PCM2_TX_LCH_RPT_SFT;
+		pcm_con |= AUD_VBT_16K_MODE_DISABLE << PCM2_VBT_16K_MODE_SFT;
+		pcm_con |= AUD_BT_MODE_DUAL_MIC_ON_TX << PCM2_BT_MODE_SFT;
+		pcm_con |= AUD_PCM_AFIFO_AFIFO << PCM2_AFIFO_SFT;
+		pcm_con |= AUD_PCM_WLEN_PCM_32_BCK_CYCLES << PCM2_WLEN_SFT;
+		pcm_con |= rate_reg << PCM2_MODE_SFT;
+		pcm_con |= AUD_PCM_FMT_PCM_MODE_B << PCM2_FMT_SFT;
+
+		regmap_update_bits(afe->regmap, PCM2_INTF_CON,
+				   0xfffffffe, pcm_con);
+		break;
+	default:
+		dev_warn(afe->dev, "%s(), id %d not support\n",
+			 __func__, dai->id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops mtk_dai_pcm_ops = {
+	.hw_params = mtk_dai_pcm_hw_params,
+};
+
+/* dai driver */
+#define MTK_PCM_RATES (SNDRV_PCM_RATE_8000 |\
+		       SNDRV_PCM_RATE_16000 |\
+		       SNDRV_PCM_RATE_32000 |\
+		       SNDRV_PCM_RATE_48000)
+
+#define MTK_PCM_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
+			 SNDRV_PCM_FMTBIT_S24_LE |\
+			 SNDRV_PCM_FMTBIT_S32_LE)
+
+static struct snd_soc_dai_driver mtk_dai_pcm_driver[] = {
+	{
+		.name = "PCM 1",
+		.id = MT6797_DAI_PCM_1,
+		.playback = {
+			.stream_name = "PCM 1 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.capture = {
+			.stream_name = "PCM 1 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_dai_pcm_ops,
+		.symmetric_rates = 1,
+		.symmetric_samplebits = 1,
+	},
+	{
+		.name = "PCM 2",
+		.id = MT6797_DAI_PCM_2,
+		.playback = {
+			.stream_name = "PCM 2 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.capture = {
+			.stream_name = "PCM 2 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = MTK_PCM_RATES,
+			.formats = MTK_PCM_FORMATS,
+		},
+		.ops = &mtk_dai_pcm_ops,
+		.symmetric_rates = 1,
+		.symmetric_samplebits = 1,
+	},
+};
+
+int mt6797_dai_pcm_register(struct mtk_base_afe *afe)
+{
+	int id = MT6797_DAI_PCM_1;
+
+	afe->sub_dais[id].dai_drivers = mtk_dai_pcm_driver;
+	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_pcm_driver);
+
+	afe->sub_dais[id].dapm_widgets = mtk_dai_pcm_widgets;
+	afe->sub_dais[id].num_dapm_widgets = ARRAY_SIZE(mtk_dai_pcm_widgets);
+	afe->sub_dais[id].dapm_routes = mtk_dai_pcm_routes;
+	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_pcm_routes);
+
+	return 0;
+}
diff --git a/sound/soc/mediatek/mt6797/mt6797-interconnection.h b/sound/soc/mediatek/mt6797/mt6797-interconnection.h
new file mode 100644
index 000000000000..07b759b20079
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-interconnection.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Mediatek MT6797 audio driver interconnection definition
+ *
+ * Copyright (c) 2018 MediaTek Inc.
+ * Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+ */
+
+#ifndef _MT6797_INTERCONNECTION_H_
+#define _MT6797_INTERCONNECTION_H_
+
+#define I_I2S0_CH1 0
+#define I_I2S0_CH2 1
+#define I_ADDA_UL_CH1 3
+#define I_ADDA_UL_CH2 4
+#define I_DL1_CH1 5
+#define I_DL1_CH2 6
+#define I_DL2_CH1 7
+#define I_DL2_CH2 8
+#define I_PCM_1_CAP_CH1 9
+#define I_GAIN1_OUT_CH1 10
+#define I_GAIN1_OUT_CH2 11
+#define I_GAIN2_OUT_CH1 12
+#define I_GAIN2_OUT_CH2 13
+#define I_PCM_2_CAP_CH1 14
+#define I_PCM_2_CAP_CH2 21
+#define I_PCM_1_CAP_CH2 22
+#define I_DL3_CH1 23
+#define I_DL3_CH2 24
+#define I_I2S2_CH1 25
+#define I_I2S2_CH2 26
+
+#endif
diff --git a/sound/soc/mediatek/mt6797/mt6797-mt6351.c b/sound/soc/mediatek/mt6797/mt6797-mt6351.c
new file mode 100644
index 000000000000..b1558c57b9ca
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-mt6351.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// mt6797-mt6351.c  --  MT6797 MT6351 ALSA SoC machine driver
+//
+// Copyright (c) 2018 MediaTek Inc.
+// Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+
+#include <linux/module.h>
+#include <sound/soc.h>
+
+#include "mt6797-afe-common.h"
+
+static struct snd_soc_dai_link mt6797_mt6351_dai_links[] = {
+	/* FE */
+	{
+		.name = "Playback_1",
+		.stream_name = "Playback_1",
+		.cpu_dai_name = "DL1",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_playback = 1,
+	},
+	{
+		.name = "Playback_2",
+		.stream_name = "Playback_2",
+		.cpu_dai_name = "DL2",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_playback = 1,
+	},
+	{
+		.name = "Playback_3",
+		.stream_name = "Playback_3",
+		.cpu_dai_name = "DL3",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_playback = 1,
+	},
+	{
+		.name = "Capture_1",
+		.stream_name = "Capture_1",
+		.cpu_dai_name = "UL1",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_capture = 1,
+	},
+	{
+		.name = "Capture_2",
+		.stream_name = "Capture_2",
+		.cpu_dai_name = "UL2",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_capture = 1,
+	},
+	{
+		.name = "Capture_3",
+		.stream_name = "Capture_3",
+		.cpu_dai_name = "UL3",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_capture = 1,
+	},
+	{
+		.name = "Capture_Mono_1",
+		.stream_name = "Capture_Mono_1",
+		.cpu_dai_name = "UL_MONO_1",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_capture = 1,
+	},
+	{
+		.name = "Hostless_LPBK",
+		.stream_name = "Hostless_LPBK",
+		.cpu_dai_name = "Hostless LPBK DAI",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+		.ignore_suspend = 1,
+	},
+	{
+		.name = "Hostless_Speech",
+		.stream_name = "Hostless_Speech",
+		.cpu_dai_name = "Hostless Speech DAI",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_PRE,
+			    SND_SOC_DPCM_TRIGGER_PRE},
+		.dynamic = 1,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+		.ignore_suspend = 1,
+	},
+	/* BE */
+	{
+		.name = "Primary Codec",
+		.cpu_dai_name = "ADDA",
+		.codec_dai_name = "mt6351-snd-codec-aif1",
+		.no_pcm = 1,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+		.ignore_suspend = 1,
+	},
+	{
+		.name = "PCM 1",
+		.cpu_dai_name = "PCM 1",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.no_pcm = 1,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+		.ignore_suspend = 1,
+	},
+	{
+		.name = "PCM 2",
+		.cpu_dai_name = "PCM 2",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.no_pcm = 1,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+		.ignore_suspend = 1,
+	},
+};
+
+static struct snd_soc_card mt6797_mt6351_card = {
+	.name = "mt6797-mt6351",
+	.owner = THIS_MODULE,
+	.dai_link = mt6797_mt6351_dai_links,
+	.num_links = ARRAY_SIZE(mt6797_mt6351_dai_links),
+};
+
+static int mt6797_mt6351_dev_probe(struct platform_device *pdev)
+{
+	struct snd_soc_card *card = &mt6797_mt6351_card;
+	struct device_node *platform_node, *codec_node;
+	int ret, i;
+
+	card->dev = &pdev->dev;
+
+	platform_node = of_parse_phandle(pdev->dev.of_node,
+					 "mediatek,platform", 0);
+	if (!platform_node) {
+		dev_err(&pdev->dev, "Property 'platform' missing or invalid\n");
+		return -EINVAL;
+	}
+	for (i = 0; i < card->num_links; i++) {
+		if (mt6797_mt6351_dai_links[i].platform_name)
+			continue;
+		mt6797_mt6351_dai_links[i].platform_of_node = platform_node;
+	}
+
+	codec_node = of_parse_phandle(pdev->dev.of_node,
+				      "mediatek,audio-codec", 0);
+	if (!codec_node) {
+		dev_err(&pdev->dev,
+			"Property 'audio-codec' missing or invalid\n");
+		return -EINVAL;
+	}
+	for (i = 0; i < card->num_links; i++) {
+		if (mt6797_mt6351_dai_links[i].codec_name)
+			continue;
+		mt6797_mt6351_dai_links[i].codec_of_node = codec_node;
+	}
+
+	ret = devm_snd_soc_register_card(&pdev->dev, card);
+	if (ret)
+		dev_err(&pdev->dev, "%s snd_soc_register_card fail %d\n",
+			__func__, ret);
+
+	return ret;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id mt6797_mt6351_dt_match[] = {
+	{.compatible = "mediatek,mt6797-mt6351-sound",},
+	{}
+};
+#endif
+
+static struct platform_driver mt6797_mt6351_driver = {
+	.driver = {
+		.name = "mt6797-mt6351",
+		.owner = THIS_MODULE,
+#ifdef CONFIG_OF
+		.of_match_table = mt6797_mt6351_dt_match,
+#endif
+	},
+	.probe = mt6797_mt6351_dev_probe,
+};
+
+module_platform_driver(mt6797_mt6351_driver);
+
+/* Module information */
+MODULE_DESCRIPTION("MT6797 MT6351 ALSA SoC machine driver");
+MODULE_AUTHOR("KaiChieh Chuang <kaichieh.chuang@mediatek.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("mt6797 mt6351 soc card");
+
diff --git a/sound/soc/mediatek/mt6797/mt6797-reg.h b/sound/soc/mediatek/mt6797/mt6797-reg.h
new file mode 100644
index 000000000000..978f146c143c
--- /dev/null
+++ b/sound/soc/mediatek/mt6797/mt6797-reg.h
@@ -0,0 +1,1015 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mt6797-reg.h  --  Mediatek 6797 audio driver reg definition
+ *
+ * Copyright (c) 2018 MediaTek Inc.
+ * Author: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
+ */
+
+#ifndef _MT6797_REG_H_
+#define _MT6797_REG_H_
+
+#define AUDIO_TOP_CON0            0x0000
+#define AUDIO_TOP_CON1            0x0004
+#define AUDIO_TOP_CON3            0x000c
+#define AFE_DAC_CON0              0x0010
+#define AFE_DAC_CON1              0x0014
+#define AFE_I2S_CON               0x0018
+#define AFE_DAIBT_CON0            0x001c
+#define AFE_CONN0                 0x0020
+#define AFE_CONN1                 0x0024
+#define AFE_CONN2                 0x0028
+#define AFE_CONN3                 0x002c
+#define AFE_CONN4                 0x0030
+#define AFE_I2S_CON1              0x0034
+#define AFE_I2S_CON2              0x0038
+#define AFE_MRGIF_CON             0x003c
+#define AFE_DL1_BASE              0x0040
+#define AFE_DL1_CUR               0x0044
+#define AFE_DL1_END               0x0048
+#define AFE_I2S_CON3              0x004c
+#define AFE_DL2_BASE              0x0050
+#define AFE_DL2_CUR               0x0054
+#define AFE_DL2_END               0x0058
+#define AFE_CONN5                 0x005c
+#define AFE_CONN_24BIT            0x006c
+#define AFE_AWB_BASE              0x0070
+#define AFE_AWB_END               0x0078
+#define AFE_AWB_CUR               0x007c
+#define AFE_VUL_BASE              0x0080
+#define AFE_VUL_END               0x0088
+#define AFE_VUL_CUR               0x008c
+#define AFE_DAI_BASE              0x0090
+#define AFE_DAI_END               0x0098
+#define AFE_DAI_CUR               0x009c
+#define AFE_CONN6                 0x00bc
+#define AFE_MEMIF_MSB             0x00cc
+#define AFE_MEMIF_MON0            0x00d0
+#define AFE_MEMIF_MON1            0x00d4
+#define AFE_MEMIF_MON2            0x00d8
+#define AFE_MEMIF_MON4            0x00e0
+#define AFE_ADDA_DL_SRC2_CON0     0x0108
+#define AFE_ADDA_DL_SRC2_CON1     0x010c
+#define AFE_ADDA_UL_SRC_CON0      0x0114
+#define AFE_ADDA_UL_SRC_CON1      0x0118
+#define AFE_ADDA_TOP_CON0         0x0120
+#define AFE_ADDA_UL_DL_CON0       0x0124
+#define AFE_ADDA_SRC_DEBUG        0x012c
+#define AFE_ADDA_SRC_DEBUG_MON0   0x0130
+#define AFE_ADDA_SRC_DEBUG_MON1   0x0134
+#define AFE_ADDA_NEWIF_CFG0       0x0138
+#define AFE_ADDA_NEWIF_CFG1       0x013c
+#define AFE_ADDA_NEWIF_CFG2       0x0140
+#define AFE_DMA_CTL               0x0150
+#define AFE_DMA_MON0              0x0154
+#define AFE_DMA_MON1              0x0158
+#define AFE_SIDETONE_DEBUG        0x01d0
+#define AFE_SIDETONE_MON          0x01d4
+#define AFE_SIDETONE_CON0         0x01e0
+#define AFE_SIDETONE_COEFF        0x01e4
+#define AFE_SIDETONE_CON1         0x01e8
+#define AFE_SIDETONE_GAIN         0x01ec
+#define AFE_SGEN_CON0             0x01f0
+#define AFE_SINEGEN_CON_TDM       0x01fc
+#define AFE_TOP_CON0              0x0200
+#define AFE_ADDA_PREDIS_CON0      0x0260
+#define AFE_ADDA_PREDIS_CON1      0x0264
+#define AFE_MRGIF_MON0            0x0270
+#define AFE_MRGIF_MON1            0x0274
+#define AFE_MRGIF_MON2            0x0278
+#define AFE_I2S_MON               0x027c
+#define AFE_MOD_DAI_BASE          0x0330
+#define AFE_MOD_DAI_END           0x0338
+#define AFE_MOD_DAI_CUR           0x033c
+#define AFE_VUL_D2_BASE           0x0350
+#define AFE_VUL_D2_END            0x0358
+#define AFE_VUL_D2_CUR            0x035c
+#define AFE_DL3_BASE              0x0360
+#define AFE_DL3_CUR               0x0364
+#define AFE_DL3_END               0x0368
+#define AFE_HDMI_OUT_CON0         0x0370
+#define AFE_HDMI_BASE             0x0374
+#define AFE_HDMI_CUR              0x0378
+#define AFE_HDMI_END              0x037c
+#define AFE_HDMI_CONN0            0x0390
+#define AFE_IRQ3_MCU_CNT_MON      0x0398
+#define AFE_IRQ4_MCU_CNT_MON      0x039c
+#define AFE_IRQ_MCU_CON           0x03a0
+#define AFE_IRQ_MCU_STATUS        0x03a4
+#define AFE_IRQ_MCU_CLR           0x03a8
+#define AFE_IRQ_MCU_CNT1          0x03ac
+#define AFE_IRQ_MCU_CNT2          0x03b0
+#define AFE_IRQ_MCU_EN            0x03b4
+#define AFE_IRQ_MCU_MON2          0x03b8
+#define AFE_IRQ_MCU_CNT5          0x03bc
+#define AFE_IRQ1_MCU_CNT_MON      0x03c0
+#define AFE_IRQ2_MCU_CNT_MON      0x03c4
+#define AFE_IRQ1_MCU_EN_CNT_MON   0x03c8
+#define AFE_IRQ5_MCU_CNT_MON      0x03cc
+#define AFE_MEMIF_MINLEN          0x03d0
+#define AFE_MEMIF_MAXLEN          0x03d4
+#define AFE_MEMIF_PBUF_SIZE       0x03d8
+#define AFE_IRQ_MCU_CNT7          0x03dc
+#define AFE_IRQ7_MCU_CNT_MON      0x03e0
+#define AFE_IRQ_MCU_CNT3          0x03e4
+#define AFE_IRQ_MCU_CNT4          0x03e8
+#define AFE_APLL1_TUNER_CFG       0x03f0
+#define AFE_APLL2_TUNER_CFG       0x03f4
+#define AFE_MEMIF_HD_MODE         0x03f8
+#define AFE_MEMIF_HDALIGN         0x03fc
+#define AFE_GAIN1_CON0            0x0410
+#define AFE_GAIN1_CON1            0x0414
+#define AFE_GAIN1_CON2            0x0418
+#define AFE_GAIN1_CON3            0x041c
+#define AFE_CONN7                 0x0420
+#define AFE_GAIN1_CUR             0x0424
+#define AFE_GAIN2_CON0            0x0428
+#define AFE_GAIN2_CON1            0x042c
+#define AFE_GAIN2_CON2            0x0430
+#define AFE_GAIN2_CON3            0x0434
+#define AFE_CONN8                 0x0438
+#define AFE_GAIN2_CUR             0x043c
+#define AFE_CONN9                 0x0440
+#define AFE_CONN10                0x0444
+#define AFE_CONN11                0x0448
+#define AFE_CONN12                0x044c
+#define AFE_CONN13                0x0450
+#define AFE_CONN14                0x0454
+#define AFE_CONN15                0x0458
+#define AFE_CONN16                0x045c
+#define AFE_CONN17                0x0460
+#define AFE_CONN18                0x0464
+#define AFE_CONN19                0x0468
+#define AFE_CONN20                0x046c
+#define AFE_CONN21                0x0470
+#define AFE_CONN22                0x0474
+#define AFE_CONN23                0x0478
+#define AFE_CONN24                0x047c
+#define AFE_CONN_RS               0x0494
+#define AFE_CONN_DI               0x0498
+#define AFE_CONN25                0x04b0
+#define AFE_CONN26                0x04b4
+#define AFE_CONN27                0x04b8
+#define AFE_CONN28                0x04bc
+#define AFE_CONN29                0x04c0
+#define AFE_SRAM_DELSEL_CON0      0x04f0
+#define AFE_SRAM_DELSEL_CON1      0x04f4
+#define AFE_ASRC_CON0             0x0500
+#define AFE_ASRC_CON1             0x0504
+#define AFE_ASRC_CON2             0x0508
+#define AFE_ASRC_CON3             0x050c
+#define AFE_ASRC_CON4             0x0510
+#define AFE_ASRC_CON5             0x0514
+#define AFE_ASRC_CON6             0x0518
+#define AFE_ASRC_CON7             0x051c
+#define AFE_ASRC_CON8             0x0520
+#define AFE_ASRC_CON9             0x0524
+#define AFE_ASRC_CON10            0x0528
+#define AFE_ASRC_CON11            0x052c
+#define PCM_INTF_CON1             0x0530
+#define PCM_INTF_CON2             0x0538
+#define PCM2_INTF_CON             0x053c
+#define AFE_TDM_CON1              0x0548
+#define AFE_TDM_CON2              0x054c
+#define AFE_ASRC_CON13            0x0550
+#define AFE_ASRC_CON14            0x0554
+#define AFE_ASRC_CON15            0x0558
+#define AFE_ASRC_CON16            0x055c
+#define AFE_ASRC_CON17            0x0560
+#define AFE_ASRC_CON18            0x0564
+#define AFE_ASRC_CON19            0x0568
+#define AFE_ASRC_CON20            0x056c
+#define AFE_ASRC_CON21            0x0570
+#define CLK_AUDDIV_0              0x05a0
+#define CLK_AUDDIV_1              0x05a4
+#define CLK_AUDDIV_2              0x05a8
+#define CLK_AUDDIV_3              0x05ac
+#define AUDIO_TOP_DBG_CON         0x05c8
+#define AUDIO_TOP_DBG_MON0        0x05cc
+#define AUDIO_TOP_DBG_MON1        0x05d0
+#define AUDIO_TOP_DBG_MON2        0x05d4
+#define AFE_ADDA2_TOP_CON0        0x0600
+#define AFE_ASRC4_CON0            0x06c0
+#define AFE_ASRC4_CON1            0x06c4
+#define AFE_ASRC4_CON2            0x06c8
+#define AFE_ASRC4_CON3            0x06cc
+#define AFE_ASRC4_CON4            0x06d0
+#define AFE_ASRC4_CON5            0x06d4
+#define AFE_ASRC4_CON6            0x06d8
+#define AFE_ASRC4_CON7            0x06dc
+#define AFE_ASRC4_CON8            0x06e0
+#define AFE_ASRC4_CON9            0x06e4
+#define AFE_ASRC4_CON10           0x06e8
+#define AFE_ASRC4_CON11           0x06ec
+#define AFE_ASRC4_CON12           0x06f0
+#define AFE_ASRC4_CON13           0x06f4
+#define AFE_ASRC4_CON14           0x06f8
+#define AFE_ASRC2_CON0            0x0700
+#define AFE_ASRC2_CON1            0x0704
+#define AFE_ASRC2_CON2            0x0708
+#define AFE_ASRC2_CON3            0x070c
+#define AFE_ASRC2_CON4            0x0710
+#define AFE_ASRC2_CON5            0x0714
+#define AFE_ASRC2_CON6            0x0718
+#define AFE_ASRC2_CON7            0x071c
+#define AFE_ASRC2_CON8            0x0720
+#define AFE_ASRC2_CON9            0x0724
+#define AFE_ASRC2_CON10           0x0728
+#define AFE_ASRC2_CON11           0x072c
+#define AFE_ASRC2_CON12           0x0730
+#define AFE_ASRC2_CON13           0x0734
+#define AFE_ASRC2_CON14           0x0738
+#define AFE_ASRC3_CON0            0x0740
+#define AFE_ASRC3_CON1            0x0744
+#define AFE_ASRC3_CON2            0x0748
+#define AFE_ASRC3_CON3            0x074c
+#define AFE_ASRC3_CON4            0x0750
+#define AFE_ASRC3_CON5            0x0754
+#define AFE_ASRC3_CON6            0x0758
+#define AFE_ASRC3_CON7            0x075c
+#define AFE_ASRC3_CON8            0x0760
+#define AFE_ASRC3_CON9            0x0764
+#define AFE_ASRC3_CON10           0x0768
+#define AFE_ASRC3_CON11           0x076c
+#define AFE_ASRC3_CON12           0x0770
+#define AFE_ASRC3_CON13           0x0774
+#define AFE_ASRC3_CON14           0x0778
+#define AFE_GENERAL_REG0          0x0800
+#define AFE_GENERAL_REG1          0x0804
+#define AFE_GENERAL_REG2          0x0808
+#define AFE_GENERAL_REG3          0x080c
+#define AFE_GENERAL_REG4          0x0810
+#define AFE_GENERAL_REG5          0x0814
+#define AFE_GENERAL_REG6          0x0818
+#define AFE_GENERAL_REG7          0x081c
+#define AFE_GENERAL_REG8          0x0820
+#define AFE_GENERAL_REG9          0x0824
+#define AFE_GENERAL_REG10         0x0828
+#define AFE_GENERAL_REG11         0x082c
+#define AFE_GENERAL_REG12         0x0830
+#define AFE_GENERAL_REG13         0x0834
+#define AFE_GENERAL_REG14         0x0838
+#define AFE_GENERAL_REG15         0x083c
+#define AFE_CBIP_CFG0             0x0840
+#define AFE_CBIP_MON0             0x0844
+#define AFE_CBIP_SLV_MUX_MON0     0x0848
+#define AFE_CBIP_SLV_DECODER_MON0 0x084c
+
+#define AFE_MAX_REGISTER AFE_CBIP_SLV_DECODER_MON0
+#define AFE_IRQ_STATUS_BITS 0x5f
+
+/* AUDIO_TOP_CON0 */
+#define AHB_IDLE_EN_INT_SFT                                 30
+#define AHB_IDLE_EN_INT_MASK                                0x1
+#define AHB_IDLE_EN_INT_MASK_SFT                            (0x1 << 30)
+#define AHB_IDLE_EN_EXT_SFT                                 29
+#define AHB_IDLE_EN_EXT_MASK                                0x1
+#define AHB_IDLE_EN_EXT_MASK_SFT                            (0x1 << 29)
+#define PDN_TML_SFT                                         27
+#define PDN_TML_MASK                                        0x1
+#define PDN_TML_MASK_SFT                                    (0x1 << 27)
+#define PDN_DAC_PREDIS_SFT                                  26
+#define PDN_DAC_PREDIS_MASK                                 0x1
+#define PDN_DAC_PREDIS_MASK_SFT                             (0x1 << 26)
+#define PDN_DAC_SFT                                         25
+#define PDN_DAC_MASK                                        0x1
+#define PDN_DAC_MASK_SFT                                    (0x1 << 25)
+#define PDN_ADC_SFT                                         24
+#define PDN_ADC_MASK                                        0x1
+#define PDN_ADC_MASK_SFT                                    (0x1 << 24)
+#define PDN_TDM_CK_SFT                                      20
+#define PDN_TDM_CK_MASK                                     0x1
+#define PDN_TDM_CK_MASK_SFT                                 (0x1 << 20)
+#define PDN_APLL_TUNER_SFT                                  19
+#define PDN_APLL_TUNER_MASK                                 0x1
+#define PDN_APLL_TUNER_MASK_SFT                             (0x1 << 19)
+#define PDN_APLL2_TUNER_SFT                                 18
+#define PDN_APLL2_TUNER_MASK                                0x1
+#define PDN_APLL2_TUNER_MASK_SFT                            (0x1 << 18)
+#define APB3_SEL_SFT                                        14
+#define APB3_SEL_MASK                                       0x1
+#define APB3_SEL_MASK_SFT                                   (0x1 << 14)
+#define APB_R2T_SFT                                         13
+#define APB_R2T_MASK                                        0x1
+#define APB_R2T_MASK_SFT                                    (0x1 << 13)
+#define APB_W2T_SFT                                         12
+#define APB_W2T_MASK                                        0x1
+#define APB_W2T_MASK_SFT                                    (0x1 << 12)
+#define PDN_24M_SFT                                         9
+#define PDN_24M_MASK                                        0x1
+#define PDN_24M_MASK_SFT                                    (0x1 << 9)
+#define PDN_22M_SFT                                         8
+#define PDN_22M_MASK                                        0x1
+#define PDN_22M_MASK_SFT                                    (0x1 << 8)
+#define PDN_ADDA4_ADC_SFT                                   7
+#define PDN_ADDA4_ADC_MASK                                  0x1
+#define PDN_ADDA4_ADC_MASK_SFT                              (0x1 << 7)
+#define PDN_I2S_SFT                                         6
+#define PDN_I2S_MASK                                        0x1
+#define PDN_I2S_MASK_SFT                                    (0x1 << 6)
+#define PDN_AFE_SFT                                         2
+#define PDN_AFE_MASK                                        0x1
+#define PDN_AFE_MASK_SFT                                    (0x1 << 2)
+
+/* AUDIO_TOP_CON1 */
+#define PDN_ADC_HIRES_TML_SFT                               17
+#define PDN_ADC_HIRES_TML_MASK                              0x1
+#define PDN_ADC_HIRES_TML_MASK_SFT                          (0x1 << 17)
+#define PDN_ADC_HIRES_SFT                                   16
+#define PDN_ADC_HIRES_MASK                                  0x1
+#define PDN_ADC_HIRES_MASK_SFT                              (0x1 << 16)
+#define I2S4_BCLK_SW_CG_SFT                                 7
+#define I2S4_BCLK_SW_CG_MASK                                0x1
+#define I2S4_BCLK_SW_CG_MASK_SFT                            (0x1 << 7)
+#define I2S3_BCLK_SW_CG_SFT                                 6
+#define I2S3_BCLK_SW_CG_MASK                                0x1
+#define I2S3_BCLK_SW_CG_MASK_SFT                            (0x1 << 6)
+#define I2S2_BCLK_SW_CG_SFT                                 5
+#define I2S2_BCLK_SW_CG_MASK                                0x1
+#define I2S2_BCLK_SW_CG_MASK_SFT                            (0x1 << 5)
+#define I2S1_BCLK_SW_CG_SFT                                 4
+#define I2S1_BCLK_SW_CG_MASK                                0x1
+#define I2S1_BCLK_SW_CG_MASK_SFT                            (0x1 << 4)
+#define I2S_SOFT_RST2_SFT                                   2
+#define I2S_SOFT_RST2_MASK                                  0x1
+#define I2S_SOFT_RST2_MASK_SFT                              (0x1 << 2)
+#define I2S_SOFT_RST_SFT                                    1
+#define I2S_SOFT_RST_MASK                                   0x1
+#define I2S_SOFT_RST_MASK_SFT                               (0x1 << 1)
+
+/* AFE_DAC_CON0 */
+#define AFE_AWB_RETM_SFT                                    31
+#define AFE_AWB_RETM_MASK                                   0x1
+#define AFE_AWB_RETM_MASK_SFT                               (0x1 << 31)
+#define AFE_DL1_DATA2_RETM_SFT                              30
+#define AFE_DL1_DATA2_RETM_MASK                             0x1
+#define AFE_DL1_DATA2_RETM_MASK_SFT                         (0x1 << 30)
+#define AFE_DL2_RETM_SFT                                    29
+#define AFE_DL2_RETM_MASK                                   0x1
+#define AFE_DL2_RETM_MASK_SFT                               (0x1 << 29)
+#define AFE_DL1_RETM_SFT                                    28
+#define AFE_DL1_RETM_MASK                                   0x1
+#define AFE_DL1_RETM_MASK_SFT                               (0x1 << 28)
+#define AFE_ON_RETM_SFT                                     27
+#define AFE_ON_RETM_MASK                                    0x1
+#define AFE_ON_RETM_MASK_SFT                                (0x1 << 27)
+#define MOD_DAI_DUP_WR_SFT                                  26
+#define MOD_DAI_DUP_WR_MASK                                 0x1
+#define MOD_DAI_DUP_WR_MASK_SFT                             (0x1 << 26)
+#define DAI_MODE_SFT                                        24
+#define DAI_MODE_MASK                                       0x3
+#define DAI_MODE_MASK_SFT                                   (0x3 << 24)
+#define VUL_DATA2_MODE_SFT                                  20
+#define VUL_DATA2_MODE_MASK                                 0xf
+#define VUL_DATA2_MODE_MASK_SFT                             (0xf << 20)
+#define DL1_DATA2_MODE_SFT                                  16
+#define DL1_DATA2_MODE_MASK                                 0xf
+#define DL1_DATA2_MODE_MASK_SFT                             (0xf << 16)
+#define DL3_MODE_SFT                                        12
+#define DL3_MODE_MASK                                       0xf
+#define DL3_MODE_MASK_SFT                                   (0xf << 12)
+#define VUL_DATA2_R_MONO_SFT                                11
+#define VUL_DATA2_R_MONO_MASK                               0x1
+#define VUL_DATA2_R_MONO_MASK_SFT                           (0x1 << 11)
+#define VUL_DATA2_DATA_SFT                                  10
+#define VUL_DATA2_DATA_MASK                                 0x1
+#define VUL_DATA2_DATA_MASK_SFT                             (0x1 << 10)
+#define VUL_DATA2_ON_SFT                                    9
+#define VUL_DATA2_ON_MASK                                   0x1
+#define VUL_DATA2_ON_MASK_SFT                               (0x1 << 9)
+#define DL1_DATA2_ON_SFT                                    8
+#define DL1_DATA2_ON_MASK                                   0x1
+#define DL1_DATA2_ON_MASK_SFT                               (0x1 << 8)
+#define MOD_DAI_ON_SFT                                      7
+#define MOD_DAI_ON_MASK                                     0x1
+#define MOD_DAI_ON_MASK_SFT                                 (0x1 << 7)
+#define AWB_ON_SFT                                          6
+#define AWB_ON_MASK                                         0x1
+#define AWB_ON_MASK_SFT                                     (0x1 << 6)
+#define DL3_ON_SFT                                          5
+#define DL3_ON_MASK                                         0x1
+#define DL3_ON_MASK_SFT                                     (0x1 << 5)
+#define DAI_ON_SFT                                          4
+#define DAI_ON_MASK                                         0x1
+#define DAI_ON_MASK_SFT                                     (0x1 << 4)
+#define VUL_ON_SFT                                          3
+#define VUL_ON_MASK                                         0x1
+#define VUL_ON_MASK_SFT                                     (0x1 << 3)
+#define DL2_ON_SFT                                          2
+#define DL2_ON_MASK                                         0x1
+#define DL2_ON_MASK_SFT                                     (0x1 << 2)
+#define DL1_ON_SFT                                          1
+#define DL1_ON_MASK                                         0x1
+#define DL1_ON_MASK_SFT                                     (0x1 << 1)
+#define AFE_ON_SFT                                          0
+#define AFE_ON_MASK                                         0x1
+#define AFE_ON_MASK_SFT                                     (0x1 << 0)
+
+/* AFE_DAC_CON1 */
+#define MOD_DAI_MODE_SFT                                    30
+#define MOD_DAI_MODE_MASK                                   0x3
+#define MOD_DAI_MODE_MASK_SFT                               (0x3 << 30)
+#define DAI_DUP_WR_SFT                                      29
+#define DAI_DUP_WR_MASK                                     0x1
+#define DAI_DUP_WR_MASK_SFT                                 (0x1 << 29)
+#define VUL_R_MONO_SFT                                      28
+#define VUL_R_MONO_MASK                                     0x1
+#define VUL_R_MONO_MASK_SFT                                 (0x1 << 28)
+#define VUL_DATA_SFT                                        27
+#define VUL_DATA_MASK                                       0x1
+#define VUL_DATA_MASK_SFT                                   (0x1 << 27)
+#define AXI_2X1_CG_DISABLE_SFT                              26
+#define AXI_2X1_CG_DISABLE_MASK                             0x1
+#define AXI_2X1_CG_DISABLE_MASK_SFT                         (0x1 << 26)
+#define AWB_R_MONO_SFT                                      25
+#define AWB_R_MONO_MASK                                     0x1
+#define AWB_R_MONO_MASK_SFT                                 (0x1 << 25)
+#define AWB_DATA_SFT                                        24
+#define AWB_DATA_MASK                                       0x1
+#define AWB_DATA_MASK_SFT                                   (0x1 << 24)
+#define DL3_DATA_SFT                                        23
+#define DL3_DATA_MASK                                       0x1
+#define DL3_DATA_MASK_SFT                                   (0x1 << 23)
+#define DL2_DATA_SFT                                        22
+#define DL2_DATA_MASK                                       0x1
+#define DL2_DATA_MASK_SFT                                   (0x1 << 22)
+#define DL1_DATA_SFT                                        21
+#define DL1_DATA_MASK                                       0x1
+#define DL1_DATA_MASK_SFT                                   (0x1 << 21)
+#define DL1_DATA2_DATA_SFT                                  20
+#define DL1_DATA2_DATA_MASK                                 0x1
+#define DL1_DATA2_DATA_MASK_SFT                             (0x1 << 20)
+#define VUL_MODE_SFT                                        16
+#define VUL_MODE_MASK                                       0xf
+#define VUL_MODE_MASK_SFT                                   (0xf << 16)
+#define AWB_MODE_SFT                                        12
+#define AWB_MODE_MASK                                       0xf
+#define AWB_MODE_MASK_SFT                                   (0xf << 12)
+#define I2S_MODE_SFT                                        8
+#define I2S_MODE_MASK                                       0xf
+#define I2S_MODE_MASK_SFT                                   (0xf << 8)
+#define DL2_MODE_SFT                                        4
+#define DL2_MODE_MASK                                       0xf
+#define DL2_MODE_MASK_SFT                                   (0xf << 4)
+#define DL1_MODE_SFT                                        0
+#define DL1_MODE_MASK                                       0xf
+#define DL1_MODE_MASK_SFT                                   (0xf << 0)
+
+/* AFE_ADDA_DL_SRC2_CON0 */
+#define DL_2_INPUT_MODE_CTL_SFT                             28
+#define DL_2_INPUT_MODE_CTL_MASK                            0xf
+#define DL_2_INPUT_MODE_CTL_MASK_SFT                        (0xf << 28)
+#define DL_2_CH1_SATURATION_EN_CTL_SFT                      27
+#define DL_2_CH1_SATURATION_EN_CTL_MASK                     0x1
+#define DL_2_CH1_SATURATION_EN_CTL_MASK_SFT                 (0x1 << 27)
+#define DL_2_CH2_SATURATION_EN_CTL_SFT                      26
+#define DL_2_CH2_SATURATION_EN_CTL_MASK                     0x1
+#define DL_2_CH2_SATURATION_EN_CTL_MASK_SFT                 (0x1 << 26)
+#define DL_2_OUTPUT_SEL_CTL_SFT                             24
+#define DL_2_OUTPUT_SEL_CTL_MASK                            0x3
+#define DL_2_OUTPUT_SEL_CTL_MASK_SFT                        (0x3 << 24)
+#define DL_2_FADEIN_0START_EN_SFT                           16
+#define DL_2_FADEIN_0START_EN_MASK                          0x3
+#define DL_2_FADEIN_0START_EN_MASK_SFT                      (0x3 << 16)
+#define DL_DISABLE_HW_CG_CTL_SFT                            15
+#define DL_DISABLE_HW_CG_CTL_MASK                           0x1
+#define DL_DISABLE_HW_CG_CTL_MASK_SFT                       (0x1 << 15)
+#define C_DATA_EN_SEL_CTL_PRE_SFT                           14
+#define C_DATA_EN_SEL_CTL_PRE_MASK                          0x1
+#define C_DATA_EN_SEL_CTL_PRE_MASK_SFT                      (0x1 << 14)
+#define DL_2_SIDE_TONE_ON_CTL_PRE_SFT                       13
+#define DL_2_SIDE_TONE_ON_CTL_PRE_MASK                      0x1
+#define DL_2_SIDE_TONE_ON_CTL_PRE_MASK_SFT                  (0x1 << 13)
+#define DL_2_MUTE_CH1_OFF_CTL_PRE_SFT                       12
+#define DL_2_MUTE_CH1_OFF_CTL_PRE_MASK                      0x1
+#define DL_2_MUTE_CH1_OFF_CTL_PRE_MASK_SFT                  (0x1 << 12)
+#define DL_2_MUTE_CH2_OFF_CTL_PRE_SFT                       11
+#define DL_2_MUTE_CH2_OFF_CTL_PRE_MASK                      0x1
+#define DL_2_MUTE_CH2_OFF_CTL_PRE_MASK_SFT                  (0x1 << 11)
+#define DL2_ARAMPSP_CTL_PRE_SFT                             9
+#define DL2_ARAMPSP_CTL_PRE_MASK                            0x3
+#define DL2_ARAMPSP_CTL_PRE_MASK_SFT                        (0x3 << 9)
+#define DL_2_IIRMODE_CTL_PRE_SFT                            6
+#define DL_2_IIRMODE_CTL_PRE_MASK                           0x7
+#define DL_2_IIRMODE_CTL_PRE_MASK_SFT                       (0x7 << 6)
+#define DL_2_VOICE_MODE_CTL_PRE_SFT                         5
+#define DL_2_VOICE_MODE_CTL_PRE_MASK                        0x1
+#define DL_2_VOICE_MODE_CTL_PRE_MASK_SFT                    (0x1 << 5)
+#define D2_2_MUTE_CH1_ON_CTL_PRE_SFT                        4
+#define D2_2_MUTE_CH1_ON_CTL_PRE_MASK                       0x1
+#define D2_2_MUTE_CH1_ON_CTL_PRE_MASK_SFT                   (0x1 << 4)
+#define D2_2_MUTE_CH2_ON_CTL_PRE_SFT                        3
+#define D2_2_MUTE_CH2_ON_CTL_PRE_MASK                       0x1
+#define D2_2_MUTE_CH2_ON_CTL_PRE_MASK_SFT                   (0x1 << 3)
+#define DL_2_IIR_ON_CTL_PRE_SFT                             2
+#define DL_2_IIR_ON_CTL_PRE_MASK                            0x1
+#define DL_2_IIR_ON_CTL_PRE_MASK_SFT                        (0x1 << 2)
+#define DL_2_GAIN_ON_CTL_PRE_SFT                            1
+#define DL_2_GAIN_ON_CTL_PRE_MASK                           0x1
+#define DL_2_GAIN_ON_CTL_PRE_MASK_SFT                       (0x1 << 1)
+#define DL_2_SRC_ON_TMP_CTL_PRE_SFT                         0
+#define DL_2_SRC_ON_TMP_CTL_PRE_MASK                        0x1
+#define DL_2_SRC_ON_TMP_CTL_PRE_MASK_SFT                    (0x1 << 0)
+
+/* AFE_ADDA_DL_SRC2_CON1 */
+#define DL_2_GAIN_CTL_PRE_SFT                               16
+#define DL_2_GAIN_CTL_PRE_MASK                              0xffff
+#define DL_2_GAIN_CTL_PRE_MASK_SFT                          (0xffff << 16)
+#define DL_2_GAIN_MODE_CTL_SFT                              0
+#define DL_2_GAIN_MODE_CTL_MASK                             0x1
+#define DL_2_GAIN_MODE_CTL_MASK_SFT                         (0x1 << 0)
+
+/* AFE_ADDA_UL_SRC_CON0 */
+#define C_COMB_OUT_SIN_GEN_CTL_SFT                          31
+#define C_COMB_OUT_SIN_GEN_CTL_MASK                         0x1
+#define C_COMB_OUT_SIN_GEN_CTL_MASK_SFT                     (0x1 << 31)
+#define C_BASEBAND_SIN_GEN_CTL_SFT                          30
+#define C_BASEBAND_SIN_GEN_CTL_MASK                         0x1
+#define C_BASEBAND_SIN_GEN_CTL_MASK_SFT                     (0x1 << 30)
+#define C_DIGMIC_PHASE_SEL_CH1_CTL_SFT                      27
+#define C_DIGMIC_PHASE_SEL_CH1_CTL_MASK                     0x7
+#define C_DIGMIC_PHASE_SEL_CH1_CTL_MASK_SFT                 (0x7 << 27)
+#define C_DIGMIC_PHASE_SEL_CH2_CTL_SFT                      24
+#define C_DIGMIC_PHASE_SEL_CH2_CTL_MASK                     0x7
+#define C_DIGMIC_PHASE_SEL_CH2_CTL_MASK_SFT                 (0x7 << 24)
+#define C_TWO_DIGITAL_MIC_CTL_SFT                           23
+#define C_TWO_DIGITAL_MIC_CTL_MASK                          0x1
+#define C_TWO_DIGITAL_MIC_CTL_MASK_SFT                      (0x1 << 23)
+#define UL_MODE_3P25M_CH2_CTL_SFT                           22
+#define UL_MODE_3P25M_CH2_CTL_MASK                          0x1
+#define UL_MODE_3P25M_CH2_CTL_MASK_SFT                      (0x1 << 22)
+#define UL_MODE_3P25M_CH1_CTL_SFT                           21
+#define UL_MODE_3P25M_CH1_CTL_MASK                          0x1
+#define UL_MODE_3P25M_CH1_CTL_MASK_SFT                      (0x1 << 21)
+#define UL_SRC_USE_CIC_OUT_CTL_SFT                          20
+#define UL_SRC_USE_CIC_OUT_CTL_MASK                         0x1
+#define UL_SRC_USE_CIC_OUT_CTL_MASK_SFT                     (0x1 << 20)
+#define UL_VOICE_MODE_CH1_CH2_CTL_SFT                       17
+#define UL_VOICE_MODE_CH1_CH2_CTL_MASK                      0x7
+#define UL_VOICE_MODE_CH1_CH2_CTL_MASK_SFT                  (0x7 << 17)
+#define DMIC_LOW_POWER_MODE_CTL_SFT                         14
+#define DMIC_LOW_POWER_MODE_CTL_MASK                        0x3
+#define DMIC_LOW_POWER_MODE_CTL_MASK_SFT                    (0x3 << 14)
+#define DMIC_48K_SEL_CTL_SFT                                13
+#define DMIC_48K_SEL_CTL_MASK                               0x1
+#define DMIC_48K_SEL_CTL_MASK_SFT                           (0x1 << 13)
+#define UL_DISABLE_HW_CG_CTL_SFT                            12
+#define UL_DISABLE_HW_CG_CTL_MASK                           0x1
+#define UL_DISABLE_HW_CG_CTL_MASK_SFT                       (0x1 << 12)
+#define UL_IIR_ON_TMP_CTL_SFT                               10
+#define UL_IIR_ON_TMP_CTL_MASK                              0x1
+#define UL_IIR_ON_TMP_CTL_MASK_SFT                          (0x1 << 10)
+#define UL_IIRMODE_CTL_SFT                                  7
+#define UL_IIRMODE_CTL_MASK                                 0x7
+#define UL_IIRMODE_CTL_MASK_SFT                             (0x7 << 7)
+#define DIGMIC_3P25M_1P625M_SEL_CTL_SFT                     5
+#define DIGMIC_3P25M_1P625M_SEL_CTL_MASK                    0x1
+#define DIGMIC_3P25M_1P625M_SEL_CTL_MASK_SFT                (0x1 << 5)
+#define AGC_260K_SEL_CH2_CTL_SFT                            4
+#define AGC_260K_SEL_CH2_CTL_MASK                           0x1
+#define AGC_260K_SEL_CH2_CTL_MASK_SFT                       (0x1 << 4)
+#define AGC_260K_SEL_CH1_CTL_SFT                            3
+#define AGC_260K_SEL_CH1_CTL_MASK                           0x1
+#define AGC_260K_SEL_CH1_CTL_MASK_SFT                       (0x1 << 3)
+#define UL_LOOP_BACK_MODE_CTL_SFT                           2
+#define UL_LOOP_BACK_MODE_CTL_MASK                          0x1
+#define UL_LOOP_BACK_MODE_CTL_MASK_SFT                      (0x1 << 2)
+#define UL_SDM_3_LEVEL_CTL_SFT                              1
+#define UL_SDM_3_LEVEL_CTL_MASK                             0x1
+#define UL_SDM_3_LEVEL_CTL_MASK_SFT                         (0x1 << 1)
+#define UL_SRC_ON_TMP_CTL_SFT                               0
+#define UL_SRC_ON_TMP_CTL_MASK                              0x1
+#define UL_SRC_ON_TMP_CTL_MASK_SFT                          (0x1 << 0)
+
+/* AFE_ADDA_UL_SRC_CON1 */
+#define C_SDM_RESET_CTL_SFT                                 31
+#define C_SDM_RESET_CTL_MASK                                0x1
+#define C_SDM_RESET_CTL_MASK_SFT                            (0x1 << 31)
+#define ADITHON_CTL_SFT                                     30
+#define ADITHON_CTL_MASK                                    0x1
+#define ADITHON_CTL_MASK_SFT                                (0x1 << 30)
+#define ADITHVAL_CTL_SFT                                    28
+#define ADITHVAL_CTL_MASK                                   0x3
+#define ADITHVAL_CTL_MASK_SFT                               (0x3 << 28)
+#define C_DAC_EN_CTL_SFT                                    27
+#define C_DAC_EN_CTL_MASK                                   0x1
+#define C_DAC_EN_CTL_MASK_SFT                               (0x1 << 27)
+#define C_MUTE_SW_CTL_SFT                                   26
+#define C_MUTE_SW_CTL_MASK                                  0x1
+#define C_MUTE_SW_CTL_MASK_SFT                              (0x1 << 26)
+#define ASDM_SRC_SEL_CTL_SFT                                25
+#define ASDM_SRC_SEL_CTL_MASK                               0x1
+#define ASDM_SRC_SEL_CTL_MASK_SFT                           (0x1 << 25)
+#define C_AMP_DIV_CH2_CTL_SFT                               21
+#define C_AMP_DIV_CH2_CTL_MASK                              0x7
+#define C_AMP_DIV_CH2_CTL_MASK_SFT                          (0x7 << 21)
+#define C_FREQ_DIV_CH2_CTL_SFT                              16
+#define C_FREQ_DIV_CH2_CTL_MASK                             0x1f
+#define C_FREQ_DIV_CH2_CTL_MASK_SFT                         (0x1f << 16)
+#define C_SINE_MODE_CH2_CTL_SFT                             12
+#define C_SINE_MODE_CH2_CTL_MASK                            0xf
+#define C_SINE_MODE_CH2_CTL_MASK_SFT                        (0xf << 12)
+#define C_AMP_DIV_CH1_CTL_SFT                               9
+#define C_AMP_DIV_CH1_CTL_MASK                              0x7
+#define C_AMP_DIV_CH1_CTL_MASK_SFT                          (0x7 << 9)
+#define C_FREQ_DIV_CH1_CTL_SFT                              4
+#define C_FREQ_DIV_CH1_CTL_MASK                             0x1f
+#define C_FREQ_DIV_CH1_CTL_MASK_SFT                         (0x1f << 4)
+#define C_SINE_MODE_CH1_CTL_SFT                             0
+#define C_SINE_MODE_CH1_CTL_MASK                            0xf
+#define C_SINE_MODE_CH1_CTL_MASK_SFT                        (0xf << 0)
+
+/* AFE_ADDA_TOP_CON0 */
+#define C_LOOP_BACK_MODE_CTL_SFT                            12
+#define C_LOOP_BACK_MODE_CTL_MASK                           0xf
+#define C_LOOP_BACK_MODE_CTL_MASK_SFT                       (0xf << 12)
+#define C_EXT_ADC_CTL_SFT                                   0
+#define C_EXT_ADC_CTL_MASK                                  0x1
+#define C_EXT_ADC_CTL_MASK_SFT                              (0x1 << 0)
+
+/* AFE_ADDA_UL_DL_CON0 */
+#define AFE_UL_DL_CON0_RESERVED_SFT                         1
+#define AFE_UL_DL_CON0_RESERVED_MASK                        0x3fff
+#define AFE_UL_DL_CON0_RESERVED_MASK_SFT                    (0x3fff << 1)
+#define ADDA_AFE_ON_SFT                                     0
+#define ADDA_AFE_ON_MASK                                    0x1
+#define ADDA_AFE_ON_MASK_SFT                                (0x1 << 0)
+
+/* AFE_IRQ_MCU_CON */
+#define IRQ7_MCU_MODE_SFT                                   24
+#define IRQ7_MCU_MODE_MASK                                  0xf
+#define IRQ7_MCU_MODE_MASK_SFT                              (0xf << 24)
+#define IRQ4_MCU_MODE_SFT                                   20
+#define IRQ4_MCU_MODE_MASK                                  0xf
+#define IRQ4_MCU_MODE_MASK_SFT                              (0xf << 20)
+#define IRQ3_MCU_MODE_SFT                                   16
+#define IRQ3_MCU_MODE_MASK                                  0xf
+#define IRQ3_MCU_MODE_MASK_SFT                              (0xf << 16)
+#define IRQ7_MCU_ON_SFT                                     14
+#define IRQ7_MCU_ON_MASK                                    0x1
+#define IRQ7_MCU_ON_MASK_SFT                                (0x1 << 14)
+#define IRQ5_MCU_ON_SFT                                     12
+#define IRQ5_MCU_ON_MASK                                    0x1
+#define IRQ5_MCU_ON_MASK_SFT                                (0x1 << 12)
+#define IRQ2_MCU_MODE_SFT                                   8
+#define IRQ2_MCU_MODE_MASK                                  0xf
+#define IRQ2_MCU_MODE_MASK_SFT                              (0xf << 8)
+#define IRQ1_MCU_MODE_SFT                                   4
+#define IRQ1_MCU_MODE_MASK                                  0xf
+#define IRQ1_MCU_MODE_MASK_SFT                              (0xf << 4)
+#define IRQ4_MCU_ON_SFT                                     3
+#define IRQ4_MCU_ON_MASK                                    0x1
+#define IRQ4_MCU_ON_MASK_SFT                                (0x1 << 3)
+#define IRQ3_MCU_ON_SFT                                     2
+#define IRQ3_MCU_ON_MASK                                    0x1
+#define IRQ3_MCU_ON_MASK_SFT                                (0x1 << 2)
+#define IRQ2_MCU_ON_SFT                                     1
+#define IRQ2_MCU_ON_MASK                                    0x1
+#define IRQ2_MCU_ON_MASK_SFT                                (0x1 << 1)
+#define IRQ1_MCU_ON_SFT                                     0
+#define IRQ1_MCU_ON_MASK                                    0x1
+#define IRQ1_MCU_ON_MASK_SFT                                (0x1 << 0)
+
+/* AFE_IRQ_MCU_EN */
+#define AFE_IRQ_CM4_EN_SFT                                  16
+#define AFE_IRQ_CM4_EN_MASK                                 0x7f
+#define AFE_IRQ_CM4_EN_MASK_SFT                             (0x7f << 16)
+#define AFE_IRQ_MD32_EN_SFT                                 8
+#define AFE_IRQ_MD32_EN_MASK                                0x7f
+#define AFE_IRQ_MD32_EN_MASK_SFT                            (0x7f << 8)
+#define AFE_IRQ_MCU_EN_SFT                                  0
+#define AFE_IRQ_MCU_EN_MASK                                 0x7f
+#define AFE_IRQ_MCU_EN_MASK_SFT                             (0x7f << 0)
+
+/* AFE_IRQ_MCU_CLR */
+#define IRQ7_MCU_CLR_SFT                                    6
+#define IRQ7_MCU_CLR_MASK                                   0x1
+#define IRQ7_MCU_CLR_MASK_SFT                               (0x1 << 6)
+#define IRQ5_MCU_CLR_SFT                                    4
+#define IRQ5_MCU_CLR_MASK                                   0x1
+#define IRQ5_MCU_CLR_MASK_SFT                               (0x1 << 4)
+#define IRQ4_MCU_CLR_SFT                                    3
+#define IRQ4_MCU_CLR_MASK                                   0x1
+#define IRQ4_MCU_CLR_MASK_SFT                               (0x1 << 3)
+#define IRQ3_MCU_CLR_SFT                                    2
+#define IRQ3_MCU_CLR_MASK                                   0x1
+#define IRQ3_MCU_CLR_MASK_SFT                               (0x1 << 2)
+#define IRQ2_MCU_CLR_SFT                                    1
+#define IRQ2_MCU_CLR_MASK                                   0x1
+#define IRQ2_MCU_CLR_MASK_SFT                               (0x1 << 1)
+#define IRQ1_MCU_CLR_SFT                                    0
+#define IRQ1_MCU_CLR_MASK                                   0x1
+#define IRQ1_MCU_CLR_MASK_SFT                               (0x1 << 0)
+
+/* AFE_IRQ_MCU_CNT1 */
+#define AFE_IRQ_MCU_CNT1_SFT                                0
+#define AFE_IRQ_MCU_CNT1_MASK                               0x3ffff
+#define AFE_IRQ_MCU_CNT1_MASK_SFT                           (0x3ffff << 0)
+
+/* AFE_IRQ_MCU_CNT2 */
+#define AFE_IRQ_MCU_CNT2_SFT                                0
+#define AFE_IRQ_MCU_CNT2_MASK                               0x3ffff
+#define AFE_IRQ_MCU_CNT2_MASK_SFT                           (0x3ffff << 0)
+
+/* AFE_IRQ_MCU_CNT3 */
+#define AFE_IRQ_MCU_CNT3_SFT                                0
+#define AFE_IRQ_MCU_CNT3_MASK                               0x3ffff
+#define AFE_IRQ_MCU_CNT3_MASK_SFT                           (0x3ffff << 0)
+
+/* AFE_IRQ_MCU_CNT4 */
+#define AFE_IRQ_MCU_CNT4_SFT                                0
+#define AFE_IRQ_MCU_CNT4_MASK                               0x3ffff
+#define AFE_IRQ_MCU_CNT4_MASK_SFT                           (0x3ffff << 0)
+
+/* AFE_IRQ_MCU_CNT5 */
+#define AFE_IRQ_MCU_CNT5_SFT                                0
+#define AFE_IRQ_MCU_CNT5_MASK                               0x3ffff
+#define AFE_IRQ_MCU_CNT5_MASK_SFT                           (0x3ffff << 0)
+
+/* AFE_IRQ_MCU_CNT7 */
+#define AFE_IRQ_MCU_CNT7_SFT                                0
+#define AFE_IRQ_MCU_CNT7_MASK                               0x3ffff
+#define AFE_IRQ_MCU_CNT7_MASK_SFT                           (0x3ffff << 0)
+
+/* AFE_MEMIF_MSB */
+#define CPU_COMPACT_MODE_SFT                                23
+#define CPU_COMPACT_MODE_MASK                               0x1
+#define CPU_COMPACT_MODE_MASK_SFT                           (0x1 << 23)
+#define CPU_HD_ALIGN_SFT                                    22
+#define CPU_HD_ALIGN_MASK                                   0x1
+#define CPU_HD_ALIGN_MASK_SFT                               (0x1 << 22)
+
+/* AFE_MEMIF_HD_MODE */
+#define HDMI_HD_SFT                                         20
+#define HDMI_HD_MASK                                        0x3
+#define HDMI_HD_MASK_SFT                                    (0x3 << 20)
+#define MOD_DAI_HD_SFT                                      18
+#define MOD_DAI_HD_MASK                                     0x3
+#define MOD_DAI_HD_MASK_SFT                                 (0x3 << 18)
+#define DAI_HD_SFT                                          16
+#define DAI_HD_MASK                                         0x3
+#define DAI_HD_MASK_SFT                                     (0x3 << 16)
+#define VUL_DATA2_HD_SFT                                    12
+#define VUL_DATA2_HD_MASK                                   0x3
+#define VUL_DATA2_HD_MASK_SFT                               (0x3 << 12)
+#define VUL_HD_SFT                                          10
+#define VUL_HD_MASK                                         0x3
+#define VUL_HD_MASK_SFT                                     (0x3 << 10)
+#define AWB_HD_SFT                                          8
+#define AWB_HD_MASK                                         0x3
+#define AWB_HD_MASK_SFT                                     (0x3 << 8)
+#define DL3_HD_SFT                                          6
+#define DL3_HD_MASK                                         0x3
+#define DL3_HD_MASK_SFT                                     (0x3 << 6)
+#define DL2_HD_SFT                                          4
+#define DL2_HD_MASK                                         0x3
+#define DL2_HD_MASK_SFT                                     (0x3 << 4)
+#define DL1_DATA2_HD_SFT                                    2
+#define DL1_DATA2_HD_MASK                                   0x3
+#define DL1_DATA2_HD_MASK_SFT                               (0x3 << 2)
+#define DL1_HD_SFT                                          0
+#define DL1_HD_MASK                                         0x3
+#define DL1_HD_MASK_SFT                                     (0x3 << 0)
+
+/* AFE_MEMIF_HDALIGN */
+#define HDMI_NORMAL_MODE_SFT                                26
+#define HDMI_NORMAL_MODE_MASK                               0x1
+#define HDMI_NORMAL_MODE_MASK_SFT                           (0x1 << 26)
+#define MOD_DAI_NORMAL_MODE_SFT                             25
+#define MOD_DAI_NORMAL_MODE_MASK                            0x1
+#define MOD_DAI_NORMAL_MODE_MASK_SFT                        (0x1 << 25)
+#define DAI_NORMAL_MODE_SFT                                 24
+#define DAI_NORMAL_MODE_MASK                                0x1
+#define DAI_NORMAL_MODE_MASK_SFT                            (0x1 << 24)
+#define VUL_DATA2_NORMAL_MODE_SFT                           22
+#define VUL_DATA2_NORMAL_MODE_MASK                          0x1
+#define VUL_DATA2_NORMAL_MODE_MASK_SFT                      (0x1 << 22)
+#define VUL_NORMAL_MODE_SFT                                 21
+#define VUL_NORMAL_MODE_MASK                                0x1
+#define VUL_NORMAL_MODE_MASK_SFT                            (0x1 << 21)
+#define AWB_NORMAL_MODE_SFT                                 20
+#define AWB_NORMAL_MODE_MASK                                0x1
+#define AWB_NORMAL_MODE_MASK_SFT                            (0x1 << 20)
+#define DL3_NORMAL_MODE_SFT                                 19
+#define DL3_NORMAL_MODE_MASK                                0x1
+#define DL3_NORMAL_MODE_MASK_SFT                            (0x1 << 19)
+#define DL2_NORMAL_MODE_SFT                                 18
+#define DL2_NORMAL_MODE_MASK                                0x1
+#define DL2_NORMAL_MODE_MASK_SFT                            (0x1 << 18)
+#define DL1_DATA2_NORMAL_MODE_SFT                           17
+#define DL1_DATA2_NORMAL_MODE_MASK                          0x1
+#define DL1_DATA2_NORMAL_MODE_MASK_SFT                      (0x1 << 17)
+#define DL1_NORMAL_MODE_SFT                                 16
+#define DL1_NORMAL_MODE_MASK                                0x1
+#define DL1_NORMAL_MODE_MASK_SFT                            (0x1 << 16)
+#define HDMI_HD_ALIGN_SFT                                   10
+#define HDMI_HD_ALIGN_MASK                                  0x1
+#define HDMI_HD_ALIGN_MASK_SFT                              (0x1 << 10)
+#define MOD_DAI_HD_ALIGN_SFT                                9
+#define MOD_DAI_HD_ALIGN_MASK                               0x1
+#define MOD_DAI_HD_ALIGN_MASK_SFT                           (0x1 << 9)
+#define DAI_ALIGN_SFT                                       8
+#define DAI_ALIGN_MASK                                      0x1
+#define DAI_ALIGN_MASK_SFT                                  (0x1 << 8)
+#define VUL2_HD_ALIGN_SFT                                   7
+#define VUL2_HD_ALIGN_MASK                                  0x1
+#define VUL2_HD_ALIGN_MASK_SFT                              (0x1 << 7)
+#define VUL_DATA2_HD_ALIGN_SFT                              6
+#define VUL_DATA2_HD_ALIGN_MASK                             0x1
+#define VUL_DATA2_HD_ALIGN_MASK_SFT                         (0x1 << 6)
+#define VUL_HD_ALIGN_SFT                                    5
+#define VUL_HD_ALIGN_MASK                                   0x1
+#define VUL_HD_ALIGN_MASK_SFT                               (0x1 << 5)
+#define AWB_HD_ALIGN_SFT                                    4
+#define AWB_HD_ALIGN_MASK                                   0x1
+#define AWB_HD_ALIGN_MASK_SFT                               (0x1 << 4)
+#define DL3_HD_ALIGN_SFT                                    3
+#define DL3_HD_ALIGN_MASK                                   0x1
+#define DL3_HD_ALIGN_MASK_SFT                               (0x1 << 3)
+#define DL2_HD_ALIGN_SFT                                    2
+#define DL2_HD_ALIGN_MASK                                   0x1
+#define DL2_HD_ALIGN_MASK_SFT                               (0x1 << 2)
+#define DL1_DATA2_HD_ALIGN_SFT                              1
+#define DL1_DATA2_HD_ALIGN_MASK                             0x1
+#define DL1_DATA2_HD_ALIGN_MASK_SFT                         (0x1 << 1)
+#define DL1_HD_ALIGN_SFT                                    0
+#define DL1_HD_ALIGN_MASK                                   0x1
+#define DL1_HD_ALIGN_MASK_SFT                               (0x1 << 0)
+
+/* PCM_INTF_CON1 */
+#define PCM_FIX_VALUE_SEL_SFT                               31
+#define PCM_FIX_VALUE_SEL_MASK                              0x1
+#define PCM_FIX_VALUE_SEL_MASK_SFT                          (0x1 << 31)
+#define PCM_BUFFER_LOOPBACK_SFT                             30
+#define PCM_BUFFER_LOOPBACK_MASK                            0x1
+#define PCM_BUFFER_LOOPBACK_MASK_SFT                        (0x1 << 30)
+#define PCM_PARALLEL_LOOPBACK_SFT                           29
+#define PCM_PARALLEL_LOOPBACK_MASK                          0x1
+#define PCM_PARALLEL_LOOPBACK_MASK_SFT                      (0x1 << 29)
+#define PCM_SERIAL_LOOPBACK_SFT                             28
+#define PCM_SERIAL_LOOPBACK_MASK                            0x1
+#define PCM_SERIAL_LOOPBACK_MASK_SFT                        (0x1 << 28)
+#define PCM_DAI_PCM_LOOPBACK_SFT                            27
+#define PCM_DAI_PCM_LOOPBACK_MASK                           0x1
+#define PCM_DAI_PCM_LOOPBACK_MASK_SFT                       (0x1 << 27)
+#define PCM_I2S_PCM_LOOPBACK_SFT                            26
+#define PCM_I2S_PCM_LOOPBACK_MASK                           0x1
+#define PCM_I2S_PCM_LOOPBACK_MASK_SFT                       (0x1 << 26)
+#define PCM_SYNC_DELSEL_SFT                                 25
+#define PCM_SYNC_DELSEL_MASK                                0x1
+#define PCM_SYNC_DELSEL_MASK_SFT                            (0x1 << 25)
+#define PCM_TX_LR_SWAP_SFT                                  24
+#define PCM_TX_LR_SWAP_MASK                                 0x1
+#define PCM_TX_LR_SWAP_MASK_SFT                             (0x1 << 24)
+#define PCM_SYNC_OUT_INV_SFT                                23
+#define PCM_SYNC_OUT_INV_MASK                               0x1
+#define PCM_SYNC_OUT_INV_MASK_SFT                           (0x1 << 23)
+#define PCM_BCLK_OUT_INV_SFT                                22
+#define PCM_BCLK_OUT_INV_MASK                               0x1
+#define PCM_BCLK_OUT_INV_MASK_SFT                           (0x1 << 22)
+#define PCM_SYNC_IN_INV_SFT                                 21
+#define PCM_SYNC_IN_INV_MASK                                0x1
+#define PCM_SYNC_IN_INV_MASK_SFT                            (0x1 << 21)
+#define PCM_BCLK_IN_INV_SFT                                 20
+#define PCM_BCLK_IN_INV_MASK                                0x1
+#define PCM_BCLK_IN_INV_MASK_SFT                            (0x1 << 20)
+#define PCM_TX_LCH_RPT_SFT                                  19
+#define PCM_TX_LCH_RPT_MASK                                 0x1
+#define PCM_TX_LCH_RPT_MASK_SFT                             (0x1 << 19)
+#define PCM_VBT_16K_MODE_SFT                                18
+#define PCM_VBT_16K_MODE_MASK                               0x1
+#define PCM_VBT_16K_MODE_MASK_SFT                           (0x1 << 18)
+#define PCM_EXT_MODEM_SFT                                   17
+#define PCM_EXT_MODEM_MASK                                  0x1
+#define PCM_EXT_MODEM_MASK_SFT                              (0x1 << 17)
+#define PCM_24BIT_SFT                                       16
+#define PCM_24BIT_MASK                                      0x1
+#define PCM_24BIT_MASK_SFT                                  (0x1 << 16)
+#define PCM_WLEN_SFT                                        14
+#define PCM_WLEN_MASK                                       0x3
+#define PCM_WLEN_MASK_SFT                                   (0x3 << 14)
+#define PCM_SYNC_LENGTH_SFT                                 9
+#define PCM_SYNC_LENGTH_MASK                                0x1f
+#define PCM_SYNC_LENGTH_MASK_SFT                            (0x1f << 9)
+#define PCM_SYNC_TYPE_SFT                                   8
+#define PCM_SYNC_TYPE_MASK                                  0x1
+#define PCM_SYNC_TYPE_MASK_SFT                              (0x1 << 8)
+#define PCM_BT_MODE_SFT                                     7
+#define PCM_BT_MODE_MASK                                    0x1
+#define PCM_BT_MODE_MASK_SFT                                (0x1 << 7)
+#define PCM_BYP_ASRC_SFT                                    6
+#define PCM_BYP_ASRC_MASK                                   0x1
+#define PCM_BYP_ASRC_MASK_SFT                               (0x1 << 6)
+#define PCM_SLAVE_SFT                                       5
+#define PCM_SLAVE_MASK                                      0x1
+#define PCM_SLAVE_MASK_SFT                                  (0x1 << 5)
+#define PCM_MODE_SFT                                        3
+#define PCM_MODE_MASK                                       0x3
+#define PCM_MODE_MASK_SFT                                   (0x3 << 3)
+#define PCM_FMT_SFT                                         1
+#define PCM_FMT_MASK                                        0x3
+#define PCM_FMT_MASK_SFT                                    (0x3 << 1)
+#define PCM_EN_SFT                                          0
+#define PCM_EN_MASK                                         0x1
+#define PCM_EN_MASK_SFT                                     (0x1 << 0)
+
+/* PCM_INTF_CON2 */
+#define PCM1_TX_FIFO_OV_SFT                                 31
+#define PCM1_TX_FIFO_OV_MASK                                0x1
+#define PCM1_TX_FIFO_OV_MASK_SFT                            (0x1 << 31)
+#define PCM1_RX_FIFO_OV_SFT                                 30
+#define PCM1_RX_FIFO_OV_MASK                                0x1
+#define PCM1_RX_FIFO_OV_MASK_SFT                            (0x1 << 30)
+#define PCM2_TX_FIFO_OV_SFT                                 29
+#define PCM2_TX_FIFO_OV_MASK                                0x1
+#define PCM2_TX_FIFO_OV_MASK_SFT                            (0x1 << 29)
+#define PCM2_RX_FIFO_OV_SFT                                 28
+#define PCM2_RX_FIFO_OV_MASK                                0x1
+#define PCM2_RX_FIFO_OV_MASK_SFT                            (0x1 << 28)
+#define PCM1_SYNC_GLITCH_SFT                                27
+#define PCM1_SYNC_GLITCH_MASK                               0x1
+#define PCM1_SYNC_GLITCH_MASK_SFT                           (0x1 << 27)
+#define PCM2_SYNC_GLITCH_SFT                                26
+#define PCM2_SYNC_GLITCH_MASK                               0x1
+#define PCM2_SYNC_GLITCH_MASK_SFT                           (0x1 << 26)
+#define PCM1_PCM2_LOOPBACK_SFT                              15
+#define PCM1_PCM2_LOOPBACK_MASK                             0x1
+#define PCM1_PCM2_LOOPBACK_MASK_SFT                         (0x1 << 15)
+#define DAI_PCM_LOOPBACK_CH_SFT                             13
+#define DAI_PCM_LOOPBACK_CH_MASK                            0x1
+#define DAI_PCM_LOOPBACK_CH_MASK_SFT                        (0x1 << 13)
+#define I2S_PCM_LOOPBACK_CH_SFT                             12
+#define I2S_PCM_LOOPBACK_CH_MASK                            0x1
+#define I2S_PCM_LOOPBACK_CH_MASK_SFT                        (0x1 << 12)
+#define PCM_USE_MD3_SFT                                     8
+#define PCM_USE_MD3_MASK                                    0x1
+#define PCM_USE_MD3_MASK_SFT                                (0x1 << 8)
+#define TX_FIX_VALUE_SFT                                    0
+#define TX_FIX_VALUE_MASK                                   0xff
+#define TX_FIX_VALUE_MASK_SFT                               (0xff << 0)
+
+/* PCM2_INTF_CON */
+#define PCM2_TX_FIX_VALUE_SFT                                24
+#define PCM2_TX_FIX_VALUE_MASK                               0xff
+#define PCM2_TX_FIX_VALUE_MASK_SFT                           (0xff << 24)
+#define PCM2_FIX_VALUE_SEL_SFT                               23
+#define PCM2_FIX_VALUE_SEL_MASK                              0x1
+#define PCM2_FIX_VALUE_SEL_MASK_SFT                          (0x1 << 23)
+#define PCM2_BUFFER_LOOPBACK_SFT                             22
+#define PCM2_BUFFER_LOOPBACK_MASK                            0x1
+#define PCM2_BUFFER_LOOPBACK_MASK_SFT                        (0x1 << 22)
+#define PCM2_PARALLEL_LOOPBACK_SFT                           21
+#define PCM2_PARALLEL_LOOPBACK_MASK                          0x1
+#define PCM2_PARALLEL_LOOPBACK_MASK_SFT                      (0x1 << 21)
+#define PCM2_SERIAL_LOOPBACK_SFT                             20
+#define PCM2_SERIAL_LOOPBACK_MASK                            0x1
+#define PCM2_SERIAL_LOOPBACK_MASK_SFT                        (0x1 << 20)
+#define PCM2_DAI_PCM_LOOPBACK_SFT                            19
+#define PCM2_DAI_PCM_LOOPBACK_MASK                           0x1
+#define PCM2_DAI_PCM_LOOPBACK_MASK_SFT                       (0x1 << 19)
+#define PCM2_I2S_PCM_LOOPBACK_SFT                            18
+#define PCM2_I2S_PCM_LOOPBACK_MASK                           0x1
+#define PCM2_I2S_PCM_LOOPBACK_MASK_SFT                       (0x1 << 18)
+#define PCM2_SYNC_DELSEL_SFT                                 17
+#define PCM2_SYNC_DELSEL_MASK                                0x1
+#define PCM2_SYNC_DELSEL_MASK_SFT                            (0x1 << 17)
+#define PCM2_TX_LR_SWAP_SFT                                  16
+#define PCM2_TX_LR_SWAP_MASK                                 0x1
+#define PCM2_TX_LR_SWAP_MASK_SFT                             (0x1 << 16)
+#define PCM2_SYNC_IN_INV_SFT                                 15
+#define PCM2_SYNC_IN_INV_MASK                                0x1
+#define PCM2_SYNC_IN_INV_MASK_SFT                            (0x1 << 15)
+#define PCM2_BCLK_IN_INV_SFT                                 14
+#define PCM2_BCLK_IN_INV_MASK                                0x1
+#define PCM2_BCLK_IN_INV_MASK_SFT                            (0x1 << 14)
+#define PCM2_TX_LCH_RPT_SFT                                  13
+#define PCM2_TX_LCH_RPT_MASK                                 0x1
+#define PCM2_TX_LCH_RPT_MASK_SFT                             (0x1 << 13)
+#define PCM2_VBT_16K_MODE_SFT                                12
+#define PCM2_VBT_16K_MODE_MASK                               0x1
+#define PCM2_VBT_16K_MODE_MASK_SFT                           (0x1 << 12)
+#define PCM2_LOOPBACK_CH_SEL_SFT                             10
+#define PCM2_LOOPBACK_CH_SEL_MASK                            0x3
+#define PCM2_LOOPBACK_CH_SEL_MASK_SFT                        (0x3 << 10)
+#define PCM2_TX2_BT_MODE_SFT                                 8
+#define PCM2_TX2_BT_MODE_MASK                                0x1
+#define PCM2_TX2_BT_MODE_MASK_SFT                            (0x1 << 8)
+#define PCM2_BT_MODE_SFT                                     7
+#define PCM2_BT_MODE_MASK                                    0x1
+#define PCM2_BT_MODE_MASK_SFT                                (0x1 << 7)
+#define PCM2_AFIFO_SFT                                       6
+#define PCM2_AFIFO_MASK                                      0x1
+#define PCM2_AFIFO_MASK_SFT                                  (0x1 << 6)
+#define PCM2_WLEN_SFT                                        5
+#define PCM2_WLEN_MASK                                       0x1
+#define PCM2_WLEN_MASK_SFT                                   (0x1 << 5)
+#define PCM2_MODE_SFT                                        3
+#define PCM2_MODE_MASK                                       0x3
+#define PCM2_MODE_MASK_SFT                                   (0x3 << 3)
+#define PCM2_FMT_SFT                                         1
+#define PCM2_FMT_MASK                                        0x3
+#define PCM2_FMT_MASK_SFT                                    (0x3 << 1)
+#define PCM2_EN_SFT                                          0
+#define PCM2_EN_MASK                                         0x1
+#define PCM2_EN_MASK_SFT                                     (0x1 << 0)
+#endif
diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-common.h b/sound/soc/mediatek/mt8173/mt8173-afe-common.h
index 9a4837cc181a..396fe2355eea 100644
--- a/sound/soc/mediatek/mt8173/mt8173-afe-common.h
+++ b/sound/soc/mediatek/mt8173/mt8173-afe-common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * mt8173_afe_common.h  --  Mediatek 8173 audio driver common definitions
  *
@@ -6,15 +7,6 @@
  *             Sascha Hauer <s.hauer@pengutronix.de>
  *             Hidalgo Huang <hidalgo.huang@mediatek.com>
  *             Ir Lian <ir.lian@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _MT8173_AFE_COMMON_H_
diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c
index 65d1433a0944..c0b6697503fd 100644
--- a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c
+++ b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Mediatek 8173 ALSA SoC AFE platform driver
  *
@@ -6,15 +7,6 @@
  *             Sascha Hauer <s.hauer@pengutronix.de>
  *             Hidalgo Huang <hidalgo.huang@mediatek.com>
  *             Ir Lian <ir.lian@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/delay.h>
@@ -303,9 +295,7 @@ static void mt8173_afe_dais_disable_clks(struct mtk_base_afe *afe,
 static int mt8173_afe_i2s_startup(struct snd_pcm_substream *substream,
 				  struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 
 	if (dai->active)
 		return 0;
@@ -318,9 +308,7 @@ static int mt8173_afe_i2s_startup(struct snd_pcm_substream *substream,
 static void mt8173_afe_i2s_shutdown(struct snd_pcm_substream *substream,
 				    struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 
 	if (dai->active)
 		return;
@@ -334,10 +322,8 @@ static void mt8173_afe_i2s_shutdown(struct snd_pcm_substream *substream,
 static int mt8173_afe_i2s_prepare(struct snd_pcm_substream *substream,
 				  struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime * const runtime = substream->runtime;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 	int ret;
 
@@ -358,9 +344,7 @@ static int mt8173_afe_i2s_prepare(struct snd_pcm_substream *substream,
 static int mt8173_afe_hdmi_startup(struct snd_pcm_substream *substream,
 				   struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 
 	if (dai->active)
@@ -374,9 +358,7 @@ static int mt8173_afe_hdmi_startup(struct snd_pcm_substream *substream,
 static void mt8173_afe_hdmi_shutdown(struct snd_pcm_substream *substream,
 				     struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 
 	if (dai->active)
@@ -389,10 +371,8 @@ static void mt8173_afe_hdmi_shutdown(struct snd_pcm_substream *substream,
 static int mt8173_afe_hdmi_prepare(struct snd_pcm_substream *substream,
 				   struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime * const runtime = substream->runtime;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 
 	unsigned int val;
@@ -454,9 +434,7 @@ static int mt8173_afe_hdmi_prepare(struct snd_pcm_substream *substream,
 static int mt8173_afe_hdmi_trigger(struct snd_pcm_substream *substream, int cmd,
 				   struct snd_soc_dai *dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
-	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
+	struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
 
 	dev_info(afe->dev, "%s cmd=%d %s\n", __func__, cmd, dai->name);
 
diff --git a/sound/soc/mediatek/mt8173/mt8173-max98090.c b/sound/soc/mediatek/mt8173/mt8173-max98090.c
index b49b527a7cf9..902d111016d6 100644
--- a/sound/soc/mediatek/mt8173/mt8173-max98090.c
+++ b/sound/soc/mediatek/mt8173/mt8173-max98090.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mt8173-max98090.c  --  MT8173 MAX98090 ALSA SoC machine driver
  *
  * Copyright (c) 2015 MediaTek Inc.
  * Author: Koro Chen <koro.chen@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>
diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c
index 904f3ee6b0eb..582174d98c6c 100644
--- a/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mt8173-rt5650-rt5514.c  --  MT8173 machine driver with RT5650/5514 codecs
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Koro Chen <koro.chen@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>
diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c
index 9c61b8c099c5..b3670c8a5b8d 100644
--- a/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mt8173-rt5650-rt5676.c  --  MT8173 machine driver with RT5650/5676 codecs
  *
  * Copyright (c) 2015 MediaTek Inc.
  * Author: Koro Chen <koro.chen@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>
diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650.c b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
index 84aa09d3dd98..7a89b4aad182 100644
--- a/sound/soc/mediatek/mt8173/mt8173-rt5650.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mt8173-rt5650.c  --  MT8173 machine driver with RT5650 codecs
  *
  * Copyright (c) 2016 MediaTek Inc.
  * Author: Koro Chen <koro.chen@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>
diff --git a/sound/soc/omap/Kconfig b/sound/soc/omap/Kconfig
index f5451c78ede5..6dccea6fdaeb 100644
--- a/sound/soc/omap/Kconfig
+++ b/sound/soc/omap/Kconfig
@@ -1,7 +1,12 @@
 config SND_OMAP_SOC
-	tristate "SoC Audio for the Texas Instruments OMAP chips"
+	tristate "SoC Audio for Texas Instruments OMAP chips (deprecated)"
 	depends on (ARCH_OMAP && DMA_OMAP) || (ARM && COMPILE_TEST)
-	select SND_DMAENGINE_PCM
+	select SND_SDMA_SOC
+
+config SND_SDMA_SOC
+	tristate "SoC Audio for Texas Instruments chips using sDMA"
+	depends on DMA_OMAP || COMPILE_TEST
+	select SND_SOC_GENERIC_DMAENGINE_PCM
 
 config SND_OMAP_SOC_DMIC
 	tristate
@@ -14,7 +19,7 @@ config SND_OMAP_SOC_MCPDM
 
 config SND_OMAP_SOC_HDMI_AUDIO
 	tristate "HDMI audio support for OMAP4+ based SoCs"
-	depends on SND_OMAP_SOC
+	depends on SND_SDMA_SOC
 	help
 	  For HDMI audio to work OMAPDSS HDMI support should be
 	  enabled.
@@ -29,8 +34,7 @@ config SND_OMAP_SOC_HDMI_AUDIO
 
 config SND_OMAP_SOC_N810
 	tristate "SoC Audio support for Nokia N810"
-	depends on SND_OMAP_SOC && MACH_NOKIA_N810 && I2C
-	depends on OMAP_MUX
+	depends on SND_SDMA_SOC && MACH_NOKIA_N810 && I2C
 	select SND_OMAP_SOC_MCBSP
 	select SND_SOC_TLV320AIC3X
 	help
@@ -38,7 +42,7 @@ config SND_OMAP_SOC_N810
 
 config SND_OMAP_SOC_RX51
 	tristate "SoC Audio support for Nokia N900 (RX-51)"
-	depends on SND_OMAP_SOC && ARM && I2C
+	depends on SND_SDMA_SOC && ARM && I2C
 	select SND_OMAP_SOC_MCBSP
 	select SND_SOC_TLV320AIC3X
 	select SND_SOC_TPA6130A2
@@ -49,7 +53,7 @@ config SND_OMAP_SOC_RX51
 
 config SND_OMAP_SOC_AMS_DELTA
 	tristate "SoC Audio support for Amstrad E3 (Delta) videophone"
-	depends on SND_OMAP_SOC && MACH_AMS_DELTA && TTY
+	depends on SND_SDMA_SOC && MACH_AMS_DELTA && TTY
 	select SND_OMAP_SOC_MCBSP
 	select SND_SOC_CX20442
 	help
@@ -68,7 +72,7 @@ config SND_OMAP_SOC_AMS_DELTA
 
 config SND_OMAP_SOC_OSK5912
 	tristate "SoC Audio support for omap osk5912"
-	depends on SND_OMAP_SOC && MACH_OMAP_OSK && I2C
+	depends on SND_SDMA_SOC && MACH_OMAP_OSK && I2C
 	select SND_OMAP_SOC_MCBSP
 	select SND_SOC_TLV320AIC23_I2C
 	help
@@ -76,7 +80,7 @@ config SND_OMAP_SOC_OSK5912
 
 config SND_OMAP_SOC_AM3517EVM
 	tristate "SoC Audio support for OMAP3517 / AM3517 EVM"
-	depends on SND_OMAP_SOC && MACH_OMAP3517EVM && I2C
+	depends on SND_SDMA_SOC && MACH_OMAP3517EVM && I2C
 	select SND_OMAP_SOC_MCBSP
 	select SND_SOC_TLV320AIC23_I2C
 	help
@@ -85,7 +89,7 @@ config SND_OMAP_SOC_AM3517EVM
 
 config SND_OMAP_SOC_OMAP_TWL4030
 	tristate "SoC Audio support for TI SoC based boards with twl4030 codec"
-	depends on TWL4030_CORE && SND_OMAP_SOC
+	depends on TWL4030_CORE && SND_SDMA_SOC
 	select SND_OMAP_SOC_MCBSP
 	select SND_SOC_TWL4030
 	help
@@ -100,7 +104,7 @@ config SND_OMAP_SOC_OMAP_TWL4030
 
 config SND_OMAP_SOC_OMAP_ABE_TWL6040
 	tristate "SoC Audio support for OMAP boards using ABE and twl6040 codec"
-	depends on TWL6040_CORE && SND_OMAP_SOC && COMMON_CLK
+	depends on TWL6040_CORE && SND_SDMA_SOC && COMMON_CLK
 	depends on ARCH_OMAP4 || (SOC_OMAP5 && MFD_PALMAS) || COMPILE_TEST
 	select SND_OMAP_SOC_DMIC
 	select SND_OMAP_SOC_MCPDM
@@ -118,7 +122,7 @@ config SND_OMAP_SOC_OMAP_ABE_TWL6040
 
 config SND_OMAP_SOC_OMAP3_PANDORA
 	tristate "SoC Audio support for OMAP3 Pandora"
-	depends on TWL4030_CORE && SND_OMAP_SOC && MACH_OMAP3_PANDORA
+	depends on TWL4030_CORE && SND_SDMA_SOC && MACH_OMAP3_PANDORA
 	select SND_OMAP_SOC_MCBSP
 	select SND_SOC_TWL4030
 	help
diff --git a/sound/soc/omap/Makefile b/sound/soc/omap/Makefile
index a6785dc4fc90..53eba3413485 100644
--- a/sound/soc/omap/Makefile
+++ b/sound/soc/omap/Makefile
@@ -1,12 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
 # OMAP Platform Support
-snd-soc-omap-objs := omap-pcm.o
+snd-soc-sdma-objs := sdma-pcm.o
 snd-soc-omap-dmic-objs := omap-dmic.o
 snd-soc-omap-mcbsp-objs := omap-mcbsp.o mcbsp.o
 snd-soc-omap-mcpdm-objs := omap-mcpdm.o
 snd-soc-omap-hdmi-audio-objs := omap-hdmi-audio.o
 
-obj-$(CONFIG_SND_OMAP_SOC) += snd-soc-omap.o
+obj-$(CONFIG_SND_SDMA_SOC) += snd-soc-sdma.o
 obj-$(CONFIG_SND_OMAP_SOC_DMIC) += snd-soc-omap-dmic.o
 obj-$(CONFIG_SND_OMAP_SOC_MCBSP) += snd-soc-omap-mcbsp.o
 obj-$(CONFIG_SND_OMAP_SOC_MCPDM) += snd-soc-omap-mcpdm.o
diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c
index 71e5f31fa306..9cfefe44a75f 100644
--- a/sound/soc/omap/n810.c
+++ b/sound/soc/omap/n810.c
@@ -80,9 +80,9 @@ static void n810_ext_control(struct snd_soc_dapm_context *dapm)
 	else
 		snd_soc_dapm_disable_pin_unlocked(dapm, "Headphone Jack");
 	if (line1l)
-		snd_soc_dapm_enable_pin_unlocked(dapm, "LINE1L");
+		snd_soc_dapm_enable_pin_unlocked(dapm, "HS Mic");
 	else
-		snd_soc_dapm_disable_pin_unlocked(dapm, "LINE1L");
+		snd_soc_dapm_disable_pin_unlocked(dapm, "HS Mic");
 
 	if (n810_dmic_func)
 		snd_soc_dapm_enable_pin_unlocked(dapm, "DMic");
@@ -222,6 +222,7 @@ static const struct snd_soc_dapm_widget aic33_dapm_widgets[] = {
 	SND_SOC_DAPM_SPK("Ext Spk", n810_spk_event),
 	SND_SOC_DAPM_HP("Headphone Jack", n810_jack_event),
 	SND_SOC_DAPM_MIC("DMic", NULL),
+	SND_SOC_DAPM_MIC("HS Mic", NULL),
 };
 
 static const struct snd_soc_dapm_route audio_map[] = {
@@ -231,8 +232,14 @@ static const struct snd_soc_dapm_route audio_map[] = {
 	{"Ext Spk", NULL, "LLOUT"},
 	{"Ext Spk", NULL, "RLOUT"},
 
-	{"DMic Rate 64", NULL, "Mic Bias"},
-	{"Mic Bias", NULL, "DMic"},
+	{"DMic Rate 64", NULL, "DMic"},
+	{"DMic", NULL, "Mic Bias"},
+
+	/*
+	 * Note that the mic bias is coming from Retu/Vilma and we don't have
+	 * control over it atm. The analog HS mic is not working. <- TODO
+	 */
+	{"LINE1L", NULL, "HS Mic"},
 };
 
 static const char *spk_function[] = {"Off", "On"};
@@ -257,9 +264,9 @@ static const struct snd_kcontrol_new aic33_n810_controls[] = {
 static struct snd_soc_dai_link n810_dai = {
 	.name = "TLV320AIC33",
 	.stream_name = "AIC33",
-	.cpu_dai_name = "omap-mcbsp.2",
-	.platform_name = "omap-mcbsp.2",
-	.codec_name = "tlv320aic3x-codec.2-0018",
+	.cpu_dai_name = "48076000.mcbsp",
+	.platform_name = "48076000.mcbsp",
+	.codec_name = "tlv320aic3x-codec.1-0018",
 	.codec_dai_name = "tlv320aic3x-hifi",
 	.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
 		   SND_SOC_DAIFMT_CBM_CFM,
diff --git a/sound/soc/omap/omap-dmic.c b/sound/soc/omap/omap-dmic.c
index 09db2aec12a3..51dd7c65096b 100644
--- a/sound/soc/omap/omap-dmic.c
+++ b/sound/soc/omap/omap-dmic.c
@@ -40,9 +40,9 @@
 #include <sound/initval.h>
 #include <sound/soc.h>
 #include <sound/dmaengine_pcm.h>
-#include <sound/omap-pcm.h>
 
 #include "omap-dmic.h"
+#include "sdma-pcm.h"
 
 struct omap_dmic {
 	struct device *dev;
@@ -281,7 +281,7 @@ static int omap_dmic_dai_trigger(struct snd_pcm_substream *substream,
 static int omap_dmic_select_fclk(struct omap_dmic *dmic, int clk_id,
 				 unsigned int freq)
 {
-	struct clk *parent_clk;
+	struct clk *parent_clk, *mux;
 	char *parent_clk_name;
 	int ret = 0;
 
@@ -329,14 +329,21 @@ static int omap_dmic_select_fclk(struct omap_dmic *dmic, int clk_id,
 		return -ENODEV;
 	}
 
+	mux = clk_get_parent(dmic->fclk);
+	if (IS_ERR(mux)) {
+		dev_err(dmic->dev, "can't get fck mux parent\n");
+		clk_put(parent_clk);
+		return -ENODEV;
+	}
+
 	mutex_lock(&dmic->mutex);
 	if (dmic->active) {
 		/* disable clock while reparenting */
 		pm_runtime_put_sync(dmic->dev);
-		ret = clk_set_parent(dmic->fclk, parent_clk);
+		ret = clk_set_parent(mux, parent_clk);
 		pm_runtime_get_sync(dmic->dev);
 	} else {
-		ret = clk_set_parent(dmic->fclk, parent_clk);
+		ret = clk_set_parent(mux, parent_clk);
 	}
 	mutex_unlock(&dmic->mutex);
 
@@ -349,6 +356,7 @@ static int omap_dmic_select_fclk(struct omap_dmic *dmic, int clk_id,
 	dmic->fclk_freq = freq;
 
 err_busy:
+	clk_put(mux);
 	clk_put(parent_clk);
 
 	return ret;
@@ -493,7 +501,7 @@ static int asoc_dmic_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = omap_pcm_platform_register(&pdev->dev);
+	ret = sdma_pcm_platform_register(&pdev->dev, NULL, "up_link");
 	if (ret)
 		return ret;
 
diff --git a/sound/soc/omap/omap-hdmi-audio.c b/sound/soc/omap/omap-hdmi-audio.c
index 8eeac7cab1c1..8a99a8837dc9 100644
--- a/sound/soc/omap/omap-hdmi-audio.c
+++ b/sound/soc/omap/omap-hdmi-audio.c
@@ -26,9 +26,10 @@
 #include <sound/dmaengine_pcm.h>
 #include <uapi/sound/asound.h>
 #include <sound/asoundef.h>
-#include <sound/omap-pcm.h>
 #include <sound/omap-hdmi-audio.h>
 
+#include "sdma-pcm.h"
+
 #define DRV_NAME "omap-hdmi-audio"
 
 struct hdmi_audio_data {
@@ -352,7 +353,7 @@ static int omap_hdmi_audio_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = omap_pcm_platform_register(ad->dssdev);
+	ret = sdma_pcm_platform_register(ad->dssdev, "audio_tx", NULL);
 	if (ret)
 		return ret;
 
diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c
index 6b40bdbef336..d0ebb6b9bfac 100644
--- a/sound/soc/omap/omap-mcbsp.c
+++ b/sound/soc/omap/omap-mcbsp.c
@@ -34,11 +34,11 @@
 #include <sound/initval.h>
 #include <sound/soc.h>
 #include <sound/dmaengine_pcm.h>
-#include <sound/omap-pcm.h>
 
 #include <linux/platform_data/asoc-ti-mcbsp.h>
 #include "mcbsp.h"
 #include "omap-mcbsp.h"
+#include "sdma-pcm.h"
 
 #define OMAP_MCBSP_RATES	(SNDRV_PCM_RATE_8000_96000)
 
@@ -868,7 +868,7 @@ static int asoc_mcbsp_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return omap_pcm_platform_register(&pdev->dev);
+	return sdma_pcm_platform_register(&pdev->dev, NULL, NULL);
 }
 
 static int asoc_mcbsp_remove(struct platform_device *pdev)
diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c
index 64609c77a79d..0e97360f9890 100644
--- a/sound/soc/omap/omap-mcpdm.c
+++ b/sound/soc/omap/omap-mcpdm.c
@@ -40,9 +40,9 @@
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
 #include <sound/dmaengine_pcm.h>
-#include <sound/omap-pcm.h>
 
 #include "omap-mcpdm.h"
+#include "sdma-pcm.h"
 
 struct mcpdm_link_config {
 	u32 link_mask; /* channel mask for the direction */
@@ -548,7 +548,7 @@ static int asoc_mcpdm_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return omap_pcm_platform_register(&pdev->dev);
+	return sdma_pcm_platform_register(&pdev->dev, "dn_link", "up_link");
 }
 
 static const struct of_device_id omap_mcpdm_of_match[] = {
diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c
deleted file mode 100644
index 778cc8f75b6a..000000000000
--- a/sound/soc/omap/omap-pcm.c
+++ /dev/null
@@ -1,262 +0,0 @@
-/*
- * omap-pcm.c  --  ALSA PCM interface for the OMAP SoC
- *
- * Copyright (C) 2008 Nokia Corporation
- *
- * Contact: Jarkko Nikula <jarkko.nikula@bitmer.com>
- *          Peter Ujfalusi <peter.ujfalusi@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- *
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/omap-dma.h>
-#include <sound/core.h>
-#include <sound/pcm.h>
-#include <sound/pcm_params.h>
-#include <sound/dmaengine_pcm.h>
-#include <sound/soc.h>
-#include <sound/omap-pcm.h>
-
-#ifdef CONFIG_ARCH_OMAP1
-#define pcm_omap1510()	cpu_is_omap1510()
-#else
-#define pcm_omap1510()	0
-#endif
-
-static struct snd_pcm_hardware omap_pcm_hardware = {
-	.info			= SNDRV_PCM_INFO_MMAP |
-				  SNDRV_PCM_INFO_MMAP_VALID |
-				  SNDRV_PCM_INFO_INTERLEAVED |
-				  SNDRV_PCM_INFO_PAUSE |
-				  SNDRV_PCM_INFO_RESUME |
-				  SNDRV_PCM_INFO_NO_PERIOD_WAKEUP,
-	.period_bytes_min	= 32,
-	.period_bytes_max	= 64 * 1024,
-	.periods_min		= 2,
-	.periods_max		= 255,
-	.buffer_bytes_max	= 128 * 1024,
-};
-
-/* sDMA supports only 1, 2, and 4 byte transfer elements. */
-static void omap_pcm_limit_supported_formats(void)
-{
-	int i;
-
-	for (i = 0; i <= SNDRV_PCM_FORMAT_LAST; i++) {
-		switch (snd_pcm_format_physical_width(i)) {
-		case 8:
-		case 16:
-		case 32:
-			omap_pcm_hardware.formats |= (1LL << i);
-			break;
-		default:
-			break;
-		}
-	}
-}
-
-/* this may get called several times by oss emulation */
-static int omap_pcm_hw_params(struct snd_pcm_substream *substream,
-			      struct snd_pcm_hw_params *params)
-{
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct omap_pcm_dma_data *dma_data;
-	struct dma_slave_config config;
-	struct dma_chan *chan;
-	int err = 0;
-
-	memset(&config, 0x00, sizeof(config));
-
-	dma_data = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream);
-
-	/* return if this is a bufferless transfer e.g.
-	 * codec <--> BT codec or GSM modem -- lg FIXME */
-	if (!dma_data)
-		return 0;
-
-	snd_pcm_set_runtime_buffer(substream, &substream->dma_buffer);
-	runtime->dma_bytes = params_buffer_bytes(params);
-
-	chan = snd_dmaengine_pcm_get_chan(substream);
-	if (!chan)
-		return -EINVAL;
-
-	/* fills in addr_width and direction */
-	err = snd_hwparams_to_dma_slave_config(substream, params, &config);
-	if (err)
-		return err;
-
-	snd_dmaengine_pcm_set_config_from_dai_data(substream,
-			snd_soc_dai_get_dma_data(rtd->cpu_dai, substream),
-			&config);
-
-	return dmaengine_slave_config(chan, &config);
-}
-
-static int omap_pcm_hw_free(struct snd_pcm_substream *substream)
-{
-	snd_pcm_set_runtime_buffer(substream, NULL);
-	return 0;
-}
-
-static snd_pcm_uframes_t omap_pcm_pointer(struct snd_pcm_substream *substream)
-{
-	snd_pcm_uframes_t offset;
-
-	if (pcm_omap1510())
-		offset = snd_dmaengine_pcm_pointer_no_residue(substream);
-	else
-		offset = snd_dmaengine_pcm_pointer(substream);
-
-	return offset;
-}
-
-static int omap_pcm_open(struct snd_pcm_substream *substream)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_dmaengine_dai_dma_data *dma_data;
-	int ret;
-
-	snd_soc_set_runtime_hwparams(substream, &omap_pcm_hardware);
-
-	dma_data = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream);
-
-	/* DT boot: filter_data is the DMA name */
-	if (rtd->cpu_dai->dev->of_node) {
-		struct dma_chan *chan;
-
-		chan = dma_request_slave_channel(rtd->cpu_dai->dev,
-						 dma_data->filter_data);
-		ret = snd_dmaengine_pcm_open(substream, chan);
-	} else {
-		ret = snd_dmaengine_pcm_open_request_chan(substream,
-							  omap_dma_filter_fn,
-							  dma_data->filter_data);
-	}
-	return ret;
-}
-
-static int omap_pcm_mmap(struct snd_pcm_substream *substream,
-	struct vm_area_struct *vma)
-{
-	struct snd_pcm_runtime *runtime = substream->runtime;
-
-	return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
-			   runtime->dma_addr, runtime->dma_bytes);
-}
-
-static const struct snd_pcm_ops omap_pcm_ops = {
-	.open		= omap_pcm_open,
-	.close		= snd_dmaengine_pcm_close_release_chan,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= omap_pcm_hw_params,
-	.hw_free	= omap_pcm_hw_free,
-	.trigger	= snd_dmaengine_pcm_trigger,
-	.pointer	= omap_pcm_pointer,
-	.mmap		= omap_pcm_mmap,
-};
-
-static int omap_pcm_preallocate_dma_buffer(struct snd_pcm *pcm,
-	int stream)
-{
-	struct snd_pcm_substream *substream = pcm->streams[stream].substream;
-	struct snd_dma_buffer *buf = &substream->dma_buffer;
-	size_t size = omap_pcm_hardware.buffer_bytes_max;
-
-	buf->dev.type = SNDRV_DMA_TYPE_DEV;
-	buf->dev.dev = pcm->card->dev;
-	buf->private_data = NULL;
-	buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
-	if (!buf->area)
-		return -ENOMEM;
-
-	buf->bytes = size;
-	return 0;
-}
-
-static void omap_pcm_free_dma_buffers(struct snd_pcm *pcm)
-{
-	struct snd_pcm_substream *substream;
-	struct snd_dma_buffer *buf;
-	int stream;
-
-	for (stream = 0; stream < 2; stream++) {
-		substream = pcm->streams[stream].substream;
-		if (!substream)
-			continue;
-
-		buf = &substream->dma_buffer;
-		if (!buf->area)
-			continue;
-
-		dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
-		buf->area = NULL;
-	}
-}
-
-static int omap_pcm_new(struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_card *card = rtd->card->snd_card;
-	struct snd_pcm *pcm = rtd->pcm;
-	int ret;
-
-	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
-	if (ret)
-		return ret;
-
-	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
-		ret = omap_pcm_preallocate_dma_buffer(pcm,
-			SNDRV_PCM_STREAM_PLAYBACK);
-		if (ret)
-			goto out;
-	}
-
-	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
-		ret = omap_pcm_preallocate_dma_buffer(pcm,
-			SNDRV_PCM_STREAM_CAPTURE);
-		if (ret)
-			goto out;
-	}
-
-out:
-	/* free preallocated buffers in case of error */
-	if (ret)
-		omap_pcm_free_dma_buffers(pcm);
-
-	return ret;
-}
-
-static const struct snd_soc_component_driver omap_soc_component = {
-	.ops		= &omap_pcm_ops,
-	.pcm_new	= omap_pcm_new,
-	.pcm_free	= omap_pcm_free_dma_buffers,
-};
-
-int omap_pcm_platform_register(struct device *dev)
-{
-	omap_pcm_limit_supported_formats();
-	return devm_snd_soc_register_component(dev, &omap_soc_component,
-					       NULL, 0);
-}
-EXPORT_SYMBOL_GPL(omap_pcm_platform_register);
-
-MODULE_AUTHOR("Jarkko Nikula <jarkko.nikula@bitmer.com>");
-MODULE_DESCRIPTION("OMAP PCM DMA module");
-MODULE_LICENSE("GPL");
diff --git a/sound/soc/omap/sdma-pcm.c b/sound/soc/omap/sdma-pcm.c
new file mode 100644
index 000000000000..21a9c2499d48
--- /dev/null
+++ b/sound/soc/omap/sdma-pcm.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/dmaengine_pcm.h>
+#include <linux/omap-dmaengine.h>
+
+#include "sdma-pcm.h"
+
+static const struct snd_pcm_hardware sdma_pcm_hardware = {
+	.info			= SNDRV_PCM_INFO_MMAP |
+				  SNDRV_PCM_INFO_MMAP_VALID |
+				  SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME |
+				  SNDRV_PCM_INFO_NO_PERIOD_WAKEUP |
+				  SNDRV_PCM_INFO_INTERLEAVED,
+	.period_bytes_min	= 32,
+	.period_bytes_max	= 64 * 1024,
+	.buffer_bytes_max	= 128 * 1024,
+	.periods_min		= 2,
+	.periods_max		= 255,
+};
+
+static const struct snd_dmaengine_pcm_config sdma_dmaengine_pcm_config = {
+	.pcm_hardware = &sdma_pcm_hardware,
+	.prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config,
+	.compat_filter_fn = omap_dma_filter_fn,
+	.prealloc_buffer_size = 128 * 1024,
+};
+
+int sdma_pcm_platform_register(struct device *dev,
+			       char *txdmachan, char *rxdmachan)
+{
+	struct snd_dmaengine_pcm_config *config;
+	unsigned int flags = SND_DMAENGINE_PCM_FLAG_COMPAT;
+
+	/* Standard names for the directions: 'tx' and 'rx' */
+	if (!txdmachan && !rxdmachan)
+		return devm_snd_dmaengine_pcm_register(dev,
+						&sdma_dmaengine_pcm_config,
+						flags);
+
+	config = devm_kzalloc(dev, sizeof(*config), GFP_KERNEL);
+	if (!config)
+		return -ENOMEM;
+
+	*config = sdma_dmaengine_pcm_config;
+
+	if (!txdmachan || !rxdmachan) {
+		/* One direction only PCM */
+		flags |= SND_DMAENGINE_PCM_FLAG_HALF_DUPLEX;
+		if (!txdmachan) {
+			txdmachan = rxdmachan;
+			rxdmachan = NULL;
+		}
+	}
+
+	config->chan_names[0] = txdmachan;
+	config->chan_names[1] = rxdmachan;
+
+	return devm_snd_dmaengine_pcm_register(dev, config, flags);
+}
+EXPORT_SYMBOL_GPL(sdma_pcm_platform_register);
+
+MODULE_AUTHOR("Peter Ujfalusi <peter.ujfalusi@ti.com>");
+MODULE_DESCRIPTION("sDMA PCM ASoC platform driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/omap/sdma-pcm.h b/sound/soc/omap/sdma-pcm.h
new file mode 100644
index 000000000000..34a7f90b2587
--- /dev/null
+++ b/sound/soc/omap/sdma-pcm.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+
+#ifndef __SDMA_PCM_H__
+#define __SDMA_PCM_H__
+
+#if IS_ENABLED(CONFIG_SND_SDMA_SOC)
+int sdma_pcm_platform_register(struct device *dev,
+			       char *txdmachan, char *rxdmachan);
+#else
+static inline int sdma_pcm_platform_register(struct device *dev,
+					     char *txdmachan, char *rxdmachan)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_SND_SDMA_SOC */
+
+#endif /* __SDMA_PCM_H__ */
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 484ab3c2ad67..960744e46edc 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -1,7 +1,6 @@
 config SND_PXA2XX_SOC
 	tristate "SoC Audio for the Intel PXA2xx chip"
 	depends on ARCH_PXA || COMPILE_TEST
-	depends on HAS_DMA
 	select SND_PXA2XX_LIB
 	help
 	  Say Y or M if you want to add support for codecs attached to
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index 0291c7cb64eb..6fc986080130 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -43,7 +43,8 @@
 struct ssp_priv {
 	struct ssp_device *ssp;
 	unsigned int sysclk;
-	int dai_fmt;
+	unsigned int dai_fmt;
+	unsigned int configured_dai_fmt;
 #ifdef CONFIG_PM
 	uint32_t	cr0;
 	uint32_t	cr1;
@@ -216,10 +217,9 @@ static int pxa_ssp_set_dai_sysclk(struct snd_soc_dai *cpu_dai,
 {
 	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
 	struct ssp_device *ssp = priv->ssp;
-	int val;
 
 	u32 sscr0 = pxa_ssp_read_reg(ssp, SSCR0) &
-		~(SSCR0_ECS |  SSCR0_NCS | SSCR0_MOD | SSCR0_ACS);
+		~(SSCR0_ECS | SSCR0_NCS | SSCR0_MOD | SSCR0_ACS);
 
 	dev_dbg(&ssp->pdev->dev,
 		"pxa_ssp_set_dai_sysclk id: %d, clk_id %d, freq %u\n",
@@ -257,8 +257,7 @@ static int pxa_ssp_set_dai_sysclk(struct snd_soc_dai *cpu_dai,
 	 * on PXA2xx.  On PXA3xx it must be enabled when doing so. */
 	if (ssp->type != PXA3xx_SSP)
 		clk_disable_unprepare(ssp->clk);
-	val = pxa_ssp_read_reg(ssp, SSCR0) | sscr0;
-	pxa_ssp_write_reg(ssp, SSCR0, val);
+	pxa_ssp_write_reg(ssp, SSCR0, sscr0);
 	if (ssp->type != PXA3xx_SSP)
 		clk_prepare_enable(ssp->clk);
 
@@ -433,36 +432,72 @@ static int pxa_ssp_set_dai_tristate(struct snd_soc_dai *cpu_dai,
 	return 0;
 }
 
+static int pxa_ssp_set_dai_fmt(struct snd_soc_dai *cpu_dai,
+			       unsigned int fmt)
+{
+	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+	case SND_SOC_DAIFMT_CBM_CFS:
+	case SND_SOC_DAIFMT_CBS_CFS:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+	case SND_SOC_DAIFMT_NB_IF:
+	case SND_SOC_DAIFMT_IB_IF:
+	case SND_SOC_DAIFMT_IB_NF:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_DSP_A:
+	case SND_SOC_DAIFMT_DSP_B:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	/* Settings will be applied in hw_params() */
+	priv->dai_fmt = fmt;
+
+	return 0;
+}
+
 /*
  * Set up the SSP DAI format.
  * The SSP Port must be inactive before calling this function as the
  * physical interface format is changed.
  */
-static int pxa_ssp_set_dai_fmt(struct snd_soc_dai *cpu_dai,
-		unsigned int fmt)
+static int pxa_ssp_configure_dai_fmt(struct ssp_priv *priv)
 {
-	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
 	struct ssp_device *ssp = priv->ssp;
 	u32 sscr0, sscr1, sspsp, scfr;
 
 	/* check if we need to change anything at all */
-	if (priv->dai_fmt == fmt)
+	if (priv->configured_dai_fmt == priv->dai_fmt)
 		return 0;
 
-	/* we can only change the settings if the port is not in use */
-	if (pxa_ssp_read_reg(ssp, SSCR0) & SSCR0_SSE) {
-		dev_err(&ssp->pdev->dev,
-			"can't change hardware dai format: stream is in use");
-		return -EINVAL;
-	}
-
 	/* reset port settings */
 	sscr0 = pxa_ssp_read_reg(ssp, SSCR0) &
-		~(SSCR0_ECS |  SSCR0_NCS | SSCR0_MOD | SSCR0_ACS);
-	sscr1 = SSCR1_RxTresh(8) | SSCR1_TxTresh(7);
-	sspsp = 0;
+		~(SSCR0_PSP | SSCR0_MOD);
+	sscr1 = pxa_ssp_read_reg(ssp, SSCR1) &
+		~(SSCR1_SCLKDIR | SSCR1_SFRMDIR | SSCR1_SCFR |
+		  SSCR1_RWOT | SSCR1_TRAIL | SSCR1_TFT | SSCR1_RFT);
+	sspsp = pxa_ssp_read_reg(ssp, SSPSP) &
+		~(SSPSP_SFRMP | SSPSP_SCMODE(3));
 
-	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	sscr1 |= SSCR1_RxTresh(8) | SSCR1_TxTresh(7);
+
+	switch (priv->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBM_CFM:
 		sscr1 |= SSCR1_SCLKDIR | SSCR1_SFRMDIR | SSCR1_SCFR;
 		break;
@@ -475,7 +510,7 @@ static int pxa_ssp_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 		return -EINVAL;
 	}
 
-	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	switch (priv->dai_fmt & SND_SOC_DAIFMT_INV_MASK) {
 	case SND_SOC_DAIFMT_NB_NF:
 		sspsp |= SSPSP_SFRMP;
 		break;
@@ -491,7 +526,7 @@ static int pxa_ssp_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 		return -EINVAL;
 	}
 
-	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	switch (priv->dai_fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		sscr0 |= SSCR0_PSP;
 		sscr1 |= SSCR1_RWOT | SSCR1_TRAIL;
@@ -513,7 +548,7 @@ static int pxa_ssp_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 	pxa_ssp_write_reg(ssp, SSCR1, sscr1);
 	pxa_ssp_write_reg(ssp, SSPSP, sspsp);
 
-	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	switch (priv->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBM_CFM:
 	case SND_SOC_DAIFMT_CBM_CFS:
 		scfr = pxa_ssp_read_reg(ssp, SSCR1) | SSCR1_SCFR;
@@ -530,7 +565,7 @@ static int pxa_ssp_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 	 * we have to defer some things until hw_params() where we
 	 * know parameters like the sample size.
 	 */
-	priv->dai_fmt = fmt;
+	priv->configured_dai_fmt = priv->dai_fmt;
 
 	return 0;
 }
@@ -551,6 +586,7 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream,
 	int width = snd_pcm_format_physical_width(params_format(params));
 	int ttsa = pxa_ssp_read_reg(ssp, SSTSA) & 0xf;
 	struct snd_dmaengine_dai_dma_data *dma_data;
+	int ret;
 
 	dma_data = snd_soc_dai_get_dma_data(cpu_dai, substream);
 
@@ -566,6 +602,10 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream,
 	if (pxa_ssp_read_reg(ssp, SSCR0) & SSCR0_SSE)
 		return 0;
 
+	ret = pxa_ssp_configure_dai_fmt(priv);
+	if (ret < 0)
+		return ret;
+
 	/* clear selected SSP bits */
 	sscr0 = pxa_ssp_read_reg(ssp, SSCR0) & ~(SSCR0_DSS | SSCR0_EDSS);
 
diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index 8ec9a074b38b..87838fa27997 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -11,24 +11,21 @@ config SND_SOC_LPASS_CPU
 
 config SND_SOC_LPASS_PLATFORM
 	tristate
-	depends on HAS_DMA
 	select REGMAP_MMIO
 
 config SND_SOC_LPASS_IPQ806X
 	tristate
-	depends on HAS_DMA
 	select SND_SOC_LPASS_CPU
 	select SND_SOC_LPASS_PLATFORM
 
 config SND_SOC_LPASS_APQ8016
 	tristate
-	depends on HAS_DMA
 	select SND_SOC_LPASS_CPU
 	select SND_SOC_LPASS_PLATFORM
 
 config SND_SOC_STORM
 	tristate "ASoC I2S support for Storm boards"
-	depends on SND_SOC_QCOM && HAS_DMA
+	depends on SND_SOC_QCOM
 	select SND_SOC_LPASS_IPQ806X
 	select SND_SOC_MAX98357A
 	help
@@ -37,9 +34,59 @@ config SND_SOC_STORM
 
 config SND_SOC_APQ8016_SBC
 	tristate "SoC Audio support for APQ8016 SBC platforms"
-	depends on SND_SOC_QCOM && HAS_DMA
+	depends on SND_SOC_QCOM
 	select SND_SOC_LPASS_APQ8016
 	help
           Support for Qualcomm Technologies LPASS audio block in
           APQ8016 SOC-based systems.
           Say Y if you want to use audio devices on MI2S.
+
+config SND_SOC_QDSP6_COMMON
+	tristate
+
+config SND_SOC_QDSP6_CORE
+	tristate
+
+config SND_SOC_QDSP6_AFE
+	tristate
+
+config SND_SOC_QDSP6_AFE_DAI
+	tristate
+
+config SND_SOC_QDSP6_ADM
+	tristate
+
+config SND_SOC_QDSP6_ROUTING
+	tristate
+
+config SND_SOC_QDSP6_ASM
+	tristate
+
+config SND_SOC_QDSP6_ASM_DAI
+	tristate
+
+config SND_SOC_QDSP6
+	tristate "SoC ALSA audio driver for QDSP6"
+	depends on QCOM_APR && HAS_DMA
+	select SND_SOC_QDSP6_COMMON
+	select SND_SOC_QDSP6_CORE
+	select SND_SOC_QDSP6_AFE
+	select SND_SOC_QDSP6_AFE_DAI
+	select SND_SOC_QDSP6_ADM
+	select SND_SOC_QDSP6_ROUTING
+	select SND_SOC_QDSP6_ASM
+	select SND_SOC_QDSP6_ASM_DAI
+	help
+	 To add support for MSM QDSP6 Soc Audio.
+	 This will enable sound soc platform specific
+	 audio drivers. This includes q6asm, q6adm,
+	 q6afe interfaces to DSP using apr.
+
+config SND_SOC_MSM8996
+	tristate "SoC Machine driver for MSM8996 and APQ8096 boards"
+	depends on QCOM_APR
+	select SND_SOC_QDSP6
+	help
+          Support for Qualcomm Technologies LPASS audio block in
+          APQ8096 SoC-based systems.
+          Say Y if you want to use audio device on this SoCs
diff --git a/sound/soc/qcom/Makefile b/sound/soc/qcom/Makefile
index d5280355c24f..206945bb9ba1 100644
--- a/sound/soc/qcom/Makefile
+++ b/sound/soc/qcom/Makefile
@@ -13,6 +13,11 @@ obj-$(CONFIG_SND_SOC_LPASS_APQ8016) += snd-soc-lpass-apq8016.o
 # Machine
 snd-soc-storm-objs := storm.o
 snd-soc-apq8016-sbc-objs := apq8016_sbc.o
+snd-soc-apq8096-objs := apq8096.o
 
 obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o
 obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o
+obj-$(CONFIG_SND_SOC_MSM8996) += snd-soc-apq8096.o
+
+#DSP lib
+obj-$(CONFIG_SND_SOC_QDSP6) += qdsp6/
diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
new file mode 100644
index 000000000000..561cd429e6f2
--- /dev/null
+++ b/sound/soc/qcom/apq8096.c
@@ -0,0 +1,255 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/soc/qcom/apr.h>
+#include <linux/module.h>
+#include <linux/component.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/pcm.h>
+
+static int apq8096_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
+				      struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *rate = hw_param_interval(params,
+					SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval *channels = hw_param_interval(params,
+					SNDRV_PCM_HW_PARAM_CHANNELS);
+
+	rate->min = rate->max = 48000;
+	channels->min = channels->max = 2;
+
+	return 0;
+}
+
+static int apq8096_sbc_parse_of(struct snd_soc_card *card)
+{
+	struct device_node *np;
+	struct device_node *codec = NULL;
+	struct device_node *platform = NULL;
+	struct device_node *cpu = NULL;
+	struct device *dev = card->dev;
+	struct snd_soc_dai_link *link;
+	int ret, num_links;
+
+	ret = snd_soc_of_parse_card_name(card, "qcom,model");
+	if (ret) {
+		dev_err(dev, "Error parsing card name: %d\n", ret);
+		return ret;
+	}
+
+	/* DAPM routes */
+	if (of_property_read_bool(dev->of_node, "qcom,audio-routing")) {
+		ret = snd_soc_of_parse_audio_routing(card,
+					"qcom,audio-routing");
+		if (ret)
+			return ret;
+	}
+
+	/* Populate links */
+	num_links = of_get_child_count(dev->of_node);
+
+	/* Allocate the DAI link array */
+	card->dai_link = kcalloc(num_links, sizeof(*link), GFP_KERNEL);
+	if (!card->dai_link)
+		return -ENOMEM;
+
+	card->num_links	= num_links;
+	link = card->dai_link;
+
+	for_each_child_of_node(dev->of_node, np) {
+		cpu = of_get_child_by_name(np, "cpu");
+		if (!cpu) {
+			dev_err(dev, "Can't find cpu DT node\n");
+			ret = -EINVAL;
+			goto err;
+		}
+
+		link->cpu_of_node = of_parse_phandle(cpu, "sound-dai", 0);
+		if (!link->cpu_of_node) {
+			dev_err(card->dev, "error getting cpu phandle\n");
+			ret = -EINVAL;
+			goto err;
+		}
+
+		ret = snd_soc_of_get_dai_name(cpu, &link->cpu_dai_name);
+		if (ret) {
+			dev_err(card->dev, "error getting cpu dai name\n");
+			goto err;
+		}
+
+		platform = of_get_child_by_name(np, "platform");
+		codec = of_get_child_by_name(np, "codec");
+		if (codec && platform) {
+			link->platform_of_node = of_parse_phandle(platform,
+								  "sound-dai",
+								   0);
+			if (!link->platform_of_node) {
+				dev_err(card->dev, "platform dai not found\n");
+				ret = -EINVAL;
+				goto err;
+			}
+
+			ret = snd_soc_of_get_dai_link_codecs(dev, codec, link);
+			if (ret < 0) {
+				dev_err(card->dev, "codec dai not found\n");
+				goto err;
+			}
+			link->no_pcm = 1;
+			link->ignore_pmdown_time = 1;
+			link->be_hw_params_fixup = apq8096_be_hw_params_fixup;
+		} else {
+			link->platform_of_node = link->cpu_of_node;
+			link->codec_dai_name = "snd-soc-dummy-dai";
+			link->codec_name = "snd-soc-dummy";
+			link->dynamic = 1;
+		}
+
+		link->ignore_suspend = 1;
+		ret = of_property_read_string(np, "link-name", &link->name);
+		if (ret) {
+			dev_err(card->dev, "error getting codec dai_link name\n");
+			goto err;
+		}
+
+		link->dpcm_playback = 1;
+		link->dpcm_capture = 1;
+		link->stream_name = link->name;
+		link++;
+	}
+
+	return 0;
+err:
+	of_node_put(cpu);
+	of_node_put(codec);
+	of_node_put(platform);
+	kfree(card->dai_link);
+	return ret;
+}
+
+static int apq8096_bind(struct device *dev)
+{
+	struct snd_soc_card *card;
+	int ret;
+
+	card = kzalloc(sizeof(*card), GFP_KERNEL);
+	if (!card)
+		return -ENOMEM;
+
+	component_bind_all(dev, card);
+	card->dev = dev;
+	ret = apq8096_sbc_parse_of(card);
+	if (ret) {
+		dev_err(dev, "Error parsing OF data\n");
+		goto err;
+	}
+
+	ret = snd_soc_register_card(card);
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	component_unbind_all(dev, card);
+	kfree(card);
+	return ret;
+}
+
+static void apq8096_unbind(struct device *dev)
+{
+	struct snd_soc_card *card = dev_get_drvdata(dev);
+
+	snd_soc_unregister_card(card);
+	component_unbind_all(dev, card);
+	kfree(card->dai_link);
+	kfree(card);
+}
+
+static const struct component_master_ops apq8096_ops = {
+	.bind = apq8096_bind,
+	.unbind = apq8096_unbind,
+};
+
+static int apq8016_compare_of(struct device *dev, void *data)
+{
+	return dev->of_node == data;
+}
+
+static void apq8016_release_of(struct device *dev, void *data)
+{
+	of_node_put(data);
+}
+
+static int add_audio_components(struct device *dev,
+				struct component_match **matchptr)
+{
+	struct device_node *np, *platform, *cpu, *node, *dai_node;
+
+	node = dev->of_node;
+
+	for_each_child_of_node(node, np) {
+		cpu = of_get_child_by_name(np, "cpu");
+		if (cpu) {
+			dai_node = of_parse_phandle(cpu, "sound-dai", 0);
+			of_node_get(dai_node);
+			component_match_add_release(dev, matchptr,
+						    apq8016_release_of,
+						    apq8016_compare_of,
+						    dai_node);
+		}
+
+		platform = of_get_child_by_name(np, "platform");
+		if (platform) {
+			dai_node = of_parse_phandle(platform, "sound-dai", 0);
+			component_match_add_release(dev, matchptr,
+						    apq8016_release_of,
+						    apq8016_compare_of,
+						    dai_node);
+		}
+	}
+
+	return 0;
+}
+
+static int apq8096_platform_probe(struct platform_device *pdev)
+{
+	struct component_match *match = NULL;
+	int ret;
+
+	ret = add_audio_components(&pdev->dev, &match);
+	if (ret)
+		return ret;
+
+	return component_master_add_with_match(&pdev->dev, &apq8096_ops, match);
+}
+
+static int apq8096_platform_remove(struct platform_device *pdev)
+{
+	component_master_del(&pdev->dev, &apq8096_ops);
+
+	return 0;
+}
+
+static const struct of_device_id msm_snd_apq8096_dt_match[] = {
+	{.compatible = "qcom,apq8096-sndcard"},
+	{}
+};
+
+MODULE_DEVICE_TABLE(of, msm_snd_apq8096_dt_match);
+
+static struct platform_driver msm_snd_apq8096_driver = {
+	.probe  = apq8096_platform_probe,
+	.remove = apq8096_platform_remove,
+	.driver = {
+		.name = "msm-snd-apq8096",
+		.owner = THIS_MODULE,
+		.of_match_table = msm_snd_apq8096_dt_match,
+	},
+};
+module_platform_driver(msm_snd_apq8096_driver);
+MODULE_AUTHOR("Srinivas Kandagatla <srinivas.kandagatla@linaro.org");
+MODULE_DESCRIPTION("APQ8096 ASoC Machine Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/Makefile b/sound/soc/qcom/qdsp6/Makefile
new file mode 100644
index 000000000000..c33b3cacbea1
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/Makefile
@@ -0,0 +1,8 @@
+obj-$(CONFIG_SND_SOC_QDSP6_COMMON) += q6dsp-common.o
+obj-$(CONFIG_SND_SOC_QDSP6_CORE) += q6core.o
+obj-$(CONFIG_SND_SOC_QDSP6_AFE) += q6afe.o
+obj-$(CONFIG_SND_SOC_QDSP6_AFE_DAI) += q6afe-dai.o
+obj-$(CONFIG_SND_SOC_QDSP6_ADM) += q6adm.o
+obj-$(CONFIG_SND_SOC_QDSP6_ROUTING) += q6routing.o
+obj-$(CONFIG_SND_SOC_QDSP6_ASM) += q6asm.o
+obj-$(CONFIG_SND_SOC_QDSP6_ASM_DAI) += q6asm-dai.o
diff --git a/sound/soc/qcom/qdsp6/q6adm.c b/sound/soc/qcom/qdsp6/q6adm.c
new file mode 100644
index 000000000000..9983c665a941
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6adm.c
@@ -0,0 +1,646 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/jiffies.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/kref.h>
+#include <linux/wait.h>
+#include <linux/soc/qcom/apr.h>
+#include <linux/platform_device.h>
+#include <sound/asound.h>
+#include "q6adm.h"
+#include "q6afe.h"
+#include "q6core.h"
+#include "q6dsp-errno.h"
+#include "q6dsp-common.h"
+
+#define ADM_CMD_DEVICE_OPEN_V5		0x00010326
+#define ADM_CMDRSP_DEVICE_OPEN_V5	0x00010329
+#define ADM_CMD_DEVICE_CLOSE_V5		0x00010327
+#define ADM_CMD_MATRIX_MAP_ROUTINGS_V5	0x00010325
+
+#define TIMEOUT_MS 1000
+#define RESET_COPP_ID 99
+#define INVALID_COPP_ID 0xFF
+/* Definition for a legacy device session. */
+#define ADM_LEGACY_DEVICE_SESSION	0
+#define ADM_MATRIX_ID_AUDIO_RX		0
+#define ADM_MATRIX_ID_AUDIO_TX		1
+
+struct q6copp {
+	int afe_port;
+	int copp_idx;
+	int id;
+	int topology;
+	int mode;
+	int rate;
+	int bit_width;
+	int channels;
+	int app_type;
+	int acdb_id;
+
+	struct aprv2_ibasic_rsp_result_t result;
+	struct kref refcount;
+	wait_queue_head_t wait;
+	struct list_head node;
+	struct q6adm *adm;
+};
+
+struct q6adm {
+	struct apr_device *apr;
+	struct device *dev;
+	struct q6core_svc_api_info ainfo;
+	unsigned long copp_bitmap[AFE_MAX_PORTS];
+	struct list_head copps_list;
+	spinlock_t copps_list_lock;
+	struct aprv2_ibasic_rsp_result_t result;
+	struct mutex lock;
+	wait_queue_head_t matrix_map_wait;
+	struct platform_device *pdev_routing;
+};
+
+struct q6adm_cmd_device_open_v5 {
+	u16 flags;
+	u16 mode_of_operation;
+	u16 endpoint_id_1;
+	u16 endpoint_id_2;
+	u32 topology_id;
+	u16 dev_num_channel;
+	u16 bit_width;
+	u32 sample_rate;
+	u8 dev_channel_mapping[8];
+} __packed;
+
+struct q6adm_cmd_matrix_map_routings_v5 {
+	u32 matrix_id;
+	u32 num_sessions;
+} __packed;
+
+struct q6adm_session_map_node_v5 {
+	u16 session_id;
+	u16 num_copps;
+} __packed;
+
+static struct q6copp *q6adm_find_copp(struct q6adm *adm, int port_idx,
+				  int copp_idx)
+{
+	struct q6copp *c = NULL;
+	struct q6copp *ret = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&adm->copps_list_lock, flags);
+	list_for_each_entry(c, &adm->copps_list, node) {
+		if ((port_idx == c->afe_port) && (copp_idx == c->copp_idx)) {
+			ret = c;
+			kref_get(&c->refcount);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&adm->copps_list_lock, flags);
+
+	return ret;
+
+}
+
+static void q6adm_free_copp(struct kref *ref)
+{
+	struct q6copp *c = container_of(ref, struct q6copp, refcount);
+	struct q6adm *adm = c->adm;
+	unsigned long flags;
+
+	spin_lock_irqsave(&adm->copps_list_lock, flags);
+	clear_bit(c->copp_idx, &adm->copp_bitmap[c->afe_port]);
+	list_del(&c->node);
+	spin_unlock_irqrestore(&adm->copps_list_lock, flags);
+	kfree(c);
+}
+
+static int q6adm_callback(struct apr_device *adev, struct apr_resp_pkt *data)
+{
+	struct aprv2_ibasic_rsp_result_t *result = data->payload;
+	int port_idx, copp_idx;
+	struct apr_hdr *hdr = &data->hdr;
+	struct q6copp *copp;
+	struct q6adm *adm = dev_get_drvdata(&adev->dev);
+
+	if (!data->payload_size)
+		return 0;
+
+	copp_idx = (hdr->token) & 0XFF;
+	port_idx = ((hdr->token) >> 16) & 0xFF;
+	if (port_idx < 0 || port_idx >= AFE_MAX_PORTS) {
+		dev_err(&adev->dev, "Invalid port idx %d token %d\n",
+		       port_idx, hdr->token);
+		return 0;
+	}
+	if (copp_idx < 0 || copp_idx >= MAX_COPPS_PER_PORT) {
+		dev_err(&adev->dev, "Invalid copp idx %d token %d\n",
+			copp_idx, hdr->token);
+		return 0;
+	}
+
+	switch (hdr->opcode) {
+	case APR_BASIC_RSP_RESULT: {
+		if (result->status != 0) {
+			dev_err(&adev->dev, "cmd = 0x%x return error = 0x%x\n",
+				result->opcode, result->status);
+		}
+		switch (result->opcode) {
+		case ADM_CMD_DEVICE_OPEN_V5:
+		case ADM_CMD_DEVICE_CLOSE_V5:
+			copp = q6adm_find_copp(adm, port_idx, copp_idx);
+			if (!copp)
+				return 0;
+
+			copp->result = *result;
+			wake_up(&copp->wait);
+			kref_put(&copp->refcount, q6adm_free_copp);
+			break;
+		case ADM_CMD_MATRIX_MAP_ROUTINGS_V5:
+			adm->result = *result;
+			wake_up(&adm->matrix_map_wait);
+			break;
+
+		default:
+			dev_err(&adev->dev, "Unknown Cmd: 0x%x\n",
+				result->opcode);
+			break;
+		}
+		return 0;
+	}
+	case ADM_CMDRSP_DEVICE_OPEN_V5: {
+		struct adm_cmd_rsp_device_open_v5 {
+			u32 status;
+			u16 copp_id;
+			u16 reserved;
+		} __packed * open = data->payload;
+
+		copp = q6adm_find_copp(adm, port_idx, copp_idx);
+		if (!copp)
+			return 0;
+
+		if (open->copp_id == INVALID_COPP_ID) {
+			dev_err(&adev->dev, "Invalid coppid rxed %d\n",
+				open->copp_id);
+			copp->result.status = ADSP_EBADPARAM;
+			wake_up(&copp->wait);
+			kref_put(&copp->refcount, q6adm_free_copp);
+			break;
+		}
+		copp->result.opcode = hdr->opcode;
+		copp->id = open->copp_id;
+		wake_up(&copp->wait);
+		kref_put(&copp->refcount, q6adm_free_copp);
+	}
+	break;
+	default:
+		dev_err(&adev->dev, "Unknown cmd:0x%x\n",
+		       hdr->opcode);
+		break;
+	}
+
+	return 0;
+}
+
+static struct q6copp *q6adm_alloc_copp(struct q6adm *adm, int port_idx)
+{
+	struct q6copp *c;
+	int idx;
+
+	idx = find_first_zero_bit(&adm->copp_bitmap[port_idx],
+				  MAX_COPPS_PER_PORT);
+
+	if (idx > MAX_COPPS_PER_PORT)
+		return ERR_PTR(-EBUSY);
+
+	c = kzalloc(sizeof(*c), GFP_ATOMIC);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	set_bit(idx, &adm->copp_bitmap[port_idx]);
+	c->copp_idx = idx;
+	c->afe_port = port_idx;
+	c->adm = adm;
+
+	init_waitqueue_head(&c->wait);
+
+	return c;
+}
+
+static int q6adm_apr_send_copp_pkt(struct q6adm *adm, struct q6copp *copp,
+				   struct apr_pkt *pkt, uint32_t rsp_opcode)
+{
+	struct device *dev = adm->dev;
+	uint32_t opcode = pkt->hdr.opcode;
+	int ret;
+
+	mutex_lock(&adm->lock);
+	copp->result.opcode = 0;
+	copp->result.status = 0;
+	ret = apr_send_pkt(adm->apr, pkt);
+	if (ret < 0) {
+		dev_err(dev, "Failed to send APR packet\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	/* Wait for the callback with copp id */
+	if (rsp_opcode)
+		ret = wait_event_timeout(copp->wait,
+					 (copp->result.opcode == opcode) ||
+					 (copp->result.opcode == rsp_opcode),
+					 msecs_to_jiffies(TIMEOUT_MS));
+	else
+		ret = wait_event_timeout(copp->wait,
+					 (copp->result.opcode == opcode),
+					 msecs_to_jiffies(TIMEOUT_MS));
+
+	if (!ret) {
+		dev_err(dev, "ADM copp cmd timedout\n");
+		ret = -ETIMEDOUT;
+	} else if (copp->result.status > 0) {
+		dev_err(dev, "DSP returned error[%d]\n",
+			copp->result.status);
+		ret = -EINVAL;
+	}
+
+err:
+	mutex_unlock(&adm->lock);
+	return ret;
+}
+
+static int q6adm_device_close(struct q6adm *adm, struct q6copp *copp,
+			      int port_id, int copp_idx)
+{
+	struct apr_pkt close;
+
+	close.hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+					APR_HDR_LEN(APR_HDR_SIZE),
+					APR_PKT_VER);
+	close.hdr.pkt_size = sizeof(close);
+	close.hdr.src_port = port_id;
+	close.hdr.dest_port = copp->id;
+	close.hdr.token = port_id << 16 | copp_idx;
+	close.hdr.opcode = ADM_CMD_DEVICE_CLOSE_V5;
+
+	return q6adm_apr_send_copp_pkt(adm, copp, &close, 0);
+}
+
+static struct q6copp *q6adm_find_matching_copp(struct q6adm *adm,
+					       int port_id, int topology,
+					       int mode, int rate,
+					       int channel_mode, int bit_width,
+					       int app_type)
+{
+	struct q6copp *c = NULL;
+	struct q6copp *ret = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&adm->copps_list_lock, flags);
+
+	list_for_each_entry(c, &adm->copps_list, node) {
+		if ((port_id == c->afe_port) && (topology == c->topology) &&
+		    (mode == c->mode) && (rate == c->rate) &&
+		    (bit_width == c->bit_width) && (app_type == c->app_type)) {
+			ret = c;
+			kref_get(&c->refcount);
+		}
+	}
+	spin_unlock_irqrestore(&adm->copps_list_lock, flags);
+
+	return ret;
+}
+
+static int q6adm_device_open(struct q6adm *adm, struct q6copp *copp,
+			     int port_id, int path, int topology,
+			     int channel_mode, int bit_width, int rate)
+{
+	struct q6adm_cmd_device_open_v5 *open;
+	int afe_port = q6afe_get_port_id(port_id);
+	struct apr_pkt *pkt;
+	void *p;
+	int ret, pkt_size;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*open);
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	open = p + APR_HDR_SIZE;
+	pkt->hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+					   APR_HDR_LEN(APR_HDR_SIZE),
+					   APR_PKT_VER);
+	pkt->hdr.pkt_size = pkt_size;
+	pkt->hdr.src_port = afe_port;
+	pkt->hdr.dest_port = afe_port;
+	pkt->hdr.token = port_id << 16 | copp->copp_idx;
+	pkt->hdr.opcode = ADM_CMD_DEVICE_OPEN_V5;
+	open->flags = ADM_LEGACY_DEVICE_SESSION;
+	open->mode_of_operation = path;
+	open->endpoint_id_1 = afe_port;
+	open->topology_id = topology;
+	open->dev_num_channel = channel_mode & 0x00FF;
+	open->bit_width = bit_width;
+	open->sample_rate = rate;
+
+	ret = q6dsp_map_channels(&open->dev_channel_mapping[0],
+				 channel_mode);
+	if (ret)
+		goto err;
+
+	ret = q6adm_apr_send_copp_pkt(adm, copp, pkt,
+				      ADM_CMDRSP_DEVICE_OPEN_V5);
+
+err:
+	kfree(pkt);
+	return ret;
+}
+
+/**
+ * q6adm_open() - open adm and grab a free copp
+ *
+ * @dev: Pointer to adm child device.
+ * @port_id: port id
+ * @path: playback or capture path.
+ * @rate: rate at which copp is required.
+ * @channel_mode: channel mode
+ * @topology: adm topology id
+ * @perf_mode: performace mode.
+ * @bit_width: audio sample bit width
+ * @app_type: Application type.
+ * @acdb_id: ACDB id
+ *
+ * Return: Will be an negative on error or a valid copp pointer on success.
+ */
+struct q6copp *q6adm_open(struct device *dev, int port_id, int path, int rate,
+	       int channel_mode, int topology, int perf_mode,
+	       uint16_t bit_width, int app_type, int acdb_id)
+{
+	struct q6adm *adm = dev_get_drvdata(dev->parent);
+	struct q6copp *copp;
+	unsigned long flags;
+	int ret = 0;
+
+	if (port_id < 0) {
+		dev_err(dev, "Invalid port_id 0x%x\n", port_id);
+		return ERR_PTR(-EINVAL);
+	}
+
+	copp = q6adm_find_matching_copp(adm, port_id, topology, perf_mode,
+				      rate, channel_mode, bit_width, app_type);
+	if (copp) {
+		dev_err(dev, "Found Matching Copp 0x%x\n", copp->copp_idx);
+		return copp;
+	}
+
+	spin_lock_irqsave(&adm->copps_list_lock, flags);
+	copp = q6adm_alloc_copp(adm, port_id);
+	if (IS_ERR_OR_NULL(copp)) {
+		spin_unlock_irqrestore(&adm->copps_list_lock, flags);
+		return ERR_CAST(copp);
+	}
+
+	list_add_tail(&copp->node, &adm->copps_list);
+	spin_unlock_irqrestore(&adm->copps_list_lock, flags);
+
+	kref_init(&copp->refcount);
+	copp->topology = topology;
+	copp->mode = perf_mode;
+	copp->rate = rate;
+	copp->channels = channel_mode;
+	copp->bit_width = bit_width;
+	copp->app_type = app_type;
+
+
+	ret = q6adm_device_open(adm, copp, port_id, path, topology,
+				channel_mode, bit_width, rate);
+	if (ret < 0) {
+		kref_put(&copp->refcount, q6adm_free_copp);
+		return ERR_PTR(ret);
+	}
+
+	return copp;
+}
+EXPORT_SYMBOL_GPL(q6adm_open);
+
+/**
+ * q6adm_get_copp_id() - get copp index
+ *
+ * @copp: Pointer to valid copp
+ *
+ * Return: Will be an negative on error or a valid copp index on success.
+ **/
+int q6adm_get_copp_id(struct q6copp *copp)
+{
+	if (!copp)
+		return -EINVAL;
+
+	return copp->copp_idx;
+}
+EXPORT_SYMBOL_GPL(q6adm_get_copp_id);
+
+/**
+ * q6adm_matrix_map() - Map asm streams and afe ports using payload
+ *
+ * @dev: Pointer to adm child device.
+ * @path: playback or capture path.
+ * @payload_map: map between session id and afe ports.
+ * @perf_mode: Performace mode.
+ *
+ * Return: Will be an negative on error or a zero on success.
+ */
+int q6adm_matrix_map(struct device *dev, int path,
+		     struct route_payload payload_map, int perf_mode)
+{
+	struct q6adm *adm = dev_get_drvdata(dev->parent);
+	struct q6adm_cmd_matrix_map_routings_v5 *route;
+	struct q6adm_session_map_node_v5 *node;
+	struct apr_pkt *pkt;
+	uint16_t *copps_list;
+	int pkt_size, ret, i, copp_idx;
+	void *matrix_map = NULL;
+	struct q6copp *copp;
+
+	/* Assumes port_ids have already been validated during adm_open */
+	pkt_size = (APR_HDR_SIZE + sizeof(*route) +  sizeof(*node) +
+		    (sizeof(uint32_t) * payload_map.num_copps));
+
+	matrix_map = kzalloc(pkt_size, GFP_KERNEL);
+	if (!matrix_map)
+		return -ENOMEM;
+
+	pkt = matrix_map;
+	route = matrix_map + APR_HDR_SIZE;
+	node = matrix_map + APR_HDR_SIZE + sizeof(*route);
+	copps_list = matrix_map + APR_HDR_SIZE + sizeof(*route) + sizeof(*node);
+
+	pkt->hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+					   APR_HDR_LEN(APR_HDR_SIZE),
+					   APR_PKT_VER);
+	pkt->hdr.pkt_size = pkt_size;
+	pkt->hdr.token = 0;
+	pkt->hdr.opcode = ADM_CMD_MATRIX_MAP_ROUTINGS_V5;
+	route->num_sessions = 1;
+
+	switch (path) {
+	case ADM_PATH_PLAYBACK:
+		route->matrix_id = ADM_MATRIX_ID_AUDIO_RX;
+		break;
+	case ADM_PATH_LIVE_REC:
+		route->matrix_id = ADM_MATRIX_ID_AUDIO_TX;
+		break;
+	default:
+		dev_err(dev, "Wrong path set[%d]\n", path);
+		break;
+	}
+
+	node->session_id = payload_map.session_id;
+	node->num_copps = payload_map.num_copps;
+
+	for (i = 0; i < payload_map.num_copps; i++) {
+		int port_idx = payload_map.port_id[i];
+
+		if (port_idx < 0) {
+			dev_err(dev, "Invalid port_id 0x%x\n",
+				payload_map.port_id[i]);
+			kfree(pkt);
+			return -EINVAL;
+		}
+		copp_idx = payload_map.copp_idx[i];
+
+		copp = q6adm_find_copp(adm, port_idx, copp_idx);
+		if (!copp) {
+			kfree(pkt);
+			return -EINVAL;
+		}
+
+		copps_list[i] = copp->id;
+		kref_put(&copp->refcount, q6adm_free_copp);
+	}
+
+	mutex_lock(&adm->lock);
+	adm->result.status = 0;
+	adm->result.opcode = 0;
+
+	ret = apr_send_pkt(adm->apr, pkt);
+	if (ret < 0) {
+		dev_err(dev, "routing for stream %d failed ret %d\n",
+		       payload_map.session_id, ret);
+		goto fail_cmd;
+	}
+	ret = wait_event_timeout(adm->matrix_map_wait,
+				 adm->result.opcode == pkt->hdr.opcode,
+				 msecs_to_jiffies(TIMEOUT_MS));
+	if (!ret) {
+		dev_err(dev, "routing for stream %d failed\n",
+		       payload_map.session_id);
+		ret = -ETIMEDOUT;
+		goto fail_cmd;
+	} else if (adm->result.status > 0) {
+		dev_err(dev, "DSP returned error[%d]\n",
+			adm->result.status);
+		ret = -EINVAL;
+		goto fail_cmd;
+	}
+
+fail_cmd:
+	mutex_unlock(&adm->lock);
+	kfree(pkt);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(q6adm_matrix_map);
+
+/**
+ * q6adm_close() - Close adm copp
+ *
+ * @dev: Pointer to adm child device.
+ * @copp: pointer to previously opened copp
+ *
+ * Return: Will be an negative on error or a zero on success.
+ */
+int q6adm_close(struct device *dev, struct q6copp *copp)
+{
+	struct q6adm *adm = dev_get_drvdata(dev->parent);
+	int ret = 0;
+
+	ret = q6adm_device_close(adm, copp, copp->afe_port, copp->copp_idx);
+	if (ret < 0) {
+		dev_err(adm->dev, "Failed to close copp %d\n", ret);
+		return ret;
+	}
+
+	kref_put(&copp->refcount, q6adm_free_copp);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(q6adm_close);
+
+static int q6adm_probe(struct apr_device *adev)
+{
+	struct device *dev = &adev->dev;
+	struct device_node *dais_np;
+	struct q6adm *adm;
+
+	adm = devm_kzalloc(&adev->dev, sizeof(*adm), GFP_KERNEL);
+	if (!adm)
+		return -ENOMEM;
+
+	adm->apr = adev;
+	dev_set_drvdata(&adev->dev, adm);
+	adm->dev = dev;
+	q6core_get_svc_api_info(adev->svc_id, &adm->ainfo);
+	mutex_init(&adm->lock);
+	init_waitqueue_head(&adm->matrix_map_wait);
+
+	INIT_LIST_HEAD(&adm->copps_list);
+	spin_lock_init(&adm->copps_list_lock);
+
+	dais_np = of_get_child_by_name(dev->of_node, "routing");
+	if (dais_np) {
+		adm->pdev_routing = of_platform_device_create(dais_np,
+							   "q6routing", dev);
+		of_node_put(dais_np);
+	}
+
+	return 0;
+}
+
+static int q6adm_remove(struct apr_device *adev)
+{
+	struct q6adm *adm = dev_get_drvdata(&adev->dev);
+
+	if (adm->pdev_routing)
+		of_platform_device_destroy(&adm->pdev_routing->dev, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id q6adm_device_id[]  = {
+	{ .compatible = "qcom,q6adm" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, q6adm_device_id);
+
+static struct apr_driver qcom_q6adm_driver = {
+	.probe = q6adm_probe,
+	.remove = q6adm_remove,
+	.callback = q6adm_callback,
+	.driver = {
+		.name = "qcom-q6adm",
+		.of_match_table = of_match_ptr(q6adm_device_id),
+	},
+};
+
+module_apr_driver(qcom_q6adm_driver);
+MODULE_DESCRIPTION("Q6 Audio Device Manager");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/q6adm.h b/sound/soc/qcom/qdsp6/q6adm.h
new file mode 100644
index 000000000000..4f56999b7fab
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6adm.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __Q6_ADM_V2_H__
+#define __Q6_ADM_V2_H__
+
+#define ADM_PATH_PLAYBACK	0x1
+#define ADM_PATH_LIVE_REC	0x2
+#define MAX_COPPS_PER_PORT	8
+#define NULL_COPP_TOPOLOGY	0x00010312
+
+/* multiple copp per stream. */
+struct route_payload {
+	int num_copps;
+	int session_id;
+	int copp_idx[MAX_COPPS_PER_PORT];
+	int port_id[MAX_COPPS_PER_PORT];
+};
+
+struct q6copp;
+struct q6copp *q6adm_open(struct device *dev, int port_id, int path, int rate,
+			   int channel_mode, int topology, int perf_mode,
+			   uint16_t bit_width, int app_type, int acdb_id);
+int q6adm_close(struct device *dev, struct q6copp *copp);
+int q6adm_get_copp_id(struct q6copp *copp);
+int q6adm_matrix_map(struct device *dev, int path,
+		     struct route_payload payload_map, int perf_mode);
+
+#endif /* __Q6_ADM_V2_H__ */
diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
new file mode 100644
index 000000000000..5002dd05bf27
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -0,0 +1,1303 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/component.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <sound/pcm.h>
+#include <sound/soc.h>
+#include <sound/pcm_params.h>
+#include "q6afe.h"
+
+#define Q6AFE_TDM_PB_DAI(pre, num, did) {				\
+		.playback = {						\
+			.stream_name = pre" TDM"#num" Playback",	\
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
+				SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000 |\
+				SNDRV_PCM_RATE_176400,			\
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |		\
+				   SNDRV_PCM_FMTBIT_S24_LE |		\
+				   SNDRV_PCM_FMTBIT_S32_LE,		\
+			.channels_min = 1,				\
+			.channels_max = 8,				\
+			.rate_min = 8000,				\
+			.rate_max = 176400,				\
+		},							\
+		.name = #did,						\
+		.ops = &q6tdm_ops,					\
+		.id = did,						\
+		.probe = msm_dai_q6_dai_probe,				\
+		.remove = msm_dai_q6_dai_remove,			\
+	}
+
+#define Q6AFE_TDM_CAP_DAI(pre, num, did) {				\
+		.capture = {						\
+			.stream_name = pre" TDM"#num" Capture",		\
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
+				SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000 |\
+				SNDRV_PCM_RATE_176400,			\
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |		\
+				   SNDRV_PCM_FMTBIT_S24_LE |		\
+				   SNDRV_PCM_FMTBIT_S32_LE,		\
+			.channels_min = 1,				\
+			.channels_max = 8,				\
+			.rate_min = 8000,				\
+			.rate_max = 176400,				\
+		},							\
+		.name = #did,						\
+		.ops = &q6tdm_ops,					\
+		.id = did,						\
+		.probe = msm_dai_q6_dai_probe,				\
+		.remove = msm_dai_q6_dai_remove,			\
+	}
+
+struct q6afe_dai_priv_data {
+	uint32_t sd_line_mask;
+	uint32_t sync_mode;
+	uint32_t sync_src;
+	uint32_t data_out_enable;
+	uint32_t invert_sync;
+	uint32_t data_delay;
+	uint32_t data_align;
+};
+
+struct q6afe_dai_data {
+	struct q6afe_port *port[AFE_PORT_MAX];
+	struct q6afe_port_config port_config[AFE_PORT_MAX];
+	bool is_port_started[AFE_PORT_MAX];
+	struct q6afe_dai_priv_data priv[AFE_PORT_MAX];
+};
+
+static int q6slim_hw_params(struct snd_pcm_substream *substream,
+			    struct snd_pcm_hw_params *params,
+			    struct snd_soc_dai *dai)
+{
+
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_slim_cfg *slim = &dai_data->port_config[dai->id].slim;
+
+	slim->num_channels = params_channels(params);
+	slim->sample_rate = params_rate(params);
+
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+	case SNDRV_PCM_FORMAT_SPECIAL:
+		slim->bit_width = 16;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		slim->bit_width = 24;
+		break;
+	case SNDRV_PCM_FORMAT_S32_LE:
+		slim->bit_width = 32;
+		break;
+	default:
+		pr_err("%s: format %d\n",
+			__func__, params_format(params));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int q6hdmi_hw_params(struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *params,
+				struct snd_soc_dai *dai)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	int channels = params_channels(params);
+	struct q6afe_hdmi_cfg *hdmi = &dai_data->port_config[dai->id].hdmi;
+
+	hdmi->sample_rate = params_rate(params);
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		hdmi->bit_width = 16;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		hdmi->bit_width = 24;
+		break;
+	}
+
+	/* HDMI spec CEA-861-E: Table 28 Audio InfoFrame Data Byte 4 */
+	switch (channels) {
+	case 2:
+		hdmi->channel_allocation = 0;
+		break;
+	case 3:
+		hdmi->channel_allocation = 0x02;
+		break;
+	case 4:
+		hdmi->channel_allocation = 0x06;
+		break;
+	case 5:
+		hdmi->channel_allocation = 0x0A;
+		break;
+	case 6:
+		hdmi->channel_allocation = 0x0B;
+		break;
+	case 7:
+		hdmi->channel_allocation = 0x12;
+		break;
+	case 8:
+		hdmi->channel_allocation = 0x13;
+		break;
+	default:
+		dev_err(dai->dev, "invalid Channels = %u\n", channels);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int q6i2s_hw_params(struct snd_pcm_substream *substream,
+			   struct snd_pcm_hw_params *params,
+			   struct snd_soc_dai *dai)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_i2s_cfg *i2s = &dai_data->port_config[dai->id].i2s_cfg;
+
+	i2s->sample_rate = params_rate(params);
+	i2s->bit_width = params_width(params);
+	i2s->num_channels = params_channels(params);
+	i2s->sd_line_mask = dai_data->priv[dai->id].sd_line_mask;
+
+	return 0;
+}
+
+static int q6i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_i2s_cfg *i2s = &dai_data->port_config[dai->id].i2s_cfg;
+
+	i2s->fmt = fmt;
+
+	return 0;
+}
+
+static int q6tdm_set_tdm_slot(struct snd_soc_dai *dai,
+				unsigned int tx_mask,
+				unsigned int rx_mask,
+				int slots, int slot_width)
+{
+
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_tdm_cfg *tdm = &dai_data->port_config[dai->id].tdm;
+	unsigned int cap_mask;
+	int rc = 0;
+
+	/* HW only supports 16 and 32 bit slot width configuration */
+	if ((slot_width != 16) && (slot_width != 32)) {
+		dev_err(dai->dev, "%s: invalid slot_width %d\n",
+			__func__, slot_width);
+		return -EINVAL;
+	}
+
+	/* HW supports 1-32 slots configuration. Typical: 1, 2, 4, 8, 16, 32 */
+	switch (slots) {
+	case 2:
+		cap_mask = 0x03;
+		break;
+	case 4:
+		cap_mask = 0x0F;
+		break;
+	case 8:
+		cap_mask = 0xFF;
+		break;
+	case 16:
+		cap_mask = 0xFFFF;
+		break;
+	default:
+		dev_err(dai->dev, "%s: invalid slots %d\n",
+			__func__, slots);
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case PRIMARY_TDM_RX_0 ... QUINARY_TDM_TX_7:
+		tdm->nslots_per_frame = slots;
+		tdm->slot_width = slot_width;
+		/* TDM RX dais ids are even and tx are odd */
+		tdm->slot_mask = (dai->id & 0x1 ? tx_mask : rx_mask) & cap_mask;
+		break;
+	default:
+		dev_err(dai->dev, "%s: invalid dai id 0x%x\n",
+			__func__, dai->id);
+		return -EINVAL;
+	}
+
+	return rc;
+}
+
+static int q6tdm_set_channel_map(struct snd_soc_dai *dai,
+				unsigned int tx_num, unsigned int *tx_slot,
+				unsigned int rx_num, unsigned int *rx_slot)
+{
+
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_tdm_cfg *tdm = &dai_data->port_config[dai->id].tdm;
+	int rc = 0;
+	int i = 0;
+
+	switch (dai->id) {
+	case PRIMARY_TDM_RX_0 ... QUINARY_TDM_TX_7:
+		if (dai->id & 0x1) {
+			if (!tx_slot) {
+				dev_err(dai->dev, "tx slot not found\n");
+				return -EINVAL;
+			}
+			if (tx_num > AFE_PORT_MAX_AUDIO_CHAN_CNT) {
+				dev_err(dai->dev, "invalid tx num %d\n",
+					tx_num);
+				return -EINVAL;
+			}
+
+			for (i = 0; i < tx_num; i++)
+				tdm->ch_mapping[i] = tx_slot[i];
+
+			for (i = tx_num; i < AFE_PORT_MAX_AUDIO_CHAN_CNT; i++)
+				tdm->ch_mapping[i] = Q6AFE_CMAP_INVALID;
+
+			tdm->num_channels = tx_num;
+		} else {
+			/* rx */
+			if (!rx_slot) {
+				dev_err(dai->dev, "rx slot not found\n");
+				return -EINVAL;
+			}
+			if (rx_num > AFE_PORT_MAX_AUDIO_CHAN_CNT) {
+				dev_err(dai->dev, "invalid rx num %d\n",
+					rx_num);
+				return -EINVAL;
+			}
+
+			for (i = 0; i < rx_num; i++)
+				tdm->ch_mapping[i] = rx_slot[i];
+
+			for (i = rx_num; i < AFE_PORT_MAX_AUDIO_CHAN_CNT; i++)
+				tdm->ch_mapping[i] = Q6AFE_CMAP_INVALID;
+
+			tdm->num_channels = rx_num;
+		}
+
+		break;
+	default:
+		dev_err(dai->dev, "%s: invalid dai id 0x%x\n",
+			__func__, dai->id);
+		return -EINVAL;
+	}
+
+	return rc;
+}
+
+static int q6tdm_hw_params(struct snd_pcm_substream *substream,
+			   struct snd_pcm_hw_params *params,
+			   struct snd_soc_dai *dai)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_tdm_cfg *tdm = &dai_data->port_config[dai->id].tdm;
+
+	tdm->bit_width = params_width(params);
+	tdm->sample_rate = params_rate(params);
+	tdm->num_channels = params_channels(params);
+	tdm->data_align_type = dai_data->priv[dai->id].data_align;
+	tdm->sync_src = dai_data->priv[dai->id].sync_src;
+	tdm->sync_mode = dai_data->priv[dai->id].sync_mode;
+
+	return 0;
+}
+static void q6afe_dai_shutdown(struct snd_pcm_substream *substream,
+				struct snd_soc_dai *dai)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	int rc;
+
+	rc = q6afe_port_stop(dai_data->port[dai->id]);
+	if (rc < 0)
+		dev_err(dai->dev, "fail to close AFE port (%d)\n", rc);
+
+	dai_data->is_port_started[dai->id] = false;
+
+}
+
+static int q6afe_dai_prepare(struct snd_pcm_substream *substream,
+		struct snd_soc_dai *dai)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	int rc;
+
+	if (dai_data->is_port_started[dai->id]) {
+		/* stop the port and restart with new port config */
+		rc = q6afe_port_stop(dai_data->port[dai->id]);
+		if (rc < 0) {
+			dev_err(dai->dev, "fail to close AFE port (%d)\n", rc);
+			return rc;
+		}
+	}
+
+	switch (dai->id) {
+	case HDMI_RX:
+		q6afe_hdmi_port_prepare(dai_data->port[dai->id],
+					&dai_data->port_config[dai->id].hdmi);
+		break;
+	case SLIMBUS_0_RX ... SLIMBUS_6_TX:
+		q6afe_slim_port_prepare(dai_data->port[dai->id],
+					&dai_data->port_config[dai->id].slim);
+		break;
+	case PRIMARY_MI2S_RX ... QUATERNARY_MI2S_TX:
+		rc = q6afe_i2s_port_prepare(dai_data->port[dai->id],
+			       &dai_data->port_config[dai->id].i2s_cfg);
+		if (rc < 0) {
+			dev_err(dai->dev, "fail to prepare AFE port %x\n",
+				dai->id);
+			return rc;
+		}
+		break;
+	case PRIMARY_TDM_RX_0 ... QUINARY_TDM_TX_7:
+		q6afe_tdm_port_prepare(dai_data->port[dai->id],
+					&dai_data->port_config[dai->id].tdm);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rc = q6afe_port_start(dai_data->port[dai->id]);
+	if (rc < 0) {
+		dev_err(dai->dev, "fail to start AFE port %x\n", dai->id);
+		return rc;
+	}
+	dai_data->is_port_started[dai->id] = true;
+
+	return 0;
+}
+
+static int q6slim_set_channel_map(struct snd_soc_dai *dai,
+				unsigned int tx_num, unsigned int *tx_slot,
+				unsigned int rx_num, unsigned int *rx_slot)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_port_config *pcfg = &dai_data->port_config[dai->id];
+	int i;
+
+	if (!rx_slot) {
+		pr_err("%s: rx slot not found\n", __func__);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < rx_num; i++) {
+		pcfg->slim.ch_mapping[i] =   rx_slot[i];
+		pr_debug("%s: find number of channels[%d] ch[%d]\n",
+		       __func__, i, rx_slot[i]);
+	}
+
+	pcfg->slim.num_channels = rx_num;
+
+	pr_debug("%s: SLIMBUS_%d_RX cnt[%d] ch[%d %d]\n", __func__,
+		(dai->id - SLIMBUS_0_RX) / 2, rx_num,
+		pcfg->slim.ch_mapping[0],
+		pcfg->slim.ch_mapping[1]);
+
+	return 0;
+}
+
+static int q6afe_mi2s_set_sysclk(struct snd_soc_dai *dai,
+		int clk_id, unsigned int freq, int dir)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_port *port = dai_data->port[dai->id];
+
+	switch (clk_id) {
+	case LPAIF_DIG_CLK:
+		return q6afe_port_set_sysclk(port, clk_id, 0, 5, freq, dir);
+	case LPAIF_BIT_CLK:
+	case LPAIF_OSR_CLK:
+		return q6afe_port_set_sysclk(port, clk_id,
+					     Q6AFE_LPASS_CLK_SRC_INTERNAL,
+					     Q6AFE_LPASS_CLK_ROOT_DEFAULT,
+					     freq, dir);
+	case Q6AFE_LPASS_CLK_ID_PRI_MI2S_IBIT ... Q6AFE_LPASS_CLK_ID_QUI_MI2S_OSR:
+	case Q6AFE_LPASS_CLK_ID_MCLK_1 ... Q6AFE_LPASS_CLK_ID_INT_MCLK_1:
+		return q6afe_port_set_sysclk(port, clk_id,
+					     Q6AFE_LPASS_CLK_ATTRIBUTE_COUPLE_NO,
+					     Q6AFE_LPASS_CLK_ROOT_DEFAULT,
+					     freq, dir);
+	case Q6AFE_LPASS_CLK_ID_PRI_TDM_IBIT ... Q6AFE_LPASS_CLK_ID_QUIN_TDM_EBIT:
+		return q6afe_port_set_sysclk(port, clk_id,
+					     Q6AFE_LPASS_CLK_ATTRIBUTE_INVERT_COUPLE_NO,
+					     Q6AFE_LPASS_CLK_ROOT_DEFAULT,
+					     freq, dir);
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_dapm_route q6afe_dapm_routes[] = {
+	{"HDMI Playback", NULL, "HDMI_RX"},
+	{"Slimbus1 Playback", NULL, "SLIMBUS_1_RX"},
+	{"Slimbus2 Playback", NULL, "SLIMBUS_2_RX"},
+	{"Slimbus3 Playback", NULL, "SLIMBUS_3_RX"},
+	{"Slimbus4 Playback", NULL, "SLIMBUS_4_RX"},
+	{"Slimbus5 Playback", NULL, "SLIMBUS_5_RX"},
+	{"Slimbus6 Playback", NULL, "SLIMBUS_6_RX"},
+
+	{"Primary MI2S Playback", NULL, "PRI_MI2S_RX"},
+	{"Secondary MI2S Playback", NULL, "SEC_MI2S_RX"},
+	{"Tertiary MI2S Playback", NULL, "TERT_MI2S_RX"},
+	{"Quaternary MI2S Playback", NULL, "QUAT_MI2S_RX"},
+
+	{"Primary TDM0 Playback", NULL, "PRIMARY_TDM_RX_0"},
+	{"Primary TDM1 Playback", NULL, "PRIMARY_TDM_RX_1"},
+	{"Primary TDM2 Playback", NULL, "PRIMARY_TDM_RX_2"},
+	{"Primary TDM3 Playback", NULL, "PRIMARY_TDM_RX_3"},
+	{"Primary TDM4 Playback", NULL, "PRIMARY_TDM_RX_4"},
+	{"Primary TDM5 Playback", NULL, "PRIMARY_TDM_RX_5"},
+	{"Primary TDM6 Playback", NULL, "PRIMARY_TDM_RX_6"},
+	{"Primary TDM7 Playback", NULL, "PRIMARY_TDM_RX_7"},
+
+	{"Secondary TDM0 Playback", NULL, "SEC_TDM_RX_0"},
+	{"Secondary TDM1 Playback", NULL, "SEC_TDM_RX_1"},
+	{"Secondary TDM2 Playback", NULL, "SEC_TDM_RX_2"},
+	{"Secondary TDM3 Playback", NULL, "SEC_TDM_RX_3"},
+	{"Secondary TDM4 Playback", NULL, "SEC_TDM_RX_4"},
+	{"Secondary TDM5 Playback", NULL, "SEC_TDM_RX_5"},
+	{"Secondary TDM6 Playback", NULL, "SEC_TDM_RX_6"},
+	{"Secondary TDM7 Playback", NULL, "SEC_TDM_RX_7"},
+
+	{"Tertiary TDM0 Playback", NULL, "TERT_TDM_RX_0"},
+	{"Tertiary TDM1 Playback", NULL, "TERT_TDM_RX_1"},
+	{"Tertiary TDM2 Playback", NULL, "TERT_TDM_RX_2"},
+	{"Tertiary TDM3 Playback", NULL, "TERT_TDM_RX_3"},
+	{"Tertiary TDM4 Playback", NULL, "TERT_TDM_RX_4"},
+	{"Tertiary TDM5 Playback", NULL, "TERT_TDM_RX_5"},
+	{"Tertiary TDM6 Playback", NULL, "TERT_TDM_RX_6"},
+	{"Tertiary TDM7 Playback", NULL, "TERT_TDM_RX_7"},
+
+	{"Quaternary TDM0 Playback", NULL, "QUAT_TDM_RX_0"},
+	{"Quaternary TDM1 Playback", NULL, "QUAT_TDM_RX_1"},
+	{"Quaternary TDM2 Playback", NULL, "QUAT_TDM_RX_2"},
+	{"Quaternary TDM3 Playback", NULL, "QUAT_TDM_RX_3"},
+	{"Quaternary TDM4 Playback", NULL, "QUAT_TDM_RX_4"},
+	{"Quaternary TDM5 Playback", NULL, "QUAT_TDM_RX_5"},
+	{"Quaternary TDM6 Playback", NULL, "QUAT_TDM_RX_6"},
+	{"Quaternary TDM7 Playback", NULL, "QUAT_TDM_RX_7"},
+
+	{"Quinary TDM0 Playback", NULL, "QUIN_TDM_RX_0"},
+	{"Quinary TDM1 Playback", NULL, "QUIN_TDM_RX_1"},
+	{"Quinary TDM2 Playback", NULL, "QUIN_TDM_RX_2"},
+	{"Quinary TDM3 Playback", NULL, "QUIN_TDM_RX_3"},
+	{"Quinary TDM4 Playback", NULL, "QUIN_TDM_RX_4"},
+	{"Quinary TDM5 Playback", NULL, "QUIN_TDM_RX_5"},
+	{"Quinary TDM6 Playback", NULL, "QUIN_TDM_RX_6"},
+	{"Quinary TDM7 Playback", NULL, "QUIN_TDM_RX_7"},
+
+	{"PRIMARY_TDM_TX_0", NULL, "Primary TDM0 Capture"},
+	{"PRIMARY_TDM_TX_1", NULL, "Primary TDM1 Capture"},
+	{"PRIMARY_TDM_TX_2", NULL, "Primary TDM2 Capture"},
+	{"PRIMARY_TDM_TX_3", NULL, "Primary TDM3 Capture"},
+	{"PRIMARY_TDM_TX_4", NULL, "Primary TDM4 Capture"},
+	{"PRIMARY_TDM_TX_5", NULL, "Primary TDM5 Capture"},
+	{"PRIMARY_TDM_TX_6", NULL, "Primary TDM6 Capture"},
+	{"PRIMARY_TDM_TX_7", NULL, "Primary TDM7 Capture"},
+
+	{"SEC_TDM_TX_0", NULL, "Secondary TDM0 Capture"},
+	{"SEC_TDM_TX_1", NULL, "Secondary TDM1 Capture"},
+	{"SEC_TDM_TX_2", NULL, "Secondary TDM2 Capture"},
+	{"SEC_TDM_TX_3", NULL, "Secondary TDM3 Capture"},
+	{"SEC_TDM_TX_4", NULL, "Secondary TDM4 Capture"},
+	{"SEC_TDM_TX_5", NULL, "Secondary TDM5 Capture"},
+	{"SEC_TDM_TX_6", NULL, "Secondary TDM6 Capture"},
+	{"SEC_TDM_TX_7", NULL, "Secondary TDM7 Capture"},
+
+	{"TERT_TDM_TX_0", NULL, "Tertiary TDM0 Capture"},
+	{"TERT_TDM_TX_1", NULL, "Tertiary TDM1 Capture"},
+	{"TERT_TDM_TX_2", NULL, "Tertiary TDM2 Capture"},
+	{"TERT_TDM_TX_3", NULL, "Tertiary TDM3 Capture"},
+	{"TERT_TDM_TX_4", NULL, "Tertiary TDM4 Capture"},
+	{"TERT_TDM_TX_5", NULL, "Tertiary TDM5 Capture"},
+	{"TERT_TDM_TX_6", NULL, "Tertiary TDM6 Capture"},
+	{"TERT_TDM_TX_7", NULL, "Tertiary TDM7 Capture"},
+
+	{"QUAT_TDM_TX_0", NULL, "Quaternary TDM0 Capture"},
+	{"QUAT_TDM_TX_1", NULL, "Quaternary TDM1 Capture"},
+	{"QUAT_TDM_TX_2", NULL, "Quaternary TDM2 Capture"},
+	{"QUAT_TDM_TX_3", NULL, "Quaternary TDM3 Capture"},
+	{"QUAT_TDM_TX_4", NULL, "Quaternary TDM4 Capture"},
+	{"QUAT_TDM_TX_5", NULL, "Quaternary TDM5 Capture"},
+	{"QUAT_TDM_TX_6", NULL, "Quaternary TDM6 Capture"},
+	{"QUAT_TDM_TX_7", NULL, "Quaternary TDM7 Capture"},
+
+	{"QUIN_TDM_TX_0", NULL, "Quinary TDM0 Capture"},
+	{"QUIN_TDM_TX_1", NULL, "Quinary TDM1 Capture"},
+	{"QUIN_TDM_TX_2", NULL, "Quinary TDM2 Capture"},
+	{"QUIN_TDM_TX_3", NULL, "Quinary TDM3 Capture"},
+	{"QUIN_TDM_TX_4", NULL, "Quinary TDM4 Capture"},
+	{"QUIN_TDM_TX_5", NULL, "Quinary TDM5 Capture"},
+	{"QUIN_TDM_TX_6", NULL, "Quinary TDM6 Capture"},
+	{"QUIN_TDM_TX_7", NULL, "Quinary TDM7 Capture"},
+
+	{"TERT_MI2S_TX", NULL, "Tertiary MI2S Capture"},
+	{"PRI_MI2S_TX", NULL, "Primary MI2S Capture"},
+	{"SEC_MI2S_TX", NULL, "Secondary MI2S Capture"},
+	{"QUAT_MI2S_TX", NULL, "Quaternary MI2S Capture"},
+};
+
+static struct snd_soc_dai_ops q6hdmi_ops = {
+	.prepare	= q6afe_dai_prepare,
+	.hw_params	= q6hdmi_hw_params,
+	.shutdown	= q6afe_dai_shutdown,
+};
+
+static struct snd_soc_dai_ops q6i2s_ops = {
+	.prepare	= q6afe_dai_prepare,
+	.hw_params	= q6i2s_hw_params,
+	.set_fmt	= q6i2s_set_fmt,
+	.shutdown	= q6afe_dai_shutdown,
+	.set_sysclk	= q6afe_mi2s_set_sysclk,
+};
+
+static struct snd_soc_dai_ops q6slim_ops = {
+	.prepare	= q6afe_dai_prepare,
+	.hw_params	= q6slim_hw_params,
+	.shutdown	= q6afe_dai_shutdown,
+	.set_channel_map = q6slim_set_channel_map,
+};
+
+static struct snd_soc_dai_ops q6tdm_ops = {
+	.prepare	= q6afe_dai_prepare,
+	.shutdown	= q6afe_dai_shutdown,
+	.set_sysclk	= q6afe_mi2s_set_sysclk,
+	.set_tdm_slot     = q6tdm_set_tdm_slot,
+	.set_channel_map  = q6tdm_set_channel_map,
+	.hw_params        = q6tdm_hw_params,
+};
+
+static int msm_dai_q6_dai_probe(struct snd_soc_dai *dai)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+	struct q6afe_port *port;
+
+	port = q6afe_port_get_from_id(dai->dev, dai->id);
+	if (IS_ERR(port)) {
+		dev_err(dai->dev, "Unable to get afe port\n");
+		return -EINVAL;
+	}
+	dai_data->port[dai->id] = port;
+
+	return 0;
+}
+
+static int msm_dai_q6_dai_remove(struct snd_soc_dai *dai)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
+
+	q6afe_port_put(dai_data->port[dai->id]);
+	dai_data->port[dai->id] = NULL;
+
+	return 0;
+}
+
+static struct snd_soc_dai_driver q6afe_dais[] = {
+	{
+		.playback = {
+			.stream_name = "HDMI Playback",
+			.rates = SNDRV_PCM_RATE_48000 |
+				 SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 2,
+			.channels_max = 8,
+			.rate_max =     192000,
+			.rate_min =	48000,
+		},
+		.ops = &q6hdmi_ops,
+		.id = HDMI_RX,
+		.name = "HDMI",
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.name = "SLIMBUS_0_RX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_0_RX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.playback = {
+			.stream_name = "Slimbus Playback",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+	}, {
+		.playback = {
+			.stream_name = "Slimbus1 Playback",
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |
+				 SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 2,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+		.name = "SLIMBUS_1_RX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_1_RX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Slimbus2 Playback",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+		.name = "SLIMBUS_2_RX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_2_RX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Slimbus3 Playback",
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |
+				 SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 2,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+		.name = "SLIMBUS_3_RX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_3_RX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Slimbus4 Playback",
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |
+				 SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 2,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+		.name = "SLIMBUS_4_RX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_4_RX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Slimbus5 Playback",
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |
+				 SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 2,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+		.name = "SLIMBUS_5_RX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_5_RX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Slimbus6 Playback",
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |
+				 SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 2,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
+		.ops = &q6slim_ops,
+		.name = "SLIMBUS_6_RX",
+		.id = SLIMBUS_6_RX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Primary MI2S Playback",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.rate_min =     8000,
+			.rate_max =     48000,
+		},
+		.id = PRIMARY_MI2S_RX,
+		.name = "PRI_MI2S_RX",
+		.ops = &q6i2s_ops,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.capture = {
+			.stream_name = "Primary MI2S Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.rate_min =     8000,
+			.rate_max =     48000,
+		},
+		.id = PRIMARY_MI2S_TX,
+		.name = "PRI_MI2S_TX",
+		.ops = &q6i2s_ops,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Secondary MI2S Playback",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.rate_min =     8000,
+			.rate_max =     48000,
+		},
+		.name = "SEC_MI2S_RX",
+		.id = SECONDARY_MI2S_RX,
+		.ops = &q6i2s_ops,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.capture = {
+			.stream_name = "Secondary MI2S Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.rate_min =     8000,
+			.rate_max =     48000,
+		},
+		.id = SECONDARY_MI2S_TX,
+		.name = "SEC_MI2S_TX",
+		.ops = &q6i2s_ops,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Tertiary MI2S Playback",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.rate_min =     8000,
+			.rate_max =     48000,
+		},
+		.name = "TERT_MI2S_RX",
+		.id = TERTIARY_MI2S_RX,
+		.ops = &q6i2s_ops,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.capture = {
+			.stream_name = "Tertiary MI2S Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.rate_min =     8000,
+			.rate_max =     48000,
+		},
+		.id = TERTIARY_MI2S_TX,
+		.name = "TERT_MI2S_TX",
+		.ops = &q6i2s_ops,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.playback = {
+			.stream_name = "Quaternary MI2S Playback",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.rate_min =     8000,
+			.rate_max =     48000,
+		},
+		.name = "QUAT_MI2S_RX",
+		.id = QUATERNARY_MI2S_RX,
+		.ops = &q6i2s_ops,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.capture = {
+			.stream_name = "Quaternary MI2S Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.rate_min =     8000,
+			.rate_max =     48000,
+		},
+		.id = QUATERNARY_MI2S_TX,
+		.name = "QUAT_MI2S_TX",
+		.ops = &q6i2s_ops,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+	},
+	Q6AFE_TDM_PB_DAI("Primary", 0, PRIMARY_TDM_RX_0),
+	Q6AFE_TDM_PB_DAI("Primary", 1, PRIMARY_TDM_RX_1),
+	Q6AFE_TDM_PB_DAI("Primary", 2, PRIMARY_TDM_RX_2),
+	Q6AFE_TDM_PB_DAI("Primary", 3, PRIMARY_TDM_RX_3),
+	Q6AFE_TDM_PB_DAI("Primary", 4, PRIMARY_TDM_RX_4),
+	Q6AFE_TDM_PB_DAI("Primary", 5, PRIMARY_TDM_RX_5),
+	Q6AFE_TDM_PB_DAI("Primary", 6, PRIMARY_TDM_RX_6),
+	Q6AFE_TDM_PB_DAI("Primary", 7, PRIMARY_TDM_RX_7),
+	Q6AFE_TDM_CAP_DAI("Primary", 0, PRIMARY_TDM_TX_0),
+	Q6AFE_TDM_CAP_DAI("Primary", 1, PRIMARY_TDM_TX_1),
+	Q6AFE_TDM_CAP_DAI("Primary", 2, PRIMARY_TDM_TX_2),
+	Q6AFE_TDM_CAP_DAI("Primary", 3, PRIMARY_TDM_TX_3),
+	Q6AFE_TDM_CAP_DAI("Primary", 4, PRIMARY_TDM_TX_4),
+	Q6AFE_TDM_CAP_DAI("Primary", 5, PRIMARY_TDM_TX_5),
+	Q6AFE_TDM_CAP_DAI("Primary", 6, PRIMARY_TDM_TX_6),
+	Q6AFE_TDM_CAP_DAI("Primary", 7, PRIMARY_TDM_TX_7),
+	Q6AFE_TDM_PB_DAI("Secondary", 0, SECONDARY_TDM_RX_0),
+	Q6AFE_TDM_PB_DAI("Secondary", 1, SECONDARY_TDM_RX_1),
+	Q6AFE_TDM_PB_DAI("Secondary", 2, SECONDARY_TDM_RX_2),
+	Q6AFE_TDM_PB_DAI("Secondary", 3, SECONDARY_TDM_RX_3),
+	Q6AFE_TDM_PB_DAI("Secondary", 4, SECONDARY_TDM_RX_4),
+	Q6AFE_TDM_PB_DAI("Secondary", 5, SECONDARY_TDM_RX_5),
+	Q6AFE_TDM_PB_DAI("Secondary", 6, SECONDARY_TDM_RX_6),
+	Q6AFE_TDM_PB_DAI("Secondary", 7, SECONDARY_TDM_RX_7),
+	Q6AFE_TDM_CAP_DAI("Secondary", 0, SECONDARY_TDM_TX_0),
+	Q6AFE_TDM_CAP_DAI("Secondary", 1, SECONDARY_TDM_TX_1),
+	Q6AFE_TDM_CAP_DAI("Secondary", 2, SECONDARY_TDM_TX_2),
+	Q6AFE_TDM_CAP_DAI("Secondary", 3, SECONDARY_TDM_TX_3),
+	Q6AFE_TDM_CAP_DAI("Secondary", 4, SECONDARY_TDM_TX_4),
+	Q6AFE_TDM_CAP_DAI("Secondary", 5, SECONDARY_TDM_TX_5),
+	Q6AFE_TDM_CAP_DAI("Secondary", 6, SECONDARY_TDM_TX_6),
+	Q6AFE_TDM_CAP_DAI("Secondary", 7, SECONDARY_TDM_TX_7),
+	Q6AFE_TDM_PB_DAI("Tertiary", 0, TERTIARY_TDM_RX_0),
+	Q6AFE_TDM_PB_DAI("Tertiary", 1, TERTIARY_TDM_RX_1),
+	Q6AFE_TDM_PB_DAI("Tertiary", 2, TERTIARY_TDM_RX_2),
+	Q6AFE_TDM_PB_DAI("Tertiary", 3, TERTIARY_TDM_RX_3),
+	Q6AFE_TDM_PB_DAI("Tertiary", 4, TERTIARY_TDM_RX_4),
+	Q6AFE_TDM_PB_DAI("Tertiary", 5, TERTIARY_TDM_RX_5),
+	Q6AFE_TDM_PB_DAI("Tertiary", 6, TERTIARY_TDM_RX_6),
+	Q6AFE_TDM_PB_DAI("Tertiary", 7, TERTIARY_TDM_RX_7),
+	Q6AFE_TDM_CAP_DAI("Tertiary", 0, TERTIARY_TDM_TX_0),
+	Q6AFE_TDM_CAP_DAI("Tertiary", 1, TERTIARY_TDM_TX_1),
+	Q6AFE_TDM_CAP_DAI("Tertiary", 2, TERTIARY_TDM_TX_2),
+	Q6AFE_TDM_CAP_DAI("Tertiary", 3, TERTIARY_TDM_TX_3),
+	Q6AFE_TDM_CAP_DAI("Tertiary", 4, TERTIARY_TDM_TX_4),
+	Q6AFE_TDM_CAP_DAI("Tertiary", 5, TERTIARY_TDM_TX_5),
+	Q6AFE_TDM_CAP_DAI("Tertiary", 6, TERTIARY_TDM_TX_6),
+	Q6AFE_TDM_CAP_DAI("Tertiary", 7, TERTIARY_TDM_TX_7),
+	Q6AFE_TDM_PB_DAI("Quaternary", 0, QUATERNARY_TDM_RX_0),
+	Q6AFE_TDM_PB_DAI("Quaternary", 1, QUATERNARY_TDM_RX_1),
+	Q6AFE_TDM_PB_DAI("Quaternary", 2, QUATERNARY_TDM_RX_2),
+	Q6AFE_TDM_PB_DAI("Quaternary", 3, QUATERNARY_TDM_RX_3),
+	Q6AFE_TDM_PB_DAI("Quaternary", 4, QUATERNARY_TDM_RX_4),
+	Q6AFE_TDM_PB_DAI("Quaternary", 5, QUATERNARY_TDM_RX_5),
+	Q6AFE_TDM_PB_DAI("Quaternary", 6, QUATERNARY_TDM_RX_6),
+	Q6AFE_TDM_PB_DAI("Quaternary", 7, QUATERNARY_TDM_RX_7),
+	Q6AFE_TDM_CAP_DAI("Quaternary", 0, QUATERNARY_TDM_TX_0),
+	Q6AFE_TDM_CAP_DAI("Quaternary", 1, QUATERNARY_TDM_TX_1),
+	Q6AFE_TDM_CAP_DAI("Quaternary", 2, QUATERNARY_TDM_TX_2),
+	Q6AFE_TDM_CAP_DAI("Quaternary", 3, QUATERNARY_TDM_TX_3),
+	Q6AFE_TDM_CAP_DAI("Quaternary", 4, QUATERNARY_TDM_TX_4),
+	Q6AFE_TDM_CAP_DAI("Quaternary", 5, QUATERNARY_TDM_TX_5),
+	Q6AFE_TDM_CAP_DAI("Quaternary", 6, QUATERNARY_TDM_TX_6),
+	Q6AFE_TDM_CAP_DAI("Quaternary", 7, QUATERNARY_TDM_TX_7),
+	Q6AFE_TDM_PB_DAI("Quinary", 0, QUINARY_TDM_RX_0),
+	Q6AFE_TDM_PB_DAI("Quinary", 1, QUINARY_TDM_RX_1),
+	Q6AFE_TDM_PB_DAI("Quinary", 2, QUINARY_TDM_RX_2),
+	Q6AFE_TDM_PB_DAI("Quinary", 3, QUINARY_TDM_RX_3),
+	Q6AFE_TDM_PB_DAI("Quinary", 4, QUINARY_TDM_RX_4),
+	Q6AFE_TDM_PB_DAI("Quinary", 5, QUINARY_TDM_RX_5),
+	Q6AFE_TDM_PB_DAI("Quinary", 6, QUINARY_TDM_RX_6),
+	Q6AFE_TDM_PB_DAI("Quinary", 7, QUINARY_TDM_RX_7),
+	Q6AFE_TDM_CAP_DAI("Quinary", 0, QUINARY_TDM_TX_0),
+	Q6AFE_TDM_CAP_DAI("Quinary", 1, QUINARY_TDM_TX_1),
+	Q6AFE_TDM_CAP_DAI("Quinary", 2, QUINARY_TDM_TX_2),
+	Q6AFE_TDM_CAP_DAI("Quinary", 3, QUINARY_TDM_TX_3),
+	Q6AFE_TDM_CAP_DAI("Quinary", 4, QUINARY_TDM_TX_4),
+	Q6AFE_TDM_CAP_DAI("Quinary", 5, QUINARY_TDM_TX_5),
+	Q6AFE_TDM_CAP_DAI("Quinary", 6, QUINARY_TDM_TX_6),
+	Q6AFE_TDM_CAP_DAI("Quinary", 7, QUINARY_TDM_TX_7),
+};
+
+static int q6afe_of_xlate_dai_name(struct snd_soc_component *component,
+				   struct of_phandle_args *args,
+				   const char **dai_name)
+{
+	int id = args->args[0];
+	int ret = -EINVAL;
+	int i;
+
+	for (i = 0; i  < ARRAY_SIZE(q6afe_dais); i++) {
+		if (q6afe_dais[i].id == id) {
+			*dai_name = q6afe_dais[i].name;
+			ret = 0;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static const struct snd_soc_dapm_widget q6afe_dai_widgets[] = {
+	SND_SOC_DAPM_AIF_OUT("HDMI_RX", "HDMI Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_RX", "Slimbus Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_RX", "Slimbus1 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_RX", "Slimbus2 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_RX", "Slimbus3 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_RX", "Slimbus4 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_RX", "Slimbus5 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_RX", "Slimbus6 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_RX", "Quaternary MI2S Playback",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_MI2S_TX", "Quaternary MI2S Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("TERT_MI2S_RX", "Tertiary MI2S Playback",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_MI2S_TX", "Tertiary MI2S Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_MI2S_RX", "Secondary MI2S Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_MI2S_TX", "Secondary MI2S Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_MI2S_RX_SD1",
+			"Secondary MI2S Playback SD1",
+			0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("PRI_MI2S_RX", "Primary MI2S Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRI_MI2S_TX", "Primary MI2S Capture",
+						0, 0, 0, 0),
+
+	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_0", "Primary TDM0 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_1", "Primary TDM1 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_2", "Primary TDM2 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_3", "Primary TDM3 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_4", "Primary TDM4 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_5", "Primary TDM5 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_6", "Primary TDM6 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_7", "Primary TDM7 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_0", "Primary TDM0 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_1", "Primary TDM1 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_2", "Primary TDM2 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_3", "Primary TDM3 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_4", "Primary TDM4 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_5", "Primary TDM5 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_6", "Primary TDM6 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_7", "Primary TDM7 Capture",
+						0, 0, 0, 0),
+
+	SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_0", "Secondary TDM0 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_1", "Secondary TDM1 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_2", "Secondary TDM2 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_3", "Secondary TDM3 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_4", "Secondary TDM4 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_5", "Secondary TDM5 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_6", "Secondary TDM6 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_7", "Secondary TDM7 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_0", "Secondary TDM0 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_1", "Secondary TDM1 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_2", "Secondary TDM2 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_3", "Secondary TDM3 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_4", "Secondary TDM4 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_5", "Secondary TDM5 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_6", "Secondary TDM6 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_7", "Secondary TDM7 Capture",
+						0, 0, 0, 0),
+
+	SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_0", "Tertiary TDM0 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_1", "Tertiary TDM1 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_2", "Tertiary TDM2 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_3", "Tertiary TDM3 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_4", "Tertiary TDM4 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_5", "Tertiary TDM5 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_6", "Tertiary TDM6 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_7", "Tertiary TDM7 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_0", "Tertiary TDM0 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_1", "Tertiary TDM1 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_2", "Tertiary TDM2 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_3", "Tertiary TDM3 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_4", "Tertiary TDM4 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_5", "Tertiary TDM5 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_6", "Tertiary TDM6 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_7", "Tertiary TDM7 Capture",
+						0, 0, 0, 0),
+
+	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_0", "Quaternary TDM0 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_1", "Quaternary TDM1 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_2", "Quaternary TDM2 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_3", "Quaternary TDM3 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_4", "Quaternary TDM4 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_5", "Quaternary TDM5 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_6", "Quaternary TDM6 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_7", "Quaternary TDM7 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_0", "Quaternary TDM0 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_1", "Quaternary TDM1 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_2", "Quaternary TDM2 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_3", "Quaternary TDM3 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_4", "Quaternary TDM4 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_5", "Quaternary TDM5 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_6", "Quaternary TDM6 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_7", "Quaternary TDM7 Capture",
+						0, 0, 0, 0),
+
+	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_0", "Quinary TDM0 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_1", "Quinary TDM1 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_2", "Quinary TDM2 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_3", "Quinary TDM3 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_4", "Quinary TDM4 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_5", "Quinary TDM5 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_6", "Quinary TDM6 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_7", "Quinary TDM7 Playback",
+			     0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_0", "Quinary TDM0 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_1", "Quinary TDM1 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_2", "Quinary TDM2 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_3", "Quinary TDM3 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_4", "Quinary TDM4 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_5", "Quinary TDM5 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_6", "Quinary TDM6 Capture",
+						0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_7", "Quinary TDM7 Capture",
+						0, 0, 0, 0),
+};
+
+static const struct snd_soc_component_driver q6afe_dai_component = {
+	.name		= "q6afe-dai-component",
+	.dapm_widgets = q6afe_dai_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(q6afe_dai_widgets),
+	.dapm_routes = q6afe_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(q6afe_dapm_routes),
+	.of_xlate_dai_name = q6afe_of_xlate_dai_name,
+
+};
+
+static void of_q6afe_parse_dai_data(struct device *dev,
+				    struct q6afe_dai_data *data)
+{
+	struct device_node *node;
+	int ret;
+
+	for_each_child_of_node(dev->of_node, node) {
+		unsigned int lines[Q6AFE_MAX_MI2S_LINES];
+		struct q6afe_dai_priv_data *priv;
+		int id, i, num_lines;
+
+		ret = of_property_read_u32(node, "reg", &id);
+		if (ret || id > AFE_PORT_MAX) {
+			dev_err(dev, "valid dai id not found:%d\n", ret);
+			continue;
+		}
+
+		switch (id) {
+		/* MI2S specific properties */
+		case PRIMARY_MI2S_RX ... QUATERNARY_MI2S_TX:
+			priv = &data->priv[id];
+			ret = of_property_read_variable_u32_array(node,
+							"qcom,sd-lines",
+							lines, 0,
+							Q6AFE_MAX_MI2S_LINES);
+			if (ret < 0)
+				num_lines = 0;
+			else
+				num_lines = ret;
+
+			priv->sd_line_mask = 0;
+
+			for (i = 0; i < num_lines; i++)
+				priv->sd_line_mask |= BIT(lines[i]);
+
+			break;
+		case PRIMARY_TDM_RX_0 ... QUINARY_TDM_TX_7:
+			priv = &data->priv[id];
+			ret = of_property_read_u32(node, "qcom,tdm-sync-mode",
+						   &priv->sync_mode);
+			if (ret) {
+				dev_err(dev, "No Sync mode from DT\n");
+				break;
+			}
+			ret = of_property_read_u32(node, "qcom,tdm-sync-src",
+						   &priv->sync_src);
+			if (ret) {
+				dev_err(dev, "No Sync Src from DT\n");
+				break;
+			}
+			ret = of_property_read_u32(node, "qcom,tdm-data-out",
+						   &priv->data_out_enable);
+			if (ret) {
+				dev_err(dev, "No Data out enable from DT\n");
+				break;
+			}
+			ret = of_property_read_u32(node, "qcom,tdm-invert-sync",
+						   &priv->invert_sync);
+			if (ret) {
+				dev_err(dev, "No Invert sync from DT\n");
+				break;
+			}
+			ret = of_property_read_u32(node, "qcom,tdm-data-delay",
+						   &priv->data_delay);
+			if (ret) {
+				dev_err(dev, "No Data Delay from DT\n");
+				break;
+			}
+			ret = of_property_read_u32(node, "qcom,tdm-data-align",
+						   &priv->data_align);
+			if (ret) {
+				dev_err(dev, "No Data align from DT\n");
+				break;
+			}
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static int q6afe_dai_bind(struct device *dev, struct device *master, void *data)
+{
+	struct q6afe_dai_data *dai_data;
+
+	dai_data = kzalloc(sizeof(*dai_data), GFP_KERNEL);
+	if (!dai_data)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, dai_data);
+
+	of_q6afe_parse_dai_data(dev, dai_data);
+
+	return snd_soc_register_component(dev, &q6afe_dai_component,
+					  q6afe_dais, ARRAY_SIZE(q6afe_dais));
+}
+
+static void q6afe_dai_unbind(struct device *dev, struct device *master,
+			     void *data)
+{
+	struct q6afe_dai_data *dai_data = dev_get_drvdata(dev);
+
+	snd_soc_unregister_component(dev);
+	kfree(dai_data);
+}
+
+static const struct component_ops q6afe_dai_comp_ops = {
+	.bind   = q6afe_dai_bind,
+	.unbind = q6afe_dai_unbind,
+};
+
+static int q6afe_dai_dev_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &q6afe_dai_comp_ops);
+}
+
+static int q6afe_dai_dev_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &q6afe_dai_comp_ops);
+	return 0;
+}
+
+static struct platform_driver q6afe_dai_platform_driver = {
+	.driver = {
+		.name = "q6afe-dai",
+	},
+	.probe = q6afe_dai_dev_probe,
+	.remove = q6afe_dai_dev_remove,
+};
+module_platform_driver(q6afe_dai_platform_driver);
+
+MODULE_DESCRIPTION("Q6 Audio Fronend dai driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c
new file mode 100644
index 000000000000..01f43218984b
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6afe.c
@@ -0,0 +1,1495 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/wait.h>
+#include <linux/jiffies.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/kref.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/soc/qcom/apr.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include "q6dsp-errno.h"
+#include "q6core.h"
+#include "q6afe.h"
+
+/* AFE CMDs */
+#define AFE_PORT_CMD_DEVICE_START	0x000100E5
+#define AFE_PORT_CMD_DEVICE_STOP	0x000100E6
+#define AFE_PORT_CMD_SET_PARAM_V2	0x000100EF
+#define AFE_SVC_CMD_SET_PARAM		0x000100f3
+#define AFE_PORT_CMDRSP_GET_PARAM_V2	0x00010106
+#define AFE_PARAM_ID_HDMI_CONFIG	0x00010210
+#define AFE_MODULE_AUDIO_DEV_INTERFACE	0x0001020C
+#define AFE_MODULE_TDM			0x0001028A
+
+#define AFE_PARAM_ID_CDC_SLIMBUS_SLAVE_CFG 0x00010235
+
+#define AFE_PARAM_ID_LPAIF_CLK_CONFIG	0x00010238
+#define AFE_PARAM_ID_INT_DIGITAL_CDC_CLK_CONFIG	0x00010239
+
+#define AFE_PARAM_ID_SLIMBUS_CONFIG    0x00010212
+#define AFE_PARAM_ID_I2S_CONFIG	0x0001020D
+#define AFE_PARAM_ID_TDM_CONFIG	0x0001029D
+#define AFE_PARAM_ID_PORT_SLOT_MAPPING_CONFIG	0x00010297
+
+/* I2S config specific */
+#define AFE_API_VERSION_I2S_CONFIG	0x1
+#define AFE_PORT_I2S_SD0		0x1
+#define AFE_PORT_I2S_SD1		0x2
+#define AFE_PORT_I2S_SD2		0x3
+#define AFE_PORT_I2S_SD3		0x4
+#define AFE_PORT_I2S_SD0_MASK		BIT(0x1)
+#define AFE_PORT_I2S_SD1_MASK		BIT(0x2)
+#define AFE_PORT_I2S_SD2_MASK		BIT(0x3)
+#define AFE_PORT_I2S_SD3_MASK		BIT(0x4)
+#define AFE_PORT_I2S_SD0_1_MASK		GENMASK(2, 1)
+#define AFE_PORT_I2S_SD2_3_MASK		GENMASK(4, 3)
+#define AFE_PORT_I2S_SD0_1_2_MASK	GENMASK(3, 1)
+#define AFE_PORT_I2S_SD0_1_2_3_MASK	GENMASK(4, 1)
+#define AFE_PORT_I2S_QUAD01		0x5
+#define AFE_PORT_I2S_QUAD23		0x6
+#define AFE_PORT_I2S_6CHS		0x7
+#define AFE_PORT_I2S_8CHS		0x8
+#define AFE_PORT_I2S_MONO		0x0
+#define AFE_PORT_I2S_STEREO		0x1
+#define AFE_PORT_CONFIG_I2S_WS_SRC_EXTERNAL	0x0
+#define AFE_PORT_CONFIG_I2S_WS_SRC_INTERNAL	0x1
+#define AFE_LINEAR_PCM_DATA				0x0
+
+
+/* Port IDs */
+#define AFE_API_VERSION_HDMI_CONFIG	0x1
+#define AFE_PORT_ID_MULTICHAN_HDMI_RX	0x100E
+
+#define AFE_API_VERSION_SLIMBUS_CONFIG 0x1
+/* Clock set API version */
+#define AFE_API_VERSION_CLOCK_SET 1
+#define Q6AFE_LPASS_CLK_CONFIG_API_VERSION	0x1
+#define AFE_MODULE_CLOCK_SET		0x0001028F
+#define AFE_PARAM_ID_CLOCK_SET		0x00010290
+
+/* SLIMbus Rx port on channel 0. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_RX      0x4000
+/* SLIMbus Tx port on channel 0. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_TX      0x4001
+/* SLIMbus Rx port on channel 1. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_RX      0x4002
+/* SLIMbus Tx port on channel 1. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_TX      0x4003
+/* SLIMbus Rx port on channel 2. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_RX      0x4004
+/* SLIMbus Tx port on channel 2. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_TX      0x4005
+/* SLIMbus Rx port on channel 3. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_3_RX      0x4006
+/* SLIMbus Tx port on channel 3. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_3_TX      0x4007
+/* SLIMbus Rx port on channel 4. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_4_RX      0x4008
+/* SLIMbus Tx port on channel 4. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_4_TX      0x4009
+/* SLIMbus Rx port on channel 5. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_5_RX      0x400a
+/* SLIMbus Tx port on channel 5. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_5_TX      0x400b
+/* SLIMbus Rx port on channel 6. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_RX      0x400c
+/* SLIMbus Tx port on channel 6. */
+#define AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_TX      0x400d
+#define AFE_PORT_ID_PRIMARY_MI2S_RX         0x1000
+#define AFE_PORT_ID_PRIMARY_MI2S_TX         0x1001
+#define AFE_PORT_ID_SECONDARY_MI2S_RX       0x1002
+#define AFE_PORT_ID_SECONDARY_MI2S_TX       0x1003
+#define AFE_PORT_ID_TERTIARY_MI2S_RX        0x1004
+#define AFE_PORT_ID_TERTIARY_MI2S_TX        0x1005
+#define AFE_PORT_ID_QUATERNARY_MI2S_RX      0x1006
+#define AFE_PORT_ID_QUATERNARY_MI2S_TX      0x1007
+
+/* Start of the range of port IDs for TDM devices. */
+#define AFE_PORT_ID_TDM_PORT_RANGE_START	0x9000
+
+/* End of the range of port IDs for TDM devices. */
+#define AFE_PORT_ID_TDM_PORT_RANGE_END \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START+0x50-1)
+
+/* Size of the range of port IDs for TDM ports. */
+#define AFE_PORT_ID_TDM_PORT_RANGE_SIZE \
+	(AFE_PORT_ID_TDM_PORT_RANGE_END - \
+	AFE_PORT_ID_TDM_PORT_RANGE_START+1)
+
+#define AFE_PORT_ID_PRIMARY_TDM_RX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x00)
+#define AFE_PORT_ID_PRIMARY_TDM_RX_1 \
+	(AFE_PORT_ID_PRIMARY_TDM_RX + 0x02)
+#define AFE_PORT_ID_PRIMARY_TDM_RX_2 \
+	(AFE_PORT_ID_PRIMARY_TDM_RX + 0x04)
+#define AFE_PORT_ID_PRIMARY_TDM_RX_3 \
+	(AFE_PORT_ID_PRIMARY_TDM_RX + 0x06)
+#define AFE_PORT_ID_PRIMARY_TDM_RX_4 \
+	(AFE_PORT_ID_PRIMARY_TDM_RX + 0x08)
+#define AFE_PORT_ID_PRIMARY_TDM_RX_5 \
+	(AFE_PORT_ID_PRIMARY_TDM_RX + 0x0A)
+#define AFE_PORT_ID_PRIMARY_TDM_RX_6 \
+	(AFE_PORT_ID_PRIMARY_TDM_RX + 0x0C)
+#define AFE_PORT_ID_PRIMARY_TDM_RX_7 \
+	(AFE_PORT_ID_PRIMARY_TDM_RX + 0x0E)
+
+#define AFE_PORT_ID_PRIMARY_TDM_TX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x01)
+#define AFE_PORT_ID_PRIMARY_TDM_TX_1 \
+	(AFE_PORT_ID_PRIMARY_TDM_TX + 0x02)
+#define AFE_PORT_ID_PRIMARY_TDM_TX_2 \
+	(AFE_PORT_ID_PRIMARY_TDM_TX + 0x04)
+#define AFE_PORT_ID_PRIMARY_TDM_TX_3 \
+	(AFE_PORT_ID_PRIMARY_TDM_TX + 0x06)
+#define AFE_PORT_ID_PRIMARY_TDM_TX_4 \
+	(AFE_PORT_ID_PRIMARY_TDM_TX + 0x08)
+#define AFE_PORT_ID_PRIMARY_TDM_TX_5 \
+	(AFE_PORT_ID_PRIMARY_TDM_TX + 0x0A)
+#define AFE_PORT_ID_PRIMARY_TDM_TX_6 \
+	(AFE_PORT_ID_PRIMARY_TDM_TX + 0x0C)
+#define AFE_PORT_ID_PRIMARY_TDM_TX_7 \
+	(AFE_PORT_ID_PRIMARY_TDM_TX + 0x0E)
+
+#define AFE_PORT_ID_SECONDARY_TDM_RX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x10)
+#define AFE_PORT_ID_SECONDARY_TDM_RX_1 \
+	(AFE_PORT_ID_SECONDARY_TDM_RX + 0x02)
+#define AFE_PORT_ID_SECONDARY_TDM_RX_2 \
+	(AFE_PORT_ID_SECONDARY_TDM_RX + 0x04)
+#define AFE_PORT_ID_SECONDARY_TDM_RX_3 \
+	(AFE_PORT_ID_SECONDARY_TDM_RX + 0x06)
+#define AFE_PORT_ID_SECONDARY_TDM_RX_4 \
+	(AFE_PORT_ID_SECONDARY_TDM_RX + 0x08)
+#define AFE_PORT_ID_SECONDARY_TDM_RX_5 \
+	(AFE_PORT_ID_SECONDARY_TDM_RX + 0x0A)
+#define AFE_PORT_ID_SECONDARY_TDM_RX_6 \
+	(AFE_PORT_ID_SECONDARY_TDM_RX + 0x0C)
+#define AFE_PORT_ID_SECONDARY_TDM_RX_7 \
+	(AFE_PORT_ID_SECONDARY_TDM_RX + 0x0E)
+
+#define AFE_PORT_ID_SECONDARY_TDM_TX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x11)
+#define AFE_PORT_ID_SECONDARY_TDM_TX_1 \
+	(AFE_PORT_ID_SECONDARY_TDM_TX + 0x02)
+#define AFE_PORT_ID_SECONDARY_TDM_TX_2 \
+	(AFE_PORT_ID_SECONDARY_TDM_TX + 0x04)
+#define AFE_PORT_ID_SECONDARY_TDM_TX_3 \
+	(AFE_PORT_ID_SECONDARY_TDM_TX + 0x06)
+#define AFE_PORT_ID_SECONDARY_TDM_TX_4 \
+	(AFE_PORT_ID_SECONDARY_TDM_TX + 0x08)
+#define AFE_PORT_ID_SECONDARY_TDM_TX_5 \
+	(AFE_PORT_ID_SECONDARY_TDM_TX + 0x0A)
+#define AFE_PORT_ID_SECONDARY_TDM_TX_6 \
+	(AFE_PORT_ID_SECONDARY_TDM_TX + 0x0C)
+#define AFE_PORT_ID_SECONDARY_TDM_TX_7 \
+	(AFE_PORT_ID_SECONDARY_TDM_TX + 0x0E)
+
+#define AFE_PORT_ID_TERTIARY_TDM_RX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x20)
+#define AFE_PORT_ID_TERTIARY_TDM_RX_1 \
+	(AFE_PORT_ID_TERTIARY_TDM_RX + 0x02)
+#define AFE_PORT_ID_TERTIARY_TDM_RX_2 \
+	(AFE_PORT_ID_TERTIARY_TDM_RX + 0x04)
+#define AFE_PORT_ID_TERTIARY_TDM_RX_3 \
+	(AFE_PORT_ID_TERTIARY_TDM_RX + 0x06)
+#define AFE_PORT_ID_TERTIARY_TDM_RX_4 \
+	(AFE_PORT_ID_TERTIARY_TDM_RX + 0x08)
+#define AFE_PORT_ID_TERTIARY_TDM_RX_5 \
+	(AFE_PORT_ID_TERTIARY_TDM_RX + 0x0A)
+#define AFE_PORT_ID_TERTIARY_TDM_RX_6 \
+	(AFE_PORT_ID_TERTIARY_TDM_RX + 0x0C)
+#define AFE_PORT_ID_TERTIARY_TDM_RX_7 \
+	(AFE_PORT_ID_TERTIARY_TDM_RX + 0x0E)
+
+#define AFE_PORT_ID_TERTIARY_TDM_TX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x21)
+#define AFE_PORT_ID_TERTIARY_TDM_TX_1 \
+	(AFE_PORT_ID_TERTIARY_TDM_TX + 0x02)
+#define AFE_PORT_ID_TERTIARY_TDM_TX_2 \
+	(AFE_PORT_ID_TERTIARY_TDM_TX + 0x04)
+#define AFE_PORT_ID_TERTIARY_TDM_TX_3 \
+	(AFE_PORT_ID_TERTIARY_TDM_TX + 0x06)
+#define AFE_PORT_ID_TERTIARY_TDM_TX_4 \
+	(AFE_PORT_ID_TERTIARY_TDM_TX + 0x08)
+#define AFE_PORT_ID_TERTIARY_TDM_TX_5 \
+	(AFE_PORT_ID_TERTIARY_TDM_TX + 0x0A)
+#define AFE_PORT_ID_TERTIARY_TDM_TX_6 \
+	(AFE_PORT_ID_TERTIARY_TDM_TX + 0x0C)
+#define AFE_PORT_ID_TERTIARY_TDM_TX_7 \
+	(AFE_PORT_ID_TERTIARY_TDM_TX + 0x0E)
+
+#define AFE_PORT_ID_QUATERNARY_TDM_RX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x30)
+#define AFE_PORT_ID_QUATERNARY_TDM_RX_1 \
+	(AFE_PORT_ID_QUATERNARY_TDM_RX + 0x02)
+#define AFE_PORT_ID_QUATERNARY_TDM_RX_2 \
+	(AFE_PORT_ID_QUATERNARY_TDM_RX + 0x04)
+#define AFE_PORT_ID_QUATERNARY_TDM_RX_3 \
+	(AFE_PORT_ID_QUATERNARY_TDM_RX + 0x06)
+#define AFE_PORT_ID_QUATERNARY_TDM_RX_4 \
+	(AFE_PORT_ID_QUATERNARY_TDM_RX + 0x08)
+#define AFE_PORT_ID_QUATERNARY_TDM_RX_5 \
+	(AFE_PORT_ID_QUATERNARY_TDM_RX + 0x0A)
+#define AFE_PORT_ID_QUATERNARY_TDM_RX_6 \
+	(AFE_PORT_ID_QUATERNARY_TDM_RX + 0x0C)
+#define AFE_PORT_ID_QUATERNARY_TDM_RX_7 \
+	(AFE_PORT_ID_QUATERNARY_TDM_RX + 0x0E)
+
+#define AFE_PORT_ID_QUATERNARY_TDM_TX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x31)
+#define AFE_PORT_ID_QUATERNARY_TDM_TX_1 \
+	(AFE_PORT_ID_QUATERNARY_TDM_TX + 0x02)
+#define AFE_PORT_ID_QUATERNARY_TDM_TX_2 \
+	(AFE_PORT_ID_QUATERNARY_TDM_TX + 0x04)
+#define AFE_PORT_ID_QUATERNARY_TDM_TX_3 \
+	(AFE_PORT_ID_QUATERNARY_TDM_TX + 0x06)
+#define AFE_PORT_ID_QUATERNARY_TDM_TX_4 \
+	(AFE_PORT_ID_QUATERNARY_TDM_TX + 0x08)
+#define AFE_PORT_ID_QUATERNARY_TDM_TX_5 \
+	(AFE_PORT_ID_QUATERNARY_TDM_TX + 0x0A)
+#define AFE_PORT_ID_QUATERNARY_TDM_TX_6 \
+	(AFE_PORT_ID_QUATERNARY_TDM_TX + 0x0C)
+#define AFE_PORT_ID_QUATERNARY_TDM_TX_7 \
+	(AFE_PORT_ID_QUATERNARY_TDM_TX + 0x0E)
+
+#define AFE_PORT_ID_QUINARY_TDM_RX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x40)
+#define AFE_PORT_ID_QUINARY_TDM_RX_1 \
+	(AFE_PORT_ID_QUINARY_TDM_RX + 0x02)
+#define AFE_PORT_ID_QUINARY_TDM_RX_2 \
+	(AFE_PORT_ID_QUINARY_TDM_RX + 0x04)
+#define AFE_PORT_ID_QUINARY_TDM_RX_3 \
+	(AFE_PORT_ID_QUINARY_TDM_RX + 0x06)
+#define AFE_PORT_ID_QUINARY_TDM_RX_4 \
+	(AFE_PORT_ID_QUINARY_TDM_RX + 0x08)
+#define AFE_PORT_ID_QUINARY_TDM_RX_5 \
+	(AFE_PORT_ID_QUINARY_TDM_RX + 0x0A)
+#define AFE_PORT_ID_QUINARY_TDM_RX_6 \
+	(AFE_PORT_ID_QUINARY_TDM_RX + 0x0C)
+#define AFE_PORT_ID_QUINARY_TDM_RX_7 \
+	(AFE_PORT_ID_QUINARY_TDM_RX + 0x0E)
+
+#define AFE_PORT_ID_QUINARY_TDM_TX \
+	(AFE_PORT_ID_TDM_PORT_RANGE_START + 0x41)
+#define AFE_PORT_ID_QUINARY_TDM_TX_1 \
+	(AFE_PORT_ID_QUINARY_TDM_TX + 0x02)
+#define AFE_PORT_ID_QUINARY_TDM_TX_2 \
+	(AFE_PORT_ID_QUINARY_TDM_TX + 0x04)
+#define AFE_PORT_ID_QUINARY_TDM_TX_3 \
+	(AFE_PORT_ID_QUINARY_TDM_TX + 0x06)
+#define AFE_PORT_ID_QUINARY_TDM_TX_4 \
+	(AFE_PORT_ID_QUINARY_TDM_TX + 0x08)
+#define AFE_PORT_ID_QUINARY_TDM_TX_5 \
+	(AFE_PORT_ID_QUINARY_TDM_TX + 0x0A)
+#define AFE_PORT_ID_QUINARY_TDM_TX_6 \
+	(AFE_PORT_ID_QUINARY_TDM_TX + 0x0C)
+#define AFE_PORT_ID_QUINARY_TDM_TX_7 \
+	(AFE_PORT_ID_QUINARY_TDM_TX + 0x0E)
+
+#define Q6AFE_LPASS_MODE_CLK1_VALID 1
+#define Q6AFE_LPASS_MODE_CLK2_VALID 2
+#define Q6AFE_LPASS_CLK_SRC_INTERNAL 1
+#define Q6AFE_LPASS_CLK_ROOT_DEFAULT 0
+#define AFE_API_VERSION_TDM_CONFIG              1
+#define AFE_API_VERSION_SLOT_MAPPING_CONFIG	1
+
+#define TIMEOUT_MS 1000
+#define AFE_CMD_RESP_AVAIL	0
+#define AFE_CMD_RESP_NONE	1
+
+struct q6afe {
+	struct apr_device *apr;
+	struct device *dev;
+	struct q6core_svc_api_info ainfo;
+	struct mutex lock;
+	struct list_head port_list;
+	spinlock_t port_list_lock;
+	struct platform_device *pdev_dais;
+};
+
+struct afe_port_cmd_device_start {
+	u16 port_id;
+	u16 reserved;
+} __packed;
+
+struct afe_port_cmd_device_stop {
+	u16 port_id;
+	u16 reserved;
+/* Reserved for 32-bit alignment. This field must be set to 0.*/
+} __packed;
+
+struct afe_port_param_data_v2 {
+	u32 module_id;
+	u32 param_id;
+	u16 param_size;
+	u16 reserved;
+} __packed;
+
+struct afe_svc_cmd_set_param {
+	uint32_t payload_size;
+	uint32_t payload_address_lsw;
+	uint32_t payload_address_msw;
+	uint32_t mem_map_handle;
+} __packed;
+
+struct afe_port_cmd_set_param_v2 {
+	u16 port_id;
+	u16 payload_size;
+	u32 payload_address_lsw;
+	u32 payload_address_msw;
+	u32 mem_map_handle;
+} __packed;
+
+struct afe_param_id_hdmi_multi_chan_audio_cfg {
+	u32 hdmi_cfg_minor_version;
+	u16 datatype;
+	u16 channel_allocation;
+	u32 sample_rate;
+	u16 bit_width;
+	u16 reserved;
+} __packed;
+
+struct afe_param_id_slimbus_cfg {
+	u32                  sb_cfg_minor_version;
+/* Minor version used for tracking the version of the SLIMBUS
+ * configuration interface.
+ * Supported values: #AFE_API_VERSION_SLIMBUS_CONFIG
+ */
+
+	u16                  slimbus_dev_id;
+/* SLIMbus hardware device ID, which is required to handle
+ * multiple SLIMbus hardware blocks.
+ * Supported values: - #AFE_SLIMBUS_DEVICE_1 - #AFE_SLIMBUS_DEVICE_2
+ */
+	u16                  bit_width;
+/* Bit width of the sample.
+ * Supported values: 16, 24
+ */
+	u16                  data_format;
+/* Data format supported by the SLIMbus hardware. The default is
+ * 0 (#AFE_SB_DATA_FORMAT_NOT_INDICATED), which indicates the
+ * hardware does not perform any format conversions before the data
+ * transfer.
+ */
+	u16                  num_channels;
+/* Number of channels.
+ * Supported values: 1 to #AFE_PORT_MAX_AUDIO_CHAN_CNT
+ */
+	u8  shared_ch_mapping[AFE_PORT_MAX_AUDIO_CHAN_CNT];
+/* Mapping of shared channel IDs (128 to 255) to which the
+ * master port is to be connected.
+ * Shared_channel_mapping[i] represents the shared channel assigned
+ * for audio channel i in multichannel audio data.
+ */
+	u32              sample_rate;
+/* Sampling rate of the port.
+ * Supported values:
+ * - #AFE_PORT_SAMPLE_RATE_8K
+ * - #AFE_PORT_SAMPLE_RATE_16K
+ * - #AFE_PORT_SAMPLE_RATE_48K
+ * - #AFE_PORT_SAMPLE_RATE_96K
+ * - #AFE_PORT_SAMPLE_RATE_192K
+ */
+} __packed;
+
+struct afe_clk_cfg {
+	u32                  i2s_cfg_minor_version;
+	u32                  clk_val1;
+	u32                  clk_val2;
+	u16                  clk_src;
+	u16                  clk_root;
+	u16                  clk_set_mode;
+	u16                  reserved;
+} __packed;
+
+struct afe_digital_clk_cfg {
+	u32                  i2s_cfg_minor_version;
+	u32                  clk_val;
+	u16                  clk_root;
+	u16                  reserved;
+} __packed;
+
+struct afe_param_id_i2s_cfg {
+	u32	i2s_cfg_minor_version;
+	u16	bit_width;
+	u16	channel_mode;
+	u16	mono_stereo;
+	u16	ws_src;
+	u32	sample_rate;
+	u16	data_format;
+	u16	reserved;
+} __packed;
+
+struct afe_param_id_tdm_cfg {
+	u32	tdm_cfg_minor_version;
+	u32	num_channels;
+	u32	sample_rate;
+	u32	bit_width;
+	u16	data_format;
+	u16	sync_mode;
+	u16	sync_src;
+	u16	nslots_per_frame;
+	u16	ctrl_data_out_enable;
+	u16	ctrl_invert_sync_pulse;
+	u16	ctrl_sync_data_delay;
+	u16	slot_width;
+	u32	slot_mask;
+} __packed;
+
+union afe_port_config {
+	struct afe_param_id_hdmi_multi_chan_audio_cfg hdmi_multi_ch;
+	struct afe_param_id_slimbus_cfg           slim_cfg;
+	struct afe_param_id_i2s_cfg	i2s_cfg;
+	struct afe_param_id_tdm_cfg	tdm_cfg;
+} __packed;
+
+
+struct afe_clk_set {
+	uint32_t clk_set_minor_version;
+	uint32_t clk_id;
+	uint32_t clk_freq_in_hz;
+	uint16_t clk_attri;
+	uint16_t clk_root;
+	uint32_t enable;
+};
+
+struct afe_param_id_slot_mapping_cfg {
+	u32	minor_version;
+	u16	num_channels;
+	u16	bitwidth;
+	u32	data_align_type;
+	u16	ch_mapping[AFE_PORT_MAX_AUDIO_CHAN_CNT];
+} __packed;
+
+struct q6afe_port {
+	wait_queue_head_t wait;
+	union afe_port_config port_cfg;
+	struct afe_param_id_slot_mapping_cfg *scfg;
+	struct aprv2_ibasic_rsp_result_t result;
+	int token;
+	int id;
+	int cfg_type;
+	struct q6afe *afe;
+	struct kref refcount;
+	struct list_head node;
+};
+
+struct afe_port_map {
+	int port_id;
+	int token;
+	int is_rx;
+	int is_dig_pcm;
+};
+
+/*
+ * Mapping between Virtual Port IDs to DSP AFE Port ID
+ * On B Family SoCs DSP Port IDs are consistent across multiple SoCs
+ * on A Family SoCs DSP port IDs are same as virtual Port IDs.
+ */
+
+static struct afe_port_map port_maps[AFE_PORT_MAX] = {
+	[HDMI_RX] = { AFE_PORT_ID_MULTICHAN_HDMI_RX, HDMI_RX, 1, 1},
+	[SLIMBUS_0_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_RX,
+				SLIMBUS_0_RX, 1, 1},
+	[SLIMBUS_1_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_RX,
+				SLIMBUS_1_RX, 1, 1},
+	[SLIMBUS_2_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_RX,
+				SLIMBUS_2_RX, 1, 1},
+	[SLIMBUS_3_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_3_RX,
+				SLIMBUS_3_RX, 1, 1},
+	[SLIMBUS_4_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_4_RX,
+				SLIMBUS_4_RX, 1, 1},
+	[SLIMBUS_5_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_5_RX,
+				SLIMBUS_5_RX, 1, 1},
+	[SLIMBUS_6_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_RX,
+				SLIMBUS_6_RX, 1, 1},
+	[PRIMARY_MI2S_RX] = { AFE_PORT_ID_PRIMARY_MI2S_RX,
+				PRIMARY_MI2S_RX, 1, 1},
+	[PRIMARY_MI2S_TX] = { AFE_PORT_ID_PRIMARY_MI2S_TX,
+				PRIMARY_MI2S_RX, 0, 1},
+	[SECONDARY_MI2S_RX] = { AFE_PORT_ID_SECONDARY_MI2S_RX,
+				SECONDARY_MI2S_RX, 1, 1},
+	[SECONDARY_MI2S_TX] = { AFE_PORT_ID_SECONDARY_MI2S_TX,
+				SECONDARY_MI2S_TX, 0, 1},
+	[TERTIARY_MI2S_RX] = { AFE_PORT_ID_TERTIARY_MI2S_RX,
+				TERTIARY_MI2S_RX, 1, 1},
+	[TERTIARY_MI2S_TX] = { AFE_PORT_ID_TERTIARY_MI2S_TX,
+				TERTIARY_MI2S_TX, 0, 1},
+	[QUATERNARY_MI2S_RX] = { AFE_PORT_ID_QUATERNARY_MI2S_RX,
+				QUATERNARY_MI2S_RX, 1, 1},
+	[QUATERNARY_MI2S_TX] = { AFE_PORT_ID_QUATERNARY_MI2S_TX,
+				QUATERNARY_MI2S_TX, 0, 1},
+	[PRIMARY_TDM_RX_0] =  { AFE_PORT_ID_PRIMARY_TDM_RX,
+				PRIMARY_TDM_RX_0, 1, 1},
+	[PRIMARY_TDM_TX_0] =  { AFE_PORT_ID_PRIMARY_TDM_TX,
+				PRIMARY_TDM_TX_0, 0, 1},
+	[PRIMARY_TDM_RX_1] =  { AFE_PORT_ID_PRIMARY_TDM_RX_1,
+				PRIMARY_TDM_RX_1, 1, 1},
+	[PRIMARY_TDM_TX_1] =  { AFE_PORT_ID_PRIMARY_TDM_TX_1,
+				PRIMARY_TDM_TX_1, 0, 1},
+	[PRIMARY_TDM_RX_2] =  { AFE_PORT_ID_PRIMARY_TDM_RX_2,
+				PRIMARY_TDM_RX_2, 1, 1},
+	[PRIMARY_TDM_TX_2] =  { AFE_PORT_ID_PRIMARY_TDM_TX_2,
+				PRIMARY_TDM_TX_2, 0, 1},
+	[PRIMARY_TDM_RX_3] =  { AFE_PORT_ID_PRIMARY_TDM_RX_3,
+				PRIMARY_TDM_RX_3, 1, 1},
+	[PRIMARY_TDM_TX_3] =  { AFE_PORT_ID_PRIMARY_TDM_TX_3,
+				PRIMARY_TDM_TX_3, 0, 1},
+	[PRIMARY_TDM_RX_4] =  { AFE_PORT_ID_PRIMARY_TDM_RX_4,
+				PRIMARY_TDM_RX_4, 1, 1},
+	[PRIMARY_TDM_TX_4] =  { AFE_PORT_ID_PRIMARY_TDM_TX_4,
+				PRIMARY_TDM_TX_4, 0, 1},
+	[PRIMARY_TDM_RX_5] =  { AFE_PORT_ID_PRIMARY_TDM_RX_5,
+				PRIMARY_TDM_RX_5, 1, 1},
+	[PRIMARY_TDM_TX_5] =  { AFE_PORT_ID_PRIMARY_TDM_TX_5,
+				PRIMARY_TDM_TX_5, 0, 1},
+	[PRIMARY_TDM_RX_6] =  { AFE_PORT_ID_PRIMARY_TDM_RX_6,
+				PRIMARY_TDM_RX_6, 1, 1},
+	[PRIMARY_TDM_TX_6] =  { AFE_PORT_ID_PRIMARY_TDM_TX_6,
+				PRIMARY_TDM_TX_6, 0, 1},
+	[PRIMARY_TDM_RX_7] =  { AFE_PORT_ID_PRIMARY_TDM_RX_7,
+				PRIMARY_TDM_RX_7, 1, 1},
+	[PRIMARY_TDM_TX_7] =  { AFE_PORT_ID_PRIMARY_TDM_TX_7,
+				PRIMARY_TDM_TX_7, 0, 1},
+	[SECONDARY_TDM_RX_0] =  { AFE_PORT_ID_SECONDARY_TDM_RX,
+				SECONDARY_TDM_RX_0, 1, 1},
+	[SECONDARY_TDM_TX_0] =  { AFE_PORT_ID_SECONDARY_TDM_TX,
+				SECONDARY_TDM_TX_0, 0, 1},
+	[SECONDARY_TDM_RX_1] =  { AFE_PORT_ID_SECONDARY_TDM_RX_1,
+				SECONDARY_TDM_RX_1, 1, 1},
+	[SECONDARY_TDM_TX_1] =  { AFE_PORT_ID_SECONDARY_TDM_TX_1,
+				SECONDARY_TDM_TX_1, 0, 1},
+	[SECONDARY_TDM_RX_2] =  { AFE_PORT_ID_SECONDARY_TDM_RX_2,
+				SECONDARY_TDM_RX_2, 1, 1},
+	[SECONDARY_TDM_TX_2] =  { AFE_PORT_ID_SECONDARY_TDM_TX_2,
+				SECONDARY_TDM_TX_2, 0, 1},
+	[SECONDARY_TDM_RX_3] =  { AFE_PORT_ID_SECONDARY_TDM_RX_3,
+				SECONDARY_TDM_RX_3, 1, 1},
+	[SECONDARY_TDM_TX_3] =  { AFE_PORT_ID_SECONDARY_TDM_TX_3,
+				SECONDARY_TDM_TX_3, 0, 1},
+	[SECONDARY_TDM_RX_4] =  { AFE_PORT_ID_SECONDARY_TDM_RX_4,
+				SECONDARY_TDM_RX_4, 1, 1},
+	[SECONDARY_TDM_TX_4] =  { AFE_PORT_ID_SECONDARY_TDM_TX_4,
+				SECONDARY_TDM_TX_4, 0, 1},
+	[SECONDARY_TDM_RX_5] =  { AFE_PORT_ID_SECONDARY_TDM_RX_5,
+				SECONDARY_TDM_RX_5, 1, 1},
+	[SECONDARY_TDM_TX_5] =  { AFE_PORT_ID_SECONDARY_TDM_TX_5,
+				SECONDARY_TDM_TX_5, 0, 1},
+	[SECONDARY_TDM_RX_6] =  { AFE_PORT_ID_SECONDARY_TDM_RX_6,
+				SECONDARY_TDM_RX_6, 1, 1},
+	[SECONDARY_TDM_TX_6] =  { AFE_PORT_ID_SECONDARY_TDM_TX_6,
+				SECONDARY_TDM_TX_6, 0, 1},
+	[SECONDARY_TDM_RX_7] =  { AFE_PORT_ID_SECONDARY_TDM_RX_7,
+				SECONDARY_TDM_RX_7, 1, 1},
+	[SECONDARY_TDM_TX_7] =  { AFE_PORT_ID_SECONDARY_TDM_TX_7,
+				SECONDARY_TDM_TX_7, 0, 1},
+	[TERTIARY_TDM_RX_0] =  { AFE_PORT_ID_TERTIARY_TDM_RX,
+				TERTIARY_TDM_RX_0, 1, 1},
+	[TERTIARY_TDM_TX_0] =  { AFE_PORT_ID_TERTIARY_TDM_TX,
+				TERTIARY_TDM_TX_0, 0, 1},
+	[TERTIARY_TDM_RX_1] =  { AFE_PORT_ID_TERTIARY_TDM_RX_1,
+				TERTIARY_TDM_RX_1, 1, 1},
+	[TERTIARY_TDM_TX_1] =  { AFE_PORT_ID_TERTIARY_TDM_TX_1,
+				TERTIARY_TDM_TX_1, 0, 1},
+	[TERTIARY_TDM_RX_2] =  { AFE_PORT_ID_TERTIARY_TDM_RX_2,
+				TERTIARY_TDM_RX_2, 1, 1},
+	[TERTIARY_TDM_TX_2] =  { AFE_PORT_ID_TERTIARY_TDM_TX_2,
+				TERTIARY_TDM_TX_2, 0, 1},
+	[TERTIARY_TDM_RX_3] =  { AFE_PORT_ID_TERTIARY_TDM_RX_3,
+				TERTIARY_TDM_RX_3, 1, 1},
+	[TERTIARY_TDM_TX_3] =  { AFE_PORT_ID_TERTIARY_TDM_TX_3,
+				TERTIARY_TDM_TX_3, 0, 1},
+	[TERTIARY_TDM_RX_4] =  { AFE_PORT_ID_TERTIARY_TDM_RX_4,
+				TERTIARY_TDM_RX_4, 1, 1},
+	[TERTIARY_TDM_TX_4] =  { AFE_PORT_ID_TERTIARY_TDM_TX_4,
+				TERTIARY_TDM_TX_4, 0, 1},
+	[TERTIARY_TDM_RX_5] =  { AFE_PORT_ID_TERTIARY_TDM_RX_5,
+				TERTIARY_TDM_RX_5, 1, 1},
+	[TERTIARY_TDM_TX_5] =  { AFE_PORT_ID_TERTIARY_TDM_TX_5,
+				TERTIARY_TDM_TX_5, 0, 1},
+	[TERTIARY_TDM_RX_6] =  { AFE_PORT_ID_TERTIARY_TDM_RX_6,
+				TERTIARY_TDM_RX_6, 1, 1},
+	[TERTIARY_TDM_TX_6] =  { AFE_PORT_ID_TERTIARY_TDM_TX_6,
+				TERTIARY_TDM_TX_6, 0, 1},
+	[TERTIARY_TDM_RX_7] =  { AFE_PORT_ID_TERTIARY_TDM_RX_7,
+				TERTIARY_TDM_RX_7, 1, 1},
+	[TERTIARY_TDM_TX_7] =  { AFE_PORT_ID_TERTIARY_TDM_TX_7,
+				TERTIARY_TDM_TX_7, 0, 1},
+	[QUATERNARY_TDM_RX_0] =  { AFE_PORT_ID_QUATERNARY_TDM_RX,
+				QUATERNARY_TDM_RX_0, 1, 1},
+	[QUATERNARY_TDM_TX_0] =  { AFE_PORT_ID_QUATERNARY_TDM_TX,
+				QUATERNARY_TDM_TX_0, 0, 1},
+	[QUATERNARY_TDM_RX_1] =  { AFE_PORT_ID_QUATERNARY_TDM_RX_1,
+				QUATERNARY_TDM_RX_1, 1, 1},
+	[QUATERNARY_TDM_TX_1] =  { AFE_PORT_ID_QUATERNARY_TDM_TX_1,
+				QUATERNARY_TDM_TX_1, 0, 1},
+	[QUATERNARY_TDM_RX_2] =  { AFE_PORT_ID_QUATERNARY_TDM_RX_2,
+				QUATERNARY_TDM_RX_2, 1, 1},
+	[QUATERNARY_TDM_TX_2] =  { AFE_PORT_ID_QUATERNARY_TDM_TX_2,
+				QUATERNARY_TDM_TX_2, 0, 1},
+	[QUATERNARY_TDM_RX_3] =  { AFE_PORT_ID_QUATERNARY_TDM_RX_3,
+				QUATERNARY_TDM_RX_3, 1, 1},
+	[QUATERNARY_TDM_TX_3] =  { AFE_PORT_ID_QUATERNARY_TDM_TX_3,
+				QUATERNARY_TDM_TX_3, 0, 1},
+	[QUATERNARY_TDM_RX_4] =  { AFE_PORT_ID_QUATERNARY_TDM_RX_4,
+				QUATERNARY_TDM_RX_4, 1, 1},
+	[QUATERNARY_TDM_TX_4] =  { AFE_PORT_ID_QUATERNARY_TDM_TX_4,
+				QUATERNARY_TDM_TX_4, 0, 1},
+	[QUATERNARY_TDM_RX_5] =  { AFE_PORT_ID_QUATERNARY_TDM_RX_5,
+				QUATERNARY_TDM_RX_5, 1, 1},
+	[QUATERNARY_TDM_TX_5] =  { AFE_PORT_ID_QUATERNARY_TDM_TX_5,
+				QUATERNARY_TDM_TX_5, 0, 1},
+	[QUATERNARY_TDM_RX_6] =  { AFE_PORT_ID_QUATERNARY_TDM_RX_6,
+				QUATERNARY_TDM_RX_6, 1, 1},
+	[QUATERNARY_TDM_TX_6] =  { AFE_PORT_ID_QUATERNARY_TDM_TX_6,
+				QUATERNARY_TDM_TX_6, 0, 1},
+	[QUATERNARY_TDM_RX_7] =  { AFE_PORT_ID_QUATERNARY_TDM_RX_7,
+				QUATERNARY_TDM_RX_7, 1, 1},
+	[QUATERNARY_TDM_TX_7] =  { AFE_PORT_ID_QUATERNARY_TDM_TX_7,
+				QUATERNARY_TDM_TX_7, 0, 1},
+	[QUINARY_TDM_RX_0] =  { AFE_PORT_ID_QUINARY_TDM_RX,
+				QUINARY_TDM_RX_0, 1, 1},
+	[QUINARY_TDM_TX_0] =  { AFE_PORT_ID_QUINARY_TDM_TX,
+				QUINARY_TDM_TX_0, 0, 1},
+	[QUINARY_TDM_RX_1] =  { AFE_PORT_ID_QUINARY_TDM_RX_1,
+				QUINARY_TDM_RX_1, 1, 1},
+	[QUINARY_TDM_TX_1] =  { AFE_PORT_ID_QUINARY_TDM_TX_1,
+				QUINARY_TDM_TX_1, 0, 1},
+	[QUINARY_TDM_RX_2] =  { AFE_PORT_ID_QUINARY_TDM_RX_2,
+				QUINARY_TDM_RX_2, 1, 1},
+	[QUINARY_TDM_TX_2] =  { AFE_PORT_ID_QUINARY_TDM_TX_2,
+				QUINARY_TDM_TX_2, 0, 1},
+	[QUINARY_TDM_RX_3] =  { AFE_PORT_ID_QUINARY_TDM_RX_3,
+				QUINARY_TDM_RX_3, 1, 1},
+	[QUINARY_TDM_TX_3] =  { AFE_PORT_ID_QUINARY_TDM_TX_3,
+				QUINARY_TDM_TX_3, 0, 1},
+	[QUINARY_TDM_RX_4] =  { AFE_PORT_ID_QUINARY_TDM_RX_4,
+				QUINARY_TDM_RX_4, 1, 1},
+	[QUINARY_TDM_TX_4] =  { AFE_PORT_ID_QUINARY_TDM_TX_4,
+				QUINARY_TDM_TX_4, 0, 1},
+	[QUINARY_TDM_RX_5] =  { AFE_PORT_ID_QUINARY_TDM_RX_5,
+				QUINARY_TDM_RX_5, 1, 1},
+	[QUINARY_TDM_TX_5] =  { AFE_PORT_ID_QUINARY_TDM_TX_5,
+				QUINARY_TDM_TX_5, 0, 1},
+	[QUINARY_TDM_RX_6] =  { AFE_PORT_ID_QUINARY_TDM_RX_6,
+				QUINARY_TDM_RX_6, 1, 1},
+	[QUINARY_TDM_TX_6] =  { AFE_PORT_ID_QUINARY_TDM_TX_6,
+				QUINARY_TDM_TX_6, 0, 1},
+	[QUINARY_TDM_RX_7] =  { AFE_PORT_ID_QUINARY_TDM_RX_7,
+				QUINARY_TDM_RX_7, 1, 1},
+	[QUINARY_TDM_TX_7] =  { AFE_PORT_ID_QUINARY_TDM_TX_7,
+				QUINARY_TDM_TX_7, 0, 1},
+};
+
+static void q6afe_port_free(struct kref *ref)
+{
+	struct q6afe_port *port;
+	struct q6afe *afe;
+	unsigned long flags;
+
+	port = container_of(ref, struct q6afe_port, refcount);
+	afe = port->afe;
+	spin_lock_irqsave(&afe->port_list_lock, flags);
+	list_del(&port->node);
+	spin_unlock_irqrestore(&afe->port_list_lock, flags);
+	kfree(port->scfg);
+	kfree(port);
+}
+
+static struct q6afe_port *q6afe_find_port(struct q6afe *afe, int token)
+{
+	struct q6afe_port *p = NULL;
+	struct q6afe_port *ret = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&afe->port_list_lock, flags);
+	list_for_each_entry(p, &afe->port_list, node)
+		if (p->token == token) {
+			ret = p;
+			kref_get(&p->refcount);
+			break;
+		}
+
+	spin_unlock_irqrestore(&afe->port_list_lock, flags);
+	return ret;
+}
+
+static int q6afe_callback(struct apr_device *adev, struct apr_resp_pkt *data)
+{
+	struct q6afe *afe = dev_get_drvdata(&adev->dev);
+	struct aprv2_ibasic_rsp_result_t *res;
+	struct apr_hdr *hdr = &data->hdr;
+	struct q6afe_port *port;
+
+	if (!data->payload_size)
+		return 0;
+
+	res = data->payload;
+	switch (hdr->opcode) {
+	case APR_BASIC_RSP_RESULT: {
+		if (res->status) {
+			dev_err(afe->dev, "cmd = 0x%x returned error = 0x%x\n",
+				res->opcode, res->status);
+		}
+		switch (res->opcode) {
+		case AFE_PORT_CMD_SET_PARAM_V2:
+		case AFE_PORT_CMD_DEVICE_STOP:
+		case AFE_PORT_CMD_DEVICE_START:
+		case AFE_SVC_CMD_SET_PARAM:
+			port = q6afe_find_port(afe, hdr->token);
+			if (port) {
+				port->result = *res;
+				wake_up(&port->wait);
+				kref_put(&port->refcount, q6afe_port_free);
+			}
+			break;
+		default:
+			dev_err(afe->dev, "Unknown cmd 0x%x\n",	res->opcode);
+			break;
+		}
+	}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * q6afe_get_port_id() - Get port id from a given port index
+ *
+ * @index: port index
+ *
+ * Return: Will be an negative on error or valid port_id on success
+ */
+int q6afe_get_port_id(int index)
+{
+	if (index < 0 || index > AFE_PORT_MAX)
+		return -EINVAL;
+
+	return port_maps[index].port_id;
+}
+EXPORT_SYMBOL_GPL(q6afe_get_port_id);
+
+static int afe_apr_send_pkt(struct q6afe *afe, struct apr_pkt *pkt,
+			    struct q6afe_port *port)
+{
+	wait_queue_head_t *wait = &port->wait;
+	struct apr_hdr *hdr = &pkt->hdr;
+	int ret;
+
+	mutex_lock(&afe->lock);
+	port->result.opcode = 0;
+	port->result.status = 0;
+
+	ret = apr_send_pkt(afe->apr, pkt);
+	if (ret < 0) {
+		dev_err(afe->dev, "packet not transmitted (%d)\n", ret);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	ret = wait_event_timeout(*wait, (port->result.opcode == hdr->opcode),
+				 msecs_to_jiffies(TIMEOUT_MS));
+	if (!ret) {
+		ret = -ETIMEDOUT;
+	} else if (port->result.status > 0) {
+		dev_err(afe->dev, "DSP returned error[%x]\n",
+			port->result.status);
+		ret = -EINVAL;
+	} else {
+		ret = 0;
+	}
+
+err:
+	mutex_unlock(&afe->lock);
+
+	return ret;
+}
+
+static int q6afe_port_set_param(struct q6afe_port *port, void *data,
+				int param_id, int module_id, int psize)
+{
+	struct afe_svc_cmd_set_param *param;
+	struct afe_port_param_data_v2 *pdata;
+	struct q6afe *afe = port->afe;
+	struct apr_pkt *pkt;
+	u16 port_id = port->id;
+	int ret, pkt_size;
+	void *p, *pl;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*param) + sizeof(*pdata) + psize;
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	param = p + APR_HDR_SIZE;
+	pdata = p + APR_HDR_SIZE + sizeof(*param);
+	pl = p + APR_HDR_SIZE + sizeof(*param) + sizeof(*pdata);
+	memcpy(pl, data, psize);
+
+	pkt->hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+					   APR_HDR_LEN(APR_HDR_SIZE),
+					   APR_PKT_VER);
+	pkt->hdr.pkt_size = pkt_size;
+	pkt->hdr.src_port = 0;
+	pkt->hdr.dest_port = 0;
+	pkt->hdr.token = port->token;
+	pkt->hdr.opcode = AFE_SVC_CMD_SET_PARAM;
+
+	param->payload_size = sizeof(*pdata) + psize;
+	param->payload_address_lsw = 0x00;
+	param->payload_address_msw = 0x00;
+	param->mem_map_handle = 0x00;
+	pdata->module_id = module_id;
+	pdata->param_id = param_id;
+	pdata->param_size = psize;
+
+	ret = afe_apr_send_pkt(afe, pkt, port);
+	if (ret)
+		dev_err(afe->dev, "AFE enable for port 0x%x failed %d\n",
+		       port_id, ret);
+
+	kfree(pkt);
+	return ret;
+}
+
+static int q6afe_port_set_param_v2(struct q6afe_port *port, void *data,
+				   int param_id, int module_id, int psize)
+{
+	struct afe_port_cmd_set_param_v2 *param;
+	struct afe_port_param_data_v2 *pdata;
+	struct q6afe *afe = port->afe;
+	struct apr_pkt *pkt;
+	u16 port_id = port->id;
+	int ret, pkt_size;
+	void *p, *pl;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*param) + sizeof(*pdata) + psize;
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	param = p + APR_HDR_SIZE;
+	pdata = p + APR_HDR_SIZE + sizeof(*param);
+	pl = p + APR_HDR_SIZE + sizeof(*param) + sizeof(*pdata);
+	memcpy(pl, data, psize);
+
+	pkt->hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+					   APR_HDR_LEN(APR_HDR_SIZE),
+					   APR_PKT_VER);
+	pkt->hdr.pkt_size = pkt_size;
+	pkt->hdr.src_port = 0;
+	pkt->hdr.dest_port = 0;
+	pkt->hdr.token = port->token;
+	pkt->hdr.opcode = AFE_PORT_CMD_SET_PARAM_V2;
+
+	param->port_id = port_id;
+	param->payload_size = sizeof(*pdata) + psize;
+	param->payload_address_lsw = 0x00;
+	param->payload_address_msw = 0x00;
+	param->mem_map_handle = 0x00;
+	pdata->module_id = module_id;
+	pdata->param_id = param_id;
+	pdata->param_size = psize;
+
+	ret = afe_apr_send_pkt(afe, pkt, port);
+	if (ret)
+		dev_err(afe->dev, "AFE enable for port 0x%x failed %d\n",
+		       port_id, ret);
+
+	kfree(pkt);
+	return ret;
+}
+
+static int q6afe_set_lpass_clock(struct q6afe_port *port,
+				 struct afe_clk_cfg *cfg)
+{
+	return q6afe_port_set_param_v2(port, cfg,
+				       AFE_PARAM_ID_LPAIF_CLK_CONFIG,
+				       AFE_MODULE_AUDIO_DEV_INTERFACE,
+				       sizeof(*cfg));
+}
+
+static int q6afe_set_lpass_clock_v2(struct q6afe_port *port,
+				 struct afe_clk_set *cfg)
+{
+	return q6afe_port_set_param(port, cfg, AFE_PARAM_ID_CLOCK_SET,
+				    AFE_MODULE_CLOCK_SET, sizeof(*cfg));
+}
+
+static int q6afe_set_digital_codec_core_clock(struct q6afe_port *port,
+					      struct afe_digital_clk_cfg *cfg)
+{
+	return q6afe_port_set_param_v2(port, cfg,
+				       AFE_PARAM_ID_INT_DIGITAL_CDC_CLK_CONFIG,
+				       AFE_MODULE_AUDIO_DEV_INTERFACE,
+				       sizeof(*cfg));
+}
+
+int q6afe_port_set_sysclk(struct q6afe_port *port, int clk_id,
+			  int clk_src, int clk_root,
+			  unsigned int freq, int dir)
+{
+	struct afe_clk_cfg ccfg = {0,};
+	struct afe_clk_set cset = {0,};
+	struct afe_digital_clk_cfg dcfg = {0,};
+	int ret;
+
+	switch (clk_id) {
+	case LPAIF_DIG_CLK:
+		dcfg.i2s_cfg_minor_version = AFE_API_VERSION_I2S_CONFIG;
+		dcfg.clk_val = freq;
+		dcfg.clk_root = clk_root;
+		ret = q6afe_set_digital_codec_core_clock(port, &dcfg);
+		break;
+	case LPAIF_BIT_CLK:
+		ccfg.i2s_cfg_minor_version = AFE_API_VERSION_I2S_CONFIG;
+		ccfg.clk_val1 = freq;
+		ccfg.clk_src = clk_src;
+		ccfg.clk_root = clk_root;
+		ccfg.clk_set_mode = Q6AFE_LPASS_MODE_CLK1_VALID;
+		ret = q6afe_set_lpass_clock(port, &ccfg);
+		break;
+
+	case LPAIF_OSR_CLK:
+		ccfg.i2s_cfg_minor_version = AFE_API_VERSION_I2S_CONFIG;
+		ccfg.clk_val2 = freq;
+		ccfg.clk_src = clk_src;
+		ccfg.clk_root = clk_root;
+		ccfg.clk_set_mode = Q6AFE_LPASS_MODE_CLK2_VALID;
+		ret = q6afe_set_lpass_clock(port, &ccfg);
+		break;
+	case Q6AFE_LPASS_CLK_ID_PRI_MI2S_IBIT ... Q6AFE_LPASS_CLK_ID_QUI_MI2S_OSR:
+	case Q6AFE_LPASS_CLK_ID_MCLK_1 ... Q6AFE_LPASS_CLK_ID_INT_MCLK_1:
+	case Q6AFE_LPASS_CLK_ID_PRI_TDM_IBIT ... Q6AFE_LPASS_CLK_ID_QUIN_TDM_EBIT:
+		cset.clk_set_minor_version = AFE_API_VERSION_CLOCK_SET;
+		cset.clk_id = clk_id;
+		cset.clk_freq_in_hz = freq;
+		cset.clk_attri = clk_src;
+		cset.clk_root = clk_root;
+		cset.enable = !!freq;
+		ret = q6afe_set_lpass_clock_v2(port, &cset);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(q6afe_port_set_sysclk);
+
+/**
+ * q6afe_port_stop() - Stop a afe port
+ *
+ * @port: Instance of port to stop
+ *
+ * Return: Will be an negative on packet size on success.
+ */
+int q6afe_port_stop(struct q6afe_port *port)
+{
+	struct afe_port_cmd_device_stop *stop;
+	struct q6afe *afe = port->afe;
+	struct apr_pkt *pkt;
+	int port_id = port->id;
+	int ret = 0;
+	int index, pkt_size;
+	void *p;
+
+	port_id = port->id;
+	index = port->token;
+	if (index < 0 || index > AFE_PORT_MAX) {
+		dev_err(afe->dev, "AFE port index[%d] invalid!\n", index);
+		return -EINVAL;
+	}
+
+	pkt_size = APR_HDR_SIZE + sizeof(*stop);
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	stop = p + APR_HDR_SIZE;
+
+	pkt->hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+					   APR_HDR_LEN(APR_HDR_SIZE),
+					   APR_PKT_VER);
+	pkt->hdr.pkt_size = pkt_size;
+	pkt->hdr.src_port = 0;
+	pkt->hdr.dest_port = 0;
+	pkt->hdr.token = index;
+	pkt->hdr.opcode = AFE_PORT_CMD_DEVICE_STOP;
+	stop->port_id = port_id;
+	stop->reserved = 0;
+
+	ret = afe_apr_send_pkt(afe, pkt, port);
+	if (ret)
+		dev_err(afe->dev, "AFE close failed %d\n", ret);
+
+	kfree(pkt);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(q6afe_port_stop);
+
+/**
+ * q6afe_slim_port_prepare() - Prepare slim afe port.
+ *
+ * @port: Instance of afe port
+ * @cfg: SLIM configuration for the afe port
+ *
+ */
+void q6afe_slim_port_prepare(struct q6afe_port *port,
+			     struct q6afe_slim_cfg *cfg)
+{
+	union afe_port_config *pcfg = &port->port_cfg;
+
+	pcfg->slim_cfg.sb_cfg_minor_version = AFE_API_VERSION_SLIMBUS_CONFIG;
+	pcfg->slim_cfg.sample_rate = cfg->sample_rate;
+	pcfg->slim_cfg.bit_width = cfg->bit_width;
+	pcfg->slim_cfg.num_channels = cfg->num_channels;
+	pcfg->slim_cfg.data_format = cfg->data_format;
+	pcfg->slim_cfg.shared_ch_mapping[0] = cfg->ch_mapping[0];
+	pcfg->slim_cfg.shared_ch_mapping[1] = cfg->ch_mapping[1];
+	pcfg->slim_cfg.shared_ch_mapping[2] = cfg->ch_mapping[2];
+	pcfg->slim_cfg.shared_ch_mapping[3] = cfg->ch_mapping[3];
+
+}
+EXPORT_SYMBOL_GPL(q6afe_slim_port_prepare);
+
+/**
+ * q6afe_tdm_port_prepare() - Prepare tdm afe port.
+ *
+ * @port: Instance of afe port
+ * @cfg: TDM configuration for the afe port
+ *
+ */
+void q6afe_tdm_port_prepare(struct q6afe_port *port,
+			     struct q6afe_tdm_cfg *cfg)
+{
+	union afe_port_config *pcfg = &port->port_cfg;
+
+	pcfg->tdm_cfg.tdm_cfg_minor_version = AFE_API_VERSION_TDM_CONFIG;
+	pcfg->tdm_cfg.num_channels = cfg->num_channels;
+	pcfg->tdm_cfg.sample_rate = cfg->sample_rate;
+	pcfg->tdm_cfg.bit_width = cfg->bit_width;
+	pcfg->tdm_cfg.data_format = cfg->data_format;
+	pcfg->tdm_cfg.sync_mode = cfg->sync_mode;
+	pcfg->tdm_cfg.sync_src = cfg->sync_src;
+	pcfg->tdm_cfg.nslots_per_frame = cfg->nslots_per_frame;
+
+	pcfg->tdm_cfg.slot_width = cfg->slot_width;
+	pcfg->tdm_cfg.slot_mask = cfg->slot_mask;
+	port->scfg = kzalloc(sizeof(*port->scfg), GFP_KERNEL);
+	if (!port->scfg)
+		return;
+
+	port->scfg->minor_version = AFE_API_VERSION_SLOT_MAPPING_CONFIG;
+	port->scfg->num_channels = cfg->num_channels;
+	port->scfg->bitwidth = cfg->bit_width;
+	port->scfg->data_align_type = cfg->data_align_type;
+	memcpy(port->scfg->ch_mapping, cfg->ch_mapping,
+			sizeof(u16) * AFE_PORT_MAX_AUDIO_CHAN_CNT);
+}
+EXPORT_SYMBOL_GPL(q6afe_tdm_port_prepare);
+
+/**
+ * q6afe_hdmi_port_prepare() - Prepare hdmi afe port.
+ *
+ * @port: Instance of afe port
+ * @cfg: HDMI configuration for the afe port
+ *
+ */
+void q6afe_hdmi_port_prepare(struct q6afe_port *port,
+			     struct q6afe_hdmi_cfg *cfg)
+{
+	union afe_port_config *pcfg = &port->port_cfg;
+
+	pcfg->hdmi_multi_ch.hdmi_cfg_minor_version =
+					AFE_API_VERSION_HDMI_CONFIG;
+	pcfg->hdmi_multi_ch.datatype = cfg->datatype;
+	pcfg->hdmi_multi_ch.channel_allocation = cfg->channel_allocation;
+	pcfg->hdmi_multi_ch.sample_rate = cfg->sample_rate;
+	pcfg->hdmi_multi_ch.bit_width = cfg->bit_width;
+}
+EXPORT_SYMBOL_GPL(q6afe_hdmi_port_prepare);
+
+/**
+ * q6afe_i2s_port_prepare() - Prepare i2s afe port.
+ *
+ * @port: Instance of afe port
+ * @cfg: I2S configuration for the afe port
+ * Return: Will be an negative on error and zero on success.
+ */
+int q6afe_i2s_port_prepare(struct q6afe_port *port, struct q6afe_i2s_cfg *cfg)
+{
+	union afe_port_config *pcfg = &port->port_cfg;
+	struct device *dev = port->afe->dev;
+	int num_sd_lines;
+
+	pcfg->i2s_cfg.i2s_cfg_minor_version = AFE_API_VERSION_I2S_CONFIG;
+	pcfg->i2s_cfg.sample_rate = cfg->sample_rate;
+	pcfg->i2s_cfg.bit_width = cfg->bit_width;
+	pcfg->i2s_cfg.data_format = AFE_LINEAR_PCM_DATA;
+
+	switch (cfg->fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		pcfg->i2s_cfg.ws_src = AFE_PORT_CONFIG_I2S_WS_SRC_INTERNAL;
+		break;
+	case SND_SOC_DAIFMT_CBM_CFM:
+		/* CPU is slave */
+		pcfg->i2s_cfg.ws_src = AFE_PORT_CONFIG_I2S_WS_SRC_EXTERNAL;
+		break;
+	default:
+		break;
+	}
+
+	num_sd_lines = hweight_long(cfg->sd_line_mask);
+
+	switch (num_sd_lines) {
+	case 0:
+		dev_err(dev, "no line is assigned\n");
+		return -EINVAL;
+	case 1:
+		switch (cfg->sd_line_mask) {
+		case AFE_PORT_I2S_SD0_MASK:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_SD0;
+			break;
+		case AFE_PORT_I2S_SD1_MASK:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_SD1;
+			break;
+		case AFE_PORT_I2S_SD2_MASK:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_SD2;
+			break;
+		case AFE_PORT_I2S_SD3_MASK:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_SD3;
+			break;
+		default:
+			dev_err(dev, "Invalid SD lines\n");
+			return -EINVAL;
+		}
+		break;
+	case 2:
+		switch (cfg->sd_line_mask) {
+		case AFE_PORT_I2S_SD0_1_MASK:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_QUAD01;
+			break;
+		case AFE_PORT_I2S_SD2_3_MASK:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_QUAD23;
+			break;
+		default:
+			dev_err(dev, "Invalid SD lines\n");
+			return -EINVAL;
+		}
+		break;
+	case 3:
+		switch (cfg->sd_line_mask) {
+		case AFE_PORT_I2S_SD0_1_2_MASK:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_6CHS;
+			break;
+		default:
+			dev_err(dev, "Invalid SD lines\n");
+			return -EINVAL;
+		}
+		break;
+	case 4:
+		switch (cfg->sd_line_mask) {
+		case AFE_PORT_I2S_SD0_1_2_3_MASK:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_8CHS;
+
+			break;
+		default:
+			dev_err(dev, "Invalid SD lines\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		dev_err(dev, "Invalid SD lines\n");
+		return -EINVAL;
+	}
+
+	switch (cfg->num_channels) {
+	case 1:
+	case 2:
+		switch (pcfg->i2s_cfg.channel_mode) {
+		case AFE_PORT_I2S_QUAD01:
+		case AFE_PORT_I2S_6CHS:
+		case AFE_PORT_I2S_8CHS:
+			pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_SD0;
+			break;
+		case AFE_PORT_I2S_QUAD23:
+				pcfg->i2s_cfg.channel_mode = AFE_PORT_I2S_SD2;
+			break;
+		}
+
+		if (cfg->num_channels == 2)
+			pcfg->i2s_cfg.mono_stereo = AFE_PORT_I2S_STEREO;
+		else
+			pcfg->i2s_cfg.mono_stereo = AFE_PORT_I2S_MONO;
+
+		break;
+	case 3:
+	case 4:
+		if (pcfg->i2s_cfg.channel_mode < AFE_PORT_I2S_QUAD01) {
+			dev_err(dev, "Invalid Channel mode\n");
+			return -EINVAL;
+		}
+		break;
+	case 5:
+	case 6:
+		if (pcfg->i2s_cfg.channel_mode < AFE_PORT_I2S_6CHS) {
+			dev_err(dev, "Invalid Channel mode\n");
+			return -EINVAL;
+		}
+		break;
+	case 7:
+	case 8:
+		if (pcfg->i2s_cfg.channel_mode < AFE_PORT_I2S_8CHS) {
+			dev_err(dev, "Invalid Channel mode\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(q6afe_i2s_port_prepare);
+
+/**
+ * q6afe_port_start() - Start a afe port
+ *
+ * @port: Instance of port to start
+ *
+ * Return: Will be an negative on packet size on success.
+ */
+int q6afe_port_start(struct q6afe_port *port)
+{
+	struct afe_port_cmd_device_start *start;
+	struct q6afe *afe = port->afe;
+	int port_id = port->id;
+	int ret, param_id = port->cfg_type;
+	struct apr_pkt *pkt;
+	int pkt_size;
+	void *p;
+
+	ret  = q6afe_port_set_param_v2(port, &port->port_cfg, param_id,
+				       AFE_MODULE_AUDIO_DEV_INTERFACE,
+				       sizeof(port->port_cfg));
+	if (ret) {
+		dev_err(afe->dev, "AFE enable for port 0x%x failed %d\n",
+			port_id, ret);
+		return ret;
+	}
+
+	if (port->scfg) {
+		ret  = q6afe_port_set_param_v2(port, port->scfg,
+					AFE_PARAM_ID_PORT_SLOT_MAPPING_CONFIG,
+					AFE_MODULE_TDM, sizeof(*port->scfg));
+		if (ret) {
+			dev_err(afe->dev, "AFE enable for port 0x%x failed %d\n",
+			port_id, ret);
+			return ret;
+		}
+	}
+
+	pkt_size = APR_HDR_SIZE + sizeof(*start);
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	start = p + APR_HDR_SIZE;
+
+	pkt->hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+					    APR_HDR_LEN(APR_HDR_SIZE),
+					    APR_PKT_VER);
+	pkt->hdr.pkt_size = pkt_size;
+	pkt->hdr.src_port = 0;
+	pkt->hdr.dest_port = 0;
+	pkt->hdr.token = port->token;
+	pkt->hdr.opcode = AFE_PORT_CMD_DEVICE_START;
+
+	start->port_id = port_id;
+
+	ret = afe_apr_send_pkt(afe, pkt, port);
+	if (ret)
+		dev_err(afe->dev, "AFE enable for port 0x%x failed %d\n",
+			port_id, ret);
+
+	kfree(pkt);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(q6afe_port_start);
+
+/**
+ * q6afe_port_get_from_id() - Get port instance from a port id
+ *
+ * @dev: Pointer to afe child device.
+ * @id: port id
+ *
+ * Return: Will be an error pointer on error or a valid afe port
+ * on success.
+ */
+struct q6afe_port *q6afe_port_get_from_id(struct device *dev, int id)
+{
+	int port_id;
+	struct q6afe *afe = dev_get_drvdata(dev->parent);
+	struct q6afe_port *port;
+	unsigned long flags;
+	int cfg_type;
+
+	if (id < 0 || id > AFE_PORT_MAX) {
+		dev_err(dev, "AFE port token[%d] invalid!\n", id);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* if port is multiple times bind/unbind before callback finishes */
+	port = q6afe_find_port(afe, id);
+	if (port) {
+		dev_err(dev, "AFE Port already open\n");
+		return port;
+	}
+
+	port_id = port_maps[id].port_id;
+
+	switch (port_id) {
+	case AFE_PORT_ID_MULTICHAN_HDMI_RX:
+		cfg_type = AFE_PARAM_ID_HDMI_CONFIG;
+		break;
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_RX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_RX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_RX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_3_RX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_4_RX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_5_RX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_RX:
+		cfg_type = AFE_PARAM_ID_SLIMBUS_CONFIG;
+		break;
+
+	case AFE_PORT_ID_PRIMARY_MI2S_RX:
+	case AFE_PORT_ID_PRIMARY_MI2S_TX:
+	case AFE_PORT_ID_SECONDARY_MI2S_RX:
+	case AFE_PORT_ID_SECONDARY_MI2S_TX:
+	case AFE_PORT_ID_TERTIARY_MI2S_RX:
+	case AFE_PORT_ID_TERTIARY_MI2S_TX:
+	case AFE_PORT_ID_QUATERNARY_MI2S_RX:
+	case AFE_PORT_ID_QUATERNARY_MI2S_TX:
+		cfg_type = AFE_PARAM_ID_I2S_CONFIG;
+		break;
+	case AFE_PORT_ID_PRIMARY_TDM_RX ... AFE_PORT_ID_QUINARY_TDM_TX_7:
+		cfg_type = AFE_PARAM_ID_TDM_CONFIG;
+		break;
+
+	default:
+		dev_err(dev, "Invalid port id 0x%x\n", port_id);
+		return ERR_PTR(-EINVAL);
+	}
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return ERR_PTR(-ENOMEM);
+
+	init_waitqueue_head(&port->wait);
+
+	port->token = id;
+	port->id = port_id;
+	port->afe = afe;
+	port->cfg_type = cfg_type;
+	kref_init(&port->refcount);
+
+	spin_lock_irqsave(&afe->port_list_lock, flags);
+	list_add_tail(&port->node, &afe->port_list);
+	spin_unlock_irqrestore(&afe->port_list_lock, flags);
+
+	return port;
+
+}
+EXPORT_SYMBOL_GPL(q6afe_port_get_from_id);
+
+/**
+ * q6afe_port_put() - Release port reference
+ *
+ * @port: Instance of port to put
+ */
+void q6afe_port_put(struct q6afe_port *port)
+{
+	kref_put(&port->refcount, q6afe_port_free);
+}
+EXPORT_SYMBOL_GPL(q6afe_port_put);
+
+static int q6afe_probe(struct apr_device *adev)
+{
+	struct q6afe *afe;
+	struct device *dev = &adev->dev;
+	struct device_node *dais_np;
+
+	afe = devm_kzalloc(dev, sizeof(*afe), GFP_KERNEL);
+	if (!afe)
+		return -ENOMEM;
+
+	q6core_get_svc_api_info(adev->svc_id, &afe->ainfo);
+	afe->apr = adev;
+	mutex_init(&afe->lock);
+	afe->dev = dev;
+	INIT_LIST_HEAD(&afe->port_list);
+	spin_lock_init(&afe->port_list_lock);
+
+	dev_set_drvdata(dev, afe);
+
+	dais_np = of_get_child_by_name(dev->of_node, "dais");
+	if (dais_np) {
+		afe->pdev_dais = of_platform_device_create(dais_np,
+							   "q6afe-dai", dev);
+		of_node_put(dais_np);
+	}
+
+	return 0;
+}
+
+static int q6afe_remove(struct apr_device *adev)
+{
+	struct q6afe *afe = dev_get_drvdata(&adev->dev);
+
+	if (afe->pdev_dais)
+		of_platform_device_destroy(&afe->pdev_dais->dev, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id q6afe_device_id[]  = {
+	{ .compatible = "qcom,q6afe" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, q6afe_device_id);
+
+static struct apr_driver qcom_q6afe_driver = {
+	.probe = q6afe_probe,
+	.remove = q6afe_remove,
+	.callback = q6afe_callback,
+	.driver = {
+		.name = "qcom-q6afe",
+		.of_match_table = of_match_ptr(q6afe_device_id),
+
+	},
+};
+
+module_apr_driver(qcom_q6afe_driver);
+MODULE_DESCRIPTION("Q6 Audio Front End");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/q6afe.h b/sound/soc/qcom/qdsp6/q6afe.h
new file mode 100644
index 000000000000..c7ed5422baff
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6afe.h
@@ -0,0 +1,211 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __Q6AFE_H__
+#define __Q6AFE_H__
+
+#include <dt-bindings/sound/qcom,q6afe.h>
+
+#define AFE_PORT_MAX		105
+
+#define MSM_AFE_PORT_TYPE_RX 0
+#define MSM_AFE_PORT_TYPE_TX 1
+#define AFE_MAX_PORTS AFE_PORT_MAX
+
+#define Q6AFE_MAX_MI2S_LINES	4
+
+#define AFE_MAX_CHAN_COUNT	8
+#define AFE_PORT_MAX_AUDIO_CHAN_CNT	0x8
+
+#define Q6AFE_LPASS_CLK_SRC_INTERNAL 1
+#define Q6AFE_LPASS_CLK_ROOT_DEFAULT 0
+
+#define LPAIF_DIG_CLK	1
+#define LPAIF_BIT_CLK	2
+#define LPAIF_OSR_CLK	3
+
+/* Clock ID for Primary I2S IBIT */
+#define Q6AFE_LPASS_CLK_ID_PRI_MI2S_IBIT                          0x100
+/* Clock ID for Primary I2S EBIT */
+#define Q6AFE_LPASS_CLK_ID_PRI_MI2S_EBIT                          0x101
+/* Clock ID for Secondary I2S IBIT */
+#define Q6AFE_LPASS_CLK_ID_SEC_MI2S_IBIT                          0x102
+/* Clock ID for Secondary I2S EBIT */
+#define Q6AFE_LPASS_CLK_ID_SEC_MI2S_EBIT                          0x103
+/* Clock ID for Tertiary I2S IBIT */
+#define Q6AFE_LPASS_CLK_ID_TER_MI2S_IBIT                          0x104
+/* Clock ID for Tertiary I2S EBIT */
+#define Q6AFE_LPASS_CLK_ID_TER_MI2S_EBIT                          0x105
+/* Clock ID for Quartnery I2S IBIT */
+#define Q6AFE_LPASS_CLK_ID_QUAD_MI2S_IBIT                         0x106
+/* Clock ID for Quartnery I2S EBIT */
+#define Q6AFE_LPASS_CLK_ID_QUAD_MI2S_EBIT                         0x107
+/* Clock ID for Speaker I2S IBIT */
+#define Q6AFE_LPASS_CLK_ID_SPEAKER_I2S_IBIT                       0x108
+/* Clock ID for Speaker I2S EBIT */
+#define Q6AFE_LPASS_CLK_ID_SPEAKER_I2S_EBIT                       0x109
+/* Clock ID for Speaker I2S OSR */
+#define Q6AFE_LPASS_CLK_ID_SPEAKER_I2S_OSR                        0x10A
+
+/* Clock ID for QUINARY  I2S IBIT */
+#define Q6AFE_LPASS_CLK_ID_QUI_MI2S_IBIT			0x10B
+/* Clock ID for QUINARY  I2S EBIT */
+#define Q6AFE_LPASS_CLK_ID_QUI_MI2S_EBIT			0x10C
+/* Clock ID for SENARY  I2S IBIT */
+#define Q6AFE_LPASS_CLK_ID_SEN_MI2S_IBIT			0x10D
+/* Clock ID for SENARY  I2S EBIT */
+#define Q6AFE_LPASS_CLK_ID_SEN_MI2S_EBIT			0x10E
+/* Clock ID for INT0 I2S IBIT  */
+#define Q6AFE_LPASS_CLK_ID_INT0_MI2S_IBIT                       0x10F
+/* Clock ID for INT1 I2S IBIT  */
+#define Q6AFE_LPASS_CLK_ID_INT1_MI2S_IBIT                       0x110
+/* Clock ID for INT2 I2S IBIT  */
+#define Q6AFE_LPASS_CLK_ID_INT2_MI2S_IBIT                       0x111
+/* Clock ID for INT3 I2S IBIT  */
+#define Q6AFE_LPASS_CLK_ID_INT3_MI2S_IBIT                       0x112
+/* Clock ID for INT4 I2S IBIT  */
+#define Q6AFE_LPASS_CLK_ID_INT4_MI2S_IBIT                       0x113
+/* Clock ID for INT5 I2S IBIT  */
+#define Q6AFE_LPASS_CLK_ID_INT5_MI2S_IBIT                       0x114
+/* Clock ID for INT6 I2S IBIT  */
+#define Q6AFE_LPASS_CLK_ID_INT6_MI2S_IBIT                       0x115
+
+/* Clock ID for QUINARY MI2S OSR CLK  */
+#define Q6AFE_LPASS_CLK_ID_QUI_MI2S_OSR                         0x116
+
+/* Clock ID for Primary PCM IBIT */
+#define Q6AFE_LPASS_CLK_ID_PRI_PCM_IBIT                           0x200
+/* Clock ID for Primary PCM EBIT */
+#define Q6AFE_LPASS_CLK_ID_PRI_PCM_EBIT                           0x201
+/* Clock ID for Secondary PCM IBIT */
+#define Q6AFE_LPASS_CLK_ID_SEC_PCM_IBIT                           0x202
+/* Clock ID for Secondary PCM EBIT */
+#define Q6AFE_LPASS_CLK_ID_SEC_PCM_EBIT                           0x203
+/* Clock ID for Tertiary PCM IBIT */
+#define Q6AFE_LPASS_CLK_ID_TER_PCM_IBIT                           0x204
+/* Clock ID for Tertiary PCM EBIT */
+#define Q6AFE_LPASS_CLK_ID_TER_PCM_EBIT                           0x205
+/* Clock ID for Quartery PCM IBIT */
+#define Q6AFE_LPASS_CLK_ID_QUAD_PCM_IBIT                          0x206
+/* Clock ID for Quartery PCM EBIT */
+#define Q6AFE_LPASS_CLK_ID_QUAD_PCM_EBIT                          0x207
+/* Clock ID for Quinary PCM IBIT */
+#define Q6AFE_LPASS_CLK_ID_QUIN_PCM_IBIT                          0x208
+/* Clock ID for Quinary PCM EBIT */
+#define Q6AFE_LPASS_CLK_ID_QUIN_PCM_EBIT                          0x209
+/* Clock ID for QUINARY PCM OSR  */
+#define Q6AFE_LPASS_CLK_ID_QUI_PCM_OSR                            0x20A
+
+/** Clock ID for Primary TDM IBIT */
+#define Q6AFE_LPASS_CLK_ID_PRI_TDM_IBIT                           0x200
+/** Clock ID for Primary TDM EBIT */
+#define Q6AFE_LPASS_CLK_ID_PRI_TDM_EBIT                           0x201
+/** Clock ID for Secondary TDM IBIT */
+#define Q6AFE_LPASS_CLK_ID_SEC_TDM_IBIT                           0x202
+/** Clock ID for Secondary TDM EBIT */
+#define Q6AFE_LPASS_CLK_ID_SEC_TDM_EBIT                           0x203
+/** Clock ID for Tertiary TDM IBIT */
+#define Q6AFE_LPASS_CLK_ID_TER_TDM_IBIT                           0x204
+/** Clock ID for Tertiary TDM EBIT */
+#define Q6AFE_LPASS_CLK_ID_TER_TDM_EBIT                           0x205
+/** Clock ID for Quartery TDM IBIT */
+#define Q6AFE_LPASS_CLK_ID_QUAD_TDM_IBIT                          0x206
+/** Clock ID for Quartery TDM EBIT */
+#define Q6AFE_LPASS_CLK_ID_QUAD_TDM_EBIT                          0x207
+/** Clock ID for Quinary TDM IBIT */
+#define Q6AFE_LPASS_CLK_ID_QUIN_TDM_IBIT                          0x208
+/** Clock ID for Quinary TDM EBIT */
+#define Q6AFE_LPASS_CLK_ID_QUIN_TDM_EBIT                          0x209
+/** Clock ID for Quinary TDM OSR */
+#define Q6AFE_LPASS_CLK_ID_QUIN_TDM_OSR                           0x20A
+
+/* Clock ID for MCLK1 */
+#define Q6AFE_LPASS_CLK_ID_MCLK_1                                 0x300
+/* Clock ID for MCLK2 */
+#define Q6AFE_LPASS_CLK_ID_MCLK_2                                 0x301
+/* Clock ID for MCLK3 */
+#define Q6AFE_LPASS_CLK_ID_MCLK_3                                 0x302
+/* Clock ID for MCLK4 */
+#define Q6AFE_LPASS_CLK_ID_MCLK_4                                 0x304
+/* Clock ID for Internal Digital Codec Core */
+#define Q6AFE_LPASS_CLK_ID_INTERNAL_DIGITAL_CODEC_CORE            0x303
+/* Clock ID for INT MCLK0 */
+#define Q6AFE_LPASS_CLK_ID_INT_MCLK_0                             0x305
+/* Clock ID for INT MCLK1 */
+#define Q6AFE_LPASS_CLK_ID_INT_MCLK_1                             0x306
+
+/* Clock attribute for invalid use (reserved for internal usage) */
+#define Q6AFE_LPASS_CLK_ATTRIBUTE_INVALID		0x0
+/* Clock attribute for no couple case */
+#define Q6AFE_LPASS_CLK_ATTRIBUTE_COUPLE_NO		0x1
+/* Clock attribute for dividend couple case */
+#define Q6AFE_LPASS_CLK_ATTRIBUTE_COUPLE_DIVIDEND	0x2
+/* Clock attribute for divisor couple case */
+#define Q6AFE_LPASS_CLK_ATTRIBUTE_COUPLE_DIVISOR	0x3
+/* Clock attribute for invert and no couple case */
+#define Q6AFE_LPASS_CLK_ATTRIBUTE_INVERT_COUPLE_NO	0x4
+
+#define Q6AFE_CMAP_INVALID		0xFFFF
+
+struct q6afe_hdmi_cfg {
+	u16                  datatype;
+	u16                  channel_allocation;
+	u32                  sample_rate;
+	u16                  bit_width;
+};
+
+struct q6afe_slim_cfg {
+	u32	sample_rate;
+	u16	bit_width;
+	u16	data_format;
+	u16	num_channels;
+	u8	ch_mapping[AFE_MAX_CHAN_COUNT];
+};
+
+struct q6afe_i2s_cfg {
+	u32	sample_rate;
+	u16	bit_width;
+	u16	data_format;
+	u16	num_channels;
+	u32	sd_line_mask;
+	int fmt;
+};
+
+struct q6afe_tdm_cfg {
+	u16	num_channels;
+	u32	sample_rate;
+	u16	bit_width;
+	u16	data_format;
+	u16	sync_mode;
+	u16	sync_src;
+	u16	nslots_per_frame;
+	u16	slot_width;
+	u16	slot_mask;
+	u32	data_align_type;
+	u16	ch_mapping[AFE_MAX_CHAN_COUNT];
+};
+
+struct q6afe_port_config {
+	struct q6afe_hdmi_cfg hdmi;
+	struct q6afe_slim_cfg slim;
+	struct q6afe_i2s_cfg i2s_cfg;
+	struct q6afe_tdm_cfg tdm;
+};
+
+struct q6afe_port;
+
+struct q6afe_port *q6afe_port_get_from_id(struct device *dev, int id);
+int q6afe_port_start(struct q6afe_port *port);
+int q6afe_port_stop(struct q6afe_port *port);
+void q6afe_port_put(struct q6afe_port *port);
+int q6afe_get_port_id(int index);
+void q6afe_hdmi_port_prepare(struct q6afe_port *port,
+			    struct q6afe_hdmi_cfg *cfg);
+void q6afe_slim_port_prepare(struct q6afe_port *port,
+			  struct q6afe_slim_cfg *cfg);
+int q6afe_i2s_port_prepare(struct q6afe_port *port, struct q6afe_i2s_cfg *cfg);
+void q6afe_tdm_port_prepare(struct q6afe_port *port, struct q6afe_tdm_cfg *cfg);
+
+int q6afe_port_set_sysclk(struct q6afe_port *port, int clk_id,
+			  int clk_src, int clk_root,
+			  unsigned int freq, int dir);
+#endif /* __Q6AFE_H__ */
diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c
new file mode 100644
index 000000000000..349c6a883c63
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6asm-dai.c
@@ -0,0 +1,624 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/component.h>
+#include <sound/soc.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/pcm.h>
+#include <asm/dma.h>
+#include <linux/dma-mapping.h>
+#include <linux/of_device.h>
+#include <sound/pcm_params.h>
+#include "q6asm.h"
+#include "q6routing.h"
+#include "q6dsp-errno.h"
+
+#define DRV_NAME	"q6asm-fe-dai"
+
+#define PLAYBACK_MIN_NUM_PERIODS    2
+#define PLAYBACK_MAX_NUM_PERIODS   8
+#define PLAYBACK_MAX_PERIOD_SIZE    65536
+#define PLAYBACK_MIN_PERIOD_SIZE    128
+#define CAPTURE_MIN_NUM_PERIODS     2
+#define CAPTURE_MAX_NUM_PERIODS     8
+#define CAPTURE_MAX_PERIOD_SIZE     4096
+#define CAPTURE_MIN_PERIOD_SIZE     320
+#define SID_MASK_DEFAULT	0xF
+
+enum stream_state {
+	Q6ASM_STREAM_IDLE = 0,
+	Q6ASM_STREAM_STOPPED,
+	Q6ASM_STREAM_RUNNING,
+};
+
+struct q6asm_dai_rtd {
+	struct snd_pcm_substream *substream;
+	phys_addr_t phys;
+	unsigned int pcm_size;
+	unsigned int pcm_count;
+	unsigned int pcm_irq_pos;       /* IRQ position */
+	unsigned int periods;
+	uint16_t bits_per_sample;
+	uint16_t source; /* Encoding source bit mask */
+	struct audio_client *audio_client;
+	uint16_t session_id;
+	enum stream_state state;
+};
+
+struct q6asm_dai_data {
+	long long int sid;
+};
+
+static struct snd_pcm_hardware q6asm_dai_hardware_capture = {
+	.info =                 (SNDRV_PCM_INFO_MMAP |
+				SNDRV_PCM_INFO_BLOCK_TRANSFER |
+				SNDRV_PCM_INFO_MMAP_VALID |
+				SNDRV_PCM_INFO_INTERLEAVED |
+				SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME),
+	.formats =              (SNDRV_PCM_FMTBIT_S16_LE |
+				SNDRV_PCM_FMTBIT_S24_LE),
+	.rates =                SNDRV_PCM_RATE_8000_48000,
+	.rate_min =             8000,
+	.rate_max =             48000,
+	.channels_min =         1,
+	.channels_max =         4,
+	.buffer_bytes_max =     CAPTURE_MAX_NUM_PERIODS *
+				CAPTURE_MAX_PERIOD_SIZE,
+	.period_bytes_min =	CAPTURE_MIN_PERIOD_SIZE,
+	.period_bytes_max =     CAPTURE_MAX_PERIOD_SIZE,
+	.periods_min =          CAPTURE_MIN_NUM_PERIODS,
+	.periods_max =          CAPTURE_MAX_NUM_PERIODS,
+	.fifo_size =            0,
+};
+
+static struct snd_pcm_hardware q6asm_dai_hardware_playback = {
+	.info =                 (SNDRV_PCM_INFO_MMAP |
+				SNDRV_PCM_INFO_BLOCK_TRANSFER |
+				SNDRV_PCM_INFO_MMAP_VALID |
+				SNDRV_PCM_INFO_INTERLEAVED |
+				SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME),
+	.formats =              (SNDRV_PCM_FMTBIT_S16_LE |
+				SNDRV_PCM_FMTBIT_S24_LE),
+	.rates =                SNDRV_PCM_RATE_8000_192000,
+	.rate_min =             8000,
+	.rate_max =             192000,
+	.channels_min =         1,
+	.channels_max =         8,
+	.buffer_bytes_max =     (PLAYBACK_MAX_NUM_PERIODS *
+				PLAYBACK_MAX_PERIOD_SIZE),
+	.period_bytes_min =	PLAYBACK_MIN_PERIOD_SIZE,
+	.period_bytes_max =     PLAYBACK_MAX_PERIOD_SIZE,
+	.periods_min =          PLAYBACK_MIN_NUM_PERIODS,
+	.periods_max =          PLAYBACK_MAX_NUM_PERIODS,
+	.fifo_size =            0,
+};
+
+#define Q6ASM_FEDAI_DRIVER(num) { \
+		.playback = {						\
+			.stream_name = "MultiMedia"#num" Playback",	\
+			.rates = (SNDRV_PCM_RATE_8000_192000|		\
+					SNDRV_PCM_RATE_KNOT),		\
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE |		\
+					SNDRV_PCM_FMTBIT_S24_LE),	\
+			.channels_min = 1,				\
+			.channels_max = 8,				\
+			.rate_min =     8000,				\
+			.rate_max =	192000,				\
+		},							\
+		.capture = {						\
+			.stream_name = "MultiMedia"#num" Capture",	\
+			.rates = (SNDRV_PCM_RATE_8000_48000|		\
+					SNDRV_PCM_RATE_KNOT),		\
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE |		\
+				    SNDRV_PCM_FMTBIT_S24_LE),		\
+			.channels_min = 1,				\
+			.channels_max = 4,				\
+			.rate_min =     8000,				\
+			.rate_max =	48000,				\
+		},							\
+		.name = "MultiMedia"#num,				\
+		.probe = fe_dai_probe,					\
+		.id = MSM_FRONTEND_DAI_MULTIMEDIA##num,			\
+	}
+
+/* Conventional and unconventional sample rate supported */
+static unsigned int supported_sample_rates[] = {
+	8000, 11025, 12000, 16000, 22050, 24000, 32000, 44100, 48000,
+	88200, 96000, 176400, 192000
+};
+
+static struct snd_pcm_hw_constraint_list constraints_sample_rates = {
+	.count = ARRAY_SIZE(supported_sample_rates),
+	.list = supported_sample_rates,
+	.mask = 0,
+};
+
+static void event_handler(uint32_t opcode, uint32_t token,
+			  uint32_t *payload, void *priv)
+{
+	struct q6asm_dai_rtd *prtd = priv;
+	struct snd_pcm_substream *substream = prtd->substream;
+
+	switch (opcode) {
+	case ASM_CLIENT_EVENT_CMD_RUN_DONE:
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+			q6asm_write_async(prtd->audio_client,
+				   prtd->pcm_count, 0, 0, NO_TIMESTAMP);
+		break;
+	case ASM_CLIENT_EVENT_CMD_EOS_DONE:
+		prtd->state = Q6ASM_STREAM_STOPPED;
+		break;
+	case ASM_CLIENT_EVENT_DATA_WRITE_DONE: {
+		prtd->pcm_irq_pos += prtd->pcm_count;
+		snd_pcm_period_elapsed(substream);
+		if (prtd->state == Q6ASM_STREAM_RUNNING)
+			q6asm_write_async(prtd->audio_client,
+					   prtd->pcm_count, 0, 0, NO_TIMESTAMP);
+
+		break;
+		}
+	case ASM_CLIENT_EVENT_DATA_READ_DONE:
+		prtd->pcm_irq_pos += prtd->pcm_count;
+		snd_pcm_period_elapsed(substream);
+		if (prtd->state == Q6ASM_STREAM_RUNNING)
+			q6asm_read(prtd->audio_client);
+
+		break;
+	default:
+		break;
+	}
+}
+
+static int q6asm_dai_prepare(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_soc_pcm_runtime *soc_prtd = substream->private_data;
+	struct q6asm_dai_rtd *prtd = runtime->private_data;
+	struct snd_soc_component *c = snd_soc_rtdcom_lookup(soc_prtd, DRV_NAME);
+	struct q6asm_dai_data *pdata;
+	int ret, i;
+
+	pdata = snd_soc_component_get_drvdata(c);
+	if (!pdata)
+		return -EINVAL;
+
+	if (!prtd || !prtd->audio_client) {
+		pr_err("%s: private data null or audio client freed\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	prtd->pcm_count = snd_pcm_lib_period_bytes(substream);
+	prtd->pcm_irq_pos = 0;
+	/* rate and channels are sent to audio driver */
+	if (prtd->state) {
+		/* clear the previous setup if any  */
+		q6asm_cmd(prtd->audio_client, CMD_CLOSE);
+		q6asm_unmap_memory_regions(substream->stream,
+					   prtd->audio_client);
+		q6routing_stream_close(soc_prtd->dai_link->id,
+					 substream->stream);
+	}
+
+	ret = q6asm_map_memory_regions(substream->stream, prtd->audio_client,
+				       prtd->phys,
+				       (prtd->pcm_size / prtd->periods),
+				       prtd->periods);
+
+	if (ret < 0) {
+		pr_err("Audio Start: Buffer Allocation failed rc = %d\n",
+							ret);
+		return -ENOMEM;
+	}
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		ret = q6asm_open_write(prtd->audio_client, FORMAT_LINEAR_PCM,
+				       prtd->bits_per_sample);
+	} else if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+		ret = q6asm_open_read(prtd->audio_client, FORMAT_LINEAR_PCM,
+				       prtd->bits_per_sample);
+	}
+
+	if (ret < 0) {
+		pr_err("%s: q6asm_open_write failed\n", __func__);
+		q6asm_audio_client_free(prtd->audio_client);
+		prtd->audio_client = NULL;
+		return -ENOMEM;
+	}
+
+	prtd->session_id = q6asm_get_session_id(prtd->audio_client);
+	ret = q6routing_stream_open(soc_prtd->dai_link->id, LEGACY_PCM_MODE,
+			      prtd->session_id, substream->stream);
+	if (ret) {
+		pr_err("%s: stream reg failed ret:%d\n", __func__, ret);
+		return ret;
+	}
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		ret = q6asm_media_format_block_multi_ch_pcm(
+				prtd->audio_client, runtime->rate,
+				runtime->channels, NULL,
+				prtd->bits_per_sample);
+	} else if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+		ret = q6asm_enc_cfg_blk_pcm_format_support(prtd->audio_client,
+					runtime->rate, runtime->channels,
+					prtd->bits_per_sample);
+
+		/* Queue the buffers */
+		for (i = 0; i < runtime->periods; i++)
+			q6asm_read(prtd->audio_client);
+
+	}
+	if (ret < 0)
+		pr_info("%s: CMD Format block failed\n", __func__);
+
+	prtd->state = Q6ASM_STREAM_RUNNING;
+
+	return 0;
+}
+
+static int q6asm_dai_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	int ret = 0;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct q6asm_dai_rtd *prtd = runtime->private_data;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		ret = q6asm_run_nowait(prtd->audio_client, 0, 0, 0);
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+		prtd->state = Q6ASM_STREAM_STOPPED;
+		ret = q6asm_cmd_nowait(prtd->audio_client, CMD_EOS);
+		break;
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		ret = q6asm_cmd_nowait(prtd->audio_client, CMD_PAUSE);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int q6asm_dai_open(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_soc_pcm_runtime *soc_prtd = substream->private_data;
+	struct snd_soc_dai *cpu_dai = soc_prtd->cpu_dai;
+	struct snd_soc_component *c = snd_soc_rtdcom_lookup(soc_prtd, DRV_NAME);
+	struct q6asm_dai_rtd *prtd;
+	struct q6asm_dai_data *pdata;
+	struct device *dev = c->dev;
+	int ret = 0;
+	int stream_id;
+
+	stream_id = cpu_dai->driver->id;
+
+	pdata = snd_soc_component_get_drvdata(c);
+	if (!pdata) {
+		pr_err("Drv data not found ..\n");
+		return -EINVAL;
+	}
+
+	prtd = kzalloc(sizeof(struct q6asm_dai_rtd), GFP_KERNEL);
+	if (prtd == NULL)
+		return -ENOMEM;
+
+	prtd->substream = substream;
+	prtd->audio_client = q6asm_audio_client_alloc(dev,
+				(q6asm_cb)event_handler, prtd, stream_id,
+				LEGACY_PCM_MODE);
+	if (!prtd->audio_client) {
+		pr_info("%s: Could not allocate memory\n", __func__);
+		kfree(prtd);
+		return -ENOMEM;
+	}
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		runtime->hw = q6asm_dai_hardware_playback;
+	else if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+		runtime->hw = q6asm_dai_hardware_capture;
+
+	ret = snd_pcm_hw_constraint_list(runtime, 0,
+				SNDRV_PCM_HW_PARAM_RATE,
+				&constraints_sample_rates);
+	if (ret < 0)
+		pr_info("snd_pcm_hw_constraint_list failed\n");
+	/* Ensure that buffer size is a multiple of period size */
+	ret = snd_pcm_hw_constraint_integer(runtime,
+					    SNDRV_PCM_HW_PARAM_PERIODS);
+	if (ret < 0)
+		pr_info("snd_pcm_hw_constraint_integer failed\n");
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		ret = snd_pcm_hw_constraint_minmax(runtime,
+			SNDRV_PCM_HW_PARAM_BUFFER_BYTES,
+			PLAYBACK_MIN_NUM_PERIODS * PLAYBACK_MIN_PERIOD_SIZE,
+			PLAYBACK_MAX_NUM_PERIODS * PLAYBACK_MAX_PERIOD_SIZE);
+		if (ret < 0) {
+			pr_err("constraint for buffer bytes min max ret = %d\n",
+									ret);
+		}
+	}
+
+	ret = snd_pcm_hw_constraint_step(runtime, 0,
+		SNDRV_PCM_HW_PARAM_PERIOD_BYTES, 32);
+	if (ret < 0) {
+		pr_err("constraint for period bytes step ret = %d\n",
+								ret);
+	}
+	ret = snd_pcm_hw_constraint_step(runtime, 0,
+		SNDRV_PCM_HW_PARAM_BUFFER_BYTES, 32);
+	if (ret < 0) {
+		pr_err("constraint for buffer bytes step ret = %d\n",
+								ret);
+	}
+
+	runtime->private_data = prtd;
+
+	snd_soc_set_runtime_hwparams(substream, &q6asm_dai_hardware_playback);
+
+	runtime->dma_bytes = q6asm_dai_hardware_playback.buffer_bytes_max;
+
+
+	if (pdata->sid < 0)
+		prtd->phys = substream->dma_buffer.addr;
+	else
+		prtd->phys = substream->dma_buffer.addr | (pdata->sid << 32);
+
+	snd_pcm_set_runtime_buffer(substream, &substream->dma_buffer);
+
+	return 0;
+}
+
+static int q6asm_dai_close(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_soc_pcm_runtime *soc_prtd = substream->private_data;
+	struct q6asm_dai_rtd *prtd = runtime->private_data;
+
+	if (prtd->audio_client) {
+		q6asm_cmd(prtd->audio_client, CMD_CLOSE);
+		q6asm_unmap_memory_regions(substream->stream,
+					   prtd->audio_client);
+		q6asm_audio_client_free(prtd->audio_client);
+		prtd->audio_client = NULL;
+	}
+	q6routing_stream_close(soc_prtd->dai_link->id,
+						substream->stream);
+	kfree(prtd);
+	return 0;
+}
+
+static snd_pcm_uframes_t q6asm_dai_pointer(struct snd_pcm_substream *substream)
+{
+
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct q6asm_dai_rtd *prtd = runtime->private_data;
+
+	if (prtd->pcm_irq_pos >= prtd->pcm_size)
+		prtd->pcm_irq_pos = 0;
+
+	return bytes_to_frames(runtime, (prtd->pcm_irq_pos));
+}
+
+static int q6asm_dai_mmap(struct snd_pcm_substream *substream,
+				struct vm_area_struct *vma)
+{
+
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_soc_pcm_runtime *soc_prtd = substream->private_data;
+	struct snd_soc_component *c = snd_soc_rtdcom_lookup(soc_prtd, DRV_NAME);
+	struct device *dev = c->dev;
+
+	return dma_mmap_coherent(dev, vma,
+			runtime->dma_area, runtime->dma_addr,
+			runtime->dma_bytes);
+}
+
+static int q6asm_dai_hw_params(struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *params)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct q6asm_dai_rtd *prtd = runtime->private_data;
+
+	prtd->pcm_size = params_buffer_bytes(params);
+	prtd->periods = params_periods(params);
+
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		prtd->bits_per_sample = 16;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		prtd->bits_per_sample = 24;
+		break;
+	}
+
+	return 0;
+}
+
+static struct snd_pcm_ops q6asm_dai_ops = {
+	.open           = q6asm_dai_open,
+	.hw_params	= q6asm_dai_hw_params,
+	.close          = q6asm_dai_close,
+	.ioctl          = snd_pcm_lib_ioctl,
+	.prepare        = q6asm_dai_prepare,
+	.trigger        = q6asm_dai_trigger,
+	.pointer        = q6asm_dai_pointer,
+	.mmap		= q6asm_dai_mmap,
+};
+
+static int q6asm_dai_pcm_new(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_pcm_substream *psubstream, *csubstream;
+	struct snd_soc_component *c = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
+	struct snd_pcm *pcm = rtd->pcm;
+	struct device *dev;
+	int size, ret;
+
+	dev = c->dev;
+	size = q6asm_dai_hardware_playback.buffer_bytes_max;
+	psubstream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
+	if (psubstream) {
+		ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, dev, size,
+					  &psubstream->dma_buffer);
+		if (ret) {
+			dev_err(dev, "Cannot allocate buffer(s)\n");
+			return ret;
+		}
+	}
+
+	csubstream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
+	if (csubstream) {
+		ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, dev, size,
+					  &csubstream->dma_buffer);
+		if (ret) {
+			dev_err(dev, "Cannot allocate buffer(s)\n");
+			if (psubstream)
+				snd_dma_free_pages(&psubstream->dma_buffer);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+static void q6asm_dai_pcm_free(struct snd_pcm *pcm)
+{
+	struct snd_pcm_substream *substream;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(pcm->streams); i++) {
+		substream = pcm->streams[i].substream;
+		if (substream) {
+			snd_dma_free_pages(&substream->dma_buffer);
+			substream->dma_buffer.area = NULL;
+			substream->dma_buffer.addr = 0;
+		}
+	}
+}
+
+static const struct snd_soc_dapm_route afe_pcm_routes[] = {
+	{"MM_DL1",  NULL, "MultiMedia1 Playback" },
+	{"MM_DL2",  NULL, "MultiMedia2 Playback" },
+	{"MM_DL3",  NULL, "MultiMedia3 Playback" },
+	{"MM_DL4",  NULL, "MultiMedia4 Playback" },
+	{"MM_DL5",  NULL, "MultiMedia5 Playback" },
+	{"MM_DL6",  NULL, "MultiMedia6 Playback" },
+	{"MM_DL7",  NULL, "MultiMedia7 Playback" },
+	{"MM_DL7",  NULL, "MultiMedia8 Playback" },
+	{"MultiMedia1 Capture", NULL, "MM_UL1"},
+	{"MultiMedia2 Capture", NULL, "MM_UL2"},
+	{"MultiMedia3 Capture", NULL, "MM_UL3"},
+	{"MultiMedia4 Capture", NULL, "MM_UL4"},
+	{"MultiMedia5 Capture", NULL, "MM_UL5"},
+	{"MultiMedia6 Capture", NULL, "MM_UL6"},
+	{"MultiMedia7 Capture", NULL, "MM_UL7"},
+	{"MultiMedia8 Capture", NULL, "MM_UL8"},
+
+};
+
+static int fe_dai_probe(struct snd_soc_dai *dai)
+{
+	struct snd_soc_dapm_context *dapm;
+
+	dapm = snd_soc_component_get_dapm(dai->component);
+	snd_soc_dapm_add_routes(dapm, afe_pcm_routes,
+				ARRAY_SIZE(afe_pcm_routes));
+
+	return 0;
+}
+
+
+static const struct snd_soc_component_driver q6asm_fe_dai_component = {
+	.name		= DRV_NAME,
+	.ops		= &q6asm_dai_ops,
+	.pcm_new	= q6asm_dai_pcm_new,
+	.pcm_free	= q6asm_dai_pcm_free,
+
+};
+
+static struct snd_soc_dai_driver q6asm_fe_dais[] = {
+	Q6ASM_FEDAI_DRIVER(1),
+	Q6ASM_FEDAI_DRIVER(2),
+	Q6ASM_FEDAI_DRIVER(3),
+	Q6ASM_FEDAI_DRIVER(4),
+	Q6ASM_FEDAI_DRIVER(5),
+	Q6ASM_FEDAI_DRIVER(6),
+	Q6ASM_FEDAI_DRIVER(7),
+	Q6ASM_FEDAI_DRIVER(8),
+};
+
+static int q6asm_dai_bind(struct device *dev, struct device *master, void *data)
+{
+	struct device_node *node = dev->of_node;
+	struct of_phandle_args args;
+	struct q6asm_dai_data *pdata;
+	int rc;
+
+	pdata = kzalloc(sizeof(struct q6asm_dai_data), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	rc = of_parse_phandle_with_fixed_args(node, "iommus", 1, 0, &args);
+	if (rc < 0)
+		pdata->sid = -1;
+	else
+		pdata->sid = args.args[0] & SID_MASK_DEFAULT;
+
+	dev_set_drvdata(dev, pdata);
+
+	return snd_soc_register_component(dev, &q6asm_fe_dai_component,
+					q6asm_fe_dais,
+					ARRAY_SIZE(q6asm_fe_dais));
+}
+static void q6asm_dai_unbind(struct device *dev, struct device *master,
+			     void *data)
+{
+	struct q6asm_dai_data *pdata = dev_get_drvdata(dev);
+
+	snd_soc_unregister_component(dev);
+
+	kfree(pdata);
+
+}
+
+static const struct component_ops q6asm_dai_comp_ops = {
+	.bind   = q6asm_dai_bind,
+	.unbind = q6asm_dai_unbind,
+};
+
+static int q6asm_dai_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &q6asm_dai_comp_ops);
+}
+
+static int q6asm_dai_dev_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &q6asm_dai_comp_ops);
+	return 0;
+}
+
+static struct platform_driver q6asm_dai_platform_driver = {
+	.driver = {
+		.name = "q6asm-dai",
+	},
+	.probe = q6asm_dai_probe,
+	.remove = q6asm_dai_dev_remove,
+};
+module_platform_driver(q6asm_dai_platform_driver);
+
+MODULE_DESCRIPTION("Q6ASM dai driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/q6asm.c b/sound/soc/qcom/qdsp6/q6asm.c
new file mode 100644
index 000000000000..530852385cad
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6asm.c
@@ -0,0 +1,1399 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/mutex.h>
+#include <linux/wait.h>
+#include <linux/module.h>
+#include <linux/soc/qcom/apr.h>
+#include <linux/device.h>
+#include <linux/of_platform.h>
+#include <linux/spinlock.h>
+#include <linux/kref.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <uapi/sound/asound.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include "q6asm.h"
+#include "q6core.h"
+#include "q6dsp-errno.h"
+#include "q6dsp-common.h"
+
+#define ASM_STREAM_CMD_CLOSE			0x00010BCD
+#define ASM_STREAM_CMD_FLUSH			0x00010BCE
+#define ASM_SESSION_CMD_PAUSE			0x00010BD3
+#define ASM_DATA_CMD_EOS			0x00010BDB
+#define ASM_NULL_POPP_TOPOLOGY			0x00010C68
+#define ASM_STREAM_CMD_FLUSH_READBUFS		0x00010C09
+#define ASM_STREAM_CMD_SET_ENCDEC_PARAM		0x00010C10
+#define ASM_STREAM_POSTPROC_TOPO_ID_NONE	0x00010C68
+#define ASM_CMD_SHARED_MEM_MAP_REGIONS		0x00010D92
+#define ASM_CMDRSP_SHARED_MEM_MAP_REGIONS	0x00010D93
+#define ASM_CMD_SHARED_MEM_UNMAP_REGIONS	0x00010D94
+#define ASM_DATA_CMD_MEDIA_FMT_UPDATE_V2	0x00010D98
+#define ASM_DATA_EVENT_WRITE_DONE_V2		0x00010D99
+#define ASM_PARAM_ID_ENCDEC_ENC_CFG_BLK_V2	0x00010DA3
+#define ASM_SESSION_CMD_RUN_V2			0x00010DAA
+#define ASM_MEDIA_FMT_MULTI_CHANNEL_PCM_V2	0x00010DA5
+#define ASM_DATA_CMD_WRITE_V2			0x00010DAB
+#define ASM_DATA_CMD_READ_V2			0x00010DAC
+#define ASM_SESSION_CMD_SUSPEND			0x00010DEC
+#define ASM_STREAM_CMD_OPEN_WRITE_V3		0x00010DB3
+#define ASM_STREAM_CMD_OPEN_READ_V3                 0x00010DB4
+#define ASM_DATA_EVENT_READ_DONE_V2 0x00010D9A
+#define ASM_STREAM_CMD_OPEN_READWRITE_V2        0x00010D8D
+
+
+#define ASM_LEGACY_STREAM_SESSION	0
+/* Bit shift for the stream_perf_mode subfield. */
+#define ASM_SHIFT_STREAM_PERF_MODE_FLAG_IN_OPEN_READ              29
+#define ASM_END_POINT_DEVICE_MATRIX	0
+#define ASM_DEFAULT_APP_TYPE		0
+#define ASM_SYNC_IO_MODE		0x0001
+#define ASM_ASYNC_IO_MODE		0x0002
+#define ASM_TUN_READ_IO_MODE		0x0004	/* tunnel read write mode */
+#define ASM_TUN_WRITE_IO_MODE		0x0008	/* tunnel read write mode */
+#define ASM_SHIFT_GAPLESS_MODE_FLAG	31
+#define ADSP_MEMORY_MAP_SHMEM8_4K_POOL	3
+
+struct avs_cmd_shared_mem_map_regions {
+	u16 mem_pool_id;
+	u16 num_regions;
+	u32 property_flag;
+} __packed;
+
+struct avs_shared_map_region_payload {
+	u32 shm_addr_lsw;
+	u32 shm_addr_msw;
+	u32 mem_size_bytes;
+} __packed;
+
+struct avs_cmd_shared_mem_unmap_regions {
+	u32 mem_map_handle;
+} __packed;
+
+struct asm_data_cmd_media_fmt_update_v2 {
+	u32 fmt_blk_size;
+} __packed;
+
+struct asm_multi_channel_pcm_fmt_blk_v2 {
+	struct asm_data_cmd_media_fmt_update_v2 fmt_blk;
+	u16 num_channels;
+	u16 bits_per_sample;
+	u32 sample_rate;
+	u16 is_signed;
+	u16 reserved;
+	u8 channel_mapping[PCM_MAX_NUM_CHANNEL];
+} __packed;
+
+struct asm_stream_cmd_set_encdec_param {
+	u32                  param_id;
+	u32                  param_size;
+} __packed;
+
+struct asm_enc_cfg_blk_param_v2 {
+	u32                  frames_per_buf;
+	u32                  enc_cfg_blk_size;
+} __packed;
+
+struct asm_multi_channel_pcm_enc_cfg_v2 {
+	struct asm_stream_cmd_set_encdec_param  encdec;
+	struct asm_enc_cfg_blk_param_v2	encblk;
+	uint16_t  num_channels;
+	uint16_t  bits_per_sample;
+	uint32_t  sample_rate;
+	uint16_t  is_signed;
+	uint16_t  reserved;
+	uint8_t   channel_mapping[8];
+} __packed;
+
+struct asm_data_cmd_read_v2 {
+	u32                  buf_addr_lsw;
+	u32                  buf_addr_msw;
+	u32                  mem_map_handle;
+	u32                  buf_size;
+	u32                  seq_id;
+} __packed;
+
+struct asm_data_cmd_read_v2_done {
+	u32	status;
+	u32	buf_addr_lsw;
+	u32	buf_addr_msw;
+};
+
+struct asm_stream_cmd_open_read_v3 {
+	u32                    mode_flags;
+	u32                    src_endpointype;
+	u32                    preprocopo_id;
+	u32                    enc_cfg_id;
+	u16                    bits_per_sample;
+	u16                    reserved;
+} __packed;
+
+struct asm_data_cmd_write_v2 {
+	u32 buf_addr_lsw;
+	u32 buf_addr_msw;
+	u32 mem_map_handle;
+	u32 buf_size;
+	u32 seq_id;
+	u32 timestamp_lsw;
+	u32 timestamp_msw;
+	u32 flags;
+} __packed;
+
+struct asm_stream_cmd_open_write_v3 {
+	uint32_t mode_flags;
+	uint16_t sink_endpointype;
+	uint16_t bits_per_sample;
+	uint32_t postprocopo_id;
+	uint32_t dec_fmt_id;
+} __packed;
+
+struct asm_session_cmd_run_v2 {
+	u32 flags;
+	u32 time_lsw;
+	u32 time_msw;
+} __packed;
+
+struct audio_buffer {
+	phys_addr_t phys;
+	uint32_t size;		/* size of buffer */
+};
+
+struct audio_port_data {
+	struct audio_buffer *buf;
+	uint32_t num_periods;
+	uint32_t dsp_buf;
+	uint32_t mem_map_handle;
+};
+
+struct q6asm {
+	struct apr_device *adev;
+	struct device *dev;
+	struct q6core_svc_api_info ainfo;
+	wait_queue_head_t mem_wait;
+	struct platform_device *pcmdev;
+	spinlock_t slock;
+	struct audio_client *session[MAX_SESSIONS + 1];
+	struct platform_device *pdev_dais;
+};
+
+struct audio_client {
+	int session;
+	q6asm_cb cb;
+	void *priv;
+	uint32_t io_mode;
+	struct apr_device *adev;
+	struct mutex cmd_lock;
+	spinlock_t lock;
+	struct kref refcount;
+	/* idx:1 out port, 0: in port */
+	struct audio_port_data port[2];
+	wait_queue_head_t cmd_wait;
+	struct aprv2_ibasic_rsp_result_t result;
+	int perf_mode;
+	int stream_id;
+	struct q6asm *q6asm;
+	struct device *dev;
+};
+
+static inline void q6asm_add_hdr(struct audio_client *ac, struct apr_hdr *hdr,
+				 uint32_t pkt_size, bool cmd_flg,
+				 uint32_t stream_id)
+{
+	hdr->hdr_field = APR_SEQ_CMD_HDR_FIELD;
+	hdr->src_port = ((ac->session << 8) & 0xFF00) | (stream_id);
+	hdr->dest_port = ((ac->session << 8) & 0xFF00) | (stream_id);
+	hdr->pkt_size = pkt_size;
+	if (cmd_flg)
+		hdr->token = ac->session;
+}
+
+static int q6asm_apr_send_session_pkt(struct q6asm *a, struct audio_client *ac,
+				      struct apr_pkt *pkt, uint32_t rsp_opcode)
+{
+	struct apr_hdr *hdr = &pkt->hdr;
+	int rc;
+
+	mutex_lock(&ac->cmd_lock);
+	ac->result.opcode = 0;
+	ac->result.status = 0;
+	rc = apr_send_pkt(a->adev, pkt);
+	if (rc < 0)
+		goto err;
+
+	if (rsp_opcode)
+		rc = wait_event_timeout(a->mem_wait,
+					(ac->result.opcode == hdr->opcode) ||
+					(ac->result.opcode == rsp_opcode),
+					5 * HZ);
+	else
+		rc = wait_event_timeout(a->mem_wait,
+					(ac->result.opcode == hdr->opcode),
+					5 * HZ);
+
+	if (!rc) {
+		dev_err(a->dev, "CMD timeout\n");
+		rc = -ETIMEDOUT;
+	} else if (ac->result.status > 0) {
+		dev_err(a->dev, "DSP returned error[%x]\n",
+			ac->result.status);
+		rc = -EINVAL;
+	}
+
+err:
+	mutex_unlock(&ac->cmd_lock);
+	return rc;
+}
+
+static int __q6asm_memory_unmap(struct audio_client *ac,
+				phys_addr_t buf_add, int dir)
+{
+	struct avs_cmd_shared_mem_unmap_regions *mem_unmap;
+	struct q6asm *a = dev_get_drvdata(ac->dev->parent);
+	struct apr_pkt *pkt;
+	int rc, pkt_size;
+	void *p;
+
+	if (ac->port[dir].mem_map_handle == 0) {
+		dev_err(ac->dev, "invalid mem handle\n");
+		return -EINVAL;
+	}
+
+	pkt_size = APR_HDR_SIZE + sizeof(*mem_unmap);
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	mem_unmap = p + APR_HDR_SIZE;
+
+	pkt->hdr.hdr_field = APR_SEQ_CMD_HDR_FIELD;
+	pkt->hdr.src_port = 0;
+	pkt->hdr.dest_port = 0;
+	pkt->hdr.pkt_size = pkt_size;
+	pkt->hdr.token = ((ac->session << 8) | dir);
+
+	pkt->hdr.opcode = ASM_CMD_SHARED_MEM_UNMAP_REGIONS;
+	mem_unmap->mem_map_handle = ac->port[dir].mem_map_handle;
+
+	rc = q6asm_apr_send_session_pkt(a, ac, pkt, 0);
+	if (rc < 0) {
+		kfree(pkt);
+		return rc;
+	}
+
+	ac->port[dir].mem_map_handle = 0;
+
+	kfree(pkt);
+	return 0;
+}
+
+
+static void q6asm_audio_client_free_buf(struct audio_client *ac,
+					struct audio_port_data *port)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ac->lock, flags);
+	port->num_periods = 0;
+	kfree(port->buf);
+	port->buf = NULL;
+	spin_unlock_irqrestore(&ac->lock, flags);
+}
+
+/**
+ * q6asm_unmap_memory_regions() - unmap memory regions in the dsp.
+ *
+ * @dir: direction of audio stream
+ * @ac: audio client instanace
+ *
+ * Return: Will be an negative value on failure or zero on success
+ */
+int q6asm_unmap_memory_regions(unsigned int dir, struct audio_client *ac)
+{
+	struct audio_port_data *port;
+	int cnt = 0;
+	int rc = 0;
+
+	port = &ac->port[dir];
+	if (!port->buf) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	cnt = port->num_periods - 1;
+	if (cnt >= 0) {
+		rc = __q6asm_memory_unmap(ac, port->buf[dir].phys, dir);
+		if (rc < 0) {
+			dev_err(ac->dev, "%s: Memory_unmap_regions failed %d\n",
+				__func__, rc);
+			goto err;
+		}
+	}
+
+	q6asm_audio_client_free_buf(ac, port);
+
+err:
+	return rc;
+}
+EXPORT_SYMBOL_GPL(q6asm_unmap_memory_regions);
+
+static int __q6asm_memory_map_regions(struct audio_client *ac, int dir,
+				      size_t period_sz, unsigned int periods,
+				      bool is_contiguous)
+{
+	struct avs_cmd_shared_mem_map_regions *cmd = NULL;
+	struct avs_shared_map_region_payload *mregions = NULL;
+	struct q6asm *a = dev_get_drvdata(ac->dev->parent);
+	struct audio_port_data *port = NULL;
+	struct audio_buffer *ab = NULL;
+	struct apr_pkt *pkt;
+	void *p;
+	unsigned long flags;
+	uint32_t num_regions, buf_sz;
+	int rc, i, pkt_size;
+
+	if (is_contiguous) {
+		num_regions = 1;
+		buf_sz = period_sz * periods;
+	} else {
+		buf_sz = period_sz;
+		num_regions = periods;
+	}
+
+	/* DSP expects size should be aligned to 4K */
+	buf_sz = ALIGN(buf_sz, 4096);
+
+	pkt_size = APR_HDR_SIZE + sizeof(*cmd) +
+		   (sizeof(*mregions) * num_regions);
+
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	cmd = p + APR_HDR_SIZE;
+	mregions = p + APR_HDR_SIZE +  sizeof(*cmd);
+
+	pkt->hdr.hdr_field = APR_SEQ_CMD_HDR_FIELD;
+	pkt->hdr.src_port = 0;
+	pkt->hdr.dest_port = 0;
+	pkt->hdr.pkt_size = pkt_size;
+	pkt->hdr.token = ((ac->session << 8) | dir);
+	pkt->hdr.opcode = ASM_CMD_SHARED_MEM_MAP_REGIONS;
+
+	cmd->mem_pool_id = ADSP_MEMORY_MAP_SHMEM8_4K_POOL;
+	cmd->num_regions = num_regions;
+	cmd->property_flag = 0x00;
+
+	spin_lock_irqsave(&ac->lock, flags);
+	port = &ac->port[dir];
+
+	for (i = 0; i < num_regions; i++) {
+		ab = &port->buf[i];
+		mregions->shm_addr_lsw = lower_32_bits(ab->phys);
+		mregions->shm_addr_msw = upper_32_bits(ab->phys);
+		mregions->mem_size_bytes = buf_sz;
+		++mregions;
+	}
+	spin_unlock_irqrestore(&ac->lock, flags);
+
+	rc = q6asm_apr_send_session_pkt(a, ac, pkt,
+					ASM_CMDRSP_SHARED_MEM_MAP_REGIONS);
+
+	kfree(pkt);
+
+	return rc;
+}
+
+/**
+ * q6asm_map_memory_regions() - map memory regions in the dsp.
+ *
+ * @dir: direction of audio stream
+ * @ac: audio client instanace
+ * @phys: physcial address that needs mapping.
+ * @period_sz: audio period size
+ * @periods: number of periods
+ *
+ * Return: Will be an negative value on failure or zero on success
+ */
+int q6asm_map_memory_regions(unsigned int dir, struct audio_client *ac,
+			     phys_addr_t phys,
+			     size_t period_sz, unsigned int periods)
+{
+	struct audio_buffer *buf;
+	unsigned long flags;
+	int cnt;
+	int rc;
+
+	spin_lock_irqsave(&ac->lock, flags);
+	if (ac->port[dir].buf) {
+		dev_err(ac->dev, "Buffer already allocated\n");
+		spin_unlock_irqrestore(&ac->lock, flags);
+		return 0;
+	}
+
+	buf = kzalloc(((sizeof(struct audio_buffer)) * periods), GFP_ATOMIC);
+	if (!buf) {
+		spin_unlock_irqrestore(&ac->lock, flags);
+		return -ENOMEM;
+	}
+
+
+	ac->port[dir].buf = buf;
+
+	buf[0].phys = phys;
+	buf[0].size = period_sz;
+
+	for (cnt = 1; cnt < periods; cnt++) {
+		if (period_sz > 0) {
+			buf[cnt].phys = buf[0].phys + (cnt * period_sz);
+			buf[cnt].size = period_sz;
+		}
+	}
+	ac->port[dir].num_periods = periods;
+
+	spin_unlock_irqrestore(&ac->lock, flags);
+
+	rc = __q6asm_memory_map_regions(ac, dir, period_sz, periods, 1);
+	if (rc < 0) {
+		dev_err(ac->dev, "Memory_map_regions failed\n");
+		q6asm_audio_client_free_buf(ac, &ac->port[dir]);
+	}
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(q6asm_map_memory_regions);
+
+static void q6asm_audio_client_release(struct kref *ref)
+{
+	struct audio_client *ac;
+	struct q6asm *a;
+	unsigned long flags;
+
+	ac = container_of(ref, struct audio_client, refcount);
+	a = ac->q6asm;
+
+	spin_lock_irqsave(&a->slock, flags);
+	a->session[ac->session] = NULL;
+	spin_unlock_irqrestore(&a->slock, flags);
+
+	kfree(ac);
+}
+
+/**
+ * q6asm_audio_client_free() - Freee allocated audio client
+ *
+ * @ac: audio client to free
+ */
+void q6asm_audio_client_free(struct audio_client *ac)
+{
+	kref_put(&ac->refcount, q6asm_audio_client_release);
+}
+EXPORT_SYMBOL_GPL(q6asm_audio_client_free);
+
+static struct audio_client *q6asm_get_audio_client(struct q6asm *a,
+						   int session_id)
+{
+	struct audio_client *ac = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&a->slock, flags);
+	if ((session_id <= 0) || (session_id > MAX_SESSIONS)) {
+		dev_err(a->dev, "invalid session: %d\n", session_id);
+		goto err;
+	}
+
+	/* check for valid session */
+	if (!a->session[session_id])
+		goto err;
+	else if (a->session[session_id]->session != session_id)
+		goto err;
+
+	ac = a->session[session_id];
+	kref_get(&ac->refcount);
+err:
+	spin_unlock_irqrestore(&a->slock, flags);
+	return ac;
+}
+
+static int32_t q6asm_stream_callback(struct apr_device *adev,
+				     struct apr_resp_pkt *data,
+				     int session_id)
+{
+	struct q6asm *q6asm = dev_get_drvdata(&adev->dev);
+	struct aprv2_ibasic_rsp_result_t *result;
+	struct apr_hdr *hdr = &data->hdr;
+	struct audio_port_data *port;
+	struct audio_client *ac;
+	uint32_t client_event = 0;
+	int ret = 0;
+
+	ac = q6asm_get_audio_client(q6asm, session_id);
+	if (!ac)/* Audio client might already be freed by now */
+		return 0;
+
+	result = data->payload;
+
+	switch (hdr->opcode) {
+	case APR_BASIC_RSP_RESULT:
+		switch (result->opcode) {
+		case ASM_SESSION_CMD_PAUSE:
+			client_event = ASM_CLIENT_EVENT_CMD_PAUSE_DONE;
+			break;
+		case ASM_SESSION_CMD_SUSPEND:
+			client_event = ASM_CLIENT_EVENT_CMD_SUSPEND_DONE;
+			break;
+		case ASM_DATA_CMD_EOS:
+			client_event = ASM_CLIENT_EVENT_CMD_EOS_DONE;
+			break;
+		case ASM_STREAM_CMD_FLUSH:
+			client_event = ASM_CLIENT_EVENT_CMD_FLUSH_DONE;
+			break;
+		case ASM_SESSION_CMD_RUN_V2:
+			client_event = ASM_CLIENT_EVENT_CMD_RUN_DONE;
+			break;
+		case ASM_STREAM_CMD_CLOSE:
+			client_event = ASM_CLIENT_EVENT_CMD_CLOSE_DONE;
+			break;
+		case ASM_STREAM_CMD_FLUSH_READBUFS:
+			client_event = ASM_CLIENT_EVENT_CMD_OUT_FLUSH_DONE;
+			break;
+		case ASM_STREAM_CMD_OPEN_WRITE_V3:
+		case ASM_STREAM_CMD_OPEN_READ_V3:
+		case ASM_STREAM_CMD_OPEN_READWRITE_V2:
+		case ASM_STREAM_CMD_SET_ENCDEC_PARAM:
+		case ASM_DATA_CMD_MEDIA_FMT_UPDATE_V2:
+			if (result->status != 0) {
+				dev_err(ac->dev,
+					"cmd = 0x%x returned error = 0x%x\n",
+					result->opcode, result->status);
+				ac->result = *result;
+				wake_up(&ac->cmd_wait);
+				ret = 0;
+				goto done;
+			}
+			break;
+		default:
+			dev_err(ac->dev, "command[0x%x] not expecting rsp\n",
+				result->opcode);
+			break;
+		}
+
+		ac->result = *result;
+		wake_up(&ac->cmd_wait);
+
+		if (ac->cb)
+			ac->cb(client_event, hdr->token,
+			       data->payload, ac->priv);
+
+		ret = 0;
+		goto done;
+
+	case ASM_DATA_EVENT_WRITE_DONE_V2:
+		client_event = ASM_CLIENT_EVENT_DATA_WRITE_DONE;
+		if (ac->io_mode & ASM_SYNC_IO_MODE) {
+			phys_addr_t phys;
+			unsigned long flags;
+
+			spin_lock_irqsave(&ac->lock, flags);
+
+			port =  &ac->port[SNDRV_PCM_STREAM_PLAYBACK];
+
+			if (!port->buf) {
+				spin_unlock_irqrestore(&ac->lock, flags);
+				ret = 0;
+				goto done;
+			}
+
+			phys = port->buf[hdr->token].phys;
+
+			if (lower_32_bits(phys) != result->opcode ||
+			    upper_32_bits(phys) != result->status) {
+				dev_err(ac->dev, "Expected addr %pa\n",
+					&port->buf[hdr->token].phys);
+				spin_unlock_irqrestore(&ac->lock, flags);
+				ret = -EINVAL;
+				goto done;
+			}
+			spin_unlock_irqrestore(&ac->lock, flags);
+		}
+		break;
+	case ASM_DATA_EVENT_READ_DONE_V2:
+		client_event = ASM_CLIENT_EVENT_DATA_READ_DONE;
+		if (ac->io_mode & ASM_SYNC_IO_MODE) {
+			struct asm_data_cmd_read_v2_done *done = data->payload;
+			unsigned long flags;
+			phys_addr_t phys;
+
+			spin_lock_irqsave(&ac->lock, flags);
+			port =  &ac->port[SNDRV_PCM_STREAM_CAPTURE];
+			if (!port->buf) {
+				spin_unlock_irqrestore(&ac->lock, flags);
+				ret = 0;
+				goto done;
+			}
+
+			phys = port->buf[hdr->token].phys;
+
+			if (upper_32_bits(phys) != done->buf_addr_msw ||
+			    lower_32_bits(phys) != done->buf_addr_lsw) {
+				dev_err(ac->dev, "Expected addr %pa %08x-%08x\n",
+					&port->buf[hdr->token].phys,
+					done->buf_addr_lsw,
+					done->buf_addr_msw);
+				spin_unlock_irqrestore(&ac->lock, flags);
+				ret = -EINVAL;
+				goto done;
+			}
+			spin_unlock_irqrestore(&ac->lock, flags);
+		}
+
+		break;
+	}
+
+	if (ac->cb)
+		ac->cb(client_event, hdr->token, data->payload, ac->priv);
+
+done:
+	kref_put(&ac->refcount, q6asm_audio_client_release);
+	return ret;
+}
+
+static int q6asm_srvc_callback(struct apr_device *adev,
+			       struct apr_resp_pkt *data)
+{
+	struct q6asm *q6asm = dev_get_drvdata(&adev->dev);
+	struct aprv2_ibasic_rsp_result_t *result;
+	struct audio_port_data *port;
+	struct audio_client *ac = NULL;
+	struct apr_hdr *hdr = &data->hdr;
+	struct q6asm *a;
+	uint32_t sid = 0;
+	uint32_t dir = 0;
+	int session_id;
+
+	session_id = (hdr->dest_port >> 8) & 0xFF;
+	if (session_id)
+		return q6asm_stream_callback(adev, data, session_id);
+
+	sid = (hdr->token >> 8) & 0x0F;
+	ac = q6asm_get_audio_client(q6asm, sid);
+	if (!ac) {
+		dev_err(&adev->dev, "Audio Client not active\n");
+		return 0;
+	}
+
+	a = dev_get_drvdata(ac->dev->parent);
+	dir = (hdr->token & 0x0F);
+	port = &ac->port[dir];
+	result = data->payload;
+
+	switch (hdr->opcode) {
+	case APR_BASIC_RSP_RESULT:
+		switch (result->opcode) {
+		case ASM_CMD_SHARED_MEM_MAP_REGIONS:
+		case ASM_CMD_SHARED_MEM_UNMAP_REGIONS:
+			ac->result = *result;
+			wake_up(&a->mem_wait);
+			break;
+		default:
+			dev_err(&adev->dev, "command[0x%x] not expecting rsp\n",
+				 result->opcode);
+			break;
+		}
+		goto done;
+	case ASM_CMDRSP_SHARED_MEM_MAP_REGIONS:
+		ac->result.status = 0;
+		ac->result.opcode = hdr->opcode;
+		port->mem_map_handle = result->opcode;
+		wake_up(&a->mem_wait);
+		break;
+	case ASM_CMD_SHARED_MEM_UNMAP_REGIONS:
+		ac->result.opcode = hdr->opcode;
+		ac->result.status = 0;
+		port->mem_map_handle = 0;
+		wake_up(&a->mem_wait);
+		break;
+	default:
+		dev_dbg(&adev->dev, "command[0x%x]success [0x%x]\n",
+			result->opcode, result->status);
+		break;
+	}
+
+	if (ac->cb)
+		ac->cb(hdr->opcode, hdr->token, data->payload, ac->priv);
+
+done:
+	kref_put(&ac->refcount, q6asm_audio_client_release);
+
+	return 0;
+}
+
+/**
+ * q6asm_get_session_id() - get session id for audio client
+ *
+ * @c: audio client pointer
+ *
+ * Return: Will be an session id of the audio client.
+ */
+int q6asm_get_session_id(struct audio_client *c)
+{
+	return c->session;
+}
+EXPORT_SYMBOL_GPL(q6asm_get_session_id);
+
+/**
+ * q6asm_audio_client_alloc() - Allocate a new audio client
+ *
+ * @dev: Pointer to asm child device.
+ * @cb: event callback.
+ * @priv: private data associated with this client.
+ * @stream_id: stream id
+ * @perf_mode: performace mode for this client
+ *
+ * Return: Will be an error pointer on error or a valid audio client
+ * on success.
+ */
+struct audio_client *q6asm_audio_client_alloc(struct device *dev, q6asm_cb cb,
+					      void *priv, int stream_id,
+					      int perf_mode)
+{
+	struct q6asm *a = dev_get_drvdata(dev->parent);
+	struct audio_client *ac;
+	unsigned long flags;
+
+	ac = q6asm_get_audio_client(a, stream_id + 1);
+	if (ac) {
+		dev_err(dev, "Audio Client already active\n");
+		return ac;
+	}
+
+	ac = kzalloc(sizeof(*ac), GFP_KERNEL);
+	if (!ac)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_irqsave(&a->slock, flags);
+	a->session[stream_id + 1] = ac;
+	spin_unlock_irqrestore(&a->slock, flags);
+	ac->session = stream_id + 1;
+	ac->cb = cb;
+	ac->dev = dev;
+	ac->q6asm = a;
+	ac->priv = priv;
+	ac->io_mode = ASM_SYNC_IO_MODE;
+	ac->perf_mode = perf_mode;
+	/* DSP expects stream id from 1 */
+	ac->stream_id = 1;
+	ac->adev = a->adev;
+	kref_init(&ac->refcount);
+
+	init_waitqueue_head(&ac->cmd_wait);
+	mutex_init(&ac->cmd_lock);
+	spin_lock_init(&ac->lock);
+
+	return ac;
+}
+EXPORT_SYMBOL_GPL(q6asm_audio_client_alloc);
+
+static int q6asm_ac_send_cmd_sync(struct audio_client *ac, struct apr_pkt *pkt)
+{
+	struct apr_hdr *hdr = &pkt->hdr;
+	int rc;
+
+	mutex_lock(&ac->cmd_lock);
+	ac->result.opcode = 0;
+	ac->result.status = 0;
+
+	rc = apr_send_pkt(ac->adev, pkt);
+	if (rc < 0)
+		goto err;
+
+	rc = wait_event_timeout(ac->cmd_wait,
+				(ac->result.opcode == hdr->opcode), 5 * HZ);
+	if (!rc) {
+		dev_err(ac->dev, "CMD timeout\n");
+		rc =  -ETIMEDOUT;
+		goto err;
+	}
+
+	if (ac->result.status > 0) {
+		dev_err(ac->dev, "DSP returned error[%x]\n",
+			ac->result.status);
+		rc = -EINVAL;
+	} else {
+		rc = 0;
+	}
+
+
+err:
+	mutex_unlock(&ac->cmd_lock);
+	return rc;
+}
+
+/**
+ * q6asm_open_write() - Open audio client for writing
+ *
+ * @ac: audio client pointer
+ * @format: audio sample format
+ * @bits_per_sample: bits per sample
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_open_write(struct audio_client *ac, uint32_t format,
+		     uint16_t bits_per_sample)
+{
+	struct asm_stream_cmd_open_write_v3 *open;
+	struct apr_pkt *pkt;
+	void *p;
+	int rc, pkt_size;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*open);
+
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	open = p + APR_HDR_SIZE;
+	q6asm_add_hdr(ac, &pkt->hdr, pkt_size, true, ac->stream_id);
+
+	pkt->hdr.opcode = ASM_STREAM_CMD_OPEN_WRITE_V3;
+	open->mode_flags = 0x00;
+	open->mode_flags |= ASM_LEGACY_STREAM_SESSION;
+
+	/* source endpoint : matrix */
+	open->sink_endpointype = ASM_END_POINT_DEVICE_MATRIX;
+	open->bits_per_sample = bits_per_sample;
+	open->postprocopo_id = ASM_NULL_POPP_TOPOLOGY;
+
+	switch (format) {
+	case FORMAT_LINEAR_PCM:
+		open->dec_fmt_id = ASM_MEDIA_FMT_MULTI_CHANNEL_PCM_V2;
+		break;
+	default:
+		dev_err(ac->dev, "Invalid format 0x%x\n", format);
+		rc = -EINVAL;
+		goto err;
+	}
+
+	rc = q6asm_ac_send_cmd_sync(ac, pkt);
+	if (rc < 0)
+		goto err;
+
+	ac->io_mode |= ASM_TUN_WRITE_IO_MODE;
+
+err:
+	kfree(pkt);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(q6asm_open_write);
+
+static int __q6asm_run(struct audio_client *ac, uint32_t flags,
+	      uint32_t msw_ts, uint32_t lsw_ts, bool wait)
+{
+	struct asm_session_cmd_run_v2 *run;
+	struct apr_pkt *pkt;
+	int pkt_size, rc;
+	void *p;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*run);
+	p = kzalloc(pkt_size, GFP_ATOMIC);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	run = p + APR_HDR_SIZE;
+
+	q6asm_add_hdr(ac, &pkt->hdr, pkt_size, true, ac->stream_id);
+
+	pkt->hdr.opcode = ASM_SESSION_CMD_RUN_V2;
+	run->flags = flags;
+	run->time_lsw = lsw_ts;
+	run->time_msw = msw_ts;
+	if (wait) {
+		rc = q6asm_ac_send_cmd_sync(ac, pkt);
+	} else {
+		rc = apr_send_pkt(ac->adev, pkt);
+		if (rc == pkt_size)
+			rc = 0;
+	}
+
+	kfree(pkt);
+	return rc;
+}
+
+/**
+ * q6asm_run() - start the audio client
+ *
+ * @ac: audio client pointer
+ * @flags: flags associated with write
+ * @msw_ts: timestamp msw
+ * @lsw_ts: timestamp lsw
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_run(struct audio_client *ac, uint32_t flags,
+	      uint32_t msw_ts, uint32_t lsw_ts)
+{
+	return __q6asm_run(ac, flags, msw_ts, lsw_ts, true);
+}
+EXPORT_SYMBOL_GPL(q6asm_run);
+
+/**
+ * q6asm_run_nowait() - start the audio client withou blocking
+ *
+ * @ac: audio client pointer
+ * @flags: flags associated with write
+ * @msw_ts: timestamp msw
+ * @lsw_ts: timestamp lsw
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_run_nowait(struct audio_client *ac, uint32_t flags,
+	      uint32_t msw_ts, uint32_t lsw_ts)
+{
+	return __q6asm_run(ac, flags, msw_ts, lsw_ts, false);
+}
+EXPORT_SYMBOL_GPL(q6asm_run_nowait);
+
+/**
+ * q6asm_media_format_block_multi_ch_pcm() - setup pcm configuration
+ *
+ * @ac: audio client pointer
+ * @rate: audio sample rate
+ * @channels: number of audio channels.
+ * @channel_map: channel map pointer
+ * @bits_per_sample: bits per sample
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_media_format_block_multi_ch_pcm(struct audio_client *ac,
+					  uint32_t rate, uint32_t channels,
+					  u8 channel_map[PCM_MAX_NUM_CHANNEL],
+					  uint16_t bits_per_sample)
+{
+	struct asm_multi_channel_pcm_fmt_blk_v2 *fmt;
+	struct apr_pkt *pkt;
+	u8 *channel_mapping;
+	void *p;
+	int rc, pkt_size;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*fmt);
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	fmt = p + APR_HDR_SIZE;
+
+	q6asm_add_hdr(ac, &pkt->hdr, pkt_size, true, ac->stream_id);
+
+	pkt->hdr.opcode = ASM_DATA_CMD_MEDIA_FMT_UPDATE_V2;
+	fmt->fmt_blk.fmt_blk_size = sizeof(*fmt) - sizeof(fmt->fmt_blk);
+	fmt->num_channels = channels;
+	fmt->bits_per_sample = bits_per_sample;
+	fmt->sample_rate = rate;
+	fmt->is_signed = 1;
+
+	channel_mapping = fmt->channel_mapping;
+
+	if (channel_map) {
+		memcpy(channel_mapping, channel_map, PCM_MAX_NUM_CHANNEL);
+	} else {
+		if (q6dsp_map_channels(channel_mapping, channels)) {
+			dev_err(ac->dev, " map channels failed %d\n", channels);
+			rc = -EINVAL;
+			goto err;
+		}
+	}
+
+	rc = q6asm_ac_send_cmd_sync(ac, pkt);
+
+err:
+	kfree(pkt);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(q6asm_media_format_block_multi_ch_pcm);
+
+/**
+ * q6asm_enc_cfg_blk_pcm_format_support() - setup pcm configuration for capture
+ *
+ * @ac: audio client pointer
+ * @rate: audio sample rate
+ * @channels: number of audio channels.
+ * @bits_per_sample: bits per sample
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_enc_cfg_blk_pcm_format_support(struct audio_client *ac,
+		uint32_t rate, uint32_t channels, uint16_t bits_per_sample)
+{
+	struct asm_multi_channel_pcm_enc_cfg_v2  *enc_cfg;
+	struct apr_pkt *pkt;
+	u8 *channel_mapping;
+	u32 frames_per_buf = 0;
+	int pkt_size, rc;
+	void *p;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*enc_cfg);
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	enc_cfg = p + APR_HDR_SIZE;
+	q6asm_add_hdr(ac, &pkt->hdr, pkt_size, true, ac->stream_id);
+
+	pkt->hdr.opcode = ASM_STREAM_CMD_SET_ENCDEC_PARAM;
+	enc_cfg->encdec.param_id = ASM_PARAM_ID_ENCDEC_ENC_CFG_BLK_V2;
+	enc_cfg->encdec.param_size = sizeof(*enc_cfg) - sizeof(enc_cfg->encdec);
+	enc_cfg->encblk.frames_per_buf = frames_per_buf;
+	enc_cfg->encblk.enc_cfg_blk_size  = enc_cfg->encdec.param_size -
+					sizeof(struct asm_enc_cfg_blk_param_v2);
+
+	enc_cfg->num_channels = channels;
+	enc_cfg->bits_per_sample = bits_per_sample;
+	enc_cfg->sample_rate = rate;
+	enc_cfg->is_signed = 1;
+	channel_mapping = enc_cfg->channel_mapping;
+
+	if (q6dsp_map_channels(channel_mapping, channels)) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	rc = q6asm_ac_send_cmd_sync(ac, pkt);
+err:
+	kfree(pkt);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(q6asm_enc_cfg_blk_pcm_format_support);
+
+/**
+ * q6asm_read() - read data of period size from audio client
+ *
+ * @ac: audio client pointer
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_read(struct audio_client *ac)
+{
+	struct asm_data_cmd_read_v2 *read;
+	struct audio_port_data *port;
+	struct audio_buffer *ab;
+	struct apr_pkt *pkt;
+	unsigned long flags;
+	int pkt_size;
+	int rc = 0;
+	void *p;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*read);
+	p = kzalloc(pkt_size, GFP_ATOMIC);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	read = p + APR_HDR_SIZE;
+
+	spin_lock_irqsave(&ac->lock, flags);
+	port = &ac->port[SNDRV_PCM_STREAM_CAPTURE];
+	q6asm_add_hdr(ac, &pkt->hdr, pkt_size, false, ac->stream_id);
+	ab = &port->buf[port->dsp_buf];
+	pkt->hdr.opcode = ASM_DATA_CMD_READ_V2;
+	read->buf_addr_lsw = lower_32_bits(ab->phys);
+	read->buf_addr_msw = upper_32_bits(ab->phys);
+	read->mem_map_handle = port->mem_map_handle;
+
+	read->buf_size = ab->size;
+	read->seq_id = port->dsp_buf;
+	pkt->hdr.token = port->dsp_buf;
+
+	port->dsp_buf++;
+
+	if (port->dsp_buf >= port->num_periods)
+		port->dsp_buf = 0;
+
+	spin_unlock_irqrestore(&ac->lock, flags);
+	rc = apr_send_pkt(ac->adev, pkt);
+	if (rc == pkt_size)
+		rc = 0;
+	else
+		pr_err("read op[0x%x]rc[%d]\n", pkt->hdr.opcode, rc);
+
+	kfree(pkt);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(q6asm_read);
+
+static int __q6asm_open_read(struct audio_client *ac,
+		uint32_t format, uint16_t bits_per_sample)
+{
+	struct asm_stream_cmd_open_read_v3 *open;
+	struct apr_pkt *pkt;
+	int pkt_size, rc;
+	void *p;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*open);
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	open = p + APR_HDR_SIZE;
+
+	q6asm_add_hdr(ac, &pkt->hdr,  pkt_size, true, ac->stream_id);
+	pkt->hdr.opcode = ASM_STREAM_CMD_OPEN_READ_V3;
+	/* Stream prio : High, provide meta info with encoded frames */
+	open->src_endpointype = ASM_END_POINT_DEVICE_MATRIX;
+
+	open->preprocopo_id = ASM_STREAM_POSTPROC_TOPO_ID_NONE;
+	open->bits_per_sample = bits_per_sample;
+	open->mode_flags = 0x0;
+
+	open->mode_flags |= ASM_LEGACY_STREAM_SESSION <<
+				ASM_SHIFT_STREAM_PERF_MODE_FLAG_IN_OPEN_READ;
+
+	switch (format) {
+	case FORMAT_LINEAR_PCM:
+		open->mode_flags |= 0x00;
+		open->enc_cfg_id = ASM_MEDIA_FMT_MULTI_CHANNEL_PCM_V2;
+		break;
+	default:
+		pr_err("Invalid format[%d]\n", format);
+	}
+
+	rc = q6asm_ac_send_cmd_sync(ac, pkt);
+
+	kfree(pkt);
+	return rc;
+}
+
+/**
+ * q6asm_open_read() - Open audio client for reading
+ *
+ * @ac: audio client pointer
+ * @format: audio sample format
+ * @bits_per_sample: bits per sample
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_open_read(struct audio_client *ac, uint32_t format,
+			uint16_t bits_per_sample)
+{
+	return __q6asm_open_read(ac, format, bits_per_sample);
+}
+EXPORT_SYMBOL_GPL(q6asm_open_read);
+
+/**
+ * q6asm_write_async() - non blocking write
+ *
+ * @ac: audio client pointer
+ * @len: lenght in bytes
+ * @msw_ts: timestamp msw
+ * @lsw_ts: timestamp lsw
+ * @wflags: flags associated with write
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_write_async(struct audio_client *ac, uint32_t len, uint32_t msw_ts,
+		       uint32_t lsw_ts, uint32_t wflags)
+{
+	struct asm_data_cmd_write_v2 *write;
+	struct audio_port_data *port;
+	struct audio_buffer *ab;
+	unsigned long flags;
+	struct apr_pkt *pkt;
+	int pkt_size;
+	int rc = 0;
+	void *p;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*write);
+	p = kzalloc(pkt_size, GFP_ATOMIC);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	write = p + APR_HDR_SIZE;
+
+	spin_lock_irqsave(&ac->lock, flags);
+	port = &ac->port[SNDRV_PCM_STREAM_PLAYBACK];
+	q6asm_add_hdr(ac, &pkt->hdr, pkt_size, false, ac->stream_id);
+
+	ab = &port->buf[port->dsp_buf];
+	pkt->hdr.token = port->dsp_buf;
+	pkt->hdr.opcode = ASM_DATA_CMD_WRITE_V2;
+	write->buf_addr_lsw = lower_32_bits(ab->phys);
+	write->buf_addr_msw = upper_32_bits(ab->phys);
+	write->buf_size = len;
+	write->seq_id = port->dsp_buf;
+	write->timestamp_lsw = lsw_ts;
+	write->timestamp_msw = msw_ts;
+	write->mem_map_handle =
+	    ac->port[SNDRV_PCM_STREAM_PLAYBACK].mem_map_handle;
+
+	if (wflags == NO_TIMESTAMP)
+		write->flags = (wflags & 0x800000FF);
+	else
+		write->flags = (0x80000000 | wflags);
+
+	port->dsp_buf++;
+
+	if (port->dsp_buf >= port->num_periods)
+		port->dsp_buf = 0;
+
+	spin_unlock_irqrestore(&ac->lock, flags);
+	rc = apr_send_pkt(ac->adev, pkt);
+	if (rc == pkt_size)
+		rc = 0;
+
+	kfree(pkt);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(q6asm_write_async);
+
+static void q6asm_reset_buf_state(struct audio_client *ac)
+{
+	struct audio_port_data *port = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ac->lock, flags);
+	port = &ac->port[SNDRV_PCM_STREAM_PLAYBACK];
+	port->dsp_buf = 0;
+	port = &ac->port[SNDRV_PCM_STREAM_CAPTURE];
+	port->dsp_buf = 0;
+	spin_unlock_irqrestore(&ac->lock, flags);
+}
+
+static int __q6asm_cmd(struct audio_client *ac, int cmd, bool wait)
+{
+	int stream_id = ac->stream_id;
+	struct apr_pkt pkt;
+	int rc;
+
+	q6asm_add_hdr(ac, &pkt.hdr, APR_HDR_SIZE, true, stream_id);
+
+	switch (cmd) {
+	case CMD_PAUSE:
+		pkt.hdr.opcode = ASM_SESSION_CMD_PAUSE;
+		break;
+	case CMD_SUSPEND:
+		pkt.hdr.opcode = ASM_SESSION_CMD_SUSPEND;
+		break;
+	case CMD_FLUSH:
+		pkt.hdr.opcode = ASM_STREAM_CMD_FLUSH;
+		break;
+	case CMD_OUT_FLUSH:
+		pkt.hdr.opcode = ASM_STREAM_CMD_FLUSH_READBUFS;
+		break;
+	case CMD_EOS:
+		pkt.hdr.opcode = ASM_DATA_CMD_EOS;
+		break;
+	case CMD_CLOSE:
+		pkt.hdr.opcode = ASM_STREAM_CMD_CLOSE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (wait)
+		rc = q6asm_ac_send_cmd_sync(ac, &pkt);
+	else
+		return apr_send_pkt(ac->adev, &pkt);
+
+	if (rc < 0)
+		return rc;
+
+	if (cmd == CMD_FLUSH)
+		q6asm_reset_buf_state(ac);
+
+	return 0;
+}
+
+/**
+ * q6asm_cmd() - run cmd on audio client
+ *
+ * @ac: audio client pointer
+ * @cmd: command to run on audio client.
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_cmd(struct audio_client *ac, int cmd)
+{
+	return __q6asm_cmd(ac, cmd, true);
+}
+EXPORT_SYMBOL_GPL(q6asm_cmd);
+
+/**
+ * q6asm_cmd_nowait() - non blocking, run cmd on audio client
+ *
+ * @ac: audio client pointer
+ * @cmd: command to run on audio client.
+ *
+ * Return: Will be an negative value on error or zero on success
+ */
+int q6asm_cmd_nowait(struct audio_client *ac, int cmd)
+{
+	return __q6asm_cmd(ac, cmd, false);
+}
+EXPORT_SYMBOL_GPL(q6asm_cmd_nowait);
+
+static int q6asm_probe(struct apr_device *adev)
+{
+	struct device *dev = &adev->dev;
+	struct device_node *dais_np;
+	struct q6asm *q6asm;
+
+	q6asm = devm_kzalloc(dev, sizeof(*q6asm), GFP_KERNEL);
+	if (!q6asm)
+		return -ENOMEM;
+
+	q6core_get_svc_api_info(adev->svc_id, &q6asm->ainfo);
+
+	q6asm->dev = dev;
+	q6asm->adev = adev;
+	init_waitqueue_head(&q6asm->mem_wait);
+	spin_lock_init(&q6asm->slock);
+	dev_set_drvdata(dev, q6asm);
+
+	dais_np = of_get_child_by_name(dev->of_node, "dais");
+	if (dais_np) {
+		q6asm->pdev_dais = of_platform_device_create(dais_np,
+							   "q6asm-dai", dev);
+		of_node_put(dais_np);
+	}
+
+	return 0;
+}
+
+static int q6asm_remove(struct apr_device *adev)
+{
+	struct q6asm *q6asm = dev_get_drvdata(&adev->dev);
+
+	if (q6asm->pdev_dais)
+		of_platform_device_destroy(&q6asm->pdev_dais->dev, NULL);
+
+	return 0;
+}
+static const struct of_device_id q6asm_device_id[]  = {
+	{ .compatible = "qcom,q6asm" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, q6asm_device_id);
+
+static struct apr_driver qcom_q6asm_driver = {
+	.probe = q6asm_probe,
+	.remove = q6asm_remove,
+	.callback = q6asm_srvc_callback,
+	.driver = {
+		.name = "qcom-q6asm",
+		.of_match_table = of_match_ptr(q6asm_device_id),
+	},
+};
+
+module_apr_driver(qcom_q6asm_driver);
+MODULE_DESCRIPTION("Q6 Audio Stream Manager driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/q6asm.h b/sound/soc/qcom/qdsp6/q6asm.h
new file mode 100644
index 000000000000..9f5fb573e4a0
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6asm.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __Q6_ASM_H__
+#define __Q6_ASM_H__
+#include "q6dsp-common.h"
+#include <dt-bindings/sound/qcom,q6asm.h>
+
+/* ASM client callback events */
+#define CMD_PAUSE			0x0001
+#define ASM_CLIENT_EVENT_CMD_PAUSE_DONE		0x1001
+#define CMD_FLUSH				0x0002
+#define ASM_CLIENT_EVENT_CMD_FLUSH_DONE		0x1002
+#define CMD_EOS				0x0003
+#define ASM_CLIENT_EVENT_CMD_EOS_DONE		0x1003
+#define CMD_CLOSE				0x0004
+#define ASM_CLIENT_EVENT_CMD_CLOSE_DONE		0x1004
+#define CMD_OUT_FLUSH				0x0005
+#define ASM_CLIENT_EVENT_CMD_OUT_FLUSH_DONE	0x1005
+#define CMD_SUSPEND				0x0006
+#define ASM_CLIENT_EVENT_CMD_SUSPEND_DONE	0x1006
+#define ASM_CLIENT_EVENT_CMD_RUN_DONE		0x1008
+#define ASM_CLIENT_EVENT_DATA_WRITE_DONE	0x1009
+#define ASM_CLIENT_EVENT_DATA_READ_DONE		0x100a
+
+enum {
+	LEGACY_PCM_MODE = 0,
+	LOW_LATENCY_PCM_MODE,
+	ULTRA_LOW_LATENCY_PCM_MODE,
+	ULL_POST_PROCESSING_PCM_MODE,
+};
+
+#define MAX_SESSIONS	8
+#define NO_TIMESTAMP    0xFF00
+#define FORMAT_LINEAR_PCM   0x0000
+
+typedef void (*q6asm_cb) (uint32_t opcode, uint32_t token,
+			  void *payload, void *priv);
+struct audio_client;
+struct audio_client *q6asm_audio_client_alloc(struct device *dev,
+					      q6asm_cb cb, void *priv,
+					      int session_id, int perf_mode);
+void q6asm_audio_client_free(struct audio_client *ac);
+int q6asm_write_async(struct audio_client *ac, uint32_t len, uint32_t msw_ts,
+		       uint32_t lsw_ts, uint32_t flags);
+int q6asm_open_write(struct audio_client *ac, uint32_t format,
+		     uint16_t bits_per_sample);
+
+int q6asm_open_read(struct audio_client *ac, uint32_t format,
+		     uint16_t bits_per_sample);
+int q6asm_enc_cfg_blk_pcm_format_support(struct audio_client *ac,
+		uint32_t rate, uint32_t channels, uint16_t bits_per_sample);
+int q6asm_read(struct audio_client *ac);
+
+int q6asm_media_format_block_multi_ch_pcm(struct audio_client *ac,
+					  uint32_t rate, uint32_t channels,
+					  u8 channel_map[PCM_MAX_NUM_CHANNEL],
+					  uint16_t bits_per_sample);
+int q6asm_run(struct audio_client *ac, uint32_t flags, uint32_t msw_ts,
+	      uint32_t lsw_ts);
+int q6asm_run_nowait(struct audio_client *ac, uint32_t flags, uint32_t msw_ts,
+		     uint32_t lsw_ts);
+int q6asm_cmd(struct audio_client *ac, int cmd);
+int q6asm_cmd_nowait(struct audio_client *ac, int cmd);
+int q6asm_get_session_id(struct audio_client *ac);
+int q6asm_map_memory_regions(unsigned int dir,
+			     struct audio_client *ac,
+			     phys_addr_t phys,
+			     size_t bufsz, unsigned int bufcnt);
+int q6asm_unmap_memory_regions(unsigned int dir, struct audio_client *ac);
+#endif /* __Q6_ASM_H__ */
diff --git a/sound/soc/qcom/qdsp6/q6core.c b/sound/soc/qcom/qdsp6/q6core.c
new file mode 100644
index 000000000000..06f03a5fe9bd
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6core.c
@@ -0,0 +1,380 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/jiffies.h>
+#include <linux/wait.h>
+#include <linux/soc/qcom/apr.h>
+#include "q6core.h"
+#include "q6dsp-errno.h"
+
+#define ADSP_STATE_READY_TIMEOUT_MS    3000
+#define Q6_READY_TIMEOUT_MS 100
+#define AVCS_CMD_ADSP_EVENT_GET_STATE		0x0001290C
+#define AVCS_CMDRSP_ADSP_EVENT_GET_STATE	0x0001290D
+#define AVCS_GET_VERSIONS       0x00012905
+#define AVCS_GET_VERSIONS_RSP   0x00012906
+#define AVCS_CMD_GET_FWK_VERSION	0x001292c
+#define AVCS_CMDRSP_GET_FWK_VERSION	0x001292d
+
+struct avcs_svc_info {
+	uint32_t service_id;
+	uint32_t version;
+} __packed;
+
+struct avcs_cmdrsp_get_version {
+	uint32_t build_id;
+	uint32_t num_services;
+	struct avcs_svc_info svc_api_info[];
+} __packed;
+
+/* for ADSP2.8 and above */
+struct avcs_svc_api_info {
+	uint32_t service_id;
+	uint32_t api_version;
+	uint32_t api_branch_version;
+} __packed;
+
+struct avcs_cmdrsp_get_fwk_version {
+	uint32_t build_major_version;
+	uint32_t build_minor_version;
+	uint32_t build_branch_version;
+	uint32_t build_subbranch_version;
+	uint32_t num_services;
+	struct avcs_svc_api_info svc_api_info[];
+} __packed;
+
+struct q6core {
+	struct apr_device *adev;
+	wait_queue_head_t wait;
+	uint32_t avcs_state;
+	struct mutex lock;
+	bool resp_received;
+	uint32_t num_services;
+	struct avcs_cmdrsp_get_fwk_version *fwk_version;
+	struct avcs_cmdrsp_get_version *svc_version;
+	bool fwk_version_supported;
+	bool get_state_supported;
+	bool get_version_supported;
+	bool is_version_requested;
+};
+
+static struct q6core *g_core;
+
+static int q6core_callback(struct apr_device *adev, struct apr_resp_pkt *data)
+{
+	struct q6core *core = dev_get_drvdata(&adev->dev);
+	struct aprv2_ibasic_rsp_result_t *result;
+	struct apr_hdr *hdr = &data->hdr;
+
+	result = data->payload;
+	switch (hdr->opcode) {
+	case APR_BASIC_RSP_RESULT:{
+		result = data->payload;
+		switch (result->opcode) {
+		case AVCS_GET_VERSIONS:
+			if (result->status == ADSP_EUNSUPPORTED)
+				core->get_version_supported = false;
+			core->resp_received = true;
+			break;
+		case AVCS_CMD_GET_FWK_VERSION:
+			if (result->status == ADSP_EUNSUPPORTED)
+				core->fwk_version_supported = false;
+			core->resp_received = true;
+			break;
+		case AVCS_CMD_ADSP_EVENT_GET_STATE:
+			if (result->status == ADSP_EUNSUPPORTED)
+				core->get_state_supported = false;
+			core->resp_received = true;
+			break;
+		}
+		break;
+	}
+	case AVCS_CMDRSP_GET_FWK_VERSION: {
+		struct avcs_cmdrsp_get_fwk_version *fwk;
+		int bytes;
+
+		fwk = data->payload;
+		bytes = sizeof(*fwk) + fwk->num_services *
+				sizeof(fwk->svc_api_info[0]);
+
+		core->fwk_version = kzalloc(bytes, GFP_ATOMIC);
+		if (!core->fwk_version)
+			return -ENOMEM;
+
+		memcpy(core->fwk_version, data->payload, bytes);
+
+		core->fwk_version_supported = true;
+		core->resp_received = true;
+
+		break;
+	}
+	case AVCS_GET_VERSIONS_RSP: {
+		struct avcs_cmdrsp_get_version *v;
+		int len;
+
+		v = data->payload;
+
+		len = sizeof(*v) + v->num_services * sizeof(v->svc_api_info[0]);
+
+		core->svc_version = kzalloc(len, GFP_ATOMIC);
+		if (!core->svc_version)
+			return -ENOMEM;
+
+		memcpy(core->svc_version, data->payload, len);
+
+		core->get_version_supported = true;
+		core->resp_received = true;
+
+		break;
+	}
+	case AVCS_CMDRSP_ADSP_EVENT_GET_STATE:
+		core->get_state_supported = true;
+		core->avcs_state = result->opcode;
+
+		core->resp_received = true;
+		break;
+	default:
+		dev_err(&adev->dev, "Message id from adsp core svc: 0x%x\n",
+			hdr->opcode);
+		break;
+	}
+
+	if (core->resp_received)
+		wake_up(&core->wait);
+
+	return 0;
+}
+
+static int q6core_get_fwk_versions(struct q6core *core)
+{
+	struct apr_device *adev = core->adev;
+	struct apr_pkt pkt;
+	int rc;
+
+	pkt.hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+				      APR_HDR_LEN(APR_HDR_SIZE), APR_PKT_VER);
+	pkt.hdr.pkt_size = APR_HDR_SIZE;
+	pkt.hdr.opcode = AVCS_CMD_GET_FWK_VERSION;
+
+	rc = apr_send_pkt(adev, &pkt);
+	if (rc < 0)
+		return rc;
+
+	rc = wait_event_timeout(core->wait, (core->resp_received),
+				msecs_to_jiffies(Q6_READY_TIMEOUT_MS));
+	if (rc > 0 && core->resp_received) {
+		core->resp_received = false;
+
+		if (!core->fwk_version_supported)
+			return -ENOTSUPP;
+		else
+			return 0;
+	}
+
+
+	return rc;
+}
+
+static int q6core_get_svc_versions(struct q6core *core)
+{
+	struct apr_device *adev = core->adev;
+	struct apr_pkt pkt;
+	int rc;
+
+	pkt.hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+				      APR_HDR_LEN(APR_HDR_SIZE), APR_PKT_VER);
+	pkt.hdr.pkt_size = APR_HDR_SIZE;
+	pkt.hdr.opcode = AVCS_GET_VERSIONS;
+
+	rc = apr_send_pkt(adev, &pkt);
+	if (rc < 0)
+		return rc;
+
+	rc = wait_event_timeout(core->wait, (core->resp_received),
+				msecs_to_jiffies(Q6_READY_TIMEOUT_MS));
+	if (rc > 0 && core->resp_received) {
+		core->resp_received = false;
+		return 0;
+	}
+
+	return rc;
+}
+
+static bool __q6core_is_adsp_ready(struct q6core *core)
+{
+	struct apr_device *adev = core->adev;
+	struct apr_pkt pkt;
+	int rc;
+
+	core->get_state_supported = false;
+
+	pkt.hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD,
+				      APR_HDR_LEN(APR_HDR_SIZE), APR_PKT_VER);
+	pkt.hdr.pkt_size = APR_HDR_SIZE;
+	pkt.hdr.opcode = AVCS_CMD_ADSP_EVENT_GET_STATE;
+
+	rc = apr_send_pkt(adev, &pkt);
+	if (rc < 0)
+		return false;
+
+	rc = wait_event_timeout(core->wait, (core->resp_received),
+				msecs_to_jiffies(Q6_READY_TIMEOUT_MS));
+	if (rc > 0 && core->resp_received) {
+		core->resp_received = false;
+
+		if (core->avcs_state)
+			return true;
+	}
+
+	/* assume that the adsp is up if we not support this command */
+	if (!core->get_state_supported)
+		return true;
+
+	return false;
+}
+
+/**
+ * q6core_get_svc_api_info() - Get version number of a service.
+ *
+ * @svc_id: service id of the service.
+ * @ainfo: Valid struct pointer to fill svc api information.
+ *
+ * Return: zero on success and error code on failure or unsupported
+ */
+int q6core_get_svc_api_info(int svc_id, struct q6core_svc_api_info *ainfo)
+{
+	int i;
+	int ret = -ENOTSUPP;
+
+	if (!g_core || !ainfo)
+		return 0;
+
+	mutex_lock(&g_core->lock);
+	if (!g_core->is_version_requested) {
+		if (q6core_get_fwk_versions(g_core) == -ENOTSUPP)
+			q6core_get_svc_versions(g_core);
+		g_core->is_version_requested = true;
+	}
+
+	if (g_core->fwk_version_supported) {
+		for (i = 0; i < g_core->fwk_version->num_services; i++) {
+			struct avcs_svc_api_info *info;
+
+			info = &g_core->fwk_version->svc_api_info[i];
+			if (svc_id != info->service_id)
+				continue;
+
+			ainfo->api_version = info->api_version;
+			ainfo->api_branch_version = info->api_branch_version;
+			ret = 0;
+			break;
+		}
+	} else if (g_core->get_version_supported) {
+		for (i = 0; i < g_core->svc_version->num_services; i++) {
+			struct avcs_svc_info *info;
+
+			info = &g_core->svc_version->svc_api_info[i];
+			if (svc_id != info->service_id)
+				continue;
+
+			ainfo->api_version = info->version;
+			ainfo->api_branch_version = 0;
+			ret = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&g_core->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(q6core_get_svc_api_info);
+
+/**
+ * q6core_is_adsp_ready() - Get status of adsp
+ *
+ * Return: Will be an true if adsp is ready and false if not.
+ */
+bool q6core_is_adsp_ready(void)
+{
+	unsigned long  timeout;
+	bool ret = false;
+
+	if (!g_core)
+		return false;
+
+	mutex_lock(&g_core->lock);
+	timeout = jiffies + msecs_to_jiffies(ADSP_STATE_READY_TIMEOUT_MS);
+	for (;;) {
+		if (__q6core_is_adsp_ready(g_core)) {
+			ret = true;
+			break;
+		}
+
+		if (!time_after(timeout, jiffies)) {
+			ret = false;
+			break;
+		}
+	}
+
+	mutex_unlock(&g_core->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(q6core_is_adsp_ready);
+
+static int q6core_probe(struct apr_device *adev)
+{
+	g_core = kzalloc(sizeof(*g_core), GFP_KERNEL);
+	if (!g_core)
+		return -ENOMEM;
+
+	dev_set_drvdata(&adev->dev, g_core);
+
+	mutex_init(&g_core->lock);
+	g_core->adev = adev;
+	init_waitqueue_head(&g_core->wait);
+	return 0;
+}
+
+static int q6core_exit(struct apr_device *adev)
+{
+	struct q6core *core = dev_get_drvdata(&adev->dev);
+
+	if (core->fwk_version_supported)
+		kfree(core->fwk_version);
+	if (core->get_version_supported)
+		kfree(core->svc_version);
+
+	g_core = NULL;
+	kfree(core);
+
+	return 0;
+}
+
+static const struct of_device_id q6core_device_id[]  = {
+	{ .compatible = "qcom,q6core" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, q6core_device_id);
+
+static struct apr_driver qcom_q6core_driver = {
+	.probe = q6core_probe,
+	.remove = q6core_exit,
+	.callback = q6core_callback,
+	.driver = {
+		.name = "qcom-q6core",
+		.of_match_table = of_match_ptr(q6core_device_id),
+	},
+};
+
+module_apr_driver(qcom_q6core_driver);
+MODULE_DESCRIPTION("q6 core");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/q6core.h b/sound/soc/qcom/qdsp6/q6core.h
new file mode 100644
index 000000000000..4105b1d730be
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6core.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __Q6CORE_H__
+#define __Q6CORE_H__
+
+struct q6core_svc_api_info {
+	uint32_t service_id;
+	uint32_t api_version;
+	uint32_t api_branch_version;
+};
+
+bool q6core_is_adsp_ready(void);
+int q6core_get_svc_api_info(int svc_id, struct q6core_svc_api_info *ainfo);
+
+#endif /* __Q6CORE_H__ */
diff --git a/sound/soc/qcom/qdsp6/q6dsp-common.c b/sound/soc/qcom/qdsp6/q6dsp-common.c
new file mode 100644
index 000000000000..d393003492c7
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6dsp-common.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include "q6dsp-common.h"
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+
+int q6dsp_map_channels(u8 ch_map[PCM_MAX_NUM_CHANNEL], int ch)
+{
+	memset(ch_map, 0, PCM_MAX_NUM_CHANNEL);
+
+	switch (ch) {
+	case 1:
+		ch_map[0] = PCM_CHANNEL_FC;
+		break;
+	case 2:
+		ch_map[0] = PCM_CHANNEL_FL;
+		ch_map[1] = PCM_CHANNEL_FR;
+		break;
+	case 3:
+		ch_map[0] = PCM_CHANNEL_FL;
+		ch_map[1] = PCM_CHANNEL_FR;
+		ch_map[2] = PCM_CHANNEL_FC;
+		break;
+	case 4:
+		ch_map[0] = PCM_CHANNEL_FL;
+		ch_map[1] = PCM_CHANNEL_FR;
+		ch_map[2] = PCM_CHANNEL_LS;
+		ch_map[3] = PCM_CHANNEL_RS;
+		break;
+	case 5:
+		ch_map[0] = PCM_CHANNEL_FL;
+		ch_map[1] = PCM_CHANNEL_FR;
+		ch_map[2] = PCM_CHANNEL_FC;
+		ch_map[3] = PCM_CHANNEL_LS;
+		ch_map[4] = PCM_CHANNEL_RS;
+		break;
+	case 6:
+		ch_map[0] = PCM_CHANNEL_FL;
+		ch_map[1] = PCM_CHANNEL_FR;
+		ch_map[2] = PCM_CHANNEL_LFE;
+		ch_map[3] = PCM_CHANNEL_FC;
+		ch_map[4] = PCM_CHANNEL_LS;
+		ch_map[5] = PCM_CHANNEL_RS;
+		break;
+	case 8:
+		ch_map[0] = PCM_CHANNEL_FL;
+		ch_map[1] = PCM_CHANNEL_FR;
+		ch_map[2] = PCM_CHANNEL_LFE;
+		ch_map[3] = PCM_CHANNEL_FC;
+		ch_map[4] = PCM_CHANNEL_LS;
+		ch_map[5] = PCM_CHANNEL_RS;
+		ch_map[6] = PCM_CHANNEL_LB;
+		ch_map[7] = PCM_CHANNEL_RB;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(q6dsp_map_channels);
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/q6dsp-common.h b/sound/soc/qcom/qdsp6/q6dsp-common.h
new file mode 100644
index 000000000000..01094d108b8a
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6dsp-common.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __Q6DSP_COMMON_H__
+#define __Q6DSP_COMMON_H__
+
+#include <linux/kernel.h>
+
+#define PCM_MAX_NUM_CHANNEL  8
+#define PCM_CHANNEL_NULL 0
+
+#define PCM_CHANNEL_FL    1	/* Front left channel. */
+#define PCM_CHANNEL_FR    2	/* Front right channel. */
+#define PCM_CHANNEL_FC    3	/* Front center channel. */
+#define PCM_CHANNEL_LS   4	/* Left surround channel. */
+#define PCM_CHANNEL_RS   5	/* Right surround channel. */
+#define PCM_CHANNEL_LFE  6	/* Low frequency effect channel. */
+#define PCM_CHANNEL_CS   7	/* Center surround channel; Rear center ch */
+#define PCM_CHANNEL_LB   8	/* Left back channel; Rear left channel. */
+#define PCM_CHANNEL_RB   9	/* Right back channel; Rear right channel. */
+#define PCM_CHANNELS   10	/* Top surround channel. */
+
+int q6dsp_map_channels(u8 ch_map[PCM_MAX_NUM_CHANNEL], int ch);
+
+#endif /* __Q6DSP_COMMON_H__ */
diff --git a/sound/soc/qcom/qdsp6/q6dsp-errno.h b/sound/soc/qcom/qdsp6/q6dsp-errno.h
new file mode 100644
index 000000000000..1ec00ff8c1d2
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6dsp-errno.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __Q6DSP_ERR_NO_H__
+#define __Q6DSP_ERR_NO_H__
+#include <linux/kernel.h>
+
+/* Success. The operation completed with no errors. */
+#define ADSP_EOK          0x00000000
+/* General failure. */
+#define ADSP_EFAILED      0x00000001
+/* Bad operation parameter. */
+#define ADSP_EBADPARAM    0x00000002
+/* Unsupported routine or operation. */
+#define ADSP_EUNSUPPORTED 0x00000003
+/* Unsupported version. */
+#define ADSP_EVERSION     0x00000004
+/* Unexpected problem encountered. */
+#define ADSP_EUNEXPECTED  0x00000005
+/* Unhandled problem occurred. */
+#define ADSP_EPANIC       0x00000006
+/* Unable to allocate resource. */
+#define ADSP_ENORESOURCE  0x00000007
+/* Invalid handle. */
+#define ADSP_EHANDLE      0x00000008
+/* Operation is already processed. */
+#define ADSP_EALREADY     0x00000009
+/* Operation is not ready to be processed. */
+#define ADSP_ENOTREADY    0x0000000A
+/* Operation is pending completion. */
+#define ADSP_EPENDING     0x0000000B
+/* Operation could not be accepted or processed. */
+#define ADSP_EBUSY        0x0000000C
+/* Operation aborted due to an error. */
+#define ADSP_EABORTED     0x0000000D
+/* Operation preempted by a higher priority. */
+#define ADSP_EPREEMPTED   0x0000000E
+/* Operation requests intervention to complete. */
+#define ADSP_ECONTINUE    0x0000000F
+/* Operation requests immediate intervention to complete. */
+#define ADSP_EIMMEDIATE   0x00000010
+/* Operation is not implemented. */
+#define ADSP_ENOTIMPL     0x00000011
+/* Operation needs more data or resources. */
+#define ADSP_ENEEDMORE    0x00000012
+/* Operation does not have memory. */
+#define ADSP_ENOMEMORY    0x00000014
+/* Item does not exist. */
+#define ADSP_ENOTEXIST    0x00000015
+/* Max count for adsp error code sent to HLOS*/
+
+#endif /*__Q6DSP_ERR_NO_H__ */
diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
new file mode 100644
index 000000000000..593f66b8622f
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -0,0 +1,1006 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2011-2017, The Linux Foundation. All rights reserved.
+// Copyright (c) 2018, Linaro Limited
+
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of_platform.h>
+#include <linux/bitops.h>
+#include <linux/component.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <sound/core.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/pcm.h>
+#include <sound/control.h>
+#include <sound/asound.h>
+#include <sound/pcm_params.h>
+#include "q6afe.h"
+#include "q6asm.h"
+#include "q6adm.h"
+#include "q6routing.h"
+
+#define DRV_NAME "q6routing-component"
+
+#define Q6ROUTING_RX_MIXERS(id)						\
+	SOC_SINGLE_EXT("MultiMedia1", id,				\
+	MSM_FRONTEND_DAI_MULTIMEDIA1, 1, 0, msm_routing_get_audio_mixer,\
+	msm_routing_put_audio_mixer),					\
+	SOC_SINGLE_EXT("MultiMedia2", id,				\
+	MSM_FRONTEND_DAI_MULTIMEDIA2, 1, 0, msm_routing_get_audio_mixer,\
+	msm_routing_put_audio_mixer),					\
+	SOC_SINGLE_EXT("MultiMedia3", id,				\
+	MSM_FRONTEND_DAI_MULTIMEDIA3, 1, 0, msm_routing_get_audio_mixer,\
+	msm_routing_put_audio_mixer),					\
+	SOC_SINGLE_EXT("MultiMedia4", id,				\
+	MSM_FRONTEND_DAI_MULTIMEDIA4, 1, 0, msm_routing_get_audio_mixer,\
+	msm_routing_put_audio_mixer),					\
+	SOC_SINGLE_EXT("MultiMedia5", id,				\
+	MSM_FRONTEND_DAI_MULTIMEDIA5, 1, 0, msm_routing_get_audio_mixer,\
+	msm_routing_put_audio_mixer),					\
+	SOC_SINGLE_EXT("MultiMedia6", id,				\
+	MSM_FRONTEND_DAI_MULTIMEDIA6, 1, 0, msm_routing_get_audio_mixer,\
+	msm_routing_put_audio_mixer),					\
+	SOC_SINGLE_EXT("MultiMedia7", id,				\
+	MSM_FRONTEND_DAI_MULTIMEDIA7, 1, 0, msm_routing_get_audio_mixer,\
+	msm_routing_put_audio_mixer),					\
+	SOC_SINGLE_EXT("MultiMedia8", id,				\
+	MSM_FRONTEND_DAI_MULTIMEDIA8, 1, 0, msm_routing_get_audio_mixer,\
+	msm_routing_put_audio_mixer),
+
+#define Q6ROUTING_RX_DAPM_ROUTE(mix_name, s)	\
+	{ mix_name, "MultiMedia1", "MM_DL1" },	\
+	{ mix_name, "MultiMedia2", "MM_DL2" },	\
+	{ mix_name, "MultiMedia3", "MM_DL3" },	\
+	{ mix_name, "MultiMedia4", "MM_DL4" },	\
+	{ mix_name, "MultiMedia5", "MM_DL5" },	\
+	{ mix_name, "MultiMedia6", "MM_DL6" },	\
+	{ mix_name, "MultiMedia7", "MM_DL7" },	\
+	{ mix_name, "MultiMedia8", "MM_DL8" },	\
+	{ s, NULL, mix_name }
+
+#define Q6ROUTING_TX_DAPM_ROUTE(mix_name)		\
+	{ mix_name, "PRI_MI2S_TX", "PRI_MI2S_TX" },	\
+	{ mix_name, "SEC_MI2S_TX", "SEC_MI2S_TX" },	\
+	{ mix_name, "QUAT_MI2S_TX", "QUAT_MI2S_TX" },	\
+	{ mix_name, "TERT_MI2S_TX", "TERT_MI2S_TX" },		\
+	{ mix_name, "PRIMARY_TDM_TX_0", "PRIMARY_TDM_TX_0"},	\
+	{ mix_name, "PRIMARY_TDM_TX_1", "PRIMARY_TDM_TX_1"},	\
+	{ mix_name, "PRIMARY_TDM_TX_2", "PRIMARY_TDM_TX_2"},	\
+	{ mix_name, "PRIMARY_TDM_TX_3", "PRIMARY_TDM_TX_3"},	\
+	{ mix_name, "PRIMARY_TDM_TX_4", "PRIMARY_TDM_TX_4"},	\
+	{ mix_name, "PRIMARY_TDM_TX_5", "PRIMARY_TDM_TX_5"},	\
+	{ mix_name, "PRIMARY_TDM_TX_6", "PRIMARY_TDM_TX_6"},	\
+	{ mix_name, "PRIMARY_TDM_TX_7", "PRIMARY_TDM_TX_7"},	\
+	{ mix_name, "SEC_TDM_TX_0", "SEC_TDM_TX_0"},		\
+	{ mix_name, "SEC_TDM_TX_1", "SEC_TDM_TX_1"},		\
+	{ mix_name, "SEC_TDM_TX_2", "SEC_TDM_TX_2"},		\
+	{ mix_name, "SEC_TDM_TX_3", "SEC_TDM_TX_3"},		\
+	{ mix_name, "SEC_TDM_TX_4", "SEC_TDM_TX_4"},		\
+	{ mix_name, "SEC_TDM_TX_5", "SEC_TDM_TX_5"},		\
+	{ mix_name, "SEC_TDM_TX_6", "SEC_TDM_TX_6"},		\
+	{ mix_name, "SEC_TDM_TX_7", "SEC_TDM_TX_7"},		\
+	{ mix_name, "TERT_TDM_TX_0", "TERT_TDM_TX_0"},		\
+	{ mix_name, "TERT_TDM_TX_1", "TERT_TDM_TX_1"},		\
+	{ mix_name, "TERT_TDM_TX_2", "TERT_TDM_TX_2"},		\
+	{ mix_name, "TERT_TDM_TX_3", "TERT_TDM_TX_3"},		\
+	{ mix_name, "TERT_TDM_TX_4", "TERT_TDM_TX_4"},		\
+	{ mix_name, "TERT_TDM_TX_5", "TERT_TDM_TX_5"},		\
+	{ mix_name, "TERT_TDM_TX_6", "TERT_TDM_TX_6"},		\
+	{ mix_name, "TERT_TDM_TX_7", "TERT_TDM_TX_7"},		\
+	{ mix_name, "QUAT_TDM_TX_0", "QUAT_TDM_TX_0"},		\
+	{ mix_name, "QUAT_TDM_TX_1", "QUAT_TDM_TX_1"},		\
+	{ mix_name, "QUAT_TDM_TX_2", "QUAT_TDM_TX_2"},		\
+	{ mix_name, "QUAT_TDM_TX_3", "QUAT_TDM_TX_3"},		\
+	{ mix_name, "QUAT_TDM_TX_4", "QUAT_TDM_TX_4"},		\
+	{ mix_name, "QUAT_TDM_TX_5", "QUAT_TDM_TX_5"},		\
+	{ mix_name, "QUAT_TDM_TX_6", "QUAT_TDM_TX_6"},		\
+	{ mix_name, "QUAT_TDM_TX_7", "QUAT_TDM_TX_7"},		\
+	{ mix_name, "QUIN_TDM_TX_0", "QUIN_TDM_TX_0"},		\
+	{ mix_name, "QUIN_TDM_TX_1", "QUIN_TDM_TX_1"},		\
+	{ mix_name, "QUIN_TDM_TX_2", "QUIN_TDM_TX_2"},		\
+	{ mix_name, "QUIN_TDM_TX_3", "QUIN_TDM_TX_3"},		\
+	{ mix_name, "QUIN_TDM_TX_4", "QUIN_TDM_TX_4"},		\
+	{ mix_name, "QUIN_TDM_TX_5", "QUIN_TDM_TX_5"},		\
+	{ mix_name, "QUIN_TDM_TX_6", "QUIN_TDM_TX_6"},		\
+	{ mix_name, "QUIN_TDM_TX_7", "QUIN_TDM_TX_7"}
+
+#define Q6ROUTING_TX_MIXERS(id)						\
+	SOC_SINGLE_EXT("PRI_MI2S_TX", PRIMARY_MI2S_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_MI2S_TX", SECONDARY_MI2S_TX,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_MI2S_TX", TERTIARY_MI2S_TX,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_MI2S_TX", QUATERNARY_MI2S_TX,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("PRIMARY_TDM_TX_0", PRIMARY_TDM_TX_0,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("PRIMARY_TDM_TX_1", PRIMARY_TDM_TX_1,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("PRIMARY_TDM_TX_2", PRIMARY_TDM_TX_2,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("PRIMARY_TDM_TX_3", PRIMARY_TDM_TX_3,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("PRIMARY_TDM_TX_4", PRIMARY_TDM_TX_4,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("PRIMARY_TDM_TX_5", PRIMARY_TDM_TX_5,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("PRIMARY_TDM_TX_6", PRIMARY_TDM_TX_6,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("PRIMARY_TDM_TX_7", PRIMARY_TDM_TX_7,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_TDM_TX_0", SECONDARY_TDM_TX_0,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_TDM_TX_1", SECONDARY_TDM_TX_1,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_TDM_TX_2", SECONDARY_TDM_TX_2,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_TDM_TX_3", SECONDARY_TDM_TX_3,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_TDM_TX_4", SECONDARY_TDM_TX_4,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_TDM_TX_5", SECONDARY_TDM_TX_5,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_TDM_TX_6", SECONDARY_TDM_TX_6,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SEC_TDM_TX_7", SECONDARY_TDM_TX_7,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_TDM_TX_0", TERTIARY_TDM_TX_0,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_TDM_TX_1", TERTIARY_TDM_TX_1,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_TDM_TX_2", TERTIARY_TDM_TX_2,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_TDM_TX_3", TERTIARY_TDM_TX_3,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_TDM_TX_4", TERTIARY_TDM_TX_4,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_TDM_TX_5", TERTIARY_TDM_TX_5,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_TDM_TX_6", TERTIARY_TDM_TX_6,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("TERT_TDM_TX_7", TERTIARY_TDM_TX_7,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_TDM_TX_0", QUATERNARY_TDM_TX_0,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_TDM_TX_1", QUATERNARY_TDM_TX_1,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_TDM_TX_2", QUATERNARY_TDM_TX_2,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_TDM_TX_3", QUATERNARY_TDM_TX_3,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_TDM_TX_4", QUATERNARY_TDM_TX_4,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_TDM_TX_5", QUATERNARY_TDM_TX_5,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_TDM_TX_6", QUATERNARY_TDM_TX_6,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUAT_TDM_TX_7", QUATERNARY_TDM_TX_7,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUIN_TDM_TX_0", QUINARY_TDM_TX_0,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUIN_TDM_TX_1", QUINARY_TDM_TX_1,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUIN_TDM_TX_2", QUINARY_TDM_TX_2,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUIN_TDM_TX_3", QUINARY_TDM_TX_3,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUIN_TDM_TX_4", QUINARY_TDM_TX_4,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUIN_TDM_TX_5", QUINARY_TDM_TX_5,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUIN_TDM_TX_6", QUINARY_TDM_TX_6,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("QUIN_TDM_TX_7", QUINARY_TDM_TX_7,		\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),
+
+struct session_data {
+	int state;
+	int port_id;
+	int path_type;
+	int app_type;
+	int acdb_id;
+	int sample_rate;
+	int bits_per_sample;
+	int channels;
+	int perf_mode;
+	int numcopps;
+	int fedai_id;
+	unsigned long copp_map;
+	struct q6copp *copps[MAX_COPPS_PER_PORT];
+};
+
+struct msm_routing_data {
+	struct session_data sessions[MAX_SESSIONS];
+	struct session_data port_data[AFE_MAX_PORTS];
+	struct device *dev;
+	struct mutex lock;
+};
+
+static struct msm_routing_data *routing_data;
+
+/**
+ * q6routing_stream_open() - Register a new stream for route setup
+ *
+ * @fedai_id: Frontend dai id.
+ * @perf_mode: Performance mode.
+ * @stream_id: ASM stream id to map.
+ * @stream_type: Direction of stream
+ *
+ * Return: Will be an negative on error or a zero on success.
+ */
+int q6routing_stream_open(int fedai_id, int perf_mode,
+			   int stream_id, int stream_type)
+{
+	int j, topology, num_copps = 0;
+	struct route_payload payload;
+	struct q6copp *copp;
+	int copp_idx;
+	struct session_data *session, *pdata;
+
+	if (!routing_data) {
+		pr_err("Routing driver not yet ready\n");
+		return -EINVAL;
+	}
+
+	session = &routing_data->sessions[stream_id - 1];
+	pdata = &routing_data->port_data[session->port_id];
+
+	mutex_lock(&routing_data->lock);
+	session->fedai_id = fedai_id;
+
+	session->path_type = pdata->path_type;
+	session->sample_rate = pdata->sample_rate;
+	session->channels = pdata->channels;
+	session->bits_per_sample = pdata->bits_per_sample;
+
+	payload.num_copps = 0; /* only RX needs to use payload */
+	topology = NULL_COPP_TOPOLOGY;
+	copp = q6adm_open(routing_data->dev, session->port_id,
+			      session->path_type, session->sample_rate,
+			      session->channels, topology, perf_mode,
+			      session->bits_per_sample, 0, 0);
+
+	if (!copp) {
+		mutex_unlock(&routing_data->lock);
+		return -EINVAL;
+	}
+
+	copp_idx = q6adm_get_copp_id(copp);
+	set_bit(copp_idx, &session->copp_map);
+	session->copps[copp_idx] = copp;
+
+	for_each_set_bit(j, &session->copp_map, MAX_COPPS_PER_PORT) {
+		payload.port_id[num_copps] = session->port_id;
+		payload.copp_idx[num_copps] = j;
+		num_copps++;
+	}
+
+	if (num_copps) {
+		payload.num_copps = num_copps;
+		payload.session_id = stream_id;
+		q6adm_matrix_map(routing_data->dev, session->path_type,
+				 payload, perf_mode);
+	}
+	mutex_unlock(&routing_data->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(q6routing_stream_open);
+
+static struct session_data *get_session_from_id(struct msm_routing_data *data,
+						int fedai_id)
+{
+	int i;
+
+	for (i = 0; i < MAX_SESSIONS; i++) {
+		if (fedai_id == data->sessions[i].fedai_id)
+			return &data->sessions[i];
+	}
+
+	return NULL;
+}
+/**
+ * q6routing_stream_close() - Deregister a stream
+ *
+ * @fedai_id: Frontend dai id.
+ * @stream_type: Direction of stream
+ *
+ * Return: Will be an negative on error or a zero on success.
+ */
+void q6routing_stream_close(int fedai_id, int stream_type)
+{
+	struct session_data *session;
+	int idx;
+
+	session = get_session_from_id(routing_data, fedai_id);
+	if (!session)
+		return;
+
+	for_each_set_bit(idx, &session->copp_map, MAX_COPPS_PER_PORT) {
+		if (session->copps[idx]) {
+			q6adm_close(routing_data->dev, session->copps[idx]);
+			session->copps[idx] = NULL;
+		}
+	}
+
+	session->fedai_id = -1;
+	session->copp_map = 0;
+}
+EXPORT_SYMBOL_GPL(q6routing_stream_close);
+
+static int msm_routing_get_audio_mixer(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_dapm_context *dapm =
+	    snd_soc_dapm_kcontrol_dapm(kcontrol);
+	struct soc_mixer_control *mc =
+	    (struct soc_mixer_control *)kcontrol->private_value;
+	int session_id = mc->shift;
+	struct snd_soc_component *c = snd_soc_dapm_to_component(dapm);
+	struct msm_routing_data *priv = dev_get_drvdata(c->dev);
+	struct session_data *session = &priv->sessions[session_id];
+
+	if (session->port_id == mc->reg)
+		ucontrol->value.integer.value[0] = 1;
+	else
+		ucontrol->value.integer.value[0] = 0;
+
+	return 0;
+}
+
+static int msm_routing_put_audio_mixer(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_dapm_context *dapm =
+				    snd_soc_dapm_kcontrol_dapm(kcontrol);
+	struct snd_soc_component *c = snd_soc_dapm_to_component(dapm);
+	struct msm_routing_data *data = dev_get_drvdata(c->dev);
+	struct soc_mixer_control *mc =
+		    (struct soc_mixer_control *)kcontrol->private_value;
+	struct snd_soc_dapm_update *update = NULL;
+	int be_id = mc->reg;
+	int session_id = mc->shift;
+	struct session_data *session = &data->sessions[session_id];
+
+	if (ucontrol->value.integer.value[0]) {
+		session->port_id = be_id;
+		snd_soc_dapm_mixer_update_power(dapm, kcontrol, 1, update);
+	} else {
+		session->port_id = -1;
+		snd_soc_dapm_mixer_update_power(dapm, kcontrol, 0, update);
+	}
+
+	return 1;
+}
+
+static const struct snd_kcontrol_new hdmi_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(HDMI_RX) };
+
+static const struct snd_kcontrol_new primary_mi2s_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_MI2S_RX) };
+
+static const struct snd_kcontrol_new secondary_mi2s_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_MI2S_RX) };
+
+static const struct snd_kcontrol_new quaternary_mi2s_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_MI2S_RX) };
+
+static const struct snd_kcontrol_new tertiary_mi2s_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_MI2S_RX) };
+
+static const struct snd_kcontrol_new slimbus_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SLIMBUS_0_RX) };
+
+static const struct snd_kcontrol_new slimbus_1_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SLIMBUS_1_RX) };
+
+static const struct snd_kcontrol_new slimbus_2_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SLIMBUS_2_RX) };
+
+static const struct snd_kcontrol_new slimbus_3_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SLIMBUS_3_RX) };
+
+static const struct snd_kcontrol_new slimbus_4_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SLIMBUS_4_RX) };
+
+static const struct snd_kcontrol_new slimbus_5_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SLIMBUS_5_RX) };
+
+static const struct snd_kcontrol_new slimbus_6_rx_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SLIMBUS_6_RX) };
+
+static const struct snd_kcontrol_new pri_tdm_rx_0_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_TDM_RX_0) };
+
+static const struct snd_kcontrol_new pri_tdm_rx_1_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_TDM_RX_1) };
+
+static const struct snd_kcontrol_new pri_tdm_rx_2_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_TDM_RX_2) };
+
+static const struct snd_kcontrol_new pri_tdm_rx_3_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_TDM_RX_3) };
+
+static const struct snd_kcontrol_new pri_tdm_rx_4_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_TDM_RX_4) };
+
+static const struct snd_kcontrol_new pri_tdm_rx_5_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_TDM_RX_5) };
+
+static const struct snd_kcontrol_new pri_tdm_rx_6_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_TDM_RX_6) };
+
+static const struct snd_kcontrol_new pri_tdm_rx_7_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(PRIMARY_TDM_RX_7) };
+
+static const struct snd_kcontrol_new sec_tdm_rx_0_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_TDM_RX_0) };
+
+static const struct snd_kcontrol_new sec_tdm_rx_1_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_TDM_RX_1) };
+
+static const struct snd_kcontrol_new sec_tdm_rx_2_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_TDM_RX_2) };
+
+static const struct snd_kcontrol_new sec_tdm_rx_3_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_TDM_RX_3) };
+
+static const struct snd_kcontrol_new sec_tdm_rx_4_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_TDM_RX_4) };
+
+static const struct snd_kcontrol_new sec_tdm_rx_5_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_TDM_RX_5) };
+
+static const struct snd_kcontrol_new sec_tdm_rx_6_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_TDM_RX_6) };
+
+static const struct snd_kcontrol_new sec_tdm_rx_7_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(SECONDARY_TDM_RX_7) };
+
+static const struct snd_kcontrol_new tert_tdm_rx_0_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_TDM_RX_0) };
+
+static const struct snd_kcontrol_new tert_tdm_rx_1_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_TDM_RX_1) };
+
+static const struct snd_kcontrol_new tert_tdm_rx_2_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_TDM_RX_2) };
+
+static const struct snd_kcontrol_new tert_tdm_rx_3_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_TDM_RX_3) };
+
+static const struct snd_kcontrol_new tert_tdm_rx_4_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_TDM_RX_4) };
+
+static const struct snd_kcontrol_new tert_tdm_rx_5_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_TDM_RX_5) };
+
+static const struct snd_kcontrol_new tert_tdm_rx_6_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_TDM_RX_6) };
+
+static const struct snd_kcontrol_new tert_tdm_rx_7_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(TERTIARY_TDM_RX_7) };
+
+static const struct snd_kcontrol_new quat_tdm_rx_0_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_TDM_RX_0) };
+
+static const struct snd_kcontrol_new quat_tdm_rx_1_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_TDM_RX_1) };
+
+static const struct snd_kcontrol_new quat_tdm_rx_2_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_TDM_RX_2) };
+
+static const struct snd_kcontrol_new quat_tdm_rx_3_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_TDM_RX_3) };
+
+static const struct snd_kcontrol_new quat_tdm_rx_4_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_TDM_RX_4) };
+
+static const struct snd_kcontrol_new quat_tdm_rx_5_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_TDM_RX_5) };
+
+static const struct snd_kcontrol_new quat_tdm_rx_6_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_TDM_RX_6) };
+
+static const struct snd_kcontrol_new quat_tdm_rx_7_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUATERNARY_TDM_RX_7) };
+
+static const struct snd_kcontrol_new quin_tdm_rx_0_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUINARY_TDM_RX_0) };
+
+static const struct snd_kcontrol_new quin_tdm_rx_1_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUINARY_TDM_RX_1) };
+
+static const struct snd_kcontrol_new quin_tdm_rx_2_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUINARY_TDM_RX_2) };
+
+static const struct snd_kcontrol_new quin_tdm_rx_3_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUINARY_TDM_RX_3) };
+
+static const struct snd_kcontrol_new quin_tdm_rx_4_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUINARY_TDM_RX_4) };
+
+static const struct snd_kcontrol_new quin_tdm_rx_5_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUINARY_TDM_RX_5) };
+
+static const struct snd_kcontrol_new quin_tdm_rx_6_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUINARY_TDM_RX_6) };
+
+static const struct snd_kcontrol_new quin_tdm_rx_7_mixer_controls[] = {
+	Q6ROUTING_RX_MIXERS(QUINARY_TDM_RX_7) };
+
+
+static const struct snd_kcontrol_new mmul1_mixer_controls[] = {
+	Q6ROUTING_TX_MIXERS(MSM_FRONTEND_DAI_MULTIMEDIA1) };
+
+static const struct snd_kcontrol_new mmul2_mixer_controls[] = {
+	Q6ROUTING_TX_MIXERS(MSM_FRONTEND_DAI_MULTIMEDIA2) };
+
+static const struct snd_kcontrol_new mmul3_mixer_controls[] = {
+	Q6ROUTING_TX_MIXERS(MSM_FRONTEND_DAI_MULTIMEDIA3) };
+
+static const struct snd_kcontrol_new mmul4_mixer_controls[] = {
+	Q6ROUTING_TX_MIXERS(MSM_FRONTEND_DAI_MULTIMEDIA4) };
+
+static const struct snd_kcontrol_new mmul5_mixer_controls[] = {
+	Q6ROUTING_TX_MIXERS(MSM_FRONTEND_DAI_MULTIMEDIA5) };
+
+static const struct snd_kcontrol_new mmul6_mixer_controls[] = {
+	Q6ROUTING_TX_MIXERS(MSM_FRONTEND_DAI_MULTIMEDIA6) };
+
+static const struct snd_kcontrol_new mmul7_mixer_controls[] = {
+	Q6ROUTING_TX_MIXERS(MSM_FRONTEND_DAI_MULTIMEDIA7) };
+
+static const struct snd_kcontrol_new mmul8_mixer_controls[] = {
+	Q6ROUTING_TX_MIXERS(MSM_FRONTEND_DAI_MULTIMEDIA8) };
+
+static const struct snd_soc_dapm_widget msm_qdsp6_widgets[] = {
+	/* Frontend AIF */
+	SND_SOC_DAPM_AIF_IN("MM_DL1", "MultiMedia1 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("MM_DL2", "MultiMedia2 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("MM_DL3", "MultiMedia3 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("MM_DL4", "MultiMedia4 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("MM_DL5", "MultiMedia5 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("MM_DL6", "MultiMedia6 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("MM_DL7", "MultiMedia7 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("MM_DL8", "MultiMedia8 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("MM_UL1", "MultiMedia1 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("MM_UL2", "MultiMedia2 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("MM_UL3", "MultiMedia3 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("MM_UL4", "MultiMedia4 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("MM_UL5", "MultiMedia5 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("MM_UL6", "MultiMedia6 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("MM_UL7", "MultiMedia7 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("MM_UL8", "MultiMedia8 Capture", 0, 0, 0, 0),
+
+	/* Mixer definitions */
+	SND_SOC_DAPM_MIXER("HDMI Mixer", SND_SOC_NOPM, 0, 0,
+			   hdmi_mixer_controls,
+			   ARRAY_SIZE(hdmi_mixer_controls)),
+
+	SND_SOC_DAPM_MIXER("SLIMBUS_0_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   slimbus_rx_mixer_controls,
+			   ARRAY_SIZE(slimbus_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SLIMBUS_1_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   slimbus_1_rx_mixer_controls,
+			   ARRAY_SIZE(slimbus_1_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SLIMBUS_2_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   slimbus_2_rx_mixer_controls,
+			   ARRAY_SIZE(slimbus_2_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SLIMBUS_3_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   slimbus_3_rx_mixer_controls,
+			   ARRAY_SIZE(slimbus_3_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SLIMBUS_4_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   slimbus_4_rx_mixer_controls,
+			   ARRAY_SIZE(slimbus_4_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SLIMBUS_5_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   slimbus_5_rx_mixer_controls,
+			    ARRAY_SIZE(slimbus_5_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SLIMBUS_6_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   slimbus_6_rx_mixer_controls,
+			   ARRAY_SIZE(slimbus_6_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRI_MI2S_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   primary_mi2s_rx_mixer_controls,
+			   ARRAY_SIZE(primary_mi2s_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SEC_MI2S_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   secondary_mi2s_rx_mixer_controls,
+			   ARRAY_SIZE(secondary_mi2s_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUAT_MI2S_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   quaternary_mi2s_rx_mixer_controls,
+			   ARRAY_SIZE(quaternary_mi2s_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("TERT_MI2S_RX Audio Mixer", SND_SOC_NOPM, 0, 0,
+			   tertiary_mi2s_rx_mixer_controls,
+			   ARRAY_SIZE(tertiary_mi2s_rx_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRIMARY_TDM_RX_0 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				pri_tdm_rx_0_mixer_controls,
+				ARRAY_SIZE(pri_tdm_rx_0_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRIMARY_TDM_RX_1 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				pri_tdm_rx_1_mixer_controls,
+				ARRAY_SIZE(pri_tdm_rx_1_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRIMARY_TDM_RX_2 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				pri_tdm_rx_2_mixer_controls,
+				ARRAY_SIZE(pri_tdm_rx_2_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRIMARY_TDM_RX_3 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				pri_tdm_rx_3_mixer_controls,
+				ARRAY_SIZE(pri_tdm_rx_3_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRIMARY_TDM_RX_4 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				pri_tdm_rx_4_mixer_controls,
+				ARRAY_SIZE(pri_tdm_rx_4_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRIMARY_TDM_RX_5 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				pri_tdm_rx_5_mixer_controls,
+				ARRAY_SIZE(pri_tdm_rx_5_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRIMARY_TDM_RX_6 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				pri_tdm_rx_6_mixer_controls,
+				ARRAY_SIZE(pri_tdm_rx_6_mixer_controls)),
+	SND_SOC_DAPM_MIXER("PRIMARY_TDM_RX_7 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				pri_tdm_rx_7_mixer_controls,
+				ARRAY_SIZE(pri_tdm_rx_7_mixer_controls)),
+
+	SND_SOC_DAPM_MIXER("SEC_TDM_RX_0 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				sec_tdm_rx_0_mixer_controls,
+				ARRAY_SIZE(sec_tdm_rx_0_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SEC_TDM_RX_1 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				sec_tdm_rx_1_mixer_controls,
+				ARRAY_SIZE(sec_tdm_rx_1_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SEC_TDM_RX_2 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				sec_tdm_rx_2_mixer_controls,
+				ARRAY_SIZE(sec_tdm_rx_2_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SEC_TDM_RX_3 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				sec_tdm_rx_3_mixer_controls,
+				ARRAY_SIZE(sec_tdm_rx_3_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SEC_TDM_RX_4 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				sec_tdm_rx_4_mixer_controls,
+				ARRAY_SIZE(sec_tdm_rx_4_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SEC_TDM_RX_5 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				sec_tdm_rx_5_mixer_controls,
+				ARRAY_SIZE(sec_tdm_rx_5_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SEC_TDM_RX_6 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				sec_tdm_rx_6_mixer_controls,
+				ARRAY_SIZE(sec_tdm_rx_6_mixer_controls)),
+	SND_SOC_DAPM_MIXER("SEC_TDM_RX_7 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				sec_tdm_rx_7_mixer_controls,
+				ARRAY_SIZE(sec_tdm_rx_7_mixer_controls)),
+
+	SND_SOC_DAPM_MIXER("TERT_TDM_RX_0 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				tert_tdm_rx_0_mixer_controls,
+				ARRAY_SIZE(tert_tdm_rx_0_mixer_controls)),
+	SND_SOC_DAPM_MIXER("TERT_TDM_RX_1 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				tert_tdm_rx_1_mixer_controls,
+				ARRAY_SIZE(tert_tdm_rx_1_mixer_controls)),
+	SND_SOC_DAPM_MIXER("TERT_TDM_RX_2 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				tert_tdm_rx_2_mixer_controls,
+				ARRAY_SIZE(tert_tdm_rx_2_mixer_controls)),
+	SND_SOC_DAPM_MIXER("TERT_TDM_RX_3 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				tert_tdm_rx_3_mixer_controls,
+				ARRAY_SIZE(tert_tdm_rx_3_mixer_controls)),
+	SND_SOC_DAPM_MIXER("TERT_TDM_RX_4 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				tert_tdm_rx_4_mixer_controls,
+				ARRAY_SIZE(tert_tdm_rx_4_mixer_controls)),
+	SND_SOC_DAPM_MIXER("TERT_TDM_RX_5 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				tert_tdm_rx_5_mixer_controls,
+				ARRAY_SIZE(tert_tdm_rx_5_mixer_controls)),
+	SND_SOC_DAPM_MIXER("TERT_TDM_RX_6 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				tert_tdm_rx_6_mixer_controls,
+				ARRAY_SIZE(tert_tdm_rx_6_mixer_controls)),
+	SND_SOC_DAPM_MIXER("TERT_TDM_RX_7 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				tert_tdm_rx_7_mixer_controls,
+				ARRAY_SIZE(tert_tdm_rx_7_mixer_controls)),
+
+	SND_SOC_DAPM_MIXER("QUAT_TDM_RX_0 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quat_tdm_rx_0_mixer_controls,
+				ARRAY_SIZE(quat_tdm_rx_0_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUAT_TDM_RX_1 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quat_tdm_rx_1_mixer_controls,
+				ARRAY_SIZE(quat_tdm_rx_1_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUAT_TDM_RX_2 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quat_tdm_rx_2_mixer_controls,
+				ARRAY_SIZE(quat_tdm_rx_2_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUAT_TDM_RX_3 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quat_tdm_rx_3_mixer_controls,
+				ARRAY_SIZE(quat_tdm_rx_3_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUAT_TDM_RX_4 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quat_tdm_rx_4_mixer_controls,
+				ARRAY_SIZE(quat_tdm_rx_4_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUAT_TDM_RX_5 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quat_tdm_rx_5_mixer_controls,
+				ARRAY_SIZE(quat_tdm_rx_5_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUAT_TDM_RX_6 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quat_tdm_rx_6_mixer_controls,
+				ARRAY_SIZE(quat_tdm_rx_6_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUAT_TDM_RX_7 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quat_tdm_rx_7_mixer_controls,
+				ARRAY_SIZE(quat_tdm_rx_7_mixer_controls)),
+
+	SND_SOC_DAPM_MIXER("QUIN_TDM_RX_0 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quin_tdm_rx_0_mixer_controls,
+				ARRAY_SIZE(quin_tdm_rx_0_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUIN_TDM_RX_1 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quin_tdm_rx_1_mixer_controls,
+				ARRAY_SIZE(quin_tdm_rx_1_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUIN_TDM_RX_2 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quin_tdm_rx_2_mixer_controls,
+				ARRAY_SIZE(quin_tdm_rx_2_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUIN_TDM_RX_3 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quin_tdm_rx_3_mixer_controls,
+				ARRAY_SIZE(quin_tdm_rx_3_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUIN_TDM_RX_4 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quin_tdm_rx_4_mixer_controls,
+				ARRAY_SIZE(quin_tdm_rx_4_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUIN_TDM_RX_5 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quin_tdm_rx_5_mixer_controls,
+				ARRAY_SIZE(quin_tdm_rx_5_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUIN_TDM_RX_6 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quin_tdm_rx_6_mixer_controls,
+				ARRAY_SIZE(quin_tdm_rx_6_mixer_controls)),
+	SND_SOC_DAPM_MIXER("QUIN_TDM_RX_7 Audio Mixer", SND_SOC_NOPM, 0, 0,
+				quin_tdm_rx_7_mixer_controls,
+				ARRAY_SIZE(quin_tdm_rx_7_mixer_controls)),
+	SND_SOC_DAPM_MIXER("MultiMedia1 Mixer", SND_SOC_NOPM, 0, 0,
+		mmul1_mixer_controls, ARRAY_SIZE(mmul1_mixer_controls)),
+	SND_SOC_DAPM_MIXER("MultiMedia2 Mixer", SND_SOC_NOPM, 0, 0,
+		mmul2_mixer_controls, ARRAY_SIZE(mmul2_mixer_controls)),
+	SND_SOC_DAPM_MIXER("MultiMedia3 Mixer", SND_SOC_NOPM, 0, 0,
+		mmul3_mixer_controls, ARRAY_SIZE(mmul3_mixer_controls)),
+	SND_SOC_DAPM_MIXER("MultiMedia4 Mixer", SND_SOC_NOPM, 0, 0,
+		mmul4_mixer_controls, ARRAY_SIZE(mmul4_mixer_controls)),
+	SND_SOC_DAPM_MIXER("MultiMedia5 Mixer", SND_SOC_NOPM, 0, 0,
+		mmul5_mixer_controls, ARRAY_SIZE(mmul5_mixer_controls)),
+	SND_SOC_DAPM_MIXER("MultiMedia6 Mixer", SND_SOC_NOPM, 0, 0,
+		mmul6_mixer_controls, ARRAY_SIZE(mmul6_mixer_controls)),
+	SND_SOC_DAPM_MIXER("MultiMedia7 Mixer", SND_SOC_NOPM, 0, 0,
+		mmul7_mixer_controls, ARRAY_SIZE(mmul7_mixer_controls)),
+	SND_SOC_DAPM_MIXER("MultiMedia8 Mixer", SND_SOC_NOPM, 0, 0,
+		mmul8_mixer_controls, ARRAY_SIZE(mmul8_mixer_controls)),
+
+};
+
+static const struct snd_soc_dapm_route intercon[] = {
+	Q6ROUTING_RX_DAPM_ROUTE("HDMI Mixer", "HDMI_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("SLIMBUS_0_RX Audio Mixer", "SLIMBUS_0_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("SLIMBUS_1_RX Audio Mixer", "SLIMBUS_1_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("SLIMBUS_2_RX Audio Mixer", "SLIMBUS_2_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("SLIMBUS_3_RX Audio Mixer", "SLIMBUS_3_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("SLIMBUS_4_RX Audio Mixer", "SLIMBUS_4_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("SLIMBUS_5_RX Audio Mixer", "SLIMBUS_5_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("SLIMBUS_6_RX Audio Mixer", "SLIMBUS_6_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_MI2S_RX Audio Mixer", "QUAT_MI2S_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_MI2S_RX Audio Mixer", "TERT_MI2S_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_MI2S_RX Audio Mixer", "SEC_MI2S_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRI_MI2S_RX Audio Mixer", "PRI_MI2S_RX"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRIMARY_TDM_RX_0 Audio Mixer",
+				"PRIMARY_TDM_RX_0"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRIMARY_TDM_RX_1 Audio Mixer",
+				"PRIMARY_TDM_RX_1"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRIMARY_TDM_RX_2 Audio Mixer",
+				"PRIMARY_TDM_RX_2"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRIMARY_TDM_RX_3 Audio Mixer",
+				"PRIMARY_TDM_RX_3"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRIMARY_TDM_RX_4 Audio Mixer",
+				"PRIMARY_TDM_RX_4"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRIMARY_TDM_RX_5 Audio Mixer",
+				"PRIMARY_TDM_RX_5"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRIMARY_TDM_RX_6 Audio Mixer",
+				"PRIMARY_TDM_RX_6"),
+	Q6ROUTING_RX_DAPM_ROUTE("PRIMARY_TDM_RX_7 Audio Mixer",
+				"PRIMARY_TDM_RX_7"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_TDM_RX_0 Audio Mixer", "SEC_TDM_RX_0"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_TDM_RX_1 Audio Mixer", "SEC_TDM_RX_1"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_TDM_RX_2 Audio Mixer", "SEC_TDM_RX_2"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_TDM_RX_3 Audio Mixer", "SEC_TDM_RX_3"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_TDM_RX_4 Audio Mixer", "SEC_TDM_RX_4"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_TDM_RX_5 Audio Mixer", "SEC_TDM_RX_5"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_TDM_RX_6 Audio Mixer", "SEC_TDM_RX_6"),
+	Q6ROUTING_RX_DAPM_ROUTE("SEC_TDM_RX_7 Audio Mixer", "SEC_TDM_RX_7"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_TDM_RX_0 Audio Mixer", "TERT_TDM_RX_0"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_TDM_RX_1 Audio Mixer", "TERT_TDM_RX_1"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_TDM_RX_2 Audio Mixer", "TERT_TDM_RX_2"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_TDM_RX_3 Audio Mixer", "TERT_TDM_RX_3"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_TDM_RX_4 Audio Mixer", "TERT_TDM_RX_4"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_TDM_RX_5 Audio Mixer", "TERT_TDM_RX_5"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_TDM_RX_6 Audio Mixer", "TERT_TDM_RX_6"),
+	Q6ROUTING_RX_DAPM_ROUTE("TERT_TDM_RX_7 Audio Mixer", "TERT_TDM_RX_7"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_TDM_RX_0 Audio Mixer", "QUAT_TDM_RX_0"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_TDM_RX_1 Audio Mixer", "QUAT_TDM_RX_1"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_TDM_RX_2 Audio Mixer", "QUAT_TDM_RX_2"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_TDM_RX_3 Audio Mixer", "QUAT_TDM_RX_3"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_TDM_RX_4 Audio Mixer", "QUAT_TDM_RX_4"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_TDM_RX_5 Audio Mixer", "QUAT_TDM_RX_5"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_TDM_RX_6 Audio Mixer", "QUAT_TDM_RX_6"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUAT_TDM_RX_7 Audio Mixer", "QUAT_TDM_RX_7"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUIN_TDM_RX_0 Audio Mixer", "QUIN_TDM_RX_0"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUIN_TDM_RX_1 Audio Mixer", "QUIN_TDM_RX_1"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUIN_TDM_RX_2 Audio Mixer", "QUIN_TDM_RX_2"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUIN_TDM_RX_3 Audio Mixer", "QUIN_TDM_RX_3"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUIN_TDM_RX_4 Audio Mixer", "QUIN_TDM_RX_4"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUIN_TDM_RX_5 Audio Mixer", "QUIN_TDM_RX_5"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUIN_TDM_RX_6 Audio Mixer", "QUIN_TDM_RX_6"),
+	Q6ROUTING_RX_DAPM_ROUTE("QUIN_TDM_RX_7 Audio Mixer", "QUIN_TDM_RX_7"),
+	Q6ROUTING_TX_DAPM_ROUTE("MultiMedia1 Mixer"),
+	Q6ROUTING_TX_DAPM_ROUTE("MultiMedia2 Mixer"),
+	Q6ROUTING_TX_DAPM_ROUTE("MultiMedia3 Mixer"),
+	Q6ROUTING_TX_DAPM_ROUTE("MultiMedia4 Mixer"),
+	Q6ROUTING_TX_DAPM_ROUTE("MultiMedia5 Mixer"),
+	Q6ROUTING_TX_DAPM_ROUTE("MultiMedia6 Mixer"),
+	Q6ROUTING_TX_DAPM_ROUTE("MultiMedia7 Mixer"),
+	Q6ROUTING_TX_DAPM_ROUTE("MultiMedia8 Mixer"),
+
+	{"MM_UL1", NULL, "MultiMedia1 Mixer"},
+	{"MM_UL2", NULL, "MultiMedia2 Mixer"},
+	{"MM_UL3", NULL, "MultiMedia3 Mixer"},
+	{"MM_UL4", NULL, "MultiMedia4 Mixer"},
+	{"MM_UL5", NULL, "MultiMedia5 Mixer"},
+	{"MM_UL6", NULL, "MultiMedia6 Mixer"},
+	{"MM_UL7", NULL, "MultiMedia7 Mixer"},
+	{"MM_UL8", NULL, "MultiMedia8 Mixer"},
+};
+
+static int routing_hw_params(struct snd_pcm_substream *substream,
+				     struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_component *c = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
+	struct msm_routing_data *data = dev_get_drvdata(c->dev);
+	unsigned int be_id = rtd->cpu_dai->id;
+	struct session_data *session;
+	int path_type;
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		path_type = ADM_PATH_PLAYBACK;
+	else
+		path_type = ADM_PATH_LIVE_REC;
+
+	if (be_id > AFE_MAX_PORTS)
+		return -EINVAL;
+
+	session = &data->port_data[be_id];
+
+	mutex_lock(&data->lock);
+
+	session->path_type = path_type;
+	session->sample_rate = params_rate(params);
+	session->channels = params_channels(params);
+
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+			session->bits_per_sample = 16;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+			session->bits_per_sample = 24;
+		break;
+	default:
+		break;
+	}
+
+	mutex_unlock(&data->lock);
+	return 0;
+}
+
+static struct snd_pcm_ops q6pcm_routing_ops = {
+	.hw_params = routing_hw_params,
+};
+
+static int msm_routing_probe(struct snd_soc_component *c)
+{
+	int i;
+
+	for (i = 0; i < MAX_SESSIONS; i++)
+		routing_data->sessions[i].port_id = -1;
+
+	return 0;
+}
+
+static const struct snd_soc_component_driver msm_soc_routing_component = {
+	.ops = &q6pcm_routing_ops,
+	.probe = msm_routing_probe,
+	.name = DRV_NAME,
+	.dapm_widgets = msm_qdsp6_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(msm_qdsp6_widgets),
+	.dapm_routes = intercon,
+	.num_dapm_routes = ARRAY_SIZE(intercon),
+};
+
+static int q6routing_dai_bind(struct device *dev, struct device *master,
+			      void *data)
+{
+	routing_data = kzalloc(sizeof(*routing_data), GFP_KERNEL);
+	if (!routing_data)
+		return -ENOMEM;
+
+	routing_data->dev = dev;
+
+	mutex_init(&routing_data->lock);
+	dev_set_drvdata(dev, routing_data);
+
+	return snd_soc_register_component(dev, &msm_soc_routing_component,
+					  NULL, 0);
+}
+
+static void q6routing_dai_unbind(struct device *dev, struct device *master,
+				 void *d)
+{
+	struct msm_routing_data *data = dev_get_drvdata(dev);
+
+	snd_soc_unregister_component(dev);
+
+	kfree(data);
+
+	routing_data = NULL;
+}
+
+static const struct component_ops q6routing_dai_comp_ops = {
+	.bind   = q6routing_dai_bind,
+	.unbind = q6routing_dai_unbind,
+};
+
+static int q6pcm_routing_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &q6routing_dai_comp_ops);
+}
+
+static int q6pcm_routing_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &q6routing_dai_comp_ops);
+	return 0;
+}
+
+static struct platform_driver q6pcm_routing_platform_driver = {
+	.driver = {
+		.name = "q6routing",
+	},
+	.probe = q6pcm_routing_probe,
+	.remove = q6pcm_routing_remove,
+};
+module_platform_driver(q6pcm_routing_platform_driver);
+
+MODULE_DESCRIPTION("Q6 Routing platform");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/qdsp6/q6routing.h b/sound/soc/qcom/qdsp6/q6routing.h
new file mode 100644
index 000000000000..35514e651130
--- /dev/null
+++ b/sound/soc/qcom/qdsp6/q6routing.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _Q6_PCM_ROUTING_H
+#define _Q6_PCM_ROUTING_H
+
+int q6routing_stream_open(int fedai_id, int perf_mode,
+			   int stream_id, int stream_type);
+void q6routing_stream_close(int fedai_id, int stream_type);
+
+#endif /*_Q6_PCM_ROUTING_H */
diff --git a/sound/soc/rockchip/rk3399_gru_sound.c b/sound/soc/rockchip/rk3399_gru_sound.c
index 9a10181a0811..f184168f9a41 100644
--- a/sound/soc/rockchip/rk3399_gru_sound.c
+++ b/sound/soc/rockchip/rk3399_gru_sound.c
@@ -220,45 +220,6 @@ static int rockchip_sound_da7219_init(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static int rockchip_sound_cdndp_hw_params(struct snd_pcm_substream *substream,
-					  struct snd_pcm_hw_params *params)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	struct snd_soc_dai *codec_dai = rtd->codec_dai;
-	int mclk, ret;
-
-	/* in bypass mode, the mclk has to be one of the frequencies below */
-	switch (params_rate(params)) {
-	case 8000:
-	case 16000:
-	case 24000:
-	case 32000:
-	case 48000:
-	case 64000:
-	case 96000:
-		mclk = 12288000;
-		break;
-	case 11025:
-	case 22050:
-	case 44100:
-	case 88200:
-		mclk = 11289600;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ret = snd_soc_dai_set_sysclk(cpu_dai, 0, mclk,
-				     SND_SOC_CLOCK_OUT);
-	if (ret < 0) {
-		dev_err(codec_dai->dev, "Can't set cpu clock out %d\n", ret);
-		return ret;
-	}
-
-	return 0;
-}
-
 static int rockchip_sound_dmic_hw_params(struct snd_pcm_substream *substream,
 			     struct snd_pcm_hw_params *params)
 {
@@ -293,10 +254,6 @@ static const struct snd_soc_ops rockchip_sound_da7219_ops = {
 	.hw_params = rockchip_sound_da7219_hw_params,
 };
 
-static const struct snd_soc_ops rockchip_sound_cdndp_ops = {
-	.hw_params = rockchip_sound_cdndp_hw_params,
-};
-
 static const struct snd_soc_ops rockchip_sound_dmic_ops = {
 	.hw_params = rockchip_sound_dmic_hw_params,
 };
@@ -323,8 +280,7 @@ static const struct snd_soc_dai_link rockchip_dais[] = {
 	[DAILINK_CDNDP] = {
 		.name = "DP",
 		.stream_name = "DP PCM",
-		.codec_dai_name = "i2s-hifi",
-		.ops = &rockchip_sound_cdndp_ops,
+		.codec_dai_name = "spdif-hifi",
 		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
 			SND_SOC_DAIFMT_CBS_CFS,
 	},
diff --git a/sound/soc/sh/Kconfig b/sound/soc/sh/Kconfig
index 1aa5cd77ca24..0ae0800bf3a8 100644
--- a/sound/soc/sh/Kconfig
+++ b/sound/soc/sh/Kconfig
@@ -1,5 +1,5 @@
-menu "SoC Audio support for SuperH"
-	depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST
+menu "SoC Audio support for Renesas SoCs"
+	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 
 config SND_SOC_PCM_SH7760
 	tristate "SoC Audio support for Renesas SH7760"
@@ -28,7 +28,7 @@ config SND_SOC_SH4_FSI
 
 config SND_SOC_SH4_SIU
 	tristate
-	depends on (SUPERH || ARCH_SHMOBILE) && HAVE_CLK
+	depends on ARCH_SHMOBILE && HAVE_CLK
 	select DMA_ENGINE
 	select DMADEVICES
 	select SH_DMAE
diff --git a/sound/soc/sh/rcar/cmd.c b/sound/soc/sh/rcar/cmd.c
index f1d4fb566892..4221937ae79b 100644
--- a/sound/soc/sh/rcar/cmd.c
+++ b/sound/soc/sh/rcar/cmd.c
@@ -125,6 +125,13 @@ static struct rsnd_mod_ops rsnd_cmd_ops = {
 	.stop	= rsnd_cmd_stop,
 };
 
+static struct rsnd_mod *rsnd_cmd_mod_get(struct rsnd_priv *priv, int id)
+{
+	if (WARN_ON(id < 0 || id >= rsnd_cmd_nr(priv)))
+		id = 0;
+
+	return rsnd_mod_get((struct rsnd_cmd *)(priv->cmd) + id);
+}
 int rsnd_cmd_attach(struct rsnd_dai_stream *io, int id)
 {
 	struct rsnd_priv *priv = rsnd_io_to_priv(io);
@@ -133,14 +140,6 @@ int rsnd_cmd_attach(struct rsnd_dai_stream *io, int id)
 	return rsnd_dai_connect(mod, io, mod->type);
 }
 
-struct rsnd_mod *rsnd_cmd_mod_get(struct rsnd_priv *priv, int id)
-{
-	if (WARN_ON(id < 0 || id >= rsnd_cmd_nr(priv)))
-		id = 0;
-
-	return rsnd_mod_get((struct rsnd_cmd *)(priv->cmd) + id);
-}
-
 int rsnd_cmd_probe(struct rsnd_priv *priv)
 {
 	struct device *dev = rsnd_priv_to_dev(priv);
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 6a76688a8ba9..af04d41a4274 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -111,7 +111,7 @@
 static const struct of_device_id rsnd_of_match[] = {
 	{ .compatible = "renesas,rcar_sound-gen1", .data = (void *)RSND_GEN1 },
 	{ .compatible = "renesas,rcar_sound-gen2", .data = (void *)RSND_GEN2 },
-	{ .compatible = "renesas,rcar_sound-gen3", .data = (void *)RSND_GEN2 }, /* gen2 compatible */
+	{ .compatible = "renesas,rcar_sound-gen3", .data = (void *)RSND_GEN3 },
 	{},
 };
 MODULE_DEVICE_TABLE(of, rsnd_of_match);
@@ -1352,6 +1352,37 @@ int rsnd_kctrl_new(struct rsnd_mod *mod,
 #define PREALLOC_BUFFER		(32 * 1024)
 #define PREALLOC_BUFFER_MAX	(32 * 1024)
 
+static int rsnd_preallocate_pages(struct snd_soc_pcm_runtime *rtd,
+				  struct rsnd_dai_stream *io,
+				  int stream)
+{
+	struct rsnd_priv *priv = rsnd_io_to_priv(io);
+	struct device *dev = rsnd_priv_to_dev(priv);
+	struct snd_pcm_substream *substream;
+	int err;
+
+	/*
+	 * use Audio-DMAC dev if we can use IPMMU
+	 * see
+	 *	rsnd_dmaen_attach()
+	 */
+	if (io->dmac_dev)
+		dev = io->dmac_dev;
+
+	for (substream = rtd->pcm->streams[stream].substream;
+	     substream;
+	     substream = substream->next) {
+		err = snd_pcm_lib_preallocate_pages(substream,
+					SNDRV_DMA_TYPE_DEV,
+					dev,
+					PREALLOC_BUFFER, PREALLOC_BUFFER_MAX);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
 static int rsnd_pcm_new(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_dai *dai = rtd->cpu_dai;
@@ -1366,11 +1397,17 @@ static int rsnd_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	if (ret)
 		return ret;
 
-	return snd_pcm_lib_preallocate_pages_for_all(
-		rtd->pcm,
-		SNDRV_DMA_TYPE_DEV,
-		rtd->card->snd_card->dev,
-		PREALLOC_BUFFER, PREALLOC_BUFFER_MAX);
+	ret = rsnd_preallocate_pages(rtd, &rdai->playback,
+				     SNDRV_PCM_STREAM_PLAYBACK);
+	if (ret)
+		return ret;
+
+	ret = rsnd_preallocate_pages(rtd, &rdai->capture,
+				     SNDRV_PCM_STREAM_CAPTURE);
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
 static const struct snd_soc_component_driver rsnd_soc_component = {
@@ -1536,7 +1573,7 @@ static int rsnd_remove(struct platform_device *pdev)
 	return ret;
 }
 
-static int rsnd_suspend(struct device *dev)
+static int __maybe_unused rsnd_suspend(struct device *dev)
 {
 	struct rsnd_priv *priv = dev_get_drvdata(dev);
 
@@ -1545,7 +1582,7 @@ static int rsnd_suspend(struct device *dev)
 	return 0;
 }
 
-static int rsnd_resume(struct device *dev)
+static int __maybe_unused rsnd_resume(struct device *dev)
 {
 	struct rsnd_priv *priv = dev_get_drvdata(dev);
 
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index 41de23417c4a..ef82b94d038b 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -253,6 +253,13 @@ static int rsnd_dmaen_attach(struct rsnd_dai_stream *io,
 		return -EAGAIN;
 	}
 
+	/*
+	 * use it for IPMMU if needed
+	 * see
+	 *	rsnd_preallocate_pages()
+	 */
+	io->dmac_dev = chan->device->dev;
+
 	dma_release_channel(chan);
 
 	dmac->dmaen_num++;
@@ -695,7 +702,7 @@ static int rsnd_dma_alloc(struct rsnd_dai_stream *io, struct rsnd_mod *mod,
 
 	rsnd_dma_of_path(mod, io, is_play, &mod_from, &mod_to);
 
-	/* for Gen2 */
+	/* for Gen2 or later */
 	if (mod_from && mod_to) {
 		ops	= &rsnd_dmapp_ops;
 		attach	= rsnd_dmapp_attach;
@@ -773,7 +780,7 @@ int rsnd_dma_probe(struct rsnd_priv *priv)
 		return 0;
 
 	/*
-	 * for Gen2
+	 * for Gen2 or later
 	 */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "audmapp");
 	dmac = devm_kzalloc(dev, sizeof(*dmac), GFP_KERNEL);
diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c
index f04c4100043a..25642e92dae0 100644
--- a/sound/soc/sh/rcar/gen.c
+++ b/sound/soc/sh/rcar/gen.c
@@ -414,7 +414,8 @@ int rsnd_gen_probe(struct rsnd_priv *priv)
 	ret = -ENODEV;
 	if (rsnd_is_gen1(priv))
 		ret = rsnd_gen1_probe(priv);
-	else if (rsnd_is_gen2(priv))
+	else if (rsnd_is_gen2(priv) ||
+		 rsnd_is_gen3(priv))
 		ret = rsnd_gen2_probe(priv);
 
 	if (ret < 0)
diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h
index 172c8d612890..6d7280d2d9be 100644
--- a/sound/soc/sh/rcar/rsnd.h
+++ b/sound/soc/sh/rcar/rsnd.h
@@ -435,6 +435,7 @@ struct rsnd_dai_stream {
 	struct snd_pcm_substream *substream;
 	struct rsnd_mod *mod[RSND_MOD_MAX];
 	struct rsnd_dai *rdai;
+	struct device *dmac_dev; /* for IPMMU */
 	u32 parent_ssi_status;
 };
 #define rsnd_io_to_mod(io, i)	((i) < RSND_MOD_MAX ? (io)->mod[(i)] : NULL)
@@ -538,6 +539,7 @@ struct rsnd_priv {
 #define RSND_GEN_MASK	(0xF << 0)
 #define RSND_GEN1	(1 << 0)
 #define RSND_GEN2	(2 << 0)
+#define RSND_GEN3	(3 << 0)
 
 	/*
 	 * below value will be filled on rsnd_gen_probe()
@@ -609,6 +611,7 @@ struct rsnd_priv {
 
 #define rsnd_is_gen1(priv)	(((priv)->flags & RSND_GEN_MASK) == RSND_GEN1)
 #define rsnd_is_gen2(priv)	(((priv)->flags & RSND_GEN_MASK) == RSND_GEN2)
+#define rsnd_is_gen3(priv)	(((priv)->flags & RSND_GEN_MASK) == RSND_GEN3)
 
 #define rsnd_flags_has(p, f) ((p)->flags & (f))
 #define rsnd_flags_set(p, f) ((p)->flags |= (f))
@@ -775,7 +778,6 @@ struct rsnd_mod *rsnd_dvc_mod_get(struct rsnd_priv *priv, int id);
 int rsnd_cmd_probe(struct rsnd_priv *priv);
 void rsnd_cmd_remove(struct rsnd_priv *priv);
 int rsnd_cmd_attach(struct rsnd_dai_stream *io, int id);
-struct rsnd_mod *rsnd_cmd_mod_get(struct rsnd_priv *priv, int id);
 
 void rsnd_mod_make_sure(struct rsnd_mod *mod, enum rsnd_mod_type type);
 #ifdef DEBUG
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 333b802681ad..9538f76f8e20 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -171,7 +171,7 @@ static void rsnd_ssi_status_check(struct rsnd_mod *mod,
 		if (status & bit)
 			return;
 
-		udelay(50);
+		udelay(5);
 	}
 
 	dev_warn(dev, "%s[%d] status check failed\n",
@@ -1004,19 +1004,26 @@ static void __rsnd_ssi_parse_hdmi_connection(struct rsnd_priv *priv,
 	struct device *dev = rsnd_priv_to_dev(priv);
 	struct rsnd_mod *mod = rsnd_io_to_mod_ssi(io);
 	struct rsnd_ssi *ssi;
+	struct device_node *remote_node = of_graph_get_port_parent(remote_ep);
+
+	/* support Gen3 only */
+	if (!rsnd_is_gen3(priv))
+		return;
 
 	if (!mod)
 		return;
 
 	ssi  = rsnd_mod_to_ssi(mod);
 
-	if (strstr(remote_ep->full_name, "hdmi0")) {
+	/* HDMI0 */
+	if (strstr(remote_node->full_name, "hdmi@fead0000")) {
 		rsnd_flags_set(ssi, RSND_SSI_HDMI0);
 		dev_dbg(dev, "%s[%d] connected to HDMI0\n",
 			 rsnd_mod_name(mod), rsnd_mod_id(mod));
 	}
 
-	if (strstr(remote_ep->full_name, "hdmi1")) {
+	/* HDMI1 */
+	if (strstr(remote_node->full_name, "hdmi@feae0000")) {
 		rsnd_flags_set(ssi, RSND_SSI_HDMI1);
 		dev_dbg(dev, "%s[%d] connected to HDMI1\n",
 			rsnd_mod_name(mod), rsnd_mod_id(mod));
diff --git a/sound/soc/soc-cache.c b/sound/soc/soc-cache.c
deleted file mode 100644
index 07f43356f963..000000000000
--- a/sound/soc/soc-cache.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * soc-cache.c  --  ASoC register cache helpers
- *
- * Copyright 2009 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
-
-#include <sound/soc.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-
-int snd_soc_cache_init(struct snd_soc_codec *codec)
-{
-	const struct snd_soc_codec_driver *codec_drv = codec->driver;
-	size_t reg_size;
-
-	reg_size = codec_drv->reg_cache_size * codec_drv->reg_word_size;
-
-	if (!reg_size)
-		return 0;
-
-	dev_dbg(codec->dev, "ASoC: Initializing cache for %s codec\n",
-				codec->component.name);
-
-	if (codec_drv->reg_cache_default)
-		codec->reg_cache = kmemdup(codec_drv->reg_cache_default,
-					   reg_size, GFP_KERNEL);
-	else
-		codec->reg_cache = kzalloc(reg_size, GFP_KERNEL);
-	if (!codec->reg_cache)
-		return -ENOMEM;
-
-	return 0;
-}
-
-/*
- * NOTE: keep in mind that this function might be called
- * multiple times.
- */
-int snd_soc_cache_exit(struct snd_soc_codec *codec)
-{
-	dev_dbg(codec->dev, "ASoC: Destroying cache for %s codec\n",
-			codec->component.name);
-	kfree(codec->reg_cache);
-	codec->reg_cache = NULL;
-	return 0;
-}
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index 82402688bd8e..e095115fa9f9 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -26,56 +26,79 @@
 #include <sound/initval.h>
 #include <sound/soc-dpcm.h>
 
-static int soc_compr_open(struct snd_compr_stream *cstream)
+static int soc_compr_components_open(struct snd_compr_stream *cstream,
+				     struct snd_soc_component **last)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
-	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	int ret = 0, __ret;
+	int ret;
 
-	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
+	for_each_rtdcom(rtd, rtdcom) {
+		component = rtdcom->component;
 
-	if (cpu_dai->driver->cops && cpu_dai->driver->cops->startup) {
-		ret = cpu_dai->driver->cops->startup(cstream, cpu_dai);
-		if (ret < 0) {
-			dev_err(cpu_dai->dev,
-				"Compress ASoC: can't open interface %s: %d\n",
-				cpu_dai->name, ret);
-			goto out;
-		}
-	}
+		if (!component->driver->compr_ops ||
+		    !component->driver->compr_ops->open)
+			continue;
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->open) {
-		ret = platform->driver->compr_ops->open(cstream);
+		ret = component->driver->compr_ops->open(cstream);
 		if (ret < 0) {
-			dev_err(platform->dev,
+			dev_err(component->dev,
 				"Compress ASoC: can't open platform %s: %d\n",
-				platform->component.name, ret);
-			goto plat_err;
+				component->name, ret);
+
+			*last = component;
+			return ret;
 		}
 	}
 
+	*last = NULL;
+	return 0;
+}
+
+static int soc_compr_components_free(struct snd_compr_stream *cstream,
+				     struct snd_soc_component *last)
+{
+	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
+	struct snd_soc_component *component;
+	struct snd_soc_rtdcom_list *rtdcom;
+
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
+		if (component == last)
+			break;
 
 		if (!component->driver->compr_ops ||
-		    !component->driver->compr_ops->open)
+		    !component->driver->compr_ops->free)
 			continue;
 
-		__ret = component->driver->compr_ops->open(cstream);
-		if (__ret < 0) {
-			dev_err(component->dev,
-				"Compress ASoC: can't open platform %s: %d\n",
-				component->name, __ret);
-			ret = __ret;
+		component->driver->compr_ops->free(cstream);
+	}
+
+	return 0;
+}
+
+static int soc_compr_open(struct snd_compr_stream *cstream)
+{
+	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
+	struct snd_soc_component *component;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	int ret;
+
+	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
+
+	if (cpu_dai->driver->cops && cpu_dai->driver->cops->startup) {
+		ret = cpu_dai->driver->cops->startup(cstream, cpu_dai);
+		if (ret < 0) {
+			dev_err(cpu_dai->dev,
+				"Compress ASoC: can't open interface %s: %d\n",
+				cpu_dai->name, ret);
+			goto out;
 		}
 	}
+
+	ret = soc_compr_components_open(cstream, &component);
 	if (ret < 0)
 		goto machine_err;
 
@@ -96,23 +119,8 @@ static int soc_compr_open(struct snd_compr_stream *cstream)
 	return 0;
 
 machine_err:
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
-		if (!component->driver->compr_ops ||
-		    !component->driver->compr_ops->free)
-			continue;
+	soc_compr_components_free(cstream, component);
 
-		component->driver->compr_ops->free(cstream);
-	}
-
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->free)
-		platform->driver->compr_ops->free(cstream);
-plat_err:
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->shutdown)
 		cpu_dai->driver->cops->shutdown(cstream, cpu_dai);
 out:
@@ -125,14 +133,12 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 	struct snd_soc_pcm_runtime *fe = cstream->private_data;
 	struct snd_pcm_substream *fe_substream =
 		 fe->pcm->streams[cstream->direction].substream;
-	struct snd_soc_platform *platform = fe->platform;
 	struct snd_soc_component *component;
-	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = fe->cpu_dai;
 	struct snd_soc_dpcm *dpcm;
 	struct snd_soc_dapm_widget_list *list;
 	int stream;
-	int ret = 0, __ret;
+	int ret;
 
 	if (cstream->direction == SND_COMPRESS_PLAYBACK)
 		stream = SNDRV_PCM_STREAM_PLAYBACK;
@@ -151,35 +157,7 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 		}
 	}
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->open) {
-		ret = platform->driver->compr_ops->open(cstream);
-		if (ret < 0) {
-			dev_err(platform->dev,
-				"Compress ASoC: can't open platform %s: %d\n",
-				platform->component.name, ret);
-			goto plat_err;
-		}
-	}
-
-	for_each_rtdcom(fe, rtdcom) {
-		component = rtdcom->component;
-
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
-		if (!component->driver->compr_ops ||
-		    !component->driver->compr_ops->open)
-			continue;
-
-		__ret = component->driver->compr_ops->open(cstream);
-		if (__ret < 0) {
-			dev_err(component->dev,
-				"Compress ASoC: can't open platform %s: %d\n",
-				component->name, __ret);
-			ret = __ret;
-		}
-	}
+	ret = soc_compr_components_open(cstream, &component);
 	if (ret < 0)
 		goto machine_err;
 
@@ -235,23 +213,8 @@ fe_err:
 	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
 		fe->dai_link->compr_ops->shutdown(cstream);
 machine_err:
-	for_each_rtdcom(fe, rtdcom) {
-		component = rtdcom->component;
-
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
+	soc_compr_components_free(cstream, component);
 
-		if (!component->driver->compr_ops ||
-		    !component->driver->compr_ops->free)
-			continue;
-
-		component->driver->compr_ops->free(cstream);
-	}
-
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->free)
-		platform->driver->compr_ops->free(cstream);
-plat_err:
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->shutdown)
 		cpu_dai->driver->cops->shutdown(cstream, cpu_dai);
 out:
@@ -292,9 +255,6 @@ static void close_delayed_work(struct work_struct *work)
 static int soc_compr_free(struct snd_compr_stream *cstream)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
-	struct snd_soc_component *component;
-	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
 	int stream;
@@ -319,22 +279,7 @@ static int soc_compr_free(struct snd_compr_stream *cstream)
 	if (rtd->dai_link->compr_ops && rtd->dai_link->compr_ops->shutdown)
 		rtd->dai_link->compr_ops->shutdown(cstream);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
-		if (!component->driver->compr_ops ||
-		    !component->driver->compr_ops->free)
-			continue;
-
-		component->driver->compr_ops->free(cstream);
-	}
-
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->free)
-		platform->driver->compr_ops->free(cstream);
+	soc_compr_components_free(cstream, NULL);
 
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->shutdown)
 		cpu_dai->driver->cops->shutdown(cstream, cpu_dai);
@@ -342,8 +287,8 @@ static int soc_compr_free(struct snd_compr_stream *cstream)
 	if (cstream->direction == SND_COMPRESS_PLAYBACK) {
 		if (snd_soc_runtime_ignore_pmdown_time(rtd)) {
 			snd_soc_dapm_stream_event(rtd,
-					SNDRV_PCM_STREAM_PLAYBACK,
-					SND_SOC_DAPM_STREAM_STOP);
+						  SNDRV_PCM_STREAM_PLAYBACK,
+						  SND_SOC_DAPM_STREAM_STOP);
 		} else {
 			rtd->pop_wait = 1;
 			queue_delayed_work(system_power_efficient_wq,
@@ -353,8 +298,8 @@ static int soc_compr_free(struct snd_compr_stream *cstream)
 	} else {
 		/* capture streams can be powered down now */
 		snd_soc_dapm_stream_event(rtd,
-			SNDRV_PCM_STREAM_CAPTURE,
-			SND_SOC_DAPM_STREAM_STOP);
+					  SNDRV_PCM_STREAM_CAPTURE,
+					  SND_SOC_DAPM_STREAM_STOP);
 	}
 
 	mutex_unlock(&rtd->pcm_mutex);
@@ -364,9 +309,6 @@ static int soc_compr_free(struct snd_compr_stream *cstream)
 static int soc_compr_free_fe(struct snd_compr_stream *cstream)
 {
 	struct snd_soc_pcm_runtime *fe = cstream->private_data;
-	struct snd_soc_platform *platform = fe->platform;
-	struct snd_soc_component *component;
-	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = fe->cpu_dai;
 	struct snd_soc_dpcm *dpcm;
 	int stream, ret;
@@ -404,22 +346,7 @@ static int soc_compr_free_fe(struct snd_compr_stream *cstream)
 	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
 		fe->dai_link->compr_ops->shutdown(cstream);
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->free)
-		platform->driver->compr_ops->free(cstream);
-
-	for_each_rtdcom(fe, rtdcom) {
-		component = rtdcom->component;
-
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
-		if (!component->driver->compr_ops ||
-		    !component->driver->compr_ops->free)
-			continue;
-
-		component->driver->compr_ops->free(cstream);
-	}
+	soc_compr_components_free(cstream, NULL);
 
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->shutdown)
 		cpu_dai->driver->cops->shutdown(cstream, cpu_dai);
@@ -432,7 +359,6 @@ static int soc_compr_trigger(struct snd_compr_stream *cstream, int cmd)
 {
 
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
@@ -441,19 +367,9 @@ static int soc_compr_trigger(struct snd_compr_stream *cstream, int cmd)
 
 	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->trigger) {
-		ret = platform->driver->compr_ops->trigger(cstream, cmd);
-		if (ret < 0)
-			goto out;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->trigger)
 			continue;
@@ -485,7 +401,6 @@ out:
 static int soc_compr_trigger_fe(struct snd_compr_stream *cstream, int cmd)
 {
 	struct snd_soc_pcm_runtime *fe = cstream->private_data;
-	struct snd_soc_platform *platform = fe->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = fe->cpu_dai;
@@ -494,19 +409,9 @@ static int soc_compr_trigger_fe(struct snd_compr_stream *cstream, int cmd)
 	if (cmd == SND_COMPR_TRIGGER_PARTIAL_DRAIN ||
 		cmd == SND_COMPR_TRIGGER_DRAIN) {
 
-		if (platform &&
-		    platform->driver->compr_ops &&
-		    platform->driver->compr_ops->trigger)
-			return platform->driver->compr_ops->trigger(cstream,
-								    cmd);
-
 		for_each_rtdcom(fe, rtdcom) {
 			component = rtdcom->component;
 
-			/* ignore duplication for now */
-			if (platform && (component == &platform->component))
-				continue;
-
 			if (!component->driver->compr_ops ||
 			    !component->driver->compr_ops->trigger)
 				continue;
@@ -523,7 +428,6 @@ static int soc_compr_trigger_fe(struct snd_compr_stream *cstream, int cmd)
 	else
 		stream = SNDRV_PCM_STREAM_CAPTURE;
 
-
 	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
 
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->trigger) {
@@ -532,19 +436,9 @@ static int soc_compr_trigger_fe(struct snd_compr_stream *cstream, int cmd)
 			goto out;
 	}
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->trigger) {
-		ret = platform->driver->compr_ops->trigger(cstream, cmd);
-		if (ret < 0)
-			goto out;
-	}
-
 	for_each_rtdcom(fe, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->trigger)
 			continue;
@@ -585,7 +479,6 @@ static int soc_compr_set_params(struct snd_compr_stream *cstream,
 					struct snd_compr_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -593,11 +486,12 @@ static int soc_compr_set_params(struct snd_compr_stream *cstream,
 
 	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
 
-	/* first we call set_params for the platform driver
-	 * this should configure the soc side
-	 * if the machine has compressed ops then we call that as well
-	 * expectation is that platform and machine will configure everything
-	 * for this compress path, like configuring pcm port for codec
+	/*
+	 * First we call set_params for the CPU DAI, then the component
+	 * driver this should configure the SoC side. If the machine has
+	 * compressed ops then we call that as well. The expectation is
+	 * that these callbacks will configure everything for this compress
+	 * path, like configuring a PCM port for a CODEC.
 	 */
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->set_params) {
 		ret = cpu_dai->driver->cops->set_params(cstream, params, cpu_dai);
@@ -605,19 +499,9 @@ static int soc_compr_set_params(struct snd_compr_stream *cstream,
 			goto err;
 	}
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->set_params) {
-		ret = platform->driver->compr_ops->set_params(cstream, params);
-		if (ret < 0)
-			goto err;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->set_params)
 			continue;
@@ -637,10 +521,10 @@ static int soc_compr_set_params(struct snd_compr_stream *cstream,
 
 	if (cstream->direction == SND_COMPRESS_PLAYBACK)
 		snd_soc_dapm_stream_event(rtd, SNDRV_PCM_STREAM_PLAYBACK,
-					SND_SOC_DAPM_STREAM_START);
+					  SND_SOC_DAPM_STREAM_START);
 	else
 		snd_soc_dapm_stream_event(rtd, SNDRV_PCM_STREAM_CAPTURE,
-					SND_SOC_DAPM_STREAM_START);
+					  SND_SOC_DAPM_STREAM_START);
 
 	/* cancel any delayed stream shutdown that is pending */
 	rtd->pop_wait = 0;
@@ -656,12 +540,11 @@ err:
 }
 
 static int soc_compr_set_params_fe(struct snd_compr_stream *cstream,
-					struct snd_compr_params *params)
+				   struct snd_compr_params *params)
 {
 	struct snd_soc_pcm_runtime *fe = cstream->private_data;
 	struct snd_pcm_substream *fe_substream =
 		 fe->pcm->streams[cstream->direction].substream;
-	struct snd_soc_platform *platform = fe->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = fe->cpu_dai;
@@ -680,19 +563,9 @@ static int soc_compr_set_params_fe(struct snd_compr_stream *cstream,
 			goto out;
 	}
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->set_params) {
-		ret = platform->driver->compr_ops->set_params(cstream, params);
-		if (ret < 0)
-			goto out;
-	}
-
 	for_each_rtdcom(fe, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->set_params)
 			continue;
@@ -738,10 +611,9 @@ out:
 }
 
 static int soc_compr_get_params(struct snd_compr_stream *cstream,
-					struct snd_codec *params)
+				struct snd_codec *params)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -755,19 +627,9 @@ static int soc_compr_get_params(struct snd_compr_stream *cstream,
 			goto err;
 	}
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->get_params) {
-		ret = platform->driver->compr_ops->get_params(cstream, params);
-		if (ret < 0)
-			goto err;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->get_params)
 			continue;
@@ -783,29 +645,18 @@ err:
 }
 
 static int soc_compr_get_caps(struct snd_compr_stream *cstream,
-				struct snd_compr_caps *caps)
+			      struct snd_compr_caps *caps)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	int ret = 0, __ret;
 
 	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->get_caps) {
-		ret = platform->driver->compr_ops->get_caps(cstream, caps);
-		if (ret < 0)
-			goto err;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->get_caps)
 			continue;
@@ -815,35 +666,23 @@ static int soc_compr_get_caps(struct snd_compr_stream *cstream,
 			ret = __ret;
 	}
 
-err:
 	mutex_unlock(&rtd->pcm_mutex);
 	return ret;
 }
 
 static int soc_compr_get_codec_caps(struct snd_compr_stream *cstream,
-				struct snd_compr_codec_caps *codec)
+				    struct snd_compr_codec_caps *codec)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	int ret = 0, __ret;
 
 	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->get_codec_caps) {
-		ret = platform->driver->compr_ops->get_codec_caps(cstream, codec);
-		if (ret < 0)
-			goto err;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->get_codec_caps)
 			continue;
@@ -853,7 +692,6 @@ static int soc_compr_get_codec_caps(struct snd_compr_stream *cstream,
 			ret = __ret;
 	}
 
-err:
 	mutex_unlock(&rtd->pcm_mutex);
 	return ret;
 }
@@ -861,7 +699,6 @@ err:
 static int soc_compr_ack(struct snd_compr_stream *cstream, size_t bytes)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -875,19 +712,9 @@ static int soc_compr_ack(struct snd_compr_stream *cstream, size_t bytes)
 			goto err;
 	}
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->ack) {
-		ret = platform->driver->compr_ops->ack(cstream, bytes);
-		if (ret < 0)
-			goto err;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->ack)
 			continue;
@@ -903,10 +730,9 @@ err:
 }
 
 static int soc_compr_pointer(struct snd_compr_stream *cstream,
-			struct snd_compr_tstamp *tstamp)
+			     struct snd_compr_tstamp *tstamp)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	int ret = 0, __ret;
@@ -917,19 +743,9 @@ static int soc_compr_pointer(struct snd_compr_stream *cstream,
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->pointer)
 		cpu_dai->driver->cops->pointer(cstream, tstamp, cpu_dai);
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->pointer) {
-		ret = platform->driver->compr_ops->pointer(cstream, tstamp);
-		if (ret < 0)
-			goto err;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->pointer)
 			continue;
@@ -939,7 +755,6 @@ static int soc_compr_pointer(struct snd_compr_stream *cstream,
 			ret = __ret;
 	}
 
-err:
 	mutex_unlock(&rtd->pcm_mutex);
 	return ret;
 }
@@ -948,26 +763,15 @@ static int soc_compr_copy(struct snd_compr_stream *cstream,
 			  char __user *buf, size_t count)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	int ret = 0;
 
 	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->copy) {
-		ret = platform->driver->compr_ops->copy(cstream, buf, count);
-		if (ret < 0)
-			goto err;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->copy)
 			continue;
@@ -976,16 +780,14 @@ static int soc_compr_copy(struct snd_compr_stream *cstream,
 		break;
 	}
 
-err:
 	mutex_unlock(&rtd->pcm_mutex);
 	return ret;
 }
 
 static int soc_compr_set_metadata(struct snd_compr_stream *cstream,
-				struct snd_compr_metadata *metadata)
+				  struct snd_compr_metadata *metadata)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -997,19 +799,9 @@ static int soc_compr_set_metadata(struct snd_compr_stream *cstream,
 			return ret;
 	}
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->set_metadata) {
-		ret = platform->driver->compr_ops->set_metadata(cstream, metadata);
-		if (ret < 0)
-			return ret;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->set_metadata)
 			continue;
@@ -1023,10 +815,9 @@ static int soc_compr_set_metadata(struct snd_compr_stream *cstream,
 }
 
 static int soc_compr_get_metadata(struct snd_compr_stream *cstream,
-				struct snd_compr_metadata *metadata)
+				  struct snd_compr_metadata *metadata)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -1038,19 +829,9 @@ static int soc_compr_get_metadata(struct snd_compr_stream *cstream,
 			return ret;
 	}
 
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->get_metadata) {
-		ret = platform->driver->compr_ops->get_metadata(cstream, metadata);
-		if (ret < 0)
-			return ret;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->get_metadata)
 			continue;
@@ -1103,7 +884,6 @@ static struct snd_compr_ops soc_compr_dyn_ops = {
  */
 int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
 {
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
@@ -1184,26 +964,17 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
 		memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops));
 	}
 
-
-	/* Add copy callback for not memory mapped DSPs */
-	if (platform && platform->driver->compr_ops && platform->driver->compr_ops->copy)
-		compr->ops->copy = soc_compr_copy;
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->copy)
 			continue;
 
 		compr->ops->copy = soc_compr_copy;
+		break;
 	}
 
-
 	mutex_init(&compr->lock);
 	ret = snd_compress_new(rtd->card->snd_card, num, direction,
 				new_name, compr);
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index bf7ca32ab31f..3d56f1fe5914 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -56,8 +56,6 @@ EXPORT_SYMBOL_GPL(snd_soc_debugfs_root);
 #endif
 
 static DEFINE_MUTEX(client_mutex);
-static LIST_HEAD(platform_list);
-static LIST_HEAD(codec_list);
 static LIST_HEAD(component_list);
 
 /*
@@ -83,98 +81,6 @@ static const char * const dmi_blacklist[] = {
 	NULL,	/* terminator */
 };
 
-/* returns the minimum number of bytes needed to represent
- * a particular given value */
-static int min_bytes_needed(unsigned long val)
-{
-	int c = 0;
-	int i;
-
-	for (i = (sizeof val * 8) - 1; i >= 0; --i, ++c)
-		if (val & (1UL << i))
-			break;
-	c = (sizeof val * 8) - c;
-	if (!c || (c % 8))
-		c = (c + 8) / 8;
-	else
-		c /= 8;
-	return c;
-}
-
-/* fill buf which is 'len' bytes with a formatted
- * string of the form 'reg: value\n' */
-static int format_register_str(struct snd_soc_codec *codec,
-			       unsigned int reg, char *buf, size_t len)
-{
-	int wordsize = min_bytes_needed(codec->driver->reg_cache_size) * 2;
-	int regsize = codec->driver->reg_word_size * 2;
-	int ret;
-
-	/* +2 for ': ' and + 1 for '\n' */
-	if (wordsize + regsize + 2 + 1 != len)
-		return -EINVAL;
-
-	sprintf(buf, "%.*x: ", wordsize, reg);
-	buf += wordsize + 2;
-
-	ret = snd_soc_read(codec, reg);
-	if (ret < 0)
-		memset(buf, 'X', regsize);
-	else
-		sprintf(buf, "%.*x", regsize, ret);
-	buf[regsize] = '\n';
-	/* no NUL-termination needed */
-	return 0;
-}
-
-/* codec register dump */
-static ssize_t soc_codec_reg_show(struct snd_soc_codec *codec, char *buf,
-				  size_t count, loff_t pos)
-{
-	int i, step = 1;
-	int wordsize, regsize;
-	int len;
-	size_t total = 0;
-	loff_t p = 0;
-
-	wordsize = min_bytes_needed(codec->driver->reg_cache_size) * 2;
-	regsize = codec->driver->reg_word_size * 2;
-
-	len = wordsize + regsize + 2 + 1;
-
-	if (!codec->driver->reg_cache_size)
-		return 0;
-
-	if (codec->driver->reg_cache_step)
-		step = codec->driver->reg_cache_step;
-
-	for (i = 0; i < codec->driver->reg_cache_size; i += step) {
-		/* only support larger than PAGE_SIZE bytes debugfs
-		 * entries for the default case */
-		if (p >= pos) {
-			if (total + len >= count - 1)
-				break;
-			format_register_str(codec, i, buf + total, len);
-			total += len;
-		}
-		p += len;
-	}
-
-	total = min(total, count - 1);
-
-	return total;
-}
-
-static ssize_t codec_reg_show(struct device *dev,
-	struct device_attribute *attr, char *buf)
-{
-	struct snd_soc_pcm_runtime *rtd = dev_get_drvdata(dev);
-
-	return soc_codec_reg_show(rtd->codec, buf, PAGE_SIZE, 0);
-}
-
-static DEVICE_ATTR_RO(codec_reg);
-
 static ssize_t pmdown_time_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -200,7 +106,6 @@ static ssize_t pmdown_time_set(struct device *dev,
 static DEVICE_ATTR(pmdown_time, 0644, pmdown_time_show, pmdown_time_set);
 
 static struct attribute *soc_dev_attrs[] = {
-	&dev_attr_codec_reg.attr,
 	&dev_attr_pmdown_time.attr,
 	NULL
 };
@@ -233,71 +138,6 @@ static const struct attribute_group *soc_dev_attr_groups[] = {
 };
 
 #ifdef CONFIG_DEBUG_FS
-static ssize_t codec_reg_read_file(struct file *file, char __user *user_buf,
-				   size_t count, loff_t *ppos)
-{
-	ssize_t ret;
-	struct snd_soc_codec *codec = file->private_data;
-	char *buf;
-
-	if (*ppos < 0 || !count)
-		return -EINVAL;
-
-	buf = kmalloc(count, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	ret = soc_codec_reg_show(codec, buf, count, *ppos);
-	if (ret >= 0) {
-		if (copy_to_user(user_buf, buf, ret)) {
-			kfree(buf);
-			return -EFAULT;
-		}
-		*ppos += ret;
-	}
-
-	kfree(buf);
-	return ret;
-}
-
-static ssize_t codec_reg_write_file(struct file *file,
-		const char __user *user_buf, size_t count, loff_t *ppos)
-{
-	char buf[32];
-	size_t buf_size;
-	char *start = buf;
-	unsigned long reg, value;
-	struct snd_soc_codec *codec = file->private_data;
-	int ret;
-
-	buf_size = min(count, (sizeof(buf)-1));
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-	buf[buf_size] = 0;
-
-	while (*start == ' ')
-		start++;
-	reg = simple_strtoul(start, &start, 16);
-	while (*start == ' ')
-		start++;
-	ret = kstrtoul(start, 16, &value);
-	if (ret)
-		return ret;
-
-	/* Userspace has been fiddling around behind the kernel's back */
-	add_taint(TAINT_USER, LOCKDEP_NOW_UNRELIABLE);
-
-	snd_soc_write(codec, reg, value);
-	return buf_size;
-}
-
-static const struct file_operations codec_reg_fops = {
-	.open = simple_open,
-	.read = codec_reg_read_file,
-	.write = codec_reg_write_file,
-	.llseek = default_llseek,
-};
-
 static void soc_init_component_debugfs(struct snd_soc_component *component)
 {
 	if (!component->card->debugfs_card_root)
@@ -326,9 +166,6 @@ static void soc_init_component_debugfs(struct snd_soc_component *component)
 
 	snd_soc_dapm_debugfs_init(snd_soc_component_get_dapm(component),
 		component->debugfs_root);
-
-	if (component->init_debugfs)
-		component->init_debugfs(component);
 }
 
 static void soc_cleanup_component_debugfs(struct snd_soc_component *component)
@@ -336,34 +173,6 @@ static void soc_cleanup_component_debugfs(struct snd_soc_component *component)
 	debugfs_remove_recursive(component->debugfs_root);
 }
 
-static void soc_init_codec_debugfs(struct snd_soc_component *component)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-	struct dentry *debugfs_reg;
-
-	debugfs_reg = debugfs_create_file("codec_reg", 0644,
-					  codec->component.debugfs_root,
-					  codec, &codec_reg_fops);
-	if (!debugfs_reg)
-		dev_warn(codec->dev,
-			"ASoC: Failed to create codec register debugfs file\n");
-}
-
-static int codec_list_show(struct seq_file *m, void *v)
-{
-	struct snd_soc_codec *codec;
-
-	mutex_lock(&client_mutex);
-
-	list_for_each_entry(codec, &codec_list, list)
-		seq_printf(m, "%s\n", codec->component.name);
-
-	mutex_unlock(&client_mutex);
-
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(codec_list);
-
 static int dai_list_show(struct seq_file *m, void *v)
 {
 	struct snd_soc_component *component;
@@ -381,20 +190,20 @@ static int dai_list_show(struct seq_file *m, void *v)
 }
 DEFINE_SHOW_ATTRIBUTE(dai_list);
 
-static int platform_list_show(struct seq_file *m, void *v)
+static int component_list_show(struct seq_file *m, void *v)
 {
-	struct snd_soc_platform *platform;
+	struct snd_soc_component *component;
 
 	mutex_lock(&client_mutex);
 
-	list_for_each_entry(platform, &platform_list, list)
-		seq_printf(m, "%s\n", platform->component.name);
+	list_for_each_entry(component, &component_list, list)
+		seq_printf(m, "%s\n", component->name);
 
 	mutex_unlock(&client_mutex);
 
 	return 0;
 }
-DEFINE_SHOW_ATTRIBUTE(platform_list);
+DEFINE_SHOW_ATTRIBUTE(component_list);
 
 static void soc_init_card_debugfs(struct snd_soc_card *card)
 {
@@ -431,17 +240,13 @@ static void snd_soc_debugfs_init(void)
 		return;
 	}
 
-	if (!debugfs_create_file("codecs", 0444, snd_soc_debugfs_root, NULL,
-				 &codec_list_fops))
-		pr_warn("ASoC: Failed to create CODEC list debugfs file\n");
-
 	if (!debugfs_create_file("dais", 0444, snd_soc_debugfs_root, NULL,
 				 &dai_list_fops))
 		pr_warn("ASoC: Failed to create DAI list debugfs file\n");
 
-	if (!debugfs_create_file("platforms", 0444, snd_soc_debugfs_root, NULL,
-				 &platform_list_fops))
-		pr_warn("ASoC: Failed to create platform list debugfs file\n");
+	if (!debugfs_create_file("components", 0444, snd_soc_debugfs_root, NULL,
+				 &component_list_fops))
+		pr_warn("ASoC: Failed to create component list debugfs file\n");
 }
 
 static void snd_soc_debugfs_exit(void)
@@ -451,8 +256,6 @@ static void snd_soc_debugfs_exit(void)
 
 #else
 
-#define soc_init_codec_debugfs NULL
-
 static inline void soc_init_component_debugfs(
 	struct snd_soc_component *component)
 {
@@ -732,8 +535,8 @@ int snd_soc_suspend(struct device *dev)
 				}
 
 			case SND_SOC_BIAS_OFF:
-				if (component->suspend)
-					component->suspend(component);
+				if (component->driver->suspend)
+					component->driver->suspend(component);
 				component->suspended = 1;
 				if (component->regmap)
 					regcache_mark_dirty(component->regmap);
@@ -804,8 +607,8 @@ static void soc_resume_deferred(struct work_struct *work)
 
 	list_for_each_entry(component, &card->component_dev_list, card_list) {
 		if (component->suspended) {
-			if (component->resume)
-				component->resume(component);
+			if (component->driver->resume)
+				component->driver->resume(component);
 			component->suspended = 0;
 		}
 	}
@@ -1045,7 +848,6 @@ static int soc_bind_dai_link(struct snd_soc_card *card,
 	struct snd_soc_dai_link_component cpu_dai_component;
 	struct snd_soc_component *component;
 	struct snd_soc_dai **codec_dais;
-	struct snd_soc_platform *platform;
 	struct device_node *platform_of_node;
 	const char *platform_name;
 	int i;
@@ -1089,7 +891,6 @@ static int soc_bind_dai_link(struct snd_soc_card *card,
 
 	/* Single codec links expect codec and codec_dai in runtime data */
 	rtd->codec_dai = codec_dais[0];
-	rtd->codec = rtd->codec_dai->codec;
 
 	/* if there's no platform we match on the empty platform */
 	platform_name = dai_link->platform_name;
@@ -1113,23 +914,6 @@ static int soc_bind_dai_link(struct snd_soc_card *card,
 		snd_soc_rtdcom_add(rtd, component);
 	}
 
-	/* find one from the set of registered platforms */
-	list_for_each_entry(platform, &platform_list, list) {
-		platform_of_node = platform->dev->of_node;
-		if (!platform_of_node && platform->dev->parent->of_node)
-			platform_of_node = platform->dev->parent->of_node;
-
-		if (dai_link->platform_of_node) {
-			if (platform_of_node != dai_link->platform_of_node)
-				continue;
-		} else {
-			if (strcmp(platform->component.name, platform_name))
-				continue;
-		}
-
-		rtd->platform = platform;
-	}
-
 	soc_add_pcm_runtime(card, rtd);
 	return 0;
 
@@ -1145,8 +929,8 @@ static void soc_remove_component(struct snd_soc_component *component)
 
 	list_del(&component->card_list);
 
-	if (component->remove)
-		component->remove(component);
+	if (component->driver->remove)
+		component->driver->remove(component);
 
 	snd_soc_dapm_free(snd_soc_component_get_dapm(component));
 
@@ -1421,7 +1205,12 @@ static void soc_set_name_prefix(struct snd_soc_card *card,
 
 	for (i = 0; i < card->num_configs; i++) {
 		struct snd_soc_codec_conf *map = &card->codec_conf[i];
-		if (map->of_node && component->dev->of_node != map->of_node)
+		struct device_node *component_of_node = component->dev->of_node;
+
+		if (!component_of_node && component->dev->parent)
+			component_of_node = component->dev->parent->of_node;
+
+		if (map->of_node && component_of_node != map->of_node)
 			continue;
 		if (map->dev_name && strcmp(component->name, map->dev_name))
 			continue;
@@ -1480,8 +1269,8 @@ static int soc_probe_component(struct snd_soc_card *card,
 		}
 	}
 
-	if (component->probe) {
-		ret = component->probe(component);
+	if (component->driver->probe) {
+		ret = component->driver->probe(component);
 		if (ret < 0) {
 			dev_err(component->dev,
 				"ASoC: failed to probe component %d\n", ret);
@@ -1838,24 +1627,6 @@ static void soc_remove_aux_devices(struct snd_soc_card *card)
 	}
 }
 
-static int snd_soc_init_codec_cache(struct snd_soc_codec *codec)
-{
-	int ret;
-
-	if (codec->cache_init)
-		return 0;
-
-	ret = snd_soc_cache_init(codec);
-	if (ret < 0) {
-		dev_err(codec->dev,
-			"ASoC: Failed to set cache compression type: %d\n",
-			ret);
-		return ret;
-	}
-	codec->cache_init = 1;
-	return 0;
-}
-
 /**
  * snd_soc_runtime_set_dai_fmt() - Change DAI link format for a ASoC runtime
  * @rtd: The runtime for which the DAI link format should be changed
@@ -1890,8 +1661,7 @@ int snd_soc_runtime_set_dai_fmt(struct snd_soc_pcm_runtime *rtd,
 
 	/* Flip the polarity for the "CPU" end of a CODEC<->CODEC link */
 	/* the component which has non_legacy_dai_naming is Codec */
-	if (cpu_dai->codec ||
-	    cpu_dai->component->driver->non_legacy_dai_naming) {
+	if (cpu_dai->component->driver->non_legacy_dai_naming) {
 		unsigned int inv_dai_fmt;
 
 		inv_dai_fmt = dai_fmt & ~SND_SOC_DAIFMT_MASTER_MASK;
@@ -2078,7 +1848,6 @@ EXPORT_SYMBOL_GPL(snd_soc_set_dmi_name);
 
 static int snd_soc_instantiate_card(struct snd_soc_card *card)
 {
-	struct snd_soc_codec *codec;
 	struct snd_soc_pcm_runtime *rtd;
 	struct snd_soc_dai_link *dai_link;
 	int ret, i, order;
@@ -2104,15 +1873,6 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 	for (i = 0; i < card->num_links; i++)
 		snd_soc_add_dai_link(card, card->dai_link+i);
 
-	/* initialize the register cache for each available codec */
-	list_for_each_entry(codec, &codec_list, list) {
-		if (codec->cache_init)
-			continue;
-		ret = snd_soc_init_codec_cache(codec);
-		if (ret < 0)
-			goto base_error;
-	}
-
 	/* card bind complete so register a sound card */
 	ret = snd_card_new(card->dev, SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1,
 			card->owner, 0, &card->snd_card);
@@ -2494,43 +2254,6 @@ int snd_soc_add_component_controls(struct snd_soc_component *component,
 EXPORT_SYMBOL_GPL(snd_soc_add_component_controls);
 
 /**
- * snd_soc_add_codec_controls - add an array of controls to a codec.
- * Convenience function to add a list of controls. Many codecs were
- * duplicating this code.
- *
- * @codec: codec to add controls to
- * @controls: array of controls to add
- * @num_controls: number of elements in the array
- *
- * Return 0 for success, else error.
- */
-int snd_soc_add_codec_controls(struct snd_soc_codec *codec,
-	const struct snd_kcontrol_new *controls, unsigned int num_controls)
-{
-	return snd_soc_add_component_controls(&codec->component, controls,
-		num_controls);
-}
-EXPORT_SYMBOL_GPL(snd_soc_add_codec_controls);
-
-/**
- * snd_soc_add_platform_controls - add an array of controls to a platform.
- * Convenience function to add a list of controls.
- *
- * @platform: platform to add controls to
- * @controls: array of controls to add
- * @num_controls: number of elements in the array
- *
- * Return 0 for success, else error.
- */
-int snd_soc_add_platform_controls(struct snd_soc_platform *platform,
-	const struct snd_kcontrol_new *controls, unsigned int num_controls)
-{
-	return snd_soc_add_component_controls(&platform->component, controls,
-		num_controls);
-}
-EXPORT_SYMBOL_GPL(snd_soc_add_platform_controls);
-
-/**
  * snd_soc_add_card_controls - add an array of controls to a SoC card.
  * Convenience function to add a list of controls.
  *
@@ -2591,27 +2314,6 @@ int snd_soc_dai_set_sysclk(struct snd_soc_dai *dai, int clk_id,
 EXPORT_SYMBOL_GPL(snd_soc_dai_set_sysclk);
 
 /**
- * snd_soc_codec_set_sysclk - configure CODEC system or master clock.
- * @codec: CODEC
- * @clk_id: DAI specific clock ID
- * @source: Source for the clock
- * @freq: new clock frequency in Hz
- * @dir: new clock direction - input/output.
- *
- * Configures the CODEC master (MCLK) or system (SYSCLK) clocking.
- */
-int snd_soc_codec_set_sysclk(struct snd_soc_codec *codec, int clk_id,
-			     int source, unsigned int freq, int dir)
-{
-	if (codec->driver->set_sysclk)
-		return codec->driver->set_sysclk(codec, clk_id, source,
-						 freq, dir);
-	else
-		return -ENOTSUPP;
-}
-EXPORT_SYMBOL_GPL(snd_soc_codec_set_sysclk);
-
-/**
  * snd_soc_component_set_sysclk - configure COMPONENT system or master clock.
  * @component: COMPONENT
  * @clk_id: DAI specific clock ID
@@ -2624,11 +2326,6 @@ EXPORT_SYMBOL_GPL(snd_soc_codec_set_sysclk);
 int snd_soc_component_set_sysclk(struct snd_soc_component *component, int clk_id,
 			     int source, unsigned int freq, int dir)
 {
-	/* will be removed */
-	if (component->set_sysclk)
-		return component->set_sysclk(component, clk_id, source,
-					     freq, dir);
-
 	if (component->driver->set_sysclk)
 		return component->driver->set_sysclk(component, clk_id, source,
 						 freq, dir);
@@ -2680,27 +2377,6 @@ int snd_soc_dai_set_pll(struct snd_soc_dai *dai, int pll_id, int source,
 EXPORT_SYMBOL_GPL(snd_soc_dai_set_pll);
 
 /*
- * snd_soc_codec_set_pll - configure codec PLL.
- * @codec: CODEC
- * @pll_id: DAI specific PLL ID
- * @source: DAI specific source for the PLL
- * @freq_in: PLL input clock frequency in Hz
- * @freq_out: requested PLL output clock frequency in Hz
- *
- * Configures and enables PLL to generate output clock based on input clock.
- */
-int snd_soc_codec_set_pll(struct snd_soc_codec *codec, int pll_id, int source,
-			  unsigned int freq_in, unsigned int freq_out)
-{
-	if (codec->driver->set_pll)
-		return codec->driver->set_pll(codec, pll_id, source,
-					      freq_in, freq_out);
-	else
-		return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(snd_soc_codec_set_pll);
-
-/*
  * snd_soc_component_set_pll - configure component PLL.
  * @component: COMPONENT
  * @pll_id: DAI specific PLL ID
@@ -2714,11 +2390,6 @@ int snd_soc_component_set_pll(struct snd_soc_component *component, int pll_id,
 			      int source, unsigned int freq_in,
 			      unsigned int freq_out)
 {
-	/* will be removed */
-	if (component->set_pll)
-		return component->set_pll(component, pll_id, source,
-					      freq_in, freq_out);
-
 	if (component->driver->set_pll)
 		return component->driver->set_pll(component, pll_id, source,
 					      freq_in, freq_out);
@@ -3112,8 +2783,7 @@ static struct snd_soc_dai *soc_add_dai(struct snd_soc_component *component,
  *                     parent's name.
  */
 static int snd_soc_register_dais(struct snd_soc_component *component,
-	struct snd_soc_dai_driver *dai_drv, size_t count,
-	bool legacy_dai_naming)
+				 struct snd_soc_dai_driver *dai_drv, size_t count)
 {
 	struct device *dev = component->dev;
 	struct snd_soc_dai *dai;
@@ -3125,7 +2795,7 @@ static int snd_soc_register_dais(struct snd_soc_component *component,
 	for (i = 0; i < count; i++) {
 
 		dai = soc_add_dai(component, dai_drv + i,
-				count == 1 && legacy_dai_naming);
+				  count == 1 && !component->driver->non_legacy_dai_naming);
 		if (dai == NULL) {
 			ret = -ENOMEM;
 			goto err;
@@ -3198,22 +2868,6 @@ static int snd_soc_component_stream_event(struct snd_soc_dapm_context *dapm,
 	return component->driver->stream_event(component, event);
 }
 
-static int snd_soc_component_drv_pcm_new(struct snd_soc_component *component,
-					struct snd_soc_pcm_runtime *rtd)
-{
-	if (component->driver->pcm_new)
-		return component->driver->pcm_new(rtd);
-
-	return 0;
-}
-
-static void snd_soc_component_drv_pcm_free(struct snd_soc_component *component,
-					  struct snd_pcm *pcm)
-{
-	if (component->driver->pcm_free)
-		component->driver->pcm_free(pcm);
-}
-
 static int snd_soc_component_set_bias_level(struct snd_soc_dapm_context *dapm,
 					enum snd_soc_bias_level level)
 {
@@ -3235,15 +2889,6 @@ static int snd_soc_component_initialize(struct snd_soc_component *component,
 
 	component->dev = dev;
 	component->driver = driver;
-	component->probe = component->driver->probe;
-	component->remove = component->driver->remove;
-	component->suspend = component->driver->suspend;
-	component->resume = component->driver->resume;
-	component->set_sysclk = component->driver->set_sysclk;
-	component->set_pll = component->driver->set_pll;
-	component->set_jack = component->driver->set_jack;
-	component->pcm_new = snd_soc_component_drv_pcm_new;
-	component->pcm_free = snd_soc_component_drv_pcm_free;
 
 	dapm = snd_soc_component_get_dapm(component);
 	dapm->dev = dev;
@@ -3312,9 +2957,11 @@ EXPORT_SYMBOL_GPL(snd_soc_component_exit_regmap);
 
 #endif
 
-static void snd_soc_component_add_unlocked(struct snd_soc_component *component)
+static void snd_soc_component_add(struct snd_soc_component *component)
 {
-	if (!component->write && !component->read) {
+	mutex_lock(&client_mutex);
+
+	if (!component->driver->write && !component->driver->read) {
 		if (!component->regmap)
 			component->regmap = dev_get_regmap(component->dev, NULL);
 		if (component->regmap)
@@ -3323,12 +2970,7 @@ static void snd_soc_component_add_unlocked(struct snd_soc_component *component)
 
 	list_add(&component->list, &component_list);
 	INIT_LIST_HEAD(&component->dobj_list);
-}
 
-static void snd_soc_component_add(struct snd_soc_component *component)
-{
-	mutex_lock(&client_mutex);
-	snd_soc_component_add_unlocked(component);
 	mutex_unlock(&client_mutex);
 }
 
@@ -3396,9 +3038,6 @@ int snd_soc_add_component(struct device *dev,
 	if (ret)
 		goto err_free;
 
-	component->ignore_pmdown_time = true;
-	component->registered_as_component = true;
-
 	if (component_driver->endianness) {
 		for (i = 0; i < num_dai; i++) {
 			convert_endianness_formats(&dai_drv[i].playback);
@@ -3406,8 +3045,7 @@ int snd_soc_add_component(struct device *dev,
 		}
 	}
 
-	ret = snd_soc_register_dais(component, dai_drv, num_dai,
-				    !component_driver->non_legacy_dai_naming);
+	ret = snd_soc_register_dais(component, dai_drv, num_dai);
 	if (ret < 0) {
 		dev_err(dev, "ASoC: Failed to register DAIs: %d\n", ret);
 		goto err_cleanup;
@@ -3453,8 +3091,7 @@ static int __snd_soc_unregister_component(struct device *dev)
 
 	mutex_lock(&client_mutex);
 	list_for_each_entry(component, &component_list, list) {
-		if (dev != component->dev ||
-		    !component->registered_as_component)
+		if (dev != component->dev)
 			continue;
 
 		snd_soc_tplg_component_remove(component, SND_SOC_TPLG_INDEX_ALL);
@@ -3503,375 +3140,6 @@ struct snd_soc_component *snd_soc_lookup_component(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(snd_soc_lookup_component);
 
-static int snd_soc_platform_drv_probe(struct snd_soc_component *component)
-{
-	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
-
-	return platform->driver->probe(platform);
-}
-
-static void snd_soc_platform_drv_remove(struct snd_soc_component *component)
-{
-	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
-
-	platform->driver->remove(platform);
-}
-
-static int snd_soc_platform_drv_pcm_new(struct snd_soc_component *component,
-					struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
-
-	if (platform->driver->pcm_new)
-		return platform->driver->pcm_new(rtd);
-
-	return 0;
-}
-
-static void snd_soc_platform_drv_pcm_free(struct snd_soc_component *component,
-					  struct snd_pcm *pcm)
-{
-	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
-
-	if (platform->driver->pcm_free)
-		platform->driver->pcm_free(pcm);
-}
-
-/**
- * snd_soc_add_platform - Add a platform to the ASoC core
- * @dev: The parent device for the platform
- * @platform: The platform to add
- * @platform_drv: The driver for the platform
- */
-int snd_soc_add_platform(struct device *dev, struct snd_soc_platform *platform,
-		const struct snd_soc_platform_driver *platform_drv)
-{
-	int ret;
-
-	ret = snd_soc_component_initialize(&platform->component,
-			&platform_drv->component_driver, dev);
-	if (ret)
-		return ret;
-
-	platform->dev = dev;
-	platform->driver = platform_drv;
-
-	if (platform_drv->probe)
-		platform->component.probe = snd_soc_platform_drv_probe;
-	if (platform_drv->remove)
-		platform->component.remove = snd_soc_platform_drv_remove;
-	if (platform_drv->pcm_new)
-		platform->component.pcm_new = snd_soc_platform_drv_pcm_new;
-	if (platform_drv->pcm_free)
-		platform->component.pcm_free = snd_soc_platform_drv_pcm_free;
-
-#ifdef CONFIG_DEBUG_FS
-	platform->component.debugfs_prefix = "platform";
-#endif
-
-	mutex_lock(&client_mutex);
-	snd_soc_component_add_unlocked(&platform->component);
-	list_add(&platform->list, &platform_list);
-	mutex_unlock(&client_mutex);
-
-	dev_dbg(dev, "ASoC: Registered platform '%s'\n",
-		platform->component.name);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_add_platform);
-
-/**
- * snd_soc_register_platform - Register a platform with the ASoC core
- *
- * @dev: The device for the platform
- * @platform_drv: The driver for the platform
- */
-int snd_soc_register_platform(struct device *dev,
-		const struct snd_soc_platform_driver *platform_drv)
-{
-	struct snd_soc_platform *platform;
-	int ret;
-
-	dev_dbg(dev, "ASoC: platform register %s\n", dev_name(dev));
-
-	platform = kzalloc(sizeof(struct snd_soc_platform), GFP_KERNEL);
-	if (platform == NULL)
-		return -ENOMEM;
-
-	ret = snd_soc_add_platform(dev, platform, platform_drv);
-	if (ret)
-		kfree(platform);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(snd_soc_register_platform);
-
-/**
- * snd_soc_remove_platform - Remove a platform from the ASoC core
- * @platform: the platform to remove
- */
-void snd_soc_remove_platform(struct snd_soc_platform *platform)
-{
-
-	mutex_lock(&client_mutex);
-	list_del(&platform->list);
-	snd_soc_component_del_unlocked(&platform->component);
-	mutex_unlock(&client_mutex);
-
-	dev_dbg(platform->dev, "ASoC: Unregistered platform '%s'\n",
-		platform->component.name);
-
-	snd_soc_component_cleanup(&platform->component);
-}
-EXPORT_SYMBOL_GPL(snd_soc_remove_platform);
-
-struct snd_soc_platform *snd_soc_lookup_platform(struct device *dev)
-{
-	struct snd_soc_platform *platform;
-
-	mutex_lock(&client_mutex);
-	list_for_each_entry(platform, &platform_list, list) {
-		if (dev == platform->dev) {
-			mutex_unlock(&client_mutex);
-			return platform;
-		}
-	}
-	mutex_unlock(&client_mutex);
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(snd_soc_lookup_platform);
-
-/**
- * snd_soc_unregister_platform - Unregister a platform from the ASoC core
- *
- * @dev: platform to unregister
- */
-void snd_soc_unregister_platform(struct device *dev)
-{
-	struct snd_soc_platform *platform;
-
-	platform = snd_soc_lookup_platform(dev);
-	if (!platform)
-		return;
-
-	snd_soc_remove_platform(platform);
-	kfree(platform);
-}
-EXPORT_SYMBOL_GPL(snd_soc_unregister_platform);
-
-static int snd_soc_codec_drv_probe(struct snd_soc_component *component)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	return codec->driver->probe(codec);
-}
-
-static void snd_soc_codec_drv_remove(struct snd_soc_component *component)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	codec->driver->remove(codec);
-}
-
-static int snd_soc_codec_drv_suspend(struct snd_soc_component *component)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	return codec->driver->suspend(codec);
-}
-
-static int snd_soc_codec_drv_resume(struct snd_soc_component *component)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	return codec->driver->resume(codec);
-}
-
-static int snd_soc_codec_drv_write(struct snd_soc_component *component,
-	unsigned int reg, unsigned int val)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	return codec->driver->write(codec, reg, val);
-}
-
-static int snd_soc_codec_drv_read(struct snd_soc_component *component,
-	unsigned int reg, unsigned int *val)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	*val = codec->driver->read(codec, reg);
-
-	return 0;
-}
-
-static int snd_soc_codec_set_sysclk_(struct snd_soc_component *component,
-			  int clk_id, int source, unsigned int freq, int dir)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	return snd_soc_codec_set_sysclk(codec, clk_id, source, freq, dir);
-}
-
-static int snd_soc_codec_set_pll_(struct snd_soc_component *component,
-				  int pll_id, int source, unsigned int freq_in,
-				  unsigned int freq_out)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	return snd_soc_codec_set_pll(codec, pll_id, source, freq_in, freq_out);
-}
-
-static int snd_soc_codec_set_jack_(struct snd_soc_component *component,
-			       struct snd_soc_jack *jack, void *data)
-{
-	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
-
-	return snd_soc_codec_set_jack(codec, jack, data);
-}
-
-static int snd_soc_codec_set_bias_level(struct snd_soc_dapm_context *dapm,
-	enum snd_soc_bias_level level)
-{
-	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(dapm);
-
-	return codec->driver->set_bias_level(codec, level);
-}
-
-/**
- * snd_soc_register_codec - Register a codec with the ASoC core
- *
- * @dev: The parent device for this codec
- * @codec_drv: Codec driver
- * @dai_drv: The associated DAI driver
- * @num_dai: Number of DAIs
- */
-int snd_soc_register_codec(struct device *dev,
-			   const struct snd_soc_codec_driver *codec_drv,
-			   struct snd_soc_dai_driver *dai_drv,
-			   int num_dai)
-{
-	struct snd_soc_dapm_context *dapm;
-	struct snd_soc_codec *codec;
-	struct snd_soc_dai *dai;
-	int ret, i;
-
-	dev_dbg(dev, "codec register %s\n", dev_name(dev));
-
-	codec = kzalloc(sizeof(struct snd_soc_codec), GFP_KERNEL);
-	if (codec == NULL)
-		return -ENOMEM;
-
-	codec->component.codec = codec;
-
-	ret = snd_soc_component_initialize(&codec->component,
-			&codec_drv->component_driver, dev);
-	if (ret)
-		goto err_free;
-
-	if (codec_drv->probe)
-		codec->component.probe = snd_soc_codec_drv_probe;
-	if (codec_drv->remove)
-		codec->component.remove = snd_soc_codec_drv_remove;
-	if (codec_drv->suspend)
-		codec->component.suspend = snd_soc_codec_drv_suspend;
-	if (codec_drv->resume)
-		codec->component.resume = snd_soc_codec_drv_resume;
-	if (codec_drv->write)
-		codec->component.write = snd_soc_codec_drv_write;
-	if (codec_drv->read)
-		codec->component.read = snd_soc_codec_drv_read;
-	if (codec_drv->set_sysclk)
-		codec->component.set_sysclk = snd_soc_codec_set_sysclk_;
-	if (codec_drv->set_pll)
-		codec->component.set_pll = snd_soc_codec_set_pll_;
-	if (codec_drv->set_jack)
-		codec->component.set_jack = snd_soc_codec_set_jack_;
-	codec->component.ignore_pmdown_time = codec_drv->ignore_pmdown_time;
-
-	dapm = snd_soc_codec_get_dapm(codec);
-	dapm->idle_bias_off = codec_drv->idle_bias_off;
-	dapm->suspend_bias_off = codec_drv->suspend_bias_off;
-	if (codec_drv->seq_notifier)
-		dapm->seq_notifier = codec_drv->seq_notifier;
-	if (codec_drv->set_bias_level)
-		dapm->set_bias_level = snd_soc_codec_set_bias_level;
-	codec->dev = dev;
-	codec->driver = codec_drv;
-	codec->component.val_bytes = codec_drv->reg_word_size;
-
-#ifdef CONFIG_DEBUG_FS
-	codec->component.init_debugfs = soc_init_codec_debugfs;
-	codec->component.debugfs_prefix = "codec";
-#endif
-
-	if (codec_drv->get_regmap)
-		codec->component.regmap = codec_drv->get_regmap(dev);
-
-	for (i = 0; i < num_dai; i++) {
-		convert_endianness_formats(&dai_drv[i].playback);
-		convert_endianness_formats(&dai_drv[i].capture);
-	}
-
-	ret = snd_soc_register_dais(&codec->component, dai_drv, num_dai, false);
-	if (ret < 0) {
-		dev_err(dev, "ASoC: Failed to register DAIs: %d\n", ret);
-		goto err_cleanup;
-	}
-
-	list_for_each_entry(dai, &codec->component.dai_list, list)
-		dai->codec = codec;
-
-	mutex_lock(&client_mutex);
-	snd_soc_component_add_unlocked(&codec->component);
-	list_add(&codec->list, &codec_list);
-	mutex_unlock(&client_mutex);
-
-	dev_dbg(codec->dev, "ASoC: Registered codec '%s'\n",
-		codec->component.name);
-	return 0;
-
-err_cleanup:
-	snd_soc_component_cleanup(&codec->component);
-err_free:
-	kfree(codec);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(snd_soc_register_codec);
-
-/**
- * snd_soc_unregister_codec - Unregister a codec from the ASoC core
- *
- * @dev: codec to unregister
- */
-void snd_soc_unregister_codec(struct device *dev)
-{
-	struct snd_soc_codec *codec;
-
-	mutex_lock(&client_mutex);
-	list_for_each_entry(codec, &codec_list, list) {
-		if (dev == codec->dev)
-			goto found;
-	}
-	mutex_unlock(&client_mutex);
-	return;
-
-found:
-	list_del(&codec->list);
-	snd_soc_component_del_unlocked(&codec->component);
-	mutex_unlock(&client_mutex);
-
-	dev_dbg(codec->dev, "ASoC: Unregistered codec '%s'\n",
-			codec->component.name);
-
-	snd_soc_component_cleanup(&codec->component);
-	snd_soc_cache_exit(codec);
-	kfree(codec);
-}
-EXPORT_SYMBOL_GPL(snd_soc_unregister_codec);
-
 /* Retrieve a card's name from device tree */
 int snd_soc_of_parse_card_name(struct snd_soc_card *card,
 			       const char *propname)
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 2d9709104ec5..36a39ba30226 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -433,6 +433,8 @@ err_data:
 static void dapm_kcontrol_free(struct snd_kcontrol *kctl)
 {
 	struct dapm_kcontrol_data *data = snd_kcontrol_chip(kctl);
+
+	list_del(&data->paths);
 	kfree(data->wlist);
 	kfree(data);
 }
@@ -724,18 +726,14 @@ static int dapm_connect_mux(struct snd_soc_dapm_context *dapm,
 		item = 0;
 	}
 
-	for (i = 0; i < e->items; i++) {
-		if (!(strcmp(control_name, e->texts[i]))) {
-			path->name = e->texts[i];
-			if (i == item)
-				path->connect = 1;
-			else
-				path->connect = 0;
-			return 0;
-		}
-	}
+	i = match_string(e->texts, e->items, control_name);
+	if (i < 0)
+		return -ENODEV;
+
+	path->name = e->texts[i];
+	path->connect = (i == item);
+	return 0;
 
-	return -ENODEV;
 }
 
 /* set up initial codec paths */
diff --git a/sound/soc/soc-devres.c b/sound/soc/soc-devres.c
index a57921eeee81..7ac745df1412 100644
--- a/sound/soc/soc-devres.c
+++ b/sound/soc/soc-devres.c
@@ -52,41 +52,6 @@ int devm_snd_soc_register_component(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_snd_soc_register_component);
 
-static void devm_platform_release(struct device *dev, void *res)
-{
-	snd_soc_unregister_platform(*(struct device **)res);
-}
-
-/**
- * devm_snd_soc_register_platform - resource managed platform registration
- * @dev: Device used to manage platform
- * @platform_drv: platform to register
- *
- * Register a platform driver with automatic unregistration when the device is
- * unregistered.
- */
-int devm_snd_soc_register_platform(struct device *dev,
-			const struct snd_soc_platform_driver *platform_drv)
-{
-	struct device **ptr;
-	int ret;
-
-	ptr = devres_alloc(devm_platform_release, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr)
-		return -ENOMEM;
-
-	ret = snd_soc_register_platform(dev, platform_drv);
-	if (ret == 0) {
-		*ptr = dev;
-		devres_add(dev, ptr);
-	} else {
-		devres_free(ptr);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(devm_snd_soc_register_platform);
-
 static void devm_card_release(struct device *dev, void *res)
 {
 	snd_soc_unregister_card(*(struct snd_soc_card **)res);
diff --git a/sound/soc/soc-io.c b/sound/soc/soc-io.c
index d36a192fbece..026cd5347e53 100644
--- a/sound/soc/soc-io.c
+++ b/sound/soc/soc-io.c
@@ -32,8 +32,6 @@ int snd_soc_component_read(struct snd_soc_component *component,
 
 	if (component->regmap)
 		ret = regmap_read(component->regmap, reg, val);
-	else if (component->read)
-		ret = component->read(component, reg, val);
 	else if (component->driver->read) {
 		*val = component->driver->read(component, reg);
 		ret = 0;
@@ -72,8 +70,6 @@ int snd_soc_component_write(struct snd_soc_component *component,
 {
 	if (component->regmap)
 		return regmap_write(component->regmap, reg, val);
-	else if (component->write)
-		return component->write(component, reg, val);
 	else if (component->driver->write)
 		return component->driver->write(component, reg, val);
 	else
@@ -209,82 +205,3 @@ int snd_soc_component_test_bits(struct snd_soc_component *component,
 	return old != new;
 }
 EXPORT_SYMBOL_GPL(snd_soc_component_test_bits);
-
-unsigned int snd_soc_read(struct snd_soc_codec *codec, unsigned int reg)
-{
-	unsigned int val;
-	int ret;
-
-	ret = snd_soc_component_read(&codec->component, reg, &val);
-	if (ret < 0)
-		return -1;
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(snd_soc_read);
-
-int snd_soc_write(struct snd_soc_codec *codec, unsigned int reg,
-	unsigned int val)
-{
-	return snd_soc_component_write(&codec->component, reg, val);
-}
-EXPORT_SYMBOL_GPL(snd_soc_write);
-
-/**
- * snd_soc_update_bits - update codec register bits
- * @codec: audio codec
- * @reg: codec register
- * @mask: register mask
- * @value: new value
- *
- * Writes new register value.
- *
- * Returns 1 for change, 0 for no change, or negative error code.
- */
-int snd_soc_update_bits(struct snd_soc_codec *codec, unsigned int reg,
-				unsigned int mask, unsigned int value)
-{
-	return snd_soc_component_update_bits(&codec->component, reg, mask,
-		value);
-}
-EXPORT_SYMBOL_GPL(snd_soc_update_bits);
-
-/**
- * snd_soc_test_bits - test register for change
- * @codec: audio codec
- * @reg: codec register
- * @mask: register mask
- * @value: new value
- *
- * Tests a register with a new value and checks if the new value is
- * different from the old value.
- *
- * Returns 1 for change else 0.
- */
-int snd_soc_test_bits(struct snd_soc_codec *codec, unsigned int reg,
-				unsigned int mask, unsigned int value)
-{
-	return snd_soc_component_test_bits(&codec->component, reg, mask, value);
-}
-EXPORT_SYMBOL_GPL(snd_soc_test_bits);
-
-int snd_soc_platform_read(struct snd_soc_platform *platform,
-					unsigned int reg)
-{
-	unsigned int val;
-	int ret;
-
-	ret = snd_soc_component_read(&platform->component, reg, &val);
-	if (ret < 0)
-		return -1;
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(snd_soc_platform_read);
-
-int snd_soc_platform_write(struct snd_soc_platform *platform,
-					 unsigned int reg, unsigned int val)
-{
-	return snd_soc_component_write(&platform->component, reg, val);
-}
-EXPORT_SYMBOL_GPL(snd_soc_platform_write);
diff --git a/sound/soc/soc-jack.c b/sound/soc/soc-jack.c
index 99902ae1a2d9..b2b16044ae80 100644
--- a/sound/soc/soc-jack.c
+++ b/sound/soc/soc-jack.c
@@ -29,24 +29,6 @@ struct jack_gpio_tbl {
 };
 
 /**
- * snd_soc_codec_set_jack - configure codec jack.
- * @codec: CODEC
- * @jack: structure to use for the jack
- * @data: can be used if codec driver need extra data for configuring jack
- *
- * Configures and enables jack detection function.
- */
-int snd_soc_codec_set_jack(struct snd_soc_codec *codec,
-	struct snd_soc_jack *jack, void *data)
-{
-	if (codec->driver->set_jack)
-		return codec->driver->set_jack(codec, jack, data);
-	else
-		return -ENOTSUPP;
-}
-EXPORT_SYMBOL_GPL(snd_soc_codec_set_jack);
-
-/**
  * snd_soc_component_set_jack - configure component jack.
  * @component: COMPONENTs
  * @jack: structure to use for the jack
@@ -57,10 +39,6 @@ EXPORT_SYMBOL_GPL(snd_soc_codec_set_jack);
 int snd_soc_component_set_jack(struct snd_soc_component *component,
 			       struct snd_soc_jack *jack, void *data)
 {
-	/* will be removed */
-	if (component->set_jack)
-		return component->set_jack(component, jack, data);
-
 	if (component->driver->set_jack)
 		return component->driver->set_jack(component, jack, data);
 
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 68d9dc930096..5e7ae47a9658 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -135,7 +135,6 @@ bool snd_soc_runtime_ignore_pmdown_time(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_component *component;
-	int i;
 	bool ignore = true;
 
 	if (!rtd->pmdown_time || rtd->dai_link->ignore_pmdown_time)
@@ -147,10 +146,6 @@ bool snd_soc_runtime_ignore_pmdown_time(struct snd_soc_pcm_runtime *rtd)
 		ignore &= !component->driver->use_pmdown_time;
 	}
 
-	/* this will be removed */
-	for (i = 0; i < rtd->num_codecs; i++)
-		ignore &= rtd->codec_dais[i]->component->ignore_pmdown_time;
-
 	return ignore;
 }
 
@@ -456,13 +451,12 @@ static void soc_pcm_init_runtime_hw(struct snd_pcm_substream *substream)
 /*
  * Called by ALSA when a PCM substream is opened, the runtime->hw record is
  * then initialized and any private data can be allocated. This also calls
- * startup for the cpu DAI, platform, machine and codec DAI.
+ * startup for the cpu DAI, component, machine and codec DAI.
  */
 static int soc_pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -492,23 +486,10 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 		}
 	}
 
-	if (platform && platform->driver->ops && platform->driver->ops->open) {
-		ret = platform->driver->ops->open(substream);
-		if (ret < 0) {
-			dev_err(platform->dev, "ASoC: can't open platform"
-				" %s: %d\n", platform->component.name, ret);
-			goto platform_err;
-		}
-	}
-
 	ret = 0;
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->open)
 			continue;
@@ -517,7 +498,7 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 		if (__ret < 0) {
 			dev_err(component->dev,
 				"ASoC: can't open component %s: %d\n",
-				component->name, ret);
+				component->name, __ret);
 			ret = __ret;
 		}
 	}
@@ -634,10 +615,6 @@ component_err:
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->close)
 			continue;
@@ -645,10 +622,6 @@ component_err:
 		component->driver->ops->close(substream);
 	}
 
-	if (platform && platform->driver->ops && platform->driver->ops->close)
-		platform->driver->ops->close(substream);
-
-platform_err:
 	if (cpu_dai->driver->ops->shutdown)
 		cpu_dai->driver->ops->shutdown(substream, cpu_dai);
 out:
@@ -701,13 +674,12 @@ static void close_delayed_work(struct work_struct *work)
 
 /*
  * Called by ALSA when a PCM substream is closed. Private data can be
- * freed here. The cpu DAI, codec DAI, machine and platform are also
+ * freed here. The cpu DAI, codec DAI, machine and components are also
  * shutdown.
  */
 static int soc_pcm_close(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -742,16 +714,9 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 	if (rtd->dai_link->ops->shutdown)
 		rtd->dai_link->ops->shutdown(substream);
 
-	if (platform && platform->driver->ops && platform->driver->ops->close)
-		platform->driver->ops->close(substream);
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->close)
 			continue;
@@ -805,7 +770,6 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 static int soc_pcm_prepare(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -823,22 +787,9 @@ static int soc_pcm_prepare(struct snd_pcm_substream *substream)
 		}
 	}
 
-	if (platform && platform->driver->ops && platform->driver->ops->prepare) {
-		ret = platform->driver->ops->prepare(substream);
-		if (ret < 0) {
-			dev_err(platform->dev, "ASoC: platform prepare error:"
-				" %d\n", ret);
-			goto out;
-		}
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->prepare)
 			continue;
@@ -932,7 +883,6 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -994,23 +944,10 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 	if (ret < 0)
 		goto interface_err;
 
-	if (platform && platform->driver->ops && platform->driver->ops->hw_params) {
-		ret = platform->driver->ops->hw_params(substream, params);
-		if (ret < 0) {
-			dev_err(platform->dev, "ASoC: %s hw params failed: %d\n",
-			       platform->component.name, ret);
-			goto platform_err;
-		}
-	}
-
 	ret = 0;
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->hw_params)
 			continue;
@@ -1019,7 +956,7 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 		if (__ret < 0) {
 			dev_err(component->dev,
 				"ASoC: %s hw params failed: %d\n",
-				component->name, ret);
+				component->name, __ret);
 			ret = __ret;
 		}
 	}
@@ -1043,10 +980,6 @@ component_err:
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->hw_free)
 			continue;
@@ -1054,10 +987,6 @@ component_err:
 		component->driver->ops->hw_free(substream);
 	}
 
-	if (platform && platform->driver->ops && platform->driver->ops->hw_free)
-		platform->driver->ops->hw_free(substream);
-
-platform_err:
 	if (cpu_dai->driver->ops->hw_free)
 		cpu_dai->driver->ops->hw_free(substream, cpu_dai);
 
@@ -1085,7 +1014,6 @@ codec_err:
 static int soc_pcm_hw_free(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -1123,18 +1051,10 @@ static int soc_pcm_hw_free(struct snd_pcm_substream *substream)
 	if (rtd->dai_link->ops->hw_free)
 		rtd->dai_link->ops->hw_free(substream);
 
-	/* free any DMA resources */
-	if (platform && platform->driver->ops && platform->driver->ops->hw_free)
-		platform->driver->ops->hw_free(substream);
-
 	/* free any component resources */
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->hw_free)
 			continue;
@@ -1159,7 +1079,6 @@ static int soc_pcm_hw_free(struct snd_pcm_substream *substream)
 static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -1176,19 +1095,9 @@ static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 		}
 	}
 
-	if (platform && platform->driver->ops && platform->driver->ops->trigger) {
-		ret = platform->driver->ops->trigger(substream, cmd);
-		if (ret < 0)
-			return ret;
-	}
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->trigger)
 			continue;
@@ -1240,13 +1149,12 @@ static int soc_pcm_bespoke_trigger(struct snd_pcm_substream *substream,
 }
 /*
  * soc level wrapper for pointer callback
- * If cpu_dai, codec_dai, platform driver has the delay callback, than
+ * If cpu_dai, codec_dai, component driver has the delay callback, then
  * the runtime->delay will be updated accordingly.
  */
 static snd_pcm_uframes_t soc_pcm_pointer(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
@@ -1257,16 +1165,9 @@ static snd_pcm_uframes_t soc_pcm_pointer(struct snd_pcm_substream *substream)
 	snd_pcm_sframes_t codec_delay = 0;
 	int i;
 
-	if (platform && platform->driver->ops && platform->driver->ops->pointer)
-		offset = platform->driver->ops->pointer(substream);
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->pointer)
 			continue;
@@ -1878,14 +1779,15 @@ static int dpcm_apply_symmetry(struct snd_pcm_substream *fe_substream,
 
 		/* Symmetry only applies if we've got an active stream. */
 		if (rtd->cpu_dai->active) {
-			err = soc_pcm_apply_symmetry(be_substream, rtd->cpu_dai);
+			err = soc_pcm_apply_symmetry(fe_substream,
+						     rtd->cpu_dai);
 			if (err < 0)
 				return err;
 		}
 
 		for (i = 0; i < rtd->num_codecs; i++) {
 			if (rtd->codec_dais[i]->active) {
-				err = soc_pcm_apply_symmetry(be_substream,
+				err = soc_pcm_apply_symmetry(fe_substream,
 							     rtd->codec_dais[i]);
 				if (err < 0)
 					return err;
@@ -1965,8 +1867,10 @@ int dpcm_be_dai_shutdown(struct snd_soc_pcm_runtime *fe, int stream)
 			continue;
 
 		if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_FREE) &&
-		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_OPEN))
-			continue;
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_OPEN)) {
+			soc_pcm_hw_free(be_substream);
+			be->dpcm[stream].state = SND_SOC_DPCM_STATE_HW_FREE;
+		}
 
 		dev_dbg(be->dev, "ASoC: close BE %s\n",
 			be->dai_link->name);
@@ -2470,20 +2374,12 @@ static int soc_pcm_ioctl(struct snd_pcm_substream *substream,
 		     unsigned int cmd, void *arg)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 
-	if (platform && platform->driver->ops && platform->driver->ops->ioctl)
-		return platform->driver->ops->ioctl(substream, cmd, arg);
-
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		/* ignore duplication for now */
-		if (platform && (component == &platform->component))
-			continue;
-
 		if (!component->driver->ops ||
 		    !component->driver->ops->ioctl)
 			continue;
@@ -2847,8 +2743,8 @@ static void soc_pcm_private_free(struct snd_pcm *pcm)
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		if (component->pcm_free)
-			component->pcm_free(component, pcm);
+		if (component->driver->pcm_free)
+			component->driver->pcm_free(pcm);
 	}
 }
 
@@ -2987,7 +2883,6 @@ static int soc_rtdcom_mmap(struct snd_pcm_substream *substream,
 /* create a new pcm */
 int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 {
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_dai *codec_dai;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_component *component;
@@ -3106,16 +3001,6 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 			rtd->ops.mmap		= soc_rtdcom_mmap;
 	}
 
-	/* overwrite */
-	if (platform && platform->driver->ops) {
-		rtd->ops.ack		= platform->driver->ops->ack;
-		rtd->ops.copy_user	= platform->driver->ops->copy_user;
-		rtd->ops.copy_kernel	= platform->driver->ops->copy_kernel;
-		rtd->ops.fill_silence	= platform->driver->ops->fill_silence;
-		rtd->ops.page		= platform->driver->ops->page;
-		rtd->ops.mmap		= platform->driver->ops->mmap;
-	}
-
 	if (playback)
 		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &rtd->ops);
 
@@ -3125,10 +3010,10 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
-		if (!component->pcm_new)
+		if (!component->driver->pcm_new)
 			continue;
 
-		ret = component->pcm_new(component, rtd);
+		ret = component->driver->pcm_new(rtd);
 		if (ret < 0) {
 			dev_err(component->dev,
 				"ASoC: pcm constructor failed: %d\n",
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index fa27d0fca6dc..3fd5d9c867b9 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -54,62 +54,6 @@
 #define SOC_TPLG_PASS_START	SOC_TPLG_PASS_MANIFEST
 #define SOC_TPLG_PASS_END	SOC_TPLG_PASS_LINK
 
-/*
- * Old version of ABI structs, supported for backward compatibility.
- */
-
-/* Manifest v4 */
-struct snd_soc_tplg_manifest_v4 {
-	__le32 size;		/* in bytes of this structure */
-	__le32 control_elems;	/* number of control elements */
-	__le32 widget_elems;	/* number of widget elements */
-	__le32 graph_elems;	/* number of graph elements */
-	__le32 pcm_elems;	/* number of PCM elements */
-	__le32 dai_link_elems;	/* number of DAI link elements */
-	struct snd_soc_tplg_private priv;
-} __packed;
-
-/* Stream Capabilities v4 */
-struct snd_soc_tplg_stream_caps_v4 {
-	__le32 size;		/* in bytes of this structure */
-	char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
-	__le64 formats;	/* supported formats SNDRV_PCM_FMTBIT_* */
-	__le32 rates;		/* supported rates SNDRV_PCM_RATE_* */
-	__le32 rate_min;	/* min rate */
-	__le32 rate_max;	/* max rate */
-	__le32 channels_min;	/* min channels */
-	__le32 channels_max;	/* max channels */
-	__le32 periods_min;	/* min number of periods */
-	__le32 periods_max;	/* max number of periods */
-	__le32 period_size_min;	/* min period size bytes */
-	__le32 period_size_max;	/* max period size bytes */
-	__le32 buffer_size_min;	/* min buffer size bytes */
-	__le32 buffer_size_max;	/* max buffer size bytes */
-} __packed;
-
-/* PCM v4 */
-struct snd_soc_tplg_pcm_v4 {
-	__le32 size;		/* in bytes of this structure */
-	char pcm_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
-	char dai_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
-	__le32 pcm_id;		/* unique ID - used to match with DAI link */
-	__le32 dai_id;		/* unique ID - used to match */
-	__le32 playback;	/* supports playback mode */
-	__le32 capture;		/* supports capture mode */
-	__le32 compress;	/* 1 = compressed; 0 = PCM */
-	struct snd_soc_tplg_stream stream[SND_SOC_TPLG_STREAM_CONFIG_MAX]; /* for DAI link */
-	__le32 num_streams;	/* number of streams */
-	struct snd_soc_tplg_stream_caps_v4 caps[2]; /* playback and capture for DAI */
-} __packed;
-
-/* Physical link config v4 */
-struct snd_soc_tplg_link_config_v4 {
-	__le32 size;            /* in bytes of this structure */
-	__le32 id;              /* unique ID - used to match */
-	struct snd_soc_tplg_stream stream[SND_SOC_TPLG_STREAM_CONFIG_MAX]; /* supported configs playback and captrure */
-	__le32 num_streams;     /* number of streams */
-} __packed;
-
 /* topology context */
 struct soc_tplg {
 	const struct firmware *fw;
@@ -513,7 +457,7 @@ static void remove_widget(struct snd_soc_component *comp,
 	 */
 	if (dobj->widget.kcontrol_type == SND_SOC_TPLG_TYPE_ENUM) {
 		/* enumerated widget mixer */
-		for (i = 0; i < w->num_kcontrols; i++) {
+		for (i = 0; w->kcontrols != NULL && i < w->num_kcontrols; i++) {
 			struct snd_kcontrol *kcontrol = w->kcontrols[i];
 			struct soc_enum *se =
 				(struct soc_enum *)kcontrol->private_value;
@@ -530,7 +474,7 @@ static void remove_widget(struct snd_soc_component *comp,
 		}
 	} else {
 		/* volume mixer or bytes controls */
-		for (i = 0; i < w->num_kcontrols; i++) {
+		for (i = 0; w->kcontrols != NULL && i < w->num_kcontrols; i++) {
 			struct snd_kcontrol *kcontrol = w->kcontrols[i];
 
 			if (dobj->widget.kcontrol_type
@@ -1325,8 +1269,10 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_denum_create(
 			ec->hdr.name);
 
 		kc[i].name = kstrdup(ec->hdr.name, GFP_KERNEL);
-		if (kc[i].name == NULL)
+		if (kc[i].name == NULL) {
+			kfree(se);
 			goto err_se;
+		}
 		kc[i].private_value = (long)se;
 		kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
 		kc[i].access = ec->hdr.access;
@@ -1442,8 +1388,10 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dbytes_create(
 			be->hdr.name, be->hdr.access);
 
 		kc[i].name = kstrdup(be->hdr.name, GFP_KERNEL);
-		if (kc[i].name == NULL)
+		if (kc[i].name == NULL) {
+			kfree(sbe);
 			goto err;
+		}
 		kc[i].private_value = (long)sbe;
 		kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
 		kc[i].access = be->hdr.access;
@@ -1750,6 +1698,9 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
 		set_stream_info(stream, caps);
 	}
 
+	if (pcm->compress)
+		dai_drv->compress_new = snd_soc_new_compress;
+
 	/* pass control to component driver for optional further init */
 	ret = soc_tplg_dai_load(tplg, dai_drv);
 	if (ret < 0) {
@@ -2002,6 +1953,21 @@ static void set_link_hw_format(struct snd_soc_dai_link *link,
 
 		link->dai_fmt = hw_config->fmt & SND_SOC_DAIFMT_FORMAT_MASK;
 
+		/* clock gating */
+		switch (hw_config->clock_gated) {
+		case SND_SOC_TPLG_DAI_CLK_GATE_GATED:
+			link->dai_fmt |= SND_SOC_DAIFMT_GATED;
+			break;
+
+		case SND_SOC_TPLG_DAI_CLK_GATE_CONT:
+			link->dai_fmt |= SND_SOC_DAIFMT_CONT;
+			break;
+
+		default:
+			/* ignore the value */
+			break;
+		}
+
 		/* clock signal polarity */
 		invert_bclk = hw_config->invert_bclk;
 		invert_fsync = hw_config->invert_fsync;
@@ -2015,13 +1981,15 @@ static void set_link_hw_format(struct snd_soc_dai_link *link,
 			link->dai_fmt |= SND_SOC_DAIFMT_IB_IF;
 
 		/* clock masters */
-		bclk_master = hw_config->bclk_master;
-		fsync_master = hw_config->fsync_master;
-		if (!bclk_master && !fsync_master)
+		bclk_master = (hw_config->bclk_master ==
+			       SND_SOC_TPLG_BCLK_CM);
+		fsync_master = (hw_config->fsync_master ==
+				SND_SOC_TPLG_FSYNC_CM);
+		if (bclk_master && fsync_master)
 			link->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
-		else if (bclk_master && !fsync_master)
-			link->dai_fmt |= SND_SOC_DAIFMT_CBS_CFM;
 		else if (!bclk_master && fsync_master)
+			link->dai_fmt |= SND_SOC_DAIFMT_CBS_CFM;
+		else if (bclk_master && !fsync_master)
 			link->dai_fmt |= SND_SOC_DAIFMT_CBM_CFS;
 		else
 			link->dai_fmt |= SND_SOC_DAIFMT_CBS_CFS;
@@ -2289,8 +2257,11 @@ static int manifest_new_ver(struct soc_tplg *tplg,
 	*manifest = NULL;
 
 	if (src->size != sizeof(*src_v4)) {
-		dev_err(tplg->dev, "ASoC: invalid manifest size\n");
-		return -EINVAL;
+		dev_warn(tplg->dev, "ASoC: invalid manifest size %d\n",
+			 src->size);
+		if (src->size)
+			return -EINVAL;
+		src->size = sizeof(*src_v4);
 	}
 
 	dev_warn(tplg->dev, "ASoC: old version of manifest\n");
@@ -2576,7 +2547,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index)
 
 			/* match index */
 			if (dobj->index != index &&
-				dobj->index != SND_SOC_TPLG_INDEX_ALL)
+				index != SND_SOC_TPLG_INDEX_ALL)
 				continue;
 
 			switch (dobj->type) {
diff --git a/sound/soc/uniphier/aio-compress.c b/sound/soc/uniphier/aio-compress.c
index 4c1027aa615e..17f773ac5ca1 100644
--- a/sound/soc/uniphier/aio-compress.c
+++ b/sound/soc/uniphier/aio-compress.c
@@ -3,19 +3,6 @@
 // Socionext UniPhier AIO Compress Audio driver.
 //
 // Copyright (c) 2017-2018 Socionext Inc.
-//
-// This program is free software; you can redistribute it and/or
-// modify it under the terms of the GNU General Public License
-// as published by the Free Software Foundation; version 2
-// of the License.
-//
-// This program is distributed in the hope that it will be useful,
-// but WITHOUT ANY WARRANTY; without even the implied warranty of
-// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-// GNU General Public License for more details.
-//
-// You should have received a copy of the GNU General Public License
-// along with this program; if not, see <http://www.gnu.org/licenses/>.
 
 #include <linux/bitfield.h>
 #include <linux/circ_buf.h>
diff --git a/sound/soc/uniphier/aio-core.c b/sound/soc/uniphier/aio-core.c
index 6d50042a4571..638cb3fc5f7b 100644
--- a/sound/soc/uniphier/aio-core.c
+++ b/sound/soc/uniphier/aio-core.c
@@ -3,19 +3,6 @@
 // Socionext UniPhier AIO ALSA common driver.
 //
 // Copyright (c) 2016-2018 Socionext Inc.
-//
-// This program is free software; you can redistribute it and/or
-// modify it under the terms of the GNU General Public License
-// as published by the Free Software Foundation; version 2
-// of the License.
-//
-// This program is distributed in the hope that it will be useful,
-// but WITHOUT ANY WARRANTY; without even the implied warranty of
-// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-// GNU General Public License for more details.
-//
-// You should have received a copy of the GNU General Public License
-// along with this program; if not, see <http://www.gnu.org/licenses/>.
 
 #include <linux/bitfield.h>
 #include <linux/errno.h>
@@ -673,6 +660,64 @@ void aio_port_set_enable(struct uniphier_aio_sub *sub, int enable)
 }
 
 /**
+ * aio_port_get_volume - get volume of AIO port block
+ * @sub: the AIO substream pointer
+ *
+ * Return: current volume, range is 0x0000 - 0xffff
+ */
+int aio_port_get_volume(struct uniphier_aio_sub *sub)
+{
+	struct regmap *r = sub->aio->chip->regmap;
+	u32 v;
+
+	regmap_read(r, OPORTMXTYVOLGAINSTATUS(sub->swm->oport.map, 0), &v);
+
+	return FIELD_GET(OPORTMXTYVOLGAINSTATUS_CUR_MASK, v);
+}
+
+/**
+ * aio_port_set_volume - set volume of AIO port block
+ * @sub: the AIO substream pointer
+ * @vol: target volume, range is 0x0000 - 0xffff.
+ *
+ * Change digital volume and perfome fade-out/fade-in effect for specified
+ * output slot of port. Gained PCM value can calculate as the following:
+ *   Gained = Original * vol / 0x4000
+ */
+void aio_port_set_volume(struct uniphier_aio_sub *sub, int vol)
+{
+	struct regmap *r = sub->aio->chip->regmap;
+	int oport_map = sub->swm->oport.map;
+	int cur, diff, slope = 0, fs;
+
+	if (sub->swm->dir == PORT_DIR_INPUT)
+		return;
+
+	cur = aio_port_get_volume(sub);
+	diff = abs(vol - cur);
+	fs = params_rate(&sub->params);
+	if (fs)
+		slope = diff / AUD_VOL_FADE_TIME * 1000 / fs;
+	slope = max(1, slope);
+
+	regmap_update_bits(r, OPORTMXTYVOLPARA1(oport_map, 0),
+			   OPORTMXTYVOLPARA1_SLOPEU_MASK, slope << 16);
+	regmap_update_bits(r, OPORTMXTYVOLPARA2(oport_map, 0),
+			   OPORTMXTYVOLPARA2_TARGET_MASK, vol);
+
+	if (cur < vol)
+		regmap_update_bits(r, OPORTMXTYVOLPARA2(oport_map, 0),
+				   OPORTMXTYVOLPARA2_FADE_MASK,
+				   OPORTMXTYVOLPARA2_FADE_FADEIN);
+	else
+		regmap_update_bits(r, OPORTMXTYVOLPARA2(oport_map, 0),
+				   OPORTMXTYVOLPARA2_FADE_MASK,
+				   OPORTMXTYVOLPARA2_FADE_FADEOUT);
+
+	regmap_write(r, AOUTFADECTR0, BIT(oport_map));
+}
+
+/**
  * aio_if_set_param - set parameters of AIO DMA I/F block
  * @sub: the AIO substream pointer
  * @pass_through: Zero if sound data is LPCM, otherwise if data is not LPCM.
diff --git a/sound/soc/uniphier/aio-cpu.c b/sound/soc/uniphier/aio-cpu.c
index 1e5eb8e6f8c7..80daec17be25 100644
--- a/sound/soc/uniphier/aio-cpu.c
+++ b/sound/soc/uniphier/aio-cpu.c
@@ -3,19 +3,6 @@
 // Socionext UniPhier AIO ALSA CPU DAI driver.
 //
 // Copyright (c) 2016-2018 Socionext Inc.
-//
-// This program is free software; you can redistribute it and/or
-// modify it under the terms of the GNU General Public License
-// as published by the Free Software Foundation; version 2
-// of the License.
-//
-// This program is distributed in the hope that it will be useful,
-// but WITHOUT ANY WARRANTY; without even the implied warranty of
-// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-// GNU General Public License for more details.
-//
-// You should have received a copy of the GNU General Public License
-// along with this program; if not, see <http://www.gnu.org/licenses/>.
 
 #include <linux/clk.h>
 #include <linux/errno.h>
@@ -45,6 +32,35 @@ static bool is_valid_pll(struct uniphier_aio_chip *chip, int pll_id)
 	return chip->plls[pll_id].enable;
 }
 
+/**
+ * find_volume - find volume supported HW port by HW port number
+ * @chip: the AIO chip pointer
+ * @oport_hw: HW port number, one of AUD_HW_XXXX
+ *
+ * Find AIO device from device list by HW port number. Volume feature is
+ * available only in Output and PCM ports, this limitation comes from HW
+ * specifications.
+ *
+ * Return: The pointer of AIO substream if successful, otherwise NULL on error.
+ */
+static struct uniphier_aio_sub *find_volume(struct uniphier_aio_chip *chip,
+					    int oport_hw)
+{
+	int i;
+
+	for (i = 0; i < chip->num_aios; i++) {
+		struct uniphier_aio_sub *sub = &chip->aios[i].sub[0];
+
+		if (!sub->swm)
+			continue;
+
+		if (sub->swm->oport.hw == oport_hw)
+			return sub;
+	}
+
+	return NULL;
+}
+
 static bool match_spec(const struct uniphier_aio_spec *spec,
 		       const char *name, int dir)
 {
@@ -300,6 +316,7 @@ static int uniphier_aio_hw_params(struct snd_pcm_substream *substream,
 	sub->setting = 1;
 
 	aio_port_reset(sub);
+	aio_port_set_volume(sub, sub->vol);
 	aio_src_reset(sub);
 
 	return 0;
@@ -386,6 +403,8 @@ int uniphier_aio_dai_probe(struct snd_soc_dai *dai)
 
 		sub->swm = &spec->swm;
 		sub->spec = spec;
+
+		sub->vol = AUD_VOL_INIT;
 	}
 
 	aio_iecout_set_enable(aio->chip, true);
@@ -462,8 +481,116 @@ err_out_clock:
 }
 EXPORT_SYMBOL_GPL(uniphier_aio_dai_resume);
 
+static int uniphier_aio_vol_info(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_info *uinfo)
+{
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
+	uinfo->count = 1;
+	uinfo->value.integer.min = 0;
+	uinfo->value.integer.max = AUD_VOL_MAX;
+
+	return 0;
+}
+
+static int uniphier_aio_vol_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct uniphier_aio_chip *chip = snd_soc_component_get_drvdata(comp);
+	struct uniphier_aio_sub *sub;
+	int oport_hw = kcontrol->private_value;
+
+	sub = find_volume(chip, oport_hw);
+	if (!sub)
+		return 0;
+
+	ucontrol->value.integer.value[0] = sub->vol;
+
+	return 0;
+}
+
+static int uniphier_aio_vol_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct uniphier_aio_chip *chip = snd_soc_component_get_drvdata(comp);
+	struct uniphier_aio_sub *sub;
+	int oport_hw = kcontrol->private_value;
+
+	sub = find_volume(chip, oport_hw);
+	if (!sub)
+		return 0;
+
+	if (sub->vol == ucontrol->value.integer.value[0])
+		return 0;
+	sub->vol = ucontrol->value.integer.value[0];
+
+	aio_port_set_volume(sub, sub->vol);
+
+	return 0;
+}
+
+static const struct snd_kcontrol_new uniphier_aio_controls[] = {
+	{
+		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+		.access = SNDRV_CTL_ELEM_ACCESS_READWRITE,
+		.name = "HPCMOUT1 Volume",
+		.info = uniphier_aio_vol_info,
+		.get = uniphier_aio_vol_get,
+		.put = uniphier_aio_vol_put,
+		.private_value = AUD_HW_HPCMOUT1,
+	},
+	{
+		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+		.access = SNDRV_CTL_ELEM_ACCESS_READWRITE,
+		.name = "PCMOUT1 Volume",
+		.info = uniphier_aio_vol_info,
+		.get = uniphier_aio_vol_get,
+		.put = uniphier_aio_vol_put,
+		.private_value = AUD_HW_PCMOUT1,
+	},
+	{
+		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+		.access = SNDRV_CTL_ELEM_ACCESS_READWRITE,
+		.name = "PCMOUT2 Volume",
+		.info = uniphier_aio_vol_info,
+		.get = uniphier_aio_vol_get,
+		.put = uniphier_aio_vol_put,
+		.private_value = AUD_HW_PCMOUT2,
+	},
+	{
+		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+		.access = SNDRV_CTL_ELEM_ACCESS_READWRITE,
+		.name = "PCMOUT3 Volume",
+		.info = uniphier_aio_vol_info,
+		.get = uniphier_aio_vol_get,
+		.put = uniphier_aio_vol_put,
+		.private_value = AUD_HW_PCMOUT3,
+	},
+	{
+		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+		.access = SNDRV_CTL_ELEM_ACCESS_READWRITE,
+		.name = "HIECOUT1 Volume",
+		.info = uniphier_aio_vol_info,
+		.get = uniphier_aio_vol_get,
+		.put = uniphier_aio_vol_put,
+		.private_value = AUD_HW_HIECOUT1,
+	},
+	{
+		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+		.access = SNDRV_CTL_ELEM_ACCESS_READWRITE,
+		.name = "IECOUT1 Volume",
+		.info = uniphier_aio_vol_info,
+		.get = uniphier_aio_vol_get,
+		.put = uniphier_aio_vol_put,
+		.private_value = AUD_HW_IECOUT1,
+	},
+};
+
 static const struct snd_soc_component_driver uniphier_aio_component = {
 	.name = "uniphier-aio",
+	.controls = uniphier_aio_controls,
+	.num_controls = ARRAY_SIZE(uniphier_aio_controls),
 };
 
 int uniphier_aio_probe(struct platform_device *pdev)
diff --git a/sound/soc/uniphier/aio-dma.c b/sound/soc/uniphier/aio-dma.c
index ef7bafa8e171..4ec6b65bfb44 100644
--- a/sound/soc/uniphier/aio-dma.c
+++ b/sound/soc/uniphier/aio-dma.c
@@ -3,19 +3,6 @@
 // Socionext UniPhier AIO DMA driver.
 //
 // Copyright (c) 2016-2018 Socionext Inc.
-//
-// This program is free software; you can redistribute it and/or
-// modify it under the terms of the GNU General Public License
-// as published by the Free Software Foundation; version 2
-// of the License.
-//
-// This program is distributed in the hope that it will be useful,
-// but WITHOUT ANY WARRANTY; without even the implied warranty of
-// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-// GNU General Public License for more details.
-//
-// You should have received a copy of the GNU General Public License
-// along with this program; if not, see <http://www.gnu.org/licenses/>.
 
 #include <linux/dma-mapping.h>
 #include <linux/errno.h>
diff --git a/sound/soc/uniphier/aio-ld11.c b/sound/soc/uniphier/aio-ld11.c
index 4c4dd3dd4dee..ab04d3331be9 100644
--- a/sound/soc/uniphier/aio-ld11.c
+++ b/sound/soc/uniphier/aio-ld11.c
@@ -3,19 +3,6 @@
 // Socionext UniPhier AIO ALSA driver for LD11/LD20.
 //
 // Copyright (c) 2016-2018 Socionext Inc.
-//
-// This program is free software; you can redistribute it and/or
-// modify it under the terms of the GNU General Public License
-// as published by the Free Software Foundation; version 2
-// of the License.
-//
-// This program is distributed in the hope that it will be useful,
-// but WITHOUT ANY WARRANTY; without even the implied warranty of
-// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-// GNU General Public License for more details.
-//
-// You should have received a copy of the GNU General Public License
-// along with this program; if not, see <http://www.gnu.org/licenses/>.
 
 #include <linux/module.h>
 
diff --git a/sound/soc/uniphier/aio-reg.h b/sound/soc/uniphier/aio-reg.h
index 136d3563cf44..45fdc6ae358a 100644
--- a/sound/soc/uniphier/aio-reg.h
+++ b/sound/soc/uniphier/aio-reg.h
@@ -3,19 +3,6 @@
  * Socionext UniPhier AIO ALSA driver.
  *
  * Copyright (c) 2016-2018 Socionext Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef SND_UNIPHIER_AIO_REG_H__
@@ -182,6 +169,7 @@
 #define PBINMXPAUSECTR1(n)               (0x20208 + 0x40 * (n))
 
 /* AOUT */
+#define AOUTFADECTR0                     0x40020
 #define AOUTENCTR0                       0x40040
 #define AOUTENCTR1                       0x40044
 #define AOUTENCTR2                       0x40048
@@ -192,6 +180,9 @@
 #define AOUTSRCRSTCTR1                   0x400c4
 #define AOUTSRCRSTCTR2                   0x400c8
 
+/* AOUT PCMOUT has 5 slots, slot0-3: D0-3, slot4: DMIX */
+#define OPORT_SLOT_MAX                     5
+
 /* AOUT(PCMOUTN) */
 #define OPORTMXCTR1(n)                   (0x42000 + 0x400 * (n))
 #define   OPORTMXCTR1_I2SLRSEL_MASK        (0x11 << 10)
@@ -372,11 +363,30 @@
 #define   OPORTMXMASK_XCKMSK_ON            (0x0 << 0)
 #define   OPORTMXMASK_XCKMSK_OFF           (0x7 << 0)
 #define OPORTMXDEBUG(n)                  (0x420fc + 0x400 * (n))
-#define OPORTMXT0RSTCTR(n)               (0x4211c + 0x400 * (n))
-#define OPORTMXT1RSTCTR(n)               (0x4213c + 0x400 * (n))
-#define OPORTMXT2RSTCTR(n)               (0x4215c + 0x400 * (n))
-#define OPORTMXT3RSTCTR(n)               (0x4217c + 0x400 * (n))
-#define OPORTMXT4RSTCTR(n)               (0x4219c + 0x400 * (n))
+#define OPORTMXTYVOLPARA1(n, m)          (0x42100 + 0x400 * (n) + 0x20 * (m))
+#define   OPORTMXTYVOLPARA1_SLOPEU_MASK    GENMASK(31, 16)
+#define OPORTMXTYVOLPARA2(n, m)          (0x42104 + 0x400 * (n) + 0x20 * (m))
+#define   OPORTMXTYVOLPARA2_FADE_MASK      GENMASK(17, 16)
+#define   OPORTMXTYVOLPARA2_FADE_NOOP      (0x0 << 16)
+#define   OPORTMXTYVOLPARA2_FADE_FADEOUT   (0x1 << 16)
+#define   OPORTMXTYVOLPARA2_FADE_FADEIN    (0x2 << 16)
+#define   OPORTMXTYVOLPARA2_TARGET_MASK    GENMASK(15, 0)
+#define OPORTMXTYVOLGAINSTATUS(n, m)     (0x42108 + 0x400 * (n) + 0x20 * (m))
+#define   OPORTMXTYVOLGAINSTATUS_CUR_MASK  GENMASK(15, 0)
+#define OPORTMXTYSLOTCTR(n, m)           (0x42114 + 0x400 * (n) + 0x20 * (m))
+#define   OPORTMXTYSLOTCTR_SLOTSEL_MASK    GENMASK(11, 8)
+#define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT0   (0x8 << 8)
+#define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT1   (0x9 << 8)
+#define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT2   (0xa << 8)
+#define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT3   (0xb << 8)
+#define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT4   (0xc << 8)
+#define   OPORTMXT0SLOTCTR_MUTEOFF_MASK    BIT(1)
+#define   OPORTMXT0SLOTCTR_MUTEOFF_MUTE    (0x0 << 1)
+#define   OPORTMXT0SLOTCTR_MUTEOFF_UNMUTE  (0x1 << 1)
+#define OPORTMXTYRSTCTR(n, m)            (0x4211c + 0x400 * (n) + 0x20 * (m))
+#define   OPORTMXT0RSTCTR_RST_MASK         BIT(1)
+#define   OPORTMXT0RSTCTR_RST_OFF          (0x0 << 1)
+#define   OPORTMXT0RSTCTR_RST_ON           (0x1 << 1)
 
 #define SBF_(frame, shift)    (((frame) * 2 - 1) << shift)
 
diff --git a/sound/soc/uniphier/aio.h b/sound/soc/uniphier/aio.h
index 8cab4a553a97..aa89c2f6fa24 100644
--- a/sound/soc/uniphier/aio.h
+++ b/sound/soc/uniphier/aio.h
@@ -3,19 +3,6 @@
  * Socionext UniPhier AIO ALSA driver.
  *
  * Copyright (c) 2016-2018 Socionext Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef SND_UNIPHIER_AIO_H__
@@ -143,6 +130,10 @@ enum IEC61937_PC {
 #define AUD_PLLDIV_1_1    2
 #define AUD_PLLDIV_2_3    3
 
+#define AUD_VOL_INIT         0x4000 /* +0dB */
+#define AUD_VOL_MAX          0xffff /* +6dB */
+#define AUD_VOL_FADE_TIME    20 /* 20ms */
+
 #define AUD_RING_SIZE            (128 * 1024)
 
 #define AUD_MIN_FRAGMENT         4
@@ -244,6 +235,7 @@ struct uniphier_aio_sub {
 	/* For PCM audio */
 	struct snd_pcm_substream *substream;
 	struct snd_pcm_hw_params params;
+	int vol;
 
 	/* For compress audio */
 	struct snd_compr_stream *cstream;
@@ -336,6 +328,8 @@ int aio_port_set_clk(struct uniphier_aio_sub *sub);
 int aio_port_set_param(struct uniphier_aio_sub *sub, int pass_through,
 		       const struct snd_pcm_hw_params *params);
 void aio_port_set_enable(struct uniphier_aio_sub *sub, int enable);
+int aio_port_get_volume(struct uniphier_aio_sub *sub);
+void aio_port_set_volume(struct uniphier_aio_sub *sub, int vol);
 int aio_if_set_param(struct uniphier_aio_sub *sub, int pass_through);
 int aio_oport_set_stream_type(struct uniphier_aio_sub *sub,
 			      enum IEC61937_PC pc);
diff --git a/sound/soc/uniphier/evea.c b/sound/soc/uniphier/evea.c
index 73fd6730095c..f9c10165fbc1 100644
--- a/sound/soc/uniphier/evea.c
+++ b/sound/soc/uniphier/evea.c
@@ -54,8 +54,21 @@ struct evea_priv {
 	int switch_hp;
 };
 
+static const char * const linsw1_sel1_text[] = {
+	"LIN1", "LIN2", "LIN3"
+};
+
+static SOC_ENUM_SINGLE_DECL(linsw1_sel1_enum,
+	ALINSW1, ALINSW1_SEL1_SHIFT,
+	linsw1_sel1_text);
+
+static const struct snd_kcontrol_new linesw1_mux[] = {
+	SOC_DAPM_ENUM("Line In 1 Source", linsw1_sel1_enum),
+};
+
 static const struct snd_soc_dapm_widget evea_widgets[] = {
-	SND_SOC_DAPM_ADC("ADC", "Capture", SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_ADC("ADC", NULL, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("Line In 1 Mux", SND_SOC_NOPM, 0, 0, linesw1_mux),
 	SND_SOC_DAPM_INPUT("LIN1_LP"),
 	SND_SOC_DAPM_INPUT("LIN1_RP"),
 	SND_SOC_DAPM_INPUT("LIN2_LP"),
@@ -63,7 +76,9 @@ static const struct snd_soc_dapm_widget evea_widgets[] = {
 	SND_SOC_DAPM_INPUT("LIN3_LP"),
 	SND_SOC_DAPM_INPUT("LIN3_RP"),
 
-	SND_SOC_DAPM_DAC("DAC", "Playback", SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_DAC("DAC HP", NULL, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_DAC("DAC LO1", NULL, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_DAC("DAC LO2", NULL, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_OUTPUT("HP1_L"),
 	SND_SOC_DAPM_OUTPUT("HP1_R"),
 	SND_SOC_DAPM_OUTPUT("LO2_L"),
@@ -71,17 +86,22 @@ static const struct snd_soc_dapm_widget evea_widgets[] = {
 };
 
 static const struct snd_soc_dapm_route evea_routes[] = {
-	{ "ADC", NULL, "LIN1_LP" },
-	{ "ADC", NULL, "LIN1_RP" },
-	{ "ADC", NULL, "LIN2_LP" },
-	{ "ADC", NULL, "LIN2_RP" },
-	{ "ADC", NULL, "LIN3_LP" },
-	{ "ADC", NULL, "LIN3_RP" },
-
-	{ "HP1_L", NULL, "DAC" },
-	{ "HP1_R", NULL, "DAC" },
-	{ "LO2_L", NULL, "DAC" },
-	{ "LO2_R", NULL, "DAC" },
+	{ "Line In 1", NULL, "ADC" },
+	{ "ADC", NULL, "Line In 1 Mux" },
+	{ "Line In 1 Mux", "LIN1", "LIN1_LP" },
+	{ "Line In 1 Mux", "LIN1", "LIN1_RP" },
+	{ "Line In 1 Mux", "LIN2", "LIN2_LP" },
+	{ "Line In 1 Mux", "LIN2", "LIN2_RP" },
+	{ "Line In 1 Mux", "LIN3", "LIN3_LP" },
+	{ "Line In 1 Mux", "LIN3", "LIN3_RP" },
+
+	{ "DAC HP", NULL, "Headphone 1" },
+	{ "DAC LO1", NULL, "Line Out 1" },
+	{ "DAC LO2", NULL, "Line Out 2" },
+	{ "HP1_L", NULL, "DAC HP" },
+	{ "HP1_R", NULL, "DAC HP" },
+	{ "LO2_L", NULL, "DAC LO2" },
+	{ "LO2_R", NULL, "DAC LO2" },
 };
 
 static void evea_set_power_state_on(struct evea_priv *evea)
@@ -280,16 +300,7 @@ static int evea_set_switch_hp(struct snd_kcontrol *kcontrol,
 	return evea_update_switch_hp(evea);
 }
 
-static const char * const linsw1_sel1_text[] = {
-	"LIN1", "LIN2", "LIN3"
-};
-
-static SOC_ENUM_SINGLE_DECL(linsw1_sel1_enum,
-	ALINSW1, ALINSW1_SEL1_SHIFT,
-	linsw1_sel1_text);
-
 static const struct snd_kcontrol_new evea_controls[] = {
-	SOC_ENUM("Line Capture Source", linsw1_sel1_enum),
 	SOC_SINGLE_BOOL_EXT("Line Capture Switch", 0,
 			    evea_get_switch_lin, evea_set_switch_lin),
 	SOC_SINGLE_BOOL_EXT("Line Playback Switch", 0,
diff --git a/sound/soc/zte/zx-i2s.c b/sound/soc/zte/zx-i2s.c
index 9a0565937d1f..0d36630aa1a7 100644
--- a/sound/soc/zte/zx-i2s.c
+++ b/sound/soc/zte/zx-i2s.c
@@ -20,9 +20,6 @@
 #include <sound/core.h>
 #include <sound/dmaengine_pcm.h>
 #include <sound/initval.h>
-#include <sound/pcm.h>
-#include <sound/pcm_params.h>
-#include <sound/soc.h>
 
 #define ZX_I2S_PROCESS_CTRL	0x04
 #define ZX_I2S_TIMING_CTRL	0x08
@@ -197,7 +194,7 @@ static int zx_i2s_set_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
 		val |= (ZX_I2S_TIMING_I2S | ZX_I2S_TIMING_LSB_JUSTIF);
 		break;
 	default:
-		dev_err(cpu_dai->dev, "Unknown i2s timeing\n");
+		dev_err(cpu_dai->dev, "Unknown i2s timing\n");
 		return -EINVAL;
 	}
 
diff --git a/sound/sound_core.c b/sound/sound_core.c
index b4efb22db561..40ad000c2e3c 100644
--- a/sound/sound_core.c
+++ b/sound/sound_core.c
@@ -413,7 +413,7 @@ int register_sound_special_device(const struct file_operations *fops, int unit,
 		break;
 	}
 	return sound_insert_unit(&chains[chain], fops, -1, unit, max_unit,
-				 name, S_IRUSR | S_IWUSR, dev);
+				 name, 0600, dev);
 }
  
 EXPORT_SYMBOL(register_sound_special_device);
@@ -440,7 +440,7 @@ EXPORT_SYMBOL(register_sound_special);
 int register_sound_mixer(const struct file_operations *fops, int dev)
 {
 	return sound_insert_unit(&chains[0], fops, dev, 0, 128,
-				 "mixer", S_IRUSR | S_IWUSR, NULL);
+				 "mixer", 0600, NULL);
 }
 
 EXPORT_SYMBOL(register_sound_mixer);
@@ -468,7 +468,7 @@ EXPORT_SYMBOL(register_sound_mixer);
 int register_sound_dsp(const struct file_operations *fops, int dev)
 {
 	return sound_insert_unit(&chains[3], fops, dev, 3, 131,
-				 "dsp", S_IWUSR | S_IRUSR, NULL);
+				 "dsp", 0600, NULL);
 }
 
 EXPORT_SYMBOL(register_sound_dsp);
diff --git a/sound/sparc/dbri.c b/sound/sparc/dbri.c
index abc7bd5055eb..7609eceba1a2 100644
--- a/sound/sparc/dbri.c
+++ b/sound/sparc/dbri.c
@@ -2518,7 +2518,7 @@ static void snd_dbri_proc(struct snd_card *card)
 #ifdef DBRI_DEBUG
 	if (!snd_card_proc_new(card, "debug", &entry)) {
 		snd_info_set_text_ops(entry, dbri, dbri_debug_read);
-		entry->mode = S_IFREG | S_IRUGO;	/* Readable only. */
+		entry->mode = S_IFREG | 0444;	/* Readable only. */
 	}
 #endif
 }
@@ -2542,7 +2542,7 @@ static int snd_dbri_create(struct snd_card *card,
 	dbri->irq = irq;
 
 	dbri->dma = dma_zalloc_coherent(&op->dev, sizeof(struct dbri_dma),
-					&dbri->dma_dvma, GFP_ATOMIC);
+					&dbri->dma_dvma, GFP_KERNEL);
 	if (!dbri->dma)
 		return -ENOMEM;
 
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 4a1c6bb3dfa0..a1ed798a1c6b 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -86,6 +86,8 @@ static bool ignore_ctl_error;
 static bool autoclock = true;
 static char *quirk_alias[SNDRV_CARDS];
 
+bool snd_usb_use_vmalloc = true;
+
 module_param_array(index, int, NULL, 0444);
 MODULE_PARM_DESC(index, "Index value for the USB audio adapter.");
 module_param_array(id, charp, NULL, 0444);
@@ -105,6 +107,8 @@ module_param(autoclock, bool, 0444);
 MODULE_PARM_DESC(autoclock, "Enable auto-clock selection for UAC2 devices (default: yes).");
 module_param_array(quirk_alias, charp, NULL, 0444);
 MODULE_PARM_DESC(quirk_alias, "Quirk aliases, e.g. 0123abcd:5678beef.");
+module_param_named(use_vmalloc, snd_usb_use_vmalloc, bool, 0444);
+MODULE_PARM_DESC(use_vmalloc, "Use vmalloc for PCM intermediate buffers (default: yes).");
 
 /*
  * we keep the snd_usb_audio_t instances by ourselves for merging
@@ -221,32 +225,13 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif)
 	struct usb_device *dev = chip->dev;
 	struct usb_host_interface *host_iface;
 	struct usb_interface_descriptor *altsd;
-	void *control_header;
 	int i, protocol;
-	int rest_bytes;
 
 	/* find audiocontrol interface */
 	host_iface = &usb_ifnum_to_if(dev, ctrlif)->altsetting[0];
-	control_header = snd_usb_find_csint_desc(host_iface->extra,
-						 host_iface->extralen,
-						 NULL, UAC_HEADER);
 	altsd = get_iface_desc(host_iface);
 	protocol = altsd->bInterfaceProtocol;
 
-	if (!control_header) {
-		dev_err(&dev->dev, "cannot find UAC_HEADER\n");
-		return -EINVAL;
-	}
-
-	rest_bytes = (void *)(host_iface->extra + host_iface->extralen) -
-		control_header;
-
-	/* just to be sure -- this shouldn't hit at all */
-	if (rest_bytes <= 0) {
-		dev_err(&dev->dev, "invalid control header\n");
-		return -EINVAL;
-	}
-
 	switch (protocol) {
 	default:
 		dev_warn(&dev->dev,
@@ -255,7 +240,25 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif)
 		/* fall through */
 
 	case UAC_VERSION_1: {
-		struct uac1_ac_header_descriptor *h1 = control_header;
+		struct uac1_ac_header_descriptor *h1;
+		int rest_bytes;
+
+		h1 = snd_usb_find_csint_desc(host_iface->extra,
+							 host_iface->extralen,
+							 NULL, UAC_HEADER);
+		if (!h1) {
+			dev_err(&dev->dev, "cannot find UAC_HEADER\n");
+			return -EINVAL;
+		}
+
+		rest_bytes = (void *)(host_iface->extra +
+				host_iface->extralen) - (void *)h1;
+
+		/* just to be sure -- this shouldn't hit at all */
+		if (rest_bytes <= 0) {
+			dev_err(&dev->dev, "invalid control header\n");
+			return -EINVAL;
+		}
 
 		if (rest_bytes < sizeof(*h1)) {
 			dev_err(&dev->dev, "too short v1 buffer descriptor\n");
@@ -308,6 +311,20 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif)
 			return -EINVAL;
 		}
 
+		if (protocol == UAC_VERSION_3) {
+			int badd = assoc->bFunctionSubClass;
+
+			if (badd != UAC3_FUNCTION_SUBCLASS_FULL_ADC_3_0 &&
+			    (badd < UAC3_FUNCTION_SUBCLASS_GENERIC_IO ||
+			     badd > UAC3_FUNCTION_SUBCLASS_SPEAKERPHONE)) {
+				dev_err(&dev->dev,
+					"Unsupported UAC3 BADD profile\n");
+				return -EINVAL;
+			}
+
+			chip->badd_profile = badd;
+		}
+
 		for (i = 0; i < assoc->bInterfaceCount; i++) {
 			int intf = assoc->bFirstInterface + i;
 
@@ -329,8 +346,9 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif)
  *
  */
 
-static int snd_usb_audio_free(struct snd_usb_audio *chip)
+static void snd_usb_audio_free(struct snd_card *card)
 {
+	struct snd_usb_audio *chip = card->private_data;
 	struct snd_usb_endpoint *ep, *n;
 
 	list_for_each_entry_safe(ep, n, &chip->ep_list, list)
@@ -339,14 +357,90 @@ static int snd_usb_audio_free(struct snd_usb_audio *chip)
 	mutex_destroy(&chip->mutex);
 	if (!atomic_read(&chip->shutdown))
 		dev_set_drvdata(&chip->dev->dev, NULL);
-	kfree(chip);
-	return 0;
 }
 
-static int snd_usb_audio_dev_free(struct snd_device *device)
+static void usb_audio_make_shortname(struct usb_device *dev,
+				     struct snd_usb_audio *chip,
+				     const struct snd_usb_audio_quirk *quirk)
 {
-	struct snd_usb_audio *chip = device->device_data;
-	return snd_usb_audio_free(chip);
+	struct snd_card *card = chip->card;
+
+	if (quirk && quirk->product_name && *quirk->product_name) {
+		strlcpy(card->shortname, quirk->product_name,
+			sizeof(card->shortname));
+		return;
+	}
+
+	/* retrieve the device string as shortname */
+	if (!dev->descriptor.iProduct ||
+	    usb_string(dev, dev->descriptor.iProduct,
+		       card->shortname, sizeof(card->shortname)) <= 0) {
+		/* no name available from anywhere, so use ID */
+		sprintf(card->shortname, "USB Device %#04x:%#04x",
+			USB_ID_VENDOR(chip->usb_id),
+			USB_ID_PRODUCT(chip->usb_id));
+	}
+
+	strim(card->shortname);
+}
+
+static void usb_audio_make_longname(struct usb_device *dev,
+				    struct snd_usb_audio *chip,
+				    const struct snd_usb_audio_quirk *quirk)
+{
+	struct snd_card *card = chip->card;
+	int len;
+
+	/* shortcut - if any pre-defined string is given, use it */
+	if (quirk && quirk->profile_name && *quirk->profile_name) {
+		strlcpy(card->longname, quirk->profile_name,
+			sizeof(card->longname));
+		return;
+	}
+
+	if (quirk && quirk->vendor_name && *quirk->vendor_name) {
+		len = strlcpy(card->longname, quirk->vendor_name, sizeof(card->longname));
+	} else {
+		/* retrieve the vendor and device strings as longname */
+		if (dev->descriptor.iManufacturer)
+			len = usb_string(dev, dev->descriptor.iManufacturer,
+					 card->longname, sizeof(card->longname));
+		else
+			len = 0;
+		/* we don't really care if there isn't any vendor string */
+	}
+	if (len > 0) {
+		strim(card->longname);
+		if (*card->longname)
+			strlcat(card->longname, " ", sizeof(card->longname));
+	}
+
+	strlcat(card->longname, card->shortname, sizeof(card->longname));
+
+	len = strlcat(card->longname, " at ", sizeof(card->longname));
+
+	if (len < sizeof(card->longname))
+		usb_make_path(dev, card->longname + len, sizeof(card->longname) - len);
+
+	switch (snd_usb_get_speed(dev)) {
+	case USB_SPEED_LOW:
+		strlcat(card->longname, ", low speed", sizeof(card->longname));
+		break;
+	case USB_SPEED_FULL:
+		strlcat(card->longname, ", full speed", sizeof(card->longname));
+		break;
+	case USB_SPEED_HIGH:
+		strlcat(card->longname, ", high speed", sizeof(card->longname));
+		break;
+	case USB_SPEED_SUPER:
+		strlcat(card->longname, ", super speed", sizeof(card->longname));
+		break;
+	case USB_SPEED_SUPER_PLUS:
+		strlcat(card->longname, ", super speed plus", sizeof(card->longname));
+		break;
+	default:
+		break;
+	}
 }
 
 /*
@@ -360,11 +454,8 @@ static int snd_usb_audio_create(struct usb_interface *intf,
 {
 	struct snd_card *card;
 	struct snd_usb_audio *chip;
-	int err, len;
+	int err;
 	char component[14];
-	static struct snd_device_ops ops = {
-		.dev_free =	snd_usb_audio_dev_free,
-	};
 
 	*rchip = NULL;
 
@@ -382,18 +473,13 @@ static int snd_usb_audio_create(struct usb_interface *intf,
 	}
 
 	err = snd_card_new(&intf->dev, index[idx], id[idx], THIS_MODULE,
-			   0, &card);
+			   sizeof(*chip), &card);
 	if (err < 0) {
 		dev_err(&dev->dev, "cannot create card instance %d\n", idx);
 		return err;
 	}
 
-	chip = kzalloc(sizeof(*chip), GFP_KERNEL);
-	if (! chip) {
-		snd_card_free(card);
-		return -ENOMEM;
-	}
-
+	chip = card->private_data;
 	mutex_init(&chip->mutex);
 	init_waitqueue_head(&chip->shutdown_wait);
 	chip->index = idx;
@@ -411,75 +497,15 @@ static int snd_usb_audio_create(struct usb_interface *intf,
 	INIT_LIST_HEAD(&chip->midi_list);
 	INIT_LIST_HEAD(&chip->mixer_list);
 
-	if ((err = snd_device_new(card, SNDRV_DEV_LOWLEVEL, chip, &ops)) < 0) {
-		snd_usb_audio_free(chip);
-		snd_card_free(card);
-		return err;
-	}
+	card->private_free = snd_usb_audio_free;
 
 	strcpy(card->driver, "USB-Audio");
 	sprintf(component, "USB%04x:%04x",
 		USB_ID_VENDOR(chip->usb_id), USB_ID_PRODUCT(chip->usb_id));
 	snd_component_add(card, component);
 
-	/* retrieve the device string as shortname */
-	if (quirk && quirk->product_name && *quirk->product_name) {
-		strlcpy(card->shortname, quirk->product_name, sizeof(card->shortname));
-	} else {
-		if (!dev->descriptor.iProduct ||
-		    usb_string(dev, dev->descriptor.iProduct,
-		    card->shortname, sizeof(card->shortname)) <= 0) {
-			/* no name available from anywhere, so use ID */
-			sprintf(card->shortname, "USB Device %#04x:%#04x",
-				USB_ID_VENDOR(chip->usb_id),
-				USB_ID_PRODUCT(chip->usb_id));
-		}
-	}
-	strim(card->shortname);
-
-	/* retrieve the vendor and device strings as longname */
-	if (quirk && quirk->vendor_name && *quirk->vendor_name) {
-		len = strlcpy(card->longname, quirk->vendor_name, sizeof(card->longname));
-	} else {
-		if (dev->descriptor.iManufacturer)
-			len = usb_string(dev, dev->descriptor.iManufacturer,
-					 card->longname, sizeof(card->longname));
-		else
-			len = 0;
-		/* we don't really care if there isn't any vendor string */
-	}
-	if (len > 0) {
-		strim(card->longname);
-		if (*card->longname)
-			strlcat(card->longname, " ", sizeof(card->longname));
-	}
-
-	strlcat(card->longname, card->shortname, sizeof(card->longname));
-
-	len = strlcat(card->longname, " at ", sizeof(card->longname));
-
-	if (len < sizeof(card->longname))
-		usb_make_path(dev, card->longname + len, sizeof(card->longname) - len);
-
-	switch (snd_usb_get_speed(dev)) {
-	case USB_SPEED_LOW:
-		strlcat(card->longname, ", low speed", sizeof(card->longname));
-		break;
-	case USB_SPEED_FULL:
-		strlcat(card->longname, ", full speed", sizeof(card->longname));
-		break;
-	case USB_SPEED_HIGH:
-		strlcat(card->longname, ", high speed", sizeof(card->longname));
-		break;
-	case USB_SPEED_SUPER:
-		strlcat(card->longname, ", super speed", sizeof(card->longname));
-		break;
-	case USB_SPEED_SUPER_PLUS:
-		strlcat(card->longname, ", super speed plus", sizeof(card->longname));
-		break;
-	default:
-		break;
-	}
+	usb_audio_make_shortname(dev, chip, quirk);
+	usb_audio_make_longname(dev, chip, quirk);
 
 	snd_usb_audio_create_proc(chip);
 
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 0b030d8fe3fa..c79749613fa6 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -443,10 +443,11 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip, int iface,
 	data[0] = rate;
 	data[1] = rate >> 8;
 	data[2] = rate >> 16;
-	if ((err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR,
-				   USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_OUT,
-				   UAC_EP_CS_ATTR_SAMPLE_RATE << 8, ep,
-				   data, sizeof(data))) < 0) {
+	err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR,
+			      USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_OUT,
+			      UAC_EP_CS_ATTR_SAMPLE_RATE << 8, ep,
+			      data, sizeof(data));
+	if (err < 0) {
 		dev_err(&dev->dev, "%d:%d: cannot set freq %d to ep %#x\n",
 			iface, fmt->altsetting, rate, ep);
 		return err;
@@ -460,10 +461,11 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip, int iface,
 	if (chip->sample_rate_read_error > 2)
 		return 0;
 
-	if ((err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC_GET_CUR,
-				   USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_IN,
-				   UAC_EP_CS_ATTR_SAMPLE_RATE << 8, ep,
-				   data, sizeof(data))) < 0) {
+	err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC_GET_CUR,
+			      USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_IN,
+			      UAC_EP_CS_ATTR_SAMPLE_RATE << 8, ep,
+			      data, sizeof(data));
+	if (err < 0) {
 		dev_err(&dev->dev, "%d:%d: cannot get freq at ep %#x\n",
 			iface, fmt->altsetting, ep);
 		chip->sample_rate_read_error++;
@@ -587,8 +589,15 @@ int snd_usb_init_sample_rate(struct snd_usb_audio *chip, int iface,
 	default:
 		return set_sample_rate_v1(chip, iface, alts, fmt, rate);
 
-	case UAC_VERSION_2:
 	case UAC_VERSION_3:
+		if (chip->badd_profile >= UAC3_FUNCTION_SUBCLASS_GENERIC_IO) {
+			if (rate != UAC3_BADD_SAMPLING_RATE)
+				return -ENXIO;
+			else
+				return 0;
+		}
+	/* fall through */
+	case UAC_VERSION_2:
 		return set_sample_rate_v2v3(chip, iface, alts, fmt, rate);
 	}
 }
diff --git a/sound/usb/helper.h b/sound/usb/helper.h
index 4463e6d6dcb3..d338bd0e0ca6 100644
--- a/sound/usb/helper.h
+++ b/sound/usb/helper.h
@@ -18,16 +18,12 @@ unsigned char snd_usb_parse_datainterval(struct snd_usb_audio *chip,
  * retrieve usb_interface descriptor from the host interface
  * (conditional for compatibility with the older API)
  */
-#ifndef get_iface_desc
 #define get_iface_desc(iface)	(&(iface)->desc)
 #define get_endpoint(alt,ep)	(&(alt)->endpoint[ep].desc)
 #define get_ep_desc(ep)		(&(ep)->desc)
 #define get_cfg_desc(cfg)	(&(cfg)->desc)
-#endif
 
-#ifndef snd_usb_get_speed
 #define snd_usb_get_speed(dev) ((dev)->speed)
-#endif
 
 static inline int snd_usb_ctrl_intf(struct snd_usb_audio *chip)
 {
diff --git a/sound/usb/line6/midi.c b/sound/usb/line6/midi.c
index 6d7cde56a355..e2cf55c53ea8 100644
--- a/sound/usb/line6/midi.c
+++ b/sound/usb/line6/midi.c
@@ -125,7 +125,7 @@ static int send_midi_async(struct usb_line6 *line6, unsigned char *data,
 	}
 
 	usb_fill_int_urb(urb, line6->usbdev,
-			 usb_sndbulkpipe(line6->usbdev,
+			 usb_sndintpipe(line6->usbdev,
 					 line6->properties->ep_ctrl_w),
 			 transfer_buffer, length, midi_sent, line6,
 			 line6->interval);
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 301ad61ed426..898afd3001ea 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -112,14 +112,12 @@ enum {
 #include "mixer_maps.c"
 
 static const struct usbmix_name_map *
-find_map(struct mixer_build *state, int unitid, int control)
+find_map(const struct usbmix_name_map *p, int unitid, int control)
 {
-	const struct usbmix_name_map *p = state->map;
-
 	if (!p)
 		return NULL;
 
-	for (p = state->map; p->id; p++) {
+	for (; p->id; p++) {
 		if (p->id == unitid &&
 		    (!control || !p->control || control == p->control))
 			return p;
@@ -201,10 +199,10 @@ static void *find_audio_control_unit(struct mixer_build *state,
 /*
  * copy a string with the given id
  */
-static int snd_usb_copy_string_desc(struct mixer_build *state,
+static int snd_usb_copy_string_desc(struct snd_usb_audio *chip,
 				    int index, char *buf, int maxlen)
 {
-	int len = usb_string(state->chip->dev, index, buf, maxlen - 1);
+	int len = usb_string(chip->dev, index, buf, maxlen - 1);
 
 	if (len < 0)
 		return 0;
@@ -600,7 +598,8 @@ int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list,
 
 	while (snd_ctl_find_id(mixer->chip->card, &kctl->id))
 		kctl->id.index++;
-	if ((err = snd_ctl_add(mixer->chip->card, kctl)) < 0) {
+	err = snd_ctl_add(mixer->chip->card, kctl);
+	if (err < 0) {
 		usb_audio_dbg(mixer->chip, "cannot add control (err = %d)\n",
 			      err);
 		return err;
@@ -658,14 +657,14 @@ static struct iterm_name_combo {
 	{ 0 },
 };
 
-static int get_term_name(struct mixer_build *state, struct usb_audio_term *iterm,
+static int get_term_name(struct snd_usb_audio *chip, struct usb_audio_term *iterm,
 			 unsigned char *name, int maxlen, int term_only)
 {
 	struct iterm_name_combo *names;
 	int len;
 
 	if (iterm->name) {
-		len = snd_usb_copy_string_desc(state, iterm->name,
+		len = snd_usb_copy_string_desc(chip, iterm->name,
 						name, maxlen);
 		if (len)
 			return len;
@@ -719,6 +718,66 @@ static int get_term_name(struct mixer_build *state, struct usb_audio_term *iterm
 }
 
 /*
+ * Get logical cluster information for UAC3 devices.
+ */
+static int get_cluster_channels_v3(struct mixer_build *state, unsigned int cluster_id)
+{
+	struct uac3_cluster_header_descriptor c_header;
+	int err;
+
+	err = snd_usb_ctl_msg(state->chip->dev,
+			usb_rcvctrlpipe(state->chip->dev, 0),
+			UAC3_CS_REQ_HIGH_CAPABILITY_DESCRIPTOR,
+			USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
+			cluster_id,
+			snd_usb_ctrl_intf(state->chip),
+			&c_header, sizeof(c_header));
+	if (err < 0)
+		goto error;
+	if (err != sizeof(c_header)) {
+		err = -EIO;
+		goto error;
+	}
+
+	return c_header.bNrChannels;
+
+error:
+	usb_audio_err(state->chip, "cannot request logical cluster ID: %d (err: %d)\n", cluster_id, err);
+	return err;
+}
+
+/*
+ * Get number of channels for a Mixer Unit.
+ */
+static int uac_mixer_unit_get_channels(struct mixer_build *state,
+				       struct uac_mixer_unit_descriptor *desc)
+{
+	int mu_channels;
+
+	if (desc->bLength < 11)
+		return -EINVAL;
+	if (!desc->bNrInPins)
+		return -EINVAL;
+
+	switch (state->mixer->protocol) {
+	case UAC_VERSION_1:
+	case UAC_VERSION_2:
+	default:
+		mu_channels = uac_mixer_unit_bNrChannels(desc);
+		break;
+	case UAC_VERSION_3:
+		mu_channels = get_cluster_channels_v3(state,
+				uac3_mixer_unit_wClusterDescrID(desc));
+		break;
+	}
+
+	if (!mu_channels)
+		return -EINVAL;
+
+	return mu_channels;
+}
+
+/*
  * parse the source unit recursively until it reaches to a terminal
  * or a branched unit.
  */
@@ -844,8 +903,12 @@ static int check_input_term(struct mixer_build *state, int id,
 				term->id = id;
 				term->type = le16_to_cpu(d->wTerminalType);
 
-				/* REVISIT: UAC3 IT doesn't have channels/cfg */
-				term->channels = 0;
+				err = get_cluster_channels_v3(state, le16_to_cpu(d->wClusterDescrID));
+				if (err < 0)
+					return err;
+				term->channels = err;
+
+				/* REVISIT: UAC3 IT doesn't have channels cfg */
 				term->chconfig = 0;
 
 				term->name = le16_to_cpu(d->wTerminalDescrStr);
@@ -865,6 +928,18 @@ static int check_input_term(struct mixer_build *state, int id,
 				term->name = le16_to_cpu(d->wClockSourceStr);
 				return 0;
 			}
+			case UAC3_MIXER_UNIT: {
+				struct uac_mixer_unit_descriptor *d = p1;
+
+				err = uac_mixer_unit_get_channels(state, d);
+				if (err < 0)
+					return err;
+
+				term->channels = err;
+				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+
+				return 0;
+			}
 			default:
 				return -ENODEV;
 			}
@@ -967,6 +1042,14 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
 		}
 		break;
 
+	case USB_ID(0x0d8c, 0x0103):
+		if (!strcmp(kctl->id.name, "PCM Playback Volume")) {
+			usb_audio_info(chip,
+				 "set volume quirk for CM102-A+/102S+\n");
+			cval->min = -256;
+		}
+		break;
+
 	case USB_ID(0x0471, 0x0101):
 	case USB_ID(0x0471, 0x0104):
 	case USB_ID(0x0471, 0x0105):
@@ -1250,6 +1333,51 @@ static int mixer_ctl_master_bool_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
+/* get the connectors status and report it as boolean type */
+static int mixer_ctl_connector_get(struct snd_kcontrol *kcontrol,
+				   struct snd_ctl_elem_value *ucontrol)
+{
+	struct usb_mixer_elem_info *cval = kcontrol->private_data;
+	struct snd_usb_audio *chip = cval->head.mixer->chip;
+	int idx = 0, validx, ret, val;
+
+	validx = cval->control << 8 | 0;
+
+	ret = snd_usb_lock_shutdown(chip) ? -EIO : 0;
+	if (ret)
+		goto error;
+
+	idx = snd_usb_ctrl_intf(chip) | (cval->head.id << 8);
+	if (cval->head.mixer->protocol == UAC_VERSION_2) {
+		struct uac2_connectors_ctl_blk uac2_conn;
+
+		ret = snd_usb_ctl_msg(chip->dev, usb_rcvctrlpipe(chip->dev, 0), UAC2_CS_CUR,
+				      USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
+				      validx, idx, &uac2_conn, sizeof(uac2_conn));
+		val = !!uac2_conn.bNrChannels;
+	} else { /* UAC_VERSION_3 */
+		struct uac3_insertion_ctl_blk uac3_conn;
+
+		ret = snd_usb_ctl_msg(chip->dev, usb_rcvctrlpipe(chip->dev, 0), UAC2_CS_CUR,
+				      USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
+				      validx, idx, &uac3_conn, sizeof(uac3_conn));
+		val = !!uac3_conn.bmConInserted;
+	}
+
+	snd_usb_unlock_shutdown(chip);
+
+	if (ret < 0) {
+error:
+		usb_audio_err(chip,
+			"cannot get connectors status: req = %#x, wValue = %#x, wIndex = %#x, type = %d\n",
+			UAC_GET_CUR, validx, idx, cval->val_type);
+		return ret;
+	}
+
+	ucontrol->value.integer.value[0] = val;
+	return 0;
+}
+
 static struct snd_kcontrol_new usb_feature_unit_ctl = {
 	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
 	.name = "", /* will be filled later manually */
@@ -1280,6 +1408,15 @@ static struct snd_kcontrol_new usb_bool_master_control_ctl_ro = {
 	.put = NULL,
 };
 
+static const struct snd_kcontrol_new usb_connector_ctl_ro = {
+	.iface = SNDRV_CTL_ELEM_IFACE_CARD,
+	.name = "", /* will be filled later manually */
+	.access = SNDRV_CTL_ELEM_ACCESS_READ,
+	.info = snd_ctl_boolean_mono_info,
+	.get = mixer_ctl_connector_get,
+	.put = NULL,
+};
+
 /*
  * This symbol is exported in order to allow the mixer quirks to
  * hook up to the standard feature unit control mechanism
@@ -1333,16 +1470,16 @@ static struct usb_feature_control_info *get_feature_control_info(int control)
 	return NULL;
 }
 
-static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
-			      unsigned int ctl_mask, int control,
-			      struct usb_audio_term *iterm, int unitid,
-			      int readonly_mask)
+static void __build_feature_ctl(struct usb_mixer_interface *mixer,
+				const struct usbmix_name_map *imap,
+				unsigned int ctl_mask, int control,
+				struct usb_audio_term *iterm,
+				struct usb_audio_term *oterm,
+				int unitid, int nameid, int readonly_mask)
 {
-	struct uac_feature_unit_descriptor *desc = raw_desc;
 	struct usb_feature_control_info *ctl_info;
 	unsigned int len = 0;
 	int mapped_name = 0;
-	int nameid = uac_feature_unit_iFeature(desc);
 	struct snd_kcontrol *kctl;
 	struct usb_mixer_elem_info *cval;
 	const struct usbmix_name_map *map;
@@ -1353,14 +1490,14 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		return;
 	}
 
-	map = find_map(state, unitid, control);
+	map = find_map(imap, unitid, control);
 	if (check_ignored_ctl(map))
 		return;
 
 	cval = kzalloc(sizeof(*cval), GFP_KERNEL);
 	if (!cval)
 		return;
-	snd_usb_mixer_elem_init_std(&cval->head, state->mixer, unitid);
+	snd_usb_mixer_elem_init_std(&cval->head, mixer, unitid);
 	cval->control = control;
 	cval->cmask = ctl_mask;
 
@@ -1369,7 +1506,7 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		kfree(cval);
 		return;
 	}
-	if (state->mixer->protocol == UAC_VERSION_1)
+	if (mixer->protocol == UAC_VERSION_1)
 		cval->val_type = ctl_info->type;
 	else /* UAC_VERSION_2 */
 		cval->val_type = ctl_info->type_uac2 >= 0 ?
@@ -1398,7 +1535,7 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		kctl = snd_ctl_new1(&usb_feature_unit_ctl, cval);
 
 	if (!kctl) {
-		usb_audio_err(state->chip, "cannot malloc kcontrol\n");
+		usb_audio_err(mixer->chip, "cannot malloc kcontrol\n");
 		kfree(cval);
 		return;
 	}
@@ -1407,7 +1544,7 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 	len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name));
 	mapped_name = len != 0;
 	if (!len && nameid)
-		len = snd_usb_copy_string_desc(state, nameid,
+		len = snd_usb_copy_string_desc(mixer->chip, nameid,
 				kctl->id.name, sizeof(kctl->id.name));
 
 	switch (control) {
@@ -1422,10 +1559,12 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		 * - otherwise, anonymous name.
 		 */
 		if (!len) {
-			len = get_term_name(state, iterm, kctl->id.name,
-					    sizeof(kctl->id.name), 1);
-			if (!len)
-				len = get_term_name(state, &state->oterm,
+			if (iterm)
+				len = get_term_name(mixer->chip, iterm,
+						    kctl->id.name,
+						    sizeof(kctl->id.name), 1);
+			if (!len && oterm)
+				len = get_term_name(mixer->chip, oterm,
 						    kctl->id.name,
 						    sizeof(kctl->id.name), 1);
 			if (!len)
@@ -1434,15 +1573,15 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		}
 
 		if (!mapped_name)
-			check_no_speaker_on_headset(kctl, state->mixer->chip->card);
+			check_no_speaker_on_headset(kctl, mixer->chip->card);
 
 		/*
 		 * determine the stream direction:
 		 * if the connected output is USB stream, then it's likely a
 		 * capture stream.  otherwise it should be playback (hopefully :)
 		 */
-		if (!mapped_name && !(state->oterm.type >> 16)) {
-			if ((state->oterm.type & 0xff00) == 0x0100)
+		if (!mapped_name && oterm && !(oterm->type >> 16)) {
+			if ((oterm->type & 0xff00) == 0x0100)
 				append_ctl_name(kctl, " Capture");
 			else
 				append_ctl_name(kctl, " Playback");
@@ -1470,7 +1609,7 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 		}
 	}
 
-	snd_usb_mixer_fu_apply_quirk(state->mixer, cval, unitid, kctl);
+	snd_usb_mixer_fu_apply_quirk(mixer, cval, unitid, kctl);
 
 	range = (cval->max - cval->min) / cval->res;
 	/*
@@ -1479,26 +1618,46 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
 	 * devices. It will definitively catch all buggy Logitech devices.
 	 */
 	if (range > 384) {
-		usb_audio_warn(state->chip,
+		usb_audio_warn(mixer->chip,
 			       "Warning! Unlikely big volume range (=%u), cval->res is probably wrong.",
 			       range);
-		usb_audio_warn(state->chip,
+		usb_audio_warn(mixer->chip,
 			       "[%d] FU [%s] ch = %d, val = %d/%d/%d",
 			       cval->head.id, kctl->id.name, cval->channels,
 			       cval->min, cval->max, cval->res);
 	}
 
-	usb_audio_dbg(state->chip, "[%d] FU [%s] ch = %d, val = %d/%d/%d\n",
+	usb_audio_dbg(mixer->chip, "[%d] FU [%s] ch = %d, val = %d/%d/%d\n",
 		      cval->head.id, kctl->id.name, cval->channels,
 		      cval->min, cval->max, cval->res);
 	snd_usb_mixer_add_control(&cval->head, kctl);
 }
 
+static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
+			      unsigned int ctl_mask, int control,
+			      struct usb_audio_term *iterm, int unitid,
+			      int readonly_mask)
+{
+	struct uac_feature_unit_descriptor *desc = raw_desc;
+	int nameid = uac_feature_unit_iFeature(desc);
+
+	__build_feature_ctl(state->mixer, state->map, ctl_mask, control,
+			iterm, &state->oterm, unitid, nameid, readonly_mask);
+}
+
+static void build_feature_ctl_badd(struct usb_mixer_interface *mixer,
+			      unsigned int ctl_mask, int control, int unitid,
+			      const struct usbmix_name_map *badd_map)
+{
+	__build_feature_ctl(mixer, badd_map, ctl_mask, control,
+			NULL, NULL, unitid, 0, 0);
+}
+
 static void get_connector_control_name(struct mixer_build *state,
 				       struct usb_audio_term *term,
 				       bool is_input, char *name, int name_size)
 {
-	int name_len = get_term_name(state, term, name, name_size, 0);
+	int name_len = get_term_name(state->chip, term, name, name_size, 0);
 
 	if (name_len == 0)
 		strlcpy(name, "Unknown", name_size);
@@ -1526,17 +1685,25 @@ static void build_connector_control(struct mixer_build *state,
 		return;
 	snd_usb_mixer_elem_init_std(&cval->head, state->mixer, term->id);
 	/*
-	 * The first byte from reading the UAC2_TE_CONNECTOR control returns the
-	 * number of channels connected.  This boolean ctl will simply report
-	 * if any channels are connected or not.
-	 * (Audio20_final.pdf Table 5-10: Connector Control CUR Parameter Block)
+	 * UAC2: The first byte from reading the UAC2_TE_CONNECTOR control returns the
+	 * number of channels connected.
+	 *
+	 * UAC3: The first byte specifies size of bitmap for the inserted controls. The
+	 * following byte(s) specifies which connectors are inserted.
+	 *
+	 * This boolean ctl will simply report if any channels are connected
+	 * or not.
 	 */
-	cval->control = UAC2_TE_CONNECTOR;
+	if (state->mixer->protocol == UAC_VERSION_2)
+		cval->control = UAC2_TE_CONNECTOR;
+	else /* UAC_VERSION_3 */
+		cval->control = UAC3_TE_INSERTION;
+
 	cval->val_type = USB_MIXER_BOOLEAN;
 	cval->channels = 1; /* report true if any channel is connected */
 	cval->min = 0;
 	cval->max = 1;
-	kctl = snd_ctl_new1(&usb_bool_master_control_ctl_ro, cval);
+	kctl = snd_ctl_new1(&usb_connector_ctl_ro, cval);
 	if (!kctl) {
 		usb_audio_err(state->chip, "cannot malloc kcontrol\n");
 		kfree(cval);
@@ -1597,7 +1764,7 @@ static int parse_clock_source_unit(struct mixer_build *state, int unitid,
 	}
 
 	kctl->private_free = snd_usb_mixer_elem_free;
-	ret = snd_usb_copy_string_desc(state, hdr->iClockSource,
+	ret = snd_usb_copy_string_desc(state->chip, hdr->iClockSource,
 				       name, sizeof(name));
 	if (ret > 0)
 		snprintf(kctl->id.name, sizeof(kctl->id.name),
@@ -1684,7 +1851,8 @@ static int parse_audio_feature_unit(struct mixer_build *state, int unitid,
 	}
 
 	/* parse the source unit */
-	if ((err = parse_audio_unit(state, hdr->bSourceID)) < 0)
+	err = parse_audio_unit(state, hdr->bSourceID);
+	if (err < 0)
 		return err;
 
 	/* determine the input source type and name */
@@ -1776,7 +1944,8 @@ static int parse_audio_feature_unit(struct mixer_build *state, int unitid,
 				build_feature_ctl(state, _ftr, ch_bits, control,
 						  &iterm, unitid, ch_read_only);
 			if (uac_v2v3_control_is_readable(master_bits, control))
-				build_feature_ctl(state, _ftr, 0, i, &iterm, unitid,
+				build_feature_ctl(state, _ftr, 0, control,
+						  &iterm, unitid,
 						  !uac_v2v3_control_is_writeable(master_bits,
 										 control));
 		}
@@ -1797,16 +1966,15 @@ static int parse_audio_feature_unit(struct mixer_build *state, int unitid,
  */
 static void build_mixer_unit_ctl(struct mixer_build *state,
 				 struct uac_mixer_unit_descriptor *desc,
-				 int in_pin, int in_ch, int unitid,
-				 struct usb_audio_term *iterm)
+				 int in_pin, int in_ch, int num_outs,
+				 int unitid, struct usb_audio_term *iterm)
 {
 	struct usb_mixer_elem_info *cval;
-	unsigned int num_outs = uac_mixer_unit_bNrChannels(desc);
 	unsigned int i, len;
 	struct snd_kcontrol *kctl;
 	const struct usbmix_name_map *map;
 
-	map = find_map(state, unitid, 0);
+	map = find_map(state->map, unitid, 0);
 	if (check_ignored_ctl(map))
 		return;
 
@@ -1839,7 +2007,7 @@ static void build_mixer_unit_ctl(struct mixer_build *state,
 
 	len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name));
 	if (!len)
-		len = get_term_name(state, iterm, kctl->id.name,
+		len = get_term_name(state->chip, iterm, kctl->id.name,
 				    sizeof(kctl->id.name), 0);
 	if (!len)
 		len = sprintf(kctl->id.name, "Mixer Source %d", in_ch + 1);
@@ -1854,16 +2022,28 @@ static int parse_audio_input_terminal(struct mixer_build *state, int unitid,
 				      void *raw_desc)
 {
 	struct usb_audio_term iterm;
-	struct uac2_input_terminal_descriptor *d = raw_desc;
+	unsigned int control, bmctls, term_id;
 
-	check_input_term(state, d->bTerminalID, &iterm);
 	if (state->mixer->protocol == UAC_VERSION_2) {
-		/* Check for jack detection. */
-		if (uac_v2v3_control_is_readable(d->bmControls,
-						 UAC2_TE_CONNECTOR)) {
-			build_connector_control(state, &iterm, true);
-		}
+		struct uac2_input_terminal_descriptor *d_v2 = raw_desc;
+		control = UAC2_TE_CONNECTOR;
+		term_id = d_v2->bTerminalID;
+		bmctls = le16_to_cpu(d_v2->bmControls);
+	} else if (state->mixer->protocol == UAC_VERSION_3) {
+		struct uac3_input_terminal_descriptor *d_v3 = raw_desc;
+		control = UAC3_TE_INSERTION;
+		term_id = d_v3->bTerminalID;
+		bmctls = le32_to_cpu(d_v3->bmControls);
+	} else {
+		return 0; /* UAC1. No Insertion control */
 	}
+
+	check_input_term(state, term_id, &iterm);
+
+	/* Check for jack detection. */
+	if (uac_v2v3_control_is_readable(bmctls, control))
+		build_connector_control(state, &iterm, true);
+
 	return 0;
 }
 
@@ -1878,14 +2058,17 @@ static int parse_audio_mixer_unit(struct mixer_build *state, int unitid,
 	int input_pins, num_ins, num_outs;
 	int pin, ich, err;
 
-	if (desc->bLength < 11 || !(input_pins = desc->bNrInPins) ||
-	    !(num_outs = uac_mixer_unit_bNrChannels(desc))) {
+	err = uac_mixer_unit_get_channels(state, desc);
+	if (err < 0) {
 		usb_audio_err(state->chip,
 			      "invalid MIXER UNIT descriptor %d\n",
 			      unitid);
-		return -EINVAL;
+		return err;
 	}
 
+	num_outs = err;
+	input_pins = desc->bNrInPins;
+
 	num_ins = 0;
 	ich = 0;
 	for (pin = 0; pin < input_pins; pin++) {
@@ -1912,7 +2095,7 @@ static int parse_audio_mixer_unit(struct mixer_build *state, int unitid,
 				}
 			}
 			if (ich_has_controls)
-				build_mixer_unit_ctl(state, desc, pin, ich,
+				build_mixer_unit_ctl(state, desc, pin, ich, num_outs,
 						     unitid, &iterm);
 		}
 	}
@@ -2089,7 +2272,8 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 	}
 
 	for (i = 0; i < num_ins; i++) {
-		if ((err = parse_audio_unit(state, desc->baSourceID[i])) < 0)
+		err = parse_audio_unit(state, desc->baSourceID[i]);
+		if (err < 0)
 			return err;
 	}
 
@@ -2105,7 +2289,7 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 
 		if (!(controls[valinfo->control / 8] & (1 << ((valinfo->control % 8) - 1))))
 			continue;
-		map = find_map(state, unitid, valinfo->control);
+		map = find_map(state->map, unitid, valinfo->control);
 		if (check_ignored_ctl(map))
 			continue;
 		cval = kzalloc(sizeof(*cval), GFP_KERNEL);
@@ -2153,7 +2337,8 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 			nameid = uac_processing_unit_iProcessing(desc, state->mixer->protocol);
 			len = 0;
 			if (nameid)
-				len = snd_usb_copy_string_desc(state, nameid,
+				len = snd_usb_copy_string_desc(state->chip,
+							       nameid,
 							       kctl->id.name,
 							       sizeof(kctl->id.name));
 			if (!len)
@@ -2301,14 +2486,15 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 	}
 
 	for (i = 0; i < desc->bNrInPins; i++) {
-		if ((err = parse_audio_unit(state, desc->baSourceID[i])) < 0)
+		err = parse_audio_unit(state, desc->baSourceID[i]);
+		if (err < 0)
 			return err;
 	}
 
 	if (desc->bNrInPins == 1) /* only one ? nonsense! */
 		return 0;
 
-	map = find_map(state, unitid, 0);
+	map = find_map(state->map, unitid, 0);
 	if (check_ignored_ctl(map))
 		return 0;
 
@@ -2349,7 +2535,8 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 		len = check_mapped_selector_name(state, unitid, i, namelist[i],
 						 MAX_ITEM_NAME_LEN);
 		if (! len && check_input_term(state, desc->baSourceID[i], &iterm) >= 0)
-			len = get_term_name(state, &iterm, namelist[i], MAX_ITEM_NAME_LEN, 0);
+			len = get_term_name(state->chip, &iterm, namelist[i],
+					    MAX_ITEM_NAME_LEN, 0);
 		if (! len)
 			sprintf(namelist[i], "Input %u", i);
 	}
@@ -2371,12 +2558,12 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 		/* if iSelector is given, use it */
 		nameid = uac_selector_unit_iSelector(desc);
 		if (nameid)
-			len = snd_usb_copy_string_desc(state, nameid,
+			len = snd_usb_copy_string_desc(state->chip, nameid,
 						       kctl->id.name,
 						       sizeof(kctl->id.name));
 		/* ... or pick up the terminal name at next */
 		if (!len)
-			len = get_term_name(state, &state->oterm,
+			len = get_term_name(state->chip, &state->oterm,
 				    kctl->id.name, sizeof(kctl->id.name), 0);
 		/* ... or use the fixed string "USB" as the last resort */
 		if (!len)
@@ -2449,7 +2636,7 @@ static int parse_audio_unit(struct mixer_build *state, int unitid)
 	} else { /* UAC_VERSION_3 */
 		switch (p1[2]) {
 		case UAC_INPUT_TERMINAL:
-			return 0; /* NOP */
+			return parse_audio_input_terminal(state, unitid, p1);
 		case UAC3_MIXER_UNIT:
 			return parse_audio_mixer_unit(state, unitid, p1);
 		case UAC3_CLOCK_SOURCE:
@@ -2494,6 +2681,246 @@ static int snd_usb_mixer_dev_free(struct snd_device *device)
 	return 0;
 }
 
+/* UAC3 predefined channels configuration */
+struct uac3_badd_profile {
+	int subclass;
+	const char *name;
+	int c_chmask;	/* capture channels mask */
+	int p_chmask;	/* playback channels mask */
+	int st_chmask;	/* side tone mixing channel mask */
+};
+
+static struct uac3_badd_profile uac3_badd_profiles[] = {
+	{
+		/*
+		 * BAIF, BAOF or combination of both
+		 * IN: Mono or Stereo cfg, Mono alt possible
+		 * OUT: Mono or Stereo cfg, Mono alt possible
+		 */
+		.subclass = UAC3_FUNCTION_SUBCLASS_GENERIC_IO,
+		.name = "GENERIC IO",
+		.c_chmask = -1,		/* dynamic channels */
+		.p_chmask = -1,		/* dynamic channels */
+	},
+	{
+		/* BAOF; Stereo only cfg, Mono alt possible */
+		.subclass = UAC3_FUNCTION_SUBCLASS_HEADPHONE,
+		.name = "HEADPHONE",
+		.p_chmask = 3,
+	},
+	{
+		/* BAOF; Mono or Stereo cfg, Mono alt possible */
+		.subclass = UAC3_FUNCTION_SUBCLASS_SPEAKER,
+		.name = "SPEAKER",
+		.p_chmask = -1,		/* dynamic channels */
+	},
+	{
+		/* BAIF; Mono or Stereo cfg, Mono alt possible */
+		.subclass = UAC3_FUNCTION_SUBCLASS_MICROPHONE,
+		.name = "MICROPHONE",
+		.c_chmask = -1,		/* dynamic channels */
+	},
+	{
+		/*
+		 * BAIOF topology
+		 * IN: Mono only
+		 * OUT: Mono or Stereo cfg, Mono alt possible
+		 */
+		.subclass = UAC3_FUNCTION_SUBCLASS_HEADSET,
+		.name = "HEADSET",
+		.c_chmask = 1,
+		.p_chmask = -1,		/* dynamic channels */
+		.st_chmask = 1,
+	},
+	{
+		/* BAIOF; IN: Mono only; OUT: Stereo only, Mono alt possible */
+		.subclass = UAC3_FUNCTION_SUBCLASS_HEADSET_ADAPTER,
+		.name = "HEADSET ADAPTER",
+		.c_chmask = 1,
+		.p_chmask = 3,
+		.st_chmask = 1,
+	},
+	{
+		/* BAIF + BAOF; IN: Mono only; OUT: Mono only */
+		.subclass = UAC3_FUNCTION_SUBCLASS_SPEAKERPHONE,
+		.name = "SPEAKERPHONE",
+		.c_chmask = 1,
+		.p_chmask = 1,
+	},
+	{ 0 } /* terminator */
+};
+
+static bool uac3_badd_func_has_valid_channels(struct usb_mixer_interface *mixer,
+					      struct uac3_badd_profile *f,
+					      int c_chmask, int p_chmask)
+{
+	/*
+	 * If both playback/capture channels are dynamic, make sure
+	 * at least one channel is present
+	 */
+	if (f->c_chmask < 0 && f->p_chmask < 0) {
+		if (!c_chmask && !p_chmask) {
+			usb_audio_warn(mixer->chip, "BAAD %s: no channels?",
+				       f->name);
+			return false;
+		}
+		return true;
+	}
+
+	if ((f->c_chmask < 0 && !c_chmask) ||
+	    (f->c_chmask >= 0 && f->c_chmask != c_chmask)) {
+		usb_audio_warn(mixer->chip, "BAAD %s c_chmask mismatch",
+			       f->name);
+		return false;
+	}
+	if ((f->p_chmask < 0 && !p_chmask) ||
+	    (f->p_chmask >= 0 && f->p_chmask != p_chmask)) {
+		usb_audio_warn(mixer->chip, "BAAD %s p_chmask mismatch",
+			       f->name);
+		return false;
+	}
+	return true;
+}
+
+/*
+ * create mixer controls for UAC3 BADD profiles
+ *
+ * UAC3 BADD device doesn't contain CS descriptors thus we will guess everything
+ *
+ * BADD device may contain Mixer Unit, which doesn't have any controls, skip it
+ */
+static int snd_usb_mixer_controls_badd(struct usb_mixer_interface *mixer,
+				       int ctrlif)
+{
+	struct usb_device *dev = mixer->chip->dev;
+	struct usb_interface_assoc_descriptor *assoc;
+	int badd_profile = mixer->chip->badd_profile;
+	struct uac3_badd_profile *f;
+	const struct usbmix_ctl_map *map;
+	int p_chmask = 0, c_chmask = 0, st_chmask = 0;
+	int i;
+
+	assoc = usb_ifnum_to_if(dev, ctrlif)->intf_assoc;
+
+	/* Detect BADD capture/playback channels from AS EP descriptors */
+	for (i = 0; i < assoc->bInterfaceCount; i++) {
+		int intf = assoc->bFirstInterface + i;
+
+		struct usb_interface *iface;
+		struct usb_host_interface *alts;
+		struct usb_interface_descriptor *altsd;
+		unsigned int maxpacksize;
+		char dir_in;
+		int chmask, num;
+
+		if (intf == ctrlif)
+			continue;
+
+		iface = usb_ifnum_to_if(dev, intf);
+		num = iface->num_altsetting;
+
+		if (num < 2)
+			return -EINVAL;
+
+		/*
+		 * The number of Channels in an AudioStreaming interface
+		 * and the audio sample bit resolution (16 bits or 24
+		 * bits) can be derived from the wMaxPacketSize field in
+		 * the Standard AS Audio Data Endpoint descriptor in
+		 * Alternate Setting 1
+		 */
+		alts = &iface->altsetting[1];
+		altsd = get_iface_desc(alts);
+
+		if (altsd->bNumEndpoints < 1)
+			return -EINVAL;
+
+		/* check direction */
+		dir_in = (get_endpoint(alts, 0)->bEndpointAddress & USB_DIR_IN);
+		maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
+
+		switch (maxpacksize) {
+		default:
+			usb_audio_err(mixer->chip,
+				"incorrect wMaxPacketSize 0x%x for BADD profile\n",
+				maxpacksize);
+			return -EINVAL;
+		case UAC3_BADD_EP_MAXPSIZE_SYNC_MONO_16:
+		case UAC3_BADD_EP_MAXPSIZE_ASYNC_MONO_16:
+		case UAC3_BADD_EP_MAXPSIZE_SYNC_MONO_24:
+		case UAC3_BADD_EP_MAXPSIZE_ASYNC_MONO_24:
+			chmask = 1;
+			break;
+		case UAC3_BADD_EP_MAXPSIZE_SYNC_STEREO_16:
+		case UAC3_BADD_EP_MAXPSIZE_ASYNC_STEREO_16:
+		case UAC3_BADD_EP_MAXPSIZE_SYNC_STEREO_24:
+		case UAC3_BADD_EP_MAXPSIZE_ASYNC_STEREO_24:
+			chmask = 3;
+			break;
+		}
+
+		if (dir_in)
+			c_chmask = chmask;
+		else
+			p_chmask = chmask;
+	}
+
+	usb_audio_dbg(mixer->chip,
+		"UAC3 BADD profile 0x%x: detected c_chmask=%d p_chmask=%d\n",
+		badd_profile, c_chmask, p_chmask);
+
+	/* check the mapping table */
+	for (map = uac3_badd_usbmix_ctl_maps; map->id; map++) {
+		if (map->id == badd_profile)
+			break;
+	}
+
+	if (!map->id)
+		return -EINVAL;
+
+	for (f = uac3_badd_profiles; f->name; f++) {
+		if (badd_profile == f->subclass)
+			break;
+	}
+	if (!f->name)
+		return -EINVAL;
+	if (!uac3_badd_func_has_valid_channels(mixer, f, c_chmask, p_chmask))
+		return -EINVAL;
+	st_chmask = f->st_chmask;
+
+	/* Playback */
+	if (p_chmask) {
+		/* Master channel, always writable */
+		build_feature_ctl_badd(mixer, 0, UAC_FU_MUTE,
+				       UAC3_BADD_FU_ID2, map->map);
+		/* Mono/Stereo volume channels, always writable */
+		build_feature_ctl_badd(mixer, p_chmask, UAC_FU_VOLUME,
+				       UAC3_BADD_FU_ID2, map->map);
+	}
+
+	/* Capture */
+	if (c_chmask) {
+		/* Master channel, always writable */
+		build_feature_ctl_badd(mixer, 0, UAC_FU_MUTE,
+				       UAC3_BADD_FU_ID5, map->map);
+		/* Mono/Stereo volume channels, always writable */
+		build_feature_ctl_badd(mixer, c_chmask, UAC_FU_VOLUME,
+				       UAC3_BADD_FU_ID5, map->map);
+	}
+
+	/* Side tone-mixing */
+	if (st_chmask) {
+		/* Master channel, always writable */
+		build_feature_ctl_badd(mixer, 0, UAC_FU_MUTE,
+				       UAC3_BADD_FU_ID7, map->map);
+		/* Mono volume channel, always writable */
+		build_feature_ctl_badd(mixer, 1, UAC_FU_VOLUME,
+				       UAC3_BADD_FU_ID7, map->map);
+	}
+
+	return 0;
+}
+
 /*
  * create mixer controls
  *
@@ -2561,7 +2988,7 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 			if (err < 0 && err != -EINVAL)
 				return err;
 
-			if (uac_v2v3_control_is_readable(desc->bmControls,
+			if (uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls),
 							 UAC2_TE_CONNECTOR)) {
 				build_connector_control(&state, &state.oterm,
 							false);
@@ -2587,6 +3014,12 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 			err = parse_audio_unit(&state, desc->bCSourceID);
 			if (err < 0 && err != -EINVAL)
 				return err;
+
+			if (uac_v2v3_control_is_readable(le32_to_cpu(desc->bmControls),
+							 UAC3_TE_INSERTION)) {
+				build_connector_control(&state, &state.oterm,
+							false);
+			}
 		}
 	}
 
@@ -2597,9 +3030,9 @@ void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid)
 {
 	struct usb_mixer_elem_list *list;
 
-	for (list = mixer->id_elems[unitid]; list; list = list->next_id_elem) {
+	for_each_mixer_elem(list, mixer, unitid) {
 		struct usb_mixer_elem_info *info =
-			(struct usb_mixer_elem_info *)list;
+			mixer_elem_list_to_info(list);
 		/* invalidate cache, so the value is read from the device */
 		info->cached = 0;
 		snd_ctl_notify(mixer->chip->card, SNDRV_CTL_EVENT_MASK_VALUE,
@@ -2610,7 +3043,7 @@ void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid)
 static void snd_usb_mixer_dump_cval(struct snd_info_buffer *buffer,
 				    struct usb_mixer_elem_list *list)
 {
-	struct usb_mixer_elem_info *cval = (struct usb_mixer_elem_info *)list;
+	struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list);
 	static char *val_types[] = {"BOOLEAN", "INV_BOOLEAN",
 				    "S8", "U8", "S16", "U16"};
 	snd_iprintf(buffer, "    Info: id=%i, control=%i, cmask=0x%x, "
@@ -2636,8 +3069,7 @@ static void snd_usb_mixer_proc_read(struct snd_info_entry *entry,
 				mixer->ignore_ctl_error);
 		snd_iprintf(buffer, "Card: %s\n", chip->card->longname);
 		for (unitid = 0; unitid < MAX_ID_ELEMS; unitid++) {
-			for (list = mixer->id_elems[unitid]; list;
-			     list = list->next_id_elem) {
+			for_each_mixer_elem(list, mixer, unitid) {
 				snd_iprintf(buffer, "  Unit: %i\n", list->id);
 				if (list->kctl)
 					snd_iprintf(buffer,
@@ -2667,19 +3099,19 @@ static void snd_usb_mixer_interrupt_v2(struct usb_mixer_interface *mixer,
 		return;
 	}
 
-	for (list = mixer->id_elems[unitid]; list; list = list->next_id_elem)
+	for_each_mixer_elem(list, mixer, unitid)
 		count++;
 
 	if (count == 0)
 		return;
 
-	for (list = mixer->id_elems[unitid]; list; list = list->next_id_elem) {
+	for_each_mixer_elem(list, mixer, unitid) {
 		struct usb_mixer_elem_info *info;
 
 		if (!list->kctl)
 			continue;
 
-		info = (struct usb_mixer_elem_info *)list;
+		info = mixer_elem_list_to_info(list);
 		if (count > 1 && info->control != control)
 			continue;
 
@@ -2800,6 +3232,48 @@ static int snd_usb_mixer_status_create(struct usb_mixer_interface *mixer)
 	return 0;
 }
 
+static int keep_iface_ctl_get(struct snd_kcontrol *kcontrol,
+			      struct snd_ctl_elem_value *ucontrol)
+{
+	struct usb_mixer_interface *mixer = snd_kcontrol_chip(kcontrol);
+
+	ucontrol->value.integer.value[0] = mixer->chip->keep_iface;
+	return 0;
+}
+
+static int keep_iface_ctl_put(struct snd_kcontrol *kcontrol,
+			      struct snd_ctl_elem_value *ucontrol)
+{
+	struct usb_mixer_interface *mixer = snd_kcontrol_chip(kcontrol);
+	bool keep_iface = !!ucontrol->value.integer.value[0];
+
+	if (mixer->chip->keep_iface == keep_iface)
+		return 0;
+	mixer->chip->keep_iface = keep_iface;
+	return 1;
+}
+
+static const struct snd_kcontrol_new keep_iface_ctl = {
+	.iface = SNDRV_CTL_ELEM_IFACE_CARD,
+	.name = "Keep Interface",
+	.info = snd_ctl_boolean_mono_info,
+	.get = keep_iface_ctl_get,
+	.put = keep_iface_ctl_put,
+};
+
+static int create_keep_iface_ctl(struct usb_mixer_interface *mixer)
+{
+	struct snd_kcontrol *kctl = snd_ctl_new1(&keep_iface_ctl, mixer);
+
+	/* need only one control per card */
+	if (snd_ctl_find_id(mixer->chip->card, &kctl->id)) {
+		snd_ctl_free_one(kctl);
+		return 0;
+	}
+
+	return snd_ctl_add(mixer->chip->card, kctl);
+}
+
 int snd_usb_create_mixer(struct snd_usb_audio *chip, int ctrlif,
 			 int ignore_error)
 {
@@ -2838,8 +3312,21 @@ int snd_usb_create_mixer(struct snd_usb_audio *chip, int ctrlif,
 		break;
 	}
 
-	if ((err = snd_usb_mixer_controls(mixer)) < 0 ||
-	    (err = snd_usb_mixer_status_create(mixer)) < 0)
+	if (mixer->protocol == UAC_VERSION_3 &&
+			chip->badd_profile >= UAC3_FUNCTION_SUBCLASS_GENERIC_IO) {
+		err = snd_usb_mixer_controls_badd(mixer, ctrlif);
+		if (err < 0)
+			goto _error;
+	} else {
+		err = snd_usb_mixer_controls(mixer);
+		if (err < 0)
+			goto _error;
+		err = snd_usb_mixer_status_create(mixer);
+		if (err < 0)
+			goto _error;
+	}
+	err = create_keep_iface_ctl(mixer);
+	if (err < 0)
 		goto _error;
 
 	snd_usb_mixer_apply_create_quirk(mixer);
@@ -2900,7 +3387,7 @@ int snd_usb_mixer_suspend(struct usb_mixer_interface *mixer)
 
 static int restore_mixer_value(struct usb_mixer_elem_list *list)
 {
-	struct usb_mixer_elem_info *cval = (struct usb_mixer_elem_info *)list;
+	struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list);
 	int c, err, idx;
 
 	if (cval->cmask) {
@@ -2936,8 +3423,7 @@ int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume)
 	if (reset_resume) {
 		/* restore cached mixer values */
 		for (id = 0; id < MAX_ID_ELEMS; id++) {
-			for (list = mixer->id_elems[id]; list;
-			     list = list->next_id_elem) {
+			for_each_mixer_elem(list, mixer, id) {
 				if (list->resume) {
 					err = list->resume(list);
 					if (err < 0)
@@ -2947,6 +3433,8 @@ int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume)
 		}
 	}
 
+	snd_usb_mixer_resume_quirk(mixer);
+
 	return snd_usb_mixer_activate(mixer);
 }
 #endif
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index ba27f7ade670..e02653465e29 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -53,6 +53,12 @@ struct usb_mixer_elem_list {
 	usb_mixer_elem_resume_func_t resume;
 };
 
+/* iterate over mixer element list of the given unit id */
+#define for_each_mixer_elem(list, mixer, id)	\
+	for ((list) = (mixer)->id_elems[id]; (list); (list) = (list)->next_id_elem)
+#define mixer_elem_list_to_info(list) \
+	container_of(list, struct usb_mixer_elem_info, head)
+
 struct usb_mixer_elem_info {
 	struct usb_mixer_elem_list head;
 	unsigned int control;	/* CS or ICN (high byte) */
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 9038b2e7df73..71069e110897 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -353,8 +353,11 @@ static struct usbmix_name_map bose_companion5_map[] = {
 /*
  * Dell usb dock with ALC4020 codec had a firmware problem where it got
  * screwed up when zero volume is passed; just skip it as a workaround
+ *
+ * Also the extension unit gives an access error, so skip it as well.
  */
 static const struct usbmix_name_map dell_alc4020_map[] = {
+	{ 4, NULL },	/* extension unit */
 	{ 16, NULL },
 	{ 19, NULL },
 	{ 0 }
@@ -482,3 +485,68 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = {
 	{ 0 } /* terminator */
 };
 
+/*
+ * Control map entries for UAC3 BADD profiles
+ */
+
+static struct usbmix_name_map uac3_badd_generic_io_map[] = {
+	{ UAC3_BADD_FU_ID2, "Generic Out Playback" },
+	{ UAC3_BADD_FU_ID5, "Generic In Capture" },
+	{ 0 }					/* terminator */
+};
+static struct usbmix_name_map uac3_badd_headphone_map[] = {
+	{ UAC3_BADD_FU_ID2, "Headphone Playback" },
+	{ 0 }					/* terminator */
+};
+static struct usbmix_name_map uac3_badd_speaker_map[] = {
+	{ UAC3_BADD_FU_ID2, "Speaker Playback" },
+	{ 0 }					/* terminator */
+};
+static struct usbmix_name_map uac3_badd_microphone_map[] = {
+	{ UAC3_BADD_FU_ID5, "Mic Capture" },
+	{ 0 }					/* terminator */
+};
+/* Covers also 'headset adapter' profile */
+static struct usbmix_name_map uac3_badd_headset_map[] = {
+	{ UAC3_BADD_FU_ID2, "Headset Playback" },
+	{ UAC3_BADD_FU_ID5, "Headset Capture" },
+	{ UAC3_BADD_FU_ID7, "Sidetone Mixing" },
+	{ 0 }					/* terminator */
+};
+static struct usbmix_name_map uac3_badd_speakerphone_map[] = {
+	{ UAC3_BADD_FU_ID2, "Speaker Playback" },
+	{ UAC3_BADD_FU_ID5, "Mic Capture" },
+	{ 0 }					/* terminator */
+};
+
+static struct usbmix_ctl_map uac3_badd_usbmix_ctl_maps[] = {
+	{
+		.id = UAC3_FUNCTION_SUBCLASS_GENERIC_IO,
+		.map = uac3_badd_generic_io_map,
+	},
+	{
+		.id = UAC3_FUNCTION_SUBCLASS_HEADPHONE,
+		.map = uac3_badd_headphone_map,
+	},
+	{
+		.id = UAC3_FUNCTION_SUBCLASS_SPEAKER,
+		.map = uac3_badd_speaker_map,
+	},
+	{
+		.id = UAC3_FUNCTION_SUBCLASS_MICROPHONE,
+		.map = uac3_badd_microphone_map,
+	},
+	{
+		.id = UAC3_FUNCTION_SUBCLASS_HEADSET,
+		.map = uac3_badd_headset_map,
+	},
+	{
+		.id = UAC3_FUNCTION_SUBCLASS_HEADSET_ADAPTER,
+		.map = uac3_badd_headset_map,
+	},
+	{
+		.id = UAC3_FUNCTION_SUBCLASS_SPEAKERPHONE,
+		.map = uac3_badd_speakerphone_map,
+	},
+	{ 0 } /* terminator */
+};
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 56537a156580..e82a72fea9a1 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -1172,7 +1172,7 @@ void snd_emuusb_set_samplerate(struct snd_usb_audio *chip,
 	int unitid = 12; /* SamleRate ExtensionUnit ID */
 
 	list_for_each_entry(mixer, &chip->mixer_list, list) {
-		cval = (struct usb_mixer_elem_info *)mixer->id_elems[unitid];
+		cval = mixer_elem_list_to_info(mixer->id_elems[unitid]);
 		if (cval) {
 			snd_usb_mixer_set_ctl_value(cval, UAC_SET_CUR,
 						    cval->control << 8,
@@ -1799,12 +1799,33 @@ static int snd_soundblaster_e1_switch_create(struct usb_mixer_interface *mixer)
 					  NULL);
 }
 
+static void dell_dock_init_vol(struct snd_usb_audio *chip, int ch, int id)
+{
+	u16 buf = 0;
+
+	snd_usb_ctl_msg(chip->dev, usb_sndctrlpipe(chip->dev, 0), UAC_SET_CUR,
+			USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT,
+			ch, snd_usb_ctrl_intf(chip) | (id << 8),
+			&buf, 2);
+}
+
+static int dell_dock_mixer_init(struct usb_mixer_interface *mixer)
+{
+	/* fix to 0dB playback volumes */
+	dell_dock_init_vol(mixer->chip, 1, 16);
+	dell_dock_init_vol(mixer->chip, 2, 16);
+	dell_dock_init_vol(mixer->chip, 1, 19);
+	dell_dock_init_vol(mixer->chip, 2, 19);
+	return 0;
+}
+
 int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer)
 {
 	int err = 0;
 	struct snd_info_entry *entry;
 
-	if ((err = snd_usb_soundblaster_remote_init(mixer)) < 0)
+	err = snd_usb_soundblaster_remote_init(mixer);
+	if (err < 0)
 		return err;
 
 	switch (mixer->chip->usb_id) {
@@ -1828,8 +1849,6 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer)
 	/* EMU0204 */
 	case USB_ID(0x041e, 0x3f19):
 		err = snd_emu0204_controls_create(mixer);
-		if (err < 0)
-			break;
 		break;
 
 	case USB_ID(0x0763, 0x2030): /* M-Audio Fast Track C400 */
@@ -1884,11 +1903,25 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer)
 	case USB_ID(0x041e, 0x323b): /* Creative Sound Blaster E1 */
 		err = snd_soundblaster_e1_switch_create(mixer);
 		break;
+	case USB_ID(0x0bda, 0x4014): /* Dell WD15 dock */
+		err = dell_dock_mixer_init(mixer);
+		break;
 	}
 
 	return err;
 }
 
+#ifdef CONFIG_PM
+void snd_usb_mixer_resume_quirk(struct usb_mixer_interface *mixer)
+{
+	switch (mixer->chip->usb_id) {
+	case USB_ID(0x0bda, 0x4014): /* Dell WD15 dock */
+		dell_dock_mixer_init(mixer);
+		break;
+	}
+}
+#endif
+
 void snd_usb_mixer_rc_memory_change(struct usb_mixer_interface *mixer,
 				    int unitid)
 {
diff --git a/sound/usb/mixer_quirks.h b/sound/usb/mixer_quirks.h
index b5abd328a361..52be26db558f 100644
--- a/sound/usb/mixer_quirks.h
+++ b/sound/usb/mixer_quirks.h
@@ -14,5 +14,9 @@ void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer,
 				  struct usb_mixer_elem_info *cval, int unitid,
 				  struct snd_kcontrol *kctl);
 
+#ifdef CONFIG_PM
+void snd_usb_mixer_resume_quirk(struct usb_mixer_interface *mixer);
+#endif
+
 #endif /* SND_USB_MIXER_QUIRKS_H */
 
diff --git a/sound/usb/mixer_scarlett.c b/sound/usb/mixer_scarlett.c
index c33e2378089d..4aeb9488a0c9 100644
--- a/sound/usb/mixer_scarlett.c
+++ b/sound/usb/mixer_scarlett.c
@@ -287,8 +287,7 @@ static int scarlett_ctl_switch_put(struct snd_kcontrol *kctl,
 
 static int scarlett_ctl_resume(struct usb_mixer_elem_list *list)
 {
-	struct usb_mixer_elem_info *elem =
-		container_of(list, struct usb_mixer_elem_info, head);
+	struct usb_mixer_elem_info *elem = mixer_elem_list_to_info(list);
 	int i;
 
 	for (i = 0; i < elem->channels; i++)
@@ -447,8 +446,7 @@ static int scarlett_ctl_enum_put(struct snd_kcontrol *kctl,
 
 static int scarlett_ctl_enum_resume(struct usb_mixer_elem_list *list)
 {
-	struct usb_mixer_elem_info *elem =
-		container_of(list, struct usb_mixer_elem_info, head);
+	struct usb_mixer_elem_info *elem = mixer_elem_list_to_info(list);
 
 	if (elem->cached)
 		snd_usb_set_cur_mix_value(elem, 0, 0, *elem->cache_val);
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 3cbfae6604f9..78d1cad08a0a 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -76,10 +76,9 @@ snd_pcm_uframes_t snd_usb_pcm_delay(struct snd_usb_substream *subs,
  */
 static snd_pcm_uframes_t snd_usb_pcm_pointer(struct snd_pcm_substream *substream)
 {
-	struct snd_usb_substream *subs;
+	struct snd_usb_substream *subs = substream->runtime->private_data;
 	unsigned int hwptr_done;
 
-	subs = (struct snd_usb_substream *)substream->runtime->private_data;
 	if (atomic_read(&subs->stream->chip->shutdown))
 		return SNDRV_PCM_POS_XRUN;
 	spin_lock(&subs->lock);
@@ -164,10 +163,11 @@ static int init_pitch_v1(struct snd_usb_audio *chip, int iface,
 	ep = get_endpoint(alts, 0)->bEndpointAddress;
 
 	data[0] = 1;
-	if ((err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR,
-				   USB_TYPE_CLASS|USB_RECIP_ENDPOINT|USB_DIR_OUT,
-				   UAC_EP_CS_ATTR_PITCH_CONTROL << 8, ep,
-				   data, sizeof(data))) < 0) {
+	err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR,
+			      USB_TYPE_CLASS|USB_RECIP_ENDPOINT|USB_DIR_OUT,
+			      UAC_EP_CS_ATTR_PITCH_CONTROL << 8, ep,
+			      data, sizeof(data));
+	if (err < 0) {
 		usb_audio_err(chip, "%d:%d: cannot set enable PITCH\n",
 			      iface, ep);
 		return err;
@@ -185,10 +185,11 @@ static int init_pitch_v2(struct snd_usb_audio *chip, int iface,
 	int err;
 
 	data[0] = 1;
-	if ((err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC2_CS_CUR,
-				   USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_OUT,
-				   UAC2_EP_CS_PITCH << 8, 0,
-				   data, sizeof(data))) < 0) {
+	err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC2_CS_CUR,
+			      USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_OUT,
+			      UAC2_EP_CS_PITCH << 8, 0,
+			      data, sizeof(data));
+	if (err < 0) {
 		usb_audio_err(chip, "%d:%d: cannot set enable PITCH (v2)\n",
 			      iface, fmt->altsetting);
 		return err;
@@ -321,6 +322,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 	struct usb_host_interface *alts;
 	struct usb_interface *iface;
 	unsigned int ep;
+	unsigned int ifnum;
 
 	/* Implicit feedback sync EPs consumers are always playback EPs */
 	if (subs->direction != SNDRV_PCM_STREAM_PLAYBACK)
@@ -330,44 +332,27 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 	case USB_ID(0x0763, 0x2030): /* M-Audio Fast Track C400 */
 	case USB_ID(0x0763, 0x2031): /* M-Audio Fast Track C600 */
 		ep = 0x81;
-		iface = usb_ifnum_to_if(dev, 3);
-
-		if (!iface || iface->num_altsetting == 0)
-			return -EINVAL;
-
-		alts = &iface->altsetting[1];
-		goto add_sync_ep;
-		break;
+		ifnum = 3;
+		goto add_sync_ep_from_ifnum;
 	case USB_ID(0x0763, 0x2080): /* M-Audio FastTrack Ultra */
 	case USB_ID(0x0763, 0x2081):
 		ep = 0x81;
-		iface = usb_ifnum_to_if(dev, 2);
-
-		if (!iface || iface->num_altsetting == 0)
-			return -EINVAL;
-
-		alts = &iface->altsetting[1];
-		goto add_sync_ep;
-	case USB_ID(0x2466, 0x8003):
+		ifnum = 2;
+		goto add_sync_ep_from_ifnum;
+	case USB_ID(0x2466, 0x8003): /* Fractal Audio Axe-Fx II */
 		ep = 0x86;
-		iface = usb_ifnum_to_if(dev, 2);
-
-		if (!iface || iface->num_altsetting == 0)
-			return -EINVAL;
-
-		alts = &iface->altsetting[1];
-		goto add_sync_ep;
-	case USB_ID(0x1397, 0x0002):
+		ifnum = 2;
+		goto add_sync_ep_from_ifnum;
+	case USB_ID(0x2466, 0x8010): /* Fractal Audio Axe-Fx III */
 		ep = 0x81;
-		iface = usb_ifnum_to_if(dev, 1);
-
-		if (!iface || iface->num_altsetting == 0)
-			return -EINVAL;
-
-		alts = &iface->altsetting[1];
-		goto add_sync_ep;
-
+		ifnum = 2;
+		goto add_sync_ep_from_ifnum;
+	case USB_ID(0x1397, 0x0002): /* Behringer UFX1204 */
+		ep = 0x81;
+		ifnum = 1;
+		goto add_sync_ep_from_ifnum;
 	}
+
 	if (attr == USB_ENDPOINT_SYNC_ASYNC &&
 	    altsd->bInterfaceClass == USB_CLASS_VENDOR_SPEC &&
 	    altsd->bInterfaceProtocol == 2 &&
@@ -382,6 +367,14 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 	/* No quirk */
 	return 0;
 
+add_sync_ep_from_ifnum:
+	iface = usb_ifnum_to_if(dev, ifnum);
+
+	if (!iface || iface->num_altsetting == 0)
+		return -EINVAL;
+
+	alts = &iface->altsetting[1];
+
 add_sync_ep:
 	subs->sync_endpoint = snd_usb_add_endpoint(subs->stream->chip,
 						   alts, ep, !subs->direction,
@@ -507,7 +500,7 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt)
 	iface = usb_ifnum_to_if(dev, fmt->iface);
 	if (WARN_ON(!iface))
 		return -EINVAL;
-	alts = &iface->altsetting[fmt->altset_idx];
+	alts = usb_altnum_to_altsetting(iface, fmt->altsetting);
 	altsd = get_iface_desc(alts);
 	if (WARN_ON(altsd->bAlternateSetting != fmt->altsetting))
 		return -EINVAL;
@@ -517,21 +510,21 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt)
 
 	/* close the old interface */
 	if (subs->interface >= 0 && subs->interface != fmt->iface) {
-		err = usb_set_interface(subs->dev, subs->interface, 0);
-		if (err < 0) {
-			dev_err(&dev->dev,
-				"%d:%d: return to setting 0 failed (%d)\n",
-				fmt->iface, fmt->altsetting, err);
-			return -EIO;
+		if (!subs->stream->chip->keep_iface) {
+			err = usb_set_interface(subs->dev, subs->interface, 0);
+			if (err < 0) {
+				dev_err(&dev->dev,
+					"%d:%d: return to setting 0 failed (%d)\n",
+					fmt->iface, fmt->altsetting, err);
+				return -EIO;
+			}
 		}
 		subs->interface = -1;
 		subs->altset_idx = 0;
 	}
 
 	/* set interface */
-	if (subs->interface != fmt->iface ||
-	    subs->altset_idx != fmt->altset_idx) {
-
+	if (iface->cur_altsetting != alts) {
 		err = snd_usb_select_mode_quirk(subs, fmt);
 		if (err < 0)
 			return -EIO;
@@ -545,12 +538,11 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt)
 		}
 		dev_dbg(&dev->dev, "setting usb interface %d:%d\n",
 			fmt->iface, fmt->altsetting);
-		subs->interface = fmt->iface;
-		subs->altset_idx = fmt->altset_idx;
-
 		snd_usb_set_interface_quirk(dev);
 	}
 
+	subs->interface = fmt->iface;
+	subs->altset_idx = fmt->altset_idx;
 	subs->data_endpoint = snd_usb_add_endpoint(subs->stream->chip,
 						   alts, fmt->endpoint, subs->direction,
 						   SND_USB_ENDPOINT_TYPE_DATA);
@@ -736,7 +728,11 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream,
 	struct audioformat *fmt;
 	int ret;
 
-	ret = snd_pcm_lib_alloc_vmalloc_buffer(substream,
+	if (snd_usb_use_vmalloc)
+		ret = snd_pcm_lib_alloc_vmalloc_buffer(substream,
+						       params_buffer_bytes(hw_params));
+	else
+		ret = snd_pcm_lib_malloc_pages(substream,
 					       params_buffer_bytes(hw_params));
 	if (ret < 0)
 		return ret;
@@ -789,7 +785,11 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream)
 		snd_usb_endpoint_deactivate(subs->data_endpoint);
 		snd_usb_unlock_shutdown(subs->stream->chip);
 	}
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+
+	if (snd_usb_use_vmalloc)
+		return snd_pcm_lib_free_vmalloc_buffer(substream);
+	else
+		return snd_pcm_lib_free_pages(substream);
 }
 
 /*
@@ -1181,9 +1181,6 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre
 		pt = 125 * (1 << fp->datainterval);
 		ptmin = min(ptmin, pt);
 	}
-	err = snd_usb_autoresume(subs->stream->chip);
-	if (err < 0)
-		return err;
 
 	param_period_time_if_needed = SNDRV_PCM_HW_PARAM_PERIOD_TIME;
 	if (subs->speed == USB_SPEED_FULL)
@@ -1192,30 +1189,37 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre
 	if (ptmin == 1000)
 		/* if period time doesn't go below 1 ms, no rules needed */
 		param_period_time_if_needed = -1;
-	snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIOD_TIME,
-				     ptmin, UINT_MAX);
-
-	if ((err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
-				       hw_rule_rate, subs,
-				       SNDRV_PCM_HW_PARAM_FORMAT,
-				       SNDRV_PCM_HW_PARAM_CHANNELS,
-				       param_period_time_if_needed,
-				       -1)) < 0)
-		goto rep_err;
-	if ((err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
-				       hw_rule_channels, subs,
-				       SNDRV_PCM_HW_PARAM_FORMAT,
-				       SNDRV_PCM_HW_PARAM_RATE,
-				       param_period_time_if_needed,
-				       -1)) < 0)
-		goto rep_err;
-	if ((err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT,
-				       hw_rule_format, subs,
-				       SNDRV_PCM_HW_PARAM_RATE,
-				       SNDRV_PCM_HW_PARAM_CHANNELS,
-				       param_period_time_if_needed,
-				       -1)) < 0)
-		goto rep_err;
+
+	err = snd_pcm_hw_constraint_minmax(runtime,
+					   SNDRV_PCM_HW_PARAM_PERIOD_TIME,
+					   ptmin, UINT_MAX);
+	if (err < 0)
+		return err;
+
+	err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
+				  hw_rule_rate, subs,
+				  SNDRV_PCM_HW_PARAM_FORMAT,
+				  SNDRV_PCM_HW_PARAM_CHANNELS,
+				  param_period_time_if_needed,
+				  -1);
+	if (err < 0)
+		return err;
+	err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
+				  hw_rule_channels, subs,
+				  SNDRV_PCM_HW_PARAM_FORMAT,
+				  SNDRV_PCM_HW_PARAM_RATE,
+				  param_period_time_if_needed,
+				  -1);
+	if (err < 0)
+		return err;
+	err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT,
+				  hw_rule_format, subs,
+				  SNDRV_PCM_HW_PARAM_RATE,
+				  SNDRV_PCM_HW_PARAM_CHANNELS,
+				  param_period_time_if_needed,
+				  -1);
+	if (err < 0)
+		return err;
 	if (param_period_time_if_needed >= 0) {
 		err = snd_pcm_hw_rule_add(runtime, 0,
 					  SNDRV_PCM_HW_PARAM_PERIOD_TIME,
@@ -1225,19 +1229,18 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre
 					  SNDRV_PCM_HW_PARAM_RATE,
 					  -1);
 		if (err < 0)
-			goto rep_err;
+			return err;
 	}
-	if ((err = snd_usb_pcm_check_knot(runtime, subs)) < 0)
-		goto rep_err;
-	return 0;
+	err = snd_usb_pcm_check_knot(runtime, subs);
+	if (err < 0)
+		return err;
 
-rep_err:
-	snd_usb_autosuspend(subs->stream->chip);
-	return err;
+	return snd_usb_autoresume(subs->stream->chip);
 }
 
-static int snd_usb_pcm_open(struct snd_pcm_substream *substream, int direction)
+static int snd_usb_pcm_open(struct snd_pcm_substream *substream)
 {
+	int direction = substream->stream;
 	struct snd_usb_stream *as = snd_pcm_substream_chip(substream);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_usb_substream *subs = &as->substream[direction];
@@ -1257,14 +1260,16 @@ static int snd_usb_pcm_open(struct snd_pcm_substream *substream, int direction)
 	return setup_hw_info(runtime, subs);
 }
 
-static int snd_usb_pcm_close(struct snd_pcm_substream *substream, int direction)
+static int snd_usb_pcm_close(struct snd_pcm_substream *substream)
 {
+	int direction = substream->stream;
 	struct snd_usb_stream *as = snd_pcm_substream_chip(substream);
 	struct snd_usb_substream *subs = &as->substream[direction];
 
 	stop_endpoints(subs, true);
 
-	if (subs->interface >= 0 &&
+	if (!as->chip->keep_iface &&
+	    subs->interface >= 0 &&
 	    !snd_usb_lock_shutdown(subs->stream->chip)) {
 		usb_set_interface(subs->dev, subs->interface, 0);
 		subs->interface = -1;
@@ -1311,7 +1316,7 @@ static void retire_capture_urb(struct snd_usb_substream *subs,
 		if (bytes % (runtime->sample_bits >> 3) != 0) {
 			int oldbytes = bytes;
 			bytes = frames * stride;
-			dev_warn(&subs->dev->dev,
+			dev_warn_ratelimited(&subs->dev->dev,
 				 "Corrected urb data len. %d->%d\n",
 							oldbytes, bytes);
 		}
@@ -1619,26 +1624,6 @@ static void retire_playback_urb(struct snd_usb_substream *subs,
 	spin_unlock_irqrestore(&subs->lock, flags);
 }
 
-static int snd_usb_playback_open(struct snd_pcm_substream *substream)
-{
-	return snd_usb_pcm_open(substream, SNDRV_PCM_STREAM_PLAYBACK);
-}
-
-static int snd_usb_playback_close(struct snd_pcm_substream *substream)
-{
-	return snd_usb_pcm_close(substream, SNDRV_PCM_STREAM_PLAYBACK);
-}
-
-static int snd_usb_capture_open(struct snd_pcm_substream *substream)
-{
-	return snd_usb_pcm_open(substream, SNDRV_PCM_STREAM_CAPTURE);
-}
-
-static int snd_usb_capture_close(struct snd_pcm_substream *substream)
-{
-	return snd_usb_pcm_close(substream, SNDRV_PCM_STREAM_CAPTURE);
-}
-
 static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substream,
 					      int cmd)
 {
@@ -1700,8 +1685,8 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream
 }
 
 static const struct snd_pcm_ops snd_usb_playback_ops = {
-	.open =		snd_usb_playback_open,
-	.close =	snd_usb_playback_close,
+	.open =		snd_usb_pcm_open,
+	.close =	snd_usb_pcm_close,
 	.ioctl =	snd_pcm_lib_ioctl,
 	.hw_params =	snd_usb_hw_params,
 	.hw_free =	snd_usb_hw_free,
@@ -1713,8 +1698,8 @@ static const struct snd_pcm_ops snd_usb_playback_ops = {
 };
 
 static const struct snd_pcm_ops snd_usb_capture_ops = {
-	.open =		snd_usb_capture_open,
-	.close =	snd_usb_capture_close,
+	.open =		snd_usb_pcm_open,
+	.close =	snd_usb_pcm_close,
 	.ioctl =	snd_pcm_lib_ioctl,
 	.hw_params =	snd_usb_hw_params,
 	.hw_free =	snd_usb_hw_free,
@@ -1725,9 +1710,50 @@ static const struct snd_pcm_ops snd_usb_capture_ops = {
 	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
+static const struct snd_pcm_ops snd_usb_playback_dev_ops = {
+	.open =		snd_usb_pcm_open,
+	.close =	snd_usb_pcm_close,
+	.ioctl =	snd_pcm_lib_ioctl,
+	.hw_params =	snd_usb_hw_params,
+	.hw_free =	snd_usb_hw_free,
+	.prepare =	snd_usb_pcm_prepare,
+	.trigger =	snd_usb_substream_playback_trigger,
+	.pointer =	snd_usb_pcm_pointer,
+	.page =		snd_pcm_sgbuf_ops_page,
+};
+
+static const struct snd_pcm_ops snd_usb_capture_dev_ops = {
+	.open =		snd_usb_pcm_open,
+	.close =	snd_usb_pcm_close,
+	.ioctl =	snd_pcm_lib_ioctl,
+	.hw_params =	snd_usb_hw_params,
+	.hw_free =	snd_usb_hw_free,
+	.prepare =	snd_usb_pcm_prepare,
+	.trigger =	snd_usb_substream_capture_trigger,
+	.pointer =	snd_usb_pcm_pointer,
+	.page =		snd_pcm_sgbuf_ops_page,
+};
+
 void snd_usb_set_pcm_ops(struct snd_pcm *pcm, int stream)
 {
-	snd_pcm_set_ops(pcm, stream,
-			stream == SNDRV_PCM_STREAM_PLAYBACK ?
-			&snd_usb_playback_ops : &snd_usb_capture_ops);
+	const struct snd_pcm_ops *ops;
+
+	if (snd_usb_use_vmalloc)
+		ops = stream == SNDRV_PCM_STREAM_PLAYBACK ?
+			&snd_usb_playback_ops : &snd_usb_capture_ops;
+	else
+		ops = stream == SNDRV_PCM_STREAM_PLAYBACK ?
+			&snd_usb_playback_dev_ops : &snd_usb_capture_dev_ops;
+	snd_pcm_set_ops(pcm, stream, ops);
+}
+
+void snd_usb_preallocate_buffer(struct snd_usb_substream *subs)
+{
+	struct snd_pcm *pcm = subs->stream->pcm;
+	struct snd_pcm_substream *s = pcm->streams[subs->direction].substream;
+	struct device *dev = subs->dev->bus->controller;
+
+	if (!snd_usb_use_vmalloc)
+		snd_pcm_lib_preallocate_pages(s, SNDRV_DMA_TYPE_DEV_SG,
+					      dev, 64*1024, 512*1024);
 }
diff --git a/sound/usb/pcm.h b/sound/usb/pcm.h
index 35740d5ef268..f77ec58bf1a1 100644
--- a/sound/usb/pcm.h
+++ b/sound/usb/pcm.h
@@ -10,6 +10,7 @@ void snd_usb_set_pcm_ops(struct snd_pcm *pcm, int stream);
 int snd_usb_init_pitch(struct snd_usb_audio *chip, int iface,
 		       struct usb_host_interface *alts,
 		       struct audioformat *fmt);
+void snd_usb_preallocate_buffer(struct snd_usb_substream *subs);
 
 
 #endif /* __USBAUDIO_PCM_H */
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 754e632a27bd..0e37e358ca97 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -3371,5 +3371,15 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 		}
 	}
 },
+/* Dell WD15 Dock */
+{
+	USB_DEVICE(0x0bda, 0x4014),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.vendor_name = "Dell",
+		.product_name = "WD15 Dock",
+		.profile_name = "Dell-WD15-Dock",
+		.ifnum = QUIRK_NO_INTERFACE
+	}
+},
 
 #undef USB_DEVICE_VENDOR_SPEC
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index acbeb52f6fd6..f4b69173682c 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -851,6 +851,36 @@ static int snd_usb_mbox2_boot_quirk(struct usb_device *dev)
 	return 0; /* Successful boot */
 }
 
+static int snd_usb_axefx3_boot_quirk(struct usb_device *dev)
+{
+	int err;
+
+	dev_dbg(&dev->dev, "Waiting for Axe-Fx III to boot up...\n");
+
+	/* If the Axe-Fx III has not fully booted, it will timeout when trying
+	 * to enable the audio streaming interface. A more generous timeout is
+	 * used here to detect when the Axe-Fx III has finished booting as the
+	 * set interface message will be acked once it has
+	 */
+	err = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
+				USB_REQ_SET_INTERFACE, USB_RECIP_INTERFACE,
+				1, 1, NULL, 0, 120000);
+	if (err < 0) {
+		dev_err(&dev->dev,
+			"failed waiting for Axe-Fx III to boot: %d\n", err);
+		return err;
+	}
+
+	dev_dbg(&dev->dev, "Axe-Fx III is now ready\n");
+
+	err = usb_set_interface(dev, 1, 0);
+	if (err < 0)
+		dev_dbg(&dev->dev,
+			"error stopping Axe-Fx III interface: %d\n", err);
+
+	return 0;
+}
+
 /*
  * Setup quirks
  */
@@ -1026,6 +1056,8 @@ int snd_usb_apply_boot_quirk(struct usb_device *dev,
 		return snd_usb_fasttrackpro_boot_quirk(dev);
 	case USB_ID(0x047f, 0xc010): /* Plantronics Gamecom 780 */
 		return snd_usb_gamecon780_boot_quirk(dev);
+	case USB_ID(0x2466, 0x8010): /* Fractal Audio Axe-Fx 3 */
+		return snd_usb_axefx3_boot_quirk(dev);
 	}
 
 	return 0;
@@ -1327,20 +1359,47 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 
 	/* XMOS based USB DACs */
 	switch (chip->usb_id) {
+	case USB_ID(0x1511, 0x0037): /* AURALiC VEGA */
+	case USB_ID(0x20b1, 0x0002): /* Wyred 4 Sound DAC-2 DSD */
+	case USB_ID(0x20b1, 0x2004): /* Matrix Audio X-SPDIF 2 */
 	case USB_ID(0x20b1, 0x3008): /* iFi Audio micro/nano iDSD */
 	case USB_ID(0x20b1, 0x2008): /* Matrix Audio X-Sabre */
 	case USB_ID(0x20b1, 0x300a): /* Matrix Audio Mini-i Pro */
 	case USB_ID(0x22d9, 0x0416): /* OPPO HA-1 */
+	case USB_ID(0x22d9, 0x0436): /* OPPO Sonica */
+	case USB_ID(0x22d9, 0x0461): /* OPPO UDP-205 */
+	case USB_ID(0x2522, 0x0012): /* LH Labs VI DAC Infinity */
+	case USB_ID(0x25ce, 0x001f): /* Mytek Brooklyn DAC */
+	case USB_ID(0x25ce, 0x0021): /* Mytek Manhattan DAC */
+	case USB_ID(0x25ce, 0x8025): /* Mytek Brooklyn DAC+ */
 	case USB_ID(0x2772, 0x0230): /* Pro-Ject Pre Box S2 Digital */
 		if (fp->altsetting == 2)
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
 		break;
 
+	case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */
+	case USB_ID(0x16b0, 0x06b2): /* NuPrime DAC-10 */
+	case USB_ID(0x16d0, 0x0733): /* Furutech ADL Stratos */
+	case USB_ID(0x16d0, 0x09db): /* NuPrime Audio DAC-9 */
+	case USB_ID(0x1db5, 0x0003): /* Bryston BDA3 */
 	case USB_ID(0x20b1, 0x000a): /* Gustard DAC-X20U */
+	case USB_ID(0x20b1, 0x2005): /* Denafrips Ares DAC */
 	case USB_ID(0x20b1, 0x2009): /* DIYINHK DSD DXD 384kHz USB to I2S/DSD */
 	case USB_ID(0x20b1, 0x2023): /* JLsounds I2SoverUSB */
+	case USB_ID(0x20b1, 0x3021): /* Eastern El. MiniMax Tube DAC Supreme */
 	case USB_ID(0x20b1, 0x3023): /* Aune X1S 32BIT/384 DSD DAC */
+	case USB_ID(0x20b1, 0x302d): /* Unison Research Unico CD Due */
+	case USB_ID(0x20b1, 0x3036): /* Holo Springs Level 3 R2R DAC */
+	case USB_ID(0x20b1, 0x307b): /* CH Precision C1 DAC */
+	case USB_ID(0x20b1, 0x3086): /* Singxer F-1 converter board */
+	case USB_ID(0x22d9, 0x0426): /* OPPO HA-2 */
+	case USB_ID(0x22e1, 0xca01): /* HDTA Serenade DSD */
+	case USB_ID(0x249c, 0x9326): /* M2Tech Young MkIII */
 	case USB_ID(0x2616, 0x0106): /* PS Audio NuWave DAC */
+	case USB_ID(0x2622, 0x0041): /* Audiolab M-DAC+ */
+	case USB_ID(0x27f7, 0x3002): /* W4S DAC-2v2SE */
+	case USB_ID(0x29a2, 0x0086): /* Mutec MC3+ USB */
+	case USB_ID(0x6b42, 0x0042): /* MSB Technology */
 		if (fp->altsetting == 3)
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
 		break;
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index 6a8f5843334e..729afd808cc4 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -106,6 +106,8 @@ static void snd_usb_init_substream(struct snd_usb_stream *as,
 	subs->ep_num = fp->endpoint;
 	if (fp->channels > subs->channels_max)
 		subs->channels_max = fp->channels;
+
+	snd_usb_preallocate_buffer(subs);
 }
 
 /* kctl callbacks for usb-audio channel maps */
@@ -349,7 +351,7 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor
 			 * TODO: this conversion is not complete, update it
 			 * after adding UAC3 values to asound.h
 			 */
-			switch (is->bChPurpose) {
+			switch (is->bChRelationship) {
 			case UAC3_CH_MONO:
 				map = SNDRV_CHMAP_MONO;
 				break;
@@ -576,7 +578,7 @@ static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip,
 
 	if (protocol == UAC_VERSION_1) {
 		attributes = csep->bmAttributes;
-	} else {
+	} else if (protocol == UAC_VERSION_2) {
 		struct uac2_iso_endpoint_descriptor *csep2 =
 			(struct uac2_iso_endpoint_descriptor *) csep;
 
@@ -585,6 +587,13 @@ static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip,
 		/* emulate the endpoint attributes of a v1 device */
 		if (csep2->bmControls & UAC2_CONTROL_PITCH)
 			attributes |= UAC_EP_CS_ATTR_PITCH_CONTROL;
+	} else { /* UAC_VERSION_3 */
+		struct uac3_iso_endpoint_descriptor *csep3 =
+			(struct uac3_iso_endpoint_descriptor *) csep;
+
+		/* emulate the endpoint attributes of a v1 device */
+		if (le32_to_cpu(csep3->bmControls) & UAC2_CONTROL_PITCH)
+			attributes |= UAC_EP_CS_ATTR_PITCH_CONTROL;
 	}
 
 	return attributes;
@@ -626,6 +635,395 @@ snd_usb_find_output_terminal_descriptor(struct usb_host_interface *ctrl_iface,
 	return NULL;
 }
 
+static struct audioformat *
+audio_format_alloc_init(struct snd_usb_audio *chip,
+		       struct usb_host_interface *alts,
+		       int protocol, int iface_no, int altset_idx,
+		       int altno, int num_channels, int clock)
+{
+	struct audioformat *fp;
+
+	fp = kzalloc(sizeof(*fp), GFP_KERNEL);
+	if (!fp)
+		return NULL;
+
+	fp->iface = iface_no;
+	fp->altsetting = altno;
+	fp->altset_idx = altset_idx;
+	fp->endpoint = get_endpoint(alts, 0)->bEndpointAddress;
+	fp->ep_attr = get_endpoint(alts, 0)->bmAttributes;
+	fp->datainterval = snd_usb_parse_datainterval(chip, alts);
+	fp->protocol = protocol;
+	fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
+	fp->channels = num_channels;
+	if (snd_usb_get_speed(chip->dev) == USB_SPEED_HIGH)
+		fp->maxpacksize = (((fp->maxpacksize >> 11) & 3) + 1)
+				* (fp->maxpacksize & 0x7ff);
+	fp->clock = clock;
+	INIT_LIST_HEAD(&fp->list);
+
+	return fp;
+}
+
+static struct audioformat *
+snd_usb_get_audioformat_uac12(struct snd_usb_audio *chip,
+			      struct usb_host_interface *alts,
+			      int protocol, int iface_no, int altset_idx,
+			      int altno, int stream, int bm_quirk)
+{
+	struct usb_device *dev = chip->dev;
+	struct uac_format_type_i_continuous_descriptor *fmt;
+	unsigned int num_channels = 0, chconfig = 0;
+	struct audioformat *fp;
+	int clock = 0;
+	u64 format;
+
+	/* get audio formats */
+	if (protocol == UAC_VERSION_1) {
+		struct uac1_as_header_descriptor *as =
+			snd_usb_find_csint_desc(alts->extra, alts->extralen,
+						NULL, UAC_AS_GENERAL);
+		struct uac_input_terminal_descriptor *iterm;
+
+		if (!as) {
+			dev_err(&dev->dev,
+				"%u:%d : UAC_AS_GENERAL descriptor not found\n",
+				iface_no, altno);
+			return NULL;
+		}
+
+		if (as->bLength < sizeof(*as)) {
+			dev_err(&dev->dev,
+				"%u:%d : invalid UAC_AS_GENERAL desc\n",
+				iface_no, altno);
+			return NULL;
+		}
+
+		format = le16_to_cpu(as->wFormatTag); /* remember the format value */
+
+		iterm = snd_usb_find_input_terminal_descriptor(chip->ctrl_intf,
+							     as->bTerminalLink);
+		if (iterm) {
+			num_channels = iterm->bNrChannels;
+			chconfig = le16_to_cpu(iterm->wChannelConfig);
+		}
+	} else { /* UAC_VERSION_2 */
+		struct uac2_input_terminal_descriptor *input_term;
+		struct uac2_output_terminal_descriptor *output_term;
+		struct uac2_as_header_descriptor *as =
+			snd_usb_find_csint_desc(alts->extra, alts->extralen,
+						NULL, UAC_AS_GENERAL);
+
+		if (!as) {
+			dev_err(&dev->dev,
+				"%u:%d : UAC_AS_GENERAL descriptor not found\n",
+				iface_no, altno);
+			return NULL;
+		}
+
+		if (as->bLength < sizeof(*as)) {
+			dev_err(&dev->dev,
+				"%u:%d : invalid UAC_AS_GENERAL desc\n",
+				iface_no, altno);
+			return NULL;
+		}
+
+		num_channels = as->bNrChannels;
+		format = le32_to_cpu(as->bmFormats);
+		chconfig = le32_to_cpu(as->bmChannelConfig);
+
+		/*
+		 * lookup the terminal associated to this interface
+		 * to extract the clock
+		 */
+		input_term = snd_usb_find_input_terminal_descriptor(chip->ctrl_intf,
+								    as->bTerminalLink);
+		if (input_term) {
+			clock = input_term->bCSourceID;
+			if (!chconfig && (num_channels == input_term->bNrChannels))
+				chconfig = le32_to_cpu(input_term->bmChannelConfig);
+			goto found_clock;
+		}
+
+		output_term = snd_usb_find_output_terminal_descriptor(chip->ctrl_intf,
+								      as->bTerminalLink);
+		if (output_term) {
+			clock = output_term->bCSourceID;
+			goto found_clock;
+		}
+
+		dev_err(&dev->dev,
+			"%u:%d : bogus bTerminalLink %d\n",
+			iface_no, altno, as->bTerminalLink);
+		return NULL;
+	}
+
+found_clock:
+	/* get format type */
+	fmt = snd_usb_find_csint_desc(alts->extra, alts->extralen,
+				      NULL, UAC_FORMAT_TYPE);
+	if (!fmt) {
+		dev_err(&dev->dev,
+			"%u:%d : no UAC_FORMAT_TYPE desc\n",
+			iface_no, altno);
+		return NULL;
+	}
+	if (((protocol == UAC_VERSION_1) && (fmt->bLength < 8))
+			|| ((protocol == UAC_VERSION_2) &&
+					(fmt->bLength < 6))) {
+		dev_err(&dev->dev,
+			"%u:%d : invalid UAC_FORMAT_TYPE desc\n",
+			iface_no, altno);
+		return NULL;
+	}
+
+	/*
+	 * Blue Microphones workaround: The last altsetting is
+	 * identical with the previous one, except for a larger
+	 * packet size, but is actually a mislabeled two-channel
+	 * setting; ignore it.
+	 *
+	 * Part 2: analyze quirk flag and format
+	 */
+	if (bm_quirk && fmt->bNrChannels == 1 && fmt->bSubframeSize == 2)
+		return NULL;
+
+	fp = audio_format_alloc_init(chip, alts, protocol, iface_no,
+				     altset_idx, altno, num_channels, clock);
+	if (!fp)
+		return ERR_PTR(-ENOMEM);
+
+	fp->attributes = parse_uac_endpoint_attributes(chip, alts, protocol,
+						       iface_no);
+
+	/* some quirks for attributes here */
+	snd_usb_audioformat_attributes_quirk(chip, fp, stream);
+
+	/* ok, let's parse further... */
+	if (snd_usb_parse_audio_format(chip, fp, format,
+					fmt, stream) < 0) {
+		kfree(fp->rate_table);
+		kfree(fp);
+		return NULL;
+	}
+
+	/* Create chmap */
+	if (fp->channels != num_channels)
+		chconfig = 0;
+
+	fp->chmap = convert_chmap(fp->channels, chconfig, protocol);
+
+	return fp;
+}
+
+static struct audioformat *
+snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip,
+			     struct usb_host_interface *alts,
+			     int iface_no, int altset_idx,
+			     int altno, int stream)
+{
+	struct usb_device *dev = chip->dev;
+	struct uac3_input_terminal_descriptor *input_term;
+	struct uac3_output_terminal_descriptor *output_term;
+	struct uac3_cluster_header_descriptor *cluster;
+	struct uac3_as_header_descriptor *as = NULL;
+	struct uac3_hc_descriptor_header hc_header;
+	struct snd_pcm_chmap_elem *chmap;
+	unsigned char badd_profile;
+	u64 badd_formats = 0;
+	unsigned int num_channels;
+	struct audioformat *fp;
+	u16 cluster_id, wLength;
+	int clock = 0;
+	int err;
+
+	badd_profile = chip->badd_profile;
+
+	if (badd_profile >= UAC3_FUNCTION_SUBCLASS_GENERIC_IO) {
+		unsigned int maxpacksize =
+			le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
+
+		switch (maxpacksize) {
+		default:
+			dev_err(&dev->dev,
+				"%u:%d : incorrect wMaxPacketSize for BADD profile\n",
+				iface_no, altno);
+			return NULL;
+		case UAC3_BADD_EP_MAXPSIZE_SYNC_MONO_16:
+		case UAC3_BADD_EP_MAXPSIZE_ASYNC_MONO_16:
+			badd_formats = SNDRV_PCM_FMTBIT_S16_LE;
+			num_channels = 1;
+			break;
+		case UAC3_BADD_EP_MAXPSIZE_SYNC_MONO_24:
+		case UAC3_BADD_EP_MAXPSIZE_ASYNC_MONO_24:
+			badd_formats = SNDRV_PCM_FMTBIT_S24_3LE;
+			num_channels = 1;
+			break;
+		case UAC3_BADD_EP_MAXPSIZE_SYNC_STEREO_16:
+		case UAC3_BADD_EP_MAXPSIZE_ASYNC_STEREO_16:
+			badd_formats = SNDRV_PCM_FMTBIT_S16_LE;
+			num_channels = 2;
+			break;
+		case UAC3_BADD_EP_MAXPSIZE_SYNC_STEREO_24:
+		case UAC3_BADD_EP_MAXPSIZE_ASYNC_STEREO_24:
+			badd_formats = SNDRV_PCM_FMTBIT_S24_3LE;
+			num_channels = 2;
+			break;
+		}
+
+		chmap = kzalloc(sizeof(*chmap), GFP_KERNEL);
+		if (!chmap)
+			return ERR_PTR(-ENOMEM);
+
+		if (num_channels == 1) {
+			chmap->map[0] = SNDRV_CHMAP_MONO;
+		} else {
+			chmap->map[0] = SNDRV_CHMAP_FL;
+			chmap->map[1] = SNDRV_CHMAP_FR;
+		}
+
+		chmap->channels = num_channels;
+		clock = UAC3_BADD_CS_ID9;
+		goto found_clock;
+	}
+
+	as = snd_usb_find_csint_desc(alts->extra, alts->extralen,
+				     NULL, UAC_AS_GENERAL);
+	if (!as) {
+		dev_err(&dev->dev,
+			"%u:%d : UAC_AS_GENERAL descriptor not found\n",
+			iface_no, altno);
+		return NULL;
+	}
+
+	if (as->bLength < sizeof(*as)) {
+		dev_err(&dev->dev,
+			"%u:%d : invalid UAC_AS_GENERAL desc\n",
+			iface_no, altno);
+		return NULL;
+	}
+
+	cluster_id = le16_to_cpu(as->wClusterDescrID);
+	if (!cluster_id) {
+		dev_err(&dev->dev,
+			"%u:%d : no cluster descriptor\n",
+			iface_no, altno);
+		return NULL;
+	}
+
+	/*
+	 * Get number of channels and channel map through
+	 * High Capability Cluster Descriptor
+	 *
+	 * First step: get High Capability header and
+	 * read size of Cluster Descriptor
+	 */
+	err = snd_usb_ctl_msg(chip->dev,
+			usb_rcvctrlpipe(chip->dev, 0),
+			UAC3_CS_REQ_HIGH_CAPABILITY_DESCRIPTOR,
+			USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
+			cluster_id,
+			snd_usb_ctrl_intf(chip),
+			&hc_header, sizeof(hc_header));
+	if (err < 0)
+		return ERR_PTR(err);
+	else if (err != sizeof(hc_header)) {
+		dev_err(&dev->dev,
+			"%u:%d : can't get High Capability descriptor\n",
+			iface_no, altno);
+		return ERR_PTR(-EIO);
+	}
+
+	/*
+	 * Second step: allocate needed amount of memory
+	 * and request Cluster Descriptor
+	 */
+	wLength = le16_to_cpu(hc_header.wLength);
+	cluster = kzalloc(wLength, GFP_KERNEL);
+	if (!cluster)
+		return ERR_PTR(-ENOMEM);
+	err = snd_usb_ctl_msg(chip->dev,
+			usb_rcvctrlpipe(chip->dev, 0),
+			UAC3_CS_REQ_HIGH_CAPABILITY_DESCRIPTOR,
+			USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
+			cluster_id,
+			snd_usb_ctrl_intf(chip),
+			cluster, wLength);
+	if (err < 0) {
+		kfree(cluster);
+		return ERR_PTR(err);
+	} else if (err != wLength) {
+		dev_err(&dev->dev,
+			"%u:%d : can't get Cluster Descriptor\n",
+			iface_no, altno);
+		kfree(cluster);
+		return ERR_PTR(-EIO);
+	}
+
+	num_channels = cluster->bNrChannels;
+	chmap = convert_chmap_v3(cluster);
+	kfree(cluster);
+
+	/*
+	 * lookup the terminal associated to this interface
+	 * to extract the clock
+	 */
+	input_term = snd_usb_find_input_terminal_descriptor(chip->ctrl_intf,
+							    as->bTerminalLink);
+	if (input_term) {
+		clock = input_term->bCSourceID;
+		goto found_clock;
+	}
+
+	output_term = snd_usb_find_output_terminal_descriptor(chip->ctrl_intf,
+							     as->bTerminalLink);
+	if (output_term) {
+		clock = output_term->bCSourceID;
+		goto found_clock;
+	}
+
+	dev_err(&dev->dev, "%u:%d : bogus bTerminalLink %d\n",
+			iface_no, altno, as->bTerminalLink);
+	kfree(chmap);
+	return NULL;
+
+found_clock:
+	fp = audio_format_alloc_init(chip, alts, UAC_VERSION_3, iface_no,
+				     altset_idx, altno, num_channels, clock);
+	if (!fp) {
+		kfree(chmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	fp->chmap = chmap;
+
+	if (badd_profile >= UAC3_FUNCTION_SUBCLASS_GENERIC_IO) {
+		fp->attributes = 0; /* No attributes */
+
+		fp->fmt_type = UAC_FORMAT_TYPE_I;
+		fp->formats = badd_formats;
+
+		fp->nr_rates = 0;	/* SNDRV_PCM_RATE_CONTINUOUS */
+		fp->rate_min = UAC3_BADD_SAMPLING_RATE;
+		fp->rate_max = UAC3_BADD_SAMPLING_RATE;
+		fp->rates = SNDRV_PCM_RATE_CONTINUOUS;
+
+	} else {
+		fp->attributes = parse_uac_endpoint_attributes(chip, alts,
+							       UAC_VERSION_3,
+							       iface_no);
+		/* ok, let's parse further... */
+		if (snd_usb_parse_audio_format_v3(chip, fp, as, stream) < 0) {
+			kfree(fp->chmap);
+			kfree(fp->rate_table);
+			kfree(fp);
+			return NULL;
+		}
+	}
+
+	return fp;
+}
+
 int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 {
 	struct usb_device *dev;
@@ -633,13 +1031,8 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 	struct usb_host_interface *alts;
 	struct usb_interface_descriptor *altsd;
 	int i, altno, err, stream;
-	u64 format = 0;
-	unsigned int num_channels = 0;
 	struct audioformat *fp = NULL;
-	int num, protocol, clock = 0;
-	struct uac_format_type_i_continuous_descriptor *fmt = NULL;
-	struct snd_pcm_chmap_elem *chmap_v3 = NULL;
-	unsigned int chconfig;
+	int num, protocol;
 
 	dev = chip->dev;
 
@@ -688,303 +1081,48 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 		    protocol <= 2)
 			protocol = UAC_VERSION_1;
 
-		chconfig = 0;
-		/* get audio formats */
 		switch (protocol) {
 		default:
 			dev_dbg(&dev->dev, "%u:%d: unknown interface protocol %#02x, assuming v1\n",
 				iface_no, altno, protocol);
 			protocol = UAC_VERSION_1;
 			/* fall through */
-
-		case UAC_VERSION_1: {
-			struct uac1_as_header_descriptor *as =
-				snd_usb_find_csint_desc(alts->extra, alts->extralen, NULL, UAC_AS_GENERAL);
-			struct uac_input_terminal_descriptor *iterm;
-
-			if (!as) {
-				dev_err(&dev->dev,
-					"%u:%d : UAC_AS_GENERAL descriptor not found\n",
-					iface_no, altno);
-				continue;
-			}
-
-			if (as->bLength < sizeof(*as)) {
-				dev_err(&dev->dev,
-					"%u:%d : invalid UAC_AS_GENERAL desc\n",
-					iface_no, altno);
-				continue;
-			}
-
-			format = le16_to_cpu(as->wFormatTag); /* remember the format value */
-
-			iterm = snd_usb_find_input_terminal_descriptor(chip->ctrl_intf,
-								       as->bTerminalLink);
-			if (iterm) {
-				num_channels = iterm->bNrChannels;
-				chconfig = le16_to_cpu(iterm->wChannelConfig);
-			}
-
-			break;
-		}
-
+		case UAC_VERSION_1:
+			/* fall through */
 		case UAC_VERSION_2: {
-			struct uac2_input_terminal_descriptor *input_term;
-			struct uac2_output_terminal_descriptor *output_term;
-			struct uac2_as_header_descriptor *as =
-				snd_usb_find_csint_desc(alts->extra, alts->extralen, NULL, UAC_AS_GENERAL);
-
-			if (!as) {
-				dev_err(&dev->dev,
-					"%u:%d : UAC_AS_GENERAL descriptor not found\n",
-					iface_no, altno);
-				continue;
-			}
-
-			if (as->bLength < sizeof(*as)) {
-				dev_err(&dev->dev,
-					"%u:%d : invalid UAC_AS_GENERAL desc\n",
-					iface_no, altno);
-				continue;
-			}
-
-			num_channels = as->bNrChannels;
-			format = le32_to_cpu(as->bmFormats);
-			chconfig = le32_to_cpu(as->bmChannelConfig);
-
-			/* lookup the terminal associated to this interface
-			 * to extract the clock */
-			input_term = snd_usb_find_input_terminal_descriptor(chip->ctrl_intf,
-									    as->bTerminalLink);
-			if (input_term) {
-				clock = input_term->bCSourceID;
-				if (!chconfig && (num_channels == input_term->bNrChannels))
-					chconfig = le32_to_cpu(input_term->bmChannelConfig);
-				break;
-			}
-
-			output_term = snd_usb_find_output_terminal_descriptor(chip->ctrl_intf,
-									      as->bTerminalLink);
-			if (output_term) {
-				clock = output_term->bCSourceID;
-				break;
-			}
-
-			dev_err(&dev->dev,
-				"%u:%d : bogus bTerminalLink %d\n",
-				iface_no, altno, as->bTerminalLink);
-			continue;
-		}
-
-		case UAC_VERSION_3: {
-			struct uac3_input_terminal_descriptor *input_term;
-			struct uac3_output_terminal_descriptor *output_term;
-			struct uac3_as_header_descriptor *as;
-			struct uac3_cluster_header_descriptor *cluster;
-			struct uac3_hc_descriptor_header hc_header;
-			u16 cluster_id, wLength;
-
-			as = snd_usb_find_csint_desc(alts->extra,
-							alts->extralen,
-							NULL, UAC_AS_GENERAL);
-
-			if (!as) {
-				dev_err(&dev->dev,
-					"%u:%d : UAC_AS_GENERAL descriptor not found\n",
-					iface_no, altno);
-				continue;
-			}
-
-			if (as->bLength < sizeof(*as)) {
-				dev_err(&dev->dev,
-					"%u:%d : invalid UAC_AS_GENERAL desc\n",
-					iface_no, altno);
-				continue;
-			}
-
-			cluster_id = le16_to_cpu(as->wClusterDescrID);
-			if (!cluster_id) {
-				dev_err(&dev->dev,
-					"%u:%d : no cluster descriptor\n",
-					iface_no, altno);
-				continue;
-			}
-
-			/*
-			 * Get number of channels and channel map through
-			 * High Capability Cluster Descriptor
-			 *
-			 * First step: get High Capability header and
-			 * read size of Cluster Descriptor
-			 */
-			err = snd_usb_ctl_msg(chip->dev,
-					usb_rcvctrlpipe(chip->dev, 0),
-					UAC3_CS_REQ_HIGH_CAPABILITY_DESCRIPTOR,
-					USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
-					cluster_id,
-					snd_usb_ctrl_intf(chip),
-					&hc_header, sizeof(hc_header));
-			if (err < 0)
-				return err;
-			else if (err != sizeof(hc_header)) {
-				dev_err(&dev->dev,
-					"%u:%d : can't get High Capability descriptor\n",
-					iface_no, altno);
-				return -EIO;
-			}
-
-			/*
-			 * Second step: allocate needed amount of memory
-			 * and request Cluster Descriptor
-			 */
-			wLength = le16_to_cpu(hc_header.wLength);
-			cluster = kzalloc(wLength, GFP_KERNEL);
-			if (!cluster)
-				return -ENOMEM;
-			err = snd_usb_ctl_msg(chip->dev,
-					usb_rcvctrlpipe(chip->dev, 0),
-					UAC3_CS_REQ_HIGH_CAPABILITY_DESCRIPTOR,
-					USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
-					cluster_id,
-					snd_usb_ctrl_intf(chip),
-					cluster, wLength);
-			if (err < 0) {
-				kfree(cluster);
-				return err;
-			} else if (err != wLength) {
-				dev_err(&dev->dev,
-					"%u:%d : can't get Cluster Descriptor\n",
-					iface_no, altno);
-				kfree(cluster);
-				return -EIO;
-			}
-
-			num_channels = cluster->bNrChannels;
-			chmap_v3 = convert_chmap_v3(cluster);
-
-			kfree(cluster);
-
-			format = le64_to_cpu(as->bmFormats);
-
-			/* lookup the terminal associated to this interface
-			 * to extract the clock */
-			input_term = snd_usb_find_input_terminal_descriptor(
-							chip->ctrl_intf,
-							as->bTerminalLink);
-
-			if (input_term) {
-				clock = input_term->bCSourceID;
-				break;
-			}
-
-			output_term = snd_usb_find_output_terminal_descriptor(chip->ctrl_intf,
-									      as->bTerminalLink);
-			if (output_term) {
-				clock = output_term->bCSourceID;
-				break;
-			}
-
-			dev_err(&dev->dev,
-				"%u:%d : bogus bTerminalLink %d\n",
-				iface_no, altno, as->bTerminalLink);
-			continue;
-		}
-		}
-
-		if (protocol == UAC_VERSION_1 || protocol == UAC_VERSION_2) {
-			/* get format type */
-			fmt = snd_usb_find_csint_desc(alts->extra,
-						      alts->extralen,
-						      NULL, UAC_FORMAT_TYPE);
-			if (!fmt) {
-				dev_err(&dev->dev,
-					"%u:%d : no UAC_FORMAT_TYPE desc\n",
-					iface_no, altno);
-				continue;
-			}
-			if (((protocol == UAC_VERSION_1) && (fmt->bLength < 8))
-					|| ((protocol == UAC_VERSION_2) &&
-							(fmt->bLength < 6))) {
-				dev_err(&dev->dev,
-					"%u:%d : invalid UAC_FORMAT_TYPE desc\n",
-					iface_no, altno);
-				continue;
-			}
+			int bm_quirk = 0;
 
 			/*
 			 * Blue Microphones workaround: The last altsetting is
 			 * identical with the previous one, except for a larger
 			 * packet size, but is actually a mislabeled two-channel
 			 * setting; ignore it.
+			 *
+			 * Part 1: prepare quirk flag
 			 */
-			if (fmt->bNrChannels == 1 &&
-			    fmt->bSubframeSize == 2 &&
-			    altno == 2 && num == 3 &&
+			if (altno == 2 && num == 3 &&
 			    fp && fp->altsetting == 1 && fp->channels == 1 &&
 			    fp->formats == SNDRV_PCM_FMTBIT_S16_LE &&
 			    protocol == UAC_VERSION_1 &&
 			    le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize) ==
 							fp->maxpacksize * 2)
-				continue;
-		}
-
-		fp = kzalloc(sizeof(*fp), GFP_KERNEL);
-		if (!fp)
-			return -ENOMEM;
+				bm_quirk = 1;
 
-		fp->iface = iface_no;
-		fp->altsetting = altno;
-		fp->altset_idx = i;
-		fp->endpoint = get_endpoint(alts, 0)->bEndpointAddress;
-		fp->ep_attr = get_endpoint(alts, 0)->bmAttributes;
-		fp->datainterval = snd_usb_parse_datainterval(chip, alts);
-		fp->protocol = protocol;
-		fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
-		fp->channels = num_channels;
-		if (snd_usb_get_speed(dev) == USB_SPEED_HIGH)
-			fp->maxpacksize = (((fp->maxpacksize >> 11) & 3) + 1)
-					* (fp->maxpacksize & 0x7ff);
-		fp->attributes = parse_uac_endpoint_attributes(chip, alts, protocol, iface_no);
-		fp->clock = clock;
-		INIT_LIST_HEAD(&fp->list);
-
-		/* some quirks for attributes here */
-		snd_usb_audioformat_attributes_quirk(chip, fp, stream);
-
-		/* ok, let's parse further... */
-		if (protocol == UAC_VERSION_1 || protocol == UAC_VERSION_2) {
-			if (snd_usb_parse_audio_format(chip, fp, format,
-							fmt, stream) < 0) {
-				kfree(fp->rate_table);
-				kfree(fp);
-				fp = NULL;
-				continue;
-			}
-		} else {
-			struct uac3_as_header_descriptor *as;
-
-			as = snd_usb_find_csint_desc(alts->extra,
-						     alts->extralen,
-						     NULL, UAC_AS_GENERAL);
-
-			if (snd_usb_parse_audio_format_v3(chip, fp, as,
-								stream) < 0) {
-				kfree(fp->rate_table);
-				kfree(fp);
-				fp = NULL;
-				continue;
-			}
+			fp = snd_usb_get_audioformat_uac12(chip, alts, protocol,
+							   iface_no, i, altno,
+							   stream, bm_quirk);
+			break;
+		}
+		case UAC_VERSION_3:
+			fp = snd_usb_get_audioformat_uac3(chip, alts,
+						iface_no, i, altno, stream);
+			break;
 		}
 
-		/* Create chmap */
-		if (fp->channels != num_channels)
-			chconfig = 0;
-
-		if (protocol == UAC_VERSION_3)
-			fp->chmap = chmap_v3;
-		else
-			fp->chmap = convert_chmap(fp->channels, chconfig,
-						  protocol);
+		if (!fp)
+			continue;
+		else if (IS_ERR(fp))
+			return PTR_ERR(fp);
 
 		dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint);
 		err = snd_usb_add_audio_stream(chip, stream, fp);
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 4d5c89a7ba2b..b9faeca645fd 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -49,6 +49,8 @@ struct snd_usb_audio {
 	int num_suspended_intf;
 	int sample_rate_read_error;
 
+	int badd_profile;		/* UAC3 BADD profile */
+
 	struct list_head pcm_list;	/* list of pcm streams */
 	struct list_head ep_list;	/* list of audio-related endpoints */
 	int pcm_devs;
@@ -59,6 +61,9 @@ struct snd_usb_audio {
 
 	int setup;			/* from the 'device_setup' module param */
 	bool autoclock;			/* from the 'autoclock' module param */
+	bool keep_iface;		/* keep interface/altset after closing
+					 * or parameter change
+					 */
 
 	struct usb_host_interface *ctrl_intf;	/* the audio control interface */
 };
@@ -109,6 +114,7 @@ enum quirk_type {
 struct snd_usb_audio_quirk {
 	const char *vendor_name;
 	const char *product_name;
+	const char *profile_name;	/* override the card->longname */
 	int16_t ifnum;
 	uint16_t type;
 	const void *data;
@@ -121,4 +127,6 @@ struct snd_usb_audio_quirk {
 int snd_usb_lock_shutdown(struct snd_usb_audio *chip);
 void snd_usb_unlock_shutdown(struct snd_usb_audio *chip);
 
+extern bool snd_usb_use_vmalloc;
+
 #endif /* __USBAUDIO_H */
diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c
index ebcab5c5465d..8082f7b077f1 100644
--- a/sound/usb/usx2y/us122l.c
+++ b/sound/usb/usx2y/us122l.c
@@ -139,7 +139,7 @@ static void usb_stream_hwdep_vm_open(struct vm_area_struct *area)
 	snd_printdd(KERN_DEBUG "%i\n", atomic_read(&us122l->mmap_count));
 }
 
-static int usb_stream_hwdep_vm_fault(struct vm_fault *vmf)
+static vm_fault_t usb_stream_hwdep_vm_fault(struct vm_fault *vmf)
 {
 	unsigned long offset;
 	struct page *page;
diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c
index d8bd7c99b48c..c1dd9a7b48df 100644
--- a/sound/usb/usx2y/usX2Yhwdep.c
+++ b/sound/usb/usx2y/usX2Yhwdep.c
@@ -31,7 +31,7 @@
 #include "usbusx2y.h"
 #include "usX2Yhwdep.h"
 
-static int snd_us428ctls_vm_fault(struct vm_fault *vmf)
+static vm_fault_t snd_us428ctls_vm_fault(struct vm_fault *vmf)
 {
 	unsigned long offset;
 	struct page * page;
diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c
index 0d050528a4e1..4fd9276b8e50 100644
--- a/sound/usb/usx2y/usx2yhwdeppcm.c
+++ b/sound/usb/usx2y/usx2yhwdeppcm.c
@@ -652,7 +652,7 @@ static void snd_usX2Y_hwdep_pcm_vm_close(struct vm_area_struct *area)
 }
 
 
-static int snd_usX2Y_hwdep_pcm_vm_fault(struct vm_fault *vmf)
+static vm_fault_t snd_usX2Y_hwdep_pcm_vm_fault(struct vm_fault *vmf)
 {
 	unsigned long offset;
 	void *vaddr;
diff --git a/sound/xen/Kconfig b/sound/xen/Kconfig
new file mode 100644
index 000000000000..4f1fceea82d2
--- /dev/null
+++ b/sound/xen/Kconfig
@@ -0,0 +1,10 @@
+# ALSA Xen drivers
+
+config SND_XEN_FRONTEND
+	tristate "Xen para-virtualized sound frontend driver"
+	depends on XEN
+	select SND_PCM
+	select XEN_XENBUS_FRONTEND
+	help
+	  Choose this option if you want to enable a para-virtualized
+	  frontend sound driver for Xen guest OSes.
diff --git a/sound/xen/Makefile b/sound/xen/Makefile
new file mode 100644
index 000000000000..1e6470ecc2f2
--- /dev/null
+++ b/sound/xen/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0 OR MIT
+
+snd_xen_front-objs := xen_snd_front.o \
+		      xen_snd_front_cfg.o \
+		      xen_snd_front_evtchnl.o \
+		      xen_snd_front_shbuf.o \
+		      xen_snd_front_alsa.o
+
+obj-$(CONFIG_SND_XEN_FRONTEND) += snd_xen_front.o
diff --git a/sound/xen/xen_snd_front.c b/sound/xen/xen_snd_front.c
new file mode 100644
index 000000000000..b089b13b5160
--- /dev/null
+++ b/sound/xen/xen_snd_front.c
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/module.h>
+
+#include <xen/page.h>
+#include <xen/platform_pci.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+
+#include <xen/interface/io/sndif.h>
+
+#include "xen_snd_front.h"
+#include "xen_snd_front_alsa.h"
+#include "xen_snd_front_evtchnl.h"
+#include "xen_snd_front_shbuf.h"
+
+static struct xensnd_req *
+be_stream_prepare_req(struct xen_snd_front_evtchnl *evtchnl, u8 operation)
+{
+	struct xensnd_req *req;
+
+	req = RING_GET_REQUEST(&evtchnl->u.req.ring,
+			       evtchnl->u.req.ring.req_prod_pvt);
+	req->operation = operation;
+	req->id = evtchnl->evt_next_id++;
+	evtchnl->evt_id = req->id;
+	return req;
+}
+
+static int be_stream_do_io(struct xen_snd_front_evtchnl *evtchnl)
+{
+	if (unlikely(evtchnl->state != EVTCHNL_STATE_CONNECTED))
+		return -EIO;
+
+	reinit_completion(&evtchnl->u.req.completion);
+	xen_snd_front_evtchnl_flush(evtchnl);
+	return 0;
+}
+
+static int be_stream_wait_io(struct xen_snd_front_evtchnl *evtchnl)
+{
+	if (wait_for_completion_timeout(&evtchnl->u.req.completion,
+			msecs_to_jiffies(VSND_WAIT_BACK_MS)) <= 0)
+		return -ETIMEDOUT;
+
+	return evtchnl->u.req.resp_status;
+}
+
+int xen_snd_front_stream_query_hw_param(struct xen_snd_front_evtchnl *evtchnl,
+					struct xensnd_query_hw_param *hw_param_req,
+					struct xensnd_query_hw_param *hw_param_resp)
+{
+	struct xensnd_req *req;
+	int ret;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	mutex_lock(&evtchnl->ring_io_lock);
+	req = be_stream_prepare_req(evtchnl, XENSND_OP_HW_PARAM_QUERY);
+	req->op.hw_param = *hw_param_req;
+	mutex_unlock(&evtchnl->ring_io_lock);
+
+	ret = be_stream_do_io(evtchnl);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	if (ret == 0)
+		*hw_param_resp = evtchnl->u.req.resp.hw_param;
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_snd_front_stream_prepare(struct xen_snd_front_evtchnl *evtchnl,
+				 struct xen_snd_front_shbuf *sh_buf,
+				 u8 format, unsigned int channels,
+				 unsigned int rate, u32 buffer_sz,
+				 u32 period_sz)
+{
+	struct xensnd_req *req;
+	int ret;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	mutex_lock(&evtchnl->ring_io_lock);
+	req = be_stream_prepare_req(evtchnl, XENSND_OP_OPEN);
+	req->op.open.pcm_format = format;
+	req->op.open.pcm_channels = channels;
+	req->op.open.pcm_rate = rate;
+	req->op.open.buffer_sz = buffer_sz;
+	req->op.open.period_sz = period_sz;
+	req->op.open.gref_directory = xen_snd_front_shbuf_get_dir_start(sh_buf);
+	mutex_unlock(&evtchnl->ring_io_lock);
+
+	ret = be_stream_do_io(evtchnl);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_snd_front_stream_close(struct xen_snd_front_evtchnl *evtchnl)
+{
+	struct xensnd_req *req;
+	int ret;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	mutex_lock(&evtchnl->ring_io_lock);
+	req = be_stream_prepare_req(evtchnl, XENSND_OP_CLOSE);
+	mutex_unlock(&evtchnl->ring_io_lock);
+
+	ret = be_stream_do_io(evtchnl);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_snd_front_stream_write(struct xen_snd_front_evtchnl *evtchnl,
+			       unsigned long pos, unsigned long count)
+{
+	struct xensnd_req *req;
+	int ret;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	mutex_lock(&evtchnl->ring_io_lock);
+	req = be_stream_prepare_req(evtchnl, XENSND_OP_WRITE);
+	req->op.rw.length = count;
+	req->op.rw.offset = pos;
+	mutex_unlock(&evtchnl->ring_io_lock);
+
+	ret = be_stream_do_io(evtchnl);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_snd_front_stream_read(struct xen_snd_front_evtchnl *evtchnl,
+			      unsigned long pos, unsigned long count)
+{
+	struct xensnd_req *req;
+	int ret;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	mutex_lock(&evtchnl->ring_io_lock);
+	req = be_stream_prepare_req(evtchnl, XENSND_OP_READ);
+	req->op.rw.length = count;
+	req->op.rw.offset = pos;
+	mutex_unlock(&evtchnl->ring_io_lock);
+
+	ret = be_stream_do_io(evtchnl);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+int xen_snd_front_stream_trigger(struct xen_snd_front_evtchnl *evtchnl,
+				 int type)
+{
+	struct xensnd_req *req;
+	int ret;
+
+	mutex_lock(&evtchnl->u.req.req_io_lock);
+
+	mutex_lock(&evtchnl->ring_io_lock);
+	req = be_stream_prepare_req(evtchnl, XENSND_OP_TRIGGER);
+	req->op.trigger.type = type;
+	mutex_unlock(&evtchnl->ring_io_lock);
+
+	ret = be_stream_do_io(evtchnl);
+
+	if (ret == 0)
+		ret = be_stream_wait_io(evtchnl);
+
+	mutex_unlock(&evtchnl->u.req.req_io_lock);
+	return ret;
+}
+
+static void xen_snd_drv_fini(struct xen_snd_front_info *front_info)
+{
+	xen_snd_front_alsa_fini(front_info);
+	xen_snd_front_evtchnl_free_all(front_info);
+}
+
+static int sndback_initwait(struct xen_snd_front_info *front_info)
+{
+	int num_streams;
+	int ret;
+
+	ret = xen_snd_front_cfg_card(front_info, &num_streams);
+	if (ret < 0)
+		return ret;
+
+	/* create event channels for all streams and publish */
+	ret = xen_snd_front_evtchnl_create_all(front_info, num_streams);
+	if (ret < 0)
+		return ret;
+
+	return xen_snd_front_evtchnl_publish_all(front_info);
+}
+
+static int sndback_connect(struct xen_snd_front_info *front_info)
+{
+	return xen_snd_front_alsa_init(front_info);
+}
+
+static void sndback_disconnect(struct xen_snd_front_info *front_info)
+{
+	xen_snd_drv_fini(front_info);
+	xenbus_switch_state(front_info->xb_dev, XenbusStateInitialising);
+}
+
+static void sndback_changed(struct xenbus_device *xb_dev,
+			    enum xenbus_state backend_state)
+{
+	struct xen_snd_front_info *front_info = dev_get_drvdata(&xb_dev->dev);
+	int ret;
+
+	dev_dbg(&xb_dev->dev, "Backend state is %s, front is %s\n",
+		xenbus_strstate(backend_state),
+		xenbus_strstate(xb_dev->state));
+
+	switch (backend_state) {
+	case XenbusStateReconfiguring:
+		/* fall through */
+	case XenbusStateReconfigured:
+		/* fall through */
+	case XenbusStateInitialised:
+		/* fall through */
+		break;
+
+	case XenbusStateInitialising:
+		/* Recovering after backend unexpected closure. */
+		sndback_disconnect(front_info);
+		break;
+
+	case XenbusStateInitWait:
+		/* Recovering after backend unexpected closure. */
+		sndback_disconnect(front_info);
+
+		ret = sndback_initwait(front_info);
+		if (ret < 0)
+			xenbus_dev_fatal(xb_dev, ret, "initializing frontend");
+		else
+			xenbus_switch_state(xb_dev, XenbusStateInitialised);
+		break;
+
+	case XenbusStateConnected:
+		if (xb_dev->state != XenbusStateInitialised)
+			break;
+
+		ret = sndback_connect(front_info);
+		if (ret < 0)
+			xenbus_dev_fatal(xb_dev, ret, "initializing frontend");
+		else
+			xenbus_switch_state(xb_dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosing:
+		/*
+		 * In this state backend starts freeing resources,
+		 * so let it go into closed state first, so we can also
+		 * remove ours.
+		 */
+		break;
+
+	case XenbusStateUnknown:
+		/* fall through */
+	case XenbusStateClosed:
+		if (xb_dev->state == XenbusStateClosed)
+			break;
+
+		sndback_disconnect(front_info);
+		break;
+	}
+}
+
+static int xen_drv_probe(struct xenbus_device *xb_dev,
+			 const struct xenbus_device_id *id)
+{
+	struct xen_snd_front_info *front_info;
+
+	front_info = devm_kzalloc(&xb_dev->dev,
+				  sizeof(*front_info), GFP_KERNEL);
+	if (!front_info)
+		return -ENOMEM;
+
+	front_info->xb_dev = xb_dev;
+	dev_set_drvdata(&xb_dev->dev, front_info);
+
+	return xenbus_switch_state(xb_dev, XenbusStateInitialising);
+}
+
+static int xen_drv_remove(struct xenbus_device *dev)
+{
+	struct xen_snd_front_info *front_info = dev_get_drvdata(&dev->dev);
+	int to = 100;
+
+	xenbus_switch_state(dev, XenbusStateClosing);
+
+	/*
+	 * On driver removal it is disconnected from XenBus,
+	 * so no backend state change events come via .otherend_changed
+	 * callback. This prevents us from exiting gracefully, e.g.
+	 * signaling the backend to free event channels, waiting for its
+	 * state to change to XenbusStateClosed and cleaning at our end.
+	 * Normally when front driver removed backend will finally go into
+	 * XenbusStateInitWait state.
+	 *
+	 * Workaround: read backend's state manually and wait with time-out.
+	 */
+	while ((xenbus_read_unsigned(front_info->xb_dev->otherend, "state",
+				     XenbusStateUnknown) != XenbusStateInitWait) &&
+	       --to)
+		msleep(10);
+
+	if (!to) {
+		unsigned int state;
+
+		state = xenbus_read_unsigned(front_info->xb_dev->otherend,
+					     "state", XenbusStateUnknown);
+		pr_err("Backend state is %s while removing driver\n",
+		       xenbus_strstate(state));
+	}
+
+	xen_snd_drv_fini(front_info);
+	xenbus_frontend_closed(dev);
+	return 0;
+}
+
+static const struct xenbus_device_id xen_drv_ids[] = {
+	{ XENSND_DRIVER_NAME },
+	{ "" }
+};
+
+static struct xenbus_driver xen_driver = {
+	.ids = xen_drv_ids,
+	.probe = xen_drv_probe,
+	.remove = xen_drv_remove,
+	.otherend_changed = sndback_changed,
+};
+
+static int __init xen_drv_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
+	/* At the moment we only support case with XEN_PAGE_SIZE == PAGE_SIZE */
+	if (XEN_PAGE_SIZE != PAGE_SIZE) {
+		pr_err(XENSND_DRIVER_NAME ": different kernel and Xen page sizes are not supported: XEN_PAGE_SIZE (%lu) != PAGE_SIZE (%lu)\n",
+		       XEN_PAGE_SIZE, PAGE_SIZE);
+		return -ENODEV;
+	}
+
+	pr_info("Initialising Xen " XENSND_DRIVER_NAME " frontend driver\n");
+	return xenbus_register_frontend(&xen_driver);
+}
+
+static void __exit xen_drv_fini(void)
+{
+	pr_info("Unregistering Xen " XENSND_DRIVER_NAME " frontend driver\n");
+	xenbus_unregister_driver(&xen_driver);
+}
+
+module_init(xen_drv_init);
+module_exit(xen_drv_fini);
+
+MODULE_DESCRIPTION("Xen virtual sound device frontend");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:" XENSND_DRIVER_NAME);
+MODULE_SUPPORTED_DEVICE("{{ALSA,Virtual soundcard}}");
diff --git a/sound/xen/xen_snd_front.h b/sound/xen/xen_snd_front.h
new file mode 100644
index 000000000000..a2ea2463bcc5
--- /dev/null
+++ b/sound/xen/xen_snd_front.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_SND_FRONT_H
+#define __XEN_SND_FRONT_H
+
+#include "xen_snd_front_cfg.h"
+
+struct xen_snd_front_card_info;
+struct xen_snd_front_evtchnl;
+struct xen_snd_front_evtchnl_pair;
+struct xen_snd_front_shbuf;
+struct xensnd_query_hw_param;
+
+struct xen_snd_front_info {
+	struct xenbus_device *xb_dev;
+
+	struct xen_snd_front_card_info *card_info;
+
+	int num_evt_pairs;
+	struct xen_snd_front_evtchnl_pair *evt_pairs;
+
+	struct xen_front_cfg_card cfg;
+};
+
+int xen_snd_front_stream_query_hw_param(struct xen_snd_front_evtchnl *evtchnl,
+					struct xensnd_query_hw_param *hw_param_req,
+					struct xensnd_query_hw_param *hw_param_resp);
+
+int xen_snd_front_stream_prepare(struct xen_snd_front_evtchnl *evtchnl,
+				 struct xen_snd_front_shbuf *sh_buf,
+				 u8 format, unsigned int channels,
+				 unsigned int rate, u32 buffer_sz,
+				 u32 period_sz);
+
+int xen_snd_front_stream_close(struct xen_snd_front_evtchnl *evtchnl);
+
+int xen_snd_front_stream_write(struct xen_snd_front_evtchnl *evtchnl,
+			       unsigned long pos, unsigned long count);
+
+int xen_snd_front_stream_read(struct xen_snd_front_evtchnl *evtchnl,
+			      unsigned long pos, unsigned long count);
+
+int xen_snd_front_stream_trigger(struct xen_snd_front_evtchnl *evtchnl,
+				 int type);
+
+#endif /* __XEN_SND_FRONT_H */
diff --git a/sound/xen/xen_snd_front_alsa.c b/sound/xen/xen_snd_front_alsa.c
new file mode 100644
index 000000000000..5a2bd70a2fa1
--- /dev/null
+++ b/sound/xen/xen_snd_front_alsa.c
@@ -0,0 +1,822 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <linux/platform_device.h>
+
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+
+#include <xen/xenbus.h>
+
+#include "xen_snd_front.h"
+#include "xen_snd_front_alsa.h"
+#include "xen_snd_front_cfg.h"
+#include "xen_snd_front_evtchnl.h"
+#include "xen_snd_front_shbuf.h"
+
+struct xen_snd_front_pcm_stream_info {
+	struct xen_snd_front_info *front_info;
+	struct xen_snd_front_evtchnl_pair *evt_pair;
+	struct xen_snd_front_shbuf sh_buf;
+	int index;
+
+	bool is_open;
+	struct snd_pcm_hardware pcm_hw;
+
+	/* Number of processed frames as reported by the backend. */
+	snd_pcm_uframes_t be_cur_frame;
+	/* Current HW pointer to be reported via .period callback. */
+	atomic_t hw_ptr;
+	/* Modulo of the number of processed frames - for period detection. */
+	u32 out_frames;
+};
+
+struct xen_snd_front_pcm_instance_info {
+	struct xen_snd_front_card_info *card_info;
+	struct snd_pcm *pcm;
+	struct snd_pcm_hardware pcm_hw;
+	int num_pcm_streams_pb;
+	struct xen_snd_front_pcm_stream_info *streams_pb;
+	int num_pcm_streams_cap;
+	struct xen_snd_front_pcm_stream_info *streams_cap;
+};
+
+struct xen_snd_front_card_info {
+	struct xen_snd_front_info *front_info;
+	struct snd_card *card;
+	struct snd_pcm_hardware pcm_hw;
+	int num_pcm_instances;
+	struct xen_snd_front_pcm_instance_info *pcm_instances;
+};
+
+struct alsa_sndif_sample_format {
+	u8 sndif;
+	snd_pcm_format_t alsa;
+};
+
+struct alsa_sndif_hw_param {
+	u8 sndif;
+	snd_pcm_hw_param_t alsa;
+};
+
+static const struct alsa_sndif_sample_format ALSA_SNDIF_FORMATS[] = {
+	{
+		.sndif = XENSND_PCM_FORMAT_U8,
+		.alsa = SNDRV_PCM_FORMAT_U8
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_S8,
+		.alsa = SNDRV_PCM_FORMAT_S8
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_U16_LE,
+		.alsa = SNDRV_PCM_FORMAT_U16_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_U16_BE,
+		.alsa = SNDRV_PCM_FORMAT_U16_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_S16_LE,
+		.alsa = SNDRV_PCM_FORMAT_S16_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_S16_BE,
+		.alsa = SNDRV_PCM_FORMAT_S16_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_U24_LE,
+		.alsa = SNDRV_PCM_FORMAT_U24_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_U24_BE,
+		.alsa = SNDRV_PCM_FORMAT_U24_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_S24_LE,
+		.alsa = SNDRV_PCM_FORMAT_S24_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_S24_BE,
+		.alsa = SNDRV_PCM_FORMAT_S24_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_U32_LE,
+		.alsa = SNDRV_PCM_FORMAT_U32_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_U32_BE,
+		.alsa = SNDRV_PCM_FORMAT_U32_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_S32_LE,
+		.alsa = SNDRV_PCM_FORMAT_S32_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_S32_BE,
+		.alsa = SNDRV_PCM_FORMAT_S32_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_A_LAW,
+		.alsa = SNDRV_PCM_FORMAT_A_LAW
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_MU_LAW,
+		.alsa = SNDRV_PCM_FORMAT_MU_LAW
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_F32_LE,
+		.alsa = SNDRV_PCM_FORMAT_FLOAT_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_F32_BE,
+		.alsa = SNDRV_PCM_FORMAT_FLOAT_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_F64_LE,
+		.alsa = SNDRV_PCM_FORMAT_FLOAT64_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_F64_BE,
+		.alsa = SNDRV_PCM_FORMAT_FLOAT64_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_IEC958_SUBFRAME_LE,
+		.alsa = SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_IEC958_SUBFRAME_BE,
+		.alsa = SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_IMA_ADPCM,
+		.alsa = SNDRV_PCM_FORMAT_IMA_ADPCM
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_MPEG,
+		.alsa = SNDRV_PCM_FORMAT_MPEG
+	},
+	{
+		.sndif = XENSND_PCM_FORMAT_GSM,
+		.alsa = SNDRV_PCM_FORMAT_GSM
+	},
+};
+
+static int to_sndif_format(snd_pcm_format_t format)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ALSA_SNDIF_FORMATS); i++)
+		if (ALSA_SNDIF_FORMATS[i].alsa == format)
+			return ALSA_SNDIF_FORMATS[i].sndif;
+
+	return -EINVAL;
+}
+
+static u64 to_sndif_formats_mask(u64 alsa_formats)
+{
+	u64 mask;
+	int i;
+
+	mask = 0;
+	for (i = 0; i < ARRAY_SIZE(ALSA_SNDIF_FORMATS); i++)
+		if (1 << ALSA_SNDIF_FORMATS[i].alsa & alsa_formats)
+			mask |= 1 << ALSA_SNDIF_FORMATS[i].sndif;
+
+	return mask;
+}
+
+static u64 to_alsa_formats_mask(u64 sndif_formats)
+{
+	u64 mask;
+	int i;
+
+	mask = 0;
+	for (i = 0; i < ARRAY_SIZE(ALSA_SNDIF_FORMATS); i++)
+		if (1 << ALSA_SNDIF_FORMATS[i].sndif & sndif_formats)
+			mask |= 1 << ALSA_SNDIF_FORMATS[i].alsa;
+
+	return mask;
+}
+
+static void stream_clear(struct xen_snd_front_pcm_stream_info *stream)
+{
+	stream->is_open = false;
+	stream->be_cur_frame = 0;
+	stream->out_frames = 0;
+	atomic_set(&stream->hw_ptr, 0);
+	xen_snd_front_evtchnl_pair_clear(stream->evt_pair);
+	xen_snd_front_shbuf_clear(&stream->sh_buf);
+}
+
+static void stream_free(struct xen_snd_front_pcm_stream_info *stream)
+{
+	xen_snd_front_shbuf_free(&stream->sh_buf);
+	stream_clear(stream);
+}
+
+static struct xen_snd_front_pcm_stream_info *
+stream_get(struct snd_pcm_substream *substream)
+{
+	struct xen_snd_front_pcm_instance_info *pcm_instance =
+			snd_pcm_substream_chip(substream);
+	struct xen_snd_front_pcm_stream_info *stream;
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		stream = &pcm_instance->streams_pb[substream->number];
+	else
+		stream = &pcm_instance->streams_cap[substream->number];
+
+	return stream;
+}
+
+static int alsa_hw_rule(struct snd_pcm_hw_params *params,
+			struct snd_pcm_hw_rule *rule)
+{
+	struct xen_snd_front_pcm_stream_info *stream = rule->private;
+	struct device *dev = &stream->front_info->xb_dev->dev;
+	struct snd_mask *formats =
+			hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+	struct snd_interval *rates =
+			hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval *channels =
+			hw_param_interval(params, SNDRV_PCM_HW_PARAM_CHANNELS);
+	struct snd_interval *period =
+			hw_param_interval(params,
+					  SNDRV_PCM_HW_PARAM_PERIOD_SIZE);
+	struct snd_interval *buffer =
+			hw_param_interval(params,
+					  SNDRV_PCM_HW_PARAM_BUFFER_SIZE);
+	struct xensnd_query_hw_param req;
+	struct xensnd_query_hw_param resp;
+	struct snd_interval interval;
+	struct snd_mask mask;
+	u64 sndif_formats;
+	int changed, ret;
+
+	/* Collect all the values we need for the query. */
+
+	req.formats = to_sndif_formats_mask((u64)formats->bits[0] |
+					    (u64)(formats->bits[1]) << 32);
+
+	req.rates.min = rates->min;
+	req.rates.max = rates->max;
+
+	req.channels.min = channels->min;
+	req.channels.max = channels->max;
+
+	req.buffer.min = buffer->min;
+	req.buffer.max = buffer->max;
+
+	req.period.min = period->min;
+	req.period.max = period->max;
+
+	ret = xen_snd_front_stream_query_hw_param(&stream->evt_pair->req,
+						  &req, &resp);
+	if (ret < 0) {
+		/* Check if this is due to backend communication error. */
+		if (ret == -EIO || ret == -ETIMEDOUT)
+			dev_err(dev, "Failed to query ALSA HW parameters\n");
+		return ret;
+	}
+
+	/* Refine HW parameters after the query. */
+	changed  = 0;
+
+	sndif_formats = to_alsa_formats_mask(resp.formats);
+	snd_mask_none(&mask);
+	mask.bits[0] = (u32)sndif_formats;
+	mask.bits[1] = (u32)(sndif_formats >> 32);
+	ret = snd_mask_refine(formats, &mask);
+	if (ret < 0)
+		return ret;
+	changed |= ret;
+
+	interval.openmin = 0;
+	interval.openmax = 0;
+	interval.integer = 1;
+
+	interval.min = resp.rates.min;
+	interval.max = resp.rates.max;
+	ret = snd_interval_refine(rates, &interval);
+	if (ret < 0)
+		return ret;
+	changed |= ret;
+
+	interval.min = resp.channels.min;
+	interval.max = resp.channels.max;
+	ret = snd_interval_refine(channels, &interval);
+	if (ret < 0)
+		return ret;
+	changed |= ret;
+
+	interval.min = resp.buffer.min;
+	interval.max = resp.buffer.max;
+	ret = snd_interval_refine(buffer, &interval);
+	if (ret < 0)
+		return ret;
+	changed |= ret;
+
+	interval.min = resp.period.min;
+	interval.max = resp.period.max;
+	ret = snd_interval_refine(period, &interval);
+	if (ret < 0)
+		return ret;
+	changed |= ret;
+
+	return changed;
+}
+
+static int alsa_open(struct snd_pcm_substream *substream)
+{
+	struct xen_snd_front_pcm_instance_info *pcm_instance =
+			snd_pcm_substream_chip(substream);
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct xen_snd_front_info *front_info =
+			pcm_instance->card_info->front_info;
+	struct device *dev = &front_info->xb_dev->dev;
+	int ret;
+
+	/*
+	 * Return our HW properties: override defaults with those configured
+	 * via XenStore.
+	 */
+	runtime->hw = stream->pcm_hw;
+	runtime->hw.info &= ~(SNDRV_PCM_INFO_MMAP |
+			      SNDRV_PCM_INFO_MMAP_VALID |
+			      SNDRV_PCM_INFO_DOUBLE |
+			      SNDRV_PCM_INFO_BATCH |
+			      SNDRV_PCM_INFO_NONINTERLEAVED |
+			      SNDRV_PCM_INFO_RESUME |
+			      SNDRV_PCM_INFO_PAUSE);
+	runtime->hw.info |= SNDRV_PCM_INFO_INTERLEAVED;
+
+	stream->evt_pair = &front_info->evt_pairs[stream->index];
+
+	stream->front_info = front_info;
+
+	stream->evt_pair->evt.u.evt.substream = substream;
+
+	stream_clear(stream);
+
+	xen_snd_front_evtchnl_pair_set_connected(stream->evt_pair, true);
+
+	ret = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT,
+				  alsa_hw_rule, stream,
+				  SNDRV_PCM_HW_PARAM_FORMAT, -1);
+	if (ret) {
+		dev_err(dev, "Failed to add HW rule for SNDRV_PCM_HW_PARAM_FORMAT\n");
+		return ret;
+	}
+
+	ret = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
+				  alsa_hw_rule, stream,
+				  SNDRV_PCM_HW_PARAM_RATE, -1);
+	if (ret) {
+		dev_err(dev, "Failed to add HW rule for SNDRV_PCM_HW_PARAM_RATE\n");
+		return ret;
+	}
+
+	ret = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
+				  alsa_hw_rule, stream,
+				  SNDRV_PCM_HW_PARAM_CHANNELS, -1);
+	if (ret) {
+		dev_err(dev, "Failed to add HW rule for SNDRV_PCM_HW_PARAM_CHANNELS\n");
+		return ret;
+	}
+
+	ret = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+				  alsa_hw_rule, stream,
+				  SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1);
+	if (ret) {
+		dev_err(dev, "Failed to add HW rule for SNDRV_PCM_HW_PARAM_PERIOD_SIZE\n");
+		return ret;
+	}
+
+	ret = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+				  alsa_hw_rule, stream,
+				  SNDRV_PCM_HW_PARAM_BUFFER_SIZE, -1);
+	if (ret) {
+		dev_err(dev, "Failed to add HW rule for SNDRV_PCM_HW_PARAM_BUFFER_SIZE\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int alsa_close(struct snd_pcm_substream *substream)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+
+	xen_snd_front_evtchnl_pair_set_connected(stream->evt_pair, false);
+	return 0;
+}
+
+static int alsa_hw_params(struct snd_pcm_substream *substream,
+			  struct snd_pcm_hw_params *params)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+	int ret;
+
+	/*
+	 * This callback may be called multiple times,
+	 * so free the previously allocated shared buffer if any.
+	 */
+	stream_free(stream);
+
+	ret = xen_snd_front_shbuf_alloc(stream->front_info->xb_dev,
+					&stream->sh_buf,
+					params_buffer_bytes(params));
+	if (ret < 0) {
+		stream_free(stream);
+		dev_err(&stream->front_info->xb_dev->dev,
+			"Failed to allocate buffers for stream with index %d\n",
+			stream->index);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int alsa_hw_free(struct snd_pcm_substream *substream)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+	int ret;
+
+	ret = xen_snd_front_stream_close(&stream->evt_pair->req);
+	stream_free(stream);
+	return ret;
+}
+
+static int alsa_prepare(struct snd_pcm_substream *substream)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+
+	if (!stream->is_open) {
+		struct snd_pcm_runtime *runtime = substream->runtime;
+		u8 sndif_format;
+		int ret;
+
+		ret = to_sndif_format(runtime->format);
+		if (ret < 0) {
+			dev_err(&stream->front_info->xb_dev->dev,
+				"Unsupported sample format: %d\n",
+				runtime->format);
+			return ret;
+		}
+		sndif_format = ret;
+
+		ret = xen_snd_front_stream_prepare(&stream->evt_pair->req,
+						   &stream->sh_buf,
+						   sndif_format,
+						   runtime->channels,
+						   runtime->rate,
+						   snd_pcm_lib_buffer_bytes(substream),
+						   snd_pcm_lib_period_bytes(substream));
+		if (ret < 0)
+			return ret;
+
+		stream->is_open = true;
+	}
+
+	return 0;
+}
+
+static int alsa_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+	int type;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+		type = XENSND_OP_TRIGGER_START;
+		break;
+
+	case SNDRV_PCM_TRIGGER_RESUME:
+		type = XENSND_OP_TRIGGER_RESUME;
+		break;
+
+	case SNDRV_PCM_TRIGGER_STOP:
+		type = XENSND_OP_TRIGGER_STOP;
+		break;
+
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		type = XENSND_OP_TRIGGER_PAUSE;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return xen_snd_front_stream_trigger(&stream->evt_pair->req, type);
+}
+
+void xen_snd_front_alsa_handle_cur_pos(struct xen_snd_front_evtchnl *evtchnl,
+				       u64 pos_bytes)
+{
+	struct snd_pcm_substream *substream = evtchnl->u.evt.substream;
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+	snd_pcm_uframes_t delta, new_hw_ptr, cur_frame;
+
+	cur_frame = bytes_to_frames(substream->runtime, pos_bytes);
+
+	delta = cur_frame - stream->be_cur_frame;
+	stream->be_cur_frame = cur_frame;
+
+	new_hw_ptr = (snd_pcm_uframes_t)atomic_read(&stream->hw_ptr);
+	new_hw_ptr = (new_hw_ptr + delta) % substream->runtime->buffer_size;
+	atomic_set(&stream->hw_ptr, (int)new_hw_ptr);
+
+	stream->out_frames += delta;
+	if (stream->out_frames > substream->runtime->period_size) {
+		stream->out_frames %= substream->runtime->period_size;
+		snd_pcm_period_elapsed(substream);
+	}
+}
+
+static snd_pcm_uframes_t alsa_pointer(struct snd_pcm_substream *substream)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+
+	return (snd_pcm_uframes_t)atomic_read(&stream->hw_ptr);
+}
+
+static int alsa_pb_copy_user(struct snd_pcm_substream *substream,
+			     int channel, unsigned long pos, void __user *src,
+			     unsigned long count)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+
+	if (unlikely(pos + count > stream->sh_buf.buffer_sz))
+		return -EINVAL;
+
+	if (copy_from_user(stream->sh_buf.buffer + pos, src, count))
+		return -EFAULT;
+
+	return xen_snd_front_stream_write(&stream->evt_pair->req, pos, count);
+}
+
+static int alsa_pb_copy_kernel(struct snd_pcm_substream *substream,
+			       int channel, unsigned long pos, void *src,
+			       unsigned long count)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+
+	if (unlikely(pos + count > stream->sh_buf.buffer_sz))
+		return -EINVAL;
+
+	memcpy(stream->sh_buf.buffer + pos, src, count);
+
+	return xen_snd_front_stream_write(&stream->evt_pair->req, pos, count);
+}
+
+static int alsa_cap_copy_user(struct snd_pcm_substream *substream,
+			      int channel, unsigned long pos, void __user *dst,
+			      unsigned long count)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+	int ret;
+
+	if (unlikely(pos + count > stream->sh_buf.buffer_sz))
+		return -EINVAL;
+
+	ret = xen_snd_front_stream_read(&stream->evt_pair->req, pos, count);
+	if (ret < 0)
+		return ret;
+
+	return copy_to_user(dst, stream->sh_buf.buffer + pos, count) ?
+		-EFAULT : 0;
+}
+
+static int alsa_cap_copy_kernel(struct snd_pcm_substream *substream,
+				int channel, unsigned long pos, void *dst,
+				unsigned long count)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+	int ret;
+
+	if (unlikely(pos + count > stream->sh_buf.buffer_sz))
+		return -EINVAL;
+
+	ret = xen_snd_front_stream_read(&stream->evt_pair->req, pos, count);
+	if (ret < 0)
+		return ret;
+
+	memcpy(dst, stream->sh_buf.buffer + pos, count);
+
+	return 0;
+}
+
+static int alsa_pb_fill_silence(struct snd_pcm_substream *substream,
+				int channel, unsigned long pos,
+				unsigned long count)
+{
+	struct xen_snd_front_pcm_stream_info *stream = stream_get(substream);
+
+	if (unlikely(pos + count > stream->sh_buf.buffer_sz))
+		return -EINVAL;
+
+	memset(stream->sh_buf.buffer + pos, 0, count);
+
+	return xen_snd_front_stream_write(&stream->evt_pair->req, pos, count);
+}
+
+/*
+ * FIXME: The mmaped data transfer is asynchronous and there is no
+ * ack signal from user-space when it is done. This is the
+ * reason it is not implemented in the PV driver as we do need
+ * to know when the buffer can be transferred to the backend.
+ */
+
+static struct snd_pcm_ops snd_drv_alsa_playback_ops = {
+	.open = alsa_open,
+	.close = alsa_close,
+	.ioctl = snd_pcm_lib_ioctl,
+	.hw_params = alsa_hw_params,
+	.hw_free = alsa_hw_free,
+	.prepare = alsa_prepare,
+	.trigger = alsa_trigger,
+	.pointer = alsa_pointer,
+	.copy_user = alsa_pb_copy_user,
+	.copy_kernel = alsa_pb_copy_kernel,
+	.fill_silence = alsa_pb_fill_silence,
+};
+
+static struct snd_pcm_ops snd_drv_alsa_capture_ops = {
+	.open = alsa_open,
+	.close = alsa_close,
+	.ioctl = snd_pcm_lib_ioctl,
+	.hw_params = alsa_hw_params,
+	.hw_free = alsa_hw_free,
+	.prepare = alsa_prepare,
+	.trigger = alsa_trigger,
+	.pointer = alsa_pointer,
+	.copy_user = alsa_cap_copy_user,
+	.copy_kernel = alsa_cap_copy_kernel,
+};
+
+static int new_pcm_instance(struct xen_snd_front_card_info *card_info,
+			    struct xen_front_cfg_pcm_instance *instance_cfg,
+			    struct xen_snd_front_pcm_instance_info *pcm_instance_info)
+{
+	struct snd_pcm *pcm;
+	int ret, i;
+
+	dev_dbg(&card_info->front_info->xb_dev->dev,
+		"New PCM device \"%s\" with id %d playback %d capture %d",
+		instance_cfg->name,
+		instance_cfg->device_id,
+		instance_cfg->num_streams_pb,
+		instance_cfg->num_streams_cap);
+
+	pcm_instance_info->card_info = card_info;
+
+	pcm_instance_info->pcm_hw = instance_cfg->pcm_hw;
+
+	if (instance_cfg->num_streams_pb) {
+		pcm_instance_info->streams_pb =
+				devm_kcalloc(&card_info->card->card_dev,
+					     instance_cfg->num_streams_pb,
+					     sizeof(struct xen_snd_front_pcm_stream_info),
+					     GFP_KERNEL);
+		if (!pcm_instance_info->streams_pb)
+			return -ENOMEM;
+	}
+
+	if (instance_cfg->num_streams_cap) {
+		pcm_instance_info->streams_cap =
+				devm_kcalloc(&card_info->card->card_dev,
+					     instance_cfg->num_streams_cap,
+					     sizeof(struct xen_snd_front_pcm_stream_info),
+					     GFP_KERNEL);
+		if (!pcm_instance_info->streams_cap)
+			return -ENOMEM;
+	}
+
+	pcm_instance_info->num_pcm_streams_pb =
+			instance_cfg->num_streams_pb;
+	pcm_instance_info->num_pcm_streams_cap =
+			instance_cfg->num_streams_cap;
+
+	for (i = 0; i < pcm_instance_info->num_pcm_streams_pb; i++) {
+		pcm_instance_info->streams_pb[i].pcm_hw =
+			instance_cfg->streams_pb[i].pcm_hw;
+		pcm_instance_info->streams_pb[i].index =
+			instance_cfg->streams_pb[i].index;
+	}
+
+	for (i = 0; i < pcm_instance_info->num_pcm_streams_cap; i++) {
+		pcm_instance_info->streams_cap[i].pcm_hw =
+			instance_cfg->streams_cap[i].pcm_hw;
+		pcm_instance_info->streams_cap[i].index =
+			instance_cfg->streams_cap[i].index;
+	}
+
+	ret = snd_pcm_new(card_info->card, instance_cfg->name,
+			  instance_cfg->device_id,
+			  instance_cfg->num_streams_pb,
+			  instance_cfg->num_streams_cap,
+			  &pcm);
+	if (ret < 0)
+		return ret;
+
+	pcm->private_data = pcm_instance_info;
+	pcm->info_flags = 0;
+	/* we want to handle all PCM operations in non-atomic context */
+	pcm->nonatomic = true;
+	strncpy(pcm->name, "Virtual card PCM", sizeof(pcm->name));
+
+	if (instance_cfg->num_streams_pb)
+		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK,
+				&snd_drv_alsa_playback_ops);
+
+	if (instance_cfg->num_streams_cap)
+		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE,
+				&snd_drv_alsa_capture_ops);
+
+	pcm_instance_info->pcm = pcm;
+	return 0;
+}
+
+int xen_snd_front_alsa_init(struct xen_snd_front_info *front_info)
+{
+	struct device *dev = &front_info->xb_dev->dev;
+	struct xen_front_cfg_card *cfg = &front_info->cfg;
+	struct xen_snd_front_card_info *card_info;
+	struct snd_card *card;
+	int ret, i;
+
+	dev_dbg(dev, "Creating virtual sound card\n");
+
+	ret = snd_card_new(dev, 0, XENSND_DRIVER_NAME, THIS_MODULE,
+			   sizeof(struct xen_snd_front_card_info), &card);
+	if (ret < 0)
+		return ret;
+
+	card_info = card->private_data;
+	card_info->front_info = front_info;
+	front_info->card_info = card_info;
+	card_info->card = card;
+	card_info->pcm_instances =
+			devm_kcalloc(dev, cfg->num_pcm_instances,
+				     sizeof(struct xen_snd_front_pcm_instance_info),
+				     GFP_KERNEL);
+	if (!card_info->pcm_instances) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	card_info->num_pcm_instances = cfg->num_pcm_instances;
+	card_info->pcm_hw = cfg->pcm_hw;
+
+	for (i = 0; i < cfg->num_pcm_instances; i++) {
+		ret = new_pcm_instance(card_info, &cfg->pcm_instances[i],
+				       &card_info->pcm_instances[i]);
+		if (ret < 0)
+			goto fail;
+	}
+
+	strncpy(card->driver, XENSND_DRIVER_NAME, sizeof(card->driver));
+	strncpy(card->shortname, cfg->name_short, sizeof(card->shortname));
+	strncpy(card->longname, cfg->name_long, sizeof(card->longname));
+
+	ret = snd_card_register(card);
+	if (ret < 0)
+		goto fail;
+
+	return 0;
+
+fail:
+	snd_card_free(card);
+	return ret;
+}
+
+void xen_snd_front_alsa_fini(struct xen_snd_front_info *front_info)
+{
+	struct xen_snd_front_card_info *card_info;
+	struct snd_card *card;
+
+	card_info = front_info->card_info;
+	if (!card_info)
+		return;
+
+	card = card_info->card;
+	if (!card)
+		return;
+
+	dev_dbg(&front_info->xb_dev->dev, "Removing virtual sound card %d\n",
+		card->number);
+	snd_card_free(card);
+
+	/* Card_info will be freed when destroying front_info->xb_dev->dev. */
+	card_info->card = NULL;
+}
diff --git a/sound/xen/xen_snd_front_alsa.h b/sound/xen/xen_snd_front_alsa.h
new file mode 100644
index 000000000000..18abd9eec967
--- /dev/null
+++ b/sound/xen/xen_snd_front_alsa.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_SND_FRONT_ALSA_H
+#define __XEN_SND_FRONT_ALSA_H
+
+struct xen_snd_front_info;
+
+int xen_snd_front_alsa_init(struct xen_snd_front_info *front_info);
+
+void xen_snd_front_alsa_fini(struct xen_snd_front_info *front_info);
+
+void xen_snd_front_alsa_handle_cur_pos(struct xen_snd_front_evtchnl *evtchnl,
+				       u64 pos_bytes);
+
+#endif /* __XEN_SND_FRONT_ALSA_H */
diff --git a/sound/xen/xen_snd_front_cfg.c b/sound/xen/xen_snd_front_cfg.c
new file mode 100644
index 000000000000..eda077c8087a
--- /dev/null
+++ b/sound/xen/xen_snd_front_cfg.c
@@ -0,0 +1,519 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <xen/xenbus.h>
+
+#include <xen/interface/io/sndif.h>
+
+#include "xen_snd_front.h"
+#include "xen_snd_front_cfg.h"
+
+/* Maximum number of supported streams. */
+#define VSND_MAX_STREAM		8
+
+struct cfg_hw_sample_rate {
+	const char *name;
+	unsigned int mask;
+	unsigned int value;
+};
+
+static const struct cfg_hw_sample_rate CFG_HW_SUPPORTED_RATES[] = {
+	{ .name = "5512",   .mask = SNDRV_PCM_RATE_5512,   .value = 5512 },
+	{ .name = "8000",   .mask = SNDRV_PCM_RATE_8000,   .value = 8000 },
+	{ .name = "11025",  .mask = SNDRV_PCM_RATE_11025,  .value = 11025 },
+	{ .name = "16000",  .mask = SNDRV_PCM_RATE_16000,  .value = 16000 },
+	{ .name = "22050",  .mask = SNDRV_PCM_RATE_22050,  .value = 22050 },
+	{ .name = "32000",  .mask = SNDRV_PCM_RATE_32000,  .value = 32000 },
+	{ .name = "44100",  .mask = SNDRV_PCM_RATE_44100,  .value = 44100 },
+	{ .name = "48000",  .mask = SNDRV_PCM_RATE_48000,  .value = 48000 },
+	{ .name = "64000",  .mask = SNDRV_PCM_RATE_64000,  .value = 64000 },
+	{ .name = "96000",  .mask = SNDRV_PCM_RATE_96000,  .value = 96000 },
+	{ .name = "176400", .mask = SNDRV_PCM_RATE_176400, .value = 176400 },
+	{ .name = "192000", .mask = SNDRV_PCM_RATE_192000, .value = 192000 },
+};
+
+struct cfg_hw_sample_format {
+	const char *name;
+	u64 mask;
+};
+
+static const struct cfg_hw_sample_format CFG_HW_SUPPORTED_FORMATS[] = {
+	{
+		.name = XENSND_PCM_FORMAT_U8_STR,
+		.mask = SNDRV_PCM_FMTBIT_U8
+	},
+	{
+		.name = XENSND_PCM_FORMAT_S8_STR,
+		.mask = SNDRV_PCM_FMTBIT_S8
+	},
+	{
+		.name = XENSND_PCM_FORMAT_U16_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_U16_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_U16_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_U16_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_S16_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_S16_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_S16_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_S16_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_U24_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_U24_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_U24_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_U24_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_S24_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_S24_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_S24_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_S24_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_U32_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_U32_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_U32_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_U32_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_S32_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_S32_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_S32_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_S32_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_A_LAW_STR,
+		.mask = SNDRV_PCM_FMTBIT_A_LAW
+	},
+	{
+		.name = XENSND_PCM_FORMAT_MU_LAW_STR,
+		.mask = SNDRV_PCM_FMTBIT_MU_LAW
+	},
+	{
+		.name = XENSND_PCM_FORMAT_F32_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_FLOAT_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_F32_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_FLOAT_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_F64_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_FLOAT64_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_F64_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_FLOAT64_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_IEC958_SUBFRAME_LE_STR,
+		.mask = SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_IEC958_SUBFRAME_BE_STR,
+		.mask = SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_BE
+	},
+	{
+		.name = XENSND_PCM_FORMAT_IMA_ADPCM_STR,
+		.mask = SNDRV_PCM_FMTBIT_IMA_ADPCM
+	},
+	{
+		.name = XENSND_PCM_FORMAT_MPEG_STR,
+		.mask = SNDRV_PCM_FMTBIT_MPEG
+	},
+	{
+		.name = XENSND_PCM_FORMAT_GSM_STR,
+		.mask = SNDRV_PCM_FMTBIT_GSM
+	},
+};
+
+static void cfg_hw_rates(char *list, unsigned int len,
+			 const char *path, struct snd_pcm_hardware *pcm_hw)
+{
+	char *cur_rate;
+	unsigned int cur_mask;
+	unsigned int cur_value;
+	unsigned int rates;
+	unsigned int rate_min;
+	unsigned int rate_max;
+	int i;
+
+	rates = 0;
+	rate_min = -1;
+	rate_max = 0;
+	while ((cur_rate = strsep(&list, XENSND_LIST_SEPARATOR))) {
+		for (i = 0; i < ARRAY_SIZE(CFG_HW_SUPPORTED_RATES); i++)
+			if (!strncasecmp(cur_rate,
+					 CFG_HW_SUPPORTED_RATES[i].name,
+					 XENSND_SAMPLE_RATE_MAX_LEN)) {
+				cur_mask = CFG_HW_SUPPORTED_RATES[i].mask;
+				cur_value = CFG_HW_SUPPORTED_RATES[i].value;
+				rates |= cur_mask;
+				if (rate_min > cur_value)
+					rate_min = cur_value;
+				if (rate_max < cur_value)
+					rate_max = cur_value;
+			}
+	}
+
+	if (rates) {
+		pcm_hw->rates = rates;
+		pcm_hw->rate_min = rate_min;
+		pcm_hw->rate_max = rate_max;
+	}
+}
+
+static void cfg_formats(char *list, unsigned int len,
+			const char *path, struct snd_pcm_hardware *pcm_hw)
+{
+	u64 formats;
+	char *cur_format;
+	int i;
+
+	formats = 0;
+	while ((cur_format = strsep(&list, XENSND_LIST_SEPARATOR))) {
+		for (i = 0; i < ARRAY_SIZE(CFG_HW_SUPPORTED_FORMATS); i++)
+			if (!strncasecmp(cur_format,
+					 CFG_HW_SUPPORTED_FORMATS[i].name,
+					 XENSND_SAMPLE_FORMAT_MAX_LEN))
+				formats |= CFG_HW_SUPPORTED_FORMATS[i].mask;
+	}
+
+	if (formats)
+		pcm_hw->formats = formats;
+}
+
+#define MAX_BUFFER_SIZE		(64 * 1024)
+#define MIN_PERIOD_SIZE		64
+#define MAX_PERIOD_SIZE		MAX_BUFFER_SIZE
+#define USE_FORMATS		(SNDRV_PCM_FMTBIT_U8 | \
+				 SNDRV_PCM_FMTBIT_S16_LE)
+#define USE_RATE		(SNDRV_PCM_RATE_CONTINUOUS | \
+				 SNDRV_PCM_RATE_8000_48000)
+#define USE_RATE_MIN		5512
+#define USE_RATE_MAX		48000
+#define USE_CHANNELS_MIN	1
+#define USE_CHANNELS_MAX	2
+#define USE_PERIODS_MIN		2
+#define USE_PERIODS_MAX		(MAX_BUFFER_SIZE / MIN_PERIOD_SIZE)
+
+static const struct snd_pcm_hardware SND_DRV_PCM_HW_DEFAULT = {
+	.info = (SNDRV_PCM_INFO_MMAP |
+		 SNDRV_PCM_INFO_INTERLEAVED |
+		 SNDRV_PCM_INFO_RESUME |
+		 SNDRV_PCM_INFO_MMAP_VALID),
+	.formats = USE_FORMATS,
+	.rates = USE_RATE,
+	.rate_min = USE_RATE_MIN,
+	.rate_max = USE_RATE_MAX,
+	.channels_min = USE_CHANNELS_MIN,
+	.channels_max = USE_CHANNELS_MAX,
+	.buffer_bytes_max = MAX_BUFFER_SIZE,
+	.period_bytes_min = MIN_PERIOD_SIZE,
+	.period_bytes_max = MAX_PERIOD_SIZE,
+	.periods_min = USE_PERIODS_MIN,
+	.periods_max = USE_PERIODS_MAX,
+	.fifo_size = 0,
+};
+
+static void cfg_read_pcm_hw(const char *path,
+			    struct snd_pcm_hardware *parent_pcm_hw,
+			    struct snd_pcm_hardware *pcm_hw)
+{
+	char *list;
+	int val;
+	size_t buf_sz;
+	unsigned int len;
+
+	/* Inherit parent's PCM HW and read overrides from XenStore. */
+	if (parent_pcm_hw)
+		*pcm_hw = *parent_pcm_hw;
+	else
+		*pcm_hw = SND_DRV_PCM_HW_DEFAULT;
+
+	val = xenbus_read_unsigned(path, XENSND_FIELD_CHANNELS_MIN, 0);
+	if (val)
+		pcm_hw->channels_min = val;
+
+	val = xenbus_read_unsigned(path, XENSND_FIELD_CHANNELS_MAX, 0);
+	if (val)
+		pcm_hw->channels_max = val;
+
+	list = xenbus_read(XBT_NIL, path, XENSND_FIELD_SAMPLE_RATES, &len);
+	if (!IS_ERR(list)) {
+		cfg_hw_rates(list, len, path, pcm_hw);
+		kfree(list);
+	}
+
+	list = xenbus_read(XBT_NIL, path, XENSND_FIELD_SAMPLE_FORMATS, &len);
+	if (!IS_ERR(list)) {
+		cfg_formats(list, len, path, pcm_hw);
+		kfree(list);
+	}
+
+	buf_sz = xenbus_read_unsigned(path, XENSND_FIELD_BUFFER_SIZE, 0);
+	if (buf_sz)
+		pcm_hw->buffer_bytes_max = buf_sz;
+
+	/* Update configuration to match new values. */
+	if (pcm_hw->channels_min > pcm_hw->channels_max)
+		pcm_hw->channels_min = pcm_hw->channels_max;
+
+	if (pcm_hw->rate_min > pcm_hw->rate_max)
+		pcm_hw->rate_min = pcm_hw->rate_max;
+
+	pcm_hw->period_bytes_max = pcm_hw->buffer_bytes_max;
+
+	pcm_hw->periods_max = pcm_hw->period_bytes_max /
+		pcm_hw->period_bytes_min;
+}
+
+static int cfg_get_stream_type(const char *path, int index,
+			       int *num_pb, int *num_cap)
+{
+	char *str = NULL;
+	char *stream_path;
+	int ret;
+
+	*num_pb = 0;
+	*num_cap = 0;
+	stream_path = kasprintf(GFP_KERNEL, "%s/%d", path, index);
+	if (!stream_path) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	str = xenbus_read(XBT_NIL, stream_path, XENSND_FIELD_TYPE, NULL);
+	if (IS_ERR(str)) {
+		ret = PTR_ERR(str);
+		str = NULL;
+		goto fail;
+	}
+
+	if (!strncasecmp(str, XENSND_STREAM_TYPE_PLAYBACK,
+			 sizeof(XENSND_STREAM_TYPE_PLAYBACK))) {
+		(*num_pb)++;
+	} else if (!strncasecmp(str, XENSND_STREAM_TYPE_CAPTURE,
+			      sizeof(XENSND_STREAM_TYPE_CAPTURE))) {
+		(*num_cap)++;
+	} else {
+		ret = -EINVAL;
+		goto fail;
+	}
+	ret = 0;
+
+fail:
+	kfree(stream_path);
+	kfree(str);
+	return ret;
+}
+
+static int cfg_stream(struct xen_snd_front_info *front_info,
+		      struct xen_front_cfg_pcm_instance *pcm_instance,
+		      const char *path, int index, int *cur_pb, int *cur_cap,
+		      int *stream_cnt)
+{
+	char *str = NULL;
+	char *stream_path;
+	struct xen_front_cfg_stream *stream;
+	int ret;
+
+	stream_path = devm_kasprintf(&front_info->xb_dev->dev,
+				     GFP_KERNEL, "%s/%d", path, index);
+	if (!stream_path) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	str = xenbus_read(XBT_NIL, stream_path, XENSND_FIELD_TYPE, NULL);
+	if (IS_ERR(str)) {
+		ret = PTR_ERR(str);
+		str = NULL;
+		goto fail;
+	}
+
+	if (!strncasecmp(str, XENSND_STREAM_TYPE_PLAYBACK,
+			 sizeof(XENSND_STREAM_TYPE_PLAYBACK))) {
+		stream = &pcm_instance->streams_pb[(*cur_pb)++];
+	} else if (!strncasecmp(str, XENSND_STREAM_TYPE_CAPTURE,
+			      sizeof(XENSND_STREAM_TYPE_CAPTURE))) {
+		stream = &pcm_instance->streams_cap[(*cur_cap)++];
+	} else {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	/* Get next stream index. */
+	stream->index = (*stream_cnt)++;
+	stream->xenstore_path = stream_path;
+	/*
+	 * Check XenStore if PCM HW configuration exists for this stream
+	 * and update if so, e.g. we inherit all values from device's PCM HW,
+	 * but can still override some of the values for the stream.
+	 */
+	cfg_read_pcm_hw(stream->xenstore_path,
+			&pcm_instance->pcm_hw, &stream->pcm_hw);
+	ret = 0;
+
+fail:
+	kfree(str);
+	return ret;
+}
+
+static int cfg_device(struct xen_snd_front_info *front_info,
+		      struct xen_front_cfg_pcm_instance *pcm_instance,
+		      struct snd_pcm_hardware *parent_pcm_hw,
+		      const char *path, int node_index, int *stream_cnt)
+{
+	char *str;
+	char *device_path;
+	int ret, i, num_streams;
+	int num_pb, num_cap;
+	int cur_pb, cur_cap;
+	char node[3];
+
+	device_path = kasprintf(GFP_KERNEL, "%s/%d", path, node_index);
+	if (!device_path)
+		return -ENOMEM;
+
+	str = xenbus_read(XBT_NIL, device_path, XENSND_FIELD_DEVICE_NAME, NULL);
+	if (!IS_ERR(str)) {
+		strlcpy(pcm_instance->name, str, sizeof(pcm_instance->name));
+		kfree(str);
+	}
+
+	pcm_instance->device_id = node_index;
+
+	/*
+	 * Check XenStore if PCM HW configuration exists for this device
+	 * and update if so, e.g. we inherit all values from card's PCM HW,
+	 * but can still override some of the values for the device.
+	 */
+	cfg_read_pcm_hw(device_path, parent_pcm_hw, &pcm_instance->pcm_hw);
+
+	/* Find out how many streams were configured in Xen store. */
+	num_streams = 0;
+	do {
+		snprintf(node, sizeof(node), "%d", num_streams);
+		if (!xenbus_exists(XBT_NIL, device_path, node))
+			break;
+
+		num_streams++;
+	} while (num_streams < VSND_MAX_STREAM);
+
+	pcm_instance->num_streams_pb = 0;
+	pcm_instance->num_streams_cap = 0;
+	/* Get number of playback and capture streams. */
+	for (i = 0; i < num_streams; i++) {
+		ret = cfg_get_stream_type(device_path, i, &num_pb, &num_cap);
+		if (ret < 0)
+			goto fail;
+
+		pcm_instance->num_streams_pb += num_pb;
+		pcm_instance->num_streams_cap += num_cap;
+	}
+
+	if (pcm_instance->num_streams_pb) {
+		pcm_instance->streams_pb =
+				devm_kcalloc(&front_info->xb_dev->dev,
+					     pcm_instance->num_streams_pb,
+					     sizeof(struct xen_front_cfg_stream),
+					     GFP_KERNEL);
+		if (!pcm_instance->streams_pb) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+	}
+
+	if (pcm_instance->num_streams_cap) {
+		pcm_instance->streams_cap =
+				devm_kcalloc(&front_info->xb_dev->dev,
+					     pcm_instance->num_streams_cap,
+					     sizeof(struct xen_front_cfg_stream),
+					     GFP_KERNEL);
+		if (!pcm_instance->streams_cap) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+	}
+
+	cur_pb = 0;
+	cur_cap = 0;
+	for (i = 0; i < num_streams; i++) {
+		ret = cfg_stream(front_info, pcm_instance, device_path, i,
+				 &cur_pb, &cur_cap, stream_cnt);
+		if (ret < 0)
+			goto fail;
+	}
+	ret = 0;
+
+fail:
+	kfree(device_path);
+	return ret;
+}
+
+int xen_snd_front_cfg_card(struct xen_snd_front_info *front_info,
+			   int *stream_cnt)
+{
+	struct xenbus_device *xb_dev = front_info->xb_dev;
+	struct xen_front_cfg_card *cfg = &front_info->cfg;
+	int ret, num_devices, i;
+	char node[3];
+
+	*stream_cnt = 0;
+	num_devices = 0;
+	do {
+		snprintf(node, sizeof(node), "%d", num_devices);
+		if (!xenbus_exists(XBT_NIL, xb_dev->nodename, node))
+			break;
+
+		num_devices++;
+	} while (num_devices < SNDRV_PCM_DEVICES);
+
+	if (!num_devices) {
+		dev_warn(&xb_dev->dev,
+			 "No devices configured for sound card at %s\n",
+			 xb_dev->nodename);
+		return -ENODEV;
+	}
+
+	/* Start from default PCM HW configuration for the card. */
+	cfg_read_pcm_hw(xb_dev->nodename, NULL, &cfg->pcm_hw);
+
+	cfg->pcm_instances =
+			devm_kcalloc(&front_info->xb_dev->dev, num_devices,
+				     sizeof(struct xen_front_cfg_pcm_instance),
+				     GFP_KERNEL);
+	if (!cfg->pcm_instances)
+		return -ENOMEM;
+
+	for (i = 0; i < num_devices; i++) {
+		ret = cfg_device(front_info, &cfg->pcm_instances[i],
+				 &cfg->pcm_hw, xb_dev->nodename, i, stream_cnt);
+		if (ret < 0)
+			return ret;
+	}
+	cfg->num_pcm_instances = num_devices;
+	return 0;
+}
+
diff --git a/sound/xen/xen_snd_front_cfg.h b/sound/xen/xen_snd_front_cfg.h
new file mode 100644
index 000000000000..2353fcc74889
--- /dev/null
+++ b/sound/xen/xen_snd_front_cfg.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_SND_FRONT_CFG_H
+#define __XEN_SND_FRONT_CFG_H
+
+#include <sound/core.h>
+#include <sound/pcm.h>
+
+struct xen_snd_front_info;
+
+struct xen_front_cfg_stream {
+	int index;
+	char *xenstore_path;
+	struct snd_pcm_hardware pcm_hw;
+};
+
+struct xen_front_cfg_pcm_instance {
+	char name[80];
+	int device_id;
+	struct snd_pcm_hardware pcm_hw;
+	int  num_streams_pb;
+	struct xen_front_cfg_stream *streams_pb;
+	int  num_streams_cap;
+	struct xen_front_cfg_stream *streams_cap;
+};
+
+struct xen_front_cfg_card {
+	char name_short[32];
+	char name_long[80];
+	struct snd_pcm_hardware pcm_hw;
+	int num_pcm_instances;
+	struct xen_front_cfg_pcm_instance *pcm_instances;
+};
+
+int xen_snd_front_cfg_card(struct xen_snd_front_info *front_info,
+			   int *stream_cnt);
+
+#endif /* __XEN_SND_FRONT_CFG_H */
diff --git a/sound/xen/xen_snd_front_evtchnl.c b/sound/xen/xen_snd_front_evtchnl.c
new file mode 100644
index 000000000000..102d6e096cc8
--- /dev/null
+++ b/sound/xen/xen_snd_front_evtchnl.c
@@ -0,0 +1,494 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+
+#include "xen_snd_front.h"
+#include "xen_snd_front_alsa.h"
+#include "xen_snd_front_cfg.h"
+#include "xen_snd_front_evtchnl.h"
+
+static irqreturn_t evtchnl_interrupt_req(int irq, void *dev_id)
+{
+	struct xen_snd_front_evtchnl *channel = dev_id;
+	struct xen_snd_front_info *front_info = channel->front_info;
+	struct xensnd_resp *resp;
+	RING_IDX i, rp;
+
+	if (unlikely(channel->state != EVTCHNL_STATE_CONNECTED))
+		return IRQ_HANDLED;
+
+	mutex_lock(&channel->ring_io_lock);
+
+again:
+	rp = channel->u.req.ring.sring->rsp_prod;
+	/* Ensure we see queued responses up to rp. */
+	rmb();
+
+	/*
+	 * Assume that the backend is trusted to always write sane values
+	 * to the ring counters, so no overflow checks on frontend side
+	 * are required.
+	 */
+	for (i = channel->u.req.ring.rsp_cons; i != rp; i++) {
+		resp = RING_GET_RESPONSE(&channel->u.req.ring, i);
+		if (resp->id != channel->evt_id)
+			continue;
+		switch (resp->operation) {
+		case XENSND_OP_OPEN:
+			/* fall through */
+		case XENSND_OP_CLOSE:
+			/* fall through */
+		case XENSND_OP_READ:
+			/* fall through */
+		case XENSND_OP_WRITE:
+			/* fall through */
+		case XENSND_OP_TRIGGER:
+			channel->u.req.resp_status = resp->status;
+			complete(&channel->u.req.completion);
+			break;
+		case XENSND_OP_HW_PARAM_QUERY:
+			channel->u.req.resp_status = resp->status;
+			channel->u.req.resp.hw_param =
+					resp->resp.hw_param;
+			complete(&channel->u.req.completion);
+			break;
+
+		default:
+			dev_err(&front_info->xb_dev->dev,
+				"Operation %d is not supported\n",
+				resp->operation);
+			break;
+		}
+	}
+
+	channel->u.req.ring.rsp_cons = i;
+	if (i != channel->u.req.ring.req_prod_pvt) {
+		int more_to_do;
+
+		RING_FINAL_CHECK_FOR_RESPONSES(&channel->u.req.ring,
+					       more_to_do);
+		if (more_to_do)
+			goto again;
+	} else {
+		channel->u.req.ring.sring->rsp_event = i + 1;
+	}
+
+	mutex_unlock(&channel->ring_io_lock);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t evtchnl_interrupt_evt(int irq, void *dev_id)
+{
+	struct xen_snd_front_evtchnl *channel = dev_id;
+	struct xensnd_event_page *page = channel->u.evt.page;
+	u32 cons, prod;
+
+	if (unlikely(channel->state != EVTCHNL_STATE_CONNECTED))
+		return IRQ_HANDLED;
+
+	mutex_lock(&channel->ring_io_lock);
+
+	prod = page->in_prod;
+	/* Ensure we see ring contents up to prod. */
+	virt_rmb();
+	if (prod == page->in_cons)
+		goto out;
+
+	/*
+	 * Assume that the backend is trusted to always write sane values
+	 * to the ring counters, so no overflow checks on frontend side
+	 * are required.
+	 */
+	for (cons = page->in_cons; cons != prod; cons++) {
+		struct xensnd_evt *event;
+
+		event = &XENSND_IN_RING_REF(page, cons);
+		if (unlikely(event->id != channel->evt_id++))
+			continue;
+
+		switch (event->type) {
+		case XENSND_EVT_CUR_POS:
+			xen_snd_front_alsa_handle_cur_pos(channel,
+							  event->op.cur_pos.position);
+			break;
+		}
+	}
+
+	page->in_cons = cons;
+	/* Ensure ring contents. */
+	virt_wmb();
+
+out:
+	mutex_unlock(&channel->ring_io_lock);
+	return IRQ_HANDLED;
+}
+
+void xen_snd_front_evtchnl_flush(struct xen_snd_front_evtchnl *channel)
+{
+	int notify;
+
+	channel->u.req.ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&channel->u.req.ring, notify);
+	if (notify)
+		notify_remote_via_irq(channel->irq);
+}
+
+static void evtchnl_free(struct xen_snd_front_info *front_info,
+			 struct xen_snd_front_evtchnl *channel)
+{
+	unsigned long page = 0;
+
+	if (channel->type == EVTCHNL_TYPE_REQ)
+		page = (unsigned long)channel->u.req.ring.sring;
+	else if (channel->type == EVTCHNL_TYPE_EVT)
+		page = (unsigned long)channel->u.evt.page;
+
+	if (!page)
+		return;
+
+	channel->state = EVTCHNL_STATE_DISCONNECTED;
+	if (channel->type == EVTCHNL_TYPE_REQ) {
+		/* Release all who still waits for response if any. */
+		channel->u.req.resp_status = -EIO;
+		complete_all(&channel->u.req.completion);
+	}
+
+	if (channel->irq)
+		unbind_from_irqhandler(channel->irq, channel);
+
+	if (channel->port)
+		xenbus_free_evtchn(front_info->xb_dev, channel->port);
+
+	/* End access and free the page. */
+	if (channel->gref != GRANT_INVALID_REF)
+		gnttab_end_foreign_access(channel->gref, 0, page);
+	else
+		free_page(page);
+
+	memset(channel, 0, sizeof(*channel));
+}
+
+void xen_snd_front_evtchnl_free_all(struct xen_snd_front_info *front_info)
+{
+	int i;
+
+	if (!front_info->evt_pairs)
+		return;
+
+	for (i = 0; i < front_info->num_evt_pairs; i++) {
+		evtchnl_free(front_info, &front_info->evt_pairs[i].req);
+		evtchnl_free(front_info, &front_info->evt_pairs[i].evt);
+	}
+
+	kfree(front_info->evt_pairs);
+	front_info->evt_pairs = NULL;
+}
+
+static int evtchnl_alloc(struct xen_snd_front_info *front_info, int index,
+			 struct xen_snd_front_evtchnl *channel,
+			 enum xen_snd_front_evtchnl_type type)
+{
+	struct xenbus_device *xb_dev = front_info->xb_dev;
+	unsigned long page;
+	grant_ref_t gref;
+	irq_handler_t handler;
+	char *handler_name = NULL;
+	int ret;
+
+	memset(channel, 0, sizeof(*channel));
+	channel->type = type;
+	channel->index = index;
+	channel->front_info = front_info;
+	channel->state = EVTCHNL_STATE_DISCONNECTED;
+	channel->gref = GRANT_INVALID_REF;
+	page = get_zeroed_page(GFP_KERNEL);
+	if (!page) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	handler_name = kasprintf(GFP_KERNEL, "%s-%s", XENSND_DRIVER_NAME,
+				 type == EVTCHNL_TYPE_REQ ?
+				 XENSND_FIELD_RING_REF :
+				 XENSND_FIELD_EVT_RING_REF);
+	if (!handler_name) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	mutex_init(&channel->ring_io_lock);
+
+	if (type == EVTCHNL_TYPE_REQ) {
+		struct xen_sndif_sring *sring = (struct xen_sndif_sring *)page;
+
+		init_completion(&channel->u.req.completion);
+		mutex_init(&channel->u.req.req_io_lock);
+		SHARED_RING_INIT(sring);
+		FRONT_RING_INIT(&channel->u.req.ring, sring, XEN_PAGE_SIZE);
+
+		ret = xenbus_grant_ring(xb_dev, sring, 1, &gref);
+		if (ret < 0) {
+			channel->u.req.ring.sring = NULL;
+			goto fail;
+		}
+
+		handler = evtchnl_interrupt_req;
+	} else {
+		ret = gnttab_grant_foreign_access(xb_dev->otherend_id,
+						  virt_to_gfn((void *)page), 0);
+		if (ret < 0)
+			goto fail;
+
+		channel->u.evt.page = (struct xensnd_event_page *)page;
+		gref = ret;
+		handler = evtchnl_interrupt_evt;
+	}
+
+	channel->gref = gref;
+
+	ret = xenbus_alloc_evtchn(xb_dev, &channel->port);
+	if (ret < 0)
+		goto fail;
+
+	ret = bind_evtchn_to_irq(channel->port);
+	if (ret < 0) {
+		dev_err(&xb_dev->dev,
+			"Failed to bind IRQ for domid %d port %d: %d\n",
+			front_info->xb_dev->otherend_id, channel->port, ret);
+		goto fail;
+	}
+
+	channel->irq = ret;
+
+	ret = request_threaded_irq(channel->irq, NULL, handler,
+				   IRQF_ONESHOT, handler_name, channel);
+	if (ret < 0) {
+		dev_err(&xb_dev->dev, "Failed to request IRQ %d: %d\n",
+			channel->irq, ret);
+		goto fail;
+	}
+
+	kfree(handler_name);
+	return 0;
+
+fail:
+	if (page)
+		free_page(page);
+	kfree(handler_name);
+	dev_err(&xb_dev->dev, "Failed to allocate ring: %d\n", ret);
+	return ret;
+}
+
+int xen_snd_front_evtchnl_create_all(struct xen_snd_front_info *front_info,
+				     int num_streams)
+{
+	struct xen_front_cfg_card *cfg = &front_info->cfg;
+	struct device *dev = &front_info->xb_dev->dev;
+	int d, ret = 0;
+
+	front_info->evt_pairs =
+			kcalloc(num_streams,
+				sizeof(struct xen_snd_front_evtchnl_pair),
+				GFP_KERNEL);
+	if (!front_info->evt_pairs)
+		return -ENOMEM;
+
+	/* Iterate over devices and their streams and create event channels. */
+	for (d = 0; d < cfg->num_pcm_instances; d++) {
+		struct xen_front_cfg_pcm_instance *pcm_instance;
+		int s, index;
+
+		pcm_instance = &cfg->pcm_instances[d];
+
+		for (s = 0; s < pcm_instance->num_streams_pb; s++) {
+			index = pcm_instance->streams_pb[s].index;
+
+			ret = evtchnl_alloc(front_info, index,
+					    &front_info->evt_pairs[index].req,
+					    EVTCHNL_TYPE_REQ);
+			if (ret < 0) {
+				dev_err(dev, "Error allocating control channel\n");
+				goto fail;
+			}
+
+			ret = evtchnl_alloc(front_info, index,
+					    &front_info->evt_pairs[index].evt,
+					    EVTCHNL_TYPE_EVT);
+			if (ret < 0) {
+				dev_err(dev, "Error allocating in-event channel\n");
+				goto fail;
+			}
+		}
+
+		for (s = 0; s < pcm_instance->num_streams_cap; s++) {
+			index = pcm_instance->streams_cap[s].index;
+
+			ret = evtchnl_alloc(front_info, index,
+					    &front_info->evt_pairs[index].req,
+					    EVTCHNL_TYPE_REQ);
+			if (ret < 0) {
+				dev_err(dev, "Error allocating control channel\n");
+				goto fail;
+			}
+
+			ret = evtchnl_alloc(front_info, index,
+					    &front_info->evt_pairs[index].evt,
+					    EVTCHNL_TYPE_EVT);
+			if (ret < 0) {
+				dev_err(dev, "Error allocating in-event channel\n");
+				goto fail;
+			}
+		}
+	}
+
+	front_info->num_evt_pairs = num_streams;
+	return 0;
+
+fail:
+	xen_snd_front_evtchnl_free_all(front_info);
+	return ret;
+}
+
+static int evtchnl_publish(struct xenbus_transaction xbt,
+			   struct xen_snd_front_evtchnl *channel,
+			   const char *path, const char *node_ring,
+			   const char *node_chnl)
+{
+	struct xenbus_device *xb_dev = channel->front_info->xb_dev;
+	int ret;
+
+	/* Write control channel ring reference. */
+	ret = xenbus_printf(xbt, path, node_ring, "%u", channel->gref);
+	if (ret < 0) {
+		dev_err(&xb_dev->dev, "Error writing ring-ref: %d\n", ret);
+		return ret;
+	}
+
+	/* Write event channel ring reference. */
+	ret = xenbus_printf(xbt, path, node_chnl, "%u", channel->port);
+	if (ret < 0) {
+		dev_err(&xb_dev->dev, "Error writing event channel: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int xen_snd_front_evtchnl_publish_all(struct xen_snd_front_info *front_info)
+{
+	struct xen_front_cfg_card *cfg = &front_info->cfg;
+	struct xenbus_transaction xbt;
+	int ret, d;
+
+again:
+	ret = xenbus_transaction_start(&xbt);
+	if (ret < 0) {
+		xenbus_dev_fatal(front_info->xb_dev, ret,
+				 "starting transaction");
+		return ret;
+	}
+
+	for (d = 0; d < cfg->num_pcm_instances; d++) {
+		struct xen_front_cfg_pcm_instance *pcm_instance;
+		int s, index;
+
+		pcm_instance = &cfg->pcm_instances[d];
+
+		for (s = 0; s < pcm_instance->num_streams_pb; s++) {
+			index = pcm_instance->streams_pb[s].index;
+
+			ret = evtchnl_publish(xbt,
+					      &front_info->evt_pairs[index].req,
+					      pcm_instance->streams_pb[s].xenstore_path,
+					      XENSND_FIELD_RING_REF,
+					      XENSND_FIELD_EVT_CHNL);
+			if (ret < 0)
+				goto fail;
+
+			ret = evtchnl_publish(xbt,
+					      &front_info->evt_pairs[index].evt,
+					      pcm_instance->streams_pb[s].xenstore_path,
+					      XENSND_FIELD_EVT_RING_REF,
+					      XENSND_FIELD_EVT_EVT_CHNL);
+			if (ret < 0)
+				goto fail;
+		}
+
+		for (s = 0; s < pcm_instance->num_streams_cap; s++) {
+			index = pcm_instance->streams_cap[s].index;
+
+			ret = evtchnl_publish(xbt,
+					      &front_info->evt_pairs[index].req,
+					      pcm_instance->streams_cap[s].xenstore_path,
+					      XENSND_FIELD_RING_REF,
+					      XENSND_FIELD_EVT_CHNL);
+			if (ret < 0)
+				goto fail;
+
+			ret = evtchnl_publish(xbt,
+					      &front_info->evt_pairs[index].evt,
+					      pcm_instance->streams_cap[s].xenstore_path,
+					      XENSND_FIELD_EVT_RING_REF,
+					      XENSND_FIELD_EVT_EVT_CHNL);
+			if (ret < 0)
+				goto fail;
+		}
+	}
+	ret = xenbus_transaction_end(xbt, 0);
+	if (ret < 0) {
+		if (ret == -EAGAIN)
+			goto again;
+
+		xenbus_dev_fatal(front_info->xb_dev, ret,
+				 "completing transaction");
+		goto fail_to_end;
+	}
+	return 0;
+fail:
+	xenbus_transaction_end(xbt, 1);
+fail_to_end:
+	xenbus_dev_fatal(front_info->xb_dev, ret, "writing XenStore");
+	return ret;
+}
+
+void xen_snd_front_evtchnl_pair_set_connected(struct xen_snd_front_evtchnl_pair *evt_pair,
+					      bool is_connected)
+{
+	enum xen_snd_front_evtchnl_state state;
+
+	if (is_connected)
+		state = EVTCHNL_STATE_CONNECTED;
+	else
+		state = EVTCHNL_STATE_DISCONNECTED;
+
+	mutex_lock(&evt_pair->req.ring_io_lock);
+	evt_pair->req.state = state;
+	mutex_unlock(&evt_pair->req.ring_io_lock);
+
+	mutex_lock(&evt_pair->evt.ring_io_lock);
+	evt_pair->evt.state = state;
+	mutex_unlock(&evt_pair->evt.ring_io_lock);
+}
+
+void xen_snd_front_evtchnl_pair_clear(struct xen_snd_front_evtchnl_pair *evt_pair)
+{
+	mutex_lock(&evt_pair->req.ring_io_lock);
+	evt_pair->req.evt_next_id = 0;
+	mutex_unlock(&evt_pair->req.ring_io_lock);
+
+	mutex_lock(&evt_pair->evt.ring_io_lock);
+	evt_pair->evt.evt_next_id = 0;
+	mutex_unlock(&evt_pair->evt.ring_io_lock);
+}
+
diff --git a/sound/xen/xen_snd_front_evtchnl.h b/sound/xen/xen_snd_front_evtchnl.h
new file mode 100644
index 000000000000..cbe51fd1ec15
--- /dev/null
+++ b/sound/xen/xen_snd_front_evtchnl.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_SND_FRONT_EVTCHNL_H
+#define __XEN_SND_FRONT_EVTCHNL_H
+
+#include <xen/interface/io/sndif.h>
+
+struct xen_snd_front_info;
+
+#ifndef GRANT_INVALID_REF
+/*
+ * FIXME: usage of grant reference 0 as invalid grant reference:
+ * grant reference 0 is valid, but never exposed to a PV driver,
+ * because of the fact it is already in use/reserved by the PV console.
+ */
+#define GRANT_INVALID_REF	0
+#endif
+
+/* Timeout in ms to wait for backend to respond. */
+#define VSND_WAIT_BACK_MS	3000
+
+enum xen_snd_front_evtchnl_state {
+	EVTCHNL_STATE_DISCONNECTED,
+	EVTCHNL_STATE_CONNECTED,
+};
+
+enum xen_snd_front_evtchnl_type {
+	EVTCHNL_TYPE_REQ,
+	EVTCHNL_TYPE_EVT,
+};
+
+struct xen_snd_front_evtchnl {
+	struct xen_snd_front_info *front_info;
+	int gref;
+	int port;
+	int irq;
+	int index;
+	/* State of the event channel. */
+	enum xen_snd_front_evtchnl_state state;
+	enum xen_snd_front_evtchnl_type type;
+	/* Either response id or incoming event id. */
+	u16 evt_id;
+	/* Next request id or next expected event id. */
+	u16 evt_next_id;
+	/* Shared ring access lock. */
+	struct mutex ring_io_lock;
+	union {
+		struct {
+			struct xen_sndif_front_ring ring;
+			struct completion completion;
+			/* Serializer for backend IO: request/response. */
+			struct mutex req_io_lock;
+
+			/* Latest response status. */
+			int resp_status;
+			union {
+				struct xensnd_query_hw_param hw_param;
+			} resp;
+		} req;
+		struct {
+			struct xensnd_event_page *page;
+			/* This is needed to handle XENSND_EVT_CUR_POS event. */
+			struct snd_pcm_substream *substream;
+		} evt;
+	} u;
+};
+
+struct xen_snd_front_evtchnl_pair {
+	struct xen_snd_front_evtchnl req;
+	struct xen_snd_front_evtchnl evt;
+};
+
+int xen_snd_front_evtchnl_create_all(struct xen_snd_front_info *front_info,
+				     int num_streams);
+
+void xen_snd_front_evtchnl_free_all(struct xen_snd_front_info *front_info);
+
+int xen_snd_front_evtchnl_publish_all(struct xen_snd_front_info *front_info);
+
+void xen_snd_front_evtchnl_flush(struct xen_snd_front_evtchnl *evtchnl);
+
+void xen_snd_front_evtchnl_pair_set_connected(struct xen_snd_front_evtchnl_pair *evt_pair,
+					      bool is_connected);
+
+void xen_snd_front_evtchnl_pair_clear(struct xen_snd_front_evtchnl_pair *evt_pair);
+
+#endif /* __XEN_SND_FRONT_EVTCHNL_H */
diff --git a/sound/xen/xen_snd_front_shbuf.c b/sound/xen/xen_snd_front_shbuf.c
new file mode 100644
index 000000000000..07ac176a41ba
--- /dev/null
+++ b/sound/xen/xen_snd_front_shbuf.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#include <linux/kernel.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+
+#include "xen_snd_front_shbuf.h"
+
+grant_ref_t xen_snd_front_shbuf_get_dir_start(struct xen_snd_front_shbuf *buf)
+{
+	if (!buf->grefs)
+		return GRANT_INVALID_REF;
+
+	return buf->grefs[0];
+}
+
+void xen_snd_front_shbuf_clear(struct xen_snd_front_shbuf *buf)
+{
+	memset(buf, 0, sizeof(*buf));
+}
+
+void xen_snd_front_shbuf_free(struct xen_snd_front_shbuf *buf)
+{
+	int i;
+
+	if (buf->grefs) {
+		for (i = 0; i < buf->num_grefs; i++)
+			if (buf->grefs[i] != GRANT_INVALID_REF)
+				gnttab_end_foreign_access(buf->grefs[i],
+							  0, 0UL);
+		kfree(buf->grefs);
+	}
+	kfree(buf->directory);
+	free_pages_exact(buf->buffer, buf->buffer_sz);
+	xen_snd_front_shbuf_clear(buf);
+}
+
+/*
+ * number of grant references a page can hold with respect to the
+ * xensnd_page_directory header
+ */
+#define XENSND_NUM_GREFS_PER_PAGE ((XEN_PAGE_SIZE - \
+		offsetof(struct xensnd_page_directory, gref)) / \
+		sizeof(grant_ref_t))
+
+static void fill_page_dir(struct xen_snd_front_shbuf *buf,
+			  int num_pages_dir)
+{
+	struct xensnd_page_directory *page_dir;
+	unsigned char *ptr;
+	int i, cur_gref, grefs_left, to_copy;
+
+	ptr = buf->directory;
+	grefs_left = buf->num_grefs - num_pages_dir;
+	/*
+	 * skip grant references at the beginning, they are for pages granted
+	 * for the page directory itself
+	 */
+	cur_gref = num_pages_dir;
+	for (i = 0; i < num_pages_dir; i++) {
+		page_dir = (struct xensnd_page_directory *)ptr;
+		if (grefs_left <= XENSND_NUM_GREFS_PER_PAGE) {
+			to_copy = grefs_left;
+			page_dir->gref_dir_next_page = GRANT_INVALID_REF;
+		} else {
+			to_copy = XENSND_NUM_GREFS_PER_PAGE;
+			page_dir->gref_dir_next_page = buf->grefs[i + 1];
+		}
+
+		memcpy(&page_dir->gref, &buf->grefs[cur_gref],
+		       to_copy * sizeof(grant_ref_t));
+
+		ptr += XEN_PAGE_SIZE;
+		grefs_left -= to_copy;
+		cur_gref += to_copy;
+	}
+}
+
+static int grant_references(struct xenbus_device *xb_dev,
+			    struct xen_snd_front_shbuf *buf,
+			    int num_pages_dir, int num_pages_buffer,
+			    int num_grefs)
+{
+	grant_ref_t priv_gref_head;
+	unsigned long frame;
+	int ret, i, j, cur_ref;
+	int otherend_id;
+
+	ret = gnttab_alloc_grant_references(num_grefs, &priv_gref_head);
+	if (ret)
+		return ret;
+
+	buf->num_grefs = num_grefs;
+	otherend_id = xb_dev->otherend_id;
+	j = 0;
+
+	for (i = 0; i < num_pages_dir; i++) {
+		cur_ref = gnttab_claim_grant_reference(&priv_gref_head);
+		if (cur_ref < 0) {
+			ret = cur_ref;
+			goto fail;
+		}
+
+		frame = xen_page_to_gfn(virt_to_page(buf->directory +
+						     XEN_PAGE_SIZE * i));
+		gnttab_grant_foreign_access_ref(cur_ref, otherend_id, frame, 0);
+		buf->grefs[j++] = cur_ref;
+	}
+
+	for (i = 0; i < num_pages_buffer; i++) {
+		cur_ref = gnttab_claim_grant_reference(&priv_gref_head);
+		if (cur_ref < 0) {
+			ret = cur_ref;
+			goto fail;
+		}
+
+		frame = xen_page_to_gfn(virt_to_page(buf->buffer +
+						     XEN_PAGE_SIZE * i));
+		gnttab_grant_foreign_access_ref(cur_ref, otherend_id, frame, 0);
+		buf->grefs[j++] = cur_ref;
+	}
+
+	gnttab_free_grant_references(priv_gref_head);
+	fill_page_dir(buf, num_pages_dir);
+	return 0;
+
+fail:
+	gnttab_free_grant_references(priv_gref_head);
+	return ret;
+}
+
+static int alloc_int_buffers(struct xen_snd_front_shbuf *buf,
+			     int num_pages_dir, int num_pages_buffer,
+			     int num_grefs)
+{
+	buf->grefs = kcalloc(num_grefs, sizeof(*buf->grefs), GFP_KERNEL);
+	if (!buf->grefs)
+		return -ENOMEM;
+
+	buf->directory = kcalloc(num_pages_dir, XEN_PAGE_SIZE, GFP_KERNEL);
+	if (!buf->directory)
+		goto fail;
+
+	buf->buffer_sz = num_pages_buffer * XEN_PAGE_SIZE;
+	buf->buffer = alloc_pages_exact(buf->buffer_sz, GFP_KERNEL);
+	if (!buf->buffer)
+		goto fail;
+
+	return 0;
+
+fail:
+	kfree(buf->grefs);
+	buf->grefs = NULL;
+	kfree(buf->directory);
+	buf->directory = NULL;
+	return -ENOMEM;
+}
+
+int xen_snd_front_shbuf_alloc(struct xenbus_device *xb_dev,
+			      struct xen_snd_front_shbuf *buf,
+			      unsigned int buffer_sz)
+{
+	int num_pages_buffer, num_pages_dir, num_grefs;
+	int ret;
+
+	xen_snd_front_shbuf_clear(buf);
+
+	num_pages_buffer = DIV_ROUND_UP(buffer_sz, XEN_PAGE_SIZE);
+	/* number of pages the page directory consumes itself */
+	num_pages_dir = DIV_ROUND_UP(num_pages_buffer,
+				     XENSND_NUM_GREFS_PER_PAGE);
+	num_grefs = num_pages_buffer + num_pages_dir;
+
+	ret = alloc_int_buffers(buf, num_pages_dir,
+				num_pages_buffer, num_grefs);
+	if (ret < 0)
+		return ret;
+
+	ret = grant_references(xb_dev, buf, num_pages_dir, num_pages_buffer,
+			       num_grefs);
+	if (ret < 0)
+		return ret;
+
+	fill_page_dir(buf, num_pages_dir);
+	return 0;
+}
diff --git a/sound/xen/xen_snd_front_shbuf.h b/sound/xen/xen_snd_front_shbuf.h
new file mode 100644
index 000000000000..d28e97c47b2c
--- /dev/null
+++ b/sound/xen/xen_snd_front_shbuf.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+/*
+ * Xen para-virtual sound device
+ *
+ * Copyright (C) 2016-2018 EPAM Systems Inc.
+ *
+ * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
+ */
+
+#ifndef __XEN_SND_FRONT_SHBUF_H
+#define __XEN_SND_FRONT_SHBUF_H
+
+#include <xen/grant_table.h>
+
+#include "xen_snd_front_evtchnl.h"
+
+struct xen_snd_front_shbuf {
+	int num_grefs;
+	grant_ref_t *grefs;
+	u8 *directory;
+	u8 *buffer;
+	size_t buffer_sz;
+};
+
+grant_ref_t xen_snd_front_shbuf_get_dir_start(struct xen_snd_front_shbuf *buf);
+
+int xen_snd_front_shbuf_alloc(struct xenbus_device *xb_dev,
+			      struct xen_snd_front_shbuf *buf,
+			      unsigned int buffer_sz);
+
+void xen_snd_front_shbuf_clear(struct xen_snd_front_shbuf *buf);
+
+void xen_snd_front_shbuf_free(struct xen_snd_front_shbuf *buf);
+
+#endif /* __XEN_SND_FRONT_SHBUF_H */
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 6edd177bb1c7..caae4843cb70 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -135,6 +135,15 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_CRM_SHIFT		7
 #define KVM_REG_ARM_32_CRN_MASK		0x0000000000007800
 #define KVM_REG_ARM_32_CRN_SHIFT	11
+/*
+ * For KVM currently all guest registers are nonsecure, but we reserve a bit
+ * in the encoding to distinguish secure from nonsecure for AArch32 system
+ * registers that are banked by security. This is 1 for the secure banked
+ * register, and 0 for the nonsecure banked register or if the register is
+ * not banked by security.
+ */
+#define KVM_REG_ARM_SECURE_MASK	0x0000000010000000
+#define KVM_REG_ARM_SECURE_SHIFT	28
 
 #define ARM_CP15_REG_SHIFT_MASK(x,n) \
 	(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)
@@ -186,6 +195,12 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_VFP_FPINST		0x1009
 #define KVM_REG_ARM_VFP_FPINST2		0x100A
 
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r)		(KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+					 KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 9abbf3044654..04b3256f8e6d 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -206,6 +206,12 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
 
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r)		(KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+					 KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d554c11e01ff..fb00a2fca990 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
-
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
@@ -207,13 +206,19 @@
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
-
+#define X86_FEATURE_MSR_SPEC_CTRL	( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
 #define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
-
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* "" AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -274,9 +279,10 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -320,6 +326,7 @@
 #define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
+#define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
@@ -333,6 +340,7 @@
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*
  * BUG word(s)
@@ -362,5 +370,6 @@
 #define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index fb3a6de7440b..6847d85400a8 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -53,12 +53,6 @@
 # define NEED_MOVBE	0
 #endif
 
-#ifdef CONFIG_X86_5LEVEL
-# define NEED_LA57	(1<<(X86_FEATURE_LA57 & 31))
-#else
-# define NEED_LA57	0
-#endif
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT
 /* Paravirtualized systems may not have PSE or PGE available */
@@ -104,7 +98,7 @@
 #define REQUIRED_MASK13	0
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	(NEED_LA57)
+#define REQUIRED_MASK16	0
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK18	0
 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index f3a960488eae..c535c2fdea13 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -354,8 +354,25 @@ struct kvm_xcrs {
 	__u64 padding[16];
 };
 
-/* definition of registers in kvm_run */
+#define KVM_SYNC_X86_REGS      (1UL << 0)
+#define KVM_SYNC_X86_SREGS     (1UL << 1)
+#define KVM_SYNC_X86_EVENTS    (1UL << 2)
+
+#define KVM_SYNC_X86_VALID_FIELDS \
+	(KVM_SYNC_X86_REGS| \
+	 KVM_SYNC_X86_SREGS| \
+	 KVM_SYNC_X86_EVENTS)
+
+/* kvm_sync_regs struct included by kvm_run struct */
 struct kvm_sync_regs {
+	/* Members of this structure are potentially malicious.
+	 * Care must be taken by code reading, esp. interpreting,
+	 * data fields from them inside KVM to prevent TOCTOU and
+	 * double-fetch types of vulnerabilities.
+	 */
+	struct kvm_regs regs;
+	struct kvm_sregs sregs;
+	struct kvm_vcpu_events events;
 };
 
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 1ea545965ee3..53b60ad452f5 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -76,6 +76,8 @@ $(OUTPUT)bpf_asm: $(OUTPUT)bpf_asm.o $(OUTPUT)bpf_exp.yacc.o $(OUTPUT)bpf_exp.le
 	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^
 
 $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
 
 clean: bpftool_clean
 	$(call QUIET_CLEAN, bpf-progs)
diff --git a/tools/bpf/bpf_dbg.c b/tools/bpf/bpf_dbg.c
index 4f254bcc4423..61b9aa5d6415 100644
--- a/tools/bpf/bpf_dbg.c
+++ b/tools/bpf/bpf_dbg.c
@@ -1063,7 +1063,7 @@ static int cmd_load_pcap(char *file)
 
 static int cmd_load(char *arg)
 {
-	char *subcmd, *cont, *tmp = strdup(arg);
+	char *subcmd, *cont = NULL, *tmp = strdup(arg);
 	int ret = CMD_OK;
 
 	subcmd = strtok_r(tmp, " ", &cont);
@@ -1073,7 +1073,10 @@ static int cmd_load(char *arg)
 		bpf_reset();
 		bpf_reset_breakpoints();
 
-		ret = cmd_load_bpf(cont);
+		if (!cont)
+			ret = CMD_ERR;
+		else
+			ret = cmd_load_bpf(cont);
 	} else if (matches(subcmd, "pcap") == 0) {
 		ret = cmd_load_pcap(cont);
 	} else {
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index a3a4427441bf..70fe61295733 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -21,6 +21,9 @@
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
+#ifndef __pure
+#define  __pure		__attribute__((pure))
+#endif
 #define  noinline	__attribute__((noinline))
 #ifndef __packed
 #define __packed	__attribute__((packed))
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 04e32f965ad7..1827c2f973f9 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -151,11 +151,21 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * required ordering.
  */
 
-#define READ_ONCE(x) \
-	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
-
-#define WRITE_ONCE(x, val) \
-	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+#define READ_ONCE(x)					\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__c = { 0 } };			\
+	__read_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+#define WRITE_ONCE(x, val)				\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__val = (val) }; 			\
+	__write_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
 
 
 #ifndef __fallthrough
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index edfeaba95429..a1a959ba24ff 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _LINUX_CORESIGHT_PMU_H
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index b21b586b9854..1738c0391da4 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -6,8 +6,9 @@
 #include <stdbool.h>
 
 #define spinlock_t		pthread_mutex_t
-#define DEFINE_SPINLOCK(x)	pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER;
+#define DEFINE_SPINLOCK(x)	pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER
 #define __SPIN_LOCK_UNLOCKED(x)	(pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER
+#define spin_lock_init(x)      pthread_mutex_init(x, NULL)
 
 #define spin_lock_irqsave(x, f)		(void)f, pthread_mutex_lock(x)
 #define spin_unlock_irqrestore(x, f)	(void)f, pthread_mutex_unlock(x)
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index f8b134f5608f..e7ee32861d51 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -27,6 +27,9 @@
 # define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
 #endif
 
+/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */
+#define MAP_FIXED_NOREPLACE	0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
+
 /*
  * Flags for mlock
  */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9d07465023a2..8c317737ba3f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -864,6 +864,7 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_set_tunnel_key flags. */
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
+#define BPF_F_SEQ_NUMBER		(1ULL << 3)
 
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
@@ -1016,6 +1017,7 @@ struct bpf_prog_info {
 	__aligned_u64 map_ids;
 	char name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
+	__u32 :32;
 	__u64 netns_dev;
 	__u64 netns_ino;
 } __attribute__((aligned(8)));
@@ -1029,6 +1031,7 @@ struct bpf_map_info {
 	__u32 map_flags;
 	char  name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
+	__u32 :32;
 	__u64 netns_dev;
 	__u64 netns_ino;
 } __attribute__((aligned(8)));
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 6d9447700e18..68699f654118 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -941,4 +941,43 @@ enum {
 	IFLA_EVENT_BONDING_OPTIONS,	/* change in bonding options */
 };
 
+/* tun section */
+
+enum {
+	IFLA_TUN_UNSPEC,
+	IFLA_TUN_OWNER,
+	IFLA_TUN_GROUP,
+	IFLA_TUN_TYPE,
+	IFLA_TUN_PI,
+	IFLA_TUN_VNET_HDR,
+	IFLA_TUN_PERSIST,
+	IFLA_TUN_MULTI_QUEUE,
+	IFLA_TUN_NUM_QUEUES,
+	IFLA_TUN_NUM_DISABLED_QUEUES,
+	__IFLA_TUN_MAX,
+};
+
+#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1)
+
+/* rmnet section */
+
+#define RMNET_FLAGS_INGRESS_DEAGGREGATION         (1U << 0)
+#define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+
+enum {
+	IFLA_RMNET_UNSPEC,
+	IFLA_RMNET_MUX_ID,
+	IFLA_RMNET_FLAGS,
+	__IFLA_RMNET_MAX,
+};
+
+#define IFLA_RMNET_MAX	(__IFLA_RMNET_MAX - 1)
+
+struct ifla_rmnet_flags {
+	__u32	flags;
+	__u32	mask;
+};
+
 #endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 6b89f87db200..b02c41e53d56 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -396,6 +396,10 @@ struct kvm_run {
 		char padding[256];
 	};
 
+	/* 2048 is the size of the char array used to bound/pad the size
+	 * of the union that holds sync regs.
+	 */
+	#define SYNC_REGS_SIZE_BYTES 2048
 	/*
 	 * shared registers between kvm and userspace.
 	 * kvm_valid_regs specifies the register classes set by the host
@@ -407,7 +411,7 @@ struct kvm_run {
 	__u64 kvm_dirty_regs;
 	union {
 		struct kvm_sync_regs regs;
-		char padding[2048];
+		char padding[SYNC_REGS_SIZE_BYTES];
 	} s;
 };
 
@@ -672,6 +676,13 @@ struct kvm_ioeventfd {
 	__u8  pad[36];
 };
 
+#define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
+                                              KVM_X86_DISABLE_EXITS_HTL | \
+                                              KVM_X86_DISABLE_EXITS_PAUSE)
+
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
 	/* in */
@@ -936,6 +947,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_GET_CPU_CHAR 151
 #define KVM_CAP_S390_BPB 152
 #define KVM_CAP_GET_MSR_FEATURES 153
+#define KVM_CAP_HYPERV_EVENTFD 154
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1375,6 +1387,10 @@ struct kvm_enc_region {
 #define KVM_MEMORY_ENCRYPT_REG_REGION    _IOR(KVMIO, 0xbb, struct kvm_enc_region)
 #define KVM_MEMORY_ENCRYPT_UNREG_REGION  _IOR(KVMIO, 0xbc, struct kvm_enc_region)
 
+/* Available with KVM_CAP_HYPERV_EVENTFD */
+#define KVM_HYPERV_EVENTFD        _IOW(KVMIO,  0xbd, struct kvm_hyperv_eventfd)
+
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1515,4 +1531,14 @@ struct kvm_assigned_msix_entry {
 #define KVM_ARM_DEV_EL1_PTIMER		(1 << 1)
 #define KVM_ARM_DEV_PMU			(1 << 2)
 
+struct kvm_hyperv_eventfd {
+	__u32 conn_id;
+	__s32 fd;
+	__u32 flags;
+	__u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 912b85b52344..b8e288a1f740 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -650,11 +650,23 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ *   PERF_RECORD_MISC_EXACT_IP           - PERF_RECORD_SAMPLE of precise events
+ *   PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ *   Indicates that the content of PERF_SAMPLE_IP points to
+ *   the actual instruction that triggered the event. See also
+ *   perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ *   Indicates that thread was preempted in TASK_RUNNING state.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT	(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index af5f8c2df87a..db9f15f5db04 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -207,4 +207,16 @@ struct prctl_mm_map {
 # define PR_SVE_VL_LEN_MASK		0xffff
 # define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
 
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL		52
+#define PR_SET_SPECULATION_CTRL		53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS		0
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED		0
+# define PR_SPEC_PRCTL			(1UL << 0)
+# define PR_SPEC_ENABLE			(1UL << 1)
+# define PR_SPEC_DISABLE		(1UL << 2)
+# define PR_SPEC_FORCE_DISABLE		(1UL << 3)
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 07d61583fd02..ed0a120d4f08 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -242,6 +242,7 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_DSD_U16_BE	((__force snd_pcm_format_t) 51) /* DSD, 2-byte samples DSD (x16), big endian */
 #define	SNDRV_PCM_FORMAT_DSD_U32_BE	((__force snd_pcm_format_t) 52) /* DSD, 4-byte samples DSD (x32), big endian */
 #define	SNDRV_PCM_FORMAT_LAST		SNDRV_PCM_FORMAT_DSD_U32_BE
+#define	SNDRV_PCM_FORMAT_FIRST		SNDRV_PCM_FORMAT_S8
 
 #ifdef SNDRV_LITTLE_ENDIAN
 #define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_LE
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 7b7fd0b18551..120037496f77 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -13,11 +13,9 @@
 
 #include "tracing_path.h"
 
-
-char tracing_mnt[PATH_MAX]         = "/sys/kernel/debug";
-char tracing_path[PATH_MAX]        = "/sys/kernel/debug/tracing";
-char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
-
+static char tracing_mnt[PATH_MAX]  = "/sys/kernel/debug";
+static char tracing_path[PATH_MAX]        = "/sys/kernel/debug/tracing";
+static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
 
 static void __tracing_path_set(const char *tracing, const char *mountpoint)
 {
@@ -76,7 +74,7 @@ char *get_tracing_file(const char *name)
 {
 	char *file;
 
-	if (asprintf(&file, "%s/%s", tracing_path, name) < 0)
+	if (asprintf(&file, "%s/%s", tracing_path_mount(), name) < 0)
 		return NULL;
 
 	return file;
@@ -87,6 +85,34 @@ void put_tracing_file(char *file)
 	free(file);
 }
 
+char *get_events_file(const char *name)
+{
+	char *file;
+
+	if (asprintf(&file, "%s/events/%s", tracing_path_mount(), name) < 0)
+		return NULL;
+
+	return file;
+}
+
+void put_events_file(char *file)
+{
+	free(file);
+}
+
+DIR *tracing_events__opendir(void)
+{
+	DIR *dir = NULL;
+	char *path = get_tracing_file("events");
+
+	if (path) {
+		dir = opendir(path);
+		put_events_file(path);
+	}
+
+	return dir;
+}
+
 int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 				   const char *sys, const char *name)
 {
@@ -129,7 +155,7 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 		snprintf(buf, size,
 			 "Error:\tNo permissions to read %s/%s\n"
 			 "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
-			 tracing_events_path, filename, tracing_mnt);
+			 tracing_events_path, filename, tracing_path_mount());
 	}
 		break;
 	default:
diff --git a/tools/lib/api/fs/tracing_path.h b/tools/lib/api/fs/tracing_path.h
index 0066f06cc381..a19136b086dc 100644
--- a/tools/lib/api/fs/tracing_path.h
+++ b/tools/lib/api/fs/tracing_path.h
@@ -3,9 +3,9 @@
 #define __API_FS_TRACING_PATH_H
 
 #include <linux/types.h>
+#include <dirent.h>
 
-extern char tracing_path[];
-extern char tracing_events_path[];
+DIR *tracing_events__opendir(void);
 
 void tracing_path_set(const char *mountpoint);
 const char *tracing_path_mount(void);
@@ -13,5 +13,10 @@ const char *tracing_path_mount(void);
 char *get_tracing_file(const char *name);
 void put_tracing_file(char *file);
 
+char *get_events_file(const char *name);
+void put_events_file(char *file);
+
+#define zput_events_file(ptr) ({ free(*ptr); *ptr = NULL; })
+
 int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name);
 #endif /* __API_FS_TRACING_PATH_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5922443063f0..0f9f06df49bc 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2035,7 +2035,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 		return -EINVAL;
 
 	obj = bpf_object__open(attr->file);
-	if (IS_ERR(obj))
+	if (IS_ERR_OR_NULL(obj))
 		return -ENOENT;
 
 	bpf_object__for_each_program(prog, obj) {
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index f6a1babcbac4..cb7154eccbdc 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -433,7 +433,7 @@ match:
 
 	if (ambiguous_option) {
 		 fprintf(stderr,
-			 " Error: Ambiguous option: %s (could be --%s%s or --%s%s)",
+			 " Error: Ambiguous option: %s (could be --%s%s or --%s%s)\n",
 			 arg,
 			 (ambiguous_flags & OPT_UNSET) ?  "no-" : "",
 			 ambiguous_option->long_name,
@@ -458,7 +458,7 @@ static void check_typos(const char *arg, const struct option *options)
 		return;
 
 	if (strstarts(arg, "no-")) {
-		fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
+		fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg);
 		exit(129);
 	}
 
@@ -466,7 +466,7 @@ static void check_typos(const char *arg, const struct option *options)
 		if (!options->long_name)
 			continue;
 		if (strstarts(options->long_name, arg)) {
-			fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
+			fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg);
 			exit(129);
 		}
 	}
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index 689b6a130dd7..96d830545bbb 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -10,6 +10,12 @@ u8 kallsyms2elf_type(char type)
 	return (type == 't' || type == 'w') ? STT_FUNC : STT_OBJECT;
 }
 
+bool kallsyms__is_function(char symbol_type)
+{
+	symbol_type = toupper(symbol_type);
+	return symbol_type == 'T' || symbol_type == 'W';
+}
+
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start))
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
index bc40101d72c1..72ab9870454b 100644
--- a/tools/lib/symbol/kallsyms.h
+++ b/tools/lib/symbol/kallsyms.h
@@ -20,6 +20,8 @@ static inline u8 kallsyms2elf_binding(char type)
 
 u8 kallsyms2elf_type(char type);
 
+bool kallsyms__is_function(char symbol_type);
+
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start));
diff --git a/tools/memory-model/Documentation/cheatsheet.txt b/tools/memory-model/Documentation/cheatsheet.txt
index 956b1ae4aafb..33ba98d72b16 100644
--- a/tools/memory-model/Documentation/cheatsheet.txt
+++ b/tools/memory-model/Documentation/cheatsheet.txt
@@ -1,6 +1,6 @@
                                   Prior Operation     Subsequent Operation
                                   ---------------  ---------------------------
-                               C  Self  R  W  RWM  Self  R  W  DR  DW  RMW  SV
+                               C  Self  R  W  RMW  Self  R  W  DR  DW  RMW  SV
                               --  ----  -  -  ---  ----  -  -  --  --  ---  --
 
 Store, e.g., WRITE_ONCE()            Y                                       Y
@@ -14,7 +14,7 @@ smp_wmb()                                  Y    W           Y       Y    W
 smp_mb() & synchronize_rcu()  CP        Y  Y    Y        Y  Y   Y   Y    Y
 Successful full non-void RMW  CP     Y  Y  Y    Y     Y  Y  Y   Y   Y    Y   Y
 smp_mb__before_atomic()       CP        Y  Y    Y        a  a   a   a    Y
-smp_mb__after_atomic()        CP        a  a    Y        Y  Y   Y   Y
+smp_mb__after_atomic()        CP        a  a    Y        Y  Y   Y   Y    Y
 
 
 Key:	C:	Ordering is cumulative
@@ -26,4 +26,5 @@ Key:	C:	Ordering is cumulative
 	DR:	Dependent read (address dependency)
 	DW:	Dependent write (address, data, or control dependency)
 	RMW:	Atomic read-modify-write operation
-	SV	Same-variable access
+	SELF:	Orders self, as opposed to accesses before and/or after
+	SV:	Orders later accesses to the same variable
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index a727c82bd434..1b09f3175a1f 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -27,7 +27,7 @@ Explanation of the Linux-Kernel Memory Consistency Model
   19. AND THEN THERE WAS ALPHA
   20. THE HAPPENS-BEFORE RELATION: hb
   21. THE PROPAGATES-BEFORE RELATION: pb
-  22. RCU RELATIONS: link, gp-link, rscs-link, and rcu-path
+  22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
   23. ODDS AND ENDS
 
 
@@ -1451,8 +1451,8 @@ they execute means that it cannot have cycles.  This requirement is
 the content of the LKMM's "propagation" axiom.
 
 
-RCU RELATIONS: link, gp-link, rscs-link, and rcu-path
------------------------------------------------------
+RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
+----------------------------------------------------
 
 RCU (Read-Copy-Update) is a powerful synchronization mechanism.  It
 rests on two concepts: grace periods and read-side critical sections.
@@ -1509,8 +1509,8 @@ y, which occurs before the end of the critical section, did not
 propagate to P1 before the end of the grace period, violating the
 Guarantee.
 
-In the kernel's implementations of RCU, the business about stores
-propagating to every CPU is realized by placing strong fences at
+In the kernel's implementations of RCU, the requirements for stores
+to propagate to every CPU are fulfilled by placing strong fences at
 suitable places in the RCU-related code.  Thus, if a critical section
 starts before a grace period does then the critical section's CPU will
 execute an smp_mb() fence after the end of the critical section and
@@ -1523,72 +1523,124 @@ executes.
 What exactly do we mean by saying that a critical section "starts
 before" or "ends after" a grace period?  Some aspects of the meaning
 are pretty obvious, as in the example above, but the details aren't
-entirely clear.  The LKMM formalizes this notion by means of a
-relation with the unfortunately generic name "link".  It is a very
-general relation; among other things, X ->link Z includes cases where
-X happens-before or is equal to some event Y which is equal to or
-comes before Z in the coherence order.  Taking Y = Z, this says that
-X ->rfe Z implies X ->link Z, and taking Y = X, it says that X ->fr Z
-and X ->co Z each imply X ->link Z.
-
-The formal definition of the link relation is more than a little
+entirely clear.  The LKMM formalizes this notion by means of the
+rcu-link relation.  rcu-link encompasses a very general notion of
+"before": Among other things, X ->rcu-link Z includes cases where X
+happens-before or is equal to some event Y which is equal to or comes
+before Z in the coherence order.  When Y = Z this says that X ->rfe Z
+implies X ->rcu-link Z.  In addition, when Y = X it says that X ->fr Z
+and X ->co Z each imply X ->rcu-link Z.
+
+The formal definition of the rcu-link relation is more than a little
 obscure, and we won't give it here.  It is closely related to the pb
 relation, and the details don't matter unless you want to comb through
 a somewhat lengthy formal proof.  Pretty much all you need to know
-about link is the information in the preceding paragraph.
-
-The LKMM goes on to define the gp-link and rscs-link relations.  They
-bring grace periods and read-side critical sections into the picture,
-in the following way:
-
-	E ->gp-link F means there is a synchronize_rcu() fence event S
-	and an event X such that E ->po S, either S ->po X or S = X,
-	and X ->link F.  In other words, E and F are connected by a
-	grace period followed by an instance of link.
-
-	E ->rscs-link F means there is a critical section delimited by
-	an rcu_read_lock() fence L and an rcu_read_unlock() fence U,
-	and an event X such that E ->po U, either L ->po X or L = X,
-	and X ->link F.  Roughly speaking, this says that some event
-	in the same critical section as E is connected by link to F.
-
-If we think of the link relation as standing for an extended "before",
-then E ->gp-link F says that E executes before a grace period which
-ends before F executes.  (In fact it says more than this, because it
-includes cases where E executes before a grace period and some store
-propagates to F's CPU before F executes and doesn't propagate to some
-other CPU until after the grace period ends.)  Similarly,
-E ->rscs-link F says that E is part of (or before the start of) a
-critical section which starts before F executes.
+about rcu-link is the information in the preceding paragraph.
+
+The LKMM also defines the gp and rscs relations.  They bring grace
+periods and read-side critical sections into the picture, in the
+following way:
+
+	E ->gp F means there is a synchronize_rcu() fence event S such
+	that E ->po S and either S ->po F or S = F.  In simple terms,
+	there is a grace period po-between E and F.
+
+	E ->rscs F means there is a critical section delimited by an
+	rcu_read_lock() fence L and an rcu_read_unlock() fence U, such
+	that E ->po U and either L ->po F or L = F.  You can think of
+	this as saying that E and F are in the same critical section
+	(in fact, it also allows E to be po-before the start of the
+	critical section and F to be po-after the end).
+
+If we think of the rcu-link relation as standing for an extended
+"before", then X ->gp Y ->rcu-link Z says that X executes before a
+grace period which ends before Z executes.  (In fact it covers more
+than this, because it also includes cases where X executes before a
+grace period and some store propagates to Z's CPU before Z executes
+but doesn't propagate to some other CPU until after the grace period
+ends.)  Similarly, X ->rscs Y ->rcu-link Z says that X is part of (or
+before the start of) a critical section which starts before Z
+executes.
+
+The LKMM goes on to define the rcu-fence relation as a sequence of gp
+and rscs links separated by rcu-link links, in which the number of gp
+links is >= the number of rscs links.  For example:
+
+	X ->gp Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+
+would imply that X ->rcu-fence V, because this sequence contains two
+gp links and only one rscs link.  (It also implies that X ->rcu-fence T
+and Z ->rcu-fence V.)  On the other hand:
+
+	X ->rscs Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+
+does not imply X ->rcu-fence V, because the sequence contains only
+one gp link but two rscs links.
+
+The rcu-fence relation is important because the Grace Period Guarantee
+means that rcu-fence acts kind of like a strong fence.  In particular,
+if W is a write and we have W ->rcu-fence Z, the Guarantee says that W
+will propagate to every CPU before Z executes.
+
+To prove this in full generality requires some intellectual effort.
+We'll consider just a very simple case:
+
+	W ->gp X ->rcu-link Y ->rscs Z.
+
+This formula means that there is a grace period G and a critical
+section C such that:
+
+	1. W is po-before G;
+
+	2. X is equal to or po-after G;
+
+	3. X comes "before" Y in some sense;
+
+	4. Y is po-before the end of C;
+
+	5. Z is equal to or po-after the start of C.
+
+From 2 - 4 we deduce that the grace period G ends before the critical
+section C.  Then the second part of the Grace Period Guarantee says
+not only that G starts before C does, but also that W (which executes
+on G's CPU before G starts) must propagate to every CPU before C
+starts.  In particular, W propagates to every CPU before Z executes
+(or finishes executing, in the case where Z is equal to the
+rcu_read_lock() fence event which starts C.)  This sort of reasoning
+can be expanded to handle all the situations covered by rcu-fence.
+
+Finally, the LKMM defines the RCU-before (rb) relation in terms of
+rcu-fence.  This is done in essentially the same way as the pb
+relation was defined in terms of strong-fence.  We will omit the
+details; the end result is that E ->rb F implies E must execute before
+F, just as E ->pb F does (and for much the same reasons).
 
 Putting this all together, the LKMM expresses the Grace Period
-Guarantee by requiring that there are no cycles consisting of gp-link
-and rscs-link connections in which the number of gp-link instances is
->= the number of rscs-link instances.  It does this by defining the
-rcu-path relation to link events E and F whenever it is possible to
-pass from E to F by a sequence of gp-link and rscs-link connections
-with at least as many of the former as the latter.  The LKMM's "rcu"
-axiom then says that there are no events E such that E ->rcu-path E.
-
-Justifying this axiom takes some intellectual effort, but it is in
-fact a valid formalization of the Grace Period Guarantee.  We won't
-attempt to go through the detailed argument, but the following
-analysis gives a taste of what is involved.  Suppose we have a
-violation of the first part of the Guarantee: A critical section
-starts before a grace period, and some store propagates to the
-critical section's CPU before the end of the critical section but
-doesn't propagate to some other CPU until after the end of the grace
-period.
+Guarantee by requiring that the rb relation does not contain a cycle.
+Equivalently, this "rcu" axiom requires that there are no events E and
+F with E ->rcu-link F ->rcu-fence E.  Or to put it a third way, the
+axiom requires that there are no cycles consisting of gp and rscs
+alternating with rcu-link, where the number of gp links is >= the
+number of rscs links.
+
+Justifying the axiom isn't easy, but it is in fact a valid
+formalization of the Grace Period Guarantee.  We won't attempt to go
+through the detailed argument, but the following analysis gives a
+taste of what is involved.  Suppose we have a violation of the first
+part of the Guarantee: A critical section starts before a grace
+period, and some store propagates to the critical section's CPU before
+the end of the critical section but doesn't propagate to some other
+CPU until after the end of the grace period.
 
 Putting symbols to these ideas, let L and U be the rcu_read_lock() and
 rcu_read_unlock() fence events delimiting the critical section in
 question, and let S be the synchronize_rcu() fence event for the grace
 period.  Saying that the critical section starts before S means there
 are events E and F where E is po-after L (which marks the start of the
-critical section), E is "before" F in the sense of the link relation,
-and F is po-before the grace period S:
+critical section), E is "before" F in the sense of the rcu-link
+relation, and F is po-before the grace period S:
 
-	L ->po E ->link F ->po S.
+	L ->po E ->rcu-link F ->po S.
 
 Let W be the store mentioned above, let Z come before the end of the
 critical section and witness that W propagates to the critical
@@ -1600,16 +1652,19 @@ some event X which is po-after S.  Symbolically, this amounts to:
 
 The fr link from Y to W indicates that W has not propagated to Y's CPU
 at the time that Y executes.  From this, it can be shown (see the
-discussion of the link relation earlier) that X and Z are connected by
-link, yielding:
+discussion of the rcu-link relation earlier) that X and Z are related
+by rcu-link, yielding:
+
+	S ->po X ->rcu-link Z ->po U.
+
+The formulas say that S is po-between F and X, hence F ->gp X.  They
+also say that Z comes before the end of the critical section and E
+comes after its start, hence Z ->rscs E.  From all this we obtain:
 
-	S ->po X ->link Z ->po U.
+	F ->gp X ->rcu-link Z ->rscs E ->rcu-link F,
 
-These formulas say that S is po-between F and X, hence F ->gp-link Z
-via X.  They also say that Z comes before the end of the critical
-section and E comes after its start, hence Z ->rscs-link F via E.  But
-now we have a forbidden cycle: F ->gp-link Z ->rscs-link F.  Thus the
-"rcu" axiom rules out this violation of the Grace Period Guarantee.
+a forbidden cycle.  Thus the "rcu" axiom rules out this violation of
+the Grace Period Guarantee.
 
 For something a little more down-to-earth, let's see how the axiom
 works out in practice.  Consider the RCU code example from above, this
@@ -1635,18 +1690,18 @@ time with statement labels added to the memory access instructions:
 	}
 
 
-If r2 = 0 at the end then P0's store at X overwrites the value
-that P1's load at Z reads from, so we have Z ->fre X and thus
-Z ->link X.  In addition, there is a synchronize_rcu() between Y and
-Z, so therefore we have Y ->gp-link X.
+If r2 = 0 at the end then P0's store at X overwrites the value that
+P1's load at Z reads from, so we have Z ->fre X and thus Z ->rcu-link X.
+In addition, there is a synchronize_rcu() between Y and Z, so therefore
+we have Y ->gp Z.
 
 If r1 = 1 at the end then P1's load at Y reads from P0's store at W,
-so we have W ->link Y.  In addition, W and X are in the same critical
-section, so therefore we have X ->rscs-link Y.
+so we have W ->rcu-link Y.  In addition, W and X are in the same critical
+section, so therefore we have X ->rscs W.
 
-This gives us a cycle, Y ->gp-link X ->rscs-link Y, with one gp-link
-and one rscs-link, violating the "rcu" axiom.  Hence the outcome is
-not allowed by the LKMM, as we would expect.
+Then X ->rscs W ->rcu-link Y ->gp Z ->rcu-link X is a forbidden cycle,
+violating the "rcu" axiom.  Hence the outcome is not allowed by the
+LKMM, as we would expect.
 
 For contrast, let's see what can happen in a more complicated example:
 
@@ -1682,15 +1737,11 @@ For contrast, let's see what can happen in a more complicated example:
 	}
 
 If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows
-that W ->rscs-link Y via X, Y ->gp-link U via Z, and U ->rscs-link W
-via V.  And just as before, this gives a cycle:
-
-	W ->rscs-link Y ->gp-link U ->rscs-link W.
-
-However, this cycle has fewer gp-link instances than rscs-link
-instances, and consequently the outcome is not forbidden by the LKMM.
-The following instruction timing diagram shows how it might actually
-occur:
+that W ->rscs X ->rcu-link Y ->gp Z ->rcu-link U ->rscs V ->rcu-link W.
+However this cycle is not forbidden, because the sequence of relations
+contains fewer instances of gp (one) than of rscs (two).  Consequently
+the outcome is allowed by the LKMM.  The following instruction timing
+diagram shows how it might actually occur:
 
 P0			P1			P2
 --------------------	--------------------	--------------------
diff --git a/tools/memory-model/Documentation/references.txt b/tools/memory-model/Documentation/references.txt
index ba2e34c2ec3f..b177f3e4a614 100644
--- a/tools/memory-model/Documentation/references.txt
+++ b/tools/memory-model/Documentation/references.txt
@@ -63,15 +63,22 @@ o	Shaked Flur, Susmit Sarkar, Christopher Pulte, Kyndylan Nienhuis,
 	Principles of Programming Languages (POPL 2017). ACM, New York,
 	NY, USA, 429–442.
 
+o	Christopher Pulte, Shaked Flur, Will Deacon, Jon French,
+	Susmit Sarkar, and Peter Sewell. 2018. "Simplifying ARM concurrency:
+	multicopy-atomic axiomatic and operational models for ARMv8". In
+	Proceedings of the ACM on Programming Languages, Volume 2, Issue
+	POPL, Article No. 19. ACM, New York, NY, USA.
+
 
 Linux-kernel memory model
 =========================
 
-o	Andrea Parri, Alan Stern, Luc Maranget, Paul E. McKenney,
-	and Jade Alglave.  2017. "A formal model of
-	Linux-kernel memory ordering - companion webpage".
-	http://moscova.inria.fr/∼maranget/cats7/linux/. (2017). [Online;
-	accessed 30-January-2017].
+o	Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and
+	Alan Stern.  2018. "Frightening small children and disconcerting
+	grown-ups: Concurrency in the Linux kernel". In Proceedings of
+	the 23rd International Conference on Architectural Support for
+	Programming Languages and Operating Systems (ASPLOS 2018). ACM,
+	New York, NY, USA, 405-418.  Webpage: http://diy.inria.fr/linux/.
 
 o	Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and
 	Alan Stern.  2017.  "A formal kernel memory-ordering model (part 1)"
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 0b3a5f3c9ccd..734f7feaa5dc 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -20,7 +20,7 @@ that litmus test to be exercised within the Linux kernel.
 REQUIREMENTS
 ============
 
-Version 7.48 of the "herd7" and "klitmus7" tools must be downloaded
+Version 7.49 of the "herd7" and "klitmus7" tools must be downloaded
 separately:
 
   https://github.com/herd/herdtools7
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 432c7cf71b23..64f5740e0e75 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -5,10 +5,10 @@
  * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>,
  *                    Andrea Parri <parri.andrea@gmail.com>
  *
- * An earlier version of this file appears in the companion webpage for
+ * An earlier version of this file appeared in the companion webpage for
  * "Frightening small children and disconcerting grown-ups: Concurrency
  * in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
- * which is to appear in ASPLOS 2018.
+ * which appeared in ASPLOS 2018.
  *)
 
 "Linux-kernel memory consistency model"
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index df97db03b6c2..59b5cbe6b624 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -5,10 +5,10 @@
  * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>,
  *                    Andrea Parri <parri.andrea@gmail.com>
  *
- * An earlier version of this file appears in the companion webpage for
+ * An earlier version of this file appeared in the companion webpage for
  * "Frightening small children and disconcerting grown-ups: Concurrency
  * in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
- * which is to appear in ASPLOS 2018.
+ * which appeared in ASPLOS 2018.
  *)
 
 "Linux-kernel memory consistency model"
@@ -100,22 +100,29 @@ let rscs = po ; crit^-1 ; po?
  * one but two non-rf relations, but only in conjunction with an RCU
  * read-side critical section.
  *)
-let link = hb* ; pb* ; prop
+let rcu-link = hb* ; pb* ; prop
 
-(* Chains that affect the RCU grace-period guarantee *)
-let gp-link = gp ; link
-let rscs-link = rscs ; link
+(*
+ * Any sequence containing at least as many grace periods as RCU read-side
+ * critical sections (joined by rcu-link) acts as a generalized strong fence.
+ *)
+let rec rcu-fence = gp |
+	(gp ; rcu-link ; rscs) |
+	(rscs ; rcu-link ; gp) |
+	(gp ; rcu-link ; rcu-fence ; rcu-link ; rscs) |
+	(rscs ; rcu-link ; rcu-fence ; rcu-link ; gp) |
+	(rcu-fence ; rcu-link ; rcu-fence)
+
+(* rb orders instructions just as pb does *)
+let rb = prop ; rcu-fence ; hb* ; pb*
+
+irreflexive rb as rcu
 
 (*
- * A cycle containing at least as many grace periods as RCU read-side
- * critical sections is forbidden.
+ * The happens-before, propagation, and rcu constraints are all
+ * expressions of temporal ordering.  They could be replaced by
+ * a single constraint on an "executes-before" relation, xb:
+ *
+ * let xb = hb | pb | rb
+ * acyclic xb as executes-before
  *)
-let rec rcu-path =
-	gp-link |
-	(gp-link ; rscs-link) |
-	(rscs-link ; gp-link) |
-	(rcu-path ; rcu-path) |
-	(gp-link ; rcu-path ; rscs-link) |
-	(rscs-link ; rcu-path ; gp-link)
-
-irreflexive rcu-path as rcu
diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def
index 397e4e67e8c8..6fa3eb28d40b 100644
--- a/tools/memory-model/linux-kernel.def
+++ b/tools/memory-model/linux-kernel.def
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0+
 //
-// An earlier version of this file appears in the companion webpage for
+// An earlier version of this file appeared in the companion webpage for
 // "Frightening small children and disconcerting grown-ups: Concurrency
 // in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
-// which is to appear in ASPLOS 2018.
+// which appeared in ASPLOS 2018.
 
 // ONCE
 READ_ONCE(X) __load{once}(X)
@@ -14,14 +14,15 @@ smp_store_release(X,V) { __store{release}(*X,V); }
 smp_load_acquire(X) __load{acquire}(*X)
 rcu_assign_pointer(X,V) { __store{release}(X,V); }
 rcu_dereference(X) __load{once}(X)
+smp_store_mb(X,V) { __store{once}(X,V); __fence{mb}; }
 
 // Fences
-smp_mb() { __fence{mb} ; }
-smp_rmb() { __fence{rmb} ; }
-smp_wmb() { __fence{wmb} ; }
-smp_mb__before_atomic() { __fence{before-atomic} ; }
-smp_mb__after_atomic() { __fence{after-atomic} ; }
-smp_mb__after_spinlock() { __fence{after-spinlock} ; }
+smp_mb() { __fence{mb}; }
+smp_rmb() { __fence{rmb}; }
+smp_wmb() { __fence{wmb}; }
+smp_mb__before_atomic() { __fence{before-atomic}; }
+smp_mb__after_atomic() { __fence{after-atomic}; }
+smp_mb__after_spinlock() { __fence{after-spinlock}; }
 
 // Exchange
 xchg(X,V)  __xchg{mb}(X,V)
@@ -34,26 +35,27 @@ cmpxchg_acquire(X,V,W) __cmpxchg{acquire}(X,V,W)
 cmpxchg_release(X,V,W) __cmpxchg{release}(X,V,W)
 
 // Spinlocks
-spin_lock(X) { __lock(X) ; }
-spin_unlock(X) { __unlock(X) ; }
+spin_lock(X) { __lock(X); }
+spin_unlock(X) { __unlock(X); }
 spin_trylock(X) __trylock(X)
+spin_is_locked(X) __islocked(X)
 
 // RCU
 rcu_read_lock() { __fence{rcu-lock}; }
-rcu_read_unlock() { __fence{rcu-unlock};}
+rcu_read_unlock() { __fence{rcu-unlock}; }
 synchronize_rcu() { __fence{sync-rcu}; }
 synchronize_rcu_expedited() { __fence{sync-rcu}; }
 
 // Atomic
 atomic_read(X) READ_ONCE(*X)
-atomic_set(X,V) { WRITE_ONCE(*X,V) ; }
+atomic_set(X,V) { WRITE_ONCE(*X,V); }
 atomic_read_acquire(X) smp_load_acquire(X)
 atomic_set_release(X,V) { smp_store_release(X,V); }
 
-atomic_add(V,X) { __atomic_op(X,+,V) ; }
-atomic_sub(V,X) { __atomic_op(X,-,V) ; }
-atomic_inc(X)   { __atomic_op(X,+,1) ; }
-atomic_dec(X)   { __atomic_op(X,-,1) ; }
+atomic_add(V,X) { __atomic_op(X,+,V); }
+atomic_sub(V,X) { __atomic_op(X,-,V); }
+atomic_inc(X)   { __atomic_op(X,+,1); }
+atomic_dec(X)   { __atomic_op(X,-,1); }
 
 atomic_add_return(V,X) __atomic_op_return{mb}(X,+,V)
 atomic_add_return_relaxed(V,X) __atomic_op_return{once}(X,+,V)
diff --git a/tools/memory-model/litmus-tests/.gitignore b/tools/memory-model/litmus-tests/.gitignore
new file mode 100644
index 000000000000..6e2ddc54152f
--- /dev/null
+++ b/tools/memory-model/litmus-tests/.gitignore
@@ -0,0 +1 @@
+*.litmus.out
diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
index 50d5db9ea983..98a3716efa37 100644
--- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
+++ b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
@@ -7,7 +7,7 @@ C IRIW+mbonceonces+OnceOnce
  * between each pairs of reads.  In other words, is smp_mb() sufficient to
  * cause two different reading processes to agree on the order of a pair
  * of writes, where each write is to a different variable by a different
- * process?
+ * process?  This litmus test exercises LKMM's "propagation" rule.
  *)
 
 {}
diff --git a/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus b/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus
new file mode 100644
index 000000000000..50f4d62bbf0e
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus
@@ -0,0 +1,35 @@
+C MP+polockmbonce+poacquiresilsil
+
+(*
+ * Result: Never
+ *
+ * Do spinlocks combined with smp_mb__after_spinlock() provide order
+ * to outside observers using spin_is_locked() to sense the lock-held
+ * state, ordered by acquire?  Note that when the first spin_is_locked()
+ * returns false and the second true, we know that the smp_load_acquire()
+ * executed before the lock was acquired (loosely speaking).
+ *)
+
+{
+}
+
+P0(spinlock_t *lo, int *x)
+{
+	spin_lock(lo);
+	smp_mb__after_spinlock();
+	WRITE_ONCE(*x, 1);
+	spin_unlock(lo);
+}
+
+P1(spinlock_t *lo, int *x)
+{
+	int r1;
+	int r2;
+	int r3;
+
+	r1 = smp_load_acquire(x);
+	r2 = spin_is_locked(lo);
+	r3 = spin_is_locked(lo);
+}
+
+exists (1:r1=1 /\ 1:r2=0 /\ 1:r3=1)
diff --git a/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus b/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus
new file mode 100644
index 000000000000..abf81e7a0895
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus
@@ -0,0 +1,34 @@
+C MP+polockonce+poacquiresilsil
+
+(*
+ * Result: Sometimes
+ *
+ * Do spinlocks provide order to outside observers using spin_is_locked()
+ * to sense the lock-held state, ordered by acquire?  Note that when the
+ * first spin_is_locked() returns false and the second true, we know that
+ * the smp_load_acquire() executed before the lock was acquired (loosely
+ * speaking).
+ *)
+
+{
+}
+
+P0(spinlock_t *lo, int *x)
+{
+	spin_lock(lo);
+	WRITE_ONCE(*x, 1);
+	spin_unlock(lo);
+}
+
+P1(spinlock_t *lo, int *x)
+{
+	int r1;
+	int r2;
+	int r3;
+
+	r1 = smp_load_acquire(x);
+	r2 = spin_is_locked(lo);
+	r3 = spin_is_locked(lo);
+}
+
+exists (1:r1=1 /\ 1:r2=0 /\ 1:r3=1)
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 04096fb8b8d9..17eb9a8c222d 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -23,7 +23,8 @@ IRIW+mbonceonces+OnceOnce.litmus
 	between each pairs of reads.  In other words, is smp_mb()
 	sufficient to cause two different reading processes to agree on
 	the order of a pair of writes, where each write is to a different
-	variable by a different process?
+	variable by a different process?  This litmus test is forbidden
+	by LKMM's propagation rule.
 
 IRIW+poonceonces+OnceOnce.litmus
 	Test of independent reads from independent writes with nothing
@@ -63,6 +64,16 @@ LB+poonceonces.litmus
 MP+onceassign+derefonce.litmus
 	As below, but with rcu_assign_pointer() and an rcu_dereference().
 
+MP+polockmbonce+poacquiresilsil.litmus
+	Protect the access with a lock and an smp_mb__after_spinlock()
+	in one process, and use an acquire load followed by a pair of
+	spin_is_locked() calls in the other process.
+
+MP+polockonce+poacquiresilsil.litmus
+	Protect the access with a lock in one process, and use an
+	acquire load followed by a pair of spin_is_locked() calls
+	in the other process.
+
 MP+polocks.litmus
 	As below, but with the second access of the writer process
 	and the first access of reader process protected by a lock.
@@ -109,8 +120,10 @@ S+wmbonceonce+poacquireonce.litmus
 
 WRC+poonceonces+Once.litmus
 WRC+pooncerelease+rmbonceonce+Once.litmus
-	These two are members of an extension of the MP litmus-test class
-	in which the first write is moved to a separate process.
+	These two are members of an extension of the MP litmus-test
+	class in which the first write is moved to a separate process.
+	The second is forbidden because smp_store_release() is
+	A-cumulative in LKMM.
 
 Z6.0+pooncelock+pooncelock+pombonce.litmus
 	Is the ordering provided by a spin_unlock() and a subsequent
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
index 97fcbffde9a0..ad3448b941e6 100644
--- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
@@ -5,7 +5,9 @@ C WRC+pooncerelease+rmbonceonce+Once
  *
  * This litmus test is an extension of the message-passing pattern, where
  * the first write is moved to a separate process.  Because it features
- * a release and a read memory barrier, it should be forbidden.
+ * a release and a read memory barrier, it should be forbidden.  More
+ * specifically, this litmus test is forbidden because smp_store_release()
+ * is A-cumulative in LKMM.
  *)
 
 {}
diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat
index ba4a4ec6d313..305ded17e741 100644
--- a/tools/memory-model/lock.cat
+++ b/tools/memory-model/lock.cat
@@ -4,46 +4,72 @@
  * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>
  *)
 
-(* Generate coherence orders and handle lock operations *)
+(*
+ * Generate coherence orders and handle lock operations
+ *
+ * Warning: spin_is_locked() crashes herd7 versions strictly before 7.48.
+ * spin_is_locked() is functional from herd7 version 7.49.
+ *)
 
 include "cross.cat"
 
-(* From lock reads to their partner lock writes *)
-let lk-rmw = ([LKR] ; po-loc ; [LKW]) \ (po ; po)
-let rmw = rmw | lk-rmw
-
 (*
- * A paired LKR must always see an unlocked value; spin_lock() calls nested
- * inside a critical section (for the same lock) always deadlock.
+ * The lock-related events generated by herd are as follows:
+ *
+ * LKR		Lock-Read: the read part of a spin_lock() or successful
+ *			spin_trylock() read-modify-write event pair
+ * LKW		Lock-Write: the write part of a spin_lock() or successful
+ *			spin_trylock() RMW event pair
+ * UL		Unlock: a spin_unlock() event
+ * LF		Lock-Fail: a failed spin_trylock() event
+ * RL		Read-Locked: a spin_is_locked() event which returns True
+ * RU		Read-Unlocked: a spin_is_locked() event which returns False
+ *
+ * LKR and LKW events always come paired, like all RMW event sequences.
+ *
+ * LKR, LF, RL, and RU are read events; LKR has Acquire ordering.
+ * LKW and UL are write events; UL has Release ordering.
+ * LKW, LF, RL, and RU have no ordering properties.
  *)
-empty ([LKW] ; po-loc ; [domain(lk-rmw)]) \ (po-loc ; [UL] ; po-loc)
-	as lock-nest
 
-(* The litmus test is invalid if an LKW event is not part of an RMW pair *)
-flag ~empty LKW \ range(lk-rmw) as unpaired-LKW
+(* Backward compatibility *)
+let RL = try RL with emptyset
+let RU = try RU with emptyset
 
-(* This will be allowed if we implement spin_is_locked() *)
-flag ~empty LKR \ domain(lk-rmw) as unpaired-LKR
+(* Treat RL as a kind of LF: a read with no ordering properties *)
+let LF = LF | RL
 
-(* There should be no R or W accesses to spinlocks *)
-let ALL-LOCKS = LKR | LKW | UL | LF
+(* There should be no ordinary R or W accesses to spinlocks *)
+let ALL-LOCKS = LKR | LKW | UL | LF | RU
 flag ~empty [M \ IW] ; loc ; [ALL-LOCKS] as mixed-lock-accesses
 
+(* Link Lock-Reads to their RMW-partner Lock-Writes *)
+let lk-rmw = ([LKR] ; po-loc ; [LKW]) \ (po ; po)
+let rmw = rmw | lk-rmw
+
+(* The litmus test is invalid if an LKR/LKW event is not part of an RMW pair *)
+flag ~empty LKW \ range(lk-rmw) as unpaired-LKW
+flag ~empty LKR \ domain(lk-rmw) as unpaired-LKR
+
+(*
+ * An LKR must always see an unlocked value; spin_lock() calls nested
+ * inside a critical section (for the same lock) always deadlock.
+ *)
+empty ([LKW] ; po-loc ; [LKR]) \ (po-loc ; [UL] ; po-loc) as lock-nest
+
 (* The final value of a spinlock should not be tested *)
 flag ~empty [FW] ; loc ; [ALL-LOCKS] as lock-final
 
-
 (*
  * Put lock operations in their appropriate classes, but leave UL out of W
  * until after the co relation has been generated.
  *)
-let R = R | LKR | LF
+let R = R | LKR | LF | RU
 let W = W | LKW
 
 let Release = Release | UL
 let Acquire = Acquire | LKR
 
-
 (* Match LKW events to their corresponding UL events *)
 let critical = ([LKW] ; po-loc ; [UL]) \ (po-loc ; [LKW | UL] ; po-loc)
 
@@ -53,27 +79,48 @@ flag ~empty UL \ range(critical) as unmatched-unlock
 let UNMATCHED-LKW = LKW \ domain(critical)
 empty ([UNMATCHED-LKW] ; loc ; [UNMATCHED-LKW]) \ id as unmatched-locks
 
-
 (* rfi for LF events: link each LKW to the LF events in its critical section *)
 let rfi-lf = ([LKW] ; po-loc ; [LF]) \ ([LKW] ; po-loc ; [UL] ; po-loc)
 
 (* rfe for LF events *)
 let all-possible-rfe-lf =
-  (*
-   * Given an LF event r, compute the possible rfe edges for that event
-   * (all those starting from LKW events in other threads),
-   * and then convert that relation to a set of single-edge relations.
-   *)
-  let possible-rfe-lf r =
-    let pair-to-relation p = p ++ 0
-    in map pair-to-relation ((LKW * {r}) & loc & ext)
-  (* Do this for each LF event r that isn't in rfi-lf *)
-  in map possible-rfe-lf (LF \ range(rfi-lf))
+	(*
+	 * Given an LF event r, compute the possible rfe edges for that event
+	 * (all those starting from LKW events in other threads),
+	 * and then convert that relation to a set of single-edge relations.
+	 *)
+	let possible-rfe-lf r =
+		let pair-to-relation p = p ++ 0
+		in map pair-to-relation ((LKW * {r}) & loc & ext)
+	(* Do this for each LF event r that isn't in rfi-lf *)
+	in map possible-rfe-lf (LF \ range(rfi-lf))
 
 (* Generate all rf relations for LF events *)
 with rfe-lf from cross(all-possible-rfe-lf)
-let rf = rf | rfi-lf | rfe-lf
+let rf-lf = rfe-lf | rfi-lf
+
+(*
+ * RU, i.e., spin_is_locked() returning False, is slightly different.
+ * We rely on the memory model to rule out cases where spin_is_locked()
+ * within one of the lock's critical sections returns False.
+ *)
+
+(* rfi for RU events: an RU may read from the last po-previous UL *)
+let rfi-ru = ([UL] ; po-loc ; [RU]) \ ([UL] ; po-loc ; [LKW] ; po-loc)
+
+(* rfe for RU events: an RU may read from an external UL or the initial write *)
+let all-possible-rfe-ru =
+	let possible-rfe-ru r =
+		let pair-to-relation p = p ++ 0
+		in map pair-to-relation (((UL | IW) * {r}) & loc & ext)
+	in map possible-rfe-ru RU
+
+(* Generate all rf relations for RU events *)
+with rfe-ru from cross(all-possible-rfe-ru)
+let rf-ru = rfe-ru | rfi-ru
 
+(* Final rf relation *)
+let rf = rf | rf-lf | rf-ru
 
 (* Generate all co relations, including LKW events but not UL *)
 let co0 = co0 | ([IW] ; loc ; [LKW]) |
diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
new file mode 100644
index 000000000000..af0aa15ab84e
--- /dev/null
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -0,0 +1,73 @@
+#!/bin/sh
+#
+# Run herd tests on all .litmus files in the specified directory (which
+# defaults to litmus-tests) and check each file's result against a "Result:"
+# comment within that litmus test.  If the verification result does not
+# match that specified in the litmus test, this script prints an error
+# message prefixed with "^^^".  It also outputs verification results to
+# a file whose name is that of the specified litmus test, but with ".out"
+# appended.
+#
+# Usage:
+#	sh checkalllitmus.sh [ directory ]
+#
+# The LINUX_HERD_OPTIONS environment variable may be used to specify
+# arguments to herd, whose default is defined by the checklitmus.sh script.
+# Thus, one would normally run this in the directory containing the memory
+# model, specifying the pathname of the litmus test to check.
+#
+# This script makes no attempt to run the litmus tests concurrently.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+litmusdir=${1-litmus-tests}
+if test -d "$litmusdir" -a -r "$litmusdir" -a -x "$litmusdir"
+then
+	:
+else
+	echo ' --- ' error: $litmusdir is not an accessible directory
+	exit 255
+fi
+
+# Find the checklitmus script.  If it is not where we expect it, then
+# assume that the caller has the PATH environment variable set
+# appropriately.
+if test -x scripts/checklitmus.sh
+then
+	clscript=scripts/checklitmus.sh
+else
+	clscript=checklitmus.sh
+fi
+
+# Run the script on all the litmus tests in the specified directory
+ret=0
+for i in litmus-tests/*.litmus
+do
+	if ! $clscript $i
+	then
+		ret=1
+	fi
+done
+if test "$ret" -ne 0
+then
+	echo " ^^^ VERIFICATION MISMATCHES"
+else
+	echo All litmus tests verified as was expected.
+fi
+exit $ret
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
new file mode 100644
index 000000000000..e2e477472844
--- /dev/null
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -0,0 +1,86 @@
+#!/bin/sh
+#
+# Run a herd test and check the result against a "Result:" comment within
+# the litmus test.  If the verification result does not match that specified
+# in the litmus test, this script prints an error message prefixed with
+# "^^^" and exits with a non-zero status.  It also outputs verification
+# results to a file whose name is that of the specified litmus test, but
+# with ".out" appended.
+#
+# Usage:
+#	sh checklitmus.sh file.litmus
+#
+# The LINUX_HERD_OPTIONS environment variable may be used to specify
+# arguments to herd, which default to "-conf linux-kernel.cfg".  Thus,
+# one would normally run this in the directory containing the memory model,
+# specifying the pathname of the litmus test to check.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+litmus=$1
+herdoptions=${LINUX_HERD_OPTIONS--conf linux-kernel.cfg}
+
+if test -f "$litmus" -a -r "$litmus"
+then
+	:
+else
+	echo ' --- ' error: \"$litmus\" is not a readable file
+	exit 255
+fi
+if grep -q '^ \* Result: ' $litmus
+then
+	outcome=`grep -m 1 '^ \* Result: ' $litmus | awk '{ print $3 }'`
+else
+	outcome=specified
+fi
+
+echo Herd options: $herdoptions > $litmus.out
+/usr/bin/time herd7 -o ~/tmp $herdoptions $litmus >> $litmus.out 2>&1
+grep "Herd options:" $litmus.out
+grep '^Observation' $litmus.out
+if grep -q '^Observation' $litmus.out
+then
+	:
+else
+	cat $litmus.out
+	echo ' ^^^ Verification error'
+	echo ' ^^^ Verification error' >> $litmus.out 2>&1
+	exit 255
+fi
+if test "$outcome" = DEADLOCK
+then
+	echo grep 3 and 4
+	if grep '^Observation' $litmus.out | grep -q 'Never 0 0$'
+	then
+		ret=0
+	else
+		echo " ^^^ Unexpected non-$outcome verification"
+		echo " ^^^ Unexpected non-$outcome verification" >> $litmus.out 2>&1
+		ret=1
+	fi
+elif grep '^Observation' $litmus.out | grep -q $outcome || test "$outcome" = Maybe
+then
+	ret=0
+else
+	echo " ^^^ Unexpected non-$outcome verification"
+	echo " ^^^ Unexpected non-$outcome verification" >> $litmus.out 2>&1
+	ret=1
+fi
+tail -2 $litmus.out | head -1
+exit $ret
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 8ae824dbfca3..f76d9914686a 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -31,8 +31,8 @@ INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
 	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS   += -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
-LDFLAGS  += -lelf $(LIBSUBCMD)
+CFLAGS   += -Werror $(WARNINGS) $(HOSTCFLAGS) -g $(INCLUDES)
+LDFLAGS  += -lelf $(LIBSUBCMD) $(HOSTLDFLAGS)
 
 # Allow old libelf to be used:
 elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
diff --git a/tools/objtool/arch/x86/include/asm/insn.h b/tools/objtool/arch/x86/include/asm/insn.h
index b3e32b010ab1..c2c01f84df75 100644
--- a/tools/objtool/arch/x86/include/asm/insn.h
+++ b/tools/objtool/arch/x86/include/asm/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
 	return insn_offset_displacement(insn) + insn->displacement.nbytes;
 }
 
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+	return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+		(insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+		 X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
 #endif /* _ASM_X86_INSN_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5409f6f6c48d..3a31b238f885 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -59,6 +59,31 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
 	return next;
 }
 
+static struct instruction *next_insn_same_func(struct objtool_file *file,
+					       struct instruction *insn)
+{
+	struct instruction *next = list_next_entry(insn, list);
+	struct symbol *func = insn->func;
+
+	if (!func)
+		return NULL;
+
+	if (&next->list != &file->insn_list && next->func == func)
+		return next;
+
+	/* Check if we're already in the subfunction: */
+	if (func == func->cfunc)
+		return NULL;
+
+	/* Move to the subfunction: */
+	return find_insn(file, func->cfunc->sec, func->cfunc->offset);
+}
+
+#define func_for_each_insn_all(file, func, insn)			\
+	for (insn = find_insn(file, func->sec, func->offset);		\
+	     insn;							\
+	     insn = next_insn_same_func(file, insn))
+
 #define func_for_each_insn(file, func, insn)				\
 	for (insn = find_insn(file, func->sec, func->offset);		\
 	     insn && &insn->list != &file->insn_list &&			\
@@ -149,10 +174,14 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
 			if (!strcmp(func->name, global_noreturns[i]))
 				return 1;
 
-	if (!func->sec)
+	if (!func->len)
 		return 0;
 
-	func_for_each_insn(file, func, insn) {
+	insn = find_insn(file, func->sec, func->offset);
+	if (!insn->func)
+		return 0;
+
+	func_for_each_insn_all(file, func, insn) {
 		empty = false;
 
 		if (insn->type == INSN_RETURN)
@@ -167,35 +196,28 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
 	 * case, the function's dead-end status depends on whether the target
 	 * of the sibling call returns.
 	 */
-	func_for_each_insn(file, func, insn) {
-		if (insn->sec != func->sec ||
-		    insn->offset >= func->offset + func->len)
-			break;
-
+	func_for_each_insn_all(file, func, insn) {
 		if (insn->type == INSN_JUMP_UNCONDITIONAL) {
 			struct instruction *dest = insn->jump_dest;
-			struct symbol *dest_func;
 
 			if (!dest)
 				/* sibling call to another file */
 				return 0;
 
-			if (dest->sec != func->sec ||
-			    dest->offset < func->offset ||
-			    dest->offset >= func->offset + func->len) {
-				/* local sibling call */
-				dest_func = find_symbol_by_offset(dest->sec,
-								  dest->offset);
-				if (!dest_func)
-					continue;
+			if (dest->func && dest->func->pfunc != insn->func->pfunc) {
 
+				/* local sibling call */
 				if (recursion == 5) {
-					WARN_FUNC("infinite recursion (objtool bug!)",
-						  dest->sec, dest->offset);
-					return -1;
+					/*
+					 * Infinite recursion: two functions
+					 * have sibling calls to each other.
+					 * This is a very rare case.  It means
+					 * they aren't dead ends.
+					 */
+					return 0;
 				}
 
-				return __dead_end_function(file, dest_func,
+				return __dead_end_function(file, dest->func,
 							   recursion + 1);
 			}
 		}
@@ -422,7 +444,7 @@ static void add_ignores(struct objtool_file *file)
 			if (!ignore_func(file, func))
 				continue;
 
-			func_for_each_insn(file, func, insn)
+			func_for_each_insn_all(file, func, insn)
 				insn->ignore = true;
 		}
 	}
@@ -782,30 +804,35 @@ out:
 	return ret;
 }
 
-static int add_switch_table(struct objtool_file *file, struct symbol *func,
-			    struct instruction *insn, struct rela *table,
-			    struct rela *next_table)
+static int add_switch_table(struct objtool_file *file, struct instruction *insn,
+			    struct rela *table, struct rela *next_table)
 {
 	struct rela *rela = table;
 	struct instruction *alt_insn;
 	struct alternative *alt;
+	struct symbol *pfunc = insn->func->pfunc;
+	unsigned int prev_offset = 0;
 
 	list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) {
 		if (rela == next_table)
 			break;
 
-		if (rela->sym->sec != insn->sec ||
-		    rela->addend <= func->offset ||
-		    rela->addend >= func->offset + func->len)
+		/* Make sure the switch table entries are consecutive: */
+		if (prev_offset && rela->offset != prev_offset + 8)
 			break;
 
-		alt_insn = find_insn(file, insn->sec, rela->addend);
-		if (!alt_insn) {
-			WARN("%s: can't find instruction at %s+0x%x",
-			     file->rodata->rela->name, insn->sec->name,
-			     rela->addend);
-			return -1;
-		}
+		/* Detect function pointers from contiguous objects: */
+		if (rela->sym->sec == pfunc->sec &&
+		    rela->addend == pfunc->offset)
+			break;
+
+		alt_insn = find_insn(file, rela->sym->sec, rela->addend);
+		if (!alt_insn)
+			break;
+
+		/* Make sure the jmp dest is in the function or subfunction: */
+		if (alt_insn->func->pfunc != pfunc)
+			break;
 
 		alt = malloc(sizeof(*alt));
 		if (!alt) {
@@ -815,6 +842,13 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func,
 
 		alt->insn = alt_insn;
 		list_add_tail(&alt->list, &insn->alts);
+		prev_offset = rela->offset;
+	}
+
+	if (!prev_offset) {
+		WARN_FUNC("can't find switch jump table",
+			  insn->sec, insn->offset);
+		return -1;
 	}
 
 	return 0;
@@ -869,40 +903,21 @@ static struct rela *find_switch_table(struct objtool_file *file,
 {
 	struct rela *text_rela, *rodata_rela;
 	struct instruction *orig_insn = insn;
+	unsigned long table_offset;
 
-	text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
-	if (text_rela && text_rela->sym == file->rodata->sym) {
-		/* case 1 */
-		rodata_rela = find_rela_by_dest(file->rodata,
-						text_rela->addend);
-		if (rodata_rela)
-			return rodata_rela;
-
-		/* case 2 */
-		rodata_rela = find_rela_by_dest(file->rodata,
-						text_rela->addend + 4);
-		if (!rodata_rela)
-			return NULL;
-
-		file->ignore_unreachables = true;
-		return rodata_rela;
-	}
-
-	/* case 3 */
 	/*
 	 * Backward search using the @first_jump_src links, these help avoid
 	 * much of the 'in between' code. Which avoids us getting confused by
 	 * it.
 	 */
-	for (insn = list_prev_entry(insn, list);
-
+	for (;
 	     &insn->list != &file->insn_list &&
 	     insn->sec == func->sec &&
 	     insn->offset >= func->offset;
 
 	     insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {
 
-		if (insn->type == INSN_JUMP_DYNAMIC)
+		if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC)
 			break;
 
 		/* allow small jumps within the range */
@@ -918,18 +933,29 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		if (!text_rela || text_rela->sym != file->rodata->sym)
 			continue;
 
+		table_offset = text_rela->addend;
+		if (text_rela->type == R_X86_64_PC32)
+			table_offset += 4;
+
 		/*
 		 * Make sure the .rodata address isn't associated with a
 		 * symbol.  gcc jump tables are anonymous data.
 		 */
-		if (find_symbol_containing(file->rodata, text_rela->addend))
+		if (find_symbol_containing(file->rodata, table_offset))
 			continue;
 
-		rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend);
-		if (!rodata_rela)
-			continue;
+		rodata_rela = find_rela_by_dest(file->rodata, table_offset);
+		if (rodata_rela) {
+			/*
+			 * Use of RIP-relative switch jumps is quite rare, and
+			 * indicates a rare GCC quirk/bug which can leave dead
+			 * code behind.
+			 */
+			if (text_rela->type == R_X86_64_PC32)
+				file->ignore_unreachables = true;
 
-		return rodata_rela;
+			return rodata_rela;
+		}
 	}
 
 	return NULL;
@@ -943,7 +969,7 @@ static int add_func_switch_tables(struct objtool_file *file,
 	struct rela *rela, *prev_rela = NULL;
 	int ret;
 
-	func_for_each_insn(file, func, insn) {
+	func_for_each_insn_all(file, func, insn) {
 		if (!last)
 			last = insn;
 
@@ -974,8 +1000,7 @@ static int add_func_switch_tables(struct objtool_file *file,
 		 * the beginning of another switch table in the same function.
 		 */
 		if (prev_jump) {
-			ret = add_switch_table(file, func, prev_jump, prev_rela,
-					       rela);
+			ret = add_switch_table(file, prev_jump, prev_rela, rela);
 			if (ret)
 				return ret;
 		}
@@ -985,7 +1010,7 @@ static int add_func_switch_tables(struct objtool_file *file,
 	}
 
 	if (prev_jump) {
-		ret = add_switch_table(file, func, prev_jump, prev_rela, NULL);
+		ret = add_switch_table(file, prev_jump, prev_rela, NULL);
 		if (ret)
 			return ret;
 	}
@@ -1749,15 +1774,13 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 	while (1) {
 		next_insn = next_insn_same_sec(file, insn);
 
-
-		if (file->c_file && func && insn->func && func != insn->func) {
+		if (file->c_file && func && insn->func && func != insn->func->pfunc) {
 			WARN("%s() falls through to next function %s()",
 			     func->name, insn->func->name);
 			return 1;
 		}
 
-		if (insn->func)
-			func = insn->func;
+		func = insn->func ? insn->func->pfunc : NULL;
 
 		if (func && insn->ignore) {
 			WARN_FUNC("BUG: why am I validating an ignored function?",
@@ -1778,7 +1801,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 
 				i = insn;
 				save_insn = NULL;
-				func_for_each_insn_continue_reverse(file, func, i) {
+				func_for_each_insn_continue_reverse(file, insn->func, i) {
 					if (i->save) {
 						save_insn = i;
 						break;
@@ -1865,7 +1888,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 		case INSN_JUMP_UNCONDITIONAL:
 			if (insn->jump_dest &&
 			    (!func || !insn->jump_dest->func ||
-			     func == insn->jump_dest->func)) {
+			     insn->jump_dest->func->pfunc == func)) {
 				ret = validate_branch(file, insn->jump_dest,
 						      state);
 				if (ret)
@@ -2060,7 +2083,7 @@ static int validate_functions(struct objtool_file *file)
 
 	for_each_sec(file, sec) {
 		list_for_each_entry(func, &sec->symbol_list, list) {
-			if (func->type != STT_FUNC)
+			if (func->type != STT_FUNC || func->pfunc != func)
 				continue;
 
 			insn = find_insn(file, sec, func->offset);
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index c1c338661699..4e60e105583e 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -79,6 +79,19 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
 	return NULL;
 }
 
+struct symbol *find_symbol_by_name(struct elf *elf, const char *name)
+{
+	struct section *sec;
+	struct symbol *sym;
+
+	list_for_each_entry(sec, &elf->sections, list)
+		list_for_each_entry(sym, &sec->symbol_list, list)
+			if (!strcmp(sym->name, name))
+				return sym;
+
+	return NULL;
+}
+
 struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
 {
 	struct symbol *sym;
@@ -203,10 +216,11 @@ static int read_sections(struct elf *elf)
 
 static int read_symbols(struct elf *elf)
 {
-	struct section *symtab;
-	struct symbol *sym;
+	struct section *symtab, *sec;
+	struct symbol *sym, *pfunc;
 	struct list_head *entry, *tmp;
 	int symbols_nr, i;
+	char *coldstr;
 
 	symtab = find_section_by_name(elf, ".symtab");
 	if (!symtab) {
@@ -281,6 +295,30 @@ static int read_symbols(struct elf *elf)
 		hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
 	}
 
+	/* Create parent/child links for any cold subfunctions */
+	list_for_each_entry(sec, &elf->sections, list) {
+		list_for_each_entry(sym, &sec->symbol_list, list) {
+			if (sym->type != STT_FUNC)
+				continue;
+			sym->pfunc = sym->cfunc = sym;
+			coldstr = strstr(sym->name, ".cold.");
+			if (coldstr) {
+				coldstr[0] = '\0';
+				pfunc = find_symbol_by_name(elf, sym->name);
+				coldstr[0] = '.';
+
+				if (!pfunc) {
+					WARN("%s(): can't find parent function",
+					     sym->name);
+					goto err;
+				}
+
+				sym->pfunc = pfunc;
+				pfunc->cfunc = sym;
+			}
+		}
+	}
+
 	return 0;
 
 err:
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index d86e2ff14466..de5cd2ddded9 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -61,6 +61,7 @@ struct symbol {
 	unsigned char bind, type;
 	unsigned long offset;
 	unsigned int len;
+	struct symbol *pfunc, *cfunc;
 };
 
 struct rela {
@@ -86,6 +87,7 @@ struct elf {
 struct elf *elf_open(const char *name, int flags);
 struct section *find_section_by_name(struct elf *elf, const char *name);
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_by_name(struct elf *elf, const char *name);
 struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index db11478e30b4..42261a9b280e 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -47,7 +47,8 @@ man5dir=$(mandir)/man5
 man7dir=$(mandir)/man7
 
 ASCIIDOC=asciidoc
-ASCIIDOC_EXTRA = --unsafe
+ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf
+ASCIIDOC_HTML = xhtml11
 MANPAGE_XSL = manpage-normal.xsl
 XMLTO_EXTRA =
 INSTALL?=install
@@ -55,6 +56,14 @@ RM ?= rm -f
 DOC_REF = origin/man
 HTML_REF = origin/html
 
+ifdef USE_ASCIIDOCTOR
+ASCIIDOC = asciidoctor
+ASCIIDOC_EXTRA = -a compat-mode
+ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions
+ASCIIDOC_EXTRA += -a mansource="perf" -a manmanual="perf Manual"
+ASCIIDOC_HTML = xhtml5
+endif
+
 infodir?=$(prefix)/share/info
 MAKEINFO=makeinfo
 INSTALL_INFO=install-info
@@ -73,10 +82,12 @@ ifeq ($(_tmp_tool_path),)
 	missing_tools = $(ASCIIDOC)
 endif
 
+ifndef USE_ASCIIDOCTOR
 _tmp_tool_path := $(call get-executable,$(XMLTO))
 ifeq ($(_tmp_tool_path),)
 	missing_tools += $(XMLTO)
 endif
+endif
 
 #
 # For asciidoc ...
@@ -264,9 +275,17 @@ clean:
 
 $(MAN_HTML): $(OUTPUT)%.html : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
-	$(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \
+	$(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \
+		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+	mv $@+ $@
+
+ifdef USE_ASCIIDOCTOR
+$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt
+	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+	$(ASCIIDOC) -b manpage -d manpage \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
 	mv $@+ $@
+endif
 
 $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
 	$(QUIET_XMLTO)$(RM) $@ && \
@@ -274,7 +293,7 @@ $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
 
 $(OUTPUT)%.xml : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
-	$(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \
+	$(ASCIIDOC) -b docbook -d manpage \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
 	mv $@+ $@
 
@@ -321,13 +340,13 @@ howto-index.txt: howto-index.sh $(wildcard howto/*.txt)
 	mv $@+ $@
 
 $(patsubst %,%.html,$(ARTICLES)) : %.html : %.txt
-	$(QUIET_ASCIIDOC)$(ASCIIDOC) -b xhtml11 $*.txt
+	$(QUIET_ASCIIDOC)$(ASCIIDOC) -b $(ASCIIDOC_HTML) $*.txt
 
 WEBDOC_DEST = /pub/software/tools/perf/docs
 
 $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
-	sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
+	sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b $(ASCIIDOC_HTML) - >$@+ && \
 	mv $@+ $@
 
 # UNIMPLEMENTED
diff --git a/tools/perf/Documentation/asciidoctor-extensions.rb b/tools/perf/Documentation/asciidoctor-extensions.rb
new file mode 100644
index 000000000000..d148fe95c0c4
--- /dev/null
+++ b/tools/perf/Documentation/asciidoctor-extensions.rb
@@ -0,0 +1,29 @@
+require 'asciidoctor'
+require 'asciidoctor/extensions'
+
+module Perf
+  module Documentation
+    class LinkPerfProcessor < Asciidoctor::Extensions::InlineMacroProcessor
+      use_dsl
+
+      named :chrome
+
+      def process(parent, target, attrs)
+        if parent.document.basebackend? 'html'
+          %(<a href="#{target}.html">#{target}(#{attrs[1]})</a>\n)
+        elsif parent.document.basebackend? 'manpage'
+          "#{target}(#{attrs[1]})"
+        elsif parent.document.basebackend? 'docbook'
+          "<citerefentry>\n" \
+            "<refentrytitle>#{target}</refentrytitle>" \
+            "<manvolnum>#{attrs[1]}</manvolnum>\n" \
+          "</citerefentry>\n"
+        end
+      end
+    end
+  end
+end
+
+Asciidoctor::Extensions.register do
+  inline_macro Perf::Documentation::LinkPerfProcessor, :linkperf
+end
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 73c2650bd0db..f6de0952ff3c 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -48,6 +48,9 @@ OPTIONS
 --purge=::
         Purge all cached binaries including older caches which have specified
 	path from the cache.
+-P::
+--purge-all::
+	Purge all cached binaries. This will flush out entire cache.
 -M::
 --missing=::
 	List missing build ids in the cache for the specified file.
@@ -59,7 +62,9 @@ OPTIONS
 	exactly same build-id, that is replaced by new one. It can be used
 	to update kallsyms and kernel dso to vmlinux in order to support
 	annotation.
-
+-l::
+--list::
+	List all valid binaries from cache.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 5b4fff3adc4b..32f4a898e3f2 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -334,6 +334,11 @@ annotate.*::
 
 		99.93 │      mov    %eax,%eax
 
+	annotate.offset_level::
+		Default is '1', meaning just jump targets will have offsets show right beside
+		the instruction. When set to '2' 'call' instructions will also have its offsets
+		shown, 3 or higher will show offsets for all instructions.
+
 hist.*::
 	hist.percentage::
 		This option control the way to calculate overhead of filtered entries -
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index b0211410969b..f8d2167cf3e7 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -28,29 +28,46 @@ OPTIONS
 <command>...::
 	Any command you can specify in a shell.
 
+-i::
+--input=<file>::
+	Input file name.
+
 -f::
 --force::
 	Don't do ownership validation
 
 -t::
---type=::
+--type=<type>::
 	Select the memory operation type: load or store (default: load,store)
 
 -D::
---dump-raw-samples=::
+--dump-raw-samples::
 	Dump the raw decoded samples on the screen in a format that is easy to parse with
 	one sample per line.
 
 -x::
---field-separator::
+--field-separator=<separator>::
 	Specify the field separator used when dump raw samples (-D option). By default,
 	The separator is the space character.
 
 -C::
---cpu-list::
-	Restrict dump of raw samples to those provided via this option. Note that the same
-	option can be passed in record mode. It will be interpreted the same way as perf
-	record.
+--cpu=<cpu>::
+	Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
+        comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default
+        is to monitor all CPUS.
+-U::
+--hide-unresolved::
+	Only display entries resolved to a symbol.
+
+-p::
+--phys-data::
+	Record/Report sample physical addresses
+
+RECORD OPTIONS
+--------------
+-e::
+--event <event>::
+	Event selector. Use 'perf mem record -e list' to list available events.
 
 -K::
 --all-kernel::
@@ -60,12 +77,15 @@ OPTIONS
 --all-user::
 	Configure all used events to run in user space.
 
---ldload::
+-v::
+--verbose::
+	Be more verbose (show counter open errors, etc)
+
+--ldlat <n>::
 	Specify desired latency for loads event.
 
--p::
---phys-data::
-	Record/Report sample physical addresses
+In addition, for report all perf report options are valid, and for record
+all perf record options.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index bb33601a823b..63f938b887dd 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -104,8 +104,8 @@ OPTIONS for 'perf sched timehist'
     kallsyms pathname
 
 -g::
---no-call-graph::
-	Do not display call chains if present.
+--call-graph::
+	Display call chains if present (default on).
 
 --max-stack::
 	Maximum number of functions to display in backtrace, default 5.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 36ec0257f8d3..afdafe2110a1 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -228,14 +228,15 @@ OPTIONS
 	For sample events it's possible to display misc field with -F +misc option,
 	following letters are displayed for each bit:
 
-	  PERF_RECORD_MISC_KERNEL        K
-	  PERF_RECORD_MISC_USER          U
-	  PERF_RECORD_MISC_HYPERVISOR    H
-	  PERF_RECORD_MISC_GUEST_KERNEL  G
-	  PERF_RECORD_MISC_GUEST_USER    g
-	  PERF_RECORD_MISC_MMAP_DATA*    M
-	  PERF_RECORD_MISC_COMM_EXEC     E
-	  PERF_RECORD_MISC_SWITCH_OUT    S
+	  PERF_RECORD_MISC_KERNEL               K
+	  PERF_RECORD_MISC_USER                 U
+	  PERF_RECORD_MISC_HYPERVISOR           H
+	  PERF_RECORD_MISC_GUEST_KERNEL         G
+	  PERF_RECORD_MISC_GUEST_USER           g
+	  PERF_RECORD_MISC_MMAP_DATA*           M
+	  PERF_RECORD_MISC_COMM_EXEC            E
+	  PERF_RECORD_MISC_SWITCH_OUT           S
+	  PERF_RECORD_MISC_SWITCH_OUT_PREEMPT   Sp
 
 	  $ perf script -F +misc ...
 	   sched-messaging  1414 K     28690.636582:       4590 cycles ...
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index f15b306be183..3a822f308e6d 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -116,6 +116,22 @@ Do not aggregate counts across all monitored CPUs.
 print counts using a CSV-style output to make it easy to import directly into
 spreadsheets. Columns are separated by the string specified in SEP.
 
+--table:: Display time for each run (-r option), in a table format, e.g.:
+
+  $ perf stat --null -r 5 --table perf bench sched pipe
+
+   Performance counter stats for 'perf bench sched pipe' (5 runs):
+
+             # Table of individual measurements:
+             5.189 (-0.293) #
+             5.189 (-0.294) #
+             5.186 (-0.296) #
+             5.663 (+0.181) ##
+             6.186 (+0.703) ####
+
+             # Final result:
+             5.483 +- 0.198 seconds time elapsed  ( +-  3.62% )
+
 -G name::
 --cgroup name::
 monitor only in the container (cgroup) called "name". This option is available only
@@ -153,7 +169,7 @@ perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- m
 
 -I msecs::
 --interval-print msecs::
-Print count deltas every N milliseconds (minimum: 10ms)
+Print count deltas every N milliseconds (minimum: 1ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index d00f0d51cab8..dfb218feaad9 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -111,8 +111,8 @@ A perf_header_string with the CPU architecture (uname -m)
 A structure defining the number of CPUs.
 
 struct nr_cpus {
-       uint32_t nr_cpus_online;
        uint32_t nr_cpus_available; /* CPUs not yet onlined */
+       uint32_t nr_cpus_online;
 };
 
 	HEADER_CPUDESC = 8,
@@ -153,10 +153,18 @@ struct {
 	HEADER_CPU_TOPOLOGY = 13,
 
 String lists defining the core and CPU threads topology.
+The string lists are followed by a variable length array
+which contains core_id and socket_id of each cpu.
+The number of entries can be determined by the size of the
+section minus the sizes of both string lists.
 
 struct {
        struct perf_header_string_list cores; /* Variable length */
        struct perf_header_string_list threads; /* Variable length */
+       struct {
+	      uint32_t core_id;
+	      uint32_t socket_id;
+       } cpus[nr]; /* Variable length records */
 };
 
 Example:
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index c7abd83a8e19..b5ac356ba323 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -68,7 +68,7 @@ ifeq ($(NO_PERF_REGS),0)
 endif
 
 ifneq ($(NO_SYSCALL_TABLE),1)
-  CFLAGS += -DHAVE_SYSCALL_TABLE
+  CFLAGS += -DHAVE_SYSCALL_TABLE_SUPPORT
 endif
 
 # So far there's only x86 and arm libdw unwind support merged in perf.
@@ -847,7 +847,7 @@ ifndef NO_JVMTI
   ifeq ($(feature-jvmti), 1)
     $(call detected_var,JDIR)
   else
-    $(warning No openjdk development package found, please install JDK package)
+    $(warning No openjdk development package found, please install JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel)
     NO_JVMTI := 1
   endif
 endif
@@ -885,6 +885,8 @@ endif
 
 # Among the variables below, these:
 #   perfexecdir
+#   perf_include_dir
+#   perf_examples_dir
 #   template_dir
 #   mandir
 #   infodir
@@ -904,6 +906,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
+perf_include_dir = lib/include/perf
+perf_examples_dir = lib/examples/perf
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
@@ -934,6 +938,8 @@ bindir_SQ = $(subst ','\'',$(bindir))
 mandir_SQ = $(subst ','\'',$(mandir))
 infodir_SQ = $(subst ','\'',$(infodir))
 perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
+perf_include_dir_SQ = $(subst ','\'',$(perf_include_dir))
+perf_examples_dir_SQ = $(subst ','\'',$(perf_examples_dir))
 template_dir_SQ = $(subst ','\'',$(template_dir))
 htmldir_SQ = $(subst ','\'',$(htmldir))
 tipdir_SQ = $(subst ','\'',$(tipdir))
@@ -944,14 +950,20 @@ srcdir_SQ = $(subst ','\'',$(srcdir))
 
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
+perf_include_instdir = $(perf_include_dir)
+perf_examples_instdir = $(perf_examples_dir)
 STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR)
 tip_instdir = $(tipdir)
 else
 perfexec_instdir = $(prefix)/$(perfexecdir)
+perf_include_instdir = $(prefix)/$(perf_include_dir)
+perf_examples_instdir = $(prefix)/$(perf_examples_dir)
 STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR)
 tip_instdir = $(prefix)/$(tipdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+perf_include_instdir_SQ = $(subst ','\'',$(perf_include_instdir))
+perf_examples_instdir_SQ = $(subst ','\'',$(perf_examples_instdir))
 STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR))
 tip_instdir_SQ = $(subst ','\'',$(tip_instdir))
 
@@ -999,6 +1011,8 @@ $(call detected_var,ETC_PERFCONFIG_SQ)
 $(call detected_var,STRACE_GROUPS_DIR_SQ)
 $(call detected_var,prefix_SQ)
 $(call detected_var,perfexecdir_SQ)
+$(call detected_var,perf_include_dir_SQ)
+$(call detected_var,perf_examples_dir_SQ)
 $(call detected_var,tipdir_SQ)
 $(call detected_var,srcdir_SQ)
 $(call detected_var,LIBDIR)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 83e453de36f8..ecc9fc952655 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -767,6 +767,16 @@ ifndef NO_JVMTI
 endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifndef NO_LIBBPF
+	$(call QUIET_INSTALL, lib) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, include/bpf) \
+		$(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, lib) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, examples/bpf) \
+		$(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+endif
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-with-kcore) \
diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h
new file mode 100644
index 000000000000..90ec4c8cb880
--- /dev/null
+++ b/tools/perf/arch/arm/include/arch-tests.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+#endif
+
+extern struct test arch_tests[];
+
+#endif
diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build
index b30eff9bcc83..883c57ff0c08 100644
--- a/tools/perf/arch/arm/tests/Build
+++ b/tools/perf/arch/arm/tests/Build
@@ -1,2 +1,4 @@
 libperf-y += regs_load.o
 libperf-y += dwarf-unwind.o
+
+libperf-y += arch-tests.o
diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c
new file mode 100644
index 000000000000..5b1543c98022
--- /dev/null
+++ b/tools/perf/arch/arm/tests/arch-tests.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "DWARF unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+	{
+		.func = NULL,
+	},
+};
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 8cb347760233..9a0242e74cfc 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_ARM_SP];
 
-	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	map = map_groups__find(thread->mg, (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index fa639e3e52ac..1ce6bdbda561 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <stdbool.h>
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 5c655ad4621e..2f595cd73da6 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <api/fs/fs.h>
diff --git a/tools/perf/arch/arm/util/cs-etm.h b/tools/perf/arch/arm/util/cs-etm.h
index 5256741be549..1a12e64f5127 100644
--- a/tools/perf/arch/arm/util/cs-etm.h
+++ b/tools/perf/arch/arm/util/cs-etm.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef INCLUDE__PERF_CS_ETM_H__
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index ac4dffc807b8..e047571e6080 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <string.h>
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
index e907f0f4c20c..5522ce384723 100644
--- a/tools/perf/arch/arm64/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_ARM64_SP];
 
-	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	map = map_groups__find(thread->mg, (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
index 30cbbd6d5be0..5f39efef0856 100644
--- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_POWERPC_R1];
 
-	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	map = map_groups__find(thread->mg, (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 0c370f81e002..3598b8b75d27 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -248,8 +248,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 
 	ip = chain->ips[2];
 
-	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
-			MAP__FUNCTION, ip, &al);
+	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 
 	if (al.map)
 		dso = al.map->dso;
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
index 6cb48e4cffd9..3afe8256eff2 100644
--- a/tools/perf/arch/s390/util/auxtrace.c
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -87,6 +87,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
 	struct perf_evsel *pos;
 	int diagnose = 0;
 
+	*err = 0;
 	if (evlist->nr_entries == 0)
 		return NULL;
 
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index a4c30f1c70be..163b92f33998 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -146,21 +146,3 @@ char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 		zfree(&buf);
 	return buf;
 }
-
-/*
- * Compare the cpuid string returned by get_cpuid() function
- * with the name generated by the jevents file read from
- * pmu-events/arch/s390/mapfile.csv.
- *
- * Parameter mapcpuid is the cpuid as stored in the
- * pmu-events/arch/s390/mapfile.csv. This is just the type number.
- * Parameter cpuid is the cpuid returned by function get_cpuid().
- */
-int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
-{
-	char *cp = strchr(cpuid, ',');
-
-	if (cp == NULL)
-		return -1;
-	return strncmp(cp + 1, mapcpuid, strlen(mapcpuid));
-}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index d74eaa7aa927..1a38e78117ce 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -21,7 +21,7 @@ _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 $(header): $(sys)/syscall_64.tbl $(systbl)
 	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
         (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \
-        || echo "Warning: Kernel ABI header at 'tools/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
+        || echo "Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
 
 clean::
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 5bd1ba8c0282..44f5aba78210 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -1,21 +1,43 @@
 // SPDX-License-Identifier: GPL-2.0
 static struct ins x86__instructions[] = {
+	{ .name = "adc",	.ops = &mov_ops,  },
+	{ .name = "adcb",	.ops = &mov_ops,  },
+	{ .name = "adcl",	.ops = &mov_ops,  },
 	{ .name = "add",	.ops = &mov_ops,  },
 	{ .name = "addl",	.ops = &mov_ops,  },
 	{ .name = "addq",	.ops = &mov_ops,  },
+	{ .name = "addsd",	.ops = &mov_ops,  },
 	{ .name = "addw",	.ops = &mov_ops,  },
 	{ .name = "and",	.ops = &mov_ops,  },
+	{ .name = "andb",	.ops = &mov_ops,  },
+	{ .name = "andl",	.ops = &mov_ops,  },
+	{ .name = "andpd",	.ops = &mov_ops,  },
+	{ .name = "andps",	.ops = &mov_ops,  },
+	{ .name = "andq",	.ops = &mov_ops,  },
+	{ .name = "andw",	.ops = &mov_ops,  },
+	{ .name = "bsr",	.ops = &mov_ops,  },
+	{ .name = "bt",		.ops = &mov_ops,  },
+	{ .name = "btr",	.ops = &mov_ops,  },
 	{ .name = "bts",	.ops = &mov_ops,  },
+	{ .name = "btsq",	.ops = &mov_ops,  },
 	{ .name = "call",	.ops = &call_ops, },
 	{ .name = "callq",	.ops = &call_ops, },
+	{ .name = "cmovbe",	.ops = &mov_ops,  },
+	{ .name = "cmove",	.ops = &mov_ops,  },
+	{ .name = "cmovae",	.ops = &mov_ops,  },
 	{ .name = "cmp",	.ops = &mov_ops,  },
 	{ .name = "cmpb",	.ops = &mov_ops,  },
 	{ .name = "cmpl",	.ops = &mov_ops,  },
 	{ .name = "cmpq",	.ops = &mov_ops,  },
 	{ .name = "cmpw",	.ops = &mov_ops,  },
 	{ .name = "cmpxch",	.ops = &mov_ops,  },
+	{ .name = "cmpxchg",	.ops = &mov_ops,  },
+	{ .name = "cs",		.ops = &mov_ops,  },
 	{ .name = "dec",	.ops = &dec_ops,  },
 	{ .name = "decl",	.ops = &dec_ops,  },
+	{ .name = "divsd",	.ops = &mov_ops,  },
+	{ .name = "divss",	.ops = &mov_ops,  },
+	{ .name = "gs",		.ops = &mov_ops,  },
 	{ .name = "imul",	.ops = &mov_ops,  },
 	{ .name = "inc",	.ops = &dec_ops,  },
 	{ .name = "incl",	.ops = &dec_ops,  },
@@ -57,25 +79,68 @@ static struct ins x86__instructions[] = {
 	{ .name = "lea",	.ops = &mov_ops,  },
 	{ .name = "lock",	.ops = &lock_ops, },
 	{ .name = "mov",	.ops = &mov_ops,  },
+	{ .name = "movapd",	.ops = &mov_ops,  },
+	{ .name = "movaps",	.ops = &mov_ops,  },
 	{ .name = "movb",	.ops = &mov_ops,  },
 	{ .name = "movdqa",	.ops = &mov_ops,  },
+	{ .name = "movdqu",	.ops = &mov_ops,  },
 	{ .name = "movl",	.ops = &mov_ops,  },
 	{ .name = "movq",	.ops = &mov_ops,  },
+	{ .name = "movsd",	.ops = &mov_ops,  },
 	{ .name = "movslq",	.ops = &mov_ops,  },
+	{ .name = "movss",	.ops = &mov_ops,  },
+	{ .name = "movupd",	.ops = &mov_ops,  },
+	{ .name = "movups",	.ops = &mov_ops,  },
+	{ .name = "movw",	.ops = &mov_ops,  },
 	{ .name = "movzbl",	.ops = &mov_ops,  },
 	{ .name = "movzwl",	.ops = &mov_ops,  },
+	{ .name = "mulsd",	.ops = &mov_ops,  },
+	{ .name = "mulss",	.ops = &mov_ops,  },
 	{ .name = "nop",	.ops = &nop_ops,  },
 	{ .name = "nopl",	.ops = &nop_ops,  },
 	{ .name = "nopw",	.ops = &nop_ops,  },
 	{ .name = "or",		.ops = &mov_ops,  },
+	{ .name = "orb",	.ops = &mov_ops,  },
 	{ .name = "orl",	.ops = &mov_ops,  },
+	{ .name = "orps",	.ops = &mov_ops,  },
+	{ .name = "orq",	.ops = &mov_ops,  },
+	{ .name = "pand",	.ops = &mov_ops,  },
+	{ .name = "paddq",	.ops = &mov_ops,  },
+	{ .name = "pcmpeqb",	.ops = &mov_ops,  },
+	{ .name = "por",	.ops = &mov_ops,  },
+	{ .name = "rclb",	.ops = &mov_ops,  },
+	{ .name = "rcll",	.ops = &mov_ops,  },
+	{ .name = "retq",	.ops = &ret_ops,  },
+	{ .name = "sbb",	.ops = &mov_ops,  },
+	{ .name = "sbbl",	.ops = &mov_ops,  },
+	{ .name = "sete",	.ops = &mov_ops,  },
+	{ .name = "sub",	.ops = &mov_ops,  },
+	{ .name = "subl",	.ops = &mov_ops,  },
+	{ .name = "subq",	.ops = &mov_ops,  },
+	{ .name = "subsd",	.ops = &mov_ops,  },
+	{ .name = "subw",	.ops = &mov_ops,  },
 	{ .name = "test",	.ops = &mov_ops,  },
 	{ .name = "testb",	.ops = &mov_ops,  },
 	{ .name = "testl",	.ops = &mov_ops,  },
+	{ .name = "ucomisd",	.ops = &mov_ops,  },
+	{ .name = "ucomiss",	.ops = &mov_ops,  },
+	{ .name = "vaddsd",	.ops = &mov_ops,  },
+	{ .name = "vandpd",	.ops = &mov_ops,  },
+	{ .name = "vmovdqa",	.ops = &mov_ops,  },
+	{ .name = "vmovq",	.ops = &mov_ops,  },
+	{ .name = "vmovsd",	.ops = &mov_ops,  },
+	{ .name = "vmulsd",	.ops = &mov_ops,  },
+	{ .name = "vorpd",	.ops = &mov_ops,  },
+	{ .name = "vsubsd",	.ops = &mov_ops,  },
+	{ .name = "vucomisd",	.ops = &mov_ops,  },
 	{ .name = "xadd",	.ops = &mov_ops,  },
 	{ .name = "xbeginl",	.ops = &jump_ops, },
 	{ .name = "xbeginq",	.ops = &jump_ops, },
-	{ .name = "retq",	.ops = &ret_ops,  },
+	{ .name = "xchg",	.ops = &mov_ops,  },
+	{ .name = "xor",	.ops = &mov_ops, },
+	{ .name = "xorb",	.ops = &mov_ops, },
+	{ .name = "xorpd",	.ops = &mov_ops, },
+	{ .name = "xorps",	.ops = &mov_ops, },
 };
 
 static bool x86__ins_is_fused(struct arch *arch, const char *ins1,
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 5aef183e2f85..4dfe42666d0c 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -4,379 +4,383 @@
 # The format is:
 # <number> <abi> <name> <entry point>
 #
+# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
+#
 # The abi is "common", "64" or "x32" for this file.
 #
-0	common	read			sys_read
-1	common	write			sys_write
-2	common	open			sys_open
-3	common	close			sys_close
-4	common	stat			sys_newstat
-5	common	fstat			sys_newfstat
-6	common	lstat			sys_newlstat
-7	common	poll			sys_poll
-8	common	lseek			sys_lseek
-9	common	mmap			sys_mmap
-10	common	mprotect		sys_mprotect
-11	common	munmap			sys_munmap
-12	common	brk			sys_brk
-13	64	rt_sigaction		sys_rt_sigaction
-14	common	rt_sigprocmask		sys_rt_sigprocmask
-15	64	rt_sigreturn		sys_rt_sigreturn/ptregs
-16	64	ioctl			sys_ioctl
-17	common	pread64			sys_pread64
-18	common	pwrite64		sys_pwrite64
-19	64	readv			sys_readv
-20	64	writev			sys_writev
-21	common	access			sys_access
-22	common	pipe			sys_pipe
-23	common	select			sys_select
-24	common	sched_yield		sys_sched_yield
-25	common	mremap			sys_mremap
-26	common	msync			sys_msync
-27	common	mincore			sys_mincore
-28	common	madvise			sys_madvise
-29	common	shmget			sys_shmget
-30	common	shmat			sys_shmat
-31	common	shmctl			sys_shmctl
-32	common	dup			sys_dup
-33	common	dup2			sys_dup2
-34	common	pause			sys_pause
-35	common	nanosleep		sys_nanosleep
-36	common	getitimer		sys_getitimer
-37	common	alarm			sys_alarm
-38	common	setitimer		sys_setitimer
-39	common	getpid			sys_getpid
-40	common	sendfile		sys_sendfile64
-41	common	socket			sys_socket
-42	common	connect			sys_connect
-43	common	accept			sys_accept
-44	common	sendto			sys_sendto
-45	64	recvfrom		sys_recvfrom
-46	64	sendmsg			sys_sendmsg
-47	64	recvmsg			sys_recvmsg
-48	common	shutdown		sys_shutdown
-49	common	bind			sys_bind
-50	common	listen			sys_listen
-51	common	getsockname		sys_getsockname
-52	common	getpeername		sys_getpeername
-53	common	socketpair		sys_socketpair
-54	64	setsockopt		sys_setsockopt
-55	64	getsockopt		sys_getsockopt
-56	common	clone			sys_clone/ptregs
-57	common	fork			sys_fork/ptregs
-58	common	vfork			sys_vfork/ptregs
-59	64	execve			sys_execve/ptregs
-60	common	exit			sys_exit
-61	common	wait4			sys_wait4
-62	common	kill			sys_kill
-63	common	uname			sys_newuname
-64	common	semget			sys_semget
-65	common	semop			sys_semop
-66	common	semctl			sys_semctl
-67	common	shmdt			sys_shmdt
-68	common	msgget			sys_msgget
-69	common	msgsnd			sys_msgsnd
-70	common	msgrcv			sys_msgrcv
-71	common	msgctl			sys_msgctl
-72	common	fcntl			sys_fcntl
-73	common	flock			sys_flock
-74	common	fsync			sys_fsync
-75	common	fdatasync		sys_fdatasync
-76	common	truncate		sys_truncate
-77	common	ftruncate		sys_ftruncate
-78	common	getdents		sys_getdents
-79	common	getcwd			sys_getcwd
-80	common	chdir			sys_chdir
-81	common	fchdir			sys_fchdir
-82	common	rename			sys_rename
-83	common	mkdir			sys_mkdir
-84	common	rmdir			sys_rmdir
-85	common	creat			sys_creat
-86	common	link			sys_link
-87	common	unlink			sys_unlink
-88	common	symlink			sys_symlink
-89	common	readlink		sys_readlink
-90	common	chmod			sys_chmod
-91	common	fchmod			sys_fchmod
-92	common	chown			sys_chown
-93	common	fchown			sys_fchown
-94	common	lchown			sys_lchown
-95	common	umask			sys_umask
-96	common	gettimeofday		sys_gettimeofday
-97	common	getrlimit		sys_getrlimit
-98	common	getrusage		sys_getrusage
-99	common	sysinfo			sys_sysinfo
-100	common	times			sys_times
-101	64	ptrace			sys_ptrace
-102	common	getuid			sys_getuid
-103	common	syslog			sys_syslog
-104	common	getgid			sys_getgid
-105	common	setuid			sys_setuid
-106	common	setgid			sys_setgid
-107	common	geteuid			sys_geteuid
-108	common	getegid			sys_getegid
-109	common	setpgid			sys_setpgid
-110	common	getppid			sys_getppid
-111	common	getpgrp			sys_getpgrp
-112	common	setsid			sys_setsid
-113	common	setreuid		sys_setreuid
-114	common	setregid		sys_setregid
-115	common	getgroups		sys_getgroups
-116	common	setgroups		sys_setgroups
-117	common	setresuid		sys_setresuid
-118	common	getresuid		sys_getresuid
-119	common	setresgid		sys_setresgid
-120	common	getresgid		sys_getresgid
-121	common	getpgid			sys_getpgid
-122	common	setfsuid		sys_setfsuid
-123	common	setfsgid		sys_setfsgid
-124	common	getsid			sys_getsid
-125	common	capget			sys_capget
-126	common	capset			sys_capset
-127	64	rt_sigpending		sys_rt_sigpending
-128	64	rt_sigtimedwait		sys_rt_sigtimedwait
-129	64	rt_sigqueueinfo		sys_rt_sigqueueinfo
-130	common	rt_sigsuspend		sys_rt_sigsuspend
-131	64	sigaltstack		sys_sigaltstack
-132	common	utime			sys_utime
-133	common	mknod			sys_mknod
+0	common	read			__x64_sys_read
+1	common	write			__x64_sys_write
+2	common	open			__x64_sys_open
+3	common	close			__x64_sys_close
+4	common	stat			__x64_sys_newstat
+5	common	fstat			__x64_sys_newfstat
+6	common	lstat			__x64_sys_newlstat
+7	common	poll			__x64_sys_poll
+8	common	lseek			__x64_sys_lseek
+9	common	mmap			__x64_sys_mmap
+10	common	mprotect		__x64_sys_mprotect
+11	common	munmap			__x64_sys_munmap
+12	common	brk			__x64_sys_brk
+13	64	rt_sigaction		__x64_sys_rt_sigaction
+14	common	rt_sigprocmask		__x64_sys_rt_sigprocmask
+15	64	rt_sigreturn		__x64_sys_rt_sigreturn/ptregs
+16	64	ioctl			__x64_sys_ioctl
+17	common	pread64			__x64_sys_pread64
+18	common	pwrite64		__x64_sys_pwrite64
+19	64	readv			__x64_sys_readv
+20	64	writev			__x64_sys_writev
+21	common	access			__x64_sys_access
+22	common	pipe			__x64_sys_pipe
+23	common	select			__x64_sys_select
+24	common	sched_yield		__x64_sys_sched_yield
+25	common	mremap			__x64_sys_mremap
+26	common	msync			__x64_sys_msync
+27	common	mincore			__x64_sys_mincore
+28	common	madvise			__x64_sys_madvise
+29	common	shmget			__x64_sys_shmget
+30	common	shmat			__x64_sys_shmat
+31	common	shmctl			__x64_sys_shmctl
+32	common	dup			__x64_sys_dup
+33	common	dup2			__x64_sys_dup2
+34	common	pause			__x64_sys_pause
+35	common	nanosleep		__x64_sys_nanosleep
+36	common	getitimer		__x64_sys_getitimer
+37	common	alarm			__x64_sys_alarm
+38	common	setitimer		__x64_sys_setitimer
+39	common	getpid			__x64_sys_getpid
+40	common	sendfile		__x64_sys_sendfile64
+41	common	socket			__x64_sys_socket
+42	common	connect			__x64_sys_connect
+43	common	accept			__x64_sys_accept
+44	common	sendto			__x64_sys_sendto
+45	64	recvfrom		__x64_sys_recvfrom
+46	64	sendmsg			__x64_sys_sendmsg
+47	64	recvmsg			__x64_sys_recvmsg
+48	common	shutdown		__x64_sys_shutdown
+49	common	bind			__x64_sys_bind
+50	common	listen			__x64_sys_listen
+51	common	getsockname		__x64_sys_getsockname
+52	common	getpeername		__x64_sys_getpeername
+53	common	socketpair		__x64_sys_socketpair
+54	64	setsockopt		__x64_sys_setsockopt
+55	64	getsockopt		__x64_sys_getsockopt
+56	common	clone			__x64_sys_clone/ptregs
+57	common	fork			__x64_sys_fork/ptregs
+58	common	vfork			__x64_sys_vfork/ptregs
+59	64	execve			__x64_sys_execve/ptregs
+60	common	exit			__x64_sys_exit
+61	common	wait4			__x64_sys_wait4
+62	common	kill			__x64_sys_kill
+63	common	uname			__x64_sys_newuname
+64	common	semget			__x64_sys_semget
+65	common	semop			__x64_sys_semop
+66	common	semctl			__x64_sys_semctl
+67	common	shmdt			__x64_sys_shmdt
+68	common	msgget			__x64_sys_msgget
+69	common	msgsnd			__x64_sys_msgsnd
+70	common	msgrcv			__x64_sys_msgrcv
+71	common	msgctl			__x64_sys_msgctl
+72	common	fcntl			__x64_sys_fcntl
+73	common	flock			__x64_sys_flock
+74	common	fsync			__x64_sys_fsync
+75	common	fdatasync		__x64_sys_fdatasync
+76	common	truncate		__x64_sys_truncate
+77	common	ftruncate		__x64_sys_ftruncate
+78	common	getdents		__x64_sys_getdents
+79	common	getcwd			__x64_sys_getcwd
+80	common	chdir			__x64_sys_chdir
+81	common	fchdir			__x64_sys_fchdir
+82	common	rename			__x64_sys_rename
+83	common	mkdir			__x64_sys_mkdir
+84	common	rmdir			__x64_sys_rmdir
+85	common	creat			__x64_sys_creat
+86	common	link			__x64_sys_link
+87	common	unlink			__x64_sys_unlink
+88	common	symlink			__x64_sys_symlink
+89	common	readlink		__x64_sys_readlink
+90	common	chmod			__x64_sys_chmod
+91	common	fchmod			__x64_sys_fchmod
+92	common	chown			__x64_sys_chown
+93	common	fchown			__x64_sys_fchown
+94	common	lchown			__x64_sys_lchown
+95	common	umask			__x64_sys_umask
+96	common	gettimeofday		__x64_sys_gettimeofday
+97	common	getrlimit		__x64_sys_getrlimit
+98	common	getrusage		__x64_sys_getrusage
+99	common	sysinfo			__x64_sys_sysinfo
+100	common	times			__x64_sys_times
+101	64	ptrace			__x64_sys_ptrace
+102	common	getuid			__x64_sys_getuid
+103	common	syslog			__x64_sys_syslog
+104	common	getgid			__x64_sys_getgid
+105	common	setuid			__x64_sys_setuid
+106	common	setgid			__x64_sys_setgid
+107	common	geteuid			__x64_sys_geteuid
+108	common	getegid			__x64_sys_getegid
+109	common	setpgid			__x64_sys_setpgid
+110	common	getppid			__x64_sys_getppid
+111	common	getpgrp			__x64_sys_getpgrp
+112	common	setsid			__x64_sys_setsid
+113	common	setreuid		__x64_sys_setreuid
+114	common	setregid		__x64_sys_setregid
+115	common	getgroups		__x64_sys_getgroups
+116	common	setgroups		__x64_sys_setgroups
+117	common	setresuid		__x64_sys_setresuid
+118	common	getresuid		__x64_sys_getresuid
+119	common	setresgid		__x64_sys_setresgid
+120	common	getresgid		__x64_sys_getresgid
+121	common	getpgid			__x64_sys_getpgid
+122	common	setfsuid		__x64_sys_setfsuid
+123	common	setfsgid		__x64_sys_setfsgid
+124	common	getsid			__x64_sys_getsid
+125	common	capget			__x64_sys_capget
+126	common	capset			__x64_sys_capset
+127	64	rt_sigpending		__x64_sys_rt_sigpending
+128	64	rt_sigtimedwait		__x64_sys_rt_sigtimedwait
+129	64	rt_sigqueueinfo		__x64_sys_rt_sigqueueinfo
+130	common	rt_sigsuspend		__x64_sys_rt_sigsuspend
+131	64	sigaltstack		__x64_sys_sigaltstack
+132	common	utime			__x64_sys_utime
+133	common	mknod			__x64_sys_mknod
 134	64	uselib
-135	common	personality		sys_personality
-136	common	ustat			sys_ustat
-137	common	statfs			sys_statfs
-138	common	fstatfs			sys_fstatfs
-139	common	sysfs			sys_sysfs
-140	common	getpriority		sys_getpriority
-141	common	setpriority		sys_setpriority
-142	common	sched_setparam		sys_sched_setparam
-143	common	sched_getparam		sys_sched_getparam
-144	common	sched_setscheduler	sys_sched_setscheduler
-145	common	sched_getscheduler	sys_sched_getscheduler
-146	common	sched_get_priority_max	sys_sched_get_priority_max
-147	common	sched_get_priority_min	sys_sched_get_priority_min
-148	common	sched_rr_get_interval	sys_sched_rr_get_interval
-149	common	mlock			sys_mlock
-150	common	munlock			sys_munlock
-151	common	mlockall		sys_mlockall
-152	common	munlockall		sys_munlockall
-153	common	vhangup			sys_vhangup
-154	common	modify_ldt		sys_modify_ldt
-155	common	pivot_root		sys_pivot_root
-156	64	_sysctl			sys_sysctl
-157	common	prctl			sys_prctl
-158	common	arch_prctl		sys_arch_prctl
-159	common	adjtimex		sys_adjtimex
-160	common	setrlimit		sys_setrlimit
-161	common	chroot			sys_chroot
-162	common	sync			sys_sync
-163	common	acct			sys_acct
-164	common	settimeofday		sys_settimeofday
-165	common	mount			sys_mount
-166	common	umount2			sys_umount
-167	common	swapon			sys_swapon
-168	common	swapoff			sys_swapoff
-169	common	reboot			sys_reboot
-170	common	sethostname		sys_sethostname
-171	common	setdomainname		sys_setdomainname
-172	common	iopl			sys_iopl/ptregs
-173	common	ioperm			sys_ioperm
+135	common	personality		__x64_sys_personality
+136	common	ustat			__x64_sys_ustat
+137	common	statfs			__x64_sys_statfs
+138	common	fstatfs			__x64_sys_fstatfs
+139	common	sysfs			__x64_sys_sysfs
+140	common	getpriority		__x64_sys_getpriority
+141	common	setpriority		__x64_sys_setpriority
+142	common	sched_setparam		__x64_sys_sched_setparam
+143	common	sched_getparam		__x64_sys_sched_getparam
+144	common	sched_setscheduler	__x64_sys_sched_setscheduler
+145	common	sched_getscheduler	__x64_sys_sched_getscheduler
+146	common	sched_get_priority_max	__x64_sys_sched_get_priority_max
+147	common	sched_get_priority_min	__x64_sys_sched_get_priority_min
+148	common	sched_rr_get_interval	__x64_sys_sched_rr_get_interval
+149	common	mlock			__x64_sys_mlock
+150	common	munlock			__x64_sys_munlock
+151	common	mlockall		__x64_sys_mlockall
+152	common	munlockall		__x64_sys_munlockall
+153	common	vhangup			__x64_sys_vhangup
+154	common	modify_ldt		__x64_sys_modify_ldt
+155	common	pivot_root		__x64_sys_pivot_root
+156	64	_sysctl			__x64_sys_sysctl
+157	common	prctl			__x64_sys_prctl
+158	common	arch_prctl		__x64_sys_arch_prctl
+159	common	adjtimex		__x64_sys_adjtimex
+160	common	setrlimit		__x64_sys_setrlimit
+161	common	chroot			__x64_sys_chroot
+162	common	sync			__x64_sys_sync
+163	common	acct			__x64_sys_acct
+164	common	settimeofday		__x64_sys_settimeofday
+165	common	mount			__x64_sys_mount
+166	common	umount2			__x64_sys_umount
+167	common	swapon			__x64_sys_swapon
+168	common	swapoff			__x64_sys_swapoff
+169	common	reboot			__x64_sys_reboot
+170	common	sethostname		__x64_sys_sethostname
+171	common	setdomainname		__x64_sys_setdomainname
+172	common	iopl			__x64_sys_iopl/ptregs
+173	common	ioperm			__x64_sys_ioperm
 174	64	create_module
-175	common	init_module		sys_init_module
-176	common	delete_module		sys_delete_module
+175	common	init_module		__x64_sys_init_module
+176	common	delete_module		__x64_sys_delete_module
 177	64	get_kernel_syms
 178	64	query_module
-179	common	quotactl		sys_quotactl
+179	common	quotactl		__x64_sys_quotactl
 180	64	nfsservctl
 181	common	getpmsg
 182	common	putpmsg
 183	common	afs_syscall
 184	common	tuxcall
 185	common	security
-186	common	gettid			sys_gettid
-187	common	readahead		sys_readahead
-188	common	setxattr		sys_setxattr
-189	common	lsetxattr		sys_lsetxattr
-190	common	fsetxattr		sys_fsetxattr
-191	common	getxattr		sys_getxattr
-192	common	lgetxattr		sys_lgetxattr
-193	common	fgetxattr		sys_fgetxattr
-194	common	listxattr		sys_listxattr
-195	common	llistxattr		sys_llistxattr
-196	common	flistxattr		sys_flistxattr
-197	common	removexattr		sys_removexattr
-198	common	lremovexattr		sys_lremovexattr
-199	common	fremovexattr		sys_fremovexattr
-200	common	tkill			sys_tkill
-201	common	time			sys_time
-202	common	futex			sys_futex
-203	common	sched_setaffinity	sys_sched_setaffinity
-204	common	sched_getaffinity	sys_sched_getaffinity
+186	common	gettid			__x64_sys_gettid
+187	common	readahead		__x64_sys_readahead
+188	common	setxattr		__x64_sys_setxattr
+189	common	lsetxattr		__x64_sys_lsetxattr
+190	common	fsetxattr		__x64_sys_fsetxattr
+191	common	getxattr		__x64_sys_getxattr
+192	common	lgetxattr		__x64_sys_lgetxattr
+193	common	fgetxattr		__x64_sys_fgetxattr
+194	common	listxattr		__x64_sys_listxattr
+195	common	llistxattr		__x64_sys_llistxattr
+196	common	flistxattr		__x64_sys_flistxattr
+197	common	removexattr		__x64_sys_removexattr
+198	common	lremovexattr		__x64_sys_lremovexattr
+199	common	fremovexattr		__x64_sys_fremovexattr
+200	common	tkill			__x64_sys_tkill
+201	common	time			__x64_sys_time
+202	common	futex			__x64_sys_futex
+203	common	sched_setaffinity	__x64_sys_sched_setaffinity
+204	common	sched_getaffinity	__x64_sys_sched_getaffinity
 205	64	set_thread_area
-206	64	io_setup		sys_io_setup
-207	common	io_destroy		sys_io_destroy
-208	common	io_getevents		sys_io_getevents
-209	64	io_submit		sys_io_submit
-210	common	io_cancel		sys_io_cancel
+206	64	io_setup		__x64_sys_io_setup
+207	common	io_destroy		__x64_sys_io_destroy
+208	common	io_getevents		__x64_sys_io_getevents
+209	64	io_submit		__x64_sys_io_submit
+210	common	io_cancel		__x64_sys_io_cancel
 211	64	get_thread_area
-212	common	lookup_dcookie		sys_lookup_dcookie
-213	common	epoll_create		sys_epoll_create
+212	common	lookup_dcookie		__x64_sys_lookup_dcookie
+213	common	epoll_create		__x64_sys_epoll_create
 214	64	epoll_ctl_old
 215	64	epoll_wait_old
-216	common	remap_file_pages	sys_remap_file_pages
-217	common	getdents64		sys_getdents64
-218	common	set_tid_address		sys_set_tid_address
-219	common	restart_syscall		sys_restart_syscall
-220	common	semtimedop		sys_semtimedop
-221	common	fadvise64		sys_fadvise64
-222	64	timer_create		sys_timer_create
-223	common	timer_settime		sys_timer_settime
-224	common	timer_gettime		sys_timer_gettime
-225	common	timer_getoverrun	sys_timer_getoverrun
-226	common	timer_delete		sys_timer_delete
-227	common	clock_settime		sys_clock_settime
-228	common	clock_gettime		sys_clock_gettime
-229	common	clock_getres		sys_clock_getres
-230	common	clock_nanosleep		sys_clock_nanosleep
-231	common	exit_group		sys_exit_group
-232	common	epoll_wait		sys_epoll_wait
-233	common	epoll_ctl		sys_epoll_ctl
-234	common	tgkill			sys_tgkill
-235	common	utimes			sys_utimes
+216	common	remap_file_pages	__x64_sys_remap_file_pages
+217	common	getdents64		__x64_sys_getdents64
+218	common	set_tid_address		__x64_sys_set_tid_address
+219	common	restart_syscall		__x64_sys_restart_syscall
+220	common	semtimedop		__x64_sys_semtimedop
+221	common	fadvise64		__x64_sys_fadvise64
+222	64	timer_create		__x64_sys_timer_create
+223	common	timer_settime		__x64_sys_timer_settime
+224	common	timer_gettime		__x64_sys_timer_gettime
+225	common	timer_getoverrun	__x64_sys_timer_getoverrun
+226	common	timer_delete		__x64_sys_timer_delete
+227	common	clock_settime		__x64_sys_clock_settime
+228	common	clock_gettime		__x64_sys_clock_gettime
+229	common	clock_getres		__x64_sys_clock_getres
+230	common	clock_nanosleep		__x64_sys_clock_nanosleep
+231	common	exit_group		__x64_sys_exit_group
+232	common	epoll_wait		__x64_sys_epoll_wait
+233	common	epoll_ctl		__x64_sys_epoll_ctl
+234	common	tgkill			__x64_sys_tgkill
+235	common	utimes			__x64_sys_utimes
 236	64	vserver
-237	common	mbind			sys_mbind
-238	common	set_mempolicy		sys_set_mempolicy
-239	common	get_mempolicy		sys_get_mempolicy
-240	common	mq_open			sys_mq_open
-241	common	mq_unlink		sys_mq_unlink
-242	common	mq_timedsend		sys_mq_timedsend
-243	common	mq_timedreceive		sys_mq_timedreceive
-244	64	mq_notify		sys_mq_notify
-245	common	mq_getsetattr		sys_mq_getsetattr
-246	64	kexec_load		sys_kexec_load
-247	64	waitid			sys_waitid
-248	common	add_key			sys_add_key
-249	common	request_key		sys_request_key
-250	common	keyctl			sys_keyctl
-251	common	ioprio_set		sys_ioprio_set
-252	common	ioprio_get		sys_ioprio_get
-253	common	inotify_init		sys_inotify_init
-254	common	inotify_add_watch	sys_inotify_add_watch
-255	common	inotify_rm_watch	sys_inotify_rm_watch
-256	common	migrate_pages		sys_migrate_pages
-257	common	openat			sys_openat
-258	common	mkdirat			sys_mkdirat
-259	common	mknodat			sys_mknodat
-260	common	fchownat		sys_fchownat
-261	common	futimesat		sys_futimesat
-262	common	newfstatat		sys_newfstatat
-263	common	unlinkat		sys_unlinkat
-264	common	renameat		sys_renameat
-265	common	linkat			sys_linkat
-266	common	symlinkat		sys_symlinkat
-267	common	readlinkat		sys_readlinkat
-268	common	fchmodat		sys_fchmodat
-269	common	faccessat		sys_faccessat
-270	common	pselect6		sys_pselect6
-271	common	ppoll			sys_ppoll
-272	common	unshare			sys_unshare
-273	64	set_robust_list		sys_set_robust_list
-274	64	get_robust_list		sys_get_robust_list
-275	common	splice			sys_splice
-276	common	tee			sys_tee
-277	common	sync_file_range		sys_sync_file_range
-278	64	vmsplice		sys_vmsplice
-279	64	move_pages		sys_move_pages
-280	common	utimensat		sys_utimensat
-281	common	epoll_pwait		sys_epoll_pwait
-282	common	signalfd		sys_signalfd
-283	common	timerfd_create		sys_timerfd_create
-284	common	eventfd			sys_eventfd
-285	common	fallocate		sys_fallocate
-286	common	timerfd_settime		sys_timerfd_settime
-287	common	timerfd_gettime		sys_timerfd_gettime
-288	common	accept4			sys_accept4
-289	common	signalfd4		sys_signalfd4
-290	common	eventfd2		sys_eventfd2
-291	common	epoll_create1		sys_epoll_create1
-292	common	dup3			sys_dup3
-293	common	pipe2			sys_pipe2
-294	common	inotify_init1		sys_inotify_init1
-295	64	preadv			sys_preadv
-296	64	pwritev			sys_pwritev
-297	64	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo
-298	common	perf_event_open		sys_perf_event_open
-299	64	recvmmsg		sys_recvmmsg
-300	common	fanotify_init		sys_fanotify_init
-301	common	fanotify_mark		sys_fanotify_mark
-302	common	prlimit64		sys_prlimit64
-303	common	name_to_handle_at	sys_name_to_handle_at
-304	common	open_by_handle_at	sys_open_by_handle_at
-305	common	clock_adjtime		sys_clock_adjtime
-306	common	syncfs			sys_syncfs
-307	64	sendmmsg		sys_sendmmsg
-308	common	setns			sys_setns
-309	common	getcpu			sys_getcpu
-310	64	process_vm_readv	sys_process_vm_readv
-311	64	process_vm_writev	sys_process_vm_writev
-312	common	kcmp			sys_kcmp
-313	common	finit_module		sys_finit_module
-314	common	sched_setattr		sys_sched_setattr
-315	common	sched_getattr		sys_sched_getattr
-316	common	renameat2		sys_renameat2
-317	common	seccomp			sys_seccomp
-318	common	getrandom		sys_getrandom
-319	common	memfd_create		sys_memfd_create
-320	common	kexec_file_load		sys_kexec_file_load
-321	common	bpf			sys_bpf
-322	64	execveat		sys_execveat/ptregs
-323	common	userfaultfd		sys_userfaultfd
-324	common	membarrier		sys_membarrier
-325	common	mlock2			sys_mlock2
-326	common	copy_file_range		sys_copy_file_range
-327	64	preadv2			sys_preadv2
-328	64	pwritev2		sys_pwritev2
-329	common	pkey_mprotect		sys_pkey_mprotect
-330	common	pkey_alloc		sys_pkey_alloc
-331	common	pkey_free		sys_pkey_free
-332	common	statx			sys_statx
+237	common	mbind			__x64_sys_mbind
+238	common	set_mempolicy		__x64_sys_set_mempolicy
+239	common	get_mempolicy		__x64_sys_get_mempolicy
+240	common	mq_open			__x64_sys_mq_open
+241	common	mq_unlink		__x64_sys_mq_unlink
+242	common	mq_timedsend		__x64_sys_mq_timedsend
+243	common	mq_timedreceive		__x64_sys_mq_timedreceive
+244	64	mq_notify		__x64_sys_mq_notify
+245	common	mq_getsetattr		__x64_sys_mq_getsetattr
+246	64	kexec_load		__x64_sys_kexec_load
+247	64	waitid			__x64_sys_waitid
+248	common	add_key			__x64_sys_add_key
+249	common	request_key		__x64_sys_request_key
+250	common	keyctl			__x64_sys_keyctl
+251	common	ioprio_set		__x64_sys_ioprio_set
+252	common	ioprio_get		__x64_sys_ioprio_get
+253	common	inotify_init		__x64_sys_inotify_init
+254	common	inotify_add_watch	__x64_sys_inotify_add_watch
+255	common	inotify_rm_watch	__x64_sys_inotify_rm_watch
+256	common	migrate_pages		__x64_sys_migrate_pages
+257	common	openat			__x64_sys_openat
+258	common	mkdirat			__x64_sys_mkdirat
+259	common	mknodat			__x64_sys_mknodat
+260	common	fchownat		__x64_sys_fchownat
+261	common	futimesat		__x64_sys_futimesat
+262	common	newfstatat		__x64_sys_newfstatat
+263	common	unlinkat		__x64_sys_unlinkat
+264	common	renameat		__x64_sys_renameat
+265	common	linkat			__x64_sys_linkat
+266	common	symlinkat		__x64_sys_symlinkat
+267	common	readlinkat		__x64_sys_readlinkat
+268	common	fchmodat		__x64_sys_fchmodat
+269	common	faccessat		__x64_sys_faccessat
+270	common	pselect6		__x64_sys_pselect6
+271	common	ppoll			__x64_sys_ppoll
+272	common	unshare			__x64_sys_unshare
+273	64	set_robust_list		__x64_sys_set_robust_list
+274	64	get_robust_list		__x64_sys_get_robust_list
+275	common	splice			__x64_sys_splice
+276	common	tee			__x64_sys_tee
+277	common	sync_file_range		__x64_sys_sync_file_range
+278	64	vmsplice		__x64_sys_vmsplice
+279	64	move_pages		__x64_sys_move_pages
+280	common	utimensat		__x64_sys_utimensat
+281	common	epoll_pwait		__x64_sys_epoll_pwait
+282	common	signalfd		__x64_sys_signalfd
+283	common	timerfd_create		__x64_sys_timerfd_create
+284	common	eventfd			__x64_sys_eventfd
+285	common	fallocate		__x64_sys_fallocate
+286	common	timerfd_settime		__x64_sys_timerfd_settime
+287	common	timerfd_gettime		__x64_sys_timerfd_gettime
+288	common	accept4			__x64_sys_accept4
+289	common	signalfd4		__x64_sys_signalfd4
+290	common	eventfd2		__x64_sys_eventfd2
+291	common	epoll_create1		__x64_sys_epoll_create1
+292	common	dup3			__x64_sys_dup3
+293	common	pipe2			__x64_sys_pipe2
+294	common	inotify_init1		__x64_sys_inotify_init1
+295	64	preadv			__x64_sys_preadv
+296	64	pwritev			__x64_sys_pwritev
+297	64	rt_tgsigqueueinfo	__x64_sys_rt_tgsigqueueinfo
+298	common	perf_event_open		__x64_sys_perf_event_open
+299	64	recvmmsg		__x64_sys_recvmmsg
+300	common	fanotify_init		__x64_sys_fanotify_init
+301	common	fanotify_mark		__x64_sys_fanotify_mark
+302	common	prlimit64		__x64_sys_prlimit64
+303	common	name_to_handle_at	__x64_sys_name_to_handle_at
+304	common	open_by_handle_at	__x64_sys_open_by_handle_at
+305	common	clock_adjtime		__x64_sys_clock_adjtime
+306	common	syncfs			__x64_sys_syncfs
+307	64	sendmmsg		__x64_sys_sendmmsg
+308	common	setns			__x64_sys_setns
+309	common	getcpu			__x64_sys_getcpu
+310	64	process_vm_readv	__x64_sys_process_vm_readv
+311	64	process_vm_writev	__x64_sys_process_vm_writev
+312	common	kcmp			__x64_sys_kcmp
+313	common	finit_module		__x64_sys_finit_module
+314	common	sched_setattr		__x64_sys_sched_setattr
+315	common	sched_getattr		__x64_sys_sched_getattr
+316	common	renameat2		__x64_sys_renameat2
+317	common	seccomp			__x64_sys_seccomp
+318	common	getrandom		__x64_sys_getrandom
+319	common	memfd_create		__x64_sys_memfd_create
+320	common	kexec_file_load		__x64_sys_kexec_file_load
+321	common	bpf			__x64_sys_bpf
+322	64	execveat		__x64_sys_execveat/ptregs
+323	common	userfaultfd		__x64_sys_userfaultfd
+324	common	membarrier		__x64_sys_membarrier
+325	common	mlock2			__x64_sys_mlock2
+326	common	copy_file_range		__x64_sys_copy_file_range
+327	64	preadv2			__x64_sys_preadv2
+328	64	pwritev2		__x64_sys_pwritev2
+329	common	pkey_mprotect		__x64_sys_pkey_mprotect
+330	common	pkey_alloc		__x64_sys_pkey_alloc
+331	common	pkey_free		__x64_sys_pkey_free
+332	common	statx			__x64_sys_statx
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation.
+# for native 64-bit operation. The __x32_compat_sys stubs are created
+# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
+# is defined.
 #
-512	x32	rt_sigaction		compat_sys_rt_sigaction
+512	x32	rt_sigaction		__x32_compat_sys_rt_sigaction
 513	x32	rt_sigreturn		sys32_x32_rt_sigreturn
-514	x32	ioctl			compat_sys_ioctl
-515	x32	readv			compat_sys_readv
-516	x32	writev			compat_sys_writev
-517	x32	recvfrom		compat_sys_recvfrom
-518	x32	sendmsg			compat_sys_sendmsg
-519	x32	recvmsg			compat_sys_recvmsg
-520	x32	execve			compat_sys_execve/ptregs
-521	x32	ptrace			compat_sys_ptrace
-522	x32	rt_sigpending		compat_sys_rt_sigpending
-523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait
-524	x32	rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
-525	x32	sigaltstack		compat_sys_sigaltstack
-526	x32	timer_create		compat_sys_timer_create
-527	x32	mq_notify		compat_sys_mq_notify
-528	x32	kexec_load		compat_sys_kexec_load
-529	x32	waitid			compat_sys_waitid
-530	x32	set_robust_list		compat_sys_set_robust_list
-531	x32	get_robust_list		compat_sys_get_robust_list
-532	x32	vmsplice		compat_sys_vmsplice
-533	x32	move_pages		compat_sys_move_pages
-534	x32	preadv			compat_sys_preadv64
-535	x32	pwritev			compat_sys_pwritev64
-536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
-537	x32	recvmmsg		compat_sys_recvmmsg
-538	x32	sendmmsg		compat_sys_sendmmsg
-539	x32	process_vm_readv	compat_sys_process_vm_readv
-540	x32	process_vm_writev	compat_sys_process_vm_writev
-541	x32	setsockopt		compat_sys_setsockopt
-542	x32	getsockopt		compat_sys_getsockopt
-543	x32	io_setup		compat_sys_io_setup
-544	x32	io_submit		compat_sys_io_submit
-545	x32	execveat		compat_sys_execveat/ptregs
-546	x32	preadv2			compat_sys_preadv64v2
-547	x32	pwritev2		compat_sys_pwritev64v2
+514	x32	ioctl			__x32_compat_sys_ioctl
+515	x32	readv			__x32_compat_sys_readv
+516	x32	writev			__x32_compat_sys_writev
+517	x32	recvfrom		__x32_compat_sys_recvfrom
+518	x32	sendmsg			__x32_compat_sys_sendmsg
+519	x32	recvmsg			__x32_compat_sys_recvmsg
+520	x32	execve			__x32_compat_sys_execve/ptregs
+521	x32	ptrace			__x32_compat_sys_ptrace
+522	x32	rt_sigpending		__x32_compat_sys_rt_sigpending
+523	x32	rt_sigtimedwait		__x32_compat_sys_rt_sigtimedwait
+524	x32	rt_sigqueueinfo		__x32_compat_sys_rt_sigqueueinfo
+525	x32	sigaltstack		__x32_compat_sys_sigaltstack
+526	x32	timer_create		__x32_compat_sys_timer_create
+527	x32	mq_notify		__x32_compat_sys_mq_notify
+528	x32	kexec_load		__x32_compat_sys_kexec_load
+529	x32	waitid			__x32_compat_sys_waitid
+530	x32	set_robust_list		__x32_compat_sys_set_robust_list
+531	x32	get_robust_list		__x32_compat_sys_get_robust_list
+532	x32	vmsplice		__x32_compat_sys_vmsplice
+533	x32	move_pages		__x32_compat_sys_move_pages
+534	x32	preadv			__x32_compat_sys_preadv64
+535	x32	pwritev			__x32_compat_sys_pwritev64
+536	x32	rt_tgsigqueueinfo	__x32_compat_sys_rt_tgsigqueueinfo
+537	x32	recvmmsg		__x32_compat_sys_recvmmsg
+538	x32	sendmmsg		__x32_compat_sys_sendmmsg
+539	x32	process_vm_readv	__x32_compat_sys_process_vm_readv
+540	x32	process_vm_writev	__x32_compat_sys_process_vm_writev
+541	x32	setsockopt		__x32_compat_sys_setsockopt
+542	x32	getsockopt		__x32_compat_sys_getsockopt
+543	x32	io_setup		__x32_compat_sys_io_setup
+544	x32	io_submit		__x32_compat_sys_io_submit
+545	x32	execveat		__x32_compat_sys_execveat/ptregs
+546	x32	preadv2			__x32_compat_sys_preadv64v2
+547	x32	pwritev2		__x32_compat_sys_pwritev64v2
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 95036c7a59e8..7879df34569a 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_X86_SP];
 
-	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	map = map_groups__find(thread->mg, (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index f95e6f46ef0d..844b8f335532 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -4,6 +4,8 @@ libperf-y += pmu.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
 libperf-y += group.o
+libperf-y += machine.o
+libperf-y += event.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
new file mode 100644
index 000000000000..675a0213044d
--- /dev/null
+++ b/tools/perf/arch/x86/util/event.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+
+#include "../../util/machine.h"
+#include "../../util/tool.h"
+#include "../../util/map.h"
+#include "../../util/util.h"
+#include "../../util/debug.h"
+
+#if defined(__x86_64__)
+
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int rc = 0;
+	struct map *pos;
+	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps;
+	union perf_event *event = zalloc(sizeof(event->mmap) +
+					 machine->id_hdr_size);
+
+	if (!event) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for extra kernel maps\n");
+		return -1;
+	}
+
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+		struct kmap *kmap;
+		size_t size;
+
+		if (!__map__is_extra_kernel_map(pos))
+			continue;
+
+		kmap = map__kmap(pos);
+
+		size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
+		       PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
+		       machine->id_hdr_size;
+
+		memset(event, 0, size);
+
+		event->mmap.header.type = PERF_RECORD_MMAP;
+
+		/*
+		 * kernel uses 0 for user space maps, see kernel/perf_event.c
+		 * __perf_event_mmap
+		 */
+		if (machine__is_host(machine))
+			event->header.misc = PERF_RECORD_MISC_KERNEL;
+		else
+			event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+		event->mmap.header.size = size;
+
+		event->mmap.start = pos->start;
+		event->mmap.len   = pos->end - pos->start;
+		event->mmap.pgoff = pos->pgoff;
+		event->mmap.pid   = machine->pid;
+
+		strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
+
+		if (perf_tool__process_synth_event(tool, event, machine,
+						   process) != 0) {
+			rc = -1;
+			break;
+		}
+	}
+
+	free(event);
+	return rc;
+}
+
+#endif
diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c
new file mode 100644
index 000000000000..4520ac53caa9
--- /dev/null
+++ b/tools/perf/arch/x86/util/machine.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <stdlib.h>
+
+#include "../../util/machine.h"
+#include "../../util/map.h"
+#include "../../util/symbol.h"
+#include "../../util/sane_ctype.h"
+
+#include <symbol/kallsyms.h>
+
+#if defined(__x86_64__)
+
+struct extra_kernel_map_info {
+	int cnt;
+	int max_cnt;
+	struct extra_kernel_map *maps;
+	bool get_entry_trampolines;
+	u64 entry_trampoline;
+};
+
+static int add_extra_kernel_map(struct extra_kernel_map_info *mi, u64 start,
+				u64 end, u64 pgoff, const char *name)
+{
+	if (mi->cnt >= mi->max_cnt) {
+		void *buf;
+		size_t sz;
+
+		mi->max_cnt = mi->max_cnt ? mi->max_cnt * 2 : 32;
+		sz = sizeof(struct extra_kernel_map) * mi->max_cnt;
+		buf = realloc(mi->maps, sz);
+		if (!buf)
+			return -1;
+		mi->maps = buf;
+	}
+
+	mi->maps[mi->cnt].start = start;
+	mi->maps[mi->cnt].end   = end;
+	mi->maps[mi->cnt].pgoff = pgoff;
+	strlcpy(mi->maps[mi->cnt].name, name, KMAP_NAME_LEN);
+
+	mi->cnt += 1;
+
+	return 0;
+}
+
+static int find_extra_kernel_maps(void *arg, const char *name, char type,
+				  u64 start)
+{
+	struct extra_kernel_map_info *mi = arg;
+
+	if (!mi->entry_trampoline && kallsyms2elf_binding(type) == STB_GLOBAL &&
+	    !strcmp(name, "_entry_trampoline")) {
+		mi->entry_trampoline = start;
+		return 0;
+	}
+
+	if (is_entry_trampoline(name)) {
+		u64 end = start + page_size;
+
+		return add_extra_kernel_map(mi, start, end, 0, name);
+	}
+
+	return 0;
+}
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+				      struct dso *kernel)
+{
+	struct extra_kernel_map_info mi = { .cnt = 0, };
+	char filename[PATH_MAX];
+	int ret;
+	int i;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
+	ret = kallsyms__parse(filename, &mi, find_extra_kernel_maps);
+	if (ret)
+		goto out_free;
+
+	if (!mi.entry_trampoline)
+		goto out_free;
+
+	for (i = 0; i < mi.cnt; i++) {
+		struct extra_kernel_map *xm = &mi.maps[i];
+
+		xm->pgoff = mi.entry_trampoline;
+		ret = machine__create_extra_kernel_map(machine, kernel, xm);
+		if (ret)
+			goto out_free;
+	}
+
+	machine->trampolines_mapped = mi.cnt;
+out_free:
+	free(mi.maps);
+	return ret;
+}
+
+#endif
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 944070e98a2c..63eb49082774 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -175,7 +175,7 @@ static const struct option options[] = {
 	OPT_UINTEGER('s', "nr_secs"	, &p0.nr_secs,		"max number of seconds to run (default: 5 secs)"),
 	OPT_UINTEGER('u', "usleep"	, &p0.sleep_usecs,	"usecs to sleep per loop iteration"),
 
-	OPT_BOOLEAN('R', "data_reads"	, &p0.data_reads,	"access the data via writes (can be mixed with -W)"),
+	OPT_BOOLEAN('R', "data_reads"	, &p0.data_reads,	"access the data via reads (can be mixed with -W)"),
 	OPT_BOOLEAN('W', "data_writes"	, &p0.data_writes,	"access the data via writes (can be mixed with -R)"),
 	OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards,	"access the data backwards as well"),
 	OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"),
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 51709a961496..da5704240239 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -45,6 +45,7 @@ struct perf_annotate {
 	bool	   print_line;
 	bool	   skip_missing;
 	bool	   has_br_stack;
+	bool	   group_set;
 	const char *sym_hist_filter;
 	const char *cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -228,7 +229,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		 */
 		if (al->sym != NULL) {
 			rb_erase(&al->sym->rb_node,
-				 &al->map->dso->symbols[al->map->type]);
+				 &al->map->dso->symbols);
 			symbol__delete(al->sym);
 			dso__reset_find_symbol_cache(al->map->dso);
 		}
@@ -508,6 +509,9 @@ int cmd_annotate(int argc, const char **argv)
 		    "Don't shorten the displayed pathnames"),
 	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
 		    "Skip symbols that cannot be annotated"),
+	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group,
+			&annotate.group_set,
+			"Show event group information together"),
 	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
 	OPT_CALLBACK(0, "symfs", NULL, "directory",
 		     "Look for files with symbols relative to this directory",
@@ -570,6 +574,9 @@ int cmd_annotate(int argc, const char **argv)
 	annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
 						      HEADER_BRANCH_STACK);
 
+	if (annotate.group_set)
+		perf_evlist__force_leader(annotate.session->evlist);
+
 	ret = symbol__annotation_init();
 	if (ret < 0)
 		goto out_delete;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 41db2cba77eb..115110a4796a 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -25,6 +25,7 @@
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/time-utils.h"
+#include "util/probe-file.h"
 
 static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 {
@@ -239,6 +240,34 @@ out:
 	return err;
 }
 
+static int build_id_cache__purge_all(void)
+{
+	struct strlist *list;
+	struct str_node *pos;
+	int err = 0;
+	char *buf;
+
+	list = build_id_cache__list_all(false);
+	if (!list) {
+		pr_debug("Failed to get buildids: -%d\n", errno);
+		return -EINVAL;
+	}
+
+	strlist__for_each_entry(pos, list) {
+		buf = build_id_cache__origname(pos->s);
+		err = build_id_cache__remove_s(pos->s);
+		pr_debug("Removing %s (%s): %s\n", buf, pos->s,
+			 err ? "FAIL" : "Ok");
+		free(buf);
+		if (err)
+			break;
+	}
+	strlist__delete(list);
+
+	pr_debug("Purged all: %s\n", err ? "FAIL" : "Ok");
+	return err;
+}
+
 static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
 {
 	char filename[PATH_MAX];
@@ -297,6 +326,26 @@ static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi)
 	return err;
 }
 
+static int build_id_cache__show_all(void)
+{
+	struct strlist *bidlist;
+	struct str_node *nd;
+	char *buf;
+
+	bidlist = build_id_cache__list_all(true);
+	if (!bidlist) {
+		pr_debug("Failed to get buildids: -%d\n", errno);
+		return -1;
+	}
+	strlist__for_each_entry(nd, bidlist) {
+		buf = build_id_cache__origname(nd->s);
+		fprintf(stdout, "%s %s\n", nd->s, buf);
+		free(buf);
+	}
+	strlist__delete(bidlist);
+	return 0;
+}
+
 int cmd_buildid_cache(int argc, const char **argv)
 {
 	struct strlist *list;
@@ -304,6 +353,9 @@ int cmd_buildid_cache(int argc, const char **argv)
 	int ret = 0;
 	int ns_id = -1;
 	bool force = false;
+	bool list_files = false;
+	bool opts_flag = false;
+	bool purge_all = false;
 	char const *add_name_list_str = NULL,
 		   *remove_name_list_str = NULL,
 		   *purge_name_list_str = NULL,
@@ -327,6 +379,8 @@ int cmd_buildid_cache(int argc, const char **argv)
 		    "file(s) to remove"),
 	OPT_STRING('p', "purge", &purge_name_list_str, "file list",
 		    "file(s) to remove (remove old caches too)"),
+	OPT_BOOLEAN('P', "purge-all", &purge_all, "purge all cached files"),
+	OPT_BOOLEAN('l', "list", &list_files, "list all cached files"),
 	OPT_STRING('M', "missing", &missing_filename, "file",
 		   "to find missing build ids in the cache"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -344,11 +398,20 @@ int cmd_buildid_cache(int argc, const char **argv)
 	argc = parse_options(argc, argv, buildid_cache_options,
 			     buildid_cache_usage, 0);
 
-	if (argc || (!add_name_list_str && !kcore_filename &&
-		     !remove_name_list_str && !purge_name_list_str &&
-		     !missing_filename && !update_name_list_str))
+	opts_flag = add_name_list_str || kcore_filename ||
+		remove_name_list_str || purge_name_list_str ||
+		missing_filename || update_name_list_str ||
+		purge_all;
+
+	if (argc || !(list_files || opts_flag))
 		usage_with_options(buildid_cache_usage, buildid_cache_options);
 
+	/* -l is exclusive. It can not be used with other options. */
+	if (list_files && opts_flag) {
+		usage_with_options_msg(buildid_cache_usage,
+			buildid_cache_options, "-l is exclusive.\n");
+	}
+
 	if (ns_id > 0)
 		nsi = nsinfo__new(ns_id);
 
@@ -366,6 +429,11 @@ int cmd_buildid_cache(int argc, const char **argv)
 
 	setup_pager();
 
+	if (list_files) {
+		ret = build_id_cache__show_all();
+		goto out;
+	}
+
 	if (add_name_list_str) {
 		list = strlist__new(add_name_list_str, NULL);
 		if (list) {
@@ -420,6 +488,13 @@ int cmd_buildid_cache(int argc, const char **argv)
 		}
 	}
 
+	if (purge_all) {
+		if (build_id_cache__purge_all()) {
+			pr_warning("Couldn't remove some caches. Error: %s.\n",
+				str_error_r(errno, sbuf, sizeof(sbuf)));
+		}
+	}
+
 	if (missing_filename)
 		ret = build_id_cache__fprintf_missing(session, stdout);
 
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 4aca13f23b9d..1c41b4eaf73c 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -439,7 +439,7 @@ int cmd_help(int argc, const char **argv)
 #ifdef HAVE_LIBELF_SUPPORT
 		"probe",
 #endif
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
 		"trace",
 #endif
 	NULL };
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40fe919bbcf3..a3b346359ba0 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -440,9 +440,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 		goto repipe;
 	}
 
-	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
-
-	if (al.map != NULL) {
+	if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) {
 		if (!al.map->dso->hit) {
 			al.map->dso->hit = 1;
 			if (map__load(al.map) >= 0) {
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
index bcfb363112d3..90d1a2305b72 100644
--- a/tools/perf/builtin-kallsyms.c
+++ b/tools/perf/builtin-kallsyms.c
@@ -27,7 +27,7 @@ static int __cmd_kallsyms(int argc, const char **argv)
 
 	for (i = 0; i < argc; ++i) {
 		struct map *map;
-		struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+		struct symbol *symbol = machine__find_kernel_symbol_by_name(machine, argv[i], &map);
 
 		if (symbol == NULL) {
 			printf("%s: not found\n", argv[i]);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index ae11e4c3516a..54d3f21b0e62 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1004,7 +1004,7 @@ static void __print_slab_result(struct rb_root *root,
 		if (is_caller) {
 			addr = data->call_site;
 			if (!raw_ip)
-				sym = machine__find_kernel_function(machine, addr, &map);
+				sym = machine__find_kernel_symbol(machine, addr, &map);
 		} else
 			addr = data->ptr;
 
@@ -1068,7 +1068,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
-		sym = machine__find_kernel_function(machine, data->callsite, &map);
+		sym = machine__find_kernel_symbol(machine, data->callsite, &map);
 		if (sym)
 			caller = sym->name;
 		else
@@ -1110,7 +1110,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
 		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
-		sym = machine__find_kernel_function(machine, data->callsite, &map);
+		sym = machine__find_kernel_symbol(machine, data->callsite, &map);
 		if (sym)
 			caller = sym->name;
 		else
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 506564651cda..57393e94d156 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -83,7 +83,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	};
 
 	argc = parse_options(argc, argv, options, record_mem_usage,
-			     PARSE_OPT_STOP_AT_NON_OPTION);
+			     PARSE_OPT_KEEP_UNKNOWN);
 
 	rec_argc = argc + 9; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -436,7 +436,7 @@ int cmd_mem(int argc, const char **argv)
 	}
 
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
-					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
+					mem_usage, PARSE_OPT_KEEP_UNKNOWN);
 
 	if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation))
 		usage_with_options(mem_usage, mem_options);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0f198f6d9b77..ad978e3ee2b8 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -194,20 +194,11 @@ out:
 	return err;
 }
 
-/*
- * Events in data file are not collect in groups, but we still want
- * the group display. Set the artificial group and set the leader's
- * forced_leader flag to notify the display code.
- */
 static void setup_forced_leader(struct report *report,
 				struct perf_evlist *evlist)
 {
-	if (report->group_set && !evlist->nr_groups) {
-		struct perf_evsel *leader = perf_evlist__first(evlist);
-
-		perf_evlist__set_leader(evlist);
-		leader->forced_leader = true;
-	}
+	if (report->group_set)
+		perf_evlist__force_leader(evlist);
 }
 
 static int process_feature_event(struct perf_tool *tool,
@@ -523,12 +514,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
 		    "As no suitable kallsyms nor vmlinux was found, kernel samples\n"
 		    "can't be resolved.";
 
-		if (kernel_map) {
-			const struct dso *kdso = kernel_map->dso;
-			if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
-				desc = "If some relocation was applied (e.g. "
-				       "kexec) symbols may be misresolved.";
-			}
+		if (kernel_map && map__has_symbols(kernel_map)) {
+			desc = "If some relocation was applied (e.g. "
+			       "kexec) symbols may be misresolved.";
 		}
 
 		ui__warning(
@@ -718,10 +706,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
 
 static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp)
 {
-	int printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += maps__fprintf_task(&mg->maps[i], indent, fp);
-	return printed;
+	return maps__fprintf_task(&mg->maps, indent, fp);
 }
 
 static void task__print_level(struct task *task, FILE *fp, int level)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 313c42423393..cefc8813e91e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -153,8 +153,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -165,8 +165,9 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
+			      PERF_OUTPUT_BPF_OUTPUT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -185,10 +186,10 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
-			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
-			      PERF_OUTPUT_PHYS_ADDR,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
+			      PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
+			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -199,8 +200,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -211,8 +212,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_SYNTH,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_SYNTH,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -544,6 +545,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 			if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
 				output[j].fields |= PERF_OUTPUT_IP;
 				output[j].fields |= PERF_OUTPUT_SYM;
+				output[j].fields |= PERF_OUTPUT_SYMOFFSET;
 				output[j].fields |= PERF_OUTPUT_DSO;
 				set_print_ip_opts(attr);
 				goto out;
@@ -657,8 +659,11 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
 			break;
 		case PERF_RECORD_SWITCH:
 		case PERF_RECORD_SWITCH_CPU_WIDE:
-			if (has(SWITCH_OUT))
+			if (has(SWITCH_OUT)) {
 				ret += fprintf(fp, "S");
+				if (sample->misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT)
+					ret += fprintf(fp, "p");
+			}
 		default:
 			break;
 		}
@@ -714,8 +719,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
 		if (PRINT_FIELD(DSO)) {
 			memset(&alf, 0, sizeof(alf));
 			memset(&alt, 0, sizeof(alt));
-			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
-			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
+			thread__find_map(thread, sample->cpumode, from, &alf);
+			thread__find_map(thread, sample->cpumode, to, &alt);
 		}
 
 		printed += fprintf(fp, " 0x%"PRIx64, from);
@@ -761,13 +766,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
 		from = br->entries[i].from;
 		to   = br->entries[i].to;
 
-		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
-		if (alf.map)
-			alf.sym = map__find_symbol(alf.map, alf.addr);
-
-		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
-		if (alt.map)
-			alt.sym = map__find_symbol(alt.map, alt.addr);
+		thread__find_symbol(thread, sample->cpumode, from, &alf);
+		thread__find_symbol(thread, sample->cpumode, to, &alt);
 
 		printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp);
 		if (PRINT_FIELD(DSO)) {
@@ -811,12 +811,12 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
 		from = br->entries[i].from;
 		to   = br->entries[i].to;
 
-		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
-		if (alf.map && !alf.map->dso->adjust_symbols)
+		if (thread__find_map(thread, sample->cpumode, from, &alf) &&
+		    !alf.map->dso->adjust_symbols)
 			from = map__map_ip(alf.map, from);
 
-		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
-		if (alt.map && !alt.map->dso->adjust_symbols)
+		if (thread__find_map(thread, sample->cpumode, to, &alt) &&
+		    !alt.map->dso->adjust_symbols)
 			to = map__map_ip(alt.map, to);
 
 		printed += fprintf(fp, " 0x%"PRIx64, from);
@@ -879,8 +879,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 		return 0;
 	}
 
-	thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
-	if (!al.map || !al.map->dso) {
+	if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) {
 		pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
 		return 0;
 	}
@@ -930,10 +929,8 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread,
 
 	memset(&al, 0, sizeof(al));
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
-	if (!al.map)
-		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
-				      addr, &al);
+	thread__find_map(thread, cpumode, addr, &al);
+
 	if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
 		return 0;
 
@@ -2801,11 +2798,11 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
 			  lang_dirent->d_name);
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
 		if (strstr(lang_path, "perl"))
 			continue;
 #endif
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
 		if (strstr(lang_path, "python"))
 			continue;
 #endif
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f5c454855908..a4f662a462c6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -164,6 +164,7 @@ static bool			forever				= false;
 static bool			metric_only			= false;
 static bool			force_metric_only		= false;
 static bool			no_merge			= false;
+static bool			walltime_run_table		= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -172,6 +173,8 @@ static bool			interval_count;
 static const char		*output_name;
 static int			output_fd;
 static int			print_free_counters_hint;
+static int			print_mixed_hw_group_error;
+static u64			*walltime_run;
 
 struct perf_stat {
 	bool			 record;
@@ -568,7 +571,7 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
 	return leader;
 }
 
-static int __run_perf_stat(int argc, const char **argv)
+static int __run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int interval = stat_config.interval;
 	int times = stat_config.times;
@@ -751,6 +754,9 @@ try_again:
 
 	t1 = rdclock();
 
+	if (walltime_run_table)
+		walltime_run[run_idx] = t1 - t0;
+
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
 	/*
@@ -765,7 +771,7 @@ try_again:
 	return WEXITSTATUS(status);
 }
 
-static int run_perf_stat(int argc, const char **argv)
+static int run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int ret;
 
@@ -778,7 +784,7 @@ static int run_perf_stat(int argc, const char **argv)
 	if (sync_run)
 		sync();
 
-	ret = __run_perf_stat(argc, argv);
+	ret = __run_perf_stat(argc, argv, run_idx);
 	if (ret)
 		return ret;
 
@@ -1126,6 +1132,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
+static bool is_mixed_hw_group(struct perf_evsel *counter)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	u32 pmu_type = counter->attr.type;
+	struct perf_evsel *pos;
+
+	if (counter->nr_members < 2)
+		return false;
+
+	evlist__for_each_entry(evlist, pos) {
+		/* software events can be part of any hardware group */
+		if (pos->attr.type == PERF_TYPE_SOFTWARE)
+			continue;
+		if (pmu_type == PERF_TYPE_SOFTWARE) {
+			pmu_type = pos->attr.type;
+			continue;
+		}
+		if (pmu_type != pos->attr.type)
+			return true;
+	}
+
+	return false;
+}
+
 static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		     char *prefix, u64 run, u64 ena, double noise,
 		     struct runtime_stat *st)
@@ -1178,8 +1208,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 			csv_sep);
 
-		if (counter->supported)
+		if (counter->supported) {
 			print_free_counters_hint = 1;
+			if (is_mixed_hw_group(counter))
+				print_mixed_hw_group_error = 1;
+		}
 
 		fprintf(stat_config.output, "%-*s%s",
 			csv_output ? 0 : unit_width,
@@ -1256,7 +1289,8 @@ static void uniquify_event_name(struct perf_evsel *counter)
 	char *new_name;
 	char *config;
 
-	if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+	if (counter->uniquified_name ||
+	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
 					   strlen(counter->pmu_name)))
 		return;
 
@@ -1274,6 +1308,8 @@ static void uniquify_event_name(struct perf_evsel *counter)
 			counter->name = new_name;
 		}
 	}
+
+	counter->uniquified_name = true;
 }
 
 static void collect_all_aliases(struct perf_evsel *counter,
@@ -1733,19 +1769,67 @@ static void print_header(int argc, const char **argv)
 	}
 }
 
+static int get_precision(double num)
+{
+	if (num > 1)
+		return 0;
+
+	return lround(ceil(-log10(num)));
+}
+
+static void print_table(FILE *output, int precision, double avg)
+{
+	char tmp[64];
+	int idx, indent = 0;
+
+	scnprintf(tmp, 64, " %17.*f", precision, avg);
+	while (tmp[indent] == ' ')
+		indent++;
+
+	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
+
+	for (idx = 0; idx < run_count; idx++) {
+		double run = (double) walltime_run[idx] / NSEC_PER_SEC;
+		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
+
+		fprintf(output, " %17.*f (%+.*f) ",
+			precision, run, precision, run - avg);
+
+		for (h = 0; h < n; h++)
+			fprintf(output, "#");
+
+		fprintf(output, "\n");
+	}
+
+	fprintf(output, "\n%*s# Final result:\n", indent, "");
+}
+
 static void print_footer(void)
 {
+	double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
 	FILE *output = stat_config.output;
 	int n;
 
 	if (!null_run)
 		fprintf(output, "\n");
-	fprintf(output, " %17.9f seconds time elapsed",
-			avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC);
-	if (run_count > 1) {
-		fprintf(output, "                                        ");
-		print_noise_pct(stddev_stats(&walltime_nsecs_stats),
-				avg_stats(&walltime_nsecs_stats));
+
+	if (run_count == 1) {
+		fprintf(output, " %17.9f seconds time elapsed", avg);
+	} else {
+		double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
+		/*
+		 * Display at most 2 more significant
+		 * digits than the stddev inaccuracy.
+		 */
+		int precision = get_precision(sd) + 2;
+
+		if (walltime_run_table)
+			print_table(output, precision, avg);
+
+		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+			precision, avg, precision, sd);
+
+		print_noise_pct(sd, avg);
 	}
 	fprintf(output, "\n\n");
 
@@ -1757,6 +1841,11 @@ static void print_footer(void)
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
 "	perf stat ...\n"
 "	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+
+	if (print_mixed_hw_group_error)
+		fprintf(output,
+			"The events in group usually have to be from "
+			"the same PMU. Try reorganizing the group.\n");
 }
 
 static void print_counters(struct timespec *ts, int argc, const char **argv)
@@ -1916,6 +2005,8 @@ static const struct option stat_options[] = {
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_INTEGER('r', "repeat", &run_count,
 		    "repeat command and print average + stddev (max: 100, forever: 0)"),
+	OPT_BOOLEAN(0, "table", &walltime_run_table,
+		    "display details about each run (only with -r option)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
 	OPT_INCR('d', "detailed", &detailed_run,
@@ -1943,7 +2034,8 @@ static const struct option stat_options[] = {
 	OPT_STRING(0, "post", &post_cmd, "command",
 			"command to run after to the measured command"),
 	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
-		    "print counts at regular interval in ms (>= 10)"),
+		    "print counts at regular interval in ms "
+		    "(overhead is possible for values <= 100ms)"),
 	OPT_INTEGER(0, "interval-count", &stat_config.times,
 		    "print counts for fixed number of times"),
 	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
@@ -2806,6 +2898,13 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
+	if (walltime_run_table && run_count <= 1) {
+		fprintf(stderr, "--table is only supported with -r\n");
+		parse_options_usage(stat_usage, stat_options, "r", 1);
+		parse_options_usage(NULL, stat_options, "table", 0);
+		goto out;
+	}
+
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
 		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
@@ -2860,6 +2959,14 @@ int cmd_stat(int argc, const char **argv)
 		run_count = 1;
 	}
 
+	if (walltime_run_table) {
+		walltime_run = zalloc(run_count * sizeof(walltime_run[0]));
+		if (!walltime_run) {
+			pr_err("failed to setup -r option");
+			goto out;
+		}
+	}
+
 	if ((stat_config.aggr_mode == AGGR_THREAD) &&
 		!target__has_task(&target)) {
 		if (!target.system_wide || target.cpu_list) {
@@ -2923,17 +3030,6 @@ int cmd_stat(int argc, const char **argv)
 		}
 	}
 
-	if (interval && interval < 100) {
-		if (interval < 10) {
-			pr_err("print interval must be >= 10ms\n");
-			parse_options_usage(stat_usage, stat_options, "I", 1);
-			goto out;
-		} else
-			pr_warning("print interval < 100ms. "
-				   "The overhead percentage could be high in some cases. "
-				   "Please proceed with caution.\n");
-	}
-
 	if (stat_config.times && interval)
 		interval_count = true;
 	else if (stat_config.times && !interval) {
@@ -2986,7 +3082,7 @@ int cmd_stat(int argc, const char **argv)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
-		status = run_perf_stat(argc, argv);
+		status = run_perf_stat(argc, argv, run_idx);
 		if (forever && status != -1) {
 			print_counters(NULL, argc, argv);
 			perf_stat__reset_stats();
@@ -3034,6 +3130,8 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__exit_aggr_mode();
 	perf_evlist__free_stats(evsel_list);
 out:
+	free(walltime_run);
+
 	if (smi_cost && smi_reset)
 		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 813698a9b8c7..a827919c6263 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -533,12 +533,8 @@ static const char *cat_backtrace(union perf_event *event,
 		}
 
 		tal.filtered = 0;
-		thread__find_addr_location(al.thread, cpumode,
-					   MAP__FUNCTION, ip, &tal);
-
-		if (tal.sym)
-			fprintf(f, "..... %016" PRIx64 " %s\n", ip,
-				tal.sym->name);
+		if (thread__find_symbol(al.thread, cpumode, ip, &tal))
+			fprintf(f, "..... %016" PRIx64 " %s\n", ip, tal.sym->name);
 		else
 			fprintf(f, "..... %016" PRIx64 "\n", ip);
 	}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index f39bd60d2708..7a349fcd3864 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -742,7 +742,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
-			  al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  al.map && map__has_symbols(al.map) ?
 			  " modules" : "");
 			if (use_browser <= 0)
 				sleep(5);
@@ -750,7 +750,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		machine->kptr_restrict_warned = true;
 	}
 
-	if (al.sym == NULL) {
+	if (al.sym == NULL && al.map != NULL) {
 		const char *msg = "Kernel samples will not be resolved.\n";
 		/*
 		 * As we do lazy loading of symtabs we only will know if the
@@ -764,8 +764,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		 * invalid --vmlinux ;-)
 		 */
 		if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
-		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
-		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
+		    __map__is_kernel(al.map) && map__has_symbols(al.map)) {
 			if (symbol_conf.vmlinux_name) {
 				char serr[256];
 				dso__strerror_load(al.map->dso, serr, sizeof(serr));
@@ -1265,7 +1264,7 @@ int cmd_top(int argc, const char **argv)
 			.proc_map_timeout    = 500,
 			.overwrite	= 1,
 		},
-		.max_stack	     = sysctl_perf_event_max_stack,
+		.max_stack	     = sysctl__max_stack(),
 		.sym_pcnt_filter     = 5,
 		.nr_threads_synthesize = UINT_MAX,
 	};
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 3ad17ee89403..560aed7da36a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2024,8 +2024,7 @@ static int trace__pgfault(struct trace *trace,
 	if (trace->summary_only)
 		goto out;
 
-	thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION,
-			      sample->ip, &al);
+	thread__find_symbol(thread, sample->cpumode, sample->ip, &al);
 
 	trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
 
@@ -2037,12 +2036,10 @@ static int trace__pgfault(struct trace *trace,
 
 	fprintf(trace->output, "] => ");
 
-	thread__find_addr_location(thread, sample->cpumode, MAP__VARIABLE,
-				   sample->addr, &al);
+	thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
 
 	if (!al.map) {
-		thread__find_addr_location(thread, sample->cpumode,
-					   MAP__FUNCTION, sample->addr, &al);
+		thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
 
 		if (al.map)
 			map_type = 'x';
@@ -3165,7 +3162,7 @@ int cmd_trace(int argc, const char **argv)
 		mmap_pages_user_set = false;
 
 	if (trace.max_stack == UINT_MAX) {
-		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
+		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl__max_stack();
 		max_stack_user_set = false;
 	}
 
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 2abe3910d6b6..50df168be326 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -60,7 +60,10 @@ static void library_status(void)
 	STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations);
 	STATUS(HAVE_GLIBC_SUPPORT, glibc);
 	STATUS(HAVE_GTK2_SUPPORT, gtk2);
+#ifndef HAVE_SYSCALL_TABLE_SUPPORT
 	STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit);
+#endif
+	STATUS(HAVE_SYSCALL_TABLE_SUPPORT, syscall_table);
 	STATUS(HAVE_LIBBFD_SUPPORT, libbfd);
 	STATUS(HAVE_LIBELF_SUPPORT, libelf);
 	STATUS(HAVE_LIBNUMA_SUPPORT, libnuma);
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 9aff89bc7535..10f333e2e825 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -55,22 +55,26 @@ include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
 '
 
-check () {
-  file=$1
+check_2 () {
+  file1=$1
+  file2=$2
 
   shift
-  opts=
-  while [ -n "$*" ]; do
-    opts="$opts \"$1\""
-    shift
-  done
+  shift
 
-  cmd="diff $opts ../$file ../../$file > /dev/null"
+  cmd="diff $* $file1 $file2 > /dev/null"
 
-  test -f ../../$file &&
+  test -f $file2 &&
   eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2
 }
 
+check () {
+  file=$1
+
+  shift
+
+  check_2 ../$file ../../$file $*
+}
 
 # Check if we have the kernel headers (tools/perf/../../include), else
 # we're probably on a detached tarball, so no point in trying to check
@@ -83,7 +87,7 @@ for i in $HEADERS; do
 done
 
 # diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S        -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check arch/x86/lib/memset_64.S        -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check include/uapi/asm-generic/mman.h -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
-check include/uapi/linux/mman.h       -I "^#include <\(uapi/\)*asm/mman.h>"
+check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
new file mode 100644
index 000000000000..b9c203219691
--- /dev/null
+++ b/tools/perf/examples/bpf/5sec.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+    Description:
+
+    . Disable strace like syscall tracing (--no-syscalls), or try tracing
+      just some (-e *sleep).
+
+    . Attach a filter function to a kernel function, returning when it should
+      be considered, i.e. appear on the output.
+
+    . Run it system wide, so that any sleep of >= 5 seconds and < than 6
+      seconds gets caught.
+
+    . Ask for callgraphs using DWARF info, so that userspace can be unwound
+
+    . While this is running, run something like "sleep 5s".
+
+    . If we decide to add tv_nsec as well, then it becomes:
+
+      int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec)
+
+      I.e. add where it comes from (rqtp->tv_nsec) and where it will be
+      accessible in the function body (nsec)
+
+    # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/
+         0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5
+                                           hrtimer_nanosleep ([kernel.kallsyms])
+                                           __x64_sys_nanosleep ([kernel.kallsyms])
+                                           do_syscall_64 ([kernel.kallsyms])
+                                           entry_SYSCALL_64 ([kernel.kallsyms])
+                                           __GI___nanosleep (/usr/lib64/libc-2.26.so)
+                                           rpl_nanosleep (/usr/bin/sleep)
+                                           xnanosleep (/usr/bin/sleep)
+                                           main (/usr/bin/sleep)
+                                           __libc_start_main (/usr/lib64/libc-2.26.so)
+                                           _start (/usr/bin/sleep)
+    ^C#
+
+   Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
+*/
+
+#include <bpf.h>
+
+int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
+{
+	return sec == 5;
+}
+
+license(GPL);
diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c
new file mode 100644
index 000000000000..3776d26db9e7
--- /dev/null
+++ b/tools/perf/examples/bpf/empty.c
@@ -0,0 +1,3 @@
+#include <bpf.h>
+
+license(GPL);
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
new file mode 100644
index 000000000000..dd764ad5efdf
--- /dev/null
+++ b/tools/perf/include/bpf/bpf.h
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _PERF_BPF_H
+#define _PERF_BPF_H
+#define SEC(NAME) __attribute__((section(NAME),  used))
+
+#define probe(function, vars) \
+	SEC(#function "=" #function " " #vars) function
+
+#define license(name) \
+char _license[] SEC("license") = #name; \
+int _version SEC("version") = LINUX_VERSION_CODE;
+
+#endif /* _PERF_BPF_H */
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 1659029d03fc..51c81509a315 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -73,7 +73,7 @@ static struct cmd_struct commands[] = {
 	{ "lock",	cmd_lock,	0 },
 	{ "kvm",	cmd_kvm,	0 },
 	{ "test",	cmd_test,	0 },
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
 	{ "trace",	cmd_trace,	0 },
 #endif
 	{ "inject",	cmd_inject,	0 },
@@ -238,7 +238,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 			(*argc)--;
 		} else if (strstarts(cmd, CMD_DEBUGFS_DIR)) {
 			tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR));
-			fprintf(stderr, "dir: %s\n", tracing_path);
+			fprintf(stderr, "dir: %s\n", tracing_path_mount());
 			if (envchanged)
 				*envchanged = 1;
 		} else if (!strcmp(cmd, "--list-cmds")) {
@@ -421,22 +421,11 @@ void pthread__unblock_sigwinch(void)
 	pthread_sigmask(SIG_UNBLOCK, &set, NULL);
 }
 
-#ifdef _SC_LEVEL1_DCACHE_LINESIZE
-#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
-#else
-static void cache_line_size(int *cacheline_sizep)
-{
-	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
-		pr_debug("cannot determine cache line size");
-}
-#endif
-
 int main(int argc, const char **argv)
 {
 	int err;
 	const char *cmd;
 	char sbuf[STRERR_BUFSIZE];
-	int value;
 
 	/* libsubcmd init */
 	exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT);
@@ -444,13 +433,6 @@ int main(int argc, const char **argv)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
-	cache_line_size(&cacheline_size);
-
-	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
-		sysctl_perf_event_max_stack = value;
-
-	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
-		sysctl_perf_event_max_contexts_per_stack = value;
 
 	cmd = extract_argv0_path(argv[0]);
 	if (!cmd)
@@ -458,15 +440,11 @@ int main(int argc, const char **argv)
 
 	srandom(time(NULL));
 
-	perf_config__init();
 	err = perf_config(perf_default_config, NULL);
 	if (err)
 		return err;
 	set_buildid_dir(NULL);
 
-	/* get debugfs/tracefs mount point from /proc/mounts */
-	tracing_path_mount();
-
 	/*
 	 * "perf-xxxx" is the same as "perf xxxx", but we obviously:
 	 *
@@ -491,7 +469,7 @@ int main(int argc, const char **argv)
 		argv[0] = cmd;
 	}
 	if (strstarts(cmd, "trace")) {
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
 		setup_path();
 		argv[0] = "trace";
 		return cmd_trace(argc, argv);
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index ca7682748a4b..78bcf7f8e206 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -1,6 +1,6 @@
 Family-model,Version,Filename,EventType
-209[78],1,cf_z10,core
-281[78],1,cf_z196,core
-282[78],1,cf_zec12,core
-296[45],1,cf_z13,core
-3906,3,cf_z14,core
+^IBM.209[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z10,core
+^IBM.281[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z196,core
+^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core
+^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
+^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 93656f2fd53a..7e3cce3bcf3b 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -29,7 +29,6 @@ GenuineIntel-6-4D,v13,silvermont,core
 GenuineIntel-6-4C,v13,silvermont,core
 GenuineIntel-6-2A,v15,sandybridge,core
 GenuineIntel-6-2C,v2,westmereep-dp,core
-GenuineIntel-6-2C,v2,westmereep-dp,core
 GenuineIntel-6-25,v2,westmereep-sp,core
 GenuineIntel-6-2F,v2,westmereex,core
 GenuineIntel-6-55,v1,skylakex,core
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index f906b793196f..8a33ca4f9e1f 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -35,3 +35,6 @@ inherit=0
 # sampling disabled
 sample_freq=0
 sample_period=0
+freq=0
+write_backward=0
+sample_id_all=0
diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index e4123c1b0e88..1ca5106df5f1 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -31,7 +31,7 @@ struct bpf_map_def SEC("maps") flip_table = {
 	.max_entries = 1,
 };
 
-SEC("func=SyS_epoll_pwait")
+SEC("func=do_epoll_wait")
 int bpf_func__SyS_epoll_pwait(void *ctx)
 {
 	int ind =0;
diff --git a/tools/perf/tests/bpf-script-test-kbuild.c b/tools/perf/tests/bpf-script-test-kbuild.c
index 3626924740d8..ff3ec8337f0a 100644
--- a/tools/perf/tests/bpf-script-test-kbuild.c
+++ b/tools/perf/tests/bpf-script-test-kbuild.c
@@ -9,7 +9,6 @@
 #define SEC(NAME) __attribute__((section(NAME), used))
 
 #include <uapi/linux/fs.h>
-#include <uapi/asm/ptrace.h>
 
 SEC("func=vfs_llseek")
 int bpf_func__vfs_llseek(void *ctx)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 625f5a6772af..2bde505e2e7e 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -118,6 +118,7 @@ static struct test generic_tests[] = {
 	{
 		.desc = "Breakpoint accounting",
 		.func = test__bp_accounting,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Number of exit events of a simple workload",
@@ -653,6 +654,15 @@ static int perf_test__list(int argc, const char **argv)
 			continue;
 
 		pr_info("%2d: %s\n", i, t->desc);
+
+		if (t->subtest.get_nr) {
+			int subn = t->subtest.get_nr();
+			int subi;
+
+			for (subi = 0; subi < subn; subi++)
+				pr_info("%2d:%1d: %s\n", i, subi + 1,
+					t->subtest.get_desc(subi));
+		}
 	}
 
 	perf_test__list_shell(argc, argv, i);
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 99936352df4f..afa4ce21ba7c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -236,14 +236,13 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
-	if (!al.map || !al.map->dso) {
+	if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) {
 		if (cpumode == PERF_RECORD_MISC_HYPERVISOR) {
 			pr_debug("Hypervisor address can not be resolved - skipping\n");
 			return 0;
 		}
 
-		pr_debug("thread__find_addr_map failed\n");
+		pr_debug("thread__find_map failed\n");
 		return -1;
 	}
 
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index f7c5b613d667..b889a28fd80b 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -131,20 +131,20 @@ struct machine *setup_fake_machine(struct machines *machines)
 			goto out;
 
 		/* emulate dso__load() */
-		dso__set_loaded(dso, MAP__FUNCTION);
+		dso__set_loaded(dso);
 
 		for (k = 0; k < fake_symbols[i].nr_syms; k++) {
 			struct symbol *sym;
 			struct fake_sym *fsym = &fake_symbols[i].syms[k];
 
 			sym = symbol__new(fsym->start, fsym->length,
-					  STB_GLOBAL, fsym->name);
+					  STB_GLOBAL, STT_FUNC, fsym->name);
 			if (sym == NULL) {
 				dso__put(dso);
 				goto out;
 			}
 
-			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
+			symbols__insert(&dso->symbols, sym);
 		}
 
 		dso__put(dso);
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index bb8e6bcb0d96..0919b0793e5b 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -75,7 +75,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
 		evsels[i] = perf_evsel__newtp("syscalls", name);
 		if (IS_ERR(evsels[i])) {
-			pr_debug("perf_evsel__new\n");
+			pr_debug("perf_evsel__new(%s)\n", name);
 			goto out_delete_evlist;
 		}
 
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 868d82b501f4..b1af2499a3c9 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -188,9 +188,8 @@ static int mmap_events(synth_cb synth)
 
 		pr_debug("looking for map %p\n", td->map);
 
-		thread__find_addr_map(thread,
-				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
-				      (unsigned long) (td->map + 1), &al);
+		thread__find_map(thread, PERF_RECORD_MISC_USER,
+				 (unsigned long) (td->map + 1), &al);
 
 		thread__put(thread);
 
@@ -218,7 +217,7 @@ static int mmap_events(synth_cb synth)
  *   perf_event__synthesize_threads    (global)
  *
  * We test we can find all memory maps via:
- *   thread__find_addr_map
+ *   thread__find_map
  *
  * by using all thread objects.
  */
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 18b06444f230..b9ebe15afb13 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,18 +1309,26 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__intel_pt(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
 	DIR *events_dir;
 	int cnt = 0;
 
-	events_dir = opendir(tracing_events_path);
+	events_dir = tracing_events__opendir();
 
 	TEST_ASSERT_VAL("Can't open events dir", events_dir);
 
 	while ((events_ent = readdir(events_dir))) {
-		char sys_path[PATH_MAX];
+		char *sys_path;
 		struct dirent *sys_ent;
 		DIR *sys_dir;
 
@@ -1331,8 +1339,8 @@ static int count_tracepoints(void)
 		    || !strcmp(events_ent->d_name, "header_page"))
 			continue;
 
-		scnprintf(sys_path, PATH_MAX, "%s/%s",
-			  tracing_events_path, events_ent->d_name);
+		sys_path = get_events_file(events_ent->d_name);
+		TEST_ASSERT_VAL("Can't get sys path", sys_path);
 
 		sys_dir = opendir(sys_path);
 		TEST_ASSERT_VAL("Can't open sys dir", sys_dir);
@@ -1348,6 +1356,7 @@ static int count_tracepoints(void)
 		}
 
 		closedir(sys_dir);
+		put_events_file(sys_path);
 	}
 
 	closedir(events_dir);
@@ -1637,6 +1646,11 @@ static struct evlist_test test__events[] = {
 		.check = test__checkevent_config_cache,
 		.id    = 51,
 	},
+	{
+		.name  = "intel_pt//u",
+		.check = test__intel_pt,
+		.id    = 52,
+	},
 };
 
 static struct evlist_test test__events_pmu[] = {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 1ecc1f0ff84a..650b208f700f 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -16,20 +16,18 @@ nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 trace_libc_inet_pton_backtrace() {
 	idx=0
 	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton[[:space:]]\($libc\)$"
+	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
 	case "$(uname -m)" in
 	s390x)
-		eventattr='call-graph=dwarf'
-		expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$"
-		expected[3]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$"
-		expected[4]="main[[:space:]]\(.*/bin/ping.*\)$"
-		expected[5]="__libc_start_main[[:space:]]\($libc\)$"
-		expected[6]="_start[[:space:]]\(.*/bin/ping.*\)$"
+		eventattr='call-graph=dwarf,max-stack=4'
+		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo[[:space:]]\($libc\)$"
-		expected[3]=".*\(.*/bin/ping.*\)$"
+		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
+		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
 		;;
 	esac
 
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 17cb1bb3448c..40e30a26b23c 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -70,6 +70,27 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
 	session = perf_session__new(&data, false, NULL);
 	TEST_ASSERT_VAL("can't get session", session);
 
+	/* On platforms with large numbers of CPUs process_cpu_topology()
+	 * might issue an error while reading the perf.data file section
+	 * HEADER_CPU_TOPOLOGY and the cpu_topology_map pointed to by member
+	 * cpu is a NULL pointer.
+	 * Example: On s390
+	 *   CPU 0 is on core_id 0 and physical_package_id 6
+	 *   CPU 1 is on core_id 1 and physical_package_id 3
+	 *
+	 *   Core_id and physical_package_id are platform and architecture
+	 *   dependend and might have higher numbers than the CPU id.
+	 *   This actually depends on the configuration.
+	 *
+	 *  In this case process_cpu_topology() prints error message:
+	 *  "socket_id number is too big. You may need to upgrade the
+	 *  perf tool."
+	 *
+	 *  This is the reason why this test might be skipped.
+	 */
+	if (!session->header.env.cpu)
+		return TEST_SKIP;
+
 	for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
 		if (!cpu_map__has(map, i))
 			continue;
@@ -95,7 +116,7 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe
 {
 	char path[PATH_MAX];
 	struct cpu_map *map;
-	int ret = -1;
+	int ret = TEST_FAIL;
 
 	TEST_ASSERT_VAL("can't get templ file", !get_temp(path));
 
@@ -110,12 +131,9 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe
 		goto free_path;
 	}
 
-	if (check_cpu_topology(path, map))
-		goto free_map;
-	ret = 0;
-
-free_map:
+	ret = check_cpu_topology(path, map);
 	cpu_map__put(map);
+
 free_path:
 	unlink(path);
 	return ret;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 1e5adb65632a..7691980b7df1 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -19,8 +19,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	struct symbol *sym;
 	struct map *kallsyms_map, *vmlinux_map, *map;
 	struct machine kallsyms, vmlinux;
-	enum map_type type = MAP__FUNCTION;
-	struct maps *maps = &vmlinux.kmaps.maps[type];
+	struct maps *maps = machine__kernel_maps(&vmlinux);
 	u64 mem_start, mem_end;
 	bool header_printed;
 
@@ -56,7 +55,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	 * be compacted against the list of modules found in the "vmlinux"
 	 * code and with the one got from /proc/modules from the "kallsyms" code.
 	 */
-	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type) <= 0) {
+	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms") <= 0) {
 		pr_debug("dso__load_kallsyms ");
 		goto out;
 	}
@@ -94,7 +93,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	 * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines
 	 * to fixup the symbols.
 	 */
-	if (machine__load_vmlinux_path(&vmlinux, type) <= 0) {
+	if (machine__load_vmlinux_path(&vmlinux) <= 0) {
 		pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n");
 		err = TEST_SKIP;
 		goto out;
@@ -108,7 +107,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	 * in the kallsyms dso. For the ones that are in both, check its names and
 	 * end addresses too.
 	 */
-	for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
+	map__for_each_symbol(vmlinux_map, sym, nd) {
 		struct symbol *pair, *first_pair;
 
 		sym  = rb_entry(nd, struct symbol, rb_node);
@@ -119,8 +118,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 		mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start);
 		mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end);
 
-		first_pair = machine__find_kernel_symbol(&kallsyms, type,
-							 mem_start, NULL);
+		first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL);
 		pair = first_pair;
 
 		if (pair && UM(pair->start) == mem_start) {
@@ -149,7 +147,7 @@ next_pair:
 				 */
 				continue;
 			} else {
-				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL);
+				pair = machine__find_kernel_symbol_by_name(&kallsyms, sym->name, NULL);
 				if (pair) {
 					if (UM(pair->start) == mem_start)
 						goto next_pair;
@@ -183,7 +181,7 @@ next_pair:
 		 * so use the short name, less descriptive but the same ("[kernel]" in
 		 * both cases.
 		 */
-		pair = map_groups__find_by_name(&kallsyms.kmaps, type,
+		pair = map_groups__find_by_name(&kallsyms.kmaps,
 						(map->dso->kernel ?
 							map->dso->short_name :
 							map->dso->name));
@@ -206,7 +204,7 @@ next_pair:
 		mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start);
 		mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end);
 
-		pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
+		pair = map_groups__find(&kallsyms.kmaps, mem_start);
 		if (pair == NULL || pair->priv)
 			continue;
 
@@ -228,7 +226,7 @@ next_pair:
 
 	header_printed = false;
 
-	maps = &kallsyms.kmaps.maps[type];
+	maps = machine__kernel_maps(&kallsyms);
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
 		if (!map->priv) {
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 417e3ecfe9d7..9f68077b241b 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -54,6 +54,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 	P_MMAP_FLAG(EXECUTABLE);
 	P_MMAP_FLAG(FILE);
 	P_MMAP_FLAG(FIXED);
+#ifdef MAP_FIXED_NOREPLACE
+	P_MMAP_FLAG(FIXED_NOREPLACE);
+#endif
 	P_MMAP_FLAG(GROWSDOWN);
 	P_MMAP_FLAG(HUGETLB);
 	P_MMAP_FLAG(LOCKED);
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 0be4138fbe71..f24722146ebe 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
 regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 12c099a87f8b..8be40fa903aa 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -692,8 +692,10 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"J             Toggle showing number of jump sources on targets\n"
 		"n             Search next string\n"
 		"o             Toggle disassembler output/simplified view\n"
+		"O             Bump offset level (jump targets -> +call -> all -> cycle thru)\n"
 		"s             Toggle source code view\n"
 		"t             Circulate percent, total period, samples view\n"
+		"c             Show min/max cycle\n"
 		"/             Search string\n"
 		"k             Toggle line numbers\n"
 		"P             Print to [symbol_name].annotation file.\n"
@@ -719,6 +721,10 @@ static int annotate_browser__run(struct annotate_browser *browser,
 			notes->options->use_offset = !notes->options->use_offset;
 			annotation__update_column_widths(notes);
 			continue;
+		case 'O':
+			if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+				notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+			continue;
 		case 'j':
 			notes->options->jump_arrows = !notes->options->jump_arrows;
 			continue;
@@ -786,6 +792,13 @@ show_sup_ins:
 				notes->options->show_total_period = true;
 			annotation__update_column_widths(notes);
 			continue;
+		case 'c':
+			if (notes->options->show_minmax_cycle)
+				notes->options->show_minmax_cycle = false;
+			else
+				notes->options->show_minmax_cycle = true;
+			annotation__update_column_widths(notes);
+			continue;
 		case K_LEFT:
 		case K_ESC:
 		case 'q':
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 0eec06c105c6..e5f247247daa 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2714,7 +2714,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"h/?/F1        Show this window\n"				\
 	"UP/DOWN/PGUP\n"						\
 	"PGDN/SPACE    Navigate\n"					\
-	"q/ESC/CTRL+C  Exit browser\n\n"				\
+	"q/ESC/CTRL+C  Exit browser or go back to previous screen\n\n"	\
 	"For multiple event sessions:\n\n"				\
 	"TAB/UNTAB     Switch events\n\n"				\
 	"For symbolic views (--sort has sym):\n\n"			\
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index e03fa75f108a..5b8b8c637686 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -104,7 +104,7 @@ int map__browse(struct map *map)
 {
 	struct map_browser mb = {
 		.b = {
-			.entries = &map->dso->symbols[map->type],
+			.entries = &map->dso->symbols,
 			.refresh = ui_browser__rb_tree_refresh,
 			.seek	 = ui_browser__rb_tree_seek,
 			.write	 = map_browser__write,
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 6832fcb2e6ff..c1eb476da91b 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -819,8 +819,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		}
 
 		if (h->ms.map == NULL && verbose > 1) {
-			__map_groups__fprintf_maps(h->thread->mg,
-						   MAP__FUNCTION, fp);
+			map_groups__fprintf(h->thread->mg, fp);
 			fprintf(fp, "%.10s end\n", graph_dotted_line);
 		}
 	}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 8052373bcd6a..5d4c45b76895 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -152,6 +152,8 @@ libperf-y += perf-hooks.o
 libperf-$(CONFIG_CXX) += c++/
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"
+
 # avoid compiler warnings in 32-bit mode
 CFLAGS_genelf_debug.o  += -Wno-packed
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index fbad8dfbb186..71897689dacf 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -46,6 +46,7 @@
 struct annotation_options annotation__default_options = {
 	.use_offset     = true,
 	.jump_arrows    = true,
+	.offset_level	= ANNOTATION__OFFSET_JUMP_TARGETS,
 };
 
 const char 	*disassembler_style;
@@ -759,6 +760,15 @@ static int __symbol__account_cycles(struct annotation *notes,
 	ch[offset].num_aggr++;
 	ch[offset].cycles_aggr += cycles;
 
+	if (cycles > ch[offset].cycles_max)
+		ch[offset].cycles_max = cycles;
+
+	if (ch[offset].cycles_min) {
+		if (cycles && cycles < ch[offset].cycles_min)
+			ch[offset].cycles_min = cycles;
+	} else
+		ch[offset].cycles_min = cycles;
+
 	if (!have_start && ch[offset].have_start)
 		return 0;
 	if (ch[offset].num) {
@@ -952,8 +962,11 @@ void annotation__compute_ipc(struct annotation *notes, size_t size)
 			if (ch->have_start)
 				annotation__count_and_fill(notes, ch->start, offset, ch);
 			al = notes->offsets[offset];
-			if (al && ch->num_aggr)
+			if (al && ch->num_aggr) {
 				al->cycles = ch->cycles_aggr / ch->num_aggr;
+				al->cycles_max = ch->cycles_max;
+				al->cycles_min = ch->cycles_min;
+			}
 			notes->have_cycles = true;
 		}
 	}
@@ -1262,6 +1275,9 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 				max_percent = sample->percent;
 		}
 
+		if (al->samples_nr > nr_percent)
+			nr_percent = al->samples_nr;
+
 		if (max_percent < min_pcnt)
 			return -1;
 
@@ -1949,6 +1965,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	u64 len;
 	int width = symbol_conf.show_total_period ? 12 : 8;
 	int graph_dotted_len;
+	char buf[512];
 
 	filename = strdup(dso->long_name);
 	if (!filename)
@@ -1961,8 +1978,11 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 
 	len = symbol__size(sym);
 
-	if (perf_evsel__is_group_event(evsel))
+	if (perf_evsel__is_group_event(evsel)) {
 		width *= evsel->nr_members;
+		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+		evsel_name = buf;
+	}
 
 	graph_dotted_len = printf(" %-*.*s|	Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
 				  width, width, symbol_conf.show_total_period ? "Period" :
@@ -2482,13 +2502,38 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		else
 			obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
 
-		if (al->cycles)
-			obj__printf(obj, "%*" PRIu64 " ",
+		if (!notes->options->show_minmax_cycle) {
+			if (al->cycles)
+				obj__printf(obj, "%*" PRIu64 " ",
 					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles);
-		else if (!show_title)
-			obj__printf(obj, "%*s", ANNOTATION__CYCLES_WIDTH, " ");
-		else
-			obj__printf(obj, "%*s ", ANNOTATION__CYCLES_WIDTH - 1, "Cycle");
+			else if (!show_title)
+				obj__printf(obj, "%*s",
+					    ANNOTATION__CYCLES_WIDTH, " ");
+			else
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__CYCLES_WIDTH - 1,
+					    "Cycle");
+		} else {
+			if (al->cycles) {
+				char str[32];
+
+				scnprintf(str, sizeof(str),
+					"%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")",
+					al->cycles, al->cycles_min,
+					al->cycles_max);
+
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
+					    str);
+			} else if (!show_title)
+				obj__printf(obj, "%*s",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH,
+					    " ");
+			else
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
+					    "Cycle(min/max)");
+		}
 	}
 
 	obj__printf(obj, " ");
@@ -2512,7 +2557,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		if (!notes->options->use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
 		} else {
-			if (al->jump_sources) {
+			if (al->jump_sources &&
+			    notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
 				if (notes->options->show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
@@ -2523,9 +2569,14 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 					obj__printf(obj, bf);
 					obj__set_color(obj, prev);
 				}
-
+print_addr:
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
 						    notes->widths.target, addr);
+			} else if (ins__is_call(&disasm_line(al)->ins) &&
+				   notes->options->offset_level >= ANNOTATION__OFFSET_CALL) {
+				goto print_addr;
+			} else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
+				goto print_addr;
 			} else {
 				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
 						    notes->widths.addr, " ");
@@ -2642,10 +2693,11 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
  */
 static struct annotation_config {
 	const char *name;
-	bool *value;
+	void *value;
 } annotation__configs[] = {
 	ANNOTATION__CFG(hide_src_code),
 	ANNOTATION__CFG(jump_arrows),
+	ANNOTATION__CFG(offset_level),
 	ANNOTATION__CFG(show_linenr),
 	ANNOTATION__CFG(show_nr_jumps),
 	ANNOTATION__CFG(show_nr_samples),
@@ -2677,8 +2729,16 @@ static int annotation__config(const char *var, const char *value,
 
 	if (cfg == NULL)
 		pr_debug("%s variable unknown, ignoring...", var);
-	else
-		*cfg->value = perf_config_bool(name, value);
+	else if (strcmp(var, "annotate.offset_level") == 0) {
+		perf_config_int(cfg->value, name, value);
+
+		if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
+			*(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
+		else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
+			*(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+	} else {
+		*(bool *)cfg->value = perf_config_bool(name, value);
+	}
 	return 0;
 }
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index db8d09bea07e..5080b6dd98b8 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -61,6 +61,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 #define ANNOTATION__IPC_WIDTH 6
 #define ANNOTATION__CYCLES_WIDTH 6
+#define ANNOTATION__MINMAX_CYCLES_WIDTH 19
 
 struct annotation_options {
 	bool hide_src_code,
@@ -69,9 +70,19 @@ struct annotation_options {
 	     show_linenr,
 	     show_nr_jumps,
 	     show_nr_samples,
-	     show_total_period;
+	     show_total_period,
+	     show_minmax_cycle;
+	u8   offset_level;
 };
 
+enum {
+	ANNOTATION__OFFSET_JUMP_TARGETS = 1,
+	ANNOTATION__OFFSET_CALL,
+	ANNOTATION__MAX_OFFSET_LEVEL,
+};
+
+#define ANNOTATION__MIN_OFFSET_LEVEL ANNOTATION__OFFSET_JUMP_TARGETS
+
 extern struct annotation_options annotation__default_options;
 
 struct annotation;
@@ -96,6 +107,8 @@ struct annotation_line {
 	int			 jump_sources;
 	float			 ipc;
 	u64			 cycles;
+	u64			 cycles_max;
+	u64			 cycles_min;
 	size_t			 privsize;
 	char			*path;
 	u32			 idx;
@@ -177,6 +190,8 @@ struct cyc_hist {
 	u64	start;
 	u64	cycles;
 	u64	cycles_aggr;
+	u64	cycles_max;
+	u64	cycles_min;
 	u32	num;
 	u32	num_aggr;
 	u8	have_start;
@@ -230,6 +245,9 @@ struct annotation {
 
 static inline int annotation__cycles_width(struct annotation *notes)
 {
+	if (notes->have_cycles && notes->options->show_minmax_cycle)
+		return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH;
+
 	return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
 }
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 857de69a5361..d056447520a2 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1679,7 +1679,7 @@ struct sym_args {
 static bool kern_sym_match(struct sym_args *args, const char *name, char type)
 {
 	/* A function with the same name, and global or the n'th found or any */
-	return symbol_type__is_a(type, MAP__FUNCTION) &&
+	return kallsyms__is_function(type) &&
 	       !strcmp(name, args->name) &&
 	       ((args->global && isupper(type)) ||
 		(args->selected && ++(args->cnt) == args->idx) ||
@@ -1784,7 +1784,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused,
 {
 	struct sym_args *args = arg;
 
-	if (!symbol_type__is_a(type, MAP__FUNCTION))
+	if (!kallsyms__is_function(type))
 		return 0;
 
 	if (!args->started) {
@@ -1915,7 +1915,7 @@ static void print_duplicate_syms(struct dso *dso, const char *sym_name)
 
 	pr_err("Multiple symbols with name '%s'\n", sym_name);
 
-	sym = dso__first_symbol(dso, MAP__FUNCTION);
+	sym = dso__first_symbol(dso);
 	while (sym) {
 		if (dso_sym_match(sym, sym_name, &cnt, -1)) {
 			pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n",
@@ -1945,7 +1945,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
 	*start = 0;
 	*size = 0;
 
-	sym = dso__first_symbol(dso, MAP__FUNCTION);
+	sym = dso__first_symbol(dso);
 	while (sym) {
 		if (*start) {
 			if (!*size)
@@ -1972,8 +1972,8 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
 
 static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso)
 {
-	struct symbol *first_sym = dso__first_symbol(dso, MAP__FUNCTION);
-	struct symbol *last_sym = dso__last_symbol(dso, MAP__FUNCTION);
+	struct symbol *first_sym = dso__first_symbol(dso);
+	struct symbol *last_sym = dso__last_symbol(dso);
 
 	if (!first_sym || !last_sym) {
 		pr_err("Failed to determine filter for %s\nNo symbols found.\n",
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index af7ad814b2c3..cee658733e2c 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
 	}
 
 	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
-	if (IS_ERR(obj)) {
+	if (IS_ERR_OR_NULL(obj)) {
 		pr_debug("bpf: failed to load buffer\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 			pr_debug("bpf: successfull builtin compilation\n");
 		obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
 
-		if (!IS_ERR(obj) && llvm_param.dump_obj)
+		if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
 			llvm__dump_obj(filename, obj_buf, obj_buf_sz);
 
 		free(obj_buf);
 	} else
 		obj = bpf_object__open(filename);
 
-	if (IS_ERR(obj)) {
+	if (IS_ERR_OR_NULL(obj)) {
 		pr_debug("bpf: failed to load %s\n", filename);
 		return obj;
 	}
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 537eadd81914..04b1d53e4bf9 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -47,9 +47,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
-
-	if (al.map != NULL)
+	if (thread__find_map(thread, sample->cpumode, sample->ip, &al))
 		al.map->dso->hit = 1;
 
 	thread__put(thread);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 84eb9393c7db..5ac157056cdf 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -707,6 +707,14 @@ struct perf_config_set *perf_config_set__new(void)
 	return set;
 }
 
+static int perf_config__init(void)
+{
+	if (config_set == NULL)
+		config_set = perf_config_set__new();
+
+	return config_set == NULL;
+}
+
 int perf_config(config_fn_t fn, void *data)
 {
 	int ret = 0;
@@ -714,7 +722,7 @@ int perf_config(config_fn_t fn, void *data)
 	struct perf_config_section *section;
 	struct perf_config_item *item;
 
-	if (config_set == NULL)
+	if (config_set == NULL && perf_config__init())
 		return -1;
 
 	perf_config_set__for_each_entry(config_set, section, item) {
@@ -735,12 +743,6 @@ int perf_config(config_fn_t fn, void *data)
 	return ret;
 }
 
-void perf_config__init(void)
-{
-	if (config_set == NULL)
-		config_set = perf_config_set__new();
-}
-
 void perf_config__exit(void)
 {
 	perf_config_set__delete(config_set);
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index baf82bf227ac..bd0a5897c76a 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -38,7 +38,6 @@ struct perf_config_set *perf_config_set__new(void);
 void perf_config_set__delete(struct perf_config_set *set);
 int perf_config_set__collect(struct perf_config_set *set, const char *file_name,
 			     const char *var, const char *value);
-void perf_config__init(void);
 void perf_config__exit(void);
 void perf_config__refresh(void);
 
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 640af88331b4..4d5fc374e730 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * SPDX-License-Identifier: GPL-2.0
- *
  * Copyright(C) 2015-2018 Linaro Limited.
  *
  * Author: Tor Jeremiassen <tor@ti.com>
@@ -97,11 +96,19 @@ int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
 	/* Nothing to do, might as well just return */
 	if (decoder->packet_count == 0)
 		return 0;
+	/*
+	 * The queueing process in function cs_etm_decoder__buffer_packet()
+	 * increments the tail *before* using it.  This is somewhat counter
+	 * intuitive but it has the advantage of centralizing tail management
+	 * at a single location.  Because of that we need to follow the same
+	 * heuristic with the head, i.e we increment it before using its
+	 * value.  Otherwise the first element of the packet queue is not
+	 * used.
+	 */
+	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
 
 	*packet = decoder->packet_buffer[decoder->head];
 
-	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
-
 	decoder->packet_count--;
 
 	return 1;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 1b0d422373be..822ba915d144 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * SPDX-License-Identifier: GPL-2.0
- *
  * Copyright(C) 2015-2018 Linaro Limited.
  *
  * Author: Tor Jeremiassen <tor@ti.com>
@@ -240,6 +239,7 @@ static void cs_etm__free(struct perf_session *session)
 	for (i = 0; i < aux->num_cpu; i++)
 		zfree(&aux->metadata[i]);
 
+	thread__zput(aux->unknown_thread);
 	zfree(&aux->metadata);
 	zfree(&aux);
 }
@@ -270,9 +270,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 		thread = etmq->etm->unknown_thread;
 	}
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al);
-
-	if (!al.map || !al.map->dso)
+	if (!thread__find_map(thread, cpumode, address, &al) || !al.map->dso)
 		return 0;
 
 	if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
@@ -613,8 +611,8 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
 	return buff->len;
 }
 
-static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
-				     struct auxtrace_queue *queue)
+static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
+				    struct auxtrace_queue *queue)
 {
 	struct cs_etm_queue *etmq = queue->priv;
 
@@ -1358,6 +1356,23 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	etm->auxtrace.free = cs_etm__free;
 	session->auxtrace = &etm->auxtrace;
 
+	etm->unknown_thread = thread__new(999999999, 999999999);
+	if (!etm->unknown_thread)
+		goto err_free_queues;
+
+	/*
+	 * Initialize list node so that at thread__zput() we can avoid
+	 * segmentation fault at list_del_init().
+	 */
+	INIT_LIST_HEAD(&etm->unknown_thread->node);
+
+	err = thread__set_comm(etm->unknown_thread, "unknown", 0);
+	if (err)
+		goto err_delete_thread;
+
+	if (thread__init_map_groups(etm->unknown_thread, etm->machine))
+		goto err_delete_thread;
+
 	if (dump_trace) {
 		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
 		return 0;
@@ -1372,16 +1387,18 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 
 	err = cs_etm__synth_events(etm, session);
 	if (err)
-		goto err_free_queues;
+		goto err_delete_thread;
 
 	err = auxtrace_queues__process_index(&etm->queues, session);
 	if (err)
-		goto err_free_queues;
+		goto err_delete_thread;
 
 	etm->data_queued = etm->queues.populated;
 
 	return 0;
 
+err_delete_thread:
+	thread__zput(etm->unknown_thread);
 err_free_queues:
 	auxtrace_queues__free(&etm->queues);
 	session->auxtrace = NULL;
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 5864d5dca616..37f8d48179ca 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef INCLUDE__UTIL_PERF_CS_ETM_H__
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index b0c2b5c5d337..7123746edcf4 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -247,9 +247,9 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 		*dso_db_id = dso->db_id;
 
 		if (!al->sym) {
-			al->sym = symbol__new(al->addr, 0, 0, "unknown");
+			al->sym = symbol__new(al->addr, 0, 0, 0, "unknown");
 			if (al->sym)
-				dso__insert_symbol(dso, al->map->type, al->sym);
+				dso__insert_symbol(dso, al->sym);
 		}
 
 		if (al->sym) {
@@ -315,8 +315,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 		al.addr = node->ip;
 
 		if (al.map && !al.sym)
-			al.sym = dso__find_symbol(al.map->dso, MAP__FUNCTION,
-						  al.addr);
+			al.sym = dso__find_symbol(al.map->dso, al.addr);
 
 		db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 36ef45b2e89d..cdfc2e5f55f5 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1014,7 +1014,7 @@ struct map *dso__new_map(const char *name)
 	struct dso *dso = dso__new(name);
 
 	if (dso)
-		map = map__new2(0, dso, MAP__FUNCTION);
+		map = map__new2(0, dso);
 
 	return map;
 }
@@ -1176,19 +1176,19 @@ int dso__name_len(const struct dso *dso)
 	return dso->short_name_len;
 }
 
-bool dso__loaded(const struct dso *dso, enum map_type type)
+bool dso__loaded(const struct dso *dso)
 {
-	return dso->loaded & (1 << type);
+	return dso->loaded;
 }
 
-bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
+bool dso__sorted_by_name(const struct dso *dso)
 {
-	return dso->sorted_by_name & (1 << type);
+	return dso->sorted_by_name;
 }
 
-void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
+void dso__set_sorted_by_name(struct dso *dso)
 {
-	dso->sorted_by_name |= (1 << type);
+	dso->sorted_by_name = true;
 }
 
 struct dso *dso__new(const char *name)
@@ -1196,12 +1196,10 @@ struct dso *dso__new(const char *name)
 	struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
 
 	if (dso != NULL) {
-		int i;
 		strcpy(dso->name, name);
 		dso__set_long_name(dso, dso->name, false);
 		dso__set_short_name(dso, dso->name, false);
-		for (i = 0; i < MAP__NR_TYPES; ++i)
-			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
+		dso->symbols = dso->symbol_names = RB_ROOT;
 		dso->data.cache = RB_ROOT;
 		dso->inlined_nodes = RB_ROOT;
 		dso->srclines = RB_ROOT;
@@ -1231,8 +1229,6 @@ struct dso *dso__new(const char *name)
 
 void dso__delete(struct dso *dso)
 {
-	int i;
-
 	if (!RB_EMPTY_NODE(&dso->rb_node))
 		pr_err("DSO %s is still in rbtree when being deleted!\n",
 		       dso->long_name);
@@ -1240,8 +1236,7 @@ void dso__delete(struct dso *dso)
 	/* free inlines first, as they reference symbols */
 	inlines__tree_delete(&dso->inlined_nodes);
 	srcline__tree_delete(&dso->srclines);
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		symbols__delete(&dso->symbols[i]);
+	symbols__delete(&dso->symbols);
 
 	if (dso->short_name_allocated) {
 		zfree((char **)&dso->short_name);
@@ -1451,9 +1446,7 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp)
 	size_t ret = 0;
 
 	list_for_each_entry(pos, head, node) {
-		int i;
-		for (i = 0; i < MAP__NR_TYPES; ++i)
-			ret += dso__fprintf(pos, i, fp);
+		ret += dso__fprintf(pos, fp);
 	}
 
 	return ret;
@@ -1467,18 +1460,17 @@ size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 	return fprintf(fp, "%s", sbuild_id);
 }
 
-size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
+size_t dso__fprintf(struct dso *dso, FILE *fp)
 {
 	struct rb_node *nd;
 	size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
 
 	if (dso->short_name != dso->long_name)
 		ret += fprintf(fp, "%s, ", dso->long_name);
-	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
-		       dso__loaded(dso, type) ? "" : "NOT ");
+	ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT ");
 	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
-	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&dso->symbols); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		ret += symbol__fprintf(pos, fp);
 	}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index c229dbe0277a..ef69de2e69ea 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -140,14 +140,14 @@ struct dso {
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
-	struct rb_root	 symbols[MAP__NR_TYPES];
-	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 symbols;
+	struct rb_root	 symbol_names;
 	struct rb_root	 inlined_nodes;
 	struct rb_root	 srclines;
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
-	} last_find_result[MAP__NR_TYPES];
+	} last_find_result;
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
@@ -164,8 +164,8 @@ struct dso {
 	u8		 short_name_allocated:1;
 	u8		 long_name_allocated:1;
 	u8		 is_64_bit:1;
-	u8		 sorted_by_name;
-	u8		 loaded;
+	bool		 sorted_by_name;
+	bool		 loaded;
 	u8		 rel;
 	u8		 build_id[BUILD_ID_SIZE];
 	u64		 text_offset;
@@ -202,14 +202,13 @@ struct dso {
  * @dso: the 'struct dso *' in which symbols itereated
  * @pos: the 'struct symbol *' to use as a loop cursor
  * @n: the 'struct rb_node *' to use as a temporary storage
- * @type: the 'enum map_type' type of symbols
  */
-#define dso__for_each_symbol(dso, pos, n, type)	\
-	symbols__for_each_entry(&(dso)->symbols[(type)], pos, n)
+#define dso__for_each_symbol(dso, pos, n)	\
+	symbols__for_each_entry(&(dso)->symbols, pos, n)
 
-static inline void dso__set_loaded(struct dso *dso, enum map_type type)
+static inline void dso__set_loaded(struct dso *dso)
 {
-	dso->loaded |= (1 << type);
+	dso->loaded = true;
 }
 
 struct dso *dso__new(const char *name);
@@ -231,11 +230,16 @@ static inline void __dso__zput(struct dso **dso)
 
 #define dso__zput(dso) __dso__zput(&dso)
 
-bool dso__loaded(const struct dso *dso, enum map_type type);
+bool dso__loaded(const struct dso *dso);
 
-bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
-void dso__set_sorted_by_name(struct dso *dso, enum map_type type);
-void dso__sort_by_name(struct dso *dso, enum map_type type);
+static inline bool dso__has_symbols(const struct dso *dso)
+{
+	return !RB_EMPTY_ROOT(&dso->symbols);
+}
+
+bool dso__sorted_by_name(const struct dso *dso);
+void dso__set_sorted_by_name(struct dso *dso);
+void dso__sort_by_name(struct dso *dso);
 
 void dso__set_build_id(struct dso *dso, void *build_id);
 bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
@@ -349,9 +353,8 @@ size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
 size_t __dsos__fprintf(struct list_head *head, FILE *fp);
 
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
-size_t dso__fprintf_symbols_by_name(struct dso *dso,
-				    enum map_type type, FILE *fp);
-size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp);
+size_t dso__fprintf(struct dso *dso, FILE *fp);
 
 static inline bool dso__is_vmlinux(struct dso *dso)
 {
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 4c842762e3f2..59f38c7693f8 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -93,6 +93,37 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	return 0;
 }
 
+static int perf_env__read_arch(struct perf_env *env)
+{
+	struct utsname uts;
+
+	if (env->arch)
+		return 0;
+
+	if (!uname(&uts))
+		env->arch = strdup(uts.machine);
+
+	return env->arch ? 0 : -ENOMEM;
+}
+
+static int perf_env__read_nr_cpus_avail(struct perf_env *env)
+{
+	if (env->nr_cpus_avail == 0)
+		env->nr_cpus_avail = cpu__max_present_cpu();
+
+	return env->nr_cpus_avail ? 0 : -ENOENT;
+}
+
+const char *perf_env__raw_arch(struct perf_env *env)
+{
+	return env && !perf_env__read_arch(env) ? env->arch : "unknown";
+}
+
+int perf_env__nr_cpus_avail(struct perf_env *env)
+{
+	return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0;
+}
+
 void cpu_cache_level__free(struct cpu_cache_level *cache)
 {
 	free(cache->type);
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index c4ef2e523367..1f3ccc368530 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -76,4 +76,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env);
 void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__arch(struct perf_env *env);
+const char *perf_env__raw_arch(struct perf_env *env);
+int perf_env__nr_cpus_avail(struct perf_env *env);
+
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index f0a6cbd033cc..0c8ecf0c78a4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -88,10 +88,10 @@ static const char *perf_ns__name(unsigned int id)
 	return perf_ns__names[id];
 }
 
-static int perf_tool__process_synth_event(struct perf_tool *tool,
-					  union perf_event *event,
-					  struct machine *machine,
-					  perf_event__handler_t process)
+int perf_tool__process_synth_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct machine *machine,
+				   perf_event__handler_t process)
 {
 	struct perf_sample synth_sample = {
 	.pid	   = -1,
@@ -464,8 +464,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 {
 	int rc = 0;
 	struct map *pos;
-	struct map_groups *kmaps = &machine->kmaps;
-	struct maps *maps = &kmaps->maps[MAP__FUNCTION];
+	struct maps *maps = machine__kernel_maps(machine);
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -488,7 +487,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
 
-		if (__map__is_kernel(pos))
+		if (!__map__is_kmodule(pos))
 			continue;
 
 		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
@@ -869,7 +868,7 @@ static int find_symbol_cb(void *arg, const char *name, char type,
 	 * Must be a function or at least an alias, as in PARISC64, where "_text" is
 	 * an 'A' to the same address as "_stext".
 	 */
-	if (!(symbol_type__is_a(type, MAP__FUNCTION) ||
+	if (!(kallsyms__is_function(type) ||
 	      type == 'A') || strcmp(name, args->name))
 		return 0;
 
@@ -889,9 +888,16 @@ int kallsyms__get_function_start(const char *kallsyms_filename,
 	return 0;
 }
 
-int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine)
+int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
+					      perf_event__handler_t process __maybe_unused,
+					      struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
+static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+						perf_event__handler_t process,
+						struct machine *machine)
 {
 	size_t size;
 	struct map *map = machine__kernel_map(machine);
@@ -944,6 +950,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	return err;
 }
 
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int err;
+
+	err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
+	if (err < 0)
+		return err;
+
+	return perf_event__synthesize_extra_kmaps(tool, process, machine);
+}
+
 int perf_event__synthesize_thread_map2(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
@@ -1421,7 +1440,9 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
 {
 	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
-	const char *in_out = out ? "OUT" : "IN ";
+	const char *in_out = !out ? "IN         " :
+		!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) ?
+				    "OUT        " : "OUT preempt";
 
 	if (event->header.type == PERF_RECORD_SWITCH)
 		return fprintf(fp, " %s\n", in_out);
@@ -1487,9 +1508,8 @@ int perf_event__process(struct perf_tool *tool __maybe_unused,
 	return machine__process_event(machine, event, sample);
 }
 
-void thread__find_addr_map(struct thread *thread, u8 cpumode,
-			   enum map_type type, u64 addr,
-			   struct addr_location *al)
+struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
+			     struct addr_location *al)
 {
 	struct map_groups *mg = thread->mg;
 	struct machine *machine = mg->machine;
@@ -1503,7 +1523,7 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode,
 
 	if (machine == NULL) {
 		al->map = NULL;
-		return;
+		return NULL;
 	}
 
 	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
@@ -1531,10 +1551,10 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode,
 			!perf_host)
 			al->filtered |= (1 << HIST_FILTER__HOST);
 
-		return;
+		return NULL;
 	}
 try_again:
-	al->map = map_groups__find(mg, type, al->addr);
+	al->map = map_groups__find(mg, al->addr);
 	if (al->map == NULL) {
 		/*
 		 * If this is outside of all known maps, and is a negative
@@ -1561,17 +1581,17 @@ try_again:
 			map__load(al->map);
 		al->addr = al->map->map_ip(al->map, al->addr);
 	}
+
+	return al->map;
 }
 
-void thread__find_addr_location(struct thread *thread,
-				u8 cpumode, enum map_type type, u64 addr,
-				struct addr_location *al)
+struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
+				   u64 addr, struct addr_location *al)
 {
-	thread__find_addr_map(thread, cpumode, type, addr, al);
-	if (al->map != NULL)
+	al->sym = NULL;
+	if (thread__find_map(thread, cpumode, addr, al))
 		al->sym = map__find_symbol(al->map, al->addr);
-	else
-		al->sym = NULL;
+	return al->sym;
 }
 
 /*
@@ -1588,7 +1608,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 		return -1;
 
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
-	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al);
+	thread__find_map(thread, sample->cpumode, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -1667,10 +1687,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 void thread__resolve(struct thread *thread, struct addr_location *al,
 		     struct perf_sample *sample)
 {
-	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->addr, al);
-	if (!al->map)
-		thread__find_addr_map(thread, sample->cpumode, MAP__VARIABLE,
-				      sample->addr, al);
+	thread__find_map(thread, sample->cpumode, sample->addr, al);
 
 	al->cpu = sample->cpu;
 	al->sym = NULL;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 0f794744919c..bfa60bcafbde 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -750,6 +750,10 @@ int perf_event__process_exit(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_tool__process_synth_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct machine *machine,
+				   perf_event__handler_t process);
 int perf_event__process(struct perf_tool *tool,
 			union perf_event *event,
 			struct perf_sample *sample,
@@ -796,6 +800,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       bool mmap_data,
 				       unsigned int proc_map_timeout);
 
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine);
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a59281d64368..e7a4b31a84fb 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1795,3 +1795,18 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
 
 	return true;
 }
+
+/*
+ * Events in data file are not collect in groups, but we still want
+ * the group display. Set the artificial group and set the leader's
+ * forced_leader flag to notify the display code.
+ */
+void perf_evlist__force_leader(struct perf_evlist *evlist)
+{
+	if (!evlist->nr_groups) {
+		struct perf_evsel *leader = perf_evlist__first(evlist);
+
+		perf_evlist__set_leader(evlist);
+		leader->forced_leader = true;
+	}
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 6c41b2f78713..dc66436add98 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -309,4 +309,7 @@ struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 					    union perf_event *event);
 
 bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
+
+void perf_evlist__force_leader(struct perf_evlist *evlist);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1ac8d9236efd..150db5ed7400 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -930,8 +930,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	 * than leader in case leader 'leads' the sampling.
 	 */
 	if ((leader != evsel) && leader->sample_read) {
-		attr->sample_freq   = 0;
-		attr->sample_period = 0;
+		attr->freq           = 0;
+		attr->sample_freq    = 0;
+		attr->sample_period  = 0;
+		attr->write_backward = 0;
+		attr->sample_id_all  = 0;
 	}
 
 	if (opts->no_samples)
@@ -1922,7 +1925,8 @@ try_fallback:
 		goto fallback_missing_features;
 	} else if (!perf_missing_features.group_read &&
 		    evsel->attr.inherit &&
-		   (evsel->attr.read_format & PERF_FORMAT_GROUP)) {
+		   (evsel->attr.read_format & PERF_FORMAT_GROUP) &&
+		   perf_evsel__is_group_leader(evsel)) {
 		perf_missing_features.group_read = true;
 		pr_debug2("switching off group read\n");
 		goto fallback_missing_features;
@@ -2754,8 +2758,14 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 		   (paranoid = perf_event_paranoid()) > 1) {
 		const char *name = perf_evsel__name(evsel);
 		char *new_name;
+		const char *sep = ":";
 
-		if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
+		/* Is there already the separator in the name. */
+		if (strchr(name, '/') ||
+		    strchr(name, ':'))
+			sep = "";
+
+		if (asprintf(&new_name, "%s%su", name, sep) < 0)
 			return false;
 
 		if (evsel->name)
@@ -2852,7 +2862,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			return scnprintf(msg, size,
 					 "Not enough memory to setup event with callchain.\n"
 					 "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n"
-					 "Hint: Current value: %d", sysctl_perf_event_max_stack);
+					 "Hint: Current value: %d", sysctl__max_stack());
 		break;
 	case ENODEV:
 		if (target->cpu_list)
@@ -2870,8 +2880,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 #if defined(__i386__) || defined(__x86_64__)
 		if (evsel->attr.type == PERF_TYPE_HARDWARE)
 			return scnprintf(msg, size, "%s",
-	"No hardware sampling interrupt available.\n"
-	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
+	"No hardware sampling interrupt available.\n");
 #endif
 		break;
 	case EBUSY:
@@ -2894,8 +2903,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 
 	return scnprintf(msg, size,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
-	"/bin/dmesg may provide additional information.\n"
-	"No CONFIG_PERF_EVENTS=y kernel support configured?",
+	"/bin/dmesg | grep -i perf may provide additional information.\n",
 			 err, str_error_r(err, sbuf, sizeof(sbuf)),
 			 perf_evsel__name(evsel));
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d3ee3af618ef..b13f5f234c8f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -115,6 +115,7 @@ struct perf_evsel {
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	bool			uniquified_name;
 	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
@@ -126,6 +127,7 @@ struct perf_evsel {
 	bool			precise_max;
 	bool			ignore_missing_thread;
 	bool			forced_leader;
+	bool			use_uncore_alias;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index c540d47583e7..aafbe54fd3fa 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -114,7 +114,7 @@ gen_build_id(struct buildid_note *note,
 
 	fd = open("/dev/urandom", O_RDONLY);
 	if (fd == -1)
-		err(1, "cannot access /dev/urandom for builid");
+		err(1, "cannot access /dev/urandom for buildid");
 
 	sret = read(fd, note->build_id, sz);
 
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index ff17920a5ebc..c3cef36d4176 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -38,7 +38,7 @@ do
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
 
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)"
+echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
 sed -n -e 's/^perf-\([^ 	]*\)[ 	].* audit*/\1/p' command-list.txt |
 sort |
 while read cmd
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 121df1683c36..a8bff2178fbc 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1320,7 +1320,8 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
 
 	dir = opendir(path);
 	if (!dir) {
-		pr_warning("failed: can't open node sysfs data\n");
+		pr_debug2("%s: could't read %s, does this arch have topology information?\n",
+			  __func__, path);
 		return -1;
 	}
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 72db2744876d..7f0c83b6332b 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -335,8 +335,7 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
 	if (!thread)
 		return -1;
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
-	if (!al.map || !al.map->dso)
+	if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
 		goto out_put;
 
 	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf,
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h
index e23578c7b1be..2669c9f748e4 100644
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ b/tools/perf/util/intel-pt-decoder/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
 	return insn_offset_displacement(insn) + insn->displacement.nbytes;
 }
 
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+	return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+		(insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+		 X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
 #endif /* _ASM_X86_INSN_H */
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 0effaff57020..492986a25ef6 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -442,8 +442,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 	}
 
 	while (1) {
-		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, *ip, &al);
-		if (!al.map || !al.map->dso)
+		if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso)
 			return -EINVAL;
 
 		if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
@@ -596,8 +595,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data)
 	if (!thread)
 		return -EINVAL;
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
-	if (!al.map || !al.map->dso)
+	if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
 		return -EINVAL;
 
 	offset = al.map->map_ip(al.map, ip);
@@ -1565,7 +1563,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 	if (map__load(map))
 		return 0;
 
-	start = dso__first_symbol(map->dso, MAP__FUNCTION);
+	start = dso__first_symbol(map->dso);
 
 	for (sym = start; sym; sym = dso__next_symbol(sym)) {
 		if (sym->binding == STB_GLOBAL &&
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 1cca0a2fa641..976e658e38dc 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -14,11 +14,12 @@
 #include "config.h"
 #include "util.h"
 #include <sys/wait.h>
+#include <subcmd/exec-cmd.h>
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
 		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS "		\
+		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
 		"-c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
@@ -212,7 +213,7 @@ version_notice(void)
 "     \t\thttp://llvm.org/apt\n\n"
 "     \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n"
 "     \toption in [llvm] section of ~/.perfconfig to:\n\n"
-"     \t  \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS \\\n"
+"     \t  \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n"
 "     \t     -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n"
 "     \t     -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n"
 "     \t(Replace /path/to/llc with path to your llc)\n\n"
@@ -431,9 +432,11 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	const char *clang_opt = llvm_param.clang_opt;
 	char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
 	char serr[STRERR_BUFSIZE];
-	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
+	char *kbuild_dir = NULL, *kbuild_include_opts = NULL,
+	     *perf_bpf_include_opts = NULL;
 	const char *template = llvm_param.clang_bpf_cmd_template;
-	char *command_echo, *command_out;
+	char *command_echo = NULL, *command_out;
+	char *perf_include_dir = system_path(PERF_INCLUDE_DIR);
 
 	if (path[0] != '-' && realpath(path, abspath) == NULL) {
 		err = errno;
@@ -471,12 +474,14 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 
 	snprintf(linux_version_code_str, sizeof(linux_version_code_str),
 		 "0x%x", kernel_version);
-
+	if (asprintf(&perf_bpf_include_opts, "-I%s/bpf", perf_include_dir) < 0)
+		goto errout;
 	force_set_env("NR_CPUS", nr_cpus_avail_str);
 	force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
 	force_set_env("CLANG_EXEC", clang_path);
 	force_set_env("CLANG_OPTIONS", clang_opt);
 	force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
+	force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts);
 	force_set_env("WORKING_DIR", kbuild_dir ? : ".");
 
 	/*
@@ -512,6 +517,8 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	free(command_out);
 	free(kbuild_dir);
 	free(kbuild_include_opts);
+	free(perf_bpf_include_opts);
+	free(perf_include_dir);
 
 	if (!p_obj_buf)
 		free(obj_buf);
@@ -526,6 +533,8 @@ errout:
 	free(kbuild_dir);
 	free(kbuild_include_opts);
 	free(obj_buf);
+	free(perf_bpf_include_opts);
+	free(perf_include_dir);
 	if (p_obj_buf)
 		*p_obj_buf = NULL;
 	if (p_obj_buf_sz)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 2eca8478e24f..e7b4a8b513f2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -24,6 +24,7 @@
 
 #include "sane_ctype.h"
 #include <symbol/kallsyms.h>
+#include <linux/mman.h>
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
 
@@ -81,8 +82,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	machine->kptr_restrict_warned = false;
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
-
-	memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps));
+	machine->vmlinux_map = NULL;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
@@ -137,13 +137,11 @@ struct machine *machine__new_kallsyms(void)
 	struct machine *machine = machine__new_host();
 	/*
 	 * FIXME:
-	 * 1) MAP__FUNCTION will go away when we stop loading separate maps for
-	 *    functions and data objects.
-	 * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely
+	 * 1) We should switch to machine__load_kallsyms(), i.e. not explicitely
 	 *    ask for not using the kcore parsing code, once this one is fixed
 	 *    to create a map per module.
 	 */
-	if (machine && machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION) <= 0) {
+	if (machine && machine__load_kallsyms(machine, "/proc/kallsyms") <= 0) {
 		machine__delete(machine);
 		machine = NULL;
 	}
@@ -673,8 +671,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 	if (kmod_path__parse_name(&m, filename))
 		return NULL;
 
-	map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION,
-				       m.name);
+	map = map_groups__find_by_name(&machine->kmaps, m.name);
 	if (map) {
 		/*
 		 * If the map's dso is an offline module, give dso__load()
@@ -689,7 +686,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 	if (dso == NULL)
 		goto out;
 
-	map = map__new2(start, dso, MAP__FUNCTION);
+	map = map__new2(start, dso);
 	if (map == NULL)
 		goto out;
 
@@ -810,8 +807,8 @@ struct process_args {
 	u64 start;
 };
 
-static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
-					   size_t bufsz)
+void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+				    size_t bufsz)
 {
 	if (machine__is_default_guest(machine))
 		scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms);
@@ -854,65 +851,171 @@ static int machine__get_running_kernel_start(struct machine *machine,
 	return 0;
 }
 
+int machine__create_extra_kernel_map(struct machine *machine,
+				     struct dso *kernel,
+				     struct extra_kernel_map *xm)
+{
+	struct kmap *kmap;
+	struct map *map;
+
+	map = map__new2(xm->start, kernel);
+	if (!map)
+		return -1;
+
+	map->end   = xm->end;
+	map->pgoff = xm->pgoff;
+
+	kmap = map__kmap(map);
+
+	kmap->kmaps = &machine->kmaps;
+	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
+
+	map_groups__insert(&machine->kmaps, map);
+
+	pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n",
+		  kmap->name, map->start, map->end);
+
+	map__put(map);
+
+	return 0;
+}
+
+static u64 find_entry_trampoline(struct dso *dso)
+{
+	/* Duplicates are removed so lookup all aliases */
+	const char *syms[] = {
+		"_entry_trampoline",
+		"__entry_trampoline_start",
+		"entry_SYSCALL_64_trampoline",
+	};
+	struct symbol *sym = dso__first_symbol(dso);
+	unsigned int i;
+
+	for (; sym; sym = dso__next_symbol(sym)) {
+		if (sym->binding != STB_GLOBAL)
+			continue;
+		for (i = 0; i < ARRAY_SIZE(syms); i++) {
+			if (!strcmp(sym->name, syms[i]))
+				return sym->start;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * These values can be used for kernels that do not have symbols for the entry
+ * trampolines in kallsyms.
+ */
+#define X86_64_CPU_ENTRY_AREA_PER_CPU	0xfffffe0000000000ULL
+#define X86_64_CPU_ENTRY_AREA_SIZE	0x2c000
+#define X86_64_ENTRY_TRAMPOLINE		0x6000
+
+/* Map x86_64 PTI entry trampolines */
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+					  struct dso *kernel)
+{
+	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps;
+	int nr_cpus_avail, cpu;
+	bool found = false;
+	struct map *map;
+	u64 pgoff;
+
+	/*
+	 * In the vmlinux case, pgoff is a virtual address which must now be
+	 * mapped to a vmlinux offset.
+	 */
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct kmap *kmap = __map__kmap(map);
+		struct map *dest_map;
+
+		if (!kmap || !is_entry_trampoline(kmap->name))
+			continue;
+
+		dest_map = map_groups__find(kmaps, map->pgoff);
+		if (dest_map != map)
+			map->pgoff = dest_map->map_ip(dest_map, map->pgoff);
+		found = true;
+	}
+	if (found || machine->trampolines_mapped)
+		return 0;
+
+	pgoff = find_entry_trampoline(kernel);
+	if (!pgoff)
+		return 0;
+
+	nr_cpus_avail = machine__nr_cpus_avail(machine);
+
+	/* Add a 1 page map for each CPU's entry trampoline */
+	for (cpu = 0; cpu < nr_cpus_avail; cpu++) {
+		u64 va = X86_64_CPU_ENTRY_AREA_PER_CPU +
+			 cpu * X86_64_CPU_ENTRY_AREA_SIZE +
+			 X86_64_ENTRY_TRAMPOLINE;
+		struct extra_kernel_map xm = {
+			.start = va,
+			.end   = va + page_size,
+			.pgoff = pgoff,
+		};
+
+		strlcpy(xm.name, ENTRY_TRAMPOLINE_NAME, KMAP_NAME_LEN);
+
+		if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0)
+			return -1;
+	}
+
+	machine->trampolines_mapped = nr_cpus_avail;
+
+	return 0;
+}
+
+int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unused,
+					     struct dso *kernel __maybe_unused)
+{
+	return 0;
+}
+
 static int
 __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
-	int type;
+	struct kmap *kmap;
+	struct map *map;
 
 	/* In case of renewal the kernel map, destroy previous one */
 	machine__destroy_kernel_maps(machine);
 
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-		struct map *map;
-
-		machine->vmlinux_maps[type] = map__new2(0, kernel, type);
-		if (machine->vmlinux_maps[type] == NULL)
-			return -1;
+	machine->vmlinux_map = map__new2(0, kernel);
+	if (machine->vmlinux_map == NULL)
+		return -1;
 
-		machine->vmlinux_maps[type]->map_ip =
-			machine->vmlinux_maps[type]->unmap_ip =
-				identity__map_ip;
-		map = __machine__kernel_map(machine, type);
-		kmap = map__kmap(map);
-		if (!kmap)
-			return -1;
+	machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
+	map = machine__kernel_map(machine);
+	kmap = map__kmap(map);
+	if (!kmap)
+		return -1;
 
-		kmap->kmaps = &machine->kmaps;
-		map_groups__insert(&machine->kmaps, map);
-	}
+	kmap->kmaps = &machine->kmaps;
+	map_groups__insert(&machine->kmaps, map);
 
 	return 0;
 }
 
 void machine__destroy_kernel_maps(struct machine *machine)
 {
-	int type;
-
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-		struct map *map = __machine__kernel_map(machine, type);
-
-		if (map == NULL)
-			continue;
+	struct kmap *kmap;
+	struct map *map = machine__kernel_map(machine);
 
-		kmap = map__kmap(map);
-		map_groups__remove(&machine->kmaps, map);
-		if (kmap && kmap->ref_reloc_sym) {
-			/*
-			 * ref_reloc_sym is shared among all maps, so free just
-			 * on one of them.
-			 */
-			if (type == MAP__FUNCTION) {
-				zfree((char **)&kmap->ref_reloc_sym->name);
-				zfree(&kmap->ref_reloc_sym);
-			} else
-				kmap->ref_reloc_sym = NULL;
-		}
+	if (map == NULL)
+		return;
 
-		map__put(machine->vmlinux_maps[type]);
-		machine->vmlinux_maps[type] = NULL;
+	kmap = map__kmap(map);
+	map_groups__remove(&machine->kmaps, map);
+	if (kmap && kmap->ref_reloc_sym) {
+		zfree((char **)&kmap->ref_reloc_sym->name);
+		zfree(&kmap->ref_reloc_sym);
 	}
+
+	map__zput(machine->vmlinux_map);
 }
 
 int machines__create_guest_kernel_maps(struct machines *machines)
@@ -989,43 +1092,35 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
 	return machine__create_kernel_maps(machine);
 }
 
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type)
+int machine__load_kallsyms(struct machine *machine, const char *filename)
 {
 	struct map *map = machine__kernel_map(machine);
 	int ret = __dso__load_kallsyms(map->dso, filename, map, true);
 
 	if (ret > 0) {
-		dso__set_loaded(map->dso, type);
+		dso__set_loaded(map->dso);
 		/*
 		 * Since /proc/kallsyms will have multiple sessions for the
 		 * kernel, with modules between them, fixup the end of all
 		 * sections.
 		 */
-		__map_groups__fixup_end(&machine->kmaps, type);
+		map_groups__fixup_end(&machine->kmaps);
 	}
 
 	return ret;
 }
 
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
+int machine__load_vmlinux_path(struct machine *machine)
 {
 	struct map *map = machine__kernel_map(machine);
 	int ret = dso__load_vmlinux_path(map->dso, map);
 
 	if (ret > 0)
-		dso__set_loaded(map->dso, type);
+		dso__set_loaded(map->dso);
 
 	return ret;
 }
 
-static void map_groups__fixup_end(struct map_groups *mg)
-{
-	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		__map_groups__fixup_end(mg, i);
-}
-
 static char *get_kernel_version(const char *root_dir)
 {
 	char version[PATH_MAX];
@@ -1062,10 +1157,9 @@ static bool is_kmod_dso(struct dso *dso)
 static int map_groups__set_module_path(struct map_groups *mg, const char *path,
 				       struct kmod_path *m)
 {
-	struct map *map;
 	char *long_name;
+	struct map *map = map_groups__find_by_name(mg, m->name);
 
-	map = map_groups__find_by_name(mg, MAP__FUNCTION, m->name);
 	if (map == NULL)
 		return 0;
 
@@ -1214,25 +1308,21 @@ static int machine__create_modules(struct machine *machine)
 static void machine__set_kernel_mmap(struct machine *machine,
 				     u64 start, u64 end)
 {
-	int i;
-
-	for (i = 0; i < MAP__NR_TYPES; i++) {
-		machine->vmlinux_maps[i]->start = start;
-		machine->vmlinux_maps[i]->end   = end;
-
-		/*
-		 * Be a bit paranoid here, some perf.data file came with
-		 * a zero sized synthesized MMAP event for the kernel.
-		 */
-		if (start == 0 && end == 0)
-			machine->vmlinux_maps[i]->end = ~0ULL;
-	}
+	machine->vmlinux_map->start = start;
+	machine->vmlinux_map->end   = end;
+	/*
+	 * Be a bit paranoid here, some perf.data file came with
+	 * a zero sized synthesized MMAP event for the kernel.
+	 */
+	if (start == 0 && end == 0)
+		machine->vmlinux_map->end = ~0ULL;
 }
 
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name = NULL;
+	struct map *map;
 	u64 addr = 0;
 	int ret;
 
@@ -1240,9 +1330,8 @@ int machine__create_kernel_maps(struct machine *machine)
 		return -1;
 
 	ret = __machine__create_kernel_maps(machine, kernel);
-	dso__put(kernel);
 	if (ret < 0)
-		return -1;
+		goto out_put;
 
 	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
 		if (machine__is_host(machine))
@@ -1255,18 +1344,35 @@ int machine__create_kernel_maps(struct machine *machine)
 
 	if (!machine__get_running_kernel_start(machine, &name, &addr)) {
 		if (name &&
-		    maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
+		    map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, addr)) {
 			machine__destroy_kernel_maps(machine);
-			return -1;
+			ret = -1;
+			goto out_put;
 		}
-		machine__set_kernel_mmap(machine, addr, 0);
+
+		/* we have a real start address now, so re-order the kmaps */
+		map = machine__kernel_map(machine);
+
+		map__get(map);
+		map_groups__remove(&machine->kmaps, map);
+
+		/* assume it's the last in the kmaps */
+		machine__set_kernel_mmap(machine, addr, ~0ULL);
+
+		map_groups__insert(&machine->kmaps, map);
+		map__put(map);
 	}
 
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(&machine->kmaps);
-	return 0;
+	if (machine__create_extra_kernel_maps(machine, kernel))
+		pr_debug("Problems creating extra kernel maps, continuing anyway...\n");
+
+	/* update end address of the kernel map using adjacent module address */
+	map = map__next(machine__kernel_map(machine));
+	if (map)
+		machine__set_kernel_mmap(machine, addr, map->start);
+out_put:
+	dso__put(kernel);
+	return ret;
 }
 
 static bool machine__uses_kcore(struct machine *machine)
@@ -1281,6 +1387,32 @@ static bool machine__uses_kcore(struct machine *machine)
 	return false;
 }
 
+static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
+					     union perf_event *event)
+{
+	return machine__is(machine, "x86_64") &&
+	       is_entry_trampoline(event->mmap.filename);
+}
+
+static int machine__process_extra_kernel_map(struct machine *machine,
+					     union perf_event *event)
+{
+	struct map *kernel_map = machine__kernel_map(machine);
+	struct dso *kernel = kernel_map ? kernel_map->dso : NULL;
+	struct extra_kernel_map xm = {
+		.start = event->mmap.start,
+		.end   = event->mmap.start + event->mmap.len,
+		.pgoff = event->mmap.pgoff,
+	};
+
+	if (kernel == NULL)
+		return -1;
+
+	strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN);
+
+	return machine__create_extra_kernel_map(machine, kernel, &xm);
+}
+
 static int machine__process_kernel_mmap_event(struct machine *machine,
 					      union perf_event *event)
 {
@@ -1373,9 +1505,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		 * time /proc/sys/kernel/kptr_restrict was non zero.
 		 */
 		if (event->mmap.pgoff != 0) {
-			maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-							 symbol_name,
-							 event->mmap.pgoff);
+			map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map,
+							symbol_name,
+							event->mmap.pgoff);
 		}
 
 		if (machine__is_default_guest(machine)) {
@@ -1384,6 +1516,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			 */
 			dso__load(kernel, machine__kernel_map(machine));
 		}
+	} else if (perf_event__is_extra_kernel_mmap(machine, event)) {
+		return machine__process_extra_kernel_map(machine, event);
 	}
 	return 0;
 out_problem:
@@ -1396,7 +1530,6 @@ int machine__process_mmap2_event(struct machine *machine,
 {
 	struct thread *thread;
 	struct map *map;
-	enum map_type type;
 	int ret = 0;
 
 	if (dump_trace)
@@ -1415,11 +1548,6 @@ int machine__process_mmap2_event(struct machine *machine,
 	if (thread == NULL)
 		goto out_problem;
 
-	if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
-		type = MAP__VARIABLE;
-	else
-		type = MAP__FUNCTION;
-
 	map = map__new(machine, event->mmap2.start,
 			event->mmap2.len, event->mmap2.pgoff,
 			event->mmap2.maj,
@@ -1427,7 +1555,7 @@ int machine__process_mmap2_event(struct machine *machine,
 			event->mmap2.ino_generation,
 			event->mmap2.prot,
 			event->mmap2.flags,
-			event->mmap2.filename, type, thread);
+			event->mmap2.filename, thread);
 
 	if (map == NULL)
 		goto out_problem_map;
@@ -1454,7 +1582,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 {
 	struct thread *thread;
 	struct map *map;
-	enum map_type type;
+	u32 prot = 0;
 	int ret = 0;
 
 	if (dump_trace)
@@ -1473,16 +1601,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	if (thread == NULL)
 		goto out_problem;
 
-	if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
-		type = MAP__VARIABLE;
-	else
-		type = MAP__FUNCTION;
+	if (!(event->header.misc & PERF_RECORD_MISC_MMAP_DATA))
+		prot = PROT_EXEC;
 
 	map = map__new(machine, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
-			0, 0, 0, 0, 0, 0,
+			0, 0, 0, 0, prot, 0,
 			event->mmap.filename,
-			type, thread);
+			thread);
 
 	if (map == NULL)
 		goto out_problem_map;
@@ -1658,7 +1784,7 @@ static void ip__resolve_ams(struct thread *thread,
 	 * Thus, we have to try consecutively until we find a match
 	 * or else, the symbol is unknown
 	 */
-	thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al);
+	thread__find_cpumode_addr_location(thread, ip, &al);
 
 	ams->addr = ip;
 	ams->al_addr = al.addr;
@@ -1675,15 +1801,7 @@ static void ip__resolve_data(struct thread *thread,
 
 	memset(&al, 0, sizeof(al));
 
-	thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al);
-	if (al.map == NULL) {
-		/*
-		 * some shared data regions have execute bit set which puts
-		 * their mapping in the MAP__FUNCTION type array.
-		 * Check there as a fallback option before dropping the sample.
-		 */
-		thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al);
-	}
+	thread__find_symbol(thread, m, addr, &al);
 
 	ams->addr = addr;
 	ams->al_addr = al.addr;
@@ -1752,8 +1870,7 @@ static int add_callchain_ip(struct thread *thread,
 	al.filtered = 0;
 	al.sym = NULL;
 	if (!cpumode) {
-		thread__find_cpumode_addr_location(thread, MAP__FUNCTION,
-						   ip, &al);
+		thread__find_cpumode_addr_location(thread, ip, &al);
 	} else {
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
@@ -1778,8 +1895,7 @@ static int add_callchain_ip(struct thread *thread,
 			}
 			return 0;
 		}
-		thread__find_addr_location(thread, *cpumode, MAP__FUNCTION,
-					   ip, &al);
+		thread__find_symbol(thread, *cpumode, ip, &al);
 	}
 
 	if (al.sym != NULL) {
@@ -1804,7 +1920,7 @@ static int add_callchain_ip(struct thread *thread,
 	}
 
 	srcline = callchain_srcline(al.map, al.sym, al.addr);
-	return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
+	return callchain_cursor_append(cursor, ip, al.map, al.sym,
 				       branch, flags, nr_loop_iter,
 				       iter_cycles, branch_from, srcline);
 }
@@ -2336,6 +2452,20 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 	return 0;
 }
 
+/*
+ * Compares the raw arch string. N.B. see instead perf_env__arch() if a
+ * normalized arch is needed.
+ */
+bool machine__is(struct machine *machine, const char *arch)
+{
+	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
+}
+
+int machine__nr_cpus_avail(struct machine *machine)
+{
+	return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
+}
+
 int machine__get_kernel_start(struct machine *machine)
 {
 	struct map *map = machine__kernel_map(machine);
@@ -2352,7 +2482,12 @@ int machine__get_kernel_start(struct machine *machine)
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
 		err = map__load(map);
-		if (!err)
+		/*
+		 * On x86_64, PTI entry trampolines are less than the
+		 * start of kernel text, but still above 2^63. So leave
+		 * kernel_start = 1ULL << 63 for x86_64.
+		 */
+		if (!err && !machine__is(machine, "x86_64"))
 			machine->kernel_start = map->start;
 	}
 	return err;
@@ -2367,7 +2502,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
 {
 	struct machine *machine = vmachine;
 	struct map *map;
-	struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map);
+	struct symbol *sym = machine__find_kernel_symbol(machine, *addrp, &map);
 
 	if (sym == NULL)
 		return NULL;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 66cc200ef86f..1de7660d93e9 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -49,13 +49,14 @@ struct machine {
 	struct perf_env   *env;
 	struct dsos	  dsos;
 	struct map_groups kmaps;
-	struct map	  *vmlinux_maps[MAP__NR_TYPES];
+	struct map	  *vmlinux_map;
 	u64		  kernel_start;
 	pid_t		  *current_tid;
 	union { /* Tool specific area */
 		void	  *priv;
 		u64	  db_id;
 	};
+	bool		  trampolines_mapped;
 };
 
 static inline struct threads *machine__threads(struct machine *machine, pid_t tid)
@@ -64,16 +65,22 @@ static inline struct threads *machine__threads(struct machine *machine, pid_t ti
 	return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE];
 }
 
+/*
+ * The main kernel (vmlinux) map
+ */
 static inline
-struct map *__machine__kernel_map(struct machine *machine, enum map_type type)
+struct map *machine__kernel_map(struct machine *machine)
 {
-	return machine->vmlinux_maps[type];
+	return machine->vmlinux_map;
 }
 
+/*
+ * kernel (the one returned by machine__kernel_map()) plus kernel modules maps
+ */
 static inline
-struct map *machine__kernel_map(struct machine *machine)
+struct maps *machine__kernel_maps(struct machine *machine)
 {
-	return __machine__kernel_map(machine, MAP__FUNCTION);
+	return &machine->kmaps.maps;
 }
 
 int machine__get_kernel_start(struct machine *machine);
@@ -182,6 +189,9 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
+bool machine__is(struct machine *machine, const char *arch);
+int machine__nr_cpus_avail(struct machine *machine);
+
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 
@@ -190,44 +200,27 @@ struct dso *machine__findnew_dso(struct machine *machine, const char *filename);
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
 static inline
-struct symbol *machine__find_kernel_symbol(struct machine *machine,
-					   enum map_type type, u64 addr,
+struct symbol *machine__find_kernel_symbol(struct machine *machine, u64 addr,
 					   struct map **mapp)
 {
-	return map_groups__find_symbol(&machine->kmaps, type, addr, mapp);
+	return map_groups__find_symbol(&machine->kmaps, addr, mapp);
 }
 
 static inline
 struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
-						   enum map_type type, const char *name,
+						   const char *name,
 						   struct map **mapp)
 {
-	return map_groups__find_symbol_by_name(&machine->kmaps, type, name, mapp);
-}
-
-static inline
-struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
-					     struct map **mapp)
-{
-	return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr,
-					   mapp);
-}
-
-static inline
-struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
-						     const char *name,
-						     struct map **mapp)
-{
-	return map_groups__find_function_by_name(&machine->kmaps, name, mapp);
+	return map_groups__find_symbol_by_name(&machine->kmaps, name, mapp);
 }
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
 int arch__fix_module_text_start(u64 *start, const char *name);
 
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type);
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type);
+int machine__load_kallsyms(struct machine *machine, const char *filename);
+
+int machine__load_vmlinux_path(struct machine *machine);
 
 size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm);
@@ -276,4 +269,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
  */
 char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
 
+void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+				    size_t bufsz);
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+				      struct dso *kernel);
+
+/* Kernel-space maps for symbols that are outside the main kernel map and module maps */
+struct extra_kernel_map {
+	u64 start;
+	u64 end;
+	u64 pgoff;
+	char name[KMAP_NAME_LEN];
+};
+
+int machine__create_extra_kernel_map(struct machine *machine,
+				     struct dso *kernel,
+				     struct extra_kernel_map *xm);
+
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+					  struct dso *kernel);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8fe57031e1a8..6ae97eda370b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -22,11 +22,6 @@
 
 static void __maps__insert(struct maps *maps, struct map *map);
 
-const char *map_type__name[MAP__NR_TYPES] = {
-	[MAP__FUNCTION] = "Functions",
-	[MAP__VARIABLE] = "Variables",
-};
-
 static inline int is_anon_memory(const char *filename, u32 flags)
 {
 	return flags & MAP_HUGETLB ||
@@ -129,10 +124,8 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 	return false;
 }
 
-void map__init(struct map *map, enum map_type type,
-	       u64 start, u64 end, u64 pgoff, struct dso *dso)
+void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
-	map->type     = type;
 	map->start    = start;
 	map->end      = end;
 	map->pgoff    = pgoff;
@@ -149,7 +142,7 @@ void map__init(struct map *map, enum map_type type,
 struct map *map__new(struct machine *machine, u64 start, u64 len,
 		     u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
 		     u64 ino_gen, u32 prot, u32 flags, char *filename,
-		     enum map_type type, struct thread *thread)
+		     struct thread *thread)
 {
 	struct map *map = malloc(sizeof(*map));
 	struct nsinfo *nsi = NULL;
@@ -173,7 +166,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		map->flags = flags;
 		nsi = nsinfo__get(thread->nsinfo);
 
-		if ((anon || no_dso) && nsi && type == MAP__FUNCTION) {
+		if ((anon || no_dso) && nsi && (prot & PROT_EXEC)) {
 			snprintf(newfilename, sizeof(newfilename),
 				 "/tmp/perf-%d.map", nsi->pid);
 			filename = newfilename;
@@ -203,7 +196,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(map, type, start, start + len, pgoff, dso);
+		map__init(map, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
 			map->map_ip = map->unmap_ip = identity__map_ip;
@@ -213,8 +206,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			 * functions still return NULL, and we avoid the
 			 * unnecessary map__load warning.
 			 */
-			if (type != MAP__FUNCTION)
-				dso__set_loaded(dso, map->type);
+			if (!(prot & PROT_EXEC))
+				dso__set_loaded(dso);
 		}
 		dso->nsinfo = nsi;
 		dso__put(dso);
@@ -231,7 +224,7 @@ out_delete:
  * they are loaded) and for vmlinux, where only after we load all the
  * symbols we'll know where it starts and ends.
  */
-struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
+struct map *map__new2(u64 start, struct dso *dso)
 {
 	struct map *map = calloc(1, (sizeof(*map) +
 				     (dso->kernel ? sizeof(struct kmap) : 0)));
@@ -239,7 +232,7 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 		/*
 		 * ->end will be filled after we load all the symbols
 		 */
-		map__init(map, type, start, 0, 0, dso);
+		map__init(map, start, 0, 0, dso);
 	}
 
 	return map;
@@ -256,7 +249,19 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
  */
 bool __map__is_kernel(const struct map *map)
 {
-	return __machine__kernel_map(map->groups->machine, map->type) == map;
+	return machine__kernel_map(map->groups->machine) == map;
+}
+
+bool __map__is_extra_kernel_map(const struct map *map)
+{
+	struct kmap *kmap = __map__kmap((struct map *)map);
+
+	return kmap && kmap->name[0];
+}
+
+bool map__has_symbols(const struct map *map)
+{
+	return dso__has_symbols(map->dso);
 }
 
 static void map__exit(struct map *map)
@@ -279,7 +284,7 @@ void map__put(struct map *map)
 
 void map__fixup_start(struct map *map)
 {
-	struct rb_root *symbols = &map->dso->symbols[map->type];
+	struct rb_root *symbols = &map->dso->symbols;
 	struct rb_node *nd = rb_first(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
@@ -289,7 +294,7 @@ void map__fixup_start(struct map *map)
 
 void map__fixup_end(struct map *map)
 {
-	struct rb_root *symbols = &map->dso->symbols[map->type];
+	struct rb_root *symbols = &map->dso->symbols;
 	struct rb_node *nd = rb_last(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
@@ -304,7 +309,7 @@ int map__load(struct map *map)
 	const char *name = map->dso->long_name;
 	int nr;
 
-	if (dso__loaded(map->dso, map->type))
+	if (dso__loaded(map->dso))
 		return 0;
 
 	nr = dso__load(map->dso, map);
@@ -348,7 +353,7 @@ struct symbol *map__find_symbol(struct map *map, u64 addr)
 	if (map__load(map) < 0)
 		return NULL;
 
-	return dso__find_symbol(map->dso, map->type, addr);
+	return dso__find_symbol(map->dso, addr);
 }
 
 struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
@@ -356,10 +361,10 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
 	if (map__load(map) < 0)
 		return NULL;
 
-	if (!dso__sorted_by_name(map->dso, map->type))
-		dso__sort_by_name(map->dso, map->type);
+	if (!dso__sorted_by_name(map->dso))
+		dso__sort_by_name(map->dso);
 
-	return dso__find_symbol_by_name(map->dso, map->type, name);
+	return dso__find_symbol_by_name(map->dso, name);
 }
 
 struct map *map__clone(struct map *from)
@@ -494,10 +499,7 @@ static void maps__init(struct maps *maps)
 
 void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
-	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		maps__init(&mg->maps[i]);
-	}
+	maps__init(&mg->maps);
 	mg->machine = machine;
 	refcount_set(&mg->refcnt, 1);
 }
@@ -525,22 +527,12 @@ static void maps__exit(struct maps *maps)
 
 void map_groups__exit(struct map_groups *mg)
 {
-	int i;
-
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		maps__exit(&mg->maps[i]);
+	maps__exit(&mg->maps);
 }
 
 bool map_groups__empty(struct map_groups *mg)
 {
-	int i;
-
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		if (maps__first(&mg->maps[i]))
-			return false;
-	}
-
-	return true;
+	return !maps__first(&mg->maps);
 }
 
 struct map_groups *map_groups__new(struct machine *machine)
@@ -566,10 +558,9 @@ void map_groups__put(struct map_groups *mg)
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
-				       enum map_type type, u64 addr,
-				       struct map **mapp)
+				       u64 addr, struct map **mapp)
 {
-	struct map *map = map_groups__find(mg, type, addr);
+	struct map *map = map_groups__find(mg, addr);
 
 	/* Ensure map is loaded before using map->map_ip */
 	if (map != NULL && map__load(map) >= 0) {
@@ -608,13 +599,10 @@ out:
 }
 
 struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
-					       enum map_type type,
 					       const char *name,
 					       struct map **mapp)
 {
-	struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp);
-
-	return sym;
+	return maps__find_symbol_by_name(&mg->maps, name, mapp);
 }
 
 int map_groups__find_ams(struct addr_map_symbol *ams)
@@ -622,8 +610,7 @@ int map_groups__find_ams(struct addr_map_symbol *ams)
 	if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
 		if (ams->map->groups == NULL)
 			return -1;
-		ams->map = map_groups__find(ams->map->groups, ams->map->type,
-					    ams->addr);
+		ams->map = map_groups__find(ams->map->groups, ams->addr);
 		if (ams->map == NULL)
 			return -1;
 	}
@@ -646,7 +633,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
 		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, pos->type, fp);
+			printed += dso__fprintf(pos->dso, fp);
 			printed += fprintf(fp, "--\n");
 		}
 	}
@@ -656,24 +643,14 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
 	return printed;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
-				  FILE *fp)
-{
-	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
-	return printed += maps__fprintf(&mg->maps[type], fp);
-}
-
 size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 {
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(mg, i, fp);
-	return printed;
+	return maps__fprintf(&mg->maps, fp);
 }
 
 static void __map_groups__insert(struct map_groups *mg, struct map *map)
 {
-	__maps__insert(&mg->maps[map->type], map);
+	__maps__insert(&mg->maps, map);
 	map->groups = mg;
 }
 
@@ -758,19 +735,18 @@ out:
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   FILE *fp)
 {
-	return maps__fixup_overlappings(&mg->maps[map->type], map, fp);
+	return maps__fixup_overlappings(&mg->maps, map, fp);
 }
 
 /*
  * XXX This should not really _copy_ te maps, but refcount them.
  */
-int map_groups__clone(struct thread *thread,
-		      struct map_groups *parent, enum map_type type)
+int map_groups__clone(struct thread *thread, struct map_groups *parent)
 {
 	struct map_groups *mg = thread->mg;
 	int err = -ENOMEM;
 	struct map *map;
-	struct maps *maps = &parent->maps[type];
+	struct maps *maps = &parent->maps;
 
 	down_read(&maps->lock);
 
@@ -877,15 +853,22 @@ struct map *map__next(struct map *map)
 	return NULL;
 }
 
-struct kmap *map__kmap(struct map *map)
+struct kmap *__map__kmap(struct map *map)
 {
-	if (!map->dso || !map->dso->kernel) {
-		pr_err("Internal error: map__kmap with a non-kernel map\n");
+	if (!map->dso || !map->dso->kernel)
 		return NULL;
-	}
 	return (struct kmap *)(map + 1);
 }
 
+struct kmap *map__kmap(struct map *map)
+{
+	struct kmap *kmap = __map__kmap(map);
+
+	if (!kmap)
+		pr_err("Internal error: map__kmap with a non-kernel map\n");
+	return kmap;
+}
+
 struct map_groups *map__kmaps(struct map *map)
 {
 	struct kmap *kmap = map__kmap(map);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 0e9bbe01b0ab..97e2a063bd65 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -8,19 +8,11 @@
 #include <linux/rbtree.h>
 #include <pthread.h>
 #include <stdio.h>
+#include <string.h>
 #include <stdbool.h>
 #include <linux/types.h>
 #include "rwsem.h"
 
-enum map_type {
-	MAP__FUNCTION = 0,
-	MAP__VARIABLE,
-};
-
-#define MAP__NR_TYPES (MAP__VARIABLE + 1)
-
-extern const char *map_type__name[MAP__NR_TYPES];
-
 struct dso;
 struct ip_callchain;
 struct ref_reloc_sym;
@@ -35,7 +27,6 @@ struct map {
 	};
 	u64			start;
 	u64			end;
-	u8 /* enum map_type */	type;
 	bool			erange_warned;
 	u32			priv;
 	u32			prot;
@@ -56,9 +47,12 @@ struct map {
 	refcount_t		refcnt;
 };
 
+#define KMAP_NAME_LEN 256
+
 struct kmap {
 	struct ref_reloc_sym	*ref_reloc_sym;
 	struct map_groups	*kmaps;
+	char			name[KMAP_NAME_LEN];
 };
 
 struct maps {
@@ -67,7 +61,7 @@ struct maps {
 };
 
 struct map_groups {
-	struct maps	 maps[MAP__NR_TYPES];
+	struct maps	 maps;
 	struct machine	 *machine;
 	refcount_t	 refcnt;
 };
@@ -85,6 +79,7 @@ static inline struct map_groups *map_groups__get(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg);
 
+struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
 struct map_groups *map__kmaps(struct map *map);
 
@@ -125,7 +120,7 @@ struct thread;
  * Note: caller must ensure map->dso is not NULL (map is loaded).
  */
 #define map__for_each_symbol(map, pos, n)	\
-	dso__for_each_symbol(map->dso, pos, n, map->type)
+	dso__for_each_symbol(map->dso, pos, n)
 
 /* map__for_each_symbol_with_name - iterate over the symbols in the given map
  *                                  that have the given name
@@ -144,13 +139,13 @@ struct thread;
 #define map__for_each_symbol_by_name(map, sym_name, pos)		\
 	__map__for_each_symbol_by_name(map, sym_name, (pos))
 
-void map__init(struct map *map, enum map_type type,
+void map__init(struct map *map,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct machine *machine, u64 start, u64 len,
 		     u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
 		     u64 ino_gen, u32 prot, u32 flags,
-		     char *filename, enum map_type type, struct thread *thread);
-struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
+		     char *filename, struct thread *thread);
+struct map *map__new2(u64 start, struct dso *dso);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
 
@@ -185,8 +180,6 @@ void map__fixup_end(struct map *map);
 
 void map__reloc_vmlinux(struct map *map);
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
-				  FILE *fp);
 void maps__insert(struct maps *maps, struct map *map);
 void maps__remove(struct maps *maps, struct map *map);
 struct map *maps__find(struct maps *maps, u64 addr);
@@ -197,34 +190,29 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct thread *thread,
-		      struct map_groups *parent, enum map_type type);
+		      struct map_groups *parent);
 size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
 
-int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
-				     u64 addr);
+int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
+				    u64 addr);
 
 static inline void map_groups__insert(struct map_groups *mg, struct map *map)
 {
-	maps__insert(&mg->maps[map->type], map);
+	maps__insert(&mg->maps, map);
 	map->groups = mg;
 }
 
 static inline void map_groups__remove(struct map_groups *mg, struct map *map)
 {
-	maps__remove(&mg->maps[map->type], map);
+	maps__remove(&mg->maps, map);
 }
 
-static inline struct map *map_groups__find(struct map_groups *mg,
-					   enum map_type type, u64 addr)
+static inline struct map *map_groups__find(struct map_groups *mg, u64 addr)
 {
-	return maps__find(&mg->maps[type], addr);
+	return maps__find(&mg->maps, addr);
 }
 
-static inline struct map *map_groups__first(struct map_groups *mg,
-					    enum map_type type)
-{
-	return maps__first(&mg->maps[type]);
-}
+struct map *map_groups__first(struct map_groups *mg);
 
 static inline struct map *map_groups__next(struct map *map)
 {
@@ -232,11 +220,9 @@ static inline struct map *map_groups__next(struct map *map)
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
-				       enum map_type type, u64 addr,
-				       struct map **mapp);
+				       u64 addr, struct map **mapp);
 
 struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
-					       enum map_type type,
 					       const char *name,
 					       struct map **mapp);
 
@@ -244,24 +230,26 @@ struct addr_map_symbol;
 
 int map_groups__find_ams(struct addr_map_symbol *ams);
 
-static inline
-struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
-						 const char *name, struct map **mapp)
-{
-	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp);
-}
-
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   FILE *fp);
 
-struct map *map_groups__find_by_name(struct map_groups *mg,
-				     enum map_type type, const char *name);
+struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
 
 bool __map__is_kernel(const struct map *map);
+bool __map__is_extra_kernel_map(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
-	return !__map__is_kernel(map);
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+}
+
+bool map__has_symbols(const struct map *map);
+
+#define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline"
+
+static inline bool is_entry_trampoline(const char *name)
+{
+	return !strcmp(name, ENTRY_TRAMPOLINE_NAME);
 }
 
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2fb0272146d8..15eec49e71a1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -156,13 +156,12 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 		    (strcmp(sys_dirent->d_name, ".")) &&	\
 		    (strcmp(sys_dirent->d_name, "..")))
 
-static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
+static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
 {
 	char evt_path[MAXPATHLEN];
 	int fd;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path,
-			sys_dir->d_name, evt_dir->d_name);
+	snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dir->d_name);
 	fd = open(evt_path, O_RDONLY);
 	if (fd < 0)
 		return -EINVAL;
@@ -171,12 +170,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 	return 0;
 }
 
-#define for_each_event(sys_dirent, evt_dir, evt_dirent)		\
+#define for_each_event(dir_path, evt_dir, evt_dirent)		\
 	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
 		if (evt_dirent->d_type == DT_DIR &&		\
 		    (strcmp(evt_dirent->d_name, ".")) &&	\
 		    (strcmp(evt_dirent->d_name, "..")) &&	\
-		    (!tp_event_has_id(sys_dirent, evt_dirent)))
+		    (!tp_event_has_id(dir_path, evt_dirent)))
 
 #define MAX_EVENT_LENGTH 512
 
@@ -190,21 +189,21 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	int fd;
 	u64 id;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return NULL;
 
 	for_each_subsystem(sys_dir, sys_dirent) {
-
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 
 			scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
 				  evt_dirent->d_name);
@@ -218,6 +217,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 			close(fd);
 			id = atoll(id_buf);
 			if (id == config) {
+				put_events_file(dir_path);
 				closedir(evt_dir);
 				closedir(sys_dir);
 				path = zalloc(sizeof(*path));
@@ -242,6 +242,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 			}
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 
 	closedir(sys_dir);
@@ -512,14 +514,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 				      struct parse_events_error *err,
 				      struct list_head *head_config)
 {
-	char evt_path[MAXPATHLEN];
+	char *evt_path;
 	struct dirent *evt_ent;
 	DIR *evt_dir;
 	int ret = 0, found = 0;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
+	evt_path = get_events_file(sys_name);
+	if (!evt_path) {
+		tracepoint_error(err, errno, sys_name, evt_name);
+		return -1;
+	}
 	evt_dir = opendir(evt_path);
 	if (!evt_dir) {
+		put_events_file(evt_path);
 		tracepoint_error(err, errno, sys_name, evt_name);
 		return -1;
 	}
@@ -545,6 +552,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 		ret = -1;
 	}
 
+	put_events_file(evt_path);
 	closedir(evt_dir);
 	return ret;
 }
@@ -570,7 +578,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 	DIR *events_dir;
 	int ret = 0;
 
-	events_dir = opendir(tracing_events_path);
+	events_dir = tracing_events__opendir();
 	if (!events_dir) {
 		tracepoint_error(err, errno, sys_name, evt_name);
 		return -1;
@@ -1219,13 +1227,16 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
-			 struct list_head *head_config, bool auto_merge_stats)
+			 struct list_head *head_config,
+			 bool auto_merge_stats,
+			 bool use_alias)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
 	struct perf_pmu *pmu;
 	struct perf_evsel *evsel;
 	struct parse_events_error *err = parse_state->error;
+	bool use_uncore_alias;
 	LIST_HEAD(config_terms);
 
 	pmu = perf_pmu__find(name);
@@ -1244,11 +1255,14 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		memset(&attr, 0, sizeof(attr));
 	}
 
+	use_uncore_alias = (pmu->is_uncore && use_alias);
+
 	if (!head_config) {
 		attr.type = pmu->type;
 		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
 		if (evsel) {
 			evsel->pmu_name = name;
+			evsel->use_uncore_alias = use_uncore_alias;
 			return 0;
 		} else {
 			return -ENOMEM;
@@ -1282,6 +1296,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel->metric_expr = info.metric_expr;
 		evsel->metric_name = info.metric_name;
 		evsel->pmu_name = name;
+		evsel->use_uncore_alias = use_uncore_alias;
 	}
 
 	return evsel ? 0 : -ENOMEM;
@@ -1317,7 +1332,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 				list_add_tail(&term->list, head);
 
 				if (!parse_events_add_pmu(parse_state, list,
-							  pmu->name, head, true)) {
+							  pmu->name, head,
+							  true, true)) {
 					pr_debug("%s -> %s/%s/\n", str,
 						 pmu->name, alias->str);
 					ok++;
@@ -1339,7 +1355,120 @@ int parse_events__modifier_group(struct list_head *list,
 	return parse_events__modifier_event(list, event_mod, true);
 }
 
-void parse_events__set_leader(char *name, struct list_head *list)
+/*
+ * Check if the two uncore PMUs are from the same uncore block
+ * The format of the uncore PMU name is uncore_#blockname_#pmuidx
+ */
+static bool is_same_uncore_block(const char *pmu_name_a, const char *pmu_name_b)
+{
+	char *end_a, *end_b;
+
+	end_a = strrchr(pmu_name_a, '_');
+	end_b = strrchr(pmu_name_b, '_');
+
+	if (!end_a || !end_b)
+		return false;
+
+	if ((end_a - pmu_name_a) != (end_b - pmu_name_b))
+		return false;
+
+	return (strncmp(pmu_name_a, pmu_name_b, end_a - pmu_name_a) == 0);
+}
+
+static int
+parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list,
+					   struct parse_events_state *parse_state)
+{
+	struct perf_evsel *evsel, *leader;
+	uintptr_t *leaders;
+	bool is_leader = true;
+	int i, nr_pmu = 0, total_members, ret = 0;
+
+	leader = list_first_entry(list, struct perf_evsel, node);
+	evsel = list_last_entry(list, struct perf_evsel, node);
+	total_members = evsel->idx - leader->idx + 1;
+
+	leaders = calloc(total_members, sizeof(uintptr_t));
+	if (WARN_ON(!leaders))
+		return 0;
+
+	/*
+	 * Going through the whole group and doing sanity check.
+	 * All members must use alias, and be from the same uncore block.
+	 * Also, storing the leader events in an array.
+	 */
+	__evlist__for_each_entry(list, evsel) {
+
+		/* Only split the uncore group which members use alias */
+		if (!evsel->use_uncore_alias)
+			goto out;
+
+		/* The events must be from the same uncore block */
+		if (!is_same_uncore_block(leader->pmu_name, evsel->pmu_name))
+			goto out;
+
+		if (!is_leader)
+			continue;
+		/*
+		 * If the event's PMU name starts to repeat, it must be a new
+		 * event. That can be used to distinguish the leader from
+		 * other members, even they have the same event name.
+		 */
+		if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) {
+			is_leader = false;
+			continue;
+		}
+		/* The name is always alias name */
+		WARN_ON(strcmp(leader->name, evsel->name));
+
+		/* Store the leader event for each PMU */
+		leaders[nr_pmu++] = (uintptr_t) evsel;
+	}
+
+	/* only one event alias */
+	if (nr_pmu == total_members) {
+		parse_state->nr_groups--;
+		goto handled;
+	}
+
+	/*
+	 * An uncore event alias is a joint name which means the same event
+	 * runs on all PMUs of a block.
+	 * Perf doesn't support mixed events from different PMUs in the same
+	 * group. The big group has to be split into multiple small groups
+	 * which only include the events from the same PMU.
+	 *
+	 * Here the uncore event aliases must be from the same uncore block.
+	 * The number of PMUs must be same for each alias. The number of new
+	 * small groups equals to the number of PMUs.
+	 * Setting the leader event for corresponding members in each group.
+	 */
+	i = 0;
+	__evlist__for_each_entry(list, evsel) {
+		if (i >= nr_pmu)
+			i = 0;
+		evsel->leader = (struct perf_evsel *) leaders[i++];
+	}
+
+	/* The number of members and group name are same for each group */
+	for (i = 0; i < nr_pmu; i++) {
+		evsel = (struct perf_evsel *) leaders[i];
+		evsel->nr_members = total_members / nr_pmu;
+		evsel->group_name = name ? strdup(name) : NULL;
+	}
+
+	/* Take the new small groups into account */
+	parse_state->nr_groups += nr_pmu - 1;
+
+handled:
+	ret = 1;
+out:
+	free(leaders);
+	return ret;
+}
+
+void parse_events__set_leader(char *name, struct list_head *list,
+			      struct parse_events_state *parse_state)
 {
 	struct perf_evsel *leader;
 
@@ -1348,6 +1477,9 @@ void parse_events__set_leader(char *name, struct list_head *list)
 		return;
 	}
 
+	if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
+		return;
+
 	__perf_evlist__set_leader(list);
 	leader = list_entry(list->next, struct perf_evsel, node);
 	leader->group_name = name ? strdup(name) : NULL;
@@ -1715,7 +1847,7 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 		struct perf_evsel *last;
 
 		if (list_empty(&parse_state.list)) {
-			WARN_ONCE(true, "WARNING: event parser found nothing");
+			WARN_ONCE(true, "WARNING: event parser found nothing\n");
 			return -1;
 		}
 
@@ -1968,13 +2100,13 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 	char **evt_list = NULL;
 	unsigned int evt_i = 0, evt_num = 0;
 	bool evt_num_known = false;
 
 restart:
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return;
 
@@ -1989,13 +2121,14 @@ restart:
 		    !strglobmatch(sys_dirent->d_name, subsys_glob))
 			continue;
 
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 			if (event_glob != NULL &&
 			    !strglobmatch(evt_dirent->d_name, event_glob))
 				continue;
@@ -2009,11 +2142,15 @@ restart:
 				 sys_dirent->d_name, evt_dirent->d_name);
 
 			evt_list[evt_i] = strdup(evt_path);
-			if (evt_list[evt_i] == NULL)
+			if (evt_list[evt_i] == NULL) {
+				put_events_file(dir_path);
 				goto out_close_evt_dir;
+			}
 			evt_i++;
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 	closedir(sys_dir);
 
@@ -2061,21 +2198,21 @@ int is_valid_tracepoint(const char *event_string)
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return 0;
 
 	for_each_subsystem(sys_dir, sys_dirent) {
-
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent->d_name, evt_dirent->d_name);
 			if (!strcmp(evt_path, event_string)) {
@@ -2085,6 +2222,8 @@ int is_valid_tracepoint(const char *event_string)
 			}
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 	closedir(sys_dir);
 	return 0;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 5015cfd58277..4473dac27aee 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -167,7 +167,9 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
-			 struct list_head *head_config, bool auto_merge_stats);
+			 struct list_head *head_config,
+			 bool auto_merge_stats,
+			 bool use_alias);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str,
@@ -178,7 +180,8 @@ int parse_events_copy_term_list(struct list_head *old,
 
 enum perf_pmu_event_symbol_type
 perf_pmu__parse_check(const char *name);
-void parse_events__set_leader(char *name, struct list_head *list);
+void parse_events__set_leader(char *name, struct list_head *list,
+			      struct parse_events_state *parse_state);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
 void parse_events_evlist_error(struct parse_events_state *parse_state,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 7afeb80cc39e..e37608a87dba 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -161,7 +161,7 @@ PE_NAME '{' events '}'
 	struct list_head *list = $3;
 
 	inc_group_count(list, _parse_state);
-	parse_events__set_leader($1, list);
+	parse_events__set_leader($1, list, _parse_state);
 	$$ = list;
 }
 |
@@ -170,7 +170,7 @@ PE_NAME '{' events '}'
 	struct list_head *list = $2;
 
 	inc_group_count(list, _parse_state);
-	parse_events__set_leader(NULL, list);
+	parse_events__set_leader(NULL, list, _parse_state);
 	$$ = list;
 }
 
@@ -232,7 +232,7 @@ PE_NAME opt_event_config
 		YYABORT;
 
 	ALLOC_LIST(list);
-	if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) {
+	if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) {
 		struct perf_pmu *pmu = NULL;
 		int ok = 0;
 		char *pattern;
@@ -251,7 +251,7 @@ PE_NAME opt_event_config
 					free(pattern);
 					YYABORT;
 				}
-				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true))
+				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false))
 					ok++;
 				parse_events_terms__delete(terms);
 			}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 064bdcb7bd78..d2fb597c9a8c 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -539,9 +539,10 @@ static bool pmu_is_uncore(const char *name)
 
 /*
  *  PMU CORE devices have different name other than cpu in sysfs on some
- *  platforms. looking for possible sysfs files to identify as core device.
+ *  platforms.
+ *  Looking for possible sysfs files to identify the arm core device.
  */
-static int is_pmu_core(const char *name)
+static int is_arm_pmu_core(const char *name)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -550,18 +551,18 @@ static int is_pmu_core(const char *name)
 	if (!sysfs)
 		return 0;
 
-	/* Look for cpu sysfs (x86 and others) */
-	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs);
-	if ((stat(path, &st) == 0) &&
-			(strncmp(name, "cpu", strlen("cpu")) == 0))
-		return 1;
-
 	/* Look for cpu sysfs (specific to arm) */
 	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
 				sysfs, name);
 	if (stat(path, &st) == 0)
 		return 1;
 
+	/* Look for cpu sysfs (specific to s390) */
+	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
+		  sysfs, name);
+	if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
+		return 1;
+
 	return 0;
 }
 
@@ -580,7 +581,7 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
  * cpuid string generated on this platform.
  * Otherwise return non-zero.
  */
-int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
 {
 	regex_t re;
 	regmatch_t pmatch[1];
@@ -662,6 +663,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 	struct pmu_events_map *map;
 	struct pmu_event *pe;
 	const char *name = pmu->name;
+	const char *pname;
 
 	map = perf_pmu__find_map(pmu);
 	if (!map)
@@ -680,11 +682,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 			break;
 		}
 
-		if (!is_pmu_core(name)) {
-			/* check for uncore devices */
-			if (pe->pmu == NULL)
-				continue;
-			if (strncmp(pe->pmu, name, strlen(pe->pmu)))
+		if (!is_arm_pmu_core(name)) {
+			pname = pe->pmu ? pe->pmu : "cpu";
+			if (strncmp(pname, name, strlen(pname)))
 				continue;
 		}
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index e1dbc9821617..3094f11e7d81 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -111,17 +111,6 @@ void exit_probe_symbol_maps(void)
 	symbol__exit();
 }
 
-static struct symbol *__find_kernel_function_by_name(const char *name,
-						     struct map **mapp)
-{
-	return machine__find_kernel_function_by_name(host_machine, name, mapp);
-}
-
-static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
-{
-	return machine__find_kernel_function(host_machine, addr, mapp);
-}
-
 static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
 {
 	/* kmap->ref_reloc_sym should be set if host_machine is initialized */
@@ -149,7 +138,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 	if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
 		*addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
 	else {
-		sym = __find_kernel_function_by_name(name, &map);
+		sym = machine__find_kernel_symbol_by_name(host_machine, name, &map);
 		if (!sym)
 			return -ENOENT;
 		*addr = map->unmap_ip(map, sym->start) -
@@ -161,8 +150,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct map_groups *grp = &host_machine->kmaps;
-	struct maps *maps = &grp->maps[MAP__FUNCTION];
+	struct maps *maps = machine__kernel_maps(host_machine);
 	struct map *pos;
 
 	/* A file path -- this is an offline module */
@@ -341,7 +329,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 		char module_name[128];
 
 		snprintf(module_name, sizeof(module_name), "[%s]", module);
-		map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+		map = map_groups__find_by_name(&host_machine->kmaps, module_name);
 		if (map) {
 			dso = map->dso;
 			goto found;
@@ -2098,7 +2086,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 		}
 		if (addr) {
 			addr += tp->offset;
-			sym = __find_kernel_function(addr, &map);
+			sym = machine__find_kernel_symbol(host_machine, addr, &map);
 		}
 	}
 
@@ -3504,19 +3492,18 @@ int show_available_funcs(const char *target, struct nsinfo *nsi,
 			       (target) ? : "kernel");
 		goto end;
 	}
-	if (!dso__sorted_by_name(map->dso, map->type))
-		dso__sort_by_name(map->dso, map->type);
+	if (!dso__sorted_by_name(map->dso))
+		dso__sort_by_name(map->dso);
 
 	/* Show all (filtered) symbols */
 	setup_pager();
 
-        for (nd = rb_first(&map->dso->symbol_names[map->type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&map->dso->symbol_names); nd; nd = rb_next(nd)) {
 		struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 
 		if (strfilter__compare(_filter, pos->sym.name))
 			printf("%s\n", pos->sym.name);
-        }
-
+	}
 end:
 	map__put(map);
 	exit_probe_symbol_maps();
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 4ae1123c6794..b76088fadf3d 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -84,8 +84,7 @@ int open_trace_file(const char *trace_file, bool readwrite)
 	char buf[PATH_MAX];
 	int ret;
 
-	ret = e_snprintf(buf, PATH_MAX, "%s/%s",
-			 tracing_path, trace_file);
+	ret = e_snprintf(buf, PATH_MAX, "%s/%s", tracing_path_mount(), trace_file);
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 10dd5fce082b..7f8afacd08ee 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -531,6 +531,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 			PyLong_FromUnsignedLongLong(sample->period));
 	pydict_set_item_string_decref(dict_sample, "phys_addr",
 			PyLong_FromUnsignedLongLong(sample->phys_addr));
+	pydict_set_item_string_decref(dict_sample, "addr",
+			PyLong_FromUnsignedLongLong(sample->addr));
 	set_sample_read_in_dict(dict_sample, sample, evsel);
 	pydict_set_item_string_decref(dict, "sample", dict_sample);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f4a7a437ee87..b998bb475589 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1973,12 +1973,11 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 	return false;
 }
 
-int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
-				     const char *symbol_name, u64 addr)
+int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr)
 {
 	char *bracket;
-	int i;
 	struct ref_reloc_sym *ref;
+	struct kmap *kmap;
 
 	ref = zalloc(sizeof(struct ref_reloc_sym));
 	if (ref == NULL)
@@ -1996,13 +1995,9 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
 
 	ref->addr = addr;
 
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		struct kmap *kmap = map__kmap(maps[i]);
-
-		if (!kmap)
-			continue;
+	kmap = map__kmap(map);
+	if (kmap)
 		kmap->ref_reloc_sym = ref;
-	}
 
 	return 0;
 }
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 26a68dfd8a4f..4058ade352a5 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2,7 +2,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
-#include <sys/mman.h>
+#include <linux/mman.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
@@ -282,7 +282,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 
 	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
 	if (sym && map) {
-		if (map->type == MAP__VARIABLE) {
+		if (sym->type == STT_OBJECT) {
 			ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
 			ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
 					ip - map->unmap_ip(map, sym->start));
@@ -1211,7 +1211,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
 
 		/* print [s] for shared data mmaps */
 		if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
-		     map && (map->type == MAP__VARIABLE) &&
+		     map && !(map->prot & PROT_EXEC) &&
 		    (map->flags & MAP_SHARED) &&
 		    (map->maj || map->min || map->ino ||
 		     map->ino_generation))
@@ -2582,7 +2582,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 		if (sort__mode != SORT_MODE__MEMORY)
 			return -EINVAL;
 
-		if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0)
+		if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0)
 			return -EINVAL;
 
 		if (sd->entry == &sort_mem_daddr_sym)
@@ -2628,7 +2628,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
 		if (*tok) {
 			ret = sort_dimension__add(list, tok, evlist, level);
 			if (ret == -EINVAL) {
-				if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok)))
+				if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok)))
 					pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
 				else
 					pr_err("Invalid --sort key: `%s'", tok);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 035b62e2c60b..9e6896293bbd 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -186,13 +186,13 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 static inline u64 cl_address(u64 address)
 {
 	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
+	return (address & ~(cacheline_size() - 1));
 }
 
 static inline u64 cl_offset(u64 address)
 {
 	/* return the cacheline of the address */
-	return (address & (cacheline_size - 1));
+	return (address & (cacheline_size() - 1));
 }
 
 enum sort_mode {
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 3c21fd059b64..09d6746e6ec8 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -103,6 +103,7 @@ static struct symbol *new_inline_sym(struct dso *dso,
 		inline_sym = symbol__new(base_sym ? base_sym->start : 0,
 					 base_sym ? base_sym->end : 0,
 					 base_sym ? base_sym->binding : 0,
+					 base_sym ? base_sym->type : 0,
 					 funcname);
 		if (inline_sym)
 			inline_sym->inlined = 1;
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 8f56ba4fd258..36efb986f7fc 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -7,8 +7,7 @@
 #include "xyarray.h"
 #include "rblist.h"
 
-struct stats
-{
+struct stats {
 	double n, mean, M2;
 	u64 max, min;
 };
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 2de770511e70..29770ea61768 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -114,16 +114,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
 		sym->st_shndx != SHN_ABS;
 }
 
-static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
+static bool elf_sym__filter(GElf_Sym *sym)
 {
-	switch (type) {
-	case MAP__FUNCTION:
-		return elf_sym__is_function(sym);
-	case MAP__VARIABLE:
-		return elf_sym__is_object(sym);
-	default:
-		return false;
-	}
+	return elf_sym__is_function(sym) || elf_sym__is_object(sym);
 }
 
 static inline const char *elf_sym__name(const GElf_Sym *sym,
@@ -150,17 +143,10 @@ static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
 	return strstr(elf_sec__name(shdr, secstrs), "data") != NULL;
 }
 
-static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
-			  enum map_type type)
+static bool elf_sec__filter(GElf_Shdr *shdr, Elf_Data *secstrs)
 {
-	switch (type) {
-	case MAP__FUNCTION:
-		return elf_sec__is_text(shdr, secstrs);
-	case MAP__VARIABLE:
-		return elf_sec__is_data(shdr, secstrs);
-	default:
-		return false;
-	}
+	return elf_sec__is_text(shdr, secstrs) || 
+	       elf_sec__is_data(shdr, secstrs);
 }
 
 static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
@@ -256,7 +242,7 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
  * And always look at the original dso, not at debuginfo packages, that
  * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
  */
-int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map)
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 {
 	uint32_t nr_rel_entries, idx;
 	GElf_Sym sym;
@@ -364,12 +350,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 			free(demangled);
 
 			f = symbol__new(plt_offset, plt_entry_size,
-					STB_GLOBAL, sympltname);
+					STB_GLOBAL, STT_FUNC, sympltname);
 			if (!f)
 				goto out_elf_end;
 
 			plt_offset += plt_entry_size;
-			symbols__insert(&dso->symbols[map->type], f);
+			symbols__insert(&dso->symbols, f);
 			++nr;
 		}
 	} else if (shdr_rel_plt.sh_type == SHT_REL) {
@@ -390,12 +376,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 			free(demangled);
 
 			f = symbol__new(plt_offset, plt_entry_size,
-					STB_GLOBAL, sympltname);
+					STB_GLOBAL, STT_FUNC, sympltname);
 			if (!f)
 				goto out_elf_end;
 
 			plt_offset += plt_entry_size;
-			symbols__insert(&dso->symbols[map->type], f);
+			symbols__insert(&dso->symbols, f);
 			++nr;
 		}
 	}
@@ -811,6 +797,110 @@ static u64 ref_reloc(struct kmap *kmap)
 void __weak arch__sym_update(struct symbol *s __maybe_unused,
 		GElf_Sym *sym __maybe_unused) { }
 
+static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
+				      GElf_Sym *sym, GElf_Shdr *shdr,
+				      struct map_groups *kmaps, struct kmap *kmap,
+				      struct dso **curr_dsop, struct map **curr_mapp,
+				      const char *section_name,
+				      bool adjust_kernel_syms, bool kmodule, bool *remap_kernel)
+{
+	struct dso *curr_dso = *curr_dsop;
+	struct map *curr_map;
+	char dso_name[PATH_MAX];
+
+	/* Adjust symbol to map to file offset */
+	if (adjust_kernel_syms)
+		sym->st_value -= shdr->sh_addr - shdr->sh_offset;
+
+	if (strcmp(section_name, (curr_dso->short_name + dso->short_name_len)) == 0)
+		return 0;
+
+	if (strcmp(section_name, ".text") == 0) {
+		/*
+		 * The initial kernel mapping is based on
+		 * kallsyms and identity maps.  Overwrite it to
+		 * map to the kernel dso.
+		 */
+		if (*remap_kernel && dso->kernel) {
+			*remap_kernel = false;
+			map->start = shdr->sh_addr + ref_reloc(kmap);
+			map->end = map->start + shdr->sh_size;
+			map->pgoff = shdr->sh_offset;
+			map->map_ip = map__map_ip;
+			map->unmap_ip = map__unmap_ip;
+			/* Ensure maps are correctly ordered */
+			if (kmaps) {
+				map__get(map);
+				map_groups__remove(kmaps, map);
+				map_groups__insert(kmaps, map);
+				map__put(map);
+			}
+		}
+
+		/*
+		 * The initial module mapping is based on
+		 * /proc/modules mapped to offset zero.
+		 * Overwrite it to map to the module dso.
+		 */
+		if (*remap_kernel && kmodule) {
+			*remap_kernel = false;
+			map->pgoff = shdr->sh_offset;
+		}
+
+		*curr_mapp = map;
+		*curr_dsop = dso;
+		return 0;
+	}
+
+	if (!kmap)
+		return 0;
+
+	snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name);
+
+	curr_map = map_groups__find_by_name(kmaps, dso_name);
+	if (curr_map == NULL) {
+		u64 start = sym->st_value;
+
+		if (kmodule)
+			start += map->start + shdr->sh_offset;
+
+		curr_dso = dso__new(dso_name);
+		if (curr_dso == NULL)
+			return -1;
+		curr_dso->kernel = dso->kernel;
+		curr_dso->long_name = dso->long_name;
+		curr_dso->long_name_len = dso->long_name_len;
+		curr_map = map__new2(start, curr_dso);
+		dso__put(curr_dso);
+		if (curr_map == NULL)
+			return -1;
+
+		if (adjust_kernel_syms) {
+			curr_map->start  = shdr->sh_addr + ref_reloc(kmap);
+			curr_map->end	 = curr_map->start + shdr->sh_size;
+			curr_map->pgoff	 = shdr->sh_offset;
+		} else {
+			curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
+		}
+		curr_dso->symtab_type = dso->symtab_type;
+		map_groups__insert(kmaps, curr_map);
+		/*
+		 * Add it before we drop the referece to curr_map, i.e. while
+		 * we still are sure to have a reference to this DSO via
+		 * *curr_map->dso.
+		 */
+		dsos__add(&map->groups->machine->dsos, curr_dso);
+		/* kmaps already got it */
+		map__put(curr_map);
+		dso__set_loaded(curr_dso);
+		*curr_mapp = curr_map;
+		*curr_dsop = curr_dso;
+	} else
+		*curr_dsop = curr_map->dso;
+
+	return 0;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, int kmodule)
 {
@@ -844,7 +934,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	 * have the wrong values for the dso maps, so remove them.
 	 */
 	if (kmodule && syms_ss->symtab)
-		symbols__delete(&dso->symbols[map->type]);
+		symbols__delete(&dso->symbols);
 
 	if (!syms_ss->symtab) {
 		/*
@@ -921,10 +1011,10 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 	dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
 	/*
-	 * Initial kernel and module mappings do not map to the dso.  For
-	 * function mappings, flag the fixups.
+	 * Initial kernel and module mappings do not map to the dso.
+	 * Flag the fixups.
 	 */
-	if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) {
+	if (dso->kernel || kmodule) {
 		remap_kernel = true;
 		adjust_kernel_syms = dso->adjust_symbols;
 	}
@@ -936,7 +1026,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		const char *section_name;
 		bool used_opd = false;
 
-		if (!is_label && !elf_sym__is_a(&sym, map->type))
+		if (!is_label && !elf_sym__filter(&sym))
 			continue;
 
 		/* Reject ARM ELF "mapping symbols": these aren't unique and
@@ -974,7 +1064,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 		gelf_getshdr(sec, &shdr);
 
-		if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
+		if (is_label && !elf_sec__filter(&shdr, secstrs))
 			continue;
 
 		section_name = elf_sec__name(&shdr, secstrs);
@@ -982,134 +1072,37 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		/* On ARM, symbols for thumb functions have 1 added to
 		 * the symbol address as a flag - remove it */
 		if ((ehdr.e_machine == EM_ARM) &&
-		    (map->type == MAP__FUNCTION) &&
+		    (GELF_ST_TYPE(sym.st_info) == STT_FUNC) &&
 		    (sym.st_value & 1))
 			--sym.st_value;
 
 		if (dso->kernel || kmodule) {
-			char dso_name[PATH_MAX];
-
-			/* Adjust symbol to map to file offset */
-			if (adjust_kernel_syms)
-				sym.st_value -= shdr.sh_addr - shdr.sh_offset;
-
-			if (strcmp(section_name,
-				   (curr_dso->short_name +
-				    dso->short_name_len)) == 0)
-				goto new_symbol;
-
-			if (strcmp(section_name, ".text") == 0) {
-				/*
-				 * The initial kernel mapping is based on
-				 * kallsyms and identity maps.  Overwrite it to
-				 * map to the kernel dso.
-				 */
-				if (remap_kernel && dso->kernel) {
-					remap_kernel = false;
-					map->start = shdr.sh_addr +
-						     ref_reloc(kmap);
-					map->end = map->start + shdr.sh_size;
-					map->pgoff = shdr.sh_offset;
-					map->map_ip = map__map_ip;
-					map->unmap_ip = map__unmap_ip;
-					/* Ensure maps are correctly ordered */
-					if (kmaps) {
-						map__get(map);
-						map_groups__remove(kmaps, map);
-						map_groups__insert(kmaps, map);
-						map__put(map);
-					}
-				}
-
-				/*
-				 * The initial module mapping is based on
-				 * /proc/modules mapped to offset zero.
-				 * Overwrite it to map to the module dso.
-				 */
-				if (remap_kernel && kmodule) {
-					remap_kernel = false;
-					map->pgoff = shdr.sh_offset;
-				}
-
-				curr_map = map;
-				curr_dso = dso;
-				goto new_symbol;
-			}
-
-			if (!kmap)
-				goto new_symbol;
-
-			snprintf(dso_name, sizeof(dso_name),
-				 "%s%s", dso->short_name, section_name);
-
-			curr_map = map_groups__find_by_name(kmaps, map->type, dso_name);
-			if (curr_map == NULL) {
-				u64 start = sym.st_value;
-
-				if (kmodule)
-					start += map->start + shdr.sh_offset;
-
-				curr_dso = dso__new(dso_name);
-				if (curr_dso == NULL)
-					goto out_elf_end;
-				curr_dso->kernel = dso->kernel;
-				curr_dso->long_name = dso->long_name;
-				curr_dso->long_name_len = dso->long_name_len;
-				curr_map = map__new2(start, curr_dso,
-						     map->type);
-				dso__put(curr_dso);
-				if (curr_map == NULL) {
-					goto out_elf_end;
-				}
-				if (adjust_kernel_syms) {
-					curr_map->start = shdr.sh_addr +
-							  ref_reloc(kmap);
-					curr_map->end = curr_map->start +
-							shdr.sh_size;
-					curr_map->pgoff = shdr.sh_offset;
-				} else {
-					curr_map->map_ip = identity__map_ip;
-					curr_map->unmap_ip = identity__map_ip;
-				}
-				curr_dso->symtab_type = dso->symtab_type;
-				map_groups__insert(kmaps, curr_map);
-				/*
-				 * Add it before we drop the referece to curr_map,
-				 * i.e. while we still are sure to have a reference
-				 * to this DSO via curr_map->dso.
-				 */
-				dsos__add(&map->groups->machine->dsos, curr_dso);
-				/* kmaps already got it */
-				map__put(curr_map);
-				dso__set_loaded(curr_dso, map->type);
-			} else
-				curr_dso = curr_map->dso;
-
-			goto new_symbol;
-		}
-
-		if ((used_opd && runtime_ss->adjust_symbols)
-				|| (!used_opd && syms_ss->adjust_symbols)) {
+			if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map,
+						       section_name, adjust_kernel_syms, kmodule, &remap_kernel))
+				goto out_elf_end;
+		} else if ((used_opd && runtime_ss->adjust_symbols) ||
+			   (!used_opd && syms_ss->adjust_symbols)) {
 			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
 				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
 				  (u64)sym.st_value, (u64)shdr.sh_addr,
 				  (u64)shdr.sh_offset);
 			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 		}
-new_symbol:
+
 		demangled = demangle_sym(dso, kmodule, elf_name);
 		if (demangled != NULL)
 			elf_name = demangled;
 
 		f = symbol__new(sym.st_value, sym.st_size,
-				GELF_ST_BIND(sym.st_info), elf_name);
+				GELF_ST_BIND(sym.st_info),
+				GELF_ST_TYPE(sym.st_info), elf_name);
 		free(demangled);
 		if (!f)
 			goto out_elf_end;
 
 		arch__sym_update(f, &sym);
 
-		__symbols__insert(&curr_dso->symbols[curr_map->type], f, dso->kernel);
+		__symbols__insert(&curr_dso->symbols, f, dso->kernel);
 		nr++;
 	}
 
@@ -1117,14 +1110,14 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		symbols__fixup_end(&dso->symbols[map->type]);
-		symbols__fixup_duplicate(&dso->symbols[map->type]);
+		symbols__fixup_end(&dso->symbols);
+		symbols__fixup_duplicate(&dso->symbols);
 		if (kmap) {
 			/*
 			 * We need to fixup this here too because we create new
 			 * maps here, for things like vsyscall sections.
 			 */
-			__map_groups__fixup_end(kmaps, map->type);
+			map_groups__fixup_end(kmaps);
 		}
 	}
 	err = nr;
@@ -1393,8 +1386,16 @@ static off_t kcore__write(struct kcore *kcore)
 
 struct phdr_data {
 	off_t offset;
+	off_t rel;
 	u64 addr;
 	u64 len;
+	struct list_head node;
+	struct phdr_data *remaps;
+};
+
+struct sym_data {
+	u64 addr;
+	struct list_head node;
 };
 
 struct kcore_copy_info {
@@ -1404,16 +1405,78 @@ struct kcore_copy_info {
 	u64 last_symbol;
 	u64 first_module;
 	u64 last_module_symbol;
-	struct phdr_data kernel_map;
-	struct phdr_data modules_map;
+	size_t phnum;
+	struct list_head phdrs;
+	struct list_head syms;
 };
 
+#define kcore_copy__for_each_phdr(k, p) \
+	list_for_each_entry((p), &(k)->phdrs, node)
+
+static struct phdr_data *phdr_data__new(u64 addr, u64 len, off_t offset)
+{
+	struct phdr_data *p = zalloc(sizeof(*p));
+
+	if (p) {
+		p->addr   = addr;
+		p->len    = len;
+		p->offset = offset;
+	}
+
+	return p;
+}
+
+static struct phdr_data *kcore_copy_info__addnew(struct kcore_copy_info *kci,
+						 u64 addr, u64 len,
+						 off_t offset)
+{
+	struct phdr_data *p = phdr_data__new(addr, len, offset);
+
+	if (p)
+		list_add_tail(&p->node, &kci->phdrs);
+
+	return p;
+}
+
+static void kcore_copy__free_phdrs(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p, *tmp;
+
+	list_for_each_entry_safe(p, tmp, &kci->phdrs, node) {
+		list_del(&p->node);
+		free(p);
+	}
+}
+
+static struct sym_data *kcore_copy__new_sym(struct kcore_copy_info *kci,
+					    u64 addr)
+{
+	struct sym_data *s = zalloc(sizeof(*s));
+
+	if (s) {
+		s->addr = addr;
+		list_add_tail(&s->node, &kci->syms);
+	}
+
+	return s;
+}
+
+static void kcore_copy__free_syms(struct kcore_copy_info *kci)
+{
+	struct sym_data *s, *tmp;
+
+	list_for_each_entry_safe(s, tmp, &kci->syms, node) {
+		list_del(&s->node);
+		free(s);
+	}
+}
+
 static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 					u64 start)
 {
 	struct kcore_copy_info *kci = arg;
 
-	if (!symbol_type__is_a(type, MAP__FUNCTION))
+	if (!kallsyms__is_function(type))
 		return 0;
 
 	if (strchr(name, '[')) {
@@ -1438,6 +1501,9 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 		return 0;
 	}
 
+	if (is_entry_trampoline(name) && !kcore_copy__new_sym(kci, start))
+		return -1;
+
 	return 0;
 }
 
@@ -1487,27 +1553,39 @@ static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
 	return 0;
 }
 
-static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
-			    u64 s, u64 e)
+static int kcore_copy__map(struct kcore_copy_info *kci, u64 start, u64 end,
+			   u64 pgoff, u64 s, u64 e)
 {
-	if (p->addr || s < start || s >= end)
-		return;
+	u64 len, offset;
+
+	if (s < start || s >= end)
+		return 0;
 
-	p->addr = s;
-	p->offset = (s - start) + pgoff;
-	p->len = e < end ? e - s : end - s;
+	offset = (s - start) + pgoff;
+	len = e < end ? e - s : end - s;
+
+	return kcore_copy_info__addnew(kci, s, len, offset) ? 0 : -1;
 }
 
 static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
 {
 	struct kcore_copy_info *kci = data;
 	u64 end = start + len;
+	struct sym_data *sdat;
 
-	kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
-			kci->etext);
+	if (kcore_copy__map(kci, start, end, pgoff, kci->stext, kci->etext))
+		return -1;
 
-	kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
-			kci->last_module_symbol);
+	if (kcore_copy__map(kci, start, end, pgoff, kci->first_module,
+			    kci->last_module_symbol))
+		return -1;
+
+	list_for_each_entry(sdat, &kci->syms, node) {
+		u64 s = round_down(sdat->addr, page_size);
+
+		if (kcore_copy__map(kci, start, end, pgoff, s, s + len))
+			return -1;
+	}
 
 	return 0;
 }
@@ -1520,6 +1598,64 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
 	return 0;
 }
 
+static void kcore_copy__find_remaps(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p, *k = NULL;
+	u64 kend;
+
+	if (!kci->stext)
+		return;
+
+	/* Find phdr that corresponds to the kernel map (contains stext) */
+	kcore_copy__for_each_phdr(kci, p) {
+		u64 pend = p->addr + p->len - 1;
+
+		if (p->addr <= kci->stext && pend >= kci->stext) {
+			k = p;
+			break;
+		}
+	}
+
+	if (!k)
+		return;
+
+	kend = k->offset + k->len;
+
+	/* Find phdrs that remap the kernel */
+	kcore_copy__for_each_phdr(kci, p) {
+		u64 pend = p->offset + p->len;
+
+		if (p == k)
+			continue;
+
+		if (p->offset >= k->offset && pend <= kend)
+			p->remaps = k;
+	}
+}
+
+static void kcore_copy__layout(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p;
+	off_t rel = 0;
+
+	kcore_copy__find_remaps(kci);
+
+	kcore_copy__for_each_phdr(kci, p) {
+		if (!p->remaps) {
+			p->rel = rel;
+			rel += p->len;
+		}
+		kci->phnum += 1;
+	}
+
+	kcore_copy__for_each_phdr(kci, p) {
+		struct phdr_data *k = p->remaps;
+
+		if (k)
+			p->rel = p->offset - k->offset + k->rel;
+	}
+}
+
 static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 				 Elf *elf)
 {
@@ -1555,7 +1691,12 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 	if (kci->first_module && !kci->last_module_symbol)
 		return -1;
 
-	return kcore_copy__read_maps(kci, elf);
+	if (kcore_copy__read_maps(kci, elf))
+		return -1;
+
+	kcore_copy__layout(kci);
+
+	return 0;
 }
 
 static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,
@@ -1678,12 +1819,15 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 {
 	struct kcore kcore;
 	struct kcore extract;
-	size_t count = 2;
 	int idx = 0, err = -1;
-	off_t offset = page_size, sz, modules_offset = 0;
+	off_t offset, sz;
 	struct kcore_copy_info kci = { .stext = 0, };
 	char kcore_filename[PATH_MAX];
 	char extract_filename[PATH_MAX];
+	struct phdr_data *p;
+
+	INIT_LIST_HEAD(&kci.phdrs);
+	INIT_LIST_HEAD(&kci.syms);
 
 	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
 		return -1;
@@ -1703,20 +1847,17 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
 		goto out_kcore_close;
 
-	if (!kci.modules_map.addr)
-		count -= 1;
-
-	if (kcore__copy_hdr(&kcore, &extract, count))
+	if (kcore__copy_hdr(&kcore, &extract, kci.phnum))
 		goto out_extract_close;
 
-	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
-			    kci.kernel_map.len))
-		goto out_extract_close;
+	offset = gelf_fsize(extract.elf, ELF_T_EHDR, 1, EV_CURRENT) +
+		 gelf_fsize(extract.elf, ELF_T_PHDR, kci.phnum, EV_CURRENT);
+	offset = round_up(offset, page_size);
+
+	kcore_copy__for_each_phdr(&kci, p) {
+		off_t offs = p->rel + offset;
 
-	if (kci.modules_map.addr) {
-		modules_offset = offset + kci.kernel_map.len;
-		if (kcore__add_phdr(&extract, idx, modules_offset,
-				    kci.modules_map.addr, kci.modules_map.len))
+		if (kcore__add_phdr(&extract, idx++, offs, p->addr, p->len))
 			goto out_extract_close;
 	}
 
@@ -1724,14 +1865,14 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	if (sz < 0 || sz > offset)
 		goto out_extract_close;
 
-	if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
-		       kci.kernel_map.len))
-		goto out_extract_close;
+	kcore_copy__for_each_phdr(&kci, p) {
+		off_t offs = p->rel + offset;
 
-	if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
-					 extract.fd, modules_offset,
-					 kci.modules_map.len))
-		goto out_extract_close;
+		if (p->remaps)
+			continue;
+		if (copy_bytes(kcore.fd, p->offset, extract.fd, offs, p->len))
+			goto out_extract_close;
+	}
 
 	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
 		goto out_extract_close;
@@ -1754,6 +1895,9 @@ out_unlink_kallsyms:
 	if (err)
 		kcore_copy__unlink(to_dir, "kallsyms");
 
+	kcore_copy__free_phdrs(&kci);
+	kcore_copy__free_syms(&kci);
+
 	return err;
 }
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index ff48d0d49584..7119df77dc0b 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -288,8 +288,7 @@ void symsrc__destroy(struct symsrc *ss)
 }
 
 int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
-				struct symsrc *ss __maybe_unused,
-				struct map *map __maybe_unused)
+				struct symsrc *ss __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 62b2dd2253eb..8c84437f2a10 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -5,6 +5,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/kernel.h>
+#include <linux/mman.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/param.h>
@@ -70,18 +71,10 @@ static enum dso_binary_type binary_type_symtab[] = {
 
 #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
 
-bool symbol_type__is_a(char symbol_type, enum map_type map_type)
+static bool symbol_type__filter(char symbol_type)
 {
 	symbol_type = toupper(symbol_type);
-
-	switch (map_type) {
-	case MAP__FUNCTION:
-		return symbol_type == 'T' || symbol_type == 'W';
-	case MAP__VARIABLE:
-		return symbol_type == 'D';
-	default:
-		return false;
-	}
+	return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D';
 }
 
 static int prefix_underscores_count(const char *str)
@@ -228,9 +221,9 @@ void symbols__fixup_end(struct rb_root *symbols)
 		curr->end = roundup(curr->start, 4096) + 4096;
 }
 
-void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
+void map_groups__fixup_end(struct map_groups *mg)
 {
-	struct maps *maps = &mg->maps[type];
+	struct maps *maps = &mg->maps;
 	struct map *next, *curr;
 
 	down_write(&maps->lock);
@@ -256,7 +249,7 @@ out_unlock:
 	up_write(&maps->lock);
 }
 
-struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
 	struct symbol *sym = calloc(1, (symbol_conf.priv_size +
@@ -274,6 +267,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 
 	sym->start   = start;
 	sym->end     = len ? start + len : start;
+	sym->type    = type;
 	sym->binding = binding;
 	sym->namelen = namelen - 1;
 
@@ -484,45 +478,40 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 
 void dso__reset_find_symbol_cache(struct dso *dso)
 {
-	enum map_type type;
-
-	for (type = MAP__FUNCTION; type <= MAP__VARIABLE; ++type) {
-		dso->last_find_result[type].addr   = 0;
-		dso->last_find_result[type].symbol = NULL;
-	}
+	dso->last_find_result.addr   = 0;
+	dso->last_find_result.symbol = NULL;
 }
 
-void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym)
+void dso__insert_symbol(struct dso *dso, struct symbol *sym)
 {
-	__symbols__insert(&dso->symbols[type], sym, dso->kernel);
+	__symbols__insert(&dso->symbols, sym, dso->kernel);
 
 	/* update the symbol cache if necessary */
-	if (dso->last_find_result[type].addr >= sym->start &&
-	    (dso->last_find_result[type].addr < sym->end ||
+	if (dso->last_find_result.addr >= sym->start &&
+	    (dso->last_find_result.addr < sym->end ||
 	    sym->start == sym->end)) {
-		dso->last_find_result[type].symbol = sym;
+		dso->last_find_result.symbol = sym;
 	}
 }
 
-struct symbol *dso__find_symbol(struct dso *dso,
-				enum map_type type, u64 addr)
+struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
 {
-	if (dso->last_find_result[type].addr != addr || dso->last_find_result[type].symbol == NULL) {
-		dso->last_find_result[type].addr   = addr;
-		dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr);
+	if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
+		dso->last_find_result.addr   = addr;
+		dso->last_find_result.symbol = symbols__find(&dso->symbols, addr);
 	}
 
-	return dso->last_find_result[type].symbol;
+	return dso->last_find_result.symbol;
 }
 
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__first_symbol(struct dso *dso)
 {
-	return symbols__first(&dso->symbols[type]);
+	return symbols__first(&dso->symbols);
 }
 
-struct symbol *dso__last_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__last_symbol(struct dso *dso)
 {
-	return symbols__last(&dso->symbols[type]);
+	return symbols__last(&dso->symbols);
 }
 
 struct symbol *dso__next_symbol(struct symbol *sym)
@@ -539,24 +528,22 @@ struct symbol *symbol__next_by_name(struct symbol *sym)
 }
 
  /*
-  * Teturns first symbol that matched with @name.
+  * Returns first symbol that matched with @name.
   */
-struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
-					const char *name)
+struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name)
 {
-	struct symbol *s = symbols__find_by_name(&dso->symbol_names[type], name,
+	struct symbol *s = symbols__find_by_name(&dso->symbol_names, name,
 						 SYMBOL_TAG_INCLUDE__NONE);
 	if (!s)
-		s = symbols__find_by_name(&dso->symbol_names[type], name,
+		s = symbols__find_by_name(&dso->symbol_names, name,
 					  SYMBOL_TAG_INCLUDE__DEFAULT_ONLY);
 	return s;
 }
 
-void dso__sort_by_name(struct dso *dso, enum map_type type)
+void dso__sort_by_name(struct dso *dso)
 {
-	dso__set_sorted_by_name(dso, type);
-	return symbols__sort_by_name(&dso->symbol_names[type],
-				     &dso->symbols[type]);
+	dso__set_sorted_by_name(dso);
+	return symbols__sort_by_name(&dso->symbol_names, &dso->symbols);
 }
 
 int modules__parse(const char *filename, void *arg,
@@ -621,11 +608,6 @@ out:
 	return err;
 }
 
-struct process_kallsyms_args {
-	struct map *map;
-	struct dso *dso;
-};
-
 /*
  * These are symbols in the kernel image, so make sure that
  * sym is from a kernel DSO.
@@ -661,10 +643,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 				       char type, u64 start)
 {
 	struct symbol *sym;
-	struct process_kallsyms_args *a = arg;
-	struct rb_root *root = &a->dso->symbols[a->map->type];
+	struct dso *dso = arg;
+	struct rb_root *root = &dso->symbols;
 
-	if (!symbol_type__is_a(type, a->map->type))
+	if (!symbol_type__filter(type))
 		return 0;
 
 	/*
@@ -672,7 +654,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 	 * symbols, setting length to 0, and rely on
 	 * symbols__fixup_end() to fix it up.
 	 */
-	sym = symbol__new(start, 0, kallsyms2elf_binding(type), name);
+	sym = symbol__new(start, 0, kallsyms2elf_binding(type), kallsyms2elf_type(type), name);
 	if (sym == NULL)
 		return -ENOMEM;
 	/*
@@ -689,21 +671,18 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
  * so that we can in the next step set the symbol ->end address and then
  * call kernel_maps__split_kallsyms.
  */
-static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
-				  struct map *map)
+static int dso__load_all_kallsyms(struct dso *dso, const char *filename)
 {
-	struct process_kallsyms_args args = { .map = map, .dso = dso, };
-	return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
+	return kallsyms__parse(filename, dso, map__process_kallsym_symbol);
 }
 
-static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
+static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct dso *dso)
 {
-	struct map_groups *kmaps = map__kmaps(map);
 	struct map *curr_map;
 	struct symbol *pos;
 	int count = 0;
-	struct rb_root old_root = dso->symbols[map->type];
-	struct rb_root *root = &dso->symbols[map->type];
+	struct rb_root old_root = dso->symbols;
+	struct rb_root *root = &dso->symbols;
 	struct rb_node *next = rb_first(root);
 
 	if (!kmaps)
@@ -723,7 +702,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
 		if (module)
 			*module = '\0';
 
-		curr_map = map_groups__find(kmaps, map->type, pos->start);
+		curr_map = map_groups__find(kmaps, pos->start);
 
 		if (!curr_map) {
 			symbol__delete(pos);
@@ -733,7 +712,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
 		pos->start -= curr_map->start - curr_map->pgoff;
 		if (pos->end)
 			pos->end -= curr_map->start - curr_map->pgoff;
-		symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+		symbols__insert(&curr_map->dso->symbols, pos);
 		++count;
 	}
 
@@ -748,22 +727,25 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
+static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, u64 delta,
+				      struct map *initial_map)
 {
-	struct map_groups *kmaps = map__kmaps(map);
 	struct machine *machine;
-	struct map *curr_map = map;
+	struct map *curr_map = initial_map;
 	struct symbol *pos;
 	int count = 0, moved = 0;
-	struct rb_root *root = &dso->symbols[map->type];
+	struct rb_root *root = &dso->symbols;
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
+	bool x86_64;
 
 	if (!kmaps)
 		return -1;
 
 	machine = kmaps->machine;
 
+	x86_64 = machine__is(machine, "x86_64");
+
 	while (next) {
 		char *module;
 
@@ -778,7 +760,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 			*module++ = '\0';
 
 			if (strcmp(curr_map->dso->short_name, module)) {
-				if (curr_map != map &&
+				if (curr_map != initial_map &&
 				    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 				    machine__is_default_guest(machine)) {
 					/*
@@ -788,18 +770,16 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 					 * symbols are in its kmap. Mark it as
 					 * loaded.
 					 */
-					dso__set_loaded(curr_map->dso,
-							curr_map->type);
+					dso__set_loaded(curr_map->dso);
 				}
 
-				curr_map = map_groups__find_by_name(kmaps,
-							map->type, module);
+				curr_map = map_groups__find_by_name(kmaps, module);
 				if (curr_map == NULL) {
 					pr_debug("%s/proc/{kallsyms,modules} "
 					         "inconsistency while looking "
 						 "for \"%s\" module!\n",
 						 machine->root_dir, module);
-					curr_map = map;
+					curr_map = initial_map;
 					goto discard_symbol;
 				}
 
@@ -809,11 +789,21 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 			}
 			/*
 			 * So that we look just like we get from .ko files,
-			 * i.e. not prelinked, relative to map->start.
+			 * i.e. not prelinked, relative to initial_map->start.
 			 */
 			pos->start = curr_map->map_ip(curr_map, pos->start);
 			pos->end   = curr_map->map_ip(curr_map, pos->end);
-		} else if (curr_map != map) {
+		} else if (x86_64 && is_entry_trampoline(pos->name)) {
+			/*
+			 * These symbols are not needed anymore since the
+			 * trampoline maps refer to the text section and it's
+			 * symbols instead. Avoid having to deal with
+			 * relocations, and the assumption that the first symbol
+			 * is the start of kernel text, by simply removing the
+			 * symbols at this point.
+			 */
+			goto discard_symbol;
+		} else if (curr_map != initial_map) {
 			char dso_name[PATH_MAX];
 			struct dso *ndso;
 
@@ -824,7 +814,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 			}
 
 			if (count == 0) {
-				curr_map = map;
+				curr_map = initial_map;
 				goto add_symbol;
 			}
 
@@ -843,7 +833,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 
 			ndso->kernel = dso->kernel;
 
-			curr_map = map__new2(pos->start, ndso, map->type);
+			curr_map = map__new2(pos->start, ndso);
 			if (curr_map == NULL) {
 				dso__put(ndso);
 				return -1;
@@ -858,9 +848,9 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 			pos->end -= delta;
 		}
 add_symbol:
-		if (curr_map != map) {
+		if (curr_map != initial_map) {
 			rb_erase(&pos->rb_node, root);
-			symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+			symbols__insert(&curr_map->dso->symbols, pos);
 			++moved;
 		} else
 			++count;
@@ -871,10 +861,10 @@ discard_symbol:
 		symbol__delete(pos);
 	}
 
-	if (curr_map != map &&
+	if (curr_map != initial_map &&
 	    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 	    machine__is_default_guest(kmaps->machine)) {
-		dso__set_loaded(curr_map->dso, curr_map->type);
+		dso__set_loaded(curr_map->dso);
 	}
 
 	return count + moved;
@@ -1035,7 +1025,12 @@ out_delete_from:
 	return ret;
 }
 
-static int do_validate_kcore_modules(const char *filename, struct map *map,
+struct map *map_groups__first(struct map_groups *mg)
+{
+	return maps__first(&mg->maps);
+}
+
+static int do_validate_kcore_modules(const char *filename,
 				  struct map_groups *kmaps)
 {
 	struct rb_root modules = RB_ROOT;
@@ -1046,13 +1041,12 @@ static int do_validate_kcore_modules(const char *filename, struct map *map,
 	if (err)
 		return err;
 
-	old_map = map_groups__first(kmaps, map->type);
+	old_map = map_groups__first(kmaps);
 	while (old_map) {
 		struct map *next = map_groups__next(old_map);
 		struct module_info *mi;
 
-		if (old_map == map || old_map->start == map->start) {
-			/* The kernel map */
+		if (!__map__is_kmodule(old_map)) {
 			old_map = next;
 			continue;
 		}
@@ -1109,7 +1103,7 @@ static int validate_kcore_modules(const char *kallsyms_filename,
 					     kallsyms_filename))
 		return -EINVAL;
 
-	if (do_validate_kcore_modules(modules_filename, map, kmaps))
+	if (do_validate_kcore_modules(modules_filename, kmaps))
 		return -EINVAL;
 
 	return 0;
@@ -1138,7 +1132,6 @@ static int validate_kcore_addresses(const char *kallsyms_filename,
 
 struct kcore_mapfn_data {
 	struct dso *dso;
-	enum map_type type;
 	struct list_head maps;
 };
 
@@ -1147,7 +1140,7 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
 	struct kcore_mapfn_data *md = data;
 	struct map *map;
 
-	map = map__new2(start, md->dso, md->type);
+	map = map__new2(start, md->dso);
 	if (map == NULL)
 		return -ENOMEM;
 
@@ -1163,13 +1156,13 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			   const char *kallsyms_filename)
 {
 	struct map_groups *kmaps = map__kmaps(map);
-	struct machine *machine;
 	struct kcore_mapfn_data md;
 	struct map *old_map, *new_map, *replacement_map = NULL;
+	struct machine *machine;
 	bool is_64_bit;
 	int err, fd;
 	char kcore_filename[PATH_MAX];
-	struct symbol *sym;
+	u64 stext;
 
 	if (!kmaps)
 		return -EINVAL;
@@ -1177,7 +1170,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	machine = kmaps->machine;
 
 	/* This function requires that the map is the kernel map */
-	if (map != machine->vmlinux_maps[map->type])
+	if (!__map__is_kernel(map))
 		return -EINVAL;
 
 	if (!filename_from_kallsyms_filename(kcore_filename, "kcore",
@@ -1189,7 +1182,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 		return -EINVAL;
 
 	md.dso = dso;
-	md.type = map->type;
 	INIT_LIST_HEAD(&md.maps);
 
 	fd = open(kcore_filename, O_RDONLY);
@@ -1200,7 +1192,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	}
 
 	/* Read new maps into temporary lists */
-	err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
+	err = file__read_maps(fd, map->prot & PROT_EXEC, kcore_mapfn, &md,
 			      &is_64_bit);
 	if (err)
 		goto out_err;
@@ -1212,7 +1204,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	}
 
 	/* Remove old maps */
-	old_map = map_groups__first(kmaps, map->type);
+	old_map = map_groups__first(kmaps);
 	while (old_map) {
 		struct map *next = map_groups__next(old_map);
 
@@ -1220,14 +1212,15 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			map_groups__remove(kmaps, old_map);
 		old_map = next;
 	}
+	machine->trampolines_mapped = false;
 
-	/* Find the kernel map using the first symbol */
-	sym = dso__first_symbol(dso, map->type);
-	list_for_each_entry(new_map, &md.maps, node) {
-		if (sym && sym->start >= new_map->start &&
-		    sym->start < new_map->end) {
-			replacement_map = new_map;
-			break;
+	/* Find the kernel map using the '_stext' symbol */
+	if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) {
+		list_for_each_entry(new_map, &md.maps, node) {
+			if (stext >= new_map->start && stext < new_map->end) {
+				replacement_map = new_map;
+				break;
+			}
 		}
 	}
 
@@ -1256,6 +1249,19 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 		map__put(new_map);
 	}
 
+	if (machine__is(machine, "x86_64")) {
+		u64 addr;
+
+		/*
+		 * If one of the corresponding symbols is there, assume the
+		 * entry trampoline maps are too.
+		 */
+		if (!kallsyms__get_function_start(kallsyms_filename,
+						  ENTRY_TRAMPOLINE_NAME,
+						  &addr))
+			machine->trampolines_mapped = true;
+	}
+
 	/*
 	 * Set the data type and long name so that kcore can be read via
 	 * dso__data_read_addr().
@@ -1268,7 +1274,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 
 	close(fd);
 
-	if (map->type == MAP__FUNCTION)
+	if (map->prot & PROT_EXEC)
 		pr_debug("Using %s for kernel object code\n", kcore_filename);
 	else
 		pr_debug("Using %s for kernel data\n", kcore_filename);
@@ -1289,14 +1295,10 @@ out_err:
  * If the kernel is relocated at boot time, kallsyms won't match.  Compute the
  * delta based on the relocation reference symbol.
  */
-static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
+static int kallsyms__delta(struct kmap *kmap, const char *filename, u64 *delta)
 {
-	struct kmap *kmap = map__kmap(map);
 	u64 addr;
 
-	if (!kmap)
-		return -1;
-
 	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name)
 		return 0;
 
@@ -1310,19 +1312,23 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
 int __dso__load_kallsyms(struct dso *dso, const char *filename,
 			 struct map *map, bool no_kcore)
 {
+	struct kmap *kmap = map__kmap(map);
 	u64 delta = 0;
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return -1;
 
-	if (dso__load_all_kallsyms(dso, filename, map) < 0)
+	if (!kmap || !kmap->kmaps)
+		return -1;
+
+	if (dso__load_all_kallsyms(dso, filename) < 0)
 		return -1;
 
-	if (kallsyms__delta(map, filename, &delta))
+	if (kallsyms__delta(kmap, filename, &delta))
 		return -1;
 
-	symbols__fixup_end(&dso->symbols[map->type]);
-	symbols__fixup_duplicate(&dso->symbols[map->type]);
+	symbols__fixup_end(&dso->symbols);
+	symbols__fixup_duplicate(&dso->symbols);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
@@ -1330,9 +1336,9 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
 		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
 	if (!no_kcore && !dso__load_kcore(dso, map, filename))
-		return dso__split_kallsyms_for_kcore(dso, map);
+		return map_groups__split_kallsyms_for_kcore(kmap->kmaps, dso);
 	else
-		return dso__split_kallsyms(dso, map, delta);
+		return map_groups__split_kallsyms(kmap->kmaps, dso, delta, map);
 }
 
 int dso__load_kallsyms(struct dso *dso, const char *filename,
@@ -1341,8 +1347,7 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	return __dso__load_kallsyms(dso, filename, map, false);
 }
 
-static int dso__load_perf_map(const char *map_path, struct dso *dso,
-			      struct map *map)
+static int dso__load_perf_map(const char *map_path, struct dso *dso)
 {
 	char *line = NULL;
 	size_t n;
@@ -1379,12 +1384,12 @@ static int dso__load_perf_map(const char *map_path, struct dso *dso,
 		if (len + 2 >= line_len)
 			continue;
 
-		sym = symbol__new(start, size, STB_GLOBAL, line + len);
+		sym = symbol__new(start, size, STB_GLOBAL, STT_FUNC, line + len);
 
 		if (sym == NULL)
 			goto out_delete_line;
 
-		symbols__insert(&dso->symbols[map->type], sym);
+		symbols__insert(&dso->symbols, sym);
 		nr_syms++;
 	}
 
@@ -1509,25 +1514,27 @@ int dso__load(struct dso *dso, struct map *map)
 	pthread_mutex_lock(&dso->lock);
 
 	/* check again under the dso->lock */
-	if (dso__loaded(dso, map->type)) {
+	if (dso__loaded(dso)) {
 		ret = 1;
 		goto out;
 	}
 
+	if (map->groups && map->groups->machine)
+		machine = map->groups->machine;
+	else
+		machine = NULL;
+
 	if (dso->kernel) {
 		if (dso->kernel == DSO_TYPE_KERNEL)
 			ret = dso__load_kernel_sym(dso, map);
 		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 			ret = dso__load_guest_kernel_sym(dso, map);
 
+		if (machine__is(machine, "x86_64"))
+			machine__map_x86_64_entry_trampolines(machine, dso);
 		goto out;
 	}
 
-	if (map->groups && map->groups->machine)
-		machine = map->groups->machine;
-	else
-		machine = NULL;
-
 	dso->adjust_symbols = 0;
 
 	if (perfmap) {
@@ -1542,7 +1549,7 @@ int dso__load(struct dso *dso, struct map *map)
 			goto out;
 		}
 
-		ret = dso__load_perf_map(map_path, dso, map);
+		ret = dso__load_perf_map(map_path, dso);
 		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
 					     DSO_BINARY_TYPE__NOT_FOUND;
 		goto out;
@@ -1651,7 +1658,7 @@ int dso__load(struct dso *dso, struct map *map)
 	if (ret > 0) {
 		int nr_plt;
 
-		nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map);
+		nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss);
 		if (nr_plt > 0)
 			ret += nr_plt;
 	}
@@ -1663,17 +1670,16 @@ out_free:
 	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
 		ret = 0;
 out:
-	dso__set_loaded(dso, map->type);
+	dso__set_loaded(dso);
 	pthread_mutex_unlock(&dso->lock);
 	nsinfo__mountns_exit(&nsc);
 
 	return ret;
 }
 
-struct map *map_groups__find_by_name(struct map_groups *mg,
-				     enum map_type type, const char *name)
+struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
 {
-	struct maps *maps = &mg->maps[type];
+	struct maps *maps = &mg->maps;
 	struct map *map;
 
 	down_read(&maps->lock);
@@ -1720,7 +1726,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 		else
 			dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
 		dso__set_long_name(dso, vmlinux, vmlinux_allocated);
-		dso__set_loaded(dso, map->type);
+		dso__set_loaded(dso);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
 
@@ -2091,16 +2097,14 @@ static bool symbol__read_kptr_restrict(void)
 
 int symbol__annotation_init(void)
 {
+	if (symbol_conf.init_annotation)
+		return 0;
+
 	if (symbol_conf.initialized) {
 		pr_err("Annotation needs to be init before symbol__init()\n");
 		return -1;
 	}
 
-	if (symbol_conf.init_annotation) {
-		pr_warning("Annotation being initialized multiple times\n");
-		return 0;
-	}
-
 	symbol_conf.priv_size += sizeof(struct annotation);
 	symbol_conf.init_annotation = true;
 	return 0;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 70c16741f50a..1a16438eb3ce 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -57,7 +57,8 @@ struct symbol {
 	u64		start;
 	u64		end;
 	u16		namelen;
-	u8		binding;
+	u8		type:4;
+	u8		binding:4;
 	u8		idle:1;
 	u8		ignore:1;
 	u8		inlined:1;
@@ -259,17 +260,16 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
 			 bool no_kcore);
 int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
 
-void dso__insert_symbol(struct dso *dso, enum map_type type,
+void dso__insert_symbol(struct dso *dso,
 			struct symbol *sym);
 
-struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
-				u64 addr);
-struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
-					const char *name);
+struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
+struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
+
 struct symbol *symbol__next_by_name(struct symbol *sym);
 
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
-struct symbol *dso__last_symbol(struct dso *dso, enum map_type type);
+struct symbol *dso__first_symbol(struct dso *dso);
+struct symbol *dso__last_symbol(struct dso *dso);
 struct symbol *dso__next_symbol(struct symbol *sym);
 
 enum dso_type dso__type_fd(int fd);
@@ -288,7 +288,7 @@ void symbol__exit(void);
 void symbol__elf_init(void);
 int symbol__annotation_init(void);
 
-struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name);
 size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
 				      const struct addr_location *al,
 				      bool unknown_as_addr,
@@ -300,7 +300,6 @@ size_t __symbol__fprintf_symname(const struct symbol *sym,
 				 bool unknown_as_addr, FILE *fp);
 size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
 size_t symbol__fprintf(struct symbol *sym, FILE *fp);
-bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
 int symbol__config_symfs(const struct option *opt __maybe_unused,
@@ -308,8 +307,7 @@ int symbol__config_symfs(const struct option *opt __maybe_unused,
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, int kmodule);
-int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
-				struct map *map);
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss);
 
 char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name);
 
@@ -317,7 +315,7 @@ void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel)
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root *symbols);
 void symbols__fixup_end(struct rb_root *symbols);
-void __map_groups__fixup_end(struct map_groups *mg, enum map_type type);
+void map_groups__fixup_end(struct map_groups *mg);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
 int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 6dd2cb88ccbe..ed0205cc7942 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -58,13 +58,13 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
 }
 
 size_t dso__fprintf_symbols_by_name(struct dso *dso,
-				    enum map_type type, FILE *fp)
+				    FILE *fp)
 {
 	size_t ret = 0;
 	struct rb_node *nd;
 	struct symbol_name_rb_node *pos;
 
-	for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&dso->symbol_names); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 		fprintf(fp, "%s\n", pos->sym.name);
 	}
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 895122d638dd..0ee7f568d60c 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -17,7 +17,7 @@
 #include <stdlib.h>
 #include <linux/compiler.h>
 
-#ifdef HAVE_SYSCALL_TABLE
+#ifdef HAVE_SYSCALL_TABLE_SUPPORT
 #include <string.h>
 #include "string2.h"
 #include "util.h"
@@ -139,7 +139,7 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g
 	return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
 }
 
-#else /* HAVE_SYSCALL_TABLE */
+#else /* HAVE_SYSCALL_TABLE_SUPPORT */
 
 #include <libaudit.h>
 
@@ -176,4 +176,4 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g
 {
 	return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
 }
-#endif /* HAVE_SYSCALL_TABLE */
+#endif /* HAVE_SYSCALL_TABLE_SUPPORT */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 68b65b10579b..2048d393ece6 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -302,23 +302,20 @@ int thread__insert_map(struct thread *thread, struct map *map)
 static int __thread__prepare_access(struct thread *thread)
 {
 	bool initialized = false;
-	int i, err = 0;
-
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		struct maps *maps = &thread->mg->maps[i];
-		struct map *map;
+	int err = 0;
+	struct maps *maps = &thread->mg->maps;
+	struct map *map;
 
-		down_read(&maps->lock);
+	down_read(&maps->lock);
 
-		for (map = maps__first(maps); map; map = map__next(map)) {
-			err = unwind__prepare_access(thread, map, &initialized);
-			if (err || initialized)
-				break;
-		}
-
-		up_read(&maps->lock);
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		err = unwind__prepare_access(thread, map, &initialized);
+		if (err || initialized)
+			break;
 	}
 
+	up_read(&maps->lock);
+
 	return err;
 }
 
@@ -335,8 +332,6 @@ static int thread__prepare_access(struct thread *thread)
 static int thread__clone_map_groups(struct thread *thread,
 				    struct thread *parent)
 {
-	int i;
-
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
 		return thread__prepare_access(thread);
@@ -348,9 +343,8 @@ static int thread__clone_map_groups(struct thread *thread,
 	}
 
 	/* But this one is new process, copy maps. */
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		if (map_groups__clone(thread, parent->mg, i) < 0)
-			return -ENOMEM;
+	if (map_groups__clone(thread, parent->mg) < 0)
+		return -ENOMEM;
 
 	return 0;
 }
@@ -371,8 +365,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 	return thread__clone_map_groups(thread, parent);
 }
 
-void thread__find_cpumode_addr_location(struct thread *thread,
-					enum map_type type, u64 addr,
+void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 					struct addr_location *al)
 {
 	size_t i;
@@ -384,7 +377,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
 	};
 
 	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
-		thread__find_addr_location(thread, cpumodes[i], type, addr, al);
+		thread__find_symbol(thread, cpumodes[i], addr, al);
 		if (al->map)
 			break;
 	}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 14d44c3235b8..07606aa6998d 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -92,16 +92,13 @@ size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
 
-void thread__find_addr_map(struct thread *thread,
-			   u8 cpumode, enum map_type type, u64 addr,
-			   struct addr_location *al);
+struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
+			     struct addr_location *al);
 
-void thread__find_addr_location(struct thread *thread,
-				u8 cpumode, enum map_type type, u64 addr,
-				struct addr_location *al);
+struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
+				   u64 addr, struct addr_location *al);
 
-void thread__find_cpumode_addr_location(struct thread *thread,
-					enum map_type type, u64 addr,
+void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 					struct addr_location *al);
 
 static inline void *thread__priv(struct thread *thread)
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d7f2113462fb..c85d0d1a65ed 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -103,11 +103,10 @@ out:
 
 static int record_header_files(void)
 {
-	char *path;
+	char *path = get_events_file("header_page");
 	struct stat st;
 	int err = -EIO;
 
-	path = get_tracing_file("events/header_page");
 	if (!path) {
 		pr_debug("can't get tracing/events/header_page");
 		return -ENOMEM;
@@ -128,9 +127,9 @@ static int record_header_files(void)
 		goto out;
 	}
 
-	put_tracing_file(path);
+	put_events_file(path);
 
-	path = get_tracing_file("events/header_event");
+	path = get_events_file("header_event");
 	if (!path) {
 		pr_debug("can't get tracing/events/header_event");
 		err = -ENOMEM;
@@ -154,7 +153,7 @@ static int record_header_files(void)
 
 	err = 0;
 out:
-	put_tracing_file(path);
+	put_events_file(path);
 	return err;
 }
 
@@ -243,7 +242,7 @@ static int record_ftrace_files(struct tracepoint_path *tps)
 	char *path;
 	int ret;
 
-	path = get_tracing_file("events/ftrace");
+	path = get_events_file("ftrace");
 	if (!path) {
 		pr_debug("can't get tracing/events/ftrace");
 		return -ENOMEM;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 0ac9077f62a2..b1e5c3a2b8e3 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -98,7 +98,7 @@ static void register_python_scripting(struct scripting_ops *scripting_ops)
 	}
 }
 
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
 void setup_python_scripting(void)
 {
 	register_python_scripting(&python_scripting_unsupported_ops);
@@ -161,7 +161,7 @@ static void register_perl_scripting(struct scripting_ops *scripting_ops)
 	}
 }
 
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
 void setup_perl_scripting(void)
 {
 	register_perl_scripting(&perl_scripting_unsupported_ops);
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 16a776371d03..1aa368603268 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -75,6 +75,7 @@ void trace_event__cleanup(struct trace_event *t)
 static struct event_format*
 tp_format(const char *sys, const char *name)
 {
+	char *tp_dir = get_events_file(sys);
 	struct pevent *pevent = tevent.pevent;
 	struct event_format *event = NULL;
 	char path[PATH_MAX];
@@ -82,8 +83,11 @@ tp_format(const char *sys, const char *name)
 	char *data;
 	int err;
 
-	scnprintf(path, PATH_MAX, "%s/%s/%s/format",
-		  tracing_events_path, sys, name);
+	if (!tp_dir)
+		return ERR_PTR(-errno);
+
+	scnprintf(path, PATH_MAX, "%s/%s/format", tp_dir, name);
+	put_events_file(tp_dir);
 
 	err = filename__read_str(path, &data, &size);
 	if (err)
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7bdd239c795c..538db4e5d1e6 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -28,10 +28,11 @@ static int __report_module(struct addr_location *al, u64 ip,
 {
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
-
-	thread__find_addr_location(ui->thread,
-				   PERF_RECORD_MISC_USER,
-				   MAP__FUNCTION, ip, al);
+	/*
+	 * Some callers will use al->sym, so we can't just use the
+	 * cheaper thread__find_map() here.
+	 */
+	thread__find_symbol(ui->thread, PERF_RECORD_MISC_USER, ip, al);
 
 	if (al->map)
 		dso = al->map->dso;
@@ -103,19 +104,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
 	struct addr_location al;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-			      MAP__FUNCTION, addr, &al);
-	if (!al.map) {
-		/*
-		 * We've seen cases (softice) where DWARF unwinder went
-		 * through non executable mmaps, which we need to lookup
-		 * in MAP__VARIABLE tree.
-		 */
-		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-				      MAP__VARIABLE, addr, &al);
-	}
-
-	if (!al.map) {
+	if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
 		return -1;
 	}
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index af873044d33a..6a11bc7e6b27 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -366,19 +366,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
 {
 	struct addr_location al;
-
-	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-			      MAP__FUNCTION, ip, &al);
-	if (!al.map) {
-		/*
-		 * We've seen cases (softice) where DWARF unwinder went
-		 * through non executable mmaps, which we need to lookup
-		 * in MAP__VARIABLE tree.
-		 */
-		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-				      MAP__VARIABLE, ip, &al);
-	}
-	return al.map;
+	return thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al);
 }
 
 static int
@@ -586,12 +574,9 @@ static int entry(u64 ip, struct thread *thread,
 	struct unwind_entry e;
 	struct addr_location al;
 
-	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
-				   MAP__FUNCTION, ip, &al);
-
+	e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 	e.ip = al.addr;
 	e.map = al.map;
-	e.sym = al.sym;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
 		 al.sym ? al.sym->name : "''",
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 1019bbc5dbd8..eac5b858a371 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -38,11 +38,43 @@ void perf_set_multithreaded(void)
 }
 
 unsigned int page_size;
-int cacheline_size;
+
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+static void cache_line_size(int *cacheline_sizep)
+{
+	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+		pr_debug("cannot determine cache line size");
+}
+#endif
+
+int cacheline_size(void)
+{
+	static int size;
+
+	if (!size)
+		cache_line_size(&size);
+
+	return size;
+}
 
 int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
 int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
+int sysctl__max_stack(void)
+{
+	int value;
+
+	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
+		sysctl_perf_event_max_stack = value;
+
+	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+		sysctl_perf_event_max_contexts_per_stack = value;
+
+	return sysctl_perf_event_max_stack;
+}
+
 bool test_attr__enabled;
 
 bool perf_host  = true;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c9626c206208..dc58254a2b69 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -43,7 +43,9 @@ size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
 extern unsigned int page_size;
-extern int cacheline_size;
+int __pure cacheline_size(void);
+
+int sysctl__max_stack(void);
 
 int fetch_kernel_version(unsigned int *puint,
 			 char *str, size_t str_sz);
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 0acb1ec0e2f0..741af209b19d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -139,12 +139,10 @@ static enum dso_type machine__thread_dso_type(struct machine *machine,
 					      struct thread *thread)
 {
 	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
-	struct map *map;
-	struct dso *dso;
+	struct map *map = map_groups__first(thread->mg);
 
-	map = map_groups__first(thread->mg, MAP__FUNCTION);
 	for (; map ; map = map_groups__next(map)) {
-		dso = map->dso;
+		struct dso *dso = map->dso;
 		if (!dso || dso->long_name[0] != '/')
 			continue;
 		dso_type = dso__type(dso, machine);
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index 2cccbba64418..f304be71c278 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -56,6 +56,7 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM}
 # to compile vs uClibc, that can be done here as well.
 CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
 CROSS_COMPILE ?= $(CROSS)
+LD = $(CC)
 HOSTCC = gcc
 
 # check if compiler option is supported
diff --git a/tools/power/pm-graph/bootgraph.py b/tools/power/pm-graph/bootgraph.py
index abb4c38f029b..8ee626c0f6a5 100755
--- a/tools/power/pm-graph/bootgraph.py
+++ b/tools/power/pm-graph/bootgraph.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/python2
 #
 # Tool for analyzing boot timing
 # Copyright (c) 2013, Intel Corporation.
diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8
index 18baaf6300c9..070be2cf7f74 100644
--- a/tools/power/pm-graph/sleepgraph.8
+++ b/tools/power/pm-graph/sleepgraph.8
@@ -168,6 +168,7 @@ Create a summary page of all tests in \fIindir\fR. Creates summary.html
 in the current folder. The output page is a table of tests with
 suspend and resume values sorted by suspend mode, host, and kernel.
 Includes test averages by mode and links to the test html files.
+Use -genhtml to include tests with missing html.
 .TP
 \fB-modes\fR
 List available suspend modes.
@@ -179,6 +180,9 @@ with any options you intend to use to see if they will work.
 \fB-fpdt\fR
 Print out the contents of the ACPI Firmware Performance Data Table.
 .TP
+\fB-battery\fR
+Print out battery status and current charge.
+.TP
 \fB-sysinfo\fR
 Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode.
 .TP
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 266409fb27ae..0c760478f7d7 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/python2
 #
 # Tool for analyzing suspend/resume timing
 # Copyright (c) 2013, Intel Corporation.
@@ -69,7 +69,7 @@ from subprocess import call, Popen, PIPE
 #	 store system values and test parameters
 class SystemValues:
 	title = 'SleepGraph'
-	version = '5.0'
+	version = '5.1'
 	ansi = False
 	rs = 0
 	display = 0
@@ -240,7 +240,7 @@ class SystemValues:
 	kprobes = dict()
 	timeformat = '%.3f'
 	cmdline = '%s %s' % \
-			(os.path.basename(sys.argv[0]), string.join(sys.argv[1:], ' '))
+			(os.path.basename(sys.argv[0]), ' '.join(sys.argv[1:]))
 	def __init__(self):
 		self.archargs = 'args_'+platform.machine()
 		self.hostname = platform.node()
@@ -917,12 +917,18 @@ class Data:
 			self.devicegroups.append([phase])
 		self.errorinfo = {'suspend':[],'resume':[]}
 	def extractErrorInfo(self):
+		elist = {
+			'HWERROR' : '.*\[ *Hardware Error *\].*',
+			'FWBUG'   : '.*\[ *Firmware Bug *\].*',
+			'BUG'     : '.*BUG.*',
+			'ERROR'   : '.*ERROR.*',
+			'WARNING' : '.*WARNING.*',
+			'IRQ'     : '.*genirq: .*',
+			'TASKFAIL': '.*Freezing of tasks failed.*',
+		}
 		lf = sysvals.openlog(sysvals.dmesgfile, 'r')
 		i = 0
 		list = []
-		# sl = start line, et = error time, el = error line
-		type = 'ERROR'
-		sl = et = el = -1
 		for line in lf:
 			i += 1
 			m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
@@ -931,43 +937,13 @@ class Data:
 			t = float(m.group('ktime'))
 			if t < self.start or t > self.end:
 				continue
-			if t < self.tSuspended:
-				dir = 'suspend'
-			else:
-				dir = 'resume'
+			dir = 'suspend' if t < self.tSuspended else 'resume'
 			msg = m.group('msg')
-			if re.match('-*\[ *cut here *\]-*', msg):
-				type = 'WARNING'
-				sl = i
-			elif re.match('genirq: .*', msg):
-				type = 'IRQ'
-				sl = i
-			elif re.match('BUG: .*', msg) or re.match('kernel BUG .*', msg):
-				type = 'BUG'
-				sl = i
-			elif re.match('-*\[ *end trace .*\]-*', msg) or \
-				re.match('R13: .*', msg):
-				if et >= 0 and sl >= 0:
-					list.append((type, dir, et, sl, i))
-					self.kerror = True
-					sl = et = el = -1
-					type = 'ERROR'
-			elif 'Call Trace:' in msg:
-				if el >= 0 and et >= 0:
-					list.append((type, dir, et, el, el))
+			for err in elist:
+				if re.match(elist[err], msg):
+					list.append((err, dir, t, i, i))
 					self.kerror = True
-				et, el = t, i
-				if sl < 0 or type == 'BUG':
-					slval = i
-					if sl >= 0:
-						slval = sl
-					list.append((type, dir, et, slval, i))
-					self.kerror = True
-					sl = et = el = -1
-					type = 'ERROR'
-		if el >= 0 and et >= 0:
-			list.append((type, dir, et, el, el))
-			self.kerror = True
+					break
 		for e in list:
 			type, dir, t, idx1, idx2 = e
 			sysvals.vprint('kernel %s found in %s at %f' % (type, dir, t))
@@ -2331,12 +2307,14 @@ class TestProps:
 		sv.suspendmode = data.stamp['mode']
 		if sv.suspendmode == 'command' and sv.ftracefile != '':
 			modes = ['on', 'freeze', 'standby', 'mem', 'disk']
-			out = Popen(['grep', 'machine_suspend', sv.ftracefile],
-				stderr=PIPE, stdout=PIPE).stdout.read()
-			m = re.match('.* machine_suspend\[(?P<mode>.*)\]', out)
-			if m and m.group('mode') in ['1', '2', '3', '4']:
-				sv.suspendmode = modes[int(m.group('mode'))]
-				data.stamp['mode'] = sv.suspendmode
+			fp = sysvals.openlog(sv.ftracefile, 'r')
+			for line in fp:
+				m = re.match('.* machine_suspend\[(?P<mode>.*)\]', line)
+				if m and m.group('mode') in ['1', '2', '3', '4']:
+					sv.suspendmode = modes[int(m.group('mode'))]
+					data.stamp['mode'] = sv.suspendmode
+					break
+			fp.close()
 		m = re.match(self.cmdlinefmt, self.cmdline)
 		if m:
 			sv.cmdline = m.group('cmd')
@@ -2413,7 +2391,7 @@ class ProcessMonitor:
 #	 markers, and/or kprobes required for primary parsing.
 def doesTraceLogHaveTraceEvents():
 	kpcheck = ['_cal: (', '_cpu_down()']
-	techeck = sysvals.traceevents[:]
+	techeck = ['suspend_resume']
 	tmcheck = ['SUSPEND START', 'RESUME COMPLETE']
 	sysvals.usekprobes = False
 	fp = sysvals.openlog(sysvals.ftracefile, 'r')
@@ -2808,7 +2786,7 @@ def parseTraceLog(live=False):
 				# -- phase changes --
 				# start of kernel suspend
 				if(re.match('suspend_enter\[.*', t.name)):
-					if(isbegin):
+					if(isbegin and data.start == data.tKernSus):
 						data.dmesg[phase]['start'] = t.time
 						data.tKernSus = t.time
 					continue
@@ -3072,13 +3050,20 @@ def parseTraceLog(live=False):
 					sysvals.vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name))
 					cg.newActionFromFunction(data)
 	if sysvals.suspendmode == 'command':
-		return testdata
+		return (testdata, '')
 
 	# fill in any missing phases
+	error = []
 	for data in testdata:
+		tn = '' if len(testdata) == 1 else ('%d' % (data.testnumber + 1))
+		terr = ''
 		lp = data.phases[0]
 		for p in data.phases:
 			if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0):
+				if not terr:
+					print 'TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp)
+					terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, lp)
+					error.append(terr)
 				sysvals.vprint('WARNING: phase "%s" is missing!' % p)
 			if(data.dmesg[p]['start'] < 0):
 				data.dmesg[p]['start'] = data.dmesg[lp]['end']
@@ -3106,7 +3091,7 @@ def parseTraceLog(live=False):
 			for j in range(i + 1, tc):
 				testdata[j].mergeOverlapDevices(devlist)
 		testdata[0].stitchTouchingThreads(testdata[1:])
-	return testdata
+	return (testdata, ', '.join(error))
 
 # Function: loadKernelLog
 # Description:
@@ -3173,7 +3158,7 @@ def loadKernelLog():
 	if data:
 		testruns.append(data)
 	if len(testruns) < 1:
-		doError(' dmesg log has no suspend/resume data: %s' \
+		print('ERROR: dmesg log has no suspend/resume data: %s' \
 			% sysvals.dmesgfile)
 
 	# fix lines with same timestamp/function with the call and return swapped
@@ -3521,68 +3506,144 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 		.summary {border:1px solid;}\n\
 		th {border: 1px solid black;background:#222;color:white;}\n\
 		td {font: 16px "Times New Roman";text-align: center;}\n\
-		tr.alt td {background:#ddd;}\n\
-		tr.avg td {background:#aaa;}\n\
+		tr.head td {border: 1px solid black;background:#aaa;}\n\
+		tr.alt {background-color:#ddd;}\n\
+		tr.notice {color:red;}\n\
+		.minval {background-color:#BBFFBB;}\n\
+		.medval {background-color:#BBBBFF;}\n\
+		.maxval {background-color:#FFBBBB;}\n\
+		.head a {color:#000;text-decoration: none;}\n\
 	</style>\n</head>\n<body>\n'
 
+	# extract the test data into list
+	list = dict()
+	tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [[], []]
+	iMin, iMed, iMax = [0, 0], [0, 0], [0, 0]
+	num = 0
+	lastmode = ''
+	cnt = {'pass':0, 'fail':0, 'hang':0}
+	for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])):
+		mode = data['mode']
+		if mode not in list:
+			list[mode] = {'data': [], 'avg': [0,0], 'min': [0,0], 'max': [0,0], 'med': [0,0]}
+		if lastmode and lastmode != mode and num > 0:
+			for i in range(2):
+				s = sorted(tMed[i])
+				list[lastmode]['med'][i] = s[int(len(s)/2)]
+				iMed[i] = tMed[i].index(list[lastmode]['med'][i])
+			list[lastmode]['avg'] = [tAvg[0] / num, tAvg[1] / num]
+			list[lastmode]['min'] = tMin
+			list[lastmode]['max'] = tMax
+			list[lastmode]['idx'] = (iMin, iMed, iMax)
+			tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [[], []]
+			iMin, iMed, iMax = [0, 0], [0, 0], [0, 0]
+			num = 0
+		tVal = [float(data['suspend']), float(data['resume'])]
+		list[mode]['data'].append([data['host'], data['kernel'],
+			data['time'], tVal[0], tVal[1], data['url'], data['result'],
+			data['issues']])
+		idx = len(list[mode]['data']) - 1
+		if data['result'] == 'pass':
+			cnt['pass'] += 1
+			for i in range(2):
+				tMed[i].append(tVal[i])
+				tAvg[i] += tVal[i]
+				if tMin[i] == 0 or tVal[i] < tMin[i]:
+					iMin[i] = idx
+					tMin[i] = tVal[i]
+				if tMax[i] == 0 or tVal[i] > tMax[i]:
+					iMax[i] = idx
+					tMax[i] = tVal[i]
+			num += 1
+		elif data['result'] == 'hang':
+			cnt['hang'] += 1
+		elif data['result'] == 'fail':
+			cnt['fail'] += 1
+		lastmode = mode
+	if lastmode and num > 0:
+		for i in range(2):
+			s = sorted(tMed[i])
+			list[lastmode]['med'][i] = s[int(len(s)/2)]
+			iMed[i] = tMed[i].index(list[lastmode]['med'][i])
+		list[lastmode]['avg'] = [tAvg[0] / num, tAvg[1] / num]
+		list[lastmode]['min'] = tMin
+		list[lastmode]['max'] = tMax
+		list[lastmode]['idx'] = (iMin, iMed, iMax)
+
 	# group test header
-	html += '<div class="stamp">%s (%d tests)</div>\n' % (folder, len(testruns))
+	desc = []
+	for ilk in sorted(cnt, reverse=True):
+		if cnt[ilk] > 0:
+			desc.append('%d %s' % (cnt[ilk], ilk))
+	html += '<div class="stamp">%s (%d tests: %s)</div>\n' % (folder, len(testruns), ', '.join(desc))
 	th = '\t<th>{0}</th>\n'
 	td = '\t<td>{0}</td>\n'
+	tdh = '\t<td{1}>{0}</td>\n'
 	tdlink = '\t<td><a href="{0}">html</a></td>\n'
 
 	# table header
 	html += '<table class="summary">\n<tr>\n' + th.format('#') +\
 		th.format('Mode') + th.format('Host') + th.format('Kernel') +\
-		th.format('Test Time') + th.format('Suspend') + th.format('Resume') +\
-		th.format('Detail') + '</tr>\n'
-
-	# test data, 1 row per test
-	avg = '<tr class="avg"><td></td><td></td><td></td><td></td>'+\
-		'<td>Average of {0} {1} tests</td><td>{2}</td><td>{3}</td><td></td></tr>\n'
-	sTimeAvg = rTimeAvg = 0.0
-	mode = ''
-	num = 0
-	for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])):
-		if mode != data['mode']:
-			# test average line
-			if(num > 0):
-				sTimeAvg /= (num - 1)
-				rTimeAvg /= (num - 1)
-				html += avg.format('%d' % (num - 1), mode,
-					'%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
-			sTimeAvg = rTimeAvg = 0.0
-			mode = data['mode']
-			num = 1
-		# alternate row color
-		if num % 2 == 1:
-			html += '<tr class="alt">\n'
+		th.format('Test Time') + th.format('Result') + th.format('Issues') +\
+		th.format('Suspend') + th.format('Resume') + th.format('Detail') + '</tr>\n'
+
+	# export list into html
+	head = '<tr class="head"><td>{0}</td><td>{1}</td>'+\
+		'<td colspan=8 class="sus">Suspend Avg={2} '+\
+		'<span class=minval><a href="#s{10}min">Min={3}</a></span> '+\
+		'<span class=medval><a href="#s{10}med">Med={4}</a></span> '+\
+		'<span class=maxval><a href="#s{10}max">Max={5}</a></span> '+\
+		'Resume Avg={6} '+\
+		'<span class=minval><a href="#r{10}min">Min={7}</a></span> '+\
+		'<span class=medval><a href="#r{10}med">Med={8}</a></span> '+\
+		'<span class=maxval><a href="#r{10}max">Max={9}</a></span></td>'+\
+		'</tr>\n'
+	headnone = '<tr class="head"><td>{0}</td><td>{1}</td><td colspan=8></td></tr>\n'
+	for mode in list:
+		# header line for each suspend mode
+		num = 0
+		tAvg, tMin, tMax, tMed = list[mode]['avg'], list[mode]['min'],\
+			list[mode]['max'], list[mode]['med']
+		count = len(list[mode]['data'])
+		if 'idx' in list[mode]:
+			iMin, iMed, iMax = list[mode]['idx']
+			html += head.format('%d' % count, mode.upper(),
+				'%.3f' % tAvg[0], '%.3f' % tMin[0], '%.3f' % tMed[0], '%.3f' % tMax[0],
+				'%.3f' % tAvg[1], '%.3f' % tMin[1], '%.3f' % tMed[1], '%.3f' % tMax[1],
+				mode.lower()
+			)
 		else:
-			html += '<tr>\n'
-		html += td.format("%d" % num)
-		num += 1
-		# basic info
-		for item in ['mode', 'host', 'kernel', 'time']:
-			val = "unknown"
-			if(item in data):
-				val = data[item]
-			html += td.format(val)
-		# suspend time
-		sTime = float(data['suspend'])
-		sTimeAvg += sTime
-		html += td.format('%.3f ms' % sTime)
-		# resume time
-		rTime = float(data['resume'])
-		rTimeAvg += rTime
-		html += td.format('%.3f ms' % rTime)
-		# link to the output html
-		html += tdlink.format(data['url']) + '</tr>\n'
-	# last test average line
-	if(num > 0):
-		sTimeAvg /= (num - 1)
-		rTimeAvg /= (num - 1)
-		html += avg.format('%d' % (num - 1), mode,
-			'%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
+			iMin = iMed = iMax = [-1, -1, -1]
+			html += headnone.format('%d' % count, mode.upper())
+		for d in list[mode]['data']:
+			# row classes - alternate row color
+			rcls = ['alt'] if num % 2 == 1 else []
+			if d[6] != 'pass':
+				rcls.append('notice')
+			html += '<tr class="'+(' '.join(rcls))+'">\n' if len(rcls) > 0 else '<tr>\n'
+			# figure out if the line has sus or res highlighted
+			idx = list[mode]['data'].index(d)
+			tHigh = ['', '']
+			for i in range(2):
+				tag = 's%s' % mode if i == 0 else 'r%s' % mode
+				if idx == iMin[i]:
+					tHigh[i] = ' id="%smin" class=minval title="Minimum"' % tag
+				elif idx == iMax[i]:
+					tHigh[i] = ' id="%smax" class=maxval title="Maximum"' % tag
+				elif idx == iMed[i]:
+					tHigh[i] = ' id="%smed" class=medval title="Median"' % tag
+			html += td.format("%d" % (list[mode]['data'].index(d) + 1)) # row
+			html += td.format(mode)										# mode
+			html += td.format(d[0])										# host
+			html += td.format(d[1])										# kernel
+			html += td.format(d[2])										# time
+			html += td.format(d[6])										# result
+			html += td.format(d[7])										# issues
+			html += tdh.format('%.3f ms' % d[3], tHigh[0]) if d[3] else td.format('')	# suspend
+			html += tdh.format('%.3f ms' % d[4], tHigh[1]) if d[4] else td.format('')	# resume
+			html += tdlink.format(d[5]) if d[5] else td.format('')		# url
+			html += '</tr>\n'
+			num += 1
 
 	# flush the data to file
 	hf = open(htmlfile, 'w')
@@ -3607,7 +3668,7 @@ def ordinal(value):
 #	 testruns: array of Data objects from parseKernelLog or parseTraceLog
 # Output:
 #	 True if the html file was created, false if it failed
-def createHTML(testruns):
+def createHTML(testruns, testfail):
 	if len(testruns) < 1:
 		print('ERROR: Not enough test data to build a timeline')
 		return
@@ -3641,6 +3702,7 @@ def createHTML(testruns):
 		'<td class="purple">{4}Firmware Resume: {2} ms</td>'\
 		'<td class="yellow" title="time from firmware mode to return from kernel enter_state({5}) [kernel time only]">{4}Kernel Resume: {3} ms</td>'\
 		'</tr>\n</table>\n'
+	html_fail = '<table class="testfail"><tr><td>{0}</td></tr></table>\n'
 
 	# html format variables
 	scaleH = 20
@@ -3708,6 +3770,9 @@ def createHTML(testruns):
 					resume_time, testdesc, stitle, rtitle)
 			devtl.html += thtml
 
+	if testfail:
+		devtl.html += html_fail.format(testfail)
+
 	# time scale for potentially multiple datasets
 	t0 = testruns[0].start
 	tMax = testruns[-1].end
@@ -4006,6 +4071,7 @@ def addCSS(hf, sv, testcount=1, kerror=False, extra=''):
 		.blue {background:rgba(169,208,245,0.4);}\n\
 		.time1 {font:22px Arial;border:1px solid;}\n\
 		.time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
+		.testfail {font:bold 22px Arial;color:red;border:1px dashed;}\n\
 		td {text-align:center;}\n\
 		r {color:#500000;font:15px Tahoma;}\n\
 		n {color:#505050;font:15px Tahoma;}\n\
@@ -4927,6 +4993,25 @@ def dmidecode(mempath, fatal=False):
 		count += 1
 	return out
 
+def getBattery():
+	p = '/sys/class/power_supply'
+	bat = dict()
+	for d in os.listdir(p):
+		type = sysvals.getVal(os.path.join(p, d, 'type')).strip().lower()
+		if type != 'battery':
+			continue
+		for v in ['status', 'energy_now', 'capacity_now']:
+			bat[v] = sysvals.getVal(os.path.join(p, d, v)).strip().lower()
+		break
+	ac = True
+	if 'status' in bat and 'discharging' in bat['status']:
+		ac = False
+	charge = 0
+	for v in ['energy_now', 'capacity_now']:
+		if v in bat and bat[v]:
+			charge = int(bat[v])
+	return (ac, charge)
+
 # Function: getFPDT
 # Description:
 #	 Read the acpi bios tables and pull out FPDT, the firmware data
@@ -5202,8 +5287,9 @@ def getArgFloat(name, args, min, max, main=True):
 
 def processData(live=False):
 	print('PROCESSING DATA')
+	error = ''
 	if(sysvals.usetraceevents):
-		testruns = parseTraceLog(live)
+		testruns, error = parseTraceLog(live)
 		if sysvals.dmesgfile:
 			for data in testruns:
 				data.extractErrorInfo()
@@ -5220,15 +5306,18 @@ def processData(live=False):
 		for data in testruns:
 			data.debugPrint()
 		sys.exit()
-
+	if len(testruns) < 1:
+		return (testruns, {'error': 'timeline generation failed'})
 	sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile)
-	createHTML(testruns)
+	createHTML(testruns, error)
 	print('DONE')
 	data = testruns[0]
 	stamp = data.stamp
 	stamp['suspend'], stamp['resume'] = data.getTimeValues()
 	if data.fwValid:
 		stamp['fwsuspend'], stamp['fwresume'] = data.fwSuspend, data.fwResume
+	if error:
+		stamp['error'] = error
 	return (testruns, stamp)
 
 # Function: rerunTest
@@ -5268,58 +5357,88 @@ def runTest(n=0):
 	sysvals.sudouser(sysvals.testdir)
 	sysvals.outputResult(stamp, n)
 
-def find_in_html(html, strs, div=False):
-	for str in strs:
-		l = len(str)
-		i = html.find(str)
-		if i >= 0:
+def find_in_html(html, start, end, firstonly=True):
+	n, out = 0, []
+	while n < len(html):
+		m = re.search(start, html[n:])
+		if not m:
 			break
-	if i < 0:
-		return ''
-	if not div:
-		return re.search(r'[-+]?\d*\.\d+|\d+', html[i+l:i+l+50]).group()
-	n = html[i+l:].find('</div>')
-	if n < 0:
+		i = m.end()
+		m = re.search(end, html[n+i:])
+		if not m:
+			break
+		j = m.start()
+		str = html[n+i:n+i+j]
+		if end == 'ms':
+			num = re.search(r'[-+]?\d*\.\d+|\d+', str)
+			str = num.group() if num else 'NaN'
+		if firstonly:
+			return str
+		out.append(str)
+		n += i+j
+	if firstonly:
 		return ''
-	return html[i+l:i+l+n]
+	return out
 
 # Function: runSummary
 # Description:
 #	 create a summary of tests in a sub-directory
-def runSummary(subdir, local=True):
+def runSummary(subdir, local=True, genhtml=False):
 	inpath = os.path.abspath(subdir)
 	outpath = inpath
 	if local:
 		outpath = os.path.abspath('.')
 	print('Generating a summary of folder "%s"' % inpath)
+	if genhtml:
+		for dirname, dirnames, filenames in os.walk(subdir):
+			sysvals.dmesgfile = sysvals.ftracefile = sysvals.htmlfile = ''
+			for filename in filenames:
+				if(re.match('.*_dmesg.txt', filename)):
+					sysvals.dmesgfile = os.path.join(dirname, filename)
+				elif(re.match('.*_ftrace.txt', filename)):
+					sysvals.ftracefile = os.path.join(dirname, filename)
+			sysvals.setOutputFile()
+			if sysvals.ftracefile and sysvals.htmlfile and \
+				not os.path.exists(sysvals.htmlfile):
+				print('FTRACE: %s' % sysvals.ftracefile)
+				if sysvals.dmesgfile:
+					print('DMESG : %s' % sysvals.dmesgfile)
+				rerunTest()
 	testruns = []
 	for dirname, dirnames, filenames in os.walk(subdir):
 		for filename in filenames:
 			if(not re.match('.*.html', filename)):
 				continue
 			file = os.path.join(dirname, filename)
-			html = open(file, 'r').read(10000)
-			suspend = find_in_html(html,
-				['Kernel Suspend: ', 'Kernel Suspend Time: '])
-			resume = find_in_html(html,
-				['Kernel Resume: ', 'Kernel Resume Time: '])
-			line = find_in_html(html, ['<div class="stamp">'], True)
+			html = open(file, 'r').read()
+			suspend = find_in_html(html, 'Kernel Suspend', 'ms')
+			resume = find_in_html(html, 'Kernel Resume', 'ms')
+			line = find_in_html(html, '<div class="stamp">', '</div>')
 			stmp = line.split()
-			if not suspend or not resume or len(stmp) < 4:
+			if not suspend or not resume or len(stmp) != 8:
 				continue
+			try:
+				dt = datetime.strptime(' '.join(stmp[3:]), '%B %d %Y, %I:%M:%S %p')
+			except:
+				continue
+			tstr = dt.strftime('%Y/%m/%d %H:%M:%S')
+			error = find_in_html(html, '<table class="testfail"><tr><td>', '</td>')
+			result = 'fail' if error else 'pass'
+			ilist = []
+			e = find_in_html(html, 'class="err"[\w=":;\.%\- ]*>', '&rarr;</div>', False)
+			for i in list(set(e)):
+				ilist.append('%sx%d' % (i, e.count(i)) if e.count(i) > 1 else i)
 			data = {
+				'mode': stmp[2],
 				'host': stmp[0],
 				'kernel': stmp[1],
-				'mode': stmp[2],
-				'time': string.join(stmp[3:], ' '),
+				'time': tstr,
+				'result': result,
+				'issues': ','.join(ilist),
 				'suspend': suspend,
 				'resume': resume,
 				'url': os.path.relpath(file, outpath),
 			}
-			if len(stmp) == 7:
-				data['kernel'] = 'unknown'
-				data['mode'] = stmp[1]
-				data['time'] = string.join(stmp[2:], ' ')
 			testruns.append(data)
 	outfile = os.path.join(outpath, 'summary.html')
 	print('Summary file: %s' % outfile)
@@ -5609,11 +5728,12 @@ def printHelp():
 	print('   -modes       List available suspend modes')
 	print('   -status      Test to see if the system is enabled to run this tool')
 	print('   -fpdt        Print out the contents of the ACPI Firmware Performance Data Table')
+	print('   -battery     Print out battery info (if available)')
 	print('   -sysinfo     Print out system info extracted from BIOS')
 	print('   -devinfo     Print out the pm settings of all devices which support runtime suspend')
 	print('   -flist       Print the list of functions currently being captured in ftrace')
 	print('   -flistall    Print all functions capable of being captured in ftrace')
-	print('   -summary directory  Create a summary of all test in this dir')
+	print('   -summary dir Create a summary of tests in this dir [-genhtml builds missing html]')
 	print('  [redo]')
 	print('   -ftrace ftracefile  Create HTML output using ftrace input (used with -dmesg)')
 	print('   -dmesg dmesgfile    Create HTML output using dmesg (used with -ftrace)')
@@ -5623,8 +5743,9 @@ def printHelp():
 # ----------------- MAIN --------------------
 # exec start (skipped if script is loaded as library)
 if __name__ == '__main__':
+	genhtml = False
 	cmd = ''
-	simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status']
+	simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status', '-battery']
 	if '-f' in sys.argv:
 		sysvals.cgskip = sysvals.configFile('cgskip.txt')
 	# loop through the command line arguments
@@ -5660,6 +5781,8 @@ if __name__ == '__main__':
 			sysvals.skiphtml = True
 		elif(arg == '-cgdump'):
 			sysvals.cgdump = True
+		elif(arg == '-genhtml'):
+			genhtml = True
 		elif(arg == '-addlogs'):
 			sysvals.dmesglog = sysvals.ftracelog = True
 		elif(arg == '-verbose'):
@@ -5856,6 +5979,8 @@ if __name__ == '__main__':
 			statusCheck(True)
 		elif(cmd == 'fpdt'):
 			getFPDT(True)
+		elif(cmd == 'battery'):
+			print 'AC Connect: %s\nCharge: %d' % getBattery()
 		elif(cmd == 'sysinfo'):
 			sysvals.printSystemInfo(True)
 		elif(cmd == 'devinfo'):
@@ -5867,7 +5992,7 @@ if __name__ == '__main__':
 		elif(cmd == 'flistall'):
 			sysvals.getFtraceFilterFunctions(False)
 		elif(cmd == 'summary'):
-			runSummary(sysvals.outdir, True)
+			runSummary(sysvals.outdir, True, genhtml)
 		sys.exit()
 
 	# if instructed, re-analyze existing data files
@@ -5920,7 +6045,7 @@ if __name__ == '__main__':
 			print('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count']))
 			sysvals.logmsg = ''
 		if not sysvals.skiphtml:
-			runSummary(sysvals.outdir, False)
+			runSummary(sysvals.outdir, False, False)
 		sysvals.sudouser(sysvals.outdir)
 	else:
 		if sysvals.outdir:
diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
index 29f50d4cfea0..84e2b648e622 100755
--- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -28,6 +28,7 @@ import subprocess
 import os
 import time
 import re
+import signal
 import sys
 import getopt
 import Gnuplot
@@ -78,11 +79,12 @@ def print_help():
     print('    Or')
     print('      ./intel_pstate_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>')
     print('    To generate trace file, parse and plot, use (sudo required):')
-    print('      sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name>')
+    print('      sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>')
     print('    Or')
-    print('      sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name>')
+    print('      sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>')
     print('    Optional argument:')
-    print('      cpus:  comma separated list of CPUs')
+    print('      cpus:   comma separated list of CPUs')
+    print('      kbytes: Kilo bytes of memory per CPU to allocate to the trace buffer. Default: 10240')
     print('  Output:')
     print('    If not already present, creates a "results/test_name" folder in the current working directory with:')
     print('      cpu.csv - comma seperated values file with trace contents and some additional calculations.')
@@ -379,7 +381,7 @@ def clear_trace_file():
         f_handle.close()
     except:
         print('IO error clearing trace file ')
-        quit()
+        sys.exit(2)
 
 def enable_trace():
     """ Enable trace """
@@ -389,7 +391,7 @@ def enable_trace():
                  , 'w').write("1")
     except:
         print('IO error enabling trace ')
-        quit()
+        sys.exit(2)
 
 def disable_trace():
     """ Disable trace """
@@ -399,17 +401,17 @@ def disable_trace():
                  , 'w').write("0")
     except:
         print('IO error disabling trace ')
-        quit()
+        sys.exit(2)
 
 def set_trace_buffer_size():
     """ Set trace buffer size """
 
     try:
-       open('/sys/kernel/debug/tracing/buffer_size_kb'
-                 , 'w').write("10240")
+       with open('/sys/kernel/debug/tracing/buffer_size_kb', 'w') as fp:
+          fp.write(memory)
     except:
-        print('IO error setting trace buffer size ')
-        quit()
+       print('IO error setting trace buffer size ')
+       sys.exit(2)
 
 def free_trace_buffer():
     """ Free the trace buffer memory """
@@ -418,8 +420,8 @@ def free_trace_buffer():
        open('/sys/kernel/debug/tracing/buffer_size_kb'
                  , 'w').write("1")
     except:
-        print('IO error setting trace buffer size ')
-        quit()
+        print('IO error freeing trace buffer ')
+        sys.exit(2)
 
 def read_trace_data(filename):
     """ Read and parse trace data """
@@ -431,7 +433,7 @@ def read_trace_data(filename):
         data = open(filename, 'r').read()
     except:
         print('Error opening ', filename)
-        quit()
+        sys.exit(2)
 
     for line in data.splitlines():
         search_obj = \
@@ -489,10 +491,22 @@ def read_trace_data(filename):
 # Now seperate the main overall csv file into per CPU csv files.
     split_csv()
 
+def signal_handler(signal, frame):
+    print(' SIGINT: Forcing cleanup before exit.')
+    if interval:
+        disable_trace()
+        clear_trace_file()
+        # Free the memory
+        free_trace_buffer()
+        sys.exit(0)
+
+signal.signal(signal.SIGINT, signal_handler)
+
 interval = ""
 filename = ""
 cpu_list = ""
 testname = ""
+memory = "10240"
 graph_data_present = False;
 
 valid1 = False
@@ -501,7 +515,7 @@ valid2 = False
 cpu_mask = zeros((MAX_CPUS,), dtype=int)
 
 try:
-    opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:",["help","trace_file=","interval=","cpu=","name="])
+    opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="])
 except getopt.GetoptError:
     print_help()
     sys.exit(2)
@@ -521,6 +535,8 @@ for opt, arg in opts:
     elif opt in ("-n", "--name"):
         valid2 = True
         testname = arg
+    elif opt in ("-m", "--memory"):
+        memory = arg
 
 if not (valid1 and valid2):
     print_help()
@@ -569,6 +585,11 @@ current_max_cpu = 0
 
 read_trace_data(filename)
 
+clear_trace_file()
+# Free the memory
+if interval:
+    free_trace_buffer()
+
 if graph_data_present == False:
     print('No valid data to plot')
     sys.exit(2)
@@ -593,9 +614,4 @@ for root, dirs, files in os.walk('.'):
     for f in files:
         fix_ownership(f)
 
-clear_trace_file()
-# Free the memory
-if interval:
-    free_trace_buffer()
-
 os.chdir('../../')
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index a9bc914a8fe8..2ab25aa38263 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -25,4 +25,4 @@ install : turbostat
 	install -d  $(DESTDIR)$(PREFIX)/bin
 	install $(BUILD_OUTPUT)/turbostat $(DESTDIR)$(PREFIX)/bin/turbostat
 	install -d  $(DESTDIR)$(PREFIX)/share/man/man8
-	install turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8
+	install -m 644 turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index ccf2a69365cc..ca9ef7017624 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -54,9 +54,12 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed.  Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed.  Otherwise, the system summary plus the specified set of CPUs are printed.  The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44
 .PP
-\fB--hide column\fP do not show the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
+\fB--hide column\fP do not show the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
 .PP
-\fB--show column\fP show only the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
+\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default.  Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds".
+The column name "all" can be used to enable all disabled-by-default built-in counters.
+.PP
+\fB--show column\fP show only the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
 .PP
 \fB--Dump\fP displays the raw counter values.
 .PP
@@ -64,6 +67,8 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--interval seconds\fP overrides the default 5.0 second measurement interval.
 .PP
+\fB--num_iterations num\fP number of the measurement iterations.
+.PP
 \fB--out output_file\fP turbostat output is written to the specified output_file.
 The file is truncated if it already exists, and it is created if it does not exist.
 .PP
@@ -86,6 +91,8 @@ displays the statistics gathered since it was forked.
 The system configuration dump (if --quiet is not used) is followed by statistics.  The first row of the statistics labels the content of each column (below).  The second row of statistics is the system summary line.  The system summary line has a '-' in the columns for the Package, Core, and CPU.  The contents of the system summary line depends on the type of column.  Columns that count items (eg. IRQ) show the sum across all CPUs in the system.  Columns that show a percentage show the average across all CPUs in the system.  Columns that dump raw MSR values simply show 0 in the summary.  After the system summary row, each row describes a specific Package/Core/CPU.  Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system.
 .SH COLUMN DESCRIPTIONS
 .nf
+\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any.  This counter is disabled by default, and is enabled with "--enable usec", or --debug.  On the summary row, usec refers to the total elapsed time to collect the counters on all cpus.
+\fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected.  This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug".  On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU.
 \fBCore\fP processor core number.  Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT).
 \fBCPU\fP Linux CPU (logical processor) number.  Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together.
 \fBPackage\fP processor package number -- not present on systems with a single processor package.
@@ -262,6 +269,21 @@ CPU	  PRF_CTRL
 
 .fi
 
+.SH INPUT
+
+For interval-mode, turbostat will immediately end the current interval
+when it sees a newline on standard input.
+turbostat will then start the next interval.
+Control-C will be send a SIGINT to turbostat,
+which will immediately abort the program with no further processing.
+.SH SIGNALS
+
+SIGINT will interrupt interval-mode.
+The end-of-interval data will be collected and displayed before turbostat exits.
+
+SIGUSR1 will end current interval,
+end-of-interval data will be collected and displayed before turbostat
+starts a new interval.
 .SH NOTES
 
 .B "turbostat "
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bd9c6b31a504..d6cff3070ebd 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -29,6 +29,7 @@
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <sys/stat.h>
+#include <sys/select.h>
 #include <sys/resource.h>
 #include <fcntl.h>
 #include <signal.h>
@@ -47,9 +48,13 @@
 char *proc_stat = "/proc/stat";
 FILE *outf;
 int *fd_percpu;
+struct timeval interval_tv = {5, 0};
 struct timespec interval_ts = {5, 0};
+struct timespec one_msec = {0, 1000000};
+unsigned int num_iterations;
 unsigned int debug;
 unsigned int quiet;
+unsigned int shown;
 unsigned int sums_need_wide_columns;
 unsigned int rapl_joules;
 unsigned int summary_only;
@@ -58,6 +63,7 @@ unsigned int dump_only;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
 unsigned int do_slm_cstates;
+unsigned int do_cnl_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
@@ -80,6 +86,8 @@ unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
 unsigned long long  gfx_cur_rc6_ms;
+unsigned long long cpuidle_cur_cpu_lpi_us;
+unsigned long long cpuidle_cur_sys_lpi_us;
 unsigned int gfx_cur_mhz;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
@@ -87,6 +95,7 @@ double rapl_power_units, rapl_time_units;
 double rapl_dram_energy_units, rapl_energy_units;
 double rapl_joule_counter_range;
 unsigned int do_core_perf_limit_reasons;
+unsigned int has_automatic_cstate_conversion;
 unsigned int do_gfx_perf_limit_reasons;
 unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
@@ -147,7 +156,9 @@ char *progname;
 #define CPU_SUBSET_MAXCPUS	1024	/* need to use before probe... */
 cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset;
 size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size;
-#define MAX_ADDED_COUNTERS 16
+#define MAX_ADDED_COUNTERS 8
+#define MAX_ADDED_THREAD_COUNTERS 24
+#define BITMASK_SIZE 32
 
 struct thread_data {
 	struct timeval tv_begin;
@@ -162,7 +173,7 @@ struct thread_data {
 	unsigned int flags;
 #define CPU_IS_FIRST_THREAD_IN_CORE	0x2
 #define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
-	unsigned long long counter[MAX_ADDED_COUNTERS];
+	unsigned long long counter[MAX_ADDED_THREAD_COUNTERS];
 } *thread_even, *thread_odd;
 
 struct core_data {
@@ -183,6 +194,8 @@ struct pkg_data {
 	unsigned long long pc8;
 	unsigned long long pc9;
 	unsigned long long pc10;
+	unsigned long long cpu_lpi;
+	unsigned long long sys_lpi;
 	unsigned long long pkg_wtd_core_c0;
 	unsigned long long pkg_any_core_c0;
 	unsigned long long pkg_any_gfxe_c0;
@@ -203,12 +216,21 @@ struct pkg_data {
 #define ODD_COUNTERS thread_odd, core_odd, package_odd
 #define EVEN_COUNTERS thread_even, core_even, package_even
 
-#define GET_THREAD(thread_base, thread_no, core_no, pkg_no) \
-	(thread_base + (pkg_no) * topo.num_cores_per_pkg * \
-		topo.num_threads_per_core + \
-		(core_no) * topo.num_threads_per_core + (thread_no))
-#define GET_CORE(core_base, core_no, pkg_no) \
-	(core_base + (pkg_no) * topo.num_cores_per_pkg + (core_no))
+#define GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no)	      \
+	((thread_base) +						      \
+	 ((pkg_no) *							      \
+	  topo.nodes_per_pkg * topo.cores_per_node * topo.threads_per_core) + \
+	 ((node_no) * topo.cores_per_node * topo.threads_per_core) +	      \
+	 ((core_no) * topo.threads_per_core) +				      \
+	 (thread_no))
+
+#define GET_CORE(core_base, core_no, node_no, pkg_no)			\
+	((core_base) +							\
+	 ((pkg_no) *  topo.nodes_per_pkg * topo.cores_per_node) +	\
+	 ((node_no) * topo.cores_per_node) +				\
+	 (core_no))
+
+
 #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
 
 enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE};
@@ -244,14 +266,25 @@ struct system_summary {
 	struct pkg_data packages;
 } average;
 
+struct cpu_topology {
+	int physical_package_id;
+	int logical_cpu_id;
+	int physical_node_id;
+	int logical_node_id;	/* 0-based count within the package */
+	int physical_core_id;
+	int thread_id;
+	cpu_set_t *put_ids; /* Processing Unit/Thread IDs */
+} *cpus;
 
 struct topo_params {
 	int num_packages;
 	int num_cpus;
 	int num_cores;
 	int max_cpu_num;
-	int num_cores_per_pkg;
-	int num_threads_per_core;
+	int max_node_num;
+	int nodes_per_pkg;
+	int cores_per_node;
+	int threads_per_core;
 } topo;
 
 struct timeval tv_even, tv_odd, tv_delta;
@@ -273,27 +306,33 @@ int cpu_is_not_present(int cpu)
 int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg_data *),
 	struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base)
 {
-	int retval, pkg_no, core_no, thread_no;
+	int retval, pkg_no, core_no, thread_no, node_no;
 
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
-		for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
-			for (thread_no = 0; thread_no <
-				topo.num_threads_per_core; ++thread_no) {
-				struct thread_data *t;
-				struct core_data *c;
-				struct pkg_data *p;
-
-				t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
-
-				if (cpu_is_not_present(t->cpu_id))
-					continue;
-
-				c = GET_CORE(core_base, core_no, pkg_no);
-				p = GET_PKG(pkg_base, pkg_no);
-
-				retval = func(t, c, p);
-				if (retval)
-					return retval;
+		for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
+			for (node_no = 0; node_no < topo.nodes_per_pkg;
+			     node_no++) {
+				for (thread_no = 0; thread_no <
+					topo.threads_per_core; ++thread_no) {
+					struct thread_data *t;
+					struct core_data *c;
+					struct pkg_data *p;
+
+					t = GET_THREAD(thread_base, thread_no,
+						       core_no, node_no,
+						       pkg_no);
+
+					if (cpu_is_not_present(t->cpu_id))
+						continue;
+
+					c = GET_CORE(core_base, core_no,
+						     node_no, pkg_no);
+					p = GET_PKG(pkg_base, pkg_no);
+
+					retval = func(t, c, p);
+					if (retval)
+						return retval;
+				}
 			}
 		}
 	}
@@ -346,6 +385,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
  * Thus, strings that are proper sub-sets must follow their more specific peers.
  */
 struct msr_counter bic[] = {
+	{ 0x0, "usec" },
+	{ 0x0, "Time_Of_Day_Seconds" },
 	{ 0x0, "Package" },
 	{ 0x0, "Avg_MHz" },
 	{ 0x0, "Bzy_MHz" },
@@ -369,7 +410,9 @@ struct msr_counter bic[] = {
 	{ 0x0, "Pkg%pc7" },
 	{ 0x0, "Pkg%pc8" },
 	{ 0x0, "Pkg%pc9" },
-	{ 0x0, "Pkg%pc10" },
+	{ 0x0, "Pk%pc10" },
+	{ 0x0, "CPU%LPI" },
+	{ 0x0, "SYS%LPI" },
 	{ 0x0, "PkgWatt" },
 	{ 0x0, "CorWatt" },
 	{ 0x0, "GFXWatt" },
@@ -389,62 +432,72 @@ struct msr_counter bic[] = {
 	{ 0x0, "Any%C0" },
 	{ 0x0, "GFX%C0" },
 	{ 0x0, "CPUGFX%" },
+	{ 0x0, "Node%" },
 };
 
 
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
-#define	BIC_Package	(1ULL << 0)
-#define	BIC_Avg_MHz	(1ULL << 1)
-#define	BIC_Bzy_MHz	(1ULL << 2)
-#define	BIC_TSC_MHz	(1ULL << 3)
-#define	BIC_IRQ		(1ULL << 4)
-#define	BIC_SMI		(1ULL << 5)
-#define	BIC_Busy	(1ULL << 6)
-#define	BIC_CPU_c1	(1ULL << 7)
-#define	BIC_CPU_c3	(1ULL << 8)
-#define	BIC_CPU_c6	(1ULL << 9)
-#define	BIC_CPU_c7	(1ULL << 10)
-#define	BIC_ThreadC	(1ULL << 11)
-#define	BIC_CoreTmp	(1ULL << 12)
-#define	BIC_CoreCnt	(1ULL << 13)
-#define	BIC_PkgTmp	(1ULL << 14)
-#define	BIC_GFX_rc6	(1ULL << 15)
-#define	BIC_GFXMHz	(1ULL << 16)
-#define	BIC_Pkgpc2	(1ULL << 17)
-#define	BIC_Pkgpc3	(1ULL << 18)
-#define	BIC_Pkgpc6	(1ULL << 19)
-#define	BIC_Pkgpc7	(1ULL << 20)
-#define	BIC_Pkgpc8	(1ULL << 21)
-#define	BIC_Pkgpc9	(1ULL << 22)
-#define	BIC_Pkgpc10	(1ULL << 23)
-#define	BIC_PkgWatt	(1ULL << 24)
-#define	BIC_CorWatt	(1ULL << 25)
-#define	BIC_GFXWatt	(1ULL << 26)
-#define	BIC_PkgCnt	(1ULL << 27)
-#define	BIC_RAMWatt	(1ULL << 28)
-#define	BIC_PKG__	(1ULL << 29)
-#define	BIC_RAM__	(1ULL << 30)
-#define	BIC_Pkg_J	(1ULL << 31)
-#define	BIC_Cor_J	(1ULL << 32)
-#define	BIC_GFX_J	(1ULL << 33)
-#define	BIC_RAM_J	(1ULL << 34)
-#define	BIC_Core	(1ULL << 35)
-#define	BIC_CPU		(1ULL << 36)
-#define	BIC_Mod_c6	(1ULL << 37)
-#define	BIC_sysfs	(1ULL << 38)
-#define	BIC_Totl_c0	(1ULL << 39)
-#define	BIC_Any_c0	(1ULL << 40)
-#define	BIC_GFX_c0	(1ULL << 41)
-#define	BIC_CPUGFX	(1ULL << 42)
-
-unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL;
-unsigned long long bic_present = BIC_sysfs;
+#define	BIC_USEC	(1ULL << 0)
+#define	BIC_TOD		(1ULL << 1)
+#define	BIC_Package	(1ULL << 2)
+#define	BIC_Avg_MHz	(1ULL << 3)
+#define	BIC_Bzy_MHz	(1ULL << 4)
+#define	BIC_TSC_MHz	(1ULL << 5)
+#define	BIC_IRQ		(1ULL << 6)
+#define	BIC_SMI		(1ULL << 7)
+#define	BIC_Busy	(1ULL << 8)
+#define	BIC_CPU_c1	(1ULL << 9)
+#define	BIC_CPU_c3	(1ULL << 10)
+#define	BIC_CPU_c6	(1ULL << 11)
+#define	BIC_CPU_c7	(1ULL << 12)
+#define	BIC_ThreadC	(1ULL << 13)
+#define	BIC_CoreTmp	(1ULL << 14)
+#define	BIC_CoreCnt	(1ULL << 15)
+#define	BIC_PkgTmp	(1ULL << 16)
+#define	BIC_GFX_rc6	(1ULL << 17)
+#define	BIC_GFXMHz	(1ULL << 18)
+#define	BIC_Pkgpc2	(1ULL << 19)
+#define	BIC_Pkgpc3	(1ULL << 20)
+#define	BIC_Pkgpc6	(1ULL << 21)
+#define	BIC_Pkgpc7	(1ULL << 22)
+#define	BIC_Pkgpc8	(1ULL << 23)
+#define	BIC_Pkgpc9	(1ULL << 24)
+#define	BIC_Pkgpc10	(1ULL << 25)
+#define BIC_CPU_LPI	(1ULL << 26)
+#define BIC_SYS_LPI	(1ULL << 27)
+#define	BIC_PkgWatt	(1ULL << 26)
+#define	BIC_CorWatt	(1ULL << 27)
+#define	BIC_GFXWatt	(1ULL << 28)
+#define	BIC_PkgCnt	(1ULL << 29)
+#define	BIC_RAMWatt	(1ULL << 30)
+#define	BIC_PKG__	(1ULL << 31)
+#define	BIC_RAM__	(1ULL << 32)
+#define	BIC_Pkg_J	(1ULL << 33)
+#define	BIC_Cor_J	(1ULL << 34)
+#define	BIC_GFX_J	(1ULL << 35)
+#define	BIC_RAM_J	(1ULL << 36)
+#define	BIC_Core	(1ULL << 37)
+#define	BIC_CPU		(1ULL << 38)
+#define	BIC_Mod_c6	(1ULL << 39)
+#define	BIC_sysfs	(1ULL << 40)
+#define	BIC_Totl_c0	(1ULL << 41)
+#define	BIC_Any_c0	(1ULL << 42)
+#define	BIC_GFX_c0	(1ULL << 43)
+#define	BIC_CPUGFX	(1ULL << 44)
+#define	BIC_Node	(1ULL << 45)
+
+#define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD)
+
+unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
+unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs;
 
 #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
+#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
 #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
 #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
 
+
 #define MAX_DEFERRED 16
 char *deferred_skip_names[MAX_DEFERRED];
 int deferred_skip_index;
@@ -469,9 +522,10 @@ void help(void)
 	"--cpu	cpu-set	limit output to summary plus cpu-set:\n"
 	"		{core | package | j,k,l..m,n-p }\n"
 	"--quiet	skip decoding system configuration header\n"
-	"--interval sec	Override default 5-second measurement interval\n"
+	"--interval sec.subsec	Override default 5-second measurement interval\n"
 	"--help		print this help message\n"
 	"--list		list column headers only\n"
+	"--num_iterations num   number of the measurement iterations\n"
 	"--out file	create or truncate \"file\" for all output\n"
 	"--version	print version information\n"
 	"\n"
@@ -496,6 +550,9 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode)
 		if (comma)
 			*comma = '\0';
 
+		if (!strcmp(name_list, "all"))
+			return ~0;
+
 		for (i = 0; i < MAX_BIC; ++i) {
 			if (!strcmp(name_list, bic[i].name)) {
 				retval |= (1ULL << i);
@@ -532,10 +589,14 @@ void print_header(char *delim)
 	struct msr_counter *mp;
 	int printed = 0;
 
-	if (debug)
-		outp += sprintf(outp, "usec %s", delim);
+	if (DO_BIC(BIC_USEC))
+		outp += sprintf(outp, "%susec", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_TOD))
+		outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Package))
 		outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_Node))
+		outp += sprintf(outp, "%sNode", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Core))
 		outp += sprintf(outp, "%sCore", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU))
@@ -576,7 +637,7 @@ void print_header(char *delim)
 
 	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
+	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
 		outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
@@ -635,6 +696,10 @@ void print_header(char *delim)
 		outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Pkgpc10))
 		outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_CPU_LPI))
+		outp += sprintf(outp, "%sCPU%%LPI", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_SYS_LPI))
+		outp += sprintf(outp, "%sSYS%%LPI", (printed++ ? delim : ""));
 
 	if (do_rapl && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
@@ -739,6 +804,9 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
 		outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
 		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
+		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
+		outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
+		outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
 		outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
 		outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
 		outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
@@ -786,7 +854,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		(cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset)))
 		return 0;
 
-	if (debug) {
+	if (DO_BIC(BIC_USEC)) {
 		/* on each row, print how many usec each timestamp took to gather */
 		struct timeval tv;
 
@@ -794,6 +862,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "%5ld\t", tv.tv_sec * 1000000 + tv.tv_usec);
 	}
 
+	/* Time_Of_Day_Seconds: on each row, print sec.usec last timestamp taken */
+	if (DO_BIC(BIC_TOD))
+		outp += sprintf(outp, "%10ld.%06ld\t", t->tv_end.tv_sec, t->tv_end.tv_usec);
+
 	interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
 
 	tsc = t->tsc * tsc_tweak;
@@ -802,6 +874,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (t == &average.threads) {
 		if (DO_BIC(BIC_Package))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		if (DO_BIC(BIC_Node))
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Core))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_CPU))
@@ -813,6 +887,15 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		}
+		if (DO_BIC(BIC_Node)) {
+			if (t)
+				outp += sprintf(outp, "%s%d",
+						(printed++ ? delim : ""),
+					      cpus[t->cpu_id].physical_node_id);
+			else
+				outp += sprintf(outp, "%s-",
+						(printed++ ? delim : ""));
+		}
 		if (DO_BIC(BIC_Core)) {
 			if (c)
 				outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_id);
@@ -882,7 +965,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
+	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
@@ -959,6 +1042,11 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_Pkgpc10))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10/tsc);
 
+	if (DO_BIC(BIC_CPU_LPI))
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
+	if (DO_BIC(BIC_SYS_LPI))
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+
 	/*
  	 * If measurement interval exceeds minimum RAPL Joule Counter range,
  	 * indicate that results are suspect by printing "**" in fraction place.
@@ -1006,7 +1094,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	}
 
 done:
-	outp += sprintf(outp, "\n");
+	if (*(outp - 1) != '\n')
+		outp += sprintf(outp, "\n");
 
 	return 0;
 }
@@ -1083,6 +1172,8 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
 	old->pc8 = new->pc8 - old->pc8;
 	old->pc9 = new->pc9 - old->pc9;
 	old->pc10 = new->pc10 - old->pc10;
+	old->cpu_lpi = new->cpu_lpi - old->cpu_lpi;
+	old->sys_lpi = new->sys_lpi - old->sys_lpi;
 	old->pkg_temp_c = new->pkg_temp_c;
 
 	/* flag an error when rc6 counter resets/wraps */
@@ -1140,6 +1231,15 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	int i;
 	struct msr_counter *mp;
 
+	/*
+	 * the timestamps from start of measurement interval are in "old"
+	 * the timestamp from end of measurement interval are in "new"
+	 * over-write old w/ new so we can print end of interval values
+	 */
+
+	old->tv_begin = new->tv_begin;
+	old->tv_end = new->tv_end;
+
 	old->tsc = new->tsc - old->tsc;
 
 	/* check for TSC < 1 Mcycles over interval */
@@ -1228,6 +1328,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	int i;
 	struct msr_counter  *mp;
 
+	t->tv_begin.tv_sec = 0;
+	t->tv_begin.tv_usec = 0;
+	t->tv_end.tv_sec = 0;
+	t->tv_end.tv_usec = 0;
+
 	t->tsc = 0;
 	t->aperf = 0;
 	t->mperf = 0;
@@ -1260,6 +1365,8 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	p->pc8 = 0;
 	p->pc9 = 0;
 	p->pc10 = 0;
+	p->cpu_lpi = 0;
+	p->sys_lpi = 0;
 
 	p->energy_pkg = 0;
 	p->energy_dram = 0;
@@ -1286,6 +1393,13 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	int i;
 	struct msr_counter *mp;
 
+	/* remember first tv_begin */
+	if (average.threads.tv_begin.tv_sec == 0)
+		average.threads.tv_begin = t->tv_begin;
+
+	/* remember last tv_end */
+	average.threads.tv_end = t->tv_end;
+
 	average.threads.tsc += t->tsc;
 	average.threads.aperf += t->aperf;
 	average.threads.mperf += t->mperf;
@@ -1341,6 +1455,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	average.packages.pc9 += p->pc9;
 	average.packages.pc10 += p->pc10;
 
+	average.packages.cpu_lpi = p->cpu_lpi;
+	average.packages.sys_lpi = p->sys_lpi;
+
 	average.packages.energy_pkg += p->energy_pkg;
 	average.packages.energy_dram += p->energy_dram;
 	average.packages.energy_cores += p->energy_cores;
@@ -1487,7 +1604,7 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
 		if (get_msr(cpu, mp->msr_num, counterp))
 			return -1;
 	} else {
-		char path[128];
+		char path[128 + PATH_BYTES];
 
 		if (mp->flags & SYSFS_PERCPU) {
 			sprintf(path, "/sys/devices/system/cpu/cpu%d/%s",
@@ -1603,7 +1720,7 @@ retry:
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) {
+	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) {
 		if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
 			return -6;
 	}
@@ -1684,6 +1801,11 @@ retry:
 		if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10))
 			return -13;
 
+	if (DO_BIC(BIC_CPU_LPI))
+		p->cpu_lpi = cpuidle_cur_cpu_lpi_us;
+	if (DO_BIC(BIC_SYS_LPI))
+		p->sys_lpi = cpuidle_cur_sys_lpi_us;
+
 	if (do_rapl & RAPL_PKG) {
 		if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
 			return -13;
@@ -1769,7 +1891,7 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV,
 int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
-int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 
 
 static void
@@ -2071,12 +2193,9 @@ dump_nhm_cst_cfg(void)
 
 	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
 
-#define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
-
 	fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr);
 
-	fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
+	fprintf(outf, " (%s%s%s%s%slocked, pkg-cstate-limit=%d (%s)",
 		(msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
 		(msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
 		(msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
@@ -2084,6 +2203,15 @@ dump_nhm_cst_cfg(void)
 		(msr & (1 << 15)) ? "" : "UN",
 		(unsigned int)msr & 0xF,
 		pkg_cstate_limit_strings[pkg_cstate_limit]);
+
+#define AUTOMATIC_CSTATE_CONVERSION		(1UL << 16)
+	if (has_automatic_cstate_conversion) {
+		fprintf(outf, ", automatic c-state conversion=%s",
+			(msr & AUTOMATIC_CSTATE_CONVERSION) ? "on" : "off");
+	}
+
+	fprintf(outf, ")\n");
+
 	return;
 }
 
@@ -2184,6 +2312,8 @@ void free_fd_percpu(void)
 
 void free_all_buffers(void)
 {
+	int i;
+
 	CPU_FREE(cpu_present_set);
 	cpu_present_set = NULL;
 	cpu_present_setsize = 0;
@@ -2216,6 +2346,12 @@ void free_all_buffers(void)
 
 	free(irq_column_2_cpu);
 	free(irqs_per_cpu);
+
+	for (i = 0; i <= topo.max_cpu_num; ++i) {
+		if (cpus[i].put_ids)
+			CPU_FREE(cpus[i].put_ids);
+	}
+	free(cpus);
 }
 
 
@@ -2240,44 +2376,6 @@ int parse_int_file(const char *fmt, ...)
 }
 
 /*
- * get_cpu_position_in_core(cpu)
- * return the position of the CPU among its HT siblings in the core
- * return -1 if the sibling is not in list
- */
-int get_cpu_position_in_core(int cpu)
-{
-	char path[64];
-	FILE *filep;
-	int this_cpu;
-	char character;
-	int i;
-
-	sprintf(path,
-		"/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list",
-		cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-
-	for (i = 0; i < topo.num_threads_per_core; i++) {
-		fscanf(filep, "%d", &this_cpu);
-		if (this_cpu == cpu) {
-			fclose(filep);
-			return i;
-		}
-
-		/* Account for no separator after last thread*/
-		if (i != (topo.num_threads_per_core - 1))
-			fscanf(filep, "%c", &character);
-	}
-
-	fclose(filep);
-	return -1;
-}
-
-/*
  * cpu_is_first_core_in_package(cpu)
  * return 1 if given CPU is 1st core in package
  */
@@ -2296,35 +2394,115 @@ int get_core_id(int cpu)
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
 }
 
-int get_num_ht_siblings(int cpu)
+void set_node_data(void)
 {
 	char path[80];
 	FILE *filep;
-	int sib1;
-	int matches = 0;
-	char character;
-	char str[100];
-	char *ch;
+	int pkg, node, cpu;
 
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
-	filep = fopen_or_die(path, "r");
+	struct pkg_node_info {
+		int count;
+		int min;
+	} *pni;
 
-	/*
-	 * file format:
-	 * A ',' separated or '-' separated set of numbers
-	 * (eg 1-2 or 1,3,4,5)
-	 */
-	fscanf(filep, "%d%c\n", &sib1, &character);
-	fseek(filep, 0, SEEK_SET);
-	fgets(str, 100, filep);
-	ch = strchr(str, character);
-	while (ch != NULL) {
-		matches++;
-		ch = strchr(ch+1, character);
+	pni = calloc(topo.num_packages, sizeof(struct pkg_node_info));
+	if (!pni)
+		err(1, "calloc pkg_node_count");
+
+	for (pkg = 0; pkg < topo.num_packages; pkg++)
+		pni[pkg].min = topo.num_cpus;
+
+	for (node = 0; node <= topo.max_node_num; node++) {
+		/* find the "first" cpu in the node */
+		sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node);
+		filep = fopen(path, "r");
+		if (!filep)
+			continue;
+		fscanf(filep, "%d", &cpu);
+		fclose(filep);
+
+		pkg = cpus[cpu].physical_package_id;
+		pni[pkg].count++;
+
+		if (node < pni[pkg].min)
+			pni[pkg].min = node;
 	}
 
+	for (pkg = 0; pkg < topo.num_packages; pkg++)
+		if (pni[pkg].count > topo.nodes_per_pkg)
+			topo.nodes_per_pkg = pni[0].count;
+
+	for (cpu = 0; cpu < topo.num_cpus; cpu++) {
+		pkg = cpus[cpu].physical_package_id;
+		node = cpus[cpu].physical_node_id;
+		cpus[cpu].logical_node_id = node - pni[pkg].min;
+	}
+	free(pni);
+
+}
+
+int get_physical_node_id(struct cpu_topology *thiscpu)
+{
+	char path[80];
+	FILE *filep;
+	int i;
+	int cpu = thiscpu->logical_cpu_id;
+
+	for (i = 0; i <= topo.max_cpu_num; i++) {
+		sprintf(path, "/sys/devices/system/cpu/cpu%d/node%i/cpulist",
+			cpu, i);
+		filep = fopen(path, "r");
+		if (!filep)
+			continue;
+		fclose(filep);
+		return i;
+	}
+	return -1;
+}
+
+int get_thread_siblings(struct cpu_topology *thiscpu)
+{
+	char path[80], character;
+	FILE *filep;
+	unsigned long map;
+	int so, shift, sib_core;
+	int cpu = thiscpu->logical_cpu_id;
+	int offset = topo.max_cpu_num + 1;
+	size_t size;
+	int thread_id = 0;
+
+	thiscpu->put_ids = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (thiscpu->thread_id < 0)
+		thiscpu->thread_id = thread_id++;
+	if (!thiscpu->put_ids)
+		return -1;
+
+	size = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(size, thiscpu->put_ids);
+
+	sprintf(path,
+		"/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
+	filep = fopen_or_die(path, "r");
+	do {
+		offset -= BITMASK_SIZE;
+		fscanf(filep, "%lx%c", &map, &character);
+		for (shift = 0; shift < BITMASK_SIZE; shift++) {
+			if ((map >> shift) & 0x1) {
+				so = shift + offset;
+				sib_core = get_core_id(so);
+				if (sib_core == thiscpu->physical_core_id) {
+					CPU_SET_S(so, size, thiscpu->put_ids);
+					if ((so != cpu) &&
+					    (cpus[so].thread_id < 0))
+						cpus[so].thread_id =
+								    thread_id++;
+				}
+			}
+		}
+	} while (!strncmp(&character, ",", 1));
 	fclose(filep);
-	return matches+1;
+
+	return CPU_COUNT_S(size, thiscpu->put_ids);
 }
 
 /*
@@ -2339,32 +2517,42 @@ int for_all_cpus_2(int (func)(struct thread_data *, struct core_data *,
 	struct thread_data *thread_base2, struct core_data *core_base2,
 	struct pkg_data *pkg_base2)
 {
-	int retval, pkg_no, core_no, thread_no;
+	int retval, pkg_no, node_no, core_no, thread_no;
 
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
-		for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
-			for (thread_no = 0; thread_no <
-				topo.num_threads_per_core; ++thread_no) {
-				struct thread_data *t, *t2;
-				struct core_data *c, *c2;
-				struct pkg_data *p, *p2;
-
-				t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
-
-				if (cpu_is_not_present(t->cpu_id))
-					continue;
-
-				t2 = GET_THREAD(thread_base2, thread_no, core_no, pkg_no);
-
-				c = GET_CORE(core_base, core_no, pkg_no);
-				c2 = GET_CORE(core_base2, core_no, pkg_no);
-
-				p = GET_PKG(pkg_base, pkg_no);
-				p2 = GET_PKG(pkg_base2, pkg_no);
-
-				retval = func(t, c, p, t2, c2, p2);
-				if (retval)
-					return retval;
+		for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) {
+			for (core_no = 0; core_no < topo.cores_per_node;
+			     ++core_no) {
+				for (thread_no = 0; thread_no <
+					topo.threads_per_core; ++thread_no) {
+					struct thread_data *t, *t2;
+					struct core_data *c, *c2;
+					struct pkg_data *p, *p2;
+
+					t = GET_THREAD(thread_base, thread_no,
+						       core_no, node_no,
+						       pkg_no);
+
+					if (cpu_is_not_present(t->cpu_id))
+						continue;
+
+					t2 = GET_THREAD(thread_base2, thread_no,
+							core_no, node_no,
+							pkg_no);
+
+					c = GET_CORE(core_base, core_no,
+						     node_no, pkg_no);
+					c2 = GET_CORE(core_base2, core_no,
+						      node_no,
+						      pkg_no);
+
+					p = GET_PKG(pkg_base, pkg_no);
+					p2 = GET_PKG(pkg_base2, pkg_no);
+
+					retval = func(t, c, p, t2, c2, p2);
+					if (retval)
+						return retval;
+				}
 			}
 		}
 	}
@@ -2409,6 +2597,20 @@ void re_initialize(void)
 	printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
 }
 
+void set_max_cpu_num(void)
+{
+	FILE *filep;
+	unsigned long dummy;
+
+	topo.max_cpu_num = 0;
+	filep = fopen_or_die(
+			"/sys/devices/system/cpu/cpu0/topology/thread_siblings",
+			"r");
+	while (fscanf(filep, "%lx,", &dummy) == 1)
+		topo.max_cpu_num += BITMASK_SIZE;
+	fclose(filep);
+	topo.max_cpu_num--; /* 0 based */
+}
 
 /*
  * count_cpus()
@@ -2416,10 +2618,7 @@ void re_initialize(void)
  */
 int count_cpus(int cpu)
 {
-	if (topo.max_cpu_num < cpu)
-		topo.max_cpu_num = cpu;
-
-	topo.num_cpus += 1;
+	topo.num_cpus++;
 	return 0;
 }
 int mark_cpu_present(int cpu)
@@ -2428,6 +2627,12 @@ int mark_cpu_present(int cpu)
 	return 0;
 }
 
+int init_thread_id(int cpu)
+{
+	cpus[cpu].thread_id = -1;
+	return 0;
+}
+
 /*
  * snapshot_proc_interrupts()
  *
@@ -2542,6 +2747,52 @@ int snapshot_gfx_mhz(void)
 }
 
 /*
+ * snapshot_cpu_lpi()
+ *
+ * record snapshot of
+ * /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_cpu_lpi_us(void)
+{
+	FILE *fp;
+	int retval;
+
+	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r");
+
+	retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us);
+	if (retval != 1)
+		err(1, "CPU LPI");
+
+	fclose(fp);
+
+	return 0;
+}
+/*
+ * snapshot_sys_lpi()
+ *
+ * record snapshot of
+ * /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_sys_lpi_us(void)
+{
+	FILE *fp;
+	int retval;
+
+	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
+
+	retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
+	if (retval != 1)
+		err(1, "SYS LPI");
+
+	fclose(fp);
+
+	return 0;
+}
+/*
  * snapshot /proc and /sys files
  *
  * return 1 if configuration restart needed, else return 0
@@ -2558,13 +2809,83 @@ int snapshot_proc_sysfs_files(void)
 	if (DO_BIC(BIC_GFXMHz))
 		snapshot_gfx_mhz();
 
+	if (DO_BIC(BIC_CPU_LPI))
+		snapshot_cpu_lpi_us();
+
+	if (DO_BIC(BIC_SYS_LPI))
+		snapshot_sys_lpi_us();
+
 	return 0;
 }
 
+int exit_requested;
+
+static void signal_handler (int signal)
+{
+	switch (signal) {
+	case SIGINT:
+		exit_requested = 1;
+		if (debug)
+			fprintf(stderr, " SIGINT\n");
+		break;
+	case SIGUSR1:
+		if (debug > 1)
+			fprintf(stderr, "SIGUSR1\n");
+		break;
+	}
+	/* make sure this manually-invoked interval is at least 1ms long */
+	nanosleep(&one_msec, NULL);
+}
+
+void setup_signal_handler(void)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+
+	sa.sa_handler = &signal_handler;
+
+	if (sigaction(SIGINT, &sa, NULL) < 0)
+		err(1, "sigaction SIGINT");
+	if (sigaction(SIGUSR1, &sa, NULL) < 0)
+		err(1, "sigaction SIGUSR1");
+}
+
+void do_sleep(void)
+{
+	struct timeval select_timeout;
+	fd_set readfds;
+	int retval;
+
+	FD_ZERO(&readfds);
+	FD_SET(0, &readfds);
+
+	if (!isatty(fileno(stdin))) {
+		nanosleep(&interval_ts, NULL);
+		return;
+	}
+
+	select_timeout = interval_tv;
+	retval = select(1, &readfds, NULL, NULL, &select_timeout);
+
+	if (retval == 1) {
+		switch (getc(stdin)) {
+		case 'q':
+			exit_requested = 1;
+			break;
+		}
+		/* make sure this manually-invoked interval is at least 1ms long */
+		nanosleep(&one_msec, NULL);
+	}
+}
+
 void turbostat_loop()
 {
 	int retval;
 	int restarted = 0;
+	int done_iters = 0;
+
+	setup_signal_handler();
 
 restart:
 	restarted++;
@@ -2581,6 +2902,7 @@ restart:
 		goto restart;
 	}
 	restarted = 0;
+	done_iters = 0;
 	gettimeofday(&tv_even, (struct timezone *)NULL);
 
 	while (1) {
@@ -2588,7 +2910,7 @@ restart:
 			re_initialize();
 			goto restart;
 		}
-		nanosleep(&interval_ts, NULL);
+		do_sleep();
 		if (snapshot_proc_sysfs_files())
 			goto restart;
 		retval = for_all_cpus(get_counters, ODD_COUNTERS);
@@ -2607,7 +2929,11 @@ restart:
 		compute_average(EVEN_COUNTERS);
 		format_all_counters(EVEN_COUNTERS);
 		flush_output_stdout();
-		nanosleep(&interval_ts, NULL);
+		if (exit_requested)
+			break;
+		if (num_iterations && ++done_iters >= num_iterations)
+			break;
+		do_sleep();
 		if (snapshot_proc_sysfs_files())
 			goto restart;
 		retval = for_all_cpus(get_counters, EVEN_COUNTERS);
@@ -2626,6 +2952,10 @@ restart:
 		compute_average(ODD_COUNTERS);
 		format_all_counters(ODD_COUNTERS);
 		flush_output_stdout();
+		if (exit_requested)
+			break;
+		if (num_iterations && ++done_iters >= num_iterations)
+			break;
 	}
 }
 
@@ -2740,6 +3070,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 		pkg_cstate_limits = hsw_pkg_cstate_limits;
 		has_misc_feature_control = 1;
 		break;
@@ -2945,6 +3276,7 @@ int has_config_tdp(unsigned int family, unsigned int model)
 	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 
 	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
@@ -3399,6 +3731,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		BIC_PRESENT(BIC_PKG__);
 		BIC_PRESENT(BIC_RAM__);
@@ -3523,6 +3856,12 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 	}
 }
 
+void automatic_cstate_conversion_probe(unsigned int family, unsigned int model)
+{
+	if (is_skx(family, model) || is_bdx(family, model))
+		has_automatic_cstate_conversion = 1;
+}
+
 int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	unsigned long long msr;
@@ -3728,6 +4067,7 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 	case INTEL_FAM6_ATOM_GEMINI_LAKE:
@@ -3761,6 +4101,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 	case INTEL_FAM6_ATOM_GEMINI_LAKE:
 		return 1;
@@ -3786,6 +4127,7 @@ int has_skl_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 		return 1;
 	}
 	return 0;
@@ -3815,6 +4157,19 @@ int is_knl(unsigned int family, unsigned int model)
 	return 0;
 }
 
+int is_cnl(unsigned int family, unsigned int model)
+{
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
+		return 1;
+	}
+
+	return 0;
+}
+
 unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
 {
 	if (is_knl(family, model))
@@ -3947,7 +4302,7 @@ void decode_misc_enable_msr(void)
 			base_cpu, msr,
 			msr & MSR_IA32_MISC_ENABLE_TM1 ? "" : "No-",
 			msr & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP ? "" : "No-",
-			msr & MSR_IA32_MISC_ENABLE_MWAIT ? "No-" : "",
+			msr & MSR_IA32_MISC_ENABLE_MWAIT ? "" : "No-",
 			msr & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE ? "No-" : "",
 			msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : "");
 }
@@ -4152,7 +4507,6 @@ void process_cpuid()
 				case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 					crystal_hz = 24000000;	/* 24.0 MHz */
 					break;
-				case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 				case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 					crystal_hz = 25000000;	/* 25.0 MHz */
 					break;
@@ -4253,6 +4607,7 @@ void process_cpuid()
 	}
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
+	do_cnl_cstates = is_cnl(family, model);
 
 	if (!quiet)
 		decode_misc_pwr_mgmt_msr();
@@ -4262,6 +4617,7 @@ void process_cpuid()
 
 	rapl_probe(family, model);
 	perf_limit_reasons_probe(family, model);
+	automatic_cstate_conversion_probe(family, model);
 
 	if (!quiet)
 		dump_cstate_pstate_config_info(family, model);
@@ -4280,6 +4636,16 @@ void process_cpuid()
 	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
 		BIC_PRESENT(BIC_GFXMHz);
 
+	if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
+		BIC_PRESENT(BIC_CPU_LPI);
+	else
+		BIC_NOT_PRESENT(BIC_CPU_LPI);
+
+	if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", R_OK))
+		BIC_PRESENT(BIC_SYS_LPI);
+	else
+		BIC_NOT_PRESENT(BIC_SYS_LPI);
+
 	if (!quiet)
 		decode_misc_feature_control();
 
@@ -4310,14 +4676,10 @@ void topology_probe()
 	int max_core_id = 0;
 	int max_package_id = 0;
 	int max_siblings = 0;
-	struct cpu_topology {
-		int core_id;
-		int physical_package_id;
-	} *cpus;
 
 	/* Initialize num_cpus, max_cpu_num */
+	set_max_cpu_num();
 	topo.num_cpus = 0;
-	topo.max_cpu_num = 0;
 	for_all_proc_cpus(count_cpus);
 	if (!summary_only && topo.num_cpus > 1)
 		BIC_PRESENT(BIC_CPU);
@@ -4357,6 +4719,7 @@ void topology_probe()
 	cpu_affinity_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
 	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
 
+	for_all_proc_cpus(init_thread_id);
 
 	/*
 	 * For online cpus
@@ -4370,26 +4733,45 @@ void topology_probe()
 				fprintf(outf, "cpu%d NOT PRESENT\n", i);
 			continue;
 		}
-		cpus[i].core_id = get_core_id(i);
-		if (cpus[i].core_id > max_core_id)
-			max_core_id = cpus[i].core_id;
 
+		cpus[i].logical_cpu_id = i;
+
+		/* get package information */
 		cpus[i].physical_package_id = get_physical_package_id(i);
 		if (cpus[i].physical_package_id > max_package_id)
 			max_package_id = cpus[i].physical_package_id;
 
-		siblings = get_num_ht_siblings(i);
+		/* get numa node information */
+		cpus[i].physical_node_id = get_physical_node_id(&cpus[i]);
+		if (cpus[i].physical_node_id > topo.max_node_num)
+			topo.max_node_num = cpus[i].physical_node_id;
+
+		/* get core information */
+		cpus[i].physical_core_id = get_core_id(i);
+		if (cpus[i].physical_core_id > max_core_id)
+			max_core_id = cpus[i].physical_core_id;
+
+		/* get thread information */
+		siblings = get_thread_siblings(&cpus[i]);
 		if (siblings > max_siblings)
 			max_siblings = siblings;
+		if (cpus[i].thread_id != -1)
+			topo.num_cores++;
+
 		if (debug > 1)
-			fprintf(outf, "cpu %d pkg %d core %d\n",
-				i, cpus[i].physical_package_id, cpus[i].core_id);
+			fprintf(outf,
+				"cpu %d pkg %d node %d core %d thread %d\n",
+				i, cpus[i].physical_package_id,
+				cpus[i].physical_node_id,
+				cpus[i].physical_core_id,
+				cpus[i].thread_id);
 	}
-	topo.num_cores_per_pkg = max_core_id + 1;
+
+	topo.cores_per_node = max_core_id + 1;
 	if (debug > 1)
 		fprintf(outf, "max_core_id %d, sizing for %d cores per package\n",
-			max_core_id, topo.num_cores_per_pkg);
-	if (!summary_only && topo.num_cores_per_pkg > 1)
+			max_core_id, topo.cores_per_node);
+	if (!summary_only && topo.cores_per_node > 1)
 		BIC_PRESENT(BIC_Core);
 
 	topo.num_packages = max_package_id + 1;
@@ -4399,33 +4781,38 @@ void topology_probe()
 	if (!summary_only && topo.num_packages > 1)
 		BIC_PRESENT(BIC_Package);
 
-	topo.num_threads_per_core = max_siblings;
+	set_node_data();
 	if (debug > 1)
-		fprintf(outf, "max_siblings %d\n", max_siblings);
+		fprintf(outf, "nodes_per_pkg %d\n", topo.nodes_per_pkg);
+	if (!summary_only && topo.nodes_per_pkg > 1)
+		BIC_PRESENT(BIC_Node);
 
-	free(cpus);
+	topo.threads_per_core = max_siblings;
+	if (debug > 1)
+		fprintf(outf, "max_siblings %d\n", max_siblings);
 }
 
 void
-allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data **p)
+allocate_counters(struct thread_data **t, struct core_data **c,
+		  struct pkg_data **p)
 {
 	int i;
+	int num_cores = topo.cores_per_node * topo.nodes_per_pkg *
+			topo.num_packages;
+	int num_threads = topo.threads_per_core * num_cores;
 
-	*t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg *
-		topo.num_packages, sizeof(struct thread_data));
+	*t = calloc(num_threads, sizeof(struct thread_data));
 	if (*t == NULL)
 		goto error;
 
-	for (i = 0; i < topo.num_threads_per_core *
-		topo.num_cores_per_pkg * topo.num_packages; i++)
+	for (i = 0; i < num_threads; i++)
 		(*t)[i].cpu_id = -1;
 
-	*c = calloc(topo.num_cores_per_pkg * topo.num_packages,
-		sizeof(struct core_data));
+	*c = calloc(num_cores, sizeof(struct core_data));
 	if (*c == NULL)
 		goto error;
 
-	for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++)
+	for (i = 0; i < num_cores; i++)
 		(*c)[i].core_id = -1;
 
 	*p = calloc(topo.num_packages, sizeof(struct pkg_data));
@@ -4442,47 +4829,39 @@ error:
 /*
  * init_counter()
  *
- * set cpu_id, core_num, pkg_num
  * set FIRST_THREAD_IN_CORE and FIRST_CORE_IN_PACKAGE
- *
- * increment topo.num_cores when 1st core in pkg seen
  */
 void init_counter(struct thread_data *thread_base, struct core_data *core_base,
-	struct pkg_data *pkg_base, int thread_num, int core_num,
-	int pkg_num, int cpu_id)
+	struct pkg_data *pkg_base, int cpu_id)
 {
+	int pkg_id = cpus[cpu_id].physical_package_id;
+	int node_id = cpus[cpu_id].logical_node_id;
+	int core_id = cpus[cpu_id].physical_core_id;
+	int thread_id = cpus[cpu_id].thread_id;
 	struct thread_data *t;
 	struct core_data *c;
 	struct pkg_data *p;
 
-	t = GET_THREAD(thread_base, thread_num, core_num, pkg_num);
-	c = GET_CORE(core_base, core_num, pkg_num);
-	p = GET_PKG(pkg_base, pkg_num);
+	t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id);
+	c = GET_CORE(core_base, core_id, node_id, pkg_id);
+	p = GET_PKG(pkg_base, pkg_id);
 
 	t->cpu_id = cpu_id;
-	if (thread_num == 0) {
+	if (thread_id == 0) {
 		t->flags |= CPU_IS_FIRST_THREAD_IN_CORE;
 		if (cpu_is_first_core_in_package(cpu_id))
 			t->flags |= CPU_IS_FIRST_CORE_IN_PACKAGE;
 	}
 
-	c->core_id = core_num;
-	p->package_id = pkg_num;
+	c->core_id = core_id;
+	p->package_id = pkg_id;
 }
 
 
 int initialize_counters(int cpu_id)
 {
-	int my_thread_id, my_core_id, my_package_id;
-
-	my_package_id = get_physical_package_id(cpu_id);
-	my_core_id = get_core_id(cpu_id);
-	my_thread_id = get_cpu_position_in_core(cpu_id);
-	if (!my_thread_id)
-		topo.num_cores++;
-
-	init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
-	init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
+	init_counter(EVEN_COUNTERS, cpu_id);
+	init_counter(ODD_COUNTERS, cpu_id);
 	return 0;
 }
 
@@ -4630,7 +5009,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 17.06.23"
+	fprintf(outf, "turbostat version 18.06.01"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -4661,7 +5040,7 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 		msrp->next = sys.tp;
 		sys.tp = msrp;
 		sys.added_thread_counters++;
-		if (sys.added_thread_counters > MAX_ADDED_COUNTERS) {
+		if (sys.added_thread_counters > MAX_ADDED_THREAD_COUNTERS) {
 			fprintf(stderr, "exceeded max %d added thread counters\n",
 				MAX_ADDED_COUNTERS);
 			exit(-1);
@@ -4820,7 +5199,7 @@ void probe_sysfs(void)
 	if (!DO_BIC(BIC_sysfs))
 		return;
 
-	for (state = 10; state > 0; --state) {
+	for (state = 10; state >= 0; --state) {
 
 		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
 			base_cpu, state);
@@ -4847,7 +5226,7 @@ void probe_sysfs(void)
 				FORMAT_PERCENT, SYSFS_PERCPU);
 	}
 
-	for (state = 10; state > 0; --state) {
+	for (state = 10; state >= 0; --state) {
 
 		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
 			base_cpu, state);
@@ -4960,34 +5339,6 @@ error:
 	exit(-1);
 }
 
-int shown;
-/*
- * parse_show_hide() - process cmdline to set default counter action
- */
-void parse_show_hide(char *optarg, enum show_hide_mode new_mode)
-{
-	/*
-	 * --show: show only those specified
-	 *  The 1st invocation will clear and replace the enabled mask
-	 *  subsequent invocations can add to it.
-	 */
-	if (new_mode == SHOW_LIST) {
-		if (shown == 0)
-			bic_enabled = bic_lookup(optarg, new_mode);
-		else
-			bic_enabled |= bic_lookup(optarg, new_mode);
-		shown = 1;
-
-		return;
-	}
-
-	/*
-	 * --hide: do not show those specified
-	 *  multiple invocations simply clear more bits in enabled mask
-	 */
-	bic_enabled &= ~bic_lookup(optarg, new_mode);
-
-}
 
 void cmdline(int argc, char **argv)
 {
@@ -4998,7 +5349,9 @@ void cmdline(int argc, char **argv)
 		{"cpu",		required_argument,	0, 'c'},
 		{"Dump",	no_argument,		0, 'D'},
 		{"debug",	no_argument,		0, 'd'},	/* internal, not documented */
+		{"enable",	required_argument,	0, 'e'},
 		{"interval",	required_argument,	0, 'i'},
+		{"num_iterations",	required_argument,	0, 'n'},
 		{"help",	no_argument,		0, 'h'},
 		{"hide",	required_argument,	0, 'H'},	// meh, -h taken by --help
 		{"Joules",	no_argument,		0, 'J'},
@@ -5014,7 +5367,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
+	while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -5026,11 +5379,20 @@ void cmdline(int argc, char **argv)
 		case 'D':
 			dump_only++;
 			break;
+		case 'e':
+			/* --enable specified counter */
+			bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+			break;
 		case 'd':
 			debug++;
+			ENABLE_BIC(BIC_DISABLED_BY_DEFAULT);
 			break;
 		case 'H':
-			parse_show_hide(optarg, HIDE_LIST);
+			/*
+			 * --hide: do not show those specified
+			 *  multiple invocations simply clear more bits in enabled mask
+			 */
+			bic_enabled &= ~bic_lookup(optarg, HIDE_LIST);
 			break;
 		case 'h':
 		default:
@@ -5046,7 +5408,8 @@ void cmdline(int argc, char **argv)
 					exit(2);
 				}
 
-				interval_ts.tv_sec = interval;
+				interval_tv.tv_sec = interval_ts.tv_sec = interval;
+				interval_tv.tv_usec = (interval - interval_tv.tv_sec) * 1000000;
 				interval_ts.tv_nsec = (interval - interval_ts.tv_sec) * 1000000000;
 			}
 			break;
@@ -5054,6 +5417,7 @@ void cmdline(int argc, char **argv)
 			rapl_joules++;
 			break;
 		case 'l':
+			ENABLE_BIC(BIC_DISABLED_BY_DEFAULT);
 			list_header_only++;
 			quiet++;
 			break;
@@ -5063,8 +5427,26 @@ void cmdline(int argc, char **argv)
 		case 'q':
 			quiet = 1;
 			break;
+		case 'n':
+			num_iterations = strtod(optarg, NULL);
+
+			if (num_iterations <= 0) {
+				fprintf(outf, "iterations %d should be positive number\n",
+					num_iterations);
+				exit(2);
+			}
+			break;
 		case 's':
-			parse_show_hide(optarg, SHOW_LIST);
+			/*
+			 * --show: show only those specified
+			 *  The 1st invocation will clear and replace the enabled mask
+			 *  subsequent invocations can add to it.
+			 */
+			if (shown == 0)
+				bic_enabled = bic_lookup(optarg, SHOW_LIST);
+			else
+				bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+			shown = 1;
 			break;
 		case 'S':
 			summary_only++;
diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile
index 2447b1bbaacf..f4534fb8b951 100644
--- a/tools/power/x86/x86_energy_perf_policy/Makefile
+++ b/tools/power/x86/x86_energy_perf_policy/Makefile
@@ -24,5 +24,5 @@ install : x86_energy_perf_policy
 	install -d  $(DESTDIR)$(PREFIX)/bin
 	install $(BUILD_OUTPUT)/x86_energy_perf_policy $(DESTDIR)$(PREFIX)/bin/x86_energy_perf_policy
 	install -d  $(DESTDIR)$(PREFIX)/share/man/man8
-	install x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8
+	install -m 644 x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index cb166be4918d..4ea385be528f 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -138,6 +138,7 @@ static u32 handle[] = {
 };
 
 static unsigned long dimm_fail_cmd_flags[NUM_DCR];
+static int dimm_fail_cmd_code[NUM_DCR];
 
 struct nfit_test_fw {
 	enum intel_fw_update_state state;
@@ -892,8 +893,11 @@ static int get_dimm(struct nfit_mem *nfit_mem, unsigned int func)
 	if (i >= ARRAY_SIZE(handle))
 		return -ENXIO;
 
-	if ((1 << func) & dimm_fail_cmd_flags[i])
+	if ((1 << func) & dimm_fail_cmd_flags[i]) {
+		if (dimm_fail_cmd_code[i])
+			return dimm_fail_cmd_code[i];
 		return -EIO;
+	}
 
 	return i;
 }
@@ -1162,12 +1166,12 @@ static int ars_state_init(struct device *dev, struct ars_state *ars_state)
 
 static void put_dimms(void *data)
 {
-	struct device **dimm_dev = data;
+	struct nfit_test *t = data;
 	int i;
 
-	for (i = 0; i < NUM_DCR; i++)
-		if (dimm_dev[i])
-			device_unregister(dimm_dev[i]);
+	for (i = 0; i < t->num_dcr; i++)
+		if (t->dimm_dev[i])
+			device_unregister(t->dimm_dev[i]);
 }
 
 static struct class *nfit_test_dimm;
@@ -1176,13 +1180,11 @@ static int dimm_name_to_id(struct device *dev)
 {
 	int dimm;
 
-	if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1
-			|| dimm >= NUM_DCR || dimm < 0)
+	if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1)
 		return -ENXIO;
 	return dimm;
 }
 
-
 static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
@@ -1191,7 +1193,7 @@ static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
 	if (dimm < 0)
 		return dimm;
 
-	return sprintf(buf, "%#x", handle[dimm]);
+	return sprintf(buf, "%#x\n", handle[dimm]);
 }
 DEVICE_ATTR_RO(handle);
 
@@ -1225,8 +1227,39 @@ static ssize_t fail_cmd_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(fail_cmd);
 
+static ssize_t fail_cmd_code_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	int dimm = dimm_name_to_id(dev);
+
+	if (dimm < 0)
+		return dimm;
+
+	return sprintf(buf, "%d\n", dimm_fail_cmd_code[dimm]);
+}
+
+static ssize_t fail_cmd_code_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t size)
+{
+	int dimm = dimm_name_to_id(dev);
+	unsigned long val;
+	ssize_t rc;
+
+	if (dimm < 0)
+		return dimm;
+
+	rc = kstrtol(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	dimm_fail_cmd_code[dimm] = val;
+	return size;
+}
+static DEVICE_ATTR_RW(fail_cmd_code);
+
 static struct attribute *nfit_test_dimm_attributes[] = {
 	&dev_attr_fail_cmd.attr,
+	&dev_attr_fail_cmd_code.attr,
 	&dev_attr_handle.attr,
 	NULL,
 };
@@ -1240,6 +1273,23 @@ static const struct attribute_group *nfit_test_dimm_attribute_groups[] = {
 	NULL,
 };
 
+static int nfit_test_dimm_init(struct nfit_test *t)
+{
+	int i;
+
+	if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t))
+		return -ENOMEM;
+	for (i = 0; i < t->num_dcr; i++) {
+		t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
+				&t->pdev.dev, 0, NULL,
+				nfit_test_dimm_attribute_groups,
+				"test_dimm%d", i + t->dcr_idx);
+		if (!t->dimm_dev[i])
+			return -ENOMEM;
+	}
+	return 0;
+}
+
 static void smart_init(struct nfit_test *t)
 {
 	int i;
@@ -1335,17 +1385,8 @@ static int nfit_test0_alloc(struct nfit_test *t)
 	if (!t->_fit)
 		return -ENOMEM;
 
-	if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t->dimm_dev))
+	if (nfit_test_dimm_init(t))
 		return -ENOMEM;
-	for (i = 0; i < NUM_DCR; i++) {
-		t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
-				&t->pdev.dev, 0, NULL,
-				nfit_test_dimm_attribute_groups,
-				"test_dimm%d", i);
-		if (!t->dimm_dev[i])
-			return -ENOMEM;
-	}
-
 	smart_init(t);
 	return ars_state_init(&t->pdev.dev, &t->ars_state);
 }
@@ -1377,6 +1418,8 @@ static int nfit_test1_alloc(struct nfit_test *t)
 	if (!t->spa_set[1])
 		return -ENOMEM;
 
+	if (nfit_test_dimm_init(t))
+		return -ENOMEM;
 	smart_init(t);
 	return ars_state_init(&t->pdev.dev, &t->ars_state);
 }
@@ -2222,6 +2265,9 @@ static void nfit_test1_setup(struct nfit_test *t)
 	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
 	set_bit(ND_INTEL_ENABLE_LSS_STATUS, &acpi_desc->dimm_cmd_force_en);
+	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
+	set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
+	set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
 }
 
 static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index fa7ee369b3c9..db66f8a0d4be 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -17,7 +17,7 @@ ifeq ($(BUILD), 32)
 	LDFLAGS += -m32
 endif
 
-targets: mapshift $(TARGETS)
+targets: generated/map-shift.h $(TARGETS)
 
 main:	$(OFILES)
 
@@ -42,9 +42,7 @@ radix-tree.c: ../../../lib/radix-tree.c
 idr.c: ../../../lib/idr.c
 	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
 
-.PHONY: mapshift
-
-mapshift:
+generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
 		echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" >		\
 				generated/map-shift.h;			\
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 6c645eb77d42..ee820fcc29b0 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -252,6 +252,13 @@ void idr_checks(void)
 	idr_remove(&idr, 3);
 	idr_remove(&idr, 0);
 
+	assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == 0);
+	idr_remove(&idr, 1);
+	for (i = 1; i < RADIX_TREE_MAP_SIZE; i++)
+		assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == i);
+	idr_remove(&idr, 1 << 30);
+	idr_destroy(&idr);
+
 	for (i = INT_MAX - 3UL; i < INT_MAX + 1UL; i++) {
 		struct item *item = item_create(i, 0);
 		assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i);
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 59245b3d587c..7bf405638b0b 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -16,6 +16,7 @@
 #include <linux/radix-tree.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
+#include <pthread.h>
 
 #include "test.h"
 
@@ -624,6 +625,67 @@ static void multiorder_account(void)
 	item_kill_tree(&tree);
 }
 
+bool stop_iteration = false;
+
+static void *creator_func(void *ptr)
+{
+	/* 'order' is set up to ensure we have sibling entries */
+	unsigned int order = RADIX_TREE_MAP_SHIFT - 1;
+	struct radix_tree_root *tree = ptr;
+	int i;
+
+	for (i = 0; i < 10000; i++) {
+		item_insert_order(tree, 0, order);
+		item_delete_rcu(tree, 0);
+	}
+
+	stop_iteration = true;
+	return NULL;
+}
+
+static void *iterator_func(void *ptr)
+{
+	struct radix_tree_root *tree = ptr;
+	struct radix_tree_iter iter;
+	struct item *item;
+	void **slot;
+
+	while (!stop_iteration) {
+		rcu_read_lock();
+		radix_tree_for_each_slot(slot, tree, &iter, 0) {
+			item = radix_tree_deref_slot(slot);
+
+			if (!item)
+				continue;
+			if (radix_tree_deref_retry(item)) {
+				slot = radix_tree_iter_retry(&iter);
+				continue;
+			}
+
+			item_sanity(item, iter.index);
+		}
+		rcu_read_unlock();
+	}
+	return NULL;
+}
+
+static void multiorder_iteration_race(void)
+{
+	const int num_threads = sysconf(_SC_NPROCESSORS_ONLN);
+	pthread_t worker_thread[num_threads];
+	RADIX_TREE(tree, GFP_KERNEL);
+	int i;
+
+	pthread_create(&worker_thread[0], NULL, &creator_func, &tree);
+	for (i = 1; i < num_threads; i++)
+		pthread_create(&worker_thread[i], NULL, &iterator_func, &tree);
+
+	for (i = 0; i < num_threads; i++)
+		pthread_join(worker_thread[i], NULL);
+
+	item_kill_tree(&tree);
+}
+
 void multiorder_checks(void)
 {
 	int i;
@@ -644,6 +706,7 @@ void multiorder_checks(void)
 	multiorder_join();
 	multiorder_split();
 	multiorder_account();
+	multiorder_iteration_race();
 
 	radix_tree_cpu_dead(0);
 }
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 5978ab1f403d..def6015570b2 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -75,6 +75,25 @@ int item_delete(struct radix_tree_root *root, unsigned long index)
 	return 0;
 }
 
+static void item_free_rcu(struct rcu_head *head)
+{
+	struct item *item = container_of(head, struct item, rcu_head);
+
+	free(item);
+}
+
+int item_delete_rcu(struct radix_tree_root *root, unsigned long index)
+{
+	struct item *item = radix_tree_delete(root, index);
+
+	if (item) {
+		item_sanity(item, index);
+		call_rcu(&item->rcu_head, item_free_rcu);
+		return 1;
+	}
+	return 0;
+}
+
 void item_check_present(struct radix_tree_root *root, unsigned long index)
 {
 	struct item *item;
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index d9c031dbeb1a..31f1d9b6f506 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -5,6 +5,7 @@
 #include <linux/rcupdate.h>
 
 struct item {
+	struct rcu_head	rcu_head;
 	unsigned long index;
 	unsigned int order;
 };
@@ -12,9 +13,11 @@ struct item {
 struct item *item_create(unsigned long index, unsigned int order);
 int __item_insert(struct radix_tree_root *root, struct item *item);
 int item_insert(struct radix_tree_root *root, unsigned long index);
+void item_sanity(struct item *item, unsigned long index);
 int item_insert_order(struct radix_tree_root *root, unsigned long index,
 			unsigned order);
 int item_delete(struct radix_tree_root *root, unsigned long index);
+int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
 struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
 
 void item_check_present(struct radix_tree_root *root, unsigned long index);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 32aafa92074c..305130de910c 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -3,6 +3,7 @@ TARGETS = android
 TARGETS += bpf
 TARGETS += breakpoints
 TARGETS += capabilities
+TARGETS += cgroup
 TARGETS += cpufreq
 TARGETS += cpu-hotplug
 TARGETS += efivarfs
@@ -28,6 +29,7 @@ TARGETS += powerpc
 TARGETS += proc
 TARGETS += pstore
 TARGETS += ptrace
+TARGETS += rtc
 TARGETS += seccomp
 TARGETS += sigaltstack
 TARGETS += size
@@ -134,7 +136,8 @@ ifdef INSTALL_PATH
 	echo "else" >> $(ALL_SCRIPT)
 	echo "  OUTPUT=/dev/stdout" >> $(ALL_SCRIPT)
 	echo "fi" >> $(ALL_SCRIPT)
-	echo "export KSFT_TAP_LEVEL=`echo 1`" >> $(ALL_SCRIPT)
+	echo "export KSFT_TAP_LEVEL=1" >> $(ALL_SCRIPT)
+	echo "export skip=4" >> $(ALL_SCRIPT)
 
 	for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index f6304d2be90c..72c25a3cb658 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -18,10 +18,6 @@ all:
 		fi \
 	done
 
-override define RUN_TESTS
-	@cd $(OUTPUT); ./run.sh
-endef
-
 override define INSTALL_RULE
 	mkdir -p $(INSTALL_PATH)
 	install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
@@ -33,10 +29,6 @@ override define INSTALL_RULE
 	done;
 endef
 
-override define EMIT_TESTS
-	echo "./run.sh"
-endef
-
 override define CLEAN
 	@for DIR in $(SUBDIRS); do		\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
diff --git a/tools/testing/selftests/android/ion/ion_test.sh b/tools/testing/selftests/android/ion/ion_test.sh
index a1aff506f5e6..69e676cfc94e 100755
--- a/tools/testing/selftests/android/ion/ion_test.sh
+++ b/tools/testing/selftests/android/ion/ion_test.sh
@@ -4,6 +4,9 @@ heapsize=4096
 TCID="ion_test.sh"
 errcode=0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 run_test()
 {
 	heaptype=$1
@@ -25,7 +28,7 @@ check_root()
 	uid=$(id -u)
 	if [ $uid -ne 0 ]; then
 		echo $TCID: must be run as root >&2
-		exit 0
+		exit $ksft_skip
 	fi
 }
 
@@ -35,7 +38,7 @@ check_device()
 	if [ ! -e $DEVICE ]; then
 		echo $TCID: No $DEVICE device found >&2
 		echo $TCID: May be CONFIG_ION is not set >&2
-		exit 0
+		exit $ksft_skip
 	fi
 }
 
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 9cf83f895d98..5e1ab2f0eb79 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -12,3 +12,6 @@ test_tcpbpf_user
 test_verifier_log
 feature
 test_libbpf_open
+test_sock
+test_sock_addr
+urandom_read
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 983dd25d49f4..1eefe211a4a8 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -5,3 +5,5 @@ CONFIG_BPF_EVENTS=y
 CONFIG_TEST_BPF=m
 CONFIG_CGROUP_BPF=y
 CONFIG_NETDEVSIM=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCH_INGRESS=y
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index faadbe233966..4123d0ab90ba 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1108,7 +1108,7 @@ static void test_stacktrace_build_id(void)
 
 	assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
 	       == 0);
-	assert(system("./urandom_read if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0);
+	assert(system("./urandom_read") == 0);
 	/* disable stack trace collection */
 	key = 0;
 	val = 1;
@@ -1158,7 +1158,7 @@ static void test_stacktrace_build_id(void)
 	} while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
 
 	CHECK(build_id_matches < 1, "build id match",
-	      "Didn't find expected build ID from the map");
+	      "Didn't find expected build ID from the map\n");
 
 disable_pmu:
 	ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index 73bb20cfb9b7..f4d99fabc56d 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -13,6 +13,7 @@
 #include <bpf/bpf.h>
 
 #include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
 
 #ifndef ARRAY_SIZE
 # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index d488f20926e8..2950f80ba7fb 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -15,6 +15,7 @@
 #include <bpf/libbpf.h>
 
 #include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
 
 #define CG_PATH	"/foo"
 #define CONNECT4_PROG_PATH	"./connect4_prog.o"
diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh
index c6e1dcf992c4..9832a875a828 100755
--- a/tools/testing/selftests/bpf/test_sock_addr.sh
+++ b/tools/testing/selftests/bpf/test_sock_addr.sh
@@ -4,7 +4,7 @@ set -eu
 
 ping_once()
 {
-	ping -q -c 1 -W 1 ${1%%/*} >/dev/null 2>&1
+	ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
 }
 
 wait_for_ip()
@@ -13,7 +13,7 @@ wait_for_ip()
 	echo -n "Wait for testing IPv4/IPv6 to become available "
 	for _i in $(seq ${MAX_PING_TRIES}); do
 		echo -n "."
-		if ping_once ${TEST_IPv4} && ping_once ${TEST_IPv6}; then
+		if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then
 			echo " OK"
 			return
 		fi
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3e7718b1a9ae..fd7de7eb329e 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -11713,6 +11713,11 @@ static void get_unpriv_disabled()
 	FILE *fd;
 
 	fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r");
+	if (!fd) {
+		perror("fopen /proc/sys/"UNPRIV_SYSCTL);
+		unpriv_disabled = true;
+		return;
+	}
 	if (fgets(buf, 2, fd) == buf && atoi(buf))
 		unpriv_disabled = true;
 	fclose(fd);
diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
index 3fece06e9f64..f82dcc1f8841 100644
--- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c
+++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
@@ -143,10 +143,14 @@ void suspend(void)
 	int err;
 	struct itimerspec spec = {};
 
+	if (getuid() != 0)
+		ksft_exit_skip("Please run the test as root - Exiting.\n");
+
 	power_state_fd = open("/sys/power/state", O_RDWR);
 	if (power_state_fd < 0)
 		ksft_exit_fail_msg(
-			"open(\"/sys/power/state\") failed (is this test running as root?)\n");
+			"open(\"/sys/power/state\") failed %s)\n",
+			strerror(errno));
 
 	timerfd = timerfd_create(CLOCK_BOOTTIME_ALARM, 0);
 	if (timerfd < 0)
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
new file mode 100644
index 000000000000..f7a31392eb2f
--- /dev/null
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wall
+
+all:
+
+TEST_GEN_PROGS = test_memcontrol
+
+include ../lib.mk
+
+$(OUTPUT)/test_memcontrol: cgroup_util.c
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
new file mode 100644
index 000000000000..b69bdeb4b9fe
--- /dev/null
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -0,0 +1,331 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/limits.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "cgroup_util.h"
+
+static ssize_t read_text(const char *path, char *buf, size_t max_len)
+{
+	ssize_t len;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	len = read(fd, buf, max_len - 1);
+	if (len < 0)
+		goto out;
+
+	buf[len] = 0;
+out:
+	close(fd);
+	return len;
+}
+
+static ssize_t write_text(const char *path, char *buf, size_t len)
+{
+	int fd;
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return fd;
+
+	len = write(fd, buf, len);
+	if (len < 0) {
+		close(fd);
+		return len;
+	}
+
+	close(fd);
+
+	return len;
+}
+
+char *cg_name(const char *root, const char *name)
+{
+	size_t len = strlen(root) + strlen(name) + 2;
+	char *ret = malloc(len);
+
+	snprintf(ret, len, "%s/%s", root, name);
+
+	return ret;
+}
+
+char *cg_name_indexed(const char *root, const char *name, int index)
+{
+	size_t len = strlen(root) + strlen(name) + 10;
+	char *ret = malloc(len);
+
+	snprintf(ret, len, "%s/%s_%d", root, name, index);
+
+	return ret;
+}
+
+int cg_read(const char *cgroup, const char *control, char *buf, size_t len)
+{
+	char path[PATH_MAX];
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+
+	if (read_text(path, buf, len) >= 0)
+		return 0;
+
+	return -1;
+}
+
+int cg_read_strcmp(const char *cgroup, const char *control,
+		   const char *expected)
+{
+	size_t size = strlen(expected) + 1;
+	char *buf;
+
+	buf = malloc(size);
+	if (!buf)
+		return -1;
+
+	if (cg_read(cgroup, control, buf, size))
+		return -1;
+
+	return strcmp(expected, buf);
+}
+
+int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
+{
+	char buf[PAGE_SIZE];
+
+	if (cg_read(cgroup, control, buf, sizeof(buf)))
+		return -1;
+
+	return strstr(buf, needle) ? 0 : -1;
+}
+
+long cg_read_long(const char *cgroup, const char *control)
+{
+	char buf[128];
+
+	if (cg_read(cgroup, control, buf, sizeof(buf)))
+		return -1;
+
+	return atol(buf);
+}
+
+long cg_read_key_long(const char *cgroup, const char *control, const char *key)
+{
+	char buf[PAGE_SIZE];
+	char *ptr;
+
+	if (cg_read(cgroup, control, buf, sizeof(buf)))
+		return -1;
+
+	ptr = strstr(buf, key);
+	if (!ptr)
+		return -1;
+
+	return atol(ptr + strlen(key));
+}
+
+int cg_write(const char *cgroup, const char *control, char *buf)
+{
+	char path[PATH_MAX];
+	size_t len = strlen(buf);
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+
+	if (write_text(path, buf, len) == len)
+		return 0;
+
+	return -1;
+}
+
+int cg_find_unified_root(char *root, size_t len)
+{
+	char buf[10 * PAGE_SIZE];
+	char *fs, *mount, *type;
+	const char delim[] = "\n\t ";
+
+	if (read_text("/proc/self/mounts", buf, sizeof(buf)) <= 0)
+		return -1;
+
+	/*
+	 * Example:
+	 * cgroup /sys/fs/cgroup cgroup2 rw,seclabel,noexec,relatime 0 0
+	 */
+	for (fs = strtok(buf, delim); fs; fs = strtok(NULL, delim)) {
+		mount = strtok(NULL, delim);
+		type = strtok(NULL, delim);
+		strtok(NULL, delim);
+		strtok(NULL, delim);
+		strtok(NULL, delim);
+
+		if (strcmp(fs, "cgroup") == 0 &&
+		    strcmp(type, "cgroup2") == 0) {
+			strncpy(root, mount, len);
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+int cg_create(const char *cgroup)
+{
+	return mkdir(cgroup, 0644);
+}
+
+static int cg_killall(const char *cgroup)
+{
+	char buf[PAGE_SIZE];
+	char *ptr = buf;
+
+	if (cg_read(cgroup, "cgroup.procs", buf, sizeof(buf)))
+		return -1;
+
+	while (ptr < buf + sizeof(buf)) {
+		int pid = strtol(ptr, &ptr, 10);
+
+		if (pid == 0)
+			break;
+		if (*ptr)
+			ptr++;
+		else
+			break;
+		if (kill(pid, SIGKILL))
+			return -1;
+	}
+
+	return 0;
+}
+
+int cg_destroy(const char *cgroup)
+{
+	int ret;
+
+retry:
+	ret = rmdir(cgroup);
+	if (ret && errno == EBUSY) {
+		ret = cg_killall(cgroup);
+		if (ret)
+			return ret;
+		usleep(100);
+		goto retry;
+	}
+
+	if (ret && errno == ENOENT)
+		ret = 0;
+
+	return ret;
+}
+
+int cg_run(const char *cgroup,
+	   int (*fn)(const char *cgroup, void *arg),
+	   void *arg)
+{
+	int pid, retcode;
+
+	pid = fork();
+	if (pid < 0) {
+		return pid;
+	} else if (pid == 0) {
+		char buf[64];
+
+		snprintf(buf, sizeof(buf), "%d", getpid());
+		if (cg_write(cgroup, "cgroup.procs", buf))
+			exit(EXIT_FAILURE);
+		exit(fn(cgroup, arg));
+	} else {
+		waitpid(pid, &retcode, 0);
+		if (WIFEXITED(retcode))
+			return WEXITSTATUS(retcode);
+		else
+			return -1;
+	}
+}
+
+int cg_run_nowait(const char *cgroup,
+		  int (*fn)(const char *cgroup, void *arg),
+		  void *arg)
+{
+	int pid;
+
+	pid = fork();
+	if (pid == 0) {
+		char buf[64];
+
+		snprintf(buf, sizeof(buf), "%d", getpid());
+		if (cg_write(cgroup, "cgroup.procs", buf))
+			exit(EXIT_FAILURE);
+		exit(fn(cgroup, arg));
+	}
+
+	return pid;
+}
+
+int get_temp_fd(void)
+{
+	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+}
+
+int alloc_pagecache(int fd, size_t size)
+{
+	char buf[PAGE_SIZE];
+	struct stat st;
+	int i;
+
+	if (fstat(fd, &st))
+		goto cleanup;
+
+	size += st.st_size;
+
+	if (ftruncate(fd, size))
+		goto cleanup;
+
+	for (i = 0; i < size; i += sizeof(buf))
+		read(fd, buf, sizeof(buf));
+
+	return 0;
+
+cleanup:
+	return -1;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+	size_t size = (unsigned long)arg;
+	char *buf, *ptr;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	free(buf);
+	return 0;
+}
+
+int is_swap_enabled(void)
+{
+	char buf[PAGE_SIZE];
+	const char delim[] = "\n";
+	int cnt = 0;
+	char *line;
+
+	if (read_text("/proc/swaps", buf, sizeof(buf)) <= 0)
+		return -1;
+
+	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
+		cnt++;
+
+	return cnt > 1;
+}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
new file mode 100644
index 000000000000..fe82a297d4e0
--- /dev/null
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+
+#define PAGE_SIZE 4096
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define MB(x) (x << 20)
+
+/*
+ * Checks if two given values differ by less than err% of their sum.
+ */
+static inline int values_close(long a, long b, int err)
+{
+	return abs(a - b) <= (a + b) / 100 * err;
+}
+
+extern int cg_find_unified_root(char *root, size_t len);
+extern char *cg_name(const char *root, const char *name);
+extern char *cg_name_indexed(const char *root, const char *name, int index);
+extern int cg_create(const char *cgroup);
+extern int cg_destroy(const char *cgroup);
+extern int cg_read(const char *cgroup, const char *control,
+		   char *buf, size_t len);
+extern int cg_read_strcmp(const char *cgroup, const char *control,
+			  const char *expected);
+extern int cg_read_strstr(const char *cgroup, const char *control,
+			  const char *needle);
+extern long cg_read_long(const char *cgroup, const char *control);
+long cg_read_key_long(const char *cgroup, const char *control, const char *key);
+extern int cg_write(const char *cgroup, const char *control, char *buf);
+extern int cg_run(const char *cgroup,
+		  int (*fn)(const char *cgroup, void *arg),
+		  void *arg);
+extern int cg_run_nowait(const char *cgroup,
+			 int (*fn)(const char *cgroup, void *arg),
+			 void *arg);
+extern int get_temp_fd(void);
+extern int alloc_pagecache(int fd, size_t size);
+extern int alloc_anon(const char *cgroup, void *arg);
+extern int is_swap_enabled(void);
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
new file mode 100644
index 000000000000..cf0bddc9d271
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -0,0 +1,1015 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <sys/wait.h>
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <netdb.h>
+#include <errno.h>
+
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+/*
+ * This test creates two nested cgroups with and without enabling
+ * the memory controller.
+ */
+static int test_memcg_subtree_control(const char *root)
+{
+	char *parent, *child, *parent2, *child2;
+	int ret = KSFT_FAIL;
+	char buf[PAGE_SIZE];
+
+	/* Create two nested cgroups with the memory controller enabled */
+	parent = cg_name(root, "memcg_test_0");
+	child = cg_name(root, "memcg_test_0/memcg_test_1");
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_read_strstr(child, "cgroup.controllers", "memory"))
+		goto cleanup;
+
+	/* Create two nested cgroups without enabling memory controller */
+	parent2 = cg_name(root, "memcg_test_1");
+	child2 = cg_name(root, "memcg_test_1/memcg_test_1");
+	if (!parent2 || !child2)
+		goto cleanup;
+
+	if (cg_create(parent2))
+		goto cleanup;
+
+	if (cg_create(child2))
+		goto cleanup;
+
+	if (cg_read(child2, "cgroup.controllers", buf, sizeof(buf)))
+		goto cleanup;
+
+	if (!cg_read_strstr(child2, "cgroup.controllers", "memory"))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(child);
+	cg_destroy(parent);
+	free(parent);
+	free(child);
+
+	cg_destroy(child2);
+	cg_destroy(parent2);
+	free(parent2);
+	free(child2);
+
+	return ret;
+}
+
+static int alloc_anon_50M_check(const char *cgroup, void *arg)
+{
+	size_t size = MB(50);
+	char *buf, *ptr;
+	long anon, current;
+	int ret = -1;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	current = cg_read_long(cgroup, "memory.current");
+	if (current < size)
+		goto cleanup;
+
+	if (!values_close(size, current, 3))
+		goto cleanup;
+
+	anon = cg_read_key_long(cgroup, "memory.stat", "anon ");
+	if (anon < 0)
+		goto cleanup;
+
+	if (!values_close(anon, current, 3))
+		goto cleanup;
+
+	ret = 0;
+cleanup:
+	free(buf);
+	return ret;
+}
+
+static int alloc_pagecache_50M_check(const char *cgroup, void *arg)
+{
+	size_t size = MB(50);
+	int ret = -1;
+	long current, file;
+	int fd;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		return -1;
+
+	if (alloc_pagecache(fd, size))
+		goto cleanup;
+
+	current = cg_read_long(cgroup, "memory.current");
+	if (current < size)
+		goto cleanup;
+
+	file = cg_read_key_long(cgroup, "memory.stat", "file ");
+	if (file < 0)
+		goto cleanup;
+
+	if (!values_close(file, current, 10))
+		goto cleanup;
+
+	ret = 0;
+
+cleanup:
+	close(fd);
+	return ret;
+}
+
+/*
+ * This test create a memory cgroup, allocates
+ * some anonymous memory and some pagecache
+ * and check memory.current and some memory.stat values.
+ */
+static int test_memcg_current(const char *root)
+{
+	int ret = KSFT_FAIL;
+	long current;
+	char *memcg;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	current = cg_read_long(memcg, "memory.current");
+	if (current != 0)
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_anon_50M_check, NULL))
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_pagecache_50M_check, NULL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+static int alloc_pagecache_50M(const char *cgroup, void *arg)
+{
+	int fd = (long)arg;
+
+	return alloc_pagecache(fd, MB(50));
+}
+
+static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg)
+{
+	int fd = (long)arg;
+	int ppid = getppid();
+
+	if (alloc_pagecache(fd, MB(50)))
+		return -1;
+
+	while (getppid() == ppid)
+		sleep(1);
+
+	return 0;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A       memory.min = 50M,  memory.max = 200M
+ * A/B     memory.min = 50M,  memory.current = 50M
+ * A/B/C   memory.min = 75M,  memory.current = 50M
+ * A/B/D   memory.min = 25M,  memory.current = 50M
+ * A/B/E   memory.min = 500M, memory.current = 0
+ * A/B/F   memory.min = 0,    memory.current = 50M
+ *
+ * Usages are pagecache, but the test keeps a running
+ * process in every leaf cgroup.
+ * Then it creates A/G and creates a significant
+ * memory pressure in it.
+ *
+ * A/B    memory.current ~= 50M
+ * A/B/C  memory.current ~= 33M
+ * A/B/D  memory.current ~= 17M
+ * A/B/E  memory.current ~= 0
+ *
+ * After that it tries to allocate more than there is
+ * unprotected memory in A available, and checks
+ * checks that memory.min protects pagecache even
+ * in this case.
+ */
+static int test_memcg_min(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent[3] = {NULL};
+	char *children[4] = {NULL};
+	long c[4];
+	int i, attempts;
+	int fd;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		goto cleanup;
+
+	parent[0] = cg_name(root, "memcg_test_0");
+	if (!parent[0])
+		goto cleanup;
+
+	parent[1] = cg_name(parent[0], "memcg_test_1");
+	if (!parent[1])
+		goto cleanup;
+
+	parent[2] = cg_name(parent[0], "memcg_test_2");
+	if (!parent[2])
+		goto cleanup;
+
+	if (cg_create(parent[0]))
+		goto cleanup;
+
+	if (cg_read_long(parent[0], "memory.min")) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_write(parent[0], "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "memory.max", "200M"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_create(parent[1]))
+		goto cleanup;
+
+	if (cg_write(parent[1], "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_create(parent[2]))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		children[i] = cg_name_indexed(parent[1], "child_memcg", i);
+		if (!children[i])
+			goto cleanup;
+
+		if (cg_create(children[i]))
+			goto cleanup;
+
+		if (i == 2)
+			continue;
+
+		cg_run_nowait(children[i], alloc_pagecache_50M_noexit,
+			      (void *)(long)fd);
+	}
+
+	if (cg_write(parent[0], "memory.min", "50M"))
+		goto cleanup;
+	if (cg_write(parent[1], "memory.min", "50M"))
+		goto cleanup;
+	if (cg_write(children[0], "memory.min", "75M"))
+		goto cleanup;
+	if (cg_write(children[1], "memory.min", "25M"))
+		goto cleanup;
+	if (cg_write(children[2], "memory.min", "500M"))
+		goto cleanup;
+	if (cg_write(children[3], "memory.min", "0"))
+		goto cleanup;
+
+	attempts = 0;
+	while (!values_close(cg_read_long(parent[1], "memory.current"),
+			     MB(150), 3)) {
+		if (attempts++ > 5)
+			break;
+		sleep(1);
+	}
+
+	if (cg_run(parent[2], alloc_anon, (void *)MB(148)))
+		goto cleanup;
+
+	if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++)
+		c[i] = cg_read_long(children[i], "memory.current");
+
+	if (!values_close(c[0], MB(33), 10))
+		goto cleanup;
+
+	if (!values_close(c[1], MB(17), 10))
+		goto cleanup;
+
+	if (!values_close(c[2], 0, 1))
+		goto cleanup;
+
+	if (!cg_run(parent[2], alloc_anon, (void *)MB(170)))
+		goto cleanup;
+
+	if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = ARRAY_SIZE(children) - 1; i >= 0; i--) {
+		if (!children[i])
+			continue;
+
+		cg_destroy(children[i]);
+		free(children[i]);
+	}
+
+	for (i = ARRAY_SIZE(parent) - 1; i >= 0; i--) {
+		if (!parent[i])
+			continue;
+
+		cg_destroy(parent[i]);
+		free(parent[i]);
+	}
+	close(fd);
+	return ret;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A       memory.low = 50M,  memory.max = 200M
+ * A/B     memory.low = 50M,  memory.current = 50M
+ * A/B/C   memory.low = 75M,  memory.current = 50M
+ * A/B/D   memory.low = 25M,  memory.current = 50M
+ * A/B/E   memory.low = 500M, memory.current = 0
+ * A/B/F   memory.low = 0,    memory.current = 50M
+ *
+ * Usages are pagecache.
+ * Then it creates A/G an creates a significant
+ * memory pressure in it.
+ *
+ * Then it checks actual memory usages and expects that:
+ * A/B    memory.current ~= 50M
+ * A/B/   memory.current ~= 33M
+ * A/B/D  memory.current ~= 17M
+ * A/B/E  memory.current ~= 0
+ *
+ * After that it tries to allocate more than there is
+ * unprotected memory in A available,
+ * and checks low and oom events in memory.events.
+ */
+static int test_memcg_low(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent[3] = {NULL};
+	char *children[4] = {NULL};
+	long low, oom;
+	long c[4];
+	int i;
+	int fd;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		goto cleanup;
+
+	parent[0] = cg_name(root, "memcg_test_0");
+	if (!parent[0])
+		goto cleanup;
+
+	parent[1] = cg_name(parent[0], "memcg_test_1");
+	if (!parent[1])
+		goto cleanup;
+
+	parent[2] = cg_name(parent[0], "memcg_test_2");
+	if (!parent[2])
+		goto cleanup;
+
+	if (cg_create(parent[0]))
+		goto cleanup;
+
+	if (cg_read_long(parent[0], "memory.low"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "memory.max", "200M"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_create(parent[1]))
+		goto cleanup;
+
+	if (cg_write(parent[1], "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_create(parent[2]))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		children[i] = cg_name_indexed(parent[1], "child_memcg", i);
+		if (!children[i])
+			goto cleanup;
+
+		if (cg_create(children[i]))
+			goto cleanup;
+
+		if (i == 2)
+			continue;
+
+		if (cg_run(children[i], alloc_pagecache_50M, (void *)(long)fd))
+			goto cleanup;
+	}
+
+	if (cg_write(parent[0], "memory.low", "50M"))
+		goto cleanup;
+	if (cg_write(parent[1], "memory.low", "50M"))
+		goto cleanup;
+	if (cg_write(children[0], "memory.low", "75M"))
+		goto cleanup;
+	if (cg_write(children[1], "memory.low", "25M"))
+		goto cleanup;
+	if (cg_write(children[2], "memory.low", "500M"))
+		goto cleanup;
+	if (cg_write(children[3], "memory.low", "0"))
+		goto cleanup;
+
+	if (cg_run(parent[2], alloc_anon, (void *)MB(148)))
+		goto cleanup;
+
+	if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++)
+		c[i] = cg_read_long(children[i], "memory.current");
+
+	if (!values_close(c[0], MB(33), 10))
+		goto cleanup;
+
+	if (!values_close(c[1], MB(17), 10))
+		goto cleanup;
+
+	if (!values_close(c[2], 0, 1))
+		goto cleanup;
+
+	if (cg_run(parent[2], alloc_anon, (void *)MB(166))) {
+		fprintf(stderr,
+			"memory.low prevents from allocating anon memory\n");
+		goto cleanup;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		oom = cg_read_key_long(children[i], "memory.events", "oom ");
+		low = cg_read_key_long(children[i], "memory.events", "low ");
+
+		if (oom)
+			goto cleanup;
+		if (i < 2 && low <= 0)
+			goto cleanup;
+		if (i >= 2 && low)
+			goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = ARRAY_SIZE(children) - 1; i >= 0; i--) {
+		if (!children[i])
+			continue;
+
+		cg_destroy(children[i]);
+		free(children[i]);
+	}
+
+	for (i = ARRAY_SIZE(parent) - 1; i >= 0; i--) {
+		if (!parent[i])
+			continue;
+
+		cg_destroy(parent[i]);
+		free(parent[i]);
+	}
+	close(fd);
+	return ret;
+}
+
+static int alloc_pagecache_max_30M(const char *cgroup, void *arg)
+{
+	size_t size = MB(50);
+	int ret = -1;
+	long current;
+	int fd;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		return -1;
+
+	if (alloc_pagecache(fd, size))
+		goto cleanup;
+
+	current = cg_read_long(cgroup, "memory.current");
+	if (current <= MB(29) || current > MB(30))
+		goto cleanup;
+
+	ret = 0;
+
+cleanup:
+	close(fd);
+	return ret;
+
+}
+
+/*
+ * This test checks that memory.high limits the amount of
+ * memory which can be consumed by either anonymous memory
+ * or pagecache.
+ */
+static int test_memcg_high(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	long high;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_read_strcmp(memcg, "memory.high", "max\n"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.high", "30M"))
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (!cg_run(memcg, alloc_pagecache_50M_check, NULL))
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_pagecache_max_30M, NULL))
+		goto cleanup;
+
+	high = cg_read_key_long(memcg, "memory.events", "high ");
+	if (high <= 0)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+/*
+ * This test checks that memory.max limits the amount of
+ * memory which can be consumed by either anonymous memory
+ * or pagecache.
+ */
+static int test_memcg_max(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	long current, max;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_read_strcmp(memcg, "memory.max", "max\n"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "30M"))
+		goto cleanup;
+
+	/* Should be killed by OOM killer */
+	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_pagecache_max_30M, NULL))
+		goto cleanup;
+
+	current = cg_read_long(memcg, "memory.current");
+	if (current > MB(30) || !current)
+		goto cleanup;
+
+	max = cg_read_key_long(memcg, "memory.events", "max ");
+	if (max <= 0)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+static int alloc_anon_50M_check_swap(const char *cgroup, void *arg)
+{
+	long mem_max = (long)arg;
+	size_t size = MB(50);
+	char *buf, *ptr;
+	long mem_current, swap_current;
+	int ret = -1;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	mem_current = cg_read_long(cgroup, "memory.current");
+	if (!mem_current || !values_close(mem_current, mem_max, 3))
+		goto cleanup;
+
+	swap_current = cg_read_long(cgroup, "memory.swap.current");
+	if (!swap_current ||
+	    !values_close(mem_current + swap_current, size, 3))
+		goto cleanup;
+
+	ret = 0;
+cleanup:
+	free(buf);
+	return ret;
+}
+
+/*
+ * This test checks that memory.swap.max limits the amount of
+ * anonymous memory which can be swapped out.
+ */
+static int test_memcg_swap_max(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	long max;
+
+	if (!is_swap_enabled())
+		return KSFT_SKIP;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.swap.current")) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_read_strcmp(memcg, "memory.max", "max\n"))
+		goto cleanup;
+
+	if (cg_read_strcmp(memcg, "memory.swap.max", "max\n"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "30M"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "30M"))
+		goto cleanup;
+
+	/* Should be killed by OOM killer */
+	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom ") != 1)
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1)
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_anon_50M_check_swap, (void *)MB(30)))
+		goto cleanup;
+
+	max = cg_read_key_long(memcg, "memory.events", "max ");
+	if (max <= 0)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM. Then it checks for oom and oom_kill events in
+ * memory.events.
+ */
+static int test_memcg_oom_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "30M"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_read_strcmp(memcg, "cgroup.procs", ""))
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom ") != 1)
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+struct tcp_server_args {
+	unsigned short port;
+	int ctl[2];
+};
+
+static int tcp_server(const char *cgroup, void *arg)
+{
+	struct tcp_server_args *srv_args = arg;
+	struct sockaddr_in6 saddr = { 0 };
+	socklen_t slen = sizeof(saddr);
+	int sk, client_sk, ctl_fd, yes = 1, ret = -1;
+
+	close(srv_args->ctl[0]);
+	ctl_fd = srv_args->ctl[1];
+
+	saddr.sin6_family = AF_INET6;
+	saddr.sin6_addr = in6addr_any;
+	saddr.sin6_port = htons(srv_args->port);
+
+	sk = socket(AF_INET6, SOCK_STREAM, 0);
+	if (sk < 0)
+		return ret;
+
+	if (setsockopt(sk, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0)
+		goto cleanup;
+
+	if (bind(sk, (struct sockaddr *)&saddr, slen)) {
+		write(ctl_fd, &errno, sizeof(errno));
+		goto cleanup;
+	}
+
+	if (listen(sk, 1))
+		goto cleanup;
+
+	ret = 0;
+	if (write(ctl_fd, &ret, sizeof(ret)) != sizeof(ret)) {
+		ret = -1;
+		goto cleanup;
+	}
+
+	client_sk = accept(sk, NULL, NULL);
+	if (client_sk < 0)
+		goto cleanup;
+
+	ret = -1;
+	for (;;) {
+		uint8_t buf[0x100000];
+
+		if (write(client_sk, buf, sizeof(buf)) <= 0) {
+			if (errno == ECONNRESET)
+				ret = 0;
+			break;
+		}
+	}
+
+	close(client_sk);
+
+cleanup:
+	close(sk);
+	return ret;
+}
+
+static int tcp_client(const char *cgroup, unsigned short port)
+{
+	const char server[] = "localhost";
+	struct addrinfo *ai;
+	char servport[6];
+	int retries = 0x10; /* nice round number */
+	int sk, ret;
+
+	snprintf(servport, sizeof(servport), "%hd", port);
+	ret = getaddrinfo(server, servport, NULL, &ai);
+	if (ret)
+		return ret;
+
+	sk = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
+	if (sk < 0)
+		goto free_ainfo;
+
+	ret = connect(sk, ai->ai_addr, ai->ai_addrlen);
+	if (ret < 0)
+		goto close_sk;
+
+	ret = KSFT_FAIL;
+	while (retries--) {
+		uint8_t buf[0x100000];
+		long current, sock;
+
+		if (read(sk, buf, sizeof(buf)) <= 0)
+			goto close_sk;
+
+		current = cg_read_long(cgroup, "memory.current");
+		sock = cg_read_key_long(cgroup, "memory.stat", "sock ");
+
+		if (current < 0 || sock < 0)
+			goto close_sk;
+
+		if (current < sock)
+			goto close_sk;
+
+		if (values_close(current, sock, 10)) {
+			ret = KSFT_PASS;
+			break;
+		}
+	}
+
+close_sk:
+	close(sk);
+free_ainfo:
+	freeaddrinfo(ai);
+	return ret;
+}
+
+/*
+ * This test checks socket memory accounting.
+ * The test forks a TCP server listens on a random port between 1000
+ * and 61000. Once it gets a client connection, it starts writing to
+ * its socket.
+ * The TCP client interleaves reads from the socket with check whether
+ * memory.current and memory.stat.sock are similar.
+ */
+static int test_memcg_sock(const char *root)
+{
+	int bind_retries = 5, ret = KSFT_FAIL, pid, err;
+	unsigned short port;
+	char *memcg;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	while (bind_retries--) {
+		struct tcp_server_args args;
+
+		if (pipe(args.ctl))
+			goto cleanup;
+
+		port = args.port = 1000 + rand() % 60000;
+
+		pid = cg_run_nowait(memcg, tcp_server, &args);
+		if (pid < 0)
+			goto cleanup;
+
+		close(args.ctl[1]);
+		if (read(args.ctl[0], &err, sizeof(err)) != sizeof(err))
+			goto cleanup;
+		close(args.ctl[0]);
+
+		if (!err)
+			break;
+		if (err != EADDRINUSE)
+			goto cleanup;
+
+		waitpid(pid, NULL, 0);
+	}
+
+	if (err == EADDRINUSE) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (tcp_client(memcg, port) != KSFT_PASS)
+		goto cleanup;
+
+	waitpid(pid, &err, 0);
+	if (WEXITSTATUS(err))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.current") < 0)
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.stat", "sock "))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct memcg_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_memcg_subtree_control),
+	T(test_memcg_current),
+	T(test_memcg_min),
+	T(test_memcg_low),
+	T(test_memcg_high),
+	T(test_memcg_max),
+	T(test_memcg_oom_events),
+	T(test_memcg_swap_max),
+	T(test_memcg_sock),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int i, ret = EXIT_SUCCESS;
+
+	if (cg_find_unified_root(root, sizeof(root)))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	/*
+	 * Check that memory controller is available:
+	 * memory is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+		ksft_exit_skip("memory controller isn't available\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ret = EXIT_FAILURE;
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
index f3a8933c1275..bab13dd025a6 100755
--- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
+++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
@@ -2,6 +2,8 @@
 # SPDX-License-Identifier: GPL-2.0
 
 SYSFS=
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
 
 prerequisite()
 {
@@ -9,7 +11,7 @@ prerequisite()
 
 	if [ $UID != 0 ]; then
 		echo $msg must be run as root >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	taskset -p 01 $$
@@ -18,12 +20,12 @@ prerequisite()
 
 	if [ ! -d "$SYSFS" ]; then
 		echo $msg sysfs is not mounted >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	if ! ls $SYSFS/devices/system/cpu/cpu* > /dev/null 2>&1; then
 		echo $msg cpu hotplug is not supported >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	echo "CPU online/offline summary:"
@@ -32,7 +34,7 @@ prerequisite()
 
 	if [[ "$online_cpus" = "$online_max" ]]; then
 		echo "$msg: since there is only one cpu: $online_cpus"
-		exit 0
+		exit $ksft_skip
 	fi
 
 	echo -e "\t Cpus in online state: $online_cpus"
@@ -237,12 +239,12 @@ prerequisite_extra()
 
 	if [ ! -d "$DEBUGFS" ]; then
 		echo $msg debugfs is not mounted >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	if [ ! -d $NOTIFIER_ERR_INJECT_DIR ]; then
 		echo $msg cpu-notifier-error-inject module is not available >&2
-		exit 0
+		exit $ksft_skip
 	fi
 }
 
diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh
index d83922de9d89..31f8c9a76c5f 100755
--- a/tools/testing/selftests/cpufreq/main.sh
+++ b/tools/testing/selftests/cpufreq/main.sh
@@ -13,6 +13,9 @@ SYSFS=
 CPUROOT=
 CPUFREQROOT=
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 helpme()
 {
 	printf "Usage: $0 [-h] [-todg args]
@@ -38,7 +41,7 @@ prerequisite()
 
 	if [ $UID != 0 ]; then
 		echo $msg must be run as root >&2
-		exit 2
+		exit $ksft_skip
 	fi
 
 	taskset -p 01 $$
diff --git a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
new file mode 100755
index 000000000000..1893d0f59ad7
--- /dev/null
+++ b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
@@ -0,0 +1,198 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+usage() { echo "usbip_test.sh -b <busid> -p <usbip tools path>"; exit 1; }
+
+while getopts "h:b:p:" arg; do
+    case "${arg}" in
+	h)
+	    usage
+	    ;;
+	b)
+	    busid=${OPTARG}
+	    ;;
+	p)
+	    tools_path=${OPTARG}
+	    ;;
+	*)
+	    usage
+	    ;;
+    esac
+done
+shift $((OPTIND-1))
+
+if [ -z "${busid}" ]; then
+	usage
+fi
+
+echo "Running USB over IP Testing on $busid";
+
+test_end_msg="End of USB over IP Testing on $busid"
+
+if [ $UID != 0 ]; then
+	echo "Please run usbip_test as root [SKIP]"
+	echo $test_end_msg
+	exit $ksft_skip
+fi
+
+echo "Load usbip_host module"
+if ! /sbin/modprobe -q -n usbip_host; then
+	echo "usbip_test: module usbip_host is not found [SKIP]"
+	echo $test_end_msg
+	exit $ksft_skip
+fi
+
+if /sbin/modprobe -q usbip_host; then
+	/sbin/modprobe -q -r test_bitmap
+	echo "usbip_test: module usbip_host is loaded [OK]"
+else
+	echo "usbip_test: module usbip_host failed to load [FAIL]"
+	echo $test_end_msg
+	exit 1
+fi
+
+echo "Load vhci_hcd module"
+if /sbin/modprobe -q vhci_hcd; then
+	/sbin/modprobe -q -r test_bitmap
+	echo "usbip_test: module vhci_hcd is loaded [OK]"
+else
+	echo "usbip_test: module vhci_hcd failed to load [FAIL]"
+	echo $test_end_msg
+	exit 1
+fi
+echo "=============================================================="
+
+cd $tools_path;
+
+if [ ! -f src/usbip ]; then
+	echo "Please build usbip tools"
+	echo $test_end_msg
+	exit $ksft_skip
+fi
+
+echo "Expect to see export-able devices";
+src/usbip list -l;
+echo "=============================================================="
+
+echo "Run lsusb to see all usb devices"
+lsusb -t;
+echo "=============================================================="
+
+src/usbipd -D;
+
+echo "Get exported devices from localhost - expect to see none";
+src/usbip list -r localhost;
+echo "=============================================================="
+
+echo "bind devices";
+src/usbip bind -b $busid;
+echo "=============================================================="
+
+echo "Run lsusb - bound devices should be under usbip_host control"
+lsusb -t;
+echo "=============================================================="
+
+echo "bind devices - expect already bound messages"
+src/usbip bind -b $busid;
+echo "=============================================================="
+
+echo "Get exported devices from localhost - expect to see exported devices";
+src/usbip list -r localhost;
+echo "=============================================================="
+
+echo "unbind devices";
+src/usbip unbind -b $busid;
+echo "=============================================================="
+
+echo "Run lsusb - bound devices should be rebound to original drivers"
+lsusb -t;
+echo "=============================================================="
+
+echo "unbind devices - expect no devices bound message";
+src/usbip unbind -b $busid;
+echo "=============================================================="
+
+echo "Get exported devices from localhost - expect to see none";
+src/usbip list -r localhost;
+echo "=============================================================="
+
+echo "List imported devices - expect to see none";
+src/usbip port;
+echo "=============================================================="
+
+echo "Import devices from localhost - should fail with no devices"
+src/usbip attach -r localhost -b $busid;
+echo "=============================================================="
+
+echo "bind devices";
+src/usbip bind -b $busid;
+echo "=============================================================="
+
+echo "List imported devices - expect to see exported devices";
+src/usbip list -r localhost;
+echo "=============================================================="
+
+echo "List imported devices - expect to see none";
+src/usbip port;
+echo "=============================================================="
+
+echo "Import devices from localhost - should work"
+src/usbip attach -r localhost -b $busid;
+echo "=============================================================="
+
+echo "List imported devices - expect to see imported devices";
+src/usbip port;
+echo "=============================================================="
+
+echo "Import devices from localhost - expect already imported messages"
+src/usbip attach -r localhost -b $busid;
+echo "=============================================================="
+
+echo "Un-import devices";
+src/usbip detach -p 00;
+src/usbip detach -p 01;
+echo "=============================================================="
+
+echo "List imported devices - expect to see none";
+src/usbip port;
+echo "=============================================================="
+
+echo "Un-import devices - expect no devices to detach messages";
+src/usbip detach -p 00;
+src/usbip detach -p 01;
+echo "=============================================================="
+
+echo "Detach invalid port tests - expect invalid port error message";
+src/usbip detach -p 100;
+echo "=============================================================="
+
+echo "Expect to see export-able devices";
+src/usbip list -l;
+echo "=============================================================="
+
+echo "Remove usbip_host module";
+rmmod usbip_host;
+
+echo "Run lsusb - bound devices should be rebound to original drivers"
+lsusb -t;
+echo "=============================================================="
+
+echo "Run bind without usbip_host - expect fail"
+src/usbip bind -b $busid;
+echo "=============================================================="
+
+echo "Run lsusb - devices that failed to bind aren't bound to any driver"
+lsusb -t;
+echo "=============================================================="
+
+echo "modprobe usbip_host - does it work?"
+/sbin/modprobe usbip_host
+echo "Should see -busid- is not in match_busid table... skip! dmesg"
+echo "=============================================================="
+dmesg | grep "is not in match_busid table"
+echo "=============================================================="
+
+echo $test_end_msg
diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh
index c6d5790575ae..a47029a799d2 100755
--- a/tools/testing/selftests/efivarfs/efivarfs.sh
+++ b/tools/testing/selftests/efivarfs/efivarfs.sh
@@ -4,18 +4,21 @@
 efivarfs_mount=/sys/firmware/efi/efivars
 test_guid=210be57c-9849-4fc7-a635-e6382d1aec27
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 check_prereqs()
 {
 	local msg="skip all tests:"
 
 	if [ $UID != 0 ]; then
 		echo $msg must be run as root >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	if ! grep -q "^\S\+ $efivarfs_mount efivarfs" /proc/mounts; then
 		echo $msg efivarfs is not mounted on $efivarfs_mount >&2
-		exit 0
+		exit $ksft_skip
 	fi
 }
 
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
index 67cd4597db2b..47cbf54d0801 100644
--- a/tools/testing/selftests/exec/execveat.c
+++ b/tools/testing/selftests/exec/execveat.c
@@ -20,6 +20,8 @@
 #include <string.h>
 #include <unistd.h>
 
+#include "../kselftest.h"
+
 static char longpath[2 * PATH_MAX] = "";
 static char *envp[] = { "IN_TEST=yes", NULL, NULL };
 static char *argv[] = { "execveat", "99", NULL };
@@ -249,8 +251,8 @@ static int run_tests(void)
 	errno = 0;
 	execveat_(-1, NULL, NULL, NULL, 0);
 	if (errno == ENOSYS) {
-		printf("[FAIL] ENOSYS calling execveat - no kernel support?\n");
-		return 1;
+		ksft_exit_skip(
+			"ENOSYS calling execveat - no kernel support?\n");
 	}
 
 	/* Change file position to confirm it doesn't affect anything */
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index 4e6d09fb166f..129880fb42d3 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,8 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := dnotify_test devpts_pts
-all: $(TEST_PROGS)
 
-include ../lib.mk
+CFLAGS += -I../../../../usr/include/
+TEST_GEN_PROGS := devpts_pts
+TEST_GEN_PROGS_EXTENDED := dnotify_test
 
-clean:
-	rm -fr $(TEST_PROGS)
+include ../lib.mk
diff --git a/tools/testing/selftests/filesystems/devpts_pts.c b/tools/testing/selftests/filesystems/devpts_pts.c
index b9055e974289..b1fc9b916ace 100644
--- a/tools/testing/selftests/filesystems/devpts_pts.c
+++ b/tools/testing/selftests/filesystems/devpts_pts.c
@@ -8,9 +8,10 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <sys/ioctl.h>
+#include <asm/ioctls.h>
 #include <sys/mount.h>
 #include <sys/wait.h>
+#include "../kselftest.h"
 
 static bool terminal_dup2(int duplicate, int original)
 {
@@ -125,10 +126,12 @@ static int do_tiocgptpeer(char *ptmx, char *expected_procfd_contents)
 		if (errno == EINVAL) {
 			fprintf(stderr, "TIOCGPTPEER is not supported. "
 					"Skipping test.\n");
-			fret = EXIT_SUCCESS;
+			fret = KSFT_SKIP;
+		} else {
+			fprintf(stderr,
+				"Failed to perform TIOCGPTPEER ioctl\n");
+			fret = EXIT_FAILURE;
 		}
-
-		fprintf(stderr, "Failed to perform TIOCGPTPEER ioctl\n");
 		goto do_cleanup;
 	}
 
@@ -279,9 +282,9 @@ int main(int argc, char *argv[])
 	int ret;
 
 	if (!isatty(STDIN_FILENO)) {
-		fprintf(stderr, "Standard input file desciptor is not attached "
+		fprintf(stderr, "Standard input file descriptor is not attached "
 				"to a terminal. Skipping test\n");
-		exit(EXIT_FAILURE);
+		exit(KSFT_SKIP);
 	}
 
 	ret = unshare(CLONE_NEWNS);
diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile
index 826f38d5dd19..261c81f08606 100644
--- a/tools/testing/selftests/firmware/Makefile
+++ b/tools/testing/selftests/firmware/Makefile
@@ -4,6 +4,7 @@
 all:
 
 TEST_PROGS := fw_run_tests.sh
+TEST_FILES := fw_fallback.sh fw_filesystem.sh fw_lib.sh
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/firmware/fw_fallback.sh b/tools/testing/selftests/firmware/fw_fallback.sh
index 8e2e34a2ca69..70d18be46af5 100755
--- a/tools/testing/selftests/firmware/fw_fallback.sh
+++ b/tools/testing/selftests/firmware/fw_fallback.sh
@@ -74,7 +74,7 @@ load_fw_custom()
 {
 	if [ ! -e "$DIR"/trigger_custom_fallback ]; then
 		echo "$0: custom fallback trigger not present, ignoring test" >&2
-		return 1
+		exit $ksft_skip
 	fi
 
 	local name="$1"
@@ -107,7 +107,7 @@ load_fw_custom_cancel()
 {
 	if [ ! -e "$DIR"/trigger_custom_fallback ]; then
 		echo "$0: canceling custom fallback trigger not present, ignoring test" >&2
-		return 1
+		exit $ksft_skip
 	fi
 
 	local name="$1"
diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index 6452d2129cd9..a4320c4b44dc 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -30,6 +30,7 @@ fi
 
 if [ ! -e "$DIR"/trigger_async_request ]; then
 	echo "$0: empty filename: async trigger not present, ignoring test" >&2
+	exit $ksft_skip
 else
 	if printf '\000' >"$DIR"/trigger_async_request 2> /dev/null; then
 		echo "$0: empty filename should not succeed (async)" >&2
@@ -69,6 +70,7 @@ fi
 # Try the asynchronous version too
 if [ ! -e "$DIR"/trigger_async_request ]; then
 	echo "$0: firmware loading: async trigger not present, ignoring test" >&2
+	exit $ksft_skip
 else
 	if ! echo -n "$NAME" >"$DIR"/trigger_async_request ; then
 		echo "$0: could not trigger async request" >&2
@@ -89,7 +91,7 @@ test_config_present()
 {
 	if [ ! -f $DIR/reset ]; then
 		echo "Configuration triggers not present, ignoring test"
-		exit 0
+		exit $ksft_skip
 	fi
 }
 
diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh
index 9ea31b57d71a..6c5f1b2ffb74 100755
--- a/tools/testing/selftests/firmware/fw_lib.sh
+++ b/tools/testing/selftests/firmware/fw_lib.sh
@@ -9,11 +9,14 @@ DIR=/sys/devices/virtual/misc/test_firmware
 PROC_CONFIG="/proc/config.gz"
 TEST_DIR=$(dirname $0)
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 print_reqs_exit()
 {
 	echo "You must have the following enabled in your kernel:" >&2
 	cat $TEST_DIR/config >&2
-	exit 1
+	exit $ksft_skip
 }
 
 test_modprobe()
@@ -88,7 +91,7 @@ verify_reqs()
 	if [ "$TEST_REQS_FW_SYSFS_FALLBACK" = "yes" ]; then
 		if [ ! "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
 			echo "usermode helper disabled so ignoring test"
-			exit 0
+			exit $ksft_skip
 		fi
 	fi
 }
@@ -154,11 +157,13 @@ test_finish()
 	if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
 		echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout
 	fi
-	if [ "$OLD_FWPATH" = "" ]; then
-		OLD_FWPATH=" "
-	fi
 	if [ "$TEST_REQS_FW_SET_CUSTOM_PATH" = "yes" ]; then
-		echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path
+		if [ "$OLD_FWPATH" = "" ]; then
+			# A zero-length write won't work; write a null byte
+			printf '\000' >/sys/module/firmware_class/parameters/path
+		else
+			echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path
+		fi
 	fi
 	if [ -f $FW ]; then
 		rm -f "$FW"
diff --git a/tools/testing/selftests/firmware/fw_run_tests.sh b/tools/testing/selftests/firmware/fw_run_tests.sh
index 06d638e9dc62..cffdd4eb0a57 100755
--- a/tools/testing/selftests/firmware/fw_run_tests.sh
+++ b/tools/testing/selftests/firmware/fw_run_tests.sh
@@ -66,5 +66,5 @@ if [ -f $FW_FORCE_SYSFS_FALLBACK ]; then
 	run_test_config_0003
 else
 	echo "Running basic kernel configuration, working with your config"
-	run_test
+	run_tests
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
index 786dce7e48be..2aabab363cfb 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
@@ -29,7 +29,7 @@ do_reset
 
 echo "Test extended error support"
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
-echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger &>/dev/null
+! echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger 2> /dev/null
 if ! grep -q "ERROR:" events/sched/sched_wakeup/hist; then
     fail "Failed to generate extended error in histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
new file mode 100644
index 000000000000..c193dce611a2
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
@@ -0,0 +1,44 @@
+#!/bin/sh
+# description: event trigger - test multiple actions on hist trigger
+
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test multiple actions on hist trigger"
+echo 'wakeup_latency u64 lat; pid_t pid' >> synthetic_events
+TRIGGER1=events/sched/sched_wakeup/trigger
+TRIGGER2=events/sched/sched_switch/trigger
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' > $TRIGGER1
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0 if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,next_pid) if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> $TRIGGER2
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index 8497a376ef9d..12631f0076a1 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -17,14 +17,6 @@ all:
 		fi \
 	done
 
-override define RUN_TESTS
-	@export KSFT_TAP_LEVEL=`echo 1`;
-	@echo "TAP version 13";
-	@echo "selftests: futex";
-	@echo "========================================";
-	@cd $(OUTPUT); ./run.sh
-endef
-
 override define INSTALL_RULE
 	mkdir -p $(INSTALL_PATH)
 	install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
@@ -36,10 +28,6 @@ override define INSTALL_RULE
 	done;
 endef
 
-override define EMIT_TESTS
-	echo "./run.sh"
-endef
-
 override define CLEAN
 	@for DIR in $(SUBDIRS); do		\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
diff --git a/tools/testing/selftests/gpio/gpio-mockup.sh b/tools/testing/selftests/gpio/gpio-mockup.sh
index 183fb932edbd..7f35b9880485 100755
--- a/tools/testing/selftests/gpio/gpio-mockup.sh
+++ b/tools/testing/selftests/gpio/gpio-mockup.sh
@@ -2,10 +2,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
 #exit status
-#1: run as non-root user
+#1: Internal error
 #2: sysfs/debugfs not mount
 #3: insert module fail when gpio-mockup is a module.
-#4: other reason.
+#4: Skip test including run as non-root user.
+#5: other reason.
 
 SYSFS=
 GPIO_SYSFS=
@@ -15,6 +16,9 @@ GPIO_DEBUGFS=
 dev_type=
 module=
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 usage()
 {
 	echo "Usage:"
@@ -34,7 +38,7 @@ prerequisite()
 	msg="skip all tests:"
 	if [ $UID != 0 ]; then
 		echo $msg must be run as root >&2
-		exit 1
+		exit $ksft_skip
 	fi
 	SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
 	if [ ! -d "$SYSFS" ]; then
@@ -73,7 +77,7 @@ remove_module()
 die()
 {
 	remove_module
-	exit 4
+	exit 5
 }
 
 test_chips()
diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c
index d21edea9c560..f6cd03a87493 100644
--- a/tools/testing/selftests/intel_pstate/aperf.c
+++ b/tools/testing/selftests/intel_pstate/aperf.c
@@ -9,6 +9,8 @@
 #include <sys/timeb.h>
 #include <sched.h>
 #include <errno.h>
+#include <string.h>
+#include "../kselftest.h"
 
 void usage(char *name) {
 	printf ("Usage: %s cpunum\n", name);
@@ -41,8 +43,8 @@ int main(int argc, char **argv) {
 	fd = open(msr_file_name, O_RDONLY);
 
 	if (fd == -1) {
-		perror("Failed to open");
-		return 1;
+		printf("/dev/cpu/%d/msr: %s\n", cpu, strerror(errno));
+		return KSFT_SKIP;
 	}
 
 	CPU_ZERO(&cpuset);
diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh
index c670359becc6..e7008f614ad7 100755
--- a/tools/testing/selftests/intel_pstate/run.sh
+++ b/tools/testing/selftests/intel_pstate/run.sh
@@ -30,9 +30,18 @@
 
 EVALUATE_ONLY=0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then
 	echo "$0 # Skipped: Test can only run on x86 architectures."
-	exit 0
+	exit $ksft_skip
+fi
+
+msg="skip all tests:"
+if [ $UID != 0 ] && [ $EVALUATE_ONLY == 0 ]; then
+    echo $msg please run this as root >&2
+    exit $ksft_skip
 fi
 
 max_cpus=$(($(nproc)-1))
@@ -48,11 +57,12 @@ function run_test () {
 
 	echo "sleeping for 5 seconds"
 	sleep 5
-	num_freqs=$(cat /proc/cpuinfo | grep MHz | sort -u | wc -l)
-	if [ $num_freqs -le 2 ]; then
-		cat /proc/cpuinfo | grep MHz | sort -u | tail -1 > /tmp/result.$1
+	grep MHz /proc/cpuinfo | sort -u > /tmp/result.freqs
+	num_freqs=$(wc -l /tmp/result.freqs | awk ' { print $1 } ')
+	if [ $num_freqs -ge 2 ]; then
+		tail -n 1 /tmp/result.freqs > /tmp/result.$1
 	else
-		cat /proc/cpuinfo | grep MHz | sort -u > /tmp/result.$1
+		cp /tmp/result.freqs /tmp/result.$1
 	fi
 	./msr 0 >> /tmp/result.$1
 
@@ -82,32 +92,37 @@ _max_freq=$(cpupower frequency-info -l | tail -1 | awk ' { print $2 } ')
 max_freq=$(($_max_freq / 1000))
 
 
-for freq in `seq $max_freq -100 $min_freq`
+[ $EVALUATE_ONLY -eq 0 ] && for freq in `seq $max_freq -100 $min_freq`
 do
 	echo "Setting maximum frequency to $freq"
 	cpupower frequency-set -g powersave --max=${freq}MHz >& /dev/null
-	[ $EVALUATE_ONLY -eq 0 ] && run_test $freq
+	run_test $freq
 done
 
-echo "=============================================================================="
+[ $EVALUATE_ONLY -eq 0 ] && cpupower frequency-set -g powersave --max=${max_freq}MHz >& /dev/null
 
+echo "========================================================================"
 echo "The marketing frequency of the cpu is $mkt_freq MHz"
 echo "The maximum frequency of the cpu is $max_freq MHz"
 echo "The minimum frequency of the cpu is $min_freq MHz"
 
-cpupower frequency-set -g powersave --max=${max_freq}MHz >& /dev/null
-
 # make a pretty table
-echo "Target      Actual      Difference     MSR(0x199)     max_perf_pct"
+echo "Target Actual Difference MSR(0x199) max_perf_pct" | tr " " "\n" > /tmp/result.tab
 for freq in `seq $max_freq -100 $min_freq`
 do
 	result_freq=$(cat /tmp/result.${freq} | grep "cpu MHz" | awk ' { print $4 } ' | awk -F "." ' { print $1 } ')
 	msr=$(cat /tmp/result.${freq} | grep "msr" | awk ' { print $3 } ')
 	max_perf_pct=$(cat /tmp/result.${freq} | grep "max_perf_pct" | awk ' { print $2 } ' )
-	if [ $result_freq -eq $freq ]; then
-		echo " $freq        $result_freq             0          $msr         $(($max_perf_pct*3300))"
-	else
-		echo " $freq        $result_freq          $(($result_freq-$freq))          $msr          $(($max_perf_pct*$max_freq))"
-	fi
+	cat >> /tmp/result.tab << EOF
+$freq
+$result_freq
+$((result_freq - freq))
+$msr
+$((max_perf_pct * max_freq))
+EOF
 done
+
+# print the table
+pr -aTt -5 < /tmp/result.tab
+
 exit 0
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index ee9382bdfadc..dac927e82336 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -196,10 +196,9 @@ int main(int argc, char **argv)
 	int msg, pid, err;
 	struct msgque_data msgque;
 
-	if (getuid() != 0) {
-		printf("Please run the test as root - Exiting.\n");
-		return ksft_exit_fail();
-	}
+	if (getuid() != 0)
+		return ksft_exit_skip(
+				"Please run the test as root - Exiting.\n");
 
 	msgque.key = ftok(argv[0], 822155650);
 	if (msgque.key == -1) {
diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index 7956ea3be667..0a76314b4414 100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -62,13 +62,16 @@ ALL_TESTS="$ALL_TESTS 0007:5:1"
 ALL_TESTS="$ALL_TESTS 0008:150:1"
 ALL_TESTS="$ALL_TESTS 0009:150:1"
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 test_modprobe()
 {
        if [ ! -d $DIR ]; then
                echo "$0: $DIR not present" >&2
                echo "You must have the following enabled in your kernel:" >&2
                cat $TEST_DIR/config >&2
-               exit 1
+               exit $ksft_skip
        fi
 }
 
@@ -105,12 +108,12 @@ test_reqs()
 {
 	if ! which modprobe 2> /dev/null > /dev/null; then
 		echo "$0: You need modprobe installed" >&2
-		exit 1
+		exit $ksft_skip
 	fi
 
 	if ! which kmod 2> /dev/null > /dev/null; then
 		echo "$0: You need kmod installed" >&2
-		exit 1
+		exit $ksft_skip
 	fi
 
 	# kmod 19 has a bad bug where it returns 0 when modprobe
@@ -124,13 +127,13 @@ test_reqs()
 		echo "$0: You need at least kmod 20" >&2
 		echo "kmod <= 19 is buggy, for details see:" >&2
 		echo "http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2
-		exit 1
+		exit $ksft_skip
 	fi
 
 	uid=$(id -u)
 	if [ $uid -ne 0 ]; then
 		echo $msg must be run as root >&2
-		exit 0
+		exit $ksft_skip
 	fi
 }
 
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index 1b9d8ecdebce..15e6b75fc3a5 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -20,7 +20,7 @@
 #define KSFT_XFAIL 2
 #define KSFT_XPASS 3
 /* Treat skip as pass */
-#define KSFT_SKIP  KSFT_PASS
+#define KSFT_SKIP  4
 
 /* counters */
 struct ksft_count {
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
new file mode 100644
index 000000000000..63fc1ab9248f
--- /dev/null
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -0,0 +1,3 @@
+set_sregs_test
+sync_regs_test
+vmx_tsc_adjust_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index dc44de904797..d9d00319b07c 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -4,17 +4,18 @@ top_srcdir = ../../../../
 UNAME_M := $(shell uname -m)
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86.c
+LIBKVM_x86_64 = lib/x86.c lib/vmx.c
 
 TEST_GEN_PROGS_x86_64 = set_sregs_test
 TEST_GEN_PROGS_x86_64 += sync_regs_test
+TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-CFLAGS += -O2 -g -I$(LINUX_HDR_PATH) -Iinclude -I$(<D)
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 57974ad46373..637b7017b6ee 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -112,24 +112,27 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
 	vm_paddr_t paddr_min, uint32_t memslot);
 
-void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid);
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
 void vcpu_set_cpuid(
 	struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid);
 
-struct kvm_cpuid2 *allocate_kvm_cpuid2(void);
 struct kvm_cpuid_entry2 *
-find_cpuid_index_entry(struct kvm_cpuid2 *cpuid, uint32_t function,
-		       uint32_t index);
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
 
 static inline struct kvm_cpuid_entry2 *
-find_cpuid_entry(struct kvm_cpuid2 *cpuid, uint32_t function)
+kvm_get_supported_cpuid_entry(uint32_t function)
 {
-	return find_cpuid_index_entry(cpuid, function, 0);
+	return kvm_get_supported_cpuid_index(function, 0);
 }
 
 struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code);
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
 
+typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
+				 vm_paddr_t vmxon_paddr,
+				 vm_vaddr_t vmcs_vaddr,
+				 vm_paddr_t vmcs_paddr);
+
 struct kvm_userspace_memory_region *
 kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
 				 uint64_t end);
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 7ab98e41324f..ac53730b30aa 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -19,6 +19,7 @@
 #include <errno.h>
 #include <unistd.h>
 #include <fcntl.h>
+#include "kselftest.h"
 
 ssize_t test_write(int fd, const void *buf, size_t count);
 ssize_t test_read(int fd, void *buf, size_t count);
diff --git a/tools/testing/selftests/kvm/include/vmx.h b/tools/testing/selftests/kvm/include/vmx.h
new file mode 100644
index 000000000000..6ed8499807fd
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/vmx.h
@@ -0,0 +1,494 @@
+/*
+ * tools/testing/selftests/kvm/include/vmx.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_VMX_H
+#define SELFTEST_KVM_VMX_H
+
+#include <stdint.h>
+#include "x86.h"
+
+#define CPUID_VMX_BIT				5
+
+#define CPUID_VMX				(1 << 5)
+
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
+#define CPU_BASED_VIRTUAL_INTR_PENDING		0x00000004
+#define CPU_BASED_USE_TSC_OFFSETING		0x00000008
+#define CPU_BASED_HLT_EXITING			0x00000080
+#define CPU_BASED_INVLPG_EXITING		0x00000200
+#define CPU_BASED_MWAIT_EXITING			0x00000400
+#define CPU_BASED_RDPMC_EXITING			0x00000800
+#define CPU_BASED_RDTSC_EXITING			0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING		0x00008000
+#define CPU_BASED_CR3_STORE_EXITING		0x00010000
+#define CPU_BASED_CR8_LOAD_EXITING		0x00080000
+#define CPU_BASED_CR8_STORE_EXITING		0x00100000
+#define CPU_BASED_TPR_SHADOW			0x00200000
+#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
+#define CPU_BASED_MOV_DR_EXITING		0x00800000
+#define CPU_BASED_UNCOND_IO_EXITING		0x01000000
+#define CPU_BASED_USE_IO_BITMAPS		0x02000000
+#define CPU_BASED_MONITOR_TRAP			0x08000000
+#define CPU_BASED_USE_MSR_BITMAPS		0x10000000
+#define CPU_BASED_MONITOR_EXITING		0x20000000
+#define CPU_BASED_PAUSE_EXITING			0x40000000
+#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS	0x80000000
+
+#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x0401e172
+
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT		0x00000002
+#define SECONDARY_EXEC_DESC			0x00000004
+#define SECONDARY_EXEC_RDTSCP			0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE	0x00000010
+#define SECONDARY_EXEC_ENABLE_VPID		0x00000020
+#define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT	0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY	0x00000200
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
+#define SECONDARY_EXEC_RDRAND_EXITING		0x00000800
+#define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC		0x00002000
+#define SECONDARY_EXEC_SHADOW_VMCS		0x00004000
+#define SECONDARY_EXEC_RDSEED_EXITING		0x00010000
+#define SECONDARY_EXEC_ENABLE_PML		0x00020000
+#define SECONDARY_EPT_VE			0x00040000
+#define SECONDARY_ENABLE_XSAV_RESTORE		0x00100000
+#define SECONDARY_EXEC_TSC_SCALING		0x02000000
+
+#define PIN_BASED_EXT_INTR_MASK			0x00000001
+#define PIN_BASED_NMI_EXITING			0x00000008
+#define PIN_BASED_VIRTUAL_NMIS			0x00000020
+#define PIN_BASED_VMX_PREEMPTION_TIMER		0x00000040
+#define PIN_BASED_POSTED_INTR			0x00000080
+
+#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x00000016
+
+#define VM_EXIT_SAVE_DEBUG_CONTROLS		0x00000004
+#define VM_EXIT_HOST_ADDR_SPACE_SIZE		0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL	0x00001000
+#define VM_EXIT_ACK_INTR_ON_EXIT		0x00008000
+#define VM_EXIT_SAVE_IA32_PAT			0x00040000
+#define VM_EXIT_LOAD_IA32_PAT			0x00080000
+#define VM_EXIT_SAVE_IA32_EFER			0x00100000
+#define VM_EXIT_LOAD_IA32_EFER			0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER	0x00400000
+
+#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR	0x00036dff
+
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS		0x00000004
+#define VM_ENTRY_IA32E_MODE			0x00000200
+#define VM_ENTRY_SMM				0x00000400
+#define VM_ENTRY_DEACT_DUAL_MONITOR		0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL	0x00002000
+#define VM_ENTRY_LOAD_IA32_PAT			0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER			0x00008000
+
+#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR	0x000011ff
+
+#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
+#define VMX_MISC_SAVE_EFER_LMA			0x00000020
+
+#define EXIT_REASON_FAILED_VMENTRY	0x80000000
+#define EXIT_REASON_EXCEPTION_NMI	0
+#define EXIT_REASON_EXTERNAL_INTERRUPT	1
+#define EXIT_REASON_TRIPLE_FAULT	2
+#define EXIT_REASON_PENDING_INTERRUPT	7
+#define EXIT_REASON_NMI_WINDOW		8
+#define EXIT_REASON_TASK_SWITCH		9
+#define EXIT_REASON_CPUID		10
+#define EXIT_REASON_HLT			12
+#define EXIT_REASON_INVD		13
+#define EXIT_REASON_INVLPG		14
+#define EXIT_REASON_RDPMC		15
+#define EXIT_REASON_RDTSC		16
+#define EXIT_REASON_VMCALL		18
+#define EXIT_REASON_VMCLEAR		19
+#define EXIT_REASON_VMLAUNCH		20
+#define EXIT_REASON_VMPTRLD		21
+#define EXIT_REASON_VMPTRST		22
+#define EXIT_REASON_VMREAD		23
+#define EXIT_REASON_VMRESUME		24
+#define EXIT_REASON_VMWRITE		25
+#define EXIT_REASON_VMOFF		26
+#define EXIT_REASON_VMON		27
+#define EXIT_REASON_CR_ACCESS		28
+#define EXIT_REASON_DR_ACCESS		29
+#define EXIT_REASON_IO_INSTRUCTION	30
+#define EXIT_REASON_MSR_READ		31
+#define EXIT_REASON_MSR_WRITE		32
+#define EXIT_REASON_INVALID_STATE	33
+#define EXIT_REASON_MWAIT_INSTRUCTION	36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION	40
+#define EXIT_REASON_MCE_DURING_VMENTRY	41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS		44
+#define EXIT_REASON_EOI_INDUCED		45
+#define EXIT_REASON_EPT_VIOLATION	48
+#define EXIT_REASON_EPT_MISCONFIG	49
+#define EXIT_REASON_INVEPT		50
+#define EXIT_REASON_RDTSCP		51
+#define EXIT_REASON_PREEMPTION_TIMER	52
+#define EXIT_REASON_INVVPID		53
+#define EXIT_REASON_WBINVD		54
+#define EXIT_REASON_XSETBV		55
+#define EXIT_REASON_APIC_WRITE		56
+#define EXIT_REASON_INVPCID		58
+#define EXIT_REASON_PML_FULL		62
+#define EXIT_REASON_XSAVES		63
+#define EXIT_REASON_XRSTORS		64
+#define LAST_EXIT_REASON		64
+
+enum vmcs_field {
+	VIRTUAL_PROCESSOR_ID		= 0x00000000,
+	POSTED_INTR_NV			= 0x00000002,
+	GUEST_ES_SELECTOR		= 0x00000800,
+	GUEST_CS_SELECTOR		= 0x00000802,
+	GUEST_SS_SELECTOR		= 0x00000804,
+	GUEST_DS_SELECTOR		= 0x00000806,
+	GUEST_FS_SELECTOR		= 0x00000808,
+	GUEST_GS_SELECTOR		= 0x0000080a,
+	GUEST_LDTR_SELECTOR		= 0x0000080c,
+	GUEST_TR_SELECTOR		= 0x0000080e,
+	GUEST_INTR_STATUS		= 0x00000810,
+	GUEST_PML_INDEX			= 0x00000812,
+	HOST_ES_SELECTOR		= 0x00000c00,
+	HOST_CS_SELECTOR		= 0x00000c02,
+	HOST_SS_SELECTOR		= 0x00000c04,
+	HOST_DS_SELECTOR		= 0x00000c06,
+	HOST_FS_SELECTOR		= 0x00000c08,
+	HOST_GS_SELECTOR		= 0x00000c0a,
+	HOST_TR_SELECTOR		= 0x00000c0c,
+	IO_BITMAP_A			= 0x00002000,
+	IO_BITMAP_A_HIGH		= 0x00002001,
+	IO_BITMAP_B			= 0x00002002,
+	IO_BITMAP_B_HIGH		= 0x00002003,
+	MSR_BITMAP			= 0x00002004,
+	MSR_BITMAP_HIGH			= 0x00002005,
+	VM_EXIT_MSR_STORE_ADDR		= 0x00002006,
+	VM_EXIT_MSR_STORE_ADDR_HIGH	= 0x00002007,
+	VM_EXIT_MSR_LOAD_ADDR		= 0x00002008,
+	VM_EXIT_MSR_LOAD_ADDR_HIGH	= 0x00002009,
+	VM_ENTRY_MSR_LOAD_ADDR		= 0x0000200a,
+	VM_ENTRY_MSR_LOAD_ADDR_HIGH	= 0x0000200b,
+	PML_ADDRESS			= 0x0000200e,
+	PML_ADDRESS_HIGH		= 0x0000200f,
+	TSC_OFFSET			= 0x00002010,
+	TSC_OFFSET_HIGH			= 0x00002011,
+	VIRTUAL_APIC_PAGE_ADDR		= 0x00002012,
+	VIRTUAL_APIC_PAGE_ADDR_HIGH	= 0x00002013,
+	APIC_ACCESS_ADDR		= 0x00002014,
+	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
+	POSTED_INTR_DESC_ADDR		= 0x00002016,
+	POSTED_INTR_DESC_ADDR_HIGH	= 0x00002017,
+	EPT_POINTER			= 0x0000201a,
+	EPT_POINTER_HIGH		= 0x0000201b,
+	EOI_EXIT_BITMAP0		= 0x0000201c,
+	EOI_EXIT_BITMAP0_HIGH		= 0x0000201d,
+	EOI_EXIT_BITMAP1		= 0x0000201e,
+	EOI_EXIT_BITMAP1_HIGH		= 0x0000201f,
+	EOI_EXIT_BITMAP2		= 0x00002020,
+	EOI_EXIT_BITMAP2_HIGH		= 0x00002021,
+	EOI_EXIT_BITMAP3		= 0x00002022,
+	EOI_EXIT_BITMAP3_HIGH		= 0x00002023,
+	VMREAD_BITMAP			= 0x00002026,
+	VMREAD_BITMAP_HIGH		= 0x00002027,
+	VMWRITE_BITMAP			= 0x00002028,
+	VMWRITE_BITMAP_HIGH		= 0x00002029,
+	XSS_EXIT_BITMAP			= 0x0000202C,
+	XSS_EXIT_BITMAP_HIGH		= 0x0000202D,
+	TSC_MULTIPLIER			= 0x00002032,
+	TSC_MULTIPLIER_HIGH		= 0x00002033,
+	GUEST_PHYSICAL_ADDRESS		= 0x00002400,
+	GUEST_PHYSICAL_ADDRESS_HIGH	= 0x00002401,
+	VMCS_LINK_POINTER		= 0x00002800,
+	VMCS_LINK_POINTER_HIGH		= 0x00002801,
+	GUEST_IA32_DEBUGCTL		= 0x00002802,
+	GUEST_IA32_DEBUGCTL_HIGH	= 0x00002803,
+	GUEST_IA32_PAT			= 0x00002804,
+	GUEST_IA32_PAT_HIGH		= 0x00002805,
+	GUEST_IA32_EFER			= 0x00002806,
+	GUEST_IA32_EFER_HIGH		= 0x00002807,
+	GUEST_IA32_PERF_GLOBAL_CTRL	= 0x00002808,
+	GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
+	GUEST_PDPTR0			= 0x0000280a,
+	GUEST_PDPTR0_HIGH		= 0x0000280b,
+	GUEST_PDPTR1			= 0x0000280c,
+	GUEST_PDPTR1_HIGH		= 0x0000280d,
+	GUEST_PDPTR2			= 0x0000280e,
+	GUEST_PDPTR2_HIGH		= 0x0000280f,
+	GUEST_PDPTR3			= 0x00002810,
+	GUEST_PDPTR3_HIGH		= 0x00002811,
+	GUEST_BNDCFGS			= 0x00002812,
+	GUEST_BNDCFGS_HIGH		= 0x00002813,
+	HOST_IA32_PAT			= 0x00002c00,
+	HOST_IA32_PAT_HIGH		= 0x00002c01,
+	HOST_IA32_EFER			= 0x00002c02,
+	HOST_IA32_EFER_HIGH		= 0x00002c03,
+	HOST_IA32_PERF_GLOBAL_CTRL	= 0x00002c04,
+	HOST_IA32_PERF_GLOBAL_CTRL_HIGH	= 0x00002c05,
+	PIN_BASED_VM_EXEC_CONTROL	= 0x00004000,
+	CPU_BASED_VM_EXEC_CONTROL	= 0x00004002,
+	EXCEPTION_BITMAP		= 0x00004004,
+	PAGE_FAULT_ERROR_CODE_MASK	= 0x00004006,
+	PAGE_FAULT_ERROR_CODE_MATCH	= 0x00004008,
+	CR3_TARGET_COUNT		= 0x0000400a,
+	VM_EXIT_CONTROLS		= 0x0000400c,
+	VM_EXIT_MSR_STORE_COUNT		= 0x0000400e,
+	VM_EXIT_MSR_LOAD_COUNT		= 0x00004010,
+	VM_ENTRY_CONTROLS		= 0x00004012,
+	VM_ENTRY_MSR_LOAD_COUNT		= 0x00004014,
+	VM_ENTRY_INTR_INFO_FIELD	= 0x00004016,
+	VM_ENTRY_EXCEPTION_ERROR_CODE	= 0x00004018,
+	VM_ENTRY_INSTRUCTION_LEN	= 0x0000401a,
+	TPR_THRESHOLD			= 0x0000401c,
+	SECONDARY_VM_EXEC_CONTROL	= 0x0000401e,
+	PLE_GAP				= 0x00004020,
+	PLE_WINDOW			= 0x00004022,
+	VM_INSTRUCTION_ERROR		= 0x00004400,
+	VM_EXIT_REASON			= 0x00004402,
+	VM_EXIT_INTR_INFO		= 0x00004404,
+	VM_EXIT_INTR_ERROR_CODE		= 0x00004406,
+	IDT_VECTORING_INFO_FIELD	= 0x00004408,
+	IDT_VECTORING_ERROR_CODE	= 0x0000440a,
+	VM_EXIT_INSTRUCTION_LEN		= 0x0000440c,
+	VMX_INSTRUCTION_INFO		= 0x0000440e,
+	GUEST_ES_LIMIT			= 0x00004800,
+	GUEST_CS_LIMIT			= 0x00004802,
+	GUEST_SS_LIMIT			= 0x00004804,
+	GUEST_DS_LIMIT			= 0x00004806,
+	GUEST_FS_LIMIT			= 0x00004808,
+	GUEST_GS_LIMIT			= 0x0000480a,
+	GUEST_LDTR_LIMIT		= 0x0000480c,
+	GUEST_TR_LIMIT			= 0x0000480e,
+	GUEST_GDTR_LIMIT		= 0x00004810,
+	GUEST_IDTR_LIMIT		= 0x00004812,
+	GUEST_ES_AR_BYTES		= 0x00004814,
+	GUEST_CS_AR_BYTES		= 0x00004816,
+	GUEST_SS_AR_BYTES		= 0x00004818,
+	GUEST_DS_AR_BYTES		= 0x0000481a,
+	GUEST_FS_AR_BYTES		= 0x0000481c,
+	GUEST_GS_AR_BYTES		= 0x0000481e,
+	GUEST_LDTR_AR_BYTES		= 0x00004820,
+	GUEST_TR_AR_BYTES		= 0x00004822,
+	GUEST_INTERRUPTIBILITY_INFO	= 0x00004824,
+	GUEST_ACTIVITY_STATE		= 0X00004826,
+	GUEST_SYSENTER_CS		= 0x0000482A,
+	VMX_PREEMPTION_TIMER_VALUE	= 0x0000482E,
+	HOST_IA32_SYSENTER_CS		= 0x00004c00,
+	CR0_GUEST_HOST_MASK		= 0x00006000,
+	CR4_GUEST_HOST_MASK		= 0x00006002,
+	CR0_READ_SHADOW			= 0x00006004,
+	CR4_READ_SHADOW			= 0x00006006,
+	CR3_TARGET_VALUE0		= 0x00006008,
+	CR3_TARGET_VALUE1		= 0x0000600a,
+	CR3_TARGET_VALUE2		= 0x0000600c,
+	CR3_TARGET_VALUE3		= 0x0000600e,
+	EXIT_QUALIFICATION		= 0x00006400,
+	GUEST_LINEAR_ADDRESS		= 0x0000640a,
+	GUEST_CR0			= 0x00006800,
+	GUEST_CR3			= 0x00006802,
+	GUEST_CR4			= 0x00006804,
+	GUEST_ES_BASE			= 0x00006806,
+	GUEST_CS_BASE			= 0x00006808,
+	GUEST_SS_BASE			= 0x0000680a,
+	GUEST_DS_BASE			= 0x0000680c,
+	GUEST_FS_BASE			= 0x0000680e,
+	GUEST_GS_BASE			= 0x00006810,
+	GUEST_LDTR_BASE			= 0x00006812,
+	GUEST_TR_BASE			= 0x00006814,
+	GUEST_GDTR_BASE			= 0x00006816,
+	GUEST_IDTR_BASE			= 0x00006818,
+	GUEST_DR7			= 0x0000681a,
+	GUEST_RSP			= 0x0000681c,
+	GUEST_RIP			= 0x0000681e,
+	GUEST_RFLAGS			= 0x00006820,
+	GUEST_PENDING_DBG_EXCEPTIONS	= 0x00006822,
+	GUEST_SYSENTER_ESP		= 0x00006824,
+	GUEST_SYSENTER_EIP		= 0x00006826,
+	HOST_CR0			= 0x00006c00,
+	HOST_CR3			= 0x00006c02,
+	HOST_CR4			= 0x00006c04,
+	HOST_FS_BASE			= 0x00006c06,
+	HOST_GS_BASE			= 0x00006c08,
+	HOST_TR_BASE			= 0x00006c0a,
+	HOST_GDTR_BASE			= 0x00006c0c,
+	HOST_IDTR_BASE			= 0x00006c0e,
+	HOST_IA32_SYSENTER_ESP		= 0x00006c10,
+	HOST_IA32_SYSENTER_EIP		= 0x00006c12,
+	HOST_RSP			= 0x00006c14,
+	HOST_RIP			= 0x00006c16,
+};
+
+struct vmx_msr_entry {
+	uint32_t index;
+	uint32_t reserved;
+	uint64_t value;
+} __attribute__ ((aligned(16)));
+
+static inline int vmxon(uint64_t phys)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(phys)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline void vmxoff(void)
+{
+	__asm__ __volatile__("vmxoff");
+}
+
+static inline int vmclear(uint64_t vmcs_pa)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(vmcs_pa)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline int vmptrld(uint64_t vmcs_pa)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(vmcs_pa)
+		: "cc", "memory");
+
+	return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmlaunch.
+ */
+static inline int vmlaunch(void)
+{
+	int ret;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "vmwrite %%rsp, %[host_rsp];"
+			     "lea 1f(%%rip), %%rax;"
+			     "vmwrite %%rax, %[host_rip];"
+			     "vmlaunch;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"((uint64_t)HOST_RSP),
+			       [host_rip]"r"((uint64_t)HOST_RIP)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int vmresume(void)
+{
+	int ret;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "vmwrite %%rsp, %[host_rsp];"
+			     "lea 1f(%%rip), %%rax;"
+			     "vmwrite %%rax, %[host_rip];"
+			     "vmresume;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"((uint64_t)HOST_RSP),
+			       [host_rip]"r"((uint64_t)HOST_RIP)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+static inline int vmread(uint64_t encoding, uint64_t *value)
+{
+	uint64_t tmp;
+	uint8_t ret;
+
+	__asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
+		: [value]"=rm"(tmp), [ret]"=rm"(ret)
+		: [encoding]"r"(encoding)
+		: "cc", "memory");
+
+	*value = tmp;
+	return ret;
+}
+
+/*
+ * A wrapper around vmread that ignores errors and returns zero if the
+ * vmread instruction fails.
+ */
+static inline uint64_t vmreadz(uint64_t encoding)
+{
+	uint64_t value = 0;
+	vmread(encoding, &value);
+	return value;
+}
+
+static inline int vmwrite(uint64_t encoding, uint64_t value)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [value]"rm"(value), [encoding]"r"(encoding)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline uint32_t vmcs_revision(void)
+{
+	return rdmsr(MSR_IA32_VMX_BASIC);
+}
+
+void prepare_for_vmx_operation(void);
+void prepare_vmcs(void *guest_rip, void *guest_rsp);
+struct kvm_vm *vm_create_default_vmx(uint32_t vcpuid,
+				     vmx_guest_code_t guest_code);
+
+#endif /* !SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index c9f5b7d4ce38..cd01144d27c8 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -13,6 +13,8 @@
 #include <execinfo.h>
 #include <sys/syscall.h>
 
+#include "../../kselftest.h"
+
 /* Dumps the current stack trace to stderr. */
 static void __attribute__((noinline)) test_dump_stack(void);
 static void test_dump_stack(void)
@@ -70,8 +72,9 @@ test_assert(bool exp, const char *exp_str,
 
 		fprintf(stderr, "==== Test Assertion Failure ====\n"
 			"  %s:%u: %s\n"
-			"  pid=%d tid=%d\n",
-			file, line, exp_str, getpid(), gettid());
+			"  pid=%d tid=%d - %s\n",
+			file, line, exp_str, getpid(), gettid(),
+			strerror(errno));
 		test_dump_stack();
 		if (fmt) {
 			fputs("  ", stderr);
@@ -80,6 +83,8 @@ test_assert(bool exp, const char *exp_str,
 		}
 		va_end(ap);
 
+		if (errno == EACCES)
+			ksft_exit_skip("Access denied - Exiting.\n");
 		exit(254);
 	}
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 7ca1bb40c498..37e2a787d2fc 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -50,8 +50,8 @@ int kvm_check_cap(long cap)
 	int kvm_fd;
 
 	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
-		KVM_DEV_PATH, kvm_fd, errno);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
 
 	ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
 	TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
@@ -91,8 +91,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 
 	vm->mode = mode;
 	kvm_fd = open(KVM_DEV_PATH, perm);
-	TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
-		KVM_DEV_PATH, kvm_fd, errno);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
 
 	/* Create VM. */
 	vm->fd = ioctl(kvm_fd, KVM_CREATE_VM, NULL);
@@ -378,7 +378,7 @@ int kvm_memcmp_hva_gva(void *hva,
  * complicated. This function uses a reasonable default length for
  * the array and performs the appropriate allocation.
  */
-struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
+static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
 {
 	struct kvm_cpuid2 *cpuid;
 	int nent = 100;
@@ -402,26 +402,31 @@ struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
  * Input Args: None
  *
  * Output Args:
- *   cpuid - The supported KVM CPUID
  *
- * Return: void
+ * Return: The supported KVM CPUID
  *
  * Get the guest CPUID supported by KVM.
  */
-void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid)
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
 {
+	static struct kvm_cpuid2 *cpuid;
 	int ret;
 	int kvm_fd;
 
+	if (cpuid)
+		return cpuid;
+
+	cpuid = allocate_kvm_cpuid2();
 	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
-		KVM_DEV_PATH, kvm_fd, errno);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
 
 	ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
 	TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
 		    ret, errno);
 
 	close(kvm_fd);
+	return cpuid;
 }
 
 /* Locate a cpuid entry.
@@ -435,12 +440,13 @@ void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid)
  * Return: A pointer to the cpuid entry. Never returns NULL.
  */
 struct kvm_cpuid_entry2 *
-find_cpuid_index_entry(struct kvm_cpuid2 *cpuid, uint32_t function,
-		       uint32_t index)
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
 {
+	struct kvm_cpuid2 *cpuid;
 	struct kvm_cpuid_entry2 *entry = NULL;
 	int i;
 
+	cpuid = kvm_get_supported_cpuid();
 	for (i = 0; i < cpuid->nent; i++) {
 		if (cpuid->entries[i].function == function &&
 		    cpuid->entries[i].index == index) {
@@ -669,8 +675,8 @@ static int vcpu_mmap_sz(void)
 	int dev_fd, ret;
 
 	dev_fd = open(KVM_DEV_PATH, O_RDONLY);
-	TEST_ASSERT(dev_fd >= 0, "%s open %s failed, rc: %i errno: %i",
-		__func__, KVM_DEV_PATH, dev_fd, errno);
+	if (dev_fd < 0)
+		exit(KSFT_SKIP);
 
 	ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
 	TEST_ASSERT(ret >= sizeof(struct kvm_run),
@@ -1435,7 +1441,7 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
 	sparsebit_idx_t pg;
 
 	TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
-		"not divisable by page size.\n"
+		"not divisible by page size.\n"
 		"  paddr_min: 0x%lx page_size: 0x%x",
 		paddr_min, vm->page_size);
 
diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c
index 0c5cf3e0cb6f..b132bc95d183 100644
--- a/tools/testing/selftests/kvm/lib/sparsebit.c
+++ b/tools/testing/selftests/kvm/lib/sparsebit.c
@@ -121,7 +121,7 @@
  *     avoided by moving the setting of the nodes mask bits into
  *     the previous nodes num_after setting.
  *
- *   + Node starting index is evenly divisable by the number of bits
+ *   + Node starting index is evenly divisible by the number of bits
  *     within a nodes mask member.
  *
  *   + Nodes never represent a range of bits that wrap around the
@@ -1741,7 +1741,7 @@ void sparsebit_validate_internal(struct sparsebit *s)
 
 		/* Validate node index is divisible by the mask size */
 		if (nodep->idx % MASK_BITS) {
-			fprintf(stderr, "Node index not divisable by "
+			fprintf(stderr, "Node index not divisible by "
 				"mask size,\n"
 				"  nodep: %p nodep->idx: 0x%lx "
 				"MASK_BITS: %lu\n",
diff --git a/tools/testing/selftests/kvm/lib/vmx.c b/tools/testing/selftests/kvm/lib/vmx.c
new file mode 100644
index 000000000000..0231bc0aae7b
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/vmx.c
@@ -0,0 +1,243 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+#include "vmx.h"
+
+/* Create a default VM for VMX tests.
+ *
+ * Input Args:
+ *   vcpuid - The id of the single VCPU to add to the VM.
+ *   guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *
+vm_create_default_vmx(uint32_t vcpuid, vmx_guest_code_t guest_code)
+{
+	struct kvm_cpuid2 *cpuid;
+	struct kvm_vm *vm;
+	vm_vaddr_t vmxon_vaddr;
+	vm_paddr_t vmxon_paddr;
+	vm_vaddr_t vmcs_vaddr;
+	vm_paddr_t vmcs_paddr;
+
+	vm = vm_create_default(vcpuid, (void *) guest_code);
+
+	/* Enable nesting in CPUID */
+	vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+
+	/* Setup of a region of guest memory for the vmxon region. */
+	vmxon_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0);
+	vmxon_paddr = addr_gva2gpa(vm, vmxon_vaddr);
+
+	/* Setup of a region of guest memory for a vmcs. */
+	vmcs_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0);
+	vmcs_paddr = addr_gva2gpa(vm, vmcs_vaddr);
+
+	vcpu_args_set(vm, vcpuid, 4, vmxon_vaddr, vmxon_paddr, vmcs_vaddr,
+		      vmcs_paddr);
+
+	return vm;
+}
+
+void prepare_for_vmx_operation(void)
+{
+	uint64_t feature_control;
+	uint64_t required;
+	unsigned long cr0;
+	unsigned long cr4;
+
+	/*
+	 * Ensure bits in CR0 and CR4 are valid in VMX operation:
+	 * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
+	 * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
+	 */
+	__asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
+	cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
+	cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
+	__asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
+
+	__asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
+	cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
+	cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
+	/* Enable VMX operation */
+	cr4 |= X86_CR4_VMXE;
+	__asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
+
+	/*
+	 * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
+	 *  Bit 0: Lock bit. If clear, VMXON causes a #GP.
+	 *  Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
+	 *    outside of SMX causes a #GP.
+	 */
+	required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	required |= FEATURE_CONTROL_LOCKED;
+	feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL);
+	if ((feature_control & required) != required)
+		wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required);
+}
+
+/*
+ * Initialize the control fields to the most basic settings possible.
+ */
+static inline void init_vmcs_control_fields(void)
+{
+	vmwrite(VIRTUAL_PROCESSOR_ID, 0);
+	vmwrite(POSTED_INTR_NV, 0);
+
+	vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PINBASED_CTLS));
+	vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PROCBASED_CTLS));
+	vmwrite(EXCEPTION_BITMAP, 0);
+	vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
+	vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
+	vmwrite(CR3_TARGET_COUNT, 0);
+	vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
+		VM_EXIT_HOST_ADDR_SPACE_SIZE);	  /* 64-bit host */
+	vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
+	vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
+		VM_ENTRY_IA32E_MODE);		  /* 64-bit guest */
+	vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
+	vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
+	vmwrite(TPR_THRESHOLD, 0);
+	vmwrite(SECONDARY_VM_EXEC_CONTROL, 0);
+
+	vmwrite(CR0_GUEST_HOST_MASK, 0);
+	vmwrite(CR4_GUEST_HOST_MASK, 0);
+	vmwrite(CR0_READ_SHADOW, get_cr0());
+	vmwrite(CR4_READ_SHADOW, get_cr4());
+}
+
+/*
+ * Initialize the host state fields based on the current host state, with
+ * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
+ * or vmresume.
+ */
+static inline void init_vmcs_host_state(void)
+{
+	uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
+
+	vmwrite(HOST_ES_SELECTOR, get_es());
+	vmwrite(HOST_CS_SELECTOR, get_cs());
+	vmwrite(HOST_SS_SELECTOR, get_ss());
+	vmwrite(HOST_DS_SELECTOR, get_ds());
+	vmwrite(HOST_FS_SELECTOR, get_fs());
+	vmwrite(HOST_GS_SELECTOR, get_gs());
+	vmwrite(HOST_TR_SELECTOR, get_tr());
+
+	if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
+		vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
+	if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
+		vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
+	if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+		vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
+			rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
+
+	vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
+
+	vmwrite(HOST_CR0, get_cr0());
+	vmwrite(HOST_CR3, get_cr3());
+	vmwrite(HOST_CR4, get_cr4());
+	vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
+	vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
+	vmwrite(HOST_TR_BASE,
+		get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
+	vmwrite(HOST_GDTR_BASE, get_gdt_base());
+	vmwrite(HOST_IDTR_BASE, get_idt_base());
+	vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
+	vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
+}
+
+/*
+ * Initialize the guest state fields essentially as a clone of
+ * the host state fields. Some host state fields have fixed
+ * values, and we set the corresponding guest state fields accordingly.
+ */
+static inline void init_vmcs_guest_state(void *rip, void *rsp)
+{
+	vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
+	vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
+	vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
+	vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
+	vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
+	vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
+	vmwrite(GUEST_LDTR_SELECTOR, 0);
+	vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
+	vmwrite(GUEST_INTR_STATUS, 0);
+	vmwrite(GUEST_PML_INDEX, 0);
+
+	vmwrite(VMCS_LINK_POINTER, -1ll);
+	vmwrite(GUEST_IA32_DEBUGCTL, 0);
+	vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
+	vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
+	vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
+		vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
+
+	vmwrite(GUEST_ES_LIMIT, -1);
+	vmwrite(GUEST_CS_LIMIT, -1);
+	vmwrite(GUEST_SS_LIMIT, -1);
+	vmwrite(GUEST_DS_LIMIT, -1);
+	vmwrite(GUEST_FS_LIMIT, -1);
+	vmwrite(GUEST_GS_LIMIT, -1);
+	vmwrite(GUEST_LDTR_LIMIT, -1);
+	vmwrite(GUEST_TR_LIMIT, 0x67);
+	vmwrite(GUEST_GDTR_LIMIT, 0xffff);
+	vmwrite(GUEST_IDTR_LIMIT, 0xffff);
+	vmwrite(GUEST_ES_AR_BYTES,
+		vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
+	vmwrite(GUEST_SS_AR_BYTES, 0xc093);
+	vmwrite(GUEST_DS_AR_BYTES,
+		vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_FS_AR_BYTES,
+		vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_GS_AR_BYTES,
+		vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
+	vmwrite(GUEST_TR_AR_BYTES, 0x8b);
+	vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
+	vmwrite(GUEST_ACTIVITY_STATE, 0);
+	vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
+	vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
+
+	vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
+	vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
+	vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
+	vmwrite(GUEST_ES_BASE, 0);
+	vmwrite(GUEST_CS_BASE, 0);
+	vmwrite(GUEST_SS_BASE, 0);
+	vmwrite(GUEST_DS_BASE, 0);
+	vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
+	vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
+	vmwrite(GUEST_LDTR_BASE, 0);
+	vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
+	vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
+	vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
+	vmwrite(GUEST_DR7, 0x400);
+	vmwrite(GUEST_RSP, (uint64_t)rsp);
+	vmwrite(GUEST_RIP, (uint64_t)rip);
+	vmwrite(GUEST_RFLAGS, 2);
+	vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+	vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
+	vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
+}
+
+void prepare_vmcs(void *guest_rip, void *guest_rsp)
+{
+	init_vmcs_control_fields();
+	init_vmcs_host_state();
+	init_vmcs_guest_state(guest_rip, guest_rsp);
+}
diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/sync_regs_test.c
index 428e9473f5e2..eae1ece3c31b 100644
--- a/tools/testing/selftests/kvm/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/sync_regs_test.c
@@ -85,6 +85,9 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left,
 {
 }
 
+#define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
+#define INVALID_SYNC_FIELD 0x80000000
+
 int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
@@ -98,9 +101,14 @@ int main(int argc, char *argv[])
 	setbuf(stdout, NULL);
 
 	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
-	TEST_ASSERT((unsigned long)cap == KVM_SYNC_X86_VALID_FIELDS,
-		    "KVM_CAP_SYNC_REGS (0x%x) != KVM_SYNC_X86_VALID_FIELDS (0x%lx)\n",
-		    cap, KVM_SYNC_X86_VALID_FIELDS);
+	if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
+		fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+	if ((cap & INVALID_SYNC_FIELD) != 0) {
+		fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+		exit(KSFT_SKIP);
+	}
 
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, guest_code);
@@ -108,7 +116,14 @@ int main(int argc, char *argv[])
 	run = vcpu_state(vm, VCPU_ID);
 
 	/* Request reading invalid register set from VCPU. */
-	run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS << 1;
+	run->kvm_valid_regs = INVALID_SYNC_FIELD;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
 		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
@@ -116,7 +131,14 @@ int main(int argc, char *argv[])
 	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
 
 	/* Request setting invalid register set into VCPU. */
-	run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS << 1;
+	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
 		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
@@ -125,7 +147,7 @@ int main(int argc, char *argv[])
 
 	/* Request and verify all valid register sets. */
 	/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
-	run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 		    "Unexpected exit reason: %u (%s),\n",
@@ -146,7 +168,7 @@ int main(int argc, char *argv[])
 	run->s.regs.sregs.apic_base = 1 << 11;
 	/* TODO run->s.regs.events.XYZ = ABC; */
 
-	run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
@@ -172,7 +194,7 @@ int main(int argc, char *argv[])
 	/* Clear kvm_dirty_regs bits, verify new s.regs values are
 	 * overwritten with existing guest values.
 	 */
-	run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = 0;
 	run->s.regs.regs.r11 = 0xDEADBEEF;
 	rv = _vcpu_run(vm, VCPU_ID);
@@ -211,7 +233,7 @@ int main(int argc, char *argv[])
 	 * with kvm_sync_regs values.
 	 */
 	run->kvm_valid_regs = 0;
-	run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS;
+	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
 	run->s.regs.regs.r11 = 0xBBBB;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
new file mode 100644
index 000000000000..d7cb7944a42e
--- /dev/null
+++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
@@ -0,0 +1,233 @@
+/*
+ * gtests/tests/vmx_tsc_adjust_test.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ *
+ * IA32_TSC_ADJUST test
+ *
+ * According to the SDM, "if an execution of WRMSR to the
+ * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
+ * the logical processor also adds (or subtracts) value X from the
+ * IA32_TSC_ADJUST MSR.
+ *
+ * Note that when L1 doesn't intercept writes to IA32_TSC, a
+ * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
+ * value.
+ *
+ * This test verifies that this unusual case is handled correctly.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "../kselftest.h"
+
+#ifndef MSR_IA32_TSC_ADJUST
+#define MSR_IA32_TSC_ADJUST 0x3b
+#endif
+
+#define PAGE_SIZE	4096
+#define VCPU_ID		5
+
+#define TSC_ADJUST_VALUE (1ll << 32)
+#define TSC_OFFSET_VALUE -(1ll << 48)
+
+enum {
+	PORT_ABORT = 0x1000,
+	PORT_REPORT,
+	PORT_DONE,
+};
+
+struct vmx_page {
+	vm_vaddr_t virt;
+	vm_paddr_t phys;
+};
+
+enum {
+	VMXON_PAGE = 0,
+	VMCS_PAGE,
+	MSR_BITMAP_PAGE,
+
+	NUM_VMX_PAGES,
+};
+
+struct kvm_single_msr {
+	struct kvm_msrs header;
+	struct kvm_msr_entry entry;
+} __attribute__((packed));
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+/* Array of vmx_page descriptors that is shared with the guest. */
+struct vmx_page *vmx_pages;
+
+#define exit_to_l0(_port, _arg) do_exit_to_l0(_port, (unsigned long) (_arg))
+static void do_exit_to_l0(uint16_t port, unsigned long arg)
+{
+	__asm__ __volatile__("in %[port], %%al"
+		:
+		: [port]"d"(port), "D"(arg)
+		: "rax");
+}
+
+
+#define GUEST_ASSERT(_condition) do {					     \
+	if (!(_condition))						     \
+		exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition); \
+} while (0)
+
+static void check_ia32_tsc_adjust(int64_t max)
+{
+	int64_t adjust;
+
+	adjust = rdmsr(MSR_IA32_TSC_ADJUST);
+	exit_to_l0(PORT_REPORT, adjust);
+	GUEST_ASSERT(adjust <= max);
+}
+
+static void l2_guest_code(void)
+{
+	uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
+
+	wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
+	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+	/* Exit to L1 */
+	__asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_page *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	uint32_t control;
+	uintptr_t save_cr3;
+
+	GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
+	wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
+	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+
+	prepare_for_vmx_operation();
+
+	/* Enter VMX root operation. */
+	*(uint32_t *)vmx_pages[VMXON_PAGE].virt = vmcs_revision();
+	GUEST_ASSERT(!vmxon(vmx_pages[VMXON_PAGE].phys));
+
+	/* Load a VMCS. */
+	*(uint32_t *)vmx_pages[VMCS_PAGE].virt = vmcs_revision();
+	GUEST_ASSERT(!vmclear(vmx_pages[VMCS_PAGE].phys));
+	GUEST_ASSERT(!vmptrld(vmx_pages[VMCS_PAGE].phys));
+
+	/* Prepare the VMCS for L2 execution. */
+	prepare_vmcs(l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
+	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+	vmwrite(MSR_BITMAP, vmx_pages[MSR_BITMAP_PAGE].phys);
+	vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
+
+	/* Jump into L2.  First, test failure to load guest CR3.  */
+	save_cr3 = vmreadz(GUEST_CR3);
+	vmwrite(GUEST_CR3, -1ull);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
+		     (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
+	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+	vmwrite(GUEST_CR3, save_cr3);
+
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+	exit_to_l0(PORT_DONE, 0);
+}
+
+static void allocate_vmx_page(struct vmx_page *page)
+{
+	vm_vaddr_t virt;
+
+	virt = vm_vaddr_alloc(vm, PAGE_SIZE, 0, 0, 0);
+	memset(addr_gva2hva(vm, virt), 0, PAGE_SIZE);
+
+	page->virt = virt;
+	page->phys = addr_gva2gpa(vm, virt);
+}
+
+static vm_vaddr_t allocate_vmx_pages(void)
+{
+	vm_vaddr_t vmx_pages_vaddr;
+	int i;
+
+	vmx_pages_vaddr = vm_vaddr_alloc(
+		vm, sizeof(struct vmx_page) * NUM_VMX_PAGES, 0, 0, 0);
+
+	vmx_pages = (void *) addr_gva2hva(vm, vmx_pages_vaddr);
+
+	for (i = 0; i < NUM_VMX_PAGES; i++)
+		allocate_vmx_page(&vmx_pages[i]);
+
+	return vmx_pages_vaddr;
+}
+
+void report(int64_t val)
+{
+	printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+	       val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t vmx_pages_vaddr;
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	if (!(entry->ecx & CPUID_VMX)) {
+		fprintf(stderr, "nested VMX not enabled, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code);
+
+	/* Allocate VMX pages and shared descriptors (vmx_pages). */
+	vmx_pages_vaddr = allocate_vmx_pages();
+	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_vaddr);
+
+	for (;;) {
+		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+		struct kvm_regs regs;
+
+		vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Got exit_reason other than KVM_EXIT_IO: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		vcpu_regs_get(vm, VCPU_ID, &regs);
+
+		switch (run->io.port) {
+		case PORT_ABORT:
+			TEST_ASSERT(false, "%s", (const char *) regs.rdi);
+			/* NOT REACHED */
+		case PORT_REPORT:
+			report(regs.rdi);
+			break;
+		case PORT_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
+		}
+	}
+
+	kvm_vm_free(vm);
+done:
+	return 0;
+}
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 195e9d4739a9..6466294366dc 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -19,25 +19,43 @@ TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 
 .ONESHELL:
+define RUN_TEST_PRINT_RESULT
+	TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST";	\
+	echo $$TEST_HDR_MSG;					\
+	echo "========================================";	\
+	if [ ! -x $$TEST ]; then	\
+		echo "$$TEST_HDR_MSG: Warning: file $$BASENAME_TEST is not executable, correct this.";\
+		echo "not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]"; \
+	else					\
+		cd `dirname $$TEST` > /dev/null; \
+		if [ "X$(summary)" != "X" ]; then	\
+			(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && \
+			echo "ok 1..$$test_num $$TEST_HDR_MSG [PASS]") || \
+			(if [ $$? -eq $$skip ]; then	\
+				echo "not ok 1..$$test_num $$TEST_HDR_MSG [SKIP]";				\
+			else echo "not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]";					\
+			fi;)			\
+		else				\
+			(./$$BASENAME_TEST &&	\
+			echo "ok 1..$$test_num $$TEST_HDR_MSG [PASS]") ||						\
+			(if [ $$? -eq $$skip ]; then \
+				echo "not ok 1..$$test_num $$TEST_HDR_MSG [SKIP]"; \
+			else echo "not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]";				\
+			fi;)		\
+		fi;				\
+		cd - > /dev/null;		\
+	fi;
+endef
+
 define RUN_TESTS
-	@export KSFT_TAP_LEVEL=`echo 1`;
-	@test_num=`echo 0`;
-	@echo "TAP version 13";
-	@for TEST in $(1); do				\
+	@export KSFT_TAP_LEVEL=`echo 1`;		\
+	test_num=`echo 0`;				\
+	skip=`echo 4`;					\
+	echo "TAP version 13";				\
+	for TEST in $(1); do				\
 		BASENAME_TEST=`basename $$TEST`;	\
 		test_num=`echo $$test_num+1 | bc`;	\
-		echo "selftests: $$BASENAME_TEST";	\
-		echo "========================================";	\
-		if [ ! -x $$TEST ]; then	\
-			echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\
-			echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \
-		else					\
-		if [ "X$(summary)" != "X" ]; then		\
-				cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests:  $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
-			else				\
-				cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests:  $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
-			fi;				\
-		fi;					\
+		$(call RUN_TEST_PRINT_RESULT,$(TEST),$(BASENAME_TEST),$(test_num),$(skip))						\
 	done;
 endef
 
@@ -76,9 +94,18 @@ else
 endif
 
 define EMIT_TESTS
-	@for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \
+	@test_num=`echo 0`;				\
+	for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \
 		BASENAME_TEST=`basename $$TEST`;	\
-		echo "(./$$BASENAME_TEST >> \$$OUTPUT 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
+		test_num=`echo $$test_num+1 | bc`;	\
+		TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST";	\
+		echo "echo $$TEST_HDR_MSG";	\
+		if [ ! -x $$TEST ]; then	\
+			echo "echo \"$$TEST_HDR_MSG: Warning: file $$BASENAME_TEST is not executable, correct this.\"";		\
+			echo "echo \"not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]\""; \
+		else
+			echo "(./$$BASENAME_TEST >> \$$OUTPUT 2>&1 && echo \"ok 1..$$test_num $$TEST_HDR_MSG [PASS]\") || (if [ \$$? -eq \$$skip ]; then echo \"not ok 1..$$test_num $$TEST_HDR_MSG [SKIP]\"; else echo \"not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]\"; fi;)"; \
+		fi;		\
 	done;
 endef
 
diff --git a/tools/testing/selftests/lib/Makefile b/tools/testing/selftests/lib/Makefile
index 08360060ab14..70d5711e3ac8 100644
--- a/tools/testing/selftests/lib/Makefile
+++ b/tools/testing/selftests/lib/Makefile
@@ -3,6 +3,6 @@
 # No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
 all:
 
-TEST_PROGS := printf.sh bitmap.sh
+TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/lib/bitmap.sh b/tools/testing/selftests/lib/bitmap.sh
index 4dee4d2a8bbe..5a90006d1aea 100755
--- a/tools/testing/selftests/lib/bitmap.sh
+++ b/tools/testing/selftests/lib/bitmap.sh
@@ -1,9 +1,13 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 # Runs bitmap infrastructure tests using test_bitmap kernel module
 if ! /sbin/modprobe -q -n test_bitmap; then
-	echo "bitmap: [SKIP]"
-	exit 77
+	echo "bitmap: module test_bitmap is not found [SKIP]"
+	exit $ksft_skip
 fi
 
 if /sbin/modprobe -q test_bitmap; then
diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh
index b363994e5e11..78e7483c8d60 100755
--- a/tools/testing/selftests/lib/prime_numbers.sh
+++ b/tools/testing/selftests/lib/prime_numbers.sh
@@ -2,9 +2,12 @@
 # SPDX-License-Identifier: GPL-2.0
 # Checks fast/slow prime_number generation for inconsistencies
 
-if ! /sbin/modprobe -q -r prime_numbers; then
-	echo "prime_numbers: [SKIP]"
-	exit 77
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if ! /sbin/modprobe -q -n prime_numbers; then
+	echo "prime_numbers: module prime_numbers is not found [SKIP]"
+	exit $ksft_skip
 fi
 
 if /sbin/modprobe -q prime_numbers selftest=65536; then
diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh
index 0c37377fd7d4..45a23e2d64ad 100755
--- a/tools/testing/selftests/lib/printf.sh
+++ b/tools/testing/selftests/lib/printf.sh
@@ -1,9 +1,13 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # Runs printf infrastructure using test_printf kernel module
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 if ! /sbin/modprobe -q -n test_printf; then
-	echo "printf: [SKIP]"
-	exit 77
+	echo "printf: module test_printf is not found [SKIP]"
+	exit $ksft_skip
 fi
 
 if /sbin/modprobe -q test_printf; then
diff --git a/tools/testing/selftests/locking/Makefile b/tools/testing/selftests/locking/Makefile
new file mode 100644
index 000000000000..6e7761ab3536
--- /dev/null
+++ b/tools/testing/selftests/locking/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for locking/ww_mutx selftests
+
+# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
+all:
+
+TEST_PROGS := ww_mutex.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/locking/ww_mutex.sh b/tools/testing/selftests/locking/ww_mutex.sh
index 2c3d6b1878c2..91e4ac7566af 100644..100755
--- a/tools/testing/selftests/locking/ww_mutex.sh
+++ b/tools/testing/selftests/locking/ww_mutex.sh
@@ -1,6 +1,14 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 # Runs API tests for struct ww_mutex (Wait/Wound mutexes)
+if ! /sbin/modprobe -q -n test-ww_mutex; then
+	echo "ww_mutex: module test-ww_mutex is not found [SKIP]"
+	exit $ksft_skip
+fi
 
 if /sbin/modprobe -q test-ww_mutex; then
        /sbin/modprobe -q -r test-ww_mutex
diff --git a/tools/testing/selftests/media_tests/Makefile b/tools/testing/selftests/media_tests/Makefile
index c82cec2497de..60826d7d37d4 100644
--- a/tools/testing/selftests/media_tests/Makefile
+++ b/tools/testing/selftests/media_tests/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+#
+CFLAGS += -I../ -I../../../../usr/include/
 TEST_GEN_PROGS := media_device_test media_device_open video_device_test
-all: $(TEST_GEN_PROGS)
 
 include ../lib.mk
diff --git a/tools/testing/selftests/media_tests/media_device_open.c b/tools/testing/selftests/media_tests/media_device_open.c
index a5ce5434bafd..93183a37b133 100644
--- a/tools/testing/selftests/media_tests/media_device_open.c
+++ b/tools/testing/selftests/media_tests/media_device_open.c
@@ -34,6 +34,8 @@
 #include <sys/stat.h>
 #include <linux/media.h>
 
+#include "../kselftest.h"
+
 int main(int argc, char **argv)
 {
 	int opt;
@@ -61,10 +63,8 @@ int main(int argc, char **argv)
 		}
 	}
 
-	if (getuid() != 0) {
-		printf("Please run the test as root - Exiting.\n");
-		exit(-1);
-	}
+	if (getuid() != 0)
+		ksft_exit_skip("Please run the test as root - Exiting.\n");
 
 	/* Open Media device and keep it open */
 	fd = open(media_device, O_RDWR);
diff --git a/tools/testing/selftests/media_tests/media_device_test.c b/tools/testing/selftests/media_tests/media_device_test.c
index 421a367e4bb3..4b9953359e40 100644
--- a/tools/testing/selftests/media_tests/media_device_test.c
+++ b/tools/testing/selftests/media_tests/media_device_test.c
@@ -39,6 +39,8 @@
 #include <time.h>
 #include <linux/media.h>
 
+#include "../kselftest.h"
+
 int main(int argc, char **argv)
 {
 	int opt;
@@ -66,10 +68,8 @@ int main(int argc, char **argv)
 		}
 	}
 
-	if (getuid() != 0) {
-		printf("Please run the test as root - Exiting.\n");
-		exit(-1);
-	}
+	if (getuid() != 0)
+		ksft_exit_skip("Please run the test as root - Exiting.\n");
 
 	/* Generate random number of interations */
 	srand((unsigned int) time(NULL));
@@ -88,7 +88,7 @@ int main(int argc, char **argv)
 	       "other Oops in the dmesg. Enable KaSan kernel\n"
 	       "config option for use-after-free error detection.\n\n");
 
-	printf("Running test for %d iternations\n", count);
+	printf("Running test for %d iterations\n", count);
 
 	while (count > 0) {
 		ret = ioctl(fd, MEDIA_IOC_DEVICE_INFO, &mdi);
diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c
index 22bffd55a523..6793f8ecc8e7 100644
--- a/tools/testing/selftests/membarrier/membarrier_test.c
+++ b/tools/testing/selftests/membarrier/membarrier_test.c
@@ -293,10 +293,9 @@ static int test_membarrier_query(void)
 		}
 		ksft_exit_fail_msg("sys_membarrier() failed\n");
 	}
-	if (!(ret & MEMBARRIER_CMD_GLOBAL)) {
-		ksft_test_result_fail("sys_membarrier() CMD_GLOBAL query failed\n");
-		ksft_exit_fail_msg("sys_membarrier is not supported.\n");
-	}
+	if (!(ret & MEMBARRIER_CMD_GLOBAL))
+		ksft_exit_skip(
+			"sys_membarrier unsupported: CMD_GLOBAL not found.\n");
 
 	ksft_test_result_pass("sys_membarrier available\n");
 	return 0;
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index 0862e6f47a38..53a848109f7b 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -4,9 +4,9 @@ CFLAGS += -I../../../../include/uapi/
 CFLAGS += -I../../../../include/
 CFLAGS += -I../../../../usr/include/
 
-TEST_PROGS := run_tests.sh
-TEST_FILES := run_fuse_test.sh
-TEST_GEN_FILES := memfd_test fuse_mnt fuse_test
+TEST_GEN_PROGS := memfd_test
+TEST_PROGS := run_fuse_test.sh run_hugetlbfs_test.sh
+TEST_GEN_FILES := fuse_mnt fuse_test
 
 fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
 
diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_hugetlbfs_test.sh
index c2d41ed81b24..fb633eeb0290 100755
--- a/tools/testing/selftests/memfd/run_tests.sh
+++ b/tools/testing/selftests/memfd/run_hugetlbfs_test.sh
@@ -1,11 +1,8 @@
 #!/bin/bash
 # please run as root
 
-#
-# Normal tests requiring no special resources
-#
-./run_fuse_test.sh
-./memfd_test
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
 
 #
 # To test memfd_create with hugetlbfs, there needs to be hpages_test
@@ -29,12 +26,13 @@ if [ -n "$freepgs" ] && [ $freepgs -lt $hpages_test ]; then
 	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
 	hpages_needed=`expr $hpages_test - $freepgs`
 
+	if [ $UID != 0 ]; then
+		echo "Please run memfd with hugetlbfs test as root"
+		exit $ksft_skip
+	fi
+
 	echo 3 > /proc/sys/vm/drop_caches
 	echo $(( $hpages_needed + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
-	if [ $? -ne 0 ]; then
-		echo "Please run this test as root"
-		exit 1
-	fi
 	while read name size unit; do
 		if [ "$name" = "HugePages_Free:" ]; then
 			freepgs=$size
@@ -53,7 +51,7 @@ if [ $freepgs -lt $hpages_test ]; then
 	fi
 	printf "Not enough huge pages available (%d < %d)\n" \
 		$freepgs $needpgs
-	exit 1
+	exit $ksft_skip
 fi
 
 #
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index 686da510f989..e0a625e34f40 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -4,11 +4,8 @@ all:
 include ../lib.mk
 
 TEST_PROGS := mem-on-off-test.sh
-override RUN_TESTS := @./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]"
-
-override EMIT_TESTS := echo "$(subst @,,$(RUN_TESTS))"
 
 run_full_test:
-	@/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]"
+	@/bin/bash ./mem-on-off-test.sh -r 10 && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]"
 
 clean:
diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
index ae2c790d0880..b37585e6aa38 100755
--- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
+++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
@@ -3,30 +3,33 @@
 
 SYSFS=
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 prerequisite()
 {
 	msg="skip all tests:"
 
 	if [ $UID != 0 ]; then
 		echo $msg must be run as root >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
 
 	if [ ! -d "$SYSFS" ]; then
 		echo $msg sysfs is not mounted >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	if ! ls $SYSFS/devices/system/memory/memory* > /dev/null 2>&1; then
 		echo $msg memory hotplug is not supported >&2
-		exit 0
+		exit $ksft_skip
 	fi
 
 	if ! grep -q 1 $SYSFS/devices/system/memory/memory*/removable; then
 		echo $msg no hot-pluggable memory >&2
-		exit 0
+		exit $ksft_skip
 	fi
 }
 
@@ -133,7 +136,8 @@ offline_memory_expect_fail()
 
 error=-12
 priority=0
-ratio=10
+# Run with default of ratio=2 for Kselftest run
+ratio=2
 retval=0
 
 while getopts e:hp:r: opt; do
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
index e094f71c6dbc..026890744215 100644
--- a/tools/testing/selftests/mount/Makefile
+++ b/tools/testing/selftests/mount/Makefile
@@ -3,15 +3,7 @@
 CFLAGS = -Wall \
          -O2
 
-TEST_GEN_PROGS := unprivileged-remount-test
+TEST_PROGS := run_tests.sh
+TEST_GEN_FILES := unprivileged-remount-test
 
 include ../lib.mk
-
-override RUN_TESTS := if [ -f /proc/self/uid_map ] ; \
-		      then	\
-				./unprivileged-remount-test ; \
-		      else	\
-				echo "WARN: No /proc/self/uid_map exist, test skipped." ; \
-		      fi
-override EMIT_TESTS := echo "$(RUN_TESTS)"
-
diff --git a/tools/testing/selftests/mount/run_tests.sh b/tools/testing/selftests/mount/run_tests.sh
new file mode 100755
index 000000000000..4ab8f507dcba
--- /dev/null
+++ b/tools/testing/selftests/mount/run_tests.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Run mount selftests
+if [ -f /proc/self/uid_map ] ; then
+	./unprivileged-remount-test ;
+else
+	echo "WARN: No /proc/self/uid_map exist, test skipped." ;
+	exit $ksft_skip
+fi
diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile
index 743d3f9e5918..8a58055fc1f5 100644
--- a/tools/testing/selftests/mqueue/Makefile
+++ b/tools/testing/selftests/mqueue/Makefile
@@ -1,17 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -O2
 LDLIBS = -lrt -lpthread -lpopt
+
 TEST_GEN_PROGS := mq_open_tests mq_perf_tests
 
 include ../lib.mk
-
-override define RUN_TESTS
-	@$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
-	@$(OUTPUT)/mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
-endef
-
-override define EMIT_TESTS
-	echo "./mq_open_tests /test1 || echo \"selftests: mq_open_tests [FAIL]\""
-	echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\""
-endef
-
diff --git a/tools/testing/selftests/mqueue/mq_open_tests.c b/tools/testing/selftests/mqueue/mq_open_tests.c
index e0a74bd207a5..9403ac01ba11 100644
--- a/tools/testing/selftests/mqueue/mq_open_tests.c
+++ b/tools/testing/selftests/mqueue/mq_open_tests.c
@@ -33,6 +33,8 @@
 #include <mqueue.h>
 #include <error.h>
 
+#include "../kselftest.h"
+
 static char *usage =
 "Usage:\n"
 "  %s path\n"
@@ -53,6 +55,7 @@ int saved_def_msgs, saved_def_msgsize, saved_max_msgs, saved_max_msgsize;
 int cur_def_msgs, cur_def_msgsize, cur_max_msgs, cur_max_msgsize;
 FILE *def_msgs, *def_msgsize, *max_msgs, *max_msgsize;
 char *queue_path;
+char *default_queue_path = "/test1";
 mqd_t queue = -1;
 
 static inline void __set(FILE *stream, int value, char *err_msg);
@@ -238,35 +241,33 @@ int main(int argc, char *argv[])
 	struct mq_attr attr, result;
 
 	if (argc != 2) {
-		fprintf(stderr, "Must pass a valid queue name\n\n");
-		fprintf(stderr, usage, argv[0]);
-		exit(1);
-	}
+		printf("Using Default queue path - %s\n", default_queue_path);
+		queue_path = default_queue_path;
+	} else {
 
 	/*
 	 * Although we can create a msg queue with a non-absolute path name,
 	 * unlink will fail.  So, if the name doesn't start with a /, add one
 	 * when we save it.
 	 */
-	if (*argv[1] == '/')
-		queue_path = strdup(argv[1]);
-	else {
-		queue_path = malloc(strlen(argv[1]) + 2);
-		if (!queue_path) {
-			perror("malloc()");
-			exit(1);
+		if (*argv[1] == '/')
+			queue_path = strdup(argv[1]);
+		else {
+			queue_path = malloc(strlen(argv[1]) + 2);
+			if (!queue_path) {
+				perror("malloc()");
+				exit(1);
+			}
+			queue_path[0] = '/';
+			queue_path[1] = 0;
+			strcat(queue_path, argv[1]);
 		}
-		queue_path[0] = '/';
-		queue_path[1] = 0;
-		strcat(queue_path, argv[1]);
 	}
 
-	if (getuid() != 0) {
-		fprintf(stderr, "Not running as root, but almost all tests "
+	if (getuid() != 0)
+		ksft_exit_skip("Not running as root, but almost all tests "
 			"require root in order to modify\nsystem settings.  "
 			"Exiting.\n");
-		exit(1);
-	}
 
 	/* Find out what files there are for us to make tweaks in */
 	def_msgs = fopen(DEF_MSGS, "r+");
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index 8188f72de93c..b019e0b8221c 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -39,6 +39,8 @@
 #include <popt.h>
 #include <error.h>
 
+#include "../kselftest.h"
+
 static char *usage =
 "Usage:\n"
 "  %s [-c #[,#..] -f] path\n"
@@ -626,12 +628,10 @@ int main(int argc, char *argv[])
 		cpus_to_pin[0] = cpus_online - 1;
 	}
 
-	if (getuid() != 0) {
-		fprintf(stderr, "Not running as root, but almost all tests "
+	if (getuid() != 0)
+		ksft_exit_skip("Not running as root, but almost all tests "
 			"require root in order to modify\nsystem settings.  "
 			"Exiting.\n");
-		exit(1);
-	}
 
 	max_msgs = fopen(MAX_MSGS, "r+");
 	max_msgsize = fopen(MAX_MSGSIZE, "r+");
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 785fc18a16b4..3ff81a478dbe 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -6,6 +6,7 @@ CFLAGS += -I../../../../usr/include/
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh
+TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 6a75a3ea44ad..7ba089b33e8b 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -7,3 +7,8 @@ CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_IPV6=y
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_VETH=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_NET_IPVTI=y
+CONFIG_INET6_XFRM_MODE_TUNNEL=y
+CONFIG_IPV6_VTI=y
+CONFIG_DUMMY=y
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 9164e60d4b66..5baac82b9287 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -5,6 +5,8 @@
 # different events.
 
 ret=0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
 
 VERBOSE=${VERBOSE:=0}
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
@@ -579,18 +581,18 @@ fib_test()
 
 if [ "$(id -u)" -ne 0 ];then
 	echo "SKIP: Need root privileges"
-	exit 0
+	exit $ksft_skip;
 fi
 
 if [ ! -x "$(command -v ip)" ]; then
 	echo "SKIP: Could not run test without ip tool"
-	exit 0
+	exit $ksft_skip
 fi
 
 ip route help 2>&1 | grep -q fibmatch
 if [ $? -ne 0 ]; then
 	echo "SKIP: iproute2 too old, missing fibmatch"
-	exit 0
+	exit $ksft_skip
 fi
 
 # start clean
diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
index 903679e0ff31..e3afcb424710 100755
--- a/tools/testing/selftests/net/netdevice.sh
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -8,6 +8,9 @@
 # if not they probably have failed earlier in the boot process and their logged error will be catched by another test
 #
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 # this function will try to up the interface
 # if already up, nothing done
 # arg1: network interface name
@@ -18,7 +21,7 @@ kci_net_start()
 	ip link show "$netdev" |grep -q UP
 	if [ $? -eq 0 ];then
 		echo "SKIP: $netdev: interface already up"
-		return 0
+		return $ksft_skip
 	fi
 
 	ip link set "$netdev" up
@@ -61,12 +64,12 @@ kci_net_setup()
 	ip address show "$netdev" |grep '^[[:space:]]*inet'
 	if [ $? -eq 0 ];then
 		echo "SKIP: $netdev: already have an IP"
-		return 0
+		return $ksft_skip
 	fi
 
 	# TODO what ipaddr to set ? DHCP ?
 	echo "SKIP: $netdev: set IP address"
-	return 0
+	return $ksft_skip
 }
 
 # test an ethtool command
@@ -84,6 +87,7 @@ kci_netdev_ethtool_test()
 	if [ $ret -ne 0 ];then
 		if [ $ret -eq "$1" ];then
 			echo "SKIP: $netdev: ethtool $2 not supported"
+			return $ksft_skip
 		else
 			echo "FAIL: $netdev: ethtool $2"
 			return 1
@@ -104,7 +108,7 @@ kci_netdev_ethtool()
 	ethtool --version 2>/dev/null >/dev/null
 	if [ $? -ne 0 ];then
 		echo "SKIP: ethtool not present"
-		return 1
+		return $ksft_skip
 	fi
 
 	TMP_ETHTOOL_FEATURES="$(mktemp)"
@@ -176,13 +180,13 @@ kci_test_netdev()
 #check for needed privileges
 if [ "$(id -u)" -ne 0 ];then
 	echo "SKIP: Need root privileges"
-	exit 0
+	exit $ksft_skip
 fi
 
 ip link show 2>/dev/null >/dev/null
 if [ $? -ne 0 ];then
 	echo "SKIP: Could not run test without the ip tool"
-	exit 0
+	exit $ksft_skip
 fi
 
 TMP_LIST_NETDEV="$(mktemp)"
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 1e428781a625..7514f93e1624 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -43,6 +43,9 @@
 #	that MTU is properly calculated instead when MTU is not configured from
 #	userspace
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 tests="
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
@@ -162,7 +165,7 @@ setup_xfrm6() {
 }
 
 setup() {
-	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return 1
+	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
 	cleanup_done=0
 	for arg do
diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c
index 7f6cd9fdacf3..7ec4fa4d55dc 100644
--- a/tools/testing/selftests/net/psock_tpacket.c
+++ b/tools/testing/selftests/net/psock_tpacket.c
@@ -60,6 +60,8 @@
 
 #include "psock_lib.h"
 
+#include "../kselftest.h"
+
 #ifndef bug_on
 # define bug_on(cond)		assert(!(cond))
 #endif
@@ -825,7 +827,7 @@ static int test_tpacket(int version, int type)
 		fprintf(stderr, "test: skip %s %s since user and kernel "
 			"space have different bit width\n",
 			tpacket_str[version], type_str[type]);
-		return 0;
+		return KSFT_SKIP;
 	}
 
 	sock = pfsocket(version);
diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c
index 365c32e84189..c9f478b40996 100644
--- a/tools/testing/selftests/net/reuseport_bpf_numa.c
+++ b/tools/testing/selftests/net/reuseport_bpf_numa.c
@@ -23,6 +23,8 @@
 #include <unistd.h>
 #include <numa.h>
 
+#include "../kselftest.h"
+
 static const int PORT = 8888;
 
 static void build_rcv_group(int *rcv_fd, size_t len, int family, int proto)
@@ -229,7 +231,7 @@ int main(void)
 	int *rcv_fd, nodes;
 
 	if (numa_available() < 0)
-		error(1, errno, "no numa api support");
+		ksft_exit_skip("no numa api support\n");
 
 	nodes = numa_max_node() + 1;
 
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index e6f485235435..fb3767844e42 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -7,6 +7,9 @@
 devdummy="test-dummy0"
 ret=0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 # set global exit status, but never reset nonzero one.
 check_err()
 {
@@ -333,7 +336,7 @@ kci_test_vrf()
 	ip link show type vrf 2>/dev/null
 	if [ $? -ne 0 ]; then
 		echo "SKIP: vrf: iproute2 too old"
-		return 0
+		return $ksft_skip
 	fi
 
 	ip link add "$vrfname" type vrf table 10
@@ -409,7 +412,7 @@ kci_test_encap_fou()
 	ip fou help 2>&1 |grep -q 'Usage: ip fou'
 	if [ $? -ne 0 ];then
 		echo "SKIP: fou: iproute2 too old"
-		return 1
+		return $ksft_skip
 	fi
 
 	ip netns exec "$testns" ip fou add port 7777 ipproto 47 2>/dev/null
@@ -444,7 +447,7 @@ kci_test_encap()
 	ip netns add "$testns"
 	if [ $? -ne 0 ]; then
 		echo "SKIP encap tests: cannot add net namespace $testns"
-		return 1
+		return $ksft_skip
 	fi
 
 	ip netns exec "$testns" ip link set lo up
@@ -469,7 +472,7 @@ kci_test_macsec()
 	ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
 	if [ $? -ne 0 ]; then
 		echo "SKIP: macsec: iproute2 too old"
-		return 0
+		return $ksft_skip
 	fi
 
 	ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on
@@ -511,14 +514,14 @@ kci_test_gretap()
 	ip netns add "$testns"
 	if [ $? -ne 0 ]; then
 		echo "SKIP gretap tests: cannot add net namespace $testns"
-		return 1
+		return $ksft_skip
 	fi
 
 	ip link help gretap 2>&1 | grep -q "^Usage:"
 	if [ $? -ne 0 ];then
 		echo "SKIP: gretap: iproute2 too old"
 		ip netns del "$testns"
-		return 1
+		return $ksft_skip
 	fi
 
 	# test native tunnel
@@ -561,14 +564,14 @@ kci_test_ip6gretap()
 	ip netns add "$testns"
 	if [ $? -ne 0 ]; then
 		echo "SKIP ip6gretap tests: cannot add net namespace $testns"
-		return 1
+		return $ksft_skip
 	fi
 
 	ip link help ip6gretap 2>&1 | grep -q "^Usage:"
 	if [ $? -ne 0 ];then
 		echo "SKIP: ip6gretap: iproute2 too old"
 		ip netns del "$testns"
-		return 1
+		return $ksft_skip
 	fi
 
 	# test native tunnel
@@ -611,13 +614,13 @@ kci_test_erspan()
 	ip link help erspan 2>&1 | grep -q "^Usage:"
 	if [ $? -ne 0 ];then
 		echo "SKIP: erspan: iproute2 too old"
-		return 1
+		return $ksft_skip
 	fi
 
 	ip netns add "$testns"
 	if [ $? -ne 0 ]; then
 		echo "SKIP erspan tests: cannot add net namespace $testns"
-		return 1
+		return $ksft_skip
 	fi
 
 	# test native tunnel erspan v1
@@ -676,13 +679,13 @@ kci_test_ip6erspan()
 	ip link help ip6erspan 2>&1 | grep -q "^Usage:"
 	if [ $? -ne 0 ];then
 		echo "SKIP: ip6erspan: iproute2 too old"
-		return 1
+		return $ksft_skip
 	fi
 
 	ip netns add "$testns"
 	if [ $? -ne 0 ]; then
 		echo "SKIP ip6erspan tests: cannot add net namespace $testns"
-		return 1
+		return $ksft_skip
 	fi
 
 	# test native tunnel ip6erspan v1
@@ -762,14 +765,14 @@ kci_test_rtnl()
 #check for needed privileges
 if [ "$(id -u)" -ne 0 ];then
 	echo "SKIP: Need root privileges"
-	exit 0
+	exit $ksft_skip
 fi
 
 for x in ip tc;do
 	$x -Version 2>/dev/null >/dev/null
 	if [ $? -ne 0 ];then
 		echo "SKIP: Could not run test without the $x tool"
-		exit 0
+		exit $ksft_skip
 	fi
 done
 
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
new file mode 100755
index 000000000000..98f650c9bf54
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -0,0 +1,56 @@
+#!/bin/sh
+#
+# Invoke a text editor on all console.log files for all runs with diagnostics,
+# that is, on all such files having a console.log.diags counterpart.
+# Note that both console.log.diags and console.log are passed to the
+# editor (currently defaulting to "vi"), allowing the user to get an
+# idea of what to search for in the console.log file.
+#
+# Usage: kvm-find-errors.sh directory
+#
+# The "directory" above should end with the date/time directory, for example,
+# "tools/testing/selftests/rcutorture/res/2018.02.25-14:27:27".
+
+rundir="${1}"
+if test -z "$rundir" -o ! -d "$rundir"
+then
+	echo Usage: $0 directory
+fi
+editor=${EDITOR-vi}
+
+# Find builds with errors
+files=
+for i in ${rundir}/*/Make.out
+do
+	if egrep -q "error:|warning:" < $i
+	then
+		egrep "error:|warning:" < $i > $i.diags
+		files="$files $i.diags $i"
+	fi
+done
+if test -n "$files"
+then
+	$editor $files
+else
+	echo No build errors.
+fi
+if grep -q -e "--buildonly" < ${rundir}/log
+then
+	echo Build-only run, no console logs to check.
+fi
+
+# Find console logs with errors
+files=
+for i in ${rundir}/*/console.log
+do
+	if test -r $i.diags
+	then
+		files="$files $i.diags $i"
+	fi
+done
+if test -n "$files"
+then
+	$editor $files
+else
+	echo No errors in console logs.
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index c2e1bb6d0cba..477ecb1293ab 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -34,11 +34,15 @@ fi
 
 configfile=`echo $i | sed -e 's/^.*\///'`
 ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
+stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null |
+	    tail -1 | sed -e 's/^\[[ 0-9.]*] //' |
+	    awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' |
+	    tr -d '\012\015'`"
 if test -z "$ngps"
 then
-	echo "$configfile -------"
+	echo "$configfile ------- " $stopstate
 else
-	title="$configfile ------- $ngps grace periods"
+	title="$configfile ------- $ngps GPs"
 	dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
 	if test -z "$dur"
 	then
@@ -46,9 +50,9 @@ else
 	else
 		ngpsps=`awk -v ngps=$ngps -v dur=$dur '
 			BEGIN { print ngps / dur }' < /dev/null`
-		title="$title ($ngpsps per second)"
+		title="$title ($ngpsps/s)"
 	fi
-	echo $title
+	echo $title $stopstate
 	nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
 	if test -z "$nclosecalls"
 	then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index f7e988f369dd..c27e97824163 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -48,10 +48,6 @@ do
 				cat $i/Make.oldconfig.err
 			fi
 			parse-build.sh $i/Make.out $configfile
-			if test "$TORTURE_SUITE" != rcuperf
-			then
-				parse-torture.sh $i/console.log $configfile
-			fi
 			parse-console.sh $i/console.log $configfile
 			if test -r $i/Warnings
 			then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 5f8fbb0d7c17..c5b0f94341d9 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -267,5 +267,4 @@ then
 	echo Unknown PID, cannot kill qemu command
 fi
 
-parse-torture.sh $resdir/console.log $title
 parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 08aa7d50ae0e..17293436f551 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -24,57 +24,146 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
+T=${TMPDIR-/tmp}/parse-console.sh.$$
 file="$1"
 title="$2"
 
+trap 'rm -f $T.seq $T.diags' 0
+
 . functions.sh
 
+# Check for presence and readability of console output file
+if test -f "$file" -a -r "$file"
+then
+	:
+else
+	echo $title unreadable console output file: $file
+	exit 1
+fi
 if grep -Pq '\x00' < $file
 then
 	print_warning Console output contains nul bytes, old qemu still running?
 fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
-if test -s $1.diags
+cat /dev/null > $file.diags
+
+# Check for proper termination, except that rcuperf runs don't indicate this.
+if test "$TORTURE_SUITE" != rcuperf
 then
-	print_warning Assertion failure in $file $title
-	# cat $1.diags
+	# check for abject failure
+
+	if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
+	then
+		nerrs=`grep --binary-files=text '!!!' $file |
+		tail -1 |
+		awk '
+		{
+			for (i=NF-8;i<=NF;i++)
+				sum+=$i;
+		}
+		END { print sum }'`
+		print_bug $title FAILURE, $nerrs instances
+		exit
+	fi
+
+	grep --binary-files=text 'torture:.*ver:' $file |
+	egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' |
+	sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
+	awk '
+	BEGIN	{
+		ver = 0;
+		badseq = 0;
+		}
+
+		{
+		if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
+			badseqno1 = ver;
+			badseqno2 = $5;
+			badseqnr = NR;
+			badseq = 1;
+		}
+		ver = $5
+		}
+
+	END	{
+		if (badseq) {
+			if (badseqno1 == badseqno2 && badseqno2 == ver)
+				print "GP HANG at " ver " torture stat " badseqnr;
+			else
+				print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
+		}
+		}' > $T.seq
+
+	if grep -q SUCCESS $file
+	then
+		if test -s $T.seq
+		then
+			print_warning $title `cat $T.seq`
+			echo "   " $file
+			exit 2
+		fi
+	else
+		if grep -q "_HOTPLUG:" $file
+		then
+			print_warning HOTPLUG FAILURES $title `cat $T.seq`
+			echo "   " $file
+			exit 3
+		fi
+		echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
+		if test -s $T.seq
+		then
+			print_warning $title `cat $T.seq`
+		fi
+		exit 2
+	fi
+fi | tee -a $file.diags
+
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file |
+grep -v 'ODEBUG: ' |
+grep -v 'Warning: unable to open an initial console' > $T.diags
+if test -s $T.diags
+then
+	print_warning "Assertion failure in $file $title"
+	# cat $T.diags
 	summary=""
-	n_badness=`grep -c Badness $1`
+	n_badness=`grep -c Badness $file`
 	if test "$n_badness" -ne 0
 	then
 		summary="$summary  Badness: $n_badness"
 	fi
-	n_warn=`grep -v 'Warning: unable to open an initial console' $1 | egrep -c 'WARNING:|Warn'`
+	n_warn=`grep -v 'Warning: unable to open an initial console' $file | egrep -c 'WARNING:|Warn'`
 	if test "$n_warn" -ne 0
 	then
 		summary="$summary  Warnings: $n_warn"
 	fi
-	n_bugs=`egrep -c 'BUG|Oops:' $1`
+	n_bugs=`egrep -c 'BUG|Oops:' $file`
 	if test "$n_bugs" -ne 0
 	then
 		summary="$summary  Bugs: $n_bugs"
 	fi
-	n_calltrace=`grep -c 'Call Trace:' $1`
+	n_calltrace=`grep -c 'Call Trace:' $file`
 	if test "$n_calltrace" -ne 0
 	then
 		summary="$summary  Call Traces: $n_calltrace"
 	fi
-	n_lockdep=`grep -c =========== $1`
+	n_lockdep=`grep -c =========== $file`
 	if test "$n_badness" -ne 0
 	then
 		summary="$summary  lockdep: $n_badness"
 	fi
-	n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1`
+	n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $file`
 	if test "$n_stalls" -ne 0
 	then
 		summary="$summary  Stalls: $n_stalls"
 	fi
-	n_starves=`grep -c 'rcu_.*kthread starved for' $1`
+	n_starves=`grep -c 'rcu_.*kthread starved for' $file`
 	if test "$n_starves" -ne 0
 	then
 		summary="$summary  Starves: $n_starves"
 	fi
 	print_warning Summary: $summary
-else
-	rm $1.diags
+	cat $T.diags >> $file.diags
+fi
+if ! test -s $file.diags
+then
+	rm -f $file.diags
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
deleted file mode 100755
index 5987e50cfeb4..000000000000
--- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh
+++ /dev/null
@@ -1,105 +0,0 @@
-#!/bin/bash
-#
-# Check the console output from a torture run for goodness.
-# The "file" is a pathname on the local system, and "title" is
-# a text string for error-message purposes.
-#
-# The file must contain torture output, but can be interspersed
-# with other dmesg text, as in console-log output.
-#
-# Usage: parse-torture.sh file title
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2011
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-T=${TMPDIR-/tmp}/parse-torture.sh.$$
-file="$1"
-title="$2"
-
-trap 'rm -f $T.seq' 0
-
-. functions.sh
-
-# check for presence of torture output file.
-
-if test -f "$file" -a -r "$file"
-then
-	:
-else
-	echo $title unreadable torture output file: $file
-	exit 1
-fi
-
-# check for abject failure
-
-if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
-then
-	nerrs=`grep --binary-files=text '!!!' $file | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
-	print_bug $title FAILURE, $nerrs instances
-	echo "   " $url
-	exit
-fi
-
-grep --binary-files=text 'torture:.*ver:' $file | egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' | sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
-awk '
-BEGIN	{
-	ver = 0;
-	badseq = 0;
-	}
-
-	{
-	if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
-		badseqno1 = ver;
-		badseqno2 = $5;
-		badseqnr = NR;
-		badseq = 1;
-	}
-	ver = $5
-	}
-
-END	{
-	if (badseq) {
-		if (badseqno1 == badseqno2 && badseqno2 == ver)
-			print "GP HANG at " ver " torture stat " badseqnr;
-		else
-			print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
-	}
-	}' > $T.seq
-
-if grep -q SUCCESS $file
-then
-	if test -s $T.seq
-	then
-		print_warning $title $title `cat $T.seq`
-		echo "   " $file
-		exit 2
-	fi
-else
-	if grep -q "_HOTPLUG:" $file
-	then
-		print_warning HOTPLUG FAILURES $title `cat $T.seq`
-		echo "   " $file
-		exit 3
-	fi
-	echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
-	if test -s $T.seq
-	then
-		print_warning $title `cat $T.seq`
-	fi
-	exit 2
-fi
diff --git a/tools/testing/selftests/rtc/.gitignore b/tools/testing/selftests/rtc/.gitignore
new file mode 100644
index 000000000000..d0ad44f6294a
--- /dev/null
+++ b/tools/testing/selftests/rtc/.gitignore
@@ -0,0 +1,2 @@
+rtctest
+setdate
diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile
new file mode 100644
index 000000000000..de9c8566672a
--- /dev/null
+++ b/tools/testing/selftests/rtc/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -O3 -Wl,-no-as-needed -Wall
+LDFLAGS += -lrt -lpthread -lm
+
+TEST_GEN_PROGS = rtctest
+
+TEST_GEN_PROGS_EXTENDED = setdate
+
+include ../lib.mk
diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c
new file mode 100644
index 000000000000..e20b017e7073
--- /dev/null
+++ b/tools/testing/selftests/rtc/rtctest.c
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Real Time Clock Driver Test Program
+ *
+ * Copyright (c) 2018 Alexandre Belloni <alexandre.belloni@bootlin.com>
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/rtc.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+#define NUM_UIE 3
+#define ALARM_DELTA 3
+
+static char *rtc_file = "/dev/rtc0";
+
+FIXTURE(rtc) {
+	int fd;
+};
+
+FIXTURE_SETUP(rtc) {
+	self->fd = open(rtc_file, O_RDONLY);
+	ASSERT_NE(-1, self->fd);
+}
+
+FIXTURE_TEARDOWN(rtc) {
+	close(self->fd);
+}
+
+TEST_F(rtc, date_read) {
+	int rc;
+	struct rtc_time rtc_tm;
+
+	/* Read the RTC time/date */
+	rc = ioctl(self->fd, RTC_RD_TIME, &rtc_tm);
+	ASSERT_NE(-1, rc);
+
+	TH_LOG("Current RTC date/time is %02d/%02d/%02d %02d:%02d:%02d.",
+	       rtc_tm.tm_mday, rtc_tm.tm_mon + 1, rtc_tm.tm_year + 1900,
+	       rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec);
+}
+
+TEST_F(rtc, uie_read) {
+	int i, rc, irq = 0;
+	unsigned long data;
+
+	/* Turn on update interrupts */
+	rc = ioctl(self->fd, RTC_UIE_ON, 0);
+	if (rc == -1) {
+		ASSERT_EQ(EINVAL, errno);
+		TH_LOG("skip update IRQs not supported.");
+		return;
+	}
+
+	for (i = 0; i < NUM_UIE; i++) {
+		/* This read will block */
+		rc = read(self->fd, &data, sizeof(data));
+		ASSERT_NE(-1, rc);
+		irq++;
+	}
+
+	EXPECT_EQ(NUM_UIE, irq);
+
+	rc = ioctl(self->fd, RTC_UIE_OFF, 0);
+	ASSERT_NE(-1, rc);
+}
+
+TEST_F(rtc, uie_select) {
+	int i, rc, irq = 0;
+	unsigned long data;
+
+	/* Turn on update interrupts */
+	rc = ioctl(self->fd, RTC_UIE_ON, 0);
+	if (rc == -1) {
+		ASSERT_EQ(EINVAL, errno);
+		TH_LOG("skip update IRQs not supported.");
+		return;
+	}
+
+	for (i = 0; i < NUM_UIE; i++) {
+		struct timeval tv = { .tv_sec = 2 };
+		fd_set readfds;
+
+		FD_ZERO(&readfds);
+		FD_SET(self->fd, &readfds);
+		/* The select will wait until an RTC interrupt happens. */
+		rc = select(self->fd + 1, &readfds, NULL, NULL, &tv);
+		ASSERT_NE(-1, rc);
+		ASSERT_NE(0, rc);
+
+		/* This read won't block */
+		rc = read(self->fd, &data, sizeof(unsigned long));
+		ASSERT_NE(-1, rc);
+		irq++;
+	}
+
+	EXPECT_EQ(NUM_UIE, irq);
+
+	rc = ioctl(self->fd, RTC_UIE_OFF, 0);
+	ASSERT_NE(-1, rc);
+}
+
+TEST_F(rtc, alarm_alm_set) {
+	struct timeval tv = { .tv_sec = ALARM_DELTA + 2 };
+	unsigned long data;
+	struct rtc_time tm;
+	fd_set readfds;
+	time_t secs, new;
+	int rc;
+
+	rc = ioctl(self->fd, RTC_RD_TIME, &tm);
+	ASSERT_NE(-1, rc);
+
+	secs = timegm((struct tm *)&tm) + ALARM_DELTA;
+	gmtime_r(&secs, (struct tm *)&tm);
+
+	rc = ioctl(self->fd, RTC_ALM_SET, &tm);
+	if (rc == -1) {
+		ASSERT_EQ(EINVAL, errno);
+		TH_LOG("skip alarms are not supported.");
+		return;
+	}
+
+	rc = ioctl(self->fd, RTC_ALM_READ, &tm);
+	ASSERT_NE(-1, rc);
+
+	TH_LOG("Alarm time now set to %02d:%02d:%02d.",
+	       tm.tm_hour, tm.tm_min, tm.tm_sec);
+
+	/* Enable alarm interrupts */
+	rc = ioctl(self->fd, RTC_AIE_ON, 0);
+	ASSERT_NE(-1, rc);
+
+	FD_ZERO(&readfds);
+	FD_SET(self->fd, &readfds);
+
+	rc = select(self->fd + 1, &readfds, NULL, NULL, &tv);
+	ASSERT_NE(-1, rc);
+	EXPECT_NE(0, rc);
+
+	/* Disable alarm interrupts */
+	rc = ioctl(self->fd, RTC_AIE_OFF, 0);
+	ASSERT_NE(-1, rc);
+
+	if (rc == 0)
+		return;
+
+	rc = read(self->fd, &data, sizeof(unsigned long));
+	ASSERT_NE(-1, rc);
+	TH_LOG("data: %lx", data);
+
+	rc = ioctl(self->fd, RTC_RD_TIME, &tm);
+	ASSERT_NE(-1, rc);
+
+	new = timegm((struct tm *)&tm);
+	ASSERT_EQ(new, secs);
+}
+
+TEST_F(rtc, alarm_wkalm_set) {
+	struct timeval tv = { .tv_sec = ALARM_DELTA + 2 };
+	struct rtc_wkalrm alarm = { 0 };
+	struct rtc_time tm;
+	unsigned long data;
+	fd_set readfds;
+	time_t secs, new;
+	int rc;
+
+	rc = ioctl(self->fd, RTC_RD_TIME, &alarm.time);
+	ASSERT_NE(-1, rc);
+
+	secs = timegm((struct tm *)&alarm.time) + ALARM_DELTA;
+	gmtime_r(&secs, (struct tm *)&alarm.time);
+
+	alarm.enabled = 1;
+
+	rc = ioctl(self->fd, RTC_WKALM_SET, &alarm);
+	if (rc == -1) {
+		ASSERT_EQ(EINVAL, errno);
+		TH_LOG("skip alarms are not supported.");
+		return;
+	}
+
+	rc = ioctl(self->fd, RTC_WKALM_RD, &alarm);
+	ASSERT_NE(-1, rc);
+
+	TH_LOG("Alarm time now set to %02d/%02d/%02d %02d:%02d:%02d.",
+	       alarm.time.tm_mday, alarm.time.tm_mon + 1,
+	       alarm.time.tm_year + 1900, alarm.time.tm_hour,
+	       alarm.time.tm_min, alarm.time.tm_sec);
+
+	FD_ZERO(&readfds);
+	FD_SET(self->fd, &readfds);
+
+	rc = select(self->fd + 1, &readfds, NULL, NULL, &tv);
+	ASSERT_NE(-1, rc);
+	EXPECT_NE(0, rc);
+
+	rc = read(self->fd, &data, sizeof(unsigned long));
+	ASSERT_NE(-1, rc);
+
+	rc = ioctl(self->fd, RTC_RD_TIME, &tm);
+	ASSERT_NE(-1, rc);
+
+	new = timegm((struct tm *)&tm);
+	ASSERT_EQ(new, secs);
+}
+
+static void __attribute__((constructor))
+__constructor_order_last(void)
+{
+	if (!__constructor_order)
+		__constructor_order = _CONSTRUCTOR_ORDER_BACKWARD;
+}
+
+int main(int argc, char **argv)
+{
+	switch (argc) {
+	case 2:
+		rtc_file = argv[1];
+		/* FALLTHROUGH */
+	case 1:
+		break;
+	default:
+		fprintf(stderr, "usage: %s [rtcdev]\n", argv[0]);
+		return 1;
+	}
+
+	return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/timers/rtctest_setdate.c b/tools/testing/selftests/rtc/setdate.c
index 2cb78489eca4..2cb78489eca4 100644
--- a/tools/testing/selftests/timers/rtctest_setdate.c
+++ b/tools/testing/selftests/rtc/setdate.c
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 168c66d74fc5..e1473234968d 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -134,11 +134,15 @@ struct seccomp_data {
 #endif
 
 #ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
 #endif
 
 #ifndef SECCOMP_FILTER_FLAG_LOG
-#define SECCOMP_FILTER_FLAG_LOG 2
+#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_SPEC_ALLOW
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
 #endif
 
 #ifndef PTRACE_SECCOMP_GET_METADATA
@@ -2072,14 +2076,26 @@ TEST(seccomp_syscall_mode_lock)
 TEST(detect_seccomp_filter_flags)
 {
 	unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
-				 SECCOMP_FILTER_FLAG_LOG };
+				 SECCOMP_FILTER_FLAG_LOG,
+				 SECCOMP_FILTER_FLAG_SPEC_ALLOW };
 	unsigned int flag, all_flags;
 	int i;
 	long ret;
 
 	/* Test detection of known-good filter flags */
 	for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+		int bits = 0;
+
 		flag = flags[i];
+		/* Make sure the flag is a single bit! */
+		while (flag) {
+			if (flag & 0x1)
+				bits ++;
+			flag >>= 1;
+		}
+		ASSERT_EQ(1, bits);
+		flag = flags[i];
+
 		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
 		ASSERT_NE(ENOSYS, errno) {
 			TH_LOG("Kernel does not support seccomp syscall!");
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 5b012f4981d4..6f289a49e5ec 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -66,7 +66,7 @@
         "cmdUnderTest": "$TC action add action bpf object-file _b.o index 667",
         "expExitCode": "0",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c default-action pipe.*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
             "$TC action flush action bpf",
@@ -92,10 +92,15 @@
         "cmdUnderTest": "$TC action add action bpf object-file _c.o index 667",
         "expExitCode": "255",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9].*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref",
         "matchCount": "0",
         "teardown": [
-            "$TC action flush action bpf",
+            [
+                "$TC action flush action bpf",
+                0,
+                1,
+                255
+            ],
             "rm -f _c.o"
         ]
     },
diff --git a/tools/testing/selftests/timers/.gitignore b/tools/testing/selftests/timers/.gitignore
index 2c8ac8416299..32a9eadb2d4e 100644
--- a/tools/testing/selftests/timers/.gitignore
+++ b/tools/testing/selftests/timers/.gitignore
@@ -9,7 +9,7 @@ nanosleep
 nsleep-lat
 posix_timers
 raw_skew
-rtctest
+rtcpie
 set-2038
 set-tai
 set-timer-lat
@@ -19,4 +19,3 @@ valid-adjtimex
 adjtick
 set-tz
 freq-step
-rtctest_setdate
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index 3496680981f2..c02683cfb6c9 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -5,13 +5,13 @@ LDFLAGS += -lrt -lpthread -lm
 # these are all "safe" tests that don't modify
 # system time or require escalated privileges
 TEST_GEN_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \
-	     inconsistency-check raw_skew threadtest rtctest
+	     inconsistency-check raw_skew threadtest rtcpie
 
 DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \
 		      skew_consistency clocksource-switch freq-step leap-a-day \
 		      leapcrash set-tai set-2038 set-tz
 
-TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS) rtctest_setdate
+TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS)
 
 
 include ../lib.mk
diff --git a/tools/testing/selftests/timers/rtcpie.c b/tools/testing/selftests/timers/rtcpie.c
new file mode 100644
index 000000000000..47b5bad1b393
--- /dev/null
+++ b/tools/testing/selftests/timers/rtcpie.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Real Time Clock Periodic Interrupt test program
+ *
+ * Since commit 6610e0893b8bc ("RTC: Rework RTC code to use timerqueue for
+ * events"), PIE are completely handled using hrtimers, without actually using
+ * any underlying hardware RTC.
+ *
+ */
+
+#include <stdio.h>
+#include <linux/rtc.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+
+/*
+ * This expects the new RTC class driver framework, working with
+ * clocks that will often not be clones of what the PC-AT had.
+ * Use the command line to specify another RTC if you need one.
+ */
+static const char default_rtc[] = "/dev/rtc0";
+
+int main(int argc, char **argv)
+{
+	int i, fd, retval, irqcount = 0;
+	unsigned long tmp, data, old_pie_rate;
+	const char *rtc = default_rtc;
+	struct timeval start, end, diff;
+
+	switch (argc) {
+	case 2:
+		rtc = argv[1];
+		/* FALLTHROUGH */
+	case 1:
+		break;
+	default:
+		fprintf(stderr, "usage:  rtctest [rtcdev] [d]\n");
+		return 1;
+	}
+
+	fd = open(rtc, O_RDONLY);
+
+	if (fd ==  -1) {
+		perror(rtc);
+		exit(errno);
+	}
+
+	/* Read periodic IRQ rate */
+	retval = ioctl(fd, RTC_IRQP_READ, &old_pie_rate);
+	if (retval == -1) {
+		/* not all RTCs support periodic IRQs */
+		if (errno == EINVAL) {
+			fprintf(stderr, "\nNo periodic IRQ support\n");
+			goto done;
+		}
+		perror("RTC_IRQP_READ ioctl");
+		exit(errno);
+	}
+	fprintf(stderr, "\nPeriodic IRQ rate is %ldHz.\n", old_pie_rate);
+
+	fprintf(stderr, "Counting 20 interrupts at:");
+	fflush(stderr);
+
+	/* The frequencies 128Hz, 256Hz, ... 8192Hz are only allowed for root. */
+	for (tmp=2; tmp<=64; tmp*=2) {
+
+		retval = ioctl(fd, RTC_IRQP_SET, tmp);
+		if (retval == -1) {
+			/* not all RTCs can change their periodic IRQ rate */
+			if (errno == EINVAL) {
+				fprintf(stderr,
+					"\n...Periodic IRQ rate is fixed\n");
+				goto done;
+			}
+			perror("RTC_IRQP_SET ioctl");
+			exit(errno);
+		}
+
+		fprintf(stderr, "\n%ldHz:\t", tmp);
+		fflush(stderr);
+
+		/* Enable periodic interrupts */
+		retval = ioctl(fd, RTC_PIE_ON, 0);
+		if (retval == -1) {
+			perror("RTC_PIE_ON ioctl");
+			exit(errno);
+		}
+
+		for (i=1; i<21; i++) {
+			gettimeofday(&start, NULL);
+			/* This blocks */
+			retval = read(fd, &data, sizeof(unsigned long));
+			if (retval == -1) {
+				perror("read");
+				exit(errno);
+			}
+			gettimeofday(&end, NULL);
+			timersub(&end, &start, &diff);
+			if (diff.tv_sec > 0 ||
+			    diff.tv_usec > ((1000000L / tmp) * 1.10)) {
+				fprintf(stderr, "\nPIE delta error: %ld.%06ld should be close to 0.%06ld\n",
+				       diff.tv_sec, diff.tv_usec,
+				       (1000000L / tmp));
+				fflush(stdout);
+				exit(-1);
+			}
+
+			fprintf(stderr, " %d",i);
+			fflush(stderr);
+			irqcount++;
+		}
+
+		/* Disable periodic interrupts */
+		retval = ioctl(fd, RTC_PIE_OFF, 0);
+		if (retval == -1) {
+			perror("RTC_PIE_OFF ioctl");
+			exit(errno);
+		}
+	}
+
+done:
+	ioctl(fd, RTC_IRQP_SET, old_pie_rate);
+
+	fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n");
+
+	close(fd);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c
deleted file mode 100644
index 411eff625e66..000000000000
--- a/tools/testing/selftests/timers/rtctest.c
+++ /dev/null
@@ -1,403 +0,0 @@
-/*
- *      Real Time Clock Driver Test/Example Program
- *
- *      Compile with:
- *		     gcc -s -Wall -Wstrict-prototypes rtctest.c -o rtctest
- *
- *      Copyright (C) 1996, Paul Gortmaker.
- *
- *      Released under the GNU General Public License, version 2,
- *      included herein by reference.
- *
- */
-
-#include <stdio.h>
-#include <linux/rtc.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
-#include <sys/types.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <errno.h>
-
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
-/*
- * This expects the new RTC class driver framework, working with
- * clocks that will often not be clones of what the PC-AT had.
- * Use the command line to specify another RTC if you need one.
- */
-static const char default_rtc[] = "/dev/rtc0";
-
-static struct rtc_time cutoff_dates[] = {
-	{
-		.tm_year = 70, /* 1970 -1900 */
-		.tm_mday = 1,
-	},
-	/* signed time_t 19/01/2038 3:14:08 */
-	{
-		.tm_year = 138,
-		.tm_mday = 19,
-	},
-	{
-		.tm_year = 138,
-		.tm_mday = 20,
-	},
-	{
-		.tm_year = 199, /* 2099 -1900 */
-		.tm_mday = 1,
-	},
-	{
-		.tm_year = 200, /* 2100 -1900 */
-		.tm_mday = 1,
-	},
-	/* unsigned time_t 07/02/2106 7:28:15*/
-	{
-		.tm_year = 205,
-		.tm_mon = 1,
-		.tm_mday = 7,
-	},
-	{
-		.tm_year = 206,
-		.tm_mon = 1,
-		.tm_mday = 8,
-	},
-	/* signed time on 64bit in nanoseconds 12/04/2262 01:47:16*/
-	{
-		.tm_year = 362,
-		.tm_mon = 3,
-		.tm_mday = 12,
-	},
-	{
-		.tm_year = 362, /* 2262 -1900 */
-		.tm_mon = 3,
-		.tm_mday = 13,
-	},
-};
-
-static int compare_dates(struct rtc_time *a, struct rtc_time *b)
-{
-	if (a->tm_year != b->tm_year ||
-	    a->tm_mon != b->tm_mon ||
-	    a->tm_mday != b->tm_mday ||
-	    a->tm_hour != b->tm_hour ||
-	    a->tm_min != b->tm_min ||
-	    ((b->tm_sec - a->tm_sec) > 1))
-		return 1;
-
-	return 0;
-}
-
-int main(int argc, char **argv)
-{
-	int i, fd, retval, irqcount = 0, dangerous = 0;
-	unsigned long tmp, data;
-	struct rtc_time rtc_tm;
-	const char *rtc = default_rtc;
-	struct timeval start, end, diff;
-
-	switch (argc) {
-	case 3:
-		if (*argv[2] == 'd')
-			dangerous = 1;
-	case 2:
-		rtc = argv[1];
-		/* FALLTHROUGH */
-	case 1:
-		break;
-	default:
-		fprintf(stderr, "usage:  rtctest [rtcdev] [d]\n");
-		return 1;
-	}
-
-	fd = open(rtc, O_RDONLY);
-
-	if (fd ==  -1) {
-		perror(rtc);
-		exit(errno);
-	}
-
-	fprintf(stderr, "\n\t\t\tRTC Driver Test Example.\n\n");
-
-	/* Turn on update interrupts (one per second) */
-	retval = ioctl(fd, RTC_UIE_ON, 0);
-	if (retval == -1) {
-		if (errno == EINVAL) {
-			fprintf(stderr,
-				"\n...Update IRQs not supported.\n");
-			goto test_READ;
-		}
-		perror("RTC_UIE_ON ioctl");
-		exit(errno);
-	}
-
-	fprintf(stderr, "Counting 5 update (1/sec) interrupts from reading %s:",
-			rtc);
-	fflush(stderr);
-	for (i=1; i<6; i++) {
-		/* This read will block */
-		retval = read(fd, &data, sizeof(unsigned long));
-		if (retval == -1) {
-			perror("read");
-			exit(errno);
-		}
-		fprintf(stderr, " %d",i);
-		fflush(stderr);
-		irqcount++;
-	}
-
-	fprintf(stderr, "\nAgain, from using select(2) on /dev/rtc:");
-	fflush(stderr);
-	for (i=1; i<6; i++) {
-		struct timeval tv = {5, 0};     /* 5 second timeout on select */
-		fd_set readfds;
-
-		FD_ZERO(&readfds);
-		FD_SET(fd, &readfds);
-		/* The select will wait until an RTC interrupt happens. */
-		retval = select(fd+1, &readfds, NULL, NULL, &tv);
-		if (retval == -1) {
-		        perror("select");
-		        exit(errno);
-		}
-		/* This read won't block unlike the select-less case above. */
-		retval = read(fd, &data, sizeof(unsigned long));
-		if (retval == -1) {
-		        perror("read");
-		        exit(errno);
-		}
-		fprintf(stderr, " %d",i);
-		fflush(stderr);
-		irqcount++;
-	}
-
-	/* Turn off update interrupts */
-	retval = ioctl(fd, RTC_UIE_OFF, 0);
-	if (retval == -1) {
-		perror("RTC_UIE_OFF ioctl");
-		exit(errno);
-	}
-
-test_READ:
-	/* Read the RTC time/date */
-	retval = ioctl(fd, RTC_RD_TIME, &rtc_tm);
-	if (retval == -1) {
-		perror("RTC_RD_TIME ioctl");
-		exit(errno);
-	}
-
-	fprintf(stderr, "\n\nCurrent RTC date/time is %d-%d-%d, %02d:%02d:%02d.\n",
-		rtc_tm.tm_mday, rtc_tm.tm_mon + 1, rtc_tm.tm_year + 1900,
-		rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec);
-
-	/* Set the alarm to 5 sec in the future, and check for rollover */
-	rtc_tm.tm_sec += 5;
-	if (rtc_tm.tm_sec >= 60) {
-		rtc_tm.tm_sec %= 60;
-		rtc_tm.tm_min++;
-	}
-	if (rtc_tm.tm_min == 60) {
-		rtc_tm.tm_min = 0;
-		rtc_tm.tm_hour++;
-	}
-	if (rtc_tm.tm_hour == 24)
-		rtc_tm.tm_hour = 0;
-
-	retval = ioctl(fd, RTC_ALM_SET, &rtc_tm);
-	if (retval == -1) {
-		if (errno == EINVAL) {
-			fprintf(stderr,
-				"\n...Alarm IRQs not supported.\n");
-			goto test_PIE;
-		}
-
-		perror("RTC_ALM_SET ioctl");
-		exit(errno);
-	}
-
-	/* Read the current alarm settings */
-	retval = ioctl(fd, RTC_ALM_READ, &rtc_tm);
-	if (retval == -1) {
-		if (errno == EINVAL) {
-			fprintf(stderr,
-					"\n...EINVAL reading current alarm setting.\n");
-			goto test_PIE;
-		}
-		perror("RTC_ALM_READ ioctl");
-		exit(errno);
-	}
-
-	fprintf(stderr, "Alarm time now set to %02d:%02d:%02d.\n",
-		rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec);
-
-	/* Enable alarm interrupts */
-	retval = ioctl(fd, RTC_AIE_ON, 0);
-	if (retval == -1) {
-		if (errno == EINVAL || errno == EIO) {
-			fprintf(stderr,
-				"\n...Alarm IRQs not supported.\n");
-			goto test_PIE;
-		}
-
-		perror("RTC_AIE_ON ioctl");
-		exit(errno);
-	}
-
-	fprintf(stderr, "Waiting 5 seconds for alarm...");
-	fflush(stderr);
-	/* This blocks until the alarm ring causes an interrupt */
-	retval = read(fd, &data, sizeof(unsigned long));
-	if (retval == -1) {
-		perror("read");
-		exit(errno);
-	}
-	irqcount++;
-	fprintf(stderr, " okay. Alarm rang.\n");
-
-	/* Disable alarm interrupts */
-	retval = ioctl(fd, RTC_AIE_OFF, 0);
-	if (retval == -1) {
-		perror("RTC_AIE_OFF ioctl");
-		exit(errno);
-	}
-
-test_PIE:
-	/* Read periodic IRQ rate */
-	retval = ioctl(fd, RTC_IRQP_READ, &tmp);
-	if (retval == -1) {
-		/* not all RTCs support periodic IRQs */
-		if (errno == EINVAL) {
-			fprintf(stderr, "\nNo periodic IRQ support\n");
-			goto test_DATE;
-		}
-		perror("RTC_IRQP_READ ioctl");
-		exit(errno);
-	}
-	fprintf(stderr, "\nPeriodic IRQ rate is %ldHz.\n", tmp);
-
-	fprintf(stderr, "Counting 20 interrupts at:");
-	fflush(stderr);
-
-	/* The frequencies 128Hz, 256Hz, ... 8192Hz are only allowed for root. */
-	for (tmp=2; tmp<=64; tmp*=2) {
-
-		retval = ioctl(fd, RTC_IRQP_SET, tmp);
-		if (retval == -1) {
-			/* not all RTCs can change their periodic IRQ rate */
-			if (errno == EINVAL) {
-				fprintf(stderr,
-					"\n...Periodic IRQ rate is fixed\n");
-				goto test_DATE;
-			}
-			perror("RTC_IRQP_SET ioctl");
-			exit(errno);
-		}
-
-		fprintf(stderr, "\n%ldHz:\t", tmp);
-		fflush(stderr);
-
-		/* Enable periodic interrupts */
-		retval = ioctl(fd, RTC_PIE_ON, 0);
-		if (retval == -1) {
-			perror("RTC_PIE_ON ioctl");
-			exit(errno);
-		}
-
-		for (i=1; i<21; i++) {
-			gettimeofday(&start, NULL);
-			/* This blocks */
-			retval = read(fd, &data, sizeof(unsigned long));
-			if (retval == -1) {
-				perror("read");
-				exit(errno);
-			}
-			gettimeofday(&end, NULL);
-			timersub(&end, &start, &diff);
-			if (diff.tv_sec > 0 ||
-			    diff.tv_usec > ((1000000L / tmp) * 1.10)) {
-				fprintf(stderr, "\nPIE delta error: %ld.%06ld should be close to 0.%06ld\n",
-				       diff.tv_sec, diff.tv_usec,
-				       (1000000L / tmp));
-				fflush(stdout);
-				exit(-1);
-			}
-
-			fprintf(stderr, " %d",i);
-			fflush(stderr);
-			irqcount++;
-		}
-
-		/* Disable periodic interrupts */
-		retval = ioctl(fd, RTC_PIE_OFF, 0);
-		if (retval == -1) {
-			perror("RTC_PIE_OFF ioctl");
-			exit(errno);
-		}
-	}
-
-test_DATE:
-	if (!dangerous)
-		goto done;
-
-	fprintf(stderr, "\nTesting problematic dates\n");
-
-	for (i = 0; i < ARRAY_SIZE(cutoff_dates); i++) {
-		struct rtc_time current;
-
-		/* Write the new date in RTC */
-		retval = ioctl(fd, RTC_SET_TIME, &cutoff_dates[i]);
-		if (retval == -1) {
-			perror("RTC_SET_TIME ioctl");
-			close(fd);
-			exit(errno);
-		}
-
-		/* Read back */
-		retval = ioctl(fd, RTC_RD_TIME, &current);
-		if (retval == -1) {
-			perror("RTC_RD_TIME ioctl");
-			exit(errno);
-		}
-
-		if(compare_dates(&cutoff_dates[i], &current)) {
-			fprintf(stderr,"Setting date %d failed\n",
-			        cutoff_dates[i].tm_year + 1900);
-			goto done;
-		}
-
-		cutoff_dates[i].tm_sec += 5;
-
-		/* Write the new alarm in RTC */
-		retval = ioctl(fd, RTC_ALM_SET, &cutoff_dates[i]);
-		if (retval == -1) {
-			perror("RTC_ALM_SET ioctl");
-			close(fd);
-			exit(errno);
-		}
-
-		/* Read back */
-		retval = ioctl(fd, RTC_ALM_READ, &current);
-		if (retval == -1) {
-			perror("RTC_ALM_READ ioctl");
-			exit(errno);
-		}
-
-		if(compare_dates(&cutoff_dates[i], &current)) {
-			fprintf(stderr,"Setting alarm %d failed\n",
-			        cutoff_dates[i].tm_year + 1900);
-			goto done;
-		}
-
-		fprintf(stderr, "Setting year %d is OK \n",
-			cutoff_dates[i].tm_year + 1900);
-	}
-done:
-	fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n");
-
-	close(fd);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d744991c0f4f..186520198de7 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -8,10 +8,11 @@ include ../lib.mk
 UNAME_M := $(shell uname -m)
 CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
 CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
+CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie)
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
 			check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \
-			protection_keys test_vdso test_vsyscall
+			protection_keys test_vdso test_vsyscall mov_ss_trap
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
@@ -31,7 +32,12 @@ BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
 BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
-CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie
+CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
+
+# call32_from_64 in thunks.S uses absolute addresses.
+ifeq ($(CAN_BUILD_WITH_NOPIE),1)
+CFLAGS += -no-pie
+endif
 
 define gen-target-rule-32
 $(1) $(1)_32: $(OUTPUT)/$(1)_32
diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c
new file mode 100644
index 000000000000..3c3a022654f3
--- /dev/null
+++ b/tools/testing/selftests/x86/mov_ss_trap.c
@@ -0,0 +1,285 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mov_ss_trap.c: Exercise the bizarre side effects of a watchpoint on MOV SS
+ *
+ * This does MOV SS from a watchpointed address followed by various
+ * types of kernel entries.  A MOV SS that hits a watchpoint will queue
+ * up a #DB trap but will not actually deliver that trap.  The trap
+ * will be delivered after the next instruction instead.  The CPU's logic
+ * seems to be:
+ *
+ *  - Any fault: drop the pending #DB trap.
+ *  - INT $N, INT3, INTO, SYSCALL, SYSENTER: enter the kernel and then
+ *    deliver #DB.
+ *  - ICEBP: enter the kernel but do not deliver the watchpoint trap
+ *  - breakpoint: only one #DB is delivered (phew!)
+ *
+ * There are plenty of ways for a kernel to handle this incorrectly.  This
+ * test tries to exercise all the cases.
+ *
+ * This should mostly cover CVE-2018-1087 and CVE-2018-8897.
+ */
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <err.h>
+#include <string.h>
+#include <setjmp.h>
+#include <sys/prctl.h>
+
+#define X86_EFLAGS_RF (1UL << 16)
+
+#if __x86_64__
+# define REG_IP REG_RIP
+#else
+# define REG_IP REG_EIP
+#endif
+
+unsigned short ss;
+extern unsigned char breakpoint_insn[];
+sigjmp_buf jmpbuf;
+static unsigned char altstack_data[SIGSTKSZ];
+
+static void enable_watchpoint(void)
+{
+	pid_t parent = getpid();
+	int status;
+
+	pid_t child = fork();
+	if (child < 0)
+		err(1, "fork");
+
+	if (child) {
+		if (waitpid(child, &status, 0) != child)
+			err(1, "waitpid for child");
+	} else {
+		unsigned long dr0, dr1, dr7;
+
+		dr0 = (unsigned long)&ss;
+		dr1 = (unsigned long)breakpoint_insn;
+		dr7 = ((1UL << 1) |	/* G0 */
+		       (3UL << 16) |	/* RW0 = read or write */
+		       (1UL << 18) |	/* LEN0 = 2 bytes */
+		       (1UL << 3));	/* G1, RW1 = insn */
+
+		if (ptrace(PTRACE_ATTACH, parent, NULL, NULL) != 0)
+			err(1, "PTRACE_ATTACH");
+
+		if (waitpid(parent, &status, 0) != parent)
+			err(1, "waitpid for child");
+
+		if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[0]), dr0) != 0)
+			err(1, "PTRACE_POKEUSER DR0");
+
+		if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[1]), dr1) != 0)
+			err(1, "PTRACE_POKEUSER DR1");
+
+		if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[7]), dr7) != 0)
+			err(1, "PTRACE_POKEUSER DR7");
+
+		printf("\tDR0 = %lx, DR1 = %lx, DR7 = %lx\n", dr0, dr1, dr7);
+
+		if (ptrace(PTRACE_DETACH, parent, NULL, NULL) != 0)
+			err(1, "PTRACE_DETACH");
+
+		exit(0);
+	}
+}
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static char const * const signames[] = {
+	[SIGSEGV] = "SIGSEGV",
+	[SIGBUS] = "SIBGUS",
+	[SIGTRAP] = "SIGTRAP",
+	[SIGILL] = "SIGILL",
+};
+
+static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
+{
+	ucontext_t *ctx = ctx_void;
+
+	printf("\tGot SIGTRAP with RIP=%lx, EFLAGS.RF=%d\n",
+	       (unsigned long)ctx->uc_mcontext.gregs[REG_IP],
+	       !!(ctx->uc_mcontext.gregs[REG_EFL] & X86_EFLAGS_RF));
+}
+
+static void handle_and_return(int sig, siginfo_t *si, void *ctx_void)
+{
+	ucontext_t *ctx = ctx_void;
+
+	printf("\tGot %s with RIP=%lx\n", signames[sig],
+	       (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
+}
+
+static void handle_and_longjmp(int sig, siginfo_t *si, void *ctx_void)
+{
+	ucontext_t *ctx = ctx_void;
+
+	printf("\tGot %s with RIP=%lx\n", signames[sig],
+	       (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
+
+	siglongjmp(jmpbuf, 1);
+}
+
+int main()
+{
+	unsigned long nr;
+
+	asm volatile ("mov %%ss, %[ss]" : [ss] "=m" (ss));
+	printf("\tSS = 0x%hx, &SS = 0x%p\n", ss, &ss);
+
+	if (prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY, 0, 0, 0) == 0)
+		printf("\tPR_SET_PTRACER_ANY succeeded\n");
+
+	printf("\tSet up a watchpoint\n");
+	sethandler(SIGTRAP, sigtrap, 0);
+	enable_watchpoint();
+
+	printf("[RUN]\tRead from watched memory (should get SIGTRAP)\n");
+	asm volatile ("mov %[ss], %[tmp]" : [tmp] "=r" (nr) : [ss] "m" (ss));
+
+	printf("[RUN]\tMOV SS; INT3\n");
+	asm volatile ("mov %[ss], %%ss; int3" :: [ss] "m" (ss));
+
+	printf("[RUN]\tMOV SS; INT 3\n");
+	asm volatile ("mov %[ss], %%ss; .byte 0xcd, 0x3" :: [ss] "m" (ss));
+
+	printf("[RUN]\tMOV SS; CS CS INT3\n");
+	asm volatile ("mov %[ss], %%ss; .byte 0x2e, 0x2e; int3" :: [ss] "m" (ss));
+
+	printf("[RUN]\tMOV SS; CSx14 INT3\n");
+	asm volatile ("mov %[ss], %%ss; .fill 14,1,0x2e; int3" :: [ss] "m" (ss));
+
+	printf("[RUN]\tMOV SS; INT 4\n");
+	sethandler(SIGSEGV, handle_and_return, SA_RESETHAND);
+	asm volatile ("mov %[ss], %%ss; int $4" :: [ss] "m" (ss));
+
+#ifdef __i386__
+	printf("[RUN]\tMOV SS; INTO\n");
+	sethandler(SIGSEGV, handle_and_return, SA_RESETHAND);
+	nr = -1;
+	asm volatile ("add $1, %[tmp]; mov %[ss], %%ss; into"
+		      : [tmp] "+r" (nr) : [ss] "m" (ss));
+#endif
+
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		printf("[RUN]\tMOV SS; ICEBP\n");
+
+		/* Some emulators (e.g. QEMU TCG) don't emulate ICEBP. */
+		sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND);
+
+		asm volatile ("mov %[ss], %%ss; .byte 0xf1" :: [ss] "m" (ss));
+	}
+
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		printf("[RUN]\tMOV SS; CLI\n");
+		sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+		asm volatile ("mov %[ss], %%ss; cli" :: [ss] "m" (ss));
+	}
+
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		printf("[RUN]\tMOV SS; #PF\n");
+		sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+		asm volatile ("mov %[ss], %%ss; mov (-1), %[tmp]"
+			      : [tmp] "=r" (nr) : [ss] "m" (ss));
+	}
+
+	/*
+	 * INT $1: if #DB has DPL=3 and there isn't special handling,
+	 * then the kernel will die.
+	 */
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		printf("[RUN]\tMOV SS; INT 1\n");
+		sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+		asm volatile ("mov %[ss], %%ss; int $1" :: [ss] "m" (ss));
+	}
+
+#ifdef __x86_64__
+	/*
+	 * In principle, we should test 32-bit SYSCALL as well, but
+	 * the calling convention is so unpredictable that it's
+	 * not obviously worth the effort.
+	 */
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		printf("[RUN]\tMOV SS; SYSCALL\n");
+		sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND);
+		nr = SYS_getpid;
+		/*
+		 * Toggle the high bit of RSP to make it noncanonical to
+		 * strengthen this test on non-SMAP systems.
+		 */
+		asm volatile ("btc $63, %%rsp\n\t"
+			      "mov %[ss], %%ss; syscall\n\t"
+			      "btc $63, %%rsp"
+			      : "+a" (nr) : [ss] "m" (ss)
+			      : "rcx"
+#ifdef __x86_64__
+				, "r11"
+#endif
+			);
+	}
+#endif
+
+	printf("[RUN]\tMOV SS; breakpointed NOP\n");
+	asm volatile ("mov %[ss], %%ss; breakpoint_insn: nop" :: [ss] "m" (ss));
+
+	/*
+	 * Invoking SYSENTER directly breaks all the rules.  Just handle
+	 * the SIGSEGV.
+	 */
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		printf("[RUN]\tMOV SS; SYSENTER\n");
+		stack_t stack = {
+			.ss_sp = altstack_data,
+			.ss_size = SIGSTKSZ,
+		};
+		if (sigaltstack(&stack, NULL) != 0)
+			err(1, "sigaltstack");
+		sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND | SA_ONSTACK);
+		nr = SYS_getpid;
+		asm volatile ("mov %[ss], %%ss; SYSENTER" : "+a" (nr)
+			      : [ss] "m" (ss) : "flags", "rcx"
+#ifdef __x86_64__
+				, "r11"
+#endif
+			);
+
+		/* We're unreachable here.  SYSENTER forgets RIP. */
+	}
+
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		printf("[RUN]\tMOV SS; INT $0x80\n");
+		sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+		nr = 20;	/* compat getpid */
+		asm volatile ("mov %[ss], %%ss; int $0x80"
+			      : "+a" (nr) : [ss] "m" (ss)
+			      : "flags"
+#ifdef __x86_64__
+				, "r8", "r9", "r10", "r11"
+#endif
+			);
+	}
+
+	printf("[OK]\tI aten't dead\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c
index 9c0325e1ea68..50f7e9272481 100644
--- a/tools/testing/selftests/x86/mpx-mini-test.c
+++ b/tools/testing/selftests/x86/mpx-mini-test.c
@@ -368,6 +368,11 @@ static int expected_bnd_index = -1;
 uint64_t shadow_plb[NR_MPX_BOUNDS_REGISTERS][2]; /* shadow MPX bound registers */
 unsigned long shadow_map[NR_MPX_BOUNDS_REGISTERS];
 
+/* Failed address bound checks: */
+#ifndef SEGV_BNDERR
+# define SEGV_BNDERR	3
+#endif
+
 /*
  * The kernel is supposed to provide some information about the bounds
  * exception in the siginfo.  It should match what we have in the bounds
@@ -419,8 +424,6 @@ void handler(int signum, siginfo_t *si, void *vucontext)
 		br_count++;
 		dprintf1("#BR 0x%jx (total seen: %d)\n", status, br_count);
 
-#define SEGV_BNDERR     3  /* failed address bound checks */
-
 		dprintf2("Saw a #BR! status 0x%jx at %016lx br_reason: %jx\n",
 				status, ip, br_reason);
 		dprintf2("si_signo: %d\n", si->si_signo);
diff --git a/tools/testing/selftests/x86/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h
index b3cb7670e026..254e5436bdd9 100644
--- a/tools/testing/selftests/x86/pkey-helpers.h
+++ b/tools/testing/selftests/x86/pkey-helpers.h
@@ -26,30 +26,26 @@ static inline void sigsafe_printf(const char *format, ...)
 {
 	va_list ap;
 
-	va_start(ap, format);
 	if (!dprint_in_signal) {
+		va_start(ap, format);
 		vprintf(format, ap);
+		va_end(ap);
 	} else {
 		int ret;
-		int len = vsnprintf(dprint_in_signal_buffer,
-				    DPRINT_IN_SIGNAL_BUF_SIZE,
-				    format, ap);
 		/*
-		 * len is amount that would have been printed,
-		 * but actual write is truncated at BUF_SIZE.
+		 * No printf() functions are signal-safe.
+		 * They deadlock easily. Write the format
+		 * string to get some output, even if
+		 * incomplete.
 		 */
-		if (len > DPRINT_IN_SIGNAL_BUF_SIZE)
-			len = DPRINT_IN_SIGNAL_BUF_SIZE;
-		ret = write(1, dprint_in_signal_buffer, len);
+		ret = write(1, format, strlen(format));
 		if (ret < 0)
-			abort();
+			exit(1);
 	}
-	va_end(ap);
 }
 #define dprintf_level(level, args...) do {	\
 	if (level <= DEBUG_LEVEL)		\
 		sigsafe_printf(args);		\
-	fflush(NULL);				\
 } while (0)
 #define dprintf0(args...) dprintf_level(0, args)
 #define dprintf1(args...) dprintf_level(1, args)
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index f15aa5a76fe3..460b4bdf4c1e 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -72,10 +72,9 @@ extern void abort_hooks(void);
 				test_nr, iteration_nr);	\
 		dprintf0("errno at assert: %d", errno);	\
 		abort_hooks();			\
-		assert(condition);		\
+		exit(__LINE__);			\
 	}					\
 } while (0)
-#define raw_assert(cond) assert(cond)
 
 void cat_into_file(char *str, char *file)
 {
@@ -87,12 +86,17 @@ void cat_into_file(char *str, char *file)
 	 * these need to be raw because they are called under
 	 * pkey_assert()
 	 */
-	raw_assert(fd >= 0);
+	if (fd < 0) {
+		fprintf(stderr, "error opening '%s'\n", str);
+		perror("error: ");
+		exit(__LINE__);
+	}
+
 	ret = write(fd, str, strlen(str));
 	if (ret != strlen(str)) {
 		perror("write to file failed");
 		fprintf(stderr, "filename: '%s' str: '%s'\n", file, str);
-		raw_assert(0);
+		exit(__LINE__);
 	}
 	close(fd);
 }
@@ -191,26 +195,30 @@ void lots_o_noops_around_write(int *write_to_me)
 #ifdef __i386__
 
 #ifndef SYS_mprotect_key
-# define SYS_mprotect_key 380
+# define SYS_mprotect_key	380
 #endif
+
 #ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc	 381
-# define SYS_pkey_free	 382
+# define SYS_pkey_alloc		381
+# define SYS_pkey_free		382
 #endif
-#define REG_IP_IDX REG_EIP
-#define si_pkey_offset 0x14
+
+#define REG_IP_IDX		REG_EIP
+#define si_pkey_offset		0x14
 
 #else
 
 #ifndef SYS_mprotect_key
-# define SYS_mprotect_key 329
+# define SYS_mprotect_key	329
 #endif
+
 #ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc	 330
-# define SYS_pkey_free	 331
+# define SYS_pkey_alloc		330
+# define SYS_pkey_free		331
 #endif
-#define REG_IP_IDX REG_RIP
-#define si_pkey_offset 0x20
+
+#define REG_IP_IDX		REG_RIP
+#define si_pkey_offset		0x20
 
 #endif
 
@@ -225,8 +233,14 @@ void dump_mem(void *dumpme, int len_bytes)
 	}
 }
 
-#define SEGV_BNDERR     3  /* failed address bound checks */
-#define SEGV_PKUERR     4
+/* Failed address bound checks: */
+#ifndef SEGV_BNDERR
+# define SEGV_BNDERR		3
+#endif
+
+#ifndef SEGV_PKUERR
+# define SEGV_PKUERR		4
+#endif
 
 static char *si_code_str(int si_code)
 {
@@ -289,13 +303,6 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 		dump_mem(pkru_ptr - 128, 256);
 	pkey_assert(*pkru_ptr);
 
-	si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
-	dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
-	dump_mem(si_pkey_ptr - 8, 24);
-	siginfo_pkey = *si_pkey_ptr;
-	pkey_assert(siginfo_pkey < NR_PKEYS);
-	last_si_pkey = siginfo_pkey;
-
 	if ((si->si_code == SEGV_MAPERR) ||
 	    (si->si_code == SEGV_ACCERR) ||
 	    (si->si_code == SEGV_BNDERR)) {
@@ -303,6 +310,13 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 		exit(4);
 	}
 
+	si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
+	dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
+	dump_mem((u8 *)si_pkey_ptr - 8, 24);
+	siginfo_pkey = *si_pkey_ptr;
+	pkey_assert(siginfo_pkey < NR_PKEYS);
+	last_si_pkey = siginfo_pkey;
+
 	dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
 	/* need __rdpkru() version so we do not do shadow_pkru checking */
 	dprintf1("signal pkru from  pkru: %08x\n", __rdpkru());
@@ -311,22 +325,6 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
 	pkru_faults++;
 	dprintf1("<<<<==================================================\n");
-	return;
-	if (trapno == 14) {
-		fprintf(stderr,
-			"ERROR: In signal handler, page fault, trapno = %d, ip = %016lx\n",
-			trapno, ip);
-		fprintf(stderr, "si_addr %p\n", si->si_addr);
-		fprintf(stderr, "REG_ERR: %lx\n",
-				(unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
-		exit(1);
-	} else {
-		fprintf(stderr, "unexpected trap %d! at 0x%lx\n", trapno, ip);
-		fprintf(stderr, "si_addr %p\n", si->si_addr);
-		fprintf(stderr, "REG_ERR: %lx\n",
-				(unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
-		exit(2);
-	}
 	dprint_in_signal = 0;
 }
 
@@ -393,10 +391,15 @@ pid_t fork_lazy_child(void)
 	return forkret;
 }
 
-#define PKEY_DISABLE_ACCESS    0x1
-#define PKEY_DISABLE_WRITE     0x2
+#ifndef PKEY_DISABLE_ACCESS
+# define PKEY_DISABLE_ACCESS	0x1
+#endif
+
+#ifndef PKEY_DISABLE_WRITE
+# define PKEY_DISABLE_WRITE	0x2
+#endif
 
-u32 pkey_get(int pkey, unsigned long flags)
+static u32 hw_pkey_get(int pkey, unsigned long flags)
 {
 	u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
 	u32 pkru = __rdpkru();
@@ -418,7 +421,7 @@ u32 pkey_get(int pkey, unsigned long flags)
 	return masked_pkru;
 }
 
-int pkey_set(int pkey, unsigned long rights, unsigned long flags)
+static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
 {
 	u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
 	u32 old_pkru = __rdpkru();
@@ -452,15 +455,15 @@ void pkey_disable_set(int pkey, int flags)
 		pkey, flags);
 	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
 
-	pkey_rights = pkey_get(pkey, syscall_flags);
+	pkey_rights = hw_pkey_get(pkey, syscall_flags);
 
-	dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
 			pkey, pkey, pkey_rights);
 	pkey_assert(pkey_rights >= 0);
 
 	pkey_rights |= flags;
 
-	ret = pkey_set(pkey, pkey_rights, syscall_flags);
+	ret = hw_pkey_set(pkey, pkey_rights, syscall_flags);
 	assert(!ret);
 	/*pkru and flags have the same format */
 	shadow_pkru |= flags << (pkey * 2);
@@ -468,8 +471,8 @@ void pkey_disable_set(int pkey, int flags)
 
 	pkey_assert(ret >= 0);
 
-	pkey_rights = pkey_get(pkey, syscall_flags);
-	dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+	pkey_rights = hw_pkey_get(pkey, syscall_flags);
+	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
 			pkey, pkey, pkey_rights);
 
 	dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
@@ -483,24 +486,24 @@ void pkey_disable_clear(int pkey, int flags)
 {
 	unsigned long syscall_flags = 0;
 	int ret;
-	int pkey_rights = pkey_get(pkey, syscall_flags);
+	int pkey_rights = hw_pkey_get(pkey, syscall_flags);
 	u32 orig_pkru = rdpkru();
 
 	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
 
-	dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
 			pkey, pkey, pkey_rights);
 	pkey_assert(pkey_rights >= 0);
 
 	pkey_rights |= flags;
 
-	ret = pkey_set(pkey, pkey_rights, 0);
+	ret = hw_pkey_set(pkey, pkey_rights, 0);
 	/* pkru and flags have the same format */
 	shadow_pkru &= ~(flags << (pkey * 2));
 	pkey_assert(ret >= 0);
 
-	pkey_rights = pkey_get(pkey, syscall_flags);
-	dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+	pkey_rights = hw_pkey_get(pkey, syscall_flags);
+	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
 			pkey, pkey, pkey_rights);
 
 	dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
@@ -674,10 +677,12 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
 struct pkey_malloc_record {
 	void *ptr;
 	long size;
+	int prot;
 };
 struct pkey_malloc_record *pkey_malloc_records;
+struct pkey_malloc_record *pkey_last_malloc_record;
 long nr_pkey_malloc_records;
-void record_pkey_malloc(void *ptr, long size)
+void record_pkey_malloc(void *ptr, long size, int prot)
 {
 	long i;
 	struct pkey_malloc_record *rec = NULL;
@@ -709,6 +714,8 @@ void record_pkey_malloc(void *ptr, long size)
 		(int)(rec - pkey_malloc_records), rec, ptr, size);
 	rec->ptr = ptr;
 	rec->size = size;
+	rec->prot = prot;
+	pkey_last_malloc_record = rec;
 	nr_pkey_malloc_records++;
 }
 
@@ -753,7 +760,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
 	pkey_assert(ptr != (void *)-1);
 	ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey);
 	pkey_assert(!ret);
-	record_pkey_malloc(ptr, size);
+	record_pkey_malloc(ptr, size, prot);
 	rdpkru();
 
 	dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr);
@@ -774,7 +781,7 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
 	size = ALIGN_UP(size, HPAGE_SIZE * 2);
 	ptr = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
 	pkey_assert(ptr != (void *)-1);
-	record_pkey_malloc(ptr, size);
+	record_pkey_malloc(ptr, size, prot);
 	mprotect_pkey(ptr, size, prot, pkey);
 
 	dprintf1("unaligned ptr: %p\n", ptr);
@@ -847,7 +854,7 @@ void *malloc_pkey_hugetlb(long size, int prot, u16 pkey)
 	pkey_assert(ptr != (void *)-1);
 	mprotect_pkey(ptr, size, prot, pkey);
 
-	record_pkey_malloc(ptr, size);
+	record_pkey_malloc(ptr, size, prot);
 
 	dprintf1("mmap()'d hugetlbfs for pkey %d @ %p\n", pkey, ptr);
 	return ptr;
@@ -869,7 +876,7 @@ void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey)
 
 	mprotect_pkey(ptr, size, prot, pkey);
 
-	record_pkey_malloc(ptr, size);
+	record_pkey_malloc(ptr, size, prot);
 
 	dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr);
 	close(fd);
@@ -918,13 +925,21 @@ void *malloc_pkey(long size, int prot, u16 pkey)
 }
 
 int last_pkru_faults;
+#define UNKNOWN_PKEY -2
 void expected_pk_fault(int pkey)
 {
 	dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n",
 			__func__, last_pkru_faults, pkru_faults);
 	dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey);
 	pkey_assert(last_pkru_faults + 1 == pkru_faults);
-	pkey_assert(last_si_pkey == pkey);
+
+       /*
+	* For exec-only memory, we do not know the pkey in
+	* advance, so skip this check.
+	*/
+	if (pkey != UNKNOWN_PKEY)
+		pkey_assert(last_si_pkey == pkey);
+
 	/*
 	 * The signal handler shold have cleared out PKRU to let the
 	 * test program continue.  We now have to restore it.
@@ -939,10 +954,11 @@ void expected_pk_fault(int pkey)
 	last_si_pkey = -1;
 }
 
-void do_not_expect_pk_fault(void)
-{
-	pkey_assert(last_pkru_faults == pkru_faults);
-}
+#define do_not_expect_pk_fault(msg)	do {			\
+	if (last_pkru_faults != pkru_faults)			\
+		dprintf0("unexpected PK fault: %s\n", msg);	\
+	pkey_assert(last_pkru_faults == pkru_faults);		\
+} while (0)
 
 int test_fds[10] = { -1 };
 int nr_test_fds;
@@ -1151,12 +1167,15 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 	pkey_assert(i < NR_PKEYS*2);
 
 	/*
-	 * There are 16 pkeys supported in hardware.  One is taken
-	 * up for the default (0) and another can be taken up by
-	 * an execute-only mapping.  Ensure that we can allocate
-	 * at least 14 (16-2).
+	 * There are 16 pkeys supported in hardware.  Three are
+	 * allocated by the time we get here:
+	 *   1. The default key (0)
+	 *   2. One possibly consumed by an execute-only mapping.
+	 *   3. One allocated by the test code and passed in via
+	 *      'pkey' to this function.
+	 * Ensure that we can allocate at least another 13 (16-3).
 	 */
-	pkey_assert(i >= NR_PKEYS-2);
+	pkey_assert(i >= NR_PKEYS-3);
 
 	for (i = 0; i < nr_allocated_pkeys; i++) {
 		err = sys_pkey_free(allocated_pkeys[i]);
@@ -1165,6 +1184,35 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 	}
 }
 
+/*
+ * pkey 0 is special.  It is allocated by default, so you do not
+ * have to call pkey_alloc() to use it first.  Make sure that it
+ * is usable.
+ */
+void test_mprotect_with_pkey_0(int *ptr, u16 pkey)
+{
+	long size;
+	int prot;
+
+	assert(pkey_last_malloc_record);
+	size = pkey_last_malloc_record->size;
+	/*
+	 * This is a bit of a hack.  But mprotect() requires
+	 * huge-page-aligned sizes when operating on hugetlbfs.
+	 * So, make sure that we use something that's a multiple
+	 * of a huge page when we can.
+	 */
+	if (size >= HPAGE_SIZE)
+		size = HPAGE_SIZE;
+	prot = pkey_last_malloc_record->prot;
+
+	/* Use pkey 0 */
+	mprotect_pkey(ptr, size, prot, 0);
+
+	/* Make sure that we can set it back to the original pkey. */
+	mprotect_pkey(ptr, size, prot, pkey);
+}
+
 void test_ptrace_of_child(int *ptr, u16 pkey)
 {
 	__attribute__((__unused__)) int peek_result;
@@ -1228,7 +1276,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
 	pkey_assert(ret != -1);
 	/* Now access from the current task, and expect NO exception: */
 	peek_result = read_ptr(plain_ptr);
-	do_not_expect_pk_fault();
+	do_not_expect_pk_fault("read plain pointer after ptrace");
 
 	ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0);
 	pkey_assert(ret != -1);
@@ -1241,12 +1289,9 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
 	free(plain_ptr_unaligned);
 }
 
-void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+void *get_pointer_to_instructions(void)
 {
 	void *p1;
-	int scratch;
-	int ptr_contents;
-	int ret;
 
 	p1 = ALIGN_PTR_UP(&lots_o_noops_around_write, PAGE_SIZE);
 	dprintf3("&lots_o_noops: %p\n", &lots_o_noops_around_write);
@@ -1256,7 +1301,23 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
 	/* Point 'p1' at the *second* page of the function: */
 	p1 += PAGE_SIZE;
 
+	/*
+	 * Try to ensure we fault this in on next touch to ensure
+	 * we get an instruction fault as opposed to a data one
+	 */
 	madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+
+	return p1;
+}
+
+void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+{
+	void *p1;
+	int scratch;
+	int ptr_contents;
+	int ret;
+
+	p1 = get_pointer_to_instructions();
 	lots_o_noops_around_write(&scratch);
 	ptr_contents = read_ptr(p1);
 	dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
@@ -1272,12 +1333,55 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
 	 */
 	madvise(p1, PAGE_SIZE, MADV_DONTNEED);
 	lots_o_noops_around_write(&scratch);
-	do_not_expect_pk_fault();
+	do_not_expect_pk_fault("executing on PROT_EXEC memory");
 	ptr_contents = read_ptr(p1);
 	dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
 	expected_pk_fault(pkey);
 }
 
+void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
+{
+	void *p1;
+	int scratch;
+	int ptr_contents;
+	int ret;
+
+	dprintf1("%s() start\n", __func__);
+
+	p1 = get_pointer_to_instructions();
+	lots_o_noops_around_write(&scratch);
+	ptr_contents = read_ptr(p1);
+	dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+
+	/* Use a *normal* mprotect(), not mprotect_pkey(): */
+	ret = mprotect(p1, PAGE_SIZE, PROT_EXEC);
+	pkey_assert(!ret);
+
+	dprintf2("pkru: %x\n", rdpkru());
+
+	/* Make sure this is an *instruction* fault */
+	madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+	lots_o_noops_around_write(&scratch);
+	do_not_expect_pk_fault("executing on PROT_EXEC memory");
+	ptr_contents = read_ptr(p1);
+	dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+	expected_pk_fault(UNKNOWN_PKEY);
+
+	/*
+	 * Put the memory back to non-PROT_EXEC.  Should clear the
+	 * exec-only pkey off the VMA and allow it to be readable
+	 * again.  Go to PROT_NONE first to check for a kernel bug
+	 * that did not clear the pkey when doing PROT_NONE.
+	 */
+	ret = mprotect(p1, PAGE_SIZE, PROT_NONE);
+	pkey_assert(!ret);
+
+	ret = mprotect(p1, PAGE_SIZE, PROT_READ|PROT_EXEC);
+	pkey_assert(!ret);
+	ptr_contents = read_ptr(p1);
+	do_not_expect_pk_fault("plain read on recently PROT_EXEC area");
+}
+
 void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
 {
 	int size = PAGE_SIZE;
@@ -1302,6 +1406,8 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = {
 	test_kernel_gup_of_access_disabled_region,
 	test_kernel_gup_write_to_write_disabled_region,
 	test_executing_on_unreadable_memory,
+	test_implicit_mprotect_exec_only_memory,
+	test_mprotect_with_pkey_0,
 	test_ptrace_of_child,
 	test_pkey_syscalls_on_non_allocated_pkey,
 	test_pkey_syscalls_bad_args,
diff --git a/tools/testing/selftests/x86/test_syscall_vdso.c b/tools/testing/selftests/x86/test_syscall_vdso.c
index 40370354d4c1..c9c3281077bc 100644
--- a/tools/testing/selftests/x86/test_syscall_vdso.c
+++ b/tools/testing/selftests/x86/test_syscall_vdso.c
@@ -100,12 +100,19 @@ asm (
 	"	shl	$32, %r8\n"
 	"	orq	$0x7f7f7f7f, %r8\n"
 	"	movq	%r8, %r9\n"
-	"	movq	%r8, %r10\n"
-	"	movq	%r8, %r11\n"
-	"	movq	%r8, %r12\n"
-	"	movq	%r8, %r13\n"
-	"	movq	%r8, %r14\n"
-	"	movq	%r8, %r15\n"
+	"	incq	%r9\n"
+	"	movq	%r9, %r10\n"
+	"	incq	%r10\n"
+	"	movq	%r10, %r11\n"
+	"	incq	%r11\n"
+	"	movq	%r11, %r12\n"
+	"	incq	%r12\n"
+	"	movq	%r12, %r13\n"
+	"	incq	%r13\n"
+	"	movq	%r13, %r14\n"
+	"	incq	%r14\n"
+	"	movq	%r14, %r15\n"
+	"	incq	%r15\n"
 	"	ret\n"
 	"	.code32\n"
 	"	.popsection\n"
@@ -128,12 +135,13 @@ int check_regs64(void)
 	int err = 0;
 	int num = 8;
 	uint64_t *r64 = &regs64.r8;
+	uint64_t expected = 0x7f7f7f7f7f7f7f7fULL;
 
 	if (!kernel_is_64bit)
 		return 0;
 
 	do {
-		if (*r64 == 0x7f7f7f7f7f7f7f7fULL)
+		if (*r64 == expected++)
 			continue; /* register did not change */
 		if (syscall_addr != (long)&int80) {
 			/*
@@ -147,18 +155,17 @@ int check_regs64(void)
 				continue;
 			}
 		} else {
-			/* INT80 syscall entrypoint can be used by
+			/*
+			 * INT80 syscall entrypoint can be used by
 			 * 64-bit programs too, unlike SYSCALL/SYSENTER.
 			 * Therefore it must preserve R12+
 			 * (they are callee-saved registers in 64-bit C ABI).
 			 *
-			 * This was probably historically not intended,
-			 * but R8..11 are clobbered (cleared to 0).
-			 * IOW: they are the only registers which aren't
-			 * preserved across INT80 syscall.
+			 * Starting in Linux 4.17 (and any kernel that
+			 * backports the change), R8..11 are preserved.
+			 * Historically (and probably unintentionally), they
+			 * were clobbered or zeroed.
 			 */
-			if (*r64 == 0 && num <= 11)
-				continue;
 		}
 		printf("[FAIL]\tR%d has changed:%016llx\n", num, *r64);
 		err++;
diff --git a/tools/testing/selftests/x86/trivial_program.c b/tools/testing/selftests/x86/trivial_program.c
new file mode 100644
index 000000000000..46a447163b93
--- /dev/null
+++ b/tools/testing/selftests/x86/trivial_program.c
@@ -0,0 +1,10 @@
+/* Trivial program to check that compilation with certain flags is working. */
+
+#include <stdio.h>
+
+int
+main(void)
+{
+	puts("");
+	return 0;
+}
diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c
index c9c81614a66a..4204359c9fee 100644
--- a/tools/usb/usbip/libsrc/vhci_driver.c
+++ b/tools/usb/usbip/libsrc/vhci_driver.c
@@ -135,11 +135,11 @@ static int refresh_imported_device_list(void)
 	return 0;
 }
 
-static int get_nports(void)
+static int get_nports(struct udev_device *hc_device)
 {
 	const char *attr_nports;
 
-	attr_nports = udev_device_get_sysattr_value(vhci_driver->hc_device, "nports");
+	attr_nports = udev_device_get_sysattr_value(hc_device, "nports");
 	if (!attr_nports) {
 		err("udev_device_get_sysattr_value nports failed");
 		return -1;
@@ -242,35 +242,41 @@ static int read_record(int rhport, char *host, unsigned long host_len,
 
 int usbip_vhci_driver_open(void)
 {
+	int nports;
+	struct udev_device *hc_device;
+
 	udev_context = udev_new();
 	if (!udev_context) {
 		err("udev_new failed");
 		return -1;
 	}
 
-	vhci_driver = calloc(1, sizeof(struct usbip_vhci_driver));
-
 	/* will be freed in usbip_driver_close() */
-	vhci_driver->hc_device =
+	hc_device =
 		udev_device_new_from_subsystem_sysname(udev_context,
 						       USBIP_VHCI_BUS_TYPE,
 						       USBIP_VHCI_DEVICE_NAME);
-	if (!vhci_driver->hc_device) {
+	if (!hc_device) {
 		err("udev_device_new_from_subsystem_sysname failed");
 		goto err;
 	}
 
-	vhci_driver->nports = get_nports();
-	dbg("available ports: %d", vhci_driver->nports);
-
-	if (vhci_driver->nports <= 0) {
+	nports = get_nports(hc_device);
+	if (nports <= 0) {
 		err("no available ports");
 		goto err;
-	} else if (vhci_driver->nports > MAXNPORT) {
-		err("port number exceeds %d", MAXNPORT);
+	}
+	dbg("available ports: %d", nports);
+
+	vhci_driver = calloc(1, sizeof(struct usbip_vhci_driver) +
+			nports * sizeof(struct usbip_imported_device));
+	if (!vhci_driver) {
+		err("vhci_driver allocation failed");
 		goto err;
 	}
 
+	vhci_driver->nports = nports;
+	vhci_driver->hc_device = hc_device;
 	vhci_driver->ncontrollers = get_ncontrollers();
 	dbg("available controllers: %d", vhci_driver->ncontrollers);
 
@@ -285,7 +291,7 @@ int usbip_vhci_driver_open(void)
 	return 0;
 
 err:
-	udev_device_unref(vhci_driver->hc_device);
+	udev_device_unref(hc_device);
 
 	if (vhci_driver)
 		free(vhci_driver);
diff --git a/tools/usb/usbip/libsrc/vhci_driver.h b/tools/usb/usbip/libsrc/vhci_driver.h
index 418b404d5121..6c9aca216705 100644
--- a/tools/usb/usbip/libsrc/vhci_driver.h
+++ b/tools/usb/usbip/libsrc/vhci_driver.h
@@ -13,7 +13,6 @@
 
 #define USBIP_VHCI_BUS_TYPE "platform"
 #define USBIP_VHCI_DEVICE_NAME "vhci_hcd.0"
-#define MAXNPORT 128
 
 enum hub_speed {
 	HUB_SPEED_HIGH = 0,
@@ -41,7 +40,7 @@ struct usbip_vhci_driver {
 
 	int ncontrollers;
 	int nports;
-	struct usbip_imported_device idev[MAXNPORT];
+	struct usbip_imported_device idev[];
 };
 
 
diff --git a/tools/usb/usbip/src/usbip_detach.c b/tools/usb/usbip/src/usbip_detach.c
index 9db9d21bb2ec..777f7286a0c5 100644
--- a/tools/usb/usbip/src/usbip_detach.c
+++ b/tools/usb/usbip/src/usbip_detach.c
@@ -43,9 +43,12 @@ void usbip_detach_usage(void)
 
 static int detach_port(char *port)
 {
-	int ret;
+	int ret = 0;
 	uint8_t portnum;
 	char path[PATH_MAX+1];
+	int i;
+	struct usbip_imported_device *idev;
+	int found = 0;
 
 	unsigned int port_len = strlen(port);
 
@@ -55,27 +58,48 @@ static int detach_port(char *port)
 			return -1;
 		}
 
-	/* check max port */
-
 	portnum = atoi(port);
 
-	/* remove the port state file */
+	ret = usbip_vhci_driver_open();
+	if (ret < 0) {
+		err("open vhci_driver");
+		return -1;
+	}
+
+	/* check for invalid port */
+	for (i = 0; i < vhci_driver->nports; i++) {
+		idev = &vhci_driver->idev[i];
+
+		if (idev->port == portnum) {
+			found = 1;
+			if (idev->status != VDEV_ST_NULL)
+				break;
+			info("Port %d is already detached!\n", idev->port);
+			goto call_driver_close;
+		}
+	}
 
+	if (!found) {
+		err("Invalid port %s > maxports %d",
+			port, vhci_driver->nports);
+		goto call_driver_close;
+	}
+
+	/* remove the port state file */
 	snprintf(path, PATH_MAX, VHCI_STATE_PATH"/port%d", portnum);
 
 	remove(path);
 	rmdir(VHCI_STATE_PATH);
 
-	ret = usbip_vhci_driver_open();
+	ret = usbip_vhci_detach_device(portnum);
 	if (ret < 0) {
-		err("open vhci_driver");
-		return -1;
+		ret = -1;
+		err("Port %d detach request failed!\n", portnum);
+		goto call_driver_close;
 	}
+	info("Port %d is now detached!\n", portnum);
 
-	ret = usbip_vhci_detach_device(portnum);
-	if (ret < 0)
-		return -1;
-
+call_driver_close:
 	usbip_vhci_driver_close();
 
 	return ret;
diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h
index 1571e24e9494..f91aeb5fe571 100644
--- a/tools/virtio/linux/dma-mapping.h
+++ b/tools/virtio/linux/dma-mapping.h
@@ -6,8 +6,6 @@
 # error Virtio userspace code does not support CONFIG_HAS_DMA
 #endif
 
-#define PCI_DMA_BUS_IS_PHYS 1
-
 enum dma_data_direction {
 	DMA_BIDIRECTIONAL = 0,
 	DMA_TO_DEVICE = 1,
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index dba629c5f8ac..a4c1b76240df 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
 static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
 static u32 kvm_next_vmid;
 static unsigned int kvm_vmid_bits __read_mostly;
-static DEFINE_SPINLOCK(kvm_vmid_lock);
+static DEFINE_RWLOCK(kvm_vmid_lock);
 
 static bool vgic_present;
 
@@ -473,11 +473,16 @@ static void update_vttbr(struct kvm *kvm)
 {
 	phys_addr_t pgd_phys;
 	u64 vmid;
+	bool new_gen;
 
-	if (!need_new_vmid_gen(kvm))
+	read_lock(&kvm_vmid_lock);
+	new_gen = need_new_vmid_gen(kvm);
+	read_unlock(&kvm_vmid_lock);
+
+	if (!new_gen)
 		return;
 
-	spin_lock(&kvm_vmid_lock);
+	write_lock(&kvm_vmid_lock);
 
 	/*
 	 * We need to re-check the vmid_gen here to ensure that if another vcpu
@@ -485,7 +490,7 @@ static void update_vttbr(struct kvm *kvm)
 	 * use the same vmid.
 	 */
 	if (!need_new_vmid_gen(kvm)) {
-		spin_unlock(&kvm_vmid_lock);
+		write_unlock(&kvm_vmid_lock);
 		return;
 	}
 
@@ -519,7 +524,7 @@ static void update_vttbr(struct kvm *kvm)
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
 	kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid;
 
-	spin_unlock(&kvm_vmid_lock);
+	write_unlock(&kvm_vmid_lock);
 }
 
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 7f6a944db23d..8d90de213ce9 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1401,6 +1401,7 @@ static void kvm_send_hwpoison_signal(unsigned long address,
 {
 	siginfo_t info;
 
+	clear_siginfo(&info);
 	info.si_signo   = SIGBUS;
 	info.si_errno   = 0;
 	info.si_code    = BUS_MCEERR_AR;
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index 6919352cbf15..c4762bef13c6 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -18,6 +18,7 @@
 #include <linux/arm-smccc.h>
 #include <linux/preempt.h>
 #include <linux/kvm_host.h>
+#include <linux/uaccess.h>
 #include <linux/wait.h>
 
 #include <asm/cputype.h>
@@ -427,3 +428,62 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 	smccc_set_retval(vcpu, val, 0, 0, 0);
 	return 1;
 }
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
+{
+	return 1;		/* PSCI version */
+}
+
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices))
+		return -EFAULT;
+
+	return 0;
+}
+
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
+		void __user *uaddr = (void __user *)(long)reg->addr;
+		u64 val;
+
+		val = kvm_psci_version(vcpu, vcpu->kvm);
+		if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
+			return -EFAULT;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
+		void __user *uaddr = (void __user *)(long)reg->addr;
+		bool wants_02;
+		u64 val;
+
+		if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
+			return -EFAULT;
+
+		wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
+
+		switch (val) {
+		case KVM_ARM_PSCI_0_1:
+			if (wants_02)
+				return -EINVAL;
+			vcpu->kvm->arch.psci_version = val;
+			return 0;
+		case KVM_ARM_PSCI_0_2:
+		case KVM_ARM_PSCI_1_0:
+			if (!wants_02)
+				return -EINVAL;
+			vcpu->kvm->arch.psci_version = val;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c
index 10b38178cff2..4ffc0b5e6105 100644
--- a/virt/kvm/arm/vgic/vgic-debug.c
+++ b/virt/kvm/arm/vgic/vgic-debug.c
@@ -211,6 +211,7 @@ static int vgic_debug_show(struct seq_file *s, void *v)
 	struct vgic_state_iter *iter = (struct vgic_state_iter *)v;
 	struct vgic_irq *irq;
 	struct kvm_vcpu *vcpu = NULL;
+	unsigned long flags;
 
 	if (iter->dist_id == 0) {
 		print_dist_state(s, &kvm->arch.vgic);
@@ -227,9 +228,9 @@ static int vgic_debug_show(struct seq_file *s, void *v)
 		irq = &kvm->arch.vgic.spis[iter->intid - VGIC_NR_PRIVATE_IRQS];
 	}
 
-	spin_lock(&irq->irq_lock);
+	spin_lock_irqsave(&irq->irq_lock, flags);
 	print_irq_state(s, irq, vcpu);
-	spin_unlock(&irq->irq_lock);
+	spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 	return 0;
 }
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 68378fe17a0e..e07156c30323 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -423,7 +423,7 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
 	 * We cannot rely on the vgic maintenance interrupt to be
 	 * delivered synchronously. This means we can only use it to
 	 * exit the VM, and we perform the handling of EOIed
-	 * interrupts on the exit path (see vgic_process_maintenance).
+	 * interrupts on the exit path (see vgic_fold_lr_state).
 	 */
 	return IRQ_HANDLED;
 }
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index a8f07243aa9f..4ed79c939fb4 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -52,6 +52,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+	unsigned long flags;
 	int ret;
 
 	/* In this case there is no put, since we keep the reference. */
@@ -71,7 +72,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	irq->intid = intid;
 	irq->target_vcpu = vcpu;
 
-	spin_lock(&dist->lpi_list_lock);
+	spin_lock_irqsave(&dist->lpi_list_lock, flags);
 
 	/*
 	 * There could be a race with another vgic_add_lpi(), so we need to
@@ -99,7 +100,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	dist->lpi_list_count++;
 
 out_unlock:
-	spin_unlock(&dist->lpi_list_lock);
+	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	/*
 	 * We "cache" the configuration table entries in our struct vgic_irq's.
@@ -280,8 +281,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
 	int ret;
 	unsigned long flags;
 
-	ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
-			     &prop, 1);
+	ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
+				  &prop, 1);
 
 	if (ret)
 		return ret;
@@ -315,6 +316,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	struct vgic_irq *irq;
+	unsigned long flags;
 	u32 *intids;
 	int irq_count, i = 0;
 
@@ -330,7 +332,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 	if (!intids)
 		return -ENOMEM;
 
-	spin_lock(&dist->lpi_list_lock);
+	spin_lock_irqsave(&dist->lpi_list_lock, flags);
 	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
 		if (i == irq_count)
 			break;
@@ -339,7 +341,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 			continue;
 		intids[i++] = irq->intid;
 	}
-	spin_unlock(&dist->lpi_list_lock);
+	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	*intid_ptr = intids;
 	return i;
@@ -348,10 +350,11 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
 {
 	int ret = 0;
+	unsigned long flags;
 
-	spin_lock(&irq->irq_lock);
+	spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->target_vcpu = vcpu;
-	spin_unlock(&irq->irq_lock);
+	spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 	if (irq->hw) {
 		struct its_vlpi_map map;
@@ -441,8 +444,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 		 * this very same byte in the last iteration. Reuse that.
 		 */
 		if (byte_offset != last_byte_offset) {
-			ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset,
-					     &pendmask, 1);
+			ret = kvm_read_guest_lock(vcpu->kvm,
+						  pendbase + byte_offset,
+						  &pendmask, 1);
 			if (ret) {
 				kfree(intids);
 				return ret;
@@ -786,7 +790,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
 		return false;
 
 	/* Each 1st level entry is represented by a 64-bit value. */
-	if (kvm_read_guest(its->dev->kvm,
+	if (kvm_read_guest_lock(its->dev->kvm,
 			   BASER_ADDRESS(baser) + index * sizeof(indirect_ptr),
 			   &indirect_ptr, sizeof(indirect_ptr)))
 		return false;
@@ -1367,8 +1371,8 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
 	cbaser = CBASER_ADDRESS(its->cbaser);
 
 	while (its->cwriter != its->creadr) {
-		int ret = kvm_read_guest(kvm, cbaser + its->creadr,
-					 cmd_buf, ITS_CMD_SIZE);
+		int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr,
+					      cmd_buf, ITS_CMD_SIZE);
 		/*
 		 * If kvm_read_guest() fails, this could be due to the guest
 		 * programming a bogus value in CBASER or something else going
@@ -1893,7 +1897,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
 		int next_offset;
 		size_t byte_offset;
 
-		ret = kvm_read_guest(kvm, gpa, entry, esz);
+		ret = kvm_read_guest_lock(kvm, gpa, entry, esz);
 		if (ret)
 			return ret;
 
@@ -2263,7 +2267,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
 	int ret;
 
 	BUG_ON(esz > sizeof(val));
-	ret = kvm_read_guest(kvm, gpa, &val, esz);
+	ret = kvm_read_guest_lock(kvm, gpa, &val, esz);
 	if (ret)
 		return ret;
 	val = le64_to_cpu(val);
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
index e21e2f49b005..ffc587bf4742 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v2.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -14,6 +14,8 @@
 #include <linux/irqchip/arm-gic.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <linux/nospec.h>
+
 #include <kvm/iodev.h>
 #include <kvm/arm_vgic.h>
 
@@ -324,6 +326,9 @@ static unsigned long vgic_mmio_read_apr(struct kvm_vcpu *vcpu,
 
 		if (n > vgic_v3_max_apr_idx(vcpu))
 			return 0;
+
+		n = array_index_nospec(n, 4);
+
 		/* GICv3 only uses ICH_AP1Rn for memory mapped (GICv2) guests */
 		return vgicv3->vgic_ap1r[n];
 	}
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index dbe99d635c80..ff9655cfeb2f 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -289,10 +289,16 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 	       irq->vcpu->cpu != -1) /* VCPU thread is running */
 		cond_resched_lock(&irq->irq_lock);
 
-	if (irq->hw)
+	if (irq->hw) {
 		vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
-	else
+	} else {
+		u32 model = vcpu->kvm->arch.vgic.vgic_model;
+
 		irq->active = active;
+		if (model == KVM_DEV_TYPE_ARM_VGIC_V2 &&
+		    active && vgic_irq_is_sgi(irq->intid))
+			irq->active_source = requester_vcpu->vcpu_id;
+	}
 
 	if (irq->active)
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 45aa433f018f..a5f2e44f1c33 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -37,13 +37,6 @@ void vgic_v2_init_lrs(void)
 		vgic_v2_write_lr(i, 0);
 }
 
-void vgic_v2_set_npie(struct kvm_vcpu *vcpu)
-{
-	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
-
-	cpuif->vgic_hcr |= GICH_HCR_NPIE;
-}
-
 void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
@@ -71,13 +64,18 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 	int lr;
 	unsigned long flags;
 
-	cpuif->vgic_hcr &= ~(GICH_HCR_UIE | GICH_HCR_NPIE);
+	cpuif->vgic_hcr &= ~GICH_HCR_UIE;
 
 	for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
 		u32 val = cpuif->vgic_lr[lr];
-		u32 intid = val & GICH_LR_VIRTUALID;
+		u32 cpuid, intid = val & GICH_LR_VIRTUALID;
 		struct vgic_irq *irq;
 
+		/* Extract the source vCPU id from the LR */
+		cpuid = val & GICH_LR_PHYSID_CPUID;
+		cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+		cpuid &= 7;
+
 		/* Notify fds when the guest EOI'ed a level-triggered SPI */
 		if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
 			kvm_notify_acked_irq(vcpu->kvm, 0,
@@ -90,17 +88,16 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 		/* Always preserve the active bit */
 		irq->active = !!(val & GICH_LR_ACTIVE_BIT);
 
+		if (irq->active && vgic_irq_is_sgi(intid))
+			irq->active_source = cpuid;
+
 		/* Edge is the only case where we preserve the pending bit */
 		if (irq->config == VGIC_CONFIG_EDGE &&
 		    (val & GICH_LR_PENDING_BIT)) {
 			irq->pending_latch = true;
 
-			if (vgic_irq_is_sgi(intid)) {
-				u32 cpuid = val & GICH_LR_PHYSID_CPUID;
-
-				cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+			if (vgic_irq_is_sgi(intid))
 				irq->source |= (1 << cpuid);
-			}
 		}
 
 		/*
@@ -152,8 +149,15 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 	u32 val = irq->intid;
 	bool allow_pending = true;
 
-	if (irq->active)
+	if (irq->active) {
 		val |= GICH_LR_ACTIVE_BIT;
+		if (vgic_irq_is_sgi(irq->intid))
+			val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT;
+		if (vgic_irq_is_multi_sgi(irq)) {
+			allow_pending = false;
+			val |= GICH_LR_EOI;
+		}
+	}
 
 	if (irq->hw) {
 		val |= GICH_LR_HW;
@@ -190,8 +194,10 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 			BUG_ON(!src);
 			val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
 			irq->source &= ~(1 << (src - 1));
-			if (irq->source)
+			if (irq->source) {
 				irq->pending_latch = true;
+				val |= GICH_LR_EOI;
+			}
 		}
 	}
 
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 8195f52ae6f0..bdcf8e7a6161 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -27,13 +27,6 @@ static bool group1_trap;
 static bool common_trap;
 static bool gicv4_enable;
 
-void vgic_v3_set_npie(struct kvm_vcpu *vcpu)
-{
-	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
-
-	cpuif->vgic_hcr |= ICH_HCR_NPIE;
-}
-
 void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
@@ -55,17 +48,23 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 	int lr;
 	unsigned long flags;
 
-	cpuif->vgic_hcr &= ~(ICH_HCR_UIE | ICH_HCR_NPIE);
+	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
 
 	for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
 		u64 val = cpuif->vgic_lr[lr];
-		u32 intid;
+		u32 intid, cpuid;
 		struct vgic_irq *irq;
+		bool is_v2_sgi = false;
 
-		if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
+		cpuid = val & GICH_LR_PHYSID_CPUID;
+		cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+
+		if (model == KVM_DEV_TYPE_ARM_VGIC_V3) {
 			intid = val & ICH_LR_VIRTUAL_ID_MASK;
-		else
+		} else {
 			intid = val & GICH_LR_VIRTUALID;
+			is_v2_sgi = vgic_irq_is_sgi(intid);
+		}
 
 		/* Notify fds when the guest EOI'ed a level-triggered IRQ */
 		if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
@@ -81,18 +80,16 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 		/* Always preserve the active bit */
 		irq->active = !!(val & ICH_LR_ACTIVE_BIT);
 
+		if (irq->active && is_v2_sgi)
+			irq->active_source = cpuid;
+
 		/* Edge is the only case where we preserve the pending bit */
 		if (irq->config == VGIC_CONFIG_EDGE &&
 		    (val & ICH_LR_PENDING_BIT)) {
 			irq->pending_latch = true;
 
-			if (vgic_irq_is_sgi(intid) &&
-			    model == KVM_DEV_TYPE_ARM_VGIC_V2) {
-				u32 cpuid = val & GICH_LR_PHYSID_CPUID;
-
-				cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+			if (is_v2_sgi)
 				irq->source |= (1 << cpuid);
-			}
 		}
 
 		/*
@@ -133,10 +130,20 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 {
 	u32 model = vcpu->kvm->arch.vgic.vgic_model;
 	u64 val = irq->intid;
-	bool allow_pending = true;
+	bool allow_pending = true, is_v2_sgi;
 
-	if (irq->active)
+	is_v2_sgi = (vgic_irq_is_sgi(irq->intid) &&
+		     model == KVM_DEV_TYPE_ARM_VGIC_V2);
+
+	if (irq->active) {
 		val |= ICH_LR_ACTIVE_BIT;
+		if (is_v2_sgi)
+			val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT;
+		if (vgic_irq_is_multi_sgi(irq)) {
+			allow_pending = false;
+			val |= ICH_LR_EOI;
+		}
+	}
 
 	if (irq->hw) {
 		val |= ICH_LR_HW;
@@ -174,8 +181,10 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 			BUG_ON(!src);
 			val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
 			irq->source &= ~(1 << (src - 1));
-			if (irq->source)
+			if (irq->source) {
 				irq->pending_latch = true;
+				val |= ICH_LR_EOI;
+			}
 		}
 	}
 
@@ -335,7 +344,7 @@ retry:
 	bit_nr = irq->intid % BITS_PER_BYTE;
 	ptr = pendbase + byte_offset;
 
-	ret = kvm_read_guest(kvm, ptr, &val, 1);
+	ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 	if (ret)
 		return ret;
 
@@ -388,7 +397,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		ptr = pendbase + byte_offset;
 
 		if (byte_offset != last_byte_offset) {
-			ret = kvm_read_guest(kvm, ptr, &val, 1);
+			ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 			if (ret)
 				return ret;
 			last_byte_offset = byte_offset;
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index e74baec76361..33c8325c8f35 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -14,11 +14,13 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/list_sort.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
+#include <linux/nospec.h>
+
 #include <asm/kvm_hyp.h>
 
 #include "vgic.h"
@@ -41,9 +43,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
  * kvm->lock (mutex)
  *   its->cmd_lock (mutex)
  *     its->its_lock (mutex)
- *       vgic_cpu->ap_list_lock
- *         kvm->lpi_list_lock
- *           vgic_irq->irq_lock
+ *       vgic_cpu->ap_list_lock		must be taken with IRQs disabled
+ *         kvm->lpi_list_lock		must be taken with IRQs disabled
+ *           vgic_irq->irq_lock		must be taken with IRQs disabled
+ *
+ * As the ap_list_lock might be taken from the timer interrupt handler,
+ * we have to disable IRQs before taking this lock and everything lower
+ * than it.
  *
  * If you need to take multiple locks, always take the upper lock first,
  * then the lower ones, e.g. first take the its_lock, then the irq_lock.
@@ -70,8 +76,9 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct vgic_irq *irq = NULL;
+	unsigned long flags;
 
-	spin_lock(&dist->lpi_list_lock);
+	spin_lock_irqsave(&dist->lpi_list_lock, flags);
 
 	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
 		if (irq->intid != intid)
@@ -87,7 +94,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
 	irq = NULL;
 
 out_unlock:
-	spin_unlock(&dist->lpi_list_lock);
+	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	return irq;
 }
@@ -101,12 +108,16 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
 			      u32 intid)
 {
 	/* SGIs and PPIs */
-	if (intid <= VGIC_MAX_PRIVATE)
+	if (intid <= VGIC_MAX_PRIVATE) {
+		intid = array_index_nospec(intid, VGIC_MAX_PRIVATE);
 		return &vcpu->arch.vgic_cpu.private_irqs[intid];
+	}
 
 	/* SPIs */
-	if (intid <= VGIC_MAX_SPI)
+	if (intid <= VGIC_MAX_SPI) {
+		intid = array_index_nospec(intid, VGIC_MAX_SPI);
 		return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
+	}
 
 	/* LPIs */
 	if (intid >= VGIC_MIN_LPI)
@@ -128,19 +139,20 @@ static void vgic_irq_release(struct kref *ref)
 void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned long flags;
 
 	if (irq->intid < VGIC_MIN_LPI)
 		return;
 
-	spin_lock(&dist->lpi_list_lock);
+	spin_lock_irqsave(&dist->lpi_list_lock, flags);
 	if (!kref_put(&irq->refcount, vgic_irq_release)) {
-		spin_unlock(&dist->lpi_list_lock);
+		spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 		return;
 	};
 
 	list_del(&irq->lpi_list);
 	dist->lpi_list_count--;
-	spin_unlock(&dist->lpi_list_lock);
+	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	kfree(irq);
 }
@@ -594,6 +606,7 @@ retry:
 
 	list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
 		struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB;
+		bool target_vcpu_needs_kick = false;
 
 		spin_lock(&irq->irq_lock);
 
@@ -664,11 +677,18 @@ retry:
 			list_del(&irq->ap_list);
 			irq->vcpu = target_vcpu;
 			list_add_tail(&irq->ap_list, &new_cpu->ap_list_head);
+			target_vcpu_needs_kick = true;
 		}
 
 		spin_unlock(&irq->irq_lock);
 		spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock);
 		spin_unlock_irqrestore(&vcpuA->arch.vgic_cpu.ap_list_lock, flags);
+
+		if (target_vcpu_needs_kick) {
+			kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu);
+			kvm_vcpu_kick(target_vcpu);
+		}
+
 		goto retry;
 	}
 
@@ -711,14 +731,6 @@ static inline void vgic_set_underflow(struct kvm_vcpu *vcpu)
 		vgic_v3_set_underflow(vcpu);
 }
 
-static inline void vgic_set_npie(struct kvm_vcpu *vcpu)
-{
-	if (kvm_vgic_global_state.type == VGIC_V2)
-		vgic_v2_set_npie(vcpu);
-	else
-		vgic_v3_set_npie(vcpu);
-}
-
 /* Requires the ap_list_lock to be held. */
 static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
 				 bool *multi_sgi)
@@ -732,17 +744,15 @@ static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
 	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
 
 	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+		int w;
+
 		spin_lock(&irq->irq_lock);
 		/* GICv2 SGIs can count for more than one... */
-		if (vgic_irq_is_sgi(irq->intid) && irq->source) {
-			int w = hweight8(irq->source);
-
-			count += w;
-			*multi_sgi |= (w > 1);
-		} else {
-			count++;
-		}
+		w = vgic_irq_get_lr_count(irq);
 		spin_unlock(&irq->irq_lock);
+
+		count += w;
+		*multi_sgi |= (w > 1);
 	}
 	return count;
 }
@@ -753,7 +763,6 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_irq *irq;
 	int count;
-	bool npie = false;
 	bool multi_sgi;
 	u8 prio = 0xff;
 
@@ -783,10 +792,8 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 		if (likely(vgic_target_oracle(irq) == vcpu)) {
 			vgic_populate_lr(vcpu, irq, count++);
 
-			if (irq->source) {
-				npie = true;
+			if (irq->source)
 				prio = irq->priority;
-			}
 		}
 
 		spin_unlock(&irq->irq_lock);
@@ -799,9 +806,6 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	if (npie)
-		vgic_set_npie(vcpu);
-
 	vcpu->arch.vgic_cpu.used_lrs = count;
 
 	/* Nuke remaining LRs */
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 830e815748a0..32c25d42c93f 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -110,6 +110,20 @@ static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq)
 	return irq->config == VGIC_CONFIG_LEVEL && irq->hw;
 }
 
+static inline int vgic_irq_get_lr_count(struct vgic_irq *irq)
+{
+	/* Account for the active state as an interrupt */
+	if (vgic_irq_is_sgi(irq->intid) && irq->source)
+		return hweight8(irq->source) + irq->active;
+
+	return irq_is_pending(irq) || irq->active;
+}
+
+static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq)
+{
+	return vgic_irq_get_lr_count(irq) > 1;
+}
+
 /*
  * This struct provides an intermediate representation of the fields contained
  * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 6e865e8b5b10..90d30fbe95ae 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -397,7 +397,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	 * Check if there was an event already pending on the eventfd
 	 * before we registered, and trigger it as if we didn't miss it.
 	 */
-	events = f.file->f_op->poll(f.file, &irqfd->pt);
+	events = vfs_poll(f.file, &irqfd->pt);
 
 	if (events & EPOLLIN)
 		schedule_work(&irqfd->inject);